3948 files changed, 166024 insertions, 73991 deletions

diff --git a/.mailmap b/.mailmap
index bf581623ee3a..a675b6759985 100644
--- a/.mailmap
+++ b/.mailmap
@@ -18,6 +18,7 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
 Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
 Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
+Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
 Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
 Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
 Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
@@ -27,6 +28,8 @@ Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
 Andreas Herrmann <aherrman@de.ibm.com>
 Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
+Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
+Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andy Adamson <andros@citi.umich.edu>
 Antoine Tenart <antoine.tenart@free-electrons.com>
diff --git a/Documentation/ABI/testing/rtc-cdev b/Documentation/ABI/testing/rtc-cdev
index 97447283f13b..25910c3c3d7e 100644
--- a/Documentation/ABI/testing/rtc-cdev
+++ b/Documentation/ABI/testing/rtc-cdev
@@ -33,6 +33,14 @@ Description:
 		  Requires a separate RTC_PIE_ON call to enable the periodic
 		  interrupts.
 
+		* RTC_VL_READ: Read the voltage inputs status of the RTC when
+		  supported. The value is a bit field of RTC_VL_*, giving the
+		  status of the main and backup voltages.
+
+		* RTC_VL_CLEAR: Clear the voltage status of the RTC. Some RTCs
+		  need user interaction when the backup power provider is
+		  replaced or charged to be able to clear the status.
+
 		The ioctl() calls supported by the older /dev/rtc interface are
 		also supported by the newer RTC class framework. However,
 		because the chips and systems are not standardized, some PC/AT
diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index 27edc06e2495..bf3b48f022dc 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -189,7 +189,8 @@ Description:
 		Access: Read
 		Valid values: "Unknown", "Good", "Overheat", "Dead",
 			      "Over voltage", "Unspecified failure", "Cold",
-			      "Watchdog timer expire", "Safety timer expire"
+			      "Watchdog timer expire", "Safety timer expire",
+			      "Over current"
 
 What:		/sys/class/power_supply/<supply_name>/precharge_current
 Date:		June 2017
diff --git a/Documentation/ABI/testing/sysfs-driver-pciback b/Documentation/ABI/testing/sysfs-driver-pciback
index 6a733bfa37e6..73308c2b81b0 100644
--- a/Documentation/ABI/testing/sysfs-driver-pciback
+++ b/Documentation/ABI/testing/sysfs-driver-pciback
@@ -11,3 +11,16 @@ Description:
                 #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
                 will allow the guest to read and write to the configuration
                 register 0x0E.
+
+What:           /sys/bus/pci/drivers/pciback/allow_interrupt_control
+Date:           Jan 2020
+KernelVersion:  5.6
+Contact:        xen-devel@lists.xenproject.org
+Description:
+                List of devices which can have interrupt control flag (INTx,
+                MSI, MSI-X) set by a connected guest. It is meant to be set
+                only when the guest is a stubdomain hosting device model (qemu)
+                and the actual device is assigned to a HVM. It is not safe
+                (similar to permissive attribute) to set for a devices assigned
+                to a PV guest. The device is automatically removed from this
+                list when the connected pcifront terminates.
diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback
index 4e7babb3ba1f..ecb7942ff146 100644
--- a/Documentation/ABI/testing/sysfs-driver-xen-blkback
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback
@@ -25,3 +25,13 @@ Description:
                 allocated without being in use. The time is in
                 seconds, 0 means indefinitely long.
                 The default is 60 seconds.
+
+What:           /sys/module/xen_blkback/parameters/buffer_squeeze_duration_ms
+Date:           December 2019
+KernelVersion:  5.6
+Contact:        SeongJae Park <sjpark@amazon.de>
+Description:
+                When memory pressure is reported to blkback this option
+                controls the duration in milliseconds that blkback will not
+                cache any page not backed by a grant mapping.
+                The default is 10ms.
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index aedeae1e8ec1..1a6cd5397129 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -1,37 +1,40 @@
 What:		/sys/fs/f2fs/<disk>/gc_max_sleep_time
 Date:		July 2013
 Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
-Description:
-		 Controls the maximun sleep time for gc_thread. Time
-		 is in milliseconds.
+Description:	Controls the maximum sleep time for gc_thread. Time
+		is in milliseconds.
 
 What:		/sys/fs/f2fs/<disk>/gc_min_sleep_time
 Date:		July 2013
 Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
-Description:
-		 Controls the minimum sleep time for gc_thread. Time
-		 is in milliseconds.
+Description:	Controls the minimum sleep time for gc_thread. Time
+		is in milliseconds.
 
 What:		/sys/fs/f2fs/<disk>/gc_no_gc_sleep_time
 Date:		July 2013
 Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
-Description:
-		 Controls the default sleep time for gc_thread. Time
-		 is in milliseconds.
+Description:	Controls the default sleep time for gc_thread. Time
+		is in milliseconds.
 
 What:		/sys/fs/f2fs/<disk>/gc_idle
 Date:		July 2013
 Contact:	"Namjae Jeon" <namjae.jeon@samsung.com>
-Description:
-		 Controls the victim selection policy for garbage collection.
+Description:	Controls the victim selection policy for garbage collection.
+		Setting gc_idle = 0(default) will disable this option. Setting
+		gc_idle = 1 will select the Cost Benefit approach & setting
+		gc_idle = 2 will select the greedy approach.
 
 What:		/sys/fs/f2fs/<disk>/reclaim_segments
 Date:		October 2013
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the issue rate of segment discard commands.
-
-What:		/sys/fs/f2fs/<disk>/max_blkaddr
+Description:	This parameter controls the number of prefree segments to be
+		reclaimed. If the number of prefree segments is larger than
+		the number of segments in the proportion to the percentage
+		over total volume size, f2fs tries to conduct checkpoint to
+		reclaim the prefree segments to free segments.
+		By default, 5% over total # of segments.
+
+What:		/sys/fs/f2fs/<disk>/main_blkaddr
 Date:		November 2019
 Contact:	"Ramon Pantin" <pantin@google.com>
 Description:
@@ -40,227 +43,278 @@ Description:
 What:		/sys/fs/f2fs/<disk>/ipu_policy
 Date:		November 2013
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the in-place-update policy.
+Description:	Controls the in-place-update policy.
+		updates in f2fs. User can set:
+		0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
+		0x04: F2FS_IPU_UTIL,  0x08: F2FS_IPU_SSR_UTIL,
+		0x10: F2FS_IPU_FSYNC, 0x20: F2FS_IPU_ASYNC,
+		0x40: F2FS_IPU_NOCACHE.
+		Refer segment.h for details.
 
 What:		/sys/fs/f2fs/<disk>/min_ipu_util
 Date:		November 2013
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the FS utilization condition for the in-place-update
-		 policies.
+Description:	Controls the FS utilization condition for the in-place-update
+		policies. It is used by F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies.
 
 What:		/sys/fs/f2fs/<disk>/min_fsync_blocks
 Date:		September 2014
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls the dirty page count condition for the in-place-update
-		 policies.
+Description:	Controls the dirty page count condition for the in-place-update
+		policies.
 
 What:		/sys/fs/f2fs/<disk>/min_seq_blocks
 Date:		August 2018
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls the dirty page count condition for batched sequential
-		 writes in ->writepages.
-
+Description:	Controls the dirty page count condition for batched sequential
+		writes in writepages.
 
 What:		/sys/fs/f2fs/<disk>/min_hot_blocks
 Date:		March 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls the dirty page count condition for redefining hot data.
+Description:	Controls the dirty page count condition for redefining hot data.
 
 What:		/sys/fs/f2fs/<disk>/min_ssr_sections
 Date:		October 2017
 Contact:	"Chao Yu" <yuchao0@huawei.com>
-Description:
-		 Controls the fee section threshold to trigger SSR allocation.
+Description:	Controls the free section threshold to trigger SSR allocation.
+		If this is large, SSR mode will be enabled early.
 
 What:		/sys/fs/f2fs/<disk>/max_small_discards
 Date:		November 2013
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the issue rate of small discard commands.
+Description:	Controls the issue rate of discard commands that consist of small
+		blocks less than 2MB. The candidates to be discarded are cached until
+		checkpoint is triggered, and issued during the checkpoint.
+		By default, it is disabled with 0.
 
-What:          /sys/fs/f2fs/<disk>/discard_granularity
-Date:          July 2017
-Contact:       "Chao Yu" <yuchao0@huawei.com>
-Description:
-		Controls discard granularity of inner discard thread, inner thread
+What:		/sys/fs/f2fs/<disk>/discard_granularity
+Date:		July 2017
+Contact:	"Chao Yu" <yuchao0@huawei.com>
+Description:	Controls discard granularity of inner discard thread. Inner thread
 		will not issue discards with size that is smaller than granularity.
-		The unit size is one block, now only support configuring in range
-		of [1, 512].
+		The unit size is one block(4KB), now only support configuring
+		in range of [1, 512]. Default value is 4(=16KB).
 
-What:          /sys/fs/f2fs/<disk>/umount_discard_timeout
-Date:          January 2019
-Contact:       "Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		Set timeout to issue discard commands during umount.
-		Default: 5 secs
+What:		/sys/fs/f2fs/<disk>/umount_discard_timeout
+Date:		January 2019
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Set timeout to issue discard commands during umount.
+	        Default: 5 secs
 
 What:		/sys/fs/f2fs/<disk>/max_victim_search
 Date:		January 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the number of trials to find a victim segment.
+Description:	Controls the number of trials to find a victim segment
+		when conducting SSR and cleaning operations. The default value
+		is 4096 which covers 8GB block address range.
 
 What:		/sys/fs/f2fs/<disk>/migration_granularity
 Date:		October 2018
 Contact:	"Chao Yu" <yuchao0@huawei.com>
-Description:
-		 Controls migration granularity of garbage collection on large
-		 section, it can let GC move partial segment{s} of one section
-		 in one GC cycle, so that dispersing heavy overhead GC to
-		 multiple lightweight one.
+Description:	Controls migration granularity of garbage collection on large
+		section, it can let GC move partial segment{s} of one section
+		in one GC cycle, so that dispersing heavy overhead GC to
+		multiple lightweight one.
 
 What:		/sys/fs/f2fs/<disk>/dir_level
 Date:		March 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the directory level for large directory.
+Description:	Controls the directory level for large directory. If a
+		directory has a number of files, it can reduce the file lookup
+		latency by increasing this dir_level value. Otherwise, it
+		needs to decrease this value to reduce the space overhead.
+		The default value is 0.
 
 What:		/sys/fs/f2fs/<disk>/ram_thresh
 Date:		March 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
-Description:
-		 Controls the memory footprint used by f2fs.
+Description:	Controls the memory footprint used by free nids and cached
+		nat entries. By default, 1 is set, which indicates
+		10 MB / 1 GB RAM.
 
 What:		/sys/fs/f2fs/<disk>/batched_trim_sections
 Date:		February 2015
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls the trimming rate in batch mode.
-		 <deprecated>
+Description:	Controls the trimming rate in batch mode.
+		<deprecated>
 
 What:		/sys/fs/f2fs/<disk>/cp_interval
 Date:		October 2015
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls the checkpoint timing.
+Description:	Controls the checkpoint timing, set to 60 seconds by default.
 
 What:		/sys/fs/f2fs/<disk>/idle_interval
 Date:		January 2016
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls the idle timing for all paths other than
-		 discard and gc path.
+Description:	Controls the idle timing of system, if there is no FS operation
+		during given interval.
+		Set to 5 seconds by default.
 
 What:		/sys/fs/f2fs/<disk>/discard_idle_interval
 Date:		September 2018
 Contact:	"Chao Yu" <yuchao0@huawei.com>
 Contact:	"Sahitya Tummala" <stummala@codeaurora.org>
-Description:
-		 Controls the idle timing for discard path.
+Description:	Controls the idle timing of discard thread given
+		this time interval.
+		Default is 5 secs.
 
 What:		/sys/fs/f2fs/<disk>/gc_idle_interval
 Date:		September 2018
 Contact:	"Chao Yu" <yuchao0@huawei.com>
 Contact:	"Sahitya Tummala" <stummala@codeaurora.org>
-Description:
-		 Controls the idle timing for gc path.
+Description:    Controls the idle timing for gc path. Set to 5 seconds by default.
 
 What:		/sys/fs/f2fs/<disk>/iostat_enable
 Date:		August 2017
 Contact:	"Chao Yu" <yuchao0@huawei.com>
-Description:
-		 Controls to enable/disable IO stat.
+Description:	Controls to enable/disable IO stat.
 
 What:		/sys/fs/f2fs/<disk>/ra_nid_pages
 Date:		October 2015
 Contact:	"Chao Yu" <chao2.yu@samsung.com>
-Description:
-		 Controls the count of nid pages to be readaheaded.
+Description:	Controls the count of nid pages to be readaheaded.
+		When building free nids, F2FS reads NAT blocks ahead for
+		speed up. Default is 0.
 
 What:		/sys/fs/f2fs/<disk>/dirty_nats_ratio
 Date:		January 2016
 Contact:	"Chao Yu" <chao2.yu@samsung.com>
-Description:
-		 Controls dirty nat entries ratio threshold, if current
-		 ratio exceeds configured threshold, checkpoint will
-		 be triggered for flushing dirty nat entries.
+Description:	Controls dirty nat entries ratio threshold, if current
+		ratio exceeds configured threshold, checkpoint will
+		be triggered for flushing dirty nat entries.
 
 What:		/sys/fs/f2fs/<disk>/lifetime_write_kbytes
 Date:		January 2016
 Contact:	"Shuoran Liu" <liushuoran@huawei.com>
-Description:
-		 Shows total written kbytes issued to disk.
+Description:	Shows total written kbytes issued to disk.
 
 What:		/sys/fs/f2fs/<disk>/features
 Date:		July 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Shows all enabled features in current device.
+Description:	Shows all enabled features in current device.
 
 What:		/sys/fs/f2fs/<disk>/inject_rate
 Date:		May 2016
 Contact:	"Sheng Yong" <shengyong1@huawei.com>
-Description:
-		 Controls the injection rate.
+Description:	Controls the injection rate of arbitrary faults.
 
 What:		/sys/fs/f2fs/<disk>/inject_type
 Date:		May 2016
 Contact:	"Sheng Yong" <shengyong1@huawei.com>
-Description:
-		 Controls the injection type.
+Description:	Controls the injection type of arbitrary faults.
+
+What:		/sys/fs/f2fs/<disk>/dirty_segments
+Date:		October 2017
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Shows the number of dirty segments.
 
 What:		/sys/fs/f2fs/<disk>/reserved_blocks
 Date:		June 2017
 Contact:	"Chao Yu" <yuchao0@huawei.com>
-Description:
-		 Controls target reserved blocks in system, the threshold
-		 is soft, it could exceed current available user space.
+Description:	Controls target reserved blocks in system, the threshold
+		is soft, it could exceed current available user space.
 
 What:		/sys/fs/f2fs/<disk>/current_reserved_blocks
 Date:		October 2017
 Contact:	"Yunlong Song" <yunlong.song@huawei.com>
 Contact:	"Chao Yu" <yuchao0@huawei.com>
-Description:
-		 Shows current reserved blocks in system, it may be temporarily
-		 smaller than target_reserved_blocks, but will gradually
-		 increase to target_reserved_blocks when more free blocks are
-		 freed by user later.
+Description:	Shows current reserved blocks in system, it may be temporarily
+		smaller than target_reserved_blocks, but will gradually
+		increase to target_reserved_blocks when more free blocks are
+		freed by user later.
 
 What:		/sys/fs/f2fs/<disk>/gc_urgent
 Date:		August 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Do background GC agressively
+Description:	Do background GC agressively when set. When gc_urgent = 1,
+		background thread starts to do GC by given gc_urgent_sleep_time
+		interval. It is set to 0 by default.
 
 What:		/sys/fs/f2fs/<disk>/gc_urgent_sleep_time
 Date:		August 2017
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
-Description:
-		 Controls sleep time of GC urgent mode
+Description:	Controls sleep time of GC urgent mode. Set to 500ms by default.
 
 What:		/sys/fs/f2fs/<disk>/readdir_ra
 Date:		November 2017
 Contact:	"Sheng Yong" <shengyong1@huawei.com>
-Description:
-		 Controls readahead inode block in readdir.
+Description:	Controls readahead inode block in readdir. Enabled by default.
+
+What:		/sys/fs/f2fs/<disk>/gc_pin_file_thresh
+Date:		January 2018
+Contact:	Jaegeuk Kim <jaegeuk@kernel.org>
+Description:	This indicates how many GC can be failed for the pinned
+		file. If it exceeds this, F2FS doesn't guarantee its pinning
+		state. 2048 trials is set by default.
 
 What:		/sys/fs/f2fs/<disk>/extension_list
 Date:		Feburary 2018
 Contact:	"Chao Yu" <yuchao0@huawei.com>
-Description:
-		 Used to control configure extension list:
-		 - Query: cat /sys/fs/f2fs/<disk>/extension_list
-		 - Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list
-		 - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
-		 - [h] means add/del hot file extension
-		 - [c] means add/del cold file extension
+Description:	Used to control configure extension list:
+		- Query: cat /sys/fs/f2fs/<disk>/extension_list
+		- Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list
+		- Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
+		- [h] means add/del hot file extension
+		- [c] means add/del cold file extension
 
 What:		/sys/fs/f2fs/<disk>/unusable
 Date		April 2019
 Contact:	"Daniel Rosenberg" <drosen@google.com>
-Description:
-		If checkpoint=disable, it displays the number of blocks that are unusable.
-                If checkpoint=enable it displays the enumber of blocks that would be unusable
-                if checkpoint=disable were to be set.
+Description:	If checkpoint=disable, it displays the number of blocks that
+		are unusable.
+		If checkpoint=enable it displays the enumber of blocks that
+		would be unusable if checkpoint=disable were to be set.
 
 What:		/sys/fs/f2fs/<disk>/encoding
 Date		July 2019
 Contact:	"Daniel Rosenberg" <drosen@google.com>
-Description:
-		Displays name and version of the encoding set for the filesystem.
-                If no encoding is set, displays (none)
+Description:	Displays name and version of the encoding set for the filesystem.
+		If no encoding is set, displays (none)
+
+What:		/sys/fs/f2fs/<disk>/free_segments
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of free segments in disk.
+
+What:		/sys/fs/f2fs/<disk>/cp_foreground_calls
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of checkpoint operations performed on demand. Available when
+		CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/cp_background_calls
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of checkpoint operations performed in the background to
+		free segments. Available when CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/gc_foreground_calls
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of garbage collection operations performed on demand.
+		Available when CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/gc_background_calls
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of garbage collection operations triggered in background.
+		Available when CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/moved_blocks_foreground
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of blocks moved by garbage collection in foreground.
+		Available when CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/moved_blocks_background
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Number of blocks moved by garbage collection in background.
+		Available when CONFIG_F2FS_STAT_FS=y.
+
+What:		/sys/fs/f2fs/<disk>/avg_vblocks
+Date:		September 2019
+Contact:	"Hridya Valsaraju" <hridya@google.com>
+Description:	Average number of valid blocks.
+		Available when CONFIG_F2FS_STAT_FS=y.
diff --git a/Documentation/PCI/msi-howto.rst b/Documentation/PCI/msi-howto.rst
index 994cbb660ade..aa2046af69f7 100644
--- a/Documentation/PCI/msi-howto.rst
+++ b/Documentation/PCI/msi-howto.rst
@@ -283,5 +283,5 @@ or disabled (0).  If 0 is found in any of the msi_bus files belonging
 to bridges between the PCI root and the device, MSIs are disabled.
 
 It is also worth checking the device driver to see whether it supports MSIs.
-For example, it may contain calls to pci_irq_alloc_vectors() with the
+For example, it may contain calls to pci_alloc_irq_vectors() with the
 PCI_IRQ_MSI or PCI_IRQ_MSIX flags.
diff --git a/Documentation/admin-guide/device-mapper/dm-raid.rst b/Documentation/admin-guide/device-mapper/dm-raid.rst
index f6344675e395..695a2ea1d1ae 100644
--- a/Documentation/admin-guide/device-mapper/dm-raid.rst
+++ b/Documentation/admin-guide/device-mapper/dm-raid.rst
@@ -419,3 +419,5 @@ Version History
 	rebuild errors.
  1.15.0 Fix size extensions not being synchronized in case of new MD bitmap
         pages allocated;  also fix those not occuring after previous reductions
+ 1.15.1 Fix argument count and arguments for rebuild/write_mostly/journal_(dev|mode)
+        on the status line.
diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst
index 9bc93f0ce0c9..9443fcef1876 100644
--- a/Documentation/admin-guide/ext4.rst
+++ b/Documentation/admin-guide/ext4.rst
@@ -92,6 +92,8 @@ Currently Available
 * efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
   the ordering)
 * Case-insensitive file name lookups
+* file-based encryption support (fscrypt)
+* file-based verity support (fsverity)
 
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ec92120a7952..ddc5ccdd4cd1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -834,6 +834,18 @@
 			dump out devices still on the deferred probe list after
 			retrying.
 
+	dfltcc=		[HW,S390]
+			Format: { on | off | def_only | inf_only | always }
+			on:       s390 zlib hardware support for compression on
+			          level 1 and decompression (default)
+			off:      No s390 zlib hardware support
+			def_only: s390 zlib hardware support for deflate
+			          only (compression on level 1)
+			inf_only: s390 zlib hardware support for inflate
+			          only (decompression)
+			always:   Same as 'on' but ignores the selected compression
+			          level always using hardware support (used for debugging)
+
 	dhash_entries=	[KNL]
 			Set number of hash buckets for dentry cache.
 
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index ab0b9ec85506..a501dc1c90d0 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -31,6 +31,7 @@ Core utilities
    generic-radix-tree
    memory-allocation
    mm-api
+   pin_user_pages
    gfp_mask-from-fs-io
    timekeeping
    boot-time-mm
@@ -40,6 +41,7 @@ Core utilities
    gcc-plugins
    symbol-namespaces
    padata
+   ioctl
 
 
 Interfaces for kernel debugging
diff --git a/Documentation/core-api/ioctl.rst b/Documentation/core-api/ioctl.rst
new file mode 100644
index 000000000000..c455db0e1627
--- /dev/null
+++ b/Documentation/core-api/ioctl.rst
@@ -0,0 +1,253 @@
+======================
+ioctl based interfaces
+======================
+
+ioctl() is the most common way for applications to interface
+with device drivers. It is flexible and easily extended by adding new
+commands and can be passed through character devices, block devices as
+well as sockets and other special file descriptors.
+
+However, it is also very easy to get ioctl command definitions wrong,
+and hard to fix them later without breaking existing applications,
+so this documentation tries to help developers get it right.
+
+Command number definitions
+==========================
+
+The command number, or request number, is the second argument passed to
+the ioctl system call. While this can be any 32-bit number that uniquely
+identifies an action for a particular driver, there are a number of
+conventions around defining them.
+
+``include/uapi/asm-generic/ioctl.h`` provides four macros for defining
+ioctl commands that follow modern conventions: ``_IO``, ``_IOR``,
+``_IOW``, and ``_IOWR``. These should be used for all new commands,
+with the correct parameters:
+
+_IO/_IOR/_IOW/_IOWR
+   The macro name specifies how the argument will be used.  It may be a
+   pointer to data to be passed into the kernel (_IOW), out of the kernel
+   (_IOR), or both (_IOWR).  _IO can indicate either commands with no
+   argument or those passing an integer value instead of a pointer.
+   It is recommended to only use _IO for commands without arguments,
+   and use pointers for passing data.
+
+type
+   An 8-bit number, often a character literal, specific to a subsystem
+   or driver, and listed in :doc:`../userspace-api/ioctl/ioctl-number`
+
+nr
+  An 8-bit number identifying the specific command, unique for a give
+  value of 'type'
+
+data_type
+  The name of the data type pointed to by the argument, the command number
+  encodes the ``sizeof(data_type)`` value in a 13-bit or 14-bit integer,
+  leading to a limit of 8191 bytes for the maximum size of the argument.
+  Note: do not pass sizeof(data_type) type into _IOR/_IOW/IOWR, as that
+  will lead to encoding sizeof(sizeof(data_type)), i.e. sizeof(size_t).
+  _IO does not have a data_type parameter.
+
+
+Interface versions
+==================
+
+Some subsystems use version numbers in data structures to overload
+commands with different interpretations of the argument.
+
+This is generally a bad idea, since changes to existing commands tend
+to break existing applications.
+
+A better approach is to add a new ioctl command with a new number. The
+old command still needs to be implemented in the kernel for compatibility,
+but this can be a wrapper around the new implementation.
+
+Return code
+===========
+
+ioctl commands can return negative error codes as documented in errno(3);
+these get turned into errno values in user space. On success, the return
+code should be zero. It is also possible but not recommended to return
+a positive 'long' value.
+
+When the ioctl callback is called with an unknown command number, the
+handler returns either -ENOTTY or -ENOIOCTLCMD, which also results in
+-ENOTTY being returned from the system call. Some subsystems return
+-ENOSYS or -EINVAL here for historic reasons, but this is wrong.
+
+Prior to Linux 5.5, compat_ioctl handlers were required to return
+-ENOIOCTLCMD in order to use the fallback conversion into native
+commands. As all subsystems are now responsible for handling compat
+mode themselves, this is no longer needed, but it may be important to
+consider when backporting bug fixes to older kernels.
+
+Timestamps
+==========
+
+Traditionally, timestamps and timeout values are passed as ``struct
+timespec`` or ``struct timeval``, but these are problematic because of
+incompatible definitions of these structures in user space after the
+move to 64-bit time_t.
+
+The ``struct __kernel_timespec`` type can be used instead to be embedded
+in other data structures when separate second/nanosecond values are
+desired, or passed to user space directly. This is still not ideal though,
+as the structure matches neither the kernel's timespec64 nor the user
+space timespec exactly. The get_timespec64() and put_timespec64() helper
+functions can be used to ensure that the layout remains compatible with
+user space and the padding is treated correctly.
+
+As it is cheap to convert seconds to nanoseconds, but the opposite
+requires an expensive 64-bit division, a simple __u64 nanosecond value
+can be simpler and more efficient.
+
+Timeout values and timestamps should ideally use CLOCK_MONOTONIC time,
+as returned by ktime_get_ns() or ktime_get_ts64().  Unlike
+CLOCK_REALTIME, this makes the timestamps immune from jumping backwards
+or forwards due to leap second adjustments and clock_settime() calls.
+
+ktime_get_real_ns() can be used for CLOCK_REALTIME timestamps that
+need to be persistent across a reboot or between multiple machines.
+
+32-bit compat mode
+==================
+
+In order to support 32-bit user space running on a 64-bit machine, each
+subsystem or driver that implements an ioctl callback handler must also
+implement the corresponding compat_ioctl handler.
+
+As long as all the rules for data structures are followed, this is as
+easy as setting the .compat_ioctl pointer to a helper function such as
+compat_ptr_ioctl() or blkdev_compat_ptr_ioctl().
+
+compat_ptr()
+------------
+
+On the s390 architecture, 31-bit user space has ambiguous representations
+for data pointers, with the upper bit being ignored. When running such
+a process in compat mode, the compat_ptr() helper must be used to
+clear the upper bit of a compat_uptr_t and turn it into a valid 64-bit
+pointer.  On other architectures, this macro only performs a cast to a
+``void __user *`` pointer.
+
+In an compat_ioctl() callback, the last argument is an unsigned long,
+which can be interpreted as either a pointer or a scalar depending on
+the command. If it is a scalar, then compat_ptr() must not be used, to
+ensure that the 64-bit kernel behaves the same way as a 32-bit kernel
+for arguments with the upper bit set.
+
+The compat_ptr_ioctl() helper can be used in place of a custom
+compat_ioctl file operation for drivers that only take arguments that
+are pointers to compatible data structures.
+
+Structure layout
+----------------
+
+Compatible data structures have the same layout on all architectures,
+avoiding all problematic members:
+
+* ``long`` and ``unsigned long`` are the size of a register, so
+  they can be either 32-bit or 64-bit wide and cannot be used in portable
+  data structures. Fixed-length replacements are ``__s32``, ``__u32``,
+  ``__s64`` and ``__u64``.
+
+* Pointers have the same problem, in addition to requiring the
+  use of compat_ptr(). The best workaround is to use ``__u64``
+  in place of pointers, which requires a cast to ``uintptr_t`` in user
+  space, and the use of u64_to_user_ptr() in the kernel to convert
+  it back into a user pointer.
+
+* On the x86-32 (i386) architecture, the alignment of 64-bit variables
+  is only 32-bit, but they are naturally aligned on most other
+  architectures including x86-64. This means a structure like::
+
+    struct foo {
+        __u32 a;
+        __u64 b;
+        __u32 c;
+    };
+
+  has four bytes of padding between a and b on x86-64, plus another four
+  bytes of padding at the end, but no padding on i386, and it needs a
+  compat_ioctl conversion handler to translate between the two formats.
+
+  To avoid this problem, all structures should have their members
+  naturally aligned, or explicit reserved fields added in place of the
+  implicit padding. The ``pahole`` tool can be used for checking the
+  alignment.
+
+* On ARM OABI user space, structures are padded to multiples of 32-bit,
+  making some structs incompatible with modern EABI kernels if they
+  do not end on a 32-bit boundary.
+
+* On the m68k architecture, struct members are not guaranteed to have an
+  alignment greater than 16-bit, which is a problem when relying on
+  implicit padding.
+
+* Bitfields and enums generally work as one would expect them to,
+  but some properties of them are implementation-defined, so it is better
+  to avoid them completely in ioctl interfaces.
+
+* ``char`` members can be either signed or unsigned, depending on
+  the architecture, so the __u8 and __s8 types should be used for 8-bit
+  integer values, though char arrays are clearer for fixed-length strings.
+
+Information leaks
+=================
+
+Uninitialized data must not be copied back to user space, as this can
+cause an information leak, which can be used to defeat kernel address
+space layout randomization (KASLR), helping in an attack.
+
+For this reason (and for compat support) it is best to avoid any
+implicit padding in data structures.  Where there is implicit padding
+in an existing structure, kernel drivers must be careful to fully
+initialize an instance of the structure before copying it to user
+space.  This is usually done by calling memset() before assigning to
+individual members.
+
+Subsystem abstractions
+======================
+
+While some device drivers implement their own ioctl function, most
+subsystems implement the same command for multiple drivers.  Ideally the
+subsystem has an .ioctl() handler that copies the arguments from and
+to user space, passing them into subsystem specific callback functions
+through normal kernel pointers.
+
+This helps in various ways:
+
+* Applications written for one driver are more likely to work for
+  another one in the same subsystem if there are no subtle differences
+  in the user space ABI.
+
+* The complexity of user space access and data structure layout is done
+  in one place, reducing the potential for implementation bugs.
+
+* It is more likely to be reviewed by experienced developers
+  that can spot problems in the interface when the ioctl is shared
+  between multiple drivers than when it is only used in a single driver.
+
+Alternatives to ioctl
+=====================
+
+There are many cases in which ioctl is not the best solution for a
+problem. Alternatives include:
+
+* System calls are a better choice for a system-wide feature that
+  is not tied to a physical device or constrained by the file system
+  permissions of a character device node
+
+* netlink is the preferred way of configuring any network related
+  objects through sockets.
+
+* debugfs is used for ad-hoc interfaces for debugging functionality
+  that does not need to be exposed as a stable interface to applications.
+
+* sysfs is a good way to expose the state of an in-kernel object
+  that is not tied to a file descriptor.
+
+* configfs can be used for more complex configuration than sysfs
+
+* A custom file system can provide extra flexibility with a simple
+  user interface but adds a lot of complexity to the implementation.
diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst
new file mode 100644
index 000000000000..1d490155ecd7
--- /dev/null
+++ b/Documentation/core-api/pin_user_pages.rst
@@ -0,0 +1,232 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====================================================
+pin_user_pages() and related calls
+====================================================
+
+.. contents:: :local:
+
+Overview
+========
+
+This document describes the following functions::
+
+ pin_user_pages()
+ pin_user_pages_fast()
+ pin_user_pages_remote()
+
+Basic description of FOLL_PIN
+=============================
+
+FOLL_PIN and FOLL_LONGTERM are flags that can be passed to the get_user_pages*()
+("gup") family of functions. FOLL_PIN has significant interactions and
+interdependencies with FOLL_LONGTERM, so both are covered here.
+
+FOLL_PIN is internal to gup, meaning that it should not appear at the gup call
+sites. This allows the associated wrapper functions  (pin_user_pages*() and
+others) to set the correct combination of these flags, and to check for problems
+as well.
+
+FOLL_LONGTERM, on the other hand, *is* allowed to be set at the gup call sites.
+This is in order to avoid creating a large number of wrapper functions to cover
+all combinations of get*(), pin*(), FOLL_LONGTERM, and more. Also, the
+pin_user_pages*() APIs are clearly distinct from the get_user_pages*() APIs, so
+that's a natural dividing line, and a good point to make separate wrapper calls.
+In other words, use pin_user_pages*() for DMA-pinned pages, and
+get_user_pages*() for other cases. There are four cases described later on in
+this document, to further clarify that concept.
+
+FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However,
+multiple threads and call sites are free to pin the same struct pages, via both
+FOLL_PIN and FOLL_GET. It's just the call site that needs to choose one or the
+other, not the struct page(s).
+
+The FOLL_PIN implementation is nearly the same as FOLL_GET, except that FOLL_PIN
+uses a different reference counting technique.
+
+FOLL_PIN is a prerequisite to FOLL_LONGTERM. Another way of saying that is,
+FOLL_LONGTERM is a specific case, more restrictive case of FOLL_PIN.
+
+Which flags are set by each wrapper
+===================================
+
+For these pin_user_pages*() functions, FOLL_PIN is OR'd in with whatever gup
+flags the caller provides. The caller is required to pass in a non-null struct
+pages* array, and the function then pin pages by incrementing each by a special
+value. For now, that value is +1, just like get_user_pages*().::
+
+ Function
+ --------
+ pin_user_pages          FOLL_PIN is always set internally by this function.
+ pin_user_pages_fast     FOLL_PIN is always set internally by this function.
+ pin_user_pages_remote   FOLL_PIN is always set internally by this function.
+
+For these get_user_pages*() functions, FOLL_GET might not even be specified.
+Behavior is a little more complex than above. If FOLL_GET was *not* specified,
+but the caller passed in a non-null struct pages* array, then the function
+sets FOLL_GET for you, and proceeds to pin pages by incrementing the refcount
+of each page by +1.::
+
+ Function
+ --------
+ get_user_pages           FOLL_GET is sometimes set internally by this function.
+ get_user_pages_fast      FOLL_GET is sometimes set internally by this function.
+ get_user_pages_remote    FOLL_GET is sometimes set internally by this function.
+
+Tracking dma-pinned pages
+=========================
+
+Some of the key design constraints, and solutions, for tracking dma-pinned
+pages:
+
+* An actual reference count, per struct page, is required. This is because
+  multiple processes may pin and unpin a page.
+
+* False positives (reporting that a page is dma-pinned, when in fact it is not)
+  are acceptable, but false negatives are not.
+
+* struct page may not be increased in size for this, and all fields are already
+  used.
+
+* Given the above, we can overload the page->_refcount field by using, sort of,
+  the upper bits in that field for a dma-pinned count. "Sort of", means that,
+  rather than dividing page->_refcount into bit fields, we simple add a medium-
+  large value (GUP_PIN_COUNTING_BIAS, initially chosen to be 1024: 10 bits) to
+  page->_refcount. This provides fuzzy behavior: if a page has get_page() called
+  on it 1024 times, then it will appear to have a single dma-pinned count.
+  And again, that's acceptable.
+
+This also leads to limitations: there are only 31-10==21 bits available for a
+counter that increments 10 bits at a time.
+
+TODO: for 1GB and larger huge pages, this is cutting it close. That's because
+when pin_user_pages() follows such pages, it increments the head page by "1"
+(where "1" used to mean "+1" for get_user_pages(), but now means "+1024" for
+pin_user_pages()) for each tail page. So if you have a 1GB huge page:
+
+* There are 256K (18 bits) worth of 4 KB tail pages.
+* There are 21 bits available to count up via GUP_PIN_COUNTING_BIAS (that is,
+  10 bits at a time)
+* There are 21 - 18 == 3 bits available to count. Except that there aren't,
+  because you need to allow for a few normal get_page() calls on the head page,
+  as well. Fortunately, the approach of using addition, rather than "hard"
+  bitfields, within page->_refcount, allows for sharing these bits gracefully.
+  But we're still looking at about 8 references.
+
+This, however, is a missing feature more than anything else, because it's easily
+solved by addressing an obvious inefficiency in the original get_user_pages()
+approach of retrieving pages: stop treating all the pages as if they were
+PAGE_SIZE. Retrieve huge pages as huge pages. The callers need to be aware of
+this, so some work is required. Once that's in place, this limitation mostly
+disappears from view, because there will be ample refcounting range available.
+
+* Callers must specifically request "dma-pinned tracking of pages". In other
+  words, just calling get_user_pages() will not suffice; a new set of functions,
+  pin_user_page() and related, must be used.
+
+FOLL_PIN, FOLL_GET, FOLL_LONGTERM: when to use which flags
+==========================================================
+
+Thanks to Jan Kara, Vlastimil Babka and several other -mm people, for describing
+these categories:
+
+CASE 1: Direct IO (DIO)
+-----------------------
+There are GUP references to pages that are serving
+as DIO buffers. These buffers are needed for a relatively short time (so they
+are not "long term"). No special synchronization with page_mkclean() or
+munmap() is provided. Therefore, flags to set at the call site are: ::
+
+    FOLL_PIN
+
+...but rather than setting FOLL_PIN directly, call sites should use one of
+the pin_user_pages*() routines that set FOLL_PIN.
+
+CASE 2: RDMA
+------------
+There are GUP references to pages that are serving as DMA
+buffers. These buffers are needed for a long time ("long term"). No special
+synchronization with page_mkclean() or munmap() is provided. Therefore, flags
+to set at the call site are: ::
+
+    FOLL_PIN | FOLL_LONGTERM
+
+NOTE: Some pages, such as DAX pages, cannot be pinned with longterm pins. That's
+because DAX pages do not have a separate page cache, and so "pinning" implies
+locking down file system blocks, which is not (yet) supported in that way.
+
+CASE 3: Hardware with page faulting support
+-------------------------------------------
+Here, a well-written driver doesn't normally need to pin pages at all. However,
+if the driver does choose to do so, it can register MMU notifiers for the range,
+and will be called back upon invalidation. Either way (avoiding page pinning, or
+using MMU notifiers to unpin upon request), there is proper synchronization with
+both filesystem and mm (page_mkclean(), munmap(), etc).
+
+Therefore, neither flag needs to be set.
+
+In this case, ideally, neither get_user_pages() nor pin_user_pages() should be
+called. Instead, the software should be written so that it does not pin pages.
+This allows mm and filesystems to operate more efficiently and reliably.
+
+CASE 4: Pinning for struct page manipulation only
+-------------------------------------------------
+Here, normal GUP calls are sufficient, so neither flag needs to be set.
+
+page_dma_pinned(): the whole point of pinning
+=============================================
+
+The whole point of marking pages as "DMA-pinned" or "gup-pinned" is to be able
+to query, "is this page DMA-pinned?" That allows code such as page_mkclean()
+(and file system writeback code in general) to make informed decisions about
+what to do when a page cannot be unmapped due to such pins.
+
+What to do in those cases is the subject of a years-long series of discussions
+and debates (see the References at the end of this document). It's a TODO item
+here: fill in the details once that's worked out. Meanwhile, it's safe to say
+that having this available: ::
+
+        static inline bool page_dma_pinned(struct page *page)
+
+...is a prerequisite to solving the long-running gup+DMA problem.
+
+Another way of thinking about FOLL_GET, FOLL_PIN, and FOLL_LONGTERM
+===================================================================
+
+Another way of thinking about these flags is as a progression of restrictions:
+FOLL_GET is for struct page manipulation, without affecting the data that the
+struct page refers to. FOLL_PIN is a *replacement* for FOLL_GET, and is for
+short term pins on pages whose data *will* get accessed. As such, FOLL_PIN is
+a "more severe" form of pinning. And finally, FOLL_LONGTERM is an even more
+restrictive case that has FOLL_PIN as a prerequisite: this is for pages that
+will be pinned longterm, and whose data will be accessed.
+
+Unit testing
+============
+This file::
+
+ tools/testing/selftests/vm/gup_benchmark.c
+
+has the following new calls to exercise the new pin*() wrapper functions:
+
+* PIN_FAST_BENCHMARK (./gup_benchmark -a)
+* PIN_BENCHMARK (./gup_benchmark -b)
+
+You can monitor how many total dma-pinned pages have been acquired and released
+since the system was booted, via two new /proc/vmstat entries: ::
+
+    /proc/vmstat/nr_foll_pin_requested
+    /proc/vmstat/nr_foll_pin_requested
+
+Those are both going to show zero, unless CONFIG_DEBUG_VM is set. This is
+because there is a noticeable performance drop in unpin_user_page(), when they
+are activated.
+
+References
+==========
+
+* `Some slow progress on get_user_pages() (Apr 2, 2019) <https://lwn.net/Articles/784574/>`_
+* `DMA and get_user_pages() (LPC: Dec 12, 2018) <https://lwn.net/Articles/774411/>`_
+* `The trouble with get_user_pages() (Apr 30, 2018) <https://lwn.net/Articles/753027/>`_
+
+John Hubbard, October, 2019
diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index e4d66e7c50de..c652d740735d 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -21,8 +21,8 @@ global variables yet.
 
 Tag-based KASAN is only supported in Clang and requires version 7.0.0 or later.
 
-Currently generic KASAN is supported for the x86_64, arm64, xtensa and s390
-architectures, and tag-based KASAN is supported only for arm64.
+Currently generic KASAN is supported for the x86_64, arm64, xtensa, s390 and
+riscv architectures, and tag-based KASAN is supported only for arm64.
 
 Usage
 -----
diff --git a/Documentation/devicetree/bindings/arm/arm-boards b/Documentation/devicetree/bindings/arm/arm-boards
index b2a9f9f8430b..96b1dad58253 100644
--- a/Documentation/devicetree/bindings/arm/arm-boards
+++ b/Documentation/devicetree/bindings/arm/arm-boards
@@ -121,7 +121,7 @@ Required properties (in root node):
 Required nodes:
 
 - soc: some node of the RealView platforms must be the SoC
-  node that contain the SoC-specific devices, withe the compatible
+  node that contain the SoC-specific devices, with the compatible
   string set to one of these tuples:
    "arm,realview-eb-soc", "simple-bus"
    "arm,realview-pb1176-soc", "simple-bus"
diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml
index f79683a628f0..b0a7454a70b8 100644
--- a/Documentation/devicetree/bindings/arm/fsl.yaml
+++ b/Documentation/devicetree/bindings/arm/fsl.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/arm/fsl.yaml#
+$id: http://devicetree.org/schemas/arm/fsl.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Freescale i.MX Platforms Device Tree Bindings
diff --git a/Documentation/devicetree/bindings/arm/idle-states.txt b/Documentation/devicetree/bindings/arm/idle-states.txt
deleted file mode 100644
index 771f5d20ae18..000000000000
--- a/Documentation/devicetree/bindings/arm/idle-states.txt
+++ /dev/null
@@ -1,706 +0,0 @@
-==========================================
-ARM idle states binding description
-==========================================
-
-==========================================
-1 - Introduction
-==========================================
-
-ARM systems contain HW capable of managing power consumption dynamically,
-where cores can be put in different low-power states (ranging from simple
-wfi to power gating) according to OS PM policies. The CPU states representing
-the range of dynamic idle states that a processor can enter at run-time, can be
-specified through device tree bindings representing the parameters required
-to enter/exit specific idle states on a given processor.
-
-According to the Server Base System Architecture document (SBSA, [3]), the
-power states an ARM CPU can be put into are identified by the following list:
-
-- Running
-- Idle_standby
-- Idle_retention
-- Sleep
-- Off
-
-The power states described in the SBSA document define the basic CPU states on
-top of which ARM platforms implement power management schemes that allow an OS
-PM implementation to put the processor in different idle states (which include
-states listed above; "off" state is not an idle state since it does not have
-wake-up capabilities, hence it is not considered in this document).
-
-Idle state parameters (e.g. entry latency) are platform specific and need to be
-characterized with bindings that provide the required information to OS PM
-code so that it can build the required tables and use them at runtime.
-
-The device tree binding definition for ARM idle states is the subject of this
-document.
-
-===========================================
-2 - idle-states definitions
-===========================================
-
-Idle states are characterized for a specific system through a set of
-timing and energy related properties, that underline the HW behaviour
-triggered upon idle states entry and exit.
-
-The following diagram depicts the CPU execution phases and related timing
-properties required to enter and exit an idle state:
-
-..__[EXEC]__|__[PREP]__|__[ENTRY]__|__[IDLE]__|__[EXIT]__|__[EXEC]__..
-	    |          |           |          |          |
-
-	    |<------ entry ------->|
-	    |       latency        |
-					      |<- exit ->|
-					      |  latency |
-	    |<-------- min-residency -------->|
-		       |<-------  wakeup-latency ------->|
-
-		Diagram 1: CPU idle state execution phases
-
-EXEC:	Normal CPU execution.
-
-PREP:	Preparation phase before committing the hardware to idle mode
-	like cache flushing. This is abortable on pending wake-up
-	event conditions. The abort latency is assumed to be negligible
-	(i.e. less than the ENTRY + EXIT duration). If aborted, CPU
-	goes back to EXEC. This phase is optional. If not abortable,
-	this should be included in the ENTRY phase instead.
-
-ENTRY:	The hardware is committed to idle mode. This period must run
-	to completion up to IDLE before anything else can happen.
-
-IDLE:	This is the actual energy-saving idle period. This may last
-	between 0 and infinite time, until a wake-up event occurs.
-
-EXIT:	Period during which the CPU is brought back to operational
-	mode (EXEC).
-
-entry-latency: Worst case latency required to enter the idle state. The
-exit-latency may be guaranteed only after entry-latency has passed.
-
-min-residency: Minimum period, including preparation and entry, for a given
-idle state to be worthwhile energywise.
-
-wakeup-latency: Maximum delay between the signaling of a wake-up event and the
-CPU being able to execute normal code again. If not specified, this is assumed
-to be entry-latency + exit-latency.
-
-These timing parameters can be used by an OS in different circumstances.
-
-An idle CPU requires the expected min-residency time to select the most
-appropriate idle state based on the expected expiry time of the next IRQ
-(i.e. wake-up) that causes the CPU to return to the EXEC phase.
-
-An operating system scheduler may need to compute the shortest wake-up delay
-for CPUs in the system by detecting how long will it take to get a CPU out
-of an idle state, e.g.:
-
-wakeup-delay = exit-latency + max(entry-latency - (now - entry-timestamp), 0)
-
-In other words, the scheduler can make its scheduling decision by selecting
-(e.g. waking-up) the CPU with the shortest wake-up delay.
-The wake-up delay must take into account the entry latency if that period
-has not expired. The abortable nature of the PREP period can be ignored
-if it cannot be relied upon (e.g. the PREP deadline may occur much sooner than
-the worst case since it depends on the CPU operating conditions, i.e. caches
-state).
-
-An OS has to reliably probe the wakeup-latency since some devices can enforce
-latency constraint guarantees to work properly, so the OS has to detect the
-worst case wake-up latency it can incur if a CPU is allowed to enter an
-idle state, and possibly to prevent that to guarantee reliable device
-functioning.
-
-The min-residency time parameter deserves further explanation since it is
-expressed in time units but must factor in energy consumption coefficients.
-
-The energy consumption of a cpu when it enters a power state can be roughly
-characterised by the following graph:
-
-               |
-               |
-               |
-           e   |
-           n   |                                      /---
-           e   |                               /------
-           r   |                        /------
-           g   |                  /-----
-           y   |           /------
-               |       ----
-               |      /|
-               |     / |
-               |    /  |
-               |   /   |
-               |  /    |
-               | /     |
-               |/      |
-          -----|-------+----------------------------------
-              0|       1                              time(ms)
-
-		Graph 1: Energy vs time example
-
-The graph is split in two parts delimited by time 1ms on the X-axis.
-The graph curve with X-axis values = { x | 0 < x < 1ms } has a steep slope
-and denotes the energy costs incurred while entering and leaving the idle
-state.
-The graph curve in the area delimited by X-axis values = {x | x > 1ms } has
-shallower slope and essentially represents the energy consumption of the idle
-state.
-
-min-residency is defined for a given idle state as the minimum expected
-residency time for a state (inclusive of preparation and entry) after
-which choosing that state become the most energy efficient option. A good
-way to visualise this, is by taking the same graph above and comparing some
-states energy consumptions plots.
-
-For sake of simplicity, let's consider a system with two idle states IDLE1,
-and IDLE2:
-
-          |
-          |
-          |
-          |                                                  /-- IDLE1
-       e  |                                              /---
-       n  |                                         /----
-       e  |                                     /---
-       r  |                                /-----/--------- IDLE2
-       g  |                    /-------/---------
-       y  |        ------------    /---|
-          |       /           /----    |
-          |      /        /---         |
-          |     /    /----             |
-          |    / /---                  |
-          |   ---                      |
-          |  /                         |
-          | /                          |
-          |/                           |                  time
-       ---/----------------------------+------------------------
-          |IDLE1-energy < IDLE2-energy | IDLE2-energy < IDLE1-energy
-                                       |
-                                IDLE2-min-residency
-
-		Graph 2: idle states min-residency example
-
-In graph 2 above, that takes into account idle states entry/exit energy
-costs, it is clear that if the idle state residency time (i.e. time till next
-wake-up IRQ) is less than IDLE2-min-residency, IDLE1 is the better idle state
-choice energywise.
-
-This is mainly down to the fact that IDLE1 entry/exit energy costs are lower
-than IDLE2.
-
-However, the lower power consumption (i.e. shallower energy curve slope) of
-idle state IDLE2 implies that after a suitable time, IDLE2 becomes more energy
-efficient.
-
-The time at which IDLE2 becomes more energy efficient than IDLE1 (and other
-shallower states in a system with multiple idle states) is defined
-IDLE2-min-residency and corresponds to the time when energy consumption of
-IDLE1 and IDLE2 states breaks even.
-
-The definitions provided in this section underpin the idle states
-properties specification that is the subject of the following sections.
-
-===========================================
-3 - idle-states node
-===========================================
-
-ARM processor idle states are defined within the idle-states node, which is
-a direct child of the cpus node [1] and provides a container where the
-processor idle states, defined as device tree nodes, are listed.
-
-- idle-states node
-
-	Usage: Optional - On ARM systems, it is a container of processor idle
-			  states nodes. If the system does not provide CPU
-			  power management capabilities, or the processor just
-			  supports idle_standby, an idle-states node is not
-			  required.
-
-	Description: idle-states node is a container node, where its
-		     subnodes describe the CPU idle states.
-
-	Node name must be "idle-states".
-
-	The idle-states node's parent node must be the cpus node.
-
-	The idle-states node's child nodes can be:
-
-	- one or more state nodes
-
-	Any other configuration is considered invalid.
-
-	An idle-states node defines the following properties:
-
-	- entry-method
-		Value type: <stringlist>
-		Usage and definition depend on ARM architecture version.
-			# On ARM v8 64-bit this property is required and must
-			  be:
-			   - "psci"
-			# On ARM 32-bit systems this property is optional
-
-This assumes that the "enable-method" property is set to "psci" in the cpu
-node[6] that is responsible for setting up CPU idle management in the OS
-implementation.
-
-The nodes describing the idle states (state) can only be defined
-within the idle-states node, any other configuration is considered invalid
-and therefore must be ignored.
-
-===========================================
-4 - state node
-===========================================
-
-A state node represents an idle state description and must be defined as
-follows:
-
-- state node
-
-	Description: must be child of the idle-states node
-
-	The state node name shall follow standard device tree naming
-	rules ([5], 2.2.1 "Node names"), in particular state nodes which
-	are siblings within a single common parent must be given a unique name.
-
-	The idle state entered by executing the wfi instruction (idle_standby
-	SBSA,[3][4]) is considered standard on all ARM platforms and therefore
-	must not be listed.
-
-	With the definitions provided above, the following list represents
-	the valid properties for a state node:
-
-	- compatible
-		Usage: Required
-		Value type: <stringlist>
-		Definition: Must be "arm,idle-state".
-
-	- local-timer-stop
-		Usage: See definition
-		Value type: <none>
-		Definition: if present the CPU local timer control logic is
-			    lost on state entry, otherwise it is retained.
-
-	- entry-latency-us
-		Usage: Required
-		Value type: <prop-encoded-array>
-		Definition: u32 value representing worst case latency in
-			    microseconds required to enter the idle state.
-
-	- exit-latency-us
-		Usage: Required
-		Value type: <prop-encoded-array>
-		Definition: u32 value representing worst case latency
-			    in microseconds required to exit the idle state.
-			    The exit-latency-us duration may be guaranteed
-			    only after entry-latency-us has passed.
-
-	- min-residency-us
-		Usage: Required
-		Value type: <prop-encoded-array>
-		Definition: u32 value representing minimum residency duration
-			    in microseconds, inclusive of preparation and
-			    entry, for this idle state to be considered
-			    worthwhile energy wise (refer to section 2 of
-			    this document for a complete description).
-
-	- wakeup-latency-us:
-		Usage: Optional
-		Value type: <prop-encoded-array>
-		Definition: u32 value representing maximum delay between the
-			    signaling of a wake-up event and the CPU being
-			    able to execute normal code again. If omitted,
-			    this is assumed to be equal to:
-
-				entry-latency-us + exit-latency-us
-
-			    It is important to supply this value on systems
-			    where the duration of PREP phase (see diagram 1,
-			    section 2) is non-neglibigle.
-			    In such systems entry-latency-us + exit-latency-us
-			    will exceed wakeup-latency-us by this duration.
-
-	- status:
-		Usage: Optional
-		Value type: <string>
-		Definition: A standard device tree property [5] that indicates
-			    the operational status of an idle-state.
-			    If present, it shall be:
-			    "okay": to indicate that the idle state is
-				    operational.
-			    "disabled": to indicate that the idle state has
-					been disabled in firmware so it is not
-					operational.
-			    If the property is not present the idle-state must
-			    be considered operational.
-
-	- idle-state-name:
-		Usage: Optional
-		Value type: <string>
-		Definition: A string used as a descriptive name for the idle
-			    state.
-
-	In addition to the properties listed above, a state node may require
-	additional properties specific to the entry-method defined in the
-	idle-states node. Please refer to the entry-method bindings
-	documentation for properties definitions.
-
-===========================================
-4 - Examples
-===========================================
-
-Example 1 (ARM 64-bit, 16-cpu system, PSCI enable-method):
-
-cpus {
-	#size-cells = <0>;
-	#address-cells = <2>;
-
-	CPU0: cpu@0 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x0>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU1: cpu@1 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x1>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU2: cpu@100 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x100>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU3: cpu@101 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x101>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU4: cpu@10000 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x10000>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU5: cpu@10001 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x10001>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU6: cpu@10100 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x10100>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU7: cpu@10101 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a57";
-		reg = <0x0 0x10101>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
-				   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU8: cpu@100000000 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x0>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU9: cpu@100000001 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x1>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU10: cpu@100000100 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x100>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU11: cpu@100000101 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x101>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU12: cpu@100010000 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x10000>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU13: cpu@100010001 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x10001>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU14: cpu@100010100 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x10100>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU15: cpu@100010101 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a53";
-		reg = <0x1 0x10101>;
-		enable-method = "psci";
-		cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
-				   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
-	};
-
-	idle-states {
-		entry-method = "psci";
-
-		CPU_RETENTION_0_0: cpu-retention-0-0 {
-			compatible = "arm,idle-state";
-			arm,psci-suspend-param = <0x0010000>;
-			entry-latency-us = <20>;
-			exit-latency-us = <40>;
-			min-residency-us = <80>;
-		};
-
-		CLUSTER_RETENTION_0: cluster-retention-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			arm,psci-suspend-param = <0x1010000>;
-			entry-latency-us = <50>;
-			exit-latency-us = <100>;
-			min-residency-us = <250>;
-			wakeup-latency-us = <130>;
-		};
-
-		CPU_SLEEP_0_0: cpu-sleep-0-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			arm,psci-suspend-param = <0x0010000>;
-			entry-latency-us = <250>;
-			exit-latency-us = <500>;
-			min-residency-us = <950>;
-		};
-
-		CLUSTER_SLEEP_0: cluster-sleep-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			arm,psci-suspend-param = <0x1010000>;
-			entry-latency-us = <600>;
-			exit-latency-us = <1100>;
-			min-residency-us = <2700>;
-			wakeup-latency-us = <1500>;
-		};
-
-		CPU_RETENTION_1_0: cpu-retention-1-0 {
-			compatible = "arm,idle-state";
-			arm,psci-suspend-param = <0x0010000>;
-			entry-latency-us = <20>;
-			exit-latency-us = <40>;
-			min-residency-us = <90>;
-		};
-
-		CLUSTER_RETENTION_1: cluster-retention-1 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			arm,psci-suspend-param = <0x1010000>;
-			entry-latency-us = <50>;
-			exit-latency-us = <100>;
-			min-residency-us = <270>;
-			wakeup-latency-us = <100>;
-		};
-
-		CPU_SLEEP_1_0: cpu-sleep-1-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			arm,psci-suspend-param = <0x0010000>;
-			entry-latency-us = <70>;
-			exit-latency-us = <100>;
-			min-residency-us = <300>;
-			wakeup-latency-us = <150>;
-		};
-
-		CLUSTER_SLEEP_1: cluster-sleep-1 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			arm,psci-suspend-param = <0x1010000>;
-			entry-latency-us = <500>;
-			exit-latency-us = <1200>;
-			min-residency-us = <3500>;
-			wakeup-latency-us = <1300>;
-		};
-	};
-
-};
-
-Example 2 (ARM 32-bit, 8-cpu system, two clusters):
-
-cpus {
-	#size-cells = <0>;
-	#address-cells = <1>;
-
-	CPU0: cpu@0 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a15";
-		reg = <0x0>;
-		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU1: cpu@1 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a15";
-		reg = <0x1>;
-		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU2: cpu@2 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a15";
-		reg = <0x2>;
-		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU3: cpu@3 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a15";
-		reg = <0x3>;
-		cpu-idle-states = <&CPU_SLEEP_0_0 &CLUSTER_SLEEP_0>;
-	};
-
-	CPU4: cpu@100 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a7";
-		reg = <0x100>;
-		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU5: cpu@101 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a7";
-		reg = <0x101>;
-		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU6: cpu@102 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a7";
-		reg = <0x102>;
-		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
-	};
-
-	CPU7: cpu@103 {
-		device_type = "cpu";
-		compatible = "arm,cortex-a7";
-		reg = <0x103>;
-		cpu-idle-states = <&CPU_SLEEP_1_0 &CLUSTER_SLEEP_1>;
-	};
-
-	idle-states {
-		CPU_SLEEP_0_0: cpu-sleep-0-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			entry-latency-us = <200>;
-			exit-latency-us = <100>;
-			min-residency-us = <400>;
-			wakeup-latency-us = <250>;
-		};
-
-		CLUSTER_SLEEP_0: cluster-sleep-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			entry-latency-us = <500>;
-			exit-latency-us = <1500>;
-			min-residency-us = <2500>;
-			wakeup-latency-us = <1700>;
-		};
-
-		CPU_SLEEP_1_0: cpu-sleep-1-0 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			entry-latency-us = <300>;
-			exit-latency-us = <500>;
-			min-residency-us = <900>;
-			wakeup-latency-us = <600>;
-		};
-
-		CLUSTER_SLEEP_1: cluster-sleep-1 {
-			compatible = "arm,idle-state";
-			local-timer-stop;
-			entry-latency-us = <800>;
-			exit-latency-us = <2000>;
-			min-residency-us = <6500>;
-			wakeup-latency-us = <2300>;
-		};
-	};
-
-};
-
-===========================================
-5 - References
-===========================================
-
-[1] ARM Linux Kernel documentation - CPUs bindings
-    Documentation/devicetree/bindings/arm/cpus.yaml
-
-[2] ARM Linux Kernel documentation - PSCI bindings
-    Documentation/devicetree/bindings/arm/psci.yaml
-
-[3] ARM Server Base System Architecture (SBSA)
-    http://infocenter.arm.com/help/index.jsp
-
-[4] ARM Architecture Reference Manuals
-    http://infocenter.arm.com/help/index.jsp
-
-[5] Devicetree Specification
-    https://www.devicetree.org/specifications/
-
-[6] ARM Linux Kernel documentation - Booting AArch64 Linux
-    Documentation/arm64/booting.rst
diff --git a/Documentation/devicetree/bindings/arm/idle-states.yaml b/Documentation/devicetree/bindings/arm/idle-states.yaml
new file mode 100644
index 000000000000..ea805c1e6b20
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/idle-states.yaml
@@ -0,0 +1,661 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/idle-states.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM idle states binding description
+
+maintainers:
+  - Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+
+description: |+
+  ==========================================
+  1 - Introduction
+  ==========================================
+
+  ARM systems contain HW capable of managing power consumption dynamically,
+  where cores can be put in different low-power states (ranging from simple wfi
+  to power gating) according to OS PM policies. The CPU states representing the
+  range of dynamic idle states that a processor can enter at run-time, can be
+  specified through device tree bindings representing the parameters required to
+  enter/exit specific idle states on a given processor.
+
+  According to the Server Base System Architecture document (SBSA, [3]), the
+  power states an ARM CPU can be put into are identified by the following list:
+
+  - Running
+  - Idle_standby
+  - Idle_retention
+  - Sleep
+  - Off
+
+  The power states described in the SBSA document define the basic CPU states on
+  top of which ARM platforms implement power management schemes that allow an OS
+  PM implementation to put the processor in different idle states (which include
+  states listed above; "off" state is not an idle state since it does not have
+  wake-up capabilities, hence it is not considered in this document).
+
+  Idle state parameters (e.g. entry latency) are platform specific and need to
+  be characterized with bindings that provide the required information to OS PM
+  code so that it can build the required tables and use them at runtime.
+
+  The device tree binding definition for ARM idle states is the subject of this
+  document.
+
+  ===========================================
+  2 - idle-states definitions
+  ===========================================
+
+  Idle states are characterized for a specific system through a set of
+  timing and energy related properties, that underline the HW behaviour
+  triggered upon idle states entry and exit.
+
+  The following diagram depicts the CPU execution phases and related timing
+  properties required to enter and exit an idle state:
+
+  ..__[EXEC]__|__[PREP]__|__[ENTRY]__|__[IDLE]__|__[EXIT]__|__[EXEC]__..
+              |          |           |          |          |
+
+              |<------ entry ------->|
+              |       latency        |
+                                                |<- exit ->|
+                                                |  latency |
+              |<-------- min-residency -------->|
+                         |<-------  wakeup-latency ------->|
+
+      Diagram 1: CPU idle state execution phases
+
+  EXEC:  Normal CPU execution.
+
+  PREP:  Preparation phase before committing the hardware to idle mode
+    like cache flushing. This is abortable on pending wake-up
+    event conditions. The abort latency is assumed to be negligible
+    (i.e. less than the ENTRY + EXIT duration). If aborted, CPU
+    goes back to EXEC. This phase is optional. If not abortable,
+    this should be included in the ENTRY phase instead.
+
+  ENTRY:  The hardware is committed to idle mode. This period must run
+    to completion up to IDLE before anything else can happen.
+
+  IDLE:  This is the actual energy-saving idle period. This may last
+    between 0 and infinite time, until a wake-up event occurs.
+
+  EXIT:  Period during which the CPU is brought back to operational
+    mode (EXEC).
+
+  entry-latency: Worst case latency required to enter the idle state. The
+  exit-latency may be guaranteed only after entry-latency has passed.
+
+  min-residency: Minimum period, including preparation and entry, for a given
+  idle state to be worthwhile energywise.
+
+  wakeup-latency: Maximum delay between the signaling of a wake-up event and the
+  CPU being able to execute normal code again. If not specified, this is assumed
+  to be entry-latency + exit-latency.
+
+  These timing parameters can be used by an OS in different circumstances.
+
+  An idle CPU requires the expected min-residency time to select the most
+  appropriate idle state based on the expected expiry time of the next IRQ
+  (i.e. wake-up) that causes the CPU to return to the EXEC phase.
+
+  An operating system scheduler may need to compute the shortest wake-up delay
+  for CPUs in the system by detecting how long will it take to get a CPU out
+  of an idle state, e.g.:
+
+  wakeup-delay = exit-latency + max(entry-latency - (now - entry-timestamp), 0)
+
+  In other words, the scheduler can make its scheduling decision by selecting
+  (e.g. waking-up) the CPU with the shortest wake-up delay.
+  The wake-up delay must take into account the entry latency if that period
+  has not expired. The abortable nature of the PREP period can be ignored
+  if it cannot be relied upon (e.g. the PREP deadline may occur much sooner than
+  the worst case since it depends on the CPU operating conditions, i.e. caches
+  state).
+
+  An OS has to reliably probe the wakeup-latency since some devices can enforce
+  latency constraint guarantees to work properly, so the OS has to detect the
+  worst case wake-up latency it can incur if a CPU is allowed to enter an
+  idle state, and possibly to prevent that to guarantee reliable device
+  functioning.
+
+  The min-residency time parameter deserves further explanation since it is
+  expressed in time units but must factor in energy consumption coefficients.
+
+  The energy consumption of a cpu when it enters a power state can be roughly
+  characterised by the following graph:
+
+                 |
+                 |
+                 |
+             e   |
+             n   |                                      /---
+             e   |                               /------
+             r   |                        /------
+             g   |                  /-----
+             y   |           /------
+                 |       ----
+                 |      /|
+                 |     / |
+                 |    /  |
+                 |   /   |
+                 |  /    |
+                 | /     |
+                 |/      |
+            -----|-------+----------------------------------
+                0|       1                              time(ms)
+
+      Graph 1: Energy vs time example
+
+  The graph is split in two parts delimited by time 1ms on the X-axis.
+  The graph curve with X-axis values = { x | 0 < x < 1ms } has a steep slope
+  and denotes the energy costs incurred while entering and leaving the idle
+  state.
+  The graph curve in the area delimited by X-axis values = {x | x > 1ms } has
+  shallower slope and essentially represents the energy consumption of the idle
+  state.
+
+  min-residency is defined for a given idle state as the minimum expected
+  residency time for a state (inclusive of preparation and entry) after
+  which choosing that state become the most energy efficient option. A good
+  way to visualise this, is by taking the same graph above and comparing some
+  states energy consumptions plots.
+
+  For sake of simplicity, let's consider a system with two idle states IDLE1,
+  and IDLE2:
+
+            |
+            |
+            |
+            |                                                  /-- IDLE1
+         e  |                                              /---
+         n  |                                         /----
+         e  |                                     /---
+         r  |                                /-----/--------- IDLE2
+         g  |                    /-------/---------
+         y  |        ------------    /---|
+            |       /           /----    |
+            |      /        /---         |
+            |     /    /----             |
+            |    / /---                  |
+            |   ---                      |
+            |  /                         |
+            | /                          |
+            |/                           |                  time
+         ---/----------------------------+------------------------
+            |IDLE1-energy < IDLE2-energy | IDLE2-energy < IDLE1-energy
+                                         |
+                                  IDLE2-min-residency
+
+      Graph 2: idle states min-residency example
+
+  In graph 2 above, that takes into account idle states entry/exit energy
+  costs, it is clear that if the idle state residency time (i.e. time till next
+  wake-up IRQ) is less than IDLE2-min-residency, IDLE1 is the better idle state
+  choice energywise.
+
+  This is mainly down to the fact that IDLE1 entry/exit energy costs are lower
+  than IDLE2.
+
+  However, the lower power consumption (i.e. shallower energy curve slope) of
+  idle state IDLE2 implies that after a suitable time, IDLE2 becomes more energy
+  efficient.
+
+  The time at which IDLE2 becomes more energy efficient than IDLE1 (and other
+  shallower states in a system with multiple idle states) is defined
+  IDLE2-min-residency and corresponds to the time when energy consumption of
+  IDLE1 and IDLE2 states breaks even.
+
+  The definitions provided in this section underpin the idle states
+  properties specification that is the subject of the following sections.
+
+  ===========================================
+  3 - idle-states node
+  ===========================================
+
+  ARM processor idle states are defined within the idle-states node, which is
+  a direct child of the cpus node [1] and provides a container where the
+  processor idle states, defined as device tree nodes, are listed.
+
+  On ARM systems, it is a container of processor idle states nodes. If the
+  system does not provide CPU power management capabilities, or the processor
+  just supports idle_standby, an idle-states node is not required.
+
+  ===========================================
+  4 - References
+  ===========================================
+
+  [1] ARM Linux Kernel documentation - CPUs bindings
+      Documentation/devicetree/bindings/arm/cpus.yaml
+
+  [2] ARM Linux Kernel documentation - PSCI bindings
+      Documentation/devicetree/bindings/arm/psci.yaml
+
+  [3] ARM Server Base System Architecture (SBSA)
+      http://infocenter.arm.com/help/index.jsp
+
+  [4] ARM Architecture Reference Manuals
+      http://infocenter.arm.com/help/index.jsp
+
+  [6] ARM Linux Kernel documentation - Booting AArch64 Linux
+      Documentation/arm64/booting.rst
+
+properties:
+  $nodename:
+    const: idle-states
+
+  entry-method:
+    description: |
+      Usage and definition depend on ARM architecture version.
+
+      On ARM v8 64-bit this property is required.
+      On ARM 32-bit systems this property is optional
+
+      This assumes that the "enable-method" property is set to "psci" in the cpu
+      node[6] that is responsible for setting up CPU idle management in the OS
+      implementation.
+    const: psci
+
+patternProperties:
+  "^(cpu|cluster)-":
+    type: object
+    description: |
+      Each state node represents an idle state description and must be defined
+      as follows.
+
+      The idle state entered by executing the wfi instruction (idle_standby
+      SBSA,[3][4]) is considered standard on all ARM platforms and therefore
+      must not be listed.
+
+      In addition to the properties listed above, a state node may require
+      additional properties specific to the entry-method defined in the
+      idle-states node. Please refer to the entry-method bindings
+      documentation for properties definitions.
+
+    properties:
+      compatible:
+        const: arm,idle-state
+
+      local-timer-stop:
+        description:
+          If present the CPU local timer control logic is
+             lost on state entry, otherwise it is retained.
+        type: boolean
+
+      entry-latency-us:
+        description:
+          Worst case latency in microseconds required to enter the idle state.
+
+      exit-latency-us:
+        description:
+          Worst case latency in microseconds required to exit the idle state.
+          The exit-latency-us duration may be guaranteed only after
+          entry-latency-us has passed.
+
+      min-residency-us:
+        description:
+          Minimum residency duration in microseconds, inclusive of preparation
+          and entry, for this idle state to be considered worthwhile energy wise
+          (refer to section 2 of this document for a complete description).
+
+      wakeup-latency-us:
+        description: |
+          Maximum delay between the signaling of a wake-up event and the CPU
+          being able to execute normal code again. If omitted, this is assumed
+          to be equal to:
+
+            entry-latency-us + exit-latency-us
+
+          It is important to supply this value on systems where the duration of
+          PREP phase (see diagram 1, section 2) is non-neglibigle. In such
+          systems entry-latency-us + exit-latency-us will exceed
+          wakeup-latency-us by this duration.
+
+      idle-state-name:
+        $ref: /schemas/types.yaml#definitions/string
+        description:
+          A string used as a descriptive name for the idle state.
+
+    required:
+      - compatible
+      - entry-latency-us
+      - exit-latency-us
+      - min-residency-us
+
+additionalProperties: false
+
+examples:
+  - |
+
+    cpus {
+        #size-cells = <0>;
+        #address-cells = <2>;
+
+        cpu@0 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x0>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@1 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x1>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@100 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x100>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@101 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x101>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@10000 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x10000>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@10001 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x10001>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@10100 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x10100>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@10101 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a57";
+            reg = <0x0 0x10101>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_0_0 &CPU_SLEEP_0_0
+                   &CLUSTER_RETENTION_0 &CLUSTER_SLEEP_0>;
+        };
+
+        cpu@100000000 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x0>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100000001 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x1>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100000100 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x100>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100000101 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x101>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100010000 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x10000>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100010001 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x10001>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100010100 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x10100>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        cpu@100010101 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a53";
+            reg = <0x1 0x10101>;
+            enable-method = "psci";
+            cpu-idle-states = <&CPU_RETENTION_1_0 &CPU_SLEEP_1_0
+                   &CLUSTER_RETENTION_1 &CLUSTER_SLEEP_1>;
+        };
+
+        idle-states {
+            entry-method = "psci";
+
+            CPU_RETENTION_0_0: cpu-retention-0-0 {
+                compatible = "arm,idle-state";
+                arm,psci-suspend-param = <0x0010000>;
+                entry-latency-us = <20>;
+                exit-latency-us = <40>;
+                min-residency-us = <80>;
+            };
+
+            CLUSTER_RETENTION_0: cluster-retention-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                arm,psci-suspend-param = <0x1010000>;
+                entry-latency-us = <50>;
+                exit-latency-us = <100>;
+                min-residency-us = <250>;
+                wakeup-latency-us = <130>;
+            };
+
+            CPU_SLEEP_0_0: cpu-sleep-0-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                arm,psci-suspend-param = <0x0010000>;
+                entry-latency-us = <250>;
+                exit-latency-us = <500>;
+                min-residency-us = <950>;
+            };
+
+            CLUSTER_SLEEP_0: cluster-sleep-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                arm,psci-suspend-param = <0x1010000>;
+                entry-latency-us = <600>;
+                exit-latency-us = <1100>;
+                min-residency-us = <2700>;
+                wakeup-latency-us = <1500>;
+            };
+
+            CPU_RETENTION_1_0: cpu-retention-1-0 {
+                compatible = "arm,idle-state";
+                arm,psci-suspend-param = <0x0010000>;
+                entry-latency-us = <20>;
+                exit-latency-us = <40>;
+                min-residency-us = <90>;
+            };
+
+            CLUSTER_RETENTION_1: cluster-retention-1 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                arm,psci-suspend-param = <0x1010000>;
+                entry-latency-us = <50>;
+                exit-latency-us = <100>;
+                min-residency-us = <270>;
+                wakeup-latency-us = <100>;
+            };
+
+            CPU_SLEEP_1_0: cpu-sleep-1-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                arm,psci-suspend-param = <0x0010000>;
+                entry-latency-us = <70>;
+                exit-latency-us = <100>;
+                min-residency-us = <300>;
+                wakeup-latency-us = <150>;
+            };
+
+            CLUSTER_SLEEP_1: cluster-sleep-1 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                arm,psci-suspend-param = <0x1010000>;
+                entry-latency-us = <500>;
+                exit-latency-us = <1200>;
+                min-residency-us = <3500>;
+                wakeup-latency-us = <1300>;
+            };
+        };
+    };
+
+  - |
+    // Example 2 (ARM 32-bit, 8-cpu system, two clusters):
+
+    cpus {
+        #size-cells = <0>;
+        #address-cells = <1>;
+
+        cpu@0 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a15";
+            reg = <0x0>;
+            cpu-idle-states = <&cpu_sleep_0_0 &cluster_sleep_0>;
+        };
+
+        cpu@1 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a15";
+            reg = <0x1>;
+            cpu-idle-states = <&cpu_sleep_0_0 &cluster_sleep_0>;
+        };
+
+        cpu@2 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a15";
+            reg = <0x2>;
+            cpu-idle-states = <&cpu_sleep_0_0 &cluster_sleep_0>;
+        };
+
+        cpu@3 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a15";
+            reg = <0x3>;
+            cpu-idle-states = <&cpu_sleep_0_0 &cluster_sleep_0>;
+        };
+
+        cpu@100 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a7";
+            reg = <0x100>;
+            cpu-idle-states = <&cpu_sleep_1_0 &cluster_sleep_1>;
+        };
+
+        cpu@101 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a7";
+            reg = <0x101>;
+            cpu-idle-states = <&cpu_sleep_1_0 &cluster_sleep_1>;
+        };
+
+        cpu@102 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a7";
+            reg = <0x102>;
+            cpu-idle-states = <&cpu_sleep_1_0 &cluster_sleep_1>;
+        };
+
+        cpu@103 {
+            device_type = "cpu";
+            compatible = "arm,cortex-a7";
+            reg = <0x103>;
+            cpu-idle-states = <&cpu_sleep_1_0 &cluster_sleep_1>;
+        };
+
+        idle-states {
+            cpu_sleep_0_0: cpu-sleep-0-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                entry-latency-us = <200>;
+                exit-latency-us = <100>;
+                min-residency-us = <400>;
+                wakeup-latency-us = <250>;
+            };
+
+            cluster_sleep_0: cluster-sleep-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                entry-latency-us = <500>;
+                exit-latency-us = <1500>;
+                min-residency-us = <2500>;
+                wakeup-latency-us = <1700>;
+            };
+
+            cpu_sleep_1_0: cpu-sleep-1-0 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                entry-latency-us = <300>;
+                exit-latency-us = <500>;
+                min-residency-us = <900>;
+                wakeup-latency-us = <600>;
+            };
+
+            cluster_sleep_1: cluster-sleep-1 {
+                compatible = "arm,idle-state";
+                local-timer-stop;
+                entry-latency-us = <800>;
+                exit-latency-us = <2000>;
+                min-residency-us = <6500>;
+                wakeup-latency-us = <2300>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml
index e39d8f02e33c..b5bef5abc281 100644
--- a/Documentation/devicetree/bindings/arm/qcom.yaml
+++ b/Documentation/devicetree/bindings/arm/qcom.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/arm/qcom.yaml#
+$id: http://devicetree.org/schemas/arm/qcom.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: QCOM device tree bindings
diff --git a/Documentation/devicetree/bindings/arm/stm32/mlahb.txt b/Documentation/devicetree/bindings/arm/stm32/mlahb.txt
deleted file mode 100644
index 25307aa1eb9b..000000000000
--- a/Documentation/devicetree/bindings/arm/stm32/mlahb.txt
+++ /dev/null
@@ -1,37 +0,0 @@
-ML-AHB interconnect bindings
-
-These bindings describe the STM32 SoCs ML-AHB interconnect bus which connects
-a Cortex-M subsystem with dedicated memories.
-The MCU SRAM and RETRAM memory parts can be accessed through different addresses
-(see "RAM aliases" in [1]) using different buses (see [2]) : balancing the
-Cortex-M firmware accesses among those ports allows to tune the system
-performance.
-
-[1]: https://www.st.com/resource/en/reference_manual/dm00327659.pdf
-[2]: https://wiki.st.com/stm32mpu/wiki/STM32MP15_RAM_mapping
-
-Required properties:
-- compatible: should be "simple-bus"
-- dma-ranges: describes memory addresses translation between the local CPU and
-	   the remote Cortex-M processor. Each memory region, is declared with
-	   3 parameters:
-		 - param 1: device base address (Cortex-M processor address)
-		 - param 2: physical base address (local CPU address)
-		 - param 3: size of the memory region.
-
-The Cortex-M remote processor accessed via the mlahb interconnect is described
-by a child node.
-
-Example:
-mlahb {
-	compatible = "simple-bus";
-	#address-cells = <1>;
-	#size-cells = <1>;
-	dma-ranges = <0x00000000 0x38000000 0x10000>,
-		     <0x10000000 0x10000000 0x60000>,
-		     <0x30000000 0x30000000 0x60000>;
-
-	m4_rproc: m4@10000000 {
-		...
-	};
-};
diff --git a/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
new file mode 100644
index 000000000000..68917bb7c7e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/stm32/st,mlahb.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/arm/stm32/st,mlahb.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: STMicroelectronics STM32 ML-AHB interconnect bindings
+
+maintainers:
+  - Fabien Dessenne <fabien.dessenne@st.com>
+  - Arnaud Pouliquen <arnaud.pouliquen@st.com>
+
+description: |
+  These bindings describe the STM32 SoCs ML-AHB interconnect bus which connects
+  a Cortex-M subsystem with dedicated memories. The MCU SRAM and RETRAM memory
+  parts can be accessed through different addresses (see "RAM aliases" in [1])
+  using different buses (see [2]): balancing the Cortex-M firmware accesses
+  among those ports allows to tune the system performance.
+  [1]: https://www.st.com/resource/en/reference_manual/dm00327659.pdf
+  [2]: https://wiki.st.com/stm32mpu/wiki/STM32MP15_RAM_mapping
+
+allOf:
+ - $ref: /schemas/simple-bus.yaml#
+
+properties:
+  compatible:
+    contains:
+      enum:
+        - st,mlahb
+
+  dma-ranges:
+    description: |
+      Describe memory addresses translation between the local CPU and the
+      remote Cortex-M processor. Each memory region, is declared with
+      3 parameters:
+      - param 1: device base address (Cortex-M processor address)
+      - param 2: physical base address (local CPU address)
+      - param 3: size of the memory region.
+    maxItems: 3
+
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 1
+
+required:
+  - compatible
+  - '#address-cells'
+  - '#size-cells'
+  - dma-ranges
+
+examples:
+  - |
+    mlahb: ahb {
+      compatible = "st,mlahb", "simple-bus";
+      #address-cells = <1>;
+      #size-cells = <1>;
+      reg = <0x10000000 0x40000>;
+      ranges;
+      dma-ranges = <0x00000000 0x38000000 0x10000>,
+                   <0x10000000 0x10000000 0x60000>,
+                   <0x30000000 0x30000000 0x60000>;
+
+      m4_rproc: m4@10000000 {
+       reg = <0x10000000 0x40000>;
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml b/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml
new file mode 100644
index 000000000000..0dedf94c8578
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/stm32/st,stm32-syscon.yaml
@@ -0,0 +1,41 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/arm/stm32/st,stm32-syscon.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: STMicroelectronics STM32 Platforms System Controller bindings
+
+maintainers:
+  - Alexandre Torgue <alexandre.torgue@st.com>
+  - Christophe Roullier <christophe.roullier@st.com>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+        - enum:
+          - st,stm32mp157-syscfg
+        - const: syscon
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+
+examples:
+  - |
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    syscfg: syscon@50020000 {
+        compatible = "st,stm32mp157-syscfg", "syscon";
+        reg = <0x50020000 0x400>;
+        clocks = <&rcc SYSCFG>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/arm/stm32/stm32-syscon.txt b/Documentation/devicetree/bindings/arm/stm32/stm32-syscon.txt
deleted file mode 100644
index c92d411fd023..000000000000
--- a/Documentation/devicetree/bindings/arm/stm32/stm32-syscon.txt
+++ /dev/null
@@ -1,16 +0,0 @@
-STMicroelectronics STM32 Platforms System Controller
-
-Properties:
-   - compatible : should contain two values. First value must be :
-                 - " st,stm32mp157-syscfg " - for stm32mp157 based SoCs,
-                 second value must be always "syscon".
-   - reg : offset and length of the register set.
-   - clocks: phandle to the syscfg clock
-
- Example:
-         syscfg: syscon@50020000 {
-                 compatible = "st,stm32mp157-syscfg", "syscon";
-                 reg = <0x50020000 0x400>;
-                 clocks = <&rcc SYSCFG>;
-         };
-
diff --git a/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml b/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml
new file mode 100644
index 000000000000..9370e64992dd
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/sunxi/allwinner,sun4i-a10-mbus.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/sunxi/allwinner,sun4i-a10-mbus.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner Memory Bus (MBUS) controller
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The MBUS controller drives the MBUS that other devices in the SoC
+  will use to perform DMA. It also has a register interface that
+  allows to monitor and control the bandwidth and priorities for
+  masters on that bus.
+
+  Each device having to perform their DMA through the MBUS must have
+  the interconnects and interconnect-names properties set to the MBUS
+  controller and with "dma-mem" as the interconnect name.
+
+properties:
+  "#interconnect-cells":
+    const: 1
+    description:
+      The content of the cell is the MBUS ID.
+
+  compatible:
+    enum:
+      - allwinner,sun5i-a13-mbus
+      - allwinner,sun8i-h3-mbus
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  dma-ranges:
+    description:
+      See section 2.3.9 of the DeviceTree Specification.
+
+required:
+  - "#interconnect-cells"
+  - compatible
+  - reg
+  - clocks
+  - dma-ranges
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun5i-ccu.h>
+
+    mbus: dram-controller@1c01000 {
+        compatible = "allwinner,sun5i-a13-mbus";
+        reg = <0x01c01000 0x1000>;
+        clocks = <&ccu CLK_MBUS>;
+        dma-ranges = <0x00000000 0x40000000 0x20000000>;
+        #interconnect-cells = <1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/arm/sunxi/sunxi-mbus.txt b/Documentation/devicetree/bindings/arm/sunxi/sunxi-mbus.txt
deleted file mode 100644
index 2005bb486705..000000000000
--- a/Documentation/devicetree/bindings/arm/sunxi/sunxi-mbus.txt
+++ /dev/null
@@ -1,37 +0,0 @@
-Allwinner Memory Bus (MBUS) controller
-
-The MBUS controller drives the MBUS that other devices in the SoC will
-use to perform DMA. It also has a register interface that allows to
-monitor and control the bandwidth and priorities for masters on that
-bus.
-
-Required properties:
- - compatible: Must be one of:
-	- allwinner,sun5i-a13-mbus
-	- allwinner,sun8i-h3-mbus
- - reg: Offset and length of the register set for the controller
- - clocks: phandle to the clock driving the controller
- - dma-ranges: See section 2.3.9 of the DeviceTree Specification
- - #interconnect-cells: Must be one, with the argument being the MBUS
-   port ID
-
-Each device having to perform their DMA through the MBUS must have the
-interconnects and interconnect-names properties set to the MBUS
-controller and with "dma-mem" as the interconnect name.
-
-Example:
-
-mbus: dram-controller@1c01000 {
-	compatible = "allwinner,sun5i-a13-mbus";
-	reg = <0x01c01000 0x1000>;
-	clocks = <&ccu CLK_MBUS>;
-	dma-ranges = <0x00000000 0x40000000 0x20000000>;
-	#interconnect-cells = <1>;
-};
-
-fe0: display-frontend@1e00000 {
-	compatible = "allwinner,sun5i-a13-display-frontend";
-	...
-	interconnects = <&mbus 19>;
-	interconnect-names = "dma-mem";
-};
diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt
index 55c6fab1b373..77091a277642 100644
--- a/Documentation/devicetree/bindings/ata/ahci-platform.txt
+++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt
@@ -9,8 +9,6 @@ PHYs.
 
 Required properties:
 - compatible        : compatible string, one of:
-  - "allwinner,sun4i-a10-ahci"
-  - "allwinner,sun8i-r40-ahci"
   - "brcm,iproc-ahci"
   - "hisilicon,hisi-ahci"
   - "cavium,octeon-7130-ahci"
@@ -45,8 +43,6 @@ Required properties when using sub-nodes:
 - #address-cells    : number of cells to encode an address
 - #size-cells       : number of cells representing the size of an address
 
-For allwinner,sun8i-r40-ahci, the reset property must be present.
-
 Sub-nodes required properties:
 - reg		    : the port number
 And at least one of the following properties:
@@ -60,14 +56,6 @@ Examples:
 		interrupts = <115>;
         };
 
-	ahci: sata@1c18000 {
-		compatible = "allwinner,sun4i-a10-ahci";
-		reg = <0x01c18000 0x1000>;
-		interrupts = <56>;
-		clocks = <&pll6 0>, <&ahb_gates 25>;
-		target-supply = <&reg_ahci_5v>;
-	};
-
 With sub-nodes:
 	sata@f7e90000 {
 		compatible = "marvell,berlin2q-achi", "generic-ahci";
diff --git a/Documentation/devicetree/bindings/ata/allwinner,sun4i-a10-ahci.yaml b/Documentation/devicetree/bindings/ata/allwinner,sun4i-a10-ahci.yaml
new file mode 100644
index 000000000000..cb530b46beff
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/allwinner,sun4i-a10-ahci.yaml
@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/allwinner,sun4i-a10-ahci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 AHCI SATA Controller bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    const: allwinner,sun4i-a10-ahci
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: AHCI Bus Clock
+      - description: AHCI Module Clock
+
+  interrupts:
+    maxItems: 1
+
+  target-supply:
+    description: Regulator for SATA target power
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    ahci: sata@1c18000 {
+        compatible = "allwinner,sun4i-a10-ahci";
+        reg = <0x01c18000 0x1000>;
+        interrupts = <56>;
+        clocks = <&pll6 0>, <&ahb_gates 25>;
+        target-supply = <&reg_ahci_5v>;
+    };
diff --git a/Documentation/devicetree/bindings/ata/allwinner,sun8i-r40-ahci.yaml b/Documentation/devicetree/bindings/ata/allwinner,sun8i-r40-ahci.yaml
new file mode 100644
index 000000000000..e6b42a113ff1
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/allwinner,sun8i-r40-ahci.yaml
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/allwinner,sun8i-r40-ahci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner R40 AHCI SATA Controller bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    const: allwinner,sun8i-r40-ahci
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: AHCI Bus Clock
+      - description: AHCI Module Clock
+
+  interrupts:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: ahci
+
+  ahci-supply:
+    description: Regulator for the AHCI controller
+
+  phy-supply:
+    description: Regulator for the SATA PHY power
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/sun8i-r40-ccu.h>
+    #include <dt-bindings/reset/sun8i-r40-ccu.h>
+
+    ahci: sata@1c18000 {
+        compatible = "allwinner,sun8i-r40-ahci";
+        reg = <0x01c18000 0x1000>;
+        interrupts = <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_SATA>, <&ccu CLK_SATA>;
+        resets = <&ccu RST_BUS_SATA>;
+        reset-names = "ahci";
+        ahci-supply = <&reg_dldo4>;
+        phy-supply = <&reg_eldo3>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/ata/faraday,ftide010.txt b/Documentation/devicetree/bindings/ata/faraday,ftide010.txt
deleted file mode 100644
index a0c64a29104d..000000000000
--- a/Documentation/devicetree/bindings/ata/faraday,ftide010.txt
+++ /dev/null
@@ -1,38 +0,0 @@
-* Faraday Technology FTIDE010 PATA controller
-
-This controller is the first Faraday IDE interface block, used in the
-StorLink SL2312 and SL3516, later known as the Cortina Systems Gemini
-platform. The controller can do PIO modes 0 through 4, Multi-word DMA
-(MWDM)modes 0 through 2 and Ultra DMA modes 0 through 6.
-
-On the Gemini platform, this PATA block is accompanied by a PATA to
-SATA bridge in order to support SATA. This is why a phandle to that
-controller is compulsory on that platform.
-
-The timing properties are unique per-SoC, not per-board.
-
-Required properties:
-- compatible: should be one of
-  "cortina,gemini-pata", "faraday,ftide010"
-  "faraday,ftide010"
-- interrupts: interrupt for the block
-- reg: registers and size for the block
-
-Optional properties:
-- clocks: a SoC clock running the peripheral.
-- clock-names: should be set to "PCLK" for the peripheral clock.
-
-Required properties for "cortina,gemini-pata" compatible:
-- sata: a phande to the Gemini PATA to SATA bridge, see
-  cortina,gemini-sata-bridge.txt for details.
-
-Example:
-
-ata@63000000 {
-	compatible = "cortina,gemini-pata", "faraday,ftide010";
-	reg = <0x63000000 0x100>;
-	interrupts = <4 IRQ_TYPE_EDGE_RISING>;
-	clocks = <&gcc GEMINI_CLK_GATE_IDE>;
-	clock-names = "PCLK";
-	sata = <&sata>;
-};
diff --git a/Documentation/devicetree/bindings/ata/faraday,ftide010.yaml b/Documentation/devicetree/bindings/ata/faraday,ftide010.yaml
new file mode 100644
index 000000000000..bfc6357476fd
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/faraday,ftide010.yaml
@@ -0,0 +1,89 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/faraday,ftide010.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Faraday Technology FTIDE010 PATA controller
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description: |
+  This controller is the first Faraday IDE interface block, used in the
+  StorLink SL3512 and SL3516, later known as the Cortina Systems Gemini
+  platform. The controller can do PIO modes 0 through 4, Multi-word DMA
+  (MWDM) modes 0 through 2 and Ultra DMA modes 0 through 6.
+
+  On the Gemini platform, this PATA block is accompanied by a PATA to
+  SATA bridge in order to support SATA. This is why a phandle to that
+  controller is compulsory on that platform.
+
+  The timing properties are unique per-SoC, not per-board.
+
+properties:
+  compatible:
+    oneOf:
+      - const: faraday,ftide010
+      - items:
+        - const: cortina,gemini-pata
+        - const: faraday,ftide010
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+
+  clock-names:
+    const: PCLK
+
+  sata:
+    description:
+      phandle to the Gemini PATA to SATA bridge, if available
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+allOf:
+  - $ref: pata-common.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: cortina,gemini-pata
+
+    then:
+      required:
+        - sata
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/clock/cortina,gemini-clock.h>
+
+    ide@63000000 {
+      compatible = "cortina,gemini-pata", "faraday,ftide010";
+      reg = <0x63000000 0x100>;
+      interrupts = <4 IRQ_TYPE_EDGE_RISING>;
+      clocks = <&gcc GEMINI_CLK_GATE_IDE>;
+      clock-names = "PCLK";
+      sata = <&sata>;
+      #address-cells = <1>;
+      #size-cells = <0>;
+      ide-port@0 {
+        reg = <0>;
+      };
+      ide-port@1 {
+        reg = <1>;
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/ata/pata-common.yaml b/Documentation/devicetree/bindings/ata/pata-common.yaml
new file mode 100644
index 000000000000..fc5ebbe7108d
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/pata-common.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/pata-common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Common Properties for Parallel AT attachment (PATA) controllers
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description: |
+  This document defines device tree properties common to most Parallel
+  ATA (PATA, also known as IDE) AT attachment storage devices.
+  It doesn't constitue a device tree binding specification by itself but is
+  meant to be referenced by device tree bindings.
+
+  The PATA (IDE) controller-specific device tree bindings are responsible for
+  defining whether each property is required or optional.
+
+properties:
+  $nodename:
+    pattern: "^ide(@.*)?$"
+    description:
+      Specifies the host controller node. PATA host controller nodes are named
+      "ide".
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+patternProperties:
+  "^ide-port@[0-1]$":
+    description: |
+      DT nodes for ports connected on the PATA host. The master drive will have
+      ID number 0 and the slave drive will have ID number 1. The PATA port
+      nodes will be named "ide-port".
+    type: object
+
+    properties:
+      reg:
+        minimum: 0
+        maximum: 1
+        description:
+          The ID number of the drive port, 0 for the master port and 1 for the
+          slave port.
+
+...
diff --git a/Documentation/devicetree/bindings/ata/sata-common.yaml b/Documentation/devicetree/bindings/ata/sata-common.yaml
new file mode 100644
index 000000000000..6783a4dec6b5
--- /dev/null
+++ b/Documentation/devicetree/bindings/ata/sata-common.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/ata/sata-common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Common Properties for Serial AT attachment (SATA) controllers
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description: |
+  This document defines device tree properties common to most Serial
+  AT attachment (SATA) storage devices. It doesn't constitute a device tree
+  binding specification by itself but is meant to be referenced by device
+  tree bindings.
+
+  The SATA controller-specific device tree bindings are responsible for
+  defining whether each property is required or optional.
+
+properties:
+  $nodename:
+    pattern: "^sata(@.*)?$"
+    description:
+      Specifies the host controller node. SATA host controller nodes are named
+      "sata"
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+patternProperties:
+  "^sata-port@[0-9a-e]$":
+    description: |
+      DT nodes for ports connected on the SATA host. The SATA port
+      nodes will be named "sata-port".
+    type: object
+
+    properties:
+      reg:
+        minimum: 0
+        maximum: 14
+        description:
+          The ID number of the drive port SATA can potentially use a port
+          multiplier making it possible to connect up to 15 disks to a single
+          SATA port.
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ahb-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ahb-clk.yaml
new file mode 100644
index 000000000000..558db4b6ed17
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ahb-clk.yaml
@@ -0,0 +1,108 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-ahb-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 AHB Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-ahb-clk
+      - allwinner,sun6i-a31-ahb1-clk
+      - allwinner,sun8i-h3-ahb2-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun4i-a10-ahb-clk
+
+    then:
+      properties:
+        clocks:
+          maxItems: 1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun6i-a31-ahb1-clk
+
+    then:
+      properties:
+        clocks:
+          maxItems: 4
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun8i-h3-ahb2-clk
+
+    then:
+      properties:
+        clocks:
+          maxItems: 2
+
+examples:
+  - |
+    ahb@1c20054 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-ahb-clk";
+        reg = <0x01c20054 0x4>;
+        clocks = <&axi>;
+        clock-output-names = "ahb";
+    };
+
+  - |
+    ahb1@1c20054 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun6i-a31-ahb1-clk";
+        reg = <0x01c20054 0x4>;
+        clocks = <&osc32k>, <&osc24M>, <&axi>, <&pll6 0>;
+        clock-output-names = "ahb1";
+    };
+
+  - |
+    ahb2_clk@1c2005c {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun8i-h3-ahb2-clk";
+        reg = <0x01c2005c 0x4>;
+        clocks = <&ahb1>, <&pll6d2>;
+        clock-output-names = "ahb2";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-apb0-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-apb0-clk.yaml
new file mode 100644
index 000000000000..b1e3d739beb2
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-apb0-clk.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-apb0-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 APB0 Bus Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-apb0-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    apb0@1c20054 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-apb0-clk";
+        reg = <0x01c20054 0x4>;
+        clocks = <&ahb>;
+        clock-output-names = "apb0";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-apb1-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-apb1-clk.yaml
new file mode 100644
index 000000000000..51b7a6d4ea54
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-apb1-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-apb1-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 APB1 Bus Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-apb1-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20058 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-apb1-clk";
+        reg = <0x01c20058 0x4>;
+        clocks = <&osc24M>, <&pll6 1>, <&osc32k>;
+        clock-output-names = "apb1";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-axi-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-axi-clk.yaml
new file mode 100644
index 000000000000..d801158e15de
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-axi-clk.yaml
@@ -0,0 +1,61 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-axi-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 AXI Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-axi-clk
+      - allwinner,sun8i-a23-axi-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    axi@1c20054 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-axi-clk";
+        reg = <0x01c20054 0x4>;
+        clocks = <&cpu>;
+        clock-output-names = "axi";
+    };
+
+  - |
+    axi_clk@1c20050 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun8i-a23-axi-clk";
+        reg = <0x01c20050 0x4>;
+        clocks = <&cpu>;
+        clock-output-names = "axi";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-cpu-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-cpu-clk.yaml
new file mode 100644
index 000000000000..0dfafba1a168
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-cpu-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-cpu-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 CPU Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-cpu-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    cpu@1c20054 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-cpu-clk";
+        reg = <0x01c20054 0x4>;
+        clocks = <&osc32k>, <&osc24M>, <&pll1>, <&dummy>;
+        clock-output-names = "cpu";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-display-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-display-clk.yaml
new file mode 100644
index 000000000000..7484a7ab7dea
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-display-clk.yaml
@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-display-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  "#reset-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-display-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20104 {
+        #clock-cells = <0>;
+        #reset-cells = <0>;
+        compatible = "allwinner,sun4i-a10-display-clk";
+        reg = <0x01c20104 0x4>;
+        clocks = <&pll3>, <&pll7>, <&pll5 1>;
+        clock-output-names = "de-be";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-gates-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-gates-clk.yaml
new file mode 100644
index 000000000000..ed1b2126a81b
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-gates-clk.yaml
@@ -0,0 +1,152 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-gates-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Bus Gates Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      This additional argument passed to that clock is the offset of
+      the bit controlling this particular gate in the register.
+
+  compatible:
+    oneOf:
+      - const: allwinner,sun4i-a10-gates-clk
+      - const: allwinner,sun4i-a10-axi-gates-clk
+      - const: allwinner,sun4i-a10-ahb-gates-clk
+      - const: allwinner,sun5i-a10s-ahb-gates-clk
+      - const: allwinner,sun5i-a13-ahb-gates-clk
+      - const: allwinner,sun7i-a20-ahb-gates-clk
+      - const: allwinner,sun6i-a31-ahb1-gates-clk
+      - const: allwinner,sun8i-a23-ahb1-gates-clk
+      - const: allwinner,sun9i-a80-ahb0-gates-clk
+      - const: allwinner,sun9i-a80-ahb1-gates-clk
+      - const: allwinner,sun9i-a80-ahb2-gates-clk
+      - const: allwinner,sun4i-a10-apb0-gates-clk
+      - const: allwinner,sun5i-a10s-apb0-gates-clk
+      - const: allwinner,sun5i-a13-apb0-gates-clk
+      - const: allwinner,sun7i-a20-apb0-gates-clk
+      - const: allwinner,sun9i-a80-apb0-gates-clk
+      - const: allwinner,sun8i-a83t-apb0-gates-clk
+      - const: allwinner,sun4i-a10-apb1-gates-clk
+      - const: allwinner,sun5i-a13-apb1-gates-clk
+      - const: allwinner,sun5i-a10s-apb1-gates-clk
+      - const: allwinner,sun6i-a31-apb1-gates-clk
+      - const: allwinner,sun7i-a20-apb1-gates-clk
+      - const: allwinner,sun8i-a23-apb1-gates-clk
+      - const: allwinner,sun9i-a80-apb1-gates-clk
+      - const: allwinner,sun6i-a31-apb2-gates-clk
+      - const: allwinner,sun8i-a23-apb2-gates-clk
+      - const: allwinner,sun8i-a83t-bus-gates-clk
+      - const: allwinner,sun9i-a80-apbs-gates-clk
+      - const: allwinner,sun4i-a10-dram-gates-clk
+
+      - items:
+        - const: allwinner,sun5i-a13-dram-gates-clk
+        - const: allwinner,sun4i-a10-gates-clk
+
+      - items:
+        - const: allwinner,sun8i-h3-apb0-gates-clk
+        - const: allwinner,sun4i-a10-gates-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-indices:
+    minItems: 1
+    maxItems: 64
+
+  clock-output-names:
+    minItems: 1
+    maxItems: 64
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-indices
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c2005c {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun4i-a10-axi-gates-clk";
+        reg = <0x01c2005c 0x4>;
+        clocks = <&axi>;
+        clock-indices = <0>;
+        clock-output-names = "axi_dram";
+    };
+
+  - |
+    clk@1c20060 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun4i-a10-ahb-gates-clk";
+        reg = <0x01c20060 0x8>;
+        clocks = <&ahb>;
+        clock-indices = <0>, <1>,
+                        <2>, <3>,
+                        <4>, <5>, <6>,
+                        <7>, <8>, <9>,
+                        <10>, <11>, <12>,
+                        <13>, <14>, <16>,
+                        <17>, <18>, <20>,
+                        <21>, <22>, <23>,
+                        <24>, <25>, <26>,
+                        <32>, <33>, <34>,
+                        <35>, <36>, <37>,
+                        <40>, <41>, <43>,
+                        <44>, <45>,
+                        <46>, <47>,
+                        <50>, <52>;
+        clock-output-names = "ahb_usb0", "ahb_ehci0",
+                             "ahb_ohci0", "ahb_ehci1",
+                             "ahb_ohci1", "ahb_ss", "ahb_dma",
+                             "ahb_bist", "ahb_mmc0", "ahb_mmc1",
+                             "ahb_mmc2", "ahb_mmc3", "ahb_ms",
+                             "ahb_nand", "ahb_sdram", "ahb_ace",
+                             "ahb_emac", "ahb_ts", "ahb_spi0",
+                             "ahb_spi1", "ahb_spi2", "ahb_spi3",
+                             "ahb_pata", "ahb_sata", "ahb_gps",
+                             "ahb_ve", "ahb_tvd", "ahb_tve0",
+                             "ahb_tve1", "ahb_lcd0", "ahb_lcd1",
+                             "ahb_csi0", "ahb_csi1", "ahb_hdmi",
+                             "ahb_de_be0", "ahb_de_be1",
+                             "ahb_de_fe0", "ahb_de_fe1",
+                             "ahb_mp", "ahb_mali400";
+    };
+
+
+  - |
+    clk@1c20068 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun4i-a10-apb0-gates-clk";
+        reg = <0x01c20068 0x4>;
+        clocks = <&apb0>;
+        clock-indices = <0>, <1>,
+                        <2>, <3>,
+                        <5>, <6>,
+                        <7>, <10>;
+        clock-output-names = "apb0_codec", "apb0_spdif",
+                             "apb0_ac97", "apb0_iis",
+                             "apb0_pio", "apb0_ir0",
+                             "apb0_ir1", "apb0_keypad";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mbus-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mbus-clk.yaml
new file mode 100644
index 000000000000..18f131e262b4
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mbus-clk.yaml
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-mbus-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 MBUS Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun5i-a13-mbus-clk
+      - allwinner,sun8i-a23-mbus-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c2015c {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun5i-a13-mbus-clk";
+        reg = <0x01c2015c 0x4>;
+        clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
+        clock-output-names = "mbus";
+    };
+
+  - |
+    clk@1c2015c {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun8i-a23-mbus-clk";
+        reg = <0x01c2015c 0x4>;
+        clocks = <&osc24M>, <&pll6 1>, <&pll5>;
+        clock-output-names = "mbus";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mmc-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mmc-clk.yaml
new file mode 100644
index 000000000000..5199285a661a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mmc-clk.yaml
@@ -0,0 +1,87 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-mmc-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Module 1 Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      There is three different outputs: the main clock, with the ID 0,
+      and the output and sample clocks, with the IDs 1 and 2,
+      respectively.
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-mmc-clk
+      - allwinner,sun9i-a80-mmc-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 2
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 3
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun4i-a10-mmc-clk
+
+then:
+  properties:
+    clocks:
+      maxItems: 3
+
+else:
+  properties:
+    clocks:
+      maxItems: 2
+
+examples:
+  - |
+    clk@1c20088 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun4i-a10-mmc-clk";
+        reg = <0x01c20088 0x4>;
+        clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
+        clock-output-names = "mmc0",
+                             "mmc0_output",
+                             "mmc0_sample";
+    };
+
+  - |
+    clk@6000410 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun9i-a80-mmc-clk";
+        reg = <0x06000410 0x4>;
+        clocks = <&osc24M>, <&pll4>;
+        clock-output-names = "mmc0", "mmc0_output",
+                             "mmc0_sample";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mod0-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mod0-clk.yaml
new file mode 100644
index 000000000000..3e2abe3e67c1
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mod0-clk.yaml
@@ -0,0 +1,80 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-mod0-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Module 0 Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun4i-a10-mod0-clk
+          - allwinner,sun9i-a80-mod0-clk
+
+  # The PRCM on the A31 and A23 will have the reg property missing,
+  # since it's set at the upper level node, and will be validated by
+  # PRCM's schema. Make sure we only validate standalone nodes.
+  required:
+    - compatible
+    - reg
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-mod0-clk
+      - allwinner,sun9i-a80-mod0-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    # On the A80, the PRCM mod0 clocks have 2 parents.
+    minItems: 2
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20080 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-mod0-clk";
+        reg = <0x01c20080 0x4>;
+        clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
+        clock-output-names = "nand";
+    };
+
+  - |
+    clk@8001454 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-mod0-clk";
+        reg = <0x08001454 0x4>;
+        clocks = <&osc32k>, <&osc24M>;
+        clock-output-names = "r_ir";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mod1-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mod1-clk.yaml
new file mode 100644
index 000000000000..7ddb55c75cff
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-mod1-clk.yaml
@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-mod1-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Module 1 Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-mod1-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun4i-a10-pll2.h>
+
+    clk@1c200c0 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-mod1-clk";
+        reg = <0x01c200c0 0x4>;
+        clocks = <&pll2 SUN4I_A10_PLL2_8X>,
+                 <&pll2 SUN4I_A10_PLL2_4X>,
+                 <&pll2 SUN4I_A10_PLL2_2X>,
+                 <&pll2 SUN4I_A10_PLL2_1X>;
+        clock-output-names = "spdif";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml
new file mode 100644
index 000000000000..69cfa4a3d562
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-osc-clk.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-osc-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Gatable Oscillator Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-osc-clk
+
+  reg:
+    maxItems: 1
+
+  clock-frequency:
+    description: >
+      Frequency of the main oscillator.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clock-frequency
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    osc24M: clk@01c20050 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-osc-clk";
+        reg = <0x01c20050 0x4>;
+        clock-frequency = <24000000>;
+        clock-output-names = "osc24M";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll1-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll1-clk.yaml
new file mode 100644
index 000000000000..e9c4cf834aa7
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll1-clk.yaml
@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-pll1-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 CPU PLL Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-pll1-clk
+      - allwinner,sun6i-a31-pll1-clk
+      - allwinner,sun8i-a23-pll1-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20000 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-pll1";
+        reg = <0x01c20000 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "osc24M";
+    };
+
+  - |
+    clk@1c20000 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun6i-a31-pll1-clk";
+        reg = <0x01c20000 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "pll1";
+    };
+
+  - |
+    clk@1c20000 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun8i-a23-pll1-clk";
+        reg = <0x01c20000 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "pll1";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll3-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll3-clk.yaml
new file mode 100644
index 000000000000..4b80a42fb3da
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll3-clk.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-pll3-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Video PLL Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-pll3-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20010 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-pll3-clk";
+        reg = <0x01c20010 0x4>;
+        clocks = <&osc3M>;
+        clock-output-names = "pll3";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll5-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll5-clk.yaml
new file mode 100644
index 000000000000..415bd77de53d
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll5-clk.yaml
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-pll5-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 DRAM PLL Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The first output is the DRAM clock output, the second is meant
+      for peripherals on the SoC.
+
+  compatible:
+    const: allwinner,sun4i-a10-pll5-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 2
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20020 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun4i-a10-pll5-clk";
+        reg = <0x01c20020 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "pll5_ddr", "pll5_other";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll6-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll6-clk.yaml
new file mode 100644
index 000000000000..ec5652f76027
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-pll6-clk.yaml
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-pll6-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Peripheral PLL Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The first output is the SATA clock output, the second is the
+      regular PLL output, the third is a PLL output at twice the rate.
+
+  compatible:
+    const: allwinner,sun4i-a10-pll6-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 3
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20028 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun4i-a10-pll6-clk";
+        reg = <0x01c20028 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "pll6_sata", "pll6_other", "pll6";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-tcon-ch0-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-tcon-ch0-clk.yaml
new file mode 100644
index 000000000000..0a335c615efd
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-tcon-ch0-clk.yaml
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-tcon-ch0-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 TCON Channel 0 Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  "#reset-cells":
+    const: 1
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-tcon-ch0-clk
+      - allwinner,sun4i-a10-tcon-ch1-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun4i-a10-tcon-ch0-clk
+
+then:
+  required:
+    - "#reset-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20118 {
+        #clock-cells = <0>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun4i-a10-tcon-ch0-clk";
+        reg = <0x01c20118 0x4>;
+        clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+        clock-output-names = "tcon-ch0-sclk";
+    };
+
+  - |
+    clk@1c2012c {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun4i-a10-tcon-ch1-clk";
+        reg = <0x01c2012c 0x4>;
+        clocks = <&pll3>, <&pll7>, <&pll3x2>, <&pll7x2>;
+        clock-output-names = "tcon-ch1-sclk";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-usb-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-usb-clk.yaml
new file mode 100644
index 000000000000..cd95d25bfe7c
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-usb-clk.yaml
@@ -0,0 +1,166 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-usb-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 USB Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The additional ID argument passed to the clock shall refer to
+      the index of the output.
+
+  "#reset-cells":
+    const: 1
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-usb-clk
+      - allwinner,sun5i-a13-usb-clk
+      - allwinner,sun6i-a31-usb-clk
+      - allwinner,sun8i-a23-usb-clk
+      - allwinner,sun8i-h3-usb-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    minItems: 2
+    maxItems: 8
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun4i-a10-usb-clk
+
+    then:
+      properties:
+        clock-output-names:
+          maxItems: 3
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun5i-a13-usb-clk
+
+    then:
+      properties:
+        clock-output-names:
+          maxItems: 2
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun6i-a31-usb-clk
+
+    then:
+      properties:
+        clock-output-names:
+          maxItems: 6
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun8i-a23-usb-clk
+
+    then:
+      properties:
+        clock-output-names:
+          maxItems: 5
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: allwinner,sun8i-h3-usb-clk
+
+    then:
+      properties:
+        clock-output-names:
+          maxItems: 8
+
+examples:
+  - |
+    clk@1c200cc {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun4i-a10-usb-clk";
+        reg = <0x01c200cc 0x4>;
+        clocks = <&pll6 1>;
+        clock-output-names = "usb_ohci0", "usb_ohci1", "usb_phy";
+    };
+
+  - |
+    clk@1c200cc {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun5i-a13-usb-clk";
+        reg = <0x01c200cc 0x4>;
+        clocks = <&pll6 1>;
+        clock-output-names = "usb_ohci0", "usb_phy";
+    };
+
+  - |
+    clk@1c200cc {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun6i-a31-usb-clk";
+        reg = <0x01c200cc 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "usb_phy0", "usb_phy1", "usb_phy2",
+                             "usb_ohci0", "usb_ohci1",
+                             "usb_ohci2";
+    };
+
+  - |
+    clk@1c200cc {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun8i-a23-usb-clk";
+        reg = <0x01c200cc 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "usb_phy0", "usb_phy1", "usb_hsic",
+                             "usb_hsic_12M", "usb_ohci0";
+    };
+
+  - |
+    clk@1c200cc {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun8i-h3-usb-clk";
+        reg = <0x01c200cc 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "usb_phy0", "usb_phy1",
+                             "usb_phy2", "usb_phy3",
+                             "usb_ohci0", "usb_ohci1",
+                             "usb_ohci2", "usb_ohci3";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ve-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ve-clk.yaml
new file mode 100644
index 000000000000..5dfd0c1c27b4
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun4i-a10-ve-clk.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-ve-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Video Engine Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  "#reset-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun4i-a10-ve-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c2013c {
+        #clock-cells = <0>;
+        #reset-cells = <0>;
+        compatible = "allwinner,sun4i-a10-ve-clk";
+        reg = <0x01c2013c 0x4>;
+        clocks = <&pll4>;
+        clock-output-names = "ve";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun5i-a13-ahb-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun5i-a13-ahb-clk.yaml
new file mode 100644
index 000000000000..99add7991c48
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun5i-a13-ahb-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun5i-a13-ahb-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A13 AHB Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun5i-a13-ahb-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    ahb@1c20054 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun5i-a13-ahb-clk";
+        reg = <0x01c20054 0x4>;
+        clocks = <&axi>, <&cpu>, <&pll6 1>;
+        clock-output-names = "ahb";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun6i-a31-pll6-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun6i-a31-pll6-clk.yaml
new file mode 100644
index 000000000000..5f377205af71
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun6i-a31-pll6-clk.yaml
@@ -0,0 +1,53 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun6i-a31-pll6-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 Peripheral PLL Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The first output is the regular PLL output, the second is a PLL
+      output at twice the rate.
+
+  compatible:
+    const: allwinner,sun6i-a31-pll6-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 2
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20028 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun6i-a31-pll6-clk";
+        reg = <0x01c20028 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "pll6", "pll6x2";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun7i-a20-gmac-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun7i-a20-gmac-clk.yaml
new file mode 100644
index 000000000000..59e5dce1b65a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun7i-a20-gmac-clk.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun7i-a20-gmac-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A20 GMAC TX Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun7i-a20-gmac-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 2
+    description: >
+      The parent clocks shall be fixed rate dummy clocks at 25 MHz and
+      125 MHz, respectively.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20164 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun7i-a20-gmac-clk";
+        reg = <0x01c20164 0x4>;
+        clocks = <&mii_phy_tx_clk>, <&gmac_int_tx_clk>;
+        clock-output-names = "gmac_tx";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun7i-a20-out-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun7i-a20-out-clk.yaml
new file mode 100644
index 000000000000..c745733bcf04
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun7i-a20-out-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun7i-a20-out-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A20 Output Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun7i-a20-out-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 3
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c201f0 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun7i-a20-out-clk";
+        reg = <0x01c201f0 0x4>;
+        clocks = <&osc24M_32k>, <&osc32k>, <&osc24M>;
+        clock-output-names = "clk_out_a";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun8i-h3-bus-gates-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun8i-h3-bus-gates-clk.yaml
new file mode 100644
index 000000000000..3eb2bf65b230
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun8i-h3-bus-gates-clk.yaml
@@ -0,0 +1,103 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun8i-h3-bus-gates-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Bus Gates Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      This additional argument passed to that clock is the offset of
+      the bit controlling this particular gate in the register.
+
+  compatible:
+    const: allwinner,sun8i-h3-bus-gates-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+
+  clock-names:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-indices:
+    minItems: 1
+    maxItems: 64
+
+  clock-output-names:
+    minItems: 1
+    maxItems: 64
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-indices
+  - clock-names
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c20060 {
+        #clock-cells = <1>;
+        compatible = "allwinner,sun8i-h3-bus-gates-clk";
+        reg = <0x01c20060 0x14>;
+        clocks = <&ahb1>, <&ahb2>, <&apb1>, <&apb2>;
+        clock-names = "ahb1", "ahb2", "apb1", "apb2";
+        clock-indices = <5>, <6>, <8>,
+                        <9>, <10>, <13>,
+                        <14>, <17>, <18>,
+                        <19>, <20>,
+                        <21>, <23>,
+                        <24>, <25>,
+                        <26>, <27>,
+                        <28>, <29>,
+                        <30>, <31>, <32>,
+                        <35>, <36>, <37>,
+                        <40>, <41>, <43>,
+                        <44>, <52>, <53>,
+                        <54>, <64>,
+                        <65>, <69>, <72>,
+                        <76>, <77>, <78>,
+                        <96>, <97>, <98>,
+                        <112>, <113>,
+                        <114>, <115>,
+                        <116>, <128>, <135>;
+        clock-output-names = "bus_ce", "bus_dma", "bus_mmc0",
+                             "bus_mmc1", "bus_mmc2", "bus_nand",
+                             "bus_sdram", "bus_gmac", "bus_ts",
+                             "bus_hstimer", "bus_spi0",
+                             "bus_spi1", "bus_otg",
+                             "bus_otg_ehci0", "bus_ehci1",
+                             "bus_ehci2", "bus_ehci3",
+                             "bus_otg_ohci0", "bus_ohci1",
+                             "bus_ohci2", "bus_ohci3", "bus_ve",
+                             "bus_lcd0", "bus_lcd1", "bus_deint",
+                             "bus_csi", "bus_tve", "bus_hdmi",
+                             "bus_de", "bus_gpu", "bus_msgbox",
+                             "bus_spinlock", "bus_codec",
+                             "bus_spdif", "bus_pio", "bus_ths",
+                             "bus_i2s0", "bus_i2s1", "bus_i2s2",
+                             "bus_i2c0", "bus_i2c1", "bus_i2c2",
+                             "bus_uart0", "bus_uart1",
+                             "bus_uart2", "bus_uart3",
+                             "bus_scr", "bus_ephy", "bus_dbg";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-ahb-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-ahb-clk.yaml
new file mode 100644
index 000000000000..d178da90aaec
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-ahb-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-ahb-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 AHB Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun9i-a80-ahb-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@6000060 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun9i-a80-ahb-clk";
+        reg = <0x06000060 0x4>;
+        clocks = <&gt_clk>, <&pll4>, <&pll12>, <&pll12>;
+        clock-output-names = "ahb0";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-apb0-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-apb0-clk.yaml
new file mode 100644
index 000000000000..0351c79bd221
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-apb0-clk.yaml
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-apb0-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 APB0 Bus Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun9i-a80-apb0-clk
+      - allwinner,sun9i-a80-apb1-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 2
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@6000070 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun9i-a80-apb0-clk";
+        reg = <0x06000070 0x4>;
+        clocks = <&osc24M>, <&pll4>;
+        clock-output-names = "apb0";
+    };
+
+  - |
+    clk@6000074 {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun9i-a80-apb1-clk";
+        reg = <0x06000074 0x4>;
+        clocks = <&osc24M>, <&pll4>;
+        clock-output-names = "apb1";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-cpus-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-cpus-clk.yaml
new file mode 100644
index 000000000000..24d5b2f1a314
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-cpus-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-cpus-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 CPUS Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun9i-a80-cpus-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@8001410 {
+        compatible = "allwinner,sun9i-a80-cpus-clk";
+        reg = <0x08001410 0x4>;
+        #clock-cells = <0>;
+        clocks = <&osc32k>, <&osc24M>, <&pll4>, <&pll3>;
+        clock-output-names = "cpus";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml
new file mode 100644
index 000000000000..07f38def7dc3
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-gt-clk.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-gt-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 GT Bus Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun9i-a80-gt-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 4
+    description: >
+      The parent order must match the hardware programming order.
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@0600005c {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun9i-a80-gt-clk";
+        reg = <0x0600005c 0x4>;
+        clocks = <&osc24M>, <&pll4>, <&pll12>, <&pll12>;
+        clock-output-names = "gt";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-mmc-config-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-mmc-config-clk.yaml
new file mode 100644
index 000000000000..20dc115fa211
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-mmc-config-clk.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-mmc-config-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 MMC Configuration Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+description: >
+  There is one clock/reset output per mmc controller. The number of
+  outputs is determined by the size of the address block, which is
+  related to the overall mmc block.
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The additional ID argument passed to the clock shall refer to
+      the index of the output.
+
+  "#reset-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun9i-a80-mmc-config-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 4
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@1c13000 {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun9i-a80-mmc-config-clk";
+        reg = <0x01c13000 0x10>;
+        clocks = <&ahb0_gates 8>;
+        resets = <&ahb0_resets 8>;
+        clock-output-names = "mmc0_config", "mmc1_config",
+                             "mmc2_config", "mmc3_config";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-pll4-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-pll4-clk.yaml
new file mode 100644
index 000000000000..b76bab6a30e9
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-pll4-clk.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-pll4-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 Peripheral PLL Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    const: allwinner,sun9i-a80-pll4-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@600000c {
+        #clock-cells = <0>;
+        compatible = "allwinner,sun9i-a80-pll4-clk";
+        reg = <0x0600000c 0x4>;
+        clocks = <&osc24M>;
+        clock-output-names = "pll4";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-usb-mod-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-usb-mod-clk.yaml
new file mode 100644
index 000000000000..15218d10e78e
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-usb-mod-clk.yaml
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-usb-mod-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 USB Module Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The additional ID argument passed to the clock shall refer to
+      the index of the output.
+
+  "#reset-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun9i-a80-usb-mod-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 6
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@a08000 {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun9i-a80-usb-mod-clk";
+        reg = <0x00a08000 0x4>;
+        clocks = <&ahb1_gates 1>;
+        clock-output-names = "usb0_ahb", "usb_ohci0",
+                             "usb1_ahb", "usb_ohci1",
+                             "usb2_ahb", "usb_ohci2";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-usb-phy-clk.yaml b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-usb-phy-clk.yaml
new file mode 100644
index 000000000000..2569041684e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/allwinner,sun9i-a80-usb-phy-clk.yaml
@@ -0,0 +1,60 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/allwinner,sun9i-a80-usb-phy-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 USB PHY Clock Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  "#clock-cells":
+    const: 1
+    description: >
+      The additional ID argument passed to the clock shall refer to
+      the index of the output.
+
+  "#reset-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun9i-a80-usb-phy-clk
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-output-names:
+    maxItems: 6
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-output-names
+
+additionalProperties: false
+
+examples:
+  - |
+    clk@a08004 {
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+        compatible = "allwinner,sun9i-a80-usb-phy-clk";
+        reg = <0x00a08004 0x4>;
+        clocks = <&ahb1_gates 1>;
+        clock-output-names = "usb_phy0", "usb_hsic1_480M",
+                             "usb_phy1", "usb_hsic2_480M",
+                             "usb_phy2", "usb_hsic_12M";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/amlogic,meson8-ddr-clkc.yaml b/Documentation/devicetree/bindings/clock/amlogic,meson8-ddr-clkc.yaml
new file mode 100644
index 000000000000..4b8669f870ec
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/amlogic,meson8-ddr-clkc.yaml
@@ -0,0 +1,50 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/amlogic,meson8-ddr-clkc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Amlogic DDR Clock Controller Device Tree Bindings
+
+maintainers:
+  - Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+
+properties:
+  compatible:
+    enum:
+      - amlogic,meson8-ddr-clkc
+      - amlogic,meson8b-ddr-clkc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: xtal
+
+  "#clock-cells":
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - "#clock-cells"
+
+additionalProperties: false
+
+examples:
+  - |
+    ddr_clkc: clock-controller@400 {
+      compatible = "amlogic,meson8-ddr-clkc";
+      reg = <0x400 0x20>;
+      clocks = <&xtal>;
+      clock-names = "xtal";
+      #clock-cells = <1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt
index 4d94091c1d2d..cc51e4746b3b 100644
--- a/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt
+++ b/Documentation/devicetree/bindings/clock/amlogic,meson8b-clkc.txt
@@ -11,6 +11,11 @@ Required Properties:
 	- "amlogic,meson8m2-clkc" for Meson8m2 (S812) SoCs
 - #clock-cells: should be 1.
 - #reset-cells: should be 1.
+- clocks: list of clock phandles, one for each entry in clock-names
+- clock-names: should contain the following:
+  * "xtal": the 24MHz system oscillator
+  * "ddr_pll": the DDR PLL clock
+  * "clk_32k": (if present) the 32kHz clock signal from GPIOAO_6 (CLK_32K_IN)
 
 Parent node should have the following properties :
 - compatible: "amlogic,meson-hhi-sysctrl", "simple-mfd", "syscon"
diff --git a/Documentation/devicetree/bindings/clock/bitmain,bm1880-clk.yaml b/Documentation/devicetree/bindings/clock/bitmain,bm1880-clk.yaml
index e63827399c1a..8559fe8f7efd 100644
--- a/Documentation/devicetree/bindings/clock/bitmain,bm1880-clk.yaml
+++ b/Documentation/devicetree/bindings/clock/bitmain,bm1880-clk.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/clock/bitmain,bm1880-clk.yaml#
+$id: http://devicetree.org/schemas/clock/bitmain,bm1880-clk.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Bitmain BM1880 Clock Controller
diff --git a/Documentation/devicetree/bindings/clock/fsl,plldig.yaml b/Documentation/devicetree/bindings/clock/fsl,plldig.yaml
new file mode 100644
index 000000000000..c8350030b374
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/fsl,plldig.yaml
@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/fsl,plldig.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP QorIQ Layerscape LS1028A Display PIXEL Clock Binding
+
+maintainers:
+  - Wen He <wen.he_1@nxp.com>
+
+description: |
+  NXP LS1028A has a clock domain PXLCLK0 used for the Display output
+  interface in the display core, as implemented in TSMC CLN28HPM PLL.
+  which generate and offers pixel clocks to Display.
+
+properties:
+  compatible:
+    const: fsl,ls1028a-plldig
+
+  reg:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 0
+
+  fsl,vco-hz:
+     description: Optional for VCO frequency of the PLL in Hertz.
+        The VCO frequency of this PLL cannot be changed during runtime
+        only at startup. Therefore, the output frequencies are very
+        limited and might not even closely match the requested frequency.
+        To work around this restriction the user may specify its own
+        desired VCO frequency for the PLL.
+     minimum: 650000000
+     maximum: 1300000000
+     default: 1188000000
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+
+examples:
+  # Display PIXEL Clock node:
+  - |
+    dpclk: clock-display@f1f0000 {
+        compatible = "fsl,ls1028a-plldig";
+        reg = <0x0 0xf1f0000 0x0 0xffff>;
+        #clock-cells = <0>;
+        clocks = <&osc_27m>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/fsl,sai-clock.yaml b/Documentation/devicetree/bindings/clock/fsl,sai-clock.yaml
new file mode 100644
index 000000000000..fc3bdfdc091a
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/fsl,sai-clock.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/fsl,sai-clock.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale SAI bitclock-as-a-clock binding
+
+maintainers:
+  - Michael Walle <michael@walle.cc>
+
+description: |
+  It is possible to use the BCLK pin of a SAI module as a generic clock
+  output. Some SoC are very constrained in their pin multiplexer
+  configuration. Eg. pins can only be changed groups. For example, on the
+  LS1028A SoC you can only enable SAIs in pairs. If you use only one SAI,
+  the second pins are wasted. Using this binding it is possible to use the
+  clock of the second SAI as a MCLK clock for an audio codec, for example.
+
+  This is a composite of a gated clock and a divider clock.
+
+properties:
+  compatible:
+    const: fsl,vf610-sai-clock
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  '#clock-cells':
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - '#clock-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        mclk: clock-mclk@f130080 {
+            compatible = "fsl,vf610-sai-clock";
+            reg = <0x0 0xf130080 0x0 0x80>;
+            #clock-cells = <0>;
+            clocks = <&parentclk>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/clock/imx8mn-clock.yaml b/Documentation/devicetree/bindings/clock/imx8mn-clock.yaml
index 622f3658bd9f..cd0b8a341321 100644
--- a/Documentation/devicetree/bindings/clock/imx8mn-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx8mn-clock.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/clock/imx8mn-clock.yaml#
+$id: http://devicetree.org/schemas/clock/imx8mn-clock.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: NXP i.MX8M Nano Clock Control Module Binding
diff --git a/Documentation/devicetree/bindings/clock/imx8mp-clock.yaml b/Documentation/devicetree/bindings/clock/imx8mp-clock.yaml
new file mode 100644
index 000000000000..89aee63c9019
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/imx8mp-clock.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/imx8mp-clock.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP i.MX8M Plus Clock Control Module Binding
+
+maintainers:
+  - Anson Huang <Anson.Huang@nxp.com>
+
+description:
+  NXP i.MX8M Plus clock control module is an integrated clock controller, which
+  generates and supplies to all modules.
+
+properties:
+  compatible:
+    const: fsl,imx8mp-ccm
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: 32k osc
+      - description: 24m osc
+      - description: ext1 clock input
+      - description: ext2 clock input
+      - description: ext3 clock input
+      - description: ext4 clock input
+
+  clock-names:
+    items:
+      - const: osc_32k
+      - const: osc_24m
+      - const: clk_ext1
+      - const: clk_ext2
+      - const: clk_ext3
+      - const: clk_ext4
+
+  '#clock-cells':
+    const: 1
+    description:
+      The clock consumer should specify the desired clock by having the clock
+      ID in its "clocks" phandle cell. See include/dt-bindings/clock/imx8mp-clock.h
+      for the full list of i.MX8M Plus clock IDs.
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+
+examples:
+  # Clock Control Module node:
+  - |
+    clk: clock-controller@30380000 {
+        compatible = "fsl,imx8mp-ccm";
+        reg = <0x30380000 0x10000>;
+        #clock-cells = <1>;
+        clocks = <&osc_32k>, <&osc_24m>, <&clk_ext1>,
+                 <&clk_ext2>, <&clk_ext3>, <&clk_ext4>;
+        clock-names = "osc_32k", "osc_24m", "clk_ext1",
+                      "clk_ext2", "clk_ext3", "clk_ext4";
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/clock/milbeaut-clock.yaml b/Documentation/devicetree/bindings/clock/milbeaut-clock.yaml
index 5cf0b811821e..f0b804a7f096 100644
--- a/Documentation/devicetree/bindings/clock/milbeaut-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/milbeaut-clock.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/clock/milbeaut-clock.yaml#
+$id: http://devicetree.org/schemas/clock/milbeaut-clock.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Milbeaut SoCs Clock Controller Binding
diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc.txt b/Documentation/devicetree/bindings/clock/qcom,dispcc.txt
deleted file mode 100644
index d639e18d0b85..000000000000
--- a/Documentation/devicetree/bindings/clock/qcom,dispcc.txt
+++ /dev/null
@@ -1,19 +0,0 @@
-Qualcomm Technologies, Inc. Display Clock Controller Binding
-------------------------------------------------------------
-
-Required properties :
-
-- compatible : shall contain "qcom,sdm845-dispcc"
-- reg : shall contain base register location and length.
-- #clock-cells : from common clock binding, shall contain 1.
-- #reset-cells : from common reset binding, shall contain 1.
-- #power-domain-cells : from generic power domain binding, shall contain 1.
-
-Example:
-	dispcc: clock-controller@af00000 {
-		compatible = "qcom,sdm845-dispcc";
-		reg = <0xaf00000 0x100000>;
-		#clock-cells = <1>;
-		#reset-cells = <1>;
-		#power-domain-cells = <1>;
-	};
diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc.yaml b/Documentation/devicetree/bindings/clock/qcom,dispcc.yaml
new file mode 100644
index 000000000000..795fe686f3ea
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,dispcc.yaml
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,dispcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Display Clock & Reset Controller Binding
+
+maintainers:
+  - Taniya Das <tdas@codeaurora.org>
+
+description: |
+  Qualcomm display clock control module which supports the clocks, resets and
+  power domains.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sc7180-dispcc
+      - qcom,sdm845-dispcc
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: Board XO source
+      - description: GPLL0 source from GCC
+
+  clock-names:
+    items:
+      - const: xo
+      - const: gpll0
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+examples:
+  # Example of DISPCC with clock node properties for SDM845:
+  - |
+    clock-controller@af00000 {
+      compatible = "qcom,sdm845-dispcc";
+      reg = <0xaf00000 0x10000>;
+      clocks = <&rpmhcc 0>, <&gcc 24>;
+      clock-names = "xo", "gpll0";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+     };
+...
diff --git a/Documentation/devicetree/bindings/clock/qcom,gcc.yaml b/Documentation/devicetree/bindings/clock/qcom,gcc.yaml
index e73a56fb60ca..e814eec1bf8d 100644
--- a/Documentation/devicetree/bindings/clock/qcom,gcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,gcc.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/clock/qcom,gcc.yaml#
+$id: http://devicetree.org/schemas/clock/qcom,gcc.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Qualcomm Global Clock & Reset Controller Binding
@@ -19,8 +19,9 @@ properties:
     enum:
        - qcom,gcc-apq8064
        - qcom,gcc-apq8084
-       - qcom,gcc-ipq8064
        - qcom,gcc-ipq4019
+       - qcom,gcc-ipq6018
+       - qcom,gcc-ipq8064
        - qcom,gcc-ipq8074
        - qcom,gcc-msm8660
        - qcom,gcc-msm8916
@@ -40,20 +41,50 @@ properties:
        - qcom,gcc-sm8150
 
   clocks:
-    minItems: 1
-    maxItems: 3
-    items:
-      - description: Board XO source
-      - description: Board active XO source
-      - description: Sleep clock source
+    oneOf:
+      #qcom,gcc-sm8150
+      #qcom,gcc-sc7180
+      - items:
+        - description: Board XO source
+        - description: Board active XO source
+        - description: Sleep clock source
+      #qcom,gcc-msm8996
+      - items:
+        - description: XO source
+        - description: Second XO source
+        - description: Sleep clock source
+      #qcom,gcc-msm8998
+      - items:
+        - description: Board XO source
+        - description: Sleep clock source
+        - description: USB 3.0 phy pipe clock
+        - description: UFS phy rx symbol clock for pipe 0
+        - description: UFS phy rx symbol clock for pipe 1
+        - description: UFS phy tx symbol clock
+        - description: PCIE phy pipe clock
 
   clock-names:
-    minItems: 1
-    maxItems: 3
-    items:
-      - const: bi_tcxo
-      - const: bi_tcxo_ao
-      - const: sleep_clk
+    oneOf:
+      #qcom,gcc-sm8150
+      #qcom,gcc-sc7180
+      - items:
+        - const: bi_tcxo
+        - const: bi_tcxo_ao
+        - const: sleep_clk
+      #qcom,gcc-msm8996
+      - items:
+        - const: cxo
+        - const: cxo2
+        - const: sleep_clk
+      #qcom,gcc-msm8998
+      - items:
+        - const: xo
+        - const: sleep_clk
+        - const: usb3_pipe
+        - const: ufs_rx_symbol0
+        - const: ufs_rx_symbol1
+        - const: ufs_tx_symbol0
+        - const: pcie0_pipe
 
   '#clock-cells':
     const: 1
@@ -118,6 +149,7 @@ else:
       compatible:
         contains:
           enum:
+            - qcom,gcc-msm8998
             - qcom,gcc-sm8150
             - qcom,gcc-sc7180
   then:
@@ -179,10 +211,35 @@ examples:
     clock-controller@100000 {
       compatible = "qcom,gcc-sc7180";
       reg = <0x100000 0x1f0000>;
-      clocks = <&rpmhcc 0>, <&rpmhcc 1>;
-      clock-names = "bi_tcxo", "bi_tcxo_ao";
+      clocks = <&rpmhcc 0>, <&rpmhcc 1>, <0>;
+      clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+
+  # Example of MSM8998 GCC:
+  - |
+    #include <dt-bindings/clock/qcom,rpmcc.h>
+    clock-controller@100000 {
+      compatible = "qcom,gcc-msm8998";
       #clock-cells = <1>;
       #reset-cells = <1>;
       #power-domain-cells = <1>;
+      reg = <0x00100000 0xb0000>;
+      clocks = <&rpmcc RPM_SMD_XO_CLK_SRC>,
+               <&sleep>,
+               <0>,
+               <0>,
+               <0>,
+               <0>,
+               <0>;
+      clock-names = "xo",
+                    "sleep_clk",
+                    "usb3_pipe",
+                    "ufs_rx_symbol0",
+                    "ufs_rx_symbol1",
+                    "ufs_tx_symbol0",
+                    "pcie0_pipe";
     };
 ...
diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.txt b/Documentation/devicetree/bindings/clock/qcom,gpucc.txt
deleted file mode 100644
index 269afe8a757e..000000000000
--- a/Documentation/devicetree/bindings/clock/qcom,gpucc.txt
+++ /dev/null
@@ -1,24 +0,0 @@
-Qualcomm Graphics Clock & Reset Controller Binding
---------------------------------------------------
-
-Required properties :
-- compatible : shall contain "qcom,sdm845-gpucc" or "qcom,msm8998-gpucc"
-- reg : shall contain base register location and length
-- #clock-cells : from common clock binding, shall contain 1
-- #reset-cells : from common reset binding, shall contain 1
-- #power-domain-cells : from generic power domain binding, shall contain 1
-- clocks : shall contain the XO clock
-	   shall contain the gpll0 out main clock (msm8998)
-- clock-names : shall be "xo"
-		shall be "gpll0" (msm8998)
-
-Example:
-	gpucc: clock-controller@5090000 {
-		compatible = "qcom,sdm845-gpucc";
-		reg = <0x5090000 0x9000>;
-		#clock-cells = <1>;
-		#reset-cells = <1>;
-		#power-domain-cells = <1>;
-		clocks = <&rpmhcc RPMH_CXO_CLK>;
-		clock-names = "xo";
-	};
diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
new file mode 100644
index 000000000000..679e7fe0fa83
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
@@ -0,0 +1,72 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,gpucc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Graphics Clock & Reset Controller Binding
+
+maintainers:
+  - Taniya Das <tdas@codeaurora.org>
+
+description: |
+  Qualcomm grpahics clock control module which supports the clocks, resets and
+  power domains.
+
+properties:
+  compatible:
+    enum:
+      - qcom,msm8998-gpucc
+      - qcom,sc7180-gpucc
+      - qcom,sdm845-gpucc
+
+  clocks:
+    minItems: 1
+    maxItems: 3
+    items:
+      - description: Board XO source
+      - description: GPLL0 main branch source from GCC(gcc_gpu_gpll0_clk_src)
+      - description: GPLL0 div branch source from GCC(gcc_gpu_gpll0_div_clk_src)
+
+  clock-names:
+    minItems: 1
+    maxItems: 3
+    items:
+      - const: xo
+      - const: gpll0_main
+      - const: gpll0_div
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+examples:
+  # Example of GPUCC with clock node properties for SDM845:
+  - |
+    clock-controller@5090000 {
+      compatible = "qcom,sdm845-gpucc";
+      reg = <0x5090000 0x9000>;
+      clocks = <&rpmhcc 0>, <&gcc 31>, <&gcc 32>;
+      clock-names = "xo", "gpll0_main", "gpll0_div";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+     };
+...
diff --git a/Documentation/devicetree/bindings/clock/qcom,mmcc.txt b/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
deleted file mode 100644
index 8b0f7841af8d..000000000000
--- a/Documentation/devicetree/bindings/clock/qcom,mmcc.txt
+++ /dev/null
@@ -1,28 +0,0 @@
-Qualcomm Multimedia Clock & Reset Controller Binding
-----------------------------------------------------
-
-Required properties :
-- compatible : shall contain only one of the following:
-
-			"qcom,mmcc-apq8064"
-			"qcom,mmcc-apq8084"
-			"qcom,mmcc-msm8660"
-			"qcom,mmcc-msm8960"
-			"qcom,mmcc-msm8974"
-			"qcom,mmcc-msm8996"
-
-- reg : shall contain base register location and length
-- #clock-cells : shall contain 1
-- #reset-cells : shall contain 1
-
-Optional properties :
-- #power-domain-cells : shall contain 1
-
-Example:
-	clock-controller@4000000 {
-		compatible = "qcom,mmcc-msm8960";
-		reg = <0x4000000 0x1000>;
-		#clock-cells = <1>;
-		#reset-cells = <1>;
-		#power-domain-cells = <1>;
-	};
diff --git a/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml b/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml
new file mode 100644
index 000000000000..85518494ce43
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,mmcc.yaml
@@ -0,0 +1,98 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,mmcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Multimedia Clock & Reset Controller Binding
+
+maintainers:
+  - Jeffrey Hugo <jhugo@codeaurora.org>
+  - Taniya Das <tdas@codeaurora.org>
+
+description: |
+  Qualcomm multimedia clock control module which supports the clocks, resets and
+  power domains.
+
+properties:
+  compatible :
+    enum:
+       - qcom,mmcc-apq8064
+       - qcom,mmcc-apq8084
+       - qcom,mmcc-msm8660
+       - qcom,mmcc-msm8960
+       - qcom,mmcc-msm8974
+       - qcom,mmcc-msm8996
+       - qcom,mmcc-msm8998
+
+  clocks:
+    items:
+      - description: Board XO source
+      - description: Board sleep source
+      - description: Global PLL 0 clock
+      - description: DSI phy instance 0 dsi clock
+      - description: DSI phy instance 0 byte clock
+      - description: DSI phy instance 1 dsi clock
+      - description: DSI phy instance 1 byte clock
+      - description: HDMI phy PLL clock
+      - description: DisplayPort phy PLL vco clock
+      - description: DisplayPort phy PLL link clock
+
+  clock-names:
+    items:
+      - const: xo
+      - const: sleep
+      - const: gpll0
+      - const: dsi0dsi
+      - const: dsi0byte
+      - const: dsi1dsi
+      - const: dsi1byte
+      - const: hdmipll
+      - const: dpvco
+      - const: dplink
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+  protected-clocks:
+    description:
+       Protected clock specifier list as per common clock binding
+
+required:
+  - compatible
+  - reg
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: qcom,mmcc-msm8998
+
+then:
+  required:
+    - clocks
+    - clock-names
+
+examples:
+  # Example for MMCC for MSM8960:
+  - |
+    clock-controller@4000000 {
+      compatible = "qcom,mmcc-msm8960";
+      reg = <0x4000000 0x1000>;
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
index 94e2f14eb967..2cd158f13bab 100644
--- a/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
+++ b/Documentation/devicetree/bindings/clock/qcom,rpmhcc.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/clock/qcom,rpmhcc.yaml#
+$id: http://devicetree.org/schemas/clock/qcom,rpmhcc.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Qualcomm Technologies, Inc. RPMh Clocks Bindings
diff --git a/Documentation/devicetree/bindings/clock/qcom,videocc.txt b/Documentation/devicetree/bindings/clock/qcom,videocc.txt
deleted file mode 100644
index 8a8622c65c5a..000000000000
--- a/Documentation/devicetree/bindings/clock/qcom,videocc.txt
+++ /dev/null
@@ -1,18 +0,0 @@
-Qualcomm Video Clock & Reset Controller Binding
------------------------------------------------
-
-Required properties :
-- compatible : shall contain "qcom,sdm845-videocc"
-- reg : shall contain base register location and length
-- #clock-cells : from common clock binding, shall contain 1.
-- #power-domain-cells : from generic power domain binding, shall contain 1.
-- #reset-cells : from common reset binding, shall contain 1.
-
-Example:
-	videocc: clock-controller@ab00000 {
-		compatible = "qcom,sdm845-videocc";
-		reg = <0xab00000 0x10000>;
-		#clock-cells = <1>;
-		#power-domain-cells = <1>;
-		#reset-cells = <1>;
-	};
diff --git a/Documentation/devicetree/bindings/clock/qcom,videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
new file mode 100644
index 000000000000..2946b240e161
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,videocc.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/qcom,videocc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Video Clock & Reset Controller Binding
+
+maintainers:
+  - Taniya Das <tdas@codeaurora.org>
+
+description: |
+  Qualcomm video clock control module which supports the clocks, resets and
+  power domains.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sc7180-videocc
+      - qcom,sdm845-videocc
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: xo
+
+  '#clock-cells':
+    const: 1
+
+  '#reset-cells':
+    const: 1
+
+  '#power-domain-cells':
+    const: 1
+
+  reg:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - '#clock-cells'
+  - '#reset-cells'
+  - '#power-domain-cells'
+
+examples:
+  # Example of VIDEOCC with clock node properties for SDM845:
+  - |
+    clock-controller@ab00000 {
+      compatible = "qcom,sdm845-videocc";
+      reg = <0xab00000 0x10000>;
+      clocks = <&rpmhcc 0>;
+      clock-names = "xo";
+      #clock-cells = <1>;
+      #reset-cells = <1>;
+      #power-domain-cells = <1>;
+     };
+...
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt
index c7674d0267a3..f4d153f24a0f 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mssr.txt
@@ -19,7 +19,7 @@ Required Properties:
       - "renesas,r8a7745-cpg-mssr" for the r8a7745 SoC (RZ/G1E)
       - "renesas,r8a77470-cpg-mssr" for the r8a77470 SoC (RZ/G1C)
       - "renesas,r8a774a1-cpg-mssr" for the r8a774a1 SoC (RZ/G2M)
-      - "renesas,r8a774b1-cpg-mssr" for the r8a774a1 SoC (RZ/G2N)
+      - "renesas,r8a774b1-cpg-mssr" for the r8a774b1 SoC (RZ/G2N)
       - "renesas,r8a774c0-cpg-mssr" for the r8a774c0 SoC (RZ/G2E)
       - "renesas,r8a7790-cpg-mssr" for the r8a7790 SoC (R-Car H2)
       - "renesas,r8a7791-cpg-mssr" for the r8a7791 SoC (R-Car M2-W)
diff --git a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.txt b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.txt
deleted file mode 100644
index fb9495ea582c..000000000000
--- a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.txt
+++ /dev/null
@@ -1,60 +0,0 @@
-STMicroelectronics STM32 Peripheral Reset Clock Controller
-==========================================================
-
-The RCC IP is both a reset and a clock controller.
-
-RCC makes also power management (resume/supend and wakeup interrupt).
-
-Please also refer to reset.txt for common reset controller binding usage.
-
-Please also refer to clock-bindings.txt for common clock controller
-binding usage.
-
-
-Required properties:
-- compatible: "st,stm32mp1-rcc", "syscon"
-- reg: should be register base and length as documented in the datasheet
-- #clock-cells: 1, device nodes should specify the clock in their
-  "clocks" property, containing a phandle to the clock device node,
-  an index specifying the clock to use.
-- #reset-cells: Shall be 1
-- interrupts: Should contain a general interrupt line and a interrupt line
-  to the wake-up of processor (CSTOP).
-
-Example:
-	rcc: rcc@50000000 {
-		compatible = "st,stm32mp1-rcc", "syscon";
-		reg = <0x50000000 0x1000>;
-		#clock-cells = <1>;
-		#reset-cells = <1>;
-		interrupts = <GIC_SPI 5 IRQ_TYPE_NONE>,
-			     <GIC_SPI 145 IRQ_TYPE_NONE>;
-	};
-
-Specifying clocks
-=================
-
-All available clocks are defined as preprocessor macros in
-dt-bindings/clock/stm32mp1-clks.h header and can be used in device
-tree sources.
-
-Specifying softreset control of devices
-=======================================
-
-Device nodes should specify the reset channel required in their "resets"
-property, containing a phandle to the reset device node and an index specifying
-which channel to use.
-The index is the bit number within the RCC registers bank, starting from RCC
-base address.
-It is calculated as: index = register_offset / 4 * 32 + bit_offset.
-Where bit_offset is the bit offset within the register.
-
-For example on STM32MP1, for LTDC reset:
- ltdc = APB4_RSTSETR_offset / 4 * 32 + LTDC_bit_offset
-      = 0x180 / 4 * 32 + 0 = 3072
-
-The list of valid indices for STM32MP1 is available in:
-include/dt-bindings/reset-controller/stm32mp1-resets.h
-
-This file implements defines like:
-#define LTDC_R	3072
diff --git a/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml
new file mode 100644
index 000000000000..4e385508f516
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/st,stm32mp1-rcc.yaml
@@ -0,0 +1,79 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/st,stm32mp1-rcc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Reset Clock Controller Binding
+
+maintainers:
+  - Gabriel Fernandez <gabriel.fernandez@st.com>
+
+description: |
+  The RCC IP is both a reset and a clock controller.
+  RCC makes also power management (resume/supend and wakeup interrupt).
+  Please also refer to reset.txt for common reset controller binding usage.
+
+  This binding uses common clock bindings
+  Documentation/devicetree/bindings/clock/clock-bindings.txt
+
+  Specifying clocks
+  =================
+
+  All available clocks are defined as preprocessor macros in
+  dt-bindings/clock/stm32mp1-clks.h header and can be used in device
+  tree sources.
+
+  Specifying softreset control of devices
+  =======================================
+
+  Device nodes should specify the reset channel required in their "resets"
+  property, containing a phandle to the reset device node and an index specifying
+  which channel to use.
+  The index is the bit number within the RCC registers bank, starting from RCC
+  base address.
+  It is calculated as: index = register_offset / 4 * 32 + bit_offset.
+  Where bit_offset is the bit offset within the register.
+
+  For example on STM32MP1, for LTDC reset:
+     ltdc = APB4_RSTSETR_offset / 4 * 32 + LTDC_bit_offset
+          = 0x180 / 4 * 32 + 0 = 3072
+
+  The list of valid indices for STM32MP1 is available in:
+  include/dt-bindings/reset-controller/stm32mp1-resets.h
+
+  This file implements defines like:
+  #define LTDC_R	3072
+
+properties:
+  "#clock-cells":
+    const: 1
+
+  "#reset-cells":
+    const: 1
+
+  compatible:
+    items:
+      - const: st,stm32mp1-rcc
+      - const: syscon
+
+  reg:
+    maxItems: 1
+
+required:
+  - "#clock-cells"
+  - "#reset-cells"
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    rcc: rcc@50000000 {
+        compatible = "st,stm32mp1-rcc", "syscon";
+        reg = <0x50000000 0x1000>;
+        #clock-cells = <1>;
+        #reset-cells = <1>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/clock/sunxi.txt b/Documentation/devicetree/bindings/clock/sunxi.txt
deleted file mode 100644
index 1a042e20b115..000000000000
--- a/Documentation/devicetree/bindings/clock/sunxi.txt
+++ /dev/null
@@ -1,225 +0,0 @@
-Device Tree Clock bindings for arch-sunxi
-
-This binding uses the common clock binding[1].
-
-[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
-
-Required properties:
-- compatible : shall be one of the following:
-	"allwinner,sun4i-a10-osc-clk" - for a gatable oscillator
-	"allwinner,sun4i-a10-pll1-clk" - for the main PLL clock and PLL4
-	"allwinner,sun6i-a31-pll1-clk" - for the main PLL clock on A31
-	"allwinner,sun8i-a23-pll1-clk" - for the main PLL clock on A23
-	"allwinner,sun4i-a10-pll3-clk" - for the video PLL clock on A10
-	"allwinner,sun9i-a80-pll4-clk" - for the peripheral PLLs on A80
-	"allwinner,sun4i-a10-pll5-clk" - for the PLL5 clock
-	"allwinner,sun4i-a10-pll6-clk" - for the PLL6 clock
-	"allwinner,sun6i-a31-pll6-clk" - for the PLL6 clock on A31
-	"allwinner,sun9i-a80-gt-clk" - for the GT bus clock on A80
-	"allwinner,sun4i-a10-cpu-clk" - for the CPU multiplexer clock
-	"allwinner,sun4i-a10-axi-clk" - for the AXI clock
-	"allwinner,sun8i-a23-axi-clk" - for the AXI clock on A23
-	"allwinner,sun4i-a10-gates-clk" - for generic gates on all compatible SoCs
-	"allwinner,sun4i-a10-axi-gates-clk" - for the AXI gates
-	"allwinner,sun4i-a10-ahb-clk" - for the AHB clock
-	"allwinner,sun5i-a13-ahb-clk" - for the AHB clock on A13
-	"allwinner,sun9i-a80-ahb-clk" - for the AHB bus clocks on A80
-	"allwinner,sun4i-a10-ahb-gates-clk" - for the AHB gates on A10
-	"allwinner,sun5i-a13-ahb-gates-clk" - for the AHB gates on A13
-	"allwinner,sun5i-a10s-ahb-gates-clk" - for the AHB gates on A10s
-	"allwinner,sun7i-a20-ahb-gates-clk" - for the AHB gates on A20
-	"allwinner,sun6i-a31-ar100-clk" - for the AR100 on A31
-	"allwinner,sun9i-a80-cpus-clk" - for the CPUS on A80
-	"allwinner,sun6i-a31-ahb1-clk" - for the AHB1 clock on A31
-	"allwinner,sun8i-h3-ahb2-clk" - for the AHB2 clock on H3
-	"allwinner,sun6i-a31-ahb1-gates-clk" - for the AHB1 gates on A31
-	"allwinner,sun8i-a23-ahb1-gates-clk" - for the AHB1 gates on A23
-	"allwinner,sun9i-a80-ahb0-gates-clk" - for the AHB0 gates on A80
-	"allwinner,sun9i-a80-ahb1-gates-clk" - for the AHB1 gates on A80
-	"allwinner,sun9i-a80-ahb2-gates-clk" - for the AHB2 gates on A80
-	"allwinner,sun4i-a10-apb0-clk" - for the APB0 clock
-	"allwinner,sun6i-a31-apb0-clk" - for the APB0 clock on A31
-	"allwinner,sun8i-a23-apb0-clk" - for the APB0 clock on A23
-	"allwinner,sun9i-a80-apb0-clk" - for the APB0 bus clock on A80
-	"allwinner,sun8i-a83t-apb0-gates-clk" - for the APB0 gates on A83T
-	"allwinner,sun4i-a10-apb0-gates-clk" - for the APB0 gates on A10
-	"allwinner,sun5i-a13-apb0-gates-clk" - for the APB0 gates on A13
-	"allwinner,sun5i-a10s-apb0-gates-clk" - for the APB0 gates on A10s
-	"allwinner,sun6i-a31-apb0-gates-clk" - for the APB0 gates on A31
-	"allwinner,sun7i-a20-apb0-gates-clk" - for the APB0 gates on A20
-	"allwinner,sun8i-a23-apb0-gates-clk" - for the APB0 gates on A23
-	"allwinner,sun8i-h3-apb0-gates-clk" - for the APB0 gates on H3
-	"allwinner,sun9i-a80-apb0-gates-clk" - for the APB0 gates on A80
-	"allwinner,sun4i-a10-apb1-clk" - for the APB1 clock
-	"allwinner,sun9i-a80-apb1-clk" - for the APB1 bus clock on A80
-	"allwinner,sun4i-a10-apb1-gates-clk" - for the APB1 gates on A10
-	"allwinner,sun5i-a13-apb1-gates-clk" - for the APB1 gates on A13
-	"allwinner,sun5i-a10s-apb1-gates-clk" - for the APB1 gates on A10s
-	"allwinner,sun6i-a31-apb1-gates-clk" - for the APB1 gates on A31
-	"allwinner,sun7i-a20-apb1-gates-clk" - for the APB1 gates on A20
-	"allwinner,sun8i-a23-apb1-gates-clk" - for the APB1 gates on A23
-	"allwinner,sun9i-a80-apb1-gates-clk" - for the APB1 gates on A80
-	"allwinner,sun6i-a31-apb2-gates-clk" - for the APB2 gates on A31
-	"allwinner,sun8i-a23-apb2-gates-clk" - for the APB2 gates on A23
-	"allwinner,sun8i-a83t-bus-gates-clk" - for the bus gates on A83T
-	"allwinner,sun8i-h3-bus-gates-clk" - for the bus gates on H3
-	"allwinner,sun9i-a80-apbs-gates-clk" - for the APBS gates on A80
-	"allwinner,sun4i-a10-display-clk" - for the display clocks on the A10
-	"allwinner,sun4i-a10-dram-gates-clk" - for the DRAM gates on A10
-	"allwinner,sun5i-a13-dram-gates-clk" - for the DRAM gates on A13
-	"allwinner,sun5i-a13-mbus-clk" - for the MBUS clock on A13
-	"allwinner,sun4i-a10-mmc-clk" - for the MMC clock
-	"allwinner,sun9i-a80-mmc-clk" - for mmc module clocks on A80
-	"allwinner,sun9i-a80-mmc-config-clk" - for mmc gates + resets on A80
-	"allwinner,sun4i-a10-mod0-clk" - for the module 0 family of clocks
-	"allwinner,sun9i-a80-mod0-clk" - for module 0 (storage) clocks on A80
-	"allwinner,sun8i-a23-mbus-clk" - for the MBUS clock on A23
-	"allwinner,sun7i-a20-out-clk" - for the external output clocks
-	"allwinner,sun7i-a20-gmac-clk" - for the GMAC clock module on A20/A31
-	"allwinner,sun4i-a10-tcon-ch0-clk" - for the TCON channel 0 clock on the A10
-	"allwinner,sun4i-a10-tcon-ch1-clk" - for the TCON channel 1 clock on the A10
-	"allwinner,sun4i-a10-usb-clk" - for usb gates + resets on A10 / A20
-	"allwinner,sun5i-a13-usb-clk" - for usb gates + resets on A13
-	"allwinner,sun6i-a31-usb-clk" - for usb gates + resets on A31
-	"allwinner,sun8i-a23-usb-clk" - for usb gates + resets on A23
-	"allwinner,sun8i-h3-usb-clk" - for usb gates + resets on H3
-	"allwinner,sun9i-a80-usb-mod-clk" - for usb gates + resets on A80
-	"allwinner,sun9i-a80-usb-phy-clk" - for usb phy gates + resets on A80
-	"allwinner,sun4i-a10-ve-clk" - for the Video Engine clock
-	"allwinner,sun6i-a31-display-clk" - for the display clocks
-
-Required properties for all clocks:
-- reg : shall be the control register address for the clock.
-- clocks : shall be the input parent clock(s) phandle for the clock. For
-	multiplexed clocks, the list order must match the hardware
-	programming order.
-- #clock-cells : from common clock binding; shall be set to 0 except for
-	the following compatibles where it shall be set to 1:
-	"allwinner,*-gates-clk", "allwinner,sun4i-pll5-clk",
-	"allwinner,sun4i-pll6-clk", "allwinner,sun6i-a31-pll6-clk",
-	"allwinner,*-usb-clk", "allwinner,*-mmc-clk",
-	"allwinner,*-mmc-config-clk"
-- clock-output-names : shall be the corresponding names of the outputs.
-	If the clock module only has one output, the name shall be the
-	module name.
-
-And "allwinner,*-usb-clk" clocks also require:
-- reset-cells : shall be set to 1
-
-The "allwinner,sun4i-a10-ve-clk" clock also requires:
-- reset-cells : shall be set to 0
-
-The "allwinner,sun9i-a80-mmc-config-clk" clock also requires:
-- #reset-cells : shall be set to 1
-- resets : shall be the reset control phandle for the mmc block.
-
-For "allwinner,sun7i-a20-gmac-clk", the parent clocks shall be fixed rate
-dummy clocks at 25 MHz and 125 MHz, respectively. See example.
-
-Clock consumers should specify the desired clocks they use with a
-"clocks" phandle cell. Consumers that are using a gated clock should
-provide an additional ID in their clock property. This ID is the
-offset of the bit controlling this particular gate in the register.
-For the other clocks with "#clock-cells" = 1, the additional ID shall
-refer to the index of the output.
-
-For "allwinner,sun6i-a31-pll6-clk", there are 2 outputs. The first output
-is the normal PLL6 output, or "pll6". The second output is rate doubled
-PLL6, or "pll6x2".
-
-The "allwinner,*-mmc-clk" clocks have three different outputs: the
-main clock, with the ID 0, and the output and sample clocks, with the
-IDs 1 and 2, respectively.
-
-The "allwinner,sun9i-a80-mmc-config-clk" clock has one clock/reset output
-per mmc controller. The number of outputs is determined by the size of
-the address block, which is related to the overall mmc block.
-
-For example:
-
-osc24M: clk@1c20050 {
-	#clock-cells = <0>;
-	compatible = "allwinner,sun4i-a10-osc-clk";
-	reg = <0x01c20050 0x4>;
-	clocks = <&osc24M_fixed>;
-	clock-output-names = "osc24M";
-};
-
-pll1: clk@1c20000 {
-	#clock-cells = <0>;
-	compatible = "allwinner,sun4i-a10-pll1-clk";
-	reg = <0x01c20000 0x4>;
-	clocks = <&osc24M>;
-	clock-output-names = "pll1";
-};
-
-pll5: clk@1c20020 {
-	#clock-cells = <1>;
-	compatible = "allwinner,sun4i-pll5-clk";
-	reg = <0x01c20020 0x4>;
-	clocks = <&osc24M>;
-	clock-output-names = "pll5_ddr", "pll5_other";
-};
-
-pll6: clk@1c20028 {
-	#clock-cells = <1>;
-	compatible = "allwinner,sun6i-a31-pll6-clk";
-	reg = <0x01c20028 0x4>;
-	clocks = <&osc24M>;
-	clock-output-names = "pll6", "pll6x2";
-};
-
-cpu: cpu@1c20054 {
-	#clock-cells = <0>;
-	compatible = "allwinner,sun4i-a10-cpu-clk";
-	reg = <0x01c20054 0x4>;
-	clocks = <&osc32k>, <&osc24M>, <&pll1>;
-	clock-output-names = "cpu";
-};
-
-mmc0_clk: clk@1c20088 {
-	#clock-cells = <1>;
-	compatible = "allwinner,sun4i-a10-mmc-clk";
-	reg = <0x01c20088 0x4>;
-	clocks = <&osc24M>, <&pll6 1>, <&pll5 1>;
-	clock-output-names = "mmc0", "mmc0_output", "mmc0_sample";
-};
-
-mii_phy_tx_clk: clk@2 {
-	#clock-cells = <0>;
-	compatible = "fixed-clock";
-	clock-frequency = <25000000>;
-	clock-output-names = "mii_phy_tx";
-};
-
-gmac_int_tx_clk: clk@3 {
-	#clock-cells = <0>;
-	compatible = "fixed-clock";
-	clock-frequency = <125000000>;
-	clock-output-names = "gmac_int_tx";
-};
-
-gmac_clk: clk@1c20164 {
-	#clock-cells = <0>;
-	compatible = "allwinner,sun7i-a20-gmac-clk";
-	reg = <0x01c20164 0x4>;
-	/*
-	 * The first clock must be fixed at 25MHz;
-	 * the second clock must be fixed at 125MHz
-	 */
-	clocks = <&mii_phy_tx_clk>, <&gmac_int_tx_clk>;
-	clock-output-names = "gmac";
-};
-
-mmc_config_clk: clk@1c13000 {
-	compatible = "allwinner,sun9i-a80-mmc-config-clk";
-	reg = <0x01c13000 0x10>;
-	clocks = <&ahb0_gates 8>;
-	clock-names = "ahb";
-	resets = <&ahb0_resets 8>;
-	reset-names = "ahb";
-	#clock-cells = <1>;
-	#reset-cells = <1>;
-	clock-output-names = "mmc0_config", "mmc1_config",
-			     "mmc2_config", "mmc3_config";
-};
diff --git a/Documentation/devicetree/bindings/clock/ti-clkctrl.txt b/Documentation/devicetree/bindings/clock/ti-clkctrl.txt
index 48ee6991f2cc..18af6b9409e3 100644
--- a/Documentation/devicetree/bindings/clock/ti-clkctrl.txt
+++ b/Documentation/devicetree/bindings/clock/ti-clkctrl.txt
@@ -16,18 +16,23 @@ For more information, please see the Linux clock framework binding at
 Documentation/devicetree/bindings/clock/clock-bindings.txt.
 
 Required properties :
-- compatible : shall be "ti,clkctrl"
+- compatible : shall be "ti,clkctrl" or a clock domain specific name:
+	       "ti,clkctrl-l4-cfg"
+	       "ti,clkctrl-l4-per"
+	       "ti,clkctrl-l4-secure"
+	       "ti,clkctrl-l4-wkup"
 - #clock-cells : shall contain 2 with the first entry being the instance
 		 offset from the clock domain base and the second being the
 		 clock index
+- reg : clock registers
 
 Example: Clock controller node on omap 4430:
 
 &cm2 {
 	l4per: cm@1400 {
 		cm_l4per@0 {
-			cm_l4per_clkctrl: clk@20 {
-				compatible = "ti,clkctrl";
+			cm_l4per_clkctrl: clock@20 {
+				compatible = "ti,clkctrl-l4-per", "ti,clkctrl";
 				reg = <0x20 0x1b0>;
 				#clock-cells = <2>;
 			};
diff --git a/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
index 10f7047755f3..21c002d28b9b 100644
--- a/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
+++ b/Documentation/devicetree/bindings/clock/ti/dra7-atl.txt
@@ -43,7 +43,7 @@ Configuration of ATL instances:
 	- aws : Audio word select signal selection
 };
 
-For valid word select signals, see the dt-bindings/clk/ti-dra7-atl.h include
+For valid word select signals, see the dt-bindings/clock/ti-dra7-atl.h include
 file.
 
 Examples:
@@ -83,7 +83,7 @@ atl: atl@4843c000 {
 	clock-names = "fck";
 };
 
-#include <dt-bindings/clk/ti-dra7-atl.h>
+#include <dt-bindings/clock/ti-dra7-atl.h>
 
 &atl {
 
diff --git a/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml b/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml
new file mode 100644
index 000000000000..229af98b1d30
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/clock/xlnx,versal-clk.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xilinx Versal clock controller
+
+maintainers:
+  - Michal Simek <michal.simek@xilinx.com>
+  - Jolly Shah <jolly.shah@xilinx.com>
+  - Rajan Vaja <rajan.vaja@xilinx.com>
+
+description: |
+  The clock controller is a hardware block of Xilinx versal clock tree. It
+  reads required input clock frequencies from the devicetree and acts as clock
+  provider for all clock consumers of PS clocks.
+
+select: false
+
+properties:
+  compatible:
+    const: xlnx,versal-clk
+
+  "#clock-cells":
+    const: 1
+
+  clocks:
+    description: List of clock specifiers which are external input
+      clocks to the given clock controller.
+    items:
+      - description: reference clock
+      - description: alternate reference clock
+      - description: alternate reference clock for programmable logic
+
+  clock-names:
+    items:
+      - const: ref
+      - const: alt_ref
+      - const: pl_alt_ref
+
+required:
+  - compatible
+  - "#clock-cells"
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+    firmware {
+      zynqmp_firmware: zynqmp-firmware {
+        compatible = "xlnx,zynqmp-firmware";
+        method = "smc";
+        versal_clk: clock-controller {
+          #clock-cells = <1>;
+          compatible = "xlnx,versal-clk";
+          clocks = <&ref>, <&alt_ref>, <&pl_alt_ref>;
+          clock-names = "ref", "alt_ref", "pl_alt_ref";
+        };
+      };
+    };
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-backend.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-backend.yaml
new file mode 100644
index 000000000000..86057d541065
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-backend.yaml
@@ -0,0 +1,291 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-display-backend.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Engine Backend Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The display engine backend exposes layers and sprites to the system.
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-display-backend
+      - allwinner,sun5i-a13-display-backend
+      - allwinner,sun6i-a31-display-backend
+      - allwinner,sun7i-a20-display-backend
+      - allwinner,sun8i-a23-display-backend
+      - allwinner,sun8i-a33-display-backend
+      - allwinner,sun9i-a80-display-backend
+
+  reg:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: Display Backend registers
+      - description: SAT registers
+
+  reg-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: be
+      - const: sat
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 3
+    maxItems: 4
+    items:
+      - description: The backend interface clock
+      - description: The backend module clock
+      - description: The backend DRAM clock
+      - description: The SAT clock
+
+  clock-names:
+    minItems: 3
+    maxItems: 4
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+      - const: sat
+
+  resets:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: The Backend reset line
+      - description: The SAT reset line
+
+  reset-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: be
+      - const: sat
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnects:
+    maxItems: 1
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnect-names:
+    const: dma-mem
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun8i-a33-display-backend
+
+then:
+  properties:
+    reg:
+      minItems: 2
+
+    reg-names:
+      minItems: 2
+
+    clocks:
+      minItems: 4
+
+    clock-names:
+      minItems: 4
+
+    resets:
+      minItems: 2
+
+    reset-names:
+      minItems: 2
+
+  required:
+    - reg-names
+    - reset-names
+
+else:
+  properties:
+    reg:
+      maxItems: 1
+
+    reg-names:
+      maxItems: 1
+
+    clocks:
+      maxItems: 3
+
+    clock-names:
+      maxItems: 3
+
+    resets:
+      maxItems: 1
+
+    reset-names:
+      maxItems: 1
+
+examples:
+  - |
+    /*
+     * This comes from the clock/sun4i-a10-ccu.h and
+     * reset/sun4i-a10-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_AHB_DE_BE0	42
+    #define CLK_DRAM_DE_BE0	140
+    #define CLK_DE_BE0		144
+    #define RST_DE_BE0		5
+
+    display-backend@1e60000 {
+        compatible = "allwinner,sun4i-a10-display-backend";
+        reg = <0x01e60000 0x10000>;
+        interrupts = <47>;
+        clocks = <&ccu CLK_AHB_DE_BE0>, <&ccu CLK_DE_BE0>,
+                 <&ccu CLK_DRAM_DE_BE0>;
+        clock-names = "ahb", "mod",
+                      "ram";
+        resets = <&ccu RST_DE_BE0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&fe0_out_be0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&fe1_out_be0>;
+                };
+            };
+
+            port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_in_be0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_in_be0>;
+                };
+            };
+        };
+    };
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-a23-a33-ccu.h and
+     * reset/sun8i-a23-a33-ccu.h headers, but we can't include them
+     * since it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_DE_BE	40
+    #define CLK_BUS_SAT		46
+    #define CLK_DRAM_DE_BE	84
+    #define CLK_DE_BE		85
+    #define RST_BUS_DE_BE	21
+    #define RST_BUS_SAT		27
+
+    display-backend@1e60000 {
+        compatible = "allwinner,sun8i-a33-display-backend";
+        reg = <0x01e60000 0x10000>, <0x01e80000 0x1000>;
+        reg-names = "be", "sat";
+        interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_DE_BE>, <&ccu CLK_DE_BE>,
+                 <&ccu CLK_DRAM_DE_BE>, <&ccu CLK_BUS_SAT>;
+        clock-names = "ahb", "mod",
+                      "ram", "sat";
+        resets = <&ccu RST_BUS_DE_BE>, <&ccu RST_BUS_SAT>;
+        reset-names = "be", "sat";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&fe0_out_be0>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+
+                endpoint {
+                    remote-endpoint = <&drc0_in_be0>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml
new file mode 100644
index 000000000000..944ff2f1cf93
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-engine.yaml
@@ -0,0 +1,114 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-display-engine.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Engine Pipeline Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The display engine pipeline (and its entry point, since it can be
+  either directly the backend or the frontend) is represented as an
+  extra node.
+
+  The Allwinner A10 Display pipeline is composed of several components
+  that are going to be documented below:
+
+  For all connections between components up to the TCONs in the
+  display pipeline, when there are multiple components of the same
+  type at the same depth, the local endpoint ID must be the same as
+  the remote component's index. For example, if the remote endpoint is
+  Frontend 1, then the local endpoint ID must be 1.
+
+  Frontend 0  [0] ------- [0]  Backend 0  [0] ------- [0]  TCON 0
+              [1] --   -- [1]             [1] --   -- [1]
+                    \ /                         \ /
+                     X                           X
+                    / \                         / \
+              [0] --   -- [0]             [0] --   -- [0]
+  Frontend 1  [1] ------- [1]  Backend 1  [1] ------- [1]  TCON 1
+
+  For a two pipeline system such as the one depicted above, the lines
+  represent the connections between the components, while the numbers
+  within the square brackets corresponds to the ID of the local endpoint.
+
+  The same rule also applies to DE 2.0 mixer-TCON connections:
+
+  Mixer 0  [0] ----------- [0]  TCON 0
+           [1] ----   ---- [1]
+                   \ /
+                    X
+                   / \
+           [0] ----   ---- [0]
+  Mixer 1  [1] ----------- [1]  TCON 1
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-display-engine
+      - allwinner,sun5i-a10s-display-engine
+      - allwinner,sun5i-a13-display-engine
+      - allwinner,sun6i-a31-display-engine
+      - allwinner,sun6i-a31s-display-engine
+      - allwinner,sun7i-a20-display-engine
+      - allwinner,sun8i-a23-display-engine
+      - allwinner,sun8i-a33-display-engine
+      - allwinner,sun8i-a83t-display-engine
+      - allwinner,sun8i-h3-display-engine
+      - allwinner,sun8i-r40-display-engine
+      - allwinner,sun8i-v3s-display-engine
+      - allwinner,sun9i-a80-display-engine
+      - allwinner,sun50i-a64-display-engine
+      - allwinner,sun50i-h6-display-engine
+
+  allwinner,pipelines:
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/phandle-array
+      - minItems: 1
+        maxItems: 2
+    description: |
+      Available display engine frontends (DE 1.0) or mixers (DE
+      2.0/3.0) available.
+
+required:
+  - compatible
+  - allwinner,pipelines
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun4i-a10-display-engine
+          - allwinner,sun6i-a31-display-engine
+          - allwinner,sun6i-a31s-display-engine
+          - allwinner,sun7i-a20-display-engine
+          - allwinner,sun8i-a83t-display-engine
+          - allwinner,sun8i-r40-display-engine
+          - allwinner,sun9i-a80-display-engine
+          - allwinner,sun50i-a64-display-engine
+
+then:
+  properties:
+    allwinner,pipelines:
+      minItems: 2
+
+else:
+  properties:
+    allwinner,pipelines:
+      maxItems: 1
+
+examples:
+  - |
+      de: display-engine {
+          compatible = "allwinner,sun4i-a10-display-engine";
+          allwinner,pipelines = <&fe0>, <&fe1>;
+      };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-frontend.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-frontend.yaml
new file mode 100644
index 000000000000..3eb1c2bbf4e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-display-frontend.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-display-frontend.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Display Engine Frontend Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The display engine frontend does formats conversion, scaling,
+  deinterlacing and color space conversion.
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-display-frontend
+      - allwinner,sun5i-a13-display-frontend
+      - allwinner,sun6i-a31-display-frontend
+      - allwinner,sun7i-a20-display-frontend
+      - allwinner,sun8i-a23-display-frontend
+      - allwinner,sun8i-a33-display-frontend
+      - allwinner,sun9i-a80-display-frontend
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The frontend interface clock
+      - description: The frontend module clock
+      - description: The frontend DRAM clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnects:
+    maxItems: 1
+
+  # FIXME: This should be made required eventually once every SoC will
+  # have the MBUS declared.
+  interconnect-names:
+    const: dma-mem
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun4i-a10-ccu.h>
+    #include <dt-bindings/reset/sun4i-a10-ccu.h>
+
+    fe0: display-frontend@1e00000 {
+        compatible = "allwinner,sun4i-a10-display-frontend";
+        reg = <0x01e00000 0x20000>;
+        interrupts = <47>;
+        clocks = <&ccu CLK_AHB_DE_FE0>, <&ccu CLK_DE_FE0>,
+                 <&ccu CLK_DRAM_DE_FE0>;
+        clock-names = "ahb", "mod",
+                      "ram";
+        resets = <&ccu RST_DE_FE0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            fe0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                fe0_out_be0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&be0_in_fe0>;
+                };
+
+                fe0_out_be1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&be1_in_fe0>;
+                };
+            };
+        };
+    };
+
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-hdmi.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-hdmi.yaml
new file mode 100644
index 000000000000..5d4915aed1e2
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-hdmi.yaml
@@ -0,0 +1,183 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-hdmi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 HDMI Controller Device Tree Bindings
+
+description: |
+  The HDMI Encoder supports the HDMI video and audio outputs, and does
+  CEC. It is one end of the pipeline.
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    oneOf:
+      - const: allwinner,sun4i-a10-hdmi
+      - const: allwinner,sun5i-a10s-hdmi
+      - const: allwinner,sun6i-a31-hdmi
+      - items:
+        - const: allwinner,sun7i-a20-hdmi
+        - const: allwinner,sun5i-a10s-hdmi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    oneOf:
+      - items:
+        - description: The HDMI interface clock
+        - description: The HDMI module clock
+        - description: The first video PLL
+        - description: The second video PLL
+
+      - items:
+        - description: The HDMI interface clock
+        - description: The HDMI module clock
+        - description: The HDMI DDC clock
+        - description: The first video PLL
+        - description: The second video PLL
+
+  clock-names:
+    oneOf:
+      - items:
+        - const: ahb
+        - const: mod
+        - const: pll-0
+        - const: pll-1
+
+      - items:
+        - const: ahb
+        - const: mod
+        - const: ddc
+        - const: pll-0
+        - const: pll-1
+
+  resets:
+    maxItems: 1
+
+  dmas:
+    items:
+      - description: DDC Transmission DMA Channel
+      - description: DDC Reception DMA Channel
+      - description: Audio Transmission DMA Channel
+
+  dma-names:
+    items:
+      - const: ddc-tx
+      - const: ddc-rx
+      - const: audio-tx
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller. Usually an HDMI
+          connector.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - dmas
+  - dma-names
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun6i-a31-hdmi
+
+then:
+  properties:
+    clocks:
+      minItems: 5
+
+    clock-names:
+      minItems: 5
+
+  required:
+    - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun4i-a10-ccu.h>
+    #include <dt-bindings/dma/sun4i-a10.h>
+    #include <dt-bindings/reset/sun4i-a10-ccu.h>
+
+    hdmi: hdmi@1c16000 {
+        compatible = "allwinner,sun4i-a10-hdmi";
+        reg = <0x01c16000 0x1000>;
+        interrupts = <58>;
+        clocks = <&ccu CLK_AHB_HDMI0>, <&ccu CLK_HDMI>,
+                 <&ccu CLK_PLL_VIDEO0_2X>,
+                 <&ccu CLK_PLL_VIDEO1_2X>;
+        clock-names = "ahb", "mod", "pll-0", "pll-1";
+        dmas = <&dma SUN4I_DMA_NORMAL 16>,
+               <&dma SUN4I_DMA_NORMAL 16>,
+               <&dma SUN4I_DMA_DEDICATED 24>;
+        dma-names = "ddc-tx", "ddc-rx", "audio-tx";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            hdmi_in: port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                hdmi_in_tcon0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_out_hdmi>;
+                };
+
+                hdmi_in_tcon1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_out_hdmi>;
+                };
+            };
+
+            hdmi_out: port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
new file mode 100644
index 000000000000..86ad617d2327
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tcon.yaml
@@ -0,0 +1,676 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-tcon.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Timings Controller (TCON) Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The TCON acts as a timing controller for RGB, LVDS and TV
+  interfaces.
+
+properties:
+  "#clock-cells":
+    const: 0
+
+  compatible:
+    oneOf:
+      - const: allwinner,sun4i-a10-tcon
+      - const: allwinner,sun5i-a13-tcon
+      - const: allwinner,sun6i-a31-tcon
+      - const: allwinner,sun6i-a31s-tcon
+      - const: allwinner,sun7i-a20-tcon
+      - const: allwinner,sun8i-a23-tcon
+      - const: allwinner,sun8i-a33-tcon
+      - const: allwinner,sun8i-a83t-tcon-lcd
+      - const: allwinner,sun8i-a83t-tcon-tv
+      - const: allwinner,sun8i-r40-tcon-tv
+      - const: allwinner,sun8i-v3s-tcon
+      - const: allwinner,sun9i-a80-tcon-lcd
+      - const: allwinner,sun9i-a80-tcon-tv
+
+      - items:
+        - enum:
+            - allwinner,sun50i-a64-tcon-lcd
+        - const: allwinner,sun8i-a83t-tcon-lcd
+
+      - items:
+        - enum:
+          - allwinner,sun8i-h3-tcon-tv
+          - allwinner,sun50i-a64-tcon-tv
+          - allwinner,sun50i-h6-tcon-tv
+        - const: allwinner,sun8i-a83t-tcon-tv
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 4
+
+  clock-names:
+    minItems: 1
+    maxItems: 4
+
+  clock-output-names:
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/string-array
+      - maxItems: 1
+    description:
+      Name of the LCD pixel clock created.
+
+  dmas:
+    maxItems: 1
+
+  resets:
+    anyOf:
+      - items:
+        - description: TCON Reset Line
+
+      - items:
+        - description: TCON Reset Line
+        - description: TCON LVDS Reset Line
+
+      - items:
+        - description: TCON Reset Line
+        - description: TCON eDP Reset Line
+
+      - items:
+        - description: TCON Reset Line
+        - description: TCON eDP Reset Line
+        - description: TCON LVDS Reset Line
+
+  reset-names:
+    oneOf:
+      - const: lcd
+
+      - items:
+        - const: lcd
+        - const: lvds
+
+      - items:
+        - const: lcd
+        - const: edp
+
+      - items:
+        - const: lcd
+        - const: edp
+        - const: lvds
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+        patternProperties:
+          "^endpoint(@[0-9])$":
+            type: object
+
+            properties:
+              allwinner,tcon-channel:
+                $ref: /schemas/types.yaml#/definitions/uint32
+                description: |
+                  TCON can have 1 or 2 channels, usually with the
+                  first channel being used for the panels interfaces
+                  (RGB, LVDS, etc.), and the second being used for the
+                  outputs that require another controller (TV Encoder,
+                  HDMI, etc.).
+
+                  If that property is present, specifies the TCON
+                  channel the endpoint is associated to. If that
+                  property is not present, the endpoint number will be
+                  used as the channel number.
+
+            unevaluatedProperties: true
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun4i-a10-tcon
+              - allwinner,sun5i-a13-tcon
+              - allwinner,sun7i-a20-tcon
+
+    then:
+      properties:
+        clocks:
+          minItems: 3
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+            - const: tcon-ch1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+
+    then:
+      properties:
+        clocks:
+          minItems: 4
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+            - const: tcon-ch1
+            - const: lvds-alt
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+
+    then:
+      properties:
+        clocks:
+          minItems: 3
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+            - const: lvds-alt
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun8i-a83t-tcon-lcd
+              - allwinner,sun8i-v3s-tcon
+              - allwinner,sun9i-a80-tcon-lcd
+
+    then:
+      properties:
+        clocks:
+          minItems: 2
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch0
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun8i-a83t-tcon-tv
+              - allwinner,sun8i-r40-tcon-tv
+              - allwinner,sun9i-a80-tcon-tv
+
+    then:
+      properties:
+        clocks:
+          minItems: 2
+
+        clock-names:
+          items:
+            - const: ahb
+            - const: tcon-ch1
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun5i-a13-tcon
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+              - allwinner,sun7i-a20-tcon
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+              - allwinner,sun8i-v3s-tcon
+              - allwinner,sun9i-a80-tcon-lcd
+              - allwinner,sun4i-a10-tcon
+              - allwinner,sun8i-a83t-tcon-lcd
+
+    then:
+      required:
+        - "#clock-cells"
+        - clock-output-names
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+              - allwinner,sun8i-a83t-tcon-lcd
+
+    then:
+      properties:
+        resets:
+          minItems: 2
+
+        reset-names:
+          items:
+            - const: lcd
+            - const: lvds
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun9i-a80-tcon-lcd
+
+    then:
+      properties:
+        resets:
+          minItems: 3
+
+        reset-names:
+          items:
+            - const: lcd
+            - const: edp
+            - const: lvds
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun9i-a80-tcon-tv
+
+    then:
+      properties:
+        resets:
+          minItems: 2
+
+        reset-names:
+          items:
+            - const: lcd
+            - const: edp
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - allwinner,sun4i-a10-tcon
+              - allwinner,sun5i-a13-tcon
+              - allwinner,sun6i-a31-tcon
+              - allwinner,sun6i-a31s-tcon
+              - allwinner,sun7i-a20-tcon
+              - allwinner,sun8i-a23-tcon
+              - allwinner,sun8i-a33-tcon
+
+    then:
+      required:
+        - dmas
+
+examples:
+  - |
+    #include <dt-bindings/dma/sun4i-a10.h>
+
+    /*
+     * This comes from the clock/sun4i-a10-ccu.h and
+     * reset/sun4i-a10-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_AHB_LCD0	56
+    #define CLK_TCON0_CH0	149
+    #define CLK_TCON0_CH1	155
+    #define RST_TCON0		11
+
+    lcd-controller@1c0c000 {
+        compatible = "allwinner,sun4i-a10-tcon";
+        reg = <0x01c0c000 0x1000>;
+        interrupts = <44>;
+        resets = <&ccu RST_TCON0>;
+        reset-names = "lcd";
+        clocks = <&ccu CLK_AHB_LCD0>,
+                 <&ccu CLK_TCON0_CH0>,
+                 <&ccu CLK_TCON0_CH1>;
+        clock-names = "ahb",
+                      "tcon-ch0",
+                      "tcon-ch1";
+        clock-output-names = "tcon0-pixel-clock";
+        #clock-cells = <0>;
+        dmas = <&dma SUN4I_DMA_DEDICATED 14>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&be0_out_tcon0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&be1_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&hdmi_in_tcon0>;
+                    allwinner,tcon-channel = <1>;
+                };
+            };
+        };
+    };
+
+    #undef CLK_AHB_LCD0
+    #undef CLK_TCON0_CH0
+    #undef CLK_TCON0_CH1
+    #undef RST_TCON0
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun6i-a31-ccu.h and
+     * reset/sun6i-a31-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_PLL_MIPI	15
+    #define CLK_AHB1_LCD0	47
+    #define CLK_LCD0_CH0	127
+    #define CLK_LCD0_CH1	129
+    #define RST_AHB1_LCD0	27
+    #define RST_AHB1_LVDS	41
+
+    lcd-controller@1c0c000 {
+        compatible = "allwinner,sun6i-a31-tcon";
+        reg = <0x01c0c000 0x1000>;
+        interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+        dmas = <&dma 11>;
+        resets = <&ccu RST_AHB1_LCD0>, <&ccu RST_AHB1_LVDS>;
+        reset-names = "lcd", "lvds";
+        clocks = <&ccu CLK_AHB1_LCD0>,
+                 <&ccu CLK_LCD0_CH0>,
+                 <&ccu CLK_LCD0_CH1>,
+                 <&ccu CLK_PLL_MIPI>;
+        clock-names = "ahb",
+                      "tcon-ch0",
+                      "tcon-ch1",
+                      "lvds-alt";
+        clock-output-names = "tcon0-pixel-clock";
+        #clock-cells = <0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&drc0_out_tcon0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&drc1_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&hdmi_in_tcon0>;
+                    allwinner,tcon-channel = <1>;
+                };
+            };
+        };
+    };
+
+    #undef CLK_PLL_MIPI
+    #undef CLK_AHB1_LCD0
+    #undef CLK_LCD0_CH0
+    #undef CLK_LCD0_CH1
+    #undef RST_AHB1_LCD0
+    #undef RST_AHB1_LVDS
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun9i-a80-ccu.h and
+     * reset/sun9i-a80-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_LCD0	102
+    #define CLK_LCD0		58
+    #define RST_BUS_LCD0	22
+    #define RST_BUS_EDP		24
+    #define RST_BUS_LVDS	25
+
+    lcd-controller@3c00000 {
+        compatible = "allwinner,sun9i-a80-tcon-lcd";
+        reg = <0x03c00000 0x10000>;
+        interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_LCD0>, <&ccu CLK_LCD0>;
+        clock-names = "ahb", "tcon-ch0";
+        resets = <&ccu RST_BUS_LCD0>, <&ccu RST_BUS_EDP>, <&ccu RST_BUS_LVDS>;
+        reset-names = "lcd", "edp", "lvds";
+        clock-output-names = "tcon0-pixel-clock";
+        #clock-cells = <0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&drc0_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+    #undef CLK_BUS_TCON0
+    #undef CLK_TCON0
+    #undef RST_BUS_TCON0
+    #undef RST_BUS_EDP
+    #undef RST_BUS_LVDS
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-a83t-ccu.h and
+     * reset/sun8i-a83t-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_TCON0	36
+    #define CLK_TCON0		85
+    #define RST_BUS_TCON0	22
+    #define RST_BUS_LVDS	31
+
+    lcd-controller@1c0c000 {
+        compatible = "allwinner,sun8i-a83t-tcon-lcd";
+        reg = <0x01c0c000 0x1000>;
+        interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_TCON0>, <&ccu CLK_TCON0>;
+        clock-names = "ahb", "tcon-ch0";
+        clock-output-names = "tcon-pixel-clock";
+        #clock-cells = <0>;
+        resets = <&ccu RST_BUS_TCON0>, <&ccu RST_BUS_LVDS>;
+        reset-names = "lcd", "lvds";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&mixer0_out_tcon0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&mixer1_out_tcon0>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+    #undef CLK_BUS_TCON0
+    #undef CLK_TCON0
+    #undef RST_BUS_TCON0
+    #undef RST_BUS_LVDS
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-r40-ccu.h and
+     * reset/sun8i-r40-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+
+    #define CLK_BUS_TCON_TV0	73
+    #define RST_BUS_TCON_TV0	49
+
+    tcon_tv0: lcd-controller@1c73000 {
+        compatible = "allwinner,sun8i-r40-tcon-tv";
+        reg = <0x01c73000 0x1000>;
+        interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_TCON_TV0>, <&tcon_top 0>;
+        clock-names = "ahb", "tcon-ch1";
+        resets = <&ccu RST_BUS_TCON_TV0>;
+        reset-names = "lcd";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0>;
+
+                endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon_top_mixer0_out_tcon_tv0>;
+                };
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon_top_mixer1_out_tcon_tv0>;
+                };
+            };
+
+            tcon_tv0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon_top_hdmi_in_tcon_tv0>;
+                };
+            };
+        };
+    };
+
+    #undef CLK_BUS_TCON_TV0
+    #undef RST_BUS_TCON_TV0
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml
new file mode 100644
index 000000000000..5d5d39665119
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun4i-a10-tv-encoder.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun4i-a10-tv-encoder.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 TV Encoder Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    const: allwinner,sun4i-a10-tv-encoder
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  port:
+    type: object
+    description:
+      A port node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt. The
+      first port should be the input endpoint, usually coming from the
+      associated TCON.
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - resets
+  - port
+
+additionalProperties: false
+
+examples:
+  - |
+    tve0: tv-encoder@1c0a000 {
+        compatible = "allwinner,sun4i-a10-tv-encoder";
+        reg = <0x01c0a000 0x1000>;
+        clocks = <&ahb_gates 34>;
+        resets = <&tcon_ch0_clk 0>;
+
+        port {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            tve0_in_tcon0: endpoint@0 {
+                reg = <0>;
+                remote-endpoint = <&tcon0_out_tve0>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-drc.yaml b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-drc.yaml
new file mode 100644
index 000000000000..0c1ce55940e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-drc.yaml
@@ -0,0 +1,138 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun6i-a31-drc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 Dynamic Range Controller Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The DRC (Dynamic Range Controller) allows to dynamically adjust
+  pixel brightness/contrast based on histogram measurements for LCD
+  content adaptive backlight control.
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun6i-a31-drc
+      - allwinner,sun6i-a31s-drc
+      - allwinner,sun8i-a23-drc
+      - allwinner,sun8i-a33-drc
+      - allwinner,sun9i-a80-drc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The DRC interface clock
+      - description: The DRC module clock
+      - description: The DRC DRAM clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    #include <dt-bindings/clock/sun6i-a31-ccu.h>
+    #include <dt-bindings/reset/sun6i-a31-ccu.h>
+
+    drc0: drc@1e70000 {
+        compatible = "allwinner,sun6i-a31-drc";
+        reg = <0x01e70000 0x10000>;
+        interrupts = <GIC_SPI 91 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_AHB1_DRC0>, <&ccu CLK_IEP_DRC0>,
+                 <&ccu CLK_DRAM_DRC0>;
+        clock-names = "ahb", "mod",
+                      "ram";
+        resets = <&ccu RST_AHB1_DRC0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            drc0_in: port@0 {
+                reg = <0>;
+
+                drc0_in_be0: endpoint {
+                    remote-endpoint = <&be0_out_drc0>;
+                };
+            };
+
+            drc0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                drc0_out_tcon0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_in_drc0>;
+                };
+
+                drc0_out_tcon1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_in_drc0>;
+                };
+            };
+        };
+    };
+
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml
index 0f7074977c04..9e90c2b00960 100644
--- a/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml
+++ b/Documentation/devicetree/bindings/display/allwinner,sun6i-a31-mipi-dsi.yaml
@@ -15,7 +15,9 @@ properties:
   "#size-cells": true
 
   compatible:
-    const: allwinner,sun6i-a31-mipi-dsi
+    enum:
+      - allwinner,sun6i-a31-mipi-dsi
+      - allwinner,sun50i-a64-mipi-dsi
 
   reg:
     maxItems: 1
@@ -24,6 +26,8 @@ properties:
     maxItems: 1
 
   clocks:
+    minItems: 1
+    maxItems: 2
     items:
       - description: Bus Clock
       - description: Module Clock
@@ -63,13 +67,38 @@ required:
   - reg
   - interrupts
   - clocks
-  - clock-names
   - phys
   - phy-names
   - resets
   - vcc-dsi-supply
   - port
 
+allOf:
+  - if:
+      properties:
+         compatible:
+           contains:
+             const: allwinner,sun6i-a31-mipi-dsi
+
+    then:
+        properties:
+          clocks:
+            minItems: 2
+
+        required:
+          - clock-names
+
+  - if:
+      properties:
+         compatible:
+           contains:
+             const: allwinner,sun50i-a64-mipi-dsi
+
+    then:
+        properties:
+          clocks:
+            minItems: 1
+
 additionalProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-de2-mixer.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-de2-mixer.yaml
new file mode 100644
index 000000000000..1dee641e3ea1
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-de2-mixer.yaml
@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-a83t-de2-mixer.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner Display Engine 2.0 Mixer Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun8i-a83t-de2-mixer-0
+      - allwinner,sun8i-a83t-de2-mixer-1
+      - allwinner,sun8i-h3-de2-mixer-0
+      - allwinner,sun8i-r40-de2-mixer-0
+      - allwinner,sun8i-r40-de2-mixer-1
+      - allwinner,sun8i-v3s-de2-mixer
+      - allwinner,sun50i-a64-de2-mixer-0
+      - allwinner,sun50i-a64-de2-mixer-1
+      - allwinner,sun50i-h6-de3-mixer-0
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The mixer interface clock
+      - description: The mixer module clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun8i-de2.h>
+    #include <dt-bindings/reset/sun8i-de2.h>
+
+    mixer0: mixer@1100000 {
+        compatible = "allwinner,sun8i-a83t-de2-mixer-0";
+        reg = <0x01100000 0x100000>;
+        clocks = <&display_clocks CLK_BUS_MIXER0>,
+                 <&display_clocks CLK_MIXER0>;
+        clock-names = "bus",
+                      "mod";
+        resets = <&display_clocks RST_MIXER0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            mixer0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                mixer0_out_tcon0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&tcon0_in_mixer0>;
+                };
+
+                mixer0_out_tcon1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&tcon1_in_mixer0>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-dw-hdmi.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-dw-hdmi.yaml
new file mode 100644
index 000000000000..4d6795690ac3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-dw-hdmi.yaml
@@ -0,0 +1,273 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-a83t-dw-hdmi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A83t DWC HDMI TX Encoder Device Tree Bindings
+
+description: |
+  The HDMI transmitter is a Synopsys DesignWare HDMI 1.4 TX controller
+  IP with Allwinner\'s own PHY IP. It supports audio and video outputs
+  and CEC.
+
+  These DT bindings follow the Synopsys DWC HDMI TX bindings defined
+  in Documentation/devicetree/bindings/display/bridge/dw_hdmi.txt with
+  the following device-specific properties.
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 0
+
+  compatible:
+    oneOf:
+      - const: allwinner,sun8i-a83t-dw-hdmi
+      - const: allwinner,sun50i-h6-dw-hdmi
+
+      - items:
+        - enum:
+          - allwinner,sun8i-h3-dw-hdmi
+          - allwinner,sun8i-r40-dw-hdmi
+          - allwinner,sun50i-a64-dw-hdmi
+        - const: allwinner,sun8i-a83t-dw-hdmi
+
+  reg:
+    maxItems: 1
+
+  reg-io-width:
+    const: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    minItems: 3
+    maxItems: 6
+    items:
+      - description: Bus Clock
+      - description: Register Clock
+      - description: TMDS Clock
+      - description: HDMI CEC Clock
+      - description: HDCP Clock
+      - description: HDCP Bus Clock
+
+  clock-names:
+    minItems: 3
+    maxItems: 6
+    items:
+      - const: iahb
+      - const: isfr
+      - const: tmds
+      - const: cec
+      - const: hdcp
+      - const: hdcp-bus
+
+  resets:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: HDMI Controller Reset
+      - description: HDCP Reset
+
+  reset-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: ctrl
+      - const: hdcp
+
+  phys:
+    maxItems: 1
+    description:
+      Phandle to the DWC HDMI PHY.
+
+  phy-names:
+    const: phy
+
+  hvcc-supply:
+    description:
+      The VCC power supply of the controller
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller. Usually the associated
+          TCON.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller. Usually an HDMI
+          connector.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - reg-io-width
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - phys
+  - phy-names
+  - ports
+
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun50i-h6-dw-hdmi
+
+then:
+  properties:
+    clocks:
+      minItems: 6
+
+    clock-names:
+      minItems: 6
+
+    resets:
+      minItems: 2
+
+    reset-names:
+      minItems: 2
+
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun8i-a83t-ccu.h and
+     * reset/sun8i-a83t-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+    #define CLK_BUS_HDMI	39
+    #define CLK_HDMI		93
+    #define CLK_HDMI_SLOW	94
+    #define RST_BUS_HDMI1	26
+
+    hdmi@1ee0000 {
+        compatible = "allwinner,sun8i-a83t-dw-hdmi";
+        reg = <0x01ee0000 0x10000>;
+        reg-io-width = <1>;
+        interrupts = <GIC_SPI 88 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_HDMI>, <&ccu CLK_HDMI_SLOW>,
+                 <&ccu CLK_HDMI>;
+        clock-names = "iahb", "isfr", "tmds";
+        resets = <&ccu RST_BUS_HDMI1>;
+        reset-names = "ctrl";
+        phys = <&hdmi_phy>;
+        phy-names = "phy";
+        pinctrl-names = "default";
+        pinctrl-0 = <&hdmi_pins>;
+        status = "disabled";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&tcon1_out_hdmi>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+    /* Cleanup after ourselves */
+    #undef CLK_BUS_HDMI
+    #undef CLK_HDMI
+    #undef CLK_HDMI_SLOW
+
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    /*
+     * This comes from the clock/sun50i-h6-ccu.h and
+     * reset/sun50i-h6-ccu.h headers, but we can't include them since
+     * it would trigger a bunch of warnings for redefinitions of
+     * symbols with the other example.
+     */
+    #define CLK_BUS_HDMI	126
+    #define CLK_BUS_HDCP	137
+    #define CLK_HDMI		123
+    #define CLK_HDMI_SLOW	124
+    #define CLK_HDMI_CEC	125
+    #define CLK_HDCP		136
+    #define RST_BUS_HDMI_SUB	57
+    #define RST_BUS_HDCP	62
+
+    hdmi@6000000 {
+        compatible = "allwinner,sun50i-h6-dw-hdmi";
+        reg = <0x06000000 0x10000>;
+        reg-io-width = <1>;
+        interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_HDMI>, <&ccu CLK_HDMI_SLOW>,
+                 <&ccu CLK_HDMI>, <&ccu CLK_HDMI_CEC>,
+                 <&ccu CLK_HDCP>, <&ccu CLK_BUS_HDCP>;
+        clock-names = "iahb", "isfr", "tmds", "cec", "hdcp",
+                      "hdcp-bus";
+        resets = <&ccu RST_BUS_HDMI_SUB>, <&ccu RST_BUS_HDCP>;
+        reset-names = "ctrl", "hdcp";
+        phys = <&hdmi_phy>;
+        phy-names = "phy";
+        pinctrl-names = "default";
+        pinctrl-0 = <&hdmi_pins>;
+        status = "disabled";
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            port@0 {
+                reg = <0>;
+
+                endpoint {
+                    remote-endpoint = <&tcon_top_hdmi_out_hdmi>;
+                };
+            };
+
+            port@1 {
+                reg = <1>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-hdmi-phy.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-hdmi-phy.yaml
new file mode 100644
index 000000000000..501cec16168c
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-a83t-hdmi-phy.yaml
@@ -0,0 +1,117 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-a83t-hdmi-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A83t HDMI PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 0
+
+  compatible:
+    enum:
+      - allwinner,sun8i-a83t-hdmi-phy
+      - allwinner,sun8i-h3-hdmi-phy
+      - allwinner,sun8i-r40-hdmi-phy
+      - allwinner,sun50i-a64-hdmi-phy
+      - allwinner,sun50i-h6-hdmi-phy
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 2
+    maxItems: 4
+    items:
+      - description: Bus Clock
+      - description: Module Clock
+      - description: Parent of the PHY clock
+      - description: Second possible parent of the PHY clock
+
+  clock-names:
+    minItems: 2
+    maxItems: 4
+    items:
+      - const: bus
+      - const: mod
+      - const: pll-0
+      - const: pll-1
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: phy
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+
+if:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun8i-r40-hdmi-phy
+
+then:
+  properties:
+    clocks:
+      minItems: 4
+
+    clock-names:
+      minItems: 4
+
+else:
+  if:
+    properties:
+      compatible:
+        contains:
+          enum:
+            - allwinner,sun8i-h3-hdmi-phy
+            - allwinner,sun50i-a64-hdmi-phy
+
+  then:
+    properties:
+      clocks:
+        minItems: 3
+
+      clock-names:
+        minItems: 3
+
+  else:
+    properties:
+      clocks:
+        maxItems: 2
+
+      clock-names:
+        maxItems: 2
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun8i-a83t-ccu.h>
+    #include <dt-bindings/reset/sun8i-a83t-ccu.h>
+
+    hdmi_phy: hdmi-phy@1ef0000 {
+        compatible = "allwinner,sun8i-a83t-hdmi-phy";
+        reg = <0x01ef0000 0x10000>;
+        clocks = <&ccu CLK_BUS_HDMI>, <&ccu CLK_HDMI_SLOW>;
+        clock-names = "bus", "mod";
+        resets = <&ccu RST_BUS_HDMI0>;
+        reset-names = "phy";
+        #phy-cells = <0>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun8i-r40-tcon-top.yaml b/Documentation/devicetree/bindings/display/allwinner,sun8i-r40-tcon-top.yaml
new file mode 100644
index 000000000000..b98ca609824b
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun8i-r40-tcon-top.yaml
@@ -0,0 +1,382 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun8i-r40-tcon-top.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner R40 TCON TOP Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  TCON TOPs main purpose is to configure whole display pipeline. It
+  determines relationships between mixers and TCONs, selects source
+  TCON for HDMI, muxes LCD and TV encoder GPIO output, selects TV
+  encoder clock source and contains additional TV TCON and DSI gates.
+
+  It allows display pipeline to be configured in very different ways:
+
+                                  / LCD0/LVDS0
+                   / [0] TCON-LCD0
+                   |              \ MIPI DSI
+   mixer0          |
+          \        / [1] TCON-LCD1 - LCD1/LVDS1
+           TCON-TOP
+          /        \ [2] TCON-TV0 [0] - TVE0/RGB
+   mixer1          |                  \
+                   |                   TCON-TOP - HDMI
+                   |                  /
+                   \ [3] TCON-TV1 [1] - TVE1/RGB
+
+  Note that both TCON TOP references same physical unit. Both mixers
+  can be connected to any TCON. Not all TCON TOP variants support all
+  features.
+
+properties:
+  "#clock-cells":
+    const: 1
+
+  compatible:
+    enum:
+      - allwinner,sun8i-r40-tcon-top
+      - allwinner,sun50i-h6-tcon-top
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 2
+    maxItems: 6
+    items:
+      - description: The TCON TOP interface clock
+      - description: The TCON TOP TV0 clock
+      - description: The TCON TOP TVE0 clock
+      - description: The TCON TOP TV1 clock
+      - description: The TCON TOP TVE1 clock
+      - description: The TCON TOP MIPI DSI clock
+
+  clock-names:
+    minItems: 2
+    maxItems: 6
+    items:
+      - const: bus
+      - const: tcon-tv0
+      - const: tve0
+      - const: tcon-tv1
+      - const: tve1
+      - const: dsi
+
+  clock-output-names:
+    minItems: 1
+    maxItems: 3
+    description: >
+      The first item is the name of the clock created for the TV0
+      channel, the second item is the name of the TCON TV1 channel
+      clock and the third one is the name of the DSI channel clock.
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+      All ports should have only one endpoint connected to
+      remote endpoint.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoint for Mixer 0 mux.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoint for Mixer 0 mux
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg: true
+
+        patternProperties:
+          "^endpoint@[0-9]$":
+            type: object
+
+            properties:
+              reg:
+                description: |
+                  ID of the target TCON
+
+            required:
+              - reg
+
+        required:
+          - "#address-cells"
+          - "#size-cells"
+
+        additionalProperties: false
+
+      port@2:
+        type: object
+        description: |
+          Input endpoint for Mixer 1 mux.
+
+      port@3:
+        type: object
+        description: |
+          Output endpoint for Mixer 1 mux
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg: true
+
+        patternProperties:
+          "^endpoint@[0-9]$":
+            type: object
+
+            properties:
+              reg:
+                description: |
+                  ID of the target TCON
+
+            required:
+              - reg
+
+        required:
+          - "#address-cells"
+          - "#size-cells"
+
+        additionalProperties: false
+
+      port@4:
+        type: object
+        description: |
+          Input endpoint for HDMI mux.
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg: true
+
+        patternProperties:
+          "^endpoint@[0-9]$":
+            type: object
+
+            properties:
+              reg:
+                description: |
+                  ID of the target TCON
+
+            required:
+              - reg
+
+        required:
+          - "#address-cells"
+          - "#size-cells"
+
+        additionalProperties: false
+
+      port@5:
+        type: object
+        description: |
+          Output endpoint for HDMI mux
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+      - port@4
+      - port@5
+
+    additionalProperties: false
+
+required:
+  - "#clock-cells"
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - clock-output-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+if:
+  properties:
+    compatible:
+      contains:
+        const: allwinner,sun50i-h6-tcon-top
+
+then:
+  properties:
+    clocks:
+      maxItems: 2
+
+    clock-output-names:
+      maxItems: 1
+
+else:
+  properties:
+    clocks:
+      minItems: 6
+
+    clock-output-names:
+      minItems: 3
+
+    ports:
+      required:
+        - port@2
+        - port@3
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    #include <dt-bindings/clock/sun8i-r40-ccu.h>
+    #include <dt-bindings/reset/sun8i-r40-ccu.h>
+
+      tcon_top: tcon-top@1c70000 {
+          compatible = "allwinner,sun8i-r40-tcon-top";
+          reg = <0x01c70000 0x1000>;
+          clocks = <&ccu CLK_BUS_TCON_TOP>,
+                   <&ccu CLK_TCON_TV0>,
+                   <&ccu CLK_TVE0>,
+                   <&ccu CLK_TCON_TV1>,
+                   <&ccu CLK_TVE1>,
+                   <&ccu CLK_DSI_DPHY>;
+          clock-names = "bus",
+                        "tcon-tv0",
+                        "tve0",
+                        "tcon-tv1",
+                        "tve1",
+                        "dsi";
+          clock-output-names = "tcon-top-tv0",
+                               "tcon-top-tv1",
+                               "tcon-top-dsi";
+          resets = <&ccu RST_BUS_TCON_TOP>;
+          #clock-cells = <1>;
+
+          ports {
+              #address-cells = <1>;
+              #size-cells = <0>;
+
+              tcon_top_mixer0_in: port@0 {
+                  reg = <0>;
+
+                  tcon_top_mixer0_in_mixer0: endpoint {
+                      remote-endpoint = <&mixer0_out_tcon_top>;
+                  };
+              };
+
+              tcon_top_mixer0_out: port@1 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <1>;
+
+                  tcon_top_mixer0_out_tcon_lcd0: endpoint@0 {
+                      reg = <0>;
+                  };
+
+                  tcon_top_mixer0_out_tcon_lcd1: endpoint@1 {
+                      reg = <1>;
+                  };
+
+                  tcon_top_mixer0_out_tcon_tv0: endpoint@2 {
+                      reg = <2>;
+                      remote-endpoint = <&tcon_tv0_in_tcon_top_mixer0>;
+                  };
+
+                  tcon_top_mixer0_out_tcon_tv1: endpoint@3 {
+                      reg = <3>;
+                      remote-endpoint = <&tcon_tv1_in_tcon_top_mixer0>;
+                  };
+              };
+
+              tcon_top_mixer1_in: port@2 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <2>;
+
+                  tcon_top_mixer1_in_mixer1: endpoint@1 {
+                      reg = <1>;
+                      remote-endpoint = <&mixer1_out_tcon_top>;
+                  };
+              };
+
+              tcon_top_mixer1_out: port@3 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <3>;
+
+                  tcon_top_mixer1_out_tcon_lcd0: endpoint@0 {
+                      reg = <0>;
+                  };
+
+                  tcon_top_mixer1_out_tcon_lcd1: endpoint@1 {
+                      reg = <1>;
+                  };
+
+                  tcon_top_mixer1_out_tcon_tv0: endpoint@2 {
+                      reg = <2>;
+                      remote-endpoint = <&tcon_tv0_in_tcon_top_mixer1>;
+                  };
+
+                  tcon_top_mixer1_out_tcon_tv1: endpoint@3 {
+                      reg = <3>;
+                      remote-endpoint = <&tcon_tv1_in_tcon_top_mixer1>;
+                  };
+              };
+
+              tcon_top_hdmi_in: port@4 {
+                  #address-cells = <1>;
+                  #size-cells = <0>;
+                  reg = <4>;
+
+                  tcon_top_hdmi_in_tcon_tv0: endpoint@0 {
+                      reg = <0>;
+                      remote-endpoint = <&tcon_tv0_out_tcon_top>;
+                  };
+
+                  tcon_top_hdmi_in_tcon_tv1: endpoint@1 {
+                      reg = <1>;
+                      remote-endpoint = <&tcon_tv1_out_tcon_top>;
+                  };
+              };
+
+              tcon_top_hdmi_out: port@5 {
+                  reg = <5>;
+
+                  tcon_top_hdmi_out_hdmi: endpoint {
+                      remote-endpoint = <&hdmi_in_tcon_top>;
+                  };
+              };
+          };
+      };
+
+...
diff --git a/Documentation/devicetree/bindings/display/allwinner,sun9i-a80-deu.yaml b/Documentation/devicetree/bindings/display/allwinner,sun9i-a80-deu.yaml
new file mode 100644
index 000000000000..96de41d32b3e
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/allwinner,sun9i-a80-deu.yaml
@@ -0,0 +1,133 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/allwinner,sun9i-a80-deu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A80 Detail Enhancement Unit Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  The DEU (Detail Enhancement Unit), found in the Allwinner A80 SoC,
+  can sharpen the display content in both luma and chroma channels.
+
+properties:
+  compatible:
+    const: allwinner,sun9i-a80-deu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The DEU interface clock
+      - description: The DEU module clock
+      - description: The DEU DRAM clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description: |
+      A ports node with endpoint definitions as defined in
+      Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: |
+          Input endpoints of the controller.
+
+      port@1:
+        type: object
+        description: |
+          Output endpoints of the controller.
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+      - port@1
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    #include <dt-bindings/clock/sun9i-a80-de.h>
+    #include <dt-bindings/reset/sun9i-a80-de.h>
+
+    deu0: deu@3300000 {
+        compatible = "allwinner,sun9i-a80-deu";
+        reg = <0x03300000 0x40000>;
+        interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&de_clocks CLK_BUS_DEU0>,
+                 <&de_clocks CLK_IEP_DEU0>,
+                 <&de_clocks CLK_DRAM_DEU0>;
+        clock-names = "ahb",
+                      "mod",
+                      "ram";
+        resets = <&de_clocks RST_DEU0>;
+
+        ports {
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            deu0_in: port@0 {
+                reg = <0>;
+
+                deu0_in_fe0: endpoint {
+                    remote-endpoint = <&fe0_out_deu0>;
+                };
+            };
+
+            deu0_out: port@1 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <1>;
+
+                deu0_out_be0: endpoint@0 {
+                    reg = <0>;
+                    remote-endpoint = <&be0_in_deu0>;
+                };
+
+                deu0_out_be1: endpoint@1 {
+                    reg = <1>;
+                    remote-endpoint = <&be1_in_deu0>;
+                };
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
new file mode 100644
index 000000000000..8f373029f5d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/bridge/lvds-codec.yaml
@@ -0,0 +1,131 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/bridge/lvds-codec.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Transparent LVDS encoders and decoders
+
+maintainers:
+  - Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
+
+description: |
+  This binding supports transparent LVDS encoders and decoders that don't
+  require any configuration.
+
+  LVDS is a physical layer specification defined in ANSI/TIA/EIA-644-A. Multiple
+  incompatible data link layers have been used over time to transmit image data
+  to LVDS panels. This binding targets devices compatible with the following
+  specifications only.
+
+  [JEIDA] "Digital Interface Standards for Monitor", JEIDA-59-1999, February
+  1999 (Version 1.0), Japan Electronic Industry Development Association (JEIDA)
+  [LDI] "Open LVDS Display Interface", May 1999 (Version 0.95), National
+  Semiconductor
+  [VESA] "VESA Notebook Panel Standard", October 2007 (Version 1.0), Video
+  Electronics Standards Association (VESA)
+
+  Those devices have been marketed under the FPD-Link and FlatLink brand names
+  among others.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+        - enum:
+          - ti,ds90c185       # For the TI DS90C185 FPD-Link Serializer
+          - ti,ds90c187       # For the TI DS90C187 FPD-Link Serializer
+          - ti,sn75lvds83     # For the TI SN75LVDS83 FlatLink transmitter
+        - const: lvds-encoder # Generic LVDS encoder compatible fallback
+      - items:
+        - enum:
+          - ti,ds90cf384a     # For the DS90CF384A FPD-Link LVDS Receiver
+        - const: lvds-decoder # Generic LVDS decoders compatible fallback
+      - enum:
+        - thine,thc63lvdm83d  # For the THC63LVDM83D LVDS serializer
+
+  ports:
+    type: object
+    description: |
+      This device has two video ports. Their connections are modeled using the
+      OF graph bindings specified in Documentation/devicetree/bindings/graph.txt
+    properties:
+      port@0:
+        type: object
+        description: |
+          For LVDS encoders, port 0 is the parallel input
+          For LVDS decoders, port 0 is the LVDS input
+
+      port@1:
+        type: object
+        description: |
+          For LVDS encoders, port 1 is the LVDS output
+          For LVDS decoders, port 1 is the parallel output
+
+    required:
+      - port@0
+      - port@1
+
+  powerdown-gpios:
+    description:
+      The GPIO used to control the power down line of this device.
+    maxItems: 1
+
+required:
+  - compatible
+  - ports
+
+examples:
+  - |
+    lvds-encoder {
+      compatible = "ti,ds90c185", "lvds-encoder";
+
+      ports {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        port@0 {
+          reg = <0>;
+
+          lvds_enc_in: endpoint {
+            remote-endpoint = <&display_out_rgb>;
+          };
+        };
+
+        port@1 {
+          reg = <1>;
+
+          lvds_enc_out: endpoint {
+            remote-endpoint = <&lvds_panel_in>;
+          };
+        };
+      };
+    };
+
+  - |
+    lvds-decoder {
+      compatible = "ti,ds90cf384a", "lvds-decoder";
+
+      ports {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        port@0 {
+          reg = <0>;
+
+          lvds_dec_in: endpoint {
+            remote-endpoint = <&display_out_lvds>;
+          };
+        };
+
+        port@1 {
+          reg = <1>;
+
+          lvds_dec_out: endpoint {
+            remote-endpoint = <&rgb_panel_in>;
+          };
+        };
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/bridge/lvds-transmitter.txt b/Documentation/devicetree/bindings/display/bridge/lvds-transmitter.txt
deleted file mode 100644
index 60091db5dfa5..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/lvds-transmitter.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-Parallel to LVDS Encoder
-------------------------
-
-This binding supports the parallel to LVDS encoders that don't require any
-configuration.
-
-LVDS is a physical layer specification defined in ANSI/TIA/EIA-644-A. Multiple
-incompatible data link layers have been used over time to transmit image data
-to LVDS panels. This binding targets devices compatible with the following
-specifications only.
-
-[JEIDA] "Digital Interface Standards for Monitor", JEIDA-59-1999, February
-1999 (Version 1.0), Japan Electronic Industry Development Association (JEIDA)
-[LDI] "Open LVDS Display Interface", May 1999 (Version 0.95), National
-Semiconductor
-[VESA] "VESA Notebook Panel Standard", October 2007 (Version 1.0), Video
-Electronics Standards Association (VESA)
-
-Those devices have been marketed under the FPD-Link and FlatLink brand names
-among others.
-
-
-Required properties:
-
-- compatible: Must be "lvds-encoder"
-
-  Any encoder compatible with this generic binding, but with additional
-  properties not listed here, must list a device specific compatible first
-  followed by this generic compatible.
-
-Required nodes:
-
-This device has two video ports. Their connections are modeled using the OF
-graph bindings specified in Documentation/devicetree/bindings/graph.txt.
-
-- Video port 0 for parallel input
-- Video port 1 for LVDS output
-
-
-Example
--------
-
-lvds-encoder {
-	compatible = "lvds-encoder";
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-
-			lvds_enc_in: endpoint {
-				remote-endpoint = <&display_out_rgb>;
-			};
-		};
-
-		port@1 {
-			reg = <1>;
-
-			lvds_enc_out: endpoint {
-				remote-endpoint = <&lvds_panel_in>;
-			};
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvdm83d.txt b/Documentation/devicetree/bindings/display/bridge/thine,thc63lvdm83d.txt
deleted file mode 100644
index fee3c88e1a17..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/thine,thc63lvdm83d.txt
+++ /dev/null
@@ -1,50 +0,0 @@
-THine Electronics THC63LVDM83D LVDS serializer
-----------------------------------------------
-
-The THC63LVDM83D is an LVDS serializer designed to support pixel data
-transmission between a host and a flat panel.
-
-Required properties:
-
-- compatible: Should be "thine,thc63lvdm83d"
-
-Optional properties:
-
-- powerdown-gpios: Power down control GPIO (the /PWDN pin, active low).
-
-Required nodes:
-
-The THC63LVDM83D has two video ports. Their connections are modeled using the
-OFgraph bindings specified in Documentation/devicetree/bindings/graph.txt.
-
-- Video port 0 for CMOS/TTL input
-- Video port 1 for LVDS output
-
-
-Example
--------
-
-	lvds_enc: encoder@0 {
-		compatible = "thine,thc63lvdm83d";
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@0 {
-				reg = <0>;
-
-				lvds_enc_in: endpoint@0 {
-					remote-endpoint = <&rgb_out>;
-				};
-			};
-
-			port@1 {
-				reg = <1>;
-
-				lvds_enc_out: endpoint@0 {
-					remote-endpoint = <&panel_in>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/display/bridge/ti,ds90c185.txt b/Documentation/devicetree/bindings/display/bridge/ti,ds90c185.txt
deleted file mode 100644
index e575f996959a..000000000000
--- a/Documentation/devicetree/bindings/display/bridge/ti,ds90c185.txt
+++ /dev/null
@@ -1,55 +0,0 @@
-Texas Instruments FPD-Link (LVDS) Serializer
---------------------------------------------
-
-The DS90C185 and DS90C187 are low-power serializers for portable
-battery-powered applications that reduces the size of the RGB
-interface between the host GPU and the display.
-
-Required properties:
-
-- compatible: Should be
-  "ti,ds90c185", "lvds-encoder"  for the TI DS90C185 FPD-Link Serializer
-  "ti,ds90c187", "lvds-encoder"  for the TI DS90C187 FPD-Link Serializer
-
-Optional properties:
-
-- powerdown-gpios: Power down control GPIO (the PDB pin, active-low)
-
-Required nodes:
-
-The devices have two video ports. Their connections are modeled using the OF
-graph bindings specified in Documentation/devicetree/bindings/graph.txt.
-
-- Video port 0 for parallel input
-- Video port 1 for LVDS output
-
-
-Example
--------
-
-lvds-encoder {
-	compatible = "ti,ds90c185", "lvds-encoder";
-
-	powerdown-gpios = <&gpio 17 GPIO_ACTIVE_LOW>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			reg = <0>;
-
-			lvds_enc_in: endpoint {
-				remote-endpoint = <&lcdc_out_rgb>;
-			};
-		};
-
-		port@1 {
-			reg = <1>;
-
-			lvds_enc_out: endpoint {
-				remote-endpoint = <&lvds_panel_in>;
-			};
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/display/dsi-controller.yaml b/Documentation/devicetree/bindings/display/dsi-controller.yaml
new file mode 100644
index 000000000000..fd986c36c737
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/dsi-controller.yaml
@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/dsi-controller.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Common Properties for DSI Display Panels
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+description: |
+  This document defines device tree properties common to DSI, Display
+  Serial Interface controllers and attached panels. It doesn't constitute
+  a device tree binding specification by itself but is meant to be referenced
+  by device tree bindings.
+
+  When referenced from panel device tree bindings the properties defined in
+  this document are defined as follows. The panel device tree bindings are
+  responsible for defining whether each property is required or optional.
+
+  Notice: this binding concerns DSI panels connected directly to a master
+  without any intermediate port graph to the panel. Each DSI master
+  can control one to four virtual channels to one panel. Each virtual
+  channel should have a node "panel" for their virtual channel with their
+  reg-property set to the virtual channel number, usually there is just
+  one virtual channel, number 0.
+
+properties:
+  $nodename:
+    pattern: "^dsi-controller(@.*)?$"
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+patternProperties:
+  "^panel@[0-3]$":
+    description: Panels connected to the DSI link
+    type: object
+
+    properties:
+      reg:
+        minimum: 0
+        maximum: 3
+        description:
+          The virtual channel number of a DSI peripheral. Must be in the range
+          from 0 to 3, as DSI uses a 2-bit addressing scheme. Some DSI
+          peripherals respond to more than a single virtual channel. In that
+          case the reg property can take multiple entries, one for each virtual
+          channel that the peripheral responds to.
+
+      clock-master:
+        type: boolean
+        description:
+           Should be enabled if the host is being used in conjunction with
+           another DSI host to drive the same peripheral. Hardware supporting
+           such a configuration generally requires the data on both the busses
+           to be driven by the same clock. Only the DSI host instance
+           controlling this clock should contain this property.
+
+      enforce-video-mode:
+        type: boolean
+        description:
+          The best option is usually to run a panel in command mode, as this
+          gives better control over the panel hardware. However for different
+          reasons like broken hardware, missing features or testing, it may be
+          useful to be able to force a command mode-capable panel into video
+          mode.
+
+    required:
+      - reg
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    dsi-controller@a0351000 {
+        reg = <0xa0351000 0x1000>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel@0 {
+            compatible = "sony,acx424akp";
+            reg = <0>;
+            vddi-supply = <&ab8500_ldo_aux1_reg>;
+            reset-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/ingenic,lcd.txt b/Documentation/devicetree/bindings/display/ingenic,lcd.txt
index 7b536c8c6dde..01e3261defb6 100644
--- a/Documentation/devicetree/bindings/display/ingenic,lcd.txt
+++ b/Documentation/devicetree/bindings/display/ingenic,lcd.txt
@@ -4,6 +4,7 @@ Required properties:
 - compatible: one of:
   * ingenic,jz4740-lcd
   * ingenic,jz4725b-lcd
+  * ingenic,jz4770-lcd
 - reg: LCD registers location and length
 - clocks: LCD pixclock and device clock specifiers.
 	   The device clock is only required on the JZ4740.
diff --git a/Documentation/devicetree/bindings/display/msm/dpu.txt b/Documentation/devicetree/bindings/display/msm/dpu.txt
index a61dd40f3792..551ae26f60da 100644
--- a/Documentation/devicetree/bindings/display/msm/dpu.txt
+++ b/Documentation/devicetree/bindings/display/msm/dpu.txt
@@ -8,7 +8,7 @@ The DPU display controller is found in SDM845 SoC.
 
 MDSS:
 Required properties:
-- compatible: "qcom,sdm845-mdss"
+- compatible:  "qcom,sdm845-mdss", "qcom,sc7180-mdss"
 - reg: physical base address and length of contoller's registers.
 - reg-names: register region names. The following region is required:
   * "mdss"
@@ -41,7 +41,7 @@ Optional properties:
 
 MDP:
 Required properties:
-- compatible: "qcom,sdm845-dpu"
+- compatible: "qcom,sdm845-dpu", "qcom,sc7180-dpu"
 - reg: physical base address and length of controller's registers.
 - reg-names : register region names. The following region is required:
   * "mdp"
diff --git a/Documentation/devicetree/bindings/display/msm/gpu.txt b/Documentation/devicetree/bindings/display/msm/gpu.txt
index 2b8fd26c43b0..7edc298a15f2 100644
--- a/Documentation/devicetree/bindings/display/msm/gpu.txt
+++ b/Documentation/devicetree/bindings/display/msm/gpu.txt
@@ -23,13 +23,18 @@ Required properties:
 - iommus: optional phandle to an adreno iommu instance
 - operating-points-v2: optional phandle to the OPP operating points
 - interconnects: optional phandle to an interconnect provider.  See
-  ../interconnect/interconnect.txt for details.
+  ../interconnect/interconnect.txt for details. Some A3xx and all A4xx platforms
+  will have two paths; all others will have one path.
+- interconnect-names: The names of the interconnect paths that correspond to the
+  interconnects property. Values must be gfx-mem and ocmem.
 - qcom,gmu: For GMU attached devices a phandle to the GMU device that will
   control the power for the GPU. Applicable targets:
     - qcom,adreno-630.2
 - zap-shader: For a5xx and a6xx devices this node contains a memory-region that
   points to reserved memory to store the zap shader that can be used to help
   bring the GPU out of secure mode.
+- firmware-name: optional property of the 'zap-shader' node, listing the
+  relative path of the device specific zap firmware.
 
 Example 3xx/4xx/a5xx:
 
@@ -76,11 +81,13 @@ Example a6xx (with GMU):
 		operating-points-v2 = <&gpu_opp_table>;
 
 		interconnects = <&rsc_hlos MASTER_GFX3D &rsc_hlos SLAVE_EBI1>;
+		interconnect-names = "gfx-mem";
 
 		qcom,gmu = <&gmu>;
 
 		zap-shader {
 			memory-region = <&zap_shader_region>;
+			firmware-name = "qcom/LENOVO/81JL/qcdxkmsuc850.mbn"
 		};
 	};
 };
diff --git a/Documentation/devicetree/bindings/display/panel/ampire,am-480272h3tmqw-t01h.yaml b/Documentation/devicetree/bindings/display/panel/ampire,am-480272h3tmqw-t01h.yaml
deleted file mode 100644
index c6e33e7f36d0..000000000000
--- a/Documentation/devicetree/bindings/display/panel/ampire,am-480272h3tmqw-t01h.yaml
+++ /dev/null
@@ -1,42 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-%YAML 1.2
----
-$id: http://devicetree.org/schemas/display/panel/ampire,am-480272h3tmqw-t01h.yaml#
-$schema: http://devicetree.org/meta-schemas/core.yaml#
-
-title: Ampire AM-480272H3TMQW-T01H 4.3" WQVGA TFT LCD panel
-
-maintainers:
-  - Yannick Fertre <yannick.fertre@st.com>
-  - Thierry Reding <treding@nvidia.com>
-
-allOf:
-  - $ref: panel-common.yaml#
-
-properties:
-  compatible:
-    const: ampire,am-480272h3tmqw-t01h
-
-  power-supply: true
-  enable-gpios: true
-  backlight: true
-  port: true
-
-required:
-  - compatible
-
-additionalProperties: false
-
-examples:
-  - |
-    panel_rgb: panel {
-      compatible = "ampire,am-480272h3tmqw-t01h";
-      enable-gpios = <&gpioa 8 1>;
-      port {
-        panel_in_rgb: endpoint {
-          remote-endpoint = <&controller_out_rgb>;
-        };
-      };
-    };
-
-...
diff --git a/Documentation/devicetree/bindings/display/panel/ampire,am800480r3tmqwa1h.txt b/Documentation/devicetree/bindings/display/panel/ampire,am800480r3tmqwa1h.txt
deleted file mode 100644
index 83e2cae1cc1b..000000000000
--- a/Documentation/devicetree/bindings/display/panel/ampire,am800480r3tmqwa1h.txt
+++ /dev/null
@@ -1,7 +0,0 @@
-Ampire AM-800480R3TMQW-A1H 7.0" WVGA TFT LCD panel
-
-Required properties:
-- compatible: should be "ampire,am800480r3tmqwa1h"
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/giantplus,gpm940b0.txt b/Documentation/devicetree/bindings/display/panel/giantplus,gpm940b0.txt
deleted file mode 100644
index 3dab52f92c26..000000000000
--- a/Documentation/devicetree/bindings/display/panel/giantplus,gpm940b0.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-GiantPlus 3.0" (320x240 pixels) 24-bit TFT LCD panel
-
-Required properties:
-- compatible: should be "giantplus,gpm940b0"
-- power-supply: as specified in the base binding
-
-Optional properties:
-- backlight: as specified in the base binding
-- enable-gpios: as specified in the base binding
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
new file mode 100644
index 000000000000..4ebcea7d0c63
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/leadtek,ltk500hd1829.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/leadtek,ltk500hd1829.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Leadtek LTK500HD1829 5.0in 720x1280 DSI panel
+
+maintainers:
+  - Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: leadtek,ltk500hd1829
+  reg: true
+  backlight: true
+  reset-gpios: true
+  iovcc-supply:
+     description: regulator that supplies the iovcc voltage
+  vcc-supply:
+     description: regulator that supplies the vcc voltage
+
+required:
+  - compatible
+  - reg
+  - backlight
+  - iovcc-supply
+  - vcc-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    dsi@ff450000 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel@0 {
+            compatible = "leadtek,ltk500hd1829";
+            reg = <0>;
+            backlight = <&backlight>;
+            iovcc-supply = <&vcc_1v8>;
+            vcc-supply = <&vcc_2v8>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/panel/logicpd,type28.yaml b/Documentation/devicetree/bindings/display/panel/logicpd,type28.yaml
new file mode 100644
index 000000000000..2834287b8d88
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/logicpd,type28.yaml
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/logicpd,type28.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Logic PD Type 28 4.3" WQVGA TFT LCD panel
+
+maintainers:
+  - Adam Ford <aford173@gmail.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: logicpd,type28
+
+  power-supply: true
+  enable-gpios: true
+  backlight: true
+  port: true
+
+required:
+  - compatible
+
+additionalProperties: false
+
+examples:
+  - |
+    lcd0: display {
+      compatible = "logicpd,type28";
+      enable-gpios = <&gpio5 27 0>;
+      backlight = <&backlight>;
+      port {
+        lcd_in: endpoint {
+          remote-endpoint = <&dpi_out>;
+        };
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
new file mode 100644
index 000000000000..8fe60ee2531c
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml
@@ -0,0 +1,69 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/panel-simple.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Simple panels with one power supply
+
+maintainers:
+  - Thierry Reding <thierry.reding@gmail.com>
+  - Sam Ravnborg <sam@ravnborg.org>
+
+description: |
+  This binding file is a collection of the simple (dumb) panels that
+  requires only a single power-supply.
+  There are optionally a backlight and an enable GPIO.
+  The panel may use an OF graph binding for the association to the display,
+  or it may be a direct child node of the display.
+
+  If the panel is more advanced a dedicated binding file is required.
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+
+  compatible:
+    enum:
+    # compatible must be listed in alphabetical order, ordered by compatible.
+    # The description in the comment is mandatory for each compatible.
+
+        # Ampire AM-480272H3TMQW-T01H 4.3" WQVGA TFT LCD panel
+      - ampire,am-480272h3tmqw-t01h
+        # Ampire AM-800480R3TMQW-A1H 7.0" WVGA TFT LCD panel
+      - ampire,am800480r3tmqwa1h
+        # AUO B116XAK01 eDP TFT LCD panel
+      - auo,b116xa01
+        # BOE NV140FHM-N49 14.0" FHD a-Si FT panel
+      - boe,nv140fhmn49
+        # GiantPlus GPM940B0 3.0" QVGA TFT LCD panel
+      - giantplus,gpm940b0
+        # Satoz SAT050AT40H12R2 5.0" WVGA TFT LCD panel
+      - satoz,sat050at40h12r2
+        # Sharp LS020B1DD01D 2.0" HQVGA TFT LCD panel
+      - sharp,ls020b1dd01d
+
+  backlight: true
+  enable-gpios: true
+  port: true
+  power-supply: true
+
+additionalProperties: false
+
+required:
+  - compatible
+  - power-supply
+
+examples:
+  - |
+    panel_rgb: panel-rgb {
+      compatible = "ampire,am-480272h3tmqw-t01h";
+      power-supply = <&vcc_lcd_reg>;
+
+      port {
+        panel_in_rgb: endpoint {
+          remote-endpoint = <&ltdc_out_rgb>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/display/panel/sharp,ls020b1dd01d.txt b/Documentation/devicetree/bindings/display/panel/sharp,ls020b1dd01d.txt
deleted file mode 100644
index e45edbc565a3..000000000000
--- a/Documentation/devicetree/bindings/display/panel/sharp,ls020b1dd01d.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-Sharp 2.0" (240x160 pixels) 16-bit TFT LCD panel
-
-Required properties:
-- compatible: should be "sharp,ls020b1dd01d"
-- power-supply: as specified in the base binding
-
-Optional properties:
-- backlight: as specified in the base binding
-- enable-gpios: as specified in the base binding
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/sony,acx424akp.yaml b/Documentation/devicetree/bindings/display/panel/sony,acx424akp.yaml
new file mode 100644
index 000000000000..185dcc8fd1f9
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sony,acx424akp.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/sony,acx424akp.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sony ACX424AKP 4" 480x864 AMOLED panel
+
+maintainers:
+  - Linus Walleij <linus.walleij@linaro.org>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: sony,acx424akp
+  reg: true
+  reset-gpios: true
+  vddi-supply:
+     description: regulator that supplies the vddi voltage
+  enforce-video-mode: true
+
+required:
+  - compatible
+  - reg
+  - reset-gpios
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+
+    dsi-controller@a0351000 {
+        compatible = "ste,mcde-dsi";
+        reg = <0xa0351000 0x1000>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        panel@0 {
+            compatible = "sony,acx424akp";
+            reg = <0>;
+            vddi-supply = <&foo>;
+            reset-gpios = <&foo_gpio 0 GPIO_ACTIVE_LOW>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
new file mode 100644
index 000000000000..186e5e1c8fa3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/xinpeng,xpp055c272.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/panel/xinpeng,xpp055c272.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Xinpeng XPP055C272 5.5in 720x1280 DSI panel
+
+maintainers:
+  - Heiko Stuebner <heiko.stuebner@theobroma-systems.com>
+
+allOf:
+  - $ref: panel-common.yaml#
+
+properties:
+  compatible:
+    const: xinpeng,xpp055c272
+  reg: true
+  backlight: true
+  reset-gpios: true
+  iovcc-supply:
+     description: regulator that supplies the iovcc voltage
+  vci-supply:
+     description: regulator that supplies the vci voltage
+
+required:
+  - compatible
+  - reg
+  - backlight
+  - iovcc-supply
+  - vci-supply
+
+additionalProperties: false
+
+examples:
+  - |
+    dsi@ff450000 {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        panel@0 {
+            compatible = "xinpeng,xpp055c272";
+            reg = <0>;
+            backlight = <&backlight>;
+            iovcc-supply = <&vcc_1v8>;
+            vci-supply = <&vcc3v3_lcd>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/display/renesas,cmm.yaml b/Documentation/devicetree/bindings/display/renesas,cmm.yaml
new file mode 100644
index 000000000000..a57037b9e9ba
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/renesas,cmm.yaml
@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/display/renesas,cmm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas R-Car Color Management Module (CMM)
+
+maintainers:
+  - Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+  - Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
+  - Jacopo Mondi <jacopo+renesas@jmondi.org>
+
+description: |+
+  Renesas R-Car color management module connected to R-Car DU video channels.
+  It provides image enhancement functions such as 1-D look-up tables (LUT),
+  3-D look-up tables (CLU), 1D-histogram generation (HGO), and color
+  space conversion (CSC).
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+        - enum:
+          - renesas,r8a7795-cmm
+          - renesas,r8a7796-cmm
+          - renesas,r8a77965-cmm
+          - renesas,r8a77990-cmm
+          - renesas,r8a77995-cmm
+        - const: renesas,rcar-gen3-cmm
+      - items:
+        - const: renesas,rcar-gen2-cmm
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - resets
+  - power-domains
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7796-cpg-mssr.h>
+    #include <dt-bindings/power/r8a7796-sysc.h>
+
+    cmm0: cmm@fea40000 {
+         compatible = "renesas,r8a7796-cmm",
+                      "renesas,rcar-gen3-cmm";
+         reg = <0 0xfea40000 0 0x1000>;
+         power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+         clocks = <&cpg CPG_MOD 711>;
+         resets = <&cpg 711>;
+    };
diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index 17cb2771364b..eb4ae41fe41f 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -41,10 +41,14 @@ Required Properties:
       supplied they must be named "dclkin.x" with "x" being the input clock
       numerical index.
 
-  - vsps: A list of phandle and channel index tuples to the VSPs that handle
-    the memory interfaces for the DU channels. The phandle identifies the VSP
-    instance that serves the DU channel, and the channel index identifies the
-    LIF instance in that VSP.
+  - renesas,cmms: A list of phandles to the CMM instances present in the SoC,
+    one for each available DU channel. The property shall not be specified for
+    SoCs that do not provide any CMM (such as V3M and V3H).
+
+  - renesas,vsps: A list of phandle and channel index tuples to the VSPs that
+    handle the memory interfaces for the DU channels. The phandle identifies the
+    VSP instance that serves the DU channel, and the channel index identifies
+    the LIF instance in that VSP.
 
 Required nodes:
 
@@ -92,7 +96,8 @@ Example: R8A7795 (R-Car H3) ES2.0 DU
 			 <&cpg CPG_MOD 722>,
 			 <&cpg CPG_MOD 721>;
 		clock-names = "du.0", "du.1", "du.2", "du.3";
-		vsps = <&vspd0 0>, <&vspd1 0>, <&vspd2 0>, <&vspd0 1>;
+		renesas,cmms = <&cmm0>, <&cmm1>, <&cmm2>, <&cmm3>;
+		renesas,vsps = <&vspd0 0>, <&vspd1 0>, <&vspd2 0>, <&vspd0 1>;
 
 		ports {
 			#address-cells = <1>;
diff --git a/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt b/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
index ce4c1fc9116c..151be3bba06f 100644
--- a/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt
@@ -4,13 +4,16 @@ Rockchip specific extensions to the Synopsys Designware MIPI DSI
 Required properties:
 - #address-cells: Should be <1>.
 - #size-cells: Should be <0>.
-- compatible: "rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi".
-	      "rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi".
+- compatible: one of
+	"rockchip,px30-mipi-dsi", "snps,dw-mipi-dsi"
+	"rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi"
+	"rockchip,rk3399-mipi-dsi", "snps,dw-mipi-dsi"
 - reg: Represent the physical address range of the controller.
 - interrupts: Represent the controller's interrupt to the CPU(s).
 - clocks, clock-names: Phandles to the controller's pll reference
-  clock(ref) and APB clock(pclk). For RK3399, a phy config clock
-  (phy_cfg) and a grf clock(grf) are required. As described in [1].
+  clock(ref) when using an internal dphy and APB clock(pclk).
+  For RK3399, a phy config clock (phy_cfg) and a grf clock(grf)
+  are required. As described in [1].
 - rockchip,grf: this soc should set GRF regs to mux vopl/vopb.
 - ports: contain a port node with endpoint definitions as defined in [2].
   For vopb,set the reg = <0> and set the reg = <1> for vopl.
@@ -18,6 +21,8 @@ Required properties:
 - video port 1 for either a panel or subsequent encoder
 
 Optional properties:
+- phys: from general PHY binding: the phandle for the PHY device.
+- phy-names: Should be "dphy" if phys references an external phy.
 - power-domains: a phandle to mipi dsi power domain node.
 - resets: list of phandle + reset specifier pairs, as described in [3].
 - reset-names: string reset name, must be "apb".
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt b/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt
index 7849ff039229..aaf8c44cf90f 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-lvds.txt
@@ -4,6 +4,7 @@ Rockchip RK3288 LVDS interface
 Required properties:
 - compatible: matching the soc type, one of
 	- "rockchip,rk3288-lvds";
+	- "rockchip,px30-lvds";
 
 - reg: physical base address of the controller and length
 	of memory mapped region.
@@ -18,6 +19,9 @@ Required properties:
 - rockchip,grf: phandle to the general register files syscon
 - rockchip,output: "rgb", "lvds" or "duallvds", This describes the output interface
 
+- phys: LVDS/DSI DPHY (px30 only)
+- phy-names: name of the PHY, must be "dphy" (px30 only)
+
 Optional properties:
 - pinctrl-names: must contain a "lcdc" entry.
 - pinctrl-0: pin control group to be used for this controller.
diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
deleted file mode 100644
index 31ab72cba3d4..000000000000
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ /dev/null
@@ -1,637 +0,0 @@
-Allwinner A10 Display Pipeline
-==============================
-
-The Allwinner A10 Display pipeline is composed of several components
-that are going to be documented below:
-
-For all connections between components up to the TCONs in the display
-pipeline, when there are multiple components of the same type at the
-same depth, the local endpoint ID must be the same as the remote
-component's index. For example, if the remote endpoint is Frontend 1,
-then the local endpoint ID must be 1.
-
-    Frontend 0  [0] ------- [0]  Backend 0  [0] ------- [0]  TCON 0
-		[1] --   -- [1]             [1] --   -- [1]
-		      \ /                         \ /
-		       X                           X
-		      / \                         / \
-		[0] --   -- [0]             [0] --   -- [0]
-    Frontend 1  [1] ------- [1]  Backend 1  [1] ------- [1]  TCON 1
-
-For a two pipeline system such as the one depicted above, the lines
-represent the connections between the components, while the numbers
-within the square brackets corresponds to the ID of the local endpoint.
-
-The same rule also applies to DE 2.0 mixer-TCON connections:
-
-    Mixer 0  [0] ----------- [0]  TCON 0
-	     [1] ----   ---- [1]
-		     \ /
-		      X
-		     / \
-	     [0] ----   ---- [0]
-    Mixer 1  [1] ----------- [1]  TCON 1
-
-HDMI Encoder
-------------
-
-The HDMI Encoder supports the HDMI video and audio outputs, and does
-CEC. It is one end of the pipeline.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-hdmi
-    * allwinner,sun5i-a10s-hdmi
-    * allwinner,sun6i-a31-hdmi
-  - reg: base address and size of memory-mapped region
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the HDMI encoder
-    * ahb: the HDMI interface clock
-    * mod: the HDMI module clock
-    * ddc: the HDMI ddc clock (A31 only)
-    * pll-0: the first video PLL
-    * pll-1: the second video PLL
-  - clock-names: the clock names mentioned above
-  - resets: phandle to the reset control for the HDMI encoder (A31 only)
-  - dmas: phandles to the DMA channels used by the HDMI encoder
-    * ddc-tx: The channel for DDC transmission
-    * ddc-rx: The channel for DDC reception
-    * audio-tx: The channel used for audio transmission
-  - dma-names: the channel names mentioned above
-
-  - ports: A ports node with endpoint definitions as defined in
-    Documentation/devicetree/bindings/media/video-interfaces.txt. The
-    first port should be the input endpoint. The second should be the
-    output, usually to an HDMI connector.
-
-DWC HDMI TX Encoder
--------------------
-
-The HDMI transmitter is a Synopsys DesignWare HDMI 1.4 TX controller IP
-with Allwinner's own PHY IP. It supports audio and video outputs and CEC.
-
-These DT bindings follow the Synopsys DWC HDMI TX bindings defined in
-Documentation/devicetree/bindings/display/bridge/dw_hdmi.txt with the
-following device-specific properties.
-
-Required properties:
-
-  - compatible: value must be one of:
-    * "allwinner,sun8i-a83t-dw-hdmi"
-    * "allwinner,sun50i-a64-dw-hdmi", "allwinner,sun8i-a83t-dw-hdmi"
-    * "allwinner,sun50i-h6-dw-hdmi"
-  - reg: base address and size of memory-mapped region
-  - reg-io-width: See dw_hdmi.txt. Shall be 1.
-  - interrupts: HDMI interrupt number
-  - clocks: phandles to the clocks feeding the HDMI encoder
-    * iahb: the HDMI bus clock
-    * isfr: the HDMI register clock
-    * tmds: TMDS clock
-    * cec: HDMI CEC clock (H6 only)
-    * hdcp: HDCP clock (H6 only)
-    * hdcp-bus: HDCP bus clock (H6 only)
-  - clock-names: the clock names mentioned above
-  - resets:
-    * ctrl: HDMI controller reset
-    * hdcp: HDCP reset (H6 only)
-  - reset-names: reset names mentioned above
-  - phys: phandle to the DWC HDMI PHY
-  - phy-names: must be "phy"
-
-  - ports: A ports node with endpoint definitions as defined in
-    Documentation/devicetree/bindings/media/video-interfaces.txt. The
-    first port should be the input endpoint. The second should be the
-    output, usually to an HDMI connector.
-
-Optional properties:
-  - hvcc-supply: the VCC power supply of the controller
-
-DWC HDMI PHY
-------------
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun8i-a83t-hdmi-phy
-    * allwinner,sun8i-h3-hdmi-phy
-    * allwinner,sun8i-r40-hdmi-phy
-    * allwinner,sun50i-a64-hdmi-phy
-    * allwinner,sun50i-h6-hdmi-phy
-  - reg: base address and size of memory-mapped region
-  - clocks: phandles to the clocks feeding the HDMI PHY
-    * bus: the HDMI PHY interface clock
-    * mod: the HDMI PHY module clock
-  - clock-names: the clock names mentioned above
-  - resets: phandle to the reset controller driving the PHY
-  - reset-names: must be "phy"
-
-H3, A64 and R40 HDMI PHY require additional clocks:
-  - pll-0: parent of phy clock
-  - pll-1: second possible phy clock parent (A64/R40 only)
-
-TV Encoder
-----------
-
-The TV Encoder supports the composite and VGA output. It is one end of
-the pipeline.
-
-Required properties:
- - compatible: value should be "allwinner,sun4i-a10-tv-encoder".
- - reg: base address and size of memory-mapped region
- - clocks: the clocks driving the TV encoder
- - resets: phandle to the reset controller driving the encoder
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoint.
-
-TCON
-----
-
-The TCON acts as a timing controller for RGB, LVDS and TV interfaces.
-
-Required properties:
- - compatible: value must be either:
-   * allwinner,sun4i-a10-tcon
-   * allwinner,sun5i-a13-tcon
-   * allwinner,sun6i-a31-tcon
-   * allwinner,sun6i-a31s-tcon
-   * allwinner,sun7i-a20-tcon
-   * allwinner,sun8i-a23-tcon
-   * allwinner,sun8i-a33-tcon
-   * allwinner,sun8i-a83t-tcon-lcd
-   * allwinner,sun8i-a83t-tcon-tv
-   * allwinner,sun8i-r40-tcon-tv
-   * allwinner,sun8i-v3s-tcon
-   * allwinner,sun9i-a80-tcon-lcd
-   * allwinner,sun9i-a80-tcon-tv
-   * "allwinner,sun50i-a64-tcon-lcd", "allwinner,sun8i-a83t-tcon-lcd"
-   * "allwinner,sun50i-a64-tcon-tv", "allwinner,sun8i-a83t-tcon-tv"
-   * allwinner,sun50i-h6-tcon-tv, allwinner,sun8i-r40-tcon-tv
- - reg: base address and size of memory-mapped region
- - interrupts: interrupt associated to this IP
- - clocks: phandles to the clocks feeding the TCON.
-   - 'ahb': the interface clocks
-   - 'tcon-ch0': The clock driving the TCON channel 0, if supported
- - resets: phandles to the reset controllers driving the encoder
-   - "lcd": the reset line for the TCON
-   - "edp": the reset line for the eDP block (A80 only)
-
- - clock-names: the clock names mentioned above
- - reset-names: the reset names mentioned above
- - clock-output-names: Name of the pixel clock created, if TCON supports
-   channel 0.
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoint, the second one the output
-
-  The output may have multiple endpoints. TCON can have 1 or 2 channels,
-  usually with the first channel being used for the panels interfaces
-  (RGB, LVDS, etc.), and the second being used for the outputs that
-  require another controller (TV Encoder, HDMI, etc.). The endpoints
-  will take an extra property, allwinner,tcon-channel, to specify the
-  channel the endpoint is associated to. If that property is not
-  present, the endpoint number will be used as the channel number.
-
-For TCONs with channel 0, there is one more clock required:
-   - 'tcon-ch0': The clock driving the TCON channel 0
-For TCONs with channel 1, there is one more clock required:
-   - 'tcon-ch1': The clock driving the TCON channel 1
-
-When TCON support LVDS (all TCONs except TV TCONs on A83T, R40 and those found
-in A13, H3, H5 and V3s SoCs), you need one more reset line:
-   - 'lvds': The reset line driving the LVDS logic
-
-And on the A23, A31, A31s and A33, you need one more clock line:
-   - 'lvds-alt': An alternative clock source, separate from the TCON channel 0
-                 clock, that can be used to drive the LVDS clock
-
-TCON TOP
---------
-
-TCON TOPs main purpose is to configure whole display pipeline. It determines
-relationships between mixers and TCONs, selects source TCON for HDMI, muxes
-LCD and TV encoder GPIO output, selects TV encoder clock source and contains
-additional TV TCON and DSI gates.
-
-It allows display pipeline to be configured in very different ways:
-
-                                / LCD0/LVDS0
-                 / [0] TCON-LCD0
-                 |              \ MIPI DSI
- mixer0          |
-        \        / [1] TCON-LCD1 - LCD1/LVDS1
-         TCON-TOP
-        /        \ [2] TCON-TV0 [0] - TVE0/RGB
- mixer1          |                  \
-                 |                   TCON-TOP - HDMI
-                 |                  /
-                 \ [3] TCON-TV1 [1] - TVE1/RGB
-
-Note that both TCON TOP references same physical unit. Both mixers can be
-connected to any TCON. Not all TCON TOP variants support all features.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun8i-r40-tcon-top
-    * allwinner,sun50i-h6-tcon-top
-  - reg: base address and size of the memory-mapped region.
-  - clocks: phandle to the clocks feeding the TCON TOP
-    * bus: TCON TOP interface clock
-    * tcon-tv0: TCON TV0 clock
-    * tve0: TVE0 clock (R40 only)
-    * tcon-tv1: TCON TV1 clock (R40 only)
-    * tve1: TVE0 clock (R40 only)
-    * dsi: MIPI DSI clock (R40 only)
-  - clock-names: clock name mentioned above
-  - resets: phandle to the reset line driving the TCON TOP
-  - #clock-cells : must contain 1
-  - clock-output-names: Names of clocks created for TCON TV0 channel clock,
-    TCON TV1 channel clock (R40 only) and DSI channel clock (R40 only), in
-    that order.
-
-- ports: A ports node with endpoint definitions as defined in
-    Documentation/devicetree/bindings/media/video-interfaces.txt. 6 ports should
-    be defined:
-    * port 0 is input for mixer0 mux
-    * port 1 is output for mixer0 mux
-    * port 2 is input for mixer1 mux
-    * port 3 is output for mixer1 mux
-    * port 4 is input for HDMI mux
-    * port 5 is output for HDMI mux
-    All output endpoints for mixer muxes and input endpoints for HDMI mux should
-    have reg property with the id of the target TCON, as shown in above graph
-    (0-3 for mixer muxes and 0-1 for HDMI mux). All ports should have only one
-    endpoint connected to remote endpoint.
-
-DRC
----
-
-The DRC (Dynamic Range Controller), found in the latest Allwinner SoCs
-(A31, A23, A33, A80), allows to dynamically adjust pixel
-brightness/contrast based on histogram measurements for LCD content
-adaptive backlight control.
-
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun6i-a31-drc
-    * allwinner,sun6i-a31s-drc
-    * allwinner,sun8i-a23-drc
-    * allwinner,sun8i-a33-drc
-    * allwinner,sun9i-a80-drc
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the DRC
-    * ahb: the DRC interface clock
-    * mod: the DRC module clock
-    * ram: the DRC DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset line driving the DRC
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the outputs
-
-Display Engine Backend
-----------------------
-
-The display engine backend exposes layers and sprites to the
-system.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-display-backend
-    * allwinner,sun5i-a13-display-backend
-    * allwinner,sun6i-a31-display-backend
-    * allwinner,sun7i-a20-display-backend
-    * allwinner,sun8i-a23-display-backend
-    * allwinner,sun8i-a33-display-backend
-    * allwinner,sun9i-a80-display-backend
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the frontend and backend
-    * ahb: the backend interface clock
-    * mod: the backend module clock
-    * ram: the backend DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset controllers driving the backend
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the output
-
-On the A33, some additional properties are required:
-  - reg needs to have an additional region corresponding to the SAT
-  - reg-names need to be set, with "be" and "sat"
-  - clocks and clock-names need to have a phandle to the SAT bus
-    clocks, whose name will be "sat"
-  - resets and reset-names need to have a phandle to the SAT bus
-    resets, whose name will be "sat"
-
-DEU
----
-
-The DEU (Detail Enhancement Unit), found in the Allwinner A80 SoC,
-can sharpen the display content in both luma and chroma channels.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun9i-a80-deu
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the DEU
-    * ahb: the DEU interface clock
-    * mod: the DEU module clock
-    * ram: the DEU DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset line driving the DEU
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the outputs
-
-Display Engine Frontend
------------------------
-
-The display engine frontend does formats conversion, scaling,
-deinterlacing and color space conversion.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-display-frontend
-    * allwinner,sun5i-a13-display-frontend
-    * allwinner,sun6i-a31-display-frontend
-    * allwinner,sun7i-a20-display-frontend
-    * allwinner,sun8i-a23-display-frontend
-    * allwinner,sun8i-a33-display-frontend
-    * allwinner,sun9i-a80-display-frontend
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the frontend and backend
-    * ahb: the backend interface clock
-    * mod: the backend module clock
-    * ram: the backend DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset controllers driving the backend
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the outputs
-
-Display Engine 2.0 Mixer
-------------------------
-
-The DE2 mixer have many functionalities, currently only layer blending is
-supported.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun8i-a83t-de2-mixer-0
-    * allwinner,sun8i-a83t-de2-mixer-1
-    * allwinner,sun8i-h3-de2-mixer-0
-    * allwinner,sun8i-r40-de2-mixer-0
-    * allwinner,sun8i-r40-de2-mixer-1
-    * allwinner,sun8i-v3s-de2-mixer
-    * allwinner,sun50i-a64-de2-mixer-0
-    * allwinner,sun50i-a64-de2-mixer-1
-    * allwinner,sun50i-h6-de3-mixer-0
-  - reg: base address and size of the memory-mapped region.
-  - clocks: phandles to the clocks feeding the mixer
-    * bus: the mixer interface clock
-    * mod: the mixer module clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset controllers driving the mixer
-
-- ports: A ports node with endpoint definitions as defined in
-  Documentation/devicetree/bindings/media/video-interfaces.txt. The
-  first port should be the input endpoints, the second one the output
-
-
-Display Engine Pipeline
------------------------
-
-The display engine pipeline (and its entry point, since it can be
-either directly the backend or the frontend) is represented as an
-extra node.
-
-Required properties:
-  - compatible: value must be one of:
-    * allwinner,sun4i-a10-display-engine
-    * allwinner,sun5i-a10s-display-engine
-    * allwinner,sun5i-a13-display-engine
-    * allwinner,sun6i-a31-display-engine
-    * allwinner,sun6i-a31s-display-engine
-    * allwinner,sun7i-a20-display-engine
-    * allwinner,sun8i-a23-display-engine
-    * allwinner,sun8i-a33-display-engine
-    * allwinner,sun8i-a83t-display-engine
-    * allwinner,sun8i-h3-display-engine
-    * allwinner,sun8i-r40-display-engine
-    * allwinner,sun8i-v3s-display-engine
-    * allwinner,sun9i-a80-display-engine
-    * allwinner,sun50i-a64-display-engine
-    * allwinner,sun50i-h6-display-engine
-
-  - allwinner,pipelines: list of phandle to the display engine
-    frontends (DE 1.0) or mixers (DE 2.0/3.0) available.
-
-Example:
-
-panel: panel {
-	compatible = "olimex,lcd-olinuxino-43-ts";
-	#address-cells = <1>;
-	#size-cells = <0>;
-
-	port {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		panel_input: endpoint {
-			remote-endpoint = <&tcon0_out_panel>;
-		};
-	};
-};
-
-connector {
-	compatible = "hdmi-connector";
-	type = "a";
-
-	port {
-		hdmi_con_in: endpoint {
-			remote-endpoint = <&hdmi_out_con>;
-		};
-	};
-};
-
-hdmi: hdmi@1c16000 {
-	compatible = "allwinner,sun5i-a10s-hdmi";
-	reg = <0x01c16000 0x1000>;
-	interrupts = <58>;
-	clocks = <&ccu CLK_AHB_HDMI>, <&ccu CLK_HDMI>,
-		 <&ccu CLK_PLL_VIDEO0_2X>,
-		 <&ccu CLK_PLL_VIDEO1_2X>;
-	clock-names = "ahb", "mod", "pll-0", "pll-1";
-	dmas = <&dma SUN4I_DMA_NORMAL 16>,
-	       <&dma SUN4I_DMA_NORMAL 16>,
-	       <&dma SUN4I_DMA_DEDICATED 24>;
-	dma-names = "ddc-tx", "ddc-rx", "audio-tx";
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		port@0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0>;
-
-			hdmi_in_tcon0: endpoint {
-				remote-endpoint = <&tcon0_out_hdmi>;
-			};
-		};
-
-		port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			hdmi_out_con: endpoint {
-				remote-endpoint = <&hdmi_con_in>;
-			};
-		};
-	};
-};
-
-tve0: tv-encoder@1c0a000 {
-	compatible = "allwinner,sun4i-a10-tv-encoder";
-	reg = <0x01c0a000 0x1000>;
-	clocks = <&ahb_gates 34>;
-	resets = <&tcon_ch0_clk 0>;
-
-	port {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		tve0_in_tcon0: endpoint@0 {
-			reg = <0>;
-			remote-endpoint = <&tcon0_out_tve0>;
-		};
-	};
-};
-
-tcon0: lcd-controller@1c0c000 {
-	compatible = "allwinner,sun5i-a13-tcon";
-	reg = <0x01c0c000 0x1000>;
-	interrupts = <44>;
-	resets = <&tcon_ch0_clk 1>;
-	reset-names = "lcd";
-	clocks = <&ahb_gates 36>,
-		 <&tcon_ch0_clk>,
-		 <&tcon_ch1_clk>;
-	clock-names = "ahb",
-		      "tcon-ch0",
-		      "tcon-ch1";
-	clock-output-names = "tcon-pixel-clock";
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		tcon0_in: port@0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0>;
-
-			tcon0_in_be0: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&be0_out_tcon0>;
-			};
-		};
-
-		tcon0_out: port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			tcon0_out_panel: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&panel_input>;
-			};
-
-			tcon0_out_tve0: endpoint@1 {
-				reg = <1>;
-				remote-endpoint = <&tve0_in_tcon0>;
-			};
-		};
-	};
-};
-
-fe0: display-frontend@1e00000 {
-	compatible = "allwinner,sun5i-a13-display-frontend";
-	reg = <0x01e00000 0x20000>;
-	interrupts = <47>;
-	clocks = <&ahb_gates 46>, <&de_fe_clk>,
-		 <&dram_gates 25>;
-	clock-names = "ahb", "mod",
-		      "ram";
-	resets = <&de_fe_clk>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		fe0_out: port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			fe0_out_be0: endpoint {
-				remote-endpoint = <&be0_in_fe0>;
-			};
-		};
-	};
-};
-
-be0: display-backend@1e60000 {
-	compatible = "allwinner,sun5i-a13-display-backend";
-	reg = <0x01e60000 0x10000>;
-	interrupts = <47>;
-	clocks = <&ahb_gates 44>, <&de_be_clk>,
-		 <&dram_gates 26>;
-	clock-names = "ahb", "mod",
-		      "ram";
-	resets = <&de_be_clk>;
-
-	ports {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		be0_in: port@0 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <0>;
-
-			be0_in_fe0: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&fe0_out_be0>;
-			};
-		};
-
-		be0_out: port@1 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg = <1>;
-
-			be0_out_tcon0: endpoint@0 {
-				reg = <0>;
-				remote-endpoint = <&tcon0_in_be0>;
-			};
-		};
-	};
-};
-
-display-engine {
-	compatible = "allwinner,sun5i-a13-display-engine";
-	allwinner,pipelines = <&fe0>;
-};
diff --git a/Documentation/devicetree/bindings/display/tilcdc/tfp410.txt b/Documentation/devicetree/bindings/display/tilcdc/tfp410.txt
deleted file mode 100644
index a58ae7756fc6..000000000000
--- a/Documentation/devicetree/bindings/display/tilcdc/tfp410.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-Device-Tree bindings for tilcdc DRM TFP410 output driver
-
-Required properties:
- - compatible: value should be "ti,tilcdc,tfp410".
- - i2c: the phandle for the i2c device to use for DDC
-
-Recommended properties:
- - pinctrl-names, pinctrl-0: the pincontrol settings to configure
-   muxing properly for pins that connect to TFP410 device
- - powerdn-gpio: the powerdown GPIO, pulled low to power down the
-   TFP410 device (for DPMS_OFF)
-
-Example:
-
-	dvicape {
-		compatible = "ti,tilcdc,tfp410";
-		i2c = <&i2c2>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&bone_dvi_cape_dvi_00A1_pins>;
-		powerdn-gpio = <&gpio2 31 0>;
-	};
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml b/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
new file mode 100644
index 000000000000..0c0ac11ad55f
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/st,stm32-dma.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/st,stm32-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 DMA Controller bindings
+
+description: |
+  The STM32 DMA is a general-purpose direct memory access controller capable of
+  supporting 8 independent DMA channels. Each channel can have up to 8 requests.
+  DMA clients connected to the STM32 DMA controller must use the format
+  described in the dma.txt file, using a four-cell specifier for each
+  channel: a phandle to the DMA controller plus the following four integer cells:
+    1. The channel id
+    2. The request line number
+    3. A 32bit mask specifying the DMA channel configuration which are device
+      dependent:
+        -bit 9: Peripheral Increment Address
+          0x0: no address increment between transfers
+          0x1: increment address between transfers
+        -bit 10: Memory Increment Address
+          0x0: no address increment between transfers
+          0x1: increment address between transfers
+        -bit 15: Peripheral Increment Offset Size
+          0x0: offset size is linked to the peripheral bus width
+          0x1: offset size is fixed to 4 (32-bit alignment)
+        -bit 16-17: Priority level
+          0x0: low
+          0x1: medium
+          0x2: high
+          0x3: very high
+    4. A 32bit bitfield value specifying DMA features which are device dependent:
+       -bit 0-1: DMA FIFO threshold selection
+         0x0: 1/4 full FIFO
+         0x1: 1/2 full FIFO
+         0x2: 3/4 full FIFO
+         0x3: full FIFO
+
+maintainers:
+  - Amelie Delaunay <amelie.delaunay@st.com>
+
+allOf:
+  - $ref: "dma-controller.yaml#"
+
+properties:
+  "#dma-cells":
+    const: 4
+
+  compatible:
+    const: st,stm32-dma
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 8
+    description: Should contain all of the per-channel DMA
+      interrupts in ascending order with respect to the
+      DMA channel index.
+
+  resets:
+    maxItems: 1
+
+  st,mem2mem:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: if defined, it indicates that the controller
+      supports memory-to-memory transfer
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    #include <dt-bindings/reset/stm32mp1-resets.h>
+    dma-controller@40026400 {
+      compatible = "st,stm32-dma";
+      reg = <0x40026400 0x400>;
+      interrupts = <56>,
+                   <57>,
+                   <58>,
+                   <59>,
+                   <60>,
+                   <68>,
+                   <69>,
+                   <70>;
+      clocks = <&clk_hclk>;
+      #dma-cells = <4>;
+      st,mem2mem;
+      resets = <&rcc 150>;
+      dma-requests = <8>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml b/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
new file mode 100644
index 000000000000..915bc4af9568
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/st,stm32-dmamux.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/st,stm32-dmamux.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 DMA MUX (DMA request router) bindings
+
+maintainers:
+  - Amelie Delaunay <amelie.delaunay@st.com>
+
+allOf:
+  - $ref: "dma-router.yaml#"
+
+properties:
+  "#dma-cells":
+    const: 3
+
+  compatible:
+    const: st,stm32h7-dmamux
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - dma-masters
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    #include <dt-bindings/reset/stm32mp1-resets.h>
+    dma-router@40020800 {
+      compatible = "st,stm32h7-dmamux";
+      reg = <0x40020800 0x3c>;
+      #dma-cells = <3>;
+      dma-requests = <128>;
+      dma-channels = <16>;
+      dma-masters = <&dma1 &dma2>;
+      clocks = <&timer_clk>;
+    };
+
+...
+
diff --git a/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml b/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
new file mode 100644
index 000000000000..c66543d0c267
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/st,stm32-mdma.yaml
@@ -0,0 +1,105 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/st,stm32-mdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 MDMA Controller bindings
+
+description: |
+  The STM32 MDMA is a general-purpose direct memory access controller capable of
+  supporting 64 independent DMA channels with 256 HW requests.
+  DMA clients connected to the STM32 MDMA controller must use the format
+  described in the dma.txt file, using a five-cell specifier for each channel:
+  a phandle to the MDMA controller plus the following five integer cells:
+    1. The request line number
+    2. The priority level
+      0x0: Low
+      0x1: Medium
+      0x2: High
+      0x3: Very high
+    3. A 32bit mask specifying the DMA channel configuration
+      -bit 0-1: Source increment mode
+        0x0: Source address pointer is fixed
+        0x2: Source address pointer is incremented after each data transfer
+        0x3: Source address pointer is decremented after each data transfer
+      -bit 2-3: Destination increment mode
+        0x0: Destination address pointer is fixed
+        0x2: Destination address pointer is incremented after each data transfer
+        0x3: Destination address pointer is decremented after each data transfer
+      -bit 8-9: Source increment offset size
+        0x0: byte (8bit)
+        0x1: half-word (16bit)
+        0x2: word (32bit)
+        0x3: double-word (64bit)
+      -bit 10-11: Destination increment offset size
+        0x0: byte (8bit)
+        0x1: half-word (16bit)
+        0x2: word (32bit)
+        0x3: double-word (64bit)
+      -bit 25-18: The number of bytes to be transferred in a single transfer
+                  (min = 1 byte, max = 128 bytes)
+      -bit 29:28: Trigger Mode
+        0x00: Each MDMA request triggers a buffer transfer (max 128 bytes)
+        0x1: Each MDMA request triggers a block transfer (max 64K bytes)
+        0x2: Each MDMA request triggers a repeated block transfer
+        0x3: Each MDMA request triggers a linked list transfer
+    4. A 32bit value specifying the register to be used to acknowledge the request
+       if no HW ack signal is used by the MDMA client
+    5. A 32bit mask specifying the value to be written to acknowledge the request
+       if no HW ack signal is used by the MDMA client
+
+maintainers:
+  - Amelie Delaunay <amelie.delaunay@st.com>
+
+allOf:
+  - $ref: "dma-controller.yaml#"
+
+properties:
+  "#dma-cells":
+    const: 5
+
+  compatible:
+    const: st,stm32h7-mdma
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  st,ahb-addr-masks:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description: Array of u32 mask to list memory devices addressed via AHB bus.
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    #include <dt-bindings/reset/stm32mp1-resets.h>
+    dma-controller@52000000 {
+      compatible = "st,stm32h7-mdma";
+      reg = <0x52000000 0x1000>;
+      interrupts = <122>;
+      clocks = <&timer_clk>;
+      resets = <&rcc 992>;
+      #dma-cells = <5>;
+      dma-channels = <16>;
+      dma-requests = <32>;
+      st,ahb-addr-masks = <0x20000000>, <0x00000000>;
+    };
+
+...
+
diff --git a/Documentation/devicetree/bindings/dma/stm32-dma.txt b/Documentation/devicetree/bindings/dma/stm32-dma.txt
deleted file mode 100644
index c5f519097204..000000000000
--- a/Documentation/devicetree/bindings/dma/stm32-dma.txt
+++ /dev/null
@@ -1,83 +0,0 @@
-* STMicroelectronics STM32 DMA controller
-
-The STM32 DMA is a general-purpose direct memory access controller capable of
-supporting 8 independent DMA channels. Each channel can have up to 8 requests.
-
-Required properties:
-- compatible: Should be "st,stm32-dma"
-- reg: Should contain DMA registers location and length. This should include
-  all of the per-channel registers.
-- interrupts: Should contain all of the per-channel DMA interrupts in
-  ascending order with respect to the DMA channel index.
-- clocks: Should contain the input clock of the DMA instance.
-- #dma-cells : Must be <4>. See DMA client paragraph for more details.
-
-Optional properties:
-- dma-requests : Number of DMA requests supported.
-- resets: Reference to a reset controller asserting the DMA controller
-- st,mem2mem: boolean; if defined, it indicates that the controller supports
-  memory-to-memory transfer
-
-Example:
-
-	dma2: dma-controller@40026400 {
-		compatible = "st,stm32-dma";
-		reg = <0x40026400 0x400>;
-		interrupts = <56>,
-			     <57>,
-			     <58>,
-			     <59>,
-			     <60>,
-			     <68>,
-			     <69>,
-			     <70>;
-		clocks = <&clk_hclk>;
-		#dma-cells = <4>;
-		st,mem2mem;
-		resets = <&rcc 150>;
-		dma-requests = <8>;
-	};
-
-* DMA client
-
-DMA clients connected to the STM32 DMA controller must use the format
-described in the dma.txt file, using a four-cell specifier for each
-channel: a phandle to the DMA controller plus the following four integer cells:
-
-1. The channel id
-2. The request line number
-3. A 32bit mask specifying the DMA channel configuration which are device
-   dependent:
-  -bit 9: Peripheral Increment Address
-	0x0: no address increment between transfers
-	0x1: increment address between transfers
- -bit 10: Memory Increment Address
-	0x0: no address increment between transfers
-	0x1: increment address between transfers
- -bit 15: Peripheral Increment Offset Size
-	0x0: offset size is linked to the peripheral bus width
-	0x1: offset size is fixed to 4 (32-bit alignment)
- -bit 16-17: Priority level
-	0x0: low
-	0x1: medium
-	0x2: high
-	0x3: very high
-4. A 32bit bitfield value specifying DMA features which are device dependent:
- -bit 0-1: DMA FIFO threshold selection
-	0x0: 1/4 full FIFO
-	0x1: 1/2 full FIFO
-	0x2: 3/4 full FIFO
-	0x3: full FIFO
-
-
-Example:
-
-	usart1: serial@40011000 {
-		compatible = "st,stm32-uart";
-		reg = <0x40011000 0x400>;
-		interrupts = <37>;
-		clocks = <&clk_pclk2>;
-		dmas = <&dma2 2 4 0x10400 0x3>,
-		       <&dma2 7 5 0x10200 0x3>;
-		dma-names = "rx", "tx";
-	};
diff --git a/Documentation/devicetree/bindings/dma/stm32-dmamux.txt b/Documentation/devicetree/bindings/dma/stm32-dmamux.txt
deleted file mode 100644
index 1b893b235507..000000000000
--- a/Documentation/devicetree/bindings/dma/stm32-dmamux.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-STM32 DMA MUX (DMA request router)
-
-Required properties:
-- compatible:	"st,stm32h7-dmamux"
-- reg:		Memory map for accessing module
-- #dma-cells:	Should be set to <3>.
-		First parameter is request line number.
-		Second is DMA channel configuration
-		Third is Fifo threshold
-		For more details about the three cells, please see
-		stm32-dma.txt documentation binding file
-- dma-masters:	Phandle pointing to the DMA controllers.
-		Several controllers are allowed. Only "st,stm32-dma" DMA
-		compatible are supported.
-
-Optional properties:
-- dma-channels : Number of DMA requests supported.
-- dma-requests : Number of DMAMUX requests supported.
-- resets: Reference to a reset controller asserting the DMA controller
-- clocks: Input clock of the DMAMUX instance.
-
-Example:
-
-/* DMA controller 1 */
-dma1: dma-controller@40020000 {
-	compatible = "st,stm32-dma";
-	reg = <0x40020000 0x400>;
-	interrupts = <11>,
-		     <12>,
-		     <13>,
-		     <14>,
-		     <15>,
-		     <16>,
-		     <17>,
-		     <47>;
-	clocks = <&timer_clk>;
-	#dma-cells = <4>;
-	st,mem2mem;
-	resets = <&rcc 150>;
-	dma-channels = <8>;
-	dma-requests = <8>;
-};
-
-/* DMA controller 1 */
-dma2: dma@40020400 {
-	compatible = "st,stm32-dma";
-	reg = <0x40020400 0x400>;
-	interrupts = <56>,
-		     <57>,
-		     <58>,
-		     <59>,
-		     <60>,
-		     <68>,
-		     <69>,
-		     <70>;
-	clocks = <&timer_clk>;
-	#dma-cells = <4>;
-	st,mem2mem;
-	resets = <&rcc 150>;
-	dma-channels = <8>;
-	dma-requests = <8>;
-};
-
-/* DMA mux */
-dmamux1: dma-router@40020800 {
-	compatible = "st,stm32h7-dmamux";
-	reg = <0x40020800 0x3c>;
-	#dma-cells = <3>;
-	dma-requests = <128>;
-	dma-channels = <16>;
-	dma-masters = <&dma1 &dma2>;
-	clocks = <&timer_clk>;
-};
-
-/* DMA client */
-usart1: serial@40011000 {
-	compatible = "st,stm32-usart", "st,stm32-uart";
-	reg = <0x40011000 0x400>;
-	interrupts = <37>;
-	clocks = <&timer_clk>;
-	dmas = <&dmamux1 41 0x414 0>,
-	       <&dmamux1 42 0x414 0>;
-	dma-names = "rx", "tx";
-};
diff --git a/Documentation/devicetree/bindings/dma/stm32-mdma.txt b/Documentation/devicetree/bindings/dma/stm32-mdma.txt
deleted file mode 100644
index d18772d6bc65..000000000000
--- a/Documentation/devicetree/bindings/dma/stm32-mdma.txt
+++ /dev/null
@@ -1,94 +0,0 @@
-* STMicroelectronics STM32 MDMA controller
-
-The STM32 MDMA is a general-purpose direct memory access controller capable of
-supporting 64 independent DMA channels with 256 HW requests.
-
-Required properties:
-- compatible: Should be "st,stm32h7-mdma"
-- reg: Should contain MDMA registers location and length. This should include
-  all of the per-channel registers.
-- interrupts: Should contain the MDMA interrupt.
-- clocks: Should contain the input clock of the DMA instance.
-- resets: Reference to a reset controller asserting the DMA controller.
-- #dma-cells : Must be <5>. See DMA client paragraph for more details.
-
-Optional properties:
-- dma-channels: Number of DMA channels supported by the controller.
-- dma-requests: Number of DMA request signals supported by the controller.
-- st,ahb-addr-masks: Array of u32 mask to list memory devices addressed via
-  AHB bus.
-
-Example:
-
-	mdma1: dma@52000000 {
-		compatible = "st,stm32h7-mdma";
-		reg = <0x52000000 0x1000>;
-		interrupts = <122>;
-		clocks = <&timer_clk>;
-		resets = <&rcc 992>;
-		#dma-cells = <5>;
-		dma-channels = <16>;
-		dma-requests = <32>;
-		st,ahb-addr-masks = <0x20000000>, <0x00000000>;
-	};
-
-* DMA client
-
-DMA clients connected to the STM32 MDMA controller must use the format
-described in the dma.txt file, using a five-cell specifier for each channel:
-a phandle to the MDMA controller plus the following five integer cells:
-
-1. The request line number
-2. The priority level
-	0x00: Low
-	0x01: Medium
-	0x10: High
-	0x11: Very high
-3. A 32bit mask specifying the DMA channel configuration
- -bit 0-1: Source increment mode
-	0x00: Source address pointer is fixed
-	0x10: Source address pointer is incremented after each data transfer
-	0x11: Source address pointer is decremented after each data transfer
- -bit 2-3: Destination increment mode
-	0x00: Destination address pointer is fixed
-	0x10: Destination address pointer is incremented after each data
-	transfer
-	0x11: Destination address pointer is decremented after each data
-	transfer
- -bit 8-9: Source increment offset size
-	0x00: byte (8bit)
-	0x01: half-word (16bit)
-	0x10: word (32bit)
-	0x11: double-word (64bit)
- -bit 10-11: Destination increment offset size
-	0x00: byte (8bit)
-	0x01: half-word (16bit)
-	0x10: word (32bit)
-	0x11: double-word (64bit)
--bit 25-18: The number of bytes to be transferred in a single transfer
-	(min = 1 byte, max = 128 bytes)
--bit 29:28: Trigger Mode
-	0x00: Each MDMA request triggers a buffer transfer (max 128 bytes)
-	0x01: Each MDMA request triggers a block transfer (max 64K bytes)
-	0x10: Each MDMA request triggers a repeated block transfer
-	0x11: Each MDMA request triggers a linked list transfer
-4. A 32bit value specifying the register to be used to acknowledge the request
-   if no HW ack signal is used by the MDMA client
-5. A 32bit mask specifying the value to be written to acknowledge the request
-   if no HW ack signal is used by the MDMA client
-
-Example:
-
-	i2c4: i2c@5c002000 {
-		compatible = "st,stm32f7-i2c";
-		reg = <0x5c002000 0x400>;
-		interrupts = <95>,
-			     <96>;
-		clocks = <&timer_clk>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-		dmas = <&mdma1 36 0x0 0x40008 0x0 0x0>,
-		       <&mdma1 37 0x0 0x40002 0x0 0x0>;
-		dma-names = "rx", "tx";
-		status = "disabled";
-	};
diff --git a/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml b/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml
index ae04903f34bf..6a742a51e2f9 100644
--- a/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml
+++ b/Documentation/devicetree/bindings/hwmon/adi,ltc2947.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/hwmon/adi,ltc2947.yaml#
+$id: http://devicetree.org/schemas/hwmon/adi,ltc2947.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Analog Devices LTC2947 high precision power and energy monitor
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
index b245363d6d60..f0c072ff9eca 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
@@ -4,6 +4,7 @@ Required properties:
 - compatible :
   - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc
   - "fsl,imx8qxp-lpi2c" for LPI2C compatible with the one integrated on i.MX8QXP soc
+  - "fsl,imx8qm-lpi2c" for LPI2C compatible with the one integrated on i.MX8QM soc
 - reg : address and length of the lpi2c master registers
 - interrupts : lpi2c interrupt
 - clocks : lpi2c clock specifier
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
index e932d5aed02f..f0934b295edc 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
@@ -2,7 +2,7 @@
 # Copyright 2019 Analog Devices Inc.
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/iio/adc/adi,ad7124.yaml#
+$id: http://devicetree.org/schemas/iio/adc/adi,ad7124.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Analog Devices AD7124 ADC device driver
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
index 567a33a83dce..84d25bd39488 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
@@ -2,7 +2,7 @@
 # Copyright 2019 Analog Devices Inc.
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/iio/adc/adi,ad7192.yaml#
+$id: http://devicetree.org/schemas/iio/adc/adi,ad7192.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Analog Devices AD7192 ADC device driver
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
index 6eb33207a167..5117ad68a584 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
@@ -82,7 +82,7 @@ properties:
       Must be the device tree identifier of the over-sampling
       mode pins. As the line is active high, it should be marked
       GPIO_ACTIVE_HIGH.
-    maxItems: 1
+    maxItems: 3
 
   adi,sw-mode:
     description:
@@ -125,9 +125,9 @@ examples:
                 adi,conversion-start-gpios = <&gpio 17 GPIO_ACTIVE_HIGH>;
                 reset-gpios = <&gpio 27 GPIO_ACTIVE_HIGH>;
                 adi,first-data-gpios = <&gpio 22 GPIO_ACTIVE_HIGH>;
-                adi,oversampling-ratio-gpios = <&gpio 18 GPIO_ACTIVE_HIGH
-                                                &gpio 23 GPIO_ACTIVE_HIGH
-                                                &gpio 26 GPIO_ACTIVE_HIGH>;
+                adi,oversampling-ratio-gpios = <&gpio 18 GPIO_ACTIVE_HIGH>,
+                                               <&gpio 23 GPIO_ACTIVE_HIGH>,
+                                               <&gpio 26 GPIO_ACTIVE_HIGH>;
                 standby-gpios = <&gpio 24 GPIO_ACTIVE_LOW>;
                 adi,sw-mode;
         };
diff --git a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
index 881059b80d61..0ce290473fb0 100644
--- a/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/microchip,mcp3911.yaml
@@ -2,7 +2,7 @@
 # Copyright 2019 Marcus Folkesson <marcus.folkesson@gmail.com>
 %YAML 1.2
 ---
-$id: "http://devicetree.org/schemas/bindings/iio/adc/microchip,mcp3911.yaml#"
+$id: "http://devicetree.org/schemas/iio/adc/microchip,mcp3911.yaml#"
 $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 
 title: Microchip MCP3911 Dual channel analog front end (ADC)
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.txt b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.txt
deleted file mode 100644
index 75ba25d062e1..000000000000
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.txt
+++ /dev/null
@@ -1,135 +0,0 @@
-STMicroelectronics STM32 DFSDM ADC device driver
-
-
-STM32 DFSDM ADC is a sigma delta analog-to-digital converter dedicated to
-interface external sigma delta modulators to STM32 micro controllers.
-It is mainly targeted for:
-- Sigma delta modulators (motor control, metering...)
-- PDM microphones (audio digital microphone)
-
-It features up to 8 serial digital interfaces (SPI or Manchester) and
-up to 4 filters on stm32h7 or 6 filters on stm32mp1.
-
-Each child node match with a filter instance.
-
-Contents of a STM32 DFSDM root node:
-------------------------------------
-Required properties:
-- compatible: Should be one of:
-  "st,stm32h7-dfsdm"
-  "st,stm32mp1-dfsdm"
-- reg: Offset and length of the DFSDM block register set.
-- clocks: IP and serial interfaces clocking. Should be set according
-		to rcc clock ID and "clock-names".
-- clock-names: Input clock name "dfsdm" must be defined,
-		"audio" is optional. If defined CLKOUT is based on the audio
-		clock, else "dfsdm" is used.
-- #interrupt-cells = <1>;
-- #address-cells = <1>;
-- #size-cells = <0>;
-
-Optional properties:
-- spi-max-frequency: Requested only for SPI master mode.
-		  SPI clock OUT frequency (Hz). This clock must be set according
-		  to "clock" property. Frequency must be a multiple of the rcc
-		  clock frequency. If not, SPI CLKOUT frequency will not be
-		  accurate.
-- pinctrl-names:	Set to "default".
-- pinctrl-0:		List of phandles pointing to pin configuration
-			nodes to set pins in mode of operation for dfsdm
-			on external pin.
-
-Contents of a STM32 DFSDM child nodes:
---------------------------------------
-
-Required properties:
-- compatible: Must be:
-	"st,stm32-dfsdm-adc" for sigma delta ADCs
-	"st,stm32-dfsdm-dmic" for audio digital microphone.
-- reg: Specifies the DFSDM filter instance used.
-	Valid values are from 0 to 3 on stm32h7, 0 to 5 on stm32mp1.
-- interrupts: IRQ lines connected to each DFSDM filter instance.
-- st,adc-channels:	List of single-ended channels muxed for this ADC.
-			valid values:
-				"st,stm32h7-dfsdm" compatibility: 0 to 7.
-- st,adc-channel-names:	List of single-ended channel names.
-- st,filter-order:  SinC filter order from 0 to 5.
-			0: FastSinC
-			[1-5]: order 1 to 5.
-			For audio purpose it is recommended to use order 3 to 5.
-- #io-channel-cells = <1>: See the IIO bindings section "IIO consumers".
-
-Required properties for "st,stm32-dfsdm-adc" compatibility:
-- io-channels: From common IIO binding. Used to pipe external sigma delta
-		modulator or internal ADC output to DFSDM channel.
-		This is not required for "st,stm32-dfsdm-pdm" compatibility as
-		PDM microphone is binded in Audio DT node.
-
-Required properties for "st,stm32-dfsdm-pdm" compatibility:
-- #sound-dai-cells: Must be set to 0.
-- dma: DMA controller phandle and DMA request line associated to the
-		filter instance (specified by the field "reg")
-- dma-names: Must be "rx"
-
-Optional properties:
-- st,adc-channel-types:	Single-ended channel input type.
-			- "SPI_R": SPI with data on rising edge (default)
-			- "SPI_F": SPI with data on falling edge
-			- "MANCH_R": manchester codec, rising edge = logic 0, falling edge = logic 1
-			- "MANCH_F": manchester codec, rising edge = logic 1, falling edge = logic 0
-- st,adc-channel-clk-src: Conversion clock source.
-			  - "CLKIN": external SPI clock (CLKIN x)
-			  - "CLKOUT": internal SPI clock (CLKOUT) (default)
-			  - "CLKOUT_F": internal SPI clock divided by 2 (falling edge).
-			  - "CLKOUT_R": internal SPI clock divided by 2 (rising edge).
-
-- st,adc-alt-channel: Must be defined if two sigma delta modulator are
-			  connected on same SPI input.
-			  If not set, channel n is connected to SPI input n.
-			  If set, channel n is connected to SPI input n + 1.
-
-- st,filter0-sync: Set to 1 to synchronize with DFSDM filter instance 0.
-		   Used for multi microphones synchronization.
-
-Example of a sigma delta adc connected on DFSDM SPI port 0
-and a pdm microphone connected on DFSDM SPI port 1:
-
-	ads1202: simple_sd_adc@0 {
-		compatible = "ads1202";
-		#io-channel-cells = <1>;
-	};
-
-	dfsdm: dfsdm@40017000 {
-		compatible = "st,stm32h7-dfsdm";
-		reg = <0x40017000 0x400>;
-		clocks = <&rcc DFSDM1_CK>;
-		clock-names = "dfsdm";
-		#interrupt-cells = <1>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		dfsdm_adc0: filter@0 {
-			compatible = "st,stm32-dfsdm-adc";
-			#io-channel-cells = <1>;
-			reg = <0>;
-			interrupts = <110>;
-			st,adc-channels = <0>;
-			st,adc-channel-names = "sd_adc0";
-			st,adc-channel-types = "SPI_F";
-			st,adc-channel-clk-src = "CLKOUT";
-			io-channels = <&ads1202 0>;
-			st,filter-order = <3>;
-		};
-		dfsdm_pdm1: filter@1 {
-			compatible = "st,stm32-dfsdm-dmic";
-			reg = <1>;
-			interrupts = <111>;
-			dmas = <&dmamux1 102 0x400 0x00>;
-			dma-names = "rx";
-			st,adc-channels = <1>;
-			st,adc-channel-names = "dmic1";
-			st,adc-channel-types = "SPI_R";
-			st,adc-channel-clk-src = "CLKOUT";
-			st,filter-order = <5>;
-		};
-	}
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
new file mode 100644
index 000000000000..acf36eef728b
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-dfsdm-adc.yaml
@@ -0,0 +1,332 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iio/adc/st,stm32-dfsdm-adc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 DFSDM ADC device driver
+
+maintainers:
+  - Fabrice Gasnier <fabrice.gasnier@st.com>
+  - Olivier Moysan <olivier.moysan@st.com>
+
+description: |
+  STM32 DFSDM ADC is a sigma delta analog-to-digital converter dedicated to
+  interface external sigma delta modulators to STM32 micro controllers.
+  It is mainly targeted for:
+  - Sigma delta modulators (motor control, metering...)
+  - PDM microphones (audio digital microphone)
+
+  It features up to 8 serial digital interfaces (SPI or Manchester) and
+  up to 4 filters on stm32h7 or 6 filters on stm32mp1.
+
+  Each child node matches with a filter instance.
+
+properties:
+  compatible:
+    enum:
+      - st,stm32h7-dfsdm
+      - st,stm32mp1-dfsdm
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description:
+          Internal clock used for DFSDM digital processing and control blocks.
+          dfsdm clock can also feed CLKOUT, when CLKOUT is used.
+      - description: audio clock can be used as an alternate to feed CLKOUT.
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: dfsdm
+      - const: audio
+    minItems: 1
+    maxItems: 2
+
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 0
+
+  spi-max-frequency:
+    description:
+      SPI clock OUT frequency (Hz). Requested only for SPI master mode.
+      This clock must be set according to the "clock" property.
+      Frequency must be a multiple of the rcc clock frequency.
+      If not, SPI CLKOUT frequency will not be accurate.
+    maximum: 20000000
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - "#address-cells"
+  - "#size-cells"
+
+patternProperties:
+  "^filter@[0-9]+$":
+    type: object
+    description: child node
+
+    properties:
+      compatible:
+        enum:
+          - st,stm32-dfsdm-adc
+          - st,stm32-dfsdm-dmic
+
+      reg:
+        description: Specifies the DFSDM filter instance used.
+        maxItems: 1
+
+      interrupts:
+        maxItems: 1
+
+      st,adc-channels:
+        description: |
+          List of single-ended channels muxed for this ADC.
+          On stm32h7 and stm32mp1:
+          - For st,stm32-dfsdm-adc: up to 8 channels numbered from 0 to 7.
+          - For st,stm32-dfsdm-dmic: 1 channel numbered from 0 to 7.
+        allOf:
+          - $ref: /schemas/types.yaml#/definitions/uint32-array
+          - items:
+              minimum: 0
+              maximum: 7
+
+      st,adc-channel-names:
+        description: List of single-ended channel names.
+        allOf:
+          - $ref: /schemas/types.yaml#/definitions/string-array
+
+      st,filter-order:
+        description: |
+          SinC filter order from 0 to 5.
+          - 0: FastSinC
+          - [1-5]: order 1 to 5.
+          For audio purpose it is recommended to use order 3 to 5.
+        allOf:
+          - $ref: /schemas/types.yaml#/definitions/uint32
+          - items:
+              minimum: 0
+              maximum: 5
+
+      "#io-channel-cells":
+        const: 1
+
+      st,adc-channel-types:
+        description: |
+          Single-ended channel input type.
+          - "SPI_R": SPI with data on rising edge (default)
+          - "SPI_F": SPI with data on falling edge
+          - "MANCH_R": manchester codec, rising edge = logic 0, falling edge = logic 1
+          - "MANCH_F": manchester codec, rising edge = logic 1, falling edge = logic 0
+        items:
+          enum: [ SPI_R, SPI_F, MANCH_R, MANCH_F ]
+        allOf:
+          - $ref: /schemas/types.yaml#/definitions/non-unique-string-array
+
+      st,adc-channel-clk-src:
+        description: |
+          Conversion clock source.
+          - "CLKIN": external SPI clock (CLKIN x)
+          - "CLKOUT": internal SPI clock (CLKOUT) (default)
+          - "CLKOUT_F": internal SPI clock divided by 2 (falling edge).
+          - "CLKOUT_R": internal SPI clock divided by 2 (rising edge).
+        items:
+          enum: [ CLKIN, CLKOUT, CLKOUT_F, CLKOUT_R ]
+        allOf:
+          - $ref: /schemas/types.yaml#/definitions/non-unique-string-array
+
+      st,adc-alt-channel:
+        description:
+          Must be defined if two sigma delta modulators are
+          connected on same SPI input.
+          If not set, channel n is connected to SPI input n.
+          If set, channel n is connected to SPI input n + 1.
+        type: boolean
+
+      st,filter0-sync:
+        description:
+          Set to 1 to synchronize with DFSDM filter instance 0.
+          Used for multi microphones synchronization.
+        type: boolean
+
+      dmas:
+        maxItems: 1
+
+      dma-names:
+        items:
+          - const: rx
+
+    required:
+      - compatible
+      - reg
+      - interrupts
+      - st,adc-channels
+      - st,adc-channel-names
+      - st,filter-order
+      - "#io-channel-cells"
+
+    allOf:
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: st,stm32-dfsdm-adc
+
+      - then:
+          properties:
+            st,adc-channels:
+              minItems: 1
+              maxItems: 8
+
+            st,adc-channel-names:
+              minItems: 1
+              maxItems: 8
+
+            st,adc-channel-types:
+              minItems: 1
+              maxItems: 8
+
+            st,adc-channel-clk-src:
+              minItems: 1
+              maxItems: 8
+
+            io-channels:
+              description:
+                From common IIO binding. Used to pipe external sigma delta
+                modulator or internal ADC output to DFSDM channel.
+                This is not required for "st,stm32-dfsdm-pdm" compatibility as
+                PDM microphone is binded in Audio DT node.
+
+          required:
+            - io-channels
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: st,stm32-dfsdm-dmic
+
+      - then:
+          properties:
+            st,adc-channels:
+              maxItems: 1
+
+            st,adc-channel-names:
+              maxItems: 1
+
+            st,adc-channel-types:
+              maxItems: 1
+
+            st,adc-channel-clk-src:
+              maxItems: 1
+
+          required:
+            - dmas
+            - dma-names
+
+          patternProperties:
+            "^dfsdm-dai+$":
+              type: object
+              description: child node
+
+              properties:
+                "#sound-dai-cells":
+                  const: 0
+
+                io-channels:
+                  description:
+                    From common IIO binding. Used to pipe external sigma delta
+                    modulator or internal ADC output to DFSDM channel.
+
+              required:
+                - "#sound-dai-cells"
+                - io-channels
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: st,stm32h7-dfsdm
+
+  - then:
+      patternProperties:
+        "^filter@[0-9]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 3
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: st,stm32mp1-dfsdm
+
+  - then:
+      patternProperties:
+        "^filter@[0-9]+$":
+          properties:
+            reg:
+              items:
+                minimum: 0
+                maximum: 5
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    dfsdm: dfsdm@4400d000 {
+      compatible = "st,stm32mp1-dfsdm";
+      reg = <0x4400d000 0x800>;
+      clocks = <&rcc DFSDM_K>, <&rcc ADFSDM_K>;
+      clock-names = "dfsdm", "audio";
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      dfsdm0: filter@0 {
+        compatible = "st,stm32-dfsdm-dmic";
+        reg = <0>;
+        interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH>;
+        dmas = <&dmamux1 101 0x400 0x01>;
+        dma-names = "rx";
+        #io-channel-cells = <1>;
+        st,adc-channels = <1>;
+        st,adc-channel-names = "dmic0";
+        st,adc-channel-types = "SPI_R";
+        st,adc-channel-clk-src = "CLKOUT";
+        st,filter-order = <5>;
+
+        asoc_pdm0: dfsdm-dai {
+          compatible = "st,stm32h7-dfsdm-dai";
+          #sound-dai-cells = <0>;
+          io-channels = <&dfsdm0 0>;
+        };
+      };
+
+      dfsdm_pdm1: filter@1 {
+        compatible = "st,stm32-dfsdm-adc";
+        reg = <1>;
+        interrupts = <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>;
+        dmas = <&dmamux1 102 0x400 0x01>;
+        dma-names = "rx";
+        #io-channel-cells = <1>;
+        st,adc-channels = <2 3>;
+        st,adc-channel-names = "in2", "in3";
+        st,adc-channel-types = "SPI_R", "SPI_R";
+        st,adc-channel-clk-src = "CLKOUT_F", "CLKOUT_F";
+        io-channels = <&sd_adc2 &sd_adc3>;
+        st,filter-order = <1>;
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/iio/dac/lltc,ltc1660.yaml b/Documentation/devicetree/bindings/iio/dac/lltc,ltc1660.yaml
index 13d005b68931..a285eaba7125 100644
--- a/Documentation/devicetree/bindings/iio/dac/lltc,ltc1660.yaml
+++ b/Documentation/devicetree/bindings/iio/dac/lltc,ltc1660.yaml
@@ -2,7 +2,7 @@
 # Copyright 2019 Marcus Folkesson <marcus.folkesson@gmail.com>
 %YAML 1.2
 ---
-$id: "http://devicetree.org/schemas/bindings/iio/dac/lltc,ltc1660.yaml#"
+$id: "http://devicetree.org/schemas/iio/dac/lltc,ltc1660.yaml#"
 $schema: "http://devicetree.org/meta-schemas/core.yaml#"
 
 title: Linear Technology Micropower octal 8-Bit and 10-Bit DACs
diff --git a/Documentation/devicetree/bindings/input/gpio-vibrator.yaml b/Documentation/devicetree/bindings/input/gpio-vibrator.yaml
index 903475f52dbd..b98bf9363c8f 100644
--- a/Documentation/devicetree/bindings/input/gpio-vibrator.yaml
+++ b/Documentation/devicetree/bindings/input/gpio-vibrator.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/bindings/input/gpio-vibrator.yaml#
+$id: http://devicetree.org/schemas/input/gpio-vibrator.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: GPIO vibrator
diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
index 0f6950073d6f..0e57315e9cbd 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
@@ -36,6 +36,8 @@ Optional properties:
  - pinctrl-0:   a phandle pointing to the pin settings for the
                 control gpios
 
+ - wakeup-source: If present the device will act as wakeup-source
+
  - threshold:   allows setting the "click"-threshold in the range
                 from 0 to 80.
 
diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
deleted file mode 100644
index fc03ea4cf5ab..000000000000
--- a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
+++ /dev/null
@@ -1,50 +0,0 @@
-Device tree bindings for Goodix GT9xx series touchscreen controller
-
-Required properties:
-
- - compatible		: Should be "goodix,gt1151"
-				 or "goodix,gt5663"
-				 or "goodix,gt5688"
-				 or "goodix,gt911"
-				 or "goodix,gt9110"
-				 or "goodix,gt912"
-				 or "goodix,gt927"
-				 or "goodix,gt9271"
-				 or "goodix,gt928"
-				 or "goodix,gt967"
- - reg			: I2C address of the chip. Should be 0x5d or 0x14
- - interrupts		: Interrupt to which the chip is connected
-
-Optional properties:
-
- - irq-gpios		: GPIO pin used for IRQ. The driver uses the
-			  interrupt gpio pin as output to reset the device.
- - reset-gpios		: GPIO pin used for reset
- - AVDD28-supply	: Analog power supply regulator on AVDD28 pin
- - VDDIO-supply		: GPIO power supply regulator on VDDIO pin
- - touchscreen-inverted-x
- - touchscreen-inverted-y
- - touchscreen-size-x
- - touchscreen-size-y
- - touchscreen-swapped-x-y
-
-The touchscreen-* properties are documented in touchscreen.txt in this
-directory.
-
-Example:
-
-	i2c@00000000 {
-		/* ... */
-
-		gt928@5d {
-			compatible = "goodix,gt928";
-			reg = <0x5d>;
-			interrupt-parent = <&gpio>;
-			interrupts = <0 0>;
-
-			irq-gpios = <&gpio1 0 0>;
-			reset-gpios = <&gpio1 1 0>;
-		};
-
-		/* ... */
-	};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml b/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml
new file mode 100644
index 000000000000..d7c3262b2494
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/goodix.yaml
@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/goodix.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Goodix GT9xx series touchscreen controller Bindings
+
+maintainers:
+  - Dmitry Torokhov <dmitry.torokhov@gmail.com>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    enum:
+      - goodix,gt1151
+      - goodix,gt5663
+      - goodix,gt5688
+      - goodix,gt911
+      - goodix,gt9110
+      - goodix,gt912
+      - goodix,gt927
+      - goodix,gt9271
+      - goodix,gt928
+      - goodix,gt967
+
+  reg:
+    enum: [ 0x5d, 0x14 ]
+
+  interrupts:
+    maxItems: 1
+
+  irq-gpios:
+    description: GPIO pin used for IRQ.
+                 The driver uses the interrupt gpio pin as
+                 output to reset the device.
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  AVDD28-supply:
+    description: Analog power supply regulator on AVDD28 pin
+
+  VDDIO-supply:
+    description: GPIO power supply regulator on VDDIO pin
+
+  touchscreen-inverted-x: true
+  touchscreen-inverted-y: true
+  touchscreen-size-x: true
+  touchscreen-size-y: true
+  touchscreen-swapped-x-y: true
+
+additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+examples:
+- |
+    i2c@00000000 {
+      #address-cells = <1>;
+      #size-cells = <0>;
+      gt928@5d {
+        compatible = "goodix,gt928";
+        reg = <0x5d>;
+        interrupt-parent = <&gpio>;
+        interrupts = <0 0>;
+        irq-gpios = <&gpio1 0 0>;
+        reset-gpios = <&gpio1 1 0>;
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt
index 8641a2d70851..e1adb902d503 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.txt
@@ -1,39 +1 @@
-General Touchscreen Properties:
-
-Optional properties for Touchscreens:
- - touchscreen-min-x		: minimum x coordinate reported (0 if not set)
- - touchscreen-min-y		: minimum y coordinate reported (0 if not set)
- - touchscreen-size-x		: horizontal resolution of touchscreen
-				  (maximum x coordinate reported + 1)
- - touchscreen-size-y		: vertical resolution of touchscreen
-				  (maximum y coordinate reported + 1)
- - touchscreen-max-pressure	: maximum reported pressure (arbitrary range
-				  dependent on the controller)
- - touchscreen-min-pressure	: minimum pressure on the touchscreen to be
-				  achieved in order for the touchscreen
-				  driver to report a touch event.
- - touchscreen-fuzz-x		: horizontal noise value of the absolute input
-				  device (in pixels)
- - touchscreen-fuzz-y		: vertical noise value of the absolute input
-				  device (in pixels)
- - touchscreen-fuzz-pressure	: pressure noise value of the absolute input
-				  device (arbitrary range dependent on the
-				  controller)
- - touchscreen-average-samples : Number of data samples which are averaged
-				  for each read (valid values dependent on the
-				  controller)
- - touchscreen-inverted-x	: X axis is inverted (boolean)
- - touchscreen-inverted-y	: Y axis is inverted (boolean)
- - touchscreen-swapped-x-y	: X and Y axis are swapped (boolean)
-				  Swapping is done after inverting the axis
- - touchscreen-x-mm		: horizontal length in mm of the touchscreen
- - touchscreen-y-mm		: vertical length in mm of the touchscreen
-
-Deprecated properties for Touchscreens:
- - x-size			: deprecated name for touchscreen-size-x
- - y-size			: deprecated name for touchscreen-size-y
- - moving-threshold		: deprecated name for a combination of
-				  touchscreen-fuzz-x and touchscreen-fuzz-y
- - contact-threshold		: deprecated name for touchscreen-fuzz-pressure
- - x-invert			: deprecated name for touchscreen-inverted-x
- - y-invert			: deprecated name for touchscreen-inverted-y
+See touchscreen.yaml
diff --git a/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
new file mode 100644
index 000000000000..d7dac16a3960
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/touchscreen.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/touchscreen.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Common touchscreen Bindings
+
+maintainers:
+  - Dmitry Torokhov <dmitry.torokhov@gmail.com>
+
+properties:
+  touchscreen-min-x:
+    description: minimum x coordinate reported
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 0
+
+  touchscreen-min-y:
+    description: minimum y coordinate reported
+    $ref: /schemas/types.yaml#/definitions/uint32
+    default: 0
+
+  touchscreen-size-x:
+    description: horizontal resolution of touchscreen (maximum x coordinate reported + 1)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-size-y:
+    description: vertical resolution of touchscreen (maximum y coordinate reported + 1)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-max-pressure:
+    description: maximum reported pressure (arbitrary range dependent on the controller)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-min-pressure:
+    description: minimum pressure on the touchscreen to be achieved in order for the
+                 touchscreen driver to report a touch event.
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-fuzz-x:
+    description: horizontal noise value of the absolute input device (in pixels)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-fuzz-y:
+    description: vertical noise value of the absolute input device (in pixels)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-fuzz-pressure:
+    description: pressure noise value of the absolute input device (arbitrary range
+                 dependent on the controller)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-average-samples:
+    description: Number of data samples which are averaged for each read (valid values
+                 dependent on the controller)
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-inverted-x:
+    description: X axis is inverted
+    type: boolean
+
+  touchscreen-inverted-y:
+    description: Y axis is inverted
+    type: boolean
+
+  touchscreen-swapped-x-y:
+    description: X and Y axis are swapped
+                 Swapping is done after inverting the axis
+    type: boolean
+
+  touchscreen-x-mm:
+    description: horizontal length in mm of the touchscreen
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  touchscreen-y-mm:
+    description: vertical length in mm of the touchscreen
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+dependencies:
+  touchscreen-size-x: [ touchscreen-size-y ]
+  touchscreen-size-y: [ touchscreen-size-x ]
+  touchscreen-x-mm: [ touchscreen-y-mm ]
+  touchscreen-y-mm: [ touchscreen-x-mm ]
diff --git a/Documentation/devicetree/bindings/iommu/iommu.txt b/Documentation/devicetree/bindings/iommu/iommu.txt
index 5a8b4624defc..3c36334e4f94 100644
--- a/Documentation/devicetree/bindings/iommu/iommu.txt
+++ b/Documentation/devicetree/bindings/iommu/iommu.txt
@@ -86,6 +86,12 @@ have a means to turn off translation. But it is invalid in such cases to
 disable the IOMMU's device tree node in the first place because it would
 prevent any driver from properly setting up the translations.
 
+Optional properties:
+--------------------
+- pasid-num-bits: Some masters support multiple address spaces for DMA, by
+  tagging DMA transactions with an address space identifier. By default,
+  this is 0, which means that the device only has one address space.
+
 
 Notes:
 ======
diff --git a/Documentation/devicetree/bindings/leds/common.txt b/Documentation/devicetree/bindings/leds/common.txt
index 9fa6f9795d50..26d770ef3601 100644
--- a/Documentation/devicetree/bindings/leds/common.txt
+++ b/Documentation/devicetree/bindings/leds/common.txt
@@ -1,173 +1 @@
-* Common leds properties.
-
-LED and flash LED devices provide the same basic functionality as current
-regulators, but extended with LED and flash LED specific features like
-blinking patterns, flash timeout, flash faults and external flash strobe mode.
-
-Many LED devices expose more than one current output that can be connected
-to one or more discrete LED component. Since the arrangement of connections
-can influence the way of the LED device initialization, the LED components
-have to be tightly coupled with the LED device binding. They are represented
-by child nodes of the parent LED device binding.
-
-
-Optional properties for child nodes:
-- led-sources : List of device current outputs the LED is connected to. The
-		outputs are identified by the numbers that must be defined
-		in the LED device binding documentation.
-
-- function: LED functon. Use one of the LED_FUNCTION_* prefixed definitions
-	    from the header include/dt-bindings/leds/common.h.
-	    If there is no matching LED_FUNCTION available, add a new one.
-
-- color : Color of the LED. Use one of the LED_COLOR_ID_* prefixed definitions
-	  from the header include/dt-bindings/leds/common.h.
-	  If there is no matching LED_COLOR_ID available, add a new one.
-
-- function-enumerator: Integer to be used when more than one instance
-                       of the same function is needed, differing only with
-		       an ordinal number.
-
-- label : The label for this LED. If omitted, the label is taken from the node
-	  name (excluding the unit address). It has to uniquely identify
-	  a device, i.e. no other LED class device can be assigned the same
-	  label. This property is deprecated - use 'function' and 'color'
-	  properties instead. function-enumerator has no effect when this
-	  property is present.
-
-- default-state : The initial state of the LED. Valid values are "on", "off",
-  and "keep". If the LED is already on or off and the default-state property is
-  set the to same value, then no glitch should be produced where the LED
-  momentarily turns off (or on). The "keep" setting will keep the LED at
-  whatever its current state is, without producing a glitch.  The default is
-  off if this property is not present.
-
-- linux,default-trigger :  This parameter, if present, is a
-    string defining the trigger assigned to the LED.  Current triggers are:
-     "backlight" - LED will act as a back-light, controlled by the framebuffer
-		   system
-     "default-on" - LED will turn on (but for leds-gpio see "default-state"
-		    property in Documentation/devicetree/bindings/leds/leds-gpio.txt)
-     "heartbeat" - LED "double" flashes at a load average based rate
-     "disk-activity" - LED indicates disk activity
-     "ide-disk" - LED indicates IDE disk activity (deprecated),
-                  in new implementations use "disk-activity"
-     "timer" - LED flashes at a fixed, configurable rate
-     "pattern" - LED alters the brightness for the specified duration with one
-                 software timer (requires "led-pattern" property)
-
-- led-pattern : Array of integers with default pattern for certain triggers.
-                Each trigger may parse this property differently:
-                - one-shot : two numbers specifying delay on and delay off (in ms),
-                - timer : two numbers specifying delay on and delay off (in ms),
-                - pattern : the pattern is given by a series of tuples, of
-                  brightness and duration (in ms).  The exact format is
-                  described in:
-                  Documentation/devicetree/bindings/leds/leds-trigger-pattern.txt
-
-
-- led-max-microamp : Maximum LED supply current in microamperes. This property
-                     can be made mandatory for the board configurations
-                     introducing a risk of hardware damage in case an excessive
-                     current is set.
-                     For flash LED controllers with configurable current this
-                     property is mandatory for the LEDs in the non-flash modes
-                     (e.g. torch or indicator).
-
-- panic-indicator : This property specifies that the LED should be used,
-		    if at all possible, as a panic indicator.
-
-- trigger-sources : List of devices which should be used as a source triggering
-		    this LED activity. Some LEDs can be related to a specific
-		    device and should somehow indicate its state. E.g. USB 2.0
-		    LED may react to device(s) in a USB 2.0 port(s).
-		    Another common example is switch or router with multiple
-		    Ethernet ports each of them having its own LED assigned
-		    (assuming they are not hardwired). In such cases this
-		    property should contain phandle(s) of related source
-		    device(s).
-		    In many cases LED can be related to more than one device
-		    (e.g. one USB LED vs. multiple USB ports). Each source
-		    should be represented by a node in the device tree and be
-		    referenced by a phandle and a set of phandle arguments. A
-		    length of arguments should be specified by the
-		    #trigger-source-cells property in the source node.
-
-Required properties for flash LED child nodes:
-- flash-max-microamp : Maximum flash LED supply current in microamperes.
-- flash-max-timeout-us : Maximum timeout in microseconds after which the flash
-                         LED is turned off.
-
-For controllers that have no configurable current the flash-max-microamp
-property can be omitted.
-For controllers that have no configurable timeout the flash-max-timeout-us
-property can be omitted.
-
-* Trigger source providers
-
-Each trigger source should be represented by a device tree node. It may be e.g.
-a USB port or an Ethernet device.
-
-Required properties for trigger source:
-- #trigger-source-cells : Number of cells in a source trigger. Typically 0 for
-			  nodes of simple trigger sources (e.g. a specific USB
-			  port).
-
-* Examples
-
-#include <dt-bindings/leds/common.h>
-
-led-controller@0 {
-	compatible = "gpio-leds";
-
-	led0 {
-		function = LED_FUNCTION_STATUS;
-		linux,default-trigger = "heartbeat";
-		gpios = <&gpio0 0 GPIO_ACTIVE_HIGH>;
-	};
-
-	led1 {
-		function = LED_FUNCTION_USB;
-		gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>;
-		trigger-sources = <&ohci_port1>, <&ehci_port1>;
-	};
-};
-
-led-controller@0 {
-	compatible = "maxim,max77693-led";
-
-	led {
-		function = LED_FUNCTION_FLASH;
-		color = <LED_COLOR_ID_WHITE>;
-		led-sources = <0>, <1>;
-		led-max-microamp = <50000>;
-		flash-max-microamp = <320000>;
-		flash-max-timeout-us = <500000>;
-	};
-};
-
-led-controller@30 {
-        compatible = "panasonic,an30259a";
-        reg = <0x30>;
-        #address-cells = <1>;
-        #size-cells = <0>;
-
-        led@1 {
-		reg = <1>;
-		linux,default-trigger = "heartbeat";
-		function = LED_FUNCTION_INDICATOR;
-		function-enumerator = <1>;
-        };
-
-        led@2 {
-		reg = <2>;
-		function = LED_FUNCTION_INDICATOR;
-		function-enumerator = <2>;
-        };
-
-        led@3 {
-		reg = <3>;
-		function = LED_FUNCTION_INDICATOR;
-		function-enumerator = <3>;
-        };
-};
+This file has moved to ./common.yaml.
diff --git a/Documentation/devicetree/bindings/leds/common.yaml b/Documentation/devicetree/bindings/leds/common.yaml
new file mode 100644
index 000000000000..d97d099b87e5
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/common.yaml
@@ -0,0 +1,228 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/common.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Common leds properties
+
+maintainers:
+  - Jacek Anaszewski <jacek.anaszewski@gmail.com>
+  - Pavel Machek <pavel@ucw.cz>
+
+description:
+  LED and flash LED devices provide the same basic functionality as current
+  regulators, but extended with LED and flash LED specific features like
+  blinking patterns, flash timeout, flash faults and external flash strobe mode.
+
+  Many LED devices expose more than one current output that can be connected
+  to one or more discrete LED component. Since the arrangement of connections
+  can influence the way of the LED device initialization, the LED components
+  have to be tightly coupled with the LED device binding. They are represented
+  by child nodes of the parent LED device binding.
+
+properties:
+  led-sources:
+    description:
+      List of device current outputs the LED is connected to. The outputs are
+      identified by the numbers that must be defined in the LED device binding
+      documentation.
+    $ref: /schemas/types.yaml#definitions/uint32-array
+
+  function:
+    description:
+      LED function. Use one of the LED_FUNCTION_* prefixed definitions
+      from the header include/dt-bindings/leds/common.h. If there is no
+      matching LED_FUNCTION available, add a new one.
+    $ref: /schemas/types.yaml#definitions/string
+
+  color:
+    description:
+      Color of the LED. Use one of the LED_COLOR_ID_* prefixed definitions from
+      the header include/dt-bindings/leds/common.h. If there is no matching
+      LED_COLOR_ID available, add a new one.
+    allOf:
+      - $ref: /schemas/types.yaml#definitions/uint32
+    minimum: 0
+    maximum: 8
+
+  function-enumerator:
+    description:
+      Integer to be used when more than one instance of the same function is
+      needed, differing only with an ordinal number.
+    $ref: /schemas/types.yaml#definitions/uint32
+
+  label:
+    description:
+      The label for this LED. If omitted, the label is taken from the node name
+      (excluding the unit address). It has to uniquely identify a device, i.e.
+      no other LED class device can be assigned the same label. This property is
+      deprecated - use 'function' and 'color' properties instead.
+      function-enumerator has no effect when this property is present.
+
+  default-state:
+    description:
+      The initial state of the LED. If the LED is already on or off and the
+      default-state property is set the to same value, then no glitch should be
+      produced where the LED momentarily turns off (or on). The "keep" setting
+      will keep the LED at whatever its current state is, without producing a
+      glitch.
+    allOf:
+      - $ref: /schemas/types.yaml#definitions/string
+    enum:
+      - on
+      - off
+      - keep
+    default: off
+
+  linux,default-trigger:
+    description:
+      This parameter, if present, is a string defining the trigger assigned to
+      the LED.
+    allOf:
+      - $ref: /schemas/types.yaml#definitions/string
+    enum:
+        # LED will act as a back-light, controlled by the framebuffer system
+      - backlight
+        # LED will turn on (but for leds-gpio see "default-state" property in
+        # Documentation/devicetree/bindings/leds/leds-gpio.txt)
+      - default-on
+        # LED "double" flashes at a load average based rate
+      - heartbeat
+        # LED indicates disk activity
+      - disk-activity
+        # LED indicates IDE disk activity (deprecated), in new implementations
+        # use "disk-activity"
+      - ide-disk
+        # LED flashes at a fixed, configurable rate
+      - timer
+        # LED alters the brightness for the specified duration with one software
+        # timer (requires "led-pattern" property)
+      - pattern
+
+  led-pattern:
+    description: |
+      Array of integers with default pattern for certain triggers.
+
+      Each trigger may parse this property differently:
+        - one-shot : two numbers specifying delay on and delay off (in ms),
+        - timer : two numbers specifying delay on and delay off (in ms),
+        - pattern : the pattern is given by a series of tuples, of
+          brightness and duration (in ms).  The exact format is
+          described in:
+          Documentation/devicetree/bindings/leds/leds-trigger-pattern.txt
+    allOf:
+      - $ref: /schemas/types.yaml#definitions/uint32-matrix
+    items:
+      minItems: 2
+      maxItems: 2
+
+  led-max-microamp:
+    description:
+      Maximum LED supply current in microamperes. This property can be made
+      mandatory for the board configurations introducing a risk of hardware
+      damage in case an excessive current is set.
+      For flash LED controllers with configurable current this property is
+      mandatory for the LEDs in the non-flash modes (e.g. torch or indicator).
+
+  panic-indicator:
+    description:
+      This property specifies that the LED should be used, if at all possible,
+      as a panic indicator.
+    type: boolean
+
+  trigger-sources:
+    description: |
+      List of devices which should be used as a source triggering this LED
+      activity. Some LEDs can be related to a specific device and should somehow
+      indicate its state. E.g. USB 2.0 LED may react to device(s) in a USB 2.0
+      port(s).
+      Another common example is switch or router with multiple Ethernet ports
+      each of them having its own LED assigned (assuming they are not
+      hardwired). In such cases this property should contain phandle(s) of
+      related source device(s).
+      In many cases LED can be related to more than one device (e.g. one USB LED
+      vs. multiple USB ports). Each source should be represented by a node in
+      the device tree and be referenced by a phandle and a set of phandle
+      arguments. A length of arguments should be specified by the
+      #trigger-source-cells property in the source node.
+    $ref: /schemas/types.yaml#definitions/phandle-array
+
+  # Required properties for flash LED child nodes:
+  flash-max-microamp:
+    description:
+      Maximum flash LED supply current in microamperes. Required for flash LED
+      nodes with configurable current.
+
+  flash-max-timeout-us:
+    description:
+      Maximum timeout in microseconds after which the flash LED is turned off.
+      Required for flash LED nodes with configurable timeout.
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/leds/common.h>
+
+    led-controller {
+        compatible = "gpio-leds";
+
+        led0 {
+            function = LED_FUNCTION_STATUS;
+            linux,default-trigger = "heartbeat";
+            gpios = <&gpio0 0 GPIO_ACTIVE_HIGH>;
+        };
+
+        led1 {
+            function = LED_FUNCTION_USB;
+            gpios = <&gpio0 1 GPIO_ACTIVE_HIGH>;
+            trigger-sources = <&ohci_port1>, <&ehci_port1>;
+        };
+    };
+
+    led-controller@0 {
+        compatible = "maxim,max77693-led";
+        reg = <0 0x100>;
+
+        led {
+            function = LED_FUNCTION_FLASH;
+            color = <LED_COLOR_ID_WHITE>;
+            led-sources = <0>, <1>;
+            led-max-microamp = <50000>;
+            flash-max-microamp = <320000>;
+            flash-max-timeout-us = <500000>;
+        };
+    };
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        led-controller@30 {
+            compatible = "panasonic,an30259a";
+            reg = <0x30>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            led@1 {
+                reg = <1>;
+                linux,default-trigger = "heartbeat";
+                function = LED_FUNCTION_INDICATOR;
+                function-enumerator = <1>;
+            };
+
+            led@2 {
+                reg = <2>;
+                function = LED_FUNCTION_INDICATOR;
+                function-enumerator = <2>;
+            };
+
+            led@3 {
+                reg = <3>;
+                function = LED_FUNCTION_INDICATOR;
+                function-enumerator = <3>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/leds/irled/spi-ir-led.txt b/Documentation/devicetree/bindings/leds/irled/spi-ir-led.txt
index 21882c8d4b0c..83ff1b4d70a6 100644
--- a/Documentation/devicetree/bindings/leds/irled/spi-ir-led.txt
+++ b/Documentation/devicetree/bindings/leds/irled/spi-ir-led.txt
@@ -8,7 +8,7 @@ Required properties:
 	- compatible: should be "ir-spi-led".
 
 Optional properties:
-	- duty-cycle: 8 bit balue that represents the percentage of one period
+	- duty-cycle: 8 bit value that represents the percentage of one period
 	  in which the signal is active.  It can be 50, 60, 70, 75, 80 or 90.
 	- led-active-low: boolean value that specifies whether the output is
 	  negated with a NOT gate.
diff --git a/Documentation/devicetree/bindings/leds/leds-gpio.txt b/Documentation/devicetree/bindings/leds/leds-gpio.txt
deleted file mode 100644
index d21281b63d38..000000000000
--- a/Documentation/devicetree/bindings/leds/leds-gpio.txt
+++ /dev/null
@@ -1,75 +0,0 @@
-LEDs connected to GPIO lines
-
-Required properties:
-- compatible : should be "gpio-leds".
-
-Each LED is represented as a sub-node of the gpio-leds device.  Each
-node's name represents the name of the corresponding LED.
-
-LED sub-node properties:
-- gpios :  Should specify the LED's GPIO, see "gpios property" in
-  Documentation/devicetree/bindings/gpio/gpio.txt.  Active low LEDs should be
-  indicated using flags in the GPIO specifier.
-- function :  (optional)
-  see Documentation/devicetree/bindings/leds/common.txt
-- color :  (optional)
-  see Documentation/devicetree/bindings/leds/common.txt
-- label :  (optional)
-  see Documentation/devicetree/bindings/leds/common.txt (deprecated)
-- linux,default-trigger :  (optional)
-  see Documentation/devicetree/bindings/leds/common.txt
-- default-state:  (optional) The initial state of the LED.
-  see Documentation/devicetree/bindings/leds/common.txt
-- retain-state-suspended: (optional) The suspend state can be retained.Such
-  as charge-led gpio.
-- retain-state-shutdown: (optional) Retain the state of the LED on shutdown.
-  Useful in BMC systems, for example when the BMC is rebooted while the host
-  remains up.
-- panic-indicator : (optional)
-  see Documentation/devicetree/bindings/leds/common.txt
-
-Examples:
-
-#include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/leds/common.h>
-
-leds {
-	compatible = "gpio-leds";
-	led0 {
-		gpios = <&mcu_pio 0 GPIO_ACTIVE_LOW>;
-		linux,default-trigger = "disk-activity";
-		function = LED_FUNCTION_DISK;
-	};
-
-	led1 {
-		gpios = <&mcu_pio 1 GPIO_ACTIVE_HIGH>;
-		/* Keep LED on if BIOS detected hardware fault */
-		default-state = "keep";
-		function = LED_FUNCTION_FAULT;
-	};
-};
-
-run-control {
-	compatible = "gpio-leds";
-	led0 {
-		gpios = <&mpc8572 6 GPIO_ACTIVE_HIGH>;
-		color = <LED_COLOR_ID_RED>;
-		default-state = "off";
-	};
-	led1 {
-		gpios = <&mpc8572 7 GPIO_ACTIVE_HIGH>;
-		color = <LED_COLOR_ID_GREEN>;
-		default-state = "on";
-	};
-};
-
-leds {
-	compatible = "gpio-leds";
-
-	led0 {
-		gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
-		linux,default-trigger = "max8903-charger-charging";
-		retain-state-suspended;
-		function = LED_FUNCTION_CHARGE;
-	};
-};
diff --git a/Documentation/devicetree/bindings/leds/leds-gpio.yaml b/Documentation/devicetree/bindings/leds/leds-gpio.yaml
new file mode 100644
index 000000000000..0e75b185dd19
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-gpio.yaml
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/leds-gpio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: LEDs connected to GPIO lines
+
+maintainers:
+  - Jacek Anaszewski <jacek.anaszewski@gmail.com>
+  - Pavel Machek <pavel@ucw.cz>
+
+description:
+  Each LED is represented as a sub-node of the gpio-leds device.  Each
+  node's name represents the name of the corresponding LED.
+
+properties:
+  compatible:
+    const: gpio-leds
+
+patternProperties:
+  # The first form is preferred, but fall back to just 'led' anywhere in the
+  # node name to at least catch some child nodes.
+  "(^led-[0-9a-f]$|led)":
+    type: object
+
+    allOf:
+      - $ref: common.yaml#
+
+    properties:
+      gpios:
+        maxItems: 1
+
+      retain-state-suspended:
+        description:
+          The suspend state can be retained.Such as charge-led gpio.
+        type: boolean
+
+      retain-state-shutdown:
+        description:
+          Retain the state of the LED on shutdown. Useful in BMC systems, for
+          example when the BMC is rebooted while the host remains up.
+        type: boolean
+
+    required:
+      - gpios
+
+additionalProperties: false
+
+examples:
+  - |
+
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/leds/common.h>
+
+    leds {
+        compatible = "gpio-leds";
+        led-0 {
+            gpios = <&mcu_pio 0 GPIO_ACTIVE_LOW>;
+            linux,default-trigger = "disk-activity";
+            function = LED_FUNCTION_DISK;
+        };
+
+        led-1 {
+            gpios = <&mcu_pio 1 GPIO_ACTIVE_HIGH>;
+            /* Keep LED on if BIOS detected hardware fault */
+            default-state = "keep";
+            function = LED_FUNCTION_FAULT;
+        };
+    };
+
+    run-control {
+        compatible = "gpio-leds";
+        led-0 {
+            gpios = <&mpc8572 6 GPIO_ACTIVE_HIGH>;
+            color = <LED_COLOR_ID_RED>;
+            default-state = "off";
+        };
+        led-1 {
+            gpios = <&mpc8572 7 GPIO_ACTIVE_HIGH>;
+            color = <LED_COLOR_ID_GREEN>;
+            default-state = "on";
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
index 4c2d923f8758..501468aa4d38 100644
--- a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
@@ -18,6 +18,10 @@ Required properties:
 Optional properties:
 	- enable-gpios : gpio pin to enable/disable the device.
 	- vled-supply : LED supply
+	- ti,ovp-microvolt: Overvoltage protection in
+	    micro-volt, can be 17000000, 21000000, 25000000 or
+	    29000000. If ti,ovp-microvolt is not specified it
+	    defaults to 29000000.
 
 Required child properties:
 	- reg : 0 - Will enable all LED sync paths
@@ -31,6 +35,8 @@ Optional child properties:
 	- label : see Documentation/devicetree/bindings/leds/common.txt (deprecated)
 	- linux,default-trigger :
 	   see Documentation/devicetree/bindings/leds/common.txt
+	- led-max-microamp :
+	   see Documentation/devicetree/bindings/leds/common.txt
 
 Example:
 
@@ -44,12 +50,14 @@ led-controller@36 {
 
 	enable-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>;
 	vled-supply = <&vbatt>;
+	ti,ovp-microvolt = <29000000>;
 
 	led@0 {
 		reg = <0>;
 		function = LED_FUNCTION_BACKLIGHT;
 		color = <LED_COLOR_ID_WHITE>;
 		linux,default-trigger = "backlight";
+		led-max-microamp = <20000>;
 	};
 }
 
diff --git a/Documentation/devicetree/bindings/leds/rohm,bd71828-leds.yaml b/Documentation/devicetree/bindings/leds/rohm,bd71828-leds.yaml
new file mode 100644
index 000000000000..b50f4bcc98f1
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/rohm,bd71828-leds.yaml
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/rohm,bd71828-leds.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ROHM BD71828 Power Management Integrated Circuit LED driver
+
+maintainers:
+  - Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
+
+description: |
+  This module is part of the ROHM BD71828 MFD device. For more details
+  see Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml.
+
+  The LED controller is represented as a sub-node of the PMIC node on the device
+  tree.
+
+  The device has two LED outputs referred as GRNLED and AMBLED in data-sheet.
+
+select: false
+
+properties:
+  compatible:
+    const: rohm,bd71828-leds
+
+patternProperties:
+  "^led-[1-2]$":
+    type: object
+    description:
+      Properties for a single LED.
+    properties:
+      #allOf:
+        #- $ref: "common.yaml#"
+      rohm,led-compatible:
+        description: LED identification string
+        allOf:
+          - $ref: "/schemas/types.yaml#/definitions/string"
+          - enum:
+            - bd71828-ambled
+            - bd71828-grnled
+      function:
+        description:
+          Purpose of LED as defined in dt-bindings/leds/common.h
+        $ref: "/schemas/types.yaml#/definitions/string"
+      color:
+        description:
+          LED colour as defined in dt-bindings/leds/common.h
+        $ref: "/schemas/types.yaml#/definitions/uint32"
+
+required:
+  - compatible
diff --git a/Documentation/devicetree/bindings/leds/trigger-source.yaml b/Documentation/devicetree/bindings/leds/trigger-source.yaml
new file mode 100644
index 000000000000..0618003e40bd
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/trigger-source.yaml
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/leds/trigger-source.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Trigger source providers
+
+maintainers:
+  - Jacek Anaszewski <jacek.anaszewski@gmail.com>
+  - Pavel Machek <pavel@ucw.cz>
+
+description:
+  Each trigger source provider should be represented by a device tree node. It
+  may be e.g. a USB port or an Ethernet device.
+
+properties:
+  '#trigger-source-cells':
+    description:
+      Number of cells in a source trigger. Typically 0 for nodes of simple
+      trigger sources (e.g. a specific USB port).
+    enum: [ 0, 1 ]
+
+...
diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.txt b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.txt
index 0278482af65c..beec612dbe6a 100644
--- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.txt
+++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.txt
@@ -21,10 +21,11 @@ platforms.
 	Usage: required
 	Value type: <prop-encoded-array>
 	Definition: must specify the base address and size of the global block
+
 - clocks:
-	Usage: required if #clocks-cells property is present
-	Value type: <phandle>
-	Definition: phandle to the input PLL, which feeds the APCS mux/divider
+	Usage: required if #clock-names property is present
+	Value type: <phandle array>
+	Definition: phandles to the two parent clocks of the clock driver.
 
 - #mbox-cells:
 	Usage: required
@@ -36,6 +37,12 @@ platforms.
 	Value type: <u32>
 	Definition: as described in clock.txt, must be 0
 
+- clock-names:
+	Usage: required if the platform data based clock driver needs to
+	retrieve the parent clock names from device tree.
+	This will requires two mandatory clocks to be defined.
+	Value type: <string-array>
+	Definition: must be "pll" and "aux"
 
 = EXAMPLE
 The following example describes the APCS HMSS found in MSM8996 and part of the
@@ -68,3 +75,14 @@ Below is another example of the APCS binding on MSM8916 platforms:
 		clocks = <&a53pll>;
 		#clock-cells = <0>;
 	};
+
+Below is another example of the APCS binding on QCS404 platforms:
+
+	apcs_glb: mailbox@b011000 {
+		compatible = "qcom,qcs404-apcs-apps-global", "syscon";
+		reg = <0x0b011000 0x1000>;
+		#mbox-cells = <1>;
+		clocks = <&apcs_hfpll>, <&gcc GCC_GPLL0_AO_OUT_MAIN>;
+		clock-names = "pll", "aux";
+		#clock-cells = <0>;
+	};
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
index 0f6374ceaa69..9af873b43acd 100644
--- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
+++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
@@ -16,7 +16,15 @@ description: |-
 
 properties:
   compatible:
-    const: allwinner,sun7i-a20-csi0
+    oneOf:
+      - const: allwinner,sun4i-a10-csi1
+      - const: allwinner,sun7i-a20-csi0
+      - items:
+        - const: allwinner,sun7i-a20-csi1
+        - const: allwinner,sun4i-a10-csi1
+      - items:
+        - const: allwinner,sun8i-r40-csi0
+        - const: allwinner,sun7i-a20-csi0
 
   reg:
     maxItems: 1
@@ -25,12 +33,16 @@ properties:
     maxItems: 1
 
   clocks:
+    minItems: 2
+    maxItems: 3
     items:
       - description: The CSI interface clock
       - description: The CSI ISP clock
       - description: The CSI DRAM clock
 
   clock-names:
+    minItems: 2
+    maxItems: 3
     items:
       - const: bus
       - const: isp
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
new file mode 100644
index 000000000000..526593c8c614
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: GPL-2.0-only
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/allwinner,sun4i-a10-video-engine.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 Video Engine Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-video-engine
+      - allwinner,sun5i-a13-video-engine
+      - allwinner,sun7i-a20-video-engine
+      - allwinner,sun8i-a33-video-engine
+      - allwinner,sun8i-h3-video-engine
+      - allwinner,sun50i-a64-video-engine
+      - allwinner,sun50i-h5-video-engine
+      - allwinner,sun50i-h6-video-engine
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus Clock
+      - description: Module Clock
+      - description: RAM Clock
+
+  clock-names:
+    items:
+      - const: ahb
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  allwinner,sram:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description: Phandle to the device SRAM
+
+  memory-region:
+    description:
+      CMA pool to use for buffers allocation instead of the default
+      CMA pool.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - allwinner,sram
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/sun7i-a20-ccu.h>
+    #include <dt-bindings/reset/sun4i-a10-ccu.h>
+
+    video-codec@1c0e000 {
+        compatible = "allwinner,sun7i-a20-video-engine";
+        reg = <0x01c0e000 0x1000>;
+        interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_AHB_VE>, <&ccu CLK_VE>,
+                 <&ccu CLK_DRAM_VE>;
+        clock-names = "ahb", "mod", "ram";
+        resets = <&ccu RST_VE>;
+        allwinner,sram = <&ve_sram 1>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml
new file mode 100644
index 000000000000..1fd9b5532a21
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml
@@ -0,0 +1,115 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/allwinner,sun6i-a31-csi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 CMOS Sensor Interface (CSI) Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  compatible:
+    enum:
+      - allwinner,sun6i-a31-csi
+      - allwinner,sun8i-a83t-csi
+      - allwinner,sun8i-h3-csi
+      - allwinner,sun8i-v3s-csi
+      - allwinner,sun50i-a64-csi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Bus Clock
+      - description: Module Clock
+      - description: DRAM Clock
+
+  clock-names:
+    items:
+      - const: bus
+      - const: mod
+      - const: ram
+
+  resets:
+    maxItems: 1
+
+  # See ./video-interfaces.txt for details
+  port:
+    type: object
+
+    properties:
+      endpoint:
+        type: object
+
+        properties:
+          remote-endpoint: true
+
+          bus-width:
+            enum: [ 8, 10, 12, 16 ]
+
+          pclk-sample: true
+          hsync-active: true
+          vsync-active: true
+
+        required:
+          - bus-width
+          - remote-endpoint
+
+    required:
+      - endpoint
+
+    additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/sun8i-v3s-ccu.h>
+    #include <dt-bindings/reset/sun8i-v3s-ccu.h>
+
+    csi1: csi@1cb4000 {
+        compatible = "allwinner,sun8i-v3s-csi";
+        reg = <0x01cb4000 0x1000>;
+        interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&ccu CLK_BUS_CSI>,
+                 <&ccu CLK_CSI1_SCLK>,
+                 <&ccu CLK_DRAM_CSI>;
+        clock-names = "bus",
+                      "mod",
+                      "ram";
+        resets = <&ccu RST_BUS_CSI>;
+
+        port {
+            /* Parallel bus endpoint */
+            csi1_ep: endpoint {
+                remote-endpoint = <&adv7611_ep>;
+                bus-width = <16>;
+
+                /*
+                 * If hsync-active/vsync-active are missing,
+                 * embedded BT.656 sync is used.
+                 */
+                 hsync-active = <0>; /* Active low */
+                 vsync-active = <0>; /* Active low */
+                 pclk-sample = <1>;  /* Rising */
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml b/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml
new file mode 100644
index 000000000000..335717e15970
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/amlogic,gx-vdec.yaml
@@ -0,0 +1,141 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright 2019 BayLibre, SAS
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/media/amlogic,gx-vdec.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Amlogic Video Decoder
+
+maintainers:
+  - Neil Armstrong <narmstrong@baylibre.com>
+  - Maxime Jourdan <mjourdan@baylibre.com>
+
+description: |
+  The video decoding IP lies within the DOS memory region,
+  except for the hardware bitstream parser that makes use of an undocumented
+  region.
+
+  It makes use of the following blocks:
+  - ESPARSER is a bitstream parser that outputs to a VIFIFO. Further VDEC blocks
+    then feed from this VIFIFO.
+  - VDEC_1 can decode MPEG-1, MPEG-2, MPEG-4 part 2, MJPEG, H.263, H.264, VC-1.
+  - VDEC_HEVC can decode HEVC and VP9.
+
+  Both VDEC_1 and VDEC_HEVC share the "vdec" IRQ and as such cannot run
+  concurrently.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+        - enum:
+          - amlogic,gxbb-vdec # GXBB (S905)
+          - amlogic,gxl-vdec # GXL (S905X, S905D)
+          - amlogic,gxm-vdec # GXM (S912)
+        - const: amlogic,gx-vdec
+      - enum:
+        - amlogic,g12a-vdec # G12A (S905X2, S905D2)
+        - amlogic,sm1-vdec # SM1 (S905X3, S905D3)
+
+  interrupts:
+    minItems: 2
+
+  interrupt-names:
+    items:
+      - const: vdec
+      - const: esparser
+
+  reg:
+    minItems: 2
+
+  reg-names:
+    items:
+      - const: dos
+      - const: esparser
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    items:
+      - const: esparser
+
+  clocks:
+    minItems: 4
+    maxItems: 5
+
+  clock-names:
+    minItems: 4
+    maxItems: 5
+    items:
+      - const: dos_parser
+      - const: dos
+      - const: vdec_1
+      - const: vdec_hevc
+      - const: vdec_hevcf
+
+  amlogic,ao-sysctrl:
+    description: should point to the AOBUS sysctrl node
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/phandle
+
+  amlogic,canvas:
+    description: should point to a canvas provider node
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/phandle
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - amlogic,gx-vdec
+
+    then:
+      properties:
+        clock-names:
+          maxItems: 4
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - amlogic,g12a-vdec
+              - amlogic,sm1-vdec
+
+    then:
+      properties:
+        clock-names:
+          minItems: 5
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - interrupts
+  - interrupt-names
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - amlogic,ao-sysctrl
+  - amlogic,canvas
+
+examples:
+  - |
+    vdec: video-decoder@c8820000 {
+          compatible = "amlogic,gxl-vdec", "amlogic,gx-vdec";
+          reg = <0xc8820000 0x10000>, <0xc110a580 0xe4>;
+          reg-names = "dos", "esparser";
+          interrupts = <44>, <32>;
+          interrupt-names = "vdec", "esparser";
+          clocks = <&clk_dos_parser> ,<&clk_dos>, <&clk_vdec_1>, <&clk_vdec_hevc>;
+          clock-names = "dos_parser", "dos", "vdec_1", "vdec_hevc";
+          resets = <&reset_parser>;
+          reset-names = "esparser";
+          amlogic,ao-sysctrl = <&sysctrl_AO>;
+          amlogic,canvas = <&canvas>;
+    };
diff --git a/Documentation/devicetree/bindings/media/amlogic,vdec.txt b/Documentation/devicetree/bindings/media/amlogic,vdec.txt
deleted file mode 100644
index 9b6aace86ca7..000000000000
--- a/Documentation/devicetree/bindings/media/amlogic,vdec.txt
+++ /dev/null
@@ -1,72 +0,0 @@
-Amlogic Video Decoder
-================================
-
-The video decoding IP lies within the DOS memory region,
-except for the hardware bitstream parser that makes use of an undocumented
-region.
-
-It makes use of the following blocks:
-
-- ESPARSER is a bitstream parser that outputs to a VIFIFO. Further VDEC blocks
-then feed from this VIFIFO.
-- VDEC_1 can decode MPEG-1, MPEG-2, MPEG-4 part 2, MJPEG, H.263, H.264, VC-1.
-- VDEC_HEVC can decode HEVC and VP9.
-
-Both VDEC_1 and VDEC_HEVC share the "vdec" IRQ and as such cannot run
-concurrently.
-
-Device Tree Bindings:
----------------------
-
-VDEC: Video Decoder
---------------------------
-
-Required properties:
-- compatible: value should be different for each SoC family as :
-	- GXBB (S905) : "amlogic,gxbb-vdec"
-	- GXL (S905X, S905D) : "amlogic,gxl-vdec"
-	- GXM (S912) : "amlogic,gxm-vdec"
-	followed by the common "amlogic,gx-vdec"
-- reg: base address and size of he following memory-mapped regions :
-	- dos
-	- esparser
-- reg-names: should contain the names of the previous memory regions
-- interrupts: should contain the following IRQs:
-	- vdec
-	- esparser
-- interrupt-names: should contain the names of the previous interrupts
-- amlogic,ao-sysctrl: should point to the AOBUS sysctrl node
-- amlogic,canvas: should point to a canvas provider node
-- clocks: should contain the following clocks :
-	- dos_parser
-	- dos
-	- vdec_1
-	- vdec_hevc
-- clock-names: should contain the names of the previous clocks
-- resets: should contain the parser reset
-- reset-names: should be "esparser"
-
-Example:
-
-vdec: video-codec@c8820000 {
-	compatible = "amlogic,gxbb-vdec", "amlogic,gx-vdec";
-	reg = <0x0 0xc8820000 0x0 0x10000>,
-	      <0x0 0xc110a580 0x0 0xe4>;
-	reg-names = "dos", "esparser";
-
-	interrupts = <GIC_SPI 44 IRQ_TYPE_EDGE_RISING>,
-		     <GIC_SPI 32 IRQ_TYPE_EDGE_RISING>;
-	interrupt-names = "vdec", "esparser";
-
-	amlogic,ao-sysctrl = <&sysctrl_AO>;
-	amlogic,canvas = <&canvas>;
-
-	clocks = <&clkc CLKID_DOS_PARSER>,
-		 <&clkc CLKID_DOS>,
-		 <&clkc CLKID_VDEC_1>,
-		 <&clkc CLKID_VDEC_HEVC>;
-	clock-names = "dos_parser", "dos", "vdec_1", "vdec_hevc";
-
-	resets = <&reset RESET_PARSER>;
-	reset-names = "esparser";
-};
diff --git a/Documentation/devicetree/bindings/media/cedrus.txt b/Documentation/devicetree/bindings/media/cedrus.txt
deleted file mode 100644
index 20c82fb0c343..000000000000
--- a/Documentation/devicetree/bindings/media/cedrus.txt
+++ /dev/null
@@ -1,57 +0,0 @@
-Device-tree bindings for the VPU found in Allwinner SoCs, referred to as the
-Video Engine (VE) in Allwinner literature.
-
-The VPU can only access the first 256 MiB of DRAM, that are DMA-mapped starting
-from the DRAM base. This requires specific memory allocation and handling.
-
-Required properties:
-- compatible		: must be one of the following compatibles:
-			- "allwinner,sun4i-a10-video-engine"
-			- "allwinner,sun5i-a13-video-engine"
-			- "allwinner,sun7i-a20-video-engine"
-			- "allwinner,sun8i-a33-video-engine"
-			- "allwinner,sun8i-h3-video-engine"
-			- "allwinner,sun50i-a64-video-engine"
-			- "allwinner,sun50i-h5-video-engine"
-			- "allwinner,sun50i-h6-video-engine"
-- reg			: register base and length of VE;
-- clocks		: list of clock specifiers, corresponding to entries in
-			  the clock-names property;
-- clock-names		: should contain "ahb", "mod" and "ram" entries;
-- resets		: phandle for reset;
-- interrupts		: VE interrupt number;
-- allwinner,sram	: SRAM region to use with the VE.
-
-Optional properties:
-- memory-region		: CMA pool to use for buffers allocation instead of the
-			  default CMA pool.
-
-Example:
-
-reserved-memory {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	ranges;
-
-	/* Address must be kept in the lower 256 MiBs of DRAM for VE. */
-	cma_pool: default-pool {
-		compatible = "shared-dma-pool";
-		size = <0x6000000>;
-		alloc-ranges = <0x4a000000 0x6000000>;
-		reusable;
-		linux,cma-default;
-	};
-};
-
-video-codec@1c0e000 {
-	compatible = "allwinner,sun7i-a20-video-engine";
-	reg = <0x01c0e000 0x1000>;
-
-	clocks = <&ccu CLK_AHB_VE>, <&ccu CLK_VE>,
-		 <&ccu CLK_DRAM_VE>;
-	clock-names = "ahb", "mod", "ram";
-
-	resets = <&ccu RST_VE>;
-	interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
-	allwinner,sram = <&ve_sram 1>;
-};
diff --git a/Documentation/devicetree/bindings/media/exynos-jpeg-codec.txt b/Documentation/devicetree/bindings/media/exynos-jpeg-codec.txt
index 38941db23dd2..ce9a22689e53 100644
--- a/Documentation/devicetree/bindings/media/exynos-jpeg-codec.txt
+++ b/Documentation/devicetree/bindings/media/exynos-jpeg-codec.txt
@@ -1,4 +1,4 @@
-Samsung S5P/EXYNOS SoC series JPEG codec
+Samsung S5P/Exynos SoC series JPEG codec
 
 Required properties:
 
diff --git a/Documentation/devicetree/bindings/media/exynos5-gsc.txt b/Documentation/devicetree/bindings/media/exynos5-gsc.txt
index bc963a6d305a..1872688fa408 100644
--- a/Documentation/devicetree/bindings/media/exynos5-gsc.txt
+++ b/Documentation/devicetree/bindings/media/exynos5-gsc.txt
@@ -1,6 +1,6 @@
 * Samsung Exynos5 G-Scaler device
 
-G-Scaler is used for scaling and color space conversion on EXYNOS5 SoCs.
+G-Scaler is used for scaling and color space conversion on Exynos5 SoCs.
 
 Required properties:
 - compatible: should be one of
diff --git a/Documentation/devicetree/bindings/media/hix5hd2-ir.txt b/Documentation/devicetree/bindings/media/hix5hd2-ir.txt
index 13ebc0fac9ea..ca4cf774662e 100644
--- a/Documentation/devicetree/bindings/media/hix5hd2-ir.txt
+++ b/Documentation/devicetree/bindings/media/hix5hd2-ir.txt
@@ -1,7 +1,8 @@
 Device-Tree bindings for hix5hd2 ir IP
 
 Required properties:
-	- compatible: Should contain "hisilicon,hix5hd2-ir".
+	- compatible: Should contain "hisilicon,hix5hd2-ir", or:
+		- "hisilicon,hi3796cv300-ir" for Hi3796CV300 IR device.
 	- reg: Base physical address of the controller and length of memory
 	  mapped region.
 	- interrupts: interrupt-specifier for the sole interrupt generated by
diff --git a/Documentation/devicetree/bindings/media/renesas,ceu.txt b/Documentation/devicetree/bindings/media/renesas,ceu.txt
deleted file mode 100644
index 3e2a2652eb19..000000000000
--- a/Documentation/devicetree/bindings/media/renesas,ceu.txt
+++ /dev/null
@@ -1,86 +0,0 @@
-Renesas Capture Engine Unit (CEU)
-----------------------------------------------
-
-The Capture Engine Unit is the image capture interface found in the Renesas
-SH Mobile, R-Mobile and RZ SoCs.
-
-The interface supports a single parallel input with data bus width of 8 or 16
-bits.
-
-Required properties:
-- compatible: Shall be one of the following values:
-	"renesas,r7s72100-ceu" for CEU units found in RZ/A1H and RZ/A1M SoCs
-	"renesas,r8a7740-ceu" for CEU units found in R-Mobile A1 R8A7740 SoCs
-- reg: Registers address base and size.
-- interrupts: The interrupt specifier.
-
-The CEU supports a single parallel input and should contain a single 'port'
-subnode with a single 'endpoint'. Connection to input devices are modeled
-according to the video interfaces OF bindings specified in:
-[1] Documentation/devicetree/bindings/media/video-interfaces.txt
-
-Optional endpoint properties applicable to parallel input bus described in
-the above mentioned "video-interfaces.txt" file are supported.
-
-- hsync-active: See [1] for description. If property is not present,
-  default is active high.
-- vsync-active: See [1] for description. If property is not present,
-  default is active high.
-- bus-width: See [1] for description. Accepted values are '8' and '16'.
-  If property is not present, default is '8'.
-- field-even-active: See [1] for description. If property is not present,
-  an even field is identified by a logic 0 (active-low signal).
-
-Example:
-
-The example describes the connection between the Capture Engine Unit and an
-OV7670 image sensor connected to i2c1 interface.
-
-ceu: ceu@e8210000 {
-	reg = <0xe8210000 0x209c>;
-	compatible = "renesas,r7s72100-ceu";
-	interrupts = <GIC_SPI 332 IRQ_TYPE_LEVEL_HIGH>;
-
-	pinctrl-names = "default";
-	pinctrl-0 = <&vio_pins>;
-
-	status = "okay";
-
-	port {
-		ceu_in: endpoint {
-			remote-endpoint = <&ov7670_out>;
-
-			hsync-active = <1>;
-			vsync-active = <0>;
-		};
-	};
-};
-
-i2c1: i2c@fcfee400 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins>;
-
-	status = "okay";
-
-	clock-frequency = <100000>;
-
-	ov7670: camera@21 {
-		compatible = "ovti,ov7670";
-		reg = <0x21>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&vio_pins>;
-
-		reset-gpios = <&port3 11 GPIO_ACTIVE_LOW>;
-		powerdown-gpios = <&port3 12 GPIO_ACTIVE_HIGH>;
-
-		port {
-			ov7670_out: endpoint {
-				remote-endpoint = <&ceu_in>;
-
-				hsync-active = <1>;
-				vsync-active = <0>;
-			};
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/media/renesas,ceu.yaml b/Documentation/devicetree/bindings/media/renesas,ceu.yaml
new file mode 100644
index 000000000000..8e9251a0f9ef
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/renesas,ceu.yaml
@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/renesas,ceu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas Capture Engine Unit (CEU) Bindings
+
+maintainers:
+  - Jacopo Mondi <jacopo+renesas@jmondi.org>
+  - linux-renesas-soc@vger.kernel.org
+
+description: |+
+  The Capture Engine Unit is the image capture interface found in the Renesas SH
+  Mobile, R-Mobile and RZ SoCs. The interface supports a single parallel input
+  with data bus width of 8 or 16 bits.
+
+properties:
+  compatible:
+    enum:
+      - renesas,r7s72100-ceu
+      - renesas,r8a7740-ceu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  port:
+    type: object
+    additionalProperties: false
+
+    properties:
+       endpoint:
+         type: object
+         additionalProperties: false
+
+         # Properties described in
+         # Documentation/devicetree/bindings/media/video-interfaces.txt
+         properties:
+           remote-endpoint: true
+           hsync-active: true
+           vsync-active: true
+           field-even-active: false
+           bus-width:
+             enum: [8, 16]
+             default: 8
+
+         required:
+           - remote-endpoint
+
+    required:
+      - endpoint
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - port
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    ceu: ceu@e8210000 {
+        reg = <0xe8210000 0x209c>;
+        compatible = "renesas,r7s72100-ceu";
+        interrupts = <GIC_SPI 332 IRQ_TYPE_LEVEL_HIGH>;
+
+        port {
+            ceu_in: endpoint {
+                remote-endpoint = <&ov7670_out>;
+                hsync-active = <1>;
+                vsync-active = <0>;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/media/renesas,csi2.txt b/Documentation/devicetree/bindings/media/renesas,csi2.txt
deleted file mode 100644
index 2da6f60b2b56..000000000000
--- a/Documentation/devicetree/bindings/media/renesas,csi2.txt
+++ /dev/null
@@ -1,107 +0,0 @@
-Renesas R-Car MIPI CSI-2
-------------------------
-
-The R-Car CSI-2 receiver device provides MIPI CSI-2 capabilities for the
-Renesas R-Car and RZ/G2 family of devices. It is used in conjunction with the
-R-Car VIN module, which provides the video capture capabilities.
-
-Mandatory properties
---------------------
- - compatible: Must be one or more of the following
-   - "renesas,r8a774a1-csi2" for the R8A774A1 device.
-   - "renesas,r8a774b1-csi2" for the R8A774B1 device.
-   - "renesas,r8a774c0-csi2" for the R8A774C0 device.
-   - "renesas,r8a7795-csi2" for the R8A7795 device.
-   - "renesas,r8a7796-csi2" for the R8A7796 device.
-   - "renesas,r8a77965-csi2" for the R8A77965 device.
-   - "renesas,r8a77970-csi2" for the R8A77970 device.
-   - "renesas,r8a77980-csi2" for the R8A77980 device.
-   - "renesas,r8a77990-csi2" for the R8A77990 device.
-
- - reg: the register base and size for the device registers
- - interrupts: the interrupt for the device
- - clocks: A phandle + clock specifier for the module clock
- - resets: A phandle + reset specifier for the module reset
-
-The device node shall contain two 'port' child nodes according to the
-bindings defined in Documentation/devicetree/bindings/media/
-video-interfaces.txt. port@0 shall connect to the CSI-2 source. port@1
-shall connect to all the R-Car VIN modules that have a hardware
-connection to the CSI-2 receiver.
-
-- port@0- Video source (mandatory)
-	- endpoint@0 - sub-node describing the endpoint that is the video source
-
-- port@1 - VIN instances (optional)
-	- One endpoint sub-node for every R-Car VIN instance which is connected
-	  to the R-Car CSI-2 receiver.
-
-Example:
-
-	csi20: csi2@fea80000 {
-		compatible = "renesas,r8a7796-csi2";
-		reg = <0 0xfea80000 0 0x10000>;
-		interrupts = <0 184 IRQ_TYPE_LEVEL_HIGH>;
-		clocks = <&cpg CPG_MOD 714>;
-		power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
-		resets = <&cpg 714>;
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			port@0 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				reg = <0>;
-
-				csi20_in: endpoint@0 {
-					reg = <0>;
-					clock-lanes = <0>;
-					data-lanes = <1>;
-					remote-endpoint = <&adv7482_txb>;
-				};
-			};
-
-			port@1 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				reg = <1>;
-
-				csi20vin0: endpoint@0 {
-					reg = <0>;
-					remote-endpoint = <&vin0csi20>;
-				};
-				csi20vin1: endpoint@1 {
-					reg = <1>;
-					remote-endpoint = <&vin1csi20>;
-				};
-				csi20vin2: endpoint@2 {
-					reg = <2>;
-					remote-endpoint = <&vin2csi20>;
-				};
-				csi20vin3: endpoint@3 {
-					reg = <3>;
-					remote-endpoint = <&vin3csi20>;
-				};
-				csi20vin4: endpoint@4 {
-					reg = <4>;
-					remote-endpoint = <&vin4csi20>;
-				};
-				csi20vin5: endpoint@5 {
-					reg = <5>;
-					remote-endpoint = <&vin5csi20>;
-				};
-				csi20vin6: endpoint@6 {
-					reg = <6>;
-					remote-endpoint = <&vin6csi20>;
-				};
-				csi20vin7: endpoint@7 {
-					reg = <7>;
-					remote-endpoint = <&vin7csi20>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/media/renesas,csi2.yaml b/Documentation/devicetree/bindings/media/renesas,csi2.yaml
new file mode 100644
index 000000000000..408442a0c389
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/renesas,csi2.yaml
@@ -0,0 +1,198 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2020 Renesas Electronics Corp.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/renesas,csi2.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas R-Car MIPI CSI-2 receiver
+
+maintainers:
+  - Niklas Söderlund <niklas.soderlund@ragnatech.se>
+
+description:
+  The R-Car CSI-2 receiver device provides MIPI CSI-2 capabilities for the
+  Renesas R-Car and RZ/G2 family of devices. It is used in conjunction with the
+  R-Car VIN module, which provides the video capture capabilities.
+
+properties:
+  compatible:
+    items:
+      - enum:
+        - renesas,r8a774a1-csi2 # RZ/G2M
+        - renesas,r8a774b1-csi2 # RZ/G2N
+        - renesas,r8a774c0-csi2 # RZ/G2E
+        - renesas,r8a7795-csi2  # R-Car H3
+        - renesas,r8a7796-csi2  # R-Car M3-W
+        - renesas,r8a77965-csi2 # R-Car M3-N
+        - renesas,r8a77970-csi2 # R-Car V3M
+        - renesas,r8a77980-csi2 # R-Car V3H
+        - renesas,r8a77990-csi2 # R-Car E3
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  ports:
+    type: object
+    description:
+      A node containing input and output port nodes with endpoint definitions
+      as documented in
+      Documentation/devicetree/bindings/media/video-interfaces.txt
+
+    properties:
+      port@0:
+        type: object
+        description:
+          Input port node, single endpoint describing the CSI-2 transmitter.
+
+        properties:
+          reg:
+            const: 0
+
+          endpoint:
+            type: object
+
+            properties:
+              clock-lanes:
+                maxItems: 1
+
+              data-lanes:
+                maxItems: 1
+
+              remote-endpoint: true
+
+            required:
+              - clock-lanes
+              - data-lanes
+              - remote-endpoint
+
+            additionalProperties: false
+
+        additionalProperties: false
+
+      port@1:
+        type: object
+        description:
+          Output port node, multiple endpoints describing all the R-Car VIN
+          modules connected the CSI-2 receiver.
+
+        properties:
+          '#address-cells':
+            const: 1
+
+          '#size-cells':
+            const: 0
+
+          reg:
+            const: 1
+
+        patternProperties:
+          "^endpoint@[0-9a-f]$":
+            type: object
+
+            properties:
+              reg:
+                maxItems: 1
+
+              remote-endpoint: true
+
+            required:
+              - reg
+              - remote-endpoint
+
+            additionalProperties: false
+
+        additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - power-domains
+  - resets
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/r8a7796-cpg-mssr.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/r8a7796-sysc.h>
+
+    csi20: csi2@fea80000 {
+            compatible = "renesas,r8a7796-csi2";
+            reg = <0 0xfea80000 0 0x10000>;
+            interrupts = <0 184 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cpg CPG_MOD 714>;
+            power-domains = <&sysc R8A7796_PD_ALWAYS_ON>;
+            resets = <&cpg 714>;
+
+            ports {
+                    #address-cells = <1>;
+                    #size-cells = <0>;
+
+                    port@0 {
+                            reg = <0>;
+
+                            csi20_in: endpoint {
+                                    clock-lanes = <0>;
+                                    data-lanes = <1>;
+                                    remote-endpoint = <&adv7482_txb>;
+                            };
+                    };
+
+                    port@1 {
+                            #address-cells = <1>;
+                            #size-cells = <0>;
+
+                            reg = <1>;
+
+                            csi20vin0: endpoint@0 {
+                                    reg = <0>;
+                                    remote-endpoint = <&vin0csi20>;
+                            };
+                            csi20vin1: endpoint@1 {
+                                    reg = <1>;
+                                    remote-endpoint = <&vin1csi20>;
+                            };
+                            csi20vin2: endpoint@2 {
+                                    reg = <2>;
+                                    remote-endpoint = <&vin2csi20>;
+                            };
+                            csi20vin3: endpoint@3 {
+                                    reg = <3>;
+                                    remote-endpoint = <&vin3csi20>;
+                            };
+                            csi20vin4: endpoint@4 {
+                                    reg = <4>;
+                                    remote-endpoint = <&vin4csi20>;
+                            };
+                            csi20vin5: endpoint@5 {
+                                    reg = <5>;
+                                    remote-endpoint = <&vin5csi20>;
+                            };
+                            csi20vin6: endpoint@6 {
+                                    reg = <6>;
+                                    remote-endpoint = <&vin6csi20>;
+                            };
+                            csi20vin7: endpoint@7 {
+                                    reg = <7>;
+                                    remote-endpoint = <&vin7csi20>;
+                            };
+                    };
+            };
+    };
diff --git a/Documentation/devicetree/bindings/media/renesas,vin.txt b/Documentation/devicetree/bindings/media/renesas,vin.txt
index e30b0d4eefdd..5eefd62ac5c5 100644
--- a/Documentation/devicetree/bindings/media/renesas,vin.txt
+++ b/Documentation/devicetree/bindings/media/renesas,vin.txt
@@ -13,6 +13,7 @@ on Gen3 and RZ/G2 platforms to a CSI-2 receiver.
    - "renesas,vin-r8a7743" for the R8A7743 device
    - "renesas,vin-r8a7744" for the R8A7744 device
    - "renesas,vin-r8a7745" for the R8A7745 device
+   - "renesas,vin-r8a77470" for the R8A77470 device
    - "renesas,vin-r8a774a1" for the R8A774A1 device
    - "renesas,vin-r8a774b1" for the R8A774B1 device
    - "renesas,vin-r8a774c0" for the R8A774C0 device
@@ -41,9 +42,6 @@ on Gen3 and RZ/G2 platforms to a CSI-2 receiver.
  - interrupts: the interrupt for the device
  - clocks: Reference to the parent clock
 
-Additionally, an alias named vinX will need to be created to specify
-which video input device this is.
-
 The per-board settings for Gen2 and RZ/G1 platforms:
 
 - port - sub-node describing a single endpoint connected to the VIN
diff --git a/Documentation/devicetree/bindings/media/samsung-fimc.txt b/Documentation/devicetree/bindings/media/samsung-fimc.txt
index 48c599dacbdf..f91b9dc80eb3 100644
--- a/Documentation/devicetree/bindings/media/samsung-fimc.txt
+++ b/Documentation/devicetree/bindings/media/samsung-fimc.txt
@@ -1,4 +1,4 @@
-Samsung S5P/EXYNOS SoC Camera Subsystem (FIMC)
+Samsung S5P/Exynos SoC Camera Subsystem (FIMC)
 ----------------------------------------------
 
 The S5P/Exynos SoC Camera subsystem comprises of multiple sub-devices
diff --git a/Documentation/devicetree/bindings/media/samsung-mipi-csis.txt b/Documentation/devicetree/bindings/media/samsung-mipi-csis.txt
index be45f0b1a449..a4149c9434ea 100644
--- a/Documentation/devicetree/bindings/media/samsung-mipi-csis.txt
+++ b/Documentation/devicetree/bindings/media/samsung-mipi-csis.txt
@@ -1,4 +1,4 @@
-Samsung S5P/EXYNOS SoC series MIPI CSI-2 receiver (MIPI CSIS)
+Samsung S5P/Exynos SoC series MIPI CSI-2 receiver (MIPI CSIS)
 -------------------------------------------------------------
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/media/sun6i-csi.txt b/Documentation/devicetree/bindings/media/sun6i-csi.txt
deleted file mode 100644
index a2e3e56f0257..000000000000
--- a/Documentation/devicetree/bindings/media/sun6i-csi.txt
+++ /dev/null
@@ -1,61 +0,0 @@
-Allwinner V3s Camera Sensor Interface
--------------------------------------
-
-Allwinner V3s SoC features a CSI module(CSI1) with parallel interface.
-
-Required properties:
-  - compatible: value must be one of:
-    * "allwinner,sun6i-a31-csi"
-    * "allwinner,sun8i-a83t-csi"
-    * "allwinner,sun8i-h3-csi"
-    * "allwinner,sun8i-v3s-csi"
-    * "allwinner,sun50i-a64-csi"
-  - reg: base address and size of the memory-mapped region.
-  - interrupts: interrupt associated to this IP
-  - clocks: phandles to the clocks feeding the CSI
-    * bus: the CSI interface clock
-    * mod: the CSI module clock
-    * ram: the CSI DRAM clock
-  - clock-names: the clock names mentioned above
-  - resets: phandles to the reset line driving the CSI
-
-The CSI node should contain one 'port' child node with one child 'endpoint'
-node, according to the bindings defined in
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-
-Endpoint node properties for CSI
----------------------------------
-See the video-interfaces.txt for a detailed description of these properties.
-- remote-endpoint	: (required) a phandle to the bus receiver's endpoint
-			   node
-- bus-width:		: (required) must be 8, 10, 12 or 16
-- pclk-sample		: (optional) (default: sample on falling edge)
-- hsync-active		: (required; parallel-only)
-- vsync-active		: (required; parallel-only)
-
-Example:
-
-csi1: csi@1cb4000 {
-	compatible = "allwinner,sun8i-v3s-csi";
-	reg = <0x01cb4000 0x1000>;
-	interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>;
-	clocks = <&ccu CLK_BUS_CSI>,
-		 <&ccu CLK_CSI1_SCLK>,
-		 <&ccu CLK_DRAM_CSI>;
-	clock-names = "bus", "mod", "ram";
-	resets = <&ccu RST_BUS_CSI>;
-
-	port {
-		/* Parallel bus endpoint */
-		csi1_ep: endpoint {
-			remote-endpoint = <&adv7611_ep>;
-			bus-width = <16>;
-
-			/* If hsync-active/vsync-active are missing,
-			   embedded BT.656 sync is used */
-			hsync-active = <0>; /* Active low */
-			vsync-active = <0>; /* Active low */
-			pclk-sample = <1>;  /* Rising */
-		};
-	};
-};
diff --git a/Documentation/devicetree/bindings/media/ti,cal.yaml b/Documentation/devicetree/bindings/media/ti,cal.yaml
new file mode 100644
index 000000000000..1ea784179536
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/ti,cal.yaml
@@ -0,0 +1,202 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/ti,cal.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments DRA72x CAMERA ADAPTATION LAYER (CAL) Device Tree Bindings
+
+maintainers:
+  - Benoit Parrot <bparrot@ti.com>
+
+description: |-
+  The Camera Adaptation Layer (CAL) is a key component for image capture
+  applications. The capture module provides the system interface and the
+  processing capability to connect CSI2 image-sensor modules to the
+  DRA72x device.
+
+  CAL supports 2 camera port nodes on MIPI bus. Each CSI2 camera port nodes
+  should contain a 'port' child node with child 'endpoint' node. Please
+  refer to the bindings defined in
+  Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+properties:
+  compatible:
+    enum:
+      # for DRA72 controllers
+      - ti,dra72-cal
+      # for DRA72 controllers pre ES2.0
+      - ti,dra72-pre-es2-cal
+      # for DRA76 controllers
+      - ti,dra76-cal
+      # for AM654 controllers
+      - ti,am654-cal
+
+  reg:
+    minItems: 2
+    items:
+      - description: The CAL main register region
+      - description: The RX Core0 (DPHY0) register region
+      - description: The RX Core1 (DPHY1) register region
+
+  reg-names:
+    minItems: 2
+    items:
+      - const: cal_top
+      - const: cal_rx_core0
+      - const: cal_rx_core1
+
+  interrupts:
+    maxItems: 1
+
+  ti,camerrx-control:
+    $ref: "/schemas/types.yaml#/definitions/phandle-array"
+    description:
+      phandle to the device control module and offset to the
+      control_camerarx_core register
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: fck
+
+  power-domains:
+    description:
+      List of phandle and PM domain specifier as documented in
+      Documentation/devicetree/bindings/power/power_domain.txt
+    maxItems: 1
+
+  # See ./video-interfaces.txt for details
+  ports:
+    type: object
+    additionalProperties: false
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        additionalProperties: false
+
+        properties:
+          reg:
+            const: 0
+            description: CSI2 Port #0
+
+        patternProperties:
+          endpoint:
+            type: object
+            additionalProperties: false
+
+            properties:
+              clock-lanes:
+                maxItems: 1
+
+              data-lanes:
+                minItems: 1
+                maxItems: 4
+
+              remote-endpoint: true
+
+        required:
+          - reg
+
+      port@1:
+        type: object
+        additionalProperties: false
+
+        properties:
+          reg:
+            const: 1
+            description: CSI2 Port #1
+
+        patternProperties:
+          endpoint:
+            type: object
+            additionalProperties: false
+
+            properties:
+              clock-lanes:
+                maxItems: 1
+
+              data-lanes:
+                minItems: 1
+                maxItems: 4
+
+              remote-endpoint: true
+
+        required:
+          - reg
+
+    required:
+      - "#address-cells"
+      - "#size-cells"
+      - port@0
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - interrupts
+  - ti,camerrx-control
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    cal: cal@4845b000 {
+        compatible = "ti,dra72-cal";
+        reg = <0x4845B000 0x400>,
+              <0x4845B800 0x40>,
+              <0x4845B900 0x40>;
+        reg-names = "cal_top",
+                    "cal_rx_core0",
+                    "cal_rx_core1";
+        interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
+        ti,camerrx-control = <&scm_conf 0xE94>;
+
+        ports {
+              #address-cells = <1>;
+              #size-cells = <0>;
+
+              csi2_0: port@0 {
+                    reg = <0>;
+                    csi2_phy0: endpoint {
+                           remote-endpoint = <&csi2_cam0>;
+                           clock-lanes = <0>;
+                           data-lanes = <1 2>;
+                    };
+              };
+        };
+    };
+
+    i2c5: i2c@4807c000 {
+        clock-frequency = <400000>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        camera-sensor@3c {
+               compatible = "ovti,ov5640";
+               reg = <0x3c>;
+
+               clocks = <&clk_ov5640_fixed>;
+               clock-names = "xclk";
+
+               port {
+                    csi2_cam0: endpoint {
+                            remote-endpoint = <&csi2_phy0>;
+                            clock-lanes = <0>;
+                            data-lanes = <1 2>;
+                    };
+               };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/media/ti-cal.txt b/Documentation/devicetree/bindings/media/ti-cal.txt
deleted file mode 100644
index ae9b52f37576..000000000000
--- a/Documentation/devicetree/bindings/media/ti-cal.txt
+++ /dev/null
@@ -1,72 +0,0 @@
-Texas Instruments DRA72x CAMERA ADAPTATION LAYER (CAL)
-------------------------------------------------------
-
-The Camera Adaptation Layer (CAL) is a key component for image capture
-applications. The capture module provides the system interface and the
-processing capability to connect CSI2 image-sensor modules to the
-DRA72x device.
-
-Required properties:
-- compatible: must be "ti,dra72-cal"
-- reg:	CAL Top level, Receiver Core #0, Receiver Core #1 and Camera RX
-	control address space
-- reg-names: cal_top, cal_rx_core0, cal_rx_core1, and camerrx_control
-	     registers
-- interrupts: should contain IRQ line for the CAL;
-
-CAL supports 2 camera port nodes on MIPI bus. Each CSI2 camera port nodes
-should contain a 'port' child node with child 'endpoint' node. Please
-refer to the bindings defined in
-Documentation/devicetree/bindings/media/video-interfaces.txt.
-
-Example:
-	cal: cal@4845b000 {
-		compatible = "ti,dra72-cal";
-		ti,hwmods = "cal";
-		reg = <0x4845B000 0x400>,
-		      <0x4845B800 0x40>,
-		      <0x4845B900 0x40>,
-		      <0x4A002e94 0x4>;
-		reg-names = "cal_top",
-			    "cal_rx_core0",
-			    "cal_rx_core1",
-			    "camerrx_control";
-		interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>;
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		ports {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			csi2_0: port@0 {
-				reg = <0>;
-				endpoint {
-					slave-mode;
-					remote-endpoint = <&ar0330_1>;
-				};
-			};
-			csi2_1: port@1 {
-				reg = <1>;
-			};
-		};
-	};
-
-	i2c5: i2c@4807c000 {
-		ar0330@10 {
-			compatible = "ti,ar0330";
-			reg = <0x10>;
-
-			port {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				ar0330_1: endpoint {
-					reg = <0>;
-					clock-lanes = <1>;
-					data-lanes = <0 2 3 4>;
-					remote-endpoint = <&csi2_0>;
-				};
-			};
-		};
-	};
diff --git a/Documentation/devicetree/bindings/mfd/ab8500.txt b/Documentation/devicetree/bindings/mfd/ab8500.txt
index b6bc30d7777e..5c6eabeed341 100644
--- a/Documentation/devicetree/bindings/mfd/ab8500.txt
+++ b/Documentation/devicetree/bindings/mfd/ab8500.txt
@@ -1,7 +1,7 @@
 * AB8500 Multi-Functional Device (MFD)
 
 Required parent device properties:
-- compatible             : contains "stericsson,ab8500";
+- compatible             : contains "stericsson,ab8500" or "stericsson,ab8505";
 - interrupts             : contains the IRQ line for the AB8500
 - interrupt-controller   : describes the AB8500 as an Interrupt Controller (has its own domain)
 - #interrupt-cells       : should be 2, for 2-cell format
@@ -49,11 +49,13 @@ ab8500-charger		 :			: vddadc       : Charger interface
 			 : CH_WD_EXP		:	       : Charger watchdog detected
 ab8500-gpadc             : HW_CONV_END          : vddadc       : Analogue to Digital Converter
                            SW_CONV_END          :              :
-ab8500-gpio              :                      :              : GPIO Controller
+ab8500-gpio              :                      :              : GPIO Controller (AB8500)
+ab8505-gpio              :                      :              : GPIO Controller (AB8505)
 ab8500-ponkey            : ONKEY_DBF            :              : Power-on Key
                            ONKEY_DBR            :              :
 ab8500-pwm               :                      :              : Pulse Width Modulator
-ab8500-regulator         :                      :              : Regulators
+ab8500-regulator         :                      :              : Regulators (AB8500)
+ab8505-regulator         :                      :              : Regulators (AB8505)
 ab8500-rtc               : 60S                  :              : Real Time Clock
                          : ALARM                :              :
 ab8500-sysctrl           :                      :              : System Control
diff --git a/Documentation/devicetree/bindings/mfd/allwinner,sun6i-a31-prcm.yaml b/Documentation/devicetree/bindings/mfd/allwinner,sun6i-a31-prcm.yaml
new file mode 100644
index 000000000000..d131759ccaf3
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/allwinner,sun6i-a31-prcm.yaml
@@ -0,0 +1,219 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/allwinner,sun6i-a31-prcm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 PRCM Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  compatible:
+    const: allwinner,sun6i-a31-prcm
+
+  reg:
+    maxItems: 1
+
+patternProperties:
+  "^.*_(clk|rst)$":
+    type: object
+
+    properties:
+      compatible:
+        enum:
+          - allwinner,sun4i-a10-mod0-clk
+          - allwinner,sun6i-a31-apb0-clk
+          - allwinner,sun6i-a31-apb0-gates-clk
+          - allwinner,sun6i-a31-ar100-clk
+          - allwinner,sun6i-a31-clock-reset
+          - fixed-factor-clock
+
+    allOf:
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun6i-a31-apb0-clk
+
+        then:
+          properties:
+            "#clock-cells":
+              const: 0
+
+            # Already checked in the main schema
+            compatible: true
+
+            clocks:
+              maxItems: 1
+
+            clock-output-names:
+              maxItems: 1
+
+            phandle: true
+
+          required:
+            - "#clock-cells"
+            - compatible
+            - clocks
+            - clock-output-names
+
+          additionalProperties: false
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun6i-a31-apb0-gates-clk
+
+        then:
+          properties:
+            "#clock-cells":
+              const: 1
+              description: >
+                This additional argument passed to that clock is the
+                offset of the bit controlling this particular gate in
+                the register.
+
+            # Already checked in the main schema
+            compatible: true
+
+            clocks:
+              maxItems: 1
+
+            clock-output-names:
+              minItems: 1
+              maxItems: 32
+
+            phandle: true
+
+          required:
+            - "#clock-cells"
+            - compatible
+            - clocks
+            - clock-output-names
+
+          additionalProperties: false
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun6i-a31-ar100-clk
+
+        then:
+          properties:
+            "#clock-cells":
+              const: 0
+
+            # Already checked in the main schema
+            compatible: true
+
+            clocks:
+              maxItems: 4
+              description: >
+                The parent order must match the hardware programming
+                order.
+
+            clock-output-names:
+              maxItems: 1
+
+            phandle: true
+
+          required:
+            - "#clock-cells"
+            - compatible
+            - clocks
+            - clock-output-names
+
+          additionalProperties: false
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun6i-a31-clock-reset
+
+        then:
+          properties:
+            "#reset-cells":
+              const: 1
+
+            # Already checked in the main schema
+            compatible: true
+
+            phandle: true
+
+          required:
+            - "#reset-cells"
+            - compatible
+
+          additionalProperties: false
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/sun6i-a31-ccu.h>
+
+    prcm@1f01400 {
+        compatible = "allwinner,sun6i-a31-prcm";
+        reg = <0x01f01400 0x200>;
+
+        ar100: ar100_clk {
+            compatible = "allwinner,sun6i-a31-ar100-clk";
+            #clock-cells = <0>;
+            clocks = <&rtc 0>, <&osc24M>,
+                     <&ccu CLK_PLL_PERIPH>,
+                     <&ccu CLK_PLL_PERIPH>;
+            clock-output-names = "ar100";
+        };
+
+        ahb0: ahb0_clk {
+            compatible = "fixed-factor-clock";
+            #clock-cells = <0>;
+            clock-div = <1>;
+            clock-mult = <1>;
+            clocks = <&ar100>;
+            clock-output-names = "ahb0";
+        };
+
+        apb0: apb0_clk {
+            compatible = "allwinner,sun6i-a31-apb0-clk";
+            #clock-cells = <0>;
+            clocks = <&ahb0>;
+            clock-output-names = "apb0";
+        };
+
+        apb0_gates: apb0_gates_clk {
+            compatible = "allwinner,sun6i-a31-apb0-gates-clk";
+            #clock-cells = <1>;
+            clocks = <&apb0>;
+            clock-output-names = "apb0_pio", "apb0_ir",
+                                 "apb0_timer", "apb0_p2wi",
+                                 "apb0_uart", "apb0_1wire",
+                                 "apb0_i2c";
+        };
+
+        ir_clk: ir_clk {
+            #clock-cells = <0>;
+            compatible = "allwinner,sun4i-a10-mod0-clk";
+            clocks = <&rtc 0>, <&osc24M>;
+            clock-output-names = "ir";
+        };
+
+        apb0_rst: apb0_rst {
+            compatible = "allwinner,sun6i-a31-clock-reset";
+            #reset-cells = <1>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/mfd/allwinner,sun8i-a23-prcm.yaml b/Documentation/devicetree/bindings/mfd/allwinner,sun8i-a23-prcm.yaml
new file mode 100644
index 000000000000..aa5e683b236c
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/allwinner,sun8i-a23-prcm.yaml
@@ -0,0 +1,200 @@
+# SPDX-License-Identifier: GPL-2.0+
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/allwinner,sun8i-a23-prcm.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A23 PRCM Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+properties:
+  compatible:
+    const: allwinner,sun8i-a23-prcm
+
+  reg:
+    maxItems: 1
+
+patternProperties:
+  "^.*(clk|rst|codec).*$":
+    type: object
+
+    properties:
+      compatible:
+        enum:
+          - fixed-factor-clock
+          - allwinner,sun8i-a23-apb0-clk
+          - allwinner,sun8i-a23-apb0-gates-clk
+          - allwinner,sun6i-a31-clock-reset
+          - allwinner,sun8i-a23-codec-analog
+
+    required:
+      - compatible
+
+    allOf:
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun8i-a23-apb0-clk
+
+        then:
+          properties:
+            "#clock-cells":
+              const: 0
+
+            # Already checked in the main schema
+            compatible: true
+
+            clocks:
+              maxItems: 1
+
+            clock-output-names:
+              maxItems: 1
+
+            phandle: true
+
+          required:
+            - "#clock-cells"
+            - compatible
+            - clocks
+            - clock-output-names
+
+          additionalProperties: false
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun8i-a23-apb0-gates-clk
+
+        then:
+          properties:
+            "#clock-cells":
+              const: 1
+              description: >
+                This additional argument passed to that clock is the
+                offset of the bit controlling this particular gate in
+                the register.
+
+            # Already checked in the main schema
+            compatible: true
+
+            clocks:
+              maxItems: 1
+
+            clock-output-names:
+              minItems: 1
+              maxItems: 32
+
+            phandle: true
+
+          required:
+            - "#clock-cells"
+            - compatible
+            - clocks
+            - clock-output-names
+
+          additionalProperties: false
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun6i-a31-clock-reset
+
+        then:
+          properties:
+            "#reset-cells":
+              const: 1
+
+            # Already checked in the main schema
+            compatible: true
+
+            phandle: true
+
+          required:
+            - "#reset-cells"
+            - compatible
+
+          additionalProperties: false
+
+      - if:
+          properties:
+            compatible:
+              contains:
+                const: allwinner,sun8i-a23-codec-analog
+
+        then:
+          properties:
+            # Already checked in the main schema
+            compatible: true
+
+            phandle: true
+
+          required:
+            - compatible
+
+          additionalProperties: false
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    prcm@1f01400 {
+        compatible = "allwinner,sun8i-a23-prcm";
+        reg = <0x01f01400 0x200>;
+
+        ar100: ar100_clk {
+            compatible = "fixed-factor-clock";
+            #clock-cells = <0>;
+            clock-div = <1>;
+            clock-mult = <1>;
+            clocks = <&osc24M>;
+            clock-output-names = "ar100";
+        };
+
+        ahb0: ahb0_clk {
+            compatible = "fixed-factor-clock";
+            #clock-cells = <0>;
+            clock-div = <1>;
+            clock-mult = <1>;
+            clocks = <&ar100>;
+            clock-output-names = "ahb0";
+        };
+
+        apb0: apb0_clk {
+            compatible = "allwinner,sun8i-a23-apb0-clk";
+            #clock-cells = <0>;
+            clocks = <&ahb0>;
+            clock-output-names = "apb0";
+        };
+
+        apb0_gates: apb0_gates_clk {
+            compatible = "allwinner,sun8i-a23-apb0-gates-clk";
+            #clock-cells = <1>;
+            clocks = <&apb0>;
+            clock-output-names = "apb0_pio", "apb0_timer",
+                                 "apb0_rsb", "apb0_uart",
+                                 "apb0_i2c";
+        };
+
+        apb0_rst: apb0_rst {
+            compatible = "allwinner,sun6i-a31-clock-reset";
+            #reset-cells = <1>;
+        };
+
+        codec_analog: codec-analog {
+            compatible = "allwinner,sun8i-a23-codec-analog";
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/mfd/atmel-usart.txt b/Documentation/devicetree/bindings/mfd/atmel-usart.txt
index 699fd3c9ace8..a09133066aff 100644
--- a/Documentation/devicetree/bindings/mfd/atmel-usart.txt
+++ b/Documentation/devicetree/bindings/mfd/atmel-usart.txt
@@ -1,10 +1,13 @@
 * Atmel Universal Synchronous Asynchronous Receiver/Transmitter (USART)
 
 Required properties for USART:
-- compatible: Should be "atmel,<chip>-usart" or "atmel,<chip>-dbgu"
-  The compatible <chip> indicated will be the first SoC to support an
-  additional mode or an USART new feature.
-  For the dbgu UART, use "atmel,<chip>-dbgu", "atmel,<chip>-usart"
+- compatible: Should be one of the following:
+	- "atmel,at91rm9200-usart"
+	- "atmel,at91sam9260-usart"
+	- "microchip,sam9x60-usart"
+	- "atmel,at91rm9200-dbgu", "atmel,at91rm9200-usart"
+	- "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"
+	- "microchip,sam9x60-dbgu", "microchip,sam9x60-usart"
 - reg: Should contain registers location and length
 - interrupts: Should contain interrupt
 - clock-names: tuple listing input clock names.
diff --git a/Documentation/devicetree/bindings/mfd/da9062.txt b/Documentation/devicetree/bindings/mfd/da9062.txt
index bc4b59de6a55..857af982c88f 100644
--- a/Documentation/devicetree/bindings/mfd/da9062.txt
+++ b/Documentation/devicetree/bindings/mfd/da9062.txt
@@ -13,6 +13,7 @@ da9062-rtc              :               : Real-Time Clock
 da9062-onkey            :               : On Key
 da9062-watchdog         :               : Watchdog Timer
 da9062-thermal          :               : Thermal
+da9062-gpio             :               : GPIOs
 
 The DA9061 PMIC consists of:
 
@@ -38,6 +39,15 @@ Required properties:
 See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
 further information on IRQ bindings.
 
+Optional properties:
+
+- gpio-controller : Marks the device as a gpio controller.
+- #gpio-cells     : Should be two. The first cell is the pin number and the
+                    second cell is used to specify the gpio polarity.
+
+See Documentation/devicetree/bindings/gpio/gpio.txt for further information on
+GPIO bindings.
+
 Sub-nodes:
 
 - regulators : This node defines the settings for the LDOs and BUCKs.
diff --git a/Documentation/devicetree/bindings/mfd/max14577.txt b/Documentation/devicetree/bindings/mfd/max14577.txt
index fc6f0f4e8beb..92070b346756 100644
--- a/Documentation/devicetree/bindings/mfd/max14577.txt
+++ b/Documentation/devicetree/bindings/mfd/max14577.txt
@@ -5,6 +5,8 @@ Battery Charger and SFOUT LDO output for powering USB devices. It is
 interfaced to host controller using I2C.
 
 MAX77836 additionally contains PMIC (with two LDO regulators) and Fuel Gauge.
+For the description of Fuel Gauge low SOC alert interrupt see:
+../power/supply/max17040_battery.txt
 
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml b/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml
new file mode 100644
index 000000000000..4fbb9e734284
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/rohm,bd71828-pmic.yaml
@@ -0,0 +1,193 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mfd/rohm,bd71828-pmic.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ROHM BD71828 Power Management Integrated Circuit bindings
+
+maintainers:
+  - Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
+
+description: |
+  BD71828GW is a single-chip power management IC for battery-powered portable
+  devices. The IC integrates 7 buck converters, 7 LDOs, and a 1500 mA
+  single-cell linear charger. Also included is a Coulomb counter, a real-time
+  clock (RTC), and a 32.768 kHz clock gate.
+
+properties:
+  compatible:
+    const: rohm,bd71828
+
+  reg:
+    description:
+      I2C slave address.
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  gpio-controller: true
+
+  "#gpio-cells":
+    const: 2
+    description: |
+      The first cell is the pin number and the second cell is used to specify
+      flags. See ../gpio/gpio.txt for more information.
+
+  clocks:
+    maxItems: 1
+
+  "#clock-cells":
+    const: 0
+
+  rohm,charger-sense-resistor-ohms:
+    minimum: 10000000
+    maximum: 50000000
+    description: |
+      BD71827 and BD71828 have SAR ADC for measuring charging currents.
+      External sense resistor (RSENSE in data sheet) should be used. If some
+      other but 30MOhm resistor is used the resistance value should be given
+      here in Ohms.
+
+  regulators:
+    $ref: ../regulator/rohm,bd71828-regulator.yaml
+    description:
+      List of child nodes that specify the regulators.
+
+  leds:
+    $ref: ../leds/rohm,bd71828-leds.yaml
+
+  gpio-reserved-ranges:
+    description: |
+      Usage of BD71828 GPIO pins can be changed via OTP. This property can be
+      used to mark the pins which should not be configured for GPIO. Please see
+      the ../gpio/gpio.txt for more information.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - "#clock-cells"
+  - regulators
+  - gpio-controller
+  - "#gpio-cells"
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/leds/common.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        pmic: pmic@4b {
+            compatible = "rohm,bd71828";
+            reg = <0x4b>;
+
+            interrupt-parent = <&gpio1>;
+            interrupts = <29 IRQ_TYPE_LEVEL_LOW>;
+
+            clocks = <&osc 0>;
+            #clock-cells = <0>;
+            clock-output-names = "bd71828-32k-out";
+
+            gpio-controller;
+            #gpio-cells = <2>;
+            gpio-reserved-ranges = <0 1>, <2 1>;
+
+            rohm,charger-sense-resistor-ohms = <10000000>;
+
+            regulators {
+                buck1: BUCK1 {
+                    regulator-name = "buck1";
+                    regulator-min-microvolt = <500000>;
+                    regulator-max-microvolt = <2000000>;
+                    regulator-ramp-delay = <2500>;
+                };
+                buck2: BUCK2 {
+                    regulator-name = "buck2";
+                    regulator-min-microvolt = <500000>;
+                    regulator-max-microvolt = <2000000>;
+                    regulator-ramp-delay = <2500>;
+                };
+                buck3: BUCK3 {
+                    regulator-name = "buck3";
+                    regulator-min-microvolt = <1200000>;
+                    regulator-max-microvolt = <2000000>;
+                };
+                buck4: BUCK4 {
+                    regulator-name = "buck4";
+                    regulator-min-microvolt = <1000000>;
+                    regulator-max-microvolt = <1800000>;
+                };
+                buck5: BUCK5 {
+                    regulator-name = "buck5";
+                    regulator-min-microvolt = <2500000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+                buck6: BUCK6 {
+                    regulator-name = "buck6";
+                    regulator-min-microvolt = <500000>;
+                    regulator-max-microvolt = <2000000>;
+                    regulator-ramp-delay = <2500>;
+                };
+                buck7: BUCK7 {
+                    regulator-name = "buck7";
+                    regulator-min-microvolt = <500000>;
+                    regulator-max-microvolt = <2000000>;
+                    regulator-ramp-delay = <2500>;
+                };
+                ldo1: LDO1 {
+                    regulator-name = "ldo1";
+                    regulator-min-microvolt = <800000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+                ldo2: LDO2 {
+                    regulator-name = "ldo2";
+                    regulator-min-microvolt = <800000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+                ldo3: LDO3 {
+                    regulator-name = "ldo3";
+                    regulator-min-microvolt = <800000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+                ldo4: LDO4 {
+                    regulator-name = "ldo4";
+                    regulator-min-microvolt = <800000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+                ldo5: LDO5 {
+                    regulator-name = "ldo5";
+                    regulator-min-microvolt = <800000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+                ldo6: LDO6 {
+                    regulator-name = "ldo6";
+                    regulator-min-microvolt = <1800000>;
+                    regulator-max-microvolt = <1800000>;
+                };
+                ldo7_reg: LDO7 {
+                    regulator-name = "ldo7";
+                    regulator-min-microvolt = <800000>;
+                    regulator-max-microvolt = <3300000>;
+                };
+            };
+
+            leds {
+                compatible = "rohm,bd71828-leds";
+
+                led-1 {
+                    rohm,led-compatible = "bd71828-grnled";
+                    function = LED_FUNCTION_INDICATOR;
+                    color = <LED_COLOR_ID_GREEN>;
+                };
+                led-2 {
+                    rohm,led-compatible = "bd71828-ambled";
+                    function = LED_FUNCTION_CHARGING;
+                    color = <LED_COLOR_ID_AMBER>;
+                };
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/mfd/sun6i-prcm.txt b/Documentation/devicetree/bindings/mfd/sun6i-prcm.txt
deleted file mode 100644
index daa091c2e67b..000000000000
--- a/Documentation/devicetree/bindings/mfd/sun6i-prcm.txt
+++ /dev/null
@@ -1,59 +0,0 @@
-* Allwinner PRCM (Power/Reset/Clock Management) Multi-Functional Device
-
-PRCM is an MFD device exposing several Power Management related devices
-(like clks and reset controllers).
-
-Required properties:
- - compatible: "allwinner,sun6i-a31-prcm" or "allwinner,sun8i-a23-prcm"
- - reg: The PRCM registers range
-
-The prcm node may contain several subdevices definitions:
- - see Documentation/devicetree/bindings/clock/sunxi.txt for clock devices
- - see Documentation/devicetree/bindings/reset/allwinner,sunxi-clock-reset.txt for reset
-   controller devices
-
-
-Example:
-
-	prcm: prcm@1f01400 {
-		compatible = "allwinner,sun6i-a31-prcm";
-		reg = <0x01f01400 0x200>;
-
-		/* Put subdevices here */
-		ar100: ar100_clk {
-			compatible = "allwinner,sun6i-a31-ar100-clk";
-			#clock-cells = <0>;
-			clocks = <&osc32k>, <&osc24M>, <&pll6>, <&pll6>;
-		};
-
-		ahb0: ahb0_clk {
-			compatible = "fixed-factor-clock";
-			#clock-cells = <0>;
-			clock-div = <1>;
-			clock-mult = <1>;
-			clocks = <&ar100_div>;
-			clock-output-names = "ahb0";
-		};
-
-		apb0: apb0_clk {
-			compatible = "allwinner,sun6i-a31-apb0-clk";
-			#clock-cells = <0>;
-			clocks = <&ahb0>;
-			clock-output-names = "apb0";
-		};
-
-		apb0_gates: apb0_gates_clk {
-			compatible = "allwinner,sun6i-a31-apb0-gates-clk";
-			#clock-cells = <1>;
-			clocks = <&apb0>;
-			clock-output-names = "apb0_pio", "apb0_ir",
-					"apb0_timer01", "apb0_p2wi",
-					"apb0_uart", "apb0_1wire",
-					"apb0_i2c";
-		};
-
-		apb0_rst: apb0_rst {
-			compatible = "allwinner,sun6i-a31-clock-reset";
-			#reset-cells = <1>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/mfd/tps6105x.txt b/Documentation/devicetree/bindings/mfd/tps6105x.txt
index 93602c7a19c8..dc448a9d5b4d 100644
--- a/Documentation/devicetree/bindings/mfd/tps6105x.txt
+++ b/Documentation/devicetree/bindings/mfd/tps6105x.txt
@@ -7,11 +7,56 @@ Required properties:
 - compatible:		"ti,tps61050" or "ti,tps61052"
 - reg:			Specifies the I2C slave address
 
-Example:
+Optional sub-node:
+
+This subnode selects the chip's operational mode.
+There can be at most one single available subnode.
+
+- regulator: presence of this sub-node puts the chip in regulator mode.
+	see ../regulator/regulator.yaml
+
+- led: presence of this sub-node puts the chip in led mode.
+	Optional properties:
+	- function : see ../leds/common.txt
+	- color    : see ../leds/common.txt
+	- label    : see ../leds/common.txt
+			(deprecated)
+
+Example (GPIO operation only):
+
+i2c0 {
+	tps61052@33 {
+		compatible = "ti,tps61052";
+		reg = <0x33>;
+	};
+};
+
+Example (GPIO + regulator operation):
 
 i2c0 {
 	tps61052@33 {
 		compatible = "ti,tps61052";
 		reg = <0x33>;
+
+		regulator {
+			regulator-min-microvolt = <5000000>;
+			regulator-max-microvolt = <5000000>;
+			regulator-always-on;
+		};
+	};
+};
+
+Example (GPIO + led operation):
+
+#include <dt-bindings/leds/common.h>
+
+i2c0 {
+	tps61052@33 {
+		compatible = "ti,tps61052";
+		reg = <0x33>;
+
+		led {
+			color = <LED_COLOR_ID_WHITE>;
+		};
 	};
 };
diff --git a/Documentation/devicetree/bindings/mips/ingenic/devices.yaml b/Documentation/devicetree/bindings/mips/ingenic/devices.yaml
new file mode 100644
index 000000000000..78dcf6ef3883
--- /dev/null
+++ b/Documentation/devicetree/bindings/mips/ingenic/devices.yaml
@@ -0,0 +1,35 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/mips/ingenic/devices.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Ingenic XBurst based Platforms Device Tree Bindings
+
+maintainers:
+  - 周琰杰 (Zhou Yanjie) <zhouyanjie@wanyeetech.com>
+description: |
+  Devices with a Ingenic XBurst CPU shall have the following properties.
+
+properties:
+  $nodename:
+    const: '/'
+  compatible:
+    oneOf:
+
+      - description: Qi Hardware Ben NanoNote
+        items:
+          - const: qi,lb60
+
+      - description: Game Consoles Worldwide GCW Zero
+        items:
+          - const: gcw,zero
+
+      - description: MIPS Creator CI20
+        items:
+          - const: img,ci20
+
+      - description: YSH & ATIL General Board CU Neo
+        items:
+          - const: yna,cu1000-neo
+...
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index c93643fceabb..0f97d711444e 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -22,6 +22,7 @@ Required properties:
 	       "fsl,imx8mm-usdhc"
 	       "fsl,imx8mn-usdhc"
 	       "fsl,imx8mp-usdhc"
+	       "fsl,imx8qm-usdhc"
 	       "fsl,imx8qxp-usdhc"
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml
index b130450c3b34..3c0df4016a12 100644
--- a/Documentation/devicetree/bindings/mmc/mmc-controller.yaml
+++ b/Documentation/devicetree/bindings/mmc/mmc-controller.yaml
@@ -96,11 +96,10 @@ properties:
     description:
       When set, no physical write-protect line is present. This
       property should only be specified when the controller has a
-      dedicated write-protect detection logic. If a GPIO is always
-      used for the write-protect detection. If a GPIO is always used
+      dedicated write-protect detection logic. If a GPIO is always used
       for the write-protect detection logic, it is sufficient to not
       specify the wp-gpios property in the absence of a write-protect
-      line.
+      line. Not used in combination with eMMC or SDIO.
 
   wp-gpios:
     description:
diff --git a/Documentation/devicetree/bindings/mtd/denali-nand.txt b/Documentation/devicetree/bindings/mtd/denali-nand.txt
index b32aed1db46d..98916a84bbf6 100644
--- a/Documentation/devicetree/bindings/mtd/denali-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/denali-nand.txt
@@ -14,6 +14,11 @@ Required properties:
     interface clock, and the ECC circuit clock.
   - clock-names: should contain "nand", "nand_x", "ecc"
 
+Optional properties:
+  - resets: may contain phandles to the controller core reset, the register
+    reset
+  - reset-names: may contain "nand", "reg"
+
 Sub-nodes:
   Sub-nodes represent available NAND chips.
 
@@ -46,6 +51,8 @@ nand: nand@ff900000 {
 	reg-names = "nand_data", "denali_reg";
 	clocks = <&nand_clk>, <&nand_x_clk>, <&nand_ecc_clk>;
 	clock-names = "nand", "nand_x", "ecc";
+	resets = <&nand_rst>, <&nand_reg_rst>;
+	reset-names = "nand", "reg";
 	interrupts = <0 144 4>;
 
 	nand@0 {
diff --git a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt
index 68b67d9db63a..999aceadb985 100644
--- a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt
@@ -11,6 +11,7 @@ Required properties:
  - compatible: should contain one of the following:
    * "qcom,qca6174-bt"
    * "qcom,wcn3990-bt"
+   * "qcom,wcn3991-bt"
    * "qcom,wcn3998-bt"
 
 Optional properties for compatible string qcom,qca6174-bt:
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index 5df4aa7f6811..87dad2dd8ca0 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -21,7 +21,8 @@ Required properties:
       - "renesas,etheravb-r8a774b1" for the R8A774B1 SoC.
       - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC.
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
-      - "renesas,etheravb-r8a7796" for the R8A7796 SoC.
+      - "renesas,etheravb-r8a7796" for the R8A77960 SoC.
+      - "renesas,etheravb-r8a77961" for the R8A77961 SoC.
       - "renesas,etheravb-r8a77965" for the R8A77965 SoC.
       - "renesas,etheravb-r8a77970" for the R8A77970 SoC.
       - "renesas,etheravb-r8a77980" for the R8A77980 SoC.
@@ -37,8 +38,8 @@ Required properties:
 - reg: Offset and length of (1) the register block and (2) the stream buffer.
        The region for the register block is mandatory.
        The region for the stream buffer is optional, as it is only present on
-       R-Car Gen2 and RZ/G1 SoCs, and on R-Car H3 (R8A7795), M3-W (R8A7796),
-       and M3-N (R8A77965).
+       R-Car Gen2 and RZ/G1 SoCs, and on R-Car H3 (R8A7795), M3-W (R8A77960),
+       M3-W+ (R8A77961), and M3-N (R8A77965).
 - interrupts: A list of interrupt-specifiers, one for each entry in
 	      interrupt-names.
 	      If interrupt-names is not present, an interrupt specifier
diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt
deleted file mode 100644
index 142a51d5a9be..000000000000
--- a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-STMicroelectronics STM32 Factory-programmed data device tree bindings
-
-This represents STM32 Factory-programmed read only non-volatile area: locked
-flash, OTP, read-only HW regs... This contains various information such as:
-analog calibration data for temperature sensor (e.g. TS_CAL1, TS_CAL2),
-internal vref (VREFIN_CAL), unique device ID...
-
-Required properties:
-- compatible:		Should be one of:
-			"st,stm32f4-otp"
-			"st,stm32mp15-bsec"
-- reg:			Offset and length of factory-programmed area.
-- #address-cells:	Should be '<1>'.
-- #size-cells:		Should be '<1>'.
-
-Optional Data cells:
-- Must be child nodes as described in nvmem.txt.
-
-Example on stm32f4:
-	romem: nvmem@1fff7800 {
-		compatible = "st,stm32f4-otp";
-		reg = <0x1fff7800 0x400>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-
-		/* Data cells: ts_cal1 at 0x1fff7a2c */
-		ts_cal1: calib@22c {
-			reg = <0x22c 0x2>;
-		};
-		...
-	};
diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
new file mode 100644
index 000000000000..d84deb4774a4
--- /dev/null
+++ b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.yaml
@@ -0,0 +1,46 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/nvmem/st,stm32-romem.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 Factory-programmed data bindings
+
+description: |
+  This represents STM32 Factory-programmed read only non-volatile area: locked
+  flash, OTP, read-only HW regs... This contains various information such as:
+  analog calibration data for temperature sensor (e.g. TS_CAL1, TS_CAL2),
+  internal vref (VREFIN_CAL), unique device ID...
+
+maintainers:
+  - Fabrice Gasnier <fabrice.gasnier@st.com>
+
+allOf:
+  - $ref: "nvmem.yaml#"
+
+properties:
+  compatible:
+    enum:
+      - st,stm32f4-otp
+      - st,stm32mp15-bsec
+
+required:
+  - "#address-cells"
+  - "#size-cells"
+  - compatible
+  - reg
+
+examples:
+  - |
+    efuse@1fff7800 {
+      compatible = "st,stm32f4-otp";
+      reg = <0x1fff7800 0x400>;
+      #address-cells = <1>;
+      #size-cells = <1>;
+
+      calib@22c {
+        reg = <0x22c 0x2>;
+      };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml b/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml
new file mode 100644
index 000000000000..aef87a33a7c9
--- /dev/null
+++ b/Documentation/devicetree/bindings/opp/allwinner,sun50i-h6-operating-points.yaml
@@ -0,0 +1,129 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/opp/allwinner,sun50i-h6-operating-points.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner H6 CPU OPP Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description: |
+  For some SoCs, the CPU frequency subset and voltage value of each
+  OPP varies based on the silicon variant in use. Allwinner Process
+  Voltage Scaling Tables defines the voltage and frequency value based
+  on the speedbin blown in the efuse combination. The
+  sun50i-cpufreq-nvmem driver reads the efuse value from the SoC to
+  provide the OPP framework with required information.
+
+properties:
+  compatible:
+    const: allwinner,sun50i-h6-operating-points
+
+  nvmem-cells:
+    description: |
+      A phandle pointing to a nvmem-cells node representing the efuse
+      registers that has information about the speedbin that is used
+      to select the right frequency/voltage value pair. Please refer
+      the for nvmem-cells bindings
+      Documentation/devicetree/bindings/nvmem/nvmem.txt and also
+      examples below.
+
+required:
+  - compatible
+  - nvmem-cells
+
+patternProperties:
+  "opp-[0-9]+":
+    type: object
+
+    properties:
+      opp-hz: true
+
+    patternProperties:
+      "opp-microvolt-.*": true
+
+    required:
+      - opp-hz
+      - opp-microvolt-speed0
+      - opp-microvolt-speed1
+      - opp-microvolt-speed2
+
+    unevaluatedProperties: false
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    cpu_opp_table: opp-table {
+        compatible = "allwinner,sun50i-h6-operating-points";
+        nvmem-cells = <&speedbin_efuse>;
+        opp-shared;
+
+        opp-480000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <480000000>;
+
+            opp-microvolt-speed0 = <880000>;
+            opp-microvolt-speed1 = <820000>;
+            opp-microvolt-speed2 = <800000>;
+        };
+
+        opp-720000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <720000000>;
+
+            opp-microvolt-speed0 = <880000>;
+            opp-microvolt-speed1 = <820000>;
+            opp-microvolt-speed2 = <800000>;
+        };
+
+        opp-816000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <816000000>;
+
+            opp-microvolt-speed0 = <880000>;
+            opp-microvolt-speed1 = <820000>;
+            opp-microvolt-speed2 = <800000>;
+        };
+
+        opp-888000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <888000000>;
+
+            opp-microvolt-speed0 = <940000>;
+            opp-microvolt-speed1 = <820000>;
+            opp-microvolt-speed2 = <800000>;
+        };
+
+        opp-1080000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <1080000000>;
+
+            opp-microvolt-speed0 = <1060000>;
+            opp-microvolt-speed1 = <880000>;
+            opp-microvolt-speed2 = <840000>;
+        };
+
+        opp-1320000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <1320000000>;
+
+            opp-microvolt-speed0 = <1160000>;
+            opp-microvolt-speed1 = <940000>;
+            opp-microvolt-speed2 = <900000>;
+        };
+
+        opp-1488000000 {
+            clock-latency-ns = <244144>; /* 8 32k periods */
+            opp-hz = /bits/ 64 <1488000000>;
+
+            opp-microvolt-speed0 = <1160000>;
+            opp-microvolt-speed1 = <1000000>;
+            opp-microvolt-speed2 = <960000>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt b/Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt
deleted file mode 100644
index 7deae57a587b..000000000000
--- a/Documentation/devicetree/bindings/opp/sun50i-nvmem-cpufreq.txt
+++ /dev/null
@@ -1,167 +0,0 @@
-Allwinner Technologies, Inc. NVMEM CPUFreq and OPP bindings
-===================================
-
-For some SoCs, the CPU frequency subset and voltage value of each OPP
-varies based on the silicon variant in use. Allwinner Process Voltage
-Scaling Tables defines the voltage and frequency value based on the
-speedbin blown in the efuse combination. The sun50i-cpufreq-nvmem driver
-reads the efuse value from the SoC to provide the OPP framework with
-required information.
-
-Required properties:
---------------------
-In 'cpus' nodes:
-- operating-points-v2: Phandle to the operating-points-v2 table to use.
-
-In 'operating-points-v2' table:
-- compatible: Should be
-	- 'allwinner,sun50i-h6-operating-points'.
-- nvmem-cells: A phandle pointing to a nvmem-cells node representing the
-		efuse registers that has information about the speedbin
-		that is used to select the right frequency/voltage value
-		pair. Please refer the for nvmem-cells bindings
-		Documentation/devicetree/bindings/nvmem/nvmem.txt and
-		also examples below.
-
-In every OPP node:
-- opp-microvolt-<name>: Voltage in micro Volts.
-			At runtime, the platform can pick a <name> and
-			matching opp-microvolt-<name> property.
-			[See: opp.txt]
-			HW:		<name>:
-			sun50i-h6	speed0 speed1 speed2
-
-Example 1:
----------
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		cpu0: cpu@0 {
-			compatible = "arm,cortex-a53";
-			device_type = "cpu";
-			reg = <0>;
-			enable-method = "psci";
-			clocks = <&ccu CLK_CPUX>;
-			clock-latency-ns = <244144>; /* 8 32k periods */
-			operating-points-v2 = <&cpu_opp_table>;
-			#cooling-cells = <2>;
-		};
-
-		cpu1: cpu@1 {
-			compatible = "arm,cortex-a53";
-			device_type = "cpu";
-			reg = <1>;
-			enable-method = "psci";
-			clocks = <&ccu CLK_CPUX>;
-			clock-latency-ns = <244144>; /* 8 32k periods */
-			operating-points-v2 = <&cpu_opp_table>;
-			#cooling-cells = <2>;
-		};
-
-		cpu2: cpu@2 {
-			compatible = "arm,cortex-a53";
-			device_type = "cpu";
-			reg = <2>;
-			enable-method = "psci";
-			clocks = <&ccu CLK_CPUX>;
-			clock-latency-ns = <244144>; /* 8 32k periods */
-			operating-points-v2 = <&cpu_opp_table>;
-			#cooling-cells = <2>;
-		};
-
-		cpu3: cpu@3 {
-			compatible = "arm,cortex-a53";
-			device_type = "cpu";
-			reg = <3>;
-			enable-method = "psci";
-			clocks = <&ccu CLK_CPUX>;
-			clock-latency-ns = <244144>; /* 8 32k periods */
-			operating-points-v2 = <&cpu_opp_table>;
-			#cooling-cells = <2>;
-		};
-        };
-
-        cpu_opp_table: opp_table {
-                compatible = "allwinner,sun50i-h6-operating-points";
-                nvmem-cells = <&speedbin_efuse>;
-                opp-shared;
-
-                opp@480000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <480000000>;
-
-                        opp-microvolt-speed0 = <880000>;
-                        opp-microvolt-speed1 = <820000>;
-                        opp-microvolt-speed2 = <800000>;
-                };
-
-                opp@720000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <720000000>;
-
-                        opp-microvolt-speed0 = <880000>;
-                        opp-microvolt-speed1 = <820000>;
-                        opp-microvolt-speed2 = <800000>;
-                };
-
-                opp@816000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <816000000>;
-
-                        opp-microvolt-speed0 = <880000>;
-                        opp-microvolt-speed1 = <820000>;
-                        opp-microvolt-speed2 = <800000>;
-                };
-
-                opp@888000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <888000000>;
-
-                        opp-microvolt-speed0 = <940000>;
-                        opp-microvolt-speed1 = <820000>;
-                        opp-microvolt-speed2 = <800000>;
-                };
-
-                opp@1080000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <1080000000>;
-
-                        opp-microvolt-speed0 = <1060000>;
-                        opp-microvolt-speed1 = <880000>;
-                        opp-microvolt-speed2 = <840000>;
-                };
-
-                opp@1320000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <1320000000>;
-
-                        opp-microvolt-speed0 = <1160000>;
-                        opp-microvolt-speed1 = <940000>;
-                        opp-microvolt-speed2 = <900000>;
-                };
-
-                opp@1488000000 {
-                        clock-latency-ns = <244144>; /* 8 32k periods */
-                        opp-hz = /bits/ 64 <1488000000>;
-
-                        opp-microvolt-speed0 = <1160000>;
-                        opp-microvolt-speed1 = <1000000>;
-                        opp-microvolt-speed2 = <960000>;
-                };
-        };
-....
-soc {
-....
-	sid: sid@3006000 {
-		compatible = "allwinner,sun50i-h6-sid";
-		reg = <0x03006000 0x400>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		....
-		speedbin_efuse: speed@1c {
-			reg = <0x1c 4>;
-		};
-        };
-};
diff --git a/Documentation/devicetree/bindings/pci/arm,juno-r1-pcie.txt b/Documentation/devicetree/bindings/pci/arm,juno-r1-pcie.txt
deleted file mode 100644
index f7514c170a32..000000000000
--- a/Documentation/devicetree/bindings/pci/arm,juno-r1-pcie.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-* ARM Juno R1 PCIe interface
-
-This PCIe host controller is based on PLDA XpressRICH3-AXI IP
-and thus inherits all the common properties defined in plda,xpressrich3-axi.txt
-as well as the base properties defined in host-generic-pci.txt.
-
-Required properties:
- - compatible: "arm,juno-r1-pcie"
- - dma-coherent: The host controller bridges the AXI transactions into PCIe bus
-   in a manner that makes the DMA operations to appear coherent to the CPUs.
diff --git a/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
new file mode 100644
index 000000000000..77d3e81a437b
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
@@ -0,0 +1,97 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/brcm,stb-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Brcmstb PCIe Host Controller Device Tree Bindings
+
+maintainers:
+  - Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
+
+allOf:
+  - $ref: /schemas/pci/pci-bus.yaml#
+
+properties:
+  compatible:
+    const: brcm,bcm2711-pcie # The Raspberry Pi 4
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: PCIe host controller
+      - description: builtin MSI controller
+
+  interrupt-names:
+    minItems: 1
+    maxItems: 2
+    items:
+      - const: pcie
+      - const: msi
+
+  ranges:
+    maxItems: 1
+
+  dma-ranges:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: sw_pcie
+
+  msi-controller:
+    description: Identifies the node as an MSI controller.
+
+  msi-parent:
+    description: MSI controller the device is capable of using.
+
+  brcm,enable-ssc:
+    description: Indicates usage of spread-spectrum clocking.
+    type: boolean
+
+required:
+  - reg
+  - dma-ranges
+  - "#interrupt-cells"
+  - interrupts
+  - interrupt-names
+  - interrupt-map-mask
+  - interrupt-map
+  - msi-controller
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    scb {
+            #address-cells = <2>;
+            #size-cells = <1>;
+            pcie0: pcie@7d500000 {
+                    compatible = "brcm,bcm2711-pcie";
+                    reg = <0x0 0x7d500000 0x9310>;
+                    device_type = "pci";
+                    #address-cells = <3>;
+                    #size-cells = <2>;
+                    #interrupt-cells = <1>;
+                    interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                                 <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>;
+                    interrupt-names = "pcie", "msi";
+                    interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+                    interrupt-map = <0 0 0 1 &gicv2 GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>;
+                    msi-parent = <&pcie0>;
+                    msi-controller;
+                    ranges = <0x02000000 0x0 0xf8000000 0x6 0x00000000 0x0 0x04000000>;
+                    dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>;
+                    brcm,enable-ssc;
+            };
+    };
diff --git a/Documentation/devicetree/bindings/pci/designware-pcie-ecam.txt b/Documentation/devicetree/bindings/pci/designware-pcie-ecam.txt
deleted file mode 100644
index 515b2f9542e5..000000000000
--- a/Documentation/devicetree/bindings/pci/designware-pcie-ecam.txt
+++ /dev/null
@@ -1,42 +0,0 @@
-* Synopsys DesignWare PCIe root complex in ECAM shift mode
-
-In some cases, firmware may already have configured the Synopsys DesignWare
-PCIe controller in RC mode with static ATU window mappings that cover all
-config, MMIO and I/O spaces in a [mostly] ECAM compatible fashion.
-In this case, there is no need for the OS to perform any low level setup
-of clocks, PHYs or device registers, nor is there any reason for the driver
-to reconfigure ATU windows for config and/or IO space accesses at runtime.
-
-In cases where the IP was synthesized with a minimum ATU window size of
-64 KB, it cannot be supported by the generic ECAM driver, because it
-requires special config space accessors that filter accesses to device #1
-and beyond on the first bus.
-
-Required properties:
-- compatible: "marvell,armada8k-pcie-ecam" or
-              "socionext,synquacer-pcie-ecam" or
-              "snps,dw-pcie-ecam" (must be preceded by a more specific match)
-
-Please refer to the binding document of "pci-host-ecam-generic" in the
-file host-generic-pci.txt for a description of the remaining required
-and optional properties.
-
-Example:
-
-    pcie1: pcie@7f000000 {
-        compatible = "socionext,synquacer-pcie-ecam", "snps,dw-pcie-ecam";
-        device_type = "pci";
-        reg = <0x0 0x7f000000 0x0 0xf00000>;
-        bus-range = <0x0 0xe>;
-        #address-cells = <3>;
-        #size-cells = <2>;
-        ranges = <0x1000000 0x00 0x00010000 0x00 0x7ff00000 0x0 0x00010000>,
-                 <0x2000000 0x00 0x70000000 0x00 0x70000000 0x0 0x0f000000>,
-                 <0x3000000 0x3f 0x00000000 0x3f 0x00000000 0x1 0x00000000>;
-
-        #interrupt-cells = <0x1>;
-        interrupt-map-mask = <0x0 0x0 0x0 0x0>;
-        interrupt-map = <0x0 0x0 0x0 0x0 &gic 0x0 0x0 0x0 182 0x4>;
-        msi-map = <0x0 &its 0x0 0x10000>;
-        dma-coherent;
-    };
diff --git a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
index 0dcb87d6554f..d6796ef54ea1 100644
--- a/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/hisilicon-pcie.txt
@@ -41,45 +41,3 @@ Hip05 Example (note that Hip06 is the same except compatible):
 				 0x0 0 0 3 &mbigen_pcie 3 12
 				 0x0 0 0 4 &mbigen_pcie 4 13>;
 	};
-
-HiSilicon Hip06/Hip07 PCIe host bridge DT (almost-ECAM) description.
-
-Some BIOSes place the host controller in a mode where it is ECAM
-compliant for all devices other than the root complex. In such cases,
-the host controller should be described as below.
-
-The properties and their meanings are identical to those described in
-host-generic-pci.txt except as listed below.
-
-Properties of the host controller node that differ from
-host-generic-pci.txt:
-
-- compatible     : Must be "hisilicon,hip06-pcie-ecam", or
-		   "hisilicon,hip07-pcie-ecam"
-
-- reg            : Two entries: First the ECAM configuration space for any
-		   other bus underneath the root bus. Second, the base
-		   and size of the HiSilicon host bridge registers include
-		   the RC's own config space.
-
-Example:
-	pcie0: pcie@a0090000 {
-		compatible = "hisilicon,hip06-pcie-ecam";
-		reg = <0 0xb0000000 0 0x2000000>,  /*  ECAM configuration space */
-		      <0 0xa0090000 0 0x10000>; /* host bridge registers */
-		bus-range = <0  31>;
-		msi-map = <0x0000 &its_dsa 0x0000 0x2000>;
-		msi-map-mask = <0xffff>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		device_type = "pci";
-		dma-coherent;
-		ranges = <0x02000000 0 0xb2000000 0x0 0xb2000000 0 0x5ff0000
-			  0x01000000 0 0 0 0xb7ff0000 0 0x10000>;
-		#interrupt-cells = <1>;
-		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <0x0 0 0 1 &mbigen_pcie0 650 4
-				 0x0 0 0 2 &mbigen_pcie0 650 4
-				 0x0 0 0 3 &mbigen_pcie0 650 4
-				 0x0 0 0 4 &mbigen_pcie0 650 4>;
-	};
diff --git a/Documentation/devicetree/bindings/pci/host-generic-pci.txt b/Documentation/devicetree/bindings/pci/host-generic-pci.txt
deleted file mode 100644
index 614b594f4e72..000000000000
--- a/Documentation/devicetree/bindings/pci/host-generic-pci.txt
+++ /dev/null
@@ -1,101 +0,0 @@
-* Generic PCI host controller
-
-Firmware-initialised PCI host controllers and PCI emulations, such as the
-virtio-pci implementations found in kvmtool and other para-virtualised
-systems, do not require driver support for complexities such as regulator
-and clock management. In fact, the controller may not even require the
-configuration of a control interface by the operating system, instead
-presenting a set of fixed windows describing a subset of IO, Memory and
-Configuration Spaces.
-
-Such a controller can be described purely in terms of the standardized device
-tree bindings communicated in pci.txt:
-
-
-Properties of the host controller node:
-
-- compatible     : Must be "pci-host-cam-generic" or "pci-host-ecam-generic"
-                   depending on the layout of configuration space (CAM vs
-                   ECAM respectively).
-
-- device_type    : Must be "pci".
-
-- ranges         : As described in IEEE Std 1275-1994, but must provide
-                   at least a definition of non-prefetchable memory. One
-                   or both of prefetchable Memory and IO Space may also
-                   be provided.
-
-- bus-range      : Optional property (also described in IEEE Std 1275-1994)
-                   to indicate the range of bus numbers for this controller.
-                   If absent, defaults to <0 255> (i.e. all buses).
-
-- #address-cells : Must be 3.
-
-- #size-cells    : Must be 2.
-
-- reg            : The Configuration Space base address and size, as accessed
-                   from the parent bus.  The base address corresponds to
-                   the first bus in the "bus-range" property.  If no
-                   "bus-range" is specified, this will be bus 0 (the default).
-
-Properties of the /chosen node:
-
-- linux,pci-probe-only
-                 : Optional property which takes a single-cell argument.
-                   If '0', then Linux will assign devices in its usual manner,
-                   otherwise it will not try to assign devices and instead use
-                   them as they are configured already.
-
-Configuration Space is assumed to be memory-mapped (as opposed to being
-accessed via an ioport) and laid out with a direct correspondence to the
-geography of a PCI bus address by concatenating the various components to
-form an offset.
-
-For CAM, this 24-bit offset is:
-
-        cfg_offset(bus, device, function, register) =
-                   bus << 16 | device << 11 | function << 8 | register
-
-While ECAM extends this by 4 bits to accommodate 4k of function space:
-
-        cfg_offset(bus, device, function, register) =
-                   bus << 20 | device << 15 | function << 12 | register
-
-Interrupt mapping is exactly as described in `Open Firmware Recommended
-Practice: Interrupt Mapping' and requires the following properties:
-
-- #interrupt-cells   : Must be 1
-
-- interrupt-map      : <see aforementioned specification>
-
-- interrupt-map-mask : <see aforementioned specification>
-
-
-Example:
-
-pci {
-    compatible = "pci-host-cam-generic"
-    device_type = "pci";
-    #address-cells = <3>;
-    #size-cells = <2>;
-    bus-range = <0x0 0x1>;
-
-    // CPU_PHYSICAL(2)  SIZE(2)
-    reg = <0x0 0x40000000  0x0 0x1000000>;
-
-    // BUS_ADDRESS(3)  CPU_PHYSICAL(2)  SIZE(2)
-    ranges = <0x01000000 0x0 0x01000000  0x0 0x01000000  0x0 0x00010000>,
-             <0x02000000 0x0 0x41000000  0x0 0x41000000  0x0 0x3f000000>;
-
-
-    #interrupt-cells = <0x1>;
-
-    // PCI_DEVICE(3)  INT#(1)  CONTROLLER(PHANDLE)  CONTROLLER_DATA(3)
-    interrupt-map = <  0x0 0x0 0x0  0x1  &gic  0x0 0x4 0x1
-                     0x800 0x0 0x0  0x1  &gic  0x0 0x5 0x1
-                    0x1000 0x0 0x0  0x1  &gic  0x0 0x6 0x1
-                    0x1800 0x0 0x0  0x1  &gic  0x0 0x7 0x1>;
-
-    // PCI_DEVICE(3)  INT#(1)
-    interrupt-map-mask = <0xf800 0x0 0x0  0x7>;
-}
diff --git a/Documentation/devicetree/bindings/pci/host-generic-pci.yaml b/Documentation/devicetree/bindings/pci/host-generic-pci.yaml
new file mode 100644
index 000000000000..47353d0cd394
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/host-generic-pci.yaml
@@ -0,0 +1,172 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/host-generic-pci.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Generic PCI host controller
+
+maintainers:
+  - Will Deacon <will@kernel.org>
+
+description: |
+  Firmware-initialised PCI host controllers and PCI emulations, such as the
+  virtio-pci implementations found in kvmtool and other para-virtualised
+  systems, do not require driver support for complexities such as regulator
+  and clock management. In fact, the controller may not even require the
+  configuration of a control interface by the operating system, instead
+  presenting a set of fixed windows describing a subset of IO, Memory and
+  Configuration Spaces.
+
+  Configuration Space is assumed to be memory-mapped (as opposed to being
+  accessed via an ioport) and laid out with a direct correspondence to the
+  geography of a PCI bus address by concatenating the various components to
+  form an offset.
+
+  For CAM, this 24-bit offset is:
+
+          cfg_offset(bus, device, function, register) =
+                     bus << 16 | device << 11 | function << 8 | register
+
+  While ECAM extends this by 4 bits to accommodate 4k of function space:
+
+          cfg_offset(bus, device, function, register) =
+                     bus << 20 | device << 15 | function << 12 | register
+
+properties:
+  compatible:
+    description: Depends on the layout of configuration space (CAM vs ECAM
+      respectively). May also have more specific compatibles.
+    oneOf:
+      - description:
+          PCIe host controller in Arm Juno based on PLDA XpressRICH3-AXI IP
+        items:
+          - const: arm,juno-r1-pcie
+          - const: plda,xpressrich3-axi
+          - const: pci-host-ecam-generic
+      - description: |
+          ThunderX PCI host controller for pass-1.x silicon
+
+          Firmware-initialized PCI host controller to on-chip devices found on
+          some Cavium ThunderX processors.  These devices have ECAM-based config
+          access, but the BARs are all at fixed addresses.  We handle the fixed
+          addresses by synthesizing Enhanced Allocation (EA) capabilities for
+          these devices.
+        const: cavium,pci-host-thunder-ecam
+      - description:
+          Cavium ThunderX PEM firmware-initialized PCIe host controller
+        const: cavium,pci-host-thunder-pem
+      - description:
+          HiSilicon Hip06/Hip07 PCIe host bridge in almost-ECAM mode. Some
+          firmware places the host controller in a mode where it is ECAM
+          compliant for all devices other than the root complex.
+        enum:
+          - hisilicon,hip06-pcie-ecam
+          - hisilicon,hip07-pcie-ecam
+      - description: |
+          In some cases, firmware may already have configured the Synopsys
+          DesignWare PCIe controller in RC mode with static ATU window mappings
+          that cover all config, MMIO and I/O spaces in a [mostly] ECAM
+          compatible fashion. In this case, there is no need for the OS to
+          perform any low level setup of clocks, PHYs or device registers, nor
+          is there any reason for the driver to reconfigure ATU windows for
+          config and/or IO space accesses at runtime.
+
+          In cases where the IP was synthesized with a minimum ATU window size
+          of 64 KB, it cannot be supported by the generic ECAM driver, because
+          it requires special config space accessors that filter accesses to
+          device #1 and beyond on the first bus.
+        items:
+          - enum:
+              - marvell,armada8k-pcie-ecam
+              - socionext,synquacer-pcie-ecam
+          - const: snps,dw-pcie-ecam
+      - description:
+          CAM or ECAM compliant PCI host controllers without any quirks
+        enum:
+          - pci-host-cam-generic
+          - pci-host-ecam-generic
+
+  reg:
+    description:
+      The Configuration Space base address and size, as accessed from the parent
+      bus. The base address corresponds to the first bus in the "bus-range"
+      property. If no "bus-range" is specified, this will be bus 0 (the
+      default). Some host controllers have a 2nd non-compliant address range,
+      so 2 entries are allowed.
+    minItems: 1
+    maxItems: 2
+
+  ranges:
+    description:
+      As described in IEEE Std 1275-1994, but must provide at least a
+      definition of non-prefetchable memory. One or both of prefetchable Memory
+      and IO Space may also be provided.
+    minItems: 1
+    maxItems: 3
+
+  dma-coherent: true
+
+required:
+  - compatible
+  - reg
+  - ranges
+
+allOf:
+  - $ref: /schemas/pci/pci-bus.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: arm,juno-r1-pcie
+    then:
+      required:
+        - dma-coherent
+
+  - if:
+      properties:
+        compatible:
+          not:
+            contains:
+              enum:
+                - cavium,pci-host-thunder-pem
+                - hisilicon,hip06-pcie-ecam
+                - hisilicon,hip07-pcie-ecam
+    then:
+      properties:
+        reg:
+          maxItems: 1
+
+examples:
+  - |
+
+    bus {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        pcie@40000000 {
+            compatible = "pci-host-cam-generic";
+            device_type = "pci";
+            #address-cells = <3>;
+            #size-cells = <2>;
+            bus-range = <0x0 0x1>;
+
+            // CPU_PHYSICAL(2)  SIZE(2)
+            reg = <0x0 0x40000000  0x0 0x1000000>;
+
+            // BUS_ADDRESS(3)  CPU_PHYSICAL(2)  SIZE(2)
+            ranges = <0x01000000 0x0 0x01000000  0x0 0x01000000  0x0 0x00010000>,
+                     <0x02000000 0x0 0x41000000  0x0 0x41000000  0x0 0x3f000000>;
+
+            #interrupt-cells = <0x1>;
+
+            // PCI_DEVICE(3)  INT#(1)  CONTROLLER(PHANDLE)  CONTROLLER_DATA(3)
+            interrupt-map = <   0x0 0x0 0x0  0x1  &gic  0x0 0x4 0x1>,
+                            < 0x800 0x0 0x0  0x1  &gic  0x0 0x5 0x1>,
+                            <0x1000 0x0 0x0  0x1  &gic  0x0 0x6 0x1>,
+                            <0x1800 0x0 0x0  0x1  &gic  0x0 0x7 0x1>;
+
+            // PCI_DEVICE(3)  INT#(1)
+            interrupt-map-mask = <0xf800 0x0 0x0  0x7>;
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
new file mode 100644
index 000000000000..48a98dae00de
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml
@@ -0,0 +1,136 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/intel-gw-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: PCIe RC controller on Intel Gateway SoCs
+
+maintainers:
+  - Dilip Kota <eswara.kota@linux.intel.com>
+
+properties:
+  compatible:
+    items:
+      - const: intel,lgm-pcie
+      - const: snps,dw-pcie
+
+  device_type:
+    const: pci
+
+  "#address-cells":
+    const: 3
+
+  "#size-cells":
+    const: 2
+
+  reg:
+    items:
+      - description: Controller control and status registers.
+      - description: PCIe configuration registers.
+      - description: Controller application registers.
+
+  reg-names:
+    items:
+      - const: dbi
+      - const: config
+      - const: app
+
+  ranges:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  phys:
+    maxItems: 1
+
+  phy-names:
+    const: pcie
+
+  reset-gpios:
+    maxItems: 1
+
+  linux,pci-domain: true
+
+  num-lanes:
+    maximum: 2
+    description: Number of lanes to use for this port.
+
+  '#interrupt-cells':
+    const: 1
+
+  interrupt-map-mask:
+    description: Standard PCI IRQ mapping properties.
+
+  interrupt-map:
+    description: Standard PCI IRQ mapping properties.
+
+  max-link-speed:
+    description: Specify PCI Gen for link capability.
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/uint32
+      - enum: [ 1, 2, 3, 4 ]
+      - default: 1
+
+  bus-range:
+    description: Range of bus numbers associated with this controller.
+
+  reset-assert-ms:
+    description: |
+      Delay after asserting reset to the PCIe device.
+    maximum: 500
+    default: 100
+
+required:
+  - compatible
+  - device_type
+  - "#address-cells"
+  - "#size-cells"
+  - reg
+  - reg-names
+  - ranges
+  - resets
+  - clocks
+  - phys
+  - phy-names
+  - reset-gpios
+  - '#interrupt-cells'
+  - interrupt-map
+  - interrupt-map-mask
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    pcie10: pcie@d0e00000 {
+      compatible = "intel,lgm-pcie", "snps,dw-pcie";
+      device_type = "pci";
+      #address-cells = <3>;
+      #size-cells = <2>;
+      reg = <0xd0e00000 0x1000>,
+            <0xd2000000 0x800000>,
+            <0xd0a41000 0x1000>;
+      reg-names = "dbi", "config", "app";
+      linux,pci-domain = <0>;
+      max-link-speed = <4>;
+      bus-range = <0x00 0x08>;
+      #interrupt-cells = <1>;
+      interrupt-map-mask = <0 0 0 0x7>;
+      interrupt-map = <0 0 0 1 &ioapic1 27 1>,
+                      <0 0 0 2 &ioapic1 28 1>,
+                      <0 0 0 3 &ioapic1 29 1>,
+                      <0 0 0 4 &ioapic1 30 1>;
+      ranges = <0x02000000 0 0xd4000000 0xd4000000 0 0x04000000>;
+      resets = <&rcu0 0x50 0>;
+      clocks = <&cgu0 120>;
+      phys = <&cb0phy0>;
+      phy-names = "pcie";
+      reset-assert-ms = <500>;
+      reset-gpios = <&gpio0 3 GPIO_ACTIVE_LOW>;
+      num-lanes = <2>;
+    };
diff --git a/Documentation/devicetree/bindings/pci/pci-thunder-ecam.txt b/Documentation/devicetree/bindings/pci/pci-thunder-ecam.txt
deleted file mode 100644
index f478874b79ce..000000000000
--- a/Documentation/devicetree/bindings/pci/pci-thunder-ecam.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-* ThunderX PCI host controller for pass-1.x silicon
-
-Firmware-initialized PCI host controller to on-chip devices found on
-some Cavium ThunderX processors.  These devices have ECAM-based config
-access, but the BARs are all at fixed addresses.  We handle the fixed
-addresses by synthesizing Enhanced Allocation (EA) capabilities for
-these devices.
-
-The properties and their meanings are identical to those described in
-host-generic-pci.txt except as listed below.
-
-Properties of the host controller node that differ from
-host-generic-pci.txt:
-
-- compatible     : Must be "cavium,pci-host-thunder-ecam"
-
-Example:
-
-	pcie@84b000000000 {
-		compatible = "cavium,pci-host-thunder-ecam";
-		device_type = "pci";
-		msi-parent = <&its>;
-		msi-map = <0 &its 0x30000 0x10000>;
-		bus-range = <0 31>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		#stream-id-cells = <1>;
-		reg = <0x84b0 0x00000000 0 0x02000000>;  /* Configuration space */
-		ranges = <0x03000000 0x8180 0x00000000 0x8180 0x00000000 0x80 0x00000000>; /* mem ranges */
-	};
diff --git a/Documentation/devicetree/bindings/pci/pci-thunder-pem.txt b/Documentation/devicetree/bindings/pci/pci-thunder-pem.txt
deleted file mode 100644
index f131faea3b7c..000000000000
--- a/Documentation/devicetree/bindings/pci/pci-thunder-pem.txt
+++ /dev/null
@@ -1,43 +0,0 @@
-* ThunderX PEM PCIe host controller
-
-Firmware-initialized PCI host controller found on some Cavium
-ThunderX processors.
-
-The properties and their meanings are identical to those described in
-host-generic-pci.txt except as listed below.
-
-Properties of the host controller node that differ from
-host-generic-pci.txt:
-
-- compatible     : Must be "cavium,pci-host-thunder-pem"
-
-- reg            : Two entries: First the configuration space for down
-                   stream devices base address and size, as accessed
-                   from the parent bus. Second, the register bank of
-                   the PEM device PCIe bridge.
-
-Example:
-
-    pci@87e0,c2000000 {
-	compatible = "cavium,pci-host-thunder-pem";
-	device_type = "pci";
-	msi-parent = <&its>;
-	msi-map = <0 &its 0x10000 0x10000>;
-	bus-range = <0x8f 0xc7>;
-	#size-cells = <2>;
-	#address-cells = <3>;
-
-	reg = <0x8880 0x8f000000 0x0 0x39000000>,  /* Configuration space */
-	      <0x87e0 0xc2000000 0x0 0x00010000>; /* PEM space */
-	ranges = <0x01000000 0x00 0x00020000 0x88b0 0x00020000 0x00 0x00010000>, /* I/O */
-		 <0x03000000 0x00 0x10000000 0x8890 0x10000000 0x0f 0xf0000000>, /* mem64 */
-		 <0x43000000 0x10 0x00000000 0x88a0 0x00000000 0x10 0x00000000>, /* mem64-pref */
-		 <0x03000000 0x87e0 0xc2f00000 0x87e0 0xc2000000 0x00 0x00100000>; /* mem64 PEM BAR4 */
-
-	#interrupt-cells = <1>;
-	interrupt-map-mask = <0 0 0 7>;
-	interrupt-map = <0 0 0 1 &gic0 0 0 0 24 4>, /* INTA */
-			<0 0 0 2 &gic0 0 0 0 25 4>, /* INTB */
-			<0 0 0 3 &gic0 0 0 0 26 4>, /* INTC */
-			<0 0 0 4 &gic0 0 0 0 27 4>; /* INTD */
-    };
diff --git a/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi.txt b/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi.txt
deleted file mode 100644
index f3f75bfb42bc..000000000000
--- a/Documentation/devicetree/bindings/pci/plda,xpressrich3-axi.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-* PLDA XpressRICH3-AXI host controller
-
-The PLDA XpressRICH3-AXI host controller can be configured in a manner that
-makes it compliant with the SBSA[1] standard published by ARM Ltd. For those
-scenarios, the host-generic-pci.txt bindings apply with the following additions
-to the compatible property:
-
-Required properties:
- - compatible: should contain "plda,xpressrich3-axi" to identify the IP used.
-
-
-[1] http://infocenter.arm.com/help/topic/com.arm.doc.den0029a/
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.txt b/Documentation/devicetree/bindings/pci/qcom,pcie.txt
index ada80b01bf0c..981b4de12807 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.txt
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.txt
@@ -11,6 +11,7 @@
 			- "qcom,pcie-ipq4019" for ipq4019
 			- "qcom,pcie-ipq8074" for ipq8074
 			- "qcom,pcie-qcs404" for qcs404
+			- "qcom,pcie-sdm845" for sdm845
 
 - reg:
 	Usage: required
@@ -126,6 +127,18 @@
 			- "master_bus"	AXI Master clock
 			- "slave_bus"	AXI Slave clock
 
+-clock-names:
+	Usage: required for sdm845
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "aux"		Auxiliary clock
+			- "cfg"		Configuration clock
+			- "bus_master"	Master AXI clock
+			- "bus_slave"	Slave AXI clock
+			- "slave_q2a"	Slave Q2A clock
+			- "tbu"		PCIe TBU clock
+			- "pipe"	PIPE clock
+
 - resets:
 	Usage: required
 	Value type: <prop-encoded-array>
@@ -188,6 +201,12 @@
 			- "pwr"			PWR reset
 			- "ahb"			AHB reset
 
+- reset-names:
+	Usage: required for sdm845
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "pci"			PCIe core reset
+
 - power-domains:
 	Usage: required for apq8084 and msm8996/apq8096
 	Value type: <prop-encoded-array>
diff --git a/Documentation/devicetree/bindings/pci/versatile.txt b/Documentation/devicetree/bindings/pci/versatile.txt
deleted file mode 100644
index 0a702b13d2ac..000000000000
--- a/Documentation/devicetree/bindings/pci/versatile.txt
+++ /dev/null
@@ -1,59 +0,0 @@
-* ARM Versatile Platform Baseboard PCI interface
-
-PCI host controller found on the ARM Versatile PB board's FPGA.
-
-Required properties:
-- compatible: should contain "arm,versatile-pci" to identify the Versatile PCI
-  controller.
-- reg: base addresses and lengths of the PCI controller. There must be 3
-  entries:
-	- Versatile-specific registers
-	- Self Config space
-	- Config space
-- #address-cells: set to <3>
-- #size-cells: set to <2>
-- device_type: set to "pci"
-- bus-range: set to <0 0xff>
-- ranges: ranges for the PCI memory and I/O regions
-- #interrupt-cells: set to <1>
-- interrupt-map-mask and interrupt-map: standard PCI properties to define
-	the mapping of the PCI interface to interrupt numbers.
-
-Example:
-
-pci-controller@10001000 {
-	compatible = "arm,versatile-pci";
-	device_type = "pci";
-	reg = <0x10001000 0x1000
-	       0x41000000 0x10000
-	       0x42000000 0x100000>;
-	bus-range = <0 0xff>;
-	#address-cells = <3>;
-	#size-cells = <2>;
-	#interrupt-cells = <1>;
-
-	ranges = <0x01000000 0 0x00000000 0x43000000 0 0x00010000   /* downstream I/O */
-		  0x02000000 0 0x50000000 0x50000000 0 0x10000000   /* non-prefetchable memory */
-		  0x42000000 0 0x60000000 0x60000000 0 0x10000000>; /* prefetchable memory */
-
-	interrupt-map-mask = <0x1800 0 0 7>;
-	interrupt-map = <0x1800 0 0 1 &sic 28
-			 0x1800 0 0 2 &sic 29
-			 0x1800 0 0 3 &sic 30
-			 0x1800 0 0 4 &sic 27
-
-			 0x1000 0 0 1 &sic 27
-			 0x1000 0 0 2 &sic 28
-			 0x1000 0 0 3 &sic 29
-			 0x1000 0 0 4 &sic 30
-
-			 0x0800 0 0 1 &sic 30
-			 0x0800 0 0 2 &sic 27
-			 0x0800 0 0 3 &sic 28
-			 0x0800 0 0 4 &sic 29
-
-			 0x0000 0 0 1 &sic 29
-			 0x0000 0 0 2 &sic 30
-			 0x0000 0 0 3 &sic 27
-			 0x0000 0 0 4 &sic 28>;
-};
diff --git a/Documentation/devicetree/bindings/pci/versatile.yaml b/Documentation/devicetree/bindings/pci/versatile.yaml
new file mode 100644
index 000000000000..07a48c27db1f
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/versatile.yaml
@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/versatile.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM Versatile Platform Baseboard PCI interface
+
+maintainers:
+  - Rob Herring <robh@kernel.org>
+
+description: |+
+  PCI host controller found on the ARM Versatile PB board's FPGA.
+
+allOf:
+  - $ref: /schemas/pci/pci-bus.yaml#
+
+properties:
+  compatible:
+    const: arm,versatile-pci
+
+  reg:
+    items:
+      - description: Versatile-specific registers
+      - description: Self Config space
+      - description: Config space
+
+  ranges:
+    maxItems: 3
+
+  "#interrupt-cells": true
+
+  interrupt-map:
+    maxItems: 16
+
+  interrupt-map-mask:
+    items:
+      - const: 0x1800
+      - const: 0
+      - const: 0
+      - const: 7
+
+required:
+  - compatible
+  - reg
+  - ranges
+  - "#interrupt-cells"
+  - interrupt-map
+  - interrupt-map-mask
+
+examples:
+  - |
+    pci@10001000 {
+      compatible = "arm,versatile-pci";
+      device_type = "pci";
+      reg = <0x10001000 0x1000>,
+            <0x41000000 0x10000>,
+            <0x42000000 0x100000>;
+      bus-range = <0 0xff>;
+      #address-cells = <3>;
+      #size-cells = <2>;
+      #interrupt-cells = <1>;
+
+      ranges =
+          <0x01000000 0 0x00000000 0x43000000 0 0x00010000>,  /* downstream I/O */
+          <0x02000000 0 0x50000000 0x50000000 0 0x10000000>,  /* non-prefetchable memory */
+          <0x42000000 0 0x60000000 0x60000000 0 0x10000000>;  /* prefetchable memory */
+
+      interrupt-map-mask = <0x1800 0 0 7>;
+      interrupt-map = <0x1800 0 0 1 &sic 28>,
+          <0x1800 0 0 2 &sic 29>,
+          <0x1800 0 0 3 &sic 30>,
+          <0x1800 0 0 4 &sic 27>,
+
+          <0x1000 0 0 1 &sic 27>,
+          <0x1000 0 0 2 &sic 28>,
+          <0x1000 0 0 3 &sic 29>,
+          <0x1000 0 0 4 &sic 30>,
+
+          <0x0800 0 0 1 &sic 30>,
+          <0x0800 0 0 2 &sic 27>,
+          <0x0800 0 0 3 &sic 28>,
+          <0x0800 0 0 4 &sic 29>,
+
+          <0x0000 0 0 1 &sic 29>,
+          <0x0000 0 0 2 &sic 30>,
+          <0x0000 0 0 3 &sic 27>,
+          <0x0000 0 0 4 &sic 28>;
+    };
+
+
+...
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml
new file mode 100644
index 000000000000..020ef9e4c411
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun4i-a10-usb-phy.yaml
@@ -0,0 +1,105 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun4i-a10-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    enum:
+      - allwinner,sun4i-a10-usb-phy
+      - allwinner,sun7i-a20-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU1 registers
+      - description: PHY PMU2 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu1
+      - const: pmu2
+
+  clocks:
+    maxItems: 1
+    description: USB PHY bus clock
+
+  clock-names:
+    const: usb_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+      - description: USB Host 2 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+      - const: usb2_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+  usb2_vbus-supply:
+    description: Regulator controlling USB2 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun4i-a10-ccu.h>
+    #include <dt-bindings/reset/sun4i-a10-ccu.h>
+
+    usbphy: phy@01c13400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun4i-a10-usb-phy";
+        reg = <0x01c13400 0x10>, <0x01c14800 0x4>, <0x01c1c800 0x4>;
+        reg-names = "phy_ctrl", "pmu1", "pmu2";
+        clocks = <&ccu CLK_USB_PHY>;
+        clock-names = "usb_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>,
+                 <&ccu RST_USB_PHY2>;
+        reset-names = "usb0_reset", "usb1_reset", "usb2_reset";
+        usb0_id_det-gpios = <&pio 7 19 GPIO_ACTIVE_HIGH>;
+        usb0_vbus_det-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>;
+        usb0_vbus-supply = <&reg_usb0_vbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+        usb2_vbus-supply = <&reg_usb2_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun50i-a64-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun50i-a64-usb-phy.yaml
new file mode 100644
index 000000000000..fd6e126fcf18
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun50i-a64-usb-phy.yaml
@@ -0,0 +1,106 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun50i-a64-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A64 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun50i-a64-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU0 registers
+      - description: PHY PMU1 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu0
+      - const: pmu1
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host 0 PHY bus clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb1_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun50i-a64-ccu.h>
+    #include <dt-bindings/reset/sun50i-a64-ccu.h>
+
+    phy@1c19400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun50i-a64-usb-phy";
+        reg = <0x01c19400 0x14>,
+              <0x01c1a800 0x4>,
+              <0x01c1b800 0x4>;
+        reg-names = "phy_ctrl",
+                    "pmu0",
+                    "pmu1";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY1>;
+        clock-names = "usb0_phy",
+                      "usb1_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>;
+        reset-names = "usb0_reset",
+                      "usb1_reset";
+        usb0_id_det-gpios = <&pio 7 9 GPIO_ACTIVE_HIGH>; /* PH9 */
+        usb0_vbus_power-supply = <&usb_power_supply>;
+        usb0_vbus-supply = <&reg_drivevbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb-phy.yaml
new file mode 100644
index 000000000000..7670411002c9
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun50i-h6-usb-phy.yaml
@@ -0,0 +1,105 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun50i-h6-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner H6 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun50i-h6-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU0 registers
+      - description: PHY PMU3 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu0
+      - const: pmu3
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host PHY bus clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb3_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb3_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb3_vbus-supply:
+    description: Regulator controlling USB3 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun50i-h6-ccu.h>
+    #include <dt-bindings/reset/sun50i-h6-ccu.h>
+
+    phy@5100400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun50i-h6-usb-phy";
+        reg = <0x05100400 0x24>,
+              <0x05101800 0x4>,
+              <0x05311800 0x4>;
+        reg-names = "phy_ctrl",
+                    "pmu0",
+                    "pmu3";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY3>;
+        clock-names = "usb0_phy",
+                      "usb3_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY3>;
+        reset-names = "usb0_reset",
+                      "usb3_reset";
+        usb0_id_det-gpios = <&pio 2 6 GPIO_ACTIVE_HIGH>; /* PC6 */
+        usb0_vbus-supply = <&reg_vcc5v>;
+        usb3_vbus-supply = <&reg_vcc5v>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun5i-a13-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun5i-a13-usb-phy.yaml
new file mode 100644
index 000000000000..9b319381d1ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun5i-a13-usb-phy.yaml
@@ -0,0 +1,93 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun5i-a13-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A13 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun5i-a13-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU1 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu1
+
+  clocks:
+    maxItems: 1
+    description: USB OTG PHY bus clock
+
+  clock-names:
+    const: usb_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun5i-ccu.h>
+    #include <dt-bindings/reset/sun5i-ccu.h>
+
+    phy@1c13400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun5i-a13-usb-phy";
+        reg = <0x01c13400 0x10>, <0x01c14800 0x4>;
+        reg-names = "phy_ctrl", "pmu1";
+        clocks = <&ccu CLK_USB_PHY0>;
+        clock-names = "usb_phy";
+        resets = <&ccu RST_USB_PHY0>, <&ccu RST_USB_PHY1>;
+        reset-names = "usb0_reset", "usb1_reset";
+        usb0_id_det-gpios = <&pio 6 2 (GPIO_ACTIVE_HIGH | GPIO_PULL_UP)>; /* PG2 */
+        usb0_vbus_det-gpios = <&pio 6 1 (GPIO_ACTIVE_HIGH | GPIO_PULL_DOWN)>; /* PG1 */
+        usb0_vbus-supply = <&reg_usb0_vbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml
index 230d74f22136..d0b541a461f3 100644
--- a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-mipi-dphy.yaml
@@ -15,7 +15,11 @@ properties:
     const: 0
 
   compatible:
-    const: allwinner,sun6i-a31-mipi-dphy
+    oneOf:
+      - const: allwinner,sun6i-a31-mipi-dphy
+      - items:
+          - const: allwinner,sun50i-a64-mipi-dphy
+          - const: allwinner,sun6i-a31-mipi-dphy
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-usb-phy.yaml
new file mode 100644
index 000000000000..b0ed01bbf3db
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun6i-a31-usb-phy.yaml
@@ -0,0 +1,119 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun6i-a31-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun6i-a31-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU1 registers
+      - description: PHY PMU2 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu1
+      - const: pmu2
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host 0 PHY bus clock
+      - description: USB Host 1 PHY bus clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb1_phy
+      - const: usb2_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+      - description: USB Host 2 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+      - const: usb2_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+  usb2_vbus-supply:
+    description: Regulator controlling USB2 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun6i-a31-ccu.h>
+    #include <dt-bindings/reset/sun6i-a31-ccu.h>
+
+    phy@1c19400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun6i-a31-usb-phy";
+        reg = <0x01c19400 0x10>,
+              <0x01c1a800 0x4>,
+              <0x01c1b800 0x4>;
+        reg-names = "phy_ctrl",
+                    "pmu1",
+                    "pmu2";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY1>,
+                 <&ccu CLK_USB_PHY2>;
+        clock-names = "usb0_phy",
+                      "usb1_phy",
+                      "usb2_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>,
+                 <&ccu RST_USB_PHY2>;
+        reset-names = "usb0_reset",
+                      "usb1_reset",
+                      "usb2_reset";
+        usb0_id_det-gpios = <&pio 0 15 GPIO_ACTIVE_HIGH>; /* PA15 */
+        usb0_vbus_det-gpios = <&pio 0 16 GPIO_ACTIVE_HIGH>; /* PA16 */
+        usb0_vbus_power-supply = <&usb_power_supply>;
+        usb0_vbus-supply = <&reg_drivevbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+        usb2_vbus-supply = <&reg_usb2_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun8i-a23-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun8i-a23-usb-phy.yaml
new file mode 100644
index 000000000000..b0674406f8aa
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun8i-a23-usb-phy.yaml
@@ -0,0 +1,102 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun8i-a23-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A23 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    enum:
+      - allwinner,sun8i-a23-usb-phy
+      - allwinner,sun8i-a33-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU1 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu1
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host 0 PHY bus clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb1_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun8i-a23-a33-ccu.h>
+    #include <dt-bindings/reset/sun8i-a23-a33-ccu.h>
+
+    phy@1c19400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun8i-a23-usb-phy";
+        reg = <0x01c19400 0x10>, <0x01c1a800 0x4>;
+        reg-names = "phy_ctrl", "pmu1";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY1>;
+        clock-names = "usb0_phy",
+                      "usb1_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>;
+        reset-names = "usb0_reset",
+                      "usb1_reset";
+        usb0_id_det-gpios = <&pio 1 3 GPIO_ACTIVE_HIGH>; /* PB3 */
+        usb0_vbus_power-supply = <&usb_power_supply>;
+        usb0_vbus-supply = <&reg_drivevbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun8i-a83t-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun8i-a83t-usb-phy.yaml
new file mode 100644
index 000000000000..48dc9c834a9b
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun8i-a83t-usb-phy.yaml
@@ -0,0 +1,122 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun8i-a83t-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A83t USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun8i-a83t-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU1 registers
+      - description: PHY PMU2 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu1
+      - const: pmu2
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host 0 PHY bus clock
+      - description: USB Host 1 PHY bus clock
+      - description: USB HSIC 12MHz clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb1_phy
+      - const: usb2_phy
+      - const: usb2_hsic_12M
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+      - description: USB Host 2 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+      - const: usb2_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+  usb2_vbus-supply:
+    description: Regulator controlling USB2 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun8i-a83t-ccu.h>
+    #include <dt-bindings/reset/sun8i-a83t-ccu.h>
+
+    phy@1c19400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun8i-a83t-usb-phy";
+        reg = <0x01c19400 0x10>,
+              <0x01c1a800 0x14>,
+              <0x01c1b800 0x14>;
+        reg-names = "phy_ctrl",
+                    "pmu1",
+                    "pmu2";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY1>,
+                 <&ccu CLK_USB_HSIC>,
+                 <&ccu CLK_USB_HSIC_12M>;
+        clock-names = "usb0_phy",
+                      "usb1_phy",
+                      "usb2_phy",
+                      "usb2_hsic_12M";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>,
+                 <&ccu RST_USB_HSIC>;
+        reset-names = "usb0_reset",
+                      "usb1_reset",
+                      "usb2_reset";
+        usb0_id_det-gpios = <&pio 7 11 GPIO_ACTIVE_HIGH>; /* PH11 */
+        usb0_vbus_power-supply = <&usb_power_supply>;
+        usb0_vbus-supply = <&reg_drivevbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+        usb2_vbus-supply = <&reg_usb2_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun8i-h3-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun8i-h3-usb-phy.yaml
new file mode 100644
index 000000000000..60c344585276
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun8i-h3-usb-phy.yaml
@@ -0,0 +1,137 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun8i-h3-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner H3 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun8i-h3-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU0 registers
+      - description: PHY PMU1 registers
+      - description: PHY PMU2 registers
+      - description: PHY PMU3 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu0
+      - const: pmu1
+      - const: pmu2
+      - const: pmu3
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host 0 PHY bus clock
+      - description: USB Host 1 PHY bus clock
+      - description: USB Host 2 PHY bus clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb1_phy
+      - const: usb2_phy
+      - const: usb3_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+      - description: USB Host 2 Controller reset
+      - description: USB Host 3 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+      - const: usb2_reset
+      - const: usb3_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+  usb2_vbus-supply:
+    description: Regulator controlling USB2 Host controller
+
+  usb3_vbus-supply:
+    description: Regulator controlling USB3 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun8i-h3-ccu.h>
+    #include <dt-bindings/reset/sun8i-h3-ccu.h>
+
+    phy@1c19400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun8i-h3-usb-phy";
+        reg = <0x01c19400 0x2c>,
+              <0x01c1a800 0x4>,
+              <0x01c1b800 0x4>,
+              <0x01c1c800 0x4>,
+              <0x01c1d800 0x4>;
+        reg-names = "phy_ctrl",
+                    "pmu0",
+                    "pmu1",
+                    "pmu2",
+                    "pmu3";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY1>,
+                 <&ccu CLK_USB_PHY2>,
+                 <&ccu CLK_USB_PHY3>;
+        clock-names = "usb0_phy",
+                      "usb1_phy",
+                      "usb2_phy",
+                      "usb3_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>,
+                 <&ccu RST_USB_PHY2>,
+                 <&ccu RST_USB_PHY3>;
+        reset-names = "usb0_reset",
+                      "usb1_reset",
+                      "usb2_reset",
+                      "usb3_reset";
+        usb0_id_det-gpios = <&pio 6 12 GPIO_ACTIVE_HIGH>; /* PG12 */
+        usb0_vbus-supply = <&reg_usb0_vbus>;
+        usb1_vbus-supply = <&reg_usb1_vbus>;
+        usb2_vbus-supply = <&reg_usb2_vbus>;
+        usb3_vbus-supply = <&reg_usb3_vbus>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun8i-r40-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun8i-r40-usb-phy.yaml
new file mode 100644
index 000000000000..a2bb36790fbd
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun8i-r40-usb-phy.yaml
@@ -0,0 +1,119 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun8i-r40-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner R40 USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun8i-r40-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU0 registers
+      - description: PHY PMU1 registers
+      - description: PHY PMU2 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu0
+      - const: pmu1
+      - const: pmu2
+
+  clocks:
+    items:
+      - description: USB OTG PHY bus clock
+      - description: USB Host 0 PHY bus clock
+      - description: USB Host 1 PHY bus clock
+
+  clock-names:
+    items:
+      - const: usb0_phy
+      - const: usb1_phy
+      - const: usb2_phy
+
+  resets:
+    items:
+      - description: USB OTG reset
+      - description: USB Host 1 Controller reset
+      - description: USB Host 2 Controller reset
+
+  reset-names:
+    items:
+      - const: usb0_reset
+      - const: usb1_reset
+      - const: usb2_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+  usb1_vbus-supply:
+    description: Regulator controlling USB1 Host controller
+
+  usb2_vbus-supply:
+    description: Regulator controlling USB2 Host controller
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun8i-r40-ccu.h>
+    #include <dt-bindings/reset/sun8i-r40-ccu.h>
+
+    phy@1c13400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun8i-r40-usb-phy";
+        reg = <0x01c13400 0x14>,
+              <0x01c14800 0x4>,
+              <0x01c19800 0x4>,
+              <0x01c1c800 0x4>;
+        reg-names = "phy_ctrl",
+                    "pmu0",
+                    "pmu1",
+                    "pmu2";
+        clocks = <&ccu CLK_USB_PHY0>,
+                 <&ccu CLK_USB_PHY1>,
+                 <&ccu CLK_USB_PHY2>;
+        clock-names = "usb0_phy",
+                      "usb1_phy",
+                      "usb2_phy";
+        resets = <&ccu RST_USB_PHY0>,
+                 <&ccu RST_USB_PHY1>,
+                 <&ccu RST_USB_PHY2>;
+        reset-names = "usb0_reset",
+                      "usb1_reset",
+                      "usb2_reset";
+        usb1_vbus-supply = <&reg_vcc5v0>;
+        usb2_vbus-supply = <&reg_vcc5v0>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/allwinner,sun8i-v3s-usb-phy.yaml b/Documentation/devicetree/bindings/phy/allwinner,sun8i-v3s-usb-phy.yaml
new file mode 100644
index 000000000000..eadfd0c9493c
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/allwinner,sun8i-v3s-usb-phy.yaml
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/allwinner,sun8i-v3s-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner V3s USB PHY Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#phy-cells":
+    const: 1
+
+  compatible:
+    const: allwinner,sun8i-v3s-usb-phy
+
+  reg:
+    items:
+      - description: PHY Control registers
+      - description: PHY PMU0 registers
+
+  reg-names:
+    items:
+      - const: phy_ctrl
+      - const: pmu0
+
+  clocks:
+    maxItems: 1
+    description: USB OTG PHY bus clock
+
+  clock-names:
+    const: usb0_phy
+
+  resets:
+    maxItems: 1
+    description: USB OTG reset
+
+  reset-names:
+    const: usb0_reset
+
+  usb0_id_det-gpios:
+    description: GPIO to the USB OTG ID pin
+
+  usb0_vbus_det-gpios:
+    description: GPIO to the USB OTG VBUS detect pin
+
+  usb0_vbus_power-supply:
+    description: Power supply to detect the USB OTG VBUS
+
+  usb0_vbus-supply:
+    description: Regulator controlling USB OTG VBUS
+
+required:
+  - "#phy-cells"
+  - compatible
+  - clocks
+  - clock-names
+  - reg
+  - reg-names
+  - resets
+  - reset-names
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/clock/sun8i-v3s-ccu.h>
+    #include <dt-bindings/reset/sun8i-v3s-ccu.h>
+
+    phy@1c19400 {
+        #phy-cells = <1>;
+        compatible = "allwinner,sun8i-v3s-usb-phy";
+        reg = <0x01c19400 0x2c>,
+              <0x01c1a800 0x4>;
+        reg-names = "phy_ctrl",
+                    "pmu0";
+        clocks = <&ccu CLK_USB_PHY0>;
+        clock-names = "usb0_phy";
+        resets = <&ccu RST_USB_PHY0>;
+        reset-names = "usb0_reset";
+        usb0_id_det-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>;
+    };
diff --git a/Documentation/devicetree/bindings/phy/intel,lgm-emmc-phy.yaml b/Documentation/devicetree/bindings/phy/intel,lgm-emmc-phy.yaml
index ff7959c21af0..0ccee64c6962 100644
--- a/Documentation/devicetree/bindings/phy/intel,lgm-emmc-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/intel,lgm-emmc-phy.yaml
@@ -45,8 +45,10 @@ examples:
     sysconf: chiptop@e0200000 {
       compatible = "intel,lgm-syscon", "syscon";
       reg = <0xe0200000 0x100>;
+      #address-cells = <1>;
+      #size-cells = <1>;
 
-      emmc-phy: emmc-phy@a8 {
+      emmc_phy: emmc-phy@a8 {
         compatible = "intel,lgm-emmc-phy";
         reg = <0x00a8 0x10>;
         clocks = <&emmc>;
diff --git a/Documentation/devicetree/bindings/phy/rockchip,px30-dsi-dphy.yaml b/Documentation/devicetree/bindings/phy/rockchip,px30-dsi-dphy.yaml
index 476c56a1dc8c..72aca81e8959 100644
--- a/Documentation/devicetree/bindings/phy/rockchip,px30-dsi-dphy.yaml
+++ b/Documentation/devicetree/bindings/phy/rockchip,px30-dsi-dphy.yaml
@@ -58,7 +58,7 @@ additionalProperties: false
 examples:
   - |
     dsi_dphy: phy@ff2e0000 {
-        compatible = "rockchip,px30-video-phy";
+        compatible = "rockchip,px30-dsi-dphy";
         reg = <0x0 0xff2e0000 0x0 0x10000>;
         clocks = <&pmucru 13>, <&cru 12>;
         clock-names = "ref", "pclk";
diff --git a/Documentation/devicetree/bindings/phy/samsung-phy.txt b/Documentation/devicetree/bindings/phy/samsung-phy.txt
index 1c40ccd40ce4..7510830a79bd 100644
--- a/Documentation/devicetree/bindings/phy/samsung-phy.txt
+++ b/Documentation/devicetree/bindings/phy/samsung-phy.txt
@@ -1,4 +1,4 @@
-Samsung S5P/EXYNOS SoC series MIPI CSIS/DSIM DPHY
+Samsung S5P/Exynos SoC series MIPI CSIS/DSIM DPHY
 -------------------------------------------------
 
 Required properties:
@@ -27,7 +27,7 @@ the PHY specifier identifies the PHY and its meaning is as follows:
 supports additional fifth PHY:
   4 - MIPI CSIS 2.
 
-Samsung EXYNOS SoC series Display Port PHY
+Samsung Exynos SoC series Display Port PHY
 -------------------------------------------------
 
 Required properties:
@@ -38,7 +38,7 @@ Required properties:
 		      control pmu registers for power isolation.
 - #phy-cells : from the generic PHY bindings, must be 0;
 
-Samsung S5P/EXYNOS SoC series USB PHY
+Samsung S5P/Exynos SoC series USB PHY
 -------------------------------------------------
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt b/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
deleted file mode 100644
index f2e120af17f0..000000000000
--- a/Documentation/devicetree/bindings/phy/sun4i-usb-phy.txt
+++ /dev/null
@@ -1,68 +0,0 @@
-Allwinner sun4i USB PHY
------------------------
-
-Required properties:
-- compatible : should be one of
-  * allwinner,sun4i-a10-usb-phy
-  * allwinner,sun5i-a13-usb-phy
-  * allwinner,sun6i-a31-usb-phy
-  * allwinner,sun7i-a20-usb-phy
-  * allwinner,sun8i-a23-usb-phy
-  * allwinner,sun8i-a33-usb-phy
-  * allwinner,sun8i-a83t-usb-phy
-  * allwinner,sun8i-h3-usb-phy
-  * allwinner,sun8i-r40-usb-phy
-  * allwinner,sun8i-v3s-usb-phy
-  * allwinner,sun50i-a64-usb-phy
-  * allwinner,sun50i-h6-usb-phy
-- reg : a list of offset + length pairs
-- reg-names :
-  * "phy_ctrl"
-  * "pmu0" for H3, V3s, A64 or H6
-  * "pmu1"
-  * "pmu2" for sun4i, sun6i, sun7i, sun8i-a83t or sun8i-h3
-  * "pmu3" for sun8i-h3 or sun50i-h6
-- #phy-cells : from the generic phy bindings, must be 1
-- clocks : phandle + clock specifier for the phy clocks
-- clock-names :
-  * "usb_phy" for sun4i, sun5i or sun7i
-  * "usb0_phy", "usb1_phy" and "usb2_phy" for sun6i
-  * "usb0_phy", "usb1_phy" for sun8i
-  * "usb0_phy", "usb1_phy", "usb2_phy" and "usb2_hsic_12M" for sun8i-a83t
-  * "usb0_phy", "usb1_phy", "usb2_phy" and "usb3_phy" for sun8i-h3
-  * "usb0_phy" and "usb3_phy" for sun50i-h6
-- resets : a list of phandle + reset specifier pairs
-- reset-names :
-  * "usb0_reset"
-  * "usb1_reset"
-  * "usb2_reset" for sun4i, sun6i, sun7i, sun8i-a83t or sun8i-h3
-  * "usb3_reset" for sun8i-h3 and sun50i-h6
-
-Optional properties:
-- usb0_id_det-gpios : gpio phandle for reading the otg id pin value
-- usb0_vbus_det-gpios : gpio phandle for detecting the presence of usb0 vbus
-- usb0_vbus_power-supply: power-supply phandle for usb0 vbus presence detect
-- usb0_vbus-supply : regulator phandle for controller usb0 vbus
-- usb1_vbus-supply : regulator phandle for controller usb1 vbus
-- usb2_vbus-supply : regulator phandle for controller usb2 vbus
-- usb3_vbus-supply : regulator phandle for controller usb3 vbus
-
-Example:
-	usbphy: phy@01c13400 {
-		#phy-cells = <1>;
-		compatible = "allwinner,sun4i-a10-usb-phy";
-		/* phy base regs, phy1 pmu reg, phy2 pmu reg */
-		reg = <0x01c13400 0x10 0x01c14800 0x4 0x01c1c800 0x4>;
-		reg-names = "phy_ctrl", "pmu1", "pmu2";
-		clocks = <&usb_clk 8>;
-		clock-names = "usb_phy";
-		resets = <&usb_clk 0>, <&usb_clk 1>, <&usb_clk 2>;
-		reset-names = "usb0_reset", "usb1_reset", "usb2_reset";
-		pinctrl-names = "default";
-		pinctrl-0 = <&usb0_id_detect_pin>, <&usb0_vbus_detect_pin>;
-		usb0_id_det-gpios = <&pio 7 19 GPIO_ACTIVE_HIGH>; /* PH19 */
-		usb0_vbus_det-gpios = <&pio 7 22 GPIO_ACTIVE_HIGH>; /* PH22 */
-		usb0_vbus-supply = <&reg_usb0_vbus>;
-		usb1_vbus-supply = <&reg_usb1_vbus>;
-		usb2_vbus-supply = <&reg_usb2_vbus>;
-	};
diff --git a/Documentation/devicetree/bindings/power/supply/battery.txt b/Documentation/devicetree/bindings/power/supply/battery.txt
index 5c913d4cf36c..3049cf88bdcf 100644
--- a/Documentation/devicetree/bindings/power/supply/battery.txt
+++ b/Documentation/devicetree/bindings/power/supply/battery.txt
@@ -35,6 +35,10 @@ Optional Properties:
    for each of the battery capacity lookup table. The first temperature value
    specifies the OCV table 0, and the second temperature value specifies the
    OCV table 1, and so on.
+ - resistance-temp-table: An array providing the temperature in degree Celsius
+   and corresponding battery internal resistance percent, which is used to look
+   up the resistance percent according to current temperature to get a accurate
+   batterty internal resistance in different temperatures.
 
 Battery properties are named, where possible, for the corresponding
 elements in enum power_supply_property, defined in
@@ -61,6 +65,7 @@ Example:
 		ocv-capacity-table-0 = <4185000 100>, <4113000 95>, <4066000 90>, ...;
 		ocv-capacity-table-1 = <4200000 100>, <4185000 95>, <4113000 90>, ...;
 		ocv-capacity-table-2 = <4250000 100>, <4200000 95>, <4185000 90>, ...;
+		resistance-temp-table = <20 100>, <10 90>, <0 80>, <(-10) 60>;
 	};
 
 	charger: charger@11 {
diff --git a/Documentation/devicetree/bindings/power/supply/bq25890.txt b/Documentation/devicetree/bindings/power/supply/bq25890.txt
index dc0568933359..dc9c8f76e06c 100644
--- a/Documentation/devicetree/bindings/power/supply/bq25890.txt
+++ b/Documentation/devicetree/bindings/power/supply/bq25890.txt
@@ -1,11 +1,14 @@
 Binding for TI bq25890 Li-Ion Charger
 
-This driver will support the bq25896 and the bq25890. There are other ICs
-in the same family but those have not been tested.
+This driver will support the bq25892, the bq25896 and the bq25890. There are
+other ICs in the same family but those have not been tested.
 
 Required properties:
 - compatible: Should contain one of the following:
     * "ti,bq25890"
+    * "ti,bq25892"
+    * "ti,bq25895"
+    * "ti,bq25896"
 - reg: integer, i2c address of the device.
 - ti,battery-regulation-voltage: integer, maximum charging voltage (in uV);
 - ti,charge-current: integer, maximum charging current (in uA);
diff --git a/Documentation/devicetree/bindings/power/supply/max17040_battery.txt b/Documentation/devicetree/bindings/power/supply/max17040_battery.txt
new file mode 100644
index 000000000000..4e0186b8380f
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/max17040_battery.txt
@@ -0,0 +1,33 @@
+max17040_battery
+~~~~~~~~~~~~~~~~
+
+Required properties :
+ - compatible : "maxim,max17040" or "maxim,max77836-battery"
+ - reg: i2c slave address
+
+Optional properties :
+- maxim,alert-low-soc-level :	The alert threshold that sets the state of
+				charge level (%) where an interrupt is
+				generated. Can be configured from 1 up to 32
+				(%). If skipped the power up default value of
+				4 (%) will be used.
+- interrupts : 			Interrupt line see Documentation/devicetree/
+				bindings/interrupt-controller/interrupts.txt
+- wakeup-source :		This device has wakeup capabilities. Use this
+				property to use alert low SOC level interrupt
+				as wake up source.
+
+Optional properties support interrupt functionality for alert low state of
+charge level, present in some ICs in the same family, and should be used with
+compatible "maxim,max77836-battery".
+
+Example:
+
+	battery-fuel-gauge@36 {
+		compatible = "maxim,max77836-battery";
+		reg = <0x36>;
+		maxim,alert-low-soc-level = <10>;
+		interrupt-parent = <&gpio7>;
+		interrupts = <2 IRQ_TYPE_EDGE_FALLING>;
+		wakeup-source;
+	};
diff --git a/Documentation/devicetree/bindings/power/supply/max17042_battery.txt b/Documentation/devicetree/bindings/power/supply/max17042_battery.txt
index 3f3894aaeebc..f34c5daae9af 100644
--- a/Documentation/devicetree/bindings/power/supply/max17042_battery.txt
+++ b/Documentation/devicetree/bindings/power/supply/max17042_battery.txt
@@ -2,7 +2,11 @@ max17042_battery
 ~~~~~~~~~~~~~~~~
 
 Required properties :
- - compatible : "maxim,max17042"
+ - compatible : one of the following
+ * "maxim,max17042"
+ * "maxim,max17047"
+ * "maxim,max17050"
+ * "maxim,max17055"
 
 Optional properties :
  - maxim,rsns-microohm : Resistance of rsns resistor in micro Ohms
diff --git a/Documentation/devicetree/bindings/power/supply/sc27xx-fg.txt b/Documentation/devicetree/bindings/power/supply/sc27xx-fg.txt
index 0a5705b8b592..b6359b590383 100644
--- a/Documentation/devicetree/bindings/power/supply/sc27xx-fg.txt
+++ b/Documentation/devicetree/bindings/power/supply/sc27xx-fg.txt
@@ -13,6 +13,8 @@ Required properties:
 - io-channel-names: Should be "bat-temp" or "charge-vol".
 - nvmem-cells: A phandle to the calibration cells provided by eFuse device.
 - nvmem-cell-names: Should be "fgu_calib".
+- sprd,calib-resistance-micro-ohms: Specify the real resistance of coulomb counter
+  chip in micro Ohms.
 - monitored-battery: Phandle of battery characteristics devicetree node.
   See Documentation/devicetree/bindings/power/supply/battery.txt
 
@@ -52,5 +54,6 @@ Example:
 			nvmem-cells = <&fgu_calib>;
 			nvmem-cell-names = "fgu_calib";
 			monitored-battery = <&bat>;
+			sprd,calib-resistance-micro-ohms = <21500>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.txt b/Documentation/devicetree/bindings/pwm/mxs-pwm.txt
index 1b06f86a7091..a1b8a482f873 100644
--- a/Documentation/devicetree/bindings/pwm/mxs-pwm.txt
+++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.txt
@@ -3,7 +3,7 @@ Freescale MXS PWM controller
 Required properties:
 - compatible: should be "fsl,imx23-pwm"
 - reg: physical base address and length of the controller's registers
-- #pwm-cells: should be 2. See pwm.yaml in this directory for a description of
+- #pwm-cells: should be 3. See pwm.yaml in this directory for a description of
   the cells format.
 - fsl,pwm-number: the number of PWM devices
 
@@ -12,6 +12,6 @@ Example:
 pwm: pwm@80064000 {
 	compatible = "fsl,imx28-pwm", "fsl,imx23-pwm";
 	reg = <0x80064000 0x2000>;
-	#pwm-cells = <2>;
+	#pwm-cells = <3>;
 	fsl,pwm-number = <8>;
 };
diff --git a/Documentation/devicetree/bindings/remoteproc/mtk,scp.txt b/Documentation/devicetree/bindings/remoteproc/mtk,scp.txt
new file mode 100644
index 000000000000..3ba668bab14b
--- /dev/null
+++ b/Documentation/devicetree/bindings/remoteproc/mtk,scp.txt
@@ -0,0 +1,36 @@
+Mediatek SCP Bindings
+----------------------------------------
+
+This binding provides support for ARM Cortex M4 Co-processor found on some
+Mediatek SoCs.
+
+Required properties:
+- compatible		Should be "mediatek,mt8183-scp"
+- reg			Should contain the address ranges for the two memory
+			regions, SRAM and CFG.
+- reg-names		Contains the corresponding names for the two memory
+			regions. These should be named "sram" & "cfg".
+- clocks		Clock for co-processor (See: ../clock/clock-bindings.txt)
+- clock-names		Contains the corresponding name for the clock. This
+			should be named "main".
+
+Subnodes
+--------
+
+Subnodes of the SCP represent rpmsg devices. The names of the devices are not
+important. The properties of these nodes are defined by the individual bindings
+for the rpmsg devices - but must contain the following property:
+
+- mtk,rpmsg-name	Contains the name for the rpmsg device. Used to match
+			the subnode to rpmsg device announced by SCP.
+
+Example:
+
+	scp: scp@10500000 {
+		compatible = "mediatek,mt8183-scp";
+		reg = <0 0x10500000 0 0x80000>,
+		      <0 0x105c0000 0 0x5000>;
+		reg-names = "sram", "cfg";
+		clocks = <&infracfg CLK_INFRA_SCPSYS>;
+		clock-names = "main";
+	};
diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.txt b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.txt
index 292dfda9770d..9938918b2fea 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,adsp.txt
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,adsp.txt
@@ -10,11 +10,17 @@ on the Qualcomm ADSP Hexagon core.
 		    "qcom,msm8974-adsp-pil"
 		    "qcom,msm8996-adsp-pil"
 		    "qcom,msm8996-slpi-pil"
+		    "qcom,msm8998-adsp-pas"
+		    "qcom,msm8998-slpi-pas"
 		    "qcom,qcs404-adsp-pas"
 		    "qcom,qcs404-cdsp-pas"
 		    "qcom,qcs404-wcss-pas"
 		    "qcom,sdm845-adsp-pas"
 		    "qcom,sdm845-cdsp-pas"
+		    "qcom,sm8150-adsp-pas"
+		    "qcom,sm8150-cdsp-pas"
+		    "qcom,sm8150-mpss-pas"
+		    "qcom,sm8150-slpi-pas"
 
 - interrupts-extended:
 	Usage: required
@@ -29,12 +35,18 @@ on the Qualcomm ADSP Hexagon core.
 	qcom,msm8974-adsp-pil:
 	qcom,msm8996-adsp-pil:
 	qcom,msm8996-slpi-pil:
+	qcom,msm8998-adsp-pas:
+	qcom,msm8998-slpi-pas:
 	qcom,qcs404-adsp-pas:
 	qcom,qcs404-cdsp-pas:
 	qcom,sdm845-adsp-pas:
 	qcom,sdm845-cdsp-pas:
+	qcom,sm8150-adsp-pas:
+	qcom,sm8150-cdsp-pas:
+	qcom,sm8150-slpi-pas:
 		    must be "wdog", "fatal", "ready", "handover", "stop-ack"
 	qcom,qcs404-wcss-pas:
+	qcom,sm8150-mpss-pas:
 		    must be "wdog", "fatal", "ready", "handover", "stop-ack",
 		    "shutdown-ack"
 
@@ -67,6 +79,38 @@ on the Qualcomm ADSP Hexagon core.
 	Definition: reference to the px regulator to be held on behalf of the
 		    booting Hexagon core
 
+- power-domains:
+	Usage: required
+	Value type: <phandle>
+	Definition: reference to power-domains that match the power-domain-names
+
+- power-domain-names:
+	Usage: required
+	Value type: <stringlist>
+	Definition: The power-domains needed depend on the compatible string:
+	qcom,msm8974-adsp-pil:
+	qcom,msm8996-adsp-pil:
+	qcom,msm8998-adsp-pas:
+		    must be "cx"
+	qcom,msm8996-slpi-pil:
+		    must be "ss_cx"
+	qcom,msm8998-slpi-pas:
+		    must be "ssc_cx"
+	qcom,qcs404-adsp-pas:
+		    must be "lpi_cx"
+	qcom,qcs404-cdsp-pas:
+	qcom,qcs404-wcss-pas:
+		    must be "mx"
+	qcom,sdm845-adsp-pas:
+	qcom,sdm845-cdsp-pas:
+	qcom,sm8150-adsp-pas:
+	qcom,sm8150-cdsp-pas:
+		    must be "cx", "load_state"
+	qcom,sm8150-mpss-pas:
+		    must be "cx", "load_state", "mss"
+	qcom,sm8150-slpi-pas:
+		    must be "lcx", "lmx", "load_state"
+
 - memory-region:
 	Usage: required
 	Value type: <phandle>
diff --git a/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt b/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt
index c416746f93cf..88dfa3fc15f7 100644
--- a/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt
+++ b/Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt
@@ -13,6 +13,7 @@ on the Qualcomm Hexagon core.
 		    "qcom,msm8974-mss-pil"
 		    "qcom,msm8996-mss-pil"
 		    "qcom,msm8998-mss-pil"
+		    "qcom,sc7180-mss-pil"
 		    "qcom,sdm845-mss-pil"
 
 - reg:
@@ -43,6 +44,7 @@ on the Qualcomm Hexagon core.
 		    must be "wdog", "fatal", "ready", "handover", "stop-ack"
 	qcom,msm8996-mss-pil:
 	qcom,msm8998-mss-pil:
+	qcom,sc7180-mss-pil:
 	qcom,sdm845-mss-pil:
 		    must be "wdog", "fatal", "ready", "handover", "stop-ack",
 		    "shutdown-ack"
@@ -75,6 +77,9 @@ on the Qualcomm Hexagon core.
 	qcom,msm8998-mss-pil:
 		    must be "iface", "bus", "mem", "xo", "gpll0_mss",
 		    "snoc_axi", "mnoc_axi", "qdss"
+	qcom,sc7180-mss-pil:
+		    must be "iface", "bus", "xo", "snoc_axi", "mnoc_axi",
+		    "mss_crypto", "mss_nav", "nav"
 	qcom,sdm845-mss-pil:
 		    must be "iface", "bus", "mem", "xo", "gpll0_mss",
 		    "snoc_axi", "mnoc_axi", "prng"
@@ -86,7 +91,7 @@ on the Qualcomm Hexagon core.
 		    reference to the list of 3 reset-controllers for the
 		    wcss sub-system
 		    reference to the list of 2 reset-controllers for the modem
-		    sub-system on SDM845 SoCs
+		    sub-system on SC7180, SDM845 SoCs
 
 - reset-names:
 	Usage: required
@@ -95,7 +100,7 @@ on the Qualcomm Hexagon core.
 		    must be "wcss_aon_reset", "wcss_reset", "wcss_q6_reset"
 		    for the wcss sub-system
 		    must be "mss_restart", "pdc_reset" for the modem
-		    sub-system on SDM845 SoCs
+		    sub-system on SC7180, SDM845 SoCs
 
 For the compatible strings below the following supplies are required:
   "qcom,q6v5-pil"
@@ -144,6 +149,7 @@ For the compatible string below the following supplies are required:
 	qcom,msm8996-mss-pil:
 	qcom,msm8998-mss-pil:
 		    must be "cx", "mx"
+	qcom,sc7180-mss-pil:
 	qcom,sdm845-mss-pil:
 		    must be "cx", "mx", "mss", "load_state"
 
@@ -165,6 +171,19 @@ For the compatible string below the following supplies are required:
 		    by the three offsets within syscon for q6, modem and nc
 		    halt registers.
 
+For the compatible strings below the following phandle references are required:
+  "qcom,sc7180-mss-pil"
+- qcom,halt-nav-regs:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: reference to a list of 2 phandles with one offset each for
+		    the modem sub-system running on SC7180 SoC. The first
+		    phandle reference is to the mss clock node followed by the
+		    offset within register space for nav halt register. The
+		    second phandle reference is to a syscon representing TCSR
+		    followed by the offset within syscon for conn_box_spare0
+		    register.
+
 = SUBNODES:
 The Hexagon node must contain two subnodes, named "mba" and "mpss" representing
 the memory regions used by the Hexagon firmware. Each sub-node must contain:
diff --git a/Documentation/devicetree/bindings/reset/allwinner,sun6i-a31-clock-reset.yaml b/Documentation/devicetree/bindings/reset/allwinner,sun6i-a31-clock-reset.yaml
new file mode 100644
index 000000000000..001c0d2a8c1f
--- /dev/null
+++ b/Documentation/devicetree/bindings/reset/allwinner,sun6i-a31-clock-reset.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/reset/allwinner,sun6i-a31-clock-reset.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A31 Peripheral Reset Controller Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+deprecated: true
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - allwinner,sun6i-a31-ahb1-reset
+          - allwinner,sun6i-a31-clock-reset
+
+  # The PRCM on the A31 and A23 will have the reg property missing,
+  # since it's set at the upper level node, and will be validated by
+  # PRCM's schema. Make sure we only validate standalone nodes.
+  required:
+    - compatible
+    - reg
+
+properties:
+  "#reset-cells":
+    const: 1
+    description: >
+      This additional argument passed to that reset controller is the
+      offset of the bit controlling this particular reset line in the
+      register.
+
+  compatible:
+    enum:
+      - allwinner,sun6i-a31-ahb1-reset
+      - allwinner,sun6i-a31-clock-reset
+
+  reg:
+    maxItems: 1
+
+required:
+  - "#reset-cells"
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    ahb1_rst: reset@1c202c0 {
+        #reset-cells = <1>;
+        compatible = "allwinner,sun6i-a31-ahb1-reset";
+        reg = <0x01c202c0 0xc>;
+    };
+
+  - |
+    apbs_rst: reset@80014b0 {
+        #reset-cells = <1>;
+        compatible = "allwinner,sun6i-a31-clock-reset";
+        reg = <0x080014b0 0x4>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/reset/allwinner,sunxi-clock-reset.txt b/Documentation/devicetree/bindings/reset/allwinner,sunxi-clock-reset.txt
deleted file mode 100644
index 4ca66c96fe97..000000000000
--- a/Documentation/devicetree/bindings/reset/allwinner,sunxi-clock-reset.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-Allwinner sunxi Peripheral Reset Controller
-===========================================
-
-Please also refer to reset.txt in this directory for common reset
-controller binding usage.
-
-Required properties:
-- compatible: Should be one of the following:
-  "allwinner,sun6i-a31-ahb1-reset"
-  "allwinner,sun6i-a31-clock-reset"
-- reg: should be register base and length as documented in the
-  datasheet
-- #reset-cells: 1, see below
-
-example:
-
-ahb1_rst: reset@1c202c0 {
-	#reset-cells = <1>;
-	compatible = "allwinner,sun6i-a31-ahb1-reset";
-	reg = <0x01c202c0 0xc>;
-};
diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
deleted file mode 100644
index 5d3791e789c6..000000000000
--- a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-Atmel AT91RM9200 Real Time Clock
-
-Required properties:
-- compatible: should be: "atmel,at91rm9200-rtc" or "atmel,at91sam9x5-rtc"
-- reg: physical base address of the controller and length of memory mapped
-  region.
-- interrupts: rtc alarm/event interrupt
-- clocks: phandle to input clock.
-
-Example:
-
-rtc@fffffe00 {
-	compatible = "atmel,at91rm9200-rtc";
-	reg = <0xfffffe00 0x100>;
-	interrupts = <1 4 7>;
-	clocks = <&clk32k>;
-};
diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
new file mode 100644
index 000000000000..02bbfe726c62
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.yaml
@@ -0,0 +1,49 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/atmel,at91rm9200-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Atmel AT91 RTC Device Tree Bindings
+
+allOf:
+  - $ref: "rtc.yaml#"
+
+maintainers:
+  - Alexandre Belloni <alexandre.belloni@bootlin.com>
+
+properties:
+  compatible:
+    enum:
+      - atmel,at91rm9200-rtc
+      - atmel,at91sam9x5-rtc
+      - atmel,sama5d4-rtc
+      - atmel,sama5d2-rtc
+      - microchip,sam9x60-rtc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    rtc@fffffe00 {
+        compatible = "atmel,at91rm9200-rtc";
+        reg = <0xfffffe00 0x100>;
+        interrupts = <1 4 7>;
+        clocks = <&clk32k>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
deleted file mode 100644
index 130ca5b98253..000000000000
--- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
+++ /dev/null
@@ -1,61 +0,0 @@
-STM32 Real Time Clock
-
-Required properties:
-- compatible: can be one of the following:
-  - "st,stm32-rtc" for devices compatible with stm32(f4/f7).
-  - "st,stm32h7-rtc" for devices compatible with stm32h7.
-  - "st,stm32mp1-rtc" for devices compatible with stm32mp1.
-- reg: address range of rtc register set.
-- clocks: can use up to two clocks, depending on part used:
-  - "rtc_ck": RTC clock source.
-  - "pclk": RTC APB interface clock.
-    It is not present on stm32(f4/f7).
-    It is required on stm32(h7/mp1).
-- clock-names: must be "rtc_ck" and "pclk".
-    It is required on stm32(h7/mp1).
-- interrupts: rtc alarm interrupt. On stm32mp1, a second interrupt is required
-  for rtc alarm wakeup interrupt.
-- st,syscfg: phandle/offset/mask triplet. The phandle to pwrcfg used to
-  access control register at offset, and change the dbp (Disable Backup
-  Protection) bit represented by the mask, mandatory to disable/enable backup
-  domain (RTC registers) write protection.
-    It is required on stm32(f4/f7/h7).
-
-Optional properties (to override default rtc_ck parent clock on stm32(f4/f7/h7):
-- assigned-clocks: reference to the rtc_ck clock entry.
-- assigned-clock-parents: phandle of the new parent clock of rtc_ck.
-
-Example:
-
-	rtc: rtc@40002800 {
-		compatible = "st,stm32-rtc";
-		reg = <0x40002800 0x400>;
-		clocks = <&rcc 1 CLK_RTC>;
-		assigned-clocks = <&rcc 1 CLK_RTC>;
-		assigned-clock-parents = <&rcc 1 CLK_LSE>;
-		interrupt-parent = <&exti>;
-		interrupts = <17 1>;
-		st,syscfg = <&pwrcfg 0x00 0x100>;
-	};
-
-	rtc: rtc@58004000 {
-		compatible = "st,stm32h7-rtc";
-		reg = <0x58004000 0x400>;
-		clocks = <&rcc RTCAPB_CK>, <&rcc RTC_CK>;
-		clock-names = "pclk", "rtc_ck";
-		assigned-clocks = <&rcc RTC_CK>;
-		assigned-clock-parents = <&rcc LSE_CK>;
-		interrupt-parent = <&exti>;
-		interrupts = <17 1>;
-		interrupt-names = "alarm";
-		st,syscfg = <&pwrcfg 0x00 0x100>;
-	};
-
-	rtc: rtc@5c004000 {
-		compatible = "st,stm32mp1-rtc";
-		reg = <0x5c004000 0x400>;
-		clocks = <&rcc RTCAPB>, <&rcc RTC>;
-		clock-names = "pclk", "rtc_ck";
-		interrupts-extended = <&intc GIC_SPI 3 IRQ_TYPE_NONE>,
-				      <&exti 19 1>;
-	};
diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
new file mode 100644
index 000000000000..0a54296d7218
--- /dev/null
+++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.yaml
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/rtc/st,stm32-rtc.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 Real Time Clock Bindings
+
+maintainers:
+  - Gabriel Fernandez <gabriel.fernandez@st.com>
+
+properties:
+  compatible:
+    enum:
+      - st,stm32-rtc
+      - st,stm32h7-rtc
+      - st,stm32mp1-rtc
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: pclk
+      - const: rtc_ck
+
+  interrupts:
+    maxItems: 1
+
+  st,syscfg:
+    allOf:
+      - $ref: "/schemas/types.yaml#/definitions/phandle-array"
+      - items:
+          minItems: 3
+          maxItems: 3
+    description: |
+       Phandle/offset/mask triplet. The phandle to pwrcfg used to
+       access control register at offset, and change the dbp (Disable Backup
+       Protection) bit represented by the mask, mandatory to disable/enable backup
+       domain (RTC registers) write protection.
+
+  assigned-clocks:
+    description: |
+      override default rtc_ck parent clock reference to the rtc_ck clock entry
+    maxItems: 1
+
+  assigned-clock-parents:
+    description: |
+      override default rtc_ck parent clock phandle of the new parent clock of rtc_ck
+    maxItems: 1
+
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: st,stm32-rtc
+
+    then:
+      properties:
+        clocks:
+          minItems: 1
+          maxItems: 1
+
+        clock-names: false
+
+      required:
+        - st,syscfg
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: st,stm32h7-rtc
+
+    then:
+       properties:
+         clocks:
+           minItems: 2
+           maxItems: 2
+
+       required:
+         - clock-names
+         - st,syscfg
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: st,stm32mp1-rtc
+
+    then:
+       properties:
+         clocks:
+           minItems: 2
+           maxItems: 2
+
+         assigned-clocks: false
+         assigned-clock-parents: false
+
+       required:
+         - clock-names
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+examples:
+  - |
+    #include <dt-bindings/mfd/stm32f4-rcc.h>
+    #include <dt-bindings/clock/stm32fx-clock.h>
+    rtc@40002800 {
+      compatible = "st,stm32-rtc";
+      reg = <0x40002800 0x400>;
+      clocks = <&rcc 1 CLK_RTC>;
+      assigned-clocks = <&rcc 1 CLK_RTC>;
+      assigned-clock-parents = <&rcc 1 CLK_LSE>;
+      interrupt-parent = <&exti>;
+      interrupts = <17 1>;
+      st,syscfg = <&pwrcfg 0x00 0x100>;
+    };
+
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    rtc@5c004000 {
+      compatible = "st,stm32mp1-rtc";
+      reg = <0x5c004000 0x400>;
+      clocks = <&rcc RTCAPB>, <&rcc RTC>;
+      clock-names = "pclk", "rtc_ck";
+      interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/serial/fsl-lpuart.txt b/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
index f5f5ab0fd14e..c904e2e68332 100644
--- a/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
+++ b/Documentation/devicetree/bindings/serial/fsl-lpuart.txt
@@ -10,6 +10,8 @@ Required properties:
     on i.MX7ULP SoC with 32-bit little-endian register organization
   - "fsl,imx8qxp-lpuart" for lpuart compatible with the one integrated
     on i.MX8QXP SoC with 32-bit little-endian register organization
+  - "fsl,imx8qm-lpuart" for lpuart compatible with the one integrated
+    on i.MX8QM SoC with 32-bit little-endian register organization
 - reg : Address and length of the register set for the device
 - interrupts : Should contain uart interrupt
 - clocks : phandle + clock specifier pairs, one for each entry in clock-names
diff --git a/Documentation/devicetree/bindings/serial/rs485.txt b/Documentation/devicetree/bindings/serial/rs485.txt
index b92592dff6dd..a7fe93efc4a5 100644
--- a/Documentation/devicetree/bindings/serial/rs485.txt
+++ b/Documentation/devicetree/bindings/serial/rs485.txt
@@ -1,31 +1 @@
-* RS485 serial communications
-
-The RTS signal is capable of automatically controlling line direction for
-the built-in half-duplex mode.
-The properties described hereafter shall be given to a half-duplex capable
-UART node.
-
-Optional properties:
-- rs485-rts-delay: prop-encoded-array <a b> where:
-  * a is the delay between rts signal and beginning of data sent in milliseconds.
-      it corresponds to the delay before sending data.
-  * b is the delay between end of data sent and rts signal in milliseconds
-      it corresponds to the delay after sending data and actual release of the line.
-  If this property is not specified, <0 0> is assumed.
-- rs485-rts-active-low: drive RTS low when sending (default is high).
-- linux,rs485-enabled-at-boot-time: empty property telling to enable the rs485
-  feature at boot time. It can be disabled later with proper ioctl.
-- rs485-rx-during-tx: empty property that enables the receiving of data even
-  while sending data.
-
-RS485 example for Atmel USART:
-	usart0: serial@fff8c000 {
-		compatible = "atmel,at91sam9260-usart";
-		reg = <0xfff8c000 0x4000>;
-		interrupts = <7>;
-		atmel,use-dma-rx;
-		atmel,use-dma-tx;
-		linux,rs485-enabled-at-boot-time;
-		rs485-rts-delay = <0 200>;		// in milliseconds
-	};
-
+See rs485.yaml
diff --git a/Documentation/devicetree/bindings/serial/rs485.yaml b/Documentation/devicetree/bindings/serial/rs485.yaml
new file mode 100644
index 000000000000..d4beaf11222d
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/rs485.yaml
@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/serial/rs485.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: RS485 serial communications Bindings
+
+description: The RTS signal is capable of automatically controlling
+             line direction for the built-in half-duplex mode.
+             The properties described hereafter shall be given to a
+             half-duplex capable UART node.
+
+maintainers:
+  -  Rob Herring <robh@kernel.org>
+
+properties:
+  rs485-rts-delay:
+    description: prop-encoded-array <a b>
+    allOf:
+      - $ref: /schemas/types.yaml#/definitions/uint32-array
+      - items:
+          items:
+            - description:
+                Delay between rts signal and beginning of data sent in milliseconds.
+                It corresponds to the delay before sending data.
+              default: 0
+              maximum: 1000
+            - description:
+                Delay between end of data sent and rts signal in milliseconds.
+                It corresponds to the delay after sending data and actual release of the line.
+              default: 0
+              maximum: 1000
+
+  rs485-rts-active-low:
+    description: drive RTS low when sending (default is high).
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  linux,rs485-enabled-at-boot-time:
+    description: enables the rs485 feature at boot time. It can be disabled later with proper ioctl.
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  rs485-rx-during-tx:
+   description: enables the receiving of data even while sending data.
+   $ref: /schemas/types.yaml#/definitions/flag
diff --git a/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml b/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml
new file mode 100644
index 000000000000..238c44192d31
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/st,stm32-uart.yaml
@@ -0,0 +1,80 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/serial/st,stm32-uart.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+maintainers:
+  - Erwan Le Ray <erwan.leray@st.com>
+
+title: STMicroelectronics STM32 USART bindings
+
+allOf:
+  - $ref: rs485.yaml
+
+properties:
+  compatible:
+    enum:
+      - st,stm32-uart
+      - st,stm32f7-uart
+      - st,stm32h7-uart
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  label:
+    description: label associated with this uart
+
+  st,hw-flow-ctrl:
+    description: enable hardware flow control
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  dmas:
+    minItems: 1
+    maxItems: 2
+
+  dma-names:
+    items:
+      enum: [ rx, tx ]
+    minItems: 1
+    maxItems: 2
+
+  wakeup-source: true
+
+  rs485-rts-delay: true
+  rs485-rts-active-low: true
+  linux,rs485-enabled-at-boot-time: true
+  rs485-rx-during-tx: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    usart1: serial@40011000 {
+      compatible = "st,stm32-uart";
+      reg = <0x40011000 0x400>;
+      interrupts = <37>;
+      clocks = <&rcc 0 164>;
+      dmas = <&dma2 2 4 0x414 0x0>,
+             <&dma2 7 4 0x414 0x0>;
+      dma-names = "rx", "tx";
+      rs485-rts-active-low;
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/serial/st,stm32-usart.txt b/Documentation/devicetree/bindings/serial/st,stm32-usart.txt
deleted file mode 100644
index 8620f7fcbd50..000000000000
--- a/Documentation/devicetree/bindings/serial/st,stm32-usart.txt
+++ /dev/null
@@ -1,57 +0,0 @@
-* STMicroelectronics STM32 USART
-
-Required properties:
-- compatible: can be either:
-  - "st,stm32-uart",
-  - "st,stm32f7-uart",
-  - "st,stm32h7-uart".
-  depending is compatible with stm32(f4), stm32f7 or stm32h7.
-- reg: The address and length of the peripheral registers space
-- interrupts:
-  - The interrupt line for the USART instance,
-  - An optional wake-up interrupt.
-- clocks: The input clock of the USART instance
-
-Optional properties:
-- resets: Must contain the phandle to the reset controller.
-- pinctrl: The reference on the pins configuration
-- st,hw-flow-ctrl: bool flag to enable hardware flow control.
-- rs485-rts-delay, rs485-rx-during-tx, rs485-rts-active-low,
-  linux,rs485-enabled-at-boot-time: see rs485.txt.
-- dmas: phandle(s) to DMA controller node(s). Refer to stm32-dma.txt
-- dma-names: "rx" and/or "tx"
-- wakeup-source: bool flag to indicate this device has wakeup capabilities
-- interrupt-names, if optional wake-up interrupt is used, should be:
-  - "event": the name for the interrupt line of the USART instance
-  - "wakeup" the name for the optional wake-up interrupt
-
-
-Examples:
-usart4: serial@40004c00 {
-	compatible = "st,stm32-uart";
-	reg = <0x40004c00 0x400>;
-	interrupts = <52>;
-	clocks = <&clk_pclk1>;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_usart4>;
-};
-
-usart2: serial@40004400 {
-	compatible = "st,stm32-uart";
-	reg = <0x40004400 0x400>;
-	interrupts = <38>;
-	clocks = <&clk_pclk1>;
-	st,hw-flow-ctrl;
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_usart2 &pinctrl_usart2_rtscts>;
-};
-
-usart1: serial@40011000 {
-	compatible = "st,stm32-uart";
-	reg = <0x40011000 0x400>;
-	interrupts = <37>;
-	clocks = <&rcc 0 164>;
-	dmas = <&dma2 2 4 0x414 0x0>,
-	       <&dma2 7 4 0x414 0x0>;
-	dma-names = "rx", "tx";
-};
diff --git a/Documentation/devicetree/bindings/spi/fsl-spi.txt b/Documentation/devicetree/bindings/spi/fsl-spi.txt
index 411375eac54d..0654380eb751 100644
--- a/Documentation/devicetree/bindings/spi/fsl-spi.txt
+++ b/Documentation/devicetree/bindings/spi/fsl-spi.txt
@@ -15,13 +15,13 @@ Required properties:
 - clock-frequency : input clock frequency to non FSL_SOC cores
 
 Optional properties:
-- gpios : specifies the gpio pins to be used for chipselects.
+- cs-gpios : specifies the gpio pins to be used for chipselects.
   The gpios will be referred to as reg = <index> in the SPI child nodes.
   If unspecified, a single SPI device without a chip select can be used.
 - fsl,spisel_boot : for the MPC8306 and MPC8309, specifies that the
   SPISEL_BOOT signal is used as chip select for a slave device. Use
   reg = <number of gpios> in the corresponding child node, i.e. 0 if
-  the gpios property is not present.
+  the cs-gpios property is not present.
 
 Example:
 	spi@4c0 {
@@ -31,8 +31,8 @@ Example:
 		interrupts = <82 0>;
 		interrupt-parent = <700>;
 		mode = "cpu";
-		gpios = <&gpio 18 1	// device reg=<0>
-			 &gpio 19 1>;	// device reg=<1>
+		cs-gpios = <&gpio 18 1		// device reg=<0>
+			    &gpio 19 1>;	// device reg=<1>
 	};
 
 
diff --git a/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
new file mode 100644
index 000000000000..80bac7a182d5
--- /dev/null
+++ b/Documentation/devicetree/bindings/sram/allwinner,sun4i-a10-system-control.yaml
@@ -0,0 +1,140 @@
+# SPDX-License-Identifier: GPL-2.0+
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sram/allwinner,sun4i-a10-system-control.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner A10 System Control Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+description:
+  The SRAM controller found on most Allwinner devices is represented
+  by a regular node for the SRAM controller itself, with sub-nodes
+  representing the SRAM handled by the SRAM controller.
+
+properties:
+  "#address-cells":
+    const: 1
+
+  "#size-cells":
+    const: 1
+
+  compatible:
+    oneOf:
+      - const: allwinner,sun4i-a10-sram-controller
+        deprecated: true
+      - const: allwinner,sun4i-a10-system-control
+      - const: allwinner,sun5i-a13-system-control
+      - items:
+        - const: allwinner,sun7i-a20-system-control
+        - const: allwinner,sun4i-a10-system-control
+      - const: allwinner,sun8i-a23-system-control
+      - const: allwinner,sun8i-h3-system-control
+      - const: allwinner,sun50i-a64-sram-controller
+        deprecated: true
+      - const: allwinner,sun50i-a64-system-control
+      - const: allwinner,sun50i-h5-system-control
+      - items:
+        - const: allwinner,sun50i-h6-system-control
+        - const: allwinner,sun50i-a64-system-control
+      - items:
+        - const: allwinner,suniv-f1c100s-system-control
+        - const: allwinner,sun4i-a10-system-control
+
+  reg:
+    maxItems: 1
+
+  ranges: true
+
+patternProperties:
+  "^sram@[a-z0-9]+":
+    type: object
+
+    properties:
+      compatible:
+        const: mmio-sram
+
+    patternProperties:
+      "^sram-section?@[a-f0-9]+$":
+        type: object
+
+        properties:
+          compatible:
+            oneOf:
+              - const: allwinner,sun4i-a10-sram-a3-a4
+              - const: allwinner,sun4i-a10-sram-c1
+              - const: allwinner,sun4i-a10-sram-d
+              - const: allwinner,sun50i-a64-sram-c
+              - items:
+                - const: allwinner,sun5i-a13-sram-a3-a4
+                - const: allwinner,sun4i-a10-sram-a3-a4
+              - items:
+                - const: allwinner,sun7i-a20-sram-a3-a4
+                - const: allwinner,sun4i-a10-sram-a3-a4
+              - items:
+                - const: allwinner,sun5i-a13-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun7i-a20-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun8i-a23-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun8i-h3-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun50i-a64-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun50i-h5-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun50i-h6-sram-c1
+                - const: allwinner,sun4i-a10-sram-c1
+              - items:
+                - const: allwinner,sun5i-a13-sram-d
+                - const: allwinner,sun4i-a10-sram-d
+              - items:
+                - const: allwinner,sun7i-a20-sram-d
+                - const: allwinner,sun4i-a10-sram-d
+              - items:
+                - const: allwinner,suniv-f1c100s-sram-d
+                - const: allwinner,sun4i-a10-sram-d
+              - items:
+                - const: allwinner,sun50i-h6-sram-c
+                - const: allwinner,sun50i-a64-sram-c
+
+required:
+  - "#address-cells"
+  - "#size-cells"
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    system-control@1c00000 {
+      compatible = "allwinner,sun4i-a10-system-control";
+      reg = <0x01c00000 0x30>;
+      #address-cells = <1>;
+      #size-cells = <1>;
+      ranges;
+
+      sram_a: sram@00000000 {
+        compatible = "mmio-sram";
+        reg = <0x00000000 0xc000>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+        ranges = <0 0x00000000 0xc000>;
+
+        emac_sram: sram-section@8000 {
+          compatible = "allwinner,sun4i-a10-sram-a3-a4";
+          reg = <0x8000 0x4000>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/sram/sram.yaml b/Documentation/devicetree/bindings/sram/sram.yaml
index ee2287a1b14d..7b83cc6c9bfa 100644
--- a/Documentation/devicetree/bindings/sram/sram.yaml
+++ b/Documentation/devicetree/bindings/sram/sram.yaml
@@ -55,7 +55,7 @@ properties:
     type: boolean
 
 patternProperties:
-  "^([a-z]*-)?sram@[a-f0-9]+$":
+  "^([a-z]*-)?sram(-section)?@[a-f0-9]+$":
     type: object
     description:
       Each child of the sram node specifies a region of reserved memory.
@@ -64,15 +64,20 @@ patternProperties:
         description:
           Should contain a vendor specific string in the form
           <vendor>,[<device>-]<usage>
-        enum:
-          - allwinner,sun9i-a80-smp-sram
-          - amlogic,meson8-smp-sram
-          - amlogic,meson8b-smp-sram
-          - renesas,smp-sram
-          - rockchip,rk3066-smp-sram
-          - samsung,exynos4210-sysram
-          - samsung,exynos4210-sysram-ns
-          - socionext,milbeaut-smp-sram
+        contains:
+          enum:
+            - allwinner,sun4i-a10-sram-a3-a4
+            - allwinner,sun4i-a10-sram-c1
+            - allwinner,sun4i-a10-sram-d
+            - allwinner,sun9i-a80-smp-sram
+            - allwinner,sun50i-a64-sram-c
+            - amlogic,meson8-smp-sram
+            - amlogic,meson8b-smp-sram
+            - renesas,smp-sram
+            - rockchip,rk3066-smp-sram
+            - samsung,exynos4210-sysram
+            - samsung,exynos4210-sysram-ns
+            - socionext,milbeaut-smp-sram
 
       reg:
         description:
diff --git a/Documentation/devicetree/bindings/sram/sunxi-sram.txt b/Documentation/devicetree/bindings/sram/sunxi-sram.txt
deleted file mode 100644
index 380246a805f2..000000000000
--- a/Documentation/devicetree/bindings/sram/sunxi-sram.txt
+++ /dev/null
@@ -1,113 +0,0 @@
-Allwinnner SoC SRAM controllers
------------------------------------------------------
-
-The SRAM controller found on most Allwinner devices is represented by
-a regular node for the SRAM controller itself, with sub-nodes
-reprensenting the SRAM handled by the SRAM controller.
-
-Controller Node
----------------
-
-Required properties:
-- compatible : should be:
-    - "allwinner,sun4i-a10-sram-controller" (deprecated)
-    - "allwinner,sun4i-a10-system-control"
-    - "allwinner,sun5i-a13-system-control"
-    - "allwinner,sun7i-a20-system-control", "allwinner,sun4i-a10-system-control"
-    - "allwinner,sun8i-a23-system-control"
-    - "allwinner,sun8i-h3-system-control"
-    - "allwinner,sun50i-a64-sram-controller" (deprecated)
-    - "allwinner,sun50i-a64-system-control"
-    - "allwinner,sun50i-h5-system-control"
-    - "allwinner,sun50i-h6-system-control", "allwinner,sun50i-a64-system-control"
-    - "allwinner,suniv-f1c100s-system-control", "allwinner,sun4i-a10-system-control"
-- reg : sram controller register offset + length
-
-SRAM nodes
-----------
-
-Each SRAM is described using the mmio-sram bindings documented in
-Documentation/devicetree/bindings/sram/sram.txt
-
-Each SRAM will have SRAM sections that are going to be handled by the
-SRAM controller as subnodes. These sections are represented following
-once again the representation described in the mmio-sram binding.
-
-The valid sections compatible for A10 are:
-    - allwinner,sun4i-a10-sram-a3-a4
-    - allwinner,sun4i-a10-sram-c1
-    - allwinner,sun4i-a10-sram-d
-
-The valid sections compatible for A13 are:
-    - allwinner,sun5i-a13-sram-a3-a4, allwinner,sun4i-a10-sram-a3-a4
-    - allwinner,sun5i-a13-sram-c1, allwinner,sun4i-a10-sram-c1
-    - allwinner,sun5i-a13-sram-d, allwinner,sun4i-a10-sram-d
-
-The valid sections compatible for A20 are:
-    - allwinner,sun7i-a20-sram-a3-a4, allwinner,sun4i-a10-sram-a3-a4
-    - allwinner,sun7i-a20-sram-c1, allwinner,sun4i-a10-sram-c1
-    - allwinner,sun7i-a20-sram-d, allwinner,sun4i-a10-sram-d
-
-The valid sections compatible for A23/A33 are:
-    - allwinner,sun8i-a23-sram-c1, allwinner,sun4i-a10-sram-c1
-
-The valid sections compatible for H3 are:
-    - allwinner,sun8i-h3-sram-c1, allwinner,sun4i-a10-sram-c1
-
-The valid sections compatible for A64 are:
-    - allwinner,sun50i-a64-sram-c
-    - allwinner,sun50i-a64-sram-c1, allwinner,sun4i-a10-sram-c1
-
-The valid sections compatible for H5 are:
-    - allwinner,sun50i-h5-sram-c1, allwinner,sun4i-a10-sram-c1
-
-The valid sections compatible for H6 are:
-    - allwinner,sun50i-h6-sram-c, allwinner,sun50i-a64-sram-c
-    - allwinner,sun50i-h6-sram-c1, allwinner,sun4i-a10-sram-c1
-
-The valid sections compatible for F1C100s are:
-    - allwinner,suniv-f1c100s-sram-d, allwinner,sun4i-a10-sram-d
-
-Devices using SRAM sections
----------------------------
-
-Some devices need to request to the SRAM controller to map an SRAM for
-their exclusive use.
-
-The relationship between such a device and an SRAM section is
-expressed through the allwinner,sram property, that will take a
-phandle and an argument.
-
-This valid values for this argument are:
-  - 0: CPU
-  - 1: Device
-
-Example
--------
-system-control@1c00000 {
-	compatible = "allwinner,sun4i-a10-system-control";
-	reg = <0x01c00000 0x30>;
-	#address-cells = <1>;
-	#size-cells = <1>;
-	ranges;
-
-	sram_a: sram@00000000 {
-		compatible = "mmio-sram";
-		reg = <0x00000000 0xc000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges = <0 0x00000000 0xc000>;
-
-		emac_sram: sram-section@8000 {
-			compatible = "allwinner,sun4i-a10-sram-a3-a4";
-			reg = <0x8000 0x4000>;
-		};
-	};
-};
-
-emac: ethernet@1c0b000 {
-	compatible = "allwinner,sun4i-a10-emac";
-	...
-
-	allwinner,sram = <&emac_sram 1>;
-};
diff --git a/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml b/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml
index b3f0fe96ff0d..102f319833d9 100644
--- a/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml
+++ b/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml
@@ -99,22 +99,22 @@ examples:
       compatible = "arm,armv7-timer-mem";
       #address-cells = <1>;
       #size-cells = <1>;
-      ranges;
+      ranges = <0 0xf0001000 0x1000>;
       reg = <0xf0000000 0x1000>;
       clock-frequency = <50000000>;
 
-      frame@f0001000 {
+      frame@0 {
         frame-number = <0>;
         interrupts = <0 13 0x8>,
                <0 14 0x8>;
-        reg = <0xf0001000 0x1000>,
-              <0xf0002000 0x1000>;
+        reg = <0x0000 0x1000>,
+              <0x1000 0x1000>;
       };
 
-      frame@f0003000 {
+      frame@2000 {
         frame-number = <1>;
         interrupts = <0 15 0x8>;
-        reg = <0xf0003000 0x1000>;
+        reg = <0x2000 0x1000>;
       };
     };
 
diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml
index 765fd1c170df..978de7d37c66 100644
--- a/Documentation/devicetree/bindings/trivial-devices.yaml
+++ b/Documentation/devicetree/bindings/trivial-devices.yaml
@@ -104,6 +104,10 @@ properties:
           - infineon,slb9645tt
             # Infineon TLV493D-A1B6 I2C 3D Magnetic Sensor
           - infineon,tlv493d-a1b6
+            # Infineon Multi-phase Digital VR Controller xdpe12254
+          - infineon,xdpe12254
+            # Infineon Multi-phase Digital VR Controller xdpe12284
+          - infineon,xdpe12284
             # Inspur Power System power supply unit version 1
           - inspur,ipsps1
             # Intersil ISL29028 Ambient Light and Proximity Sensor
@@ -132,6 +136,8 @@ properties:
           - maxim,max6621
             # 9-Bit/12-Bit Temperature Sensors with I²C-Compatible Serial Interface
           - maxim,max6625
+            # 3-Channel Remote Temperature Sensor
+          - maxim,max31730
             # mCube 3-axis 8-bit digital accelerometer
           - mcube,mc3230
             # MEMSIC 2-axis 8-bit digital accelerometer
@@ -354,6 +360,10 @@ properties:
           - ti,tmp103
             # Digital Temperature Sensor
           - ti,tmp275
+            # TI Dual channel DCAP+ multiphase controller TPS53679
+          - ti,tps53679
+            # TI Dual channel DCAP+ multiphase controller TPS53688
+          - ti,tps53688
             # Winbond/Nuvoton H/W Monitor
           - winbond,w83793
             # i2c trusted platform module (TPM)
diff --git a/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml b/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml
index 4efb77b653ab..267fce165994 100644
--- a/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml
+++ b/Documentation/devicetree/bindings/usb/amlogic,meson-g12a-usb-ctrl.yaml
@@ -107,7 +107,7 @@ examples:
               reg = <0xff400000 0x40000>;
               interrupts = <31>;
               clocks = <&clkc_usb1>;
-              clock-names = "ddr";
+              clock-names = "otg";
               phys = <&usb2_phy1>;
               dr_mode = "peripheral";
               g-rx-fifo-size = <192>;
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
deleted file mode 100644
index aafff3a6904d..000000000000
--- a/Documentation/devicetree/bindings/usb/dwc2.txt
+++ /dev/null
@@ -1,64 +0,0 @@
-Platform DesignWare HS OTG USB 2.0 controller
------------------------------------------------------
-
-Required properties:
-- compatible : One of:
-  - brcm,bcm2835-usb: The DWC2 USB controller instance in the BCM2835 SoC.
-  - hisilicon,hi6220-usb: The DWC2 USB controller instance in the hi6220 SoC.
-  - rockchip,rk3066-usb: The DWC2 USB controller instance in the rk3066 Soc;
-  - "rockchip,px30-usb", "rockchip,rk3066-usb", "snps,dwc2": for px30 Soc;
-  - "rockchip,rk3188-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3188 Soc;
-  - "rockchip,rk3288-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3288 Soc;
-  - "lantiq,arx100-usb": The DWC2 USB controller instance in Lantiq ARX SoCs;
-  - "lantiq,xrx200-usb": The DWC2 USB controller instance in Lantiq XRX SoCs;
-  - "amlogic,meson8-usb": The DWC2 USB controller instance in Amlogic Meson8 SoCs;
-  - "amlogic,meson8b-usb": The DWC2 USB controller instance in Amlogic Meson8b SoCs;
-  - "amlogic,meson-gxbb-usb": The DWC2 USB controller instance in Amlogic S905 SoCs;
-  - "amlogic,meson-g12a-usb": The DWC2 USB controller instance in Amlogic G12A SoCs;
-  - "amcc,dwc-otg": The DWC2 USB controller instance in AMCC Canyonlands 460EX SoCs;
-  - snps,dwc2: A generic DWC2 USB controller with default parameters.
-  - "st,stm32f4x9-fsotg": The DWC2 USB FS/HS controller instance in STM32F4x9 SoCs
-  configured in FS mode;
-  - "st,stm32f4x9-hsotg": The DWC2 USB HS controller instance in STM32F4x9 SoCs
-  configured in HS mode;
-  - "st,stm32f7-hsotg": The DWC2 USB HS controller instance in STM32F7 SoCs
-    configured in HS mode;
-- reg : Should contain 1 register range (address and length)
-- interrupts : Should contain 1 interrupt
-- clocks: clock provider specifier
-- clock-names: shall be "otg"
-Refer to clk/clock-bindings.txt for generic clock consumer properties
-
-Optional properties:
-- phys: phy provider specifier
-- phy-names: shall be "usb2-phy"
-- vbus-supply: reference to the VBUS regulator. Depending on the current mode
-  this is enabled (in "host" mode") or disabled (in "peripheral" mode). The
-  regulator is updated if the controller is configured in "otg" mode and the
-  status changes between "host" and "peripheral".
-Refer to phy/phy-bindings.txt for generic phy consumer properties
-- dr_mode: shall be one of "host", "peripheral" and "otg"
-  Refer to usb/generic.txt
-- g-rx-fifo-size: size of rx fifo size in gadget mode.
-- g-np-tx-fifo-size: size of non-periodic tx fifo size in gadget mode.
-- g-tx-fifo-size: size of periodic tx fifo per endpoint (except ep0) in gadget mode.
-- snps,need-phy-for-wake: If present indicates that the phy needs to be left
-                          on for remote wakeup during suspend.
-- snps,reset-phy-on-wake: If present indicates that we need to reset the PHY when
-                          we detect a wakeup.  This is due to a hardware errata.
-
-Deprecated properties:
-- g-use-dma: gadget DMA mode is automatically detected
-
-Example:
-
-        usb@101c0000 {
-                compatible = "ralink,rt3050-usb, snps,dwc2";
-                reg = <0x101c0000 40000>;
-                interrupts = <18>;
-		clocks = <&usb_otg_ahb_clk>;
-		clock-names = "otg";
-		phys = <&usbphy>;
-		phy-names = "usb2-phy";
-		snps,need-phy-for-wake;
-        };
diff --git a/Documentation/devicetree/bindings/usb/dwc2.yaml b/Documentation/devicetree/bindings/usb/dwc2.yaml
new file mode 100644
index 000000000000..71cf7ba32237
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/dwc2.yaml
@@ -0,0 +1,151 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/usb/dwc2.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: DesignWare HS OTG USB 2.0 controller Bindings
+
+maintainers:
+  - Rob Herring <robh@kernel.org>
+
+properties:
+  compatible:
+    oneOf:
+      - const: brcm,bcm2835-usb
+      - const: hisilicon,hi6220-usb
+      - items:
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - items:
+          - const: rockchip,px30-usb
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - items:
+          - const: rockchip,rk3036-usb
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - items:
+          - const: rockchip,rv1108-usb
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - items:
+          - const: rockchip,rk3188-usb
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - items:
+          - const: rockchip,rk3228-usb
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - items:
+          - const: rockchip,rk3288-usb
+          - const: rockchip,rk3066-usb
+          - const: snps,dwc2
+      - const: lantiq,arx100-usb
+      - const: lantiq,xrx200-usb
+      - items:
+          - const: amlogic,meson8-usb
+          - const: snps,dwc2
+      - items:
+          - const: amlogic,meson8b-usb
+          - const: snps,dwc2
+      - const: amlogic,meson-gxbb-usb
+      - items:
+          - const: amlogic,meson-g12a-usb
+          - const: snps,dwc2
+      - const: amcc,dwc-otg
+      - const: snps,dwc2
+      - const: st,stm32f4x9-fsotg
+      - const: st,stm32f4x9-hsotg
+      - const: st,stm32f7-hsotg
+      - const: samsung,s3c6400-hsotg
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: otg
+
+  resets:
+    items:
+     - description: common reset
+     - description: ecc reset
+    minItems: 1
+
+  reset-names:
+    items:
+     - const: dwc2
+     - const: dwc2-ecc
+    minItems: 1
+
+  phys:
+    maxItems: 1
+
+  phy-names:
+    const: usb2-phy
+
+  vbus-supply:
+    description: reference to the VBUS regulator. Depending on the current mode
+      this is enabled (in "host" mode") or disabled (in "peripheral" mode). The
+      regulator is updated if the controller is configured in "otg" mode and the
+      status changes between "host" and "peripheral".
+
+  vusb_d-supply:
+    description: phandle to voltage regulator of digital section,
+
+  vusb_a-supply:
+    description: phandle to voltage regulator of analog section.
+
+  dr_mode:
+    enum: [host, peripheral, otg]
+
+  g-rx-fifo-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: size of rx fifo size in gadget mode.
+
+  g-np-tx-fifo-size:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: size of non-periodic tx fifo size in gadget mode.
+
+  g-tx-fifo-size:
+    $ref: /schemas/types.yaml#/definitions/uint32-array
+    description: size of periodic tx fifo per endpoint (except ep0) in gadget mode.
+
+  snps,need-phy-for-wake:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: If present indicates that the phy needs to be left on for remote wakeup during suspend.
+
+  snps,reset-phy-on-wake:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: If present indicates that we need to reset the PHY when we detect a wakeup.
+                 This is due to a hardware errata.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
+additionalProperties: false
+
+examples:
+  - |
+      usb@101c0000 {
+        compatible = "rockchip,rk3066-usb", "snps,dwc2";
+        reg = <0x10180000 0x40000>;
+        interrupts = <18>;
+        clocks = <&usb_otg_ahb_clk>;
+        clock-names = "otg";
+        phys = <&usbphy>;
+        phy-names = "usb2-phy";
+      };
+
+...
diff --git a/Documentation/devicetree/bindings/usb/generic.txt b/Documentation/devicetree/bindings/usb/generic.txt
index cf5a1ad456e6..e6790d2a4da9 100644
--- a/Documentation/devicetree/bindings/usb/generic.txt
+++ b/Documentation/devicetree/bindings/usb/generic.txt
@@ -2,10 +2,11 @@ Generic USB Properties
 
 Optional properties:
  - maximum-speed: tells USB controllers we want to work up to a certain
-			speed. Valid arguments are "super-speed", "high-speed",
-			"full-speed" and "low-speed". In case this isn't passed
-			via DT, USB controllers should default to their maximum
-			HW capability.
+			speed. Valid arguments are "super-speed-plus",
+			"super-speed", "high-speed", "full-speed" and
+			"low-speed". In case this isn't passed via DT, USB
+			controllers should default to their maximum HW
+			capability.
  - dr_mode: tells Dual-Role USB controllers that we want to work on a
 			particular mode. Valid arguments are "host",
 			"peripheral" and "otg". In case this attribute isn't
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml
index 315ebac520b3..7fcd48adc276 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.yaml
+++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml
@@ -151,6 +151,8 @@ patternProperties:
     description: Bosch Sensortec GmbH
   "^boundary,.*":
     description: Boundary Devices Inc.
+  "^broadmobi,.*":
+    description: Shanghai Broadmobi Communication Technology Co.,Ltd.
   "^brcm,.*":
     description: Broadcom Corporation
   "^buffalo,.*":
@@ -159,6 +161,8 @@ patternProperties:
     description: B&R Industrial Automation GmbH
   "^bticino,.*":
     description: Bticino International
+  "^calaosystems,.*":
+    description: CALAO Systems SAS
   "^calxeda,.*":
     description: Calxeda
   "^capella,.*":
@@ -477,6 +481,8 @@ patternProperties:
     description: Shenzhen Jesurun Electronics Business Dept.
   "^jianda,.*":
     description: Jiandangjing Technology Co., Ltd.
+  "^kam,.*":
+    description: Kamstrup A/S
   "^karo,.*":
     description: Ka-Ro electronics GmbH
   "^keithkoep,.*":
@@ -515,6 +521,8 @@ patternProperties:
     description: Lantiq Semiconductor
   "^lattice,.*":
     description: Lattice Semiconductor
+  "^leadtek,.*":
+    description: Shenzhen Leadtek Technology Co., Ltd.
   "^leez,.*":
     description: Leez
   "^lego,.*":
@@ -547,6 +555,8 @@ patternProperties:
     description: Logic PD, Inc.
   "^longcheer,.*":
     description: Longcheer Technology (Shanghai) Co., Ltd.
+  "^loongson,.*":
+    description: Loongson Technology Corporation Limited
   "^lsi,.*":
     description: LSI Corp. (LSI Logic)
   "^lwn,.*":
@@ -615,6 +625,8 @@ patternProperties:
     description: Moxa Inc.
   "^mpl,.*":
     description: MPL AG
+  "^mps,.*":
+    description: Monolithic Power Systems Inc.
   "^mqmaker,.*":
     description: mqmaker Inc.
   "^mscc,.*":
@@ -827,6 +839,8 @@ patternProperties:
     description: Sancloud Ltd
   "^sandisk,.*":
     description: Sandisk Corporation
+  "^satoz,.*":
+    description: Satoz International Co., Ltd
   "^sbs,.*":
     description: Smart Battery System
   "^schindler,.*":
@@ -915,8 +929,12 @@ patternProperties:
     description: Startek
   "^ste,.*":
     description: ST-Ericsson
+    deprecated: true
   "^stericsson,.*":
     description: ST-Ericsson
+  "^st-ericsson,.*":
+    description: ST-Ericsson
+    deprecated: true
   "^summit,.*":
     description: Summit microelectronics
   "^sunchip,.*":
@@ -1060,12 +1078,16 @@ patternProperties:
     description: Extreme Engineering Solutions (X-ES)
   "^xillybus,.*":
     description: Xillybus Ltd.
+  "^xinpeng,.*":
+    description: Shenzhen Xinpeng Technology Co., Ltd
   "^xlnx,.*":
     description: Xilinx
   "^xunlong,.*":
     description: Shenzhen Xunlong Software CO.,Limited
   "^xylon,.*":
     description: Xylon
+  "^yna,.*":
+    description: YSH & ATIL
   "^yones-toptech,.*":
     description: Yones Toptech Co., Ltd.
   "^ysoft,.*":
diff --git a/Documentation/devicetree/bindings/watchdog/renesas,wdt.txt b/Documentation/devicetree/bindings/watchdog/renesas,wdt.txt
index a5bf04dba410..79b3c62f183d 100644
--- a/Documentation/devicetree/bindings/watchdog/renesas,wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/renesas,wdt.txt
@@ -19,6 +19,7 @@ Required properties:
 	         - "renesas,r8a7794-wdt" (R-Car E2)
 	         - "renesas,r8a7795-wdt" (R-Car H3)
 	         - "renesas,r8a7796-wdt" (R-Car M3-W)
+	         - "renesas,r8a77961-wdt" (R-Car M3-W+)
 		 - "renesas,r8a77965-wdt" (R-Car M3-N)
 	         - "renesas,r8a77970-wdt" (R-Car V3M)
 	         - "renesas,r8a77990-wdt" (R-Car E3)
diff --git a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.txt b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.txt
deleted file mode 100644
index d8f4430b0a13..000000000000
--- a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.txt
+++ /dev/null
@@ -1,26 +0,0 @@
-STM32 Independent WatchDoG (IWDG)
----------------------------------
-
-Required properties:
-- compatible: Should be either:
-  - "st,stm32-iwdg"
-  - "st,stm32mp1-iwdg"
-- reg: Physical base address and length of the registers set for the device
-- clocks: Reference to the clock entry lsi. Additional pclk clock entry
-  is required only for st,stm32mp1-iwdg.
-- clock-names: Name of the clocks used.
-  "lsi" for st,stm32-iwdg
-  "lsi", "pclk" for st,stm32mp1-iwdg
-
-Optional Properties:
-- timeout-sec: Watchdog timeout value in seconds.
-
-Example:
-
-iwdg: watchdog@40003000 {
-	compatible = "st,stm32-iwdg";
-	reg = <0x40003000 0x400>;
-	clocks = <&clk_lsi>;
-	clock-names = "lsi";
-	timeout-sec = <32>;
-};
diff --git a/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml
new file mode 100644
index 000000000000..a27c504e2e4f
--- /dev/null
+++ b/Documentation/devicetree/bindings/watchdog/st,stm32-iwdg.yaml
@@ -0,0 +1,57 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/watchdog/st,stm32-iwdg.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: STMicroelectronics STM32 Independent WatchDoG (IWDG) bindings
+
+maintainers:
+  - Yannick Fertre <yannick.fertre@st.com>
+  - Christophe Roullier <christophe.roullier@st.com>
+
+allOf:
+  - $ref: "watchdog.yaml#"
+
+properties:
+  compatible:
+    enum:
+      - st,stm32-iwdg
+      - st,stm32mp1-iwdg
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: Low speed clock
+      - description: Optional peripheral clock
+    minItems: 1
+    maxItems: 2
+
+  clock-names:
+    items:
+      enum:
+        - lsi
+        - pclk
+    minItems: 1
+    maxItems: 2
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+
+examples:
+  - |
+    #include <dt-bindings/clock/stm32mp1-clks.h>
+    watchdog@5a002000 {
+      compatible = "st,stm32mp1-iwdg";
+      reg = <0x5a002000 0x400>;
+      clocks = <&rcc IWDG2>, <&rcc CK_LSI>;
+      clock-names = "pclk", "lsi";
+      timeout-sec = <32>;
+    };
+
+...
diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst
index efcd5d21dc2b..7635ab230456 100644
--- a/Documentation/devicetree/writing-schema.rst
+++ b/Documentation/devicetree/writing-schema.rst
@@ -121,7 +121,13 @@ Several executables (dt-doc-validate, dt-mk-schema, dt-validate) will be
 installed. Ensure they are in your PATH (~/.local/bin by default).
 
 dtc must also be built with YAML output support enabled. This requires that
-libyaml and its headers be installed on the host system.
+libyaml and its headers be installed on the host system. For some distributions
+that involves installing the development package, such as:
+
+Debian:
+  apt-get install libyaml-dev
+Fedora:
+  dnf -y install libyaml-devel
 
 Running checks
 ~~~~~~~~~~~~~~
diff --git a/Documentation/driver-api/dmaengine/client.rst b/Documentation/driver-api/dmaengine/client.rst
index a9a7a3c84c63..e5953e7e4bf4 100644
--- a/Documentation/driver-api/dmaengine/client.rst
+++ b/Documentation/driver-api/dmaengine/client.rst
@@ -151,8 +151,8 @@ The details of these operations are:
      Note that callbacks will always be invoked from the DMA
      engines tasklet, never from interrupt context.
 
-  Optional: per descriptor metadata
-  ---------------------------------
+Optional: per descriptor metadata
+---------------------------------
   DMAengine provides two ways for metadata support.
 
   DESC_METADATA_CLIENT
diff --git a/Documentation/driver-api/thermal/cpu-idle-cooling.rst b/Documentation/driver-api/thermal/cpu-idle-cooling.rst
index e4f0859486c7..9f0016ee4cfb 100644
--- a/Documentation/driver-api/thermal/cpu-idle-cooling.rst
+++ b/Documentation/driver-api/thermal/cpu-idle-cooling.rst
@@ -65,6 +65,8 @@ We use a fixed duration of idle injection that gives an acceptable
 performance penalty and a fixed latency. Mitigation can be increased
 or decreased by modulating the duty cycle of the idle injection.
 
+::
+
      ^
      |
      |
@@ -91,6 +93,8 @@ computed.
 The governor will change the cooling device state thus the duty cycle
 and this variation will modulate the cooling effect.
 
+::
+
      ^
      |
      |
@@ -154,6 +158,7 @@ equation:
 
  P(opp)target = ((Trunning x (P(opp)running) + (Tidle x P(opp)idle)) /
 			(Trunning + Tidle)
+
   ...
 
  Tidle = Trunning x ((P(opp)running / P(opp)target) - 1)
diff --git a/Documentation/fb/fbcon.rst b/Documentation/fb/fbcon.rst
index ebca41785abe..e57a3d1d085a 100644
--- a/Documentation/fb/fbcon.rst
+++ b/Documentation/fb/fbcon.rst
@@ -127,7 +127,7 @@ C. Boot options
 	is typically located on the same video card.  Thus, the consoles that
 	are controlled by the VGA console will be garbled.
 
-4. fbcon=rotate:<n>
+5. fbcon=rotate:<n>
 
 	This option changes the orientation angle of the console display. The
 	value 'n' accepts the following:
@@ -152,21 +152,21 @@ C. Boot options
 	Actually, the underlying fb driver is totally ignorant of console
 	rotation.
 
-5. fbcon=margin:<color>
+6. fbcon=margin:<color>
 
 	This option specifies the color of the margins. The margins are the
 	leftover area at the right and the bottom of the screen that are not
 	used by text. By default, this area will be black. The 'color' value
 	is an integer number that depends on the framebuffer driver being used.
 
-6. fbcon=nodefer
+7. fbcon=nodefer
 
 	If the kernel is compiled with deferred fbcon takeover support, normally
 	the framebuffer contents, left in place by the firmware/bootloader, will
 	be preserved until there actually is some text is output to the console.
 	This option causes fbcon to bind immediately to the fbdev device.
 
-7. fbcon=logo-pos:<location>
+8. fbcon=logo-pos:<location>
 
 	The only possible 'location' is 'center' (without quotes), and when
 	given, the bootup logo is moved from the default top-left corner
@@ -174,6 +174,11 @@ C. Boot options
 	displayed due to multiple CPUs, the collected line of logos is moved
 	as a whole.
 
+9. fbcon=logo-count:<n>
+
+	The value 'n' overrides the number of bootup logos. 0 disables the
+	logo, and -1 gives the default which is the number of online CPUs.
+
 C. Attaching, Detaching and Unloading
 
 Before going on to how to attach, detach and unload the framebuffer console, an
diff --git a/Documentation/fb/modedb.rst b/Documentation/fb/modedb.rst
index 9c4e3fd39e6d..624d08fd2856 100644
--- a/Documentation/fb/modedb.rst
+++ b/Documentation/fb/modedb.rst
@@ -65,6 +65,9 @@ Valid options are::
   - reflect_y (boolean): Perform an axial symmetry on the Y axis
   - rotate (integer): Rotate the initial framebuffer by x
     degrees. Valid values are 0, 90, 180 and 270.
+  - panel_orientation, one of "normal", "upside_down", "left_side_up", or
+    "right_side_up". For KMS drivers only, this sets the "panel orientation"
+    property on the kms connector as hint for kms users.
 
 
 -----------------------------------------------------------------------------
diff --git a/Documentation/features/core/jump-labels/arch-support.txt b/Documentation/features/core/jump-labels/arch-support.txt
index cae7be2f7725..632a1c7aefa2 100644
--- a/Documentation/features/core/jump-labels/arch-support.txt
+++ b/Documentation/features/core/jump-labels/arch-support.txt
@@ -7,7 +7,7 @@
     |         arch |status|
     -----------------------
     |       alpha: | TODO |
-    |         arc: | TODO |
+    |         arc: |  ok  |
     |         arm: |  ok  |
     |       arm64: |  ok  |
     |         c6x: | TODO |
diff --git a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
index 4fae0464ddff..32b297295fff 100644
--- a/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
+++ b/Documentation/features/debug/kprobes-on-ftrace/arch-support.txt
@@ -24,7 +24,7 @@
     |      parisc: |  ok  |
     |     powerpc: |  ok  |
     |       riscv: | TODO |
-    |        s390: | TODO |
+    |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
     |          um: | TODO |
diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index 3135b80df6da..4eb3e2ddd00e 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -235,6 +235,17 @@ checkpoint=%s[:%u[%]]     Set to "disable" to turn off checkpointing. Set to "en
                        hide up to all remaining free space. The actual space that
                        would be unusable can be viewed at /sys/fs/f2fs/<disk>/unusable
                        This space is reclaimed once checkpoint=enable.
+compress_algorithm=%s  Control compress algorithm, currently f2fs supports "lzo"
+                       and "lz4" algorithm.
+compress_log_size=%u   Support configuring compress cluster size, the size will
+                       be 4KB * (1 << %u), 16KB is minimum size, also it's
+                       default size.
+compress_extension=%s  Support adding specified extension, so that f2fs can enable
+                       compression on those corresponding files, e.g. if all files
+                       with '.ext' has high compression rate, we can set the '.ext'
+                       on compression extension list and enable compression on
+                       these file by default rather than to enable it via ioctl.
+                       For other files, we can still enable compression via ioctl.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -259,170 +270,6 @@ The files in each per-device directory are shown in table below.
 
 Files in /sys/fs/f2fs/<devname>
 (see also Documentation/ABI/testing/sysfs-fs-f2fs)
-..............................................................................
- File                         Content
-
- gc_urgent_sleep_time         This parameter controls sleep time for gc_urgent.
-                              500 ms is set by default. See above gc_urgent.
-
- gc_min_sleep_time            This tuning parameter controls the minimum sleep
-                              time for the garbage collection thread. Time is
-                              in milliseconds.
-
- gc_max_sleep_time            This tuning parameter controls the maximum sleep
-                              time for the garbage collection thread. Time is
-                              in milliseconds.
-
- gc_no_gc_sleep_time          This tuning parameter controls the default sleep
-                              time for the garbage collection thread. Time is
-                              in milliseconds.
-
- gc_idle                      This parameter controls the selection of victim
-                              policy for garbage collection. Setting gc_idle = 0
-                              (default) will disable this option. Setting
-                              gc_idle = 1 will select the Cost Benefit approach
-                              & setting gc_idle = 2 will select the greedy approach.
-
- gc_urgent                    This parameter controls triggering background GCs
-                              urgently or not. Setting gc_urgent = 0 [default]
-                              makes back to default behavior, while if it is set
-                              to 1, background thread starts to do GC by given
-                              gc_urgent_sleep_time interval.
-
- reclaim_segments             This parameter controls the number of prefree
-                              segments to be reclaimed. If the number of prefree
-			      segments is larger than the number of segments
-			      in the proportion to the percentage over total
-			      volume size, f2fs tries to conduct checkpoint to
-			      reclaim the prefree segments to free segments.
-			      By default, 5% over total # of segments.
-
- main_blkaddr                 This value gives the first block address of
-			      MAIN area in the partition.
-
- max_small_discards	      This parameter controls the number of discard
-			      commands that consist small blocks less than 2MB.
-			      The candidates to be discarded are cached until
-			      checkpoint is triggered, and issued during the
-			      checkpoint. By default, it is disabled with 0.
-
- discard_granularity	      This parameter controls the granularity of discard
-			      command size. It will issue discard commands iif
-			      the size is larger than given granularity. Its
-			      unit size is 4KB, and 4 (=16KB) is set by default.
-			      The maximum value is 128 (=512KB).
-
- reserved_blocks	      This parameter indicates the number of blocks that
-			      f2fs reserves internally for root.
-
- batched_trim_sections	      This parameter controls the number of sections
-                              to be trimmed out in batch mode when FITRIM
-                              conducts. 32 sections is set by default.
-
- ipu_policy                   This parameter controls the policy of in-place
-                              updates in f2fs. There are five policies:
-                               0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
-                               0x04: F2FS_IPU_UTIL,  0x08: F2FS_IPU_SSR_UTIL,
-                               0x10: F2FS_IPU_FSYNC.
-
- min_ipu_util                 This parameter controls the threshold to trigger
-                              in-place-updates. The number indicates percentage
-                              of the filesystem utilization, and used by
-                              F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies.
-
- min_fsync_blocks             This parameter controls the threshold to trigger
-                              in-place-updates when F2FS_IPU_FSYNC mode is set.
-			      The number indicates the number of dirty pages
-			      when fsync needs to flush on its call path. If
-			      the number is less than this value, it triggers
-			      in-place-updates.
-
- min_seq_blocks		      This parameter controls the threshold to serialize
-			      write IOs issued by multiple threads in parallel.
-
- min_hot_blocks		      This parameter controls the threshold to allocate
-			      a hot data log for pending data blocks to write.
-
- min_ssr_sections	      This parameter adds the threshold when deciding
-			      SSR block allocation. If this is large, SSR mode
-			      will be enabled early.
-
- ram_thresh                   This parameter controls the memory footprint used
-			      by free nids and cached nat entries. By default,
-			      1 is set, which indicates 10 MB / 1 GB RAM.
-
- ra_nid_pages		      When building free nids, F2FS reads NAT blocks
-			      ahead for speed up. Default is 0.
-
- dirty_nats_ratio	      Given dirty ratio of cached nat entries, F2FS
-			      determines flushing them in background.
-
- max_victim_search	      This parameter controls the number of trials to
-			      find a victim segment when conducting SSR and
-			      cleaning operations. The default value is 4096
-			      which covers 8GB block address range.
-
- migration_granularity	      For large-sized sections, F2FS can stop GC given
-			      this granularity instead of reclaiming entire
-			      section.
-
- dir_level                    This parameter controls the directory level to
-			      support large directory. If a directory has a
-			      number of files, it can reduce the file lookup
-			      latency by increasing this dir_level value.
-			      Otherwise, it needs to decrease this value to
-			      reduce the space overhead. The default value is 0.
-
- cp_interval		      F2FS tries to do checkpoint periodically, 60 secs
-			      by default.
-
- idle_interval		      F2FS detects system is idle, if there's no F2FS
-			      operations during given interval, 5 secs by
-			      default.
-
- discard_idle_interval	      F2FS detects the discard thread is idle, given
-			      time interval. Default is 5 secs.
-
- gc_idle_interval	      F2FS detects the GC thread is idle, given time
-			      interval. Default is 5 secs.
-
- umount_discard_timeout       When unmounting the disk, F2FS waits for finishing
-			      queued discard commands which can take huge time.
-			      This gives time out for it, 5 secs by default.
-
- iostat_enable		      This controls to enable/disable iostat in F2FS.
-
- readdir_ra		      This enables/disabled readahead of inode blocks
-			      in readdir, and default is enabled.
-
- gc_pin_file_thresh	      This indicates how many GC can be failed for the
-			      pinned file. If it exceeds this, F2FS doesn't
-			      guarantee its pinning state. 2048 trials is set
-			      by default.
-
- extension_list		      This enables to change extension_list for hot/cold
-			      files in runtime.
-
- inject_rate		      This controls injection rate of arbitrary faults.
-
- inject_type		      This controls injection type of arbitrary faults.
-
- dirty_segments 	      This shows # of dirty segments.
-
- lifetime_write_kbytes	      This shows # of data written to the disk.
-
- features		      This shows current features enabled on F2FS.
-
- current_reserved_blocks      This shows # of blocks currently reserved.
-
- unusable                     If checkpoint=disable, this shows the number of
-                              blocks that are unusable.
-                              If checkpoint=enable it shows the number of blocks
-                              that would be unusable if checkpoint=disable were
-                              to be set.
-
-encoding 	              This shows the encoding used for casefolding.
-                              If casefolding is not enabled, returns (none)
 
 ================================================================================
 USAGE
@@ -840,3 +687,44 @@ zero or random data, which is useful to the below scenario where:
  4. address = fibmap(fd, offset)
  5. open(blkdev)
  6. write(blkdev, address)
+
+Compression implementation
+--------------------------
+
+- New term named cluster is defined as basic unit of compression, file can
+be divided into multiple clusters logically. One cluster includes 4 << n
+(n >= 0) logical pages, compression size is also cluster size, each of
+cluster can be compressed or not.
+
+- In cluster metadata layout, one special block address is used to indicate
+cluster is compressed one or normal one, for compressed cluster, following
+metadata maps cluster to [1, 4 << n - 1] physical blocks, in where f2fs
+stores data including compress header and compressed data.
+
+- In order to eliminate write amplification during overwrite, F2FS only
+support compression on write-once file, data can be compressed only when
+all logical blocks in file are valid and cluster compress ratio is lower
+than specified threshold.
+
+- To enable compression on regular inode, there are three ways:
+* chattr +c file
+* chattr +c dir; touch dir/file
+* mount w/ -o compress_extension=ext; touch file.ext
+
+Compress metadata layout:
+                             [Dnode Structure]
+             +-----------------------------------------------+
+             | cluster 1 | cluster 2 | ......... | cluster N |
+             +-----------------------------------------------+
+             .           .                       .           .
+       .                       .                .                      .
+  .         Compressed Cluster       .        .        Normal Cluster            .
++----------+---------+---------+---------+  +---------+---------+---------+---------+
+|compr flag| block 1 | block 2 | block 3 |  | block 1 | block 2 | block 3 | block 4 |
++----------+---------+---------+---------+  +---------+---------+---------+---------+
+           .                             .
+         .                                           .
+       .                                                           .
+      +-------------+-------------+----------+----------------------------+
+      | data length | data chksum | reserved |      compressed data       |
+      +-------------+-------------+----------+----------------------------+
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index 01e909245fcd..bd9932344804 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -1016,9 +1016,9 @@ astute users may notice some differences in behavior:
 - Direct I/O is not supported on encrypted files.  Attempts to use
   direct I/O on such files will fall back to buffered I/O.
 
-- The fallocate operations FALLOC_FL_COLLAPSE_RANGE,
-  FALLOC_FL_INSERT_RANGE, and FALLOC_FL_ZERO_RANGE are not supported
-  on encrypted files and will fail with EOPNOTSUPP.
+- The fallocate operations FALLOC_FL_COLLAPSE_RANGE and
+  FALLOC_FL_INSERT_RANGE are not supported on encrypted files and will
+  fail with EOPNOTSUPP.
 
 - Online defragmentation of encrypted files is not supported.  The
   EXT4_IOC_MOVE_EXT and F2FS_IOC_MOVE_RANGE ioctls will fail with
diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst
index 966bd2d9f0cc..a73320576ca9 100644
--- a/Documentation/gpu/drm-internals.rst
+++ b/Documentation/gpu/drm-internals.rst
@@ -24,9 +24,9 @@ Driver Initialization
 At the core of every DRM driver is a :c:type:`struct drm_driver
 <drm_driver>` structure. Drivers typically statically initialize
 a drm_driver structure, and then pass it to
-:c:func:`drm_dev_alloc()` to allocate a device instance. After the
+drm_dev_alloc() to allocate a device instance. After the
 device instance is fully initialized it can be registered (which makes
-it accessible from userspace) using :c:func:`drm_dev_register()`.
+it accessible from userspace) using drm_dev_register().
 
 The :c:type:`struct drm_driver <drm_driver>` structure
 contains static information that describes the driver and features it
diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 23a3c986ef6d..906771e03103 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -3,7 +3,7 @@ Kernel Mode Setting (KMS)
 =========================
 
 Drivers must initialize the mode setting core by calling
-:c:func:`drm_mode_config_init()` on the DRM device. The function
+drm_mode_config_init() on the DRM device. The function
 initializes the :c:type:`struct drm_device <drm_device>`
 mode_config field and never fails. Once done, mode configuration must
 be setup by initializing the following fields.
@@ -181,8 +181,7 @@ Setting`_). The somewhat surprising part here is that properties are not
 directly instantiated on each object, but free-standing mode objects themselves,
 represented by :c:type:`struct drm_property <drm_property>`, which only specify
 the type and value range of a property. Any given property can be attached
-multiple times to different objects using :c:func:`drm_object_attach_property()
-<drm_object_attach_property>`.
+multiple times to different objects using drm_object_attach_property().
 
 .. kernel-doc:: include/drm/drm_mode_object.h
    :internal:
@@ -260,7 +259,8 @@ Taken all together there's two consequences for the atomic design:
   drm_connector_state <drm_connector_state>` for connectors. These are the only
   objects with userspace-visible and settable state. For internal state drivers
   can subclass these structures through embeddeding, or add entirely new state
-  structures for their globally shared hardware functions.
+  structures for their globally shared hardware functions, see :c:type:`struct
+  drm_private_state<drm_private_state>`.
 
 - An atomic update is assembled and validated as an entirely free-standing pile
   of structures within the :c:type:`drm_atomic_state <drm_atomic_state>`
@@ -269,6 +269,14 @@ Taken all together there's two consequences for the atomic design:
   to the driver and modeset objects. This way rolling back an update boils down
   to releasing memory and unreferencing objects like framebuffers.
 
+Locking of atomic state structures is internally using :c:type:`struct
+drm_modeset_lock <drm_modeset_lock>`. As a general rule the locking shouldn't be
+exposed to drivers, instead the right locks should be automatically acquired by
+any function that duplicates or peeks into a state, like e.g.
+drm_atomic_get_crtc_state().  Locking only protects the software data
+structure, ordering of committing state changes to hardware is sequenced using
+:c:type:`struct drm_crtc_commit <drm_crtc_commit>`.
+
 Read on in this chapter, and also in :ref:`drm_atomic_helper` for more detailed
 coverage of specific topics.
 
@@ -479,6 +487,9 @@ Color Management Properties
 .. kernel-doc:: drivers/gpu/drm/drm_color_mgmt.c
    :export:
 
+.. kernel-doc:: include/drm/drm_color_mgmt.h
+   :internal:
+
 Tile Group Property
 -------------------
 
diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index 59619296c84b..c77b32601260 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -149,19 +149,19 @@ struct :c:type:`struct drm_gem_object <drm_gem_object>`.
 To create a GEM object, a driver allocates memory for an instance of its
 specific GEM object type and initializes the embedded struct
 :c:type:`struct drm_gem_object <drm_gem_object>` with a call
-to :c:func:`drm_gem_object_init()`. The function takes a pointer
+to drm_gem_object_init(). The function takes a pointer
 to the DRM device, a pointer to the GEM object and the buffer object
 size in bytes.
 
 GEM uses shmem to allocate anonymous pageable memory.
-:c:func:`drm_gem_object_init()` will create an shmfs file of the
+drm_gem_object_init() will create an shmfs file of the
 requested size and store it into the struct :c:type:`struct
 drm_gem_object <drm_gem_object>` filp field. The memory is
 used as either main storage for the object when the graphics hardware
 uses system memory directly or as a backing store otherwise.
 
 Drivers are responsible for the actual physical pages allocation by
-calling :c:func:`shmem_read_mapping_page_gfp()` for each page.
+calling shmem_read_mapping_page_gfp() for each page.
 Note that they can decide to allocate pages when initializing the GEM
 object, or to delay allocation until the memory is needed (for instance
 when a page fault occurs as a result of a userspace memory access or
@@ -170,20 +170,18 @@ when the driver needs to start a DMA transfer involving the memory).
 Anonymous pageable memory allocation is not always desired, for instance
 when the hardware requires physically contiguous system memory as is
 often the case in embedded devices. Drivers can create GEM objects with
-no shmfs backing (called private GEM objects) by initializing them with
-a call to :c:func:`drm_gem_private_object_init()` instead of
-:c:func:`drm_gem_object_init()`. Storage for private GEM objects
-must be managed by drivers.
+no shmfs backing (called private GEM objects) by initializing them with a call
+to drm_gem_private_object_init() instead of drm_gem_object_init(). Storage for
+private GEM objects must be managed by drivers.
 
 GEM Objects Lifetime
 --------------------
 
 All GEM objects are reference-counted by the GEM core. References can be
-acquired and release by :c:func:`calling drm_gem_object_get()` and
-:c:func:`drm_gem_object_put()` respectively. The caller must hold the
-:c:type:`struct drm_device <drm_device>` struct_mutex lock when calling
-:c:func:`drm_gem_object_get()`. As a convenience, GEM provides
-:c:func:`drm_gem_object_put_unlocked()` functions that can be called without
+acquired and release by calling drm_gem_object_get() and drm_gem_object_put()
+respectively. The caller must hold the :c:type:`struct drm_device <drm_device>`
+struct_mutex lock when calling drm_gem_object_get(). As a convenience, GEM
+provides drm_gem_object_put_unlocked() functions that can be called without
 holding the lock.
 
 When the last reference to a GEM object is released the GEM core calls
@@ -194,7 +192,7 @@ free the GEM object and all associated resources.
 void (\*gem_free_object) (struct drm_gem_object \*obj); Drivers are
 responsible for freeing all GEM object resources. This includes the
 resources created by the GEM core, which need to be released with
-:c:func:`drm_gem_object_release()`.
+drm_gem_object_release().
 
 GEM Objects Naming
 ------------------
@@ -210,13 +208,11 @@ to the GEM object in other standard or driver-specific ioctls. Closing a
 DRM file handle frees all its GEM handles and dereferences the
 associated GEM objects.
 
-To create a handle for a GEM object drivers call
-:c:func:`drm_gem_handle_create()`. The function takes a pointer
-to the DRM file and the GEM object and returns a locally unique handle.
-When the handle is no longer needed drivers delete it with a call to
-:c:func:`drm_gem_handle_delete()`. Finally the GEM object
-associated with a handle can be retrieved by a call to
-:c:func:`drm_gem_object_lookup()`.
+To create a handle for a GEM object drivers call drm_gem_handle_create(). The
+function takes a pointer to the DRM file and the GEM object and returns a
+locally unique handle.  When the handle is no longer needed drivers delete it
+with a call to drm_gem_handle_delete(). Finally the GEM object associated with a
+handle can be retrieved by a call to drm_gem_object_lookup().
 
 Handles don't take ownership of GEM objects, they only take a reference
 to the object that will be dropped when the handle is destroyed. To
@@ -258,7 +254,7 @@ The mmap system call can't be used directly to map GEM objects, as they
 don't have their own file handle. Two alternative methods currently
 co-exist to map GEM objects to userspace. The first method uses a
 driver-specific ioctl to perform the mapping operation, calling
-:c:func:`do_mmap()` under the hood. This is often considered
+do_mmap() under the hood. This is often considered
 dubious, seems to be discouraged for new GEM-enabled drivers, and will
 thus not be described here.
 
@@ -267,23 +263,22 @@ The second method uses the mmap system call on the DRM file handle. void
 offset); DRM identifies the GEM object to be mapped by a fake offset
 passed through the mmap offset argument. Prior to being mapped, a GEM
 object must thus be associated with a fake offset. To do so, drivers
-must call :c:func:`drm_gem_create_mmap_offset()` on the object.
+must call drm_gem_create_mmap_offset() on the object.
 
 Once allocated, the fake offset value must be passed to the application
 in a driver-specific way and can then be used as the mmap offset
 argument.
 
-The GEM core provides a helper method :c:func:`drm_gem_mmap()` to
+The GEM core provides a helper method drm_gem_mmap() to
 handle object mapping. The method can be set directly as the mmap file
 operation handler. It will look up the GEM object based on the offset
 value and set the VMA operations to the :c:type:`struct drm_driver
-<drm_driver>` gem_vm_ops field. Note that
-:c:func:`drm_gem_mmap()` doesn't map memory to userspace, but
-relies on the driver-provided fault handler to map pages individually.
+<drm_driver>` gem_vm_ops field. Note that drm_gem_mmap() doesn't map memory to
+userspace, but relies on the driver-provided fault handler to map pages
+individually.
 
-To use :c:func:`drm_gem_mmap()`, drivers must fill the struct
-:c:type:`struct drm_driver <drm_driver>` gem_vm_ops field
-with a pointer to VM operations.
+To use drm_gem_mmap(), drivers must fill the struct :c:type:`struct drm_driver
+<drm_driver>` gem_vm_ops field with a pointer to VM operations.
 
 The VM operations is a :c:type:`struct vm_operations_struct <vm_operations_struct>`
 made up of several fields, the more interesting ones being:
@@ -298,9 +293,8 @@ made up of several fields, the more interesting ones being:
 
 
 The open and close operations must update the GEM object reference
-count. Drivers can use the :c:func:`drm_gem_vm_open()` and
-:c:func:`drm_gem_vm_close()` helper functions directly as open
-and close handlers.
+count. Drivers can use the drm_gem_vm_open() and drm_gem_vm_close() helper
+functions directly as open and close handlers.
 
 The fault operation handler is responsible for mapping individual pages
 to userspace when a page fault occurs. Depending on the memory
@@ -312,12 +306,12 @@ Drivers that want to map the GEM object upfront instead of handling page
 faults can implement their own mmap file operation handler.
 
 For platforms without MMU the GEM core provides a helper method
-:c:func:`drm_gem_cma_get_unmapped_area`. The mmap() routines will call
-this to get a proposed address for the mapping.
+drm_gem_cma_get_unmapped_area(). The mmap() routines will call this to get a
+proposed address for the mapping.
 
-To use :c:func:`drm_gem_cma_get_unmapped_area`, drivers must fill the
-struct :c:type:`struct file_operations <file_operations>` get_unmapped_area
-field with a pointer on :c:func:`drm_gem_cma_get_unmapped_area`.
+To use drm_gem_cma_get_unmapped_area(), drivers must fill the struct
+:c:type:`struct file_operations <file_operations>` get_unmapped_area field with
+a pointer on drm_gem_cma_get_unmapped_area().
 
 More detailed information about get_unmapped_area can be found in
 Documentation/nommu-mmap.txt
diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst
index 94f90521f58c..56fec6ed1ad8 100644
--- a/Documentation/gpu/drm-uapi.rst
+++ b/Documentation/gpu/drm-uapi.rst
@@ -254,36 +254,45 @@ Validating changes with IGT
 There's a collection of tests that aims to cover the whole functionality of
 DRM drivers and that can be used to check that changes to DRM drivers or the
 core don't regress existing functionality. This test suite is called IGT and
-its code can be found in https://cgit.freedesktop.org/drm/igt-gpu-tools/.
+its code and instructions to build and run can be found in
+https://gitlab.freedesktop.org/drm/igt-gpu-tools/.
 
-To build IGT, start by installing its build dependencies. In Debian-based
-systems::
+Using VKMS to test DRM API
+--------------------------
 
-	# apt-get build-dep intel-gpu-tools
+VKMS is a software-only model of a KMS driver that is useful for testing
+and for running compositors. VKMS aims to enable a virtual display without
+the need for a hardware display capability. These characteristics made VKMS
+a perfect tool for validating the DRM core behavior and also support the
+compositor developer. VKMS makes it possible to test DRM functions in a
+virtual machine without display, simplifying the validation of some of the
+core changes.
 
-And in Fedora-based systems::
+To Validate changes in DRM API with VKMS, start setting the kernel: make
+sure to enable VKMS module; compile the kernel with the VKMS enabled and
+install it in the target machine. VKMS can be run in a Virtual Machine
+(QEMU, virtme or similar). It's recommended the use of KVM with the minimum
+of 1GB of RAM and four cores.
 
-	# dnf builddep intel-gpu-tools
+It's possible to run the IGT-tests in a VM in two ways:
 
-Then clone the repository::
+	1. Use IGT inside a VM
+	2. Use IGT from the host machine and write the results in a shared directory.
 
-	$ git clone git://anongit.freedesktop.org/drm/igt-gpu-tools
+As follow, there is an example of using a VM with a shared directory with
+the host machine to run igt-tests. As an example it's used virtme::
 
-Configure the build system and start the build::
+	$ virtme-run --rwdir /path/for/shared_dir --kdir=path/for/kernel/directory --mods=auto
 
-	$ cd igt-gpu-tools && ./autogen.sh && make -j6
+Run the igt-tests in the guest machine, as example it's ran the 'kms_flip'
+tests::
 
-Download the piglit dependency::
+	$ /path/for/igt-gpu-tools/scripts/run-tests.sh -p -s -t "kms_flip.*" -v
 
-	$ ./scripts/run-tests.sh -d
-
-And run the tests::
-
-	$ ./scripts/run-tests.sh -t kms -t core -s
-
-run-tests.sh is a wrapper around piglit that will execute the tests matching
-the -t options. A report in HTML format will be available in
-./results/html/index.html. Results can be compared with piglit.
+In this example, instead of build the igt_runner, Piglit is used
+(-p option); it's created html summary of the tests results and it's saved
+in the folder "igt-gpu-tools/results"; it's executed only the igt-tests
+matching the -t option.
 
 Display CRC Support
 -------------------
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index d0947c5c4ab8..e539c42a3e78 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -466,9 +466,6 @@ GuC-based command submission
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
    :doc: GuC-based command submission
 
-.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
-   :internal:
-
 HuC
 ---
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 6792fa9b6b6b..bc869b23fc39 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -142,14 +142,14 @@ Contact: Daniel Vetter, respective driver maintainers
 
 Level: Advanced
 
-Convert instances of dev_info/dev_err/dev_warn to their DRM_DEV_* equivalent
-----------------------------------------------------------------------------
+Convert logging to drm_* functions with drm_device paramater
+------------------------------------------------------------
 
 For drivers which could have multiple instances, it is necessary to
 differentiate between which is which in the logs. Since DRM_INFO/WARN/ERROR
 don't do this, drivers used dev_info/warn/err to make this differentiation. We
-now have DRM_DEV_* variants of the drm print macros, so we can start to convert
-those drivers back to using drm-formwatted specific log messages.
+now have drm_* variants of the drm print functions, so we can start to convert
+those drivers back to using drm-formatted specific log messages.
 
 Before you start this conversion please contact the relevant maintainers to make
 sure your work will be merged - not everyone agrees that the DRM dmesg macros
@@ -171,23 +171,40 @@ Contact: Maintainer of the driver you plan to convert
 
 Level: Intermediate
 
-Convert drivers to use drm_fb_helper_fbdev_setup/teardown()
------------------------------------------------------------
+Convert drivers to use drm_fbdev_generic_setup()
+------------------------------------------------
 
-Most drivers can use drm_fb_helper_fbdev_setup() except maybe:
+Most drivers can use drm_fbdev_generic_setup(). Driver have to implement
+atomic modesetting and GEM vmap support. Current generic fbdev emulation
+expects the framebuffer in system memory (or system-like memory).
 
-- amdgpu which has special logic to decide whether to call
-  drm_helper_disable_unused_functions()
+Contact: Maintainer of the driver you plan to convert
+
+Level: Intermediate
 
-- armada which isn't atomic and doesn't call
-  drm_helper_disable_unused_functions()
+drm_framebuffer_funcs and drm_mode_config_funcs.fb_create cleanup
+-----------------------------------------------------------------
 
-- i915 which calls drm_fb_helper_initial_config() in a worker
+A lot more drivers could be switched over to the drm_gem_framebuffer helpers.
+Various hold-ups:
 
-Drivers that use drm_framebuffer_remove() to clean up the fbdev framebuffer can
-probably use drm_fb_helper_fbdev_teardown().
+- Need to switch over to the generic dirty tracking code using
+  drm_atomic_helper_dirtyfb first (e.g. qxl).
 
-Contact: Maintainer of the driver you plan to convert
+- Need to switch to drm_fbdev_generic_setup(), otherwise a lot of the custom fb
+  setup code can't be deleted.
+
+- Many drivers wrap drm_gem_fb_create() only to check for valid formats. For
+  atomic drivers we could check for valid formats by calling
+  drm_plane_check_pixel_format() against all planes, and pass if any plane
+  supports the format. For non-atomic that's not possible since like the format
+  list for the primary plane is fake and we'd therefor reject valid formats.
+
+- Many drivers subclass drm_framebuffer, we'd need a embedding compatible
+  version of the varios drm_gem_fb_create functions. Maybe called
+  drm_gem_fb_create/_with_dirty/_with_funcs as needed.
+
+Contact: Daniel Vetter
 
 Level: Intermediate
 
@@ -328,8 +345,8 @@ drm_fb_helper tasks
   these igt tests need to be fixed: kms_fbcon_fbt@psr and
   kms_fbcon_fbt@psr-suspend.
 
-- The max connector argument for drm_fb_helper_init() and
-  drm_fb_helper_fbdev_setup() isn't used anymore and can be removed.
+- The max connector argument for drm_fb_helper_init() isn't used anymore and
+  can be removed.
 
 - The helper doesn't keep an array of connectors anymore so these can be
   removed: drm_fb_helper_single_add_all_connectors(),
@@ -351,6 +368,23 @@ connector register/unregister fixes
 
 Level: Intermediate
 
+Remove load/unload callbacks from all non-DRIVER_LEGACY drivers
+---------------------------------------------------------------
+
+The load/unload callbacks in struct &drm_driver are very much midlayers, plus
+for historical reasons they get the ordering wrong (and we can't fix that)
+between setting up the &drm_driver structure and calling drm_dev_register().
+
+- Rework drivers to no longer use the load/unload callbacks, directly coding the
+  load/unload sequence into the driver's probe function.
+
+- Once all non-DRIVER_LEGACY drivers are converted, disallow the load/unload
+  callbacks for all modern drivers.
+
+Contact: Daniel Vetter
+
+Level: Intermediate
+
 Core refactorings
 =================
 
diff --git a/Documentation/kbuild/kconfig-language.rst b/Documentation/kbuild/kconfig-language.rst
index 231e6a64957f..d0111dd26410 100644
--- a/Documentation/kbuild/kconfig-language.rst
+++ b/Documentation/kbuild/kconfig-language.rst
@@ -591,7 +591,8 @@ The two different resolutions for b) can be tested in the sample Kconfig file
 Documentation/kbuild/Kconfig.recursion-issue-02.
 
 Below is a list of examples of prior fixes for these types of recursive issues;
-all errors appear to involve one or more select's and one or more "depends on".
+all errors appear to involve one or more "select" statements and one or more
+"depends on".
 
 ============    ===================================
 commit          fix
@@ -653,7 +654,7 @@ the use of the xconfig configurator [1]_. Work should be done to confirm if
 the deduced semantics matches our intended Kconfig design goals.
 
 Having well defined semantics can be useful for tools for practical
-evaluation of depenencies, for instance one such use known case was work to
+evaluation of dependencies, for instance one such case was work to
 express in boolean abstraction of the inferred semantics of Kconfig to
 translate Kconfig logic into boolean formulas and run a SAT solver on this to
 find dead code / features (always inactive), 114 dead features were found in
@@ -680,7 +681,7 @@ abstraction the inferred semantics of Kconfig to translate Kconfig logic into
 boolean formulas and run a SAT solver on it [5]_. Another known related project
 is CADOS [6]_ (former VAMOS [7]_) and the tools, mainly undertaker [8]_, which
 has been introduced first with [9]_.  The basic concept of undertaker is to
-exract variability models from Kconfig, and put them together with a
+extract variability models from Kconfig and put them together with a
 propositional formula extracted from CPP #ifdefs and build-rules into a SAT
 solver in order to find dead code, dead files, and dead symbols. If using a SAT
 solver is desirable on Kconfig one approach would be to evaluate repurposing
diff --git a/Documentation/kbuild/kconfig.rst b/Documentation/kbuild/kconfig.rst
index a9a855f894b3..dce6801d66c9 100644
--- a/Documentation/kbuild/kconfig.rst
+++ b/Documentation/kbuild/kconfig.rst
@@ -154,11 +154,6 @@ KCONFIG_AUTOCONFIG
 This environment variable can be set to specify the path & name of the
 "auto.conf" file.  Its default value is "include/config/auto.conf".
 
-KCONFIG_TRISTATE
-----------------
-This environment variable can be set to specify the path & name of the
-"tristate.conf" file.  Its default value is "include/config/tristate.conf".
-
 KCONFIG_AUTOHEADER
 ------------------
 This environment variable can be set to specify the path & name of the
diff --git a/Documentation/media/kapi/dtv-frontend.rst b/Documentation/media/kapi/dtv-frontend.rst
index fbc5517c8d5a..b362109bb131 100644
--- a/Documentation/media/kapi/dtv-frontend.rst
+++ b/Documentation/media/kapi/dtv-frontend.rst
@@ -15,8 +15,8 @@ The header file for this API is named ``dvb_frontend.h`` and located in
 Demodulator driver
 ^^^^^^^^^^^^^^^^^^
 
-The demodulator driver is responsible to talk with the decoding part of the
-hardware. Such driver should implement :c:type:`dvb_frontend_ops`, with
+The demodulator driver is responsible for talking with the decoding part of the
+hardware. Such driver should implement :c:type:`dvb_frontend_ops`, which
 tells what type of digital TV standards are supported, and points to a
 series of functions that allow the DVB core to command the hardware via
 the code under ``include/media/dvb_frontend.c``.
@@ -120,7 +120,7 @@ Satellite TV reception is::
 
 .. |delta|   unicode:: U+00394
 
-The ``include/media/dvb_frontend.c`` has a kernel thread with is
+The ``include/media/dvb_frontend.c`` has a kernel thread which is
 responsible for tuning the device. It supports multiple algorithms to
 detect a channel, as defined at enum :c:func:`dvbfe_algo`.
 
@@ -220,11 +220,11 @@ Signal strength (:ref:`DTV-STAT-SIGNAL-STRENGTH`)
   - As the gain is visible through the set of registers that adjust the gain,
     typically, this statistics is always available [#f3]_.
 
-  - Drivers should try to make it available all the times, as this statistics
+  - Drivers should try to make it available all the times, as these statistics
     can be used when adjusting an antenna position and to check for troubles
     at the cabling.
 
-  .. [#f3] On a few devices, the gain keeps floating if no carrier.
+  .. [#f3] On a few devices, the gain keeps floating if there is no carrier.
      On such devices, strength report should check first if carrier is
      detected at the tuner (``FE_HAS_CARRIER``, see :c:type:`fe_status`),
      and otherwise return the lowest possible value.
@@ -232,7 +232,7 @@ Signal strength (:ref:`DTV-STAT-SIGNAL-STRENGTH`)
 Carrier Signal to Noise ratio (:ref:`DTV-STAT-CNR`)
   - Signal to Noise ratio for the main carrier.
 
-  - Signal to Noise measurement depends on the device. On some hardware, is
+  - Signal to Noise measurement depends on the device. On some hardware, it is
     available when the main carrier is detected. On those hardware, CNR
     measurement usually comes from the tuner (e. g. after ``FE_HAS_CARRIER``,
     see :c:type:`fe_status`).
@@ -323,8 +323,8 @@ A typical example of the logic that handle status and statistics is::
 		.read_status = foo_get_status_and_stats,
 	};
 
-Statistics collect
-^^^^^^^^^^^^^^^^^^
+Statistics collection
+^^^^^^^^^^^^^^^^^^^^^
 
 On almost all frontend hardware, the bit and byte counts are stored by
 the hardware after a certain amount of time or after the total bit/block
diff --git a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
index d0902f356d65..2535b77e3459 100644
--- a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
@@ -177,7 +177,7 @@ Available follower modes are:
       - ``CEC_MODE_MONITOR``
       - 0xe0
       - Put the file descriptor into monitor mode. Can only be used in
-	combination with :ref:`CEC_MODE_NO_INITIATOR <CEC-MODE-NO-INITIATOR>`,i
+	combination with :ref:`CEC_MODE_NO_INITIATOR <CEC-MODE-NO-INITIATOR>`,
 	otherwise the ``EINVAL`` error code will be returned.
 	In monitor mode all messages this CEC
 	device transmits and all messages it receives (both broadcast
diff --git a/Documentation/media/uapi/dvb/video-get-event.rst b/Documentation/media/uapi/dvb/video-get-event.rst
index def6c40db601..7f03fbe3d3b0 100644
--- a/Documentation/media/uapi/dvb/video-get-event.rst
+++ b/Documentation/media/uapi/dvb/video-get-event.rst
@@ -81,7 +81,7 @@ for this ioctl call.
 	#define VIDEO_EVENT_FRAME_RATE_CHANGED	2
 	#define VIDEO_EVENT_DECODER_STOPPED 	3
 	#define VIDEO_EVENT_VSYNC 		4
-		__kernel_time_t timestamp;
+		long timestamp;
 		union {
 			video_size_t size;
 			unsigned int frame_rate;	/* in frames per 1000sec */
diff --git a/Documentation/media/uapi/dvb/video_types.rst b/Documentation/media/uapi/dvb/video_types.rst
index 479942ce6fb8..2697400ccf62 100644
--- a/Documentation/media/uapi/dvb/video_types.rst
+++ b/Documentation/media/uapi/dvb/video_types.rst
@@ -170,7 +170,7 @@ VIDEO_GET_EVENT call.
     #define VIDEO_EVENT_FRAME_RATE_CHANGED  2
     #define VIDEO_EVENT_DECODER_STOPPED     3
     #define VIDEO_EVENT_VSYNC       4
-	__kernel_time_t timestamp;
+	long timestamp;
 	union {
 	    video_size_t size;
 	    unsigned int frame_rate;    /* in frames per 1000sec */
diff --git a/Documentation/media/uapi/v4l/pixfmt-reserved.rst b/Documentation/media/uapi/v4l/pixfmt-reserved.rst
index b2cd155e691b..7d98a7bf9f1f 100644
--- a/Documentation/media/uapi/v4l/pixfmt-reserved.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-reserved.rst
@@ -55,8 +55,7 @@ please make a proposal on the linux-media mailing list.
 
       - ``V4L2_PIX_FMT_HM12``
       - 'HM12'
-      - YUV 4:2:0 format used by the IVTV driver,
-	`http://www.ivtvdriver.org/ <http://www.ivtvdriver.org/>`__
+      - YUV 4:2:0 format used by the IVTV driver.
 
 	The format is documented in the kernel sources in the file
 	``Documentation/media/v4l-drivers/cx2341x.rst``
diff --git a/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst b/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst
index 960851275f23..045540bc0d86 100644
--- a/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-srggb12p.rst
@@ -13,7 +13,7 @@
 .. _v4l2-pix-fmt-sgrbg12p:
 
 *******************************************************************************************************************************
-V4L2_PIX_FMT_SRGGB12P ('pRAA'), V4L2_PIX_FMT_SGRBG12P ('pgAA'), V4L2_PIX_FMT_SGBRG12P ('pGAA'), V4L2_PIX_FMT_SBGGR12P ('pBAA'),
+V4L2_PIX_FMT_SRGGB12P ('pRCC'), V4L2_PIX_FMT_SGRBG12P ('pgCC'), V4L2_PIX_FMT_SGBRG12P ('pGCC'), V4L2_PIX_FMT_SBGGR12P ('pBCC'),
 *******************************************************************************************************************************
 
 
diff --git a/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst b/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst
index 1a988d7e7ff8..051ae3d05bc3 100644
--- a/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst
@@ -13,7 +13,7 @@
 .. _v4l2-pix-fmt-sgrbg14p:
 
 *******************************************************************************************************************************
-V4L2_PIX_FMT_SRGGB14P ('pRCC'), V4L2_PIX_FMT_SGRBG14P ('pgCC'), V4L2_PIX_FMT_SGBRG14P ('pGCC'), V4L2_PIX_FMT_SBGGR14P ('pBCC'),
+V4L2_PIX_FMT_SRGGB14P ('pREE'), V4L2_PIX_FMT_SGRBG14P ('pgEE'), V4L2_PIX_FMT_SGBRG14P ('pGEE'), V4L2_PIX_FMT_SBGGR14P ('pBEE'),
 *******************************************************************************************************************************
 
 *man V4L2_PIX_FMT_SRGGB14P(2)*
diff --git a/Documentation/media/uapi/v4l/pixfmt-tch-td16.rst b/Documentation/media/uapi/v4l/pixfmt-tch-td16.rst
index 4031b175257c..6f1be873bec1 100644
--- a/Documentation/media/uapi/v4l/pixfmt-tch-td16.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-tch-td16.rst
@@ -15,7 +15,7 @@ V4L2_TCH_FMT_DELTA_TD16 ('TD16')
 
 *man V4L2_TCH_FMT_DELTA_TD16(2)*
 
-16-bit signed Touch Delta
+16-bit signed little endian Touch Delta
 
 
 Description
@@ -37,38 +37,38 @@ Each cell is one byte.
     :widths:       2 1 1 1 1 1 1 1 1
 
     * - start + 0:
-      - D'\ :sub:`00high`
       - D'\ :sub:`00low`
-      - D'\ :sub:`01high`
+      - D'\ :sub:`00high`
       - D'\ :sub:`01low`
-      - D'\ :sub:`02high`
+      - D'\ :sub:`01high`
       - D'\ :sub:`02low`
-      - D'\ :sub:`03high`
+      - D'\ :sub:`02high`
       - D'\ :sub:`03low`
+      - D'\ :sub:`03high`
     * - start + 8:
-      - D'\ :sub:`10high`
       - D'\ :sub:`10low`
-      - D'\ :sub:`11high`
+      - D'\ :sub:`10high`
       - D'\ :sub:`11low`
-      - D'\ :sub:`12high`
+      - D'\ :sub:`11high`
       - D'\ :sub:`12low`
-      - D'\ :sub:`13high`
+      - D'\ :sub:`12high`
       - D'\ :sub:`13low`
+      - D'\ :sub:`13high`
     * - start + 16:
-      - D'\ :sub:`20high`
       - D'\ :sub:`20low`
-      - D'\ :sub:`21high`
+      - D'\ :sub:`20high`
       - D'\ :sub:`21low`
-      - D'\ :sub:`22high`
+      - D'\ :sub:`21high`
       - D'\ :sub:`22low`
-      - D'\ :sub:`23high`
+      - D'\ :sub:`22high`
       - D'\ :sub:`23low`
+      - D'\ :sub:`23high`
     * - start + 24:
-      - D'\ :sub:`30high`
       - D'\ :sub:`30low`
-      - D'\ :sub:`31high`
+      - D'\ :sub:`30high`
       - D'\ :sub:`31low`
-      - D'\ :sub:`32high`
+      - D'\ :sub:`31high`
       - D'\ :sub:`32low`
-      - D'\ :sub:`33high`
+      - D'\ :sub:`32high`
       - D'\ :sub:`33low`
+      - D'\ :sub:`33high`
diff --git a/Documentation/media/uapi/v4l/pixfmt-tch-tu16.rst b/Documentation/media/uapi/v4l/pixfmt-tch-tu16.rst
index 8278543be99a..cb3da6687a58 100644
--- a/Documentation/media/uapi/v4l/pixfmt-tch-tu16.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-tch-tu16.rst
@@ -15,7 +15,7 @@ V4L2_TCH_FMT_TU16 ('TU16')
 
 *man V4L2_TCH_FMT_TU16(2)*
 
-16-bit unsigned raw touch data
+16-bit unsigned little endian raw touch data
 
 
 Description
@@ -36,38 +36,38 @@ Each cell is one byte.
     :widths:       2 1 1 1 1 1 1 1 1
 
     * - start + 0:
-      - R'\ :sub:`00high`
       - R'\ :sub:`00low`
-      - R'\ :sub:`01high`
+      - R'\ :sub:`00high`
       - R'\ :sub:`01low`
-      - R'\ :sub:`02high`
+      - R'\ :sub:`01high`
       - R'\ :sub:`02low`
-      - R'\ :sub:`03high`
+      - R'\ :sub:`02high`
       - R'\ :sub:`03low`
+      - R'\ :sub:`03high`
     * - start + 8:
-      - R'\ :sub:`10high`
       - R'\ :sub:`10low`
-      - R'\ :sub:`11high`
+      - R'\ :sub:`10high`
       - R'\ :sub:`11low`
-      - R'\ :sub:`12high`
+      - R'\ :sub:`11high`
       - R'\ :sub:`12low`
-      - R'\ :sub:`13high`
+      - R'\ :sub:`12high`
       - R'\ :sub:`13low`
+      - R'\ :sub:`13high`
     * - start + 16:
-      - R'\ :sub:`20high`
       - R'\ :sub:`20low`
-      - R'\ :sub:`21high`
+      - R'\ :sub:`20high`
       - R'\ :sub:`21low`
-      - R'\ :sub:`22high`
+      - R'\ :sub:`21high`
       - R'\ :sub:`22low`
-      - R'\ :sub:`23high`
+      - R'\ :sub:`22high`
       - R'\ :sub:`23low`
+      - R'\ :sub:`23high`
     * - start + 24:
-      - R'\ :sub:`30high`
       - R'\ :sub:`30low`
-      - R'\ :sub:`31high`
+      - R'\ :sub:`30high`
       - R'\ :sub:`31low`
-      - R'\ :sub:`32high`
+      - R'\ :sub:`31high`
       - R'\ :sub:`32low`
-      - R'\ :sub:`33high`
+      - R'\ :sub:`32high`
       - R'\ :sub:`33low`
+      - R'\ :sub:`33high`
diff --git a/Documentation/media/uapi/v4l/vidioc-enum-fmt.rst b/Documentation/media/uapi/v4l/vidioc-enum-fmt.rst
index 399ef1062bac..8ca6ab701e4a 100644
--- a/Documentation/media/uapi/v4l/vidioc-enum-fmt.rst
+++ b/Documentation/media/uapi/v4l/vidioc-enum-fmt.rst
@@ -44,7 +44,9 @@ To enumerate image formats applications initialize the ``type`` and
 the :ref:`VIDIOC_ENUM_FMT` ioctl with a pointer to this structure. Drivers
 fill the rest of the structure or return an ``EINVAL`` error code. All
 formats are enumerable by beginning at index zero and incrementing by
-one until ``EINVAL`` is returned.
+one until ``EINVAL`` is returned. If applicable, drivers shall return
+formats in preference order, where preferred formats are returned before
+(that is, with lower ``index`` value) less-preferred formats.
 
 .. note::
 
diff --git a/Documentation/media/uapi/v4l/vidioc-g-dv-timings.rst b/Documentation/media/uapi/v4l/vidioc-g-dv-timings.rst
index 5712bd48e687..5c675cbac4cf 100644
--- a/Documentation/media/uapi/v4l/vidioc-g-dv-timings.rst
+++ b/Documentation/media/uapi/v4l/vidioc-g-dv-timings.rst
@@ -279,7 +279,7 @@ EBUSY
 	then it will set this flag to signal this to the application.
     * - ``V4L2_DV_FL_HALF_LINE``
       - Specific to interlaced formats: if set, then the vertical
-	backporch of field 1 (aka the odd field) is really one half-line
+	frontporch of field 1 (aka the odd field) is really one half-line
 	longer and the vertical backporch of field 2 (aka the even field)
 	is really one half-line shorter, so each field has exactly the
 	same number of half-lines. Whether half-lines can be detected or
diff --git a/Documentation/media/v4l-drivers/cx18.rst b/Documentation/media/v4l-drivers/cx18.rst
deleted file mode 100644
index 16895a734bae..000000000000
--- a/Documentation/media/v4l-drivers/cx18.rst
+++ /dev/null
@@ -1,39 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-The cx18 driver
-===============
-
-.. note::
-
-   This documentation is outdated.
-
-Some notes regarding the cx18 driver for the Conexant CX23418 MPEG
-encoder chip:
-
-1) Currently supported are:
-
-	- Hauppauge HVR-1600
-	- Compro VideoMate H900
-	- Yuan MPC718
-	- Conexant Raptor PAL/SECAM devkit
-
-2) Some people have problems getting the i2c bus to work.
-   The symptom is that the eeprom cannot be read and the card is
-   unusable. This is probably fixed, but if you have problems
-   then post to the video4linux or ivtv-users mailing list.
-
-3) VBI (raw or sliced) has not yet been implemented.
-
-4) MPEG indexing is not yet implemented.
-
-5) The driver is still a bit rough around the edges, this should
-   improve over time.
-
-
-Firmware:
-
-You can obtain the firmware files here:
-
-http://dl.ivtvdriver.org/ivtv/firmware/cx18-firmware.tar.gz
-
-Untar and copy the .fw files to your firmware directory.
diff --git a/Documentation/media/v4l-drivers/index.rst b/Documentation/media/v4l-drivers/index.rst
index c4c78a28654c..b41fea23fe5d 100644
--- a/Documentation/media/v4l-drivers/index.rst
+++ b/Documentation/media/v4l-drivers/index.rst
@@ -38,7 +38,6 @@ For more details see the file COPYING in the source distribution of Linux.
 	bttv
 	cafe_ccic
 	cpia2
-	cx18
 	cx2341x
 	cx88
 	davinci-vpbe
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index ec3b5865c1be..7146da061693 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1868,12 +1868,16 @@ There are some more advanced barrier functions:
  (*) smp_mb__before_atomic();
  (*) smp_mb__after_atomic();
 
-     These are for use with atomic (such as add, subtract, increment and
-     decrement) functions that don't return a value, especially when used for
-     reference counting.  These functions do not imply memory barriers.
-
-     These are also used for atomic bitop functions that do not return a
-     value (such as set_bit and clear_bit).
+     These are for use with atomic RMW functions that do not imply memory
+     barriers, but where the code needs a memory barrier. Examples for atomic
+     RMW functions that do not imply are memory barrier are e.g. add,
+     subtract, (failed) conditional operations, _relaxed functions,
+     but not atomic_read or atomic_set. A common example where a memory
+     barrier may be required is when atomic ops are used for reference
+     counting.
+
+     These are also used for atomic RMW bitop functions that do not imply a
+     memory barrier (such as set_bit and clear_bit).
 
      As an example, consider a piece of code that marks an object as being dead
      and then decrements the object's reference count:
diff --git a/Documentation/networking/nf_flowtable.txt b/Documentation/networking/nf_flowtable.txt
index ca2136c76042..0bf32d1121be 100644
--- a/Documentation/networking/nf_flowtable.txt
+++ b/Documentation/networking/nf_flowtable.txt
@@ -76,7 +76,7 @@ flowtable and add one rule to your forward chain.
 
         table inet x {
 		flowtable f {
-			hook ingress priority 0 devices = { eth0, eth1 };
+			hook ingress priority 0; devices = { eth0, eth1 };
 		}
                 chain y {
                         type filter hook forward priority 0; policy accept;
diff --git a/Documentation/powerpc/imc.rst b/Documentation/powerpc/imc.rst
new file mode 100644
index 000000000000..633bcee7dc85
--- /dev/null
+++ b/Documentation/powerpc/imc.rst
@@ -0,0 +1,199 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. _imc:
+
+===================================
+IMC (In-Memory Collection Counters)
+===================================
+
+Anju T Sudhakar, 10 May 2019
+
+.. contents::
+    :depth: 3
+
+
+Basic overview
+==============
+
+IMC (In-Memory collection counters) is a hardware monitoring facility that
+collects large numbers of hardware performance events at Nest level (these are
+on-chip but off-core), Core level and Thread level.
+
+The Nest PMU counters are handled by a Nest IMC microcode which runs in the OCC
+(On-Chip Controller) complex. The microcode collects the counter data and moves
+the nest IMC counter data to memory.
+
+The Core and Thread IMC PMU counters are handled in the core. Core level PMU
+counters give us the IMC counters' data per core and thread level PMU counters
+give us the IMC counters' data per CPU thread.
+
+OPAL obtains the IMC PMU and supported events information from the IMC Catalog
+and passes on to the kernel via the device tree. The event's information
+contains:
+
+- Event name
+- Event Offset
+- Event description
+
+and possibly also:
+
+- Event scale
+- Event unit
+
+Some PMUs may have a common scale and unit values for all their supported
+events. For those cases, the scale and unit properties for those events must be
+inherited from the PMU.
+
+The event offset in the memory is where the counter data gets accumulated.
+
+IMC catalog is available at:
+	https://github.com/open-power/ima-catalog
+
+The kernel discovers the IMC counters information in the device tree at the
+`imc-counters` device node which has a compatible field
+`ibm,opal-in-memory-counters`. From the device tree, the kernel parses the PMUs
+and their event's information and register the PMU and its attributes in the
+kernel.
+
+IMC example usage
+=================
+
+.. code-block:: sh
+
+  # perf list
+  [...]
+  nest_mcs01/PM_MCS01_64B_RD_DISP_PORT01/            [Kernel PMU event]
+  nest_mcs01/PM_MCS01_64B_RD_DISP_PORT23/            [Kernel PMU event]
+  [...]
+  core_imc/CPM_0THRD_NON_IDLE_PCYC/                  [Kernel PMU event]
+  core_imc/CPM_1THRD_NON_IDLE_INST/                  [Kernel PMU event]
+  [...]
+  thread_imc/CPM_0THRD_NON_IDLE_PCYC/                [Kernel PMU event]
+  thread_imc/CPM_1THRD_NON_IDLE_INST/                [Kernel PMU event]
+
+To see per chip data for nest_mcs0/PM_MCS_DOWN_128B_DATA_XFER_MC0/:
+
+.. code-block:: sh
+
+  # ./perf stat -e "nest_mcs01/PM_MCS01_64B_WR_DISP_PORT01/" -a --per-socket
+
+To see non-idle instructions for core 0:
+
+.. code-block:: sh
+
+  # ./perf stat -e "core_imc/CPM_NON_IDLE_INST/" -C 0 -I 1000
+
+To see non-idle instructions for a "make":
+
+.. code-block:: sh
+
+  # ./perf stat -e "thread_imc/CPM_NON_IDLE_PCYC/" make
+
+
+IMC Trace-mode
+===============
+
+POWER9 supports two modes for IMC which are the Accumulation mode and Trace
+mode. In Accumulation mode, event counts are accumulated in system Memory.
+Hypervisor then reads the posted counts periodically or when requested. In IMC
+Trace mode, the 64 bit trace SCOM value is initialized with the event
+information. The CPMCxSEL and CPMC_LOAD in the trace SCOM, specifies the event
+to be monitored and the sampling duration. On each overflow in the CPMCxSEL,
+hardware snapshots the program counter along with event counts and writes into
+memory pointed by LDBAR.
+
+LDBAR is a 64 bit special purpose per thread register, it has bits to indicate
+whether hardware is configured for accumulation or trace mode.
+
+LDBAR Register Layout
+---------------------
+
+  +-------+----------------------+
+  | 0     | Enable/Disable       |
+  +-------+----------------------+
+  | 1     | 0: Accumulation Mode |
+  |       +----------------------+
+  |       | 1: Trace Mode        |
+  +-------+----------------------+
+  | 2:3   | Reserved             |
+  +-------+----------------------+
+  | 4-6   | PB scope             |
+  +-------+----------------------+
+  | 7     | Reserved             |
+  +-------+----------------------+
+  | 8:50  | Counter Address      |
+  +-------+----------------------+
+  | 51:63 | Reserved             |
+  +-------+----------------------+
+
+TRACE_IMC_SCOM bit representation
+---------------------------------
+
+  +-------+------------+
+  | 0:1   | SAMPSEL    |
+  +-------+------------+
+  | 2:33  | CPMC_LOAD  |
+  +-------+------------+
+  | 34:40 | CPMC1SEL   |
+  +-------+------------+
+  | 41:47 | CPMC2SEL   |
+  +-------+------------+
+  | 48:50 | BUFFERSIZE |
+  +-------+------------+
+  | 51:63 | RESERVED   |
+  +-------+------------+
+
+CPMC_LOAD contains the sampling duration. SAMPSEL and CPMCxSEL determines the
+event to count. BUFFERSIZE indicates the memory range. On each overflow,
+hardware snapshots the program counter along with event counts and updates the
+memory and reloads the CMPC_LOAD value for the next sampling duration. IMC
+hardware does not support exceptions, so it quietly wraps around if memory
+buffer reaches the end.
+
+*Currently the event monitored for trace-mode is fixed as cycle.*
+
+Trace IMC example usage
+=======================
+
+.. code-block:: sh
+
+  # perf list
+  [....]
+  trace_imc/trace_cycles/                            [Kernel PMU event]
+
+To record an application/process with trace-imc event:
+
+.. code-block:: sh
+
+  # perf record -e trace_imc/trace_cycles/ yes > /dev/null
+  [ perf record: Woken up 1 times to write data ]
+  [ perf record: Captured and wrote 0.012 MB perf.data (21 samples) ]
+
+The `perf.data` generated, can be read using perf report.
+
+Benefits of using IMC trace-mode
+================================
+
+PMI (Performance Monitoring Interrupts) interrupt handling is avoided, since IMC
+trace mode snapshots the program counter and updates to the memory. And this
+also provide a way for the operating system to do instruction sampling in real
+time without PMI processing overhead.
+
+Performance data using `perf top` with and without trace-imc event.
+
+PMI interrupts count when `perf top` command is executed without trace-imc event.
+
+.. code-block:: sh
+
+  # grep PMI /proc/interrupts
+  PMI:          0          0          0          0   Performance monitoring interrupts
+  # ./perf top
+  ...
+  # grep PMI /proc/interrupts
+  PMI:      39735       8710      17338      17801   Performance monitoring interrupts
+  # ./perf top -e trace_imc/trace_cycles/
+  ...
+  # grep PMI /proc/interrupts
+  PMI:      39735       8710      17338      17801   Performance monitoring interrupts
+
+
+That is, the PMI interrupt counts do not increment when using the `trace_imc` event.
diff --git a/Documentation/powerpc/index.rst b/Documentation/powerpc/index.rst
index ba5edb3211c0..0d45f0fc8e57 100644
--- a/Documentation/powerpc/index.rst
+++ b/Documentation/powerpc/index.rst
@@ -18,9 +18,11 @@ powerpc
     elfnote
     firmware-assisted-dump
     hvcs
+    imc
     isa-versions
     kaslr-booke32
     mpc52xx
+    papr_hcalls
     pci_iov_resource_on_powernv
     pmu-ebb
     ptrace
diff --git a/Documentation/powerpc/papr_hcalls.rst b/Documentation/powerpc/papr_hcalls.rst
new file mode 100644
index 000000000000..3493631a60f8
--- /dev/null
+++ b/Documentation/powerpc/papr_hcalls.rst
@@ -0,0 +1,250 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+Hypercall Op-codes (hcalls)
+===========================
+
+Overview
+=========
+
+Virtualization on 64-bit Power Book3S Platforms is based on the PAPR
+specification [1]_ which describes the run-time environment for a guest
+operating system and how it should interact with the hypervisor for
+privileged operations. Currently there are two PAPR compliant hypervisors:
+
+- **IBM PowerVM (PHYP)**: IBM's proprietary hypervisor that supports AIX,
+  IBM-i and  Linux as supported guests (termed as Logical Partitions
+  or LPARS). It supports the full PAPR specification.
+
+- **Qemu/KVM**: Supports PPC64 linux guests running on a PPC64 linux host.
+  Though it only implements a subset of PAPR specification called LoPAPR [2]_.
+
+On PPC64 arch a guest kernel running on top of a PAPR hypervisor is called
+a *pSeries guest*. A pseries guest runs in a supervisor mode (HV=0) and must
+issue hypercalls to the hypervisor whenever it needs to perform an action
+that is hypervisor priviledged [3]_ or for other services managed by the
+hypervisor.
+
+Hence a Hypercall (hcall) is essentially a request by the pseries guest
+asking hypervisor to perform a privileged operation on behalf of the guest. The
+guest issues a with necessary input operands. The hypervisor after performing
+the privilege operation returns a status code and output operands back to the
+guest.
+
+HCALL ABI
+=========
+The ABI specification for a hcall between a pseries guest and PAPR hypervisor
+is covered in section 14.5.3 of ref [2]_. Switch to the  Hypervisor context is
+done via the instruction **HVCS** that expects the Opcode for hcall is set in *r3*
+and any in-arguments for the hcall are provided in registers *r4-r12*. If values
+have to be passed through a memory buffer, the data stored in that buffer should be
+in Big-endian byte order.
+
+Once control is returns back to the guest after hypervisor has serviced the
+'HVCS' instruction the return value of the hcall is available in *r3* and any
+out values are returned in registers *r4-r12*. Again like in case of in-arguments,
+any out values stored in a memory buffer will be in Big-endian byte order.
+
+Powerpc arch code provides convenient wrappers named **plpar_hcall_xxx** defined
+in a arch specific header [4]_ to issue hcalls from the linux kernel
+running as pseries guest.
+
+Register Conventions
+====================
+
+Any hcall should follow same register convention as described in section 2.2.1.1
+of "64-Bit ELF V2 ABI Specification: Power Architecture"[5]_. Table below
+summarizes these conventions:
+
++----------+----------+-------------------------------------------+
+| Register |Volatile  |  Purpose                                  |
+| Range    |(Y/N)     |                                           |
++==========+==========+===========================================+
+|   r0     |    Y     |  Optional-usage                           |
++----------+----------+-------------------------------------------+
+|   r1     |    N     |  Stack Pointer                            |
++----------+----------+-------------------------------------------+
+|   r2     |    N     |  TOC                                      |
++----------+----------+-------------------------------------------+
+|   r3     |    Y     |  hcall opcode/return value                |
++----------+----------+-------------------------------------------+
+|  r4-r10  |    Y     |  in and out values                        |
++----------+----------+-------------------------------------------+
+|   r11    |    Y     |  Optional-usage/Environmental pointer     |
++----------+----------+-------------------------------------------+
+|   r12    |    Y     |  Optional-usage/Function entry address at |
+|          |          |  global entry point                       |
++----------+----------+-------------------------------------------+
+|   r13    |    N     |  Thread-Pointer                           |
++----------+----------+-------------------------------------------+
+|  r14-r31 |    N     |  Local Variables                          |
++----------+----------+-------------------------------------------+
+|    LR    |    Y     |  Link Register                            |
++----------+----------+-------------------------------------------+
+|   CTR    |    Y     |  Loop Counter                             |
++----------+----------+-------------------------------------------+
+|   XER    |    Y     |  Fixed-point exception register.          |
++----------+----------+-------------------------------------------+
+|  CR0-1   |    Y     |  Condition register fields.               |
++----------+----------+-------------------------------------------+
+|  CR2-4   |    N     |  Condition register fields.               |
++----------+----------+-------------------------------------------+
+|  CR5-7   |    Y     |  Condition register fields.               |
++----------+----------+-------------------------------------------+
+|  Others  |    N     |                                           |
++----------+----------+-------------------------------------------+
+
+DRC & DRC Indexes
+=================
+::
+
+     DR1                                  Guest
+     +--+        +------------+         +---------+
+     |  | <----> |            |         |  User   |
+     +--+  DRC1  |            |   DRC   |  Space  |
+                 |    PAPR    |  Index  +---------+
+     DR2         | Hypervisor |         |         |
+     +--+        |            | <-----> |  Kernel |
+     |  | <----> |            |  Hcall  |         |
+     +--+  DRC2  +------------+         +---------+
+
+PAPR hypervisor terms shared hardware resources like PCI devices, NVDIMMs etc
+available for use by LPARs as Dynamic Resource (DR). When a DR is allocated to
+an LPAR, PHYP creates a data-structure called Dynamic Resource Connector (DRC)
+to manage LPAR access. An LPAR refers to a DRC via an opaque 32-bit number
+called DRC-Index. The DRC-index value is provided to the LPAR via device-tree
+where its present as an attribute in the device tree node associated with the
+DR.
+
+HCALL Return-values
+===================
+
+After servicing the hcall, hypervisor sets the return-value in *r3* indicating
+success or failure of the hcall. In case of a failure an error code indicates
+the cause for error. These codes are defined and documented in arch specific
+header [4]_.
+
+In some cases a hcall can potentially take a long time and need to be issued
+multiple times in order to be completely serviced. These hcalls will usually
+accept an opaque value *continue-token* within there argument list and a
+return value of *H_CONTINUE* indicates that hypervisor hasn't still finished
+servicing the hcall yet.
+
+To make such hcalls the guest need to set *continue-token == 0* for the
+initial call and use the hypervisor returned value of *continue-token*
+for each subsequent hcall until hypervisor returns a non *H_CONTINUE*
+return value.
+
+HCALL Op-codes
+==============
+
+Below is a partial list of HCALLs that are supported by PHYP. For the
+corresponding opcode values please look into the arch specific header [4]_:
+
+**H_SCM_READ_METADATA**
+
+| Input: *drcIndex, offset, buffer-address, numBytesToRead*
+| Out: *numBytesRead*
+| Return Value: *H_Success, H_Parameter, H_P2, H_P3, H_Hardware*
+
+Given a DRC Index of an NVDIMM, read N-bytes from the the metadata area
+associated with it, at a specified offset and copy it to provided buffer.
+The metadata area stores configuration information such as label information,
+bad-blocks etc. The metadata area is located out-of-band of NVDIMM storage
+area hence a separate access semantics is provided.
+
+**H_SCM_WRITE_METADATA**
+
+| Input: *drcIndex, offset, data, numBytesToWrite*
+| Out: *None*
+| Return Value: *H_Success, H_Parameter, H_P2, H_P4, H_Hardware*
+
+Given a DRC Index of an NVDIMM, write N-bytes to the metadata area
+associated with it, at the specified offset and from the provided buffer.
+
+**H_SCM_BIND_MEM**
+
+| Input: *drcIndex, startingScmBlockIndex, numScmBlocksToBind,*
+| *targetLogicalMemoryAddress, continue-token*
+| Out: *continue-token, targetLogicalMemoryAddress, numScmBlocksToBound*
+| Return Value: *H_Success, H_Parameter, H_P2, H_P3, H_P4, H_Overlap,*
+| *H_Too_Big, H_P5, H_Busy*
+
+Given a DRC-Index of an NVDIMM, map a continuous SCM blocks range
+*(startingScmBlockIndex, startingScmBlockIndex+numScmBlocksToBind)* to the guest
+at *targetLogicalMemoryAddress* within guest physical address space. In
+case *targetLogicalMemoryAddress == 0xFFFFFFFF_FFFFFFFF* then hypervisor
+assigns a target address to the guest. The HCALL can fail if the Guest has
+an active PTE entry to the SCM block being bound.
+
+**H_SCM_UNBIND_MEM**
+| Input: drcIndex, startingScmLogicalMemoryAddress, numScmBlocksToUnbind
+| Out: numScmBlocksUnbound
+| Return Value: *H_Success, H_Parameter, H_P2, H_P3, H_In_Use, H_Overlap,*
+| *H_Busy, H_LongBusyOrder1mSec, H_LongBusyOrder10mSec*
+
+Given a DRC-Index of an NVDimm, unmap *numScmBlocksToUnbind* SCM blocks starting
+at *startingScmLogicalMemoryAddress* from guest physical address space. The
+HCALL can fail if the Guest has an active PTE entry to the SCM block being
+unbound.
+
+**H_SCM_QUERY_BLOCK_MEM_BINDING**
+
+| Input: *drcIndex, scmBlockIndex*
+| Out: *Guest-Physical-Address*
+| Return Value: *H_Success, H_Parameter, H_P2, H_NotFound*
+
+Given a DRC-Index and an SCM Block index return the guest physical address to
+which the SCM block is mapped to.
+
+**H_SCM_QUERY_LOGICAL_MEM_BINDING**
+
+| Input: *Guest-Physical-Address*
+| Out: *drcIndex, scmBlockIndex*
+| Return Value: *H_Success, H_Parameter, H_P2, H_NotFound*
+
+Given a guest physical address return which DRC Index and SCM block is mapped
+to that address.
+
+**H_SCM_UNBIND_ALL**
+
+| Input: *scmTargetScope, drcIndex*
+| Out: *None*
+| Return Value: *H_Success, H_Parameter, H_P2, H_P3, H_In_Use, H_Busy,*
+| *H_LongBusyOrder1mSec, H_LongBusyOrder10mSec*
+
+Depending on the Target scope unmap all SCM blocks belonging to all NVDIMMs
+or all SCM blocks belonging to a single NVDIMM identified by its drcIndex
+from the LPAR memory.
+
+**H_SCM_HEALTH**
+
+| Input: drcIndex
+| Out: *health-bitmap, health-bit-valid-bitmap*
+| Return Value: *H_Success, H_Parameter, H_Hardware*
+
+Given a DRC Index return the info on predictive failure and overall health of
+the NVDIMM. The asserted bits in the health-bitmap indicate a single predictive
+failure and health-bit-valid-bitmap indicate which bits in health-bitmap are
+valid.
+
+**H_SCM_PERFORMANCE_STATS**
+
+| Input: drcIndex, resultBuffer Addr
+| Out: None
+| Return Value:  *H_Success, H_Parameter, H_Unsupported, H_Hardware, H_Authority, H_Privilege*
+
+Given a DRC Index collect the performance statistics for NVDIMM and copy them
+to the resultBuffer.
+
+References
+==========
+.. [1] "Power Architecture Platform Reference"
+       https://en.wikipedia.org/wiki/Power_Architecture_Platform_Reference
+.. [2] "Linux on Power Architecture Platform Reference"
+       https://members.openpowerfoundation.org/document/dl/469
+.. [3] "Definitions and Notation" Book III-Section 14.5.3
+       https://openpowerfoundation.org/?resource_lib=power-isa-version-3-0
+.. [4] arch/powerpc/include/asm/hvcall.h
+.. [5] "64-Bit ELF V2 ABI Specification: Power Architecture"
+       https://openpowerfoundation.org/?resource_lib=64-bit-elf-v2-abi-specification-power-architecture
diff --git a/Documentation/powerpc/ultravisor.rst b/Documentation/powerpc/ultravisor.rst
index 730854f73830..363736d7fd36 100644
--- a/Documentation/powerpc/ultravisor.rst
+++ b/Documentation/powerpc/ultravisor.rst
@@ -948,6 +948,66 @@ Use cases
     up its internal state for this virtual machine.
 
 
+H_SVM_INIT_ABORT
+----------------
+
+    Abort the process of securing an SVM.
+
+Syntax
+~~~~~~
+
+.. code-block:: c
+
+	uint64_t hypercall(const uint64_t H_SVM_INIT_ABORT)
+
+Return values
+~~~~~~~~~~~~~
+
+    One of the following values:
+
+	* H_PARAMETER 		on successfully cleaning up the state,
+				Hypervisor will return this value to the
+				**guest**, to indicate that the underlying
+				UV_ESM ultracall failed.
+
+	* H_STATE		if called after a VM has gone secure (i.e
+				H_SVM_INIT_DONE hypercall was successful).
+
+	* H_UNSUPPORTED		if called from a wrong context (e.g. from a
+				normal VM).
+
+Description
+~~~~~~~~~~~
+
+    Abort the process of securing a virtual machine. This call must
+    be made after a prior call to ``H_SVM_INIT_START`` hypercall and
+    before a call to ``H_SVM_INIT_DONE``.
+
+    On entry into this hypercall the non-volatile GPRs and FPRs are
+    expected to contain the values they had at the time the VM issued
+    the UV_ESM ultracall. Further ``SRR0`` is expected to contain the
+    address of the instruction after the ``UV_ESM`` ultracall and ``SRR1``
+    the MSR value with which to return to the VM.
+
+    This hypercall will cleanup any partial state that was established for
+    the VM since the prior ``H_SVM_INIT_START`` hypercall, including paging
+    out pages that were paged-into secure memory, and issue the
+    ``UV_SVM_TERMINATE`` ultracall to terminate the VM.
+
+    After the partial state is cleaned up, control returns to the VM
+    (**not Ultravisor**), at the address specified in ``SRR0`` with the
+    MSR values set to the value in ``SRR1``.
+
+Use cases
+~~~~~~~~~
+
+    If after a successful call to ``H_SVM_INIT_START``, the Ultravisor
+    encounters an error while securing a virtual machine, either due
+    to lack of resources or because the VM's security information could
+    not be validated, Ultravisor informs the Hypervisor about it.
+    Hypervisor should use this call to clean up any internal state for
+    this virtual machine and return to the VM.
+
 H_SVM_PAGE_IN
 -------------
 
diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt
index ebb37b34dcfc..3a0c819c3573 100644
--- a/Documentation/virt/kvm/api.txt
+++ b/Documentation/virt/kvm/api.txt
@@ -2196,6 +2196,15 @@ arm64 CCSIDR registers are demultiplexed by CSSELR value:
 arm64 system registers have the following id bit patterns:
   0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
 
+WARNING:
+     Two system register IDs do not follow the specified pattern.  These
+     are KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT, which map to
+     system registers CNTV_CVAL_EL0 and CNTVCT_EL0 respectively.  These
+     two had their values accidentally swapped, which means TIMER_CVAL is
+     derived from the register encoding for CNTVCT_EL0 and TIMER_CNT is
+     derived from the register encoding for CNTV_CVAL_EL0.  As this is
+     API, it must remain this way.
+
 arm64 firmware pseudo-registers have the following bit pattern:
   0x6030 0000 0014 <regno:16>
 
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index 893a8ba0e9fe..95fec5968362 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -149,14 +149,14 @@ CPU page table into a device page table; HMM helps keep both synchronized. A
 device driver that wants to mirror a process address space must start with the
 registration of a mmu_interval_notifier::
 
- mni->ops = &driver_ops;
- int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni,
-			          unsigned long start, unsigned long length,
-			          struct mm_struct *mm);
+ int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub,
+				  struct mm_struct *mm, unsigned long start,
+				  unsigned long length,
+				  const struct mmu_interval_notifier_ops *ops);
 
-During the driver_ops->invalidate() callback the device driver must perform
-the update action to the range (mark range read only, or fully unmap,
-etc.). The device must complete the update before the driver callback returns.
+During the ops->invalidate() callback the device driver must perform the
+update action to the range (mark range read only, or fully unmap, etc.). The
+device must complete the update before the driver callback returns.
 
 When the device driver wants to populate a range of virtual addresses, it can
 use::
@@ -183,7 +183,7 @@ The usage pattern is::
       struct hmm_range range;
       ...
 
-      range.notifier = &mni;
+      range.notifier = &interval_sub;
       range.start = ...;
       range.end = ...;
       range.pfns = ...;
@@ -191,11 +191,11 @@ The usage pattern is::
       range.values = ...;
       range.pfn_shift = ...;
 
-      if (!mmget_not_zero(mni->notifier.mm))
+      if (!mmget_not_zero(interval_sub->notifier.mm))
           return -EFAULT;
 
  again:
-      range.notifier_seq = mmu_interval_read_begin(&mni);
+      range.notifier_seq = mmu_interval_read_begin(&interval_sub);
       down_read(&mm->mmap_sem);
       ret = hmm_range_fault(&range, HMM_RANGE_SNAPSHOT);
       if (ret) {
diff --git a/Documentation/vm/zswap.rst b/Documentation/vm/zswap.rst
index 1444ecd40911..61f6185188cd 100644
--- a/Documentation/vm/zswap.rst
+++ b/Documentation/vm/zswap.rst
@@ -130,6 +130,19 @@ checking for the same-value filled pages during store operation. However, the
 existing pages which are marked as same-value filled pages remain stored
 unchanged in zswap until they are either loaded or invalidated.
 
+To prevent zswap from shrinking pool when zswap is full and there's a high
+pressure on swap (this will result in flipping pages in and out zswap pool
+without any real benefit but with a performance drop for the system), a
+special parameter has been introduced to implement a sort of hysteresis to
+refuse taking pages into zswap pool until it has sufficient space if the limit
+has been hit. To set the threshold at which zswap would start accepting pages
+again after it became full, use the sysfs ``accept_threhsold_percent``
+attribute, e. g.::
+
+	echo 80 > /sys/module/zswap/parameters/accept_threhsold_percent
+
+Setting this parameter to 100 will disable the hysteresis.
+
 A debugfs interface is provided for various statistic about pool size, number
 of pages stored, same-value filled pages and various counters for the reasons
 pages are rejected.
diff --git a/Documentation/x86/intel_mpx.rst b/Documentation/x86/intel_mpx.rst
deleted file mode 100644
index 387a640941a6..000000000000
--- a/Documentation/x86/intel_mpx.rst
+++ /dev/null
@@ -1,252 +0,0 @@
-.. SPDX-License-Identifier: GPL-2.0
-
-===========================================
-Intel(R) Memory Protection Extensions (MPX)
-===========================================
-
-Intel(R) MPX Overview
-=====================
-
-Intel(R) Memory Protection Extensions (Intel(R) MPX) is a new capability
-introduced into Intel Architecture. Intel MPX provides hardware features
-that can be used in conjunction with compiler changes to check memory
-references, for those references whose compile-time normal intentions are
-usurped at runtime due to buffer overflow or underflow.
-
-You can tell if your CPU supports MPX by looking in /proc/cpuinfo::
-
-	cat /proc/cpuinfo  | grep ' mpx '
-
-For more information, please refer to Intel(R) Architecture Instruction
-Set Extensions Programming Reference, Chapter 9: Intel(R) Memory Protection
-Extensions.
-
-Note: As of December 2014, no hardware with MPX is available but it is
-possible to use SDE (Intel(R) Software Development Emulator) instead, which
-can be downloaded from
-http://software.intel.com/en-us/articles/intel-software-development-emulator
-
-
-How to get the advantage of MPX
-===============================
-
-For MPX to work, changes are required in the kernel, binutils and compiler.
-No source changes are required for applications, just a recompile.
-
-There are a lot of moving parts of this to all work right. The following
-is how we expect the compiler, application and kernel to work together.
-
-1) Application developer compiles with -fmpx. The compiler will add the
-   instrumentation as well as some setup code called early after the app
-   starts. New instruction prefixes are noops for old CPUs.
-2) That setup code allocates (virtual) space for the "bounds directory",
-   points the "bndcfgu" register to the directory (must also set the valid
-   bit) and notifies the kernel (via the new prctl(PR_MPX_ENABLE_MANAGEMENT))
-   that the app will be using MPX.  The app must be careful not to access
-   the bounds tables between the time when it populates "bndcfgu" and
-   when it calls the prctl().  This might be hard to guarantee if the app
-   is compiled with MPX.  You can add "__attribute__((bnd_legacy))" to
-   the function to disable MPX instrumentation to help guarantee this.
-   Also be careful not to call out to any other code which might be
-   MPX-instrumented.
-3) The kernel detects that the CPU has MPX, allows the new prctl() to
-   succeed, and notes the location of the bounds directory. Userspace is
-   expected to keep the bounds directory at that location. We note it
-   instead of reading it each time because the 'xsave' operation needed
-   to access the bounds directory register is an expensive operation.
-4) If the application needs to spill bounds out of the 4 registers, it
-   issues a bndstx instruction. Since the bounds directory is empty at
-   this point, a bounds fault (#BR) is raised, the kernel allocates a
-   bounds table (in the user address space) and makes the relevant entry
-   in the bounds directory point to the new table.
-5) If the application violates the bounds specified in the bounds registers,
-   a separate kind of #BR is raised which will deliver a signal with
-   information about the violation in the 'struct siginfo'.
-6) Whenever memory is freed, we know that it can no longer contain valid
-   pointers, and we attempt to free the associated space in the bounds
-   tables. If an entire table becomes unused, we will attempt to free
-   the table and remove the entry in the directory.
-
-To summarize, there are essentially three things interacting here:
-
-GCC with -fmpx:
- * enables annotation of code with MPX instructions and prefixes
- * inserts code early in the application to call in to the "gcc runtime"
-GCC MPX Runtime:
- * Checks for hardware MPX support in cpuid leaf
- * allocates virtual space for the bounds directory (malloc() essentially)
- * points the hardware BNDCFGU register at the directory
- * calls a new prctl(PR_MPX_ENABLE_MANAGEMENT) to notify the kernel to
-   start managing the bounds directories
-Kernel MPX Code:
- * Checks for hardware MPX support in cpuid leaf
- * Handles #BR exceptions and sends SIGSEGV to the app when it violates
-   bounds, like during a buffer overflow.
- * When bounds are spilled in to an unallocated bounds table, the kernel
-   notices in the #BR exception, allocates the virtual space, then
-   updates the bounds directory to point to the new table. It keeps
-   special track of the memory with a VM_MPX flag.
- * Frees unused bounds tables at the time that the memory they described
-   is unmapped.
-
-
-How does MPX kernel code work
-=============================
-
-Handling #BR faults caused by MPX
----------------------------------
-
-When MPX is enabled, there are 2 new situations that can generate
-#BR faults.
-
-  * new bounds tables (BT) need to be allocated to save bounds.
-  * bounds violation caused by MPX instructions.
-
-We hook #BR handler to handle these two new situations.
-
-On-demand kernel allocation of bounds tables
---------------------------------------------
-
-MPX only has 4 hardware registers for storing bounds information. If
-MPX-enabled code needs more than these 4 registers, it needs to spill
-them somewhere. It has two special instructions for this which allow
-the bounds to be moved between the bounds registers and some new "bounds
-tables".
-
-#BR exceptions are a new class of exceptions just for MPX. They are
-similar conceptually to a page fault and will be raised by the MPX
-hardware during both bounds violations or when the tables are not
-present. The kernel handles those #BR exceptions for not-present tables
-by carving the space out of the normal processes address space and then
-pointing the bounds-directory over to it.
-
-The tables need to be accessed and controlled by userspace because
-the instructions for moving bounds in and out of them are extremely
-frequent. They potentially happen every time a register points to
-memory. Any direct kernel involvement (like a syscall) to access the
-tables would obviously destroy performance.
-
-Why not do this in userspace? MPX does not strictly require anything in
-the kernel. It can theoretically be done completely from userspace. Here
-are a few ways this could be done. We don't think any of them are practical
-in the real-world, but here they are.
-
-:Q: Can virtual space simply be reserved for the bounds tables so that we
-    never have to allocate them?
-:A: MPX-enabled application will possibly create a lot of bounds tables in
-    process address space to save bounds information. These tables can take
-    up huge swaths of memory (as much as 80% of the memory on the system)
-    even if we clean them up aggressively. In the worst-case scenario, the
-    tables can be 4x the size of the data structure being tracked. IOW, a
-    1-page structure can require 4 bounds-table pages. An X-GB virtual
-    area needs 4*X GB of virtual space, plus 2GB for the bounds directory.
-    If we were to preallocate them for the 128TB of user virtual address
-    space, we would need to reserve 512TB+2GB, which is larger than the
-    entire virtual address space today. This means they can not be reserved
-    ahead of time. Also, a single process's pre-populated bounds directory
-    consumes 2GB of virtual *AND* physical memory. IOW, it's completely
-    infeasible to prepopulate bounds directories.
-
-:Q: Can we preallocate bounds table space at the same time memory is
-    allocated which might contain pointers that might eventually need
-    bounds tables?
-:A: This would work if we could hook the site of each and every memory
-    allocation syscall. This can be done for small, constrained applications.
-    But, it isn't practical at a larger scale since a given app has no
-    way of controlling how all the parts of the app might allocate memory
-    (think libraries). The kernel is really the only place to intercept
-    these calls.
-
-:Q: Could a bounds fault be handed to userspace and the tables allocated
-    there in a signal handler instead of in the kernel?
-:A: mmap() is not on the list of safe async handler functions and even
-    if mmap() would work it still requires locking or nasty tricks to
-    keep track of the allocation state there.
-
-Having ruled out all of the userspace-only approaches for managing
-bounds tables that we could think of, we create them on demand in
-the kernel.
-
-Decoding MPX instructions
--------------------------
-
-If a #BR is generated due to a bounds violation caused by MPX.
-We need to decode MPX instructions to get violation address and
-set this address into extended struct siginfo.
-
-The _sigfault field of struct siginfo is extended as follow::
-
-  87		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-  88		struct {
-  89			void __user *_addr; /* faulting insn/memory ref. */
-  90 #ifdef __ARCH_SI_TRAPNO
-  91			int _trapno;	/* TRAP # which caused the signal */
-  92 #endif
-  93			short _addr_lsb; /* LSB of the reported address */
-  94			struct {
-  95				void __user *_lower;
-  96				void __user *_upper;
-  97			} _addr_bnd;
-  98		} _sigfault;
-
-The '_addr' field refers to violation address, and new '_addr_and'
-field refers to the upper/lower bounds when a #BR is caused.
-
-Glibc will be also updated to support this new siginfo. So user
-can get violation address and bounds when bounds violations occur.
-
-Cleanup unused bounds tables
-----------------------------
-
-When a BNDSTX instruction attempts to save bounds to a bounds directory
-entry marked as invalid, a #BR is generated. This is an indication that
-no bounds table exists for this entry. In this case the fault handler
-will allocate a new bounds table on demand.
-
-Since the kernel allocated those tables on-demand without userspace
-knowledge, it is also responsible for freeing them when the associated
-mappings go away.
-
-Here, the solution for this issue is to hook do_munmap() to check
-whether one process is MPX enabled. If yes, those bounds tables covered
-in the virtual address region which is being unmapped will be freed also.
-
-Adding new prctl commands
--------------------------
-
-Two new prctl commands are added to enable and disable MPX bounds tables
-management in kernel.
-::
-
-  155	#define PR_MPX_ENABLE_MANAGEMENT	43
-  156	#define PR_MPX_DISABLE_MANAGEMENT	44
-
-Runtime library in userspace is responsible for allocation of bounds
-directory. So kernel have to use XSAVE instruction to get the base
-of bounds directory from BNDCFG register.
-
-But XSAVE is expected to be very expensive. In order to do performance
-optimization, we have to get the base of bounds directory and save it
-into struct mm_struct to be used in future during PR_MPX_ENABLE_MANAGEMENT
-command execution.
-
-
-Special rules
-=============
-
-1) If userspace is requesting help from the kernel to do the management
-of bounds tables, it may not create or modify entries in the bounds directory.
-
-Certainly users can allocate bounds tables and forcibly point the bounds
-directory at them through XSAVE instruction, and then set valid bit
-of bounds entry to have this entry valid.  But, the kernel will decline
-to assist in managing these tables.
-
-2) Userspace may not take multiple bounds directory entries and point
-them at the same bounds table.
-
-This is allowed architecturally.  See more information "Intel(R) Architecture
-Instruction Set Extensions Programming Reference" (9.3.4).
-
-However, if users did this, the kernel might be fooled in to unmapping an
-in-use bounds table since it does not recognize sharing.
diff --git a/MAINTAINERS b/MAINTAINERS
index a704cb9316e2..777f87ac2551 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -317,30 +317,30 @@ ACPI
 M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 M:	Len Brown <lenb@kernel.org>
 L:	linux-acpi@vger.kernel.org
+S:	Supported
 W:	https://01.org/linux-acpi
-Q:	https://patchwork.kernel.org/project/linux-acpi/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
+Q:	https://patchwork.kernel.org/project/linux-acpi/list/
 B:	https://bugzilla.kernel.org
-S:	Supported
+F:	Documentation/ABI/testing/configfs-acpi
+F:	Documentation/ABI/testing/sysfs-bus-acpi
+F:	Documentation/firmware-guide/acpi/
 F:	drivers/acpi/
+F:	drivers/pci/*/*acpi*
+F:	drivers/pci/*acpi*
 F:	drivers/pnp/pnpacpi/
+F:	include/acpi/
 F:	include/linux/acpi.h
 F:	include/linux/fwnode.h
-F:	include/acpi/
-F:	Documentation/firmware-guide/acpi/
-F:	Documentation/ABI/testing/sysfs-bus-acpi
-F:	Documentation/ABI/testing/configfs-acpi
-F:	drivers/pci/*acpi*
-F:	drivers/pci/*/*acpi*
 F:	tools/power/acpi/
 
 ACPI APEI
 M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 M:	Len Brown <lenb@kernel.org>
-L:	linux-acpi@vger.kernel.org
 R:	James Morse <james.morse@arm.com>
 R:	Tony Luck <tony.luck@intel.com>
 R:	Borislav Petkov <bp@alien8.de>
+L:	linux-acpi@vger.kernel.org
 F:	drivers/acpi/apei/
 
 ACPI COMPONENT ARCHITECTURE (ACPICA)
@@ -349,13 +349,13 @@ M:	Erik Kaneda <erik.kaneda@intel.com>
 M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
 L:	linux-acpi@vger.kernel.org
 L:	devel@acpica.org
+S:	Supported
 W:	https://acpica.org/
 W:	https://github.com/acpica/acpica/
-Q:	https://patchwork.kernel.org/project/linux-acpi/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
+Q:	https://patchwork.kernel.org/project/linux-acpi/list/
 B:	https://bugzilla.kernel.org
 B:	https://bugs.acpica.org
-S:	Supported
 F:	drivers/acpi/acpica/
 F:	include/acpi/
 F:	tools/power/acpi/
@@ -363,9 +363,9 @@ F:	tools/power/acpi/
 ACPI FAN DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
+S:	Supported
 W:	https://01.org/linux-acpi
 B:	https://bugzilla.kernel.org
-S:	Supported
 F:	drivers/acpi/fan.c
 
 ACPI FOR ARM64 (ACPI/arm64)
@@ -389,26 +389,26 @@ M:	Len Brown <lenb@kernel.org>
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 R:	Mika Westerberg <mika.westerberg@linux.intel.com>
 L:	linux-acpi@vger.kernel.org
-Q:	https://patchwork.kernel.org/project/linux-acpi/list/
+S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
+Q:	https://patchwork.kernel.org/project/linux-acpi/list/
 B:	https://bugzilla.kernel.org
-S:	Supported
 F:	drivers/acpi/pmic/
 
 ACPI THERMAL DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
+S:	Supported
 W:	https://01.org/linux-acpi
 B:	https://bugzilla.kernel.org
-S:	Supported
 F:	drivers/acpi/*thermal*
 
 ACPI VIDEO DRIVER
 M:	Zhang Rui <rui.zhang@intel.com>
 L:	linux-acpi@vger.kernel.org
+S:	Supported
 W:	https://01.org/linux-acpi
 B:	https://bugzilla.kernel.org
-S:	Supported
 F:	drivers/acpi/acpi_video.c
 
 ACPI WMI DRIVER
@@ -4478,13 +4478,10 @@ F:	drivers/net/wireless/st/cw1200/
 
 CX18 VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
-L:	ivtv-devel@ivtvdriver.org (subscribers-only)
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 W:	https://linuxtv.org
-W:	http://www.ivtvdriver.org/index.php/Cx18
 S:	Maintained
-F:	Documentation/media/v4l-drivers/cx18*
 F:	drivers/media/pci/cx18/
 F:	include/uapi/linux/ivtv*
 
@@ -5025,6 +5022,24 @@ F:	Documentation/driver-api/dma-buf.rst
 K:	dma_(buf|fence|resv)
 T:	git git://anongit.freedesktop.org/drm/drm-misc
 
+DMA-BUF HEAPS FRAMEWORK
+M:	Sumit Semwal <sumit.semwal@linaro.org>
+R:	Andrew F. Davis <afd@ti.com>
+R:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
+R:	Liam Mark <lmark@codeaurora.org>
+R:	Laura Abbott <labbott@redhat.com>
+R:	Brian Starkey <Brian.Starkey@arm.com>
+R:	John Stultz <john.stultz@linaro.org>
+S:	Maintained
+L:	linux-media@vger.kernel.org
+L:	dri-devel@lists.freedesktop.org
+L:	linaro-mm-sig@lists.linaro.org (moderated for non-subscribers)
+F:	include/uapi/linux/dma-heap.h
+F:	include/linux/dma-heap.h
+F:	drivers/dma-buf/dma-heap.c
+F:	drivers/dma-buf/heaps/*
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+
 DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
 M:	Vinod Koul <vkoul@kernel.org>
 L:	dmaengine@vger.kernel.org
@@ -5230,6 +5245,12 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 S:	Maintained
 F:	drivers/gpu/drm/bochs/
 
+DRM DRIVER FOR BOE HIMAX8279D PANELS
+M:	Jerry Han <hanxu5@huaqin.corp-partner.google.com>
+S:	Maintained
+F:	drivers/gpu/drm/panel/panel-boe-himax8279d.c
+F:	Documentation/devicetree/bindings/display/panel/boe,himax8279d.txt
+
 DRM DRIVER FOR FARADAY TVE200 TV ENCODER
 M:	Linus Walleij <linus.walleij@linaro.org>
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -5385,6 +5406,12 @@ S:	Maintained
 F:	drivers/gpu/drm/tiny/st7735r.c
 F:	Documentation/devicetree/bindings/display/sitronix,st7735r.txt
 
+DRM DRIVER FOR SONY ACX424AKP PANELS
+M:	Linus Walleij <linus.walleij@linaro.org>
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+S:	Maintained
+F:	drivers/gpu/drm/panel/panel-sony-acx424akp.c
+
 DRM DRIVER FOR ST-ERICSSON MCDE
 M:	Linus Walleij <linus.walleij@linaro.org>
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -5457,7 +5484,6 @@ F:	include/linux/vga*
 DRM DRIVERS AND MISC GPU PATCHES
 M:	Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
 M:	Maxime Ripard <mripard@kernel.org>
-M:	Sean Paul <sean@poorly.run>
 W:	https://01.org/linuxgraphics/gfx-docs/maintainer-tools/drm-misc.html
 S:	Maintained
 T:	git git://anongit.freedesktop.org/drm/drm-misc
@@ -7352,6 +7378,7 @@ F:	drivers/hwtracing/
 HARDWARE SPINLOCK CORE
 M:	Ohad Ben-Cohen <ohad@wizery.com>
 M:	Bjorn Andersson <bjorn.andersson@linaro.org>
+R:	Baolin Wang <baolin.wang7@gmail.com>
 L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git hwspinlock-next
@@ -7631,9 +7658,8 @@ S:	Orphan
 F:	drivers/net/usb/hso.c
 
 HSR NETWORK PROTOCOL
-M:	Arvid Brodin <arvid.brodin@alten.se>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	net/hsr/
 
 HT16K33 LED CONTROLLER DRIVER
@@ -8171,8 +8197,7 @@ F:	Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt
 F:	drivers/auxdisplay/img-ascii-lcd.c
 
 IMGTEC IR DECODER DRIVER
-M:	James Hogan <jhogan@kernel.org>
-S:	Maintained
+S:	Orphan
 F:	drivers/media/rc/img-ir/
 
 IMON SOUNDGRAPH USB IR RECEIVER
@@ -8883,8 +8908,10 @@ L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
 L:	netdev@vger.kernel.org
 W:	http://www.isdn4linux.de
 S:	Maintained
-F:	drivers/isdn/mISDN
-F:	drivers/isdn/hardware
+F:	drivers/isdn/mISDN/
+F:	drivers/isdn/hardware/
+F:	drivers/isdn/Kconfig
+F:	drivers/isdn/Makefile
 
 ISDN/CMTP OVER BLUETOOTH
 M:	Karsten Keil <isdn@linux-pingi.de>
@@ -8917,10 +8944,9 @@ F:	drivers/media/tuners/it913x*
 
 IVTV VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
-L:	ivtv-devel@ivtvdriver.org (subscribers-only)
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
-W:	http://www.ivtvdriver.org
+W:	https://linuxtv.org
 S:	Maintained
 F:	Documentation/media/v4l-drivers/ivtv*
 F:	drivers/media/pci/ivtv/
@@ -10366,7 +10392,7 @@ L:	linux-media@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
-F:	Documentation/devicetree/bindings/media/renesas,ceu.txt
+F:	Documentation/devicetree/bindings/media/renesas,ceu.yaml
 F:	drivers/media/platform/renesas-ceu.c
 F:	include/media/drv-intf/renesas-ceu.h
 
@@ -10404,7 +10430,7 @@ L:	linux-media@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 S:	Supported
-F:	Documentation/devicetree/bindings/media/renesas,csi2.txt
+F:	Documentation/devicetree/bindings/media/renesas,csi2.yaml
 F:	Documentation/devicetree/bindings/media/renesas,vin.txt
 F:	drivers/media/platform/rcar-vin/
 
@@ -11087,7 +11113,6 @@ F:	drivers/usb/image/microtek.*
 MIPS
 M:	Ralf Baechle <ralf@linux-mips.org>
 M:	Paul Burton <paulburton@kernel.org>
-M:	James Hogan <jhogan@kernel.org>
 L:	linux-mips@vger.kernel.org
 W:	http://www.linux-mips.org/
 T:	git git://git.linux-mips.org/pub/scm/ralf/linux.git
@@ -12696,7 +12721,7 @@ M:	Rob Herring <robh@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/pci/versatile.txt
+F:	Documentation/devicetree/bindings/pci/versatile.yaml
 F:	drivers/pci/controller/pci-versatile.c
 
 PCI DRIVER FOR ARMADA 8K
@@ -12729,7 +12754,7 @@ M:	Will Deacon <will@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	Documentation/devicetree/bindings/pci/host-generic-pci.txt
+F:	Documentation/devicetree/bindings/pci/host-generic-pci.yaml
 F:	drivers/pci/controller/pci-host-common.c
 F:	drivers/pci/controller/pci-host-generic.c
 
@@ -12891,7 +12916,7 @@ F:	arch/x86/kernel/early-quirks.c
 
 PCI NATIVE HOST BRIDGE AND ENDPOINT DRIVERS
 M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
-R:	Andrew Murray <andrew.murray@arm.com>
+R:	Andrew Murray <amurray@thegoodpenguin.co.uk>
 L:	linux-pci@vger.kernel.org
 Q:	http://patchwork.ozlabs.org/project/linux-pci/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/pci.git/
@@ -13312,11 +13337,6 @@ T:	git git://github.com/intel/pm-graph
 S:	Supported
 F:	tools/power/pm-graph
 
-PNP SUPPORT
-M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
-S:	Maintained
-F:	drivers/pnp/
-
 PNI RM3100 IIO DRIVER
 M:	Song Qiang <songqiang1304521@gmail.com>
 L:	linux-iio@vger.kernel.org
@@ -13324,6 +13344,11 @@ S:	Maintained
 F:	drivers/iio/magnetometer/rm3100*
 F:	Documentation/devicetree/bindings/iio/magnetometer/pni,rm3100.txt
 
+PNP SUPPORT
+M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
+S:	Maintained
+F:	drivers/pnp/
+
 POSIX CLOCKS and TIMERS
 M:	Thomas Gleixner <tglx@linutronix.de>
 L:	linux-kernel@vger.kernel.org
@@ -14269,6 +14294,12 @@ F:	drivers/hid/hid-roccat*
 F:	include/linux/hid-roccat*
 F:	Documentation/ABI/*/sysfs-driver-hid-roccat*
 
+ROCKCHIP ISP V1 DRIVER
+M:	Helen Koike <helen.koike@collabora.com>
+L:	linux-media@vger.kernel.org
+S:	Maintained
+F:	drivers/staging/media/rkisp1/
+
 ROCKCHIP RASTER 2D GRAPHIC ACCELERATION UNIT DRIVER
 M:	Jacob Chen <jacob-chen@iotwrt.com>
 M:	Ezequiel Garcia <ezequiel@collabora.com>
@@ -16709,6 +16740,7 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/platform/ti-vpe/
 F:	Documentation/devicetree/bindings/media/ti,vpe.yaml
+	Documentation/devicetree/bindings/media/ti,cal.yaml
 
 TI WILINK WIRELESS DRIVERS
 L:	linux-wireless@vger.kernel.org
@@ -18076,8 +18108,8 @@ F:	Documentation/core-api/workqueue.rst
 X-POWERS AXP288 PMIC DRIVERS
 M:	Hans de Goede <hdegoede@redhat.com>
 S:	Maintained
-N:	axp288
 F:	drivers/acpi/pmic/intel_pmic_xpower.c
+N:	axp288
 
 X-POWERS MULTIFUNCTION PMIC DEVICE DRIVERS
 M:	Chen-Yu Tsai <wens@csie.org>
diff --git a/Makefile b/Makefile
index 6a01b073915e..65a5dc653deb 100644
--- a/Makefile
+++ b/Makefile
@@ -423,7 +423,6 @@ INSTALLKERNEL  := installkernel
 DEPMOD		= /sbin/depmod
 PERL		= perl
 PYTHON		= python
-PYTHON2		= python2
 PYTHON3		= python3
 CHECK		= sparse
 BASH		= bash
@@ -474,7 +473,7 @@ CLANG_FLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
 export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE LEX YACC AWK INSTALLKERNEL
-export PERL PYTHON PYTHON2 PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
+export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
 export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS
@@ -674,7 +673,7 @@ $(KCONFIG_CONFIG):
 #
 # This exploits the 'multi-target pattern rule' trick.
 # The syncconfig should be executed only once to make all the targets.
-%/auto.conf %/auto.conf.cmd %/tristate.conf: $(KCONFIG_CONFIG)
+%/auto.conf %/auto.conf.cmd: $(KCONFIG_CONFIG)
 	$(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
 else # !may-sync-config
 # External modules and some install targets need include/generated/autoconf.h
@@ -1278,24 +1277,13 @@ all: modules
 # using awk while concatenating to the final file.
 
 PHONY += modules
-modules: $(if $(KBUILD_BUILTIN),vmlinux) modules.order modules.builtin
+modules: $(if $(KBUILD_BUILTIN),vmlinux) modules.order
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/modules-check.sh
 
 modules.order: descend
 	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
 
-modbuiltin-dirs := $(addprefix _modbuiltin_, $(build-dirs))
-
-modules.builtin: $(modbuiltin-dirs)
-	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
-
-PHONY += $(modbuiltin-dirs)
-# tristate.conf is not included from this Makefile. Add it as a prerequisite
-# here to make it self-healing in case somebody accidentally removes it.
-$(modbuiltin-dirs): include/config/tristate.conf
-	$(Q)$(MAKE) $(modbuiltin)=$(patsubst _modbuiltin_%,%,$@)
-
 # Target to prepare building external modules
 PHONY += modules_prepare
 modules_prepare: prepare
@@ -1315,7 +1303,7 @@ _modinst_:
 		ln -s $(CURDIR) $(MODLIB)/build ; \
 	fi
 	@sed 's:^:kernel/:' modules.order > $(MODLIB)/modules.order
-	@sed 's:^:kernel/:' modules.builtin > $(MODLIB)/modules.builtin
+	@cp -f modules.builtin $(MODLIB)/
 	@cp -f $(objtree)/modules.builtin.modinfo $(MODLIB)/
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst
 
@@ -1357,7 +1345,7 @@ endif # CONFIG_MODULES
 
 # Directories & files removed with 'make clean'
 CLEAN_DIRS  += include/ksym
-CLEAN_FILES += modules.builtin.modinfo modules.nsdeps
+CLEAN_FILES += modules.builtin modules.builtin.modinfo modules.nsdeps
 
 # Directories & files removed with 'make mrproper'
 MRPROPER_DIRS  += include/config include/generated          \
@@ -1712,7 +1700,7 @@ clean: $(clean-dirs)
 		-o -name '*.lex.c' -o -name '*.tab.[ch]' \
 		-o -name '*.asn1.[ch]' \
 		-o -name '*.symtypes' -o -name 'modules.order' \
-		-o -name modules.builtin -o -name '.tmp_*.o.*' \
+		-o -name '.tmp_*.o.*' \
 		-o -name '*.c.[012]*.*' \
 		-o -name '*.ll' \
 		-o -name '*.gcno' \) -type f -print | xargs rm -f
diff --git a/arch/Kconfig b/arch/Kconfig
index 48b5e103bdb0..98de654b79b3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -393,18 +393,23 @@ config HAVE_ARCH_JUMP_LABEL
 config HAVE_ARCH_JUMP_LABEL_RELATIVE
 	bool
 
-config HAVE_RCU_TABLE_FREE
+config MMU_GATHER_TABLE_FREE
 	bool
 
-config HAVE_RCU_TABLE_NO_INVALIDATE
+config MMU_GATHER_RCU_TABLE_FREE
 	bool
+	select MMU_GATHER_TABLE_FREE
 
-config HAVE_MMU_GATHER_PAGE_SIZE
+config MMU_GATHER_PAGE_SIZE
 	bool
 
-config HAVE_MMU_GATHER_NO_GATHER
+config MMU_GATHER_NO_RANGE
 	bool
 
+config MMU_GATHER_NO_GATHER
+	bool
+	depends on MMU_GATHER_TABLE_FREE
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 
diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c
index 7268222cf4e1..528d2be58182 100644
--- a/arch/alpha/kernel/srm_env.c
+++ b/arch/alpha/kernel/srm_env.c
@@ -119,13 +119,12 @@ static ssize_t srm_env_proc_write(struct file *file, const char __user *buffer,
 	return res;
 }
 
-static const struct file_operations srm_env_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= srm_env_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= srm_env_proc_write,
+static const struct proc_ops srm_env_proc_ops = {
+	.proc_open	= srm_env_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= srm_env_proc_write,
 };
 
 static int __init
@@ -182,7 +181,7 @@ srm_env_init(void)
 	entry = srm_named_entries;
 	while (entry->name && entry->id) {
 		if (!proc_create_data(entry->name, 0644, named_dir,
-			     &srm_env_proc_fops, (void *)entry->id))
+			     &srm_env_proc_ops, (void *)entry->id))
 			goto cleanup;
 		entry++;
 	}
@@ -194,7 +193,7 @@ srm_env_init(void)
 		char name[4];
 		sprintf(name, "%ld", var_num);
 		if (!proc_create_data(name, 0644, numbered_dir,
-			     &srm_env_proc_fops, (void *)var_num))
+			     &srm_env_proc_ops, (void *)var_num))
 			goto cleanup;
 	}
 
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 4d7f2ffa957c..36d42da7466a 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -476,3 +476,4 @@
 544	common	pidfd_open			sys_pidfd_open
 # 545 reserved for clone3
 547	common	openat2				sys_openat2
+548	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 5f448201955b..ff2a393b635c 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -28,6 +28,7 @@ config ARC
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_COPY_THREAD_TLS
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_FUTEX_CMPXCHG if FUTEX
@@ -350,9 +351,8 @@ config NODES_SHIFT
 	  Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory
 	  zones.
 
-if ISA_ARCOMPACT
-
 config ARC_COMPACT_IRQ_LEVELS
+	depends on ISA_ARCOMPACT
 	bool "Setup Timer IRQ as high Priority"
 	# if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy
 	depends on !SMP
@@ -360,14 +360,10 @@ config ARC_COMPACT_IRQ_LEVELS
 config ARC_FPU_SAVE_RESTORE
 	bool "Enable FPU state persistence across context switch"
 	help
-	  Double Precision Floating Point unit had dedicated regs which
-	  need to be saved/restored across context-switch.
-	  Note that ARC FPU is overly simplistic, unlike say x86, which has
-	  hardware pieces to allow software to conditionally save/restore,
-	  based on actual usage of FPU by a task. Thus our implemn does
-	  this for all tasks in system.
-
-endif #ISA_ARCOMPACT
+	  ARCompact FPU has internal registers to assist with Double precision
+	  Floating Point operations. There are control and stauts registers
+	  for floating point exceptions and rounding modes. These are
+	  preserved across task context switch when enabled.
 
 config ARC_CANT_LLSC
 	def_bool n
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index f9a5c9ddcae7..1d109b06e7d8 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -78,6 +78,7 @@
 			interrupt-names = "macirq";
 			phy-mode = "rgmii";
 			snps,pbl = < 32 >;
+			snps,multicast-filter-bins = <256>;
 			clocks = <&apbclk>;
 			clock-names = "stmmaceth";
 			max-speed = <100>;
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 5134f0baf33c..f7e432448e4b 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -39,6 +39,8 @@
 #define ARC_REG_CLUSTER_BCR	0xcf
 #define ARC_REG_AUX_ICCM	0x208	/* ICCM Base Addr (ARCv2) */
 #define ARC_REG_LPB_CTRL	0x488	/* ARCv2 Loop Buffer control */
+#define ARC_REG_FPU_CTRL	0x300
+#define ARC_REG_FPU_STATUS	0x301
 
 /* Common for ARCompact and ARCv2 status register */
 #define ARC_REG_STATUS32	0x0A
diff --git a/arch/arc/include/asm/fpu.h b/arch/arc/include/asm/fpu.h
new file mode 100644
index 000000000000..64347250fdf5
--- /dev/null
+++ b/arch/arc/include/asm/fpu.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 Synopsys, Inc. (www.synopsys.com)
+ *
+ */
+
+#ifndef _ASM_ARC_FPU_H
+#define _ASM_ARC_FPU_H
+
+#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
+
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_ISA_ARCOMPACT
+
+/* These DPFP regs need to be saved/restored across ctx-sw */
+struct arc_fpu {
+	struct {
+		unsigned int l, h;
+	} aux_dpfp[2];
+};
+
+#define fpu_init_task(regs)
+
+#else
+
+/*
+ * ARCv2 FPU Control aux register
+ *   - bits to enable Traps on Exceptions
+ *   - Rounding mode
+ *
+ * ARCv2 FPU Status aux register
+ *   - FPU exceptions flags (Inv, Div-by-Zero, overflow, underflow, inexact)
+ *   - Flag Write Enable to clear flags explicitly (vs. by fpu instructions
+ *     only
+ */
+
+struct arc_fpu {
+	unsigned int ctrl, status;
+};
+
+extern void fpu_init_task(struct pt_regs *regs);
+
+#endif	/* !CONFIG_ISA_ARCOMPACT */
+
+extern void fpu_save_restore(struct task_struct *p, struct task_struct *n);
+
+#else	/* !CONFIG_ARC_FPU_SAVE_RESTORE */
+
+#define fpu_save_restore(p, n)
+#define fpu_init_task(regs)
+
+#endif	/* CONFIG_ARC_FPU_SAVE_RESTORE */
+
+#endif	/* _ASM_ARC_FPU_H */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 9019ed9f9c94..12be7e1b7cc0 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -273,6 +273,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep)
 #define pmd_none(x)			(!pmd_val(x))
 #define	pmd_bad(x)			((pmd_val(x) & ~PAGE_MASK))
 #define pmd_present(x)			(pmd_val(x))
+#define pmd_leaf(x)			(pmd_val(x) & _PAGE_HW_SZ)
 #define pmd_clear(xp)			do { pmd_val(*(xp)) = 0; } while (0)
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 706edeaa5583..ec532d1e0725 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -14,15 +14,7 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/ptrace.h>
-
-#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
-/* These DPFP regs need to be saved/restored across ctx-sw */
-struct arc_fpu {
-	struct {
-		unsigned int l, h;
-	} aux_dpfp[2];
-};
-#endif
+#include <asm/fpu.h>
 
 #ifdef CONFIG_ARC_PLAT_EZNPS
 struct eznps_dp {
diff --git a/arch/arc/include/asm/switch_to.h b/arch/arc/include/asm/switch_to.h
index 77f123385e96..aadf65b2b56c 100644
--- a/arch/arc/include/asm/switch_to.h
+++ b/arch/arc/include/asm/switch_to.h
@@ -9,19 +9,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/sched.h>
-
-#ifdef CONFIG_ARC_FPU_SAVE_RESTORE
-
-extern void fpu_save_restore(struct task_struct *p, struct task_struct *n);
-#define ARC_FPU_PREV(p, n)	fpu_save_restore(p, n)
-#define ARC_FPU_NEXT(t)
-
-#else
-
-#define ARC_FPU_PREV(p, n)
-#define ARC_FPU_NEXT(n)
-
-#endif /* !CONFIG_ARC_FPU_SAVE_RESTORE */
+#include <asm/fpu.h>
 
 #ifdef CONFIG_ARC_PLAT_EZNPS
 extern void dp_save_restore(struct task_struct *p, struct task_struct *n);
@@ -36,9 +24,8 @@ struct task_struct *__switch_to(struct task_struct *p, struct task_struct *n);
 #define switch_to(prev, next, last)	\
 do {					\
 	ARC_EZNPS_DP_PREV(prev, next);	\
-	ARC_FPU_PREV(prev, next);	\
+	fpu_save_restore(prev, next);	\
 	last = __switch_to(prev, next);\
-	ARC_FPU_NEXT(next);		\
 	mb();				\
 } while (0)
 
diff --git a/arch/arc/include/asm/syscalls.h b/arch/arc/include/asm/syscalls.h
index 7ddba13e9b59..c3f4714a4f5c 100644
--- a/arch/arc/include/asm/syscalls.h
+++ b/arch/arc/include/asm/syscalls.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 
 int sys_clone_wrapper(int, int, int, int, int);
+int sys_clone3_wrapper(void *, size_t);
 int sys_cacheflush(uint32_t, uint32_t uint32_t);
 int sys_arc_settls(void *);
 int sys_arc_gettls(void);
diff --git a/arch/arc/include/uapi/asm/unistd.h b/arch/arc/include/uapi/asm/unistd.h
index 5eafa1115162..fa2713ae6bea 100644
--- a/arch/arc/include/uapi/asm/unistd.h
+++ b/arch/arc/include/uapi/asm/unistd.h
@@ -21,6 +21,7 @@
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_SYS_EXECVE
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_TIME32_SYSCALLS
diff --git a/arch/arc/kernel/Makefile b/arch/arc/kernel/Makefile
index e784f5396dda..75539670431a 100644
--- a/arch/arc/kernel/Makefile
+++ b/arch/arc/kernel/Makefile
@@ -23,7 +23,9 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
 obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 
 obj-$(CONFIG_ARC_FPU_SAVE_RESTORE)	+= fpu.o
+ifdef CONFIG_ISA_ARCOMPACT
 CFLAGS_fpu.o   += -mdpfp
+endif
 
 ifdef CONFIG_ARC_DW2_UNWIND
 CFLAGS_ctx_sw.o += -fno-omit-frame-pointer
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 1f6bb184a44d..60406ec62eb8 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -35,6 +35,18 @@ ENTRY(sys_clone_wrapper)
 	b .Lret_from_system_call
 END(sys_clone_wrapper)
 
+ENTRY(sys_clone3_wrapper)
+	SAVE_CALLEE_SAVED_USER
+	bl  @sys_clone3
+	DISCARD_CALLEE_SAVED_USER
+
+	GET_CURR_THR_INFO_FLAGS   r10
+	btst r10, TIF_SYSCALL_TRACE
+	bnz  tracesys_exit
+
+	b .Lret_from_system_call
+END(sys_clone3_wrapper)
+
 ENTRY(ret_from_fork)
 	; when the forked child comes here from the __switch_to function
 	; r0 has the last task pointer.
diff --git a/arch/arc/kernel/fpu.c b/arch/arc/kernel/fpu.c
index 07e22b563fbb..c67c0f0f5f77 100644
--- a/arch/arc/kernel/fpu.c
+++ b/arch/arc/kernel/fpu.c
@@ -6,7 +6,9 @@
  */
 
 #include <linux/sched.h>
-#include <asm/switch_to.h>
+#include <asm/fpu.h>
+
+#ifdef CONFIG_ISA_ARCOMPACT
 
 /*
  * To save/restore FPU regs, simplest scheme would use LR/SR insns.
@@ -50,3 +52,28 @@ void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
 		: "r" (zero), "r" (*(readfrom + 3)), "r" (*(readfrom + 2))
 	);
 }
+
+#else
+
+void fpu_init_task(struct pt_regs *regs)
+{
+	/* default rounding mode */
+	write_aux_reg(ARC_REG_FPU_CTRL, 0x100);
+
+	/* set "Write enable" to allow explicit write to exception flags */
+	write_aux_reg(ARC_REG_FPU_STATUS, 0x80000000);
+}
+
+void fpu_save_restore(struct task_struct *prev, struct task_struct *next)
+{
+	struct arc_fpu *save = &prev->thread.fpu;
+	struct arc_fpu *restore = &next->thread.fpu;
+
+	save->ctrl = read_aux_reg(ARC_REG_FPU_CTRL);
+	save->status = read_aux_reg(ARC_REG_FPU_STATUS);
+
+	write_aux_reg(ARC_REG_FPU_CTRL, restore->ctrl);
+	write_aux_reg(ARC_REG_FPU_STATUS, restore->status);
+}
+
+#endif
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index e1889ce3faf9..315528f04bc1 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -20,6 +20,8 @@
 #include <linux/elf.h>
 #include <linux/tick.h>
 
+#include <asm/fpu.h>
+
 SYSCALL_DEFINE1(arc_settls, void *, user_tls_data_ptr)
 {
 	task_thread_info(current)->thr_ptr = (unsigned int)user_tls_data_ptr;
@@ -171,9 +173,8 @@ asmlinkage void ret_from_fork(void);
  * |    user_r25    |
  * ------------------  <===== END of PAGE
  */
-int copy_thread(unsigned long clone_flags,
-		unsigned long usp, unsigned long kthread_arg,
-		struct task_struct *p)
+int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
+	unsigned long kthread_arg, struct task_struct *p, unsigned long tls)
 {
 	struct pt_regs *c_regs;        /* child's pt_regs */
 	unsigned long *childksp;       /* to unwind out of __switch_to() */
@@ -231,7 +232,7 @@ int copy_thread(unsigned long clone_flags,
 		 * set task's userland tls data ptr from 4th arg
 		 * clone C-lib call is difft from clone sys-call
 		 */
-		task_thread_info(p)->thr_ptr = regs->r3;
+		task_thread_info(p)->thr_ptr = tls;
 	} else {
 		/* Normal fork case: set parent's TLS ptr in child */
 		task_thread_info(p)->thr_ptr =
@@ -264,7 +265,7 @@ int copy_thread(unsigned long clone_flags,
 /*
  * Do necessary setup to start up a new user task
  */
-void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp)
+void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long usp)
 {
 	regs->sp = usp;
 	regs->ret = pc;
@@ -280,6 +281,8 @@ void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp)
 	regs->eflags = 0;
 #endif
 
+	fpu_init_task(regs);
+
 	/* bogus seed values for debugging */
 	regs->lp_start = 0x10;
 	regs->lp_end = 0x80;
diff --git a/arch/arc/kernel/sys.c b/arch/arc/kernel/sys.c
index fddecc76efb7..1069446bdc58 100644
--- a/arch/arc/kernel/sys.c
+++ b/arch/arc/kernel/sys.c
@@ -7,6 +7,7 @@
 #include <asm/syscalls.h>
 
 #define sys_clone	sys_clone_wrapper
+#define sys_clone3	sys_clone3_wrapper
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0b1b1c66bce9..97864aabc2a6 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -74,7 +74,7 @@ config ARM
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
-	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
@@ -102,7 +102,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_RCU_TABLE_FREE if SMP && ARM_LPAE
+	select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
@@ -1905,7 +1905,7 @@ config XIP_DEFLATED_DATA
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
 	depends on (!SMP || PM_SLEEP_SMP)
-	depends on !CPU_V7M
+	depends on MMU
 	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index a1e883c5e5c4..da599c3a1193 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -110,12 +110,12 @@ endif
 
 # -fstack-protector-strong triggers protection checks in this code,
 # but it is being used too early to link to meaningful stack_chk logic.
-nossp_flags := $(call cc-option, -fno-stack-protector)
-CFLAGS_atags_to_fdt.o := $(nossp_flags)
-CFLAGS_fdt.o := $(nossp_flags)
-CFLAGS_fdt_ro.o := $(nossp_flags)
-CFLAGS_fdt_rw.o := $(nossp_flags)
-CFLAGS_fdt_wip.o := $(nossp_flags)
+nossp-flags-$(CONFIG_CC_HAS_STACKPROTECTOR_NONE) := -fno-stack-protector
+CFLAGS_atags_to_fdt.o := $(nossp-flags-y)
+CFLAGS_fdt.o := $(nossp-flags-y)
+CFLAGS_fdt_ro.o := $(nossp-flags-y)
+CFLAGS_fdt_rw.o := $(nossp-flags-y)
+CFLAGS_fdt_wip.o := $(nossp-flags-y)
 
 ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin -I$(obj)
 asflags-y := -DZIMAGE
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index ead21e5f2b80..088b0a060876 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -140,6 +140,17 @@
 #endif
 		.endm
 
+		.macro	enable_cp15_barriers, reg
+		mrc	p15, 0, \reg, c1, c0, 0	@ read SCTLR
+		tst	\reg, #(1 << 5)		@ CP15BEN bit set?
+		bne	.L_\@
+		orr	\reg, \reg, #(1 << 5)	@ CP15 barrier instructions
+		mcr	p15, 0, \reg, c1, c0, 0	@ write SCTLR
+ ARM(		.inst   0xf57ff06f		@ v7+ isb	)
+ THUMB(		isb						)
+.L_\@:
+		.endm
+
 		.section ".start", "ax"
 /*
  * sort out different calling conventions
@@ -820,6 +831,7 @@ __armv4_mmu_cache_on:
 		mov	pc, r12
 
 __armv7_mmu_cache_on:
+		enable_cp15_barriers	r11
 		mov	r12, lr
 #ifdef CONFIG_MMU
 		mrc	p15, 0, r11, c0, c1, 4	@ read ID_MMFR0
@@ -1209,6 +1221,7 @@ __armv6_mmu_cache_flush:
 		mov	pc, lr
 
 __armv7_mmu_cache_flush:
+		enable_cp15_barriers	r10
 		tst	r4, #1
 		bne	iflush
 		mrc	p15, 0, r10, c0, c1, 5	@ read ID_MMFR1
@@ -1447,21 +1460,7 @@ ENTRY(efi_stub_entry)
 
 		@ Preserve return value of efi_entry() in r4
 		mov	r4, r0
-
-		@ our cache maintenance code relies on CP15 barrier instructions
-		@ but since we arrived here with the MMU and caches configured
-		@ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
-		@ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
-		@ the enable path will be executed on v7+ only.
-		mrc	p15, 0, r1, c1, c0, 0	@ read SCTLR
-		tst	r1, #(1 << 5)		@ CP15BEN bit set?
-		bne	0f
-		orr	r1, r1, #(1 << 5)	@ CP15 barrier instructions
-		mcr	p15, 0, r1, c1, c0, 0	@ write SCTLR
- ARM(		.inst	0xf57ff06f		@ v7+ isb	)
- THUMB(		isb						)
-
-0:		bl	cache_clean_flush
+		bl	cache_clean_flush
 		bl	cache_off
 
 		@ Set parameters for booting zImage according to boot protocol
diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi
index 82eeba8faef1..23244b5a9942 100644
--- a/arch/arm/boot/dts/dra7-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra7-evm-common.dtsi
@@ -4,7 +4,7 @@
  */
 
 #include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/clk/ti-dra7-atl.h>
+#include <dt-bindings/clock/ti-dra7-atl.h>
 #include <dt-bindings/input/input.h>
 
 / {
diff --git a/arch/arm/boot/dts/dra72-evm-common.dtsi b/arch/arm/boot/dts/dra72-evm-common.dtsi
index 8641a3d7d8ad..9eabfd1502da 100644
--- a/arch/arm/boot/dts/dra72-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra72-evm-common.dtsi
@@ -6,7 +6,7 @@
 
 #include "dra72x.dtsi"
 #include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/clk/ti-dra7-atl.h>
+#include <dt-bindings/clock/ti-dra7-atl.h>
 
 / {
 	compatible = "ti,dra72-evm", "ti,dra722", "ti,dra72", "ti,dra7";
diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi
index 93e1eb83bed9..ccf0fd477cf9 100644
--- a/arch/arm/boot/dts/dra7xx-clocks.dtsi
+++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi
@@ -1734,6 +1734,20 @@
 		};
 	};
 
+	gpu_cm: gpu-cm@1200 {
+		compatible = "ti,omap4-cm";
+		reg = <0x1200 0x100>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x1200 0x100>;
+
+		gpu_clkctrl: gpu-clkctrl@20 {
+			compatible = "ti,clkctrl";
+			reg = <0x20 0x4>;
+			#clock-cells = <2>;
+		};
+	};
+
 	l3init_cm: l3init-cm@1300 {
 		compatible = "ti,omap4-cm";
 		reg = <0x1300 0x100>;
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 9b118516d2db..3944305e81df 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -9,18 +9,29 @@
 
 #include <linux/kvm_host.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmio.h>
 #include <asm/kvm_arm.h>
 #include <asm/cputype.h>
 
 /* arm64 compatibility macros */
+#define PSR_AA32_MODE_FIQ	FIQ_MODE
+#define PSR_AA32_MODE_SVC	SVC_MODE
 #define PSR_AA32_MODE_ABT	ABT_MODE
 #define PSR_AA32_MODE_UND	UND_MODE
 #define PSR_AA32_T_BIT		PSR_T_BIT
+#define PSR_AA32_F_BIT		PSR_F_BIT
 #define PSR_AA32_I_BIT		PSR_I_BIT
 #define PSR_AA32_A_BIT		PSR_A_BIT
 #define PSR_AA32_E_BIT		PSR_E_BIT
 #define PSR_AA32_IT_MASK	PSR_IT_MASK
+#define PSR_AA32_GE_MASK	0x000f0000
+#define PSR_AA32_DIT_BIT	0x00200000
+#define PSR_AA32_PAN_BIT	0x00400000
+#define PSR_AA32_SSBS_BIT	0x00800000
+#define PSR_AA32_Q_BIT		PSR_Q_BIT
+#define PSR_AA32_V_BIT		PSR_V_BIT
+#define PSR_AA32_C_BIT		PSR_C_BIT
+#define PSR_AA32_Z_BIT		PSR_Z_BIT
+#define PSR_AA32_N_BIT		PSR_N_BIT
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 
@@ -41,6 +52,11 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 	*__vcpu_spsr(vcpu) = v;
 }
 
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	return spsr;
+}
+
 static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
 					 u8 reg_num)
 {
@@ -182,6 +198,11 @@ static inline bool kvm_vcpu_dabt_issext(struct kvm_vcpu *vcpu)
 	return kvm_vcpu_get_hsr(vcpu) & HSR_SSE;
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT;
@@ -198,7 +219,7 @@ static inline bool kvm_vcpu_dabt_is_cm(struct kvm_vcpu *vcpu)
 }
 
 /* Get Access Size from a data abort */
-static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
+static inline unsigned int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
 {
 	switch ((kvm_vcpu_get_hsr(vcpu) >> 22) & 0x3) {
 	case 0:
@@ -209,7 +230,7 @@ static inline int kvm_vcpu_dabt_get_as(struct kvm_vcpu *vcpu)
 		return 4;
 	default:
 		kvm_err("Hardware is weird: SAS 0b11 is reserved\n");
-		return -EFAULT;
+		return 4;
 	}
 }
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 556cd818eccf..c3314b286a61 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -14,7 +14,6 @@
 #include <asm/cputype.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmio.h>
 #include <asm/fpstate.h>
 #include <kvm/arm_arch_timer.h>
 
@@ -202,9 +201,6 @@ struct kvm_vcpu_arch {
 	 /* Don't run the guest (internal implementation need) */
 	bool pause;
 
-	/* IO related fields */
-	struct kvm_decode mmio_decode;
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -284,8 +280,6 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 
-struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
@@ -300,6 +294,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 static inline void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 				     int exception_index) {}
 
+/* MMIO helpers */
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		 phys_addr_t fault_ipa);
+
 static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
@@ -363,9 +365,9 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
 static inline bool kvm_arch_requires_vhe(void) { return false; }
 static inline void kvm_arch_hardware_unsetup(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) {}
 
 static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index 40e9034db601..3c1b55ecc578 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -10,6 +10,7 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/cp15.h>
+#include <asm/kvm_arm.h>
 #include <asm/vfp.h>
 
 #define __hyp_text __section(.hyp.text) notrace
diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h
deleted file mode 100644
index 7c0eddb0adb2..000000000000
--- a/arch/arm/include/asm/kvm_mmio.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Author: Christoffer Dall <c.dall@virtualopensystems.com>
- */
-
-#ifndef __ARM_KVM_MMIO_H__
-#define __ARM_KVM_MMIO_H__
-
-#include <linux/kvm_host.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_arm.h>
-
-struct kvm_decode {
-	unsigned long rt;
-	bool sign_extend;
-};
-
-void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
-unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
-
-int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		 phys_addr_t fault_ipa);
-
-#endif	/* __ARM_KVM_MMIO_H__ */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index 51beec41d48c..0d3ea35c97fe 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -189,6 +189,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 }
 
 #define pmd_large(pmd)		(pmd_val(pmd) & 2)
+#define pmd_leaf(pmd)		(pmd_val(pmd) & 2)
 #define pmd_bad(pmd)		(pmd_val(pmd) & 2)
 #define pmd_present(pmd)	(pmd_val(pmd))
 
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 5b18295021a0..ad55ab068dbf 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -134,6 +134,7 @@
 #define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 						 PMD_TYPE_SECT)
 #define pmd_large(pmd)		pmd_sect(pmd)
+#define pmd_leaf(pmd)		pmd_sect(pmd)
 
 #define pud_clear(pudp)			\
 	do {				\
diff --git a/arch/arm/include/asm/pgtable-nommu.h b/arch/arm/include/asm/pgtable-nommu.h
index 010fa1a35a68..30fb2330f57b 100644
--- a/arch/arm/include/asm/pgtable-nommu.h
+++ b/arch/arm/include/asm/pgtable-nommu.h
@@ -42,12 +42,6 @@
 
 #define swapper_pg_dir ((pgd_t *) 0)
 
-#define __swp_type(x)		(0)
-#define __swp_offset(x)		(0)
-#define __swp_entry(typ,off)	((swp_entry_t) { ((typ) | ((off) << 7)) })
-#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(x)	((pte_t) { (x).val })
-
 
 typedef pte_t *pte_addr_t;
 
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 669474add486..4d4e7b6aabff 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -37,10 +37,6 @@ static inline void __tlb_remove_table(void *_table)
 
 #include <asm-generic/tlb.h>
 
-#ifndef CONFIG_HAVE_RCU_TABLE_FREE
-#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry)
-#endif
-
 static inline void
 __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
 {
diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c
index 312cb89ec364..4247ebf4b893 100644
--- a/arch/arm/kernel/atags_proc.c
+++ b/arch/arm/kernel/atags_proc.c
@@ -17,9 +17,9 @@ static ssize_t atags_read(struct file *file, char __user *buf,
 	return simple_read_from_buffer(buf, count, ppos, b->data, b->size);
 }
 
-static const struct file_operations atags_fops = {
-	.read = atags_read,
-	.llseek = default_llseek,
+static const struct proc_ops atags_proc_ops = {
+	.proc_read	= atags_read,
+	.proc_lseek	= default_llseek,
 };
 
 #define BOOT_PARAMS_SIZE 1536
@@ -61,7 +61,7 @@ static int __init init_atags_procfs(void)
 	b->size = size;
 	memcpy(b->data, atags_copy, size);
 
-	tags_entry = proc_create_data("atags", 0400, NULL, &atags_fops, b);
+	tags_entry = proc_create_data("atags", 0400, NULL, &atags_proc_ops, b);
 	if (!tags_entry)
 		goto nomem;
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 71778bb0475b..cc726afea023 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -92,6 +92,8 @@ static int save_trace(struct stackframe *frame, void *d)
 		return 0;
 
 	regs = (struct pt_regs *)frame->sp;
+	if ((unsigned long)&regs[1] > ALIGN(frame->sp, THREAD_SIZE))
+		return 0;
 
 	trace->entries[trace->nr_entries++] = regs->ARM_pc;
 
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index abb7dd7e656f..1e70e7227f0f 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -64,14 +64,16 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long);
 
 void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
 {
+	unsigned long end = frame + 4 + sizeof(struct pt_regs);
+
 #ifdef CONFIG_KALLSYMS
 	printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
 #else
 	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
 #endif
 
-	if (in_entry_text(from))
-		dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
+	if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE))
+		dump_mem("", "Exception stack", frame + 4, end);
 }
 
 void dump_backtrace_stm(u32 *stack, u32 instruction)
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 0e6f23504c26..9f7ae0d8690f 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -34,11 +34,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 static u64 core_reg_offset_from_id(u64 id)
 {
 	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 788c5cf46de5..84718eddae60 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -162,12 +162,12 @@ static ssize_t alignment_proc_write(struct file *file, const char __user *buffer
 	return count;
 }
 
-static const struct file_operations alignment_proc_fops = {
-	.open		= alignment_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= alignment_proc_write,
+static const struct proc_ops alignment_proc_ops = {
+	.proc_open	= alignment_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= alignment_proc_write,
 };
 #endif /* CONFIG_PROC_FS */
 
@@ -1016,7 +1016,7 @@ static int __init alignment_init(void)
 	struct proc_dir_entry *res;
 
 	res = proc_create("cpu/alignment", S_IWUSR | S_IRUGO, NULL,
-			  &alignment_proc_fops);
+			  &alignment_proc_ops);
 	if (!res)
 		return -ENOMEM;
 #endif
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e822af0d9219..9414d72f664b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -221,7 +221,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static int __dma_supported(struct device *dev, u64 mask, bool warn)
 {
-	unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
+	unsigned long max_dma_pfn = min(max_pfn - 1, arm_dma_pfn_limit);
 
 	/*
 	 * Translate the device's DMA mask to a PFN limit.  This
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 3ef204137e73..054be44d1cdb 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -324,7 +324,7 @@ static inline void poison_init_mem(void *s, size_t count)
 		*p++ = 0xe7fddef0;
 }
 
-static inline void
+static inline void __init
 free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct page *start_pg, *end_pg;
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 4ba54bc7e19a..4d1cf74a2caa 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -450,3 +450,4 @@
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index de238b59d9eb..0b30e884e088 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -104,6 +104,7 @@ config ARM64
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP
+	select GENERIC_PTDUMP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
@@ -164,7 +165,7 @@ config ARM64
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_RCU_TABLE_FREE
+	select MMU_GATHER_RCU_TABLE_FREE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index cf09010d825f..1c906d932d6b 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -1,22 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
-config ARM64_PTDUMP_CORE
-	def_bool n
-
-config ARM64_PTDUMP_DEBUGFS
-	bool "Export kernel pagetable layout to userspace via debugfs"
-	depends on DEBUG_KERNEL
-	select ARM64_PTDUMP_CORE
-	select DEBUG_FS
-        help
-	  Say Y here if you want to show the kernel pagetable layout in a
-	  debugfs file. This information is only useful for kernel developers
-	  who are working in architecture specific areas of the kernel.
-	  It is probably not a good idea to enable this feature in a production
-	  kernel.
-
-	  If in doubt, say N.
-
 config PID_IN_CONTEXTIDR
 	bool "Write the current PID to the CONTEXTIDR register"
 	help
@@ -42,7 +25,7 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
 
 config DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	select ARM64_PTDUMP_CORE
+	select PTDUMP_CORE
 	---help---
 	  Generate a warning if any W+X mappings are found at boot.
 
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index bd23f87d6c55..d3077c991962 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -3,7 +3,6 @@ generic-y += bugs.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
-generic-y += dma-contiguous.h
 generic-y += dma-mapping.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index b0d53a265f1d..935d2aa231bf 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -4,6 +4,9 @@
  */
 #ifndef __ASM_COMPAT_H
 #define __ASM_COMPAT_H
+
+#include <asm-generic/compat.h>
+
 #ifdef CONFIG_COMPAT
 
 /*
@@ -13,8 +16,6 @@
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
 
-#include <asm-generic/compat.h>
-
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
 #define COMPAT_UTS_MACHINE	"armv8b\0\0"
@@ -113,23 +114,6 @@ typedef u32		compat_sigset_word;
 
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
 #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 #define COMPAT_MINSIGSTKSZ	2048
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5efe5ca8fecf..688c63412cc2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -17,7 +17,6 @@
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
-#include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
 #include <asm/virt.h>
@@ -219,6 +218,38 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
 }
 
+/*
+ * The layout of SPSR for an AArch32 state is different when observed from an
+ * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
+ * view given an AArch64 view.
+ *
+ * In ARM DDI 0487E.a see:
+ *
+ * - The AArch64 view (SPSR_EL2) in section C5.2.18, page C5-426
+ * - The AArch32 view (SPSR_abt) in section G8.2.126, page G8-6256
+ * - The AArch32 view (SPSR_und) in section G8.2.132, page G8-6280
+ *
+ * Which show the following differences:
+ *
+ * | Bit | AA64 | AA32 | Notes                       |
+ * +-----+------+------+-----------------------------|
+ * | 24  | DIT  | J    | J is RES0 in ARMv8          |
+ * | 21  | SS   | DIT  | SS doesn't exist in AArch32 |
+ *
+ * ... and all other bits are (currently) common.
+ */
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	const unsigned long overlap = BIT(24) | BIT(21);
+	unsigned long dit = !!(spsr & PSR_AA32_DIT_BIT);
+
+	spsr &= ~overlap;
+
+	spsr |= dit << 21;
+
+	return spsr;
+}
+
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
 	u32 mode;
@@ -283,6 +314,11 @@ static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+}
+
 static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
@@ -304,7 +340,7 @@ static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
 }
 
-static inline int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
+static inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
 	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f5acdde17f3b..d87aa609d2b6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -24,7 +24,6 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmio.h>
 #include <asm/thread_info.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -53,7 +52,7 @@ int kvm_arm_init_sve(void);
 
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
+void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
@@ -325,9 +324,6 @@ struct kvm_vcpu_arch {
 	/* Don't run the guest (internal implementation need) */
 	bool pause;
 
-	/* IO related fields */
-	struct kvm_decode mmio_decode;
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -446,8 +442,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 
-struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
@@ -491,6 +485,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index);
 
+/* MMIO helpers */
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		 phys_addr_t fault_ipa);
+
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
deleted file mode 100644
index 02b5c48fd467..000000000000
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Author: Christoffer Dall <c.dall@virtualopensystems.com>
- */
-
-#ifndef __ARM64_KVM_MMIO_H__
-#define __ARM64_KVM_MMIO_H__
-
-#include <linux/kvm_host.h>
-#include <asm/kvm_arm.h>
-
-/*
- * This is annoying. The mmio code requires this, even if we don't
- * need any decoding. To be fixed.
- */
-struct kvm_decode {
-	unsigned long rt;
-	bool sign_extend;
-};
-
-void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
-unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
-
-int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		 phys_addr_t fault_ipa);
-
-#endif	/* __ARM64_KVM_MMIO_H__ */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index cd5de0e40bfa..538c85e62f86 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -441,6 +441,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				 PMD_TYPE_TABLE)
 #define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_SECT)
+#define pmd_leaf(pmd)		pmd_sect(pmd)
 
 #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
 static inline bool pud_sect(pud_t pud) { return false; }
@@ -525,6 +526,7 @@ static inline void pte_unmap(pte_t *pte) { }
 #define pud_none(pud)		(!pud_val(pud))
 #define pud_bad(pud)		(!(pud_val(pud) & PUD_TABLE_BIT))
 #define pud_present(pud)	pte_present(pud_pte(pud))
+#define pud_leaf(pud)		pud_sect(pud)
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h
index 0b8e7269ec82..38187f74e089 100644
--- a/arch/arm64/include/asm/ptdump.h
+++ b/arch/arm64/include/asm/ptdump.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_PTDUMP_H
 #define __ASM_PTDUMP_H
 
-#ifdef CONFIG_ARM64_PTDUMP_CORE
+#ifdef CONFIG_PTDUMP_CORE
 
 #include <linux/mm_types.h>
 #include <linux/seq_file.h>
@@ -21,15 +21,15 @@ struct ptdump_info {
 	unsigned long			base_addr;
 };
 
-void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
-#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS
+void ptdump_walk(struct seq_file *s, struct ptdump_info *info);
+#ifdef CONFIG_PTDUMP_DEBUGFS
 void ptdump_debugfs_register(struct ptdump_info *info, const char *name);
 #else
 static inline void ptdump_debugfs_register(struct ptdump_info *info,
 					   const char *name) { }
 #endif
 void ptdump_check_wx(void);
-#endif /* CONFIG_ARM64_PTDUMP_CORE */
+#endif /* CONFIG_PTDUMP_CORE */
 
 #ifdef CONFIG_DEBUG_WX
 #define debug_checkwx()	ptdump_check_wx()
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index fbebb411ae20..bf57308fcd63 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -62,6 +62,7 @@
 #define PSR_AA32_I_BIT		0x00000080
 #define PSR_AA32_A_BIT		0x00000100
 #define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_PAN_BIT	0x00400000
 #define PSR_AA32_SSBS_BIT	0x00800000
 #define PSR_AA32_DIT_BIT	0x01000000
 #define PSR_AA32_Q_BIT		0x08000000
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 0f255a23733d..1dd22da1c3a9 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		438
+#define __NR_compat_syscalls		439
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 57f6f592d460..c1c61635f89c 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -881,6 +881,8 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)
 __SYSCALL(__NR_clone3, sys_clone3)
 #define __NR_openat2 437
 __SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 820e5751ada7..ba85bb23f060 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -220,10 +220,18 @@ struct kvm_vcpu_events {
 #define KVM_REG_ARM_PTIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 2, 2)
 #define KVM_REG_ARM_PTIMER_CNT		ARM64_SYS_REG(3, 3, 14, 0, 1)
 
-/* EL0 Virtual Timer Registers */
+/*
+ * EL0 Virtual Timer Registers
+ *
+ * WARNING:
+ *      KVM_REG_ARM_TIMER_CVAL and KVM_REG_ARM_TIMER_CNT are not defined
+ *      with the appropriate register encodings.  Their values have been
+ *      accidentally swapped.  As this is set API, the definitions here
+ *      must be used, rather than ones derived from the encodings.
+ */
 #define KVM_REG_ARM_TIMER_CTL		ARM64_SYS_REG(3, 3, 14, 3, 1)
-#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 #define KVM_REG_ARM_TIMER_CVAL		ARM64_SYS_REG(3, 3, 14, 0, 2)
+#define KVM_REG_ARM_TIMER_CNT		ARM64_SYS_REG(3, 3, 14, 3, 2)
 
 /* KVM-as-firmware specific pseudo-registers */
 #define KVM_REG_ARM_FW			(0x0014 << KVM_REG_ARM_COPROC_SHIFT)
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 7ed9294e2004..d1bb5b69f1ce 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -49,6 +49,7 @@
 #define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
+#define PSR_DIT_BIT	0x01000000
 #define PSR_V_BIT	0x10000000
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 43487f035385..7a7e425616b5 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -101,7 +101,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu)
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 {
 	bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY);
-	unsigned long mdscr;
+	unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2;
 
 	trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug);
 
@@ -197,6 +197,10 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu)
 	if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE))
 		vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY;
 
+	/* Write mdcr_el2 changes since vcpu_load on VHE systems */
+	if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2)
+		write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+
 	trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2);
 	trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1));
 }
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 2fff06114a8f..2bd92301d32f 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -47,11 +47,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 static bool core_reg_offset_is_vreg(u64 off)
 {
 	return off >= KVM_REG_ARM_CORE_REG(fp_regs.vregs) &&
diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
index 0c6832ec52b1..d22d0534dd60 100644
--- a/arch/arm64/kvm/hyp/entry.S
+++ b/arch/arm64/kvm/hyp/entry.S
@@ -51,7 +51,7 @@
  * u64 __guest_enter(struct kvm_vcpu *vcpu,
  *		     struct kvm_cpu_context *host_ctxt);
  */
-ENTRY(__guest_enter)
+SYM_FUNC_START(__guest_enter)
 	// x0: vcpu
 	// x1: host context
 	// x2-x17: clobbered by macros
@@ -100,9 +100,8 @@ alternative_else_nop_endif
 	// Do not touch any register after this!
 	eret
 	sb
-ENDPROC(__guest_enter)
 
-ENTRY(__guest_exit)
+SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
 	// x0: return code
 	// x1: vcpu
 	// x2-x29,lr: vcpu regs
@@ -195,4 +194,4 @@ abort_guest_exit_end:
 	msr	spsr_el2, x4
 	orr	x0, x0, x5
 1:	ret
-ENDPROC(__guest_exit)
+SYM_FUNC_END(__guest_enter)
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index ccdb6a051ab2..6aafc2825c1c 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -14,9 +14,6 @@
 #include <asm/kvm_emulate.h>
 #include <asm/esr.h>
 
-#define PSTATE_FAULT_BITS_64 	(PSR_MODE_EL1h | PSR_A_BIT | PSR_F_BIT | \
-				 PSR_I_BIT | PSR_D_BIT)
-
 #define CURRENT_EL_SP_EL0_VECTOR	0x0
 #define CURRENT_EL_SP_ELx_VECTOR	0x200
 #define LOWER_EL_AArch64_VECTOR		0x400
@@ -50,6 +47,69 @@ static u64 get_except_vector(struct kvm_vcpu *vcpu, enum exception_type type)
 	return vcpu_read_sys_reg(vcpu, VBAR_EL1) + exc_offset + type;
 }
 
+/*
+ * When an exception is taken, most PSTATE fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all
+ * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx
+ * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0.
+ *
+ * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429.
+ * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426.
+ *
+ * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except64_pstate(struct kvm_vcpu *vcpu)
+{
+	unsigned long sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_N_BIT);
+	new |= (old & PSR_Z_BIT);
+	new |= (old & PSR_C_BIT);
+	new |= (old & PSR_V_BIT);
+
+	// TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
+
+	new |= (old & PSR_DIT_BIT);
+
+	// PSTATE.UAO is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D5-2579.
+
+	// PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0
+	// SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page D5-2578.
+	new |= (old & PSR_PAN_BIT);
+	if (!(sctlr & SCTLR_EL1_SPAN))
+		new |= PSR_PAN_BIT;
+
+	// PSTATE.SS is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D2-2452.
+
+	// PSTATE.IL is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D1-2306.
+
+	// PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64
+	// See ARM DDI 0487E.a, page D13-3258
+	if (sctlr & SCTLR_ELx_DSSBS)
+		new |= PSR_SSBS_BIT;
+
+	// PSTATE.BTYPE is set to zero upon any exception to AArch64
+	// See ARM DDI 0487E.a, pages D1-2293 to D1-2294.
+
+	new |= PSR_D_BIT;
+	new |= PSR_A_BIT;
+	new |= PSR_I_BIT;
+	new |= PSR_F_BIT;
+
+	new |= PSR_MODE_EL1h;
+
+	return new;
+}
+
 static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr)
 {
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
@@ -59,7 +119,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr
 	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
-	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
 	vcpu_write_spsr(vcpu, cpsr);
 
 	vcpu_write_sys_reg(vcpu, addr, FAR_EL1);
@@ -94,7 +154,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu)
 	vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu));
 	*vcpu_pc(vcpu) = get_except_vector(vcpu, except_type_sync);
 
-	*vcpu_cpsr(vcpu) = PSTATE_FAULT_BITS_64;
+	*vcpu_cpsr(vcpu) = get_except64_pstate(vcpu);
 	vcpu_write_spsr(vcpu, cpsr);
 
 	/*
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f4a8ae918827..30b7ea680f66 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -204,7 +204,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	kfree(vcpu->arch.sve_state);
 }
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index dab1fea4752a..a4f48c1ac28c 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -13,52 +13,46 @@
 #include <asm/kvm_mmu.h>
 
 /*
- * The LSB of the random hyp VA tag or 0 if no randomization is used.
+ * The LSB of the HYP VA tag
  */
 static u8 tag_lsb;
 /*
- * The random hyp VA tag value with the region bit if hyp randomization is used
+ * The HYP VA tag value with the region bit
  */
 static u64 tag_val;
 static u64 va_mask;
 
+/*
+ * We want to generate a hyp VA with the following format (with V ==
+ * vabits_actual):
+ *
+ *  63 ... V |     V-1    | V-2 .. tag_lsb | tag_lsb - 1 .. 0
+ *  ---------------------------------------------------------
+ * | 0000000 | hyp_va_msb |   random tag   |  kern linear VA |
+ *           |--------- tag_val -----------|----- va_mask ---|
+ *
+ * which does not conflict with the idmap regions.
+ */
 __init void kvm_compute_layout(void)
 {
 	phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
 	u64 hyp_va_msb;
-	int kva_msb;
 
 	/* Where is my RAM region? */
 	hyp_va_msb  = idmap_addr & BIT(vabits_actual - 1);
 	hyp_va_msb ^= BIT(vabits_actual - 1);
 
-	kva_msb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^
+	tag_lsb = fls64((u64)phys_to_virt(memblock_start_of_DRAM()) ^
 			(u64)(high_memory - 1));
 
-	if (kva_msb == (vabits_actual - 1)) {
-		/*
-		 * No space in the address, let's compute the mask so
-		 * that it covers (vabits_actual - 1) bits, and the region
-		 * bit. The tag stays set to zero.
-		 */
-		va_mask  = BIT(vabits_actual - 1) - 1;
-		va_mask |= hyp_va_msb;
-	} else {
-		/*
-		 * We do have some free bits to insert a random tag.
-		 * Hyp VAs are now created from kernel linear map VAs
-		 * using the following formula (with V == vabits_actual):
-		 *
-		 *  63 ... V |     V-1    | V-2 .. tag_lsb | tag_lsb - 1 .. 0
-		 *  ---------------------------------------------------------
-		 * | 0000000 | hyp_va_msb |    random tag  |  kern linear VA |
-		 */
-		tag_lsb = kva_msb;
-		va_mask = GENMASK_ULL(tag_lsb - 1, 0);
-		tag_val = get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
-		tag_val |= hyp_va_msb;
-		tag_val >>= tag_lsb;
+	va_mask = GENMASK_ULL(tag_lsb - 1, 0);
+	tag_val = hyp_va_msb;
+
+	if (tag_lsb != (vabits_actual - 1)) {
+		/* We have some free bits to insert a random tag. */
+		tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb);
 	}
+	tag_val >>= tag_lsb;
 }
 
 static u32 compute_instruction(int n, u32 rd, u32 rn)
@@ -117,11 +111,11 @@ void __init kvm_update_va_mask(struct alt_instr *alt,
 		 * VHE doesn't need any address translation, let's NOP
 		 * everything.
 		 *
-		 * Alternatively, if we don't have any spare bits in
-		 * the address, NOP everything after masking that
-		 * kernel VA.
+		 * Alternatively, if the tag is zero (because the layout
+		 * dictates it and we don't have any spare bits in the
+		 * address), NOP everything after masking the kernel VA.
 		 */
-		if (has_vhe() || (!tag_lsb && i > 0)) {
+		if (has_vhe() || (!tag_val && i > 0)) {
 			updptr[i] = cpu_to_le32(aarch64_insn_gen_nop());
 			continue;
 		}
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 849c1df3d214..d91030f0ffee 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,8 +4,8 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_ARM64_PTDUMP_CORE)	+= dump.o
-obj-$(CONFIG_ARM64_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
+obj-$(CONFIG_PTDUMP_CORE)	+= dump.o
+obj-$(CONFIG_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
 obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 KASAN_SANITIZE_physaddr.o	+= n
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 0a920b538a89..860c00ec8bd3 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -15,6 +15,7 @@
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/ptdump.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 
@@ -75,10 +76,11 @@ static struct addr_marker address_markers[] = {
  * dumps out a description of the range.
  */
 struct pg_state {
+	struct ptdump_state ptdump;
 	struct seq_file *seq;
 	const struct addr_marker *marker;
 	unsigned long start_address;
-	unsigned level;
+	int level;
 	u64 current_prot;
 	bool check_wx;
 	unsigned long wx_pages;
@@ -174,11 +176,14 @@ struct pg_level {
 };
 
 static struct pg_level pg_level[] = {
-	{
-	}, { /* pgd */
+	{ /* pgd */
 		.name	= "PGD",
 		.bits	= pte_bits,
 		.num	= ARRAY_SIZE(pte_bits),
+	}, { /* p4d */
+		.name	= "P4D",
+		.bits	= pte_bits,
+		.num	= ARRAY_SIZE(pte_bits),
 	}, { /* pud */
 		.name	= (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
 		.bits	= pte_bits,
@@ -241,13 +246,17 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
 	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
 }
 
-static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
-				u64 val)
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
+		      unsigned long val)
 {
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
 	static const char units[] = "KMGTPE";
-	u64 prot = val & pg_level[level].mask;
+	u64 prot = 0;
+
+	if (level >= 0)
+		prot = val & pg_level[level].mask;
 
-	if (!st->level) {
+	if (st->level == -1) {
 		st->level = level;
 		st->current_prot = prot;
 		st->start_address = addr;
@@ -260,21 +269,22 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 		if (st->current_prot) {
 			note_prot_uxn(st, addr);
 			note_prot_wx(st, addr);
-			pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx   ",
+		}
+
+		pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx   ",
 				   st->start_address, addr);
 
-			delta = (addr - st->start_address) >> 10;
-			while (!(delta & 1023) && unit[1]) {
-				delta >>= 10;
-				unit++;
-			}
-			pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
-				   pg_level[st->level].name);
-			if (pg_level[st->level].bits)
-				dump_prot(st, pg_level[st->level].bits,
-					  pg_level[st->level].num);
-			pt_dump_seq_puts(st->seq, "\n");
+		delta = (addr - st->start_address) >> 10;
+		while (!(delta & 1023) && unit[1]) {
+			delta >>= 10;
+			unit++;
 		}
+		pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+				   pg_level[st->level].name);
+		if (st->current_prot && pg_level[st->level].bits)
+			dump_prot(st, pg_level[st->level].bits,
+				  pg_level[st->level].num);
+		pt_dump_seq_puts(st->seq, "\n");
 
 		if (addr >= st->marker[1].start_address) {
 			st->marker++;
@@ -293,85 +303,27 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 
 }
 
-static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start,
-		     unsigned long end)
-{
-	unsigned long addr = start;
-	pte_t *ptep = pte_offset_kernel(pmdp, start);
-
-	do {
-		note_page(st, addr, 4, READ_ONCE(pte_val(*ptep)));
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-}
-
-static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start,
-		     unsigned long end)
-{
-	unsigned long next, addr = start;
-	pmd_t *pmdp = pmd_offset(pudp, start);
-
-	do {
-		pmd_t pmd = READ_ONCE(*pmdp);
-		next = pmd_addr_end(addr, end);
-
-		if (pmd_none(pmd) || pmd_sect(pmd)) {
-			note_page(st, addr, 3, pmd_val(pmd));
-		} else {
-			BUG_ON(pmd_bad(pmd));
-			walk_pte(st, pmdp, addr, next);
-		}
-	} while (pmdp++, addr = next, addr != end);
-}
-
-static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start,
-		     unsigned long end)
+void ptdump_walk(struct seq_file *s, struct ptdump_info *info)
 {
-	unsigned long next, addr = start;
-	pud_t *pudp = pud_offset(pgdp, start);
-
-	do {
-		pud_t pud = READ_ONCE(*pudp);
-		next = pud_addr_end(addr, end);
-
-		if (pud_none(pud) || pud_sect(pud)) {
-			note_page(st, addr, 2, pud_val(pud));
-		} else {
-			BUG_ON(pud_bad(pud));
-			walk_pmd(st, pudp, addr, next);
-		}
-	} while (pudp++, addr = next, addr != end);
-}
+	unsigned long end = ~0UL;
+	struct pg_state st;
 
-static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
-		     unsigned long start)
-{
-	unsigned long end = (start < TASK_SIZE_64) ? TASK_SIZE_64 : 0;
-	unsigned long next, addr = start;
-	pgd_t *pgdp = pgd_offset(mm, start);
-
-	do {
-		pgd_t pgd = READ_ONCE(*pgdp);
-		next = pgd_addr_end(addr, end);
-
-		if (pgd_none(pgd)) {
-			note_page(st, addr, 1, pgd_val(pgd));
-		} else {
-			BUG_ON(pgd_bad(pgd));
-			walk_pud(st, pgdp, addr, next);
-		}
-	} while (pgdp++, addr = next, addr != end);
-}
+	if (info->base_addr < TASK_SIZE_64)
+		end = TASK_SIZE_64;
 
-void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info)
-{
-	struct pg_state st = {
-		.seq = m,
+	st = (struct pg_state){
+		.seq = s,
 		.marker = info->markers,
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]){
+				{info->base_addr, end},
+				{0, 0}
+			}
+		}
 	};
 
-	walk_pgd(&st, info->mm, info->base_addr);
-
-	note_page(&st, 0, 0, 0);
+	ptdump_walk_pgd(&st.ptdump, info->mm, NULL);
 }
 
 static void ptdump_initialize(void)
@@ -398,11 +350,19 @@ void ptdump_check_wx(void)
 			{ 0, NULL},
 			{ -1, NULL},
 		},
+		.level = -1,
 		.check_wx = true,
+		.ptdump = {
+			.note_page = note_page,
+			.range = (struct ptdump_range[]) {
+				{PAGE_OFFSET, ~0UL},
+				{0, 0}
+			}
+		}
 	};
 
-	walk_pgd(&st, &init_mm, PAGE_OFFSET);
-	note_page(&st, 0, 0, 0);
+	ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
+
 	if (st.wx_pages || st.uxn_pages)
 		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
 			st.wx_pages, st.uxn_pages);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 40797cbfba2d..128f70852bf3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -943,13 +943,13 @@ int __init arch_ioremap_pud_supported(void)
 	 * SW table walks can't handle removal of intermediate entries.
 	 */
 	return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
-	       !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS);
+	       !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
 }
 
 int __init arch_ioremap_pmd_supported(void)
 {
 	/* See arch_ioremap_pud_supported() */
-	return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS);
+	return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
 }
 
 int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
index 064163f25592..1f2eae3e988b 100644
--- a/arch/arm64/mm/ptdump_debugfs.c
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -7,7 +7,7 @@
 static int ptdump_show(struct seq_file *m, void *v)
 {
 	struct ptdump_info *info = m->private;
-	ptdump_walk_pgd(m, info);
+	ptdump_walk(m, info);
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(ptdump);
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index 4d4754e6bf89..bc15a26c782f 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -7,7 +7,6 @@ generic-y += delay.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
-generic-y += dma-contiguous.h
 generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index b392c0a50346..a25ab9b37953 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -331,10 +331,10 @@ retry:
 	return size;
 }
 
-static const struct file_operations salinfo_event_fops = {
-	.open  = salinfo_event_open,
-	.read  = salinfo_event_read,
-	.llseek = noop_llseek,
+static const struct proc_ops salinfo_event_proc_ops = {
+	.proc_open	= salinfo_event_open,
+	.proc_read	= salinfo_event_read,
+	.proc_lseek	= noop_llseek,
 };
 
 static int
@@ -534,12 +534,12 @@ salinfo_log_write(struct file *file, const char __user *buffer, size_t count, lo
 	return count;
 }
 
-static const struct file_operations salinfo_data_fops = {
-	.open    = salinfo_log_open,
-	.release = salinfo_log_release,
-	.read    = salinfo_log_read,
-	.write   = salinfo_log_write,
-	.llseek  = default_llseek,
+static const struct proc_ops salinfo_data_proc_ops = {
+	.proc_open	= salinfo_log_open,
+	.proc_release	= salinfo_log_release,
+	.proc_read	= salinfo_log_read,
+	.proc_write	= salinfo_log_write,
+	.proc_lseek	= default_llseek,
 };
 
 static int salinfo_cpu_online(unsigned int cpu)
@@ -617,13 +617,13 @@ salinfo_init(void)
 			continue;
 
 		entry = proc_create_data("event", S_IRUSR, dir,
-					 &salinfo_event_fops, data);
+					 &salinfo_event_proc_ops, data);
 		if (!entry)
 			continue;
 		*sdir++ = entry;
 
 		entry = proc_create_data("data", S_IRUSR | S_IWUSR, dir,
-					 &salinfo_data_fops, data);
+					 &salinfo_data_proc_ops, data);
 		if (!entry)
 			continue;
 		*sdir++ = entry;
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 8d36f2e2dc89..042911e670b8 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -357,3 +357,4 @@
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/m68k/kernel/bootinfo_proc.c b/arch/m68k/kernel/bootinfo_proc.c
index 3b9cab84917d..857fa2aaa748 100644
--- a/arch/m68k/kernel/bootinfo_proc.c
+++ b/arch/m68k/kernel/bootinfo_proc.c
@@ -26,9 +26,9 @@ static ssize_t bootinfo_read(struct file *file, char __user *buf,
 				       bootinfo_size);
 }
 
-static const struct file_operations bootinfo_fops = {
-	.read = bootinfo_read,
-	.llseek = default_llseek,
+static const struct proc_ops bootinfo_proc_ops = {
+	.proc_read	= bootinfo_read,
+	.proc_lseek	= default_llseek,
 };
 
 void __init save_bootinfo(const struct bi_record *bi)
@@ -67,7 +67,7 @@ static int __init init_bootinfo_procfs(void)
 	if (!bootinfo_copy)
 		return -ENOMEM;
 
-	pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_fops, NULL);
+	pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_proc_ops, NULL);
 	if (!pde) {
 		kfree(bootinfo_copy);
 		return -ENOMEM;
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index b911e0f50a71..f4f49fcb76d0 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -436,3 +436,4 @@
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				__sys_clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index a105f113fd67..6a331bd57ea8 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -27,6 +27,7 @@ config MICROBLAZE
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_KGDB
 	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/microblaze/configs/mmu_defconfig b/arch/microblaze/configs/mmu_defconfig
index b3b433db89d8..9b8a50f30662 100644
--- a/arch/microblaze/configs/mmu_defconfig
+++ b/arch/microblaze/configs/mmu_defconfig
@@ -26,6 +26,7 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_EFI_PARTITION is not set
+CONFIG_CMA=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -73,7 +74,7 @@ CONFIG_FB_XILINX=y
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=y
 CONFIG_UIO_DMEM_GENIRQ=y
-CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
@@ -82,10 +83,11 @@ CONFIG_NFS_FS=y
 CONFIG_CIFS=y
 CONFIG_CIFS_STATS2=y
 CONFIG_ENCRYPTED_KEYS=y
+CONFIG_DMA_CMA=y
 CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_SLAB=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_SPINLOCK=y
 CONFIG_KGDB=y
 CONFIG_KGDB_TESTS=y
 CONFIG_KGDB_KDB=y
+CONFIG_DEBUG_SLAB=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_SPINLOCK=y
diff --git a/arch/microblaze/configs/nommu_defconfig b/arch/microblaze/configs/nommu_defconfig
index 377de39ccb8c..8c420782d6e4 100644
--- a/arch/microblaze/configs/nommu_defconfig
+++ b/arch/microblaze/configs/nommu_defconfig
@@ -70,7 +70,7 @@ CONFIG_XILINX_WATCHDOG=y
 CONFIG_FB=y
 CONFIG_FB_XILINX=y
 # CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_CRAMFS=y
 CONFIG_ROMFS_FS=y
diff --git a/arch/microblaze/kernel/cpu/cache.c b/arch/microblaze/kernel/cpu/cache.c
index 0bde47e4fa69..dcba53803fa5 100644
--- a/arch/microblaze/kernel/cpu/cache.c
+++ b/arch/microblaze/kernel/cpu/cache.c
@@ -92,7 +92,8 @@ static inline void __disable_dcache_nomsr(void)
 #define CACHE_LOOP_LIMITS(start, end, cache_line_length, cache_size)	\
 do {									\
 	int align = ~(cache_line_length - 1);				\
-	end = min(start + cache_size, end);				\
+	if (start <  UINT_MAX - cache_size)				\
+		end = min(start + cache_size, end);			\
 	start &= align;							\
 } while (0)
 
diff --git a/arch/microblaze/kernel/cpu/cpuinfo.c b/arch/microblaze/kernel/cpu/cpuinfo.c
index ef2f49471a2a..cd9b4450763b 100644
--- a/arch/microblaze/kernel/cpu/cpuinfo.c
+++ b/arch/microblaze/kernel/cpu/cpuinfo.c
@@ -51,6 +51,7 @@ const struct cpu_ver_key cpu_ver_lookup[] = {
 	{"9.5", 0x22},
 	{"9.6", 0x23},
 	{"10.0", 0x24},
+	{"11.0", 0x25},
 	{NULL, 0},
 };
 
diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S
index 7d2894418691..14b276406153 100644
--- a/arch/microblaze/kernel/head.S
+++ b/arch/microblaze/kernel/head.S
@@ -121,10 +121,10 @@ no_fdt_arg:
 	tophys(r4,r4)			/* convert to phys address */
 	ori	r3, r0, COMMAND_LINE_SIZE - 1 /* number of loops */
 _copy_command_line:
-	/* r2=r5+r6 - r5 contain pointer to command line */
+	/* r2=r5+r11 - r5 contain pointer to command line */
 	lbu	r2, r5, r11
 	beqid	r2, skip		/* Skip if no data */
-	sb	r2, r4, r11		/* addr[r4+r6]= r2 */
+	sb	r2, r4, r11		/* addr[r4+r11]= r2 */
 	addik	r11, r11, 1		/* increment counting */
 	bgtid	r3, _copy_command_line	/* loop for all entries       */
 	addik	r3, r3, -1		/* decrement loop */
@@ -139,8 +139,8 @@ skip:
 	ori	r4, r0, TOPHYS(_bram_load_start)	/* save bram context */
 	ori	r3, r0, (LMB_SIZE - 4)
 _copy_bram:
-	lw	r7, r0, r11		/* r7 = r0 + r6 */
-	sw	r7, r4, r11		/* addr[r4 + r6] = r7 */
+	lw	r7, r0, r11		/* r7 = r0 + r11 */
+	sw	r7, r4, r11		/* addr[r4 + r11] = r7 */
 	addik	r11, r11, 4		/* increment counting */
 	bgtid	r3, _copy_bram		/* loop for all entries */
 	addik	r3, r3, -4		/* descrement loop */
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index c04385e60833..4c67b11f9c9e 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 050fc621c920..1056f1674065 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -7,6 +7,7 @@
  * for more details.
  */
 
+#include <linux/dma-contiguous.h>
 #include <linux/memblock.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -345,6 +346,9 @@ asmlinkage void __init mmu_init(void)
 	/* This will also cause that unflatten device tree will be allocated
 	 * inside 768MB limit */
 	memblock_set_current_limit(memory_start + lowmem_size - 1);
+
+	/* CMA initialization */
+	dma_contiguous_reserve(memory_start + lowmem_size - 1);
 }
 
 /* This is only called until mem_init is done. */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a2739a34bb12..797d7f1ad5fe 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -5,9 +5,11 @@ config MIPS
 	select ARCH_32BIT_OFF_T if !64BIT
 	select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT
 	select ARCH_CLOCKSOURCE_DATA
+	select ARCH_HAS_FORTIFY_SOURCE
+	select ARCH_HAS_KCOV
+	select ARCH_HAS_PTE_SPECIAL if !(32BIT && CPU_HAS_RIXI)
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_SUPPORTS_UPROBES
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF if 64BIT
@@ -47,7 +49,7 @@ config MIPS
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if CPU_SUPPORTS_HUGEPAGES
 	select HAVE_ASM_MODVERSIONS
-	select HAVE_EBPF_JIT if 64BIT && !CPU_MICROMIPS && TARGET_ISA_REV >= 2
+	select HAVE_CBPF_JIT if !64BIT && !CPU_MICROMIPS
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
@@ -55,11 +57,14 @@ config MIPS
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
+	select HAVE_EBPF_JIT if 64BIT && !CPU_MICROMIPS && TARGET_ISA_REV >= 2
 	select HAVE_EXIT_THREAD
 	select HAVE_FAST_GUP
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_VDSO
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
@@ -78,18 +83,14 @@ config MIPS
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP
-	select HAVE_GENERIC_VDSO
 	select IRQ_FORCED_THREADING
 	select ISA if EISA
-	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select MODULES_USE_ELF_REL if MODULES
+	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select PERF_USE_VMALLOC
 	select RTC_LIB
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
-	select ARCH_HAS_PTE_SPECIAL if !(32BIT && CPU_HAS_RIXI)
-	select ARCH_HAS_KCOV
-	select HAVE_GCC_PLUGINS
 
 menu "Machine selection"
 
@@ -104,20 +105,18 @@ config MIPS_GENERIC
 	select CEVT_R4K
 	select CLKSRC_MIPS_GIC
 	select COMMON_CLK
-	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
+	select CPU_MIPSR2_IRQ_VI
 	select CSRC_R4K
 	select DMA_PERDEV_COHERENT
 	select HAVE_PCI
 	select IRQ_MIPS_CPU
-	select LIBFDT
 	select MIPS_AUTO_PFN_OFFSET
 	select MIPS_CPU_SCACHE
 	select MIPS_GIC
 	select MIPS_L1_CACHE_SHIFT_7
 	select NO_EXCEPT_FILL
 	select PCI_DRIVERS_GENERIC
-	select PINCTRL
 	select SMP_UP if SMP
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_MIPS32_R1
@@ -132,11 +131,12 @@ config MIPS_GENERIC
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_MICROMIPS
-	select SYS_SUPPORTS_MIPS_CPS
 	select SYS_SUPPORTS_MIPS16
+	select SYS_SUPPORTS_MIPS_CPS
 	select SYS_SUPPORTS_MULTITHREADING
 	select SYS_SUPPORTS_RELOCATABLE
 	select SYS_SUPPORTS_SMARTMIPS
+	select UHI_BOOT
 	select USB_EHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN
 	select USB_EHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN
 	select USB_OHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN
@@ -144,7 +144,6 @@ config MIPS_GENERIC
 	select USB_UHCI_BIG_ENDIAN_DESC if CPU_BIG_ENDIAN
 	select USB_UHCI_BIG_ENDIAN_MMIO if CPU_BIG_ENDIAN
 	select USE_OF
-	select UHI_BOOT
 	help
 	  Select this to build a kernel which aims to support multiple boards,
 	  generally using a flattened device tree passed from the bootloader
@@ -403,7 +402,6 @@ config MACH_INGENIC
 	select GENERIC_IRQ_CHIP
 	select BUILTIN_DTB if MIPS_NO_APPENDED_DTB
 	select USE_OF
-	select LIBFDT
 
 config LANTIQ
 	bool "Lantiq based platforms"
@@ -510,7 +508,6 @@ config MACH_PISTACHIO
 	select DMA_NONCOHERENT
 	select GPIOLIB
 	select IRQ_MIPS_CPU
-	select LIBFDT
 	select MFD_SYSCON
 	select MIPS_CPU_SCACHE
 	select MIPS_GIC
@@ -548,7 +545,6 @@ config MIPS_MALTA
 	select I8253
 	select I8259
 	select IRQ_MIPS_CPU
-	select LIBFDT
 	select MIPS_BONITO64
 	select MIPS_CPU_SCACHE
 	select MIPS_GIC
@@ -980,7 +976,6 @@ config CAVIUM_OCTEON_SOC
 	select ZONE_DMA32
 	select HOLES_IN_ZONE
 	select GPIOLIB
-	select LIBFDT
 	select USE_OF
 	select ARCH_SPARSEMEM_ENABLE
 	select SYS_SUPPORTS_SMP
@@ -1223,8 +1218,7 @@ config NO_IOPORT_MAP
 	def_bool n
 
 config GENERIC_CSUM
-	bool
-	default y if !CPU_HAS_LOAD_STORE_LR
+	def_bool CPU_NO_LOAD_STORE_LR
 
 config GENERIC_ISA_DMA
 	bool
@@ -1442,11 +1436,14 @@ config CPU_LOONGSON64
 	bool "Loongson 64-bit CPU"
 	depends on SYS_HAS_CPU_LOONGSON64
 	select ARCH_HAS_PHYS_TO_DMA
+	select CPU_MIPSR2
+	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
 	select CPU_SUPPORTS_MSA
-	select CPU_HAS_LOAD_STORE_LR
+	select CPU_DIEI_BROKEN if !LOONGSON3_ENHANCEMENT
+	select CPU_MIPSR2_IRQ_VI
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
 	select MIPS_ASID_BITS_VARIABLE
@@ -1464,8 +1461,6 @@ config CPU_LOONGSON64
 config LOONGSON3_ENHANCEMENT
 	bool "New Loongson-3 CPU Enhancements"
 	default n
-	select CPU_MIPSR2
-	select CPU_HAS_PREFETCH
 	depends on CPU_LOONGSON64
 	help
 	  New Loongson-3 cores (since Loongson-3A R2, as opposed to Loongson-3A
@@ -1542,7 +1537,6 @@ config CPU_MIPS32_R1
 	bool "MIPS32 Release 1"
 	depends on SYS_HAS_CPU_MIPS32_R1
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	help
@@ -1560,7 +1554,6 @@ config CPU_MIPS32_R2
 	bool "MIPS32 Release 2"
 	depends on SYS_HAS_CPU_MIPS32_R2
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
@@ -1576,6 +1569,7 @@ config CPU_MIPS32_R6
 	bool "MIPS32 Release 6"
 	depends on SYS_HAS_CPU_MIPS32_R6
 	select CPU_HAS_PREFETCH
+	select CPU_NO_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
@@ -1591,7 +1585,6 @@ config CPU_MIPS64_R1
 	bool "MIPS64 Release 1"
 	depends on SYS_HAS_CPU_MIPS64_R1
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1611,7 +1604,6 @@ config CPU_MIPS64_R2
 	bool "MIPS64 Release 2"
 	depends on SYS_HAS_CPU_MIPS64_R2
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1629,6 +1621,7 @@ config CPU_MIPS64_R6
 	bool "MIPS64 Release 6"
 	depends on SYS_HAS_CPU_MIPS64_R6
 	select CPU_HAS_PREFETCH
+	select CPU_NO_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1646,7 +1639,6 @@ config CPU_R3000
 	bool "R3000"
 	depends on SYS_HAS_CPU_R3000
 	select CPU_HAS_WB
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_R3K_TLB
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1662,7 +1654,6 @@ config CPU_TX39XX
 	bool "R39XX"
 	depends on SYS_HAS_CPU_TX39XX
 	select CPU_SUPPORTS_32BIT_KERNEL
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_R3K_TLB
 
 config CPU_VR41XX
@@ -1670,7 +1661,6 @@ config CPU_VR41XX
 	depends on SYS_HAS_CPU_VR41XX
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
-	select CPU_HAS_LOAD_STORE_LR
 	help
 	  The options selects support for the NEC VR4100 series of processors.
 	  Only choose this option if you have one of these processors as a
@@ -1683,7 +1673,6 @@ config CPU_R4X00
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HUGEPAGES
-	select CPU_HAS_LOAD_STORE_LR
 	help
 	  MIPS Technologies R4000-series processors other than 4300, including
 	  the R4000, R4400, R4600, and 4700.
@@ -1692,7 +1681,6 @@ config CPU_TX49XX
 	bool "R49XX"
 	depends on SYS_HAS_CPU_TX49XX
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HUGEPAGES
@@ -1703,7 +1691,6 @@ config CPU_R5000
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HUGEPAGES
-	select CPU_HAS_LOAD_STORE_LR
 	help
 	  MIPS Technologies R5000-series processors other than the Nevada.
 
@@ -1713,7 +1700,6 @@ config CPU_R5500
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HUGEPAGES
-	select CPU_HAS_LOAD_STORE_LR
 	help
 	  NEC VR5500 and VR5500A series processors implement 64-bit MIPS IV
 	  instruction set.
@@ -1724,7 +1710,6 @@ config CPU_NEVADA
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HUGEPAGES
-	select CPU_HAS_LOAD_STORE_LR
 	help
 	  QED / PMC-Sierra RM52xx-series ("Nevada") processors.
 
@@ -1732,7 +1717,6 @@ config CPU_R10000
 	bool "R10000"
 	depends on SYS_HAS_CPU_R10000
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1744,7 +1728,6 @@ config CPU_RM7000
 	bool "RM7000"
 	depends on SYS_HAS_CPU_RM7000
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1753,7 +1736,6 @@ config CPU_RM7000
 config CPU_SB1
 	bool "SB1"
 	depends on SYS_HAS_CPU_SB1
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1764,7 +1746,6 @@ config CPU_CAVIUM_OCTEON
 	bool "Cavium Octeon processor"
 	depends on SYS_HAS_CPU_CAVIUM_OCTEON
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select WEAK_ORDERING
 	select CPU_SUPPORTS_HIGHMEM
@@ -1794,7 +1775,6 @@ config CPU_BMIPS
 	select WEAK_ORDERING
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_CPUFREQ
 	select MIPS_EXTERNAL_TIMER
 	help
@@ -1803,7 +1783,6 @@ config CPU_BMIPS
 config CPU_XLR
 	bool "Netlogic XLR SoC"
 	depends on SYS_HAS_CPU_XLR
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
@@ -1822,7 +1801,6 @@ config CPU_XLP
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_MIPSR2
 	select CPU_SUPPORTS_HUGEPAGES
 	select MIPS_ASID_BITS_VARIABLE
@@ -1928,14 +1906,12 @@ config CPU_LOONGSON2EF
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
 	select ARCH_HAS_PHYS_TO_DMA
-	select CPU_HAS_LOAD_STORE_LR
 
 config CPU_LOONGSON32
 	bool
 	select CPU_MIPS32
 	select CPU_MIPSR2
 	select CPU_HAS_PREFETCH
-	select CPU_HAS_LOAD_STORE_LR
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_CPUFREQ
@@ -2110,12 +2086,14 @@ config CPU_MIPSR2
 	bool
 	default y if CPU_MIPS32_R2 || CPU_MIPS64_R2 || CPU_CAVIUM_OCTEON
 	select CPU_HAS_RIXI
+	select CPU_HAS_DIEI if !CPU_DIEI_BROKEN
 	select MIPS_SPRAM
 
 config CPU_MIPSR6
 	bool
 	default y if CPU_MIPS32_R6 || CPU_MIPS64_R6
 	select CPU_HAS_RIXI
+	select CPU_HAS_DIEI if !CPU_DIEI_BROKEN
 	select HAVE_ARCH_BITREVERSE
 	select MIPS_ASID_BITS_VARIABLE
 	select MIPS_CRC_SUPPORT
@@ -2575,15 +2553,23 @@ config CPU_HAS_WB
 config XKS01
 	bool
 
+config CPU_HAS_DIEI
+	depends on !CPU_DIEI_BROKEN
+	bool
+
+config CPU_DIEI_BROKEN
+	bool
+
 config CPU_HAS_RIXI
 	bool
 
-config CPU_HAS_LOAD_STORE_LR
+config CPU_NO_LOAD_STORE_LR
 	bool
 	help
-	  CPU has support for unaligned load and store instructions:
+	  CPU lacks support for unaligned load and store instructions:
 	  LWL, LWR, SWL, SWR (Load/store word left/right).
-	  LDL, LDR, SDL, SDR (Load/store doubleword left/right, for 64bit systems).
+	  LDL, LDR, SDL, SDR (Load/store doubleword left/right, for 64bit
+	  systems).
 
 #
 # Vectored interrupt mode is an R2 feature
@@ -2696,6 +2682,14 @@ config NUMA
 config SYS_SUPPORTS_NUMA
 	bool
 
+config HAVE_SETUP_PER_CPU_AREA
+	def_bool y
+	depends on NUMA
+
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool y
+	depends on NUMA
+
 config RELOCATABLE
 	bool "Relocatable kernel"
 	depends on SYS_SUPPORTS_RELOCATABLE && (CPU_MIPS32_R2 || CPU_MIPS64_R2 || CPU_MIPS32_R6 || CPU_MIPS64_R6 || CAVIUM_OCTEON_SOC)
diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink
index f03fdc95143e..4b1d3ba3a8a2 100644
--- a/arch/mips/Makefile.postlink
+++ b/arch/mips/Makefile.postlink
@@ -17,7 +17,7 @@ quiet_cmd_ls3_llsc = LLSCCHK $@
       cmd_ls3_llsc = $(CMD_LS3_LLSC) $@
 
 CMD_RELOCS = arch/mips/boot/tools/relocs
-quiet_cmd_relocs = RELOCS $@
+quiet_cmd_relocs = RELOCS  $@
       cmd_relocs = $(CMD_RELOCS) $@
 
 # `@true` prevents complaint when there is nothing to be done
diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 528bd73d530a..4ed45ade32a1 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -123,7 +123,7 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS
 targets += vmlinux.its
 targets += vmlinux.gz.its
 targets += vmlinux.bz2.its
-targets += vmlinux.lzmo.its
+targets += vmlinux.lzma.its
 targets += vmlinux.lzo.its
 
 quiet_cmd_cpp_its_S = ITS     $@
diff --git a/arch/mips/boot/dts/ingenic/Makefile b/arch/mips/boot/dts/ingenic/Makefile
index 9cc48441eb71..e1654291a7b0 100644
--- a/arch/mips/boot/dts/ingenic/Makefile
+++ b/arch/mips/boot/dts/ingenic/Makefile
@@ -2,5 +2,6 @@
 dtb-$(CONFIG_JZ4740_QI_LB60)	+= qi_lb60.dtb
 dtb-$(CONFIG_JZ4770_GCW0)	+= gcw0.dtb
 dtb-$(CONFIG_JZ4780_CI20)	+= ci20.dtb
+dtb-$(CONFIG_X1000_CU1000_NEO)	+= cu1000-neo.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/boot/dts/ingenic/cu1000-neo.dts b/arch/mips/boot/dts/ingenic/cu1000-neo.dts
new file mode 100644
index 000000000000..03abd94acd84
--- /dev/null
+++ b/arch/mips/boot/dts/ingenic/cu1000-neo.dts
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/dts-v1/;
+
+#include "x1000.dtsi"
+#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/clock/ingenic,tcu.h>
+#include <dt-bindings/interrupt-controller/irq.h>
+
+/ {
+	compatible = "yna,cu1000-neo", "ingenic,x1000";
+	model = "YSH & ATIL General Board CU Neo";
+
+	aliases {
+		serial2 = &uart2;
+	};
+
+	chosen {
+		stdout-path = "serial2:115200n8";
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x04000000>;
+	};
+
+	wlan_pwrseq: msc1-pwrseq {
+		compatible = "mmc-pwrseq-simple";
+
+		clocks = <&lpoclk>;
+		clock-names = "ext_clock";
+
+		reset-gpios = <&gpc 17 GPIO_ACTIVE_LOW>;
+		post-power-on-delay-ms = <200>;
+
+		lpoclk: ap6212a {
+			compatible = "fixed-clock";
+			#clock-cells = <0>;
+			clock-frequency = <32768>;
+		};
+	};
+};
+
+&exclk {
+	clock-frequency = <24000000>;
+};
+
+&tcu {
+	/* 1500 kHz for the system timer and clocksource */
+	assigned-clocks = <&tcu TCU_CLK_TIMER0>, <&tcu TCU_CLK_TIMER2>;
+	assigned-clock-rates = <1500000>, <1500000>;
+
+	/* Use channel #0 for the system timer channel #2 for the clocksource */
+	ingenic,pwm-channels-mask = <0xfa>;
+};
+
+&i2c0 {
+	status = "okay";
+
+	clock-frequency = <400000>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_i2c0>;
+
+	ads7830@48 {
+		compatible = "ti,ads7830";
+		reg = <0x48>;
+	};
+};
+
+&uart2 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_uart2>;
+
+	status = "okay";
+};
+
+&mac {
+	phy-mode = "rmii";
+	phy-handle = <&lan8720a>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_mac>;
+
+	snps,reset-gpio = <&gpc 23 GPIO_ACTIVE_LOW>; /* PC23 */
+	snps,reset-active-low;
+	snps,reset-delays-us = <0 10000 30000>;
+
+	status = "okay";
+};
+
+&mdio {
+	status = "okay";
+
+	lan8720a: ethernet-phy@0 {
+		compatible = "ethernet-phy-id0007.c0f0", "ethernet-phy-ieee802.3-c22";
+		reg = <0>;
+	};
+};
+
+&msc0 {
+	bus-width = <8>;
+	max-frequency = <50000000>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_msc0>;
+
+	non-removable;
+
+	status = "okay";
+};
+
+&msc1 {
+	bus-width = <4>;
+	max-frequency = <50000000>;
+
+	pinctrl-names = "default";
+	pinctrl-0 = <&pins_msc1>;
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	non-removable;
+
+	mmc-pwrseq = <&wlan_pwrseq>;
+
+	status = "okay";
+
+	ap6212a: wifi@1 {
+		compatible = "brcm,bcm4329-fmac";
+		reg = <1>;
+
+		interrupt-parent = <&gpc>;
+		interrupts = <16 IRQ_TYPE_EDGE_FALLING>;
+		interrupt-names = "host-wake";
+
+		brcm,drive-strength = <10>;
+	};
+};
+
+&pinctrl {
+	pins_i2c0: i2c0 {
+		function = "i2c0";
+		groups = "i2c0-data";
+		bias-disable;
+	};
+
+	pins_uart2: uart2 {
+		function = "uart2";
+		groups = "uart2-data-d";
+		bias-disable;
+	};
+
+	pins_mac: mac {
+		function = "mac";
+		groups = "mac";
+		bias-disable;
+	};
+
+	pins_msc0: msc0 {
+		function = "mmc0";
+		groups = "mmc0-1bit", "mmc0-4bit", "mmc0-8bit";
+		bias-disable;
+	};
+
+	pins_msc1: msc1 {
+		function = "mmc1";
+		groups = "mmc1-1bit", "mmc1-4bit";
+		bias-disable;
+	};
+};
diff --git a/arch/mips/boot/dts/ingenic/x1000.dtsi b/arch/mips/boot/dts/ingenic/x1000.dtsi
new file mode 100644
index 000000000000..4994c695a1a7
--- /dev/null
+++ b/arch/mips/boot/dts/ingenic/x1000.dtsi
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <dt-bindings/clock/x1000-cgu.h>
+#include <dt-bindings/dma/x1000-dma.h>
+
+/ {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	compatible = "ingenic,x1000", "ingenic,x1000e";
+
+	cpuintc: interrupt-controller {
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+		interrupt-controller;
+		compatible = "mti,cpu-interrupt-controller";
+	};
+
+	intc: interrupt-controller@10001000 {
+		compatible = "ingenic,x1000-intc", "ingenic,jz4780-intc";
+		reg = <0x10001000 0x50>;
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		interrupt-parent = <&cpuintc>;
+		interrupts = <2>;
+	};
+
+	exclk: ext {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+	};
+
+	rtclk: rtc {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <32768>;
+	};
+
+	cgu: x1000-cgu@10000000 {
+		compatible = "ingenic,x1000-cgu";
+		reg = <0x10000000 0x100>;
+
+		#clock-cells = <1>;
+
+		clocks = <&exclk>, <&rtclk>;
+		clock-names = "ext", "rtc";
+	};
+
+	tcu: timer@10002000 {
+		compatible = "ingenic,x1000-tcu",
+				 "ingenic,jz4770-tcu",
+				 "simple-mfd";
+		reg = <0x10002000 0x1000>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0x0 0x10002000 0x1000>;
+
+		#clock-cells = <1>;
+
+		clocks = <&cgu X1000_CLK_RTCLK
+			  &cgu X1000_CLK_EXCLK
+			  &cgu X1000_CLK_PCLK>;
+		clock-names = "rtc", "ext", "pclk";
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <27 26 25>;
+
+		wdt: watchdog@0 {
+			compatible = "ingenic,x1000-watchdog", "ingenic,jz4780-watchdog";
+			reg = <0x0 0x10>;
+
+			clocks = <&cgu X1000_CLK_RTCLK>;
+			clock-names = "wdt";
+		};
+	};
+
+	rtc: rtc@10003000 {
+		compatible = "ingenic,x1000-rtc", "ingenic,jz4780-rtc";
+		reg = <0x10003000 0x4c>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <32>;
+
+		clocks = <&cgu X1000_CLK_RTCLK>;
+		clock-names = "rtc";
+	};
+
+	pinctrl: pin-controller@10010000 {
+		compatible = "ingenic,x1000-pinctrl";
+		reg = <0x10010000 0x800>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		gpa: gpio@0 {
+			compatible = "ingenic,x1000-gpio";
+			reg = <0>;
+
+			gpio-controller;
+			gpio-ranges = <&pinctrl 0 0 32>;
+			#gpio-cells = <2>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <17>;
+		};
+
+		gpb: gpio@1 {
+			compatible = "ingenic,x1000-gpio";
+			reg = <1>;
+
+			gpio-controller;
+			gpio-ranges = <&pinctrl 0 32 32>;
+			#gpio-cells = <2>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <16>;
+		};
+
+		gpc: gpio@2 {
+			compatible = "ingenic,x1000-gpio";
+			reg = <2>;
+
+			gpio-controller;
+			gpio-ranges = <&pinctrl 0 64 32>;
+			#gpio-cells = <2>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <15>;
+		};
+
+		gpd: gpio@3 {
+			compatible = "ingenic,x1000-gpio";
+			reg = <3>;
+
+			gpio-controller;
+			gpio-ranges = <&pinctrl 0 96 32>;
+			#gpio-cells = <2>;
+
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			interrupt-parent = <&intc>;
+			interrupts = <14>;
+		};
+	};
+
+	i2c0: i2c-controller@10050000 {
+		compatible = "ingenic,x1000-i2c";
+		reg = <0x10050000 0x1000>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <60>;
+
+		clocks = <&cgu X1000_CLK_I2C0>;
+
+		status = "disabled";
+	};
+
+	i2c1: i2c-controller@10051000 {
+		compatible = "ingenic,x1000-i2c";
+		reg = <0x10051000 0x1000>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <59>;
+
+		clocks = <&cgu X1000_CLK_I2C1>;
+
+		status = "disabled";
+	};
+
+	i2c2: i2c-controller@10052000 {
+		compatible = "ingenic,x1000-i2c";
+		reg = <0x10052000 0x1000>;
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <58>;
+
+		clocks = <&cgu X1000_CLK_I2C2>;
+
+		status = "disabled";
+	};
+
+	uart0: serial@10030000 {
+		compatible = "ingenic,x1000-uart";
+		reg = <0x10030000 0x100>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <51>;
+
+		clocks = <&exclk>, <&cgu X1000_CLK_UART0>;
+		clock-names = "baud", "module";
+
+		status = "disabled";
+	};
+
+	uart1: serial@10031000 {
+		compatible = "ingenic,x1000-uart";
+		reg = <0x10031000 0x100>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <50>;
+
+		clocks = <&exclk>, <&cgu X1000_CLK_UART1>;
+		clock-names = "baud", "module";
+
+		status = "disabled";
+	};
+
+	uart2: serial@10032000 {
+		compatible = "ingenic,x1000-uart";
+		reg = <0x10032000 0x100>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <49>;
+
+		clocks = <&exclk>, <&cgu X1000_CLK_UART2>;
+		clock-names = "baud", "module";
+
+		status = "disabled";
+	};
+
+	pdma: dma-controller@13420000 {
+		compatible = "ingenic,x1000-dma";
+		reg = <0x13420000 0x400
+			   0x13421000 0x40>;
+		#dma-cells = <2>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <10>;
+
+		clocks = <&cgu X1000_CLK_PDMA>;
+	};
+
+	mac: ethernet@134b0000 {
+		compatible = "ingenic,x1000-mac", "snps,dwmac";
+		reg = <0x134b0000 0x2000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <55>;
+		interrupt-names = "macirq";
+
+		clocks = <&cgu X1000_CLK_MAC>;
+		clock-names = "stmmaceth";
+
+		status = "disabled";
+
+		mdio: mdio {
+			compatible = "snps,dwmac-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			status = "disabled";
+		};
+	};
+
+	msc0: mmc@13450000 {
+		compatible = "ingenic,x1000-mmc";
+		reg = <0x13450000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <37>;
+
+		clocks = <&cgu X1000_CLK_MSC0>;
+		clock-names = "mmc";
+
+		cap-sd-highspeed;
+		cap-mmc-highspeed;
+		cap-sdio-irq;
+
+		dmas = <&pdma X1000_DMA_MSC0_RX 0xffffffff>,
+			   <&pdma X1000_DMA_MSC0_TX 0xffffffff>;
+		dma-names = "rx", "tx";
+
+		status = "disabled";
+	};
+
+	msc1: mmc@13460000 {
+		compatible = "ingenic,x1000-mmc";
+		reg = <0x13460000 0x1000>;
+
+		interrupt-parent = <&intc>;
+		interrupts = <36>;
+
+		clocks = <&cgu X1000_CLK_MSC1>;
+		clock-names = "mmc";
+
+		cap-sd-highspeed;
+		cap-mmc-highspeed;
+		cap-sdio-irq;
+
+		dmas = <&pdma X1000_DMA_MSC1_RX 0xffffffff>,
+			   <&pdma X1000_DMA_MSC1_TX 0xffffffff>;
+		dma-names = "rx", "tx";
+
+		status = "disabled";
+	};
+};
diff --git a/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
index aa5caaa31104..6069b33cf09f 100644
--- a/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
+++ b/arch/mips/boot/dts/ralink/gardena_smart_gateway_mt7688.dts
@@ -177,6 +177,9 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinmux_i2s_gpio>;		/* GPIO0..3 */
 
+	fifo-size = <8>;
+	tx-threshold = <8>;
+
 	rts-gpios = <&gpio 1 GPIO_ACTIVE_LOW>;
 	cts-gpios = <&gpio 2 GPIO_ACTIVE_LOW>;
 };
@@ -195,3 +198,8 @@
 &watchdog {
 	status = "okay";
 };
+
+&wmac {
+	status = "okay";
+	mediatek,mtd-eeprom = <&factory 0x0000>;
+};
diff --git a/arch/mips/boot/dts/ralink/mt7628a.dtsi b/arch/mips/boot/dts/ralink/mt7628a.dtsi
index 742bcc1dc2e0..892e8ab863c5 100644
--- a/arch/mips/boot/dts/ralink/mt7628a.dtsi
+++ b/arch/mips/boot/dts/ralink/mt7628a.dtsi
@@ -285,4 +285,14 @@
 		interrupt-parent = <&intc>;
 		interrupts = <18>;
 	};
+
+	wmac: wmac@10300000 {
+		compatible = "mediatek,mt7628-wmac";
+		reg = <0x10300000 0x100000>;
+
+		interrupt-parent = <&cpuintc>;
+		interrupts = <6>;
+
+		status = "disabled";
+	};
 };
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index f97be32bf699..6bd1e97effdf 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -2193,7 +2193,7 @@ static int octeon_irq_cib_map(struct irq_domain *d,
 	struct octeon_irq_cib_chip_data *cd;
 
 	if (hw >= host_data->max_bits) {
-		pr_err("ERROR: %s mapping %u is to big!\n",
+		pr_err("ERROR: %s mapping %u is too big!\n",
 		       irq_domain_get_of_node(d)->name, (unsigned)hw);
 		return -EINVAL;
 	}
diff --git a/arch/mips/configs/cu1000-neo_defconfig b/arch/mips/configs/cu1000-neo_defconfig
new file mode 100644
index 000000000000..9b05a8fdabe1
--- /dev/null
+++ b/arch/mips/configs/cu1000-neo_defconfig
@@ -0,0 +1,117 @@
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_KERNEL_GZIP=y
+CONFIG_SYSVIPC=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_CGROUPS=y
+CONFIG_MEMCG=y
+CONFIG_MEMCG_KMEM=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+CONFIG_MACH_INGENIC=y
+CONFIG_X1000_CU1000_NEO=y
+CONFIG_HIGHMEM=y
+CONFIG_HZ_100=y
+# CONFIG_SECCOMP is not set
+# CONFIG_SUSPEND is not set
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_COMPACTION is not set
+CONFIG_CMA=y
+CONFIG_CMA_AREAS=7
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_CFG80211=y
+CONFIG_UEVENT_HELPER=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+# CONFIG_FW_LOADER is not set
+# CONFIG_ALLOW_DEV_COREDUMP is not set
+CONFIG_NETDEVICES=y
+CONFIG_STMMAC_ETH=y
+CONFIG_SMSC_PHY=y
+CONFIG_BRCMFMAC=y
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_LEGACY_PTY_COUNT=2
+CONFIG_SERIAL_EARLYCON=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=3
+CONFIG_SERIAL_8250_RUNTIME_UARTS=3
+CONFIG_SERIAL_8250_INGENIC=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_I2C=y
+CONFIG_I2C_JZ4780=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_SENSORS_ADS7828=y
+CONFIG_WATCHDOG=y
+CONFIG_JZ4740_WDT=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
+# CONFIG_VGA_CONSOLE is not set
+# CONFIG_HID is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_MMC=y
+CONFIG_MMC_JZ4740=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_JZ4740=y
+CONFIG_DMADEVICES=y
+CONFIG_DMA_JZ4780=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_NVMEM=y
+CONFIG_NVMEM_SYSFS=y
+CONFIG_EXT4_FS=y
+# CONFIG_DNOTIFY is not set
+CONFIG_AUTOFS_FS=y
+CONFIG_PROC_KCORE=y
+# CONFIG_PROC_PAGE_MONITOR is not set
+CONFIG_TMPFS=y
+CONFIG_CONFIGFS_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NLS=y
+CONFIG_NLS_CODEPAGE_936=y
+CONFIG_NLS_CODEPAGE_950=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_CRYPTO_ECHAINIV=y
+CONFIG_CRYPTO_AES=y
+CONFIG_CRYPTO_DEFLATE=y
+CONFIG_CRYPTO_LZO=y
+CONFIG_PRINTK_TIME=y
+CONFIG_CONSOLE_LOGLEVEL_DEFAULT=15
+CONFIG_CONSOLE_LOGLEVEL_QUIET=15
+CONFIG_MESSAGE_LOGLEVEL_DEFAULT=7
+CONFIG_DEBUG_INFO=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_DEBUG_FS=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PANIC_TIMEOUT=10
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+CONFIG_STACKTRACE=y
+# CONFIG_FTRACE is not set
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="earlycon clk_ignore_unused"
diff --git a/arch/mips/configs/generic/board-ocelot.config b/arch/mips/configs/generic/board-ocelot.config
index 1134fbb99fc2..7626f2a75b03 100644
--- a/arch/mips/configs/generic/board-ocelot.config
+++ b/arch/mips/configs/generic/board-ocelot.config
@@ -41,6 +41,7 @@ CONFIG_SPI_DESIGNWARE=y
 CONFIG_SPI_DW_MMIO=y
 CONFIG_SPI_SPIDEV=y
 
+CONFIG_PINCTRL=y
 CONFIG_PINCTRL_OCELOT=y
 
 CONFIG_GPIO_SYSFS=y
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 61b0fc2026e6..4ebd8ce254ce 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -6,7 +6,6 @@ generated-y += syscall_table_64_n64.h
 generated-y += syscall_table_64_o32.h
 generic-y += current.h
 generic-y += device.h
-generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
 generic-y += export.h
 generic-y += irq_work.h
@@ -19,6 +18,7 @@ generic-y += preempt.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
 generic-y += sections.h
+generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
 generic-y += user.h
diff --git a/arch/mips/include/asm/bootinfo.h b/arch/mips/include/asm/bootinfo.h
index d41a5057bc69..61727785a247 100644
--- a/arch/mips/include/asm/bootinfo.h
+++ b/arch/mips/include/asm/bootinfo.h
@@ -81,6 +81,7 @@ enum loongson2ef_machine_type {
 #define  MACH_INGENIC_JZ4770	2	/* JZ4770 SOC		*/
 #define  MACH_INGENIC_JZ4780	3	/* JZ4780 SOC		*/
 #define  MACH_INGENIC_X1000		4	/* X1000 SOC		*/
+#define  MACH_INGENIC_X1830		5	/* X1830 SOC		*/
 
 extern char *system_type;
 const char *get_system_type(void);
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index c99166eadbde..255afcdd79c9 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -100,24 +100,6 @@ typedef u32		compat_sigset_word;
 
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	/* cast to a __user pointer via "unsigned long" makes sparse happy */
-	return (void __user *)(unsigned long)(long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
 	struct pt_regs *regs = (struct pt_regs *)
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 983a6a7f43a1..de44c92b1c1f 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -555,6 +555,10 @@
 # define cpu_has_perf		__opt(MIPS_CPU_PERF)
 #endif
 
+#ifndef cpu_has_mac2008_only
+# define cpu_has_mac2008_only	__opt(MIPS_CPU_MAC_2008_ONLY)
+#endif
+
 #ifdef CONFIG_SMP
 /*
  * Some systems share FTLB RAMs between threads within a core (siblings in
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index ea830783d663..216a22916740 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -46,7 +46,7 @@
 #define PRID_COMP_NETLOGIC	0x0c0000
 #define PRID_COMP_CAVIUM	0x0d0000
 #define PRID_COMP_LOONGSON	0x140000
-#define PRID_COMP_INGENIC_D0	0xd00000	/* JZ4740, JZ4750 */
+#define PRID_COMP_INGENIC_D0	0xd00000	/* JZ4740, JZ4750, X1830 */
 #define PRID_COMP_INGENIC_D1	0xd10000	/* JZ4770, JZ4775, X1000 */
 #define PRID_COMP_INGENIC_E1	0xe10000	/* JZ4780 */
 
@@ -185,7 +185,8 @@
  * These are the PRID's for when 23:16 == PRID_COMP_INGENIC_*
  */
 
-#define PRID_IMP_XBURST	       0x0200
+#define PRID_IMP_XBURST_REV1	0x0200	/* XBurst with MXU SIMD ISA		*/
+#define PRID_IMP_XBURST_REV2	0x0100	/* XBurst with MXU2 SIMD ISA	*/
 
 /*
  * These are the PRID's for when 23:16 == PRID_COMP_NETLOGIC
@@ -415,6 +416,7 @@ enum cpu_type_enum {
 #define MIPS_CPU_MT_PER_TC_PERF_COUNTERS \
 				BIT_ULL(56)	/* CPU has perf counters implemented per TC (MIPSMT ASE) */
 #define MIPS_CPU_MMID		BIT_ULL(57)	/* CPU supports MemoryMapIDs */
+#define MIPS_CPU_MAC_2008_ONLY	BIT_ULL(58)	/* CPU Only support MAC2008 Fused multiply-add instruction */
 
 /*
  * CPU ASE encodings
diff --git a/arch/mips/include/asm/gio_device.h b/arch/mips/include/asm/gio_device.h
index c52948f9ca95..159087f5386e 100644
--- a/arch/mips/include/asm/gio_device.h
+++ b/arch/mips/include/asm/gio_device.h
@@ -32,8 +32,6 @@ struct gio_driver {
 };
 #define to_gio_driver(drv) container_of(drv, struct gio_driver, driver)
 
-extern const struct gio_device_id *gio_match_device(const struct gio_device_id *,
-						    const struct gio_device *);
 extern struct gio_device *gio_dev_get(struct gio_device *);
 extern void gio_dev_put(struct gio_device *);
 
diff --git a/arch/mips/include/asm/hazards.h b/arch/mips/include/asm/hazards.h
index a4f48b0f5541..a0b92205f933 100644
--- a/arch/mips/include/asm/hazards.h
+++ b/arch/mips/include/asm/hazards.h
@@ -23,7 +23,7 @@
  * TLB hazards
  */
 #if (defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)) && \
-	!defined(CONFIG_CPU_CAVIUM_OCTEON) && !defined(CONFIG_LOONGSON3_ENHANCEMENT)
+	!defined(CONFIG_CPU_CAVIUM_OCTEON) && !defined(CONFIG_CPU_LOONGSON64)
 
 /*
  * MIPSR2 defines ehb for hazard avoidance
@@ -158,7 +158,7 @@ do {									\
 } while (0)
 
 #elif defined(CONFIG_MIPS_ALCHEMY) || defined(CONFIG_CPU_CAVIUM_OCTEON) || \
-	defined(CONFIG_CPU_LOONGSON2EF) || defined(CONFIG_LOONGSON3_ENHANCEMENT) || \
+	defined(CONFIG_CPU_LOONGSON2EF) || defined(CONFIG_CPU_LOONGSON64) || \
 	defined(CONFIG_CPU_R10000) || defined(CONFIG_CPU_R5500) || defined(CONFIG_CPU_XLR)
 
 /*
diff --git a/arch/mips/include/asm/irqflags.h b/arch/mips/include/asm/irqflags.h
index c4728bbdf15b..47a8ffc0b413 100644
--- a/arch/mips/include/asm/irqflags.h
+++ b/arch/mips/include/asm/irqflags.h
@@ -18,7 +18,7 @@
 #include <asm/compiler.h>
 #include <asm/hazards.h>
 
-#if defined(CONFIG_CPU_MIPSR2) || defined (CONFIG_CPU_MIPSR6)
+#if defined(CONFIG_CPU_HAS_DIEI)
 
 static inline void arch_local_irq_disable(void)
 {
@@ -94,7 +94,7 @@ static inline void arch_local_irq_restore(unsigned long flags)
 void arch_local_irq_disable(void);
 unsigned long arch_local_irq_save(void);
 void arch_local_irq_restore(unsigned long flags);
-#endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
+#endif /* CONFIG_CPU_HAS_DIEI */
 
 static inline void arch_local_irq_enable(void)
 {
@@ -102,7 +102,7 @@ static inline void arch_local_irq_enable(void)
 	"	.set	push						\n"
 	"	.set	reorder						\n"
 	"	.set	noat						\n"
-#if   defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
+#if defined(CONFIG_CPU_HAS_DIEI)
 	"	ei							\n"
 #else
 	"	mfc0	$1,$12						\n"
diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h
index 02783e141c32..fef0fda8f82f 100644
--- a/arch/mips/include/asm/local.h
+++ b/arch/mips/include/asm/local.h
@@ -37,6 +37,7 @@ static __inline__ long local_add_return(long i, local_t * l)
 		__asm__ __volatile__(
 		"	.set	push					\n"
 		"	.set	arch=r4000				\n"
+			__SYNC(full, loongson3_war) "			\n"
 		"1:"	__LL	"%1, %2		# local_add_return	\n"
 		"	addu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
@@ -52,6 +53,7 @@ static __inline__ long local_add_return(long i, local_t * l)
 		__asm__ __volatile__(
 		"	.set	push					\n"
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
+			__SYNC(full, loongson3_war) "			\n"
 		"1:"	__LL	"%1, %2		# local_add_return	\n"
 		"	addu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
@@ -84,6 +86,7 @@ static __inline__ long local_sub_return(long i, local_t * l)
 		__asm__ __volatile__(
 		"	.set	push					\n"
 		"	.set	arch=r4000				\n"
+			__SYNC(full, loongson3_war) "			\n"
 		"1:"	__LL	"%1, %2		# local_sub_return	\n"
 		"	subu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
@@ -99,6 +102,7 @@ static __inline__ long local_sub_return(long i, local_t * l)
 		__asm__ __volatile__(
 		"	.set	push					\n"
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
+			__SYNC(full, loongson3_war) "			\n"
 		"1:"	__LL	"%1, %2		# local_sub_return	\n"
 		"	subu	%0, %1, %3				\n"
 			__SC	"%0, %2					\n"
diff --git a/arch/mips/include/asm/mach-ip27/kernel-entry-init.h b/arch/mips/include/asm/mach-ip27/kernel-entry-init.h
index f992c1db876b..3e54f605a70b 100644
--- a/arch/mips/include/asm/mach-ip27/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-ip27/kernel-entry-init.h
@@ -10,20 +10,10 @@
 #define __ASM_MACH_IP27_KERNEL_ENTRY_H
 
 #include <asm/sn/addrs.h>
-#include <asm/sn/sn0/hubni.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/klkernvars.h>
 
 /*
- * Returns the local nasid into res.
- */
-	.macro GET_NASID_ASM res
-	dli	\res, LOCAL_HUB_ADDR(NI_STATUS_REV_ID)
-	ld	\res, (\res)
-	and	\res, NSRI_NODEID_MASK
-	dsrl	\res, NSRI_NODEID_SHFT
-	.endm
-
-/*
  * TLB bits
  */
 #define PAGE_GLOBAL		(1 << 6)
diff --git a/arch/mips/include/asm/mach-ip27/mangle-port.h b/arch/mips/include/asm/mach-ip27/mangle-port.h
index f6e4912ea062..27c56efa519f 100644
--- a/arch/mips/include/asm/mach-ip27/mangle-port.h
+++ b/arch/mips/include/asm/mach-ip27/mangle-port.h
@@ -8,7 +8,7 @@
 #ifndef __ASM_MACH_IP27_MANGLE_PORT_H
 #define __ASM_MACH_IP27_MANGLE_PORT_H
 
-#define __swizzle_addr_b(port)	(port)
+#define __swizzle_addr_b(port)	((port) ^ 3)
 #define __swizzle_addr_w(port)	((port) ^ 2)
 #define __swizzle_addr_l(port)	(port)
 #define __swizzle_addr_q(port)	(port)
@@ -20,6 +20,6 @@
 # define ioswabl(a, x)		(x)
 # define __mem_ioswabl(a, x)	cpu_to_le32(x)
 # define ioswabq(a, x)		(x)
-# define __mem_ioswabq(a, x)	cpu_to_le32(x)
+# define __mem_ioswabq(a, x)	cpu_to_le64(x)
 
 #endif /* __ASM_MACH_IP27_MANGLE_PORT_H */
diff --git a/arch/mips/include/asm/mach-ip27/mmzone.h b/arch/mips/include/asm/mach-ip27/mmzone.h
index f463826515df..08c36e50a860 100644
--- a/arch/mips/include/asm/mach-ip27/mmzone.h
+++ b/arch/mips/include/asm/mach-ip27/mmzone.h
@@ -4,7 +4,8 @@
 
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
-#include <asm/sn/hub.h>
+#include <asm/sn/agent.h>
+#include <asm/sn/klkernvars.h>
 
 #define pa_to_nid(addr)		NASID_GET(addr)
 
@@ -12,7 +13,6 @@ struct hub_data {
 	kern_vars_t	kern_vars;
 	DECLARE_BITMAP(h_bigwin_used, HUB_NUM_BIG_WINDOW);
 	cpumask_t	h_cpus;
-	unsigned long slice_map;
 };
 
 struct node_data {
diff --git a/arch/mips/include/asm/mach-ip27/topology.h b/arch/mips/include/asm/mach-ip27/topology.h
index be61ddcdacab..d66cc53feab8 100644
--- a/arch/mips/include/asm/mach-ip27/topology.h
+++ b/arch/mips/include/asm/mach-ip27/topology.h
@@ -2,12 +2,12 @@
 #ifndef _ASM_MACH_TOPOLOGY_H
 #define _ASM_MACH_TOPOLOGY_H	1
 
-#include <asm/sn/hub.h>
 #include <asm/sn/types.h>
 #include <asm/mmzone.h>
 
 struct cpuinfo_ip27 {
 	nasid_t		p_nasid;	/* my node ID in numa-as-id-space */
+	unsigned short	p_speed;	/* cpu speed in MHz */
 	unsigned char	p_slice;	/* Physical position on node board */
 };
 
diff --git a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
index 7dc8d75445a9..4fab38c743dd 100644
--- a/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-loongson64/cpu-feature-overrides.h
@@ -46,5 +46,7 @@
 #define cpu_has_wsbh		1
 #define cpu_has_ic_fills_f_dc	1
 #define cpu_hwrena_impl_bits	0xc0000000
+#define cpu_has_mac2008_only	1
+#define cpu_has_mips_r2_exec_hazard 0
 
 #endif /* __ASM_MACH_LOONGSON64_CPU_FEATURE_OVERRIDES_H */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 0d5a30988697..796fe47cfd17 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1101,9 +1101,12 @@
 /*
  * Bits 22:20 of the FPU Status Register will be read as 0,
  * and should be written as zero.
+ * MAC2008 was removed in Release 5 so we still treat it as
+ * reserved.
  */
 #define FPU_CSR_RSVD	(_ULCAST_(7) << 20)
 
+#define FPU_CSR_MAC2008	(_ULCAST_(1) << 20)
 #define FPU_CSR_ABS2008	(_ULCAST_(1) << 19)
 #define FPU_CSR_NAN2008	(_ULCAST_(1) << 18)
 
diff --git a/arch/mips/include/asm/pci/bridge.h b/arch/mips/include/asm/pci/bridge.h
index 3bc630ff9ad4..9c476a0400e0 100644
--- a/arch/mips/include/asm/pci/bridge.h
+++ b/arch/mips/include/asm/pci/bridge.h
@@ -806,7 +806,8 @@ struct bridge_controller {
 	unsigned long		baddr;
 	unsigned long		intr_addr;
 	struct irq_domain	*domain;
-	unsigned int		pci_int[8];
+	unsigned int		pci_int[8][2];
+	unsigned int		int_mapping[8][2];
 	u32			ioc3_sid[8];
 	nasid_t			nasid;
 };
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 91b89aab1787..aef5378f909c 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -639,6 +639,11 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifdef _PAGE_HUGE
+#define pmd_leaf(pmd)	((pmd_val(pmd) & _PAGE_HUGE) != 0)
+#define pud_leaf(pud)	((pud_val(pud) & _PAGE_HUGE) != 0)
+#endif
+
 #define gup_fast_permitted(start, end)	(!cpu_has_dc_aliases)
 
 #include <asm-generic/pgtable.h>
diff --git a/arch/mips/include/asm/serial.h b/arch/mips/include/asm/serial.h
deleted file mode 100644
index 2777148dbfc5..000000000000
--- a/arch/mips/include/asm/serial.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2017 MIPS Tech, LLC
- */
-#ifndef __ASM__SERIAL_H
-#define __ASM__SERIAL_H
-
-#ifdef CONFIG_MIPS_GENERIC
-/*
- * Generic kernels cannot know a correct value for all platforms at
- * compile time. Set it to 0 to prevent 8250_early using it
- */
-#define BASE_BAUD 0
-#else
-#include <asm-generic/serial.h>
-#endif
-
-#endif /* __ASM__SERIAL_H */
diff --git a/arch/mips/include/asm/sn/arch.h b/arch/mips/include/asm/sn/arch.h
index f7d3273d9599..9a9682543e89 100644
--- a/arch/mips/include/asm/sn/arch.h
+++ b/arch/mips/include/asm/sn/arch.h
@@ -25,7 +25,4 @@
 #define INVALID_MODULE		(moduleid_t)-1
 #define INVALID_PARTID		(partid_t)-1
 
-extern nasid_t get_nasid(void);
-extern int get_cpu_slice(cpuid_t);
-
 #endif /* _ASM_SN_ARCH_H */
diff --git a/arch/mips/include/asm/sn/hub.h b/arch/mips/include/asm/sn/hub.h
deleted file mode 100644
index 45878fbefbae..000000000000
--- a/arch/mips/include/asm/sn/hub.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_SN_HUB_H
-#define __ASM_SN_HUB_H
-
-#include <linux/types.h>
-#include <linux/cpumask.h>
-#include <asm/sn/types.h>
-#include <asm/sn/io.h>
-#include <asm/sn/klkernvars.h>
-#include <asm/xtalk/xtalk.h>
-
-/* ip27-hubio.c */
-extern unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget,
-			  unsigned long xtalk_addr, size_t size);
-extern void hub_pio_init(nasid_t nasid);
-
-#endif /* __ASM_SN_HUB_H */
diff --git a/arch/mips/include/asm/sn/intr.h b/arch/mips/include/asm/sn/intr.h
index fc1348193957..3d6954d370dc 100644
--- a/arch/mips/include/asm/sn/intr.h
+++ b/arch/mips/include/asm/sn/intr.h
@@ -8,15 +8,6 @@
 #ifndef __ASM_SN_INTR_H
 #define __ASM_SN_INTR_H
 
-/* Number of interrupt levels associated with each interrupt register. */
-#define N_INTPEND_BITS		64
-
-#define INT_PEND0_BASELVL	0
-#define INT_PEND1_BASELVL	64
-
-#define N_INTPENDJUNK_BITS	8
-#define INTPENDJUNK_CLRBIT	0x80
-
 /*
  * Macros to manipulate the interrupt register on the calling hub chip.
  */
@@ -84,14 +75,6 @@ do {								\
 #define CPU_RESCHED_B_IRQ	 8
 #define CPU_CALL_A_IRQ		 9
 #define CPU_CALL_B_IRQ		10
-#define MSC_MESG_INTR		11
-#define BASE_PCI_IRQ		12
-
-/*
- * INT_PEND0 again, bits determined by hardware / hardcoded:
- */
-#define SDISK_INTR		63	/* SABLE name */
-#define IP_PEND0_6_63		63	/* What is this bit? */
 
 /*
  * INT_PEND1 hard-coded bits:
diff --git a/arch/mips/include/asm/sn/ioc3.h b/arch/mips/include/asm/sn/ioc3.h
index 78ef760ddde4..2c09c17cadcd 100644
--- a/arch/mips/include/asm/sn/ioc3.h
+++ b/arch/mips/include/asm/sn/ioc3.h
@@ -21,50 +21,50 @@ struct ioc3_serialregs {
 
 /* SUPERIO uart register map */
 struct ioc3_uartregs {
+	u8	iu_lcr;
 	union {
-		u8	iu_rbr;	/* read only, DLAB == 0 */
-		u8	iu_thr;	/* write only, DLAB == 0 */
-		u8	iu_dll;	/* DLAB == 1 */
+		u8	iu_iir;	/* read only */
+		u8	iu_fcr;	/* write only */
 	};
 	union {
 		u8	iu_ier;	/* DLAB == 0 */
 		u8	iu_dlm;	/* DLAB == 1 */
 	};
 	union {
-		u8	iu_iir;	/* read only */
-		u8	iu_fcr;	/* write only */
+		u8	iu_rbr;	/* read only, DLAB == 0 */
+		u8	iu_thr;	/* write only, DLAB == 0 */
+		u8	iu_dll;	/* DLAB == 1 */
 	};
-	u8	iu_lcr;
-	u8	iu_mcr;
-	u8	iu_lsr;
-	u8	iu_msr;
 	u8	iu_scr;
+	u8	iu_msr;
+	u8	iu_lsr;
+	u8	iu_mcr;
 };
 
 struct ioc3_sioregs {
 	u8	fill[0x141];	/* starts at 0x141 */
 
-	u8	uartc;
 	u8	kbdcg;
+	u8	uartc;
 
-	u8	fill0[0x150 - 0x142 - 1];
+	u8	fill0[0x151 - 0x142 - 1];
 
-	u8	pp_data;
-	u8	pp_dsr;
 	u8	pp_dcr;
+	u8	pp_dsr;
+	u8	pp_data;
 
-	u8	fill1[0x158 - 0x152 - 1];
+	u8	fill1[0x159 - 0x153 - 1];
 
-	u8	pp_fifa;
-	u8	pp_cfgb;
 	u8	pp_ecr;
+	u8	pp_cfgb;
+	u8	pp_fifa;
 
-	u8	fill2[0x168 - 0x15a - 1];
+	u8	fill2[0x16a - 0x15b - 1];
 
-	u8	rtcad;
 	u8	rtcdat;
+	u8	rtcad;
 
-	u8	fill3[0x170 - 0x169 - 1];
+	u8	fill3[0x170 - 0x16b - 1];
 
 	struct ioc3_uartregs	uartb;	/* 0x20170  */
 	struct ioc3_uartregs	uarta;	/* 0x20178  */
@@ -598,5 +598,9 @@ struct ioc3_etxd {
 #define	IOC3_SUBSYS_IP30_SYSBOARD	0xc304
 #define	IOC3_SUBSYS_MENET		0xc305
 #define	IOC3_SUBSYS_MENET4		0xc306
+#define	IOC3_SUBSYS_IO7			0xc307
+#define	IOC3_SUBSYS_IO8			0xc308
+#define	IOC3_SUBSYS_IO9			0xc309
+#define	IOC3_SUBSYS_IP34_SYSBOARD	0xc30A
 
 #endif /* MIPS_SN_IOC3_H */
diff --git a/arch/mips/include/asm/sn/klconfig.h b/arch/mips/include/asm/sn/klconfig.h
index 467c313d5767..117f85e4bef5 100644
--- a/arch/mips/include/asm/sn/klconfig.h
+++ b/arch/mips/include/asm/sn/klconfig.h
@@ -889,10 +889,6 @@ typedef union {
 extern lboard_t *find_lboard(lboard_t *start, unsigned char type);
 extern klinfo_t *find_component(lboard_t *brd, klinfo_t *kli, unsigned char type);
 extern klinfo_t *find_first_component(lboard_t *brd, unsigned char type);
-extern klcpu_t *nasid_slice_to_cpuinfo(nasid_t, int);
 extern lboard_t *find_lboard_class(lboard_t *start, unsigned char brd_class);
 
-
-extern klcpu_t *sn_get_cpuinfo(cpuid_t cpu);
-
 #endif /* _ASM_SN_KLCONFIG_H */
diff --git a/arch/mips/include/asm/sn/kldir.h b/arch/mips/include/asm/sn/kldir.h
index bfb3aec94539..245f59bf3845 100644
--- a/arch/mips/include/asm/sn/kldir.h
+++ b/arch/mips/include/asm/sn/kldir.h
@@ -1,201 +1,16 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Derived from IRIX <sys/SN/kldir.h>, revision 1.21.
- *
- * Copyright (C) 1992 - 1997, 1999, 2000 Silicon Graphics, Inc.
- * Copyright (C) 1999, 2000 by Ralf Baechle
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+
 #ifndef _ASM_SN_KLDIR_H
 #define _ASM_SN_KLDIR_H
 
-
-/*
- * The kldir memory area resides at a fixed place in each node's memory and
- * provides pointers to most other IP27 memory areas.  This allows us to
- * resize and/or relocate memory areas at a later time without breaking all
- * firmware and kernels that use them.	Indices in the array are
- * permanently dedicated to areas listed below.	 Some memory areas (marked
- * below) reside at a permanently fixed location, but are included in the
- * directory for completeness.
- */
-
 #define KLDIR_MAGIC		0x434d5f53505f5357
 
-/*
- * The upper portion of the memory map applies during boot
- * only and is overwritten by IRIX/SYMMON.
- *
- *				      MEMORY MAP PER NODE
- *
- * 0x2000000 (32M)	   +-----------------------------------------+
- *			   |	  IO6 BUFFERS FOR FLASH ENET IOC3    |
- * 0x1F80000 (31.5M)	   +-----------------------------------------+
- *			   |	  IO6 TEXT/DATA/BSS/stack	     |
- * 0x1C00000 (30M)	   +-----------------------------------------+
- *			   |	  IO6 PROM DEBUG TEXT/DATA/BSS/stack |
- * 0x0800000 (28M)	   +-----------------------------------------+
- *			   |	  IP27 PROM TEXT/DATA/BSS/stack	     |
- * 0x1B00000 (27M)	   +-----------------------------------------+
- *			   |	  IP27 CFG			     |
- * 0x1A00000 (26M)	   +-----------------------------------------+
- *			   |	  Graphics PROM			     |
- * 0x1800000 (24M)	   +-----------------------------------------+
- *			   |	  3rd Party PROM drivers	     |
- * 0x1600000 (22M)	   +-----------------------------------------+
- *			   |					     |
- *			   |	  Free				     |
- *			   |					     |
- *			   +-----------------------------------------+
- *			   |	  UNIX DEBUG Version		     |
- * 0x190000 (2M--)	   +-----------------------------------------+
- *			   |	  SYMMON			     |
- *			   |	  (For UNIX Debug only)		     |
- * 0x34000 (208K)	   +-----------------------------------------+
- *			   |	  SYMMON STACK [NUM_CPU_PER_NODE]    |
- *			   |	  (For UNIX Debug only)		     |
- * 0x25000 (148K)	   +-----------------------------------------+
- *			   |	  KLCONFIG - II (temp)		     |
- *			   |					     |
- *			   |	----------------------------	     |
- *			   |					     |
- *			   |	  UNIX NON-DEBUG Version	     |
- * 0x19000 (100K)	   +-----------------------------------------+
- *
- *
- * The lower portion of the memory map contains information that is
- * permanent and is used by the IP27PROM, IO6PROM and IRIX.
- *
- * 0x19000 (100K)	   +-----------------------------------------+
- *			   |					     |
- *			   |	  PI Error Spools (32K)		     |
- *			   |					     |
- * 0x12000 (72K)	   +-----------------------------------------+
- *			   |	  Unused			     |
- * 0x11c00 (71K)	   +-----------------------------------------+
- *			   |	  CPU 1 NMI Eframe area		     |
- * 0x11a00 (70.5K)	   +-----------------------------------------+
- *			   |	  CPU 0 NMI Eframe area		     |
- * 0x11800 (70K)	   +-----------------------------------------+
- *			   |	  CPU 1 NMI Register save area	     |
- * 0x11600 (69.5K)	   +-----------------------------------------+
- *			   |	  CPU 0 NMI Register save area	     |
- * 0x11400 (69K)	   +-----------------------------------------+
- *			   |	  GDA (1k)			     |
- * 0x11000 (68K)	   +-----------------------------------------+
- *			   |	  Early cache Exception stack	     |
- *			   |		 and/or			     |
- *			   |	  kernel/io6prom nmi registers	     |
- * 0x10800  (66k)	   +-----------------------------------------+
- *			   |	  cache error eframe		     |
- * 0x10400 (65K)	   +-----------------------------------------+
- *			   |	  Exception Handlers (UALIAS copy)   |
- * 0x10000 (64K)	   +-----------------------------------------+
- *			   |					     |
- *			   |					     |
- *			   |	  KLCONFIG - I (permanent) (48K)     |
- *			   |					     |
- *			   |					     |
- *			   |					     |
- * 0x4000 (16K)		   +-----------------------------------------+
- *			   |	  NMI Handler (Protected Page)	     |
- * 0x3000 (12K)		   +-----------------------------------------+
- *			   |	  ARCS PVECTORS (master node only)   |
- * 0x2c00 (11K)		   +-----------------------------------------+
- *			   |	  ARCS TVECTORS (master node only)   |
- * 0x2800 (10K)		   +-----------------------------------------+
- *			   |	  LAUNCH [NUM_CPU]		     |
- * 0x2400 (9K)		   +-----------------------------------------+
- *			   |	  Low memory directory (KLDIR)	     |
- * 0x2000 (8K)		   +-----------------------------------------+
- *			   |	  ARCS SPB (1K)			     |
- * 0x1000 (4K)		   +-----------------------------------------+
- *			   |	  Early cache Exception stack	     |
- *			   |		 and/or			     |
- *			   |	  kernel/io6prom nmi registers	     |
- * 0x800  (2k)		   +-----------------------------------------+
- *			   |	  cache error eframe		     |
- * 0x400 (1K)		   +-----------------------------------------+
- *			   |	  Exception Handlers		     |
- * 0x0	 (0K)		   +-----------------------------------------+
- */
-
-#ifdef __ASSEMBLY__
 #define KLDIR_OFF_MAGIC			0x00
 #define KLDIR_OFF_OFFSET		0x08
 #define KLDIR_OFF_POINTER		0x10
 #define KLDIR_OFF_SIZE			0x18
 #define KLDIR_OFF_COUNT			0x20
 #define KLDIR_OFF_STRIDE		0x28
-#endif /* __ASSEMBLY__ */
-
-/*
- * This is defined here because IP27_SYMMON_STK_SIZE must be at least what
- * we define here.  Since it's set up in the prom.  We can't redefine it later
- * and expect more space to be allocated.  The way to find out the true size
- * of the symmon stacks is to divide SYMMON_STK_SIZE by SYMMON_STK_STRIDE
- * for a particular node.
- */
-#define SYMMON_STACK_SIZE		0x8000
-
-#if defined(PROM)
-
-/*
- * These defines are prom version dependent.  No code other than the IP27
- * prom should attempt to use these values.
- */
-#define IP27_LAUNCH_OFFSET		0x2400
-#define IP27_LAUNCH_SIZE		0x400
-#define IP27_LAUNCH_COUNT		2
-#define IP27_LAUNCH_STRIDE		0x200
-
-#define IP27_KLCONFIG_OFFSET		0x4000
-#define IP27_KLCONFIG_SIZE		0xc000
-#define IP27_KLCONFIG_COUNT		1
-#define IP27_KLCONFIG_STRIDE		0
-
-#define IP27_NMI_OFFSET			0x3000
-#define IP27_NMI_SIZE			0x40
-#define IP27_NMI_COUNT			2
-#define IP27_NMI_STRIDE			0x40
-
-#define IP27_PI_ERROR_OFFSET		0x12000
-#define IP27_PI_ERROR_SIZE		0x4000
-#define IP27_PI_ERROR_COUNT		1
-#define IP27_PI_ERROR_STRIDE		0
-
-#define IP27_SYMMON_STK_OFFSET		0x25000
-#define IP27_SYMMON_STK_SIZE		0xe000
-#define IP27_SYMMON_STK_COUNT		2
-/* IP27_SYMMON_STK_STRIDE must be >= SYMMON_STACK_SIZE */
-#define IP27_SYMMON_STK_STRIDE		0x7000
-
-#define IP27_FREEMEM_OFFSET		0x19000
-#define IP27_FREEMEM_SIZE		-1
-#define IP27_FREEMEM_COUNT		1
-#define IP27_FREEMEM_STRIDE		0
-
-#endif /* PROM */
-/*
- * There will be only one of these in a partition so the IO6 must set it up.
- */
-#define IO6_GDA_OFFSET			0x11000
-#define IO6_GDA_SIZE			0x400
-#define IO6_GDA_COUNT			1
-#define IO6_GDA_STRIDE			0
-
-/*
- * save area of kernel nmi regs in the prom format
- */
-#define IP27_NMI_KREGS_OFFSET		0x11400
-#define IP27_NMI_KREGS_CPU_SIZE		0x200
-/*
- * save area of kernel nmi regs in eframe format
- */
-#define IP27_NMI_EFRAME_OFFSET		0x11800
-#define IP27_NMI_EFRAME_SIZE		0x200
 
 #define KLDIR_ENT_SIZE			0x40
 #define KLDIR_MAX_ENTRIES		(0x400 / 0x40)
@@ -214,4 +29,8 @@ typedef struct kldir_ent_s {
 } kldir_ent_t;
 #endif /* !__ASSEMBLY__ */
 
+#ifdef CONFIG_SGI_IP27
+#include <asm/sn/sn0/kldir.h>
+#endif
+
 #endif /* _ASM_SN_KLDIR_H */
diff --git a/arch/mips/include/asm/sn/sn0/hub.h b/arch/mips/include/asm/sn/sn0/hub.h
index d78dd76d5dcf..c84adde36d41 100644
--- a/arch/mips/include/asm/sn/sn0/hub.h
+++ b/arch/mips/include/asm/sn/sn0/hub.h
@@ -37,4 +37,26 @@
 #define UATTR_MSPEC	2
 #define UATTR_UNCAC	3
 
+#ifdef __ASSEMBLY__
+/*
+ * Returns the local nasid into res.
+ */
+	.macro GET_NASID_ASM res
+	dli	\res, LOCAL_HUB_ADDR(NI_STATUS_REV_ID)
+	ld	\res, (\res)
+	and	\res, NSRI_NODEID_MASK
+	dsrl	\res, NSRI_NODEID_SHFT
+	.endm
+#else
+
+/*
+ * get_nasid() returns the physical node id number of the caller.
+ */
+static inline nasid_t get_nasid(void)
+{
+	return (nasid_t)((LOCAL_HUB_L(NI_STATUS_REV_ID) & NSRI_NODEID_MASK)
+			 >> NSRI_NODEID_SHFT);
+}
+#endif
+
 #endif /* _ASM_SN_SN0_HUB_H */
diff --git a/arch/mips/include/asm/sn/sn0/hubni.h b/arch/mips/include/asm/sn/sn0/hubni.h
index b73c4bee65f2..b8253142cb83 100644
--- a/arch/mips/include/asm/sn/sn0/hubni.h
+++ b/arch/mips/include/asm/sn/sn0/hubni.h
@@ -250,6 +250,14 @@ typedef union	hubni_port_error_u {
 #define NI_LLP_CB_MAX		0xff
 #define NI_LLP_SN_MAX		0xff
 
+static inline int get_region_shift(void)
+{
+	if (LOCAL_HUB_L(NI_STATUS_REV_ID) & NSRI_REGIONSIZE_MASK)
+		return NASID_TO_FINEREG_SHFT;
+
+	return NASID_TO_COARSEREG_SHFT;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_SGI_SN0_HUBNI_H */
diff --git a/arch/mips/include/asm/sn/sn0/ip27.h b/arch/mips/include/asm/sn/sn0/ip27.h
deleted file mode 100644
index 3b5efeefcc3f..000000000000
--- a/arch/mips/include/asm/sn/sn0/ip27.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Derived from IRIX <sys/SN/SN0/IP27.h>.
- *
- * Copyright (C) 1992 - 1997, 1999 Silicon Graphics, Inc.
- * Copyright (C) 1999, 2006 by Ralf Baechle
- */
-#ifndef _ASM_SN_SN0_IP27_H
-#define _ASM_SN_SN0_IP27_H
-
-#include <asm/mipsregs.h>
-
-/*
- * Simple definitions for the masks which remove SW bits from pte.
- */
-
-#define TLBLO_HWBITSHIFT	0		/* Shift value, for masking */
-
-#ifndef __ASSEMBLY__
-
-#define CAUSE_BERRINTR		IE_IRQ5
-
-#define ECCF_CACHE_ERR	0
-#define ECCF_TAGLO	1
-#define ECCF_ECC	2
-#define ECCF_ERROREPC	3
-#define ECCF_PADDR	4
-#define ECCF_SIZE	(5 * sizeof(long))
-
-#endif /* !__ASSEMBLY__ */
-
-#ifdef __ASSEMBLY__
-
-/*
- * KL_GET_CPUNUM (similar to EV_GET_SPNUM for EVEREST platform) reads
- * the processor number of the calling processor.  The proc parameters
- * must be a register.
- */
-#define KL_GET_CPUNUM(proc)				\
-	dli	proc, LOCAL_HUB(0);			\
-	ld	proc, PI_CPU_NUM(proc)
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * R10000 status register interrupt bit mask usage for IP27.
- */
-#define SRB_SWTIMO	IE_SW0		/* 0x0100 */
-#define SRB_NET		IE_SW1		/* 0x0200 */
-#define SRB_DEV0	IE_IRQ0		/* 0x0400 */
-#define SRB_DEV1	IE_IRQ1		/* 0x0800 */
-#define SRB_TIMOCLK	IE_IRQ2		/* 0x1000 */
-#define SRB_PROFCLK	IE_IRQ3		/* 0x2000 */
-#define SRB_ERR		IE_IRQ4		/* 0x4000 */
-#define SRB_SCHEDCLK	IE_IRQ5		/* 0x8000 */
-
-#define SR_IBIT_HI	SRB_DEV0
-#define SR_IBIT_PROF	SRB_PROFCLK
-
-#define SRB_SWTIMO_IDX		0
-#define SRB_NET_IDX		1
-#define SRB_DEV0_IDX		2
-#define SRB_DEV1_IDX		3
-#define SRB_TIMOCLK_IDX		4
-#define SRB_PROFCLK_IDX		5
-#define SRB_ERR_IDX		6
-#define SRB_SCHEDCLK_IDX	7
-
-#define NUM_CAUSE_INTRS		8
-
-#define SCACHE_LINESIZE 128
-#define SCACHE_LINEMASK (SCACHE_LINESIZE - 1)
-
-#include <asm/sn/addrs.h>
-
-#define LED_CYCLE_MASK	0x0f
-#define LED_CYCLE_SHFT	4
-
-#define SEND_NMI(_nasid, _slice)	\
-	  REMOTE_HUB_S((_nasid),  (PI_NMI_A + ((_slice) * PI_NMI_OFFSET)), 1)
-
-#endif /* _ASM_SN_SN0_IP27_H */
diff --git a/arch/mips/include/asm/sn/sn0/kldir.h b/arch/mips/include/asm/sn/sn0/kldir.h
new file mode 100644
index 000000000000..1b10af6cbd5e
--- /dev/null
+++ b/arch/mips/include/asm/sn/sn0/kldir.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Derived from IRIX <sys/SN/kldir.h>, revision 1.21.
+ *
+ * Copyright (C) 1992 - 1997, 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 1999, 2000 by Ralf Baechle
+ */
+#ifndef _ASM_SN_SN0_KLDIR_H
+#define _ASM_SN_SN0_KLDIR_H
+
+
+/*
+ * The kldir memory area resides at a fixed place in each node's memory and
+ * provides pointers to most other IP27 memory areas.  This allows us to
+ * resize and/or relocate memory areas at a later time without breaking all
+ * firmware and kernels that use them.	Indices in the array are
+ * permanently dedicated to areas listed below.	 Some memory areas (marked
+ * below) reside at a permanently fixed location, but are included in the
+ * directory for completeness.
+ */
+
+/*
+ * The upper portion of the memory map applies during boot
+ * only and is overwritten by IRIX/SYMMON.
+ *
+ *				      MEMORY MAP PER NODE
+ *
+ * 0x2000000 (32M)	   +-----------------------------------------+
+ *			   |	  IO6 BUFFERS FOR FLASH ENET IOC3    |
+ * 0x1F80000 (31.5M)	   +-----------------------------------------+
+ *			   |	  IO6 TEXT/DATA/BSS/stack	     |
+ * 0x1C00000 (30M)	   +-----------------------------------------+
+ *			   |	  IO6 PROM DEBUG TEXT/DATA/BSS/stack |
+ * 0x0800000 (28M)	   +-----------------------------------------+
+ *			   |	  IP27 PROM TEXT/DATA/BSS/stack	     |
+ * 0x1B00000 (27M)	   +-----------------------------------------+
+ *			   |	  IP27 CFG			     |
+ * 0x1A00000 (26M)	   +-----------------------------------------+
+ *			   |	  Graphics PROM			     |
+ * 0x1800000 (24M)	   +-----------------------------------------+
+ *			   |	  3rd Party PROM drivers	     |
+ * 0x1600000 (22M)	   +-----------------------------------------+
+ *			   |					     |
+ *			   |	  Free				     |
+ *			   |					     |
+ *			   +-----------------------------------------+
+ *			   |	  UNIX DEBUG Version		     |
+ * 0x190000 (2M--)	   +-----------------------------------------+
+ *			   |	  SYMMON			     |
+ *			   |	  (For UNIX Debug only)		     |
+ * 0x34000 (208K)	   +-----------------------------------------+
+ *			   |	  SYMMON STACK [NUM_CPU_PER_NODE]    |
+ *			   |	  (For UNIX Debug only)		     |
+ * 0x25000 (148K)	   +-----------------------------------------+
+ *			   |	  KLCONFIG - II (temp)		     |
+ *			   |					     |
+ *			   |	----------------------------	     |
+ *			   |					     |
+ *			   |	  UNIX NON-DEBUG Version	     |
+ * 0x19000 (100K)	   +-----------------------------------------+
+ *
+ *
+ * The lower portion of the memory map contains information that is
+ * permanent and is used by the IP27PROM, IO6PROM and IRIX.
+ *
+ * 0x19000 (100K)	   +-----------------------------------------+
+ *			   |					     |
+ *			   |	  PI Error Spools (32K)		     |
+ *			   |					     |
+ * 0x12000 (72K)	   +-----------------------------------------+
+ *			   |	  Unused			     |
+ * 0x11c00 (71K)	   +-----------------------------------------+
+ *			   |	  CPU 1 NMI Eframe area		     |
+ * 0x11a00 (70.5K)	   +-----------------------------------------+
+ *			   |	  CPU 0 NMI Eframe area		     |
+ * 0x11800 (70K)	   +-----------------------------------------+
+ *			   |	  CPU 1 NMI Register save area	     |
+ * 0x11600 (69.5K)	   +-----------------------------------------+
+ *			   |	  CPU 0 NMI Register save area	     |
+ * 0x11400 (69K)	   +-----------------------------------------+
+ *			   |	  GDA (1k)			     |
+ * 0x11000 (68K)	   +-----------------------------------------+
+ *			   |	  Early cache Exception stack	     |
+ *			   |		 and/or			     |
+ *			   |	  kernel/io6prom nmi registers	     |
+ * 0x10800  (66k)	   +-----------------------------------------+
+ *			   |	  cache error eframe		     |
+ * 0x10400 (65K)	   +-----------------------------------------+
+ *			   |	  Exception Handlers (UALIAS copy)   |
+ * 0x10000 (64K)	   +-----------------------------------------+
+ *			   |					     |
+ *			   |					     |
+ *			   |	  KLCONFIG - I (permanent) (48K)     |
+ *			   |					     |
+ *			   |					     |
+ *			   |					     |
+ * 0x4000 (16K)		   +-----------------------------------------+
+ *			   |	  NMI Handler (Protected Page)	     |
+ * 0x3000 (12K)		   +-----------------------------------------+
+ *			   |	  ARCS PVECTORS (master node only)   |
+ * 0x2c00 (11K)		   +-----------------------------------------+
+ *			   |	  ARCS TVECTORS (master node only)   |
+ * 0x2800 (10K)		   +-----------------------------------------+
+ *			   |	  LAUNCH [NUM_CPU]		     |
+ * 0x2400 (9K)		   +-----------------------------------------+
+ *			   |	  Low memory directory (KLDIR)	     |
+ * 0x2000 (8K)		   +-----------------------------------------+
+ *			   |	  ARCS SPB (1K)			     |
+ * 0x1000 (4K)		   +-----------------------------------------+
+ *			   |	  Early cache Exception stack	     |
+ *			   |		 and/or			     |
+ *			   |	  kernel/io6prom nmi registers	     |
+ * 0x800  (2k)		   +-----------------------------------------+
+ *			   |	  cache error eframe		     |
+ * 0x400 (1K)		   +-----------------------------------------+
+ *			   |	  Exception Handlers		     |
+ * 0x0	 (0K)		   +-----------------------------------------+
+ */
+
+/*
+ * This is defined here because IP27_SYMMON_STK_SIZE must be at least what
+ * we define here.  Since it's set up in the prom.  We can't redefine it later
+ * and expect more space to be allocated.  The way to find out the true size
+ * of the symmon stacks is to divide SYMMON_STK_SIZE by SYMMON_STK_STRIDE
+ * for a particular node.
+ */
+#define SYMMON_STACK_SIZE		0x8000
+
+#if defined(PROM)
+
+/*
+ * These defines are prom version dependent.  No code other than the IP27
+ * prom should attempt to use these values.
+ */
+#define IP27_LAUNCH_OFFSET		0x2400
+#define IP27_LAUNCH_SIZE		0x400
+#define IP27_LAUNCH_COUNT		2
+#define IP27_LAUNCH_STRIDE		0x200
+
+#define IP27_KLCONFIG_OFFSET		0x4000
+#define IP27_KLCONFIG_SIZE		0xc000
+#define IP27_KLCONFIG_COUNT		1
+#define IP27_KLCONFIG_STRIDE		0
+
+#define IP27_NMI_OFFSET			0x3000
+#define IP27_NMI_SIZE			0x40
+#define IP27_NMI_COUNT			2
+#define IP27_NMI_STRIDE			0x40
+
+#define IP27_PI_ERROR_OFFSET		0x12000
+#define IP27_PI_ERROR_SIZE		0x4000
+#define IP27_PI_ERROR_COUNT		1
+#define IP27_PI_ERROR_STRIDE		0
+
+#define IP27_SYMMON_STK_OFFSET		0x25000
+#define IP27_SYMMON_STK_SIZE		0xe000
+#define IP27_SYMMON_STK_COUNT		2
+/* IP27_SYMMON_STK_STRIDE must be >= SYMMON_STACK_SIZE */
+#define IP27_SYMMON_STK_STRIDE		0x7000
+
+#define IP27_FREEMEM_OFFSET		0x19000
+#define IP27_FREEMEM_SIZE		-1
+#define IP27_FREEMEM_COUNT		1
+#define IP27_FREEMEM_STRIDE		0
+
+#endif /* PROM */
+/*
+ * There will be only one of these in a partition so the IO6 must set it up.
+ */
+#define IO6_GDA_OFFSET			0x11000
+#define IO6_GDA_SIZE			0x400
+#define IO6_GDA_COUNT			1
+#define IO6_GDA_STRIDE			0
+
+/*
+ * save area of kernel nmi regs in the prom format
+ */
+#define IP27_NMI_KREGS_OFFSET		0x11400
+#define IP27_NMI_KREGS_CPU_SIZE		0x200
+/*
+ * save area of kernel nmi regs in eframe format
+ */
+#define IP27_NMI_EFRAME_OFFSET		0x11800
+#define IP27_NMI_EFRAME_SIZE		0x200
+
+#endif /* _ASM_SN_SN0_KLDIR_H */
diff --git a/arch/mips/include/asm/sn/sn_private.h b/arch/mips/include/asm/sn/sn_private.h
deleted file mode 100644
index 63a2c30d81c6..000000000000
--- a/arch/mips/include/asm/sn/sn_private.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_SN_SN_PRIVATE_H
-#define __ASM_SN_SN_PRIVATE_H
-
-#include <asm/sn/types.h>
-
-extern nasid_t master_nasid;
-
-extern void cpu_node_probe(void);
-extern void hub_rtc_init(nasid_t nasid);
-extern void cpu_time_init(void);
-extern void per_cpu_init(void);
-extern void install_cpu_nmi_handler(int slice);
-extern void install_ipi(void);
-extern void setup_replication_mask(void);
-extern void replicate_kernel_text(void);
-extern unsigned long node_getfirstfree(nasid_t nasid);
-
-#endif /* __ASM_SN_SN_PRIVATE_H */
diff --git a/arch/mips/include/asm/sn/types.h b/arch/mips/include/asm/sn/types.h
index 203c927e84d1..451ba1ee41ad 100644
--- a/arch/mips/include/asm/sn/types.h
+++ b/arch/mips/include/asm/sn/types.h
@@ -11,6 +11,8 @@
 
 #include <linux/types.h>
 
+#ifndef __ASSEMBLY__
+
 typedef unsigned long	cpuid_t;
 typedef signed short	nasid_t;	/* node id in numa-as-id space */
 typedef signed char	partid_t;	/* partition ID type */
@@ -18,4 +20,6 @@ typedef signed short	moduleid_t;	/* user-visible module number type */
 
 typedef dev_t		vertex_hdl_t;	/* hardware graph vertex handle */
 
+#endif
+
 #endif /* _ASM_SN_TYPES_H */
diff --git a/arch/mips/jz4740/Kconfig b/arch/mips/jz4740/Kconfig
index 4dd0c446ecec..412d2faa3cdf 100644
--- a/arch/mips/jz4740/Kconfig
+++ b/arch/mips/jz4740/Kconfig
@@ -16,6 +16,10 @@ config JZ4780_CI20
 	bool "MIPS Creator CI20"
 	select MACH_JZ4780
 
+config X1000_CU1000_NEO
+	bool "YSH & ATIL CU1000 Module with Neo backplane"
+	select MACH_X1000
+
 endchoice
 
 config MACH_JZ4740
@@ -33,3 +37,9 @@ config MACH_JZ4780
 	select MIPS_CPU_SCACHE
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_SUPPORTS_HIGHMEM
+
+config MACH_X1000
+	bool
+	select MIPS_CPU_SCACHE
+	select SYS_HAS_CPU_MIPS32_R2
+	select SYS_SUPPORTS_HIGHMEM
diff --git a/arch/mips/jz4740/setup.c b/arch/mips/jz4740/setup.c
index dc8ee21e0948..880c26857aff 100644
--- a/arch/mips/jz4740/setup.c
+++ b/arch/mips/jz4740/setup.c
@@ -44,6 +44,8 @@ static void __init jz4740_detect_mem(void)
 
 static unsigned long __init get_board_mach_type(const void *fdt)
 {
+	if (!fdt_node_check_compatible(fdt, 0, "ingenic,x1830"))
+		return MACH_INGENIC_X1830;
 	if (!fdt_node_check_compatible(fdt, 0, "ingenic,x1000"))
 		return MACH_INGENIC_X1000;
 	if (!fdt_node_check_compatible(fdt, 0, "ingenic,jz4780"))
@@ -86,6 +88,8 @@ void __init device_tree_init(void)
 const char *get_system_type(void)
 {
 	switch (mips_machtype) {
+	case MACH_INGENIC_X1830:
+		return "X1830";
 	case MACH_INGENIC_X1000:
 		return "X1000";
 	case MACH_INGENIC_JZ4780:
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index c54332697673..6ab6b03d35ba 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -102,7 +102,12 @@ static void cpu_set_fpu_2008(struct cpuinfo_mips *c)
 		if (fir & MIPS_FPIR_HAS2008) {
 			fcsr = read_32bit_cp1_register(CP1_STATUS);
 
-			fcsr0 = fcsr & ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008);
+			/*
+			 * MAC2008 toolchain never landed in real world, so we're only
+			 * testing wether it can be disabled and don't try to enabled
+			 * it.
+			 */
+			fcsr0 = fcsr & ~(FPU_CSR_ABS2008 | FPU_CSR_NAN2008 | FPU_CSR_MAC2008);
 			write_32bit_cp1_register(CP1_STATUS, fcsr0);
 			fcsr0 = read_32bit_cp1_register(CP1_STATUS);
 
@@ -112,6 +117,15 @@ static void cpu_set_fpu_2008(struct cpuinfo_mips *c)
 
 			write_32bit_cp1_register(CP1_STATUS, fcsr);
 
+			if (c->isa_level & (MIPS_CPU_ISA_M32R2 | MIPS_CPU_ISA_M64R2)) {
+				/*
+				 * The bit for MAC2008 might be reused by R6 in future,
+				 * so we only test for R2-R5.
+				 */
+				if (fcsr0 & FPU_CSR_MAC2008)
+					c->options |= MIPS_CPU_MAC_2008_ONLY;
+			}
+
 			if (!(fcsr0 & FPU_CSR_NAN2008))
 				c->options |= MIPS_CPU_NAN_LEGACY;
 			if (fcsr1 & FPU_CSR_NAN2008)
@@ -1960,10 +1974,8 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 	BUG_ON(!__builtin_constant_p(cpu_has_counter) || cpu_has_counter);
 
 	switch (c->processor_id & PRID_IMP_MASK) {
-	case PRID_IMP_XBURST:
-		c->cputype = CPU_XBURST;
-		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
-		__cpu_name[cpu] = "Ingenic JZRISC";
+	case PRID_IMP_XBURST_REV1:
+
 		/*
 		 * The XBurst core by default attempts to avoid branch target
 		 * buffer lookups by detecting & special casing loops. This
@@ -1971,34 +1983,43 @@ static inline void cpu_probe_ingenic(struct cpuinfo_mips *c, unsigned int cpu)
 		 * Set cp0 config7 bit 4 to disable this feature.
 		 */
 		set_c0_config7(MIPS_CONF7_BTB_LOOP_EN);
-		break;
-	default:
-		panic("Unknown Ingenic Processor ID!");
-		break;
-	}
 
-	switch (c->processor_id & PRID_COMP_MASK) {
-	/*
-	 * The config0 register in the XBurst CPUs with a processor ID of
-	 * PRID_COMP_INGENIC_D1 has an abandoned huge page tlb mode, this
-	 * mode is not compatible with the MIPS standard, it will cause
-	 * tlbmiss and into an infinite loop (line 21 in the tlb-funcs.S)
-	 * when starting the init process. After chip reset, the default
-	 * is HPTLB mode, Write 0xa9000000 to cp0 register 5 sel 4 to
-	 * switch back to VTLB mode to prevent getting stuck.
-	 */
-	case PRID_COMP_INGENIC_D1:
-		write_c0_page_ctrl(XBURST_PAGECTRL_HPTLB_DIS);
-		break;
-	/*
-	 * The config0 register in the XBurst CPUs with a processor ID of
-	 * PRID_COMP_INGENIC_D0 report themselves as MIPS32r2 compatible,
-	 * but they don't actually support this ISA.
-	 */
-	case PRID_COMP_INGENIC_D0:
-		c->isa_level &= ~MIPS_CPU_ISA_M32R2;
+		switch (c->processor_id & PRID_COMP_MASK) {
+
+		/*
+		 * The config0 register in the XBurst CPUs with a processor ID of
+		 * PRID_COMP_INGENIC_D0 report themselves as MIPS32r2 compatible,
+		 * but they don't actually support this ISA.
+		 */
+		case PRID_COMP_INGENIC_D0:
+			c->isa_level &= ~MIPS_CPU_ISA_M32R2;
+			break;
+
+		/*
+		 * The config0 register in the XBurst CPUs with a processor ID of
+		 * PRID_COMP_INGENIC_D1 has an abandoned huge page tlb mode, this
+		 * mode is not compatible with the MIPS standard, it will cause
+		 * tlbmiss and into an infinite loop (line 21 in the tlb-funcs.S)
+		 * when starting the init process. After chip reset, the default
+		 * is HPTLB mode, Write 0xa9000000 to cp0 register 5 sel 4 to
+		 * switch back to VTLB mode to prevent getting stuck.
+		 */
+		case PRID_COMP_INGENIC_D1:
+			write_c0_page_ctrl(XBURST_PAGECTRL_HPTLB_DIS);
+			break;
+
+		default:
+			break;
+		}
+	/* fall-through */
+	case PRID_IMP_XBURST_REV2:
+		c->cputype = CPU_XBURST;
+		c->writecombine = _CACHE_UNCACHED_ACCELERATED;
+		__cpu_name[cpu] = "Ingenic XBurst";
 		break;
+
 	default:
+		panic("Unknown Ingenic Processor ID!");
 		break;
 	}
 }
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index a28057946ed1..1ac2752fb791 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -515,8 +515,7 @@ static void __init request_crashkernel(struct resource *res)
 	ret = request_resource(res, &crashk_res);
 	if (!ret)
 		pr_info("Reserving %ldMB of memory at %ldMB for crashkernel\n",
-			(unsigned long)((crashk_res.end -
-					 crashk_res.start + 1) >> 20),
+			(unsigned long)(resource_size(&crashk_res) >> 20),
 			(unsigned long)(crashk_res.start  >> 20));
 }
 #else /* !defined(CONFIG_KEXEC)		*/
@@ -698,8 +697,7 @@ static void __init arch_mem_init(char **cmdline_p)
 	mips_parse_crashkernel();
 #ifdef CONFIG_KEXEC
 	if (crashk_res.start != crashk_res.end)
-		memblock_reserve(crashk_res.start,
-				 crashk_res.end - crashk_res.start + 1);
+		memblock_reserve(crashk_res.start, resource_size(&crashk_res));
 #endif
 	device_tree_init();
 	sparse_init();
diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c
index f2973ce87f53..abdd7aaa3311 100644
--- a/arch/mips/kernel/sync-r4k.c
+++ b/arch/mips/kernel/sync-r4k.c
@@ -90,6 +90,9 @@ void synchronise_count_master(int cpu)
 void synchronise_count_slave(int cpu)
 {
 	int i;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	/*
 	 * Not every cpu is online at the time this gets called,
@@ -113,5 +116,7 @@ void synchronise_count_slave(int cpu)
 	}
 	/* Arrange for an interrupt in a short while */
 	write_c0_compare(read_c0_count() + COUNTON);
+
+	local_irq_restore(flags);
 }
 #undef NR_LOOPS
diff --git a/arch/mips/kernel/syscalls/Makefile b/arch/mips/kernel/syscalls/Makefile
index a3d4bec695c6..6efb2f6889a7 100644
--- a/arch/mips/kernel/syscalls/Makefile
+++ b/arch/mips/kernel/syscalls/Makefile
@@ -18,7 +18,7 @@ quiet_cmd_syshdr = SYSHDR  $@
 		   '$(syshdr_pfx_$(basetarget))'		\
 		   '$(syshdr_offset_$(basetarget))'
 
-quiet_cmd_sysnr = SYSNR  $@
+quiet_cmd_sysnr = SYSNR   $@
       cmd_sysnr = $(CONFIG_SHELL) '$(sysnr)' '$<' '$@'		\
 		  '$(sysnr_abis_$(basetarget))'			\
 		  '$(sysnr_pfx_$(basetarget))'			\
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 68c9ec06851f..1f9e8ad636cc 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -375,3 +375,4 @@
 434	n32	pidfd_open			sys_pidfd_open
 435	n32	clone3				__sys_clone3
 437	n32	openat2				sys_openat2
+438	n32	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 42a72d010050..c0b9d802dbf6 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -351,3 +351,4 @@
 434	n64	pidfd_open			sys_pidfd_open
 435	n64	clone3				__sys_clone3
 437	n64	openat2				sys_openat2
+438	n64	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index f114c4aed0ed..ac586774c980 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -424,3 +424,4 @@
 434	o32	pidfd_open			sys_pidfd_open
 435	o32	clone3				__sys_clone3
 437	o32	openat2				sys_openat2
+438	o32	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 83f2a437d9e2..31968cbd6464 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -210,11 +210,6 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 			regs.regs[29] = task->thread.reg29;
 			regs.regs[31] = 0;
 			regs.cp0_epc = task->thread.reg31;
-#ifdef CONFIG_KGDB_KDB
-		} else if (atomic_read(&kgdb_active) != -1 &&
-			   kdb_current_regs) {
-			memcpy(&regs, kdb_current_regs, sizeof(regs));
-#endif /* CONFIG_KGDB_KDB */
 		} else {
 			prepare_frametrace(&regs);
 		}
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index 92bd2b0f0548..ca6fc4762d97 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -131,7 +131,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 #define     _LoadW(addr, value, res, type)   \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -152,7 +152,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#else /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 /* For CPUs without lwl instruction */
 #define     _LoadW(addr, value, res, type) \
 do {                                                        \
@@ -187,7 +187,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 
 #define     _LoadHWU(addr, value, res, type) \
 do {                                                        \
@@ -213,7 +213,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 #define     _LoadWU(addr, value, res, type)  \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -256,7 +256,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#else /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 /* For CPUs without lwl and ldl instructions */
 #define	    _LoadWU(addr, value, res, type) \
 do {                                                        \
@@ -340,7 +340,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 
 
 #define     _StoreHW(addr, value, res, type) \
@@ -366,7 +366,7 @@ do {                                                        \
 			: "r" (value), "r" (addr), "i" (-EFAULT));\
 } while(0)
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 #define     _StoreW(addr, value, res, type)  \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -407,7 +407,7 @@ do {                                                        \
 		: "r" (value), "r" (addr), "i" (-EFAULT));  \
 } while(0)
 
-#else /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 #define     _StoreW(addr, value, res, type)  \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -483,7 +483,7 @@ do {                                                        \
 		: "memory");                                \
 } while(0)
 
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 
 #else /* __BIG_ENDIAN */
 
@@ -509,7 +509,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 #define     _LoadW(addr, value, res, type)   \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -530,7 +530,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#else  /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 /* For CPUs without lwl instruction */
 #define     _LoadW(addr, value, res, type) \
 do {                                                        \
@@ -565,7 +565,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 
 
 #define     _LoadHWU(addr, value, res, type) \
@@ -592,7 +592,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 #define     _LoadWU(addr, value, res, type)  \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -635,7 +635,7 @@ do {                                                        \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
 
-#else /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 /* For CPUs without lwl and ldl instructions */
 #define	    _LoadWU(addr, value, res, type) \
 do {                                                        \
@@ -718,7 +718,7 @@ do {                                                        \
 			: "=&r" (value), "=r" (res)	    \
 			: "r" (addr), "i" (-EFAULT));       \
 } while(0)
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 
 #define     _StoreHW(addr, value, res, type) \
 do {                                                        \
@@ -743,7 +743,7 @@ do {                                                        \
 			: "r" (value), "r" (addr), "i" (-EFAULT));\
 } while(0)
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 #define     _StoreW(addr, value, res, type)  \
 do {                                                        \
 		__asm__ __volatile__ (                      \
@@ -784,7 +784,7 @@ do {                                                        \
 		: "r" (value), "r" (addr), "i" (-EFAULT));  \
 } while(0)
 
-#else /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 /* For CPUs without swl and sdl instructions */
 #define     _StoreW(addr, value, res, type)  \
 do {                                                        \
@@ -861,7 +861,7 @@ do {                                                        \
 		: "memory");                                \
 } while(0)
 
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 #endif
 
 #define LoadHWU(addr, value, res)	_LoadHWU(addr, value, res, kernel)
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 1109924560d8..2606f3f02b54 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -156,7 +156,7 @@ void kvm_mips_free_vcpus(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		kvm_arch_vcpu_free(vcpu);
+		kvm_vcpu_destroy(vcpu);
 	}
 
 	mutex_lock(&kvm->lock);
@@ -280,25 +280,27 @@ static inline void dump_handler(const char *symbol, void *start, void *end)
 	pr_debug("\tEND(%s)\n", symbol);
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
+{
+	return 0;
+}
+
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	int err, size;
 	void *gebase, *p, *handler, *refill_start, *refill_end;
 	int i;
 
-	struct kvm_vcpu *vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
-
-	if (!vcpu) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	err = kvm_vcpu_init(vcpu, kvm, id);
+	kvm_debug("kvm @ %p: create cpu %d at %p\n",
+		  vcpu->kvm, vcpu->vcpu_id, vcpu);
 
+	err = kvm_mips_callbacks->vcpu_init(vcpu);
 	if (err)
-		goto out_free_cpu;
+		return err;
 
-	kvm_debug("kvm @ %p: create cpu %d at %p\n", kvm, id, vcpu);
+	hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup;
 
 	/*
 	 * Allocate space for host mode exception handlers that handle
@@ -313,7 +315,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 
 	if (!gebase) {
 		err = -ENOMEM;
-		goto out_uninit_cpu;
+		goto out_uninit_vcpu;
 	}
 	kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n",
 		  ALIGN(size, PAGE_SIZE), gebase);
@@ -392,38 +394,33 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.last_sched_cpu = -1;
 	vcpu->arch.last_exec_cpu = -1;
 
-	return vcpu;
+	/* Initial guest state */
+	err = kvm_mips_callbacks->vcpu_setup(vcpu);
+	if (err)
+		goto out_free_commpage;
+
+	return 0;
 
+out_free_commpage:
+	kfree(vcpu->arch.kseg0_commpage);
 out_free_gebase:
 	kfree(gebase);
-
-out_uninit_cpu:
-	kvm_vcpu_uninit(vcpu);
-
-out_free_cpu:
-	kfree(vcpu);
-
-out:
-	return ERR_PTR(err);
+out_uninit_vcpu:
+	kvm_mips_callbacks->vcpu_uninit(vcpu);
+	return err;
 }
 
-void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	hrtimer_cancel(&vcpu->arch.comparecount_timer);
 
-	kvm_vcpu_uninit(vcpu);
-
 	kvm_mips_dump_stats(vcpu);
 
 	kvm_mmu_free_memory_caches(vcpu);
 	kfree(vcpu->arch.guest_ebase);
 	kfree(vcpu->arch.kseg0_commpage);
-	kfree(vcpu);
-}
 
-void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
-{
-	kvm_arch_vcpu_free(vcpu);
+	kvm_mips_callbacks->vcpu_uninit(vcpu);
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
@@ -1233,37 +1230,12 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer)
 	return kvm_mips_count_timeout(vcpu);
 }
 
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	int err;
-
-	err = kvm_mips_callbacks->vcpu_init(vcpu);
-	if (err)
-		return err;
-
-	hrtimer_init(&vcpu->arch.comparecount_timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_REL);
-	vcpu->arch.comparecount_timer.function = kvm_mips_comparecount_wakeup;
-	return 0;
-}
-
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-	kvm_mips_callbacks->vcpu_uninit(vcpu);
-}
-
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 				  struct kvm_translation *tr)
 {
 	return 0;
 }
 
-/* Initial guest state */
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
-	return kvm_mips_callbacks->vcpu_setup(vcpu);
-}
-
 static void kvm_mips_set_c0_status(void)
 {
 	u32 status = read_c0_status();
diff --git a/arch/mips/lasat/picvue_proc.c b/arch/mips/lasat/picvue_proc.c
index 8126f15b8e09..61c033494af5 100644
--- a/arch/mips/lasat/picvue_proc.c
+++ b/arch/mips/lasat/picvue_proc.c
@@ -89,13 +89,12 @@ static ssize_t pvc_line_proc_write(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations pvc_line_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pvc_line_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= pvc_line_proc_write,
+static const struct proc_ops pvc_line_proc_ops = {
+	.proc_open	= pvc_line_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= pvc_line_proc_write,
 };
 
 static ssize_t pvc_scroll_proc_write(struct file *file, const char __user *buf,
@@ -148,13 +147,12 @@ static int pvc_scroll_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, pvc_scroll_proc_show, NULL);
 }
 
-static const struct file_operations pvc_scroll_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pvc_scroll_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= pvc_scroll_proc_write,
+static const struct proc_ops pvc_scroll_proc_ops = {
+	.proc_open	= pvc_scroll_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= pvc_scroll_proc_write,
 };
 
 void pvc_proc_timerfunc(struct timer_list *unused)
@@ -189,12 +187,11 @@ static int __init pvc_proc_init(void)
 	}
 	for (i = 0; i < PVC_NLINES; i++) {
 		proc_entry = proc_create_data(pvc_linename[i], 0644, dir,
-					&pvc_line_proc_fops, &pvc_linedata[i]);
+					&pvc_line_proc_ops, &pvc_linedata[i]);
 		if (proc_entry == NULL)
 			goto error;
 	}
-	proc_entry = proc_create("scroll", 0644, dir,
-				 &pvc_scroll_proc_fops);
+	proc_entry = proc_create("scroll", 0644, dir, &pvc_scroll_proc_ops);
 	if (proc_entry == NULL)
 		goto error;
 
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index cdd19d8561e8..f7994d936505 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -301,14 +301,14 @@
 	 and	t0, src, ADDRMASK
 	PREFS(	0, 2*32(src) )
 	PREFD(	1, 2*32(dst) )
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 	bnez	t1, .Ldst_unaligned\@
 	 nop
 	bnez	t0, .Lsrc_unaligned_dst_aligned\@
-#else
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 	or	t0, t0, t1
 	bnez	t0, .Lcopy_unaligned_bytes\@
-#endif
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 	/*
 	 * use delay slot for fall-through
 	 * src and dst are aligned; need to compute rem
@@ -389,7 +389,7 @@
 	bne	rem, len, 1b
 	.set	noreorder
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 	/*
 	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
 	 * A loop would do only a byte at a time with possible branch
@@ -491,7 +491,7 @@
 	bne	len, rem, 1b
 	.set	noreorder
 
-#endif /* CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* !CONFIG_CPU_NO_LOAD_STORE_LR */
 .Lcopy_bytes_checklen\@:
 	beqz	len, .Ldone\@
 	 nop
@@ -520,7 +520,7 @@
 	jr	ra
 	 nop
 
-#ifndef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifdef CONFIG_CPU_NO_LOAD_STORE_LR
 .Lcopy_unaligned_bytes\@:
 1:
 	COPY_BYTE(0)
@@ -534,7 +534,7 @@
 	ADD	src, src, 8
 	b	1b
 	 ADD	dst, dst, 8
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 	.if __memcpy == 1
 	END(memcpy)
 	.set __memcpy, 0
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 418611ef13cf..d5449e8a3dfc 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -115,7 +115,7 @@
 #endif
 	.set		reorder
 
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 	R10KCBARRIER(0(ra))
 #ifdef __MIPSEB__
 	EX(LONG_S_L, a1, (a0), .Lfirst_fixup\@)	/* make word/dword aligned */
@@ -125,7 +125,7 @@
 	PTR_SUBU	a0, t0			/* long align ptr */
 	PTR_ADDU	a2, t0			/* correct size */
 
-#else /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 #define STORE_BYTE(N)				\
 	EX(sb, a1, N(a0), .Lbyte_fixup\@);	\
 	.set		noreorder;		\
@@ -150,7 +150,7 @@
 	ori		a0, STORMASK
 	xori		a0, STORMASK
 	PTR_ADDIU	a0, STORSIZE
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 1:	ori		t1, a2, 0x3f		/* # of full blocks */
 	xori		t1, 0x3f
 	andi		t0, a2, 0x40-STORSIZE
@@ -185,7 +185,7 @@
 
 	.set		noreorder
 	beqz		a2, 1f
-#ifdef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifndef CONFIG_CPU_NO_LOAD_STORE_LR
 	 PTR_ADDU	a0, a2			/* What's left */
 	.set		reorder
 	R10KCBARRIER(0(ra))
@@ -194,7 +194,7 @@
 #else
 	EX(LONG_S_L, a1, -1(a0), .Llast_fixup\@)
 #endif
-#else
+#else /* CONFIG_CPU_NO_LOAD_STORE_LR */
 	 PTR_SUBU	t0, $0, a2
 	.set		reorder
 	move		a2, zero		/* No remaining longs */
@@ -211,7 +211,7 @@
 	EX(sb, a1, 6(a0), .Lbyte_fixup\@)
 #endif
 0:
-#endif
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 1:	move		a2, zero
 	jr		ra
 
@@ -234,7 +234,7 @@
 	.hidden __memset
 	.endif
 
-#ifndef CONFIG_CPU_HAS_LOAD_STORE_LR
+#ifdef CONFIG_CPU_NO_LOAD_STORE_LR
 .Lbyte_fixup\@:
 	/*
 	 * unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1
@@ -243,7 +243,7 @@
 	PTR_SUBU	a2, t0
 	PTR_ADDIU	a2, 1
 	jr		ra
-#endif /* !CONFIG_CPU_HAS_LOAD_STORE_LR */
+#endif /* CONFIG_CPU_NO_LOAD_STORE_LR */
 
 .Lfirst_fixup\@:
 	/* unset_bytes already in a2 */
diff --git a/arch/mips/lib/mips-atomic.c b/arch/mips/lib/mips-atomic.c
index 5530070e0d05..de03838b343b 100644
--- a/arch/mips/lib/mips-atomic.c
+++ b/arch/mips/lib/mips-atomic.c
@@ -15,7 +15,7 @@
 #include <linux/export.h>
 #include <linux/stringify.h>
 
-#if !defined(CONFIG_CPU_MIPSR2) && !defined(CONFIG_CPU_MIPSR6)
+#if !defined(CONFIG_CPU_HAS_DIEI)
 
 /*
  * For cli() we have to insert nops to make sure that the new value
@@ -110,4 +110,4 @@ notrace void arch_local_irq_restore(unsigned long flags)
 }
 EXPORT_SYMBOL(arch_local_irq_restore);
 
-#endif /* !CONFIG_CPU_MIPSR2 && !CONFIG_CPU_MIPSR6 */
+#endif /* !CONFIG_CPU_HAS_DIEI */
diff --git a/arch/mips/loongson2ef/common/pm.c b/arch/mips/loongson2ef/common/pm.c
index 11f4cfd581fb..bcb7ae9777cf 100644
--- a/arch/mips/loongson2ef/common/pm.c
+++ b/arch/mips/loongson2ef/common/pm.c
@@ -91,7 +91,7 @@ static inline void stop_perf_counters(void)
 
 static void loongson_suspend_enter(void)
 {
-	static unsigned int cached_cpu_freq;
+	unsigned int cached_cpu_freq;
 
 	/* setup wakeup events via enabling the IRQs */
 	setup_wakeup_events();
diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c
index ef94a2278561..e5b40c5e3296 100644
--- a/arch/mips/loongson64/numa.c
+++ b/arch/mips/loongson64/numa.c
@@ -75,7 +75,7 @@ static int __init compute_node_distance(int row, int col)
 				loongson_sysconf.cores_per_package;
 
 	if (col == row)
-		return 0;
+		return LOCAL_DISTANCE;
 	else if (package_row == package_col)
 		return 40;
 	else
diff --git a/arch/mips/loongson64/platform.c b/arch/mips/loongson64/platform.c
index 13f3404f0030..9674ae1361a8 100644
--- a/arch/mips/loongson64/platform.c
+++ b/arch/mips/loongson64/platform.c
@@ -27,6 +27,9 @@ static int __init loongson3_platform_init(void)
 			continue;
 
 		pdev = kzalloc(sizeof(struct platform_device), GFP_KERNEL);
+		if (!pdev)
+			return -ENOMEM;
+
 		pdev->name = loongson_sysconf.sensors[i].name;
 		pdev->id = loongson_sysconf.sensors[i].id;
 		pdev->dev.platform_data = &loongson_sysconf.sensors[i];
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 710e1f804a54..9701c89e7e14 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1514,16 +1514,28 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			break;
 
 		case madd_s_op:
-			handler = fpemu_sp_madd;
+			if (cpu_has_mac2008_only)
+				handler = ieee754sp_madd;
+			else
+				handler = fpemu_sp_madd;
 			goto scoptop;
 		case msub_s_op:
-			handler = fpemu_sp_msub;
+			if (cpu_has_mac2008_only)
+				handler = ieee754sp_msub;
+			else
+				handler = fpemu_sp_msub;
 			goto scoptop;
 		case nmadd_s_op:
-			handler = fpemu_sp_nmadd;
+			if (cpu_has_mac2008_only)
+				handler = ieee754sp_nmadd;
+			else
+				handler = fpemu_sp_nmadd;
 			goto scoptop;
 		case nmsub_s_op:
-			handler = fpemu_sp_nmsub;
+			if (cpu_has_mac2008_only)
+				handler = ieee754sp_nmsub;
+			else
+				handler = fpemu_sp_nmsub;
 			goto scoptop;
 
 		      scoptop:
@@ -1610,15 +1622,27 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			break;
 
 		case madd_d_op:
-			handler = fpemu_dp_madd;
+			if (cpu_has_mac2008_only)
+				handler = ieee754dp_madd;
+			else
+				handler = fpemu_dp_madd;
 			goto dcoptop;
 		case msub_d_op:
-			handler = fpemu_dp_msub;
+			if (cpu_has_mac2008_only)
+				handler = ieee754dp_msub;
+			else
+				handler = fpemu_dp_msub;
 			goto dcoptop;
 		case nmadd_d_op:
-			handler = fpemu_dp_nmadd;
+			if (cpu_has_mac2008_only)
+				handler = ieee754dp_nmadd;
+			else
+				handler = fpemu_dp_nmadd;
 			goto dcoptop;
 		case nmsub_d_op:
+			if (cpu_has_mac2008_only)
+				handler = ieee754dp_nmsub;
+			else
 			handler = fpemu_dp_nmsub;
 			goto dcoptop;
 
diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c
index 3da0ce44cdef..e24ef374d828 100644
--- a/arch/mips/math-emu/dp_maddf.c
+++ b/arch/mips/math-emu/dp_maddf.c
@@ -68,6 +68,12 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 
 	ieee754_clearcx();
 
+	rs = xs ^ ys;
+	if (flags & MADDF_NEGATE_PRODUCT)
+		rs ^= 1;
+	if (flags & MADDF_NEGATE_ADDITION)
+		zs ^= 1;
+
 	/*
 	 * Handle the cases when at least one of x, y or z is a NaN.
 	 * Order of precedence is sNaN, qNaN and z, x, y.
@@ -104,9 +110,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		if ((zc == IEEE754_CLASS_INF) &&
-		    ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) ||
-		     ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) {
+		if ((zc == IEEE754_CLASS_INF) && (zs != rs)) {
 			/*
 			 * Cases of addition of infinities with opposite signs
 			 * or subtraction of infinities with same signs.
@@ -116,15 +120,10 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 		}
 		/*
 		 * z is here either not an infinity, or an infinity having the
-		 * same sign as product (x*y) (in case of MADDF.D instruction)
-		 * or product -(x*y) (in MSUBF.D case). The result must be an
-		 * infinity, and its sign is determined only by the value of
-		 * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y.
+		 * same sign as product (x*y). The result must be an infinity,
+		 * and its sign is determined only by the sign of product (x*y).
 		 */
-		if (flags & MADDF_NEGATE_PRODUCT)
-			return ieee754dp_inf(1 ^ (xs ^ ys));
-		else
-			return ieee754dp_inf(xs ^ ys);
+		return ieee754dp_inf(rs);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
@@ -135,10 +134,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 			return ieee754dp_inf(zs);
 		if (zc == IEEE754_CLASS_ZERO) {
 			/* Handle cases +0 + (-0) and similar ones. */
-			if ((!(flags & MADDF_NEGATE_PRODUCT)
-					&& (zs == (xs ^ ys))) ||
-			    ((flags & MADDF_NEGATE_PRODUCT)
-					&& (zs != (xs ^ ys))))
+			if (zs == rs)
 				/*
 				 * Cases of addition of zeros of equal signs
 				 * or subtraction of zeroes of opposite signs.
@@ -187,9 +183,6 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x,
 	assert(ym & DP_HIDDEN_BIT);
 
 	re = xe + ye;
-	rs = xs ^ ys;
-	if (flags & MADDF_NEGATE_PRODUCT)
-		rs ^= 1;
 
 	/* shunt to top of word */
 	xm <<= 64 - (DP_FBITS + 1);
@@ -340,3 +333,27 @@ union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
 {
 	return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
 }
+
+union ieee754dp ieee754dp_madd(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	return _dp_maddf(z, x, y, 0);
+}
+
+union ieee754dp ieee754dp_msub(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	return _dp_maddf(z, x, y, MADDF_NEGATE_ADDITION);
+}
+
+union ieee754dp ieee754dp_nmadd(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT|MADDF_NEGATE_ADDITION);
+}
+
+union ieee754dp ieee754dp_nmsub(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y)
+{
+	return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
+}
diff --git a/arch/mips/math-emu/ieee754.h b/arch/mips/math-emu/ieee754.h
index b9167bd4eb60..090caa740b1e 100644
--- a/arch/mips/math-emu/ieee754.h
+++ b/arch/mips/math-emu/ieee754.h
@@ -68,6 +68,14 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x,
 				union ieee754sp y);
 union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
 				union ieee754sp y);
+union ieee754sp ieee754sp_madd(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y);
+union ieee754sp ieee754sp_msub(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y);
+union ieee754sp ieee754sp_nmadd(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y);
+union ieee754sp ieee754sp_nmsub(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y);
 int ieee754sp_2008class(union ieee754sp x);
 union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y);
 union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y);
@@ -103,6 +111,14 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x,
 				union ieee754dp y);
 union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x,
 				union ieee754dp y);
+union ieee754dp ieee754dp_madd(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y);
+union ieee754dp ieee754dp_msub(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y);
+union ieee754dp ieee754dp_nmadd(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y);
+union ieee754dp ieee754dp_nmsub(union ieee754dp z, union ieee754dp x,
+				union ieee754dp y);
 int ieee754dp_2008class(union ieee754dp x);
 union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y);
 union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y);
diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h
index 52b20119e315..2c3b13546ac8 100644
--- a/arch/mips/math-emu/ieee754int.h
+++ b/arch/mips/math-emu/ieee754int.h
@@ -16,6 +16,7 @@
 
 enum maddf_flags {
 	MADDF_NEGATE_PRODUCT	= 1 << 0,
+	MADDF_NEGATE_ADDITION	= 1 << 1,
 };
 
 static inline void ieee754_clearcx(void)
diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c
index d638354add6d..1b85b1a527ac 100644
--- a/arch/mips/math-emu/sp_maddf.c
+++ b/arch/mips/math-emu/sp_maddf.c
@@ -36,6 +36,12 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 
 	ieee754_clearcx();
 
+	rs = xs ^ ys;
+	if (flags & MADDF_NEGATE_PRODUCT)
+		rs ^= 1;
+	if (flags & MADDF_NEGATE_ADDITION)
+		zs ^= 1;
+
 	/*
 	 * Handle the cases when at least one of x, y or z is a NaN.
 	 * Order of precedence is sNaN, qNaN and z, x, y.
@@ -73,9 +79,7 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM):
 	case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF):
-		if ((zc == IEEE754_CLASS_INF) &&
-		    ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) ||
-		     ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) {
+		if ((zc == IEEE754_CLASS_INF) && (zs != rs)) {
 			/*
 			 * Cases of addition of infinities with opposite signs
 			 * or subtraction of infinities with same signs.
@@ -85,15 +89,10 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 		}
 		/*
 		 * z is here either not an infinity, or an infinity having the
-		 * same sign as product (x*y) (in case of MADDF.D instruction)
-		 * or product -(x*y) (in MSUBF.D case). The result must be an
-		 * infinity, and its sign is determined only by the value of
-		 * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y.
+		 * same sign as product (x*y). The result must be an infinity,
+		 * and its sign is determined only by the sign of product (x*y).
 		 */
-		if (flags & MADDF_NEGATE_PRODUCT)
-			return ieee754sp_inf(1 ^ (xs ^ ys));
-		else
-			return ieee754sp_inf(xs ^ ys);
+		return ieee754sp_inf(rs);
 
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO):
 	case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM):
@@ -104,10 +103,7 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 			return ieee754sp_inf(zs);
 		if (zc == IEEE754_CLASS_ZERO) {
 			/* Handle cases +0 + (-0) and similar ones. */
-			if ((!(flags & MADDF_NEGATE_PRODUCT)
-					&& (zs == (xs ^ ys))) ||
-			    ((flags & MADDF_NEGATE_PRODUCT)
-					&& (zs != (xs ^ ys))))
+			if (zs == rs)
 				/*
 				 * Cases of addition of zeros of equal signs
 				 * or subtraction of zeroes of opposite signs.
@@ -158,9 +154,6 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x,
 	assert(ym & SP_HIDDEN_BIT);
 
 	re = xe + ye;
-	rs = xs ^ ys;
-	if (flags & MADDF_NEGATE_PRODUCT)
-		rs ^= 1;
 
 	/* Multiple 24 bit xm and ym to give 48 bit results */
 	rm64 = (uint64_t)xm * ym;
@@ -260,3 +253,27 @@ union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x,
 {
 	return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
 }
+
+union ieee754sp ieee754sp_madd(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	return _sp_maddf(z, x, y, 0);
+}
+
+union ieee754sp ieee754sp_msub(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	return _sp_maddf(z, x, y, MADDF_NEGATE_ADDITION);
+}
+
+union ieee754sp ieee754sp_nmadd(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT|MADDF_NEGATE_ADDITION);
+}
+
+union ieee754sp ieee754sp_nmsub(union ieee754sp z, union ieee754sp x,
+				union ieee754sp y)
+{
+	return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT);
+}
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 50f9ed8c6c1b..79684000de0e 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -508,6 +508,51 @@ void __ref free_initmem(void)
 		free_initmem_default(POISON_FREE_INITMEM);
 }
 
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	return node_distance(cpu_to_node(from), cpu_to_node(to));
+}
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+				       size_t align)
+{
+	return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_ACCESSIBLE,
+				      cpu_to_node(cpu));
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	memblock_free_early(__pa(ptr), size);
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Always reserve area for module percpu variables.  That's
+	 * what the legacy allocator did.
+	 */
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+				    pcpu_cpu_distance,
+				    pcpu_fc_alloc, pcpu_fc_free);
+	if (rc < 0)
+		panic("Failed to initialize percpu areas.");
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+#endif
+
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 unsigned long pgd_current[NR_CPUS];
 #endif
diff --git a/arch/mips/net/Makefile b/arch/mips/net/Makefile
index 2d03af7d6b19..d55912349039 100644
--- a/arch/mips/net/Makefile
+++ b/arch/mips/net/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 # MIPS networking code
 
+obj-$(CONFIG_MIPS_CBPF_JIT) += bpf_jit.o bpf_jit_asm.o
 obj-$(CONFIG_MIPS_EBPF_JIT) += ebpf_jit.o
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
new file mode 100644
index 000000000000..0af88622c619
--- /dev/null
+++ b/arch/mips/net/bpf_jit.c
@@ -0,0 +1,1270 @@
+/*
+ * Just-In-Time compiler for BPF filters on MIPS
+ *
+ * Copyright (c) 2014 Imagination Technologies Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/filter.h>
+#include <linux/if_vlan.h>
+#include <linux/moduleloader.h>
+#include <linux/netdevice.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <asm/asm.h>
+#include <asm/bitops.h>
+#include <asm/cacheflush.h>
+#include <asm/cpu-features.h>
+#include <asm/uasm.h>
+
+#include "bpf_jit.h"
+
+/* ABI
+ * r_skb_hl	SKB header length
+ * r_data	SKB data pointer
+ * r_off	Offset
+ * r_A		BPF register A
+ * r_X		BPF register X
+ * r_skb	*skb
+ * r_M		*scratch memory
+ * r_skb_len	SKB length
+ *
+ * On entry (*bpf_func)(*skb, *filter)
+ * a0 = MIPS_R_A0 = skb;
+ * a1 = MIPS_R_A1 = filter;
+ *
+ * Stack
+ * ...
+ * M[15]
+ * M[14]
+ * M[13]
+ * ...
+ * M[0] <-- r_M
+ * saved reg k-1
+ * saved reg k-2
+ * ...
+ * saved reg 0 <-- r_sp
+ * <no argument area>
+ *
+ *                     Packet layout
+ *
+ * <--------------------- len ------------------------>
+ * <--skb-len(r_skb_hl)-->< ----- skb->data_len ------>
+ * ----------------------------------------------------
+ * |                  skb->data                       |
+ * ----------------------------------------------------
+ */
+
+#define ptr typeof(unsigned long)
+
+#define SCRATCH_OFF(k)		(4 * (k))
+
+/* JIT flags */
+#define SEEN_CALL		(1 << BPF_MEMWORDS)
+#define SEEN_SREG_SFT		(BPF_MEMWORDS + 1)
+#define SEEN_SREG_BASE		(1 << SEEN_SREG_SFT)
+#define SEEN_SREG(x)		(SEEN_SREG_BASE << (x))
+#define SEEN_OFF		SEEN_SREG(2)
+#define SEEN_A			SEEN_SREG(3)
+#define SEEN_X			SEEN_SREG(4)
+#define SEEN_SKB		SEEN_SREG(5)
+#define SEEN_MEM		SEEN_SREG(6)
+/* SEEN_SK_DATA also implies skb_hl an skb_len */
+#define SEEN_SKB_DATA		(SEEN_SREG(7) | SEEN_SREG(1) | SEEN_SREG(0))
+
+/* Arguments used by JIT */
+#define ARGS_USED_BY_JIT	2 /* only applicable to 64-bit */
+
+#define SBIT(x)			(1 << (x)) /* Signed version of BIT() */
+
+/**
+ * struct jit_ctx - JIT context
+ * @skf:		The sk_filter
+ * @prologue_bytes:	Number of bytes for prologue
+ * @idx:		Instruction index
+ * @flags:		JIT flags
+ * @offsets:		Instruction offsets
+ * @target:		Memory location for the compiled filter
+ */
+struct jit_ctx {
+	const struct bpf_prog *skf;
+	unsigned int prologue_bytes;
+	u32 idx;
+	u32 flags;
+	u32 *offsets;
+	u32 *target;
+};
+
+
+static inline int optimize_div(u32 *k)
+{
+	/* power of 2 divides can be implemented with right shift */
+	if (!(*k & (*k-1))) {
+		*k = ilog2(*k);
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline void emit_jit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx);
+
+/* Simply emit the instruction if the JIT memory space has been allocated */
+#define emit_instr(ctx, func, ...)			\
+do {							\
+	if ((ctx)->target != NULL) {			\
+		u32 *p = &(ctx)->target[ctx->idx];	\
+		uasm_i_##func(&p, ##__VA_ARGS__);	\
+	}						\
+	(ctx)->idx++;					\
+} while (0)
+
+/*
+ * Similar to emit_instr but it must be used when we need to emit
+ * 32-bit or 64-bit instructions
+ */
+#define emit_long_instr(ctx, func, ...)			\
+do {							\
+	if ((ctx)->target != NULL) {			\
+		u32 *p = &(ctx)->target[ctx->idx];	\
+		UASM_i_##func(&p, ##__VA_ARGS__);	\
+	}						\
+	(ctx)->idx++;					\
+} while (0)
+
+/* Determine if immediate is within the 16-bit signed range */
+static inline bool is_range16(s32 imm)
+{
+	return !(imm >= SBIT(15) || imm < -SBIT(15));
+}
+
+static inline void emit_addu(unsigned int dst, unsigned int src1,
+			     unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, addu, dst, src1, src2);
+}
+
+static inline void emit_nop(struct jit_ctx *ctx)
+{
+	emit_instr(ctx, nop);
+}
+
+/* Load a u32 immediate to a register */
+static inline void emit_load_imm(unsigned int dst, u32 imm, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		/* addiu can only handle s16 */
+		if (!is_range16(imm)) {
+			u32 *p = &ctx->target[ctx->idx];
+			uasm_i_lui(&p, r_tmp_imm, (s32)imm >> 16);
+			p = &ctx->target[ctx->idx + 1];
+			uasm_i_ori(&p, dst, r_tmp_imm, imm & 0xffff);
+		} else {
+			u32 *p = &ctx->target[ctx->idx];
+			uasm_i_addiu(&p, dst, r_zero, imm);
+		}
+	}
+	ctx->idx++;
+
+	if (!is_range16(imm))
+		ctx->idx++;
+}
+
+static inline void emit_or(unsigned int dst, unsigned int src1,
+			   unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, or, dst, src1, src2);
+}
+
+static inline void emit_ori(unsigned int dst, unsigned src, u32 imm,
+			    struct jit_ctx *ctx)
+{
+	if (imm >= BIT(16)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_or(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, ori, dst, src, imm);
+	}
+}
+
+static inline void emit_daddiu(unsigned int dst, unsigned int src,
+			       int imm, struct jit_ctx *ctx)
+{
+	/*
+	 * Only used for stack, so the imm is relatively small
+	 * and it fits in 15-bits
+	 */
+	emit_instr(ctx, daddiu, dst, src, imm);
+}
+
+static inline void emit_addiu(unsigned int dst, unsigned int src,
+			      u32 imm, struct jit_ctx *ctx)
+{
+	if (!is_range16(imm)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_addu(dst, r_tmp, src, ctx);
+	} else {
+		emit_instr(ctx, addiu, dst, src, imm);
+	}
+}
+
+static inline void emit_and(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, and, dst, src1, src2);
+}
+
+static inline void emit_andi(unsigned int dst, unsigned int src,
+			     u32 imm, struct jit_ctx *ctx)
+{
+	/* If imm does not fit in u16 then load it to register */
+	if (imm >= BIT(16)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_and(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, andi, dst, src, imm);
+	}
+}
+
+static inline void emit_xor(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, xor, dst, src1, src2);
+}
+
+static inline void emit_xori(ptr dst, ptr src, u32 imm, struct jit_ctx *ctx)
+{
+	/* If imm does not fit in u16 then load it to register */
+	if (imm >= BIT(16)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_xor(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, xori, dst, src, imm);
+	}
+}
+
+static inline void emit_stack_offset(int offset, struct jit_ctx *ctx)
+{
+	emit_long_instr(ctx, ADDIU, r_sp, r_sp, offset);
+}
+
+static inline void emit_subu(unsigned int dst, unsigned int src1,
+			     unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, subu, dst, src1, src2);
+}
+
+static inline void emit_neg(unsigned int reg, struct jit_ctx *ctx)
+{
+	emit_subu(reg, r_zero, reg, ctx);
+}
+
+static inline void emit_sllv(unsigned int dst, unsigned int src,
+			     unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, sllv, dst, src, sa);
+}
+
+static inline void emit_sll(unsigned int dst, unsigned int src,
+			    unsigned int sa, struct jit_ctx *ctx)
+{
+	/* sa is 5-bits long */
+	if (sa >= BIT(5))
+		/* Shifting >= 32 results in zero */
+		emit_jit_reg_move(dst, r_zero, ctx);
+	else
+		emit_instr(ctx, sll, dst, src, sa);
+}
+
+static inline void emit_srlv(unsigned int dst, unsigned int src,
+			     unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, srlv, dst, src, sa);
+}
+
+static inline void emit_srl(unsigned int dst, unsigned int src,
+			    unsigned int sa, struct jit_ctx *ctx)
+{
+	/* sa is 5-bits long */
+	if (sa >= BIT(5))
+		/* Shifting >= 32 results in zero */
+		emit_jit_reg_move(dst, r_zero, ctx);
+	else
+		emit_instr(ctx, srl, dst, src, sa);
+}
+
+static inline void emit_slt(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, slt, dst, src1, src2);
+}
+
+static inline void emit_sltu(unsigned int dst, unsigned int src1,
+			     unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, sltu, dst, src1, src2);
+}
+
+static inline void emit_sltiu(unsigned dst, unsigned int src,
+			      unsigned int imm, struct jit_ctx *ctx)
+{
+	/* 16 bit immediate */
+	if (!is_range16((s32)imm)) {
+		emit_load_imm(r_tmp, imm, ctx);
+		emit_sltu(dst, src, r_tmp, ctx);
+	} else {
+		emit_instr(ctx, sltiu, dst, src, imm);
+	}
+
+}
+
+/* Store register on the stack */
+static inline void emit_store_stack_reg(ptr reg, ptr base,
+					unsigned int offset,
+					struct jit_ctx *ctx)
+{
+	emit_long_instr(ctx, SW, reg, offset, base);
+}
+
+static inline void emit_store(ptr reg, ptr base, unsigned int offset,
+			      struct jit_ctx *ctx)
+{
+	emit_instr(ctx, sw, reg, offset, base);
+}
+
+static inline void emit_load_stack_reg(ptr reg, ptr base,
+				       unsigned int offset,
+				       struct jit_ctx *ctx)
+{
+	emit_long_instr(ctx, LW, reg, offset, base);
+}
+
+static inline void emit_load(unsigned int reg, unsigned int base,
+			     unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lw, reg, offset, base);
+}
+
+static inline void emit_load_byte(unsigned int reg, unsigned int base,
+				  unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lb, reg, offset, base);
+}
+
+static inline void emit_half_load(unsigned int reg, unsigned int base,
+				  unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lh, reg, offset, base);
+}
+
+static inline void emit_half_load_unsigned(unsigned int reg, unsigned int base,
+					   unsigned int offset, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, lhu, reg, offset, base);
+}
+
+static inline void emit_mul(unsigned int dst, unsigned int src1,
+			    unsigned int src2, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, mul, dst, src1, src2);
+}
+
+static inline void emit_div(unsigned int dst, unsigned int src,
+			    struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		u32 *p = &ctx->target[ctx->idx];
+		uasm_i_divu(&p, dst, src);
+		p = &ctx->target[ctx->idx + 1];
+		uasm_i_mflo(&p, dst);
+	}
+	ctx->idx += 2; /* 2 insts */
+}
+
+static inline void emit_mod(unsigned int dst, unsigned int src,
+			    struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		u32 *p = &ctx->target[ctx->idx];
+		uasm_i_divu(&p, dst, src);
+		p = &ctx->target[ctx->idx + 1];
+		uasm_i_mfhi(&p, dst);
+	}
+	ctx->idx += 2; /* 2 insts */
+}
+
+static inline void emit_dsll(unsigned int dst, unsigned int src,
+			     unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, dsll, dst, src, sa);
+}
+
+static inline void emit_dsrl32(unsigned int dst, unsigned int src,
+			       unsigned int sa, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, dsrl32, dst, src, sa);
+}
+
+static inline void emit_wsbh(unsigned int dst, unsigned int src,
+			     struct jit_ctx *ctx)
+{
+	emit_instr(ctx, wsbh, dst, src);
+}
+
+/* load pointer to register */
+static inline void emit_load_ptr(unsigned int dst, unsigned int src,
+				     int imm, struct jit_ctx *ctx)
+{
+	/* src contains the base addr of the 32/64-pointer */
+	emit_long_instr(ctx, LW, dst, imm, src);
+}
+
+/* load a function pointer to register */
+static inline void emit_load_func(unsigned int reg, ptr imm,
+				  struct jit_ctx *ctx)
+{
+	if (IS_ENABLED(CONFIG_64BIT)) {
+		/* At this point imm is always 64-bit */
+		emit_load_imm(r_tmp, (u64)imm >> 32, ctx);
+		emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */
+		emit_ori(r_tmp, r_tmp_imm, (imm >> 16) & 0xffff, ctx);
+		emit_dsll(r_tmp_imm, r_tmp, 16, ctx); /* left shift by 16 */
+		emit_ori(reg, r_tmp_imm, imm & 0xffff, ctx);
+	} else {
+		emit_load_imm(reg, imm, ctx);
+	}
+}
+
+/* Move to real MIPS register */
+static inline void emit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx)
+{
+	emit_long_instr(ctx, ADDU, dst, src, r_zero);
+}
+
+/* Move to JIT (32-bit) register */
+static inline void emit_jit_reg_move(ptr dst, ptr src, struct jit_ctx *ctx)
+{
+	emit_addu(dst, src, r_zero, ctx);
+}
+
+/* Compute the immediate value for PC-relative branches. */
+static inline u32 b_imm(unsigned int tgt, struct jit_ctx *ctx)
+{
+	if (ctx->target == NULL)
+		return 0;
+
+	/*
+	 * We want a pc-relative branch. We only do forward branches
+	 * so tgt is always after pc. tgt is the instruction offset
+	 * we want to jump to.
+
+	 * Branch on MIPS:
+	 * I: target_offset <- sign_extend(offset)
+	 * I+1: PC += target_offset (delay slot)
+	 *
+	 * ctx->idx currently points to the branch instruction
+	 * but the offset is added to the delay slot so we need
+	 * to subtract 4.
+	 */
+	return ctx->offsets[tgt] -
+		(ctx->idx * 4 - ctx->prologue_bytes) - 4;
+}
+
+static inline void emit_bcond(int cond, unsigned int reg1, unsigned int reg2,
+			     unsigned int imm, struct jit_ctx *ctx)
+{
+	if (ctx->target != NULL) {
+		u32 *p = &ctx->target[ctx->idx];
+
+		switch (cond) {
+		case MIPS_COND_EQ:
+			uasm_i_beq(&p, reg1, reg2, imm);
+			break;
+		case MIPS_COND_NE:
+			uasm_i_bne(&p, reg1, reg2, imm);
+			break;
+		case MIPS_COND_ALL:
+			uasm_i_b(&p, imm);
+			break;
+		default:
+			pr_warn("%s: Unhandled branch conditional: %d\n",
+				__func__, cond);
+		}
+	}
+	ctx->idx++;
+}
+
+static inline void emit_b(unsigned int imm, struct jit_ctx *ctx)
+{
+	emit_bcond(MIPS_COND_ALL, r_zero, r_zero, imm, ctx);
+}
+
+static inline void emit_jalr(unsigned int link, unsigned int reg,
+			     struct jit_ctx *ctx)
+{
+	emit_instr(ctx, jalr, link, reg);
+}
+
+static inline void emit_jr(unsigned int reg, struct jit_ctx *ctx)
+{
+	emit_instr(ctx, jr, reg);
+}
+
+static inline u16 align_sp(unsigned int num)
+{
+	/* Double word alignment for 32-bit, quadword for 64-bit */
+	unsigned int align = IS_ENABLED(CONFIG_64BIT) ? 16 : 8;
+	num = (num + (align - 1)) & -align;
+	return num;
+}
+
+static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
+{
+	int i = 0, real_off = 0;
+	u32 sflags, tmp_flags;
+
+	/* Adjust the stack pointer */
+	if (offset)
+		emit_stack_offset(-align_sp(offset), ctx);
+
+	tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT;
+	/* sflags is essentially a bitmap */
+	while (tmp_flags) {
+		if ((sflags >> i) & 0x1) {
+			emit_store_stack_reg(MIPS_R_S0 + i, r_sp, real_off,
+					     ctx);
+			real_off += SZREG;
+		}
+		i++;
+		tmp_flags >>= 1;
+	}
+
+	/* save return address */
+	if (ctx->flags & SEEN_CALL) {
+		emit_store_stack_reg(r_ra, r_sp, real_off, ctx);
+		real_off += SZREG;
+	}
+
+	/* Setup r_M leaving the alignment gap if necessary */
+	if (ctx->flags & SEEN_MEM) {
+		if (real_off % (SZREG * 2))
+			real_off += SZREG;
+		emit_long_instr(ctx, ADDIU, r_M, r_sp, real_off);
+	}
+}
+
+static void restore_bpf_jit_regs(struct jit_ctx *ctx,
+				 unsigned int offset)
+{
+	int i, real_off = 0;
+	u32 sflags, tmp_flags;
+
+	tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT;
+	/* sflags is a bitmap */
+	i = 0;
+	while (tmp_flags) {
+		if ((sflags >> i) & 0x1) {
+			emit_load_stack_reg(MIPS_R_S0 + i, r_sp, real_off,
+					    ctx);
+			real_off += SZREG;
+		}
+		i++;
+		tmp_flags >>= 1;
+	}
+
+	/* restore return address */
+	if (ctx->flags & SEEN_CALL)
+		emit_load_stack_reg(r_ra, r_sp, real_off, ctx);
+
+	/* Restore the sp and discard the scrach memory */
+	if (offset)
+		emit_stack_offset(align_sp(offset), ctx);
+}
+
+static unsigned int get_stack_depth(struct jit_ctx *ctx)
+{
+	int sp_off = 0;
+
+
+	/* How may s* regs do we need to preserved? */
+	sp_off += hweight32(ctx->flags >> SEEN_SREG_SFT) * SZREG;
+
+	if (ctx->flags & SEEN_MEM)
+		sp_off += 4 * BPF_MEMWORDS; /* BPF_MEMWORDS are 32-bit */
+
+	if (ctx->flags & SEEN_CALL)
+		sp_off += SZREG; /* Space for our ra register */
+
+	return sp_off;
+}
+
+static void build_prologue(struct jit_ctx *ctx)
+{
+	int sp_off;
+
+	/* Calculate the total offset for the stack pointer */
+	sp_off = get_stack_depth(ctx);
+	save_bpf_jit_regs(ctx, sp_off);
+
+	if (ctx->flags & SEEN_SKB)
+		emit_reg_move(r_skb, MIPS_R_A0, ctx);
+
+	if (ctx->flags & SEEN_SKB_DATA) {
+		/* Load packet length */
+		emit_load(r_skb_len, r_skb, offsetof(struct sk_buff, len),
+			  ctx);
+		emit_load(r_tmp, r_skb, offsetof(struct sk_buff, data_len),
+			  ctx);
+		/* Load the data pointer */
+		emit_load_ptr(r_skb_data, r_skb,
+			      offsetof(struct sk_buff, data), ctx);
+		/* Load the header length */
+		emit_subu(r_skb_hl, r_skb_len, r_tmp, ctx);
+	}
+
+	if (ctx->flags & SEEN_X)
+		emit_jit_reg_move(r_X, r_zero, ctx);
+
+	/*
+	 * Do not leak kernel data to userspace, we only need to clear
+	 * r_A if it is ever used.  In fact if it is never used, we
+	 * will not save/restore it, so clearing it in this case would
+	 * corrupt the state of the caller.
+	 */
+	if (bpf_needs_clear_a(&ctx->skf->insns[0]) &&
+	    (ctx->flags & SEEN_A))
+		emit_jit_reg_move(r_A, r_zero, ctx);
+}
+
+static void build_epilogue(struct jit_ctx *ctx)
+{
+	unsigned int sp_off;
+
+	/* Calculate the total offset for the stack pointer */
+
+	sp_off = get_stack_depth(ctx);
+	restore_bpf_jit_regs(ctx, sp_off);
+
+	/* Return */
+	emit_jr(r_ra, ctx);
+	emit_nop(ctx);
+}
+
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative : func) : \
+	 func##_positive)
+
+static int build_body(struct jit_ctx *ctx)
+{
+	const struct bpf_prog *prog = ctx->skf;
+	const struct sock_filter *inst;
+	unsigned int i, off, condt;
+	u32 k, b_off __maybe_unused;
+	u8 (*sk_load_func)(unsigned long *skb, int offset);
+
+	for (i = 0; i < prog->len; i++) {
+		u16 code;
+
+		inst = &(prog->insns[i]);
+		pr_debug("%s: code->0x%02x, jt->0x%x, jf->0x%x, k->0x%x\n",
+			 __func__, inst->code, inst->jt, inst->jf, inst->k);
+		k = inst->k;
+		code = bpf_anc_helper(inst);
+
+		if (ctx->target == NULL)
+			ctx->offsets[i] = ctx->idx * 4;
+
+		switch (code) {
+		case BPF_LD | BPF_IMM:
+			/* A <- k ==> li r_A, k */
+			ctx->flags |= SEEN_A;
+			emit_load_imm(r_A, k, ctx);
+			break;
+		case BPF_LD | BPF_W | BPF_LEN:
+			BUILD_BUG_ON(sizeof_field(struct sk_buff, len) != 4);
+			/* A <- len ==> lw r_A, offset(skb) */
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			off = offsetof(struct sk_buff, len);
+			emit_load(r_A, r_skb, off, ctx);
+			break;
+		case BPF_LD | BPF_MEM:
+			/* A <- M[k] ==> lw r_A, offset(M) */
+			ctx->flags |= SEEN_MEM | SEEN_A;
+			emit_load(r_A, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_LD | BPF_W | BPF_ABS:
+			/* A <- P[k:4] */
+			sk_load_func = CHOOSE_LOAD_FUNC(k, sk_load_word);
+			goto load;
+		case BPF_LD | BPF_H | BPF_ABS:
+			/* A <- P[k:2] */
+			sk_load_func = CHOOSE_LOAD_FUNC(k, sk_load_half);
+			goto load;
+		case BPF_LD | BPF_B | BPF_ABS:
+			/* A <- P[k:1] */
+			sk_load_func = CHOOSE_LOAD_FUNC(k, sk_load_byte);
+load:
+			emit_load_imm(r_off, k, ctx);
+load_common:
+			ctx->flags |= SEEN_CALL | SEEN_OFF |
+				SEEN_SKB | SEEN_A | SEEN_SKB_DATA;
+
+			emit_load_func(r_s0, (ptr)sk_load_func, ctx);
+			emit_reg_move(MIPS_R_A0, r_skb, ctx);
+			emit_jalr(MIPS_R_RA, r_s0, ctx);
+			/* Load second argument to delay slot */
+			emit_reg_move(MIPS_R_A1, r_off, ctx);
+			/* Check the error value */
+			emit_bcond(MIPS_COND_EQ, r_ret, 0, b_imm(i + 1, ctx),
+				   ctx);
+			/* Load return register on DS for failures */
+			emit_reg_move(r_ret, r_zero, ctx);
+			/* Return with error */
+			emit_b(b_imm(prog->len, ctx), ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_LD | BPF_W | BPF_IND:
+			/* A <- P[X + k:4] */
+			sk_load_func = sk_load_word;
+			goto load_ind;
+		case BPF_LD | BPF_H | BPF_IND:
+			/* A <- P[X + k:2] */
+			sk_load_func = sk_load_half;
+			goto load_ind;
+		case BPF_LD | BPF_B | BPF_IND:
+			/* A <- P[X + k:1] */
+			sk_load_func = sk_load_byte;
+load_ind:
+			ctx->flags |= SEEN_OFF | SEEN_X;
+			emit_addiu(r_off, r_X, k, ctx);
+			goto load_common;
+		case BPF_LDX | BPF_IMM:
+			/* X <- k */
+			ctx->flags |= SEEN_X;
+			emit_load_imm(r_X, k, ctx);
+			break;
+		case BPF_LDX | BPF_MEM:
+			/* X <- M[k] */
+			ctx->flags |= SEEN_X | SEEN_MEM;
+			emit_load(r_X, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_LDX | BPF_W | BPF_LEN:
+			/* X <- len */
+			ctx->flags |= SEEN_X | SEEN_SKB;
+			off = offsetof(struct sk_buff, len);
+			emit_load(r_X, r_skb, off, ctx);
+			break;
+		case BPF_LDX | BPF_B | BPF_MSH:
+			/* X <- 4 * (P[k:1] & 0xf) */
+			ctx->flags |= SEEN_X | SEEN_CALL | SEEN_SKB;
+			/* Load offset to a1 */
+			emit_load_func(r_s0, (ptr)sk_load_byte, ctx);
+			/*
+			 * This may emit two instructions so it may not fit
+			 * in the delay slot. So use a0 in the delay slot.
+			 */
+			emit_load_imm(MIPS_R_A1, k, ctx);
+			emit_jalr(MIPS_R_RA, r_s0, ctx);
+			emit_reg_move(MIPS_R_A0, r_skb, ctx); /* delay slot */
+			/* Check the error value */
+			emit_bcond(MIPS_COND_NE, r_ret, 0,
+				   b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_zero, ctx);
+			/* We are good */
+			/* X <- P[1:K] & 0xf */
+			emit_andi(r_X, r_A, 0xf, ctx);
+			/* X << 2 */
+			emit_b(b_imm(i + 1, ctx), ctx);
+			emit_sll(r_X, r_X, 2, ctx); /* delay slot */
+			break;
+		case BPF_ST:
+			/* M[k] <- A */
+			ctx->flags |= SEEN_MEM | SEEN_A;
+			emit_store(r_A, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_STX:
+			/* M[k] <- X */
+			ctx->flags |= SEEN_MEM | SEEN_X;
+			emit_store(r_X, r_M, SCRATCH_OFF(k), ctx);
+			break;
+		case BPF_ALU | BPF_ADD | BPF_K:
+			/* A += K */
+			ctx->flags |= SEEN_A;
+			emit_addiu(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_ADD | BPF_X:
+			/* A += X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_addu(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_SUB | BPF_K:
+			/* A -= K */
+			ctx->flags |= SEEN_A;
+			emit_addiu(r_A, r_A, -k, ctx);
+			break;
+		case BPF_ALU | BPF_SUB | BPF_X:
+			/* A -= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_subu(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_MUL | BPF_K:
+			/* A *= K */
+			/* Load K to scratch register before MUL */
+			ctx->flags |= SEEN_A;
+			emit_load_imm(r_s0, k, ctx);
+			emit_mul(r_A, r_A, r_s0, ctx);
+			break;
+		case BPF_ALU | BPF_MUL | BPF_X:
+			/* A *= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_mul(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_DIV | BPF_K:
+			/* A /= k */
+			if (k == 1)
+				break;
+			if (optimize_div(&k)) {
+				ctx->flags |= SEEN_A;
+				emit_srl(r_A, r_A, k, ctx);
+				break;
+			}
+			ctx->flags |= SEEN_A;
+			emit_load_imm(r_s0, k, ctx);
+			emit_div(r_A, r_s0, ctx);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_K:
+			/* A %= k */
+			if (k == 1) {
+				ctx->flags |= SEEN_A;
+				emit_jit_reg_move(r_A, r_zero, ctx);
+			} else {
+				ctx->flags |= SEEN_A;
+				emit_load_imm(r_s0, k, ctx);
+				emit_mod(r_A, r_s0, ctx);
+			}
+			break;
+		case BPF_ALU | BPF_DIV | BPF_X:
+			/* A /= X */
+			ctx->flags |= SEEN_X | SEEN_A;
+			/* Check if r_X is zero */
+			emit_bcond(MIPS_COND_EQ, r_X, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_load_imm(r_ret, 0, ctx); /* delay slot */
+			emit_div(r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_MOD | BPF_X:
+			/* A %= X */
+			ctx->flags |= SEEN_X | SEEN_A;
+			/* Check if r_X is zero */
+			emit_bcond(MIPS_COND_EQ, r_X, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_load_imm(r_ret, 0, ctx); /* delay slot */
+			emit_mod(r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_OR | BPF_K:
+			/* A |= K */
+			ctx->flags |= SEEN_A;
+			emit_ori(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_OR | BPF_X:
+			/* A |= X */
+			ctx->flags |= SEEN_A;
+			emit_ori(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_XOR | BPF_K:
+			/* A ^= k */
+			ctx->flags |= SEEN_A;
+			emit_xori(r_A, r_A, k, ctx);
+			break;
+		case BPF_ANC | SKF_AD_ALU_XOR_X:
+		case BPF_ALU | BPF_XOR | BPF_X:
+			/* A ^= X */
+			ctx->flags |= SEEN_A;
+			emit_xor(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_AND | BPF_K:
+			/* A &= K */
+			ctx->flags |= SEEN_A;
+			emit_andi(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_AND | BPF_X:
+			/* A &= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_and(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_LSH | BPF_K:
+			/* A <<= K */
+			ctx->flags |= SEEN_A;
+			emit_sll(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_LSH | BPF_X:
+			/* A <<= X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_sllv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_RSH | BPF_K:
+			/* A >>= K */
+			ctx->flags |= SEEN_A;
+			emit_srl(r_A, r_A, k, ctx);
+			break;
+		case BPF_ALU | BPF_RSH | BPF_X:
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_srlv(r_A, r_A, r_X, ctx);
+			break;
+		case BPF_ALU | BPF_NEG:
+			/* A = -A */
+			ctx->flags |= SEEN_A;
+			emit_neg(r_A, ctx);
+			break;
+		case BPF_JMP | BPF_JA:
+			/* pc += K */
+			emit_b(b_imm(i + k + 1, ctx), ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_JMP | BPF_JEQ | BPF_K:
+			/* pc += ( A == K ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_EQ | MIPS_COND_K;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JEQ | BPF_X:
+			ctx->flags |= SEEN_X;
+			/* pc += ( A == X ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_EQ | MIPS_COND_X;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGE | BPF_K:
+			/* pc += ( A >= K ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GE | MIPS_COND_K;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGE | BPF_X:
+			ctx->flags |= SEEN_X;
+			/* pc += ( A >= X ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GE | MIPS_COND_X;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGT | BPF_K:
+			/* pc += ( A > K ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GT | MIPS_COND_K;
+			goto jmp_cmp;
+		case BPF_JMP | BPF_JGT | BPF_X:
+			ctx->flags |= SEEN_X;
+			/* pc += ( A > X ) ? pc->jt : pc->jf */
+			condt = MIPS_COND_GT | MIPS_COND_X;
+jmp_cmp:
+			/* Greater or Equal */
+			if ((condt & MIPS_COND_GE) ||
+			    (condt & MIPS_COND_GT)) {
+				if (condt & MIPS_COND_K) { /* K */
+					ctx->flags |= SEEN_A;
+					emit_sltiu(r_s0, r_A, k, ctx);
+				} else { /* X */
+					ctx->flags |= SEEN_A |
+						SEEN_X;
+					emit_sltu(r_s0, r_A, r_X, ctx);
+				}
+				/* A < (K|X) ? r_scrach = 1 */
+				b_off = b_imm(i + inst->jf + 1, ctx);
+				emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off,
+					   ctx);
+				emit_nop(ctx);
+				/* A > (K|X) ? scratch = 0 */
+				if (condt & MIPS_COND_GT) {
+					/* Checking for equality */
+					ctx->flags |= SEEN_A | SEEN_X;
+					if (condt & MIPS_COND_K)
+						emit_load_imm(r_s0, k, ctx);
+					else
+						emit_jit_reg_move(r_s0, r_X,
+								  ctx);
+					b_off = b_imm(i + inst->jf + 1, ctx);
+					emit_bcond(MIPS_COND_EQ, r_A, r_s0,
+						   b_off, ctx);
+					emit_nop(ctx);
+					/* Finally, A > K|X */
+					b_off = b_imm(i + inst->jt + 1, ctx);
+					emit_b(b_off, ctx);
+					emit_nop(ctx);
+				} else {
+					/* A >= (K|X) so jump */
+					b_off = b_imm(i + inst->jt + 1, ctx);
+					emit_b(b_off, ctx);
+					emit_nop(ctx);
+				}
+			} else {
+				/* A == K|X */
+				if (condt & MIPS_COND_K) { /* K */
+					ctx->flags |= SEEN_A;
+					emit_load_imm(r_s0, k, ctx);
+					/* jump true */
+					b_off = b_imm(i + inst->jt + 1, ctx);
+					emit_bcond(MIPS_COND_EQ, r_A, r_s0,
+						   b_off, ctx);
+					emit_nop(ctx);
+					/* jump false */
+					b_off = b_imm(i + inst->jf + 1,
+						      ctx);
+					emit_bcond(MIPS_COND_NE, r_A, r_s0,
+						   b_off, ctx);
+					emit_nop(ctx);
+				} else { /* X */
+					/* jump true */
+					ctx->flags |= SEEN_A | SEEN_X;
+					b_off = b_imm(i + inst->jt + 1,
+						      ctx);
+					emit_bcond(MIPS_COND_EQ, r_A, r_X,
+						   b_off, ctx);
+					emit_nop(ctx);
+					/* jump false */
+					b_off = b_imm(i + inst->jf + 1, ctx);
+					emit_bcond(MIPS_COND_NE, r_A, r_X,
+						   b_off, ctx);
+					emit_nop(ctx);
+				}
+			}
+			break;
+		case BPF_JMP | BPF_JSET | BPF_K:
+			ctx->flags |= SEEN_A;
+			/* pc += (A & K) ? pc -> jt : pc -> jf */
+			emit_load_imm(r_s1, k, ctx);
+			emit_and(r_s0, r_A, r_s1, ctx);
+			/* jump true */
+			b_off = b_imm(i + inst->jt + 1, ctx);
+			emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off, ctx);
+			emit_nop(ctx);
+			/* jump false */
+			b_off = b_imm(i + inst->jf + 1, ctx);
+			emit_b(b_off, ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_JMP | BPF_JSET | BPF_X:
+			ctx->flags |= SEEN_X | SEEN_A;
+			/* pc += (A & X) ? pc -> jt : pc -> jf */
+			emit_and(r_s0, r_A, r_X, ctx);
+			/* jump true */
+			b_off = b_imm(i + inst->jt + 1, ctx);
+			emit_bcond(MIPS_COND_NE, r_s0, r_zero, b_off, ctx);
+			emit_nop(ctx);
+			/* jump false */
+			b_off = b_imm(i + inst->jf + 1, ctx);
+			emit_b(b_off, ctx);
+			emit_nop(ctx);
+			break;
+		case BPF_RET | BPF_A:
+			ctx->flags |= SEEN_A;
+			if (i != prog->len - 1)
+				/*
+				 * If this is not the last instruction
+				 * then jump to the epilogue
+				 */
+				emit_b(b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_A, ctx); /* delay slot */
+			break;
+		case BPF_RET | BPF_K:
+			/*
+			 * It can emit two instructions so it does not fit on
+			 * the delay slot.
+			 */
+			emit_load_imm(r_ret, k, ctx);
+			if (i != prog->len - 1) {
+				/*
+				 * If this is not the last instruction
+				 * then jump to the epilogue
+				 */
+				emit_b(b_imm(prog->len, ctx), ctx);
+				emit_nop(ctx);
+			}
+			break;
+		case BPF_MISC | BPF_TAX:
+			/* X = A */
+			ctx->flags |= SEEN_X | SEEN_A;
+			emit_jit_reg_move(r_X, r_A, ctx);
+			break;
+		case BPF_MISC | BPF_TXA:
+			/* A = X */
+			ctx->flags |= SEEN_A | SEEN_X;
+			emit_jit_reg_move(r_A, r_X, ctx);
+			break;
+		/* AUX */
+		case BPF_ANC | SKF_AD_PROTOCOL:
+			/* A = ntohs(skb->protocol */
+			ctx->flags |= SEEN_SKB | SEEN_OFF | SEEN_A;
+			BUILD_BUG_ON(sizeof_field(struct sk_buff,
+						  protocol) != 2);
+			off = offsetof(struct sk_buff, protocol);
+			emit_half_load(r_A, r_skb, off, ctx);
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+			/* This needs little endian fixup */
+			if (cpu_has_wsbh) {
+				/* R2 and later have the wsbh instruction */
+				emit_wsbh(r_A, r_A, ctx);
+			} else {
+				/* Get first byte */
+				emit_andi(r_tmp_imm, r_A, 0xff, ctx);
+				/* Shift it */
+				emit_sll(r_tmp, r_tmp_imm, 8, ctx);
+				/* Get second byte */
+				emit_srl(r_tmp_imm, r_A, 8, ctx);
+				emit_andi(r_tmp_imm, r_tmp_imm, 0xff, ctx);
+				/* Put everyting together in r_A */
+				emit_or(r_A, r_tmp, r_tmp_imm, ctx);
+			}
+#endif
+			break;
+		case BPF_ANC | SKF_AD_CPU:
+			ctx->flags |= SEEN_A | SEEN_OFF;
+			/* A = current_thread_info()->cpu */
+			BUILD_BUG_ON(sizeof_field(struct thread_info,
+						  cpu) != 4);
+			off = offsetof(struct thread_info, cpu);
+			/* $28/gp points to the thread_info struct */
+			emit_load(r_A, 28, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_IFINDEX:
+			/* A = skb->dev->ifindex */
+		case BPF_ANC | SKF_AD_HATYPE:
+			/* A = skb->dev->type */
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			off = offsetof(struct sk_buff, dev);
+			/* Load *dev pointer */
+			emit_load_ptr(r_s0, r_skb, off, ctx);
+			/* error (0) in the delay slot */
+			emit_bcond(MIPS_COND_EQ, r_s0, r_zero,
+				   b_imm(prog->len, ctx), ctx);
+			emit_reg_move(r_ret, r_zero, ctx);
+			if (code == (BPF_ANC | SKF_AD_IFINDEX)) {
+				BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4);
+				off = offsetof(struct net_device, ifindex);
+				emit_load(r_A, r_s0, off, ctx);
+			} else { /* (code == (BPF_ANC | SKF_AD_HATYPE) */
+				BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2);
+				off = offsetof(struct net_device, type);
+				emit_half_load_unsigned(r_A, r_s0, off, ctx);
+			}
+			break;
+		case BPF_ANC | SKF_AD_MARK:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4);
+			off = offsetof(struct sk_buff, mark);
+			emit_load(r_A, r_skb, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_RXHASH:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4);
+			off = offsetof(struct sk_buff, hash);
+			emit_load(r_A, r_skb, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_VLAN_TAG:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(sizeof_field(struct sk_buff,
+						  vlan_tci) != 2);
+			off = offsetof(struct sk_buff, vlan_tci);
+			emit_half_load_unsigned(r_A, r_skb, off, ctx);
+			break;
+		case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			emit_load_byte(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET(), ctx);
+			if (PKT_VLAN_PRESENT_BIT)
+				emit_srl(r_A, r_A, PKT_VLAN_PRESENT_BIT, ctx);
+			if (PKT_VLAN_PRESENT_BIT < 7)
+				emit_andi(r_A, r_A, 1, ctx);
+			break;
+		case BPF_ANC | SKF_AD_PKTTYPE:
+			ctx->flags |= SEEN_SKB;
+
+			emit_load_byte(r_tmp, r_skb, PKT_TYPE_OFFSET(), ctx);
+			/* Keep only the last 3 bits */
+			emit_andi(r_A, r_tmp, PKT_TYPE_MAX, ctx);
+#ifdef __BIG_ENDIAN_BITFIELD
+			/* Get the actual packet type to the lower 3 bits */
+			emit_srl(r_A, r_A, 5, ctx);
+#endif
+			break;
+		case BPF_ANC | SKF_AD_QUEUE:
+			ctx->flags |= SEEN_SKB | SEEN_A;
+			BUILD_BUG_ON(sizeof_field(struct sk_buff,
+						  queue_mapping) != 2);
+			BUILD_BUG_ON(offsetof(struct sk_buff,
+					      queue_mapping) > 0xff);
+			off = offsetof(struct sk_buff, queue_mapping);
+			emit_half_load_unsigned(r_A, r_skb, off, ctx);
+			break;
+		default:
+			pr_debug("%s: Unhandled opcode: 0x%02x\n", __FILE__,
+				 inst->code);
+			return -1;
+		}
+	}
+
+	/* compute offsets only during the first pass */
+	if (ctx->target == NULL)
+		ctx->offsets[i] = ctx->idx * 4;
+
+	return 0;
+}
+
+void bpf_jit_compile(struct bpf_prog *fp)
+{
+	struct jit_ctx ctx;
+	unsigned int alloc_size, tmp_idx;
+
+	if (!bpf_jit_enable)
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	ctx.offsets = kcalloc(fp->len + 1, sizeof(*ctx.offsets), GFP_KERNEL);
+	if (ctx.offsets == NULL)
+		return;
+
+	ctx.skf = fp;
+
+	if (build_body(&ctx))
+		goto out;
+
+	tmp_idx = ctx.idx;
+	build_prologue(&ctx);
+	ctx.prologue_bytes = (ctx.idx - tmp_idx) * 4;
+	/* just to complete the ctx.idx count */
+	build_epilogue(&ctx);
+
+	alloc_size = 4 * ctx.idx;
+	ctx.target = module_alloc(alloc_size);
+	if (ctx.target == NULL)
+		goto out;
+
+	/* Clean it */
+	memset(ctx.target, 0, alloc_size);
+
+	ctx.idx = 0;
+
+	/* Generate the actual JIT code */
+	build_prologue(&ctx);
+	build_body(&ctx);
+	build_epilogue(&ctx);
+
+	/* Update the icache */
+	flush_icache_range((ptr)ctx.target, (ptr)(ctx.target + ctx.idx));
+
+	if (bpf_jit_enable > 1)
+		/* Dump JIT code */
+		bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
+
+	fp->bpf_func = (void *)ctx.target;
+	fp->jited = 1;
+
+out:
+	kfree(ctx.offsets);
+}
+
+void bpf_jit_free(struct bpf_prog *fp)
+{
+	if (fp->jited)
+		module_memfree(fp->bpf_func);
+
+	bpf_prog_unlock_free(fp);
+}
diff --git a/arch/mips/net/bpf_jit_asm.S b/arch/mips/net/bpf_jit_asm.S
new file mode 100644
index 000000000000..57154c5883b6
--- /dev/null
+++ b/arch/mips/net/bpf_jit_asm.S
@@ -0,0 +1,285 @@
+/*
+ * bpf_jib_asm.S: Packet/header access helper functions for MIPS/MIPS64 BPF
+ * compiler.
+ *
+ * Copyright (C) 2015 Imagination Technologies Ltd.
+ * Author: Markos Chandras <markos.chandras@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; version 2 of the License.
+ */
+
+#include <asm/asm.h>
+#include <asm/isa-rev.h>
+#include <asm/regdef.h>
+#include "bpf_jit.h"
+
+/* ABI
+ *
+ * r_skb_hl	skb header length
+ * r_skb_data	skb data
+ * r_off(a1)	offset register
+ * r_A		BPF register A
+ * r_X		PF register X
+ * r_skb(a0)	*skb
+ * r_M		*scratch memory
+ * r_skb_le	skb length
+ * r_s0		Scratch register 0
+ * r_s1		Scratch register 1
+ *
+ * On entry:
+ * a0: *skb
+ * a1: offset (imm or imm + X)
+ *
+ * All non-BPF-ABI registers are free for use. On return, we only
+ * care about r_ret. The BPF-ABI registers are assumed to remain
+ * unmodified during the entire filter operation.
+ */
+
+#define skb	a0
+#define offset	a1
+#define SKF_LL_OFF  (-0x200000) /* Can't include linux/filter.h in assembly */
+
+	/* We know better :) so prevent assembler reordering etc */
+	.set 	noreorder
+
+#define is_offset_negative(TYPE)				\
+	/* If offset is negative we have more work to do */	\
+	slti	t0, offset, 0;					\
+	bgtz	t0, bpf_slow_path_##TYPE##_neg;			\
+	/* Be careful what follows in DS. */
+
+#define is_offset_in_header(SIZE, TYPE)				\
+	/* Reading from header? */				\
+	addiu	$r_s0, $r_skb_hl, -SIZE;			\
+	slt	t0, $r_s0, offset;				\
+	bgtz	t0, bpf_slow_path_##TYPE;			\
+
+LEAF(sk_load_word)
+	is_offset_negative(word)
+FEXPORT(sk_load_word_positive)
+	is_offset_in_header(4, word)
+	/* Offset within header boundaries */
+	PTR_ADDU t1, $r_skb_data, offset
+	.set	reorder
+	lw	$r_A, 0(t1)
+	.set	noreorder
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if MIPS_ISA_REV >= 2
+	wsbh	t0, $r_A
+	rotr	$r_A, t0, 16
+# else
+	sll	t0, $r_A, 24
+	srl	t1, $r_A, 24
+	srl	t2, $r_A, 8
+	or	t0, t0, t1
+	andi	t2, t2, 0xff00
+	andi	t1, $r_A, 0xff00
+	or	t0, t0, t2
+	sll	t1, t1, 8
+	or	$r_A, t0, t1
+# endif
+#endif
+	jr	$r_ra
+	 move	$r_ret, zero
+	END(sk_load_word)
+
+LEAF(sk_load_half)
+	is_offset_negative(half)
+FEXPORT(sk_load_half_positive)
+	is_offset_in_header(2, half)
+	/* Offset within header boundaries */
+	PTR_ADDU t1, $r_skb_data, offset
+	lhu	$r_A, 0(t1)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if MIPS_ISA_REV >= 2
+	wsbh	$r_A, $r_A
+# else
+	sll	t0, $r_A, 8
+	srl	t1, $r_A, 8
+	andi	t0, t0, 0xff00
+	or	$r_A, t0, t1
+# endif
+#endif
+	jr	$r_ra
+	 move	$r_ret, zero
+	END(sk_load_half)
+
+LEAF(sk_load_byte)
+	is_offset_negative(byte)
+FEXPORT(sk_load_byte_positive)
+	is_offset_in_header(1, byte)
+	/* Offset within header boundaries */
+	PTR_ADDU t1, $r_skb_data, offset
+	lbu	$r_A, 0(t1)
+	jr	$r_ra
+	 move	$r_ret, zero
+	END(sk_load_byte)
+
+/*
+ * call skb_copy_bits:
+ * (prototype in linux/skbuff.h)
+ *
+ * int skb_copy_bits(sk_buff *skb, int offset, void *to, int len)
+ *
+ * o32 mandates we leave 4 spaces for argument registers in case
+ * the callee needs to use them. Even though we don't care about
+ * the argument registers ourselves, we need to allocate that space
+ * to remain ABI compliant since the callee may want to use that space.
+ * We also allocate 2 more spaces for $r_ra and our return register (*to).
+ *
+ * n64 is a bit different. The *caller* will allocate the space to preserve
+ * the arguments. So in 64-bit kernels, we allocate the 4-arg space for no
+ * good reason but it does not matter that much really.
+ *
+ * (void *to) is returned in r_s0
+ *
+ */
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define DS_OFFSET(SIZE) (4 * SZREG)
+#else
+#define DS_OFFSET(SIZE) ((4 * SZREG) + (4 - SIZE))
+#endif
+#define bpf_slow_path_common(SIZE)				\
+	/* Quick check. Are we within reasonable boundaries? */ \
+	LONG_ADDIU	$r_s1, $r_skb_len, -SIZE;		\
+	sltu		$r_s0, offset, $r_s1;			\
+	beqz		$r_s0, fault;				\
+	/* Load 4th argument in DS */				\
+	 LONG_ADDIU	a3, zero, SIZE;				\
+	PTR_ADDIU	$r_sp, $r_sp, -(6 * SZREG);		\
+	PTR_LA		t0, skb_copy_bits;			\
+	PTR_S		$r_ra, (5 * SZREG)($r_sp);		\
+	/* Assign low slot to a2 */				\
+	PTR_ADDIU	a2, $r_sp, DS_OFFSET(SIZE);		\
+	jalr		t0;					\
+	/* Reset our destination slot (DS but it's ok) */	\
+	 INT_S		zero, (4 * SZREG)($r_sp);		\
+	/*							\
+	 * skb_copy_bits returns 0 on success and -EFAULT	\
+	 * on error. Our data live in a2. Do not bother with	\
+	 * our data if an error has been returned.		\
+	 */							\
+	/* Restore our frame */					\
+	PTR_L		$r_ra, (5 * SZREG)($r_sp);		\
+	INT_L		$r_s0, (4 * SZREG)($r_sp);		\
+	bltz		v0, fault;				\
+	 PTR_ADDIU	$r_sp, $r_sp, 6 * SZREG;		\
+	move		$r_ret, zero;				\
+
+NESTED(bpf_slow_path_word, (6 * SZREG), $r_sp)
+	bpf_slow_path_common(4)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if MIPS_ISA_REV >= 2
+	wsbh	t0, $r_s0
+	jr	$r_ra
+	 rotr	$r_A, t0, 16
+# else
+	sll	t0, $r_s0, 24
+	srl	t1, $r_s0, 24
+	srl	t2, $r_s0, 8
+	or	t0, t0, t1
+	andi	t2, t2, 0xff00
+	andi	t1, $r_s0, 0xff00
+	or	t0, t0, t2
+	sll	t1, t1, 8
+	jr	$r_ra
+	 or	$r_A, t0, t1
+# endif
+#else
+	jr	$r_ra
+	 move	$r_A, $r_s0
+#endif
+
+	END(bpf_slow_path_word)
+
+NESTED(bpf_slow_path_half, (6 * SZREG), $r_sp)
+	bpf_slow_path_common(2)
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if MIPS_ISA_REV >= 2
+	jr	$r_ra
+	 wsbh	$r_A, $r_s0
+# else
+	sll	t0, $r_s0, 8
+	andi	t1, $r_s0, 0xff00
+	andi	t0, t0, 0xff00
+	srl	t1, t1, 8
+	jr	$r_ra
+	 or	$r_A, t0, t1
+# endif
+#else
+	jr	$r_ra
+	 move	$r_A, $r_s0
+#endif
+
+	END(bpf_slow_path_half)
+
+NESTED(bpf_slow_path_byte, (6 * SZREG), $r_sp)
+	bpf_slow_path_common(1)
+	jr	$r_ra
+	 move	$r_A, $r_s0
+
+	END(bpf_slow_path_byte)
+
+/*
+ * Negative entry points
+ */
+	.macro bpf_is_end_of_data
+	li	t0, SKF_LL_OFF
+	/* Reading link layer data? */
+	slt	t1, offset, t0
+	bgtz	t1, fault
+	/* Be careful what follows in DS. */
+	.endm
+/*
+ * call skb_copy_bits:
+ * (prototype in linux/filter.h)
+ *
+ * void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb,
+ *                                            int k, unsigned int size)
+ *
+ * see above (bpf_slow_path_common) for ABI restrictions
+ */
+#define bpf_negative_common(SIZE)					\
+	PTR_ADDIU	$r_sp, $r_sp, -(6 * SZREG);			\
+	PTR_LA		t0, bpf_internal_load_pointer_neg_helper;	\
+	PTR_S		$r_ra, (5 * SZREG)($r_sp);			\
+	jalr		t0;						\
+	 li		a2, SIZE;					\
+	PTR_L		$r_ra, (5 * SZREG)($r_sp);			\
+	/* Check return pointer */					\
+	beqz		v0, fault;					\
+	 PTR_ADDIU	$r_sp, $r_sp, 6 * SZREG;			\
+	/* Preserve our pointer */					\
+	move		$r_s0, v0;					\
+	/* Set return value */						\
+	move		$r_ret, zero;					\
+
+bpf_slow_path_word_neg:
+	bpf_is_end_of_data
+NESTED(sk_load_word_negative, (6 * SZREG), $r_sp)
+	bpf_negative_common(4)
+	jr	$r_ra
+	 lw	$r_A, 0($r_s0)
+	END(sk_load_word_negative)
+
+bpf_slow_path_half_neg:
+	bpf_is_end_of_data
+NESTED(sk_load_half_negative, (6 * SZREG), $r_sp)
+	bpf_negative_common(2)
+	jr	$r_ra
+	 lhu	$r_A, 0($r_s0)
+	END(sk_load_half_negative)
+
+bpf_slow_path_byte_neg:
+	bpf_is_end_of_data
+NESTED(sk_load_byte_negative, (6 * SZREG), $r_sp)
+	bpf_negative_common(1)
+	jr	$r_ra
+	 lbu	$r_A, 0($r_s0)
+	END(sk_load_byte_negative)
+
+fault:
+	jr	$r_ra
+	 addiu $r_ret, zero, 1
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index 8e26b120f994..d85cbf84e41c 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -10,7 +10,7 @@
 #include <asm/sn/addrs.h>
 #include <asm/sn/types.h>
 #include <asm/sn/klconfig.h>
-#include <asm/sn/hub.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/ioc3.h>
 #include <asm/pci/bridge.h>
 
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 5c1a196be0c5..3b2552fb7735 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -437,17 +437,28 @@ static int bridge_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	struct irq_alloc_info info;
 	int irq;
 
-	irq = bc->pci_int[slot];
+	switch (pin) {
+	case PCI_INTERRUPT_UNKNOWN:
+	case PCI_INTERRUPT_INTA:
+	case PCI_INTERRUPT_INTC:
+		pin = 0;
+		break;
+	case PCI_INTERRUPT_INTB:
+	case PCI_INTERRUPT_INTD:
+		pin = 1;
+	}
+
+	irq = bc->pci_int[slot][pin];
 	if (irq == -1) {
 		info.ctrl = bc;
 		info.nasid = bc->nasid;
-		info.pin = slot;
+		info.pin = bc->int_mapping[slot][pin];
 
 		irq = irq_domain_alloc_irqs(bc->domain, 1, bc->nasid, &info);
 		if (irq < 0)
 			return irq;
 
-		bc->pci_int[slot] = irq;
+		bc->pci_int[slot][pin] = irq;
 	}
 	return irq;
 }
@@ -458,21 +469,26 @@ static void bridge_setup_ip27_baseio6g(struct bridge_controller *bc)
 {
 	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP27_BASEIO6G);
 	bc->ioc3_sid[6] = IOC3_SID(IOC3_SUBSYS_IP27_MIO);
+	bc->int_mapping[2][1] = 4;
+	bc->int_mapping[6][1] = 6;
 }
 
 static void bridge_setup_ip27_baseio(struct bridge_controller *bc)
 {
 	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP27_BASEIO);
+	bc->int_mapping[2][1] = 4;
 }
 
 static void bridge_setup_ip29_baseio(struct bridge_controller *bc)
 {
 	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP29_SYSBOARD);
+	bc->int_mapping[2][1] = 3;
 }
 
 static void bridge_setup_ip30_sysboard(struct bridge_controller *bc)
 {
 	bc->ioc3_sid[2] = IOC3_SID(IOC3_SUBSYS_IP30_SYSBOARD);
+	bc->int_mapping[2][1] = 4;
 }
 
 static void bridge_setup_menet(struct bridge_controller *bc)
@@ -483,6 +499,26 @@ static void bridge_setup_menet(struct bridge_controller *bc)
 	bc->ioc3_sid[3] = IOC3_SID(IOC3_SUBSYS_MENET4);
 }
 
+static void bridge_setup_io7(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[4] = IOC3_SID(IOC3_SUBSYS_IO7);
+}
+
+static void bridge_setup_io8(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[4] = IOC3_SID(IOC3_SUBSYS_IO8);
+}
+
+static void bridge_setup_io9(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[1] = IOC3_SID(IOC3_SUBSYS_IO9);
+}
+
+static void bridge_setup_ip34_fuel_sysboard(struct bridge_controller *bc)
+{
+	bc->ioc3_sid[4] = IOC3_SID(IOC3_SUBSYS_IP34_SYSBOARD);
+}
+
 #define BRIDGE_BOARD_SETUP(_partno, _setup)	\
 	{ .match = _partno, .setup = _setup }
 
@@ -500,6 +536,10 @@ static const struct {
 	BRIDGE_BOARD_SETUP("030-0887-", bridge_setup_ip30_sysboard),
 	BRIDGE_BOARD_SETUP("030-1467-", bridge_setup_ip30_sysboard),
 	BRIDGE_BOARD_SETUP("030-0873-", bridge_setup_menet),
+	BRIDGE_BOARD_SETUP("030-1557-", bridge_setup_io7),
+	BRIDGE_BOARD_SETUP("030-1673-", bridge_setup_io8),
+	BRIDGE_BOARD_SETUP("030-1771-", bridge_setup_io9),
+	BRIDGE_BOARD_SETUP("030-1707-", bridge_setup_ip34_fuel_sysboard),
 };
 
 static void bridge_setup_board(struct bridge_controller *bc, char *partnum)
@@ -655,7 +695,11 @@ static int bridge_probe(struct platform_device *pdev)
 
 	for (slot = 0; slot < 8; slot++) {
 		bridge_set(bc, b_device[slot].reg, BRIDGE_DEV_SWAP_DIR);
-		bc->pci_int[slot] = -1;
+		bc->pci_int[slot][0] = -1;
+		bc->pci_int[slot][1] = -1;
+		/* default interrupt pin mapping */
+		bc->int_mapping[slot][0] = slot;
+		bc->int_mapping[slot][1] = slot ^ 4;
 	}
 	bridge_read(bc, b_wid_tflush);	  /* wait until Bridge PIO complete */
 
diff --git a/arch/mips/ralink/ill_acc.c b/arch/mips/ralink/ill_acc.c
index 0ddeb31afa93..bdf53807d7c2 100644
--- a/arch/mips/ralink/ill_acc.c
+++ b/arch/mips/ralink/ill_acc.c
@@ -67,11 +67,13 @@ static int __init ill_acc_of_setup(void)
 	irq = irq_of_parse_and_map(np, 0);
 	if (!irq) {
 		dev_err(&pdev->dev, "failed to get irq\n");
+		put_device(&pdev->dev);
 		return -EINVAL;
 	}
 
 	if (request_irq(irq, ill_acc_irq_handler, 0, "ill_acc", &pdev->dev)) {
 		dev_err(&pdev->dev, "failed to request irq\n");
+		put_device(&pdev->dev);
 		return -EINVAL;
 	}
 
diff --git a/arch/mips/sgi-ip22/ip22-gio.c b/arch/mips/sgi-ip22/ip22-gio.c
index 282b47c2dc27..de0768a49ee8 100644
--- a/arch/mips/sgi-ip22/ip22-gio.c
+++ b/arch/mips/sgi-ip22/ip22-gio.c
@@ -47,8 +47,9 @@ static struct device gio_bus = {
  * Used by a driver to check whether an of_device present in the
  * system is in its list of supported devices.
  */
-const struct gio_device_id *gio_match_device(const struct gio_device_id *match,
-		     const struct gio_device *dev)
+static const struct gio_device_id *
+gio_match_device(const struct gio_device_id *match,
+		 const struct gio_device *dev)
 {
 	const struct gio_device_id *ids;
 
@@ -58,7 +59,6 @@ const struct gio_device_id *gio_match_device(const struct gio_device_id *match,
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(gio_match_device);
 
 struct gio_device *gio_dev_get(struct gio_device *dev)
 {
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index 73ad29b180fb..5a38ae6bdfa9 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -16,8 +16,8 @@
 
 #include <asm/ptrace.h>
 #include <asm/sn/addrs.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/arch.h>
-#include <asm/sn/sn0/hub.h>
 #include <asm/tlbdebug.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
@@ -30,29 +30,31 @@ static void dump_hub_information(unsigned long errst0, unsigned long errst1)
 		{ "WERR", "Uncached Partial Write", "PWERR", "Write Timeout",
 		  NULL, NULL, NULL, NULL }
 	};
-	int wrb = errst1 & PI_ERR_ST1_WRBRRB_MASK;
+	union pi_err_stat0 st0;
+	union pi_err_stat1 st1;
 
-	if (!(errst0 & PI_ERR_ST0_VALID_MASK)) {
-		printk("Hub does not contain valid error information\n");
+	st0.pi_stat0_word = errst0;
+	st1.pi_stat1_word = errst1;
+
+	if (!st0.pi_stat0_fmt.s0_valid) {
+		pr_info("Hub does not contain valid error information\n");
 		return;
 	}
 
-
-	printk("Hub has valid error information:\n");
-	if (errst0 & PI_ERR_ST0_OVERRUN_MASK)
-		printk("Overrun is set.	 Error stack may contain additional "
+	pr_info("Hub has valid error information:\n");
+	if (st0.pi_stat0_fmt.s0_ovr_run)
+		pr_info("Overrun is set. Error stack may contain additional "
 		       "information.\n");
-	printk("Hub error address is %08lx\n",
-	       (errst0 & PI_ERR_ST0_ADDR_MASK) >> (PI_ERR_ST0_ADDR_SHFT - 3));
-	printk("Incoming message command 0x%lx\n",
-	       (errst0 & PI_ERR_ST0_CMD_MASK) >> PI_ERR_ST0_CMD_SHFT);
-	printk("Supplemental field of incoming message is 0x%lx\n",
-	       (errst0 & PI_ERR_ST0_SUPPL_MASK) >> PI_ERR_ST0_SUPPL_SHFT);
-	printk("T5 Rn (for RRB only) is 0x%lx\n",
-	       (errst0 & PI_ERR_ST0_REQNUM_MASK) >> PI_ERR_ST0_REQNUM_SHFT);
-	printk("Error type is %s\n", err_type[wrb]
-	       [(errst0 & PI_ERR_ST0_TYPE_MASK) >> PI_ERR_ST0_TYPE_SHFT]
-		? : "invalid");
+	pr_info("Hub error address is %08lx\n",
+		(unsigned long)st0.pi_stat0_fmt.s0_addr);
+	pr_info("Incoming message command 0x%lx\n",
+		(unsigned long)st0.pi_stat0_fmt.s0_cmd);
+	pr_info("Supplemental field of incoming message is 0x%lx\n",
+		(unsigned long)st0.pi_stat0_fmt.s0_supl);
+	pr_info("T5 Rn (for RRB only) is 0x%lx\n",
+		(unsigned long)st0.pi_stat0_fmt.s0_t5_req);
+	pr_info("Error type is %s\n", err_type[st1.pi_stat1_fmt.s1_rw_rb]
+	       [st0.pi_stat0_fmt.s0_err_type] ? : "invalid");
 }
 
 int ip27_be_handler(struct pt_regs *regs, int is_fixup)
diff --git a/arch/mips/sgi-ip27/ip27-common.h b/arch/mips/sgi-ip27/ip27-common.h
index 3ffbcf9bfd41..ed008a08464c 100644
--- a/arch/mips/sgi-ip27/ip27-common.h
+++ b/arch/mips/sgi-ip27/ip27-common.h
@@ -3,8 +3,18 @@
 #ifndef __IP27_COMMON_H
 #define __IP27_COMMON_H
 
-extern void ip27_reboot_setup(void);
+extern nasid_t master_nasid;
+
+extern void cpu_node_probe(void);
 extern void hub_rt_clock_event_init(void);
+extern void hub_rtc_init(nasid_t nasid);
+extern void install_cpu_nmi_handler(int slice);
+extern void install_ipi(void);
+extern void ip27_reboot_setup(void);
 extern const struct plat_smp_ops ip27_smp_ops;
+extern unsigned long node_getfirstfree(nasid_t nasid);
+extern void per_cpu_init(void);
+extern void replicate_kernel_text(void);
+extern void setup_replication_mask(void);
 
 #endif /* __IP27_COMMON_H */
diff --git a/arch/mips/sgi-ip27/ip27-console.c b/arch/mips/sgi-ip27/ip27-console.c
index 5886bee89d06..7737a88c6569 100644
--- a/arch/mips/sgi-ip27/ip27-console.c
+++ b/arch/mips/sgi-ip27/ip27-console.c
@@ -9,14 +9,15 @@
 #include <asm/page.h>
 #include <asm/setup.h>
 #include <asm/sn/addrs.h>
-#include <asm/sn/sn0/hub.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/klconfig.h>
 #include <asm/sn/ioc3.h>
-#include <asm/sn/sn_private.h>
 
 #include <linux/serial.h>
 #include <linux/serial_core.h>
 
+#include "ip27-common.h"
+
 #define IOC3_CLK	(22000000 / 3)
 #define IOC3_FLAGS	(0)
 
diff --git a/arch/mips/sgi-ip27/ip27-hubio.c b/arch/mips/sgi-ip27/ip27-hubio.c
index a538d0ceb61d..8352eb6403b4 100644
--- a/arch/mips/sgi-ip27/ip27-hubio.c
+++ b/arch/mips/sgi-ip27/ip27-hubio.c
@@ -11,7 +11,9 @@
 #include <linux/mmzone.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
-#include <asm/sn/hub.h>
+#include <asm/sn/agent.h>
+#include <asm/sn/io.h>
+#include <asm/xtalk/xtalk.h>
 
 
 static int force_fire_and_forget = 1;
@@ -82,7 +84,7 @@ unsigned long hub_pio_map(nasid_t nasid, xwidgetnum_t widget,
  */
 static void hub_setup_prb(nasid_t nasid, int prbnum, int credits)
 {
-	iprb_t prb;
+	union iprb_u prb;
 	int prb_offset;
 
 	/*
@@ -135,7 +137,7 @@ static void hub_setup_prb(nasid_t nasid, int prbnum, int credits)
 static void hub_set_piomode(nasid_t nasid)
 {
 	u64 ii_iowa;
-	hubii_wcr_t ii_wcr;
+	union hubii_wcr_u ii_wcr;
 	unsigned i;
 
 	ii_iowa = REMOTE_HUB_L(nasid, IIO_OUTWIDGET_ACCESS);
diff --git a/arch/mips/sgi-ip27/ip27-init.c b/arch/mips/sgi-ip27/ip27-init.c
index f597e1ee2df7..32bcb8d1dd88 100644
--- a/arch/mips/sgi-ip27/ip27-init.c
+++ b/arch/mips/sgi-ip27/ip27-init.c
@@ -19,23 +19,18 @@
 #include <asm/pgtable.h>
 #include <asm/sgialib.h>
 #include <asm/time.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/types.h>
-#include <asm/sn/sn0/addrs.h>
-#include <asm/sn/sn0/hubni.h>
-#include <asm/sn/sn0/hubio.h>
 #include <asm/sn/klconfig.h>
 #include <asm/sn/ioc3.h>
 #include <asm/mipsregs.h>
 #include <asm/sn/gda.h>
-#include <asm/sn/hub.h>
 #include <asm/sn/intr.h>
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/mmu_context.h>
 #include <asm/thread_info.h>
 #include <asm/sn/launch.h>
-#include <asm/sn/sn_private.h>
-#include <asm/sn/sn0/ip27.h>
 #include <asm/sn/mapped_kernel.h>
 
 #include "ip27-common.h"
@@ -77,18 +72,14 @@ static void per_hub_init(nasid_t nasid)
 void per_cpu_init(void)
 {
 	int cpu = smp_processor_id();
-	int slice = LOCAL_HUB_L(PI_CPU_NUM);
 	nasid_t nasid = get_nasid();
-	struct hub_data *hub = hub_data(nasid);
-
-	if (test_and_set_bit(slice, &hub->slice_map))
-		return;
 
 	clear_c0_status(ST0_IM);
 
 	per_hub_init(nasid);
 
-	cpu_time_init();
+	pr_info("CPU %d clock is %dMHz.\n", cpu, sn_cpu_info[cpu].p_speed);
+
 	install_ipi();
 
 	/* Install our NMI handler if symmon hasn't installed one. */
@@ -98,16 +89,6 @@ void per_cpu_init(void)
 	enable_percpu_irq(IP27_HUB_PEND1_IRQ, IRQ_TYPE_NONE);
 }
 
-/*
- * get_nasid() returns the physical node id number of the caller.
- */
-nasid_t
-get_nasid(void)
-{
-	return (nasid_t)((LOCAL_HUB_L(NI_STATUS_REV_ID) & NSRI_NODEID_MASK)
-			 >> NSRI_NODEID_SHFT);
-}
-
 void __init plat_mem_setup(void)
 {
 	u64 p, e, n_mode;
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index c72ae330ea93..42df9fafa943 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -19,7 +19,6 @@
 #include <asm/sn/addrs.h>
 #include <asm/sn/agent.h>
 #include <asm/sn/arch.h>
-#include <asm/sn/hub.h>
 #include <asm/sn/intr.h>
 #include <asm/sn/irq_alloc.h>
 
@@ -288,11 +287,9 @@ void __init arch_init_irq(void)
 	 * Mark these as reserved right away so they won't be used accidentally
 	 * later.
 	 */
-	for (i = 0; i <= BASE_PCI_IRQ; i++)
+	for (i = 0; i <= CPU_CALL_B_IRQ; i++)
 		set_bit(i, hub_irq_map);
 
-	set_bit(IP_PEND0_6_63, hub_irq_map);
-
 	for (i = NI_BRDCAST_ERR_A; i <= MSC_PANIC_INTR; i++)
 		set_bit(i, hub_irq_map);
 
diff --git a/arch/mips/sgi-ip27/ip27-klconfig.c b/arch/mips/sgi-ip27/ip27-klconfig.c
index 6cb2160e7689..81a1646e609a 100644
--- a/arch/mips/sgi-ip27/ip27-klconfig.c
+++ b/arch/mips/sgi-ip27/ip27-klconfig.c
@@ -72,54 +72,3 @@ lboard_t *find_lboard_class(lboard_t *start, unsigned char brd_type)
 	/* Didn't find it. */
 	return (lboard_t *)NULL;
 }
-
-klcpu_t *nasid_slice_to_cpuinfo(nasid_t nasid, int slice)
-{
-	lboard_t *brd;
-	klcpu_t *acpu;
-
-	if (!(brd = find_lboard((lboard_t *)KL_CONFIG_INFO(nasid), KLTYPE_IP27)))
-		return (klcpu_t *)NULL;
-
-	if (!(acpu = (klcpu_t *)find_first_component(brd, KLSTRUCT_CPU)))
-		return (klcpu_t *)NULL;
-
-	do {
-		if ((acpu->cpu_info.physid) == slice)
-			return acpu;
-	} while ((acpu = (klcpu_t *)find_component(brd, (klinfo_t *)acpu,
-								KLSTRUCT_CPU)));
-	return (klcpu_t *)NULL;
-}
-
-klcpu_t *sn_get_cpuinfo(cpuid_t cpu)
-{
-	nasid_t nasid;
-	int slice;
-	klcpu_t *acpu;
-
-	if (!(cpu < MAXCPUS)) {
-		printk("sn_get_cpuinfo: illegal cpuid 0x%lx\n", cpu);
-		return NULL;
-	}
-
-	nasid = cputonasid(cpu);
-	if (nasid  == INVALID_NASID)
-		return NULL;
-
-	for (slice = 0; slice < CPUS_PER_NODE; slice++) {
-		acpu = nasid_slice_to_cpuinfo(nasid, slice);
-		if (acpu && acpu->cpu_info.virtid == cpu)
-			return acpu;
-	}
-	return NULL;
-}
-
-int get_cpu_slice(cpuid_t cpu)
-{
-	klcpu_t *acpu;
-
-	if ((acpu = sn_get_cpuinfo(cpu)) == NULL)
-		return -1;
-	return acpu->cpu_info.physid;
-}
diff --git a/arch/mips/sgi-ip27/ip27-klnuma.c b/arch/mips/sgi-ip27/ip27-klnuma.c
index ee1c6ff4aa00..abd7a84df7dd 100644
--- a/arch/mips/sgi-ip27/ip27-klnuma.c
+++ b/arch/mips/sgi-ip27/ip27-klnuma.c
@@ -16,11 +16,11 @@
 #include <asm/sn/types.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
-#include <asm/sn/hub.h>
 #include <asm/sn/mapped_kernel.h>
-#include <asm/sn/sn_private.h>
 
-static cpumask_t ktext_repmask;
+#include "ip27-common.h"
+
+static nodemask_t ktext_repmask;
 
 /*
  * XXX - This needs to be much smarter about where it puts copies of the
@@ -30,8 +30,8 @@ static cpumask_t ktext_repmask;
 void __init setup_replication_mask(void)
 {
 	/* Set only the master cnode's bit.  The master cnode is always 0. */
-	cpumask_clear(&ktext_repmask);
-	cpumask_set_cpu(0, &ktext_repmask);
+	nodes_clear(ktext_repmask);
+	node_set(0, ktext_repmask);
 
 #ifdef CONFIG_REPLICATE_KTEXT
 #ifndef CONFIG_MAPPED_KERNEL
@@ -44,7 +44,7 @@ void __init setup_replication_mask(void)
 			if (nasid == 0)
 				continue;
 			/* Advertise that we have a copy of the kernel */
-			cpumask_set_cpu(nasid, &ktext_repmask);
+			node_set(nasid, ktext_repmask);
 		}
 	}
 #endif
@@ -98,7 +98,7 @@ void __init replicate_kernel_text(void)
 			continue;
 
 		/* Check if this node should get a copy of the kernel */
-		if (cpumask_test_cpu(client_nasid, &ktext_repmask)) {
+		if (node_isset(client_nasid, ktext_repmask)) {
 			server_nasid = client_nasid;
 			copy_kernel(server_nasid);
 		}
@@ -122,7 +122,7 @@ unsigned long node_getfirstfree(nasid_t nasid)
 	loadbase += 16777216;
 #endif
 	offset = PAGE_ALIGN((unsigned long)(&_end)) - loadbase;
-	if ((nasid == 0) || (cpumask_test_cpu(nasid, &ktext_repmask)))
+	if ((nasid == 0) || (node_isset(nasid, ktext_repmask)))
 		return TO_NODE(nasid, offset) >> PAGE_SHIFT;
 	else
 		return KDM_TO_PHYS(PAGE_ALIGN(SYMMON_STK_ADDR(nasid, 0))) >> PAGE_SHIFT;
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index 563aad5e6398..a45691e6ab90 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -25,10 +25,10 @@
 #include <asm/sections.h>
 
 #include <asm/sn/arch.h>
-#include <asm/sn/hub.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/klconfig.h>
-#include <asm/sn/sn_private.h>
 
+#include "ip27-common.h"
 
 #define SLOT_PFNSHIFT		(SLOT_SHIFT - PAGE_SHIFT)
 #define PFN_NASIDSHFT		(NASID_SHFT - PAGE_SHIFT)
@@ -37,31 +37,18 @@ struct node_data *__node_data[MAX_NUMNODES];
 
 EXPORT_SYMBOL(__node_data);
 
-static int fine_mode;
-
-static int is_fine_dirmode(void)
-{
-	return ((LOCAL_HUB_L(NI_STATUS_REV_ID) & NSRI_REGIONSIZE_MASK) >> NSRI_REGIONSIZE_SHFT) & REGIONSIZE_FINE;
-}
-
-static u64 get_region(nasid_t nasid)
-{
-	if (fine_mode)
-		return nasid >> NASID_TO_FINEREG_SHFT;
-	else
-		return nasid >> NASID_TO_COARSEREG_SHFT;
-}
-
-static u64 region_mask;
-
-static void gen_region_mask(u64 *region_mask)
+static u64 gen_region_mask(void)
 {
+	int region_shift;
+	u64 region_mask;
 	nasid_t nasid;
 
-	(*region_mask) = 0;
-	for_each_online_node(nasid) {
-		(*region_mask) |= 1ULL << get_region(nasid);
-	}
+	region_shift = get_region_shift();
+	region_mask = 0;
+	for_each_online_node(nasid)
+		region_mask |= BIT_ULL(nasid >> region_shift);
+
+	return region_mask;
 }
 
 #define rou_rflag	rou_flags
@@ -148,25 +135,25 @@ static int __init compute_node_distance(nasid_t nasid_a, nasid_t nasid_b)
 		} while ((brd = find_lboard_class(KLCF_NEXT(brd), KLTYPE_ROUTER)));
 	}
 
+	if (nasid_a == nasid_b)
+		return LOCAL_DISTANCE;
+
+	if (router_a == router_b)
+		return LOCAL_DISTANCE + 1;
+
 	if (router_a == NULL) {
 		pr_info("node_distance: router_a NULL\n");
-		return -1;
+		return 255;
 	}
 	if (router_b == NULL) {
 		pr_info("node_distance: router_b NULL\n");
-		return -1;
+		return 255;
 	}
 
-	if (nasid_a == nasid_b)
-		return 0;
-
-	if (router_a == router_b)
-		return 1;
-
 	router_distance = 100;
 	router_recurse(router_a, router_b, 2);
 
-	return router_distance;
+	return LOCAL_DISTANCE + router_distance;
 }
 
 static void __init init_topology_matrix(void)
@@ -281,10 +268,10 @@ static unsigned long __init slot_psize_compute(nasid_t nasid, int slot)
 
 static void __init mlreset(void)
 {
+	u64 region_mask;
 	nasid_t nasid;
 
 	master_nasid = get_nasid();
-	fine_mode = is_fine_dirmode();
 
 	/*
 	 * Probe for all CPUs - this creates the cpumask and sets up the
@@ -297,7 +284,7 @@ static void __init mlreset(void)
 	init_topology_matrix();
 	dump_topology();
 
-	gen_region_mask(&region_mask);
+	region_mask = gen_region_mask();
 
 	setup_replication_mask();
 
diff --git a/arch/mips/sgi-ip27/ip27-nmi.c b/arch/mips/sgi-ip27/ip27-nmi.c
index daf3670d94e7..84889b57d5ff 100644
--- a/arch/mips/sgi-ip27/ip27-nmi.c
+++ b/arch/mips/sgi-ip27/ip27-nmi.c
@@ -9,7 +9,7 @@
 #include <asm/sn/addrs.h>
 #include <asm/sn/nmi.h>
 #include <asm/sn/arch.h>
-#include <asm/sn/sn0/hub.h>
+#include <asm/sn/agent.h>
 
 #if 0
 #define NODE_NUM_CPUS(n)	CNODE_NUM_CPUS(n)
@@ -17,6 +17,9 @@
 #define NODE_NUM_CPUS(n)	CPUS_PER_NODE
 #endif
 
+#define SEND_NMI(_nasid, _slice)	\
+	REMOTE_HUB_S((_nasid),  (PI_NMI_A + ((_slice) * PI_NMI_OFFSET)), 1)
+
 typedef unsigned long machreg_t;
 
 static arch_spinlock_t nmi_lock = __ARCH_SPIN_LOCK_UNLOCKED;
diff --git a/arch/mips/sgi-ip27/ip27-reset.c b/arch/mips/sgi-ip27/ip27-reset.c
index 74d078247e49..5ac5ad638734 100644
--- a/arch/mips/sgi-ip27/ip27-reset.c
+++ b/arch/mips/sgi-ip27/ip27-reset.c
@@ -22,9 +22,9 @@
 #include <asm/reboot.h>
 #include <asm/sgialib.h>
 #include <asm/sn/addrs.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
-#include <asm/sn/sn0/hub.h>
 
 #include "ip27-common.h"
 
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index faa0244c8b0c..5d2652a1d35a 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -15,36 +15,22 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
+#include <asm/sn/agent.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
 #include <asm/sn/intr.h>
 #include <asm/sn/klconfig.h>
 #include <asm/sn/launch.h>
 #include <asm/sn/mapped_kernel.h>
-#include <asm/sn/sn_private.h>
 #include <asm/sn/types.h>
-#include <asm/sn/sn0/hubpi.h>
-#include <asm/sn/sn0/hubio.h>
-#include <asm/sn/sn0/ip27.h>
 
 #include "ip27-common.h"
 
-/*
- * Takes as first input the PROM assigned cpu id, and the kernel
- * assigned cpu id as the second.
- */
-static void alloc_cpupda(nasid_t nasid, cpuid_t cpu, int cpunum)
-{
-	cputonasid(cpunum) = nasid;
-	cputoslice(cpunum) = get_cpu_slice(cpu);
-}
-
-static int do_cpumask(nasid_t nasid, int highest)
+static int node_scan_cpus(nasid_t nasid, int highest)
 {
-	static int tot_cpus_found = 0;
+	static int cpus_found;
 	lboard_t *brd;
 	klcpu_t *acpu;
-	int cpus_found = 0;
 	cpuid_t cpuid;
 
 	brd = find_lboard((lboard_t *)KL_CONFIG_INFO(nasid), KLTYPE_IP27);
@@ -55,13 +41,15 @@ static int do_cpumask(nasid_t nasid, int highest)
 			cpuid = acpu->cpu_info.virtid;
 			/* Only let it join in if it's marked enabled */
 			if ((acpu->cpu_info.flags & KLINFO_ENABLE) &&
-			    (tot_cpus_found != NR_CPUS)) {
+			    (cpus_found != NR_CPUS)) {
 				if (cpuid > highest)
 					highest = cpuid;
 				set_cpu_possible(cpuid, true);
-				alloc_cpupda(nasid, cpuid, tot_cpus_found);
+				cputonasid(cpus_found) = nasid;
+				cputoslice(cpus_found) = acpu->cpu_info.physid;
+				sn_cpu_info[cpus_found].p_speed =
+							acpu->cpu_speed;
 				cpus_found++;
-				tot_cpus_found++;
 			}
 			acpu = (klcpu_t *)find_component(brd, (klinfo_t *)acpu,
 								KLSTRUCT_CPU);
@@ -87,7 +75,7 @@ void cpu_node_probe(void)
 		if (nasid == INVALID_NASID)
 			break;
 		node_set_online(nasid);
-		highest = do_cpumask(nasid, highest);
+		highest = node_scan_cpus(nasid, highest);
 	}
 
 	printk("Discovered %d cpus on %d nodes\n", highest + 1, num_online_nodes());
@@ -180,7 +168,8 @@ static void __init ip27_smp_setup(void)
 	/*
 	 * PROM sets up system, that boot cpu is always first CPU on nasid 0
 	 */
-	alloc_cpupda(0, 0, 0);
+	cputonasid(0) = 0;
+	cputoslice(0) = LOCAL_HUB_L(PI_CPU_NUM);
 }
 
 static void __init ip27_prepare_cpus(unsigned int max_cpus)
diff --git a/arch/mips/sgi-ip27/ip27-timer.c b/arch/mips/sgi-ip27/ip27-timer.c
index 17302bbfa7a6..61f3565f3645 100644
--- a/arch/mips/sgi-ip27/ip27-timer.c
+++ b/arch/mips/sgi-ip27/ip27-timer.c
@@ -25,17 +25,14 @@
 #include <asm/sn/klconfig.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/addrs.h>
-#include <asm/sn/sn_private.h>
-#include <asm/sn/sn0/ip27.h>
-#include <asm/sn/sn0/hub.h>
+#include <asm/sn/agent.h>
+
+#include "ip27-common.h"
 
 #define TICK_SIZE (tick_nsec / 1000)
 
 /* Includes for ioc3_init().  */
 #include <asm/sn/types.h>
-#include <asm/sn/sn0/addrs.h>
-#include <asm/sn/sn0/hubni.h>
-#include <asm/sn/sn0/hubio.h>
 #include <asm/pci/bridge.h>
 
 #include "ip27-common.h"
@@ -153,25 +150,6 @@ void __init plat_time_init(void)
 	hub_rt_clock_event_init();
 }
 
-void cpu_time_init(void)
-{
-	lboard_t *board;
-	klcpu_t *cpu;
-	int cpuid;
-
-	/* Don't use ARCS.  ARCS is fragile.  Klconfig is simple and sane.  */
-	board = find_lboard(KL_CONFIG_INFO(get_nasid()), KLTYPE_IP27);
-	if (!board)
-		panic("Can't find board info for myself.");
-
-	cpuid = LOCAL_HUB_L(PI_CPU_NUM) ? IP27_CPU0_INDEX : IP27_CPU1_INDEX;
-	cpu = (klcpu_t *) KLCF_COMP(board, cpuid);
-	if (!cpu)
-		panic("No information about myself?");
-
-	printk("CPU %d clock is %dMHz.\n", smp_processor_id(), cpu->cpu_speed);
-}
-
 void hub_rtc_init(nasid_t nasid)
 {
 
@@ -190,23 +168,3 @@ void hub_rtc_init(nasid_t nasid)
 		LOCAL_HUB_S(PI_RT_PEND_B, 0);
 	}
 }
-
-static int __init sgi_ip27_rtc_devinit(void)
-{
-	struct resource res;
-
-	memset(&res, 0, sizeof(res));
-	res.start = XPHYSADDR(KL_CONFIG_CH_CONS_INFO(master_nasid)->memory_base +
-			      IOC3_BYTEBUS_DEV0);
-	res.end = res.start + 32767;
-	res.flags = IORESOURCE_MEM;
-
-	return IS_ERR(platform_device_register_simple("rtc-m48t35", -1,
-						      &res, 1));
-}
-
-/*
- * kludge make this a device_initcall after ioc3 resource conflicts
- * are resolved
- */
-late_initcall(sgi_ip27_rtc_devinit);
diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c
index 5218b900f855..000ede156bdc 100644
--- a/arch/mips/sgi-ip27/ip27-xtalk.c
+++ b/arch/mips/sgi-ip27/ip27-xtalk.c
@@ -15,7 +15,6 @@
 #include <asm/sn/addrs.h>
 #include <asm/sn/types.h>
 #include <asm/sn/klconfig.h>
-#include <asm/sn/hub.h>
 #include <asm/pci/bridge.h>
 #include <asm/xtalk/xtalk.h>
 
diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c
index d46655b914f1..c2ffcb920250 100644
--- a/arch/mips/sgi-ip30/ip30-irq.c
+++ b/arch/mips/sgi-ip30/ip30-irq.c
@@ -232,9 +232,10 @@ static void heart_domain_free(struct irq_domain *domain,
 		return;
 
 	irqd = irq_domain_get_irq_data(domain, virq);
-	clear_bit(irqd->hwirq, heart_irq_map);
-	if (irqd && irqd->chip_data)
+	if (irqd) {
+		clear_bit(irqd->hwirq, heart_irq_map);
 		kfree(irqd->chip_data);
+	}
 }
 
 static const struct irq_domain_ops heart_domain_ops = {
diff --git a/arch/mips/vdso/genvdso.c b/arch/mips/vdso/genvdso.c
index b66b6b1c4aeb..be57b832bbe0 100644
--- a/arch/mips/vdso/genvdso.c
+++ b/arch/mips/vdso/genvdso.c
@@ -251,6 +251,18 @@ int main(int argc, char **argv)
 	fprintf(out_file, "#include <linux/linkage.h>\n");
 	fprintf(out_file, "#include <linux/mm.h>\n");
 	fprintf(out_file, "#include <asm/vdso.h>\n");
+	fprintf(out_file, "static int vdso_mremap(\n");
+	fprintf(out_file, "	const struct vm_special_mapping *sm,\n");
+	fprintf(out_file, "	struct vm_area_struct *new_vma)\n");
+	fprintf(out_file, "{\n");
+	fprintf(out_file, "	unsigned long new_size =\n");
+	fprintf(out_file, "	new_vma->vm_end - new_vma->vm_start;\n");
+	fprintf(out_file, "	if (vdso_image.size != new_size)\n");
+	fprintf(out_file, "		return -EINVAL;\n");
+	fprintf(out_file, "	current->mm->context.vdso =\n");
+	fprintf(out_file, "	(void __user *)(new_vma->vm_start);\n");
+	fprintf(out_file, "	return 0;\n");
+	fprintf(out_file, "}\n");
 
 	/* Write out the stripped VDSO data. */
 	fprintf(out_file,
@@ -275,6 +287,7 @@ int main(int argc, char **argv)
 	fprintf(out_file, "\t.mapping = {\n");
 	fprintf(out_file, "\t\t.name = \"[vdso]\",\n");
 	fprintf(out_file, "\t\t.pages = vdso_pages,\n");
+	fprintf(out_file, "\t\t.mremap = vdso_mremap,\n");
 	fprintf(out_file, "\t},\n");
 
 	/* Calculate and write symbol offsets to <output file> */
diff --git a/arch/parisc/configs/712_defconfig b/arch/parisc/configs/712_defconfig
deleted file mode 100644
index d3e3d94e90c3..000000000000
--- a/arch/parisc/configs/712_defconfig
+++ /dev/null
@@ -1,181 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PA7100LC=y
-CONFIG_PREEMPT_VOLUNTARY=y
-CONFIG_GSC_LASI=y
-# CONFIG_PDC_CHASSIS is not set
-CONFIG_BINFMT_MISC=m
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_DIAG=m
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-CONFIG_LLC2=m
-CONFIG_NET_PKTGEN=m
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_PARPORT=y
-CONFIG_PARPORT_PC=m
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=6144
-CONFIG_ATA_OVER_ETH=m
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_ISCSI_ATTRS=m
-CONFIG_SCSI_LASI700=y
-CONFIG_SCSI_DEBUG=m
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=m
-CONFIG_MD_LINEAR=m
-CONFIG_MD_RAID0=m
-CONFIG_MD_RAID1=m
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_TUN=m
-CONFIG_LASI_82596=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_KEYBOARD_HIL_OLD is not set
-CONFIG_MOUSE_SERIAL=m
-CONFIG_LEGACY_PTY_COUNT=64
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=17
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-# CONFIG_SERIAL_MUX is not set
-CONFIG_PDC_CONSOLE=y
-CONFIG_PRINTER=m
-CONFIG_PPDEV=m
-# CONFIG_HW_RANDOM is not set
-CONFIG_RAW_DRIVER=y
-# CONFIG_HWMON is not set
-CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-CONFIG_DUMMY_CONSOLE_COLUMNS=128
-CONFIG_DUMMY_CONSOLE_ROWS=48
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
-CONFIG_SND_HARMONY=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_JFS_FS=m
-CONFIG_XFS_FS=m
-CONFIG_AUTOFS4_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_UFS_FS=m
-CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_737=m
-CONFIG_NLS_CODEPAGE_775=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_CODEPAGE_852=m
-CONFIG_NLS_CODEPAGE_855=m
-CONFIG_NLS_CODEPAGE_857=m
-CONFIG_NLS_CODEPAGE_860=m
-CONFIG_NLS_CODEPAGE_861=m
-CONFIG_NLS_CODEPAGE_862=m
-CONFIG_NLS_CODEPAGE_863=m
-CONFIG_NLS_CODEPAGE_864=m
-CONFIG_NLS_CODEPAGE_865=m
-CONFIG_NLS_CODEPAGE_866=m
-CONFIG_NLS_CODEPAGE_869=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_CODEPAGE_950=m
-CONFIG_NLS_CODEPAGE_932=m
-CONFIG_NLS_CODEPAGE_949=m
-CONFIG_NLS_CODEPAGE_874=m
-CONFIG_NLS_ISO8859_8=m
-CONFIG_NLS_CODEPAGE_1250=m
-CONFIG_NLS_CODEPAGE_1251=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_2=m
-CONFIG_NLS_ISO8859_3=m
-CONFIG_NLS_ISO8859_4=m
-CONFIG_NLS_ISO8859_5=m
-CONFIG_NLS_ISO8859_6=m
-CONFIG_NLS_ISO8859_7=m
-CONFIG_NLS_ISO8859_9=m
-CONFIG_NLS_ISO8859_13=m
-CONFIG_NLS_ISO8859_14=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_KOI8_R=m
-CONFIG_NLS_KOI8_U=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_DEFLATE=m
-# CONFIG_CRYPTO_HW is not set
-CONFIG_FONTS=y
-CONFIG_FONT_8x8=y
-CONFIG_FONT_8x16=y
diff --git a/arch/parisc/configs/a500_defconfig b/arch/parisc/configs/a500_defconfig
deleted file mode 100644
index 3335734bfadd..000000000000
--- a/arch/parisc/configs/a500_defconfig
+++ /dev/null
@@ -1,177 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PA8X00=y
-CONFIG_64BIT=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=8
-# CONFIG_GSC is not set
-CONFIG_PCI=y
-CONFIG_PCI_LBA=y
-CONFIG_PCCARD=m
-# CONFIG_PCMCIA_LOAD_CIS is not set
-CONFIG_YENTA=m
-CONFIG_PD6729=m
-CONFIG_I82092=m
-# CONFIG_SUPERIO is not set
-# CONFIG_CHASSIS_LCD_LED is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET6_AH=m
-CONFIG_INET6_ESP=m
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_NETFILTER=y
-# CONFIG_NETFILTER_XT_MATCH_DCCP is not set
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_IP6_NF_IPTABLES=m
-CONFIG_IP6_NF_MATCH_FRAG=m
-CONFIG_IP6_NF_MATCH_OPTS=m
-CONFIG_IP6_NF_MATCH_HL=m
-CONFIG_IP6_NF_MATCH_IPV6HEADER=m
-CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_FILTER=m
-CONFIG_IP6_NF_TARGET_REJECT=m
-CONFIG_IP6_NF_MANGLE=m
-CONFIG_IP6_NF_RAW=m
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
-CONFIG_LLC2=m
-CONFIG_NET_PKTGEN=m
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_BLK_DEV_UMEM=m
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=6144
-CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_ISCSI_ATTRS=m
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_QLOGIC_1280=m
-CONFIG_SCSI_DEBUG=m
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_FUSION=y
-CONFIG_FUSION_SPI=m
-CONFIG_FUSION_CTL=m
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_TUN=m
-CONFIG_PCMCIA_3C574=m
-CONFIG_PCMCIA_3C589=m
-CONFIG_VORTEX=m
-CONFIG_TYPHOON=m
-CONFIG_ACENIC=m
-CONFIG_ACENIC_OMIT_TIGON_I=y
-CONFIG_PCNET32=m
-CONFIG_TIGON3=m
-CONFIG_NET_TULIP=y
-CONFIG_DE2104X=m
-CONFIG_TULIP=y
-CONFIG_TULIP_MMIO=y
-CONFIG_PCMCIA_XIRCOM=m
-CONFIG_HP100=m
-CONFIG_E100=m
-CONFIG_E1000=m
-CONFIG_PCMCIA_SMC91C92=m
-CONFIG_PCMCIA_XIRC2PS=m
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_LEGACY_PTYS is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_CS=m
-CONFIG_SERIAL_8250_NR_UARTS=17
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_PDC_CONSOLE=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_RAW_DRIVER=y
-# CONFIG_HWMON is not set
-CONFIG_AGP=y
-CONFIG_AGP_PARISC=y
-# CONFIG_STI_CONSOLE is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_JFS_FS=m
-CONFIG_XFS_FS=m
-CONFIG_AUTOFS4_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_UFS_FS=m
-CONFIG_NFS_FS=m
-CONFIG_NFS_V4=m
-CONFIG_NFSD=m
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
-CONFIG_MAGIC_SYSRQ=y
-# CONFIG_DEBUG_BUGVERBOSE is not set
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_BLOWFISH=m
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/parisc/configs/b180_defconfig b/arch/parisc/configs/b180_defconfig
deleted file mode 100644
index 07fde5bd6974..000000000000
--- a/arch/parisc/configs/b180_defconfig
+++ /dev/null
@@ -1,97 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODVERSIONS=y
-CONFIG_PA7100LC=y
-CONFIG_HPPB=y
-CONFIG_IOMMU_CCIO=y
-CONFIG_GSC_LASI=y
-CONFIG_GSC_WAX=y
-CONFIG_EISA=y
-CONFIG_ISA=y
-CONFIG_PCI=y
-CONFIG_GSC_DINO=y
-# CONFIG_PDC_CHASSIS is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_PARPORT=y
-CONFIG_PARPORT_PC=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
-CONFIG_CDROM_PKTCDVD=m
-CONFIG_ATA_OVER_ETH=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_LASI700=y
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0
-CONFIG_SCSI_ZALON=y
-CONFIG_SCSI_NCR53C8XX_SYNC=40
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_NETDEVICES=y
-CONFIG_NET_TULIP=y
-CONFIG_TULIP=y
-CONFIG_LASI_82596=y
-CONFIG_PPP=y
-CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_HIL_OLD is not set
-CONFIG_INPUT_MISC=y
-# CONFIG_SERIO_SERPORT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=13
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_PRINTER=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_FB=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
-CONFIG_SND_HARMONY=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_AUTOFS4_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NFSD_V3=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_UTF8=m
-CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_SECURITY=y
diff --git a/arch/parisc/configs/c3000_defconfig b/arch/parisc/configs/c3000_defconfig
deleted file mode 100644
index 64d45a8b6ca0..000000000000
--- a/arch/parisc/configs/c3000_defconfig
+++ /dev/null
@@ -1,151 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PA8X00=y
-CONFIG_PREEMPT_VOLUNTARY=y
-# CONFIG_GSC is not set
-CONFIG_PCI=y
-CONFIG_PCI_LBA=y
-# CONFIG_PDC_CHASSIS is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_DIAG is not set
-CONFIG_INET6_IPCOMP=m
-CONFIG_IPV6_TUNNEL=m
-CONFIG_NETFILTER=y
-CONFIG_NET_PKTGEN=m
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_BLK_DEV_UMEM=m
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_NS87415=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_ISCSI_ATTRS=m
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=0
-CONFIG_SCSI_DEBUG=m
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_BLK_DEV_DM=m
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_ZERO=m
-CONFIG_DM_MULTIPATH=m
-CONFIG_FUSION=y
-CONFIG_FUSION_SPI=m
-CONFIG_FUSION_CTL=m
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_TUN=m
-CONFIG_ACENIC=m
-CONFIG_TIGON3=m
-CONFIG_NET_TULIP=y
-CONFIG_DE2104X=m
-CONFIG_TULIP=y
-CONFIG_TULIP_MMIO=y
-CONFIG_E100=m
-CONFIG_E1000=m
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_KEYBOARD_ATKBD is not set
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_SERIO=m
-CONFIG_SERIO_LIBPS2=m
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=13
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_RAW_DRIVER=y
-# CONFIG_HWMON is not set
-CONFIG_FB=y
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
-CONFIG_SND_AD1889=y
-CONFIG_USB_HIDDEV=y
-CONFIG_USB=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_PRINTER=m
-CONFIG_USB_STORAGE=m
-CONFIG_USB_STORAGE_USBAT=m
-CONFIG_USB_STORAGE_SDDR09=m
-CONFIG_USB_STORAGE_SDDR55=m
-CONFIG_USB_STORAGE_JUMPSHOT=m
-CONFIG_USB_MDC800=m
-CONFIG_USB_MICROTEK=m
-CONFIG_USB_LEGOTOWER=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_XFS_FS=m
-CONFIG_AUTOFS4_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NFSD_V3=y
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_UTF8=m
-CONFIG_DEBUG_FS=y
-CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_MUTEXES=y
-# CONFIG_DEBUG_BUGVERBOSE is not set
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_MD5=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_DES=m
-# CONFIG_CRYPTO_HW is not set
diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig
deleted file mode 100644
index db864b18962a..000000000000
--- a/arch/parisc/configs/c8000_defconfig
+++ /dev/null
@@ -1,234 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-# CONFIG_CROSS_MEMORY_ATTACH is not set
-CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_BSD_PROCESS_ACCT_V3=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_RELAY=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
-CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_BLK_DEV_INTEGRITY=y
-CONFIG_PA8X00=y
-CONFIG_64BIT=y
-CONFIG_SMP=y
-CONFIG_PREEMPT=y
-CONFIG_IOMMU_CCIO=y
-CONFIG_PCI=y
-CONFIG_PCI_LBA=y
-# CONFIG_SUPERIO is not set
-# CONFIG_CHASSIS_LCD_LED is not set
-# CONFIG_PDC_CHASSIS is not set
-# CONFIG_PDC_CHASSIS_WARN is not set
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
-CONFIG_BINFMT_MISC=m
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_XFRM_SUB_POLICY=y
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_IP_PNP_RARP=y
-CONFIG_NET_IPIP=m
-CONFIG_IP_MROUTE=y
-CONFIG_IP_PIMSM_V1=y
-CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_BEET=m
-CONFIG_INET_DIAG=m
-# CONFIG_IPV6 is not set
-CONFIG_IP_DCCP=m
-# CONFIG_IP_DCCP_CCID3 is not set
-CONFIG_TIPC=m
-CONFIG_LLC2=m
-CONFIG_DNS_RESOLVER=y
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-CONFIG_PARPORT=y
-CONFIG_PARPORT_PC=y
-CONFIG_PARPORT_PC_FIFO=y
-CONFIG_BLK_DEV_UMEM=m
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_BLK_DEV_SX8=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=6144
-CONFIG_CDROM_PKTCDVD=m
-CONFIG_CDROM_PKTCDVD_WCACHE=y
-CONFIG_ATA_OVER_ETH=m
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_PLATFORM=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=m
-CONFIG_BLK_DEV_SR=m
-CONFIG_CHR_DEV_SG=y
-CONFIG_CHR_DEV_SCH=m
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_LOGGING=y
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_SAS_LIBSAS=m
-CONFIG_ISCSI_TCP=m
-CONFIG_ISCSI_BOOT_SYSFS=m
-CONFIG_ATA=y
-CONFIG_PATA_SIL680=y
-CONFIG_FUSION=y
-CONFIG_FUSION_SPI=y
-CONFIG_FUSION_SAS=y
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
-CONFIG_NETCONSOLE=m
-CONFIG_TUN=y
-CONFIG_E1000=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_WLAN is not set
-CONFIG_INPUT_FF_MEMLESS=m
-# CONFIG_KEYBOARD_ATKBD is not set
-# CONFIG_KEYBOARD_HIL_OLD is not set
-# CONFIG_KEYBOARD_HIL is not set
-# CONFIG_MOUSE_PS2 is not set
-CONFIG_INPUT_MISC=y
-CONFIG_SERIO_SERPORT=m
-CONFIG_SERIO_PARKBD=m
-CONFIG_SERIO_GSCPS2=m
-# CONFIG_HP_SDC is not set
-CONFIG_SERIO_PCIPS2=m
-CONFIG_SERIO_LIBPS2=y
-CONFIG_SERIO_RAW=m
-CONFIG_SERIAL_8250=y
-# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=8
-CONFIG_SERIAL_8250_RUNTIME_UARTS=8
-CONFIG_SERIAL_8250_EXTENDED=y
-# CONFIG_SERIAL_MUX is not set
-CONFIG_SERIAL_JSM=m
-CONFIG_PRINTER=y
-CONFIG_HW_RANDOM=y
-CONFIG_RAW_DRIVER=m
-CONFIG_PTP_1588_CLOCK=y
-CONFIG_SSB=m
-CONFIG_SSB_DRIVER_PCICORE=y
-CONFIG_AGP=y
-CONFIG_AGP_PARISC=y
-CONFIG_DRM=y
-CONFIG_DRM_RADEON=y
-CONFIG_FIRMWARE_EDID=y
-CONFIG_FB_FOREIGN_ENDIAN=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-# CONFIG_FB_STI is not set
-# CONFIG_LCD_CLASS_DEVICE is not set
-# CONFIG_BACKLIGHT_GENERIC is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
-# CONFIG_STI_CONSOLE is not set
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_SOUND=m
-CONFIG_SND=m
-CONFIG_SND_VERBOSE_PRINTK=y
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
-CONFIG_SND_AD1889=m
-# CONFIG_SND_USB is not set
-# CONFIG_SND_GSC is not set
-CONFIG_USB=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_STORAGE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_REISERFS_FS=m
-CONFIG_REISERFS_PROC_INFO=y
-CONFIG_XFS_FS=m
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_QUOTA=y
-CONFIG_QFMT_V1=m
-CONFIG_QFMT_V2=m
-CONFIG_AUTOFS4_FS=m
-CONFIG_FUSE_FS=m
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_MSDOS_FS=m
-CONFIG_VFAT_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_XATTR=y
-CONFIG_NFS_FS=m
-CONFIG_NLS_CODEPAGE_437=m
-CONFIG_NLS_CODEPAGE_737=m
-CONFIG_NLS_CODEPAGE_775=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_CODEPAGE_852=m
-CONFIG_NLS_CODEPAGE_855=m
-CONFIG_NLS_CODEPAGE_857=m
-CONFIG_NLS_CODEPAGE_860=m
-CONFIG_NLS_CODEPAGE_861=m
-CONFIG_NLS_CODEPAGE_862=m
-CONFIG_NLS_CODEPAGE_863=m
-CONFIG_NLS_CODEPAGE_864=m
-CONFIG_NLS_CODEPAGE_865=m
-CONFIG_NLS_CODEPAGE_866=m
-CONFIG_NLS_CODEPAGE_869=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_CODEPAGE_950=m
-CONFIG_NLS_CODEPAGE_932=m
-CONFIG_NLS_CODEPAGE_949=m
-CONFIG_NLS_CODEPAGE_874=m
-CONFIG_NLS_ISO8859_8=m
-CONFIG_NLS_CODEPAGE_1250=m
-CONFIG_NLS_CODEPAGE_1251=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=m
-CONFIG_NLS_ISO8859_2=m
-CONFIG_NLS_ISO8859_3=m
-CONFIG_NLS_ISO8859_4=m
-CONFIG_NLS_ISO8859_5=m
-CONFIG_NLS_ISO8859_6=m
-CONFIG_NLS_ISO8859_7=m
-CONFIG_NLS_ISO8859_9=m
-CONFIG_NLS_ISO8859_13=m
-CONFIG_NLS_ISO8859_14=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_KOI8_R=m
-CONFIG_NLS_KOI8_U=m
-CONFIG_NLS_UTF8=m
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_SLAB=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_BLOCK_EXT_DEVT=y
-CONFIG_LATENCYTOP=y
-CONFIG_KEYS=y
-# CONFIG_CRYPTO_HW is not set
-CONFIG_FONTS=y
diff --git a/arch/parisc/configs/defconfig b/arch/parisc/configs/defconfig
deleted file mode 100644
index 5b877ca34ebf..000000000000
--- a/arch/parisc/configs/defconfig
+++ /dev/null
@@ -1,206 +0,0 @@
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PA7100LC=y
-CONFIG_PREEMPT_VOLUNTARY=y
-CONFIG_IOMMU_CCIO=y
-CONFIG_GSC_LASI=y
-CONFIG_GSC_WAX=y
-CONFIG_EISA=y
-CONFIG_PCI=y
-CONFIG_GSC_DINO=y
-CONFIG_PCI_LBA=y
-CONFIG_PCCARD=y
-CONFIG_YENTA=y
-CONFIG_PD6729=y
-CONFIG_I82092=y
-CONFIG_BINFMT_MISC=m
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_DIAG=m
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_LLC2=m
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_PARPORT=y
-CONFIG_PARPORT_PC=m
-CONFIG_PARPORT_PC_PCMCIA=m
-CONFIG_PARPORT_1284=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=6144
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECS=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_NS87415=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_LASI700=y
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_ZALON=y
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_MD_RAID10=y
-CONFIG_BLK_DEV_DM=y
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_TUN=m
-CONFIG_ACENIC=y
-CONFIG_TIGON3=y
-CONFIG_NET_TULIP=y
-CONFIG_TULIP=y
-CONFIG_LASI_82596=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_KEYBOARD_HIL_OLD is not set
-CONFIG_MOUSE_SERIAL=y
-CONFIG_LEGACY_PTY_COUNT=64
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_CS=y
-CONFIG_SERIAL_8250_NR_UARTS=17
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_PRINTER=m
-CONFIG_PPDEV=m
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-CONFIG_DUMMY_CONSOLE_COLUMNS=128
-CONFIG_DUMMY_CONSOLE_ROWS=48
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_DYNAMIC_MINORS=y
-CONFIG_SND_SEQUENCER=y
-CONFIG_SND_AD1889=y
-CONFIG_SND_HARMONY=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_NTRIG=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_HID_TOPSEED=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_UHCI_HCD=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_737=m
-CONFIG_NLS_CODEPAGE_775=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_CODEPAGE_852=m
-CONFIG_NLS_CODEPAGE_855=m
-CONFIG_NLS_CODEPAGE_857=m
-CONFIG_NLS_CODEPAGE_860=m
-CONFIG_NLS_CODEPAGE_861=m
-CONFIG_NLS_CODEPAGE_862=m
-CONFIG_NLS_CODEPAGE_863=m
-CONFIG_NLS_CODEPAGE_864=m
-CONFIG_NLS_CODEPAGE_865=m
-CONFIG_NLS_CODEPAGE_866=m
-CONFIG_NLS_CODEPAGE_869=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_CODEPAGE_950=m
-CONFIG_NLS_CODEPAGE_932=m
-CONFIG_NLS_CODEPAGE_949=m
-CONFIG_NLS_CODEPAGE_874=m
-CONFIG_NLS_ISO8859_8=m
-CONFIG_NLS_CODEPAGE_1250=y
-CONFIG_NLS_CODEPAGE_1251=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_2=m
-CONFIG_NLS_ISO8859_3=m
-CONFIG_NLS_ISO8859_4=m
-CONFIG_NLS_ISO8859_5=m
-CONFIG_NLS_ISO8859_6=m
-CONFIG_NLS_ISO8859_7=m
-CONFIG_NLS_ISO8859_9=m
-CONFIG_NLS_ISO8859_13=m
-CONFIG_NLS_ISO8859_14=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_KOI8_R=m
-CONFIG_NLS_KOI8_U=m
-CONFIG_NLS_UTF8=y
-CONFIG_DEBUG_FS=y
-CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_KEYS=y
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-# CONFIG_CRYPTO_HW is not set
-CONFIG_LIBCRC32C=m
-CONFIG_FONTS=y
diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig
index c7a5726728a4..61bac8ff8f22 100644
--- a/arch/parisc/configs/generic-32bit_defconfig
+++ b/arch/parisc/configs/generic-32bit_defconfig
@@ -10,23 +10,20 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
 CONFIG_SLAB=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
 CONFIG_PA7100LC=y
 CONFIG_SMP=y
 CONFIG_HZ_100=y
 CONFIG_IOMMU_CCIO=y
 CONFIG_GSC_LASI=y
 CONFIG_GSC_WAX=y
-CONFIG_EISA=y
-CONFIG_PCI=y
 CONFIG_GSC_DINO=y
 CONFIG_PCI_LBA=y
-CONFIG_PCCARD=m
-CONFIG_YENTA=m
 # CONFIG_PDC_CHASSIS is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_UNUSED_SYMBOLS=y
+# CONFIG_BLK_DEV_BSG is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_NET=y
@@ -35,17 +32,15 @@ CONFIG_UNIX=y
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
 CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_BOOTP=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 CONFIG_INET_DIAG=m
 CONFIG_LLC2=m
 # CONFIG_WIRELESS is not set
+CONFIG_EISA=y
+CONFIG_PCI=y
+CONFIG_PCCARD=m
+CONFIG_YENTA=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
@@ -88,7 +83,6 @@ CONFIG_TUN=m
 # CONFIG_NET_VENDOR_ALTEON is not set
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
@@ -97,8 +91,6 @@ CONFIG_NET_TULIP=y
 CONFIG_TULIP=y
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_EXAR is not set
-# CONFIG_NET_VENDOR_HP is not set
 CONFIG_LASI_82596=y
 # CONFIG_NET_VENDOR_MELLANOX is not set
 # CONFIG_NET_VENDOR_MICREL is not set
@@ -106,10 +98,9 @@ CONFIG_LASI_82596=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
-# CONFIG_NET_PACKET_ENGINE is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
-# CONFIG_NET_VENDOR_REALTEK is not set
 # CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SILAN is not set
 # CONFIG_NET_VENDOR_SIS is not set
@@ -142,7 +133,6 @@ CONFIG_PPDEV=m
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 # CONFIG_HWMON is not set
-CONFIG_AGP=y
 CONFIG_FB=y
 CONFIG_FB_FOREIGN_ENDIAN=y
 CONFIG_FB_MODE_HELPERS=y
@@ -230,63 +220,11 @@ CONFIG_CIFS_WEAK_PW_HASH=y
 CONFIG_CIFS_XATTR=y
 CONFIG_CIFS_POSIX=y
 # CONFIG_CIFS_DEBUG is not set
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_737=m
-CONFIG_NLS_CODEPAGE_775=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_CODEPAGE_852=m
-CONFIG_NLS_CODEPAGE_855=m
-CONFIG_NLS_CODEPAGE_857=m
-CONFIG_NLS_CODEPAGE_860=m
-CONFIG_NLS_CODEPAGE_861=m
-CONFIG_NLS_CODEPAGE_862=m
-CONFIG_NLS_CODEPAGE_863=m
-CONFIG_NLS_CODEPAGE_864=m
-CONFIG_NLS_CODEPAGE_865=m
-CONFIG_NLS_CODEPAGE_866=m
-CONFIG_NLS_CODEPAGE_869=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_CODEPAGE_950=m
-CONFIG_NLS_CODEPAGE_932=m
-CONFIG_NLS_CODEPAGE_949=m
-CONFIG_NLS_CODEPAGE_874=m
-CONFIG_NLS_ISO8859_8=m
-CONFIG_NLS_CODEPAGE_1250=y
-CONFIG_NLS_CODEPAGE_1251=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_2=m
-CONFIG_NLS_ISO8859_3=m
-CONFIG_NLS_ISO8859_4=m
-CONFIG_NLS_ISO8859_5=m
-CONFIG_NLS_ISO8859_6=m
-CONFIG_NLS_ISO8859_7=m
-CONFIG_NLS_ISO8859_9=m
-CONFIG_NLS_ISO8859_13=m
-CONFIG_NLS_ISO8859_14=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_KOI8_R=m
-CONFIG_NLS_KOI8_U=m
-CONFIG_NLS_UTF8=y
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_SHIRQ=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_LATENCYTOP=y
-CONFIG_LKDTM=m
-CONFIG_KEYS=y
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_MD5=y
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA1=y
-CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_TGR192=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_ANUBIS=m
@@ -302,3 +240,14 @@ CONFIG_CRYPTO_DEFLATE=y
 CONFIG_CRC_CCITT=m
 CONFIG_CRC_T10DIF=y
 CONFIG_FONTS=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_RT_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_LATENCYTOP=y
+CONFIG_LKDTM=m
diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig
index d39e7f821aba..59561e04e659 100644
--- a/arch/parisc/configs/generic-64bit_defconfig
+++ b/arch/parisc/configs/generic-64bit_defconfig
@@ -17,27 +17,24 @@ CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 # CONFIG_COMPAT_BRK is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_FORCE_LOAD=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_BLK_DEV_INTEGRITY=y
-# CONFIG_IOSCHED_DEADLINE is not set
 CONFIG_PA8X00=y
 CONFIG_64BIT=y
 CONFIG_SMP=y
-# CONFIG_COMPACTION is not set
 CONFIG_HPPB=y
 CONFIG_IOMMU_CCIO=y
 CONFIG_GSC_LASI=y
 CONFIG_GSC_WAX=y
-CONFIG_PCI=y
-CONFIG_PCI_STUB=m
-CONFIG_PCI_IOV=y
 CONFIG_GSC_DINO=y
 CONFIG_PCI_LBA=y
+CONFIG_MODULES=y
+CONFIG_MODULE_FORCE_LOAD=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_BINFMT_MISC=m
+# CONFIG_COMPACTION is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -47,18 +44,17 @@ CONFIG_XFRM_MIGRATE=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_PNP=y
-CONFIG_IP_PNP_BOOTP=y
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_ADVANCED is not set
 CONFIG_NETFILTER_NETLINK_LOG=y
 CONFIG_DCB=y
 # CONFIG_WIRELESS is not set
+CONFIG_PCI=y
+CONFIG_PCI_STUB=m
+CONFIG_PCI_IOV=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_LOOP=y
@@ -102,7 +98,6 @@ CONFIG_TUN=y
 # CONFIG_NET_VENDOR_ALTEON is not set
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CHELSIO is not set
@@ -111,10 +106,8 @@ CONFIG_NET_TULIP=y
 CONFIG_TULIP=y
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
-# CONFIG_NET_VENDOR_EXAR is not set
-CONFIG_HP100=m
-CONFIG_E1000=y
 CONFIG_LASI_82596=y
+CONFIG_E1000=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
 # CONFIG_NET_VENDOR_MICREL is not set
@@ -124,9 +117,8 @@ CONFIG_LASI_82596=y
 # CONFIG_NET_VENDOR_OKI is not set
 CONFIG_QLA3XXX=m
 CONFIG_QLCNIC=m
-CONFIG_QLGE=m
-# CONFIG_NET_VENDOR_REALTEK is not set
 # CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SILAN is not set
 # CONFIG_NET_VENDOR_SIS is not set
@@ -153,9 +145,6 @@ CONFIG_SMSC_PHY=m
 CONFIG_STE10XP=m
 CONFIG_VITESSE_PHY=m
 CONFIG_SLIP=m
-CONFIG_SLIP_COMPRESSED=y
-CONFIG_SLIP_SMART=y
-CONFIG_SLIP_MODE_SLIP6=y
 # CONFIG_WLAN is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_HIL_OLD is not set
@@ -208,34 +197,18 @@ CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
 # CONFIG_BACKLIGHT_GENERIC is not set
 CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
 CONFIG_HIDRAW=y
 CONFIG_HID_PID=y
 CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
-CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_DYNAMIC_MINORS=y
-CONFIG_USB_MON=m
-CONFIG_USB_WUSB_CBAF=m
-CONFIG_USB_XHCI_HCD=m
-CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_NEW_LEDS=y
-CONFIG_LEDS_CLASS=y
-CONFIG_LEDS_TRIGGERS=y
-CONFIG_LEDS_TRIGGER_TIMER=y
-CONFIG_LEDS_TRIGGER_ONESHOT=y
-CONFIG_LEDS_TRIGGER_DISK=y
-CONFIG_LEDS_TRIGGER_HEARTBEAT=m
-CONFIG_LEDS_TRIGGER_BACKLIGHT=m
-CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=m
 CONFIG_UIO_AEC=m
 CONFIG_UIO_SERCOS3=m
 CONFIG_UIO_PCI_GENERIC=m
 CONFIG_STAGING=y
+CONFIG_QLGE=m
+CONFIG_HP100=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_SECURITY=y
@@ -272,14 +245,6 @@ CONFIG_NLS_ASCII=m
 CONFIG_NLS_ISO8859_1=m
 CONFIG_NLS_ISO8859_2=m
 CONFIG_NLS_UTF8=m
-CONFIG_PRINTK_TIME=y
-CONFIG_STRIP_ASM_SYMS=y
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_DEBUG_FS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-# CONFIG_SCHED_DEBUG is not set
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
@@ -292,3 +257,10 @@ CONFIG_CRYPTO_DEFLATE=m
 # CONFIG_CRYPTO_HW is not set
 CONFIG_CRC_CCITT=m
 CONFIG_LIBCRC32C=y
+CONFIG_PRINTK_TIME=y
+CONFIG_STRIP_ASM_SYMS=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_SCHED_DEBUG is not set
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index e03e3c849f40..2f4f66a3bac0 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -173,23 +173,6 @@ struct compat_shmid64_ds {
 #define COMPAT_ELF_NGREG 80
 typedef compat_ulong_t compat_elf_gregset_t[COMPAT_ELF_NGREG];
 
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
 static __inline__ void __user *arch_compat_alloc_user_space(long len)
 {
 	struct pt_regs *regs = &current->thread.regs;
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b550ae9a7fea..52a15f5cd130 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -434,3 +434,4 @@
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3_wrapper
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 354cf060b67f..5224fb38d766 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -351,7 +351,6 @@ static void __init map_pages(unsigned long start_vaddr,
 			     unsigned long start_paddr, unsigned long size,
 			     pgprot_t pgprot, int force)
 {
-	pgd_t *pg_dir;
 	pmd_t *pmd;
 	pte_t *pg_table;
 	unsigned long end_paddr;
@@ -372,62 +371,37 @@ static void __init map_pages(unsigned long start_vaddr,
 
 	end_paddr = start_paddr + size;
 
-	pg_dir = pgd_offset_k(start_vaddr);
-
-#if PTRS_PER_PMD == 1
-	start_pmd = 0;
-#else
+	/* for 2-level configuration PTRS_PER_PMD is 0 so start_pmd will be 0 */
 	start_pmd = ((start_vaddr >> PMD_SHIFT) & (PTRS_PER_PMD - 1));
-#endif
 	start_pte = ((start_vaddr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1));
 
 	address = start_paddr;
 	vaddr = start_vaddr;
 	while (address < end_paddr) {
-#if PTRS_PER_PMD == 1
-		pmd = (pmd_t *)__pa(pg_dir);
-#else
-		pmd = (pmd_t *)pgd_address(*pg_dir);
-
-		/*
-		 * pmd is physical at this point
-		 */
+		pgd_t *pgd = pgd_offset_k(vaddr);
+		p4d_t *p4d = p4d_offset(pgd, vaddr);
+		pud_t *pud = pud_offset(p4d, vaddr);
 
-		if (!pmd) {
+#if CONFIG_PGTABLE_LEVELS == 3
+		if (pud_none(*pud)) {
 			pmd = memblock_alloc(PAGE_SIZE << PMD_ORDER,
 					     PAGE_SIZE << PMD_ORDER);
 			if (!pmd)
 				panic("pmd allocation failed.\n");
-			pmd = (pmd_t *) __pa(pmd);
+			pud_populate(NULL, pud, pmd);
 		}
-
-		pud_populate(NULL, (pud_t *)pg_dir, __va(pmd));
 #endif
-		pg_dir++;
-
-		/* now change pmd to kernel virtual addresses */
 
-		pmd = (pmd_t *)__va(pmd) + start_pmd;
+		pmd = pmd_offset(pud, vaddr);
 		for (tmp1 = start_pmd; tmp1 < PTRS_PER_PMD; tmp1++, pmd++) {
-
-			/*
-			 * pg_table is physical at this point
-			 */
-
-			pg_table = (pte_t *)pmd_address(*pmd);
-			if (!pg_table) {
-				pg_table = memblock_alloc(PAGE_SIZE,
-							  PAGE_SIZE);
+			if (pmd_none(*pmd)) {
+				pg_table = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 				if (!pg_table)
 					panic("page table allocation failed\n");
-				pg_table = (pte_t *) __pa(pg_table);
+				pmd_populate_kernel(NULL, pmd, pg_table);
 			}
 
-			pmd_populate_kernel(NULL, pmd, __va(pg_table));
-
-			/* now change pg_table to kernel virtual addresses */
-
-			pg_table = (pte_t *) __va(pg_table) + start_pte;
+			pg_table = pte_offset_kernel(pmd, vaddr);
 			for (tmp2 = start_pte; tmp2 < PTRS_PER_PTE; tmp2++, pg_table++) {
 				pte_t pte;
 				pgprot_t prot;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index e7c607059f54..497b7d0b2d7e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -1,10 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 source "arch/powerpc/platforms/Kconfig.cputype"
 
-config PPC32
-	bool
-	default y if !PPC64
-
 config 32BIT
 	bool
 	default y if PPC32
@@ -133,7 +129,7 @@ config PPC
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
-	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
+	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
 	select ARCH_HAS_UACCESS_MCSAFE		if PPC64
@@ -173,6 +169,7 @@ config PPC
 	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if PPC32
+	select HAVE_ARCH_KASAN_VMALLOC		if PPC32
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if COMPAT
@@ -222,9 +219,8 @@ config PPC
 	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_RCU_TABLE_FREE		if SMP
-	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
-	select HAVE_MMU_GATHER_PAGE_SIZE
+	select MMU_GATHER_RCU_TABLE_FREE
+	select MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -238,6 +234,7 @@ config PPC
 	select NEED_DMA_MAP_STATE		if PPC64 || NOT_COHERENT_CACHE
 	select NEED_SG_DMA_LENGTH
 	select OF
+	select OF_DMA_DEFAULT_COHERENT		if !NOT_COHERENT_CACHE
 	select OF_EARLY_FLATTREE
 	select OLD_SIGACTION			if PPC32
 	select OLD_SIGSUSPEND
@@ -482,7 +479,7 @@ config MPROFILE_KERNEL
 config HOTPLUG_CPU
 	bool "Support for enabling/disabling CPUs"
 	depends on SMP && (PPC_PSERIES || \
-	PPC_PMAC || PPC_POWERNV || FSL_SOC_BOOKE)
+		PPC_PMAC || PPC_POWERNV || FSL_SOC_BOOKE)
 	help
 	  Say Y here to be able to disable and re-enable individual
 	  CPUs at runtime on SMP machines.
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 4e1d39847462..0b063830eea8 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -371,7 +371,7 @@ config PPC_PTDUMP
 
 config PPC_DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	depends on PPC_PTDUMP
+	depends on PPC_PTDUMP && STRICT_KERNEL_RWX
 	help
 	  Generate a warning if any W+X mappings are found at boot.
 
diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink
index 134f12f89b92..2268396ff4bb 100644
--- a/arch/powerpc/Makefile.postlink
+++ b/arch/powerpc/Makefile.postlink
@@ -17,11 +17,11 @@ quiet_cmd_head_check = CHKHEAD $@
 quiet_cmd_relocs_check = CHKREL  $@
 ifdef CONFIG_PPC_BOOK3S_64
       cmd_relocs_check =						\
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@" ; \
+	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" ; \
 	$(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@"
 else
       cmd_relocs_check =						\
-	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$@"
+	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
 endif
 
 # `@true` prevents complaint when there is nothing to be done
diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c
index 1699e9531552..00c4d843a023 100644
--- a/arch/powerpc/boot/4xx.c
+++ b/arch/powerpc/boot/4xx.c
@@ -228,7 +228,7 @@ void ibm4xx_denali_fixup_memsize(void)
 		dpath = 8; /* 64 bits */
 
 	/* get address pins (rows) */
- 	val = SDRAM0_READ(DDR0_42);
+	val = SDRAM0_READ(DDR0_42);
 
 	row = DDR_GET_VAL(val, DDR_APIN, DDR_APIN_SHIFT);
 	if (row > max_row)
diff --git a/arch/powerpc/boot/dts/mgcoge.dts b/arch/powerpc/boot/dts/mgcoge.dts
index a2dd5f1da621..7de068991bde 100644
--- a/arch/powerpc/boot/dts/mgcoge.dts
+++ b/arch/powerpc/boot/dts/mgcoge.dts
@@ -224,7 +224,7 @@
 				reg = <0x11a80 0x40 0x89fc 0x2>;
 				interrupts = <2 8>;
 				interrupt-parent = <&PIC>;
-				gpios = < &cpm2_pio_d 19 0>;
+				cs-gpios = < &cpm2_pio_d 19 0>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 				ds3106@1 {
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index b6257186528e..ecebc27a2898 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -249,7 +249,7 @@
 			reg = <0x4c0 0x40>;
 			interrupts = <2>;
 			interrupt-parent = <&qeic>;
-			gpios = <&qe_pio_d 13 0>;
+			cs-gpios = <&qe_pio_d 13 0>;
 			mode = "cpu-qe";
 
 			mmc-slot@0 {
diff --git a/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
index 1a8321ac105a..33bbe58c1ad0 100644
--- a/arch/powerpc/boot/dts/mpc8610_hpcd.dts
+++ b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
@@ -200,7 +200,7 @@
 			interrupts = <59 2>;
 			interrupt-parent = <&mpic>;
 			mode = "cpu";
-			gpios = <&sdcsr_pio 7 0>;
+			cs-gpios = <&sdcsr_pio 7 0>;
 			sleep = <&pmc 0x00000800 0>;
 
 			mmc-slot@0 {
diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig
index f0c8a07cc274..7705a5c3f4ea 100644
--- a/arch/powerpc/configs/44x/akebono_defconfig
+++ b/arch/powerpc/configs/44x/akebono_defconfig
@@ -59,7 +59,6 @@ CONFIG_BLK_DEV_SD=y
 # CONFIG_NET_VENDOR_DLINK is not set
 # CONFIG_NET_VENDOR_EMULEX is not set
 # CONFIG_NET_VENDOR_EXAR is not set
-# CONFIG_NET_VENDOR_HP is not set
 CONFIG_IBM_EMAC=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MELLANOX is not set
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index ed02f12dbd54..22dc0dadf576 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -10,8 +10,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_AMIGA_PARTITION=y
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_EBONY is not set
 CONFIG_SAM440EP=y
 CONFIG_CMDLINE_BOOL=y
diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig
index fdb11daeb688..789622ffd844 100644
--- a/arch/powerpc/configs/52xx/pcm030_defconfig
+++ b/arch/powerpc/configs/52xx/pcm030_defconfig
@@ -14,8 +14,6 @@ CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_CHRP is not set
 CONFIG_PPC_MPC52xx=y
 CONFIG_PPC_MPC5200_SIMPLE=y
diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig
index 648c6b3dccf9..24bf1bde1bb4 100644
--- a/arch/powerpc/configs/83xx/kmeter1_defconfig
+++ b/arch/powerpc/configs/83xx/kmeter1_defconfig
@@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_MSDOS_PARTITION is not set
-# CONFIG_IOSCHED_DEADLINE is not set
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_CHRP is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_83xx=y
diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig
index 510f7fd1f6a3..f55e23cb176c 100644
--- a/arch/powerpc/configs/adder875_defconfig
+++ b/arch/powerpc/configs/adder875_defconfig
@@ -9,7 +9,6 @@ CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_PPC_ADDER875=y
 CONFIG_8xx_COPYBACK=y
 CONFIG_GEN_RTC=y
diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig
index 6e08d9502d89..00d69965f898 100644
--- a/arch/powerpc/configs/ep8248e_defconfig
+++ b/arch/powerpc/configs/ep8248e_defconfig
@@ -6,7 +6,6 @@ CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
 CONFIG_SLAB=y
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_CHRP is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_82xx=y
diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig
index 9c1bf60f1e19..0e2e5e81a359 100644
--- a/arch/powerpc/configs/ep88xc_defconfig
+++ b/arch/powerpc/configs/ep88xc_defconfig
@@ -11,7 +11,6 @@ CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_PPC_EP88XC=y
 CONFIG_8xx_COPYBACK=y
 CONFIG_GEN_RTC=y
diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig
index 6ce4f206eac7..dcc8dccf54f3 100644
--- a/arch/powerpc/configs/mgcoge_defconfig
+++ b/arch/powerpc/configs/mgcoge_defconfig
@@ -12,7 +12,6 @@ CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_SLAB=y
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_82xx=y
 CONFIG_MGCOGE=y
diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig
index 1f3a045ab081..e39346b3dc3b 100644
--- a/arch/powerpc/configs/mpc512x_defconfig
+++ b/arch/powerpc/configs/mpc512x_defconfig
@@ -9,7 +9,6 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_CHRP is not set
 CONFIG_PPC_MPC512x=y
 CONFIG_MPC512x_LPBFIFO=y
diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig
index 0327a329316f..82a008c04eae 100644
--- a/arch/powerpc/configs/mpc885_ads_defconfig
+++ b/arch/powerpc/configs/mpc885_ads_defconfig
@@ -11,7 +11,6 @@ CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_8xx_COPYBACK=y
 CONFIG_GEN_RTC=y
 CONFIG_HZ_100=y
diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig
index 32841456a573..71749377d164 100644
--- a/arch/powerpc/configs/powernv_defconfig
+++ b/arch/powerpc/configs/powernv_defconfig
@@ -181,7 +181,6 @@ CONFIG_MLX5_FPGA=y
 CONFIG_MLX5_CORE_EN=y
 CONFIG_MLX5_CORE_IPOIB=y
 CONFIG_MYRI10GE=m
-CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
 CONFIG_USB_NET_DRIVERS=m
 # CONFIG_WLAN is not set
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index b250e6f5a7ca..7e68cb222c7b 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -189,7 +189,6 @@ CONFIG_MLX4_EN=m
 CONFIG_MYRI10GE=m
 CONFIG_S2IO=m
 CONFIG_PASEMI_MAC=y
-CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
 CONFIG_SUNGEM=y
 CONFIG_GELIC_NET=m
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 7e28919041cf..3e2f44f38ac5 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -507,7 +507,6 @@ CONFIG_FORCEDETH=m
 CONFIG_HAMACHI=m
 CONFIG_YELLOWFIN=m
 CONFIG_QLA3XXX=m
-CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
 CONFIG_8139CP=m
 CONFIG_8139TOO=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 26126b4d4de3..6b68109e248f 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -169,7 +169,6 @@ CONFIG_IXGBE=m
 CONFIG_I40E=m
 CONFIG_MLX4_EN=m
 CONFIG_MYRI10GE=m
-CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 069f67f12731..1b6bdad36b13 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -1,8 +1,3 @@
-CONFIG_PPC64=y
-CONFIG_ALTIVEC=y
-CONFIG_VSX=y
-CONFIG_NR_CPUS=2048
-CONFIG_CPU_LITTLE_ENDIAN=y
 CONFIG_KERNEL_XZ=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
@@ -28,17 +23,15 @@ CONFIG_EXPERT=y
 # CONFIG_AIO is not set
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
+# CONFIG_SLAB_MERGE_DEFAULT is not set
+CONFIG_SLAB_FREELIST_RANDOM=y
 CONFIG_SLAB_FREELIST_HARDENED=y
-CONFIG_JUMP_LABEL=y
-CONFIG_STRICT_KERNEL_RWX=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_SIG=y
-CONFIG_MODULE_SIG_FORCE=y
-CONFIG_MODULE_SIG_SHA512=y
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MQ_IOSCHED_DEADLINE is not set
-# CONFIG_MQ_IOSCHED_KYBER is not set
+CONFIG_PPC64=y
+CONFIG_ALTIVEC=y
+CONFIG_VSX=y
+CONFIG_NR_CPUS=2048
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_PANIC_TIMEOUT=30
 # CONFIG_PPC_VAS is not set
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
@@ -46,17 +39,27 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_IDLE=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC=y
+CONFIG_KEXEC_FILE=y
 CONFIG_PRESERVE_FA_DUMP=y
 CONFIG_IRQ_ALL_CPUS=y
 CONFIG_NUMA=y
-# CONFIG_COMPACTION is not set
-# CONFIG_MIGRATION is not set
 CONFIG_PPC_64K_PAGES=y
 CONFIG_SCHED_SMT=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="console=tty0 console=hvc0 ipr.fast_reboot=1 quiet"
 # CONFIG_SECCOMP is not set
 # CONFIG_PPC_MEM_KEYS is not set
+CONFIG_JUMP_LABEL=y
+CONFIG_STRICT_KERNEL_RWX=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_SIG_FORCE=y
+CONFIG_MODULE_SIG_SHA512=y
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MQ_IOSCHED_DEADLINE is not set
+# CONFIG_MQ_IOSCHED_KYBER is not set
+# CONFIG_COMPACTION is not set
+# CONFIG_MIGRATION is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -138,7 +141,6 @@ CONFIG_TIGON3=m
 CONFIG_BNX2X=m
 # CONFIG_NET_VENDOR_BROCADE is not set
 # CONFIG_NET_VENDOR_CADENCE is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CAVIUM is not set
 CONFIG_CHELSIO_T1=m
 # CONFIG_NET_VENDOR_CISCO is not set
@@ -147,7 +149,6 @@ CONFIG_CHELSIO_T1=m
 # CONFIG_NET_VENDOR_DLINK is not set
 CONFIG_BE2NET=m
 # CONFIG_NET_VENDOR_EZCHIP is not set
-# CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_E1000=m
 CONFIG_E1000E=m
@@ -155,7 +156,6 @@ CONFIG_IGB=m
 CONFIG_IXGB=m
 CONFIG_IXGBE=m
 CONFIG_I40E=m
-CONFIG_S2IO=m
 # CONFIG_NET_VENDOR_MARVELL is not set
 CONFIG_MLX4_EN=m
 # CONFIG_MLX4_CORE_GEN2 is not set
@@ -166,12 +166,12 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MYRI10GE=m
 # CONFIG_NET_VENDOR_NATSEMI is not set
+CONFIG_S2IO=m
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
-CONFIG_QLGE=m
 CONFIG_NETXEN_NIC=m
 CONFIG_QED=m
 CONFIG_QEDE=m
@@ -238,7 +238,6 @@ CONFIG_HID_CYPRESS=y
 CONFIG_HID_EZKEY=y
 CONFIG_HID_ITE=y
 CONFIG_HID_KENSINGTON=y
-CONFIG_HID_LOGITECH=y
 CONFIG_HID_MICROSOFT=y
 CONFIG_HID_MONTEREY=y
 CONFIG_USB_HIDDEV=y
@@ -275,6 +274,18 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
+CONFIG_ENCRYPTED_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_HARDENED_USERCOPY=y
+# CONFIG_HARDENED_USERCOPY_FALLBACK is not set
+CONFIG_HARDENED_USERCOPY_PAGESPAN=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY=y
+# CONFIG_INTEGRITY is not set
+CONFIG_LSM="yama,loadpin,safesetid,integrity"
+# CONFIG_CRYPTO_HW is not set
 CONFIG_CRC16=y
 CONFIG_CRC_ITU_T=y
 CONFIG_LIBCRC32C=y
@@ -285,17 +296,20 @@ CONFIG_LIBCRC32C=y
 # CONFIG_XZ_DEC_SPARC is not set
 CONFIG_PRINTK_TIME=y
 CONFIG_MAGIC_SYSRQ=y
+CONFIG_SLUB_DEBUG_ON=y
+CONFIG_SCHED_STACK_END_CHECK=y
 CONFIG_DEBUG_STACKOVERFLOW=y
+CONFIG_PANIC_ON_OOPS=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_HARDLOCKUP_DETECTOR=y
 CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y
 CONFIG_WQ_WATCHDOG=y
 # CONFIG_SCHED_DEBUG is not set
+CONFIG_DEBUG_SG=y
+CONFIG_DEBUG_NOTIFIERS=y
+CONFIG_BUG_ON_DATA_CORRUPTION=y
+CONFIG_DEBUG_CREDENTIALS=y
 # CONFIG_FTRACE is not set
-# CONFIG_RUNTIME_TESTING_MENU is not set
 CONFIG_XMON=y
-CONFIG_XMON_DEFAULT=y
-CONFIG_ENCRYPTED_KEYS=y
-# CONFIG_CRYPTO_ECHAINIV is not set
-# CONFIG_CRYPTO_HW is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig
index 29b19ec7e5d7..b964084e4056 100644
--- a/arch/powerpc/configs/storcenter_defconfig
+++ b/arch/powerpc/configs/storcenter_defconfig
@@ -77,5 +77,4 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_CRC_T10DIF=y
-# CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig
index ffed2b4256d6..eda8bfb2d0a3 100644
--- a/arch/powerpc/configs/tqm8xx_defconfig
+++ b/arch/powerpc/configs/tqm8xx_defconfig
@@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_SRCVERSION_ALL=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_IOSCHED_CFQ is not set
 CONFIG_TQM8XX=y
 CONFIG_8xx_COPYBACK=y
 # CONFIG_8xx_CPU15 is not set
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index a09595f00cab..9a53e29680f4 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -6,27 +6,28 @@
 
 #include <asm/machdep.h>
 
-static inline int arch_get_random_long(unsigned long *v)
+static inline bool __must_check arch_get_random_long(unsigned long *v)
 {
-	return 0;
+	return false;
 }
 
-static inline int arch_get_random_int(unsigned int *v)
+static inline bool __must_check arch_get_random_int(unsigned int *v)
 {
-	return 0;
+	return false;
 }
 
-static inline int arch_get_random_seed_long(unsigned long *v)
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
 	if (ppc_md.get_random_seed)
 		return ppc_md.get_random_seed(v);
 
-	return 0;
+	return false;
 }
-static inline int arch_get_random_seed_int(unsigned int *v)
+
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
 	unsigned long val;
-	int rc;
+	bool rc;
 
 	rc = arch_get_random_seed_long(&val);
 	if (rc)
@@ -34,16 +35,6 @@ static inline int arch_get_random_seed_int(unsigned int *v)
 
 	return rc;
 }
-
-static inline int arch_has_random(void)
-{
-	return 0;
-}
-
-static inline int arch_has_random_seed(void)
-{
-	return !!ppc_md.get_random_seed;
-}
 #endif /* CONFIG_ARCH_RANDOM */
 
 #ifdef CONFIG_PPC_POWERNV
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index f9dc597b0b86..3c0ba22dc360 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -102,41 +102,91 @@ static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 	isync();	/* Context sync required after mtsrin() */
 }
 
-static inline void allow_user_access(void __user *to, const void __user *from, u32 size)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      u32 size, unsigned long dir)
 {
 	u32 addr, end;
 
-	if (__builtin_constant_p(to) && to == NULL)
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	BUILD_BUG_ON(dir == KUAP_CURRENT);
+
+	if (!(dir & KUAP_WRITE))
 		return;
 
 	addr = (__force u32)to;
 
-	if (!addr || addr >= TASK_SIZE || !size)
+	if (unlikely(addr >= TASK_SIZE || !size))
 		return;
 
 	end = min(addr + size, TASK_SIZE);
+
 	current->thread.kuap = (addr & 0xf0000000) | ((((end - 1) >> 28) + 1) & 0xf);
 	kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end);	/* Clear Ks */
 }
 
-static inline void prevent_user_access(void __user *to, const void __user *from, u32 size)
+static __always_inline void prevent_user_access(void __user *to, const void __user *from,
+						u32 size, unsigned long dir)
 {
-	u32 addr = (__force u32)to;
-	u32 end = min(addr + size, TASK_SIZE);
+	u32 addr, end;
+
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+
+	if (dir == KUAP_CURRENT) {
+		u32 kuap = current->thread.kuap;
 
-	if (!addr || addr >= TASK_SIZE || !size)
+		if (unlikely(!kuap))
+			return;
+
+		addr = kuap & 0xf0000000;
+		end = kuap << 28;
+	} else if (dir & KUAP_WRITE) {
+		addr = (__force u32)to;
+		end = min(addr + size, TASK_SIZE);
+
+		if (unlikely(addr >= TASK_SIZE || !size))
+			return;
+	} else {
 		return;
+	}
 
 	current->thread.kuap = 0;
 	kuap_update_sr(mfsrin(addr) | SR_KS, addr, end);	/* set Ks */
 }
 
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+static inline unsigned long prevent_user_access_return(void)
+{
+	unsigned long flags = current->thread.kuap;
+	unsigned long addr = flags & 0xf0000000;
+	unsigned long end = flags << 28;
+	void __user *to = (__force void __user *)addr;
+
+	if (flags)
+		prevent_user_access(to, to, end - addr, KUAP_READ_WRITE);
+
+	return flags;
+}
+
+static inline void restore_user_access(unsigned long flags)
 {
+	unsigned long addr = flags & 0xf0000000;
+	unsigned long end = flags << 28;
+	void __user *to = (__force void __user *)addr;
+
+	if (flags)
+		allow_user_access(to, to, end - addr, KUAP_READ_WRITE);
+}
+
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+	unsigned long begin = regs->kuap & 0xf0000000;
+	unsigned long end = regs->kuap << 28;
+
 	if (!is_write)
 		return false;
 
-	return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !");
+	return WARN(address < begin || address >= end,
+		    "Bug: write fault blocked by segment registers !");
 }
 
 #endif /* CONFIG_PPC_KUAP */
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 998317702630..dc5c039eb28e 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -49,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
 
 #define get_hugepd_cache_index(x)  (x)
 
-#ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 				    void *table, int shift)
 {
@@ -66,13 +65,6 @@ static inline void __tlb_remove_table(void *_table)
 
 	pgtable_free(table, shift);
 }
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
-				    void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 0796533d37dd..5b39c11e884a 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -193,7 +193,12 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
 #else
 #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
 #endif
+
+#ifdef CONFIG_KASAN_VMALLOC
+#define VMALLOC_END	_ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#else
 #define VMALLOC_END	ioremap_bot
+#endif
 
 #ifndef __ASSEMBLY__
 #include <linux/sched.h>
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index f254de956d6a..90dd3a3fc8c7 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -63,6 +63,14 @@
  * because that would require an expensive read/modify write of the AMR.
  */
 
+static inline unsigned long get_kuap(void)
+{
+	if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
+		return 0;
+
+	return mfspr(SPRN_AMR);
+}
+
 static inline void set_kuap(unsigned long value)
 {
 	if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
@@ -77,25 +85,43 @@ static inline void set_kuap(unsigned long value)
 	isync();
 }
 
-static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size)
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size, unsigned long dir)
 {
 	// This is written so we can resolve to a single case at build time
-	if (__builtin_constant_p(to) && to == NULL)
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+	if (dir == KUAP_READ)
 		set_kuap(AMR_KUAP_BLOCK_WRITE);
-	else if (__builtin_constant_p(from) && from == NULL)
+	else if (dir == KUAP_WRITE)
 		set_kuap(AMR_KUAP_BLOCK_READ);
-	else
+	else if (dir == KUAP_READ_WRITE)
 		set_kuap(0);
+	else
+		BUILD_BUG();
 }
 
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size)
+				       unsigned long size, unsigned long dir)
+{
+	set_kuap(AMR_KUAP_BLOCKED);
+}
+
+static inline unsigned long prevent_user_access_return(void)
 {
+	unsigned long flags = get_kuap();
+
 	set_kuap(AMR_KUAP_BLOCKED);
+
+	return flags;
+}
+
+static inline void restore_user_access(unsigned long flags)
+{
+	set_kuap(flags);
 }
 
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
 		    (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index f6968c811026..a41e91bd0580 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -19,9 +19,7 @@ extern struct vmemmap_backing *vmemmap_list;
 extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
 extern void pmd_fragment_free(unsigned long *);
 extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
-#ifdef CONFIG_SMP
 extern void __tlb_remove_table(void *_table);
-#endif
 void pte_frag_destroy(void *pte_frag);
 
 static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index b01624e5c467..201a69e6a355 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1355,18 +1355,21 @@ static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_va
  * Like pmd_huge() and pmd_large(), but works regardless of config options
  */
 #define pmd_is_leaf pmd_is_leaf
+#define pmd_leaf pmd_is_leaf
 static inline bool pmd_is_leaf(pmd_t pmd)
 {
 	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 }
 
 #define pud_is_leaf pud_is_leaf
+#define pud_leaf pud_is_leaf
 static inline bool pud_is_leaf(pud_t pud)
 {
 	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
 }
 
 #define pgd_is_leaf pgd_is_leaf
+#define pgd_leaf pgd_is_leaf
 static inline bool pgd_is_leaf(pgd_t pgd)
 {
 	return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 74d0db511099..3e3cdfaa76c6 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -96,23 +96,6 @@ typedef u32		compat_sigset_word;
 
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
 	struct pt_regs *regs = current->thread.regs;
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index cf00ff0d121d..40a4d3c6fd99 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -212,6 +212,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_P9_TLBIE_STQ_BUG	LONG_ASM_CONST(0x0000400000000000)
 #define CPU_FTR_P9_TIDR			LONG_ASM_CONST(0x0000800000000000)
 #define CPU_FTR_P9_TLBIE_ERAT_BUG	LONG_ASM_CONST(0x0001000000000000)
+#define CPU_FTR_P9_RADIX_PREFETCH_BUG	LONG_ASM_CONST(0x0002000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -459,8 +460,10 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
 	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
 	    CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR)
-#define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
-#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
+#define CPU_FTRS_POWER9_DD2_0 (CPU_FTRS_POWER9 | CPU_FTR_P9_RADIX_PREFETCH_BUG)
+#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | \
+			       CPU_FTR_P9_RADIX_PREFETCH_BUG | \
+			       CPU_FTR_POWER9_DD2_1)
 #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
 			       CPU_FTR_P9_TM_HV_ASSIST | \
 			       CPU_FTR_P9_TM_XER_SO_BUG)
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index b3e214a97f3a..ca33f4ef6cb4 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -33,7 +33,7 @@
 #define FW_FEATURE_LLAN		ASM_CONST(0x0000000000010000)
 #define FW_FEATURE_BULK_REMOVE	ASM_CONST(0x0000000000020000)
 #define FW_FEATURE_XDABR	ASM_CONST(0x0000000000040000)
-#define FW_FEATURE_MULTITCE	ASM_CONST(0x0000000000080000)
+#define FW_FEATURE_PUT_TCE_IND	ASM_CONST(0x0000000000080000)
 #define FW_FEATURE_SPLPAR	ASM_CONST(0x0000000000100000)
 #define FW_FEATURE_LPAR		ASM_CONST(0x0000000000400000)
 #define FW_FEATURE_PS3_LV1	ASM_CONST(0x0000000000800000)
@@ -51,6 +51,7 @@
 #define FW_FEATURE_BLOCK_REMOVE ASM_CONST(0x0000001000000000)
 #define FW_FEATURE_PAPR_SCM 	ASM_CONST(0x0000002000000000)
 #define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
+#define FW_FEATURE_STUFF_TCE	ASM_CONST(0x0000008000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -63,7 +64,8 @@ enum {
 		FW_FEATURE_MIGRATE | FW_FEATURE_PERFMON | FW_FEATURE_CRQ |
 		FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
 		FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
-		FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
+		FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE |
+		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
 		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 13bd870609c3..e90c073e437e 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -350,6 +350,7 @@
 #define H_SVM_PAGE_OUT		0xEF04
 #define H_SVM_INIT_START	0xEF08
 #define H_SVM_INIT_DONE		0xEF0C
+#define H_SVM_INIT_ABORT	0xEF14
 
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 27ac6f5d2891..f2f8d8aa8e3b 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -34,7 +34,11 @@ struct arch_hw_breakpoint {
 #define HW_BRK_TYPE_PRIV_ALL	(HW_BRK_TYPE_USER | HW_BRK_TYPE_KERNEL | \
 				 HW_BRK_TYPE_HYP)
 
+#ifdef CONFIG_PPC_8xx
+#define HW_BREAKPOINT_ALIGN 0x3
+#else
 #define HW_BREAKPOINT_ALIGN 0x7
+#endif
 
 #define DABR_MAX_LEN	8
 #define DAWR_MAX_LEN	512
diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h
index 296e51c2f066..fbff9ff9032e 100644
--- a/arch/powerpc/include/asm/kasan.h
+++ b/arch/powerpc/include/asm/kasan.h
@@ -31,9 +31,11 @@
 void kasan_early_init(void);
 void kasan_mmu_init(void);
 void kasan_init(void);
+void kasan_late_init(void);
 #else
 static inline void kasan_init(void) { }
 static inline void kasan_mmu_init(void) { }
+static inline void kasan_late_init(void) { }
 #endif
 
 #endif /* __ASSEMBLY */
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index 5b5e39643a27..92bcd1a26d73 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -2,6 +2,16 @@
 #ifndef _ASM_POWERPC_KUP_H_
 #define _ASM_POWERPC_KUP_H_
 
+#define KUAP_READ	1
+#define KUAP_WRITE	2
+#define KUAP_READ_WRITE	(KUAP_READ | KUAP_WRITE)
+/*
+ * For prevent_user_access() only.
+ * Use the current saved situation instead of the to/from/size params.
+ * Used on book3s/32
+ */
+#define KUAP_CURRENT	4
+
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/kup-radix.h>
 #endif
@@ -42,32 +52,55 @@ void setup_kuap(bool disabled);
 #else
 static inline void setup_kuap(bool disabled) { }
 static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size) { }
+				     unsigned long size, unsigned long dir) { }
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size) { }
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write) { return false; }
+				       unsigned long size, unsigned long dir) { }
+static inline unsigned long prevent_user_access_return(void) { return 0UL; }
+static inline void restore_user_access(unsigned long flags) { }
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+	return false;
+}
 #endif /* CONFIG_PPC_KUAP */
 
 static inline void allow_read_from_user(const void __user *from, unsigned long size)
 {
-	allow_user_access(NULL, from, size);
+	allow_user_access(NULL, from, size, KUAP_READ);
 }
 
 static inline void allow_write_to_user(void __user *to, unsigned long size)
 {
-	allow_user_access(to, NULL, size);
+	allow_user_access(to, NULL, size, KUAP_WRITE);
+}
+
+static inline void allow_read_write_user(void __user *to, const void __user *from,
+					 unsigned long size)
+{
+	allow_user_access(to, from, size, KUAP_READ_WRITE);
 }
 
 static inline void prevent_read_from_user(const void __user *from, unsigned long size)
 {
-	prevent_user_access(NULL, from, size);
+	prevent_user_access(NULL, from, size, KUAP_READ);
 }
 
 static inline void prevent_write_to_user(void __user *to, unsigned long size)
 {
-	prevent_user_access(to, NULL, size);
+	prevent_user_access(to, NULL, size, KUAP_WRITE);
+}
+
+static inline void prevent_read_write_user(void __user *to, const void __user *from,
+					   unsigned long size)
+{
+	prevent_user_access(to, from, size, KUAP_READ_WRITE);
+}
+
+static inline void prevent_current_access_user(void)
+{
+	prevent_user_access(NULL, NULL, ~0UL, KUAP_CURRENT);
 }
 
 #endif /* !__ASSEMBLY__ */
 
-#endif /* _ASM_POWERPC_KUP_H_ */
+#endif /* _ASM_POWERPC_KUAP_H_ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
index 50204e228f16..5a9834e0e2d1 100644
--- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
+++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
@@ -19,8 +19,9 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
 unsigned long kvmppc_h_svm_init_start(struct kvm *kvm);
 unsigned long kvmppc_h_svm_init_done(struct kvm *kvm);
 int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn);
+unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm);
 void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
-			     struct kvm *kvm);
+			     struct kvm *kvm, bool skip_page_out);
 #else
 static inline int kvmppc_uvmem_init(void)
 {
@@ -62,6 +63,11 @@ static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
 	return H_UNSUPPORTED;
 }
 
+static inline unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
+{
+	return H_UNSUPPORTED;
+}
+
 static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 {
 	return -EFAULT;
@@ -69,6 +75,6 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 
 static inline void
 kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
-			struct kvm *kvm) { }
+			struct kvm *kvm, bool skip_page_out) { }
 #endif /* CONFIG_PPC_UV */
 #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0a398f2321c2..6e8b8ffd06ad 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -278,6 +278,7 @@ struct kvm_resize_hpt;
 /* Flag values for kvm_arch.secure_guest */
 #define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */
 #define KVMPPC_SECURE_INIT_DONE  0x2 /* H_SVM_INIT_DONE completed */
+#define KVMPPC_SECURE_INIT_ABORT 0x4 /* H_SVM_INIT_ABORT issued */
 
 struct kvm_arch {
 	unsigned int lpid;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3d2f871241a8..bc2494e5710a 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,8 +119,7 @@ extern int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr,
 			enum xlate_instdata xlid, enum xlate_readwrite xlrw,
 			struct kvmppc_pte *pte);
 
-extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
-                                                unsigned int id);
+extern int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_check_processor_compat(void);
@@ -274,7 +273,7 @@ struct kvmppc_ops {
 	void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags);
 	void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr);
 	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
-	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id);
+	int (*vcpu_create)(struct kvm_vcpu *vcpu);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
 	int (*check_requests)(struct kvm_vcpu *vcpu);
 	int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log);
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 58efca934311..360367c579de 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -238,11 +238,6 @@ static inline void arch_unmap(struct mm_struct *mm,
 		mm->context.vdso_base = 0;
 }
 
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-				     struct vm_area_struct *vma)
-{
-}
-
 #ifdef CONFIG_PPC_MEM_KEYS
 bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write,
 			       bool execute, bool foreign);
diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
index 1006a427e99c..85ed2390fb99 100644
--- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h
@@ -35,18 +35,33 @@
 #include <asm/reg.h>
 
 static inline void allow_user_access(void __user *to, const void __user *from,
-				     unsigned long size)
+				     unsigned long size, unsigned long dir)
 {
 	mtspr(SPRN_MD_AP, MD_APG_INIT);
 }
 
 static inline void prevent_user_access(void __user *to, const void __user *from,
-				       unsigned long size)
+				       unsigned long size, unsigned long dir)
 {
 	mtspr(SPRN_MD_AP, MD_APG_KUAP);
 }
 
-static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+static inline unsigned long prevent_user_access_return(void)
+{
+	unsigned long flags = mfspr(SPRN_MD_AP);
+
+	mtspr(SPRN_MD_AP, MD_APG_KUAP);
+
+	return flags;
+}
+
+static inline void restore_user_access(unsigned long flags)
+{
+	mtspr(SPRN_MD_AP, flags);
+}
+
+static inline bool
+bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 {
 	return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000),
 		    "Bug: fault blocked by AP register !");
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 552b96eef0c8..60c4d829152e 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -114,7 +114,12 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
 #else
 #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
 #endif
+
+#ifdef CONFIG_KASAN_VMALLOC
+#define VMALLOC_END	_ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#else
 #define VMALLOC_END	ioremap_bot
+#endif
 
 /*
  * Bits in a linux-style PTE.  These match the bits in the
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 332b13b4ecdb..29c43665a753 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -46,7 +46,6 @@ static inline void pgtable_free(void *table, int shift)
 
 #define get_hugepd_cache_index(x)	(x)
 
-#ifdef CONFIG_SMP
 static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
 {
 	unsigned long pgf = (unsigned long)table;
@@ -64,13 +63,6 @@ static inline void __tlb_remove_table(void *_table)
 	pgtable_free(table, shift);
 }
 
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
-	pgtable_free(table, shift);
-}
-#endif
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 7f1fd41e3065..86332080399a 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -209,7 +209,7 @@ static inline bool pfn_valid(unsigned long pfn)
  */
 #if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE)
 #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET))
-#define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET)
+#define __pa(x) ((phys_addr_t)(unsigned long)(x) - VIRT_PHYS_OFFSET)
 #else
 #ifdef CONFIG_PPC64
 /*
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index ea6ec65970ef..69f4cb3b7c56 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -223,12 +223,15 @@ struct pci_dn {
 extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
 					   int devfn);
 extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
-extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev);
-extern void remove_dev_pci_data(struct pci_dev *pdev);
 extern struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 					       struct device_node *dn);
 extern void pci_remove_device_node_info(struct device_node *dn);
 
+#ifdef CONFIG_PCI_IOV
+struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev);
+void remove_sriov_vf_pdns(struct pci_dev *pdev);
+#endif
+
 static inline int pci_device_from_OF_node(struct device_node *np,
 					  u8 *bus, u8 *devfn)
 {
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 327567b8f7d6..63ed7e3b0ba3 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -113,7 +113,6 @@ extern pgprot_t	pci_phys_mem_access_prot(struct file *file,
 					 pgprot_t prot);
 
 extern resource_size_t pcibios_io_space_offset(struct pci_controller *hose);
-extern void pcibios_setup_bus_devices(struct pci_bus *bus);
 extern void pcibios_setup_bus_self(struct pci_bus *bus);
 extern void pcibios_setup_phb_io_space(struct pci_controller *hose);
 extern void pcibios_scan_phb(struct pci_controller *hose);
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 0e4ec8cc37b7..8cc543ed114c 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -94,12 +94,6 @@ void mark_initmem_nx(void);
 static inline void mark_initmem_nx(void) { }
 #endif
 
-#ifdef CONFIG_PPC_DEBUG_WX
-void ptdump_check_wx(void);
-#else
-static inline void ptdump_check_wx(void) { }
-#endif
-
 /*
  * When used, PTE_FRAG_NR is defined in subarch pgtable.h
  * so we are sure it is included when arriving here.
diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h
index edcb1fc50aeb..d0ee0ede5767 100644
--- a/arch/powerpc/include/asm/pnv-pci.h
+++ b/arch/powerpc/include/asm/pnv-pci.h
@@ -15,6 +15,7 @@
 #define PCI_SLOT_ID_PREFIX	(1UL << 63)
 #define PCI_SLOT_ID(phb_id, bdfn)	\
 	(PCI_SLOT_ID_PREFIX | ((uint64_t)(bdfn) << 16) | (phb_id))
+#define PCI_PHB_SLOT_ID(phb_id)		(phb_id)
 
 extern int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id);
 extern int pnv_pci_get_device_tree(uint32_t phandle, void *buf, uint64_t len);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index a9993e7a443b..8387698bd5b6 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -163,6 +163,12 @@ struct thread_struct {
 #if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
 	unsigned long	kuap;		/* opened segments for user access */
 #endif
+#ifdef CONFIG_VMAP_STACK
+	unsigned long	srr0;
+	unsigned long	srr1;
+	unsigned long	dar;
+	unsigned long	dsisr;
+#endif
 	/* Debug Registers */
 	struct debug_reg debug;
 	struct thread_fp_state	fp_state;
@@ -412,6 +418,9 @@ static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
 extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
 extern unsigned long isa206_idle_insn_mayloss(unsigned long type);
+#ifdef CONFIG_PPC_970_NAP
+extern void power4_idle_nap(void);
+#endif
 
 extern unsigned long cpuidle_disable;
 enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF};
diff --git a/arch/powerpc/include/asm/reg_8xx.h b/arch/powerpc/include/asm/reg_8xx.h
index 07df35ee8cbc..299ee7be0f67 100644
--- a/arch/powerpc/include/asm/reg_8xx.h
+++ b/arch/powerpc/include/asm/reg_8xx.h
@@ -35,7 +35,21 @@
 #define SPRN_CMPE	152
 #define SPRN_CMPF	153
 #define SPRN_LCTRL1	156
+#define   LCTRL1_CTE_GT		0xc0000000
+#define   LCTRL1_CTF_LT		0x14000000
+#define   LCTRL1_CRWE_RW	0x00000000
+#define   LCTRL1_CRWE_RO	0x00040000
+#define   LCTRL1_CRWE_WO	0x000c0000
+#define   LCTRL1_CRWF_RW	0x00000000
+#define   LCTRL1_CRWF_RO	0x00010000
+#define   LCTRL1_CRWF_WO	0x00030000
 #define SPRN_LCTRL2	157
+#define   LCTRL2_LW0EN		0x80000000
+#define   LCTRL2_LW0LA_E	0x00000000
+#define   LCTRL2_LW0LA_F	0x04000000
+#define   LCTRL2_LW0LA_EandF	0x08000000
+#define   LCTRL2_LW0LADC	0x02000000
+#define   LCTRL2_SLW0EN		0x00000002
 #ifdef CONFIG_PPC_8xx
 #define SPRN_ICTRL	158
 #endif
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 8e1d0195ac36..a2270749b282 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -10,13 +10,31 @@
 #define _ASM_POWERPC_THREAD_INFO_H
 
 #include <asm/asm-const.h>
+#include <asm/page.h>
 
 #ifdef __KERNEL__
 
+#if defined(CONFIG_VMAP_STACK) && CONFIG_THREAD_SHIFT < PAGE_SHIFT
+#define THREAD_SHIFT		PAGE_SHIFT
+#else
 #define THREAD_SHIFT		CONFIG_THREAD_SHIFT
+#endif
 
 #define THREAD_SIZE		(1 << THREAD_SHIFT)
 
+/*
+ * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by
+ * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry
+ * assembly.
+ */
+#ifdef CONFIG_VMAP_STACK
+#define THREAD_ALIGN_SHIFT	(THREAD_SHIFT + 1)
+#else
+#define THREAD_ALIGN_SHIFT	THREAD_SHIFT
+#endif
+
+#define THREAD_ALIGN		(1 << THREAD_ALIGN_SHIFT)
+
 #ifndef __ASSEMBLY__
 #include <linux/cache.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index b2c0be93929d..7f3a8b902325 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -26,6 +26,17 @@
 
 #define tlb_flush tlb_flush
 extern void tlb_flush(struct mmu_gather *tlb);
+/*
+ * book3s:
+ * Hash does not use the linux page-tables, so we can avoid
+ * the TLB invalidate for page-table freeing, Radix otoh does use the
+ * page-tables and needs the TLBI.
+ *
+ * nohash:
+ * We still do TLB invalidate in the __pte_free_tlb routine before we
+ * add the page table pages to mmu gather table batch.
+ */
+#define tlb_needs_table_invalidate()	radix_enabled()
 
 /* Get the generic bits... */
 #include <asm-generic/tlb.h>
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index c92fe7fe9692..2f500debae21 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -91,9 +91,14 @@ static inline int __access_ok(unsigned long addr, unsigned long size,
 	__put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
 #define __get_user(x, ptr) \
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)), true)
 #define __put_user(x, ptr) \
-	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), true)
+
+#define __get_user_allowed(x, ptr) \
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)), false)
+#define __put_user_allowed(x, ptr) \
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), false)
 
 #define __get_user_inatomic(x, ptr) \
 	__get_user_nosleep((x), (ptr), sizeof(*(ptr)))
@@ -138,10 +143,9 @@ extern long __put_user_bad(void);
 		: "r" (x), "b" (addr), "i" (-EFAULT), "0" (err))
 #endif /* __powerpc64__ */
 
-#define __put_user_size(x, ptr, size, retval)			\
+#define __put_user_size_allowed(x, ptr, size, retval)		\
 do {								\
 	retval = 0;						\
-	allow_write_to_user(ptr, size);				\
 	switch (size) {						\
 	  case 1: __put_user_asm(x, ptr, retval, "stb"); break;	\
 	  case 2: __put_user_asm(x, ptr, retval, "sth"); break;	\
@@ -149,17 +153,26 @@ do {								\
 	  case 8: __put_user_asm2(x, ptr, retval); break;	\
 	  default: __put_user_bad();				\
 	}							\
+} while (0)
+
+#define __put_user_size(x, ptr, size, retval)			\
+do {								\
+	allow_write_to_user(ptr, size);				\
+	__put_user_size_allowed(x, ptr, size, retval);		\
 	prevent_write_to_user(ptr, size);			\
 } while (0)
 
-#define __put_user_nocheck(x, ptr, size)			\
+#define __put_user_nocheck(x, ptr, size, do_allow)			\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
 	if (!is_kernel_addr((unsigned long)__pu_addr))		\
 		might_fault();					\
 	__chk_user_ptr(ptr);					\
-	__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	if (do_allow)								\
+		__put_user_size((x), __pu_addr, (size), __pu_err);		\
+	else									\
+		__put_user_size_allowed((x), __pu_addr, (size), __pu_err);	\
 	__pu_err;						\
 })
 
@@ -236,13 +249,12 @@ extern long __get_user_bad(void);
 		: "b" (addr), "i" (-EFAULT), "0" (err))
 #endif /* __powerpc64__ */
 
-#define __get_user_size(x, ptr, size, retval)			\
+#define __get_user_size_allowed(x, ptr, size, retval)		\
 do {								\
 	retval = 0;						\
 	__chk_user_ptr(ptr);					\
 	if (size > sizeof(x))					\
 		(x) = __get_user_bad();				\
-	allow_read_from_user(ptr, size);			\
 	switch (size) {						\
 	case 1: __get_user_asm(x, ptr, retval, "lbz"); break;	\
 	case 2: __get_user_asm(x, ptr, retval, "lhz"); break;	\
@@ -250,6 +262,12 @@ do {								\
 	case 8: __get_user_asm2(x, ptr, retval);  break;	\
 	default: (x) = __get_user_bad();			\
 	}							\
+} while (0)
+
+#define __get_user_size(x, ptr, size, retval)			\
+do {								\
+	allow_read_from_user(ptr, size);			\
+	__get_user_size_allowed(x, ptr, size, retval);		\
 	prevent_read_from_user(ptr, size);			\
 } while (0)
 
@@ -260,7 +278,7 @@ do {								\
 #define __long_type(x) \
 	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
-#define __get_user_nocheck(x, ptr, size)			\
+#define __get_user_nocheck(x, ptr, size, do_allow)			\
 ({								\
 	long __gu_err;						\
 	__long_type(*(ptr)) __gu_val;				\
@@ -269,7 +287,10 @@ do {								\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
 	barrier_nospec();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	if (do_allow)								\
+		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);		\
+	else									\
+		__get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err);	\
 	(x) = (__typeof__(*(ptr)))__gu_val;			\
 	__gu_err;						\
 })
@@ -313,9 +334,9 @@ raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
 	unsigned long ret;
 
 	barrier_nospec();
-	allow_user_access(to, from, n);
+	allow_read_write_user(to, from, n);
 	ret = __copy_tofrom_user(to, from, n);
-	prevent_user_access(to, from, n);
+	prevent_read_write_user(to, from, n);
 	return ret;
 }
 #endif /* __powerpc64__ */
@@ -356,33 +377,40 @@ static inline unsigned long raw_copy_from_user(void *to,
 	return ret;
 }
 
-static inline unsigned long raw_copy_to_user(void __user *to,
-		const void *from, unsigned long n)
+static inline unsigned long
+raw_copy_to_user_allowed(void __user *to, const void *from, unsigned long n)
 {
-	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		ret = 1;
+		unsigned long ret = 1;
 
 		switch (n) {
 		case 1:
-			__put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret);
+			__put_user_size_allowed(*(u8 *)from, (u8 __user *)to, 1, ret);
 			break;
 		case 2:
-			__put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret);
+			__put_user_size_allowed(*(u16 *)from, (u16 __user *)to, 2, ret);
 			break;
 		case 4:
-			__put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret);
+			__put_user_size_allowed(*(u32 *)from, (u32 __user *)to, 4, ret);
 			break;
 		case 8:
-			__put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret);
+			__put_user_size_allowed(*(u64 *)from, (u64 __user *)to, 8, ret);
 			break;
 		}
 		if (ret == 0)
 			return 0;
 	}
 
+	return __copy_tofrom_user(to, (__force const void __user *)from, n);
+}
+
+static inline unsigned long
+raw_copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned long ret;
+
 	allow_write_to_user(to, n);
-	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
+	ret = raw_copy_to_user_allowed(to, from, n);
 	prevent_write_to_user(to, n);
 	return ret;
 }
@@ -428,4 +456,22 @@ extern long __copy_from_user_flushcache(void *dst, const void __user *src,
 extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
 			   size_t len);
 
+static __must_check inline bool user_access_begin(const void __user *ptr, size_t len)
+{
+	if (unlikely(!access_ok(ptr, len)))
+		return false;
+	allow_read_write_user((void __user *)ptr, ptr, len);
+	return true;
+}
+#define user_access_begin	user_access_begin
+#define user_access_end		prevent_current_access_user
+#define user_access_save	prevent_user_access_return
+#define user_access_restore	restore_user_access
+
+#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
+#define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e)
+#define unsafe_put_user(x, p, e) unsafe_op_wrap(__put_user_allowed(x, p), e)
+#define unsafe_copy_to_user(d, s, l, e) \
+	unsafe_op_wrap(raw_copy_to_user_allowed(d, s, l), e)
+
 #endif	/* _ARCH_POWERPC_UACCESS_H */
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index 40f13f3626d3..b9ef6cf50ea5 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -108,16 +108,22 @@ struct vdso_data {
 	__u32 stamp_sec_fraction;	/* fractional seconds of stamp_xtime */
 	__u32 hrtimer_res;		/* hrtimer resolution */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
-	__u32 dcache_block_size;	/* L1 d-cache block size     */
-	__u32 icache_block_size;	/* L1 i-cache block size     */
-	__u32 dcache_log_block_size;	/* L1 d-cache log block size */
-	__u32 icache_log_block_size;	/* L1 i-cache log block size */
 };
 
 #endif /* CONFIG_PPC64 */
 
 extern struct vdso_data *vdso_data;
 
+#else /* __ASSEMBLY__ */
+
+.macro get_datapage ptr, tmp
+	bcl	20, 31, .+4
+	mflr	\ptr
+	addi	\ptr, \ptr, (__kernel_datapage_offset - (.-4))@l
+	lwz	\tmp, 0(\ptr)
+	add	\ptr, \tmp, \ptr
+.endm
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index 24cdf97376c4..93f982dbb3d4 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -87,56 +87,56 @@ extern bool __xive_enabled;
 
 static inline bool xive_enabled(void) { return __xive_enabled; }
 
-extern bool xive_spapr_init(void);
-extern bool xive_native_init(void);
-extern void xive_smp_probe(void);
-extern int  xive_smp_prepare_cpu(unsigned int cpu);
-extern void xive_smp_setup_cpu(void);
-extern void xive_smp_disable_cpu(void);
-extern void xive_teardown_cpu(void);
-extern void xive_shutdown(void);
-extern void xive_flush_interrupt(void);
+bool xive_spapr_init(void);
+bool xive_native_init(void);
+void xive_smp_probe(void);
+int  xive_smp_prepare_cpu(unsigned int cpu);
+void xive_smp_setup_cpu(void);
+void xive_smp_disable_cpu(void);
+void xive_teardown_cpu(void);
+void xive_shutdown(void);
+void xive_flush_interrupt(void);
 
 /* xmon hook */
-extern void xmon_xive_do_dump(int cpu);
-extern int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d);
+void xmon_xive_do_dump(int cpu);
+int xmon_xive_get_irq_config(u32 hw_irq, struct irq_data *d);
 
 /* APIs used by KVM */
-extern u32 xive_native_default_eq_shift(void);
-extern u32 xive_native_alloc_vp_block(u32 max_vcpus);
-extern void xive_native_free_vp_block(u32 vp_base);
-extern int xive_native_populate_irq_data(u32 hw_irq,
-					 struct xive_irq_data *data);
-extern void xive_cleanup_irq_data(struct xive_irq_data *xd);
-extern u32 xive_native_alloc_irq(void);
-extern void xive_native_free_irq(u32 irq);
-extern int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
-
-extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
-				       __be32 *qpage, u32 order, bool can_escalate);
-extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
-
-extern void xive_native_sync_source(u32 hw_irq);
-extern void xive_native_sync_queue(u32 hw_irq);
-extern bool is_xive_irq(struct irq_chip *chip);
-extern int xive_native_enable_vp(u32 vp_id, bool single_escalation);
-extern int xive_native_disable_vp(u32 vp_id);
-extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
-extern bool xive_native_has_single_escalation(void);
-
-extern int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
-				      u64 *out_qpage,
-				      u64 *out_qsize,
-				      u64 *out_qeoi_page,
-				      u32 *out_escalate_irq,
-				      u64 *out_qflags);
-
-extern int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle,
-				       u32 *qindex);
-extern int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle,
-				       u32 qindex);
-extern int xive_native_get_vp_state(u32 vp_id, u64 *out_state);
-extern bool xive_native_has_queue_state_support(void);
+u32 xive_native_default_eq_shift(void);
+u32 xive_native_alloc_vp_block(u32 max_vcpus);
+void xive_native_free_vp_block(u32 vp_base);
+int xive_native_populate_irq_data(u32 hw_irq,
+				  struct xive_irq_data *data);
+void xive_cleanup_irq_data(struct xive_irq_data *xd);
+u32 xive_native_alloc_irq(void);
+void xive_native_free_irq(u32 irq);
+int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq);
+
+int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
+				__be32 *qpage, u32 order, bool can_escalate);
+void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
+
+void xive_native_sync_source(u32 hw_irq);
+void xive_native_sync_queue(u32 hw_irq);
+bool is_xive_irq(struct irq_chip *chip);
+int xive_native_enable_vp(u32 vp_id, bool single_escalation);
+int xive_native_disable_vp(u32 vp_id);
+int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
+bool xive_native_has_single_escalation(void);
+
+int xive_native_get_queue_info(u32 vp_id, uint32_t prio,
+			       u64 *out_qpage,
+			       u64 *out_qsize,
+			       u64 *out_qeoi_page,
+			       u32 *out_escalate_irq,
+			       u64 *out_qflags);
+
+int xive_native_get_queue_state(u32 vp_id, uint32_t prio, u32 *qtoggle,
+				u32 *qindex);
+int xive_native_set_queue_state(u32 vp_id, uint32_t prio, u32 qtoggle,
+				u32 qindex);
+int xive_native_get_vp_state(u32 vp_id, u64 *out_state);
+bool xive_native_has_queue_state_support(void);
 
 #else
 
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 157b0147921f..78a1b22d4fd8 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -62,8 +62,7 @@ obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
-obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
-obj-$(CONFIG_PPC_P7_NAP)	+= idle_book3s.o
+obj-$(CONFIG_PPC_BOOK3S_IDLE)	+= idle_book3s.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3d47aec7becf..c25e562f1cd9 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -127,6 +127,12 @@ int main(void)
 	OFFSET(KSP_VSID, thread_struct, ksp_vsid);
 #else /* CONFIG_PPC64 */
 	OFFSET(PGDIR, thread_struct, pgdir);
+#ifdef CONFIG_VMAP_STACK
+	OFFSET(SRR0, thread_struct, srr0);
+	OFFSET(SRR1, thread_struct, srr1);
+	OFFSET(DAR, thread_struct, dar);
+	OFFSET(DSISR, thread_struct, dsisr);
+#endif
 #ifdef CONFIG_SPE
 	OFFSET(THREAD_EVR0, thread_struct, evr[0]);
 	OFFSET(THREAD_ACC, thread_struct, acc);
@@ -389,11 +395,11 @@ int main(void)
 	OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec);
 	OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
 	OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
+#ifdef CONFIG_PPC64
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
 	OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
 	OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
 	OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size);
-#ifdef CONFIG_PPC64
 	OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
 	OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec);
 	OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec);
@@ -413,7 +419,10 @@ int main(void)
 	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
 	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
 	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
+	DEFINE(CLOCK_MAX, CLOCK_TAI);
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
+	DEFINE(EINVAL, EINVAL);
+	DEFINE(KTIME_LOW_RES, KTIME_LOW_RES);
 
 #ifdef CONFIG_BUG
 	DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 180b3a5d1001..182b4047c1ef 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -727,17 +727,20 @@ static __init void cpufeatures_cpu_quirks(void)
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
 	 */
-	if ((version & 0xffffefff) == 0x004e0200)
-		; /* DD2.0 has no feature flag */
-	else if ((version & 0xffffefff) == 0x004e0201)
+	if ((version & 0xffffefff) == 0x004e0200) {
+		/* DD2.0 has no feature flag */
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+	} else if ((version & 0xffffefff) == 0x004e0201) {
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
-	else if ((version & 0xffffefff) == 0x004e0202) {
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+	} else if ((version & 0xffffefff) == 0x004e0202) {
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
-	} else if ((version & 0xffff0000) == 0x004e0000)
+	} else if ((version & 0xffff0000) == 0x004e0000) {
 		/* DD2.1 and up have DD2_1 */
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+	}
 
 	if ((version & 0xffff0000) == 0x004e0000) {
 		cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index bc8a551013be..17cb3e9b5697 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -503,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	rc = 1;
 	if (pe->state & EEH_PE_ISOLATED) {
 		pe->check_count++;
-		if (pe->check_count % EEH_MAX_FAILS == 0) {
+		if (pe->check_count == EEH_MAX_FAILS) {
 			dn = pci_device_to_OF_node(dev);
 			if (dn)
 				location = of_get_property(dn, "ibm,loc-code",
@@ -1191,7 +1191,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 		eeh_rmv_from_parent_pe(edev);
 		eeh_addr_cache_rmv_dev(edev->pdev);
 		eeh_sysfs_remove_device(edev->pdev);
-		edev->mode &= ~EEH_DEV_SYSFS;
 
 		/*
 		 * We definitely should have the PCI device removed
@@ -1296,17 +1295,11 @@ void eeh_remove_device(struct pci_dev *dev)
 	edev->pdev = NULL;
 
 	/*
-	 * The flag "in_error" is used to trace EEH devices for VFs
-	 * in error state or not. It's set in eeh_report_error(). If
-	 * it's not set, eeh_report_{reset,resume}() won't be called
-	 * for the VF EEH device.
+	 * eeh_sysfs_remove_device() uses pci_dev_to_eeh_dev() so we need to
+	 * remove the sysfs files before clearing dev.archdata.edev
 	 */
-	edev->in_error = false;
-	dev->dev.archdata.edev = NULL;
-	if (!(edev->pe->state & EEH_PE_KEEP))
-		eeh_rmv_from_parent_pe(edev);
-	else
-		edev->mode |= EEH_DEV_DISCONNECTED;
+	if (edev->mode & EEH_DEV_SYSFS)
+		eeh_sysfs_remove_device(dev);
 
 	/*
 	 * We're removing from the PCI subsystem, that means
@@ -1317,8 +1310,19 @@ void eeh_remove_device(struct pci_dev *dev)
 	edev->mode |= EEH_DEV_NO_HANDLER;
 
 	eeh_addr_cache_rmv_dev(dev);
-	eeh_sysfs_remove_device(dev);
-	edev->mode &= ~EEH_DEV_SYSFS;
+
+	/*
+	 * The flag "in_error" is used to trace EEH devices for VFs
+	 * in error state or not. It's set in eeh_report_error(). If
+	 * it's not set, eeh_report_{reset,resume}() won't be called
+	 * for the VF EEH device.
+	 */
+	edev->in_error = false;
+	dev->dev.archdata.edev = NULL;
+	if (!(edev->pe->state & EEH_PE_KEEP))
+		eeh_rmv_from_parent_pe(edev);
+	else
+		edev->mode |= EEH_DEV_DISCONNECTED;
 }
 
 int eeh_unfreeze_pe(struct eeh_pe *pe)
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index cf11277ebd02..6b50bf15d8c1 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -159,18 +159,10 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo,
 
 static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 {
-	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 	int i;
 
-	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
-	if (!pdn) {
-		pr_warn("PCI: no pci dn found for dev=%s\n",
-			pci_name(dev));
-		return;
-	}
-
-	edev = pdn_to_eeh_dev(pdn);
+	edev = pci_dev_to_eeh_dev(dev);
 	if (!edev) {
 		pr_warn("PCI: no EEH dev found for %s\n",
 			pci_name(dev));
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 3dd1a422fc29..a1eaffe868de 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -525,12 +525,6 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata)
 
 		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
 		edev->pdev = NULL;
-
-		/*
-		 * We have to set the VF PE number to invalid one, which is
-		 * required to plug the VF successfully.
-		 */
-		pdn->pe_number = IODA_INVALID_PE;
 #endif
 		if (rmv_data)
 			list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index ab44d965a53c..4fb0f1e1017a 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -14,7 +14,7 @@
 /**
  * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
  * @_name: name of file in sysfs directory
- * @_memb: name of member in struct pci_dn to access
+ * @_memb: name of member in struct eeh_dev to access
  * @_format: printf format for display
  *
  * All of the attributes look very similar, so just
@@ -75,7 +75,7 @@ static ssize_t eeh_pe_state_store(struct device *dev,
 
 static DEVICE_ATTR_RW(eeh_pe_state);
 
-#ifdef CONFIG_PCI_IOV
+#if defined(CONFIG_PCI_IOV) && defined(CONFIG_PPC_PSERIES)
 static ssize_t eeh_notify_resume_show(struct device *dev,
 				      struct device_attribute *attr, char *buf)
 {
@@ -86,7 +86,6 @@ static ssize_t eeh_notify_resume_show(struct device *dev,
 	if (!edev || !edev->pe)
 		return -ENODEV;
 
-	pdn = pci_get_pdn(pdev);
 	return sprintf(buf, "%d\n", pdn->last_allow_rc);
 }
 
@@ -132,7 +131,7 @@ static void eeh_notify_resume_remove(struct pci_dev *pdev)
 #else
 static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; }
 static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { }
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_IOV && CONFIG PPC_PSERIES*/
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
@@ -160,22 +159,23 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
 
+	if (!edev) {
+		WARN_ON(eeh_enabled());
+		return;
+	}
+
+	edev->mode &= ~EEH_DEV_SYSFS;
+
 	/*
 	 * The parent directory might have been removed. We needn't
 	 * continue for that case.
 	 */
-	if (!pdev->dev.kobj.sd) {
-		if (edev)
-			edev->mode &= ~EEH_DEV_SYSFS;
+	if (!pdev->dev.kobj.sd)
 		return;
-	}
 
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
 	eeh_notify_resume_remove(pdev);
-
-	if (edev)
-		edev->mode &= ~EEH_DEV_SYSFS;
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e1a4c39b83b8..77abbc34bbe0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -140,6 +140,7 @@ transfer_to_handler:
 	stw	r12,_CTR(r11)
 	stw	r2,_XER(r11)
 	mfspr	r12,SPRN_SPRG_THREAD
+	tovirt_vmstack r12, r12
 	beq	2f			/* if from user, fix up THREAD.regs */
 	addi	r2, r12, -THREAD
 	addi	r11,r1,STACK_FRAME_OVERHEAD
@@ -179,11 +180,13 @@ transfer_to_handler:
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
          * check for stack overflow
          */
-	kuap_save_and_lock r11, r12, r9, r2, r0
+	kuap_save_and_lock r11, r12, r9, r2, r6
 	addi	r2, r12, -THREAD
+#ifndef CONFIG_VMAP_STACK
 	lwz	r9,KSP_LIMIT(r12)
 	cmplw	r1,r9			/* if r1 <= ksp_limit */
 	ble-	stack_ovf		/* then the kernel stack overflowed */
+#endif
 5:
 #if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
 	lwz	r12,TI_LOCAL_FLAGS(r2)
@@ -195,7 +198,8 @@ transfer_to_handler:
 transfer_to_handler_cont:
 3:
 	mflr	r9
-	tovirt(r2, r2)			/* set r2 to current */
+	tovirt_novmstack r2, r2 	/* set r2 to current */
+	tovirt_vmstack r9, r9
 	lwz	r11,0(r9)		/* virtual address of handler */
 	lwz	r9,4(r9)		/* where to go when done */
 #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
@@ -284,9 +288,11 @@ reenable_mmu:
 	rlwinm	r9,r9,0,~MSR_EE
 	lwz	r12,_LINK(r11)		/* and return to address in LR */
 	kuap_restore r11, r2, r3, r4, r5
+	lwz	r2, GPR2(r11)
 	b	fast_exception_return
 #endif
 
+#ifndef CONFIG_VMAP_STACK
 /*
  * On kernel stack overflow, load up an initial stack pointer
  * and call StackOverflow(regs), which should not return.
@@ -312,6 +318,7 @@ stack_ovf:
 	mtspr	SPRN_SRR1,r10
 	SYNC
 	RFI
+#endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 trace_syscall_entry_irq_off:
@@ -397,7 +404,7 @@ ret_from_syscall:
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
 	/* Note: We don't bother telling lockdep about it */
 	SYNC
-	MTMSRD(r10)
+	mtmsr	r10
 	lwz	r9,TI_FLAGS(r2)
 	li	r8,-MAX_ERRNO
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
@@ -554,7 +561,7 @@ syscall_exit_work:
 	 */
 	ori	r10,r10,MSR_EE
 	SYNC
-	MTMSRD(r10)
+	mtmsr	r10
 
 	/* Save NVGPRS if they're not saved already */
 	lwz	r4,_TRAP(r1)
@@ -621,7 +628,6 @@ ppc_swapcontext:
  */
 	.globl	handle_page_fault
 handle_page_fault:
-	stw	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_BOOK3S_32
 	andis.  r0,r5,DSISR_DABRMATCH@h
@@ -697,7 +703,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 	and.	r0,r0,r11	/* FP or altivec or SPE enabled? */
 	beq+	1f
 	andc	r11,r11,r0
-	MTMSRD(r11)
+	mtmsr	r11
 	isync
 1:	stw	r11,_MSR(r1)
 	mfcr	r10
@@ -831,7 +837,7 @@ ret_from_except:
 	/* Note: We don't bother telling lockdep about it */
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	SYNC			/* Some chip revs have problems here... */
-	MTMSRD(r10)		/* disable interrupts */
+	mtmsr	r10		/* disable interrupts */
 
 	lwz	r3,_MSR(r1)	/* Returning to user mode? */
 	andi.	r0,r3,MSR_PR
@@ -998,7 +1004,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	 */
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI)
 	SYNC
-	MTMSRD(r10)		/* clear the RI bit */
+	mtmsr	r10		/* clear the RI bit */
 	.globl exc_exit_restart
 exc_exit_restart:
 	lwz	r12,_NIP(r1)
@@ -1234,7 +1240,7 @@ do_resched:			/* r10 contains MSR_KERNEL here */
 #endif
 	ori	r10,r10,MSR_EE
 	SYNC
-	MTMSRD(r10)		/* hard-enable interrupts */
+	mtmsr	r10		/* hard-enable interrupts */
 	bl	schedule
 recheck:
 	/* Note: And we don't tell it we are disabling them again
@@ -1243,7 +1249,7 @@ recheck:
 	 */
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	SYNC
-	MTMSRD(r10)		/* disable interrupts */
+	mtmsr	r10		/* disable interrupts */
 	lwz	r9,TI_FLAGS(r2)
 	andi.	r0,r9,_TIF_NEED_RESCHED
 	bne-	do_resched
@@ -1252,7 +1258,7 @@ recheck:
 do_user_signal:			/* r10 contains MSR_KERNEL here */
 	ori	r10,r10,MSR_EE
 	SYNC
-	MTMSRD(r10)		/* hard-enable interrupts */
+	mtmsr	r10		/* hard-enable interrupts */
 	/* save r13-r31 in the exception frame, if not already done */
 	lwz	r3,_TRAP(r1)
 	andi.	r0,r3,1
@@ -1334,14 +1340,14 @@ _GLOBAL(enter_rtas)
 	lis	r6,1f@ha	/* physical return address for rtas */
 	addi	r6,r6,1f@l
 	tophys(r6,r6)
-	tophys(r7,r1)
+	tophys_novmstack r7, r1
 	lwz	r8,RTASENTRY(r4)
 	lwz	r4,RTASBASE(r4)
 	mfmsr	r9
 	stw	r9,8(r1)
 	LOAD_REG_IMMEDIATE(r0,MSR_KERNEL)
 	SYNC			/* disable interrupts so SRR0/1 */
-	MTMSRD(r0)		/* don't get trashed */
+	mtmsr	r0		/* don't get trashed */
 	li	r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
 	mtlr	r6
 	stw	r7, THREAD + RTAS_SP(r2)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a9a1d3cdb523..6ba675b0cf7d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -597,8 +597,7 @@ _GLOBAL(_switch)
 	std	r0,16(r1)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 	/* r3-r13 are caller saved -- Cort */
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_NVGPRS(r1)
 	std	r0,_NIP(r1)	/* Return to switch caller */
 	mfcr	r23
 	std	r23,_CCR(r1)
@@ -722,8 +721,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtcrf	0xFF,r6
 
 	/* r3-r13 are destroyed -- Cort */
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
+	REST_NVGPRS(r1)
 
 	/* convert old thread to its task_struct for return value */
 	addi	r3,r3,-THREAD
@@ -1155,8 +1153,7 @@ _GLOBAL(enter_rtas)
    	 */
 	SAVE_GPR(2, r1)			/* Save the TOC */
 	SAVE_GPR(13, r1)		/* Save paca */
-	SAVE_8GPRS(14, r1)		/* Save the non-volatiles */
-	SAVE_10GPRS(22, r1)		/* ditto */
+	SAVE_NVGPRS(r1)			/* Save the non-volatiles */
 
 	mfcr	r4
 	std	r4,_CCR(r1)
@@ -1263,8 +1260,7 @@ rtas_restore_regs:
 	/* relocation is on at this point */
 	REST_GPR(2, r1)			/* Restore the TOC */
 	REST_GPR(13, r1)		/* Restore paca */
-	REST_8GPRS(14, r1)		/* Restore the non-volatiles */
-	REST_10GPRS(22, r1)		/* ditto */
+	REST_NVGPRS(r1)			/* Restore the non-volatiles */
 
 	GET_PACA(r13)
 
@@ -1298,8 +1294,7 @@ _GLOBAL(enter_prom)
    	 */
 	SAVE_GPR(2, r1)
 	SAVE_GPR(13, r1)
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_NVGPRS(r1)
 	mfcr	r10
 	mfmsr	r11
 	std	r10,_CCR(r1)
@@ -1343,8 +1338,7 @@ _GLOBAL(enter_prom)
 	/* Restore other registers */
 	REST_GPR(2, r1)
 	REST_GPR(13, r1)
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
+	REST_NVGPRS(r1)
 	ld	r4,_CCR(r1)
 	mtcr	r4
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 46508b148e16..ffc15f4f079d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1408,22 +1408,9 @@ EXC_VIRT_NONE(0x4b00, 0x100)
  *
  * Call convention:
  *
- * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
- *
- * For hypercalls, the register convention is as follows:
- * r0 volatile
- * r1-2 nonvolatile
- * r3 volatile parameter and return value for status
- * r4-r10 volatile input and output value
- * r11 volatile hypercall number and output value
- * r12 volatile input and output value
- * r13-r31 nonvolatile
- * LR nonvolatile
- * CTR volatile
- * XER volatile
- * CR0-1 CR5-7 volatile
- * CR2-4 nonvolatile
- * Other registers nonvolatile
+ * syscall and hypercalls register conventions are documented in
+ * Documentation/powerpc/syscall64-abi.rst and
+ * Documentation/powerpc/papr_hcalls.rst respectively.
  *
  * The intersection of volatile registers that don't contain possible
  * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
@@ -2208,11 +2195,20 @@ __end_interrupts:
 DEFINE_FIXED_SYMBOL(__end_interrupts)
 
 #ifdef CONFIG_PPC_970_NAP
+	/*
+	 * Called by exception entry code if _TLF_NAPPING was set, this clears
+	 * the NAPPING flag, and redirects the exception exit to
+	 * power4_fixup_nap_return.
+	 */
+	.globl power4_fixup_nap
 EXC_COMMON_BEGIN(power4_fixup_nap)
 	andc	r9,r9,r10
 	std	r9,TI_LOCAL_FLAGS(r11)
-	ld	r10,_LINK(r1)		/* make idle task do the */
-	std	r10,_NIP(r1)		/* equivalent of a blr */
+	LOAD_REG_ADDR(r10, power4_idle_nap_return)
+	std	r10,_NIP(r1)
+	blr
+
+power4_idle_nap_return:
 	blr
 #endif
 
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 0bb991ddd264..3235a8da6af7 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -94,6 +94,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
 	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
+#ifdef CONFIG_VMAP_STACK
+	tovirt(r5, r5)
+#endif
 	lwz	r4,THREAD_FPEXC_MODE(r5)
 	ori	r9,r9,MSR_FP		/* enable FP for current */
 	or	r9,r9,r4
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 4a24f8f026c7..0493fcac6409 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -272,16 +272,21 @@ __secondary_hold_acknowledge:
  */
 	. = 0x200
 	DO_KVM  0x200
-	mtspr	SPRN_SPRG_SCRATCH0,r10
-	mtspr	SPRN_SPRG_SCRATCH1,r11
-	mfcr	r10
+MachineCheck:
+	EXCEPTION_PROLOG_0
+#ifdef CONFIG_VMAP_STACK
+	li	r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r11
+	isync
+#endif
 #ifdef CONFIG_PPC_CHRP
 	mfspr	r11, SPRN_SPRG_THREAD
+	tovirt_vmstack r11, r11
 	lwz	r11, RTAS_SP(r11)
 	cmpwi	cr1, r11, 0
 	bne	cr1, 7f
 #endif /* CONFIG_PPC_CHRP */
-	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_1 for_rtas=1
 7:	EXCEPTION_PROLOG_2
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_CHRP
@@ -296,24 +301,21 @@ __secondary_hold_acknowledge:
 	. = 0x300
 	DO_KVM  0x300
 DataAccess:
-	EXCEPTION_PROLOG
-	mfspr	r10,SPRN_DSISR
-	stw	r10,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	get_and_save_dar_dsisr_on_stack	r4, r5, r11
+BEGIN_MMU_FTR_SECTION
 #ifdef CONFIG_PPC_KUAP
-	andis.	r0,r10,(DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
 #else
-	andis.	r0,r10,(DSISR_BAD_FAULT_32S|DSISR_DABRMATCH)@h
+	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
 #endif
-	bne	1f			/* if not, try to put a PTE */
-	mfspr	r4,SPRN_DAR		/* into the hash table */
-	rlwinm	r3,r10,32-15,21,21	/* DSISR_STORE -> _PAGE_RW */
-BEGIN_MMU_FTR_SECTION
+	bne	handle_page_fault_tramp_2	/* if not, try to put a PTE */
+	rlwinm	r3, r5, 32 - 15, 21, 21		/* DSISR_STORE -> _PAGE_RW */
 	bl	hash_page
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
-1:	lwz	r5,_DSISR(r11)		/* get DSISR value */
-	mfspr	r4,SPRN_DAR
-	EXC_XFER_LITE(0x300, handle_page_fault)
-
+	b	handle_page_fault_tramp_1
+FTR_SECTION_ELSE
+	b	handle_page_fault_tramp_2
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
 
 /* Instruction access exception. */
 	. = 0x400
@@ -329,6 +331,7 @@ BEGIN_MMU_FTR_SECTION
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 1:	mr	r4,r12
 	andis.	r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
+	stw	r4, _DAR(r11)
 	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* External interrupt */
@@ -338,11 +341,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 	. = 0x600
 	DO_KVM  0x600
 Alignment:
-	EXCEPTION_PROLOG
-	mfspr	r4,SPRN_DAR
-	stw	r4,_DAR(r11)
-	mfspr	r5,SPRN_DSISR
-	stw	r5,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	save_dar_dsisr_on_stack r4, r5, r11
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_STD(0x600, alignment_exception)
 
@@ -645,6 +645,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
 
 	. = 0x3000
 
+handle_page_fault_tramp_1:
+	lwz	r4, _DAR(r11)
+	lwz	r5, _DSISR(r11)
+	/* fall through */
+handle_page_fault_tramp_2:
+	EXC_XFER_LITE(0x300, handle_page_fault)
+
+stack_overflow:
+	vmap_stack_overflow_exception
+
 AltiVecUnavailable:
 	EXCEPTION_PROLOG
 #ifdef CONFIG_ALTIVEC
@@ -917,6 +927,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 	ori	r4,r4,2f@l
 	tophys(r4,r4)
 	li	r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+
+	.align	4
 	mtspr	SPRN_SRR0,r4
 	mtspr	SPRN_SRR1,r3
 	SYNC
@@ -1058,6 +1070,8 @@ _ENTRY(update_bats)
 	rlwinm	r0, r6, 0, ~MSR_RI
 	rlwinm	r0, r0, 0, ~MSR_EE
 	mtmsr	r0
+
+	.align	4
 	mtspr	SPRN_SRR0, r4
 	mtspr	SPRN_SRR1, r3
 	SYNC
@@ -1097,6 +1111,8 @@ mmu_off:
 	andi.	r0,r3,MSR_DR|MSR_IR		/* MMU enabled? */
 	beqlr
 	andc	r3,r3,r0
+
+	.align	4
 	mtspr	SPRN_SRR0,r4
 	mtspr	SPRN_SRR1,r3
 	sync
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 8abc7783dbe5..a6a5fbbf8504 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -10,28 +10,60 @@
  * We assume sprg3 has the physical address of the current
  * task's thread_struct.
  */
+.macro EXCEPTION_PROLOG handle_dar_dsisr=0
+	EXCEPTION_PROLOG_0	handle_dar_dsisr=\handle_dar_dsisr
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2	handle_dar_dsisr=\handle_dar_dsisr
+.endm
 
-.macro EXCEPTION_PROLOG
+.macro EXCEPTION_PROLOG_0 handle_dar_dsisr=0
 	mtspr	SPRN_SPRG_SCRATCH0,r10
 	mtspr	SPRN_SPRG_SCRATCH1,r11
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r10, SPRN_SPRG_THREAD
+	.if	\handle_dar_dsisr
+	mfspr	r11, SPRN_DAR
+	stw	r11, DAR(r10)
+	mfspr	r11, SPRN_DSISR
+	stw	r11, DSISR(r10)
+	.endif
+	mfspr	r11, SPRN_SRR0
+	stw	r11, SRR0(r10)
+#endif
+	mfspr	r11, SPRN_SRR1		/* check whether user or kernel */
+#ifdef CONFIG_VMAP_STACK
+	stw	r11, SRR1(r10)
+#endif
 	mfcr	r10
-	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
+	andi.	r11, r11, MSR_PR
 .endm
 
-.macro EXCEPTION_PROLOG_1
-	mfspr	r11,SPRN_SRR1		/* check whether user or kernel */
-	andi.	r11,r11,MSR_PR
+.macro EXCEPTION_PROLOG_1 for_rtas=0
+#ifdef CONFIG_VMAP_STACK
+	.ifeq	\for_rtas
+	li	r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r11
+	isync
+	.endif
+	subi	r11, r1, INT_FRAME_SIZE		/* use r1 if kernel */
+#else
 	tophys(r11,r1)			/* use tophys(r1) if kernel */
+	subi	r11, r11, INT_FRAME_SIZE	/* alloc exc. frame */
+#endif
 	beq	1f
 	mfspr	r11,SPRN_SPRG_THREAD
+	tovirt_vmstack r11, r11
 	lwz	r11,TASK_STACK-THREAD(r11)
-	addi	r11,r11,THREAD_SIZE
-	tophys(r11,r11)
-1:	subi	r11,r11,INT_FRAME_SIZE	/* alloc exc. frame */
+	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+	tophys_novmstack r11, r11
+1:
+#ifdef CONFIG_VMAP_STACK
+	mtcrf	0x7f, r11
+	bt	32 - THREAD_ALIGN_SHIFT, stack_overflow
+#endif
 .endm
 
-.macro EXCEPTION_PROLOG_2
+.macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0
 	stw	r10,_CCR(r11)		/* save registers */
 	stw	r12,GPR12(r11)
 	stw	r9,GPR9(r11)
@@ -41,16 +73,33 @@
 	stw	r12,GPR11(r11)
 	mflr	r10
 	stw	r10,_LINK(r11)
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r12, SPRN_SPRG_THREAD
+	tovirt(r12, r12)
+	.if	\handle_dar_dsisr
+	lwz	r10, DAR(r12)
+	stw	r10, _DAR(r11)
+	lwz	r10, DSISR(r12)
+	stw	r10, _DSISR(r11)
+	.endif
+	lwz	r9, SRR1(r12)
+	lwz	r12, SRR0(r12)
+#else
 	mfspr	r12,SPRN_SRR0
 	mfspr	r9,SPRN_SRR1
+#endif
 	stw	r1,GPR1(r11)
 	stw	r1,0(r11)
-	tovirt(r1,r11)			/* set new kernel sp */
+	tovirt_novmstack r1, r11	/* set new kernel sp */
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #else
+#ifdef CONFIG_VMAP_STACK
+	li	r10, MSR_KERNEL & ~MSR_IR /* can take exceptions */
+#else
 	li	r10,MSR_KERNEL & ~(MSR_IR|MSR_DR) /* can take exceptions */
-	MTMSRD(r10)			/* (except for mach check in rtas) */
+#endif
+	mtmsr	r10			/* (except for mach check in rtas) */
 #endif
 	stw	r0,GPR0(r11)
 	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -62,25 +111,46 @@
 
 .macro SYSCALL_ENTRY trapno
 	mfspr	r12,SPRN_SPRG_THREAD
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r9, SPRN_SRR0
+	mfspr	r11, SPRN_SRR1
+	stw	r9, SRR0(r12)
+	stw	r11, SRR1(r12)
+#endif
 	mfcr	r10
 	lwz	r11,TASK_STACK-THREAD(r12)
-	mflr	r9
-	addi	r11,r11,THREAD_SIZE - INT_FRAME_SIZE
 	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
-	tophys(r11,r11)
+	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+#ifdef CONFIG_VMAP_STACK
+	li	r9, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r9
+	isync
+#endif
+	tovirt_vmstack r12, r12
+	tophys_novmstack r11, r11
+	mflr	r9
 	stw	r10,_CCR(r11)		/* save registers */
+	stw	r9, _LINK(r11)
+#ifdef CONFIG_VMAP_STACK
+	lwz	r10, SRR0(r12)
+	lwz	r9, SRR1(r12)
+#else
 	mfspr	r10,SPRN_SRR0
-	stw	r9,_LINK(r11)
 	mfspr	r9,SPRN_SRR1
+#endif
 	stw	r1,GPR1(r11)
 	stw	r1,0(r11)
-	tovirt(r1,r11)			/* set new kernel sp */
+	tovirt_novmstack r1, r11	/* set new kernel sp */
 	stw	r10,_NIP(r11)
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #else
+#ifdef CONFIG_VMAP_STACK
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~MSR_IR) /* can take exceptions */
+#else
 	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
-	MTMSRD(r10)			/* (except for mach check in rtas) */
+#endif
+	mtmsr	r10			/* (except for mach check in rtas) */
 #endif
 	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
 	stw	r2,GPR2(r11)
@@ -118,7 +188,7 @@
 #endif
 
 3:
-	tovirt(r2, r2)			/* set r2 to current */
+	tovirt_novmstack r2, r2 	/* set r2 to current */
 	lis	r11, transfer_to_syscall@h
 	ori	r11, r11, transfer_to_syscall@l
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -141,6 +211,54 @@
 	RFI				/* jump to handler, enable MMU */
 .endm
 
+.macro save_dar_dsisr_on_stack reg1, reg2, sp
+#ifndef CONFIG_VMAP_STACK
+	mfspr	\reg1, SPRN_DAR
+	mfspr	\reg2, SPRN_DSISR
+	stw	\reg1, _DAR(\sp)
+	stw	\reg2, _DSISR(\sp)
+#endif
+.endm
+
+.macro get_and_save_dar_dsisr_on_stack reg1, reg2, sp
+#ifdef CONFIG_VMAP_STACK
+	lwz	\reg1, _DAR(\sp)
+	lwz	\reg2, _DSISR(\sp)
+#else
+	save_dar_dsisr_on_stack \reg1, \reg2, \sp
+#endif
+.endm
+
+.macro tovirt_vmstack dst, src
+#ifdef CONFIG_VMAP_STACK
+	tovirt(\dst, \src)
+#else
+	.ifnc	\dst, \src
+	mr	\dst, \src
+	.endif
+#endif
+.endm
+
+.macro tovirt_novmstack dst, src
+#ifndef CONFIG_VMAP_STACK
+	tovirt(\dst, \src)
+#else
+	.ifnc	\dst, \src
+	mr	\dst, \src
+	.endif
+#endif
+.endm
+
+.macro tophys_novmstack dst, src
+#ifndef CONFIG_VMAP_STACK
+	tophys(\dst, \src)
+#else
+	.ifnc	\dst, \src
+	mr	\dst, \src
+	.endif
+#endif
+.endm
+
 /*
  * Note: code which follows this uses cr0.eq (set if from kernel),
  * r11, r12 (SRR0), and r9 (SRR1).
@@ -187,4 +305,28 @@ label:
 	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
 			  ret_from_except)
 
+.macro vmap_stack_overflow_exception
+#ifdef CONFIG_VMAP_STACK
+#ifdef CONFIG_SMP
+	mfspr	r11, SPRN_SPRG_THREAD
+	tovirt(r11, r11)
+	lwz	r11, TASK_CPU - THREAD(r11)
+	slwi	r11, r11, 3
+	addis	r11, r11, emergency_ctx@ha
+#else
+	lis	r11, emergency_ctx@ha
+#endif
+	lwz	r11, emergency_ctx@l(r11)
+	cmpwi	cr1, r11, 0
+	bne	cr1, 1f
+	lis	r11, init_thread_union@ha
+	addi	r11, r11, init_thread_union@l
+1:	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+	EXCEPTION_PROLOG_2
+	SAVE_NVGPRS(r11)
+	addi	r3, r1, STACK_FRAME_OVERHEAD
+	EXC_XFER_STD(0, stack_overflow_exception)
+#endif
+.endm
+
 #endif /* __HEAD_32_H__ */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 585ea1976550..9bb663977e84 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -313,6 +313,7 @@ _ENTRY(saved_ksp_limit)
 	START_EXCEPTION(0x0400, InstructionAccess)
 	EXCEPTION_PROLOG
 	mr	r4,r12			/* Pass SRR0 as arg2 */
+	stw	r4, _DEAR(r11)
 	li	r5,0			/* Pass zero as arg3 */
 	EXC_XFER_LITE(0x400, handle_page_fault)
 
@@ -676,6 +677,7 @@ DataAccess:
 	mfspr	r5,SPRN_ESR		/* Grab the ESR, save it, pass arg3 */
 	stw	r5,_ESR(r11)
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
+	stw	r4, _DEAR(r11)
 	EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Other PowerPC processors, namely those derived from the 6xx-series
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 19f583e18402..9922306ae512 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -127,56 +127,36 @@ instruction_counter:
 /* Machine check */
 	. = 0x200
 MachineCheck:
-	EXCEPTION_PROLOG
-	mfspr r4,SPRN_DAR
-	stw r4,_DAR(r11)
-	li r5,RPN_PATTERN
-	mtspr SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
-	mfspr r5,SPRN_DSISR
-	stw r5,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	save_dar_dsisr_on_stack r4, r5, r11
+	li	r6, RPN_PATTERN
+	mtspr	SPRN_DAR, r6	/* Tag DAR, to be used in DTLB Error */
 	addi r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_STD(0x200, machine_check_exception)
 
-/* Data access exception.
- * This is "never generated" by the MPC8xx.
- */
-	. = 0x300
-DataAccess:
-
-/* Instruction access exception.
- * This is "never generated" by the MPC8xx.
- */
-	. = 0x400
-InstructionAccess:
-
 /* External interrupt */
 	EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
 
 /* Alignment exception */
 	. = 0x600
 Alignment:
-	EXCEPTION_PROLOG
-	mfspr	r4,SPRN_DAR
-	stw	r4,_DAR(r11)
-	li	r5,RPN_PATTERN
-	mtspr	SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
-	mfspr	r5,SPRN_DSISR
-	stw	r5,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	save_dar_dsisr_on_stack r4, r5, r11
+	li	r6, RPN_PATTERN
+	mtspr	SPRN_DAR, r6	/* Tag DAR, to be used in DTLB Error */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_STD(0x600, alignment_exception)
+	b	.Lalignment_exception_ool
 
 /* Program check exception */
 	EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
 
-/* No FPU on MPC8xx.  This exception is not supposed to happen.
-*/
-	EXCEPTION(0x800, FPUnavailable, unknown_exception, EXC_XFER_STD)
-
 /* Decrementer */
 	EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
 
-	EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_STD)
+	/* With VMAP_STACK there's not enough room for this at 0x600 */
+	. = 0xa00
+.Lalignment_exception_ool:
+	EXC_XFER_STD(0x600, alignment_exception)
 
 /* System call */
 	. = 0xc00
@@ -185,25 +165,12 @@ SystemCall:
 
 /* Single step - not used on 601 */
 	EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD)
-	EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_STD)
 
 /* On the MPC8xx, this is a software emulation interrupt.  It occurs
  * for all unimplemented and illegal instructions.
  */
 	EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD)
 
-/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
-#ifdef CONFIG_PERF_EVENTS
-	patch_site	0f, patch__dtlbmiss_perf
-0:	lwz	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
-	addi	r10, r10, 1
-	stw	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	rfi
-#endif
-
 	. = 0x1100
 /*
  * For the MPC8xx, this is a software tablewalk to load the instruction
@@ -343,8 +310,8 @@ ITLBMissLinear:
 
 	. = 0x1200
 DataStoreTLBMiss:
-	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
+	mtspr	SPRN_DAR, r10
+	mtspr	SPRN_M_TW, r11
 	mfcr	r11
 
 	/* If we are faulting a kernel address, we have to use the
@@ -409,10 +376,10 @@ DataStoreTLBMiss:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
 
-0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
+0:	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
 	rfi
 	patch_site	0b, patch__dtlbmiss_exit_1
 
@@ -428,10 +395,10 @@ DTLBMissIMMR:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
 
-0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
+0:	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
 	rfi
 	patch_site	0b, patch__dtlbmiss_exit_2
 
@@ -465,10 +432,10 @@ DTLBMissLinear:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
 
-0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
+0:	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
 	rfi
 	patch_site	0b, patch__dtlbmiss_exit_3
 
@@ -486,6 +453,7 @@ InstructionTLBError:
 	tlbie	r4
 	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
 .Litlbie:
+	stw	r4, _DAR(r11)
 	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
@@ -494,58 +462,69 @@ InstructionTLBError:
  */
 	. = 0x1400
 DataTLBError:
-	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
-	mfcr	r10
-
+	EXCEPTION_PROLOG_0 handle_dar_dsisr=1
 	mfspr	r11, SPRN_DAR
-	cmpwi	cr0, r11, RPN_PATTERN
-	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
+	cmpwi	cr1, r11, RPN_PATTERN
+	beq-	cr1, FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
+#ifdef CONFIG_VMAP_STACK
+	li	r11, RPN_PATTERN
+	mtspr	SPRN_DAR, r11	/* Tag DAR, to be used in DTLB Error */
+#endif
 	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
-	mfspr	r5,SPRN_DSISR
-	stw	r5,_DSISR(r11)
-	mfspr	r4,SPRN_DAR
+	EXCEPTION_PROLOG_2 handle_dar_dsisr=1
+	get_and_save_dar_dsisr_on_stack r4, r5, r11
 	andis.	r10,r5,DSISR_NOHPTE@h
 	beq+	.Ldtlbie
 	tlbie	r4
 .Ldtlbie:
+#ifndef CONFIG_VMAP_STACK
 	li	r10,RPN_PATTERN
 	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
+#endif
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXC_XFER_LITE(0x300, handle_page_fault)
 
-	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_STD)
+/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
+#ifdef CONFIG_PERF_EVENTS
+	patch_site	0f, patch__dtlbmiss_perf
+0:	lwz	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+	addi	r10, r10, 1
+	stw	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
+	rfi
+#endif
+
+stack_overflow:
+	vmap_stack_overflow_exception
 
 /* On the MPC8xx, these next four traps are used for development
  * support of breakpoints and such.  Someday I will get around to
  * using them.
  */
-	. = 0x1c00
-DataBreakpoint:
-	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
-	mfcr	r10
-	mfspr	r11, SPRN_SRR0
-	cmplwi	cr0, r11, (.Ldtlbie - PAGE_OFFSET)@l
-	cmplwi	cr7, r11, (.Litlbie - PAGE_OFFSET)@l
-	beq-	cr0, 11f
-	beq-	cr7, 11f
+do_databreakpoint:
 	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
+	EXCEPTION_PROLOG_2 handle_dar_dsisr=1
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	mfspr	r4,SPRN_BAR
 	stw	r4,_DAR(r11)
+#ifdef CONFIG_VMAP_STACK
+	lwz	r5,_DSISR(r11)
+#else
 	mfspr	r5,SPRN_DSISR
+#endif
 	EXC_XFER_STD(0x1c00, do_break)
-11:
+
+	. = 0x1c00
+DataBreakpoint:
+	EXCEPTION_PROLOG_0 handle_dar_dsisr=1
+	mfspr	r11, SPRN_SRR0
+	cmplwi	cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l
+	cmplwi	cr7, r11, (.Litlbie - PAGE_OFFSET)@l
+	cror	4*cr1+eq, 4*cr1+eq, 4*cr7+eq
+	bne	cr1, do_databreakpoint
 	mtcr	r10
 	mfspr	r10, SPRN_SPRG_SCRATCH0
 	mfspr	r11, SPRN_SPRG_SCRATCH1
@@ -581,9 +560,9 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	mfspr	r10, SPRN_SRR0
 	mtspr	SPRN_MD_EPN, r10
 	rlwinm	r11, r10, 16, 0xfff8
-	cmpli	cr0, r11, PAGE_OFFSET@h
+	cmpli	cr1, r11, PAGE_OFFSET@h
 	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
-	blt+	3f
+	blt+	cr1, 3f
 	rlwinm	r11, r10, 16, 0xfff8
 
 0:	cmpli	cr7, r11, (PAGE_OFFSET + 0x1800000)@h
@@ -598,7 +577,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 3:
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
 	mtspr	SPRN_MD_TWC, r11
-	mtcr	r11
+	mtcrf	0x01, r11
 	mfspr	r11, SPRN_MD_TWC
 	lwz	r11, 0(r11)	/* Get the pte */
 	bt	28,200f		/* bit 28 = Large page (8M) */
@@ -611,16 +590,16 @@ FixupDAR:/* Entry point for dcbx workaround. */
  * no need to include them here */
 	xoris	r10, r11, 0x7c00	/* check if major OP code is 31 */
 	rlwinm	r10, r10, 0, 21, 5
-	cmpwi	cr0, r10, 2028	/* Is dcbz? */
-	beq+	142f
-	cmpwi	cr0, r10, 940	/* Is dcbi? */
-	beq+	142f
-	cmpwi	cr0, r10, 108	/* Is dcbst? */
-	beq+	144f		/* Fix up store bit! */
-	cmpwi	cr0, r10, 172	/* Is dcbf? */
-	beq+	142f
-	cmpwi	cr0, r10, 1964	/* Is icbi? */
-	beq+	142f
+	cmpwi	cr1, r10, 2028	/* Is dcbz? */
+	beq+	cr1, 142f
+	cmpwi	cr1, r10, 940	/* Is dcbi? */
+	beq+	cr1, 142f
+	cmpwi	cr1, r10, 108	/* Is dcbst? */
+	beq+	cr1, 144f		/* Fix up store bit! */
+	cmpwi	cr1, r10, 172	/* Is dcbf? */
+	beq+	cr1, 142f
+	cmpwi	cr1, r10, 1964	/* Is icbi? */
+	beq+	cr1, 142f
 141:	mfspr	r10,SPRN_M_TW
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
@@ -679,8 +658,9 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	add	r10, r10, r30	;b	151f
 	add	r10, r10, r31
 151:
-	rlwinm. r11,r11,19,24,28	/* offset into jump table for reg RA */
-	beq	152f			/* if reg RA is zero, don't add it */
+	rlwinm	r11,r11,19,24,28	/* offset into jump table for reg RA */
+	cmpwi	cr1, r11, 0
+	beq	cr1, 152f		/* if reg RA is zero, don't add it */
 	addi	r11, r11, 150b@l	/* add start of table */
 	mtctr	r11			/* load ctr with jump address */
 	rlwinm	r11,r11,0,16,10		/* make sure we don't execute this more than once */
@@ -688,7 +668,14 @@ FixupDAR:/* Entry point for dcbx workaround. */
 152:
 	mfdar	r11
 	mtctr	r11			/* restore ctr reg from DAR */
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r11, SPRN_SPRG_THREAD
+	stw	r10, DAR(r11)
+	mfspr	r10, SPRN_DSISR
+	stw	r10, DSISR(r11)
+#else
 	mtdar	r10			/* save fault EA to DAR */
+#endif
 	mfspr	r10,SPRN_M_TW
 	b	DARFixed		/* Go back to normal TLB handling */
 
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 2ae635df9026..37fc84ed90e3 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -467,6 +467,7 @@ label:
 	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r5,_ESR(r11);						      \
 	mfspr	r4,SPRN_DEAR;		/* Grab the DEAR */		      \
+	stw	r4, _DEAR(r11);						      \
 	EXC_XFER_LITE(0x0300, handle_page_fault)
 
 #define INSTRUCTION_STORAGE_EXCEPTION					      \
@@ -475,6 +476,7 @@ label:
 	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r5,_ESR(r11);						      \
 	mr      r4,r12;                 /* Pass SRR0 as arg2 */		      \
+	stw	r4, _DEAR(r11);						      \
 	li      r5,0;                   /* Pass zero as arg3 */		      \
 	EXC_XFER_LITE(0x0400, handle_page_fault)
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 6f7a3a7162c5..840af004041e 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -378,6 +378,7 @@ interrupt_base:
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
 	andis.	r10,r5,(ESR_ILK|ESR_DLK)@h
 	bne	1f
+	stw	r4, _DEAR(r11)
 	EXC_XFER_LITE(0x0300, handle_page_fault)
 1:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 58ce3d37c2a3..2462cd7c565c 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -160,6 +160,9 @@ static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw)
 		/* DAWR region can't cross 512 bytes boundary */
 		if ((start_addr >> 9) != (end_addr >> 9))
 			return -EINVAL;
+	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
+		/* 8xx can setup a range without limitation */
+		max_len = U16_MAX;
 	}
 
 	if (hw_len > max_len)
@@ -328,13 +331,11 @@ int hw_breakpoint_handler(struct die_args *args)
 	}
 
 	info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
-	if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		if (!dar_within_range(regs->dar, info))
-			info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
-	} else {
-		if (!stepping_handler(regs, bp, info))
-			goto out;
-	}
+	if (!dar_within_range(regs->dar, info))
+		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+
+	if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info))
+		goto out;
 
 	/*
 	 * As a policy, the callback is invoked in a 'trigger-after-execute'
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index a36fd053c3db..422e31d2f5a2 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -77,6 +77,31 @@ void arch_cpu_idle(void)
 
 int powersave_nap;
 
+#ifdef CONFIG_PPC_970_NAP
+void power4_idle(void)
+{
+	if (!cpu_has_feature(CPU_FTR_CAN_NAP))
+		return;
+
+	if (!powersave_nap)
+		return;
+
+	if (!prep_irq_for_idle())
+		return;
+
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		asm volatile("DSSALL ; sync" ::: "memory");
+
+	power4_idle_nap();
+
+	/*
+	 * power4_idle_nap returns with interrupts enabled (soft and hard).
+	 * to our caller with interrupts enabled (soft and hard). Our caller
+	 * can cope with either interrupts disabled or enabled upon return.
+	 */
+}
+#endif
+
 #ifdef CONFIG_SYSCTL
 /*
  * Register the sysctl to set/clear powersave_nap.
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index d32751994a62..22f249b6f58d 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -15,7 +15,9 @@
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/thread_info.h> /* TLF_NAPPING */
 
+#ifdef CONFIG_PPC_P7_NAP
 /*
  * Desired PSSCR in r3
  *
@@ -181,4 +183,22 @@ _GLOBAL(isa206_idle_insn_mayloss)
 	bne	2f
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
 2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+#endif
 
+#ifdef CONFIG_PPC_970_NAP
+_GLOBAL(power4_idle_nap)
+	LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
+	ld	r9,PACA_THREAD_INFO(r13)
+	ld	r8,TI_LOCAL_FLAGS(r9)
+	ori	r8,r8,_TLF_NAPPING
+	std	r8,TI_LOCAL_FLAGS(r9)
+	/*
+	 * NAPPING bit is set, from this point onward power4_fixup_nap
+	 * will cause exceptions to return to power4_idle_nap_return.
+	 */
+1:	sync
+	isync
+	mtmsrd	r7
+	isync
+	b	1b
+#endif
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
deleted file mode 100644
index 33c625329078..000000000000
--- a/arch/powerpc/kernel/idle_power4.S
+++ /dev/null
@@ -1,83 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  This file contains the power_save function for 970-family CPUs.
- */
-
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/irqflags.h>
-#include <asm/hw_irq.h>
-#include <asm/feature-fixups.h>
-
-#undef DEBUG
-
-	.text
-
-_GLOBAL(power4_idle)
-BEGIN_FTR_SECTION
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
-	/* Now check if user or arch enabled NAP mode */
-	LOAD_REG_ADDRBASE(r3,powersave_nap)
-	lwz	r4,ADDROFF(powersave_nap)(r3)
-	cmpwi	0,r4,0
-	beqlr
-
-	/* This sequence is similar to prep_irq_for_idle() */
-
-	/* Hard disable interrupts */
-	mfmsr	r7
-	rldicl	r0,r7,48,1
-	rotldi	r0,r0,16
-	mtmsrd	r0,1
-
-	/* Check if something happened while soft-disabled */
-	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
-	bne-	2f
-
-	/*
-	 * Soft-enable interrupts. This will make power4_fixup_nap return
-	 * to our caller with interrupts enabled (soft and hard). The caller
-	 * can cope with either interrupts disabled or enabled upon return.
-	 */
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/* Tell the tracer interrupts are on, because idle responds to them. */
-	mflr	r0
-	std	r0,16(r1)
-	stdu    r1,-128(r1)
-	bl	trace_hardirqs_on
-	addi    r1,r1,128
-	ld	r0,16(r1)
-	mtlr	r0
-	mfmsr	r7
-#endif /* CONFIG_TRACE_IRQFLAGS */
-
-	li	r0,IRQS_ENABLED
-	stb	r0,PACAIRQSOFTMASK(r13)	/* we'll hard-enable shortly */
-BEGIN_FTR_SECTION
-	DSSALL
-	sync
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	ld	r9, PACA_THREAD_INFO(r13)
-	ld	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
-	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
-	std	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
-	ori	r7,r7,MSR_EE
-	oris	r7,r7,MSR_POW@h
-1:	sync
-	isync
-	mtmsrd	r7
-	isync
-	b	1b
-
-2:	/* Return if an interrupt had happened while soft disabled */
-	/* Set the HARD_DIS flag because interrupts are now hard disabled */
-	ori	r0,r0,PACA_IRQ_HARD_DIS
-	stb	r0,PACAIRQHAPPENED(r13)
-	blr
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index add67498c126..5c9b11878555 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -50,6 +50,7 @@
 #include <linux/debugfs.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/vmalloc.h>
 
 #include <linux/uaccess.h>
 #include <asm/io.h>
@@ -664,8 +665,29 @@ void do_IRQ(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+static void *__init alloc_vm_stack(void)
+{
+	return __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START,
+				    VMALLOC_END, THREADINFO_GFP, PAGE_KERNEL,
+				     0, NUMA_NO_NODE, (void*)_RET_IP_);
+}
+
+static void __init vmap_irqstack_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		softirq_ctx[i] = alloc_vm_stack();
+		hardirq_ctx[i] = alloc_vm_stack();
+	}
+}
+
+
 void __init init_IRQ(void)
 {
+	if (IS_ENABLED(CONFIG_VMAP_STACK))
+		vmap_irqstack_init();
+
 	if (ppc_md.init_IRQ)
 		ppc_md.init_IRQ();
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 1c448cf25506..c6c03416a151 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -261,12 +261,6 @@ int pcibios_sriov_disable(struct pci_dev *pdev)
 
 #endif /* CONFIG_PCI_IOV */
 
-void pcibios_bus_add_device(struct pci_dev *pdev)
-{
-	if (ppc_md.pcibios_bus_add_device)
-		ppc_md.pcibios_bus_add_device(pdev);
-}
-
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -964,7 +958,7 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		phb->controller_ops.dma_bus_setup(bus);
 }
 
-static void pcibios_setup_device(struct pci_dev *dev)
+void pcibios_bus_add_device(struct pci_dev *dev)
 {
 	struct pci_controller *phb;
 	/* Fixup NUMA node as it may not be setup yet by the generic
@@ -985,17 +979,13 @@ static void pcibios_setup_device(struct pci_dev *dev)
 	pci_read_irq_line(dev);
 	if (ppc_md.pci_irq_fixup)
 		ppc_md.pci_irq_fixup(dev);
+
+	if (ppc_md.pcibios_bus_add_device)
+		ppc_md.pcibios_bus_add_device(dev);
 }
 
 int pcibios_add_device(struct pci_dev *dev)
 {
-	/*
-	 * We can only call pcibios_setup_device() after bus setup is complete,
-	 * since some of the platform specific DMA setup code depends on it.
-	 */
-	if (dev->bus->is_added)
-		pcibios_setup_device(dev);
-
 #ifdef CONFIG_PCI_IOV
 	if (ppc_md.pcibios_fixup_sriov)
 		ppc_md.pcibios_fixup_sriov(dev);
@@ -1004,24 +994,6 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
-void pcibios_setup_bus_devices(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	pr_debug("PCI: Fixup bus devices %d (%s)\n",
-		 bus->number, bus->self ? pci_name(bus->self) : "PHB");
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		/* Cardbus can call us to add new devices to a bus, so ignore
-		 * those who are already fully discovered
-		 */
-		if (pci_dev_is_added(dev))
-			continue;
-
-		pcibios_setup_device(dev);
-	}
-}
-
 void pcibios_set_master(struct pci_dev *dev)
 {
 	/* No special bus mastering setup handling */
@@ -1037,19 +1009,9 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 
 	/* Now fixup the bus bus */
 	pcibios_setup_bus_self(bus);
-
-	/* Now fixup devices on that bus */
-	pcibios_setup_bus_devices(bus);
 }
 EXPORT_SYMBOL(pcibios_fixup_bus);
 
-void pci_fixup_cardbus(struct pci_bus *bus)
-{
-	/* Now fixup devices on that bus */
-	pcibios_setup_bus_devices(bus);
-}
-
-
 static int skip_isa_ioresource_align(struct pci_dev *dev)
 {
 	if (pci_has_flag(PCI_CAN_SKIP_ISA_ALIGN) &&
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index fc62c4bc47b1..d6a67f814983 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -134,7 +134,6 @@ void pci_hp_add_devices(struct pci_bus *bus)
 		 */
 		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
 		pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		pcibios_setup_bus_devices(bus);
 		max = bus->busn_res.start;
 		/*
 		 * Scan bridges that are already configured. We don't touch
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 9524009ca1ae..4e654df55969 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -125,7 +125,7 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 }
 
 #ifdef CONFIG_PCI_IOV
-static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent,
 					   int vf_index,
 					   int busno, int devfn)
 {
@@ -151,17 +151,15 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
 
 	return pdn;
 }
-#endif
 
-struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev)
 {
-#ifdef CONFIG_PCI_IOV
 	struct pci_dn *parent, *pdn;
 	int i;
 
 	/* Only support IOV for now */
-	if (!pdev->is_physfn)
-		return pci_get_pdn(pdev);
+	if (WARN_ON(!pdev->is_physfn))
+		return NULL;
 
 	/* Check if VFs have been populated */
 	pdn = pci_get_pdn(pdev);
@@ -176,7 +174,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
 		struct eeh_dev *edev __maybe_unused;
 
-		pdn = add_one_dev_pci_data(parent, i,
+		pdn = add_one_sriov_vf_pdn(parent, i,
 					   pci_iov_virtfn_bus(pdev, i),
 					   pci_iov_virtfn_devfn(pdev, i));
 		if (!pdn) {
@@ -192,31 +190,17 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 		edev->physfn = pdev;
 #endif /* CONFIG_EEH */
 	}
-#endif /* CONFIG_PCI_IOV */
-
 	return pci_get_pdn(pdev);
 }
 
-void remove_dev_pci_data(struct pci_dev *pdev)
+void remove_sriov_vf_pdns(struct pci_dev *pdev)
 {
-#ifdef CONFIG_PCI_IOV
 	struct pci_dn *parent;
 	struct pci_dn *pdn, *tmp;
 	int i;
 
-	/*
-	 * VF and VF PE are created/released dynamically, so we need to
-	 * bind/unbind them.  Otherwise the VF and VF PE would be mismatched
-	 * when re-enabling SR-IOV.
-	 */
-	if (pdev->is_virtfn) {
-		pdn = pci_get_pdn(pdev);
-		pdn->pe_number = IODA_INVALID_PE;
-		return;
-	}
-
 	/* Only support IOV PF for now */
-	if (!pdev->is_physfn)
+	if (WARN_ON(!pdev->is_physfn))
 		return;
 
 	/* Check if VFs have been populated */
@@ -244,9 +228,22 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 				continue;
 
 #ifdef CONFIG_EEH
-			/* Release EEH device for the VF */
+			/*
+			 * Release EEH state for this VF. The PCI core
+			 * has already torn down the pci_dev for this VF, but
+			 * we're responsible to removing the eeh_dev since it
+			 * has the same lifetime as the pci_dn that spawned it.
+			 */
 			edev = pdn_to_eeh_dev(pdn);
 			if (edev) {
+				/*
+				 * We allocate pci_dn's for the totalvfs count,
+				 * but only only the vfs that were activated
+				 * have a configured PE.
+				 */
+				if (edev->pe)
+					eeh_rmv_from_parent_pe(edev);
+
 				pdn->edev = NULL;
 				kfree(edev);
 			}
@@ -258,8 +255,8 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 			kfree(pdn);
 		}
 	}
-#endif /* CONFIG_PCI_IOV */
 }
+#endif /* CONFIG_PCI_IOV */
 
 struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 					struct device_node *dn)
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index f91d7e94872e..c3024f104765 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -414,7 +414,6 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
 	 */
 	if (!rescan_existing)
 		pcibios_setup_bus_self(bus);
-	pcibios_setup_bus_devices(bus);
 
 	/* Now scan child busses */
 	for_each_pci_bridge(dev, bus)
diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c
index be3758d54e59..877817471e3c 100644
--- a/arch/powerpc/kernel/proc_powerpc.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -39,10 +39,10 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
 	return 0;
 }
 
-static const struct file_operations page_map_fops = {
-	.llseek	= page_map_seek,
-	.read	= page_map_read,
-	.mmap	= page_map_mmap
+static const struct proc_ops page_map_proc_ops = {
+	.proc_lseek	= page_map_seek,
+	.proc_read	= page_map_read,
+	.proc_mmap	= page_map_mmap,
 };
 
 
@@ -51,7 +51,7 @@ static int __init proc_ppc64_init(void)
 	struct proc_dir_entry *pde;
 
 	pde = proc_create_data("powerpc/systemcfg", S_IFREG | 0444, NULL,
-			       &page_map_fops, vdso_data);
+			       &page_map_proc_ops, vdso_data);
 	if (!pde)
 		return 1;
 	proc_set_size(pde, PAGE_SIZE);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4df94b6e2f32..fad50db9dcf2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -740,28 +740,6 @@ static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 		mtspr(SPRN_DABRX, dabrx);
 	return 0;
 }
-#elif defined(CONFIG_PPC_8xx)
-static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
-{
-	unsigned long addr = dabr & ~HW_BRK_TYPE_DABR;
-	unsigned long lctrl1 = 0x90000000; /* compare type: equal on E & F */
-	unsigned long lctrl2 = 0x8e000002; /* watchpoint 1 on cmp E | F */
-
-	if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
-		lctrl1 |= 0xa0000;
-	else if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
-		lctrl1 |= 0xf0000;
-	else if ((dabr & HW_BRK_TYPE_RDWR) == 0)
-		lctrl2 = 0;
-
-	mtspr(SPRN_LCTRL2, 0);
-	mtspr(SPRN_CMPE, addr);
-	mtspr(SPRN_CMPF, addr + 4);
-	mtspr(SPRN_LCTRL1, lctrl1);
-	mtspr(SPRN_LCTRL2, lctrl2);
-
-	return 0;
-}
 #else
 static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 {
@@ -782,6 +760,39 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk)
 	return __set_dabr(dabr, dabrx);
 }
 
+static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
+{
+	unsigned long lctrl1 = LCTRL1_CTE_GT | LCTRL1_CTF_LT | LCTRL1_CRWE_RW |
+			       LCTRL1_CRWF_RW;
+	unsigned long lctrl2 = LCTRL2_LW0EN | LCTRL2_LW0LADC | LCTRL2_SLW0EN;
+	unsigned long start_addr = brk->address & ~HW_BREAKPOINT_ALIGN;
+	unsigned long end_addr = (brk->address + brk->len - 1) | HW_BREAKPOINT_ALIGN;
+
+	if (start_addr == 0)
+		lctrl2 |= LCTRL2_LW0LA_F;
+	else if (end_addr == ~0U)
+		lctrl2 |= LCTRL2_LW0LA_E;
+	else
+		lctrl2 |= LCTRL2_LW0LA_EandF;
+
+	mtspr(SPRN_LCTRL2, 0);
+
+	if ((brk->type & HW_BRK_TYPE_RDWR) == 0)
+		return 0;
+
+	if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
+		lctrl1 |= LCTRL1_CRWE_RO | LCTRL1_CRWF_RO;
+	if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
+		lctrl1 |= LCTRL1_CRWE_WO | LCTRL1_CRWF_WO;
+
+	mtspr(SPRN_CMPE, start_addr - 1);
+	mtspr(SPRN_CMPF, end_addr + 1);
+	mtspr(SPRN_LCTRL1, lctrl1);
+	mtspr(SPRN_LCTRL2, lctrl2);
+
+	return 0;
+}
+
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
@@ -789,6 +800,8 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 	if (dawr_enabled())
 		// Power8 or later
 		set_dawr(brk);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		set_breakpoint_8xx(brk);
 	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
 		// Power7 or earlier
 		set_dabr(brk);
@@ -1264,16 +1277,6 @@ void show_user_instructions(struct pt_regs *regs)
 
 	pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
 
-	/*
-	 * Make sure the NIP points at userspace, not kernel text/data or
-	 * elsewhere.
-	 */
-	if (!__access_ok(pc, NR_INSN_TO_PRINT * sizeof(int), USER_DS)) {
-		pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
-			current->comm, current->pid);
-		return;
-	}
-
 	seq_buf_init(&s, buf, sizeof(buf));
 
 	while (n) {
@@ -1284,7 +1287,7 @@ void show_user_instructions(struct pt_regs *regs)
 		for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
 			int instr;
 
-			if (probe_kernel_address((const void *)pc, instr)) {
+			if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) {
 				seq_buf_printf(&s, "XXXXXXXX ");
 				continue;
 			}
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 487dcd8da4de..2d33f342a293 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -159,12 +159,12 @@ static int poweron_open(struct inode *inode, struct file *file)
 	return single_open(file, ppc_rtas_poweron_show, NULL);
 }
 
-static const struct file_operations ppc_rtas_poweron_operations = {
-	.open		= poweron_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.write		= ppc_rtas_poweron_write,
-	.release	= single_release,
+static const struct proc_ops ppc_rtas_poweron_proc_ops = {
+	.proc_open	= poweron_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= ppc_rtas_poweron_write,
+	.proc_release	= single_release,
 };
 
 static int progress_open(struct inode *inode, struct file *file)
@@ -172,12 +172,12 @@ static int progress_open(struct inode *inode, struct file *file)
 	return single_open(file, ppc_rtas_progress_show, NULL);
 }
 
-static const struct file_operations ppc_rtas_progress_operations = {
-	.open		= progress_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.write		= ppc_rtas_progress_write,
-	.release	= single_release,
+static const struct proc_ops ppc_rtas_progress_proc_ops = {
+	.proc_open	= progress_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= ppc_rtas_progress_write,
+	.proc_release	= single_release,
 };
 
 static int clock_open(struct inode *inode, struct file *file)
@@ -185,12 +185,12 @@ static int clock_open(struct inode *inode, struct file *file)
 	return single_open(file, ppc_rtas_clock_show, NULL);
 }
 
-static const struct file_operations ppc_rtas_clock_operations = {
-	.open		= clock_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.write		= ppc_rtas_clock_write,
-	.release	= single_release,
+static const struct proc_ops ppc_rtas_clock_proc_ops = {
+	.proc_open	= clock_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= ppc_rtas_clock_write,
+	.proc_release	= single_release,
 };
 
 static int tone_freq_open(struct inode *inode, struct file *file)
@@ -198,12 +198,12 @@ static int tone_freq_open(struct inode *inode, struct file *file)
 	return single_open(file, ppc_rtas_tone_freq_show, NULL);
 }
 
-static const struct file_operations ppc_rtas_tone_freq_operations = {
-	.open		= tone_freq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.write		= ppc_rtas_tone_freq_write,
-	.release	= single_release,
+static const struct proc_ops ppc_rtas_tone_freq_proc_ops = {
+	.proc_open	= tone_freq_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= ppc_rtas_tone_freq_write,
+	.proc_release	= single_release,
 };
 
 static int tone_volume_open(struct inode *inode, struct file *file)
@@ -211,12 +211,12 @@ static int tone_volume_open(struct inode *inode, struct file *file)
 	return single_open(file, ppc_rtas_tone_volume_show, NULL);
 }
 
-static const struct file_operations ppc_rtas_tone_volume_operations = {
-	.open		= tone_volume_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.write		= ppc_rtas_tone_volume_write,
-	.release	= single_release,
+static const struct proc_ops ppc_rtas_tone_volume_proc_ops = {
+	.proc_open	= tone_volume_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= ppc_rtas_tone_volume_write,
+	.proc_release	= single_release,
 };
 
 static int ppc_rtas_find_all_sensors(void);
@@ -238,17 +238,17 @@ static int __init proc_rtas_init(void)
 		return -ENODEV;
 
 	proc_create("powerpc/rtas/progress", 0644, NULL,
-		    &ppc_rtas_progress_operations);
+		    &ppc_rtas_progress_proc_ops);
 	proc_create("powerpc/rtas/clock", 0644, NULL,
-		    &ppc_rtas_clock_operations);
+		    &ppc_rtas_clock_proc_ops);
 	proc_create("powerpc/rtas/poweron", 0644, NULL,
-		    &ppc_rtas_poweron_operations);
+		    &ppc_rtas_poweron_proc_ops);
 	proc_create_single("powerpc/rtas/sensors", 0444, NULL,
 			ppc_rtas_sensors_show);
 	proc_create("powerpc/rtas/frequency", 0644, NULL,
-		    &ppc_rtas_tone_freq_operations);
+		    &ppc_rtas_tone_freq_proc_ops);
 	proc_create("powerpc/rtas/volume", 0644, NULL,
-		    &ppc_rtas_tone_volume_operations);
+		    &ppc_rtas_tone_volume_proc_ops);
 	proc_create_single("powerpc/rtas/rmo_buffer", 0400, NULL,
 			ppc_rtas_rmo_buf_show);
 	return 0;
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 84f794782c62..a99179d83538 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -655,7 +655,7 @@ struct rtas_flash_file {
 	const char *filename;
 	const char *rtas_call_name;
 	int *status;
-	const struct file_operations fops;
+	const struct proc_ops ops;
 };
 
 static const struct rtas_flash_file rtas_flash_files[] = {
@@ -663,36 +663,36 @@ static const struct rtas_flash_file rtas_flash_files[] = {
 		.filename	= "powerpc/rtas/" FIRMWARE_FLASH_NAME,
 		.rtas_call_name	= "ibm,update-flash-64-and-reboot",
 		.status		= &rtas_update_flash_data.status,
-		.fops.read	= rtas_flash_read_msg,
-		.fops.write	= rtas_flash_write,
-		.fops.release	= rtas_flash_release,
-		.fops.llseek	= default_llseek,
+		.ops.proc_read	= rtas_flash_read_msg,
+		.ops.proc_write	= rtas_flash_write,
+		.ops.proc_release = rtas_flash_release,
+		.ops.proc_lseek	= default_llseek,
 	},
 	{
 		.filename	= "powerpc/rtas/" FIRMWARE_UPDATE_NAME,
 		.rtas_call_name	= "ibm,update-flash-64-and-reboot",
 		.status		= &rtas_update_flash_data.status,
-		.fops.read	= rtas_flash_read_num,
-		.fops.write	= rtas_flash_write,
-		.fops.release	= rtas_flash_release,
-		.fops.llseek	= default_llseek,
+		.ops.proc_read	= rtas_flash_read_num,
+		.ops.proc_write	= rtas_flash_write,
+		.ops.proc_release = rtas_flash_release,
+		.ops.proc_lseek	= default_llseek,
 	},
 	{
 		.filename	= "powerpc/rtas/" VALIDATE_FLASH_NAME,
 		.rtas_call_name	= "ibm,validate-flash-image",
 		.status		= &rtas_validate_flash_data.status,
-		.fops.read	= validate_flash_read,
-		.fops.write	= validate_flash_write,
-		.fops.release	= validate_flash_release,
-		.fops.llseek	= default_llseek,
+		.ops.proc_read	= validate_flash_read,
+		.ops.proc_write	= validate_flash_write,
+		.ops.proc_release = validate_flash_release,
+		.ops.proc_lseek	= default_llseek,
 	},
 	{
 		.filename	= "powerpc/rtas/" MANAGE_FLASH_NAME,
 		.rtas_call_name	= "ibm,manage-flash-image",
 		.status		= &rtas_manage_flash_data.status,
-		.fops.read	= manage_flash_read,
-		.fops.write	= manage_flash_write,
-		.fops.llseek	= default_llseek,
+		.ops.proc_read	= manage_flash_read,
+		.ops.proc_write	= manage_flash_write,
+		.ops.proc_lseek	= default_llseek,
 	}
 };
 
@@ -723,7 +723,7 @@ static int __init rtas_flash_init(void)
 		const struct rtas_flash_file *f = &rtas_flash_files[i];
 		int token;
 
-		if (!proc_create(f->filename, 0600, NULL, &f->fops))
+		if (!proc_create(f->filename, 0600, NULL, &f->ops))
 			goto enomem;
 
 		/*
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 8d02e047f96a..89b798f8f656 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -385,12 +385,12 @@ static __poll_t rtas_log_poll(struct file *file, poll_table * wait)
 	return 0;
 }
 
-static const struct file_operations proc_rtas_log_operations = {
-	.read =		rtas_log_read,
-	.poll =		rtas_log_poll,
-	.open =		rtas_log_open,
-	.release =	rtas_log_release,
-	.llseek =	noop_llseek,
+static const struct proc_ops rtas_log_proc_ops = {
+	.proc_read	= rtas_log_read,
+	.proc_poll	= rtas_log_poll,
+	.proc_open	= rtas_log_open,
+	.proc_release	= rtas_log_release,
+	.proc_lseek	= noop_llseek,
 };
 
 static int enable_surveillance(int timeout)
@@ -572,7 +572,7 @@ static int __init rtas_init(void)
 		return -ENODEV;
 
 	entry = proc_create("powerpc/rtas/error_log", 0400, NULL,
-			    &proc_rtas_log_operations);
+			    &rtas_log_proc_ops);
 	if (!entry)
 		printk(KERN_ERR "Failed to create error_log proc entry\n");
 
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index c82577c4b15d..2dd0d9cb5a20 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -35,7 +35,7 @@ void exc_lvl_early_init(void);
 static inline void exc_lvl_early_init(void) { };
 #endif
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || defined(CONFIG_VMAP_STACK)
 void emergency_stack_init(void);
 #else
 static inline void emergency_stack_init(void) { };
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index dcffe927f5b9..5b49b26eb154 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -140,7 +140,7 @@ arch_initcall(ppc_init);
 
 static void *__init alloc_stack(void)
 {
-	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
+	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
 
 	if (!ptr)
 		panic("cannot allocate %d bytes for stack at %pS\n",
@@ -153,6 +153,9 @@ void __init irqstack_early_init(void)
 {
 	unsigned int i;
 
+	if (IS_ENABLED(CONFIG_VMAP_STACK))
+		return;
+
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by default */
 	for_each_possible_cpu(i) {
@@ -161,6 +164,18 @@ void __init irqstack_early_init(void)
 	}
 }
 
+#ifdef CONFIG_VMAP_STACK
+void *emergency_ctx[NR_CPUS] __ro_after_init;
+
+void __init emergency_stack_init(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		emergency_ctx[i] = alloc_stack();
+}
+#endif
+
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 void __init exc_lvl_early_init(void)
 {
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6104917a282d..e05e6dd67ae6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -633,7 +633,7 @@ static void *__init alloc_stack(unsigned long limit, int cpu)
 
 	BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
 
-	ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_SIZE,
+	ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_ALIGN,
 				     MEMBLOCK_LOW_LIMIT, limit,
 				     early_cpu_to_node(cpu));
 	if (!ptr)
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index a8b5ecb5b602..35b61bfc1b1a 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -518,3 +518,4 @@
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 014ff0701f24..82a3438300fd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1637,6 +1637,15 @@ void StackOverflow(struct pt_regs *regs)
 	panic("kernel stack overflow");
 }
 
+void stack_overflow_exception(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+
+	die("Kernel stack overflow", regs, SIGSEGV);
+
+	exception_exit(prev_state);
+}
+
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index eae9ddaecbcf..b9a108411c0d 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -728,11 +728,6 @@ static int __init vdso_init(void)
 	 */
 	vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT;
 	DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages);
-#else
-	vdso_data->dcache_block_size = L1_CACHE_BYTES;
-	vdso_data->dcache_log_block_size = L1_CACHE_SHIFT;
-	vdso_data->icache_block_size = L1_CACHE_BYTES;
-	vdso_data->icache_log_block_size = L1_CACHE_SHIFT;
 #endif /* CONFIG_PPC64 */
 
 
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 06f54d947057..e147bbdc12cd 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -2,9 +2,7 @@
 
 # List of files in the vdso, has to be asm only for now
 
-obj-vdso32-$(CONFIG_PPC64) = getcpu.o
-obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \
-		$(obj-vdso32-y)
+obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
 
 # Build rules
 
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 7f882e7b9f43..3440ddf21c8b 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -8,7 +8,9 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 
 	.text
 
@@ -22,42 +24,62 @@
  */
 V_FUNCTION_BEGIN(__kernel_sync_dicache)
   .cfi_startproc
+#ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	mr	r11,r3
-	bl	__get_datapage@local
+	get_datapage	r10, r0
 	mtlr	r12
-	mr	r10,r3
+#endif
 
+#ifdef CONFIG_PPC64
 	lwz	r7,CFG_DCACHE_BLOCKSZ(r10)
 	addi	r5,r7,-1
-	andc	r6,r11,r5		/* round low to line bdy */
+#else
+	li	r5, L1_CACHE_BYTES - 1
+#endif
+	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
+#ifdef CONFIG_PPC64
 	lwz	r9,CFG_DCACHE_LOGBLOCKSZ(r10)
 	srw.	r8,r8,r9		/* compute line count */
+#else
+	srwi.	r8, r8, L1_CACHE_SHIFT
+	mr	r7, r6
+#endif
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
 	mtctr	r8
 1:	dcbst	0,r6
+#ifdef CONFIG_PPC64
 	add	r6,r6,r7
+#else
+	addi	r6, r6, L1_CACHE_BYTES
+#endif
 	bdnz	1b
 	sync
 
 /* Now invalidate the instruction cache */
 
+#ifdef CONFIG_PPC64
 	lwz	r7,CFG_ICACHE_BLOCKSZ(r10)
 	addi	r5,r7,-1
-	andc	r6,r11,r5		/* round low to line bdy */
+	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5
 	lwz	r9,CFG_ICACHE_LOGBLOCKSZ(r10)
 	srw.	r8,r8,r9		/* compute line count */
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
+#endif
 	mtctr	r8
+#ifdef CONFIG_PPC64
 2:	icbi	0,r6
 	add	r6,r6,r7
+#else
+2:	icbi	0, r7
+	addi	r7, r7, L1_CACHE_BYTES
+#endif
 	bdnz	2b
 	isync
 	li	r3,0
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 6c7401bd284e..217bb630f8f9 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -10,35 +10,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 
 	.text
 	.global	__kernel_datapage_offset;
 __kernel_datapage_offset:
 	.long	0
 
-V_FUNCTION_BEGIN(__get_datapage)
-  .cfi_startproc
-	/* We don't want that exposed or overridable as we want other objects
-	 * to be able to bl directly to here
-	 */
-	.protected __get_datapage
-	.hidden __get_datapage
-
-	mflr	r0
-  .cfi_register lr,r0
-
-	bcl	20,31,data_page_branch
-data_page_branch:
-	mflr	r3
-	mtlr	r0
-	addi	r3, r3, __kernel_datapage_offset-data_page_branch
-	lwz	r0,0(r3)
-  .cfi_restore lr
-	add	r3,r0,r3
-	blr
-  .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
 /*
  * void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
  *
@@ -52,11 +30,10 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	mr	r4,r3
-	bl	__get_datapage@local
+	mr.	r4,r3
+	get_datapage	r3, r0
 	mtlr	r12
 	addi	r3,r3,CFG_SYSCALL_MAP32
-	cmpli	cr0,r4,0
 	beqlr
 	li	r0,NR_syscalls
 	stw	r0,0(r4)
@@ -75,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	bl	__get_datapage@local
+	get_datapage	r3, r0
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 	lwz	r3,CFG_TB_TICKS_PER_SEC(r3)
 	mtlr	r12
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index 63e914539e1a..ff5e214fec41 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -15,6 +15,7 @@
  * int __kernel_getcpu(unsigned *cpu, unsigned *node);
  *
  */
+#if defined(CONFIG_PPC64)
 V_FUNCTION_BEGIN(__kernel_getcpu)
   .cfi_startproc
 	mfspr	r5,SPRN_SPRG_VDSO_READ
@@ -24,10 +25,26 @@ V_FUNCTION_BEGIN(__kernel_getcpu)
 	rlwinm  r7,r5,16,31-15,31-0
 	beq	cr0,1f
 	stw	r6,0(r3)
-1:	beq	cr1,2f
-	stw	r7,0(r4)
-2:	crclr	cr0*4+so
+1:	crclr	cr0*4+so
 	li	r3,0			/* always success */
+	beqlr	cr1
+	stw	r7,0(r4)
+	blr
+  .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
+#elif !defined(CONFIG_SMP)
+V_FUNCTION_BEGIN(__kernel_getcpu)
+  .cfi_startproc
+	cmpwi	cr0, r3, 0
+	cmpwi	cr1, r4, 0
+	li	r5, 0
+	beq	cr0, 1f
+	stw	r5, 0(r3)
+1:	li	r3, 0			/* always success */
+	crclr	cr0*4+so
+	beqlr	cr1
+	stw	r5, 0(r4)
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_getcpu)
+#endif
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 3306672f57a9..a3951567118a 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -9,6 +9,7 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
@@ -31,28 +32,26 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	mflr	r12
   .cfi_register lr,r12
 
-	mr	r10,r3			/* r10 saves tv */
+	mr.	r10,r3			/* r10 saves tv */
 	mr	r11,r4			/* r11 saves tz */
-	bl	__get_datapage@local	/* get data page */
-	mr	r9, r3			/* datapage ptr in r9 */
-	cmplwi	r10,0			/* check if tv is NULL */
+	get_datapage	r9, r0
 	beq	3f
-	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
-	addi	r7,r7,1000000@l		/* so we get microseconds in r4 */
+	LOAD_REG_IMMEDIATE(r7, 1000000)	/* load up USEC_PER_SEC */
 	bl	__do_get_tspec@local	/* get sec/usec from tb & kernel */
 	stw	r3,TVAL32_TV_SEC(r10)
 	stw	r4,TVAL32_TV_USEC(r10)
 
 3:	cmplwi	r11,0			/* check if tz is NULL */
-	beq	1f
+	mtlr	r12
+	crclr	cr0*4+so
+	li	r3,0
+	beqlr
+
 	lwz	r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
 	lwz	r5,CFG_TZ_DSTTIME(r9)
 	stw	r4,TZONE_TZ_MINWEST(r11)
 	stw	r5,TZONE_TZ_DSTTIME(r11)
 
-1:	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_gettimeofday)
@@ -69,17 +68,23 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	cmpli	cr0,r3,CLOCK_REALTIME
 	cmpli	cr1,r3,CLOCK_MONOTONIC
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-	bne	cr0,99f
+
+	cmpli	cr5,r3,CLOCK_REALTIME_COARSE
+	cmpli	cr6,r3,CLOCK_MONOTONIC_COARSE
+	cror	cr5*4+eq,cr5*4+eq,cr6*4+eq
+
+	cror	cr0*4+eq,cr0*4+eq,cr5*4+eq
+	bne	cr0, .Lgettime_fallback
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
 	mr	r11,r4			/* r11 saves tp */
-	bl	__get_datapage@local	/* get data page */
-	mr	r9,r3			/* datapage ptr in r9 */
-	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
-	ori	r7,r7,NSEC_PER_SEC@l
-50:	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
-	bne	cr1,80f			/* not monotonic -> all done */
+	get_datapage	r9, r0
+	LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC)	/* load up NSEC_PER_SEC */
+	beq	cr5, .Lcoarse_clocks
+.Lprecise_clocks:
+	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
+	bne	cr1, .Lfinish		/* not monotonic -> all done */
 
 	/*
 	 * CLOCK_MONOTONIC
@@ -103,12 +108,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	add	r9,r9,r0
 	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
-	bne-	50b
+	bne-	.Lprecise_clocks
+	b	.Lfinish_monotonic
+
+	/*
+	 * For coarse clocks we get data directly from the vdso data page, so
+	 * we don't need to call __do_get_tspec, but we still need to do the
+	 * counter trick.
+	 */
+.Lcoarse_clocks:
+	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+	andi.	r0,r8,1                 /* pending update ? loop */
+	bne-	.Lcoarse_clocks
+	add	r9,r9,r0		/* r0 is already 0 */
+
+	/*
+	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+	 * too
+	 */
+	lwz	r3,STAMP_XTIME_SEC+LOPART(r9)
+	lwz	r4,STAMP_XTIME_NSEC+LOPART(r9)
+	bne	cr6,1f
+
+	/* CLOCK_MONOTONIC_COARSE */
+	lwz	r5,(WTOM_CLOCK_SEC+LOPART)(r9)
+	lwz	r6,WTOM_CLOCK_NSEC(r9)
+
+	/* check if counter has updated */
+	or	r0,r6,r5
+1:	or	r0,r0,r3
+	or	r0,r0,r4
+	xor	r0,r0,r0
+	add	r3,r3,r0
+	lwz	r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
+	cmpl	cr0,r0,r8               /* check if updated */
+	bne-	.Lcoarse_clocks
+
+	/* Counter has not updated, so continue calculating proper values for
+	 * sec and nsec if monotonic coarse, or just return with the proper
+	 * values for realtime.
+	 */
+	bne	cr6, .Lfinish
 
 	/* Calculate and store result. Note that this mimics the C code,
 	 * which may cause funny results if nsec goes negative... is that
 	 * possible at all ?
 	 */
+.Lfinish_monotonic:
 	add	r3,r3,r5
 	add	r4,r4,r6
 	cmpw	cr0,r4,r7
@@ -116,11 +162,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	blt	1f
 	subf	r4,r7,r4
 	addi	r3,r3,1
-1:	bge	cr1,80f
+1:	bge	cr1, .Lfinish
 	addi	r3,r3,-1
 	add	r4,r4,r7
 
-80:	stw	r3,TSPC32_TV_SEC(r11)
+.Lfinish:
+	stw	r3,TSPC32_TV_SEC(r11)
 	stw	r4,TSPC32_TV_NSEC(r11)
 
 	mtlr	r12
@@ -131,7 +178,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-99:
+.Lgettime_fallback:
 	li	r0,__NR_clock_gettime
   .cfi_restore lr
 	sc
@@ -149,17 +196,20 @@ V_FUNCTION_END(__kernel_clock_gettime)
 V_FUNCTION_BEGIN(__kernel_clock_getres)
   .cfi_startproc
 	/* Check for supported clock IDs */
-	cmpwi	cr0,r3,CLOCK_REALTIME
-	cmpwi	cr1,r3,CLOCK_MONOTONIC
-	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-	bne	cr0,99f
+	cmplwi	cr0, r3, CLOCK_MAX
+	cmpwi	cr1, r3, CLOCK_REALTIME_COARSE
+	cmpwi	cr7, r3, CLOCK_MONOTONIC_COARSE
+	bgt	cr0, 99f
+	LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES)
+	beq	cr1, 1f
+	beq	cr7, 1f
 
 	mflr	r12
   .cfi_register lr,r12
-	bl	__get_datapage@local	/* get data page */
+	get_datapage	r3, r0
 	lwz	r5, CLOCK_HRTIMER_RES(r3)
 	mtlr	r12
-	li	r3,0
+1:	li	r3,0
 	cmpli	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
@@ -168,11 +218,11 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	blr
 
 	/*
-	 * syscall fallback
+	 * invalid clock
 	 */
 99:
-	li	r0,__NR_clock_getres
-	sc
+	li	r3, EINVAL
+	crset	so
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_clock_getres)
@@ -190,16 +240,15 @@ V_FUNCTION_BEGIN(__kernel_time)
   .cfi_register lr,r12
 
 	mr	r11,r3			/* r11 holds t */
-	bl	__get_datapage@local
-	mr	r9, r3			/* datapage ptr in r9 */
+	get_datapage	r9, r0
 
 	lwz	r3,STAMP_XTIME_SEC+LOPART(r9)
 
 	cmplwi	r11,0			/* check if t is NULL */
-	beq	2f
-	stw	r3,0(r11)		/* store result at *t */
-2:	mtlr	r12
+	mtlr	r12
 	crclr	cr0*4+so
+	beqlr
+	stw	r3,0(r11)		/* store result at *t */
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_time)
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 00c025ba4a92..5206c2eb2a1d 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -155,7 +155,7 @@ VERSION
 		__kernel_sync_dicache_p5;
 		__kernel_sigtramp32;
 		__kernel_sigtramp_rt32;
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || !defined(CONFIG_SMP)
 		__kernel_getcpu;
 #endif
 
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 8eb867dbad5f..25c14a0981bf 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -67,6 +67,9 @@ _GLOBAL(load_up_altivec)
 #ifdef CONFIG_PPC32
 	mfspr	r5,SPRN_SPRG_THREAD		/* current task's THREAD (phys) */
 	oris	r9,r9,MSR_VEC@h
+#ifdef CONFIG_VMAP_STACK
+	tovirt(r5, r5)
+#endif
 #else
 	ld	r4,PACACURRENT(r13)
 	addi	r5,r4,THREAD		/* Get THREAD */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8834220036a5..b4c89a1acebb 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -323,7 +323,7 @@ SECTIONS
 #endif
 
 	/* The initial task and kernel stack */
-	INIT_TASK_DATA_SECTION(THREAD_SIZE)
+	INIT_TASK_DATA_SECTION(THREAD_ALIGN)
 
 	.data..page_aligned : AT(ADDR(.data..page_aligned) - LOAD_OFFSET) {
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 58a59ee998e2..d07a8e12fa15 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -471,11 +471,6 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvmppc_load_last_inst);
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -789,9 +784,9 @@ void kvmppc_decrementer_func(struct kvm_vcpu *vcpu)
 	kvm_vcpu_kick(vcpu);
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu)
 {
-	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
+	return vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index d381526c5c9b..6c372f5c61b6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -284,7 +284,7 @@ static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Protect linux PTE lookup from page table destruction */
 	rcu_read_lock_sched();	/* this disables preemption too */
 	ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel,
-				current->mm->pgd, false, pte_idx_ret);
+				kvm->mm->pgd, false, pte_idx_ret);
 	rcu_read_unlock_sched();
 	if (ret == H_TOO_HARD) {
 		/* this can't happen */
@@ -573,7 +573,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	is_ci = false;
 	pfn = 0;
 	page = NULL;
-	mm = current->mm;
+	mm = kvm->mm;
 	pte_size = PAGE_SIZE;
 	writing = (dsisr & DSISR_ISSTORE) != 0;
 	/* If writing != 0, then the HPTE must allow writing, if we get here */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index da857c8ba6e4..803940d79b73 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -63,12 +63,10 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
 	}
 	isync();
 
-	pagefault_disable();
 	if (is_load)
-		ret = raw_copy_from_user(to, from, n);
+		ret = probe_user_read(to, (const void __user *)from, n);
 	else
-		ret = raw_copy_to_user(to, from, n);
-	pagefault_enable();
+		ret = probe_user_write((void __user *)to, from, n);
 
 	/* switch the pid first to avoid running host with unallocated pid */
 	if (quadrant == 1 && pid != old_pid)
@@ -1102,7 +1100,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	unsigned int shift;
 
 	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)
-		kvmppc_uvmem_drop_pages(memslot, kvm);
+		kvmppc_uvmem_drop_pages(memslot, kvm, true);
 
 	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
 		return;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 883a66e76638..ee6c103bb7d5 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -253,10 +253,11 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 		}
 	}
 
+	account_locked_vm(kvm->mm,
+		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
+
 	kvm_put_kvm(stt->kvm);
 
-	account_locked_vm(current->mm,
-		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
 	call_rcu(&stt->rcu, release_spapr_tce_table);
 
 	return 0;
@@ -272,6 +273,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
 	struct kvmppc_spapr_tce_table *siter;
+	struct mm_struct *mm = kvm->mm;
 	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
 
@@ -280,7 +282,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		return -EINVAL;
 
 	npages = kvmppc_tce_pages(size);
-	ret = account_locked_vm(current->mm, kvmppc_stt_pages(npages), true);
+	ret = account_locked_vm(mm, kvmppc_stt_pages(npages), true);
 	if (ret)
 		return ret;
 
@@ -326,7 +328,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 
 	kfree(stt);
  fail_acct:
-	account_locked_vm(current->mm, kvmppc_stt_pages(npages), false);
+	account_locked_vm(mm, kvmppc_stt_pages(npages), false);
 	return ret;
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6ff3f896d908..2cefd071b848 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1091,6 +1091,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	case H_SVM_INIT_DONE:
 		ret = kvmppc_h_svm_init_done(vcpu->kvm);
 		break;
+	case H_SVM_INIT_ABORT:
+		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
+		break;
 
 	default:
 		return RESUME_HOST;
@@ -2271,22 +2274,16 @@ static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
 }
 #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
-						   unsigned int id)
+static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu;
 	int err;
 	int core;
 	struct kvmppc_vcore *vcore;
+	struct kvm *kvm;
+	unsigned int id;
 
-	err = -ENOMEM;
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu)
-		goto out;
-
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
+	kvm = vcpu->kvm;
+	id = vcpu->vcpu_id;
 
 	vcpu->arch.shared = &vcpu->arch.shregs;
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -2368,7 +2365,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	mutex_unlock(&kvm->lock);
 
 	if (!vcore)
-		goto free_vcpu;
+		return err;
 
 	spin_lock(&vcore->lock);
 	++vcore->num_threads;
@@ -2383,12 +2380,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 
 	debugfs_vcpu_init(vcpu, id);
 
-	return vcpu;
-
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
-out:
-	return ERR_PTR(err);
+	return 0;
 }
 
 static int kvmhv_set_smt_mode(struct kvm *kvm, unsigned long smt_mode,
@@ -2442,8 +2434,6 @@ static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
 	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
 	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
 	spin_unlock(&vcpu->arch.vpa_update_lock);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
@@ -4285,7 +4275,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	user_vrsave = mfspr(SPRN_VRSAVE);
 
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
-	vcpu->arch.pgdir = current->mm->pgd;
+	vcpu->arch.pgdir = kvm->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
@@ -4640,14 +4630,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 
 	/* Look up the VMA for the start of this memory slot */
 	hva = memslot->userspace_addr;
-	down_read(&current->mm->mmap_sem);
-	vma = find_vma(current->mm, hva);
+	down_read(&kvm->mm->mmap_sem);
+	vma = find_vma(kvm->mm, hva);
 	if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
 		goto up_out;
 
 	psize = vma_kernel_pagesize(vma);
 
-	up_read(&current->mm->mmap_sem);
+	up_read(&kvm->mm->mmap_sem);
 
 	/* We can handle 4k, 64k or 16M pages in the VRMA */
 	if (psize >= 0x1000000)
@@ -4680,7 +4670,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	return err;
 
  up_out:
-	up_read(&current->mm->mmap_sem);
+	up_read(&kvm->mm->mmap_sem);
 	goto out_srcu;
 }
 
@@ -5477,7 +5467,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 			continue;
 
 		kvm_for_each_memslot(memslot, slots) {
-			kvmppc_uvmem_drop_pages(memslot, kvm);
+			kvmppc_uvmem_drop_pages(memslot, kvm, true);
 			uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
 		}
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index c6fbbd29bd87..dbc2fecc37f0 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1801,6 +1801,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	tlbsync
 	ptesync
 
+BEGIN_FTR_SECTION
 	/* Radix: Handle the case where the guest used an illegal PID */
 	LOAD_REG_ADDR(r4, mmu_base_pid)
 	lwz	r3, VCPU_GUEST_PID(r9)
@@ -1830,6 +1831,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	addi	r7,r7,0x1000
 	bdnz	1b
 	ptesync
+END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG)
 
 2:
 #endif /* CONFIG_PPC_RADIX_MMU */
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 2de264fc3156..79b1202b1c62 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -258,7 +258,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
  * QEMU page table with normal PTEs from newly allocated pages.
  */
 void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
-			     struct kvm *kvm)
+			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
@@ -276,7 +276,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = true;
+		pvt->skip_page_out = skip_page_out;
 		mutex_unlock(&kvm->arch.uvmem_lock);
 
 		pfn = gfn_to_pfn(kvm, gfn);
@@ -286,6 +286,34 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 	}
 }
 
+unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
+{
+	int srcu_idx;
+	struct kvm_memory_slot *memslot;
+
+	/*
+	 * Expect to be called only after INIT_START and before INIT_DONE.
+	 * If INIT_DONE was completed, use normal VM termination sequence.
+	 */
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return H_STATE;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	kvm_for_each_memslot(memslot, kvm_memslots(kvm))
+		kvmppc_uvmem_drop_pages(memslot, kvm, false);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	kvm->arch.secure_guest = 0;
+	uv_svm_terminate(kvm->arch.lpid);
+
+	return H_PARAMETER;
+}
+
 /*
  * Get a free device PFN from the pool
  *
@@ -543,7 +571,7 @@ kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start,
 
 	ret = migrate_vma_setup(&mig);
 	if (ret)
-		return ret;
+		goto out;
 
 	spage = migrate_pfn_to_page(*mig.src);
 	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index ce4fcf76e53e..729a0f12a752 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1744,21 +1744,17 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
-						   unsigned int id)
+static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s;
-	struct kvm_vcpu *vcpu;
-	int err = -ENOMEM;
 	unsigned long p;
+	int err;
 
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu)
-		goto out;
+	err = -ENOMEM;
 
 	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
 	if (!vcpu_book3s)
-		goto free_vcpu;
+		goto out;
 	vcpu->arch.book3s = vcpu_book3s;
 
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
@@ -1768,14 +1764,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 		goto free_vcpu3s;
 #endif
 
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_shadow_vcpu;
-
-	err = -ENOMEM;
 	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (!p)
-		goto uninit_vcpu;
+		goto free_shadow_vcpu;
 	vcpu->arch.shared = (void *)p;
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Always start the shared struct in native endian mode */
@@ -1806,22 +1797,20 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 
 	err = kvmppc_mmu_init(vcpu);
 	if (err < 0)
-		goto uninit_vcpu;
+		goto free_shared_page;
 
-	return vcpu;
+	return 0;
 
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
+free_shared_page:
+	free_page((unsigned long)vcpu->arch.shared);
 free_shadow_vcpu:
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 free_vcpu3s:
 #endif
 	vfree(vcpu_book3s);
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
@@ -1829,12 +1818,10 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
-	kvm_vcpu_uninit(vcpu);
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 #endif
 	vfree(vcpu_book3s);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
@@ -2030,6 +2017,7 @@ static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
 {
 	/* We should not get called */
 	BUG();
+	return 0;
 }
 #endif /* CONFIG_PPC64 */
 
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 66858b7d3c6b..85215e79db42 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -484,7 +484,7 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
 	kvmppc_xive_select_irq(state, &hw_num, &xd);
 
 	/*
-	 * See command in xive_lock_and_mask() concerning masking
+	 * See comment in xive_lock_and_mask() concerning masking
 	 * via firmware.
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index d83adb1e1490..6ef0151ff70a 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -631,7 +631,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 	if (1ull << kvm_eq.qshift > page_size) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
 		pr_warn("Incompatible host page size %lx!\n", page_size);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index be9a45874194..7b27604adadf 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -775,7 +775,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	debug = current->thread.debug;
 	current->thread.debug = vcpu->arch.dbg_reg;
 
-	vcpu->arch.pgdir = current->mm->pgd;
+	vcpu->arch.pgdir = vcpu->kvm->mm->pgd;
 	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
@@ -1377,36 +1377,6 @@ static void kvmppc_set_tsr(struct kvm_vcpu *vcpu, u32 new_tsr)
 	update_timer_ints(vcpu);
 }
 
-/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
-	int i;
-	int r;
-
-	vcpu->arch.regs.nip = 0;
-	vcpu->arch.shared->pir = vcpu->vcpu_id;
-	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
-	kvmppc_set_msr(vcpu, 0);
-
-#ifndef CONFIG_KVM_BOOKE_HV
-	vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS;
-	vcpu->arch.shadow_pid = 1;
-	vcpu->arch.shared->msr = 0;
-#endif
-
-	/* Eye-catching numbers so we know if the guest takes an interrupt
-	 * before it's programmed its own IVPR/IVORs. */
-	vcpu->arch.ivpr = 0x55550000;
-	for (i = 0; i < BOOKE_IRQPRIO_MAX; i++)
-		vcpu->arch.ivor[i] = 0x7700 | i * 4;
-
-	kvmppc_init_timing_stats(vcpu);
-
-	r = kvmppc_core_vcpu_setup(vcpu);
-	kvmppc_sanity_check(vcpu);
-	return r;
-}
-
 int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	/* setup watchdog timer once */
@@ -2114,9 +2084,40 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return kvm->arch.kvm_ops->init_vm(kvm);
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu)
 {
-	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
+	int i;
+	int r;
+
+	r = vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu);
+	if (r)
+		return r;
+
+	/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
+	vcpu->arch.regs.nip = 0;
+	vcpu->arch.shared->pir = vcpu->vcpu_id;
+	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
+	kvmppc_set_msr(vcpu, 0);
+
+#ifndef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS;
+	vcpu->arch.shadow_pid = 1;
+	vcpu->arch.shared->msr = 0;
+#endif
+
+	/* Eye-catching numbers so we know if the guest takes an interrupt
+	 * before it's programmed its own IVPR/IVORs. */
+	vcpu->arch.ivpr = 0x55550000;
+	for (i = 0; i < BOOKE_IRQPRIO_MAX; i++)
+		vcpu->arch.ivor[i] = 0x7700 | i * 4;
+
+	kvmppc_init_timing_stats(vcpu);
+
+	r = kvmppc_core_vcpu_setup(vcpu);
+	if (r)
+		vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
+	kvmppc_sanity_check(vcpu);
+	return r;
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 00649ca5fa9a..f2b4feaff6d2 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -433,31 +433,16 @@ static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
-						     unsigned int id)
+static int kvmppc_core_vcpu_create_e500(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
-	struct kvm_vcpu *vcpu;
 	int err;
 
-	BUILD_BUG_ON_MSG(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0,
-		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+	BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0);
+	vcpu_e500 = to_e500(vcpu);
 
-	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu_e500) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	vcpu = &vcpu_e500->vcpu;
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
-
-	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) {
-		err = -ENOMEM;
-		goto uninit_vcpu;
-	}
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+		return -ENOMEM;
 
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
@@ -469,18 +454,13 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
 		goto uninit_tlb;
 	}
 
-	return vcpu;
+	return 0;
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
 uninit_id:
 	kvmppc_e500_id_table_free(vcpu_e500);
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
-out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
@@ -490,8 +470,6 @@ static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)vcpu->arch.shared);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
 	kvmppc_e500_id_table_free(vcpu_e500);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
 static int kvmppc_core_init_vm_e500(struct kvm *kvm)
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 318e65c65999..e6b06cb2b92c 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -301,30 +301,20 @@ static int kvmppc_set_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
-						       unsigned int id)
+static int kvmppc_core_vcpu_create_e500mc(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
-	struct kvm_vcpu *vcpu;
 	int err;
 
-	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu_e500) {
-		err = -ENOMEM;
-		goto out;
-	}
-	vcpu = &vcpu_e500->vcpu;
+	BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0);
+	vcpu_e500 = to_e500(vcpu);
 
 	/* Invalid PIR value -- this LPID dosn't have valid state on any cpu */
 	vcpu->arch.oldpir = 0xffffffff;
 
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
-
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
-		goto uninit_vcpu;
+		return err;
 
 	vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	if (!vcpu->arch.shared) {
@@ -332,17 +322,11 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
 		goto uninit_tlb;
 	}
 
-	return vcpu;
+	return 0;
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
-
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
-out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu)
@@ -351,8 +335,6 @@ static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu)
 
 	free_page((unsigned long)vcpu->arch.shared);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
 static int kvmppc_core_init_vm_e500mc(struct kvm *kvm)
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 2e496eb86e94..1139bc56e004 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -73,7 +73,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	u32 inst;
-	int ra, rs, rt;
 	enum emulation_result emulated = EMULATE_FAIL;
 	int advance = 1;
 	struct instruction_op op;
@@ -85,10 +84,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	if (emulated != EMULATE_DONE)
 		return emulated;
 
-	ra = get_ra(inst);
-	rs = get_rs(inst);
-	rt = get_rt(inst);
-
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 416fb3d2a1d0..1af96fb5dc6f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -475,7 +475,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 #endif
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arch_vcpu_free(vcpu);
+		kvm_vcpu_destroy(vcpu);
 
 	mutex_lock(&kvm->lock);
 	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
@@ -720,22 +720,55 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	kvmppc_core_flush_memslot(kvm, slot);
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
+{
+	return 0;
+}
+
+static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
-	vcpu = kvmppc_core_vcpu_create(kvm, id);
-	if (!IS_ERR(vcpu)) {
-		vcpu->arch.wqp = &vcpu->wq;
-		kvmppc_create_vcpu_debugfs(vcpu, id);
-	}
-	return vcpu;
+
+	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
+	kvmppc_decrementer_func(vcpu);
+
+	return HRTIMER_NORESTART;
+}
+
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	int err;
+
+	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
+	vcpu->arch.dec_expires = get_tb();
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	mutex_init(&vcpu->arch.exit_timing_lock);
+#endif
+	err = kvmppc_subarch_vcpu_init(vcpu);
+	if (err)
+		return err;
+
+	err = kvmppc_core_vcpu_create(vcpu);
+	if (err)
+		goto out_vcpu_uninit;
+
+	vcpu->arch.wqp = &vcpu->wq;
+	kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id);
+	return 0;
+
+out_vcpu_uninit:
+	kvmppc_mmu_destroy(vcpu);
+	kvmppc_subarch_vcpu_uninit(vcpu);
+	return err;
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	/* Make sure we're not using the vcpu anymore */
 	hrtimer_cancel(&vcpu->arch.dec_timer);
@@ -758,11 +791,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	}
 
 	kvmppc_core_vcpu_free(vcpu);
-}
 
-void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
-{
-	kvm_arch_vcpu_free(vcpu);
+	kvmppc_mmu_destroy(vcpu);
+	kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -770,37 +801,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvmppc_core_pending_dec(vcpu);
 }
 
-static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
-{
-	struct kvm_vcpu *vcpu;
-
-	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
-	kvmppc_decrementer_func(vcpu);
-
-	return HRTIMER_NORESTART;
-}
-
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	int ret;
-
-	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
-	vcpu->arch.dec_expires = get_tb();
-
-#ifdef CONFIG_KVM_EXIT_TIMING
-	mutex_init(&vcpu->arch.exit_timing_lock);
-#endif
-	ret = kvmppc_subarch_vcpu_init(vcpu);
-	return ret;
-}
-
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-	kvmppc_mmu_destroy(vcpu);
-	kvmppc_subarch_vcpu_uninit(vcpu);
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_BOOKE
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 8bbbd9775c8a..c11b0a005196 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -25,6 +25,12 @@
 #include <asm/feature-fixups.h>
 #include <asm/code-patching-asm.h>
 
+#ifdef CONFIG_VMAP_STACK
+#define ADDR_OFFSET	0
+#else
+#define ADDR_OFFSET	PAGE_OFFSET
+#endif
+
 #ifdef CONFIG_SMP
 	.section .bss
 	.align	2
@@ -47,8 +53,8 @@ mmu_hash_lock:
 	.text
 _GLOBAL(hash_page)
 #ifdef CONFIG_SMP
-	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@h
-	ori	r8, r8, (mmu_hash_lock - PAGE_OFFSET)@l
+	lis	r8, (mmu_hash_lock - ADDR_OFFSET)@h
+	ori	r8, r8, (mmu_hash_lock - ADDR_OFFSET)@l
 	lis	r0,0x0fff
 	b	10f
 11:	lwz	r6,0(r8)
@@ -66,9 +72,12 @@ _GLOBAL(hash_page)
 	cmplw	0,r4,r0
 	ori	r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
 	mfspr	r5, SPRN_SPRG_PGDIR	/* phys page-table root */
+#ifdef CONFIG_VMAP_STACK
+	tovirt(r5, r5)
+#endif
 	blt+	112f			/* assume user more likely */
-	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
-	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
+	lis	r5, (swapper_pg_dir - ADDR_OFFSET)@ha	/* if kernel address, use */
+	addi	r5 ,r5 ,(swapper_pg_dir - ADDR_OFFSET)@l	/* kernel page table */
 	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
 112:
 #ifndef CONFIG_PTE_64BIT
@@ -80,6 +89,9 @@ _GLOBAL(hash_page)
 	lwzx	r8,r8,r5		/* Get L1 entry */
 	rlwinm.	r8,r8,0,0,20		/* extract pt base address */
 #endif
+#ifdef CONFIG_VMAP_STACK
+	tovirt(r8, r8)
+#endif
 #ifdef CONFIG_SMP
 	beq-	hash_page_out		/* return if no mapping */
 #else
@@ -137,9 +149,9 @@ retry:
 
 #ifdef CONFIG_SMP
 	eieio
-	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
+	lis	r8, (mmu_hash_lock - ADDR_OFFSET)@ha
 	li	r0,0
-	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
+	stw	r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8)
 #endif
 
 	/* Return from the exception */
@@ -152,9 +164,9 @@ retry:
 #ifdef CONFIG_SMP
 hash_page_out:
 	eieio
-	lis	r8, (mmu_hash_lock - PAGE_OFFSET)@ha
+	lis	r8, (mmu_hash_lock - ADDR_OFFSET)@ha
 	li	r0,0
-	stw	r0, (mmu_hash_lock - PAGE_OFFSET)@l(r8)
+	stw	r0, (mmu_hash_lock - ADDR_OFFSET)@l(r8)
 	blr
 #endif /* CONFIG_SMP */
 
@@ -329,7 +341,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	patch_site	1f, patch__hash_page_A1
 	patch_site	2f, patch__hash_page_A2
 	/* Get the address of the primary PTE group in the hash table (r3) */
-0:	lis	r0, (Hash_base - PAGE_OFFSET)@h	/* base address of hash table */
+0:	lis	r0, (Hash_base - ADDR_OFFSET)@h	/* base address of hash table */
 1:	rlwimi	r0,r3,LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT    /* VSID -> hash */
 2:	rlwinm	r3,r4,20+LG_PTEG_SIZE,HASH_LEFT,HASH_RIGHT /* PI -> hash */
 	xor	r3,r3,r0		/* make primary hash */
@@ -343,10 +355,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	beq+	10f			/* no PTE: go look for an empty slot */
 	tlbie	r4
 
-	lis	r4, (htab_hash_searches - PAGE_OFFSET)@ha
-	lwz	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
+	lis	r4, (htab_hash_searches - ADDR_OFFSET)@ha
+	lwz	r6, (htab_hash_searches - ADDR_OFFSET)@l(r4)
 	addi	r6,r6,1			/* count how many searches we do */
-	stw	r6, (htab_hash_searches - PAGE_OFFSET)@l(r4)
+	stw	r6, (htab_hash_searches - ADDR_OFFSET)@l(r4)
 
 	/* Search the primary PTEG for a PTE whose 1st (d)word matches r5 */
 	mtctr	r0
@@ -378,10 +390,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	beq+	found_empty
 
 	/* update counter of times that the primary PTEG is full */
-	lis	r4, (primary_pteg_full - PAGE_OFFSET)@ha
-	lwz	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
+	lis	r4, (primary_pteg_full - ADDR_OFFSET)@ha
+	lwz	r6, (primary_pteg_full - ADDR_OFFSET)@l(r4)
 	addi	r6,r6,1
-	stw	r6, (primary_pteg_full - PAGE_OFFSET)@l(r4)
+	stw	r6, (primary_pteg_full - ADDR_OFFSET)@l(r4)
 
 	patch_site	0f, patch__hash_page_C
 	/* Search the secondary PTEG for an empty slot */
@@ -415,8 +427,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT)
 	 * lockup here but that shouldn't happen
 	 */
 
-1:	lis	r4, (next_slot - PAGE_OFFSET)@ha	/* get next evict slot */
-	lwz	r6, (next_slot - PAGE_OFFSET)@l(r4)
+1:	lis	r4, (next_slot - ADDR_OFFSET)@ha	/* get next evict slot */
+	lwz	r6, (next_slot - ADDR_OFFSET)@l(r4)
 	addi	r6,r6,HPTE_SIZE			/* search for candidate */
 	andi.	r6,r6,7*HPTE_SIZE
 	stw	r6,next_slot@l(r4)
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 69b2419accef..0a1c65a2c565 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -413,6 +413,7 @@ void __init MMU_init_hw(void)
 void __init MMU_init_hw_patch(void)
 {
 	unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE);
+	unsigned int hash;
 
 	if (ppc_md.progress)
 		ppc_md.progress("hash:patch", 0x345);
@@ -424,8 +425,12 @@ void __init MMU_init_hw_patch(void)
 	/*
 	 * Patch up the instructions in hashtable.S:create_hpte
 	 */
-	modify_instruction_site(&patch__hash_page_A0, 0xffff,
-				((unsigned int)Hash - PAGE_OFFSET) >> 16);
+	if (IS_ENABLED(CONFIG_VMAP_STACK))
+		hash = (unsigned int)Hash;
+	else
+		hash = (unsigned int)Hash - PAGE_OFFSET;
+
+	modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16);
 	modify_instruction_site(&patch__hash_page_A1, 0x7c0, hash_mb << 6);
 	modify_instruction_site(&patch__hash_page_A2, 0x7c0, hash_mb2 << 6);
 	modify_instruction_site(&patch__hash_page_B, 0xffff, hmask);
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index b30435c7d804..523d4d39d11e 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -652,6 +652,7 @@ static void init_hpte_page_sizes(void)
 
 static void __init htab_init_page_sizes(void)
 {
+	bool aligned = true;
 	init_hpte_page_sizes();
 
 	if (!debug_pagealloc_enabled()) {
@@ -659,7 +660,15 @@ static void __init htab_init_page_sizes(void)
 		 * Pick a size for the linear mapping. Currently, we only
 		 * support 16M, 1M and 4K which is the default
 		 */
-		if (mmu_psize_defs[MMU_PAGE_16M].shift)
+		if (IS_ENABLED(STRICT_KERNEL_RWX) &&
+		    (unsigned long)_stext % 0x1000000) {
+			if (mmu_psize_defs[MMU_PAGE_16M].shift)
+				pr_warn("Kernel not 16M aligned, "
+					"disabling 16M linear map alignment");
+			aligned = false;
+		}
+
+		if (mmu_psize_defs[MMU_PAGE_16M].shift && aligned)
 			mmu_linear_psize = MMU_PAGE_16M;
 		else if (mmu_psize_defs[MMU_PAGE_1M].shift)
 			mmu_linear_psize = MMU_PAGE_1M;
diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c
index 56cc84520577..eba73ebd8ae5 100644
--- a/arch/powerpc/mm/book3s64/iommu_api.c
+++ b/arch/powerpc/mm/book3s64/iommu_api.c
@@ -103,7 +103,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	for (entry = 0; entry < entries; entry += chunk) {
 		unsigned long n = min(entries - entry, chunk);
 
-		ret = get_user_pages(ua + (entry << PAGE_SHIFT), n,
+		ret = pin_user_pages(ua + (entry << PAGE_SHIFT), n,
 				FOLL_WRITE | FOLL_LONGTERM,
 				mem->hpages + entry, NULL);
 		if (ret == n) {
@@ -167,9 +167,8 @@ good_exit:
 	return 0;
 
 free_exit:
-	/* free the reference taken */
-	for (i = 0; i < pinned; i++)
-		put_page(mem->hpages[i]);
+	/* free the references taken */
+	unpin_user_pages(mem->hpages, pinned);
 
 	vfree(mem->hpas);
 	kfree(mem);
@@ -215,7 +214,8 @@ static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
 		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
 			SetPageDirty(page);
 
-		put_page(page);
+		unpin_user_page(page);
+
 		mem->hpas[i] = 0;
 	}
 }
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 75483b40fcb1..2bf7e1b4fd82 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -378,7 +378,6 @@ static inline void pgtable_free(void *table, int index)
 	}
 }
 
-#ifdef CONFIG_SMP
 void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
 {
 	unsigned long pgf = (unsigned long)table;
@@ -395,12 +394,6 @@ void __tlb_remove_table(void *_table)
 
 	return pgtable_free(table, index);
 }
-#else
-void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
-{
-	return pgtable_free(table, index);
-}
-#endif
 
 #ifdef CONFIG_PROC_FS
 atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 974109bb85db..dd1bea45325c 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -337,7 +337,11 @@ static void __init radix_init_pgtable(void)
 	}
 
 	/* Find out how many PID bits are supported */
-	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+	if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
+		if (!mmu_pid_bits)
+			mmu_pid_bits = 20;
+		mmu_base_pid = 1;
+	} else if (cpu_has_feature(CPU_FTR_HVMODE)) {
 		if (!mmu_pid_bits)
 			mmu_pid_bits = 20;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index a95175c0972b..03f43c924e00 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -1161,6 +1161,9 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 	if (unlikely(pid == MMU_NO_CONTEXT))
 		return;
 
+	if (!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG))
+		return;
+
 	/*
 	 * If this context hasn't run on that CPU before and KVM is
 	 * around, there's a slim chance that the guest on another
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index b5047f9b5dec..8db0507619e2 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -233,7 +233,7 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code,
 
 	// Read/write fault in a valid region (the exception table search passed
 	// above), but blocked by KUAP is bad, it can never succeed.
-	if (bad_kuap_fault(regs, is_write))
+	if (bad_kuap_fault(regs, address, is_write))
 		return true;
 
 	// What's left? Kernel fault on user in well defined regions (extable
@@ -279,12 +279,8 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address,
 		if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) &&
 		    access_ok(nip, sizeof(*nip))) {
 			unsigned int inst;
-			int res;
 
-			pagefault_disable();
-			res = __get_user_inatomic(inst, nip);
-			pagefault_enable();
-			if (!res)
+			if (!probe_user_read(&inst, nip, sizeof(inst)))
 				return !store_updates_sp(inst);
 			*must_retry = true;
 		}
@@ -354,6 +350,9 @@ static void sanity_check_fault(bool is_write, bool is_user,
 	 * Userspace trying to access kernel address, we get PROTFAULT for that.
 	 */
 	if (is_user && address >= TASK_SIZE) {
+		if ((long)address == -1)
+			return;
+
 		pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
 				   current->comm, current->pid, address,
 				   from_kuid(&init_user_ns, current_uid()));
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 0e6ed4413eea..16dd95bd0749 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -12,7 +12,7 @@
 #include <asm/code-patching.h>
 #include <mm/mmu_decl.h>
 
-static pgprot_t kasan_prot_ro(void)
+static pgprot_t __init kasan_prot_ro(void)
 {
 	if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE))
 		return PAGE_READONLY;
@@ -20,7 +20,7 @@ static pgprot_t kasan_prot_ro(void)
 	return PAGE_KERNEL_RO;
 }
 
-static void kasan_populate_pte(pte_t *ptep, pgprot_t prot)
+static void __init kasan_populate_pte(pte_t *ptep, pgprot_t prot)
 {
 	unsigned long va = (unsigned long)kasan_early_shadow_page;
 	phys_addr_t pa = __pa(kasan_early_shadow_page);
@@ -30,29 +30,25 @@ static void kasan_populate_pte(pte_t *ptep, pgprot_t prot)
 		__set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
 }
 
-static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
+static int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
 {
 	pmd_t *pmd;
 	unsigned long k_cur, k_next;
-	pgprot_t prot = slab_is_available() ? kasan_prot_ro() : PAGE_KERNEL;
+	pte_t *new = NULL;
 
 	pmd = pmd_offset(pud_offset(pgd_offset_k(k_start), k_start), k_start);
 
 	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++) {
-		pte_t *new;
-
 		k_next = pgd_addr_end(k_cur, k_end);
 		if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
 			continue;
 
-		if (slab_is_available())
-			new = pte_alloc_one_kernel(&init_mm);
-		else
+		if (!new)
 			new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
 
 		if (!new)
 			return -ENOMEM;
-		kasan_populate_pte(new, prot);
+		kasan_populate_pte(new, PAGE_KERNEL);
 
 		smp_wmb(); /* See comment in __pte_alloc */
 
@@ -63,39 +59,27 @@ static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned l
 			new = NULL;
 		}
 		spin_unlock(&init_mm.page_table_lock);
-
-		if (new && slab_is_available())
-			pte_free_kernel(&init_mm, new);
 	}
 	return 0;
 }
 
-static void __ref *kasan_get_one_page(void)
-{
-	if (slab_is_available())
-		return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-
-	return memblock_alloc(PAGE_SIZE, PAGE_SIZE);
-}
-
-static int __ref kasan_init_region(void *start, size_t size)
+static int __init kasan_init_region(void *start, size_t size)
 {
 	unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start);
 	unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size);
 	unsigned long k_cur;
 	int ret;
-	void *block = NULL;
+	void *block;
 
 	ret = kasan_init_shadow_page_tables(k_start, k_end);
 	if (ret)
 		return ret;
 
-	if (!slab_is_available())
-		block = memblock_alloc(k_end - k_start, PAGE_SIZE);
+	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 
 	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
 		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
-		void *va = block ? block + k_cur - k_start : kasan_get_one_page();
+		void *va = block + k_cur - k_start;
 		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
 
 		if (!va)
@@ -129,6 +113,31 @@ static void __init kasan_remap_early_shadow_ro(void)
 	flush_tlb_kernel_range(KASAN_SHADOW_START, KASAN_SHADOW_END);
 }
 
+static void __init kasan_unmap_early_shadow_vmalloc(void)
+{
+	unsigned long k_start = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_START);
+	unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END);
+	unsigned long k_cur;
+	phys_addr_t pa = __pa(kasan_early_shadow_page);
+
+	if (!early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
+		int ret = kasan_init_shadow_page_tables(k_start, k_end);
+
+		if (ret)
+			panic("kasan: kasan_init_shadow_page_tables() failed");
+	}
+	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
+		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
+
+		if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
+			continue;
+
+		__set_pte_at(&init_mm, k_cur, ptep, __pte(0), 0);
+	}
+	flush_tlb_kernel_range(k_start, k_end);
+}
+
 void __init kasan_mmu_init(void)
 {
 	int ret;
@@ -165,34 +174,22 @@ void __init kasan_init(void)
 	pr_info("KASAN init done\n");
 }
 
-#ifdef CONFIG_MODULES
-void *module_alloc(unsigned long size)
+void __init kasan_late_init(void)
 {
-	void *base;
-
-	base = __vmalloc_node_range(size, MODULE_ALIGN, VMALLOC_START, VMALLOC_END,
-				    GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
-				    NUMA_NO_NODE, __builtin_return_address(0));
-
-	if (!base)
-		return NULL;
-
-	if (!kasan_init_region(base, size))
-		return base;
-
-	vfree(base);
-
-	return NULL;
+	if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
+		kasan_unmap_early_shadow_vmalloc();
 }
-#endif
 
 #ifdef CONFIG_PPC_BOOK3S_32
 u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0};
 
 static void __init kasan_early_hash_table(void)
 {
-	modify_instruction_site(&patch__hash_page_A0, 0xffff, __pa(early_hash) >> 16);
-	modify_instruction_site(&patch__flush_hash_A0, 0xffff, __pa(early_hash) >> 16);
+	unsigned int hash = IS_ENABLED(CONFIG_VMAP_STACK) ? (unsigned int)early_hash :
+							    __pa(early_hash);
+
+	modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16);
+	modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16);
 
 	Hash = (struct hash_pte *)early_hash;
 }
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index f5535eae637f..ef7b1119b2e2 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -49,6 +49,7 @@
 #include <asm/fixmap.h>
 #include <asm/swiotlb.h>
 #include <asm/rtas.h>
+#include <asm/kasan.h>
 
 #include <mm/mmu_decl.h>
 
@@ -301,6 +302,9 @@ void __init mem_init(void)
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 	set_max_mapnr(max_pfn);
+
+	kasan_late_init();
+
 	memblock_free_all();
 
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 8e99649c24fc..7097e07a209a 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -181,3 +181,9 @@ void mmu_mark_rodata_ro(void);
 static inline void mmu_mark_initmem_nx(void) { }
 static inline void mmu_mark_rodata_ro(void) { }
 #endif
+
+#ifdef CONFIG_PPC_DEBUG_WX
+void ptdump_check_wx(void);
+#else
+static inline void ptdump_check_wx(void) { }
+#endif
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 96eb8e43f39b..3189308dece4 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -21,33 +21,34 @@ extern int __map_without_ltlbs;
 static unsigned long block_mapped_ram;
 
 /*
- * Return PA for this VA if it is in an area mapped with LTLBs.
+ * Return PA for this VA if it is in an area mapped with LTLBs or fixmap.
  * Otherwise, returns 0
  */
 phys_addr_t v_block_mapped(unsigned long va)
 {
 	unsigned long p = PHYS_IMMR_BASE;
 
-	if (__map_without_ltlbs)
-		return 0;
 	if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE)
 		return p + va - VIRT_IMMR_BASE;
+	if (__map_without_ltlbs)
+		return 0;
 	if (va >= PAGE_OFFSET && va < PAGE_OFFSET + block_mapped_ram)
 		return __pa(va);
 	return 0;
 }
 
 /*
- * Return VA for a given PA mapped with LTLBs or 0 if not mapped
+ * Return VA for a given PA mapped with LTLBs or fixmap
+ * Return 0 if not mapped
  */
 unsigned long p_block_mapped(phys_addr_t pa)
 {
 	unsigned long p = PHYS_IMMR_BASE;
 
-	if (__map_without_ltlbs)
-		return 0;
 	if (pa >= p && pa < p + IMMR_SIZE)
 		return VIRT_IMMR_BASE + pa - p;
+	if (__map_without_ltlbs)
+		return 0;
 	if (pa < block_mapped_ram)
 		return (unsigned long)__va(pa);
 	return 0;
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 50d68d21ddcc..3c7dec70cda0 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1616,11 +1616,11 @@ static ssize_t topology_write(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations topology_ops = {
-	.read = seq_read,
-	.write = topology_write,
-	.open = topology_open,
-	.release = single_release
+static const struct proc_ops topology_proc_ops = {
+	.proc_read	= seq_read,
+	.proc_write	= topology_write,
+	.proc_open	= topology_open,
+	.proc_release	= single_release,
 };
 
 static int topology_update_init(void)
@@ -1630,7 +1630,7 @@ static int topology_update_init(void)
 	if (vphn_enabled)
 		topology_schedule_update();
 
-	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
+	if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_proc_ops))
 		return -ENOMEM;
 
 	topology_inited = 1;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 73b84166d06a..5fb90edd865e 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -218,6 +218,7 @@ void mark_rodata_ro(void)
 
 	if (v_block_mapped((unsigned long)_sinittext)) {
 		mmu_mark_rodata_ro();
+		ptdump_check_wx();
 		return;
 	}
 
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 2f9ddc29c535..206156255247 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -24,6 +24,8 @@
 #include <asm/page.h>
 #include <asm/pgalloc.h>
 
+#include <mm/mmu_decl.h>
+
 #include "ptdump.h"
 
 /*
@@ -173,10 +175,12 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
 
 static void note_prot_wx(struct pg_state *st, unsigned long addr)
 {
+	pte_t pte = __pte(st->current_flags);
+
 	if (!IS_ENABLED(CONFIG_PPC_DEBUG_WX) || !st->check_wx)
 		return;
 
-	if (!((st->current_flags & pgprot_val(PAGE_KERNEL_X)) == pgprot_val(PAGE_KERNEL_X)))
+	if (!pte_write(pte) || !pte_exec(pte))
 		return;
 
 	WARN_ONCE(1, "powerpc/mm: Found insecure W+X mapping at address %p/%pS\n",
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index 43245f4a9bcb..6f347fa29f41 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -9,7 +9,7 @@
 #include <linux/sched.h>
 #include <asm/processor.h>
 #include <linux/uaccess.h>
-#include <asm/compat.h>
+#include <linux/compat.h>
 #include <asm/oprofile_impl.h>
 
 #define STACK_SP(STACK)		*(STACK)
@@ -28,15 +28,12 @@ static unsigned int user_getsp32(unsigned int sp, int is_first)
 	unsigned int stack_frame[2];
 	void __user *p = compat_ptr(sp);
 
-	if (!access_ok(p, sizeof(stack_frame)))
-		return 0;
-
 	/*
 	 * The most likely reason for this is that we returned -EFAULT,
 	 * which means that we've done all that we can do from
 	 * interrupt context.
 	 */
-	if (__copy_from_user_inatomic(stack_frame, p, sizeof(stack_frame)))
+	if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame)))
 		return 0;
 
 	if (!is_first)
@@ -54,11 +51,7 @@ static unsigned long user_getsp64(unsigned long sp, int is_first)
 {
 	unsigned long stack_frame[3];
 
-	if (!access_ok((void __user *)sp, sizeof(stack_frame)))
-		return 0;
-
-	if (__copy_from_user_inatomic(stack_frame, (void __user *)sp,
-					sizeof(stack_frame)))
+	if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame)))
 		return 0;
 
 	if (!is_first)
@@ -103,7 +96,6 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 			first_frame = 0;
 		}
 	} else {
-		pagefault_disable();
 #ifdef CONFIG_PPC64
 		if (!is_32bit_task()) {
 			while (depth--) {
@@ -112,7 +104,6 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 					break;
 				first_frame = 0;
 			}
-			pagefault_enable();
 			return;
 		}
 #endif
@@ -123,6 +114,5 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 				break;
 			first_frame = 0;
 		}
-		pagefault_enable();
 	}
 }
diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c
index 19124b0b171a..1ad03c55c88c 100644
--- a/arch/powerpc/perf/8xx-pmu.c
+++ b/arch/powerpc/perf/8xx-pmu.c
@@ -157,10 +157,6 @@ static void mpc8xx_pmu_read(struct perf_event *event)
 
 static void mpc8xx_pmu_del(struct perf_event *event, int flags)
 {
-	/* mfspr r10, SPRN_SPRG_SCRATCH0 */
-	unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
-			    __PPC_SPR(SPRN_SPRG_SCRATCH0);
-
 	mpc8xx_pmu_read(event);
 
 	/* If it was the last user, stop counting to avoid useles overhead */
@@ -173,6 +169,10 @@ static void mpc8xx_pmu_del(struct perf_event *event, int flags)
 		break;
 	case PERF_8xx_ID_ITLB_LOAD_MISS:
 		if (atomic_dec_return(&itlb_miss_ref) == 0) {
+			/* mfspr r10, SPRN_SPRG_SCRATCH0 */
+			unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
+					    __PPC_SPR(SPRN_SPRG_SCRATCH0);
+
 			patch_instruction_site(&patch__itlbmiss_exit_1, insn);
 #ifndef CONFIG_PIN_TLB_TEXT
 			patch_instruction_site(&patch__itlbmiss_exit_2, insn);
@@ -181,6 +181,10 @@ static void mpc8xx_pmu_del(struct perf_event *event, int flags)
 		break;
 	case PERF_8xx_ID_DTLB_LOAD_MISS:
 		if (atomic_dec_return(&dtlb_miss_ref) == 0) {
+			/* mfspr r10, SPRN_DAR */
+			unsigned int insn = PPC_INST_MFSPR | __PPC_RS(R10) |
+					    __PPC_SPR(SPRN_DAR);
+
 			patch_instruction_site(&patch__dtlbmiss_exit_1, insn);
 			patch_instruction_site(&patch__dtlbmiss_exit_2, insn);
 			patch_instruction_site(&patch__dtlbmiss_exit_3, insn);
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 35d542515faf..cbc251981209 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -155,12 +155,8 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
 	    ((unsigned long)ptr & 7))
 		return -EFAULT;
 
-	pagefault_disable();
-	if (!__get_user_inatomic(*ret, ptr)) {
-		pagefault_enable();
+	if (!probe_user_read(ret, ptr, sizeof(*ret)))
 		return 0;
-	}
-	pagefault_enable();
 
 	return read_user_stack_slow(ptr, ret, 8);
 }
@@ -171,12 +167,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	pagefault_disable();
-	if (!__get_user_inatomic(*ret, ptr)) {
-		pagefault_enable();
+	if (!probe_user_read(ret, ptr, sizeof(*ret)))
 		return 0;
-	}
-	pagefault_enable();
 
 	return read_user_stack_slow(ptr, ret, 4);
 }
@@ -293,17 +285,11 @@ static void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
  */
 static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret)
 {
-	int rc;
-
 	if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) ||
 	    ((unsigned long)ptr & 3))
 		return -EFAULT;
 
-	pagefault_disable();
-	rc = __get_user_inatomic(*ret, ptr);
-	pagefault_enable();
-
-	return rc;
+	return probe_user_read(ret, ptr, sizeof(*ret));
 }
 
 static inline void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 48604625ab31..3086055bf681 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -415,7 +415,6 @@ static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in)
 static __u64 power_pmu_bhrb_to(u64 addr)
 {
 	unsigned int instr;
-	int ret;
 	__u64 target;
 
 	if (is_kernel_addr(addr)) {
@@ -426,13 +425,8 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	}
 
 	/* Userspace: need copy instruction here then translate it */
-	pagefault_disable();
-	ret = __get_user_inatomic(instr, (unsigned int __user *)addr);
-	if (ret) {
-		pagefault_enable();
+	if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr)))
 		return 0;
-	}
-	pagefault_enable();
 
 	target = branch_target(&instr);
 	if ((!target) || (instr & BRANCH_ABSOLUTE))
diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
index 13631f35cd14..04bf6ecf7d55 100644
--- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
+++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c
@@ -434,9 +434,9 @@ static int mpc512x_lpbfifo_probe(struct platform_device *pdev)
 	memset(&lpbfifo, 0, sizeof(struct lpbfifo_data));
 	spin_lock_init(&lpbfifo.lock);
 
-	lpbfifo.chan = dma_request_slave_channel(&pdev->dev, "rx-tx");
-	if (lpbfifo.chan == NULL)
-		return -EPROBE_DEFER;
+	lpbfifo.chan = dma_request_chan(&pdev->dev, "rx-tx");
+	if (IS_ERR(lpbfifo.chan))
+		return PTR_ERR(lpbfifo.chan);
 
 	if (of_address_to_resource(pdev->dev.of_node, 0, &r) != 0) {
 		dev_err(&pdev->dev, "bad 'reg' in 'sclpc' device tree node\n");
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index 273145aed90a..b0d5471f620d 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -64,7 +64,7 @@ static void quirk_mpc8360e_qe_enet10(void)
 		return;
 	}
 
-	base = ioremap(res.start, res.end - res.start + 1);
+	base = ioremap(res.start, resource_size(&res));
 
 	/*
 	 * set output delay adjustments to default values according
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 8c7ea2486bc0..48f7d96ae37d 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -252,6 +252,15 @@ static int smp_85xx_start_cpu(int cpu)
 	out_be64((u64 *)(&spin_table->addr_h),
 		__pa(ppc_function_entry(generic_secondary_smp_init)));
 #else
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	/*
+	 * We need also to write addr_h to spin table for systems
+	 * in which their physical memory start address was configured
+	 * to above 4G, otherwise the secondary core can not get
+	 * correct entry to start from.
+	 */
+	out_be32(&spin_table->addr_h, __pa(__early_start) >> 32);
+#endif
 	out_be32(&spin_table->addr_l, __pa(__early_start));
 #endif
 	flush_spin_table(spin_table);
diff --git a/arch/powerpc/platforms/85xx/twr_p102x.c b/arch/powerpc/platforms/85xx/twr_p102x.c
index 6c3c0cdaee9a..b301ef9d6ce7 100644
--- a/arch/powerpc/platforms/85xx/twr_p102x.c
+++ b/arch/powerpc/platforms/85xx/twr_p102x.c
@@ -60,10 +60,6 @@ static void __init twr_p1025_pic_init(void)
  */
 static void __init twr_p1025_setup_arch(void)
 {
-#ifdef CONFIG_QUICC_ENGINE
-	struct device_node *np;
-#endif
-
 	if (ppc_md.progress)
 		ppc_md.progress("twr_p1025_setup_arch()", 0);
 
@@ -77,6 +73,7 @@ static void __init twr_p1025_setup_arch(void)
 #if IS_ENABLED(CONFIG_UCC_GETH) || IS_ENABLED(CONFIG_SERIAL_QE)
 	if (machine_is(twr_p1025)) {
 		struct ccsr_guts __iomem *guts;
+		struct device_node *np;
 
 		np = of_find_compatible_node(NULL, NULL, "fsl,p1021-guts");
 		if (np) {
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index e28df298df56..1f8025383caa 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -177,6 +177,10 @@ config PPC_970_NAP
 config PPC_P7_NAP
 	bool
 
+config PPC_BOOK3S_IDLE
+	def_bool y
+	depends on (PPC_970_NAP || PPC_P7_NAP)
+
 config PPC_INDIRECT_PIO
 	bool
 	select GENERIC_IOMAP
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 8d7f9c3dc771..6caedc88474f 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,4 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
+config PPC32
+	bool
+	default y if !PPC64
+	select KASAN_VMALLOC if KASAN && MODULES
+
 config PPC64
 	bool "64-bit kernel"
 	select ZLIB_DEFLATE
@@ -31,12 +36,14 @@ config PPC_BOOK3S_6xx
 	select PPC_HAVE_PMU_SUPPORT
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
+	select HAVE_ARCH_VMAP_STACK
 
 config PPC_BOOK3S_601
 	bool "PowerPC 601"
 	select PPC_BOOK3S_32
 	select PPC_FPU
 	select PPC_HAVE_KUAP
+	select HAVE_ARCH_VMAP_STACK
 
 config PPC_85xx
 	bool "Freescale 85xx"
@@ -49,6 +56,7 @@ config PPC_8xx
 	select PPC_HAVE_KUEP
 	select PPC_HAVE_KUAP
 	select PPC_MM_SLICES if HUGETLB_PAGE
+	select HAVE_ARCH_VMAP_STACK
 
 config 40x
 	bool "AMCC 40x"
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 47f73103ef74..6f019df37916 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -229,7 +229,7 @@ static void __init maple_init_IRQ(void)
 	root = of_find_node_by_path("/");
 	naddr = of_n_addr_cells(root);
 	opprop = of_get_property(root, "platform-open-pic", &opplen);
-	if (opprop != 0) {
+	if (opprop) {
 		openpic_addr = of_read_number(opprop, naddr);
 		has_isus = (opplen > naddr);
 		printk(KERN_DEBUG "OpenPIC addr: %lx, has ISUs: %d\n",
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index a6ee08009f0f..2b3dfd0b6cdd 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -790,48 +790,81 @@ static int opal_sysfs_init(void)
 	return 0;
 }
 
-static ssize_t symbol_map_read(struct file *fp, struct kobject *kobj,
-			       struct bin_attribute *bin_attr,
-			       char *buf, loff_t off, size_t count)
+static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
+				struct bin_attribute *bin_attr, char *buf,
+				loff_t off, size_t count)
 {
 	return memory_read_from_buffer(buf, count, &off, bin_attr->private,
 				       bin_attr->size);
 }
 
-static struct bin_attribute symbol_map_attr = {
-	.attr = {.name = "symbol_map", .mode = 0400},
-	.read = symbol_map_read
-};
-
-static void opal_export_symmap(void)
+static int opal_add_one_export(struct kobject *parent, const char *export_name,
+			       struct device_node *np, const char *prop_name)
 {
-	const __be64 *syms;
-	unsigned int size;
-	struct device_node *fw;
+	struct bin_attribute *attr = NULL;
+	const char *name = NULL;
+	u64 vals[2];
 	int rc;
 
-	fw = of_find_node_by_path("/ibm,opal/firmware");
-	if (!fw)
-		return;
-	syms = of_get_property(fw, "symbol-map", &size);
-	if (!syms || size != 2 * sizeof(__be64))
-		return;
+	rc = of_property_read_u64_array(np, prop_name, &vals[0], 2);
+	if (rc)
+		goto out;
 
-	/* Setup attributes */
-	symbol_map_attr.private = __va(be64_to_cpu(syms[0]));
-	symbol_map_attr.size = be64_to_cpu(syms[1]);
+	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	name = kstrdup(export_name, GFP_KERNEL);
+	if (!name) {
+		rc = -ENOMEM;
+		goto out;
+	}
 
-	rc = sysfs_create_bin_file(opal_kobj, &symbol_map_attr);
-	if (rc)
-		pr_warn("Error %d creating OPAL symbols file\n", rc);
+	sysfs_bin_attr_init(attr);
+	attr->attr.name = name;
+	attr->attr.mode = 0400;
+	attr->read = export_attr_read;
+	attr->private = __va(vals[0]);
+	attr->size = vals[1];
+
+	rc = sysfs_create_bin_file(parent, attr);
+out:
+	if (rc) {
+		kfree(name);
+		kfree(attr);
+	}
+
+	return rc;
 }
 
-static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
-				struct bin_attribute *bin_attr, char *buf,
-				loff_t off, size_t count)
+static void opal_add_exported_attrs(struct device_node *np,
+				    struct kobject *kobj)
 {
-	return memory_read_from_buffer(buf, count, &off, bin_attr->private,
-				       bin_attr->size);
+	struct device_node *child;
+	struct property *prop;
+
+	for_each_property_of_node(np, prop) {
+		int rc;
+
+		if (!strcmp(prop->name, "name") ||
+		    !strcmp(prop->name, "phandle"))
+			continue;
+
+		rc = opal_add_one_export(kobj, prop->name, np, prop->name);
+		if (rc) {
+			pr_warn("Unable to add export %pOF/%s, rc = %d!\n",
+				np, prop->name, rc);
+		}
+	}
+
+	for_each_child_of_node(np, child) {
+		struct kobject *child_kobj;
+
+		child_kobj = kobject_create_and_add(child->name, kobj);
+		if (!child_kobj) {
+			pr_err("Unable to create export dir for %pOF\n", child);
+			continue;
+		}
+
+		opal_add_exported_attrs(child, child_kobj);
+	}
 }
 
 /*
@@ -843,11 +876,8 @@ static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
  */
 static void opal_export_attrs(void)
 {
-	struct bin_attribute *attr;
 	struct device_node *np;
-	struct property *prop;
 	struct kobject *kobj;
-	u64 vals[2];
 	int rc;
 
 	np = of_find_node_by_path("/ibm,opal/firmware/exports");
@@ -861,41 +891,16 @@ static void opal_export_attrs(void)
 		return;
 	}
 
-	for_each_property_of_node(np, prop) {
-		if (!strcmp(prop->name, "name") || !strcmp(prop->name, "phandle"))
-			continue;
-
-		if (of_property_read_u64_array(np, prop->name, &vals[0], 2))
-			continue;
-
-		attr = kzalloc(sizeof(*attr), GFP_KERNEL);
+	opal_add_exported_attrs(np, kobj);
 
-		if (attr == NULL) {
-			pr_warn("Failed kmalloc for bin_attribute!");
-			continue;
-		}
-
-		sysfs_bin_attr_init(attr);
-		attr->attr.name = kstrdup(prop->name, GFP_KERNEL);
-		attr->attr.mode = 0400;
-		attr->read = export_attr_read;
-		attr->private = __va(vals[0]);
-		attr->size = vals[1];
-
-		if (attr->attr.name == NULL) {
-			pr_warn("Failed kstrdup for bin_attribute attr.name");
-			kfree(attr);
-			continue;
-		}
-
-		rc = sysfs_create_bin_file(kobj, attr);
-		if (rc) {
-			pr_warn("Error %d creating OPAL sysfs exports/%s file\n",
-				 rc, prop->name);
-			kfree(attr->attr.name);
-			kfree(attr);
-		}
-	}
+	/*
+	 * NB: symbol_map existed before the generic export interface so it
+	 * lives under the top level opal_kobj.
+	 */
+	rc = opal_add_one_export(opal_kobj, "symbol_map",
+				 np->parent, "symbol-map");
+	if (rc)
+		pr_warn("Error %d creating OPAL symbols file\n", rc);
 
 	of_node_put(np);
 }
@@ -1042,8 +1047,6 @@ static int __init opal_init(void)
 	/* Create "opal" kobject under /sys/firmware */
 	rc = opal_sysfs_init();
 	if (rc == 0) {
-		/* Export symbol map to userspace */
-		opal_export_symmap();
 		/* Setup dump region interface */
 		opal_dump_region_init();
 		/* Setup error log interface */
@@ -1056,11 +1059,10 @@ static int __init opal_init(void)
 		opal_sys_param_init();
 		/* Setup message log sysfs interface. */
 		opal_msglog_sysfs_init();
+		/* Add all export properties*/
+		opal_export_attrs();
 	}
 
-	/* Export all properties */
-	opal_export_attrs();
-
 	/* Initialize platform devices: IPMI backend, PRD & flash interface */
 	opal_pdev_init("ibm,opal-ipmi");
 	opal_pdev_init("ibm,opal-flash");
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index da1068a9c263..22c22cd7bd82 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -188,7 +188,7 @@ static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 	unsigned int pe_num = pe->pe_number;
 
 	WARN_ON(pe->pdev);
-	WARN_ON(pe->npucomp); /* NPUs are not supposed to be freed */
+	WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */
 	kfree(pe->npucomp);
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
 	clear_bit(pe_num, phb->ioda.pe_alloc);
@@ -777,6 +777,34 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 	return 0;
 }
 
+static void pnv_ioda_unset_peltv(struct pnv_phb *phb,
+				 struct pnv_ioda_pe *pe,
+				 struct pci_dev *parent)
+{
+	int64_t rc;
+
+	while (parent) {
+		struct pci_dn *pdn = pci_get_pdn(parent);
+
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
+						pe->pe_number,
+						OPAL_REMOVE_PE_FROM_DOMAIN);
+			/* XXX What to do in case of error ? */
+		}
+		parent = parent->bus->self;
+	}
+
+	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
+				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+	/* Disassociate PE in PELT */
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
+}
+
 static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
@@ -792,7 +820,7 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
 		parent = pe->pbus->self;
 		if (pe->flags & PNV_IODA_PE_BUS_ALL)
-			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+			count = resource_size(&pe->pbus->busn_res);
 		else
 			count = 1;
 
@@ -827,25 +855,13 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	for (rid = pe->rid; rid < rid_end; rid++)
 		phb->ioda.pe_rmap[rid] = IODA_INVALID_PE;
 
-	/* Release from all parents PELT-V */
-	while (parent) {
-		struct pci_dn *pdn = pci_get_pdn(parent);
-		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
-			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
-						pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
-			/* XXX What to do in case of error ? */
-		}
-		parent = parent->bus->self;
-	}
-
-	opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number,
-				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+	/*
+	 * Release from all parents PELT-V. NPUs don't have a PELTV
+	 * table
+	 */
+	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+		pnv_ioda_unset_peltv(phb, pe, parent);
 
-	/* Disassociate PE in PELT */
-	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
-				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
-	if (rc)
-		pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc);
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
 			     bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
 	if (rc)
@@ -874,7 +890,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
 		parent = pe->pbus->self;
 		if (pe->flags & PNV_IODA_PE_BUS_ALL)
-			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+			count = resource_size(&pe->pbus->busn_res);
 		else
 			count = 1;
 
@@ -1062,20 +1078,20 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 		return NULL;
 	}
 
-	/* NOTE: We get only one ref to the pci_dev for the pdn, not for the
-	 * pointer in the PE data structure, both should be destroyed at the
-	 * same time. However, this needs to be looked at more closely again
-	 * once we actually start removing things (Hotplug, SR-IOV, ...)
+	/* NOTE: We don't get a reference for the pointer in the PE
+	 * data structure, both the device and PE structures should be
+	 * destroyed at the same time. However, removing nvlink
+	 * devices will need some work.
 	 *
 	 * At some point we want to remove the PDN completely anyways
 	 */
-	pci_dev_get(dev);
 	pdn->pe_number = pe->pe_number;
 	pe->flags = PNV_IODA_PE_DEV;
 	pe->pdev = dev;
 	pe->pbus = NULL;
 	pe->mve_number = -1;
 	pe->rid = dev->bus->number << 8 | pdn->devfn;
+	pe->device_count++;
 
 	pe_info(pe, "Associated device to PE\n");
 
@@ -1084,13 +1100,13 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 		pnv_ioda_free_pe(pe);
 		pdn->pe_number = IODA_INVALID_PE;
 		pe->pdev = NULL;
-		pci_dev_put(dev);
 		return NULL;
 	}
 
 	/* Put PE to the list */
+	mutex_lock(&phb->ioda.pe_list_mutex);
 	list_add_tail(&pe->list, &phb->ioda.pe_list);
-
+	mutex_unlock(&phb->ioda.pe_list_mutex);
 	return pe;
 }
 
@@ -1206,6 +1222,14 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 	struct pnv_phb *phb = hose->private_data;
 
 	/*
+	 * Intentionally leak a reference on the npu device (for
+	 * nvlink only; this is not an opencapi path) to make sure it
+	 * never goes away, as it's been the case all along and some
+	 * work is needed otherwise.
+	 */
+	pci_dev_get(npu_pdev);
+
+	/*
 	 * Due to a hardware errata PE#0 on the NPU is reserved for
 	 * error handling. This means we only have three PEs remaining
 	 * which need to be assigned to four links, implying some
@@ -1228,11 +1252,11 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
 			 */
 			dev_info(&npu_pdev->dev,
 				"Associating to existing PE %x\n", pe_num);
-			pci_dev_get(npu_pdev);
 			npu_pdn = pci_get_pdn(npu_pdev);
 			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
 			npu_pdn->pe_number = pe_num;
 			phb->ioda.pe_rmap[rid] = pe->pe_number;
+			pe->device_count++;
 
 			/* Map the PE to this link */
 			rc = opal_pci_set_pe(phb->opal_id, pe_num, rid,
@@ -1268,8 +1292,6 @@ static void pnv_pci_ioda_setup_PEs(void)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
-	struct pci_bus *bus;
-	struct pci_dev *pdev;
 	struct pnv_ioda_pe *pe;
 
 	list_for_each_entry(hose, &hose_list, list_node) {
@@ -1281,11 +1303,6 @@ static void pnv_pci_ioda_setup_PEs(void)
 			if (phb->model == PNV_PHB_MODEL_NPU2)
 				WARN_ON_ONCE(pnv_npu2_init(hose));
 		}
-		if (phb->type == PNV_PHB_NPU_OCAPI) {
-			bus = hose->bus;
-			list_for_each_entry(pdev, &bus->devices, bus_list)
-				pnv_ioda_setup_dev_PE(pdev);
-		}
 	}
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
@@ -1558,6 +1575,10 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 
 	/* Reserve PE for each VF */
 	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
+		int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index);
+		int vf_bus = pci_iov_virtfn_bus(pdev, vf_index);
+		struct pci_dn *vf_pdn;
+
 		if (pdn->m64_single_mode)
 			pe_num = pdn->pe_num_map[vf_index];
 		else
@@ -1570,13 +1591,11 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		pe->pbus = NULL;
 		pe->parent_dev = pdev;
 		pe->mve_number = -1;
-		pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
-			   pci_iov_virtfn_devfn(pdev, vf_index);
+		pe->rid = (vf_bus << 8) | vf_devfn;
 
 		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n",
 			hose->global_number, pdev->bus->number,
-			PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
-			PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+			PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num);
 
 		if (pnv_ioda_configure_pe(phb, pe)) {
 			/* XXX What do we do here ? */
@@ -1590,6 +1609,15 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 		list_add_tail(&pe->list, &phb->ioda.pe_list);
 		mutex_unlock(&phb->ioda.pe_list_mutex);
 
+		/* associate this pe to it's pdn */
+		list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) {
+			if (vf_pdn->busno == vf_bus &&
+			    vf_pdn->devfn == vf_devfn) {
+				vf_pdn->pe_number = pe_num;
+				break;
+			}
+		}
+
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
 #ifdef CONFIG_IOMMU_API
 		iommu_register_group(&pe->table_group,
@@ -1719,21 +1747,23 @@ int pnv_pcibios_sriov_disable(struct pci_dev *pdev)
 	pnv_pci_sriov_disable(pdev);
 
 	/* Release PCI data */
-	remove_dev_pci_data(pdev);
+	remove_sriov_vf_pdns(pdev);
 	return 0;
 }
 
 int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 {
 	/* Allocate PCI data */
-	add_dev_pci_data(pdev);
+	add_sriov_vf_pdns(pdev);
 
 	return pnv_pci_sriov_enable(pdev, num_vfs);
 }
 #endif /* CONFIG_PCI_IOV */
 
-static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
+static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev)
 {
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pnv_ioda_pe *pe;
 
@@ -2889,9 +2919,6 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	struct pci_dn *pdn;
 	int mul, total_vfs;
 
-	if (!pdev->is_physfn || pci_dev_is_added(pdev))
-		return;
-
 	pdn = pci_get_pdn(pdev);
 	pdn->vfs_expanded = 0;
 	pdn->m64_single_mode = false;
@@ -2966,6 +2993,30 @@ truncate_iov:
 		res->end = res->start - 1;
 	}
 }
+
+static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev)
+{
+	if (WARN_ON(pci_dev_is_added(pdev)))
+		return;
+
+	if (pdev->is_virtfn) {
+		struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev);
+
+		/*
+		 * VF PEs are single-device PEs so their pdev pointer needs to
+		 * be set. The pdev doesn't exist when the PE is allocated (in
+		 * (pcibios_sriov_enable()) so we fix it up here.
+		 */
+		pe->pdev = pdev;
+		WARN_ON(!(pe->flags & PNV_IODA_PE_VF));
+	} else if (pdev->is_physfn) {
+		/*
+		 * For PFs adjust their allocated IOV resources to match what
+		 * the PHB can support using it's M64 BAR table.
+		 */
+		pnv_pci_ioda_fixup_iov_resources(pdev);
+	}
+}
 #endif /* CONFIG_PCI_IOV */
 
 static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
@@ -3062,19 +3113,9 @@ static void pnv_ioda_setup_pe_seg(struct pnv_ioda_pe *pe)
 #ifdef CONFIG_DEBUG_FS
 static int pnv_pci_diag_data_set(void *data, u64 val)
 {
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
+	struct pnv_phb *phb = data;
 	s64 ret;
 
-	if (val != 1ULL)
-		return -EINVAL;
-
-	hose = (struct pci_controller *)data;
-	if (!hose || !hose->private_data)
-		return -ENODEV;
-
-	phb = hose->private_data;
-
 	/* Retrieve the diag data from firmware */
 	ret = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag_data,
 					  phb->diag_data_size);
@@ -3089,6 +3130,33 @@ static int pnv_pci_diag_data_set(void *data, u64 val)
 DEFINE_DEBUGFS_ATTRIBUTE(pnv_pci_diag_data_fops, NULL, pnv_pci_diag_data_set,
 			 "%llu\n");
 
+static int pnv_pci_ioda_pe_dump(void *data, u64 val)
+{
+	struct pnv_phb *phb = data;
+	int pe_num;
+
+	for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
+		struct pnv_ioda_pe *pe = &phb->ioda.pe_array[pe_num];
+
+		if (!test_bit(pe_num, phb->ioda.pe_alloc))
+			continue;
+
+		pe_warn(pe, "rid: %04x dev count: %2d flags: %s%s%s%s%s%s\n",
+			pe->rid, pe->device_count,
+			(pe->flags & PNV_IODA_PE_DEV) ? "dev " : "",
+			(pe->flags & PNV_IODA_PE_BUS) ? "bus " : "",
+			(pe->flags & PNV_IODA_PE_BUS_ALL) ? "all " : "",
+			(pe->flags & PNV_IODA_PE_MASTER) ? "master " : "",
+			(pe->flags & PNV_IODA_PE_SLAVE) ? "slave " : "",
+			(pe->flags & PNV_IODA_PE_VF) ? "vf " : "");
+	}
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(pnv_pci_ioda_pe_dump_fops, NULL,
+			 pnv_pci_ioda_pe_dump, "%llu\n");
+
 #endif /* CONFIG_DEBUG_FS */
 
 static void pnv_pci_ioda_create_dbgfs(void)
@@ -3113,7 +3181,9 @@ static void pnv_pci_ioda_create_dbgfs(void)
 		}
 
 		debugfs_create_file_unsafe("dump_diag_regs", 0200, phb->dbgfs,
-					   hose, &pnv_pci_diag_data_fops);
+					   phb, &pnv_pci_diag_data_fops);
+		debugfs_create_file_unsafe("dump_ioda_pe_state", 0200, phb->dbgfs,
+					   phb, &pnv_pci_ioda_pe_dump_fops);
 	}
 #endif /* CONFIG_DEBUG_FS */
 }
@@ -3383,6 +3453,28 @@ static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 	return true;
 }
 
+static bool pnv_ocapi_enable_device_hook(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn;
+	struct pnv_ioda_pe *pe;
+
+	if (!phb->initialized)
+		return true;
+
+	pdn = pci_get_pdn(dev);
+	if (!pdn)
+		return false;
+
+	if (pdn->pe_number == IODA_INVALID_PE) {
+		pe = pnv_ioda_setup_dev_PE(dev);
+		if (!pe)
+			return false;
+	}
+	return true;
+}
+
 static long pnv_pci_ioda1_unset_window(struct iommu_table_group *table_group,
 				       int num)
 {
@@ -3512,7 +3604,10 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 	struct pnv_phb *phb = pe->phb;
 	struct pnv_ioda_pe *slave, *tmp;
 
+	mutex_lock(&phb->ioda.pe_list_mutex);
 	list_del(&pe->list);
+	mutex_unlock(&phb->ioda.pe_list_mutex);
+
 	switch (phb->type) {
 	case PNV_PHB_IODA1:
 		pnv_pci_ioda1_release_pe_dma(pe);
@@ -3520,6 +3615,8 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe)
 	case PNV_PHB_IODA2:
 		pnv_pci_ioda2_release_pe_dma(pe);
 		break;
+	case PNV_PHB_NPU_OCAPI:
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -3594,9 +3691,29 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 		       OPAL_ASSERT_RESET);
 }
 
+static void pnv_pci_ioda_dma_bus_setup(struct pci_bus *bus)
+{
+	struct pci_controller *hose = bus->sysdata;
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+
+	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+		if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
+			continue;
+
+		if (!pe->pbus)
+			continue;
+
+		if (bus->number == ((pe->rid >> 8) & 0xFF)) {
+			pe->pbus = bus;
+			break;
+		}
+	}
+}
+
 static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
-	.dma_dev_setup		= pnv_pci_dma_dev_setup,
-	.dma_bus_setup		= pnv_pci_dma_bus_setup,
+	.dma_dev_setup		= pnv_pci_ioda_dma_dev_setup,
+	.dma_bus_setup		= pnv_pci_ioda_dma_bus_setup,
 	.iommu_bypass_supported	= pnv_pci_ioda_iommu_bypass_supported,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
@@ -3609,7 +3726,6 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 };
 
 static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
-	.dma_dev_setup		= pnv_pci_dma_dev_setup,
 	.setup_msi_irqs		= pnv_setup_msi_irqs,
 	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
 	.enable_device_hook	= pnv_pci_enable_device_hook,
@@ -3620,7 +3736,8 @@ static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
 };
 
 static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
-	.enable_device_hook	= pnv_pci_enable_device_hook,
+	.enable_device_hook	= pnv_ocapi_enable_device_hook,
+	.release_device		= pnv_pci_release_device,
 	.window_alignment	= pnv_pci_window_alignment,
 	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
 	.shutdown		= pnv_pci_ioda_shutdown,
@@ -3855,14 +3972,13 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		hose->controller_ops = pnv_npu_ocapi_ioda_controller_ops;
 		break;
 	default:
-		phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 		hose->controller_ops = pnv_pci_ioda_controller_ops;
 	}
 
 	ppc_md.pcibios_default_alignment = pnv_pci_default_alignment;
 
 #ifdef CONFIG_PCI_IOV
-	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov;
 	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
 	ppc_md.pcibios_sriov_enable = pnv_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pnv_pcibios_sriov_disable;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index c0bea75ac27b..5bf818246339 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -38,7 +38,7 @@ static DEFINE_MUTEX(tunnel_mutex);
 
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 {
-	struct device_node *parent = np;
+	struct device_node *node = np;
 	u32 bdfn;
 	u64 phbid;
 	int ret;
@@ -48,25 +48,29 @@ int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 		return -ENXIO;
 
 	bdfn = ((bdfn & 0x00ffff00) >> 8);
-	while ((parent = of_get_parent(parent))) {
-		if (!PCI_DN(parent)) {
-			of_node_put(parent);
+	for (node = np; node; node = of_get_parent(node)) {
+		if (!PCI_DN(node)) {
+			of_node_put(node);
 			break;
 		}
 
-		if (!of_device_is_compatible(parent, "ibm,ioda2-phb") &&
-		    !of_device_is_compatible(parent, "ibm,ioda3-phb")) {
-			of_node_put(parent);
+		if (!of_device_is_compatible(node, "ibm,ioda2-phb") &&
+		    !of_device_is_compatible(node, "ibm,ioda3-phb") &&
+		    !of_device_is_compatible(node, "ibm,ioda2-npu2-opencapi-phb")) {
+			of_node_put(node);
 			continue;
 		}
 
-		ret = of_property_read_u64(parent, "ibm,opal-phbid", &phbid);
+		ret = of_property_read_u64(node, "ibm,opal-phbid", &phbid);
 		if (ret) {
-			of_node_put(parent);
+			of_node_put(node);
 			return -ENXIO;
 		}
 
-		*id = PCI_SLOT_ID(phbid, bdfn);
+		if (of_device_is_compatible(node, "ibm,ioda2-npu2-opencapi-phb"))
+			*id = PCI_PHB_SLOT_ID(phbid);
+		else
+			*id = PCI_SLOT_ID(phbid, bdfn);
 		return 0;
 	}
 
@@ -810,53 +814,6 @@ struct iommu_table *pnv_pci_table_alloc(int nid)
 	return tbl;
 }
 
-void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-#ifdef CONFIG_PCI_IOV
-	struct pnv_ioda_pe *pe;
-	struct pci_dn *pdn;
-
-	/* Fix the VF pdn PE number */
-	if (pdev->is_virtfn) {
-		pdn = pci_get_pdn(pdev);
-		WARN_ON(pdn->pe_number != IODA_INVALID_PE);
-		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-			if (pe->rid == ((pdev->bus->number << 8) |
-			    (pdev->devfn & 0xff))) {
-				pdn->pe_number = pe->pe_number;
-				pe->pdev = pdev;
-				break;
-			}
-		}
-	}
-#endif /* CONFIG_PCI_IOV */
-
-	if (phb && phb->dma_dev_setup)
-		phb->dma_dev_setup(phb, pdev);
-}
-
-void pnv_pci_dma_bus_setup(struct pci_bus *bus)
-{
-	struct pci_controller *hose = bus->sysdata;
-	struct pnv_phb *phb = hose->private_data;
-	struct pnv_ioda_pe *pe;
-
-	list_for_each_entry(pe, &phb->ioda.pe_list, list) {
-		if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)))
-			continue;
-
-		if (!pe->pbus)
-			continue;
-
-		if (bus->number == ((pe->rid >> 8) & 0xFF)) {
-			pe->pbus = bus;
-			break;
-		}
-	}
-}
-
 struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index f914f0b14e4e..d3bbdeab3a32 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -108,7 +108,6 @@ struct pnv_phb {
 	int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
 			 unsigned int hwirq, unsigned int virq,
 			 unsigned int is_64, struct msi_msg *msg);
-	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	int (*init_m64)(struct pnv_phb *phb);
 	int (*get_pe_state)(struct pnv_phb *phb, int pe_no);
 	void (*freeze_pe)(struct pnv_phb *phb, int pe_no);
@@ -189,8 +188,6 @@ extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
-extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev);
-extern void pnv_pci_dma_bus_setup(struct pci_bus *bus);
 extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
 extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 83498604d322..11fdae81b5dd 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -233,6 +233,10 @@ static void  __noreturn pnv_restart(char *cmd)
 			rc = opal_cec_reboot();
 		else if (strcmp(cmd, "full") == 0)
 			rc = opal_cec_reboot2(OPAL_REBOOT_FULL_IPL, NULL);
+		else if (strcmp(cmd, "mpipl") == 0)
+			rc = opal_cec_reboot2(OPAL_REBOOT_MPIPL, NULL);
+		else if (strcmp(cmd, "error") == 0)
+			rc = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, NULL);
 		else
 			rc = OPAL_UNSUPPORTED;
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 595e9f8a6539..24c18362e5ea 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -21,7 +21,6 @@ config PPC_PSERIES
 	select PPC_DOORBELL
 	select HOTPLUG_CPU
 	select ARCH_RANDOM
-	select PPC_DOORBELL
 	select FORCE_SMP
 	select SWIOTLB
 	default y
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index d4a8f1702417..3e49cc23a97a 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -22,6 +22,7 @@
 #include <asm/firmware.h>
 #include <asm/prom.h>
 #include <asm/udbg.h>
+#include <asm/svm.h>
 
 #include "pseries.h"
 
@@ -55,7 +56,8 @@ hypertas_fw_features_table[] = {
 	{FW_FEATURE_LLAN,		"hcall-lLAN"},
 	{FW_FEATURE_BULK_REMOVE,	"hcall-bulk"},
 	{FW_FEATURE_XDABR,		"hcall-xdabr"},
-	{FW_FEATURE_MULTITCE,		"hcall-multi-tce"},
+	{FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE,
+					"hcall-multi-tce"},
 	{FW_FEATURE_SPLPAR,		"hcall-splpar"},
 	{FW_FEATURE_VPHN,		"hcall-vphn"},
 	{FW_FEATURE_SET_MODE,		"hcall-set-mode"},
@@ -100,6 +102,12 @@ static void __init fw_hypertas_feature_init(const char *hypertas,
 		}
 	}
 
+	if (is_secure_guest() &&
+	    (powerpc_firmware_features & FW_FEATURE_PUT_TCE_IND)) {
+		powerpc_firmware_features &= ~FW_FEATURE_PUT_TCE_IND;
+		pr_debug("SVM: disabling PUT_TCE_IND firmware feature\n");
+	}
+
 	pr_debug(" <- fw_hypertas_feature_init()\n");
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index c126b94d1943..a4d40a3ceea3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -360,8 +360,10 @@ static bool lmb_is_removable(struct drmem_lmb *lmb)
 
 	for (i = 0; i < scns_per_block; i++) {
 		pfn = PFN_DOWN(phys_addr);
-		if (!pfn_present(pfn))
+		if (!pfn_present(pfn)) {
+			phys_addr += MIN_MEMORY_BLOCK_SIZE;
 			continue;
+		}
 
 		rc = rc && is_mem_section_removable(pfn, PAGES_PER_SECTION);
 		phys_addr += MIN_MEMORY_BLOCK_SIZE;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6ba081dd61c9..2e0a8eab5588 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -36,7 +36,6 @@
 #include <asm/udbg.h>
 #include <asm/mmzone.h>
 #include <asm/plpar_wrappers.h>
-#include <asm/svm.h>
 
 #include "pseries.h"
 
@@ -133,10 +132,10 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 	return be64_to_cpu(*tcep);
 }
 
-static void tce_free_pSeriesLP(struct iommu_table*, long, long);
+static void tce_free_pSeriesLP(unsigned long liobn, long, long);
 static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
 
-static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 				long npages, unsigned long uaddr,
 				enum dma_data_direction direction,
 				unsigned long attrs)
@@ -147,25 +146,25 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	int ret = 0;
 	long tcenum_start = tcenum, npages_start = npages;
 
-	rpn = __pa(uaddr) >> TCE_SHIFT;
+	rpn = __pa(uaddr) >> tceshift;
 	proto_tce = TCE_PCI_READ;
 	if (direction != DMA_TO_DEVICE)
 		proto_tce |= TCE_PCI_WRITE;
 
 	while (npages--) {
-		tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
-		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
+		tce = proto_tce | (rpn & TCE_RPN_MASK) << tceshift;
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << tceshift, tce);
 
 		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 			ret = (int)rc;
-			tce_free_pSeriesLP(tbl, tcenum_start,
+			tce_free_pSeriesLP(liobn, tcenum_start,
 			                   (npages_start - (npages + 1)));
 			break;
 		}
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
-			printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
+			printk("\tindex   = 0x%llx\n", (u64)liobn);
 			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
 			printk("\ttce val = 0x%llx\n", tce );
 			dump_stack();
@@ -193,8 +192,9 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	int ret = 0;
 	unsigned long flags;
 
-	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_MULTITCE)) {
-		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+	if ((npages == 1) || !firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) {
+		return tce_build_pSeriesLP(tbl->it_index, tcenum,
+					   tbl->it_page_shift, npages, uaddr,
 		                           direction, attrs);
 	}
 
@@ -210,8 +210,9 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
 			local_irq_restore(flags);
-			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
-					    direction, attrs);
+			return tce_build_pSeriesLP(tbl->it_index, tcenum,
+					tbl->it_page_shift,
+					npages, uaddr, direction, attrs);
 		}
 		__this_cpu_write(tce_page, tcep);
 	}
@@ -262,16 +263,16 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
-static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
+static void tce_free_pSeriesLP(unsigned long liobn, long tcenum, long npages)
 {
 	u64 rc;
 
 	while (npages--) {
-		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, 0);
+		rc = plpar_tce_put((u64)liobn, (u64)tcenum << 12, 0);
 
 		if (rc && printk_ratelimit()) {
 			printk("tce_free_pSeriesLP: plpar_tce_put failed. rc=%lld\n", rc);
-			printk("\tindex   = 0x%llx\n", (u64)tbl->it_index);
+			printk("\tindex   = 0x%llx\n", (u64)liobn);
 			printk("\ttcenum  = 0x%llx\n", (u64)tcenum);
 			dump_stack();
 		}
@@ -285,8 +286,8 @@ static void tce_freemulti_pSeriesLP(struct iommu_table *tbl, long tcenum, long n
 {
 	u64 rc;
 
-	if (!firmware_has_feature(FW_FEATURE_MULTITCE))
-		return tce_free_pSeriesLP(tbl, tcenum, npages);
+	if (!firmware_has_feature(FW_FEATURE_STUFF_TCE))
+		return tce_free_pSeriesLP(tbl->it_index, tcenum, npages);
 
 	rc = plpar_tce_stuff((u64)tbl->it_index, (u64)tcenum << 12, 0, npages);
 
@@ -401,6 +402,19 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 	u64 rc = 0;
 	long l, limit;
 
+	if (!firmware_has_feature(FW_FEATURE_PUT_TCE_IND)) {
+		unsigned long tceshift = be32_to_cpu(maprange->tce_shift);
+		unsigned long dmastart = (start_pfn << PAGE_SHIFT) +
+				be64_to_cpu(maprange->dma_base);
+		unsigned long tcenum = dmastart >> tceshift;
+		unsigned long npages = num_pfn << PAGE_SHIFT >> tceshift;
+		void *uaddr = __va(start_pfn << PAGE_SHIFT);
+
+		return tce_build_pSeriesLP(be32_to_cpu(maprange->liobn),
+				tcenum, tceshift, npages, (unsigned long) uaddr,
+				DMA_BIDIRECTIONAL, 0);
+	}
+
 	local_irq_disable();	/* to protect tcep and the page behind it */
 	tcep = __this_cpu_read(tce_page);
 
@@ -1320,24 +1334,18 @@ void iommu_init_early_pSeries(void)
 	of_reconfig_notifier_register(&iommu_reconfig_nb);
 	register_memory_notifier(&iommu_mem_nb);
 
-	/*
-	 * Secure guest memory is inacessible to devices so regular DMA isn't
-	 * possible.
-	 *
-	 * In that case keep devices' dma_map_ops as NULL so that the generic
-	 * DMA code path will use SWIOTLB to bounce buffers for DMA.
-	 */
-	if (!is_secure_guest())
-		set_pci_dma_ops(&dma_iommu_ops);
+	set_pci_dma_ops(&dma_iommu_ops);
 }
 
 static int __init disable_multitce(char *str)
 {
 	if (strcmp(str, "off") == 0 &&
 	    firmware_has_feature(FW_FEATURE_LPAR) &&
-	    firmware_has_feature(FW_FEATURE_MULTITCE)) {
+	    (firmware_has_feature(FW_FEATURE_PUT_TCE_IND) ||
+	     firmware_has_feature(FW_FEATURE_STUFF_TCE))) {
 		printk(KERN_INFO "Disabling MULTITCE firmware feature\n");
-		powerpc_firmware_features &= ~FW_FEATURE_MULTITCE;
+		powerpc_firmware_features &=
+			~(FW_FEATURE_PUT_TCE_IND | FW_FEATURE_STUFF_TCE);
 	}
 	return 1;
 }
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 60cb29ae4739..3c3da25b445c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -582,12 +582,12 @@ static int vcpudispatch_stats_open(struct inode *inode, struct file *file)
 	return single_open(file, vcpudispatch_stats_display, NULL);
 }
 
-static const struct file_operations vcpudispatch_stats_proc_ops = {
-	.open		= vcpudispatch_stats_open,
-	.read		= seq_read,
-	.write		= vcpudispatch_stats_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops vcpudispatch_stats_proc_ops = {
+	.proc_open	= vcpudispatch_stats_open,
+	.proc_read	= seq_read,
+	.proc_write	= vcpudispatch_stats_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 static ssize_t vcpudispatch_stats_freq_write(struct file *file,
@@ -626,12 +626,12 @@ static int vcpudispatch_stats_freq_open(struct inode *inode, struct file *file)
 	return single_open(file, vcpudispatch_stats_freq_display, NULL);
 }
 
-static const struct file_operations vcpudispatch_stats_freq_proc_ops = {
-	.open		= vcpudispatch_stats_freq_open,
-	.read		= seq_read,
-	.write		= vcpudispatch_stats_freq_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops vcpudispatch_stats_freq_proc_ops = {
+	.proc_open	= vcpudispatch_stats_freq_open,
+	.proc_read	= seq_read,
+	.proc_write	= vcpudispatch_stats_freq_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 static int __init vcpudispatch_stats_procfs_init(void)
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index e33e8bc4b69b..b8d28ab88178 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -435,10 +435,10 @@ static void maxmem_data(struct seq_file *m)
 {
 	unsigned long maxmem = 0;
 
-	maxmem += drmem_info->n_lmbs * drmem_info->lmb_size;
+	maxmem += (unsigned long)drmem_info->n_lmbs * drmem_info->lmb_size;
 	maxmem += hugetlb_total_pages() * PAGE_SIZE;
 
-	seq_printf(m, "MaxMem=%ld\n", maxmem);
+	seq_printf(m, "MaxMem=%lu\n", maxmem);
 }
 
 static int pseries_lparcfg_data(struct seq_file *m, void *v)
@@ -698,12 +698,12 @@ static int lparcfg_open(struct inode *inode, struct file *file)
 	return single_open(file, lparcfg_data, NULL);
 }
 
-static const struct file_operations lparcfg_fops = {
-	.read		= seq_read,
-	.write		= lparcfg_write,
-	.open		= lparcfg_open,
-	.release	= single_release,
-	.llseek		= seq_lseek,
+static const struct proc_ops lparcfg_proc_ops = {
+	.proc_read	= seq_read,
+	.proc_write	= lparcfg_write,
+	.proc_open	= lparcfg_open,
+	.proc_release	= single_release,
+	.proc_lseek	= seq_lseek,
 };
 
 static int __init lparcfg_init(void)
@@ -714,7 +714,7 @@ static int __init lparcfg_init(void)
 	if (firmware_has_feature(FW_FEATURE_SPLPAR))
 		mode |= 0200;
 
-	if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops)) {
+	if (!proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_proc_ops)) {
 		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
 		return -EIO;
 	}
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index c2ef320ba1bf..0b4467e378e5 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -69,7 +69,8 @@ static int drc_pmem_bind(struct papr_scm_priv *p)
 		return rc;
 
 	p->bound_addr = saved;
-	dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
+	dev_dbg(&p->pdev->dev, "bound drc 0x%x to 0x%lx\n",
+		p->drc_index, (unsigned long)saved);
 	return rc;
 }
 
@@ -133,7 +134,7 @@ static int drc_pmem_query_n_bind(struct papr_scm_priv *p)
 		goto err_out;
 
 	p->bound_addr = start_addr;
-	dev_dbg(&p->pdev->dev, "bound drc 0x%x to %pR\n", p->drc_index, &p->res);
+	dev_dbg(&p->pdev->dev, "bound drc 0x%x to 0x%lx\n", p->drc_index, start_addr);
 	return rc;
 
 err_out:
@@ -322,6 +323,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	p->bus = nvdimm_bus_register(NULL, &p->bus_desc);
 	if (!p->bus) {
 		dev_err(dev, "Error creating nvdimm bus %pOF\n", p->dn);
+		kfree(p->bus_desc.provider_name);
 		return -ENXIO;
 	}
 
@@ -356,7 +358,6 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	ndr_desc.mapping = &mapping;
 	ndr_desc.num_mappings = 1;
 	ndr_desc.nd_set = &p->nd_set;
-	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
 
 	if (p->is_volatile)
 		p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
@@ -477,6 +478,7 @@ static int papr_scm_remove(struct platform_device *pdev)
 
 	nvdimm_bus_unregister(p->bus);
 	drc_pmem_unbind(p);
+	kfree(p->bus_desc.provider_name);
 	kfree(p);
 
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 722830978639..911534b89c85 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -192,7 +192,7 @@ int pseries_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 int pseries_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 {
 	/* Allocate PCI data */
-	add_dev_pci_data(pdev);
+	add_sriov_vf_pdns(pdev);
 	return pseries_pci_sriov_enable(pdev, num_vfs);
 }
 
@@ -204,7 +204,7 @@ int pseries_pcibios_sriov_disable(struct pci_dev *pdev)
 	/* Releasing pe_num_map */
 	kfree(pdn->pe_num_map);
 	/* Release PCI data */
-	remove_dev_pci_data(pdev);
+	remove_sriov_vf_pdns(pdev);
 	pci_vf_drivers_autoprobe(pdev, true);
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 8a9c4fb95b8b..7f7369fec46b 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -391,9 +391,9 @@ out:
 	return rv ? rv : count;
 }
 
-static const struct file_operations ofdt_fops = {
-	.write = ofdt_write,
-	.llseek = noop_llseek,
+static const struct proc_ops ofdt_proc_ops = {
+	.proc_write	= ofdt_write,
+	.proc_lseek	= noop_llseek,
 };
 
 /* create /proc/powerpc/ofdt write-only by root */
@@ -401,7 +401,7 @@ static int proc_ppc64_create_ofdt(void)
 {
 	struct proc_dir_entry *ent;
 
-	ent = proc_create("powerpc/ofdt", 0200, NULL, &ofdt_fops);
+	ent = proc_create("powerpc/ofdt", 0200, NULL, &ofdt_proc_ops);
 	if (ent)
 		proc_set_size(ent, 0);
 
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index a0001280503c..2879c4f0ceb7 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -152,13 +152,12 @@ static int scanlog_release(struct inode * inode, struct file * file)
 	return 0;
 }
 
-static const struct file_operations scanlog_fops = {
-	.owner		= THIS_MODULE,
-	.read		= scanlog_read,
-	.write		= scanlog_write,
-	.open		= scanlog_open,
-	.release	= scanlog_release,
-	.llseek		= noop_llseek,
+static const struct proc_ops scanlog_proc_ops = {
+	.proc_read	= scanlog_read,
+	.proc_write	= scanlog_write,
+	.proc_open	= scanlog_open,
+	.proc_release	= scanlog_release,
+	.proc_lseek	= noop_llseek,
 };
 
 static int __init scanlog_init(void)
@@ -176,7 +175,7 @@ static int __init scanlog_init(void)
 		goto err;
 
 	ent = proc_create("powerpc/rtas/scan-log-dump", 0400, NULL,
-			  &scanlog_fops);
+			  &scanlog_proc_ops);
 	if (!ent)
 		goto err;
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 79e2287991db..f682b7babc09 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1176,6 +1176,8 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 	if (tbl == NULL)
 		return NULL;
 
+	kref_init(&tbl->it_kref);
+
 	of_parse_dma_window(dev->dev.of_node, dma_window,
 			    &tbl->it_index, &offset, &size);
 
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 617a443d673d..4a8874bc1057 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1065,13 +1065,11 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs)
 	addr += mfspr(SPRN_MCAR);
 
 	if (is_in_pci_mem_space(addr)) {
-		if (user_mode(regs)) {
-			pagefault_disable();
-			ret = get_user(inst, (__u32 __user *)regs->nip);
-			pagefault_enable();
-		} else {
+		if (user_mode(regs))
+			ret = probe_user_read(&inst, (void __user *)regs->nip,
+					      sizeof(inst));
+		else
 			ret = probe_kernel_address((void *)regs->nip, inst);
-		}
 
 		if (!ret && mcheck_handle_load(regs, inst)) {
 			regs->nip += 4;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 934a77324f6b..a3a72b780e67 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -964,7 +964,7 @@ static struct irq_chip mpic_irq_chip = {
 };
 
 #ifdef CONFIG_SMP
-static struct irq_chip mpic_ipi_chip = {
+static const struct irq_chip mpic_ipi_chip = {
 	.irq_mask	= mpic_mask_ipi,
 	.irq_unmask	= mpic_unmask_ipi,
 	.irq_eoi	= mpic_end_ipi,
@@ -978,7 +978,7 @@ static struct irq_chip mpic_tm_chip = {
 };
 
 #ifdef CONFIG_MPIC_U3_HT_IRQS
-static struct irq_chip mpic_irq_ht_chip = {
+static const struct irq_chip mpic_irq_ht_chip = {
 	.irq_startup	= mpic_startup_ht_irq,
 	.irq_shutdown	= mpic_shutdown_ht_irq,
 	.irq_mask	= mpic_mask_irq,
diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh
index 7b9fe0a567cf..014e00e74d2b 100755
--- a/arch/powerpc/tools/relocs_check.sh
+++ b/arch/powerpc/tools/relocs_check.sh
@@ -10,14 +10,21 @@
 # based on relocs_check.pl
 # Copyright © 2009 IBM Corporation
 
-if [ $# -lt 2 ]; then
-	echo "$0 [path to objdump] [path to vmlinux]" 1>&2
+if [ $# -lt 3 ]; then
+	echo "$0 [path to objdump] [path to nm] [path to vmlinux]" 1>&2
 	exit 1
 fi
 
-# Have Kbuild supply the path to objdump so we handle cross compilation.
+# Have Kbuild supply the path to objdump and nm so we handle cross compilation.
 objdump="$1"
-vmlinux="$2"
+nm="$2"
+vmlinux="$3"
+
+# Remove from the bad relocations those that match an undefined weak symbol
+# which will result in an absolute relocation to 0.
+# Weak unresolved symbols are of that form in nm output:
+# "                  w _binary__btf_vmlinux_bin_end"
+undef_weak_symbols=$($nm "$vmlinux" | awk '$1 ~ /w/ { print $2 }')
 
 bad_relocs=$(
 $objdump -R "$vmlinux" |
@@ -26,8 +33,6 @@ $objdump -R "$vmlinux" |
 	# These relocations are okay
 	# On PPC64:
 	#	R_PPC64_RELATIVE, R_PPC64_NONE
-	#	R_PPC64_ADDR64 mach_<name>
-	#	R_PPC64_ADDR64 __crc_<name>
 	# On PPC:
 	#	R_PPC_RELATIVE, R_PPC_ADDR16_HI,
 	#	R_PPC_ADDR16_HA,R_PPC_ADDR16_LO,
@@ -39,8 +44,7 @@ R_PPC_ADDR16_HI
 R_PPC_ADDR16_HA
 R_PPC_RELATIVE
 R_PPC_NONE' |
-	grep -E -v '\<R_PPC64_ADDR64[[:space:]]+mach_' |
-	grep -E -v '\<R_PPC64_ADDR64[[:space:]]+__crc_'
+	([ "$undef_weak_symbols" ] && grep -F -w -v "$undef_weak_symbols" || cat)
 )
 
 if [ -z "$bad_relocs" ]; then
diff --git a/arch/powerpc/xmon/dis-asm.h b/arch/powerpc/xmon/dis-asm.h
index c4d246ebca37..c4c982d6402e 100644
--- a/arch/powerpc/xmon/dis-asm.h
+++ b/arch/powerpc/xmon/dis-asm.h
@@ -13,13 +13,13 @@ extern int print_insn_spu(unsigned long insn, unsigned long memaddr);
 #else
 static inline int print_insn_powerpc(unsigned long insn, unsigned long memaddr)
 {
-	printf("%.8x", insn);
+	printf("%.8lx", insn);
 	return 0;
 }
 
 static inline int print_insn_spu(unsigned long insn, unsigned long memaddr)
 {
-	printf("%.8x", insn);
+	printf("%.8lx", insn);
 	return 0;
 }
 #endif
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a7056049709e..e8c84d265602 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1192,16 +1192,19 @@ static int do_step(struct pt_regs *regs)
 
 static void bootcmds(void)
 {
+	char tmp[64];
 	int cmd;
 
 	cmd = inchar();
-	if (cmd == 'r')
-		ppc_md.restart(NULL);
-	else if (cmd == 'h')
+	if (cmd == 'r') {
+		getstring(tmp, 64);
+		ppc_md.restart(tmp);
+	} else if (cmd == 'h') {
 		ppc_md.halt();
-	else if (cmd == 'p')
+	} else if (cmd == 'p') {
 		if (pm_power_off)
 			pm_power_off();
+	}
 }
 
 static int cpu_cmd(void)
@@ -1949,15 +1952,14 @@ static void dump_300_sprs(void)
 
 	printf("pidr   = %.16lx  tidr  = %.16lx\n",
 		mfspr(SPRN_PID), mfspr(SPRN_TIDR));
-	printf("asdr   = %.16lx  psscr = %.16lx\n",
-		mfspr(SPRN_ASDR), hv ? mfspr(SPRN_PSSCR)
-					: mfspr(SPRN_PSSCR_PR));
+	printf("psscr  = %.16lx\n",
+		hv ? mfspr(SPRN_PSSCR) : mfspr(SPRN_PSSCR_PR));
 
 	if (!hv)
 		return;
 
-	printf("ptcr   = %.16lx\n",
-		mfspr(SPRN_PTCR));
+	printf("ptcr   = %.16lx  asdr  = %.16lx\n",
+		mfspr(SPRN_PTCR), mfspr(SPRN_ASDR));
 #endif
 }
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index fa7dc03459e7..73f029eae0cc 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -12,8 +12,6 @@ config 32BIT
 
 config RISCV
 	def_bool y
-	# even on 32-bit, physical (and DMA) addresses are > 32-bits
-	select PHYS_ADDR_T_64BIT
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_IRQ
@@ -57,6 +55,7 @@ config RISCV
 	select GENERIC_ARCH_TOPOLOGY if SMP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MMIOWB
+	select ARCH_HAS_DEBUG_VIRTUAL
 	select HAVE_EBPF_JIT if 64BIT
 	select EDAC_SUPPORT
 	select ARCH_HAS_GIGANTIC_PAGE
@@ -66,6 +65,7 @@ config RISCV
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select HAVE_COPY_THREAD_TLS
+	select HAVE_ARCH_KASAN if MMU && 64BIT
 
 config ARCH_MMAP_RND_BITS_MIN
 	default 18 if 64BIT
diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
index a2e3d54e830c..7db861053483 100644
--- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
+++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi
@@ -268,6 +268,19 @@
 			interrupts = <1 2 3>;
 			reg = <0x0 0x2010000 0x0 0x1000>;
 		};
-
+		gpio: gpio@10060000 {
+			compatible = "sifive,fu540-c000-gpio", "sifive,gpio0";
+			interrupt-parent = <&plic0>;
+			interrupts = <7>, <8>, <9>, <10>, <11>, <12>, <13>,
+				     <14>, <15>, <16>, <17>, <18>, <19>, <20>,
+				     <21>, <22>;
+			reg = <0x0 0x10060000 0x0 0x1000>;
+			gpio-controller;
+			#gpio-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			clocks = <&prci PRCI_CLK_TLCLK>;
+			status = "disabled";
+		};
 	};
 };
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 88cfcb96bf23..609198cb1163 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -94,3 +94,7 @@
 &pwm1 {
 	status = "okay";
 };
+
+&gpio {
+	status = "okay";
+};
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 1efaeddf1e4b..ec0ca8c6ab64 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -7,7 +7,6 @@ generic-y += div64.h
 generic-y += extable.h
 generic-y += flat.h
 generic-y += dma.h
-generic-y += dma-contiguous.h
 generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
new file mode 100644
index 000000000000..eee6e6588b12
--- /dev/null
+++ b/arch/riscv/include/asm/kasan.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2019 Andes Technology Corporation */
+
+#ifndef __ASM_KASAN_H
+#define __ASM_KASAN_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_KASAN
+
+#include <asm/pgtable.h>
+
+#define KASAN_SHADOW_SCALE_SHIFT	3
+
+#define KASAN_SHADOW_SIZE	(UL(1) << (38 - KASAN_SHADOW_SCALE_SHIFT))
+#define KASAN_SHADOW_START	0xffffffc000000000 /* 2^64 - 2^38 */
+#define KASAN_SHADOW_END	(KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
+
+#define KASAN_SHADOW_OFFSET	(KASAN_SHADOW_END - (1ULL << \
+					(64 - KASAN_SHADOW_SCALE_SHIFT)))
+
+void kasan_init(void);
+asmlinkage void kasan_early_init(void);
+
+#endif
+#endif
+#endif /* __ASM_KASAN_H */
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index ac699246ae7e..8ca1930caa44 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -100,8 +100,20 @@ extern unsigned long pfn_base;
 extern unsigned long max_low_pfn;
 extern unsigned long min_low_pfn;
 
-#define __pa(x)		((unsigned long)(x) - va_pa_offset)
-#define __va(x)		((void *)((unsigned long) (x) + va_pa_offset))
+#define __pa_to_va_nodebug(x)	((void *)((unsigned long) (x) + va_pa_offset))
+#define __va_to_pa_nodebug(x)	((unsigned long)(x) - va_pa_offset)
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern phys_addr_t __virt_to_phys(unsigned long x);
+extern phys_addr_t __phys_addr_symbol(unsigned long x);
+#else
+#define __virt_to_phys(x)	__va_to_pa_nodebug(x)
+#define __phys_addr_symbol(x)	__va_to_pa_nodebug(x)
+#endif /* CONFIG_DEBUG_VIRTUAL */
+
+#define __pa_symbol(x)	__phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0))
+#define __pa(x)		__virt_to_phys((unsigned long)(x))
+#define __va(x)		((void *)__pa_to_va_nodebug((phys_addr_t)(x)))
 
 #define phys_to_pfn(phys)	(PFN_DOWN(phys))
 #define pfn_to_phys(pfn)	(PFN_PHYS(pfn))
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 74630989006d..b15f70a1fdfa 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -43,6 +43,13 @@ static inline int pud_bad(pud_t pud)
 	return !pud_present(pud);
 }
 
+#define pud_leaf	pud_leaf
+static inline int pud_leaf(pud_t pud)
+{
+	return pud_present(pud) &&
+	       (pud_val(pud) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+}
+
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	*pudp = pud;
@@ -58,6 +65,11 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
 	return (unsigned long)pfn_to_virt(pud_val(pud) >> _PAGE_PFN_SHIFT);
 }
 
+static inline struct page *pud_page(pud_t pud)
+{
+	return pfn_to_page(pud_val(pud) >> _PAGE_PFN_SHIFT);
+}
+
 #define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index f66b87314fa2..e43041519edd 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -130,6 +130,13 @@ static inline int pmd_bad(pmd_t pmd)
 	return !pmd_present(pmd);
 }
 
+#define pmd_leaf	pmd_leaf
+static inline int pmd_leaf(pmd_t pmd)
+{
+	return pmd_present(pmd) &&
+	       (pmd_val(pmd) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC));
+}
+
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h
index 1b5d44585962..924af13f8555 100644
--- a/arch/riscv/include/asm/string.h
+++ b/arch/riscv/include/asm/string.h
@@ -11,8 +11,17 @@
 
 #define __HAVE_ARCH_MEMSET
 extern asmlinkage void *memset(void *, int, size_t);
+extern asmlinkage void *__memset(void *, int, size_t);
 
 #define __HAVE_ARCH_MEMCPY
 extern asmlinkage void *memcpy(void *, const void *, size_t);
+extern asmlinkage void *__memcpy(void *, const void *, size_t);
 
+/* For those files which don't want to check by kasan. */
+#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
+
+#define memcpy(dst, src, len) __memcpy(dst, src, len)
+#define memset(s, c, n) __memset(s, c, n)
+
+#endif
 #endif /* _ASM_RISCV_STRING_H */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index a4242be66966..271860fc2c3f 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -121,6 +121,9 @@ clear_bss_done:
 	sw zero, TASK_TI_CPU(tp)
 	la sp, init_thread_union + THREAD_SIZE
 
+#ifdef CONFIG_KASAN
+	call kasan_early_init
+#endif
 	/* Start the kernel */
 	call parse_dtb
 	tail start_kernel
diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c
index 2a02b7eebee0..450492e1cb4e 100644
--- a/arch/riscv/kernel/riscv_ksyms.c
+++ b/arch/riscv/kernel/riscv_ksyms.c
@@ -11,3 +11,5 @@
  */
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(__memset);
+EXPORT_SYMBOL(__memcpy);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 9babfcf3bb70..0a6d415b0a5a 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -24,6 +24,7 @@
 #include <asm/smp.h>
 #include <asm/tlbflush.h>
 #include <asm/thread_info.h>
+#include <asm/kasan.h>
 
 #include "head.h"
 
@@ -74,6 +75,10 @@ void __init setup_arch(char **cmdline_p)
 	swiotlb_init(1);
 #endif
 
+#ifdef CONFIG_KASAN
+	kasan_init();
+#endif
+
 #ifdef CONFIG_SMP
 	setup_smp();
 #endif
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 12f42f96d46e..1e0193ded420 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -46,6 +46,7 @@ SECTIONS
 		KPROBES_TEXT
 		ENTRY_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		_etext = .;
 	}
diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S
index b4c477846e91..51ab716253fa 100644
--- a/arch/riscv/lib/memcpy.S
+++ b/arch/riscv/lib/memcpy.S
@@ -7,7 +7,8 @@
 #include <asm/asm.h>
 
 /* void *memcpy(void *, const void *, size_t) */
-ENTRY(memcpy)
+ENTRY(__memcpy)
+WEAK(memcpy)
 	move t6, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented copy for small sizes */
@@ -104,4 +105,4 @@ ENTRY(memcpy)
 	bltu a1, a3, 5b
 6:
 	ret
-END(memcpy)
+END(__memcpy)
diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S
index 5a7386b47175..34c5360c6705 100644
--- a/arch/riscv/lib/memset.S
+++ b/arch/riscv/lib/memset.S
@@ -8,7 +8,8 @@
 #include <asm/asm.h>
 
 /* void *memset(void *, int, size_t) */
-ENTRY(memset)
+ENTRY(__memset)
+WEAK(memset)
 	move t0, a0  /* Preserve return value */
 
 	/* Defer to byte-oriented fill for small sizes */
@@ -109,4 +110,4 @@ ENTRY(memset)
 	bltu t0, a3, 5b
 6:
 	ret
-END(memset)
+END(__memset)
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index a1bd95c8047a..50b7af58c566 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -15,3 +15,11 @@ ifeq ($(CONFIG_MMU),y)
 obj-$(CONFIG_SMP) += tlbflush.o
 endif
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_KASAN)   += kasan_init.o
+
+ifdef CONFIG_KASAN
+KASAN_SANITIZE_kasan_init.o := n
+KASAN_SANITIZE_init.o := n
+endif
+
+obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
new file mode 100644
index 000000000000..f0cc86040587
--- /dev/null
+++ b/arch/riscv/mm/kasan_init.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2019 Andes Technology Corporation
+
+#include <linux/pfn.h>
+#include <linux/init_task.h>
+#include <linux/kasan.h>
+#include <linux/kernel.h>
+#include <linux/memblock.h>
+#include <asm/tlbflush.h>
+#include <asm/pgtable.h>
+#include <asm/fixmap.h>
+
+extern pgd_t early_pg_dir[PTRS_PER_PGD];
+asmlinkage void __init kasan_early_init(void)
+{
+	uintptr_t i;
+	pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
+
+	for (i = 0; i < PTRS_PER_PTE; ++i)
+		set_pte(kasan_early_shadow_pte + i,
+			mk_pte(virt_to_page(kasan_early_shadow_page),
+			PAGE_KERNEL));
+
+	for (i = 0; i < PTRS_PER_PMD; ++i)
+		set_pmd(kasan_early_shadow_pmd + i,
+		 pfn_pmd(PFN_DOWN(__pa((uintptr_t)kasan_early_shadow_pte)),
+			__pgprot(_PAGE_TABLE)));
+
+	for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
+	     i += PGDIR_SIZE, ++pgd)
+		set_pgd(pgd,
+		 pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))),
+			__pgprot(_PAGE_TABLE)));
+
+	/* init for swapper_pg_dir */
+	pgd = pgd_offset_k(KASAN_SHADOW_START);
+
+	for (i = KASAN_SHADOW_START; i < KASAN_SHADOW_END;
+	     i += PGDIR_SIZE, ++pgd)
+		set_pgd(pgd,
+		 pfn_pgd(PFN_DOWN(__pa(((uintptr_t)kasan_early_shadow_pmd))),
+			__pgprot(_PAGE_TABLE)));
+
+	flush_tlb_all();
+}
+
+static void __init populate(void *start, void *end)
+{
+	unsigned long i;
+	unsigned long vaddr = (unsigned long)start & PAGE_MASK;
+	unsigned long vend = PAGE_ALIGN((unsigned long)end);
+	unsigned long n_pages = (vend - vaddr) / PAGE_SIZE;
+	unsigned long n_pmds =
+		(n_pages % PTRS_PER_PTE) ? n_pages / PTRS_PER_PTE + 1 :
+						n_pages / PTRS_PER_PTE;
+	pgd_t *pgd = pgd_offset_k(vaddr);
+	pmd_t *pmd = memblock_alloc(n_pmds * sizeof(pmd_t), PAGE_SIZE);
+	pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE);
+
+	for (i = 0; i < n_pages; i++) {
+		phys_addr_t phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
+
+		set_pte(pte + i, pfn_pte(PHYS_PFN(phys), PAGE_KERNEL));
+	}
+
+	for (i = 0; i < n_pmds; ++pgd, i += PTRS_PER_PMD)
+		set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(((uintptr_t)(pmd + i)))),
+				__pgprot(_PAGE_TABLE)));
+
+	for (i = 0; i < n_pages; ++pmd, i += PTRS_PER_PTE)
+		set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa((uintptr_t)(pte + i))),
+				__pgprot(_PAGE_TABLE)));
+
+	flush_tlb_all();
+	memset(start, 0, end - start);
+}
+
+void __init kasan_init(void)
+{
+	struct memblock_region *reg;
+	unsigned long i;
+
+	kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
+			(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
+
+	for_each_memblock(memory, reg) {
+		void *start = (void *)__va(reg->base);
+		void *end = (void *)__va(reg->base + reg->size);
+
+		if (start >= end)
+			break;
+
+		populate(kasan_mem_to_shadow(start),
+			 kasan_mem_to_shadow(end));
+	};
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte(&kasan_early_shadow_pte[i],
+			mk_pte(virt_to_page(kasan_early_shadow_page),
+			__pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_ACCESSED)));
+
+	memset(kasan_early_shadow_page, 0, PAGE_SIZE);
+	init_task.kasan_depth = 0;
+}
diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c
new file mode 100644
index 000000000000..e8e4dcd39fed
--- /dev/null
+++ b/arch/riscv/mm/physaddr.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/types.h>
+#include <linux/mmdebug.h>
+#include <linux/mm.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+
+phys_addr_t __virt_to_phys(unsigned long x)
+{
+	phys_addr_t y = x - PAGE_OFFSET;
+
+	/*
+	 * Boundary checking aginst the kernel linear mapping space.
+	 */
+	WARN(y >= KERN_VIRT_SIZE,
+	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
+	     (void *)x, (void *)x);
+
+	return __va_to_pa_nodebug(x);
+}
+EXPORT_SYMBOL(__virt_to_phys);
+
+phys_addr_t __phys_addr_symbol(unsigned long x)
+{
+	unsigned long kernel_start = (unsigned long)PAGE_OFFSET;
+	unsigned long kernel_end = (unsigned long)_end;
+
+	/*
+	 * Boundary checking aginst the kernel image mapping.
+	 * __pa_symbol should only be used on kernel symbol addresses.
+	 */
+	VIRTUAL_BUG_ON(x < kernel_start || x > kernel_end);
+
+	return __va_to_pa_nodebug(x);
+}
+EXPORT_SYMBOL(__phys_addr_symbol);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 287714d51b47..8abe77536d9d 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -156,6 +156,7 @@ config S390
 	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
+	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
 	select HAVE_KVM
 	select HAVE_LIVEPATCH
@@ -163,13 +164,13 @@ config S390
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MEMBLOCK_PHYS_MAP
-	select HAVE_MMU_GATHER_NO_GATHER
+	select MMU_GATHER_NO_GATHER
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NOP_MCOUNT
 	select HAVE_OPROFILE
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
-	select HAVE_RCU_TABLE_FREE
+	select MMU_GATHER_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RSEQ
diff --git a/arch/s390/boot/compressed/decompressor.c b/arch/s390/boot/compressed/decompressor.c
index 45046630c56a..368fd372c875 100644
--- a/arch/s390/boot/compressed/decompressor.c
+++ b/arch/s390/boot/compressed/decompressor.c
@@ -30,13 +30,13 @@ extern unsigned char _compressed_start[];
 extern unsigned char _compressed_end[];
 
 #ifdef CONFIG_HAVE_KERNEL_BZIP2
-#define HEAP_SIZE	0x400000
+#define BOOT_HEAP_SIZE	0x400000
 #else
-#define HEAP_SIZE	0x10000
+#define BOOT_HEAP_SIZE	0x10000
 #endif
 
 static unsigned long free_mem_ptr = (unsigned long) _end;
-static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE;
+static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE;
 
 #ifdef CONFIG_KERNEL_GZIP
 #include "../../../../lib/decompress_inflate.c"
@@ -62,7 +62,7 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + HEAP_SIZE;
 #include "../../../../lib/decompress_unxz.c"
 #endif
 
-#define decompress_offset ALIGN((unsigned long)_end + HEAP_SIZE, PAGE_SIZE)
+#define decompress_offset ALIGN((unsigned long)_end + BOOT_HEAP_SIZE, PAGE_SIZE)
 
 unsigned long mem_safe_offset(void)
 {
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 24ef67eb1cef..357adad991d2 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -14,6 +14,7 @@
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
 struct ipl_parameter_block __bootdata_preserved(ipl_block);
 int __bootdata_preserved(ipl_block_valid);
+unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL;
 
 unsigned long __bootdata(vmalloc_size) = VMALLOC_DEFAULT_SIZE;
 unsigned long __bootdata(memory_end);
@@ -229,6 +230,19 @@ void parse_boot_command_line(void)
 		if (!strcmp(param, "vmalloc") && val)
 			vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE);
 
+		if (!strcmp(param, "dfltcc")) {
+			if (!strcmp(val, "off"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_DISABLED;
+			else if (!strcmp(val, "on"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_FULL;
+			else if (!strcmp(val, "def_only"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_DEFLATE_ONLY;
+			else if (!strcmp(val, "inf_only"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_INFLATE_ONLY;
+			else if (!strcmp(val, "always"))
+				zlib_dfltcc_support = ZLIB_DFLTCC_FULL_DEBUG;
+		}
+
 		if (!strcmp(param, "noexec")) {
 			rc = kstrtobool(val, &enabled);
 			if (!rc && !enabled)
diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c
index e2a85783f804..f3caeb17c85b 100644
--- a/arch/s390/crypto/paes_s390.c
+++ b/arch/s390/crypto/paes_s390.c
@@ -5,7 +5,7 @@
  * s390 implementation of the AES Cipher Algorithm with protected keys.
  *
  * s390 Version:
- *   Copyright IBM Corp. 2017,2019
+ *   Copyright IBM Corp. 2017,2020
  *   Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *		Harald Freudenberger <freude@de.ibm.com>
  */
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/cpufeature.h>
 #include <linux/init.h>
+#include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/xts.h>
@@ -32,11 +33,11 @@
  * is called. As paes can handle different kinds of key blobs
  * and padding is also possible, the limits need to be generous.
  */
-#define PAES_MIN_KEYSIZE 64
-#define PAES_MAX_KEYSIZE 256
+#define PAES_MIN_KEYSIZE 16
+#define PAES_MAX_KEYSIZE 320
 
 static u8 *ctrblk;
-static DEFINE_SPINLOCK(ctrblk_lock);
+static DEFINE_MUTEX(ctrblk_lock);
 
 static cpacf_mask_t km_functions, kmc_functions, kmctr_functions;
 
@@ -53,19 +54,46 @@ struct key_blob {
 	unsigned int keylen;
 };
 
-static inline int _copy_key_to_kb(struct key_blob *kb,
-				  const u8 *key,
-				  unsigned int keylen)
-{
-	if (keylen <= sizeof(kb->keybuf))
+static inline int _key_to_kb(struct key_blob *kb,
+			     const u8 *key,
+			     unsigned int keylen)
+{
+	struct clearkey_header {
+		u8  type;
+		u8  res0[3];
+		u8  version;
+		u8  res1[3];
+		u32 keytype;
+		u32 len;
+	} __packed * h;
+
+	switch (keylen) {
+	case 16:
+	case 24:
+	case 32:
+		/* clear key value, prepare pkey clear key token in keybuf */
+		memset(kb->keybuf, 0, sizeof(kb->keybuf));
+		h = (struct clearkey_header *) kb->keybuf;
+		h->version = 0x02; /* TOKVER_CLEAR_KEY */
+		h->keytype = (keylen - 8) >> 3;
+		h->len = keylen;
+		memcpy(kb->keybuf + sizeof(*h), key, keylen);
+		kb->keylen = sizeof(*h) + keylen;
 		kb->key = kb->keybuf;
-	else {
-		kb->key = kmalloc(keylen, GFP_KERNEL);
-		if (!kb->key)
-			return -ENOMEM;
+		break;
+	default:
+		/* other key material, let pkey handle this */
+		if (keylen <= sizeof(kb->keybuf))
+			kb->key = kb->keybuf;
+		else {
+			kb->key = kmalloc(keylen, GFP_KERNEL);
+			if (!kb->key)
+				return -ENOMEM;
+		}
+		memcpy(kb->key, key, keylen);
+		kb->keylen = keylen;
+		break;
 	}
-	memcpy(kb->key, key, keylen);
-	kb->keylen = keylen;
 
 	return 0;
 }
@@ -82,16 +110,18 @@ static inline void _free_kb_keybuf(struct key_blob *kb)
 struct s390_paes_ctx {
 	struct key_blob kb;
 	struct pkey_protkey pk;
+	spinlock_t pk_lock;
 	unsigned long fc;
 };
 
 struct s390_pxts_ctx {
 	struct key_blob kb[2];
 	struct pkey_protkey pk[2];
+	spinlock_t pk_lock;
 	unsigned long fc;
 };
 
-static inline int __paes_convert_key(struct key_blob *kb,
+static inline int __paes_keyblob2pkey(struct key_blob *kb,
 				     struct pkey_protkey *pk)
 {
 	int i, ret;
@@ -106,22 +136,18 @@ static inline int __paes_convert_key(struct key_blob *kb,
 	return ret;
 }
 
-static int __paes_set_key(struct s390_paes_ctx *ctx)
+static inline int __paes_convert_key(struct s390_paes_ctx *ctx)
 {
-	unsigned long fc;
+	struct pkey_protkey pkey;
 
-	if (__paes_convert_key(&ctx->kb, &ctx->pk))
+	if (__paes_keyblob2pkey(&ctx->kb, &pkey))
 		return -EINVAL;
 
-	/* Pick the correct function code based on the protected key type */
-	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KM_PAES_128 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KM_PAES_192 :
-		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ? CPACF_KM_PAES_256 : 0;
-
-	/* Check if the function code is available */
-	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
+	spin_lock_bh(&ctx->pk_lock);
+	memcpy(&ctx->pk, &pkey, sizeof(pkey));
+	spin_unlock_bh(&ctx->pk_lock);
 
-	return ctx->fc ? 0 : -EINVAL;
+	return 0;
 }
 
 static int ecb_paes_init(struct crypto_skcipher *tfm)
@@ -129,6 +155,7 @@ static int ecb_paes_init(struct crypto_skcipher *tfm)
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb.key = NULL;
+	spin_lock_init(&ctx->pk_lock);
 
 	return 0;
 }
@@ -140,6 +167,24 @@ static void ecb_paes_exit(struct crypto_skcipher *tfm)
 	_free_kb_keybuf(&ctx->kb);
 }
 
+static inline int __ecb_paes_set_key(struct s390_paes_ctx *ctx)
+{
+	unsigned long fc;
+
+	if (__paes_convert_key(ctx))
+		return -EINVAL;
+
+	/* Pick the correct function code based on the protected key type */
+	fc = (ctx->pk.type == PKEY_KEYTYPE_AES_128) ? CPACF_KM_PAES_128 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_192) ? CPACF_KM_PAES_192 :
+		(ctx->pk.type == PKEY_KEYTYPE_AES_256) ? CPACF_KM_PAES_256 : 0;
+
+	/* Check if the function code is available */
+	ctx->fc = (fc && cpacf_test_func(&km_functions, fc)) ? fc : 0;
+
+	return ctx->fc ? 0 : -EINVAL;
+}
+
 static int ecb_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 			    unsigned int key_len)
 {
@@ -147,11 +192,11 @@ static int ecb_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
-	rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
+	rc = _key_to_kb(&ctx->kb, in_key, key_len);
 	if (rc)
 		return rc;
 
-	return __paes_set_key(ctx);
+	return __ecb_paes_set_key(ctx);
 }
 
 static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier)
@@ -161,18 +206,31 @@ static int ecb_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 	struct skcipher_walk walk;
 	unsigned int nbytes, n, k;
 	int ret;
+	struct {
+		u8 key[MAXPROTKEYSIZE];
+	} param;
 
 	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
+
+	spin_lock_bh(&ctx->pk_lock);
+	memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+	spin_unlock_bh(&ctx->pk_lock);
+
 	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
-		k = cpacf_km(ctx->fc | modifier, ctx->pk.protkey,
+		k = cpacf_km(ctx->fc | modifier, &param,
 			     walk.dst.virt.addr, walk.src.virt.addr, n);
 		if (k)
 			ret = skcipher_walk_done(&walk, nbytes - k);
 		if (k < n) {
-			if (__paes_set_key(ctx) != 0)
+			if (__paes_convert_key(ctx))
 				return skcipher_walk_done(&walk, -EIO);
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
 	return ret;
@@ -210,6 +268,7 @@ static int cbc_paes_init(struct crypto_skcipher *tfm)
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb.key = NULL;
+	spin_lock_init(&ctx->pk_lock);
 
 	return 0;
 }
@@ -221,11 +280,11 @@ static void cbc_paes_exit(struct crypto_skcipher *tfm)
 	_free_kb_keybuf(&ctx->kb);
 }
 
-static int __cbc_paes_set_key(struct s390_paes_ctx *ctx)
+static inline int __cbc_paes_set_key(struct s390_paes_ctx *ctx)
 {
 	unsigned long fc;
 
-	if (__paes_convert_key(&ctx->kb, &ctx->pk))
+	if (__paes_convert_key(ctx))
 		return -EINVAL;
 
 	/* Pick the correct function code based on the protected key type */
@@ -246,7 +305,7 @@ static int cbc_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
-	rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
+	rc = _key_to_kb(&ctx->kb, in_key, key_len);
 	if (rc)
 		return rc;
 
@@ -268,8 +327,12 @@ static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 	ret = skcipher_walk_virt(&walk, req, false);
 	if (ret)
 		return ret;
+
 	memcpy(param.iv, walk.iv, AES_BLOCK_SIZE);
+	spin_lock_bh(&ctx->pk_lock);
 	memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+	spin_unlock_bh(&ctx->pk_lock);
+
 	while ((nbytes = walk.nbytes) != 0) {
 		/* only use complete blocks */
 		n = nbytes & ~(AES_BLOCK_SIZE - 1);
@@ -280,9 +343,11 @@ static int cbc_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 			ret = skcipher_walk_done(&walk, nbytes - k);
 		}
 		if (k < n) {
-			if (__cbc_paes_set_key(ctx) != 0)
+			if (__paes_convert_key(ctx))
 				return skcipher_walk_done(&walk, -EIO);
+			spin_lock_bh(&ctx->pk_lock);
 			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
 	return ret;
@@ -322,6 +387,7 @@ static int xts_paes_init(struct crypto_skcipher *tfm)
 
 	ctx->kb[0].key = NULL;
 	ctx->kb[1].key = NULL;
+	spin_lock_init(&ctx->pk_lock);
 
 	return 0;
 }
@@ -334,12 +400,27 @@ static void xts_paes_exit(struct crypto_skcipher *tfm)
 	_free_kb_keybuf(&ctx->kb[1]);
 }
 
-static int __xts_paes_set_key(struct s390_pxts_ctx *ctx)
+static inline int __xts_paes_convert_key(struct s390_pxts_ctx *ctx)
+{
+	struct pkey_protkey pkey0, pkey1;
+
+	if (__paes_keyblob2pkey(&ctx->kb[0], &pkey0) ||
+	    __paes_keyblob2pkey(&ctx->kb[1], &pkey1))
+		return -EINVAL;
+
+	spin_lock_bh(&ctx->pk_lock);
+	memcpy(&ctx->pk[0], &pkey0, sizeof(pkey0));
+	memcpy(&ctx->pk[1], &pkey1, sizeof(pkey1));
+	spin_unlock_bh(&ctx->pk_lock);
+
+	return 0;
+}
+
+static inline int __xts_paes_set_key(struct s390_pxts_ctx *ctx)
 {
 	unsigned long fc;
 
-	if (__paes_convert_key(&ctx->kb[0], &ctx->pk[0]) ||
-	    __paes_convert_key(&ctx->kb[1], &ctx->pk[1]))
+	if (__xts_paes_convert_key(ctx))
 		return -EINVAL;
 
 	if (ctx->pk[0].type != ctx->pk[1].type)
@@ -371,10 +452,10 @@ static int xts_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 
 	_free_kb_keybuf(&ctx->kb[0]);
 	_free_kb_keybuf(&ctx->kb[1]);
-	rc = _copy_key_to_kb(&ctx->kb[0], in_key, key_len);
+	rc = _key_to_kb(&ctx->kb[0], in_key, key_len);
 	if (rc)
 		return rc;
-	rc = _copy_key_to_kb(&ctx->kb[1], in_key + key_len, key_len);
+	rc = _key_to_kb(&ctx->kb[1], in_key + key_len, key_len);
 	if (rc)
 		return rc;
 
@@ -416,15 +497,17 @@ static int xts_paes_crypt(struct skcipher_request *req, unsigned long modifier)
 	ret = skcipher_walk_virt(&walk, req, false);
 	if (ret)
 		return ret;
+
 	keylen = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 48 : 64;
 	offset = (ctx->pk[0].type == PKEY_KEYTYPE_AES_128) ? 16 : 0;
-retry:
+
 	memset(&pcc_param, 0, sizeof(pcc_param));
 	memcpy(pcc_param.tweak, walk.iv, sizeof(pcc_param.tweak));
+	spin_lock_bh(&ctx->pk_lock);
 	memcpy(pcc_param.key + offset, ctx->pk[1].protkey, keylen);
-	cpacf_pcc(ctx->fc, pcc_param.key + offset);
-
 	memcpy(xts_param.key + offset, ctx->pk[0].protkey, keylen);
+	spin_unlock_bh(&ctx->pk_lock);
+	cpacf_pcc(ctx->fc, pcc_param.key + offset);
 	memcpy(xts_param.init, pcc_param.xts, 16);
 
 	while ((nbytes = walk.nbytes) != 0) {
@@ -435,11 +518,15 @@ retry:
 		if (k)
 			ret = skcipher_walk_done(&walk, nbytes - k);
 		if (k < n) {
-			if (__xts_paes_set_key(ctx) != 0)
+			if (__xts_paes_convert_key(ctx))
 				return skcipher_walk_done(&walk, -EIO);
-			goto retry;
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(xts_param.key + offset,
+			       ctx->pk[0].protkey, keylen);
+			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
+
 	return ret;
 }
 
@@ -476,6 +563,7 @@ static int ctr_paes_init(struct crypto_skcipher *tfm)
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	ctx->kb.key = NULL;
+	spin_lock_init(&ctx->pk_lock);
 
 	return 0;
 }
@@ -487,11 +575,11 @@ static void ctr_paes_exit(struct crypto_skcipher *tfm)
 	_free_kb_keybuf(&ctx->kb);
 }
 
-static int __ctr_paes_set_key(struct s390_paes_ctx *ctx)
+static inline int __ctr_paes_set_key(struct s390_paes_ctx *ctx)
 {
 	unsigned long fc;
 
-	if (__paes_convert_key(&ctx->kb, &ctx->pk))
+	if (__paes_convert_key(ctx))
 		return -EINVAL;
 
 	/* Pick the correct function code based on the protected key type */
@@ -513,7 +601,7 @@ static int ctr_paes_set_key(struct crypto_skcipher *tfm, const u8 *in_key,
 	struct s390_paes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
 	_free_kb_keybuf(&ctx->kb);
-	rc = _copy_key_to_kb(&ctx->kb, in_key, key_len);
+	rc = _key_to_kb(&ctx->kb, in_key, key_len);
 	if (rc)
 		return rc;
 
@@ -543,49 +631,65 @@ static int ctr_paes_crypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	unsigned int nbytes, n, k;
 	int ret, locked;
-
-	locked = spin_trylock(&ctrblk_lock);
+	struct {
+		u8 key[MAXPROTKEYSIZE];
+	} param;
 
 	ret = skcipher_walk_virt(&walk, req, false);
+	if (ret)
+		return ret;
+
+	spin_lock_bh(&ctx->pk_lock);
+	memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+	spin_unlock_bh(&ctx->pk_lock);
+
+	locked = mutex_trylock(&ctrblk_lock);
+
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
 		n = AES_BLOCK_SIZE;
 		if (nbytes >= 2*AES_BLOCK_SIZE && locked)
 			n = __ctrblk_init(ctrblk, walk.iv, nbytes);
 		ctrptr = (n > AES_BLOCK_SIZE) ? ctrblk : walk.iv;
-		k = cpacf_kmctr(ctx->fc, ctx->pk.protkey, walk.dst.virt.addr,
+		k = cpacf_kmctr(ctx->fc, &param, walk.dst.virt.addr,
 				walk.src.virt.addr, n, ctrptr);
 		if (k) {
 			if (ctrptr == ctrblk)
 				memcpy(walk.iv, ctrptr + k - AES_BLOCK_SIZE,
 				       AES_BLOCK_SIZE);
 			crypto_inc(walk.iv, AES_BLOCK_SIZE);
-			ret = skcipher_walk_done(&walk, nbytes - n);
+			ret = skcipher_walk_done(&walk, nbytes - k);
 		}
 		if (k < n) {
-			if (__ctr_paes_set_key(ctx) != 0) {
+			if (__paes_convert_key(ctx)) {
 				if (locked)
-					spin_unlock(&ctrblk_lock);
+					mutex_unlock(&ctrblk_lock);
 				return skcipher_walk_done(&walk, -EIO);
 			}
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+			spin_unlock_bh(&ctx->pk_lock);
 		}
 	}
 	if (locked)
-		spin_unlock(&ctrblk_lock);
+		mutex_unlock(&ctrblk_lock);
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
 	 */
 	if (nbytes) {
 		while (1) {
-			if (cpacf_kmctr(ctx->fc, ctx->pk.protkey, buf,
+			if (cpacf_kmctr(ctx->fc, &param, buf,
 					walk.src.virt.addr, AES_BLOCK_SIZE,
 					walk.iv) == AES_BLOCK_SIZE)
 				break;
-			if (__ctr_paes_set_key(ctx) != 0)
+			if (__paes_convert_key(ctx))
 				return skcipher_walk_done(&walk, -EIO);
+			spin_lock_bh(&ctx->pk_lock);
+			memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE);
+			spin_unlock_bh(&ctx->pk_lock);
 		}
 		memcpy(walk.dst.virt.addr, buf, nbytes);
 		crypto_inc(walk.iv, AES_BLOCK_SIZE);
-		ret = skcipher_walk_done(&walk, 0);
+		ret = skcipher_walk_done(&walk, nbytes);
 	}
 
 	return ret;
@@ -618,12 +722,12 @@ static inline void __crypto_unregister_skcipher(struct skcipher_alg *alg)
 
 static void paes_s390_fini(void)
 {
-	if (ctrblk)
-		free_page((unsigned long) ctrblk);
 	__crypto_unregister_skcipher(&ctr_paes_alg);
 	__crypto_unregister_skcipher(&xts_paes_alg);
 	__crypto_unregister_skcipher(&cbc_paes_alg);
 	__crypto_unregister_skcipher(&ecb_paes_alg);
+	if (ctrblk)
+		free_page((unsigned long) ctrblk);
 }
 
 static int __init paes_s390_init(void)
@@ -661,14 +765,14 @@ static int __init paes_s390_init(void)
 	if (cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_128) ||
 	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_192) ||
 	    cpacf_test_func(&kmctr_functions, CPACF_KMCTR_PAES_256)) {
-		ret = crypto_register_skcipher(&ctr_paes_alg);
-		if (ret)
-			goto out_err;
 		ctrblk = (u8 *) __get_free_page(GFP_KERNEL);
 		if (!ctrblk) {
 			ret = -ENOMEM;
 			goto out_err;
 		}
+		ret = crypto_register_skcipher(&ctr_paes_alg);
+		if (ret)
+			goto out_err;
 	}
 
 	return 0;
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 2531f673f099..1832ae6442ef 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -7,7 +7,6 @@ generated-y += unistd_nr.h
 generic-y += asm-offsets.h
 generic-y += cacheflush.h
 generic-y += device.h
-generic-y += dma-contiguous.h
 generic-y += dma-mapping.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index c67b82dfa558..de61ce562052 100644
--- a/arch/s390/include/asm/archrandom.h
+++ b/arch/s390/include/asm/archrandom.h
@@ -21,29 +21,17 @@ extern atomic64_t s390_arch_random_counter;
 
 bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
 
-static inline bool arch_has_random(void)
+static inline bool __must_check arch_get_random_long(unsigned long *v)
 {
 	return false;
 }
 
-static inline bool arch_has_random_seed(void)
+static inline bool __must_check arch_get_random_int(unsigned int *v)
 {
-	if (static_branch_likely(&s390_arch_random_available))
-		return true;
 	return false;
 }
 
-static inline bool arch_get_random_long(unsigned long *v)
-{
-	return false;
-}
-
-static inline bool arch_get_random_int(unsigned int *v)
-{
-	return false;
-}
-
-static inline bool arch_get_random_seed_long(unsigned long *v)
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
 		return s390_arch_random_generate((u8 *)v, sizeof(*v));
@@ -51,7 +39,7 @@ static inline bool arch_get_random_seed_long(unsigned long *v)
 	return false;
 }
 
-static inline bool arch_get_random_seed_int(unsigned int *v)
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
 		return s390_arch_random_generate((u8 *)v, sizeof(*v));
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 63b46e30b2c3..9547cd5d6cdc 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -177,11 +177,7 @@ static inline void __user *compat_ptr(compat_uptr_t uptr)
 {
 	return (void __user *)(unsigned long)(uptr & 0x7fffffffUL);
 }
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
+#define compat_ptr(uptr) compat_ptr(uptr)
 
 #ifdef CONFIG_COMPAT
 
diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index b106aa29bf55..09cdb632a490 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -54,7 +54,6 @@ typedef u16 kprobe_opcode_t;
 struct arch_specific_insn {
 	/* copy of original instruction */
 	kprobe_opcode_t *insn;
-	unsigned int is_ftrace_insn : 1;
 };
 
 struct prev_kprobe {
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 02f4c21c57f6..11ecc4071a29 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -914,7 +914,6 @@ extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc);
 
 static inline void kvm_arch_hardware_disable(void) {}
 static inline void kvm_arch_sync_events(struct kvm *kvm) {}
-static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
 static inline void kvm_arch_free_memslot(struct kvm *kvm,
 		struct kvm_memory_slot *free, struct kvm_memory_slot *dont) {}
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index a4d38092530a..85e944f04c70 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -33,6 +33,8 @@
 #define ARCH_HAS_PREPARE_HUGEPAGE
 #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
 
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+
 #include <asm/setup.h>
 #ifndef __ASSEMBLY__
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 7b03037a8475..137a3920ca36 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -673,6 +673,7 @@ static inline int pud_none(pud_t pud)
 	return pud_val(pud) == _REGION3_ENTRY_EMPTY;
 }
 
+#define pud_leaf	pud_large
 static inline int pud_large(pud_t pud)
 {
 	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) != _REGION_ENTRY_TYPE_R3)
@@ -690,6 +691,7 @@ static inline unsigned long pud_pfn(pud_t pud)
 	return (pud_val(pud) & origin_mask) >> PAGE_SHIFT;
 }
 
+#define pmd_leaf	pmd_large
 static inline int pmd_large(pmd_t pmd)
 {
 	return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0;
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 69289e99cabd..b241ddb67caf 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -79,6 +79,13 @@ struct parmarea {
 	char command_line[ARCH_COMMAND_LINE_SIZE];	/* 0x10480 */
 };
 
+extern unsigned int zlib_dfltcc_support;
+#define ZLIB_DFLTCC_DISABLED		0
+#define ZLIB_DFLTCC_FULL		1
+#define ZLIB_DFLTCC_DEFLATE_ONLY	2
+#define ZLIB_DFLTCC_INFLATE_ONLY	3
+#define ZLIB_DFLTCC_FULL_DEBUG		4
+
 extern int noexec_disabled;
 extern int memory_end_set;
 extern unsigned long memory_end;
diff --git a/arch/s390/include/uapi/asm/pkey.h b/arch/s390/include/uapi/asm/pkey.h
index e22f0720bbb8..d27d7d329263 100644
--- a/arch/s390/include/uapi/asm/pkey.h
+++ b/arch/s390/include/uapi/asm/pkey.h
@@ -25,10 +25,11 @@
 #define MAXPROTKEYSIZE	64	/* a protected key blob may be up to 64 bytes */
 #define MAXCLRKEYSIZE	32	   /* a clear key value may be up to 32 bytes */
 #define MAXAESCIPHERKEYSIZE 136  /* our aes cipher keys have always 136 bytes */
+#define MINEP11AESKEYBLOBSIZE 256  /* min EP11 AES key blob size  */
+#define MAXEP11AESKEYBLOBSIZE 320  /* max EP11 AES key blob size */
 
-/* Minimum and maximum size of a key blob */
+/* Minimum size of a key blob */
 #define MINKEYBLOBSIZE	SECKEYBLOBSIZE
-#define MAXKEYBLOBSIZE	MAXAESCIPHERKEYSIZE
 
 /* defines for the type field within the pkey_protkey struct */
 #define PKEY_KEYTYPE_AES_128		      1
@@ -39,6 +40,7 @@
 enum pkey_key_type {
 	PKEY_TYPE_CCA_DATA   = (__u32) 1,
 	PKEY_TYPE_CCA_CIPHER = (__u32) 2,
+	PKEY_TYPE_EP11	     = (__u32) 3,
 };
 
 /* the newer ioctls use a pkey_key_size enum for key size information */
@@ -200,7 +202,7 @@ struct pkey_kblob2pkey {
 
 /*
  * Generate secure key, version 2.
- * Generate either a CCA AES secure key or a CCA AES cipher key.
+ * Generate CCA AES secure key, CCA AES cipher key or EP11 AES secure key.
  * There needs to be a list of apqns given with at least one entry in there.
  * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
  * is not supported. The implementation walks through the list of apqns and
@@ -210,10 +212,13 @@ struct pkey_kblob2pkey {
  * (return -1 with errno ENODEV). You may use the PKEY_APQNS4KT ioctl to
  * generate a list of apqns based on the key type to generate.
  * The keygenflags argument is passed to the low level generation functions
- * individual for the key type and has a key type specific meaning. Currently
- * only CCA AES cipher keys react to this parameter: Use one or more of the
- * PKEY_KEYGEN_* flags to widen the export possibilities. By default a cipher
- * key is only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC).
+ * individual for the key type and has a key type specific meaning. When
+ * generating CCA cipher keys you can use one or more of the PKEY_KEYGEN_*
+ * flags to widen the export possibilities. By default a cipher key is
+ * only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC).
+ * The keygenflag argument for generating an EP11 AES key should either be 0
+ * to use the defaults which are XCP_BLOB_ENCRYPT, XCP_BLOB_DECRYPT and
+ * XCP_BLOB_PROTKEY_EXTRACTABLE or a valid combination of XCP_BLOB_* flags.
  */
 struct pkey_genseck2 {
 	struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets*/
@@ -229,8 +234,8 @@ struct pkey_genseck2 {
 
 /*
  * Generate secure key from clear key value, version 2.
- * Construct a CCA AES secure key or CCA AES cipher key from a given clear key
- * value.
+ * Construct an CCA AES secure key, CCA AES cipher key or EP11 AES secure
+ * key from a given clear key value.
  * There needs to be a list of apqns given with at least one entry in there.
  * All apqns in the list need to be exact apqns, 0xFFFF as ANY card or domain
  * is not supported. The implementation walks through the list of apqns and
@@ -240,10 +245,13 @@ struct pkey_genseck2 {
  * (return -1 with errno ENODEV). You may use the PKEY_APQNS4KT ioctl to
  * generate a list of apqns based on the key type to generate.
  * The keygenflags argument is passed to the low level generation functions
- * individual for the key type and has a key type specific meaning. Currently
- * only CCA AES cipher keys react to this parameter: Use one or more of the
- * PKEY_KEYGEN_* flags to widen the export possibilities. By default a cipher
- * key is only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC).
+ * individual for the key type and has a key type specific meaning. When
+ * generating CCA cipher keys you can use one or more of the PKEY_KEYGEN_*
+ * flags to widen the export possibilities. By default a cipher key is
+ * only exportable for CPACF (PKEY_KEYGEN_XPRT_CPAC).
+ * The keygenflag argument for generating an EP11 AES key should either be 0
+ * to use the defaults which are XCP_BLOB_ENCRYPT, XCP_BLOB_DECRYPT and
+ * XCP_BLOB_PROTKEY_EXTRACTABLE or a valid combination of XCP_BLOB_* flags.
  */
 struct pkey_clr2seck2 {
 	struct pkey_apqn __user *apqns; /* in: ptr to list of apqn targets */
@@ -266,14 +274,19 @@ struct pkey_clr2seck2 {
  * with one apqn able to handle this key.
  * The function also checks for the master key verification patterns
  * of the key matching to the current or alternate mkvp of the apqn.
- * Currently CCA AES secure keys and CCA AES cipher keys are supported.
- * The flags field is updated with some additional info about the apqn mkvp
+ * For CCA AES secure keys and CCA AES cipher keys this means to check
+ * the key's mkvp against the current or old mkvp of the apqns. The flags
+ * field is updated with some additional info about the apqn mkvp
  * match: If the current mkvp matches to the key's mkvp then the
  * PKEY_FLAGS_MATCH_CUR_MKVP bit is set, if the alternate mkvp matches to
  * the key's mkvp the PKEY_FLAGS_MATCH_ALT_MKVP is set. For CCA keys the
  * alternate mkvp is the old master key verification pattern.
  * CCA AES secure keys are also checked to have the CPACF export allowed
  * bit enabled (XPRTCPAC) in the kmf1 field.
+ * EP11 keys are also supported and the wkvp of the key is checked against
+ * the current wkvp of the apqns. There is no alternate for this type of
+ * key and so on a match the flag PKEY_FLAGS_MATCH_CUR_MKVP always is set.
+ * EP11 keys are also checked to have XCP_BLOB_PROTKEY_EXTRACTABLE set.
  * The ioctl returns 0 as long as the given or found apqn matches to
  * matches with the current or alternate mkvp to the key's mkvp. If the given
  * apqn does not match or there is no such apqn found, -1 with errno
@@ -313,16 +326,20 @@ struct pkey_kblob2pkey2 {
 /*
  * Build a list of APQNs based on a key blob given.
  * Is able to find out which type of secure key is given (CCA AES secure
- * key or CCA AES cipher key) and tries to find all matching crypto cards
- * based on the MKVP and maybe other criterias (like CCA AES cipher keys
- * need a CEX5C or higher). The list of APQNs is further filtered by the key's
- * mkvp which needs to match to either the current mkvp or the alternate mkvp
- * (which is the old mkvp on CCA adapters) of the apqns. The flags argument may
- * be used to limit the matching apqns. If the PKEY_FLAGS_MATCH_CUR_MKVP is
- * given, only the current mkvp of each apqn is compared. Likewise with the
- * PKEY_FLAGS_MATCH_ALT_MKVP. If both are given, it is assumed to
- * return apqns where either the current or the alternate mkvp
+ * key, CCA AES cipher key or EP11 AES key) and tries to find all matching
+ * crypto cards based on the MKVP and maybe other criterias (like CCA AES
+ * cipher keys need a CEX5C or higher, EP11 keys with BLOB_PKEY_EXTRACTABLE
+ * need a CEX7 and EP11 api version 4). The list of APQNs is further filtered
+ * by the key's mkvp which needs to match to either the current mkvp (CCA and
+ * EP11) or the alternate mkvp (old mkvp, CCA adapters only) of the apqns. The
+ * flags argument may be used to limit the matching apqns. If the
+ * PKEY_FLAGS_MATCH_CUR_MKVP is given, only the current mkvp of each apqn is
+ * compared. Likewise with the PKEY_FLAGS_MATCH_ALT_MKVP. If both are given, it
+ * is assumed to return apqns where either the current or the alternate mkvp
  * matches. At least one of the matching flags needs to be given.
+ * The flags argument for EP11 keys has no further action and is currently
+ * ignored (but needs to be given as PKEY_FLAGS_MATCH_CUR_MKVP) as there is only
+ * the wkvp from the key to match against the apqn's wkvp.
  * The list of matching apqns is stored into the space given by the apqns
  * argument and the number of stored entries goes into apqn_entries. If the list
  * is empty (apqn_entries is 0) the apqn_entries field is updated to the number
@@ -356,6 +373,10 @@ struct pkey_apqns4key {
  * If both are given, it is assumed to return apqns where either the
  * current or the alternate mkvp matches. If no match flag is given
  * (flags is 0) the mkvp values are ignored for the match process.
+ * For EP11 keys there is only the current wkvp. So if the apqns should also
+ * match to a given wkvp, then the PKEY_FLAGS_MATCH_CUR_MKVP flag should be
+ * set. The wkvp value is 32 bytes but only the leftmost 16 bytes are compared
+ * against the leftmost 16 byte of the wkvp of the apqn.
  * The list of matching apqns is stored into the space given by the apqns
  * argument and the number of stored entries goes into apqn_entries. If the list
  * is empty (apqn_entries is 0) the apqn_entries field is updated to the number
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index f9e5e1f0821d..5a2177e96e88 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -161,17 +161,17 @@ struct ica_xcRB {
  * @payload_len:	Payload length
  */
 struct ep11_cprb {
-	__u16		cprb_len;
-	unsigned char	cprb_ver_id;
-	unsigned char	pad_000[2];
-	unsigned char	flags;
-	unsigned char	func_id[2];
-	__u32		source_id;
-	__u32		target_id;
-	__u32		ret_code;
-	__u32		reserved1;
-	__u32		reserved2;
-	__u32		payload_len;
+	__u16	cprb_len;
+	__u8	cprb_ver_id;
+	__u8	pad_000[2];
+	__u8	flags;
+	__u8	func_id[2];
+	__u32	source_id;
+	__u32	target_id;
+	__u32	ret_code;
+	__u32	reserved1;
+	__u32	reserved2;
+	__u32	payload_len;
 } __attribute__((packed));
 
 /**
@@ -197,13 +197,13 @@ struct ep11_target_dev {
  */
 struct ep11_urb {
 	__u16		targets_num;
-	__u64		targets;
+	__u8 __user    *targets;
 	__u64		weight;
 	__u64		req_no;
 	__u64		req_len;
-	__u64		req;
+	__u8 __user    *req;
 	__u64		resp_len;
-	__u64		resp;
+	__u8 __user    *resp;
 } __attribute__((packed));
 
 /**
@@ -237,7 +237,9 @@ struct zcrypt_device_matrix_ext {
 	struct zcrypt_device_status_ext device[MAX_ZDEV_ENTRIES_EXT];
 };
 
-#define AUTOSELECT 0xFFFFFFFF
+#define AUTOSELECT  0xFFFFFFFF
+#define AUTOSEL_AP  ((__u16) 0xFFFF)
+#define AUTOSEL_DOM ((__u16) 0xFFFF)
 
 #define ZCRYPT_IOCTL_MAGIC 'z'
 
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1bb85f60c0dd..4cd9b1ada834 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -72,15 +72,6 @@ static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
 #endif
 }
 
-static inline int is_kprobe_on_ftrace(struct ftrace_insn *insn)
-{
-#ifdef CONFIG_KPROBES
-	if (insn->opc == BREAKPOINT_INSTRUCTION)
-		return 1;
-#endif
-	return 0;
-}
-
 static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn)
 {
 #ifdef CONFIG_KPROBES
@@ -114,16 +105,6 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
 		/* Initial code replacement */
 		ftrace_generate_orig_insn(&orig);
 		ftrace_generate_nop_insn(&new);
-	} else if (is_kprobe_on_ftrace(&old)) {
-		/*
-		 * If we find a breakpoint instruction, a kprobe has been
-		 * placed at the beginning of the function. We write the
-		 * constant KPROBE_ON_FTRACE_NOP into the remaining four
-		 * bytes of the original instruction so that the kprobes
-		 * handler can execute a nop, if it reaches this breakpoint.
-		 */
-		ftrace_generate_kprobe_call_insn(&orig);
-		ftrace_generate_kprobe_nop_insn(&new);
 	} else {
 		/* Replace ftrace call with a nop. */
 		ftrace_generate_call_insn(&orig, rec->ip);
@@ -142,21 +123,10 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
 		return -EFAULT;
-	if (is_kprobe_on_ftrace(&old)) {
-		/*
-		 * If we find a breakpoint instruction, a kprobe has been
-		 * placed at the beginning of the function. We write the
-		 * constant KPROBE_ON_FTRACE_CALL into the remaining four
-		 * bytes of the original instruction so that the kprobes
-		 * handler can execute a brasl if it reaches this breakpoint.
-		 */
-		ftrace_generate_kprobe_nop_insn(&orig);
-		ftrace_generate_kprobe_call_insn(&new);
-	} else {
-		/* Replace nop with an ftrace call. */
-		ftrace_generate_nop_insn(&orig);
-		ftrace_generate_call_insn(&new, rec->ip);
-	}
+	/* Replace nop with an ftrace call. */
+	ftrace_generate_nop_insn(&orig);
+	ftrace_generate_call_insn(&new, rec->ip);
+
 	/* Verify that the to be replaced code matches what we expect. */
 	if (memcmp(&orig, &old, sizeof(old)))
 		return -EINVAL;
@@ -241,3 +211,45 @@ int ftrace_disable_ftrace_graph_caller(void)
 }
 
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_KPROBES_ON_FTRACE
+void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+		struct ftrace_ops *ops, struct pt_regs *regs)
+{
+	struct kprobe_ctlblk *kcb;
+	struct kprobe *p = get_kprobe((kprobe_opcode_t *)ip);
+
+	if (unlikely(!p) || kprobe_disabled(p))
+		return;
+
+	if (kprobe_running()) {
+		kprobes_inc_nmissed_count(p);
+		return;
+	}
+
+	__this_cpu_write(current_kprobe, p);
+
+	kcb = get_kprobe_ctlblk();
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+	instruction_pointer_set(regs, ip);
+
+	if (!p->pre_handler || !p->pre_handler(p, regs)) {
+
+		instruction_pointer_set(regs, ip + MCOUNT_INSN_SIZE);
+
+		if (unlikely(p->post_handler)) {
+			kcb->kprobe_status = KPROBE_HIT_SSDONE;
+			p->post_handler(p, regs, 0);
+		}
+	}
+	__this_cpu_write(current_kprobe, NULL);
+}
+NOKPROBE_SYMBOL(kprobe_ftrace_handler);
+
+int arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+	p->ainsn.insn = NULL;
+	return 0;
+}
+#endif
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 6f1388391620..548d0ea9808d 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -56,21 +56,10 @@ struct kprobe_insn_cache kprobe_s390_insn_slots = {
 
 static void copy_instruction(struct kprobe *p)
 {
-	unsigned long ip = (unsigned long) p->addr;
 	s64 disp, new_disp;
 	u64 addr, new_addr;
 
-	if (ftrace_location(ip) == ip) {
-		/*
-		 * If kprobes patches the instruction that is morphed by
-		 * ftrace make sure that kprobes always sees the branch
-		 * "jg .+24" that skips the mcount block or the "brcl 0,0"
-		 * in case of hotpatch.
-		 */
-		ftrace_generate_nop_insn((struct ftrace_insn *)p->ainsn.insn);
-		p->ainsn.is_ftrace_insn = 1;
-	} else
-		memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8));
+	memcpy(p->ainsn.insn, p->addr, insn_length(*p->addr >> 8));
 	p->opcode = p->ainsn.insn[0];
 	if (!probe_is_insn_relative_long(p->ainsn.insn))
 		return;
@@ -136,11 +125,6 @@ int arch_prepare_kprobe(struct kprobe *p)
 }
 NOKPROBE_SYMBOL(arch_prepare_kprobe);
 
-int arch_check_ftrace_location(struct kprobe *p)
-{
-	return 0;
-}
-
 struct swap_insn_args {
 	struct kprobe *p;
 	unsigned int arm_kprobe : 1;
@@ -149,28 +133,11 @@ struct swap_insn_args {
 static int swap_instruction(void *data)
 {
 	struct swap_insn_args *args = data;
-	struct ftrace_insn new_insn, *insn;
 	struct kprobe *p = args->p;
-	size_t len;
-
-	new_insn.opc = args->arm_kprobe ? BREAKPOINT_INSTRUCTION : p->opcode;
-	len = sizeof(new_insn.opc);
-	if (!p->ainsn.is_ftrace_insn)
-		goto skip_ftrace;
-	len = sizeof(new_insn);
-	insn = (struct ftrace_insn *) p->addr;
-	if (args->arm_kprobe) {
-		if (is_ftrace_nop(insn))
-			new_insn.disp = KPROBE_ON_FTRACE_NOP;
-		else
-			new_insn.disp = KPROBE_ON_FTRACE_CALL;
-	} else {
-		ftrace_generate_call_insn(&new_insn, (unsigned long)p->addr);
-		if (insn->disp == KPROBE_ON_FTRACE_NOP)
-			ftrace_generate_nop_insn(&new_insn);
-	}
-skip_ftrace:
-	s390_kernel_write(p->addr, &new_insn, len);
+	u16 opc;
+
+	opc = args->arm_kprobe ? BREAKPOINT_INSTRUCTION : p->opcode;
+	s390_kernel_write(p->addr, &opc, sizeof(opc));
 	return 0;
 }
 NOKPROBE_SYMBOL(swap_instruction);
@@ -464,24 +431,6 @@ static void resume_execution(struct kprobe *p, struct pt_regs *regs)
 	unsigned long ip = regs->psw.addr;
 	int fixup = probe_get_fixup_type(p->ainsn.insn);
 
-	/* Check if the kprobes location is an enabled ftrace caller */
-	if (p->ainsn.is_ftrace_insn) {
-		struct ftrace_insn *insn = (struct ftrace_insn *) p->addr;
-		struct ftrace_insn call_insn;
-
-		ftrace_generate_call_insn(&call_insn, (unsigned long) p->addr);
-		/*
-		 * A kprobe on an enabled ftrace call site actually single
-		 * stepped an unconditional branch (ftrace nop equivalent).
-		 * Now we need to fixup things and pretend that a brasl r0,...
-		 * was executed instead.
-		 */
-		if (insn->disp == KPROBE_ON_FTRACE_CALL) {
-			ip += call_insn.disp * 2 - MCOUNT_INSN_SIZE;
-			regs->gprs[0] = (unsigned long)p->addr + sizeof(*insn);
-		}
-	}
-
 	if (fixup & FIXUP_PSW_NORMAL)
 		ip += (unsigned long) p->addr - (unsigned long) p->ainsn.insn;
 
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index f942341429b1..7458dcfd6464 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -42,6 +42,9 @@ ENTRY(ftrace_caller)
 	.globl	ftrace_regs_caller
 	.set	ftrace_regs_caller,ftrace_caller
 	stg	%r14,(__SF_GPRS+8*8)(%r15)	# save traced function caller
+	lghi	%r14,0				# save condition code
+	ipm	%r14				# don't put any instructions
+	sllg	%r14,%r14,16			# clobbering CC before this point
 	lgr	%r1,%r15
 #if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT))
 	aghi	%r0,MCOUNT_RETURN_FIXUP
@@ -54,6 +57,9 @@ ENTRY(ftrace_caller)
 	# allocate pt_regs and stack frame for ftrace_trace_function
 	aghi	%r15,-STACK_FRAME_SIZE
 	stg	%r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+	stg	%r14,(STACK_PTREGS_PSW)(%r15)
+	lg	%r14,(__SF_GPRS+8*8)(%r1)	# restore original return address
+	stosm	(STACK_PTREGS_PSW)(%r15),0
 	aghi	%r1,-TRACED_FUNC_FRAME_SIZE
 	stg	%r1,__SF_BACKCHAIN(%r15)
 	stg	%r0,(STACK_PTREGS_PSW+8)(%r15)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 87a467dff5eb..b2c2f75860e8 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -111,6 +111,8 @@ unsigned long __bootdata_preserved(__etext_dma);
 unsigned long __bootdata_preserved(__sdma);
 unsigned long __bootdata_preserved(__edma);
 unsigned long __bootdata_preserved(__kaslr_offset);
+unsigned int __bootdata_preserved(zlib_dfltcc_support);
+EXPORT_SYMBOL(zlib_dfltcc_support);
 
 unsigned long VMALLOC_START;
 EXPORT_SYMBOL(VMALLOC_START);
@@ -759,14 +761,6 @@ static void __init free_mem_detect_info(void)
 		memblock_free(start, size);
 }
 
-static void __init memblock_physmem_add(phys_addr_t start, phys_addr_t size)
-{
-	memblock_dbg("memblock_physmem_add: [%#016llx-%#016llx]\n",
-		     start, start + size - 1);
-	memblock_add_range(&memblock.memory, start, size, 0, 0);
-	memblock_add_range(&memblock.physmem, start, size, 0, 0);
-}
-
 static const char * __init get_mem_info_source(void)
 {
 	switch (mem_detect.info_source) {
@@ -791,8 +785,10 @@ static void __init memblock_add_mem_detect_info(void)
 		     get_mem_info_source(), mem_detect.info_source);
 	/* keep memblock lists close to the kernel */
 	memblock_set_bottom_up(true);
-	for_each_mem_detect_block(i, &start, &end)
+	for_each_mem_detect_block(i, &start, &end) {
+		memblock_add(start, end - start);
 		memblock_physmem_add(start, end - start);
+	}
 	memblock_set_bottom_up(false);
 	memblock_dump_all();
 }
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 16b571c06161..bd7bd3581a0f 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
 434  common	pidfd_open		sys_pidfd_open			sys_pidfd_open
 435  common	clone3			sys_clone3			sys_clone3
 437  common	openat2			sys_openat2			sys_openat2
+438  common	pidfd_getfd		sys_pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d9e6bf3d54f0..8646c99217f2 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2530,9 +2530,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
 	free_page((unsigned long)(vcpu->arch.sie_block));
-
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static void kvm_free_vcpus(struct kvm *kvm)
@@ -2541,7 +2538,7 @@ static void kvm_free_vcpus(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arch_vcpu_destroy(vcpu);
+		kvm_vcpu_destroy(vcpu);
 
 	mutex_lock(&kvm->lock);
 	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
@@ -2703,39 +2700,6 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
 	return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
 }
 
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
-	kvm_clear_async_pf_completion_queue(vcpu);
-	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
-				    KVM_SYNC_GPRS |
-				    KVM_SYNC_ACRS |
-				    KVM_SYNC_CRS |
-				    KVM_SYNC_ARCH0 |
-				    KVM_SYNC_PFAULT;
-	kvm_s390_set_prefix(vcpu, 0);
-	if (test_kvm_facility(vcpu->kvm, 64))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
-	if (test_kvm_facility(vcpu->kvm, 82))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
-	if (test_kvm_facility(vcpu->kvm, 133))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
-	if (test_kvm_facility(vcpu->kvm, 156))
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN;
-	/* fprs can be synchronized via vrs, even if the guest has no vx. With
-	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
-	 */
-	if (MACHINE_HAS_VX)
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
-	else
-		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
-
-	if (kvm_is_ucontrol(vcpu->kvm))
-		return __kvm_ucontrol_vcpu_init(vcpu);
-
-	return 0;
-}
-
 /* needs disabled preemption to protect from TOD sync and vcpu_load/put */
 static void __start_cpu_timer_accounting(struct kvm_vcpu *vcpu)
 {
@@ -2962,7 +2926,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
 }
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
 
@@ -3035,26 +2999,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
-				      unsigned int id)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 {
-	struct kvm_vcpu *vcpu;
-	struct sie_page *sie_page;
-	int rc = -EINVAL;
-
 	if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
-		goto out;
-
-	rc = -ENOMEM;
+		return -EINVAL;
+	return 0;
+}
 
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu)
-		goto out;
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	struct sie_page *sie_page;
+	int rc;
 
 	BUILD_BUG_ON(sizeof(struct sie_page) != 4096);
 	sie_page = (struct sie_page *) get_zeroed_page(GFP_KERNEL);
 	if (!sie_page)
-		goto out_free_cpu;
+		return -ENOMEM;
 
 	vcpu->arch.sie_block = &sie_page->sie_block;
 	vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
@@ -3063,27 +3023,59 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	vcpu->arch.sie_block->mso = 0;
 	vcpu->arch.sie_block->msl = sclp.hamax;
 
-	vcpu->arch.sie_block->icpua = id;
+	vcpu->arch.sie_block->icpua = vcpu->vcpu_id;
 	spin_lock_init(&vcpu->arch.local_int.lock);
-	vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa_int.origin;
+	vcpu->arch.sie_block->gd = (u32)(u64)vcpu->kvm->arch.gisa_int.origin;
 	if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
 		vcpu->arch.sie_block->gd |= GISA_FORMAT1;
 	seqcount_init(&vcpu->arch.cputm_seqcount);
 
-	rc = kvm_vcpu_init(vcpu, kvm, id);
+	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+	kvm_clear_async_pf_completion_queue(vcpu);
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
+				    KVM_SYNC_GPRS |
+				    KVM_SYNC_ACRS |
+				    KVM_SYNC_CRS |
+				    KVM_SYNC_ARCH0 |
+				    KVM_SYNC_PFAULT;
+	kvm_s390_set_prefix(vcpu, 0);
+	if (test_kvm_facility(vcpu->kvm, 64))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
+	if (test_kvm_facility(vcpu->kvm, 133))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
+	if (test_kvm_facility(vcpu->kvm, 156))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN;
+	/* fprs can be synchronized via vrs, even if the guest has no vx. With
+	 * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+	 */
+	if (MACHINE_HAS_VX)
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
+	else
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
+
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		rc = __kvm_ucontrol_vcpu_init(vcpu);
+		if (rc)
+			goto out_free_sie_block;
+	}
+
+	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK",
+		 vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
+	trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
+
+	rc = kvm_s390_vcpu_setup(vcpu);
 	if (rc)
-		goto out_free_sie_block;
-	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
-		 vcpu->arch.sie_block);
-	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
+		goto out_ucontrol_uninit;
+	return 0;
 
-	return vcpu;
+out_ucontrol_uninit:
+	if (kvm_is_ucontrol(vcpu->kvm))
+		gmap_remove(vcpu->arch.gmap);
 out_free_sie_block:
 	free_page((unsigned long)(vcpu->arch.sie_block));
-out_free_cpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
-out:
-	return ERR_PTR(rc);
+	return rc;
 }
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index b0246c705a19..5674710a4841 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -2,7 +2,7 @@
 /*
  *  IBM System z Huge TLB Page Support for Kernel.
  *
- *    Copyright IBM Corp. 2007,2016
+ *    Copyright IBM Corp. 2007,2020
  *    Author(s): Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
@@ -11,6 +11,9 @@
 
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/security.h>
 
 /*
  * If the bit selected by single-bit bitmask "a" is set within "x", move
@@ -267,3 +270,98 @@ static __init int setup_hugepagesz(char *opt)
 	return 1;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
+		unsigned long addr, unsigned long len,
+		unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+	struct vm_unmapped_area_info info;
+
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = current->mm->mmap_base;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	return vm_unmapped_area(&info);
+}
+
+static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
+		unsigned long addr0, unsigned long len,
+		unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+	struct vm_unmapped_area_info info;
+	unsigned long addr;
+
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = max(PAGE_SIZE, mmap_min_addr);
+	info.high_limit = current->mm->mmap_base;
+	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+	info.align_offset = 0;
+	addr = vm_unmapped_area(&info);
+
+	/*
+	 * A failed mmap() very likely causes application failure,
+	 * so fall back to the bottom-up function here. This scenario
+	 * can happen with large stack limits and large mmap()
+	 * allocations.
+	 */
+	if (addr & ~PAGE_MASK) {
+		VM_BUG_ON(addr != -ENOMEM);
+		info.flags = 0;
+		info.low_limit = TASK_UNMAPPED_BASE;
+		info.high_limit = TASK_SIZE;
+		addr = vm_unmapped_area(&info);
+	}
+
+	return addr;
+}
+
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (len > TASK_SIZE - mmap_min_addr)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED) {
+		if (prepare_hugepage_range(file, addr, len))
+			return -EINVAL;
+		goto check_asce_limit;
+	}
+
+	if (addr) {
+		addr = ALIGN(addr, huge_page_size(h));
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
+		    (!vma || addr + len <= vm_start_gap(vma)))
+			goto check_asce_limit;
+	}
+
+	if (mm->get_unmapped_area == arch_get_unmapped_area)
+		addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
+				pgoff, flags);
+	else
+		addr = hugetlb_get_unmapped_area_topdown(file, addr, len,
+				pgoff, flags);
+	if (addr & ~PAGE_MASK)
+		return addr;
+
+check_asce_limit:
+	if (addr + len > current->mm->context.asce_limit &&
+	    addr + len <= TASK_SIZE) {
+		rc = crst_table_upgrade(mm, addr + len);
+		if (rc)
+			return (unsigned long) rc;
+	}
+	return addr;
+}
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index a7185cc18626..c7a30fcd135f 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/sh/mm/alignment.c b/arch/sh/mm/alignment.c
index ec2b25302427..fb517b82a87b 100644
--- a/arch/sh/mm/alignment.c
+++ b/arch/sh/mm/alignment.c
@@ -152,13 +152,12 @@ static ssize_t alignment_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations alignment_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= alignment_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= alignment_proc_write,
+static const struct proc_ops alignment_proc_ops = {
+	.proc_open	= alignment_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= alignment_proc_write,
 };
 
 /*
@@ -176,12 +175,12 @@ static int __init alignment_init(void)
 		return -ENOMEM;
 
 	res = proc_create_data("alignment", S_IWUSR | S_IRUGO, dir,
-			       &alignment_proc_fops, &se_usermode);
+			       &alignment_proc_ops, &se_usermode);
 	if (!res)
 		return -ENOMEM;
 
         res = proc_create_data("kernel_alignment", S_IWUSR | S_IRUGO, dir,
-			       &alignment_proc_fops, &se_kernmode_warn);
+			       &alignment_proc_ops, &se_kernmode_warn);
         if (!res)
                 return -ENOMEM;
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index e8c3ea01c12f..c1dd6dd642f4 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -64,8 +64,7 @@ config SPARC64
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
-	select HAVE_RCU_TABLE_FREE if SMP
-	select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
+	select MMU_GATHER_RCU_TABLE_FREE if SMP
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index 30b1763580b1..40a267b3bd52 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -125,23 +125,6 @@ typedef u32		compat_sigset_word;
 
 #define COMPAT_OFF_T_MAX	0x7fffffff
 
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
 #ifdef CONFIG_COMPAT
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h
index 9d3e5cc95bbb..264e76ceccf6 100644
--- a/arch/sparc/include/asm/pgalloc_64.h
+++ b/arch/sparc/include/asm/pgalloc_64.h
@@ -16,12 +16,12 @@
 
 extern struct kmem_cache *pgtable_cache;
 
-static inline void __pgd_populate(pgd_t *pgd, pud_t *pud)
+static inline void __p4d_populate(p4d_t *p4d, pud_t *pud)
 {
-	pgd_set(pgd, pud);
+	p4d_set(p4d, pud);
 }
 
-#define pgd_populate(MM, PGD, PUD)	__pgd_populate(PGD, PUD)
+#define p4d_populate(MM, P4D, PUD)	__p4d_populate(P4D, PUD)
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 6ae8016ef4ec..65494c3a420e 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -13,7 +13,7 @@
  * the SpitFire page tables.
  */
 
-#include <asm-generic/5level-fixup.h>
+#include <asm-generic/pgtable-nop4d.h>
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <asm/types.h>
@@ -683,6 +683,7 @@ static inline unsigned long pte_special(pte_t pte)
 	return pte_val(pte) & _PAGE_SPECIAL;
 }
 
+#define pmd_leaf	pmd_large
 static inline unsigned long pmd_large(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
@@ -810,9 +811,9 @@ static inline int pmd_present(pmd_t pmd)
 
 #define pud_bad(pud)			(pud_val(pud) & ~PAGE_MASK)
 
-#define pgd_none(pgd)			(!pgd_val(pgd))
+#define p4d_none(p4d)			(!p4d_val(p4d))
 
-#define pgd_bad(pgd)			(pgd_val(pgd) & ~PAGE_MASK)
+#define p4d_bad(p4d)			(p4d_val(p4d) & ~PAGE_MASK)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void set_pmd_at(struct mm_struct *mm, unsigned long addr,
@@ -859,14 +860,15 @@ static inline unsigned long pud_page_vaddr(pud_t pud)
 #define pmd_clear(pmdp)			(pmd_val(*(pmdp)) = 0UL)
 #define pud_present(pud)		(pud_val(pud) != 0U)
 #define pud_clear(pudp)			(pud_val(*(pudp)) = 0UL)
-#define pgd_page_vaddr(pgd)		\
-	((unsigned long) __va(pgd_val(pgd)))
-#define pgd_present(pgd)		(pgd_val(pgd) != 0U)
-#define pgd_clear(pgdp)			(pgd_val(*(pgdp)) = 0UL)
+#define p4d_page_vaddr(p4d)		\
+	((unsigned long) __va(p4d_val(p4d)))
+#define p4d_present(p4d)		(p4d_val(p4d) != 0U)
+#define p4d_clear(p4dp)			(p4d_val(*(p4dp)) = 0UL)
 
 /* only used by the stubbed out hugetlb gup code, should never be called */
-#define pgd_page(pgd)			NULL
+#define p4d_page(p4d)			NULL
 
+#define pud_leaf	pud_large
 static inline unsigned long pud_large(pud_t pud)
 {
 	pte_t pte = __pte(pud_val(pud));
@@ -884,8 +886,8 @@ static inline unsigned long pud_pfn(pud_t pud)
 /* Same in both SUN4V and SUN4U.  */
 #define pte_none(pte) 			(!pte_val(pte))
 
-#define pgd_set(pgdp, pudp)	\
-	(pgd_val(*(pgdp)) = (__pa((unsigned long) (pudp))))
+#define p4d_set(p4dp, pudp)	\
+	(p4d_val(*(p4dp)) = (__pa((unsigned long) (pudp))))
 
 /* to find an entry in a page-table-directory. */
 #define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
@@ -896,8 +898,8 @@ static inline unsigned long pud_pfn(pud_t pud)
 
 /* Find an entry in the third-level page table.. */
 #define pud_index(address)	(((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
-#define pud_offset(pgdp, address)	\
-	((pud_t *) pgd_page_vaddr(*(pgdp)) + pud_index(address))
+#define pud_offset(p4dp, address)	\
+	((pud_t *) p4d_page_vaddr(*(p4dp)) + pud_index(address))
 
 /* Find an entry in the second-level page table.. */
 #define pmd_offset(pudp, address)	\
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index a2f3fa61ee36..6820d357581c 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -28,6 +28,15 @@ void flush_tlb_pending(void);
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #define tlb_flush(tlb)	flush_tlb_pending()
 
+/*
+ * SPARC64's hardware TLB fill does not use the Linux page-tables
+ * and therefore we don't need a TLBI when freeing page-table pages.
+ */
+
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
+#define tlb_needs_table_invalidate()	(false)
+#endif
+
 #include <asm-generic/tlb.h>
 
 #endif /* _SPARC64_TLB_H */
diff --git a/arch/sparc/include/uapi/asm/ipcbuf.h b/arch/sparc/include/uapi/asm/ipcbuf.h
index 5b933a598a33..0ea1240d2ea1 100644
--- a/arch/sparc/include/uapi/asm/ipcbuf.h
+++ b/arch/sparc/include/uapi/asm/ipcbuf.h
@@ -17,19 +17,19 @@
 
 struct ipc64_perm
 {
-	__kernel_key_t	key;
-	__kernel_uid_t	uid;
-	__kernel_gid_t	gid;
-	__kernel_uid_t	cuid;
-	__kernel_gid_t	cgid;
+	__kernel_key_t		key;
+	__kernel_uid32_t	uid;
+	__kernel_gid32_t	gid;
+	__kernel_uid32_t	cuid;
+	__kernel_gid32_t	cgid;
 #ifndef __arch64__
-	unsigned short	__pad0;
+	unsigned short		__pad0;
 #endif
-	__kernel_mode_t	mode;
-	unsigned short	__pad1;
-	unsigned short	seq;
-	unsigned long long __unused1;
-	unsigned long long __unused2;
+	__kernel_mode_t		mode;
+	unsigned short		__pad1;
+	unsigned short		seq;
+	unsigned long long	__unused1;
+	unsigned long long	__unused2;
 };
 
 #endif /* __SPARC_IPCBUF_H */
diff --git a/arch/sparc/include/uapi/asm/statfs.h b/arch/sparc/include/uapi/asm/statfs.h
deleted file mode 100644
index 20c8f5bd340e..000000000000
--- a/arch/sparc/include/uapi/asm/statfs.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef ___ASM_SPARC_STATFS_H
-#define ___ASM_SPARC_STATFS_H
-
-#include <asm-generic/statfs.h>
-
-#endif
diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c
index a6292f8ed180..bd48575172c3 100644
--- a/arch/sparc/kernel/led.c
+++ b/arch/sparc/kernel/led.c
@@ -104,13 +104,12 @@ static ssize_t led_proc_write(struct file *file, const char __user *buffer,
 	return count;
 }
 
-static const struct file_operations led_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= led_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= led_proc_write,
+static const struct proc_ops led_proc_ops = {
+	.proc_open	= led_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= led_proc_write,
 };
 
 static struct proc_dir_entry *led;
@@ -121,7 +120,7 @@ static int __init led_init(void)
 {
 	timer_setup(&led_blink_timer, led_blink, 0);
 
-	led = proc_create("led", 0, NULL, &led_proc_fops);
+	led = proc_create("led", 0, NULL, &led_proc_ops);
 	if (!led)
 		return -ENOMEM;
 
diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c
index ec244d1022ce..da8902295c8c 100644
--- a/arch/sparc/kernel/prom_32.c
+++ b/arch/sparc/kernel/prom_32.c
@@ -132,12 +132,13 @@ static void __init ebus_path_component(struct device_node *dp, char *tmp_buf)
 		regs->which_io, regs->phys_addr);
 }
 
-/* "name:vendor:device@irq,addrlo" */
+/* "name@irq,addrlo" */
 static void __init ambapp_path_component(struct device_node *dp, char *tmp_buf)
 {
 	const char *name = of_get_property(dp, "name", NULL);
 	struct amba_prom_registers *regs;
-	unsigned int *intr, *device, *vendor, reg0;
+	unsigned int *intr;
+	unsigned int reg0;
 	struct property *prop;
 	int interrupt = 0;
 
@@ -159,18 +160,7 @@ static void __init ambapp_path_component(struct device_node *dp, char *tmp_buf)
 	else
 		intr = prop->value;
 
-	prop = of_find_property(dp, "vendor", NULL);
-	if (!prop)
-		return;
-	vendor = prop->value;
-	prop = of_find_property(dp, "device", NULL);
-	if (!prop)
-		return;
-	device = prop->value;
-
-	sprintf(tmp_buf, "%s:%d:%d@%x,%x",
-		name, *vendor, *device,
-		*intr, reg0);
+	sprintf(tmp_buf, "%s@%x,%x", name, *intr, reg0);
 }
 
 static void __init __build_path_component(struct device_node *dp, char *tmp_buf)
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index a237810aa9f4..2a734ecd0a40 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -299,6 +299,7 @@ static void flush_signal_insns(unsigned long address)
 	unsigned long pstate, paddr;
 	pte_t *ptep, pte;
 	pgd_t *pgdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 
@@ -318,7 +319,10 @@ static void flush_signal_insns(unsigned long address)
 	pgdp = pgd_offset(current->mm, address);
 	if (pgd_none(*pgdp))
 		goto out_irqs_on;
-	pudp = pud_offset(pgdp, address);
+	p4dp = p4d_offset(pgdp, address);
+	if (p4d_none(*p4dp))
+		goto out_irqs_on;
+	pudp = pud_offset(p4dp, address);
 	if (pud_none(*pudp))
 		goto out_irqs_on;
 	pmdp = pmd_offset(pudp, address);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 9b4506373353..80f20b3808ee 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1621,6 +1621,7 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
 static void __init pcpu_populate_pte(unsigned long addr)
 {
 	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -1633,7 +1634,17 @@ static void __init pcpu_populate_pte(unsigned long addr)
 		pgd_populate(&init_mm, pgd, new);
 	}
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d)) {
+		pud_t *new;
+
+		new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+		if (!new)
+			goto err_alloc;
+		p4d_populate(&init_mm, p4d, new);
+	}
+
+	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud)) {
 		pmd_t *new;
 
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 34917617f258..6b92fadb6ec7 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -551,7 +551,7 @@ out_unlock:
 SYSCALL_DEFINE1(sparc_adjtimex, struct __kernel_timex __user *, txc_p)
 {
 	struct __kernel_timex txc;
-	struct __kernel_old_timeval *tv = (void *)&txc_p->time;
+	struct __kernel_old_timeval *tv = (void *)&txc.time;
 	int ret;
 
 	/* Copy the user data space into the kernel copy
@@ -576,7 +576,7 @@ SYSCALL_DEFINE2(sparc_clock_adjtime, const clockid_t, which_clock,
 		struct __kernel_timex __user *, txc_p)
 {
 	struct __kernel_timex txc;
-	struct __kernel_old_timeval *tv = (void *)&txc_p->time;
+	struct __kernel_old_timeval *tv = (void *)&txc.time;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_POSIX_TIMERS)) {
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index b11c19552022..f13615ecdecc 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -482,3 +482,4 @@
 434	common	pidfd_open			sys_pidfd_open
 # 435 reserved for clone3
 437	common	openat2			sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 7ec79918b566..f99e99e58075 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -171,12 +171,14 @@ SECTIONS
 	}
 	PERCPU_SECTION(SMP_CACHE_BYTES)
 
-#ifdef CONFIG_JUMP_LABEL
 	. = ALIGN(PAGE_SIZE);
 	.exit.text : {
 		EXIT_TEXT
 	}
-#endif
+
+	.exit.data : {
+		EXIT_DATA
+	}
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 2371fb6b97e4..8b7ddbd14b65 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -80,6 +80,7 @@ static void __kprobes bad_kernel_pc(struct pt_regs *regs, unsigned long vaddr)
 static unsigned int get_user_insn(unsigned long tpc)
 {
 	pgd_t *pgdp = pgd_offset(current->mm, tpc);
+	p4d_t *p4dp;
 	pud_t *pudp;
 	pmd_t *pmdp;
 	pte_t *ptep, pte;
@@ -88,7 +89,10 @@ static unsigned int get_user_insn(unsigned long tpc)
 
 	if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp)))
 		goto out;
-	pudp = pud_offset(pgdp, tpc);
+	p4dp = p4d_offset(pgdp, tpc);
+	if (p4d_none(*p4dp) || unlikely(p4d_bad(*p4dp)))
+		goto out;
+	pudp = pud_offset(p4dp, tpc);
 	if (pud_none(*pudp) || unlikely(pud_bad(*pudp)))
 		goto out;
 
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index f78793a06bbd..7b9fa861b67c 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -277,11 +277,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return NULL;
 	if (sz >= PUD_SIZE)
@@ -298,13 +300,17 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd_none(*pgd))
 		return NULL;
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud))
 		return NULL;
 	if (is_hugetlb_pud(*pud))
@@ -449,7 +455,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	mm_dec_nr_pmds(tlb->mm);
 }
 
-static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
 				   unsigned long addr, unsigned long end,
 				   unsigned long floor, unsigned long ceiling)
 {
@@ -458,7 +464,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	unsigned long start;
 
 	start = addr;
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -481,8 +487,8 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	if (end - 1 > ceiling - 1)
 		return;
 
-	pud = pud_offset(pgd, start);
-	pgd_clear(pgd);
+	pud = pud_offset(p4d, start);
+	p4d_clear(p4d);
 	pud_free_tlb(tlb, pud, start);
 	mm_dec_nr_puds(tlb->mm);
 }
@@ -492,6 +498,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 			    unsigned long floor, unsigned long ceiling)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	unsigned long next;
 
 	addr &= PMD_MASK;
@@ -511,10 +518,11 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 		return;
 
 	pgd = pgd_offset(tlb->mm, addr);
+	p4d = p4d_offset(pgd, addr);
 	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
 			continue;
-		hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
-	} while (pgd++, addr = next, addr != end);
+		hugetlb_free_pud_range(tlb, p4d, addr, next, floor, ceiling);
+	} while (p4d++, addr = next, addr != end);
 }
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index e6d91819da92..1cf0d666dea3 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -530,7 +530,8 @@ void __kprobes flush_icache_range(unsigned long start, unsigned long end)
 				paddr = kaddr & mask;
 			else {
 				pgd_t *pgdp = pgd_offset_k(kaddr);
-				pud_t *pudp = pud_offset(pgdp, kaddr);
+				p4d_t *p4dp = p4d_offset(pgdp, kaddr);
+				pud_t *pudp = pud_offset(p4dp, kaddr);
 				pmd_t *pmdp = pmd_offset(pudp, kaddr);
 				pte_t *ptep = pte_offset_kernel(pmdp, kaddr);
 
@@ -1653,6 +1654,7 @@ static unsigned long max_phys_bits = 40;
 bool kern_addr_valid(unsigned long addr)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -1674,7 +1676,11 @@ bool kern_addr_valid(unsigned long addr)
 	if (pgd_none(*pgd))
 		return 0;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return 0;
+
+	pud = pud_offset(p4d, addr);
 	if (pud_none(*pud))
 		return 0;
 
@@ -1800,6 +1806,7 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 	while (vstart < vend) {
 		unsigned long this_end, paddr = __pa(vstart);
 		pgd_t *pgd = pgd_offset_k(vstart);
+		p4d_t *p4d;
 		pud_t *pud;
 		pmd_t *pmd;
 		pte_t *pte;
@@ -1814,7 +1821,20 @@ static unsigned long __ref kernel_map_range(unsigned long pstart,
 			alloc_bytes += PAGE_SIZE;
 			pgd_populate(&init_mm, pgd, new);
 		}
-		pud = pud_offset(pgd, vstart);
+
+		p4d = p4d_offset(pgd, vstart);
+		if (p4d_none(*p4d)) {
+			pud_t *new;
+
+			new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE,
+						  PAGE_SIZE);
+			if (!new)
+				goto err_alloc;
+			alloc_bytes += PAGE_SIZE;
+			p4d_populate(&init_mm, p4d, new);
+		}
+
+		pud = pud_offset(p4d, vstart);
 		if (pud_none(*pud)) {
 			pmd_t *new;
 
@@ -2612,13 +2632,18 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 	for (; vstart < vend; vstart += PMD_SIZE) {
 		pgd_t *pgd = vmemmap_pgd_populate(vstart, node);
 		unsigned long pte;
+		p4d_t *p4d;
 		pud_t *pud;
 		pmd_t *pmd;
 
 		if (!pgd)
 			return -ENOMEM;
 
-		pud = vmemmap_pud_populate(pgd, vstart, node);
+		p4d = vmemmap_p4d_populate(pgd, vstart, node);
+		if (!p4d)
+			return -ENOMEM;
+
+		pud = vmemmap_pud_populate(p4d, vstart, node);
 		if (!pud)
 			return -ENOMEM;
 
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 0117489e9b30..b80a1d616e4e 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -752,10 +752,9 @@ static ssize_t mconsole_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations mconsole_proc_fops = {
-	.owner		= THIS_MODULE,
-	.write		= mconsole_proc_write,
-	.llseek		= noop_llseek,
+static const struct proc_ops mconsole_proc_ops = {
+	.proc_write	= mconsole_proc_write,
+	.proc_lseek	= noop_llseek,
 };
 
 static int create_proc_mconsole(void)
@@ -765,7 +764,7 @@ static int create_proc_mconsole(void)
 	if (notify_socket == NULL)
 		return 0;
 
-	ent = proc_create("mconsole", 0200, NULL, &mconsole_proc_fops);
+	ent = proc_create("mconsole", 0200, NULL, &mconsole_proc_ops);
 	if (ent == NULL) {
 		printk(KERN_INFO "create_proc_mconsole : proc_create failed\n");
 		return 0;
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index dcabb463e011..247f95da057b 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -113,6 +113,7 @@ static const struct block_device_operations ubd_blops = {
         .open		= ubd_open,
         .release	= ubd_release,
         .ioctl		= ubd_ioctl,
+        .compat_ioctl	= blkdev_compat_ptr_ioctl,
 	.getgeo		= ubd_getgeo,
 };
 
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
index 5aee0626e390..b4deb1bfbb68 100644
--- a/arch/um/include/asm/mmu_context.h
+++ b/arch/um/include/asm/mmu_context.h
@@ -25,11 +25,6 @@ static inline void arch_unmap(struct mm_struct *mm,
 			unsigned long start, unsigned long end)
 {
 }
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-				     struct vm_area_struct *vma)
-{
-}
-
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
 {
diff --git a/arch/um/kernel/exitcode.c b/arch/um/kernel/exitcode.c
index 369fd844e195..43edc2aa57e4 100644
--- a/arch/um/kernel/exitcode.c
+++ b/arch/um/kernel/exitcode.c
@@ -55,20 +55,19 @@ static ssize_t exitcode_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations exitcode_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= exitcode_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= exitcode_proc_write,
+static const struct proc_ops exitcode_proc_ops = {
+	.proc_open	= exitcode_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= exitcode_proc_write,
 };
 
 static int make_proc_exitcode(void)
 {
 	struct proc_dir_entry *ent;
 
-	ent = proc_create("exitcode", 0600, NULL, &exitcode_proc_fops);
+	ent = proc_create("exitcode", 0600, NULL, &exitcode_proc_ops);
 	if (ent == NULL) {
 		printk(KERN_WARNING "make_proc_exitcode : Failed to register "
 		       "/proc/exitcode\n");
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 17045e7211bf..56a094182bf5 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -348,13 +348,12 @@ static ssize_t sysemu_proc_write(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations sysemu_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= sysemu_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= sysemu_proc_write,
+static const struct proc_ops sysemu_proc_ops = {
+	.proc_open	= sysemu_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= sysemu_proc_write,
 };
 
 int __init make_proc_sysemu(void)
@@ -363,7 +362,7 @@ int __init make_proc_sysemu(void)
 	if (!sysemu_supported)
 		return 0;
 
-	ent = proc_create("sysemu", 0600, NULL, &sysemu_proc_fops);
+	ent = proc_create("sysemu", 0600, NULL, &sysemu_proc_ops);
 
 	if (ent == NULL)
 	{
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index 247a07ae2cdc..388c0c811c68 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -89,11 +89,6 @@ static inline void arch_unmap(struct mm_struct *mm,
 {
 }
 
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-				     struct vm_area_struct *vma)
-{
-}
-
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
 {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a283336bb5d5..beea77046f9b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -120,6 +120,7 @@ config X86
 	select GENERIC_IRQ_RESERVATION_MODE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PENDING_IRQ		if SMP
+	select GENERIC_PTDUMP
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
@@ -202,7 +203,7 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_RCU_TABLE_FREE		if PARAVIRT
+	select MMU_GATHER_RCU_TABLE_FREE		if PARAVIRT
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
@@ -1888,34 +1889,6 @@ config X86_UMIP
 	  specific cases in protected and virtual-8086 modes. Emulated
 	  results are dummy.
 
-config X86_INTEL_MPX
-	prompt "Intel MPX (Memory Protection Extensions)"
-	def_bool n
-	# Note: only available in 64-bit mode due to VMA flags shortage
-	depends on CPU_SUP_INTEL && X86_64
-	select ARCH_USES_HIGH_VMA_FLAGS
-	---help---
-	  MPX provides hardware features that can be used in
-	  conjunction with compiler-instrumented code to check
-	  memory references.  It is designed to detect buffer
-	  overflow or underflow bugs.
-
-	  This option enables running applications which are
-	  instrumented or otherwise use MPX.  It does not use MPX
-	  itself inside the kernel or to protect the kernel
-	  against bad memory references.
-
-	  Enabling this option will make the kernel larger:
-	  ~8k of kernel text and 36 bytes of data on a 64-bit
-	  defconfig.  It adds a long to the 'mm_struct' which
-	  will increase the kernel memory overhead of each
-	  process and adds some branches to paths used during
-	  exec() and munmap().
-
-	  For details, see Documentation/x86/intel_mpx.rst
-
-	  If unsure, say N.
-
 config X86_INTEL_MEMORY_PROTECTION_KEYS
 	prompt "Intel Memory Protection Keys"
 	def_bool y
@@ -2959,9 +2932,6 @@ config HAVE_ATOMIC_IOMAP
 	def_bool y
 	depends on X86_32
 
-config X86_DEV_DMA_OPS
-	bool
-
 source "drivers/firmware/Kconfig"
 
 source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index c4eab8ed33a3..2e74690b028a 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -62,26 +62,10 @@ config EARLY_PRINTK_USB_XDBC
 config MCSAFE_TEST
 	def_bool n
 
-config X86_PTDUMP_CORE
-	def_bool n
-
-config X86_PTDUMP
-	tristate "Export kernel pagetable layout to userspace via debugfs"
-	depends on DEBUG_KERNEL
-	select DEBUG_FS
-	select X86_PTDUMP_CORE
-	---help---
-	  Say Y here if you want to show the kernel pagetable layout in a
-	  debugfs file. This information is only useful for kernel developers
-	  who are working in architecture specific areas of the kernel.
-	  It is probably not a good idea to enable this feature in a production
-	  kernel.
-	  If in doubt, say "N"
-
 config EFI_PGT_DUMP
 	bool "Dump the EFI pagetable"
 	depends on EFI
-	select X86_PTDUMP_CORE
+	select PTDUMP_CORE
 	---help---
 	  Enable this if you want to dump the EFI page table before
 	  enabling virtual mode. This can be used to debug miscellaneous
@@ -90,7 +74,7 @@ config EFI_PGT_DUMP
 
 config DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	select X86_PTDUMP_CORE
+	select PTDUMP_CORE
 	---help---
 	  Generate a warning if any W+X mappings are found at boot.
 
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index d22a8b5c3fab..c17cb77eb150 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -441,3 +441,4 @@
 434	i386	pidfd_open		sys_pidfd_open			__ia32_sys_pidfd_open
 435	i386	clone3			sys_clone3			__ia32_sys_clone3
 437	i386	openat2			sys_openat2			__ia32_sys_openat2
+438	i386	pidfd_getfd		sys_pidfd_getfd			__ia32_sys_pidfd_getfd
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9035647ef236..44d510bc9b78 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -358,6 +358,7 @@
 434	common	pidfd_open		__x64_sys_pidfd_open
 435	common	clone3			__x64_sys_clone3/ptregs
 437	common	openat2			__x64_sys_openat2
+438	common	pidfd_getfd		__x64_sys_pidfd_getfd
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 8b52bc5ddf69..ea34464d6221 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -7,7 +7,6 @@ generated-y += unistd_32_ia32.h
 generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
 
-generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += export.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index af45e1452f09..7a4bb1bd4bdb 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -27,7 +27,7 @@
 
 /* Unconditional execution of RDRAND and RDSEED */
 
-static inline bool rdrand_long(unsigned long *v)
+static inline bool __must_check rdrand_long(unsigned long *v)
 {
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
@@ -41,7 +41,7 @@ static inline bool rdrand_long(unsigned long *v)
 	return false;
 }
 
-static inline bool rdrand_int(unsigned int *v)
+static inline bool __must_check rdrand_int(unsigned int *v)
 {
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
@@ -55,7 +55,7 @@ static inline bool rdrand_int(unsigned int *v)
 	return false;
 }
 
-static inline bool rdseed_long(unsigned long *v)
+static inline bool __must_check rdseed_long(unsigned long *v)
 {
 	bool ok;
 	asm volatile(RDSEED_LONG
@@ -64,7 +64,7 @@ static inline bool rdseed_long(unsigned long *v)
 	return ok;
 }
 
-static inline bool rdseed_int(unsigned int *v)
+static inline bool __must_check rdseed_int(unsigned int *v)
 {
 	bool ok;
 	asm volatile(RDSEED_INT
@@ -73,10 +73,6 @@ static inline bool rdseed_int(unsigned int *v)
 	return ok;
 }
 
-/* Conditional execution based on CPU type */
-#define arch_has_random()	static_cpu_has(X86_FEATURE_RDRAND)
-#define arch_has_random_seed()	static_cpu_has(X86_FEATURE_RDSEED)
-
 /*
  * These are the generic interfaces; they must not be declared if the
  * stubs in <linux/random.h> are to be invoked,
@@ -84,24 +80,24 @@ static inline bool rdseed_int(unsigned int *v)
  */
 #ifdef CONFIG_ARCH_RANDOM
 
-static inline bool arch_get_random_long(unsigned long *v)
+static inline bool __must_check arch_get_random_long(unsigned long *v)
 {
-	return arch_has_random() ? rdrand_long(v) : false;
+	return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_long(v) : false;
 }
 
-static inline bool arch_get_random_int(unsigned int *v)
+static inline bool __must_check arch_get_random_int(unsigned int *v)
 {
-	return arch_has_random() ? rdrand_int(v) : false;
+	return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_int(v) : false;
 }
 
-static inline bool arch_get_random_seed_long(unsigned long *v)
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
-	return arch_has_random_seed() ? rdseed_long(v) : false;
+	return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_long(v) : false;
 }
 
-static inline bool arch_get_random_seed_int(unsigned int *v)
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
-	return arch_has_random_seed() ? rdseed_int(v) : false;
+	return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_int(v) : false;
 }
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h
index 794eb2129bc6..92ae28389940 100644
--- a/arch/x86/include/asm/bugs.h
+++ b/arch/x86/include/asm/bugs.h
@@ -6,12 +6,6 @@
 
 extern void check_bugs(void);
 
-#if defined(CONFIG_CPU_SUP_INTEL)
-void check_mpx_erratum(struct cpuinfo_x86 *c);
-#else
-static inline void check_mpx_erratum(struct cpuinfo_x86 *c) {}
-#endif
-
 #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
 int ppro_with_ram_bug(void);
 #else
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 22c4dfe65992..52e9f3480f69 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -177,23 +177,6 @@ typedef struct user_regs_struct compat_elf_gregset_t;
 	(!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
 #endif
 
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
 	compat_uptr_t sp;
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 5e12c63b47aa..7e31f7f1bb06 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -8,16 +8,6 @@ struct dev_archdata {
 #endif
 };
 
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-struct dma_domain {
-	struct list_head node;
-	const struct dma_map_ops *dma_ops;
-	int domain_nr;
-};
-void add_dma_domain(struct dma_domain *domain);
-void del_dma_domain(struct dma_domain *domain);
-#endif
-
 struct pdev_archdata {
 };
 
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 8e1d0bb46361..4ea8584682f9 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
  * cpu_feature_enabled().
  */
 
-#ifdef CONFIG_X86_INTEL_MPX
-# define DISABLE_MPX	0
-#else
-# define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
-#endif
-
 #ifdef CONFIG_X86_SMAP
 # define DISABLE_SMAP	0
 #else
@@ -74,7 +68,7 @@
 #define DISABLED_MASK6	0
 #define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
-#define DISABLED_MASK9	(DISABLE_MPX|DISABLE_SMAP)
+#define DISABLED_MASK9	(DISABLE_SMAP)
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	0
 #define DISABLED_MASK12	0
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 5f10f7f2098d..92abc1e42bfc 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -809,7 +809,8 @@ union hv_synic_sint {
 		u64 reserved1:8;
 		u64 masked:1;
 		u64 auto_eoi:1;
-		u64 reserved2:46;
+		u64 polling:1;
+		u64 reserved2:45;
 	} __packed;
 };
 
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 77cf6c11f66b..03946eb3e2b9 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -222,6 +222,10 @@ struct x86_emulate_ops {
 
 	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt, u32 *eax, u32 *ebx,
 			  u32 *ecx, u32 *edx, bool check_limit);
+	bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt);
+	bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt);
+	bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt);
+
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 
 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b79cd6aa4075..329d01c689b7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -175,6 +175,11 @@ enum {
 	VCPU_SREG_LDTR,
 };
 
+enum exit_fastpath_completion {
+	EXIT_FASTPATH_NONE,
+	EXIT_FASTPATH_SKIP_EMUL_INS,
+};
+
 #include <asm/kvm_emulate.h>
 
 #define KVM_NR_MEM_OBJS 40
@@ -378,12 +383,12 @@ struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
-	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err,
+	int (*page_fault)(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 err,
 			  bool prefault);
 	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
 				  struct x86_exception *fault);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
-			    struct x86_exception *exception);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t gva_or_gpa,
+			    u32 access, struct x86_exception *exception);
 	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
 			       struct x86_exception *exception);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -606,7 +611,7 @@ struct kvm_vcpu_arch {
 	 * Paging state of an L2 guest (used for nested npt)
 	 *
 	 * This context will save all necessary information to walk page tables
-	 * of the an L2 guest. This context is only initialized for page table
+	 * of an L2 guest. This context is only initialized for page table
 	 * walking and not for faulting since we never handle l2 page faults on
 	 * the host.
 	 */
@@ -685,10 +690,10 @@ struct kvm_vcpu_arch {
 	bool pvclock_set_guest_stopped_request;
 
 	struct {
+		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
-		struct gfn_to_hva_cache stime;
-		struct kvm_steal_time steal;
+		struct gfn_to_pfn_cache cache;
 	} st;
 
 	u64 tsc_offset;
@@ -1022,6 +1027,11 @@ struct kvm_lapic_irq {
 	bool msi_redir_hint;
 };
 
+static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
+{
+	return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
+}
+
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
@@ -1040,7 +1050,7 @@ struct kvm_x86_ops {
 	void (*vm_destroy)(struct kvm *kvm);
 
 	/* Create, but do not attach this VCPU */
-	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
+	int (*vcpu_create)(struct kvm_vcpu *vcpu);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
 	void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
 
@@ -1090,7 +1100,8 @@ struct kvm_x86_ops {
 	void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
 
 	void (*run)(struct kvm_vcpu *vcpu);
-	int (*handle_exit)(struct kvm_vcpu *vcpu);
+	int (*handle_exit)(struct kvm_vcpu *vcpu,
+		enum exit_fastpath_completion exit_fastpath);
 	int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
 	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
@@ -1140,11 +1151,13 @@ struct kvm_x86_ops {
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage);
-	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
+	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu,
+		enum exit_fastpath_completion *exit_fastpath);
 	bool (*mpx_supported)(void);
 	bool (*xsaves_supported)(void);
 	bool (*umip_emulated)(void);
 	bool (*pt_supported)(void);
+	bool (*pku_supported)(void);
 
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 	void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
@@ -1468,7 +1481,7 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
@@ -1614,7 +1627,6 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 int kvm_is_in_guest(void);
 
 int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
-int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index e78c7db87801..bdeae9291e5c 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -50,10 +50,6 @@ typedef struct {
 	u16 pkey_allocation_map;
 	s16 execute_only_pkey;
 #endif
-#ifdef CONFIG_X86_INTEL_MPX
-	/* address of the bounds directory */
-	void __user *bd_addr;
-#endif
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(mm)						\
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index b243234e90cb..b538d9ddee9c 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -12,7 +12,6 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
-#include <asm/mpx.h>
 #include <asm/debugreg.h>
 
 extern atomic64_t last_mm_ctx_id;
@@ -200,34 +199,9 @@ static inline bool is_64bit_mm(struct mm_struct *mm)
 }
 #endif
 
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-		struct vm_area_struct *vma)
-{
-	mpx_mm_init(mm);
-}
-
 static inline void arch_unmap(struct mm_struct *mm, unsigned long start,
 			      unsigned long end)
 {
-	/*
-	 * mpx_notify_unmap() goes and reads a rarely-hot
-	 * cacheline in the mm_struct.  That can be expensive
-	 * enough to be seen in profiles.
-	 *
-	 * The mpx_notify_unmap() call and its contents have been
-	 * observed to affect munmap() performance on hardware
-	 * where MPX is not present.
-	 *
-	 * The unlikely() optimizes for the fast case: no MPX
-	 * in the CPU, or no MPX use in the process.  Even if
-	 * we get this wrong (in the unlikely event that MPX
-	 * is widely enabled on some system) the overhead of
-	 * MPX itself (reading bounds tables) is expected to
-	 * overwhelm the overhead of getting this unlikely()
-	 * consistently wrong.
-	 */
-	if (unlikely(cpu_feature_enabled(X86_FEATURE_MPX)))
-		mpx_notify_unmap(mm, start, end);
 }
 
 /*
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
deleted file mode 100644
index 143a5c193ed3..000000000000
--- a/arch/x86/include/asm/mpx.h
+++ /dev/null
@@ -1,116 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_MPX_H
-#define _ASM_X86_MPX_H
-
-#include <linux/types.h>
-#include <linux/mm_types.h>
-
-#include <asm/ptrace.h>
-#include <asm/insn.h>
-
-/*
- * NULL is theoretically a valid place to put the bounds
- * directory, so point this at an invalid address.
- */
-#define MPX_INVALID_BOUNDS_DIR	((void __user *)-1)
-#define MPX_BNDCFG_ENABLE_FLAG	0x1
-#define MPX_BD_ENTRY_VALID_FLAG	0x1
-
-/*
- * The upper 28 bits [47:20] of the virtual address in 64-bit
- * are used to index into bounds directory (BD).
- *
- * The directory is 2G (2^31) in size, and with 8-byte entries
- * it has 2^28 entries.
- */
-#define MPX_BD_SIZE_BYTES_64	(1UL<<31)
-#define MPX_BD_ENTRY_BYTES_64	8
-#define MPX_BD_NR_ENTRIES_64	(MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64)
-
-/*
- * The 32-bit directory is 4MB (2^22) in size, and with 4-byte
- * entries it has 2^20 entries.
- */
-#define MPX_BD_SIZE_BYTES_32	(1UL<<22)
-#define MPX_BD_ENTRY_BYTES_32	4
-#define MPX_BD_NR_ENTRIES_32	(MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32)
-
-/*
- * A 64-bit table is 4MB total in size, and an entry is
- * 4 64-bit pointers in size.
- */
-#define MPX_BT_SIZE_BYTES_64	(1UL<<22)
-#define MPX_BT_ENTRY_BYTES_64	32
-#define MPX_BT_NR_ENTRIES_64	(MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64)
-
-/*
- * A 32-bit table is 16kB total in size, and an entry is
- * 4 32-bit pointers in size.
- */
-#define MPX_BT_SIZE_BYTES_32	(1UL<<14)
-#define MPX_BT_ENTRY_BYTES_32	16
-#define MPX_BT_NR_ENTRIES_32	(MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32)
-
-#define MPX_BNDSTA_TAIL		2
-#define MPX_BNDCFG_TAIL		12
-#define MPX_BNDSTA_ADDR_MASK	(~((1UL<<MPX_BNDSTA_TAIL)-1))
-#define MPX_BNDCFG_ADDR_MASK	(~((1UL<<MPX_BNDCFG_TAIL)-1))
-#define MPX_BNDSTA_ERROR_CODE	0x3
-
-struct mpx_fault_info {
-	void __user *addr;
-	void __user *lower;
-	void __user *upper;
-};
-
-#ifdef CONFIG_X86_INTEL_MPX
-
-extern int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs);
-extern int mpx_handle_bd_fault(void);
-
-static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
-{
-	return (mm->context.bd_addr != MPX_INVALID_BOUNDS_DIR);
-}
-
-static inline void mpx_mm_init(struct mm_struct *mm)
-{
-	/*
-	 * NULL is theoretically a valid place to put the bounds
-	 * directory, so point this at an invalid address.
-	 */
-	mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
-}
-
-extern void mpx_notify_unmap(struct mm_struct *mm, unsigned long start, unsigned long end);
-extern unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, unsigned long flags);
-
-#else
-static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
-{
-	return -EINVAL;
-}
-static inline int mpx_handle_bd_fault(void)
-{
-	return -EINVAL;
-}
-static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
-{
-	return 0;
-}
-static inline void mpx_mm_init(struct mm_struct *mm)
-{
-}
-static inline void mpx_notify_unmap(struct mm_struct *mm,
-				    unsigned long start, unsigned long end)
-{
-}
-
-static inline unsigned long mpx_unmapped_area_check(unsigned long addr,
-		unsigned long len, unsigned long flags)
-{
-	return addr;
-}
-#endif /* CONFIG_X86_INTEL_MPX */
-
-#endif /* _ASM_X86_MPX_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index c1fdd43fe187..40ac1330adb2 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -25,7 +25,7 @@ struct pci_sysdata {
 	void		*fwnode;	/* IRQ domain for MSI assignment */
 #endif
 #if IS_ENABLED(CONFIG_VMD)
-	bool vmd_domain;		/* True if in Intel VMD domain */
+	struct pci_dev	*vmd_dev;	/* VMD Device if in Intel VMD domain */
 #endif
 };
 
@@ -35,12 +35,15 @@ extern int noioapicreroute;
 
 #ifdef CONFIG_PCI
 
+static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus)
+{
+	return bus->sysdata;
+}
+
 #ifdef CONFIG_PCI_DOMAINS
 static inline int pci_domain_nr(struct pci_bus *bus)
 {
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->domain;
+	return to_pci_sysdata(bus)->domain;
 }
 
 static inline int pci_proc_domain(struct pci_bus *bus)
@@ -52,24 +55,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
 static inline void *_pci_root_bus_fwnode(struct pci_bus *bus)
 {
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->fwnode;
+	return to_pci_sysdata(bus)->fwnode;
 }
 
 #define pci_root_bus_fwnode	_pci_root_bus_fwnode
 #endif
 
+#if IS_ENABLED(CONFIG_VMD)
 static inline bool is_vmd(struct pci_bus *bus)
 {
-#if IS_ENABLED(CONFIG_VMD)
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->vmd_domain;
-#else
-	return false;
-#endif
+	return to_pci_sysdata(bus)->vmd_dev != NULL;
 }
+#else
+#define is_vmd(bus)		false
+#endif /* CONFIG_VMD */
 
 /* Can be used to override the logic in pci_scan_bus for skipping
    already-configured bus numbers - to be used for buggy BIOSes
@@ -124,9 +123,7 @@ void native_restore_msi_irqs(struct pci_dev *dev);
 /* Returns the node based on pci bus */
 static inline int __pcibus_to_node(const struct pci_bus *bus)
 {
-	const struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->node;
+	return to_pci_sysdata(bus)->node;
 }
 
 static inline const struct cpumask *
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index ad97dc155195..7e118660bbd9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -29,8 +29,9 @@
 extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 
-void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
-void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
+void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
+				   bool user);
 void ptdump_walk_pgd_level_checkwx(void);
 void ptdump_walk_user_pgd_level_checkwx(void);
 
@@ -239,6 +240,7 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
 	return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
+#define p4d_leaf	p4d_large
 static inline int p4d_large(p4d_t p4d)
 {
 	/* No 512 GiB pages yet */
@@ -247,6 +249,7 @@ static inline int p4d_large(p4d_t p4d)
 
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
 
+#define pmd_leaf	pmd_large
 static inline int pmd_large(pmd_t pte)
 {
 	return pmd_flags(pte) & _PAGE_PSE;
@@ -874,6 +877,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
 }
 
+#define pud_leaf	pud_large
 static inline int pud_large(pud_t pud)
 {
 	return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
@@ -885,6 +889,7 @@ static inline int pud_bad(pud_t pud)
 	return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
 }
 #else
+#define pud_leaf	pud_large
 static inline int pud_large(pud_t pud)
 {
 	return 0;
@@ -1233,6 +1238,7 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
 }
 
+#define pgd_leaf	pgd_large
 static inline int pgd_large(pgd_t pgd) { return 0; }
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index ea7400726d7a..0239998d8cdc 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -566,6 +566,10 @@ static inline void update_page_count(int level, unsigned long pages) { }
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 				    unsigned int *level);
+
+struct mm_struct;
+extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address,
+				   unsigned int *level);
 extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6fb4870ed759..09705ccc393c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -947,24 +947,6 @@ extern int set_tsc_mode(unsigned int val);
 
 DECLARE_PER_CPU(u64, msr_misc_features_shadow);
 
-/* Register/unregister a process' MPX related resource */
-#define MPX_ENABLE_MANAGEMENT()	mpx_enable_management()
-#define MPX_DISABLE_MANAGEMENT()	mpx_disable_management()
-
-#ifdef CONFIG_X86_INTEL_MPX
-extern int mpx_enable_management(void);
-extern int mpx_disable_management(void);
-#else
-static inline int mpx_enable_management(void)
-{
-	return -EINVAL;
-}
-static inline int mpx_disable_management(void)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_X86_INTEL_MPX */
-
 #ifdef CONFIG_CPU_SUP_AMD
 extern u16 amd_get_nb_id(int cpu);
 extern u32 amd_get_nodes_per_socket(void);
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index f23e7aaff4cd..820082bd6880 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -29,8 +29,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
  * shootdown, enablement code for several hypervisors overrides
  * .flush_tlb_others hook in pv_mmu_ops and implements it by issuing
  * a hypercall. To keep software pagetable walkers safe in this case we
- * switch to RCU based table free (HAVE_RCU_TABLE_FREE). See the comment
- * below 'ifdef CONFIG_HAVE_RCU_TABLE_FREE' in include/asm-generic/tlb.h
+ * switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the comment
+ * below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
  * for more details.
  */
 static inline void __tlb_remove_table(void *table)
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
deleted file mode 100644
index 54133017267c..000000000000
--- a/arch/x86/include/asm/trace/mpx.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM mpx
-
-#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_MPX_H
-
-#include <linux/tracepoint.h>
-
-#ifdef CONFIG_X86_INTEL_MPX
-
-TRACE_EVENT(mpx_bounds_register_exception,
-
-	TP_PROTO(void __user *addr_referenced,
-		 const struct mpx_bndreg *bndreg),
-	TP_ARGS(addr_referenced, bndreg),
-
-	TP_STRUCT__entry(
-		__field(void __user *, addr_referenced)
-		__field(u64, lower_bound)
-		__field(u64, upper_bound)
-	),
-
-	TP_fast_assign(
-		__entry->addr_referenced = addr_referenced;
-		__entry->lower_bound = bndreg->lower_bound;
-		__entry->upper_bound = bndreg->upper_bound;
-	),
-	/*
-	 * Note that we are printing out the '~' of the upper
-	 * bounds register here.  It is actually stored in its
-	 * one's complement form so that its 'init' state
-	 * corresponds to all 0's.  But, that looks like
-	 * gibberish when printed out, so print out the 1's
-	 * complement instead of the actual value here.  Note
-	 * though that you still need to specify filters for the
-	 * actual value, not the displayed one.
-	 */
-	TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx",
-		__entry->addr_referenced,
-		__entry->lower_bound,
-		~__entry->upper_bound
-	)
-);
-
-TRACE_EVENT(bounds_exception_mpx,
-
-	TP_PROTO(const struct mpx_bndcsr *bndcsr),
-	TP_ARGS(bndcsr),
-
-	TP_STRUCT__entry(
-		__field(u64, bndcfgu)
-		__field(u64, bndstatus)
-	),
-
-	TP_fast_assign(
-		/* need to get rid of the 'const' on bndcsr */
-		__entry->bndcfgu   = (u64)bndcsr->bndcfgu;
-		__entry->bndstatus = (u64)bndcsr->bndstatus;
-	),
-
-	TP_printk("bndcfgu:0x%llx bndstatus:0x%llx",
-		__entry->bndcfgu,
-		__entry->bndstatus)
-);
-
-DECLARE_EVENT_CLASS(mpx_range_trace,
-
-	TP_PROTO(unsigned long start,
-		 unsigned long end),
-	TP_ARGS(start, end),
-
-	TP_STRUCT__entry(
-		__field(unsigned long, start)
-		__field(unsigned long, end)
-	),
-
-	TP_fast_assign(
-		__entry->start = start;
-		__entry->end   = end;
-	),
-
-	TP_printk("[0x%p:0x%p]",
-		(void *)__entry->start,
-		(void *)__entry->end
-	)
-);
-
-DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap,
-	TP_PROTO(unsigned long start, unsigned long end),
-	TP_ARGS(start, end)
-);
-
-DEFINE_EVENT(mpx_range_trace, mpx_unmap_search,
-	TP_PROTO(unsigned long start, unsigned long end),
-	TP_ARGS(start, end)
-);
-
-TRACE_EVENT(mpx_new_bounds_table,
-
-	TP_PROTO(unsigned long table_vaddr),
-	TP_ARGS(table_vaddr),
-
-	TP_STRUCT__entry(
-		__field(unsigned long, table_vaddr)
-	),
-
-	TP_fast_assign(
-		__entry->table_vaddr = table_vaddr;
-	),
-
-	TP_printk("table vaddr:%p", (void *)__entry->table_vaddr)
-);
-
-#else
-
-/*
- * This gets used outside of MPX-specific code, so we need a stub.
- */
-static inline
-void trace_bounds_exception_mpx(const struct mpx_bndcsr *bndcsr)
-{
-}
-
-#endif /* CONFIG_X86_INTEL_MPX */
-
-#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH asm/trace/
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE mpx
-#endif /* _TRACE_MPX_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9fbba31be825..d380b3b7ddd9 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -22,8 +22,8 @@
 /*
  * Definitions of Primary Processor-Based VM-Execution Controls.
  */
-#define CPU_BASED_VIRTUAL_INTR_PENDING          VMCS_CONTROL_BIT(VIRTUAL_INTR_PENDING)
-#define CPU_BASED_USE_TSC_OFFSETING             VMCS_CONTROL_BIT(TSC_OFFSETTING)
+#define CPU_BASED_INTR_WINDOW_EXITING           VMCS_CONTROL_BIT(VIRTUAL_INTR_PENDING)
+#define CPU_BASED_USE_TSC_OFFSETTING            VMCS_CONTROL_BIT(TSC_OFFSETTING)
 #define CPU_BASED_HLT_EXITING                   VMCS_CONTROL_BIT(HLT_EXITING)
 #define CPU_BASED_INVLPG_EXITING                VMCS_CONTROL_BIT(INVLPG_EXITING)
 #define CPU_BASED_MWAIT_EXITING                 VMCS_CONTROL_BIT(MWAIT_EXITING)
@@ -34,7 +34,7 @@
 #define CPU_BASED_CR8_LOAD_EXITING              VMCS_CONTROL_BIT(CR8_LOAD_EXITING)
 #define CPU_BASED_CR8_STORE_EXITING             VMCS_CONTROL_BIT(CR8_STORE_EXITING)
 #define CPU_BASED_TPR_SHADOW                    VMCS_CONTROL_BIT(VIRTUAL_TPR)
-#define CPU_BASED_VIRTUAL_NMI_PENDING		VMCS_CONTROL_BIT(VIRTUAL_NMI_PENDING)
+#define CPU_BASED_NMI_WINDOW_EXITING		VMCS_CONTROL_BIT(VIRTUAL_NMI_PENDING)
 #define CPU_BASED_MOV_DR_EXITING                VMCS_CONTROL_BIT(MOV_DR_EXITING)
 #define CPU_BASED_UNCOND_IO_EXITING             VMCS_CONTROL_BIT(UNCOND_IO_EXITING)
 #define CPU_BASED_USE_IO_BITMAPS                VMCS_CONTROL_BIT(USE_IO_BITMAPS)
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 3eb8411ab60e..e95b72ec19bc 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -33,7 +33,7 @@
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
 
-#define EXIT_REASON_PENDING_INTERRUPT   7
+#define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
 #define EXIT_REASON_TASK_SWITCH         9
 #define EXIT_REASON_CPUID               10
@@ -94,7 +94,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
-	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
+	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
 	{ EXIT_REASON_CPUID,                 "CPUID" }, \
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 6175e370ee4a..9b294c13809a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -94,6 +94,7 @@ obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace_$(BITS).o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
+obj-$(CONFIG_CRASH_CORE)	+= crash_core_$(BITS).o
 obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC_CORE)	+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_KEXEC_FILE)	+= kexec-bzimage64.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 34360ca301a2..15ac0d5f4b40 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -23,6 +23,7 @@
 #include <asm/nmi.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 86b8241c8209..52c9bfbbdb2a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -164,22 +164,6 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
-static int __init x86_mpx_setup(char *s)
-{
-	/* require an exact match without trailing characters */
-	if (strlen(s))
-		return 0;
-
-	/* do not emit a message if the feature is not present */
-	if (!boot_cpu_has(X86_FEATURE_MPX))
-		return 1;
-
-	setup_clear_cpu_cap(X86_FEATURE_MPX);
-	pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n");
-	return 1;
-}
-__setup("nompx", x86_mpx_setup);
-
 #ifdef CONFIG_X86_64
 static int __init x86_nopcid_setup(char *s)
 {
@@ -306,8 +290,6 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
 static __init int setup_disable_smep(char *arg)
 {
 	setup_clear_cpu_cap(X86_FEATURE_SMEP);
-	/* Check for things that depend on SMEP being enabled: */
-	check_mpx_erratum(&boot_cpu_data);
 	return 1;
 }
 __setup("nosmep", setup_disable_smep);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 57473e2c0869..be82cd5841c3 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -32,41 +32,6 @@
 #endif
 
 /*
- * Just in case our CPU detection goes bad, or you have a weird system,
- * allow a way to override the automatic disabling of MPX.
- */
-static int forcempx;
-
-static int __init forcempx_setup(char *__unused)
-{
-	forcempx = 1;
-
-	return 1;
-}
-__setup("intel-skd-046-workaround=disable", forcempx_setup);
-
-void check_mpx_erratum(struct cpuinfo_x86 *c)
-{
-	if (forcempx)
-		return;
-	/*
-	 * Turn off the MPX feature on CPUs where SMEP is not
-	 * available or disabled.
-	 *
-	 * Works around Intel Erratum SKD046: "Branch Instructions
-	 * May Initialize MPX Bound Registers Incorrectly".
-	 *
-	 * This might falsely disable MPX on systems without
-	 * SMEP, like Atom processors without SMEP.  But there
-	 * is no such hardware known at the moment.
-	 */
-	if (cpu_has(c, X86_FEATURE_MPX) && !cpu_has(c, X86_FEATURE_SMEP)) {
-		setup_clear_cpu_cap(X86_FEATURE_MPX);
-		pr_warn("x86/mpx: Disabling MPX since SMEP not present\n");
-	}
-}
-
-/*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
  * CPU models in which having conflicting memory types still leads to
@@ -330,7 +295,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 			c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
 	}
 
-	check_mpx_erratum(c);
 	check_memory_type_self_snoop_errata(c);
 
 	/*
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index da532f656a7b..a5c506f6da7f 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -396,15 +396,16 @@ static int mtrr_open(struct inode *inode, struct file *file)
 	return single_open(file, mtrr_seq_show, NULL);
 }
 
-static const struct file_operations mtrr_fops = {
-	.owner			= THIS_MODULE,
-	.open			= mtrr_open,
-	.read			= seq_read,
-	.llseek			= seq_lseek,
-	.write			= mtrr_write,
-	.unlocked_ioctl		= mtrr_ioctl,
-	.compat_ioctl		= mtrr_ioctl,
-	.release		= mtrr_close,
+static const struct proc_ops mtrr_proc_ops = {
+	.proc_open		= mtrr_open,
+	.proc_read		= seq_read,
+	.proc_lseek		= seq_lseek,
+	.proc_write		= mtrr_write,
+	.proc_ioctl		= mtrr_ioctl,
+#ifdef CONFIG_COMPAT
+	.proc_compat_ioctl	= mtrr_ioctl,
+#endif
+	.proc_release		= mtrr_close,
 };
 
 static int __init mtrr_if_init(void)
@@ -417,7 +418,7 @@ static int __init mtrr_if_init(void)
 	    (!cpu_has(c, X86_FEATURE_CENTAUR_MCR)))
 		return -ENODEV;
 
-	proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops);
+	proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_proc_ops);
 	return 0;
 }
 arch_initcall(mtrr_if_init);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 1504bcabc63c..8ca5e510f3ce 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2060,7 +2060,7 @@ static int rdt_get_tree(struct fs_context *fc)
 
 	if (rdt_mon_capable) {
 		ret = mongroup_create_dir(rdtgroup_default.kn,
-					  NULL, "mon_groups",
+					  &rdtgroup_default, "mon_groups",
 					  &kn_mongrp);
 		if (ret < 0)
 			goto out_info;
@@ -2295,7 +2295,11 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 	list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
 		free_rmid(sentry->mon.rmid);
 		list_del(&sentry->mon.crdtgrp_list);
-		kfree(sentry);
+
+		if (atomic_read(&sentry->waitcount) != 0)
+			sentry->flags = RDT_DELETED;
+		else
+			kfree(sentry);
 	}
 }
 
@@ -2333,7 +2337,11 @@ static void rmdir_all_sub(void)
 
 		kernfs_remove(rdtgrp->kn);
 		list_del(&rdtgrp->rdtgroup_list);
-		kfree(rdtgrp);
+
+		if (atomic_read(&rdtgrp->waitcount) != 0)
+			rdtgrp->flags = RDT_DELETED;
+		else
+			kfree(rdtgrp);
 	}
 	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
 	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
@@ -2536,7 +2544,7 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
 	/*
 	 * Create the mon_data directory first.
 	 */
-	ret = mongroup_create_dir(parent_kn, NULL, "mon_data", &kn);
+	ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
 	if (ret)
 		return ret;
 
@@ -2726,7 +2734,6 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 }
 
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
-			     struct kernfs_node *prgrp_kn,
 			     const char *name, umode_t mode,
 			     enum rdt_group_type rtype, struct rdtgroup **r)
 {
@@ -2735,7 +2742,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	uint files = 0;
 	int ret;
 
-	prdtgrp = rdtgroup_kn_lock_live(prgrp_kn);
+	prdtgrp = rdtgroup_kn_lock_live(parent_kn);
 	if (!prdtgrp) {
 		ret = -ENODEV;
 		goto out_unlock;
@@ -2808,7 +2815,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	kernfs_activate(kn);
 
 	/*
-	 * The caller unlocks the prgrp_kn upon success.
+	 * The caller unlocks the parent_kn upon success.
 	 */
 	return 0;
 
@@ -2819,7 +2826,7 @@ out_destroy:
 out_free_rgrp:
 	kfree(rdtgrp);
 out_unlock:
-	rdtgroup_kn_unlock(prgrp_kn);
+	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
 
@@ -2836,15 +2843,12 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
  * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
  */
 static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
-			      struct kernfs_node *prgrp_kn,
-			      const char *name,
-			      umode_t mode)
+			      const char *name, umode_t mode)
 {
 	struct rdtgroup *rdtgrp, *prgrp;
 	int ret;
 
-	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTMON_GROUP,
-				&rdtgrp);
+	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp);
 	if (ret)
 		return ret;
 
@@ -2857,7 +2861,7 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
 	 */
 	list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
 
-	rdtgroup_kn_unlock(prgrp_kn);
+	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
 
@@ -2866,7 +2870,6 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
  * to allocate and monitor resources.
  */
 static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
-				   struct kernfs_node *prgrp_kn,
 				   const char *name, umode_t mode)
 {
 	struct rdtgroup *rdtgrp;
@@ -2874,8 +2877,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	u32 closid;
 	int ret;
 
-	ret = mkdir_rdt_prepare(parent_kn, prgrp_kn, name, mode, RDTCTRL_GROUP,
-				&rdtgrp);
+	ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp);
 	if (ret)
 		return ret;
 
@@ -2900,7 +2902,7 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 		 * Create an empty mon_groups directory to hold the subset
 		 * of tasks and cpus to monitor.
 		 */
-		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
+		ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
 		if (ret) {
 			rdt_last_cmd_puts("kernfs subdir error\n");
 			goto out_del_list;
@@ -2916,7 +2918,7 @@ out_id_free:
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
 out_unlock:
-	rdtgroup_kn_unlock(prgrp_kn);
+	rdtgroup_kn_unlock(parent_kn);
 	return ret;
 }
 
@@ -2949,14 +2951,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	 * subdirectory
 	 */
 	if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn)
-		return rdtgroup_mkdir_ctrl_mon(parent_kn, parent_kn, name, mode);
+		return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
 
 	/*
 	 * If RDT monitoring is supported and the parent directory is a valid
 	 * "mon_groups" directory, add a monitoring subdirectory.
 	 */
 	if (rdt_mon_capable && is_mon_groups(parent_kn, name))
-		return rdtgroup_mkdir_mon(parent_kn, parent_kn->parent, name, mode);
+		return rdtgroup_mkdir_mon(parent_kn, name, mode);
 
 	return -EPERM;
 }
@@ -3042,13 +3044,13 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	closid_free(rdtgrp->closid);
 	free_rmid(rdtgrp->mon.rmid);
 
+	rdtgroup_ctrl_remove(kn, rdtgrp);
+
 	/*
 	 * Free all the child monitor group rmids.
 	 */
 	free_all_child_rdtgrp(rdtgrp);
 
-	rdtgroup_ctrl_remove(kn, rdtgrp);
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/crash_core_32.c
new file mode 100644
index 000000000000..c0159a7bca6d
--- /dev/null
+++ b/arch/x86/kernel/crash_core_32.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/crash_core.h>
+
+#include <asm/pgtable.h>
+#include <asm/setup.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+#ifdef CONFIG_NUMA
+	VMCOREINFO_SYMBOL(node_data);
+	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
+#ifdef CONFIG_X86_PAE
+	VMCOREINFO_CONFIG(X86_PAE);
+#endif
+}
diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/crash_core_64.c
new file mode 100644
index 000000000000..845a57eb4eb7
--- /dev/null
+++ b/arch/x86/kernel/crash_core_64.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/crash_core.h>
+
+#include <asm/pgtable.h>
+#include <asm/setup.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+	u64 sme_mask = sme_me_mask;
+
+	VMCOREINFO_NUMBER(phys_base);
+	VMCOREINFO_SYMBOL(init_top_pgt);
+	vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
+			      pgtable_l5_enabled());
+
+#ifdef CONFIG_NUMA
+	VMCOREINFO_SYMBOL(node_data);
+	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
+#endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
+	VMCOREINFO_NUMBER(sme_mask);
+}
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 7b45e8daad22..02bddfc122a4 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -250,15 +250,3 @@ void machine_kexec(struct kimage *image)
 
 	__ftrace_enabled_restore(save_ftrace_enabled);
 }
-
-void arch_crash_save_vmcoreinfo(void)
-{
-#ifdef CONFIG_NUMA
-	VMCOREINFO_SYMBOL(node_data);
-	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
-#endif
-#ifdef CONFIG_X86_PAE
-	VMCOREINFO_CONFIG(X86_PAE);
-#endif
-}
-
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 16e125a50b33..ad5cdd6a5f23 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -398,25 +398,6 @@ void machine_kexec(struct kimage *image)
 	__ftrace_enabled_restore(save_ftrace_enabled);
 }
 
-void arch_crash_save_vmcoreinfo(void)
-{
-	u64 sme_mask = sme_me_mask;
-
-	VMCOREINFO_NUMBER(phys_base);
-	VMCOREINFO_SYMBOL(init_top_pgt);
-	vmcoreinfo_append_str("NUMBER(pgtable_l5_enabled)=%d\n",
-			pgtable_l5_enabled());
-
-#ifdef CONFIG_NUMA
-	VMCOREINFO_SYMBOL(node_data);
-	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
-#endif
-	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
-			      kaslr_offset());
-	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
-	VMCOREINFO_NUMBER(sme_mask);
-}
-
 /* arch-dependent functionality related to kexec file-based syscall */
 
 #ifdef CONFIG_KEXEC_FILE
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1e4c20a1efec..a74262c71484 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -893,8 +893,6 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = _brk_end;
 
-	mpx_mm_init(&init_mm);
-
 	code_resource.start = __pa_symbol(_text);
 	code_resource.end = __pa_symbol(_etext)-1;
 	rodata_resource.start = __pa_symbol(__start_rodata);
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index f7476ce23b6e..ca3c11a17b5a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -22,7 +22,6 @@
 #include <asm/elf.h>
 #include <asm/ia32.h>
 #include <asm/syscalls.h>
-#include <asm/mpx.h>
 
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
@@ -137,10 +136,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_unmapped_area_info info;
 	unsigned long begin, end;
 
-	addr = mpx_unmapped_area_check(addr, len, flags);
-	if (IS_ERR_VALUE(addr))
-		return addr;
-
 	if (flags & MAP_FIXED)
 		return addr;
 
@@ -180,10 +175,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
 
-	addr = mpx_unmapped_area_check(addr, len, flags);
-	if (IS_ERR_VALUE(addr))
-		return addr;
-
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
 		return -ENOMEM;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9e6f822922a3..6ef00eb6fbb9 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -52,8 +52,6 @@
 #include <asm/mach_traps.h>
 #include <asm/alternative.h>
 #include <asm/fpu/xstate.h>
-#include <asm/trace/mpx.h>
-#include <asm/mpx.h>
 #include <asm/vm86.h>
 #include <asm/umip.h>
 #include <asm/insn.h>
@@ -436,8 +434,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign
 
 dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 {
-	const struct mpx_bndcsr *bndcsr;
-
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
 			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
@@ -447,76 +443,6 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 	if (!user_mode(regs))
 		die("bounds", regs, error_code);
 
-	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
-		/* The exception is not from Intel MPX */
-		goto exit_trap;
-	}
-
-	/*
-	 * We need to look at BNDSTATUS to resolve this exception.
-	 * A NULL here might mean that it is in its 'init state',
-	 * which is all zeros which indicates MPX was not
-	 * responsible for the exception.
-	 */
-	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
-	if (!bndcsr)
-		goto exit_trap;
-
-	trace_bounds_exception_mpx(bndcsr);
-	/*
-	 * The error code field of the BNDSTATUS register communicates status
-	 * information of a bound range exception #BR or operation involving
-	 * bound directory.
-	 */
-	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
-	case 2:	/* Bound directory has invalid entry. */
-		if (mpx_handle_bd_fault())
-			goto exit_trap;
-		break; /* Success, it was handled */
-	case 1: /* Bound violation. */
-	{
-		struct task_struct *tsk = current;
-		struct mpx_fault_info mpx;
-
-		if (mpx_fault_info(&mpx, regs)) {
-			/*
-			 * We failed to decode the MPX instruction.  Act as if
-			 * the exception was not caused by MPX.
-			 */
-			goto exit_trap;
-		}
-		/*
-		 * Success, we decoded the instruction and retrieved
-		 * an 'mpx' containing the address being accessed
-		 * which caused the exception.  This information
-		 * allows and application to possibly handle the
-		 * #BR exception itself.
-		 */
-		if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs,
-				       error_code))
-			break;
-
-		show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code);
-
-		force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper);
-		break;
-	}
-	case 0: /* No exception caused by Intel MPX operations. */
-		goto exit_trap;
-	default:
-		die("bounds", regs, error_code);
-	}
-
-	return;
-
-exit_trap:
-	/*
-	 * This path out is for all the cases where we could not
-	 * handle the exception in some way (like allocating a
-	 * table or telling userspace about it.  We will also end
-	 * up here if the kernel has MPX turned off at compile
-	 * time..
-	 */
 	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL);
 }
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index cf55629ff0ff..b1c469446b07 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -62,7 +62,7 @@ u64 kvm_supported_xcr0(void)
 	return xcr0;
 }
 
-#define F(x) bit(X86_FEATURE_##x)
+#define F feature_bit
 
 int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
@@ -281,8 +281,9 @@ out:
 	return r;
 }
 
-static void cpuid_mask(u32 *word, int wordnum)
+static __always_inline void cpuid_mask(u32 *word, int wordnum)
 {
+	reverse_cpuid_check(wordnum);
 	*word &= boot_cpu_data.x86_capability[wordnum];
 }
 
@@ -352,6 +353,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
 	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
 	unsigned f_la57;
+	unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0;
 
 	/* cpuid 7.0.ebx */
 	const u32 kvm_cpuid_7_0_ebx_x86_features =
@@ -363,7 +365,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
+		F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/;
@@ -392,6 +394,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 		/* Set LA57 based on hardware capability. */
 		entry->ecx |= f_la57;
 		entry->ecx |= f_umip;
+		entry->ecx |= f_pku;
 		/* PKU is not yet implemented for shadow paging. */
 		if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 			entry->ecx &= ~F(PKU);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index d78a61408243..7366c618aa04 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -53,15 +53,46 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_7_ECX]         = {         7, 0, CPUID_ECX},
 	[CPUID_8000_0007_EBX] = {0x80000007, 0, CPUID_EBX},
 	[CPUID_7_EDX]         = {         7, 0, CPUID_EDX},
+	[CPUID_7_1_EAX]       = {         7, 1, CPUID_EAX},
 };
 
-static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature)
+/*
+ * Reverse CPUID and its derivatives can only be used for hardware-defined
+ * feature words, i.e. words whose bits directly correspond to a CPUID leaf.
+ * Retrieving a feature bit or masking guest CPUID from a Linux-defined word
+ * is nonsensical as the bit number/mask is an arbitrary software-defined value
+ * and can't be used by KVM to query/control guest capabilities.  And obviously
+ * the leaf being queried must have an entry in the lookup table.
+ */
+static __always_inline void reverse_cpuid_check(unsigned x86_leaf)
 {
-	unsigned x86_leaf = x86_feature / 32;
-
+	BUILD_BUG_ON(x86_leaf == CPUID_LNX_1);
+	BUILD_BUG_ON(x86_leaf == CPUID_LNX_2);
+	BUILD_BUG_ON(x86_leaf == CPUID_LNX_3);
+	BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
 	BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
 	BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
+}
+
+/*
+ * Retrieve the bit mask from an X86_FEATURE_* definition.  Features contain
+ * the hardware defined bit number (stored in bits 4:0) and a software defined
+ * "word" (stored in bits 31:5).  The word is used to index into arrays of
+ * bit masks that hold the per-cpu feature capabilities, e.g. this_cpu_has().
+ */
+static __always_inline u32 __feature_bit(int x86_feature)
+{
+	reverse_cpuid_check(x86_feature / 32);
+	return 1 << (x86_feature & 31);
+}
 
+#define feature_bit(name)  __feature_bit(X86_FEATURE_##name)
+
+static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned x86_feature)
+{
+	unsigned x86_leaf = x86_feature / 32;
+
+	reverse_cpuid_check(x86_leaf);
 	return reverse_cpuid[x86_leaf];
 }
 
@@ -93,15 +124,11 @@ static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, unsigned x86_
 {
 	int *reg;
 
-	if (x86_feature == X86_FEATURE_XSAVE &&
-			!static_cpu_has(X86_FEATURE_XSAVE))
-		return false;
-
 	reg = guest_cpuid_get_register(vcpu, x86_feature);
 	if (!reg)
 		return false;
 
-	return *reg & bit(x86_feature);
+	return *reg & __feature_bit(x86_feature);
 }
 
 static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x86_feature)
@@ -110,7 +137,7 @@ static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, unsigned x8
 
 	reg = guest_cpuid_get_register(vcpu, x86_feature);
 	if (reg)
-		*reg &= ~bit(x86_feature);
+		*reg &= ~__feature_bit(x86_feature);
 }
 
 static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 952d1a4f4d7e..ddbc61984227 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -22,6 +22,7 @@
 #include "kvm_cache_regs.h"
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
+#include <asm/fpu/api.h>
 #include <asm/debugreg.h>
 #include <asm/nospec-branch.h>
 
@@ -310,7 +311,9 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
 #define ON64(x)
 #endif
 
-static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
+typedef void (*fastop_t)(struct fastop *);
+
+static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 
 #define __FOP_FUNC(name) \
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
@@ -1075,8 +1078,23 @@ static void fetch_register_operand(struct operand *op)
 	}
 }
 
-static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
+static void emulator_get_fpu(void)
+{
+	fpregs_lock();
+
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+}
+
+static void emulator_put_fpu(void)
 {
+	fpregs_unlock();
+}
+
+static void read_sse_reg(sse128_t *data, int reg)
+{
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1098,11 +1116,12 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 #endif
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
-static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
-			  int reg)
+static void write_sse_reg(sse128_t *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1124,10 +1143,12 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 #endif
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
-static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+static void read_mmx_reg(u64 *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1139,10 +1160,12 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
-static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+static void write_mmx_reg(u64 *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1154,6 +1177,7 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1161,7 +1185,9 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fninit");
+	emulator_put_fpu();
 	return X86EMUL_CONTINUE;
 }
 
@@ -1172,7 +1198,9 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fnstcw %0": "+m"(fcw));
+	emulator_put_fpu();
 
 	ctxt->dst.val = fcw;
 
@@ -1186,7 +1214,9 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fnstsw %0": "+m"(fsw));
+	emulator_put_fpu();
 
 	ctxt->dst.val = fsw;
 
@@ -1205,7 +1235,7 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 		op->type = OP_XMM;
 		op->bytes = 16;
 		op->addr.xmm = reg;
-		read_sse_reg(ctxt, &op->vec_val, reg);
+		read_sse_reg(&op->vec_val, reg);
 		return;
 	}
 	if (ctxt->d & Mmx) {
@@ -1256,7 +1286,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 			op->type = OP_XMM;
 			op->bytes = 16;
 			op->addr.xmm = ctxt->modrm_rm;
-			read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm);
+			read_sse_reg(&op->vec_val, ctxt->modrm_rm);
 			return rc;
 		}
 		if (ctxt->d & Mmx) {
@@ -1833,10 +1863,10 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
 				       op->bytes * op->count);
 		break;
 	case OP_XMM:
-		write_sse_reg(ctxt, &op->vec_val, op->addr.xmm);
+		write_sse_reg(&op->vec_val, op->addr.xmm);
 		break;
 	case OP_MM:
-		write_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
+		write_mmx_reg(&op->mm_val, op->addr.mm);
 		break;
 	case OP_NONE:
 		/* no writeback */
@@ -2348,12 +2378,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
 static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
 {
 #ifdef CONFIG_X86_64
-	u32 eax, ebx, ecx, edx;
-
-	eax = 0x80000001;
-	ecx = 0;
-	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
-	return edx & bit(X86_FEATURE_LM);
+	return ctxt->ops->guest_has_long_mode(ctxt);
 #else
 	return false;
 #endif
@@ -3618,18 +3643,11 @@ static int em_mov(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-#define FFL(x) bit(X86_FEATURE_##x)
-
 static int em_movbe(struct x86_emulate_ctxt *ctxt)
 {
-	u32 ebx, ecx, edx, eax = 1;
 	u16 tmp;
 
-	/*
-	 * Check MOVBE is set in the guest-visible CPUID leaf.
-	 */
-	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
-	if (!(ecx & FFL(MOVBE)))
+	if (!ctxt->ops->guest_has_movbe(ctxt))
 		return emulate_ud(ctxt);
 
 	switch (ctxt->op_bytes) {
@@ -4027,10 +4045,7 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 
 static int check_fxsr(struct x86_emulate_ctxt *ctxt)
 {
-	u32 eax = 1, ebx, ecx = 0, edx;
-
-	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
-	if (!(edx & FFL(FXSR)))
+	if (!ctxt->ops->guest_has_fxsr(ctxt))
 		return emulate_ud(ctxt);
 
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
@@ -4092,8 +4107,12 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	emulator_get_fpu();
+
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
+	emulator_put_fpu();
+
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4136,6 +4155,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	emulator_get_fpu();
+
 	if (size < __fxstate_size(16)) {
 		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
@@ -4151,6 +4172,8 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
+	emulator_put_fpu();
+
 	return rc;
 }
 
@@ -5210,16 +5233,28 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 				ctxt->ad_bytes = def_ad_bytes ^ 6;
 			break;
 		case 0x26:	/* ES override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_ES;
+			break;
 		case 0x2e:	/* CS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_CS;
+			break;
 		case 0x36:	/* SS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_SS;
+			break;
 		case 0x3e:	/* DS override */
 			has_seg_override = true;
-			ctxt->seg_override = (ctxt->b >> 3) & 3;
+			ctxt->seg_override = VCPU_SREG_DS;
 			break;
 		case 0x64:	/* FS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_FS;
+			break;
 		case 0x65:	/* GS override */
 			has_seg_override = true;
-			ctxt->seg_override = ctxt->b & 7;
+			ctxt->seg_override = VCPU_SREG_GS;
 			break;
 		case 0x40 ... 0x4f: /* REX */
 			if (mode != X86EMUL_MODE_PROT64)
@@ -5303,10 +5338,15 @@ done_prefixes:
 			}
 			break;
 		case Escape:
-			if (ctxt->modrm > 0xbf)
-				opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
-			else
+			if (ctxt->modrm > 0xbf) {
+				size_t size = ARRAY_SIZE(opcode.u.esc->high);
+				u32 index = array_index_nospec(
+					ctxt->modrm - 0xc0, size);
+
+				opcode = opcode.u.esc->high[index];
+			} else {
 				opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
+			}
 			break;
 		case InstrDual:
 			if ((ctxt->modrm >> 6) == 3)
@@ -5448,7 +5488,9 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
+	emulator_get_fpu();
 	rc = asm_safe("fwait");
+	emulator_put_fpu();
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
@@ -5456,14 +5498,13 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
-				       struct operand *op)
+static void fetch_possible_mmx_operand(struct operand *op)
 {
 	if (op->type == OP_MM)
-		read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
+		read_mmx_reg(&op->mm_val, op->addr.mm);
 }
 
-static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
+static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop)
 {
 	ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
 
@@ -5539,10 +5580,10 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 			 * Now that we know the fpu is exception safe, we can fetch
 			 * operands from it.
 			 */
-			fetch_possible_mmx_operand(ctxt, &ctxt->src);
-			fetch_possible_mmx_operand(ctxt, &ctxt->src2);
+			fetch_possible_mmx_operand(&ctxt->src);
+			fetch_possible_mmx_operand(&ctxt->src2);
 			if (!(ctxt->d & Mov))
-				fetch_possible_mmx_operand(ctxt, &ctxt->dst);
+				fetch_possible_mmx_operand(&ctxt->dst);
 		}
 
 		if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) {
@@ -5641,14 +5682,10 @@ special_insn:
 		ctxt->eflags &= ~X86_EFLAGS_RF;
 
 	if (ctxt->execute) {
-		if (ctxt->d & Fastop) {
-			void (*fop)(struct fastop *) = (void *)ctxt->execute;
-			rc = fastop(ctxt, fop);
-			if (rc != X86EMUL_CONTINUE)
-				goto done;
-			goto writeback;
-		}
-		rc = ctxt->execute(ctxt);
+		if (ctxt->d & Fastop)
+			rc = fastop(ctxt, (fastop_t)ctxt->execute);
+		else
+			rc = ctxt->execute(ctxt);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		goto writeback;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 23ff65504d7e..4df1c965bf1a 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -33,6 +33,7 @@
 #include <trace/events/kvm.h>
 
 #include "trace.h"
+#include "irq.h"
 
 #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
 
@@ -809,11 +810,12 @@ static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu,
 				     u32 index, u64 *pdata)
 {
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+	size_t size = ARRAY_SIZE(hv->hv_crash_param);
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+	if (WARN_ON_ONCE(index >= size))
 		return -EINVAL;
 
-	*pdata = hv->hv_crash_param[index];
+	*pdata = hv->hv_crash_param[array_index_nospec(index, size)];
 	return 0;
 }
 
@@ -852,11 +854,12 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
 				     u32 index, u64 data)
 {
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+	size_t size = ARRAY_SIZE(hv->hv_crash_param);
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+	if (WARN_ON_ONCE(index >= size))
 		return -EINVAL;
 
-	hv->hv_crash_param[index] = data;
+	hv->hv_crash_param[array_index_nospec(index, size)] = data;
 	return 0;
 }
 
@@ -1058,7 +1061,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 			return 1;
 		break;
 	default:
-		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+		vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
 		return 1;
 	}
@@ -1121,7 +1124,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 			return 1;
 
 		/*
-		 * Clear apic_assist portion of f(struct hv_vp_assist_page
+		 * Clear apic_assist portion of struct hv_vp_assist_page
 		 * only, there can be valuable data in the rest which needs
 		 * to be preserved e.g. on migration.
 		 */
@@ -1178,7 +1181,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 			return 1;
 		break;
 	default:
-		vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n",
+		vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n",
 			    msr, data);
 		return 1;
 	}
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 8b38bb4868a6..629a09ca9860 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -460,10 +460,14 @@ static int picdev_write(struct kvm_pic *s,
 	switch (addr) {
 	case 0x20:
 	case 0x21:
+		pic_lock(s);
+		pic_ioport_write(&s->pics[0], addr, data);
+		pic_unlock(s);
+		break;
 	case 0xa0:
 	case 0xa1:
 		pic_lock(s);
-		pic_ioport_write(&s->pics[addr >> 7], addr, data);
+		pic_ioport_write(&s->pics[1], addr, data);
 		pic_unlock(s);
 		break;
 	case 0x4d0:
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 9fd2dd89a1c5..26aa22cb9b29 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -36,6 +36,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/nospec.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/current.h>
@@ -68,13 +69,14 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 	default:
 		{
 			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
-			u64 redir_content;
+			u64 redir_content = ~0ULL;
 
-			if (redir_index < IOAPIC_NUM_PINS)
-				redir_content =
-					ioapic->redirtbl[redir_index].bits;
-			else
-				redir_content = ~0ULL;
+			if (redir_index < IOAPIC_NUM_PINS) {
+				u32 index = array_index_nospec(
+					redir_index, IOAPIC_NUM_PINS);
+
+				redir_content = ioapic->redirtbl[index].bits;
+			}
 
 			result = (ioapic->ioregsel & 0x1) ?
 			    (redir_content >> 32) & 0xffffffff :
@@ -108,8 +110,9 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 	union kvm_ioapic_redirect_entry *e;
 
 	e = &ioapic->redirtbl[RTC_GSI];
-	if (!kvm_apic_match_dest(vcpu, NULL, 0,	e->fields.dest_id,
-				e->fields.dest_mode))
+	if (!kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+				 e->fields.dest_id,
+				 kvm_lapic_irq_dest_mode(!!e->fields.dest_mode)))
 		return;
 
 	new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
@@ -188,7 +191,7 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 	/*
 	 * Return 0 for coalesced interrupts; for edge-triggered interrupts,
 	 * this only happens if a previous edge has not been delivered due
-	 * do masking.  For level interrupts, the remote_irr field tells
+	 * to masking.  For level interrupts, the remote_irr field tells
 	 * us if the interrupt is waiting for an EOI.
 	 *
 	 * RTC is special: it is edge-triggered, but userspace likes to know
@@ -250,8 +253,10 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
 		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
 		    index == RTC_GSI) {
-			if (kvm_apic_match_dest(vcpu, NULL, 0,
-			             e->fields.dest_id, e->fields.dest_mode) ||
+			u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
+
+			if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+						e->fields.dest_id, dm) ||
 			    kvm_apic_pending_eoi(vcpu, e->fields.vector))
 				__set_bit(e->fields.vector,
 					  ioapic_handled_vectors);
@@ -292,6 +297,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 
 		if (index >= IOAPIC_NUM_PINS)
 			return;
+		index = array_index_nospec(index, IOAPIC_NUM_PINS);
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
 		/* Preserve read-only fields */
@@ -327,11 +333,12 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		if (e->fields.delivery_mode == APIC_DM_FIXED) {
 			struct kvm_lapic_irq irq;
 
-			irq.shorthand = 0;
+			irq.shorthand = APIC_DEST_NOSHORT;
 			irq.vector = e->fields.vector;
 			irq.delivery_mode = e->fields.delivery_mode << 8;
 			irq.dest_id = e->fields.dest_id;
-			irq.dest_mode = e->fields.dest_mode;
+			irq.dest_mode =
+			    kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
 			bitmap_zero(&vcpu_bitmap, 16);
 			kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
 						 &vcpu_bitmap);
@@ -343,7 +350,9 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 				 * keep ioapic_handled_vectors synchronized.
 				 */
 				irq.dest_id = old_dest_id;
-				irq.dest_mode = old_dest_mode;
+				irq.dest_mode =
+				    kvm_lapic_irq_dest_mode(
+					!!e->fields.dest_mode);
 				kvm_bitmap_or_dest_vcpus(ioapic->kvm, &irq,
 							 &vcpu_bitmap);
 			}
@@ -369,11 +378,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 
 	irqe.dest_id = entry->fields.dest_id;
 	irqe.vector = entry->fields.vector;
-	irqe.dest_mode = entry->fields.dest_mode;
+	irqe.dest_mode = kvm_lapic_irq_dest_mode(!!entry->fields.dest_mode);
 	irqe.trig_mode = entry->fields.trig_mode;
 	irqe.delivery_mode = entry->fields.delivery_mode << 8;
 	irqe.level = 1;
-	irqe.shorthand = 0;
+	irqe.shorthand = APIC_DEST_NOSHORT;
 	irqe.msi_redir_hint = false;
 
 	if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index ea1a4e0297da..2fb2e3c80724 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -116,9 +116,6 @@ static inline int ioapic_in_kernel(struct kvm *kvm)
 }
 
 void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
-bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
-		int short_hand, unsigned int dest, int dest_mode);
-int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
 			int trigger_mode);
 int kvm_ioapic_init(struct kvm *kvm);
@@ -126,9 +123,6 @@ void kvm_ioapic_destroy(struct kvm *kvm);
 int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 		       int level, bool line_status);
 void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
-int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
-			     struct kvm_lapic_irq *irq,
-			     struct dest_map *dest_map);
 void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 7c6233d37c64..f173ab6b407e 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -113,5 +113,8 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu);
 
 int kvm_setup_default_irq_routing(struct kvm *kvm);
 int kvm_setup_empty_irq_routing(struct kvm *kvm);
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+			     struct kvm_lapic_irq *irq,
+			     struct dest_map *dest_map);
 
 #endif
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 8ecd48d31800..79afa0bb5f41 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -52,15 +52,15 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
 	unsigned int dest_vcpus = 0;
 
-	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
-			kvm_lowest_prio_delivery(irq)) {
+	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
+		return r;
+
+	if (irq->dest_mode == APIC_DEST_PHYSICAL &&
+	    irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) {
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
 		irq->delivery_mode = APIC_DM_FIXED;
 	}
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
-		return r;
-
 	memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -114,13 +114,14 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 		irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi);
 	irq->vector = (e->msi.data &
 			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
-	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq->dest_mode = kvm_lapic_irq_dest_mode(
+	    !!((1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo));
 	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
 	irq->delivery_mode = e->msi.data & 0x700;
 	irq->msi_redir_hint = ((e->msi.address_lo
 		& MSI_ADDR_REDIRECTION_LOWPRI) > 0);
 	irq->level = 1;
-	irq->shorthand = 0;
+	irq->shorthand = APIC_DEST_NOSHORT;
 }
 EXPORT_SYMBOL_GPL(kvm_set_msi_irq);
 
@@ -416,7 +417,8 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
+			if (irq.level &&
+			    kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
 						irq.dest_id, irq.dest_mode))
 				__set_bit(irq.vector, ioapic_handled_vectors);
 		}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index cf9177b4a07f..cce1e6b204c8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -56,9 +56,6 @@
 #define APIC_VERSION			(0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16))
 #define LAPIC_MMIO_LENGTH		(1 << 12)
 /* followed define is not in apicdef.h */
-#define APIC_SHORT_MASK			0xc0000
-#define APIC_DEST_NOSHORT		0x0
-#define APIC_DEST_MASK			0x800
 #define MAX_APIC_VECTOR			256
 #define APIC_VECTORS_PER_REG		32
 
@@ -792,13 +789,13 @@ static u32 kvm_apic_mda(struct kvm_vcpu *vcpu, unsigned int dest_id,
 }
 
 bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
-			   int short_hand, unsigned int dest, int dest_mode)
+			   int shorthand, unsigned int dest, int dest_mode)
 {
 	struct kvm_lapic *target = vcpu->arch.apic;
 	u32 mda = kvm_apic_mda(vcpu, dest, source, target);
 
 	ASSERT(target);
-	switch (short_hand) {
+	switch (shorthand) {
 	case APIC_DEST_NOSHORT:
 		if (dest_mode == APIC_DEST_PHYSICAL)
 			return kvm_apic_match_physical_addr(target, mda);
@@ -967,12 +964,12 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 }
 
 /*
- * This routine tries to handler interrupts in posted mode, here is how
+ * This routine tries to handle interrupts in posted mode, here is how
  * it deals with different cases:
  * - For single-destination interrupts, handle it in posted mode
  * - Else if vector hashing is enabled and it is a lowest-priority
  *   interrupt, handle it in posted mode and use the following mechanism
- *   to find the destinaiton vCPU.
+ *   to find the destination vCPU.
  *	1. For lowest-priority interrupts, store all the possible
  *	   destination vCPUs in an array.
  *	2. Use "guest vector % max number of destination vCPUs" to find
@@ -1151,7 +1148,7 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			if (!kvm_apic_present(vcpu))
 				continue;
 			if (!kvm_apic_match_dest(vcpu, NULL,
-						 irq->delivery_mode,
+						 irq->shorthand,
 						 irq->dest_id,
 						 irq->dest_mode))
 				continue;
@@ -1574,9 +1571,9 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	kvm_apic_local_deliver(apic, APIC_LVTT);
-	if (apic_lvtt_tscdeadline(apic))
+	if (apic_lvtt_tscdeadline(apic)) {
 		ktimer->tscdeadline = 0;
-	if (apic_lvtt_oneshot(apic)) {
+	} else if (apic_lvtt_oneshot(apic)) {
 		ktimer->tscdeadline = 0;
 		ktimer->target_expiration = 0;
 	}
@@ -1963,15 +1960,20 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
-	case APIC_LVTERR:
+	case APIC_LVTERR: {
 		/* TODO: Check vector */
+		size_t size;
+		u32 index;
+
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
-
-		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
+		size = ARRAY_SIZE(apic_lvt_mask);
+		index = array_index_nospec(
+				(reg - APIC_LVTT) >> 4, size);
+		val &= apic_lvt_mask[index];
 		kvm_lapic_set_reg(apic, reg, val);
-
 		break;
+	}
 
 	case APIC_LVTT:
 		if (!kvm_apic_sw_enabled(apic))
@@ -2373,14 +2375,13 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
 {
 	u32 lvt0 = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVT0);
-	int r = 0;
 
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
-		r = 1;
+		return 1;
 	if ((lvt0 & APIC_LVT_MASKED) == 0 &&
 	    GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT)
-		r = 1;
-	return r;
+		return 1;
+	return 0;
 }
 
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 39925afdfcdc..ec730ce7a344 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -10,8 +10,9 @@
 #define KVM_APIC_SIPI		1
 #define KVM_APIC_LVT_NUM	6
 
-#define KVM_APIC_SHORT_MASK	0xc0000
-#define KVM_APIC_DEST_MASK	0x800
+#define APIC_SHORT_MASK			0xc0000
+#define APIC_DEST_NOSHORT		0x0
+#define APIC_DEST_MASK			0x800
 
 #define APIC_BUS_CYCLE_NS       1
 #define APIC_BUS_FREQUENCY      (1000000000ULL / APIC_BUS_CYCLE_NS)
@@ -82,8 +83,8 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val);
 int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 		       void *data);
 bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
-			   int short_hand, unsigned int dest, int dest_mode);
-
+			   int shorthand, unsigned int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
 bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
 bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
 void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a32b847a8089..adc84f0f16ba 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -418,22 +418,24 @@ static inline bool is_access_track_spte(u64 spte)
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(18, 0)
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(17, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
 #define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
 						    MMIO_SPTE_GEN_LOW_START)
 
-#define MMIO_SPTE_GEN_HIGH_START	52
-#define MMIO_SPTE_GEN_HIGH_END		61
+#define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
+#define MMIO_SPTE_GEN_HIGH_END		62
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
+
 static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
+	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
 	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
 	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
@@ -444,8 +446,6 @@ static u64 get_mmio_spte_generation(u64 spte)
 {
 	u64 gen;
 
-	spte &= ~shadow_mmio_mask;
-
 	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
 	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
 	return gen;
@@ -538,16 +538,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 static u8 kvm_get_shadow_phys_bits(void)
 {
 	/*
-	 * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
-	 * in CPU detection code, but MKTME treats those reduced bits as
-	 * 'keyID' thus they are not reserved bits. Therefore for MKTME
-	 * we should still return physical address bits reported by CPUID.
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+	 * in CPU detection code, but the processor treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+	 * the physical address bits reported by CPUID.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_TME) ||
-	    WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
-		return boot_cpu_data.x86_phys_bits;
+	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+		return cpuid_eax(0x80000008) & 0xff;
 
-	return cpuid_eax(0x80000008) & 0xff;
+	/*
+	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+	 * custom CPUID.  Proceed with whatever the kernel found since these features
+	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+	 */
+	return boot_cpu_data.x86_phys_bits;
 }
 
 static void kvm_mmu_reset_all_pte_masks(void)
@@ -1260,56 +1264,6 @@ static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
 	list_del(&sp->lpage_disallowed_link);
 }
 
-static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
-					  struct kvm_memory_slot *slot)
-{
-	struct kvm_lpage_info *linfo;
-
-	if (slot) {
-		linfo = lpage_info_slot(gfn, slot, level);
-		return !!linfo->disallow_lpage;
-	}
-
-	return true;
-}
-
-static bool mmu_gfn_lpage_is_disallowed(struct kvm_vcpu *vcpu, gfn_t gfn,
-					int level)
-{
-	struct kvm_memory_slot *slot;
-
-	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
-}
-
-static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
-{
-	unsigned long page_size;
-	int i, ret = 0;
-
-	page_size = kvm_host_page_size(kvm, gfn);
-
-	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
-		if (page_size >= KVM_HPAGE_SIZE(i))
-			ret = i;
-		else
-			break;
-	}
-
-	return ret;
-}
-
-static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot,
-					  bool no_dirty_log)
-{
-	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
-		return false;
-	if (no_dirty_log && slot->dirty_bitmap)
-		return false;
-
-	return true;
-}
-
 static struct kvm_memory_slot *
 gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 			    bool no_dirty_log)
@@ -1317,40 +1271,14 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 	struct kvm_memory_slot *slot;
 
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	if (!memslot_valid_for_gpte(slot, no_dirty_log))
-		slot = NULL;
+	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+		return NULL;
+	if (no_dirty_log && slot->dirty_bitmap)
+		return NULL;
 
 	return slot;
 }
 
-static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn,
-			 bool *force_pt_level)
-{
-	int host_level, level, max_level;
-	struct kvm_memory_slot *slot;
-
-	if (unlikely(*force_pt_level))
-		return PT_PAGE_TABLE_LEVEL;
-
-	slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn);
-	*force_pt_level = !memslot_valid_for_gpte(slot, true);
-	if (unlikely(*force_pt_level))
-		return PT_PAGE_TABLE_LEVEL;
-
-	host_level = host_mapping_level(vcpu->kvm, large_gfn);
-
-	if (host_level == PT_PAGE_TABLE_LEVEL)
-		return host_level;
-
-	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
-
-	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
-		if (__mmu_gfn_lpage_is_disallowed(large_gfn, level, slot))
-			break;
-
-	return level - 1;
-}
-
 /*
  * About rmap_head encoding:
  *
@@ -1410,7 +1338,7 @@ pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head,
 	if (j != 0)
 		return;
 	if (!prev_desc && !desc->more)
-		rmap_head->val = (unsigned long)desc->sptes[0];
+		rmap_head->val = 0;
 	else
 		if (prev_desc)
 			prev_desc->more = desc->more;
@@ -1525,7 +1453,7 @@ struct rmap_iterator {
 /*
  * Iteration must be started by this function.  This should also be used after
  * removing/dropping sptes from the rmap link because in such cases the
- * information in the itererator may not be valid.
+ * information in the iterator may not be valid.
  *
  * Returns sptep if found, NULL otherwise.
  */
@@ -2899,6 +2827,26 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
 	return kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
 }
 
+static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
+{
+	LIST_HEAD(invalid_list);
+
+	if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES))
+		return 0;
+
+	while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) {
+		if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list))
+			break;
+
+		++vcpu->kvm->stat.mmu_recycled;
+	}
+	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
+
+	if (!kvm_mmu_available_pages(vcpu->kvm))
+		return -ENOSPC;
+	return 0;
+}
+
 /*
  * Changing the number of mmu pages allocated to the vm
  * Note: if goal_nr_mmu_pages is too small, you will get dead lock
@@ -3099,17 +3047,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	spte |= (u64)pfn << PAGE_SHIFT;
 
 	if (pte_access & ACC_WRITE_MASK) {
-
-		/*
-		 * Other vcpu creates new sp in the window between
-		 * mapping_level() and acquiring mmu-lock. We can
-		 * allow guest to retry the access, the mapping can
-		 * be fixed if guest refault.
-		 */
-		if (level > PT_PAGE_TABLE_LEVEL &&
-		    mmu_gfn_lpage_is_disallowed(vcpu, gfn, level))
-			goto done;
-
 		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
 
 		/*
@@ -3141,7 +3078,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 set_pte:
 	if (mmu_spte_update(sptep, spte))
 		ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
-done:
 	return ret;
 }
 
@@ -3294,6 +3230,83 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
+static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
+				  kvm_pfn_t pfn, struct kvm_memory_slot *slot)
+{
+	unsigned long hva;
+	pte_t *pte;
+	int level;
+
+	BUILD_BUG_ON(PT_PAGE_TABLE_LEVEL != (int)PG_LEVEL_4K ||
+		     PT_DIRECTORY_LEVEL != (int)PG_LEVEL_2M ||
+		     PT_PDPE_LEVEL != (int)PG_LEVEL_1G);
+
+	if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn))
+		return PT_PAGE_TABLE_LEVEL;
+
+	/*
+	 * Note, using the already-retrieved memslot and __gfn_to_hva_memslot()
+	 * is not solely for performance, it's also necessary to avoid the
+	 * "writable" check in __gfn_to_hva_many(), which will always fail on
+	 * read-only memslots due to gfn_to_hva() assuming writes.  Earlier
+	 * page fault steps have already verified the guest isn't writing a
+	 * read-only memslot.
+	 */
+	hva = __gfn_to_hva_memslot(slot, gfn);
+
+	pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level);
+	if (unlikely(!pte))
+		return PT_PAGE_TABLE_LEVEL;
+
+	return level;
+}
+
+static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
+				   int max_level, kvm_pfn_t *pfnp)
+{
+	struct kvm_memory_slot *slot;
+	struct kvm_lpage_info *linfo;
+	kvm_pfn_t pfn = *pfnp;
+	kvm_pfn_t mask;
+	int level;
+
+	if (unlikely(max_level == PT_PAGE_TABLE_LEVEL))
+		return PT_PAGE_TABLE_LEVEL;
+
+	if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn))
+		return PT_PAGE_TABLE_LEVEL;
+
+	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true);
+	if (!slot)
+		return PT_PAGE_TABLE_LEVEL;
+
+	max_level = min(max_level, kvm_x86_ops->get_lpage_level());
+	for ( ; max_level > PT_PAGE_TABLE_LEVEL; max_level--) {
+		linfo = lpage_info_slot(gfn, slot, max_level);
+		if (!linfo->disallow_lpage)
+			break;
+	}
+
+	if (max_level == PT_PAGE_TABLE_LEVEL)
+		return PT_PAGE_TABLE_LEVEL;
+
+	level = host_pfn_mapping_level(vcpu, gfn, pfn, slot);
+	if (level == PT_PAGE_TABLE_LEVEL)
+		return level;
+
+	level = min(level, max_level);
+
+	/*
+	 * mmu_notifier_retry() was successful and mmu_lock is held, so
+	 * the pmd can't be split from under us.
+	 */
+	mask = KVM_PAGES_PER_HPAGE(level) - 1;
+	VM_BUG_ON((gfn & mask) != (pfn & mask));
+	*pfnp = pfn & ~mask;
+
+	return level;
+}
+
 static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
 				       gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
 {
@@ -3318,18 +3331,20 @@ static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
 }
 
 static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
-			int map_writable, int level, kvm_pfn_t pfn,
-			bool prefault, bool lpage_disallowed)
+			int map_writable, int max_level, kvm_pfn_t pfn,
+			bool prefault, bool account_disallowed_nx_lpage)
 {
 	struct kvm_shadow_walk_iterator it;
 	struct kvm_mmu_page *sp;
-	int ret;
+	int level, ret;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	gfn_t base_gfn = gfn;
 
-	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
+	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
 		return RET_PF_RETRY;
 
+	level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn);
+
 	trace_kvm_mmu_spte_requested(gpa, level, pfn);
 	for_each_shadow_entry(vcpu, gpa, it) {
 		/*
@@ -3348,7 +3363,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 					      it.level - 1, true, ACC_ALL);
 
 			link_shadow_page(vcpu, it.sptep, sp);
-			if (lpage_disallowed)
+			if (account_disallowed_nx_lpage)
 				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
@@ -3384,45 +3399,6 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
 	return -EFAULT;
 }
 
-static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
-					gfn_t gfn, kvm_pfn_t *pfnp,
-					int *levelp)
-{
-	kvm_pfn_t pfn = *pfnp;
-	int level = *levelp;
-
-	/*
-	 * Check if it's a transparent hugepage. If this would be an
-	 * hugetlbfs page, level wouldn't be set to
-	 * PT_PAGE_TABLE_LEVEL and there would be no adjustment done
-	 * here.
-	 */
-	if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
-	    !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
-	    PageTransCompoundMap(pfn_to_page(pfn)) &&
-	    !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
-		unsigned long mask;
-		/*
-		 * mmu_notifier_retry was successful and we hold the
-		 * mmu_lock here, so the pmd can't become splitting
-		 * from under us, and in turn
-		 * __split_huge_page_refcount() can't run from under
-		 * us and we can safely transfer the refcount from
-		 * PG_tail to PG_head as we switch the pfn to tail to
-		 * head.
-		 */
-		*levelp = level = PT_DIRECTORY_LEVEL;
-		mask = KVM_PAGES_PER_HPAGE(level) - 1;
-		VM_BUG_ON((gfn & mask) != (pfn & mask));
-		if (pfn & mask) {
-			kvm_release_pfn_clean(pfn);
-			pfn &= ~mask;
-			kvm_get_pfn(pfn);
-			*pfnp = pfn;
-		}
-	}
-}
-
 static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 				kvm_pfn_t pfn, unsigned access, int *ret_val)
 {
@@ -3528,7 +3504,7 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte)
  * - true: let the vcpu to access on the same address again.
  * - false: let the real page fault path to fix it.
  */
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
+static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
@@ -3537,9 +3513,6 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	u64 spte = 0ull;
 	uint retry_count = 0;
 
-	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
-		return false;
-
 	if (!page_fault_can_be_fast(error_code))
 		return false;
 
@@ -3548,9 +3521,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 	do {
 		u64 new_spte;
 
-		for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
-			if (!is_shadow_present_pte(spte) ||
-			    iterator.level < level)
+		for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
+			if (!is_shadow_present_pte(spte))
 				break;
 
 		sp = page_header(__pa(iterator.sptep));
@@ -3626,71 +3598,13 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
 
 	} while (true);
 
-	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
+	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
 			      spte, fault_handled);
 	walk_shadow_page_lockless_end(vcpu);
 
 	return fault_handled;
 }
 
-static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
-static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
-
-static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
-			 gfn_t gfn, bool prefault)
-{
-	int r;
-	int level;
-	bool force_pt_level;
-	kvm_pfn_t pfn;
-	unsigned long mmu_seq;
-	bool map_writable, write = error_code & PFERR_WRITE_MASK;
-	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
-				is_nx_huge_page_enabled();
-
-	force_pt_level = lpage_disallowed;
-	level = mapping_level(vcpu, gfn, &force_pt_level);
-	if (likely(!force_pt_level)) {
-		/*
-		 * This path builds a PAE pagetable - so we can map
-		 * 2mb pages at maximum. Therefore check if the level
-		 * is larger than that.
-		 */
-		if (level > PT_DIRECTORY_LEVEL)
-			level = PT_DIRECTORY_LEVEL;
-
-		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
-	}
-
-	if (fast_page_fault(vcpu, v, level, error_code))
-		return RET_PF_RETRY;
-
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
-	smp_rmb();
-
-	if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
-		return RET_PF_RETRY;
-
-	if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
-		return r;
-
-	r = RET_PF_RETRY;
-	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
-		goto out_unlock;
-	if (make_mmu_pages_available(vcpu) < 0)
-		goto out_unlock;
-	if (likely(!force_pt_level))
-		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
-			 prefault, false);
-out_unlock:
-	spin_unlock(&vcpu->kvm->mmu_lock);
-	kvm_release_pfn_clean(pfn);
-	return r;
-}
-
 static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 			       struct list_head *invalid_list)
 {
@@ -3981,7 +3895,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				  u32 access, struct x86_exception *exception)
 {
 	if (exception)
@@ -3989,7 +3903,7 @@ static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
 	return vaddr;
 }
 
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
 					 u32 access,
 					 struct x86_exception *exception)
 {
@@ -4001,20 +3915,14 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
 static bool
 __is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level)
 {
-	int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f;
+	int bit7 = (pte >> 7) & 1;
 
-	return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) |
-		((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0);
+	return pte & rsvd_check->rsvd_bits_mask[bit7][level-1];
 }
 
-static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
+static bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, u64 pte)
 {
-	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level);
-}
-
-static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level)
-{
-	return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level);
+	return rsvd_check->bad_mt_xwr & BIT_ULL(pte & 0x3f);
 }
 
 static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
@@ -4038,11 +3946,11 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	u64 sptes[PT64_ROOT_MAX_LEVEL], spte = 0ull;
+	struct rsvd_bits_validate *rsvd_check;
 	int root, leaf;
 	bool reserved = false;
 
-	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
-		goto exit;
+	rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
 
 	walk_shadow_page_lockless_begin(vcpu);
 
@@ -4058,8 +3966,13 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 		if (!is_shadow_present_pte(spte))
 			break;
 
-		reserved |= is_shadow_zero_bits_set(vcpu->arch.mmu, spte,
-						    iterator.level);
+		/*
+		 * Use a bitwise-OR instead of a logical-OR to aggregate the
+		 * reserved bit and EPT's invalid memtype/XWR checks to avoid
+		 * adding a Jcc in the loop.
+		 */
+		reserved |= __is_bad_mt_xwr(rsvd_check, spte) |
+			    __is_rsvd_bits_set(rsvd_check, spte, iterator.level);
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -4073,7 +3986,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 			root--;
 		}
 	}
-exit:
+
 	*sptep = spte;
 	return reserved;
 }
@@ -4137,9 +4050,6 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	struct kvm_shadow_walk_iterator iterator;
 	u64 spte;
 
-	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
-		return;
-
 	walk_shadow_page_lockless_begin(vcpu);
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
 		clear_sp_write_flooding_count(iterator.sptep);
@@ -4149,29 +4059,8 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr)
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
-				u32 error_code, bool prefault)
-{
-	gfn_t gfn = gva >> PAGE_SHIFT;
-	int r;
-
-	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
-
-	if (page_fault_handle_page_track(vcpu, error_code, gfn))
-		return RET_PF_EMULATE;
-
-	r = mmu_topup_memory_caches(vcpu);
-	if (r)
-		return r;
-
-	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
-
-
-	return nonpaging_map(vcpu, gva & PAGE_MASK,
-			     error_code, gfn, prefault);
-}
-
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				   gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
@@ -4180,11 +4069,13 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable)
 {
 	struct kvm_memory_slot *slot;
 	bool async;
@@ -4204,12 +4095,12 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 		return false; /* *pfn has correct page already */
 
 	if (!prefault && kvm_can_do_async_pf(vcpu)) {
-		trace_kvm_try_async_get_page(gva, gfn);
+		trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
-			trace_kvm_async_pf_doublefault(gva, gfn);
+			trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return true;
-		} else if (kvm_arch_setup_async_pf(vcpu, gva, gfn))
+		} else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
 			return true;
 	}
 
@@ -4217,11 +4108,77 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	return false;
 }
 
+static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
+			     bool prefault, int max_level, bool is_tdp)
+{
+	bool write = error_code & PFERR_WRITE_MASK;
+	bool exec = error_code & PFERR_FETCH_MASK;
+	bool lpage_disallowed = exec && is_nx_huge_page_enabled();
+	bool map_writable;
+
+	gfn_t gfn = gpa >> PAGE_SHIFT;
+	unsigned long mmu_seq;
+	kvm_pfn_t pfn;
+	int r;
+
+	if (page_fault_handle_page_track(vcpu, error_code, gfn))
+		return RET_PF_EMULATE;
+
+	r = mmu_topup_memory_caches(vcpu);
+	if (r)
+		return r;
+
+	if (lpage_disallowed)
+		max_level = PT_PAGE_TABLE_LEVEL;
+
+	if (fast_page_fault(vcpu, gpa, error_code))
+		return RET_PF_RETRY;
+
+	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
+		return RET_PF_RETRY;
+
+	if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r))
+		return r;
+
+	r = RET_PF_RETRY;
+	spin_lock(&vcpu->kvm->mmu_lock);
+	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
+		goto out_unlock;
+	if (make_mmu_pages_available(vcpu) < 0)
+		goto out_unlock;
+	r = __direct_map(vcpu, gpa, write, map_writable, max_level, pfn,
+			 prefault, is_tdp && lpage_disallowed);
+
+out_unlock:
+	spin_unlock(&vcpu->kvm->mmu_lock);
+	kvm_release_pfn_clean(pfn);
+	return r;
+}
+
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
+				u32 error_code, bool prefault)
+{
+	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
+
+	/* This path builds a PAE pagetable, we can map 2mb pages at maximum. */
+	return direct_page_fault(vcpu, gpa & PAGE_MASK, error_code, prefault,
+				 PT_DIRECTORY_LEVEL, false);
+}
+
 int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 				u64 fault_address, char *insn, int insn_len)
 {
 	int r = 1;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
+	if (WARN_ON_ONCE(fault_address >> 32))
+		return -EFAULT;
+#endif
+
 	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
@@ -4249,76 +4206,23 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 }
 EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
 
-static bool
-check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
-{
-	int page_num = KVM_PAGES_PER_HPAGE(level);
-
-	gfn &= ~(page_num - 1);
-
-	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
-}
-
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			  bool prefault)
 {
-	kvm_pfn_t pfn;
-	int r;
-	int level;
-	bool force_pt_level;
-	gfn_t gfn = gpa >> PAGE_SHIFT;
-	unsigned long mmu_seq;
-	int write = error_code & PFERR_WRITE_MASK;
-	bool map_writable;
-	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
-				is_nx_huge_page_enabled();
-
-	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
+	int max_level;
 
-	if (page_fault_handle_page_track(vcpu, error_code, gfn))
-		return RET_PF_EMULATE;
+	for (max_level = PT_MAX_HUGEPAGE_LEVEL;
+	     max_level > PT_PAGE_TABLE_LEVEL;
+	     max_level--) {
+		int page_num = KVM_PAGES_PER_HPAGE(max_level);
+		gfn_t base = (gpa >> PAGE_SHIFT) & ~(page_num - 1);
 
-	r = mmu_topup_memory_caches(vcpu);
-	if (r)
-		return r;
-
-	force_pt_level =
-		lpage_disallowed ||
-		!check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
-	level = mapping_level(vcpu, gfn, &force_pt_level);
-	if (likely(!force_pt_level)) {
-		if (level > PT_DIRECTORY_LEVEL &&
-		    !check_hugepage_cache_consistency(vcpu, gfn, level))
-			level = PT_DIRECTORY_LEVEL;
-		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
+		if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num))
+			break;
 	}
 
-	if (fast_page_fault(vcpu, gpa, level, error_code))
-		return RET_PF_RETRY;
-
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
-	smp_rmb();
-
-	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
-		return RET_PF_RETRY;
-
-	if (handle_abnormal_pfn(vcpu, 0, gfn, pfn, ACC_ALL, &r))
-		return r;
-
-	r = RET_PF_RETRY;
-	spin_lock(&vcpu->kvm->mmu_lock);
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
-		goto out_unlock;
-	if (make_mmu_pages_available(vcpu) < 0)
-		goto out_unlock;
-	if (likely(!force_pt_level))
-		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
-			 prefault, lpage_disallowed);
-out_unlock:
-	spin_unlock(&vcpu->kvm->mmu_lock);
-	kvm_release_pfn_clean(pfn);
-	return r;
+	return direct_page_fault(vcpu, gpa, error_code, prefault,
+				 max_level, true);
 }
 
 static void nonpaging_init_context(struct kvm_vcpu *vcpu,
@@ -5496,47 +5400,30 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
 
-static int make_mmu_pages_available(struct kvm_vcpu *vcpu)
-{
-	LIST_HEAD(invalid_list);
-
-	if (likely(kvm_mmu_available_pages(vcpu->kvm) >= KVM_MIN_FREE_MMU_PAGES))
-		return 0;
-
-	while (kvm_mmu_available_pages(vcpu->kvm) < KVM_REFILL_PAGES) {
-		if (!prepare_zap_oldest_mmu_page(vcpu->kvm, &invalid_list))
-			break;
-
-		++vcpu->kvm->stat.mmu_recycled;
-	}
-	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
-
-	if (!kvm_mmu_available_pages(vcpu->kvm))
-		return -ENOSPC;
-	return 0;
-}
-
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = 0;
 	bool direct = vcpu->arch.mmu->direct_map;
 
+	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
+		return RET_PF_RETRY;
+
 	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
 	if (vcpu->arch.mmu->direct_map) {
 		vcpu->arch.gpa_available = true;
-		vcpu->arch.gpa_val = cr2;
+		vcpu->arch.gpa_val = cr2_or_gpa;
 	}
 
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, cr2, direct);
+		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
 					       lower_32_bits(error_code),
 					       false);
 		WARN_ON(r == RET_PF_INVALID);
@@ -5556,7 +5443,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 */
 	if (vcpu->arch.mmu->direct_map &&
 	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
-		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
 		return 1;
 	}
 
@@ -5571,7 +5458,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	 * explicitly shadowing L1's page tables, i.e. unprotecting something
 	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
 	 */
-	if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu))
+	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
 		emulation_type = EMULTYPE_ALLOW_RETRY;
 emulate:
 	/*
@@ -5586,7 +5473,7 @@ emulate:
 			return 1;
 	}
 
-	return x86_emulate_instruction(vcpu, cr2, emulation_type, insn,
+	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
 				       insn_len);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
@@ -6015,8 +5902,8 @@ restart:
 		 * mapping if the indirect sp has level = 1.
 		 */
 		if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
-		    !kvm_is_zone_device_pfn(pfn) &&
-		    PageTransCompoundMap(pfn_to_page(pfn))) {
+		    (kvm_is_zone_device_pfn(pfn) ||
+		     PageCompound(pfn_to_page(pfn)))) {
 			pte_list_remove(rmap_head, sptep);
 
 			if (kvm_available_flush_tlb_with_range())
@@ -6249,7 +6136,7 @@ static void kvm_set_mmio_spte_mask(void)
 	 * If reserved bit is not supported, clear the present bit to disable
 	 * mmio page fault.
 	 */
-	if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52)
+	if (shadow_phys_bits == 52)
 		mask &= ~1ull;
 
 	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 97b21e7fd013..4e1ef0473663 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -128,6 +128,21 @@ static inline int FNAME(is_present_gpte)(unsigned long pte)
 #endif
 }
 
+static bool FNAME(is_bad_mt_xwr)(struct rsvd_bits_validate *rsvd_check, u64 gpte)
+{
+#if PTTYPE != PTTYPE_EPT
+	return false;
+#else
+	return __is_bad_mt_xwr(rsvd_check, gpte);
+#endif
+}
+
+static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+	return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level) ||
+	       FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte);
+}
+
 static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			       pt_element_t __user *ptep_user, unsigned index,
 			       pt_element_t orig_pte, pt_element_t new_pte)
@@ -175,9 +190,6 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu_page *sp, u64 *spte,
 				  u64 gpte)
 {
-	if (is_rsvd_bits_set(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
-		goto no_present;
-
 	if (!FNAME(is_present_gpte)(gpte))
 		goto no_present;
 
@@ -186,6 +198,9 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 	    !(gpte & PT_GUEST_ACCESSED_MASK))
 		goto no_present;
 
+	if (FNAME(is_rsvd_bits_set)(vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+		goto no_present;
+
 	return false;
 
 no_present:
@@ -291,11 +306,11 @@ static inline unsigned FNAME(gpte_pkeys)(struct kvm_vcpu *vcpu, u64 gpte)
 }
 
 /*
- * Fetch a guest pte for a guest virtual address
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
  */
 static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				    gva_t addr, u32 access)
+				    gpa_t addr, u32 access)
 {
 	int ret;
 	pt_element_t pte;
@@ -400,7 +415,7 @@ retry_walk:
 		if (unlikely(!FNAME(is_present_gpte)(pte)))
 			goto error;
 
-		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
+		if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, walker->level))) {
 			errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
@@ -496,7 +511,7 @@ error:
 }
 
 static int FNAME(walk_addr)(struct guest_walker *walker,
-			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
+			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
 {
 	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);
@@ -611,17 +626,17 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * If the guest tries to write a write-protected page, we need to
  * emulate this operation, return 1 to indicate this case.
  */
-static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			 struct guest_walker *gw,
-			 int write_fault, int hlevel,
+			 int write_fault, int max_level,
 			 kvm_pfn_t pfn, bool map_writable, bool prefault,
 			 bool lpage_disallowed)
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
-	int top_level, ret;
-	gfn_t gfn, base_gfn;
+	int top_level, hlevel, ret;
+	gfn_t base_gfn = gw->gfn;
 
 	direct_access = gw->pte_access;
 
@@ -637,7 +652,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	if (FNAME(gpte_changed)(vcpu, gw, top_level))
 		goto out_gpte_changed;
 
-	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa))
+	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
 		goto out_gpte_changed;
 
 	for (shadow_walk_init(&it, vcpu, addr);
@@ -666,12 +681,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	/*
-	 * FNAME(page_fault) might have clobbered the bottom bits of
-	 * gw->gfn, restore them from the virtual address.
-	 */
-	gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
-	base_gfn = gfn;
+	hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn);
 
 	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
 
@@ -682,9 +692,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 		 * We cannot overwrite existing page tables with an NX
 		 * large page, as the leaf could be executable.
 		 */
-		disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
+		disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel);
 
-		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
+		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == hlevel)
 			break;
 
@@ -765,7 +775,7 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
@@ -773,12 +783,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	struct guest_walker walker;
 	int r;
 	kvm_pfn_t pfn;
-	int level = PT_PAGE_TABLE_LEVEL;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
 	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
 				is_nx_huge_page_enabled();
-	bool force_pt_level = lpage_disallowed;
+	int max_level;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -818,14 +827,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
 	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
 
-	if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) {
-		level = mapping_level(vcpu, walker.gfn, &force_pt_level);
-		if (likely(!force_pt_level)) {
-			level = min(walker.level, level);
-			walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1);
-		}
-	} else
-		force_pt_level = true;
+	if (lpage_disallowed || is_self_change_mapping)
+		max_level = PT_PAGE_TABLE_LEVEL;
+	else
+		max_level = walker.level;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
@@ -865,10 +870,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
 	if (make_mmu_pages_available(vcpu) < 0)
 		goto out_unlock;
-	if (!force_pt_level)
-		transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
-	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
-			 level, pfn, map_writable, prefault, lpage_disallowed);
+	r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn,
+			 map_writable, prefault, lpage_disallowed);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:
@@ -945,18 +948,19 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 
@@ -964,7 +968,8 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
 }
 
 #if PTTYPE != PTTYPE_EPT
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
+/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
+static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
 {
@@ -972,6 +977,11 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit GVA should be impossible on 32-bit KVM. */
+	WARN_ON_ONCE(vaddr >> 32);
+#endif
+
 	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
 
 	if (r) {
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 7ca8831c7d1a..3c6522b84ff1 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -249,13 +249,13 @@ TRACE_EVENT(
 
 TRACE_EVENT(
 	fast_page_fault,
-	TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+	TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,
 		 u64 *sptep, u64 old_spte, bool retry),
-	TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry),
+	TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry),
 
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
-		__field(gva_t, gva)
+		__field(gpa_t, cr2_or_gpa)
 		__field(u32, error_code)
 		__field(u64 *, sptep)
 		__field(u64, old_spte)
@@ -265,7 +265,7 @@ TRACE_EVENT(
 
 	TP_fast_assign(
 		__entry->vcpu_id = vcpu->vcpu_id;
-		__entry->gva = gva;
+		__entry->cr2_or_gpa = cr2_or_gpa;
 		__entry->error_code = error_code;
 		__entry->sptep = sptep;
 		__entry->old_spte = old_spte;
@@ -273,9 +273,9 @@ TRACE_EVENT(
 		__entry->retry = retry;
 	),
 
-	TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx"
+	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
 		  " new %llx spurious %d fixed %d", __entry->vcpu_id,
-		  __entry->gva, __print_flags(__entry->error_code, "|",
+		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
 		  kvm_mmu_trace_pferr_flags), __entry->sptep,
 		  __entry->old_spte, __entry->new_spte,
 		  __spte_satisfied(old_spte), __spte_satisfied(new_spte)
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 25ce3edd1872..7f0059aa30e1 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -192,11 +192,15 @@ static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit)
 		break;
 	case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000:
 		*seg = 1;
-		*unit = msr - MSR_MTRRfix16K_80000;
+		*unit = array_index_nospec(
+			msr - MSR_MTRRfix16K_80000,
+			MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1);
 		break;
 	case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
 		*seg = 2;
-		*unit = msr - MSR_MTRRfix4K_C0000;
+		*unit = array_index_nospec(
+			msr - MSR_MTRRfix4K_C0000,
+			MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1);
 		break;
 	default:
 		return false;
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7ebb62326c14..13332984b6d5 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -2,6 +2,8 @@
 #ifndef __KVM_X86_PMU_H
 #define __KVM_X86_PMU_H
 
+#include <linux/nospec.h>
+
 #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu)
 #define pmu_to_vcpu(pmu)  (container_of((pmu), struct kvm_vcpu, arch.pmu))
 #define pmc_to_pmu(pmc)   (&(pmc)->vcpu->arch.pmu)
@@ -102,8 +104,12 @@ static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu,
 static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
 					 u32 base)
 {
-	if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
-		return &pmu->gp_counters[msr - base];
+	if (msr >= base && msr < base + pmu->nr_arch_gp_counters) {
+		u32 index = array_index_nospec(msr - base,
+					       pmu->nr_arch_gp_counters);
+
+		return &pmu->gp_counters[index];
+	}
 
 	return NULL;
 }
@@ -113,8 +119,12 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr)
 {
 	int base = MSR_CORE_PERF_FIXED_CTR0;
 
-	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
-		return &pmu->fixed_counters[msr - base];
+	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) {
+		u32 index = array_index_nospec(msr - base,
+					       pmu->nr_arch_fixed_counters);
+
+		return &pmu->fixed_counters[index];
+	}
 
 	return NULL;
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 122d4ce3b1ab..9dbb990c319a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1307,6 +1307,47 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * The default MMIO mask is a single bit (excluding the present bit),
+ * which could conflict with the memory encryption bit. Check for
+ * memory encryption support and override the default MMIO mask if
+ * memory encryption is enabled.
+ */
+static __init void svm_adjust_mmio_mask(void)
+{
+	unsigned int enc_bit, mask_bit;
+	u64 msr, mask;
+
+	/* If there is no memory encryption support, use existing mask */
+	if (cpuid_eax(0x80000000) < 0x8000001f)
+		return;
+
+	/* If memory encryption is not enabled, use existing mask */
+	rdmsrl(MSR_K8_SYSCFG, msr);
+	if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+		return;
+
+	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
+	mask_bit = boot_cpu_data.x86_phys_bits;
+
+	/* Increment the mask bit if it is the same as the encryption bit */
+	if (enc_bit == mask_bit)
+		mask_bit++;
+
+	/*
+	 * If the mask bit location is below 52, then some bits above the
+	 * physical addressing limit will always be reserved, so use the
+	 * rsvd_bits() function to generate the mask. This mask, along with
+	 * the present bit, will be used to generate a page fault with
+	 * PFER.RSV = 1.
+	 *
+	 * If the mask bit location is 52 (or above), then clear the mask.
+	 */
+	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -1361,6 +1402,8 @@ static __init int svm_hardware_setup(void)
 		}
 	}
 
+	svm_adjust_mmio_mask();
+
 	for_each_possible_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
@@ -2144,7 +2187,7 @@ static int avic_init_vcpu(struct vcpu_svm *svm)
 	return ret;
 }
 
-static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
+static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
 	struct page *page;
@@ -2153,39 +2196,13 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	struct page *nested_msrpm_pages;
 	int err;
 
-	BUILD_BUG_ON_MSG(offsetof(struct vcpu_svm, vcpu) != 0,
-		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
-
-	svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
-	if (!svm) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
-						     GFP_KERNEL_ACCOUNT);
-	if (!svm->vcpu.arch.user_fpu) {
-		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
-		err = -ENOMEM;
-		goto free_partial_svm;
-	}
-
-	svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
-						     GFP_KERNEL_ACCOUNT);
-	if (!svm->vcpu.arch.guest_fpu) {
-		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
-		err = -ENOMEM;
-		goto free_user_fpu;
-	}
-
-	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
-	if (err)
-		goto free_svm;
+	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
+	svm = to_svm(vcpu);
 
 	err = -ENOMEM;
 	page = alloc_page(GFP_KERNEL_ACCOUNT);
 	if (!page)
-		goto uninit;
+		goto out;
 
 	msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
@@ -2222,9 +2239,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
-	svm_init_osvw(&svm->vcpu);
+	svm_init_osvw(vcpu);
 
-	return &svm->vcpu;
+	return 0;
 
 free_page4:
 	__free_page(hsave_page);
@@ -2234,16 +2251,8 @@ free_page2:
 	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
 free_page1:
 	__free_page(page);
-uninit:
-	kvm_vcpu_uninit(&svm->vcpu);
-free_svm:
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
-free_user_fpu:
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
-free_partial_svm:
-	kmem_cache_free(kvm_vcpu_cache, svm);
 out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void svm_clear_current_vmcb(struct vmcb *vmcb)
@@ -2269,10 +2278,6 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
-	kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
-	kmem_cache_free(kvm_vcpu_cache, svm);
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -4281,12 +4286,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
 			return 1;
 
-		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+		if (data & ~kvm_spec_ctrl_valid_bits(vcpu))
 			return 1;
 
 		svm->spec_ctrl = data;
-
 		if (!data)
 			break;
 
@@ -4310,13 +4313,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-
+		if (!boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			return 1;
 		if (!data)
 			break;
 
 		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-		if (is_guest_mode(vcpu))
-			break;
 		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
@@ -4519,9 +4521,9 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		 */
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			bool m = kvm_apic_match_dest(vcpu, apic,
-						     icrl & KVM_APIC_SHORT_MASK,
+						     icrl & APIC_SHORT_MASK,
 						     GET_APIC_DEST_FIELD(icrh),
-						     icrl & KVM_APIC_DEST_MASK);
+						     icrl & APIC_DEST_MASK);
 
 			if (m && !avic_vcpu_is_running(vcpu))
 				kvm_vcpu_wake_up(vcpu);
@@ -4935,7 +4937,8 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = control->exit_info_2;
 }
 
-static int handle_exit(struct kvm_vcpu *vcpu)
+static int handle_exit(struct kvm_vcpu *vcpu,
+	enum exit_fastpath_completion exit_fastpath)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct kvm_run *kvm_run = vcpu->run;
@@ -4993,7 +4996,10 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 		       __func__, svm->vmcb->control.exit_int_info,
 		       exit_code);
 
-	if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
+	if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) {
+		kvm_skip_emulated_instruction(vcpu);
+		return 1;
+	} else if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
 	    || !svm_exit_handlers[exit_code]) {
 		vcpu_unimpl(vcpu, "svm: unexpected exit reason 0x%x\n", exit_code);
 		dump_vmcb(vcpu);
@@ -5913,6 +5919,7 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
+				    boot_cpu_has(X86_FEATURE_XSAVE) &&
 				    boot_cpu_has(X86_FEATURE_XSAVES);
 
 	/* Update nrips enabled cache */
@@ -5924,14 +5931,14 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 	guest_cpuid_clear(vcpu, X86_FEATURE_X2APIC);
 }
 
-#define F(x) bit(X86_FEATURE_##x)
+#define F feature_bit
 
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
 	case 0x1:
 		if (avic)
-			entry->ecx &= ~bit(X86_FEATURE_X2APIC);
+			entry->ecx &= ~F(X2APIC);
 		break;
 	case 0x80000001:
 		if (nested)
@@ -6001,6 +6008,11 @@ static bool svm_has_wbinvd_exit(void)
 	return true;
 }
 
+static bool svm_pku_supported(void)
+{
+	return false;
+}
+
 #define PRE_EX(exit)  { .exit_code = (exit), \
 			.stage = X86_ICPT_PRE_EXCEPT, }
 #define POST_EX(exit) { .exit_code = (exit), \
@@ -6186,9 +6198,12 @@ out:
 	return ret;
 }
 
-static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
+static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu,
+	enum exit_fastpath_completion *exit_fastpath)
 {
-
+	if (!is_guest_mode(vcpu) &&
+		to_svm(vcpu)->vmcb->control.exit_code == EXIT_REASON_MSR_WRITE)
+		*exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu);
 }
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
@@ -7341,6 +7356,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.xsaves_supported = svm_xsaves_supported,
 	.umip_emulated = svm_umip_emulated,
 	.pt_supported = svm_pt_supported,
+	.pku_supported = svm_pku_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 7aa69716d516..283bdb7071af 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -145,6 +145,11 @@ static inline bool vmx_umip_emulated(void)
 		SECONDARY_EXEC_DESC;
 }
 
+static inline bool vmx_pku_supported(void)
+{
+	return boot_cpu_has(X86_FEATURE_PKU);
+}
+
 static inline bool cpu_has_vmx_rdtscp(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index 72359709cdc1..89c3e0caf39f 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -350,17 +350,12 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 			uint16_t *vmcs_version)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled;
 
 	vmx->nested.enlightened_vmcs_enabled = true;
 
 	if (vmcs_version)
 		*vmcs_version = nested_get_evmcs_version(vcpu);
 
-	/* We don't support disabling the feature for simplicity. */
-	if (evmcs_already_enabled)
-		return 0;
-
 	vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
 	vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
 	vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 6879966b7648..2db21d59eaf5 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -28,16 +28,6 @@ module_param(nested_early_check, bool, S_IRUGO);
 	failed;								\
 })
 
-#define SET_MSR_OR_WARN(vcpu, idx, data)				\
-({									\
-	bool failed = kvm_set_msr(vcpu, idx, data);			\
-	if (failed)							\
-		pr_warn_ratelimited(					\
-				"%s cannot write MSR (0x%x, 0x%llx)\n",	\
-				__func__, idx, data);			\
-	failed;								\
-})
-
 /*
  * Hyper-V requires all of these, so mark them as supported even though
  * they are just treated the same as all-context.
@@ -2172,8 +2162,8 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 	 * EXEC CONTROLS
 	 */
 	exec_control = vmx_exec_control(vmx); /* L0's desires */
-	exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
-	exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
+	exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING;
+	exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING;
 	exec_control &= ~CPU_BASED_TPR_SHADOW;
 	exec_control |= vmcs12->cpu_based_vm_exec_control;
 
@@ -2550,8 +2540,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
-	    SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-			    vmcs12->guest_ia32_perf_global_ctrl))
+	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+				     vmcs12->guest_ia32_perf_global_ctrl)))
 		return -EINVAL;
 
 	kvm_rsp_write(vcpu, vmcs12->guest_rsp);
@@ -2566,7 +2556,7 @@ static int nested_vmx_check_nmi_controls(struct vmcs12 *vmcs12)
 		return -EINVAL;
 
 	if (CC(!nested_cpu_has_virtual_nmis(vmcs12) &&
-	       nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING)))
+	       nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING)))
 		return -EINVAL;
 
 	return 0;
@@ -2823,7 +2813,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(vmcs12->host_ss_selector == 0 && !ia32e))
 		return -EINVAL;
 
-#ifdef CONFIG_X86_64
 	if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
 	    CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
 	    CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
@@ -2831,7 +2820,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
 	    CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
 		return -EINVAL;
-#endif
 
 	/*
 	 * If the load IA32_EFER VM-exit control is 1, bits reserved in the
@@ -2899,6 +2887,10 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	    CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)))
 		return -EINVAL;
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
+	    CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+		return -EINVAL;
+
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
 	    CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))
 		return -EINVAL;
@@ -3048,9 +3040,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
-						 struct vmcs12 *vmcs12);
-
 static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -3183,7 +3172,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	u32 exit_qual;
 
 	evaluate_pending_interrupts = exec_controls_get(vmx) &
-		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+		(CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
 	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
 		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
 
@@ -3230,7 +3219,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	}
 
 	enter_guest_mode(vcpu);
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
 		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
 
 	if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
@@ -3294,7 +3283,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	 * 26.7 "VM-entry failures during or after loading guest state".
 	 */
 vmentry_fail_vmexit_guest_mode:
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
 		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
 	leave_guest_mode(vcpu);
 
@@ -3407,8 +3396,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 */
 	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
 	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
-	    !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) &&
-	    !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) &&
+	    !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) &&
+	    !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) &&
 	      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
 		vmx->nested.nested_run_pending = 0;
 		return kvm_vcpu_halt(vcpu);
@@ -3427,7 +3416,7 @@ vmentry_failed:
 
 /*
  * On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date
- * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK).
+ * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK).
  * This function returns the new value we should put in vmcs12.guest_cr0.
  * It's not enough to just return the vmcs02 GUEST_CR0. Rather,
  *  1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now
@@ -3999,8 +3988,8 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 		vcpu->arch.pat = vmcs12->host_ia32_pat;
 	}
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
-		SET_MSR_OR_WARN(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
-				vmcs12->host_ia32_perf_global_ctrl);
+		WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+					 vmcs12->host_ia32_perf_global_ctrl));
 
 	/* Set L1 segment info according to Intel SDM
 	    27.5.2 Loading Host Segment and Descriptor-Table Registers */
@@ -4209,7 +4198,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	if (nested_cpu_has_preemption_timer(vmcs12))
 		hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);
 
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
 		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
 
 	if (likely(!vmx->fail)) {
@@ -4751,36 +4740,32 @@ static int handle_vmresume(struct kvm_vcpu *vcpu)
 
 static int handle_vmread(struct kvm_vcpu *vcpu)
 {
-	unsigned long field;
-	u64 field_value;
+	struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
+						    : get_vmcs12(vcpu);
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	int len;
-	gva_t gva = 0;
-	struct vmcs12 *vmcs12;
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct x86_exception e;
+	unsigned long field;
+	u64 value;
+	gva_t gva = 0;
 	short offset;
+	int len;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+	/*
+	 * In VMX non-root operation, when the VMCS-link pointer is -1ull,
+	 * any VMREAD sets the ALU flags for VMfailInvalid.
+	 */
+	if (vmx->nested.current_vmptr == -1ull ||
+	    (is_guest_mode(vcpu) &&
+	     get_vmcs12(vcpu)->vmcs_link_pointer == -1ull))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (!is_guest_mode(vcpu))
-		vmcs12 = get_vmcs12(vcpu);
-	else {
-		/*
-		 * When vmcs->vmcs_link_pointer is -1ull, any VMREAD
-		 * to shadowed-field sets the ALU flags for VMfailInvalid.
-		 */
-		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
-			return nested_vmx_failInvalid(vcpu);
-		vmcs12 = get_shadow_vmcs12(vcpu);
-	}
-
 	/* Decode instruction info and find the field to read */
-	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+	field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf));
 
 	offset = vmcs_field_to_offset(field);
 	if (offset < 0)
@@ -4790,25 +4775,26 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
 		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
-	/* Read the field, zero-extended to a u64 field_value */
-	field_value = vmcs12_read_any(vmcs12, field, offset);
+	/* Read the field, zero-extended to a u64 value */
+	value = vmcs12_read_any(vmcs12, field, offset);
 
 	/*
 	 * Now copy part of this value to register or memory, as requested.
 	 * Note that the number of bits actually copied is 32 or 64 depending
 	 * on the guest's mode (32 or 64 bit), not on the given field's length.
 	 */
-	if (vmx_instruction_info & (1u << 10)) {
-		kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
-			field_value);
+	if (instr_info & BIT(10)) {
+		kvm_register_writel(vcpu, (((instr_info) >> 3) & 0xf), value);
 	} else {
 		len = is_64_bit_mode(vcpu) ? 8 : 4;
 		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, true, len, &gva))
+					instr_info, true, len, &gva))
 			return 1;
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
-		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+		if (kvm_write_guest_virt_system(vcpu, gva, &value, len, &e)) {
 			kvm_inject_page_fault(vcpu, &e);
+			return 1;
+		}
 	}
 
 	return nested_vmx_succeed(vcpu);
@@ -4840,46 +4826,58 @@ static bool is_shadow_field_ro(unsigned long field)
 
 static int handle_vmwrite(struct kvm_vcpu *vcpu)
 {
+	struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
+						    : get_vmcs12(vcpu);
+	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+	u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct x86_exception e;
 	unsigned long field;
-	int len;
+	short offset;
 	gva_t gva;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+	int len;
 
-	/* The value to write might be 32 or 64 bits, depending on L1's long
+	/*
+	 * The value to write might be 32 or 64 bits, depending on L1's long
 	 * mode, and eventually we need to write that into a field of several
 	 * possible lengths. The code below first zero-extends the value to 64
-	 * bit (field_value), and then copies only the appropriate number of
+	 * bit (value), and then copies only the appropriate number of
 	 * bits into the vmcs12 field.
 	 */
-	u64 field_value = 0;
-	struct x86_exception e;
-	struct vmcs12 *vmcs12;
-	short offset;
+	u64 value = 0;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (vmx->nested.current_vmptr == -1ull)
+	/*
+	 * In VMX non-root operation, when the VMCS-link pointer is -1ull,
+	 * any VMWRITE sets the ALU flags for VMfailInvalid.
+	 */
+	if (vmx->nested.current_vmptr == -1ull ||
+	    (is_guest_mode(vcpu) &&
+	     get_vmcs12(vcpu)->vmcs_link_pointer == -1ull))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (vmx_instruction_info & (1u << 10))
-		field_value = kvm_register_readl(vcpu,
-			(((vmx_instruction_info) >> 3) & 0xf));
+	if (instr_info & BIT(10))
+		value = kvm_register_readl(vcpu, (((instr_info) >> 3) & 0xf));
 	else {
 		len = is_64_bit_mode(vcpu) ? 8 : 4;
 		if (get_vmx_mem_address(vcpu, exit_qualification,
-				vmx_instruction_info, false, len, &gva))
+					instr_info, false, len, &gva))
 			return 1;
-		if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) {
+		if (kvm_read_guest_virt(vcpu, gva, &value, len, &e)) {
 			kvm_inject_page_fault(vcpu, &e);
 			return 1;
 		}
 	}
 
+	field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf));
+
+	offset = vmcs_field_to_offset(field);
+	if (offset < 0)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_UNSUPPORTED_VMCS_COMPONENT);
 
-	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
 	/*
 	 * If the vCPU supports "VMWRITE to any supported field in the
 	 * VMCS," then the "read-only" fields are actually read/write.
@@ -4889,29 +4887,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 		return nested_vmx_failValid(vcpu,
 			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
 
-	if (!is_guest_mode(vcpu)) {
-		vmcs12 = get_vmcs12(vcpu);
-
-		/*
-		 * Ensure vmcs12 is up-to-date before any VMWRITE that dirties
-		 * vmcs12, else we may crush a field or consume a stale value.
-		 */
-		if (!is_shadow_field_rw(field))
-			copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
-	} else {
-		/*
-		 * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
-		 * to shadowed-field sets the ALU flags for VMfailInvalid.
-		 */
-		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
-			return nested_vmx_failInvalid(vcpu);
-		vmcs12 = get_shadow_vmcs12(vcpu);
-	}
-
-	offset = vmcs_field_to_offset(field);
-	if (offset < 0)
-		return nested_vmx_failValid(vcpu,
-			VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+	/*
+	 * Ensure vmcs12 is up-to-date before any VMWRITE that dirties
+	 * vmcs12, else we may crush a field or consume a stale value.
+	 */
+	if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field))
+		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
 	/*
 	 * Some Intel CPUs intentionally drop the reserved bits of the AR byte
@@ -4922,9 +4903,9 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 	 * the stripped down value, L2 sees the full value as stored by KVM).
 	 */
 	if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES)
-		field_value &= 0x1f0ff;
+		value &= 0x1f0ff;
 
-	vmcs12_write_any(vmcs12, field, offset, field_value);
+	vmcs12_write_any(vmcs12, field, offset, value);
 
 	/*
 	 * Do not track vmcs12 dirty-state if in guest-mode as we actually
@@ -4941,7 +4922,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 			preempt_disable();
 			vmcs_load(vmx->vmcs01.shadow_vmcs);
 
-			__vmcs_writel(field, field_value);
+			__vmcs_writel(field, value);
 
 			vmcs_clear(vmx->vmcs01.shadow_vmcs);
 			vmcs_load(vmx->loaded_vmcs->vmcs);
@@ -5524,10 +5505,10 @@ bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 		return false;
 	case EXIT_REASON_TRIPLE_FAULT:
 		return true;
-	case EXIT_REASON_PENDING_INTERRUPT:
-		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING);
+	case EXIT_REASON_INTERRUPT_WINDOW:
+		return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING);
 	case EXIT_REASON_NMI_WINDOW:
-		return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING);
+		return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING);
 	case EXIT_REASON_TASK_SWITCH:
 		return true;
 	case EXIT_REASON_CPUID:
@@ -6015,8 +5996,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 	msrs->procbased_ctls_low =
 		CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
 	msrs->procbased_ctls_high &=
-		CPU_BASED_VIRTUAL_INTR_PENDING |
-		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
+		CPU_BASED_INTR_WINDOW_EXITING |
+		CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING |
 		CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
 		CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
 		CPU_BASED_CR3_STORE_EXITING |
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 7023138b1cb0..34a3a17bb6d7 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -86,10 +86,14 @@ static unsigned intel_find_arch_event(struct kvm_pmu *pmu,
 
 static unsigned intel_find_fixed_event(int idx)
 {
-	if (idx >= ARRAY_SIZE(fixed_pmc_events))
+	u32 event;
+	size_t size = ARRAY_SIZE(fixed_pmc_events);
+
+	if (idx >= size)
 		return PERF_COUNT_HW_MAX;
 
-	return intel_arch_events[fixed_pmc_events[idx]].event_type;
+	event = fixed_pmc_events[array_index_nospec(idx, size)];
+	return intel_arch_events[event].event_type;
 }
 
 /* check if a PMC is enabled by comparing it with globl_ctrl bits. */
@@ -130,16 +134,20 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
 	struct kvm_pmc *counters;
+	unsigned int num_counters;
 
 	idx &= ~(3u << 30);
-	if (!fixed && idx >= pmu->nr_arch_gp_counters)
-		return NULL;
-	if (fixed && idx >= pmu->nr_arch_fixed_counters)
+	if (fixed) {
+		counters = pmu->fixed_counters;
+		num_counters = pmu->nr_arch_fixed_counters;
+	} else {
+		counters = pmu->gp_counters;
+		num_counters = pmu->nr_arch_gp_counters;
+	}
+	if (idx >= num_counters)
 		return NULL;
-	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
 	*mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
-
-	return &counters[idx];
+	return &counters[array_index_nospec(idx, num_counters)];
 }
 
 static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
diff --git a/arch/x86/kvm/vmx/vmcs_shadow_fields.h b/arch/x86/kvm/vmx/vmcs_shadow_fields.h
index eb1ecd16fd22..cad128d1657b 100644
--- a/arch/x86/kvm/vmx/vmcs_shadow_fields.h
+++ b/arch/x86/kvm/vmx/vmcs_shadow_fields.h
@@ -23,12 +23,12 @@ BUILD_BUG_ON(1)
  *
  * When adding or removing fields here, note that shadowed
  * fields must always be synced by prepare_vmcs02, not just
- * prepare_vmcs02_full.
+ * prepare_vmcs02_rare.
  */
 
 /*
  * Keeping the fields ordered by size is an attempt at improving
- * branch prediction in vmcs_read_any and vmcs_write_any.
+ * branch prediction in vmcs12_read_any and vmcs12_write_any.
  */
 
 /* 16-bits */
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index cdb4bf50ee14..c475fa2aaae0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1057,6 +1057,12 @@ static unsigned long segment_base(u16 selector)
 }
 #endif
 
+static inline bool pt_can_write_msr(struct vcpu_vmx *vmx)
+{
+	return (pt_mode == PT_MODE_HOST_GUEST) &&
+	       !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
+}
+
 static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
 {
 	u32 i;
@@ -1716,7 +1722,7 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
 	if (is_guest_mode(vcpu) &&
-	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING))
 		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
 
 	return vcpu->arch.tsc_offset;
@@ -1734,7 +1740,7 @@ static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	 * to the newly set TSC to get L2's TSC.
 	 */
 	if (is_guest_mode(vcpu) &&
-	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING))
 		g_tsc_offset = vmcs12->tsc_offset;
 
 	trace_kvm_write_tsc_offset(vcpu->vcpu_id,
@@ -1773,8 +1779,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
 	default:
 		return 1;
 	}
-
-	return 0;
 }
 
 /*
@@ -1916,7 +1920,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 }
 
 /*
- * Writes msr value into into the appropriate "register".
+ * Writes msr value into the appropriate "register".
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
@@ -1994,12 +1998,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
-		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+		if (data & ~kvm_spec_ctrl_valid_bits(vcpu))
 			return 1;
 
 		vmx->spec_ctrl = data;
-
 		if (!data)
 			break;
 
@@ -2010,7 +2012,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 *
 		 * For nested:
 		 * The handling of the MSR bitmap for L2 guests is done in
-		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * nested_vmx_prepare_msr_bitmap. We should not touch the
 		 * vmcs02.msr_bitmap here since it gets completely overwritten
 		 * in the merging. We update the vmcs01 here for L1 as well
 		 * since it will end up touching the MSR anyway now.
@@ -2033,7 +2035,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-
+		if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL))
+			return 1;
 		if (!data)
 			break;
 
@@ -2046,7 +2049,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 *
 		 * For nested:
 		 * The handling of the MSR bitmap for L2 guests is done in
-		 * nested_vmx_merge_msr_bitmap. We should not touch the
+		 * nested_vmx_prepare_msr_bitmap. We should not touch the
 		 * vmcs02.msr_bitmap here since it gets completely overwritten
 		 * in the merging.
 		 */
@@ -2104,47 +2107,50 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		pt_update_intercept_for_msr(vmx);
 		break;
 	case MSR_IA32_RTIT_STATUS:
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
-			(data & MSR_IA32_RTIT_STATUS_MASK))
+		if (!pt_can_write_msr(vmx))
+			return 1;
+		if (data & MSR_IA32_RTIT_STATUS_MASK)
 			return 1;
 		vmx->pt_desc.guest.status = data;
 		break;
 	case MSR_IA32_RTIT_CR3_MATCH:
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
-			!intel_pt_validate_cap(vmx->pt_desc.caps,
-						PT_CAP_cr3_filtering))
+		if (!pt_can_write_msr(vmx))
+			return 1;
+		if (!intel_pt_validate_cap(vmx->pt_desc.caps,
+					   PT_CAP_cr3_filtering))
 			return 1;
 		vmx->pt_desc.guest.cr3_match = data;
 		break;
 	case MSR_IA32_RTIT_OUTPUT_BASE:
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
-			(!intel_pt_validate_cap(vmx->pt_desc.caps,
-					PT_CAP_topa_output) &&
-			 !intel_pt_validate_cap(vmx->pt_desc.caps,
-					PT_CAP_single_range_output)) ||
-			(data & MSR_IA32_RTIT_OUTPUT_BASE_MASK))
+		if (!pt_can_write_msr(vmx))
+			return 1;
+		if (!intel_pt_validate_cap(vmx->pt_desc.caps,
+					   PT_CAP_topa_output) &&
+		    !intel_pt_validate_cap(vmx->pt_desc.caps,
+					   PT_CAP_single_range_output))
+			return 1;
+		if (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)
 			return 1;
 		vmx->pt_desc.guest.output_base = data;
 		break;
 	case MSR_IA32_RTIT_OUTPUT_MASK:
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
-			(!intel_pt_validate_cap(vmx->pt_desc.caps,
-					PT_CAP_topa_output) &&
-			 !intel_pt_validate_cap(vmx->pt_desc.caps,
-					PT_CAP_single_range_output)))
+		if (!pt_can_write_msr(vmx))
+			return 1;
+		if (!intel_pt_validate_cap(vmx->pt_desc.caps,
+					   PT_CAP_topa_output) &&
+		    !intel_pt_validate_cap(vmx->pt_desc.caps,
+					   PT_CAP_single_range_output))
 			return 1;
 		vmx->pt_desc.guest.output_mask = data;
 		break;
 	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
+		if (!pt_can_write_msr(vmx))
+			return 1;
 		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
-		if ((pt_mode != PT_MODE_HOST_GUEST) ||
-			(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) ||
-			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
-					PT_CAP_num_address_ranges)))
+		if (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
+						       PT_CAP_num_address_ranges))
+			return 1;
+		if (is_noncanonical_address(data, vcpu))
 			return 1;
 		if (index % 2)
 			vmx->pt_desc.guest.addr_b[index / 2] = data;
@@ -2322,7 +2328,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	      CPU_BASED_CR3_STORE_EXITING |
 	      CPU_BASED_UNCOND_IO_EXITING |
 	      CPU_BASED_MOV_DR_EXITING |
-	      CPU_BASED_USE_TSC_OFFSETING |
+	      CPU_BASED_USE_TSC_OFFSETTING |
 	      CPU_BASED_MWAIT_EXITING |
 	      CPU_BASED_MONITOR_EXITING |
 	      CPU_BASED_INVLPG_EXITING |
@@ -2657,8 +2663,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 
 	vmx->rmode.vm86_active = 0;
 
-	vmx_segment_cache_clear(vmx);
-
 	vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
@@ -3444,7 +3448,7 @@ out:
 static int init_rmode_identity_map(struct kvm *kvm)
 {
 	struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
-	int i, idx, r = 0;
+	int i, r = 0;
 	kvm_pfn_t identity_map_pfn;
 	u32 tmp;
 
@@ -3452,7 +3456,7 @@ static int init_rmode_identity_map(struct kvm *kvm)
 	mutex_lock(&kvm->slots_lock);
 
 	if (likely(kvm_vmx->ept_identity_pagetable_done))
-		goto out2;
+		goto out;
 
 	if (!kvm_vmx->ept_identity_map_addr)
 		kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
@@ -3461,9 +3465,8 @@ static int init_rmode_identity_map(struct kvm *kvm)
 	r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
 				    kvm_vmx->ept_identity_map_addr, PAGE_SIZE);
 	if (r < 0)
-		goto out2;
+		goto out;
 
-	idx = srcu_read_lock(&kvm->srcu);
 	r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
 	if (r < 0)
 		goto out;
@@ -3479,9 +3482,6 @@ static int init_rmode_identity_map(struct kvm *kvm)
 	kvm_vmx->ept_identity_pagetable_done = true;
 
 out:
-	srcu_read_unlock(&kvm->srcu, idx);
-
-out2:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
@@ -4009,6 +4009,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 	if (vmx_xsaves_supported()) {
 		/* Exposing XSAVES only when XSAVE is exposed */
 		bool xsaves_enabled =
+			boot_cpu_has(X86_FEATURE_XSAVE) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 			guest_cpuid_has(vcpu, X86_FEATURE_XSAVES);
 
@@ -4319,7 +4320,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
-	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING);
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING);
 }
 
 static void enable_nmi_window(struct kvm_vcpu *vcpu)
@@ -4330,7 +4331,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 		return;
 	}
 
-	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING);
+	exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING);
 }
 
 static void vmx_inject_irq(struct kvm_vcpu *vcpu)
@@ -4455,8 +4456,11 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	if (enable_unrestricted_guest)
 		return 0;
 
-	ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
-				    PAGE_SIZE * 3);
+	mutex_lock(&kvm->slots_lock);
+	ret = __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr,
+				      PAGE_SIZE * 3);
+	mutex_unlock(&kvm->slots_lock);
+
 	if (ret)
 		return ret;
 	to_kvm_vmx(kvm)->tss_addr = addr;
@@ -4938,7 +4942,7 @@ static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu)
 
 static int handle_interrupt_window(struct kvm_vcpu *vcpu)
 {
-	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_INTR_PENDING);
+	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_INTR_WINDOW_EXITING);
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
@@ -5151,7 +5155,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 static int handle_nmi_window(struct kvm_vcpu *vcpu)
 {
 	WARN_ON_ONCE(!enable_vnmi);
-	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_VIRTUAL_NMI_PENDING);
+	exec_controls_clearbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING);
 	++vcpu->stat.nmi_window_exits;
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 
@@ -5172,7 +5176,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 	WARN_ON_ONCE(vmx->emulation_required && vmx->nested.nested_run_pending);
 
 	intr_window_requested = exec_controls_get(vmx) &
-				CPU_BASED_VIRTUAL_INTR_PENDING;
+				CPU_BASED_INTR_WINDOW_EXITING;
 
 	while (vmx->emulation_required && count-- != 0) {
 		if (intr_window_requested && vmx_interrupt_allowed(vcpu))
@@ -5496,7 +5500,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_CPUID]                   = kvm_emulate_cpuid,
 	[EXIT_REASON_MSR_READ]                = kvm_emulate_rdmsr,
 	[EXIT_REASON_MSR_WRITE]               = kvm_emulate_wrmsr,
-	[EXIT_REASON_PENDING_INTERRUPT]       = handle_interrupt_window,
+	[EXIT_REASON_INTERRUPT_WINDOW]        = handle_interrupt_window,
 	[EXIT_REASON_HLT]                     = kvm_emulate_halt,
 	[EXIT_REASON_INVD]		      = handle_invd,
 	[EXIT_REASON_INVLPG]		      = handle_invlpg,
@@ -5783,7 +5787,8 @@ void dump_vmcs(void)
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
  */
-static int vmx_handle_exit(struct kvm_vcpu *vcpu)
+static int vmx_handle_exit(struct kvm_vcpu *vcpu,
+	enum exit_fastpath_completion exit_fastpath)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exit_reason = vmx->exit_reason;
@@ -5869,34 +5874,44 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	if (exit_reason < kvm_vmx_max_exit_handlers
-	    && kvm_vmx_exit_handlers[exit_reason]) {
+	if (exit_fastpath == EXIT_FASTPATH_SKIP_EMUL_INS) {
+		kvm_skip_emulated_instruction(vcpu);
+		return 1;
+	}
+
+	if (exit_reason >= kvm_vmx_max_exit_handlers)
+		goto unexpected_vmexit;
 #ifdef CONFIG_RETPOLINE
-		if (exit_reason == EXIT_REASON_MSR_WRITE)
-			return kvm_emulate_wrmsr(vcpu);
-		else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER)
-			return handle_preemption_timer(vcpu);
-		else if (exit_reason == EXIT_REASON_PENDING_INTERRUPT)
-			return handle_interrupt_window(vcpu);
-		else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
-			return handle_external_interrupt(vcpu);
-		else if (exit_reason == EXIT_REASON_HLT)
-			return kvm_emulate_halt(vcpu);
-		else if (exit_reason == EXIT_REASON_EPT_MISCONFIG)
-			return handle_ept_misconfig(vcpu);
+	if (exit_reason == EXIT_REASON_MSR_WRITE)
+		return kvm_emulate_wrmsr(vcpu);
+	else if (exit_reason == EXIT_REASON_PREEMPTION_TIMER)
+		return handle_preemption_timer(vcpu);
+	else if (exit_reason == EXIT_REASON_INTERRUPT_WINDOW)
+		return handle_interrupt_window(vcpu);
+	else if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT)
+		return handle_external_interrupt(vcpu);
+	else if (exit_reason == EXIT_REASON_HLT)
+		return kvm_emulate_halt(vcpu);
+	else if (exit_reason == EXIT_REASON_EPT_MISCONFIG)
+		return handle_ept_misconfig(vcpu);
 #endif
-		return kvm_vmx_exit_handlers[exit_reason](vcpu);
-	} else {
-		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
-				exit_reason);
-		dump_vmcs();
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror =
+
+	exit_reason = array_index_nospec(exit_reason,
+					 kvm_vmx_max_exit_handlers);
+	if (!kvm_vmx_exit_handlers[exit_reason])
+		goto unexpected_vmexit;
+
+	return kvm_vmx_exit_handlers[exit_reason](vcpu);
+
+unexpected_vmexit:
+	vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+	dump_vmcs();
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror =
 			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
-		vcpu->run->internal.ndata = 1;
-		vcpu->run->internal.data[0] = exit_reason;
-		return 0;
-	}
+	vcpu->run->internal.ndata = 1;
+	vcpu->run->internal.data[0] = exit_reason;
+	return 0;
 }
 
 /*
@@ -6217,7 +6232,8 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 }
 STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff);
 
-static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
+static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu,
+	enum exit_fastpath_completion *exit_fastpath)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
@@ -6225,6 +6241,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 		handle_external_interrupt_irqoff(vcpu);
 	else if (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI)
 		handle_exception_nmi_irqoff(vmx);
+	else if (!is_guest_mode(vcpu) &&
+		vmx->exit_reason == EXIT_REASON_MSR_WRITE)
+		*exit_fastpath = handle_fastpath_set_msr_irqoff(vcpu);
 }
 
 static bool vmx_has_emulated_msr(int index)
@@ -6633,60 +6652,31 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 	free_vpid(vmx->vpid);
 	nested_vmx_free_vcpu(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
-	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
-	kmem_cache_free(kvm_vcpu_cache, vmx);
 }
 
-static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
+static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 {
-	int err;
 	struct vcpu_vmx *vmx;
 	unsigned long *msr_bitmap;
-	int i, cpu;
-
-	BUILD_BUG_ON_MSG(offsetof(struct vcpu_vmx, vcpu) != 0,
-		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
-
-	vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
-	if (!vmx)
-		return ERR_PTR(-ENOMEM);
+	int i, cpu, err;
 
-	vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
-			GFP_KERNEL_ACCOUNT);
-	if (!vmx->vcpu.arch.user_fpu) {
-		printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
-		err = -ENOMEM;
-		goto free_partial_vcpu;
-	}
+	BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
+	vmx = to_vmx(vcpu);
 
-	vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
-			GFP_KERNEL_ACCOUNT);
-	if (!vmx->vcpu.arch.guest_fpu) {
-		printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
-		err = -ENOMEM;
-		goto free_user_fpu;
-	}
+	err = -ENOMEM;
 
 	vmx->vpid = allocate_vpid();
 
-	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
-
-	err = -ENOMEM;
-
 	/*
 	 * If PML is turned on, failure on enabling PML just results in failure
 	 * of creating the vcpu, therefore we can simplify PML logic (by
 	 * avoiding dealing with cases, such as enabling PML partially on vcpus
-	 * for the guest, etc.
+	 * for the guest), etc.
 	 */
 	if (enable_pml) {
 		vmx->pml_pg = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 		if (!vmx->pml_pg)
-			goto uninit_vcpu;
+			goto free_vpid;
 	}
 
 	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS);
@@ -6731,7 +6721,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
-	if (kvm_cstate_in_guest(kvm)) {
+	if (kvm_cstate_in_guest(vcpu->kvm)) {
 		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
 		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
 		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
@@ -6741,19 +6731,19 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
 	cpu = get_cpu();
-	vmx_vcpu_load(&vmx->vcpu, cpu);
-	vmx->vcpu.cpu = cpu;
+	vmx_vcpu_load(vcpu, cpu);
+	vcpu->cpu = cpu;
 	init_vmcs(vmx);
-	vmx_vcpu_put(&vmx->vcpu);
+	vmx_vcpu_put(vcpu);
 	put_cpu();
-	if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
-		err = alloc_apic_access_page(kvm);
+	if (cpu_need_virtualize_apic_accesses(vcpu)) {
+		err = alloc_apic_access_page(vcpu->kvm);
 		if (err)
 			goto free_vmcs;
 	}
 
 	if (enable_ept && !enable_unrestricted_guest) {
-		err = init_rmode_identity_map(kvm);
+		err = init_rmode_identity_map(vcpu->kvm);
 		if (err)
 			goto free_vmcs;
 	}
@@ -6761,7 +6751,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
 					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(&vmx->vcpu));
+					   kvm_vcpu_apicv_active(vcpu));
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
@@ -6779,22 +6769,15 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	vmx->ept_pointer = INVALID_PAGE;
 
-	return &vmx->vcpu;
+	return 0;
 
 free_vmcs:
 	free_loaded_vmcs(vmx->loaded_vmcs);
 free_pml:
 	vmx_destroy_pml_buffer(vmx);
-uninit_vcpu:
-	kvm_vcpu_uninit(&vmx->vcpu);
-free_vcpu:
+free_vpid:
 	free_vpid(vmx->vpid);
-	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
-free_user_fpu:
-	kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
-free_partial_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vmx);
-	return ERR_PTR(err);
+	return err;
 }
 
 #define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html for details.\n"
@@ -6946,28 +6929,28 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 } while (0)
 
 	entry = kvm_find_cpuid_entry(vcpu, 0x1, 0);
-	cr4_fixed1_update(X86_CR4_VME,        edx, bit(X86_FEATURE_VME));
-	cr4_fixed1_update(X86_CR4_PVI,        edx, bit(X86_FEATURE_VME));
-	cr4_fixed1_update(X86_CR4_TSD,        edx, bit(X86_FEATURE_TSC));
-	cr4_fixed1_update(X86_CR4_DE,         edx, bit(X86_FEATURE_DE));
-	cr4_fixed1_update(X86_CR4_PSE,        edx, bit(X86_FEATURE_PSE));
-	cr4_fixed1_update(X86_CR4_PAE,        edx, bit(X86_FEATURE_PAE));
-	cr4_fixed1_update(X86_CR4_MCE,        edx, bit(X86_FEATURE_MCE));
-	cr4_fixed1_update(X86_CR4_PGE,        edx, bit(X86_FEATURE_PGE));
-	cr4_fixed1_update(X86_CR4_OSFXSR,     edx, bit(X86_FEATURE_FXSR));
-	cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, bit(X86_FEATURE_XMM));
-	cr4_fixed1_update(X86_CR4_VMXE,       ecx, bit(X86_FEATURE_VMX));
-	cr4_fixed1_update(X86_CR4_SMXE,       ecx, bit(X86_FEATURE_SMX));
-	cr4_fixed1_update(X86_CR4_PCIDE,      ecx, bit(X86_FEATURE_PCID));
-	cr4_fixed1_update(X86_CR4_OSXSAVE,    ecx, bit(X86_FEATURE_XSAVE));
+	cr4_fixed1_update(X86_CR4_VME,        edx, feature_bit(VME));
+	cr4_fixed1_update(X86_CR4_PVI,        edx, feature_bit(VME));
+	cr4_fixed1_update(X86_CR4_TSD,        edx, feature_bit(TSC));
+	cr4_fixed1_update(X86_CR4_DE,         edx, feature_bit(DE));
+	cr4_fixed1_update(X86_CR4_PSE,        edx, feature_bit(PSE));
+	cr4_fixed1_update(X86_CR4_PAE,        edx, feature_bit(PAE));
+	cr4_fixed1_update(X86_CR4_MCE,        edx, feature_bit(MCE));
+	cr4_fixed1_update(X86_CR4_PGE,        edx, feature_bit(PGE));
+	cr4_fixed1_update(X86_CR4_OSFXSR,     edx, feature_bit(FXSR));
+	cr4_fixed1_update(X86_CR4_OSXMMEXCPT, edx, feature_bit(XMM));
+	cr4_fixed1_update(X86_CR4_VMXE,       ecx, feature_bit(VMX));
+	cr4_fixed1_update(X86_CR4_SMXE,       ecx, feature_bit(SMX));
+	cr4_fixed1_update(X86_CR4_PCIDE,      ecx, feature_bit(PCID));
+	cr4_fixed1_update(X86_CR4_OSXSAVE,    ecx, feature_bit(XSAVE));
 
 	entry = kvm_find_cpuid_entry(vcpu, 0x7, 0);
-	cr4_fixed1_update(X86_CR4_FSGSBASE,   ebx, bit(X86_FEATURE_FSGSBASE));
-	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
-	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
-	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
-	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
-	cr4_fixed1_update(X86_CR4_LA57,       ecx, bit(X86_FEATURE_LA57));
+	cr4_fixed1_update(X86_CR4_FSGSBASE,   ebx, feature_bit(FSGSBASE));
+	cr4_fixed1_update(X86_CR4_SMEP,       ebx, feature_bit(SMEP));
+	cr4_fixed1_update(X86_CR4_SMAP,       ebx, feature_bit(SMAP));
+	cr4_fixed1_update(X86_CR4_PKE,        ecx, feature_bit(PKU));
+	cr4_fixed1_update(X86_CR4_UMIP,       ecx, feature_bit(UMIP));
+	cr4_fixed1_update(X86_CR4_LA57,       ecx, feature_bit(LA57));
 
 #undef cr4_fixed1_update
 }
@@ -7101,7 +7084,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	if (func == 1 && nested)
-		entry->ecx |= bit(X86_FEATURE_VMX);
+		entry->ecx |= feature_bit(VMX);
 }
 
 static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu)
@@ -7843,6 +7826,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.xsaves_supported = vmx_xsaves_supported,
 	.umip_emulated = vmx_umip_emulated,
 	.pt_supported = vmx_pt_supported,
+	.pku_supported = vmx_pku_supported,
 
 	.request_immediate_exit = vmx_request_immediate_exit,
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 740d3ee42455..2d3be7f3ad67 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -93,6 +93,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
+static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
+
 #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
 #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
@@ -879,30 +881,44 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
-{
-	if (cr4 & CR4_RESERVED_BITS)
-		return -EINVAL;
+#define __cr4_reserved_bits(__cpu_has, __c)		\
+({							\
+	u64 __reserved_bits = CR4_RESERVED_BITS;	\
+							\
+	if (!__cpu_has(__c, X86_FEATURE_XSAVE))		\
+		__reserved_bits |= X86_CR4_OSXSAVE;	\
+	if (!__cpu_has(__c, X86_FEATURE_SMEP))		\
+		__reserved_bits |= X86_CR4_SMEP;	\
+	if (!__cpu_has(__c, X86_FEATURE_SMAP))		\
+		__reserved_bits |= X86_CR4_SMAP;	\
+	if (!__cpu_has(__c, X86_FEATURE_FSGSBASE))	\
+		__reserved_bits |= X86_CR4_FSGSBASE;	\
+	if (!__cpu_has(__c, X86_FEATURE_PKU))		\
+		__reserved_bits |= X86_CR4_PKE;		\
+	if (!__cpu_has(__c, X86_FEATURE_LA57))		\
+		__reserved_bits |= X86_CR4_LA57;	\
+	__reserved_bits;				\
+})
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
-		return -EINVAL;
-
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
-		return -EINVAL;
+static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
+{
+	u64 reserved_bits = __cr4_reserved_bits(cpu_has, c);
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
-		return -EINVAL;
+	if (cpuid_ecx(0x7) & feature_bit(LA57))
+		reserved_bits &= ~X86_CR4_LA57;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
-		return -EINVAL;
+	if (kvm_x86_ops->umip_emulated())
+		reserved_bits &= ~X86_CR4_UMIP;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
-		return -EINVAL;
+	return reserved_bits;
+}
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	if (cr4 & cr4_reserved_bits)
 		return -EINVAL;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+	if (cr4 & __cr4_reserved_bits(guest_cpuid_has, vcpu))
 		return -EINVAL;
 
 	return 0;
@@ -1047,9 +1063,11 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
 
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		vcpu->arch.db[dr] = val;
+		vcpu->arch.db[array_index_nospec(dr, size)] = val;
 		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
 			vcpu->arch.eff_db[dr] = val;
 		break;
@@ -1064,7 +1082,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 	case 5:
 		/* fall through */
 	default: /* 7 */
-		if (val & 0xffffffff00000000ULL)
+		if (!kvm_dr7_valid(val))
 			return -1; /* #GP */
 		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
 		kvm_update_dr7(vcpu);
@@ -1086,9 +1104,11 @@ EXPORT_SYMBOL_GPL(kvm_set_dr);
 
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		*val = vcpu->arch.db[dr];
+		*val = vcpu->arch.db[array_index_nospec(dr, size)];
 		break;
 	case 4:
 		/* fall through */
@@ -1212,6 +1232,7 @@ static const u32 emulated_msrs_all[] = {
 	MSR_MISC_FEATURES_ENABLES,
 	MSR_AMD64_VIRT_SPEC_CTRL,
 	MSR_IA32_POWER_CTL,
+	MSR_IA32_UCODE_REV,
 
 	/*
 	 * The following list leaves out MSRs whose values are determined
@@ -1526,6 +1547,49 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr);
 
 /*
+ * The fast path for frequent and performance sensitive wrmsr emulation,
+ * i.e. the sending of IPI, sending IPI early in the VM-Exit flow reduces
+ * the latency of virtual IPI by avoiding the expensive bits of transitioning
+ * from guest to host, e.g. reacquiring KVM's SRCU lock. In contrast to the
+ * other cases which must be called after interrupts are enabled on the host.
+ */
+static int handle_fastpath_set_x2apic_icr_irqoff(struct kvm_vcpu *vcpu, u64 data)
+{
+	if (lapic_in_kernel(vcpu) && apic_x2apic_mode(vcpu->arch.apic) &&
+		((data & APIC_DEST_MASK) == APIC_DEST_PHYSICAL) &&
+		((data & APIC_MODE_MASK) == APIC_DM_FIXED)) {
+
+		kvm_lapic_set_reg(vcpu->arch.apic, APIC_ICR2, (u32)(data >> 32));
+		return kvm_lapic_reg_write(vcpu->arch.apic, APIC_ICR, (u32)data);
+	}
+
+	return 1;
+}
+
+enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu)
+{
+	u32 msr = kvm_rcx_read(vcpu);
+	u64 data = kvm_read_edx_eax(vcpu);
+	int ret = 0;
+
+	switch (msr) {
+	case APIC_BASE_MSR + (APIC_ICR >> 4):
+		ret = handle_fastpath_set_x2apic_icr_irqoff(vcpu, data);
+		break;
+	default:
+		return EXIT_FASTPATH_NONE;
+	}
+
+	if (!ret) {
+		trace_kvm_msr_write(msr, data);
+		return EXIT_FASTPATH_SKIP_EMUL_INS;
+	}
+
+	return EXIT_FASTPATH_NONE;
+}
+EXPORT_SYMBOL_GPL(handle_fastpath_set_msr_irqoff);
+
+/*
  * Adapt set_msr() to msr_io()'s calling convention
  */
 static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
@@ -2485,7 +2549,10 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
 			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
@@ -2581,45 +2648,47 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
+	/* -EAGAIN is returned in atomic context so we can just return. */
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
+			&map, &vcpu->arch.st.cache, false))
 		return;
 
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
 	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+		st->preempted & KVM_VCPU_FLUSH_TLB);
+	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 		kvm_vcpu_flush_tlb(vcpu, false);
 
-	if (vcpu->arch.st.steal.version & 1)
-		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
+	vcpu->arch.st.preempted = 0;
 
-	vcpu->arch.st.steal.version += 1;
+	if (st->version & 1)
+		st->version += 1;  /* first time write, random junk */
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	st->version += 1;
 
 	smp_wmb();
 
-	vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+	st->steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
-
 	smp_wmb();
 
-	vcpu->arch.st.steal.version += 1;
+	st->version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false);
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
@@ -2786,11 +2855,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data & KVM_STEAL_RESERVED_MASK)
 			return 1;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-						data & KVM_STEAL_VALID_BITS,
-						sizeof(struct kvm_steal_time)))
-			return 1;
-
 		vcpu->arch.st.msr_val = data;
 
 		if (!(data & KVM_MSR_ENABLED))
@@ -2926,7 +2990,10 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			data = vcpu->arch.mce_banks[offset];
 			break;
 		}
@@ -3458,10 +3525,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
-	fpregs_assert_state_consistent();
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_return();
-
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -3501,15 +3564,25 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
+	if (vcpu->arch.st.preempted)
+		return;
+
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
+			&vcpu->arch.st.cache, true))
+		return;
+
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
-			&vcpu->arch.st.steal.preempted,
-			offsetof(struct kvm_steal_time, preempted),
-			sizeof(vcpu->arch.st.steal.preempted));
+	st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
+
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -4660,9 +4733,6 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 {
 	struct kvm_pit *pit = kvm->arch.vpit;
 
-	if (!pit)
-		return -ENXIO;
-
 	/* pit->pit_state.lock was overloaded to prevent userspace from getting
 	 * an inconsistent state after running multiple KVM_REINJECT_CONTROL
 	 * ioctls in parallel.  Use a separate lock if that ioctl isn't rare.
@@ -5029,6 +5099,9 @@ set_identity_unlock:
 		r =  -EFAULT;
 		if (copy_from_user(&control, argp, sizeof(control)))
 			goto out;
+		r = -ENXIO;
+		if (!kvm->arch.vpit)
+			goto out;
 		r = kvm_vm_ioctl_reinject(kvm, &control);
 		break;
 	}
@@ -6186,6 +6259,21 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
 	return kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx, check_limit);
 }
 
+static bool emulator_guest_has_long_mode(struct x86_emulate_ctxt *ctxt)
+{
+	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_LM);
+}
+
+static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt)
+{
+	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE);
+}
+
+static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt)
+{
+	return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR);
+}
+
 static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
 {
 	return kvm_register_read(emul_to_vcpu(ctxt), reg);
@@ -6263,6 +6351,9 @@ static const struct x86_emulate_ops emulate_ops = {
 	.fix_hypercall       = emulator_fix_hypercall,
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
+	.guest_has_long_mode = emulator_guest_has_long_mode,
+	.guest_has_movbe     = emulator_guest_has_movbe,
+	.guest_has_fxsr      = emulator_guest_has_fxsr,
 	.set_nmi_mask        = emulator_set_nmi_mask,
 	.get_hflags          = emulator_get_hflags,
 	.set_hflags          = emulator_set_hflags,
@@ -6379,11 +6470,11 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type)
 	return 1;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  bool write_fault_to_shadow_pgtable,
 				  int emulation_type)
 {
-	gpa_t gpa = cr2;
+	gpa_t gpa = cr2_or_gpa;
 	kvm_pfn_t pfn;
 
 	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
@@ -6397,7 +6488,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
 		 */
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 		/*
 		 * If the mapping is invalid in guest, let cpu retry
@@ -6454,10 +6545,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
-			      unsigned long cr2,  int emulation_type)
+			      gpa_t cr2_or_gpa,  int emulation_type)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;
 
 	last_retry_eip = vcpu->arch.last_retry_eip;
 	last_retry_addr = vcpu->arch.last_retry_addr;
@@ -6486,14 +6577,14 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	if (x86_page_table_writing_insn(ctxt))
 		return false;
 
-	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
 		return false;
 
 	vcpu->arch.last_retry_eip = ctxt->eip;
-	vcpu->arch.last_retry_addr = cr2;
+	vcpu->arch.last_retry_addr = cr2_or_gpa;
 
 	if (!vcpu->arch.mmu->direct_map)
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
@@ -6639,11 +6730,8 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
 	return false;
 }
 
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			    unsigned long cr2,
-			    int emulation_type,
-			    void *insn,
-			    int insn_len)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			    int emulation_type, void *insn, int insn_len)
 {
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -6689,8 +6777,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 				kvm_queue_exception(vcpu, UD_VECTOR);
 				return 1;
 			}
-			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
-						emulation_type))
+			if (reexecute_instruction(vcpu, cr2_or_gpa,
+						  write_fault_to_spt,
+						  emulation_type))
 				return 1;
 			if (ctxt->have_exception) {
 				/*
@@ -6724,7 +6813,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		return 1;
 	}
 
-	if (retry_instruction(ctxt, cr2, emulation_type))
+	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
 		return 1;
 
 	/* this is needed for vmware backdoor interface to work since it
@@ -6736,7 +6825,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 restart:
 	/* Save the faulting GPA (cr2) in the address field */
-	ctxt->exception.address = cr2;
+	ctxt->exception.address = cr2_or_gpa;
 
 	r = x86_emulate_insn(ctxt);
 
@@ -6744,7 +6833,7 @@ restart:
 		return 1;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
 					emulation_type))
 			return 1;
 
@@ -7357,8 +7446,8 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
 {
 	struct kvm_lapic_irq lapic_irq;
 
-	lapic_irq.shorthand = 0;
-	lapic_irq.dest_mode = 0;
+	lapic_irq.shorthand = APIC_DEST_NOSHORT;
+	lapic_irq.dest_mode = APIC_DEST_PHYSICAL;
 	lapic_irq.level = 0;
 	lapic_irq.dest_id = apicid;
 	lapic_irq.msi_redir_hint = false;
@@ -7997,6 +8086,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_int_win =
 		dm_request_for_irq_injection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
+	enum exit_fastpath_completion exit_fastpath = EXIT_FASTPATH_NONE;
 
 	bool req_immediate_exit = false;
 
@@ -8198,8 +8288,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	trace_kvm_entry(vcpu->vcpu_id);
 	guest_enter_irqoff();
 
-	/* The preempt notifier should have taken care of the FPU already.  */
-	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -8243,7 +8334,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
-	kvm_x86_ops->handle_exit_irqoff(vcpu);
+	kvm_x86_ops->handle_exit_irqoff(vcpu, &exit_fastpath);
 
 	/*
 	 * Consume any pending interrupts, including the possible source of
@@ -8287,7 +8378,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_lapic_sync_from_vapic(vcpu);
 
 	vcpu->arch.gpa_available = false;
-	r = kvm_x86_ops->handle_exit(vcpu);
+	r = kvm_x86_ops->handle_exit(vcpu, exit_fastpath);
 	return r;
 
 cancel_injection:
@@ -8471,12 +8562,26 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void kvm_save_current_fpu(struct fpu *fpu)
+{
+	/*
+	 * If the target FPU state is not resident in the CPU registers, just
+	 * memcpy() from current, else save CPU state directly to the target.
+	 */
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&fpu->state, &current->thread.fpu.state,
+		       fpu_kernel_xstate_size);
+	else
+		copy_fpregs_to_fpstate(fpu);
+}
+
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
+	kvm_save_current_fpu(vcpu->arch.user_fpu);
+
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8492,7 +8597,8 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
+	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+
 	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();
@@ -8714,6 +8820,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
 	vcpu_load(vcpu);
+	if (kvm_mpx_supported())
+		kvm_load_guest_fpu(vcpu);
 
 	kvm_apic_accept_events(vcpu);
 	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
@@ -8722,6 +8830,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 	else
 		mp_state->mp_state = vcpu->arch.mp_state;
 
+	if (kvm_mpx_supported())
+		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
 	return 0;
 }
@@ -9082,33 +9192,90 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
-void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 {
-	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
-
-	kvmclock_reset(vcpu);
+	if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
+		pr_warn_once("kvm: SMP vm created on host with unstable TSC; "
+			     "guest TSC will not be reliable\n");
 
-	kvm_x86_ops->vcpu_free(vcpu);
-	free_cpumask_var(wbinvd_dirty_mask);
+	return 0;
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
-						unsigned int id)
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu;
+	struct page *page;
+	int r;
 
-	if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
-		printk_once(KERN_WARNING
-		"kvm: SMP vm created on host with unstable TSC; "
-		"guest TSC will not be reliable\n");
+	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
+	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+	else
+		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
 
-	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
+	kvm_set_tsc_khz(vcpu, max_tsc_khz);
 
-	return vcpu;
-}
+	r = kvm_mmu_create(vcpu);
+	if (r < 0)
+		return r;
+
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
+		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
+		if (r < 0)
+			goto fail_mmu_destroy;
+	} else
+		static_key_slow_inc(&kvm_no_apic_vcpu);
+
+	r = -ENOMEM;
+
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page)
+		goto fail_free_lapic;
+	vcpu->arch.pio_data = page_address(page);
+
+	vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4,
+				       GFP_KERNEL_ACCOUNT);
+	if (!vcpu->arch.mce_banks)
+		goto fail_free_pio_data;
+	vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;
+
+	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask,
+				GFP_KERNEL_ACCOUNT))
+		goto fail_free_mce_banks;
+
+	vcpu->arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						GFP_KERNEL_ACCOUNT);
+	if (!vcpu->arch.user_fpu) {
+		pr_err("kvm: failed to allocate userspace's fpu\n");
+		goto free_wbinvd_dirty_mask;
+	}
+
+	vcpu->arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
+						 GFP_KERNEL_ACCOUNT);
+	if (!vcpu->arch.guest_fpu) {
+		pr_err("kvm: failed to allocate vcpu's fpu\n");
+		goto free_user_fpu;
+	}
+	fx_init(vcpu);
+
+	vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+
+	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+
+	vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
+
+	kvm_async_pf_hash_reset(vcpu);
+	kvm_pmu_init(vcpu);
+
+	vcpu->arch.pending_external_vector = -1;
+	vcpu->arch.preempted_in_kernel = false;
+
+	kvm_hv_vcpu_init(vcpu);
+
+	r = kvm_x86_ops->vcpu_create(vcpu);
+	if (r)
+		goto free_guest_fpu;
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
 	vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
 	vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
 	kvm_vcpu_mtrr_init(vcpu);
@@ -9117,6 +9284,22 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	kvm_init_mmu(vcpu, false);
 	vcpu_put(vcpu);
 	return 0;
+
+free_guest_fpu:
+	kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+free_user_fpu:
+	kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
+free_wbinvd_dirty_mask:
+	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+fail_free_mce_banks:
+	kfree(vcpu->arch.mce_banks);
+fail_free_pio_data:
+	free_page((unsigned long)vcpu->arch.pio_data);
+fail_free_lapic:
+	kvm_free_lapic(vcpu);
+fail_mmu_destroy:
+	kvm_mmu_destroy(vcpu);
+	return r;
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
@@ -9149,13 +9332,29 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.apf.msr_val = 0;
+	struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache;
+	int idx;
 
-	vcpu_load(vcpu);
-	kvm_mmu_unload(vcpu);
-	vcpu_put(vcpu);
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
+
+	kvmclock_reset(vcpu);
 
 	kvm_x86_ops->vcpu_free(vcpu);
+
+	free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+	kmem_cache_free(x86_fpu_cache, vcpu->arch.user_fpu);
+	kmem_cache_free(x86_fpu_cache, vcpu->arch.guest_fpu);
+
+	kvm_hv_vcpu_uninit(vcpu);
+	kvm_pmu_destroy(vcpu);
+	kfree(vcpu->arch.mce_banks);
+	kvm_free_lapic(vcpu);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	kvm_mmu_destroy(vcpu);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	free_page((unsigned long)vcpu->arch.pio_data);
+	if (!lapic_in_kernel(vcpu))
+		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9171,7 +9370,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	vcpu->arch.nmi_injected = false;
 	kvm_clear_interrupt_queue(vcpu);
 	kvm_clear_exception_queue(vcpu);
-	vcpu->arch.exception.pending = false;
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	kvm_update_dr0123(vcpu);
@@ -9347,6 +9545,8 @@ int kvm_arch_hardware_setup(void)
 	if (r != 0)
 		return r;
 
+	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+
 	if (kvm_has_tsc_control) {
 		/*
 		 * Make sure the user can only configure tsc_khz values that
@@ -9375,6 +9575,13 @@ void kvm_arch_hardware_unsetup(void)
 
 int kvm_arch_check_processor_compat(void)
 {
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+
+	WARN_ON(!irqs_disabled());
+
+	if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits)
+		return -EIO;
+
 	return kvm_x86_ops->check_processor_compatibility();
 }
 
@@ -9392,98 +9599,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 struct static_key kvm_no_apic_vcpu __read_mostly;
 EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
 
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	struct page *page;
-	int r;
-
-	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
-	if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
-		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-	else
-		vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
-
-	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!page) {
-		r = -ENOMEM;
-		goto fail;
-	}
-	vcpu->arch.pio_data = page_address(page);
-
-	kvm_set_tsc_khz(vcpu, max_tsc_khz);
-
-	r = kvm_mmu_create(vcpu);
-	if (r < 0)
-		goto fail_free_pio_data;
-
-	if (irqchip_in_kernel(vcpu->kvm)) {
-		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu->kvm);
-		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
-		if (r < 0)
-			goto fail_mmu_destroy;
-	} else
-		static_key_slow_inc(&kvm_no_apic_vcpu);
-
-	vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4,
-				       GFP_KERNEL_ACCOUNT);
-	if (!vcpu->arch.mce_banks) {
-		r = -ENOMEM;
-		goto fail_free_lapic;
-	}
-	vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;
-
-	if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask,
-				GFP_KERNEL_ACCOUNT)) {
-		r = -ENOMEM;
-		goto fail_free_mce_banks;
-	}
-
-	fx_init(vcpu);
-
-	vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
-
-	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
-
-	vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
-
-	kvm_async_pf_hash_reset(vcpu);
-	kvm_pmu_init(vcpu);
-
-	vcpu->arch.pending_external_vector = -1;
-	vcpu->arch.preempted_in_kernel = false;
-
-	kvm_hv_vcpu_init(vcpu);
-
-	return 0;
-
-fail_free_mce_banks:
-	kfree(vcpu->arch.mce_banks);
-fail_free_lapic:
-	kvm_free_lapic(vcpu);
-fail_mmu_destroy:
-	kvm_mmu_destroy(vcpu);
-fail_free_pio_data:
-	free_page((unsigned long)vcpu->arch.pio_data);
-fail:
-	return r;
-}
-
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-	int idx;
-
-	kvm_hv_vcpu_uninit(vcpu);
-	kvm_pmu_destroy(vcpu);
-	kfree(vcpu->arch.mce_banks);
-	kvm_free_lapic(vcpu);
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	kvm_mmu_destroy(vcpu);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	free_page((unsigned long)vcpu->arch.pio_data);
-	if (!lapic_in_kernel(vcpu))
-		static_key_slow_dec(&kvm_no_apic_vcpu);
-}
-
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -9558,7 +9673,7 @@ static void kvm_free_vcpus(struct kvm *kvm)
 		kvm_unload_vcpu_mmu(vcpu);
 	}
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arch_vcpu_free(vcpu);
+		kvm_vcpu_destroy(vcpu);
 
 	mutex_lock(&kvm->lock);
 	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
@@ -9627,18 +9742,6 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
 }
 EXPORT_SYMBOL_GPL(__x86_set_memory_region);
 
-int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
-{
-	int r;
-
-	mutex_lock(&kvm->slots_lock);
-	r = __x86_set_memory_region(kvm, id, gpa, size);
-	mutex_unlock(&kvm->slots_lock);
-
-	return r;
-}
-EXPORT_SYMBOL_GPL(x86_set_memory_region);
-
 void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 {
 	kvm_mmu_pre_destroy_vm(kvm);
@@ -9652,9 +9755,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		 * unless the the memory map has changed due to process exit
 		 * or fd copying.
 		 */
-		x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0);
-		x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0);
-		x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
+		mutex_lock(&kvm->slots_lock);
+		__x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+					0, 0);
+		__x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
+					0, 0);
+		__x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0);
+		mutex_unlock(&kvm->slots_lock);
 	}
 	if (kvm_x86_ops->vm_destroy)
 		kvm_x86_ops->vm_destroy(kvm);
@@ -9758,11 +9865,18 @@ out_free:
 
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
+	struct kvm_vcpu *vcpu;
+	int i;
+
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
 	kvm_mmu_invalidate_mmio_sptes(kvm, gen);
+
+	/* Force re-initialization of steal_time cache */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -9792,7 +9906,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 	 *
 	 * The reason is, in case of PML, we need to set D-bit for any slots
 	 * with dirty logging disabled in order to eliminate unnecessary GPA
-	 * logging in PML buffer (and potential PML buffer full VMEXT). This
+	 * logging in PML buffer (and potential PML buffer full VMEXIT). This
 	 * guarantees leaving PML enabled during guest's lifetime won't have
 	 * any additional overhead from PML when guest is running with dirty
 	 * logging disabled for memory slots.
@@ -10014,7 +10128,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -10127,7 +10241,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
 	if (kvm_can_deliver_async_pf(vcpu) &&
@@ -10162,7 +10276,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
 
 	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
 	    !apf_get_user(vcpu, &val)) {
@@ -10284,7 +10398,6 @@ bool kvm_vector_hashing_enabled(void)
 {
 	return vector_hashing;
 }
-EXPORT_SYMBOL_GPL(kvm_vector_hashing_enabled);
 
 bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 {
@@ -10292,6 +10405,28 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
+u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu)
+{
+	uint64_t bits = SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD;
+
+	/* The STIBP bit doesn't fault even if it's not advertised */
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) &&
+	    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS))
+		bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP);
+	if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL) &&
+	    !boot_cpu_has(X86_FEATURE_AMD_IBRS))
+		bits &= ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP);
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL_SSBD) &&
+	    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
+		bits &= ~SPEC_CTRL_SSBD;
+	if (!boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) &&
+	    !boot_cpu_has(X86_FEATURE_AMD_SSBD))
+		bits &= ~SPEC_CTRL_SSBD;
+
+	return bits;
+}
+EXPORT_SYMBOL_GPL(kvm_spec_ctrl_valid_bits);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 29391af8871d..2d2ff855773b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -144,11 +144,6 @@ static inline bool is_pae_paging(struct kvm_vcpu *vcpu)
 	return !is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu);
 }
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
 {
 	return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48;
@@ -166,21 +161,13 @@ static inline u64 get_canonical(u64 la, u8 vaddr_bits)
 
 static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
 {
-#ifdef CONFIG_X86_64
 	return get_canonical(la, vcpu_virt_addr_bits(vcpu)) != la;
-#else
-	return false;
-#endif
 }
 
 static inline bool emul_is_noncanonical_address(u64 la,
 						struct x86_emulate_ctxt *ctxt)
 {
-#ifdef CONFIG_X86_64
 	return get_canonical(la, ctxt_virt_addr_bits(ctxt)) != la;
-#else
-	return false;
-#endif
 }
 
 static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
@@ -289,8 +276,9 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
 bool kvm_vector_hashing_enabled(void);
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len);
+enum exit_fastpath_completion handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
 				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
@@ -369,7 +357,14 @@ static inline bool kvm_pat_valid(u64 data)
 	return (data | ((data & 0x0202020202020202ull) << 1)) == data;
 }
 
+static inline bool kvm_dr7_valid(unsigned long data)
+{
+	/* Bits [63:32] are reserved */
+	return !(data >> 32);
+}
+
 void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu);
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
+u64 kvm_spec_ctrl_valid_bits(struct kvm_vcpu *vcpu);
 
 #endif
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 8908c58bd6cd..53adc1762ec0 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -929,7 +929,7 @@ EndTable
 
 GrpTable: Grp3_2
 0: TEST Ev,Iz
-1:
+1: TEST Ev,Iz
 2: NOT Ev
 3: NEG Ev
 4: MUL rAX,Ev
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 345848f270e3..98f7c6fa2eaa 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -28,8 +28,8 @@ CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_X86_PTDUMP_CORE)	+= dump_pagetables.o
-obj-$(CONFIG_X86_PTDUMP)	+= debug_pagetables.o
+obj-$(CONFIG_PTDUMP_CORE)	+= dump_pagetables.o
+obj-$(CONFIG_PTDUMP_DEBUGFS)	+= debug_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
@@ -45,7 +45,6 @@ obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
 obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
-obj-$(CONFIG_X86_INTEL_MPX)			+= mpx.o
 obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
 obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
 obj-$(CONFIG_PAGE_TABLE_ISOLATION)		+= pti.o
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index 39001a401eff..4a3b62f780b4 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -7,7 +7,7 @@
 
 static int ptdump_show(struct seq_file *m, void *v)
 {
-	ptdump_walk_pgd_level_debugfs(m, NULL, false);
+	ptdump_walk_pgd_level_debugfs(m, &init_mm, false);
 	return 0;
 }
 
@@ -15,11 +15,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 static int ptdump_curknl_show(struct seq_file *m, void *v)
 {
-	if (current->mm->pgd) {
-		down_read(&current->mm->mmap_sem);
-		ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
-		up_read(&current->mm->mmap_sem);
-	}
+	if (current->mm->pgd)
+		ptdump_walk_pgd_level_debugfs(m, current->mm, false);
 	return 0;
 }
 
@@ -28,11 +25,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curknl);
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 static int ptdump_curusr_show(struct seq_file *m, void *v)
 {
-	if (current->mm->pgd) {
-		down_read(&current->mm->mmap_sem);
-		ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
-		up_read(&current->mm->mmap_sem);
-	}
+	if (current->mm->pgd)
+		ptdump_walk_pgd_level_debugfs(m, current->mm, true);
 	return 0;
 }
 
@@ -43,7 +37,7 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curusr);
 static int ptdump_efi_show(struct seq_file *m, void *v)
 {
 	if (efi_mm.pgd)
-		ptdump_walk_pgd_level_debugfs(m, efi_mm.pgd, false);
+		ptdump_walk_pgd_level_debugfs(m, &efi_mm, false);
 	return 0;
 }
 
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ab67822fd2f4..64229dad7eab 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -16,6 +16,7 @@
 #include <linux/seq_file.h>
 #include <linux/highmem.h>
 #include <linux/pci.h>
+#include <linux/ptdump.h>
 
 #include <asm/e820/types.h>
 #include <asm/pgtable.h>
@@ -26,16 +27,18 @@
  * when a "break" in the continuity is found.
  */
 struct pg_state {
+	struct ptdump_state ptdump;
 	int level;
-	pgprot_t current_prot;
+	pgprotval_t current_prot;
 	pgprotval_t effective_prot;
+	pgprotval_t prot_levels[5];
 	unsigned long start_address;
-	unsigned long current_address;
 	const struct addr_marker *marker;
 	unsigned long lines;
 	bool to_dmesg;
 	bool check_wx;
 	unsigned long wx_pages;
+	struct seq_file *seq;
 };
 
 struct addr_marker {
@@ -174,11 +177,10 @@ static struct addr_marker address_markers[] = {
 /*
  * Print a readable form of a pgprot_t to the seq_file
  */
-static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
+static void printk_prot(struct seq_file *m, pgprotval_t pr, int level, bool dmsg)
 {
-	pgprotval_t pr = pgprot_val(prot);
 	static const char * const level_name[] =
-		{ "cr3", "pgd", "p4d", "pud", "pmd", "pte" };
+		{ "pgd", "p4d", "pud", "pmd", "pte" };
 
 	if (!(pr & _PAGE_PRESENT)) {
 		/* Not present */
@@ -202,12 +204,12 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 			pt_dump_cont_printf(m, dmsg, "    ");
 
 		/* Bit 7 has a different meaning on level 3 vs 4 */
-		if (level <= 4 && pr & _PAGE_PSE)
+		if (level <= 3 && pr & _PAGE_PSE)
 			pt_dump_cont_printf(m, dmsg, "PSE ");
 		else
 			pt_dump_cont_printf(m, dmsg, "    ");
-		if ((level == 5 && pr & _PAGE_PAT) ||
-		    ((level == 4 || level == 3) && pr & _PAGE_PAT_LARGE))
+		if ((level == 4 && pr & _PAGE_PAT) ||
+		    ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
 			pt_dump_cont_printf(m, dmsg, "PAT ");
 		else
 			pt_dump_cont_printf(m, dmsg, "    ");
@@ -223,24 +225,11 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 	pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
 }
 
-/*
- * On 64 bits, sign-extend the 48 bit address to 64 bit
- */
-static unsigned long normalize_addr(unsigned long u)
-{
-	int shift;
-	if (!IS_ENABLED(CONFIG_X86_64))
-		return u;
-
-	shift = 64 - (__VIRTUAL_MASK_SHIFT + 1);
-	return (signed long)(u << shift) >> shift;
-}
-
-static void note_wx(struct pg_state *st)
+static void note_wx(struct pg_state *st, unsigned long addr)
 {
 	unsigned long npages;
 
-	npages = (st->current_address - st->start_address) / PAGE_SIZE;
+	npages = (addr - st->start_address) / PAGE_SIZE;
 
 #ifdef CONFIG_PCI_BIOS
 	/*
@@ -248,7 +237,7 @@ static void note_wx(struct pg_state *st)
 	 * Inform about it, but avoid the warning.
 	 */
 	if (pcibios_enabled && st->start_address >= PAGE_OFFSET + BIOS_BEGIN &&
-	    st->current_address <= PAGE_OFFSET + BIOS_END) {
+	    addr <= PAGE_OFFSET + BIOS_END) {
 		pr_warn_once("x86/mm: PCI BIOS W+X mapping %lu pages\n", npages);
 		return;
 	}
@@ -260,27 +249,47 @@ static void note_wx(struct pg_state *st)
 		  (void *)st->start_address);
 }
 
+static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
+{
+	return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |
+	       ((prot1 | prot2) & _PAGE_NX);
+}
+
 /*
  * This function gets called on a break in a continuous series
  * of PTE entries; the next one is different so we need to
  * print what we collected so far.
  */
-static void note_page(struct seq_file *m, struct pg_state *st,
-		      pgprot_t new_prot, pgprotval_t new_eff, int level)
+static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
+		      unsigned long val)
 {
-	pgprotval_t prot, cur, eff;
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	pgprotval_t new_prot, new_eff;
+	pgprotval_t cur, eff;
 	static const char units[] = "BKMGTPE";
+	struct seq_file *m = st->seq;
+
+	new_prot = val & PTE_FLAGS_MASK;
+
+	if (level > 0) {
+		new_eff = effective_prot(st->prot_levels[level - 1],
+					 new_prot);
+	} else {
+		new_eff = new_prot;
+	}
+
+	if (level >= 0)
+		st->prot_levels[level] = new_eff;
 
 	/*
 	 * If we have a "break" in the series, we need to flush the state that
 	 * we have now. "break" is either changing perms, levels or
 	 * address space marker.
 	 */
-	prot = pgprot_val(new_prot);
-	cur = pgprot_val(st->current_prot);
+	cur = st->current_prot;
 	eff = st->effective_prot;
 
-	if (!st->level) {
+	if (st->level == -1) {
 		/* First entry */
 		st->current_prot = new_prot;
 		st->effective_prot = new_eff;
@@ -289,14 +298,14 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		st->lines = 0;
 		pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
 				   st->marker->name);
-	} else if (prot != cur || new_eff != eff || level != st->level ||
-		   st->current_address >= st->marker[1].start_address) {
+	} else if (new_prot != cur || new_eff != eff || level != st->level ||
+		   addr >= st->marker[1].start_address) {
 		const char *unit = units;
 		unsigned long delta;
 		int width = sizeof(unsigned long) * 2;
 
 		if (st->check_wx && (eff & _PAGE_RW) && !(eff & _PAGE_NX))
-			note_wx(st);
+			note_wx(st, addr);
 
 		/*
 		 * Now print the actual finished series
@@ -306,9 +315,9 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 			pt_dump_seq_printf(m, st->to_dmesg,
 					   "0x%0*lx-0x%0*lx   ",
 					   width, st->start_address,
-					   width, st->current_address);
+					   width, addr);
 
-			delta = st->current_address - st->start_address;
+			delta = addr - st->start_address;
 			while (!(delta & 1023) && unit[1]) {
 				delta >>= 10;
 				unit++;
@@ -325,7 +334,7 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 		 * such as the start of vmalloc space etc.
 		 * This helps in the interpretation.
 		 */
-		if (st->current_address >= st->marker[1].start_address) {
+		if (addr >= st->marker[1].start_address) {
 			if (st->marker->max_lines &&
 			    st->lines > st->marker->max_lines) {
 				unsigned long nskip =
@@ -341,222 +350,45 @@ static void note_page(struct seq_file *m, struct pg_state *st,
 					   st->marker->name);
 		}
 
-		st->start_address = st->current_address;
+		st->start_address = addr;
 		st->current_prot = new_prot;
 		st->effective_prot = new_eff;
 		st->level = level;
 	}
 }
 
-static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
-{
-	return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |
-	       ((prot1 | prot2) & _PAGE_NX);
-}
-
-static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr,
-			   pgprotval_t eff_in, unsigned long P)
-{
-	int i;
-	pte_t *pte;
-	pgprotval_t prot, eff;
-
-	for (i = 0; i < PTRS_PER_PTE; i++) {
-		st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT);
-		pte = pte_offset_map(&addr, st->current_address);
-		prot = pte_flags(*pte);
-		eff = effective_prot(eff_in, prot);
-		note_page(m, st, __pgprot(prot), eff, 5);
-		pte_unmap(pte);
-	}
-}
-#ifdef CONFIG_KASAN
-
-/*
- * This is an optimization for KASAN=y case. Since all kasan page tables
- * eventually point to the kasan_early_shadow_page we could call note_page()
- * right away without walking through lower level page tables. This saves
- * us dozens of seconds (minutes for 5-level config) while checking for
- * W+X mapping or reading kernel_page_tables debugfs file.
- */
-static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
-				void *pt)
-{
-	if (__pa(pt) == __pa(kasan_early_shadow_pmd) ||
-	    (pgtable_l5_enabled() &&
-			__pa(pt) == __pa(kasan_early_shadow_p4d)) ||
-	    __pa(pt) == __pa(kasan_early_shadow_pud)) {
-		pgprotval_t prot = pte_flags(kasan_early_shadow_pte[0]);
-		note_page(m, st, __pgprot(prot), 0, 5);
-		return true;
-	}
-	return false;
-}
-#else
-static inline bool kasan_page_table(struct seq_file *m, struct pg_state *st,
-				void *pt)
-{
-	return false;
-}
-#endif
-
-#if PTRS_PER_PMD > 1
-
-static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
-			   pgprotval_t eff_in, unsigned long P)
-{
-	int i;
-	pmd_t *start, *pmd_start;
-	pgprotval_t prot, eff;
-
-	pmd_start = start = (pmd_t *)pud_page_vaddr(addr);
-	for (i = 0; i < PTRS_PER_PMD; i++) {
-		st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT);
-		if (!pmd_none(*start)) {
-			prot = pmd_flags(*start);
-			eff = effective_prot(eff_in, prot);
-			if (pmd_large(*start) || !pmd_present(*start)) {
-				note_page(m, st, __pgprot(prot), eff, 4);
-			} else if (!kasan_page_table(m, st, pmd_start)) {
-				walk_pte_level(m, st, *start, eff,
-					       P + i * PMD_LEVEL_MULT);
-			}
-		} else
-			note_page(m, st, __pgprot(0), 0, 4);
-		start++;
-	}
-}
-
-#else
-#define walk_pmd_level(m,s,a,e,p) walk_pte_level(m,s,__pmd(pud_val(a)),e,p)
-#define pud_large(a) pmd_large(__pmd(pud_val(a)))
-#define pud_none(a)  pmd_none(__pmd(pud_val(a)))
-#endif
-
-#if PTRS_PER_PUD > 1
-
-static void walk_pud_level(struct seq_file *m, struct pg_state *st, p4d_t addr,
-			   pgprotval_t eff_in, unsigned long P)
-{
-	int i;
-	pud_t *start, *pud_start;
-	pgprotval_t prot, eff;
-
-	pud_start = start = (pud_t *)p4d_page_vaddr(addr);
-
-	for (i = 0; i < PTRS_PER_PUD; i++) {
-		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
-		if (!pud_none(*start)) {
-			prot = pud_flags(*start);
-			eff = effective_prot(eff_in, prot);
-			if (pud_large(*start) || !pud_present(*start)) {
-				note_page(m, st, __pgprot(prot), eff, 3);
-			} else if (!kasan_page_table(m, st, pud_start)) {
-				walk_pmd_level(m, st, *start, eff,
-					       P + i * PUD_LEVEL_MULT);
-			}
-		} else
-			note_page(m, st, __pgprot(0), 0, 3);
-
-		start++;
-	}
-}
-
-#else
-#define walk_pud_level(m,s,a,e,p) walk_pmd_level(m,s,__pud(p4d_val(a)),e,p)
-#define p4d_large(a) pud_large(__pud(p4d_val(a)))
-#define p4d_none(a)  pud_none(__pud(p4d_val(a)))
-#endif
-
-static void walk_p4d_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
-			   pgprotval_t eff_in, unsigned long P)
-{
-	int i;
-	p4d_t *start, *p4d_start;
-	pgprotval_t prot, eff;
-
-	if (PTRS_PER_P4D == 1)
-		return walk_pud_level(m, st, __p4d(pgd_val(addr)), eff_in, P);
-
-	p4d_start = start = (p4d_t *)pgd_page_vaddr(addr);
-
-	for (i = 0; i < PTRS_PER_P4D; i++) {
-		st->current_address = normalize_addr(P + i * P4D_LEVEL_MULT);
-		if (!p4d_none(*start)) {
-			prot = p4d_flags(*start);
-			eff = effective_prot(eff_in, prot);
-			if (p4d_large(*start) || !p4d_present(*start)) {
-				note_page(m, st, __pgprot(prot), eff, 2);
-			} else if (!kasan_page_table(m, st, p4d_start)) {
-				walk_pud_level(m, st, *start, eff,
-					       P + i * P4D_LEVEL_MULT);
-			}
-		} else
-			note_page(m, st, __pgprot(0), 0, 2);
-
-		start++;
-	}
-}
-
-#define pgd_large(a) (pgtable_l5_enabled() ? pgd_large(a) : p4d_large(__p4d(pgd_val(a))))
-#define pgd_none(a)  (pgtable_l5_enabled() ? pgd_none(a) : p4d_none(__p4d(pgd_val(a))))
-
-static inline bool is_hypervisor_range(int idx)
-{
-#ifdef CONFIG_X86_64
-	/*
-	 * A hole in the beginning of kernel address space reserved
-	 * for a hypervisor.
-	 */
-	return	(idx >= pgd_index(GUARD_HOLE_BASE_ADDR)) &&
-		(idx <  pgd_index(GUARD_HOLE_END_ADDR));
-#else
-	return false;
-#endif
-}
-
-static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
+static void ptdump_walk_pgd_level_core(struct seq_file *m,
+				       struct mm_struct *mm, pgd_t *pgd,
 				       bool checkwx, bool dmesg)
 {
-	pgd_t *start = INIT_PGD;
-	pgprotval_t prot, eff;
-	int i;
-	struct pg_state st = {};
-
-	if (pgd) {
-		start = pgd;
-		st.to_dmesg = dmesg;
-	}
+	const struct ptdump_range ptdump_ranges[] = {
+#ifdef CONFIG_X86_64
 
-	st.check_wx = checkwx;
-	if (checkwx)
-		st.wx_pages = 0;
+#define normalize_addr_shift (64 - (__VIRTUAL_MASK_SHIFT + 1))
+#define normalize_addr(u) ((signed long)((u) << normalize_addr_shift) >> \
+			   normalize_addr_shift)
 
-	for (i = 0; i < PTRS_PER_PGD; i++) {
-		st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
-		if (!pgd_none(*start) && !is_hypervisor_range(i)) {
-			prot = pgd_flags(*start);
-#ifdef CONFIG_X86_PAE
-			eff = _PAGE_USER | _PAGE_RW;
+	{0, PTRS_PER_PGD * PGD_LEVEL_MULT / 2},
+	{normalize_addr(PTRS_PER_PGD * PGD_LEVEL_MULT / 2), ~0UL},
 #else
-			eff = prot;
+	{0, ~0UL},
 #endif
-			if (pgd_large(*start) || !pgd_present(*start)) {
-				note_page(m, &st, __pgprot(prot), eff, 1);
-			} else {
-				walk_p4d_level(m, &st, *start, eff,
-					       i * PGD_LEVEL_MULT);
-			}
-		} else
-			note_page(m, &st, __pgprot(0), 0, 1);
+	{0, 0}
+};
 
-		cond_resched();
-		start++;
-	}
+	struct pg_state st = {
+		.ptdump = {
+			.note_page	= note_page,
+			.range		= ptdump_ranges
+		},
+		.level = -1,
+		.to_dmesg	= dmesg,
+		.check_wx	= checkwx,
+		.seq		= m
+	};
+
+	ptdump_walk_pgd(&st.ptdump, mm, pgd);
 
-	/* Flush out the last page */
-	st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT);
-	note_page(m, &st, __pgprot(0), 0, 0);
 	if (!checkwx)
 		return;
 	if (st.wx_pages)
@@ -566,18 +398,20 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 		pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n");
 }
 
-void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
+void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm)
 {
-	ptdump_walk_pgd_level_core(m, pgd, false, true);
+	ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true);
 }
 
-void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
+				   bool user)
 {
+	pgd_t *pgd = mm->pgd;
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 	if (user && boot_cpu_has(X86_FEATURE_PTI))
 		pgd = kernel_to_user_pgdp(pgd);
 #endif
-	ptdump_walk_pgd_level_core(m, pgd, false, false);
+	ptdump_walk_pgd_level_core(m, mm, pgd, false, false);
 }
 EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
 
@@ -592,13 +426,13 @@ void ptdump_walk_user_pgd_level_checkwx(void)
 
 	pr_info("x86/mm: Checking user space page tables\n");
 	pgd = kernel_to_user_pgdp(pgd);
-	ptdump_walk_pgd_level_core(NULL, pgd, true, false);
+	ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false);
 #endif
 }
 
 void ptdump_walk_pgd_level_checkwx(void)
 {
-	ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+	ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
 }
 
 static int __init pt_dump_init(void)
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index fab095362c50..5bfd5aef5378 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -19,7 +19,6 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 #include <asm/elf.h>
-#include <asm/mpx.h>
 
 #if 0	/* This is just for testing */
 struct page *
@@ -151,10 +150,6 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
 
-	addr = mpx_unmapped_area_check(addr, len, flags);
-	if (IS_ERR_VALUE(addr))
-		return addr;
-
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index aae9a933dfd4..cb91eccc4960 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -163,8 +163,6 @@ unsigned long get_mmap_base(int is_legacy)
 
 const char *arch_vma_name(struct vm_area_struct *vma)
 {
-	if (vma->vm_flags & VM_MPX)
-		return "[mpx]";
 	return NULL;
 }
 
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
deleted file mode 100644
index 895fb7a9294d..000000000000
--- a/arch/x86/mm/mpx.c
+++ /dev/null
@@ -1,938 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * mpx.c - Memory Protection eXtensions
- *
- * Copyright (c) 2014, Intel Corporation.
- * Qiaowei Ren <qiaowei.ren@intel.com>
- * Dave Hansen <dave.hansen@intel.com>
- */
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/mm_types.h>
-#include <linux/mman.h>
-#include <linux/syscalls.h>
-#include <linux/sched/sysctl.h>
-
-#include <asm/insn.h>
-#include <asm/insn-eval.h>
-#include <asm/mmu_context.h>
-#include <asm/mpx.h>
-#include <asm/processor.h>
-#include <asm/fpu/internal.h>
-
-#define CREATE_TRACE_POINTS
-#include <asm/trace/mpx.h>
-
-static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
-{
-	if (is_64bit_mm(mm))
-		return MPX_BD_SIZE_BYTES_64;
-	else
-		return MPX_BD_SIZE_BYTES_32;
-}
-
-static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
-{
-	if (is_64bit_mm(mm))
-		return MPX_BT_SIZE_BYTES_64;
-	else
-		return MPX_BT_SIZE_BYTES_32;
-}
-
-/*
- * This is really a simplified "vm_mmap". it only handles MPX
- * bounds tables (the bounds directory is user-allocated).
- */
-static unsigned long mpx_mmap(unsigned long len)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, populate;
-
-	/* Only bounds table can be allocated here */
-	if (len != mpx_bt_size_bytes(mm))
-		return -EINVAL;
-
-	down_write(&mm->mmap_sem);
-	addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE,
-		       MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate, NULL);
-	up_write(&mm->mmap_sem);
-	if (populate)
-		mm_populate(addr, populate);
-
-	return addr;
-}
-
-static int mpx_insn_decode(struct insn *insn,
-			   struct pt_regs *regs)
-{
-	unsigned char buf[MAX_INSN_SIZE];
-	int x86_64 = !test_thread_flag(TIF_IA32);
-	int not_copied;
-	int nr_copied;
-
-	not_copied = copy_from_user(buf, (void __user *)regs->ip, sizeof(buf));
-	nr_copied = sizeof(buf) - not_copied;
-	/*
-	 * The decoder _should_ fail nicely if we pass it a short buffer.
-	 * But, let's not depend on that implementation detail.  If we
-	 * did not get anything, just error out now.
-	 */
-	if (!nr_copied)
-		return -EFAULT;
-	insn_init(insn, buf, nr_copied, x86_64);
-	insn_get_length(insn);
-	/*
-	 * copy_from_user() tries to get as many bytes as we could see in
-	 * the largest possible instruction.  If the instruction we are
-	 * after is shorter than that _and_ we attempt to copy from
-	 * something unreadable, we might get a short read.  This is OK
-	 * as long as the read did not stop in the middle of the
-	 * instruction.  Check to see if we got a partial instruction.
-	 */
-	if (nr_copied < insn->length)
-		return -EFAULT;
-
-	insn_get_opcode(insn);
-	/*
-	 * We only _really_ need to decode bndcl/bndcn/bndcu
-	 * Error out on anything else.
-	 */
-	if (insn->opcode.bytes[0] != 0x0f)
-		goto bad_opcode;
-	if ((insn->opcode.bytes[1] != 0x1a) &&
-	    (insn->opcode.bytes[1] != 0x1b))
-		goto bad_opcode;
-
-	return 0;
-bad_opcode:
-	return -EINVAL;
-}
-
-/*
- * If a bounds overflow occurs then a #BR is generated. This
- * function decodes MPX instructions to get violation address
- * and set this address into extended struct siginfo.
- *
- * Note that this is not a super precise way of doing this.
- * Userspace could have, by the time we get here, written
- * anything it wants in to the instructions.  We can not
- * trust anything about it.  They might not be valid
- * instructions or might encode invalid registers, etc...
- */
-int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs)
-{
-	const struct mpx_bndreg_state *bndregs;
-	const struct mpx_bndreg *bndreg;
-	struct insn insn;
-	uint8_t bndregno;
-	int err;
-
-	err = mpx_insn_decode(&insn, regs);
-	if (err)
-		goto err_out;
-
-	/*
-	 * We know at this point that we are only dealing with
-	 * MPX instructions.
-	 */
-	insn_get_modrm(&insn);
-	bndregno = X86_MODRM_REG(insn.modrm.value);
-	if (bndregno > 3) {
-		err = -EINVAL;
-		goto err_out;
-	}
-	/* get bndregs field from current task's xsave area */
-	bndregs = get_xsave_field_ptr(XFEATURE_BNDREGS);
-	if (!bndregs) {
-		err = -EINVAL;
-		goto err_out;
-	}
-	/* now go select the individual register in the set of 4 */
-	bndreg = &bndregs->bndreg[bndregno];
-
-	/*
-	 * The registers are always 64-bit, but the upper 32
-	 * bits are ignored in 32-bit mode.  Also, note that the
-	 * upper bounds are architecturally represented in 1's
-	 * complement form.
-	 *
-	 * The 'unsigned long' cast is because the compiler
-	 * complains when casting from integers to different-size
-	 * pointers.
-	 */
-	info->lower = (void __user *)(unsigned long)bndreg->lower_bound;
-	info->upper = (void __user *)(unsigned long)~bndreg->upper_bound;
-	info->addr  = insn_get_addr_ref(&insn, regs);
-
-	/*
-	 * We were not able to extract an address from the instruction,
-	 * probably because there was something invalid in it.
-	 */
-	if (info->addr == (void __user *)-1) {
-		err = -EINVAL;
-		goto err_out;
-	}
-	trace_mpx_bounds_register_exception(info->addr, bndreg);
-	return 0;
-err_out:
-	/* info might be NULL, but kfree() handles that */
-	return err;
-}
-
-static __user void *mpx_get_bounds_dir(void)
-{
-	const struct mpx_bndcsr *bndcsr;
-
-	if (!cpu_feature_enabled(X86_FEATURE_MPX))
-		return MPX_INVALID_BOUNDS_DIR;
-
-	/*
-	 * The bounds directory pointer is stored in a register
-	 * only accessible if we first do an xsave.
-	 */
-	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
-	if (!bndcsr)
-		return MPX_INVALID_BOUNDS_DIR;
-
-	/*
-	 * Make sure the register looks valid by checking the
-	 * enable bit.
-	 */
-	if (!(bndcsr->bndcfgu & MPX_BNDCFG_ENABLE_FLAG))
-		return MPX_INVALID_BOUNDS_DIR;
-
-	/*
-	 * Lastly, mask off the low bits used for configuration
-	 * flags, and return the address of the bounds table.
-	 */
-	return (void __user *)(unsigned long)
-		(bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
-}
-
-int mpx_enable_management(void)
-{
-	void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
-	struct mm_struct *mm = current->mm;
-	int ret = 0;
-
-	/*
-	 * runtime in the userspace will be responsible for allocation of
-	 * the bounds directory. Then, it will save the base of the bounds
-	 * directory into XSAVE/XRSTOR Save Area and enable MPX through
-	 * XRSTOR instruction.
-	 *
-	 * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is
-	 * expected to be relatively expensive. Storing the bounds
-	 * directory here means that we do not have to do xsave in the
-	 * unmap path; we can just use mm->context.bd_addr instead.
-	 */
-	bd_base = mpx_get_bounds_dir();
-	down_write(&mm->mmap_sem);
-
-	/* MPX doesn't support addresses above 47 bits yet. */
-	if (find_vma(mm, DEFAULT_MAP_WINDOW)) {
-		pr_warn_once("%s (%d): MPX cannot handle addresses "
-				"above 47-bits. Disabling.",
-				current->comm, current->pid);
-		ret = -ENXIO;
-		goto out;
-	}
-	mm->context.bd_addr = bd_base;
-	if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR)
-		ret = -ENXIO;
-out:
-	up_write(&mm->mmap_sem);
-	return ret;
-}
-
-int mpx_disable_management(void)
-{
-	struct mm_struct *mm = current->mm;
-
-	if (!cpu_feature_enabled(X86_FEATURE_MPX))
-		return -ENXIO;
-
-	down_write(&mm->mmap_sem);
-	mm->context.bd_addr = MPX_INVALID_BOUNDS_DIR;
-	up_write(&mm->mmap_sem);
-	return 0;
-}
-
-static int mpx_cmpxchg_bd_entry(struct mm_struct *mm,
-		unsigned long *curval,
-		unsigned long __user *addr,
-		unsigned long old_val, unsigned long new_val)
-{
-	int ret;
-	/*
-	 * user_atomic_cmpxchg_inatomic() actually uses sizeof()
-	 * the pointer that we pass to it to figure out how much
-	 * data to cmpxchg.  We have to be careful here not to
-	 * pass a pointer to a 64-bit data type when we only want
-	 * a 32-bit copy.
-	 */
-	if (is_64bit_mm(mm)) {
-		ret = user_atomic_cmpxchg_inatomic(curval,
-				addr, old_val, new_val);
-	} else {
-		u32 uninitialized_var(curval_32);
-		u32 old_val_32 = old_val;
-		u32 new_val_32 = new_val;
-		u32 __user *addr_32 = (u32 __user *)addr;
-
-		ret = user_atomic_cmpxchg_inatomic(&curval_32,
-				addr_32, old_val_32, new_val_32);
-		*curval = curval_32;
-	}
-	return ret;
-}
-
-/*
- * With 32-bit mode, a bounds directory is 4MB, and the size of each
- * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB,
- * and the size of each bounds table is 4MB.
- */
-static int allocate_bt(struct mm_struct *mm, long __user *bd_entry)
-{
-	unsigned long expected_old_val = 0;
-	unsigned long actual_old_val = 0;
-	unsigned long bt_addr;
-	unsigned long bd_new_entry;
-	int ret = 0;
-
-	/*
-	 * Carve the virtual space out of userspace for the new
-	 * bounds table:
-	 */
-	bt_addr = mpx_mmap(mpx_bt_size_bytes(mm));
-	if (IS_ERR((void *)bt_addr))
-		return PTR_ERR((void *)bt_addr);
-	/*
-	 * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
-	 */
-	bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
-
-	/*
-	 * Go poke the address of the new bounds table in to the
-	 * bounds directory entry out in userspace memory.  Note:
-	 * we may race with another CPU instantiating the same table.
-	 * In that case the cmpxchg will see an unexpected
-	 * 'actual_old_val'.
-	 *
-	 * This can fault, but that's OK because we do not hold
-	 * mmap_sem at this point, unlike some of the other part
-	 * of the MPX code that have to pagefault_disable().
-	 */
-	ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,	bd_entry,
-				   expected_old_val, bd_new_entry);
-	if (ret)
-		goto out_unmap;
-
-	/*
-	 * The user_atomic_cmpxchg_inatomic() will only return nonzero
-	 * for faults, *not* if the cmpxchg itself fails.  Now we must
-	 * verify that the cmpxchg itself completed successfully.
-	 */
-	/*
-	 * We expected an empty 'expected_old_val', but instead found
-	 * an apparently valid entry.  Assume we raced with another
-	 * thread to instantiate this table and desclare succecss.
-	 */
-	if (actual_old_val & MPX_BD_ENTRY_VALID_FLAG) {
-		ret = 0;
-		goto out_unmap;
-	}
-	/*
-	 * We found a non-empty bd_entry but it did not have the
-	 * VALID_FLAG set.  Return an error which will result in
-	 * a SEGV since this probably means that somebody scribbled
-	 * some invalid data in to a bounds table.
-	 */
-	if (expected_old_val != actual_old_val) {
-		ret = -EINVAL;
-		goto out_unmap;
-	}
-	trace_mpx_new_bounds_table(bt_addr);
-	return 0;
-out_unmap:
-	vm_munmap(bt_addr, mpx_bt_size_bytes(mm));
-	return ret;
-}
-
-/*
- * When a BNDSTX instruction attempts to save bounds to a bounds
- * table, it will first attempt to look up the table in the
- * first-level bounds directory.  If it does not find a table in
- * the directory, a #BR is generated and we get here in order to
- * allocate a new table.
- *
- * With 32-bit mode, the size of BD is 4MB, and the size of each
- * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
- * and the size of each bound table is 4MB.
- */
-static int do_mpx_bt_fault(void)
-{
-	unsigned long bd_entry, bd_base;
-	const struct mpx_bndcsr *bndcsr;
-	struct mm_struct *mm = current->mm;
-
-	bndcsr = get_xsave_field_ptr(XFEATURE_BNDCSR);
-	if (!bndcsr)
-		return -EINVAL;
-	/*
-	 * Mask off the preserve and enable bits
-	 */
-	bd_base = bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK;
-	/*
-	 * The hardware provides the address of the missing or invalid
-	 * entry via BNDSTATUS, so we don't have to go look it up.
-	 */
-	bd_entry = bndcsr->bndstatus & MPX_BNDSTA_ADDR_MASK;
-	/*
-	 * Make sure the directory entry is within where we think
-	 * the directory is.
-	 */
-	if ((bd_entry < bd_base) ||
-	    (bd_entry >= bd_base + mpx_bd_size_bytes(mm)))
-		return -EINVAL;
-
-	return allocate_bt(mm, (long __user *)bd_entry);
-}
-
-int mpx_handle_bd_fault(void)
-{
-	/*
-	 * Userspace never asked us to manage the bounds tables,
-	 * so refuse to help.
-	 */
-	if (!kernel_managing_mpx_tables(current->mm))
-		return -EINVAL;
-
-	return do_mpx_bt_fault();
-}
-
-/*
- * A thin wrapper around get_user_pages().  Returns 0 if the
- * fault was resolved or -errno if not.
- */
-static int mpx_resolve_fault(long __user *addr, int write)
-{
-	long gup_ret;
-	int nr_pages = 1;
-
-	gup_ret = get_user_pages((unsigned long)addr, nr_pages,
-			write ? FOLL_WRITE : 0,	NULL, NULL);
-	/*
-	 * get_user_pages() returns number of pages gotten.
-	 * 0 means we failed to fault in and get anything,
-	 * probably because 'addr' is bad.
-	 */
-	if (!gup_ret)
-		return -EFAULT;
-	/* Other error, return it */
-	if (gup_ret < 0)
-		return gup_ret;
-	/* must have gup'd a page and gup_ret>0, success */
-	return 0;
-}
-
-static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
-					     unsigned long bd_entry)
-{
-	unsigned long bt_addr = bd_entry;
-	int align_to_bytes;
-	/*
-	 * Bit 0 in a bt_entry is always the valid bit.
-	 */
-	bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG;
-	/*
-	 * Tables are naturally aligned at 8-byte boundaries
-	 * on 64-bit and 4-byte boundaries on 32-bit.  The
-	 * documentation makes it appear that the low bits
-	 * are ignored by the hardware, so we do the same.
-	 */
-	if (is_64bit_mm(mm))
-		align_to_bytes = 8;
-	else
-		align_to_bytes = 4;
-	bt_addr &= ~(align_to_bytes-1);
-	return bt_addr;
-}
-
-/*
- * We only want to do a 4-byte get_user() on 32-bit.  Otherwise,
- * we might run off the end of the bounds table if we are on
- * a 64-bit kernel and try to get 8 bytes.
- */
-static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
-		long __user *bd_entry_ptr)
-{
-	u32 bd_entry_32;
-	int ret;
-
-	if (is_64bit_mm(mm))
-		return get_user(*bd_entry_ret, bd_entry_ptr);
-
-	/*
-	 * Note that get_user() uses the type of the *pointer* to
-	 * establish the size of the get, not the destination.
-	 */
-	ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr);
-	*bd_entry_ret = bd_entry_32;
-	return ret;
-}
-
-/*
- * Get the base of bounds tables pointed by specific bounds
- * directory entry.
- */
-static int get_bt_addr(struct mm_struct *mm,
-			long __user *bd_entry_ptr,
-			unsigned long *bt_addr_result)
-{
-	int ret;
-	int valid_bit;
-	unsigned long bd_entry;
-	unsigned long bt_addr;
-
-	if (!access_ok((bd_entry_ptr), sizeof(*bd_entry_ptr)))
-		return -EFAULT;
-
-	while (1) {
-		int need_write = 0;
-
-		pagefault_disable();
-		ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr);
-		pagefault_enable();
-		if (!ret)
-			break;
-		if (ret == -EFAULT)
-			ret = mpx_resolve_fault(bd_entry_ptr, need_write);
-		/*
-		 * If we could not resolve the fault, consider it
-		 * userspace's fault and error out.
-		 */
-		if (ret)
-			return ret;
-	}
-
-	valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG;
-	bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry);
-
-	/*
-	 * When the kernel is managing bounds tables, a bounds directory
-	 * entry will either have a valid address (plus the valid bit)
-	 * *OR* be completely empty. If we see a !valid entry *and* some
-	 * data in the address field, we know something is wrong. This
-	 * -EINVAL return will cause a SIGSEGV.
-	 */
-	if (!valid_bit && bt_addr)
-		return -EINVAL;
-	/*
-	 * Do we have an completely zeroed bt entry?  That is OK.  It
-	 * just means there was no bounds table for this memory.  Make
-	 * sure to distinguish this from -EINVAL, which will cause
-	 * a SEGV.
-	 */
-	if (!valid_bit)
-		return -ENOENT;
-
-	*bt_addr_result = bt_addr;
-	return 0;
-}
-
-static inline int bt_entry_size_bytes(struct mm_struct *mm)
-{
-	if (is_64bit_mm(mm))
-		return MPX_BT_ENTRY_BYTES_64;
-	else
-		return MPX_BT_ENTRY_BYTES_32;
-}
-
-/*
- * Take a virtual address and turns it in to the offset in bytes
- * inside of the bounds table where the bounds table entry
- * controlling 'addr' can be found.
- */
-static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm,
-		unsigned long addr)
-{
-	unsigned long bt_table_nr_entries;
-	unsigned long offset = addr;
-
-	if (is_64bit_mm(mm)) {
-		/* Bottom 3 bits are ignored on 64-bit */
-		offset >>= 3;
-		bt_table_nr_entries = MPX_BT_NR_ENTRIES_64;
-	} else {
-		/* Bottom 2 bits are ignored on 32-bit */
-		offset >>= 2;
-		bt_table_nr_entries = MPX_BT_NR_ENTRIES_32;
-	}
-	/*
-	 * We know the size of the table in to which we are
-	 * indexing, and we have eliminated all the low bits
-	 * which are ignored for indexing.
-	 *
-	 * Mask out all the high bits which we do not need
-	 * to index in to the table.  Note that the tables
-	 * are always powers of two so this gives us a proper
-	 * mask.
-	 */
-	offset &= (bt_table_nr_entries-1);
-	/*
-	 * We now have an entry offset in terms of *entries* in
-	 * the table.  We need to scale it back up to bytes.
-	 */
-	offset *= bt_entry_size_bytes(mm);
-	return offset;
-}
-
-/*
- * How much virtual address space does a single bounds
- * directory entry cover?
- *
- * Note, we need a long long because 4GB doesn't fit in
- * to a long on 32-bit.
- */
-static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
-{
-	unsigned long long virt_space;
-	unsigned long long GB = (1ULL << 30);
-
-	/*
-	 * This covers 32-bit emulation as well as 32-bit kernels
-	 * running on 64-bit hardware.
-	 */
-	if (!is_64bit_mm(mm))
-		return (4ULL * GB) / MPX_BD_NR_ENTRIES_32;
-
-	/*
-	 * 'x86_virt_bits' returns what the hardware is capable
-	 * of, and returns the full >32-bit address space when
-	 * running 32-bit kernels on 64-bit hardware.
-	 */
-	virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
-	return virt_space / MPX_BD_NR_ENTRIES_64;
-}
-
-/*
- * Free the backing physical pages of bounds table 'bt_addr'.
- * Assume start...end is within that bounds table.
- */
-static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
-		unsigned long bt_addr,
-		unsigned long start_mapping, unsigned long end_mapping)
-{
-	struct vm_area_struct *vma;
-	unsigned long addr, len;
-	unsigned long start;
-	unsigned long end;
-
-	/*
-	 * if we 'end' on a boundary, the offset will be 0 which
-	 * is not what we want.  Back it up a byte to get the
-	 * last bt entry.  Then once we have the entry itself,
-	 * move 'end' back up by the table entry size.
-	 */
-	start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping);
-	end   = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1);
-	/*
-	 * Move end back up by one entry.  Among other things
-	 * this ensures that it remains page-aligned and does
-	 * not screw up zap_page_range()
-	 */
-	end += bt_entry_size_bytes(mm);
-
-	/*
-	 * Find the first overlapping vma. If vma->vm_start > start, there
-	 * will be a hole in the bounds table. This -EINVAL return will
-	 * cause a SIGSEGV.
-	 */
-	vma = find_vma(mm, start);
-	if (!vma || vma->vm_start > start)
-		return -EINVAL;
-
-	/*
-	 * A NUMA policy on a VM_MPX VMA could cause this bounds table to
-	 * be split. So we need to look across the entire 'start -> end'
-	 * range of this bounds table, find all of the VM_MPX VMAs, and
-	 * zap only those.
-	 */
-	addr = start;
-	while (vma && vma->vm_start < end) {
-		/*
-		 * We followed a bounds directory entry down
-		 * here.  If we find a non-MPX VMA, that's bad,
-		 * so stop immediately and return an error.  This
-		 * probably results in a SIGSEGV.
-		 */
-		if (!(vma->vm_flags & VM_MPX))
-			return -EINVAL;
-
-		len = min(vma->vm_end, end) - addr;
-		zap_page_range(vma, addr, len);
-		trace_mpx_unmap_zap(addr, addr+len);
-
-		vma = vma->vm_next;
-		addr = vma->vm_start;
-	}
-	return 0;
-}
-
-static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm,
-		unsigned long addr)
-{
-	/*
-	 * There are several ways to derive the bd offsets.  We
-	 * use the following approach here:
-	 * 1. We know the size of the virtual address space
-	 * 2. We know the number of entries in a bounds table
-	 * 3. We know that each entry covers a fixed amount of
-	 *    virtual address space.
-	 * So, we can just divide the virtual address by the
-	 * virtual space used by one entry to determine which
-	 * entry "controls" the given virtual address.
-	 */
-	if (is_64bit_mm(mm)) {
-		int bd_entry_size = 8; /* 64-bit pointer */
-		/*
-		 * Take the 64-bit addressing hole in to account.
-		 */
-		addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1);
-		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
-	} else {
-		int bd_entry_size = 4; /* 32-bit pointer */
-		/*
-		 * 32-bit has no hole so this case needs no mask
-		 */
-		return (addr / bd_entry_virt_space(mm)) * bd_entry_size;
-	}
-	/*
-	 * The two return calls above are exact copies.  If we
-	 * pull out a single copy and put it in here, gcc won't
-	 * realize that we're doing a power-of-2 divide and use
-	 * shifts.  It uses a real divide.  If we put them up
-	 * there, it manages to figure it out (gcc 4.8.3).
-	 */
-}
-
-static int unmap_entire_bt(struct mm_struct *mm,
-		long __user *bd_entry, unsigned long bt_addr)
-{
-	unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
-	unsigned long uninitialized_var(actual_old_val);
-	int ret;
-
-	while (1) {
-		int need_write = 1;
-		unsigned long cleared_bd_entry = 0;
-
-		pagefault_disable();
-		ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val,
-				bd_entry, expected_old_val, cleared_bd_entry);
-		pagefault_enable();
-		if (!ret)
-			break;
-		if (ret == -EFAULT)
-			ret = mpx_resolve_fault(bd_entry, need_write);
-		/*
-		 * If we could not resolve the fault, consider it
-		 * userspace's fault and error out.
-		 */
-		if (ret)
-			return ret;
-	}
-	/*
-	 * The cmpxchg was performed, check the results.
-	 */
-	if (actual_old_val != expected_old_val) {
-		/*
-		 * Someone else raced with us to unmap the table.
-		 * That is OK, since we were both trying to do
-		 * the same thing.  Declare success.
-		 */
-		if (!actual_old_val)
-			return 0;
-		/*
-		 * Something messed with the bounds directory
-		 * entry.  We hold mmap_sem for read or write
-		 * here, so it could not be a _new_ bounds table
-		 * that someone just allocated.  Something is
-		 * wrong, so pass up the error and SIGSEGV.
-		 */
-		return -EINVAL;
-	}
-	/*
-	 * Note, we are likely being called under do_munmap() already. To
-	 * avoid recursion, do_munmap() will check whether it comes
-	 * from one bounds table through VM_MPX flag.
-	 */
-	return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm), NULL);
-}
-
-static int try_unmap_single_bt(struct mm_struct *mm,
-	       unsigned long start, unsigned long end)
-{
-	struct vm_area_struct *next;
-	struct vm_area_struct *prev;
-	/*
-	 * "bta" == Bounds Table Area: the area controlled by the
-	 * bounds table that we are unmapping.
-	 */
-	unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1);
-	unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm);
-	unsigned long uninitialized_var(bt_addr);
-	void __user *bde_vaddr;
-	int ret;
-	/*
-	 * We already unlinked the VMAs from the mm's rbtree so 'start'
-	 * is guaranteed to be in a hole. This gets us the first VMA
-	 * before the hole in to 'prev' and the next VMA after the hole
-	 * in to 'next'.
-	 */
-	next = find_vma_prev(mm, start, &prev);
-	/*
-	 * Do not count other MPX bounds table VMAs as neighbors.
-	 * Although theoretically possible, we do not allow bounds
-	 * tables for bounds tables so our heads do not explode.
-	 * If we count them as neighbors here, we may end up with
-	 * lots of tables even though we have no actual table
-	 * entries in use.
-	 */
-	while (next && (next->vm_flags & VM_MPX))
-		next = next->vm_next;
-	while (prev && (prev->vm_flags & VM_MPX))
-		prev = prev->vm_prev;
-	/*
-	 * We know 'start' and 'end' lie within an area controlled
-	 * by a single bounds table.  See if there are any other
-	 * VMAs controlled by that bounds table.  If there are not
-	 * then we can "expand" the are we are unmapping to possibly
-	 * cover the entire table.
-	 */
-	next = find_vma_prev(mm, start, &prev);
-	if ((!prev || prev->vm_end <= bta_start_vaddr) &&
-	    (!next || next->vm_start >= bta_end_vaddr)) {
-		/*
-		 * No neighbor VMAs controlled by same bounds
-		 * table.  Try to unmap the whole thing
-		 */
-		start = bta_start_vaddr;
-		end = bta_end_vaddr;
-	}
-
-	bde_vaddr = mm->context.bd_addr + mpx_get_bd_entry_offset(mm, start);
-	ret = get_bt_addr(mm, bde_vaddr, &bt_addr);
-	/*
-	 * No bounds table there, so nothing to unmap.
-	 */
-	if (ret == -ENOENT) {
-		ret = 0;
-		return 0;
-	}
-	if (ret)
-		return ret;
-	/*
-	 * We are unmapping an entire table.  Either because the
-	 * unmap that started this whole process was large enough
-	 * to cover an entire table, or that the unmap was small
-	 * but was the area covered by a bounds table.
-	 */
-	if ((start == bta_start_vaddr) &&
-	    (end == bta_end_vaddr))
-		return unmap_entire_bt(mm, bde_vaddr, bt_addr);
-	return zap_bt_entries_mapping(mm, bt_addr, start, end);
-}
-
-static int mpx_unmap_tables(struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	unsigned long one_unmap_start;
-	trace_mpx_unmap_search(start, end);
-
-	one_unmap_start = start;
-	while (one_unmap_start < end) {
-		int ret;
-		unsigned long next_unmap_start = ALIGN(one_unmap_start+1,
-						       bd_entry_virt_space(mm));
-		unsigned long one_unmap_end = end;
-		/*
-		 * if the end is beyond the current bounds table,
-		 * move it back so we only deal with a single one
-		 * at a time
-		 */
-		if (one_unmap_end > next_unmap_start)
-			one_unmap_end = next_unmap_start;
-		ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end);
-		if (ret)
-			return ret;
-
-		one_unmap_start = next_unmap_start;
-	}
-	return 0;
-}
-
-/*
- * Free unused bounds tables covered in a virtual address region being
- * munmap()ed. Assume end > start.
- *
- * This function will be called by do_munmap(), and the VMAs covering
- * the virtual address region start...end have already been split if
- * necessary, and the 'vma' is the first vma in this range (start -> end).
- */
-void mpx_notify_unmap(struct mm_struct *mm, unsigned long start,
-		      unsigned long end)
-{
-	struct vm_area_struct *vma;
-	int ret;
-
-	/*
-	 * Refuse to do anything unless userspace has asked
-	 * the kernel to help manage the bounds tables,
-	 */
-	if (!kernel_managing_mpx_tables(current->mm))
-		return;
-	/*
-	 * This will look across the entire 'start -> end' range,
-	 * and find all of the non-VM_MPX VMAs.
-	 *
-	 * To avoid recursion, if a VM_MPX vma is found in the range
-	 * (start->end), we will not continue follow-up work. This
-	 * recursion represents having bounds tables for bounds tables,
-	 * which should not occur normally. Being strict about it here
-	 * helps ensure that we do not have an exploitable stack overflow.
-	 */
-	vma = find_vma(mm, start);
-	while (vma && vma->vm_start < end) {
-		if (vma->vm_flags & VM_MPX)
-			return;
-		vma = vma->vm_next;
-	}
-
-	ret = mpx_unmap_tables(mm, start, end);
-	if (ret)
-		force_sig(SIGSEGV);
-}
-
-/* MPX cannot handle addresses above 47 bits yet. */
-unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
-		unsigned long flags)
-{
-	if (!kernel_managing_mpx_tables(current->mm))
-		return addr;
-	if (addr + len <= DEFAULT_MAP_WINDOW)
-		return addr;
-	if (flags & MAP_FIXED)
-		return -ENOMEM;
-
-	/*
-	 * Requested len is larger than the whole area we're allowed to map in.
-	 * Resetting hinting address wouldn't do much good -- fail early.
-	 */
-	if (len > DEFAULT_MAP_WINDOW)
-		return -ENOMEM;
-
-	/* Look for unmap area within DEFAULT_MAP_WINDOW */
-	return 0;
-}
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 62a8ebe72a52..c4aedd00c1ba 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -618,6 +618,17 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 }
 EXPORT_SYMBOL_GPL(lookup_address);
 
+/*
+ * Lookup the page table entry for a virtual address in a given mm. Return a
+ * pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address,
+			    unsigned int *level)
+{
+	return lookup_address_in_pgd(pgd_offset(mm, address), address, level);
+}
+EXPORT_SYMBOL_GPL(lookup_address_in_mm);
+
 static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
 				  unsigned int *level)
 {
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 1e59df041456..df1d95913d4e 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -625,43 +625,6 @@ unsigned int pcibios_assign_all_busses(void)
 	return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0;
 }
 
-#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS)
-static LIST_HEAD(dma_domain_list);
-static DEFINE_SPINLOCK(dma_domain_list_lock);
-
-void add_dma_domain(struct dma_domain *domain)
-{
-	spin_lock(&dma_domain_list_lock);
-	list_add(&domain->node, &dma_domain_list);
-	spin_unlock(&dma_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(add_dma_domain);
-
-void del_dma_domain(struct dma_domain *domain)
-{
-	spin_lock(&dma_domain_list_lock);
-	list_del(&domain->node);
-	spin_unlock(&dma_domain_list_lock);
-}
-EXPORT_SYMBOL_GPL(del_dma_domain);
-
-static void set_dma_domain_ops(struct pci_dev *pdev)
-{
-	struct dma_domain *domain;
-
-	spin_lock(&dma_domain_list_lock);
-	list_for_each_entry(domain, &dma_domain_list, node) {
-		if (pci_domain_nr(pdev->bus) == domain->domain_nr) {
-			pdev->dev.dma_ops = domain->dma_ops;
-			break;
-		}
-	}
-	spin_unlock(&dma_domain_list_lock);
-}
-#else
-static void set_dma_domain_ops(struct pci_dev *pdev) {}
-#endif
-
 static void set_dev_domain_options(struct pci_dev *pdev)
 {
 	if (is_vmd(pdev->bus))
@@ -697,7 +660,6 @@ int pcibios_add_device(struct pci_dev *dev)
 		pa_data = data->next;
 		memunmap(data);
 	}
-	set_dma_domain_ops(dev);
 	set_dev_domain_options(dev);
 	return 0;
 }
@@ -736,3 +698,13 @@ int pci_ext_cfg_avail(void)
 	else
 		return 0;
 }
+
+#if IS_ENABLED(CONFIG_VMD)
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev)
+{
+	if (is_vmd(dev->bus))
+		return to_pci_sysdata(dev->bus)->vmd_dev;
+
+	return dev;
+}
+#endif
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 71dddd1620f9..081d466002c9 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -49,7 +49,7 @@ void efi_sync_low_kernel_mappings(void) {}
 void __init efi_dump_pagetable(void)
 {
 #ifdef CONFIG_EFI_PGT_DUMP
-	ptdump_walk_pgd_level(NULL, swapper_pg_dir);
+	ptdump_walk_pgd_level(NULL, &init_mm);
 #endif
 }
 
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index e2accfe636bd..fa8506e76bbe 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -471,9 +471,9 @@ void __init efi_dump_pagetable(void)
 {
 #ifdef CONFIG_EFI_PGT_DUMP
 	if (efi_have_uv1_memmap())
-		ptdump_walk_pgd_level(NULL, swapper_pg_dir);
+		ptdump_walk_pgd_level(NULL, &init_mm);
 	else
-		ptdump_walk_pgd_level(NULL, efi_mm.pgd);
+		ptdump_walk_pgd_level(NULL, &efi_mm);
 #endif
 }
 
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
index 44d1f884c3d3..139738bbdd36 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
@@ -6,21 +6,31 @@
  * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
  */
 
-#include <linux/gpio.h>
-#include <linux/platform_data/tc35876x.h>
+#include <linux/gpio/machine.h>
 #include <asm/intel-mid.h>
 
+static struct gpiod_lookup_table tc35876x_gpio_table = {
+	.dev_id	= "i2c_disp_brig",
+	.table	= {
+		GPIO_LOOKUP("0000:00:0c.0", -1, "bridge-reset", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("0000:00:0c.0", -1, "bl-en", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("0000:00:0c.0", -1, "vadd", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 /*tc35876x DSI_LVDS bridge chip and panel platform data*/
 static void *tc35876x_platform_data(void *data)
 {
-	static struct tc35876x_platform_data pdata;
+	struct gpiod_lookup_table *table = &tc35876x_gpio_table;
+	struct gpiod_lookup *lookup = table->table;
 
-	/* gpio pins set to -1 will not be used by the driver */
-	pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN");
-	pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN");
-	pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3");
+	lookup[0].chip_hwnum = get_gpio_by_name("LCMB_RXEN");
+	lookup[1].chip_hwnum = get_gpio_by_name("6S6P_BL_EN");
+	lookup[2].chip_hwnum = get_gpio_by_name("EN_VREG_LCD_V3P3");
+	gpiod_add_lookup_table(table);
 
-	return &pdata;
+	return NULL;
 }
 
 static const struct devs_id tc35876x_dev_id __initconst = {
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 5f0a96bf27a1..1fd321f37f1b 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1668,12 +1668,12 @@ static int tunables_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations proc_uv_ptc_operations = {
-	.open		= ptc_proc_open,
-	.read		= seq_read,
-	.write		= ptc_proc_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops uv_ptc_proc_ops = {
+	.proc_open	= ptc_proc_open,
+	.proc_read	= seq_read,
+	.proc_write	= ptc_proc_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static const struct file_operations tunables_fops = {
@@ -1691,7 +1691,7 @@ static int __init uv_ptc_init(void)
 		return 0;
 
 	proc_uv_ptc = proc_create(UV_PTC_BASENAME, 0444, NULL,
-				  &proc_uv_ptc_operations);
+				  &uv_ptc_proc_ops);
 	if (!proc_uv_ptc) {
 		pr_err("unable to create %s proc entry\n",
 		       UV_PTC_BASENAME);
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 3acc31e55e02..271917c24b7f 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -4,7 +4,6 @@ generic-y += bug.h
 generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
-generic-y += dma-contiguous.h
 generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index f0a68013c038..85a9ab1bc04d 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -407,3 +407,4 @@
 434	common	pidfd_open			sys_pidfd_open
 435	common	clone3				sys_clone3
 437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index f9cd45860bee..833109880165 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -251,10 +251,10 @@ out_free:
 	return err;
 }
 
-static const struct file_operations fops = {
-	.read = proc_read_simdisk,
-	.write = proc_write_simdisk,
-	.llseek = default_llseek,
+static const struct proc_ops simdisk_proc_ops = {
+	.proc_read	= proc_read_simdisk,
+	.proc_write	= proc_write_simdisk,
+	.proc_lseek	= default_llseek,
 };
 
 static int __init simdisk_setup(struct simdisk *dev, int which,
@@ -290,7 +290,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
 	set_capacity(dev->gd, 0);
 	add_disk(dev->gd);
 
-	dev->procfile = proc_create_data(tmp, 0644, procdir, &fops, dev);
+	dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev);
 	return 0;
 
 out_alloc_disk:
diff --git a/block/Makefile b/block/Makefile
index f6cef6d4363c..1a43750f4b01 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -25,7 +25,6 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
 obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 
-obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
diff --git a/block/bsg.c b/block/bsg.c
index 833c44b3d458..d7bae94b64d9 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -382,6 +382,7 @@ static const struct file_operations bsg_fops = {
 	.open		=	bsg_open,
 	.release	=	bsg_release,
 	.unlocked_ioctl	=	bsg_ioctl,
+	.compat_ioctl	=	compat_ptr_ioctl,
 	.owner		=	THIS_MODULE,
 	.llseek		=	default_llseek,
 };
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
deleted file mode 100644
index 3ed7a0f144a9..000000000000
--- a/block/compat_ioctl.c
+++ /dev/null
@@ -1,427 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/blkdev.h>
-#include <linux/blkpg.h>
-#include <linux/blktrace_api.h>
-#include <linux/cdrom.h>
-#include <linux/compat.h>
-#include <linux/elevator.h>
-#include <linux/hdreg.h>
-#include <linux/pr.h>
-#include <linux/slab.h>
-#include <linux/syscalls.h>
-#include <linux/types.h>
-#include <linux/uaccess.h>
-
-static int compat_put_ushort(unsigned long arg, unsigned short val)
-{
-	return put_user(val, (unsigned short __user *)compat_ptr(arg));
-}
-
-static int compat_put_int(unsigned long arg, int val)
-{
-	return put_user(val, (compat_int_t __user *)compat_ptr(arg));
-}
-
-static int compat_put_uint(unsigned long arg, unsigned int val)
-{
-	return put_user(val, (compat_uint_t __user *)compat_ptr(arg));
-}
-
-static int compat_put_long(unsigned long arg, long val)
-{
-	return put_user(val, (compat_long_t __user *)compat_ptr(arg));
-}
-
-static int compat_put_ulong(unsigned long arg, compat_ulong_t val)
-{
-	return put_user(val, (compat_ulong_t __user *)compat_ptr(arg));
-}
-
-static int compat_put_u64(unsigned long arg, u64 val)
-{
-	return put_user(val, (compat_u64 __user *)compat_ptr(arg));
-}
-
-struct compat_hd_geometry {
-	unsigned char heads;
-	unsigned char sectors;
-	unsigned short cylinders;
-	u32 start;
-};
-
-static int compat_hdio_getgeo(struct gendisk *disk, struct block_device *bdev,
-			struct compat_hd_geometry __user *ugeo)
-{
-	struct hd_geometry geo;
-	int ret;
-
-	if (!ugeo)
-		return -EINVAL;
-	if (!disk->fops->getgeo)
-		return -ENOTTY;
-
-	memset(&geo, 0, sizeof(geo));
-	/*
-	 * We need to set the startsect first, the driver may
-	 * want to override it.
-	 */
-	geo.start = get_start_sect(bdev);
-	ret = disk->fops->getgeo(bdev, &geo);
-	if (ret)
-		return ret;
-
-	ret = copy_to_user(ugeo, &geo, 4);
-	ret |= put_user(geo.start, &ugeo->start);
-	if (ret)
-		ret = -EFAULT;
-
-	return ret;
-}
-
-static int compat_hdio_ioctl(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	unsigned long __user *p;
-	int error;
-
-	p = compat_alloc_user_space(sizeof(unsigned long));
-	error = __blkdev_driver_ioctl(bdev, mode,
-				cmd, (unsigned long)p);
-	if (error == 0) {
-		unsigned int __user *uvp = compat_ptr(arg);
-		unsigned long v;
-		if (get_user(v, p) || put_user(v, uvp))
-			error = -EFAULT;
-	}
-	return error;
-}
-
-struct compat_cdrom_read_audio {
-	union cdrom_addr	addr;
-	u8			addr_format;
-	compat_int_t		nframes;
-	compat_caddr_t		buf;
-};
-
-struct compat_cdrom_generic_command {
-	unsigned char	cmd[CDROM_PACKET_SIZE];
-	compat_caddr_t	buffer;
-	compat_uint_t	buflen;
-	compat_int_t	stat;
-	compat_caddr_t	sense;
-	unsigned char	data_direction;
-	compat_int_t	quiet;
-	compat_int_t	timeout;
-	compat_caddr_t	reserved[1];
-};
-
-static int compat_cdrom_read_audio(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	struct cdrom_read_audio __user *cdread_audio;
-	struct compat_cdrom_read_audio __user *cdread_audio32;
-	__u32 data;
-	void __user *datap;
-
-	cdread_audio = compat_alloc_user_space(sizeof(*cdread_audio));
-	cdread_audio32 = compat_ptr(arg);
-
-	if (copy_in_user(&cdread_audio->addr,
-			 &cdread_audio32->addr,
-			 (sizeof(*cdread_audio32) -
-			  sizeof(compat_caddr_t))))
-		return -EFAULT;
-
-	if (get_user(data, &cdread_audio32->buf))
-		return -EFAULT;
-	datap = compat_ptr(data);
-	if (put_user(datap, &cdread_audio->buf))
-		return -EFAULT;
-
-	return __blkdev_driver_ioctl(bdev, mode, cmd,
-			(unsigned long)cdread_audio);
-}
-
-static int compat_cdrom_generic_command(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	struct cdrom_generic_command __user *cgc;
-	struct compat_cdrom_generic_command __user *cgc32;
-	u32 data;
-	unsigned char dir;
-	int itmp;
-
-	cgc = compat_alloc_user_space(sizeof(*cgc));
-	cgc32 = compat_ptr(arg);
-
-	if (copy_in_user(&cgc->cmd, &cgc32->cmd, sizeof(cgc->cmd)) ||
-	    get_user(data, &cgc32->buffer) ||
-	    put_user(compat_ptr(data), &cgc->buffer) ||
-	    copy_in_user(&cgc->buflen, &cgc32->buflen,
-			 (sizeof(unsigned int) + sizeof(int))) ||
-	    get_user(data, &cgc32->sense) ||
-	    put_user(compat_ptr(data), &cgc->sense) ||
-	    get_user(dir, &cgc32->data_direction) ||
-	    put_user(dir, &cgc->data_direction) ||
-	    get_user(itmp, &cgc32->quiet) ||
-	    put_user(itmp, &cgc->quiet) ||
-	    get_user(itmp, &cgc32->timeout) ||
-	    put_user(itmp, &cgc->timeout) ||
-	    get_user(data, &cgc32->reserved[0]) ||
-	    put_user(compat_ptr(data), &cgc->reserved[0]))
-		return -EFAULT;
-
-	return __blkdev_driver_ioctl(bdev, mode, cmd, (unsigned long)cgc);
-}
-
-struct compat_blkpg_ioctl_arg {
-	compat_int_t op;
-	compat_int_t flags;
-	compat_int_t datalen;
-	compat_caddr_t data;
-};
-
-static int compat_blkpg_ioctl(struct block_device *bdev, fmode_t mode,
-		unsigned int cmd, struct compat_blkpg_ioctl_arg __user *ua32)
-{
-	struct blkpg_ioctl_arg __user *a = compat_alloc_user_space(sizeof(*a));
-	compat_caddr_t udata;
-	compat_int_t n;
-	int err;
-
-	err = get_user(n, &ua32->op);
-	err |= put_user(n, &a->op);
-	err |= get_user(n, &ua32->flags);
-	err |= put_user(n, &a->flags);
-	err |= get_user(n, &ua32->datalen);
-	err |= put_user(n, &a->datalen);
-	err |= get_user(udata, &ua32->data);
-	err |= put_user(compat_ptr(udata), &a->data);
-	if (err)
-		return err;
-
-	return blkdev_ioctl(bdev, mode, cmd, (unsigned long)a);
-}
-
-#define BLKBSZGET_32		_IOR(0x12, 112, int)
-#define BLKBSZSET_32		_IOW(0x12, 113, int)
-#define BLKGETSIZE64_32		_IOR(0x12, 114, int)
-
-static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
-			unsigned cmd, unsigned long arg)
-{
-	switch (cmd) {
-	case HDIO_GET_UNMASKINTR:
-	case HDIO_GET_MULTCOUNT:
-	case HDIO_GET_KEEPSETTINGS:
-	case HDIO_GET_32BIT:
-	case HDIO_GET_NOWERR:
-	case HDIO_GET_DMA:
-	case HDIO_GET_NICE:
-	case HDIO_GET_WCACHE:
-	case HDIO_GET_ACOUSTIC:
-	case HDIO_GET_ADDRESS:
-	case HDIO_GET_BUSSTATE:
-		return compat_hdio_ioctl(bdev, mode, cmd, arg);
-	case CDROMREADAUDIO:
-		return compat_cdrom_read_audio(bdev, mode, cmd, arg);
-	case CDROM_SEND_PACKET:
-		return compat_cdrom_generic_command(bdev, mode, cmd, arg);
-
-	/*
-	 * No handler required for the ones below, we just need to
-	 * convert arg to a 64 bit pointer.
-	 */
-	case BLKSECTSET:
-	/*
-	 * 0x03 -- HD/IDE ioctl's used by hdparm and friends.
-	 *         Some need translations, these do not.
-	 */
-	case HDIO_GET_IDENTITY:
-	case HDIO_DRIVE_TASK:
-	case HDIO_DRIVE_CMD:
-	/* 0x330 is reserved -- it used to be HDIO_GETGEO_BIG */
-	case 0x330:
-	/* CDROM stuff */
-	case CDROMPAUSE:
-	case CDROMRESUME:
-	case CDROMPLAYMSF:
-	case CDROMPLAYTRKIND:
-	case CDROMREADTOCHDR:
-	case CDROMREADTOCENTRY:
-	case CDROMSTOP:
-	case CDROMSTART:
-	case CDROMEJECT:
-	case CDROMVOLCTRL:
-	case CDROMSUBCHNL:
-	case CDROMMULTISESSION:
-	case CDROM_GET_MCN:
-	case CDROMRESET:
-	case CDROMVOLREAD:
-	case CDROMSEEK:
-	case CDROMPLAYBLK:
-	case CDROMCLOSETRAY:
-	case CDROM_DISC_STATUS:
-	case CDROM_CHANGER_NSLOTS:
-	case CDROM_GET_CAPABILITY:
-	/* Ignore cdrom.h about these next 5 ioctls, they absolutely do
-	 * not take a struct cdrom_read, instead they take a struct cdrom_msf
-	 * which is compatible.
-	 */
-	case CDROMREADMODE2:
-	case CDROMREADMODE1:
-	case CDROMREADRAW:
-	case CDROMREADCOOKED:
-	case CDROMREADALL:
-	/* DVD ioctls */
-	case DVD_READ_STRUCT:
-	case DVD_WRITE_STRUCT:
-	case DVD_AUTH:
-		arg = (unsigned long)compat_ptr(arg);
-	/* These intepret arg as an unsigned long, not as a pointer,
-	 * so we must not do compat_ptr() conversion. */
-	case HDIO_SET_MULTCOUNT:
-	case HDIO_SET_UNMASKINTR:
-	case HDIO_SET_KEEPSETTINGS:
-	case HDIO_SET_32BIT:
-	case HDIO_SET_NOWERR:
-	case HDIO_SET_DMA:
-	case HDIO_SET_PIO_MODE:
-	case HDIO_SET_NICE:
-	case HDIO_SET_WCACHE:
-	case HDIO_SET_ACOUSTIC:
-	case HDIO_SET_BUSSTATE:
-	case HDIO_SET_ADDRESS:
-	case CDROMEJECT_SW:
-	case CDROM_SET_OPTIONS:
-	case CDROM_CLEAR_OPTIONS:
-	case CDROM_SELECT_SPEED:
-	case CDROM_SELECT_DISC:
-	case CDROM_MEDIA_CHANGED:
-	case CDROM_DRIVE_STATUS:
-	case CDROM_LOCKDOOR:
-	case CDROM_DEBUG:
-		break;
-	default:
-		/* unknown ioctl number */
-		return -ENOIOCTLCMD;
-	}
-
-	return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
-}
-
-/* Most of the generic ioctls are handled in the normal fallback path.
-   This assumes the blkdev's low level compat_ioctl always returns
-   ENOIOCTLCMD for unknown ioctls. */
-long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
-{
-	int ret = -ENOIOCTLCMD;
-	struct inode *inode = file->f_mapping->host;
-	struct block_device *bdev = inode->i_bdev;
-	struct gendisk *disk = bdev->bd_disk;
-	fmode_t mode = file->f_mode;
-	loff_t size;
-	unsigned int max_sectors;
-
-	/*
-	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
-	 * to updated it before every ioctl.
-	 */
-	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY;
-	else
-		mode &= ~FMODE_NDELAY;
-
-	switch (cmd) {
-	case HDIO_GETGEO:
-		return compat_hdio_getgeo(disk, bdev, compat_ptr(arg));
-	case BLKPBSZGET:
-		return compat_put_uint(arg, bdev_physical_block_size(bdev));
-	case BLKIOMIN:
-		return compat_put_uint(arg, bdev_io_min(bdev));
-	case BLKIOOPT:
-		return compat_put_uint(arg, bdev_io_opt(bdev));
-	case BLKALIGNOFF:
-		return compat_put_int(arg, bdev_alignment_offset(bdev));
-	case BLKDISCARDZEROES:
-		return compat_put_uint(arg, 0);
-	case BLKFLSBUF:
-	case BLKROSET:
-	case BLKDISCARD:
-	case BLKSECDISCARD:
-	case BLKZEROOUT:
-	/*
-	 * the ones below are implemented in blkdev_locked_ioctl,
-	 * but we call blkdev_ioctl, which gets the lock for us
-	 */
-	case BLKRRPART:
-	case BLKREPORTZONE:
-	case BLKRESETZONE:
-	case BLKOPENZONE:
-	case BLKCLOSEZONE:
-	case BLKFINISHZONE:
-	case BLKGETZONESZ:
-	case BLKGETNRZONES:
-		return blkdev_ioctl(bdev, mode, cmd,
-				(unsigned long)compat_ptr(arg));
-	case BLKBSZSET_32:
-		return blkdev_ioctl(bdev, mode, BLKBSZSET,
-				(unsigned long)compat_ptr(arg));
-	case BLKPG:
-		return compat_blkpg_ioctl(bdev, mode, cmd, compat_ptr(arg));
-	case BLKRAGET:
-	case BLKFRAGET:
-		if (!arg)
-			return -EINVAL;
-		return compat_put_long(arg,
-			       (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512);
-	case BLKROGET: /* compatible */
-		return compat_put_int(arg, bdev_read_only(bdev) != 0);
-	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
-		return compat_put_int(arg, block_size(bdev));
-	case BLKSSZGET: /* get block device hardware sector size */
-		return compat_put_int(arg, bdev_logical_block_size(bdev));
-	case BLKSECTGET:
-		max_sectors = min_t(unsigned int, USHRT_MAX,
-				    queue_max_sectors(bdev_get_queue(bdev)));
-		return compat_put_ushort(arg, max_sectors);
-	case BLKROTATIONAL:
-		return compat_put_ushort(arg,
-					 !blk_queue_nonrot(bdev_get_queue(bdev)));
-	case BLKRASET: /* compatible, but no compat_ptr (!) */
-	case BLKFRASET:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EACCES;
-		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
-		return 0;
-	case BLKGETSIZE:
-		size = i_size_read(bdev->bd_inode);
-		if ((size >> 9) > ~0UL)
-			return -EFBIG;
-		return compat_put_ulong(arg, size >> 9);
-
-	case BLKGETSIZE64_32:
-		return compat_put_u64(arg, i_size_read(bdev->bd_inode));
-
-	case BLKTRACESETUP32:
-	case BLKTRACESTART: /* compatible */
-	case BLKTRACESTOP:  /* compatible */
-	case BLKTRACETEARDOWN: /* compatible */
-		ret = blk_trace_ioctl(bdev, cmd, compat_ptr(arg));
-		return ret;
-	case IOC_PR_REGISTER:
-	case IOC_PR_RESERVE:
-	case IOC_PR_RELEASE:
-	case IOC_PR_PREEMPT:
-	case IOC_PR_PREEMPT_ABORT:
-	case IOC_PR_CLEAR:
-		return blkdev_ioctl(bdev, mode, cmd,
-				(unsigned long)compat_ptr(arg));
-	default:
-		if (disk->fops->compat_ioctl)
-			ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
-		if (ret == -ENOIOCTLCMD)
-			ret = compat_blkdev_driver_ioctl(bdev, mode, cmd, arg);
-		return ret;
-	}
-}
diff --git a/block/ioctl.c b/block/ioctl.c
index 5de98b97af2a..127194b9f9bd 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/capability.h>
+#include <linux/compat.h>
 #include <linux/blkdev.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
@@ -11,12 +12,12 @@
 #include <linux/pr.h>
 #include <linux/uaccess.h>
 
-static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
+static int blkpg_do_ioctl(struct block_device *bdev,
+			  struct blkpg_partition __user *upart, int op)
 {
 	struct block_device *bdevp;
 	struct gendisk *disk;
 	struct hd_struct *part, *lpart;
-	struct blkpg_ioctl_arg a;
 	struct blkpg_partition p;
 	struct disk_part_iter piter;
 	long long start, length;
@@ -24,9 +25,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
-	if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg)))
-		return -EFAULT;
-	if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition)))
+	if (copy_from_user(&p, upart, sizeof(struct blkpg_partition)))
 		return -EFAULT;
 	disk = bdev->bd_disk;
 	if (bdev != bdev->bd_contains)
@@ -34,7 +33,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	partno = p.pno;
 	if (partno <= 0)
 		return -EINVAL;
-	switch (a.op) {
+	switch (op) {
 		case BLKPG_ADD_PARTITION:
 			start = p.start >> 9;
 			length = p.length >> 9;
@@ -155,6 +154,39 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 	}
 }
 
+static int blkpg_ioctl(struct block_device *bdev,
+		       struct blkpg_ioctl_arg __user *arg)
+{
+	struct blkpg_partition __user *udata;
+	int op;
+
+	if (get_user(op, &arg->op) || get_user(udata, &arg->data))
+		return -EFAULT;
+
+	return blkpg_do_ioctl(bdev, udata, op);
+}
+
+#ifdef CONFIG_COMPAT
+struct compat_blkpg_ioctl_arg {
+	compat_int_t op;
+	compat_int_t flags;
+	compat_int_t datalen;
+	compat_caddr_t data;
+};
+
+static int compat_blkpg_ioctl(struct block_device *bdev,
+			      struct compat_blkpg_ioctl_arg __user *arg)
+{
+	compat_caddr_t udata;
+	int op;
+
+	if (get_user(op, &arg->op) || get_user(udata, &arg->data))
+		return -EFAULT;
+
+	return blkpg_do_ioctl(bdev, compat_ptr(udata), op);
+}
+#endif
+
 static int blkdev_reread_part(struct block_device *bdev)
 {
 	int ret;
@@ -238,36 +270,48 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 			BLKDEV_ZERO_NOUNMAP);
 }
 
-static int put_ushort(unsigned long arg, unsigned short val)
+static int put_ushort(unsigned short __user *argp, unsigned short val)
 {
-	return put_user(val, (unsigned short __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_int(unsigned long arg, int val)
+static int put_int(int __user *argp, int val)
 {
-	return put_user(val, (int __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_uint(unsigned long arg, unsigned int val)
+static int put_uint(unsigned int __user *argp, unsigned int val)
 {
-	return put_user(val, (unsigned int __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_long(unsigned long arg, long val)
+static int put_long(long __user *argp, long val)
 {
-	return put_user(val, (long __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_ulong(unsigned long arg, unsigned long val)
+static int put_ulong(unsigned long __user *argp, unsigned long val)
 {
-	return put_user(val, (unsigned long __user *)arg);
+	return put_user(val, argp);
 }
 
-static int put_u64(unsigned long arg, u64 val)
+static int put_u64(u64 __user *argp, u64 val)
 {
-	return put_user(val, (u64 __user *)arg);
+	return put_user(val, argp);
 }
 
+#ifdef CONFIG_COMPAT
+static int compat_put_long(compat_long_t *argp, long val)
+{
+	return put_user(val, argp);
+}
+
+static int compat_put_ulong(compat_ulong_t *argp, compat_ulong_t val)
+{
+	return put_user(val, argp);
+}
+#endif
+
 int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned cmd, unsigned long arg)
 {
@@ -285,6 +329,26 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
  */
 EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
 
+#ifdef CONFIG_COMPAT
+/*
+ * This is the equivalent of compat_ptr_ioctl(), to be used by block
+ * drivers that implement only commands that are completely compatible
+ * between 32-bit and 64-bit user space
+ */
+int blkdev_compat_ptr_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned cmd, unsigned long arg)
+{
+	struct gendisk *disk = bdev->bd_disk;
+
+	if (disk->fops->ioctl)
+		return disk->fops->ioctl(bdev, mode, cmd,
+					 (unsigned long)compat_ptr(arg));
+
+	return -ENOIOCTLCMD;
+}
+EXPORT_SYMBOL(blkdev_compat_ptr_ioctl);
+#endif
+
 static int blkdev_pr_register(struct block_device *bdev,
 		struct pr_registration __user *arg)
 {
@@ -455,6 +519,45 @@ static int blkdev_getgeo(struct block_device *bdev,
 	return 0;
 }
 
+#ifdef CONFIG_COMPAT
+struct compat_hd_geometry {
+	unsigned char heads;
+	unsigned char sectors;
+	unsigned short cylinders;
+	u32 start;
+};
+
+static int compat_hdio_getgeo(struct block_device *bdev,
+			      struct compat_hd_geometry __user *ugeo)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct hd_geometry geo;
+	int ret;
+
+	if (!ugeo)
+		return -EINVAL;
+	if (!disk->fops->getgeo)
+		return -ENOTTY;
+
+	memset(&geo, 0, sizeof(geo));
+	/*
+	 * We need to set the startsect first, the driver may
+	 * want to override it.
+	 */
+	geo.start = get_start_sect(bdev);
+	ret = disk->fops->getgeo(bdev, &geo);
+	if (ret)
+		return ret;
+
+	ret = copy_to_user(ugeo, &geo, 4);
+	ret |= put_user(geo.start, &ugeo->start);
+	if (ret)
+		ret = -EFAULT;
+
+	return ret;
+}
+#endif
+
 /* set the logical block size */
 static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 		int __user *argp)
@@ -481,13 +584,13 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 }
 
 /*
- * always keep this in sync with compat_blkdev_ioctl()
+ * Common commands that are handled the same way on native and compat
+ * user space. Note the separate arg/argp parameters that are needed
+ * to deal with the compat_ptr() conversion.
  */
-int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
-			unsigned long arg)
+static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode,
+				unsigned cmd, unsigned long arg, void __user *argp)
 {
-	void __user *argp = (void __user *)arg;
-	loff_t size;
 	unsigned int max_sectors;
 
 	switch (cmd) {
@@ -510,60 +613,39 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFINISHZONE:
 		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
 	case BLKGETZONESZ:
-		return put_uint(arg, bdev_zone_sectors(bdev));
+		return put_uint(argp, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:
-		return put_uint(arg, blkdev_nr_zones(bdev->bd_disk));
-	case HDIO_GETGEO:
-		return blkdev_getgeo(bdev, argp);
-	case BLKRAGET:
-	case BLKFRAGET:
-		if (!arg)
-			return -EINVAL;
-		return put_long(arg, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
+		return put_uint(argp, blkdev_nr_zones(bdev->bd_disk));
 	case BLKROGET:
-		return put_int(arg, bdev_read_only(bdev) != 0);
-	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
-		return put_int(arg, block_size(bdev));
+		return put_int(argp, bdev_read_only(bdev) != 0);
 	case BLKSSZGET: /* get block device logical block size */
-		return put_int(arg, bdev_logical_block_size(bdev));
+		return put_int(argp, bdev_logical_block_size(bdev));
 	case BLKPBSZGET: /* get block device physical block size */
-		return put_uint(arg, bdev_physical_block_size(bdev));
+		return put_uint(argp, bdev_physical_block_size(bdev));
 	case BLKIOMIN:
-		return put_uint(arg, bdev_io_min(bdev));
+		return put_uint(argp, bdev_io_min(bdev));
 	case BLKIOOPT:
-		return put_uint(arg, bdev_io_opt(bdev));
+		return put_uint(argp, bdev_io_opt(bdev));
 	case BLKALIGNOFF:
-		return put_int(arg, bdev_alignment_offset(bdev));
+		return put_int(argp, bdev_alignment_offset(bdev));
 	case BLKDISCARDZEROES:
-		return put_uint(arg, 0);
+		return put_uint(argp, 0);
 	case BLKSECTGET:
 		max_sectors = min_t(unsigned int, USHRT_MAX,
 				    queue_max_sectors(bdev_get_queue(bdev)));
-		return put_ushort(arg, max_sectors);
+		return put_ushort(argp, max_sectors);
 	case BLKROTATIONAL:
-		return put_ushort(arg, !blk_queue_nonrot(bdev_get_queue(bdev)));
+		return put_ushort(argp, !blk_queue_nonrot(bdev_get_queue(bdev)));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
-	case BLKBSZSET:
-		return blkdev_bszset(bdev, mode, argp);
-	case BLKPG:
-		return blkpg_ioctl(bdev, argp);
 	case BLKRRPART:
 		return blkdev_reread_part(bdev);
-	case BLKGETSIZE:
-		size = i_size_read(bdev->bd_inode);
-		if ((size >> 9) > ~0UL)
-			return -EFBIG;
-		return put_ulong(arg, size >> 9);
-	case BLKGETSIZE64:
-		return put_u64(arg, i_size_read(bdev->bd_inode));
 	case BLKTRACESTART:
 	case BLKTRACESTOP:
-	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
 	case IOC_PR_REGISTER:
@@ -579,7 +661,132 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case IOC_PR_CLEAR:
 		return blkdev_pr_clear(bdev, argp);
 	default:
+		return -ENOIOCTLCMD;
+	}
+}
+
+/*
+ * Always keep this in sync with compat_blkdev_ioctl()
+ * to handle all incompatible commands in both functions.
+ *
+ * New commands must be compatible and go into blkdev_common_ioctl
+ */
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+			unsigned long arg)
+{
+	int ret;
+	loff_t size;
+	void __user *argp = (void __user *)arg;
+
+	switch (cmd) {
+	/* These need separate implementations for the data structure */
+	case HDIO_GETGEO:
+		return blkdev_getgeo(bdev, argp);
+	case BLKPG:
+		return blkpg_ioctl(bdev, argp);
+
+	/* Compat mode returns 32-bit data instead of 'long' */
+	case BLKRAGET:
+	case BLKFRAGET:
+		if (!argp)
+			return -EINVAL;
+		return put_long(argp, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
+	case BLKGETSIZE:
+		size = i_size_read(bdev->bd_inode);
+		if ((size >> 9) > ~0UL)
+			return -EFBIG;
+		return put_ulong(argp, size >> 9);
+
+	/* The data is compatible, but the command number is different */
+	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
+		return put_int(argp, block_size(bdev));
+	case BLKBSZSET:
+		return blkdev_bszset(bdev, mode, argp);
+	case BLKGETSIZE64:
+		return put_u64(argp, i_size_read(bdev->bd_inode));
+
+	/* Incompatible alignment on i386 */
+	case BLKTRACESETUP:
+		return blk_trace_ioctl(bdev, cmd, argp);
+	default:
+		break;
+	}
+
+	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
+	if (ret == -ENOIOCTLCMD)
 		return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */
+
+#ifdef CONFIG_COMPAT
+
+#define BLKBSZGET_32		_IOR(0x12, 112, int)
+#define BLKBSZSET_32		_IOW(0x12, 113, int)
+#define BLKGETSIZE64_32		_IOR(0x12, 114, int)
+
+/* Most of the generic ioctls are handled in the normal fallback path.
+   This assumes the blkdev's low level compat_ioctl always returns
+   ENOIOCTLCMD for unknown ioctls. */
+long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	int ret;
+	void __user *argp = compat_ptr(arg);
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *bdev = inode->i_bdev;
+	struct gendisk *disk = bdev->bd_disk;
+	fmode_t mode = file->f_mode;
+	loff_t size;
+
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
+	if (file->f_flags & O_NDELAY)
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
+
+	switch (cmd) {
+	/* These need separate implementations for the data structure */
+	case HDIO_GETGEO:
+		return compat_hdio_getgeo(bdev, argp);
+	case BLKPG:
+		return compat_blkpg_ioctl(bdev, argp);
+
+	/* Compat mode returns 32-bit data instead of 'long' */
+	case BLKRAGET:
+	case BLKFRAGET:
+		if (!argp)
+			return -EINVAL;
+		return compat_put_long(argp,
+			       (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512);
+	case BLKGETSIZE:
+		size = i_size_read(bdev->bd_inode);
+		if ((size >> 9) > ~0UL)
+			return -EFBIG;
+		return compat_put_ulong(argp, size >> 9);
+
+	/* The data is compatible, but the command number is different */
+	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
+		return put_int(argp, bdev_logical_block_size(bdev));
+	case BLKBSZSET_32:
+		return blkdev_bszset(bdev, mode, argp);
+	case BLKGETSIZE64_32:
+		return put_u64(argp, i_size_read(bdev->bd_inode));
+
+	/* Incompatible alignment on i386 */
+	case BLKTRACESETUP32:
+		return blk_trace_ioctl(bdev, cmd, argp);
+	default:
+		break;
 	}
+
+	ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
+	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
+		ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
+
+	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_ioctl);
+#endif
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 650bade5ea5a..b4e73d5dd5c2 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -20,6 +20,7 @@
 #include <scsi/scsi.h>
 #include <scsi/scsi_ioctl.h>
 #include <scsi/scsi_cmnd.h>
+#include <scsi/sg.h>
 
 struct blk_cmd_filter {
 	unsigned long read_ok[BLK_SCSI_CMD_PER_LONG];
@@ -550,34 +551,6 @@ static inline int blk_send_start_stop(struct request_queue *q,
 	return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data);
 }
 
-#ifdef CONFIG_COMPAT
-struct compat_sg_io_hdr {
-	compat_int_t interface_id;	/* [i] 'S' for SCSI generic (required) */
-	compat_int_t dxfer_direction;	/* [i] data transfer direction  */
-	unsigned char cmd_len;		/* [i] SCSI command length ( <= 16 bytes) */
-	unsigned char mx_sb_len;	/* [i] max length to write to sbp */
-	unsigned short iovec_count;	/* [i] 0 implies no scatter gather */
-	compat_uint_t dxfer_len;	/* [i] byte count of data transfer */
-	compat_uint_t dxferp;		/* [i], [*io] points to data transfer memory
-						or scatter gather list */
-	compat_uptr_t cmdp;		/* [i], [*i] points to command to perform */
-	compat_uptr_t sbp;		/* [i], [*o] points to sense_buffer memory */
-	compat_uint_t timeout;		/* [i] MAX_UINT->no timeout (unit: millisec) */
-	compat_uint_t flags;		/* [i] 0 -> default, see SG_FLAG... */
-	compat_int_t pack_id;		/* [i->o] unused internally (normally) */
-	compat_uptr_t usr_ptr;		/* [i->o] unused internally */
-	unsigned char status;		/* [o] scsi status */
-	unsigned char masked_status;	/* [o] shifted, masked scsi status */
-	unsigned char msg_status;	/* [o] messaging level data (optional) */
-	unsigned char sb_len_wr;	/* [o] byte count actually written to sbp */
-	unsigned short host_status;	/* [o] errors from host adapter */
-	unsigned short driver_status;	/* [o] errors from software driver */
-	compat_int_t resid;		/* [o] dxfer_len - actual_transferred */
-	compat_uint_t duration;		/* [o] time taken by cmd (unit: millisec) */
-	compat_uint_t info;		/* [o] auxiliary information */
-};
-#endif
-
 int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp)
 {
 #ifdef CONFIG_COMPAT
@@ -666,6 +639,136 @@ int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp)
 }
 EXPORT_SYMBOL(get_sg_io_hdr);
 
+#ifdef CONFIG_COMPAT
+struct compat_cdrom_generic_command {
+	unsigned char	cmd[CDROM_PACKET_SIZE];
+	compat_caddr_t	buffer;
+	compat_uint_t	buflen;
+	compat_int_t	stat;
+	compat_caddr_t	sense;
+	unsigned char	data_direction;
+	compat_int_t	quiet;
+	compat_int_t	timeout;
+	compat_caddr_t	reserved[1];
+};
+#endif
+
+static int scsi_get_cdrom_generic_arg(struct cdrom_generic_command *cgc,
+				      const void __user *arg)
+{
+#ifdef CONFIG_COMPAT
+	if (in_compat_syscall()) {
+		struct compat_cdrom_generic_command cgc32;
+
+		if (copy_from_user(&cgc32, arg, sizeof(cgc32)))
+			return -EFAULT;
+
+		*cgc = (struct cdrom_generic_command) {
+			.buffer		= compat_ptr(cgc32.buffer),
+			.buflen		= cgc32.buflen,
+			.stat		= cgc32.stat,
+			.sense		= compat_ptr(cgc32.sense),
+			.data_direction	= cgc32.data_direction,
+			.quiet		= cgc32.quiet,
+			.timeout	= cgc32.timeout,
+			.reserved[0]	= compat_ptr(cgc32.reserved[0]),
+		};
+		memcpy(&cgc->cmd, &cgc32.cmd, CDROM_PACKET_SIZE);
+		return 0;
+	}
+#endif
+	if (copy_from_user(cgc, arg, sizeof(*cgc)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int scsi_put_cdrom_generic_arg(const struct cdrom_generic_command *cgc,
+				      void __user *arg)
+{
+#ifdef CONFIG_COMPAT
+	if (in_compat_syscall()) {
+		struct compat_cdrom_generic_command cgc32 = {
+			.buffer		= (uintptr_t)(cgc->buffer),
+			.buflen		= cgc->buflen,
+			.stat		= cgc->stat,
+			.sense		= (uintptr_t)(cgc->sense),
+			.data_direction	= cgc->data_direction,
+			.quiet		= cgc->quiet,
+			.timeout	= cgc->timeout,
+			.reserved[0]	= (uintptr_t)(cgc->reserved[0]),
+		};
+		memcpy(&cgc32.cmd, &cgc->cmd, CDROM_PACKET_SIZE);
+
+		if (copy_to_user(arg, &cgc32, sizeof(cgc32)))
+			return -EFAULT;
+
+		return 0;
+	}
+#endif
+	if (copy_to_user(arg, cgc, sizeof(*cgc)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int scsi_cdrom_send_packet(struct request_queue *q,
+				  struct gendisk *bd_disk,
+				  fmode_t mode, void __user *arg)
+{
+	struct cdrom_generic_command cgc;
+	struct sg_io_hdr hdr;
+	int err;
+
+	err = scsi_get_cdrom_generic_arg(&cgc, arg);
+	if (err)
+		return err;
+
+	cgc.timeout = clock_t_to_jiffies(cgc.timeout);
+	memset(&hdr, 0, sizeof(hdr));
+	hdr.interface_id = 'S';
+	hdr.cmd_len = sizeof(cgc.cmd);
+	hdr.dxfer_len = cgc.buflen;
+	switch (cgc.data_direction) {
+		case CGC_DATA_UNKNOWN:
+			hdr.dxfer_direction = SG_DXFER_UNKNOWN;
+			break;
+		case CGC_DATA_WRITE:
+			hdr.dxfer_direction = SG_DXFER_TO_DEV;
+			break;
+		case CGC_DATA_READ:
+			hdr.dxfer_direction = SG_DXFER_FROM_DEV;
+			break;
+		case CGC_DATA_NONE:
+			hdr.dxfer_direction = SG_DXFER_NONE;
+			break;
+		default:
+			return -EINVAL;
+	}
+
+	hdr.dxferp = cgc.buffer;
+	hdr.sbp = cgc.sense;
+	if (hdr.sbp)
+		hdr.mx_sb_len = sizeof(struct request_sense);
+	hdr.timeout = jiffies_to_msecs(cgc.timeout);
+	hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
+	hdr.cmd_len = sizeof(cgc.cmd);
+
+	err = sg_io(q, bd_disk, &hdr, mode);
+	if (err == -EFAULT)
+		return -EFAULT;
+
+	if (hdr.status)
+		return -EIO;
+
+	cgc.stat = err;
+	cgc.buflen = hdr.resid;
+	if (scsi_put_cdrom_generic_arg(&cgc, arg))
+		return -EFAULT;
+
+	return err;
+}
+
 int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mode,
 		   unsigned int cmd, void __user *arg)
 {
@@ -716,60 +819,9 @@ int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mod
 				err = -EFAULT;
 			break;
 		}
-		case CDROM_SEND_PACKET: {
-			struct cdrom_generic_command cgc;
-			struct sg_io_hdr hdr;
-
-			err = -EFAULT;
-			if (copy_from_user(&cgc, arg, sizeof(cgc)))
-				break;
-			cgc.timeout = clock_t_to_jiffies(cgc.timeout);
-			memset(&hdr, 0, sizeof(hdr));
-			hdr.interface_id = 'S';
-			hdr.cmd_len = sizeof(cgc.cmd);
-			hdr.dxfer_len = cgc.buflen;
-			err = 0;
-			switch (cgc.data_direction) {
-				case CGC_DATA_UNKNOWN:
-					hdr.dxfer_direction = SG_DXFER_UNKNOWN;
-					break;
-				case CGC_DATA_WRITE:
-					hdr.dxfer_direction = SG_DXFER_TO_DEV;
-					break;
-				case CGC_DATA_READ:
-					hdr.dxfer_direction = SG_DXFER_FROM_DEV;
-					break;
-				case CGC_DATA_NONE:
-					hdr.dxfer_direction = SG_DXFER_NONE;
-					break;
-				default:
-					err = -EINVAL;
-			}
-			if (err)
-				break;
-
-			hdr.dxferp = cgc.buffer;
-			hdr.sbp = cgc.sense;
-			if (hdr.sbp)
-				hdr.mx_sb_len = sizeof(struct request_sense);
-			hdr.timeout = jiffies_to_msecs(cgc.timeout);
-			hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
-			hdr.cmd_len = sizeof(cgc.cmd);
-
-			err = sg_io(q, bd_disk, &hdr, mode);
-			if (err == -EFAULT)
-				break;
-
-			if (hdr.status)
-				err = -EIO;
-
-			cgc.stat = err;
-			cgc.buflen = hdr.resid;
-			if (copy_to_user(arg, &cgc, sizeof(cgc)))
-				err = -EFAULT;
-
+		case CDROM_SEND_PACKET:
+			err = scsi_cdrom_send_packet(q, bd_disk, mode, arg);
 			break;
-		}
 
 		/*
 		 * old junk scsi send command ioctl
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 3d8e53010cda..439367a8e95c 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -171,7 +171,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	sa->salg_name[sizeof(sa->salg_name) + addr_len - sizeof(*sa) - 1] = 0;
 
 	type = alg_get_type(sa->salg_type);
-	if (IS_ERR(type) && PTR_ERR(type) == -ENOENT) {
+	if (PTR_ERR(type) == -ENOENT) {
 		request_module("algif-%s", sa->salg_type);
 		type = alg_get_type(sa->salg_type);
 	}
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 70f740b09684..db18df6cb330 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -69,10 +69,6 @@ ACPI_MODULE_NAME("acpi_lpss");
 #define LPSS_SAVE_CTX			BIT(4)
 #define LPSS_NO_D3_DELAY		BIT(5)
 
-/* Crystal Cove PMIC shares same ACPI ID between different platforms */
-#define BYT_CRC_HRV			2
-#define CHT_CRC_HRV			3
-
 struct lpss_private_data;
 
 struct lpss_device_desc {
@@ -158,7 +154,7 @@ static void lpss_deassert_reset(struct lpss_private_data *pdata)
  */
 static struct pwm_lookup byt_pwm_lookup[] = {
 	PWM_LOOKUP_WITH_MODULE("80860F09:00", 0, "0000:00:02.0",
-			       "pwm_backlight", 0, PWM_POLARITY_NORMAL,
+			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
 			       "pwm-lpss-platform"),
 };
 
@@ -170,8 +166,7 @@ static void byt_pwm_setup(struct lpss_private_data *pdata)
 	if (!adev->pnp.unique_id || strcmp(adev->pnp.unique_id, "1"))
 		return;
 
-	if (!acpi_dev_present("INT33FD", NULL, BYT_CRC_HRV))
-		pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
+	pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
 }
 
 #define LPSS_I2C_ENABLE			0x6c
@@ -204,7 +199,7 @@ static void byt_i2c_setup(struct lpss_private_data *pdata)
 /* BSW PWM used for backlight control by the i915 driver */
 static struct pwm_lookup bsw_pwm_lookup[] = {
 	PWM_LOOKUP_WITH_MODULE("80862288:00", 0, "0000:00:02.0",
-			       "pwm_backlight", 0, PWM_POLARITY_NORMAL,
+			       "pwm_soc_backlight", 0, PWM_POLARITY_NORMAL,
 			       "pwm-lpss-platform"),
 };
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 6078064684c6..ed3d2d1a7ae9 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -11,6 +11,7 @@
 #define pr_fmt(fmt)	"ACPI: IORT: " fmt
 
 #include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
 #include <linux/iommu.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
@@ -902,9 +903,9 @@ static inline bool iort_iommu_driver_enabled(u8 type)
 {
 	switch (type) {
 	case ACPI_IORT_NODE_SMMU_V3:
-		return IS_BUILTIN(CONFIG_ARM_SMMU_V3);
+		return IS_ENABLED(CONFIG_ARM_SMMU_V3);
 	case ACPI_IORT_NODE_SMMU:
-		return IS_BUILTIN(CONFIG_ARM_SMMU);
+		return IS_ENABLED(CONFIG_ARM_SMMU);
 	default:
 		pr_warn("IORT node type %u does not describe an SMMU\n", type);
 		return false;
@@ -976,6 +977,20 @@ static int iort_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
 	return iort_iommu_xlate(info->dev, parent, streamid);
 }
 
+static void iort_named_component_init(struct device *dev,
+				      struct acpi_iort_node *node)
+{
+	struct acpi_iort_named_component *nc;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+
+	if (!fwspec)
+		return;
+
+	nc = (struct acpi_iort_named_component *)node->node_data;
+	fwspec->num_pasid_bits = FIELD_GET(ACPI_IORT_NC_PASID_BITS,
+					   nc->node_flags);
+}
+
 /**
  * iort_iommu_configure - Set-up IOMMU configuration for a device.
  *
@@ -1030,6 +1045,9 @@ const struct iommu_ops *iort_iommu_configure(struct device *dev)
 			if (parent)
 				err = iort_iommu_xlate(dev, parent, streamid);
 		} while (parent && !err);
+
+		if (!err)
+			iort_named_component_init(dev, node);
 	}
 
 	/*
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 15cc7d5a6185..111a407dcc77 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -1202,13 +1202,12 @@ static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, acpi_battery_alarm_proc_show, PDE_DATA(inode));
 }
 
-static const struct file_operations acpi_battery_alarm_fops = {
-	.owner		= THIS_MODULE,
-	.open		= acpi_battery_alarm_proc_open,
-	.read		= seq_read,
-	.write		= acpi_battery_write_alarm,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops acpi_battery_alarm_proc_ops = {
+	.proc_open	= acpi_battery_alarm_proc_open,
+	.proc_read	= seq_read,
+	.proc_write	= acpi_battery_write_alarm,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 static int acpi_battery_add_fs(struct acpi_device *device)
@@ -1228,7 +1227,7 @@ static int acpi_battery_add_fs(struct acpi_device *device)
 			acpi_battery_state_proc_show, acpi_driver_data(device)))
 		return -ENODEV;
 	if (!proc_create_data("alarm", S_IFREG | S_IRUGO | S_IWUSR,
-			acpi_device_dir(device), &acpi_battery_alarm_fops,
+			acpi_device_dir(device), &acpi_battery_alarm_proc_ops,
 			acpi_driver_data(device)))
 		return -ENODEV;
 	return 0;
diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c
index 652f19e6c541..0e62ef265ce4 100644
--- a/drivers/acpi/proc.c
+++ b/drivers/acpi/proc.c
@@ -136,18 +136,17 @@ acpi_system_wakeup_device_open_fs(struct inode *inode, struct file *file)
 			   PDE_DATA(inode));
 }
 
-static const struct file_operations acpi_system_wakeup_device_fops = {
-	.owner = THIS_MODULE,
-	.open = acpi_system_wakeup_device_open_fs,
-	.read = seq_read,
-	.write = acpi_system_write_wakeup_device,
-	.llseek = seq_lseek,
-	.release = single_release,
+static const struct proc_ops acpi_system_wakeup_device_proc_ops = {
+	.proc_open	= acpi_system_wakeup_device_open_fs,
+	.proc_read	= seq_read,
+	.proc_write	= acpi_system_write_wakeup_device,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 void __init acpi_sleep_proc_init(void)
 {
 	/* 'wakeup device' [R/W] */
 	proc_create("wakeup", S_IFREG | S_IRUGO | S_IWUSR,
-		    acpi_root_dir, &acpi_system_wakeup_device_fops);
+		    acpi_root_dir, &acpi_system_wakeup_device_proc_ops);
 }
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 915650bf519f..6d3448895382 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1462,7 +1462,7 @@ int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
 	iort_dma_setup(dev, &dma_addr, &size);
 
 	iommu = iort_iommu_configure(dev);
-	if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
 	arch_setup_dma_ops(dev, dma_addr, size,
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index d831a61e0010..19067a5e5293 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -27,6 +27,7 @@
 #include <linux/acpi.h>
 #include <linux/workqueue.h>
 #include <linux/uaccess.h>
+#include <linux/units.h>
 
 #define PREFIX "ACPI: "
 
@@ -172,7 +173,7 @@ struct acpi_thermal {
 	struct acpi_handle_list devices;
 	struct thermal_zone_device *thermal_zone;
 	int tz_enabled;
-	int kelvin_offset;
+	int kelvin_offset;	/* in millidegrees */
 	struct work_struct thermal_check_work;
 };
 
@@ -297,7 +298,8 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 			if (crt == -1) {
 				tz->trips.critical.flags.valid = 0;
 			} else if (crt > 0) {
-				unsigned long crt_k = CELSIUS_TO_DECI_KELVIN(crt);
+				unsigned long crt_k = celsius_to_deci_kelvin(crt);
+
 				/*
 				 * Allow override critical threshold
 				 */
@@ -333,7 +335,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 		if (psv == -1) {
 			status = AE_SUPPORT;
 		} else if (psv > 0) {
-			tmp = CELSIUS_TO_DECI_KELVIN(psv);
+			tmp = celsius_to_deci_kelvin(psv);
 			status = AE_OK;
 		} else {
 			status = acpi_evaluate_integer(tz->device->handle,
@@ -413,7 +415,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 					break;
 				if (i == 1)
 					tz->trips.active[0].temperature =
-						CELSIUS_TO_DECI_KELVIN(act);
+						celsius_to_deci_kelvin(act);
 				else
 					/*
 					 * Don't allow override higher than
@@ -421,9 +423,9 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 					 */
 					tz->trips.active[i - 1].temperature =
 						(tz->trips.active[i - 2].temperature <
-						CELSIUS_TO_DECI_KELVIN(act) ?
+						celsius_to_deci_kelvin(act) ?
 						tz->trips.active[i - 2].temperature :
-						CELSIUS_TO_DECI_KELVIN(act));
+						celsius_to_deci_kelvin(act));
 				break;
 			} else {
 				tz->trips.active[i].temperature = tmp;
@@ -519,7 +521,7 @@ static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
 	if (result)
 		return result;
 
-	*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(tz->temperature,
+	*temp = deci_kelvin_to_millicelsius_with_offset(tz->temperature,
 							tz->kelvin_offset);
 	return 0;
 }
@@ -624,7 +626,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 
 	if (tz->trips.critical.flags.valid) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.critical.temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -634,7 +636,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 
 	if (tz->trips.hot.flags.valid) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.hot.temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -644,7 +646,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 
 	if (tz->trips.passive.flags.valid) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.passive.temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -655,7 +657,7 @@ static int thermal_get_trip_temp(struct thermal_zone_device *thermal,
 	for (i = 0; i < ACPI_THERMAL_MAX_ACTIVE &&
 		tz->trips.active[i].flags.valid; i++) {
 		if (!trip) {
-			*temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+			*temp = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.active[i].temperature,
 				tz->kelvin_offset);
 			return 0;
@@ -672,7 +674,7 @@ static int thermal_get_crit_temp(struct thermal_zone_device *thermal,
 	struct acpi_thermal *tz = thermal->devdata;
 
 	if (tz->trips.critical.flags.valid) {
-		*temperature = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+		*temperature = deci_kelvin_to_millicelsius_with_offset(
 				tz->trips.critical.temperature,
 				tz->kelvin_offset);
 		return 0;
@@ -692,7 +694,7 @@ static int thermal_get_trend(struct thermal_zone_device *thermal,
 
 	if (type == THERMAL_TRIP_ACTIVE) {
 		int trip_temp;
-		int temp = DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(
+		int temp = deci_kelvin_to_millicelsius_with_offset(
 					tz->temperature, tz->kelvin_offset);
 		if (thermal_get_trip_temp(thermal, trip, &trip_temp))
 			return -EINVAL;
@@ -1043,9 +1045,9 @@ static void acpi_thermal_guess_offset(struct acpi_thermal *tz)
 {
 	if (tz->trips.critical.flags.valid &&
 	    (tz->trips.critical.temperature % 5) == 1)
-		tz->kelvin_offset = 2731;
+		tz->kelvin_offset = 273100;
 	else
-		tz->kelvin_offset = 2732;
+		tz->kelvin_offset = 273200;
 }
 
 static void acpi_thermal_check_fn(struct work_struct *work)
@@ -1087,7 +1089,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 	INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);
 
 	pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device),
-		acpi_device_bid(device), DECI_KELVIN_TO_CELSIUS(tz->temperature));
+		acpi_device_bid(device), deci_kelvin_to_celsius(tz->temperature));
 	goto end;
 
 free_memory:
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 9fcc761031d8..a6b2082c24f8 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2249,10 +2249,12 @@ static void binder_deferred_fd_close(int fd)
 		return;
 	init_task_work(&twcb->twork, binder_do_fd_close);
 	__close_fd_get_file(fd, &twcb->file);
-	if (twcb->file)
+	if (twcb->file) {
+		filp_close(twcb->file, current->files);
 		task_work_add(current, &twcb->twork, true);
-	else
+	} else {
 		kfree(twcb);
+	}
 }
 
 static void binder_transaction_buffer_release(struct binder_proc *proc,
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 4bfd1b14b390..11ea1aff40db 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -81,6 +81,7 @@ enum board_ids {
 
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static void ahci_remove_one(struct pci_dev *dev);
+static void ahci_shutdown_one(struct pci_dev *dev);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
 static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
@@ -606,6 +607,7 @@ static struct pci_driver ahci_pci_driver = {
 	.id_table		= ahci_pci_tbl,
 	.probe			= ahci_init_one,
 	.remove			= ahci_remove_one,
+	.shutdown		= ahci_shutdown_one,
 	.driver = {
 		.pm		= &ahci_pci_pm_ops,
 	},
@@ -1877,6 +1879,11 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 }
 
+static void ahci_shutdown_one(struct pci_dev *pdev)
+{
+	ata_pci_shutdown_one(pdev);
+}
+
 static void ahci_remove_one(struct pci_dev *pdev)
 {
 	pm_runtime_get_noresume(&pdev->dev);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6f4ab5c5b52d..42c8728f6117 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6767,6 +6767,26 @@ void ata_pci_remove_one(struct pci_dev *pdev)
 	ata_host_detach(host);
 }
 
+void ata_pci_shutdown_one(struct pci_dev *pdev)
+{
+	struct ata_host *host = pci_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+
+		ap->pflags |= ATA_PFLAG_FROZEN;
+
+		/* Disable port interrupts */
+		if (ap->ops->freeze)
+			ap->ops->freeze(ap);
+
+		/* Stop the port DMA engines */
+		if (ap->ops->port_stop)
+			ap->ops->port_stop(ap);
+	}
+}
+
 /* move to PCI subsystem */
 int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits)
 {
@@ -7387,6 +7407,7 @@ EXPORT_SYMBOL_GPL(ata_timing_cycle2mode);
 
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL_GPL(pci_test_config_bits);
+EXPORT_SYMBOL_GPL(ata_pci_shutdown_one);
 EXPORT_SYMBOL_GPL(ata_pci_remove_one);
 #ifdef CONFIG_PM
 EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend);
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 58e09ffe8b9c..eb2eb599e602 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -17,6 +17,7 @@
  *  - http://www.t13.org/
  */
 
+#include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
@@ -761,6 +762,10 @@ static int ata_ioc32(struct ata_port *ap)
 	return 0;
 }
 
+/*
+ * This handles both native and compat commands, so anything added
+ * here must have a compatible argument, or check in_compat_syscall()
+ */
 int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev,
 		     unsigned int cmd, void __user *arg)
 {
@@ -773,6 +778,10 @@ int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev,
 		spin_lock_irqsave(ap->lock, flags);
 		val = ata_ioc32(ap);
 		spin_unlock_irqrestore(ap->lock, flags);
+#ifdef CONFIG_COMPAT
+		if (in_compat_syscall())
+			return put_user(val, (compat_ulong_t __user *)arg);
+#endif
 		return put_user(val, (unsigned long __user *)arg);
 
 	case HDIO_SET_32BIT:
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index 391dff0f25a2..e9cf31f38450 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -526,9 +526,10 @@ static void data_xfer(struct work_struct *work)
 
 	/* request dma channels */
 	/* dma_request_channel may sleep, so calling from process context */
-	acdev->dma_chan = dma_request_slave_channel(acdev->host->dev, "data");
-	if (!acdev->dma_chan) {
+	acdev->dma_chan = dma_request_chan(acdev->host->dev, "data");
+	if (IS_ERR(acdev->dma_chan)) {
 		dev_err(acdev->host->dev, "Unable to get dma_chan\n");
+		acdev->dma_chan = NULL;
 		goto chan_request_fail;
 	}
 
@@ -539,6 +540,7 @@ static void data_xfer(struct work_struct *work)
 	}
 
 	dma_release_channel(acdev->dma_chan);
+	acdev->dma_chan = NULL;
 
 	/* data xferred successfully */
 	if (!ret) {
diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c
index 3fe0754c0d52..8eb066abbd9c 100644
--- a/drivers/ata/pata_pcmcia.c
+++ b/drivers/ata/pata_pcmcia.c
@@ -309,6 +309,7 @@ static const struct pcmcia_device_id pcmcia_devices[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x0098, 0x0000),	/* Toshiba */
 	PCMCIA_DEVICE_MANF_CARD(0x00a4, 0x002d),
 	PCMCIA_DEVICE_MANF_CARD(0x00ce, 0x0000),	/* Samsung */
+	PCMCIA_DEVICE_MANF_CARD(0x00f1, 0x0101),	/* SanDisk High (>8G) CFA */
 	PCMCIA_DEVICE_MANF_CARD(0x0319, 0x0000),	/* Hitachi */
 	PCMCIA_DEVICE_MANF_CARD(0x2080, 0x0001),
 	PCMCIA_DEVICE_MANF_CARD(0x4e01, 0x0100),	/* Viking CFA */
diff --git a/drivers/auxdisplay/cfag12864bfb.c b/drivers/auxdisplay/cfag12864bfb.c
index 4074886b7bc8..2002291ab338 100644
--- a/drivers/auxdisplay/cfag12864bfb.c
+++ b/drivers/auxdisplay/cfag12864bfb.c
@@ -57,7 +57,7 @@ static int cfag12864bfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	return vm_map_pages_zero(vma, &pages, 1);
 }
 
-static struct fb_ops cfag12864bfb_ops = {
+static const struct fb_ops cfag12864bfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_read = fb_sys_read,
 	.fb_write = fb_sys_write,
diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c
index a2fcde582e2a..d951d54b26f5 100644
--- a/drivers/auxdisplay/ht16k33.c
+++ b/drivers/auxdisplay/ht16k33.c
@@ -228,7 +228,7 @@ static int ht16k33_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	return vm_map_pages_zero(vma, &pages, 1);
 }
 
-static struct fb_ops ht16k33_fb_ops = {
+static const struct fb_ops ht16k33_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_read = fb_sys_read,
 	.fb_write = fb_sys_write,
diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c
index 20736aaa0e69..f7bd0f4db13d 100644
--- a/drivers/base/attribute_container.c
+++ b/drivers/base/attribute_container.c
@@ -236,6 +236,109 @@ attribute_container_remove_device(struct device *dev,
 	mutex_unlock(&attribute_container_mutex);
 }
 
+static int
+do_attribute_container_device_trigger_safe(struct device *dev,
+					   struct attribute_container *cont,
+					   int (*fn)(struct attribute_container *,
+						     struct device *, struct device *),
+					   int (*undo)(struct attribute_container *,
+						       struct device *, struct device *))
+{
+	int ret;
+	struct internal_container *ic, *failed;
+	struct klist_iter iter;
+
+	if (attribute_container_no_classdevs(cont))
+		return fn(cont, dev, NULL);
+
+	klist_for_each_entry(ic, &cont->containers, node, &iter) {
+		if (dev == ic->classdev.parent) {
+			ret = fn(cont, dev, &ic->classdev);
+			if (ret) {
+				failed = ic;
+				klist_iter_exit(&iter);
+				goto fail;
+			}
+		}
+	}
+	return 0;
+
+fail:
+	if (!undo)
+		return ret;
+
+	/* Attempt to undo the work partially done. */
+	klist_for_each_entry(ic, &cont->containers, node, &iter) {
+		if (ic == failed) {
+			klist_iter_exit(&iter);
+			break;
+		}
+		if (dev == ic->classdev.parent)
+			undo(cont, dev, &ic->classdev);
+	}
+	return ret;
+}
+
+/**
+ * attribute_container_device_trigger_safe - execute a trigger for each
+ * matching classdev or fail all of them.
+ *
+ * @dev:  The generic device to run the trigger for
+ * @fn	  the function to execute for each classdev.
+ * @undo  A function to undo the work previously done in case of error
+ *
+ * This function is a safe version of
+ * attribute_container_device_trigger. It stops on the first error and
+ * undo the partial work that has been done, on previous classdev.  It
+ * is guaranteed that either they all succeeded, or none of them
+ * succeeded.
+ */
+int
+attribute_container_device_trigger_safe(struct device *dev,
+					int (*fn)(struct attribute_container *,
+						  struct device *,
+						  struct device *),
+					int (*undo)(struct attribute_container *,
+						    struct device *,
+						    struct device *))
+{
+	struct attribute_container *cont, *failed = NULL;
+	int ret = 0;
+
+	mutex_lock(&attribute_container_mutex);
+
+	list_for_each_entry(cont, &attribute_container_list, node) {
+
+		if (!cont->match(cont, dev))
+			continue;
+
+		ret = do_attribute_container_device_trigger_safe(dev, cont,
+								 fn, undo);
+		if (ret) {
+			failed = cont;
+			break;
+		}
+	}
+
+	if (ret && !WARN_ON(!undo)) {
+		list_for_each_entry(cont, &attribute_container_list, node) {
+
+			if (failed == cont)
+				break;
+
+			if (!cont->match(cont, dev))
+				continue;
+
+			do_attribute_container_device_trigger_safe(dev, cont,
+								   undo, NULL);
+		}
+	}
+
+	mutex_unlock(&attribute_container_mutex);
+	return ret;
+
+}
+
 /**
  * attribute_container_device_trigger - execute a trigger for each matching classdev
  *
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 799b43191dea..b9f474c11393 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -70,20 +70,6 @@ void unregister_memory_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_memory_notifier);
 
-static ATOMIC_NOTIFIER_HEAD(memory_isolate_chain);
-
-int register_memory_isolate_notifier(struct notifier_block *nb)
-{
-	return atomic_notifier_chain_register(&memory_isolate_chain, nb);
-}
-EXPORT_SYMBOL(register_memory_isolate_notifier);
-
-void unregister_memory_isolate_notifier(struct notifier_block *nb)
-{
-	atomic_notifier_chain_unregister(&memory_isolate_chain, nb);
-}
-EXPORT_SYMBOL(unregister_memory_isolate_notifier);
-
 static void memory_block_release(struct device *dev)
 {
 	struct memory_block *mem = to_memory_block(dev);
@@ -175,11 +161,6 @@ int memory_notify(unsigned long val, void *v)
 	return blocking_notifier_call_chain(&memory_chain, val, v);
 }
 
-int memory_isolate_notify(unsigned long val, void *v)
-{
-	return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
-}
-
 /*
  * The probe routines leave the pages uninitialized, just as the bootmem code
  * does. Make sure we do not access them, but instead use only information from
@@ -225,7 +206,7 @@ static bool pages_correctly_probed(unsigned long start_pfn)
  */
 static int
 memory_block_action(unsigned long start_section_nr, unsigned long action,
-		    int online_type)
+		    int online_type, int nid)
 {
 	unsigned long start_pfn;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
@@ -238,7 +219,7 @@ memory_block_action(unsigned long start_section_nr, unsigned long action,
 		if (!pages_correctly_probed(start_pfn))
 			return -EBUSY;
 
-		ret = online_pages(start_pfn, nr_pages, online_type);
+		ret = online_pages(start_pfn, nr_pages, online_type, nid);
 		break;
 	case MEM_OFFLINE:
 		ret = offline_pages(start_pfn, nr_pages);
@@ -264,7 +245,7 @@ static int memory_block_change_state(struct memory_block *mem,
 		mem->state = MEM_GOING_OFFLINE;
 
 	ret = memory_block_action(mem->start_section_nr, to_state,
-				mem->online_type);
+				  mem->online_type, mem->nid);
 
 	mem->state = ret ? from_state_req : to_state;
 
@@ -395,7 +376,6 @@ static ssize_t valid_zones_show(struct device *dev,
 	struct memory_block *mem = to_memory_block(dev);
 	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	unsigned long valid_start_pfn, valid_end_pfn;
 	struct zone *default_zone;
 	int nid;
 
@@ -408,11 +388,11 @@ static ssize_t valid_zones_show(struct device *dev,
 		 * The block contains more than one zone can not be offlined.
 		 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
 		 */
-		if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages,
-					  &valid_start_pfn, &valid_end_pfn))
+		default_zone = test_pages_in_a_zone(start_pfn,
+						    start_pfn + nr_pages);
+		if (!default_zone)
 			return sprintf(buf, "none\n");
-		start_pfn = valid_start_pfn;
-		strcat(buf, page_zone(pfn_to_page(start_pfn))->name);
+		strcat(buf, default_zone->name);
 		goto out;
 	}
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 134a8af51511..0e99a760aebd 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -273,10 +273,38 @@ static void dpm_wait_for_suppliers(struct device *dev, bool async)
 	device_links_read_unlock(idx);
 }
 
-static void dpm_wait_for_superior(struct device *dev, bool async)
+static bool dpm_wait_for_superior(struct device *dev, bool async)
 {
-	dpm_wait(dev->parent, async);
+	struct device *parent;
+
+	/*
+	 * If the device is resumed asynchronously and the parent's callback
+	 * deletes both the device and the parent itself, the parent object may
+	 * be freed while this function is running, so avoid that by reference
+	 * counting the parent once more unless the device has been deleted
+	 * already (in which case return right away).
+	 */
+	mutex_lock(&dpm_list_mtx);
+
+	if (!device_pm_initialized(dev)) {
+		mutex_unlock(&dpm_list_mtx);
+		return false;
+	}
+
+	parent = get_device(dev->parent);
+
+	mutex_unlock(&dpm_list_mtx);
+
+	dpm_wait(parent, async);
+	put_device(parent);
+
 	dpm_wait_for_suppliers(dev, async);
+
+	/*
+	 * If the parent's callback has deleted the device, attempting to resume
+	 * it would be invalid, so avoid doing that then.
+	 */
+	return device_pm_initialized(dev);
 }
 
 static void dpm_wait_for_consumers(struct device *dev, bool async)
@@ -621,7 +649,8 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn
 	if (!dev->power.is_noirq_suspended)
 		goto Out;
 
-	dpm_wait_for_superior(dev, async);
+	if (!dpm_wait_for_superior(dev, async))
+		goto Out;
 
 	skip_resume = dev_pm_may_skip_resume(dev);
 
@@ -829,7 +858,8 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn
 	if (!dev->power.is_late_suspended)
 		goto Out;
 
-	dpm_wait_for_superior(dev, async);
+	if (!dpm_wait_for_superior(dev, async))
+		goto Out;
 
 	callback = dpm_subsys_resume_early_cb(dev, state, &info);
 
@@ -944,7 +974,9 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)
 		goto Complete;
 	}
 
-	dpm_wait_for_superior(dev, async);
+	if (!dpm_wait_for_superior(dev, async))
+		goto Complete;
+
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
 
diff --git a/drivers/base/transport_class.c b/drivers/base/transport_class.c
index 5ed86ded6e6b..ccc86206e508 100644
--- a/drivers/base/transport_class.c
+++ b/drivers/base/transport_class.c
@@ -30,6 +30,10 @@
 #include <linux/attribute_container.h>
 #include <linux/transport_class.h>
 
+static int transport_remove_classdev(struct attribute_container *cont,
+				     struct device *dev,
+				     struct device *classdev);
+
 /**
  * transport_class_register - register an initial transport class
  *
@@ -172,10 +176,11 @@ static int transport_add_class_device(struct attribute_container *cont,
  * routine is simply a trigger point used to add the device to the
  * system and register attributes for it.
  */
-
-void transport_add_device(struct device *dev)
+int transport_add_device(struct device *dev)
 {
-	attribute_container_device_trigger(dev, transport_add_class_device);
+	return attribute_container_device_trigger_safe(dev,
+					transport_add_class_device,
+					transport_remove_classdev);
 }
 EXPORT_SYMBOL_GPL(transport_add_device);
 
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index bd19f8af950b..7b32fb673375 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -329,6 +329,7 @@ static const struct block_device_operations aoe_bdops = {
 	.open = aoeblk_open,
 	.release = aoeblk_release,
 	.ioctl = aoeblk_ioctl,
+	.compat_ioctl = blkdev_compat_ptr_ioctl,
 	.getgeo = aoeblk_getgeo,
 	.owner = THIS_MODULE,
 };
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 485865fd0412..cd3612e4e2e1 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3879,6 +3879,9 @@ static int fd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int
 {
 	int drive = (long)bdev->bd_disk->private_data;
 	switch (cmd) {
+	case CDROMEJECT: /* CD-ROM eject */
+	case 0x6470:	 /* SunOS floppy eject */
+
 	case FDMSGON:
 	case FDMSGOFF:
 	case FDSETEMSGTRESH:
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index ae8d4bc532b0..16510795e377 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -263,34 +263,34 @@ static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
 }
 
 /* The following macro should only be used with TYPE = {uint, ulong, bool}. */
-#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY)					\
-static ssize_t									\
-nullb_device_##NAME##_show(struct config_item *item, char *page)		\
-{										\
-	return nullb_device_##TYPE##_attr_show(					\
-				to_nullb_device(item)->NAME, page);		\
-}										\
-static ssize_t									\
-nullb_device_##NAME##_store(struct config_item *item, const char *page,		\
-			    size_t count)					\
-{										\
-	int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;	\
-	struct nullb_device *dev = to_nullb_device(item);			\
-	TYPE new_value;								\
-	int ret;								\
-										\
-	ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);	\
-	if (ret < 0)								\
-		return ret;							\
-	if (apply_fn)								\
-		ret = apply_fn(dev, new_value);					\
-	else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) 		\
-		ret = -EBUSY;							\
-	if (ret < 0)								\
-		return ret;							\
-	dev->NAME = new_value;							\
-	return count;								\
-}										\
+#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY)				\
+static ssize_t								\
+nullb_device_##NAME##_show(struct config_item *item, char *page)	\
+{									\
+	return nullb_device_##TYPE##_attr_show(				\
+				to_nullb_device(item)->NAME, page);	\
+}									\
+static ssize_t								\
+nullb_device_##NAME##_store(struct config_item *item, const char *page,	\
+			    size_t count)				\
+{									\
+	int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;\
+	struct nullb_device *dev = to_nullb_device(item);		\
+	TYPE uninitialized_var(new_value);				\
+	int ret;							\
+									\
+	ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);\
+	if (ret < 0)							\
+		return ret;						\
+	if (apply_fn)							\
+		ret = apply_fn(dev, new_value);				\
+	else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) 	\
+		ret = -EBUSY;						\
+	if (ret < 0)							\
+		return ret;						\
+	dev->NAME = new_value;						\
+	return count;							\
+}									\
 CONFIGFS_ATTR(nullb_device_, NAME);
 
 static int nullb_apply_submit_queues(struct nullb_device *dev,
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 636bfea2de6f..117cfc8cd05a 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -275,6 +275,9 @@ static const struct block_device_operations pcd_bdops = {
 	.open		= pcd_block_open,
 	.release	= pcd_block_release,
 	.ioctl		= pcd_block_ioctl,
+#ifdef CONFIG_COMPAT
+	.ioctl		= blkdev_compat_ptr_ioctl,
+#endif
 	.check_events	= pcd_block_check_events,
 };
 
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 6f9ad3fc716f..c0967507d085 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -874,6 +874,7 @@ static const struct block_device_operations pd_fops = {
 	.open		= pd_open,
 	.release	= pd_release,
 	.ioctl		= pd_ioctl,
+	.compat_ioctl	= pd_ioctl,
 	.getgeo		= pd_getgeo,
 	.check_events	= pd_check_events,
 	.revalidate_disk= pd_revalidate
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 6b7d4cab3687..bb09f21ce21a 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -276,6 +276,7 @@ static const struct block_device_operations pf_fops = {
 	.open		= pf_open,
 	.release	= pf_release,
 	.ioctl		= pf_ioctl,
+	.compat_ioctl	= pf_ioctl,
 	.getgeo		= pf_getgeo,
 	.check_events	= pf_check_events,
 };
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 861fc65a1b75..5f970a7d32c0 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2663,28 +2663,6 @@ static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
 	return ret;
 }
 
-#ifdef CONFIG_COMPAT
-static int pkt_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg)
-{
-	switch (cmd) {
-	/* compatible */
-	case CDROMEJECT:
-	case CDROMMULTISESSION:
-	case CDROMREADTOCENTRY:
-	case SCSI_IOCTL_SEND_COMMAND:
-		return pkt_ioctl(bdev, mode, cmd, (unsigned long)compat_ptr(arg));
-
-
-	/* FIXME: no handler so far */
-	case CDROM_LAST_WRITTEN:
-	/* handled in compat_blkdev_driver_ioctl */
-	case CDROM_SEND_PACKET:
-	default:
-		return -ENOIOCTLCMD;
-	}
-}
-#endif
-
 static unsigned int pkt_check_events(struct gendisk *disk,
 				     unsigned int clearing)
 {
@@ -2706,9 +2684,7 @@ static const struct block_device_operations pktcdvd_ops = {
 	.open =			pkt_open,
 	.release =		pkt_close,
 	.ioctl =		pkt_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl =		pkt_compat_ioctl,
-#endif
+	.compat_ioctl =		blkdev_compat_ptr_ioctl,
 	.check_events =		pkt_check_events,
 };
 
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 571612e233fe..39aeebc6837d 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -171,6 +171,7 @@ static const struct block_device_operations vdc_fops = {
 	.owner		= THIS_MODULE,
 	.getgeo		= vdc_getgeo,
 	.ioctl		= vdc_ioctl,
+	.compat_ioctl	= blkdev_compat_ptr_ioctl,
 };
 
 static void vdc_blk_queue_start(struct vdc_port *port)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7ffd719d89de..fbbf18ac1d5d 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -405,6 +405,9 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 
 static const struct block_device_operations virtblk_fops = {
 	.ioctl  = virtblk_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = blkdev_compat_ptr_ioctl,
+#endif
 	.owner  = THIS_MODULE,
 	.getgeo = virtblk_getgeo,
 };
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 716b99aa2307..c2f71265af4b 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -62,8 +62,8 @@
  * IO workloads.
  */
 
-static int xen_blkif_max_buffer_pages = 1024;
-module_param_named(max_buffer_pages, xen_blkif_max_buffer_pages, int, 0644);
+static int max_buffer_pages = 1024;
+module_param_named(max_buffer_pages, max_buffer_pages, int, 0644);
 MODULE_PARM_DESC(max_buffer_pages,
 "Maximum number of free pages to keep in each block backend buffer");
 
@@ -78,8 +78,8 @@ MODULE_PARM_DESC(max_buffer_pages,
  * algorithm.
  */
 
-static int xen_blkif_max_pgrants = 1056;
-module_param_named(max_persistent_grants, xen_blkif_max_pgrants, int, 0644);
+static int max_pgrants = 1056;
+module_param_named(max_persistent_grants, max_pgrants, int, 0644);
 MODULE_PARM_DESC(max_persistent_grants,
                  "Maximum number of grants to map persistently");
 
@@ -88,8 +88,8 @@ MODULE_PARM_DESC(max_persistent_grants,
  * use. The time is in seconds, 0 means indefinitely long.
  */
 
-static unsigned int xen_blkif_pgrant_timeout = 60;
-module_param_named(persistent_grant_unused_seconds, xen_blkif_pgrant_timeout,
+static unsigned int pgrant_timeout = 60;
+module_param_named(persistent_grant_unused_seconds, pgrant_timeout,
 		   uint, 0644);
 MODULE_PARM_DESC(persistent_grant_unused_seconds,
 		 "Time in seconds an unused persistent grant is allowed to "
@@ -137,9 +137,8 @@ module_param(log_stats, int, 0644);
 
 static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt)
 {
-	return xen_blkif_pgrant_timeout &&
-	       (jiffies - persistent_gnt->last_used >=
-		HZ * xen_blkif_pgrant_timeout);
+	return pgrant_timeout && (jiffies - persistent_gnt->last_used >=
+			HZ * pgrant_timeout);
 }
 
 static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page)
@@ -234,7 +233,7 @@ static int add_persistent_gnt(struct xen_blkif_ring *ring,
 	struct persistent_gnt *this;
 	struct xen_blkif *blkif = ring->blkif;
 
-	if (ring->persistent_gnt_c >= xen_blkif_max_pgrants) {
+	if (ring->persistent_gnt_c >= max_pgrants) {
 		if (!blkif->vbd.overflow_max_grants)
 			blkif->vbd.overflow_max_grants = 1;
 		return -EBUSY;
@@ -397,14 +396,13 @@ static void purge_persistent_gnt(struct xen_blkif_ring *ring)
 		goto out;
 	}
 
-	if (ring->persistent_gnt_c < xen_blkif_max_pgrants ||
-	    (ring->persistent_gnt_c == xen_blkif_max_pgrants &&
+	if (ring->persistent_gnt_c < max_pgrants ||
+	    (ring->persistent_gnt_c == max_pgrants &&
 	    !ring->blkif->vbd.overflow_max_grants)) {
 		num_clean = 0;
 	} else {
-		num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN;
-		num_clean = ring->persistent_gnt_c - xen_blkif_max_pgrants +
-			    num_clean;
+		num_clean = (max_pgrants / 100) * LRU_PERCENT_CLEAN;
+		num_clean = ring->persistent_gnt_c - max_pgrants + num_clean;
 		num_clean = min(ring->persistent_gnt_c, num_clean);
 		pr_debug("Going to purge at least %u persistent grants\n",
 			 num_clean);
@@ -599,8 +597,7 @@ static void print_stats(struct xen_blkif_ring *ring)
 		 current->comm, ring->st_oo_req,
 		 ring->st_rd_req, ring->st_wr_req,
 		 ring->st_f_req, ring->st_ds_req,
-		 ring->persistent_gnt_c,
-		 xen_blkif_max_pgrants);
+		 ring->persistent_gnt_c, max_pgrants);
 	ring->st_print = jiffies + msecs_to_jiffies(10 * 1000);
 	ring->st_rd_req = 0;
 	ring->st_wr_req = 0;
@@ -656,8 +653,11 @@ purge_gnt_list:
 			ring->next_lru = jiffies + msecs_to_jiffies(LRU_INTERVAL);
 		}
 
-		/* Shrink if we have more than xen_blkif_max_buffer_pages */
-		shrink_free_pagepool(ring, xen_blkif_max_buffer_pages);
+		/* Shrink the free pages pool if it is too large. */
+		if (time_before(jiffies, blkif->buffer_squeeze_end))
+			shrink_free_pagepool(ring, 0);
+		else
+			shrink_free_pagepool(ring, max_buffer_pages);
 
 		if (log_stats && time_after(jiffies, ring->st_print))
 			print_stats(ring);
@@ -884,7 +884,7 @@ again:
 			continue;
 		}
 		if (use_persistent_gnts &&
-		    ring->persistent_gnt_c < xen_blkif_max_pgrants) {
+		    ring->persistent_gnt_c < max_pgrants) {
 			/*
 			 * We are using persistent grants, the grant is
 			 * not mapped but we might have room for it.
@@ -911,7 +911,7 @@ again:
 			pages[seg_idx]->persistent_gnt = persistent_gnt;
 			pr_debug("grant %u added to the tree of persistent grants, using %u/%u\n",
 				 persistent_gnt->gnt, ring->persistent_gnt_c,
-				 xen_blkif_max_pgrants);
+				 max_pgrants);
 			goto next;
 		}
 		if (use_persistent_gnts && !blkif->vbd.overflow_max_grants) {
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 49132b0adbbe..a3eeccf3ac5f 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -319,6 +319,7 @@ struct xen_blkif {
 	/* All rings for this device. */
 	struct xen_blkif_ring	*rings;
 	unsigned int		nr_rings;
+	unsigned long		buffer_squeeze_end;
 };
 
 struct seg_buf {
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 4c5d99f87813..42944d41aea0 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -467,7 +467,6 @@ static void xenvbd_sysfs_delif(struct xenbus_device *dev)
 	device_remove_file(&dev->dev, &dev_attr_physical_device);
 }
 
-
 static void xen_vbd_free(struct xen_vbd *vbd)
 {
 	if (vbd->bdev)
@@ -524,6 +523,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
 		handle, blkif->domid);
 	return 0;
 }
+
 static int xen_blkbk_remove(struct xenbus_device *dev)
 {
 	struct backend_info *be = dev_get_drvdata(&dev->dev);
@@ -607,6 +607,7 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info
 	if (err)
 		dev_warn(&dev->dev, "writing feature-discard (%d)", err);
 }
+
 int xen_blkbk_barrier(struct xenbus_transaction xbt,
 		      struct backend_info *be, int state)
 {
@@ -691,7 +692,6 @@ fail:
 	return err;
 }
 
-
 /*
  * Callback received when the hotplug scripts have placed the physical-device
  * node.  Read it and the mode node, and create a vbd.  If the frontend is
@@ -783,7 +783,6 @@ static void backend_changed(struct xenbus_watch *watch,
 	}
 }
 
-
 /*
  * Callback received when the frontend's state changes.
  */
@@ -858,9 +857,27 @@ static void frontend_changed(struct xenbus_device *dev,
 	}
 }
 
+/* Once a memory pressure is detected, squeeze free page pools for a while. */
+static unsigned int buffer_squeeze_duration_ms = 10;
+module_param_named(buffer_squeeze_duration_ms,
+		buffer_squeeze_duration_ms, int, 0644);
+MODULE_PARM_DESC(buffer_squeeze_duration_ms,
+"Duration in ms to squeeze pages buffer when a memory pressure is detected");
 
-/* ** Connection ** */
+/*
+ * Callback received when the memory pressure is detected.
+ */
+static void reclaim_memory(struct xenbus_device *dev)
+{
+	struct backend_info *be = dev_get_drvdata(&dev->dev);
 
+	if (!be)
+		return;
+	be->blkif->buffer_squeeze_end = jiffies +
+		msecs_to_jiffies(buffer_squeeze_duration_ms);
+}
+
+/* ** Connection ** */
 
 /*
  * Write the physical details regarding the block device to the store, and
@@ -1152,6 +1169,7 @@ static struct xenbus_driver xen_blkbk_driver = {
 	.remove = xen_blkbk_remove,
 	.otherend_changed = frontend_changed,
 	.allow_rebind = true,
+	.reclaim_memory = reclaim_memory,
 };
 
 int xen_blkif_xenbus_init(void)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 61491167da19..e2ad6bba2281 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2630,6 +2630,7 @@ static const struct block_device_operations xlvbd_block_fops =
 	.release = blkif_release,
 	.getgeo = blkif_getgeo,
 	.ioctl = blkif_ioctl,
+	.compat_ioctl = blkdev_compat_ptr_ioctl,
 };
 
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 4285e75e52c3..1bdb5793842b 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -207,14 +207,17 @@ static inline void zram_fill_page(void *ptr, unsigned long len,
 
 static bool page_same_filled(void *ptr, unsigned long *element)
 {
-	unsigned int pos;
 	unsigned long *page;
 	unsigned long val;
+	unsigned int pos, last_pos = PAGE_SIZE / sizeof(*page) - 1;
 
 	page = (unsigned long *)ptr;
 	val = page[0];
 
-	for (pos = 1; pos < PAGE_SIZE / sizeof(*page); pos++) {
+	if (val != page[last_pos])
+		return false;
+
+	for (pos = 1; pos < last_pos; pos++) {
 		if (val != page[pos])
 			return false;
 	}
@@ -626,7 +629,7 @@ static ssize_t writeback_store(struct device *dev,
 	struct bio bio;
 	struct bio_vec bio_vec;
 	struct page *page;
-	ssize_t ret;
+	ssize_t ret = len;
 	int mode;
 	unsigned long blk_idx = 0;
 
@@ -762,7 +765,6 @@ next:
 
 	if (blk_idx)
 		free_block_bdev(zram, blk_idx);
-	ret = len;
 	__free_page(page);
 release_init_lock:
 	up_read(&zram->init_lock);
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index eebdcbef0578..faca0f346fff 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -3017,9 +3017,31 @@ static noinline int mmc_ioctl_cdrom_read_audio(struct cdrom_device_info *cdi,
 	struct cdrom_read_audio ra;
 	int lba;
 
-	if (copy_from_user(&ra, (struct cdrom_read_audio __user *)arg,
-			   sizeof(ra)))
-		return -EFAULT;
+#ifdef CONFIG_COMPAT
+	if (in_compat_syscall()) {
+		struct compat_cdrom_read_audio {
+			union cdrom_addr	addr;
+			u8			addr_format;
+			compat_int_t		nframes;
+			compat_caddr_t		buf;
+		} ra32;
+
+		if (copy_from_user(&ra32, arg, sizeof(ra32)))
+			return -EFAULT;
+
+		ra = (struct cdrom_read_audio) {
+			.addr		= ra32.addr,
+			.addr_format	= ra32.addr_format,
+			.nframes	= ra32.nframes,
+			.buf		= compat_ptr(ra32.buf),
+		};
+	} else
+#endif
+	{
+		if (copy_from_user(&ra, (struct cdrom_read_audio __user *)arg,
+				   sizeof(ra)))
+			return -EFAULT;
+	}
 
 	if (ra.addr_format == CDROM_MSF)
 		lba = msf_to_lba(ra.addr.msf.minute,
@@ -3271,9 +3293,10 @@ static noinline int mmc_ioctl_cdrom_last_written(struct cdrom_device_info *cdi,
 	ret = cdrom_get_last_written(cdi, &last);
 	if (ret)
 		return ret;
-	if (copy_to_user((long __user *)arg, &last, sizeof(last)))
-		return -EFAULT;
-	return 0;
+	if (in_compat_syscall())
+		return put_user(last, (__s32 __user *)arg);
+
+	return put_user(last, (long __user *)arg);
 }
 
 static int mmc_ioctl(struct cdrom_device_info *cdi, unsigned int cmd,
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 5b21dc421c94..886b2638c730 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -518,6 +518,9 @@ static const struct block_device_operations gdrom_bdops = {
 	.release		= gdrom_bdops_release,
 	.check_events		= gdrom_bdops_check_events,
 	.ioctl			= gdrom_bdops_ioctl,
+#ifdef CONFIG_COMPAT
+	.ioctl			= blkdev_compat_ptr_ioctl,
+#endif
 };
 
 static irqreturn_t gdrom_command_interrupt(int irq, void *dev_id)
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index aed2c45f7968..ed3b7dab678d 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -855,7 +855,7 @@ int hpet_alloc(struct hpet_data *hdp)
 		return 0;
 	}
 
-	hpetp = kzalloc(struct_size(hpetp, hp_dev, hdp->hd_nirqs - 1),
+	hpetp = kzalloc(struct_size(hpetp, hp_dev, hdp->hd_nirqs),
 			GFP_KERNEL);
 
 	if (!hpetp)
diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
index d2a5791eb49f..cbf5eaea662c 100644
--- a/drivers/char/hw_random/bcm2835-rng.c
+++ b/drivers/char/hw_random/bcm2835-rng.c
@@ -157,7 +157,7 @@ static int bcm2835_rng_probe(struct platform_device *pdev)
 
 	/* Clock is optional on most platforms */
 	priv->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
+	if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
 	priv->rng.name = pdev->name;
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index 0ed07d16ec8e..65952393e1bb 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -476,7 +476,7 @@ static int omap_rng_probe(struct platform_device *pdev)
 	}
 
 	priv->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(priv->clk) && PTR_ERR(priv->clk) == -EPROBE_DEFER)
+	if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 	if (!IS_ERR(priv->clk)) {
 		ret = clk_prepare_enable(priv->clk);
@@ -488,7 +488,7 @@ static int omap_rng_probe(struct platform_device *pdev)
 	}
 
 	priv->clk_reg = devm_clk_get(&pdev->dev, "reg");
-	if (IS_ERR(priv->clk_reg) && PTR_ERR(priv->clk_reg) == -EPROBE_DEFER)
+	if (PTR_ERR(priv->clk_reg) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 	if (!IS_ERR(priv->clk_reg)) {
 		ret = clk_prepare_enable(priv->clk_reg);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index cda12933a17d..c7f9584de2c8 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -307,6 +307,8 @@
  * Eastlake, Steve Crocker, and Jeff Schiller.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/utsname.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -354,7 +356,6 @@
 #define INPUT_POOL_WORDS	(1 << (INPUT_POOL_SHIFT-5))
 #define OUTPUT_POOL_SHIFT	10
 #define OUTPUT_POOL_WORDS	(1 << (OUTPUT_POOL_SHIFT-5))
-#define SEC_XFER_SIZE		512
 #define EXTRACT_SIZE		10
 
 
@@ -371,12 +372,6 @@
 #define ENTROPY_BITS(r) ((r)->entropy_count >> ENTROPY_SHIFT)
 
 /*
- * The minimum number of bits of entropy before we wake up a read on
- * /dev/random.  Should be enough to do a significant reseed.
- */
-static int random_read_wakeup_bits = 64;
-
-/*
  * If the entropy count falls under this number of bits, then we
  * should wake up processes which are selecting or polling on write
  * access to /dev/random.
@@ -436,42 +431,11 @@ static const struct poolinfo {
 	/* was: x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 */
 	/* x^128 + x^104 + x^76 + x^51 +x^25 + x + 1 */
 	{ S(128),	104,	76,	51,	25,	1 },
-	/* was: x^32 + x^26 + x^20 + x^14 + x^7 + x + 1 */
-	/* x^32 + x^26 + x^19 + x^14 + x^7 + x + 1 */
-	{ S(32),	26,	19,	14,	7,	1 },
-#if 0
-	/* x^2048 + x^1638 + x^1231 + x^819 + x^411 + x + 1  -- 115 */
-	{ S(2048),	1638,	1231,	819,	411,	1 },
-
-	/* x^1024 + x^817 + x^615 + x^412 + x^204 + x + 1 -- 290 */
-	{ S(1024),	817,	615,	412,	204,	1 },
-
-	/* x^1024 + x^819 + x^616 + x^410 + x^207 + x^2 + 1 -- 115 */
-	{ S(1024),	819,	616,	410,	207,	2 },
-
-	/* x^512 + x^411 + x^308 + x^208 + x^104 + x + 1 -- 225 */
-	{ S(512),	411,	308,	208,	104,	1 },
-
-	/* x^512 + x^409 + x^307 + x^206 + x^102 + x^2 + 1 -- 95 */
-	{ S(512),	409,	307,	206,	102,	2 },
-	/* x^512 + x^409 + x^309 + x^205 + x^103 + x^2 + 1 -- 95 */
-	{ S(512),	409,	309,	205,	103,	2 },
-
-	/* x^256 + x^205 + x^155 + x^101 + x^52 + x + 1 -- 125 */
-	{ S(256),	205,	155,	101,	52,	1 },
-
-	/* x^128 + x^103 + x^78 + x^51 + x^27 + x^2 + 1 -- 70 */
-	{ S(128),	103,	78,	51,	27,	2 },
-
-	/* x^64 + x^52 + x^39 + x^26 + x^14 + x + 1 -- 15 */
-	{ S(64),	52,	39,	26,	14,	1 },
-#endif
 };
 
 /*
  * Static global variables
  */
-static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
 static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
 static struct fasync_struct *fasync;
 
@@ -530,11 +494,8 @@ struct entropy_store {
 	const struct poolinfo *poolinfo;
 	__u32 *pool;
 	const char *name;
-	struct entropy_store *pull;
-	struct work_struct push_work;
 
 	/* read-write data: */
-	unsigned long last_pulled;
 	spinlock_t lock;
 	unsigned short add_ptr;
 	unsigned short input_rotate;
@@ -550,9 +511,7 @@ static ssize_t _extract_entropy(struct entropy_store *r, void *buf,
 				size_t nbytes, int fips);
 
 static void crng_reseed(struct crng_state *crng, struct entropy_store *r);
-static void push_to_pool(struct work_struct *work);
 static __u32 input_pool_data[INPUT_POOL_WORDS] __latent_entropy;
-static __u32 blocking_pool_data[OUTPUT_POOL_WORDS] __latent_entropy;
 
 static struct entropy_store input_pool = {
 	.poolinfo = &poolinfo_table[0],
@@ -561,16 +520,6 @@ static struct entropy_store input_pool = {
 	.pool = input_pool_data
 };
 
-static struct entropy_store blocking_pool = {
-	.poolinfo = &poolinfo_table[1],
-	.name = "blocking",
-	.pull = &input_pool,
-	.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
-	.pool = blocking_pool_data,
-	.push_work = __WORK_INITIALIZER(blocking_pool.push_work,
-					push_to_pool),
-};
-
 static __u32 const twist_table[8] = {
 	0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
 	0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
@@ -759,22 +708,17 @@ retry:
 		} while (unlikely(entropy_count < pool_size-2 && pnfrac));
 	}
 
-	if (unlikely(entropy_count < 0)) {
-		pr_warn("random: negative entropy/overflow: pool %s count %d\n",
+	if (WARN_ON(entropy_count < 0)) {
+		pr_warn("negative entropy/overflow: pool %s count %d\n",
 			r->name, entropy_count);
-		WARN_ON(1);
 		entropy_count = 0;
 	} else if (entropy_count > pool_size)
 		entropy_count = pool_size;
-	if ((r == &blocking_pool) && !r->initialized &&
-	    (entropy_count >> ENTROPY_SHIFT) > 128)
-		has_initialized = 1;
 	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
 		goto retry;
 
 	if (has_initialized) {
 		r->initialized = 1;
-		wake_up_interruptible(&random_read_wait);
 		kill_fasync(&fasync, SIGIO, POLL_IN);
 	}
 
@@ -783,36 +727,13 @@ retry:
 
 	if (r == &input_pool) {
 		int entropy_bits = entropy_count >> ENTROPY_SHIFT;
-		struct entropy_store *other = &blocking_pool;
 
 		if (crng_init < 2) {
 			if (entropy_bits < 128)
 				return;
 			crng_reseed(&primary_crng, r);
-			entropy_bits = r->entropy_count >> ENTROPY_SHIFT;
-		}
-
-		/* initialize the blocking pool if necessary */
-		if (entropy_bits >= random_read_wakeup_bits &&
-		    !other->initialized) {
-			schedule_work(&other->push_work);
-			return;
-		}
-
-		/* should we wake readers? */
-		if (entropy_bits >= random_read_wakeup_bits &&
-		    wq_has_sleeper(&random_read_wait)) {
-			wake_up_interruptible(&random_read_wait);
-			kill_fasync(&fasync, SIGIO, POLL_IN);
+			entropy_bits = ENTROPY_BITS(r);
 		}
-		/* If the input pool is getting full, and the blocking
-		 * pool has room, send some entropy to the blocking
-		 * pool.
-		 */
-		if (!work_pending(&other->push_work) &&
-		    (ENTROPY_BITS(r) > 6 * r->poolinfo->poolbytes) &&
-		    (ENTROPY_BITS(other) <= 6 * other->poolinfo->poolbytes))
-			schedule_work(&other->push_work);
 	}
 }
 
@@ -884,7 +805,7 @@ static void crng_initialize(struct crng_state *crng)
 		invalidate_batched_entropy();
 		numa_crng_init();
 		crng_init = 2;
-		pr_notice("random: crng done (trusting CPU's manufacturer)\n");
+		pr_notice("crng done (trusting CPU's manufacturer)\n");
 	}
 	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
 }
@@ -946,8 +867,7 @@ static int crng_fast_load(const char *cp, size_t len)
 	if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
 		invalidate_batched_entropy();
 		crng_init = 1;
-		wake_up_interruptible(&crng_init_wait);
-		pr_notice("random: fast init done\n");
+		pr_notice("fast init done\n");
 	}
 	return 1;
 }
@@ -1032,16 +952,15 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 		crng_init = 2;
 		process_random_ready_list();
 		wake_up_interruptible(&crng_init_wait);
-		pr_notice("random: crng init done\n");
+		kill_fasync(&fasync, SIGIO, POLL_IN);
+		pr_notice("crng init done\n");
 		if (unseeded_warning.missed) {
-			pr_notice("random: %d get_random_xx warning(s) missed "
-				  "due to ratelimiting\n",
+			pr_notice("%d get_random_xx warning(s) missed due to ratelimiting\n",
 				  unseeded_warning.missed);
 			unseeded_warning.missed = 0;
 		}
 		if (urandom_warning.missed) {
-			pr_notice("random: %d urandom warning(s) missed "
-				  "due to ratelimiting\n",
+			pr_notice("%d urandom warning(s) missed due to ratelimiting\n",
 				  urandom_warning.missed);
 			urandom_warning.missed = 0;
 		}
@@ -1246,7 +1165,7 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	/*
 	 * delta is now minimum absolute delta.
 	 * Round down by 1 bit on general principles,
-	 * and limit entropy entimate to 12 bits.
+	 * and limit entropy estimate to 12 bits.
 	 */
 	credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
 }
@@ -1390,57 +1309,6 @@ EXPORT_SYMBOL_GPL(add_disk_randomness);
  *********************************************************************/
 
 /*
- * This utility inline function is responsible for transferring entropy
- * from the primary pool to the secondary extraction pool. We make
- * sure we pull enough for a 'catastrophic reseed'.
- */
-static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes);
-static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
-{
-	if (!r->pull ||
-	    r->entropy_count >= (nbytes << (ENTROPY_SHIFT + 3)) ||
-	    r->entropy_count > r->poolinfo->poolfracbits)
-		return;
-
-	_xfer_secondary_pool(r, nbytes);
-}
-
-static void _xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
-{
-	__u32	tmp[OUTPUT_POOL_WORDS];
-
-	int bytes = nbytes;
-
-	/* pull at least as much as a wakeup */
-	bytes = max_t(int, bytes, random_read_wakeup_bits / 8);
-	/* but never more than the buffer size */
-	bytes = min_t(int, bytes, sizeof(tmp));
-
-	trace_xfer_secondary_pool(r->name, bytes * 8, nbytes * 8,
-				  ENTROPY_BITS(r), ENTROPY_BITS(r->pull));
-	bytes = extract_entropy(r->pull, tmp, bytes,
-				random_read_wakeup_bits / 8, 0);
-	mix_pool_bytes(r, tmp, bytes);
-	credit_entropy_bits(r, bytes*8);
-}
-
-/*
- * Used as a workqueue function so that when the input pool is getting
- * full, we can "spill over" some entropy to the output pools.  That
- * way the output pools can store some of the excess entropy instead
- * of letting it go to waste.
- */
-static void push_to_pool(struct work_struct *work)
-{
-	struct entropy_store *r = container_of(work, struct entropy_store,
-					      push_work);
-	BUG_ON(!r);
-	_xfer_secondary_pool(r, random_read_wakeup_bits/8);
-	trace_push_to_pool(r->name, r->entropy_count >> ENTROPY_SHIFT,
-			   r->pull->entropy_count >> ENTROPY_SHIFT);
-}
-
-/*
  * This function decides how many bytes to actually take from the
  * given pool, and also debits the entropy count accordingly.
  */
@@ -1465,10 +1333,9 @@ retry:
 	if (ibytes < min)
 		ibytes = 0;
 
-	if (unlikely(entropy_count < 0)) {
-		pr_warn("random: negative entropy count: pool %s count %d\n",
+	if (WARN_ON(entropy_count < 0)) {
+		pr_warn("negative entropy count: pool %s count %d\n",
 			r->name, entropy_count);
-		WARN_ON(1);
 		entropy_count = 0;
 	}
 	nfrac = ibytes << (ENTROPY_SHIFT + 3);
@@ -1481,8 +1348,7 @@ retry:
 		goto retry;
 
 	trace_debit_entropy(r->name, 8 * ibytes);
-	if (ibytes &&
-	    (r->entropy_count >> ENTROPY_SHIFT) < random_write_wakeup_bits) {
+	if (ibytes && ENTROPY_BITS(r) < random_write_wakeup_bits) {
 		wake_up_interruptible(&random_write_wait);
 		kill_fasync(&fasync, SIGIO, POLL_OUT);
 	}
@@ -1603,7 +1469,6 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 			spin_unlock_irqrestore(&r->lock, flags);
 			trace_extract_entropy(r->name, EXTRACT_SIZE,
 					      ENTROPY_BITS(r), _RET_IP_);
-			xfer_secondary_pool(r, EXTRACT_SIZE);
 			extract_buf(r, tmp);
 			spin_lock_irqsave(&r->lock, flags);
 			memcpy(r->last_data, tmp, EXTRACT_SIZE);
@@ -1612,60 +1477,11 @@ static ssize_t extract_entropy(struct entropy_store *r, void *buf,
 	}
 
 	trace_extract_entropy(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
-	xfer_secondary_pool(r, nbytes);
 	nbytes = account(r, nbytes, min, reserved);
 
 	return _extract_entropy(r, buf, nbytes, fips_enabled);
 }
 
-/*
- * This function extracts randomness from the "entropy pool", and
- * returns it in a userspace buffer.
- */
-static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
-				    size_t nbytes)
-{
-	ssize_t ret = 0, i;
-	__u8 tmp[EXTRACT_SIZE];
-	int large_request = (nbytes > 256);
-
-	trace_extract_entropy_user(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
-	if (!r->initialized && r->pull) {
-		xfer_secondary_pool(r, ENTROPY_BITS(r->pull)/8);
-		if (!r->initialized)
-			return 0;
-	}
-	xfer_secondary_pool(r, nbytes);
-	nbytes = account(r, nbytes, 0, 0);
-
-	while (nbytes) {
-		if (large_request && need_resched()) {
-			if (signal_pending(current)) {
-				if (ret == 0)
-					ret = -ERESTARTSYS;
-				break;
-			}
-			schedule();
-		}
-
-		extract_buf(r, tmp);
-		i = min_t(int, nbytes, EXTRACT_SIZE);
-		if (copy_to_user(buf, tmp, i)) {
-			ret = -EFAULT;
-			break;
-		}
-
-		nbytes -= i;
-		buf += i;
-		ret += i;
-	}
-
-	/* Wipe data just returned from memory */
-	memzero_explicit(tmp, sizeof(tmp));
-
-	return ret;
-}
-
 #define warn_unseeded_randomness(previous) \
 	_warn_unseeded_randomness(__func__, (void *) _RET_IP_, (previous))
 
@@ -1687,8 +1503,9 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
 	print_once = true;
 #endif
 	if (__ratelimit(&unseeded_warning))
-		pr_notice("random: %s called from %pS with crng_init=%d\n",
-			  func_name, caller, crng_init);
+		printk_deferred(KERN_NOTICE "random: %s called from %pS "
+				"with crng_init=%d\n", func_name, caller,
+				crng_init);
 }
 
 /*
@@ -1931,7 +1748,6 @@ static void __init init_std_data(struct entropy_store *r)
 	ktime_t now = ktime_get_real();
 	unsigned long rv;
 
-	r->last_pulled = jiffies;
 	mix_pool_bytes(r, &now, sizeof(now));
 	for (i = r->poolinfo->poolbytes; i > 0; i -= sizeof(rv)) {
 		if (!arch_get_random_seed_long(&rv) &&
@@ -1955,7 +1771,6 @@ static void __init init_std_data(struct entropy_store *r)
 int __init rand_initialize(void)
 {
 	init_std_data(&input_pool);
-	init_std_data(&blocking_pool);
 	crng_initialize(&primary_crng);
 	crng_global_init_time = jiffies;
 	if (ratelimit_disable) {
@@ -1983,40 +1798,15 @@ void rand_initialize_disk(struct gendisk *disk)
 #endif
 
 static ssize_t
-_random_read(int nonblock, char __user *buf, size_t nbytes)
+urandom_read_nowarn(struct file *file, char __user *buf, size_t nbytes,
+		    loff_t *ppos)
 {
-	ssize_t n;
-
-	if (nbytes == 0)
-		return 0;
-
-	nbytes = min_t(size_t, nbytes, SEC_XFER_SIZE);
-	while (1) {
-		n = extract_entropy_user(&blocking_pool, buf, nbytes);
-		if (n < 0)
-			return n;
-		trace_random_read(n*8, (nbytes-n)*8,
-				  ENTROPY_BITS(&blocking_pool),
-				  ENTROPY_BITS(&input_pool));
-		if (n > 0)
-			return n;
-
-		/* Pool is (near) empty.  Maybe wait and retry. */
-		if (nonblock)
-			return -EAGAIN;
-
-		wait_event_interruptible(random_read_wait,
-		    blocking_pool.initialized &&
-		    (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits));
-		if (signal_pending(current))
-			return -ERESTARTSYS;
-	}
-}
+	int ret;
 
-static ssize_t
-random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
-{
-	return _random_read(file->f_flags & O_NONBLOCK, buf, nbytes);
+	nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
+	ret = extract_crng_user(buf, nbytes);
+	trace_urandom_read(8 * nbytes, 0, ENTROPY_BITS(&input_pool));
+	return ret;
 }
 
 static ssize_t
@@ -2024,22 +1814,29 @@ urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
 	unsigned long flags;
 	static int maxwarn = 10;
-	int ret;
 
 	if (!crng_ready() && maxwarn > 0) {
 		maxwarn--;
 		if (__ratelimit(&urandom_warning))
-			printk(KERN_NOTICE "random: %s: uninitialized "
-			       "urandom read (%zd bytes read)\n",
-			       current->comm, nbytes);
+			pr_notice("%s: uninitialized urandom read (%zd bytes read)\n",
+				  current->comm, nbytes);
 		spin_lock_irqsave(&primary_crng.lock, flags);
 		crng_init_cnt = 0;
 		spin_unlock_irqrestore(&primary_crng.lock, flags);
 	}
-	nbytes = min_t(size_t, nbytes, INT_MAX >> (ENTROPY_SHIFT + 3));
-	ret = extract_crng_user(buf, nbytes);
-	trace_urandom_read(8 * nbytes, 0, ENTROPY_BITS(&input_pool));
-	return ret;
+
+	return urandom_read_nowarn(file, buf, nbytes, ppos);
+}
+
+static ssize_t
+random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+{
+	int ret;
+
+	ret = wait_for_random_bytes();
+	if (ret != 0)
+		return ret;
+	return urandom_read_nowarn(file, buf, nbytes, ppos);
 }
 
 static __poll_t
@@ -2047,10 +1844,10 @@ random_poll(struct file *file, poll_table * wait)
 {
 	__poll_t mask;
 
-	poll_wait(file, &random_read_wait, wait);
+	poll_wait(file, &crng_init_wait, wait);
 	poll_wait(file, &random_write_wait, wait);
 	mask = 0;
-	if (ENTROPY_BITS(&input_pool) >= random_read_wakeup_bits)
+	if (crng_ready())
 		mask |= EPOLLIN | EPOLLRDNORM;
 	if (ENTROPY_BITS(&input_pool) < random_write_wakeup_bits)
 		mask |= EPOLLOUT | EPOLLWRNORM;
@@ -2141,7 +1938,6 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		input_pool.entropy_count = 0;
-		blocking_pool.entropy_count = 0;
 		return 0;
 	case RNDRESEEDCRNG:
 		if (!capable(CAP_SYS_ADMIN))
@@ -2185,23 +1981,27 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 {
 	int ret;
 
-	if (flags & ~(GRND_NONBLOCK|GRND_RANDOM))
+	if (flags & ~(GRND_NONBLOCK|GRND_RANDOM|GRND_INSECURE))
+		return -EINVAL;
+
+	/*
+	 * Requesting insecure and blocking randomness at the same time makes
+	 * no sense.
+	 */
+	if ((flags & (GRND_INSECURE|GRND_RANDOM)) == (GRND_INSECURE|GRND_RANDOM))
 		return -EINVAL;
 
 	if (count > INT_MAX)
 		count = INT_MAX;
 
-	if (flags & GRND_RANDOM)
-		return _random_read(flags & GRND_NONBLOCK, buf, count);
-
-	if (!crng_ready()) {
+	if (!(flags & GRND_INSECURE) && !crng_ready()) {
 		if (flags & GRND_NONBLOCK)
 			return -EAGAIN;
 		ret = wait_for_random_bytes();
 		if (unlikely(ret))
 			return ret;
 	}
-	return urandom_read(NULL, buf, count, NULL);
+	return urandom_read_nowarn(NULL, buf, count, NULL);
 }
 
 /********************************************************************
@@ -2214,8 +2014,7 @@ SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
 
 #include <linux/sysctl.h>
 
-static int min_read_thresh = 8, min_write_thresh;
-static int max_read_thresh = OUTPUT_POOL_WORDS * 32;
+static int min_write_thresh;
 static int max_write_thresh = INPUT_POOL_WORDS * 32;
 static int random_min_urandom_seed = 60;
 static char sysctl_bootid[16];
@@ -2291,15 +2090,6 @@ struct ctl_table random_table[] = {
 		.data		= &input_pool.entropy_count,
 	},
 	{
-		.procname	= "read_wakeup_threshold",
-		.data		= &random_read_wakeup_bits,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_read_thresh,
-		.extra2		= &max_read_thresh,
-	},
-	{
 		.procname	= "write_wakeup_threshold",
 		.data		= &random_write_wakeup_bits,
 		.maxlen		= sizeof(int),
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 45653a0e6ecd..bcb257baed06 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -27,7 +27,7 @@ config COMMON_CLK_WM831X
 	tristate "Clock driver for WM831x/2x PMICs"
 	depends on MFD_WM831X
 	---help---
-          Supports the clocking subsystem of the WM831x/2x series of
+	  Supports the clocking subsystem of the WM831x/2x series of
 	  PMICs from Wolfson Microelectronics.
 
 source "drivers/clk/versatile/Kconfig"
@@ -174,6 +174,18 @@ config COMMON_CLK_CS2000_CP
 	help
 	  If you say yes here you get support for the CS2000 clock multiplier.
 
+config COMMON_CLK_FSL_SAI
+	bool "Clock driver for BCLK of Freescale SAI cores"
+	depends on ARCH_LAYERSCAPE || COMPILE_TEST
+	help
+	  This driver supports the Freescale SAI (Synchronous Audio Interface)
+	  to be used as a generic clock output. Some SoCs have restrictions
+	  regarding the possible pin multiplexer settings. Eg. on some SoCs
+	  two SAI interfaces can only be enabled together. If just one is
+	  needed, the BCLK pin of the second one can be used as general
+	  purpose clock output. Ideally, it can be used to drive an audio
+	  codec (sometimes known as MCLK).
+
 config COMMON_CLK_GEMINI
 	bool "Clock driver for Cortina Systems Gemini SoC"
 	depends on ARCH_GEMINI || COMPILE_TEST
@@ -225,6 +237,16 @@ config CLK_QORIQ
 	  This adds the clock driver support for Freescale QorIQ platforms
 	  using common clock framework.
 
+config CLK_LS1028A_PLLDIG
+        tristate "Clock driver for LS1028A Display output"
+        depends on ARCH_LAYERSCAPE || COMPILE_TEST
+        default ARCH_LAYERSCAPE
+        help
+          This driver support the Display output interfaces(LCD, DPHY) pixel clocks
+          of the QorIQ Layerscape LS1028A, as implemented TSMC CLN28HPM PLL. Not all
+          features of the PLL are currently supported by the driver. By default,
+          configured bypass mode with this PLL.
+
 config COMMON_CLK_XGENE
 	bool "Clock driver for APM XGene SoC"
 	default ARCH_XGENE
@@ -305,10 +327,10 @@ config COMMON_CLK_MMP2
 	  Support for Marvell MMP2 and MMP3 SoC clocks
 
 config COMMON_CLK_BD718XX
-	tristate "Clock driver for ROHM BD718x7 PMIC"
-	depends on MFD_ROHM_BD718XX || MFD_ROHM_BD70528
+	tristate "Clock driver for 32K clk gates on ROHM PMICs"
+	depends on MFD_ROHM_BD718XX || MFD_ROHM_BD70528 || MFD_ROHM_BD71828
 	help
-	  This driver supports ROHM BD71837, ROHM BD71847 and
+	  This driver supports ROHM BD71837, ROHM BD71847, ROHM BD71828 and
 	  ROHM BD70528 PMICs clock gates.
 
 config COMMON_CLK_FIXED_MMIO
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index 0696a0c1ab58..f4169cc2fd31 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_ARCH_CLPS711X)		+= clk-clps711x.o
 obj-$(CONFIG_COMMON_CLK_CS2000_CP)	+= clk-cs2000-cp.o
 obj-$(CONFIG_ARCH_EFM32)		+= clk-efm32gg.o
 obj-$(CONFIG_COMMON_CLK_FIXED_MMIO)	+= clk-fixed-mmio.o
+obj-$(CONFIG_COMMON_CLK_FSL_SAI)	+= clk-fsl-sai.o
 obj-$(CONFIG_COMMON_CLK_GEMINI)		+= clk-gemini.o
 obj-$(CONFIG_COMMON_CLK_ASPEED)		+= clk-aspeed.o
 obj-$(CONFIG_MACH_ASPEED_G6)		+= clk-ast2600.o
@@ -44,6 +45,7 @@ obj-$(CONFIG_ARCH_NPCM7XX)	    	+= clk-npcm7xx.o
 obj-$(CONFIG_ARCH_NSPIRE)		+= clk-nspire.o
 obj-$(CONFIG_COMMON_CLK_OXNAS)		+= clk-oxnas.o
 obj-$(CONFIG_COMMON_CLK_PALMAS)		+= clk-palmas.o
+obj-$(CONFIG_CLK_LS1028A_PLLDIG)	+= clk-plldig.o
 obj-$(CONFIG_COMMON_CLK_PWM)		+= clk-pwm.o
 obj-$(CONFIG_CLK_QORIQ)			+= clk-qoriq.o
 obj-$(CONFIG_COMMON_CLK_RK808)		+= clk-rk808.o
diff --git a/drivers/clk/at91/clk-sam9x60-pll.c b/drivers/clk/at91/clk-sam9x60-pll.c
index 34b817825b22..dfb354a5ff18 100644
--- a/drivers/clk/at91/clk-sam9x60-pll.c
+++ b/drivers/clk/at91/clk-sam9x60-pll.c
@@ -25,7 +25,8 @@
 #define		PMC_PLL_CTRL1_MUL_MSK		GENMASK(30, 24)
 
 #define PMC_PLL_ACR	0x18
-#define		PMC_PLL_ACR_DEFAULT		0x1b040010UL
+#define		PMC_PLL_ACR_DEFAULT_UPLL	0x12020010UL
+#define		PMC_PLL_ACR_DEFAULT_PLLA	0x00020010UL
 #define		PMC_PLL_ACR_UTMIVR		BIT(12)
 #define		PMC_PLL_ACR_UTMIBG		BIT(13)
 #define		PMC_PLL_ACR_LOOP_FILTER_MSK	GENMASK(31, 24)
@@ -88,7 +89,10 @@ static int sam9x60_pll_prepare(struct clk_hw *hw)
 	}
 
 	/* Recommended value for PMC_PLL_ACR */
-	val = PMC_PLL_ACR_DEFAULT;
+	if (pll->characteristics->upll)
+		val = PMC_PLL_ACR_DEFAULT_UPLL;
+	else
+		val = PMC_PLL_ACR_DEFAULT_PLLA;
 	regmap_write(regmap, PMC_PLL_ACR, val);
 
 	regmap_write(regmap, PMC_PLL_CTRL1,
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 86238d5ecb4d..77398aefeb6d 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -47,6 +47,7 @@ static const struct clk_programmable_layout sam9x60_programmable_layout = {
 	.pres_shift = 8,
 	.css_mask = 0x1f,
 	.have_slck_mck = 0,
+	.is_pres_direct = 1,
 };
 
 static const struct clk_pcr_layout sam9x60_pcr_layout = {
diff --git a/drivers/clk/clk-asm9260.c b/drivers/clk/clk-asm9260.c
index dd0f90c9dd0e..536b59aabd2c 100644
--- a/drivers/clk/clk-asm9260.c
+++ b/drivers/clk/clk-asm9260.c
@@ -260,7 +260,6 @@ static void __init asm9260_acc_init(struct device_node *np)
 	const char *ref_clk, *pll_clk = "pll";
 	u32 rate;
 	int n;
-	u32 accuracy = 0;
 
 	clk_data = kzalloc(struct_size(clk_data, hws, MAX_CLKS), GFP_KERNEL);
 	if (!clk_data)
@@ -275,10 +274,11 @@ static void __init asm9260_acc_init(struct device_node *np)
 	/* register pll */
 	rate = (ioread32(base + HW_SYSPLLCTRL) & 0xffff) * 1000000;
 
+	/* TODO: Convert to DT parent scheme */
 	ref_clk = of_clk_get_parent_name(np, 0);
-	accuracy = clk_get_accuracy(__clk_lookup(ref_clk));
-	hw = clk_hw_register_fixed_rate_with_accuracy(NULL, pll_clk,
-			ref_clk, 0, rate, accuracy);
+	hw = __clk_hw_register_fixed_rate_with_accuracy(NULL, NULL, pll_clk,
+			ref_clk, NULL, NULL, 0, rate, 0,
+			CLK_FIXED_RATE_PARENT_ACCURACY);
 
 	if (IS_ERR(hw))
 		panic("%pOFn: can't register REFCLK. Check DT!", np);
diff --git a/drivers/clk/clk-bd718x7.c b/drivers/clk/clk-bd718x7.c
index 00926c587390..b52e8d6f660c 100644
--- a/drivers/clk/clk-bd718x7.c
+++ b/drivers/clk/clk-bd718x7.c
@@ -7,12 +7,25 @@
 #include <linux/err.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/mfd/rohm-bd718x7.h>
-#include <linux/mfd/rohm-bd70528.h>
+#include <linux/mfd/rohm-generic.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/regmap.h>
 
+/* clk control registers */
+/* BD70528 */
+#define BD70528_REG_OUT32K	0x2c
+/* BD71828 */
+#define BD71828_REG_OUT32K	0x4B
+/* BD71837 and BD71847 */
+#define BD718XX_REG_OUT32K	0x2E
+
+/*
+ * BD71837, BD71847, BD70528 and BD71828 all use bit [0] to clk output control
+ */
+#define CLK_OUT_EN_MASK		BIT(0)
+
+
 struct bd718xx_clk {
 	struct clk_hw hw;
 	u8 reg;
@@ -21,10 +34,8 @@ struct bd718xx_clk {
 	struct rohm_regmap_dev *mfd;
 };
 
-static int bd71837_clk_set(struct clk_hw *hw, int status)
+static int bd71837_clk_set(struct bd718xx_clk *c, unsigned int status)
 {
-	struct bd718xx_clk *c = container_of(hw, struct bd718xx_clk, hw);
-
 	return regmap_update_bits(c->mfd->regmap, c->reg, c->mask, status);
 }
 
@@ -33,14 +44,16 @@ static void bd71837_clk_disable(struct clk_hw *hw)
 	int rv;
 	struct bd718xx_clk *c = container_of(hw, struct bd718xx_clk, hw);
 
-	rv = bd71837_clk_set(hw, 0);
+	rv = bd71837_clk_set(c, 0);
 	if (rv)
 		dev_dbg(&c->pdev->dev, "Failed to disable 32K clk (%d)\n", rv);
 }
 
 static int bd71837_clk_enable(struct clk_hw *hw)
 {
-	return bd71837_clk_set(hw, 1);
+	struct bd718xx_clk *c = container_of(hw, struct bd718xx_clk, hw);
+
+	return bd71837_clk_set(c, 0xffffffff);
 }
 
 static int bd71837_clk_is_enabled(struct clk_hw *hw)
@@ -74,6 +87,7 @@ static int bd71837_clk_probe(struct platform_device *pdev)
 		.name = "bd718xx-32k-out",
 		.ops = &bd71837_clk_ops,
 	};
+	enum rohm_chip_type chip = platform_get_device_id(pdev)->driver_data;
 
 	c = devm_kzalloc(&pdev->dev, sizeof(*c), GFP_KERNEL);
 	if (!c)
@@ -87,15 +101,19 @@ static int bd71837_clk_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "No parent clk found\n");
 		return -EINVAL;
 	}
-	switch (mfd->chip_type) {
+	switch (chip) {
 	case ROHM_CHIP_TYPE_BD71837:
 	case ROHM_CHIP_TYPE_BD71847:
 		c->reg = BD718XX_REG_OUT32K;
-		c->mask = BD718XX_OUT32K_EN;
+		c->mask = CLK_OUT_EN_MASK;
+		break;
+	case ROHM_CHIP_TYPE_BD71828:
+		c->reg = BD71828_REG_OUT32K;
+		c->mask = CLK_OUT_EN_MASK;
 		break;
 	case ROHM_CHIP_TYPE_BD70528:
-		c->reg = BD70528_REG_CLK_OUT;
-		c->mask = BD70528_CLK_OUT_EN_MASK;
+		c->reg = BD70528_REG_OUT32K;
+		c->mask = CLK_OUT_EN_MASK;
 		break;
 	default:
 		dev_err(&pdev->dev, "Unknown clk chip\n");
@@ -121,11 +139,21 @@ static int bd71837_clk_probe(struct platform_device *pdev)
 	return rval;
 }
 
+static const struct platform_device_id bd718x7_clk_id[] = {
+	{ "bd71837-clk", ROHM_CHIP_TYPE_BD71837 },
+	{ "bd71847-clk", ROHM_CHIP_TYPE_BD71847 },
+	{ "bd70528-clk", ROHM_CHIP_TYPE_BD70528 },
+	{ "bd71828-clk", ROHM_CHIP_TYPE_BD71828 },
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, bd718x7_clk_id);
+
 static struct platform_driver bd71837_clk = {
 	.driver = {
 		.name = "bd718xx-clk",
 	},
 	.probe = bd71837_clk_probe,
+	.id_table = bd718x7_clk_id,
 };
 
 module_platform_driver(bd71837_clk);
diff --git a/drivers/clk/clk-bm1880.c b/drivers/clk/clk-bm1880.c
index 4cd175afce9b..e6d6599d310a 100644
--- a/drivers/clk/clk-bm1880.c
+++ b/drivers/clk/clk-bm1880.c
@@ -474,11 +474,10 @@ static struct bm1880_composite_clock bm1880_composite_clks[] = {
 static unsigned long bm1880_pll_rate_calc(u32 regval, unsigned long parent_rate)
 {
 	u64 numerator;
-	u32 fbdiv, fref, refdiv;
+	u32 fbdiv, refdiv;
 	u32 postdiv1, postdiv2, denominator;
 
 	fbdiv = (regval >> 16) & 0xfff;
-	fref = parent_rate;
 	refdiv = regval & 0x1f;
 	postdiv1 = (regval >> 8) & 0x7;
 	postdiv2 = (regval >> 12) & 0x7;
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 3e9c3e608769..7376f573bfdb 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -199,8 +199,9 @@ static void clk_composite_disable(struct clk_hw *hw)
 	gate_ops->disable(gate_hw);
 }
 
-struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name,
-			const char * const *parent_names, int num_parents,
+static struct clk_hw *__clk_hw_register_composite(struct device *dev,
+			const char *name, const char * const *parent_names,
+			const struct clk_parent_data *pdata, int num_parents,
 			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
 			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
@@ -218,7 +219,10 @@ struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name,
 
 	init.name = name;
 	init.flags = flags;
-	init.parent_names = parent_names;
+	if (parent_names)
+		init.parent_names = parent_names;
+	else
+		init.parent_data = pdata;
 	init.num_parents = num_parents;
 	hw = &composite->hw;
 
@@ -312,6 +316,34 @@ err:
 	return hw;
 }
 
+struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name,
+			const char * const *parent_names, int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __clk_hw_register_composite(dev, name, parent_names, NULL,
+					   num_parents, mux_hw, mux_ops,
+					   rate_hw, rate_ops, gate_hw,
+					   gate_ops, flags);
+}
+
+struct clk_hw *clk_hw_register_composite_pdata(struct device *dev,
+			const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	return __clk_hw_register_composite(dev, name, NULL, parent_data,
+					   num_parents, mux_hw, mux_ops,
+					   rate_hw, rate_ops, gate_hw,
+					   gate_ops, flags);
+}
+
 struct clk *clk_register_composite(struct device *dev, const char *name,
 			const char * const *parent_names, int num_parents,
 			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
@@ -329,6 +361,24 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 	return hw->clk;
 }
 
+struct clk *clk_register_composite_pdata(struct device *dev, const char *name,
+			const struct clk_parent_data *parent_data,
+			int num_parents,
+			struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+			struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+			struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+			unsigned long flags)
+{
+	struct clk_hw *hw;
+
+	hw = clk_hw_register_composite_pdata(dev, name, parent_data,
+			num_parents, mux_hw, mux_ops, rate_hw, rate_ops,
+			gate_hw, gate_ops, flags);
+	if (IS_ERR(hw))
+		return ERR_CAST(hw);
+	return hw->clk;
+}
+
 void clk_unregister_composite(struct clk *clk)
 {
 	struct clk_composite *composite;
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 098b2b01f0af..8de12cb0c43d 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -463,11 +463,12 @@ const struct clk_ops clk_divider_ro_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_divider_ro_ops);
 
-static struct clk_hw *_register_divider(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, const struct clk_div_table *table,
-		spinlock_t *lock)
+struct clk_hw *__clk_hw_register_divider(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock)
 {
 	struct clk_divider *div;
 	struct clk_hw *hw;
@@ -514,55 +515,7 @@ static struct clk_hw *_register_divider(struct device *dev, const char *name,
 
 	return hw;
 }
-
-/**
- * clk_register_divider - register a divider clock with the clock framework
- * @dev: device registering this clock
- * @name: name of this clock
- * @parent_name: name of clock's parent
- * @flags: framework-specific flags
- * @reg: register address to adjust divider
- * @shift: number of bits to shift the bitfield
- * @width: width of the bitfield
- * @clk_divider_flags: divider-specific flags for this clock
- * @lock: shared register lock for this clock
- */
-struct clk *clk_register_divider(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, spinlock_t *lock)
-{
-	struct clk_hw *hw;
-
-	hw =  _register_divider(dev, name, parent_name, flags, reg, shift,
-			width, clk_divider_flags, NULL, lock);
-	if (IS_ERR(hw))
-		return ERR_CAST(hw);
-	return hw->clk;
-}
-EXPORT_SYMBOL_GPL(clk_register_divider);
-
-/**
- * clk_hw_register_divider - register a divider clock with the clock framework
- * @dev: device registering this clock
- * @name: name of this clock
- * @parent_name: name of clock's parent
- * @flags: framework-specific flags
- * @reg: register address to adjust divider
- * @shift: number of bits to shift the bitfield
- * @width: width of the bitfield
- * @clk_divider_flags: divider-specific flags for this clock
- * @lock: shared register lock for this clock
- */
-struct clk_hw *clk_hw_register_divider(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, spinlock_t *lock)
-{
-	return _register_divider(dev, name, parent_name, flags, reg, shift,
-			width, clk_divider_flags, NULL, lock);
-}
-EXPORT_SYMBOL_GPL(clk_hw_register_divider);
+EXPORT_SYMBOL_GPL(__clk_hw_register_divider);
 
 /**
  * clk_register_divider_table - register a table based divider clock with
@@ -586,39 +539,15 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name,
 {
 	struct clk_hw *hw;
 
-	hw =  _register_divider(dev, name, parent_name, flags, reg, shift,
-			width, clk_divider_flags, table, lock);
+	hw =  __clk_hw_register_divider(dev, NULL, name, parent_name, NULL,
+			NULL, flags, reg, shift, width, clk_divider_flags,
+			table, lock);
 	if (IS_ERR(hw))
 		return ERR_CAST(hw);
 	return hw->clk;
 }
 EXPORT_SYMBOL_GPL(clk_register_divider_table);
 
-/**
- * clk_hw_register_divider_table - register a table based divider clock with
- * the clock framework
- * @dev: device registering this clock
- * @name: name of this clock
- * @parent_name: name of clock's parent
- * @flags: framework-specific flags
- * @reg: register address to adjust divider
- * @shift: number of bits to shift the bitfield
- * @width: width of the bitfield
- * @clk_divider_flags: divider-specific flags for this clock
- * @table: array of divider/value pairs ending with a div set to 0
- * @lock: shared register lock for this clock
- */
-struct clk_hw *clk_hw_register_divider_table(struct device *dev,
-		const char *name, const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, const struct clk_div_table *table,
-		spinlock_t *lock)
-{
-	return _register_divider(dev, name, parent_name, flags, reg, shift,
-			width, clk_divider_flags, table, lock);
-}
-EXPORT_SYMBOL_GPL(clk_hw_register_divider_table);
-
 void clk_unregister_divider(struct clk *clk)
 {
 	struct clk_divider *div;
diff --git a/drivers/clk/clk-fixed-rate.c b/drivers/clk/clk-fixed-rate.c
index 2c4486c09040..77499a27c8fb 100644
--- a/drivers/clk/clk-fixed-rate.c
+++ b/drivers/clk/clk-fixed-rate.c
@@ -24,6 +24,8 @@
  * parent - fixed parent.  No clk_set_parent support
  */
 
+#define to_clk_fixed_rate(_hw) container_of(_hw, struct clk_fixed_rate, hw)
+
 static unsigned long clk_fixed_rate_recalc_rate(struct clk_hw *hw,
 		unsigned long parent_rate)
 {
@@ -33,7 +35,12 @@ static unsigned long clk_fixed_rate_recalc_rate(struct clk_hw *hw,
 static unsigned long clk_fixed_rate_recalc_accuracy(struct clk_hw *hw,
 		unsigned long parent_accuracy)
 {
-	return to_clk_fixed_rate(hw)->fixed_accuracy;
+	struct clk_fixed_rate *fixed = to_clk_fixed_rate(hw);
+
+	if (fixed->flags & CLK_FIXED_RATE_PARENT_ACCURACY)
+		return parent_accuracy;
+
+	return fixed->fixed_accuracy;
 }
 
 const struct clk_ops clk_fixed_rate_ops = {
@@ -42,24 +49,17 @@ const struct clk_ops clk_fixed_rate_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_fixed_rate_ops);
 
-/**
- * clk_hw_register_fixed_rate_with_accuracy - register fixed-rate clock with
- * the clock framework
- * @dev: device that is registering this clock
- * @name: name of this clock
- * @parent_name: name of clock's parent
- * @flags: framework-specific flags
- * @fixed_rate: non-adjustable clock rate
- * @fixed_accuracy: non-adjustable clock rate
- */
-struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev,
-		const char *name, const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate, unsigned long fixed_accuracy)
+struct clk_hw *__clk_hw_register_fixed_rate(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		unsigned long fixed_rate, unsigned long fixed_accuracy,
+		unsigned long clk_fixed_flags)
 {
 	struct clk_fixed_rate *fixed;
 	struct clk_hw *hw;
 	struct clk_init_data init = {};
-	int ret;
+	int ret = -EINVAL;
 
 	/* allocate fixed-rate clock */
 	fixed = kzalloc(sizeof(*fixed), GFP_KERNEL);
@@ -69,17 +69,26 @@ struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev,
 	init.name = name;
 	init.ops = &clk_fixed_rate_ops;
 	init.flags = flags;
-	init.parent_names = (parent_name ? &parent_name: NULL);
-	init.num_parents = (parent_name ? 1 : 0);
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.parent_hws = parent_hw ? &parent_hw : NULL;
+	init.parent_data = parent_data;
+	if (parent_name || parent_hw || parent_data)
+		init.num_parents = 1;
+	else
+		init.num_parents = 0;
 
 	/* struct clk_fixed_rate assignments */
+	fixed->flags = clk_fixed_flags;
 	fixed->fixed_rate = fixed_rate;
 	fixed->fixed_accuracy = fixed_accuracy;
 	fixed->hw.init = &init;
 
 	/* register the clock */
 	hw = &fixed->hw;
-	ret = clk_hw_register(dev, hw);
+	if (dev || !np)
+		ret = clk_hw_register(dev, hw);
+	else if (np)
+		ret = of_clk_hw_register(np, hw);
 	if (ret) {
 		kfree(fixed);
 		hw = ERR_PTR(ret);
@@ -87,47 +96,20 @@ struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev,
 
 	return hw;
 }
-EXPORT_SYMBOL_GPL(clk_hw_register_fixed_rate_with_accuracy);
+EXPORT_SYMBOL_GPL(__clk_hw_register_fixed_rate);
 
-struct clk *clk_register_fixed_rate_with_accuracy(struct device *dev,
-		const char *name, const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate, unsigned long fixed_accuracy)
+struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
+		const char *parent_name, unsigned long flags,
+		unsigned long fixed_rate)
 {
 	struct clk_hw *hw;
 
 	hw = clk_hw_register_fixed_rate_with_accuracy(dev, name, parent_name,
-			flags, fixed_rate, fixed_accuracy);
+						      flags, fixed_rate, 0);
 	if (IS_ERR(hw))
 		return ERR_CAST(hw);
 	return hw->clk;
 }
-EXPORT_SYMBOL_GPL(clk_register_fixed_rate_with_accuracy);
-
-/**
- * clk_hw_register_fixed_rate - register fixed-rate clock with the clock
- * framework
- * @dev: device that is registering this clock
- * @name: name of this clock
- * @parent_name: name of clock's parent
- * @flags: framework-specific flags
- * @fixed_rate: non-adjustable clock rate
- */
-struct clk_hw *clk_hw_register_fixed_rate(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate)
-{
-	return clk_hw_register_fixed_rate_with_accuracy(dev, name, parent_name,
-						     flags, fixed_rate, 0);
-}
-EXPORT_SYMBOL_GPL(clk_hw_register_fixed_rate);
-
-struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate)
-{
-	return clk_register_fixed_rate_with_accuracy(dev, name, parent_name,
-						     flags, fixed_rate, 0);
-}
 EXPORT_SYMBOL_GPL(clk_register_fixed_rate);
 
 void clk_unregister_fixed_rate(struct clk *clk)
@@ -155,9 +137,9 @@ void clk_hw_unregister_fixed_rate(struct clk_hw *hw)
 EXPORT_SYMBOL_GPL(clk_hw_unregister_fixed_rate);
 
 #ifdef CONFIG_OF
-static struct clk *_of_fixed_clk_setup(struct device_node *node)
+static struct clk_hw *_of_fixed_clk_setup(struct device_node *node)
 {
-	struct clk *clk;
+	struct clk_hw *hw;
 	const char *clk_name = node->name;
 	u32 rate;
 	u32 accuracy = 0;
@@ -170,18 +152,18 @@ static struct clk *_of_fixed_clk_setup(struct device_node *node)
 
 	of_property_read_string(node, "clock-output-names", &clk_name);
 
-	clk = clk_register_fixed_rate_with_accuracy(NULL, clk_name, NULL,
+	hw = clk_hw_register_fixed_rate_with_accuracy(NULL, clk_name, NULL,
 						    0, rate, accuracy);
-	if (IS_ERR(clk))
-		return clk;
+	if (IS_ERR(hw))
+		return hw;
 
-	ret = of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	ret = of_clk_add_hw_provider(node, of_clk_hw_simple_get, hw);
 	if (ret) {
-		clk_unregister(clk);
+		clk_hw_unregister_fixed_rate(hw);
 		return ERR_PTR(ret);
 	}
 
-	return clk;
+	return hw;
 }
 
 /**
@@ -195,27 +177,27 @@ CLK_OF_DECLARE(fixed_clk, "fixed-clock", of_fixed_clk_setup);
 
 static int of_fixed_clk_remove(struct platform_device *pdev)
 {
-	struct clk *clk = platform_get_drvdata(pdev);
+	struct clk_hw *hw = platform_get_drvdata(pdev);
 
 	of_clk_del_provider(pdev->dev.of_node);
-	clk_unregister_fixed_rate(clk);
+	clk_hw_unregister_fixed_rate(hw);
 
 	return 0;
 }
 
 static int of_fixed_clk_probe(struct platform_device *pdev)
 {
-	struct clk *clk;
+	struct clk_hw *hw;
 
 	/*
 	 * This function is not executed when of_fixed_clk_setup
 	 * succeeded.
 	 */
-	clk = _of_fixed_clk_setup(pdev->dev.of_node);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+	hw = _of_fixed_clk_setup(pdev->dev.of_node);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
 
-	platform_set_drvdata(pdev, clk);
+	platform_set_drvdata(pdev, hw);
 
 	return 0;
 }
@@ -224,7 +206,6 @@ static const struct of_device_id of_fixed_clk_ids[] = {
 	{ .compatible = "fixed-clock" },
 	{ }
 };
-MODULE_DEVICE_TABLE(of, of_fixed_clk_ids);
 
 static struct platform_driver of_fixed_clk_driver = {
 	.driver = {
diff --git a/drivers/clk/clk-fsl-sai.c b/drivers/clk/clk-fsl-sai.c
new file mode 100644
index 000000000000..0221180a4dd7
--- /dev/null
+++ b/drivers/clk/clk-fsl-sai.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Freescale SAI BCLK as a generic clock driver
+ *
+ * Copyright 2020 Michael Walle <michael@walle.cc>
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+#define I2S_CSR		0x00
+#define I2S_CR2		0x08
+#define CSR_BCE_BIT	28
+#define CR2_BCD		BIT(24)
+#define CR2_DIV_SHIFT	0
+#define CR2_DIV_WIDTH	8
+
+struct fsl_sai_clk {
+	struct clk_divider div;
+	struct clk_gate gate;
+	spinlock_t lock;
+};
+
+static int fsl_sai_clk_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct fsl_sai_clk *sai_clk;
+	struct clk_parent_data pdata = { .index = 0 };
+	void __iomem *base;
+	struct clk_hw *hw;
+	struct resource *res;
+
+	sai_clk = devm_kzalloc(dev, sizeof(*sai_clk), GFP_KERNEL);
+	if (!sai_clk)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	spin_lock_init(&sai_clk->lock);
+
+	sai_clk->gate.reg = base + I2S_CSR;
+	sai_clk->gate.bit_idx = CSR_BCE_BIT;
+	sai_clk->gate.lock = &sai_clk->lock;
+
+	sai_clk->div.reg = base + I2S_CR2;
+	sai_clk->div.shift = CR2_DIV_SHIFT;
+	sai_clk->div.width = CR2_DIV_WIDTH;
+	sai_clk->div.lock = &sai_clk->lock;
+
+	/* set clock direction, we are the BCLK master */
+	writel(CR2_BCD, base + I2S_CR2);
+
+	hw = clk_hw_register_composite_pdata(dev, dev->of_node->name,
+					     &pdata, 1, NULL, NULL,
+					     &sai_clk->div.hw,
+					     &clk_divider_ops,
+					     &sai_clk->gate.hw,
+					     &clk_gate_ops,
+					     CLK_SET_RATE_GATE);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw);
+}
+
+static const struct of_device_id of_fsl_sai_clk_ids[] = {
+	{ .compatible = "fsl,vf610-sai-clock" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, of_fsl_sai_clk_ids);
+
+static struct platform_driver fsl_sai_clk_driver = {
+	.probe = fsl_sai_clk_probe,
+	.driver		= {
+		.name	= "fsl-sai-clk",
+		.of_match_table = of_fsl_sai_clk_ids,
+	},
+};
+module_platform_driver(fsl_sai_clk_driver);
+
+MODULE_DESCRIPTION("Freescale SAI bitclock-as-a-clock driver");
+MODULE_AUTHOR("Michael Walle <michael@walle.cc>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:fsl-sai-clk");
diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c
index 670053c58c1a..2ca1f2ac38a6 100644
--- a/drivers/clk/clk-gate.c
+++ b/drivers/clk/clk-gate.c
@@ -123,26 +123,18 @@ const struct clk_ops clk_gate_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_gate_ops);
 
-/**
- * clk_hw_register_gate - register a gate clock with the clock framework
- * @dev: device that is registering this clock
- * @name: name of this clock
- * @parent_name: name of this clock's parent
- * @flags: framework-specific flags for this clock
- * @reg: register address to control gating of this clock
- * @bit_idx: which bit in the register controls gating of this clock
- * @clk_gate_flags: gate-specific flags for this clock
- * @lock: shared register lock for this clock
- */
-struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
+struct clk_hw *__clk_hw_register_gate(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data,
+		unsigned long flags,
 		void __iomem *reg, u8 bit_idx,
 		u8 clk_gate_flags, spinlock_t *lock)
 {
 	struct clk_gate *gate;
 	struct clk_hw *hw;
 	struct clk_init_data init = {};
-	int ret;
+	int ret = -EINVAL;
 
 	if (clk_gate_flags & CLK_GATE_HIWORD_MASK) {
 		if (bit_idx > 15) {
@@ -160,7 +152,12 @@ struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name,
 	init.ops = &clk_gate_ops;
 	init.flags = flags;
 	init.parent_names = parent_name ? &parent_name : NULL;
-	init.num_parents = parent_name ? 1 : 0;
+	init.parent_hws = parent_hw ? &parent_hw : NULL;
+	init.parent_data = parent_data;
+	if (parent_name || parent_hw || parent_data)
+		init.num_parents = 1;
+	else
+		init.num_parents = 0;
 
 	/* struct clk_gate assignments */
 	gate->reg = reg;
@@ -170,15 +167,19 @@ struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name,
 	gate->hw.init = &init;
 
 	hw = &gate->hw;
-	ret = clk_hw_register(dev, hw);
+	if (dev || !np)
+		ret = clk_hw_register(dev, hw);
+	else if (np)
+		ret = of_clk_hw_register(np, hw);
 	if (ret) {
 		kfree(gate);
 		hw = ERR_PTR(ret);
 	}
 
 	return hw;
+
 }
-EXPORT_SYMBOL_GPL(clk_hw_register_gate);
+EXPORT_SYMBOL_GPL(__clk_hw_register_gate);
 
 struct clk *clk_register_gate(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c
index 13304cf5f2a8..70397b4b5ffe 100644
--- a/drivers/clk/clk-gpio.c
+++ b/drivers/clk/clk-gpio.c
@@ -28,6 +28,26 @@
  * parent - fixed parent.  No clk_set_parent support
  */
 
+/**
+ * struct clk_gpio - gpio gated clock
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @gpiod:	gpio descriptor
+ *
+ * Clock with a gpio control for enabling and disabling the parent clock
+ * or switching between two parents by asserting or deasserting the gpio.
+ *
+ * Implements .enable, .disable and .is_enabled or
+ * .get_parent, .set_parent and .determine_rate depending on which clk_ops
+ * is used.
+ */
+struct clk_gpio {
+	struct clk_hw	hw;
+	struct gpio_desc *gpiod;
+};
+
+#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw)
+
 static int clk_gpio_gate_enable(struct clk_hw *hw)
 {
 	struct clk_gpio *clk = to_clk_gpio(hw);
@@ -51,12 +71,11 @@ static int clk_gpio_gate_is_enabled(struct clk_hw *hw)
 	return gpiod_get_value(clk->gpiod);
 }
 
-const struct clk_ops clk_gpio_gate_ops = {
+static const struct clk_ops clk_gpio_gate_ops = {
 	.enable = clk_gpio_gate_enable,
 	.disable = clk_gpio_gate_disable,
 	.is_enabled = clk_gpio_gate_is_enabled,
 };
-EXPORT_SYMBOL_GPL(clk_gpio_gate_ops);
 
 static int clk_sleeping_gpio_gate_prepare(struct clk_hw *hw)
 {
@@ -111,67 +130,49 @@ static int clk_gpio_mux_set_parent(struct clk_hw *hw, u8 index)
 	return 0;
 }
 
-const struct clk_ops clk_gpio_mux_ops = {
+static const struct clk_ops clk_gpio_mux_ops = {
 	.get_parent = clk_gpio_mux_get_parent,
 	.set_parent = clk_gpio_mux_set_parent,
 	.determine_rate = __clk_mux_determine_rate,
 };
-EXPORT_SYMBOL_GPL(clk_gpio_mux_ops);
 
-static struct clk_hw *clk_register_gpio(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod,
-		unsigned long flags, const struct clk_ops *clk_gpio_ops)
+static struct clk_hw *clk_register_gpio(struct device *dev, u8 num_parents,
+					struct gpio_desc *gpiod,
+					const struct clk_ops *clk_gpio_ops)
 {
 	struct clk_gpio *clk_gpio;
 	struct clk_hw *hw;
 	struct clk_init_data init = {};
 	int err;
+	const struct clk_parent_data gpio_parent_data[] = {
+		{ .index = 0 },
+		{ .index = 1 },
+	};
 
-	if (dev)
-		clk_gpio = devm_kzalloc(dev, sizeof(*clk_gpio),	GFP_KERNEL);
-	else
-		clk_gpio = kzalloc(sizeof(*clk_gpio), GFP_KERNEL);
-
+	clk_gpio = devm_kzalloc(dev, sizeof(*clk_gpio),	GFP_KERNEL);
 	if (!clk_gpio)
 		return ERR_PTR(-ENOMEM);
 
-	init.name = name;
+	init.name = dev->of_node->name;
 	init.ops = clk_gpio_ops;
-	init.flags = flags;
-	init.parent_names = parent_names;
+	init.parent_data = gpio_parent_data;
 	init.num_parents = num_parents;
+	init.flags = CLK_SET_RATE_PARENT;
 
 	clk_gpio->gpiod = gpiod;
 	clk_gpio->hw.init = &init;
 
 	hw = &clk_gpio->hw;
-	if (dev)
-		err = devm_clk_hw_register(dev, hw);
-	else
-		err = clk_hw_register(NULL, hw);
-
-	if (!err)
-		return hw;
-
-	if (!dev) {
-		kfree(clk_gpio);
-	}
+	err = devm_clk_hw_register(dev, hw);
+	if (err)
+		return ERR_PTR(err);
 
-	return ERR_PTR(err);
+	return hw;
 }
 
-/**
- * clk_hw_register_gpio_gate - register a gpio clock gate with the clock
- * framework
- * @dev: device that is registering this clock
- * @name: name of this clock
- * @parent_name: name of this clock's parent
- * @gpiod: gpio descriptor to gate this clock
- * @flags: clock flags
- */
-struct clk_hw *clk_hw_register_gpio_gate(struct device *dev, const char *name,
-		const char *parent_name, struct gpio_desc *gpiod,
-		unsigned long flags)
+static struct clk_hw *clk_hw_register_gpio_gate(struct device *dev,
+						int num_parents,
+						struct gpio_desc *gpiod)
 {
 	const struct clk_ops *ops;
 
@@ -180,88 +181,36 @@ struct clk_hw *clk_hw_register_gpio_gate(struct device *dev, const char *name,
 	else
 		ops = &clk_gpio_gate_ops;
 
-	return clk_register_gpio(dev, name,
-			(parent_name ? &parent_name : NULL),
-			(parent_name ? 1 : 0), gpiod, flags, ops);
+	return clk_register_gpio(dev, num_parents, gpiod, ops);
 }
-EXPORT_SYMBOL_GPL(clk_hw_register_gpio_gate);
 
-struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
-		const char *parent_name, struct gpio_desc *gpiod,
-		unsigned long flags)
+static struct clk_hw *clk_hw_register_gpio_mux(struct device *dev,
+					       struct gpio_desc *gpiod)
 {
-	struct clk_hw *hw;
-
-	hw = clk_hw_register_gpio_gate(dev, name, parent_name, gpiod, flags);
-	if (IS_ERR(hw))
-		return ERR_CAST(hw);
-	return hw->clk;
+	return clk_register_gpio(dev, 2, gpiod, &clk_gpio_mux_ops);
 }
-EXPORT_SYMBOL_GPL(clk_register_gpio_gate);
-
-/**
- * clk_hw_register_gpio_mux - register a gpio clock mux with the clock framework
- * @dev: device that is registering this clock
- * @name: name of this clock
- * @parent_names: names of this clock's parents
- * @num_parents: number of parents listed in @parent_names
- * @gpiod: gpio descriptor to gate this clock
- * @flags: clock flags
- */
-struct clk_hw *clk_hw_register_gpio_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod,
-		unsigned long flags)
-{
-	if (num_parents != 2) {
-		pr_err("mux-clock %s must have 2 parents\n", name);
-		return ERR_PTR(-EINVAL);
-	}
-
-	return clk_register_gpio(dev, name, parent_names, num_parents,
-			gpiod, flags, &clk_gpio_mux_ops);
-}
-EXPORT_SYMBOL_GPL(clk_hw_register_gpio_mux);
-
-struct clk *clk_register_gpio_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod,
-		unsigned long flags)
-{
-	struct clk_hw *hw;
-
-	hw = clk_hw_register_gpio_mux(dev, name, parent_names, num_parents,
-			gpiod, flags);
-	if (IS_ERR(hw))
-		return ERR_CAST(hw);
-	return hw->clk;
-}
-EXPORT_SYMBOL_GPL(clk_register_gpio_mux);
 
 static int gpio_clk_driver_probe(struct platform_device *pdev)
 {
-	struct device_node *node = pdev->dev.of_node;
-	const char **parent_names, *gpio_name;
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node;
+	const char *gpio_name;
 	unsigned int num_parents;
 	struct gpio_desc *gpiod;
-	struct clk *clk;
+	struct clk_hw *hw;
 	bool is_mux;
 	int ret;
 
+	is_mux = of_device_is_compatible(node, "gpio-mux-clock");
+
 	num_parents = of_clk_get_parent_count(node);
-	if (num_parents) {
-		parent_names = devm_kcalloc(&pdev->dev, num_parents,
-					    sizeof(char *), GFP_KERNEL);
-		if (!parent_names)
-			return -ENOMEM;
-
-		of_clk_parent_fill(node, parent_names, num_parents);
-	} else {
-		parent_names = NULL;
+	if (is_mux && num_parents != 2) {
+		dev_err(dev, "mux-clock must have 2 parents\n");
+		return -EINVAL;
 	}
 
-	is_mux = of_device_is_compatible(node, "gpio-mux-clock");
-
 	gpio_name = is_mux ? "select" : "enable";
-	gpiod = devm_gpiod_get(&pdev->dev, gpio_name, GPIOD_OUT_LOW);
+	gpiod = devm_gpiod_get(dev, gpio_name, GPIOD_OUT_LOW);
 	if (IS_ERR(gpiod)) {
 		ret = PTR_ERR(gpiod);
 		if (ret == -EPROBE_DEFER)
@@ -275,16 +224,13 @@ static int gpio_clk_driver_probe(struct platform_device *pdev)
 	}
 
 	if (is_mux)
-		clk = clk_register_gpio_mux(&pdev->dev, node->name,
-				parent_names, num_parents, gpiod, 0);
+		hw = clk_hw_register_gpio_mux(dev, gpiod);
 	else
-		clk = clk_register_gpio_gate(&pdev->dev, node->name,
-				parent_names ?  parent_names[0] : NULL, gpiod,
-				CLK_SET_RATE_PARENT);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+		hw = clk_hw_register_gpio_gate(dev, num_parents, gpiod);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
 
-	return of_clk_add_provider(node, of_clk_src_simple_get, clk);
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw);
 }
 
 static const struct of_device_id gpio_clk_match_table[] = {
diff --git a/drivers/clk/clk-mux.c b/drivers/clk/clk-mux.c
index 570b6e5b603b..e54e79714818 100644
--- a/drivers/clk/clk-mux.c
+++ b/drivers/clk/clk-mux.c
@@ -145,17 +145,19 @@ const struct clk_ops clk_mux_ro_ops = {
 };
 EXPORT_SYMBOL_GPL(clk_mux_ro_ops);
 
-struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u32 mask,
+struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np,
+		const char *name, u8 num_parents,
+		const char * const *parent_names,
+		const struct clk_hw **parent_hws,
+		const struct clk_parent_data *parent_data,
+		unsigned long flags, void __iomem *reg, u8 shift, u32 mask,
 		u8 clk_mux_flags, u32 *table, spinlock_t *lock)
 {
 	struct clk_mux *mux;
 	struct clk_hw *hw;
 	struct clk_init_data init = {};
 	u8 width = 0;
-	int ret;
+	int ret = -EINVAL;
 
 	if (clk_mux_flags & CLK_MUX_HIWORD_MASK) {
 		width = fls(mask) - ffs(mask) + 1;
@@ -177,6 +179,8 @@ struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name,
 		init.ops = &clk_mux_ops;
 	init.flags = flags;
 	init.parent_names = parent_names;
+	init.parent_data = parent_data;
+	init.parent_hws = parent_hws;
 	init.num_parents = num_parents;
 
 	/* struct clk_mux assignments */
@@ -189,7 +193,10 @@ struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name,
 	mux->hw.init = &init;
 
 	hw = &mux->hw;
-	ret = clk_hw_register(dev, hw);
+	if (dev || !np)
+		ret = clk_hw_register(dev, hw);
+	else if (np)
+		ret = of_clk_hw_register(np, hw);
 	if (ret) {
 		kfree(mux);
 		hw = ERR_PTR(ret);
@@ -197,53 +204,24 @@ struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name,
 
 	return hw;
 }
-EXPORT_SYMBOL_GPL(clk_hw_register_mux_table);
+EXPORT_SYMBOL_GPL(__clk_hw_register_mux);
 
 struct clk *clk_register_mux_table(struct device *dev, const char *name,
 		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u32 mask,
+		unsigned long flags, void __iomem *reg, u8 shift, u32 mask,
 		u8 clk_mux_flags, u32 *table, spinlock_t *lock)
 {
 	struct clk_hw *hw;
 
-	hw = clk_hw_register_mux_table(dev, name, parent_names, num_parents,
-				       flags, reg, shift, mask, clk_mux_flags,
-				       table, lock);
+	hw = clk_hw_register_mux_table(dev, name, parent_names,
+				       num_parents, flags, reg, shift, mask,
+				       clk_mux_flags, table, lock);
 	if (IS_ERR(hw))
 		return ERR_CAST(hw);
 	return hw->clk;
 }
 EXPORT_SYMBOL_GPL(clk_register_mux_table);
 
-struct clk *clk_register_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_mux_flags, spinlock_t *lock)
-{
-	u32 mask = BIT(width) - 1;
-
-	return clk_register_mux_table(dev, name, parent_names, num_parents,
-				      flags, reg, shift, mask, clk_mux_flags,
-				      NULL, lock);
-}
-EXPORT_SYMBOL_GPL(clk_register_mux);
-
-struct clk_hw *clk_hw_register_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_mux_flags, spinlock_t *lock)
-{
-	u32 mask = BIT(width) - 1;
-
-	return clk_hw_register_mux_table(dev, name, parent_names, num_parents,
-				      flags, reg, shift, mask, clk_mux_flags,
-				      NULL, lock);
-}
-EXPORT_SYMBOL_GPL(clk_hw_register_mux);
-
 void clk_unregister_mux(struct clk *clk)
 {
 	struct clk_mux *mux;
diff --git a/drivers/clk/clk-plldig.c b/drivers/clk/clk-plldig.c
new file mode 100644
index 000000000000..312b8312d503
--- /dev/null
+++ b/drivers/clk/clk-plldig.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 NXP
+ *
+ * Clock driver for LS1028A Display output interfaces(LCD, DPHY).
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/bitfield.h>
+
+/* PLLDIG register offsets and bit masks */
+#define PLLDIG_REG_PLLSR            0x24
+#define PLLDIG_LOCK_MASK            BIT(2)
+#define PLLDIG_REG_PLLDV            0x28
+#define PLLDIG_MFD_MASK             GENMASK(7, 0)
+#define PLLDIG_RFDPHI1_MASK         GENMASK(30, 25)
+#define PLLDIG_REG_PLLFM            0x2c
+#define PLLDIG_SSCGBYP_ENABLE       BIT(30)
+#define PLLDIG_REG_PLLFD            0x30
+#define PLLDIG_FDEN                 BIT(30)
+#define PLLDIG_FRAC_MASK            GENMASK(15, 0)
+#define PLLDIG_REG_PLLCAL1          0x38
+#define PLLDIG_REG_PLLCAL2          0x3c
+
+/* Range of the VCO frequencies, in Hz */
+#define PLLDIG_MIN_VCO_FREQ         650000000
+#define PLLDIG_MAX_VCO_FREQ         1300000000
+
+/* Range of the output frequencies, in Hz */
+#define PHI1_MIN_FREQ               27000000UL
+#define PHI1_MAX_FREQ               600000000UL
+
+/* Maximum value of the reduced frequency divider */
+#define MAX_RFDPHI1          63UL
+
+/* Best value of multiplication factor divider */
+#define PLLDIG_DEFAULT_MFD   44
+
+/*
+ * Denominator part of the fractional part of the
+ * loop multiplication factor.
+ */
+#define MFDEN          20480
+
+static const struct clk_parent_data parent_data[] = {
+	{ .index = 0 },
+};
+
+struct clk_plldig {
+	struct clk_hw hw;
+	void __iomem *regs;
+	unsigned int vco_freq;
+};
+
+#define to_clk_plldig(_hw)	container_of(_hw, struct clk_plldig, hw)
+
+static int plldig_enable(struct clk_hw *hw)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+	u32 val;
+
+	val = readl(data->regs + PLLDIG_REG_PLLFM);
+	/*
+	 * Use Bypass mode with PLL off by default, the frequency overshoot
+	 * detector output was disable. SSCG Bypass mode should be enable.
+	 */
+	val |= PLLDIG_SSCGBYP_ENABLE;
+	writel(val, data->regs + PLLDIG_REG_PLLFM);
+
+	return 0;
+}
+
+static void plldig_disable(struct clk_hw *hw)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+	u32 val;
+
+	val = readl(data->regs + PLLDIG_REG_PLLFM);
+
+	val &= ~PLLDIG_SSCGBYP_ENABLE;
+	val |= FIELD_PREP(PLLDIG_SSCGBYP_ENABLE, 0x0);
+
+	writel(val, data->regs + PLLDIG_REG_PLLFM);
+}
+
+static int plldig_is_enabled(struct clk_hw *hw)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+
+	return readl(data->regs + PLLDIG_REG_PLLFM) &
+			      PLLDIG_SSCGBYP_ENABLE;
+}
+
+static unsigned long plldig_recalc_rate(struct clk_hw *hw,
+					unsigned long parent_rate)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+	u32 val, rfdphi1;
+
+	val = readl(data->regs + PLLDIG_REG_PLLDV);
+
+	/* Check if PLL is bypassed */
+	if (val & PLLDIG_SSCGBYP_ENABLE)
+		return parent_rate;
+
+	rfdphi1 = FIELD_GET(PLLDIG_RFDPHI1_MASK, val);
+
+	/*
+	 * If RFDPHI1 has a value of 1 the VCO frequency is also divided by
+	 * one.
+	 */
+	if (!rfdphi1)
+		rfdphi1 = 1;
+
+	return DIV_ROUND_UP(data->vco_freq, rfdphi1);
+}
+
+static unsigned long plldig_calc_target_div(unsigned long vco_freq,
+					    unsigned long target_rate)
+{
+	unsigned long div;
+
+	div = DIV_ROUND_CLOSEST(vco_freq, target_rate);
+	div = clamp(div, 1UL, MAX_RFDPHI1);
+
+	return div;
+}
+
+static int plldig_determine_rate(struct clk_hw *hw,
+				 struct clk_rate_request *req)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+	unsigned int div;
+
+	req->rate = clamp(req->rate, PHI1_MIN_FREQ, PHI1_MAX_FREQ);
+	div = plldig_calc_target_div(data->vco_freq, req->rate);
+	req->rate = DIV_ROUND_UP(data->vco_freq, div);
+
+	return 0;
+}
+
+static int plldig_set_rate(struct clk_hw *hw, unsigned long rate,
+		unsigned long parent_rate)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+	unsigned int val, cond;
+	unsigned int rfdphi1;
+
+	rate = clamp(rate, PHI1_MIN_FREQ, PHI1_MAX_FREQ);
+	rfdphi1 = plldig_calc_target_div(data->vco_freq, rate);
+
+	/* update the divider value */
+	val = readl(data->regs + PLLDIG_REG_PLLDV);
+	val &= ~PLLDIG_RFDPHI1_MASK;
+	val |= FIELD_PREP(PLLDIG_RFDPHI1_MASK, rfdphi1);
+	writel(val, data->regs + PLLDIG_REG_PLLDV);
+
+	/* waiting for old lock state to clear */
+	udelay(200);
+
+	/* Wait until PLL is locked or timeout */
+	return readl_poll_timeout_atomic(data->regs + PLLDIG_REG_PLLSR, cond,
+					 cond & PLLDIG_LOCK_MASK, 0,
+					 USEC_PER_MSEC);
+}
+
+static const struct clk_ops plldig_clk_ops = {
+	.enable = plldig_enable,
+	.disable = plldig_disable,
+	.is_enabled = plldig_is_enabled,
+	.recalc_rate = plldig_recalc_rate,
+	.determine_rate = plldig_determine_rate,
+	.set_rate = plldig_set_rate,
+};
+
+static int plldig_init(struct clk_hw *hw)
+{
+	struct clk_plldig *data = to_clk_plldig(hw);
+	struct clk_hw *parent = clk_hw_get_parent(hw);
+	unsigned long parent_rate = clk_hw_get_rate(parent);
+	unsigned long val;
+	unsigned long long lltmp;
+	unsigned int mfd, fracdiv = 0;
+
+	if (!parent)
+		return -EINVAL;
+
+	if (data->vco_freq) {
+		mfd = data->vco_freq / parent_rate;
+		lltmp = data->vco_freq % parent_rate;
+		lltmp *= MFDEN;
+		do_div(lltmp, parent_rate);
+		fracdiv = lltmp;
+	} else {
+		mfd = PLLDIG_DEFAULT_MFD;
+		data->vco_freq = parent_rate * mfd;
+	}
+
+	val = FIELD_PREP(PLLDIG_MFD_MASK, mfd);
+	writel(val, data->regs + PLLDIG_REG_PLLDV);
+
+	/* Enable fractional divider */
+	if (fracdiv) {
+		val = FIELD_PREP(PLLDIG_FRAC_MASK, fracdiv);
+		val |= PLLDIG_FDEN;
+		writel(val, data->regs + PLLDIG_REG_PLLFD);
+	}
+
+	return 0;
+}
+
+static int plldig_clk_probe(struct platform_device *pdev)
+{
+	struct clk_plldig *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(data->regs))
+		return PTR_ERR(data->regs);
+
+	data->hw.init = CLK_HW_INIT_PARENTS_DATA("dpclk",
+						 parent_data,
+						 &plldig_clk_ops,
+						 0);
+
+	ret = devm_clk_hw_register(dev, &data->hw);
+	if (ret) {
+		dev_err(dev, "failed to register %s clock\n",
+						dev->of_node->name);
+		return ret;
+	}
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					  &data->hw);
+	if (ret) {
+		dev_err(dev, "unable to add clk provider\n");
+		return ret;
+	}
+
+	/*
+	 * The frequency of the VCO cannot be changed during runtime.
+	 * Therefore, let the user specify a desired frequency.
+	 */
+	if (!of_property_read_u32(dev->of_node, "fsl,vco-hz",
+				  &data->vco_freq)) {
+		if (data->vco_freq < PLLDIG_MIN_VCO_FREQ ||
+		    data->vco_freq > PLLDIG_MAX_VCO_FREQ)
+			return -EINVAL;
+	}
+
+	return plldig_init(&data->hw);
+}
+
+static const struct of_device_id plldig_clk_id[] = {
+	{ .compatible = "fsl,ls1028a-plldig" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, plldig_clk_id);
+
+static struct platform_driver plldig_clk_driver = {
+	.driver = {
+		.name = "plldig-clock",
+		.of_match_table = plldig_clk_id,
+	},
+	.probe = plldig_clk_probe,
+};
+module_platform_driver(plldig_clk_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Wen He <wen.he_1@nxp.com>");
+MODULE_DESCRIPTION("LS1028A Display output interface pixel clock driver");
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index bed140f7375f..d5946f7486d6 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -342,6 +342,32 @@ static const struct clockgen_muxinfo ls1046a_hwa2 = {
 	},
 };
 
+static const struct clockgen_muxinfo ls1088a_hwa1 = {
+	{
+		{},
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV1 },
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV2 },
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV3 },
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV4 },
+		{},
+		{ CLKSEL_VALID, CGA_PLL2, PLL_DIV2 },
+		{ CLKSEL_VALID, CGA_PLL2, PLL_DIV3 },
+	},
+};
+
+static const struct clockgen_muxinfo ls1088a_hwa2 = {
+	{
+		{},
+		{ CLKSEL_VALID, CGA_PLL2, PLL_DIV1 },
+		{ CLKSEL_VALID, CGA_PLL2, PLL_DIV2 },
+		{ CLKSEL_VALID, CGA_PLL2, PLL_DIV3 },
+		{ CLKSEL_VALID, CGA_PLL2, PLL_DIV4 },
+		{},
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV2 },
+		{ CLKSEL_VALID, CGA_PLL1, PLL_DIV3 },
+	},
+};
+
 static const struct clockgen_muxinfo ls1012a_cmux = {
 	{
 		[0] = { CLKSEL_VALID, CGA_PLL1, PLL_DIV1 },
@@ -607,6 +633,9 @@ static const struct clockgen_chipinfo chipinfo[] = {
 		.cmux_groups = {
 			&clockgen2_cmux_cga12
 		},
+		.hwaccel = {
+			&ls1088a_hwa1, &ls1088a_hwa2
+		},
 		.cmux_to_group = {
 			0, 0, -1
 		},
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 772258de2d1f..f0f2b599fd7e 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -429,7 +429,7 @@ static void clk_core_fill_parent_index(struct clk_core *core, u8 index)
 			parent = ERR_PTR(-EPROBE_DEFER);
 	} else {
 		parent = clk_core_get(core, index);
-		if (IS_ERR(parent) && PTR_ERR(parent) == -ENOENT && entry->name)
+		if (PTR_ERR(parent) == -ENOENT && entry->name)
 			parent = clk_core_lookup(entry->name);
 	}
 
@@ -2996,6 +2996,41 @@ static int clk_dump_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(clk_dump);
 
+#undef CLOCK_ALLOW_WRITE_DEBUGFS
+#ifdef CLOCK_ALLOW_WRITE_DEBUGFS
+/*
+ * This can be dangerous, therefore don't provide any real compile time
+ * configuration option for this feature.
+ * People who want to use this will need to modify the source code directly.
+ */
+static int clk_rate_set(void *data, u64 val)
+{
+	struct clk_core *core = data;
+	int ret;
+
+	clk_prepare_lock();
+	ret = clk_core_set_rate_nolock(core, val);
+	clk_prepare_unlock();
+
+	return ret;
+}
+
+#define clk_rate_mode	0644
+#else
+#define clk_rate_set	NULL
+#define clk_rate_mode	0444
+#endif
+
+static int clk_rate_get(void *data, u64 *val)
+{
+	struct clk_core *core = data;
+
+	*val = core->rate;
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(clk_rate_fops, clk_rate_get, clk_rate_set, "%llu\n");
+
 static const struct {
 	unsigned long flag;
 	const char *name;
@@ -3145,7 +3180,8 @@ static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 	root = debugfs_create_dir(core->name, pdentry);
 	core->dentry = root;
 
-	debugfs_create_ulong("clk_rate", 0444, root, &core->rate);
+	debugfs_create_file("clk_rate", clk_rate_mode, root, core,
+			    &clk_rate_fops);
 	debugfs_create_file("clk_min_rate", 0444, root, core, &clk_min_rate_fops);
 	debugfs_create_file("clk_max_rate", 0444, root, core, &clk_max_rate_fops);
 	debugfs_create_ulong("clk_accuracy", 0444, root, &core->accuracy);
@@ -3338,6 +3374,26 @@ static int __clk_core_init(struct clk_core *core)
 		goto out;
 	}
 
+	/*
+	 * optional platform-specific magic
+	 *
+	 * The .init callback is not used by any of the basic clock types, but
+	 * exists for weird hardware that must perform initialization magic for
+	 * CCF to get an accurate view of clock for any other callbacks. It may
+	 * also be used needs to perform dynamic allocations. Such allocation
+	 * must be freed in the terminate() callback.
+	 * This callback shall not be used to initialize the parameters state,
+	 * such as rate, parent, etc ...
+	 *
+	 * If it exist, this callback should called before any other callback of
+	 * the clock
+	 */
+	if (core->ops->init) {
+		ret = core->ops->init(core->hw);
+		if (ret)
+			goto out;
+	}
+
 	core->parent = __clk_init_parent(core);
 
 	/*
@@ -3363,17 +3419,6 @@ static int __clk_core_init(struct clk_core *core)
 	}
 
 	/*
-	 * optional platform-specific magic
-	 *
-	 * The .init callback is not used by any of the basic clock types, but
-	 * exists for weird hardware that must perform initialization magic.
-	 * Please consider other ways of solving initialization problems before
-	 * using this callback, as its use is discouraged.
-	 */
-	if (core->ops->init)
-		core->ops->init(core->hw);
-
-	/*
 	 * Set clk's accuracy.  The preferred method is to use
 	 * .recalc_accuracy. For simple clocks and lazy developers the default
 	 * fallback is to use the parent's accuracy.  If a clock doesn't have a
@@ -3427,13 +3472,18 @@ static int __clk_core_init(struct clk_core *core)
 		unsigned long flags;
 
 		ret = clk_core_prepare(core);
-		if (ret)
+		if (ret) {
+			pr_warn("%s: critical clk '%s' failed to prepare\n",
+			       __func__, core->name);
 			goto out;
+		}
 
 		flags = clk_enable_lock();
 		ret = clk_core_enable(core);
 		clk_enable_unlock(flags);
 		if (ret) {
+			pr_warn("%s: critical clk '%s' failed to enable\n",
+			       __func__, core->name);
 			clk_core_unprepare(core);
 			goto out;
 		}
@@ -3733,6 +3783,28 @@ fail_out:
 }
 
 /**
+ * dev_or_parent_of_node() - Get device node of @dev or @dev's parent
+ * @dev: Device to get device node of
+ *
+ * Return: device node pointer of @dev, or the device node pointer of
+ * @dev->parent if dev doesn't have a device node, or NULL if neither
+ * @dev or @dev->parent have a device node.
+ */
+static struct device_node *dev_or_parent_of_node(struct device *dev)
+{
+	struct device_node *np;
+
+	if (!dev)
+		return NULL;
+
+	np = dev_of_node(dev);
+	if (!np)
+		np = dev_of_node(dev->parent);
+
+	return np;
+}
+
+/**
  * clk_register - allocate a new clock, register it and return an opaque cookie
  * @dev: device that is registering this clock
  * @hw: link to hardware-specific clock data
@@ -3747,7 +3819,7 @@ fail_out:
  */
 struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 {
-	return __clk_register(dev, dev_of_node(dev), hw);
+	return __clk_register(dev, dev_or_parent_of_node(dev), hw);
 }
 EXPORT_SYMBOL_GPL(clk_register);
 
@@ -3763,7 +3835,8 @@ EXPORT_SYMBOL_GPL(clk_register);
  */
 int clk_hw_register(struct device *dev, struct clk_hw *hw)
 {
-	return PTR_ERR_OR_ZERO(__clk_register(dev, dev_of_node(dev), hw));
+	return PTR_ERR_OR_ZERO(__clk_register(dev, dev_or_parent_of_node(dev),
+			       hw));
 }
 EXPORT_SYMBOL_GPL(clk_hw_register);
 
@@ -3866,6 +3939,7 @@ static void clk_core_evict_parent_cache(struct clk_core *core)
 void clk_unregister(struct clk *clk)
 {
 	unsigned long flags;
+	const struct clk_ops *ops;
 
 	if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
 		return;
@@ -3874,7 +3948,8 @@ void clk_unregister(struct clk *clk)
 
 	clk_prepare_lock();
 
-	if (clk->core->ops == &clk_nodrv_ops) {
+	ops = clk->core->ops;
+	if (ops == &clk_nodrv_ops) {
 		pr_err("%s: unregistered clock: %s\n", __func__,
 		       clk->core->name);
 		goto unlock;
@@ -3887,6 +3962,9 @@ void clk_unregister(struct clk *clk)
 	clk->core->ops = &clk_nodrv_ops;
 	clk_enable_unlock(flags);
 
+	if (ops->terminate)
+		ops->terminate(clk->core->hw);
+
 	if (!hlist_empty(&clk->core->children)) {
 		struct clk_core *child;
 		struct hlist_node *t;
diff --git a/drivers/clk/imx/Kconfig b/drivers/clk/imx/Kconfig
index 1ac0c7990392..01eadee88d66 100644
--- a/drivers/clk/imx/Kconfig
+++ b/drivers/clk/imx/Kconfig
@@ -20,6 +20,12 @@ config CLK_IMX8MN
 	help
 	    Build the driver for i.MX8MN CCM Clock Driver
 
+config CLK_IMX8MP
+	bool "IMX8MP CCM Clock Driver"
+	depends on ARCH_MXC && ARM64
+	help
+	    Build the driver for i.MX8MP CCM Clock Driver
+
 config CLK_IMX8MQ
 	bool "IMX8MQ CCM Clock Driver"
 	depends on ARCH_MXC && ARM64
diff --git a/drivers/clk/imx/Makefile b/drivers/clk/imx/Makefile
index 77a3d714f1d5..928f874c73d2 100644
--- a/drivers/clk/imx/Makefile
+++ b/drivers/clk/imx/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_MXC_CLK) += \
 	clk-pllv2.o \
 	clk-pllv3.o \
 	clk-pllv4.o \
-	clk-sccg-pll.o \
+	clk-sscg-pll.o \
 	clk-pll14xx.o
 
 obj-$(CONFIG_MXC_CLK_SCU) += \
@@ -27,6 +27,7 @@ obj-$(CONFIG_MXC_CLK_SCU) += \
 
 obj-$(CONFIG_CLK_IMX8MM) += clk-imx8mm.o
 obj-$(CONFIG_CLK_IMX8MN) += clk-imx8mn.o
+obj-$(CONFIG_CLK_IMX8MP) += clk-imx8mp.o
 obj-$(CONFIG_CLK_IMX8MQ) += clk-imx8mq.o
 obj-$(CONFIG_CLK_IMX8QXP) += clk-imx8qxp.o clk-imx8qxp-lpcg.o
 
diff --git a/drivers/clk/imx/clk-composite-7ulp.c b/drivers/clk/imx/clk-composite-7ulp.c
index 060f8600ea0d..b9efcc8a855d 100644
--- a/drivers/clk/imx/clk-composite-7ulp.c
+++ b/drivers/clk/imx/clk-composite-7ulp.c
@@ -21,7 +21,7 @@
 #define PCG_PCD_WIDTH	3
 #define PCG_PCD_MASK	0x7
 
-struct clk_hw *imx7ulp_clk_composite(const char *name,
+struct clk_hw *imx7ulp_clk_hw_composite(const char *name,
 				     const char * const *parent_names,
 				     int num_parents, bool mux_present,
 				     bool rate_present, bool gate_present,
diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c
index d3486ee79ab5..20f7c91c03d2 100644
--- a/drivers/clk/imx/clk-composite-8m.c
+++ b/drivers/clk/imx/clk-composite-8m.c
@@ -123,7 +123,7 @@ static const struct clk_ops imx8m_clk_composite_divider_ops = {
 	.set_rate = imx8m_clk_composite_divider_set_rate,
 };
 
-struct clk *imx8m_clk_composite_flags(const char *name,
+struct clk_hw *imx8m_clk_hw_composite_flags(const char *name,
 					const char * const *parent_names,
 					int num_parents, void __iomem *reg,
 					unsigned long flags)
@@ -171,7 +171,7 @@ struct clk *imx8m_clk_composite_flags(const char *name,
 	if (IS_ERR(hw))
 		goto fail;
 
-	return hw->clk;
+	return hw;
 
 fail:
 	kfree(gate);
diff --git a/drivers/clk/imx/clk-divider-gate.c b/drivers/clk/imx/clk-divider-gate.c
index 2a8352a316c7..0322a843d245 100644
--- a/drivers/clk/imx/clk-divider-gate.c
+++ b/drivers/clk/imx/clk-divider-gate.c
@@ -43,7 +43,7 @@ static unsigned long clk_divider_gate_recalc_rate(struct clk_hw *hw,
 {
 	struct clk_divider_gate *div_gate = to_clk_divider_gate(hw);
 	struct clk_divider *div = to_clk_divider(hw);
-	unsigned long flags = 0;
+	unsigned long flags;
 	unsigned int val;
 
 	spin_lock_irqsave(div->lock, flags);
@@ -75,7 +75,7 @@ static int clk_divider_gate_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct clk_divider_gate *div_gate = to_clk_divider_gate(hw);
 	struct clk_divider *div = to_clk_divider(hw);
-	unsigned long flags = 0;
+	unsigned long flags;
 	int value;
 	u32 val;
 
@@ -104,7 +104,7 @@ static int clk_divider_enable(struct clk_hw *hw)
 {
 	struct clk_divider_gate *div_gate = to_clk_divider_gate(hw);
 	struct clk_divider *div = to_clk_divider(hw);
-	unsigned long flags = 0;
+	unsigned long flags;
 	u32 val;
 
 	if (!div_gate->cached_val) {
@@ -127,7 +127,7 @@ static void clk_divider_disable(struct clk_hw *hw)
 {
 	struct clk_divider_gate *div_gate = to_clk_divider_gate(hw);
 	struct clk_divider *div = to_clk_divider(hw);
-	unsigned long flags = 0;
+	unsigned long flags;
 	u32 val;
 
 	spin_lock_irqsave(div->lock, flags);
@@ -167,13 +167,13 @@ static const struct clk_ops clk_divider_gate_ops = {
 };
 
 /*
- * NOTE: In order to resue the most code from the common divider,
+ * NOTE: In order to reuse the most code from the common divider,
  * we also design our divider following the way that provids an extra
  * clk_divider_flags, however it's fixed to CLK_DIVIDER_ONE_BASED by
  * default as our HW is. Besides that it supports only CLK_DIVIDER_READ_ONLY
  * flag which can be specified by user flexibly.
  */
-struct clk_hw *imx_clk_divider_gate(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_divider_gate(const char *name, const char *parent_name,
 				    unsigned long flags, void __iomem *reg,
 				    u8 shift, u8 width, u8 clk_divider_flags,
 				    const struct clk_div_table *table,
diff --git a/drivers/clk/imx/clk-frac-pll.c b/drivers/clk/imx/clk-frac-pll.c
index fece503e3610..101e0a300376 100644
--- a/drivers/clk/imx/clk-frac-pll.c
+++ b/drivers/clk/imx/clk-frac-pll.c
@@ -201,8 +201,9 @@ static const struct clk_ops clk_frac_pll_ops = {
 	.set_rate	= clk_pll_set_rate,
 };
 
-struct clk *imx_clk_frac_pll(const char *name, const char *parent_name,
-			     void __iomem *base)
+struct clk_hw *imx_clk_hw_frac_pll(const char *name,
+				   const char *parent_name,
+				   void __iomem *base)
 {
 	struct clk_init_data init;
 	struct clk_frac_pll *pll;
@@ -230,5 +231,5 @@ struct clk *imx_clk_frac_pll(const char *name, const char *parent_name,
 		return ERR_PTR(ret);
 	}
 
-	return hw->clk;
+	return hw;
 }
diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index 60f2de851f39..ba33c79158de 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -598,7 +598,10 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	}
 
 	hws[IMX6QDL_CLK_PLL4_POST_DIV] = clk_hw_register_divider_table(NULL, "pll4_post_div", "pll4_audio", CLK_SET_RATE_PARENT, base + 0x70, 19, 2, 0, post_div_table, &imx_ccm_lock);
-	hws[IMX6QDL_CLK_PLL4_AUDIO_DIV] = clk_hw_register_divider(NULL, "pll4_audio_div", "pll4_post_div", CLK_SET_RATE_PARENT, base + 0x170, 15, 1, 0, &imx_ccm_lock);
+	if (clk_on_imx6q() || clk_on_imx6qp())
+		hws[IMX6QDL_CLK_PLL4_AUDIO_DIV] = imx_clk_hw_fixed_factor("pll4_audio_div", "pll4_post_div", 1, 1);
+	else
+		hws[IMX6QDL_CLK_PLL4_AUDIO_DIV] = clk_hw_register_divider(NULL, "pll4_audio_div", "pll4_post_div", CLK_SET_RATE_PARENT, base + 0x170, 15, 1, 0, &imx_ccm_lock);
 	hws[IMX6QDL_CLK_PLL5_POST_DIV] = clk_hw_register_divider_table(NULL, "pll5_post_div", "pll5_video", CLK_SET_RATE_PARENT, base + 0xa0, 19, 2, 0, post_div_table, &imx_ccm_lock);
 	hws[IMX6QDL_CLK_PLL5_VIDEO_DIV] = clk_hw_register_divider_table(NULL, "pll5_video_div", "pll5_post_div", CLK_SET_RATE_PARENT, base + 0x170, 30, 2, 0, video_div_table, &imx_ccm_lock);
 
diff --git a/drivers/clk/imx/clk-imx7ulp.c b/drivers/clk/imx/clk-imx7ulp.c
index 281191b55b3a..0620d6c8c072 100644
--- a/drivers/clk/imx/clk-imx7ulp.c
+++ b/drivers/clk/imx/clk-imx7ulp.c
@@ -59,7 +59,7 @@ static struct clk **pcc3_uart_clks[ARRAY_SIZE(pcc3_uart_clk_ids) + 1] __initdata
 static void __init imx7ulp_clk_scg1_init(struct device_node *np)
 {
 	struct clk_hw_onecell_data *clk_data;
-	struct clk_hw **clks;
+	struct clk_hw **hws;
 	void __iomem *base;
 
 	clk_data = kzalloc(struct_size(clk_data, hws, IMX7ULP_CLK_SCG1_END),
@@ -68,76 +68,76 @@ static void __init imx7ulp_clk_scg1_init(struct device_node *np)
 		return;
 
 	clk_data->num = IMX7ULP_CLK_SCG1_END;
-	clks = clk_data->hws;
+	hws = clk_data->hws;
 
-	clks[IMX7ULP_CLK_DUMMY]		= imx_clk_hw_fixed("dummy", 0);
+	hws[IMX7ULP_CLK_DUMMY]		= imx_clk_hw_fixed("dummy", 0);
 
-	clks[IMX7ULP_CLK_ROSC]		= imx_obtain_fixed_clk_hw(np, "rosc");
-	clks[IMX7ULP_CLK_SOSC]		= imx_obtain_fixed_clk_hw(np, "sosc");
-	clks[IMX7ULP_CLK_SIRC]		= imx_obtain_fixed_clk_hw(np, "sirc");
-	clks[IMX7ULP_CLK_FIRC]		= imx_obtain_fixed_clk_hw(np, "firc");
-	clks[IMX7ULP_CLK_UPLL]		= imx_obtain_fixed_clk_hw(np, "upll");
+	hws[IMX7ULP_CLK_ROSC]		= imx_obtain_fixed_clk_hw(np, "rosc");
+	hws[IMX7ULP_CLK_SOSC]		= imx_obtain_fixed_clk_hw(np, "sosc");
+	hws[IMX7ULP_CLK_SIRC]		= imx_obtain_fixed_clk_hw(np, "sirc");
+	hws[IMX7ULP_CLK_FIRC]		= imx_obtain_fixed_clk_hw(np, "firc");
+	hws[IMX7ULP_CLK_UPLL]		= imx_obtain_fixed_clk_hw(np, "upll");
 
 	/* SCG1 */
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 
 	/* NOTE: xPLL config can't be changed when xPLL is enabled */
-	clks[IMX7ULP_CLK_APLL_PRE_SEL]	= imx_clk_hw_mux_flags("apll_pre_sel", base + 0x508, 0, 1, pll_pre_sels, ARRAY_SIZE(pll_pre_sels), CLK_SET_PARENT_GATE);
-	clks[IMX7ULP_CLK_SPLL_PRE_SEL]	= imx_clk_hw_mux_flags("spll_pre_sel", base + 0x608, 0, 1, pll_pre_sels, ARRAY_SIZE(pll_pre_sels), CLK_SET_PARENT_GATE);
+	hws[IMX7ULP_CLK_APLL_PRE_SEL]	= imx_clk_hw_mux_flags("apll_pre_sel", base + 0x508, 0, 1, pll_pre_sels, ARRAY_SIZE(pll_pre_sels), CLK_SET_PARENT_GATE);
+	hws[IMX7ULP_CLK_SPLL_PRE_SEL]	= imx_clk_hw_mux_flags("spll_pre_sel", base + 0x608, 0, 1, pll_pre_sels, ARRAY_SIZE(pll_pre_sels), CLK_SET_PARENT_GATE);
 
 	/*							   name		    parent_name	   reg			shift	width	flags */
-	clks[IMX7ULP_CLK_APLL_PRE_DIV]	= imx_clk_hw_divider_flags("apll_pre_div", "apll_pre_sel", base + 0x508,	8,	3,	CLK_SET_RATE_GATE);
-	clks[IMX7ULP_CLK_SPLL_PRE_DIV]	= imx_clk_hw_divider_flags("spll_pre_div", "spll_pre_sel", base + 0x608,	8,	3,	CLK_SET_RATE_GATE);
+	hws[IMX7ULP_CLK_APLL_PRE_DIV]	= imx_clk_hw_divider_flags("apll_pre_div", "apll_pre_sel", base + 0x508,	8,	3,	CLK_SET_RATE_GATE);
+	hws[IMX7ULP_CLK_SPLL_PRE_DIV]	= imx_clk_hw_divider_flags("spll_pre_div", "spll_pre_sel", base + 0x608,	8,	3,	CLK_SET_RATE_GATE);
 
 	/*						name	 parent_name	 base */
-	clks[IMX7ULP_CLK_APLL]		= imx_clk_pllv4("apll",  "apll_pre_div", base + 0x500);
-	clks[IMX7ULP_CLK_SPLL]		= imx_clk_pllv4("spll",  "spll_pre_div", base + 0x600);
+	hws[IMX7ULP_CLK_APLL]		= imx_clk_hw_pllv4("apll",  "apll_pre_div", base + 0x500);
+	hws[IMX7ULP_CLK_SPLL]		= imx_clk_hw_pllv4("spll",  "spll_pre_div", base + 0x600);
 
 	/* APLL PFDs */
-	clks[IMX7ULP_CLK_APLL_PFD0]	= imx_clk_pfdv2("apll_pfd0", "apll", base + 0x50c, 0);
-	clks[IMX7ULP_CLK_APLL_PFD1]	= imx_clk_pfdv2("apll_pfd1", "apll", base + 0x50c, 1);
-	clks[IMX7ULP_CLK_APLL_PFD2]	= imx_clk_pfdv2("apll_pfd2", "apll", base + 0x50c, 2);
-	clks[IMX7ULP_CLK_APLL_PFD3]	= imx_clk_pfdv2("apll_pfd3", "apll", base + 0x50c, 3);
+	hws[IMX7ULP_CLK_APLL_PFD0]	= imx_clk_hw_pfdv2("apll_pfd0", "apll", base + 0x50c, 0);
+	hws[IMX7ULP_CLK_APLL_PFD1]	= imx_clk_hw_pfdv2("apll_pfd1", "apll", base + 0x50c, 1);
+	hws[IMX7ULP_CLK_APLL_PFD2]	= imx_clk_hw_pfdv2("apll_pfd2", "apll", base + 0x50c, 2);
+	hws[IMX7ULP_CLK_APLL_PFD3]	= imx_clk_hw_pfdv2("apll_pfd3", "apll", base + 0x50c, 3);
 
 	/* SPLL PFDs */
-	clks[IMX7ULP_CLK_SPLL_PFD0]	= imx_clk_pfdv2("spll_pfd0", "spll", base + 0x60C, 0);
-	clks[IMX7ULP_CLK_SPLL_PFD1]	= imx_clk_pfdv2("spll_pfd1", "spll", base + 0x60C, 1);
-	clks[IMX7ULP_CLK_SPLL_PFD2]	= imx_clk_pfdv2("spll_pfd2", "spll", base + 0x60C, 2);
-	clks[IMX7ULP_CLK_SPLL_PFD3]	= imx_clk_pfdv2("spll_pfd3", "spll", base + 0x60C, 3);
+	hws[IMX7ULP_CLK_SPLL_PFD0]	= imx_clk_hw_pfdv2("spll_pfd0", "spll", base + 0x60C, 0);
+	hws[IMX7ULP_CLK_SPLL_PFD1]	= imx_clk_hw_pfdv2("spll_pfd1", "spll", base + 0x60C, 1);
+	hws[IMX7ULP_CLK_SPLL_PFD2]	= imx_clk_hw_pfdv2("spll_pfd2", "spll", base + 0x60C, 2);
+	hws[IMX7ULP_CLK_SPLL_PFD3]	= imx_clk_hw_pfdv2("spll_pfd3", "spll", base + 0x60C, 3);
 
 	/* PLL Mux */
-	clks[IMX7ULP_CLK_APLL_PFD_SEL]	= imx_clk_hw_mux_flags("apll_pfd_sel", base + 0x508, 14, 2, apll_pfd_sels, ARRAY_SIZE(apll_pfd_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
-	clks[IMX7ULP_CLK_SPLL_PFD_SEL]	= imx_clk_hw_mux_flags("spll_pfd_sel", base + 0x608, 14, 2, spll_pfd_sels, ARRAY_SIZE(spll_pfd_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
-	clks[IMX7ULP_CLK_APLL_SEL]	= imx_clk_hw_mux_flags("apll_sel", base + 0x508, 1, 1, apll_sels, ARRAY_SIZE(apll_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
-	clks[IMX7ULP_CLK_SPLL_SEL]	= imx_clk_hw_mux_flags("spll_sel", base + 0x608, 1, 1, spll_sels, ARRAY_SIZE(spll_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
+	hws[IMX7ULP_CLK_APLL_PFD_SEL]	= imx_clk_hw_mux_flags("apll_pfd_sel", base + 0x508, 14, 2, apll_pfd_sels, ARRAY_SIZE(apll_pfd_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
+	hws[IMX7ULP_CLK_SPLL_PFD_SEL]	= imx_clk_hw_mux_flags("spll_pfd_sel", base + 0x608, 14, 2, spll_pfd_sels, ARRAY_SIZE(spll_pfd_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
+	hws[IMX7ULP_CLK_APLL_SEL]	= imx_clk_hw_mux_flags("apll_sel", base + 0x508, 1, 1, apll_sels, ARRAY_SIZE(apll_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
+	hws[IMX7ULP_CLK_SPLL_SEL]	= imx_clk_hw_mux_flags("spll_sel", base + 0x608, 1, 1, spll_sels, ARRAY_SIZE(spll_sels), CLK_SET_RATE_PARENT | CLK_SET_PARENT_GATE);
 
-	clks[IMX7ULP_CLK_SPLL_BUS_CLK]	= imx_clk_divider_gate("spll_bus_clk", "spll_sel", CLK_SET_RATE_GATE, base + 0x604, 8, 3, 0, ulp_div_table, &imx_ccm_lock);
+	hws[IMX7ULP_CLK_SPLL_BUS_CLK]	= imx_clk_hw_divider_gate("spll_bus_clk", "spll_sel", CLK_SET_RATE_GATE, base + 0x604, 8, 3, 0, ulp_div_table, &imx_ccm_lock);
 
 	/* scs/ddr/nic select different clock source requires that clock to be enabled first */
-	clks[IMX7ULP_CLK_SYS_SEL]	= imx_clk_hw_mux2("scs_sel", base + 0x14, 24, 4, scs_sels, ARRAY_SIZE(scs_sels));
-	clks[IMX7ULP_CLK_HSRUN_SYS_SEL] = imx_clk_hw_mux2("hsrun_scs_sel", base + 0x1c, 24, 4, scs_sels, ARRAY_SIZE(scs_sels));
-	clks[IMX7ULP_CLK_NIC_SEL]	= imx_clk_hw_mux2("nic_sel", base + 0x40, 28, 1, nic_sels, ARRAY_SIZE(nic_sels));
-	clks[IMX7ULP_CLK_DDR_SEL]	= imx_clk_hw_mux_flags("ddr_sel", base + 0x30, 24, 2, ddr_sels, ARRAY_SIZE(ddr_sels), CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
+	hws[IMX7ULP_CLK_SYS_SEL]	= imx_clk_hw_mux2("scs_sel", base + 0x14, 24, 4, scs_sels, ARRAY_SIZE(scs_sels));
+	hws[IMX7ULP_CLK_HSRUN_SYS_SEL] = imx_clk_hw_mux2("hsrun_scs_sel", base + 0x1c, 24, 4, scs_sels, ARRAY_SIZE(scs_sels));
+	hws[IMX7ULP_CLK_NIC_SEL]	= imx_clk_hw_mux2("nic_sel", base + 0x40, 28, 1, nic_sels, ARRAY_SIZE(nic_sels));
+	hws[IMX7ULP_CLK_DDR_SEL]	= imx_clk_hw_mux_flags("ddr_sel", base + 0x30, 24, 2, ddr_sels, ARRAY_SIZE(ddr_sels), CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
 
-	clks[IMX7ULP_CLK_CORE_DIV]	= imx_clk_hw_divider_flags("divcore",	"scs_sel",  base + 0x14, 16, 4, CLK_SET_RATE_PARENT);
-	clks[IMX7ULP_CLK_HSRUN_CORE_DIV] = imx_clk_hw_divider_flags("hsrun_divcore", "hsrun_scs_sel", base + 0x1c, 16, 4, CLK_SET_RATE_PARENT);
+	hws[IMX7ULP_CLK_CORE_DIV]	= imx_clk_hw_divider_flags("divcore",	"scs_sel",  base + 0x14, 16, 4, CLK_SET_RATE_PARENT);
+	hws[IMX7ULP_CLK_HSRUN_CORE_DIV] = imx_clk_hw_divider_flags("hsrun_divcore", "hsrun_scs_sel", base + 0x1c, 16, 4, CLK_SET_RATE_PARENT);
 
-	clks[IMX7ULP_CLK_DDR_DIV]	= imx_clk_divider_gate("ddr_clk", "ddr_sel", CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, base + 0x30, 0, 3,
+	hws[IMX7ULP_CLK_DDR_DIV]	= imx_clk_hw_divider_gate("ddr_clk", "ddr_sel", CLK_SET_RATE_PARENT | CLK_IS_CRITICAL, base + 0x30, 0, 3,
 							       0, ulp_div_table, &imx_ccm_lock);
 
-	clks[IMX7ULP_CLK_NIC0_DIV]	= imx_clk_hw_divider_flags("nic0_clk",		"nic_sel",  base + 0x40, 24, 4, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
-	clks[IMX7ULP_CLK_NIC1_DIV]	= imx_clk_hw_divider_flags("nic1_clk",		"nic0_clk", base + 0x40, 16, 4, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
-	clks[IMX7ULP_CLK_NIC1_BUS_DIV]	= imx_clk_hw_divider_flags("nic1_bus_clk",	"nic0_clk", base + 0x40, 4,  4, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
+	hws[IMX7ULP_CLK_NIC0_DIV]	= imx_clk_hw_divider_flags("nic0_clk",		"nic_sel",  base + 0x40, 24, 4, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
+	hws[IMX7ULP_CLK_NIC1_DIV]	= imx_clk_hw_divider_flags("nic1_clk",		"nic0_clk", base + 0x40, 16, 4, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
+	hws[IMX7ULP_CLK_NIC1_BUS_DIV]	= imx_clk_hw_divider_flags("nic1_bus_clk",	"nic0_clk", base + 0x40, 4,  4, CLK_SET_RATE_PARENT | CLK_IS_CRITICAL);
 
-	clks[IMX7ULP_CLK_GPU_DIV]	= imx_clk_hw_divider("gpu_clk", "nic0_clk", base + 0x40, 20, 4);
+	hws[IMX7ULP_CLK_GPU_DIV]	= imx_clk_hw_divider("gpu_clk", "nic0_clk", base + 0x40, 20, 4);
 
-	clks[IMX7ULP_CLK_SOSC_BUS_CLK]	= imx_clk_divider_gate("sosc_bus_clk", "sosc", 0, base + 0x104, 8, 3,
+	hws[IMX7ULP_CLK_SOSC_BUS_CLK]	= imx_clk_hw_divider_gate("sosc_bus_clk", "sosc", 0, base + 0x104, 8, 3,
 							       CLK_DIVIDER_READ_ONLY, ulp_div_table, &imx_ccm_lock);
-	clks[IMX7ULP_CLK_FIRC_BUS_CLK]	= imx_clk_divider_gate("firc_bus_clk", "firc", 0, base + 0x304, 8, 3,
+	hws[IMX7ULP_CLK_FIRC_BUS_CLK]	= imx_clk_hw_divider_gate("firc_bus_clk", "firc", 0, base + 0x304, 8, 3,
 							       CLK_DIVIDER_READ_ONLY, ulp_div_table, &imx_ccm_lock);
 
-	imx_check_clk_hws(clks, clk_data->num);
+	imx_check_clk_hws(hws, clk_data->num);
 
 	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 }
@@ -146,7 +146,7 @@ CLK_OF_DECLARE(imx7ulp_clk_scg1, "fsl,imx7ulp-scg1", imx7ulp_clk_scg1_init);
 static void __init imx7ulp_clk_pcc2_init(struct device_node *np)
 {
 	struct clk_hw_onecell_data *clk_data;
-	struct clk_hw **clks;
+	struct clk_hw **hws;
 	void __iomem *base;
 	int i;
 
@@ -156,42 +156,42 @@ static void __init imx7ulp_clk_pcc2_init(struct device_node *np)
 		return;
 
 	clk_data->num = IMX7ULP_CLK_PCC2_END;
-	clks = clk_data->hws;
+	hws = clk_data->hws;
 
 	/* PCC2 */
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 
-	clks[IMX7ULP_CLK_DMA1]		= imx_clk_hw_gate("dma1", "nic1_clk", base + 0x20, 30);
-	clks[IMX7ULP_CLK_RGPIO2P1]	= imx_clk_hw_gate("rgpio2p1", "nic1_bus_clk", base + 0x3c, 30);
-	clks[IMX7ULP_CLK_DMA_MUX1]	= imx_clk_hw_gate("dma_mux1", "nic1_bus_clk", base + 0x84, 30);
-	clks[IMX7ULP_CLK_CAAM]		= imx_clk_hw_gate("caam", "nic1_clk", base + 0x90, 30);
-	clks[IMX7ULP_CLK_LPTPM4]	= imx7ulp_clk_composite("lptpm4",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x94);
-	clks[IMX7ULP_CLK_LPTPM5]	= imx7ulp_clk_composite("lptpm5",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x98);
-	clks[IMX7ULP_CLK_LPIT1]		= imx7ulp_clk_composite("lpit1",   periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x9c);
-	clks[IMX7ULP_CLK_LPSPI2]	= imx7ulp_clk_composite("lpspi2",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xa4);
-	clks[IMX7ULP_CLK_LPSPI3]	= imx7ulp_clk_composite("lpspi3",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xa8);
-	clks[IMX7ULP_CLK_LPI2C4]	= imx7ulp_clk_composite("lpi2c4",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xac);
-	clks[IMX7ULP_CLK_LPI2C5]	= imx7ulp_clk_composite("lpi2c5",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xb0);
-	clks[IMX7ULP_CLK_LPUART4]	= imx7ulp_clk_composite("lpuart4", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xb4);
-	clks[IMX7ULP_CLK_LPUART5]	= imx7ulp_clk_composite("lpuart5", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xb8);
-	clks[IMX7ULP_CLK_FLEXIO1]	= imx7ulp_clk_composite("flexio1", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xc4);
-	clks[IMX7ULP_CLK_USB0]		= imx7ulp_clk_composite("usb0",    periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xcc);
-	clks[IMX7ULP_CLK_USB1]		= imx7ulp_clk_composite("usb1",    periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xd0);
-	clks[IMX7ULP_CLK_USB_PHY]	= imx_clk_hw_gate("usb_phy", "nic1_bus_clk", base + 0xd4, 30);
-	clks[IMX7ULP_CLK_USDHC0]	= imx7ulp_clk_composite("usdhc0",  periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xdc);
-	clks[IMX7ULP_CLK_USDHC1]	= imx7ulp_clk_composite("usdhc1",  periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xe0);
-	clks[IMX7ULP_CLK_WDG1]		= imx7ulp_clk_composite("wdg1",    periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, true,  true, base + 0xf4);
-	clks[IMX7ULP_CLK_WDG2]		= imx7ulp_clk_composite("sdg2",    periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, true,  true, base + 0x10c);
-
-	imx_check_clk_hws(clks, clk_data->num);
+	hws[IMX7ULP_CLK_DMA1]		= imx_clk_hw_gate("dma1", "nic1_clk", base + 0x20, 30);
+	hws[IMX7ULP_CLK_RGPIO2P1]	= imx_clk_hw_gate("rgpio2p1", "nic1_bus_clk", base + 0x3c, 30);
+	hws[IMX7ULP_CLK_DMA_MUX1]	= imx_clk_hw_gate("dma_mux1", "nic1_bus_clk", base + 0x84, 30);
+	hws[IMX7ULP_CLK_CAAM]		= imx_clk_hw_gate("caam", "nic1_clk", base + 0x90, 30);
+	hws[IMX7ULP_CLK_LPTPM4]		= imx7ulp_clk_hw_composite("lptpm4",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x94);
+	hws[IMX7ULP_CLK_LPTPM5]		= imx7ulp_clk_hw_composite("lptpm5",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x98);
+	hws[IMX7ULP_CLK_LPIT1]		= imx7ulp_clk_hw_composite("lpit1",   periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x9c);
+	hws[IMX7ULP_CLK_LPSPI2]		= imx7ulp_clk_hw_composite("lpspi2",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xa4);
+	hws[IMX7ULP_CLK_LPSPI3]		= imx7ulp_clk_hw_composite("lpspi3",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xa8);
+	hws[IMX7ULP_CLK_LPI2C4]		= imx7ulp_clk_hw_composite("lpi2c4",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xac);
+	hws[IMX7ULP_CLK_LPI2C5]		= imx7ulp_clk_hw_composite("lpi2c5",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xb0);
+	hws[IMX7ULP_CLK_LPUART4]	= imx7ulp_clk_hw_composite("lpuart4", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xb4);
+	hws[IMX7ULP_CLK_LPUART5]	= imx7ulp_clk_hw_composite("lpuart5", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xb8);
+	hws[IMX7ULP_CLK_FLEXIO1]	= imx7ulp_clk_hw_composite("flexio1", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0xc4);
+	hws[IMX7ULP_CLK_USB0]		= imx7ulp_clk_hw_composite("usb0",    periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xcc);
+	hws[IMX7ULP_CLK_USB1]		= imx7ulp_clk_hw_composite("usb1",    periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xd0);
+	hws[IMX7ULP_CLK_USB_PHY]	= imx_clk_hw_gate("usb_phy", "nic1_bus_clk", base + 0xd4, 30);
+	hws[IMX7ULP_CLK_USDHC0]		= imx7ulp_clk_hw_composite("usdhc0",  periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xdc);
+	hws[IMX7ULP_CLK_USDHC1]		= imx7ulp_clk_hw_composite("usdhc1",  periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xe0);
+	hws[IMX7ULP_CLK_WDG1]		= imx7ulp_clk_hw_composite("wdg1",    periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, true,  true, base + 0xf4);
+	hws[IMX7ULP_CLK_WDG2]		= imx7ulp_clk_hw_composite("wdg2",    periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, true,  true, base + 0x10c);
+
+	imx_check_clk_hws(hws, clk_data->num);
 
 	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 
 	for (i = 0; i < ARRAY_SIZE(pcc2_uart_clk_ids); i++) {
 		int index = pcc2_uart_clk_ids[i];
 
-		pcc2_uart_clks[i] = &clks[index]->clk;
+		pcc2_uart_clks[i] = &hws[index]->clk;
 	}
 
 	imx_register_uart_clocks(pcc2_uart_clks);
@@ -201,7 +201,7 @@ CLK_OF_DECLARE(imx7ulp_clk_pcc2, "fsl,imx7ulp-pcc2", imx7ulp_clk_pcc2_init);
 static void __init imx7ulp_clk_pcc3_init(struct device_node *np)
 {
 	struct clk_hw_onecell_data *clk_data;
-	struct clk_hw **clks;
+	struct clk_hw **hws;
 	void __iomem *base;
 	int i;
 
@@ -211,41 +211,41 @@ static void __init imx7ulp_clk_pcc3_init(struct device_node *np)
 		return;
 
 	clk_data->num = IMX7ULP_CLK_PCC3_END;
-	clks = clk_data->hws;
+	hws = clk_data->hws;
 
 	/* PCC3 */
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 
-	clks[IMX7ULP_CLK_LPTPM6]	= imx7ulp_clk_composite("lptpm6",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x84);
-	clks[IMX7ULP_CLK_LPTPM7]	= imx7ulp_clk_composite("lptpm7",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x88);
+	hws[IMX7ULP_CLK_LPTPM6]	= imx7ulp_clk_hw_composite("lptpm6",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x84);
+	hws[IMX7ULP_CLK_LPTPM7]	= imx7ulp_clk_hw_composite("lptpm7",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x88);
 
-	clks[IMX7ULP_CLK_MMDC]		= clk_hw_register_gate(NULL, "mmdc", "nic1_clk", CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
+	hws[IMX7ULP_CLK_MMDC]		= clk_hw_register_gate(NULL, "mmdc", "nic1_clk", CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
 							       base + 0xac, 30, 0, &imx_ccm_lock);
-	clks[IMX7ULP_CLK_LPI2C6]	= imx7ulp_clk_composite("lpi2c6",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x90);
-	clks[IMX7ULP_CLK_LPI2C7]	= imx7ulp_clk_composite("lpi2c7",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x94);
-	clks[IMX7ULP_CLK_LPUART6]	= imx7ulp_clk_composite("lpuart6", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x98);
-	clks[IMX7ULP_CLK_LPUART7]	= imx7ulp_clk_composite("lpuart7", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x9c);
-	clks[IMX7ULP_CLK_DSI]		= imx7ulp_clk_composite("dsi",     periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, true,  true, base + 0xa4);
-	clks[IMX7ULP_CLK_LCDIF]		= imx7ulp_clk_composite("lcdif",   periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xa8);
+	hws[IMX7ULP_CLK_LPI2C6]	= imx7ulp_clk_hw_composite("lpi2c6",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x90);
+	hws[IMX7ULP_CLK_LPI2C7]	= imx7ulp_clk_hw_composite("lpi2c7",  periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x94);
+	hws[IMX7ULP_CLK_LPUART6]	= imx7ulp_clk_hw_composite("lpuart6", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x98);
+	hws[IMX7ULP_CLK_LPUART7]	= imx7ulp_clk_hw_composite("lpuart7", periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, false, true, base + 0x9c);
+	hws[IMX7ULP_CLK_DSI]		= imx7ulp_clk_hw_composite("dsi",     periph_bus_sels, ARRAY_SIZE(periph_bus_sels), true, true,  true, base + 0xa4);
+	hws[IMX7ULP_CLK_LCDIF]		= imx7ulp_clk_hw_composite("lcdif",   periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, true,  true, base + 0xa8);
 
-	clks[IMX7ULP_CLK_VIU]		= imx_clk_hw_gate("viu",   "nic1_clk",	   base + 0xa0, 30);
-	clks[IMX7ULP_CLK_PCTLC]		= imx_clk_hw_gate("pctlc", "nic1_bus_clk", base + 0xb8, 30);
-	clks[IMX7ULP_CLK_PCTLD]		= imx_clk_hw_gate("pctld", "nic1_bus_clk", base + 0xbc, 30);
-	clks[IMX7ULP_CLK_PCTLE]		= imx_clk_hw_gate("pctle", "nic1_bus_clk", base + 0xc0, 30);
-	clks[IMX7ULP_CLK_PCTLF]		= imx_clk_hw_gate("pctlf", "nic1_bus_clk", base + 0xc4, 30);
+	hws[IMX7ULP_CLK_VIU]		= imx_clk_hw_gate("viu",   "nic1_clk",	   base + 0xa0, 30);
+	hws[IMX7ULP_CLK_PCTLC]		= imx_clk_hw_gate("pctlc", "nic1_bus_clk", base + 0xb8, 30);
+	hws[IMX7ULP_CLK_PCTLD]		= imx_clk_hw_gate("pctld", "nic1_bus_clk", base + 0xbc, 30);
+	hws[IMX7ULP_CLK_PCTLE]		= imx_clk_hw_gate("pctle", "nic1_bus_clk", base + 0xc0, 30);
+	hws[IMX7ULP_CLK_PCTLF]		= imx_clk_hw_gate("pctlf", "nic1_bus_clk", base + 0xc4, 30);
 
-	clks[IMX7ULP_CLK_GPU3D]		= imx7ulp_clk_composite("gpu3d",   periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, false, true, base + 0x140);
-	clks[IMX7ULP_CLK_GPU2D]		= imx7ulp_clk_composite("gpu2d",   periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, false, true, base + 0x144);
+	hws[IMX7ULP_CLK_GPU3D]		= imx7ulp_clk_hw_composite("gpu3d",   periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, false, true, base + 0x140);
+	hws[IMX7ULP_CLK_GPU2D]		= imx7ulp_clk_hw_composite("gpu2d",   periph_plat_sels, ARRAY_SIZE(periph_plat_sels), true, false, true, base + 0x144);
 
-	imx_check_clk_hws(clks, clk_data->num);
+	imx_check_clk_hws(hws, clk_data->num);
 
 	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 
 	for (i = 0; i < ARRAY_SIZE(pcc3_uart_clk_ids); i++) {
 		int index = pcc3_uart_clk_ids[i];
 
-		pcc3_uart_clks[i] = &clks[index]->clk;
+		pcc3_uart_clks[i] = &hws[index]->clk;
 	}
 
 	imx_register_uart_clocks(pcc3_uart_clks);
@@ -255,7 +255,7 @@ CLK_OF_DECLARE(imx7ulp_clk_pcc3, "fsl,imx7ulp-pcc3", imx7ulp_clk_pcc3_init);
 static void __init imx7ulp_clk_smc1_init(struct device_node *np)
 {
 	struct clk_hw_onecell_data *clk_data;
-	struct clk_hw **clks;
+	struct clk_hw **hws;
 	void __iomem *base;
 
 	clk_data = kzalloc(struct_size(clk_data, hws, IMX7ULP_CLK_SMC1_END),
@@ -264,15 +264,15 @@ static void __init imx7ulp_clk_smc1_init(struct device_node *np)
 		return;
 
 	clk_data->num = IMX7ULP_CLK_SMC1_END;
-	clks = clk_data->hws;
+	hws = clk_data->hws;
 
 	/* SMC1 */
 	base = of_iomap(np, 0);
 	WARN_ON(!base);
 
-	clks[IMX7ULP_CLK_ARM] = imx_clk_hw_mux_flags("arm", base + 0x10, 8, 2, arm_sels, ARRAY_SIZE(arm_sels), CLK_IS_CRITICAL);
+	hws[IMX7ULP_CLK_ARM] = imx_clk_hw_mux_flags("arm", base + 0x10, 8, 2, arm_sels, ARRAY_SIZE(arm_sels), CLK_IS_CRITICAL);
 
-	imx_check_clk_hws(clks, clk_data->num);
+	imx_check_clk_hws(hws, clk_data->num);
 
 	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_data);
 }
diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c
index 030b15d7c0ce..2ed93fc25087 100644
--- a/drivers/clk/imx/clk-imx8mm.c
+++ b/drivers/clk/imx/clk-imx8mm.c
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 #include "clk.h"
@@ -285,118 +286,126 @@ static const char *imx8mm_dram_core_sels[] = {"dram_pll_out", "dram_alt_root", }
 static const char *imx8mm_clko1_sels[] = {"osc_24m", "sys_pll1_800m", "osc_27m", "sys_pll1_200m", "audio_pll2_out",
 					 "vpu_pll", "sys_pll1_80m", };
 
-static struct clk *clks[IMX8MM_CLK_END];
-static struct clk_onecell_data clk_data;
+static struct clk_hw_onecell_data *clk_hw_data;
+static struct clk_hw **hws;
 
-static struct clk ** const uart_clks[] = {
-	&clks[IMX8MM_CLK_UART1_ROOT],
-	&clks[IMX8MM_CLK_UART2_ROOT],
-	&clks[IMX8MM_CLK_UART3_ROOT],
-	&clks[IMX8MM_CLK_UART4_ROOT],
-	NULL
+static const int uart_clk_ids[] = {
+	IMX8MM_CLK_UART1_ROOT,
+	IMX8MM_CLK_UART2_ROOT,
+	IMX8MM_CLK_UART3_ROOT,
+	IMX8MM_CLK_UART4_ROOT,
 };
+static struct clk **uart_hws[ARRAY_SIZE(uart_clk_ids) + 1];
 
 static int imx8mm_clocks_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	void __iomem *base;
-	int ret;
+	int ret, i;
 
-	clks[IMX8MM_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
-	clks[IMX8MM_CLK_24M] = of_clk_get_by_name(np, "osc_24m");
-	clks[IMX8MM_CLK_32K] = of_clk_get_by_name(np, "osc_32k");
-	clks[IMX8MM_CLK_EXT1] = of_clk_get_by_name(np, "clk_ext1");
-	clks[IMX8MM_CLK_EXT2] = of_clk_get_by_name(np, "clk_ext2");
-	clks[IMX8MM_CLK_EXT3] = of_clk_get_by_name(np, "clk_ext3");
-	clks[IMX8MM_CLK_EXT4] = of_clk_get_by_name(np, "clk_ext4");
+	clk_hw_data = kzalloc(struct_size(clk_hw_data, hws,
+					  IMX8MM_CLK_END), GFP_KERNEL);
+	if (WARN_ON(!clk_hw_data))
+		return -ENOMEM;
+
+	clk_hw_data->num = IMX8MM_CLK_END;
+	hws = clk_hw_data->hws;
+
+	hws[IMX8MM_CLK_DUMMY] = imx_clk_hw_fixed("dummy", 0);
+	hws[IMX8MM_CLK_24M] = imx_obtain_fixed_clk_hw(np, "osc_24m");
+	hws[IMX8MM_CLK_32K] = imx_obtain_fixed_clk_hw(np, "osc_32k");
+	hws[IMX8MM_CLK_EXT1] = imx_obtain_fixed_clk_hw(np, "clk_ext1");
+	hws[IMX8MM_CLK_EXT2] = imx_obtain_fixed_clk_hw(np, "clk_ext2");
+	hws[IMX8MM_CLK_EXT3] = imx_obtain_fixed_clk_hw(np, "clk_ext3");
+	hws[IMX8MM_CLK_EXT4] = imx_obtain_fixed_clk_hw(np, "clk_ext4");
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mm-anatop");
 	base = of_iomap(np, 0);
 	if (WARN_ON(!base))
 		return -ENOMEM;
 
-	clks[IMX8MM_AUDIO_PLL1_REF_SEL] = imx_clk_mux("audio_pll1_ref_sel", base + 0x0, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_AUDIO_PLL2_REF_SEL] = imx_clk_mux("audio_pll2_ref_sel", base + 0x14, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_VIDEO_PLL1_REF_SEL] = imx_clk_mux("video_pll1_ref_sel", base + 0x28, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_DRAM_PLL_REF_SEL] = imx_clk_mux("dram_pll_ref_sel", base + 0x50, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_GPU_PLL_REF_SEL] = imx_clk_mux("gpu_pll_ref_sel", base + 0x64, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_VPU_PLL_REF_SEL] = imx_clk_mux("vpu_pll_ref_sel", base + 0x74, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_ARM_PLL_REF_SEL] = imx_clk_mux("arm_pll_ref_sel", base + 0x84, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MM_SYS_PLL3_REF_SEL] = imx_clk_mux("sys_pll3_ref_sel", base + 0x114, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-
-	clks[IMX8MM_AUDIO_PLL1] = imx_clk_pll14xx("audio_pll1", "audio_pll1_ref_sel", base, &imx_1443x_pll);
-	clks[IMX8MM_AUDIO_PLL2] = imx_clk_pll14xx("audio_pll2", "audio_pll2_ref_sel", base + 0x14, &imx_1443x_pll);
-	clks[IMX8MM_VIDEO_PLL1] = imx_clk_pll14xx("video_pll1", "video_pll1_ref_sel", base + 0x28, &imx_1443x_pll);
-	clks[IMX8MM_DRAM_PLL] = imx_clk_pll14xx("dram_pll", "dram_pll_ref_sel", base + 0x50, &imx_1443x_pll);
-	clks[IMX8MM_GPU_PLL] = imx_clk_pll14xx("gpu_pll", "gpu_pll_ref_sel", base + 0x64, &imx_1416x_pll);
-	clks[IMX8MM_VPU_PLL] = imx_clk_pll14xx("vpu_pll", "vpu_pll_ref_sel", base + 0x74, &imx_1416x_pll);
-	clks[IMX8MM_ARM_PLL] = imx_clk_pll14xx("arm_pll", "arm_pll_ref_sel", base + 0x84, &imx_1416x_pll);
-	clks[IMX8MM_SYS_PLL1] = imx_clk_fixed("sys_pll1", 800000000);
-	clks[IMX8MM_SYS_PLL2] = imx_clk_fixed("sys_pll2", 1000000000);
-	clks[IMX8MM_SYS_PLL3] = imx_clk_pll14xx("sys_pll3", "sys_pll3_ref_sel", base + 0x114, &imx_1416x_pll);
+	hws[IMX8MM_AUDIO_PLL1_REF_SEL] = imx_clk_hw_mux("audio_pll1_ref_sel", base + 0x0, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_AUDIO_PLL2_REF_SEL] = imx_clk_hw_mux("audio_pll2_ref_sel", base + 0x14, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_VIDEO_PLL1_REF_SEL] = imx_clk_hw_mux("video_pll1_ref_sel", base + 0x28, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_DRAM_PLL_REF_SEL] = imx_clk_hw_mux("dram_pll_ref_sel", base + 0x50, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_GPU_PLL_REF_SEL] = imx_clk_hw_mux("gpu_pll_ref_sel", base + 0x64, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_VPU_PLL_REF_SEL] = imx_clk_hw_mux("vpu_pll_ref_sel", base + 0x74, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_ARM_PLL_REF_SEL] = imx_clk_hw_mux("arm_pll_ref_sel", base + 0x84, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MM_SYS_PLL3_REF_SEL] = imx_clk_hw_mux("sys_pll3_ref_sel", base + 0x114, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+
+	hws[IMX8MM_AUDIO_PLL1] = imx_clk_hw_pll14xx("audio_pll1", "audio_pll1_ref_sel", base, &imx_1443x_pll);
+	hws[IMX8MM_AUDIO_PLL2] = imx_clk_hw_pll14xx("audio_pll2", "audio_pll2_ref_sel", base + 0x14, &imx_1443x_pll);
+	hws[IMX8MM_VIDEO_PLL1] = imx_clk_hw_pll14xx("video_pll1", "video_pll1_ref_sel", base + 0x28, &imx_1443x_pll);
+	hws[IMX8MM_DRAM_PLL] = imx_clk_hw_pll14xx("dram_pll", "dram_pll_ref_sel", base + 0x50, &imx_1443x_dram_pll);
+	hws[IMX8MM_GPU_PLL] = imx_clk_hw_pll14xx("gpu_pll", "gpu_pll_ref_sel", base + 0x64, &imx_1416x_pll);
+	hws[IMX8MM_VPU_PLL] = imx_clk_hw_pll14xx("vpu_pll", "vpu_pll_ref_sel", base + 0x74, &imx_1416x_pll);
+	hws[IMX8MM_ARM_PLL] = imx_clk_hw_pll14xx("arm_pll", "arm_pll_ref_sel", base + 0x84, &imx_1416x_pll);
+	hws[IMX8MM_SYS_PLL1] = imx_clk_hw_fixed("sys_pll1", 800000000);
+	hws[IMX8MM_SYS_PLL2] = imx_clk_hw_fixed("sys_pll2", 1000000000);
+	hws[IMX8MM_SYS_PLL3] = imx_clk_hw_pll14xx("sys_pll3", "sys_pll3_ref_sel", base + 0x114, &imx_1416x_pll);
 
 	/* PLL bypass out */
-	clks[IMX8MM_AUDIO_PLL1_BYPASS] = imx_clk_mux_flags("audio_pll1_bypass", base, 16, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_AUDIO_PLL2_BYPASS] = imx_clk_mux_flags("audio_pll2_bypass", base + 0x14, 16, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_VIDEO_PLL1_BYPASS] = imx_clk_mux_flags("video_pll1_bypass", base + 0x28, 16, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_DRAM_PLL_BYPASS] = imx_clk_mux_flags("dram_pll_bypass", base + 0x50, 16, 1, dram_pll_bypass_sels, ARRAY_SIZE(dram_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_GPU_PLL_BYPASS] = imx_clk_mux_flags("gpu_pll_bypass", base + 0x64, 28, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_VPU_PLL_BYPASS] = imx_clk_mux_flags("vpu_pll_bypass", base + 0x74, 28, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_ARM_PLL_BYPASS] = imx_clk_mux_flags("arm_pll_bypass", base + 0x84, 28, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MM_SYS_PLL3_BYPASS] = imx_clk_mux_flags("sys_pll3_bypass", base + 0x114, 28, 1, sys_pll3_bypass_sels, ARRAY_SIZE(sys_pll3_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_AUDIO_PLL1_BYPASS] = imx_clk_hw_mux_flags("audio_pll1_bypass", base, 16, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_AUDIO_PLL2_BYPASS] = imx_clk_hw_mux_flags("audio_pll2_bypass", base + 0x14, 16, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_VIDEO_PLL1_BYPASS] = imx_clk_hw_mux_flags("video_pll1_bypass", base + 0x28, 16, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_DRAM_PLL_BYPASS] = imx_clk_hw_mux_flags("dram_pll_bypass", base + 0x50, 16, 1, dram_pll_bypass_sels, ARRAY_SIZE(dram_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_GPU_PLL_BYPASS] = imx_clk_hw_mux_flags("gpu_pll_bypass", base + 0x64, 28, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_VPU_PLL_BYPASS] = imx_clk_hw_mux_flags("vpu_pll_bypass", base + 0x74, 28, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_ARM_PLL_BYPASS] = imx_clk_hw_mux_flags("arm_pll_bypass", base + 0x84, 28, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MM_SYS_PLL3_BYPASS] = imx_clk_hw_mux_flags("sys_pll3_bypass", base + 0x114, 28, 1, sys_pll3_bypass_sels, ARRAY_SIZE(sys_pll3_bypass_sels), CLK_SET_RATE_PARENT);
 
 	/* PLL out gate */
-	clks[IMX8MM_AUDIO_PLL1_OUT] = imx_clk_gate("audio_pll1_out", "audio_pll1_bypass", base, 13);
-	clks[IMX8MM_AUDIO_PLL2_OUT] = imx_clk_gate("audio_pll2_out", "audio_pll2_bypass", base + 0x14, 13);
-	clks[IMX8MM_VIDEO_PLL1_OUT] = imx_clk_gate("video_pll1_out", "video_pll1_bypass", base + 0x28, 13);
-	clks[IMX8MM_DRAM_PLL_OUT] = imx_clk_gate("dram_pll_out", "dram_pll_bypass", base + 0x50, 13);
-	clks[IMX8MM_GPU_PLL_OUT] = imx_clk_gate("gpu_pll_out", "gpu_pll_bypass", base + 0x64, 11);
-	clks[IMX8MM_VPU_PLL_OUT] = imx_clk_gate("vpu_pll_out", "vpu_pll_bypass", base + 0x74, 11);
-	clks[IMX8MM_ARM_PLL_OUT] = imx_clk_gate("arm_pll_out", "arm_pll_bypass", base + 0x84, 11);
-	clks[IMX8MM_SYS_PLL3_OUT] = imx_clk_gate("sys_pll3_out", "sys_pll3_bypass", base + 0x114, 11);
+	hws[IMX8MM_AUDIO_PLL1_OUT] = imx_clk_hw_gate("audio_pll1_out", "audio_pll1_bypass", base, 13);
+	hws[IMX8MM_AUDIO_PLL2_OUT] = imx_clk_hw_gate("audio_pll2_out", "audio_pll2_bypass", base + 0x14, 13);
+	hws[IMX8MM_VIDEO_PLL1_OUT] = imx_clk_hw_gate("video_pll1_out", "video_pll1_bypass", base + 0x28, 13);
+	hws[IMX8MM_DRAM_PLL_OUT] = imx_clk_hw_gate("dram_pll_out", "dram_pll_bypass", base + 0x50, 13);
+	hws[IMX8MM_GPU_PLL_OUT] = imx_clk_hw_gate("gpu_pll_out", "gpu_pll_bypass", base + 0x64, 11);
+	hws[IMX8MM_VPU_PLL_OUT] = imx_clk_hw_gate("vpu_pll_out", "vpu_pll_bypass", base + 0x74, 11);
+	hws[IMX8MM_ARM_PLL_OUT] = imx_clk_hw_gate("arm_pll_out", "arm_pll_bypass", base + 0x84, 11);
+	hws[IMX8MM_SYS_PLL3_OUT] = imx_clk_hw_gate("sys_pll3_out", "sys_pll3_bypass", base + 0x114, 11);
 
 	/* SYS PLL1 fixed output */
-	clks[IMX8MM_SYS_PLL1_40M_CG] = imx_clk_gate("sys_pll1_40m_cg", "sys_pll1", base + 0x94, 27);
-	clks[IMX8MM_SYS_PLL1_80M_CG] = imx_clk_gate("sys_pll1_80m_cg", "sys_pll1", base + 0x94, 25);
-	clks[IMX8MM_SYS_PLL1_100M_CG] = imx_clk_gate("sys_pll1_100m_cg", "sys_pll1", base + 0x94, 23);
-	clks[IMX8MM_SYS_PLL1_133M_CG] = imx_clk_gate("sys_pll1_133m_cg", "sys_pll1", base + 0x94, 21);
-	clks[IMX8MM_SYS_PLL1_160M_CG] = imx_clk_gate("sys_pll1_160m_cg", "sys_pll1", base + 0x94, 19);
-	clks[IMX8MM_SYS_PLL1_200M_CG] = imx_clk_gate("sys_pll1_200m_cg", "sys_pll1", base + 0x94, 17);
-	clks[IMX8MM_SYS_PLL1_266M_CG] = imx_clk_gate("sys_pll1_266m_cg", "sys_pll1", base + 0x94, 15);
-	clks[IMX8MM_SYS_PLL1_400M_CG] = imx_clk_gate("sys_pll1_400m_cg", "sys_pll1", base + 0x94, 13);
-	clks[IMX8MM_SYS_PLL1_OUT] = imx_clk_gate("sys_pll1_out", "sys_pll1", base + 0x94, 11);
-
-	clks[IMX8MM_SYS_PLL1_40M] = imx_clk_fixed_factor("sys_pll1_40m", "sys_pll1_40m_cg", 1, 20);
-	clks[IMX8MM_SYS_PLL1_80M] = imx_clk_fixed_factor("sys_pll1_80m", "sys_pll1_80m_cg", 1, 10);
-	clks[IMX8MM_SYS_PLL1_100M] = imx_clk_fixed_factor("sys_pll1_100m", "sys_pll1_100m_cg", 1, 8);
-	clks[IMX8MM_SYS_PLL1_133M] = imx_clk_fixed_factor("sys_pll1_133m", "sys_pll1_133m_cg", 1, 6);
-	clks[IMX8MM_SYS_PLL1_160M] = imx_clk_fixed_factor("sys_pll1_160m", "sys_pll1_160m_cg", 1, 5);
-	clks[IMX8MM_SYS_PLL1_200M] = imx_clk_fixed_factor("sys_pll1_200m", "sys_pll1_200m_cg", 1, 4);
-	clks[IMX8MM_SYS_PLL1_266M] = imx_clk_fixed_factor("sys_pll1_266m", "sys_pll1_266m_cg", 1, 3);
-	clks[IMX8MM_SYS_PLL1_400M] = imx_clk_fixed_factor("sys_pll1_400m", "sys_pll1_400m_cg", 1, 2);
-	clks[IMX8MM_SYS_PLL1_800M] = imx_clk_fixed_factor("sys_pll1_800m", "sys_pll1_out", 1, 1);
+	hws[IMX8MM_SYS_PLL1_40M_CG] = imx_clk_hw_gate("sys_pll1_40m_cg", "sys_pll1", base + 0x94, 27);
+	hws[IMX8MM_SYS_PLL1_80M_CG] = imx_clk_hw_gate("sys_pll1_80m_cg", "sys_pll1", base + 0x94, 25);
+	hws[IMX8MM_SYS_PLL1_100M_CG] = imx_clk_hw_gate("sys_pll1_100m_cg", "sys_pll1", base + 0x94, 23);
+	hws[IMX8MM_SYS_PLL1_133M_CG] = imx_clk_hw_gate("sys_pll1_133m_cg", "sys_pll1", base + 0x94, 21);
+	hws[IMX8MM_SYS_PLL1_160M_CG] = imx_clk_hw_gate("sys_pll1_160m_cg", "sys_pll1", base + 0x94, 19);
+	hws[IMX8MM_SYS_PLL1_200M_CG] = imx_clk_hw_gate("sys_pll1_200m_cg", "sys_pll1", base + 0x94, 17);
+	hws[IMX8MM_SYS_PLL1_266M_CG] = imx_clk_hw_gate("sys_pll1_266m_cg", "sys_pll1", base + 0x94, 15);
+	hws[IMX8MM_SYS_PLL1_400M_CG] = imx_clk_hw_gate("sys_pll1_400m_cg", "sys_pll1", base + 0x94, 13);
+	hws[IMX8MM_SYS_PLL1_OUT] = imx_clk_hw_gate("sys_pll1_out", "sys_pll1", base + 0x94, 11);
+
+	hws[IMX8MM_SYS_PLL1_40M] = imx_clk_hw_fixed_factor("sys_pll1_40m", "sys_pll1_40m_cg", 1, 20);
+	hws[IMX8MM_SYS_PLL1_80M] = imx_clk_hw_fixed_factor("sys_pll1_80m", "sys_pll1_80m_cg", 1, 10);
+	hws[IMX8MM_SYS_PLL1_100M] = imx_clk_hw_fixed_factor("sys_pll1_100m", "sys_pll1_100m_cg", 1, 8);
+	hws[IMX8MM_SYS_PLL1_133M] = imx_clk_hw_fixed_factor("sys_pll1_133m", "sys_pll1_133m_cg", 1, 6);
+	hws[IMX8MM_SYS_PLL1_160M] = imx_clk_hw_fixed_factor("sys_pll1_160m", "sys_pll1_160m_cg", 1, 5);
+	hws[IMX8MM_SYS_PLL1_200M] = imx_clk_hw_fixed_factor("sys_pll1_200m", "sys_pll1_200m_cg", 1, 4);
+	hws[IMX8MM_SYS_PLL1_266M] = imx_clk_hw_fixed_factor("sys_pll1_266m", "sys_pll1_266m_cg", 1, 3);
+	hws[IMX8MM_SYS_PLL1_400M] = imx_clk_hw_fixed_factor("sys_pll1_400m", "sys_pll1_400m_cg", 1, 2);
+	hws[IMX8MM_SYS_PLL1_800M] = imx_clk_hw_fixed_factor("sys_pll1_800m", "sys_pll1_out", 1, 1);
 
 	/* SYS PLL2 fixed output */
-	clks[IMX8MM_SYS_PLL2_50M_CG] = imx_clk_gate("sys_pll2_50m_cg", "sys_pll2", base + 0x104, 27);
-	clks[IMX8MM_SYS_PLL2_100M_CG] = imx_clk_gate("sys_pll2_100m_cg", "sys_pll2", base + 0x104, 25);
-	clks[IMX8MM_SYS_PLL2_125M_CG] = imx_clk_gate("sys_pll2_125m_cg", "sys_pll2", base + 0x104, 23);
-	clks[IMX8MM_SYS_PLL2_166M_CG] = imx_clk_gate("sys_pll2_166m_cg", "sys_pll2", base + 0x104, 21);
-	clks[IMX8MM_SYS_PLL2_200M_CG] = imx_clk_gate("sys_pll2_200m_cg", "sys_pll2", base + 0x104, 19);
-	clks[IMX8MM_SYS_PLL2_250M_CG] = imx_clk_gate("sys_pll2_250m_cg", "sys_pll2", base + 0x104, 17);
-	clks[IMX8MM_SYS_PLL2_333M_CG] = imx_clk_gate("sys_pll2_333m_cg", "sys_pll2", base + 0x104, 15);
-	clks[IMX8MM_SYS_PLL2_500M_CG] = imx_clk_gate("sys_pll2_500m_cg", "sys_pll2", base + 0x104, 13);
-	clks[IMX8MM_SYS_PLL2_OUT] = imx_clk_gate("sys_pll2_out", "sys_pll2", base + 0x104, 11);
-
-	clks[IMX8MM_SYS_PLL2_50M] = imx_clk_fixed_factor("sys_pll2_50m", "sys_pll2_50m_cg", 1, 20);
-	clks[IMX8MM_SYS_PLL2_100M] = imx_clk_fixed_factor("sys_pll2_100m", "sys_pll2_100m_cg", 1, 10);
-	clks[IMX8MM_SYS_PLL2_125M] = imx_clk_fixed_factor("sys_pll2_125m", "sys_pll2_125m_cg", 1, 8);
-	clks[IMX8MM_SYS_PLL2_166M] = imx_clk_fixed_factor("sys_pll2_166m", "sys_pll2_166m_cg", 1, 6);
-	clks[IMX8MM_SYS_PLL2_200M] = imx_clk_fixed_factor("sys_pll2_200m", "sys_pll2_200m_cg", 1, 5);
-	clks[IMX8MM_SYS_PLL2_250M] = imx_clk_fixed_factor("sys_pll2_250m", "sys_pll2_250m_cg", 1, 4);
-	clks[IMX8MM_SYS_PLL2_333M] = imx_clk_fixed_factor("sys_pll2_333m", "sys_pll2_333m_cg", 1, 3);
-	clks[IMX8MM_SYS_PLL2_500M] = imx_clk_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2);
-	clks[IMX8MM_SYS_PLL2_1000M] = imx_clk_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1);
+	hws[IMX8MM_SYS_PLL2_50M_CG] = imx_clk_hw_gate("sys_pll2_50m_cg", "sys_pll2", base + 0x104, 27);
+	hws[IMX8MM_SYS_PLL2_100M_CG] = imx_clk_hw_gate("sys_pll2_100m_cg", "sys_pll2", base + 0x104, 25);
+	hws[IMX8MM_SYS_PLL2_125M_CG] = imx_clk_hw_gate("sys_pll2_125m_cg", "sys_pll2", base + 0x104, 23);
+	hws[IMX8MM_SYS_PLL2_166M_CG] = imx_clk_hw_gate("sys_pll2_166m_cg", "sys_pll2", base + 0x104, 21);
+	hws[IMX8MM_SYS_PLL2_200M_CG] = imx_clk_hw_gate("sys_pll2_200m_cg", "sys_pll2", base + 0x104, 19);
+	hws[IMX8MM_SYS_PLL2_250M_CG] = imx_clk_hw_gate("sys_pll2_250m_cg", "sys_pll2", base + 0x104, 17);
+	hws[IMX8MM_SYS_PLL2_333M_CG] = imx_clk_hw_gate("sys_pll2_333m_cg", "sys_pll2", base + 0x104, 15);
+	hws[IMX8MM_SYS_PLL2_500M_CG] = imx_clk_hw_gate("sys_pll2_500m_cg", "sys_pll2", base + 0x104, 13);
+	hws[IMX8MM_SYS_PLL2_OUT] = imx_clk_hw_gate("sys_pll2_out", "sys_pll2", base + 0x104, 11);
+
+	hws[IMX8MM_SYS_PLL2_50M] = imx_clk_hw_fixed_factor("sys_pll2_50m", "sys_pll2_50m_cg", 1, 20);
+	hws[IMX8MM_SYS_PLL2_100M] = imx_clk_hw_fixed_factor("sys_pll2_100m", "sys_pll2_100m_cg", 1, 10);
+	hws[IMX8MM_SYS_PLL2_125M] = imx_clk_hw_fixed_factor("sys_pll2_125m", "sys_pll2_125m_cg", 1, 8);
+	hws[IMX8MM_SYS_PLL2_166M] = imx_clk_hw_fixed_factor("sys_pll2_166m", "sys_pll2_166m_cg", 1, 6);
+	hws[IMX8MM_SYS_PLL2_200M] = imx_clk_hw_fixed_factor("sys_pll2_200m", "sys_pll2_200m_cg", 1, 5);
+	hws[IMX8MM_SYS_PLL2_250M] = imx_clk_hw_fixed_factor("sys_pll2_250m", "sys_pll2_250m_cg", 1, 4);
+	hws[IMX8MM_SYS_PLL2_333M] = imx_clk_hw_fixed_factor("sys_pll2_333m", "sys_pll2_333m_cg", 1, 3);
+	hws[IMX8MM_SYS_PLL2_500M] = imx_clk_hw_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2);
+	hws[IMX8MM_SYS_PLL2_1000M] = imx_clk_hw_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1);
 
 	np = dev->of_node;
 	base = devm_platform_ioremap_resource(pdev, 0);
@@ -404,204 +413,213 @@ static int imx8mm_clocks_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	/* Core Slice */
-	clks[IMX8MM_CLK_A53_SRC] = imx_clk_mux2("arm_a53_src", base + 0x8000, 24, 3, imx8mm_a53_sels, ARRAY_SIZE(imx8mm_a53_sels));
-	clks[IMX8MM_CLK_M4_SRC] = imx_clk_mux2("arm_m4_src", base + 0x8080, 24, 3, imx8mm_m4_sels, ARRAY_SIZE(imx8mm_m4_sels));
-	clks[IMX8MM_CLK_VPU_SRC] = imx_clk_mux2("vpu_src", base + 0x8100, 24, 3, imx8mm_vpu_sels, ARRAY_SIZE(imx8mm_vpu_sels));
-	clks[IMX8MM_CLK_GPU3D_SRC] = imx_clk_mux2("gpu3d_src", base + 0x8180, 24, 3,  imx8mm_gpu3d_sels, ARRAY_SIZE(imx8mm_gpu3d_sels));
-	clks[IMX8MM_CLK_GPU2D_SRC] = imx_clk_mux2("gpu2d_src", base + 0x8200, 24, 3, imx8mm_gpu2d_sels,  ARRAY_SIZE(imx8mm_gpu2d_sels));
-	clks[IMX8MM_CLK_A53_CG] = imx_clk_gate3("arm_a53_cg", "arm_a53_src", base + 0x8000, 28);
-	clks[IMX8MM_CLK_M4_CG] = imx_clk_gate3("arm_m4_cg", "arm_m4_src", base + 0x8080, 28);
-	clks[IMX8MM_CLK_VPU_CG] = imx_clk_gate3("vpu_cg", "vpu_src", base + 0x8100, 28);
-	clks[IMX8MM_CLK_GPU3D_CG] = imx_clk_gate3("gpu3d_cg", "gpu3d_src", base + 0x8180, 28);
-	clks[IMX8MM_CLK_GPU2D_CG] = imx_clk_gate3("gpu2d_cg", "gpu2d_src", base + 0x8200, 28);
-	clks[IMX8MM_CLK_A53_DIV] = imx_clk_divider2("arm_a53_div", "arm_a53_cg", base + 0x8000, 0, 3);
-	clks[IMX8MM_CLK_M4_DIV] = imx_clk_divider2("arm_m4_div", "arm_m4_cg", base + 0x8080, 0, 3);
-	clks[IMX8MM_CLK_VPU_DIV] = imx_clk_divider2("vpu_div", "vpu_cg", base + 0x8100, 0, 3);
-	clks[IMX8MM_CLK_GPU3D_DIV] = imx_clk_divider2("gpu3d_div", "gpu3d_cg", base + 0x8180, 0, 3);
-	clks[IMX8MM_CLK_GPU2D_DIV] = imx_clk_divider2("gpu2d_div", "gpu2d_cg", base + 0x8200, 0, 3);
+	hws[IMX8MM_CLK_A53_SRC] = imx_clk_hw_mux2("arm_a53_src", base + 0x8000, 24, 3, imx8mm_a53_sels, ARRAY_SIZE(imx8mm_a53_sels));
+	hws[IMX8MM_CLK_M4_SRC] = imx_clk_hw_mux2("arm_m4_src", base + 0x8080, 24, 3, imx8mm_m4_sels, ARRAY_SIZE(imx8mm_m4_sels));
+	hws[IMX8MM_CLK_VPU_SRC] = imx_clk_hw_mux2("vpu_src", base + 0x8100, 24, 3, imx8mm_vpu_sels, ARRAY_SIZE(imx8mm_vpu_sels));
+	hws[IMX8MM_CLK_GPU3D_SRC] = imx_clk_hw_mux2("gpu3d_src", base + 0x8180, 24, 3,  imx8mm_gpu3d_sels, ARRAY_SIZE(imx8mm_gpu3d_sels));
+	hws[IMX8MM_CLK_GPU2D_SRC] = imx_clk_hw_mux2("gpu2d_src", base + 0x8200, 24, 3, imx8mm_gpu2d_sels,  ARRAY_SIZE(imx8mm_gpu2d_sels));
+	hws[IMX8MM_CLK_A53_CG] = imx_clk_hw_gate3("arm_a53_cg", "arm_a53_src", base + 0x8000, 28);
+	hws[IMX8MM_CLK_M4_CG] = imx_clk_hw_gate3("arm_m4_cg", "arm_m4_src", base + 0x8080, 28);
+	hws[IMX8MM_CLK_VPU_CG] = imx_clk_hw_gate3("vpu_cg", "vpu_src", base + 0x8100, 28);
+	hws[IMX8MM_CLK_GPU3D_CG] = imx_clk_hw_gate3("gpu3d_cg", "gpu3d_src", base + 0x8180, 28);
+	hws[IMX8MM_CLK_GPU2D_CG] = imx_clk_hw_gate3("gpu2d_cg", "gpu2d_src", base + 0x8200, 28);
+	hws[IMX8MM_CLK_A53_DIV] = imx_clk_hw_divider2("arm_a53_div", "arm_a53_cg", base + 0x8000, 0, 3);
+	hws[IMX8MM_CLK_M4_DIV] = imx_clk_hw_divider2("arm_m4_div", "arm_m4_cg", base + 0x8080, 0, 3);
+	hws[IMX8MM_CLK_VPU_DIV] = imx_clk_hw_divider2("vpu_div", "vpu_cg", base + 0x8100, 0, 3);
+	hws[IMX8MM_CLK_GPU3D_DIV] = imx_clk_hw_divider2("gpu3d_div", "gpu3d_cg", base + 0x8180, 0, 3);
+	hws[IMX8MM_CLK_GPU2D_DIV] = imx_clk_hw_divider2("gpu2d_div", "gpu2d_cg", base + 0x8200, 0, 3);
 
 	/* BUS */
-	clks[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_composite_critical("main_axi",  imx8mm_main_axi_sels, base + 0x8800);
-	clks[IMX8MM_CLK_ENET_AXI] = imx8m_clk_composite("enet_axi", imx8mm_enet_axi_sels, base + 0x8880);
-	clks[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
-	clks[IMX8MM_CLK_VPU_BUS] = imx8m_clk_composite("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980);
-	clks[IMX8MM_CLK_DISP_AXI] = imx8m_clk_composite("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00);
-	clks[IMX8MM_CLK_DISP_APB] = imx8m_clk_composite("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80);
-	clks[IMX8MM_CLK_DISP_RTRM] = imx8m_clk_composite("disp_rtrm", imx8mm_disp_rtrm_sels, base + 0x8b00);
-	clks[IMX8MM_CLK_USB_BUS] = imx8m_clk_composite("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80);
-	clks[IMX8MM_CLK_GPU_AXI] = imx8m_clk_composite("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00);
-	clks[IMX8MM_CLK_GPU_AHB] = imx8m_clk_composite("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80);
-	clks[IMX8MM_CLK_NOC] = imx8m_clk_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00);
-	clks[IMX8MM_CLK_NOC_APB] = imx8m_clk_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
+	hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi",  imx8mm_main_axi_sels, base + 0x8800);
+	hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite("enet_axi", imx8mm_enet_axi_sels, base + 0x8880);
+	hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900);
+	hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980);
+	hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00);
+	hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80);
+	hws[IMX8MM_CLK_DISP_RTRM] = imx8m_clk_hw_composite("disp_rtrm", imx8mm_disp_rtrm_sels, base + 0x8b00);
+	hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80);
+	hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00);
+	hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80);
+	hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00);
+	hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80);
 
 	/* AHB */
-	clks[IMX8MM_CLK_AHB] = imx8m_clk_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
-	clks[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_composite("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100);
+	hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000);
+	hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100);
 
 	/* IPG */
-	clks[IMX8MM_CLK_IPG_ROOT] = imx_clk_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
-	clks[IMX8MM_CLK_IPG_AUDIO_ROOT] = imx_clk_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
+	hws[IMX8MM_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
+	hws[IMX8MM_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
+
+	/*
+	 * DRAM clocks are manipulated from TF-A outside clock framework.
+	 * Mark with GET_RATE_NOCACHE to always read div value from hardware
+	 */
+	hws[IMX8MM_CLK_DRAM_ALT] = __imx8m_clk_hw_composite("dram_alt", imx8mm_dram_alt_sels, base + 0xa000, CLK_GET_RATE_NOCACHE);
+	hws[IMX8MM_CLK_DRAM_APB] = __imx8m_clk_hw_composite("dram_apb", imx8mm_dram_apb_sels, base + 0xa080, CLK_IS_CRITICAL | CLK_GET_RATE_NOCACHE);
 
 	/* IP */
-	clks[IMX8MM_CLK_DRAM_ALT] = imx8m_clk_composite("dram_alt", imx8mm_dram_alt_sels, base + 0xa000);
-	clks[IMX8MM_CLK_DRAM_APB] = imx8m_clk_composite_critical("dram_apb", imx8mm_dram_apb_sels, base + 0xa080);
-	clks[IMX8MM_CLK_VPU_G1] = imx8m_clk_composite("vpu_g1", imx8mm_vpu_g1_sels, base + 0xa100);
-	clks[IMX8MM_CLK_VPU_G2] = imx8m_clk_composite("vpu_g2", imx8mm_vpu_g2_sels, base + 0xa180);
-	clks[IMX8MM_CLK_DISP_DTRC] = imx8m_clk_composite("disp_dtrc", imx8mm_disp_dtrc_sels, base + 0xa200);
-	clks[IMX8MM_CLK_DISP_DC8000] = imx8m_clk_composite("disp_dc8000", imx8mm_disp_dc8000_sels, base + 0xa280);
-	clks[IMX8MM_CLK_PCIE1_CTRL] = imx8m_clk_composite("pcie1_ctrl", imx8mm_pcie1_ctrl_sels, base + 0xa300);
-	clks[IMX8MM_CLK_PCIE1_PHY] = imx8m_clk_composite("pcie1_phy", imx8mm_pcie1_phy_sels, base + 0xa380);
-	clks[IMX8MM_CLK_PCIE1_AUX] = imx8m_clk_composite("pcie1_aux", imx8mm_pcie1_aux_sels, base + 0xa400);
-	clks[IMX8MM_CLK_DC_PIXEL] = imx8m_clk_composite("dc_pixel", imx8mm_dc_pixel_sels, base + 0xa480);
-	clks[IMX8MM_CLK_LCDIF_PIXEL] = imx8m_clk_composite("lcdif_pixel", imx8mm_lcdif_pixel_sels, base + 0xa500);
-	clks[IMX8MM_CLK_SAI1] = imx8m_clk_composite("sai1", imx8mm_sai1_sels, base + 0xa580);
-	clks[IMX8MM_CLK_SAI2] = imx8m_clk_composite("sai2", imx8mm_sai2_sels, base + 0xa600);
-	clks[IMX8MM_CLK_SAI3] = imx8m_clk_composite("sai3", imx8mm_sai3_sels, base + 0xa680);
-	clks[IMX8MM_CLK_SAI4] = imx8m_clk_composite("sai4", imx8mm_sai4_sels, base + 0xa700);
-	clks[IMX8MM_CLK_SAI5] = imx8m_clk_composite("sai5", imx8mm_sai5_sels, base + 0xa780);
-	clks[IMX8MM_CLK_SAI6] = imx8m_clk_composite("sai6", imx8mm_sai6_sels, base + 0xa800);
-	clks[IMX8MM_CLK_SPDIF1] = imx8m_clk_composite("spdif1", imx8mm_spdif1_sels, base + 0xa880);
-	clks[IMX8MM_CLK_SPDIF2] = imx8m_clk_composite("spdif2", imx8mm_spdif2_sels, base + 0xa900);
-	clks[IMX8MM_CLK_ENET_REF] = imx8m_clk_composite("enet_ref", imx8mm_enet_ref_sels, base + 0xa980);
-	clks[IMX8MM_CLK_ENET_TIMER] = imx8m_clk_composite("enet_timer", imx8mm_enet_timer_sels, base + 0xaa00);
-	clks[IMX8MM_CLK_ENET_PHY_REF] = imx8m_clk_composite("enet_phy", imx8mm_enet_phy_sels, base + 0xaa80);
-	clks[IMX8MM_CLK_NAND] = imx8m_clk_composite("nand", imx8mm_nand_sels, base + 0xab00);
-	clks[IMX8MM_CLK_QSPI] = imx8m_clk_composite("qspi", imx8mm_qspi_sels, base + 0xab80);
-	clks[IMX8MM_CLK_USDHC1] = imx8m_clk_composite("usdhc1", imx8mm_usdhc1_sels, base + 0xac00);
-	clks[IMX8MM_CLK_USDHC2] = imx8m_clk_composite("usdhc2", imx8mm_usdhc2_sels, base + 0xac80);
-	clks[IMX8MM_CLK_I2C1] = imx8m_clk_composite("i2c1", imx8mm_i2c1_sels, base + 0xad00);
-	clks[IMX8MM_CLK_I2C2] = imx8m_clk_composite("i2c2", imx8mm_i2c2_sels, base + 0xad80);
-	clks[IMX8MM_CLK_I2C3] = imx8m_clk_composite("i2c3", imx8mm_i2c3_sels, base + 0xae00);
-	clks[IMX8MM_CLK_I2C4] = imx8m_clk_composite("i2c4", imx8mm_i2c4_sels, base + 0xae80);
-	clks[IMX8MM_CLK_UART1] = imx8m_clk_composite("uart1", imx8mm_uart1_sels, base + 0xaf00);
-	clks[IMX8MM_CLK_UART2] = imx8m_clk_composite("uart2", imx8mm_uart2_sels, base + 0xaf80);
-	clks[IMX8MM_CLK_UART3] = imx8m_clk_composite("uart3", imx8mm_uart3_sels, base + 0xb000);
-	clks[IMX8MM_CLK_UART4] = imx8m_clk_composite("uart4", imx8mm_uart4_sels, base + 0xb080);
-	clks[IMX8MM_CLK_USB_CORE_REF] = imx8m_clk_composite("usb_core_ref", imx8mm_usb_core_sels, base + 0xb100);
-	clks[IMX8MM_CLK_USB_PHY_REF] = imx8m_clk_composite("usb_phy_ref", imx8mm_usb_phy_sels, base + 0xb180);
-	clks[IMX8MM_CLK_GIC] = imx8m_clk_composite_critical("gic", imx8mm_gic_sels, base + 0xb200);
-	clks[IMX8MM_CLK_ECSPI1] = imx8m_clk_composite("ecspi1", imx8mm_ecspi1_sels, base + 0xb280);
-	clks[IMX8MM_CLK_ECSPI2] = imx8m_clk_composite("ecspi2", imx8mm_ecspi2_sels, base + 0xb300);
-	clks[IMX8MM_CLK_PWM1] = imx8m_clk_composite("pwm1", imx8mm_pwm1_sels, base + 0xb380);
-	clks[IMX8MM_CLK_PWM2] = imx8m_clk_composite("pwm2", imx8mm_pwm2_sels, base + 0xb400);
-	clks[IMX8MM_CLK_PWM3] = imx8m_clk_composite("pwm3", imx8mm_pwm3_sels, base + 0xb480);
-	clks[IMX8MM_CLK_PWM4] = imx8m_clk_composite("pwm4", imx8mm_pwm4_sels, base + 0xb500);
-	clks[IMX8MM_CLK_GPT1] = imx8m_clk_composite("gpt1", imx8mm_gpt1_sels, base + 0xb580);
-	clks[IMX8MM_CLK_WDOG] = imx8m_clk_composite("wdog", imx8mm_wdog_sels, base + 0xb900);
-	clks[IMX8MM_CLK_WRCLK] = imx8m_clk_composite("wrclk", imx8mm_wrclk_sels, base + 0xb980);
-	clks[IMX8MM_CLK_CLKO1] = imx8m_clk_composite("clko1", imx8mm_clko1_sels, base + 0xba00);
-	clks[IMX8MM_CLK_DSI_CORE] = imx8m_clk_composite("dsi_core", imx8mm_dsi_core_sels, base + 0xbb00);
-	clks[IMX8MM_CLK_DSI_PHY_REF] = imx8m_clk_composite("dsi_phy_ref", imx8mm_dsi_phy_sels, base + 0xbb80);
-	clks[IMX8MM_CLK_DSI_DBI] = imx8m_clk_composite("dsi_dbi", imx8mm_dsi_dbi_sels, base + 0xbc00);
-	clks[IMX8MM_CLK_USDHC3] = imx8m_clk_composite("usdhc3", imx8mm_usdhc3_sels, base + 0xbc80);
-	clks[IMX8MM_CLK_CSI1_CORE] = imx8m_clk_composite("csi1_core", imx8mm_csi1_core_sels, base + 0xbd00);
-	clks[IMX8MM_CLK_CSI1_PHY_REF] = imx8m_clk_composite("csi1_phy_ref", imx8mm_csi1_phy_sels, base + 0xbd80);
-	clks[IMX8MM_CLK_CSI1_ESC] = imx8m_clk_composite("csi1_esc", imx8mm_csi1_esc_sels, base + 0xbe00);
-	clks[IMX8MM_CLK_CSI2_CORE] = imx8m_clk_composite("csi2_core", imx8mm_csi2_core_sels, base + 0xbe80);
-	clks[IMX8MM_CLK_CSI2_PHY_REF] = imx8m_clk_composite("csi2_phy_ref", imx8mm_csi2_phy_sels, base + 0xbf00);
-	clks[IMX8MM_CLK_CSI2_ESC] = imx8m_clk_composite("csi2_esc", imx8mm_csi2_esc_sels, base + 0xbf80);
-	clks[IMX8MM_CLK_PCIE2_CTRL] = imx8m_clk_composite("pcie2_ctrl", imx8mm_pcie2_ctrl_sels, base + 0xc000);
-	clks[IMX8MM_CLK_PCIE2_PHY] = imx8m_clk_composite("pcie2_phy", imx8mm_pcie2_phy_sels, base + 0xc080);
-	clks[IMX8MM_CLK_PCIE2_AUX] = imx8m_clk_composite("pcie2_aux", imx8mm_pcie2_aux_sels, base + 0xc100);
-	clks[IMX8MM_CLK_ECSPI3] = imx8m_clk_composite("ecspi3", imx8mm_ecspi3_sels, base + 0xc180);
-	clks[IMX8MM_CLK_PDM] = imx8m_clk_composite("pdm", imx8mm_pdm_sels, base + 0xc200);
-	clks[IMX8MM_CLK_VPU_H1] = imx8m_clk_composite("vpu_h1", imx8mm_vpu_h1_sels, base + 0xc280);
+	hws[IMX8MM_CLK_VPU_G1] = imx8m_clk_hw_composite("vpu_g1", imx8mm_vpu_g1_sels, base + 0xa100);
+	hws[IMX8MM_CLK_VPU_G2] = imx8m_clk_hw_composite("vpu_g2", imx8mm_vpu_g2_sels, base + 0xa180);
+	hws[IMX8MM_CLK_DISP_DTRC] = imx8m_clk_hw_composite("disp_dtrc", imx8mm_disp_dtrc_sels, base + 0xa200);
+	hws[IMX8MM_CLK_DISP_DC8000] = imx8m_clk_hw_composite("disp_dc8000", imx8mm_disp_dc8000_sels, base + 0xa280);
+	hws[IMX8MM_CLK_PCIE1_CTRL] = imx8m_clk_hw_composite("pcie1_ctrl", imx8mm_pcie1_ctrl_sels, base + 0xa300);
+	hws[IMX8MM_CLK_PCIE1_PHY] = imx8m_clk_hw_composite("pcie1_phy", imx8mm_pcie1_phy_sels, base + 0xa380);
+	hws[IMX8MM_CLK_PCIE1_AUX] = imx8m_clk_hw_composite("pcie1_aux", imx8mm_pcie1_aux_sels, base + 0xa400);
+	hws[IMX8MM_CLK_DC_PIXEL] = imx8m_clk_hw_composite("dc_pixel", imx8mm_dc_pixel_sels, base + 0xa480);
+	hws[IMX8MM_CLK_LCDIF_PIXEL] = imx8m_clk_hw_composite("lcdif_pixel", imx8mm_lcdif_pixel_sels, base + 0xa500);
+	hws[IMX8MM_CLK_SAI1] = imx8m_clk_hw_composite("sai1", imx8mm_sai1_sels, base + 0xa580);
+	hws[IMX8MM_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mm_sai2_sels, base + 0xa600);
+	hws[IMX8MM_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mm_sai3_sels, base + 0xa680);
+	hws[IMX8MM_CLK_SAI4] = imx8m_clk_hw_composite("sai4", imx8mm_sai4_sels, base + 0xa700);
+	hws[IMX8MM_CLK_SAI5] = imx8m_clk_hw_composite("sai5", imx8mm_sai5_sels, base + 0xa780);
+	hws[IMX8MM_CLK_SAI6] = imx8m_clk_hw_composite("sai6", imx8mm_sai6_sels, base + 0xa800);
+	hws[IMX8MM_CLK_SPDIF1] = imx8m_clk_hw_composite("spdif1", imx8mm_spdif1_sels, base + 0xa880);
+	hws[IMX8MM_CLK_SPDIF2] = imx8m_clk_hw_composite("spdif2", imx8mm_spdif2_sels, base + 0xa900);
+	hws[IMX8MM_CLK_ENET_REF] = imx8m_clk_hw_composite("enet_ref", imx8mm_enet_ref_sels, base + 0xa980);
+	hws[IMX8MM_CLK_ENET_TIMER] = imx8m_clk_hw_composite("enet_timer", imx8mm_enet_timer_sels, base + 0xaa00);
+	hws[IMX8MM_CLK_ENET_PHY_REF] = imx8m_clk_hw_composite("enet_phy", imx8mm_enet_phy_sels, base + 0xaa80);
+	hws[IMX8MM_CLK_NAND] = imx8m_clk_hw_composite("nand", imx8mm_nand_sels, base + 0xab00);
+	hws[IMX8MM_CLK_QSPI] = imx8m_clk_hw_composite("qspi", imx8mm_qspi_sels, base + 0xab80);
+	hws[IMX8MM_CLK_USDHC1] = imx8m_clk_hw_composite("usdhc1", imx8mm_usdhc1_sels, base + 0xac00);
+	hws[IMX8MM_CLK_USDHC2] = imx8m_clk_hw_composite("usdhc2", imx8mm_usdhc2_sels, base + 0xac80);
+	hws[IMX8MM_CLK_I2C1] = imx8m_clk_hw_composite("i2c1", imx8mm_i2c1_sels, base + 0xad00);
+	hws[IMX8MM_CLK_I2C2] = imx8m_clk_hw_composite("i2c2", imx8mm_i2c2_sels, base + 0xad80);
+	hws[IMX8MM_CLK_I2C3] = imx8m_clk_hw_composite("i2c3", imx8mm_i2c3_sels, base + 0xae00);
+	hws[IMX8MM_CLK_I2C4] = imx8m_clk_hw_composite("i2c4", imx8mm_i2c4_sels, base + 0xae80);
+	hws[IMX8MM_CLK_UART1] = imx8m_clk_hw_composite("uart1", imx8mm_uart1_sels, base + 0xaf00);
+	hws[IMX8MM_CLK_UART2] = imx8m_clk_hw_composite("uart2", imx8mm_uart2_sels, base + 0xaf80);
+	hws[IMX8MM_CLK_UART3] = imx8m_clk_hw_composite("uart3", imx8mm_uart3_sels, base + 0xb000);
+	hws[IMX8MM_CLK_UART4] = imx8m_clk_hw_composite("uart4", imx8mm_uart4_sels, base + 0xb080);
+	hws[IMX8MM_CLK_USB_CORE_REF] = imx8m_clk_hw_composite("usb_core_ref", imx8mm_usb_core_sels, base + 0xb100);
+	hws[IMX8MM_CLK_USB_PHY_REF] = imx8m_clk_hw_composite("usb_phy_ref", imx8mm_usb_phy_sels, base + 0xb180);
+	hws[IMX8MM_CLK_GIC] = imx8m_clk_hw_composite_critical("gic", imx8mm_gic_sels, base + 0xb200);
+	hws[IMX8MM_CLK_ECSPI1] = imx8m_clk_hw_composite("ecspi1", imx8mm_ecspi1_sels, base + 0xb280);
+	hws[IMX8MM_CLK_ECSPI2] = imx8m_clk_hw_composite("ecspi2", imx8mm_ecspi2_sels, base + 0xb300);
+	hws[IMX8MM_CLK_PWM1] = imx8m_clk_hw_composite("pwm1", imx8mm_pwm1_sels, base + 0xb380);
+	hws[IMX8MM_CLK_PWM2] = imx8m_clk_hw_composite("pwm2", imx8mm_pwm2_sels, base + 0xb400);
+	hws[IMX8MM_CLK_PWM3] = imx8m_clk_hw_composite("pwm3", imx8mm_pwm3_sels, base + 0xb480);
+	hws[IMX8MM_CLK_PWM4] = imx8m_clk_hw_composite("pwm4", imx8mm_pwm4_sels, base + 0xb500);
+	hws[IMX8MM_CLK_GPT1] = imx8m_clk_hw_composite("gpt1", imx8mm_gpt1_sels, base + 0xb580);
+	hws[IMX8MM_CLK_WDOG] = imx8m_clk_hw_composite("wdog", imx8mm_wdog_sels, base + 0xb900);
+	hws[IMX8MM_CLK_WRCLK] = imx8m_clk_hw_composite("wrclk", imx8mm_wrclk_sels, base + 0xb980);
+	hws[IMX8MM_CLK_CLKO1] = imx8m_clk_hw_composite("clko1", imx8mm_clko1_sels, base + 0xba00);
+	hws[IMX8MM_CLK_DSI_CORE] = imx8m_clk_hw_composite("dsi_core", imx8mm_dsi_core_sels, base + 0xbb00);
+	hws[IMX8MM_CLK_DSI_PHY_REF] = imx8m_clk_hw_composite("dsi_phy_ref", imx8mm_dsi_phy_sels, base + 0xbb80);
+	hws[IMX8MM_CLK_DSI_DBI] = imx8m_clk_hw_composite("dsi_dbi", imx8mm_dsi_dbi_sels, base + 0xbc00);
+	hws[IMX8MM_CLK_USDHC3] = imx8m_clk_hw_composite("usdhc3", imx8mm_usdhc3_sels, base + 0xbc80);
+	hws[IMX8MM_CLK_CSI1_CORE] = imx8m_clk_hw_composite("csi1_core", imx8mm_csi1_core_sels, base + 0xbd00);
+	hws[IMX8MM_CLK_CSI1_PHY_REF] = imx8m_clk_hw_composite("csi1_phy_ref", imx8mm_csi1_phy_sels, base + 0xbd80);
+	hws[IMX8MM_CLK_CSI1_ESC] = imx8m_clk_hw_composite("csi1_esc", imx8mm_csi1_esc_sels, base + 0xbe00);
+	hws[IMX8MM_CLK_CSI2_CORE] = imx8m_clk_hw_composite("csi2_core", imx8mm_csi2_core_sels, base + 0xbe80);
+	hws[IMX8MM_CLK_CSI2_PHY_REF] = imx8m_clk_hw_composite("csi2_phy_ref", imx8mm_csi2_phy_sels, base + 0xbf00);
+	hws[IMX8MM_CLK_CSI2_ESC] = imx8m_clk_hw_composite("csi2_esc", imx8mm_csi2_esc_sels, base + 0xbf80);
+	hws[IMX8MM_CLK_PCIE2_CTRL] = imx8m_clk_hw_composite("pcie2_ctrl", imx8mm_pcie2_ctrl_sels, base + 0xc000);
+	hws[IMX8MM_CLK_PCIE2_PHY] = imx8m_clk_hw_composite("pcie2_phy", imx8mm_pcie2_phy_sels, base + 0xc080);
+	hws[IMX8MM_CLK_PCIE2_AUX] = imx8m_clk_hw_composite("pcie2_aux", imx8mm_pcie2_aux_sels, base + 0xc100);
+	hws[IMX8MM_CLK_ECSPI3] = imx8m_clk_hw_composite("ecspi3", imx8mm_ecspi3_sels, base + 0xc180);
+	hws[IMX8MM_CLK_PDM] = imx8m_clk_hw_composite("pdm", imx8mm_pdm_sels, base + 0xc200);
+	hws[IMX8MM_CLK_VPU_H1] = imx8m_clk_hw_composite("vpu_h1", imx8mm_vpu_h1_sels, base + 0xc280);
 
 	/* CCGR */
-	clks[IMX8MM_CLK_ECSPI1_ROOT] = imx_clk_gate4("ecspi1_root_clk", "ecspi1", base + 0x4070, 0);
-	clks[IMX8MM_CLK_ECSPI2_ROOT] = imx_clk_gate4("ecspi2_root_clk", "ecspi2", base + 0x4080, 0);
-	clks[IMX8MM_CLK_ECSPI3_ROOT] = imx_clk_gate4("ecspi3_root_clk", "ecspi3", base + 0x4090, 0);
-	clks[IMX8MM_CLK_ENET1_ROOT] = imx_clk_gate4("enet1_root_clk", "enet_axi", base + 0x40a0, 0);
-	clks[IMX8MM_CLK_GPIO1_ROOT] = imx_clk_gate4("gpio1_root_clk", "ipg_root", base + 0x40b0, 0);
-	clks[IMX8MM_CLK_GPIO2_ROOT] = imx_clk_gate4("gpio2_root_clk", "ipg_root", base + 0x40c0, 0);
-	clks[IMX8MM_CLK_GPIO3_ROOT] = imx_clk_gate4("gpio3_root_clk", "ipg_root", base + 0x40d0, 0);
-	clks[IMX8MM_CLK_GPIO4_ROOT] = imx_clk_gate4("gpio4_root_clk", "ipg_root", base + 0x40e0, 0);
-	clks[IMX8MM_CLK_GPIO5_ROOT] = imx_clk_gate4("gpio5_root_clk", "ipg_root", base + 0x40f0, 0);
-	clks[IMX8MM_CLK_GPT1_ROOT] = imx_clk_gate4("gpt1_root_clk", "gpt1", base + 0x4100, 0);
-	clks[IMX8MM_CLK_I2C1_ROOT] = imx_clk_gate4("i2c1_root_clk", "i2c1", base + 0x4170, 0);
-	clks[IMX8MM_CLK_I2C2_ROOT] = imx_clk_gate4("i2c2_root_clk", "i2c2", base + 0x4180, 0);
-	clks[IMX8MM_CLK_I2C3_ROOT] = imx_clk_gate4("i2c3_root_clk", "i2c3", base + 0x4190, 0);
-	clks[IMX8MM_CLK_I2C4_ROOT] = imx_clk_gate4("i2c4_root_clk", "i2c4", base + 0x41a0, 0);
-	clks[IMX8MM_CLK_MU_ROOT] = imx_clk_gate4("mu_root_clk", "ipg_root", base + 0x4210, 0);
-	clks[IMX8MM_CLK_OCOTP_ROOT] = imx_clk_gate4("ocotp_root_clk", "ipg_root", base + 0x4220, 0);
-	clks[IMX8MM_CLK_PCIE1_ROOT] = imx_clk_gate4("pcie1_root_clk", "pcie1_ctrl", base + 0x4250, 0);
-	clks[IMX8MM_CLK_PWM1_ROOT] = imx_clk_gate4("pwm1_root_clk", "pwm1", base + 0x4280, 0);
-	clks[IMX8MM_CLK_PWM2_ROOT] = imx_clk_gate4("pwm2_root_clk", "pwm2", base + 0x4290, 0);
-	clks[IMX8MM_CLK_PWM3_ROOT] = imx_clk_gate4("pwm3_root_clk", "pwm3", base + 0x42a0, 0);
-	clks[IMX8MM_CLK_PWM4_ROOT] = imx_clk_gate4("pwm4_root_clk", "pwm4", base + 0x42b0, 0);
-	clks[IMX8MM_CLK_QSPI_ROOT] = imx_clk_gate4("qspi_root_clk", "qspi", base + 0x42f0, 0);
-	clks[IMX8MM_CLK_NAND_ROOT] = imx_clk_gate2_shared2("nand_root_clk", "nand", base + 0x4300, 0, &share_count_nand);
-	clks[IMX8MM_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", base + 0x4300, 0, &share_count_nand);
-	clks[IMX8MM_CLK_SAI1_ROOT] = imx_clk_gate2_shared2("sai1_root_clk", "sai1", base + 0x4330, 0, &share_count_sai1);
-	clks[IMX8MM_CLK_SAI1_IPG] = imx_clk_gate2_shared2("sai1_ipg_clk", "ipg_audio_root", base + 0x4330, 0, &share_count_sai1);
-	clks[IMX8MM_CLK_SAI2_ROOT] = imx_clk_gate2_shared2("sai2_root_clk", "sai2", base + 0x4340, 0, &share_count_sai2);
-	clks[IMX8MM_CLK_SAI2_IPG] = imx_clk_gate2_shared2("sai2_ipg_clk", "ipg_audio_root", base + 0x4340, 0, &share_count_sai2);
-	clks[IMX8MM_CLK_SAI3_ROOT] = imx_clk_gate2_shared2("sai3_root_clk", "sai3", base + 0x4350, 0, &share_count_sai3);
-	clks[IMX8MM_CLK_SAI3_IPG] = imx_clk_gate2_shared2("sai3_ipg_clk", "ipg_audio_root", base + 0x4350, 0, &share_count_sai3);
-	clks[IMX8MM_CLK_SAI4_ROOT] = imx_clk_gate2_shared2("sai4_root_clk", "sai4", base + 0x4360, 0, &share_count_sai4);
-	clks[IMX8MM_CLK_SAI4_IPG] = imx_clk_gate2_shared2("sai4_ipg_clk", "ipg_audio_root", base + 0x4360, 0, &share_count_sai4);
-	clks[IMX8MM_CLK_SAI5_ROOT] = imx_clk_gate2_shared2("sai5_root_clk", "sai5", base + 0x4370, 0, &share_count_sai5);
-	clks[IMX8MM_CLK_SAI5_IPG] = imx_clk_gate2_shared2("sai5_ipg_clk", "ipg_audio_root", base + 0x4370, 0, &share_count_sai5);
-	clks[IMX8MM_CLK_SAI6_ROOT] = imx_clk_gate2_shared2("sai6_root_clk", "sai6", base + 0x4380, 0, &share_count_sai6);
-	clks[IMX8MM_CLK_SAI6_IPG] = imx_clk_gate2_shared2("sai6_ipg_clk", "ipg_audio_root", base + 0x4380, 0, &share_count_sai6);
-	clks[IMX8MM_CLK_SNVS_ROOT] = imx_clk_gate4("snvs_root_clk", "ipg_root", base + 0x4470, 0);
-	clks[IMX8MM_CLK_UART1_ROOT] = imx_clk_gate4("uart1_root_clk", "uart1", base + 0x4490, 0);
-	clks[IMX8MM_CLK_UART2_ROOT] = imx_clk_gate4("uart2_root_clk", "uart2", base + 0x44a0, 0);
-	clks[IMX8MM_CLK_UART3_ROOT] = imx_clk_gate4("uart3_root_clk", "uart3", base + 0x44b0, 0);
-	clks[IMX8MM_CLK_UART4_ROOT] = imx_clk_gate4("uart4_root_clk", "uart4", base + 0x44c0, 0);
-	clks[IMX8MM_CLK_USB1_CTRL_ROOT] = imx_clk_gate4("usb1_ctrl_root_clk", "usb_bus", base + 0x44d0, 0);
-	clks[IMX8MM_CLK_GPU3D_ROOT] = imx_clk_gate4("gpu3d_root_clk", "gpu3d_div", base + 0x44f0, 0);
-	clks[IMX8MM_CLK_USDHC1_ROOT] = imx_clk_gate4("usdhc1_root_clk", "usdhc1", base + 0x4510, 0);
-	clks[IMX8MM_CLK_USDHC2_ROOT] = imx_clk_gate4("usdhc2_root_clk", "usdhc2", base + 0x4520, 0);
-	clks[IMX8MM_CLK_WDOG1_ROOT] = imx_clk_gate4("wdog1_root_clk", "wdog", base + 0x4530, 0);
-	clks[IMX8MM_CLK_WDOG2_ROOT] = imx_clk_gate4("wdog2_root_clk", "wdog", base + 0x4540, 0);
-	clks[IMX8MM_CLK_WDOG3_ROOT] = imx_clk_gate4("wdog3_root_clk", "wdog", base + 0x4550, 0);
-	clks[IMX8MM_CLK_VPU_G1_ROOT] = imx_clk_gate4("vpu_g1_root_clk", "vpu_g1", base + 0x4560, 0);
-	clks[IMX8MM_CLK_GPU_BUS_ROOT] = imx_clk_gate4("gpu_root_clk", "gpu_axi", base + 0x4570, 0);
-	clks[IMX8MM_CLK_VPU_H1_ROOT] = imx_clk_gate4("vpu_h1_root_clk", "vpu_h1", base + 0x4590, 0);
-	clks[IMX8MM_CLK_VPU_G2_ROOT] = imx_clk_gate4("vpu_g2_root_clk", "vpu_g2", base + 0x45a0, 0);
-	clks[IMX8MM_CLK_PDM_ROOT] = imx_clk_gate2_shared2("pdm_root_clk", "pdm", base + 0x45b0, 0, &share_count_pdm);
-	clks[IMX8MM_CLK_PDM_IPG]  = imx_clk_gate2_shared2("pdm_ipg_clk", "ipg_audio_root", base + 0x45b0, 0, &share_count_pdm);
-	clks[IMX8MM_CLK_DISP_ROOT] = imx_clk_gate2_shared2("disp_root_clk", "disp_dc8000", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MM_CLK_DISP_AXI_ROOT]  = imx_clk_gate2_shared2("disp_axi_root_clk", "disp_axi", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MM_CLK_DISP_APB_ROOT]  = imx_clk_gate2_shared2("disp_apb_root_clk", "disp_apb", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MM_CLK_DISP_RTRM_ROOT] = imx_clk_gate2_shared2("disp_rtrm_root_clk", "disp_rtrm", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MM_CLK_USDHC3_ROOT] = imx_clk_gate4("usdhc3_root_clk", "usdhc3", base + 0x45e0, 0);
-	clks[IMX8MM_CLK_TMU_ROOT] = imx_clk_gate4("tmu_root_clk", "ipg_root", base + 0x4620, 0);
-	clks[IMX8MM_CLK_VPU_DEC_ROOT] = imx_clk_gate4("vpu_dec_root_clk", "vpu_bus", base + 0x4630, 0);
-	clks[IMX8MM_CLK_SDMA1_ROOT] = imx_clk_gate4("sdma1_clk", "ipg_root", base + 0x43a0, 0);
-	clks[IMX8MM_CLK_SDMA2_ROOT] = imx_clk_gate4("sdma2_clk", "ipg_audio_root", base + 0x43b0, 0);
-	clks[IMX8MM_CLK_SDMA3_ROOT] = imx_clk_gate4("sdma3_clk", "ipg_audio_root", base + 0x45f0, 0);
-	clks[IMX8MM_CLK_GPU2D_ROOT] = imx_clk_gate4("gpu2d_root_clk", "gpu2d_div", base + 0x4660, 0);
-	clks[IMX8MM_CLK_CSI1_ROOT] = imx_clk_gate4("csi1_root_clk", "csi1_core", base + 0x4650, 0);
-
-	clks[IMX8MM_CLK_GPT_3M] = imx_clk_fixed_factor("gpt_3m", "osc_24m", 1, 8);
-
-	clks[IMX8MM_CLK_DRAM_ALT_ROOT] = imx_clk_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
-	clks[IMX8MM_CLK_DRAM_CORE] = imx_clk_mux2_flags("dram_core_clk", base + 0x9800, 24, 1, imx8mm_dram_core_sels, ARRAY_SIZE(imx8mm_dram_core_sels), CLK_IS_CRITICAL);
-
-	clks[IMX8MM_CLK_ARM] = imx_clk_cpu("arm", "arm_a53_div",
-					   clks[IMX8MM_CLK_A53_DIV],
-					   clks[IMX8MM_CLK_A53_SRC],
-					   clks[IMX8MM_ARM_PLL_OUT],
-					   clks[IMX8MM_SYS_PLL1_800M]);
-
-	imx_check_clocks(clks, ARRAY_SIZE(clks));
-
-	clk_data.clks = clks;
-	clk_data.clk_num = ARRAY_SIZE(clks);
-	ret = of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+	hws[IMX8MM_CLK_ECSPI1_ROOT] = imx_clk_hw_gate4("ecspi1_root_clk", "ecspi1", base + 0x4070, 0);
+	hws[IMX8MM_CLK_ECSPI2_ROOT] = imx_clk_hw_gate4("ecspi2_root_clk", "ecspi2", base + 0x4080, 0);
+	hws[IMX8MM_CLK_ECSPI3_ROOT] = imx_clk_hw_gate4("ecspi3_root_clk", "ecspi3", base + 0x4090, 0);
+	hws[IMX8MM_CLK_ENET1_ROOT] = imx_clk_hw_gate4("enet1_root_clk", "enet_axi", base + 0x40a0, 0);
+	hws[IMX8MM_CLK_GPIO1_ROOT] = imx_clk_hw_gate4("gpio1_root_clk", "ipg_root", base + 0x40b0, 0);
+	hws[IMX8MM_CLK_GPIO2_ROOT] = imx_clk_hw_gate4("gpio2_root_clk", "ipg_root", base + 0x40c0, 0);
+	hws[IMX8MM_CLK_GPIO3_ROOT] = imx_clk_hw_gate4("gpio3_root_clk", "ipg_root", base + 0x40d0, 0);
+	hws[IMX8MM_CLK_GPIO4_ROOT] = imx_clk_hw_gate4("gpio4_root_clk", "ipg_root", base + 0x40e0, 0);
+	hws[IMX8MM_CLK_GPIO5_ROOT] = imx_clk_hw_gate4("gpio5_root_clk", "ipg_root", base + 0x40f0, 0);
+	hws[IMX8MM_CLK_GPT1_ROOT] = imx_clk_hw_gate4("gpt1_root_clk", "gpt1", base + 0x4100, 0);
+	hws[IMX8MM_CLK_I2C1_ROOT] = imx_clk_hw_gate4("i2c1_root_clk", "i2c1", base + 0x4170, 0);
+	hws[IMX8MM_CLK_I2C2_ROOT] = imx_clk_hw_gate4("i2c2_root_clk", "i2c2", base + 0x4180, 0);
+	hws[IMX8MM_CLK_I2C3_ROOT] = imx_clk_hw_gate4("i2c3_root_clk", "i2c3", base + 0x4190, 0);
+	hws[IMX8MM_CLK_I2C4_ROOT] = imx_clk_hw_gate4("i2c4_root_clk", "i2c4", base + 0x41a0, 0);
+	hws[IMX8MM_CLK_MU_ROOT] = imx_clk_hw_gate4("mu_root_clk", "ipg_root", base + 0x4210, 0);
+	hws[IMX8MM_CLK_OCOTP_ROOT] = imx_clk_hw_gate4("ocotp_root_clk", "ipg_root", base + 0x4220, 0);
+	hws[IMX8MM_CLK_PCIE1_ROOT] = imx_clk_hw_gate4("pcie1_root_clk", "pcie1_ctrl", base + 0x4250, 0);
+	hws[IMX8MM_CLK_PWM1_ROOT] = imx_clk_hw_gate4("pwm1_root_clk", "pwm1", base + 0x4280, 0);
+	hws[IMX8MM_CLK_PWM2_ROOT] = imx_clk_hw_gate4("pwm2_root_clk", "pwm2", base + 0x4290, 0);
+	hws[IMX8MM_CLK_PWM3_ROOT] = imx_clk_hw_gate4("pwm3_root_clk", "pwm3", base + 0x42a0, 0);
+	hws[IMX8MM_CLK_PWM4_ROOT] = imx_clk_hw_gate4("pwm4_root_clk", "pwm4", base + 0x42b0, 0);
+	hws[IMX8MM_CLK_QSPI_ROOT] = imx_clk_hw_gate4("qspi_root_clk", "qspi", base + 0x42f0, 0);
+	hws[IMX8MM_CLK_NAND_ROOT] = imx_clk_hw_gate2_shared2("nand_root_clk", "nand", base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MM_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_hw_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MM_CLK_SAI1_ROOT] = imx_clk_hw_gate2_shared2("sai1_root_clk", "sai1", base + 0x4330, 0, &share_count_sai1);
+	hws[IMX8MM_CLK_SAI1_IPG] = imx_clk_hw_gate2_shared2("sai1_ipg_clk", "ipg_audio_root", base + 0x4330, 0, &share_count_sai1);
+	hws[IMX8MM_CLK_SAI2_ROOT] = imx_clk_hw_gate2_shared2("sai2_root_clk", "sai2", base + 0x4340, 0, &share_count_sai2);
+	hws[IMX8MM_CLK_SAI2_IPG] = imx_clk_hw_gate2_shared2("sai2_ipg_clk", "ipg_audio_root", base + 0x4340, 0, &share_count_sai2);
+	hws[IMX8MM_CLK_SAI3_ROOT] = imx_clk_hw_gate2_shared2("sai3_root_clk", "sai3", base + 0x4350, 0, &share_count_sai3);
+	hws[IMX8MM_CLK_SAI3_IPG] = imx_clk_hw_gate2_shared2("sai3_ipg_clk", "ipg_audio_root", base + 0x4350, 0, &share_count_sai3);
+	hws[IMX8MM_CLK_SAI4_ROOT] = imx_clk_hw_gate2_shared2("sai4_root_clk", "sai4", base + 0x4360, 0, &share_count_sai4);
+	hws[IMX8MM_CLK_SAI4_IPG] = imx_clk_hw_gate2_shared2("sai4_ipg_clk", "ipg_audio_root", base + 0x4360, 0, &share_count_sai4);
+	hws[IMX8MM_CLK_SAI5_ROOT] = imx_clk_hw_gate2_shared2("sai5_root_clk", "sai5", base + 0x4370, 0, &share_count_sai5);
+	hws[IMX8MM_CLK_SAI5_IPG] = imx_clk_hw_gate2_shared2("sai5_ipg_clk", "ipg_audio_root", base + 0x4370, 0, &share_count_sai5);
+	hws[IMX8MM_CLK_SAI6_ROOT] = imx_clk_hw_gate2_shared2("sai6_root_clk", "sai6", base + 0x4380, 0, &share_count_sai6);
+	hws[IMX8MM_CLK_SAI6_IPG] = imx_clk_hw_gate2_shared2("sai6_ipg_clk", "ipg_audio_root", base + 0x4380, 0, &share_count_sai6);
+	hws[IMX8MM_CLK_SNVS_ROOT] = imx_clk_hw_gate4("snvs_root_clk", "ipg_root", base + 0x4470, 0);
+	hws[IMX8MM_CLK_UART1_ROOT] = imx_clk_hw_gate4("uart1_root_clk", "uart1", base + 0x4490, 0);
+	hws[IMX8MM_CLK_UART2_ROOT] = imx_clk_hw_gate4("uart2_root_clk", "uart2", base + 0x44a0, 0);
+	hws[IMX8MM_CLK_UART3_ROOT] = imx_clk_hw_gate4("uart3_root_clk", "uart3", base + 0x44b0, 0);
+	hws[IMX8MM_CLK_UART4_ROOT] = imx_clk_hw_gate4("uart4_root_clk", "uart4", base + 0x44c0, 0);
+	hws[IMX8MM_CLK_USB1_CTRL_ROOT] = imx_clk_hw_gate4("usb1_ctrl_root_clk", "usb_bus", base + 0x44d0, 0);
+	hws[IMX8MM_CLK_GPU3D_ROOT] = imx_clk_hw_gate4("gpu3d_root_clk", "gpu3d_div", base + 0x44f0, 0);
+	hws[IMX8MM_CLK_USDHC1_ROOT] = imx_clk_hw_gate4("usdhc1_root_clk", "usdhc1", base + 0x4510, 0);
+	hws[IMX8MM_CLK_USDHC2_ROOT] = imx_clk_hw_gate4("usdhc2_root_clk", "usdhc2", base + 0x4520, 0);
+	hws[IMX8MM_CLK_WDOG1_ROOT] = imx_clk_hw_gate4("wdog1_root_clk", "wdog", base + 0x4530, 0);
+	hws[IMX8MM_CLK_WDOG2_ROOT] = imx_clk_hw_gate4("wdog2_root_clk", "wdog", base + 0x4540, 0);
+	hws[IMX8MM_CLK_WDOG3_ROOT] = imx_clk_hw_gate4("wdog3_root_clk", "wdog", base + 0x4550, 0);
+	hws[IMX8MM_CLK_VPU_G1_ROOT] = imx_clk_hw_gate4("vpu_g1_root_clk", "vpu_g1", base + 0x4560, 0);
+	hws[IMX8MM_CLK_GPU_BUS_ROOT] = imx_clk_hw_gate4("gpu_root_clk", "gpu_axi", base + 0x4570, 0);
+	hws[IMX8MM_CLK_VPU_H1_ROOT] = imx_clk_hw_gate4("vpu_h1_root_clk", "vpu_h1", base + 0x4590, 0);
+	hws[IMX8MM_CLK_VPU_G2_ROOT] = imx_clk_hw_gate4("vpu_g2_root_clk", "vpu_g2", base + 0x45a0, 0);
+	hws[IMX8MM_CLK_PDM_ROOT] = imx_clk_hw_gate2_shared2("pdm_root_clk", "pdm", base + 0x45b0, 0, &share_count_pdm);
+	hws[IMX8MM_CLK_PDM_IPG]  = imx_clk_hw_gate2_shared2("pdm_ipg_clk", "ipg_audio_root", base + 0x45b0, 0, &share_count_pdm);
+	hws[IMX8MM_CLK_DISP_ROOT] = imx_clk_hw_gate2_shared2("disp_root_clk", "disp_dc8000", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MM_CLK_DISP_AXI_ROOT]  = imx_clk_hw_gate2_shared2("disp_axi_root_clk", "disp_axi", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MM_CLK_DISP_APB_ROOT]  = imx_clk_hw_gate2_shared2("disp_apb_root_clk", "disp_apb", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MM_CLK_DISP_RTRM_ROOT] = imx_clk_hw_gate2_shared2("disp_rtrm_root_clk", "disp_rtrm", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MM_CLK_USDHC3_ROOT] = imx_clk_hw_gate4("usdhc3_root_clk", "usdhc3", base + 0x45e0, 0);
+	hws[IMX8MM_CLK_TMU_ROOT] = imx_clk_hw_gate4("tmu_root_clk", "ipg_root", base + 0x4620, 0);
+	hws[IMX8MM_CLK_VPU_DEC_ROOT] = imx_clk_hw_gate4("vpu_dec_root_clk", "vpu_bus", base + 0x4630, 0);
+	hws[IMX8MM_CLK_SDMA1_ROOT] = imx_clk_hw_gate4("sdma1_clk", "ipg_root", base + 0x43a0, 0);
+	hws[IMX8MM_CLK_SDMA2_ROOT] = imx_clk_hw_gate4("sdma2_clk", "ipg_audio_root", base + 0x43b0, 0);
+	hws[IMX8MM_CLK_SDMA3_ROOT] = imx_clk_hw_gate4("sdma3_clk", "ipg_audio_root", base + 0x45f0, 0);
+	hws[IMX8MM_CLK_GPU2D_ROOT] = imx_clk_hw_gate4("gpu2d_root_clk", "gpu2d_div", base + 0x4660, 0);
+	hws[IMX8MM_CLK_CSI1_ROOT] = imx_clk_hw_gate4("csi1_root_clk", "csi1_core", base + 0x4650, 0);
+
+	hws[IMX8MM_CLK_GPT_3M] = imx_clk_hw_fixed_factor("gpt_3m", "osc_24m", 1, 8);
+
+	hws[IMX8MM_CLK_DRAM_ALT_ROOT] = imx_clk_hw_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
+	hws[IMX8MM_CLK_DRAM_CORE] = imx_clk_hw_mux2_flags("dram_core_clk", base + 0x9800, 24, 1, imx8mm_dram_core_sels, ARRAY_SIZE(imx8mm_dram_core_sels), CLK_IS_CRITICAL);
+
+	hws[IMX8MM_CLK_ARM] = imx_clk_hw_cpu("arm", "arm_a53_div",
+					   hws[IMX8MM_CLK_A53_DIV]->clk,
+					   hws[IMX8MM_CLK_A53_SRC]->clk,
+					   hws[IMX8MM_ARM_PLL_OUT]->clk,
+					   hws[IMX8MM_SYS_PLL1_800M]->clk);
+
+	imx_check_clk_hws(hws, IMX8MM_CLK_END);
+
+	ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data);
 	if (ret < 0) {
-		pr_err("failed to register clks for i.MX8MM\n");
-		goto unregister_clks;
+		dev_err(dev, "failed to register clks for i.MX8MM\n");
+		goto unregister_hws;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(uart_clk_ids); i++) {
+		int index = uart_clk_ids[i];
+
+		uart_hws[i] = &hws[index]->clk;
 	}
 
-	imx_register_uart_clocks(uart_clks);
+	imx_register_uart_clocks(uart_hws);
 
 	return 0;
 
-unregister_clks:
-	imx_unregister_clocks(clks, ARRAY_SIZE(clks));
+unregister_hws:
+	imx_unregister_hw_clocks(hws, IMX8MM_CLK_END);
 
 	return ret;
 }
@@ -616,6 +634,11 @@ static struct platform_driver imx8mm_clk_driver = {
 	.probe = imx8mm_clocks_probe,
 	.driver = {
 		.name = "imx8mm-ccm",
+		/*
+		 * Disable bind attributes: clocks are not removed and
+		 * reloading the driver will crash or break devices.
+		 */
+		.suppress_bind_attrs = true,
 		.of_match_table = of_match_ptr(imx8mm_clk_of_match),
 	},
 };
diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c
index 9f5a5a56b45e..c5e7316b4c66 100644
--- a/drivers/clk/imx/clk-imx8mn.c
+++ b/drivers/clk/imx/clk-imx8mn.c
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 #include "clk.h"
@@ -280,284 +281,302 @@ static const char * const imx8mn_clko2_sels[] = {"osc_24m", "sys_pll2_200m", "sy
 						 "sys_pll2_166m", "sys_pll3_out", "audio_pll1_out",
 						 "video_pll1_out", "osc_32k", };
 
-static struct clk *clks[IMX8MN_CLK_END];
-static struct clk_onecell_data clk_data;
+static struct clk_hw_onecell_data *clk_hw_data;
+static struct clk_hw **hws;
 
-static struct clk ** const uart_clks[] = {
-	&clks[IMX8MN_CLK_UART1_ROOT],
-	&clks[IMX8MN_CLK_UART2_ROOT],
-	&clks[IMX8MN_CLK_UART3_ROOT],
-	&clks[IMX8MN_CLK_UART4_ROOT],
-	NULL
+static const int uart_clk_ids[] = {
+	IMX8MN_CLK_UART1_ROOT,
+	IMX8MN_CLK_UART2_ROOT,
+	IMX8MN_CLK_UART3_ROOT,
+	IMX8MN_CLK_UART4_ROOT,
 };
+static struct clk **uart_hws[ARRAY_SIZE(uart_clk_ids) + 1];
 
 static int imx8mn_clocks_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	void __iomem *base;
-	int ret;
+	int ret, i;
 
-	clks[IMX8MN_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
-	clks[IMX8MN_CLK_24M] = of_clk_get_by_name(np, "osc_24m");
-	clks[IMX8MN_CLK_32K] = of_clk_get_by_name(np, "osc_32k");
-	clks[IMX8MN_CLK_EXT1] = of_clk_get_by_name(np, "clk_ext1");
-	clks[IMX8MN_CLK_EXT2] = of_clk_get_by_name(np, "clk_ext2");
-	clks[IMX8MN_CLK_EXT3] = of_clk_get_by_name(np, "clk_ext3");
-	clks[IMX8MN_CLK_EXT4] = of_clk_get_by_name(np, "clk_ext4");
+	clk_hw_data = kzalloc(struct_size(clk_hw_data, hws,
+					  IMX8MN_CLK_END), GFP_KERNEL);
+	if (WARN_ON(!clk_hw_data))
+		return -ENOMEM;
+
+	clk_hw_data->num = IMX8MN_CLK_END;
+	hws = clk_hw_data->hws;
+
+	hws[IMX8MN_CLK_DUMMY] = imx_clk_hw_fixed("dummy", 0);
+	hws[IMX8MN_CLK_24M] = imx_obtain_fixed_clk_hw(np, "osc_24m");
+	hws[IMX8MN_CLK_32K] = imx_obtain_fixed_clk_hw(np, "osc_32k");
+	hws[IMX8MN_CLK_EXT1] = imx_obtain_fixed_clk_hw(np, "clk_ext1");
+	hws[IMX8MN_CLK_EXT2] = imx_obtain_fixed_clk_hw(np, "clk_ext2");
+	hws[IMX8MN_CLK_EXT3] = imx_obtain_fixed_clk_hw(np, "clk_ext3");
+	hws[IMX8MN_CLK_EXT4] = imx_obtain_fixed_clk_hw(np, "clk_ext4");
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mn-anatop");
 	base = of_iomap(np, 0);
 	if (WARN_ON(!base)) {
 		ret = -ENOMEM;
-		goto unregister_clks;
+		goto unregister_hws;
 	}
 
-	clks[IMX8MN_AUDIO_PLL1_REF_SEL] = imx_clk_mux("audio_pll1_ref_sel", base + 0x0, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_AUDIO_PLL2_REF_SEL] = imx_clk_mux("audio_pll2_ref_sel", base + 0x14, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_VIDEO_PLL1_REF_SEL] = imx_clk_mux("video_pll1_ref_sel", base + 0x28, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_DRAM_PLL_REF_SEL] = imx_clk_mux("dram_pll_ref_sel", base + 0x50, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_GPU_PLL_REF_SEL] = imx_clk_mux("gpu_pll_ref_sel", base + 0x64, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_VPU_PLL_REF_SEL] = imx_clk_mux("vpu_pll_ref_sel", base + 0x74, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_ARM_PLL_REF_SEL] = imx_clk_mux("arm_pll_ref_sel", base + 0x84, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MN_SYS_PLL3_REF_SEL] = imx_clk_mux("sys_pll3_ref_sel", base + 0x114, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-
-	clks[IMX8MN_AUDIO_PLL1] = imx_clk_pll14xx("audio_pll1", "audio_pll1_ref_sel", base, &imx_1443x_pll);
-	clks[IMX8MN_AUDIO_PLL2] = imx_clk_pll14xx("audio_pll2", "audio_pll2_ref_sel", base + 0x14, &imx_1443x_pll);
-	clks[IMX8MN_VIDEO_PLL1] = imx_clk_pll14xx("video_pll1", "video_pll1_ref_sel", base + 0x28, &imx_1443x_pll);
-	clks[IMX8MN_DRAM_PLL] = imx_clk_pll14xx("dram_pll", "dram_pll_ref_sel", base + 0x50, &imx_1443x_pll);
-	clks[IMX8MN_GPU_PLL] = imx_clk_pll14xx("gpu_pll", "gpu_pll_ref_sel", base + 0x64, &imx_1416x_pll);
-	clks[IMX8MN_VPU_PLL] = imx_clk_pll14xx("vpu_pll", "vpu_pll_ref_sel", base + 0x74, &imx_1416x_pll);
-	clks[IMX8MN_ARM_PLL] = imx_clk_pll14xx("arm_pll", "arm_pll_ref_sel", base + 0x84, &imx_1416x_pll);
-	clks[IMX8MN_SYS_PLL1] = imx_clk_fixed("sys_pll1", 800000000);
-	clks[IMX8MN_SYS_PLL2] = imx_clk_fixed("sys_pll2", 1000000000);
-	clks[IMX8MN_SYS_PLL3] = imx_clk_pll14xx("sys_pll3", "sys_pll3_ref_sel", base + 0x114, &imx_1416x_pll);
+	hws[IMX8MN_AUDIO_PLL1_REF_SEL] = imx_clk_hw_mux("audio_pll1_ref_sel", base + 0x0, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_AUDIO_PLL2_REF_SEL] = imx_clk_hw_mux("audio_pll2_ref_sel", base + 0x14, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_VIDEO_PLL1_REF_SEL] = imx_clk_hw_mux("video_pll1_ref_sel", base + 0x28, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_DRAM_PLL_REF_SEL] = imx_clk_hw_mux("dram_pll_ref_sel", base + 0x50, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_GPU_PLL_REF_SEL] = imx_clk_hw_mux("gpu_pll_ref_sel", base + 0x64, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_VPU_PLL_REF_SEL] = imx_clk_hw_mux("vpu_pll_ref_sel", base + 0x74, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_ARM_PLL_REF_SEL] = imx_clk_hw_mux("arm_pll_ref_sel", base + 0x84, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MN_SYS_PLL3_REF_SEL] = imx_clk_hw_mux("sys_pll3_ref_sel", base + 0x114, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+
+	hws[IMX8MN_AUDIO_PLL1] = imx_clk_hw_pll14xx("audio_pll1", "audio_pll1_ref_sel", base, &imx_1443x_pll);
+	hws[IMX8MN_AUDIO_PLL2] = imx_clk_hw_pll14xx("audio_pll2", "audio_pll2_ref_sel", base + 0x14, &imx_1443x_pll);
+	hws[IMX8MN_VIDEO_PLL1] = imx_clk_hw_pll14xx("video_pll1", "video_pll1_ref_sel", base + 0x28, &imx_1443x_pll);
+	hws[IMX8MN_DRAM_PLL] = imx_clk_hw_pll14xx("dram_pll", "dram_pll_ref_sel", base + 0x50, &imx_1443x_dram_pll);
+	hws[IMX8MN_GPU_PLL] = imx_clk_hw_pll14xx("gpu_pll", "gpu_pll_ref_sel", base + 0x64, &imx_1416x_pll);
+	hws[IMX8MN_VPU_PLL] = imx_clk_hw_pll14xx("vpu_pll", "vpu_pll_ref_sel", base + 0x74, &imx_1416x_pll);
+	hws[IMX8MN_ARM_PLL] = imx_clk_hw_pll14xx("arm_pll", "arm_pll_ref_sel", base + 0x84, &imx_1416x_pll);
+	hws[IMX8MN_SYS_PLL1] = imx_clk_hw_fixed("sys_pll1", 800000000);
+	hws[IMX8MN_SYS_PLL2] = imx_clk_hw_fixed("sys_pll2", 1000000000);
+	hws[IMX8MN_SYS_PLL3] = imx_clk_hw_pll14xx("sys_pll3", "sys_pll3_ref_sel", base + 0x114, &imx_1416x_pll);
 
 	/* PLL bypass out */
-	clks[IMX8MN_AUDIO_PLL1_BYPASS] = imx_clk_mux_flags("audio_pll1_bypass", base, 16, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_AUDIO_PLL2_BYPASS] = imx_clk_mux_flags("audio_pll2_bypass", base + 0x14, 16, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_VIDEO_PLL1_BYPASS] = imx_clk_mux_flags("video_pll1_bypass", base + 0x28, 16, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_DRAM_PLL_BYPASS] = imx_clk_mux_flags("dram_pll_bypass", base + 0x50, 16, 1, dram_pll_bypass_sels, ARRAY_SIZE(dram_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_GPU_PLL_BYPASS] = imx_clk_mux_flags("gpu_pll_bypass", base + 0x64, 28, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_VPU_PLL_BYPASS] = imx_clk_mux_flags("vpu_pll_bypass", base + 0x74, 28, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_ARM_PLL_BYPASS] = imx_clk_mux_flags("arm_pll_bypass", base + 0x84, 28, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MN_SYS_PLL3_BYPASS] = imx_clk_mux_flags("sys_pll3_bypass", base + 0x114, 28, 1, sys_pll3_bypass_sels, ARRAY_SIZE(sys_pll3_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_AUDIO_PLL1_BYPASS] = imx_clk_hw_mux_flags("audio_pll1_bypass", base, 16, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_AUDIO_PLL2_BYPASS] = imx_clk_hw_mux_flags("audio_pll2_bypass", base + 0x14, 16, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_VIDEO_PLL1_BYPASS] = imx_clk_hw_mux_flags("video_pll1_bypass", base + 0x28, 16, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_DRAM_PLL_BYPASS] = imx_clk_hw_mux_flags("dram_pll_bypass", base + 0x50, 16, 1, dram_pll_bypass_sels, ARRAY_SIZE(dram_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_GPU_PLL_BYPASS] = imx_clk_hw_mux_flags("gpu_pll_bypass", base + 0x64, 28, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_VPU_PLL_BYPASS] = imx_clk_hw_mux_flags("vpu_pll_bypass", base + 0x74, 28, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_ARM_PLL_BYPASS] = imx_clk_hw_mux_flags("arm_pll_bypass", base + 0x84, 28, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MN_SYS_PLL3_BYPASS] = imx_clk_hw_mux_flags("sys_pll3_bypass", base + 0x114, 28, 1, sys_pll3_bypass_sels, ARRAY_SIZE(sys_pll3_bypass_sels), CLK_SET_RATE_PARENT);
 
 	/* PLL out gate */
-	clks[IMX8MN_AUDIO_PLL1_OUT] = imx_clk_gate("audio_pll1_out", "audio_pll1_bypass", base, 13);
-	clks[IMX8MN_AUDIO_PLL2_OUT] = imx_clk_gate("audio_pll2_out", "audio_pll2_bypass", base + 0x14, 13);
-	clks[IMX8MN_VIDEO_PLL1_OUT] = imx_clk_gate("video_pll1_out", "video_pll1_bypass", base + 0x28, 13);
-	clks[IMX8MN_DRAM_PLL_OUT] = imx_clk_gate("dram_pll_out", "dram_pll_bypass", base + 0x50, 13);
-	clks[IMX8MN_GPU_PLL_OUT] = imx_clk_gate("gpu_pll_out", "gpu_pll_bypass", base + 0x64, 11);
-	clks[IMX8MN_VPU_PLL_OUT] = imx_clk_gate("vpu_pll_out", "vpu_pll_bypass", base + 0x74, 11);
-	clks[IMX8MN_ARM_PLL_OUT] = imx_clk_gate("arm_pll_out", "arm_pll_bypass", base + 0x84, 11);
-	clks[IMX8MN_SYS_PLL3_OUT] = imx_clk_gate("sys_pll3_out", "sys_pll3_bypass", base + 0x114, 11);
+	hws[IMX8MN_AUDIO_PLL1_OUT] = imx_clk_hw_gate("audio_pll1_out", "audio_pll1_bypass", base, 13);
+	hws[IMX8MN_AUDIO_PLL2_OUT] = imx_clk_hw_gate("audio_pll2_out", "audio_pll2_bypass", base + 0x14, 13);
+	hws[IMX8MN_VIDEO_PLL1_OUT] = imx_clk_hw_gate("video_pll1_out", "video_pll1_bypass", base + 0x28, 13);
+	hws[IMX8MN_DRAM_PLL_OUT] = imx_clk_hw_gate("dram_pll_out", "dram_pll_bypass", base + 0x50, 13);
+	hws[IMX8MN_GPU_PLL_OUT] = imx_clk_hw_gate("gpu_pll_out", "gpu_pll_bypass", base + 0x64, 11);
+	hws[IMX8MN_VPU_PLL_OUT] = imx_clk_hw_gate("vpu_pll_out", "vpu_pll_bypass", base + 0x74, 11);
+	hws[IMX8MN_ARM_PLL_OUT] = imx_clk_hw_gate("arm_pll_out", "arm_pll_bypass", base + 0x84, 11);
+	hws[IMX8MN_SYS_PLL3_OUT] = imx_clk_hw_gate("sys_pll3_out", "sys_pll3_bypass", base + 0x114, 11);
 
 	/* SYS PLL1 fixed output */
-	clks[IMX8MN_SYS_PLL1_40M_CG] = imx_clk_gate("sys_pll1_40m_cg", "sys_pll1", base + 0x94, 27);
-	clks[IMX8MN_SYS_PLL1_80M_CG] = imx_clk_gate("sys_pll1_80m_cg", "sys_pll1", base + 0x94, 25);
-	clks[IMX8MN_SYS_PLL1_100M_CG] = imx_clk_gate("sys_pll1_100m_cg", "sys_pll1", base + 0x94, 23);
-	clks[IMX8MN_SYS_PLL1_133M_CG] = imx_clk_gate("sys_pll1_133m_cg", "sys_pll1", base + 0x94, 21);
-	clks[IMX8MN_SYS_PLL1_160M_CG] = imx_clk_gate("sys_pll1_160m_cg", "sys_pll1", base + 0x94, 19);
-	clks[IMX8MN_SYS_PLL1_200M_CG] = imx_clk_gate("sys_pll1_200m_cg", "sys_pll1", base + 0x94, 17);
-	clks[IMX8MN_SYS_PLL1_266M_CG] = imx_clk_gate("sys_pll1_266m_cg", "sys_pll1", base + 0x94, 15);
-	clks[IMX8MN_SYS_PLL1_400M_CG] = imx_clk_gate("sys_pll1_400m_cg", "sys_pll1", base + 0x94, 13);
-	clks[IMX8MN_SYS_PLL1_OUT] = imx_clk_gate("sys_pll1_out", "sys_pll1", base + 0x94, 11);
-
-	clks[IMX8MN_SYS_PLL1_40M] = imx_clk_fixed_factor("sys_pll1_40m", "sys_pll1_40m_cg", 1, 20);
-	clks[IMX8MN_SYS_PLL1_80M] = imx_clk_fixed_factor("sys_pll1_80m", "sys_pll1_80m_cg", 1, 10);
-	clks[IMX8MN_SYS_PLL1_100M] = imx_clk_fixed_factor("sys_pll1_100m", "sys_pll1_100m_cg", 1, 8);
-	clks[IMX8MN_SYS_PLL1_133M] = imx_clk_fixed_factor("sys_pll1_133m", "sys_pll1_133m_cg", 1, 6);
-	clks[IMX8MN_SYS_PLL1_160M] = imx_clk_fixed_factor("sys_pll1_160m", "sys_pll1_160m_cg", 1, 5);
-	clks[IMX8MN_SYS_PLL1_200M] = imx_clk_fixed_factor("sys_pll1_200m", "sys_pll1_200m_cg", 1, 4);
-	clks[IMX8MN_SYS_PLL1_266M] = imx_clk_fixed_factor("sys_pll1_266m", "sys_pll1_266m_cg", 1, 3);
-	clks[IMX8MN_SYS_PLL1_400M] = imx_clk_fixed_factor("sys_pll1_400m", "sys_pll1_400m_cg", 1, 2);
-	clks[IMX8MN_SYS_PLL1_800M] = imx_clk_fixed_factor("sys_pll1_800m", "sys_pll1_out", 1, 1);
+	hws[IMX8MN_SYS_PLL1_40M_CG] = imx_clk_hw_gate("sys_pll1_40m_cg", "sys_pll1", base + 0x94, 27);
+	hws[IMX8MN_SYS_PLL1_80M_CG] = imx_clk_hw_gate("sys_pll1_80m_cg", "sys_pll1", base + 0x94, 25);
+	hws[IMX8MN_SYS_PLL1_100M_CG] = imx_clk_hw_gate("sys_pll1_100m_cg", "sys_pll1", base + 0x94, 23);
+	hws[IMX8MN_SYS_PLL1_133M_CG] = imx_clk_hw_gate("sys_pll1_133m_cg", "sys_pll1", base + 0x94, 21);
+	hws[IMX8MN_SYS_PLL1_160M_CG] = imx_clk_hw_gate("sys_pll1_160m_cg", "sys_pll1", base + 0x94, 19);
+	hws[IMX8MN_SYS_PLL1_200M_CG] = imx_clk_hw_gate("sys_pll1_200m_cg", "sys_pll1", base + 0x94, 17);
+	hws[IMX8MN_SYS_PLL1_266M_CG] = imx_clk_hw_gate("sys_pll1_266m_cg", "sys_pll1", base + 0x94, 15);
+	hws[IMX8MN_SYS_PLL1_400M_CG] = imx_clk_hw_gate("sys_pll1_400m_cg", "sys_pll1", base + 0x94, 13);
+	hws[IMX8MN_SYS_PLL1_OUT] = imx_clk_hw_gate("sys_pll1_out", "sys_pll1", base + 0x94, 11);
+
+	hws[IMX8MN_SYS_PLL1_40M] = imx_clk_hw_fixed_factor("sys_pll1_40m", "sys_pll1_40m_cg", 1, 20);
+	hws[IMX8MN_SYS_PLL1_80M] = imx_clk_hw_fixed_factor("sys_pll1_80m", "sys_pll1_80m_cg", 1, 10);
+	hws[IMX8MN_SYS_PLL1_100M] = imx_clk_hw_fixed_factor("sys_pll1_100m", "sys_pll1_100m_cg", 1, 8);
+	hws[IMX8MN_SYS_PLL1_133M] = imx_clk_hw_fixed_factor("sys_pll1_133m", "sys_pll1_133m_cg", 1, 6);
+	hws[IMX8MN_SYS_PLL1_160M] = imx_clk_hw_fixed_factor("sys_pll1_160m", "sys_pll1_160m_cg", 1, 5);
+	hws[IMX8MN_SYS_PLL1_200M] = imx_clk_hw_fixed_factor("sys_pll1_200m", "sys_pll1_200m_cg", 1, 4);
+	hws[IMX8MN_SYS_PLL1_266M] = imx_clk_hw_fixed_factor("sys_pll1_266m", "sys_pll1_266m_cg", 1, 3);
+	hws[IMX8MN_SYS_PLL1_400M] = imx_clk_hw_fixed_factor("sys_pll1_400m", "sys_pll1_400m_cg", 1, 2);
+	hws[IMX8MN_SYS_PLL1_800M] = imx_clk_hw_fixed_factor("sys_pll1_800m", "sys_pll1_out", 1, 1);
 
 	/* SYS PLL2 fixed output */
-	clks[IMX8MN_SYS_PLL2_50M_CG] = imx_clk_gate("sys_pll2_50m_cg", "sys_pll2", base + 0x104, 27);
-	clks[IMX8MN_SYS_PLL2_100M_CG] = imx_clk_gate("sys_pll2_100m_cg", "sys_pll2", base + 0x104, 25);
-	clks[IMX8MN_SYS_PLL2_125M_CG] = imx_clk_gate("sys_pll2_125m_cg", "sys_pll2", base + 0x104, 23);
-	clks[IMX8MN_SYS_PLL2_166M_CG] = imx_clk_gate("sys_pll2_166m_cg", "sys_pll2", base + 0x104, 21);
-	clks[IMX8MN_SYS_PLL2_200M_CG] = imx_clk_gate("sys_pll2_200m_cg", "sys_pll2", base + 0x104, 19);
-	clks[IMX8MN_SYS_PLL2_250M_CG] = imx_clk_gate("sys_pll2_250m_cg", "sys_pll2", base + 0x104, 17);
-	clks[IMX8MN_SYS_PLL2_333M_CG] = imx_clk_gate("sys_pll2_333m_cg", "sys_pll2", base + 0x104, 15);
-	clks[IMX8MN_SYS_PLL2_500M_CG] = imx_clk_gate("sys_pll2_500m_cg", "sys_pll2", base + 0x104, 13);
-	clks[IMX8MN_SYS_PLL2_OUT] = imx_clk_gate("sys_pll2_out", "sys_pll2", base + 0x104, 11);
-
-	clks[IMX8MN_SYS_PLL2_50M] = imx_clk_fixed_factor("sys_pll2_50m", "sys_pll2_50m_cg", 1, 20);
-	clks[IMX8MN_SYS_PLL2_100M] = imx_clk_fixed_factor("sys_pll2_100m", "sys_pll2_100m_cg", 1, 10);
-	clks[IMX8MN_SYS_PLL2_125M] = imx_clk_fixed_factor("sys_pll2_125m", "sys_pll2_125m_cg", 1, 8);
-	clks[IMX8MN_SYS_PLL2_166M] = imx_clk_fixed_factor("sys_pll2_166m", "sys_pll2_166m_cg", 1, 6);
-	clks[IMX8MN_SYS_PLL2_200M] = imx_clk_fixed_factor("sys_pll2_200m", "sys_pll2_200m_cg", 1, 5);
-	clks[IMX8MN_SYS_PLL2_250M] = imx_clk_fixed_factor("sys_pll2_250m", "sys_pll2_250m_cg", 1, 4);
-	clks[IMX8MN_SYS_PLL2_333M] = imx_clk_fixed_factor("sys_pll2_333m", "sys_pll2_333m_cg", 1, 3);
-	clks[IMX8MN_SYS_PLL2_500M] = imx_clk_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2);
-	clks[IMX8MN_SYS_PLL2_1000M] = imx_clk_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1);
+	hws[IMX8MN_SYS_PLL2_50M_CG] = imx_clk_hw_gate("sys_pll2_50m_cg", "sys_pll2", base + 0x104, 27);
+	hws[IMX8MN_SYS_PLL2_100M_CG] = imx_clk_hw_gate("sys_pll2_100m_cg", "sys_pll2", base + 0x104, 25);
+	hws[IMX8MN_SYS_PLL2_125M_CG] = imx_clk_hw_gate("sys_pll2_125m_cg", "sys_pll2", base + 0x104, 23);
+	hws[IMX8MN_SYS_PLL2_166M_CG] = imx_clk_hw_gate("sys_pll2_166m_cg", "sys_pll2", base + 0x104, 21);
+	hws[IMX8MN_SYS_PLL2_200M_CG] = imx_clk_hw_gate("sys_pll2_200m_cg", "sys_pll2", base + 0x104, 19);
+	hws[IMX8MN_SYS_PLL2_250M_CG] = imx_clk_hw_gate("sys_pll2_250m_cg", "sys_pll2", base + 0x104, 17);
+	hws[IMX8MN_SYS_PLL2_333M_CG] = imx_clk_hw_gate("sys_pll2_333m_cg", "sys_pll2", base + 0x104, 15);
+	hws[IMX8MN_SYS_PLL2_500M_CG] = imx_clk_hw_gate("sys_pll2_500m_cg", "sys_pll2", base + 0x104, 13);
+	hws[IMX8MN_SYS_PLL2_OUT] = imx_clk_hw_gate("sys_pll2_out", "sys_pll2", base + 0x104, 11);
+
+	hws[IMX8MN_SYS_PLL2_50M] = imx_clk_hw_fixed_factor("sys_pll2_50m", "sys_pll2_50m_cg", 1, 20);
+	hws[IMX8MN_SYS_PLL2_100M] = imx_clk_hw_fixed_factor("sys_pll2_100m", "sys_pll2_100m_cg", 1, 10);
+	hws[IMX8MN_SYS_PLL2_125M] = imx_clk_hw_fixed_factor("sys_pll2_125m", "sys_pll2_125m_cg", 1, 8);
+	hws[IMX8MN_SYS_PLL2_166M] = imx_clk_hw_fixed_factor("sys_pll2_166m", "sys_pll2_166m_cg", 1, 6);
+	hws[IMX8MN_SYS_PLL2_200M] = imx_clk_hw_fixed_factor("sys_pll2_200m", "sys_pll2_200m_cg", 1, 5);
+	hws[IMX8MN_SYS_PLL2_250M] = imx_clk_hw_fixed_factor("sys_pll2_250m", "sys_pll2_250m_cg", 1, 4);
+	hws[IMX8MN_SYS_PLL2_333M] = imx_clk_hw_fixed_factor("sys_pll2_333m", "sys_pll2_333m_cg", 1, 3);
+	hws[IMX8MN_SYS_PLL2_500M] = imx_clk_hw_fixed_factor("sys_pll2_500m", "sys_pll2_500m_cg", 1, 2);
+	hws[IMX8MN_SYS_PLL2_1000M] = imx_clk_hw_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1);
 
 	np = dev->of_node;
 	base = devm_platform_ioremap_resource(pdev, 0);
 	if (WARN_ON(IS_ERR(base))) {
 		ret = PTR_ERR(base);
-		goto unregister_clks;
+		goto unregister_hws;
 	}
 
 	/* CORE */
-	clks[IMX8MN_CLK_A53_SRC] = imx_clk_mux2("arm_a53_src", base + 0x8000, 24, 3, imx8mn_a53_sels, ARRAY_SIZE(imx8mn_a53_sels));
-	clks[IMX8MN_CLK_GPU_CORE_SRC] = imx_clk_mux2("gpu_core_src", base + 0x8180, 24, 3,  imx8mn_gpu_core_sels, ARRAY_SIZE(imx8mn_gpu_core_sels));
-	clks[IMX8MN_CLK_GPU_SHADER_SRC] = imx_clk_mux2("gpu_shader_src", base + 0x8200, 24, 3, imx8mn_gpu_shader_sels,  ARRAY_SIZE(imx8mn_gpu_shader_sels));
-	clks[IMX8MN_CLK_A53_CG] = imx_clk_gate3("arm_a53_cg", "arm_a53_src", base + 0x8000, 28);
-	clks[IMX8MN_CLK_GPU_CORE_CG] = imx_clk_gate3("gpu_core_cg", "gpu_core_src", base + 0x8180, 28);
-	clks[IMX8MN_CLK_GPU_SHADER_CG] = imx_clk_gate3("gpu_shader_cg", "gpu_shader_src", base + 0x8200, 28);
+	hws[IMX8MN_CLK_A53_SRC] = imx_clk_hw_mux2("arm_a53_src", base + 0x8000, 24, 3, imx8mn_a53_sels, ARRAY_SIZE(imx8mn_a53_sels));
+	hws[IMX8MN_CLK_GPU_CORE_SRC] = imx_clk_hw_mux2("gpu_core_src", base + 0x8180, 24, 3,  imx8mn_gpu_core_sels, ARRAY_SIZE(imx8mn_gpu_core_sels));
+	hws[IMX8MN_CLK_GPU_SHADER_SRC] = imx_clk_hw_mux2("gpu_shader_src", base + 0x8200, 24, 3, imx8mn_gpu_shader_sels,  ARRAY_SIZE(imx8mn_gpu_shader_sels));
+	hws[IMX8MN_CLK_A53_CG] = imx_clk_hw_gate3("arm_a53_cg", "arm_a53_src", base + 0x8000, 28);
+	hws[IMX8MN_CLK_GPU_CORE_CG] = imx_clk_hw_gate3("gpu_core_cg", "gpu_core_src", base + 0x8180, 28);
+	hws[IMX8MN_CLK_GPU_SHADER_CG] = imx_clk_hw_gate3("gpu_shader_cg", "gpu_shader_src", base + 0x8200, 28);
 
-	clks[IMX8MN_CLK_A53_DIV] = imx_clk_divider2("arm_a53_div", "arm_a53_cg", base + 0x8000, 0, 3);
-	clks[IMX8MN_CLK_GPU_CORE_DIV] = imx_clk_divider2("gpu_core_div", "gpu_core_cg", base + 0x8180, 0, 3);
-	clks[IMX8MN_CLK_GPU_SHADER_DIV] = imx_clk_divider2("gpu_shader_div", "gpu_shader_cg", base + 0x8200, 0, 3);
+	hws[IMX8MN_CLK_A53_DIV] = imx_clk_hw_divider2("arm_a53_div", "arm_a53_cg", base + 0x8000, 0, 3);
+	hws[IMX8MN_CLK_GPU_CORE_DIV] = imx_clk_hw_divider2("gpu_core_div", "gpu_core_cg", base + 0x8180, 0, 3);
+	hws[IMX8MN_CLK_GPU_SHADER_DIV] = imx_clk_hw_divider2("gpu_shader_div", "gpu_shader_cg", base + 0x8200, 0, 3);
 
 	/* BUS */
-	clks[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
-	clks[IMX8MN_CLK_ENET_AXI] = imx8m_clk_composite("enet_axi", imx8mn_enet_axi_sels, base + 0x8880);
-	clks[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_composite("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900);
-	clks[IMX8MN_CLK_DISP_AXI] = imx8m_clk_composite("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00);
-	clks[IMX8MN_CLK_DISP_APB] = imx8m_clk_composite("disp_apb", imx8mn_disp_apb_sels, base + 0x8a80);
-	clks[IMX8MN_CLK_USB_BUS] = imx8m_clk_composite("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80);
-	clks[IMX8MN_CLK_GPU_AXI] = imx8m_clk_composite("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00);
-	clks[IMX8MN_CLK_GPU_AHB] = imx8m_clk_composite("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80);
-	clks[IMX8MN_CLK_NOC] = imx8m_clk_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00);
-
-	clks[IMX8MN_CLK_AHB] = imx8m_clk_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
-	clks[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_composite("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100);
-	clks[IMX8MN_CLK_IPG_ROOT] = imx_clk_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
-	clks[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
-	clks[IMX8MN_CLK_DRAM_CORE] = imx_clk_mux2_flags("dram_core_clk", base + 0x9800, 24, 1, imx8mn_dram_core_sels, ARRAY_SIZE(imx8mn_dram_core_sels), CLK_IS_CRITICAL);
-	clks[IMX8MN_CLK_DRAM_ALT] = imx8m_clk_composite("dram_alt", imx8mn_dram_alt_sels, base + 0xa000);
-	clks[IMX8MN_CLK_DRAM_APB] = imx8m_clk_composite_critical("dram_apb", imx8mn_dram_apb_sels, base + 0xa080);
-	clks[IMX8MN_CLK_DISP_PIXEL] = imx8m_clk_composite("disp_pixel", imx8mn_disp_pixel_sels, base + 0xa500);
-	clks[IMX8MN_CLK_SAI2] = imx8m_clk_composite("sai2", imx8mn_sai2_sels, base + 0xa600);
-	clks[IMX8MN_CLK_SAI3] = imx8m_clk_composite("sai3", imx8mn_sai3_sels, base + 0xa680);
-	clks[IMX8MN_CLK_SAI5] = imx8m_clk_composite("sai5", imx8mn_sai5_sels, base + 0xa780);
-	clks[IMX8MN_CLK_SAI6] = imx8m_clk_composite("sai6", imx8mn_sai6_sels, base + 0xa800);
-	clks[IMX8MN_CLK_SPDIF1] = imx8m_clk_composite("spdif1", imx8mn_spdif1_sels, base + 0xa880);
-	clks[IMX8MN_CLK_ENET_REF] = imx8m_clk_composite("enet_ref", imx8mn_enet_ref_sels, base + 0xa980);
-	clks[IMX8MN_CLK_ENET_TIMER] = imx8m_clk_composite("enet_timer", imx8mn_enet_timer_sels, base + 0xaa00);
-	clks[IMX8MN_CLK_ENET_PHY_REF] = imx8m_clk_composite("enet_phy", imx8mn_enet_phy_sels, base + 0xaa80);
-	clks[IMX8MN_CLK_NAND] = imx8m_clk_composite("nand", imx8mn_nand_sels, base + 0xab00);
-	clks[IMX8MN_CLK_QSPI] = imx8m_clk_composite("qspi", imx8mn_qspi_sels, base + 0xab80);
-	clks[IMX8MN_CLK_USDHC1] = imx8m_clk_composite("usdhc1", imx8mn_usdhc1_sels, base + 0xac00);
-	clks[IMX8MN_CLK_USDHC2] = imx8m_clk_composite("usdhc2", imx8mn_usdhc2_sels, base + 0xac80);
-	clks[IMX8MN_CLK_I2C1] = imx8m_clk_composite("i2c1", imx8mn_i2c1_sels, base + 0xad00);
-	clks[IMX8MN_CLK_I2C2] = imx8m_clk_composite("i2c2", imx8mn_i2c2_sels, base + 0xad80);
-	clks[IMX8MN_CLK_I2C3] = imx8m_clk_composite("i2c3", imx8mn_i2c3_sels, base + 0xae00);
-	clks[IMX8MN_CLK_I2C4] = imx8m_clk_composite("i2c4", imx8mn_i2c4_sels, base + 0xae80);
-	clks[IMX8MN_CLK_UART1] = imx8m_clk_composite("uart1", imx8mn_uart1_sels, base + 0xaf00);
-	clks[IMX8MN_CLK_UART2] = imx8m_clk_composite("uart2", imx8mn_uart2_sels, base + 0xaf80);
-	clks[IMX8MN_CLK_UART3] = imx8m_clk_composite("uart3", imx8mn_uart3_sels, base + 0xb000);
-	clks[IMX8MN_CLK_UART4] = imx8m_clk_composite("uart4", imx8mn_uart4_sels, base + 0xb080);
-	clks[IMX8MN_CLK_USB_CORE_REF] = imx8m_clk_composite("usb_core_ref", imx8mn_usb_core_sels, base + 0xb100);
-	clks[IMX8MN_CLK_USB_PHY_REF] = imx8m_clk_composite("usb_phy_ref", imx8mn_usb_phy_sels, base + 0xb180);
-	clks[IMX8MN_CLK_GIC] = imx8m_clk_composite_critical("gic", imx8mn_gic_sels, base + 0xb200);
-	clks[IMX8MN_CLK_ECSPI1] = imx8m_clk_composite("ecspi1", imx8mn_ecspi1_sels, base + 0xb280);
-	clks[IMX8MN_CLK_ECSPI2] = imx8m_clk_composite("ecspi2", imx8mn_ecspi2_sels, base + 0xb300);
-	clks[IMX8MN_CLK_PWM1] = imx8m_clk_composite("pwm1", imx8mn_pwm1_sels, base + 0xb380);
-	clks[IMX8MN_CLK_PWM2] = imx8m_clk_composite("pwm2", imx8mn_pwm2_sels, base + 0xb400);
-	clks[IMX8MN_CLK_PWM3] = imx8m_clk_composite("pwm3", imx8mn_pwm3_sels, base + 0xb480);
-	clks[IMX8MN_CLK_PWM4] = imx8m_clk_composite("pwm4", imx8mn_pwm4_sels, base + 0xb500);
-	clks[IMX8MN_CLK_WDOG] = imx8m_clk_composite("wdog", imx8mn_wdog_sels, base + 0xb900);
-	clks[IMX8MN_CLK_WRCLK] = imx8m_clk_composite("wrclk", imx8mn_wrclk_sels, base + 0xb980);
-	clks[IMX8MN_CLK_CLKO1] = imx8m_clk_composite("clko1", imx8mn_clko1_sels, base + 0xba00);
-	clks[IMX8MN_CLK_CLKO2] = imx8m_clk_composite("clko2", imx8mn_clko2_sels, base + 0xba80);
-	clks[IMX8MN_CLK_DSI_CORE] = imx8m_clk_composite("dsi_core", imx8mn_dsi_core_sels, base + 0xbb00);
-	clks[IMX8MN_CLK_DSI_PHY_REF] = imx8m_clk_composite("dsi_phy_ref", imx8mn_dsi_phy_sels, base + 0xbb80);
-	clks[IMX8MN_CLK_DSI_DBI] = imx8m_clk_composite("dsi_dbi", imx8mn_dsi_dbi_sels, base + 0xbc00);
-	clks[IMX8MN_CLK_USDHC3] = imx8m_clk_composite("usdhc3", imx8mn_usdhc3_sels, base + 0xbc80);
-	clks[IMX8MN_CLK_CAMERA_PIXEL] = imx8m_clk_composite("camera_pixel", imx8mn_camera_pixel_sels, base + 0xbd00);
-	clks[IMX8MN_CLK_CSI1_PHY_REF] = imx8m_clk_composite("csi1_phy_ref", imx8mn_csi1_phy_sels, base + 0xbd80);
-	clks[IMX8MN_CLK_CSI2_PHY_REF] = imx8m_clk_composite("csi2_phy_ref", imx8mn_csi2_phy_sels, base + 0xbf00);
-	clks[IMX8MN_CLK_CSI2_ESC] = imx8m_clk_composite("csi2_esc", imx8mn_csi2_esc_sels, base + 0xbf80);
-	clks[IMX8MN_CLK_ECSPI3] = imx8m_clk_composite("ecspi3", imx8mn_ecspi3_sels, base + 0xc180);
-	clks[IMX8MN_CLK_PDM] = imx8m_clk_composite("pdm", imx8mn_pdm_sels, base + 0xc200);
-	clks[IMX8MN_CLK_SAI7] = imx8m_clk_composite("sai7", imx8mn_sai7_sels, base + 0xc300);
-
-	clks[IMX8MN_CLK_ECSPI1_ROOT] = imx_clk_gate4("ecspi1_root_clk", "ecspi1", base + 0x4070, 0);
-	clks[IMX8MN_CLK_ECSPI2_ROOT] = imx_clk_gate4("ecspi2_root_clk", "ecspi2", base + 0x4080, 0);
-	clks[IMX8MN_CLK_ECSPI3_ROOT] = imx_clk_gate4("ecspi3_root_clk", "ecspi3", base + 0x4090, 0);
-	clks[IMX8MN_CLK_ENET1_ROOT] = imx_clk_gate4("enet1_root_clk", "enet_axi", base + 0x40a0, 0);
-	clks[IMX8MN_CLK_GPIO1_ROOT] = imx_clk_gate4("gpio1_root_clk", "ipg_root", base + 0x40b0, 0);
-	clks[IMX8MN_CLK_GPIO2_ROOT] = imx_clk_gate4("gpio2_root_clk", "ipg_root", base + 0x40c0, 0);
-	clks[IMX8MN_CLK_GPIO3_ROOT] = imx_clk_gate4("gpio3_root_clk", "ipg_root", base + 0x40d0, 0);
-	clks[IMX8MN_CLK_GPIO4_ROOT] = imx_clk_gate4("gpio4_root_clk", "ipg_root", base + 0x40e0, 0);
-	clks[IMX8MN_CLK_GPIO5_ROOT] = imx_clk_gate4("gpio5_root_clk", "ipg_root", base + 0x40f0, 0);
-	clks[IMX8MN_CLK_I2C1_ROOT] = imx_clk_gate4("i2c1_root_clk", "i2c1", base + 0x4170, 0);
-	clks[IMX8MN_CLK_I2C2_ROOT] = imx_clk_gate4("i2c2_root_clk", "i2c2", base + 0x4180, 0);
-	clks[IMX8MN_CLK_I2C3_ROOT] = imx_clk_gate4("i2c3_root_clk", "i2c3", base + 0x4190, 0);
-	clks[IMX8MN_CLK_I2C4_ROOT] = imx_clk_gate4("i2c4_root_clk", "i2c4", base + 0x41a0, 0);
-	clks[IMX8MN_CLK_MU_ROOT] = imx_clk_gate4("mu_root_clk", "ipg_root", base + 0x4210, 0);
-	clks[IMX8MN_CLK_OCOTP_ROOT] = imx_clk_gate4("ocotp_root_clk", "ipg_root", base + 0x4220, 0);
-	clks[IMX8MN_CLK_PWM1_ROOT] = imx_clk_gate4("pwm1_root_clk", "pwm1", base + 0x4280, 0);
-	clks[IMX8MN_CLK_PWM2_ROOT] = imx_clk_gate4("pwm2_root_clk", "pwm2", base + 0x4290, 0);
-	clks[IMX8MN_CLK_PWM3_ROOT] = imx_clk_gate4("pwm3_root_clk", "pwm3", base + 0x42a0, 0);
-	clks[IMX8MN_CLK_PWM4_ROOT] = imx_clk_gate4("pwm4_root_clk", "pwm4", base + 0x42b0, 0);
-	clks[IMX8MN_CLK_QSPI_ROOT] = imx_clk_gate4("qspi_root_clk", "qspi", base + 0x42f0, 0);
-	clks[IMX8MN_CLK_NAND_ROOT] = imx_clk_gate2_shared2("nand_root_clk", "nand", base + 0x4300, 0, &share_count_nand);
-	clks[IMX8MN_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", base + 0x4300, 0, &share_count_nand);
-	clks[IMX8MN_CLK_SAI2_ROOT] = imx_clk_gate2_shared2("sai2_root_clk", "sai2", base + 0x4340, 0, &share_count_sai2);
-	clks[IMX8MN_CLK_SAI2_IPG] = imx_clk_gate2_shared2("sai2_ipg_clk", "ipg_audio_root", base + 0x4340, 0, &share_count_sai2);
-	clks[IMX8MN_CLK_SAI3_ROOT] = imx_clk_gate2_shared2("sai3_root_clk", "sai3", base + 0x4350, 0, &share_count_sai3);
-	clks[IMX8MN_CLK_SAI3_IPG] = imx_clk_gate2_shared2("sai3_ipg_clk", "ipg_audio_root", base + 0x4350, 0, &share_count_sai3);
-	clks[IMX8MN_CLK_SAI5_ROOT] = imx_clk_gate2_shared2("sai5_root_clk", "sai5", base + 0x4370, 0, &share_count_sai5);
-	clks[IMX8MN_CLK_SAI5_IPG] = imx_clk_gate2_shared2("sai5_ipg_clk", "ipg_audio_root", base + 0x4370, 0, &share_count_sai5);
-	clks[IMX8MN_CLK_SAI6_ROOT] = imx_clk_gate2_shared2("sai6_root_clk", "sai6", base + 0x4380, 0, &share_count_sai6);
-	clks[IMX8MN_CLK_SAI6_IPG] = imx_clk_gate2_shared2("sai6_ipg_clk", "ipg_audio_root", base + 0x4380, 0, &share_count_sai6);
-	clks[IMX8MN_CLK_UART1_ROOT] = imx_clk_gate4("uart1_root_clk", "uart1", base + 0x4490, 0);
-	clks[IMX8MN_CLK_UART2_ROOT] = imx_clk_gate4("uart2_root_clk", "uart2", base + 0x44a0, 0);
-	clks[IMX8MN_CLK_UART3_ROOT] = imx_clk_gate4("uart3_root_clk", "uart3", base + 0x44b0, 0);
-	clks[IMX8MN_CLK_UART4_ROOT] = imx_clk_gate4("uart4_root_clk", "uart4", base + 0x44c0, 0);
-	clks[IMX8MN_CLK_USB1_CTRL_ROOT] = imx_clk_gate4("usb1_ctrl_root_clk", "usb_core_ref", base + 0x44d0, 0);
-	clks[IMX8MN_CLK_GPU_CORE_ROOT] = imx_clk_gate4("gpu_core_root_clk", "gpu_core_div", base + 0x44f0, 0);
-	clks[IMX8MN_CLK_USDHC1_ROOT] = imx_clk_gate4("usdhc1_root_clk", "usdhc1", base + 0x4510, 0);
-	clks[IMX8MN_CLK_USDHC2_ROOT] = imx_clk_gate4("usdhc2_root_clk", "usdhc2", base + 0x4520, 0);
-	clks[IMX8MN_CLK_WDOG1_ROOT] = imx_clk_gate4("wdog1_root_clk", "wdog", base + 0x4530, 0);
-	clks[IMX8MN_CLK_WDOG2_ROOT] = imx_clk_gate4("wdog2_root_clk", "wdog", base + 0x4540, 0);
-	clks[IMX8MN_CLK_WDOG3_ROOT] = imx_clk_gate4("wdog3_root_clk", "wdog", base + 0x4550, 0);
-	clks[IMX8MN_CLK_GPU_BUS_ROOT] = imx_clk_gate4("gpu_root_clk", "gpu_axi", base + 0x4570, 0);
-	clks[IMX8MN_CLK_ASRC_ROOT] = imx_clk_gate4("asrc_root_clk", "audio_ahb", base + 0x4580, 0);
-	clks[IMX8MN_CLK_PDM_ROOT] = imx_clk_gate2_shared2("pdm_root_clk", "pdm", base + 0x45b0, 0, &share_count_pdm);
-	clks[IMX8MN_CLK_PDM_IPG]  = imx_clk_gate2_shared2("pdm_ipg_clk", "ipg_audio_root", base + 0x45b0, 0, &share_count_pdm);
-	clks[IMX8MN_CLK_DISP_AXI_ROOT]  = imx_clk_gate2_shared2("disp_axi_root_clk", "disp_axi", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MN_CLK_DISP_APB_ROOT]  = imx_clk_gate2_shared2("disp_apb_root_clk", "disp_apb", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MN_CLK_CAMERA_PIXEL_ROOT] = imx_clk_gate2_shared2("camera_pixel_clk", "camera_pixel", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MN_CLK_DISP_PIXEL_ROOT] = imx_clk_gate2_shared2("disp_pixel_clk", "disp_pixel", base + 0x45d0, 0, &share_count_disp);
-	clks[IMX8MN_CLK_USDHC3_ROOT] = imx_clk_gate4("usdhc3_root_clk", "usdhc3", base + 0x45e0, 0);
-	clks[IMX8MN_CLK_TMU_ROOT] = imx_clk_gate4("tmu_root_clk", "ipg_root", base + 0x4620, 0);
-	clks[IMX8MN_CLK_SDMA1_ROOT] = imx_clk_gate4("sdma1_clk", "ipg_root", base + 0x43a0, 0);
-	clks[IMX8MN_CLK_SDMA2_ROOT] = imx_clk_gate4("sdma2_clk", "ipg_audio_root", base + 0x43b0, 0);
-	clks[IMX8MN_CLK_SDMA3_ROOT] = imx_clk_gate4("sdma3_clk", "ipg_audio_root", base + 0x45f0, 0);
-	clks[IMX8MN_CLK_SAI7_ROOT] = imx_clk_gate2_shared2("sai7_root_clk", "sai7", base + 0x4650, 0, &share_count_sai7);
-
-	clks[IMX8MN_CLK_DRAM_ALT_ROOT] = imx_clk_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
-
-	clks[IMX8MN_CLK_ARM] = imx_clk_cpu("arm", "arm_a53_div",
-					   clks[IMX8MN_CLK_A53_DIV],
-					   clks[IMX8MN_CLK_A53_SRC],
-					   clks[IMX8MN_ARM_PLL_OUT],
-					   clks[IMX8MN_SYS_PLL1_800M]);
-
-	imx_check_clocks(clks, ARRAY_SIZE(clks));
-
-	clk_data.clks = clks;
-	clk_data.clk_num = ARRAY_SIZE(clks);
-	ret = of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+	hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800);
+	hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite("enet_axi", imx8mn_enet_axi_sels, base + 0x8880);
+	hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900);
+	hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00);
+	hws[IMX8MN_CLK_DISP_APB] = imx8m_clk_hw_composite("disp_apb", imx8mn_disp_apb_sels, base + 0x8a80);
+	hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80);
+	hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00);
+	hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80);
+	hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00);
+
+	hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000);
+	hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100);
+	hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
+	hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
+	hws[IMX8MN_CLK_DRAM_CORE] = imx_clk_hw_mux2_flags("dram_core_clk", base + 0x9800, 24, 1, imx8mn_dram_core_sels, ARRAY_SIZE(imx8mn_dram_core_sels), CLK_IS_CRITICAL);
+
+	/*
+	 * DRAM clocks are manipulated from TF-A outside clock framework.
+	 * Mark with GET_RATE_NOCACHE to always read div value from hardware
+	 */
+	hws[IMX8MN_CLK_DRAM_ALT] = __imx8m_clk_hw_composite("dram_alt", imx8mn_dram_alt_sels, base + 0xa000, CLK_GET_RATE_NOCACHE);
+	hws[IMX8MN_CLK_DRAM_APB] = __imx8m_clk_hw_composite("dram_apb", imx8mn_dram_apb_sels, base + 0xa080, CLK_IS_CRITICAL | CLK_GET_RATE_NOCACHE);
+
+	hws[IMX8MN_CLK_DISP_PIXEL] = imx8m_clk_hw_composite("disp_pixel", imx8mn_disp_pixel_sels, base + 0xa500);
+	hws[IMX8MN_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mn_sai2_sels, base + 0xa600);
+	hws[IMX8MN_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mn_sai3_sels, base + 0xa680);
+	hws[IMX8MN_CLK_SAI5] = imx8m_clk_hw_composite("sai5", imx8mn_sai5_sels, base + 0xa780);
+	hws[IMX8MN_CLK_SAI6] = imx8m_clk_hw_composite("sai6", imx8mn_sai6_sels, base + 0xa800);
+	hws[IMX8MN_CLK_SPDIF1] = imx8m_clk_hw_composite("spdif1", imx8mn_spdif1_sels, base + 0xa880);
+	hws[IMX8MN_CLK_ENET_REF] = imx8m_clk_hw_composite("enet_ref", imx8mn_enet_ref_sels, base + 0xa980);
+	hws[IMX8MN_CLK_ENET_TIMER] = imx8m_clk_hw_composite("enet_timer", imx8mn_enet_timer_sels, base + 0xaa00);
+	hws[IMX8MN_CLK_ENET_PHY_REF] = imx8m_clk_hw_composite("enet_phy", imx8mn_enet_phy_sels, base + 0xaa80);
+	hws[IMX8MN_CLK_NAND] = imx8m_clk_hw_composite("nand", imx8mn_nand_sels, base + 0xab00);
+	hws[IMX8MN_CLK_QSPI] = imx8m_clk_hw_composite("qspi", imx8mn_qspi_sels, base + 0xab80);
+	hws[IMX8MN_CLK_USDHC1] = imx8m_clk_hw_composite("usdhc1", imx8mn_usdhc1_sels, base + 0xac00);
+	hws[IMX8MN_CLK_USDHC2] = imx8m_clk_hw_composite("usdhc2", imx8mn_usdhc2_sels, base + 0xac80);
+	hws[IMX8MN_CLK_I2C1] = imx8m_clk_hw_composite("i2c1", imx8mn_i2c1_sels, base + 0xad00);
+	hws[IMX8MN_CLK_I2C2] = imx8m_clk_hw_composite("i2c2", imx8mn_i2c2_sels, base + 0xad80);
+	hws[IMX8MN_CLK_I2C3] = imx8m_clk_hw_composite("i2c3", imx8mn_i2c3_sels, base + 0xae00);
+	hws[IMX8MN_CLK_I2C4] = imx8m_clk_hw_composite("i2c4", imx8mn_i2c4_sels, base + 0xae80);
+	hws[IMX8MN_CLK_UART1] = imx8m_clk_hw_composite("uart1", imx8mn_uart1_sels, base + 0xaf00);
+	hws[IMX8MN_CLK_UART2] = imx8m_clk_hw_composite("uart2", imx8mn_uart2_sels, base + 0xaf80);
+	hws[IMX8MN_CLK_UART3] = imx8m_clk_hw_composite("uart3", imx8mn_uart3_sels, base + 0xb000);
+	hws[IMX8MN_CLK_UART4] = imx8m_clk_hw_composite("uart4", imx8mn_uart4_sels, base + 0xb080);
+	hws[IMX8MN_CLK_USB_CORE_REF] = imx8m_clk_hw_composite("usb_core_ref", imx8mn_usb_core_sels, base + 0xb100);
+	hws[IMX8MN_CLK_USB_PHY_REF] = imx8m_clk_hw_composite("usb_phy_ref", imx8mn_usb_phy_sels, base + 0xb180);
+	hws[IMX8MN_CLK_GIC] = imx8m_clk_hw_composite_critical("gic", imx8mn_gic_sels, base + 0xb200);
+	hws[IMX8MN_CLK_ECSPI1] = imx8m_clk_hw_composite("ecspi1", imx8mn_ecspi1_sels, base + 0xb280);
+	hws[IMX8MN_CLK_ECSPI2] = imx8m_clk_hw_composite("ecspi2", imx8mn_ecspi2_sels, base + 0xb300);
+	hws[IMX8MN_CLK_PWM1] = imx8m_clk_hw_composite("pwm1", imx8mn_pwm1_sels, base + 0xb380);
+	hws[IMX8MN_CLK_PWM2] = imx8m_clk_hw_composite("pwm2", imx8mn_pwm2_sels, base + 0xb400);
+	hws[IMX8MN_CLK_PWM3] = imx8m_clk_hw_composite("pwm3", imx8mn_pwm3_sels, base + 0xb480);
+	hws[IMX8MN_CLK_PWM4] = imx8m_clk_hw_composite("pwm4", imx8mn_pwm4_sels, base + 0xb500);
+	hws[IMX8MN_CLK_WDOG] = imx8m_clk_hw_composite("wdog", imx8mn_wdog_sels, base + 0xb900);
+	hws[IMX8MN_CLK_WRCLK] = imx8m_clk_hw_composite("wrclk", imx8mn_wrclk_sels, base + 0xb980);
+	hws[IMX8MN_CLK_CLKO1] = imx8m_clk_hw_composite("clko1", imx8mn_clko1_sels, base + 0xba00);
+	hws[IMX8MN_CLK_CLKO2] = imx8m_clk_hw_composite("clko2", imx8mn_clko2_sels, base + 0xba80);
+	hws[IMX8MN_CLK_DSI_CORE] = imx8m_clk_hw_composite("dsi_core", imx8mn_dsi_core_sels, base + 0xbb00);
+	hws[IMX8MN_CLK_DSI_PHY_REF] = imx8m_clk_hw_composite("dsi_phy_ref", imx8mn_dsi_phy_sels, base + 0xbb80);
+	hws[IMX8MN_CLK_DSI_DBI] = imx8m_clk_hw_composite("dsi_dbi", imx8mn_dsi_dbi_sels, base + 0xbc00);
+	hws[IMX8MN_CLK_USDHC3] = imx8m_clk_hw_composite("usdhc3", imx8mn_usdhc3_sels, base + 0xbc80);
+	hws[IMX8MN_CLK_CAMERA_PIXEL] = imx8m_clk_hw_composite("camera_pixel", imx8mn_camera_pixel_sels, base + 0xbd00);
+	hws[IMX8MN_CLK_CSI1_PHY_REF] = imx8m_clk_hw_composite("csi1_phy_ref", imx8mn_csi1_phy_sels, base + 0xbd80);
+	hws[IMX8MN_CLK_CSI2_PHY_REF] = imx8m_clk_hw_composite("csi2_phy_ref", imx8mn_csi2_phy_sels, base + 0xbf00);
+	hws[IMX8MN_CLK_CSI2_ESC] = imx8m_clk_hw_composite("csi2_esc", imx8mn_csi2_esc_sels, base + 0xbf80);
+	hws[IMX8MN_CLK_ECSPI3] = imx8m_clk_hw_composite("ecspi3", imx8mn_ecspi3_sels, base + 0xc180);
+	hws[IMX8MN_CLK_PDM] = imx8m_clk_hw_composite("pdm", imx8mn_pdm_sels, base + 0xc200);
+	hws[IMX8MN_CLK_SAI7] = imx8m_clk_hw_composite("sai7", imx8mn_sai7_sels, base + 0xc300);
+
+	hws[IMX8MN_CLK_ECSPI1_ROOT] = imx_clk_hw_gate4("ecspi1_root_clk", "ecspi1", base + 0x4070, 0);
+	hws[IMX8MN_CLK_ECSPI2_ROOT] = imx_clk_hw_gate4("ecspi2_root_clk", "ecspi2", base + 0x4080, 0);
+	hws[IMX8MN_CLK_ECSPI3_ROOT] = imx_clk_hw_gate4("ecspi3_root_clk", "ecspi3", base + 0x4090, 0);
+	hws[IMX8MN_CLK_ENET1_ROOT] = imx_clk_hw_gate4("enet1_root_clk", "enet_axi", base + 0x40a0, 0);
+	hws[IMX8MN_CLK_GPIO1_ROOT] = imx_clk_hw_gate4("gpio1_root_clk", "ipg_root", base + 0x40b0, 0);
+	hws[IMX8MN_CLK_GPIO2_ROOT] = imx_clk_hw_gate4("gpio2_root_clk", "ipg_root", base + 0x40c0, 0);
+	hws[IMX8MN_CLK_GPIO3_ROOT] = imx_clk_hw_gate4("gpio3_root_clk", "ipg_root", base + 0x40d0, 0);
+	hws[IMX8MN_CLK_GPIO4_ROOT] = imx_clk_hw_gate4("gpio4_root_clk", "ipg_root", base + 0x40e0, 0);
+	hws[IMX8MN_CLK_GPIO5_ROOT] = imx_clk_hw_gate4("gpio5_root_clk", "ipg_root", base + 0x40f0, 0);
+	hws[IMX8MN_CLK_I2C1_ROOT] = imx_clk_hw_gate4("i2c1_root_clk", "i2c1", base + 0x4170, 0);
+	hws[IMX8MN_CLK_I2C2_ROOT] = imx_clk_hw_gate4("i2c2_root_clk", "i2c2", base + 0x4180, 0);
+	hws[IMX8MN_CLK_I2C3_ROOT] = imx_clk_hw_gate4("i2c3_root_clk", "i2c3", base + 0x4190, 0);
+	hws[IMX8MN_CLK_I2C4_ROOT] = imx_clk_hw_gate4("i2c4_root_clk", "i2c4", base + 0x41a0, 0);
+	hws[IMX8MN_CLK_MU_ROOT] = imx_clk_hw_gate4("mu_root_clk", "ipg_root", base + 0x4210, 0);
+	hws[IMX8MN_CLK_OCOTP_ROOT] = imx_clk_hw_gate4("ocotp_root_clk", "ipg_root", base + 0x4220, 0);
+	hws[IMX8MN_CLK_PWM1_ROOT] = imx_clk_hw_gate4("pwm1_root_clk", "pwm1", base + 0x4280, 0);
+	hws[IMX8MN_CLK_PWM2_ROOT] = imx_clk_hw_gate4("pwm2_root_clk", "pwm2", base + 0x4290, 0);
+	hws[IMX8MN_CLK_PWM3_ROOT] = imx_clk_hw_gate4("pwm3_root_clk", "pwm3", base + 0x42a0, 0);
+	hws[IMX8MN_CLK_PWM4_ROOT] = imx_clk_hw_gate4("pwm4_root_clk", "pwm4", base + 0x42b0, 0);
+	hws[IMX8MN_CLK_QSPI_ROOT] = imx_clk_hw_gate4("qspi_root_clk", "qspi", base + 0x42f0, 0);
+	hws[IMX8MN_CLK_NAND_ROOT] = imx_clk_hw_gate2_shared2("nand_root_clk", "nand", base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MN_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_hw_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MN_CLK_SAI2_ROOT] = imx_clk_hw_gate2_shared2("sai2_root_clk", "sai2", base + 0x4340, 0, &share_count_sai2);
+	hws[IMX8MN_CLK_SAI2_IPG] = imx_clk_hw_gate2_shared2("sai2_ipg_clk", "ipg_audio_root", base + 0x4340, 0, &share_count_sai2);
+	hws[IMX8MN_CLK_SAI3_ROOT] = imx_clk_hw_gate2_shared2("sai3_root_clk", "sai3", base + 0x4350, 0, &share_count_sai3);
+	hws[IMX8MN_CLK_SAI3_IPG] = imx_clk_hw_gate2_shared2("sai3_ipg_clk", "ipg_audio_root", base + 0x4350, 0, &share_count_sai3);
+	hws[IMX8MN_CLK_SAI5_ROOT] = imx_clk_hw_gate2_shared2("sai5_root_clk", "sai5", base + 0x4370, 0, &share_count_sai5);
+	hws[IMX8MN_CLK_SAI5_IPG] = imx_clk_hw_gate2_shared2("sai5_ipg_clk", "ipg_audio_root", base + 0x4370, 0, &share_count_sai5);
+	hws[IMX8MN_CLK_SAI6_ROOT] = imx_clk_hw_gate2_shared2("sai6_root_clk", "sai6", base + 0x4380, 0, &share_count_sai6);
+	hws[IMX8MN_CLK_SAI6_IPG] = imx_clk_hw_gate2_shared2("sai6_ipg_clk", "ipg_audio_root", base + 0x4380, 0, &share_count_sai6);
+	hws[IMX8MN_CLK_UART1_ROOT] = imx_clk_hw_gate4("uart1_root_clk", "uart1", base + 0x4490, 0);
+	hws[IMX8MN_CLK_UART2_ROOT] = imx_clk_hw_gate4("uart2_root_clk", "uart2", base + 0x44a0, 0);
+	hws[IMX8MN_CLK_UART3_ROOT] = imx_clk_hw_gate4("uart3_root_clk", "uart3", base + 0x44b0, 0);
+	hws[IMX8MN_CLK_UART4_ROOT] = imx_clk_hw_gate4("uart4_root_clk", "uart4", base + 0x44c0, 0);
+	hws[IMX8MN_CLK_USB1_CTRL_ROOT] = imx_clk_hw_gate4("usb1_ctrl_root_clk", "usb_bus", base + 0x44d0, 0);
+	hws[IMX8MN_CLK_GPU_CORE_ROOT] = imx_clk_hw_gate4("gpu_core_root_clk", "gpu_core_div", base + 0x44f0, 0);
+	hws[IMX8MN_CLK_USDHC1_ROOT] = imx_clk_hw_gate4("usdhc1_root_clk", "usdhc1", base + 0x4510, 0);
+	hws[IMX8MN_CLK_USDHC2_ROOT] = imx_clk_hw_gate4("usdhc2_root_clk", "usdhc2", base + 0x4520, 0);
+	hws[IMX8MN_CLK_WDOG1_ROOT] = imx_clk_hw_gate4("wdog1_root_clk", "wdog", base + 0x4530, 0);
+	hws[IMX8MN_CLK_WDOG2_ROOT] = imx_clk_hw_gate4("wdog2_root_clk", "wdog", base + 0x4540, 0);
+	hws[IMX8MN_CLK_WDOG3_ROOT] = imx_clk_hw_gate4("wdog3_root_clk", "wdog", base + 0x4550, 0);
+	hws[IMX8MN_CLK_GPU_BUS_ROOT] = imx_clk_hw_gate4("gpu_root_clk", "gpu_axi", base + 0x4570, 0);
+	hws[IMX8MN_CLK_ASRC_ROOT] = imx_clk_hw_gate4("asrc_root_clk", "audio_ahb", base + 0x4580, 0);
+	hws[IMX8MN_CLK_PDM_ROOT] = imx_clk_hw_gate2_shared2("pdm_root_clk", "pdm", base + 0x45b0, 0, &share_count_pdm);
+	hws[IMX8MN_CLK_PDM_IPG]  = imx_clk_hw_gate2_shared2("pdm_ipg_clk", "ipg_audio_root", base + 0x45b0, 0, &share_count_pdm);
+	hws[IMX8MN_CLK_DISP_AXI_ROOT]  = imx_clk_hw_gate2_shared2("disp_axi_root_clk", "disp_axi", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MN_CLK_DISP_APB_ROOT]  = imx_clk_hw_gate2_shared2("disp_apb_root_clk", "disp_apb", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MN_CLK_CAMERA_PIXEL_ROOT] = imx_clk_hw_gate2_shared2("camera_pixel_clk", "camera_pixel", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MN_CLK_DISP_PIXEL_ROOT] = imx_clk_hw_gate2_shared2("disp_pixel_clk", "disp_pixel", base + 0x45d0, 0, &share_count_disp);
+	hws[IMX8MN_CLK_USDHC3_ROOT] = imx_clk_hw_gate4("usdhc3_root_clk", "usdhc3", base + 0x45e0, 0);
+	hws[IMX8MN_CLK_TMU_ROOT] = imx_clk_hw_gate4("tmu_root_clk", "ipg_root", base + 0x4620, 0);
+	hws[IMX8MN_CLK_SDMA1_ROOT] = imx_clk_hw_gate4("sdma1_clk", "ipg_root", base + 0x43a0, 0);
+	hws[IMX8MN_CLK_SDMA2_ROOT] = imx_clk_hw_gate4("sdma2_clk", "ipg_audio_root", base + 0x43b0, 0);
+	hws[IMX8MN_CLK_SDMA3_ROOT] = imx_clk_hw_gate4("sdma3_clk", "ipg_audio_root", base + 0x45f0, 0);
+	hws[IMX8MN_CLK_SAI7_ROOT] = imx_clk_hw_gate2_shared2("sai7_root_clk", "sai7", base + 0x4650, 0, &share_count_sai7);
+
+	hws[IMX8MN_CLK_DRAM_ALT_ROOT] = imx_clk_hw_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
+
+	hws[IMX8MN_CLK_ARM] = imx_clk_hw_cpu("arm", "arm_a53_div",
+					   hws[IMX8MN_CLK_A53_DIV]->clk,
+					   hws[IMX8MN_CLK_A53_SRC]->clk,
+					   hws[IMX8MN_ARM_PLL_OUT]->clk,
+					   hws[IMX8MN_SYS_PLL1_800M]->clk);
+
+	imx_check_clk_hws(hws, IMX8MN_CLK_END);
+
+	ret = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data);
 	if (ret < 0) {
-		dev_err(dev, "failed to register clks for i.MX8MN\n");
-		goto unregister_clks;
+		dev_err(dev, "failed to register hws for i.MX8MN\n");
+		goto unregister_hws;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(uart_clk_ids); i++) {
+		int index = uart_clk_ids[i];
+
+		uart_hws[i] = &hws[index]->clk;
 	}
 
-	imx_register_uart_clocks(uart_clks);
+	imx_register_uart_clocks(uart_hws);
 
 	return 0;
 
-unregister_clks:
-	imx_unregister_clocks(clks, ARRAY_SIZE(clks));
+unregister_hws:
+	imx_unregister_hw_clocks(hws, IMX8MN_CLK_END);
 
 	return ret;
 }
@@ -572,6 +591,11 @@ static struct platform_driver imx8mn_clk_driver = {
 	.probe = imx8mn_clocks_probe,
 	.driver = {
 		.name = "imx8mn-ccm",
+		/*
+		 * Disable bind attributes: clocks are not removed and
+		 * reloading the driver will crash or break devices.
+		 */
+		.suppress_bind_attrs = true,
 		.of_match_table = of_match_ptr(imx8mn_clk_of_match),
 	},
 };
diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
new file mode 100644
index 000000000000..f6c120cca0d4
--- /dev/null
+++ b/drivers/clk/imx/clk-imx8mp.c
@@ -0,0 +1,764 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 NXP.
+ */
+
+#include <dt-bindings/clock/imx8mp-clock.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#include "clk.h"
+
+static u32 share_count_nand;
+static u32 share_count_media;
+
+static const char * const pll_ref_sels[] = { "osc_24m", "dummy", "dummy", "dummy", };
+static const char * const audio_pll1_bypass_sels[] = {"audio_pll1", "audio_pll1_ref_sel", };
+static const char * const audio_pll2_bypass_sels[] = {"audio_pll2", "audio_pll2_ref_sel", };
+static const char * const video_pll1_bypass_sels[] = {"video_pll1", "video_pll1_ref_sel", };
+static const char * const dram_pll_bypass_sels[] = {"dram_pll", "dram_pll_ref_sel", };
+static const char * const gpu_pll_bypass_sels[] = {"gpu_pll", "gpu_pll_ref_sel", };
+static const char * const vpu_pll_bypass_sels[] = {"vpu_pll", "vpu_pll_ref_sel", };
+static const char * const arm_pll_bypass_sels[] = {"arm_pll", "arm_pll_ref_sel", };
+static const char * const sys_pll1_bypass_sels[] = {"sys_pll1", "sys_pll1_ref_sel", };
+static const char * const sys_pll2_bypass_sels[] = {"sys_pll2", "sys_pll2_ref_sel", };
+static const char * const sys_pll3_bypass_sels[] = {"sys_pll3", "sys_pll3_ref_sel", };
+
+static const char * const imx8mp_a53_sels[] = {"osc_24m", "arm_pll_out", "sys_pll2_500m",
+					       "sys_pll2_1000m", "sys_pll1_800m", "sys_pll1_400m",
+					       "audio_pll1_out", "sys_pll3_out", };
+
+static const char * const imx8mp_m7_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll2_250m",
+					      "vpu_pll_out", "sys_pll1_800m", "audio_pll1_out",
+					      "video_pll1_out", "sys_pll3_out", };
+
+static const char * const imx8mp_ml_sels[] = {"osc_24m", "gpu_pll_out", "sys_pll1_800m",
+					      "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+					      "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_gpu3d_core_sels[] = {"osc_24m", "gpu_pll_out", "sys_pll1_800m",
+						      "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						      "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_gpu3d_shader_sels[] = {"osc_24m", "gpu_pll_out", "sys_pll1_800m",
+							"sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+							"video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_gpu2d_sels[] = {"osc_24m", "gpu_pll_out", "sys_pll1_800m",
+						 "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						 "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_audio_axi_sels[] = {"osc_24m", "gpu_pll_out", "sys_pll1_800m",
+						     "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						     "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_hsio_axi_sels[] = {"osc_24m", "sys_pll2_500m", "sys_pll1_800m",
+						    "sys_pll2_100m", "sys_pll2_200m", "clk_ext2",
+						    "clk_ext4", "audio_pll2_out", };
+
+static const char * const imx8mp_media_isp_sels[] = {"osc_24m", "sys_pll2_1000m", "sys_pll1_800m",
+						     "sys_pll3_out", "sys_pll1_400m", "audio_pll2_out",
+						     "clk_ext1", "sys_pll2_500m", };
+
+static const char * const imx8mp_main_axi_sels[] = {"osc_24m", "sys_pll2_333m", "sys_pll1_800m",
+						    "sys_pll2_250m", "sys_pll2_1000m", "audio_pll1_out",
+						    "video_pll1_out", "sys_pll1_100m",};
+
+static const char * const imx8mp_enet_axi_sels[] = {"osc_24m", "sys_pll1_266m", "sys_pll1_800m",
+						    "sys_pll2_250m", "sys_pll2_200m", "audio_pll1_out",
+						    "video_pll1_out", "sys_pll3_out", };
+
+static const char * const imx8mp_nand_usdhc_sels[] = {"osc_24m", "sys_pll1_266m", "sys_pll1_800m",
+						      "sys_pll2_200m", "sys_pll1_133m", "sys_pll3_out",
+						      "sys_pll2_250m", "audio_pll1_out", };
+
+static const char * const imx8mp_vpu_bus_sels[] = {"osc_24m", "sys_pll1_800m", "vpu_pll_out",
+						   "audio_pll2_out", "sys_pll3_out", "sys_pll2_1000m",
+						   "sys_pll2_200m", "sys_pll1_100m", };
+
+static const char * const imx8mp_media_axi_sels[] = {"osc_24m", "sys_pll2_1000m", "sys_pll1_800m",
+						     "sys_pll3_out", "sys_pll1_40m", "audio_pll2_out",
+						     "clk_ext1", "sys_pll2_500m", };
+
+static const char * const imx8mp_media_apb_sels[] = {"osc_24m", "sys_pll2_125m", "sys_pll1_800m",
+						     "sys_pll3_out", "sys_pll1_40m", "audio_pll2_out",
+						     "clk_ext1", "sys_pll1_133m", };
+
+static const char * const imx8mp_gpu_axi_sels[] = {"osc_24m", "sys_pll1_800m", "gpu_pll_out",
+						   "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						   "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_gpu_ahb_sels[] = {"osc_24m", "sys_pll1_800m", "gpu_pll_out",
+						   "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						   "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_noc_sels[] = {"osc_24m", "sys_pll1_800m", "sys_pll3_out",
+					       "sys_pll2_1000m", "sys_pll2_500m", "audio_pll1_out",
+					       "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_noc_io_sels[] = {"osc_24m", "sys_pll1_800m", "sys_pll3_out",
+						  "sys_pll2_1000m", "sys_pll2_500m", "audio_pll1_out",
+						  "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_ml_axi_sels[] = {"osc_24m", "sys_pll1_800m", "gpu_pll_out",
+						  "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						  "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_ml_ahb_sels[] = {"osc_24m", "sys_pll1_800m", "gpu_pll_out",
+						  "sys_pll3_out", "sys_pll2_1000m", "audio_pll1_out",
+						  "video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_ahb_sels[] = {"osc_24m", "sys_pll1_133m", "sys_pll1_800m",
+					       "sys_pll1_400m", "sys_pll2_125m", "sys_pll3_out",
+					       "audio_pll1_out", "video_pll1_out", };
+
+static const char * const imx8mp_audio_ahb_sels[] = {"osc_24m", "sys_pll2_500m", "sys_pll1_800m",
+						     "sys_pll2_1000m", "sys_pll2_166m", "sys_pll3_out",
+						     "audio_pll1_out", "video_pll1_out", };
+
+static const char * const imx8mp_mipi_dsi_esc_rx_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_80m",
+							   "sys_pll1_800m", "sys_pll2_1000m",
+							   "sys_pll3_out", "clk_ext3", "audio_pll2_out", };
+
+static const char * const imx8mp_dram_alt_sels[] = {"osc_24m", "sys_pll1_800m", "sys_pll1_100m",
+						    "sys_pll2_500m", "sys_pll2_1000m", "sys_pll3_out",
+						    "audio_pll1_out", "sys_pll1_266m", };
+
+static const char * const imx8mp_dram_apb_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+						    "sys_pll1_160m", "sys_pll1_800m", "sys_pll3_out",
+						    "sys_pll2_250m", "audio_pll2_out", };
+
+static const char * const imx8mp_vpu_g1_sels[] = {"osc_24m", "vpu_pll_out", "sys_pll1_800m",
+						  "sys_pll2_1000m", "sys_pll1_100m", "sys_pll2_125m",
+						  "sys_pll3_out", "audio_pll1_out", };
+
+static const char * const imx8mp_vpu_g2_sels[] = {"osc_24m", "vpu_pll_out", "sys_pll1_800m",
+						  "sys_pll2_1000m", "sys_pll1_100m", "sys_pll2_125m",
+						  "sys_pll3_out", "audio_pll1_out", };
+
+static const char * const imx8mp_can1_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+						"sys_pll1_160m", "sys_pll1_800m", "sys_pll3_out",
+						"sys_pll2_250m", "audio_pll2_out", };
+
+static const char * const imx8mp_can2_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+						"sys_pll1_160m", "sys_pll1_800m", "sys_pll3_out",
+						"sys_pll2_250m", "audio_pll2_out", };
+
+static const char * const imx8mp_memrepair_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						     "sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						     "audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_pcie_phy_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll2_500m",
+						    "clk_ext1", "clk_ext2", "clk_ext3",
+						    "clk_ext4", "sys_pll1_400m", };
+
+static const char * const imx8mp_pcie_aux_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll2_50m",
+						    "sys_pll3_out", "sys_pll2_100m", "sys_pll1_80m",
+						    "sys_pll1_160m", "sys_pll1_200m", };
+
+static const char * const imx8mp_i2c5_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						"sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						"audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_i2c6_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						"sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						"audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_sai1_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext1", "clk_ext2", };
+
+static const char * const imx8mp_sai2_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext2", "clk_ext3", };
+
+static const char * const imx8mp_sai3_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext3", "clk_ext4", };
+
+static const char * const imx8mp_sai4_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext1", "clk_ext2", };
+
+static const char * const imx8mp_sai5_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext2", "clk_ext3", };
+
+static const char * const imx8mp_sai6_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext3", "clk_ext4", };
+
+static const char * const imx8mp_enet_qos_sels[] = {"osc_24m", "sys_pll2_125m", "sys_pll2_50m",
+						    "sys_pll2_100m", "sys_pll1_160m", "audio_pll1_out",
+						    "video_pll1_out", "clk_ext4", };
+
+static const char * const imx8mp_enet_qos_timer_sels[] = {"osc_24m", "sys_pll2_100m", "audio_pll1_out",
+							  "clk_ext1", "clk_ext2", "clk_ext3",
+							  "clk_ext4", "video_pll1_out", };
+
+static const char * const imx8mp_enet_ref_sels[] = {"osc_24m", "sys_pll2_125m", "sys_pll2_50m",
+						    "sys_pll2_100m", "sys_pll1_160m", "audio_pll1_out",
+						    "video_pll1_out", "clk_ext4", };
+
+static const char * const imx8mp_enet_timer_sels[] = {"osc_24m", "sys_pll2_100m", "audio_pll1_out",
+						      "clk_ext1", "clk_ext2", "clk_ext3",
+						      "clk_ext4", "video_pll1_out", };
+
+static const char * const imx8mp_enet_phy_ref_sels[] = {"osc_24m", "sys_pll2_50m", "sys_pll2_125m",
+							"sys_pll2_200m", "sys_pll2_500m", "audio_pll1_out",
+							"video_pll1_out", "audio_pll2_out", };
+
+static const char * const imx8mp_nand_sels[] = {"osc_24m", "sys_pll2_500m", "audio_pll1_out",
+						"sys_pll1_400m", "audio_pll2_out", "sys_pll3_out",
+						"sys_pll2_250m", "video_pll1_out", };
+
+static const char * const imx8mp_qspi_sels[] = {"osc_24m", "sys_pll1_400m", "sys_pll2_333m",
+						"sys_pll2_500m", "audio_pll2_out", "sys_pll1_266m",
+						"sys_pll3_out", "sys_pll1_100m", };
+
+static const char * const imx8mp_usdhc1_sels[] = {"osc_24m", "sys_pll1_400m", "sys_pll1_800m",
+						  "sys_pll2_500m", "sys_pll3_out", "sys_pll1_266m",
+						  "audio_pll2_out", "sys_pll1_100m", };
+
+static const char * const imx8mp_usdhc2_sels[] = {"osc_24m", "sys_pll1_400m", "sys_pll1_800m",
+						  "sys_pll2_500m", "sys_pll3_out", "sys_pll1_266m",
+						  "audio_pll2_out", "sys_pll1_100m", };
+
+static const char * const imx8mp_i2c1_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						"sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						"audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_i2c2_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						"sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						"audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_i2c3_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						"sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						"audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_i2c4_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						"sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						"audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_uart1_sels[] = {"osc_24m", "sys_pll1_80m", "sys_pll2_200m",
+						 "sys_pll2_100m", "sys_pll3_out", "clk_ext2",
+						 "clk_ext4", "audio_pll2_out", };
+
+static const char * const imx8mp_uart2_sels[] = {"osc_24m", "sys_pll1_80m", "sys_pll2_200m",
+						 "sys_pll2_100m", "sys_pll3_out", "clk_ext2",
+						 "clk_ext3", "audio_pll2_out", };
+
+static const char * const imx8mp_uart3_sels[] = {"osc_24m", "sys_pll1_80m", "sys_pll2_200m",
+						 "sys_pll2_100m", "sys_pll3_out", "clk_ext2",
+						 "clk_ext4", "audio_pll2_out", };
+
+static const char * const imx8mp_uart4_sels[] = {"osc_24m", "sys_pll1_80m", "sys_pll2_200m",
+						 "sys_pll2_100m", "sys_pll3_out", "clk_ext2",
+						 "clk_ext3", "audio_pll2_out", };
+
+static const char * const imx8mp_usb_core_ref_sels[] = {"osc_24m", "sys_pll1_100m", "sys_pll1_40m",
+							"sys_pll2_100m", "sys_pll2_200m", "clk_ext2",
+							"clk_ext3", "audio_pll2_out", };
+
+static const char * const imx8mp_usb_phy_ref_sels[] = {"osc_24m", "sys_pll1_100m", "sys_pll1_40m",
+						       "sys_pll2_100m", "sys_pll2_200m", "clk_ext2",
+						       "clk_ext3", "audio_pll2_out", };
+
+static const char * const imx8mp_gic_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+					       "sys_pll2_100m", "sys_pll1_800m",
+					       "sys_pll2_500m", "clk_ext4", "audio_pll2_out" };
+
+static const char * const imx8mp_ecspi1_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+						  "sys_pll1_160m", "sys_pll1_800m", "sys_pll3_out",
+						  "sys_pll2_250m", "audio_pll2_out", };
+
+static const char * const imx8mp_ecspi2_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+						  "sys_pll1_160m", "sys_pll1_800m", "sys_pll3_out",
+						  "sys_pll2_250m", "audio_pll2_out", };
+
+static const char * const imx8mp_pwm1_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_160m",
+						"sys_pll1_40m", "sys_pll3_out", "clk_ext1",
+						"sys_pll1_80m", "video_pll1_out", };
+
+static const char * const imx8mp_pwm2_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_160m",
+						"sys_pll1_40m", "sys_pll3_out", "clk_ext1",
+						"sys_pll1_80m", "video_pll1_out", };
+
+static const char * const imx8mp_pwm3_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_160m",
+						"sys_pll1_40m", "sys_pll3_out", "clk_ext2",
+						"sys_pll1_80m", "video_pll1_out", };
+
+static const char * const imx8mp_pwm4_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_160m",
+						"sys_pll1_40m", "sys_pll3_out", "clk_ext2",
+						"sys_pll1_80m", "video_pll1_out", };
+
+static const char * const imx8mp_gpt1_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_400m",
+						"sys_pll1_40m", "video_pll1_out", "sys_pll1_80m",
+						"audio_pll1_out", "clk_ext1" };
+
+static const char * const imx8mp_gpt2_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_400m",
+						"sys_pll1_40m", "video_pll1_out", "sys_pll1_80m",
+						"audio_pll1_out", "clk_ext2" };
+
+static const char * const imx8mp_gpt3_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_400m",
+						"sys_pll1_40m", "video_pll1_out", "sys_pll1_80m",
+						"audio_pll1_out", "clk_ext3" };
+
+static const char * const imx8mp_gpt4_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_400m",
+						"sys_pll1_40m", "video_pll1_out", "sys_pll1_80m",
+						"audio_pll1_out", "clk_ext1" };
+
+static const char * const imx8mp_gpt5_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_400m",
+						"sys_pll1_40m", "video_pll1_out", "sys_pll1_80m",
+						"audio_pll1_out", "clk_ext2" };
+
+static const char * const imx8mp_gpt6_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_400m",
+						"sys_pll1_40m", "video_pll1_out", "sys_pll1_80m",
+						"audio_pll1_out", "clk_ext3" };
+
+static const char * const imx8mp_wdog_sels[] = {"osc_24m", "sys_pll1_133m", "sys_pll1_160m",
+						"vpu_pll_out", "sys_pll2_125m", "sys_pll3_out",
+						"sys_pll1_80m", "sys_pll2_166m" };
+
+static const char * const imx8mp_wrclk_sels[] = {"osc_24m", "sys_pll1_40m", "vpu_pll_out",
+						 "sys_pll3_out", "sys_pll2_200m", "sys_pll1_266m",
+						 "sys_pll2_500m", "sys_pll1_100m" };
+
+static const char * const imx8mp_ipp_do_clko1_sels[] = {"osc_24m", "sys_pll1_800m", "sys_pll1_133m",
+							"sys_pll1_200m", "audio_pll2_out", "sys_pll2_500m",
+							"vpu_pll_out", "sys_pll1_80m" };
+
+static const char * const imx8mp_ipp_do_clko2_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_400m",
+							"sys_pll1_166m", "sys_pll3_out", "audio_pll1_out",
+							"video_pll1_out", "osc_32k" };
+
+static const char * const imx8mp_hdmi_fdcc_tst_sels[] = {"osc_24m", "sys_pll1_266m", "sys_pll2_250m",
+							 "sys_pll1_800m", "sys_pll2_1000m", "sys_pll3_out",
+							 "audio_pll2_out", "video_pll1_out", };
+
+static const char * const imx8mp_hdmi_27m_sels[] = {"osc_24m", "sys_pll1_160m", "sys_pll2_50m",
+						    "sys_pll3_out", "audio_pll1_out", "video_pll1_out",
+						    "audio_pll2_out", "sys_pll1_133m", };
+
+static const char * const imx8mp_hdmi_ref_266m_sels[] = {"osc_24m", "sys_pll1_400m", "sys_pll3_out",
+							 "sys_pll2_333m", "sys_pll1_266m", "sys_pll2_200m",
+							 "audio_pll1_out", "video_pll1_out", };
+
+static const char * const imx8mp_usdhc3_sels[] = {"osc_24m", "sys_pll1_400m", "sys_pll1_800m",
+						  "sys_pll2_500m", "sys_pll3_out", "sys_pll1_266m",
+						  "audio_pll2_out", "sys_pll1_100m", };
+
+static const char * const imx8mp_media_cam1_pix_sels[] = {"osc_24m", "sys_pll1_266m", "sys_pll2_250m",
+							  "sys_pll1_800m", "sys_pll2_1000m",
+							  "sys_pll3_out", "audio_pll2_out",
+							  "video_pll1_out", };
+
+static const char * const imx8mp_media_mipi_phy1_ref_sels[] = {"osc_24m", "sys_pll2_333m", "sys_pll2_100m",
+							       "sys_pll1_800m", "sys_pll2_1000m",
+							       "clk_ext2", "audio_pll2_out",
+							       "video_pll1_out", };
+
+static const char * const imx8mp_media_disp1_pix_sels[] = {"osc_24m", "video_pll1_out", "audio_pll2_out",
+							   "audio_pll1_out", "sys_pll1_800m",
+							   "sys_pll2_1000m", "sys_pll3_out", "clk_ext4", };
+
+static const char * const imx8mp_media_cam2_pix_sels[] = {"osc_24m", "sys_pll1_266m", "sys_pll2_250m",
+							  "sys_pll1_800m", "sys_pll2_1000m",
+							  "sys_pll3_out", "audio_pll2_out",
+							  "video_pll1_out", };
+
+static const char * const imx8mp_media_mipi_phy2_ref_sels[] = {"osc_24m", "sys_pll2_333m", "sys_pll2_100m",
+							       "sys_pll1_800m", "sys_pll2_1000m",
+							       "clk_ext2", "audio_pll2_out",
+							       "video_pll1_out", };
+
+static const char * const imx8mp_media_mipi_csi2_esc_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll1_80m",
+							       "sys_pll1_800m", "sys_pll2_1000m",
+							       "sys_pll3_out", "clk_ext3",
+							       "audio_pll2_out", };
+
+static const char * const imx8mp_pcie2_ctrl_sels[] = {"osc_24m", "sys_pll2_250m", "sys_pll2_200m",
+						      "sys_pll1_266m", "sys_pll1_800m", "sys_pll2_500m",
+						      "sys_pll2_333m", "sys_pll3_out", };
+
+static const char * const imx8mp_pcie2_phy_sels[] = {"osc_24m", "sys_pll2_100m", "sys_pll2_500m",
+						     "clk_ext1", "clk_ext2", "clk_ext3",
+						     "clk_ext4", "sys_pll1_400m", };
+
+static const char * const imx8mp_media_mipi_test_byte_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll2_50m",
+								"sys_pll3_out", "sys_pll2_100m",
+								"sys_pll1_80m", "sys_pll1_160m",
+								"sys_pll1_200m", };
+
+static const char * const imx8mp_ecspi3_sels[] = {"osc_24m", "sys_pll2_200m", "sys_pll1_40m",
+						  "sys_pll1_160m", "sys_pll1_800m", "sys_pll3_out",
+						  "sys_pll2_250m", "audio_pll2_out", };
+
+static const char * const imx8mp_pdm_sels[] = {"osc_24m", "sys_pll2_100m", "audio_pll1_out",
+					       "sys_pll1_800m", "sys_pll2_1000m", "sys_pll3_out",
+					       "clk_ext3", "audio_pll2_out", };
+
+static const char * const imx8mp_vpu_vc8000e_sels[] = {"osc_24m", "vpu_pll_out", "sys_pll1_800m",
+						       "sys_pll2_1000m", "audio_pll2_out", "sys_pll2_125m",
+						       "sys_pll3_out", "audio_pll1_out", };
+
+static const char * const imx8mp_sai7_sels[] = {"osc_24m", "audio_pll1_out", "audio_pll2_out",
+						"video_pll1_out", "sys_pll1_133m", "osc_hdmi",
+						"clk_ext3", "clk_ext4", };
+
+static const char * const imx8mp_dram_core_sels[] = {"dram_pll_out", "dram_alt_root", };
+
+static struct clk_hw **hws;
+static struct clk_hw_onecell_data *clk_hw_data;
+
+static const int uart_clk_ids[] = {
+	IMX8MP_CLK_UART1_ROOT,
+	IMX8MP_CLK_UART2_ROOT,
+	IMX8MP_CLK_UART3_ROOT,
+	IMX8MP_CLK_UART4_ROOT,
+};
+static struct clk **uart_clks[ARRAY_SIZE(uart_clk_ids) + 1];
+
+static int imx8mp_clocks_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	void __iomem *anatop_base, *ccm_base;
+	int i;
+
+	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mp-anatop");
+	anatop_base = of_iomap(np, 0);
+	if (WARN_ON(!anatop_base))
+		return -ENOMEM;
+
+	np = dev->of_node;
+	ccm_base = devm_platform_ioremap_resource(pdev, 0);
+	if (WARN_ON(IS_ERR(ccm_base))) {
+		iounmap(anatop_base);
+		return PTR_ERR(ccm_base);
+	}
+
+	clk_hw_data = kzalloc(struct_size(clk_hw_data, hws, IMX8MP_CLK_END), GFP_KERNEL);
+	if (WARN_ON(!clk_hw_data)) {
+		iounmap(anatop_base);
+		return -ENOMEM;
+	}
+
+	clk_hw_data->num = IMX8MP_CLK_END;
+	hws = clk_hw_data->hws;
+
+	hws[IMX8MP_CLK_DUMMY] = imx_clk_hw_fixed("dummy", 0);
+	hws[IMX8MP_CLK_24M] = imx_obtain_fixed_clk_hw(np, "osc_24m");
+	hws[IMX8MP_CLK_32K] = imx_obtain_fixed_clk_hw(np, "osc_32k");
+	hws[IMX8MP_CLK_EXT1] = imx_obtain_fixed_clk_hw(np, "clk_ext1");
+	hws[IMX8MP_CLK_EXT2] = imx_obtain_fixed_clk_hw(np, "clk_ext2");
+	hws[IMX8MP_CLK_EXT3] = imx_obtain_fixed_clk_hw(np, "clk_ext3");
+	hws[IMX8MP_CLK_EXT4] = imx_obtain_fixed_clk_hw(np, "clk_ext4");
+
+	hws[IMX8MP_AUDIO_PLL1_REF_SEL] = imx_clk_hw_mux("audio_pll1_ref_sel", anatop_base + 0x0, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_AUDIO_PLL2_REF_SEL] = imx_clk_hw_mux("audio_pll2_ref_sel", anatop_base + 0x14, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_VIDEO_PLL1_REF_SEL] = imx_clk_hw_mux("video_pll1_ref_sel", anatop_base + 0x28, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_DRAM_PLL_REF_SEL] = imx_clk_hw_mux("dram_pll_ref_sel", anatop_base + 0x50, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_GPU_PLL_REF_SEL] = imx_clk_hw_mux("gpu_pll_ref_sel", anatop_base + 0x64, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_VPU_PLL_REF_SEL] = imx_clk_hw_mux("vpu_pll_ref_sel", anatop_base + 0x74, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_ARM_PLL_REF_SEL] = imx_clk_hw_mux("arm_pll_ref_sel", anatop_base + 0x84, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_SYS_PLL1_REF_SEL] = imx_clk_hw_mux("sys_pll1_ref_sel", anatop_base + 0x94, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_SYS_PLL2_REF_SEL] = imx_clk_hw_mux("sys_pll2_ref_sel", anatop_base + 0x104, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MP_SYS_PLL3_REF_SEL] = imx_clk_hw_mux("sys_pll3_ref_sel", anatop_base + 0x114, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+
+	hws[IMX8MP_AUDIO_PLL1] = imx_clk_hw_pll14xx("audio_pll1", "audio_pll1_ref_sel", anatop_base, &imx_1443x_pll);
+	hws[IMX8MP_AUDIO_PLL2] = imx_clk_hw_pll14xx("audio_pll2", "audio_pll2_ref_sel", anatop_base + 0x14, &imx_1443x_pll);
+	hws[IMX8MP_VIDEO_PLL1] = imx_clk_hw_pll14xx("video_pll1", "video_pll1_ref_sel", anatop_base + 0x28, &imx_1443x_pll);
+	hws[IMX8MP_DRAM_PLL] = imx_clk_hw_pll14xx("dram_pll", "dram_pll_ref_sel", anatop_base + 0x50, &imx_1443x_dram_pll);
+	hws[IMX8MP_GPU_PLL] = imx_clk_hw_pll14xx("gpu_pll", "gpu_pll_ref_sel", anatop_base + 0x64, &imx_1416x_pll);
+	hws[IMX8MP_VPU_PLL] = imx_clk_hw_pll14xx("vpu_pll", "vpu_pll_ref_sel", anatop_base + 0x74, &imx_1416x_pll);
+	hws[IMX8MP_ARM_PLL] = imx_clk_hw_pll14xx("arm_pll", "arm_pll_ref_sel", anatop_base + 0x84, &imx_1416x_pll);
+	hws[IMX8MP_SYS_PLL1] = imx_clk_hw_pll14xx("sys_pll1", "sys_pll1_ref_sel", anatop_base + 0x94, &imx_1416x_pll);
+	hws[IMX8MP_SYS_PLL2] = imx_clk_hw_pll14xx("sys_pll2", "sys_pll2_ref_sel", anatop_base + 0x104, &imx_1416x_pll);
+	hws[IMX8MP_SYS_PLL3] = imx_clk_hw_pll14xx("sys_pll3", "sys_pll3_ref_sel", anatop_base + 0x114, &imx_1416x_pll);
+
+	hws[IMX8MP_AUDIO_PLL1_BYPASS] = imx_clk_hw_mux_flags("audio_pll1_bypass", anatop_base, 4, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_AUDIO_PLL2_BYPASS] = imx_clk_hw_mux_flags("audio_pll2_bypass", anatop_base + 0x14, 4, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_VIDEO_PLL1_BYPASS] = imx_clk_hw_mux_flags("video_pll1_bypass", anatop_base + 0x28, 4, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_DRAM_PLL_BYPASS] = imx_clk_hw_mux_flags("dram_pll_bypass", anatop_base + 0x50, 4, 1, dram_pll_bypass_sels, ARRAY_SIZE(dram_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_GPU_PLL_BYPASS] = imx_clk_hw_mux_flags("gpu_pll_bypass", anatop_base + 0x64, 4, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_VPU_PLL_BYPASS] = imx_clk_hw_mux_flags("vpu_pll_bypass", anatop_base + 0x74, 4, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_ARM_PLL_BYPASS] = imx_clk_hw_mux_flags("arm_pll_bypass", anatop_base + 0x84, 4, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_SYS_PLL1_BYPASS] = imx_clk_hw_mux_flags("sys_pll1_bypass", anatop_base + 0x94, 4, 1, sys_pll1_bypass_sels, ARRAY_SIZE(sys_pll1_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_SYS_PLL2_BYPASS] = imx_clk_hw_mux_flags("sys_pll2_bypass", anatop_base + 0x104, 4, 1, sys_pll2_bypass_sels, ARRAY_SIZE(sys_pll2_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MP_SYS_PLL3_BYPASS] = imx_clk_hw_mux_flags("sys_pll3_bypass", anatop_base + 0x114, 4, 1, sys_pll3_bypass_sels, ARRAY_SIZE(sys_pll3_bypass_sels), CLK_SET_RATE_PARENT);
+
+	hws[IMX8MP_AUDIO_PLL1_OUT] = imx_clk_hw_gate("audio_pll1_out", "audio_pll1_bypass", anatop_base, 13);
+	hws[IMX8MP_AUDIO_PLL2_OUT] = imx_clk_hw_gate("audio_pll2_out", "audio_pll2_bypass", anatop_base + 0x14, 13);
+	hws[IMX8MP_VIDEO_PLL1_OUT] = imx_clk_hw_gate("video_pll1_out", "video_pll1_bypass", anatop_base + 0x28, 13);
+	hws[IMX8MP_DRAM_PLL_OUT] = imx_clk_hw_gate("dram_pll_out", "dram_pll_bypass", anatop_base + 0x50, 13);
+	hws[IMX8MP_GPU_PLL_OUT] = imx_clk_hw_gate("gpu_pll_out", "gpu_pll_bypass", anatop_base + 0x64, 11);
+	hws[IMX8MP_VPU_PLL_OUT] = imx_clk_hw_gate("vpu_pll_out", "vpu_pll_bypass", anatop_base + 0x74, 11);
+	hws[IMX8MP_ARM_PLL_OUT] = imx_clk_hw_gate("arm_pll_out", "arm_pll_bypass", anatop_base + 0x84, 11);
+	hws[IMX8MP_SYS_PLL1_OUT] = imx_clk_hw_gate("sys_pll1_out", "sys_pll1_bypass", anatop_base + 0x94, 11);
+	hws[IMX8MP_SYS_PLL2_OUT] = imx_clk_hw_gate("sys_pll2_out", "sys_pll2_bypass", anatop_base + 0x104, 11);
+	hws[IMX8MP_SYS_PLL3_OUT] = imx_clk_hw_gate("sys_pll3_out", "sys_pll3_bypass", anatop_base + 0x114, 11);
+
+	hws[IMX8MP_SYS_PLL1_40M] = imx_clk_hw_fixed_factor("sys_pll1_40m", "sys_pll1_out", 1, 20);
+	hws[IMX8MP_SYS_PLL1_80M] = imx_clk_hw_fixed_factor("sys_pll1_80m", "sys_pll1_out", 1, 10);
+	hws[IMX8MP_SYS_PLL1_100M] = imx_clk_hw_fixed_factor("sys_pll1_100m", "sys_pll1_out", 1, 8);
+	hws[IMX8MP_SYS_PLL1_133M] = imx_clk_hw_fixed_factor("sys_pll1_133m", "sys_pll1_out", 1, 6);
+	hws[IMX8MP_SYS_PLL1_160M] = imx_clk_hw_fixed_factor("sys_pll1_160m", "sys_pll1_out", 1, 5);
+	hws[IMX8MP_SYS_PLL1_200M] = imx_clk_hw_fixed_factor("sys_pll1_200m", "sys_pll1_out", 1, 4);
+	hws[IMX8MP_SYS_PLL1_266M] = imx_clk_hw_fixed_factor("sys_pll1_266m", "sys_pll1_out", 1, 3);
+	hws[IMX8MP_SYS_PLL1_400M] = imx_clk_hw_fixed_factor("sys_pll1_400m", "sys_pll1_out", 1, 2);
+	hws[IMX8MP_SYS_PLL1_800M] = imx_clk_hw_fixed_factor("sys_pll1_800m", "sys_pll1_out", 1, 1);
+
+	hws[IMX8MP_SYS_PLL2_50M] = imx_clk_hw_fixed_factor("sys_pll2_50m", "sys_pll2_out", 1, 20);
+	hws[IMX8MP_SYS_PLL2_100M] = imx_clk_hw_fixed_factor("sys_pll2_100m", "sys_pll2_out", 1, 10);
+	hws[IMX8MP_SYS_PLL2_125M] = imx_clk_hw_fixed_factor("sys_pll2_125m", "sys_pll2_out", 1, 8);
+	hws[IMX8MP_SYS_PLL2_166M] = imx_clk_hw_fixed_factor("sys_pll2_166m", "sys_pll2_out", 1, 6);
+	hws[IMX8MP_SYS_PLL2_200M] = imx_clk_hw_fixed_factor("sys_pll2_200m", "sys_pll2_out", 1, 5);
+	hws[IMX8MP_SYS_PLL2_250M] = imx_clk_hw_fixed_factor("sys_pll2_250m", "sys_pll2_out", 1, 4);
+	hws[IMX8MP_SYS_PLL2_333M] = imx_clk_hw_fixed_factor("sys_pll2_333m", "sys_pll2_out", 1, 3);
+	hws[IMX8MP_SYS_PLL2_500M] = imx_clk_hw_fixed_factor("sys_pll2_500m", "sys_pll2_out", 1, 2);
+	hws[IMX8MP_SYS_PLL2_1000M] = imx_clk_hw_fixed_factor("sys_pll2_1000m", "sys_pll2_out", 1, 1);
+
+	hws[IMX8MP_CLK_A53_SRC] = imx_clk_hw_mux2("arm_a53_src", ccm_base + 0x8000, 24, 3, imx8mp_a53_sels, ARRAY_SIZE(imx8mp_a53_sels));
+	hws[IMX8MP_CLK_M7_SRC] = imx_clk_hw_mux2("arm_m7_src", ccm_base + 0x8080, 24, 3, imx8mp_m7_sels, ARRAY_SIZE(imx8mp_m7_sels));
+	hws[IMX8MP_CLK_ML_SRC] = imx_clk_hw_mux2("ml_src", ccm_base + 0x8100, 24, 3, imx8mp_ml_sels, ARRAY_SIZE(imx8mp_ml_sels));
+	hws[IMX8MP_CLK_GPU3D_CORE_SRC] = imx_clk_hw_mux2("gpu3d_core_src", ccm_base + 0x8180, 24, 3,  imx8mp_gpu3d_core_sels, ARRAY_SIZE(imx8mp_gpu3d_core_sels));
+	hws[IMX8MP_CLK_GPU3D_SHADER_SRC] = imx_clk_hw_mux2("gpu3d_shader_src", ccm_base + 0x8200, 24, 3, imx8mp_gpu3d_shader_sels, ARRAY_SIZE(imx8mp_gpu3d_shader_sels));
+	hws[IMX8MP_CLK_GPU2D_SRC] = imx_clk_hw_mux2("gpu2d_src", ccm_base + 0x8280, 24, 3, imx8mp_gpu2d_sels, ARRAY_SIZE(imx8mp_gpu2d_sels));
+	hws[IMX8MP_CLK_AUDIO_AXI_SRC] = imx_clk_hw_mux2("audio_axi_src", ccm_base + 0x8300, 24, 3, imx8mp_audio_axi_sels, ARRAY_SIZE(imx8mp_audio_axi_sels));
+	hws[IMX8MP_CLK_HSIO_AXI_SRC] = imx_clk_hw_mux2("hsio_axi_src", ccm_base + 0x8380, 24, 3, imx8mp_hsio_axi_sels, ARRAY_SIZE(imx8mp_hsio_axi_sels));
+	hws[IMX8MP_CLK_MEDIA_ISP_SRC] = imx_clk_hw_mux2("media_isp_src", ccm_base + 0x8400, 24, 3, imx8mp_media_isp_sels, ARRAY_SIZE(imx8mp_media_isp_sels));
+	hws[IMX8MP_CLK_A53_CG] = imx_clk_hw_gate3("arm_a53_cg", "arm_a53_src", ccm_base + 0x8000, 28);
+	hws[IMX8MP_CLK_M4_CG] = imx_clk_hw_gate3("arm_m7_cg", "arm_m7_src", ccm_base + 0x8080, 28);
+	hws[IMX8MP_CLK_ML_CG] = imx_clk_hw_gate3("ml_cg", "ml_src", ccm_base + 0x8100, 28);
+	hws[IMX8MP_CLK_GPU3D_CORE_CG] = imx_clk_hw_gate3("gpu3d_core_cg", "gpu3d_core_src", ccm_base + 0x8180, 28);
+	hws[IMX8MP_CLK_GPU3D_SHADER_CG] = imx_clk_hw_gate3("gpu3d_shader_cg", "gpu3d_shader_src", ccm_base + 0x8200, 28);
+	hws[IMX8MP_CLK_GPU2D_CG] = imx_clk_hw_gate3("gpu2d_cg", "gpu2d_src", ccm_base + 0x8280, 28);
+	hws[IMX8MP_CLK_AUDIO_AXI_CG] = imx_clk_hw_gate3("audio_axi_cg", "audio_axi_src", ccm_base + 0x8300, 28);
+	hws[IMX8MP_CLK_HSIO_AXI_CG] = imx_clk_hw_gate3("hsio_axi_cg", "hsio_axi_src", ccm_base + 0x8380, 28);
+	hws[IMX8MP_CLK_MEDIA_ISP_CG] = imx_clk_hw_gate3("media_isp_cg", "media_isp_src", ccm_base + 0x8400, 28);
+	hws[IMX8MP_CLK_A53_DIV] = imx_clk_hw_divider2("arm_a53_div", "arm_a53_cg", ccm_base + 0x8000, 0, 3);
+	hws[IMX8MP_CLK_M7_DIV] = imx_clk_hw_divider2("arm_m7_div", "arm_m7_cg", ccm_base + 0x8080, 0, 3);
+	hws[IMX8MP_CLK_ML_DIV] = imx_clk_hw_divider2("ml_div", "ml_cg", ccm_base + 0x8100, 0, 3);
+	hws[IMX8MP_CLK_GPU3D_CORE_DIV] = imx_clk_hw_divider2("gpu3d_core_div", "gpu3d_core_cg", ccm_base + 0x8180, 0, 3);
+	hws[IMX8MP_CLK_GPU3D_SHADER_DIV] = imx_clk_hw_divider2("gpu3d_shader_div", "gpu3d_shader_cg", ccm_base + 0x8200, 0, 3);
+	hws[IMX8MP_CLK_GPU2D_DIV] = imx_clk_hw_divider2("gpu2d_div", "gpu2d_cg", ccm_base + 0x8280, 0, 3);
+	hws[IMX8MP_CLK_AUDIO_AXI_DIV] = imx_clk_hw_divider2("audio_axi_div", "audio_axi_cg", ccm_base + 0x8300, 0, 3);
+	hws[IMX8MP_CLK_HSIO_AXI_DIV] = imx_clk_hw_divider2("hsio_axi_div", "hsio_axi_cg", ccm_base + 0x8380, 0, 3);
+	hws[IMX8MP_CLK_MEDIA_ISP_DIV] = imx_clk_hw_divider2("media_isp_div", "media_isp_cg", ccm_base + 0x8400, 0, 3);
+
+	hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800);
+	hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880);
+	hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900);
+	hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980);
+	hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00);
+	hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80);
+	hws[IMX8MP_CLK_HDMI_APB] = imx8m_clk_hw_composite("hdmi_apb", imx8mp_media_apb_sels, ccm_base + 0x8b00);
+	hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite("hdmi_axi", imx8mp_media_apb_sels, ccm_base + 0x8b80);
+	hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00);
+	hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80);
+	hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00);
+	hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80);
+	hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00);
+	hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80);
+
+	hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000);
+	hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100);
+	hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200);
+
+	hws[IMX8MP_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb_root", ccm_base + 0x9080, 0, 1);
+	hws[IMX8MP_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", ccm_base + 0x9180, 0, 1);
+
+	hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000);
+	hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080);
+	hws[IMX8MP_CLK_VPU_G1] = imx8m_clk_hw_composite("vpu_g1", imx8mp_vpu_g1_sels, ccm_base + 0xa100);
+	hws[IMX8MP_CLK_VPU_G2] = imx8m_clk_hw_composite("vpu_g2", imx8mp_vpu_g2_sels, ccm_base + 0xa180);
+	hws[IMX8MP_CLK_CAN1] = imx8m_clk_hw_composite("can1", imx8mp_can1_sels, ccm_base + 0xa200);
+	hws[IMX8MP_CLK_CAN2] = imx8m_clk_hw_composite("can2", imx8mp_can2_sels, ccm_base + 0xa280);
+	hws[IMX8MP_CLK_MEMREPAIR] = imx8m_clk_hw_composite("memrepair", imx8mp_memrepair_sels, ccm_base + 0xa300);
+	hws[IMX8MP_CLK_PCIE_PHY] = imx8m_clk_hw_composite("pcie_phy", imx8mp_pcie_phy_sels, ccm_base + 0xa380);
+	hws[IMX8MP_CLK_PCIE_AUX] = imx8m_clk_hw_composite("pcie_aux", imx8mp_pcie_aux_sels, ccm_base + 0xa400);
+	hws[IMX8MP_CLK_I2C5] = imx8m_clk_hw_composite("i2c5", imx8mp_i2c5_sels, ccm_base + 0xa480);
+	hws[IMX8MP_CLK_I2C6] = imx8m_clk_hw_composite("i2c6", imx8mp_i2c6_sels, ccm_base + 0xa500);
+	hws[IMX8MP_CLK_SAI1] = imx8m_clk_hw_composite("sai1", imx8mp_sai1_sels, ccm_base + 0xa580);
+	hws[IMX8MP_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mp_sai2_sels, ccm_base + 0xa600);
+	hws[IMX8MP_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mp_sai3_sels, ccm_base + 0xa680);
+	hws[IMX8MP_CLK_SAI4] = imx8m_clk_hw_composite("sai4", imx8mp_sai4_sels, ccm_base + 0xa700);
+	hws[IMX8MP_CLK_SAI5] = imx8m_clk_hw_composite("sai5", imx8mp_sai5_sels, ccm_base + 0xa780);
+	hws[IMX8MP_CLK_SAI6] = imx8m_clk_hw_composite("sai6", imx8mp_sai6_sels, ccm_base + 0xa800);
+	hws[IMX8MP_CLK_ENET_QOS] = imx8m_clk_hw_composite("enet_qos", imx8mp_enet_qos_sels, ccm_base + 0xa880);
+	hws[IMX8MP_CLK_ENET_QOS_TIMER] = imx8m_clk_hw_composite("enet_qos_timer", imx8mp_enet_qos_timer_sels, ccm_base + 0xa900);
+	hws[IMX8MP_CLK_ENET_REF] = imx8m_clk_hw_composite("enet_ref", imx8mp_enet_ref_sels, ccm_base + 0xa980);
+	hws[IMX8MP_CLK_ENET_TIMER] = imx8m_clk_hw_composite("enet_timer", imx8mp_enet_timer_sels, ccm_base + 0xaa00);
+	hws[IMX8MP_CLK_ENET_PHY_REF] = imx8m_clk_hw_composite("enet_phy_ref", imx8mp_enet_phy_ref_sels, ccm_base + 0xaa80);
+	hws[IMX8MP_CLK_NAND] = imx8m_clk_hw_composite("nand", imx8mp_nand_sels, ccm_base + 0xab00);
+	hws[IMX8MP_CLK_QSPI] = imx8m_clk_hw_composite("qspi", imx8mp_qspi_sels, ccm_base + 0xab80);
+	hws[IMX8MP_CLK_USDHC1] = imx8m_clk_hw_composite("usdhc1", imx8mp_usdhc1_sels, ccm_base + 0xac00);
+	hws[IMX8MP_CLK_USDHC2] = imx8m_clk_hw_composite("usdhc2", imx8mp_usdhc2_sels, ccm_base + 0xac80);
+	hws[IMX8MP_CLK_I2C1] = imx8m_clk_hw_composite("i2c1", imx8mp_i2c1_sels, ccm_base + 0xad00);
+	hws[IMX8MP_CLK_I2C2] = imx8m_clk_hw_composite("i2c2", imx8mp_i2c2_sels, ccm_base + 0xad80);
+	hws[IMX8MP_CLK_I2C3] = imx8m_clk_hw_composite("i2c3", imx8mp_i2c3_sels, ccm_base + 0xae00);
+	hws[IMX8MP_CLK_I2C4] = imx8m_clk_hw_composite("i2c4", imx8mp_i2c4_sels, ccm_base + 0xae80);
+
+	hws[IMX8MP_CLK_UART1] = imx8m_clk_hw_composite("uart1", imx8mp_uart1_sels, ccm_base + 0xaf00);
+	hws[IMX8MP_CLK_UART2] = imx8m_clk_hw_composite("uart2", imx8mp_uart2_sels, ccm_base + 0xaf80);
+	hws[IMX8MP_CLK_UART3] = imx8m_clk_hw_composite("uart3", imx8mp_uart3_sels, ccm_base + 0xb000);
+	hws[IMX8MP_CLK_UART4] = imx8m_clk_hw_composite("uart4", imx8mp_uart4_sels, ccm_base + 0xb080);
+	hws[IMX8MP_CLK_USB_CORE_REF] = imx8m_clk_hw_composite("usb_core_ref", imx8mp_usb_core_ref_sels, ccm_base + 0xb100);
+	hws[IMX8MP_CLK_USB_PHY_REF] = imx8m_clk_hw_composite("usb_phy_ref", imx8mp_usb_phy_ref_sels, ccm_base + 0xb180);
+	hws[IMX8MP_CLK_GIC] = imx8m_clk_hw_composite_critical("gic", imx8mp_gic_sels, ccm_base + 0xb200);
+	hws[IMX8MP_CLK_ECSPI1] = imx8m_clk_hw_composite("ecspi1", imx8mp_ecspi1_sels, ccm_base + 0xb280);
+	hws[IMX8MP_CLK_ECSPI2] = imx8m_clk_hw_composite("ecspi2", imx8mp_ecspi2_sels, ccm_base + 0xb300);
+	hws[IMX8MP_CLK_PWM1] = imx8m_clk_hw_composite("pwm1", imx8mp_pwm1_sels, ccm_base + 0xb380);
+	hws[IMX8MP_CLK_PWM2] = imx8m_clk_hw_composite("pwm2", imx8mp_pwm2_sels, ccm_base + 0xb400);
+	hws[IMX8MP_CLK_PWM3] = imx8m_clk_hw_composite("pwm3", imx8mp_pwm3_sels, ccm_base + 0xb480);
+	hws[IMX8MP_CLK_PWM4] = imx8m_clk_hw_composite("pwm4", imx8mp_pwm4_sels, ccm_base + 0xb500);
+
+	hws[IMX8MP_CLK_GPT1] = imx8m_clk_hw_composite("gpt1", imx8mp_gpt1_sels, ccm_base + 0xb580);
+	hws[IMX8MP_CLK_GPT2] = imx8m_clk_hw_composite("gpt2", imx8mp_gpt2_sels, ccm_base + 0xb600);
+	hws[IMX8MP_CLK_GPT3] = imx8m_clk_hw_composite("gpt3", imx8mp_gpt3_sels, ccm_base + 0xb680);
+	hws[IMX8MP_CLK_GPT4] = imx8m_clk_hw_composite("gpt4", imx8mp_gpt4_sels, ccm_base + 0xb700);
+	hws[IMX8MP_CLK_GPT5] = imx8m_clk_hw_composite("gpt5", imx8mp_gpt5_sels, ccm_base + 0xb780);
+	hws[IMX8MP_CLK_GPT6] = imx8m_clk_hw_composite("gpt6", imx8mp_gpt6_sels, ccm_base + 0xb800);
+	hws[IMX8MP_CLK_WDOG] = imx8m_clk_hw_composite("wdog", imx8mp_wdog_sels, ccm_base + 0xb900);
+	hws[IMX8MP_CLK_WRCLK] = imx8m_clk_hw_composite("wrclk", imx8mp_wrclk_sels, ccm_base + 0xb980);
+	hws[IMX8MP_CLK_IPP_DO_CLKO1] = imx8m_clk_hw_composite("ipp_do_clko1", imx8mp_ipp_do_clko1_sels, ccm_base + 0xba00);
+	hws[IMX8MP_CLK_IPP_DO_CLKO2] = imx8m_clk_hw_composite("ipp_do_clko2", imx8mp_ipp_do_clko2_sels, ccm_base + 0xba80);
+	hws[IMX8MP_CLK_HDMI_FDCC_TST] = imx8m_clk_hw_composite("hdmi_fdcc_tst", imx8mp_hdmi_fdcc_tst_sels, ccm_base + 0xbb00);
+	hws[IMX8MP_CLK_HDMI_27M] = imx8m_clk_hw_composite("hdmi_27m", imx8mp_hdmi_27m_sels, ccm_base + 0xbb80);
+	hws[IMX8MP_CLK_HDMI_REF_266M] = imx8m_clk_hw_composite("hdmi_ref_266m", imx8mp_hdmi_ref_266m_sels, ccm_base + 0xbc00);
+	hws[IMX8MP_CLK_USDHC3] = imx8m_clk_hw_composite("usdhc3", imx8mp_usdhc3_sels, ccm_base + 0xbc80);
+	hws[IMX8MP_CLK_MEDIA_CAM1_PIX] = imx8m_clk_hw_composite("media_cam1_pix", imx8mp_media_cam1_pix_sels, ccm_base + 0xbd00);
+	hws[IMX8MP_CLK_MEDIA_MIPI_PHY1_REF] = imx8m_clk_hw_composite("media_mipi_phy1_ref", imx8mp_media_mipi_phy1_ref_sels, ccm_base + 0xbd80);
+	hws[IMX8MP_CLK_MEDIA_DISP1_PIX] = imx8m_clk_hw_composite("media_disp1_pix", imx8mp_media_disp1_pix_sels, ccm_base + 0xbe00);
+	hws[IMX8MP_CLK_MEDIA_CAM2_PIX] = imx8m_clk_hw_composite("media_cam2_pix", imx8mp_media_cam2_pix_sels, ccm_base + 0xbe80);
+	hws[IMX8MP_CLK_MEDIA_MIPI_PHY2_REF] = imx8m_clk_hw_composite("media_mipi_phy2_ref", imx8mp_media_mipi_phy2_ref_sels, ccm_base + 0xbf00);
+	hws[IMX8MP_CLK_MEDIA_MIPI_CSI2_ESC] = imx8m_clk_hw_composite("media_mipi_csi2_esc", imx8mp_media_mipi_csi2_esc_sels, ccm_base + 0xbf80);
+	hws[IMX8MP_CLK_PCIE2_CTRL] = imx8m_clk_hw_composite("pcie2_ctrl", imx8mp_pcie2_ctrl_sels, ccm_base + 0xc000);
+	hws[IMX8MP_CLK_PCIE2_PHY] = imx8m_clk_hw_composite("pcie2_phy", imx8mp_pcie2_phy_sels, ccm_base + 0xc080);
+	hws[IMX8MP_CLK_MEDIA_MIPI_TEST_BYTE] = imx8m_clk_hw_composite("media_mipi_test_byte", imx8mp_media_mipi_test_byte_sels, ccm_base + 0xc100);
+	hws[IMX8MP_CLK_ECSPI3] = imx8m_clk_hw_composite("ecspi3", imx8mp_ecspi3_sels, ccm_base + 0xc180);
+	hws[IMX8MP_CLK_PDM] = imx8m_clk_hw_composite("pdm", imx8mp_pdm_sels, ccm_base + 0xc200);
+	hws[IMX8MP_CLK_VPU_VC8000E] = imx8m_clk_hw_composite("vpu_vc8000e", imx8mp_vpu_vc8000e_sels, ccm_base + 0xc280);
+	hws[IMX8MP_CLK_SAI7] = imx8m_clk_hw_composite("sai7", imx8mp_sai7_sels, ccm_base + 0xc300);
+
+	hws[IMX8MP_CLK_DRAM_ALT_ROOT] = imx_clk_hw_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
+	hws[IMX8MP_CLK_DRAM_CORE] = imx_clk_hw_mux2_flags("dram_core_clk", ccm_base + 0x9800, 24, 1, imx8mp_dram_core_sels, ARRAY_SIZE(imx8mp_dram_core_sels), CLK_IS_CRITICAL);
+
+	hws[IMX8MP_CLK_DRAM1_ROOT] = imx_clk_hw_gate4_flags("dram1_root_clk", "dram_core_clk", ccm_base + 0x4050, 0, CLK_IS_CRITICAL);
+	hws[IMX8MP_CLK_ECSPI1_ROOT] = imx_clk_hw_gate4("ecspi1_root_clk", "ecspi1", ccm_base + 0x4070, 0);
+	hws[IMX8MP_CLK_ECSPI2_ROOT] = imx_clk_hw_gate4("ecspi2_root_clk", "ecspi2", ccm_base + 0x4080, 0);
+	hws[IMX8MP_CLK_ECSPI3_ROOT] = imx_clk_hw_gate4("ecspi3_root_clk", "ecspi3", ccm_base + 0x4090, 0);
+	hws[IMX8MP_CLK_ENET1_ROOT] = imx_clk_hw_gate4("enet1_root_clk", "enet_axi", ccm_base + 0x40a0, 0);
+	hws[IMX8MP_CLK_GPIO1_ROOT] = imx_clk_hw_gate4("gpio1_root_clk", "ipg_root", ccm_base + 0x40b0, 0);
+	hws[IMX8MP_CLK_GPIO2_ROOT] = imx_clk_hw_gate4("gpio2_root_clk", "ipg_root", ccm_base + 0x40c0, 0);
+	hws[IMX8MP_CLK_GPIO3_ROOT] = imx_clk_hw_gate4("gpio3_root_clk", "ipg_root", ccm_base + 0x40d0, 0);
+	hws[IMX8MP_CLK_GPIO4_ROOT] = imx_clk_hw_gate4("gpio4_root_clk", "ipg_root", ccm_base + 0x40e0, 0);
+	hws[IMX8MP_CLK_GPIO5_ROOT] = imx_clk_hw_gate4("gpio5_root_clk", "ipg_root", ccm_base + 0x40f0, 0);
+	hws[IMX8MP_CLK_GPT1_ROOT] = imx_clk_hw_gate4("gpt1_root_clk", "gpt1", ccm_base + 0x4100, 0);
+	hws[IMX8MP_CLK_GPT2_ROOT] = imx_clk_hw_gate4("gpt2_root_clk", "gpt2", ccm_base + 0x4110, 0);
+	hws[IMX8MP_CLK_GPT3_ROOT] = imx_clk_hw_gate4("gpt3_root_clk", "gpt3", ccm_base + 0x4120, 0);
+	hws[IMX8MP_CLK_GPT4_ROOT] = imx_clk_hw_gate4("gpt4_root_clk", "gpt4", ccm_base + 0x4130, 0);
+	hws[IMX8MP_CLK_GPT5_ROOT] = imx_clk_hw_gate4("gpt5_root_clk", "gpt5", ccm_base + 0x4140, 0);
+	hws[IMX8MP_CLK_GPT6_ROOT] = imx_clk_hw_gate4("gpt6_root_clk", "gpt6", ccm_base + 0x4150, 0);
+	hws[IMX8MP_CLK_I2C1_ROOT] = imx_clk_hw_gate4("i2c1_root_clk", "i2c1", ccm_base + 0x4170, 0);
+	hws[IMX8MP_CLK_I2C2_ROOT] = imx_clk_hw_gate4("i2c2_root_clk", "i2c2", ccm_base + 0x4180, 0);
+	hws[IMX8MP_CLK_I2C3_ROOT] = imx_clk_hw_gate4("i2c3_root_clk", "i2c3", ccm_base + 0x4190, 0);
+	hws[IMX8MP_CLK_I2C4_ROOT] = imx_clk_hw_gate4("i2c4_root_clk", "i2c4", ccm_base + 0x41a0, 0);
+	hws[IMX8MP_CLK_PCIE_ROOT] = imx_clk_hw_gate4("pcie_root_clk", "pcie_aux", ccm_base + 0x4250, 0);
+	hws[IMX8MP_CLK_PWM1_ROOT] = imx_clk_hw_gate4("pwm1_root_clk", "pwm1", ccm_base + 0x4280, 0);
+	hws[IMX8MP_CLK_PWM2_ROOT] = imx_clk_hw_gate4("pwm2_root_clk", "pwm2", ccm_base + 0x4290, 0);
+	hws[IMX8MP_CLK_PWM3_ROOT] = imx_clk_hw_gate4("pwm3_root_clk", "pwm3", ccm_base + 0x42a0, 0);
+	hws[IMX8MP_CLK_PWM4_ROOT] = imx_clk_hw_gate4("pwm4_root_clk", "pwm4", ccm_base + 0x42b0, 0);
+	hws[IMX8MP_CLK_QOS_ROOT] = imx_clk_hw_gate4("qos_root_clk", "ipg_root", ccm_base + 0x42c0, 0);
+	hws[IMX8MP_CLK_QOS_ENET_ROOT] = imx_clk_hw_gate4("qos_enet_root_clk", "ipg_root", ccm_base + 0x42e0, 0);
+	hws[IMX8MP_CLK_QSPI_ROOT] = imx_clk_hw_gate4("qspi_root_clk", "qspi", ccm_base + 0x42f0, 0);
+	hws[IMX8MP_CLK_NAND_ROOT] = imx_clk_hw_gate2_shared2("nand_root_clk", "nand", ccm_base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MP_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_hw_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", ccm_base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MP_CLK_I2C5_ROOT] = imx_clk_hw_gate2("i2c5_root_clk", "i2c5", ccm_base + 0x4330, 0);
+	hws[IMX8MP_CLK_I2C6_ROOT] = imx_clk_hw_gate2("i2c6_root_clk", "i2c6", ccm_base + 0x4340, 0);
+	hws[IMX8MP_CLK_CAN1_ROOT] = imx_clk_hw_gate2("can1_root_clk", "can1", ccm_base + 0x4350, 0);
+	hws[IMX8MP_CLK_CAN2_ROOT] = imx_clk_hw_gate2("can2_root_clk", "can2", ccm_base + 0x4360, 0);
+	hws[IMX8MP_CLK_SDMA1_ROOT] = imx_clk_hw_gate4("sdma1_root_clk", "ipg_root", ccm_base + 0x43a0, 0);
+	hws[IMX8MP_CLK_ENET_QOS_ROOT] = imx_clk_hw_gate4("enet_qos_root_clk", "enet_axi", ccm_base + 0x43b0, 0);
+	hws[IMX8MP_CLK_SIM_ENET_ROOT] = imx_clk_hw_gate4("sim_enet_root_clk", "enet_axi", ccm_base + 0x4400, 0);
+	hws[IMX8MP_CLK_GPU2D_ROOT] = imx_clk_hw_gate4("gpu2d_root_clk", "gpu2d_div", ccm_base + 0x4450, 0);
+	hws[IMX8MP_CLK_GPU3D_ROOT] = imx_clk_hw_gate4("gpu3d_root_clk", "gpu3d_core_div", ccm_base + 0x4460, 0);
+	hws[IMX8MP_CLK_SNVS_ROOT] = imx_clk_hw_gate4("snvs_root_clk", "ipg_root", ccm_base + 0x4470, 0);
+	hws[IMX8MP_CLK_UART1_ROOT] = imx_clk_hw_gate4("uart1_root_clk", "uart1", ccm_base + 0x4490, 0);
+	hws[IMX8MP_CLK_UART2_ROOT] = imx_clk_hw_gate4("uart2_root_clk", "uart2", ccm_base + 0x44a0, 0);
+	hws[IMX8MP_CLK_UART3_ROOT] = imx_clk_hw_gate4("uart3_root_clk", "uart3", ccm_base + 0x44b0, 0);
+	hws[IMX8MP_CLK_UART4_ROOT] = imx_clk_hw_gate4("uart4_root_clk", "uart4", ccm_base + 0x44c0, 0);
+	hws[IMX8MP_CLK_USB_ROOT] = imx_clk_hw_gate4("usb_root_clk", "osc_32k", ccm_base + 0x44d0, 0);
+	hws[IMX8MP_CLK_USB_PHY_ROOT] = imx_clk_hw_gate4("usb_phy_root_clk", "usb_phy_ref", ccm_base + 0x44f0, 0);
+	hws[IMX8MP_CLK_USDHC1_ROOT] = imx_clk_hw_gate4("usdhc1_root_clk", "usdhc1", ccm_base + 0x4510, 0);
+	hws[IMX8MP_CLK_USDHC2_ROOT] = imx_clk_hw_gate4("usdhc2_root_clk", "usdhc2", ccm_base + 0x4520, 0);
+	hws[IMX8MP_CLK_WDOG1_ROOT] = imx_clk_hw_gate4("wdog1_root_clk", "wdog", ccm_base + 0x4530, 0);
+	hws[IMX8MP_CLK_WDOG2_ROOT] = imx_clk_hw_gate4("wdog2_root_clk", "wdog", ccm_base + 0x4540, 0);
+	hws[IMX8MP_CLK_WDOG3_ROOT] = imx_clk_hw_gate4("wdog3_root_clk", "wdog", ccm_base + 0x4550, 0);
+	hws[IMX8MP_CLK_VPU_G1_ROOT] = imx_clk_hw_gate4("vpu_g1_root_clk", "vpu_g1", ccm_base + 0x4560, 0);
+	hws[IMX8MP_CLK_GPU_ROOT] = imx_clk_hw_gate4("gpu_root_clk", "gpu_axi", ccm_base + 0x4570, 0);
+	hws[IMX8MP_CLK_VPU_VC8KE_ROOT] = imx_clk_hw_gate4("vpu_vc8ke_root_clk", "vpu_vc8000e", ccm_base + 0x4590, 0);
+	hws[IMX8MP_CLK_VPU_G2_ROOT] = imx_clk_hw_gate4("vpu_g2_root_clk", "vpu_g2", ccm_base + 0x45a0, 0);
+	hws[IMX8MP_CLK_NPU_ROOT] = imx_clk_hw_gate4("npu_root_clk", "ml_div", ccm_base + 0x45b0, 0);
+	hws[IMX8MP_CLK_HSIO_ROOT] = imx_clk_hw_gate4("hsio_root_clk", "ipg_root", ccm_base + 0x45c0, 0);
+	hws[IMX8MP_CLK_MEDIA_APB_ROOT] = imx_clk_hw_gate2_shared2("media_apb_root_clk", "media_apb", ccm_base + 0x45d0, 0, &share_count_media);
+	hws[IMX8MP_CLK_MEDIA_AXI_ROOT] = imx_clk_hw_gate2_shared2("media_axi_root_clk", "media_axi", ccm_base + 0x45d0, 0, &share_count_media);
+	hws[IMX8MP_CLK_MEDIA_CAM1_PIX_ROOT] = imx_clk_hw_gate2_shared2("media_cam1_pix_root_clk", "media_cam1_pix", ccm_base + 0x45d0, 0, &share_count_media);
+	hws[IMX8MP_CLK_MEDIA_CAM2_PIX_ROOT] = imx_clk_hw_gate2_shared2("media_cam2_pix_root_clk", "media_cam2_pix", ccm_base + 0x45d0, 0, &share_count_media);
+	hws[IMX8MP_CLK_MEDIA_DISP1_PIX_ROOT] = imx_clk_hw_gate2_shared2("media_disp1_pix_root_clk", "media_disp1_pix", ccm_base + 0x45d0, 0, &share_count_media);
+	hws[IMX8MP_CLK_MEDIA_DISP2_PIX_ROOT] = imx_clk_hw_gate2_shared2("media_disp2_pix_root_clk", "media_disp2_pix", ccm_base + 0x45d0, 0, &share_count_media);
+	hws[IMX8MP_CLK_MEDIA_ISP_ROOT] = imx_clk_hw_gate2_shared2("media_isp_root_clk", "media_isp_div", ccm_base + 0x45d0, 0, &share_count_media);
+
+	hws[IMX8MP_CLK_USDHC3_ROOT] = imx_clk_hw_gate4("usdhc3_root_clk", "usdhc3", ccm_base + 0x45e0, 0);
+	hws[IMX8MP_CLK_HDMI_ROOT] = imx_clk_hw_gate4("hdmi_root_clk", "hdmi_axi", ccm_base + 0x45f0, 0);
+	hws[IMX8MP_CLK_TSENSOR_ROOT] = imx_clk_hw_gate4("tsensor_root_clk", "ipg_root", ccm_base + 0x4620, 0);
+	hws[IMX8MP_CLK_VPU_ROOT] = imx_clk_hw_gate4("vpu_root_clk", "vpu_bus", ccm_base + 0x4630, 0);
+	hws[IMX8MP_CLK_AUDIO_ROOT] = imx_clk_hw_gate4("audio_root_clk", "ipg_root", ccm_base + 0x4650, 0);
+
+	hws[IMX8MP_CLK_ARM] = imx_clk_hw_cpu("arm", "arm_a53_div",
+					     hws[IMX8MP_CLK_A53_DIV]->clk,
+					     hws[IMX8MP_CLK_A53_SRC]->clk,
+					     hws[IMX8MP_ARM_PLL_OUT]->clk,
+					     hws[IMX8MP_SYS_PLL1_800M]->clk);
+
+	imx_check_clk_hws(hws, IMX8MP_CLK_END);
+
+	of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data);
+
+	for (i = 0; i < ARRAY_SIZE(uart_clk_ids); i++) {
+		int index = uart_clk_ids[i];
+
+		uart_clks[i] = &hws[index]->clk;
+	}
+
+	imx_register_uart_clocks(uart_clks);
+
+	return 0;
+}
+
+static const struct of_device_id imx8mp_clk_of_match[] = {
+	{ .compatible = "fsl,imx8mp-ccm" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, imx8mp_clk_of_match);
+
+static struct platform_driver imx8mp_clk_driver = {
+	.probe = imx8mp_clocks_probe,
+	.driver = {
+		.name = "imx8mp-ccm",
+		/*
+		 * Disable bind attributes: clocks are not removed and
+		 * reloading the driver will crash or break devices.
+		 */
+		.suppress_bind_attrs = true,
+		.of_match_table = of_match_ptr(imx8mp_clk_of_match),
+	},
+};
+module_platform_driver(imx8mp_clk_driver);
diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c
index 5f10a606d836..4c0edca1a6d0 100644
--- a/drivers/clk/imx/clk-imx8mq.c
+++ b/drivers/clk/imx/clk-imx8mq.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/platform_device.h>
 
 #include "clk.h"
@@ -24,8 +25,6 @@ static u32 share_count_sai6;
 static u32 share_count_dcss;
 static u32 share_count_nand;
 
-static struct clk *clks[IMX8MQ_CLK_END];
-
 static const char * const pll_ref_sels[] = { "osc_25m", "osc_27m", "dummy", "dummy", };
 static const char * const arm_pll_bypass_sels[] = {"arm_pll", "arm_pll_ref_sel", };
 static const char * const gpu_pll_bypass_sels[] = {"gpu_pll", "gpu_pll_ref_sel", };
@@ -269,124 +268,133 @@ static const char * const imx8mq_clko1_sels[] = {"osc_25m", "sys1_pll_800m", "os
 static const char * const imx8mq_clko2_sels[] = {"osc_25m", "sys2_pll_200m", "sys1_pll_400m", "sys2_pll_166m",
 					  "sys3_pll_out", "audio_pll1_out", "video_pll1_out", "ckil", };
 
-static struct clk_onecell_data clk_data;
+static struct clk_hw_onecell_data *clk_hw_data;
+static struct clk_hw **hws;
 
-static struct clk ** const uart_clks[] = {
-	&clks[IMX8MQ_CLK_UART1_ROOT],
-	&clks[IMX8MQ_CLK_UART2_ROOT],
-	&clks[IMX8MQ_CLK_UART3_ROOT],
-	&clks[IMX8MQ_CLK_UART4_ROOT],
-	NULL
+static const int uart_clk_ids[] = {
+	IMX8MQ_CLK_UART1_ROOT,
+	IMX8MQ_CLK_UART2_ROOT,
+	IMX8MQ_CLK_UART3_ROOT,
+	IMX8MQ_CLK_UART4_ROOT,
 };
+static struct clk **uart_hws[ARRAY_SIZE(uart_clk_ids) + 1];
 
 static int imx8mq_clocks_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	void __iomem *base;
-	int err;
+	int err, i;
+
+	clk_hw_data = kzalloc(struct_size(clk_hw_data, hws,
+					  IMX8MQ_CLK_END), GFP_KERNEL);
+	if (WARN_ON(!clk_hw_data))
+		return -ENOMEM;
+
+	clk_hw_data->num = IMX8MQ_CLK_END;
+	hws = clk_hw_data->hws;
 
-	clks[IMX8MQ_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
-	clks[IMX8MQ_CLK_32K] = of_clk_get_by_name(np, "ckil");
-	clks[IMX8MQ_CLK_25M] = of_clk_get_by_name(np, "osc_25m");
-	clks[IMX8MQ_CLK_27M] = of_clk_get_by_name(np, "osc_27m");
-	clks[IMX8MQ_CLK_EXT1] = of_clk_get_by_name(np, "clk_ext1");
-	clks[IMX8MQ_CLK_EXT2] = of_clk_get_by_name(np, "clk_ext2");
-	clks[IMX8MQ_CLK_EXT3] = of_clk_get_by_name(np, "clk_ext3");
-	clks[IMX8MQ_CLK_EXT4] = of_clk_get_by_name(np, "clk_ext4");
+	hws[IMX8MQ_CLK_DUMMY] = imx_clk_hw_fixed("dummy", 0);
+	hws[IMX8MQ_CLK_32K] = imx_obtain_fixed_clk_hw(np, "ckil");
+	hws[IMX8MQ_CLK_25M] = imx_obtain_fixed_clk_hw(np, "osc_25m");
+	hws[IMX8MQ_CLK_27M] = imx_obtain_fixed_clk_hw(np, "osc_27m");
+	hws[IMX8MQ_CLK_EXT1] = imx_obtain_fixed_clk_hw(np, "clk_ext1");
+	hws[IMX8MQ_CLK_EXT2] = imx_obtain_fixed_clk_hw(np, "clk_ext2");
+	hws[IMX8MQ_CLK_EXT3] = imx_obtain_fixed_clk_hw(np, "clk_ext3");
+	hws[IMX8MQ_CLK_EXT4] = imx_obtain_fixed_clk_hw(np, "clk_ext4");
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx8mq-anatop");
 	base = of_iomap(np, 0);
 	if (WARN_ON(!base))
 		return -ENOMEM;
 
-	clks[IMX8MQ_ARM_PLL_REF_SEL] = imx_clk_mux("arm_pll_ref_sel", base + 0x28, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_GPU_PLL_REF_SEL] = imx_clk_mux("gpu_pll_ref_sel", base + 0x18, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_VPU_PLL_REF_SEL] = imx_clk_mux("vpu_pll_ref_sel", base + 0x20, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_AUDIO_PLL1_REF_SEL] = imx_clk_mux("audio_pll1_ref_sel", base + 0x0, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_AUDIO_PLL2_REF_SEL] = imx_clk_mux("audio_pll2_ref_sel", base + 0x8, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_VIDEO_PLL1_REF_SEL] = imx_clk_mux("video_pll1_ref_sel", base + 0x10, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_SYS3_PLL1_REF_SEL]	= imx_clk_mux("sys3_pll1_ref_sel", base + 0x48, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_DRAM_PLL1_REF_SEL]	= imx_clk_mux("dram_pll1_ref_sel", base + 0x60, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-	clks[IMX8MQ_VIDEO2_PLL1_REF_SEL] = imx_clk_mux("video2_pll1_ref_sel", base + 0x54, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
-
-	clks[IMX8MQ_ARM_PLL_REF_DIV]	= imx_clk_divider("arm_pll_ref_div", "arm_pll_ref_sel", base + 0x28, 5, 6);
-	clks[IMX8MQ_GPU_PLL_REF_DIV]	= imx_clk_divider("gpu_pll_ref_div", "gpu_pll_ref_sel", base + 0x18, 5, 6);
-	clks[IMX8MQ_VPU_PLL_REF_DIV]	= imx_clk_divider("vpu_pll_ref_div", "vpu_pll_ref_sel", base + 0x20, 5, 6);
-	clks[IMX8MQ_AUDIO_PLL1_REF_DIV] = imx_clk_divider("audio_pll1_ref_div", "audio_pll1_ref_sel", base + 0x0, 5, 6);
-	clks[IMX8MQ_AUDIO_PLL2_REF_DIV] = imx_clk_divider("audio_pll2_ref_div", "audio_pll2_ref_sel", base + 0x8, 5, 6);
-	clks[IMX8MQ_VIDEO_PLL1_REF_DIV] = imx_clk_divider("video_pll1_ref_div", "video_pll1_ref_sel", base + 0x10, 5, 6);
-
-	clks[IMX8MQ_ARM_PLL] = imx_clk_frac_pll("arm_pll", "arm_pll_ref_div", base + 0x28);
-	clks[IMX8MQ_GPU_PLL] = imx_clk_frac_pll("gpu_pll", "gpu_pll_ref_div", base + 0x18);
-	clks[IMX8MQ_VPU_PLL] = imx_clk_frac_pll("vpu_pll", "vpu_pll_ref_div", base + 0x20);
-	clks[IMX8MQ_AUDIO_PLL1] = imx_clk_frac_pll("audio_pll1", "audio_pll1_ref_div", base + 0x0);
-	clks[IMX8MQ_AUDIO_PLL2] = imx_clk_frac_pll("audio_pll2", "audio_pll2_ref_div", base + 0x8);
-	clks[IMX8MQ_VIDEO_PLL1] = imx_clk_frac_pll("video_pll1", "video_pll1_ref_div", base + 0x10);
+	hws[IMX8MQ_ARM_PLL_REF_SEL] = imx_clk_hw_mux("arm_pll_ref_sel", base + 0x28, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_GPU_PLL_REF_SEL] = imx_clk_hw_mux("gpu_pll_ref_sel", base + 0x18, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_VPU_PLL_REF_SEL] = imx_clk_hw_mux("vpu_pll_ref_sel", base + 0x20, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_AUDIO_PLL1_REF_SEL] = imx_clk_hw_mux("audio_pll1_ref_sel", base + 0x0, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_AUDIO_PLL2_REF_SEL] = imx_clk_hw_mux("audio_pll2_ref_sel", base + 0x8, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_VIDEO_PLL1_REF_SEL] = imx_clk_hw_mux("video_pll1_ref_sel", base + 0x10, 16, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_SYS3_PLL1_REF_SEL]	= imx_clk_hw_mux("sys3_pll1_ref_sel", base + 0x48, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_DRAM_PLL1_REF_SEL]	= imx_clk_hw_mux("dram_pll1_ref_sel", base + 0x60, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+	hws[IMX8MQ_VIDEO2_PLL1_REF_SEL] = imx_clk_hw_mux("video2_pll1_ref_sel", base + 0x54, 0, 2, pll_ref_sels, ARRAY_SIZE(pll_ref_sels));
+
+	hws[IMX8MQ_ARM_PLL_REF_DIV]	= imx_clk_hw_divider("arm_pll_ref_div", "arm_pll_ref_sel", base + 0x28, 5, 6);
+	hws[IMX8MQ_GPU_PLL_REF_DIV]	= imx_clk_hw_divider("gpu_pll_ref_div", "gpu_pll_ref_sel", base + 0x18, 5, 6);
+	hws[IMX8MQ_VPU_PLL_REF_DIV]	= imx_clk_hw_divider("vpu_pll_ref_div", "vpu_pll_ref_sel", base + 0x20, 5, 6);
+	hws[IMX8MQ_AUDIO_PLL1_REF_DIV] = imx_clk_hw_divider("audio_pll1_ref_div", "audio_pll1_ref_sel", base + 0x0, 5, 6);
+	hws[IMX8MQ_AUDIO_PLL2_REF_DIV] = imx_clk_hw_divider("audio_pll2_ref_div", "audio_pll2_ref_sel", base + 0x8, 5, 6);
+	hws[IMX8MQ_VIDEO_PLL1_REF_DIV] = imx_clk_hw_divider("video_pll1_ref_div", "video_pll1_ref_sel", base + 0x10, 5, 6);
+
+	hws[IMX8MQ_ARM_PLL] = imx_clk_hw_frac_pll("arm_pll", "arm_pll_ref_div", base + 0x28);
+	hws[IMX8MQ_GPU_PLL] = imx_clk_hw_frac_pll("gpu_pll", "gpu_pll_ref_div", base + 0x18);
+	hws[IMX8MQ_VPU_PLL] = imx_clk_hw_frac_pll("vpu_pll", "vpu_pll_ref_div", base + 0x20);
+	hws[IMX8MQ_AUDIO_PLL1] = imx_clk_hw_frac_pll("audio_pll1", "audio_pll1_ref_div", base + 0x0);
+	hws[IMX8MQ_AUDIO_PLL2] = imx_clk_hw_frac_pll("audio_pll2", "audio_pll2_ref_div", base + 0x8);
+	hws[IMX8MQ_VIDEO_PLL1] = imx_clk_hw_frac_pll("video_pll1", "video_pll1_ref_div", base + 0x10);
 
 	/* PLL bypass out */
-	clks[IMX8MQ_ARM_PLL_BYPASS] = imx_clk_mux_flags("arm_pll_bypass", base + 0x28, 14, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
-	clks[IMX8MQ_GPU_PLL_BYPASS] = imx_clk_mux("gpu_pll_bypass", base + 0x18, 14, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels));
-	clks[IMX8MQ_VPU_PLL_BYPASS] = imx_clk_mux("vpu_pll_bypass", base + 0x20, 14, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels));
-	clks[IMX8MQ_AUDIO_PLL1_BYPASS] = imx_clk_mux("audio_pll1_bypass", base + 0x0, 14, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels));
-	clks[IMX8MQ_AUDIO_PLL2_BYPASS] = imx_clk_mux("audio_pll2_bypass", base + 0x8, 14, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels));
-	clks[IMX8MQ_VIDEO_PLL1_BYPASS] = imx_clk_mux("video_pll1_bypass", base + 0x10, 14, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels));
+	hws[IMX8MQ_ARM_PLL_BYPASS] = imx_clk_hw_mux_flags("arm_pll_bypass", base + 0x28, 14, 1, arm_pll_bypass_sels, ARRAY_SIZE(arm_pll_bypass_sels), CLK_SET_RATE_PARENT);
+	hws[IMX8MQ_GPU_PLL_BYPASS] = imx_clk_hw_mux("gpu_pll_bypass", base + 0x18, 14, 1, gpu_pll_bypass_sels, ARRAY_SIZE(gpu_pll_bypass_sels));
+	hws[IMX8MQ_VPU_PLL_BYPASS] = imx_clk_hw_mux("vpu_pll_bypass", base + 0x20, 14, 1, vpu_pll_bypass_sels, ARRAY_SIZE(vpu_pll_bypass_sels));
+	hws[IMX8MQ_AUDIO_PLL1_BYPASS] = imx_clk_hw_mux("audio_pll1_bypass", base + 0x0, 14, 1, audio_pll1_bypass_sels, ARRAY_SIZE(audio_pll1_bypass_sels));
+	hws[IMX8MQ_AUDIO_PLL2_BYPASS] = imx_clk_hw_mux("audio_pll2_bypass", base + 0x8, 14, 1, audio_pll2_bypass_sels, ARRAY_SIZE(audio_pll2_bypass_sels));
+	hws[IMX8MQ_VIDEO_PLL1_BYPASS] = imx_clk_hw_mux("video_pll1_bypass", base + 0x10, 14, 1, video_pll1_bypass_sels, ARRAY_SIZE(video_pll1_bypass_sels));
 
 	/* PLL OUT GATE */
-	clks[IMX8MQ_ARM_PLL_OUT] = imx_clk_gate("arm_pll_out", "arm_pll_bypass", base + 0x28, 21);
-	clks[IMX8MQ_GPU_PLL_OUT] = imx_clk_gate("gpu_pll_out", "gpu_pll_bypass", base + 0x18, 21);
-	clks[IMX8MQ_VPU_PLL_OUT] = imx_clk_gate("vpu_pll_out", "vpu_pll_bypass", base + 0x20, 21);
-	clks[IMX8MQ_AUDIO_PLL1_OUT] = imx_clk_gate("audio_pll1_out", "audio_pll1_bypass", base + 0x0, 21);
-	clks[IMX8MQ_AUDIO_PLL2_OUT] = imx_clk_gate("audio_pll2_out", "audio_pll2_bypass", base + 0x8, 21);
-	clks[IMX8MQ_VIDEO_PLL1_OUT] = imx_clk_gate("video_pll1_out", "video_pll1_bypass", base + 0x10, 21);
-
-	clks[IMX8MQ_SYS1_PLL_OUT] = imx_clk_fixed("sys1_pll_out", 800000000);
-	clks[IMX8MQ_SYS2_PLL_OUT] = imx_clk_fixed("sys2_pll_out", 1000000000);
-	clks[IMX8MQ_SYS3_PLL_OUT] = imx_clk_sccg_pll("sys3_pll_out", sys3_pll_out_sels, ARRAY_SIZE(sys3_pll_out_sels), 0, 0, 0, base + 0x48, CLK_IS_CRITICAL);
-	clks[IMX8MQ_DRAM_PLL_OUT] = imx_clk_sccg_pll("dram_pll_out", dram_pll_out_sels, ARRAY_SIZE(dram_pll_out_sels), 0, 0, 0, base + 0x60, CLK_IS_CRITICAL);
-	clks[IMX8MQ_VIDEO2_PLL_OUT] = imx_clk_sccg_pll("video2_pll_out", video2_pll_out_sels, ARRAY_SIZE(video2_pll_out_sels), 0, 0, 0, base + 0x54, 0);
+	hws[IMX8MQ_ARM_PLL_OUT] = imx_clk_hw_gate("arm_pll_out", "arm_pll_bypass", base + 0x28, 21);
+	hws[IMX8MQ_GPU_PLL_OUT] = imx_clk_hw_gate("gpu_pll_out", "gpu_pll_bypass", base + 0x18, 21);
+	hws[IMX8MQ_VPU_PLL_OUT] = imx_clk_hw_gate("vpu_pll_out", "vpu_pll_bypass", base + 0x20, 21);
+	hws[IMX8MQ_AUDIO_PLL1_OUT] = imx_clk_hw_gate("audio_pll1_out", "audio_pll1_bypass", base + 0x0, 21);
+	hws[IMX8MQ_AUDIO_PLL2_OUT] = imx_clk_hw_gate("audio_pll2_out", "audio_pll2_bypass", base + 0x8, 21);
+	hws[IMX8MQ_VIDEO_PLL1_OUT] = imx_clk_hw_gate("video_pll1_out", "video_pll1_bypass", base + 0x10, 21);
+
+	hws[IMX8MQ_SYS1_PLL_OUT] = imx_clk_hw_fixed("sys1_pll_out", 800000000);
+	hws[IMX8MQ_SYS2_PLL_OUT] = imx_clk_hw_fixed("sys2_pll_out", 1000000000);
+	hws[IMX8MQ_SYS3_PLL_OUT] = imx_clk_hw_sscg_pll("sys3_pll_out", sys3_pll_out_sels, ARRAY_SIZE(sys3_pll_out_sels), 0, 0, 0, base + 0x48, CLK_IS_CRITICAL);
+	hws[IMX8MQ_DRAM_PLL_OUT] = imx_clk_hw_sscg_pll("dram_pll_out", dram_pll_out_sels, ARRAY_SIZE(dram_pll_out_sels), 0, 0, 0, base + 0x60, CLK_IS_CRITICAL | CLK_GET_RATE_NOCACHE);
+	hws[IMX8MQ_VIDEO2_PLL_OUT] = imx_clk_hw_sscg_pll("video2_pll_out", video2_pll_out_sels, ARRAY_SIZE(video2_pll_out_sels), 0, 0, 0, base + 0x54, 0);
 
 	/* SYS PLL1 fixed output */
-	clks[IMX8MQ_SYS1_PLL_40M_CG] = imx_clk_gate("sys1_pll_40m_cg", "sys1_pll_out", base + 0x30, 9);
-	clks[IMX8MQ_SYS1_PLL_80M_CG] = imx_clk_gate("sys1_pll_80m_cg", "sys1_pll_out", base + 0x30, 11);
-	clks[IMX8MQ_SYS1_PLL_100M_CG] = imx_clk_gate("sys1_pll_100m_cg", "sys1_pll_out", base + 0x30, 13);
-	clks[IMX8MQ_SYS1_PLL_133M_CG] = imx_clk_gate("sys1_pll_133m_cg", "sys1_pll_out", base + 0x30, 15);
-	clks[IMX8MQ_SYS1_PLL_160M_CG] = imx_clk_gate("sys1_pll_160m_cg", "sys1_pll_out", base + 0x30, 17);
-	clks[IMX8MQ_SYS1_PLL_200M_CG] = imx_clk_gate("sys1_pll_200m_cg", "sys1_pll_out", base + 0x30, 19);
-	clks[IMX8MQ_SYS1_PLL_266M_CG] = imx_clk_gate("sys1_pll_266m_cg", "sys1_pll_out", base + 0x30, 21);
-	clks[IMX8MQ_SYS1_PLL_400M_CG] = imx_clk_gate("sys1_pll_400m_cg", "sys1_pll_out", base + 0x30, 23);
-	clks[IMX8MQ_SYS1_PLL_800M_CG] = imx_clk_gate("sys1_pll_800m_cg", "sys1_pll_out", base + 0x30, 25);
-
-	clks[IMX8MQ_SYS1_PLL_40M] = imx_clk_fixed_factor("sys1_pll_40m", "sys1_pll_40m_cg", 1, 20);
-	clks[IMX8MQ_SYS1_PLL_80M] = imx_clk_fixed_factor("sys1_pll_80m", "sys1_pll_80m_cg", 1, 10);
-	clks[IMX8MQ_SYS1_PLL_100M] = imx_clk_fixed_factor("sys1_pll_100m", "sys1_pll_100m_cg", 1, 8);
-	clks[IMX8MQ_SYS1_PLL_133M] = imx_clk_fixed_factor("sys1_pll_133m", "sys1_pll_133m_cg", 1, 6);
-	clks[IMX8MQ_SYS1_PLL_160M] = imx_clk_fixed_factor("sys1_pll_160m", "sys1_pll_160m_cg", 1, 5);
-	clks[IMX8MQ_SYS1_PLL_200M] = imx_clk_fixed_factor("sys1_pll_200m", "sys1_pll_200m_cg", 1, 4);
-	clks[IMX8MQ_SYS1_PLL_266M] = imx_clk_fixed_factor("sys1_pll_266m", "sys1_pll_266m_cg", 1, 3);
-	clks[IMX8MQ_SYS1_PLL_400M] = imx_clk_fixed_factor("sys1_pll_400m", "sys1_pll_400m_cg", 1, 2);
-	clks[IMX8MQ_SYS1_PLL_800M] = imx_clk_fixed_factor("sys1_pll_800m", "sys1_pll_800m_cg", 1, 1);
+	hws[IMX8MQ_SYS1_PLL_40M_CG] = imx_clk_hw_gate("sys1_pll_40m_cg", "sys1_pll_out", base + 0x30, 9);
+	hws[IMX8MQ_SYS1_PLL_80M_CG] = imx_clk_hw_gate("sys1_pll_80m_cg", "sys1_pll_out", base + 0x30, 11);
+	hws[IMX8MQ_SYS1_PLL_100M_CG] = imx_clk_hw_gate("sys1_pll_100m_cg", "sys1_pll_out", base + 0x30, 13);
+	hws[IMX8MQ_SYS1_PLL_133M_CG] = imx_clk_hw_gate("sys1_pll_133m_cg", "sys1_pll_out", base + 0x30, 15);
+	hws[IMX8MQ_SYS1_PLL_160M_CG] = imx_clk_hw_gate("sys1_pll_160m_cg", "sys1_pll_out", base + 0x30, 17);
+	hws[IMX8MQ_SYS1_PLL_200M_CG] = imx_clk_hw_gate("sys1_pll_200m_cg", "sys1_pll_out", base + 0x30, 19);
+	hws[IMX8MQ_SYS1_PLL_266M_CG] = imx_clk_hw_gate("sys1_pll_266m_cg", "sys1_pll_out", base + 0x30, 21);
+	hws[IMX8MQ_SYS1_PLL_400M_CG] = imx_clk_hw_gate("sys1_pll_400m_cg", "sys1_pll_out", base + 0x30, 23);
+	hws[IMX8MQ_SYS1_PLL_800M_CG] = imx_clk_hw_gate("sys1_pll_800m_cg", "sys1_pll_out", base + 0x30, 25);
+
+	hws[IMX8MQ_SYS1_PLL_40M] = imx_clk_hw_fixed_factor("sys1_pll_40m", "sys1_pll_40m_cg", 1, 20);
+	hws[IMX8MQ_SYS1_PLL_80M] = imx_clk_hw_fixed_factor("sys1_pll_80m", "sys1_pll_80m_cg", 1, 10);
+	hws[IMX8MQ_SYS1_PLL_100M] = imx_clk_hw_fixed_factor("sys1_pll_100m", "sys1_pll_100m_cg", 1, 8);
+	hws[IMX8MQ_SYS1_PLL_133M] = imx_clk_hw_fixed_factor("sys1_pll_133m", "sys1_pll_133m_cg", 1, 6);
+	hws[IMX8MQ_SYS1_PLL_160M] = imx_clk_hw_fixed_factor("sys1_pll_160m", "sys1_pll_160m_cg", 1, 5);
+	hws[IMX8MQ_SYS1_PLL_200M] = imx_clk_hw_fixed_factor("sys1_pll_200m", "sys1_pll_200m_cg", 1, 4);
+	hws[IMX8MQ_SYS1_PLL_266M] = imx_clk_hw_fixed_factor("sys1_pll_266m", "sys1_pll_266m_cg", 1, 3);
+	hws[IMX8MQ_SYS1_PLL_400M] = imx_clk_hw_fixed_factor("sys1_pll_400m", "sys1_pll_400m_cg", 1, 2);
+	hws[IMX8MQ_SYS1_PLL_800M] = imx_clk_hw_fixed_factor("sys1_pll_800m", "sys1_pll_800m_cg", 1, 1);
 
 	/* SYS PLL2 fixed output */
-	clks[IMX8MQ_SYS2_PLL_50M_CG] = imx_clk_gate("sys2_pll_50m_cg", "sys2_pll_out", base + 0x3c, 9);
-	clks[IMX8MQ_SYS2_PLL_100M_CG] = imx_clk_gate("sys2_pll_100m_cg", "sys2_pll_out", base + 0x3c, 11);
-	clks[IMX8MQ_SYS2_PLL_125M_CG] = imx_clk_gate("sys2_pll_125m_cg", "sys2_pll_out", base + 0x3c, 13);
-	clks[IMX8MQ_SYS2_PLL_166M_CG] = imx_clk_gate("sys2_pll_166m_cg", "sys2_pll_out", base + 0x3c, 15);
-	clks[IMX8MQ_SYS2_PLL_200M_CG] = imx_clk_gate("sys2_pll_200m_cg", "sys2_pll_out", base + 0x3c, 17);
-	clks[IMX8MQ_SYS2_PLL_250M_CG] = imx_clk_gate("sys2_pll_250m_cg", "sys2_pll_out", base + 0x3c, 19);
-	clks[IMX8MQ_SYS2_PLL_333M_CG] = imx_clk_gate("sys2_pll_333m_cg", "sys2_pll_out", base + 0x3c, 21);
-	clks[IMX8MQ_SYS2_PLL_500M_CG] = imx_clk_gate("sys2_pll_500m_cg", "sys2_pll_out", base + 0x3c, 23);
-	clks[IMX8MQ_SYS2_PLL_1000M_CG] = imx_clk_gate("sys2_pll_1000m_cg", "sys2_pll_out", base + 0x3c, 25);
-
-	clks[IMX8MQ_SYS2_PLL_50M] = imx_clk_fixed_factor("sys2_pll_50m", "sys2_pll_50m_cg", 1, 20);
-	clks[IMX8MQ_SYS2_PLL_100M] = imx_clk_fixed_factor("sys2_pll_100m", "sys2_pll_100m_cg", 1, 10);
-	clks[IMX8MQ_SYS2_PLL_125M] = imx_clk_fixed_factor("sys2_pll_125m", "sys2_pll_125m_cg", 1, 8);
-	clks[IMX8MQ_SYS2_PLL_166M] = imx_clk_fixed_factor("sys2_pll_166m", "sys2_pll_166m_cg", 1, 6);
-	clks[IMX8MQ_SYS2_PLL_200M] = imx_clk_fixed_factor("sys2_pll_200m", "sys2_pll_200m_cg", 1, 5);
-	clks[IMX8MQ_SYS2_PLL_250M] = imx_clk_fixed_factor("sys2_pll_250m", "sys2_pll_250m_cg", 1, 4);
-	clks[IMX8MQ_SYS2_PLL_333M] = imx_clk_fixed_factor("sys2_pll_333m", "sys2_pll_333m_cg", 1, 3);
-	clks[IMX8MQ_SYS2_PLL_500M] = imx_clk_fixed_factor("sys2_pll_500m", "sys2_pll_500m_cg", 1, 2);
-	clks[IMX8MQ_SYS2_PLL_1000M] = imx_clk_fixed_factor("sys2_pll_1000m", "sys2_pll_1000m_cg", 1, 1);
+	hws[IMX8MQ_SYS2_PLL_50M_CG] = imx_clk_hw_gate("sys2_pll_50m_cg", "sys2_pll_out", base + 0x3c, 9);
+	hws[IMX8MQ_SYS2_PLL_100M_CG] = imx_clk_hw_gate("sys2_pll_100m_cg", "sys2_pll_out", base + 0x3c, 11);
+	hws[IMX8MQ_SYS2_PLL_125M_CG] = imx_clk_hw_gate("sys2_pll_125m_cg", "sys2_pll_out", base + 0x3c, 13);
+	hws[IMX8MQ_SYS2_PLL_166M_CG] = imx_clk_hw_gate("sys2_pll_166m_cg", "sys2_pll_out", base + 0x3c, 15);
+	hws[IMX8MQ_SYS2_PLL_200M_CG] = imx_clk_hw_gate("sys2_pll_200m_cg", "sys2_pll_out", base + 0x3c, 17);
+	hws[IMX8MQ_SYS2_PLL_250M_CG] = imx_clk_hw_gate("sys2_pll_250m_cg", "sys2_pll_out", base + 0x3c, 19);
+	hws[IMX8MQ_SYS2_PLL_333M_CG] = imx_clk_hw_gate("sys2_pll_333m_cg", "sys2_pll_out", base + 0x3c, 21);
+	hws[IMX8MQ_SYS2_PLL_500M_CG] = imx_clk_hw_gate("sys2_pll_500m_cg", "sys2_pll_out", base + 0x3c, 23);
+	hws[IMX8MQ_SYS2_PLL_1000M_CG] = imx_clk_hw_gate("sys2_pll_1000m_cg", "sys2_pll_out", base + 0x3c, 25);
+
+	hws[IMX8MQ_SYS2_PLL_50M] = imx_clk_hw_fixed_factor("sys2_pll_50m", "sys2_pll_50m_cg", 1, 20);
+	hws[IMX8MQ_SYS2_PLL_100M] = imx_clk_hw_fixed_factor("sys2_pll_100m", "sys2_pll_100m_cg", 1, 10);
+	hws[IMX8MQ_SYS2_PLL_125M] = imx_clk_hw_fixed_factor("sys2_pll_125m", "sys2_pll_125m_cg", 1, 8);
+	hws[IMX8MQ_SYS2_PLL_166M] = imx_clk_hw_fixed_factor("sys2_pll_166m", "sys2_pll_166m_cg", 1, 6);
+	hws[IMX8MQ_SYS2_PLL_200M] = imx_clk_hw_fixed_factor("sys2_pll_200m", "sys2_pll_200m_cg", 1, 5);
+	hws[IMX8MQ_SYS2_PLL_250M] = imx_clk_hw_fixed_factor("sys2_pll_250m", "sys2_pll_250m_cg", 1, 4);
+	hws[IMX8MQ_SYS2_PLL_333M] = imx_clk_hw_fixed_factor("sys2_pll_333m", "sys2_pll_333m_cg", 1, 3);
+	hws[IMX8MQ_SYS2_PLL_500M] = imx_clk_hw_fixed_factor("sys2_pll_500m", "sys2_pll_500m_cg", 1, 2);
+	hws[IMX8MQ_SYS2_PLL_1000M] = imx_clk_hw_fixed_factor("sys2_pll_1000m", "sys2_pll_1000m_cg", 1, 1);
 
 	np = dev->of_node;
 	base = devm_platform_ioremap_resource(pdev, 0);
@@ -394,206 +402,213 @@ static int imx8mq_clocks_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	/* CORE */
-	clks[IMX8MQ_CLK_A53_SRC] = imx_clk_mux2("arm_a53_src", base + 0x8000, 24, 3, imx8mq_a53_sels, ARRAY_SIZE(imx8mq_a53_sels));
-	clks[IMX8MQ_CLK_M4_SRC] = imx_clk_mux2("arm_m4_src", base + 0x8080, 24, 3, imx8mq_arm_m4_sels, ARRAY_SIZE(imx8mq_arm_m4_sels));
-	clks[IMX8MQ_CLK_VPU_SRC] = imx_clk_mux2("vpu_src", base + 0x8100, 24, 3, imx8mq_vpu_sels, ARRAY_SIZE(imx8mq_vpu_sels));
-	clks[IMX8MQ_CLK_GPU_CORE_SRC] = imx_clk_mux2("gpu_core_src", base + 0x8180, 24, 3,  imx8mq_gpu_core_sels, ARRAY_SIZE(imx8mq_gpu_core_sels));
-	clks[IMX8MQ_CLK_GPU_SHADER_SRC] = imx_clk_mux2("gpu_shader_src", base + 0x8200, 24, 3, imx8mq_gpu_shader_sels,  ARRAY_SIZE(imx8mq_gpu_shader_sels));
-
-	clks[IMX8MQ_CLK_A53_CG] = imx_clk_gate3_flags("arm_a53_cg", "arm_a53_src", base + 0x8000, 28, CLK_IS_CRITICAL);
-	clks[IMX8MQ_CLK_M4_CG] = imx_clk_gate3("arm_m4_cg", "arm_m4_src", base + 0x8080, 28);
-	clks[IMX8MQ_CLK_VPU_CG] = imx_clk_gate3("vpu_cg", "vpu_src", base + 0x8100, 28);
-	clks[IMX8MQ_CLK_GPU_CORE_CG] = imx_clk_gate3("gpu_core_cg", "gpu_core_src", base + 0x8180, 28);
-	clks[IMX8MQ_CLK_GPU_SHADER_CG] = imx_clk_gate3("gpu_shader_cg", "gpu_shader_src", base + 0x8200, 28);
-
-	clks[IMX8MQ_CLK_A53_DIV] = imx_clk_divider2("arm_a53_div", "arm_a53_cg", base + 0x8000, 0, 3);
-	clks[IMX8MQ_CLK_M4_DIV] = imx_clk_divider2("arm_m4_div", "arm_m4_cg", base + 0x8080, 0, 3);
-	clks[IMX8MQ_CLK_VPU_DIV] = imx_clk_divider2("vpu_div", "vpu_cg", base + 0x8100, 0, 3);
-	clks[IMX8MQ_CLK_GPU_CORE_DIV] = imx_clk_divider2("gpu_core_div", "gpu_core_cg", base + 0x8180, 0, 3);
-	clks[IMX8MQ_CLK_GPU_SHADER_DIV] = imx_clk_divider2("gpu_shader_div", "gpu_shader_cg", base + 0x8200, 0, 3);
+	hws[IMX8MQ_CLK_A53_SRC] = imx_clk_hw_mux2("arm_a53_src", base + 0x8000, 24, 3, imx8mq_a53_sels, ARRAY_SIZE(imx8mq_a53_sels));
+	hws[IMX8MQ_CLK_M4_SRC] = imx_clk_hw_mux2("arm_m4_src", base + 0x8080, 24, 3, imx8mq_arm_m4_sels, ARRAY_SIZE(imx8mq_arm_m4_sels));
+	hws[IMX8MQ_CLK_VPU_SRC] = imx_clk_hw_mux2("vpu_src", base + 0x8100, 24, 3, imx8mq_vpu_sels, ARRAY_SIZE(imx8mq_vpu_sels));
+	hws[IMX8MQ_CLK_GPU_CORE_SRC] = imx_clk_hw_mux2("gpu_core_src", base + 0x8180, 24, 3,  imx8mq_gpu_core_sels, ARRAY_SIZE(imx8mq_gpu_core_sels));
+	hws[IMX8MQ_CLK_GPU_SHADER_SRC] = imx_clk_hw_mux2("gpu_shader_src", base + 0x8200, 24, 3, imx8mq_gpu_shader_sels,  ARRAY_SIZE(imx8mq_gpu_shader_sels));
+
+	hws[IMX8MQ_CLK_A53_CG] = imx_clk_hw_gate3_flags("arm_a53_cg", "arm_a53_src", base + 0x8000, 28, CLK_IS_CRITICAL);
+	hws[IMX8MQ_CLK_M4_CG] = imx_clk_hw_gate3("arm_m4_cg", "arm_m4_src", base + 0x8080, 28);
+	hws[IMX8MQ_CLK_VPU_CG] = imx_clk_hw_gate3("vpu_cg", "vpu_src", base + 0x8100, 28);
+	hws[IMX8MQ_CLK_GPU_CORE_CG] = imx_clk_hw_gate3("gpu_core_cg", "gpu_core_src", base + 0x8180, 28);
+	hws[IMX8MQ_CLK_GPU_SHADER_CG] = imx_clk_hw_gate3("gpu_shader_cg", "gpu_shader_src", base + 0x8200, 28);
+
+	hws[IMX8MQ_CLK_A53_DIV] = imx_clk_hw_divider2("arm_a53_div", "arm_a53_cg", base + 0x8000, 0, 3);
+	hws[IMX8MQ_CLK_M4_DIV] = imx_clk_hw_divider2("arm_m4_div", "arm_m4_cg", base + 0x8080, 0, 3);
+	hws[IMX8MQ_CLK_VPU_DIV] = imx_clk_hw_divider2("vpu_div", "vpu_cg", base + 0x8100, 0, 3);
+	hws[IMX8MQ_CLK_GPU_CORE_DIV] = imx_clk_hw_divider2("gpu_core_div", "gpu_core_cg", base + 0x8180, 0, 3);
+	hws[IMX8MQ_CLK_GPU_SHADER_DIV] = imx_clk_hw_divider2("gpu_shader_div", "gpu_shader_cg", base + 0x8200, 0, 3);
 
 	/* BUS */
-	clks[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
-	clks[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_composite("enet_axi", imx8mq_enet_axi_sels, base + 0x8880);
-	clks[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_composite("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900);
-	clks[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_composite("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980);
-	clks[IMX8MQ_CLK_DISP_AXI] = imx8m_clk_composite("disp_axi", imx8mq_disp_axi_sels, base + 0x8a00);
-	clks[IMX8MQ_CLK_DISP_APB] = imx8m_clk_composite("disp_apb", imx8mq_disp_apb_sels, base + 0x8a80);
-	clks[IMX8MQ_CLK_DISP_RTRM] = imx8m_clk_composite("disp_rtrm", imx8mq_disp_rtrm_sels, base + 0x8b00);
-	clks[IMX8MQ_CLK_USB_BUS] = imx8m_clk_composite("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80);
-	clks[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_composite("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00);
-	clks[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_composite("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80);
-	clks[IMX8MQ_CLK_NOC] = imx8m_clk_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00);
-	clks[IMX8MQ_CLK_NOC_APB] = imx8m_clk_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
+	hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800);
+	hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite("enet_axi", imx8mq_enet_axi_sels, base + 0x8880);
+	hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900);
+	hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980);
+	hws[IMX8MQ_CLK_DISP_AXI] = imx8m_clk_hw_composite("disp_axi", imx8mq_disp_axi_sels, base + 0x8a00);
+	hws[IMX8MQ_CLK_DISP_APB] = imx8m_clk_hw_composite("disp_apb", imx8mq_disp_apb_sels, base + 0x8a80);
+	hws[IMX8MQ_CLK_DISP_RTRM] = imx8m_clk_hw_composite("disp_rtrm", imx8mq_disp_rtrm_sels, base + 0x8b00);
+	hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80);
+	hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00);
+	hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80);
+	hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00);
+	hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80);
 
 	/* AHB */
 	/* AHB clock is used by the AHB bus therefore marked as critical */
-	clks[IMX8MQ_CLK_AHB] = imx8m_clk_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
-	clks[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_composite("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100);
+	hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000);
+	hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100);
 
 	/* IPG */
-	clks[IMX8MQ_CLK_IPG_ROOT] = imx_clk_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
-	clks[IMX8MQ_CLK_IPG_AUDIO_ROOT] = imx_clk_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
+	hws[IMX8MQ_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1);
+	hws[IMX8MQ_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1);
+
+	/*
+	 * DRAM clocks are manipulated from TF-A outside clock framework.
+	 * Mark with GET_RATE_NOCACHE to always read div value from hardware
+	 */
+	hws[IMX8MQ_CLK_DRAM_CORE] = imx_clk_hw_mux2_flags("dram_core_clk", base + 0x9800, 24, 1, imx8mq_dram_core_sels, ARRAY_SIZE(imx8mq_dram_core_sels), CLK_IS_CRITICAL);
+	hws[IMX8MQ_CLK_DRAM_ALT] = __imx8m_clk_hw_composite("dram_alt", imx8mq_dram_alt_sels, base + 0xa000, CLK_GET_RATE_NOCACHE);
+	hws[IMX8MQ_CLK_DRAM_APB] = __imx8m_clk_hw_composite("dram_apb", imx8mq_dram_apb_sels, base + 0xa080, CLK_IS_CRITICAL | CLK_GET_RATE_NOCACHE);
 
 	/* IP */
-	clks[IMX8MQ_CLK_DRAM_CORE] = imx_clk_mux2_flags("dram_core_clk", base + 0x9800, 24, 1, imx8mq_dram_core_sels, ARRAY_SIZE(imx8mq_dram_core_sels), CLK_IS_CRITICAL);
-
-	clks[IMX8MQ_CLK_DRAM_ALT] = imx8m_clk_composite("dram_alt", imx8mq_dram_alt_sels, base + 0xa000);
-	clks[IMX8MQ_CLK_DRAM_APB] = imx8m_clk_composite_critical("dram_apb", imx8mq_dram_apb_sels, base + 0xa080);
-	clks[IMX8MQ_CLK_VPU_G1] = imx8m_clk_composite("vpu_g1", imx8mq_vpu_g1_sels, base + 0xa100);
-	clks[IMX8MQ_CLK_VPU_G2] = imx8m_clk_composite("vpu_g2", imx8mq_vpu_g2_sels, base + 0xa180);
-	clks[IMX8MQ_CLK_DISP_DTRC] = imx8m_clk_composite("disp_dtrc", imx8mq_disp_dtrc_sels, base + 0xa200);
-	clks[IMX8MQ_CLK_DISP_DC8000] = imx8m_clk_composite("disp_dc8000", imx8mq_disp_dc8000_sels, base + 0xa280);
-	clks[IMX8MQ_CLK_PCIE1_CTRL] = imx8m_clk_composite("pcie1_ctrl", imx8mq_pcie1_ctrl_sels, base + 0xa300);
-	clks[IMX8MQ_CLK_PCIE1_PHY] = imx8m_clk_composite("pcie1_phy", imx8mq_pcie1_phy_sels, base + 0xa380);
-	clks[IMX8MQ_CLK_PCIE1_AUX] = imx8m_clk_composite("pcie1_aux", imx8mq_pcie1_aux_sels, base + 0xa400);
-	clks[IMX8MQ_CLK_DC_PIXEL] = imx8m_clk_composite("dc_pixel", imx8mq_dc_pixel_sels, base + 0xa480);
-	clks[IMX8MQ_CLK_LCDIF_PIXEL] = imx8m_clk_composite("lcdif_pixel", imx8mq_lcdif_pixel_sels, base + 0xa500);
-	clks[IMX8MQ_CLK_SAI1] = imx8m_clk_composite("sai1", imx8mq_sai1_sels, base + 0xa580);
-	clks[IMX8MQ_CLK_SAI2] = imx8m_clk_composite("sai2", imx8mq_sai2_sels, base + 0xa600);
-	clks[IMX8MQ_CLK_SAI3] = imx8m_clk_composite("sai3", imx8mq_sai3_sels, base + 0xa680);
-	clks[IMX8MQ_CLK_SAI4] = imx8m_clk_composite("sai4", imx8mq_sai4_sels, base + 0xa700);
-	clks[IMX8MQ_CLK_SAI5] = imx8m_clk_composite("sai5", imx8mq_sai5_sels, base + 0xa780);
-	clks[IMX8MQ_CLK_SAI6] = imx8m_clk_composite("sai6", imx8mq_sai6_sels, base + 0xa800);
-	clks[IMX8MQ_CLK_SPDIF1] = imx8m_clk_composite("spdif1", imx8mq_spdif1_sels, base + 0xa880);
-	clks[IMX8MQ_CLK_SPDIF2] = imx8m_clk_composite("spdif2", imx8mq_spdif2_sels, base + 0xa900);
-	clks[IMX8MQ_CLK_ENET_REF] = imx8m_clk_composite("enet_ref", imx8mq_enet_ref_sels, base + 0xa980);
-	clks[IMX8MQ_CLK_ENET_TIMER] = imx8m_clk_composite("enet_timer", imx8mq_enet_timer_sels, base + 0xaa00);
-	clks[IMX8MQ_CLK_ENET_PHY_REF] = imx8m_clk_composite("enet_phy", imx8mq_enet_phy_sels, base + 0xaa80);
-	clks[IMX8MQ_CLK_NAND] = imx8m_clk_composite("nand", imx8mq_nand_sels, base + 0xab00);
-	clks[IMX8MQ_CLK_QSPI] = imx8m_clk_composite("qspi", imx8mq_qspi_sels, base + 0xab80);
-	clks[IMX8MQ_CLK_USDHC1] = imx8m_clk_composite("usdhc1", imx8mq_usdhc1_sels, base + 0xac00);
-	clks[IMX8MQ_CLK_USDHC2] = imx8m_clk_composite("usdhc2", imx8mq_usdhc2_sels, base + 0xac80);
-	clks[IMX8MQ_CLK_I2C1] = imx8m_clk_composite("i2c1", imx8mq_i2c1_sels, base + 0xad00);
-	clks[IMX8MQ_CLK_I2C2] = imx8m_clk_composite("i2c2", imx8mq_i2c2_sels, base + 0xad80);
-	clks[IMX8MQ_CLK_I2C3] = imx8m_clk_composite("i2c3", imx8mq_i2c3_sels, base + 0xae00);
-	clks[IMX8MQ_CLK_I2C4] = imx8m_clk_composite("i2c4", imx8mq_i2c4_sels, base + 0xae80);
-	clks[IMX8MQ_CLK_UART1] = imx8m_clk_composite("uart1", imx8mq_uart1_sels, base + 0xaf00);
-	clks[IMX8MQ_CLK_UART2] = imx8m_clk_composite("uart2", imx8mq_uart2_sels, base + 0xaf80);
-	clks[IMX8MQ_CLK_UART3] = imx8m_clk_composite("uart3", imx8mq_uart3_sels, base + 0xb000);
-	clks[IMX8MQ_CLK_UART4] = imx8m_clk_composite("uart4", imx8mq_uart4_sels, base + 0xb080);
-	clks[IMX8MQ_CLK_USB_CORE_REF] = imx8m_clk_composite("usb_core_ref", imx8mq_usb_core_sels, base + 0xb100);
-	clks[IMX8MQ_CLK_USB_PHY_REF] = imx8m_clk_composite("usb_phy_ref", imx8mq_usb_phy_sels, base + 0xb180);
-	clks[IMX8MQ_CLK_GIC] = imx8m_clk_composite_critical("gic", imx8mq_gic_sels, base + 0xb200);
-	clks[IMX8MQ_CLK_ECSPI1] = imx8m_clk_composite("ecspi1", imx8mq_ecspi1_sels, base + 0xb280);
-	clks[IMX8MQ_CLK_ECSPI2] = imx8m_clk_composite("ecspi2", imx8mq_ecspi2_sels, base + 0xb300);
-	clks[IMX8MQ_CLK_PWM1] = imx8m_clk_composite("pwm1", imx8mq_pwm1_sels, base + 0xb380);
-	clks[IMX8MQ_CLK_PWM2] = imx8m_clk_composite("pwm2", imx8mq_pwm2_sels, base + 0xb400);
-	clks[IMX8MQ_CLK_PWM3] = imx8m_clk_composite("pwm3", imx8mq_pwm3_sels, base + 0xb480);
-	clks[IMX8MQ_CLK_PWM4] = imx8m_clk_composite("pwm4", imx8mq_pwm4_sels, base + 0xb500);
-	clks[IMX8MQ_CLK_GPT1] = imx8m_clk_composite("gpt1", imx8mq_gpt1_sels, base + 0xb580);
-	clks[IMX8MQ_CLK_WDOG] = imx8m_clk_composite("wdog", imx8mq_wdog_sels, base + 0xb900);
-	clks[IMX8MQ_CLK_WRCLK] = imx8m_clk_composite("wrclk", imx8mq_wrclk_sels, base + 0xb980);
-	clks[IMX8MQ_CLK_CLKO1] = imx8m_clk_composite("clko1", imx8mq_clko1_sels, base + 0xba00);
-	clks[IMX8MQ_CLK_CLKO2] = imx8m_clk_composite("clko2", imx8mq_clko2_sels, base + 0xba80);
-	clks[IMX8MQ_CLK_DSI_CORE] = imx8m_clk_composite("dsi_core", imx8mq_dsi_core_sels, base + 0xbb00);
-	clks[IMX8MQ_CLK_DSI_PHY_REF] = imx8m_clk_composite("dsi_phy_ref", imx8mq_dsi_phy_sels, base + 0xbb80);
-	clks[IMX8MQ_CLK_DSI_DBI] = imx8m_clk_composite("dsi_dbi", imx8mq_dsi_dbi_sels, base + 0xbc00);
-	clks[IMX8MQ_CLK_DSI_ESC] = imx8m_clk_composite("dsi_esc", imx8mq_dsi_esc_sels, base + 0xbc80);
-	clks[IMX8MQ_CLK_DSI_AHB] = imx8m_clk_composite("dsi_ahb", imx8mq_dsi_ahb_sels, base + 0x9200);
-	clks[IMX8MQ_CLK_DSI_IPG_DIV] = imx_clk_divider2("dsi_ipg_div", "dsi_ahb", base + 0x9280, 0, 6);
-	clks[IMX8MQ_CLK_CSI1_CORE] = imx8m_clk_composite("csi1_core", imx8mq_csi1_core_sels, base + 0xbd00);
-	clks[IMX8MQ_CLK_CSI1_PHY_REF] = imx8m_clk_composite("csi1_phy_ref", imx8mq_csi1_phy_sels, base + 0xbd80);
-	clks[IMX8MQ_CLK_CSI1_ESC] = imx8m_clk_composite("csi1_esc", imx8mq_csi1_esc_sels, base + 0xbe00);
-	clks[IMX8MQ_CLK_CSI2_CORE] = imx8m_clk_composite("csi2_core", imx8mq_csi2_core_sels, base + 0xbe80);
-	clks[IMX8MQ_CLK_CSI2_PHY_REF] = imx8m_clk_composite("csi2_phy_ref", imx8mq_csi2_phy_sels, base + 0xbf00);
-	clks[IMX8MQ_CLK_CSI2_ESC] = imx8m_clk_composite("csi2_esc", imx8mq_csi2_esc_sels, base + 0xbf80);
-	clks[IMX8MQ_CLK_PCIE2_CTRL] = imx8m_clk_composite("pcie2_ctrl", imx8mq_pcie2_ctrl_sels, base + 0xc000);
-	clks[IMX8MQ_CLK_PCIE2_PHY] = imx8m_clk_composite("pcie2_phy", imx8mq_pcie2_phy_sels, base + 0xc080);
-	clks[IMX8MQ_CLK_PCIE2_AUX] = imx8m_clk_composite("pcie2_aux", imx8mq_pcie2_aux_sels, base + 0xc100);
-	clks[IMX8MQ_CLK_ECSPI3] = imx8m_clk_composite("ecspi3", imx8mq_ecspi3_sels, base + 0xc180);
-
-	clks[IMX8MQ_CLK_ECSPI1_ROOT] = imx_clk_gate4("ecspi1_root_clk", "ecspi1", base + 0x4070, 0);
-	clks[IMX8MQ_CLK_ECSPI2_ROOT] = imx_clk_gate4("ecspi2_root_clk", "ecspi2", base + 0x4080, 0);
-	clks[IMX8MQ_CLK_ECSPI3_ROOT] = imx_clk_gate4("ecspi3_root_clk", "ecspi3", base + 0x4090, 0);
-	clks[IMX8MQ_CLK_ENET1_ROOT] = imx_clk_gate4("enet1_root_clk", "enet_axi", base + 0x40a0, 0);
-	clks[IMX8MQ_CLK_GPIO1_ROOT] = imx_clk_gate4("gpio1_root_clk", "ipg_root", base + 0x40b0, 0);
-	clks[IMX8MQ_CLK_GPIO2_ROOT] = imx_clk_gate4("gpio2_root_clk", "ipg_root", base + 0x40c0, 0);
-	clks[IMX8MQ_CLK_GPIO3_ROOT] = imx_clk_gate4("gpio3_root_clk", "ipg_root", base + 0x40d0, 0);
-	clks[IMX8MQ_CLK_GPIO4_ROOT] = imx_clk_gate4("gpio4_root_clk", "ipg_root", base + 0x40e0, 0);
-	clks[IMX8MQ_CLK_GPIO5_ROOT] = imx_clk_gate4("gpio5_root_clk", "ipg_root", base + 0x40f0, 0);
-	clks[IMX8MQ_CLK_GPT1_ROOT] = imx_clk_gate4("gpt1_root_clk", "gpt1", base + 0x4100, 0);
-	clks[IMX8MQ_CLK_I2C1_ROOT] = imx_clk_gate4("i2c1_root_clk", "i2c1", base + 0x4170, 0);
-	clks[IMX8MQ_CLK_I2C2_ROOT] = imx_clk_gate4("i2c2_root_clk", "i2c2", base + 0x4180, 0);
-	clks[IMX8MQ_CLK_I2C3_ROOT] = imx_clk_gate4("i2c3_root_clk", "i2c3", base + 0x4190, 0);
-	clks[IMX8MQ_CLK_I2C4_ROOT] = imx_clk_gate4("i2c4_root_clk", "i2c4", base + 0x41a0, 0);
-	clks[IMX8MQ_CLK_MU_ROOT] = imx_clk_gate4("mu_root_clk", "ipg_root", base + 0x4210, 0);
-	clks[IMX8MQ_CLK_OCOTP_ROOT] = imx_clk_gate4("ocotp_root_clk", "ipg_root", base + 0x4220, 0);
-	clks[IMX8MQ_CLK_PCIE1_ROOT] = imx_clk_gate4("pcie1_root_clk", "pcie1_ctrl", base + 0x4250, 0);
-	clks[IMX8MQ_CLK_PCIE2_ROOT] = imx_clk_gate4("pcie2_root_clk", "pcie2_ctrl", base + 0x4640, 0);
-	clks[IMX8MQ_CLK_PWM1_ROOT] = imx_clk_gate4("pwm1_root_clk", "pwm1", base + 0x4280, 0);
-	clks[IMX8MQ_CLK_PWM2_ROOT] = imx_clk_gate4("pwm2_root_clk", "pwm2", base + 0x4290, 0);
-	clks[IMX8MQ_CLK_PWM3_ROOT] = imx_clk_gate4("pwm3_root_clk", "pwm3", base + 0x42a0, 0);
-	clks[IMX8MQ_CLK_PWM4_ROOT] = imx_clk_gate4("pwm4_root_clk", "pwm4", base + 0x42b0, 0);
-	clks[IMX8MQ_CLK_QSPI_ROOT] = imx_clk_gate4("qspi_root_clk", "qspi", base + 0x42f0, 0);
-	clks[IMX8MQ_CLK_RAWNAND_ROOT] = imx_clk_gate2_shared2("nand_root_clk", "nand", base + 0x4300, 0, &share_count_nand);
-	clks[IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", base + 0x4300, 0, &share_count_nand);
-	clks[IMX8MQ_CLK_SAI1_ROOT] = imx_clk_gate2_shared2("sai1_root_clk", "sai1", base + 0x4330, 0, &share_count_sai1);
-	clks[IMX8MQ_CLK_SAI1_IPG] = imx_clk_gate2_shared2("sai1_ipg_clk", "ipg_audio_root", base + 0x4330, 0, &share_count_sai1);
-	clks[IMX8MQ_CLK_SAI2_ROOT] = imx_clk_gate2_shared2("sai2_root_clk", "sai2", base + 0x4340, 0, &share_count_sai2);
-	clks[IMX8MQ_CLK_SAI2_IPG] = imx_clk_gate2_shared2("sai2_ipg_clk", "ipg_root", base + 0x4340, 0, &share_count_sai2);
-	clks[IMX8MQ_CLK_SAI3_ROOT] = imx_clk_gate2_shared2("sai3_root_clk", "sai3", base + 0x4350, 0, &share_count_sai3);
-	clks[IMX8MQ_CLK_SAI3_IPG] = imx_clk_gate2_shared2("sai3_ipg_clk", "ipg_root", base + 0x4350, 0, &share_count_sai3);
-	clks[IMX8MQ_CLK_SAI4_ROOT] = imx_clk_gate2_shared2("sai4_root_clk", "sai4", base + 0x4360, 0, &share_count_sai4);
-	clks[IMX8MQ_CLK_SAI4_IPG] = imx_clk_gate2_shared2("sai4_ipg_clk", "ipg_audio_root", base + 0x4360, 0, &share_count_sai4);
-	clks[IMX8MQ_CLK_SAI5_ROOT] = imx_clk_gate2_shared2("sai5_root_clk", "sai5", base + 0x4370, 0, &share_count_sai5);
-	clks[IMX8MQ_CLK_SAI5_IPG] = imx_clk_gate2_shared2("sai5_ipg_clk", "ipg_audio_root", base + 0x4370, 0, &share_count_sai5);
-	clks[IMX8MQ_CLK_SAI6_ROOT] = imx_clk_gate2_shared2("sai6_root_clk", "sai6", base + 0x4380, 0, &share_count_sai6);
-	clks[IMX8MQ_CLK_SAI6_IPG] = imx_clk_gate2_shared2("sai6_ipg_clk", "ipg_audio_root", base + 0x4380, 0, &share_count_sai6);
-	clks[IMX8MQ_CLK_SNVS_ROOT] = imx_clk_gate4("snvs_root_clk", "ipg_root", base + 0x4470, 0);
-	clks[IMX8MQ_CLK_UART1_ROOT] = imx_clk_gate4("uart1_root_clk", "uart1", base + 0x4490, 0);
-	clks[IMX8MQ_CLK_UART2_ROOT] = imx_clk_gate4("uart2_root_clk", "uart2", base + 0x44a0, 0);
-	clks[IMX8MQ_CLK_UART3_ROOT] = imx_clk_gate4("uart3_root_clk", "uart3", base + 0x44b0, 0);
-	clks[IMX8MQ_CLK_UART4_ROOT] = imx_clk_gate4("uart4_root_clk", "uart4", base + 0x44c0, 0);
-	clks[IMX8MQ_CLK_USB1_CTRL_ROOT] = imx_clk_gate4("usb1_ctrl_root_clk", "usb_bus", base + 0x44d0, 0);
-	clks[IMX8MQ_CLK_USB2_CTRL_ROOT] = imx_clk_gate4("usb2_ctrl_root_clk", "usb_bus", base + 0x44e0, 0);
-	clks[IMX8MQ_CLK_USB1_PHY_ROOT] = imx_clk_gate4("usb1_phy_root_clk", "usb_phy_ref", base + 0x44f0, 0);
-	clks[IMX8MQ_CLK_USB2_PHY_ROOT] = imx_clk_gate4("usb2_phy_root_clk", "usb_phy_ref", base + 0x4500, 0);
-	clks[IMX8MQ_CLK_USDHC1_ROOT] = imx_clk_gate4("usdhc1_root_clk", "usdhc1", base + 0x4510, 0);
-	clks[IMX8MQ_CLK_USDHC2_ROOT] = imx_clk_gate4("usdhc2_root_clk", "usdhc2", base + 0x4520, 0);
-	clks[IMX8MQ_CLK_WDOG1_ROOT] = imx_clk_gate4("wdog1_root_clk", "wdog", base + 0x4530, 0);
-	clks[IMX8MQ_CLK_WDOG2_ROOT] = imx_clk_gate4("wdog2_root_clk", "wdog", base + 0x4540, 0);
-	clks[IMX8MQ_CLK_WDOG3_ROOT] = imx_clk_gate4("wdog3_root_clk", "wdog", base + 0x4550, 0);
-	clks[IMX8MQ_CLK_VPU_G1_ROOT] = imx_clk_gate2_flags("vpu_g1_root_clk", "vpu_g1", base + 0x4560, 0, CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
-	clks[IMX8MQ_CLK_GPU_ROOT] = imx_clk_gate4("gpu_root_clk", "gpu_core_div", base + 0x4570, 0);
-	clks[IMX8MQ_CLK_VPU_G2_ROOT] = imx_clk_gate2_flags("vpu_g2_root_clk", "vpu_g2", base + 0x45a0, 0, CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
-	clks[IMX8MQ_CLK_DISP_ROOT] = imx_clk_gate2_shared2("disp_root_clk", "disp_dc8000", base + 0x45d0, 0, &share_count_dcss);
-	clks[IMX8MQ_CLK_DISP_AXI_ROOT]  = imx_clk_gate2_shared2("disp_axi_root_clk", "disp_axi", base + 0x45d0, 0, &share_count_dcss);
-	clks[IMX8MQ_CLK_DISP_APB_ROOT]  = imx_clk_gate2_shared2("disp_apb_root_clk", "disp_apb", base + 0x45d0, 0, &share_count_dcss);
-	clks[IMX8MQ_CLK_DISP_RTRM_ROOT] = imx_clk_gate2_shared2("disp_rtrm_root_clk", "disp_rtrm", base + 0x45d0, 0, &share_count_dcss);
-	clks[IMX8MQ_CLK_TMU_ROOT] = imx_clk_gate4("tmu_root_clk", "ipg_root", base + 0x4620, 0);
-	clks[IMX8MQ_CLK_VPU_DEC_ROOT] = imx_clk_gate2_flags("vpu_dec_root_clk", "vpu_bus", base + 0x4630, 0, CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
-	clks[IMX8MQ_CLK_CSI1_ROOT] = imx_clk_gate4("csi1_root_clk", "csi1_core", base + 0x4650, 0);
-	clks[IMX8MQ_CLK_CSI2_ROOT] = imx_clk_gate4("csi2_root_clk", "csi2_core", base + 0x4660, 0);
-	clks[IMX8MQ_CLK_SDMA1_ROOT] = imx_clk_gate4("sdma1_clk", "ipg_root", base + 0x43a0, 0);
-	clks[IMX8MQ_CLK_SDMA2_ROOT] = imx_clk_gate4("sdma2_clk", "ipg_audio_root", base + 0x43b0, 0);
-
-	clks[IMX8MQ_GPT_3M_CLK] = imx_clk_fixed_factor("gpt_3m", "osc_25m", 1, 8);
-	clks[IMX8MQ_CLK_DRAM_ALT_ROOT] = imx_clk_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
-
-	clks[IMX8MQ_CLK_ARM] = imx_clk_cpu("arm", "arm_a53_div",
-					   clks[IMX8MQ_CLK_A53_DIV],
-					   clks[IMX8MQ_CLK_A53_SRC],
-					   clks[IMX8MQ_ARM_PLL_OUT],
-					   clks[IMX8MQ_SYS1_PLL_800M]);
-
-	imx_check_clocks(clks, ARRAY_SIZE(clks));
-
-	clk_data.clks = clks;
-	clk_data.clk_num = ARRAY_SIZE(clks);
-
-	err = of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
+	hws[IMX8MQ_CLK_VPU_G1] = imx8m_clk_hw_composite("vpu_g1", imx8mq_vpu_g1_sels, base + 0xa100);
+	hws[IMX8MQ_CLK_VPU_G2] = imx8m_clk_hw_composite("vpu_g2", imx8mq_vpu_g2_sels, base + 0xa180);
+	hws[IMX8MQ_CLK_DISP_DTRC] = imx8m_clk_hw_composite("disp_dtrc", imx8mq_disp_dtrc_sels, base + 0xa200);
+	hws[IMX8MQ_CLK_DISP_DC8000] = imx8m_clk_hw_composite("disp_dc8000", imx8mq_disp_dc8000_sels, base + 0xa280);
+	hws[IMX8MQ_CLK_PCIE1_CTRL] = imx8m_clk_hw_composite("pcie1_ctrl", imx8mq_pcie1_ctrl_sels, base + 0xa300);
+	hws[IMX8MQ_CLK_PCIE1_PHY] = imx8m_clk_hw_composite("pcie1_phy", imx8mq_pcie1_phy_sels, base + 0xa380);
+	hws[IMX8MQ_CLK_PCIE1_AUX] = imx8m_clk_hw_composite("pcie1_aux", imx8mq_pcie1_aux_sels, base + 0xa400);
+	hws[IMX8MQ_CLK_DC_PIXEL] = imx8m_clk_hw_composite("dc_pixel", imx8mq_dc_pixel_sels, base + 0xa480);
+	hws[IMX8MQ_CLK_LCDIF_PIXEL] = imx8m_clk_hw_composite("lcdif_pixel", imx8mq_lcdif_pixel_sels, base + 0xa500);
+	hws[IMX8MQ_CLK_SAI1] = imx8m_clk_hw_composite("sai1", imx8mq_sai1_sels, base + 0xa580);
+	hws[IMX8MQ_CLK_SAI2] = imx8m_clk_hw_composite("sai2", imx8mq_sai2_sels, base + 0xa600);
+	hws[IMX8MQ_CLK_SAI3] = imx8m_clk_hw_composite("sai3", imx8mq_sai3_sels, base + 0xa680);
+	hws[IMX8MQ_CLK_SAI4] = imx8m_clk_hw_composite("sai4", imx8mq_sai4_sels, base + 0xa700);
+	hws[IMX8MQ_CLK_SAI5] = imx8m_clk_hw_composite("sai5", imx8mq_sai5_sels, base + 0xa780);
+	hws[IMX8MQ_CLK_SAI6] = imx8m_clk_hw_composite("sai6", imx8mq_sai6_sels, base + 0xa800);
+	hws[IMX8MQ_CLK_SPDIF1] = imx8m_clk_hw_composite("spdif1", imx8mq_spdif1_sels, base + 0xa880);
+	hws[IMX8MQ_CLK_SPDIF2] = imx8m_clk_hw_composite("spdif2", imx8mq_spdif2_sels, base + 0xa900);
+	hws[IMX8MQ_CLK_ENET_REF] = imx8m_clk_hw_composite("enet_ref", imx8mq_enet_ref_sels, base + 0xa980);
+	hws[IMX8MQ_CLK_ENET_TIMER] = imx8m_clk_hw_composite("enet_timer", imx8mq_enet_timer_sels, base + 0xaa00);
+	hws[IMX8MQ_CLK_ENET_PHY_REF] = imx8m_clk_hw_composite("enet_phy", imx8mq_enet_phy_sels, base + 0xaa80);
+	hws[IMX8MQ_CLK_NAND] = imx8m_clk_hw_composite("nand", imx8mq_nand_sels, base + 0xab00);
+	hws[IMX8MQ_CLK_QSPI] = imx8m_clk_hw_composite("qspi", imx8mq_qspi_sels, base + 0xab80);
+	hws[IMX8MQ_CLK_USDHC1] = imx8m_clk_hw_composite("usdhc1", imx8mq_usdhc1_sels, base + 0xac00);
+	hws[IMX8MQ_CLK_USDHC2] = imx8m_clk_hw_composite("usdhc2", imx8mq_usdhc2_sels, base + 0xac80);
+	hws[IMX8MQ_CLK_I2C1] = imx8m_clk_hw_composite("i2c1", imx8mq_i2c1_sels, base + 0xad00);
+	hws[IMX8MQ_CLK_I2C2] = imx8m_clk_hw_composite("i2c2", imx8mq_i2c2_sels, base + 0xad80);
+	hws[IMX8MQ_CLK_I2C3] = imx8m_clk_hw_composite("i2c3", imx8mq_i2c3_sels, base + 0xae00);
+	hws[IMX8MQ_CLK_I2C4] = imx8m_clk_hw_composite("i2c4", imx8mq_i2c4_sels, base + 0xae80);
+	hws[IMX8MQ_CLK_UART1] = imx8m_clk_hw_composite("uart1", imx8mq_uart1_sels, base + 0xaf00);
+	hws[IMX8MQ_CLK_UART2] = imx8m_clk_hw_composite("uart2", imx8mq_uart2_sels, base + 0xaf80);
+	hws[IMX8MQ_CLK_UART3] = imx8m_clk_hw_composite("uart3", imx8mq_uart3_sels, base + 0xb000);
+	hws[IMX8MQ_CLK_UART4] = imx8m_clk_hw_composite("uart4", imx8mq_uart4_sels, base + 0xb080);
+	hws[IMX8MQ_CLK_USB_CORE_REF] = imx8m_clk_hw_composite("usb_core_ref", imx8mq_usb_core_sels, base + 0xb100);
+	hws[IMX8MQ_CLK_USB_PHY_REF] = imx8m_clk_hw_composite("usb_phy_ref", imx8mq_usb_phy_sels, base + 0xb180);
+	hws[IMX8MQ_CLK_GIC] = imx8m_clk_hw_composite_critical("gic", imx8mq_gic_sels, base + 0xb200);
+	hws[IMX8MQ_CLK_ECSPI1] = imx8m_clk_hw_composite("ecspi1", imx8mq_ecspi1_sels, base + 0xb280);
+	hws[IMX8MQ_CLK_ECSPI2] = imx8m_clk_hw_composite("ecspi2", imx8mq_ecspi2_sels, base + 0xb300);
+	hws[IMX8MQ_CLK_PWM1] = imx8m_clk_hw_composite("pwm1", imx8mq_pwm1_sels, base + 0xb380);
+	hws[IMX8MQ_CLK_PWM2] = imx8m_clk_hw_composite("pwm2", imx8mq_pwm2_sels, base + 0xb400);
+	hws[IMX8MQ_CLK_PWM3] = imx8m_clk_hw_composite("pwm3", imx8mq_pwm3_sels, base + 0xb480);
+	hws[IMX8MQ_CLK_PWM4] = imx8m_clk_hw_composite("pwm4", imx8mq_pwm4_sels, base + 0xb500);
+	hws[IMX8MQ_CLK_GPT1] = imx8m_clk_hw_composite("gpt1", imx8mq_gpt1_sels, base + 0xb580);
+	hws[IMX8MQ_CLK_WDOG] = imx8m_clk_hw_composite("wdog", imx8mq_wdog_sels, base + 0xb900);
+	hws[IMX8MQ_CLK_WRCLK] = imx8m_clk_hw_composite("wrclk", imx8mq_wrclk_sels, base + 0xb980);
+	hws[IMX8MQ_CLK_CLKO1] = imx8m_clk_hw_composite("clko1", imx8mq_clko1_sels, base + 0xba00);
+	hws[IMX8MQ_CLK_CLKO2] = imx8m_clk_hw_composite("clko2", imx8mq_clko2_sels, base + 0xba80);
+	hws[IMX8MQ_CLK_DSI_CORE] = imx8m_clk_hw_composite("dsi_core", imx8mq_dsi_core_sels, base + 0xbb00);
+	hws[IMX8MQ_CLK_DSI_PHY_REF] = imx8m_clk_hw_composite("dsi_phy_ref", imx8mq_dsi_phy_sels, base + 0xbb80);
+	hws[IMX8MQ_CLK_DSI_DBI] = imx8m_clk_hw_composite("dsi_dbi", imx8mq_dsi_dbi_sels, base + 0xbc00);
+	hws[IMX8MQ_CLK_DSI_ESC] = imx8m_clk_hw_composite("dsi_esc", imx8mq_dsi_esc_sels, base + 0xbc80);
+	hws[IMX8MQ_CLK_DSI_AHB] = imx8m_clk_hw_composite("dsi_ahb", imx8mq_dsi_ahb_sels, base + 0x9200);
+	hws[IMX8MQ_CLK_DSI_IPG_DIV] = imx_clk_hw_divider2("dsi_ipg_div", "dsi_ahb", base + 0x9280, 0, 6);
+	hws[IMX8MQ_CLK_CSI1_CORE] = imx8m_clk_hw_composite("csi1_core", imx8mq_csi1_core_sels, base + 0xbd00);
+	hws[IMX8MQ_CLK_CSI1_PHY_REF] = imx8m_clk_hw_composite("csi1_phy_ref", imx8mq_csi1_phy_sels, base + 0xbd80);
+	hws[IMX8MQ_CLK_CSI1_ESC] = imx8m_clk_hw_composite("csi1_esc", imx8mq_csi1_esc_sels, base + 0xbe00);
+	hws[IMX8MQ_CLK_CSI2_CORE] = imx8m_clk_hw_composite("csi2_core", imx8mq_csi2_core_sels, base + 0xbe80);
+	hws[IMX8MQ_CLK_CSI2_PHY_REF] = imx8m_clk_hw_composite("csi2_phy_ref", imx8mq_csi2_phy_sels, base + 0xbf00);
+	hws[IMX8MQ_CLK_CSI2_ESC] = imx8m_clk_hw_composite("csi2_esc", imx8mq_csi2_esc_sels, base + 0xbf80);
+	hws[IMX8MQ_CLK_PCIE2_CTRL] = imx8m_clk_hw_composite("pcie2_ctrl", imx8mq_pcie2_ctrl_sels, base + 0xc000);
+	hws[IMX8MQ_CLK_PCIE2_PHY] = imx8m_clk_hw_composite("pcie2_phy", imx8mq_pcie2_phy_sels, base + 0xc080);
+	hws[IMX8MQ_CLK_PCIE2_AUX] = imx8m_clk_hw_composite("pcie2_aux", imx8mq_pcie2_aux_sels, base + 0xc100);
+	hws[IMX8MQ_CLK_ECSPI3] = imx8m_clk_hw_composite("ecspi3", imx8mq_ecspi3_sels, base + 0xc180);
+
+	hws[IMX8MQ_CLK_ECSPI1_ROOT] = imx_clk_hw_gate4("ecspi1_root_clk", "ecspi1", base + 0x4070, 0);
+	hws[IMX8MQ_CLK_ECSPI2_ROOT] = imx_clk_hw_gate4("ecspi2_root_clk", "ecspi2", base + 0x4080, 0);
+	hws[IMX8MQ_CLK_ECSPI3_ROOT] = imx_clk_hw_gate4("ecspi3_root_clk", "ecspi3", base + 0x4090, 0);
+	hws[IMX8MQ_CLK_ENET1_ROOT] = imx_clk_hw_gate4("enet1_root_clk", "enet_axi", base + 0x40a0, 0);
+	hws[IMX8MQ_CLK_GPIO1_ROOT] = imx_clk_hw_gate4("gpio1_root_clk", "ipg_root", base + 0x40b0, 0);
+	hws[IMX8MQ_CLK_GPIO2_ROOT] = imx_clk_hw_gate4("gpio2_root_clk", "ipg_root", base + 0x40c0, 0);
+	hws[IMX8MQ_CLK_GPIO3_ROOT] = imx_clk_hw_gate4("gpio3_root_clk", "ipg_root", base + 0x40d0, 0);
+	hws[IMX8MQ_CLK_GPIO4_ROOT] = imx_clk_hw_gate4("gpio4_root_clk", "ipg_root", base + 0x40e0, 0);
+	hws[IMX8MQ_CLK_GPIO5_ROOT] = imx_clk_hw_gate4("gpio5_root_clk", "ipg_root", base + 0x40f0, 0);
+	hws[IMX8MQ_CLK_GPT1_ROOT] = imx_clk_hw_gate4("gpt1_root_clk", "gpt1", base + 0x4100, 0);
+	hws[IMX8MQ_CLK_I2C1_ROOT] = imx_clk_hw_gate4("i2c1_root_clk", "i2c1", base + 0x4170, 0);
+	hws[IMX8MQ_CLK_I2C2_ROOT] = imx_clk_hw_gate4("i2c2_root_clk", "i2c2", base + 0x4180, 0);
+	hws[IMX8MQ_CLK_I2C3_ROOT] = imx_clk_hw_gate4("i2c3_root_clk", "i2c3", base + 0x4190, 0);
+	hws[IMX8MQ_CLK_I2C4_ROOT] = imx_clk_hw_gate4("i2c4_root_clk", "i2c4", base + 0x41a0, 0);
+	hws[IMX8MQ_CLK_MU_ROOT] = imx_clk_hw_gate4("mu_root_clk", "ipg_root", base + 0x4210, 0);
+	hws[IMX8MQ_CLK_OCOTP_ROOT] = imx_clk_hw_gate4("ocotp_root_clk", "ipg_root", base + 0x4220, 0);
+	hws[IMX8MQ_CLK_PCIE1_ROOT] = imx_clk_hw_gate4("pcie1_root_clk", "pcie1_ctrl", base + 0x4250, 0);
+	hws[IMX8MQ_CLK_PCIE2_ROOT] = imx_clk_hw_gate4("pcie2_root_clk", "pcie2_ctrl", base + 0x4640, 0);
+	hws[IMX8MQ_CLK_PWM1_ROOT] = imx_clk_hw_gate4("pwm1_root_clk", "pwm1", base + 0x4280, 0);
+	hws[IMX8MQ_CLK_PWM2_ROOT] = imx_clk_hw_gate4("pwm2_root_clk", "pwm2", base + 0x4290, 0);
+	hws[IMX8MQ_CLK_PWM3_ROOT] = imx_clk_hw_gate4("pwm3_root_clk", "pwm3", base + 0x42a0, 0);
+	hws[IMX8MQ_CLK_PWM4_ROOT] = imx_clk_hw_gate4("pwm4_root_clk", "pwm4", base + 0x42b0, 0);
+	hws[IMX8MQ_CLK_QSPI_ROOT] = imx_clk_hw_gate4("qspi_root_clk", "qspi", base + 0x42f0, 0);
+	hws[IMX8MQ_CLK_RAWNAND_ROOT] = imx_clk_hw_gate2_shared2("nand_root_clk", "nand", base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK] = imx_clk_hw_gate2_shared2("nand_usdhc_rawnand_clk", "nand_usdhc_bus", base + 0x4300, 0, &share_count_nand);
+	hws[IMX8MQ_CLK_SAI1_ROOT] = imx_clk_hw_gate2_shared2("sai1_root_clk", "sai1", base + 0x4330, 0, &share_count_sai1);
+	hws[IMX8MQ_CLK_SAI1_IPG] = imx_clk_hw_gate2_shared2("sai1_ipg_clk", "ipg_audio_root", base + 0x4330, 0, &share_count_sai1);
+	hws[IMX8MQ_CLK_SAI2_ROOT] = imx_clk_hw_gate2_shared2("sai2_root_clk", "sai2", base + 0x4340, 0, &share_count_sai2);
+	hws[IMX8MQ_CLK_SAI2_IPG] = imx_clk_hw_gate2_shared2("sai2_ipg_clk", "ipg_root", base + 0x4340, 0, &share_count_sai2);
+	hws[IMX8MQ_CLK_SAI3_ROOT] = imx_clk_hw_gate2_shared2("sai3_root_clk", "sai3", base + 0x4350, 0, &share_count_sai3);
+	hws[IMX8MQ_CLK_SAI3_IPG] = imx_clk_hw_gate2_shared2("sai3_ipg_clk", "ipg_root", base + 0x4350, 0, &share_count_sai3);
+	hws[IMX8MQ_CLK_SAI4_ROOT] = imx_clk_hw_gate2_shared2("sai4_root_clk", "sai4", base + 0x4360, 0, &share_count_sai4);
+	hws[IMX8MQ_CLK_SAI4_IPG] = imx_clk_hw_gate2_shared2("sai4_ipg_clk", "ipg_audio_root", base + 0x4360, 0, &share_count_sai4);
+	hws[IMX8MQ_CLK_SAI5_ROOT] = imx_clk_hw_gate2_shared2("sai5_root_clk", "sai5", base + 0x4370, 0, &share_count_sai5);
+	hws[IMX8MQ_CLK_SAI5_IPG] = imx_clk_hw_gate2_shared2("sai5_ipg_clk", "ipg_audio_root", base + 0x4370, 0, &share_count_sai5);
+	hws[IMX8MQ_CLK_SAI6_ROOT] = imx_clk_hw_gate2_shared2("sai6_root_clk", "sai6", base + 0x4380, 0, &share_count_sai6);
+	hws[IMX8MQ_CLK_SAI6_IPG] = imx_clk_hw_gate2_shared2("sai6_ipg_clk", "ipg_audio_root", base + 0x4380, 0, &share_count_sai6);
+	hws[IMX8MQ_CLK_SNVS_ROOT] = imx_clk_hw_gate4("snvs_root_clk", "ipg_root", base + 0x4470, 0);
+	hws[IMX8MQ_CLK_UART1_ROOT] = imx_clk_hw_gate4("uart1_root_clk", "uart1", base + 0x4490, 0);
+	hws[IMX8MQ_CLK_UART2_ROOT] = imx_clk_hw_gate4("uart2_root_clk", "uart2", base + 0x44a0, 0);
+	hws[IMX8MQ_CLK_UART3_ROOT] = imx_clk_hw_gate4("uart3_root_clk", "uart3", base + 0x44b0, 0);
+	hws[IMX8MQ_CLK_UART4_ROOT] = imx_clk_hw_gate4("uart4_root_clk", "uart4", base + 0x44c0, 0);
+	hws[IMX8MQ_CLK_USB1_CTRL_ROOT] = imx_clk_hw_gate4("usb1_ctrl_root_clk", "usb_bus", base + 0x44d0, 0);
+	hws[IMX8MQ_CLK_USB2_CTRL_ROOT] = imx_clk_hw_gate4("usb2_ctrl_root_clk", "usb_bus", base + 0x44e0, 0);
+	hws[IMX8MQ_CLK_USB1_PHY_ROOT] = imx_clk_hw_gate4("usb1_phy_root_clk", "usb_phy_ref", base + 0x44f0, 0);
+	hws[IMX8MQ_CLK_USB2_PHY_ROOT] = imx_clk_hw_gate4("usb2_phy_root_clk", "usb_phy_ref", base + 0x4500, 0);
+	hws[IMX8MQ_CLK_USDHC1_ROOT] = imx_clk_hw_gate4("usdhc1_root_clk", "usdhc1", base + 0x4510, 0);
+	hws[IMX8MQ_CLK_USDHC2_ROOT] = imx_clk_hw_gate4("usdhc2_root_clk", "usdhc2", base + 0x4520, 0);
+	hws[IMX8MQ_CLK_WDOG1_ROOT] = imx_clk_hw_gate4("wdog1_root_clk", "wdog", base + 0x4530, 0);
+	hws[IMX8MQ_CLK_WDOG2_ROOT] = imx_clk_hw_gate4("wdog2_root_clk", "wdog", base + 0x4540, 0);
+	hws[IMX8MQ_CLK_WDOG3_ROOT] = imx_clk_hw_gate4("wdog3_root_clk", "wdog", base + 0x4550, 0);
+	hws[IMX8MQ_CLK_VPU_G1_ROOT] = imx_clk_hw_gate2_flags("vpu_g1_root_clk", "vpu_g1", base + 0x4560, 0, CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
+	hws[IMX8MQ_CLK_GPU_ROOT] = imx_clk_hw_gate4("gpu_root_clk", "gpu_core_div", base + 0x4570, 0);
+	hws[IMX8MQ_CLK_VPU_G2_ROOT] = imx_clk_hw_gate2_flags("vpu_g2_root_clk", "vpu_g2", base + 0x45a0, 0, CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
+	hws[IMX8MQ_CLK_DISP_ROOT] = imx_clk_hw_gate2_shared2("disp_root_clk", "disp_dc8000", base + 0x45d0, 0, &share_count_dcss);
+	hws[IMX8MQ_CLK_DISP_AXI_ROOT]  = imx_clk_hw_gate2_shared2("disp_axi_root_clk", "disp_axi", base + 0x45d0, 0, &share_count_dcss);
+	hws[IMX8MQ_CLK_DISP_APB_ROOT]  = imx_clk_hw_gate2_shared2("disp_apb_root_clk", "disp_apb", base + 0x45d0, 0, &share_count_dcss);
+	hws[IMX8MQ_CLK_DISP_RTRM_ROOT] = imx_clk_hw_gate2_shared2("disp_rtrm_root_clk", "disp_rtrm", base + 0x45d0, 0, &share_count_dcss);
+	hws[IMX8MQ_CLK_TMU_ROOT] = imx_clk_hw_gate4("tmu_root_clk", "ipg_root", base + 0x4620, 0);
+	hws[IMX8MQ_CLK_VPU_DEC_ROOT] = imx_clk_hw_gate2_flags("vpu_dec_root_clk", "vpu_bus", base + 0x4630, 0, CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE);
+	hws[IMX8MQ_CLK_CSI1_ROOT] = imx_clk_hw_gate4("csi1_root_clk", "csi1_core", base + 0x4650, 0);
+	hws[IMX8MQ_CLK_CSI2_ROOT] = imx_clk_hw_gate4("csi2_root_clk", "csi2_core", base + 0x4660, 0);
+	hws[IMX8MQ_CLK_SDMA1_ROOT] = imx_clk_hw_gate4("sdma1_clk", "ipg_root", base + 0x43a0, 0);
+	hws[IMX8MQ_CLK_SDMA2_ROOT] = imx_clk_hw_gate4("sdma2_clk", "ipg_audio_root", base + 0x43b0, 0);
+
+	hws[IMX8MQ_GPT_3M_CLK] = imx_clk_hw_fixed_factor("gpt_3m", "osc_25m", 1, 8);
+	hws[IMX8MQ_CLK_DRAM_ALT_ROOT] = imx_clk_hw_fixed_factor("dram_alt_root", "dram_alt", 1, 4);
+
+	hws[IMX8MQ_CLK_ARM] = imx_clk_hw_cpu("arm", "arm_a53_div",
+					   hws[IMX8MQ_CLK_A53_DIV]->clk,
+					   hws[IMX8MQ_CLK_A53_SRC]->clk,
+					   hws[IMX8MQ_ARM_PLL_OUT]->clk,
+					   hws[IMX8MQ_SYS1_PLL_800M]->clk);
+
+	imx_check_clk_hws(hws, IMX8MQ_CLK_END);
+
+	err = of_clk_add_hw_provider(np, of_clk_hw_onecell_get, clk_hw_data);
 	if (err < 0) {
-		dev_err(dev, "failed to register clks for i.MX8MQ\n");
-		goto unregister_clks;
+		dev_err(dev, "failed to register hws for i.MX8MQ\n");
+		goto unregister_hws;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(uart_clk_ids); i++) {
+		int index = uart_clk_ids[i];
+
+		uart_hws[i] = &hws[index]->clk;
 	}
 
-	imx_register_uart_clocks(uart_clks);
+	imx_register_uart_clocks(uart_hws);
 
 	return 0;
 
-unregister_clks:
-	imx_unregister_clocks(clks, ARRAY_SIZE(clks));
+unregister_hws:
+	imx_unregister_hw_clocks(hws, IMX8MQ_CLK_END);
 
 	return err;
 }
@@ -609,6 +624,11 @@ static struct platform_driver imx8mq_clk_driver = {
 	.probe = imx8mq_clocks_probe,
 	.driver = {
 		.name = "imx8mq-ccm",
+		/*
+		 * Disable bind attributes: clocks are not removed and
+		 * reloading the driver will crash or break devices.
+		 */
+		.suppress_bind_attrs = true,
 		.of_match_table = of_match_ptr(imx8mq_clk_of_match),
 	},
 };
diff --git a/drivers/clk/imx/clk-imx8qxp-lpcg.c b/drivers/clk/imx/clk-imx8qxp-lpcg.c
index c0aff7ca6374..04c8ee35e14c 100644
--- a/drivers/clk/imx/clk-imx8qxp-lpcg.c
+++ b/drivers/clk/imx/clk-imx8qxp-lpcg.c
@@ -173,6 +173,17 @@ static int imx8qxp_lpcg_clk_probe(struct platform_device *pdev)
 	if (!ss_lpcg)
 		return -ENODEV;
 
+	/*
+	 * Please don't replace this with devm_platform_ioremap_resource.
+	 *
+	 * devm_platform_ioremap_resource calls devm_ioremap_resource which
+	 * differs from devm_ioremap by also calling devm_request_mem_region
+	 * and preventing other mappings in the same area.
+	 *
+	 * On imx8 the LPCG nodes map entire subsystems and overlap
+	 * peripherals, this means that using devm_platform_ioremap_resource
+	 * will cause many devices to fail to probe including serial ports.
+	 */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res)
 		return -EINVAL;
diff --git a/drivers/clk/imx/clk-pfdv2.c b/drivers/clk/imx/clk-pfdv2.c
index a03bbed662c6..de93ce73101b 100644
--- a/drivers/clk/imx/clk-pfdv2.c
+++ b/drivers/clk/imx/clk-pfdv2.c
@@ -166,7 +166,7 @@ static const struct clk_ops clk_pfdv2_ops = {
 	.is_enabled     = clk_pfdv2_is_enabled,
 };
 
-struct clk_hw *imx_clk_pfdv2(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_pfdv2(const char *name, const char *parent_name,
 			     void __iomem *reg, u8 idx)
 {
 	struct clk_init_data init;
diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c
index 3636c8035c7d..5b0519a81a7a 100644
--- a/drivers/clk/imx/clk-pll14xx.c
+++ b/drivers/clk/imx/clk-pll14xx.c
@@ -67,6 +67,13 @@ struct imx_pll14xx_clk imx_1443x_pll = {
 	.rate_count = ARRAY_SIZE(imx_pll1443x_tbl),
 };
 
+struct imx_pll14xx_clk imx_1443x_dram_pll = {
+	.type = PLL_1443X,
+	.rate_table = imx_pll1443x_tbl,
+	.rate_count = ARRAY_SIZE(imx_pll1443x_tbl),
+	.flags = CLK_GET_RATE_NOCACHE,
+};
+
 struct imx_pll14xx_clk imx_1416x_pll = {
 	.type = PLL_1416X,
 	.rate_table = imx_pll1416x_tbl,
@@ -369,13 +376,14 @@ static const struct clk_ops clk_pll1443x_ops = {
 	.set_rate	= clk_pll1443x_set_rate,
 };
 
-struct clk *imx_clk_pll14xx(const char *name, const char *parent_name,
-			    void __iomem *base,
-			    const struct imx_pll14xx_clk *pll_clk)
+struct clk_hw *imx_clk_hw_pll14xx(const char *name, const char *parent_name,
+				  void __iomem *base,
+				  const struct imx_pll14xx_clk *pll_clk)
 {
 	struct clk_pll14xx *pll;
-	struct clk *clk;
+	struct clk_hw *hw;
 	struct clk_init_data init;
+	int ret;
 	u32 val;
 
 	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
@@ -412,12 +420,15 @@ struct clk *imx_clk_pll14xx(const char *name, const char *parent_name,
 	val &= ~BYPASS_MASK;
 	writel_relaxed(val, pll->base + GNRL_CTL);
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk)) {
-		pr_err("%s: failed to register pll %s %lu\n",
-			__func__, name, PTR_ERR(clk));
+	hw = &pll->hw;
+
+	ret = clk_hw_register(NULL, hw);
+	if (ret) {
+		pr_err("%s: failed to register pll %s %d\n",
+			__func__, name, ret);
 		kfree(pll);
+		return ERR_PTR(ret);
 	}
 
-	return clk;
+	return hw;
 }
diff --git a/drivers/clk/imx/clk-pllv1.c b/drivers/clk/imx/clk-pllv1.c
index 4ba9973d4c18..de4f8a41a7d0 100644
--- a/drivers/clk/imx/clk-pllv1.c
+++ b/drivers/clk/imx/clk-pllv1.c
@@ -111,12 +111,13 @@ static const struct clk_ops clk_pllv1_ops = {
 	.recalc_rate = clk_pllv1_recalc_rate,
 };
 
-struct clk *imx_clk_pllv1(enum imx_pllv1_type type, const char *name,
+struct clk_hw *imx_clk_hw_pllv1(enum imx_pllv1_type type, const char *name,
 		const char *parent, void __iomem *base)
 {
 	struct clk_pllv1 *pll;
-	struct clk *clk;
+	struct clk_hw *hw;
 	struct clk_init_data init;
+	int ret;
 
 	pll = kmalloc(sizeof(*pll), GFP_KERNEL);
 	if (!pll)
@@ -132,10 +133,13 @@ struct clk *imx_clk_pllv1(enum imx_pllv1_type type, const char *name,
 	init.num_parents = 1;
 
 	pll->hw.init = &init;
+	hw = &pll->hw;
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk))
+	ret = clk_hw_register(NULL, hw);
+	if (ret) {
 		kfree(pll);
+		return ERR_PTR(ret);
+	}
 
-	return clk;
+	return hw;
 }
diff --git a/drivers/clk/imx/clk-pllv2.c b/drivers/clk/imx/clk-pllv2.c
index eeba3cb14e2d..ff17f0664faa 100644
--- a/drivers/clk/imx/clk-pllv2.c
+++ b/drivers/clk/imx/clk-pllv2.c
@@ -239,12 +239,13 @@ static const struct clk_ops clk_pllv2_ops = {
 	.set_rate = clk_pllv2_set_rate,
 };
 
-struct clk *imx_clk_pllv2(const char *name, const char *parent,
+struct clk_hw *imx_clk_hw_pllv2(const char *name, const char *parent,
 		void __iomem *base)
 {
 	struct clk_pllv2 *pll;
-	struct clk *clk;
+	struct clk_hw *hw;
 	struct clk_init_data init;
+	int ret;
 
 	pll = kzalloc(sizeof(*pll), GFP_KERNEL);
 	if (!pll)
@@ -259,10 +260,13 @@ struct clk *imx_clk_pllv2(const char *name, const char *parent,
 	init.num_parents = 1;
 
 	pll->hw.init = &init;
+	hw = &pll->hw;
 
-	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk))
+	ret = clk_hw_register(NULL, hw);
+	if (ret) {
 		kfree(pll);
+		return ERR_PTR(ret);
+	}
 
-	return clk;
+	return hw;
 }
diff --git a/drivers/clk/imx/clk-pllv4.c b/drivers/clk/imx/clk-pllv4.c
index 8155b12cf0e1..f51a800c268c 100644
--- a/drivers/clk/imx/clk-pllv4.c
+++ b/drivers/clk/imx/clk-pllv4.c
@@ -206,7 +206,7 @@ static const struct clk_ops clk_pllv4_ops = {
 	.is_enabled	= clk_pllv4_is_enabled,
 };
 
-struct clk_hw *imx_clk_pllv4(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_pllv4(const char *name, const char *parent_name,
 			  void __iomem *base)
 {
 	struct clk_pllv4 *pll;
diff --git a/drivers/clk/imx/clk-sccg-pll.c b/drivers/clk/imx/clk-sscg-pll.c
index 5d65f65c512e..acd1b9002be6 100644
--- a/drivers/clk/imx/clk-sccg-pll.c
+++ b/drivers/clk/imx/clk-sscg-pll.c
@@ -67,7 +67,7 @@
 
 #define PLL_SCCG_LOCK_TIMEOUT		70
 
-struct clk_sccg_pll_setup {
+struct clk_sscg_pll_setup {
 	int divr1, divf1;
 	int divr2, divf2;
 	int divq;
@@ -83,22 +83,22 @@ struct clk_sccg_pll_setup {
 	int fout_error;
 };
 
-struct clk_sccg_pll {
+struct clk_sscg_pll {
 	struct clk_hw	hw;
 	const struct clk_ops  ops;
 
 	void __iomem *base;
 
-	struct clk_sccg_pll_setup setup;
+	struct clk_sscg_pll_setup setup;
 
 	u8 parent;
 	u8 bypass1;
 	u8 bypass2;
 };
 
-#define to_clk_sccg_pll(_hw) container_of(_hw, struct clk_sccg_pll, hw)
+#define to_clk_sscg_pll(_hw) container_of(_hw, struct clk_sscg_pll, hw)
 
-static int clk_sccg_pll_wait_lock(struct clk_sccg_pll *pll)
+static int clk_sscg_pll_wait_lock(struct clk_sscg_pll *pll)
 {
 	u32 val;
 
@@ -112,15 +112,15 @@ static int clk_sccg_pll_wait_lock(struct clk_sccg_pll *pll)
 	return 0;
 }
 
-static int clk_sccg_pll2_check_match(struct clk_sccg_pll_setup *setup,
-					struct clk_sccg_pll_setup *temp_setup)
+static int clk_sscg_pll2_check_match(struct clk_sscg_pll_setup *setup,
+					struct clk_sscg_pll_setup *temp_setup)
 {
 	int new_diff = temp_setup->fout - temp_setup->fout_request;
 	int diff = temp_setup->fout_error;
 
 	if (abs(diff) > abs(new_diff)) {
 		temp_setup->fout_error = new_diff;
-		memcpy(setup, temp_setup, sizeof(struct clk_sccg_pll_setup));
+		memcpy(setup, temp_setup, sizeof(struct clk_sscg_pll_setup));
 
 		if (temp_setup->fout_request == temp_setup->fout)
 			return 0;
@@ -128,8 +128,8 @@ static int clk_sccg_pll2_check_match(struct clk_sccg_pll_setup *setup,
 	return -1;
 }
 
-static int clk_sccg_divq_lookup(struct clk_sccg_pll_setup *setup,
-				struct clk_sccg_pll_setup *temp_setup)
+static int clk_sscg_divq_lookup(struct clk_sscg_pll_setup *setup,
+				struct clk_sscg_pll_setup *temp_setup)
 {
 	int ret = -EINVAL;
 
@@ -144,7 +144,7 @@ static int clk_sccg_divq_lookup(struct clk_sccg_pll_setup *setup,
 			temp_setup->fout = temp_setup->vco2;
 			do_div(temp_setup->fout, 2 * (temp_setup->divq + 1));
 
-			ret = clk_sccg_pll2_check_match(setup, temp_setup);
+			ret = clk_sscg_pll2_check_match(setup, temp_setup);
 			if (!ret) {
 				temp_setup->bypass = PLL_BYPASS1;
 				return ret;
@@ -155,14 +155,14 @@ static int clk_sccg_divq_lookup(struct clk_sccg_pll_setup *setup,
 	return ret;
 }
 
-static int clk_sccg_divf2_lookup(struct clk_sccg_pll_setup *setup,
-					struct clk_sccg_pll_setup *temp_setup)
+static int clk_sscg_divf2_lookup(struct clk_sscg_pll_setup *setup,
+					struct clk_sscg_pll_setup *temp_setup)
 {
 	int ret = -EINVAL;
 
 	for (temp_setup->divf2 = 0; temp_setup->divf2 <= PLL_DIVF2_MAX;
 	     temp_setup->divf2++) {
-		ret = clk_sccg_divq_lookup(setup, temp_setup);
+		ret = clk_sscg_divq_lookup(setup, temp_setup);
 		if (!ret)
 			return ret;
 	}
@@ -170,8 +170,8 @@ static int clk_sccg_divf2_lookup(struct clk_sccg_pll_setup *setup,
 	return ret;
 }
 
-static int clk_sccg_divr2_lookup(struct clk_sccg_pll_setup *setup,
-				struct clk_sccg_pll_setup *temp_setup)
+static int clk_sscg_divr2_lookup(struct clk_sscg_pll_setup *setup,
+				struct clk_sscg_pll_setup *temp_setup)
 {
 	int ret = -EINVAL;
 
@@ -181,7 +181,7 @@ static int clk_sccg_divr2_lookup(struct clk_sccg_pll_setup *setup,
 		do_div(temp_setup->ref_div2, temp_setup->divr2 + 1);
 		if (temp_setup->ref_div2 >= PLL_STAGE2_REF_MIN_FREQ &&
 		    temp_setup->ref_div2 <= PLL_STAGE2_REF_MAX_FREQ) {
-			ret = clk_sccg_divf2_lookup(setup, temp_setup);
+			ret = clk_sscg_divf2_lookup(setup, temp_setup);
 			if (!ret)
 				return ret;
 		}
@@ -190,8 +190,8 @@ static int clk_sccg_divr2_lookup(struct clk_sccg_pll_setup *setup,
 	return ret;
 }
 
-static int clk_sccg_pll2_find_setup(struct clk_sccg_pll_setup *setup,
-					struct clk_sccg_pll_setup *temp_setup,
+static int clk_sscg_pll2_find_setup(struct clk_sscg_pll_setup *setup,
+					struct clk_sscg_pll_setup *temp_setup,
 					uint64_t ref)
 {
 
@@ -202,12 +202,12 @@ static int clk_sccg_pll2_find_setup(struct clk_sccg_pll_setup *setup,
 
 	temp_setup->vco1 = ref;
 
-	ret = clk_sccg_divr2_lookup(setup, temp_setup);
+	ret = clk_sscg_divr2_lookup(setup, temp_setup);
 	return ret;
 }
 
-static int clk_sccg_divf1_lookup(struct clk_sccg_pll_setup *setup,
-				struct clk_sccg_pll_setup *temp_setup)
+static int clk_sscg_divf1_lookup(struct clk_sscg_pll_setup *setup,
+				struct clk_sscg_pll_setup *temp_setup)
 {
 	int ret = -EINVAL;
 
@@ -219,7 +219,7 @@ static int clk_sccg_divf1_lookup(struct clk_sccg_pll_setup *setup,
 		vco1 *= 2;
 		vco1 *= temp_setup->divf1 + 1;
 
-		ret = clk_sccg_pll2_find_setup(setup, temp_setup, vco1);
+		ret = clk_sscg_pll2_find_setup(setup, temp_setup, vco1);
 		if (!ret) {
 			temp_setup->bypass = PLL_BYPASS_NONE;
 			return ret;
@@ -229,8 +229,8 @@ static int clk_sccg_divf1_lookup(struct clk_sccg_pll_setup *setup,
 	return ret;
 }
 
-static int clk_sccg_divr1_lookup(struct clk_sccg_pll_setup *setup,
-				struct clk_sccg_pll_setup *temp_setup)
+static int clk_sscg_divr1_lookup(struct clk_sscg_pll_setup *setup,
+				struct clk_sscg_pll_setup *temp_setup)
 {
 	int ret = -EINVAL;
 
@@ -240,7 +240,7 @@ static int clk_sccg_divr1_lookup(struct clk_sccg_pll_setup *setup,
 		do_div(temp_setup->ref_div1, temp_setup->divr1 + 1);
 		if (temp_setup->ref_div1 >= PLL_STAGE1_REF_MIN_FREQ &&
 		    temp_setup->ref_div1 <= PLL_STAGE1_REF_MAX_FREQ) {
-			ret = clk_sccg_divf1_lookup(setup, temp_setup);
+			ret = clk_sscg_divf1_lookup(setup, temp_setup);
 			if (!ret)
 				return ret;
 		}
@@ -249,8 +249,8 @@ static int clk_sccg_divr1_lookup(struct clk_sccg_pll_setup *setup,
 	return ret;
 }
 
-static int clk_sccg_pll1_find_setup(struct clk_sccg_pll_setup *setup,
-					struct clk_sccg_pll_setup *temp_setup,
+static int clk_sscg_pll1_find_setup(struct clk_sscg_pll_setup *setup,
+					struct clk_sscg_pll_setup *temp_setup,
 					uint64_t ref)
 {
 
@@ -261,20 +261,20 @@ static int clk_sccg_pll1_find_setup(struct clk_sccg_pll_setup *setup,
 
 	temp_setup->ref = ref;
 
-	ret = clk_sccg_divr1_lookup(setup, temp_setup);
+	ret = clk_sscg_divr1_lookup(setup, temp_setup);
 
 	return ret;
 }
 
-static int clk_sccg_pll_find_setup(struct clk_sccg_pll_setup *setup,
+static int clk_sscg_pll_find_setup(struct clk_sscg_pll_setup *setup,
 					uint64_t prate,
 					uint64_t rate, int try_bypass)
 {
-	struct clk_sccg_pll_setup temp_setup;
+	struct clk_sscg_pll_setup temp_setup;
 	int ret = -EINVAL;
 
-	memset(&temp_setup, 0, sizeof(struct clk_sccg_pll_setup));
-	memset(setup, 0, sizeof(struct clk_sccg_pll_setup));
+	memset(&temp_setup, 0, sizeof(struct clk_sscg_pll_setup));
+	memset(setup, 0, sizeof(struct clk_sscg_pll_setup));
 
 	temp_setup.fout_error = PLL_OUT_MAX_FREQ;
 	temp_setup.fout_request = rate;
@@ -290,11 +290,11 @@ static int clk_sccg_pll_find_setup(struct clk_sccg_pll_setup *setup,
 		break;
 
 	case PLL_BYPASS1:
-		ret = clk_sccg_pll2_find_setup(setup, &temp_setup, prate);
+		ret = clk_sscg_pll2_find_setup(setup, &temp_setup, prate);
 		break;
 
 	case PLL_BYPASS_NONE:
-		ret = clk_sccg_pll1_find_setup(setup, &temp_setup, prate);
+		ret = clk_sscg_pll1_find_setup(setup, &temp_setup, prate);
 		break;
 	}
 
@@ -302,30 +302,30 @@ static int clk_sccg_pll_find_setup(struct clk_sccg_pll_setup *setup,
 }
 
 
-static int clk_sccg_pll_is_prepared(struct clk_hw *hw)
+static int clk_sscg_pll_is_prepared(struct clk_hw *hw)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
 
 	u32 val = readl_relaxed(pll->base + PLL_CFG0);
 
 	return (val & PLL_PD_MASK) ? 0 : 1;
 }
 
-static int clk_sccg_pll_prepare(struct clk_hw *hw)
+static int clk_sscg_pll_prepare(struct clk_hw *hw)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
 	u32 val;
 
 	val = readl_relaxed(pll->base + PLL_CFG0);
 	val &= ~PLL_PD_MASK;
 	writel_relaxed(val, pll->base + PLL_CFG0);
 
-	return clk_sccg_pll_wait_lock(pll);
+	return clk_sscg_pll_wait_lock(pll);
 }
 
-static void clk_sccg_pll_unprepare(struct clk_hw *hw)
+static void clk_sscg_pll_unprepare(struct clk_hw *hw)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
 	u32 val;
 
 	val = readl_relaxed(pll->base + PLL_CFG0);
@@ -333,10 +333,10 @@ static void clk_sccg_pll_unprepare(struct clk_hw *hw)
 	writel_relaxed(val, pll->base + PLL_CFG0);
 }
 
-static unsigned long clk_sccg_pll_recalc_rate(struct clk_hw *hw,
+static unsigned long clk_sscg_pll_recalc_rate(struct clk_hw *hw,
 					 unsigned long parent_rate)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
 	u32 val, divr1, divf1, divr2, divf2, divq;
 	u64 temp64;
 
@@ -364,11 +364,11 @@ static unsigned long clk_sccg_pll_recalc_rate(struct clk_hw *hw,
 	return temp64;
 }
 
-static int clk_sccg_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+static int clk_sscg_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 			    unsigned long parent_rate)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
-	struct clk_sccg_pll_setup *setup = &pll->setup;
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
+	struct clk_sscg_pll_setup *setup = &pll->setup;
 	u32 val;
 
 	/* set bypass here too since the parent might be the same */
@@ -387,12 +387,12 @@ static int clk_sccg_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	val |= FIELD_PREP(PLL_DIVQ_MASK, setup->divq);
 	writel_relaxed(val, pll->base + PLL_CFG2);
 
-	return clk_sccg_pll_wait_lock(pll);
+	return clk_sscg_pll_wait_lock(pll);
 }
 
-static u8 clk_sccg_pll_get_parent(struct clk_hw *hw)
+static u8 clk_sscg_pll_get_parent(struct clk_hw *hw)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
 	u32 val;
 	u8 ret = pll->parent;
 
@@ -404,9 +404,9 @@ static u8 clk_sccg_pll_get_parent(struct clk_hw *hw)
 	return ret;
 }
 
-static int clk_sccg_pll_set_parent(struct clk_hw *hw, u8 index)
+static int clk_sscg_pll_set_parent(struct clk_hw *hw, u8 index)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
 	u32 val;
 
 	val = readl(pll->base + PLL_CFG0);
@@ -414,18 +414,18 @@ static int clk_sccg_pll_set_parent(struct clk_hw *hw, u8 index)
 	val |= FIELD_PREP(SSCG_PLL_BYPASS_MASK, pll->setup.bypass);
 	writel(val, pll->base + PLL_CFG0);
 
-	return clk_sccg_pll_wait_lock(pll);
+	return clk_sscg_pll_wait_lock(pll);
 }
 
-static int __clk_sccg_pll_determine_rate(struct clk_hw *hw,
+static int __clk_sscg_pll_determine_rate(struct clk_hw *hw,
 					struct clk_rate_request *req,
 					uint64_t min,
 					uint64_t max,
 					uint64_t rate,
 					int bypass)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
-	struct clk_sccg_pll_setup *setup = &pll->setup;
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
+	struct clk_sscg_pll_setup *setup = &pll->setup;
 	struct clk_hw *parent_hw = NULL;
 	int bypass_parent_index;
 	int ret = -EINVAL;
@@ -448,7 +448,7 @@ static int __clk_sccg_pll_determine_rate(struct clk_hw *hw,
 	parent_hw = clk_hw_get_parent_by_index(hw, bypass_parent_index);
 	ret = __clk_determine_rate(parent_hw, req);
 	if (!ret) {
-		ret = clk_sccg_pll_find_setup(setup, req->rate,
+		ret = clk_sscg_pll_find_setup(setup, req->rate,
 						rate, bypass);
 	}
 
@@ -459,11 +459,11 @@ static int __clk_sccg_pll_determine_rate(struct clk_hw *hw,
 	return ret;
 }
 
-static int clk_sccg_pll_determine_rate(struct clk_hw *hw,
+static int clk_sscg_pll_determine_rate(struct clk_hw *hw,
 				       struct clk_rate_request *req)
 {
-	struct clk_sccg_pll *pll = to_clk_sccg_pll(hw);
-	struct clk_sccg_pll_setup *setup = &pll->setup;
+	struct clk_sscg_pll *pll = to_clk_sscg_pll(hw);
+	struct clk_sscg_pll_setup *setup = &pll->setup;
 	uint64_t rate = req->rate;
 	uint64_t min = req->min_rate;
 	uint64_t max = req->max_rate;
@@ -472,18 +472,18 @@ static int clk_sccg_pll_determine_rate(struct clk_hw *hw,
 	if (rate < PLL_OUT_MIN_FREQ || rate > PLL_OUT_MAX_FREQ)
 		return ret;
 
-	ret = __clk_sccg_pll_determine_rate(hw, req, req->rate, req->rate,
+	ret = __clk_sscg_pll_determine_rate(hw, req, req->rate, req->rate,
 						rate, PLL_BYPASS2);
 	if (!ret)
 		return ret;
 
-	ret = __clk_sccg_pll_determine_rate(hw, req, PLL_STAGE1_REF_MIN_FREQ,
+	ret = __clk_sscg_pll_determine_rate(hw, req, PLL_STAGE1_REF_MIN_FREQ,
 						PLL_STAGE1_REF_MAX_FREQ, rate,
 						PLL_BYPASS1);
 	if (!ret)
 		return ret;
 
-	ret = __clk_sccg_pll_determine_rate(hw, req, PLL_REF_MIN_FREQ,
+	ret = __clk_sscg_pll_determine_rate(hw, req, PLL_REF_MIN_FREQ,
 						PLL_REF_MAX_FREQ, rate,
 						PLL_BYPASS_NONE);
 	if (!ret)
@@ -495,25 +495,25 @@ static int clk_sccg_pll_determine_rate(struct clk_hw *hw,
 	return ret;
 }
 
-static const struct clk_ops clk_sccg_pll_ops = {
-	.prepare	= clk_sccg_pll_prepare,
-	.unprepare	= clk_sccg_pll_unprepare,
-	.is_prepared	= clk_sccg_pll_is_prepared,
-	.recalc_rate	= clk_sccg_pll_recalc_rate,
-	.set_rate	= clk_sccg_pll_set_rate,
-	.set_parent	= clk_sccg_pll_set_parent,
-	.get_parent	= clk_sccg_pll_get_parent,
-	.determine_rate	= clk_sccg_pll_determine_rate,
+static const struct clk_ops clk_sscg_pll_ops = {
+	.prepare	= clk_sscg_pll_prepare,
+	.unprepare	= clk_sscg_pll_unprepare,
+	.is_prepared	= clk_sscg_pll_is_prepared,
+	.recalc_rate	= clk_sscg_pll_recalc_rate,
+	.set_rate	= clk_sscg_pll_set_rate,
+	.set_parent	= clk_sscg_pll_set_parent,
+	.get_parent	= clk_sscg_pll_get_parent,
+	.determine_rate	= clk_sscg_pll_determine_rate,
 };
 
-struct clk *imx_clk_sccg_pll(const char *name,
+struct clk_hw *imx_clk_hw_sscg_pll(const char *name,
 				const char * const *parent_names,
 				u8 num_parents,
 				u8 parent, u8 bypass1, u8 bypass2,
 				void __iomem *base,
 				unsigned long flags)
 {
-	struct clk_sccg_pll *pll;
+	struct clk_sscg_pll *pll;
 	struct clk_init_data init;
 	struct clk_hw *hw;
 	int ret;
@@ -528,7 +528,7 @@ struct clk *imx_clk_sccg_pll(const char *name,
 
 	pll->base = base;
 	init.name = name;
-	init.ops = &clk_sccg_pll_ops;
+	init.ops = &clk_sscg_pll_ops;
 
 	init.flags = flags;
 	init.parent_names = parent_names;
@@ -545,5 +545,5 @@ struct clk *imx_clk_sccg_pll(const char *name,
 		return ERR_PTR(ret);
 	}
 
-	return hw->clk;
+	return hw;
 }
diff --git a/drivers/clk/imx/clk.c b/drivers/clk/imx/clk.c
index cfc05e43c343..87ab8db3d282 100644
--- a/drivers/clk/imx/clk.c
+++ b/drivers/clk/imx/clk.c
@@ -22,6 +22,14 @@ void imx_unregister_clocks(struct clk *clks[], unsigned int count)
 		clk_unregister(clks[i]);
 }
 
+void imx_unregister_hw_clocks(struct clk_hw *hws[], unsigned int count)
+{
+	unsigned int i;
+
+	for (i = 0; i < count; i++)
+		clk_hw_unregister(hws[i]);
+}
+
 void __init imx_mmdc_mask_handshake(void __iomem *ccm_base,
 				    unsigned int chn)
 {
@@ -94,8 +102,8 @@ struct clk_hw * __init imx_obtain_fixed_clock_hw(
 	return __clk_get_hw(clk);
 }
 
-struct clk_hw * __init imx_obtain_fixed_clk_hw(struct device_node *np,
-					       const char *name)
+struct clk_hw * imx_obtain_fixed_clk_hw(struct device_node *np,
+					const char *name)
 {
 	struct clk *clk;
 
diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h
index bc5bb6ac8636..b05213b91dcf 100644
--- a/drivers/clk/imx/clk.h
+++ b/drivers/clk/imx/clk.h
@@ -12,6 +12,7 @@ void imx_check_clk_hws(struct clk_hw *clks[], unsigned int count);
 void imx_register_uart_clocks(struct clk ** const clks[]);
 void imx_mmdc_mask_handshake(void __iomem *ccm_base, unsigned int chn);
 void imx_unregister_clocks(struct clk *clks[], unsigned int count);
+void imx_unregister_hw_clocks(struct clk_hw *hws[], unsigned int count);
 
 extern void imx_cscmr1_fixup(u32 *val);
 
@@ -24,7 +25,7 @@ enum imx_pllv1_type {
 	IMX_PLLV1_IMX35,
 };
 
-enum imx_sccg_pll_type {
+enum imx_sscg_pll_type {
 	SCCG_PLL1,
 	SCCG_PLL2,
 };
@@ -52,64 +53,98 @@ struct imx_pll14xx_clk {
 
 extern struct imx_pll14xx_clk imx_1416x_pll;
 extern struct imx_pll14xx_clk imx_1443x_pll;
+extern struct imx_pll14xx_clk imx_1443x_dram_pll;
 
 #define imx_clk_cpu(name, parent_name, div, mux, pll, step) \
-	imx_clk_hw_cpu(name, parent_name, div, mux, pll, step)->clk
+	to_clk(imx_clk_hw_cpu(name, parent_name, div, mux, pll, step))
 
 #define clk_register_gate2(dev, name, parent_name, flags, reg, bit_idx, \
 				cgr_val, clk_gate_flags, lock, share_count) \
-	clk_hw_register_gate2(dev, name, parent_name, flags, reg, bit_idx, \
-				cgr_val, clk_gate_flags, lock, share_count)->clk
+	to_clk(clk_hw_register_gate2(dev, name, parent_name, flags, reg, bit_idx, \
+				cgr_val, clk_gate_flags, lock, share_count))
 
 #define imx_clk_pllv3(type, name, parent_name, base, div_mask) \
-	imx_clk_hw_pllv3(type, name, parent_name, base, div_mask)->clk
+	to_clk(imx_clk_hw_pllv3(type, name, parent_name, base, div_mask))
 
 #define imx_clk_pfd(name, parent_name, reg, idx) \
-	imx_clk_hw_pfd(name, parent_name, reg, idx)->clk
+	to_clk(imx_clk_hw_pfd(name, parent_name, reg, idx))
 
 #define imx_clk_gate_exclusive(name, parent, reg, shift, exclusive_mask) \
-	imx_clk_hw_gate_exclusive(name, parent, reg, shift, exclusive_mask)->clk
+	to_clk(imx_clk_hw_gate_exclusive(name, parent, reg, shift, exclusive_mask))
+
+#define imx_clk_fixed(name, rate) \
+	to_clk(imx_clk_hw_fixed(name, rate))
 
 #define imx_clk_fixed_factor(name, parent, mult, div) \
-	imx_clk_hw_fixed_factor(name, parent, mult, div)->clk
+	to_clk(imx_clk_hw_fixed_factor(name, parent, mult, div))
+
+#define imx_clk_divider(name, parent, reg, shift, width) \
+	to_clk(imx_clk_hw_divider(name, parent, reg, shift, width))
 
 #define imx_clk_divider2(name, parent, reg, shift, width) \
-	imx_clk_hw_divider2(name, parent, reg, shift, width)->clk
+	to_clk(imx_clk_hw_divider2(name, parent, reg, shift, width))
+
+#define imx_clk_divider_flags(name, parent, reg, shift, width, flags) \
+	to_clk(imx_clk_hw_divider_flags(name, parent, reg, shift, width, flags))
+
+#define imx_clk_gate(name, parent, reg, shift) \
+	to_clk(imx_clk_hw_gate(name, parent, reg, shift))
 
 #define imx_clk_gate_dis(name, parent, reg, shift) \
-	imx_clk_hw_gate_dis(name, parent, reg, shift)->clk
+	to_clk(imx_clk_hw_gate_dis(name, parent, reg, shift))
 
 #define imx_clk_gate2(name, parent, reg, shift) \
-	imx_clk_hw_gate2(name, parent, reg, shift)->clk
+	to_clk(imx_clk_hw_gate2(name, parent, reg, shift))
 
 #define imx_clk_gate2_flags(name, parent, reg, shift, flags) \
-	imx_clk_hw_gate2_flags(name, parent, reg, shift, flags)->clk
+	to_clk(imx_clk_hw_gate2_flags(name, parent, reg, shift, flags))
 
 #define imx_clk_gate2_shared2(name, parent, reg, shift, share_count) \
-	imx_clk_hw_gate2_shared2(name, parent, reg, shift, share_count)->clk
+	to_clk(imx_clk_hw_gate2_shared2(name, parent, reg, shift, share_count))
 
 #define imx_clk_gate3(name, parent, reg, shift) \
-	imx_clk_hw_gate3(name, parent, reg, shift)->clk
+	to_clk(imx_clk_hw_gate3(name, parent, reg, shift))
 
 #define imx_clk_gate4(name, parent, reg, shift) \
-	imx_clk_hw_gate4(name, parent, reg, shift)->clk
+	to_clk(imx_clk_hw_gate4(name, parent, reg, shift))
 
 #define imx_clk_mux(name, reg, shift, width, parents, num_parents) \
-	imx_clk_hw_mux(name, reg, shift, width, parents, num_parents)->clk
+	to_clk(imx_clk_hw_mux(name, reg, shift, width, parents, num_parents))
+
+#define imx_clk_pllv1(type, name, parent, base) \
+	to_clk(imx_clk_hw_pllv1(type, name, parent, base))
+
+#define imx_clk_pllv2(name, parent, base) \
+	to_clk(imx_clk_hw_pllv2(name, parent, base))
+
+#define imx_clk_frac_pll(name, parent_name, base) \
+	to_clk(imx_clk_hw_frac_pll(name, parent_name, base))
+
+#define imx_clk_sscg_pll(name, parent_names, num_parents, parent,\
+				bypass1, bypass2, base, flags) \
+	to_clk(imx_clk_hw_sscg_pll(name, parent_names, num_parents, parent,\
+				bypass1, bypass2, base, flags))
 
 struct clk *imx_clk_pll14xx(const char *name, const char *parent_name,
 		 void __iomem *base, const struct imx_pll14xx_clk *pll_clk);
 
-struct clk *imx_clk_pllv1(enum imx_pllv1_type type, const char *name,
+#define imx_clk_pll14xx(name, parent_name, base, pll_clk) \
+	to_clk(imx_clk_hw_pll14xx(name, parent_name, base, pll_clk))
+
+struct clk_hw *imx_clk_hw_pll14xx(const char *name, const char *parent_name,
+				  void __iomem *base,
+				  const struct imx_pll14xx_clk *pll_clk);
+
+struct clk_hw *imx_clk_hw_pllv1(enum imx_pllv1_type type, const char *name,
 		const char *parent, void __iomem *base);
 
-struct clk *imx_clk_pllv2(const char *name, const char *parent,
+struct clk_hw *imx_clk_hw_pllv2(const char *name, const char *parent,
 		void __iomem *base);
 
-struct clk *imx_clk_frac_pll(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_frac_pll(const char *name, const char *parent_name,
 			     void __iomem *base);
 
-struct clk *imx_clk_sccg_pll(const char *name,
+struct clk_hw *imx_clk_hw_sscg_pll(const char *name,
 				const char * const *parent_names,
 				u8 num_parents,
 				u8 parent, u8 bypass1, u8 bypass2,
@@ -149,7 +184,7 @@ struct clk_hw *imx_clk_hw_pllv3(enum imx_pllv3_type type, const char *name,
 		.kdiv	=	(_k),			\
 	}
 
-struct clk_hw *imx_clk_pllv4(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_pllv4(const char *name, const char *parent_name,
 			     void __iomem *base);
 
 struct clk_hw *clk_hw_register_gate2(struct device *dev, const char *name,
@@ -173,7 +208,7 @@ struct clk_hw *imx_clk_hw_gate_exclusive(const char *name, const char *parent,
 struct clk_hw *imx_clk_hw_pfd(const char *name, const char *parent_name,
 		void __iomem *reg, u8 idx);
 
-struct clk_hw *imx_clk_pfdv2(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_pfdv2(const char *name, const char *parent_name,
 			     void __iomem *reg, u8 idx);
 
 struct clk_hw *imx_clk_hw_busy_divider(const char *name, const char *parent_name,
@@ -184,7 +219,7 @@ struct clk_hw *imx_clk_hw_busy_mux(const char *name, void __iomem *reg, u8 shift
 			     u8 width, void __iomem *busy_reg, u8 busy_shift,
 			     const char * const *parent_names, int num_parents);
 
-struct clk_hw *imx7ulp_clk_composite(const char *name,
+struct clk_hw *imx7ulp_clk_hw_composite(const char *name,
 				     const char * const *parent_names,
 				     int num_parents, bool mux_present,
 				     bool rate_present, bool gate_present,
@@ -198,9 +233,11 @@ struct clk_hw *imx_clk_hw_fixup_mux(const char *name, void __iomem *reg,
 			      u8 shift, u8 width, const char * const *parents,
 			      int num_parents, void (*fixup)(u32 *val));
 
-static inline struct clk *imx_clk_fixed(const char *name, int rate)
+static inline struct clk *to_clk(struct clk_hw *hw)
 {
-	return clk_register_fixed_rate(NULL, name, NULL, 0, rate);
+	if (IS_ERR_OR_NULL(hw))
+		return ERR_CAST(hw);
+	return hw->clk;
 }
 
 static inline struct clk_hw *imx_clk_hw_fixed(const char *name, int rate)
@@ -224,13 +261,6 @@ static inline struct clk_hw *imx_clk_hw_fixed_factor(const char *name,
 			CLK_SET_RATE_PARENT, mult, div);
 }
 
-static inline struct clk *imx_clk_divider(const char *name, const char *parent,
-		void __iomem *reg, u8 shift, u8 width)
-{
-	return clk_register_divider(NULL, name, parent, CLK_SET_RATE_PARENT,
-			reg, shift, width, 0, &imx_ccm_lock);
-}
-
 static inline struct clk_hw *imx_clk_hw_divider(const char *name,
 						const char *parent,
 						void __iomem *reg, u8 shift,
@@ -240,14 +270,6 @@ static inline struct clk_hw *imx_clk_hw_divider(const char *name,
 				       reg, shift, width, 0, &imx_ccm_lock);
 }
 
-static inline struct clk *imx_clk_divider_flags(const char *name,
-		const char *parent, void __iomem *reg, u8 shift, u8 width,
-		unsigned long flags)
-{
-	return clk_register_divider(NULL, name, parent, flags,
-			reg, shift, width, 0, &imx_ccm_lock);
-}
-
 static inline struct clk_hw *imx_clk_hw_divider_flags(const char *name,
 						   const char *parent,
 						   void __iomem *reg, u8 shift,
@@ -274,13 +296,6 @@ static inline struct clk *imx_clk_divider2_flags(const char *name,
 			reg, shift, width, 0, &imx_ccm_lock);
 }
 
-static inline struct clk *imx_clk_gate(const char *name, const char *parent,
-		void __iomem *reg, u8 shift)
-{
-	return clk_register_gate(NULL, name, parent, CLK_SET_RATE_PARENT, reg,
-			shift, 0, &imx_ccm_lock);
-}
-
 static inline struct clk_hw *imx_clk_hw_gate_flags(const char *name, const char *parent,
 		void __iomem *reg, u8 shift, unsigned long flags)
 {
@@ -355,15 +370,18 @@ static inline struct clk_hw *imx_clk_hw_gate3(const char *name, const char *pare
 			reg, shift, 0, &imx_ccm_lock);
 }
 
-static inline struct clk *imx_clk_gate3_flags(const char *name,
+static inline struct clk_hw *imx_clk_hw_gate3_flags(const char *name,
 		const char *parent, void __iomem *reg, u8 shift,
 		unsigned long flags)
 {
-	return clk_register_gate(NULL, name, parent,
+	return clk_hw_register_gate(NULL, name, parent,
 			flags | CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
 			reg, shift, 0, &imx_ccm_lock);
 }
 
+#define imx_clk_gate3_flags(name, parent, reg, shift, flags) \
+	to_clk(imx_clk_hw_gate3_flags(name, parent, reg, shift, flags))
+
 static inline struct clk_hw *imx_clk_hw_gate4(const char *name, const char *parent,
 		void __iomem *reg, u8 shift)
 {
@@ -372,15 +390,18 @@ static inline struct clk_hw *imx_clk_hw_gate4(const char *name, const char *pare
 			reg, shift, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
-static inline struct clk *imx_clk_gate4_flags(const char *name,
+static inline struct clk_hw *imx_clk_hw_gate4_flags(const char *name,
 		const char *parent, void __iomem *reg, u8 shift,
 		unsigned long flags)
 {
-	return clk_register_gate2(NULL, name, parent,
+	return clk_hw_register_gate2(NULL, name, parent,
 			flags | CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
 			reg, shift, 0x3, 0, &imx_ccm_lock, NULL);
 }
 
+#define imx_clk_gate4_flags(name, parent, reg, shift, flags) \
+	to_clk(imx_clk_hw_gate4_flags(name, parent, reg, shift, flags))
+
 static inline struct clk_hw *imx_clk_hw_mux(const char *name, void __iomem *reg,
 			u8 shift, u8 width, const char * const *parents,
 			int num_parents)
@@ -420,6 +441,16 @@ static inline struct clk *imx_clk_mux_flags(const char *name,
 			&imx_ccm_lock);
 }
 
+static inline struct clk_hw *imx_clk_hw_mux2_flags(const char *name,
+		void __iomem *reg, u8 shift, u8 width,
+		const char * const *parents,
+		int num_parents, unsigned long flags)
+{
+	return clk_hw_register_mux(NULL, name, parents, num_parents,
+			flags | CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE,
+			reg, shift, width, 0, &imx_ccm_lock);
+}
+
 static inline struct clk *imx_clk_mux2_flags(const char *name,
 		void __iomem *reg, u8 shift, u8 width,
 		const char * const *parents,
@@ -446,23 +477,38 @@ struct clk_hw *imx_clk_hw_cpu(const char *name, const char *parent_name,
 		struct clk *div, struct clk *mux, struct clk *pll,
 		struct clk *step);
 
-struct clk *imx8m_clk_composite_flags(const char *name,
-					const char * const *parent_names,
-					int num_parents, void __iomem *reg,
-					unsigned long flags);
+struct clk_hw *imx8m_clk_hw_composite_flags(const char *name,
+					    const char * const *parent_names,
+					    int num_parents,
+					    void __iomem *reg,
+					    unsigned long flags);
 
-#define __imx8m_clk_composite(name, parent_names, reg, flags) \
-	imx8m_clk_composite_flags(name, parent_names, \
+#define imx8m_clk_composite_flags(name, parent_names, num_parents, reg, \
+				  flags) \
+	to_clk(imx8m_clk_hw_composite_flags(name, parent_names, \
+				num_parents, reg, flags))
+
+#define __imx8m_clk_hw_composite(name, parent_names, reg, flags) \
+	imx8m_clk_hw_composite_flags(name, parent_names, \
 		ARRAY_SIZE(parent_names), reg, \
 		flags | CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE)
 
+#define __imx8m_clk_composite(name, parent_names, reg, flags) \
+	to_clk(__imx8m_clk_hw_composite(name, parent_names, reg, flags))
+
+#define imx8m_clk_hw_composite(name, parent_names, reg) \
+	__imx8m_clk_hw_composite(name, parent_names, reg, 0)
+
 #define imx8m_clk_composite(name, parent_names, reg) \
 	__imx8m_clk_composite(name, parent_names, reg, 0)
 
+#define imx8m_clk_hw_composite_critical(name, parent_names, reg) \
+	__imx8m_clk_hw_composite(name, parent_names, reg, CLK_IS_CRITICAL)
+
 #define imx8m_clk_composite_critical(name, parent_names, reg) \
 	__imx8m_clk_composite(name, parent_names, reg, CLK_IS_CRITICAL)
 
-struct clk_hw *imx_clk_divider_gate(const char *name, const char *parent_name,
+struct clk_hw *imx_clk_hw_divider_gate(const char *name, const char *parent_name,
 		unsigned long flags, void __iomem *reg, u8 shift, u8 width,
 		u8 clk_divider_flags, const struct clk_div_table *table,
 		spinlock_t *lock);
diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig
index 7efc3617bbd5..ea3c70d1307e 100644
--- a/drivers/clk/mediatek/Kconfig
+++ b/drivers/clk/mediatek/Kconfig
@@ -174,36 +174,36 @@ config COMMON_CLK_MT6779_AUDSYS
 	  This driver supports Mediatek MT6779 audsys clocks.
 
 config COMMON_CLK_MT6797
-       bool "Clock driver for MediaTek MT6797"
-       depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST
-       select COMMON_CLK_MEDIATEK
-       default ARCH_MEDIATEK && ARM64
-       ---help---
-         This driver supports MediaTek MT6797 basic clocks.
+	bool "Clock driver for MediaTek MT6797"
+	depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST
+	select COMMON_CLK_MEDIATEK
+	default ARCH_MEDIATEK && ARM64
+	---help---
+	  This driver supports MediaTek MT6797 basic clocks.
 
 config COMMON_CLK_MT6797_MMSYS
-       bool "Clock driver for MediaTek MT6797 mmsys"
-       depends on COMMON_CLK_MT6797
-       ---help---
-         This driver supports MediaTek MT6797 mmsys clocks.
+	bool "Clock driver for MediaTek MT6797 mmsys"
+	depends on COMMON_CLK_MT6797
+	---help---
+	  This driver supports MediaTek MT6797 mmsys clocks.
 
 config COMMON_CLK_MT6797_IMGSYS
-       bool "Clock driver for MediaTek MT6797 imgsys"
-       depends on COMMON_CLK_MT6797
-       ---help---
-         This driver supports MediaTek MT6797 imgsys clocks.
+	bool "Clock driver for MediaTek MT6797 imgsys"
+	depends on COMMON_CLK_MT6797
+	---help---
+	  This driver supports MediaTek MT6797 imgsys clocks.
 
 config COMMON_CLK_MT6797_VDECSYS
-       bool "Clock driver for MediaTek MT6797 vdecsys"
-       depends on COMMON_CLK_MT6797
-       ---help---
-         This driver supports MediaTek MT6797 vdecsys clocks.
+	bool "Clock driver for MediaTek MT6797 vdecsys"
+	depends on COMMON_CLK_MT6797
+	---help---
+	  This driver supports MediaTek MT6797 vdecsys clocks.
 
 config COMMON_CLK_MT6797_VENCSYS
-       bool "Clock driver for MediaTek MT6797 vencsys"
-       depends on COMMON_CLK_MT6797
-       ---help---
-         This driver supports MediaTek MT6797 vencsys clocks.
+	bool "Clock driver for MediaTek MT6797 vencsys"
+	depends on COMMON_CLK_MT6797
+	---help---
+	  This driver supports MediaTek MT6797 vencsys clocks.
 
 config COMMON_CLK_MT7622
 	bool "Clock driver for MediaTek MT7622"
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index 3939f218587a..6eca2a406ee3 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -18,4 +18,4 @@ obj-$(CONFIG_COMMON_CLK_AXG) += axg.o axg-aoclk.o
 obj-$(CONFIG_COMMON_CLK_AXG_AUDIO) += axg-audio.o
 obj-$(CONFIG_COMMON_CLK_GXBB) += gxbb.o gxbb-aoclk.o
 obj-$(CONFIG_COMMON_CLK_G12A) += g12a.o g12a-aoclk.o
-obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
+obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o meson8-ddr.o
diff --git a/drivers/clk/meson/clk-mpll.c b/drivers/clk/meson/clk-mpll.c
index 2d39a8bc367c..fc9df4860872 100644
--- a/drivers/clk/meson/clk-mpll.c
+++ b/drivers/clk/meson/clk-mpll.c
@@ -129,7 +129,7 @@ static int mpll_set_rate(struct clk_hw *hw,
 	return 0;
 }
 
-static void mpll_init(struct clk_hw *hw)
+static int mpll_init(struct clk_hw *hw)
 {
 	struct clk_regmap *clk = to_clk_regmap(hw);
 	struct meson_clk_mpll_data *mpll = meson_clk_mpll_data(clk);
@@ -151,6 +151,8 @@ static void mpll_init(struct clk_hw *hw)
 	/* Set the magic misc bit if required */
 	if (MESON_PARM_APPLICABLE(&mpll->misc))
 		meson_parm_write(clk->map, &mpll->misc, 1);
+
+	return 0;
 }
 
 const struct clk_ops meson_clk_mpll_ro_ops = {
diff --git a/drivers/clk/meson/clk-phase.c b/drivers/clk/meson/clk-phase.c
index 80c3ada193a4..fe22e171121a 100644
--- a/drivers/clk/meson/clk-phase.c
+++ b/drivers/clk/meson/clk-phase.c
@@ -78,7 +78,7 @@ meson_clk_triphase_data(struct clk_regmap *clk)
 	return (struct meson_clk_triphase_data *)clk->data;
 }
 
-static void meson_clk_triphase_sync(struct clk_hw *hw)
+static int meson_clk_triphase_sync(struct clk_hw *hw)
 {
 	struct clk_regmap *clk = to_clk_regmap(hw);
 	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
@@ -88,6 +88,8 @@ static void meson_clk_triphase_sync(struct clk_hw *hw)
 	val = meson_parm_read(clk->map, &tph->ph0);
 	meson_parm_write(clk->map, &tph->ph1, val);
 	meson_parm_write(clk->map, &tph->ph2, val);
+
+	return 0;
 }
 
 static int meson_clk_triphase_get_phase(struct clk_hw *hw)
diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c
index ddb1e5634739..b17a13e9337c 100644
--- a/drivers/clk/meson/clk-pll.c
+++ b/drivers/clk/meson/clk-pll.c
@@ -77,6 +77,15 @@ static unsigned long meson_clk_pll_recalc_rate(struct clk_hw *hw,
 	unsigned int m, n, frac;
 
 	n = meson_parm_read(clk->map, &pll->n);
+
+	/*
+	 * On some HW, N is set to zero on init. This value is invalid as
+	 * it would result in a division by zero. The rate can't be
+	 * calculated in this case
+	 */
+	if (n == 0)
+		return 0;
+
 	m = meson_parm_read(clk->map, &pll->m);
 
 	frac = MESON_PARM_APPLICABLE(&pll->frac) ?
@@ -277,7 +286,7 @@ static int meson_clk_pll_wait_lock(struct clk_hw *hw)
 	return -ETIMEDOUT;
 }
 
-static void meson_clk_pll_init(struct clk_hw *hw)
+static int meson_clk_pll_init(struct clk_hw *hw)
 {
 	struct clk_regmap *clk = to_clk_regmap(hw);
 	struct meson_clk_pll_data *pll = meson_clk_pll_data(clk);
@@ -288,6 +297,8 @@ static void meson_clk_pll_init(struct clk_hw *hw)
 				       pll->init_count);
 		meson_parm_write(clk->map, &pll->rst, 0);
 	}
+
+	return 0;
 }
 
 static int meson_clk_pll_is_enabled(struct clk_hw *hw)
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index b3af61cc6fb9..d2760a021301 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -4692,6 +4692,7 @@ static struct clk_regmap *const g12a_clk_regmaps[] = {
 	&g12a_bt656,
 	&g12a_usb1_to_ddr,
 	&g12a_mmc_pclk,
+	&g12a_uart2,
 	&g12a_vpu_intr,
 	&g12a_gic,
 	&g12a_sd_emmc_a_clk0,
diff --git a/drivers/clk/meson/meson8-ddr.c b/drivers/clk/meson/meson8-ddr.c
new file mode 100644
index 000000000000..4b73ea244b63
--- /dev/null
+++ b/drivers/clk/meson/meson8-ddr.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Amlogic Meson8 DDR clock controller
+ *
+ * Copyright (C) 2019 Martin Blumenstingl <martin.blumenstingl@googlemail.com>
+ */
+
+#include <dt-bindings/clock/meson8-ddr-clkc.h>
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+
+#include "clk-regmap.h"
+#include "clk-pll.h"
+
+#define AM_DDR_PLL_CNTL			0x00
+#define AM_DDR_PLL_CNTL1		0x04
+#define AM_DDR_PLL_CNTL2		0x08
+#define AM_DDR_PLL_CNTL3		0x0c
+#define AM_DDR_PLL_CNTL4		0x10
+#define AM_DDR_PLL_STS			0x14
+#define DDR_CLK_CNTL			0x18
+#define DDR_CLK_STS			0x1c
+
+static struct clk_regmap meson8_ddr_pll_dco = {
+	.data = &(struct meson_clk_pll_data){
+		.en = {
+			.reg_off = AM_DDR_PLL_CNTL,
+			.shift   = 30,
+			.width   = 1,
+		},
+		.m = {
+			.reg_off = AM_DDR_PLL_CNTL,
+			.shift   = 0,
+			.width   = 9,
+		},
+		.n = {
+			.reg_off = AM_DDR_PLL_CNTL,
+			.shift   = 9,
+			.width   = 5,
+		},
+		.l = {
+			.reg_off = AM_DDR_PLL_CNTL,
+			.shift   = 31,
+			.width   = 1,
+		},
+		.rst = {
+			.reg_off = AM_DDR_PLL_CNTL,
+			.shift   = 29,
+			.width   = 1,
+		},
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "ddr_pll_dco",
+		.ops = &meson_clk_pll_ro_ops,
+		.parent_data = &(const struct clk_parent_data) {
+			.fw_name = "xtal",
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_regmap meson8_ddr_pll = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = AM_DDR_PLL_CNTL,
+		.shift = 16,
+		.width = 2,
+		.flags = CLK_DIVIDER_POWER_OF_TWO,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "ddr_pll",
+		.ops = &clk_regmap_divider_ro_ops,
+		.parent_hws = (const struct clk_hw *[]) {
+			&meson8_ddr_pll_dco.hw
+		},
+		.num_parents = 1,
+	},
+};
+
+static struct clk_hw_onecell_data meson8_ddr_clk_hw_onecell_data = {
+	.hws = {
+		[DDR_CLKID_DDR_PLL_DCO]		= &meson8_ddr_pll_dco.hw,
+		[DDR_CLKID_DDR_PLL]		= &meson8_ddr_pll.hw,
+	},
+	.num = 2,
+};
+
+static struct clk_regmap *const meson8_ddr_clk_regmaps[] = {
+	&meson8_ddr_pll_dco,
+	&meson8_ddr_pll,
+};
+
+static const struct regmap_config meson8_ddr_clkc_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = DDR_CLK_STS,
+};
+
+static int meson8_ddr_clkc_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	void __iomem *base;
+	struct clk_hw *hw;
+	int ret, i;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	regmap = devm_regmap_init_mmio(&pdev->dev, base,
+				       &meson8_ddr_clkc_regmap_config);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* Populate regmap */
+	for (i = 0; i < ARRAY_SIZE(meson8_ddr_clk_regmaps); i++)
+		meson8_ddr_clk_regmaps[i]->map = regmap;
+
+	/* Register all clks */
+	for (i = 0; i < meson8_ddr_clk_hw_onecell_data.num; i++) {
+		hw = meson8_ddr_clk_hw_onecell_data.hws[i];
+
+		ret = devm_clk_hw_register(&pdev->dev, hw);
+		if (ret) {
+			dev_err(&pdev->dev, "Clock registration failed\n");
+			return ret;
+		}
+	}
+
+	return devm_of_clk_add_hw_provider(&pdev->dev, of_clk_hw_onecell_get,
+					   &meson8_ddr_clk_hw_onecell_data);
+}
+
+static const struct of_device_id meson8_ddr_clkc_match_table[] = {
+	{ .compatible = "amlogic,meson8-ddr-clkc" },
+	{ .compatible = "amlogic,meson8b-ddr-clkc" },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver meson8_ddr_clkc_driver = {
+	.probe		= meson8_ddr_clkc_probe,
+	.driver		= {
+		.name	= "meson8-ddr-clkc",
+		.of_match_table = meson8_ddr_clkc_match_table,
+	},
+};
+
+builtin_platform_driver(meson8_ddr_clkc_driver);
diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c
index 67e6691e080c..9fd31f23b2a9 100644
--- a/drivers/clk/meson/meson8b.c
+++ b/drivers/clk/meson/meson8b.c
@@ -97,8 +97,10 @@ static struct clk_regmap meson8b_fixed_pll_dco = {
 	.hw.init = &(struct clk_init_data){
 		.name = "fixed_pll_dco",
 		.ops = &meson_clk_pll_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw
+		.parent_data = &(const struct clk_parent_data) {
+			.fw_name = "xtal",
+			.name = "xtal",
+			.index = -1,
 		},
 		.num_parents = 1,
 	},
@@ -162,8 +164,10 @@ static struct clk_regmap meson8b_hdmi_pll_dco = {
 		/* sometimes also called "HPLL" or "HPLL PLL" */
 		.name = "hdmi_pll_dco",
 		.ops = &meson_clk_pll_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw
+		.parent_data = &(const struct clk_parent_data) {
+			.fw_name = "xtal",
+			.name = "xtal",
+			.index = -1,
 		},
 		.num_parents = 1,
 	},
@@ -237,8 +241,10 @@ static struct clk_regmap meson8b_sys_pll_dco = {
 	.hw.init = &(struct clk_init_data){
 		.name = "sys_pll_dco",
 		.ops = &meson_clk_pll_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw
+		.parent_data = &(const struct clk_parent_data) {
+			.fw_name = "xtal",
+			.name = "xtal",
+			.index = -1,
 		},
 		.num_parents = 1,
 	},
@@ -631,9 +637,9 @@ static struct clk_regmap meson8b_cpu_in_sel = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_in_sel",
 		.ops = &clk_regmap_mux_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw,
-			&meson8b_sys_pll.hw,
+		.parent_data = (const struct clk_parent_data[]) {
+			{ .fw_name = "xtal", .name = "xtal", .index = -1, },
+			{ .hw = &meson8b_sys_pll.hw, },
 		},
 		.num_parents = 2,
 		.flags = (CLK_SET_RATE_PARENT |
@@ -736,9 +742,9 @@ static struct clk_regmap meson8b_cpu_clk = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk",
 		.ops = &clk_regmap_mux_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw,
-			&meson8b_cpu_scale_out_sel.hw,
+		.parent_data = (const struct clk_parent_data[]) {
+			{ .fw_name = "xtal", .name = "xtal", .index = -1, },
+			{ .hw = &meson8b_cpu_scale_out_sel.hw, },
 		},
 		.num_parents = 2,
 		.flags = (CLK_SET_RATE_PARENT |
@@ -758,12 +764,12 @@ static struct clk_regmap meson8b_nand_clk_sel = {
 		.name = "nand_clk_sel",
 		.ops = &clk_regmap_mux_ops,
 		/* FIXME all other parents are unknown: */
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_fclk_div4.hw,
-			&meson8b_fclk_div3.hw,
-			&meson8b_fclk_div5.hw,
-			&meson8b_fclk_div7.hw,
-			&meson8b_xtal.hw,
+		.parent_data = (const struct clk_parent_data[]) {
+			{ .hw = &meson8b_fclk_div4.hw, },
+			{ .hw = &meson8b_fclk_div3.hw, },
+			{ .hw = &meson8b_fclk_div5.hw, },
+			{ .hw = &meson8b_fclk_div7.hw, },
+			{ .fw_name = "xtal", .name = "xtal", .index = -1, },
 		},
 		.num_parents = 5,
 		.flags = CLK_SET_RATE_PARENT,
@@ -1721,8 +1727,10 @@ static struct clk_regmap meson8b_hdmi_sys_sel = {
 		.name = "hdmi_sys_sel",
 		.ops = &clk_regmap_mux_ro_ops,
 		/* FIXME: all other parents are unknown */
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw
+		.parent_data = &(const struct clk_parent_data) {
+			.fw_name = "xtal",
+			.name = "xtal",
+			.index = -1,
 		},
 		.num_parents = 1,
 		.flags = CLK_SET_RATE_NO_REPARENT,
@@ -1764,17 +1772,20 @@ static struct clk_regmap meson8b_hdmi_sys = {
 
 /*
  * The MALI IP is clocked by two identical clocks (mali_0 and mali_1)
- * muxed by a glitch-free switch on Meson8b and Meson8m2. Meson8 only
- * has mali_0 and no glitch-free mux.
+ * muxed by a glitch-free switch on Meson8b and Meson8m2. The CCF can
+ * actually manage this glitch-free mux because it does top-to-bottom
+ * updates the each clock tree and switches to the "inactive" one when
+ * CLK_SET_RATE_GATE is set.
+ * Meson8 only has mali_0 and no glitch-free mux.
  */
-static const struct clk_hw *meson8b_mali_0_1_parent_hws[] = {
-	&meson8b_xtal.hw,
-	&meson8b_mpll2.hw,
-	&meson8b_mpll1.hw,
-	&meson8b_fclk_div7.hw,
-	&meson8b_fclk_div4.hw,
-	&meson8b_fclk_div3.hw,
-	&meson8b_fclk_div5.hw,
+static const struct clk_parent_data meson8b_mali_0_1_parent_data[] = {
+	{ .fw_name = "xtal", .name = "xtal", .index = -1, },
+	{ .hw = &meson8b_mpll2.hw, },
+	{ .hw = &meson8b_mpll1.hw, },
+	{ .hw = &meson8b_fclk_div7.hw, },
+	{ .hw = &meson8b_fclk_div4.hw, },
+	{ .hw = &meson8b_fclk_div3.hw, },
+	{ .hw = &meson8b_fclk_div5.hw, },
 };
 
 static u32 meson8b_mali_0_1_mux_table[] = { 0, 2, 3, 4, 5, 6, 7 };
@@ -1789,8 +1800,8 @@ static struct clk_regmap meson8b_mali_0_sel = {
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_0_sel",
 		.ops = &clk_regmap_mux_ops,
-		.parent_hws = meson8b_mali_0_1_parent_hws,
-		.num_parents = ARRAY_SIZE(meson8b_mali_0_1_parent_hws),
+		.parent_data = meson8b_mali_0_1_parent_data,
+		.num_parents = ARRAY_SIZE(meson8b_mali_0_1_parent_data),
 		/*
 		 * Don't propagate rate changes up because the only changeable
 		 * parents are mpll1 and mpll2 but we need those for audio and
@@ -1830,7 +1841,7 @@ static struct clk_regmap meson8b_mali_0 = {
 			&meson8b_mali_0_div.hw
 		},
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT,
+		.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1844,8 +1855,8 @@ static struct clk_regmap meson8b_mali_1_sel = {
 	.hw.init = &(struct clk_init_data){
 		.name = "mali_1_sel",
 		.ops = &clk_regmap_mux_ops,
-		.parent_hws = meson8b_mali_0_1_parent_hws,
-		.num_parents = ARRAY_SIZE(meson8b_mali_0_1_parent_hws),
+		.parent_data = meson8b_mali_0_1_parent_data,
+		.num_parents = ARRAY_SIZE(meson8b_mali_0_1_parent_data),
 		/*
 		 * Don't propagate rate changes up because the only changeable
 		 * parents are mpll1 and mpll2 but we need those for audio and
@@ -1885,7 +1896,7 @@ static struct clk_regmap meson8b_mali_1 = {
 			&meson8b_mali_1_div.hw
 		},
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT,
+		.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -1944,8 +1955,10 @@ static struct clk_regmap meson8m2_gp_pll_dco = {
 	.hw.init = &(struct clk_init_data){
 		.name = "gp_pll_dco",
 		.ops = &meson_clk_pll_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&meson8b_xtal.hw
+		.parent_data = &(const struct clk_parent_data) {
+			.fw_name = "xtal",
+			.name = "xtal",
+			.index = -1,
 		},
 		.num_parents = 1,
 	},
@@ -3585,7 +3598,7 @@ static const struct reset_control_ops meson8b_clk_reset_ops = {
 
 struct meson8b_nb_data {
 	struct notifier_block nb;
-	struct clk_hw_onecell_data *onecell_data;
+	struct clk_hw *cpu_clk;
 };
 
 static int meson8b_cpu_clk_notifier_cb(struct notifier_block *nb,
@@ -3593,30 +3606,25 @@ static int meson8b_cpu_clk_notifier_cb(struct notifier_block *nb,
 {
 	struct meson8b_nb_data *nb_data =
 		container_of(nb, struct meson8b_nb_data, nb);
-	struct clk_hw **hws = nb_data->onecell_data->hws;
-	struct clk_hw *cpu_clk_hw, *parent_clk_hw;
-	struct clk *cpu_clk, *parent_clk;
+	struct clk_hw *parent_clk;
 	int ret;
 
 	switch (event) {
 	case PRE_RATE_CHANGE:
-		parent_clk_hw = hws[CLKID_XTAL];
+		/* xtal */
+		parent_clk = clk_hw_get_parent_by_index(nb_data->cpu_clk, 0);
 		break;
 
 	case POST_RATE_CHANGE:
-		parent_clk_hw = hws[CLKID_CPU_SCALE_OUT_SEL];
+		/* cpu_scale_out_sel */
+		parent_clk = clk_hw_get_parent_by_index(nb_data->cpu_clk, 1);
 		break;
 
 	default:
 		return NOTIFY_DONE;
 	}
 
-	cpu_clk_hw = hws[CLKID_CPUCLK];
-	cpu_clk = __clk_lookup(clk_hw_get_name(cpu_clk_hw));
-
-	parent_clk = __clk_lookup(clk_hw_get_name(parent_clk_hw));
-
-	ret = clk_set_parent(cpu_clk, parent_clk);
+	ret = clk_hw_set_parent(nb_data->cpu_clk, parent_clk);
 	if (ret)
 		return notifier_from_errno(ret);
 
@@ -3682,20 +3690,26 @@ static void __init meson8b_clkc_init_common(struct device_node *np,
 		meson8b_clk_regmaps[i]->map = map;
 
 	/*
-	 * register all clks
-	 * CLKID_UNUSED = 0, so skip it and start with CLKID_XTAL = 1
+	 * always skip CLKID_UNUSED and also skip XTAL if the .dtb provides the
+	 * XTAL clock as input.
 	 */
-	for (i = CLKID_XTAL; i < CLK_NR_CLKS; i++) {
+	if (!IS_ERR(of_clk_get_by_name(np, "xtal")))
+		i = CLKID_PLL_FIXED;
+	else
+		i = CLKID_XTAL;
+
+	/* register all clks */
+	for (; i < CLK_NR_CLKS; i++) {
 		/* array might be sparse */
 		if (!clk_hw_onecell_data->hws[i])
 			continue;
 
-		ret = clk_hw_register(NULL, clk_hw_onecell_data->hws[i]);
+		ret = of_clk_hw_register(np, clk_hw_onecell_data->hws[i]);
 		if (ret)
 			return;
 	}
 
-	meson8b_cpu_nb_data.onecell_data = clk_hw_onecell_data;
+	meson8b_cpu_nb_data.cpu_clk = clk_hw_onecell_data->hws[CLKID_CPUCLK];
 
 	/*
 	 * FIXME we shouldn't program the muxes in notifier handlers. The
diff --git a/drivers/clk/meson/sclk-div.c b/drivers/clk/meson/sclk-div.c
index 3acf03780221..76d31c0a3342 100644
--- a/drivers/clk/meson/sclk-div.c
+++ b/drivers/clk/meson/sclk-div.c
@@ -216,7 +216,7 @@ static int sclk_div_is_enabled(struct clk_hw *hw)
 	return 0;
 }
 
-static void sclk_div_init(struct clk_hw *hw)
+static int sclk_div_init(struct clk_hw *hw)
 {
 	struct clk_regmap *clk = to_clk_regmap(hw);
 	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
@@ -231,6 +231,8 @@ static void sclk_div_init(struct clk_hw *hw)
 		sclk->cached_div = val + 1;
 
 	sclk_div_get_duty_cycle(hw, &sclk->cached_duty);
+
+	return 0;
 }
 
 const struct clk_ops meson_sclk_div_ops = {
diff --git a/drivers/clk/microchip/clk-core.c b/drivers/clk/microchip/clk-core.c
index 567755d6f844..1b4f023cdc8b 100644
--- a/drivers/clk/microchip/clk-core.c
+++ b/drivers/clk/microchip/clk-core.c
@@ -266,10 +266,12 @@ static void roclk_disable(struct clk_hw *hw)
 	writel(REFO_ON | REFO_OE, PIC32_CLR(refo->ctrl_reg));
 }
 
-static void roclk_init(struct clk_hw *hw)
+static int roclk_init(struct clk_hw *hw)
 {
 	/* initialize clock in disabled state */
 	roclk_disable(hw);
+
+	return 0;
 }
 
 static u8 roclk_get_parent(struct clk_hw *hw)
@@ -880,7 +882,7 @@ static int sclk_set_parent(struct clk_hw *hw, u8 index)
 	return err;
 }
 
-static void sclk_init(struct clk_hw *hw)
+static int sclk_init(struct clk_hw *hw)
 {
 	struct pic32_sys_clk *sclk = clkhw_to_sys_clk(hw);
 	unsigned long flags;
@@ -899,6 +901,8 @@ static void sclk_init(struct clk_hw *hw)
 		writel(v, sclk->slew_reg);
 		spin_unlock_irqrestore(&sclk->core->reg_lock, flags);
 	}
+
+	return 0;
 }
 
 /* sclk with post-divider */
diff --git a/drivers/clk/mmp/clk-frac.c b/drivers/clk/mmp/clk-frac.c
index 90bf181f191a..fabc09aca6c4 100644
--- a/drivers/clk/mmp/clk-frac.c
+++ b/drivers/clk/mmp/clk-frac.c
@@ -109,7 +109,7 @@ static int clk_factor_set_rate(struct clk_hw *hw, unsigned long drate,
 	return 0;
 }
 
-static void clk_factor_init(struct clk_hw *hw)
+static int clk_factor_init(struct clk_hw *hw)
 {
 	struct mmp_clk_factor *factor = to_clk_factor(hw);
 	struct mmp_clk_factor_masks *masks = factor->masks;
@@ -146,6 +146,8 @@ static void clk_factor_init(struct clk_hw *hw)
 
 	if (factor->lock)
 		spin_unlock_irqrestore(factor->lock, flags);
+
+	return 0;
 }
 
 static const struct clk_ops clk_factor_ops = {
diff --git a/drivers/clk/mmp/clk-mix.c b/drivers/clk/mmp/clk-mix.c
index 90814b2613c0..d2cd36c54474 100644
--- a/drivers/clk/mmp/clk-mix.c
+++ b/drivers/clk/mmp/clk-mix.c
@@ -419,12 +419,14 @@ static int mmp_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	}
 }
 
-static void mmp_clk_mix_init(struct clk_hw *hw)
+static int mmp_clk_mix_init(struct clk_hw *hw)
 {
 	struct mmp_clk_mix *mix = to_clk_mix(hw);
 
 	if (mix->table)
 		_filter_clk_table(mix, mix->table, mix->table_size);
+
+	return 0;
 }
 
 const struct clk_ops mmp_clk_mix_ops = {
diff --git a/drivers/clk/mvebu/Kconfig b/drivers/clk/mvebu/Kconfig
index 415e6906a113..ded07b0bd0d5 100644
--- a/drivers/clk/mvebu/Kconfig
+++ b/drivers/clk/mvebu/Kconfig
@@ -29,7 +29,7 @@ config ARMADA_39X_CLK
 	select MVEBU_CLK_COMMON
 
 config ARMADA_37XX_CLK
-       bool
+	bool
 
 config ARMADA_XP_CLK
 	bool
diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 3b33ef129274..15cdcdc9b3b8 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config KRAIT_CLOCKS
-       bool
-       select KRAIT_L2_ACCESSORS
+	bool
+	select KRAIT_L2_ACCESSORS
 
 config QCOM_GDSC
 	bool
@@ -14,6 +14,7 @@ menuconfig COMMON_CLK_QCOM
 	tristate "Support for Qualcomm's clock controllers"
 	depends on OF
 	depends on ARCH_QCOM || COMPILE_TEST
+	select RATIONAL
 	select REGMAP_MMIO
 	select RESET_CONTROLLER
 
@@ -95,6 +96,14 @@ config IPQ_GCC_4019
 	  Say Y if you want to use peripheral devices such as UART, SPI,
 	  i2c, USB, SD/eMMC, etc.
 
+config IPQ_GCC_6018
+	tristate "IPQ6018 Global Clock Controller"
+	help
+	  Support for global clock controller on ipq6018 devices.
+	  Say Y if you want to use peripheral devices such as UART, SPI,
+	  i2c, USB, SD/eMMC, etc. Select this for the root clock
+	  of ipq6018.
+
 config IPQ_GCC_806X
 	tristate "IPQ806x Global Clock Controller"
 	help
@@ -229,6 +238,15 @@ config MSM_GPUCC_8998
 	  Say Y if you want to support graphics controller devices and
 	  functionality such as 3D graphics.
 
+config MSM_MMCC_8998
+	tristate "MSM8998 Multimedia Clock Controller"
+	select MSM_GCC_8998
+	select QCOM_GDSC
+	help
+	  Support for the multimedia clock controller on msm8998 devices.
+	  Say Y if you want to support multimedia devices such as display,
+	  graphics, video encode/decode, camera, etc.
+
 config QCS_GCC_404
 	tristate "QCS404 Global Clock Controller"
 	help
@@ -236,6 +254,15 @@ config QCS_GCC_404
 	  Say Y if you want to use multimedia devices or peripheral
 	  devices such as UART, SPI, I2C, USB, SD/eMMC, PCIe etc.
 
+config SC_DISPCC_7180
+	tristate "SC7180 Display Clock Controller"
+	select SC_GCC_7180
+	help
+	  Support for the display clock controller on Qualcomm Technologies, Inc
+	  SC7180 devices.
+	  Say Y if you want to support display devices and functionality such as
+	  splash screen.
+
 config SC_GCC_7180
 	tristate "SC7180 Global Clock Controller"
 	select QCOM_GDSC
@@ -245,6 +272,22 @@ config SC_GCC_7180
 	  Say Y if you want to use peripheral devices such as UART, SPI,
 	  I2C, USB, UFS, SDCC, etc.
 
+config SC_GPUCC_7180
+	tristate "SC7180 Graphics Clock Controller"
+	select SC_GCC_7180
+	help
+	  Support for the graphics clock controller on SC7180 devices.
+	  Say Y if you want to support graphics controller devices and
+	  functionality such as 3D graphics.
+
+config SC_VIDEOCC_7180
+	tristate "SC7180 Video Clock Controller"
+	select SC_GCC_7180
+	help
+	  Support for the video clock controller on SC7180 devices.
+	  Say Y if you want to support video devices and functionality such as
+	  video encode and decode.
+
 config SDM_CAMCC_845
 	tristate "SDM845 Camera Clock Controller"
 	select SDM_GCC_845
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index d899661d0f44..656a87e629d4 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -20,6 +20,7 @@ clk-qcom-$(CONFIG_QCOM_GDSC) += gdsc.o
 obj-$(CONFIG_APQ_GCC_8084) += gcc-apq8084.o
 obj-$(CONFIG_APQ_MMCC_8084) += mmcc-apq8084.o
 obj-$(CONFIG_IPQ_GCC_4019) += gcc-ipq4019.o
+obj-$(CONFIG_IPQ_GCC_6018) += gcc-ipq6018.o
 obj-$(CONFIG_IPQ_GCC_806X) += gcc-ipq806x.o
 obj-$(CONFIG_IPQ_GCC_8074) += gcc-ipq8074.o
 obj-$(CONFIG_IPQ_LCC_806X) += lcc-ipq806x.o
@@ -37,6 +38,7 @@ obj-$(CONFIG_MSM_GPUCC_8998) += gpucc-msm8998.o
 obj-$(CONFIG_MSM_MMCC_8960) += mmcc-msm8960.o
 obj-$(CONFIG_MSM_MMCC_8974) += mmcc-msm8974.o
 obj-$(CONFIG_MSM_MMCC_8996) += mmcc-msm8996.o
+obj-$(CONFIG_MSM_MMCC_8998) += mmcc-msm8998.o
 obj-$(CONFIG_QCOM_A53PLL) += a53-pll.o
 obj-$(CONFIG_QCOM_CLK_APCS_MSM8916) += apcs-msm8916.o
 obj-$(CONFIG_QCOM_CLK_RPM) += clk-rpm.o
@@ -45,7 +47,10 @@ obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o
 obj-$(CONFIG_QCS_GCC_404) += gcc-qcs404.o
 obj-$(CONFIG_QCS_Q6SSTOP_404) += q6sstop-qcs404.o
 obj-$(CONFIG_QCS_TURING_404) += turingcc-qcs404.o
+obj-$(CONFIG_SC_DISPCC_7180) += dispcc-sc7180.o
 obj-$(CONFIG_SC_GCC_7180) += gcc-sc7180.o
+obj-$(CONFIG_SC_GPUCC_7180) += gpucc-sc7180.o
+obj-$(CONFIG_SC_VIDEOCC_7180) += videocc-sc7180.o
 obj-$(CONFIG_SDM_CAMCC_845) += camcc-sdm845.o
 obj-$(CONFIG_SDM_DISPCC_845) += dispcc-sdm845.o
 obj-$(CONFIG_SDM_GCC_660) += gcc-sdm660.o
diff --git a/drivers/clk/qcom/apcs-msm8916.c b/drivers/clk/qcom/apcs-msm8916.c
index a6c89a310b18..cf69a97d0439 100644
--- a/drivers/clk/qcom/apcs-msm8916.c
+++ b/drivers/clk/qcom/apcs-msm8916.c
@@ -19,9 +19,9 @@
 
 static const u32 gpll0_a53cc_map[] = { 4, 5 };
 
-static const char * const gpll0_a53cc[] = {
-	"gpll0_vote",
-	"a53pll",
+static const struct clk_parent_data pdata[] = {
+	{ .fw_name = "aux", .name = "gpll0_vote", },
+	{ .fw_name = "pll", .name = "a53pll", },
 };
 
 /*
@@ -62,8 +62,8 @@ static int qcom_apcs_msm8916_clk_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	init.name = "a53mux";
-	init.parent_names = gpll0_a53cc;
-	init.num_parents = ARRAY_SIZE(gpll0_a53cc);
+	init.parent_data = pdata;
+	init.num_parents = ARRAY_SIZE(pdata);
 	init.ops = &clk_regmap_mux_div_ops;
 	init.flags = CLK_SET_RATE_PARENT;
 
@@ -79,7 +79,8 @@ static int qcom_apcs_msm8916_clk_probe(struct platform_device *pdev)
 	a53cc->pclk = devm_clk_get(parent, NULL);
 	if (IS_ERR(a53cc->pclk)) {
 		ret = PTR_ERR(a53cc->pclk);
-		dev_err(dev, "failed to get clk: %d\n", ret);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get clk: %d\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 055318f97991..7c2936da9b14 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -878,6 +878,14 @@ static long clk_trion_pll_round_rate(struct clk_hw *hw, unsigned long rate,
 	return clamp(rate, min_freq, max_freq);
 }
 
+const struct clk_ops clk_alpha_pll_fixed_ops = {
+	.enable = clk_alpha_pll_enable,
+	.disable = clk_alpha_pll_disable,
+	.is_enabled = clk_alpha_pll_is_enabled,
+	.recalc_rate = clk_alpha_pll_recalc_rate,
+};
+EXPORT_SYMBOL_GPL(clk_alpha_pll_fixed_ops);
+
 const struct clk_ops clk_alpha_pll_ops = {
 	.enable = clk_alpha_pll_enable,
 	.disable = clk_alpha_pll_disable,
@@ -1024,6 +1032,25 @@ void clk_fabia_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
 		regmap_write(regmap, PLL_CONFIG_CTL(pll),
 						config->config_ctl_val);
 
+	if (config->config_ctl_hi_val)
+		regmap_write(regmap, PLL_CONFIG_CTL_U(pll),
+						config->config_ctl_hi_val);
+
+	if (config->user_ctl_val)
+		regmap_write(regmap, PLL_USER_CTL(pll), config->user_ctl_val);
+
+	if (config->user_ctl_hi_val)
+		regmap_write(regmap, PLL_USER_CTL_U(pll),
+						config->user_ctl_hi_val);
+
+	if (config->test_ctl_val)
+		regmap_write(regmap, PLL_TEST_CTL(pll),
+						config->test_ctl_val);
+
+	if (config->test_ctl_hi_val)
+		regmap_write(regmap, PLL_TEST_CTL_U(pll),
+						config->test_ctl_hi_val);
+
 	if (config->post_div_mask) {
 		mask = config->post_div_mask;
 		val = config->post_div_val;
@@ -1141,14 +1168,9 @@ static int alpha_pll_fabia_set_rate(struct clk_hw *hw, unsigned long rate,
 						unsigned long prate)
 {
 	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
-	u32 val, l, alpha_width = pll_alpha_width(pll);
+	u32 l, alpha_width = pll_alpha_width(pll);
 	u64 a;
 	unsigned long rrate;
-	int ret = 0;
-
-	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
-	if (ret)
-		return ret;
 
 	rrate = alpha_pll_round_rate(rate, prate, &l, &a, alpha_width);
 
@@ -1167,7 +1189,64 @@ static int alpha_pll_fabia_set_rate(struct clk_hw *hw, unsigned long rate,
 	return __clk_alpha_pll_update_latch(pll);
 }
 
+static int alpha_pll_fabia_prepare(struct clk_hw *hw)
+{
+	struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+	const struct pll_vco *vco;
+	struct clk_hw *parent_hw;
+	unsigned long cal_freq, rrate;
+	u32 cal_l, val, alpha_width = pll_alpha_width(pll);
+	u64 a;
+	int ret;
+
+	/* Check if calibration needs to be done i.e. PLL is in reset */
+	ret = regmap_read(pll->clkr.regmap, PLL_MODE(pll), &val);
+	if (ret)
+		return ret;
+
+	/* Return early if calibration is not needed. */
+	if (val & PLL_RESET_N)
+		return 0;
+
+	vco = alpha_pll_find_vco(pll, clk_hw_get_rate(hw));
+	if (!vco) {
+		pr_err("alpha pll: not in a valid vco range\n");
+		return -EINVAL;
+	}
+
+	cal_freq = DIV_ROUND_CLOSEST((pll->vco_table[0].min_freq +
+				pll->vco_table[0].max_freq) * 54, 100);
+
+	parent_hw = clk_hw_get_parent(hw);
+	if (!parent_hw)
+		return -EINVAL;
+
+	rrate = alpha_pll_round_rate(cal_freq, clk_hw_get_rate(parent_hw),
+					&cal_l, &a, alpha_width);
+	/*
+	 * Due to a limited number of bits for fractional rate programming, the
+	 * rounded up rate could be marginally higher than the requested rate.
+	 */
+	if (rrate > (cal_freq + FABIA_PLL_RATE_MARGIN) || rrate < cal_freq)
+		return -EINVAL;
+
+	/* Setup PLL for calibration frequency */
+	regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), cal_l);
+
+	/* Bringup the PLL at calibration frequency */
+	ret = clk_alpha_pll_enable(hw);
+	if (ret) {
+		pr_err("alpha pll calibration failed\n");
+		return ret;
+	}
+
+	clk_alpha_pll_disable(hw);
+
+	return 0;
+}
+
 const struct clk_ops clk_alpha_pll_fabia_ops = {
+	.prepare = alpha_pll_fabia_prepare,
 	.enable = alpha_pll_fabia_enable,
 	.disable = alpha_pll_fabia_disable,
 	.is_enabled = clk_alpha_pll_is_enabled,
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index 15f27f4b06df..fbc1f67c7a26 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -94,6 +94,10 @@ struct alpha_pll_config {
 	u32 alpha_hi;
 	u32 config_ctl_val;
 	u32 config_ctl_hi_val;
+	u32 user_ctl_val;
+	u32 user_ctl_hi_val;
+	u32 test_ctl_val;
+	u32 test_ctl_hi_val;
 	u32 main_output_mask;
 	u32 aux_output_mask;
 	u32 aux2_output_mask;
@@ -109,6 +113,7 @@ struct alpha_pll_config {
 };
 
 extern const struct clk_ops clk_alpha_pll_ops;
+extern const struct clk_ops clk_alpha_pll_fixed_ops;
 extern const struct clk_ops clk_alpha_pll_hwfsm_ops;
 extern const struct clk_ops clk_alpha_pll_postdiv_ops;
 extern const struct clk_ops clk_alpha_pll_huayra_ops;
diff --git a/drivers/clk/qcom/clk-hfpll.c b/drivers/clk/qcom/clk-hfpll.c
index 3c04805f2a55..e847d586a73a 100644
--- a/drivers/clk/qcom/clk-hfpll.c
+++ b/drivers/clk/qcom/clk-hfpll.c
@@ -196,7 +196,7 @@ static unsigned long clk_hfpll_recalc_rate(struct clk_hw *hw,
 	return l_val * parent_rate;
 }
 
-static void clk_hfpll_init(struct clk_hw *hw)
+static int clk_hfpll_init(struct clk_hw *hw)
 {
 	struct clk_hfpll *h = to_clk_hfpll(hw);
 	struct hfpll_data const *hd = h->d;
@@ -206,7 +206,7 @@ static void clk_hfpll_init(struct clk_hw *hw)
 	regmap_read(regmap, hd->mode_reg, &mode);
 	if (mode != (PLL_BYPASSNL | PLL_RESET_N | PLL_OUTCTRL)) {
 		__clk_hfpll_init_once(hw);
-		return;
+		return 0;
 	}
 
 	if (hd->status_reg) {
@@ -218,6 +218,8 @@ static void clk_hfpll_init(struct clk_hw *hw)
 			__clk_hfpll_init_once(hw);
 		}
 	}
+
+	return 0;
 }
 
 static int hfpll_is_enabled(struct clk_hw *hw)
diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index 78358b81d249..86d2b8b90173 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -161,6 +161,7 @@ extern const struct clk_ops clk_byte2_ops;
 extern const struct clk_ops clk_pixel_ops;
 extern const struct clk_ops clk_gfx3d_ops;
 extern const struct clk_ops clk_rcg2_shared_ops;
+extern const struct clk_ops clk_dp_ops;
 
 struct clk_rcg_dfs_data {
 	struct clk_rcg2 *rcg;
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index 8f4b9bec2956..da045b200def 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -10,6 +10,7 @@
 #include <linux/export.h>
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
+#include <linux/rational.h>
 #include <linux/regmap.h>
 #include <linux/math64.h>
 #include <linux/slab.h>
@@ -1124,3 +1125,79 @@ int qcom_cc_register_rcg_dfs(struct regmap *regmap,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qcom_cc_register_rcg_dfs);
+
+static int clk_rcg2_dp_set_rate(struct clk_hw *hw, unsigned long rate,
+			unsigned long parent_rate)
+{
+	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
+	struct freq_tbl f = { 0 };
+	u32 mask = BIT(rcg->hid_width) - 1;
+	u32 hid_div, cfg;
+	int i, num_parents = clk_hw_get_num_parents(hw);
+	unsigned long num, den;
+
+	rational_best_approximation(parent_rate, rate,
+			GENMASK(rcg->mnd_width - 1, 0),
+			GENMASK(rcg->mnd_width - 1, 0), &den, &num);
+
+	if (!num || !den)
+		return -EINVAL;
+
+	regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG, &cfg);
+	hid_div = cfg;
+	cfg &= CFG_SRC_SEL_MASK;
+	cfg >>= CFG_SRC_SEL_SHIFT;
+
+	for (i = 0; i < num_parents; i++) {
+		if (cfg == rcg->parent_map[i].cfg) {
+			f.src = rcg->parent_map[i].src;
+			break;
+		}
+	}
+
+	f.pre_div = hid_div;
+	f.pre_div >>= CFG_SRC_DIV_SHIFT;
+	f.pre_div &= mask;
+
+	if (num != den) {
+		f.m = num;
+		f.n = den;
+	} else {
+		f.m = 0;
+		f.n = 0;
+	}
+
+	return clk_rcg2_configure(rcg, &f);
+}
+
+static int clk_rcg2_dp_set_rate_and_parent(struct clk_hw *hw,
+		unsigned long rate, unsigned long parent_rate, u8 index)
+{
+	return clk_rcg2_dp_set_rate(hw, rate, parent_rate);
+}
+
+static int clk_rcg2_dp_determine_rate(struct clk_hw *hw,
+				struct clk_rate_request *req)
+{
+	struct clk_rate_request parent_req = *req;
+	int ret;
+
+	ret = __clk_determine_rate(clk_hw_get_parent(hw), &parent_req);
+	if (ret)
+		return ret;
+
+	req->best_parent_rate = parent_req.rate;
+
+	return 0;
+}
+
+const struct clk_ops clk_dp_ops = {
+	.is_enabled = clk_rcg2_is_enabled,
+	.get_parent = clk_rcg2_get_parent,
+	.set_parent = clk_rcg2_set_parent,
+	.recalc_rate = clk_rcg2_recalc_rate,
+	.set_rate = clk_rcg2_dp_set_rate,
+	.set_rate_and_parent = clk_rcg2_dp_set_rate_and_parent,
+	.determine_rate = clk_rcg2_dp_determine_rate,
+};
+EXPORT_SYMBOL_GPL(clk_dp_ops);
diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
index 7ed313ad6e43..98a118c1e244 100644
--- a/drivers/clk/qcom/clk-rpmh.c
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -396,6 +396,7 @@ static struct clk_hw *sc7180_rpmh_clocks[] = {
 	[RPMH_RF_CLK1_A]	= &sdm845_rf_clk1_ao.hw,
 	[RPMH_RF_CLK2]		= &sdm845_rf_clk2.hw,
 	[RPMH_RF_CLK2_A]	= &sdm845_rf_clk2_ao.hw,
+	[RPMH_IPA_CLK]		= &sdm845_ipa.hw,
 };
 
 static const struct clk_rpmh_desc clk_rpmh_sc7180 = {
@@ -431,11 +432,16 @@ static int clk_rpmh_probe(struct platform_device *pdev)
 	hw_clks = desc->clks;
 
 	for (i = 0; i < desc->num_clks; i++) {
-		const char *name = hw_clks[i]->init->name;
+		const char *name;
 		u32 res_addr;
 		size_t aux_data_len;
 		const struct bcm_db *data;
 
+		if (!hw_clks[i])
+			continue;
+
+		name = hw_clks[i]->init->name;
+
 		rpmh_clk = to_clk_rpmh(hw_clks[i]);
 		res_addr = cmd_db_read_addr(rpmh_clk->res_name);
 		if (!res_addr) {
@@ -481,9 +487,9 @@ static int clk_rpmh_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id clk_rpmh_match_table[] = {
+	{ .compatible = "qcom,sc7180-rpmh-clk", .data = &clk_rpmh_sc7180},
 	{ .compatible = "qcom,sdm845-rpmh-clk", .data = &clk_rpmh_sdm845},
 	{ .compatible = "qcom,sm8150-rpmh-clk", .data = &clk_rpmh_sm8150},
-	{ .compatible = "qcom,sc7180-rpmh-clk", .data = &clk_rpmh_sc7180},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, clk_rpmh_match_table);
diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c
index 930fa4a4c52a..0bbfef9fa6de 100644
--- a/drivers/clk/qcom/clk-smd-rpm.c
+++ b/drivers/clk/qcom/clk-smd-rpm.c
@@ -485,6 +485,8 @@ static struct clk_smd_rpm *msm8974_clks[] = {
 	[RPM_SMD_MMSSNOC_AHB_CLK]	= &msm8974_mmssnoc_ahb_clk,
 	[RPM_SMD_MMSSNOC_AHB_A_CLK]	= &msm8974_mmssnoc_ahb_a_clk,
 	[RPM_SMD_BIMC_CLK]		= &msm8974_bimc_clk,
+	[RPM_SMD_GFX3D_CLK_SRC]		= &msm8974_gfx3d_clk_src,
+	[RPM_SMD_GFX3D_A_CLK_SRC]	= &msm8974_gfx3d_a_clk_src,
 	[RPM_SMD_BIMC_A_CLK]		= &msm8974_bimc_a_clk,
 	[RPM_SMD_OCMEMGX_CLK]		= &msm8974_ocmemgx_clk,
 	[RPM_SMD_OCMEMGX_A_CLK]		= &msm8974_ocmemgx_a_clk,
@@ -648,6 +650,7 @@ static const struct rpm_smd_clk_desc rpm_clk_qcs404 = {
 };
 
 /* msm8998 */
+DEFINE_CLK_SMD_RPM(msm8998, bimc_clk, bimc_a_clk, QCOM_SMD_RPM_MEM_CLK, 0);
 DEFINE_CLK_SMD_RPM(msm8998, pcnoc_clk, pcnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 0);
 DEFINE_CLK_SMD_RPM(msm8998, snoc_clk, snoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 1);
 DEFINE_CLK_SMD_RPM(msm8998, cnoc_clk, cnoc_a_clk, QCOM_SMD_RPM_BUS_CLK, 2);
@@ -671,6 +674,8 @@ DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk2_pin, rf_clk2_a_pin, 5);
 DEFINE_CLK_SMD_RPM_XO_BUFFER(msm8998, rf_clk3, rf_clk3_a, 6);
 DEFINE_CLK_SMD_RPM_XO_BUFFER_PINCTRL(msm8998, rf_clk3_pin, rf_clk3_a_pin, 6);
 static struct clk_smd_rpm *msm8998_clks[] = {
+	[RPM_SMD_BIMC_CLK] = &msm8998_bimc_clk,
+	[RPM_SMD_BIMC_A_CLK] = &msm8998_bimc_a_clk,
 	[RPM_SMD_PCNOC_CLK] = &msm8998_pcnoc_clk,
 	[RPM_SMD_PCNOC_A_CLK] = &msm8998_pcnoc_a_clk,
 	[RPM_SMD_SNOC_CLK] = &msm8998_snoc_clk,
diff --git a/drivers/clk/qcom/dispcc-sc7180.c b/drivers/clk/qcom/dispcc-sc7180.c
new file mode 100644
index 000000000000..30c1e25d3edb
--- /dev/null
+++ b/drivers/clk/qcom/dispcc-sc7180.c
@@ -0,0 +1,776 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,dispcc-sc7180.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap-divider.h"
+#include "common.h"
+#include "gdsc.h"
+
+enum {
+	P_BI_TCXO,
+	P_CHIP_SLEEP_CLK,
+	P_CORE_BI_PLL_TEST_SE,
+	P_DISP_CC_PLL0_OUT_EVEN,
+	P_DISP_CC_PLL0_OUT_MAIN,
+	P_DP_PHY_PLL_LINK_CLK,
+	P_DP_PHY_PLL_VCO_DIV_CLK,
+	P_DSI0_PHY_PLL_OUT_BYTECLK,
+	P_DSI0_PHY_PLL_OUT_DSICLK,
+	P_GPLL0_OUT_MAIN,
+};
+
+static const struct pll_vco fabia_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static struct clk_alpha_pll disp_cc_pll0 = {
+	.offset = 0x0,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_pll0",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+static const struct clk_div_table post_div_table_disp_cc_pll0_out_even[] = {
+	{ 0x0, 1 },
+	{ }
+};
+
+static struct clk_alpha_pll_postdiv disp_cc_pll0_out_even = {
+	.offset = 0x0,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_disp_cc_pll0_out_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_disp_cc_pll0_out_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_pll0_out_even",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &disp_cc_pll0.clkr.hw,
+		},
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static const struct parent_map disp_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data disp_cc_parent_data_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map disp_cc_parent_map_1[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DP_PHY_PLL_LINK_CLK, 1 },
+	{ P_DP_PHY_PLL_VCO_DIV_CLK, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data disp_cc_parent_data_1[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .fw_name = "dp_phy_pll_link_clk", .name = "dp_phy_pll_link_clk" },
+	{ .fw_name = "dp_phy_pll_vco_div_clk",
+				.name = "dp_phy_pll_vco_div_clk"},
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map disp_cc_parent_map_2[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DSI0_PHY_PLL_OUT_BYTECLK, 1 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data disp_cc_parent_data_2[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .fw_name = "dsi0_phy_pll_out_byteclk",
+				.name = "dsi0_phy_pll_out_byteclk" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map disp_cc_parent_map_3[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DISP_CC_PLL0_OUT_MAIN, 1 },
+	{ P_GPLL0_OUT_MAIN, 4 },
+	{ P_DISP_CC_PLL0_OUT_EVEN, 5 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data disp_cc_parent_data_3[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &disp_cc_pll0.clkr.hw },
+	{ .fw_name = "gcc_disp_gpll0_clk_src" },
+	{ .hw = &disp_cc_pll0_out_even.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map disp_cc_parent_map_4[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPLL0_OUT_MAIN, 4 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data disp_cc_parent_data_4[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .fw_name = "gcc_disp_gpll0_clk_src" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map disp_cc_parent_map_5[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DSI0_PHY_PLL_OUT_DSICLK, 1 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data disp_cc_parent_data_5[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .fw_name = "dsi0_phy_pll_out_dsiclk",
+				.name = "dsi0_phy_pll_out_dsiclk" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_ahb_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(37500000, P_GPLL0_OUT_MAIN, 16, 0, 0),
+	F(75000000, P_GPLL0_OUT_MAIN, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_ahb_clk_src = {
+	.cmd_rcgr = 0x22bc,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_4,
+	.freq_tbl = ftbl_disp_cc_mdss_ahb_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_ahb_clk_src",
+		.parent_data = disp_cc_parent_data_4,
+		.num_parents = 3,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_byte0_clk_src = {
+	.cmd_rcgr = 0x2110,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_2,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_byte0_clk_src",
+		.parent_data = disp_cc_parent_data_2,
+		.num_parents = 3,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_dp_aux_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_aux_clk_src = {
+	.cmd_rcgr = 0x21dc,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.freq_tbl = ftbl_disp_cc_mdss_dp_aux_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_aux_clk_src",
+		.parent_data = disp_cc_parent_data_0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_crypto_clk_src = {
+	.cmd_rcgr = 0x2194,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_crypto_clk_src",
+		.parent_data = disp_cc_parent_data_1,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_link_clk_src = {
+	.cmd_rcgr = 0x2178,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_link_clk_src",
+		.parent_data = disp_cc_parent_data_1,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_pixel_clk_src = {
+	.cmd_rcgr = 0x21ac,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_pixel_clk_src",
+		.parent_data = disp_cc_parent_data_1,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_dp_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_esc0_clk_src = {
+	.cmd_rcgr = 0x2148,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_2,
+	.freq_tbl = ftbl_disp_cc_mdss_dp_aux_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_esc0_clk_src",
+		.parent_data = disp_cc_parent_data_2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_mdp_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0),
+	F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0),
+	F(345000000, P_DISP_CC_PLL0_OUT_MAIN, 4, 0, 0),
+	F(460000000, P_DISP_CC_PLL0_OUT_MAIN, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_mdp_clk_src = {
+	.cmd_rcgr = 0x20c8,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_3,
+	.freq_tbl = ftbl_disp_cc_mdss_mdp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_mdp_clk_src",
+		.parent_data = disp_cc_parent_data_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_pclk0_clk_src = {
+	.cmd_rcgr = 0x2098,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_5,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_pclk0_clk_src",
+		.parent_data = disp_cc_parent_data_5,
+		.num_parents = 3,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_pixel_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_rot_clk_src = {
+	.cmd_rcgr = 0x20e0,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_3,
+	.freq_tbl = ftbl_disp_cc_mdss_mdp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_rot_clk_src",
+		.parent_data = disp_cc_parent_data_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_vsync_clk_src = {
+	.cmd_rcgr = 0x20f8,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.freq_tbl = ftbl_disp_cc_mdss_dp_aux_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_vsync_clk_src",
+		.parent_data = disp_cc_parent_data_0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_branch disp_cc_mdss_ahb_clk = {
+	.halt_reg = 0x2080,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2080,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_byte0_clk = {
+	.halt_reg = 0x2028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_byte0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = {
+	.reg = 0x2128,
+	.shift = 0,
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "disp_cc_mdss_byte0_div_clk_src",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &disp_cc_mdss_byte0_clk_src.clkr.hw
+		},
+		.num_parents = 1,
+		.ops = &clk_regmap_div_ops,
+	},
+};
+
+static struct clk_regmap_div disp_cc_mdss_dp_link_div_clk_src = {
+	.reg = 0x2190,
+	.shift = 0,
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data) {
+		.name = "disp_cc_mdss_dp_link_div_clk_src",
+		.parent_data = &(const struct clk_parent_data){
+			.hw = &disp_cc_mdss_dp_link_clk_src.clkr.hw
+		},
+		.num_parents = 1,
+		.ops = &clk_regmap_div_ops,
+	},
+};
+
+static struct clk_branch disp_cc_mdss_byte0_intf_clk = {
+	.halt_reg = 0x202c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x202c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_intf_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_byte0_div_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_aux_clk = {
+	.halt_reg = 0x2054,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_aux_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_dp_aux_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_crypto_clk = {
+	.halt_reg = 0x2048,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_crypto_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_dp_crypto_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_link_clk = {
+	.halt_reg = 0x2040,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_link_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_dp_link_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_link_intf_clk = {
+	.halt_reg = 0x2044,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_link_intf_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_dp_link_div_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_pixel_clk = {
+	.halt_reg = 0x204c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x204c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_pixel_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_dp_pixel_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_esc0_clk = {
+	.halt_reg = 0x2038,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_esc0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_esc0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_mdp_clk = {
+	.halt_reg = 0x200c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x200c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_mdp_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_mdp_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_mdp_lut_clk = {
+	.halt_reg = 0x201c,
+	.halt_check = BRANCH_VOTED,
+	.clkr = {
+		.enable_reg = 0x201c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_mdp_lut_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_mdp_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_non_gdsc_ahb_clk = {
+	.halt_reg = 0x4004,
+	.halt_check = BRANCH_VOTED,
+	.clkr = {
+		.enable_reg = 0x4004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_non_gdsc_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_pclk0_clk = {
+	.halt_reg = 0x2004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_pclk0_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_pclk0_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rot_clk = {
+	.halt_reg = 0x2014,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rot_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_rot_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rscc_ahb_clk = {
+	.halt_reg = 0x400c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x400c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rscc_ahb_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_ahb_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rscc_vsync_clk = {
+	.halt_reg = 0x4008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x4008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rscc_vsync_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_vsync_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_vsync_clk = {
+	.halt_reg = 0x2024,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_vsync_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &disp_cc_mdss_vsync_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc mdss_gdsc = {
+	.gdscr = 0x3000,
+	.pd = {
+		.name = "mdss_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = HW_CTRL,
+};
+
+static struct gdsc *disp_cc_sc7180_gdscs[] = {
+	[MDSS_GDSC] = &mdss_gdsc,
+};
+
+static struct clk_regmap *disp_cc_sc7180_clocks[] = {
+	[DISP_CC_MDSS_AHB_CLK] = &disp_cc_mdss_ahb_clk.clkr,
+	[DISP_CC_MDSS_AHB_CLK_SRC] = &disp_cc_mdss_ahb_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE0_CLK] = &disp_cc_mdss_byte0_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_CLK_SRC] = &disp_cc_mdss_byte0_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE0_DIV_CLK_SRC] = &disp_cc_mdss_byte0_div_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE0_INTF_CLK] = &disp_cc_mdss_byte0_intf_clk.clkr,
+	[DISP_CC_MDSS_DP_AUX_CLK] = &disp_cc_mdss_dp_aux_clk.clkr,
+	[DISP_CC_MDSS_DP_AUX_CLK_SRC] = &disp_cc_mdss_dp_aux_clk_src.clkr,
+	[DISP_CC_MDSS_DP_CRYPTO_CLK] = &disp_cc_mdss_dp_crypto_clk.clkr,
+	[DISP_CC_MDSS_DP_CRYPTO_CLK_SRC] = &disp_cc_mdss_dp_crypto_clk_src.clkr,
+	[DISP_CC_MDSS_DP_LINK_CLK] = &disp_cc_mdss_dp_link_clk.clkr,
+	[DISP_CC_MDSS_DP_LINK_CLK_SRC] = &disp_cc_mdss_dp_link_clk_src.clkr,
+	[DISP_CC_MDSS_DP_LINK_DIV_CLK_SRC] =
+				&disp_cc_mdss_dp_link_div_clk_src.clkr,
+	[DISP_CC_MDSS_DP_LINK_INTF_CLK] = &disp_cc_mdss_dp_link_intf_clk.clkr,
+	[DISP_CC_MDSS_DP_PIXEL_CLK] = &disp_cc_mdss_dp_pixel_clk.clkr,
+	[DISP_CC_MDSS_DP_PIXEL_CLK_SRC] = &disp_cc_mdss_dp_pixel_clk_src.clkr,
+	[DISP_CC_MDSS_ESC0_CLK] = &disp_cc_mdss_esc0_clk.clkr,
+	[DISP_CC_MDSS_ESC0_CLK_SRC] = &disp_cc_mdss_esc0_clk_src.clkr,
+	[DISP_CC_MDSS_MDP_CLK] = &disp_cc_mdss_mdp_clk.clkr,
+	[DISP_CC_MDSS_MDP_CLK_SRC] = &disp_cc_mdss_mdp_clk_src.clkr,
+	[DISP_CC_MDSS_MDP_LUT_CLK] = &disp_cc_mdss_mdp_lut_clk.clkr,
+	[DISP_CC_MDSS_NON_GDSC_AHB_CLK] = &disp_cc_mdss_non_gdsc_ahb_clk.clkr,
+	[DISP_CC_MDSS_PCLK0_CLK] = &disp_cc_mdss_pclk0_clk.clkr,
+	[DISP_CC_MDSS_PCLK0_CLK_SRC] = &disp_cc_mdss_pclk0_clk_src.clkr,
+	[DISP_CC_MDSS_ROT_CLK] = &disp_cc_mdss_rot_clk.clkr,
+	[DISP_CC_MDSS_ROT_CLK_SRC] = &disp_cc_mdss_rot_clk_src.clkr,
+	[DISP_CC_MDSS_RSCC_AHB_CLK] = &disp_cc_mdss_rscc_ahb_clk.clkr,
+	[DISP_CC_MDSS_RSCC_VSYNC_CLK] = &disp_cc_mdss_rscc_vsync_clk.clkr,
+	[DISP_CC_MDSS_VSYNC_CLK] = &disp_cc_mdss_vsync_clk.clkr,
+	[DISP_CC_MDSS_VSYNC_CLK_SRC] = &disp_cc_mdss_vsync_clk_src.clkr,
+	[DISP_CC_PLL0] = &disp_cc_pll0.clkr,
+	[DISP_CC_PLL0_OUT_EVEN] = &disp_cc_pll0_out_even.clkr,
+};
+
+static const struct regmap_config disp_cc_sc7180_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = 0x10000,
+	.fast_io = true,
+};
+
+static const struct qcom_cc_desc disp_cc_sc7180_desc = {
+	.config = &disp_cc_sc7180_regmap_config,
+	.clks = disp_cc_sc7180_clocks,
+	.num_clks = ARRAY_SIZE(disp_cc_sc7180_clocks),
+	.gdscs = disp_cc_sc7180_gdscs,
+	.num_gdscs = ARRAY_SIZE(disp_cc_sc7180_gdscs),
+};
+
+static const struct of_device_id disp_cc_sc7180_match_table[] = {
+	{ .compatible = "qcom,sc7180-dispcc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, disp_cc_sc7180_match_table);
+
+static int disp_cc_sc7180_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	struct alpha_pll_config disp_cc_pll_config = {};
+
+	regmap = qcom_cc_map(pdev, &disp_cc_sc7180_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* 1380MHz configuration */
+	disp_cc_pll_config.l = 0x47;
+	disp_cc_pll_config.alpha = 0xe000;
+	disp_cc_pll_config.user_ctl_val = 0x00000001;
+	disp_cc_pll_config.user_ctl_hi_val = 0x00004805;
+
+	clk_fabia_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll_config);
+
+	return qcom_cc_really_probe(pdev, &disp_cc_sc7180_desc, regmap);
+}
+
+static struct platform_driver disp_cc_sc7180_driver = {
+	.probe = disp_cc_sc7180_probe,
+	.driver = {
+		.name = "sc7180-dispcc",
+		.of_match_table = disp_cc_sc7180_match_table,
+	},
+};
+
+static int __init disp_cc_sc7180_init(void)
+{
+	return platform_driver_register(&disp_cc_sc7180_driver);
+}
+subsys_initcall(disp_cc_sc7180_init);
+
+static void __exit disp_cc_sc7180_exit(void)
+{
+	platform_driver_unregister(&disp_cc_sc7180_driver);
+}
+module_exit(disp_cc_sc7180_exit);
+
+MODULE_DESCRIPTION("QTI DISP_CC SC7180 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c
index 0cc4909b5dbe..5c932cd17b14 100644
--- a/drivers/clk/qcom/dispcc-sdm845.c
+++ b/drivers/clk/qcom/dispcc-sdm845.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  */
 
 #include <linux/clk-provider.h>
@@ -29,6 +29,8 @@ enum {
 	P_DSI1_PHY_PLL_OUT_DSICLK,
 	P_GPLL0_OUT_MAIN,
 	P_GPLL0_OUT_MAIN_DIV,
+	P_DP_PHY_PLL_LINK_CLK,
+	P_DP_PHY_PLL_VCO_DIV_CLK,
 };
 
 static const struct parent_map disp_cc_parent_map_0[] = {
@@ -45,6 +47,20 @@ static const char * const disp_cc_parent_names_0[] = {
 	"core_bi_pll_test_se",
 };
 
+static const struct parent_map disp_cc_parent_map_1[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DP_PHY_PLL_LINK_CLK, 1 },
+	{ P_DP_PHY_PLL_VCO_DIV_CLK, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_1[] = {
+	"bi_tcxo",
+	"dp_link_clk_divsel_ten",
+	"dp_vco_divided_clk_src_mux",
+	"core_bi_pll_test_se",
+};
+
 static const struct parent_map disp_cc_parent_map_2[] = {
 	{ P_BI_TCXO, 0 },
 	{ P_CORE_BI_PLL_TEST_SE, 7 },
@@ -128,6 +144,81 @@ static struct clk_rcg2 disp_cc_mdss_byte1_clk_src = {
 	},
 };
 
+static const struct freq_tbl ftbl_disp_cc_mdss_dp_aux_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_aux_clk_src = {
+	.cmd_rcgr = 0x219c,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_2,
+	.freq_tbl = ftbl_disp_cc_mdss_dp_aux_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_aux_clk_src",
+		.parent_names = disp_cc_parent_names_2,
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_crypto_clk_src = {
+	.cmd_rcgr = 0x2154,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_crypto_clk_src",
+		.parent_names = disp_cc_parent_names_1,
+		.num_parents = 4,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_link_clk_src = {
+	.cmd_rcgr = 0x2138,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_link_clk_src",
+		.parent_names = disp_cc_parent_names_1,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_pixel1_clk_src = {
+	.cmd_rcgr = 0x2184,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_pixel1_clk_src",
+		.parent_names = disp_cc_parent_names_1,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_dp_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_dp_pixel_clk_src = {
+	.cmd_rcgr = 0x216c,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_1,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_dp_pixel_clk_src",
+		.parent_names = disp_cc_parent_names_1,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_dp_ops,
+	},
+};
+
 static const struct freq_tbl ftbl_disp_cc_mdss_esc0_clk_src[] = {
 	F(19200000, P_BI_TCXO, 1, 0, 0),
 	{ }
@@ -391,6 +482,114 @@ static struct clk_branch disp_cc_mdss_byte1_intf_clk = {
 	},
 };
 
+static struct clk_branch disp_cc_mdss_dp_aux_clk = {
+	.halt_reg = 0x2054,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_aux_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_dp_aux_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_crypto_clk = {
+	.halt_reg = 0x2048,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_crypto_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_dp_crypto_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_link_clk = {
+	.halt_reg = 0x2040,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_link_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_dp_link_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* reset state of disp_cc_mdss_dp_link_div_clk_src divider is 0x3 (div 4) */
+static struct clk_branch disp_cc_mdss_dp_link_intf_clk = {
+	.halt_reg = 0x2044,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_link_intf_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_dp_link_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_pixel1_clk = {
+	.halt_reg = 0x2050,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2050,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_pixel1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_dp_pixel1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_dp_pixel_clk = {
+	.halt_reg = 0x204c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x204c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_dp_pixel_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_dp_pixel_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch disp_cc_mdss_esc0_clk = {
 	.halt_reg = 0x2038,
 	.halt_check = BRANCH_HALT,
@@ -589,6 +788,19 @@ static struct clk_regmap *disp_cc_sdm845_clocks[] = {
 	[DISP_CC_MDSS_BYTE1_INTF_CLK] = &disp_cc_mdss_byte1_intf_clk.clkr,
 	[DISP_CC_MDSS_BYTE1_DIV_CLK_SRC] =
 					&disp_cc_mdss_byte1_div_clk_src.clkr,
+	[DISP_CC_MDSS_DP_AUX_CLK] = &disp_cc_mdss_dp_aux_clk.clkr,
+	[DISP_CC_MDSS_DP_AUX_CLK_SRC] = &disp_cc_mdss_dp_aux_clk_src.clkr,
+	[DISP_CC_MDSS_DP_CRYPTO_CLK] = &disp_cc_mdss_dp_crypto_clk.clkr,
+	[DISP_CC_MDSS_DP_CRYPTO_CLK_SRC] =
+					&disp_cc_mdss_dp_crypto_clk_src.clkr,
+	[DISP_CC_MDSS_DP_LINK_CLK] = &disp_cc_mdss_dp_link_clk.clkr,
+	[DISP_CC_MDSS_DP_LINK_CLK_SRC] = &disp_cc_mdss_dp_link_clk_src.clkr,
+	[DISP_CC_MDSS_DP_LINK_INTF_CLK] = &disp_cc_mdss_dp_link_intf_clk.clkr,
+	[DISP_CC_MDSS_DP_PIXEL1_CLK] = &disp_cc_mdss_dp_pixel1_clk.clkr,
+	[DISP_CC_MDSS_DP_PIXEL1_CLK_SRC] =
+					&disp_cc_mdss_dp_pixel1_clk_src.clkr,
+	[DISP_CC_MDSS_DP_PIXEL_CLK] = &disp_cc_mdss_dp_pixel_clk.clkr,
+	[DISP_CC_MDSS_DP_PIXEL_CLK_SRC] = &disp_cc_mdss_dp_pixel_clk_src.clkr,
 	[DISP_CC_MDSS_ESC0_CLK] = &disp_cc_mdss_esc0_clk.clkr,
 	[DISP_CC_MDSS_ESC0_CLK_SRC] = &disp_cc_mdss_esc0_clk_src.clkr,
 	[DISP_CC_MDSS_ESC1_CLK] = &disp_cc_mdss_esc1_clk.clkr,
diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c
new file mode 100644
index 000000000000..3f9c2f61a5d9
--- /dev/null
+++ b/drivers/clk/qcom/gcc-ipq6018.c
@@ -0,0 +1,4635 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+
+#include <linux/reset-controller.h>
+#include <dt-bindings/clock/qcom,gcc-ipq6018.h>
+#include <dt-bindings/reset/qcom,gcc-ipq6018.h>
+
+#include "common.h"
+#include "clk-regmap.h"
+#include "clk-pll.h"
+#include "clk-rcg.h"
+#include "clk-branch.h"
+#include "clk-alpha-pll.h"
+#include "clk-regmap-divider.h"
+#include "clk-regmap-mux.h"
+#include "reset.h"
+
+#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
+
+enum {
+	P_XO,
+	P_BIAS_PLL,
+	P_UNIPHY0_RX,
+	P_UNIPHY0_TX,
+	P_UNIPHY1_RX,
+	P_BIAS_PLL_NSS_NOC,
+	P_UNIPHY1_TX,
+	P_PCIE20_PHY0_PIPE,
+	P_USB3PHY_0_PIPE,
+	P_GPLL0,
+	P_GPLL0_DIV2,
+	P_GPLL2,
+	P_GPLL4,
+	P_GPLL6,
+	P_SLEEP_CLK,
+	P_UBI32_PLL,
+	P_NSS_CRYPTO_PLL,
+	P_PI_SLEEP,
+};
+
+static struct clk_alpha_pll gpll0_main = {
+	.offset = 0x21000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll0_main",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+		},
+	},
+};
+
+static struct clk_fixed_factor gpll0_out_main_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "gpll0_out_main_div2",
+		.parent_hws = (const struct clk_hw *[]){
+				&gpll0_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll0 = {
+	.offset = 0x21000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll0",
+		.parent_hws = (const struct clk_hw *[]){
+				&gpll0_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_gpll0_out_main_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw},
+	{ .hw = &gpll0_out_main_div2.hw},
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static struct clk_alpha_pll ubi32_pll_main = {
+	.offset = 0x25000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_HUAYRA],
+	.flags = SUPPORTS_DYNAMIC_UPDATE,
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(6),
+		.hw.init = &(struct clk_init_data){
+			.name = "ubi32_pll_main",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_huayra_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv ubi32_pll = {
+	.offset = 0x25000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_HUAYRA],
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ubi32_pll",
+		.parent_hws = (const struct clk_hw *[]){
+				&ubi32_pll_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll gpll6_main = {
+	.offset = 0x37000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_BRAMMO],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(7),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll6_main",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll6 = {
+	.offset = 0x37000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_BRAMMO],
+	.width = 2,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll6",
+		.parent_hws = (const struct clk_hw *[]){
+				&gpll6_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll gpll4_main = {
+	.offset = 0x24000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(5),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll4_main",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll4 = {
+	.offset = 0x24000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll4",
+		.parent_hws = (const struct clk_hw *[]){
+				&gpll4_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_pcnoc_bfdcd_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0, 16, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 pcnoc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x27000,
+	.freq_tbl = ftbl_pcnoc_bfdcd_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcnoc_bfdcd_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_alpha_pll gpll2_main = {
+	.offset = 0x4a000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpll2_main",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv gpll2 = {
+	.offset = 0x4a000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpll2",
+		.parent_hws = (const struct clk_hw *[]){
+				&gpll2_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_alpha_pll nss_crypto_pll_main = {
+	.offset = 0x22000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.clkr = {
+		.enable_reg = 0x0b000,
+		.enable_mask = BIT(4),
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_crypto_pll_main",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv nss_crypto_pll = {
+	.offset = 0x22000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
+	.width = 4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_crypto_pll",
+		.parent_hws = (const struct clk_hw *[]){
+				&nss_crypto_pll_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_ro_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_qdss_tsctr_clk_src[] = {
+	F(160000000, P_GPLL0_DIV2, 2.5, 0, 0),
+	F(320000000, P_GPLL0, 2.5, 0, 0),
+	F(600000000, P_GPLL4, 2, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll4_gpll0_gpll6_gpll0_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll4.clkr.hw },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map gcc_xo_gpll4_gpll0_gpll6_gpll0_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL4, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL6, 3 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static struct clk_rcg2 qdss_tsctr_clk_src = {
+	.cmd_rcgr = 0x29064,
+	.freq_tbl = ftbl_qdss_tsctr_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll4_gpll0_gpll6_gpll0_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "qdss_tsctr_clk_src",
+		.parent_data = gcc_xo_gpll4_gpll0_gpll6_gpll0_div2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_fixed_factor qdss_dap_sync_clk_src = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "qdss_dap_sync_clk_src",
+		.parent_hws = (const struct clk_hw *[]){
+				&qdss_tsctr_clk_src.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_qdss_at_clk_src[] = {
+	F(66670000, P_GPLL0_DIV2, 6, 0, 0),
+	F(240000000, P_GPLL4, 5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 qdss_at_clk_src = {
+	.cmd_rcgr = 0x2900c,
+	.freq_tbl = ftbl_qdss_at_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll4_gpll0_gpll6_gpll0_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "qdss_at_clk_src",
+		.parent_data = gcc_xo_gpll4_gpll0_gpll6_gpll0_div2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_fixed_factor qdss_tsctr_div2_clk_src = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "qdss_tsctr_div2_clk_src",
+		.parent_hws = (const struct clk_hw *[]){
+				&qdss_tsctr_clk_src.clkr.hw },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_fixed_factor_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_ppe_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(300000000, P_BIAS_PLL, 1, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_bias_gpll0_gpll4_nss_ubi32[] = {
+	{ .fw_name = "xo" },
+	{ .fw_name = "bias_pll_cc_clk" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll4.clkr.hw },
+	{ .hw = &nss_crypto_pll.clkr.hw },
+	{ .hw = &ubi32_pll.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_bias_gpll0_gpll4_nss_ubi32_map[] = {
+	{ P_XO, 0 },
+	{ P_BIAS_PLL, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL4, 3 },
+	{ P_NSS_CRYPTO_PLL, 4 },
+	{ P_UBI32_PLL, 5 },
+};
+
+static struct clk_rcg2 nss_ppe_clk_src = {
+	.cmd_rcgr = 0x68080,
+	.freq_tbl = ftbl_nss_ppe_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_bias_gpll0_gpll4_nss_ubi32_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ppe_clk_src",
+		.parent_data = gcc_xo_bias_gpll0_gpll4_nss_ubi32,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_xo_clk_src = {
+	.halt_reg = 0x30018,
+	.clkr = {
+		.enable_reg = 0x30018,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_xo_clk_src",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_ce_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll0[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+};
+
+static struct clk_rcg2 nss_ce_clk_src = {
+	.cmd_rcgr = 0x68098,
+	.freq_tbl = ftbl_nss_ce_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ce_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_sleep_clk_src = {
+	.halt_reg = 0x30000,
+	.clkr = {
+		.enable_reg = 0x30000,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sleep_clk_src",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "sleep_clk",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_snoc_nssnoc_bfdcd_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0_DIV2, 8, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(133333333, P_GPLL0, 6, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	F(266666667, P_GPLL0, 3, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data
+			gcc_xo_gpll0_gpll6_gpll0_out_main_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll6_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_GPLL0_DIV2, 3 },
+};
+
+static struct clk_rcg2 snoc_nssnoc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x76054,
+	.freq_tbl = ftbl_snoc_nssnoc_bfdcd_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "snoc_nssnoc_bfdcd_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_apss_ahb_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_GPLL0_DIV2, 16, 0, 0),
+	F(50000000, P_GPLL0, 16, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 apss_ahb_clk_src = {
+	.cmd_rcgr = 0x46000,
+	.freq_tbl = ftbl_apss_ahb_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "apss_ahb_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port5_rx_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY1_RX, 12.5, 0, 0),
+	F(25000000, P_UNIPHY0_RX, 5, 0, 0),
+	F(78125000, P_UNIPHY1_RX, 4, 0, 0),
+	F(125000000, P_UNIPHY1_RX, 2.5, 0, 0),
+	F(125000000, P_UNIPHY0_RX, 1, 0, 0),
+	F(156250000, P_UNIPHY1_RX, 2, 0, 0),
+	F(312500000, P_UNIPHY1_RX, 1, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data
+gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias[] = {
+	{ .fw_name = "xo" },
+	{ .fw_name = "uniphy0_gcc_rx_clk" },
+	{ .fw_name = "uniphy0_gcc_tx_clk" },
+	{ .fw_name = "uniphy1_gcc_rx_clk" },
+	{ .fw_name = "uniphy1_gcc_tx_clk" },
+	{ .hw = &ubi32_pll.clkr.hw },
+	{ .fw_name = "bias_pll_cc_clk" },
+};
+
+static const struct parent_map
+gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_RX, 1 },
+	{ P_UNIPHY0_TX, 2 },
+	{ P_UNIPHY1_RX, 3 },
+	{ P_UNIPHY1_TX, 4 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static struct clk_rcg2 nss_port5_rx_clk_src = {
+	.cmd_rcgr = 0x68060,
+	.freq_tbl = ftbl_nss_port5_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port5_rx_clk_src",
+		.parent_data = gcc_xo_uniphy0_rx_tx_uniphy1_rx_tx_ubi32_bias,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port5_tx_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY1_TX, 12.5, 0, 0),
+	F(25000000, P_UNIPHY0_TX, 5, 0, 0),
+	F(78125000, P_UNIPHY1_TX, 4, 0, 0),
+	F(125000000, P_UNIPHY1_TX, 2.5, 0, 0),
+	F(125000000, P_UNIPHY0_TX, 1, 0, 0),
+	F(156250000, P_UNIPHY1_TX, 2, 0, 0),
+	F(312500000, P_UNIPHY1_TX, 1, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data
+gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias[] = {
+	{ .fw_name = "xo" },
+	{ .fw_name = "uniphy0_gcc_tx_clk" },
+	{ .fw_name = "uniphy0_gcc_rx_clk" },
+	{ .fw_name = "uniphy1_gcc_tx_clk" },
+	{ .fw_name = "uniphy1_gcc_rx_clk" },
+	{ .hw = &ubi32_pll.clkr.hw },
+	{ .fw_name = "bias_pll_cc_clk" },
+};
+
+static const struct parent_map
+gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_TX, 1 },
+	{ P_UNIPHY0_RX, 2 },
+	{ P_UNIPHY1_TX, 3 },
+	{ P_UNIPHY1_RX, 4 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static struct clk_rcg2 nss_port5_tx_clk_src = {
+	.cmd_rcgr = 0x68068,
+	.freq_tbl = ftbl_nss_port5_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port5_tx_clk_src",
+		.parent_data = gcc_xo_uniphy0_tx_rx_uniphy1_tx_rx_ubi32_bias,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_pcie_axi_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	F(240000000, P_GPLL4, 5, 0, 0),
+	{ }
+};
+
+static const struct freq_tbl ftbl_pcie_rchng_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_gpll4[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll4.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll4_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL4, 2 },
+};
+
+static struct clk_rcg2 pcie0_axi_clk_src = {
+	.cmd_rcgr = 0x75054,
+	.freq_tbl = ftbl_pcie_axi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll4_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie0_axi_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll4,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_usb0_master_clk_src[] = {
+	F(80000000, P_GPLL0_DIV2, 5, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(133330000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_out_main_div2_gpll0[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0_out_main_div2.hw },
+	{ .hw = &gpll0.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_out_main_div2_gpll0_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0_DIV2, 2 },
+	{ P_GPLL0, 1 },
+};
+
+static struct clk_rcg2 usb0_master_clk_src = {
+	.cmd_rcgr = 0x3e00c,
+	.freq_tbl = ftbl_usb0_master_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_out_main_div2_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb0_master_clk_src",
+		.parent_data = gcc_xo_gpll0_out_main_div2_gpll0,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div apss_ahb_postdiv_clk_src = {
+	.reg = 0x46018,
+	.shift = 4,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "apss_ahb_postdiv_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&apss_ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+		},
+	},
+};
+
+static struct clk_fixed_factor gcc_xo_div4_clk_src = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "gcc_xo_div4_clk_src",
+		.parent_hws = (const struct clk_hw *[]){
+				&gcc_xo_clk_src.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port1_rx_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY0_RX, 5, 0, 0),
+	F(125000000, P_UNIPHY0_RX, 1, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_uniphy0_rx_tx_ubi32_bias[] = {
+	{ .fw_name = "xo" },
+	{ .fw_name = "uniphy0_gcc_rx_clk" },
+	{ .fw_name = "uniphy0_gcc_tx_clk" },
+	{ .hw = &ubi32_pll.clkr.hw },
+	{ .fw_name = "bias_pll_cc_clk" },
+};
+
+static const struct parent_map gcc_xo_uniphy0_rx_tx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_RX, 1 },
+	{ P_UNIPHY0_TX, 2 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static struct clk_rcg2 nss_port1_rx_clk_src = {
+	.cmd_rcgr = 0x68020,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port1_rx_clk_src",
+		.parent_data = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_port1_tx_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_UNIPHY0_TX, 5, 0, 0),
+	F(125000000, P_UNIPHY0_TX, 1, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_uniphy0_tx_rx_ubi32_bias[] = {
+	{ .fw_name = "xo" },
+	{ .fw_name = "uniphy0_gcc_tx_clk" },
+	{ .fw_name = "uniphy0_gcc_rx_clk" },
+	{ .hw = &ubi32_pll.clkr.hw },
+	{ .fw_name = "bias_pll_cc_clk" },
+};
+
+static const struct parent_map gcc_xo_uniphy0_tx_rx_ubi32_bias_map[] = {
+	{ P_XO, 0 },
+	{ P_UNIPHY0_TX, 1 },
+	{ P_UNIPHY0_RX, 2 },
+	{ P_UBI32_PLL, 5 },
+	{ P_BIAS_PLL, 6 },
+};
+
+static struct clk_rcg2 nss_port1_tx_clk_src = {
+	.cmd_rcgr = 0x68028,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port1_tx_clk_src",
+		.parent_data = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 nss_port2_rx_clk_src = {
+	.cmd_rcgr = 0x68030,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port2_rx_clk_src",
+		.parent_data = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 nss_port2_tx_clk_src = {
+	.cmd_rcgr = 0x68038,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port2_tx_clk_src",
+		.parent_data = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 nss_port3_rx_clk_src = {
+	.cmd_rcgr = 0x68040,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port3_rx_clk_src",
+		.parent_data = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 nss_port3_tx_clk_src = {
+	.cmd_rcgr = 0x68048,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port3_tx_clk_src",
+		.parent_data = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 nss_port4_rx_clk_src = {
+	.cmd_rcgr = 0x68050,
+	.freq_tbl = ftbl_nss_port1_rx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_rx_tx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port4_rx_clk_src",
+		.parent_data = gcc_xo_uniphy0_rx_tx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 nss_port4_tx_clk_src = {
+	.cmd_rcgr = 0x68058,
+	.freq_tbl = ftbl_nss_port1_tx_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_uniphy0_tx_rx_ubi32_bias_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_port4_tx_clk_src",
+		.parent_data = gcc_xo_uniphy0_tx_rx_ubi32_bias,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port5_rx_div_clk_src = {
+	.reg = 0x68440,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port5_rx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_rx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port5_tx_div_clk_src = {
+	.reg = 0x68444,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port5_tx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_tx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_apss_axi_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(100000000, P_GPLL0_DIV2, 4, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	F(308570000, P_GPLL6, 3.5, 0, 0),
+	F(400000000, P_GPLL0, 2, 0, 0),
+	F(533000000, P_GPLL0, 1.5, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_gpll6_ubi32_gpll0_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+	{ .hw = &ubi32_pll.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map
+gcc_xo_gpll0_gpll6_ubi32_gpll0_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_UBI32_PLL, 3 },
+	{ P_GPLL0_DIV2, 6 },
+};
+
+static struct clk_rcg2 apss_axi_clk_src = {
+	.cmd_rcgr = 0x38048,
+	.freq_tbl = ftbl_apss_axi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_ubi32_gpll0_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "apss_axi_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_ubi32_gpll0_div2,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_nss_crypto_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(300000000, P_NSS_CRYPTO_PLL, 2, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_nss_crypto_pll_gpll0[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &nss_crypto_pll.clkr.hw },
+	{ .hw = &gpll0.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_nss_crypto_pll_gpll0_map[] = {
+	{ P_XO, 0 },
+	{ P_NSS_CRYPTO_PLL, 1 },
+	{ P_GPLL0, 2 },
+};
+
+static struct clk_rcg2 nss_crypto_clk_src = {
+	.cmd_rcgr = 0x68144,
+	.freq_tbl = ftbl_nss_crypto_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_nss_crypto_pll_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_crypto_clk_src",
+		.parent_data = gcc_xo_nss_crypto_pll_gpll0,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_regmap_div nss_port1_rx_div_clk_src = {
+	.reg = 0x68400,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port1_rx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+				&nss_port1_rx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port1_tx_div_clk_src = {
+	.reg = 0x68404,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port1_tx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port1_tx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port2_rx_div_clk_src = {
+	.reg = 0x68410,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port2_rx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port2_rx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port2_tx_div_clk_src = {
+	.reg = 0x68414,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port2_tx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port2_tx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port3_rx_div_clk_src = {
+	.reg = 0x68420,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port3_rx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port3_rx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port3_tx_div_clk_src = {
+	.reg = 0x68424,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port3_tx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port3_tx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port4_rx_div_clk_src = {
+	.reg = 0x68430,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port4_rx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port4_rx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_regmap_div nss_port4_tx_div_clk_src = {
+	.reg = 0x68434,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_port4_tx_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port4_tx_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_nss_ubi_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(149760000, P_UBI32_PLL, 10, 0, 0),
+	F(187200000, P_UBI32_PLL, 8, 0, 0),
+	F(249600000, P_UBI32_PLL, 6, 0, 0),
+	F(374400000, P_UBI32_PLL, 4, 0, 0),
+	F(748800000, P_UBI32_PLL, 2, 0, 0),
+	F(1497600000, P_UBI32_PLL, 1, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data
+			gcc_xo_ubi32_pll_gpll0_gpll2_gpll4_gpll6[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &ubi32_pll.clkr.hw },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll2.clkr.hw },
+	{ .hw = &gpll4.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_ubi32_gpll0_gpll2_gpll4_gpll6_map[] = {
+	{ P_XO, 0 },
+	{ P_UBI32_PLL, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL2, 3 },
+	{ P_GPLL4, 4 },
+	{ P_GPLL6, 5 },
+};
+
+static struct clk_rcg2 nss_ubi0_clk_src = {
+	.cmd_rcgr = 0x68104,
+	.freq_tbl = ftbl_nss_ubi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_ubi32_gpll0_gpll2_gpll4_gpll6_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "nss_ubi0_clk_src",
+		.parent_data = gcc_xo_ubi32_pll_gpll0_gpll2_gpll4_gpll6,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_adss_pwm_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 adss_pwm_clk_src = {
+	.cmd_rcgr = 0x1c008,
+	.freq_tbl = ftbl_adss_pwm_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "adss_pwm_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_blsp1_qup_i2c_apps_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_GPLL0_DIV2, 16, 0, 0),
+	F(50000000, P_GPLL0, 16, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 blsp1_qup1_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x0200c,
+	.freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup1_i2c_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_blsp1_qup_spi_apps_clk_src[] = {
+	F(960000, P_XO, 10, 2, 5),
+	F(4800000, P_XO, 5, 0, 0),
+	F(9600000, P_XO, 2, 4, 5),
+	F(12500000, P_GPLL0_DIV2, 16, 1, 2),
+	F(16000000, P_GPLL0, 10, 1, 5),
+	F(24000000, P_XO, 1, 0, 0),
+	F(25000000, P_GPLL0, 16, 1, 2),
+	F(50000000, P_GPLL0, 16, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 blsp1_qup1_spi_apps_clk_src = {
+	.cmd_rcgr = 0x02024,
+	.freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup1_spi_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup2_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x03000,
+	.freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup2_i2c_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup2_spi_apps_clk_src = {
+	.cmd_rcgr = 0x03014,
+	.freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup2_spi_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup3_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x04000,
+	.freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup3_i2c_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup3_spi_apps_clk_src = {
+	.cmd_rcgr = 0x04014,
+	.freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup3_spi_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup4_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x05000,
+	.freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup4_i2c_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup4_spi_apps_clk_src = {
+	.cmd_rcgr = 0x05014,
+	.freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup4_spi_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup5_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x06000,
+	.freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup5_i2c_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup5_spi_apps_clk_src = {
+	.cmd_rcgr = 0x06014,
+	.freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup5_spi_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup6_i2c_apps_clk_src = {
+	.cmd_rcgr = 0x07000,
+	.freq_tbl = ftbl_blsp1_qup_i2c_apps_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup6_i2c_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_qup6_spi_apps_clk_src = {
+	.cmd_rcgr = 0x07014,
+	.freq_tbl = ftbl_blsp1_qup_spi_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_qup6_spi_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_blsp1_uart_apps_clk_src[] = {
+	F(3686400, P_GPLL0_DIV2, 1, 144, 15625),
+	F(7372800, P_GPLL0_DIV2, 1, 288, 15625),
+	F(14745600, P_GPLL0_DIV2, 1, 576, 15625),
+	F(16000000, P_GPLL0_DIV2, 5, 1, 5),
+	F(24000000, P_XO, 1, 0, 0),
+	F(24000000, P_GPLL0, 1, 3, 100),
+	F(25000000, P_GPLL0, 16, 1, 2),
+	F(32000000, P_GPLL0, 1, 1, 25),
+	F(40000000, P_GPLL0, 1, 1, 20),
+	F(46400000, P_GPLL0, 1, 29, 500),
+	F(48000000, P_GPLL0, 1, 3, 50),
+	F(51200000, P_GPLL0, 1, 8, 125),
+	F(56000000, P_GPLL0, 1, 7, 100),
+	F(58982400, P_GPLL0, 1, 1152, 15625),
+	F(60000000, P_GPLL0, 1, 3, 40),
+	F(64000000, P_GPLL0, 12.5, 1, 1),
+	{ }
+};
+
+static struct clk_rcg2 blsp1_uart1_apps_clk_src = {
+	.cmd_rcgr = 0x02044,
+	.freq_tbl = ftbl_blsp1_uart_apps_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart1_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart2_apps_clk_src = {
+	.cmd_rcgr = 0x03034,
+	.freq_tbl = ftbl_blsp1_uart_apps_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart2_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart3_apps_clk_src = {
+	.cmd_rcgr = 0x04034,
+	.freq_tbl = ftbl_blsp1_uart_apps_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart3_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart4_apps_clk_src = {
+	.cmd_rcgr = 0x05034,
+	.freq_tbl = ftbl_blsp1_uart_apps_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart4_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart5_apps_clk_src = {
+	.cmd_rcgr = 0x06034,
+	.freq_tbl = ftbl_blsp1_uart_apps_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart5_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 blsp1_uart6_apps_clk_src = {
+	.cmd_rcgr = 0x07034,
+	.freq_tbl = ftbl_blsp1_uart_apps_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "blsp1_uart6_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_crypto_clk_src[] = {
+	F(40000000, P_GPLL0_DIV2, 10, 0, 0),
+	F(80000000, P_GPLL0, 10, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 crypto_clk_src = {
+	.cmd_rcgr = 0x16004,
+	.freq_tbl = ftbl_crypto_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "crypto_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_gp_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0_DIV2, 8, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	F(266666666, P_GPLL0, 3, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_sleep_clk[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+	{ .fw_name = "sleep_clk" },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_GPLL0_DIV2, 4 },
+	{ P_SLEEP_CLK, 6 },
+};
+
+static struct clk_rcg2 gp1_clk_src = {
+	.cmd_rcgr = 0x08004,
+	.freq_tbl = ftbl_gp_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp1_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_gpll0_sleep_clk,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gp2_clk_src = {
+	.cmd_rcgr = 0x09004,
+	.freq_tbl = ftbl_gp_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp2_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_gpll0_sleep_clk,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 gp3_clk_src = {
+	.cmd_rcgr = 0x0a004,
+	.freq_tbl = ftbl_gp_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gp3_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_gpll0_sleep_clk,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_fixed_factor nss_ppe_cdiv_clk_src = {
+	.mult = 1,
+	.div = 4,
+	.hw.init = &(struct clk_init_data){
+		.name = "nss_ppe_cdiv_clk_src",
+		.parent_hws = (const struct clk_hw *[]){
+				&nss_ppe_clk_src.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap_div nss_ubi0_div_clk_src = {
+	.reg = 0x68118,
+	.shift = 0,
+	.width = 4,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "nss_ubi0_div_clk_src",
+			.parent_hws = (const struct clk_hw *[]){
+				&nss_ubi0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ro_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_pcie_aux_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_core_pi_sleep_clk[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .fw_name = "sleep_clk" },
+};
+
+static const struct parent_map gcc_xo_gpll0_core_pi_sleep_clk_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 2 },
+	{ P_PI_SLEEP, 6 },
+};
+
+static struct clk_rcg2 pcie0_aux_clk_src = {
+	.cmd_rcgr = 0x75024,
+	.freq_tbl = ftbl_pcie_aux_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_core_pi_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie0_aux_clk_src",
+		.parent_data = gcc_xo_gpll0_core_pi_sleep_clk,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct clk_parent_data gcc_pcie20_phy0_pipe_clk_xo[] = {
+	{ .fw_name = "pcie20_phy0_pipe_clk" },
+	{ .fw_name = "xo" },
+};
+
+static const struct parent_map gcc_pcie20_phy0_pipe_clk_xo_map[] = {
+	{ P_PCIE20_PHY0_PIPE, 0 },
+	{ P_XO, 2 },
+};
+
+static struct clk_regmap_mux pcie0_pipe_clk_src = {
+	.reg = 0x7501c,
+	.shift = 8,
+	.width = 2,
+	.parent_map = gcc_pcie20_phy0_pipe_clk_xo_map,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "pcie0_pipe_clk_src",
+			.parent_data = gcc_pcie20_phy0_pipe_clk_xo,
+			.num_parents = 2,
+			.ops = &clk_regmap_mux_closest_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_sdcc_apps_clk_src[] = {
+	F(144000, P_XO, 16, 12, 125),
+	F(400000, P_XO, 12, 1, 5),
+	F(24000000, P_GPLL2, 12, 1, 4),
+	F(48000000, P_GPLL2, 12, 1, 2),
+	F(96000000, P_GPLL2, 12, 0, 0),
+	F(177777778, P_GPLL0, 4.5, 0, 0),
+	F(192000000, P_GPLL2, 6, 0, 0),
+	F(384000000, P_GPLL2, 3, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data
+			gcc_xo_gpll0_gpll2_gpll0_out_main_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll2.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL2, 2 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static struct clk_rcg2 sdcc1_apps_clk_src = {
+	.cmd_rcgr = 0x42004,
+	.freq_tbl = ftbl_sdcc_apps_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll2_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc1_apps_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll2_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_usb_aux_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 usb0_aux_clk_src = {
+	.cmd_rcgr = 0x3e05c,
+	.freq_tbl = ftbl_usb_aux_clk_src,
+	.mnd_width = 16,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_core_pi_sleep_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb0_aux_clk_src",
+		.parent_data = gcc_xo_gpll0_core_pi_sleep_clk,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_usb_mock_utmi_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(60000000, P_GPLL6, 6, 1, 3),
+	{ }
+};
+
+static const struct clk_parent_data
+			gcc_xo_gpll6_gpll0_gpll0_out_main_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll6.clkr.hw },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map gcc_xo_gpll6_gpll0_gpll0_out_main_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL6, 1 },
+	{ P_GPLL0, 3 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static struct clk_rcg2 usb0_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x3e020,
+	.freq_tbl = ftbl_usb_mock_utmi_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll6_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb0_mock_utmi_clk_src",
+		.parent_data = gcc_xo_gpll6_gpll0_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct clk_parent_data gcc_usb3phy_0_cc_pipe_clk_xo[] = {
+	{ .fw_name = "usb3phy_0_cc_pipe_clk" },
+	{ .fw_name = "xo" },
+};
+
+static const struct parent_map gcc_usb3phy_0_cc_pipe_clk_xo_map[] = {
+	{ P_USB3PHY_0_PIPE, 0 },
+	{ P_XO, 2 },
+};
+
+static struct clk_regmap_mux usb0_pipe_clk_src = {
+	.reg = 0x3e048,
+	.shift = 8,
+	.width = 2,
+	.parent_map = gcc_usb3phy_0_cc_pipe_clk_xo_map,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "usb0_pipe_clk_src",
+			.parent_data = gcc_usb3phy_0_cc_pipe_clk_xo,
+			.num_parents = 2,
+			.ops = &clk_regmap_mux_closest_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_sdcc_ice_core_clk_src[] = {
+	F(80000000, P_GPLL0_DIV2, 5, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	F(216000000, P_GPLL6, 5, 0, 0),
+	F(308570000, P_GPLL6, 3.5, 0, 0),
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_gpll6_gpll0_div2[] = {
+	{ .fw_name = "xo"},
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll6_gpll0_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL6, 2 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static struct clk_rcg2 sdcc1_ice_core_clk_src = {
+	.cmd_rcgr = 0x5d000,
+	.freq_tbl = ftbl_sdcc_ice_core_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "sdcc1_ice_core_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_gpll0_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_qdss_stm_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0_DIV2, 8, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 qdss_stm_clk_src = {
+	.cmd_rcgr = 0x2902C,
+	.freq_tbl = ftbl_qdss_stm_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "qdss_stm_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll0_out_main_div2,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_qdss_traceclkin_clk_src[] = {
+	F(80000000, P_GPLL0_DIV2, 5, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	F(300000000, P_GPLL4, 4, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data gcc_xo_gpll4_gpll0_gpll0_div2[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll4.clkr.hw },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll0_out_main_div2.hw },
+};
+
+static const struct parent_map gcc_xo_gpll4_gpll0_gpll0_div2_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL4, 1 },
+	{ P_GPLL0, 2 },
+	{ P_GPLL0_DIV2, 4 },
+};
+
+static struct clk_rcg2 qdss_traceclkin_clk_src = {
+	.cmd_rcgr = 0x29048,
+	.freq_tbl = ftbl_qdss_traceclkin_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll4_gpll0_gpll0_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "qdss_traceclkin_clk_src",
+		.parent_data = gcc_xo_gpll4_gpll0_gpll0_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 usb1_mock_utmi_clk_src = {
+	.cmd_rcgr = 0x3f020,
+	.freq_tbl = ftbl_usb_mock_utmi_clk_src,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll6_gpll0_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "usb1_mock_utmi_clk_src",
+		.parent_data = gcc_xo_gpll6_gpll0_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_adss_pwm_clk = {
+	.halt_reg = 0x1c020,
+	.clkr = {
+		.enable_reg = 0x1c020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_adss_pwm_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&adss_pwm_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_apss_ahb_clk = {
+	.halt_reg = 0x4601c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(14),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_apss_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&apss_ahb_postdiv_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_system_noc_bfdcd_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0_DIV2, 8, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	F(133333333, P_GPLL0, 6, 0, 0),
+	F(160000000, P_GPLL0, 5, 0, 0),
+	F(200000000, P_GPLL0, 4, 0, 0),
+	F(266666667, P_GPLL0, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 system_noc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x26004,
+	.freq_tbl = ftbl_system_noc_bfdcd_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll6_gpll0_out_main_div2_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "system_noc_bfdcd_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll6_gpll0_out_main_div2,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_ubi32_mem_noc_bfdcd_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(307670000, P_BIAS_PLL_NSS_NOC, 1.5, 0, 0),
+	F(533333333, P_GPLL0, 1.5, 0, 0),
+	{ }
+};
+
+static const struct clk_parent_data
+			gcc_xo_gpll0_gpll2_bias_pll_nss_noc_clk[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll2.clkr.hw },
+	{ .fw_name = "bias_pll_nss_noc_clk" },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll2_bias_pll_nss_noc_clk_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL2, 3 },
+	{ P_BIAS_PLL_NSS_NOC, 4 },
+};
+
+static struct clk_rcg2 ubi32_mem_noc_bfdcd_clk_src = {
+	.cmd_rcgr = 0x68088,
+	.freq_tbl = ftbl_ubi32_mem_noc_bfdcd_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll2_bias_pll_nss_noc_clk_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ubi32_mem_noc_bfdcd_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll2_bias_pll_nss_noc_clk,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_apss_axi_clk = {
+	.halt_reg = 0x46020,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(13),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_apss_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&apss_axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_ahb_clk = {
+	.halt_reg = 0x01008,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(10),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup1_i2c_apps_clk = {
+	.halt_reg = 0x02008,
+	.clkr = {
+		.enable_reg = 0x02008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup1_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup1_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup1_spi_apps_clk = {
+	.halt_reg = 0x02004,
+	.clkr = {
+		.enable_reg = 0x02004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup1_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup1_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup2_i2c_apps_clk = {
+	.halt_reg = 0x03010,
+	.clkr = {
+		.enable_reg = 0x03010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup2_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup2_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup2_spi_apps_clk = {
+	.halt_reg = 0x0300c,
+	.clkr = {
+		.enable_reg = 0x0300c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup2_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup2_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup3_i2c_apps_clk = {
+	.halt_reg = 0x04010,
+	.clkr = {
+		.enable_reg = 0x04010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup3_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup3_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup3_spi_apps_clk = {
+	.halt_reg = 0x0400c,
+	.clkr = {
+		.enable_reg = 0x0400c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup3_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup3_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup4_i2c_apps_clk = {
+	.halt_reg = 0x05010,
+	.clkr = {
+		.enable_reg = 0x05010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup4_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup4_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup4_spi_apps_clk = {
+	.halt_reg = 0x0500c,
+	.clkr = {
+		.enable_reg = 0x0500c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup4_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup4_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup5_i2c_apps_clk = {
+	.halt_reg = 0x06010,
+	.clkr = {
+		.enable_reg = 0x06010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup5_i2c_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup5_i2c_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup5_spi_apps_clk = {
+	.halt_reg = 0x0600c,
+	.clkr = {
+		.enable_reg = 0x0600c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup5_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup5_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_qup6_spi_apps_clk = {
+	.halt_reg = 0x0700c,
+	.clkr = {
+		.enable_reg = 0x0700c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_qup6_spi_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_qup6_spi_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart1_apps_clk = {
+	.halt_reg = 0x0203c,
+	.clkr = {
+		.enable_reg = 0x0203c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart1_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_uart1_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart2_apps_clk = {
+	.halt_reg = 0x0302c,
+	.clkr = {
+		.enable_reg = 0x0302c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart2_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_uart2_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart3_apps_clk = {
+	.halt_reg = 0x0402c,
+	.clkr = {
+		.enable_reg = 0x0402c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart3_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_uart3_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart4_apps_clk = {
+	.halt_reg = 0x0502c,
+	.clkr = {
+		.enable_reg = 0x0502c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart4_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_uart4_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart5_apps_clk = {
+	.halt_reg = 0x0602c,
+	.clkr = {
+		.enable_reg = 0x0602c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart5_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_uart5_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_blsp1_uart6_apps_clk = {
+	.halt_reg = 0x0702c,
+	.clkr = {
+		.enable_reg = 0x0702c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_blsp1_uart6_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&blsp1_uart6_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_ahb_clk = {
+	.halt_reg = 0x16024,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_axi_clk = {
+	.halt_reg = 0x16020,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_clk = {
+	.halt_reg = 0x1601c,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(2),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&crypto_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_fixed_factor gpll6_out_main_div2 = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "gpll6_out_main_div2",
+		.parent_hws = (const struct clk_hw *[]){
+				&gpll6_main.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_branch gcc_xo_clk = {
+	.halt_reg = 0x30030,
+	.clkr = {
+		.enable_reg = 0x30030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_xo_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_xo_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp1_clk = {
+	.halt_reg = 0x08000,
+	.clkr = {
+		.enable_reg = 0x08000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp1_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gp1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp2_clk = {
+	.halt_reg = 0x09000,
+	.clkr = {
+		.enable_reg = 0x09000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp2_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gp2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_gp3_clk = {
+	.halt_reg = 0x0a000,
+	.clkr = {
+		.enable_reg = 0x0a000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_gp3_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gp3_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_mdio_ahb_clk = {
+	.halt_reg = 0x58004,
+	.clkr = {
+		.enable_reg = 0x58004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_mdio_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_crypto_ppe_clk = {
+	.halt_reg = 0x68310,
+	.clkr = {
+		.enable_reg = 0x68310,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_crypto_ppe_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ce_apb_clk = {
+	.halt_reg = 0x68174,
+	.clkr = {
+		.enable_reg = 0x68174,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ce_apb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ce_axi_clk = {
+	.halt_reg = 0x68170,
+	.clkr = {
+		.enable_reg = 0x68170,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ce_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_cfg_clk = {
+	.halt_reg = 0x68160,
+	.clkr = {
+		.enable_reg = 0x68160,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_cfg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_crypto_clk = {
+	.halt_reg = 0x68164,
+	.clkr = {
+		.enable_reg = 0x68164,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_crypto_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_crypto_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_csr_clk = {
+	.halt_reg = 0x68318,
+	.clkr = {
+		.enable_reg = 0x68318,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_csr_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_edma_cfg_clk = {
+	.halt_reg = 0x6819C,
+	.clkr = {
+		.enable_reg = 0x6819C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_edma_cfg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_edma_clk = {
+	.halt_reg = 0x68198,
+	.clkr = {
+		.enable_reg = 0x68198,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_edma_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_noc_clk = {
+	.halt_reg = 0x68168,
+	.clkr = {
+		.enable_reg = 0x68168,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_noc_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&snoc_nssnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_utcm_clk = {
+	.halt_reg = 0x2606c,
+	.clkr = {
+		.enable_reg = 0x2606c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_utcm_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&snoc_nssnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_snoc_nssnoc_clk = {
+	.halt_reg = 0x26070,
+	.clkr = {
+		.enable_reg = 0x26070,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_snoc_nssnoc_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&snoc_nssnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct freq_tbl ftbl_wcss_ahb_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(133333333, P_GPLL0, 6, 0, 0),
+	{ }
+};
+
+static const struct freq_tbl ftbl_q6_axi_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(400000000, P_GPLL0, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 wcss_ahb_clk_src = {
+	.cmd_rcgr = 0x59020,
+	.freq_tbl = ftbl_wcss_ahb_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "wcss_ahb_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct clk_parent_data gcc_xo_gpll0_gpll2_gpll4_gpll6[] = {
+	{ .fw_name = "xo" },
+	{ .hw = &gpll0.clkr.hw },
+	{ .hw = &gpll2.clkr.hw },
+	{ .hw = &gpll4.clkr.hw },
+	{ .hw = &gpll6.clkr.hw },
+};
+
+static const struct parent_map gcc_xo_gpll0_gpll2_gpll4_gpll6_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 1 },
+	{ P_GPLL2, 2 },
+	{ P_GPLL4, 3 },
+	{ P_GPLL6, 4 },
+};
+
+static struct clk_rcg2 q6_axi_clk_src = {
+	.cmd_rcgr = 0x59120,
+	.freq_tbl = ftbl_q6_axi_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_gpll2_gpll4_gpll6_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "q6_axi_clk_src",
+		.parent_data = gcc_xo_gpll0_gpll2_gpll4_gpll6,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_lpass_core_axim_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(100000000, P_GPLL0, 8, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 lpass_core_axim_clk_src = {
+	.cmd_rcgr = 0x1F020,
+	.freq_tbl = ftbl_lpass_core_axim_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "lpass_core_axim_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_lpass_snoc_cfg_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(266666667, P_GPLL0, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 lpass_snoc_cfg_clk_src = {
+	.cmd_rcgr = 0x1F040,
+	.freq_tbl = ftbl_lpass_snoc_cfg_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "lpass_snoc_cfg_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_lpass_q6_axim_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(400000000, P_GPLL0, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 lpass_q6_axim_clk_src = {
+	.cmd_rcgr = 0x1F008,
+	.freq_tbl = ftbl_lpass_q6_axim_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "lpass_q6_axim_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct freq_tbl ftbl_rbcpr_wcss_clk_src[] = {
+	F(24000000, P_XO, 1, 0, 0),
+	F(50000000, P_GPLL0, 16, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 rbcpr_wcss_clk_src = {
+	.cmd_rcgr = 0x3a00c,
+	.freq_tbl = ftbl_rbcpr_wcss_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_out_main_div2_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "rbcpr_wcss_clk_src",
+		.parent_data = gcc_xo_gpll0_out_main_div2_gpll0,
+		.num_parents = 3,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_lpass_core_axim_clk = {
+	.halt_reg = 0x1F028,
+	.clkr = {
+		.enable_reg = 0x1F028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_core_axim_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_core_axim_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_snoc_cfg_clk = {
+	.halt_reg = 0x1F048,
+	.clkr = {
+		.enable_reg = 0x1F048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_snoc_cfg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_snoc_cfg_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_q6_axim_clk = {
+	.halt_reg = 0x1F010,
+	.clkr = {
+		.enable_reg = 0x1F010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_q6_axim_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_q6_axim_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_q6_atbm_at_clk = {
+	.halt_reg = 0x1F018,
+	.clkr = {
+		.enable_reg = 0x1F018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_q6_atbm_at_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&qdss_at_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_q6_pclkdbg_clk = {
+	.halt_reg = 0x1F01C,
+	.clkr = {
+		.enable_reg = 0x1F01C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_q6_pclkdbg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&qdss_dap_sync_clk_src.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_q6ss_tsctr_1to2_clk = {
+	.halt_reg = 0x1F014,
+	.clkr = {
+		.enable_reg = 0x1F014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_q6ss_tsctr_1to2_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&qdss_tsctr_div2_clk_src.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_q6ss_trig_clk = {
+	.halt_reg = 0x1F038,
+	.clkr = {
+		.enable_reg = 0x1F038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_q6ss_trig_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&qdss_dap_sync_clk_src.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_lpass_tbu_clk = {
+	.halt_reg = 0x12094,
+	.clkr = {
+		.enable_reg = 0xb00c,
+		.enable_mask = BIT(10),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_lpass_tbu_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_q6_axim_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcnoc_lpass_clk = {
+	.halt_reg = 0x27020,
+	.clkr = {
+		.enable_reg = 0x27020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcnoc_lpass_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_core_axim_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_mem_noc_lpass_clk = {
+	.halt_reg = 0x1D044,
+	.clkr = {
+		.enable_reg = 0x1D044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_mem_noc_lpass_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_q6_axim_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_snoc_lpass_cfg_clk = {
+	.halt_reg = 0x26074,
+	.clkr = {
+		.enable_reg = 0x26074,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_snoc_lpass_cfg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&lpass_snoc_cfg_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_mem_noc_ubi32_clk = {
+	.halt_reg = 0x1D03C,
+	.clkr = {
+		.enable_reg = 0x1D03C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_mem_noc_ubi32_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&ubi32_mem_noc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port1_rx_clk = {
+	.halt_reg = 0x68240,
+	.clkr = {
+		.enable_reg = 0x68240,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port1_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port1_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port1_tx_clk = {
+	.halt_reg = 0x68244,
+	.clkr = {
+		.enable_reg = 0x68244,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port1_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port1_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port2_rx_clk = {
+	.halt_reg = 0x68248,
+	.clkr = {
+		.enable_reg = 0x68248,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port2_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port2_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port2_tx_clk = {
+	.halt_reg = 0x6824c,
+	.clkr = {
+		.enable_reg = 0x6824c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port2_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port2_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port3_rx_clk = {
+	.halt_reg = 0x68250,
+	.clkr = {
+		.enable_reg = 0x68250,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port3_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port3_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port3_tx_clk = {
+	.halt_reg = 0x68254,
+	.clkr = {
+		.enable_reg = 0x68254,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port3_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port3_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port4_rx_clk = {
+	.halt_reg = 0x68258,
+	.clkr = {
+		.enable_reg = 0x68258,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port4_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port4_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port4_tx_clk = {
+	.halt_reg = 0x6825c,
+	.clkr = {
+		.enable_reg = 0x6825c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port4_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port4_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port5_rx_clk = {
+	.halt_reg = 0x68260,
+	.clkr = {
+		.enable_reg = 0x68260,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port5_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_port5_tx_clk = {
+	.halt_reg = 0x68264,
+	.clkr = {
+		.enable_reg = 0x68264,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_port5_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_cfg_clk = {
+	.halt_reg = 0x68194,
+	.clkr = {
+		.enable_reg = 0x68194,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_cfg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_clk = {
+	.halt_reg = 0x68190,
+	.clkr = {
+		.enable_reg = 0x68190,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ppe_ipe_clk = {
+	.halt_reg = 0x68338,
+	.clkr = {
+		.enable_reg = 0x68338,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ppe_ipe_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nss_ptp_ref_clk = {
+	.halt_reg = 0x6816C,
+	.clkr = {
+		.enable_reg = 0x6816C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nss_ptp_ref_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_cdiv_clk_src.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ce_apb_clk = {
+	.halt_reg = 0x6830C,
+	.clkr = {
+		.enable_reg = 0x6830C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ce_apb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ce_axi_clk = {
+	.halt_reg = 0x68308,
+	.clkr = {
+		.enable_reg = 0x68308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ce_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_crypto_clk = {
+	.halt_reg = 0x68314,
+	.clkr = {
+		.enable_reg = 0x68314,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_crypto_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_crypto_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ppe_cfg_clk = {
+	.halt_reg = 0x68304,
+	.clkr = {
+		.enable_reg = 0x68304,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ppe_cfg_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ppe_clk = {
+	.halt_reg = 0x68300,
+	.clkr = {
+		.enable_reg = 0x68300,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ppe_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_qosgen_ref_clk = {
+	.halt_reg = 0x68180,
+	.clkr = {
+		.enable_reg = 0x68180,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_qosgen_ref_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_xo_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_snoc_clk = {
+	.halt_reg = 0x68188,
+	.clkr = {
+		.enable_reg = 0x68188,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_snoc_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&system_noc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_timeout_ref_clk = {
+	.halt_reg = 0x68184,
+	.clkr = {
+		.enable_reg = 0x68184,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_timeout_ref_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_xo_div4_clk_src.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_nssnoc_ubi0_ahb_clk = {
+	.halt_reg = 0x68270,
+	.clkr = {
+		.enable_reg = 0x68270,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_nssnoc_ubi0_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port1_mac_clk = {
+	.halt_reg = 0x68320,
+	.clkr = {
+		.enable_reg = 0x68320,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port1_mac_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port2_mac_clk = {
+	.halt_reg = 0x68324,
+	.clkr = {
+		.enable_reg = 0x68324,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port2_mac_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port3_mac_clk = {
+	.halt_reg = 0x68328,
+	.clkr = {
+		.enable_reg = 0x68328,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port3_mac_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port4_mac_clk = {
+	.halt_reg = 0x6832c,
+	.clkr = {
+		.enable_reg = 0x6832c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port4_mac_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_port5_mac_clk = {
+	.halt_reg = 0x68330,
+	.clkr = {
+		.enable_reg = 0x68330,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_port5_mac_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ppe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_ahb_clk = {
+	.halt_reg = 0x6820C,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x6820C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ce_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_axi_clk = {
+	.halt_reg = 0x68200,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x68200,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&ubi32_mem_noc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_nc_axi_clk = {
+	.halt_reg = 0x68204,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x68204,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_nc_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&snoc_nssnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_ubi0_core_clk = {
+	.halt_reg = 0x68210,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x68210,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_ubi0_core_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_ubi0_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_ahb_clk = {
+	.halt_reg = 0x75010,
+	.clkr = {
+		.enable_reg = 0x75010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_aux_clk = {
+	.halt_reg = 0x75014,
+	.clkr = {
+		.enable_reg = 0x75014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_aux_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_aux_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_axi_m_clk = {
+	.halt_reg = 0x75008,
+	.clkr = {
+		.enable_reg = 0x75008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_axi_m_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_axi_s_clk = {
+	.halt_reg = 0x7500c,
+	.clkr = {
+		.enable_reg = 0x7500c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_axi_s_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_pcie0_axi_clk = {
+	.halt_reg = 0x26048,
+	.clkr = {
+		.enable_reg = 0x26048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_pcie0_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_pipe_clk = {
+	.halt_reg = 0x75018,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x75018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_pipe_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_pipe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_prng_ahb_clk = {
+	.halt_reg = 0x13004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.clkr = {
+		.enable_reg = 0x0b004,
+		.enable_mask = BIT(8),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_prng_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_qdss_dap_clk = {
+	.halt_reg = 0x29084,
+	.clkr = {
+		.enable_reg = 0x29084,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_qdss_dap_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&qdss_dap_sync_clk_src.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_qpic_ahb_clk = {
+	.halt_reg = 0x57024,
+	.clkr = {
+		.enable_reg = 0x57024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_qpic_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_qpic_clk = {
+	.halt_reg = 0x57020,
+	.clkr = {
+		.enable_reg = 0x57020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_qpic_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_ahb_clk = {
+	.halt_reg = 0x4201c,
+	.clkr = {
+		.enable_reg = 0x4201c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_apps_clk = {
+	.halt_reg = 0x42018,
+	.clkr = {
+		.enable_reg = 0x42018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_apps_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&sdcc1_apps_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_ahb_clk = {
+	.halt_reg = 0x56008,
+	.clkr = {
+		.enable_reg = 0x56008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port1_rx_clk = {
+	.halt_reg = 0x56010,
+	.clkr = {
+		.enable_reg = 0x56010,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port1_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port1_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port1_tx_clk = {
+	.halt_reg = 0x56014,
+	.clkr = {
+		.enable_reg = 0x56014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port1_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port1_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port2_rx_clk = {
+	.halt_reg = 0x56018,
+	.clkr = {
+		.enable_reg = 0x56018,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port2_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port2_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port2_tx_clk = {
+	.halt_reg = 0x5601c,
+	.clkr = {
+		.enable_reg = 0x5601c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port2_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port2_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port3_rx_clk = {
+	.halt_reg = 0x56020,
+	.clkr = {
+		.enable_reg = 0x56020,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port3_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port3_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port3_tx_clk = {
+	.halt_reg = 0x56024,
+	.clkr = {
+		.enable_reg = 0x56024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port3_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port3_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port4_rx_clk = {
+	.halt_reg = 0x56028,
+	.clkr = {
+		.enable_reg = 0x56028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port4_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port4_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port4_tx_clk = {
+	.halt_reg = 0x5602c,
+	.clkr = {
+		.enable_reg = 0x5602c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port4_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port4_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port5_rx_clk = {
+	.halt_reg = 0x56030,
+	.clkr = {
+		.enable_reg = 0x56030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port5_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_port5_tx_clk = {
+	.halt_reg = 0x56034,
+	.clkr = {
+		.enable_reg = 0x56034,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_port5_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy0_sys_clk = {
+	.halt_reg = 0x5600C,
+	.clkr = {
+		.enable_reg = 0x5600C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy0_sys_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_xo_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_ahb_clk = {
+	.halt_reg = 0x56108,
+	.clkr = {
+		.enable_reg = 0x56108,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_port5_rx_clk = {
+	.halt_reg = 0x56110,
+	.clkr = {
+		.enable_reg = 0x56110,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_port5_rx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_rx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_port5_tx_clk = {
+	.halt_reg = 0x56114,
+	.clkr = {
+		.enable_reg = 0x56114,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_port5_tx_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&nss_port5_tx_div_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_uniphy1_sys_clk = {
+	.halt_reg = 0x5610C,
+	.clkr = {
+		.enable_reg = 0x5610C,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_uniphy1_sys_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_xo_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_aux_clk = {
+	.halt_reg = 0x3e044,
+	.clkr = {
+		.enable_reg = 0x3e044,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_aux_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb0_aux_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_master_clk = {
+	.halt_reg = 0x3e000,
+	.clkr = {
+		.enable_reg = 0x3e000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_master_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb0_master_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_snoc_bus_timeout2_ahb_clk = {
+	.halt_reg = 0x47014,
+	.clkr = {
+		.enable_reg = 0x47014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_snoc_bus_timeout2_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb0_master_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_rcg2 pcie0_rchng_clk_src = {
+	.cmd_rcgr = 0x75070,
+	.freq_tbl = ftbl_pcie_rchng_clk_src,
+	.hid_width = 5,
+	.parent_map = gcc_xo_gpll0_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pcie0_rchng_clk_src",
+		.parent_data = gcc_xo_gpll0,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch gcc_pcie0_rchng_clk = {
+	.halt_reg = 0x75070,
+	.clkr = {
+		.enable_reg = 0x75070,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_rchng_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_rchng_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_pcie0_axi_s_bridge_clk = {
+	.halt_reg = 0x75048,
+	.clkr = {
+		.enable_reg = 0x75048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_pcie0_axi_s_bridge_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcie0_axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sys_noc_usb0_axi_clk = {
+	.halt_reg = 0x26040,
+	.clkr = {
+		.enable_reg = 0x26040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sys_noc_usb0_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb0_master_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_mock_utmi_clk = {
+	.halt_reg = 0x3e008,
+	.clkr = {
+		.enable_reg = 0x3e008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_mock_utmi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb0_mock_utmi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_phy_cfg_ahb_clk = {
+	.halt_reg = 0x3e080,
+	.clkr = {
+		.enable_reg = 0x3e080,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_phy_cfg_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_pipe_clk = {
+	.halt_reg = 0x3e040,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x3e040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_pipe_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb0_pipe_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb0_sleep_clk = {
+	.halt_reg = 0x3e004,
+	.clkr = {
+		.enable_reg = 0x3e004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb0_sleep_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_sleep_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_master_clk = {
+	.halt_reg = 0x3f000,
+	.clkr = {
+		.enable_reg = 0x3f000,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_master_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_mock_utmi_clk = {
+	.halt_reg = 0x3f008,
+	.clkr = {
+		.enable_reg = 0x3f008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_mock_utmi_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&usb1_mock_utmi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_phy_cfg_ahb_clk = {
+	.halt_reg = 0x3f080,
+	.clkr = {
+		.enable_reg = 0x3f080,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_phy_cfg_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_usb1_sleep_clk = {
+	.halt_reg = 0x3f004,
+	.clkr = {
+		.enable_reg = 0x3f004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_usb1_sleep_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_sleep_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cmn_12gpll_ahb_clk = {
+	.halt_reg = 0x56308,
+	.clkr = {
+		.enable_reg = 0x56308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cmn_12gpll_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cmn_12gpll_sys_clk = {
+	.halt_reg = 0x5630c,
+	.clkr = {
+		.enable_reg = 0x5630c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cmn_12gpll_sys_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&gcc_xo_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_sdcc1_ice_core_clk = {
+	.halt_reg = 0x5d014,
+	.clkr = {
+		.enable_reg = 0x5d014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_sdcc1_ice_core_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&sdcc1_ice_core_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_dcc_clk = {
+	.halt_reg = 0x77004,
+	.clkr = {
+		.enable_reg = 0x77004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_dcc_clk",
+			.parent_hws = (const struct clk_hw *[]){
+					&pcnoc_bfdcd_clk_src.clkr.hw },
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static const struct alpha_pll_config ubi32_pll_config = {
+	.l = 0x3e,
+	.alpha = 0x57,
+	.config_ctl_val = 0x240d6aa8,
+	.config_ctl_hi_val = 0x3c2,
+	.main_output_mask = BIT(0),
+	.aux_output_mask = BIT(1),
+	.pre_div_val = 0x0,
+	.pre_div_mask = BIT(12),
+	.post_div_val = 0x0,
+	.post_div_mask = GENMASK(9, 8),
+};
+
+static const struct alpha_pll_config nss_crypto_pll_config = {
+	.l = 0x32,
+	.alpha = 0x0,
+	.alpha_hi = 0x0,
+	.config_ctl_val = 0x4001055b,
+	.main_output_mask = BIT(0),
+	.pre_div_val = 0x0,
+	.pre_div_mask = GENMASK(14, 12),
+	.post_div_val = 0x1 << 8,
+	.post_div_mask = GENMASK(11, 8),
+	.vco_mask = GENMASK(21, 20),
+	.vco_val = 0x0,
+	.alpha_en_mask = BIT(24),
+};
+
+static struct clk_hw *gcc_ipq6018_hws[] = {
+	&gpll0_out_main_div2.hw,
+	&gcc_xo_div4_clk_src.hw,
+	&nss_ppe_cdiv_clk_src.hw,
+	&gpll6_out_main_div2.hw,
+	&qdss_dap_sync_clk_src.hw,
+	&qdss_tsctr_div2_clk_src.hw,
+};
+
+static struct clk_regmap *gcc_ipq6018_clks[] = {
+	[GPLL0_MAIN] = &gpll0_main.clkr,
+	[GPLL0] = &gpll0.clkr,
+	[UBI32_PLL_MAIN] = &ubi32_pll_main.clkr,
+	[UBI32_PLL] = &ubi32_pll.clkr,
+	[GPLL6_MAIN] = &gpll6_main.clkr,
+	[GPLL6] = &gpll6.clkr,
+	[GPLL4_MAIN] = &gpll4_main.clkr,
+	[GPLL4] = &gpll4.clkr,
+	[PCNOC_BFDCD_CLK_SRC] = &pcnoc_bfdcd_clk_src.clkr,
+	[GPLL2_MAIN] = &gpll2_main.clkr,
+	[GPLL2] = &gpll2.clkr,
+	[NSS_CRYPTO_PLL_MAIN] = &nss_crypto_pll_main.clkr,
+	[NSS_CRYPTO_PLL] = &nss_crypto_pll.clkr,
+	[QDSS_TSCTR_CLK_SRC] = &qdss_tsctr_clk_src.clkr,
+	[QDSS_AT_CLK_SRC] = &qdss_at_clk_src.clkr,
+	[NSS_PPE_CLK_SRC] = &nss_ppe_clk_src.clkr,
+	[GCC_XO_CLK_SRC] = &gcc_xo_clk_src.clkr,
+	[SYSTEM_NOC_BFDCD_CLK_SRC] = &system_noc_bfdcd_clk_src.clkr,
+	[SNOC_NSSNOC_BFDCD_CLK_SRC] = &snoc_nssnoc_bfdcd_clk_src.clkr,
+	[NSS_CE_CLK_SRC] = &nss_ce_clk_src.clkr,
+	[GCC_SLEEP_CLK_SRC] = &gcc_sleep_clk_src.clkr,
+	[APSS_AHB_CLK_SRC] = &apss_ahb_clk_src.clkr,
+	[NSS_PORT5_RX_CLK_SRC] = &nss_port5_rx_clk_src.clkr,
+	[NSS_PORT5_TX_CLK_SRC] = &nss_port5_tx_clk_src.clkr,
+	[UBI32_MEM_NOC_BFDCD_CLK_SRC] = &ubi32_mem_noc_bfdcd_clk_src.clkr,
+	[PCIE0_AXI_CLK_SRC] = &pcie0_axi_clk_src.clkr,
+	[USB0_MASTER_CLK_SRC] = &usb0_master_clk_src.clkr,
+	[APSS_AHB_POSTDIV_CLK_SRC] = &apss_ahb_postdiv_clk_src.clkr,
+	[NSS_PORT1_RX_CLK_SRC] = &nss_port1_rx_clk_src.clkr,
+	[NSS_PORT1_TX_CLK_SRC] = &nss_port1_tx_clk_src.clkr,
+	[NSS_PORT2_RX_CLK_SRC] = &nss_port2_rx_clk_src.clkr,
+	[NSS_PORT2_TX_CLK_SRC] = &nss_port2_tx_clk_src.clkr,
+	[NSS_PORT3_RX_CLK_SRC] = &nss_port3_rx_clk_src.clkr,
+	[NSS_PORT3_TX_CLK_SRC] = &nss_port3_tx_clk_src.clkr,
+	[NSS_PORT4_RX_CLK_SRC] = &nss_port4_rx_clk_src.clkr,
+	[NSS_PORT4_TX_CLK_SRC] = &nss_port4_tx_clk_src.clkr,
+	[NSS_PORT5_RX_DIV_CLK_SRC] = &nss_port5_rx_div_clk_src.clkr,
+	[NSS_PORT5_TX_DIV_CLK_SRC] = &nss_port5_tx_div_clk_src.clkr,
+	[APSS_AXI_CLK_SRC] = &apss_axi_clk_src.clkr,
+	[NSS_CRYPTO_CLK_SRC] = &nss_crypto_clk_src.clkr,
+	[NSS_PORT1_RX_DIV_CLK_SRC] = &nss_port1_rx_div_clk_src.clkr,
+	[NSS_PORT1_TX_DIV_CLK_SRC] = &nss_port1_tx_div_clk_src.clkr,
+	[NSS_PORT2_RX_DIV_CLK_SRC] = &nss_port2_rx_div_clk_src.clkr,
+	[NSS_PORT2_TX_DIV_CLK_SRC] = &nss_port2_tx_div_clk_src.clkr,
+	[NSS_PORT3_RX_DIV_CLK_SRC] = &nss_port3_rx_div_clk_src.clkr,
+	[NSS_PORT3_TX_DIV_CLK_SRC] = &nss_port3_tx_div_clk_src.clkr,
+	[NSS_PORT4_RX_DIV_CLK_SRC] = &nss_port4_rx_div_clk_src.clkr,
+	[NSS_PORT4_TX_DIV_CLK_SRC] = &nss_port4_tx_div_clk_src.clkr,
+	[NSS_UBI0_CLK_SRC] = &nss_ubi0_clk_src.clkr,
+	[ADSS_PWM_CLK_SRC] = &adss_pwm_clk_src.clkr,
+	[BLSP1_QUP1_I2C_APPS_CLK_SRC] = &blsp1_qup1_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP1_SPI_APPS_CLK_SRC] = &blsp1_qup1_spi_apps_clk_src.clkr,
+	[BLSP1_QUP2_I2C_APPS_CLK_SRC] = &blsp1_qup2_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP2_SPI_APPS_CLK_SRC] = &blsp1_qup2_spi_apps_clk_src.clkr,
+	[BLSP1_QUP3_I2C_APPS_CLK_SRC] = &blsp1_qup3_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP3_SPI_APPS_CLK_SRC] = &blsp1_qup3_spi_apps_clk_src.clkr,
+	[BLSP1_QUP4_I2C_APPS_CLK_SRC] = &blsp1_qup4_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP4_SPI_APPS_CLK_SRC] = &blsp1_qup4_spi_apps_clk_src.clkr,
+	[BLSP1_QUP5_I2C_APPS_CLK_SRC] = &blsp1_qup5_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP5_SPI_APPS_CLK_SRC] = &blsp1_qup5_spi_apps_clk_src.clkr,
+	[BLSP1_QUP6_I2C_APPS_CLK_SRC] = &blsp1_qup6_i2c_apps_clk_src.clkr,
+	[BLSP1_QUP6_SPI_APPS_CLK_SRC] = &blsp1_qup6_spi_apps_clk_src.clkr,
+	[BLSP1_UART1_APPS_CLK_SRC] = &blsp1_uart1_apps_clk_src.clkr,
+	[BLSP1_UART2_APPS_CLK_SRC] = &blsp1_uart2_apps_clk_src.clkr,
+	[BLSP1_UART3_APPS_CLK_SRC] = &blsp1_uart3_apps_clk_src.clkr,
+	[BLSP1_UART4_APPS_CLK_SRC] = &blsp1_uart4_apps_clk_src.clkr,
+	[BLSP1_UART5_APPS_CLK_SRC] = &blsp1_uart5_apps_clk_src.clkr,
+	[BLSP1_UART6_APPS_CLK_SRC] = &blsp1_uart6_apps_clk_src.clkr,
+	[CRYPTO_CLK_SRC] = &crypto_clk_src.clkr,
+	[GP1_CLK_SRC] = &gp1_clk_src.clkr,
+	[GP2_CLK_SRC] = &gp2_clk_src.clkr,
+	[GP3_CLK_SRC] = &gp3_clk_src.clkr,
+	[NSS_UBI0_DIV_CLK_SRC] = &nss_ubi0_div_clk_src.clkr,
+	[PCIE0_AUX_CLK_SRC] = &pcie0_aux_clk_src.clkr,
+	[PCIE0_PIPE_CLK_SRC] = &pcie0_pipe_clk_src.clkr,
+	[SDCC1_APPS_CLK_SRC] = &sdcc1_apps_clk_src.clkr,
+	[USB0_AUX_CLK_SRC] = &usb0_aux_clk_src.clkr,
+	[USB0_MOCK_UTMI_CLK_SRC] = &usb0_mock_utmi_clk_src.clkr,
+	[USB0_PIPE_CLK_SRC] = &usb0_pipe_clk_src.clkr,
+	[USB1_MOCK_UTMI_CLK_SRC] = &usb1_mock_utmi_clk_src.clkr,
+	[GCC_ADSS_PWM_CLK] = &gcc_adss_pwm_clk.clkr,
+	[GCC_APSS_AHB_CLK] = &gcc_apss_ahb_clk.clkr,
+	[GCC_APSS_AXI_CLK] = &gcc_apss_axi_clk.clkr,
+	[GCC_BLSP1_AHB_CLK] = &gcc_blsp1_ahb_clk.clkr,
+	[GCC_BLSP1_QUP1_I2C_APPS_CLK] = &gcc_blsp1_qup1_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP1_SPI_APPS_CLK] = &gcc_blsp1_qup1_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP2_I2C_APPS_CLK] = &gcc_blsp1_qup2_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP2_SPI_APPS_CLK] = &gcc_blsp1_qup2_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP3_I2C_APPS_CLK] = &gcc_blsp1_qup3_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP3_SPI_APPS_CLK] = &gcc_blsp1_qup3_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP4_I2C_APPS_CLK] = &gcc_blsp1_qup4_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP4_SPI_APPS_CLK] = &gcc_blsp1_qup4_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP5_I2C_APPS_CLK] = &gcc_blsp1_qup5_i2c_apps_clk.clkr,
+	[GCC_BLSP1_QUP5_SPI_APPS_CLK] = &gcc_blsp1_qup5_spi_apps_clk.clkr,
+	[GCC_BLSP1_QUP6_SPI_APPS_CLK] = &gcc_blsp1_qup6_spi_apps_clk.clkr,
+	[GCC_BLSP1_UART1_APPS_CLK] = &gcc_blsp1_uart1_apps_clk.clkr,
+	[GCC_BLSP1_UART2_APPS_CLK] = &gcc_blsp1_uart2_apps_clk.clkr,
+	[GCC_BLSP1_UART3_APPS_CLK] = &gcc_blsp1_uart3_apps_clk.clkr,
+	[GCC_BLSP1_UART4_APPS_CLK] = &gcc_blsp1_uart4_apps_clk.clkr,
+	[GCC_BLSP1_UART5_APPS_CLK] = &gcc_blsp1_uart5_apps_clk.clkr,
+	[GCC_BLSP1_UART6_APPS_CLK] = &gcc_blsp1_uart6_apps_clk.clkr,
+	[GCC_CRYPTO_AHB_CLK] = &gcc_crypto_ahb_clk.clkr,
+	[GCC_CRYPTO_AXI_CLK] = &gcc_crypto_axi_clk.clkr,
+	[GCC_CRYPTO_CLK] = &gcc_crypto_clk.clkr,
+	[GCC_XO_CLK] = &gcc_xo_clk.clkr,
+	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
+	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
+	[GCC_GP3_CLK] = &gcc_gp3_clk.clkr,
+	[GCC_MDIO_AHB_CLK] = &gcc_mdio_ahb_clk.clkr,
+	[GCC_CRYPTO_PPE_CLK] = &gcc_crypto_ppe_clk.clkr,
+	[GCC_NSS_CE_APB_CLK] = &gcc_nss_ce_apb_clk.clkr,
+	[GCC_NSS_CE_AXI_CLK] = &gcc_nss_ce_axi_clk.clkr,
+	[GCC_NSS_CFG_CLK] = &gcc_nss_cfg_clk.clkr,
+	[GCC_NSS_CRYPTO_CLK] = &gcc_nss_crypto_clk.clkr,
+	[GCC_NSS_CSR_CLK] = &gcc_nss_csr_clk.clkr,
+	[GCC_NSS_EDMA_CFG_CLK] = &gcc_nss_edma_cfg_clk.clkr,
+	[GCC_NSS_EDMA_CLK] = &gcc_nss_edma_clk.clkr,
+	[GCC_NSS_NOC_CLK] = &gcc_nss_noc_clk.clkr,
+	[GCC_UBI0_UTCM_CLK] = &gcc_ubi0_utcm_clk.clkr,
+	[GCC_SNOC_NSSNOC_CLK] = &gcc_snoc_nssnoc_clk.clkr,
+	[GCC_NSS_PORT1_RX_CLK] = &gcc_nss_port1_rx_clk.clkr,
+	[GCC_NSS_PORT1_TX_CLK] = &gcc_nss_port1_tx_clk.clkr,
+	[GCC_NSS_PORT2_RX_CLK] = &gcc_nss_port2_rx_clk.clkr,
+	[GCC_NSS_PORT2_TX_CLK] = &gcc_nss_port2_tx_clk.clkr,
+	[GCC_NSS_PORT3_RX_CLK] = &gcc_nss_port3_rx_clk.clkr,
+	[GCC_NSS_PORT3_TX_CLK] = &gcc_nss_port3_tx_clk.clkr,
+	[GCC_NSS_PORT4_RX_CLK] = &gcc_nss_port4_rx_clk.clkr,
+	[GCC_NSS_PORT4_TX_CLK] = &gcc_nss_port4_tx_clk.clkr,
+	[GCC_NSS_PORT5_RX_CLK] = &gcc_nss_port5_rx_clk.clkr,
+	[GCC_NSS_PORT5_TX_CLK] = &gcc_nss_port5_tx_clk.clkr,
+	[GCC_NSS_PPE_CFG_CLK] = &gcc_nss_ppe_cfg_clk.clkr,
+	[GCC_NSS_PPE_CLK] = &gcc_nss_ppe_clk.clkr,
+	[GCC_NSS_PPE_IPE_CLK] = &gcc_nss_ppe_ipe_clk.clkr,
+	[GCC_NSS_PTP_REF_CLK] = &gcc_nss_ptp_ref_clk.clkr,
+	[GCC_NSSNOC_CE_APB_CLK] = &gcc_nssnoc_ce_apb_clk.clkr,
+	[GCC_NSSNOC_CE_AXI_CLK] = &gcc_nssnoc_ce_axi_clk.clkr,
+	[GCC_NSSNOC_CRYPTO_CLK] = &gcc_nssnoc_crypto_clk.clkr,
+	[GCC_NSSNOC_PPE_CFG_CLK] = &gcc_nssnoc_ppe_cfg_clk.clkr,
+	[GCC_NSSNOC_PPE_CLK] = &gcc_nssnoc_ppe_clk.clkr,
+	[GCC_NSSNOC_QOSGEN_REF_CLK] = &gcc_nssnoc_qosgen_ref_clk.clkr,
+	[GCC_NSSNOC_SNOC_CLK] = &gcc_nssnoc_snoc_clk.clkr,
+	[GCC_NSSNOC_TIMEOUT_REF_CLK] = &gcc_nssnoc_timeout_ref_clk.clkr,
+	[GCC_NSSNOC_UBI0_AHB_CLK] = &gcc_nssnoc_ubi0_ahb_clk.clkr,
+	[GCC_PORT1_MAC_CLK] = &gcc_port1_mac_clk.clkr,
+	[GCC_PORT2_MAC_CLK] = &gcc_port2_mac_clk.clkr,
+	[GCC_PORT3_MAC_CLK] = &gcc_port3_mac_clk.clkr,
+	[GCC_PORT4_MAC_CLK] = &gcc_port4_mac_clk.clkr,
+	[GCC_PORT5_MAC_CLK] = &gcc_port5_mac_clk.clkr,
+	[GCC_UBI0_AHB_CLK] = &gcc_ubi0_ahb_clk.clkr,
+	[GCC_UBI0_AXI_CLK] = &gcc_ubi0_axi_clk.clkr,
+	[GCC_UBI0_NC_AXI_CLK] = &gcc_ubi0_nc_axi_clk.clkr,
+	[GCC_UBI0_CORE_CLK] = &gcc_ubi0_core_clk.clkr,
+	[GCC_PCIE0_AHB_CLK] = &gcc_pcie0_ahb_clk.clkr,
+	[GCC_PCIE0_AUX_CLK] = &gcc_pcie0_aux_clk.clkr,
+	[GCC_PCIE0_AXI_M_CLK] = &gcc_pcie0_axi_m_clk.clkr,
+	[GCC_PCIE0_AXI_S_CLK] = &gcc_pcie0_axi_s_clk.clkr,
+	[GCC_SYS_NOC_PCIE0_AXI_CLK] = &gcc_sys_noc_pcie0_axi_clk.clkr,
+	[GCC_PCIE0_PIPE_CLK] = &gcc_pcie0_pipe_clk.clkr,
+	[GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr,
+	[GCC_QDSS_DAP_CLK] = &gcc_qdss_dap_clk.clkr,
+	[GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr,
+	[GCC_QPIC_CLK] = &gcc_qpic_clk.clkr,
+	[GCC_SDCC1_AHB_CLK] = &gcc_sdcc1_ahb_clk.clkr,
+	[GCC_SDCC1_APPS_CLK] = &gcc_sdcc1_apps_clk.clkr,
+	[GCC_UNIPHY0_AHB_CLK] = &gcc_uniphy0_ahb_clk.clkr,
+	[GCC_UNIPHY0_PORT1_RX_CLK] = &gcc_uniphy0_port1_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT1_TX_CLK] = &gcc_uniphy0_port1_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT2_RX_CLK] = &gcc_uniphy0_port2_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT2_TX_CLK] = &gcc_uniphy0_port2_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT3_RX_CLK] = &gcc_uniphy0_port3_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT3_TX_CLK] = &gcc_uniphy0_port3_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT4_RX_CLK] = &gcc_uniphy0_port4_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT4_TX_CLK] = &gcc_uniphy0_port4_tx_clk.clkr,
+	[GCC_UNIPHY0_PORT5_RX_CLK] = &gcc_uniphy0_port5_rx_clk.clkr,
+	[GCC_UNIPHY0_PORT5_TX_CLK] = &gcc_uniphy0_port5_tx_clk.clkr,
+	[GCC_UNIPHY0_SYS_CLK] = &gcc_uniphy0_sys_clk.clkr,
+	[GCC_UNIPHY1_AHB_CLK] = &gcc_uniphy1_ahb_clk.clkr,
+	[GCC_UNIPHY1_PORT5_RX_CLK] = &gcc_uniphy1_port5_rx_clk.clkr,
+	[GCC_UNIPHY1_PORT5_TX_CLK] = &gcc_uniphy1_port5_tx_clk.clkr,
+	[GCC_UNIPHY1_SYS_CLK] = &gcc_uniphy1_sys_clk.clkr,
+	[GCC_USB0_AUX_CLK] = &gcc_usb0_aux_clk.clkr,
+	[GCC_SYS_NOC_USB0_AXI_CLK] = &gcc_sys_noc_usb0_axi_clk.clkr,
+	[GCC_SNOC_BUS_TIMEOUT2_AHB_CLK] = &gcc_snoc_bus_timeout2_ahb_clk.clkr,
+	[GCC_USB0_MASTER_CLK] = &gcc_usb0_master_clk.clkr,
+	[GCC_USB0_MOCK_UTMI_CLK] = &gcc_usb0_mock_utmi_clk.clkr,
+	[GCC_USB0_PHY_CFG_AHB_CLK] = &gcc_usb0_phy_cfg_ahb_clk.clkr,
+	[GCC_USB0_PIPE_CLK] = &gcc_usb0_pipe_clk.clkr,
+	[GCC_USB0_SLEEP_CLK] = &gcc_usb0_sleep_clk.clkr,
+	[GCC_USB1_MASTER_CLK] = &gcc_usb1_master_clk.clkr,
+	[GCC_USB1_MOCK_UTMI_CLK] = &gcc_usb1_mock_utmi_clk.clkr,
+	[GCC_USB1_PHY_CFG_AHB_CLK] = &gcc_usb1_phy_cfg_ahb_clk.clkr,
+	[GCC_USB1_SLEEP_CLK] = &gcc_usb1_sleep_clk.clkr,
+	[GCC_CMN_12GPLL_AHB_CLK] = &gcc_cmn_12gpll_ahb_clk.clkr,
+	[GCC_CMN_12GPLL_SYS_CLK] = &gcc_cmn_12gpll_sys_clk.clkr,
+	[GCC_SDCC1_ICE_CORE_CLK] = &gcc_sdcc1_ice_core_clk.clkr,
+	[SDCC1_ICE_CORE_CLK_SRC] = &sdcc1_ice_core_clk_src.clkr,
+	[GCC_DCC_CLK] = &gcc_dcc_clk.clkr,
+	[PCIE0_RCHNG_CLK_SRC] = &pcie0_rchng_clk_src.clkr,
+	[GCC_PCIE0_AXI_S_BRIDGE_CLK] = &gcc_pcie0_axi_s_bridge_clk.clkr,
+	[PCIE0_RCHNG_CLK] = &gcc_pcie0_rchng_clk.clkr,
+	[WCSS_AHB_CLK_SRC] = &wcss_ahb_clk_src.clkr,
+	[Q6_AXI_CLK_SRC] = &q6_axi_clk_src.clkr,
+	[RBCPR_WCSS_CLK_SRC] = &rbcpr_wcss_clk_src.clkr,
+	[GCC_LPASS_CORE_AXIM_CLK] = &gcc_lpass_core_axim_clk.clkr,
+	[LPASS_CORE_AXIM_CLK_SRC] = &lpass_core_axim_clk_src.clkr,
+	[GCC_LPASS_SNOC_CFG_CLK] = &gcc_lpass_snoc_cfg_clk.clkr,
+	[LPASS_SNOC_CFG_CLK_SRC] = &lpass_snoc_cfg_clk_src.clkr,
+	[GCC_LPASS_Q6_AXIM_CLK] = &gcc_lpass_q6_axim_clk.clkr,
+	[LPASS_Q6_AXIM_CLK_SRC] = &lpass_q6_axim_clk_src.clkr,
+	[GCC_LPASS_Q6_ATBM_AT_CLK] = &gcc_lpass_q6_atbm_at_clk.clkr,
+	[GCC_LPASS_Q6_PCLKDBG_CLK] = &gcc_lpass_q6_pclkdbg_clk.clkr,
+	[GCC_LPASS_Q6SS_TSCTR_1TO2_CLK] = &gcc_lpass_q6ss_tsctr_1to2_clk.clkr,
+	[GCC_LPASS_Q6SS_TRIG_CLK] = &gcc_lpass_q6ss_trig_clk.clkr,
+	[GCC_LPASS_TBU_CLK] = &gcc_lpass_tbu_clk.clkr,
+	[GCC_PCNOC_LPASS_CLK] = &gcc_pcnoc_lpass_clk.clkr,
+	[GCC_MEM_NOC_UBI32_CLK] = &gcc_mem_noc_ubi32_clk.clkr,
+	[GCC_MEM_NOC_LPASS_CLK] = &gcc_mem_noc_lpass_clk.clkr,
+	[GCC_SNOC_LPASS_CFG_CLK] = &gcc_snoc_lpass_cfg_clk.clkr,
+	[QDSS_STM_CLK_SRC] = &qdss_stm_clk_src.clkr,
+	[QDSS_TRACECLKIN_CLK_SRC] = &qdss_traceclkin_clk_src.clkr,
+};
+
+static const struct qcom_reset_map gcc_ipq6018_resets[] = {
+	[GCC_BLSP1_BCR] = { 0x01000, 0 },
+	[GCC_BLSP1_QUP1_BCR] = { 0x02000, 0 },
+	[GCC_BLSP1_UART1_BCR] = { 0x02038, 0 },
+	[GCC_BLSP1_QUP2_BCR] = { 0x03008, 0 },
+	[GCC_BLSP1_UART2_BCR] = { 0x03028, 0 },
+	[GCC_BLSP1_QUP3_BCR] = { 0x04008, 0 },
+	[GCC_BLSP1_UART3_BCR] = { 0x04028, 0 },
+	[GCC_BLSP1_QUP4_BCR] = { 0x05008, 0 },
+	[GCC_BLSP1_UART4_BCR] = { 0x05028, 0 },
+	[GCC_BLSP1_QUP5_BCR] = { 0x06008, 0 },
+	[GCC_BLSP1_UART5_BCR] = { 0x06028, 0 },
+	[GCC_BLSP1_QUP6_BCR] = { 0x07008, 0 },
+	[GCC_BLSP1_UART6_BCR] = { 0x07028, 0 },
+	[GCC_IMEM_BCR] = { 0x0e000, 0 },
+	[GCC_SMMU_BCR] = { 0x12000, 0 },
+	[GCC_APSS_TCU_BCR] = { 0x12050, 0 },
+	[GCC_SMMU_XPU_BCR] = { 0x12054, 0 },
+	[GCC_PCNOC_TBU_BCR] = { 0x12058, 0 },
+	[GCC_SMMU_CFG_BCR] = { 0x1208c, 0 },
+	[GCC_PRNG_BCR] = { 0x13000, 0 },
+	[GCC_BOOT_ROM_BCR] = { 0x13008, 0 },
+	[GCC_CRYPTO_BCR] = { 0x16000, 0 },
+	[GCC_WCSS_BCR] = { 0x18000, 0 },
+	[GCC_WCSS_Q6_BCR] = { 0x18100, 0 },
+	[GCC_NSS_BCR] = { 0x19000, 0 },
+	[GCC_SEC_CTRL_BCR] = { 0x1a000, 0 },
+	[GCC_ADSS_BCR] = { 0x1c000, 0 },
+	[GCC_DDRSS_BCR] = { 0x1e000, 0 },
+	[GCC_SYSTEM_NOC_BCR] = { 0x26000, 0 },
+	[GCC_PCNOC_BCR] = { 0x27018, 0 },
+	[GCC_TCSR_BCR] = { 0x28000, 0 },
+	[GCC_QDSS_BCR] = { 0x29000, 0 },
+	[GCC_DCD_BCR] = { 0x2a000, 0 },
+	[GCC_MSG_RAM_BCR] = { 0x2b000, 0 },
+	[GCC_MPM_BCR] = { 0x2c000, 0 },
+	[GCC_SPDM_BCR] = { 0x2f000, 0 },
+	[GCC_RBCPR_BCR] = { 0x33000, 0 },
+	[GCC_RBCPR_MX_BCR] = { 0x33014, 0 },
+	[GCC_TLMM_BCR] = { 0x34000, 0 },
+	[GCC_RBCPR_WCSS_BCR] = { 0x3a000, 0 },
+	[GCC_USB0_PHY_BCR] = { 0x3e034, 0 },
+	[GCC_USB3PHY_0_PHY_BCR] = { 0x3e03c, 0 },
+	[GCC_USB0_BCR] = { 0x3e070, 0 },
+	[GCC_USB1_BCR] = { 0x3f070, 0 },
+	[GCC_QUSB2_0_PHY_BCR] = { 0x4103c, 0 },
+	[GCC_QUSB2_1_PHY_BCR] = { 0x41040, 0 },
+	[GCC_SDCC1_BCR] = { 0x42000, 0 },
+	[GCC_SNOC_BUS_TIMEOUT0_BCR] = { 0x47000, 0 },
+	[GCC_SNOC_BUS_TIMEOUT1_BCR] = { 0x47008, 0 },
+	[GCC_SNOC_BUS_TIMEOUT2_BCR] = { 0x47010, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT0_BCR] = { 0x48000, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT1_BCR] = { 0x48008, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT2_BCR] = { 0x48010, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT3_BCR] = { 0x48018, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT4_BCR] = { 0x48020, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT5_BCR] = { 0x48028, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT6_BCR] = { 0x48030, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT7_BCR] = { 0x48038, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT8_BCR] = { 0x48040, 0 },
+	[GCC_PCNOC_BUS_TIMEOUT9_BCR] = { 0x48048, 0 },
+	[GCC_UNIPHY0_BCR] = { 0x56000, 0 },
+	[GCC_UNIPHY1_BCR] = { 0x56100, 0 },
+	[GCC_CMN_12GPLL_BCR] = { 0x56300, 0 },
+	[GCC_QPIC_BCR] = { 0x57018, 0 },
+	[GCC_MDIO_BCR] = { 0x58000, 0 },
+	[GCC_WCSS_CORE_TBU_BCR] = { 0x66000, 0 },
+	[GCC_WCSS_Q6_TBU_BCR] = { 0x67000, 0 },
+	[GCC_USB0_TBU_BCR] = { 0x6a000, 0 },
+	[GCC_PCIE0_TBU_BCR] = { 0x6b000, 0 },
+	[GCC_NSS_NOC_TBU_BCR] = { 0x6e000, 0 },
+	[GCC_PCIE0_BCR] = { 0x75004, 0 },
+	[GCC_PCIE0_PHY_BCR] = { 0x75038, 0 },
+	[GCC_PCIE0PHY_PHY_BCR] = { 0x7503c, 0 },
+	[GCC_PCIE0_LINK_DOWN_BCR] = { 0x75044, 0 },
+	[GCC_DCC_BCR] = { 0x77000, 0 },
+	[GCC_APC0_VOLTAGE_DROOP_DETECTOR_BCR] = { 0x78000, 0 },
+	[GCC_SMMU_CATS_BCR] = { 0x7c000, 0 },
+	[GCC_UBI0_AXI_ARES] = { 0x68010, 0 },
+	[GCC_UBI0_AHB_ARES] = { 0x68010, 1 },
+	[GCC_UBI0_NC_AXI_ARES] = { 0x68010, 2 },
+	[GCC_UBI0_DBG_ARES] = { 0x68010, 3 },
+	[GCC_UBI0_CORE_CLAMP_ENABLE] = { 0x68010, 4 },
+	[GCC_UBI0_CLKRST_CLAMP_ENABLE] = { 0x68010, 5 },
+	[GCC_UBI0_UTCM_ARES] = { 0x68010, 6 },
+	[GCC_UBI0_CORE_ARES] = { 0x68010, 7 },
+	[GCC_NSS_CFG_ARES] = { 0x68010, 16 },
+	[GCC_NSS_NOC_ARES] = { 0x68010, 18 },
+	[GCC_NSS_CRYPTO_ARES] = { 0x68010, 19 },
+	[GCC_NSS_CSR_ARES] = { 0x68010, 20 },
+	[GCC_NSS_CE_APB_ARES] = { 0x68010, 21 },
+	[GCC_NSS_CE_AXI_ARES] = { 0x68010, 22 },
+	[GCC_NSSNOC_CE_APB_ARES] = { 0x68010, 23 },
+	[GCC_NSSNOC_CE_AXI_ARES] = { 0x68010, 24 },
+	[GCC_NSSNOC_UBI0_AHB_ARES] = { 0x68010, 25 },
+	[GCC_NSSNOC_SNOC_ARES] = { 0x68010, 27 },
+	[GCC_NSSNOC_CRYPTO_ARES] = { 0x68010, 28 },
+	[GCC_NSSNOC_ATB_ARES] = { 0x68010, 29 },
+	[GCC_NSSNOC_QOSGEN_REF_ARES] = { 0x68010, 30 },
+	[GCC_NSSNOC_TIMEOUT_REF_ARES] = { 0x68010, 31 },
+	[GCC_PCIE0_PIPE_ARES] = { 0x75040, 0 },
+	[GCC_PCIE0_SLEEP_ARES] = { 0x75040, 1 },
+	[GCC_PCIE0_CORE_STICKY_ARES] = { 0x75040, 2 },
+	[GCC_PCIE0_AXI_MASTER_ARES] = { 0x75040, 3 },
+	[GCC_PCIE0_AXI_SLAVE_ARES] = { 0x75040, 4 },
+	[GCC_PCIE0_AHB_ARES] = { 0x75040, 5 },
+	[GCC_PCIE0_AXI_MASTER_STICKY_ARES] = { 0x75040, 6 },
+	[GCC_PCIE0_AXI_SLAVE_STICKY_ARES] = { 0x75040, 7 },
+	[GCC_PPE_FULL_RESET] = { 0x68014, 0 },
+	[GCC_UNIPHY0_SOFT_RESET] = { 0x56004, 0 },
+	[GCC_UNIPHY0_XPCS_RESET] = { 0x56004, 2 },
+	[GCC_UNIPHY1_SOFT_RESET] = { 0x56104, 0 },
+	[GCC_UNIPHY1_XPCS_RESET] = { 0x56104, 2 },
+	[GCC_EDMA_HW_RESET] = { 0x68014, 0 },
+	[GCC_NSSPORT1_RESET] = { 0x68014, 0 },
+	[GCC_NSSPORT2_RESET] = { 0x68014, 0 },
+	[GCC_NSSPORT3_RESET] = { 0x68014, 0 },
+	[GCC_NSSPORT4_RESET] = { 0x68014, 0 },
+	[GCC_NSSPORT5_RESET] = { 0x68014, 0 },
+	[GCC_UNIPHY0_PORT1_ARES] = { 0x56004, 0 },
+	[GCC_UNIPHY0_PORT2_ARES] = { 0x56004, 0 },
+	[GCC_UNIPHY0_PORT3_ARES] = { 0x56004, 0 },
+	[GCC_UNIPHY0_PORT4_ARES] = { 0x56004, 0 },
+	[GCC_UNIPHY0_PORT5_ARES] = { 0x56004, 0 },
+	[GCC_UNIPHY0_PORT_4_5_RESET] = { 0x56004, 0 },
+	[GCC_UNIPHY0_PORT_4_RESET] = { 0x56004, 0 },
+	[GCC_LPASS_BCR] = {0x1F000, 0},
+	[GCC_UBI32_TBU_BCR] = {0x65000, 0},
+	[GCC_LPASS_TBU_BCR] = {0x6C000, 0},
+	[GCC_WCSSAON_RESET] = {0x59010, 0},
+	[GCC_LPASS_Q6_AXIM_ARES] = {0x1F004, 0},
+	[GCC_LPASS_Q6SS_TSCTR_1TO2_ARES] = {0x1F004, 1},
+	[GCC_LPASS_Q6SS_TRIG_ARES] = {0x1F004, 2},
+	[GCC_LPASS_Q6_ATBM_AT_ARES] = {0x1F004, 3},
+	[GCC_LPASS_Q6_PCLKDBG_ARES] = {0x1F004, 4},
+	[GCC_LPASS_CORE_AXIM_ARES] = {0x1F004, 5},
+	[GCC_LPASS_SNOC_CFG_ARES] = {0x1F004, 6},
+	[GCC_WCSS_DBG_ARES] = {0x59008, 0},
+	[GCC_WCSS_ECAHB_ARES] = {0x59008, 1},
+	[GCC_WCSS_ACMT_ARES] = {0x59008, 2},
+	[GCC_WCSS_DBG_BDG_ARES] = {0x59008, 3},
+	[GCC_WCSS_AHB_S_ARES] = {0x59008, 4},
+	[GCC_WCSS_AXI_M_ARES] = {0x59008, 5},
+	[GCC_Q6SS_DBG_ARES] = {0x59110, 0},
+	[GCC_Q6_AHB_S_ARES] = {0x59110, 1},
+	[GCC_Q6_AHB_ARES] = {0x59110, 2},
+	[GCC_Q6_AXIM2_ARES] = {0x59110, 3},
+	[GCC_Q6_AXIM_ARES] = {0x59110, 4},
+};
+
+static const struct of_device_id gcc_ipq6018_match_table[] = {
+	{ .compatible = "qcom,gcc-ipq6018" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gcc_ipq6018_match_table);
+
+static const struct regmap_config gcc_ipq6018_regmap_config = {
+	.reg_bits       = 32,
+	.reg_stride     = 4,
+	.val_bits       = 32,
+	.max_register   = 0x7fffc,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc gcc_ipq6018_desc = {
+	.config = &gcc_ipq6018_regmap_config,
+	.clks = gcc_ipq6018_clks,
+	.num_clks = ARRAY_SIZE(gcc_ipq6018_clks),
+	.resets = gcc_ipq6018_resets,
+	.num_resets = ARRAY_SIZE(gcc_ipq6018_resets),
+	.clk_hws = gcc_ipq6018_hws,
+	.num_clk_hws = ARRAY_SIZE(gcc_ipq6018_hws),
+};
+
+static int gcc_ipq6018_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+
+	regmap = qcom_cc_map(pdev, &gcc_ipq6018_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* Disable SW_COLLAPSE for USB0 GDSCR */
+	regmap_update_bits(regmap, 0x3e078, BIT(0), 0x0);
+	/* Enable SW_OVERRIDE for USB0 GDSCR */
+	regmap_update_bits(regmap, 0x3e078, BIT(2), BIT(2));
+	/* Disable SW_COLLAPSE for USB1 GDSCR */
+	regmap_update_bits(regmap, 0x3f078, BIT(0), 0x0);
+	/* Enable SW_OVERRIDE for USB1 GDSCR */
+	regmap_update_bits(regmap, 0x3f078, BIT(2), BIT(2));
+
+	/* SW Workaround for UBI Huyara PLL */
+	regmap_update_bits(regmap, 0x2501c, BIT(26), BIT(26));
+
+	clk_alpha_pll_configure(&ubi32_pll_main, regmap, &ubi32_pll_config);
+
+	clk_alpha_pll_configure(&nss_crypto_pll_main, regmap,
+				&nss_crypto_pll_config);
+
+	return qcom_cc_really_probe(pdev, &gcc_ipq6018_desc, regmap);
+}
+
+static struct platform_driver gcc_ipq6018_driver = {
+	.probe = gcc_ipq6018_probe,
+	.driver = {
+		.name   = "qcom,gcc-ipq6018",
+		.of_match_table = gcc_ipq6018_match_table,
+	},
+};
+
+static int __init gcc_ipq6018_init(void)
+{
+	return platform_driver_register(&gcc_ipq6018_driver);
+}
+core_initcall(gcc_ipq6018_init);
+
+static void __exit gcc_ipq6018_exit(void)
+{
+	platform_driver_unregister(&gcc_ipq6018_driver);
+}
+module_exit(gcc_ipq6018_exit);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. GCC IPQ6018 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index d004cdaa0e39..3c3a7ff04562 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -3046,7 +3046,10 @@ static struct clk_branch gcc_usb3_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_usb3_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
@@ -3060,7 +3063,10 @@ static struct clk_branch gcc_hdmi_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_hdmi_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
@@ -3074,7 +3080,10 @@ static struct clk_branch gcc_edp_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_edp_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
@@ -3088,7 +3097,10 @@ static struct clk_branch gcc_ufs_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_ufs_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
@@ -3102,7 +3114,10 @@ static struct clk_branch gcc_pcie_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_pcie_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
@@ -3116,7 +3131,10 @@ static struct clk_branch gcc_rx2_usb2_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_rx2_usb2_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
@@ -3130,7 +3148,10 @@ static struct clk_branch gcc_rx1_usb2_clkref_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_rx1_usb2_clkref_clk",
-			.parent_names = (const char *[]){ "xo" },
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "cxo2",
+				.name = "xo",
+			},
 			.num_parents = 1,
 			.ops = &clk_branch2_ops,
 		},
diff --git a/drivers/clk/qcom/gcc-msm8998.c b/drivers/clk/qcom/gcc-msm8998.c
index cf31b5d03270..df1d7056436c 100644
--- a/drivers/clk/qcom/gcc-msm8998.c
+++ b/drivers/clk/qcom/gcc-msm8998.c
@@ -1996,6 +1996,19 @@ static struct clk_branch gcc_gp3_clk = {
 	},
 };
 
+static struct clk_branch gcc_bimc_gfx_clk = {
+	.halt_reg = 0x46040,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x46040,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_bimc_gfx_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct clk_branch gcc_gpu_bimc_gfx_clk = {
 	.halt_reg = 0x71010,
 	.halt_check = BRANCH_HALT,
@@ -2810,6 +2823,7 @@ static struct clk_regmap *gcc_msm8998_clocks[] = {
 	[GCC_GP1_CLK] = &gcc_gp1_clk.clkr,
 	[GCC_GP2_CLK] = &gcc_gp2_clk.clkr,
 	[GCC_GP3_CLK] = &gcc_gp3_clk.clkr,
+	[GCC_BIMC_GFX_CLK] = &gcc_bimc_gfx_clk.clkr,
 	[GCC_GPU_BIMC_GFX_CLK] = &gcc_gpu_bimc_gfx_clk.clkr,
 	[GCC_GPU_BIMC_GFX_SRC_CLK] = &gcc_gpu_bimc_gfx_src_clk.clkr,
 	[GCC_GPU_CFG_AHB_CLK] = &gcc_gpu_cfg_ahb_clk.clkr,
diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c
index 9b0c4ce2ef4e..46d314d69250 100644
--- a/drivers/clk/qcom/gcc-qcs404.c
+++ b/drivers/clk/qcom/gcc-qcs404.c
@@ -330,7 +330,7 @@ static struct clk_alpha_pll gpll0_ao_out_main = {
 			.parent_names = (const char *[]){ "cxo" },
 			.num_parents = 1,
 			.flags = CLK_IS_CRITICAL,
-			.ops = &clk_alpha_pll_ops,
+			.ops = &clk_alpha_pll_fixed_ops,
 		},
 	},
 };
diff --git a/drivers/clk/qcom/gpucc-sc7180.c b/drivers/clk/qcom/gpucc-sc7180.c
new file mode 100644
index 000000000000..ec61194cceaf
--- /dev/null
+++ b/drivers/clk/qcom/gpucc-sc7180.c
@@ -0,0 +1,266 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,gpucc-sc7180.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "common.h"
+#include "gdsc.h"
+
+#define CX_GMU_CBCR_SLEEP_MASK		0xF
+#define CX_GMU_CBCR_SLEEP_SHIFT		4
+#define CX_GMU_CBCR_WAKE_MASK		0xF
+#define CX_GMU_CBCR_WAKE_SHIFT		8
+#define CLK_DIS_WAIT_SHIFT		12
+#define CLK_DIS_WAIT_MASK		(0xf << CLK_DIS_WAIT_SHIFT)
+
+enum {
+	P_BI_TCXO,
+	P_CORE_BI_PLL_TEST_SE,
+	P_GPLL0_OUT_MAIN,
+	P_GPLL0_OUT_MAIN_DIV,
+	P_GPU_CC_PLL1_OUT_EVEN,
+	P_GPU_CC_PLL1_OUT_MAIN,
+	P_GPU_CC_PLL1_OUT_ODD,
+};
+
+static const struct pll_vco fabia_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static struct clk_alpha_pll gpu_cc_pll1 = {
+	.offset = 0x100,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_pll1",
+			.parent_data =  &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+static const struct parent_map gpu_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_GPU_CC_PLL1_OUT_MAIN, 3 },
+	{ P_GPLL0_OUT_MAIN, 5 },
+	{ P_GPLL0_OUT_MAIN_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data gpu_cc_parent_data_0[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &gpu_cc_pll1.clkr.hw },
+	{ .fw_name = "gcc_gpu_gpll0_clk_src" },
+	{ .fw_name = "gcc_gpu_gpll0_div_clk_src" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct freq_tbl ftbl_gpu_cc_gmu_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN_DIV, 1.5, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 gpu_cc_gmu_clk_src = {
+	.cmd_rcgr = 0x1120,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = gpu_cc_parent_map_0,
+	.freq_tbl = ftbl_gpu_cc_gmu_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "gpu_cc_gmu_clk_src",
+		.parent_data = gpu_cc_parent_data_0,
+		.num_parents = 5,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_branch gpu_cc_crc_ahb_clk = {
+	.halt_reg = 0x107c,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x107c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_crc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_gmu_clk = {
+	.halt_reg = 0x1098,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x1098,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_gmu_clk",
+			.parent_data =  &(const struct clk_parent_data){
+				.hw = &gpu_cc_gmu_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cx_snoc_dvm_clk = {
+	.halt_reg = 0x108c,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x108c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cx_snoc_dvm_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cxo_aon_clk = {
+	.halt_reg = 0x1004,
+	.halt_check = BRANCH_HALT_DELAY,
+	.clkr = {
+		.enable_reg = 0x1004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cxo_aon_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gpu_cc_cxo_clk = {
+	.halt_reg = 0x109c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x109c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gpu_cc_cxo_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc cx_gdsc = {
+	.gdscr = 0x106c,
+	.gds_hw_ctrl = 0x1540,
+	.pd = {
+		.name = "cx_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = VOTABLE,
+};
+
+static struct gdsc *gpu_cc_sc7180_gdscs[] = {
+	[CX_GDSC] = &cx_gdsc,
+};
+
+static struct clk_regmap *gpu_cc_sc7180_clocks[] = {
+	[GPU_CC_CXO_CLK] = &gpu_cc_cxo_clk.clkr,
+	[GPU_CC_CRC_AHB_CLK] = &gpu_cc_crc_ahb_clk.clkr,
+	[GPU_CC_CX_GMU_CLK] = &gpu_cc_cx_gmu_clk.clkr,
+	[GPU_CC_CX_SNOC_DVM_CLK] = &gpu_cc_cx_snoc_dvm_clk.clkr,
+	[GPU_CC_CXO_AON_CLK] = &gpu_cc_cxo_aon_clk.clkr,
+	[GPU_CC_GMU_CLK_SRC] = &gpu_cc_gmu_clk_src.clkr,
+	[GPU_CC_PLL1] = &gpu_cc_pll1.clkr,
+};
+
+static const struct regmap_config gpu_cc_sc7180_regmap_config = {
+	.reg_bits =	32,
+	.reg_stride =	4,
+	.val_bits =	32,
+	.max_register =	0x8008,
+	.fast_io =	true,
+};
+
+static const struct qcom_cc_desc gpu_cc_sc7180_desc = {
+	.config = &gpu_cc_sc7180_regmap_config,
+	.clks = gpu_cc_sc7180_clocks,
+	.num_clks = ARRAY_SIZE(gpu_cc_sc7180_clocks),
+	.gdscs = gpu_cc_sc7180_gdscs,
+	.num_gdscs = ARRAY_SIZE(gpu_cc_sc7180_gdscs),
+};
+
+static const struct of_device_id gpu_cc_sc7180_match_table[] = {
+	{ .compatible = "qcom,sc7180-gpucc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, gpu_cc_sc7180_match_table);
+
+static int gpu_cc_sc7180_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	struct alpha_pll_config gpu_cc_pll_config = {};
+	unsigned int value, mask;
+
+	regmap = qcom_cc_map(pdev, &gpu_cc_sc7180_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	/* 360MHz Configuration */
+	gpu_cc_pll_config.l = 0x12;
+	gpu_cc_pll_config.alpha = 0xc000;
+	gpu_cc_pll_config.config_ctl_val = 0x20485699;
+	gpu_cc_pll_config.config_ctl_hi_val = 0x00002067;
+	gpu_cc_pll_config.user_ctl_val = 0x00000001;
+	gpu_cc_pll_config.user_ctl_hi_val = 0x00004805;
+	gpu_cc_pll_config.test_ctl_hi_val = 0x40000000;
+
+	clk_fabia_pll_configure(&gpu_cc_pll1, regmap, &gpu_cc_pll_config);
+
+	/* Recommended WAKEUP/SLEEP settings for the gpu_cc_cx_gmu_clk */
+	mask = CX_GMU_CBCR_WAKE_MASK << CX_GMU_CBCR_WAKE_SHIFT;
+	mask |= CX_GMU_CBCR_SLEEP_MASK << CX_GMU_CBCR_SLEEP_SHIFT;
+	value = 0xF << CX_GMU_CBCR_WAKE_SHIFT | 0xF << CX_GMU_CBCR_SLEEP_SHIFT;
+	regmap_update_bits(regmap, 0x1098, mask, value);
+
+	/* Configure clk_dis_wait for gpu_cx_gdsc */
+	regmap_update_bits(regmap, 0x106c, CLK_DIS_WAIT_MASK,
+						8 << CLK_DIS_WAIT_SHIFT);
+
+	return qcom_cc_really_probe(pdev, &gpu_cc_sc7180_desc, regmap);
+}
+
+static struct platform_driver gpu_cc_sc7180_driver = {
+	.probe = gpu_cc_sc7180_probe,
+	.driver = {
+		.name = "sc7180-gpucc",
+		.of_match_table = gpu_cc_sc7180_match_table,
+	},
+};
+
+static int __init gpu_cc_sc7180_init(void)
+{
+	return platform_driver_register(&gpu_cc_sc7180_driver);
+}
+subsys_initcall(gpu_cc_sc7180_init);
+
+static void __exit gpu_cc_sc7180_exit(void)
+{
+	platform_driver_unregister(&gpu_cc_sc7180_driver);
+}
+module_exit(gpu_cc_sc7180_exit);
+
+MODULE_DESCRIPTION("QTI GPU_CC SC7180 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/hfpll.c b/drivers/clk/qcom/hfpll.c
index a6de7101430c..5ff7f5a60620 100644
--- a/drivers/clk/qcom/hfpll.c
+++ b/drivers/clk/qcom/hfpll.c
@@ -53,10 +53,18 @@ static int qcom_hfpll_probe(struct platform_device *pdev)
 	struct regmap *regmap;
 	struct clk_hfpll *h;
 	struct clk_init_data init = {
-		.parent_names = (const char *[]){ "xo" },
 		.num_parents = 1,
 		.ops = &clk_ops_hfpll,
+		/*
+		 * rather than marking the clock critical and forcing the clock
+		 * to be always enabled, we make sure that the clock is not
+		 * disabled: the firmware remains responsible of enabling this
+		 * clock (for more info check the commit log)
+		 */
+		.flags = CLK_IGNORE_UNUSED,
 	};
+	int ret;
+	struct clk_parent_data pdata = { .index = 0 };
 
 	h = devm_kzalloc(dev, sizeof(*h), GFP_KERNEL);
 	if (!h)
@@ -75,11 +83,20 @@ static int qcom_hfpll_probe(struct platform_device *pdev)
 					  0, &init.name))
 		return -ENODEV;
 
+	init.parent_data = &pdata;
+
 	h->d = &hdata;
 	h->clkr.hw.init = &init;
 	spin_lock_init(&h->lock);
 
-	return devm_clk_register_regmap(&pdev->dev, &h->clkr);
+	ret = devm_clk_register_regmap(dev, &h->clkr);
+	if (ret) {
+		dev_err(dev, "failed to register regmap clock: %d\n", ret);
+		return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+					   &h->clkr.hw);
 }
 
 static struct platform_driver qcom_hfpll_driver = {
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index bcb0a397ef91..015426262d08 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -452,18 +452,6 @@ static struct clk_rcg2 mdp_clk_src = {
 	},
 };
 
-static struct clk_rcg2 gfx3d_clk_src = {
-	.cmd_rcgr = 0x4000,
-	.hid_width = 5,
-	.parent_map = mmcc_xo_mmpll0_1_2_gpll0_map,
-	.clkr.hw.init = &(struct clk_init_data){
-		.name = "gfx3d_clk_src",
-		.parent_names = mmcc_xo_mmpll0_1_2_gpll0,
-		.num_parents = 5,
-		.ops = &clk_rcg2_ops,
-	},
-};
-
 static struct freq_tbl ftbl_camss_jpeg_jpeg0_2_clk[] = {
 	F(75000000, P_GPLL0, 8, 0, 0),
 	F(133330000, P_GPLL0, 4.5, 0, 0),
@@ -2411,7 +2399,6 @@ static struct clk_regmap *mmcc_msm8974_clocks[] = {
 	[VFE0_CLK_SRC] = &vfe0_clk_src.clkr,
 	[VFE1_CLK_SRC] = &vfe1_clk_src.clkr,
 	[MDP_CLK_SRC] = &mdp_clk_src.clkr,
-	[GFX3D_CLK_SRC] = &gfx3d_clk_src.clkr,
 	[JPEG0_CLK_SRC] = &jpeg0_clk_src.clkr,
 	[JPEG1_CLK_SRC] = &jpeg1_clk_src.clkr,
 	[JPEG2_CLK_SRC] = &jpeg2_clk_src.clkr,
diff --git a/drivers/clk/qcom/mmcc-msm8998.c b/drivers/clk/qcom/mmcc-msm8998.c
new file mode 100644
index 000000000000..dd68983fe22e
--- /dev/null
+++ b/drivers/clk/qcom/mmcc-msm8998.c
@@ -0,0 +1,2913 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/clk-provider.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/clock/qcom,mmcc-msm8998.h>
+
+#include "common.h"
+#include "clk-regmap.h"
+#include "clk-regmap-divider.h"
+#include "clk-alpha-pll.h"
+#include "clk-rcg.h"
+#include "clk-branch.h"
+#include "reset.h"
+#include "gdsc.h"
+
+enum {
+	P_XO,
+	P_GPLL0,
+	P_GPLL0_DIV,
+	P_MMPLL0_OUT_EVEN,
+	P_MMPLL1_OUT_EVEN,
+	P_MMPLL3_OUT_EVEN,
+	P_MMPLL4_OUT_EVEN,
+	P_MMPLL5_OUT_EVEN,
+	P_MMPLL6_OUT_EVEN,
+	P_MMPLL7_OUT_EVEN,
+	P_MMPLL10_OUT_EVEN,
+	P_DSI0PLL,
+	P_DSI1PLL,
+	P_DSI0PLL_BYTE,
+	P_DSI1PLL_BYTE,
+	P_HDMIPLL,
+	P_DPVCO,
+	P_DPLINK,
+	P_CORE_BI_PLL_TEST_SE,
+};
+
+static struct clk_fixed_factor gpll0_div = {
+	.mult = 1,
+	.div = 2,
+	.hw.init = &(struct clk_init_data){
+		.name = "mmss_gpll0_div",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "gpll0",
+			.name = "gpll0"
+		},
+		.num_parents = 1,
+		.ops = &clk_fixed_factor_ops,
+	},
+};
+
+static const struct clk_div_table post_div_table_fabia_even[] = {
+	{ 0x0, 1 },
+	{ 0x1, 2 },
+	{ 0x3, 4 },
+	{ 0x7, 8 },
+	{ }
+};
+
+static struct clk_alpha_pll mmpll0 = {
+	.offset = 0xc000,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.enable_reg = 0x1e0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmpll0",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+				.name = "xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fixed_fabia_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll0_out_even = {
+	.offset = 0xc000,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll0_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll0.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll1 = {
+	.offset = 0xc050,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.enable_reg = 0x1e0,
+		.enable_mask = BIT(1),
+		.hw.init = &(struct clk_init_data){
+			.name = "mmpll1",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "xo",
+				.name = "xo"
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fixed_fabia_ops,
+		},
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll1_out_even = {
+	.offset = 0xc050,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll1_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll1.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll3 = {
+	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll3",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "xo",
+			.name = "xo"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_fixed_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll3_out_even = {
+	.offset = 0x0,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll3_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll3.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll4 = {
+	.offset = 0x50,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll4",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "xo",
+			.name = "xo"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_fixed_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll4_out_even = {
+	.offset = 0x50,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll4_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll4.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll5 = {
+	.offset = 0xa0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll5",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "xo",
+			.name = "xo"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_fixed_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll5_out_even = {
+	.offset = 0xa0,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll5_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll5.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll6 = {
+	.offset = 0xf0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll6",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "xo",
+			.name = "xo"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_fixed_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll6_out_even = {
+	.offset = 0xf0,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll6_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll6.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll7 = {
+	.offset = 0x140,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll7",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "xo",
+			.name = "xo"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_fixed_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll7_out_even = {
+	.offset = 0x140,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll7_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll7.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll mmpll10 = {
+	.offset = 0x190,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll10",
+		.parent_data = &(const struct clk_parent_data){
+			.fw_name = "xo",
+			.name = "xo"
+		},
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_fixed_fabia_ops,
+	},
+};
+
+static struct clk_alpha_pll_postdiv mmpll10_out_even = {
+	.offset = 0x190,
+	.post_div_shift = 8,
+	.post_div_table = post_div_table_fabia_even,
+	.num_post_div = ARRAY_SIZE(post_div_table_fabia_even),
+	.width = 4,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mmpll10_out_even",
+		.parent_hws = (const struct clk_hw *[]){ &mmpll10.clkr.hw },
+		.num_parents = 1,
+		.ops = &clk_alpha_pll_postdiv_fabia_ops,
+	},
+};
+
+static const struct parent_map mmss_xo_hdmi_map[] = {
+	{ P_XO, 0 },
+	{ P_HDMIPLL, 1 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_hdmi[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .fw_name = "hdmipll", .name = "hdmipll" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_dsi0pll_dsi1pll_map[] = {
+	{ P_XO, 0 },
+	{ P_DSI0PLL, 1 },
+	{ P_DSI1PLL, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_dsi0pll_dsi1pll[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .fw_name = "dsi0dsi", .name = "dsi0dsi" },
+	{ .fw_name = "dsi1dsi", .name = "dsi1dsi" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_dsibyte_map[] = {
+	{ P_XO, 0 },
+	{ P_DSI0PLL_BYTE, 1 },
+	{ P_DSI1PLL_BYTE, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_dsibyte[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .fw_name = "dsi0byte", .name = "dsi0byte" },
+	{ .fw_name = "dsi1byte", .name = "dsi1byte" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_dp_map[] = {
+	{ P_XO, 0 },
+	{ P_DPLINK, 1 },
+	{ P_DPVCO, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_dp[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .fw_name = "dplink", .name = "dplink" },
+	{ .fw_name = "dpvco", .name = "dpvco" },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll0_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL0_OUT_EVEN, 1 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll0_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll0_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll0_mmpll1_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL0_OUT_EVEN, 1 },
+	{ P_MMPLL1_OUT_EVEN, 2 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll0_mmpll1_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll0_out_even.clkr.hw },
+	{ .hw = &mmpll1_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll0_mmpll5_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL0_OUT_EVEN, 1 },
+	{ P_MMPLL5_OUT_EVEN, 2 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll0_mmpll5_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll0_out_even.clkr.hw },
+	{ .hw = &mmpll5_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL0_OUT_EVEN, 1 },
+	{ P_MMPLL3_OUT_EVEN, 3 },
+	{ P_MMPLL6_OUT_EVEN, 4 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll0_out_even.clkr.hw },
+	{ .hw = &mmpll3_out_even.clkr.hw },
+	{ .hw = &mmpll6_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL4_OUT_EVEN, 1 },
+	{ P_MMPLL7_OUT_EVEN, 2 },
+	{ P_MMPLL10_OUT_EVEN, 3 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll4_out_even.clkr.hw },
+	{ .hw = &mmpll7_out_even.clkr.hw },
+	{ .hw = &mmpll10_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll0_mmpll7_mmpll10_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL0_OUT_EVEN, 1 },
+	{ P_MMPLL7_OUT_EVEN, 2 },
+	{ P_MMPLL10_OUT_EVEN, 3 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll0_mmpll7_mmpll10_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll0_out_even.clkr.hw },
+	{ .hw = &mmpll7_out_even.clkr.hw },
+	{ .hw = &mmpll10_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct parent_map mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map[] = {
+	{ P_XO, 0 },
+	{ P_MMPLL0_OUT_EVEN, 1 },
+	{ P_MMPLL4_OUT_EVEN, 2 },
+	{ P_MMPLL7_OUT_EVEN, 3 },
+	{ P_MMPLL10_OUT_EVEN, 4 },
+	{ P_GPLL0, 5 },
+	{ P_GPLL0_DIV, 6 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 }
+};
+
+static const struct clk_parent_data mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div[] = {
+	{ .fw_name = "xo", .name = "xo" },
+	{ .hw = &mmpll0_out_even.clkr.hw },
+	{ .hw = &mmpll4_out_even.clkr.hw },
+	{ .hw = &mmpll7_out_even.clkr.hw },
+	{ .hw = &mmpll10_out_even.clkr.hw },
+	{ .fw_name = "gpll0", .name = "gpll0" },
+	{ .hw = &gpll0_div.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static struct clk_rcg2 byte0_clk_src = {
+	.cmd_rcgr = 0x2120,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dsibyte_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "byte0_clk_src",
+		.parent_data = mmss_xo_dsibyte,
+		.num_parents = 4,
+		.ops = &clk_byte2_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_rcg2 byte1_clk_src = {
+	.cmd_rcgr = 0x2140,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dsibyte_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "byte1_clk_src",
+		.parent_data = mmss_xo_dsibyte,
+		.num_parents = 4,
+		.ops = &clk_byte2_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_cci_clk_src[] = {
+	F(37500000, P_GPLL0, 16, 0, 0),
+	F(50000000, P_GPLL0, 12, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cci_clk_src = {
+	.cmd_rcgr = 0x3300,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_cci_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cci_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_cpp_clk_src[] = {
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(384000000, P_MMPLL4_OUT_EVEN, 2, 0, 0),
+	F(404000000, P_MMPLL0_OUT_EVEN, 2, 0, 0),
+	F(480000000, P_MMPLL7_OUT_EVEN, 2, 0, 0),
+	F(576000000, P_MMPLL10_OUT_EVEN, 1, 0, 0),
+	F(600000000, P_GPLL0, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 cpp_clk_src = {
+	.cmd_rcgr = 0x3640,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_cpp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "cpp_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_csi_clk_src[] = {
+	F(164571429, P_MMPLL10_OUT_EVEN, 3.5, 0, 0),
+	F(256000000, P_MMPLL4_OUT_EVEN, 3, 0, 0),
+	F(274290000, P_MMPLL7_OUT_EVEN, 3.5, 0, 0),
+	F(300000000, P_GPLL0, 2, 0, 0),
+	F(384000000, P_MMPLL4_OUT_EVEN, 2, 0, 0),
+	F(576000000, P_MMPLL10_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 csi0_clk_src = {
+	.cmd_rcgr = 0x3090,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi0_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi1_clk_src = {
+	.cmd_rcgr = 0x3100,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi1_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi2_clk_src = {
+	.cmd_rcgr = 0x3160,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi2_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi3_clk_src = {
+	.cmd_rcgr = 0x31c0,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi3_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_csiphy_clk_src[] = {
+	F(164571429, P_MMPLL10_OUT_EVEN, 3.5, 0, 0),
+	F(256000000, P_MMPLL4_OUT_EVEN, 3, 0, 0),
+	F(274290000, P_MMPLL7_OUT_EVEN, 3.5, 0, 0),
+	F(300000000, P_GPLL0, 2, 0, 0),
+	F(384000000, P_MMPLL4_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 csiphy_clk_src = {
+	.cmd_rcgr = 0x3800,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csiphy_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csiphy_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_csiphytimer_clk_src[] = {
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(269333333, P_MMPLL0_OUT_EVEN, 3, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 csi0phytimer_clk_src = {
+	.cmd_rcgr = 0x3000,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csiphytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi0phytimer_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi1phytimer_clk_src = {
+	.cmd_rcgr = 0x3030,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csiphytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi1phytimer_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 csi2phytimer_clk_src = {
+	.cmd_rcgr = 0x3060,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_csiphytimer_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "csi2phytimer_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_dp_aux_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 dp_aux_clk_src = {
+	.cmd_rcgr = 0x2260,
+	.hid_width = 5,
+	.parent_map = mmss_xo_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_dp_aux_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "dp_aux_clk_src",
+		.parent_data = mmss_xo_gpll0_gpll0_div,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_dp_crypto_clk_src[] = {
+	F(101250, P_DPLINK, 1, 5, 16),
+	F(168750, P_DPLINK, 1, 5, 16),
+	F(337500, P_DPLINK, 1, 5, 16),
+	{ }
+};
+
+static struct clk_rcg2 dp_crypto_clk_src = {
+	.cmd_rcgr = 0x2220,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dp_map,
+	.freq_tbl = ftbl_dp_crypto_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "dp_crypto_clk_src",
+		.parent_data = mmss_xo_dp,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_dp_link_clk_src[] = {
+	F(162000, P_DPLINK, 2, 0, 0),
+	F(270000, P_DPLINK, 2, 0, 0),
+	F(540000, P_DPLINK, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 dp_link_clk_src = {
+	.cmd_rcgr = 0x2200,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dp_map,
+	.freq_tbl = ftbl_dp_link_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "dp_link_clk_src",
+		.parent_data = mmss_xo_dp,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_dp_pixel_clk_src[] = {
+	F(154000000, P_DPVCO, 1, 0, 0),
+	F(337500000, P_DPVCO, 2, 0, 0),
+	F(675000000, P_DPVCO, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 dp_pixel_clk_src = {
+	.cmd_rcgr = 0x2240,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dp_map,
+	.freq_tbl = ftbl_dp_pixel_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "dp_pixel_clk_src",
+		.parent_data = mmss_xo_dp,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_esc_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 esc0_clk_src = {
+	.cmd_rcgr = 0x2160,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dsibyte_map,
+	.freq_tbl = ftbl_esc_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "esc0_clk_src",
+		.parent_data = mmss_xo_dsibyte,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 esc1_clk_src = {
+	.cmd_rcgr = 0x2180,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dsibyte_map,
+	.freq_tbl = ftbl_esc_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "esc1_clk_src",
+		.parent_data = mmss_xo_dsibyte,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_extpclk_clk_src[] = {
+	{ .src = P_HDMIPLL },
+	{ }
+};
+
+static struct clk_rcg2 extpclk_clk_src = {
+	.cmd_rcgr = 0x2060,
+	.hid_width = 5,
+	.parent_map = mmss_xo_hdmi_map,
+	.freq_tbl = ftbl_extpclk_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "extpclk_clk_src",
+		.parent_data = mmss_xo_hdmi,
+		.num_parents = 3,
+		.ops = &clk_byte_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_fd_core_clk_src[] = {
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(404000000, P_MMPLL0_OUT_EVEN, 2, 0, 0),
+	F(480000000, P_MMPLL7_OUT_EVEN, 2, 0, 0),
+	F(576000000, P_MMPLL10_OUT_EVEN, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 fd_core_clk_src = {
+	.cmd_rcgr = 0x3b00,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_fd_core_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "fd_core_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_hdmi_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 hdmi_clk_src = {
+	.cmd_rcgr = 0x2100,
+	.hid_width = 5,
+	.parent_map = mmss_xo_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_hdmi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "hdmi_clk_src",
+		.parent_data = mmss_xo_gpll0_gpll0_div,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_jpeg0_clk_src[] = {
+	F(75000000, P_GPLL0, 8, 0, 0),
+	F(150000000, P_GPLL0, 4, 0, 0),
+	F(320000000, P_MMPLL7_OUT_EVEN, 3, 0, 0),
+	F(480000000, P_MMPLL7_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 jpeg0_clk_src = {
+	.cmd_rcgr = 0x3500,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_jpeg0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "jpeg0_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_maxi_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(75000000, P_GPLL0_DIV, 4, 0, 0),
+	F(171428571, P_GPLL0, 3.5, 0, 0),
+	F(323200000, P_MMPLL0_OUT_EVEN, 2.5, 0, 0),
+	F(406000000, P_MMPLL1_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 maxi_clk_src = {
+	.cmd_rcgr = 0xf020,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll1_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_maxi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "maxi_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll1_gpll0_gpll0_div,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_mclk_clk_src[] = {
+	F(4800000, P_XO, 4, 0, 0),
+	F(6000000, P_GPLL0_DIV, 10, 1, 5),
+	F(8000000, P_GPLL0_DIV, 1, 2, 75),
+	F(9600000, P_XO, 2, 0, 0),
+	F(16666667, P_GPLL0_DIV, 2, 1, 9),
+	F(19200000, P_XO, 1, 0, 0),
+	F(24000000, P_GPLL0_DIV, 1, 2, 25),
+	F(33333333, P_GPLL0_DIV, 1, 2, 9),
+	F(48000000, P_GPLL0, 1, 2, 25),
+	F(66666667, P_GPLL0, 1, 2, 9),
+	{ }
+};
+
+static struct clk_rcg2 mclk0_clk_src = {
+	.cmd_rcgr = 0x3360,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_mclk_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk0_clk_src",
+		.parent_data = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 mclk1_clk_src = {
+	.cmd_rcgr = 0x3390,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_mclk_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk1_clk_src",
+		.parent_data = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 mclk2_clk_src = {
+	.cmd_rcgr = 0x33c0,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_mclk_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk2_clk_src",
+		.parent_data = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 mclk3_clk_src = {
+	.cmd_rcgr = 0x33f0,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_mclk_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mclk3_clk_src",
+		.parent_data = mmss_xo_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_mdp_clk_src[] = {
+	F(85714286, P_GPLL0, 7, 0, 0),
+	F(100000000, P_GPLL0, 6, 0, 0),
+	F(150000000, P_GPLL0, 4, 0, 0),
+	F(171428571, P_GPLL0, 3.5, 0, 0),
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(275000000, P_MMPLL5_OUT_EVEN, 3, 0, 0),
+	F(300000000, P_GPLL0, 2, 0, 0),
+	F(330000000, P_MMPLL5_OUT_EVEN, 2.5, 0, 0),
+	F(412500000, P_MMPLL5_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 mdp_clk_src = {
+	.cmd_rcgr = 0x2040,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll5_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_mdp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "mdp_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll5_gpll0_gpll0_div,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_vsync_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vsync_clk_src = {
+	.cmd_rcgr = 0x2080,
+	.hid_width = 5,
+	.parent_map = mmss_xo_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_vsync_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vsync_clk_src",
+		.parent_data = mmss_xo_gpll0_gpll0_div,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_ahb_clk_src[] = {
+	F(19200000, P_XO, 1, 0, 0),
+	F(40000000, P_GPLL0, 15, 0, 0),
+	F(80800000, P_MMPLL0_OUT_EVEN, 10, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 ahb_clk_src = {
+	.cmd_rcgr = 0x5000,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_ahb_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "ahb_clk_src",
+		.parent_data = mmss_xo_mmpll0_gpll0_gpll0_div,
+		.num_parents = 5,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_axi_clk_src[] = {
+	F(75000000, P_GPLL0, 8, 0, 0),
+	F(171428571, P_GPLL0, 3.5, 0, 0),
+	F(240000000, P_GPLL0, 2.5, 0, 0),
+	F(323200000, P_MMPLL0_OUT_EVEN, 2.5, 0, 0),
+	F(406000000, P_MMPLL0_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+/* RO to linux */
+static struct clk_rcg2 axi_clk_src = {
+	.cmd_rcgr = 0xd000,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll1_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_axi_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "axi_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll1_gpll0_gpll0_div,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 pclk0_clk_src = {
+	.cmd_rcgr = 0x2000,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dsi0pll_dsi1pll_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pclk0_clk_src",
+		.parent_data = mmss_xo_dsi0pll_dsi1pll,
+		.num_parents = 4,
+		.ops = &clk_pixel_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_rcg2 pclk1_clk_src = {
+	.cmd_rcgr = 0x2020,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = mmss_xo_dsi0pll_dsi1pll_map,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "pclk1_clk_src",
+		.parent_data = mmss_xo_dsi0pll_dsi1pll,
+		.num_parents = 4,
+		.ops = &clk_pixel_ops,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static const struct freq_tbl ftbl_rot_clk_src[] = {
+	F(171428571, P_GPLL0, 3.5, 0, 0),
+	F(275000000, P_MMPLL5_OUT_EVEN, 3, 0, 0),
+	F(330000000, P_MMPLL5_OUT_EVEN, 2.5, 0, 0),
+	F(412500000, P_MMPLL5_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 rot_clk_src = {
+	.cmd_rcgr = 0x21a0,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll5_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_rot_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "rot_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll5_gpll0_gpll0_div,
+		.num_parents = 6,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_video_core_clk_src[] = {
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(269330000, P_MMPLL0_OUT_EVEN, 3, 0, 0),
+	F(355200000, P_MMPLL6_OUT_EVEN, 2.5, 0, 0),
+	F(444000000, P_MMPLL6_OUT_EVEN, 2, 0, 0),
+	F(533000000, P_MMPLL3_OUT_EVEN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 video_core_clk_src = {
+	.cmd_rcgr = 0x1000,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_video_core_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "video_core_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 video_subcore0_clk_src = {
+	.cmd_rcgr = 0x1060,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_video_core_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "video_subcore0_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 video_subcore1_clk_src = {
+	.cmd_rcgr = 0x1080,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_video_core_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "video_subcore1_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll3_mmpll6_gpll0_gpll0_div,
+		.num_parents = 7,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_vfe_clk_src[] = {
+	F(200000000, P_GPLL0, 3, 0, 0),
+	F(300000000, P_GPLL0, 2, 0, 0),
+	F(320000000, P_MMPLL7_OUT_EVEN, 3, 0, 0),
+	F(384000000, P_MMPLL4_OUT_EVEN, 2, 0, 0),
+	F(404000000, P_MMPLL0_OUT_EVEN, 2, 0, 0),
+	F(480000000, P_MMPLL7_OUT_EVEN, 2, 0, 0),
+	F(576000000, P_MMPLL10_OUT_EVEN, 1, 0, 0),
+	F(600000000, P_GPLL0, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 vfe0_clk_src = {
+	.cmd_rcgr = 0x3600,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_vfe_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vfe0_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 vfe1_clk_src = {
+	.cmd_rcgr = 0x3620,
+	.hid_width = 5,
+	.parent_map = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div_map,
+	.freq_tbl = ftbl_vfe_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "vfe1_clk_src",
+		.parent_data = mmss_xo_mmpll0_mmpll4_mmpll7_mmpll10_gpll0_gpll0_div,
+		.num_parents = 8,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch misc_ahb_clk = {
+	.halt_reg = 0x328,
+	.clkr = {
+		.enable_reg = 0x328,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "misc_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch video_core_clk = {
+	.halt_reg = 0x1028,
+	.clkr = {
+		.enable_reg = 0x1028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_core_clk",
+			.parent_hws = (const struct clk_hw *[]){ &video_core_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch video_ahb_clk = {
+	.halt_reg = 0x1030,
+	.clkr = {
+		.enable_reg = 0x1030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch video_axi_clk = {
+	.halt_reg = 0x1034,
+	.clkr = {
+		.enable_reg = 0x1034,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch video_maxi_clk = {
+	.halt_reg = 0x1038,
+	.clkr = {
+		.enable_reg = 0x1038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_maxi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &maxi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch video_subcore0_clk = {
+	.halt_reg = 0x1048,
+	.clkr = {
+		.enable_reg = 0x1048,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_subcore0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &video_subcore0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch video_subcore1_clk = {
+	.halt_reg = 0x104c,
+	.clkr = {
+		.enable_reg = 0x104c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_subcore1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &video_subcore1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_ahb_clk = {
+	.halt_reg = 0x2308,
+	.clkr = {
+		.enable_reg = 0x2308,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_hdmi_dp_ahb_clk = {
+	.halt_reg = 0x230c,
+	.clkr = {
+		.enable_reg = 0x230c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_hdmi_dp_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_axi_clk = {
+	.halt_reg = 0x2310,
+	.clkr = {
+		.enable_reg = 0x2310,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mdss_pclk0_clk = {
+	.halt_reg = 0x2314,
+	.clkr = {
+		.enable_reg = 0x2314,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_pclk0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &pclk0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_pclk1_clk = {
+	.halt_reg = 0x2318,
+	.clkr = {
+		.enable_reg = 0x2318,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_pclk1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &pclk1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_mdp_clk = {
+	.halt_reg = 0x231c,
+	.clkr = {
+		.enable_reg = 0x231c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_mdp_clk",
+			.parent_hws = (const struct clk_hw *[]){ &mdp_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_mdp_lut_clk = {
+	.halt_reg = 0x2320,
+	.clkr = {
+		.enable_reg = 0x2320,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_mdp_lut_clk",
+			.parent_hws = (const struct clk_hw *[]){ &mdp_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_extpclk_clk = {
+	.halt_reg = 0x2324,
+	.clkr = {
+		.enable_reg = 0x2324,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_extpclk_clk",
+			.parent_hws = (const struct clk_hw *[]){ &extpclk_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_vsync_clk = {
+	.halt_reg = 0x2328,
+	.clkr = {
+		.enable_reg = 0x2328,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_vsync_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vsync_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_hdmi_clk = {
+	.halt_reg = 0x2338,
+	.clkr = {
+		.enable_reg = 0x2338,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_hdmi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &hdmi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_byte0_clk = {
+	.halt_reg = 0x233c,
+	.clkr = {
+		.enable_reg = 0x233c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_byte0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &byte0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_byte1_clk = {
+	.halt_reg = 0x2340,
+	.clkr = {
+		.enable_reg = 0x2340,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_byte1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &byte1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_esc0_clk = {
+	.halt_reg = 0x2344,
+	.clkr = {
+		.enable_reg = 0x2344,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_esc0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &esc0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_esc1_clk = {
+	.halt_reg = 0x2348,
+	.clkr = {
+		.enable_reg = 0x2348,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_esc1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &esc1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_rot_clk = {
+	.halt_reg = 0x2350,
+	.clkr = {
+		.enable_reg = 0x2350,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_rot_clk",
+			.parent_hws = (const struct clk_hw *[]){ &rot_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_dp_link_clk = {
+	.halt_reg = 0x2354,
+	.clkr = {
+		.enable_reg = 0x2354,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_dp_link_clk",
+			.parent_hws = (const struct clk_hw *[]){ &dp_link_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_dp_link_intf_clk = {
+	.halt_reg = 0x2358,
+	.clkr = {
+		.enable_reg = 0x2358,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_dp_link_intf_clk",
+			.parent_hws = (const struct clk_hw *[]){ &dp_link_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_dp_crypto_clk = {
+	.halt_reg = 0x235c,
+	.clkr = {
+		.enable_reg = 0x235c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_dp_crypto_clk",
+			.parent_hws = (const struct clk_hw *[]){ &dp_crypto_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_dp_pixel_clk = {
+	.halt_reg = 0x2360,
+	.clkr = {
+		.enable_reg = 0x2360,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_dp_pixel_clk",
+			.parent_hws = (const struct clk_hw *[]){ &dp_pixel_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_dp_aux_clk = {
+	.halt_reg = 0x2364,
+	.clkr = {
+		.enable_reg = 0x2364,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_dp_aux_clk",
+			.parent_hws = (const struct clk_hw *[]){ &dp_aux_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_byte0_intf_clk = {
+	.halt_reg = 0x2374,
+	.clkr = {
+		.enable_reg = 0x2374,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_byte0_intf_clk",
+			.parent_hws = (const struct clk_hw *[]){ &byte0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mdss_byte1_intf_clk = {
+	.halt_reg = 0x2378,
+	.clkr = {
+		.enable_reg = 0x2378,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mdss_byte1_intf_clk",
+			.parent_hws = (const struct clk_hw *[]){ &byte1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0phytimer_clk = {
+	.halt_reg = 0x3024,
+	.clkr = {
+		.enable_reg = 0x3024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0phytimer_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi0phytimer_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1phytimer_clk = {
+	.halt_reg = 0x3054,
+	.clkr = {
+		.enable_reg = 0x3054,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1phytimer_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi1phytimer_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2phytimer_clk = {
+	.halt_reg = 0x3084,
+	.clkr = {
+		.enable_reg = 0x3084,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2phytimer_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi2phytimer_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0_clk = {
+	.halt_reg = 0x30b4,
+	.clkr = {
+		.enable_reg = 0x30b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0_ahb_clk = {
+	.halt_reg = 0x30bc,
+	.clkr = {
+		.enable_reg = 0x30bc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0rdi_clk = {
+	.halt_reg = 0x30d4,
+	.clkr = {
+		.enable_reg = 0x30d4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0rdi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi0pix_clk = {
+	.halt_reg = 0x30e4,
+	.clkr = {
+		.enable_reg = 0x30e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi0pix_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1_clk = {
+	.halt_reg = 0x3124,
+	.clkr = {
+		.enable_reg = 0x3124,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1_ahb_clk = {
+	.halt_reg = 0x3128,
+	.clkr = {
+		.enable_reg = 0x3128,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1rdi_clk = {
+	.halt_reg = 0x3144,
+	.clkr = {
+		.enable_reg = 0x3144,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1rdi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi1pix_clk = {
+	.halt_reg = 0x3154,
+	.clkr = {
+		.enable_reg = 0x3154,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi1pix_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2_clk = {
+	.halt_reg = 0x3184,
+	.clkr = {
+		.enable_reg = 0x3184,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2_ahb_clk = {
+	.halt_reg = 0x3188,
+	.clkr = {
+		.enable_reg = 0x3188,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2rdi_clk = {
+	.halt_reg = 0x31a4,
+	.clkr = {
+		.enable_reg = 0x31a4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2rdi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi2pix_clk = {
+	.halt_reg = 0x31b4,
+	.clkr = {
+		.enable_reg = 0x31b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi2pix_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3_clk = {
+	.halt_reg = 0x31e4,
+	.clkr = {
+		.enable_reg = 0x31e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi3_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3_ahb_clk = {
+	.halt_reg = 0x31e8,
+	.clkr = {
+		.enable_reg = 0x31e8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3rdi_clk = {
+	.halt_reg = 0x3204,
+	.clkr = {
+		.enable_reg = 0x3204,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3rdi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi3_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi3pix_clk = {
+	.halt_reg = 0x3214,
+	.clkr = {
+		.enable_reg = 0x3214,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi3pix_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csi3_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_ispif_ahb_clk = {
+	.halt_reg = 0x3224,
+	.clkr = {
+		.enable_reg = 0x3224,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_ispif_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cci_clk = {
+	.halt_reg = 0x3344,
+	.clkr = {
+		.enable_reg = 0x3344,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cci_clk",
+			.parent_hws = (const struct clk_hw *[]){ &cci_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cci_ahb_clk = {
+	.halt_reg = 0x3348,
+	.clkr = {
+		.enable_reg = 0x3348,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cci_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk0_clk = {
+	.halt_reg = 0x3384,
+	.clkr = {
+		.enable_reg = 0x3384,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &mclk0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk1_clk = {
+	.halt_reg = 0x33b4,
+	.clkr = {
+		.enable_reg = 0x33b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &mclk1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk2_clk = {
+	.halt_reg = 0x33e4,
+	.clkr = {
+		.enable_reg = 0x33e4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk2_clk",
+			.parent_hws = (const struct clk_hw *[]){ &mclk2_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_mclk3_clk = {
+	.halt_reg = 0x3414,
+	.clkr = {
+		.enable_reg = 0x3414,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_mclk3_clk",
+			.parent_hws = (const struct clk_hw *[]){ &mclk3_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_top_ahb_clk = {
+	.halt_reg = 0x3484,
+	.clkr = {
+		.enable_reg = 0x3484,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_top_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_ahb_clk = {
+	.halt_reg = 0x348c,
+	.clkr = {
+		.enable_reg = 0x348c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_micro_ahb_clk = {
+	.halt_reg = 0x3494,
+	.clkr = {
+		.enable_reg = 0x3494,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_micro_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg0_clk = {
+	.halt_reg = 0x35a8,
+	.clkr = {
+		.enable_reg = 0x35a8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &jpeg0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_ahb_clk = {
+	.halt_reg = 0x35b4,
+	.clkr = {
+		.enable_reg = 0x35b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_jpeg_axi_clk = {
+	.halt_reg = 0x35b8,
+	.clkr = {
+		.enable_reg = 0x35b8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_jpeg_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe0_ahb_clk = {
+	.halt_reg = 0x3668,
+	.clkr = {
+		.enable_reg = 0x3668,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe0_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe1_ahb_clk = {
+	.halt_reg = 0x3678,
+	.clkr = {
+		.enable_reg = 0x3678,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe1_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe0_clk = {
+	.halt_reg = 0x36a8,
+	.clkr = {
+		.enable_reg = 0x36a8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vfe0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe1_clk = {
+	.halt_reg = 0x36ac,
+	.clkr = {
+		.enable_reg = 0x36ac,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vfe1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cpp_clk = {
+	.halt_reg = 0x36b0,
+	.clkr = {
+		.enable_reg = 0x36b0,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cpp_clk",
+			.parent_hws = (const struct clk_hw *[]){ &cpp_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cpp_ahb_clk = {
+	.halt_reg = 0x36b4,
+	.clkr = {
+		.enable_reg = 0x36b4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cpp_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_vbif_ahb_clk = {
+	.halt_reg = 0x36b8,
+	.clkr = {
+		.enable_reg = 0x36b8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_vbif_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe_vbif_axi_clk = {
+	.halt_reg = 0x36bc,
+	.clkr = {
+		.enable_reg = 0x36bc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe_vbif_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_cpp_axi_clk = {
+	.halt_reg = 0x36c4,
+	.clkr = {
+		.enable_reg = 0x36c4,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cpp_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch camss_cpp_vbif_ahb_clk = {
+	.halt_reg = 0x36c8,
+	.clkr = {
+		.enable_reg = 0x36c8,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cpp_vbif_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi_vfe0_clk = {
+	.halt_reg = 0x3704,
+	.clkr = {
+		.enable_reg = 0x3704,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi_vfe0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vfe0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csi_vfe1_clk = {
+	.halt_reg = 0x3714,
+	.clkr = {
+		.enable_reg = 0x3714,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csi_vfe1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vfe1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe0_stream_clk = {
+	.halt_reg = 0x3720,
+	.clkr = {
+		.enable_reg = 0x3720,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe0_stream_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vfe0_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_vfe1_stream_clk = {
+	.halt_reg = 0x3724,
+	.clkr = {
+		.enable_reg = 0x3724,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_vfe1_stream_clk",
+			.parent_hws = (const struct clk_hw *[]){ &vfe1_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cphy_csid0_clk = {
+	.halt_reg = 0x3730,
+	.clkr = {
+		.enable_reg = 0x3730,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cphy_csid0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cphy_csid1_clk = {
+	.halt_reg = 0x3734,
+	.clkr = {
+		.enable_reg = 0x3734,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cphy_csid1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cphy_csid2_clk = {
+	.halt_reg = 0x3738,
+	.clkr = {
+		.enable_reg = 0x3738,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cphy_csid2_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_cphy_csid3_clk = {
+	.halt_reg = 0x373c,
+	.clkr = {
+		.enable_reg = 0x373c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_cphy_csid3_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csiphy0_clk = {
+	.halt_reg = 0x3740,
+	.clkr = {
+		.enable_reg = 0x3740,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csiphy0_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csiphy1_clk = {
+	.halt_reg = 0x3744,
+	.clkr = {
+		.enable_reg = 0x3744,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csiphy1_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch camss_csiphy2_clk = {
+	.halt_reg = 0x3748,
+	.clkr = {
+		.enable_reg = 0x3748,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "camss_csiphy2_clk",
+			.parent_hws = (const struct clk_hw *[]){ &csiphy_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch fd_core_clk = {
+	.halt_reg = 0x3b68,
+	.clkr = {
+		.enable_reg = 0x3b68,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "fd_core_clk",
+			.parent_hws = (const struct clk_hw *[]){ &fd_core_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch fd_core_uar_clk = {
+	.halt_reg = 0x3b6c,
+	.clkr = {
+		.enable_reg = 0x3b6c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "fd_core_uar_clk",
+			.parent_hws = (const struct clk_hw *[]){ &fd_core_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch fd_ahb_clk = {
+	.halt_reg = 0x3b74,
+	.clkr = {
+		.enable_reg = 0x3b74,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "fd_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch mnoc_ahb_clk = {
+	.halt_reg = 0x5024,
+	.clkr = {
+		.enable_reg = 0x5024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mnoc_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch bimc_smmu_ahb_clk = {
+	.halt_reg = 0xe004,
+	.clkr = {
+		.enable_reg = 0xe004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "bimc_smmu_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch bimc_smmu_axi_clk = {
+	.halt_reg = 0xe008,
+	.clkr = {
+		.enable_reg = 0xe008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "bimc_smmu_axi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &axi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch mnoc_maxi_clk = {
+	.halt_reg = 0xf004,
+	.clkr = {
+		.enable_reg = 0xf004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "mnoc_maxi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &maxi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch vmem_maxi_clk = {
+	.halt_reg = 0xf064,
+	.clkr = {
+		.enable_reg = 0xf064,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vmem_maxi_clk",
+			.parent_hws = (const struct clk_hw *[]){ &maxi_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_branch vmem_ahb_clk = {
+	.halt_reg = 0xf068,
+	.clkr = {
+		.enable_reg = 0xf068,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "vmem_ahb_clk",
+			.parent_hws = (const struct clk_hw *[]){ &ahb_clk_src.clkr.hw },
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+			.flags = CLK_SET_RATE_PARENT,
+		},
+	},
+};
+
+static struct clk_hw *mmcc_msm8998_hws[] = {
+	&gpll0_div.hw,
+};
+
+static struct gdsc video_top_gdsc = {
+	.gdscr = 0x1024,
+	.pd = {
+		.name = "video_top",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc video_subcore0_gdsc = {
+	.gdscr = 0x1040,
+	.pd = {
+		.name = "video_subcore0",
+	},
+	.parent = &video_top_gdsc.pd,
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc video_subcore1_gdsc = {
+	.gdscr = 0x1044,
+	.pd = {
+		.name = "video_subcore1",
+	},
+	.parent = &video_top_gdsc.pd,
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc mdss_gdsc = {
+	.gdscr = 0x2304,
+	.cxcs = (unsigned int []){ 0x2310, 0x2350, 0x231c, 0x2320 },
+	.cxc_count = 4,
+	.pd = {
+		.name = "mdss",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc camss_top_gdsc = {
+	.gdscr = 0x34a0,
+	.cxcs = (unsigned int []){ 0x35b8, 0x36c4, 0x3704, 0x3714, 0x3494,
+				   0x35a8, 0x3868 },
+	.cxc_count = 7,
+	.pd = {
+		.name = "camss_top",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc camss_vfe0_gdsc = {
+	.gdscr = 0x3664,
+	.pd = {
+		.name = "camss_vfe0",
+	},
+	.parent = &camss_top_gdsc.pd,
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc camss_vfe1_gdsc = {
+	.gdscr = 0x3674,
+	.pd = {
+		.name = "camss_vfe1_gdsc",
+	},
+	.parent = &camss_top_gdsc.pd,
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc camss_cpp_gdsc = {
+	.gdscr = 0x36d4,
+	.pd = {
+		.name = "camss_cpp",
+	},
+	.parent = &camss_top_gdsc.pd,
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc bimc_smmu_gdsc = {
+	.gdscr = 0xe020,
+	.gds_hw_ctrl = 0xe024,
+	.pd = {
+		.name = "bimc_smmu",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = HW_CTRL,
+};
+
+static struct clk_regmap *mmcc_msm8998_clocks[] = {
+	[MMPLL0] = &mmpll0.clkr,
+	[MMPLL0_OUT_EVEN] = &mmpll0_out_even.clkr,
+	[MMPLL1] = &mmpll1.clkr,
+	[MMPLL1_OUT_EVEN] = &mmpll1_out_even.clkr,
+	[MMPLL3] = &mmpll3.clkr,
+	[MMPLL3_OUT_EVEN] = &mmpll3_out_even.clkr,
+	[MMPLL4] = &mmpll4.clkr,
+	[MMPLL4_OUT_EVEN] = &mmpll4_out_even.clkr,
+	[MMPLL5] = &mmpll5.clkr,
+	[MMPLL5_OUT_EVEN] = &mmpll5_out_even.clkr,
+	[MMPLL6] = &mmpll6.clkr,
+	[MMPLL6_OUT_EVEN] = &mmpll6_out_even.clkr,
+	[MMPLL7] = &mmpll7.clkr,
+	[MMPLL7_OUT_EVEN] = &mmpll7_out_even.clkr,
+	[MMPLL10] = &mmpll10.clkr,
+	[MMPLL10_OUT_EVEN] = &mmpll10_out_even.clkr,
+	[BYTE0_CLK_SRC] = &byte0_clk_src.clkr,
+	[BYTE1_CLK_SRC] = &byte1_clk_src.clkr,
+	[CCI_CLK_SRC] = &cci_clk_src.clkr,
+	[CPP_CLK_SRC] = &cpp_clk_src.clkr,
+	[CSI0_CLK_SRC] = &csi0_clk_src.clkr,
+	[CSI1_CLK_SRC] = &csi1_clk_src.clkr,
+	[CSI2_CLK_SRC] = &csi2_clk_src.clkr,
+	[CSI3_CLK_SRC] = &csi3_clk_src.clkr,
+	[CSIPHY_CLK_SRC] = &csiphy_clk_src.clkr,
+	[CSI0PHYTIMER_CLK_SRC] = &csi0phytimer_clk_src.clkr,
+	[CSI1PHYTIMER_CLK_SRC] = &csi1phytimer_clk_src.clkr,
+	[CSI2PHYTIMER_CLK_SRC] = &csi2phytimer_clk_src.clkr,
+	[DP_AUX_CLK_SRC] = &dp_aux_clk_src.clkr,
+	[DP_CRYPTO_CLK_SRC] = &dp_crypto_clk_src.clkr,
+	[DP_LINK_CLK_SRC] = &dp_link_clk_src.clkr,
+	[DP_PIXEL_CLK_SRC] = &dp_pixel_clk_src.clkr,
+	[ESC0_CLK_SRC] = &esc0_clk_src.clkr,
+	[ESC1_CLK_SRC] = &esc1_clk_src.clkr,
+	[EXTPCLK_CLK_SRC] = &extpclk_clk_src.clkr,
+	[FD_CORE_CLK_SRC] = &fd_core_clk_src.clkr,
+	[HDMI_CLK_SRC] = &hdmi_clk_src.clkr,
+	[JPEG0_CLK_SRC] = &jpeg0_clk_src.clkr,
+	[MAXI_CLK_SRC] = &maxi_clk_src.clkr,
+	[MCLK0_CLK_SRC] = &mclk0_clk_src.clkr,
+	[MCLK1_CLK_SRC] = &mclk1_clk_src.clkr,
+	[MCLK2_CLK_SRC] = &mclk2_clk_src.clkr,
+	[MCLK3_CLK_SRC] = &mclk3_clk_src.clkr,
+	[MDP_CLK_SRC] = &mdp_clk_src.clkr,
+	[VSYNC_CLK_SRC] = &vsync_clk_src.clkr,
+	[AHB_CLK_SRC] = &ahb_clk_src.clkr,
+	[AXI_CLK_SRC] = &axi_clk_src.clkr,
+	[PCLK0_CLK_SRC] = &pclk0_clk_src.clkr,
+	[PCLK1_CLK_SRC] = &pclk1_clk_src.clkr,
+	[ROT_CLK_SRC] = &rot_clk_src.clkr,
+	[VIDEO_CORE_CLK_SRC] = &video_core_clk_src.clkr,
+	[VIDEO_SUBCORE0_CLK_SRC] = &video_subcore0_clk_src.clkr,
+	[VIDEO_SUBCORE1_CLK_SRC] = &video_subcore1_clk_src.clkr,
+	[VFE0_CLK_SRC] = &vfe0_clk_src.clkr,
+	[VFE1_CLK_SRC] = &vfe1_clk_src.clkr,
+	[MISC_AHB_CLK] = &misc_ahb_clk.clkr,
+	[VIDEO_CORE_CLK] = &video_core_clk.clkr,
+	[VIDEO_AHB_CLK] = &video_ahb_clk.clkr,
+	[VIDEO_AXI_CLK] = &video_axi_clk.clkr,
+	[VIDEO_MAXI_CLK] = &video_maxi_clk.clkr,
+	[VIDEO_SUBCORE0_CLK] = &video_subcore0_clk.clkr,
+	[VIDEO_SUBCORE1_CLK] = &video_subcore1_clk.clkr,
+	[MDSS_AHB_CLK] = &mdss_ahb_clk.clkr,
+	[MDSS_HDMI_DP_AHB_CLK] = &mdss_hdmi_dp_ahb_clk.clkr,
+	[MDSS_AXI_CLK] = &mdss_axi_clk.clkr,
+	[MDSS_PCLK0_CLK] = &mdss_pclk0_clk.clkr,
+	[MDSS_PCLK1_CLK] = &mdss_pclk1_clk.clkr,
+	[MDSS_MDP_CLK] = &mdss_mdp_clk.clkr,
+	[MDSS_MDP_LUT_CLK] = &mdss_mdp_lut_clk.clkr,
+	[MDSS_EXTPCLK_CLK] = &mdss_extpclk_clk.clkr,
+	[MDSS_VSYNC_CLK] = &mdss_vsync_clk.clkr,
+	[MDSS_HDMI_CLK] = &mdss_hdmi_clk.clkr,
+	[MDSS_BYTE0_CLK] = &mdss_byte0_clk.clkr,
+	[MDSS_BYTE1_CLK] = &mdss_byte1_clk.clkr,
+	[MDSS_ESC0_CLK] = &mdss_esc0_clk.clkr,
+	[MDSS_ESC1_CLK] = &mdss_esc1_clk.clkr,
+	[MDSS_ROT_CLK] = &mdss_rot_clk.clkr,
+	[MDSS_DP_LINK_CLK] = &mdss_dp_link_clk.clkr,
+	[MDSS_DP_LINK_INTF_CLK] = &mdss_dp_link_intf_clk.clkr,
+	[MDSS_DP_CRYPTO_CLK] = &mdss_dp_crypto_clk.clkr,
+	[MDSS_DP_PIXEL_CLK] = &mdss_dp_pixel_clk.clkr,
+	[MDSS_DP_AUX_CLK] = &mdss_dp_aux_clk.clkr,
+	[MDSS_BYTE0_INTF_CLK] = &mdss_byte0_intf_clk.clkr,
+	[MDSS_BYTE1_INTF_CLK] = &mdss_byte1_intf_clk.clkr,
+	[CAMSS_CSI0PHYTIMER_CLK] = &camss_csi0phytimer_clk.clkr,
+	[CAMSS_CSI1PHYTIMER_CLK] = &camss_csi1phytimer_clk.clkr,
+	[CAMSS_CSI2PHYTIMER_CLK] = &camss_csi2phytimer_clk.clkr,
+	[CAMSS_CSI0_CLK] = &camss_csi0_clk.clkr,
+	[CAMSS_CSI0_AHB_CLK] = &camss_csi0_ahb_clk.clkr,
+	[CAMSS_CSI0RDI_CLK] = &camss_csi0rdi_clk.clkr,
+	[CAMSS_CSI0PIX_CLK] = &camss_csi0pix_clk.clkr,
+	[CAMSS_CSI1_CLK] = &camss_csi1_clk.clkr,
+	[CAMSS_CSI1_AHB_CLK] = &camss_csi1_ahb_clk.clkr,
+	[CAMSS_CSI1RDI_CLK] = &camss_csi1rdi_clk.clkr,
+	[CAMSS_CSI1PIX_CLK] = &camss_csi1pix_clk.clkr,
+	[CAMSS_CSI2_CLK] = &camss_csi2_clk.clkr,
+	[CAMSS_CSI2_AHB_CLK] = &camss_csi2_ahb_clk.clkr,
+	[CAMSS_CSI2RDI_CLK] = &camss_csi2rdi_clk.clkr,
+	[CAMSS_CSI2PIX_CLK] = &camss_csi2pix_clk.clkr,
+	[CAMSS_CSI3_CLK] = &camss_csi3_clk.clkr,
+	[CAMSS_CSI3_AHB_CLK] = &camss_csi3_ahb_clk.clkr,
+	[CAMSS_CSI3RDI_CLK] = &camss_csi3rdi_clk.clkr,
+	[CAMSS_CSI3PIX_CLK] = &camss_csi3pix_clk.clkr,
+	[CAMSS_ISPIF_AHB_CLK] = &camss_ispif_ahb_clk.clkr,
+	[CAMSS_CCI_CLK] = &camss_cci_clk.clkr,
+	[CAMSS_CCI_AHB_CLK] = &camss_cci_ahb_clk.clkr,
+	[CAMSS_MCLK0_CLK] = &camss_mclk0_clk.clkr,
+	[CAMSS_MCLK1_CLK] = &camss_mclk1_clk.clkr,
+	[CAMSS_MCLK2_CLK] = &camss_mclk2_clk.clkr,
+	[CAMSS_MCLK3_CLK] = &camss_mclk3_clk.clkr,
+	[CAMSS_TOP_AHB_CLK] = &camss_top_ahb_clk.clkr,
+	[CAMSS_AHB_CLK] = &camss_ahb_clk.clkr,
+	[CAMSS_MICRO_AHB_CLK] = &camss_micro_ahb_clk.clkr,
+	[CAMSS_JPEG0_CLK] = &camss_jpeg0_clk.clkr,
+	[CAMSS_JPEG_AHB_CLK] = &camss_jpeg_ahb_clk.clkr,
+	[CAMSS_JPEG_AXI_CLK] = &camss_jpeg_axi_clk.clkr,
+	[CAMSS_VFE0_AHB_CLK] = &camss_vfe0_ahb_clk.clkr,
+	[CAMSS_VFE1_AHB_CLK] = &camss_vfe1_ahb_clk.clkr,
+	[CAMSS_VFE0_CLK] = &camss_vfe0_clk.clkr,
+	[CAMSS_VFE1_CLK] = &camss_vfe1_clk.clkr,
+	[CAMSS_CPP_CLK] = &camss_cpp_clk.clkr,
+	[CAMSS_CPP_AHB_CLK] = &camss_cpp_ahb_clk.clkr,
+	[CAMSS_VFE_VBIF_AHB_CLK] = &camss_vfe_vbif_ahb_clk.clkr,
+	[CAMSS_VFE_VBIF_AXI_CLK] = &camss_vfe_vbif_axi_clk.clkr,
+	[CAMSS_CPP_AXI_CLK] = &camss_cpp_axi_clk.clkr,
+	[CAMSS_CPP_VBIF_AHB_CLK] = &camss_cpp_vbif_ahb_clk.clkr,
+	[CAMSS_CSI_VFE0_CLK] = &camss_csi_vfe0_clk.clkr,
+	[CAMSS_CSI_VFE1_CLK] = &camss_csi_vfe1_clk.clkr,
+	[CAMSS_VFE0_STREAM_CLK] = &camss_vfe0_stream_clk.clkr,
+	[CAMSS_VFE1_STREAM_CLK] = &camss_vfe1_stream_clk.clkr,
+	[CAMSS_CPHY_CSID0_CLK] = &camss_cphy_csid0_clk.clkr,
+	[CAMSS_CPHY_CSID1_CLK] = &camss_cphy_csid1_clk.clkr,
+	[CAMSS_CPHY_CSID2_CLK] = &camss_cphy_csid2_clk.clkr,
+	[CAMSS_CPHY_CSID3_CLK] = &camss_cphy_csid3_clk.clkr,
+	[CAMSS_CSIPHY0_CLK] = &camss_csiphy0_clk.clkr,
+	[CAMSS_CSIPHY1_CLK] = &camss_csiphy1_clk.clkr,
+	[CAMSS_CSIPHY2_CLK] = &camss_csiphy2_clk.clkr,
+	[FD_CORE_CLK] = &fd_core_clk.clkr,
+	[FD_CORE_UAR_CLK] = &fd_core_uar_clk.clkr,
+	[FD_AHB_CLK] = &fd_ahb_clk.clkr,
+	[MNOC_AHB_CLK] = &mnoc_ahb_clk.clkr,
+	[BIMC_SMMU_AHB_CLK] = &bimc_smmu_ahb_clk.clkr,
+	[BIMC_SMMU_AXI_CLK] = &bimc_smmu_axi_clk.clkr,
+	[MNOC_MAXI_CLK] = &mnoc_maxi_clk.clkr,
+	[VMEM_MAXI_CLK] = &vmem_maxi_clk.clkr,
+	[VMEM_AHB_CLK] = &vmem_ahb_clk.clkr,
+};
+
+static struct gdsc *mmcc_msm8998_gdscs[] = {
+	[VIDEO_TOP_GDSC] = &video_top_gdsc,
+	[VIDEO_SUBCORE0_GDSC] = &video_subcore0_gdsc,
+	[VIDEO_SUBCORE1_GDSC] = &video_subcore1_gdsc,
+	[MDSS_GDSC] = &mdss_gdsc,
+	[CAMSS_TOP_GDSC] = &camss_top_gdsc,
+	[CAMSS_VFE0_GDSC] = &camss_vfe0_gdsc,
+	[CAMSS_VFE1_GDSC] = &camss_vfe1_gdsc,
+	[CAMSS_CPP_GDSC] = &camss_cpp_gdsc,
+	[BIMC_SMMU_GDSC] = &bimc_smmu_gdsc,
+};
+
+static const struct qcom_reset_map mmcc_msm8998_resets[] = {
+	[SPDM_BCR] = { 0x200 },
+	[SPDM_RM_BCR] = { 0x300 },
+	[MISC_BCR] = { 0x320 },
+	[VIDEO_TOP_BCR] = { 0x1020 },
+	[THROTTLE_VIDEO_BCR] = { 0x1180 },
+	[MDSS_BCR] = { 0x2300 },
+	[THROTTLE_MDSS_BCR] = { 0x2460 },
+	[CAMSS_PHY0_BCR] = { 0x3020 },
+	[CAMSS_PHY1_BCR] = { 0x3050 },
+	[CAMSS_PHY2_BCR] = { 0x3080 },
+	[CAMSS_CSI0_BCR] = { 0x30b0 },
+	[CAMSS_CSI0RDI_BCR] = { 0x30d0 },
+	[CAMSS_CSI0PIX_BCR] = { 0x30e0 },
+	[CAMSS_CSI1_BCR] = { 0x3120 },
+	[CAMSS_CSI1RDI_BCR] = { 0x3140 },
+	[CAMSS_CSI1PIX_BCR] = { 0x3150 },
+	[CAMSS_CSI2_BCR] = { 0x3180 },
+	[CAMSS_CSI2RDI_BCR] = { 0x31a0 },
+	[CAMSS_CSI2PIX_BCR] = { 0x31b0 },
+	[CAMSS_CSI3_BCR] = { 0x31e0 },
+	[CAMSS_CSI3RDI_BCR] = { 0x3200 },
+	[CAMSS_CSI3PIX_BCR] = { 0x3210 },
+	[CAMSS_ISPIF_BCR] = { 0x3220 },
+	[CAMSS_CCI_BCR] = { 0x3340 },
+	[CAMSS_TOP_BCR] = { 0x3480 },
+	[CAMSS_AHB_BCR] = { 0x3488 },
+	[CAMSS_MICRO_BCR] = { 0x3490 },
+	[CAMSS_JPEG_BCR] = { 0x35a0 },
+	[CAMSS_VFE0_BCR] = { 0x3660 },
+	[CAMSS_VFE1_BCR] = { 0x3670 },
+	[CAMSS_VFE_VBIF_BCR] = { 0x36a0 },
+	[CAMSS_CPP_TOP_BCR] = { 0x36c0 },
+	[CAMSS_CPP_BCR] = { 0x36d0 },
+	[CAMSS_CSI_VFE0_BCR] = { 0x3700 },
+	[CAMSS_CSI_VFE1_BCR] = { 0x3710 },
+	[CAMSS_FD_BCR] = { 0x3b60 },
+	[THROTTLE_CAMSS_BCR] = { 0x3c30 },
+	[MNOCAHB_BCR] = { 0x5020 },
+	[MNOCAXI_BCR] = { 0xd020 },
+	[BMIC_SMMU_BCR] = { 0xe000 },
+	[MNOC_MAXI_BCR] = { 0xf000 },
+	[VMEM_BCR] = { 0xf060 },
+	[BTO_BCR] = { 0x10004 },
+};
+
+static const struct regmap_config mmcc_msm8998_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x10004,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc mmcc_msm8998_desc = {
+	.config = &mmcc_msm8998_regmap_config,
+	.clks = mmcc_msm8998_clocks,
+	.num_clks = ARRAY_SIZE(mmcc_msm8998_clocks),
+	.resets = mmcc_msm8998_resets,
+	.num_resets = ARRAY_SIZE(mmcc_msm8998_resets),
+	.gdscs = mmcc_msm8998_gdscs,
+	.num_gdscs = ARRAY_SIZE(mmcc_msm8998_gdscs),
+	.clk_hws = mmcc_msm8998_hws,
+	.num_clk_hws = ARRAY_SIZE(mmcc_msm8998_hws),
+};
+
+static const struct of_device_id mmcc_msm8998_match_table[] = {
+	{ .compatible = "qcom,mmcc-msm8998" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mmcc_msm8998_match_table);
+
+static int mmcc_msm8998_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+
+	regmap = qcom_cc_map(pdev, &mmcc_msm8998_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	return qcom_cc_really_probe(pdev, &mmcc_msm8998_desc, regmap);
+}
+
+static struct platform_driver mmcc_msm8998_driver = {
+	.probe		= mmcc_msm8998_probe,
+	.driver		= {
+		.name	= "mmcc-msm8998",
+		.of_match_table = mmcc_msm8998_match_table,
+	},
+};
+module_platform_driver(mmcc_msm8998_driver);
+
+MODULE_DESCRIPTION("QCOM MMCC MSM8998 Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/qcom/videocc-sc7180.c b/drivers/clk/qcom/videocc-sc7180.c
new file mode 100644
index 000000000000..76add30024aa
--- /dev/null
+++ b/drivers/clk/qcom/videocc-sc7180.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <dt-bindings/clock/qcom,videocc-sc7180.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap.h"
+#include "common.h"
+#include "gdsc.h"
+
+enum {
+	P_BI_TCXO,
+	P_CHIP_SLEEP_CLK,
+	P_CORE_BI_PLL_TEST_SE,
+	P_VIDEO_PLL0_OUT_EVEN,
+	P_VIDEO_PLL0_OUT_MAIN,
+	P_VIDEO_PLL0_OUT_ODD,
+};
+
+static const struct pll_vco fabia_vco[] = {
+	{ 249600000, 2000000000, 0 },
+};
+
+static struct clk_alpha_pll video_pll0 = {
+	.offset = 0x42c,
+	.vco_table = fabia_vco,
+	.num_vco = ARRAY_SIZE(fabia_vco),
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "video_pll0",
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "bi_tcxo",
+			},
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+static const struct parent_map video_cc_parent_map_1[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_VIDEO_PLL0_OUT_MAIN, 1 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const struct clk_parent_data video_cc_parent_data_1[] = {
+	{ .fw_name = "bi_tcxo" },
+	{ .hw = &video_pll0.clkr.hw },
+	{ .fw_name = "core_bi_pll_test_se", .name = "core_bi_pll_test_se" },
+};
+
+static const struct freq_tbl ftbl_video_cc_venus_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(150000000, P_VIDEO_PLL0_OUT_MAIN, 4, 0, 0),
+	F(270000000, P_VIDEO_PLL0_OUT_MAIN, 2.5, 0, 0),
+	F(340000000, P_VIDEO_PLL0_OUT_MAIN, 2, 0, 0),
+	F(434000000, P_VIDEO_PLL0_OUT_MAIN, 2, 0, 0),
+	F(500000000, P_VIDEO_PLL0_OUT_MAIN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 video_cc_venus_clk_src = {
+	.cmd_rcgr = 0x7f0,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = video_cc_parent_map_1,
+	.freq_tbl = ftbl_video_cc_venus_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "video_cc_venus_clk_src",
+		.parent_data = video_cc_parent_data_1,
+		.num_parents = 3,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_branch video_cc_vcodec0_axi_clk = {
+	.halt_reg = 0x9ec,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x9ec,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_cc_vcodec0_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch video_cc_vcodec0_core_clk = {
+	.halt_reg = 0x890,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x890,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_cc_vcodec0_core_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &video_cc_venus_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch video_cc_venus_ahb_clk = {
+	.halt_reg = 0xa4c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0xa4c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_cc_venus_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch video_cc_venus_ctl_axi_clk = {
+	.halt_reg = 0x9cc,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x9cc,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_cc_venus_ctl_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch video_cc_venus_ctl_core_clk = {
+	.halt_reg = 0x850,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x850,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "video_cc_venus_ctl_core_clk",
+			.parent_data = &(const struct clk_parent_data){
+				.hw = &video_cc_venus_clk_src.clkr.hw,
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc venus_gdsc = {
+	.gdscr = 0x814,
+	.pd = {
+		.name = "venus_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct gdsc vcodec0_gdsc = {
+	.gdscr = 0x874,
+	.pd = {
+		.name = "vcodec0_gdsc",
+	},
+	.flags = HW_CTRL,
+	.pwrsts = PWRSTS_OFF_ON,
+};
+
+static struct clk_regmap *video_cc_sc7180_clocks[] = {
+	[VIDEO_CC_VCODEC0_AXI_CLK] = &video_cc_vcodec0_axi_clk.clkr,
+	[VIDEO_CC_VCODEC0_CORE_CLK] = &video_cc_vcodec0_core_clk.clkr,
+	[VIDEO_CC_VENUS_AHB_CLK] = &video_cc_venus_ahb_clk.clkr,
+	[VIDEO_CC_VENUS_CLK_SRC] = &video_cc_venus_clk_src.clkr,
+	[VIDEO_CC_VENUS_CTL_AXI_CLK] = &video_cc_venus_ctl_axi_clk.clkr,
+	[VIDEO_CC_VENUS_CTL_CORE_CLK] = &video_cc_venus_ctl_core_clk.clkr,
+	[VIDEO_PLL0] = &video_pll0.clkr,
+};
+
+static struct gdsc *video_cc_sc7180_gdscs[] = {
+	[VENUS_GDSC] = &venus_gdsc,
+	[VCODEC0_GDSC] = &vcodec0_gdsc,
+};
+
+static const struct regmap_config video_cc_sc7180_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.max_register = 0xb94,
+	.fast_io = true,
+};
+
+static const struct qcom_cc_desc video_cc_sc7180_desc = {
+	.config = &video_cc_sc7180_regmap_config,
+	.clks = video_cc_sc7180_clocks,
+	.num_clks = ARRAY_SIZE(video_cc_sc7180_clocks),
+	.gdscs = video_cc_sc7180_gdscs,
+	.num_gdscs = ARRAY_SIZE(video_cc_sc7180_gdscs),
+};
+
+static const struct of_device_id video_cc_sc7180_match_table[] = {
+	{ .compatible = "qcom,sc7180-videocc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, video_cc_sc7180_match_table);
+
+static int video_cc_sc7180_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	struct alpha_pll_config video_pll0_config = {};
+
+	regmap = qcom_cc_map(pdev, &video_cc_sc7180_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	video_pll0_config.l = 0x1f;
+	video_pll0_config.alpha = 0x4000;
+	video_pll0_config.user_ctl_val = 0x00000001;
+	video_pll0_config.user_ctl_hi_val = 0x00004805;
+
+	clk_fabia_pll_configure(&video_pll0, regmap, &video_pll0_config);
+
+	/* Keep VIDEO_CC_XO_CLK ALWAYS-ON */
+	regmap_update_bits(regmap, 0x984, 0x1, 0x1);
+
+	return qcom_cc_really_probe(pdev, &video_cc_sc7180_desc, regmap);
+}
+
+static struct platform_driver video_cc_sc7180_driver = {
+	.probe = video_cc_sc7180_probe,
+	.driver = {
+		.name = "sc7180-videocc",
+		.of_match_table = video_cc_sc7180_match_table,
+	},
+};
+
+static int __init video_cc_sc7180_init(void)
+{
+	return platform_driver_register(&video_cc_sc7180_driver);
+}
+subsys_initcall(video_cc_sc7180_init);
+
+static void __exit video_cc_sc7180_exit(void)
+{
+	platform_driver_unregister(&video_cc_sc7180_driver);
+}
+module_exit(video_cc_sc7180_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("QTI VIDEOCC SC7180 Driver");
diff --git a/drivers/clk/renesas/Kconfig b/drivers/clk/renesas/Kconfig
index 4cd846bc98cc..250d8165167a 100644
--- a/drivers/clk/renesas/Kconfig
+++ b/drivers/clk/renesas/Kconfig
@@ -20,8 +20,8 @@ config CLK_RENESAS
 	select CLK_R8A7791 if ARCH_R8A7791 || ARCH_R8A7793
 	select CLK_R8A7792 if ARCH_R8A7792
 	select CLK_R8A7794 if ARCH_R8A7794
-	select CLK_R8A7795 if ARCH_R8A7795
-	select CLK_R8A77960 if ARCH_R8A77960 || ARCH_R8A7796
+	select CLK_R8A7795 if ARCH_R8A77950 || ARCH_R8A77951 || ARCH_R8A7795
+	select CLK_R8A77960 if ARCH_R8A77960
 	select CLK_R8A77961 if ARCH_R8A77961
 	select CLK_R8A77965 if ARCH_R8A77965
 	select CLK_R8A77970 if ARCH_R8A77970
diff --git a/drivers/clk/renesas/r7s9210-cpg-mssr.c b/drivers/clk/renesas/r7s9210-cpg-mssr.c
index cf65d4e0e116..443bff08df4c 100644
--- a/drivers/clk/renesas/r7s9210-cpg-mssr.c
+++ b/drivers/clk/renesas/r7s9210-cpg-mssr.c
@@ -93,6 +93,7 @@ static const struct mssr_mod_clk r7s9210_mod_clks[] __initconst = {
 	DEF_MOD_STB("ether1",	 64,	R7S9210_CLK_B),
 	DEF_MOD_STB("ether0",	 65,	R7S9210_CLK_B),
 
+	DEF_MOD_STB("spibsc",	 83,	R7S9210_CLK_P1),
 	DEF_MOD_STB("i2c3",	 84,	R7S9210_CLK_P1),
 	DEF_MOD_STB("i2c2",	 85,	R7S9210_CLK_P1),
 	DEF_MOD_STB("i2c1",	 86,	R7S9210_CLK_P1),
diff --git a/drivers/clk/renesas/rcar-gen2-cpg.h b/drivers/clk/renesas/rcar-gen2-cpg.h
index db2f57ef2f99..bdcd4a38d48d 100644
--- a/drivers/clk/renesas/rcar-gen2-cpg.h
+++ b/drivers/clk/renesas/rcar-gen2-cpg.h
@@ -24,10 +24,10 @@ enum rcar_gen2_clk_types {
 };
 
 struct rcar_gen2_cpg_pll_config {
-	unsigned int extal_div;
-	unsigned int pll1_mult;
-	unsigned int pll3_mult;
-	unsigned int pll0_mult;		/* leave as zero if PLL0CR exists */
+	u8 extal_div;
+	u8 pll1_mult;
+	u8 pll3_mult;
+	u8 pll0_mult;		/* leave as zero if PLL0CR exists */
 };
 
 struct clk *rcar_gen2_cpg_clk_register(struct device *dev,
diff --git a/drivers/clk/renesas/rcar-gen3-cpg.c b/drivers/clk/renesas/rcar-gen3-cpg.c
index c97b647db9b6..488f8b3980c5 100644
--- a/drivers/clk/renesas/rcar-gen3-cpg.c
+++ b/drivers/clk/renesas/rcar-gen3-cpg.c
@@ -470,7 +470,8 @@ static struct clk * __init cpg_rpc_clk_register(const char *name,
 
 	clk = clk_register_composite(NULL, name, &parent_name, 1, NULL, NULL,
 				     &rpc->div.hw,  &clk_divider_ops,
-				     &rpc->gate.hw, &clk_gate_ops, 0);
+				     &rpc->gate.hw, &clk_gate_ops,
+				     CLK_SET_RATE_PARENT);
 	if (IS_ERR(clk)) {
 		kfree(rpc);
 		return clk;
@@ -506,7 +507,8 @@ static struct clk * __init cpg_rpcd2_clk_register(const char *name,
 
 	clk = clk_register_composite(NULL, name, &parent_name, 1, NULL, NULL,
 				     &rpcd2->fixed.hw, &clk_fixed_factor_ops,
-				     &rpcd2->gate.hw, &clk_gate_ops, 0);
+				     &rpcd2->gate.hw, &clk_gate_ops,
+				     CLK_SET_RATE_PARENT);
 	if (IS_ERR(clk))
 		kfree(rpcd2);
 
diff --git a/drivers/clk/rockchip/clk-pll.c b/drivers/clk/rockchip/clk-pll.c
index 198417d56300..10560d963baf 100644
--- a/drivers/clk/rockchip/clk-pll.c
+++ b/drivers/clk/rockchip/clk-pll.c
@@ -282,7 +282,7 @@ static int rockchip_rk3036_pll_is_enabled(struct clk_hw *hw)
 	return !(pllcon & RK3036_PLLCON1_PWRDOWN);
 }
 
-static void rockchip_rk3036_pll_init(struct clk_hw *hw)
+static int rockchip_rk3036_pll_init(struct clk_hw *hw)
 {
 	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
 	const struct rockchip_pll_rate_table *rate;
@@ -290,14 +290,14 @@ static void rockchip_rk3036_pll_init(struct clk_hw *hw)
 	unsigned long drate;
 
 	if (!(pll->flags & ROCKCHIP_PLL_SYNC_RATE))
-		return;
+		return 0;
 
 	drate = clk_hw_get_rate(hw);
 	rate = rockchip_get_pll_settings(pll, drate);
 
 	/* when no rate setting for the current rate, rely on clk_set_rate */
 	if (!rate)
-		return;
+		return 0;
 
 	rockchip_rk3036_pll_get_params(pll, &cur);
 
@@ -319,13 +319,15 @@ static void rockchip_rk3036_pll_init(struct clk_hw *hw)
 		if (!parent) {
 			pr_warn("%s: parent of %s not available\n",
 				__func__, __clk_get_name(hw->clk));
-			return;
+			return 0;
 		}
 
 		pr_debug("%s: pll %s: rate params do not match rate table, adjusting\n",
 			 __func__, __clk_get_name(hw->clk));
 		rockchip_rk3036_pll_set_params(pll, rate);
 	}
+
+	return 0;
 }
 
 static const struct clk_ops rockchip_rk3036_pll_clk_norate_ops = {
@@ -515,7 +517,7 @@ static int rockchip_rk3066_pll_is_enabled(struct clk_hw *hw)
 	return !(pllcon & RK3066_PLLCON3_PWRDOWN);
 }
 
-static void rockchip_rk3066_pll_init(struct clk_hw *hw)
+static int rockchip_rk3066_pll_init(struct clk_hw *hw)
 {
 	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
 	const struct rockchip_pll_rate_table *rate;
@@ -523,14 +525,14 @@ static void rockchip_rk3066_pll_init(struct clk_hw *hw)
 	unsigned long drate;
 
 	if (!(pll->flags & ROCKCHIP_PLL_SYNC_RATE))
-		return;
+		return 0;
 
 	drate = clk_hw_get_rate(hw);
 	rate = rockchip_get_pll_settings(pll, drate);
 
 	/* when no rate setting for the current rate, rely on clk_set_rate */
 	if (!rate)
-		return;
+		return 0;
 
 	rockchip_rk3066_pll_get_params(pll, &cur);
 
@@ -543,6 +545,8 @@ static void rockchip_rk3066_pll_init(struct clk_hw *hw)
 			 __func__, clk_hw_get_name(hw));
 		rockchip_rk3066_pll_set_params(pll, rate);
 	}
+
+	return 0;
 }
 
 static const struct clk_ops rockchip_rk3066_pll_clk_norate_ops = {
@@ -761,7 +765,7 @@ static int rockchip_rk3399_pll_is_enabled(struct clk_hw *hw)
 	return !(pllcon & RK3399_PLLCON3_PWRDOWN);
 }
 
-static void rockchip_rk3399_pll_init(struct clk_hw *hw)
+static int rockchip_rk3399_pll_init(struct clk_hw *hw)
 {
 	struct rockchip_clk_pll *pll = to_rockchip_clk_pll(hw);
 	const struct rockchip_pll_rate_table *rate;
@@ -769,14 +773,14 @@ static void rockchip_rk3399_pll_init(struct clk_hw *hw)
 	unsigned long drate;
 
 	if (!(pll->flags & ROCKCHIP_PLL_SYNC_RATE))
-		return;
+		return 0;
 
 	drate = clk_hw_get_rate(hw);
 	rate = rockchip_get_pll_settings(pll, drate);
 
 	/* when no rate setting for the current rate, rely on clk_set_rate */
 	if (!rate)
-		return;
+		return 0;
 
 	rockchip_rk3399_pll_get_params(pll, &cur);
 
@@ -798,13 +802,15 @@ static void rockchip_rk3399_pll_init(struct clk_hw *hw)
 		if (!parent) {
 			pr_warn("%s: parent of %s not available\n",
 				__func__, __clk_get_name(hw->clk));
-			return;
+			return 0;
 		}
 
 		pr_debug("%s: pll %s: rate params do not match rate table, adjusting\n",
 			 __func__, __clk_get_name(hw->clk));
 		rockchip_rk3399_pll_set_params(pll, rate);
 	}
+
+	return 0;
 }
 
 static const struct clk_ops rockchip_rk3399_pll_clk_norate_ops = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
index 49bd7a4c015c..5f66bf879772 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.c
@@ -921,11 +921,26 @@ static const struct sunxi_ccu_desc sun50i_a64_ccu_desc = {
 	.num_resets	= ARRAY_SIZE(sun50i_a64_ccu_resets),
 };
 
+static struct ccu_pll_nb sun50i_a64_pll_cpu_nb = {
+	.common	= &pll_cpux_clk.common,
+	/* copy from pll_cpux_clk */
+	.enable	= BIT(31),
+	.lock	= BIT(28),
+};
+
+static struct ccu_mux_nb sun50i_a64_cpu_nb = {
+	.common		= &cpux_clk.common,
+	.cm		= &cpux_clk.mux,
+	.delay_us	= 1, /* > 8 clock cycles at 24 MHz */
+	.bypass_index	= 1, /* index of 24 MHz oscillator */
+};
+
 static int sun50i_a64_ccu_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	void __iomem *reg;
 	u32 val;
+	int ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg = devm_ioremap_resource(&pdev->dev, res);
@@ -939,7 +954,18 @@ static int sun50i_a64_ccu_probe(struct platform_device *pdev)
 
 	writel(0x515, reg + SUN50I_A64_PLL_MIPI_REG);
 
-	return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a64_ccu_desc);
+	ret = sunxi_ccu_probe(pdev->dev.of_node, reg, &sun50i_a64_ccu_desc);
+	if (ret)
+		return ret;
+
+	/* Gate then ungate PLL CPU after any rate changes */
+	ccu_pll_notifier_register(&sun50i_a64_pll_cpu_nb);
+
+	/* Reparent CPU during PLL CPU rate changes */
+	ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
+				  &sun50i_a64_cpu_nb);
+
+	return 0;
 }
 
 static const struct of_device_id sun50i_a64_ccu_ids[] = {
diff --git a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h
index 979929276709..116e6f826d04 100644
--- a/drivers/clk/sunxi-ng/ccu-sun50i-a64.h
+++ b/drivers/clk/sunxi-ng/ccu-sun50i-a64.h
@@ -36,7 +36,6 @@
 #define CLK_PLL_HSIC			18
 #define CLK_PLL_DE			19
 #define CLK_PLL_DDR1			20
-#define CLK_CPUX			21
 #define CLK_AXI				22
 #define CLK_APB				23
 #define CLK_AHB1			24
diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.h b/drivers/clk/sunxi-ng/ccu-sun6i-a31.h
index a361388b4670..3ed2a59b0dc6 100644
--- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.h
+++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.h
@@ -32,7 +32,9 @@
 /* The PLL_VIDEO1_2X clock is exported */
 
 #define CLK_PLL_GPU		14
-#define CLK_PLL_MIPI		15
+
+/* The PLL_VIDEO1_2X clock is exported */
+
 #define CLK_PLL9		16
 #define CLK_PLL10		17
 
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-a23-a33.h b/drivers/clk/sunxi-ng/ccu-sun8i-a23-a33.h
index 72df69291cc6..5bf5c4d13b4c 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-a23-a33.h
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-a23-a33.h
@@ -24,7 +24,9 @@
 #define CLK_PLL_PERIPH		10
 #define CLK_PLL_PERIPH_2X	11
 #define CLK_PLL_GPU		12
-#define CLK_PLL_MIPI		13
+
+/* The PLL MIPI clock is exported */
+
 #define CLK_PLL_HSIC		14
 #define CLK_PLL_DE		15
 #define CLK_PLL_DDR1		16
diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
index a69637b6b0c1..6f7071df8e1c 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
@@ -55,10 +55,6 @@
 
 /* Some more module clocks are exported */
 
-#define CLK_MBUS		155
-
-/* Another bunch of module clocks are exported */
-
 #define CLK_NUMBER		(CLK_OUTB + 1)
 
 #endif /* _CCU_SUN8I_R40_H_ */
diff --git a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
index a165e7172346..4c75b0770c74 100644
--- a/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
+++ b/drivers/clk/sunxi/clk-sun6i-apb0-gates.c
@@ -37,7 +37,6 @@ static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
 	struct clk_onecell_data *clk_data;
-	const struct of_device_id *device;
 	const struct gates_data *data;
 	const char *clk_parent;
 	const char *clk_name;
@@ -50,10 +49,9 @@ static int sun6i_a31_apb0_gates_clk_probe(struct platform_device *pdev)
 	if (!np)
 		return -ENODEV;
 
-	device = of_match_device(sun6i_a31_apb0_gates_clk_dt_ids, &pdev->dev);
-	if (!device)
+	data = of_device_get_match_data(&pdev->dev);
+	if (!data)
 		return -ENODEV;
-	data = device->data;
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg = devm_ioremap_resource(&pdev->dev, r);
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
index c051d92c2bbf..cfbaa90c7adb 100644
--- a/drivers/clk/tegra/clk-dfll.c
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -1487,7 +1487,6 @@ static int dfll_init(struct tegra_dfll *td)
 	td->last_unrounded_rate = 0;
 
 	pm_runtime_enable(td->dev);
-	pm_runtime_irq_safe(td->dev);
 	pm_runtime_get_sync(td->dev);
 
 	dfll_set_mode(td, DFLL_DISABLED);
@@ -1516,7 +1515,7 @@ di_err1:
 
 /**
  * tegra_dfll_suspend - check DFLL is disabled
- * @dev: DFLL device *
+ * @dev: DFLL instance
  *
  * DFLL clock should be disabled by the CPUFreq driver. So, make
  * sure it is disabled and disable all clocks needed by the DFLL.
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index ca0de5f11f84..38daf483ddf1 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -40,8 +40,13 @@ static unsigned long clk_frac_div_recalc_rate(struct clk_hw *hw,
 	int div, mul;
 	u64 rate = parent_rate;
 
-	reg = readl_relaxed(divider->reg) >> divider->shift;
-	div = reg & div_mask(divider);
+	reg = readl_relaxed(divider->reg);
+
+	if ((divider->flags & TEGRA_DIVIDER_UART) &&
+	    !(reg & PERIPH_CLK_UART_DIV_ENB))
+		return rate;
+
+	div = (reg >> divider->shift) & div_mask(divider);
 
 	mul = get_mul(divider);
 	div += mul;
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 0d07c0ba49b6..2b2a3b81c16b 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -777,7 +777,11 @@ static struct tegra_periph_init_data gate_clks[] = {
 	GATE("ahbdma", "hclk", 33, 0, tegra_clk_ahbdma, 0),
 	GATE("apbdma", "pclk", 34, 0, tegra_clk_apbdma, 0),
 	GATE("kbc", "clk_32k", 36, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_kbc, 0),
-	GATE("fuse", "clk_m", 39, TEGRA_PERIPH_ON_APB, tegra_clk_fuse, 0),
+	/*
+	 * Critical for RAM re-repair operation, which must occur on resume
+	 * from LP1 system suspend and as part of CCPLEX cluster switching.
+	 */
+	GATE("fuse", "clk_m", 39, TEGRA_PERIPH_ON_APB, tegra_clk_fuse, CLK_IS_CRITICAL),
 	GATE("fuse_burn", "clk_m", 39, TEGRA_PERIPH_ON_APB, tegra_clk_fuse_burn, 0),
 	GATE("kfuse", "clk_m", 40, TEGRA_PERIPH_ON_APB, tegra_clk_kfuse, 0),
 	GATE("apbif", "clk_m", 107, TEGRA_PERIPH_ON_APB, tegra_clk_apbif, 0),
diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c
index 4d8222f5c638..fff5cba87637 100644
--- a/drivers/clk/tegra/clk-tegra20.c
+++ b/drivers/clk/tegra/clk-tegra20.c
@@ -1046,11 +1046,9 @@ static struct tegra_clk_init_table init_table[] __initdata = {
 	{ TEGRA20_CLK_SBC3, TEGRA20_CLK_PLL_P, 100000000, 0 },
 	{ TEGRA20_CLK_SBC4, TEGRA20_CLK_PLL_P, 100000000, 0 },
 	{ TEGRA20_CLK_HOST1X, TEGRA20_CLK_PLL_C, 150000000, 0 },
-	{ TEGRA20_CLK_DISP1, TEGRA20_CLK_PLL_P, 600000000, 0 },
-	{ TEGRA20_CLK_DISP2, TEGRA20_CLK_PLL_P, 600000000, 0 },
 	{ TEGRA20_CLK_GR2D, TEGRA20_CLK_PLL_C, 300000000, 0 },
 	{ TEGRA20_CLK_GR3D, TEGRA20_CLK_PLL_C, 300000000, 0 },
-	{ TEGRA20_CLK_VDE, TEGRA20_CLK_CLK_MAX, 300000000, 0 },
+	{ TEGRA20_CLK_VDE, TEGRA20_CLK_PLL_C, 300000000, 0 },
 	/* must be the last entry */
 	{ TEGRA20_CLK_CLK_MAX, TEGRA20_CLK_CLK_MAX, 0, 0 },
 };
diff --git a/drivers/clk/tegra/clk-tegra30.c b/drivers/clk/tegra/clk-tegra30.c
index c8bc18e4d7e5..b20891489e11 100644
--- a/drivers/clk/tegra/clk-tegra30.c
+++ b/drivers/clk/tegra/clk-tegra30.c
@@ -1251,14 +1251,12 @@ static struct tegra_clk_init_table init_table[] __initdata = {
 	{ TEGRA30_CLK_SBC6, TEGRA30_CLK_PLL_P, 100000000, 0 },
 	{ TEGRA30_CLK_PLL_C, TEGRA30_CLK_CLK_MAX, 600000000, 0 },
 	{ TEGRA30_CLK_HOST1X, TEGRA30_CLK_PLL_C, 150000000, 0 },
-	{ TEGRA30_CLK_DISP1, TEGRA30_CLK_PLL_P, 600000000, 0 },
-	{ TEGRA30_CLK_DISP2, TEGRA30_CLK_PLL_P, 600000000, 0 },
 	{ TEGRA30_CLK_TWD, TEGRA30_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA30_CLK_GR2D, TEGRA30_CLK_PLL_C, 300000000, 0 },
 	{ TEGRA30_CLK_GR3D, TEGRA30_CLK_PLL_C, 300000000, 0 },
 	{ TEGRA30_CLK_GR3D2, TEGRA30_CLK_PLL_C, 300000000, 0 },
 	{ TEGRA30_CLK_PLL_U, TEGRA30_CLK_CLK_MAX, 480000000, 0 },
-	{ TEGRA30_CLK_VDE, TEGRA30_CLK_CLK_MAX, 600000000, 0 },
+	{ TEGRA30_CLK_VDE, TEGRA30_CLK_PLL_C, 600000000, 0 },
 	{ TEGRA30_CLK_SPDIF_IN_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
 	{ TEGRA30_CLK_I2S0_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
 	{ TEGRA30_CLK_I2S1_SYNC, TEGRA30_CLK_CLK_MAX, 24000000, 0 },
diff --git a/drivers/clk/ti/clk-54xx.c b/drivers/clk/ti/clk-54xx.c
index c9608e5d993a..14d98a890c02 100644
--- a/drivers/clk/ti/clk-54xx.c
+++ b/drivers/clk/ti/clk-54xx.c
@@ -35,6 +35,20 @@ static const struct omap_clkctrl_reg_data omap5_dsp_clkctrl_regs[] __initconst =
 	{ 0 },
 };
 
+static const char * const omap5_aess_fclk_parents[] __initconst = {
+	"abe_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data omap5_aess_fclk_data __initconst = {
+	.max_div = 2,
+};
+
+static const struct omap_clkctrl_bit_data omap5_aess_bit_data[] __initconst = {
+	{ 24, TI_CLK_DIVIDER, omap5_aess_fclk_parents, &omap5_aess_fclk_data },
+	{ 0 },
+};
+
 static const char * const omap5_dmic_gfclk_parents[] __initconst = {
 	"abe_cm:clk:0018:26",
 	"pad_clks_ck",
@@ -122,6 +136,7 @@ static const struct omap_clkctrl_bit_data omap5_timer8_bit_data[] __initconst =
 
 static const struct omap_clkctrl_reg_data omap5_abe_clkctrl_regs[] __initconst = {
 	{ OMAP5_L4_ABE_CLKCTRL, NULL, 0, "abe_iclk" },
+	{ OMAP5_AESS_CLKCTRL, omap5_aess_bit_data, CLKF_SW_SUP, "abe_cm:clk:0008:24" },
 	{ OMAP5_MCPDM_CLKCTRL, NULL, CLKF_SW_SUP, "pad_clks_ck" },
 	{ OMAP5_DMIC_CLKCTRL, omap5_dmic_bit_data, CLKF_SW_SUP, "abe_cm:clk:0018:24" },
 	{ OMAP5_MCBSP1_CLKCTRL, omap5_mcbsp1_bit_data, CLKF_SW_SUP, "abe_cm:clk:0028:24" },
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 5f46782cebeb..14b645093107 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -146,6 +146,29 @@ static const struct omap_clkctrl_reg_data dra7_rtc_clkctrl_regs[] __initconst =
 	{ 0 },
 };
 
+static const char * const dra7_cam_gfclk_mux_parents[] __initconst = {
+	"l3_iclk_div",
+	"core_iss_main_clk",
+	NULL,
+};
+
+static const struct omap_clkctrl_bit_data dra7_cam_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_cam_gfclk_mux_parents, NULL },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_cam_clkctrl_regs[] __initconst = {
+	{ DRA7_CAM_VIP1_CLKCTRL, dra7_cam_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_CAM_VIP2_CLKCTRL, dra7_cam_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ DRA7_CAM_VIP3_CLKCTRL, dra7_cam_bit_data, CLKF_HW_SUP, "l3_iclk_div" },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_vpe_clkctrl_regs[] __initconst = {
+	{ DRA7_VPE_VPE_CLKCTRL, NULL, CLKF_HW_SUP, "dpll_core_h23x2_ck" },
+	{ 0 },
+};
+
 static const struct omap_clkctrl_reg_data dra7_coreaon_clkctrl_regs[] __initconst = {
 	{ DRA7_COREAON_SMARTREFLEX_MPU_CLKCTRL, NULL, CLKF_SW_SUP, "wkupaon_iclk_mux" },
 	{ DRA7_COREAON_SMARTREFLEX_CORE_CLKCTRL, NULL, CLKF_SW_SUP, "wkupaon_iclk_mux" },
@@ -275,6 +298,40 @@ static const struct omap_clkctrl_reg_data dra7_dss_clkctrl_regs[] __initconst =
 	{ 0 },
 };
 
+static const char * const dra7_gpu_core_mux_parents[] __initconst = {
+	"dpll_core_h14x2_ck",
+	"dpll_per_h14x2_ck",
+	"dpll_gpu_m2_ck",
+	NULL,
+};
+
+static const char * const dra7_gpu_hyd_mux_parents[] __initconst = {
+	"dpll_core_h14x2_ck",
+	"dpll_per_h14x2_ck",
+	"dpll_gpu_m2_ck",
+	NULL,
+};
+
+static const char * const dra7_gpu_sys_clk_parents[] __initconst = {
+	"sys_clkin",
+	NULL,
+};
+
+static const struct omap_clkctrl_div_data dra7_gpu_sys_clk_data __initconst = {
+	.max_div = 2,
+};
+
+static const struct omap_clkctrl_bit_data dra7_gpu_core_bit_data[] __initconst = {
+	{ 24, TI_CLK_MUX, dra7_gpu_core_mux_parents, NULL, },
+	{ 26, TI_CLK_MUX, dra7_gpu_hyd_mux_parents, NULL, },
+	{ 0 },
+};
+
+static const struct omap_clkctrl_reg_data dra7_gpu_clkctrl_regs[] __initconst = {
+	{ DRA7_GPU_CLKCTRL, dra7_gpu_core_bit_data, CLKF_SW_SUP, "gpu_cm:clk:0000:24", },
+	{ 0 },
+};
+
 static const char * const dra7_mmc1_fclk_mux_parents[] __initconst = {
 	"func_128m_clk",
 	"dpll_per_m2x2_ck",
@@ -405,7 +462,7 @@ static const struct omap_clkctrl_bit_data dra7_gmac_bit_data[] __initconst = {
 };
 
 static const struct omap_clkctrl_reg_data dra7_gmac_clkctrl_regs[] __initconst = {
-	{ DRA7_GMAC_GMAC_CLKCTRL, dra7_gmac_bit_data, CLKF_SW_SUP, "dpll_gmac_ck" },
+	{ DRA7_GMAC_GMAC_CLKCTRL, dra7_gmac_bit_data, CLKF_SW_SUP, "gmac_main_clk" },
 	{ 0 },
 };
 
@@ -769,6 +826,7 @@ const struct omap_clkctrl_data dra7_clkctrl_data[] __initconst = {
 	{ 0x4a005550, dra7_ipu_clkctrl_regs },
 	{ 0x4a005620, dra7_dsp2_clkctrl_regs },
 	{ 0x4a005720, dra7_rtc_clkctrl_regs },
+	{ 0x4a005760, dra7_vpe_clkctrl_regs },
 	{ 0x4a008620, dra7_coreaon_clkctrl_regs },
 	{ 0x4a008720, dra7_l3main1_clkctrl_regs },
 	{ 0x4a008920, dra7_ipu2_clkctrl_regs },
@@ -777,7 +835,9 @@ const struct omap_clkctrl_data dra7_clkctrl_data[] __initconst = {
 	{ 0x4a008c00, dra7_atl_clkctrl_regs },
 	{ 0x4a008d20, dra7_l4cfg_clkctrl_regs },
 	{ 0x4a008e20, dra7_l3instr_clkctrl_regs },
+	{ 0x4a009020, dra7_cam_clkctrl_regs },
 	{ 0x4a009120, dra7_dss_clkctrl_regs },
+	{ 0x4a009220, dra7_gpu_clkctrl_regs },
 	{ 0x4a009320, dra7_l3init_clkctrl_regs },
 	{ 0x4a0093b0, dra7_pcie_clkctrl_regs },
 	{ 0x4a0093d0, dra7_gmac_clkctrl_regs },
diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c
index e0b8ed3a1e80..3da33c786d77 100644
--- a/drivers/clk/ti/clk.c
+++ b/drivers/clk/ti/clk.c
@@ -171,7 +171,9 @@ void __init ti_dt_clocks_register(struct ti_dt_clk oclks[])
 		node = of_find_node_by_name(NULL, buf);
 		if (num_args && compat_mode) {
 			parent = node;
-			node = of_get_child_by_name(parent, "clk");
+			node = of_get_child_by_name(parent, "clock");
+			if (!node)
+				node = of_get_child_by_name(parent, "clk");
 			of_node_put(parent);
 		}
 
diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c
index 17b9a761242f..062266034d84 100644
--- a/drivers/clk/ti/clkctrl.c
+++ b/drivers/clk/ti/clkctrl.c
@@ -440,6 +440,63 @@ static void __init _clkctrl_add_provider(void *data,
 	of_clk_add_hw_provider(np, _ti_omap4_clkctrl_xlate, data);
 }
 
+/* Get clock name based on compatible string for clkctrl */
+static char * __init clkctrl_get_name(struct device_node *np)
+{
+	struct property *prop;
+	const int prefix_len = 11;
+	const char *compat;
+	char *name;
+
+	of_property_for_each_string(np, "compatible", prop, compat) {
+		if (!strncmp("ti,clkctrl-", compat, prefix_len)) {
+			/* Two letter minimum name length for l3, l4 etc */
+			if (strnlen(compat + prefix_len, 16) < 2)
+				continue;
+			name = kasprintf(GFP_KERNEL, "%s", compat + prefix_len);
+			if (!name)
+				continue;
+			strreplace(name, '-', '_');
+
+			return name;
+		}
+	}
+	of_node_put(np);
+
+	return NULL;
+}
+
+/* Get clkctrl clock base name based on clkctrl_name or dts node */
+static const char * __init clkctrl_get_clock_name(struct device_node *np,
+						  const char *clkctrl_name,
+						  int offset, int index,
+						  bool legacy_naming)
+{
+	char *clock_name;
+
+	/* l4per-clkctrl:1234:0 style naming based on clkctrl_name */
+	if (clkctrl_name && !legacy_naming) {
+		clock_name = kasprintf(GFP_KERNEL, "%s-clkctrl:%04x:%d",
+				       clkctrl_name, offset, index);
+		strreplace(clock_name, '_', '-');
+
+		return clock_name;
+	}
+
+	/* l4per:1234:0 old style naming based on clkctrl_name */
+	if (clkctrl_name)
+		return kasprintf(GFP_KERNEL, "%s_cm:clk:%04x:%d",
+				 clkctrl_name, offset, index);
+
+	/* l4per_cm:1234:0 old style naming based on parent node name */
+	if (legacy_naming)
+		return kasprintf(GFP_KERNEL, "%pOFn:clk:%04x:%d",
+				 np->parent, offset, index);
+
+	/* l4per-clkctrl:1234:0 style naming based on node name */
+	return kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", np, offset, index);
+}
+
 static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 {
 	struct omap_clkctrl_provider *provider;
@@ -448,8 +505,10 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 	struct clk_init_data init = { NULL };
 	struct clk_hw_omap *hw;
 	struct clk *clk;
-	struct omap_clkctrl_clk *clkctrl_clk;
+	struct omap_clkctrl_clk *clkctrl_clk = NULL;
 	const __be32 *addrp;
+	bool legacy_naming;
+	char *clkctrl_name;
 	u32 addr;
 	int ret;
 	char *c;
@@ -537,7 +596,19 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 
 	provider->base = of_iomap(node, 0);
 
-	if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) {
+	legacy_naming = ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT;
+	clkctrl_name = clkctrl_get_name(node);
+	if (clkctrl_name) {
+		provider->clkdm_name = kasprintf(GFP_KERNEL,
+						 "%s_clkdm", clkctrl_name);
+		goto clkdm_found;
+	}
+
+	/*
+	 * The code below can be removed when all clkctrl nodes use domain
+	 * specific compatible proprerty and standard clock node naming
+	 */
+	if (legacy_naming) {
 		provider->clkdm_name = kasprintf(GFP_KERNEL, "%pOFnxxx", node->parent);
 		if (!provider->clkdm_name) {
 			kfree(provider);
@@ -573,7 +644,7 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 			*c = '_';
 		c++;
 	}
-
+clkdm_found:
 	INIT_LIST_HEAD(&provider->clocks);
 
 	/* Generate clocks */
@@ -612,15 +683,15 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 		init.flags = 0;
 		if (reg_data->flags & CLKF_SET_RATE_PARENT)
 			init.flags |= CLK_SET_RATE_PARENT;
-		if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT)
-			init.name = kasprintf(GFP_KERNEL, "%pOFn:%pOFn:%04x:%d",
-					      node->parent, node,
-					      reg_data->offset, 0);
-		else
-			init.name = kasprintf(GFP_KERNEL, "%pOFn:%04x:%d",
-					      node, reg_data->offset, 0);
+
+		init.name = clkctrl_get_clock_name(node, clkctrl_name,
+						   reg_data->offset, 0,
+						   legacy_naming);
+		if (!init.name)
+			goto cleanup;
+
 		clkctrl_clk = kzalloc(sizeof(*clkctrl_clk), GFP_KERNEL);
-		if (!init.name || !clkctrl_clk)
+		if (!clkctrl_clk)
 			goto cleanup;
 
 		init.ops = &omap4_clkctrl_clk_ops;
@@ -642,11 +713,14 @@ static void __init _ti_omap4_clkctrl_setup(struct device_node *node)
 	if (ret == -EPROBE_DEFER)
 		ti_clk_retry_init(node, provider, _clkctrl_add_provider);
 
+	kfree(clkctrl_name);
+
 	return;
 
 cleanup:
 	kfree(hw);
 	kfree(init.name);
+	kfree(clkctrl_name);
 	kfree(clkctrl_clk);
 }
 CLK_OF_DECLARE(ti_omap4_clkctrl_clock, "ti,clkctrl",
diff --git a/drivers/clk/ti/clock.h b/drivers/clk/ti/clock.h
index e6995c04001e..f1dd62de2bfc 100644
--- a/drivers/clk/ti/clock.h
+++ b/drivers/clk/ti/clock.h
@@ -253,7 +253,7 @@ extern const struct clk_ops omap_gate_clk_ops;
 
 extern struct ti_clk_features ti_clk_features;
 
-void omap2_init_clk_clkdm(struct clk_hw *hw);
+int omap2_init_clk_clkdm(struct clk_hw *hw);
 int omap2_clkops_enable_clkdm(struct clk_hw *hw);
 void omap2_clkops_disable_clkdm(struct clk_hw *hw);
 
diff --git a/drivers/clk/ti/clockdomain.c b/drivers/clk/ti/clockdomain.c
index 423a99b9f10c..ee56306f79d5 100644
--- a/drivers/clk/ti/clockdomain.c
+++ b/drivers/clk/ti/clockdomain.c
@@ -101,16 +101,16 @@ void omap2_clkops_disable_clkdm(struct clk_hw *hw)
  *
  * Convert a clockdomain name stored in a struct clk 'clk' into a
  * clockdomain pointer, and save it into the struct clk.  Intended to be
- * called during clk_register().  No return value.
+ * called during clk_register(). Returns 0 on success, -EERROR otherwise.
  */
-void omap2_init_clk_clkdm(struct clk_hw *hw)
+int omap2_init_clk_clkdm(struct clk_hw *hw)
 {
 	struct clk_hw_omap *clk = to_clk_hw_omap(hw);
 	struct clockdomain *clkdm;
 	const char *clk_name;
 
 	if (!clk->clkdm_name)
-		return;
+		return 0;
 
 	clk_name = __clk_get_name(hw->clk);
 
@@ -123,6 +123,8 @@ void omap2_init_clk_clkdm(struct clk_hw *hw)
 		pr_debug("clock: could not associate clk %s to clkdm %s\n",
 			 clk_name, clk->clkdm_name);
 	}
+
+	return 0;
 }
 
 static void __init of_ti_clockdomain_setup(struct device_node *node)
diff --git a/drivers/clk/uniphier/clk-uniphier-peri.c b/drivers/clk/uniphier/clk-uniphier-peri.c
index 9caa52944b1c..3e32db9dad81 100644
--- a/drivers/clk/uniphier/clk-uniphier-peri.c
+++ b/drivers/clk/uniphier/clk-uniphier-peri.c
@@ -18,8 +18,8 @@
 #define UNIPHIER_PERI_CLK_FI2C(idx, ch)					\
 	UNIPHIER_CLK_GATE("i2c" #ch, (idx), "i2c", 0x24, 24 + (ch))
 
-#define UNIPHIER_PERI_CLK_SCSSI(idx)					\
-	UNIPHIER_CLK_GATE("scssi", (idx), "spi", 0x20, 17)
+#define UNIPHIER_PERI_CLK_SCSSI(idx, ch)				\
+	UNIPHIER_CLK_GATE("scssi" #ch, (idx), "spi", 0x20, 17 + (ch))
 
 #define UNIPHIER_PERI_CLK_MCSSI(idx)					\
 	UNIPHIER_CLK_GATE("mcssi", (idx), "spi", 0x24, 14)
@@ -35,7 +35,7 @@ const struct uniphier_clk_data uniphier_ld4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_I2C(6, 2),
 	UNIPHIER_PERI_CLK_I2C(7, 3),
 	UNIPHIER_PERI_CLK_I2C(8, 4),
-	UNIPHIER_PERI_CLK_SCSSI(11),
+	UNIPHIER_PERI_CLK_SCSSI(11, 0),
 	{ /* sentinel */ }
 };
 
@@ -51,7 +51,10 @@ const struct uniphier_clk_data uniphier_pro4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_FI2C(8, 4),
 	UNIPHIER_PERI_CLK_FI2C(9, 5),
 	UNIPHIER_PERI_CLK_FI2C(10, 6),
-	UNIPHIER_PERI_CLK_SCSSI(11),
-	UNIPHIER_PERI_CLK_MCSSI(12),
+	UNIPHIER_PERI_CLK_SCSSI(11, 0),
+	UNIPHIER_PERI_CLK_SCSSI(12, 1),
+	UNIPHIER_PERI_CLK_SCSSI(13, 2),
+	UNIPHIER_PERI_CLK_SCSSI(14, 3),
+	UNIPHIER_PERI_CLK_MCSSI(15),
 	{ /* sentinel */ }
 };
diff --git a/drivers/clk/ux500/u8500_of_clk.c b/drivers/clk/ux500/u8500_of_clk.c
index 72ed97c6662a..0aedd42fad52 100644
--- a/drivers/clk/ux500/u8500_of_clk.c
+++ b/drivers/clk/ux500/u8500_of_clk.c
@@ -99,8 +99,10 @@ static void u8500_clk_init(struct device_node *np)
 	if (fw_version != NULL) {
 		switch (fw_version->project) {
 		case PRCMU_FW_PROJECT_U8500_C2:
+		case PRCMU_FW_PROJECT_U8500_MBL:
 		case PRCMU_FW_PROJECT_U8520:
 		case PRCMU_FW_PROJECT_U8420:
+		case PRCMU_FW_PROJECT_U8420_SYSCLK:
 			sgaclk_parent = "soc0_pll";
 			break;
 		default:
diff --git a/drivers/clk/versatile/Kconfig b/drivers/clk/versatile/Kconfig
index ac766855ba16..c2618f1477a2 100644
--- a/drivers/clk/versatile/Kconfig
+++ b/drivers/clk/versatile/Kconfig
@@ -9,7 +9,7 @@ config COMMON_CLK_VERSATILE
 		COMPILE_TEST
 	select REGMAP_MMIO
 	---help---
-          Supports clocking on ARM Reference designs:
+	  Supports clocking on ARM Reference designs:
 	  - Integrator/AP and Integrator/CP
 	  - RealView PB1176, EB, PB11MP and PBX
 	  - Versatile Express
diff --git a/drivers/clk/zynqmp/clkc.c b/drivers/clk/zynqmp/clkc.c
index a11f93ecbf34..10e89f23880b 100644
--- a/drivers/clk/zynqmp/clkc.c
+++ b/drivers/clk/zynqmp/clkc.c
@@ -2,7 +2,7 @@
 /*
  * Zynq UltraScale+ MPSoC clock controller
  *
- *  Copyright (C) 2016-2018 Xilinx
+ *  Copyright (C) 2016-2019 Xilinx
  *
  * Based on drivers/clk/zynq/clkc.c
  */
@@ -749,6 +749,7 @@ static int zynqmp_clock_probe(struct platform_device *pdev)
 
 static const struct of_device_id zynqmp_clock_of_match[] = {
 	{.compatible = "xlnx,zynqmp-clk"},
+	{.compatible = "xlnx,versal-clk"},
 	{},
 };
 MODULE_DEVICE_TABLE(of, zynqmp_clock_of_match);
diff --git a/drivers/clk/zynqmp/divider.c b/drivers/clk/zynqmp/divider.c
index d8f5b70d2709..4be2cc76aa2e 100644
--- a/drivers/clk/zynqmp/divider.c
+++ b/drivers/clk/zynqmp/divider.c
@@ -2,7 +2,7 @@
 /*
  * Zynq UltraScale+ MPSoC Divider support
  *
- *  Copyright (C) 2016-2018 Xilinx
+ *  Copyright (C) 2016-2019 Xilinx
  *
  * Adjustable divider clock implementation
  */
@@ -41,12 +41,30 @@ struct zynqmp_clk_divider {
 	bool is_frac;
 	u32 clk_id;
 	u32 div_type;
+	u16 max_div;
 };
 
 static inline int zynqmp_divider_get_val(unsigned long parent_rate,
-					 unsigned long rate)
+					 unsigned long rate, u16 flags)
 {
-	return DIV_ROUND_CLOSEST(parent_rate, rate);
+	int up, down;
+	unsigned long up_rate, down_rate;
+
+	if (flags & CLK_DIVIDER_POWER_OF_TWO) {
+		up = DIV_ROUND_UP_ULL((u64)parent_rate, rate);
+		down = DIV_ROUND_DOWN_ULL((u64)parent_rate, rate);
+
+		up = __roundup_pow_of_two(up);
+		down = __rounddown_pow_of_two(down);
+
+		up_rate = DIV_ROUND_UP_ULL((u64)parent_rate, up);
+		down_rate = DIV_ROUND_UP_ULL((u64)parent_rate, down);
+
+		return (rate - up_rate) <= (down_rate - rate) ? up : down;
+
+	} else {
+		return DIV_ROUND_CLOSEST(parent_rate, rate);
+	}
 }
 
 /**
@@ -78,6 +96,9 @@ static unsigned long zynqmp_clk_divider_recalc_rate(struct clk_hw *hw,
 	else
 		value = div >> 16;
 
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+		value = 1 << value;
+
 	if (!value) {
 		WARN(!(divider->flags & CLK_DIVIDER_ALLOW_ZERO),
 		     "%s: Zero divisor and CLK_DIVIDER_ALLOW_ZERO not set\n",
@@ -88,6 +109,42 @@ static unsigned long zynqmp_clk_divider_recalc_rate(struct clk_hw *hw,
 	return DIV_ROUND_UP_ULL(parent_rate, value);
 }
 
+static void zynqmp_get_divider2_val(struct clk_hw *hw,
+				    unsigned long rate,
+				    unsigned long parent_rate,
+				    struct zynqmp_clk_divider *divider,
+				    int *bestdiv)
+{
+	int div1;
+	int div2;
+	long error = LONG_MAX;
+	struct clk_hw *parent_hw = clk_hw_get_parent(hw);
+	struct zynqmp_clk_divider *pdivider = to_zynqmp_clk_divider(parent_hw);
+
+	if (!pdivider)
+		return;
+
+	*bestdiv = 1;
+	for (div1 = 1; div1 <= pdivider->max_div;) {
+		for (div2 = 1; div2 <= divider->max_div;) {
+			long new_error = ((parent_rate / div1) / div2) - rate;
+
+			if (abs(new_error) < abs(error)) {
+				*bestdiv = div2;
+				error = new_error;
+			}
+			if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+				div2 = div2 << 1;
+			else
+				div2++;
+		}
+		if (pdivider->flags & CLK_DIVIDER_POWER_OF_TWO)
+			div1 = div1 << 1;
+		else
+			div1++;
+	}
+}
+
 /**
  * zynqmp_clk_divider_round_rate() - Round rate of divider clock
  * @hw:			handle between common and hardware-specific interfaces
@@ -120,10 +177,23 @@ static long zynqmp_clk_divider_round_rate(struct clk_hw *hw,
 		else
 			bestdiv  = bestdiv >> 16;
 
+		if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+			bestdiv = 1 << bestdiv;
+
 		return DIV_ROUND_UP_ULL((u64)*prate, bestdiv);
 	}
 
-	bestdiv = zynqmp_divider_get_val(*prate, rate);
+	bestdiv = zynqmp_divider_get_val(*prate, rate, divider->flags);
+
+	/*
+	 * In case of two divisors, compute best divider values and return
+	 * divider2 value based on compute value. div1 will  be automatically
+	 * set to optimum based on required total divider value.
+	 */
+	if (div_type == TYPE_DIV2 &&
+	    (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
+		zynqmp_get_divider2_val(hw, rate, *prate, divider, &bestdiv);
+	}
 
 	if ((clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) && divider->is_frac)
 		bestdiv = rate % *prate ? 1 : bestdiv;
@@ -151,7 +221,7 @@ static int zynqmp_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 	int ret;
 	const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops();
 
-	value = zynqmp_divider_get_val(parent_rate, rate);
+	value = zynqmp_divider_get_val(parent_rate, rate, divider->flags);
 	if (div_type == TYPE_DIV1) {
 		div = value & 0xFFFF;
 		div |= 0xffff << 16;
@@ -160,6 +230,9 @@ static int zynqmp_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 		div |= value << 16;
 	}
 
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+		div = __ffs(div);
+
 	ret = eemi_ops->clock_setdivider(clk_id, div);
 
 	if (ret)
@@ -176,6 +249,35 @@ static const struct clk_ops zynqmp_clk_divider_ops = {
 };
 
 /**
+ * zynqmp_clk_get_max_divisor() - Get maximum supported divisor from firmware.
+ * @clk_id:		Id of clock
+ * @type:		Divider type
+ *
+ * Return: Maximum divisor of a clock if query data is successful
+ *	   U16_MAX in case of query data is not success
+ */
+u32 zynqmp_clk_get_max_divisor(u32 clk_id, u32 type)
+{
+	const struct zynqmp_eemi_ops *eemi_ops = zynqmp_pm_get_eemi_ops();
+	struct zynqmp_pm_query_data qdata = {0};
+	u32 ret_payload[PAYLOAD_ARG_CNT];
+	int ret;
+
+	qdata.qid = PM_QID_CLOCK_GET_MAX_DIVISOR;
+	qdata.arg1 = clk_id;
+	qdata.arg2 = type;
+	ret = eemi_ops->query_data(qdata, ret_payload);
+	/*
+	 * To maintain backward compatibility return maximum possible value
+	 * (0xFFFF) if query for max divisor is not successful.
+	 */
+	if (ret)
+		return U16_MAX;
+
+	return ret_payload[1];
+}
+
+/**
  * zynqmp_clk_register_divider() - Register a divider clock
  * @name:		Name of this clock
  * @clk_id:		Id of clock
@@ -215,6 +317,12 @@ struct clk_hw *zynqmp_clk_register_divider(const char *name,
 	div->clk_id = clk_id;
 	div->div_type = nodes->type;
 
+	/*
+	 * To achieve best possible rate, maximum limit of divider is required
+	 * while computation.
+	 */
+	div->max_div = zynqmp_clk_get_max_divisor(clk_id, nodes->type);
+
 	hw = &div->hw;
 	ret = clk_hw_register(NULL, hw);
 	if (ret) {
diff --git a/drivers/clk/zynqmp/pll.c b/drivers/clk/zynqmp/pll.c
index a541397a172c..89b599530105 100644
--- a/drivers/clk/zynqmp/pll.c
+++ b/drivers/clk/zynqmp/pll.c
@@ -188,10 +188,12 @@ static int zynqmp_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 		frac = (parent_rate * f) / FRAC_DIV;
 
 		ret = eemi_ops->clock_setdivider(clk_id, m);
-		if (ret)
+		if (ret == -EUSERS)
+			WARN(1, "More than allowed devices are using the %s, which is forbidden\n",
+			     clk_name);
+		else if (ret)
 			pr_warn_once("%s() set divider failed for %s, ret = %d\n",
 				     __func__, clk_name, ret);
-
 		eemi_ops->ioctl(0, IOCTL_SET_PLL_FRAC_DATA, clk_id, f, NULL);
 
 		return rate + frac;
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index a06777c35fc0..bda0b2406fba 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -221,7 +221,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 	return ret;
 }
 
-static int cppc_verify_policy(struct cpufreq_policy *policy)
+static int cppc_verify_policy(struct cpufreq_policy_data *policy)
 {
 	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index cd53272e2fa2..f7a7bcf6f52e 100644
--- a/drivers/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -291,7 +291,7 @@ static int nforce2_target(struct cpufreq_policy *policy,
  * nforce2_verify - verifies a new CPUFreq policy
  * @policy: new policy
  */
-static int nforce2_verify(struct cpufreq_policy *policy)
+static int nforce2_verify(struct cpufreq_policy_data *policy)
 {
 	unsigned int fsb_pol_max;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 77114a3897fb..4adac3a8c265 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -74,6 +74,9 @@ static void cpufreq_exit_governor(struct cpufreq_policy *policy);
 static int cpufreq_start_governor(struct cpufreq_policy *policy);
 static void cpufreq_stop_governor(struct cpufreq_policy *policy);
 static void cpufreq_governor_limits(struct cpufreq_policy *policy);
+static int cpufreq_set_policy(struct cpufreq_policy *policy,
+			      struct cpufreq_governor *new_gov,
+			      unsigned int new_pol);
 
 /**
  * Two notifier lists: the "policy" list is involved in the
@@ -616,25 +619,22 @@ static struct cpufreq_governor *find_governor(const char *str_governor)
 	return NULL;
 }
 
-static int cpufreq_parse_policy(char *str_governor,
-				struct cpufreq_policy *policy)
+static unsigned int cpufreq_parse_policy(char *str_governor)
 {
-	if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
-		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
-		return 0;
-	}
-	if (!strncasecmp(str_governor, "powersave", CPUFREQ_NAME_LEN)) {
-		policy->policy = CPUFREQ_POLICY_POWERSAVE;
-		return 0;
-	}
-	return -EINVAL;
+	if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN))
+		return CPUFREQ_POLICY_PERFORMANCE;
+
+	if (!strncasecmp(str_governor, "powersave", CPUFREQ_NAME_LEN))
+		return CPUFREQ_POLICY_POWERSAVE;
+
+	return CPUFREQ_POLICY_UNKNOWN;
 }
 
 /**
  * cpufreq_parse_governor - parse a governor string only for has_target()
+ * @str_governor: Governor name.
  */
-static int cpufreq_parse_governor(char *str_governor,
-				  struct cpufreq_policy *policy)
+static struct cpufreq_governor *cpufreq_parse_governor(char *str_governor)
 {
 	struct cpufreq_governor *t;
 
@@ -648,7 +648,7 @@ static int cpufreq_parse_governor(char *str_governor,
 
 		ret = request_module("cpufreq_%s", str_governor);
 		if (ret)
-			return -EINVAL;
+			return NULL;
 
 		mutex_lock(&cpufreq_governor_mutex);
 
@@ -659,12 +659,7 @@ static int cpufreq_parse_governor(char *str_governor,
 
 	mutex_unlock(&cpufreq_governor_mutex);
 
-	if (t) {
-		policy->governor = t;
-		return 0;
-	}
-
-	return -EINVAL;
+	return t;
 }
 
 /**
@@ -765,28 +760,33 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 					const char *buf, size_t count)
 {
+	char str_governor[16];
 	int ret;
-	char	str_governor[16];
-	struct cpufreq_policy new_policy;
-
-	memcpy(&new_policy, policy, sizeof(*policy));
 
 	ret = sscanf(buf, "%15s", str_governor);
 	if (ret != 1)
 		return -EINVAL;
 
 	if (cpufreq_driver->setpolicy) {
-		if (cpufreq_parse_policy(str_governor, &new_policy))
+		unsigned int new_pol;
+
+		new_pol = cpufreq_parse_policy(str_governor);
+		if (!new_pol)
 			return -EINVAL;
+
+		ret = cpufreq_set_policy(policy, NULL, new_pol);
 	} else {
-		if (cpufreq_parse_governor(str_governor, &new_policy))
+		struct cpufreq_governor *new_gov;
+
+		new_gov = cpufreq_parse_governor(str_governor);
+		if (!new_gov)
 			return -EINVAL;
-	}
 
-	ret = cpufreq_set_policy(policy, &new_policy);
+		ret = cpufreq_set_policy(policy, new_gov,
+					 CPUFREQ_POLICY_UNKNOWN);
 
-	if (new_policy.governor)
-		module_put(new_policy.governor->owner);
+		module_put(new_gov->owner);
+	}
 
 	return ret ? ret : count;
 }
@@ -1053,40 +1053,33 @@ __weak struct cpufreq_governor *cpufreq_default_governor(void)
 
 static int cpufreq_init_policy(struct cpufreq_policy *policy)
 {
-	struct cpufreq_governor *gov = NULL, *def_gov = NULL;
-	struct cpufreq_policy new_policy;
-
-	memcpy(&new_policy, policy, sizeof(*policy));
-
-	def_gov = cpufreq_default_governor();
+	struct cpufreq_governor *def_gov = cpufreq_default_governor();
+	struct cpufreq_governor *gov = NULL;
+	unsigned int pol = CPUFREQ_POLICY_UNKNOWN;
 
 	if (has_target()) {
-		/*
-		 * Update governor of new_policy to the governor used before
-		 * hotplug
-		 */
+		/* Update policy governor to the one used before hotplug. */
 		gov = find_governor(policy->last_governor);
 		if (gov) {
 			pr_debug("Restoring governor %s for cpu %d\n",
-				policy->governor->name, policy->cpu);
-		} else {
-			if (!def_gov)
-				return -ENODATA;
+				 policy->governor->name, policy->cpu);
+		} else if (def_gov) {
 			gov = def_gov;
+		} else {
+			return -ENODATA;
 		}
-		new_policy.governor = gov;
 	} else {
 		/* Use the default policy if there is no last_policy. */
 		if (policy->last_policy) {
-			new_policy.policy = policy->last_policy;
+			pol = policy->last_policy;
+		} else if (def_gov) {
+			pol = cpufreq_parse_policy(def_gov->name);
 		} else {
-			if (!def_gov)
-				return -ENODATA;
-			cpufreq_parse_policy(def_gov->name, &new_policy);
+			return -ENODATA;
 		}
 	}
 
-	return cpufreq_set_policy(policy, &new_policy);
+	return cpufreq_set_policy(policy, gov, pol);
 }
 
 static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
@@ -1114,13 +1107,10 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 
 void refresh_frequency_limits(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy new_policy;
-
 	if (!policy_is_inactive(policy)) {
-		new_policy = *policy;
 		pr_debug("updating policy for CPU %u\n", policy->cpu);
 
-		cpufreq_set_policy(policy, &new_policy);
+		cpufreq_set_policy(policy, policy->governor, policy->policy);
 	}
 }
 EXPORT_SYMBOL(refresh_frequency_limits);
@@ -2364,46 +2354,49 @@ EXPORT_SYMBOL(cpufreq_get_policy);
 /**
  * cpufreq_set_policy - Modify cpufreq policy parameters.
  * @policy: Policy object to modify.
- * @new_policy: New policy data.
+ * @new_gov: Policy governor pointer.
+ * @new_pol: Policy value (for drivers with built-in governors).
  *
- * Pass @new_policy to the cpufreq driver's ->verify() callback. Next, copy the
- * min and max parameters of @new_policy to @policy and either invoke the
- * driver's ->setpolicy() callback (if present) or carry out a governor update
- * for @policy.  That is, run the current governor's ->limits() callback (if the
- * governor field in @new_policy points to the same object as the one in
- * @policy) or replace the governor for @policy with the new one stored in
- * @new_policy.
+ * Invoke the cpufreq driver's ->verify() callback to sanity-check the frequency
+ * limits to be set for the policy, update @policy with the verified limits
+ * values and either invoke the driver's ->setpolicy() callback (if present) or
+ * carry out a governor update for @policy.  That is, run the current governor's
+ * ->limits() callback (if @new_gov points to the same object as the one in
+ * @policy) or replace the governor for @policy with @new_gov.
  *
  * The cpuinfo part of @policy is not updated by this function.
  */
-int cpufreq_set_policy(struct cpufreq_policy *policy,
-		       struct cpufreq_policy *new_policy)
+static int cpufreq_set_policy(struct cpufreq_policy *policy,
+			      struct cpufreq_governor *new_gov,
+			      unsigned int new_pol)
 {
+	struct cpufreq_policy_data new_data;
 	struct cpufreq_governor *old_gov;
 	int ret;
 
-	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
-		 new_policy->cpu, new_policy->min, new_policy->max);
-
-	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
-
+	memcpy(&new_data.cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
+	new_data.freq_table = policy->freq_table;
+	new_data.cpu = policy->cpu;
 	/*
 	 * PM QoS framework collects all the requests from users and provide us
 	 * the final aggregated value here.
 	 */
-	new_policy->min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN);
-	new_policy->max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX);
+	new_data.min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN);
+	new_data.max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX);
+
+	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
+		 new_data.cpu, new_data.min, new_data.max);
 
 	/*
 	 * Verify that the CPU speed can be set within these limits and make sure
 	 * that min <= max.
 	 */
-	ret = cpufreq_driver->verify(new_policy);
+	ret = cpufreq_driver->verify(&new_data);
 	if (ret)
 		return ret;
 
-	policy->min = new_policy->min;
-	policy->max = new_policy->max;
+	policy->min = new_data.min;
+	policy->max = new_data.max;
 	trace_cpu_frequency_limits(policy);
 
 	policy->cached_target_freq = UINT_MAX;
@@ -2412,12 +2405,12 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 		 policy->min, policy->max);
 
 	if (cpufreq_driver->setpolicy) {
-		policy->policy = new_policy->policy;
+		policy->policy = new_pol;
 		pr_debug("setting range\n");
 		return cpufreq_driver->setpolicy(policy);
 	}
 
-	if (new_policy->governor == policy->governor) {
+	if (new_gov == policy->governor) {
 		pr_debug("governor limits update\n");
 		cpufreq_governor_limits(policy);
 		return 0;
@@ -2434,7 +2427,7 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	}
 
 	/* start new governor */
-	policy->governor = new_policy->governor;
+	policy->governor = new_gov;
 	ret = cpufreq_init_governor(policy);
 	if (!ret) {
 		ret = cpufreq_start_governor(policy);
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index ded427e0a488..e117b0059123 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -60,7 +60,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 		return 0;
 }
 
-int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
+int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy,
 				   struct cpufreq_frequency_table *table)
 {
 	struct cpufreq_frequency_table *pos;
@@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
  * Generic routine to verify policy & frequency table, requires driver to set
  * policy->freq_table prior to it.
  */
-int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy)
+int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy)
 {
 	if (!policy->freq_table)
 		return -ENODEV;
diff --git a/drivers/cpufreq/gx-suspmod.c b/drivers/cpufreq/gx-suspmod.c
index e97b5733aa24..75b3ef7ec679 100644
--- a/drivers/cpufreq/gx-suspmod.c
+++ b/drivers/cpufreq/gx-suspmod.c
@@ -328,7 +328,7 @@ static void gx_set_cpuspeed(struct cpufreq_policy *policy, unsigned int khz)
  *      for the hardware supported by the driver.
  */
 
-static int cpufreq_gx_verify(struct cpufreq_policy *policy)
+static int cpufreq_gx_verify(struct cpufreq_policy_data *policy)
 {
 	unsigned int tmp_freq = 0;
 	u8 tmp1, tmp2;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ad6a17cf0011..c81e1ff29069 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2036,8 +2036,9 @@ static int intel_pstate_get_max_freq(struct cpudata *cpu)
 			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
 }
 
-static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
-					    struct cpudata *cpu)
+static void intel_pstate_update_perf_limits(struct cpudata *cpu,
+					    unsigned int policy_min,
+					    unsigned int policy_max)
 {
 	int max_freq = intel_pstate_get_max_freq(cpu);
 	int32_t max_policy_perf, min_policy_perf;
@@ -2056,18 +2057,17 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
 		turbo_max = cpu->pstate.turbo_pstate;
 	}
 
-	max_policy_perf = max_state * policy->max / max_freq;
-	if (policy->max == policy->min) {
+	max_policy_perf = max_state * policy_max / max_freq;
+	if (policy_max == policy_min) {
 		min_policy_perf = max_policy_perf;
 	} else {
-		min_policy_perf = max_state * policy->min / max_freq;
+		min_policy_perf = max_state * policy_min / max_freq;
 		min_policy_perf = clamp_t(int32_t, min_policy_perf,
 					  0, max_policy_perf);
 	}
 
 	pr_debug("cpu:%d max_state %d min_policy_perf:%d max_policy_perf:%d\n",
-		 policy->cpu, max_state,
-		 min_policy_perf, max_policy_perf);
+		 cpu->cpu, max_state, min_policy_perf, max_policy_perf);
 
 	/* Normalize user input to [min_perf, max_perf] */
 	if (per_cpu_limits) {
@@ -2081,7 +2081,7 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
 		global_min = DIV_ROUND_UP(turbo_max * global.min_perf_pct, 100);
 		global_min = clamp_t(int32_t, global_min, 0, global_max);
 
-		pr_debug("cpu:%d global_min:%d global_max:%d\n", policy->cpu,
+		pr_debug("cpu:%d global_min:%d global_max:%d\n", cpu->cpu,
 			 global_min, global_max);
 
 		cpu->min_perf_ratio = max(min_policy_perf, global_min);
@@ -2094,7 +2094,7 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
 					  cpu->max_perf_ratio);
 
 	}
-	pr_debug("cpu:%d max_perf_ratio:%d min_perf_ratio:%d\n", policy->cpu,
+	pr_debug("cpu:%d max_perf_ratio:%d min_perf_ratio:%d\n", cpu->cpu,
 		 cpu->max_perf_ratio,
 		 cpu->min_perf_ratio);
 }
@@ -2114,7 +2114,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	mutex_lock(&intel_pstate_limits_lock);
 
-	intel_pstate_update_perf_limits(policy, cpu);
+	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);
 
 	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		/*
@@ -2143,8 +2143,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
-					 struct cpudata *cpu)
+static void intel_pstate_adjust_policy_max(struct cpudata *cpu,
+					   struct cpufreq_policy_data *policy)
 {
 	if (!hwp_active &&
 	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
@@ -2155,7 +2155,7 @@ static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
 	}
 }
 
-static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
+static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 
@@ -2163,11 +2163,7 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
 				     intel_pstate_get_max_freq(cpu));
 
-	if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
-	    policy->policy != CPUFREQ_POLICY_PERFORMANCE)
-		return -EINVAL;
-
-	intel_pstate_adjust_policy_max(policy, cpu);
+	intel_pstate_adjust_policy_max(cpu, policy);
 
 	return 0;
 }
@@ -2268,7 +2264,7 @@ static struct cpufreq_driver intel_pstate = {
 	.name		= "intel_pstate",
 };
 
-static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
+static int intel_cpufreq_verify_policy(struct cpufreq_policy_data *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 
@@ -2276,9 +2272,9 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
 				     intel_pstate_get_max_freq(cpu));
 
-	intel_pstate_adjust_policy_max(policy, cpu);
+	intel_pstate_adjust_policy_max(cpu, policy);
 
-	intel_pstate_update_perf_limits(policy, cpu);
+	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/longrun.c b/drivers/cpufreq/longrun.c
index 64b8689f7a4a..0b08be8bff76 100644
--- a/drivers/cpufreq/longrun.c
+++ b/drivers/cpufreq/longrun.c
@@ -122,7 +122,7 @@ static int longrun_set_policy(struct cpufreq_policy *policy)
  * Validates a new CPUFreq policy. This function has to be called with
  * cpufreq_driver locked.
  */
-static int longrun_verify_policy(struct cpufreq_policy *policy)
+static int longrun_verify_policy(struct cpufreq_policy_data *policy)
 {
 	if (!policy)
 		return -EINVAL;
@@ -130,10 +130,6 @@ static int longrun_verify_policy(struct cpufreq_policy *policy)
 	policy->cpu = 0;
 	cpufreq_verify_within_cpu_limits(policy);
 
-	if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
-	    (policy->policy != CPUFREQ_POLICY_PERFORMANCE))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 89d4fa8b65e9..5789fe7a94bd 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -109,7 +109,7 @@ struct pcc_cpu {
 
 static struct pcc_cpu __percpu *pcc_cpu_info;
 
-static int pcc_cpufreq_verify(struct cpufreq_policy *policy)
+static int pcc_cpufreq_verify(struct cpufreq_policy_data *policy)
 {
 	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 5096c0ab781b..0ac265d47ef0 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -87,7 +87,7 @@ static int sh_cpufreq_target(struct cpufreq_policy *policy,
 	return work_on_cpu(policy->cpu, __sh_cpufreq_target, &data);
 }
 
-static int sh_cpufreq_verify(struct cpufreq_policy *policy)
+static int sh_cpufreq_verify(struct cpufreq_policy_data *policy)
 {
 	struct clk *cpuclk = &per_cpu(sh_cpuclk, policy->cpu);
 	struct cpufreq_frequency_table *freq_table;
diff --git a/drivers/cpufreq/unicore2-cpufreq.c b/drivers/cpufreq/unicore2-cpufreq.c
index 707dbc1b7ac8..98d392196df2 100644
--- a/drivers/cpufreq/unicore2-cpufreq.c
+++ b/drivers/cpufreq/unicore2-cpufreq.c
@@ -22,7 +22,7 @@ static struct cpufreq_driver ucv2_driver;
 /* make sure that only the "userspace" governor is run
  * -- anything else wouldn't make sense on this platform, anyway.
  */
-static int ucv2_verify_speed(struct cpufreq_policy *policy)
+static int ucv2_verify_speed(struct cpufreq_policy_data *policy)
 {
 	if (policy->cpu)
 		return -EINVAL;
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index a23b6752d11a..0613bb7770f5 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -44,4 +44,15 @@ config DMABUF_SELFTESTS
 	default n
 	depends on DMA_SHARED_BUFFER
 
+menuconfig DMABUF_HEAPS
+	bool "DMA-BUF Userland Memory Heaps"
+	select DMA_SHARED_BUFFER
+	help
+	  Choose this option to enable the DMA-BUF userland memory heaps.
+	  This options creates per heap chardevs in /dev/dma_heap/ which
+	  allows userspace to allocate dma-bufs that can be shared
+	  between drivers.
+
+source "drivers/dma-buf/heaps/Kconfig"
+
 endmenu
diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile
index 03479da06422..9c190026bfab 100644
--- a/drivers/dma-buf/Makefile
+++ b/drivers/dma-buf/Makefile
@@ -1,6 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y := dma-buf.o dma-fence.o dma-fence-array.o dma-fence-chain.o \
 	 dma-resv.o seqno-fence.o
+obj-$(CONFIG_DMABUF_HEAPS)	+= dma-heap.o
+obj-$(CONFIG_DMABUF_HEAPS)	+= heaps/
 obj-$(CONFIG_SYNC_FILE)		+= sync_file.o
 obj-$(CONFIG_SW_SYNC)		+= sw_sync.o sync_debug.o
 obj-$(CONFIG_UDMABUF)		+= udmabuf.o
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index ce41cd9b758a..d4097856c86b 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -878,29 +878,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
  *   with calls to dma_buf_begin_cpu_access() and dma_buf_end_cpu_access()
  *   access.
  *
- *   To support dma_buf objects residing in highmem cpu access is page-based
- *   using an api similar to kmap. Accessing a dma_buf is done in aligned chunks
- *   of PAGE_SIZE size. Before accessing a chunk it needs to be mapped, which
- *   returns a pointer in kernel virtual address space. Afterwards the chunk
- *   needs to be unmapped again. There is no limit on how often a given chunk
- *   can be mapped and unmapped, i.e. the importer does not need to call
- *   begin_cpu_access again before mapping the same chunk again.
- *
- *   Interfaces::
- *      void \*dma_buf_kmap(struct dma_buf \*, unsigned long);
- *      void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*);
- *
- *   Implementing the functions is optional for exporters and for importers all
- *   the restrictions of using kmap apply.
- *
- *   dma_buf kmap calls outside of the range specified in begin_cpu_access are
- *   undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on
- *   the partial chunks at the beginning and end but may return stale or bogus
- *   data outside of the range (in these partial chunks).
- *
- *   For some cases the overhead of kmap can be too high, a vmap interface
- *   is introduced. This interface should be used very carefully, as vmalloc
- *   space is a limited resources on many architectures.
+ *   Since for most kernel internal dma-buf accesses need the entire buffer, a
+ *   vmap interface is introduced. Note that on very old 32-bit architectures
+ *   vmalloc space might be limited and result in vmap calls failing.
  *
  *   Interfaces::
  *      void \*dma_buf_vmap(struct dma_buf \*dmabuf)
@@ -1050,43 +1030,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf,
 }
 EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
 
-/**
- * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
- * same restrictions as for kmap and friends apply.
- * @dmabuf:	[in]	buffer to map page from.
- * @page_num:	[in]	page in PAGE_SIZE units to map.
- *
- * This call must always succeed, any necessary preparations that might fail
- * need to be done in begin_cpu_access.
- */
-void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
-{
-	WARN_ON(!dmabuf);
-
-	if (!dmabuf->ops->map)
-		return NULL;
-	return dmabuf->ops->map(dmabuf, page_num);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kmap);
-
-/**
- * dma_buf_kunmap - Unmap a page obtained by dma_buf_kmap.
- * @dmabuf:	[in]	buffer to unmap page from.
- * @page_num:	[in]	page in PAGE_SIZE units to unmap.
- * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap.
- *
- * This call must always succeed.
- */
-void dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long page_num,
-		    void *vaddr)
-{
-	WARN_ON(!dmabuf);
-
-	if (dmabuf->ops->unmap)
-		dmabuf->ops->unmap(dmabuf, page_num, vaddr);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kunmap);
-
 
 /**
  * dma_buf_mmap - Setup up a userspace mmap with the given vma
diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c
new file mode 100644
index 000000000000..afd22c9dbdcf
--- /dev/null
+++ b/drivers/dma-buf/dma-heap.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Framework for userspace DMA-BUF allocations
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#include <linux/cdev.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/err.h>
+#include <linux/xarray.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/syscalls.h>
+#include <linux/dma-heap.h>
+#include <uapi/linux/dma-heap.h>
+
+#define DEVNAME "dma_heap"
+
+#define NUM_HEAP_MINORS 128
+
+/**
+ * struct dma_heap - represents a dmabuf heap in the system
+ * @name:		used for debugging/device-node name
+ * @ops:		ops struct for this heap
+ * @heap_devt		heap device node
+ * @list		list head connecting to list of heaps
+ * @heap_cdev		heap char device
+ *
+ * Represents a heap of memory from which buffers can be made.
+ */
+struct dma_heap {
+	const char *name;
+	const struct dma_heap_ops *ops;
+	void *priv;
+	dev_t heap_devt;
+	struct list_head list;
+	struct cdev heap_cdev;
+};
+
+static LIST_HEAD(heap_list);
+static DEFINE_MUTEX(heap_list_lock);
+static dev_t dma_heap_devt;
+static struct class *dma_heap_class;
+static DEFINE_XARRAY_ALLOC(dma_heap_minors);
+
+static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
+				 unsigned int fd_flags,
+				 unsigned int heap_flags)
+{
+	/*
+	 * Allocations from all heaps have to begin
+	 * and end on page boundaries.
+	 */
+	len = PAGE_ALIGN(len);
+	if (!len)
+		return -EINVAL;
+
+	return heap->ops->allocate(heap, len, fd_flags, heap_flags);
+}
+
+static int dma_heap_open(struct inode *inode, struct file *file)
+{
+	struct dma_heap *heap;
+
+	heap = xa_load(&dma_heap_minors, iminor(inode));
+	if (!heap) {
+		pr_err("dma_heap: minor %d unknown.\n", iminor(inode));
+		return -ENODEV;
+	}
+
+	/* instance data as context */
+	file->private_data = heap;
+	nonseekable_open(inode, file);
+
+	return 0;
+}
+
+static long dma_heap_ioctl_allocate(struct file *file, void *data)
+{
+	struct dma_heap_allocation_data *heap_allocation = data;
+	struct dma_heap *heap = file->private_data;
+	int fd;
+
+	if (heap_allocation->fd)
+		return -EINVAL;
+
+	if (heap_allocation->fd_flags & ~DMA_HEAP_VALID_FD_FLAGS)
+		return -EINVAL;
+
+	if (heap_allocation->heap_flags & ~DMA_HEAP_VALID_HEAP_FLAGS)
+		return -EINVAL;
+
+	fd = dma_heap_buffer_alloc(heap, heap_allocation->len,
+				   heap_allocation->fd_flags,
+				   heap_allocation->heap_flags);
+	if (fd < 0)
+		return fd;
+
+	heap_allocation->fd = fd;
+
+	return 0;
+}
+
+static unsigned int dma_heap_ioctl_cmds[] = {
+	DMA_HEAP_IOCTL_ALLOC,
+};
+
+static long dma_heap_ioctl(struct file *file, unsigned int ucmd,
+			   unsigned long arg)
+{
+	char stack_kdata[128];
+	char *kdata = stack_kdata;
+	unsigned int kcmd;
+	unsigned int in_size, out_size, drv_size, ksize;
+	int nr = _IOC_NR(ucmd);
+	int ret = 0;
+
+	if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds))
+		return -EINVAL;
+
+	/* Get the kernel ioctl cmd that matches */
+	kcmd = dma_heap_ioctl_cmds[nr];
+
+	/* Figure out the delta between user cmd size and kernel cmd size */
+	drv_size = _IOC_SIZE(kcmd);
+	out_size = _IOC_SIZE(ucmd);
+	in_size = out_size;
+	if ((ucmd & kcmd & IOC_IN) == 0)
+		in_size = 0;
+	if ((ucmd & kcmd & IOC_OUT) == 0)
+		out_size = 0;
+	ksize = max(max(in_size, out_size), drv_size);
+
+	/* If necessary, allocate buffer for ioctl argument */
+	if (ksize > sizeof(stack_kdata)) {
+		kdata = kmalloc(ksize, GFP_KERNEL);
+		if (!kdata)
+			return -ENOMEM;
+	}
+
+	if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) {
+		ret = -EFAULT;
+		goto err;
+	}
+
+	/* zero out any difference between the kernel/user structure size */
+	if (ksize > in_size)
+		memset(kdata + in_size, 0, ksize - in_size);
+
+	switch (kcmd) {
+	case DMA_HEAP_IOCTL_ALLOC:
+		ret = dma_heap_ioctl_allocate(file, kdata);
+		break;
+	default:
+		ret = -ENOTTY;
+		goto err;
+	}
+
+	if (copy_to_user((void __user *)arg, kdata, out_size) != 0)
+		ret = -EFAULT;
+err:
+	if (kdata != stack_kdata)
+		kfree(kdata);
+	return ret;
+}
+
+static const struct file_operations dma_heap_fops = {
+	.owner          = THIS_MODULE,
+	.open		= dma_heap_open,
+	.unlocked_ioctl = dma_heap_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= dma_heap_ioctl,
+#endif
+};
+
+/**
+ * dma_heap_get_drvdata() - get per-subdriver data for the heap
+ * @heap: DMA-Heap to retrieve private data for
+ *
+ * Returns:
+ * The per-subdriver data for the heap.
+ */
+void *dma_heap_get_drvdata(struct dma_heap *heap)
+{
+	return heap->priv;
+}
+
+struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info)
+{
+	struct dma_heap *heap, *h, *err_ret;
+	struct device *dev_ret;
+	unsigned int minor;
+	int ret;
+
+	if (!exp_info->name || !strcmp(exp_info->name, "")) {
+		pr_err("dma_heap: Cannot add heap without a name\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!exp_info->ops || !exp_info->ops->allocate) {
+		pr_err("dma_heap: Cannot add heap with invalid ops struct\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* check the name is unique */
+	mutex_lock(&heap_list_lock);
+	list_for_each_entry(h, &heap_list, list) {
+		if (!strcmp(h->name, exp_info->name)) {
+			mutex_unlock(&heap_list_lock);
+			pr_err("dma_heap: Already registered heap named %s\n",
+			       exp_info->name);
+			return ERR_PTR(-EINVAL);
+		}
+	}
+	mutex_unlock(&heap_list_lock);
+
+	heap = kzalloc(sizeof(*heap), GFP_KERNEL);
+	if (!heap)
+		return ERR_PTR(-ENOMEM);
+
+	heap->name = exp_info->name;
+	heap->ops = exp_info->ops;
+	heap->priv = exp_info->priv;
+
+	/* Find unused minor number */
+	ret = xa_alloc(&dma_heap_minors, &minor, heap,
+		       XA_LIMIT(0, NUM_HEAP_MINORS - 1), GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("dma_heap: Unable to get minor number for heap\n");
+		err_ret = ERR_PTR(ret);
+		goto err0;
+	}
+
+	/* Create device */
+	heap->heap_devt = MKDEV(MAJOR(dma_heap_devt), minor);
+
+	cdev_init(&heap->heap_cdev, &dma_heap_fops);
+	ret = cdev_add(&heap->heap_cdev, heap->heap_devt, 1);
+	if (ret < 0) {
+		pr_err("dma_heap: Unable to add char device\n");
+		err_ret = ERR_PTR(ret);
+		goto err1;
+	}
+
+	dev_ret = device_create(dma_heap_class,
+				NULL,
+				heap->heap_devt,
+				NULL,
+				heap->name);
+	if (IS_ERR(dev_ret)) {
+		pr_err("dma_heap: Unable to create device\n");
+		err_ret = ERR_CAST(dev_ret);
+		goto err2;
+	}
+	/* Add heap to the list */
+	mutex_lock(&heap_list_lock);
+	list_add(&heap->list, &heap_list);
+	mutex_unlock(&heap_list_lock);
+
+	return heap;
+
+err2:
+	cdev_del(&heap->heap_cdev);
+err1:
+	xa_erase(&dma_heap_minors, minor);
+err0:
+	kfree(heap);
+	return err_ret;
+}
+
+static char *dma_heap_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "dma_heap/%s", dev_name(dev));
+}
+
+static int dma_heap_init(void)
+{
+	int ret;
+
+	ret = alloc_chrdev_region(&dma_heap_devt, 0, NUM_HEAP_MINORS, DEVNAME);
+	if (ret)
+		return ret;
+
+	dma_heap_class = class_create(THIS_MODULE, DEVNAME);
+	if (IS_ERR(dma_heap_class)) {
+		unregister_chrdev_region(dma_heap_devt, NUM_HEAP_MINORS);
+		return PTR_ERR(dma_heap_class);
+	}
+	dma_heap_class->devnode = dma_heap_devnode;
+
+	return 0;
+}
+subsys_initcall(dma_heap_init);
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 709002515550..4264e64788c4 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -34,6 +34,7 @@
 
 #include <linux/dma-resv.h>
 #include <linux/export.h>
+#include <linux/sched/mm.h>
 
 /**
  * DOC: Reservation Object Overview
@@ -95,6 +96,37 @@ static void dma_resv_list_free(struct dma_resv_list *list)
 	kfree_rcu(list, rcu);
 }
 
+#if IS_ENABLED(CONFIG_LOCKDEP)
+static int __init dma_resv_lockdep(void)
+{
+	struct mm_struct *mm = mm_alloc();
+	struct ww_acquire_ctx ctx;
+	struct dma_resv obj;
+	int ret;
+
+	if (!mm)
+		return -ENOMEM;
+
+	dma_resv_init(&obj);
+
+	down_read(&mm->mmap_sem);
+	ww_acquire_init(&ctx, &reservation_ww_class);
+	ret = dma_resv_lock(&obj, &ctx);
+	if (ret == -EDEADLK)
+		dma_resv_lock_slow(&obj, &ctx);
+	fs_reclaim_acquire(GFP_KERNEL);
+	fs_reclaim_release(GFP_KERNEL);
+	ww_mutex_unlock(&obj.lock);
+	ww_acquire_fini(&ctx);
+	up_read(&mm->mmap_sem);
+	
+	mmput(mm);
+
+	return 0;
+}
+subsys_initcall(dma_resv_lockdep);
+#endif
+
 /**
  * dma_resv_init - initialize a reservation object
  * @obj: the reservation object
diff --git a/drivers/dma-buf/heaps/Kconfig b/drivers/dma-buf/heaps/Kconfig
new file mode 100644
index 000000000000..a5eef06c4226
--- /dev/null
+++ b/drivers/dma-buf/heaps/Kconfig
@@ -0,0 +1,14 @@
+config DMABUF_HEAPS_SYSTEM
+	bool "DMA-BUF System Heap"
+	depends on DMABUF_HEAPS
+	help
+	  Choose this option to enable the system dmabuf heap. The system heap
+	  is backed by pages from the buddy allocator. If in doubt, say Y.
+
+config DMABUF_HEAPS_CMA
+	bool "DMA-BUF CMA Heap"
+	depends on DMABUF_HEAPS && DMA_CMA
+	help
+	  Choose this option to enable dma-buf CMA heap. This heap is backed
+	  by the Contiguous Memory Allocator (CMA). If your system has these
+	  regions, you should say Y here.
diff --git a/drivers/dma-buf/heaps/Makefile b/drivers/dma-buf/heaps/Makefile
new file mode 100644
index 000000000000..6e54cdec3da0
--- /dev/null
+++ b/drivers/dma-buf/heaps/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y					+= heap-helpers.o
+obj-$(CONFIG_DMABUF_HEAPS_SYSTEM)	+= system_heap.o
+obj-$(CONFIG_DMABUF_HEAPS_CMA)		+= cma_heap.o
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
new file mode 100644
index 000000000000..626cf7fd033a
--- /dev/null
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF CMA heap exporter
+ *
+ * Copyright (C) 2012, 2019 Linaro Ltd.
+ * Author: <benjamin.gaignard@linaro.org> for ST-Ericsson.
+ */
+
+#include <linux/cma.h>
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/dma-contiguous.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/sched/signal.h>
+
+#include "heap-helpers.h"
+
+struct cma_heap {
+	struct dma_heap *heap;
+	struct cma *cma;
+};
+
+static void cma_heap_free(struct heap_helper_buffer *buffer)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(buffer->heap);
+	unsigned long nr_pages = buffer->pagecount;
+	struct page *cma_pages = buffer->priv_virt;
+
+	/* free page list */
+	kfree(buffer->pages);
+	/* release memory */
+	cma_release(cma_heap->cma, cma_pages, nr_pages);
+	kfree(buffer);
+}
+
+/* dmabuf heap CMA operations functions */
+static int cma_heap_allocate(struct dma_heap *heap,
+			     unsigned long len,
+			     unsigned long fd_flags,
+			     unsigned long heap_flags)
+{
+	struct cma_heap *cma_heap = dma_heap_get_drvdata(heap);
+	struct heap_helper_buffer *helper_buffer;
+	struct page *cma_pages;
+	size_t size = PAGE_ALIGN(len);
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	unsigned long align = get_order(size);
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	if (align > CONFIG_CMA_ALIGNMENT)
+		align = CONFIG_CMA_ALIGNMENT;
+
+	helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL);
+	if (!helper_buffer)
+		return -ENOMEM;
+
+	init_heap_helper_buffer(helper_buffer, cma_heap_free);
+	helper_buffer->heap = heap;
+	helper_buffer->size = len;
+
+	cma_pages = cma_alloc(cma_heap->cma, nr_pages, align, false);
+	if (!cma_pages)
+		goto free_buf;
+
+	if (PageHighMem(cma_pages)) {
+		unsigned long nr_clear_pages = nr_pages;
+		struct page *page = cma_pages;
+
+		while (nr_clear_pages > 0) {
+			void *vaddr = kmap_atomic(page);
+
+			memset(vaddr, 0, PAGE_SIZE);
+			kunmap_atomic(vaddr);
+			/*
+			 * Avoid wasting time zeroing memory if the process
+			 * has been killed by by SIGKILL
+			 */
+			if (fatal_signal_pending(current))
+				goto free_cma;
+
+			page++;
+			nr_clear_pages--;
+		}
+	} else {
+		memset(page_address(cma_pages), 0, size);
+	}
+
+	helper_buffer->pagecount = nr_pages;
+	helper_buffer->pages = kmalloc_array(helper_buffer->pagecount,
+					     sizeof(*helper_buffer->pages),
+					     GFP_KERNEL);
+	if (!helper_buffer->pages) {
+		ret = -ENOMEM;
+		goto free_cma;
+	}
+
+	for (pg = 0; pg < helper_buffer->pagecount; pg++)
+		helper_buffer->pages[pg] = &cma_pages[pg];
+
+	/* create the dmabuf */
+	dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto free_pages;
+	}
+
+	helper_buffer->dmabuf = dmabuf;
+	helper_buffer->priv_virt = cma_pages;
+
+	ret = dma_buf_fd(dmabuf, fd_flags);
+	if (ret < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+		return ret;
+	}
+
+	return ret;
+
+free_pages:
+	kfree(helper_buffer->pages);
+free_cma:
+	cma_release(cma_heap->cma, cma_pages, nr_pages);
+free_buf:
+	kfree(helper_buffer);
+	return ret;
+}
+
+static const struct dma_heap_ops cma_heap_ops = {
+	.allocate = cma_heap_allocate,
+};
+
+static int __add_cma_heap(struct cma *cma, void *data)
+{
+	struct cma_heap *cma_heap;
+	struct dma_heap_export_info exp_info;
+
+	cma_heap = kzalloc(sizeof(*cma_heap), GFP_KERNEL);
+	if (!cma_heap)
+		return -ENOMEM;
+	cma_heap->cma = cma;
+
+	exp_info.name = cma_get_name(cma);
+	exp_info.ops = &cma_heap_ops;
+	exp_info.priv = cma_heap;
+
+	cma_heap->heap = dma_heap_add(&exp_info);
+	if (IS_ERR(cma_heap->heap)) {
+		int ret = PTR_ERR(cma_heap->heap);
+
+		kfree(cma_heap);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int add_default_cma_heap(void)
+{
+	struct cma *default_cma = dev_get_cma_area(NULL);
+	int ret = 0;
+
+	if (default_cma)
+		ret = __add_cma_heap(default_cma, NULL);
+
+	return ret;
+}
+module_init(add_default_cma_heap);
+MODULE_DESCRIPTION("DMA-BUF CMA Heap");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma-buf/heaps/heap-helpers.c b/drivers/dma-buf/heaps/heap-helpers.c
new file mode 100644
index 000000000000..9f964ca3f59c
--- /dev/null
+++ b/drivers/dma-buf/heaps/heap-helpers.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <uapi/linux/dma-heap.h>
+
+#include "heap-helpers.h"
+
+void init_heap_helper_buffer(struct heap_helper_buffer *buffer,
+			     void (*free)(struct heap_helper_buffer *))
+{
+	buffer->priv_virt = NULL;
+	mutex_init(&buffer->lock);
+	buffer->vmap_cnt = 0;
+	buffer->vaddr = NULL;
+	buffer->pagecount = 0;
+	buffer->pages = NULL;
+	INIT_LIST_HEAD(&buffer->attachments);
+	buffer->free = free;
+}
+
+struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer,
+					  int fd_flags)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+	exp_info.ops = &heap_helper_ops;
+	exp_info.size = buffer->size;
+	exp_info.flags = fd_flags;
+	exp_info.priv = buffer;
+
+	return dma_buf_export(&exp_info);
+}
+
+static void *dma_heap_map_kernel(struct heap_helper_buffer *buffer)
+{
+	void *vaddr;
+
+	vaddr = vmap(buffer->pages, buffer->pagecount, VM_MAP, PAGE_KERNEL);
+	if (!vaddr)
+		return ERR_PTR(-ENOMEM);
+
+	return vaddr;
+}
+
+static void dma_heap_buffer_destroy(struct heap_helper_buffer *buffer)
+{
+	if (buffer->vmap_cnt > 0) {
+		WARN(1, "%s: buffer still mapped in the kernel\n", __func__);
+		vunmap(buffer->vaddr);
+	}
+
+	buffer->free(buffer);
+}
+
+static void *dma_heap_buffer_vmap_get(struct heap_helper_buffer *buffer)
+{
+	void *vaddr;
+
+	if (buffer->vmap_cnt) {
+		buffer->vmap_cnt++;
+		return buffer->vaddr;
+	}
+	vaddr = dma_heap_map_kernel(buffer);
+	if (IS_ERR(vaddr))
+		return vaddr;
+	buffer->vaddr = vaddr;
+	buffer->vmap_cnt++;
+	return vaddr;
+}
+
+static void dma_heap_buffer_vmap_put(struct heap_helper_buffer *buffer)
+{
+	if (!--buffer->vmap_cnt) {
+		vunmap(buffer->vaddr);
+		buffer->vaddr = NULL;
+	}
+}
+
+struct dma_heaps_attachment {
+	struct device *dev;
+	struct sg_table table;
+	struct list_head list;
+};
+
+static int dma_heap_attach(struct dma_buf *dmabuf,
+			   struct dma_buf_attachment *attachment)
+{
+	struct dma_heaps_attachment *a;
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	int ret;
+
+	a = kzalloc(sizeof(*a), GFP_KERNEL);
+	if (!a)
+		return -ENOMEM;
+
+	ret = sg_alloc_table_from_pages(&a->table, buffer->pages,
+					buffer->pagecount, 0,
+					buffer->pagecount << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret) {
+		kfree(a);
+		return ret;
+	}
+
+	a->dev = attachment->dev;
+	INIT_LIST_HEAD(&a->list);
+
+	attachment->priv = a;
+
+	mutex_lock(&buffer->lock);
+	list_add(&a->list, &buffer->attachments);
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void dma_heap_detach(struct dma_buf *dmabuf,
+			    struct dma_buf_attachment *attachment)
+{
+	struct dma_heaps_attachment *a = attachment->priv;
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	list_del(&a->list);
+	mutex_unlock(&buffer->lock);
+
+	sg_free_table(&a->table);
+	kfree(a);
+}
+
+static
+struct sg_table *dma_heap_map_dma_buf(struct dma_buf_attachment *attachment,
+				      enum dma_data_direction direction)
+{
+	struct dma_heaps_attachment *a = attachment->priv;
+	struct sg_table *table;
+
+	table = &a->table;
+
+	if (!dma_map_sg(attachment->dev, table->sgl, table->nents,
+			direction))
+		table = ERR_PTR(-ENOMEM);
+	return table;
+}
+
+static void dma_heap_unmap_dma_buf(struct dma_buf_attachment *attachment,
+				   struct sg_table *table,
+				   enum dma_data_direction direction)
+{
+	dma_unmap_sg(attachment->dev, table->sgl, table->nents, direction);
+}
+
+static vm_fault_t dma_heap_vm_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct heap_helper_buffer *buffer = vma->vm_private_data;
+
+	if (vmf->pgoff > buffer->pagecount)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = buffer->pages[vmf->pgoff];
+	get_page(vmf->page);
+
+	return 0;
+}
+
+static const struct vm_operations_struct dma_heap_vm_ops = {
+	.fault = dma_heap_vm_fault,
+};
+
+static int dma_heap_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
+		return -EINVAL;
+
+	vma->vm_ops = &dma_heap_vm_ops;
+	vma->vm_private_data = buffer;
+
+	return 0;
+}
+
+static void dma_heap_dma_buf_release(struct dma_buf *dmabuf)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	dma_heap_buffer_destroy(buffer);
+}
+
+static int dma_heap_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
+					     enum dma_data_direction direction)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	struct dma_heaps_attachment *a;
+	int ret = 0;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		invalidate_kernel_vmap_range(buffer->vaddr, buffer->size);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		dma_sync_sg_for_cpu(a->dev, a->table.sgl, a->table.nents,
+				    direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return ret;
+}
+
+static int dma_heap_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
+					   enum dma_data_direction direction)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	struct dma_heaps_attachment *a;
+
+	mutex_lock(&buffer->lock);
+
+	if (buffer->vmap_cnt)
+		flush_kernel_vmap_range(buffer->vaddr, buffer->size);
+
+	list_for_each_entry(a, &buffer->attachments, list) {
+		dma_sync_sg_for_device(a->dev, a->table.sgl, a->table.nents,
+				       direction);
+	}
+	mutex_unlock(&buffer->lock);
+
+	return 0;
+}
+
+static void *dma_heap_dma_buf_vmap(struct dma_buf *dmabuf)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+	void *vaddr;
+
+	mutex_lock(&buffer->lock);
+	vaddr = dma_heap_buffer_vmap_get(buffer);
+	mutex_unlock(&buffer->lock);
+
+	return vaddr;
+}
+
+static void dma_heap_dma_buf_vunmap(struct dma_buf *dmabuf, void *vaddr)
+{
+	struct heap_helper_buffer *buffer = dmabuf->priv;
+
+	mutex_lock(&buffer->lock);
+	dma_heap_buffer_vmap_put(buffer);
+	mutex_unlock(&buffer->lock);
+}
+
+const struct dma_buf_ops heap_helper_ops = {
+	.map_dma_buf = dma_heap_map_dma_buf,
+	.unmap_dma_buf = dma_heap_unmap_dma_buf,
+	.mmap = dma_heap_mmap,
+	.release = dma_heap_dma_buf_release,
+	.attach = dma_heap_attach,
+	.detach = dma_heap_detach,
+	.begin_cpu_access = dma_heap_dma_buf_begin_cpu_access,
+	.end_cpu_access = dma_heap_dma_buf_end_cpu_access,
+	.vmap = dma_heap_dma_buf_vmap,
+	.vunmap = dma_heap_dma_buf_vunmap,
+};
diff --git a/drivers/dma-buf/heaps/heap-helpers.h b/drivers/dma-buf/heaps/heap-helpers.h
new file mode 100644
index 000000000000..805d2df88024
--- /dev/null
+++ b/drivers/dma-buf/heaps/heap-helpers.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DMABUF Heaps helper code
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#ifndef _HEAP_HELPERS_H
+#define _HEAP_HELPERS_H
+
+#include <linux/dma-heap.h>
+#include <linux/list.h>
+
+/**
+ * struct heap_helper_buffer - helper buffer metadata
+ * @heap:		back pointer to the heap the buffer came from
+ * @dmabuf:		backing dma-buf for this buffer
+ * @size:		size of the buffer
+ * @priv_virt		pointer to heap specific private value
+ * @lock		mutext to protect the data in this structure
+ * @vmap_cnt		count of vmap references on the buffer
+ * @vaddr		vmap'ed virtual address
+ * @pagecount		number of pages in the buffer
+ * @pages		list of page pointers
+ * @attachments		list of device attachments
+ *
+ * @free		heap callback to free the buffer
+ */
+struct heap_helper_buffer {
+	struct dma_heap *heap;
+	struct dma_buf *dmabuf;
+	size_t size;
+
+	void *priv_virt;
+	struct mutex lock;
+	int vmap_cnt;
+	void *vaddr;
+	pgoff_t pagecount;
+	struct page **pages;
+	struct list_head attachments;
+
+	void (*free)(struct heap_helper_buffer *buffer);
+};
+
+void init_heap_helper_buffer(struct heap_helper_buffer *buffer,
+			     void (*free)(struct heap_helper_buffer *));
+
+struct dma_buf *heap_helper_export_dmabuf(struct heap_helper_buffer *buffer,
+					  int fd_flags);
+
+extern const struct dma_buf_ops heap_helper_ops;
+#endif /* _HEAP_HELPERS_H */
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
new file mode 100644
index 000000000000..0bf688e3c023
--- /dev/null
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMABUF System heap exporter
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-heap.h>
+#include <linux/err.h>
+#include <linux/highmem.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <asm/page.h>
+
+#include "heap-helpers.h"
+
+struct dma_heap *sys_heap;
+
+static void system_heap_free(struct heap_helper_buffer *buffer)
+{
+	pgoff_t pg;
+
+	for (pg = 0; pg < buffer->pagecount; pg++)
+		__free_page(buffer->pages[pg]);
+	kfree(buffer->pages);
+	kfree(buffer);
+}
+
+static int system_heap_allocate(struct dma_heap *heap,
+				unsigned long len,
+				unsigned long fd_flags,
+				unsigned long heap_flags)
+{
+	struct heap_helper_buffer *helper_buffer;
+	struct dma_buf *dmabuf;
+	int ret = -ENOMEM;
+	pgoff_t pg;
+
+	helper_buffer = kzalloc(sizeof(*helper_buffer), GFP_KERNEL);
+	if (!helper_buffer)
+		return -ENOMEM;
+
+	init_heap_helper_buffer(helper_buffer, system_heap_free);
+	helper_buffer->heap = heap;
+	helper_buffer->size = len;
+
+	helper_buffer->pagecount = len / PAGE_SIZE;
+	helper_buffer->pages = kmalloc_array(helper_buffer->pagecount,
+					     sizeof(*helper_buffer->pages),
+					     GFP_KERNEL);
+	if (!helper_buffer->pages) {
+		ret = -ENOMEM;
+		goto err0;
+	}
+
+	for (pg = 0; pg < helper_buffer->pagecount; pg++) {
+		/*
+		 * Avoid trying to allocate memory if the process
+		 * has been killed by by SIGKILL
+		 */
+		if (fatal_signal_pending(current))
+			goto err1;
+
+		helper_buffer->pages[pg] = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!helper_buffer->pages[pg])
+			goto err1;
+	}
+
+	/* create the dmabuf */
+	dmabuf = heap_helper_export_dmabuf(helper_buffer, fd_flags);
+	if (IS_ERR(dmabuf)) {
+		ret = PTR_ERR(dmabuf);
+		goto err1;
+	}
+
+	helper_buffer->dmabuf = dmabuf;
+
+	ret = dma_buf_fd(dmabuf, fd_flags);
+	if (ret < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+		return ret;
+	}
+
+	return ret;
+
+err1:
+	while (pg > 0)
+		__free_page(helper_buffer->pages[--pg]);
+	kfree(helper_buffer->pages);
+err0:
+	kfree(helper_buffer);
+
+	return ret;
+}
+
+static const struct dma_heap_ops system_heap_ops = {
+	.allocate = system_heap_allocate,
+};
+
+static int system_heap_create(void)
+{
+	struct dma_heap_export_info exp_info;
+	int ret = 0;
+
+	exp_info.name = "system";
+	exp_info.ops = &system_heap_ops;
+	exp_info.priv = NULL;
+
+	sys_heap = dma_heap_add(&exp_info);
+	if (IS_ERR(sys_heap))
+		ret = PTR_ERR(sys_heap);
+
+	return ret;
+}
+module_init(system_heap_create);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 9635897458a0..acb26c627d27 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -18,6 +18,8 @@ static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes  */
 struct udmabuf {
 	pgoff_t pagecount;
 	struct page **pages;
+	struct sg_table *sg;
+	struct miscdevice *device;
 };
 
 static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
@@ -46,10 +48,10 @@ static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
 	return 0;
 }
 
-static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
-				    enum dma_data_direction direction)
+static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
+				     enum dma_data_direction direction)
 {
-	struct udmabuf *ubuf = at->dmabuf->priv;
+	struct udmabuf *ubuf = buf->priv;
 	struct sg_table *sg;
 	int ret;
 
@@ -61,7 +63,7 @@ static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
 					GFP_KERNEL);
 	if (ret < 0)
 		goto err;
-	if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction)) {
+	if (!dma_map_sg(dev, sg->sgl, sg->nents, direction)) {
 		ret = -EINVAL;
 		goto err;
 	}
@@ -73,54 +75,89 @@ err:
 	return ERR_PTR(ret);
 }
 
+static void put_sg_table(struct device *dev, struct sg_table *sg,
+			 enum dma_data_direction direction)
+{
+	dma_unmap_sg(dev, sg->sgl, sg->nents, direction);
+	sg_free_table(sg);
+	kfree(sg);
+}
+
+static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
+				    enum dma_data_direction direction)
+{
+	return get_sg_table(at->dev, at->dmabuf, direction);
+}
+
 static void unmap_udmabuf(struct dma_buf_attachment *at,
 			  struct sg_table *sg,
 			  enum dma_data_direction direction)
 {
-	dma_unmap_sg(at->dev, sg->sgl, sg->nents, direction);
-	sg_free_table(sg);
-	kfree(sg);
+	return put_sg_table(at->dev, sg, direction);
 }
 
 static void release_udmabuf(struct dma_buf *buf)
 {
 	struct udmabuf *ubuf = buf->priv;
+	struct device *dev = ubuf->device->this_device;
 	pgoff_t pg;
 
+	if (ubuf->sg)
+		put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
+
 	for (pg = 0; pg < ubuf->pagecount; pg++)
 		put_page(ubuf->pages[pg]);
 	kfree(ubuf->pages);
 	kfree(ubuf);
 }
 
-static void *kmap_udmabuf(struct dma_buf *buf, unsigned long page_num)
+static int begin_cpu_udmabuf(struct dma_buf *buf,
+			     enum dma_data_direction direction)
 {
 	struct udmabuf *ubuf = buf->priv;
-	struct page *page = ubuf->pages[page_num];
+	struct device *dev = ubuf->device->this_device;
+
+	if (!ubuf->sg) {
+		ubuf->sg = get_sg_table(dev, buf, direction);
+		if (IS_ERR(ubuf->sg))
+			return PTR_ERR(ubuf->sg);
+	} else {
+		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
+				    direction);
+	}
 
-	return kmap(page);
+	return 0;
 }
 
-static void kunmap_udmabuf(struct dma_buf *buf, unsigned long page_num,
-			   void *vaddr)
+static int end_cpu_udmabuf(struct dma_buf *buf,
+			   enum dma_data_direction direction)
 {
-	kunmap(vaddr);
+	struct udmabuf *ubuf = buf->priv;
+	struct device *dev = ubuf->device->this_device;
+
+	if (!ubuf->sg)
+		return -EINVAL;
+
+	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	return 0;
 }
 
 static const struct dma_buf_ops udmabuf_ops = {
-	.map_dma_buf	  = map_udmabuf,
-	.unmap_dma_buf	  = unmap_udmabuf,
-	.release	  = release_udmabuf,
-	.map		  = kmap_udmabuf,
-	.unmap		  = kunmap_udmabuf,
-	.mmap		  = mmap_udmabuf,
+	.cache_sgt_mapping = true,
+	.map_dma_buf	   = map_udmabuf,
+	.unmap_dma_buf	   = unmap_udmabuf,
+	.release	   = release_udmabuf,
+	.mmap		   = mmap_udmabuf,
+	.begin_cpu_access  = begin_cpu_udmabuf,
+	.end_cpu_access    = end_cpu_udmabuf,
 };
 
 #define SEALS_WANTED (F_SEAL_SHRINK)
 #define SEALS_DENIED (F_SEAL_WRITE)
 
-static long udmabuf_create(const struct udmabuf_create_list *head,
-			   const struct udmabuf_create_item *list)
+static long udmabuf_create(struct miscdevice *device,
+			   struct udmabuf_create_list *head,
+			   struct udmabuf_create_item *list)
 {
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
 	struct file *memfd = NULL;
@@ -187,6 +224,7 @@ static long udmabuf_create(const struct udmabuf_create_list *head,
 	exp_info.priv = ubuf;
 	exp_info.flags = O_RDWR;
 
+	ubuf->device = device;
 	buf = dma_buf_export(&exp_info);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
@@ -224,7 +262,7 @@ static long udmabuf_ioctl_create(struct file *filp, unsigned long arg)
 	list.offset = create.offset;
 	list.size   = create.size;
 
-	return udmabuf_create(&head, &list);
+	return udmabuf_create(filp->private_data, &head, &list);
 }
 
 static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
@@ -243,7 +281,7 @@ static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
 	if (IS_ERR(list))
 		return PTR_ERR(list);
 
-	ret = udmabuf_create(&head, list);
+	ret = udmabuf_create(filp->private_data, &head, list);
 	kfree(list);
 	return ret;
 }
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index f3ef4edd4de1..c3b1283b6d31 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -756,22 +756,21 @@ struct dma_chan *dma_request_chan(struct device *dev, const char *name)
 	}
 	mutex_unlock(&dma_list_mutex);
 
-	if (!IS_ERR_OR_NULL(chan))
-		goto found;
-
-	return ERR_PTR(-EPROBE_DEFER);
+	if (IS_ERR_OR_NULL(chan))
+		return chan ? chan : ERR_PTR(-EPROBE_DEFER);
 
 found:
-	chan->slave = dev;
 	chan->name = kasprintf(GFP_KERNEL, "dma:%s", name);
 	if (!chan->name)
-		return ERR_PTR(-ENOMEM);
+		return chan;
+	chan->slave = dev;
 
 	if (sysfs_create_link(&chan->dev->device.kobj, &dev->kobj,
 			      DMA_SLAVE_NAME))
-		dev_err(dev, "Cannot create DMA %s symlink\n", DMA_SLAVE_NAME);
+		dev_warn(dev, "Cannot create DMA %s symlink\n", DMA_SLAVE_NAME);
 	if (sysfs_create_link(&dev->kobj, &chan->dev->device.kobj, chan->name))
-		dev_err(dev, "Cannot create DMA %s symlink\n", chan->name);
+		dev_warn(dev, "Cannot create DMA %s symlink\n", chan->name);
+
 	return chan;
 }
 EXPORT_SYMBOL_GPL(dma_request_chan);
@@ -830,13 +829,14 @@ void dma_release_channel(struct dma_chan *chan)
 	/* drop PRIVATE cap enabled by __dma_request_channel() */
 	if (--chan->device->privatecnt == 0)
 		dma_cap_clear(DMA_PRIVATE, chan->device->cap_mask);
+
 	if (chan->slave) {
+		sysfs_remove_link(&chan->dev->device.kobj, DMA_SLAVE_NAME);
 		sysfs_remove_link(&chan->slave->kobj, chan->name);
 		kfree(chan->name);
 		chan->name = NULL;
 		chan->slave = NULL;
 	}
-	sysfs_remove_link(&chan->dev->device.kobj, DMA_SLAVE_NAME);
 	mutex_unlock(&dma_list_mutex);
 }
 EXPORT_SYMBOL_GPL(dma_release_channel);
@@ -962,6 +962,9 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 
 	tchan = list_first_entry_or_null(&device->channels,
 					 struct dma_chan, device_node);
+	if (!tchan)
+		return -ENODEV;
+
 	if (tchan->dev) {
 		idr_ref = tchan->dev->idr_ref;
 	} else {
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 849c50ab939a..6d907fe150aa 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -66,7 +66,7 @@ static inline bool is_idxd_wq_dmaengine(struct idxd_wq *wq)
 
 static inline bool is_idxd_wq_cdev(struct idxd_wq *wq)
 {
-	return wq->type == IDXD_WQT_USER ? true : false;
+	return wq->type == IDXD_WQT_USER;
 }
 
 static int idxd_config_bus_match(struct device *dev,
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index e3850f04f676..157c959311ea 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -750,7 +750,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 	}
 
 	xor_dev->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(xor_dev->clk) && PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) {
+	if (PTR_ERR(xor_dev->clk) == -EPROBE_DEFER) {
 		ret = EPROBE_DEFER;
 		goto disable_reg_clk;
 	}
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 899b803842bb..9dda2602c862 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -27,7 +27,7 @@
 
 extern u64 efi_system_table;
 
-#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS
+#if defined(CONFIG_PTDUMP_DEBUGFS) && defined(CONFIG_ARM64)
 #include <asm/ptdump.h>
 
 static struct ptdump_info efi_ptdump_info = {
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 7e12cbdf957c..96758b71a8db 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -104,6 +104,7 @@ struct ibft_control {
 	u16 tgt0_off;
 	u16 nic1_off;
 	u16 tgt1_off;
+	u16 expansion[0];
 } __attribute__((__packed__));
 
 struct ibft_initiator {
@@ -235,7 +236,7 @@ static int ibft_verify_hdr(char *t, struct ibft_hdr *hdr, int id, int length)
 				"found %d instead!\n", t, id, hdr->id);
 		return -ENODEV;
 	}
-	if (hdr->length != length) {
+	if (length && hdr->length != length) {
 		printk(KERN_ERR "iBFT error: We expected the %s " \
 				"field header.length to have %d but " \
 				"found %d instead!\n", t, length, hdr->length);
@@ -749,16 +750,16 @@ static int __init ibft_register_kobjects(struct acpi_table_ibft *header)
 	control = (void *)header + sizeof(*header);
 	end = (void *)control + control->hdr.length;
 	eot_offset = (void *)header + header->header.length - (void *)control;
-	rc = ibft_verify_hdr("control", (struct ibft_hdr *)control, id_control,
-			     sizeof(*control));
+	rc = ibft_verify_hdr("control", (struct ibft_hdr *)control, id_control, 0);
 
 	/* iBFT table safety checking */
 	rc |= ((control->hdr.index) ? -ENODEV : 0);
+	rc |= ((control->hdr.length < sizeof(*control)) ? -ENODEV : 0);
 	if (rc) {
 		printk(KERN_ERR "iBFT error: Control header is invalid!\n");
 		return rc;
 	}
-	for (ptr = &control->initiator_off; ptr < end; ptr += sizeof(u16)) {
+	for (ptr = &control->initiator_off; ptr + sizeof(u16) <= end; ptr += sizeof(u16)) {
 		offset = *(u16 *)ptr;
 		if (offset && offset < header->header.length &&
 						offset < eot_offset) {
diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index 75bdfaa08380..74d9f13d72c4 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -48,6 +48,8 @@ static int zynqmp_pm_ret_code(u32 ret_status)
 		return -EACCES;
 	case XST_PM_ABORT_SUSPEND:
 		return -ECANCELED;
+	case XST_PM_MULT_USER:
+		return -EUSERS;
 	case XST_PM_INTERNAL:
 	case XST_PM_CONFLICT:
 	case XST_PM_INVALID_NODE:
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index b585f2ef6dd9..b8013cf90064 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -1035,6 +1035,18 @@ config GPIO_BD70528
 	  This driver can also be built as a module. If so, the module
 	  will be called gpio-bd70528.
 
+config GPIO_BD71828
+	tristate "ROHM BD71828 GPIO support"
+	depends on MFD_ROHM_BD71828
+	help
+	  Support for GPIOs on ROHM BD71828 PMIC. There are three GPIOs
+	  available on the ROHM PMIC in total. The GPIOs are limited to
+	  outputs only and pins must be configured to GPIO outputs by
+	  OTP. Enable this only if you want to use these pins as outputs.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called gpio-bd71828.
+
 config GPIO_BD9571MWV
 	tristate "ROHM BD9571 GPIO support"
 	depends on MFD_BD9571MWV
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 76ff2a5feaba..0b571264ddbc 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_GPIO_ATH79)		+= gpio-ath79.o
 obj-$(CONFIG_GPIO_BCM_KONA)		+= gpio-bcm-kona.o
 obj-$(CONFIG_GPIO_BCM_XGS_IPROC)	+= gpio-xgs-iproc.o
 obj-$(CONFIG_GPIO_BD70528)		+= gpio-bd70528.o
+obj-$(CONFIG_GPIO_BD71828)		+= gpio-bd71828.o
 obj-$(CONFIG_GPIO_BD9571MWV)		+= gpio-bd9571mwv.o
 obj-$(CONFIG_GPIO_BRCMSTB)		+= gpio-brcmstb.o
 obj-$(CONFIG_GPIO_BT8XX)		+= gpio-bt8xx.o
diff --git a/drivers/gpio/gpio-bd71828.c b/drivers/gpio/gpio-bd71828.c
new file mode 100644
index 000000000000..04aade9e0a4d
--- /dev/null
+++ b/drivers/gpio/gpio-bd71828.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2018 ROHM Semiconductors
+
+#include <linux/gpio/driver.h>
+#include <linux/mfd/rohm-bd71828.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define GPIO_OUT_REG(off) (BD71828_REG_GPIO_CTRL1 + (off))
+#define HALL_GPIO_OFFSET 3
+
+/*
+ * These defines can be removed when
+ * "gpio: Add definition for GPIO direction"
+ * (9208b1e77d6e8e9776f34f46ef4079ecac9c3c25 in GPIO tree) gets merged,
+ */
+#ifndef GPIO_LINE_DIRECTION_IN
+	#define GPIO_LINE_DIRECTION_IN 1
+	#define GPIO_LINE_DIRECTION_OUT 0
+#endif
+
+struct bd71828_gpio {
+	struct rohm_regmap_dev chip;
+	struct gpio_chip gpio;
+};
+
+static void bd71828_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			     int value)
+{
+	int ret;
+	struct bd71828_gpio *bdgpio = gpiochip_get_data(chip);
+	u8 val = (value) ? BD71828_GPIO_OUT_HI : BD71828_GPIO_OUT_LO;
+
+	/*
+	 * The HALL input pin can only be used as input. If this is the pin
+	 * we are dealing with - then we are done
+	 */
+	if (offset == HALL_GPIO_OFFSET)
+		return;
+
+	ret = regmap_update_bits(bdgpio->chip.regmap, GPIO_OUT_REG(offset),
+				 BD71828_GPIO_OUT_MASK, val);
+	if (ret)
+		dev_err(bdgpio->chip.dev, "Could not set gpio to %d\n", value);
+}
+
+static int bd71828_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	int ret;
+	unsigned int val;
+	struct bd71828_gpio *bdgpio = gpiochip_get_data(chip);
+
+	if (offset == HALL_GPIO_OFFSET)
+		ret = regmap_read(bdgpio->chip.regmap, BD71828_REG_IO_STAT,
+				  &val);
+	else
+		ret = regmap_read(bdgpio->chip.regmap, GPIO_OUT_REG(offset),
+				  &val);
+	if (!ret)
+		ret = (val & BD71828_GPIO_OUT_MASK);
+
+	return ret;
+}
+
+static int bd71828_gpio_set_config(struct gpio_chip *chip, unsigned int offset,
+				   unsigned long config)
+{
+	struct bd71828_gpio *bdgpio = gpiochip_get_data(chip);
+
+	if (offset == HALL_GPIO_OFFSET)
+		return -ENOTSUPP;
+
+	switch (pinconf_to_config_param(config)) {
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		return regmap_update_bits(bdgpio->chip.regmap,
+					  GPIO_OUT_REG(offset),
+					  BD71828_GPIO_DRIVE_MASK,
+					  BD71828_GPIO_OPEN_DRAIN);
+	case PIN_CONFIG_DRIVE_PUSH_PULL:
+		return regmap_update_bits(bdgpio->chip.regmap,
+					  GPIO_OUT_REG(offset),
+					  BD71828_GPIO_DRIVE_MASK,
+					  BD71828_GPIO_PUSH_PULL);
+	default:
+		break;
+	}
+	return -ENOTSUPP;
+}
+
+static int bd71828_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+	/*
+	 * Pin usage is selected by OTP data. We can't read it runtime. Hence
+	 * we trust that if the pin is not excluded by "gpio-reserved-ranges"
+	 * the OTP configuration is set to OUT. (Other pins but HALL input pin
+	 * on BD71828 can't really be used for general purpose input - input
+	 * states are used for specific cases like regulator control or
+	 * PMIC_ON_REQ.
+	 */
+	if (offset == HALL_GPIO_OFFSET)
+		return GPIO_LINE_DIRECTION_IN;
+
+	return GPIO_LINE_DIRECTION_OUT;
+}
+
+static int bd71828_probe(struct platform_device *pdev)
+{
+	struct bd71828_gpio *bdgpio;
+	struct rohm_regmap_dev *bd71828;
+
+	bd71828 = dev_get_drvdata(pdev->dev.parent);
+	if (!bd71828) {
+		dev_err(&pdev->dev, "No MFD driver data\n");
+		return -EINVAL;
+	}
+
+	bdgpio = devm_kzalloc(&pdev->dev, sizeof(*bdgpio),
+			      GFP_KERNEL);
+	if (!bdgpio)
+		return -ENOMEM;
+
+	bdgpio->chip.dev = &pdev->dev;
+	bdgpio->gpio.parent = pdev->dev.parent;
+	bdgpio->gpio.label = "bd71828-gpio";
+	bdgpio->gpio.owner = THIS_MODULE;
+	bdgpio->gpio.get_direction = bd71828_get_direction;
+	bdgpio->gpio.set_config = bd71828_gpio_set_config;
+	bdgpio->gpio.can_sleep = true;
+	bdgpio->gpio.get = bd71828_gpio_get;
+	bdgpio->gpio.set = bd71828_gpio_set;
+	bdgpio->gpio.base = -1;
+
+	/*
+	 * See if we need some implementation to mark some PINs as
+	 * not controllable based on DT info or if core can handle
+	 * "gpio-reserved-ranges" and exclude them from control
+	 */
+	bdgpio->gpio.ngpio = 4;
+	bdgpio->gpio.of_node = pdev->dev.parent->of_node;
+	bdgpio->chip.regmap = bd71828->regmap;
+
+	return devm_gpiochip_add_data(&pdev->dev, &bdgpio->gpio,
+				     bdgpio);
+}
+
+static struct platform_driver bd71828_gpio = {
+	.driver = {
+		.name = "bd71828-gpio"
+	},
+	.probe = bd71828_probe,
+};
+
+module_platform_driver(bd71828_gpio);
+
+MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
+MODULE_DESCRIPTION("BD71828 voltage regulator driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:bd71828-gpio");
diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c
index 4421be09b960..72b6001c56ef 100644
--- a/drivers/gpio/gpiolib-devres.c
+++ b/drivers/gpio/gpiolib-devres.c
@@ -308,7 +308,7 @@ devm_gpiod_get_array_optional(struct device *dev, const char *con_id,
 	struct gpio_descs *descs;
 
 	descs = devm_gpiod_get_array(dev, con_id, flags);
-	if (IS_ERR(descs) && (PTR_ERR(descs) == -ENOENT))
+	if (PTR_ERR(descs) == -ENOENT)
 		return NULL;
 
 	return descs;
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 1b3f217a35e2..c6d30f73df07 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -484,24 +484,24 @@ struct gpio_desc *of_find_gpio(struct device *dev, const char *con_id,
 			break;
 	}
 
-	if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) {
+	if (PTR_ERR(desc) == -ENOENT) {
 		/* Special handling for SPI GPIOs if used */
 		desc = of_find_spi_gpio(dev, con_id, &of_flags);
 	}
 
-	if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) {
+	if (PTR_ERR(desc) == -ENOENT) {
 		/* This quirk looks up flags and all */
 		desc = of_find_spi_cs_gpio(dev, con_id, idx, flags);
 		if (!IS_ERR(desc))
 			return desc;
 	}
 
-	if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT) {
+	if (PTR_ERR(desc) == -ENOENT) {
 		/* Special handling for regulator GPIOs if used */
 		desc = of_find_regulator_gpio(dev, con_id, &of_flags);
 	}
 
-	if (IS_ERR(desc) && PTR_ERR(desc) == -ENOENT)
+	if (PTR_ERR(desc) == -ENOENT)
 		desc = of_find_arizona_gpio(dev, con_id, &of_flags);
 
 	if (IS_ERR(desc))
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 99ac27a72e28..753283486037 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -5039,7 +5039,7 @@ struct gpio_descs *__must_check gpiod_get_array_optional(struct device *dev,
 	struct gpio_descs *descs;
 
 	descs = gpiod_get_array(dev, con_id, flags);
-	if (IS_ERR(descs) && (PTR_ERR(descs) == -ENOENT))
+	if (PTR_ERR(descs) == -ENOENT)
 		return NULL;
 
 	return descs;
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index bfdadc3667e0..d0aa6cff2e02 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -54,6 +54,9 @@ config DRM_DEBUG_MM
 
 	  If in doubt, say "N".
 
+config DRM_EXPORT_FOR_TESTS
+	bool
+
 config DRM_DEBUG_SELFTEST
 	tristate "kselftests for DRM"
 	depends on DRM
@@ -61,6 +64,7 @@ config DRM_DEBUG_SELFTEST
 	select PRIME_NUMBERS
 	select DRM_LIB_RANDOM
 	select DRM_KMS_HELPER
+	select DRM_EXPORT_FOR_TESTS if m
 	default n
 	help
 	  This option provides kernel modules that can be used to run
@@ -164,6 +168,7 @@ config DRM_LOAD_EDID_FIRMWARE
 
 config DRM_DP_CEC
 	bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support"
+	depends on DRM
 	select CEC_CORE
 	help
 	  Choose this option if you want to enable HDMI CEC support for
@@ -294,9 +299,6 @@ config DRM_VKMS
 
 	  If M is selected the module will be called vkms.
 
-config DRM_ATI_PCIGART
-        bool
-
 source "drivers/gpu/drm/exynos/Kconfig"
 
 source "drivers/gpu/drm/rockchip/Kconfig"
@@ -393,7 +395,6 @@ menuconfig DRM_LEGACY
 	bool "Enable legacy drivers (DANGEROUS)"
 	depends on DRM && MMU
 	select DRM_VM
-	select DRM_ATI_PCIGART if PCI
 	help
 	  Enable legacy DRI1 drivers. Those drivers expose unsafe and dangerous
 	  APIs to user-space, which can be used to circumvent access
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 9f1c7c486f88..6493088a0fdd 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -5,7 +5,7 @@
 
 drm-y       :=	drm_auth.o drm_cache.o \
 		drm_file.o drm_gem.o drm_ioctl.o drm_irq.o \
-		drm_memory.o drm_drv.o drm_pci.o \
+		drm_memory.o drm_drv.o \
 		drm_sysfs.o drm_hashtab.o drm_mm.o \
 		drm_crtc.o drm_fourcc.o drm_modes.o drm_edid.o \
 		drm_encoder_slave.o \
@@ -25,10 +25,10 @@ drm-$(CONFIG_DRM_VM) += drm_vm.o
 drm-$(CONFIG_COMPAT) += drm_ioc32.o
 drm-$(CONFIG_DRM_GEM_CMA_HELPER) += drm_gem_cma_helper.o
 drm-$(CONFIG_DRM_GEM_SHMEM_HELPER) += drm_gem_shmem_helper.o
-drm-$(CONFIG_DRM_ATI_PCIGART) += ati_pcigart.o
 drm-$(CONFIG_DRM_PANEL) += drm_panel.o
 drm-$(CONFIG_OF) += drm_of.o
 drm-$(CONFIG_AGP) += drm_agpsupport.o
+drm-$(CONFIG_PCI) += drm_pci.o
 drm-$(CONFIG_DEBUG_FS) += drm_debugfs.o drm_debugfs_crc.o
 drm-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o
 
diff --git a/drivers/gpu/drm/amd/acp/Kconfig b/drivers/gpu/drm/amd/acp/Kconfig
index 0d12ebf66174..13340f353ea8 100644
--- a/drivers/gpu/drm/amd/acp/Kconfig
+++ b/drivers/gpu/drm/amd/acp/Kconfig
@@ -2,11 +2,11 @@
 menu "ACP (Audio CoProcessor) Configuration"
 
 config DRM_AMD_ACP
-       bool "Enable AMD Audio CoProcessor IP support"
-       depends on DRM_AMDGPU
-       select MFD_CORE
-       select PM_GENERIC_DOMAINS if PM
-       help
+	bool "Enable AMD Audio CoProcessor IP support"
+	depends on DRM_AMDGPU
+	select MFD_CORE
+	select PM_GENERIC_DOMAINS if PM
+	help
 	Choose this option to enable ACP IP support for AMD SOCs.
 	This adds the ACP (Audio CoProcessor) IP driver and wires
 	it up into the amdgpu driver.  The ACP block provides the DMA
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index ca0e435559d5..7ae3b22c5628 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -147,12 +147,16 @@ amdgpu-y += \
 	vce_v3_0.o \
 	vce_v4_0.o
 
-# add VCN block
+# add VCN and JPEG block
 amdgpu-y += \
 	amdgpu_vcn.o \
 	vcn_v1_0.o \
 	vcn_v2_0.o \
-	vcn_v2_5.o
+	vcn_v2_5.o \
+	amdgpu_jpeg.o \
+	jpeg_v1_0.o \
+	jpeg_v2_0.o \
+	jpeg_v2_5.o
 
 # add ATHUB block
 amdgpu-y += \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 0c229a92a24b..b1bb10625cd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -69,6 +69,7 @@
 #include "amdgpu_uvd.h"
 #include "amdgpu_vce.h"
 #include "amdgpu_vcn.h"
+#include "amdgpu_jpeg.h"
 #include "amdgpu_mn.h"
 #include "amdgpu_gmc.h"
 #include "amdgpu_gfx.h"
@@ -89,6 +90,7 @@
 #include "amdgpu_mes.h"
 #include "amdgpu_umc.h"
 #include "amdgpu_mmhub.h"
+#include "amdgpu_df.h"
 
 #define MAX_GPU_INSTANCE		16
 
@@ -588,6 +590,8 @@ struct amdgpu_asic_funcs {
 	bool (*need_reset_on_init)(struct amdgpu_device *adev);
 	/* PCIe replay counter */
 	uint64_t (*get_pcie_replay_count)(struct amdgpu_device *adev);
+	/* device supports BACO */
+	bool (*supports_baco)(struct amdgpu_device *adev);
 };
 
 /*
@@ -633,9 +637,8 @@ struct amdgpu_fw_vram_usage {
 	struct amdgpu_bo *reserved_bo;
 	void *va;
 
-	/* Offset on the top of VRAM, used as c2p write buffer.
+	/* GDDR6 training support flag.
 	*/
-	u64 mem_train_fb_loc;
 	bool mem_train_support;
 };
 
@@ -662,29 +665,6 @@ struct amdgpu_mmio_remap {
 	resource_size_t bus_addr;
 };
 
-struct amdgpu_df_funcs {
-	void (*sw_init)(struct amdgpu_device *adev);
-	void (*sw_fini)(struct amdgpu_device *adev);
-	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
-				      bool enable);
-	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
-	u32 (*get_hbm_channel_number)(struct amdgpu_device *adev);
-	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
-						 bool enable);
-	void (*get_clockgating_state)(struct amdgpu_device *adev,
-				      u32 *flags);
-	void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev,
-					    bool enable);
-	int (*pmc_start)(struct amdgpu_device *adev, uint64_t config,
-					 int is_enable);
-	int (*pmc_stop)(struct amdgpu_device *adev, uint64_t config,
-					 int is_disable);
-	void (*pmc_get_count)(struct amdgpu_device *adev, uint64_t config,
-					 uint64_t *count);
-	uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val);
-	void (*set_fica)(struct amdgpu_device *adev, uint32_t ficaa_val,
-			 uint32_t ficadl_val, uint32_t ficadh_val);
-};
 /* Define the HW IP blocks will be used in driver , add more if necessary */
 enum amd_hw_ip_block_type {
 	GC_HWIP = 1,
@@ -704,6 +684,7 @@ enum amd_hw_ip_block_type {
 	MP1_HWIP,
 	UVD_HWIP,
 	VCN_HWIP = UVD_HWIP,
+	JPEG_HWIP = VCN_HWIP,
 	VCE_HWIP,
 	DF_HWIP,
 	DCE_HWIP,
@@ -899,6 +880,9 @@ struct amdgpu_device {
 	/* vcn */
 	struct amdgpu_vcn		vcn;
 
+	/* jpeg */
+	struct amdgpu_jpeg		jpeg;
+
 	/* firmwares */
 	struct amdgpu_firmware		firmware;
 
@@ -924,6 +908,9 @@ struct amdgpu_device {
 	bool                            enable_mes;
 	struct amdgpu_mes               mes;
 
+	/* df */
+	struct amdgpu_df                df;
+
 	struct amdgpu_ip_block          ip_blocks[AMDGPU_MAX_IP_NUM];
 	int				num_ip_blocks;
 	struct mutex	mn_lock;
@@ -937,8 +924,6 @@ struct amdgpu_device {
 	/* soc15 register offset based on ip, instance and  segment */
 	uint32_t 		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
 
-	const struct amdgpu_df_funcs	*df_funcs;
-
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     delayed_init_work;
 
@@ -982,6 +967,11 @@ struct amdgpu_device {
 
 	/* device pstate */
 	int				pstate;
+	/* enable runtime pm on the device */
+	bool                            runpm;
+
+	bool                            pm_sysfs_en;
+	bool                            ucode_sysfs_en;
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
@@ -1117,6 +1107,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define amdgpu_asic_get_pcie_usage(adev, cnt0, cnt1) ((adev)->asic_funcs->get_pcie_usage((adev), (cnt0), (cnt1)))
 #define amdgpu_asic_need_reset_on_init(adev) (adev)->asic_funcs->need_reset_on_init((adev))
 #define amdgpu_asic_get_pcie_replay_count(adev) ((adev)->asic_funcs->get_pcie_replay_count((adev)))
+#define amdgpu_asic_supports_baco(adev) (adev)->asic_funcs->supports_baco((adev))
+
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
 /* Common functions */
@@ -1133,9 +1125,12 @@ void amdgpu_device_program_register_sequence(struct amdgpu_device *adev,
 					     const u32 *registers,
 					     const u32 array_size);
 
-bool amdgpu_device_is_px(struct drm_device *dev);
+bool amdgpu_device_supports_boco(struct drm_device *dev);
+bool amdgpu_device_supports_baco(struct drm_device *dev);
 bool amdgpu_device_is_peer_accessible(struct amdgpu_device *adev,
 				      struct amdgpu_device *peer_adev);
+int amdgpu_device_baco_enter(struct drm_device *dev);
+int amdgpu_device_baco_exit(struct drm_device *dev);
 
 /* atpx handler */
 #if defined(CONFIG_VGA_SWITCHEROO)
@@ -1173,8 +1168,8 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv);
 void amdgpu_driver_postclose_kms(struct drm_device *dev,
 				 struct drm_file *file_priv);
 int amdgpu_device_ip_suspend(struct amdgpu_device *adev);
-int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon);
-int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon);
+int amdgpu_device_suspend(struct drm_device *dev, bool fbcon);
+int amdgpu_device_resume(struct drm_device *dev, bool fbcon);
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe);
 int amdgpu_enable_vblank_kms(struct drm_device *dev, unsigned int pipe);
 void amdgpu_disable_vblank_kms(struct drm_device *dev, unsigned int pipe);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index d3da9dde4ee1..8609287620ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -613,15 +613,9 @@ void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
 
-	if (is_support_sw_smu(adev))
-		smu_switch_power_profile(&adev->smu,
-					 PP_SMC_POWER_PROFILE_COMPUTE,
-					 !idle);
-	else if (adev->powerplay.pp_funcs &&
-		 adev->powerplay.pp_funcs->switch_power_profile)
-		amdgpu_dpm_switch_power_profile(adev,
-						PP_SMC_POWER_PROFILE_COMPUTE,
-						!idle);
+	amdgpu_dpm_switch_power_profile(adev,
+					PP_SMC_POWER_PROFILE_COMPUTE,
+					!idle);
 }
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
@@ -634,6 +628,38 @@ bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 	return false;
 }
 
+int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	if (adev->family == AMDGPU_FAMILY_AI) {
+		int i;
+
+		for (i = 0; i < adev->num_vmhubs; i++)
+			amdgpu_gmc_flush_gpu_tlb(adev, vmid, i, 0);
+	} else {
+		amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB_0, 0);
+	}
+
+	return 0;
+}
+
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	uint32_t flush_type = 0;
+	bool all_hub = false;
+
+	if (adev->gmc.xgmi.num_physical_nodes &&
+		adev->asic_type == CHIP_VEGA20)
+		flush_type = 2;
+
+	if (adev->family == AMDGPU_FAMILY_AI)
+		all_hub = true;
+
+	return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub);
+}
+
 bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 069d5d230810..47b0f2957d1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -136,6 +136,8 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t *ib_cmd, uint32_t ib_len);
 void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd);
+int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid);
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index b6713e0ed1b2..4bcc175a149d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -46,6 +46,8 @@
 #include "soc15.h"
 #include "soc15d.h"
 #include "amdgpu_amdkfd_gfx_v9.h"
+#include "gfxhub_v1_0.h"
+#include "mmhub_v9_4.h"
 
 #define HQD_N_REGS 56
 #define DUMP_REG(addr) do {				\
@@ -69,32 +71,56 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t sdma_engine_reg_base[8] = {
-		SOC15_REG_OFFSET(SDMA0, 0,
-				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA1, 0,
-				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA2, 0,
-				 mmSDMA2_RLC0_RB_CNTL) - mmSDMA2_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA3, 0,
-				 mmSDMA3_RLC0_RB_CNTL) - mmSDMA3_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA4, 0,
-				 mmSDMA4_RLC0_RB_CNTL) - mmSDMA4_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA5, 0,
-				 mmSDMA5_RLC0_RB_CNTL) - mmSDMA5_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA6, 0,
-				 mmSDMA6_RLC0_RB_CNTL) - mmSDMA6_RLC0_RB_CNTL,
-		SOC15_REG_OFFSET(SDMA7, 0,
-				 mmSDMA7_RLC0_RB_CNTL) - mmSDMA7_RLC0_RB_CNTL
-	};
-
-	uint32_t retval = sdma_engine_reg_base[engine_id]
+	uint32_t sdma_engine_reg_base = 0;
+	uint32_t sdma_rlc_reg_offset;
+
+	switch (engine_id) {
+	default:
+		dev_warn(adev->dev,
+			 "Invalid sdma engine id (%d), using engine id 0\n",
+			 engine_id);
+		/* fall through */
+	case 0:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0,
+				mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL;
+		break;
+	case 1:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0,
+				mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL;
+		break;
+	case 2:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA2, 0,
+				mmSDMA2_RLC0_RB_CNTL) - mmSDMA2_RLC0_RB_CNTL;
+		break;
+	case 3:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA3, 0,
+				mmSDMA3_RLC0_RB_CNTL) - mmSDMA3_RLC0_RB_CNTL;
+		break;
+	case 4:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA4, 0,
+				mmSDMA4_RLC0_RB_CNTL) - mmSDMA4_RLC0_RB_CNTL;
+		break;
+	case 5:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA5, 0,
+				mmSDMA5_RLC0_RB_CNTL) - mmSDMA5_RLC0_RB_CNTL;
+		break;
+	case 6:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA6, 0,
+				mmSDMA6_RLC0_RB_CNTL) - mmSDMA6_RLC0_RB_CNTL;
+		break;
+	case 7:
+		sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA7, 0,
+				mmSDMA7_RLC0_RB_CNTL) - mmSDMA7_RLC0_RB_CNTL;
+		break;
+	}
+
+	sdma_rlc_reg_offset = sdma_engine_reg_base
 		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
 	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
-			queue_id, retval);
+			queue_id, sdma_rlc_reg_offset);
 
-	return retval;
+	return sdma_rlc_reg_offset;
 }
 
 static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
@@ -258,11 +284,28 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 	return 0;
 }
 
+static void kgd_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
+		uint64_t page_table_base)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
+		pr_err("trying to set page table base for wrong VMID %u\n",
+		       vmid);
+		return;
+	}
+
+	mmhub_v9_4_setup_vm_pt_regs(adev, vmid, page_table_base);
+
+	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+}
+
 const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_gfx_v9_init_interrupts,
 	.hqd_load = kgd_gfx_v9_hqd_load,
+	.hiq_mqd_load = kgd_gfx_v9_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_gfx_v9_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -277,8 +320,6 @@ const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = kgd_gfx_v9_get_tile_config,
-	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.invalidate_tlbs = kgd_gfx_v9_invalidate_tlbs,
-	.invalidate_tlbs_vmid = kgd_gfx_v9_invalidate_tlbs_vmid,
+	.set_vm_context_page_table_base = kgd_set_vm_context_page_table_base,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 61cd707158e4..a7b17c8deb00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -107,13 +107,13 @@ static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
-static uint32_t get_queue_mask(struct amdgpu_device *adev,
+static uint64_t get_queue_mask(struct amdgpu_device *adev,
 			       uint32_t pipe_id, uint32_t queue_id)
 {
-	unsigned int bit = (pipe_id * adev->gfx.mec.num_queue_per_pipe +
-			    queue_id) & 31;
+	unsigned int bit = pipe_id * adev->gfx.mec.num_queue_per_pipe +
+			queue_id;
 
-	return ((uint32_t)1) << bit;
+	return 1ull << bit;
 }
 
 static void release_queue(struct kgd_dev *kgd)
@@ -268,21 +268,6 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	pr_debug("Load hqd of pipe %d queue %d\n", pipe_id, queue_id);
 	acquire_queue(kgd, pipe_id, queue_id);
 
-	/* HIQ is set during driver init period with vmid set to 0*/
-	if (m->cp_hqd_vmid == 0) {
-		uint32_t value, mec, pipe;
-
-		mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
-		pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
-
-		pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
-			mec, pipe, queue_id);
-		value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
-		value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1,
-			((mec << 5) | (pipe << 3) | queue_id | 0x80));
-		WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value);
-	}
-
 	/* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */
 	mqd_hqd = &m->cp_mqd_base_addr_lo;
 	hqd_base = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
@@ -332,9 +317,10 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 		       lower_32_bits((uint64_t)wptr));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uint64_t)wptr));
-		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__, get_queue_mask(adev, pipe_id, queue_id));
+		pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__,
+			 (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
-		       get_queue_mask(adev, pipe_id, queue_id));
+		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
@@ -350,6 +336,59 @@ static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
+static int kgd_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
+	struct v10_compute_mqd *m;
+	uint32_t mec, pipe;
+	int r;
+
+	m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
+		 mec, pipe, queue_id);
+
+	spin_lock(&adev->gfx.kiq.ring_lock);
+	r = amdgpu_ring_alloc(kiq_ring, 7);
+	if (r) {
+		pr_err("Failed to alloc KIQ (%d).\n", r);
+		goto out_unlock;
+	}
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			  PACKET3_MAP_QUEUES_VMID(m->cp_hqd_vmid) | /* VMID */
+			  PACKET3_MAP_QUEUES_QUEUE(queue_id) |
+			  PACKET3_MAP_QUEUES_PIPE(pipe) |
+			  PACKET3_MAP_QUEUES_ME((mec - 1)) |
+			  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
+			  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
+			  PACKET3_MAP_QUEUES_ENGINE_SEL(1) | /* engine_sel: hiq */
+			  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_DOORBELL_OFFSET(doorbell_off));
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_hi);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_hi);
+	amdgpu_ring_commit(kiq_ring);
+
+out_unlock:
+	spin_unlock(&adev->gfx.kiq.ring_lock);
+	release_queue(kgd);
+
+	return r;
+}
+
 static int kgd_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs)
@@ -686,71 +725,6 @@ static bool get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
-static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid)
-{
-	signed long r;
-	uint32_t seq;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	spin_lock(&adev->gfx.kiq.ring_lock);
-	amdgpu_ring_alloc(ring, 12); /* fence + invalidate_tlbs package*/
-	amdgpu_ring_write(ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
-	amdgpu_ring_write(ring,
-			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
-			PACKET3_INVALIDATE_TLBS_PASID(pasid));
-	amdgpu_fence_emit_polling(ring, &seq);
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq.ring_lock);
-
-	r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
-	if (r < 1) {
-		DRM_ERROR("wait for kiq fence error: %ld.\n", r);
-		return -ETIME;
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	uint16_t queried_pasid;
-	bool ret;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	if (amdgpu_emu_mode == 0 && ring->sched.ready)
-		return invalidate_tlbs_with_kiq(adev, pasid);
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		ret = get_atc_vmid_pasid_mapping_info(kgd, vmid,
-				&queried_pasid);
-		if (ret	&& queried_pasid == pasid) {
-			amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-					AMDGPU_GFXHUB_0, 0);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return 0;
-	}
-
-	amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB_0, 0);
-	return 0;
-}
-
 static int kgd_address_watch_disable(struct kgd_dev *kgd)
 {
 	return 0;
@@ -817,6 +791,7 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_init_interrupts,
 	.hqd_load = kgd_hqd_load,
+	.hiq_mqd_load = kgd_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -832,7 +807,5 @@ const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
 			get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = amdgpu_amdkfd_get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 6e6f0a99ec06..8f052e98a3c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -696,45 +696,6 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		lower_32_bits(page_table_base));
 }
 
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	unsigned int tmp;
-
-	if (adev->in_gpu_reset)
-		return -EIO;
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
-			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
-			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-			RREG32(mmVM_INVALIDATE_RESPONSE);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid\n");
-		return 0;
-	}
-
-	WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-	RREG32(mmVM_INVALIDATE_RESPONSE);
-	return 0;
-}
-
  /**
   * read_vmid_from_vmfault_reg - read vmid from register
   *
@@ -771,7 +732,5 @@ const struct kfd2kgd_calls gfx_v7_kfd2kgd = {
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.get_tile_config = get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index bfbddedb2380..19a10db93d68 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -657,45 +657,6 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 			lower_32_bits(page_table_base));
 }
 
-static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid;
-	unsigned int tmp;
-
-	if (adev->in_gpu_reset)
-		return -EIO;
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
-			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
-			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-			RREG32(mmVM_INVALIDATE_RESPONSE);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return -EINVAL;
-	}
-
-	WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
-	RREG32(mmVM_INVALIDATE_RESPONSE);
-	return 0;
-}
-
 const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
@@ -717,6 +678,4 @@ const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.get_tile_config = get_tile_config,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 47c853ef1051..8562afe5b761 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -40,7 +40,6 @@
 #include "soc15d.h"
 #include "mmhub_v1_0.h"
 #include "gfxhub_v1_0.h"
-#include "gmc_v9_0.h"
 
 
 enum hqd_dequeue_request_type {
@@ -104,13 +103,13 @@ static void acquire_queue(struct kgd_dev *kgd, uint32_t pipe_id,
 	lock_srbm(kgd, mec, pipe, queue_id, 0);
 }
 
-static uint32_t get_queue_mask(struct amdgpu_device *adev,
+static uint64_t get_queue_mask(struct amdgpu_device *adev,
 			       uint32_t pipe_id, uint32_t queue_id)
 {
-	unsigned int bit = (pipe_id * adev->gfx.mec.num_queue_per_pipe +
-			    queue_id) & 31;
+	unsigned int bit = pipe_id * adev->gfx.mec.num_queue_per_pipe +
+			queue_id;
 
-	return ((uint32_t)1) << bit;
+	return 1ull << bit;
 }
 
 static void release_queue(struct kgd_dev *kgd)
@@ -259,21 +258,6 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 
 	acquire_queue(kgd, pipe_id, queue_id);
 
-	/* HIQ is set during driver init period with vmid set to 0*/
-	if (m->cp_hqd_vmid == 0) {
-		uint32_t value, mec, pipe;
-
-		mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
-		pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
-
-		pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
-			mec, pipe, queue_id);
-		value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS));
-		value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1,
-			((mec << 5) | (pipe << 3) | queue_id | 0x80));
-		WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value);
-	}
-
 	/* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */
 	mqd_hqd = &m->cp_mqd_base_addr_lo;
 	hqd_base = SOC15_REG_OFFSET(GC, 0, mmCP_MQD_BASE_ADDR);
@@ -324,7 +308,7 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 		WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI),
 		       upper_32_bits((uintptr_t)wptr));
 		WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
-		       get_queue_mask(adev, pipe_id, queue_id));
+		       (uint32_t)get_queue_mask(adev, pipe_id, queue_id));
 	}
 
 	/* Start the EOP fetcher */
@@ -340,6 +324,59 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 	return 0;
 }
 
+int kgd_gfx_v9_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
+	struct v9_mqd *m;
+	uint32_t mec, pipe;
+	int r;
+
+	m = get_mqd(mqd);
+
+	acquire_queue(kgd, pipe_id, queue_id);
+
+	mec = (pipe_id / adev->gfx.mec.num_pipe_per_mec) + 1;
+	pipe = (pipe_id % adev->gfx.mec.num_pipe_per_mec);
+
+	pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n",
+		 mec, pipe, queue_id);
+
+	spin_lock(&adev->gfx.kiq.ring_lock);
+	r = amdgpu_ring_alloc(kiq_ring, 7);
+	if (r) {
+		pr_err("Failed to alloc KIQ (%d).\n", r);
+		goto out_unlock;
+	}
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			  PACKET3_MAP_QUEUES_VMID(m->cp_hqd_vmid) | /* VMID */
+			  PACKET3_MAP_QUEUES_QUEUE(queue_id) |
+			  PACKET3_MAP_QUEUES_PIPE(pipe) |
+			  PACKET3_MAP_QUEUES_ME((mec - 1)) |
+			  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
+			  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
+			  PACKET3_MAP_QUEUES_ENGINE_SEL(1) | /* engine_sel: hiq */
+			  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_MAP_QUEUES_DOORBELL_OFFSET(doorbell_off));
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_mqd_base_addr_hi);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_lo);
+	amdgpu_ring_write(kiq_ring, m->cp_hqd_pq_wptr_poll_addr_hi);
+	amdgpu_ring_commit(kiq_ring);
+
+out_unlock:
+	spin_unlock(&adev->gfx.kiq.ring_lock);
+	release_queue(kgd);
+
+	return r;
+}
+
 int kgd_gfx_v9_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs)
@@ -618,100 +655,6 @@ bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
-static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid,
-			uint32_t flush_type)
-{
-	signed long r;
-	uint32_t seq;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-
-	spin_lock(&adev->gfx.kiq.ring_lock);
-	amdgpu_ring_alloc(ring, 12); /* fence + invalidate_tlbs package*/
-	amdgpu_ring_write(ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
-	amdgpu_ring_write(ring,
-			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
-			PACKET3_INVALIDATE_TLBS_ALL_HUB(1) |
-			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
-			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(flush_type));
-	amdgpu_fence_emit_polling(ring, &seq);
-	amdgpu_ring_commit(ring);
-	spin_unlock(&adev->gfx.kiq.ring_lock);
-
-	r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
-	if (r < 1) {
-		DRM_ERROR("wait for kiq fence error: %ld.\n", r);
-		return -ETIME;
-	}
-
-	return 0;
-}
-
-int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int vmid, i;
-	uint16_t queried_pasid;
-	bool ret;
-	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
-	uint32_t flush_type = 0;
-
-	if (adev->in_gpu_reset)
-		return -EIO;
-	if (adev->gmc.xgmi.num_physical_nodes &&
-		adev->asic_type == CHIP_VEGA20)
-		flush_type = 2;
-
-	if (ring->sched.ready)
-		return invalidate_tlbs_with_kiq(adev, pasid, flush_type);
-
-	for (vmid = 0; vmid < 16; vmid++) {
-		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
-			continue;
-
-		ret = kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(kgd, vmid,
-				&queried_pasid);
-		if (ret && queried_pasid == pasid) {
-			for (i = 0; i < adev->num_vmhubs; i++)
-				amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-							i, flush_type);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-int kgd_gfx_v9_invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-	int i;
-
-	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
-		pr_err("non kfd vmid %d\n", vmid);
-		return 0;
-	}
-
-	/* Use legacy mode tlb invalidation.
-	 *
-	 * Currently on Raven the code below is broken for anything but
-	 * legacy mode due to a MMHUB power gating problem. A workaround
-	 * is for MMHUB to wait until the condition PER_VMID_INVALIDATE_REQ
-	 * == PER_VMID_INVALIDATE_ACK instead of simply waiting for the ack
-	 * bit.
-	 *
-	 * TODO 1: agree on the right set of invalidation registers for
-	 * KFD use. Use the last one for now. Invalidate both GC and
-	 * MMHUB.
-	 *
-	 * TODO 2: support range-based invalidation, requires kfg2kgd
-	 * interface change
-	 */
-	for (i = 0; i < adev->num_vmhubs; i++)
-		amdgpu_gmc_flush_gpu_tlb(adev, vmid, i, 0);
-
-	return 0;
-}
-
 int kgd_gfx_v9_address_watch_disable(struct kgd_dev *kgd)
 {
 	return 0;
@@ -758,8 +701,8 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 	return 0;
 }
 
-void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_t page_table_base)
+static void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd,
+			uint32_t vmid, uint64_t page_table_base)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 
@@ -769,16 +712,7 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmi
 		return;
 	}
 
-	/* TODO: take advantage of per-process address space size. For
-	 * now, all processes share the same address space size, like
-	 * on GFX8 and older.
-	 */
-	if (adev->asic_type == CHIP_ARCTURUS) {
-		/* Two MMHUBs */
-		mmhub_v9_4_setup_vm_pt_regs(adev, 0, vmid, page_table_base);
-		mmhub_v9_4_setup_vm_pt_regs(adev, 1, vmid, page_table_base);
-	} else
-		mmhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
+	mmhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 
 	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 }
@@ -788,6 +722,7 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_gfx_v9_init_interrupts,
 	.hqd_load = kgd_gfx_v9_hqd_load,
+	.hiq_mqd_load = kgd_gfx_v9_hiq_mqd_load,
 	.hqd_sdma_load = kgd_hqd_sdma_load,
 	.hqd_dump = kgd_gfx_v9_hqd_dump,
 	.hqd_sdma_dump = kgd_hqd_sdma_dump,
@@ -803,7 +738,5 @@ const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = kgd_gfx_v9_get_tile_config,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
-	.invalidate_tlbs = kgd_gfx_v9_invalidate_tlbs,
-	.invalidate_tlbs_vmid = kgd_gfx_v9_invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index d9e9ad22b2bd..63d3e6683dfe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -33,6 +33,9 @@ int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
 			uint32_t queue_id, uint32_t __user *wptr,
 			uint32_t wptr_shift, uint32_t wptr_mask,
 			struct mm_struct *mm);
+int kgd_gfx_v9_hiq_mqd_load(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off);
 int kgd_gfx_v9_hqd_dump(struct kgd_dev *kgd,
 			uint32_t pipe_id, uint32_t queue_id,
 			uint32_t (**dump)[2], uint32_t *n_regs);
@@ -57,9 +60,5 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 
 bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
 					uint8_t vmid, uint16_t *p_pasid);
-void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_t page_table_base);
-int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
-int kgd_gfx_v9_invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
 int kgd_gfx_v9_get_tile_config(struct kgd_dev *kgd,
 		struct tile_config *config);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 888209eb8cec..b2487f4f271b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -85,7 +85,7 @@ static bool check_if_add_bo_to_vm(struct amdgpu_vm *avm,
 }
 
 /* Set memory usage limits. Current, limits are
- *  System (TTM + userptr) memory - 3/4th System RAM
+ *  System (TTM + userptr) memory - 15/16th System RAM
  *  TTM memory - 3/8th System RAM
  */
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
@@ -98,7 +98,7 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 	mem *= si.mem_unit;
 
 	spin_lock_init(&kfd_mem_limit.mem_limit_lock);
-	kfd_mem_limit.max_system_mem_limit = (mem >> 1) + (mem >> 2);
+	kfd_mem_limit.max_system_mem_limit = mem - (mem >> 4);
 	kfd_mem_limit.max_ttm_mem_limit = (mem >> 1) - (mem >> 3);
 	pr_debug("Kernel memory limit %lluM, TTM limit %lluM\n",
 		(kfd_mem_limit.max_system_mem_limit >> 20),
@@ -358,7 +358,7 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	if (ret)
 		return ret;
 
-	return amdgpu_sync_fence(NULL, sync, vm->last_update, false);
+	return amdgpu_sync_fence(sync, vm->last_update, false);
 }
 
 static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
@@ -750,7 +750,7 @@ static int unmap_bo_from_gpuvm(struct amdgpu_device *adev,
 
 	amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);
 
-	amdgpu_sync_fence(NULL, sync, bo_va->last_pt_update, false);
+	amdgpu_sync_fence(sync, bo_va->last_pt_update, false);
 
 	return 0;
 }
@@ -769,7 +769,7 @@ static int update_gpuvm_pte(struct amdgpu_device *adev,
 		return ret;
 	}
 
-	return amdgpu_sync_fence(NULL, sync, bo_va->last_pt_update, false);
+	return amdgpu_sync_fence(sync, bo_va->last_pt_update, false);
 }
 
 static int map_bo_to_gpuvm(struct amdgpu_device *adev,
@@ -1674,10 +1674,10 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem,
 				struct mm_struct *mm)
 {
 	struct amdkfd_process_info *process_info = mem->process_info;
-	int invalid, evicted_bos;
+	int evicted_bos;
 	int r = 0;
 
-	invalid = atomic_inc_return(&mem->invalid);
+	atomic_inc(&mem->invalid);
 	evicted_bos = atomic_inc_return(&process_info->evicted_bos);
 	if (evicted_bos == 1) {
 		/* First eviction, stop the queues */
@@ -2048,7 +2048,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 			pr_debug("Memory eviction: Validate BOs failed. Try again\n");
 			goto validate_map_fail;
 		}
-		ret = amdgpu_sync_fence(NULL, &sync_obj, bo->tbo.moving, false);
+		ret = amdgpu_sync_fence(&sync_obj, bo->tbo.moving, false);
 		if (ret) {
 			pr_debug("Memory eviction: Sync BO fence failed. Try again\n");
 			goto validate_map_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 72232fccf61a..fdd52d86a4d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -338,17 +338,9 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 		path_size += le16_to_cpu(path->usSize);
 
 		if (device_support & le16_to_cpu(path->usDeviceTag)) {
-			uint8_t con_obj_id, con_obj_num, con_obj_type;
-
-			con_obj_id =
+			uint8_t con_obj_id =
 			    (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK)
 			    >> OBJECT_ID_SHIFT;
-			con_obj_num =
-			    (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK)
-			    >> ENUM_ID_SHIFT;
-			con_obj_type =
-			    (le16_to_cpu(path->usConnObjectId) &
-			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
 			/* Skip TV/CV support */
 			if ((le16_to_cpu(path->usDeviceTag) ==
@@ -373,15 +365,7 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device *
 			router.ddc_valid = false;
 			router.cd_valid = false;
 			for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) {
-				uint8_t grph_obj_id, grph_obj_num, grph_obj_type;
-
-				grph_obj_id =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-				grph_obj_num =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     ENUM_ID_MASK) >> ENUM_ID_SHIFT;
-				grph_obj_type =
+				uint8_t grph_obj_type =
 				    (le16_to_cpu(path->usGraphicObjIds[j]) &
 				     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
@@ -2038,7 +2022,7 @@ int amdgpu_atombios_init(struct amdgpu_device *adev)
 	if (adev->is_atom_fw) {
 		amdgpu_atomfirmware_scratch_regs_init(adev);
 		amdgpu_atomfirmware_allocate_fb_scratch(adev);
-		ret = amdgpu_atomfirmware_get_mem_train_fb_loc(adev);
+		ret = amdgpu_atomfirmware_get_mem_train_info(adev);
 		if (ret) {
 			DRM_ERROR("Failed to get mem train fb location.\n");
 			return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index ff4eb96bdfb5..58f9d8c3a17a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -525,16 +525,12 @@ static int gddr6_mem_train_support(struct amdgpu_device *adev)
 	return ret;
 }
 
-int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev)
+int amdgpu_atomfirmware_get_mem_train_info(struct amdgpu_device *adev)
 {
 	struct atom_context *ctx = adev->mode_info.atom_context;
-	unsigned char *bios = ctx->bios;
-	struct vram_reserve_block *reserved_block;
-	int index, block_number;
+	int index;
 	uint8_t frev, crev;
 	uint16_t data_offset, size;
-	uint32_t start_address_in_kb;
-	uint64_t offset;
 	int ret;
 
 	adev->fw_vram_usage.mem_train_support = false;
@@ -569,32 +565,6 @@ int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev)
 		return -EINVAL;
 	}
 
-	reserved_block = (struct vram_reserve_block *)
-		(bios + data_offset + sizeof(struct atom_common_table_header));
-	block_number = ((unsigned int)size - sizeof(struct atom_common_table_header))
-		/ sizeof(struct vram_reserve_block);
-	reserved_block += (block_number > 0) ? block_number-1 : 0;
-	DRM_DEBUG("block_number:0x%04x, last block: 0x%08xkb sz, %dkb fw, %dkb drv.\n",
-		  block_number,
-		  le32_to_cpu(reserved_block->start_address_in_kb),
-		  le16_to_cpu(reserved_block->used_by_firmware_in_kb),
-		  le16_to_cpu(reserved_block->used_by_driver_in_kb));
-	if (reserved_block->used_by_firmware_in_kb > 0) {
-		start_address_in_kb = le32_to_cpu(reserved_block->start_address_in_kb);
-		offset = (uint64_t)start_address_in_kb * ONE_KiB;
-		if ((offset & (ONE_MiB - 1)) < (4 * ONE_KiB + 1) ) {
-			offset -= ONE_MiB;
-		}
-
-		offset &= ~(ONE_MiB - 1);
-		adev->fw_vram_usage.mem_train_fb_loc = offset;
-		adev->fw_vram_usage.mem_train_support = true;
-		DRM_DEBUG("mem_train_fb_loc:0x%09llx.\n", offset);
-		ret = 0;
-	} else {
-		DRM_ERROR("used_by_firmware_in_kb is 0!\n");
-		ret = -EINVAL;
-	}
-
-	return ret;
+	adev->fw_vram_usage.mem_train_support = true;
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index f871af5ea6f3..434fe2fa0089 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -31,7 +31,7 @@ void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 	int *vram_width, int *vram_type, int *vram_vendor);
-int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev);
+int amdgpu_atomfirmware_get_mem_train_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5ca905b4a0fb..a52a084158b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -795,29 +795,23 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(adev, &p->job->sync,
-			      fpriv->prt_va->last_pt_update, false);
+	r = amdgpu_sync_vm_fence(&p->job->sync, fpriv->prt_va->last_pt_update);
 	if (r)
 		return r;
 
 	if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
-		struct dma_fence *f;
-
 		bo_va = fpriv->csa_va;
 		BUG_ON(!bo_va);
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
 
-		f = bo_va->last_pt_update;
-		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
+		r = amdgpu_sync_vm_fence(&p->job->sync, bo_va->last_pt_update);
 		if (r)
 			return r;
 	}
 
 	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-		struct dma_fence *f;
-
 		/* ignore duplicates */
 		bo = ttm_to_amdgpu_bo(e->tv.bo);
 		if (!bo)
@@ -831,8 +825,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		if (r)
 			return r;
 
-		f = bo_va->last_pt_update;
-		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
+		r = amdgpu_sync_vm_fence(&p->job->sync, bo_va->last_pt_update);
 		if (r)
 			return r;
 	}
@@ -845,7 +838,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_sync_fence(adev, &p->job->sync, vm->last_update, false);
+	r = amdgpu_sync_vm_fence(&p->job->sync, vm->last_update);
 	if (r)
 		return r;
 
@@ -916,6 +909,11 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 		if (parser->entity && parser->entity != entity)
 			return -EINVAL;
 
+		/* Return if there is no run queue associated with this entity.
+		 * Possibly because of disabled HW IP*/
+		if (entity->rq == NULL)
+			return -EINVAL;
+
 		parser->entity = entity;
 
 		ring = to_amdgpu_ring(entity->rq->sched);
@@ -987,7 +985,7 @@ static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
 			dma_fence_put(old);
 		}
 
-		r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
+		r = amdgpu_sync_fence(&p->job->sync, fence, true);
 		dma_fence_put(fence);
 		if (r)
 			return r;
@@ -1009,7 +1007,7 @@ static int amdgpu_syncobj_lookup_and_add_to_sync(struct amdgpu_cs_parser *p,
 		return r;
 	}
 
-	r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
+	r = amdgpu_sync_fence(&p->job->sync, fence, true);
 	dma_fence_put(fence);
 
 	return r;
@@ -1236,7 +1234,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 		goto error_abort;
 	}
 
-	job->owner = p->filp;
 	p->fence = dma_fence_get(&job->base.s_fence->finished);
 
 	amdgpu_ctx_add_fence(p->ctx, entity, p->fence, &seq);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 6614d8a6f4c8..64e2babbc36e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -74,7 +74,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 			   struct amdgpu_ctx *ctx)
 {
 	unsigned num_entities = amdgpu_ctx_total_num_entities();
-	unsigned i, j, k;
+	unsigned i, j;
 	int r;
 
 	if (priority < 0 || priority >= DRM_SCHED_PRIORITY_MAX)
@@ -121,72 +121,57 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 	ctx->override_priority = DRM_SCHED_PRIORITY_UNSET;
 
 	for (i = 0; i < AMDGPU_HW_IP_NUM; ++i) {
-		struct amdgpu_ring *rings[AMDGPU_MAX_RINGS];
-		struct drm_sched_rq *rqs[AMDGPU_MAX_RINGS];
-		unsigned num_rings = 0;
-		unsigned num_rqs = 0;
+		struct drm_gpu_scheduler **scheds;
+		struct drm_gpu_scheduler *sched;
+		unsigned num_scheds = 0;
 
 		switch (i) {
 		case AMDGPU_HW_IP_GFX:
-			rings[0] = &adev->gfx.gfx_ring[0];
-			num_rings = 1;
+			sched = &adev->gfx.gfx_ring[0].sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_COMPUTE:
-			for (j = 0; j < adev->gfx.num_compute_rings; ++j)
-				rings[j] = &adev->gfx.compute_ring[j];
-			num_rings = adev->gfx.num_compute_rings;
+			scheds = adev->gfx.compute_sched;
+			num_scheds = adev->gfx.num_compute_sched;
 			break;
 		case AMDGPU_HW_IP_DMA:
-			for (j = 0; j < adev->sdma.num_instances; ++j)
-				rings[j] = &adev->sdma.instance[j].ring;
-			num_rings = adev->sdma.num_instances;
+			scheds = adev->sdma.sdma_sched;
+			num_scheds = adev->sdma.num_sdma_sched;
 			break;
 		case AMDGPU_HW_IP_UVD:
-			rings[0] = &adev->uvd.inst[0].ring;
-			num_rings = 1;
+			sched = &adev->uvd.inst[0].ring.sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_VCE:
-			rings[0] = &adev->vce.ring[0];
-			num_rings = 1;
+			sched = &adev->vce.ring[0].sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
-			rings[0] = &adev->uvd.inst[0].ring_enc[0];
-			num_rings = 1;
+			sched = &adev->uvd.inst[0].ring_enc[0].sched;
+			scheds = &sched;
+			num_scheds = 1;
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
-			for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-				if (adev->vcn.harvest_config & (1 << j))
-					continue;
-				rings[num_rings++] = &adev->vcn.inst[j].ring_dec;
-			}
+			scheds = adev->vcn.vcn_dec_sched;
+			num_scheds =  adev->vcn.num_vcn_dec_sched;
 			break;
 		case AMDGPU_HW_IP_VCN_ENC:
-			for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-				if (adev->vcn.harvest_config & (1 << j))
-					continue;
-				for (k = 0; k < adev->vcn.num_enc_rings; ++k)
-					rings[num_rings++] = &adev->vcn.inst[j].ring_enc[k];
-			}
+			scheds = adev->vcn.vcn_enc_sched;
+			num_scheds =  adev->vcn.num_vcn_enc_sched;
 			break;
 		case AMDGPU_HW_IP_VCN_JPEG:
-			for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
-				if (adev->vcn.harvest_config & (1 << j))
-					continue;
-				rings[num_rings++] = &adev->vcn.inst[j].ring_jpeg;
-			}
+			scheds = adev->jpeg.jpeg_sched;
+			num_scheds =  adev->jpeg.num_jpeg_sched;
 			break;
 		}
 
-		for (j = 0; j < num_rings; ++j) {
-			if (!rings[j]->adev)
-				continue;
-
-			rqs[num_rqs++] = &rings[j]->sched.sched_rq[priority];
-		}
-
 		for (j = 0; j < amdgpu_ctx_num_entities[i]; ++j)
 			r = drm_sched_entity_init(&ctx->entities[i][j].entity,
-						  rqs, num_rqs, &ctx->guilty);
+						  priority, scheds,
+						  num_scheds, &ctx->guilty);
 		if (r)
 			goto error_cleanup_entities;
 	}
@@ -627,3 +612,45 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 	idr_destroy(&mgr->ctx_handles);
 	mutex_destroy(&mgr->lock);
 }
+
+void amdgpu_ctx_init_sched(struct amdgpu_device *adev)
+{
+	int i, j;
+
+	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
+		adev->gfx.gfx_sched[i] = &adev->gfx.gfx_ring[i].sched;
+		adev->gfx.num_gfx_sched++;
+	}
+
+	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+		adev->gfx.compute_sched[i] = &adev->gfx.compute_ring[i].sched;
+		adev->gfx.num_compute_sched++;
+	}
+
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		adev->sdma.sdma_sched[i] = &adev->sdma.instance[i].ring.sched;
+		adev->sdma.num_sdma_sched++;
+	}
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+		adev->vcn.vcn_dec_sched[adev->vcn.num_vcn_dec_sched++] =
+			&adev->vcn.inst[i].ring_dec.sched;
+	}
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		if (adev->vcn.harvest_config & (1 << i))
+			continue;
+		for (j = 0; j < adev->vcn.num_enc_rings; ++j)
+			adev->vcn.vcn_enc_sched[adev->vcn.num_vcn_enc_sched++] =
+				&adev->vcn.inst[i].ring_enc[j].sched;
+	}
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+		adev->jpeg.jpeg_sched[adev->jpeg.num_jpeg_sched++] =
+			&adev->jpeg.inst[i].ring_dec.sched;
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
index da808633732b..4ad90a44dc3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
@@ -87,4 +87,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
 long amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr, long timeout);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
+void amdgpu_ctx_init_sched(struct amdgpu_device *adev);
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 8e6726e0d035..f24ed9a1a3e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -26,6 +26,7 @@
 #include <linux/kthread.h>
 #include <linux/pci.h>
 #include <linux/uaccess.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_debugfs.h>
 
@@ -129,7 +130,7 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 			sh_bank = 0xFFFFFFFF;
 		if (instance_bank == 0x3FF)
 			instance_bank = 0xFFFFFFFF;
-		use_bank = 1;
+		use_bank = true;
 	} else if (*pos & (1ULL << 61)) {
 
 		me = (*pos & GENMASK_ULL(33, 24)) >> 24;
@@ -137,17 +138,24 @@ static int  amdgpu_debugfs_process_reg_op(bool read, struct file *f,
 		queue = (*pos & GENMASK_ULL(53, 44)) >> 44;
 		vmid = (*pos & GENMASK_ULL(58, 54)) >> 54;
 
-		use_ring = 1;
+		use_ring = true;
 	} else {
-		use_bank = use_ring = 0;
+		use_bank = use_ring = false;
 	}
 
 	*pos &= (1UL << 22) - 1;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	if (use_bank) {
 		if ((sh_bank != 0xFFFFFFFF && sh_bank >= adev->gfx.config.max_sh_per_se) ||
-		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines))
+		    (se_bank != 0xFFFFFFFF && se_bank >= adev->gfx.config.max_shader_engines)) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 		mutex_lock(&adev->grbm_idx_mutex);
 		amdgpu_gfx_select_se_sh(adev, se_bank,
 					sh_bank, instance_bank);
@@ -193,6 +201,9 @@ end:
 	if (pm_pg_lock)
 		mutex_unlock(&adev->pm.mutex);
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -237,13 +248,20 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		value = RREG32_PCIE(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		result += 4;
 		buf += 4;
@@ -251,6 +269,9 @@ static ssize_t amdgpu_debugfs_regs_pcie_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -276,12 +297,19 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		r = get_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		WREG32_PCIE(*pos >> 2, value);
 
@@ -291,6 +319,9 @@ static ssize_t amdgpu_debugfs_regs_pcie_write(struct file *f, const char __user
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -316,13 +347,20 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		value = RREG32_DIDT(*pos >> 2);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		result += 4;
 		buf += 4;
@@ -330,6 +368,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -355,12 +396,19 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		r = get_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		WREG32_DIDT(*pos >> 2, value);
 
@@ -370,6 +418,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -395,13 +446,20 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		value = RREG32_SMC(*pos);
 		r = put_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		result += 4;
 		buf += 4;
@@ -409,6 +467,9 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf,
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -434,12 +495,19 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	while (size) {
 		uint32_t value;
 
 		r = get_user(value, (uint32_t *)buf);
-		if (r)
+		if (r) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return r;
+		}
 
 		WREG32_SMC(*pos, value);
 
@@ -449,6 +517,9 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user *
 		size -= 4;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return result;
 }
 
@@ -572,7 +643,16 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
 	idx = *pos >> 2;
 
 	valuesize = sizeof(values);
+
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	r = amdgpu_dpm_read_sensor(adev, idx, &values[0], &valuesize);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -633,6 +713,10 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	wave = (*pos & GENMASK_ULL(36, 31)) >> 31;
 	simd = (*pos & GENMASK_ULL(44, 37)) >> 37;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* switch to the specific se/sh/cu */
 	mutex_lock(&adev->grbm_idx_mutex);
 	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
@@ -644,6 +728,9 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
 	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (!x)
 		return -EINVAL;
 
@@ -711,6 +798,10 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	if (!data)
 		return -ENOMEM;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* switch to the specific se/sh/cu */
 	mutex_lock(&adev->grbm_idx_mutex);
 	amdgpu_gfx_select_se_sh(adev, se, sh, cu);
@@ -726,6 +817,9 @@ static ssize_t amdgpu_debugfs_gpr_read(struct file *f, char __user *buf,
 	amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	while (size) {
 		uint32_t value;
 
@@ -859,6 +953,10 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 	struct amdgpu_device *adev = dev->dev_private;
 	int r = 0, i;
 
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
+
 	/* Avoid accidently unparking the sched thread during GPU reset */
 	mutex_lock(&adev->lock_reset);
 
@@ -889,6 +987,9 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 
 	mutex_unlock(&adev->lock_reset);
 
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
@@ -907,8 +1008,17 @@ static int amdgpu_debugfs_evict_vram(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
 
 	seq_printf(m, "(%d)\n", amdgpu_bo_evict_vram(adev));
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
@@ -917,8 +1027,17 @@ static int amdgpu_debugfs_evict_gtt(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
 
 	seq_printf(m, "(%d)\n", ttm_bo_evict_mm(&adev->mman.bdev, TTM_PL_TT));
+
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c17505fba988..53d882000101 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -66,6 +66,7 @@
 #include "amdgpu_pmu.h"
 
 #include <linux/suspend.h>
+#include <drm/task_barrier.h>
 
 MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
@@ -137,14 +138,14 @@ static DEVICE_ATTR(pcie_replay_count, S_IRUGO,
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev);
 
 /**
- * amdgpu_device_is_px - Is the device is a dGPU with HG/PX power control
+ * amdgpu_device_supports_boco - Is the device a dGPU with HG/PX power control
  *
  * @dev: drm_device pointer
  *
  * Returns true if the device is a dGPU with HG/PX power control,
  * otherwise return false.
  */
-bool amdgpu_device_is_px(struct drm_device *dev)
+bool amdgpu_device_supports_boco(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = dev->dev_private;
 
@@ -154,6 +155,21 @@ bool amdgpu_device_is_px(struct drm_device *dev)
 }
 
 /**
+ * amdgpu_device_supports_baco - Does the device support BACO
+ *
+ * @dev: drm_device pointer
+ *
+ * Returns true if the device supporte BACO,
+ * otherwise return false.
+ */
+bool amdgpu_device_supports_baco(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+
+	return amdgpu_asic_supports_baco(adev);
+}
+
+/**
  * VRAM access helper functions.
  *
  * amdgpu_device_vram_access - read/write a buffer in vram
@@ -1016,8 +1032,6 @@ def_value:
  */
 static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 {
-	int ret = 0;
-
 	if (amdgpu_sched_jobs < 4) {
 		dev_warn(adev->dev, "sched jobs (%d) must be at least 4\n",
 			 amdgpu_sched_jobs);
@@ -1057,7 +1071,7 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -1072,8 +1086,9 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
+	int r;
 
-	if (amdgpu_device_is_px(dev) && state == VGA_SWITCHEROO_OFF)
+	if (amdgpu_device_supports_boco(dev) && state == VGA_SWITCHEROO_OFF)
 		return;
 
 	if (state == VGA_SWITCHEROO_ON) {
@@ -1081,7 +1096,12 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		/* don't suspend or resume card normally */
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 
-		amdgpu_device_resume(dev, true, true);
+		pci_set_power_state(dev->pdev, PCI_D0);
+		pci_restore_state(dev->pdev);
+		r = pci_enable_device(dev->pdev);
+		if (r)
+			DRM_WARN("pci_enable_device failed (%d)\n", r);
+		amdgpu_device_resume(dev, true);
 
 		dev->switch_power_state = DRM_SWITCH_POWER_ON;
 		drm_kms_helper_poll_enable(dev);
@@ -1089,7 +1109,11 @@ static void amdgpu_switcheroo_set_state(struct pci_dev *pdev, enum vga_switchero
 		pr_info("amdgpu: switched off\n");
 		drm_kms_helper_poll_disable(dev);
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		amdgpu_device_suspend(dev, true, true);
+		amdgpu_device_suspend(dev, true);
+		pci_save_state(dev->pdev);
+		/* Shut down the device */
+		pci_disable_device(dev->pdev);
+		pci_set_power_state(dev->pdev, PCI_D3cold);
 		dev->switch_power_state = DRM_SWITCH_POWER_OFF;
 	}
 }
@@ -1527,7 +1551,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 		}
 
 parse_soc_bounding_box:
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		/*
 		 * soc bounding box info is not integrated in disocovery table,
 		 * we always need to parse it from gpu info firmware.
@@ -1538,7 +1561,6 @@ parse_soc_bounding_box:
 									le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 			adev->dm.soc_bounding_box = &gpu_info_fw->soc_bounding_box;
 		}
-#endif
 		break;
 	}
 	default:
@@ -1787,7 +1809,8 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev)
 		}
 	}
 
-	r = amdgpu_pm_load_smu_firmware(adev, &smu_version);
+	if (!amdgpu_sriov_vf(adev) || adev->asic_type == CHIP_TONGA)
+		r = amdgpu_pm_load_smu_firmware(adev, &smu_version);
 
 	return r;
 }
@@ -1854,6 +1877,9 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 		}
 	}
 
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_init_data_exchange(adev);
+
 	r = amdgpu_ib_pool_init(adev);
 	if (r) {
 		dev_err(adev->dev, "IB initialization failed (%d).\n", r);
@@ -1895,11 +1921,8 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	amdgpu_amdkfd_device_init(adev);
 
 init_failed:
-	if (amdgpu_sriov_vf(adev)) {
-		if (!r)
-			amdgpu_virt_init_data_exchange(adev);
+	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, true);
-	}
 
 	return r;
 }
@@ -1938,6 +1961,7 @@ static bool amdgpu_device_check_vram_lost(struct amdgpu_device *adev)
  * amdgpu_device_set_cg_state - set clockgating for amdgpu device
  *
  * @adev: amdgpu_device pointer
+ * @state: clockgating state (gate or ungate)
  *
  * The list of all the hardware IPs that make up the asic is walked and the
  * set_clockgating_state callbacks are run.
@@ -1962,6 +1986,7 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG &&
 		    adev->ip_blocks[i].version->funcs->set_clockgating_state) {
 			/* enable clockgating to save power */
 			r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
@@ -1992,6 +2017,7 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
 		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG &&
 		    adev->ip_blocks[i].version->funcs->set_powergating_state) {
 			/* enable powergating to save power */
 			r = adev->ip_blocks[i].version->funcs->set_powergating_state((void *)adev,
@@ -2319,14 +2345,7 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 		/* handle putting the SMC in the appropriate state */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
-			if (is_support_sw_smu(adev)) {
-				r = smu_set_mp1_state(&adev->smu, adev->mp1_state);
-			} else if (adev->powerplay.pp_funcs &&
-					   adev->powerplay.pp_funcs->set_mp1_state) {
-				r = adev->powerplay.pp_funcs->set_mp1_state(
-					adev->powerplay.pp_handle,
-					adev->mp1_state);
-			}
+			r = amdgpu_dpm_set_mp1_state(adev, adev->mp1_state);
 			if (r) {
 				DRM_ERROR("SMC failed to set mp1 state %d, %d\n",
 					  adev->mp1_state, r);
@@ -2413,7 +2432,8 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 		AMD_IP_BLOCK_TYPE_GFX,
 		AMD_IP_BLOCK_TYPE_SDMA,
 		AMD_IP_BLOCK_TYPE_UVD,
-		AMD_IP_BLOCK_TYPE_VCE
+		AMD_IP_BLOCK_TYPE_VCE,
+		AMD_IP_BLOCK_TYPE_VCN
 	};
 
 	for (i = 0; i < ARRAY_SIZE(ip_order); i++) {
@@ -2428,7 +2448,11 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 				block->status.hw)
 				continue;
 
-			r = block->version->funcs->hw_init(adev);
+			if (block->version->type == AMD_IP_BLOCK_TYPE_SMC)
+				r = block->version->funcs->resume(adev);
+			else
+				r = block->version->funcs->hw_init(adev);
+
 			DRM_INFO("RE-INIT-late: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
@@ -2600,20 +2624,19 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case CHIP_RAVEN:
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case CHIP_RENOIR:
 #endif
 		return amdgpu_dc != 0;
 #endif
 	default:
+		if (amdgpu_dc > 0)
+			DRM_INFO("Display Core has been requested via kernel parameter "
+					 "but isn't supported by ASIC, ignoring\n");
 		return false;
 	}
 }
@@ -2638,8 +2661,38 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 {
 	struct amdgpu_device *adev =
 		container_of(__work, struct amdgpu_device, xgmi_reset_work);
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+
+	/* It's a bug to not have a hive within this function */
+	if (WARN_ON(!hive))
+		return;
+
+	/*
+	 * Use task barrier to synchronize all xgmi reset works across the
+	 * hive. task_barrier_enter and task_barrier_exit will block
+	 * until all the threads running the xgmi reset works reach
+	 * those points. task_barrier_full will do both blocks.
+	 */
+	if (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+
+		task_barrier_enter(&hive->tb);
+		adev->asic_reset_res = amdgpu_device_baco_enter(adev->ddev);
+
+		if (adev->asic_reset_res)
+			goto fail;
+
+		task_barrier_exit(&hive->tb);
+		adev->asic_reset_res = amdgpu_device_baco_exit(adev->ddev);
+
+		if (adev->asic_reset_res)
+			goto fail;
+	} else {
+
+		task_barrier_full(&hive->tb);
+		adev->asic_reset_res =  amdgpu_asic_reset(adev);
+	}
 
-	adev->asic_reset_res =  amdgpu_asic_reset(adev);
+fail:
 	if (adev->asic_reset_res)
 		DRM_WARN("ASIC reset failed with error, %d for drm dev, %s",
 			 adev->asic_reset_res, adev->ddev->unique);
@@ -2731,7 +2784,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		       uint32_t flags)
 {
 	int r, i;
-	bool runtime = false;
+	bool boco = false;
 	u32 max_MBps;
 
 	adev->shutdown = false;
@@ -2754,7 +2807,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->mman.buffer_funcs = NULL;
 	adev->mman.buffer_funcs_ring = NULL;
 	adev->vm_manager.vm_pte_funcs = NULL;
-	adev->vm_manager.vm_pte_num_rqs = 0;
+	adev->vm_manager.vm_pte_num_scheds = 0;
 	adev->gmc.gmc_funcs = NULL;
 	adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS);
 	bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
@@ -2794,9 +2847,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	mutex_init(&adev->virt.vf_errors.lock);
 	hash_init(adev->mn_hash);
 	mutex_init(&adev->lock_reset);
-	mutex_init(&adev->notifier_lock);
-	mutex_init(&adev->virt.dpm_mutex);
 	mutex_init(&adev->psp.mutex);
+	mutex_init(&adev->notifier_lock);
 
 	r = amdgpu_device_check_arguments(adev);
 	if (r)
@@ -2902,12 +2954,15 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	 * ignore it */
 	vga_client_register(adev->pdev, adev, NULL, amdgpu_device_vga_set_decode);
 
-	if (amdgpu_device_is_px(ddev))
-		runtime = true;
-	if (!pci_is_thunderbolt_attached(adev->pdev))
+	if (amdgpu_device_supports_boco(ddev))
+		boco = true;
+	if (amdgpu_has_atpx() &&
+	    (amdgpu_is_atpx_hybrid() ||
+	     amdgpu_has_atpx_dgpu_power_cntl()) &&
+	    !pci_is_thunderbolt_attached(adev->pdev))
 		vga_switcheroo_register_client(adev->pdev,
-					       &amdgpu_switcheroo_ops, runtime);
-	if (runtime)
+					       &amdgpu_switcheroo_ops, boco);
+	if (boco)
 		vga_switcheroo_init_domain_pm_ops(adev->dev, &adev->vga_pm_domain);
 
 	if (amdgpu_emu_mode == 1) {
@@ -2994,11 +3049,17 @@ fence_driver_init:
 		}
 		dev_err(adev->dev, "amdgpu_device_ip_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
-		if (amdgpu_virt_request_full_gpu(adev, false))
-			amdgpu_virt_release_full_gpu(adev, false);
 		goto failed;
 	}
 
+	DRM_DEBUG("SE %d, SH per SE %d, CU per SH %d, active_cu_number %d\n",
+			adev->gfx.config.max_shader_engines,
+			adev->gfx.config.max_sh_per_se,
+			adev->gfx.config.max_cu_per_sh,
+			adev->gfx.cu_info.number);
+
+	amdgpu_ctx_init_sched(adev);
+
 	adev->accel_working = true;
 
 	amdgpu_vm_check_compute_bug(adev);
@@ -3013,16 +3074,19 @@ fence_driver_init:
 
 	amdgpu_fbdev_init(adev);
 
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev))
-		amdgpu_pm_virt_sysfs_init(adev);
-
 	r = amdgpu_pm_sysfs_init(adev);
-	if (r)
+	if (r) {
+		adev->pm_sysfs_en = false;
 		DRM_ERROR("registering pm debugfs failed (%d).\n", r);
+	} else
+		adev->pm_sysfs_en = true;
 
 	r = amdgpu_ucode_sysfs_init(adev);
-	if (r)
+	if (r) {
+		adev->ucode_sysfs_en = false;
 		DRM_ERROR("Creating firmware sysfs failed (%d).\n", r);
+	} else
+		adev->ucode_sysfs_en = true;
 
 	r = amdgpu_debugfs_gem_init(adev);
 	if (r)
@@ -3091,7 +3155,7 @@ fence_driver_init:
 
 failed:
 	amdgpu_vf_error_trans_all(adev);
-	if (runtime)
+	if (boco)
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 
 	return r;
@@ -3122,7 +3186,8 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 			drm_atomic_helper_shutdown(adev->ddev);
 	}
 	amdgpu_fence_driver_fini(adev);
-	amdgpu_pm_sysfs_fini(adev);
+	if (adev->pm_sysfs_en)
+		amdgpu_pm_sysfs_fini(adev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_device_ip_fini(adev);
 	if (adev->firmware.gpu_info_fw) {
@@ -3139,9 +3204,12 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 
 	kfree(adev->bios);
 	adev->bios = NULL;
-	if (!pci_is_thunderbolt_attached(adev->pdev))
+	if (amdgpu_has_atpx() &&
+	    (amdgpu_is_atpx_hybrid() ||
+	     amdgpu_has_atpx_dgpu_power_cntl()) &&
+	    !pci_is_thunderbolt_attached(adev->pdev))
 		vga_switcheroo_unregister_client(adev->pdev);
-	if (adev->flags & AMD_IS_PX)
+	if (amdgpu_device_supports_boco(adev->ddev))
 		vga_switcheroo_fini_domain_pm_ops(adev->dev);
 	vga_client_register(adev->pdev, NULL, NULL, NULL);
 	if (adev->rio_mem)
@@ -3150,12 +3218,11 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	iounmap(adev->rmmio);
 	adev->rmmio = NULL;
 	amdgpu_device_doorbell_fini(adev);
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev))
-		amdgpu_pm_virt_sysfs_fini(adev);
 
 	amdgpu_debugfs_regs_cleanup(adev);
 	device_remove_file(adev->dev, &dev_attr_pcie_replay_count);
-	amdgpu_ucode_sysfs_fini(adev);
+	if (adev->ucode_sysfs_en)
+		amdgpu_ucode_sysfs_fini(adev);
 	if (IS_ENABLED(CONFIG_PERF_EVENTS))
 		amdgpu_pmu_fini(adev);
 	amdgpu_debugfs_preempt_cleanup(adev);
@@ -3178,7 +3245,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
  * Returns 0 for success or an error on failure.
  * Called at driver suspend.
  */
-int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
+int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 {
 	struct amdgpu_device *adev;
 	struct drm_crtc *crtc;
@@ -3261,13 +3328,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	 */
 	amdgpu_bo_evict_vram(adev);
 
-	if (suspend) {
-		pci_save_state(dev->pdev);
-		/* Shut down the device */
-		pci_disable_device(dev->pdev);
-		pci_set_power_state(dev->pdev, PCI_D3hot);
-	}
-
 	return 0;
 }
 
@@ -3282,7 +3342,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
  * Returns 0 for success or an error on failure.
  * Called at driver resume.
  */
-int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
+int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
 {
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
@@ -3293,14 +3353,6 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (resume) {
-		pci_set_power_state(dev->pdev, PCI_D0);
-		pci_restore_state(dev->pdev);
-		r = pci_enable_device(dev->pdev);
-		if (r)
-			return r;
-	}
-
 	/* post card */
 	if (amdgpu_device_need_post(adev)) {
 		r = amdgpu_atom_asic_init(adev->mode_info.atom_context);
@@ -3639,13 +3691,12 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	amdgpu_amdkfd_pre_reset(adev);
-
 	/* Resume IP prior to SMC */
 	r = amdgpu_device_ip_reinit_early_sriov(adev);
 	if (r)
 		goto error;
 
+	amdgpu_virt_init_data_exchange(adev);
 	/* we need recover gart prior to run SMC/CP/SDMA resume */
 	amdgpu_gtt_mgr_recover(&adev->mman.bdev.man[TTM_PL_TT]);
 
@@ -3663,7 +3714,6 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	amdgpu_amdkfd_post_reset(adev);
 
 error:
-	amdgpu_virt_init_data_exchange(adev);
 	amdgpu_virt_release_full_gpu(adev, true);
 	if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
 		amdgpu_inc_vram_lost(adev);
@@ -3709,6 +3759,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev)
 		case CHIP_VEGA10:
 		case CHIP_VEGA12:
 		case CHIP_RAVEN:
+		case CHIP_ARCTURUS:
 			break;
 		default:
 			goto disabled;
@@ -3785,7 +3836,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 		list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 			/* For XGMI run all resets in parallel to speed up the process */
 			if (tmp_adev->gmc.xgmi.num_physical_nodes > 1) {
-				if (!queue_work(system_highpri_wq, &tmp_adev->xgmi_reset_work))
+				if (!queue_work(system_unbound_wq, &tmp_adev->xgmi_reset_work))
 					r = -EALREADY;
 			} else
 				r = amdgpu_asic_reset(tmp_adev);
@@ -3797,7 +3848,7 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 			}
 		}
 
-		/* For XGMI wait for all PSP resets to complete before proceed */
+		/* For XGMI wait for all resets to complete before proceed */
 		if (!r) {
 			list_for_each_entry(tmp_adev, device_list_handle,
 					    gmc.xgmi.head) {
@@ -3811,6 +3862,8 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 		}
 	}
 
+	if (!r && amdgpu_ras_intr_triggered())
+		amdgpu_ras_intr_cleared();
 
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 		if (need_full_reset) {
@@ -3899,7 +3952,7 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
 		mutex_lock(&adev->lock_reset);
 
 	atomic_inc(&adev->gpu_reset_counter);
-	adev->in_gpu_reset = 1;
+	adev->in_gpu_reset = true;
 	switch (amdgpu_asic_reset_method(adev)) {
 	case AMD_RESET_METHOD_MODE1:
 		adev->mp1_state = PP_MP1_STATE_SHUTDOWN;
@@ -3919,7 +3972,7 @@ static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 {
 	amdgpu_vf_error_trans_all(adev);
 	adev->mp1_state = PP_MP1_STATE_NONE;
-	adev->in_gpu_reset = 0;
+	adev->in_gpu_reset = false;
 	mutex_unlock(&adev->lock_reset);
 }
 
@@ -3943,12 +3996,15 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	struct amdgpu_device *tmp_adev = NULL;
 	int i, r = 0;
 	bool in_ras_intr = amdgpu_ras_intr_triggered();
+	bool use_baco =
+		(amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) ?
+		true : false;
 
 	/*
 	 * Flush RAM to disk so that after reboot
 	 * the user can read log and see why the system rebooted.
 	 */
-	if (in_ras_intr && amdgpu_ras_get_context(adev)->reboot) {
+	if (in_ras_intr && !use_baco && amdgpu_ras_get_context(adev)->reboot) {
 
 		DRM_WARN("Emergency reboot.");
 
@@ -3959,7 +4015,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	need_full_reset = job_signaled = false;
 	INIT_LIST_HEAD(&device_list);
 
-	dev_info(adev->dev, "GPU %s begin!\n", in_ras_intr ? "jobs stop":"reset");
+	dev_info(adev->dev, "GPU %s begin!\n",
+		(in_ras_intr && !use_baco) ? "jobs stop":"reset");
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
 
@@ -4026,7 +4083,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		amdgpu_unregister_gpu_instance(tmp_adev);
 
 		/* disable ras on ALL IPs */
-		if (!in_ras_intr && amdgpu_device_ip_need_full_reset(tmp_adev))
+		if (!(in_ras_intr && !use_baco) &&
+		      amdgpu_device_ip_need_full_reset(tmp_adev))
 			amdgpu_ras_suspend(tmp_adev);
 
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -4037,13 +4095,13 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
 
-			if (in_ras_intr)
+			if (in_ras_intr && !use_baco)
 				amdgpu_job_stop_all_jobs_on_sched(&ring->sched);
 		}
 	}
 
 
-	if (in_ras_intr)
+	if (in_ras_intr && !use_baco)
 		goto skip_sched_resume;
 
 	/*
@@ -4136,7 +4194,7 @@ skip_hw_reset:
 skip_sched_resume:
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
 		/*unlock kfd: SRIOV would do it separately */
-		if (!in_ras_intr && !amdgpu_sriov_vf(tmp_adev))
+		if (!(in_ras_intr && !use_baco) && !amdgpu_sriov_vf(tmp_adev))
 	                amdgpu_amdkfd_post_reset(tmp_adev);
 		amdgpu_device_unlock_adev(tmp_adev);
 	}
@@ -4285,3 +4343,35 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 	}
 }
 
+int amdgpu_device_baco_enter(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+
+	if (!amdgpu_device_supports_baco(adev->ddev))
+		return -ENOTSUPP;
+
+	if (ras && ras->supported)
+		adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
+
+	return amdgpu_dpm_baco_enter(adev);
+}
+
+int amdgpu_device_baco_exit(struct drm_device *dev)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int ret = 0;
+
+	if (!amdgpu_device_supports_baco(adev->ddev))
+		return -ENOTSUPP;
+
+	ret = amdgpu_dpm_baco_exit(adev);
+	if (ret)
+		return ret;
+
+	if (ras && ras->supported)
+		adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
new file mode 100644
index 000000000000..61a26c15c8dd
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_df.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2020 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __AMDGPU_DF_H__
+#define __AMDGPU_DF_H__
+
+struct amdgpu_df_hash_status {
+	bool hash_64k;
+	bool hash_2m;
+	bool hash_1g;
+};
+
+struct amdgpu_df_funcs {
+	void (*sw_init)(struct amdgpu_device *adev);
+	void (*sw_fini)(struct amdgpu_device *adev);
+	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
+				      bool enable);
+	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
+	u32 (*get_hbm_channel_number)(struct amdgpu_device *adev);
+	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
+						 bool enable);
+	void (*get_clockgating_state)(struct amdgpu_device *adev,
+				      u32 *flags);
+	void (*enable_ecc_force_par_wr_rmw)(struct amdgpu_device *adev,
+					    bool enable);
+	int (*pmc_start)(struct amdgpu_device *adev, uint64_t config,
+					 int is_enable);
+	int (*pmc_stop)(struct amdgpu_device *adev, uint64_t config,
+					 int is_disable);
+	void (*pmc_get_count)(struct amdgpu_device *adev, uint64_t config,
+					 uint64_t *count);
+	uint64_t (*get_fica)(struct amdgpu_device *adev, uint32_t ficaa_val);
+	void (*set_fica)(struct amdgpu_device *adev, uint32_t ficaa_val,
+			 uint32_t ficadl_val, uint32_t ficadh_val);
+};
+
+struct amdgpu_df {
+	struct amdgpu_df_hash_status	hash_status;
+	const struct amdgpu_df_funcs	*funcs;
+};
+
+#endif /* __AMDGPU_DF_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 3cadb0b76f22..6d520a3eec40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -513,13 +513,23 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 	 * will not allow USWC mappings.
 	 * Also, don't allow GTT domain if the BO doens't have USWC falg set.
 	 */
-	if (adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type < CHIP_RAVEN &&
-	    (adev->flags & AMD_IS_APU) &&
-	    (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
+	if ((bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
 	    amdgpu_bo_support_uswc(bo_flags) &&
-	    amdgpu_device_asic_has_dc_support(adev->asic_type))
-		domain |= AMDGPU_GEM_DOMAIN_GTT;
+	    amdgpu_device_asic_has_dc_support(adev->asic_type)) {
+		switch (adev->asic_type) {
+		case CHIP_CARRIZO:
+		case CHIP_STONEY:
+			domain |= AMDGPU_GEM_DOMAIN_GTT;
+			break;
+		case CHIP_RAVEN:
+			/* enable S/G on PCO and RV2 */
+			if (adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
+				domain |= AMDGPU_GEM_DOMAIN_GTT;
+			break;
+		default:
+			break;
+		}
+	}
 #endif
 
 	return domain;
@@ -690,7 +700,6 @@ bool amdgpu_display_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
 	struct amdgpu_encoder *amdgpu_encoder;
 	struct drm_connector *connector;
-	struct amdgpu_connector *amdgpu_connector;
 	u32 src_v = 1, dst_v = 1;
 	u32 src_h = 1, dst_h = 1;
 
@@ -702,7 +711,6 @@ bool amdgpu_display_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 			continue;
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 		connector = amdgpu_get_connector_for_encoder(encoder);
-		amdgpu_connector = to_amdgpu_connector(connector);
 
 		/* set scaling */
 		if (amdgpu_encoder->rmx_type == RMX_OFF)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index e2eec7b66334..a59cd47aa6c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -360,10 +360,8 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 		return ERR_PTR(-EPERM);
 
 	buf = drm_gem_prime_export(gobj, flags);
-	if (!IS_ERR(buf)) {
-		buf->file->f_mapping = gobj->dev->anon_inode->i_mapping;
+	if (!IS_ERR(buf))
 		buf->ops = &amdgpu_dmabuf_ops;
-	}
 
 	return buf;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 9cc270efee7c..a2e8c3dfb4f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -946,20 +946,63 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 	bool swsmu = is_support_sw_smu(adev);
 
 	switch (block_type) {
-	case AMD_IP_BLOCK_TYPE_GFX:
 	case AMD_IP_BLOCK_TYPE_UVD:
-	case AMD_IP_BLOCK_TYPE_VCN:
 	case AMD_IP_BLOCK_TYPE_VCE:
+		if (swsmu) {
+			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
+		} else if (adev->powerplay.pp_funcs &&
+			   adev->powerplay.pp_funcs->set_powergating_by_smu) {
+			/*
+			 * TODO: need a better lock mechanism
+			 *
+			 * Here adev->pm.mutex lock protection is enforced on
+			 * UVD and VCE cases only. Since for other cases, there
+			 * may be already lock protection in amdgpu_pm.c.
+			 * This is a quick fix for the deadlock issue below.
+			 *     NFO: task ocltst:2028 blocked for more than 120 seconds.
+			 *     Tainted: G           OE     5.0.0-37-generic #40~18.04.1-Ubuntu
+			 *     echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
+			 *     cltst          D    0  2028   2026 0x00000000
+			 *     all Trace:
+			 *     __schedule+0x2c0/0x870
+			 *     schedule+0x2c/0x70
+			 *     schedule_preempt_disabled+0xe/0x10
+			 *     __mutex_lock.isra.9+0x26d/0x4e0
+			 *     __mutex_lock_slowpath+0x13/0x20
+			 *     ? __mutex_lock_slowpath+0x13/0x20
+			 *     mutex_lock+0x2f/0x40
+			 *     amdgpu_dpm_set_powergating_by_smu+0x64/0xe0 [amdgpu]
+			 *     gfx_v8_0_enable_gfx_static_mg_power_gating+0x3c/0x70 [amdgpu]
+			 *     gfx_v8_0_set_powergating_state+0x66/0x260 [amdgpu]
+			 *     amdgpu_device_ip_set_powergating_state+0x62/0xb0 [amdgpu]
+			 *     pp_dpm_force_performance_level+0xe7/0x100 [amdgpu]
+			 *     amdgpu_set_dpm_forced_performance_level+0x129/0x330 [amdgpu]
+			 */
+			mutex_lock(&adev->pm.mutex);
+			ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
+				(adev)->powerplay.pp_handle, block_type, gate));
+			mutex_unlock(&adev->pm.mutex);
+		}
+		break;
+	case AMD_IP_BLOCK_TYPE_GFX:
+	case AMD_IP_BLOCK_TYPE_VCN:
 	case AMD_IP_BLOCK_TYPE_SDMA:
 		if (swsmu)
 			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
-		else
+		else if (adev->powerplay.pp_funcs &&
+			 adev->powerplay.pp_funcs->set_powergating_by_smu)
 			ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
 				(adev)->powerplay.pp_handle, block_type, gate));
 		break;
+	case AMD_IP_BLOCK_TYPE_JPEG:
+		if (swsmu)
+			ret = smu_dpm_set_power_gate(&adev->smu, block_type, gate);
+		break;
 	case AMD_IP_BLOCK_TYPE_GMC:
 	case AMD_IP_BLOCK_TYPE_ACP:
-		ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
+		if (adev->powerplay.pp_funcs &&
+		    adev->powerplay.pp_funcs->set_powergating_by_smu)
+			ret = ((adev)->powerplay.pp_funcs->set_powergating_by_smu(
 				(adev)->powerplay.pp_handle, block_type, gate));
 		break;
 	default:
@@ -968,3 +1011,163 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, uint32_t block
 
 	return ret;
 }
+
+int amdgpu_dpm_baco_enter(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_baco_enter(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->set_asic_baco_state)
+			return -ENOENT;
+
+		/* enter BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 1);
+	}
+
+	return ret;
+}
+
+int amdgpu_dpm_baco_exit(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_baco_exit(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->set_asic_baco_state)
+			return -ENOENT;
+
+		/* exit BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 0);
+	}
+
+	return ret;
+}
+
+int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
+			     enum pp_mp1_state mp1_state)
+{
+	int ret = 0;
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_set_mp1_state(&adev->smu, mp1_state);
+	} else if (adev->powerplay.pp_funcs &&
+		   adev->powerplay.pp_funcs->set_mp1_state) {
+		ret = adev->powerplay.pp_funcs->set_mp1_state(
+				adev->powerplay.pp_handle,
+				mp1_state);
+	}
+
+	return ret;
+}
+
+bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	bool baco_cap;
+
+	if (is_support_sw_smu(adev)) {
+		return smu_baco_is_support(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->get_asic_baco_capability)
+			return false;
+
+		if (pp_funcs->get_asic_baco_capability(pp_handle, &baco_cap))
+			return false;
+
+		return baco_cap ? true : false;
+	}
+}
+
+int amdgpu_dpm_mode2_reset(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+
+	if (is_support_sw_smu(adev)) {
+		return smu_mode2_reset(smu);
+	} else {
+		if (!pp_funcs || !pp_funcs->asic_reset_mode_2)
+			return -ENOENT;
+
+		return pp_funcs->asic_reset_mode_2(pp_handle);
+	}
+}
+
+int amdgpu_dpm_baco_reset(struct amdgpu_device *adev)
+{
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct smu_context *smu = &adev->smu;
+	int ret = 0;
+
+	dev_info(adev->dev, "GPU BACO reset\n");
+
+	if (is_support_sw_smu(adev)) {
+		ret = smu_baco_enter(smu);
+		if (ret)
+			return ret;
+
+		ret = smu_baco_exit(smu);
+		if (ret)
+			return ret;
+	} else {
+		if (!pp_funcs
+		    || !pp_funcs->set_asic_baco_state)
+			return -ENOENT;
+
+		/* enter BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 1);
+		if (ret)
+			return ret;
+
+		/* exit BACO state */
+		ret = pp_funcs->set_asic_baco_state(pp_handle, 0);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
+				    enum PP_SMC_POWER_PROFILE type,
+				    bool en)
+{
+	int ret = 0;
+
+	if (is_support_sw_smu(adev))
+		ret = smu_switch_power_profile(&adev->smu, type, en);
+	else if (adev->powerplay.pp_funcs &&
+		 adev->powerplay.pp_funcs->switch_power_profile)
+		ret = adev->powerplay.pp_funcs->switch_power_profile(
+			adev->powerplay.pp_handle, type, en);
+
+	return ret;
+}
+
+int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
+			       uint32_t pstate)
+{
+	int ret = 0;
+
+	if (is_support_sw_smu_xgmi(adev))
+		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
+	else if (adev->powerplay.pp_funcs &&
+		 adev->powerplay.pp_funcs->set_xgmi_pstate)
+		ret = adev->powerplay.pp_funcs->set_xgmi_pstate(adev->powerplay.pp_handle,
+								pstate);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 2cfb677272af..902ca6c00cca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -341,10 +341,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->reset_power_profile_state(\
 			(adev)->powerplay.pp_handle, request))
 
-#define amdgpu_dpm_switch_power_profile(adev, type, en) \
-		((adev)->powerplay.pp_funcs->switch_power_profile(\
-			(adev)->powerplay.pp_handle, type, en))
-
 #define amdgpu_dpm_set_clockgating_by_smu(adev, msg_id) \
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
@@ -517,4 +513,24 @@ extern int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low);
 
 extern int amdgpu_dpm_get_mclk(struct amdgpu_device *adev, bool low);
 
+int amdgpu_dpm_set_xgmi_pstate(struct amdgpu_device *adev,
+			       uint32_t pstate);
+
+int amdgpu_dpm_switch_power_profile(struct amdgpu_device *adev,
+				    enum PP_SMC_POWER_PROFILE type,
+				    bool en);
+
+int amdgpu_dpm_baco_reset(struct amdgpu_device *adev);
+
+int amdgpu_dpm_mode2_reset(struct amdgpu_device *adev);
+
+bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev);
+
+int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
+			     enum pp_mp1_state mp1_state);
+
+int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
+
+int amdgpu_dpm_baco_enter(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 30a1e3ac21d6..94e2fd758e01 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1147,7 +1147,7 @@ static int amdgpu_pmops_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_suspend(drm_dev, true, true);
+	return amdgpu_device_suspend(drm_dev, true);
 }
 
 static int amdgpu_pmops_resume(struct device *dev)
@@ -1155,13 +1155,14 @@ static int amdgpu_pmops_resume(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
 	/* GPU comes up enabled by the bios on resume */
-	if (amdgpu_device_is_px(drm_dev)) {
+	if (amdgpu_device_supports_boco(drm_dev) ||
+	    amdgpu_device_supports_baco(drm_dev)) {
 		pm_runtime_disable(dev);
 		pm_runtime_set_active(dev);
 		pm_runtime_enable(dev);
 	}
 
-	return amdgpu_device_resume(drm_dev, true, true);
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_freeze(struct device *dev)
@@ -1170,7 +1171,7 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	struct amdgpu_device *adev = drm_dev->dev_private;
 	int r;
 
-	r = amdgpu_device_suspend(drm_dev, false, true);
+	r = amdgpu_device_suspend(drm_dev, true);
 	if (r)
 		return r;
 	return amdgpu_asic_reset(adev);
@@ -1180,46 +1181,66 @@ static int amdgpu_pmops_thaw(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_resume(drm_dev, false, true);
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_poweroff(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_suspend(drm_dev, true, true);
+	return amdgpu_device_suspend(drm_dev, true);
 }
 
 static int amdgpu_pmops_restore(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
-	return amdgpu_device_resume(drm_dev, false, true);
+	return amdgpu_device_resume(drm_dev, true);
 }
 
 static int amdgpu_pmops_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	int ret;
+	struct amdgpu_device *adev = drm_dev->dev_private;
+	int ret, i;
 
-	if (!amdgpu_device_is_px(drm_dev)) {
+	if (!adev->runpm) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+	/* wait for all rings to drain before suspending */
+	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
+		struct amdgpu_ring *ring = adev->rings[i];
+		if (ring && ring->sched.ready) {
+			ret = amdgpu_fence_wait_empty(ring);
+			if (ret)
+				return -EBUSY;
+		}
+	}
+
+	if (amdgpu_device_supports_boco(drm_dev))
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
 	drm_kms_helper_poll_disable(drm_dev);
 
-	ret = amdgpu_device_suspend(drm_dev, false, false);
-	pci_save_state(pdev);
-	pci_disable_device(pdev);
-	pci_ignore_hotplug(pdev);
-	if (amdgpu_is_atpx_hybrid())
-		pci_set_power_state(pdev, PCI_D3cold);
-	else if (!amdgpu_has_atpx_dgpu_power_cntl())
-		pci_set_power_state(pdev, PCI_D3hot);
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	ret = amdgpu_device_suspend(drm_dev, false);
+	if (amdgpu_device_supports_boco(drm_dev)) {
+		/* Only need to handle PCI state in the driver for ATPX
+		 * PCI core handles it for _PR3.
+		 */
+		if (amdgpu_is_atpx_hybrid()) {
+			pci_ignore_hotplug(pdev);
+		} else {
+			pci_save_state(pdev);
+			pci_disable_device(pdev);
+			pci_ignore_hotplug(pdev);
+			pci_set_power_state(pdev, PCI_D3cold);
+		}
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF;
+	} else if (amdgpu_device_supports_baco(drm_dev)) {
+		amdgpu_device_baco_enter(drm_dev);
+	}
 
 	return 0;
 }
@@ -1228,34 +1249,45 @@ static int amdgpu_pmops_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct amdgpu_device *adev = drm_dev->dev_private;
 	int ret;
 
-	if (!amdgpu_device_is_px(drm_dev))
+	if (!adev->runpm)
 		return -EINVAL;
 
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
-
-	if (amdgpu_is_atpx_hybrid() ||
-	    !amdgpu_has_atpx_dgpu_power_cntl())
-		pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
-	ret = pci_enable_device(pdev);
-	if (ret)
-		return ret;
-	pci_set_master(pdev);
-
-	ret = amdgpu_device_resume(drm_dev, false, false);
+	if (amdgpu_device_supports_boco(drm_dev)) {
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
+
+		/* Only need to handle PCI state in the driver for ATPX
+		 * PCI core handles it for _PR3.
+		 */
+		if (amdgpu_is_atpx_hybrid()) {
+			pci_set_master(pdev);
+		} else {
+			pci_set_power_state(pdev, PCI_D0);
+			pci_restore_state(pdev);
+			ret = pci_enable_device(pdev);
+			if (ret)
+				return ret;
+			pci_set_master(pdev);
+		}
+	} else if (amdgpu_device_supports_baco(drm_dev)) {
+		amdgpu_device_baco_exit(drm_dev);
+	}
+	ret = amdgpu_device_resume(drm_dev, false);
 	drm_kms_helper_poll_enable(drm_dev);
-	drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
+	if (amdgpu_device_supports_boco(drm_dev))
+		drm_dev->switch_power_state = DRM_SWITCH_POWER_ON;
 	return 0;
 }
 
 static int amdgpu_pmops_runtime_idle(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_dev->dev_private;
 	struct drm_crtc *crtc;
 
-	if (!amdgpu_device_is_px(drm_dev)) {
+	if (!adev->runpm) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 143753d237e7..2672dc64a310 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -69,7 +69,7 @@ amdgpufb_release(struct fb_info *info, int user)
 	return 0;
 }
 
-static struct fb_ops amdgpufb_ops = {
+static const struct fb_ops amdgpufb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = amdgpufb_open,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 377fe20bce23..3c01252b1e0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -34,6 +34,7 @@
 #include <linux/kref.h>
 #include <linux/slab.h>
 #include <linux/firmware.h>
+#include <linux/pm_runtime.h>
 
 #include <drm/drm_debugfs.h>
 
@@ -154,7 +155,7 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 		       seq);
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
-
+	pm_runtime_get_noresume(adev->ddev->dev);
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	if (unlikely(rcu_dereference_protected(*ptr, 1))) {
 		struct dma_fence *old;
@@ -234,6 +235,7 @@ static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring)
 bool amdgpu_fence_process(struct amdgpu_ring *ring)
 {
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
+	struct amdgpu_device *adev = ring->adev;
 	uint32_t seq, last_seq;
 	int r;
 
@@ -274,6 +276,8 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)
 			BUG();
 
 		dma_fence_put(fence);
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 	} while (last_seq != seq);
 
 	return true;
@@ -737,10 +741,18 @@ static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return 0;
 
 	seq_printf(m, "gpu recover\n");
 	amdgpu_device_gpu_recover(adev, NULL);
 
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 19705e399905..e01e681d2a60 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -302,6 +302,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
  * @pages: number of pages to bind
  * @pagelist: pages to bind
  * @dma_addr: DMA addresses of pages
+ * @flags: page table entry flags
  *
  * Binds the requested pages to the gart page table
  * (all asics).
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index e00b46180d2e..b88b8b82bb64 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -543,12 +543,6 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 	if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 		return;
 
-	if (!is_support_sw_smu(adev) &&
-	    (!adev->powerplay.pp_funcs ||
-	     !adev->powerplay.pp_funcs->set_powergating_by_smu))
-		return;
-
-
 	mutex_lock(&adev->gfx.gfx_off_mutex);
 
 	if (!enable)
@@ -641,7 +635,7 @@ int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
 		kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
 		if (adev->gfx.funcs->query_ras_error_count)
 			adev->gfx.funcs->query_ras_error_count(adev, err_data);
-		amdgpu_ras_reset_gpu(adev, 0);
+		amdgpu_ras_reset_gpu(adev);
 	}
 	return AMDGPU_RAS_SUCCESS;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 0ae0a2715b0d..af4bd279f42f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -76,11 +76,15 @@ struct kiq_pm4_funcs {
 					struct amdgpu_ring *ring,
 					u64 addr,
 					u64 seq);
+	void (*kiq_invalidate_tlbs)(struct amdgpu_ring *kiq_ring,
+				uint16_t pasid, uint32_t flush_type,
+				bool all_hub);
 	/* Packet sizes */
 	int set_resources_size;
 	int map_queues_size;
 	int unmap_queues_size;
 	int query_status_size;
+	int invalidate_tlbs_size;
 };
 
 struct amdgpu_kiq {
@@ -269,8 +273,12 @@ struct amdgpu_gfx {
 	bool				me_fw_write_wait;
 	bool				cp_fw_write_wait;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
+	struct drm_gpu_scheduler	*gfx_sched[AMDGPU_MAX_GFX_RINGS];
+	uint32_t			num_gfx_sched;
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
+	struct drm_gpu_scheduler	*compute_sched[AMDGPU_MAX_COMPUTE_RINGS];
+	uint32_t			num_compute_sched;
 	unsigned			num_compute_rings;
 	struct amdgpu_irq_src		eop_irq;
 	struct amdgpu_irq_src		priv_reg_irq;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index a12f33c0f5df..5884ab590486 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -223,7 +223,7 @@ void amdgpu_gmc_agp_location(struct amdgpu_device *adev, struct amdgpu_gmc *mc)
 	u64 size_af, size_bf;
 
 	if (amdgpu_sriov_vf(adev)) {
-		mc->agp_start = 0xffffffff;
+		mc->agp_start = 0xffffffffffff;
 		mc->agp_end = 0x0;
 		mc->agp_size = 0;
 
@@ -333,3 +333,43 @@ void amdgpu_gmc_ras_fini(struct amdgpu_device *adev)
 	amdgpu_mmhub_ras_fini(adev);
 	amdgpu_xgmi_ras_fini(adev);
 }
+
+	/*
+	 * The latest engine allocation on gfx9/10 is:
+	 * Engine 2, 3: firmware
+	 * Engine 0, 1, 4~16: amdgpu ring,
+	 *                    subject to change when ring number changes
+	 * Engine 17: Gart flushes
+	 */
+#define GFXHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
+#define MMHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
+
+int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] =
+		{GFXHUB_FREE_VM_INV_ENGS_BITMAP, MMHUB_FREE_VM_INV_ENGS_BITMAP,
+		GFXHUB_FREE_VM_INV_ENGS_BITMAP};
+	unsigned i;
+	unsigned vmhub, inv_eng;
+
+	for (i = 0; i < adev->num_rings; ++i) {
+		ring = adev->rings[i];
+		vmhub = ring->funcs->vmhub;
+
+		inv_eng = ffs(vm_inv_engs[vmhub]);
+		if (!inv_eng) {
+			dev_err(adev->dev, "no VM inv eng for ring %s\n",
+				ring->name);
+			return -EINVAL;
+		}
+
+		ring->vm_inv_eng = inv_eng - 1;
+		vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
+
+		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
+			 ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index b499a3de8bb6..86267baca07c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -60,6 +60,11 @@
  */
 #define AMDGPU_GMC_FAULT_TIMEOUT	5000ULL
 
+/*
+ * Default stolen memory size, 1024 * 768 * 4
+ */
+#define AMDGPU_STOLEN_BIST_TRAINING_DEFAULT_SIZE	0x300000ULL
+
 struct firmware;
 
 /*
@@ -92,6 +97,9 @@ struct amdgpu_gmc_funcs {
 	/* flush the vm tlb via mmio */
 	void (*flush_gpu_tlb)(struct amdgpu_device *adev, uint32_t vmid,
 				uint32_t vmhub, uint32_t flush_type);
+	/* flush the vm tlb via pasid */
+	int (*flush_gpu_tlb_pasid)(struct amdgpu_device *adev, uint16_t pasid,
+					uint32_t flush_type, bool all_hub);
 	/* flush the vm tlb via ring */
 	uint64_t (*emit_flush_gpu_tlb)(struct amdgpu_ring *ring, unsigned vmid,
 				       uint64_t pd_addr);
@@ -216,6 +224,9 @@ struct amdgpu_gmc {
 };
 
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
+#define amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, type, allhub) \
+	((adev)->gmc.gmc_funcs->flush_gpu_tlb_pasid \
+	((adev), (pasid), (type), (allhub)))
 #define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
 #define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid))
 #define amdgpu_gmc_map_mtype(adev, flags) (adev)->gmc.gmc_funcs->map_mtype((adev),(flags))
@@ -267,5 +278,6 @@ bool amdgpu_gmc_filter_faults(struct amdgpu_device *adev, uint64_t addr,
 			      uint16_t pasid, uint64_t timestamp);
 int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev);
 void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
+int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 6f9289735e31..3a67f6c046d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -206,7 +206,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm,
 	int r;
 
 	if (ring->vmid_wait && !dma_fence_is_signaled(ring->vmid_wait))
-		return amdgpu_sync_fence(adev, sync, ring->vmid_wait, false);
+		return amdgpu_sync_fence(sync, ring->vmid_wait, false);
 
 	fences = kmalloc_array(sizeof(void *), id_mgr->num_ids, GFP_KERNEL);
 	if (!fences)
@@ -241,7 +241,7 @@ static int amdgpu_vmid_grab_idle(struct amdgpu_vm *vm,
 			return -ENOMEM;
 		}
 
-		r = amdgpu_sync_fence(adev, sync, &array->base, false);
+		r = amdgpu_sync_fence(sync, &array->base, false);
 		dma_fence_put(ring->vmid_wait);
 		ring->vmid_wait = &array->base;
 		return r;
@@ -294,7 +294,7 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 		tmp = amdgpu_sync_peek_fence(&(*id)->active, ring);
 		if (tmp) {
 			*id = NULL;
-			r = amdgpu_sync_fence(adev, sync, tmp, false);
+			r = amdgpu_sync_fence(sync, tmp, false);
 			return r;
 		}
 		needs_flush = true;
@@ -303,7 +303,7 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 	/* Good we can use this VMID. Remember this submission as
 	* user of the VMID.
 	*/
-	r = amdgpu_sync_fence(ring->adev, &(*id)->active, fence, false);
+	r = amdgpu_sync_fence(&(*id)->active, fence, false);
 	if (r)
 		return r;
 
@@ -375,7 +375,7 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm,
 		/* Good, we can use this VMID. Remember this submission as
 		 * user of the VMID.
 		 */
-		r = amdgpu_sync_fence(ring->adev, &(*id)->active, fence, false);
+		r = amdgpu_sync_fence(&(*id)->active, fence, false);
 		if (r)
 			return r;
 
@@ -435,8 +435,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 			id = idle;
 
 			/* Remember this submission as user of the VMID */
-			r = amdgpu_sync_fence(ring->adev, &id->active,
-					      fence, false);
+			r = amdgpu_sync_fence(&id->active, fence, false);
 			if (r)
 				goto error;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
index 6d8f05511aba..111a301ce878 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -66,7 +66,6 @@ int amdgpu_ih_ring_init(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
 		if (ih->ring == NULL)
 			return -ENOMEM;
 
-		memset((void *)ih->ring, 0, ih->ring_size + 8);
 		ih->gpu_addr = dma_addr;
 		ih->wptr_addr = dma_addr + ih->ring_size;
 		ih->wptr_cpu = &ih->ring[ih->ring_size / 4];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 30d540d23b77..5ed4227f304b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -55,6 +55,7 @@
 #include "amdgpu_connectors.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
+#include "amdgpu_ras.h"
 
 #include <linux/pm_runtime.h>
 
@@ -162,13 +163,15 @@ irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 	 * register to check whether the interrupt is triggered or not, and properly
 	 * ack the interrupt if it is there
 	 */
-	if (adev->nbio.funcs &&
-	    adev->nbio.funcs->handle_ras_controller_intr_no_bifring)
-		adev->nbio.funcs->handle_ras_controller_intr_no_bifring(adev);
-
-	if (adev->nbio.funcs &&
-	    adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring)
-		adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring(adev);
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__PCIE_BIF)) {
+		if (adev->nbio.funcs &&
+		    adev->nbio.funcs->handle_ras_controller_intr_no_bifring)
+			adev->nbio.funcs->handle_ras_controller_intr_no_bifring(adev);
+
+		if (adev->nbio.funcs &&
+		    adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring)
+			adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring(adev);
+	}
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4fb20e870e63..d42be880a236 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -153,7 +153,6 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 	if (r)
 		return r;
 
-	job->owner = owner;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
 	priority = job->base.s_priority;
@@ -193,8 +192,7 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 	fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 	if (fence && explicit) {
 		if (drm_sched_dependency_optimized(fence, s_entity)) {
-			r = amdgpu_sync_fence(ring->adev, &job->sched_sync,
-					      fence, false);
+			r = amdgpu_sync_fence(&job->sched_sync, fence, false);
 			if (r)
 				DRM_ERROR("Error adding fence (%d)\n", r);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index dc7ee9358dcd..3f7b8433d179 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -49,7 +49,6 @@ struct amdgpu_job {
 	uint32_t		preamble_status;
 	uint32_t                preemption_status;
 	uint32_t		num_ibs;
-	void			*owner;
 	bool                    vm_needs_flush;
 	uint64_t		vm_pd_addr;
 	unsigned		vmid;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
new file mode 100644
index 000000000000..5727f00afc8e
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -0,0 +1,211 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "amdgpu_pm.h"
+#include "soc15d.h"
+#include "soc15_common.h"
+
+#define JPEG_IDLE_TIMEOUT	msecs_to_jiffies(1000)
+
+static void amdgpu_jpeg_idle_work_handler(struct work_struct *work);
+
+int amdgpu_jpeg_sw_init(struct amdgpu_device *adev)
+{
+	INIT_DELAYED_WORK(&adev->jpeg.idle_work, amdgpu_jpeg_idle_work_handler);
+
+	return 0;
+}
+
+int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev)
+{
+	int i;
+
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		amdgpu_ring_fini(&adev->jpeg.inst[i].ring_dec);
+	}
+
+	return 0;
+}
+
+int amdgpu_jpeg_suspend(struct amdgpu_device *adev)
+{
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
+
+	return 0;
+}
+
+int amdgpu_jpeg_resume(struct amdgpu_device *adev)
+{
+	return 0;
+}
+
+static void amdgpu_jpeg_idle_work_handler(struct work_struct *work)
+{
+	struct amdgpu_device *adev =
+		container_of(work, struct amdgpu_device, jpeg.idle_work.work);
+	unsigned int fences = 0;
+	unsigned int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		fences += amdgpu_fence_count_emitted(&adev->jpeg.inst[i].ring_dec);
+	}
+
+	if (fences == 0)
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
+						       AMD_PG_STATE_GATE);
+	else
+		schedule_delayed_work(&adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
+}
+
+void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	bool set_clocks = !cancel_delayed_work_sync(&adev->jpeg.idle_work);
+
+	if (set_clocks)
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_JPEG,
+						       AMD_PG_STATE_UNGATE);
+}
+
+void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring)
+{
+	schedule_delayed_work(&ring->adev->jpeg.idle_work, JPEG_IDLE_TIMEOUT);
+}
+
+int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	int r;
+
+	WREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch, 0xCAFEDEAD);
+	r = amdgpu_ring_alloc(ring, 3);
+	if (r)
+		return r;
+
+	amdgpu_ring_write(ring, PACKET0(adev->jpeg.internal.jpeg_pitch, 0));
+	amdgpu_ring_write(ring, 0xDEADBEEF);
+	amdgpu_ring_commit(ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
+	return r;
+}
+
+static int amdgpu_jpeg_dec_set_reg(struct amdgpu_ring *ring, uint32_t handle,
+		struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_job *job;
+	struct amdgpu_ib *ib;
+	struct dma_fence *f = NULL;
+	const unsigned ib_size_dw = 16;
+	int i, r;
+
+	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+	if (r)
+		return r;
+
+	ib = &job->ibs[0];
+
+	ib->ptr[0] = PACKETJ(adev->jpeg.internal.jpeg_pitch, 0, 0, PACKETJ_TYPE0);
+	ib->ptr[1] = 0xDEADBEEF;
+	for (i = 2; i < 16; i += 2) {
+		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ib->ptr[i+1] = 0;
+	}
+	ib->length_dw = 16;
+
+	r = amdgpu_job_submit_direct(job, ring, &f);
+	if (r)
+		goto err;
+
+	if (fence)
+		*fence = dma_fence_get(f);
+	dma_fence_put(f);
+
+	return 0;
+
+err:
+	amdgpu_job_free(job);
+	return r;
+}
+
+int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	struct dma_fence *fence = NULL;
+	long r = 0;
+
+	r = amdgpu_jpeg_dec_set_reg(ring, 1, &fence);
+	if (r)
+		goto error;
+
+	r = dma_fence_wait_timeout(fence, false, timeout);
+	if (r == 0) {
+		r = -ETIMEDOUT;
+		goto error;
+	} else if (r < 0) {
+		goto error;
+	} else {
+		r = 0;
+	}
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(adev->jpeg.inst[ring->me].external.jpeg_pitch);
+		if (tmp == 0xDEADBEEF)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
+	dma_fence_put(fence);
+error:
+	return r;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
new file mode 100644
index 000000000000..bd9ef9cc86de
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __AMDGPU_JPEG_H__
+#define __AMDGPU_JPEG_H__
+
+#define AMDGPU_MAX_JPEG_INSTANCES	2
+
+#define AMDGPU_JPEG_HARVEST_JPEG0 (1 << 0)
+#define AMDGPU_JPEG_HARVEST_JPEG1 (1 << 1)
+
+struct amdgpu_jpeg_reg{
+	unsigned jpeg_pitch;
+};
+
+struct amdgpu_jpeg_inst {
+	struct amdgpu_ring ring_dec;
+	struct amdgpu_irq_src irq;
+	struct amdgpu_jpeg_reg external;
+};
+
+struct amdgpu_jpeg {
+	uint8_t	num_jpeg_inst;
+	struct amdgpu_jpeg_inst inst[AMDGPU_MAX_JPEG_INSTANCES];
+	struct amdgpu_jpeg_reg internal;
+	struct drm_gpu_scheduler *jpeg_sched[AMDGPU_MAX_JPEG_INSTANCES];
+	uint32_t num_jpeg_sched;
+	unsigned harvest_config;
+	struct delayed_work idle_work;
+	enum amd_powergating_state cur_state;
+};
+
+int amdgpu_jpeg_sw_init(struct amdgpu_device *adev);
+int amdgpu_jpeg_sw_fini(struct amdgpu_device *adev);
+int amdgpu_jpeg_suspend(struct amdgpu_device *adev);
+int amdgpu_jpeg_resume(struct amdgpu_device *adev);
+
+void amdgpu_jpeg_ring_begin_use(struct amdgpu_ring *ring);
+void amdgpu_jpeg_ring_end_use(struct amdgpu_ring *ring);
+
+int amdgpu_jpeg_dec_ring_test_ring(struct amdgpu_ring *ring);
+int amdgpu_jpeg_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
+
+#endif /*__AMDGPU_JPEG_H__*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index b6db28a570c2..60591dbc2097 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -91,7 +91,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_request_full_gpu(adev, false);
 
-	if (amdgpu_device_is_px(dev)) {
+	if (adev->runpm) {
 		pm_runtime_get_sync(dev->dev);
 		pm_runtime_forbid(dev->dev);
 	}
@@ -150,8 +150,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	}
 	dev->dev_private = (void *)adev;
 
-	if ((amdgpu_runtime_pm != 0) &&
-	    amdgpu_has_atpx() &&
+	if (amdgpu_has_atpx() &&
 	    (amdgpu_is_atpx_hybrid() ||
 	     amdgpu_has_atpx_dgpu_power_cntl()) &&
 	    ((flags & AMD_IS_APU) == 0) &&
@@ -170,6 +169,13 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		goto out;
 	}
 
+	if (amdgpu_device_supports_boco(dev) &&
+	    (amdgpu_runtime_pm != 0)) /* enable runpm by default */
+		adev->runpm = true;
+	else if (amdgpu_device_supports_baco(dev) &&
+		 (amdgpu_runtime_pm > 0)) /* enable runpm if runpm=1 */
+		adev->runpm = true;
+
 	/* Call ACPI methods: require modeset init
 	 * but failure is not fatal
 	 */
@@ -180,7 +186,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 				"Error during ACPI methods call\n");
 	}
 
-	if (amdgpu_device_is_px(dev)) {
+	if (adev->runpm) {
 		dev_pm_set_driver_flags(dev->dev, DPM_FLAG_NEVER_SKIP);
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
@@ -193,7 +199,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 out:
 	if (r) {
 		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
-		if (adev->rmmio && amdgpu_device_is_px(dev))
+		if (adev->rmmio && adev->runpm)
 			pm_runtime_put_noidle(dev->dev);
 		amdgpu_driver_unload_kms(dev);
 	}
@@ -293,6 +299,10 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 		fw_info->ver = adev->dm.dmcu_fw_version;
 		fw_info->feature = 0;
 		break;
+	case AMDGPU_INFO_FW_DMCUB:
+		fw_info->ver = adev->dm.dmcub_fw_version;
+		fw_info->feature = 0;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -396,12 +406,14 @@ static int amdgpu_hw_ip_info(struct amdgpu_device *adev,
 		ib_size_alignment = 1;
 		break;
 	case AMDGPU_HW_IP_VCN_JPEG:
-		type = AMD_IP_BLOCK_TYPE_VCN;
-		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-			if (adev->uvd.harvest_config & (1 << i))
+		type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ?
+			AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN;
+
+		for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+			if (adev->jpeg.harvest_config & (1 << i))
 				continue;
 
-			if (adev->vcn.inst[i].ring_jpeg.sched.ready)
+			if (adev->jpeg.inst[i].ring_dec.sched.ready)
 				++num_rings;
 		}
 		ib_start_alignment = 16;
@@ -517,9 +529,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 		case AMDGPU_HW_IP_VCN_ENC:
-		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			break;
+		case AMDGPU_HW_IP_VCN_JPEG:
+			type = (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_JPEG)) ?
+				AMD_IP_BLOCK_TYPE_JPEG : AMD_IP_BLOCK_TYPE_VCN;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -688,10 +703,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		if (adev->pm.dpm_enabled) {
 			dev_info.max_engine_clock = amdgpu_dpm_get_sclk(adev, false) * 10;
 			dev_info.max_memory_clock = amdgpu_dpm_get_mclk(adev, false) * 10;
-		} else if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev) &&
-			   adev->virt.ops->get_pp_clk) {
-			dev_info.max_engine_clock = amdgpu_virt_get_sclk(adev, false) * 10;
-			dev_info.max_memory_clock = amdgpu_virt_get_mclk(adev, false) * 10;
 		} else {
 			dev_info.max_engine_clock = adev->clock.default_sclk * 10;
 			dev_info.max_memory_clock = adev->clock.default_mclk * 10;
@@ -1394,6 +1405,14 @@ static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data)
 	seq_printf(m, "DMCU feature version: %u, firmware version: 0x%08x\n",
 		   fw_info.feature, fw_info.ver);
 
+	/* DMCUB */
+	query_fw.fw_type = AMDGPU_INFO_FW_DMCUB;
+	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+	if (ret)
+		return ret;
+	seq_printf(m, "DMCUB feature version: %u, firmware version: 0x%08x\n",
+		   fw_info.feature, fw_info.ver);
+
 
 	seq_printf(m, "VBIOS version: %s\n", ctx->vbios_version);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index f205f56e3358..b03b1eb7ba04 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -37,6 +37,7 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/nospec.h>
+#include <linux/pm_runtime.h>
 #include "hwmgr.h"
 #define WIDTH_4K 3840
 
@@ -158,6 +159,14 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_pm_state_type pm;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		if (adev->smu.ppt_funcs->get_current_power_state)
@@ -170,6 +179,9 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev,
 		pm = adev->pm.dpm.user_state;
 	}
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(pm == POWER_STATE_TYPE_BATTERY) ? "battery" :
 			(pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance");
@@ -183,6 +195,10 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_pm_state_type  state;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
 
 	if (strncmp("battery", buf, strlen("battery")) == 0)
 		state = POWER_STATE_TYPE_BATTERY;
@@ -190,10 +206,12 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
 		state = POWER_STATE_TYPE_BALANCED;
 	else if (strncmp("performance", buf, strlen("performance")) == 0)
 		state = POWER_STATE_TYPE_PERFORMANCE;
-	else {
-		count = -EINVAL;
-		goto fail;
-	}
+	else
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		mutex_lock(&adev->pm.mutex);
@@ -206,12 +224,11 @@ static ssize_t amdgpu_set_dpm_state(struct device *dev,
 		adev->pm.dpm.user_state = state;
 		mutex_unlock(&adev->pm.mutex);
 
-		/* Can't set dpm state when the card is off */
-		if (!(adev->flags & AMD_IS_PX) ||
-		    (ddev->switch_power_state == DRM_SWITCH_POWER_ON))
-			amdgpu_pm_compute_clocks(adev);
+		amdgpu_pm_compute_clocks(adev);
 	}
-fail:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -282,13 +299,14 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	enum amd_dpm_forced_level level = 0xff;
+	int ret;
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return 0;
 
-	if ((adev->flags & AMD_IS_PX) &&
-	    (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return snprintf(buf, PAGE_SIZE, "off\n");
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		level = smu_get_performance_level(&adev->smu);
@@ -297,6 +315,9 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev,
 	else
 		level = adev->pm.dpm.forced_level;
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(level == AMD_DPM_FORCED_LEVEL_AUTO) ? "auto" :
 			(level == AMD_DPM_FORCED_LEVEL_LOW) ? "low" :
@@ -320,9 +341,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	enum amd_dpm_forced_level current_level = 0xff;
 	int ret = 0;
 
-	/* Can't force performance level when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
 		return -EINVAL;
 
 	if (strncmp("low", buf, strlen("low")) == 0) {
@@ -344,30 +363,23 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	} else if (strncmp("profile_peak", buf, strlen("profile_peak")) == 0) {
 		level = AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
 	}  else {
-		count = -EINVAL;
-		goto fail;
+		return -EINVAL;
 	}
 
-	/* handle sriov case here */
-	if (amdgpu_sriov_vf(adev)) {
-		if (amdgim_is_hwperf(adev) &&
-		    adev->virt.ops->force_dpm_level) {
-			mutex_lock(&adev->pm.mutex);
-			adev->virt.ops->force_dpm_level(adev, level);
-			mutex_unlock(&adev->pm.mutex);
-			return count;
-		} else {
-			return -EINVAL;
-		}
-	}
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		current_level = smu_get_performance_level(&adev->smu);
 	else if (adev->powerplay.pp_funcs->get_performance_level)
 		current_level = amdgpu_dpm_get_performance_level(adev);
 
-	if (current_level == level)
+	if (current_level == level) {
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		return count;
+	}
 
 	/* profile_exit setting is valid only when current mode is in profile mode */
 	if (!(current_level & (AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
@@ -376,29 +388,40 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev,
 	    AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)) &&
 	    (level == AMD_DPM_FORCED_LEVEL_PROFILE_EXIT)) {
 		pr_err("Currently not in any profile mode!\n");
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		return -EINVAL;
 	}
 
 	if (is_support_sw_smu(adev)) {
 		ret = smu_force_performance_level(&adev->smu, level);
-		if (ret)
-			count = -EINVAL;
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
+			return -EINVAL;
+		}
 	} else if (adev->powerplay.pp_funcs->force_performance_level) {
 		mutex_lock(&adev->pm.mutex);
 		if (adev->pm.dpm.thermal_active) {
-			count = -EINVAL;
 			mutex_unlock(&adev->pm.mutex);
-			goto fail;
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
+			return -EINVAL;
 		}
 		ret = amdgpu_dpm_force_performance_level(adev, level);
-		if (ret)
-			count = -EINVAL;
-		else
+		if (ret) {
+			mutex_unlock(&adev->pm.mutex);
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
+			return -EINVAL;
+		} else {
 			adev->pm.dpm.forced_level = level;
+		}
 		mutex_unlock(&adev->pm.mutex);
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
-fail:
 	return count;
 }
 
@@ -411,6 +434,10 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev,
 	struct pp_states_info data;
 	int i, buf_len, ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_get_power_num_states(&adev->smu, &data);
 		if (ret)
@@ -418,6 +445,9 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev,
 	} else if (adev->powerplay.pp_funcs->get_pp_num_states)
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	buf_len = snprintf(buf, PAGE_SIZE, "states: %d\n", data.nums);
 	for (i = 0; i < data.nums; i++)
 		buf_len += snprintf(buf + buf_len, PAGE_SIZE, "%d %s\n", i,
@@ -440,6 +470,13 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev,
 	enum amd_pm_state_type pm = 0;
 	int i = 0, ret = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		pm = smu_get_current_power_state(smu);
 		ret = smu_get_power_num_states(smu, &data);
@@ -451,6 +488,9 @@ static ssize_t amdgpu_get_pp_cur_state(struct device *dev,
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 	}
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	for (i = 0; i < data.nums; i++) {
 		if (pm == data.states[i])
 			break;
@@ -469,6 +509,9 @@ static ssize_t amdgpu_get_pp_force_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
 	if (adev->pp_force_state_enabled)
 		return amdgpu_get_pp_cur_state(dev, attr, buf);
 	else
@@ -486,6 +529,9 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 	unsigned long idx;
 	int ret;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	if (strlen(buf) == 1)
 		adev->pp_force_state_enabled = false;
 	else if (is_support_sw_smu(adev))
@@ -495,14 +541,18 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 		struct pp_states_info data;
 
 		ret = kstrtoul(buf, 0, &idx);
-		if (ret || idx >= ARRAY_SIZE(data.states)) {
-			count = -EINVAL;
-			goto fail;
-		}
+		if (ret || idx >= ARRAY_SIZE(data.states))
+			return -EINVAL;
+
 		idx = array_index_nospec(idx, ARRAY_SIZE(data.states));
 
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 		state = data.states[idx];
+
+		ret = pm_runtime_get_sync(ddev->dev);
+		if (ret < 0)
+			return ret;
+
 		/* only set user selected power states */
 		if (state != POWER_STATE_TYPE_INTERNAL_BOOT &&
 		    state != POWER_STATE_TYPE_DEFAULT) {
@@ -510,8 +560,10 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 					AMD_PP_TASK_ENABLE_USER_STATE, &state);
 			adev->pp_force_state_enabled = true;
 		}
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 	}
-fail:
+
 	return count;
 }
 
@@ -533,17 +585,32 @@ static ssize_t amdgpu_get_pp_table(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	char *table = NULL;
-	int size;
+	int size, ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		size = smu_sys_get_pp_table(&adev->smu, (void **)&table);
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		if (size < 0)
 			return size;
-	}
-	else if (adev->powerplay.pp_funcs->get_pp_table)
+	} else if (adev->powerplay.pp_funcs->get_pp_table) {
 		size = amdgpu_dpm_get_pp_table(adev, &table);
-	else
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
+		if (size < 0)
+			return size;
+	} else {
+		pm_runtime_mark_last_busy(ddev->dev);
+		pm_runtime_put_autosuspend(ddev->dev);
 		return 0;
+	}
 
 	if (size >= PAGE_SIZE)
 		size = PAGE_SIZE - 1;
@@ -562,13 +629,26 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_sys_set_pp_table(&adev->smu, (void *)buf, count);
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return ret;
+		}
 	} else if (adev->powerplay.pp_funcs->set_pp_table)
 		amdgpu_dpm_set_pp_table(adev, buf, count);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -654,6 +734,9 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 	const char delimiter[3] = {' ', '\n', '\0'};
 	uint32_t type;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	if (count > 127)
 		return -EINVAL;
 
@@ -689,18 +772,28 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 			tmp_str++;
 	}
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_od_edit_dpm_table(&adev->smu, type,
 					    parameter, parameter_size);
 
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return -EINVAL;
+		}
 	} else {
 		if (adev->powerplay.pp_funcs->odn_edit_dpm_table) {
 			ret = amdgpu_dpm_odn_edit_dpm_table(adev, type,
 						parameter, parameter_size);
-			if (ret)
+			if (ret) {
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
 				return -EINVAL;
+			}
 		}
 
 		if (type == PP_OD_COMMIT_DPM_TABLE) {
@@ -708,12 +801,18 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev,
 				amdgpu_dpm_dispatch_task(adev,
 						AMD_PP_TASK_READJUST_POWER_STATE,
 						NULL);
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
 				return count;
 			} else {
+				pm_runtime_mark_last_busy(ddev->dev);
+				pm_runtime_put_autosuspend(ddev->dev);
 				return -EINVAL;
 			}
 		}
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	return count;
 }
@@ -724,24 +823,33 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	uint32_t size = 0;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		size = smu_print_clk_levels(&adev->smu, SMU_OD_SCLK, buf);
 		size += smu_print_clk_levels(&adev->smu, SMU_OD_MCLK, buf+size);
 		size += smu_print_clk_levels(&adev->smu, SMU_OD_VDDC_CURVE, buf+size);
 		size += smu_print_clk_levels(&adev->smu, SMU_OD_RANGE, buf+size);
-		return size;
 	} else if (adev->powerplay.pp_funcs->print_clock_levels) {
 		size = amdgpu_dpm_print_clock_levels(adev, OD_SCLK, buf);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_MCLK, buf+size);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_VDDC_CURVE, buf+size);
 		size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf+size);
-		return size;
 	} else {
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
+	return size;
 }
 
 /**
@@ -770,21 +878,36 @@ static ssize_t amdgpu_set_pp_feature_status(struct device *dev,
 	uint64_t featuremask;
 	int ret;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	ret = kstrtou64(buf, 0, &featuremask);
 	if (ret)
 		return -EINVAL;
 
 	pr_debug("featuremask = 0x%llx\n", featuremask);
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		ret = smu_sys_set_pp_feature_mask(&adev->smu, featuremask);
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return -EINVAL;
+		}
 	} else if (adev->powerplay.pp_funcs->set_ppfeature_status) {
 		ret = amdgpu_dpm_set_ppfeature_status(adev, featuremask);
-		if (ret)
+		if (ret) {
+			pm_runtime_mark_last_busy(ddev->dev);
+			pm_runtime_put_autosuspend(ddev->dev);
 			return -EINVAL;
+		}
 	}
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	return count;
 }
@@ -795,13 +918,27 @@ static ssize_t amdgpu_get_pp_feature_status(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
 
-	if (is_support_sw_smu(adev)) {
-		return smu_sys_get_pp_feature_mask(&adev->smu, buf);
-	} else if (adev->powerplay.pp_funcs->get_ppfeature_status)
-		return amdgpu_dpm_get_ppfeature_status(adev, buf);
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
+	if (is_support_sw_smu(adev))
+		size = smu_sys_get_pp_feature_mask(&adev->smu, buf);
+	else if (adev->powerplay.pp_funcs->get_ppfeature_status)
+		size = amdgpu_dpm_get_ppfeature_status(adev, buf);
+	else
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
-	return snprintf(buf, PAGE_SIZE, "\n");
+	return size;
 }
 
 /**
@@ -840,17 +977,27 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
 
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev) &&
-	    adev->virt.ops->get_pp_clk)
-		return adev->virt.ops->get_pp_clk(adev, PP_SCLK, buf);
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_SCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_SCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_SCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_SCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 /*
@@ -899,18 +1046,25 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
-	if (amdgpu_sriov_vf(adev))
-		return 0;
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_SCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (ret)
 		return -EINVAL;
 
@@ -923,17 +1077,27 @@ static ssize_t amdgpu_get_pp_dpm_mclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
 
-	if (amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev) &&
-	    adev->virt.ops->get_pp_clk)
-		return adev->virt.ops->get_pp_clk(adev, PP_MCLK, buf);
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_MCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_MCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_MCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_MCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
@@ -943,21 +1107,28 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
-	int ret;
 	uint32_t mask = 0;
+	int ret;
 
-	if (amdgpu_sriov_vf(adev))
-		return 0;
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+			return -EINVAL;
 
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_MCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (ret)
 		return -EINVAL;
 
@@ -970,13 +1141,27 @@ static ssize_t amdgpu_get_pp_dpm_socclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_SOCCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_SOCCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_SOCCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_SOCCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
@@ -989,14 +1174,26 @@ static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_SOCCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SOCCLK, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1010,13 +1207,27 @@ static ssize_t amdgpu_get_pp_dpm_fclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_FCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_FCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_FCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_FCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
@@ -1029,14 +1240,26 @@ static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_FCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_FCLK, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1050,13 +1273,27 @@ static ssize_t amdgpu_get_pp_dpm_dcefclk(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_DCEFCLK, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_DCEFCLK, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_DCEFCLK, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_DCEFCLK, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
@@ -1069,14 +1306,26 @@ static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_DCEFCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_DCEFCLK, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1090,13 +1339,27 @@ static ssize_t amdgpu_get_pp_dpm_pcie(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_print_clk_levels(&adev->smu, SMU_PCIE, buf);
+		size = smu_print_clk_levels(&adev->smu, SMU_PCIE, buf);
 	else if (adev->powerplay.pp_funcs->print_clock_levels)
-		return amdgpu_dpm_print_clock_levels(adev, PP_PCIE, buf);
+		size = amdgpu_dpm_print_clock_levels(adev, PP_PCIE, buf);
 	else
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
@@ -1109,14 +1372,26 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	int ret;
 	uint32_t mask = 0;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
+
 	ret = amdgpu_read_mask(buf, count, &mask);
 	if (ret)
 		return ret;
 
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_force_clk_levels(&adev->smu, SMU_PCIE, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
+	else
+		ret = 0;
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
 	if (ret)
 		return -EINVAL;
@@ -1131,12 +1406,23 @@ static ssize_t amdgpu_get_pp_sclk_od(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	uint32_t value = 0;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		value = smu_get_od_percentage(&(adev->smu), SMU_OD_SCLK);
 	else if (adev->powerplay.pp_funcs->get_sclk_od)
 		value = amdgpu_dpm_get_sclk_od(adev);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", value);
 }
 
@@ -1150,12 +1436,17 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
 	int ret;
 	long int value;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	ret = kstrtol(buf, 0, &value);
 
-	if (ret) {
-		count = -EINVAL;
-		goto fail;
-	}
+	if (ret)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		value = smu_set_od_percentage(&(adev->smu), SMU_OD_SCLK, (uint32_t)value);
@@ -1171,7 +1462,9 @@ static ssize_t amdgpu_set_pp_sclk_od(struct device *dev,
 		}
 	}
 
-fail:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -1182,12 +1475,23 @@ static ssize_t amdgpu_get_pp_mclk_od(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	uint32_t value = 0;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
 		value = smu_get_od_percentage(&(adev->smu), SMU_OD_MCLK);
 	else if (adev->powerplay.pp_funcs->get_mclk_od)
 		value = amdgpu_dpm_get_mclk_od(adev);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", value);
 }
 
@@ -1201,12 +1505,17 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
 	int ret;
 	long int value;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	ret = kstrtol(buf, 0, &value);
 
-	if (ret) {
-		count = -EINVAL;
-		goto fail;
-	}
+	if (ret)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		value = smu_set_od_percentage(&(adev->smu), SMU_OD_MCLK, (uint32_t)value);
@@ -1222,7 +1531,9 @@ static ssize_t amdgpu_set_pp_mclk_od(struct device *dev,
 		}
 	}
 
-fail:
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return count;
 }
 
@@ -1252,13 +1563,27 @@ static ssize_t amdgpu_get_pp_power_profile_mode(struct device *dev,
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
+	ssize_t size;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev))
-		return smu_get_power_profile_mode(&adev->smu, buf);
+		size = smu_get_power_profile_mode(&adev->smu, buf);
 	else if (adev->powerplay.pp_funcs->get_power_profile_mode)
-		return amdgpu_dpm_get_power_profile_mode(adev, buf);
+		size = amdgpu_dpm_get_power_profile_mode(adev, buf);
+	else
+		size = snprintf(buf, PAGE_SIZE, "\n");
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
 
-	return snprintf(buf, PAGE_SIZE, "\n");
+	return size;
 }
 
 
@@ -1283,7 +1608,10 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 	tmp[1] = '\0';
 	ret = kstrtol(tmp, 0, &profile_mode);
 	if (ret)
-		goto fail;
+		return -EINVAL;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return -EINVAL;
 
 	if (profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
 		if (count < 2 || count > 127)
@@ -1295,23 +1623,30 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 		while (tmp_str[0]) {
 			sub_str = strsep(&tmp_str, delimiter);
 			ret = kstrtol(sub_str, 0, &parameter[parameter_size]);
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
+			if (ret)
+				return -EINVAL;
 			parameter_size++;
 			while (isspace(*tmp_str))
 				tmp_str++;
 		}
 	}
 	parameter[parameter_size] = profile_mode;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev))
 		ret = smu_set_power_profile_mode(&adev->smu, parameter, parameter_size, true);
 	else if (adev->powerplay.pp_funcs->set_power_profile_mode)
 		ret = amdgpu_dpm_set_power_profile_mode(adev, parameter, parameter_size);
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (!ret)
 		return count;
-fail:
+
 	return -EINVAL;
 }
 
@@ -1331,10 +1666,20 @@ static ssize_t amdgpu_get_busy_percent(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int r, value, size = sizeof(value);
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	r = pm_runtime_get_sync(ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* read the IP busy sensor */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_LOAD,
 				   (void *)&value, &size);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1357,10 +1702,20 @@ static ssize_t amdgpu_get_memory_busy_percent(struct device *dev,
 	struct amdgpu_device *adev = ddev->dev_private;
 	int r, value, size = sizeof(value);
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	r = pm_runtime_get_sync(ddev->dev);
+	if (r < 0)
+		return r;
+
 	/* read the IP busy sensor */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MEM_LOAD,
 				   (void *)&value, &size);
 
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1386,8 +1741,20 @@ static ssize_t amdgpu_get_pcie_bw(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	uint64_t count0, count1;
+	int ret;
+
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	ret = pm_runtime_get_sync(ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	amdgpu_asic_get_pcie_usage(adev, &count0, &count1);
+
+	pm_runtime_mark_last_busy(ddev->dev);
+	pm_runtime_put_autosuspend(ddev->dev);
+
 	return snprintf(buf, PAGE_SIZE,	"%llu %llu %i\n",
 			count0, count1, pcie_get_mps(adev->pdev));
 }
@@ -1409,6 +1776,9 @@ static ssize_t amdgpu_get_unique_id(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
 	if (adev->unique_id)
 		return snprintf(buf, PAGE_SIZE, "%016llx\n", adev->unique_id);
 
@@ -1472,42 +1842,43 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	int channel = to_sensor_dev_attr(attr)->index;
 	int r, temp = 0, size = sizeof(temp);
 
-	/* Can't get temperature when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
-
 	if (channel >= PP_TEMP_MAX)
 		return -EINVAL;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	switch (channel) {
 	case PP_TEMP_JUNCTION:
 		/* get current junction temperature */
 		r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
 					   (void *)&temp, &size);
-		if (r)
-			return r;
 		break;
 	case PP_TEMP_EDGE:
 		/* get current edge temperature */
 		r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_EDGE_TEMP,
 					   (void *)&temp, &size);
-		if (r)
-			return r;
 		break;
 	case PP_TEMP_MEM:
 		/* get current memory temperature */
 		r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MEM_TEMP,
 					   (void *)&temp, &size);
-		if (r)
-			return r;
+		break;
+	default:
+		r = -EINVAL;
 		break;
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (r)
+		return r;
+
 	return snprintf(buf, PAGE_SIZE, "%d\n", temp);
 }
 
@@ -1603,15 +1974,27 @@ static ssize_t amdgpu_hwmon_get_pwm1_enable(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	u32 pwm_mode = 0;
+	int ret;
+
+	ret = pm_runtime_get_sync(adev->ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	} else {
-		if (!adev->powerplay.pp_funcs->get_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->get_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return sprintf(buf, "%i\n", pwm_mode);
 }
 
@@ -1621,27 +2004,32 @@ static ssize_t amdgpu_hwmon_set_pwm1_enable(struct device *dev,
 					    size_t count)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	int err;
+	int err, ret;
 	int value;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
-
 	err = kstrtoint(buf, 10, &value);
 	if (err)
 		return err;
 
+	ret = pm_runtime_get_sync(adev->ddev->dev);
+	if (ret < 0)
+		return ret;
+
 	if (is_support_sw_smu(adev)) {
 		smu_set_fan_control_mode(&adev->smu, value);
 	} else {
-		if (!adev->powerplay.pp_funcs->set_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->set_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 
 		amdgpu_dpm_set_fan_control_mode(adev, value);
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return count;
 }
 
@@ -1668,34 +2056,43 @@ static ssize_t amdgpu_hwmon_set_pwm1(struct device *dev,
 	u32 value;
 	u32 pwm_mode;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
 	if (is_support_sw_smu(adev))
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	else
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
+
 	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
 		pr_info("manual fan speed control should be enabled first\n");
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return -EINVAL;
 	}
 
 	err = kstrtou32(buf, 10, &value);
-	if (err)
+	if (err) {
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return err;
+	}
 
 	value = (value * 100) / 255;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_set_fan_speed_percent(&adev->smu, value);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->set_fan_speed_percent) {
+	else if (adev->powerplay.pp_funcs->set_fan_speed_percent)
 		err = amdgpu_dpm_set_fan_speed_percent(adev, value);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return count;
 }
@@ -1708,20 +2105,22 @@ static ssize_t amdgpu_hwmon_get_pwm1(struct device *dev,
 	int err;
 	u32 speed = 0;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_get_fan_speed_percent(&adev->smu, &speed);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->get_fan_speed_percent) {
+	else if (adev->powerplay.pp_funcs->get_fan_speed_percent)
 		err = amdgpu_dpm_get_fan_speed_percent(adev, &speed);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	speed = (speed * 255) / 100;
 
@@ -1736,20 +2135,22 @@ static ssize_t amdgpu_hwmon_get_fan1_input(struct device *dev,
 	int err;
 	u32 speed = 0;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_get_fan_speed_rpm(&adev->smu, &speed);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
+	else if (adev->powerplay.pp_funcs->get_fan_speed_rpm)
 		err = amdgpu_dpm_get_fan_speed_rpm(adev, &speed);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return sprintf(buf, "%i\n", speed);
 }
@@ -1763,8 +2164,16 @@ static ssize_t amdgpu_hwmon_get_fan1_min(struct device *dev,
 	u32 size = sizeof(min_rpm);
 	int r;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MIN_FAN_RPM,
 				   (void *)&min_rpm, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1780,8 +2189,16 @@ static ssize_t amdgpu_hwmon_get_fan1_max(struct device *dev,
 	u32 size = sizeof(max_rpm);
 	int r;
 
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
+
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_MAX_FAN_RPM,
 				   (void *)&max_rpm, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1796,20 +2213,22 @@ static ssize_t amdgpu_hwmon_get_fan1_target(struct device *dev,
 	int err;
 	u32 rpm = 0;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_get_fan_speed_rpm(&adev->smu, &rpm);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
+	else if (adev->powerplay.pp_funcs->get_fan_speed_rpm)
 		err = amdgpu_dpm_get_fan_speed_rpm(adev, &rpm);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return sprintf(buf, "%i\n", rpm);
 }
@@ -1823,32 +2242,40 @@ static ssize_t amdgpu_hwmon_set_fan1_target(struct device *dev,
 	u32 value;
 	u32 pwm_mode;
 
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
 	if (is_support_sw_smu(adev))
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	else
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 
-	if (pwm_mode != AMD_FAN_CTRL_MANUAL)
+	if (pwm_mode != AMD_FAN_CTRL_MANUAL) {
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return -ENODATA;
-
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	}
 
 	err = kstrtou32(buf, 10, &value);
-	if (err)
+	if (err) {
+		pm_runtime_mark_last_busy(adev->ddev->dev);
+		pm_runtime_put_autosuspend(adev->ddev->dev);
 		return err;
+	}
 
-	if (is_support_sw_smu(adev)) {
+	if (is_support_sw_smu(adev))
 		err = smu_set_fan_speed_rpm(&adev->smu, value);
-		if (err)
-			return err;
-	} else if (adev->powerplay.pp_funcs->set_fan_speed_rpm) {
+	else if (adev->powerplay.pp_funcs->set_fan_speed_rpm)
 		err = amdgpu_dpm_set_fan_speed_rpm(adev, value);
-		if (err)
-			return err;
-	}
+	else
+		err = -EINVAL;
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	if (err)
+		return err;
 
 	return count;
 }
@@ -1859,15 +2286,27 @@ static ssize_t amdgpu_hwmon_get_fan1_enable(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	u32 pwm_mode = 0;
+	int ret;
+
+	ret = pm_runtime_get_sync(adev->ddev->dev);
+	if (ret < 0)
+		return ret;
 
 	if (is_support_sw_smu(adev)) {
 		pwm_mode = smu_get_fan_control_mode(&adev->smu);
 	} else {
-		if (!adev->powerplay.pp_funcs->get_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->get_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 
 		pwm_mode = amdgpu_dpm_get_fan_control_mode(adev);
 	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return sprintf(buf, "%i\n", pwm_mode == AMD_FAN_CTRL_AUTO ? 0 : 1);
 }
 
@@ -1881,12 +2320,6 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 	int value;
 	u32 pwm_mode;
 
-	/* Can't adjust fan when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (adev->ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
-
-
 	err = kstrtoint(buf, 10, &value);
 	if (err)
 		return err;
@@ -1898,14 +2331,24 @@ static ssize_t amdgpu_hwmon_set_fan1_enable(struct device *dev,
 	else
 		return -EINVAL;
 
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
 	if (is_support_sw_smu(adev)) {
 		smu_set_fan_control_mode(&adev->smu, pwm_mode);
 	} else {
-		if (!adev->powerplay.pp_funcs->set_fan_control_mode)
+		if (!adev->powerplay.pp_funcs->set_fan_control_mode) {
+			pm_runtime_mark_last_busy(adev->ddev->dev);
+			pm_runtime_put_autosuspend(adev->ddev->dev);
 			return -EINVAL;
+		}
 		amdgpu_dpm_set_fan_control_mode(adev, pwm_mode);
 	}
 
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	return count;
 }
 
@@ -1914,18 +2357,20 @@ static ssize_t amdgpu_hwmon_show_vddgfx(struct device *dev,
 					char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	u32 vddgfx;
 	int r, size = sizeof(vddgfx);
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the voltage */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDGFX,
 				   (void *)&vddgfx, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1944,7 +2389,6 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 				       char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	u32 vddnb;
 	int r, size = sizeof(vddnb);
 
@@ -1952,14 +2396,17 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 	if  (!(adev->flags & AMD_IS_APU))
 		return -EINVAL;
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the voltage */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VDDNB,
 				   (void *)&vddnb, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -1978,19 +2425,21 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev,
 					   char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	u32 query = 0;
 	int r, size = sizeof(u32);
 	unsigned uw;
 
-	/* Can't get power when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the voltage */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_POWER,
 				   (void *)&query, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -2013,16 +2462,27 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	uint32_t limit = 0;
+	ssize_t size;
+	int r;
+
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	if (is_support_sw_smu(adev)) {
 		smu_get_power_limit(&adev->smu, &limit, true, true);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, true);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else {
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	return size;
 }
 
 static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
@@ -2031,16 +2491,27 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	uint32_t limit = 0;
+	ssize_t size;
+	int r;
+
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	if (is_support_sw_smu(adev)) {
 		smu_get_power_limit(&adev->smu, &limit, false,  true);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, false);
-		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
+		size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else {
-		return snprintf(buf, PAGE_SIZE, "\n");
+		size = snprintf(buf, PAGE_SIZE, "\n");
 	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
+	return size;
 }
 
 
@@ -2053,19 +2524,29 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
 	int err;
 	u32 value;
 
+	if (amdgpu_sriov_vf(adev))
+		return -EINVAL;
+
 	err = kstrtou32(buf, 10, &value);
 	if (err)
 		return err;
 
 	value = value / 1000000; /* convert to Watt */
 
-	if (is_support_sw_smu(adev)) {
+
+	err = pm_runtime_get_sync(adev->ddev->dev);
+	if (err < 0)
+		return err;
+
+	if (is_support_sw_smu(adev))
 		err = smu_set_power_limit(&adev->smu, value);
-	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->set_power_limit) {
+	else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->set_power_limit)
 		err = adev->powerplay.pp_funcs->set_power_limit(adev->powerplay.pp_handle, value);
-	} else {
+	else
 		err = -EINVAL;
-	}
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
 
 	if (err)
 		return err;
@@ -2078,18 +2559,20 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	uint32_t sclk;
 	int r, size = sizeof(sclk);
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the sclk */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_SCLK,
 				   (void *)&sclk, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -2108,18 +2591,20 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev,
 				      char *buf)
 {
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
-	struct drm_device *ddev = adev->ddev;
 	uint32_t mclk;
 	int r, size = sizeof(mclk);
 
-	/* Can't get voltage when the card is off */
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
-		return -EINVAL;
+	r = pm_runtime_get_sync(adev->ddev->dev);
+	if (r < 0)
+		return r;
 
 	/* get the sclk */
 	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GFX_MCLK,
 				   (void *)&mclk, &size);
+
+	pm_runtime_mark_last_busy(adev->ddev->dev);
+	pm_runtime_put_autosuspend(adev->ddev->dev);
+
 	if (r)
 		return r;
 
@@ -2299,6 +2784,23 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj,
 	struct amdgpu_device *adev = dev_get_drvdata(dev);
 	umode_t effective_mode = attr->mode;
 
+	/* under multi-vf mode, the hwmon attributes are all not supported */
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	/* there is no fan under pp one vf mode */
+	if (amdgpu_sriov_is_pp_one_vf(adev) &&
+	    (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
+	     attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
+	     attr == &sensor_dev_attr_pwm1_max.dev_attr.attr ||
+	     attr == &sensor_dev_attr_pwm1_min.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_input.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_min.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_max.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_target.dev_attr.attr ||
+	     attr == &sensor_dev_attr_fan1_enable.dev_attr.attr))
+		return 0;
+
 	/* Skip fan attributes if fan is not present */
 	if (adev->pm.no_fan && (attr == &sensor_dev_attr_pwm1.dev_attr.attr ||
 	    attr == &sensor_dev_attr_pwm1_enable.dev_attr.attr ||
@@ -2666,17 +3168,12 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 {
 	int ret = 0;
-	if (is_support_sw_smu(adev)) {
-	    ret = smu_dpm_set_power_gate(&adev->smu, AMD_IP_BLOCK_TYPE_UVD, enable);
-	    if (ret)
-		DRM_ERROR("[SW SMU]: dpm enable uvd failed, state = %s, ret = %d. \n",
-			  enable ? "true" : "false", ret);
-	} else if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
-		/* enable/disable UVD */
-		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
-		mutex_unlock(&adev->pm.mutex);
-	}
+
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s uvd failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
+
 	/* enable/disable Low Memory PState for UVD (4k videos) */
 	if (adev->asic_type == CHIP_STONEY &&
 		adev->uvd.decode_image_width >= WIDTH_4K) {
@@ -2693,17 +3190,11 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
 {
 	int ret = 0;
-	if (is_support_sw_smu(adev)) {
-	    ret = smu_dpm_set_power_gate(&adev->smu, AMD_IP_BLOCK_TYPE_VCE, enable);
-	    if (ret)
-		DRM_ERROR("[SW SMU]: dpm enable vce failed, state = %s, ret = %d. \n",
-			  enable ? "true" : "false", ret);
-	} else if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
-		/* enable/disable VCE */
-		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
-		mutex_unlock(&adev->pm.mutex);
-	}
+
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s vce failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
 }
 
 void amdgpu_pm_print_power_states(struct amdgpu_device *adev)
@@ -2718,42 +3209,14 @@ void amdgpu_pm_print_power_states(struct amdgpu_device *adev)
 
 }
 
-int amdgpu_pm_virt_sysfs_init(struct amdgpu_device *adev)
+void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable)
 {
 	int ret = 0;
 
-	if (!(amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev)))
-		return ret;
-
-	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk);
-	if (ret) {
-		DRM_ERROR("failed to create device file pp_dpm_sclk\n");
-		return ret;
-	}
-
-	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk);
-	if (ret) {
-		DRM_ERROR("failed to create device file pp_dpm_mclk\n");
-		return ret;
-	}
-
-	ret = device_create_file(adev->dev, &dev_attr_power_dpm_force_performance_level);
-	if (ret) {
-		DRM_ERROR("failed to create device file for dpm state\n");
-		return ret;
-	}
-
-	return ret;
-}
-
-void amdgpu_pm_virt_sysfs_fini(struct amdgpu_device *adev)
-{
-	if (!(amdgpu_sriov_vf(adev) && amdgim_is_hwperf(adev)))
-		return;
-
-	device_remove_file(adev->dev, &dev_attr_power_dpm_force_performance_level);
-	device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk);
-	device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk);
+	ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_JPEG, !enable);
+	if (ret)
+		DRM_ERROR("Dpm %s jpeg failed, ret = %d. \n",
+			  enable ? "enable" : "disable", ret);
 }
 
 int amdgpu_pm_load_smu_firmware(struct amdgpu_device *adev, uint32_t *smu_version)
@@ -3163,8 +3626,12 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct drm_device *ddev = adev->ddev;
 	u32 flags = 0;
+	int r;
+
+	r = pm_runtime_get_sync(dev->dev);
+	if (r < 0)
+		return r;
 
 	amdgpu_device_ip_get_clockgating_state(adev, &flags);
 	seq_printf(m, "Clock Gating Flags Mask: 0x%x\n", flags);
@@ -3173,23 +3640,28 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data)
 
 	if (!adev->pm.dpm_enabled) {
 		seq_printf(m, "dpm not enabled\n");
+		pm_runtime_mark_last_busy(dev->dev);
+		pm_runtime_put_autosuspend(dev->dev);
 		return 0;
 	}
-	if  ((adev->flags & AMD_IS_PX) &&
-	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
-		seq_printf(m, "PX asic powered off\n");
-	} else if (!is_support_sw_smu(adev) && adev->powerplay.pp_funcs->debugfs_print_current_performance_level) {
+
+	if (!is_support_sw_smu(adev) &&
+	    adev->powerplay.pp_funcs->debugfs_print_current_performance_level) {
 		mutex_lock(&adev->pm.mutex);
 		if (adev->powerplay.pp_funcs->debugfs_print_current_performance_level)
 			adev->powerplay.pp_funcs->debugfs_print_current_performance_level(adev, m);
 		else
 			seq_printf(m, "Debugfs support not implemented for this asic\n");
 		mutex_unlock(&adev->pm.mutex);
+		r = 0;
 	} else {
-		return amdgpu_debugfs_pm_info_pp(m, adev);
+		r = amdgpu_debugfs_pm_info_pp(m, adev);
 	}
 
-	return 0;
+	pm_runtime_mark_last_busy(dev->dev);
+	pm_runtime_put_autosuspend(dev->dev);
+
+	return r;
 }
 
 static const struct drm_info_list amdgpu_pm_info_list[] = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
index ef31448ee8d8..3da1da277805 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.h
@@ -41,5 +41,6 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev);
 void amdgpu_dpm_thermal_work_handler(struct work_struct *work);
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable);
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable);
+void amdgpu_dpm_enable_jpeg(struct amdgpu_device *adev, bool enable);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
index 0e6dba9f60f0..07914e34bc25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
@@ -74,9 +74,9 @@ static void amdgpu_perf_start(struct perf_event *event, int flags)
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
 		if (!(flags & PERF_EF_RELOAD))
-			pe->adev->df_funcs->pmc_start(pe->adev, hwc->conf, 1);
+			pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
 
-		pe->adev->df_funcs->pmc_start(pe->adev, hwc->conf, 0);
+		pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 0);
 		break;
 	default:
 		break;
@@ -101,13 +101,13 @@ static void amdgpu_perf_read(struct perf_event *event)
 
 		switch (pe->pmu_perf_type) {
 		case PERF_TYPE_AMDGPU_DF:
-			pe->adev->df_funcs->pmc_get_count(pe->adev, hwc->conf,
+			pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->conf,
 							  &count);
 			break;
 		default:
 			count = 0;
 			break;
-		};
+		}
 	} while (local64_cmpxchg(&hwc->prev_count, prev, count) != prev);
 
 	local64_add(count - prev, &event->count);
@@ -126,11 +126,11 @@ static void amdgpu_perf_stop(struct perf_event *event, int flags)
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		pe->adev->df_funcs->pmc_stop(pe->adev, hwc->conf, 0);
+		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 0);
 		break;
 	default:
 		break;
-	};
+	}
 
 	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 	hwc->state |= PERF_HES_STOPPED;
@@ -156,11 +156,11 @@ static int amdgpu_perf_add(struct perf_event *event, int flags)
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		retval = pe->adev->df_funcs->pmc_start(pe->adev, hwc->conf, 1);
+		retval = pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
 		break;
 	default:
 		return 0;
-	};
+	}
 
 	if (retval)
 		return retval;
@@ -184,11 +184,11 @@ static void amdgpu_perf_del(struct perf_event *event, int flags)
 
 	switch (pe->pmu_perf_type) {
 	case PERF_TYPE_AMDGPU_DF:
-		pe->adev->df_funcs->pmc_stop(pe->adev, hwc->conf, 1);
+		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 1);
 		break;
 	default:
 		break;
-	};
+	}
 
 	perf_event_update_userpage(event);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index e1b8d8daeafc..3a1570dafe34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -158,7 +158,7 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	memcpy(psp->cmd_buf_mem, cmd, sizeof(struct psp_gfx_cmd_resp));
 
 	index = atomic_inc_return(&psp->fence_value);
-	ret = psp_cmd_submit(psp, psp->cmd_buf_mc_addr, fence_mc_addr, index);
+	ret = psp_ring_cmd_submit(psp, psp->cmd_buf_mc_addr, fence_mc_addr, index);
 	if (ret) {
 		atomic_dec(&psp->fence_value);
 		mutex_unlock(&psp->mutex);
@@ -191,9 +191,9 @@ psp_cmd_submit_buf(struct psp_context *psp,
 		if (ucode)
 			DRM_WARN("failed to load ucode id (%d) ",
 				  ucode->ucode_id);
-		DRM_DEBUG_DRIVER("psp command (0x%X) failed and response status is (0x%X)\n",
+		DRM_WARN("psp command (0x%X) failed and response status is (0x%X)\n",
 			 psp->cmd_buf_mem->cmd_id,
-			 psp->cmd_buf_mem->resp.status & GFX_CMD_STATUS_MASK);
+			 psp->cmd_buf_mem->resp.status);
 		if (!timeout) {
 			mutex_unlock(&psp->mutex);
 			return -EINVAL;
@@ -318,35 +318,17 @@ static int psp_tmr_load(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_asd_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-				 uint64_t asd_mc, uint64_t asd_mc_shared,
-				 uint32_t size, uint32_t shared_size)
+static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				uint64_t asd_mc, uint32_t size)
 {
 	cmd->cmd_id = GFX_CMD_ID_LOAD_ASD;
 	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(asd_mc);
 	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(asd_mc);
 	cmd->cmd.cmd_load_ta.app_len = size;
 
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(asd_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(asd_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
-static int psp_asd_init(struct psp_context *psp)
-{
-	int ret;
-
-	/*
-	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
-	 * physical) for shared ASD <-> Driver
-	 */
-	ret = amdgpu_bo_create_kernel(psp->adev, PSP_ASD_SHARED_MEM_SIZE,
-				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				      &psp->asd_shared_bo,
-				      &psp->asd_shared_mc_addr,
-				      &psp->asd_shared_buf);
-
-	return ret;
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = 0;
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = 0;
+	cmd->cmd.cmd_load_ta.cmd_buf_len = 0;
 }
 
 static int psp_asd_load(struct psp_context *psp)
@@ -368,11 +350,49 @@ static int psp_asd_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->asd_start_addr, psp->asd_ucode_size);
 
-	psp_prep_asd_cmd_buf(cmd, psp->fw_pri_mc_addr, psp->asd_shared_mc_addr,
-			     psp->asd_ucode_size, PSP_ASD_SHARED_MEM_SIZE);
+	psp_prep_asd_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
+				  psp->asd_ucode_size);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd,
+				 psp->fence_buf_mc_addr);
+	if (!ret) {
+		psp->asd_context.asd_initialized = true;
+		psp->asd_context.session_id = cmd->resp.session_id;
+	}
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static void psp_prep_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				       uint32_t session_id)
+{
+	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
+	cmd->cmd.cmd_unload_ta.session_id = session_id;
+}
+
+static int psp_asd_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->asd_context.asd_initialized)
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_ta_unload_cmd_buf(cmd, psp->asd_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
+	if (!ret)
+		psp->asd_context.asd_initialized = false;
 
 	kfree(cmd);
 
@@ -407,18 +427,20 @@ int psp_reg_program(struct psp_context *psp, enum psp_reg_prog_id reg,
 	return ret;
 }
 
-static void psp_prep_xgmi_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					  uint64_t xgmi_ta_mc, uint64_t xgmi_mc_shared,
-					  uint32_t xgmi_ta_size, uint32_t shared_size)
+static void psp_prep_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				     uint64_t ta_bin_mc,
+				     uint32_t ta_bin_size,
+				     uint64_t ta_shared_mc,
+				     uint32_t ta_shared_size)
 {
-        cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-        cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(xgmi_ta_mc);
-        cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(xgmi_ta_mc);
-        cmd->cmd.cmd_load_ta.app_len = xgmi_ta_size;
+	cmd->cmd_id 				= GFX_CMD_ID_LOAD_TA;
+	cmd->cmd.cmd_load_ta.app_phy_addr_lo 	= lower_32_bits(ta_bin_mc);
+	cmd->cmd.cmd_load_ta.app_phy_addr_hi 	= upper_32_bits(ta_bin_mc);
+	cmd->cmd.cmd_load_ta.app_len 		= ta_bin_size;
 
-        cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(xgmi_mc_shared);
-        cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(xgmi_mc_shared);
-        cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(ta_shared_mc);
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(ta_shared_mc);
+	cmd->cmd.cmd_load_ta.cmd_buf_len 	 = ta_shared_size;
 }
 
 static int psp_xgmi_init_shared_buf(struct psp_context *psp)
@@ -438,6 +460,36 @@ static int psp_xgmi_init_shared_buf(struct psp_context *psp)
 	return ret;
 }
 
+static void psp_prep_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+				       uint32_t ta_cmd_id,
+				       uint32_t session_id)
+{
+	cmd->cmd_id 				= GFX_CMD_ID_INVOKE_CMD;
+	cmd->cmd.cmd_invoke_cmd.session_id 	= session_id;
+	cmd->cmd.cmd_invoke_cmd.ta_cmd_id 	= ta_cmd_id;
+}
+
+int psp_ta_invoke(struct psp_context *psp,
+		  uint32_t ta_cmd_id,
+		  uint32_t session_id)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_ta_invoke_cmd_buf(cmd, ta_cmd_id, session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd,
+				 psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
 static int psp_xgmi_load(struct psp_context *psp)
 {
 	int ret;
@@ -446,8 +498,6 @@ static int psp_xgmi_load(struct psp_context *psp)
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
 
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!cmd)
@@ -456,9 +506,11 @@ static int psp_xgmi_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_xgmi_start_addr, psp->ta_xgmi_ucode_size);
 
-	psp_prep_xgmi_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				      psp->xgmi_context.xgmi_shared_mc_addr,
-				      psp->ta_xgmi_ucode_size, PSP_XGMI_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_xgmi_ucode_size,
+				 psp->xgmi_context.xgmi_shared_mc_addr,
+				 PSP_XGMI_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
@@ -473,29 +525,25 @@ static int psp_xgmi_load(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_xgmi_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t xgmi_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
-	cmd->cmd.cmd_unload_ta.session_id = xgmi_session_id;
-}
-
 static int psp_xgmi_unload(struct psp_context *psp)
 {
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
+	struct amdgpu_device *adev = psp->adev;
+
+	/* XGMI TA unload currently is not supported on Arcturus */
+	if (adev->asic_type == CHIP_ARCTURUS)
+		return 0;
 
 	/*
 	 * TODO: bypass the unloading in sriov for now
 	 */
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
 
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;
 
-	psp_prep_xgmi_ta_unload_cmd_buf(cmd, psp->xgmi_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->xgmi_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
@@ -505,40 +553,9 @@ static int psp_xgmi_unload(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_xgmi_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t ta_cmd_id,
-					    uint32_t xgmi_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = xgmi_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
-	/*
-	 * TODO: bypass the loading in sriov for now
-	*/
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
-
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_xgmi_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-					psp->xgmi_context.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd,
-				 psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-        return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->xgmi_context.session_id);
 }
 
 static int psp_xgmi_terminate(struct psp_context *psp)
@@ -594,20 +611,6 @@ static int psp_xgmi_initialize(struct psp_context *psp)
 }
 
 // ras begin
-static void psp_prep_ras_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-		uint64_t ras_ta_mc, uint64_t ras_mc_shared,
-		uint32_t ras_ta_size, uint32_t shared_size)
-{
-	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(ras_ta_mc);
-	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(ras_ta_mc);
-	cmd->cmd.cmd_load_ta.app_len = ras_ta_size;
-
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(ras_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(ras_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
 static int psp_ras_init_shared_buf(struct psp_context *psp)
 {
 	int ret;
@@ -643,15 +646,17 @@ static int psp_ras_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_ras_start_addr, psp->ta_ras_ucode_size);
 
-	psp_prep_ras_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-			psp->ras.ras_shared_mc_addr,
-			psp->ta_ras_ucode_size, PSP_RAS_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_ras_ucode_size,
+				 psp->ras.ras_shared_mc_addr,
+				 PSP_RAS_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->ras.ras_initialized = 1;
+		psp->ras.ras_initialized = true;
 		psp->ras.session_id = cmd->resp.session_id;
 	}
 
@@ -660,13 +665,6 @@ static int psp_ras_load(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_ras_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-						uint32_t ras_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
-	cmd->cmd.cmd_unload_ta.session_id = ras_session_id;
-}
-
 static int psp_ras_unload(struct psp_context *psp)
 {
 	int ret;
@@ -682,7 +680,7 @@ static int psp_ras_unload(struct psp_context *psp)
 	if (!cmd)
 		return -ENOMEM;
 
-	psp_prep_ras_ta_unload_cmd_buf(cmd, psp->ras.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->ras.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 			psp->fence_buf_mc_addr);
@@ -692,40 +690,15 @@ static int psp_ras_unload(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_ras_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-		uint32_t ta_cmd_id,
-		uint32_t ras_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = ras_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_ras_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-			psp->ras.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd,
-			psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-	return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->ras.session_id);
 }
 
 int psp_ras_enable_features(struct psp_context *psp,
@@ -771,7 +744,7 @@ static int psp_ras_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->ras.ras_initialized = 0;
+	psp->ras.ras_initialized = false;
 
 	/* free ras shared memory */
 	amdgpu_bo_free_kernel(&psp->ras.ras_shared_bo,
@@ -812,24 +785,6 @@ static int psp_ras_initialize(struct psp_context *psp)
 // ras end
 
 // HDCP start
-static void psp_prep_hdcp_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					  uint64_t hdcp_ta_mc,
-					  uint64_t hdcp_mc_shared,
-					  uint32_t hdcp_ta_size,
-					  uint32_t shared_size)
-{
-	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(hdcp_ta_mc);
-	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(hdcp_ta_mc);
-	cmd->cmd.cmd_load_ta.app_len = hdcp_ta_size;
-
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo =
-		lower_32_bits(hdcp_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi =
-		upper_32_bits(hdcp_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
 static int psp_hdcp_init_shared_buf(struct psp_context *psp)
 {
 	int ret;
@@ -866,15 +821,16 @@ static int psp_hdcp_load(struct psp_context *psp)
 	memcpy(psp->fw_pri_buf, psp->ta_hdcp_start_addr,
 	       psp->ta_hdcp_ucode_size);
 
-	psp_prep_hdcp_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				      psp->hdcp_context.hdcp_shared_mc_addr,
-				      psp->ta_hdcp_ucode_size,
-				      PSP_HDCP_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_hdcp_ucode_size,
+				 psp->hdcp_context.hdcp_shared_mc_addr,
+				 PSP_HDCP_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->hdcp_context.hdcp_initialized = 1;
+		psp->hdcp_context.hdcp_initialized = true;
 		psp->hdcp_context.session_id = cmd->resp.session_id;
 	}
 
@@ -910,12 +866,6 @@ static int psp_hdcp_initialize(struct psp_context *psp)
 
 	return 0;
 }
-static void psp_prep_hdcp_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t hdcp_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
-	cmd->cmd.cmd_unload_ta.session_id = hdcp_session_id;
-}
 
 static int psp_hdcp_unload(struct psp_context *psp)
 {
@@ -932,7 +882,7 @@ static int psp_hdcp_unload(struct psp_context *psp)
 	if (!cmd)
 		return -ENOMEM;
 
-	psp_prep_hdcp_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
+	psp_prep_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
@@ -941,39 +891,15 @@ static int psp_hdcp_unload(struct psp_context *psp)
 	return ret;
 }
 
-static void psp_prep_hdcp_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					    uint32_t ta_cmd_id,
-					    uint32_t hdcp_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = hdcp_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_hdcp_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-					psp->hdcp_context.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-	return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->hdcp_context.session_id);
 }
 
 static int psp_hdcp_terminate(struct psp_context *psp)
@@ -993,7 +919,7 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->hdcp_context.hdcp_initialized = 0;
+	psp->hdcp_context.hdcp_initialized = false;
 
 	/* free hdcp shared memory */
 	amdgpu_bo_free_kernel(&psp->hdcp_context.hdcp_shared_bo,
@@ -1005,22 +931,6 @@ static int psp_hdcp_terminate(struct psp_context *psp)
 // HDCP end
 
 // DTM start
-static void psp_prep_dtm_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					 uint64_t dtm_ta_mc,
-					 uint64_t dtm_mc_shared,
-					 uint32_t dtm_ta_size,
-					 uint32_t shared_size)
-{
-	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
-	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(dtm_ta_mc);
-	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(dtm_ta_mc);
-	cmd->cmd.cmd_load_ta.app_len = dtm_ta_size;
-
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(dtm_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(dtm_mc_shared);
-	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
-}
-
 static int psp_dtm_init_shared_buf(struct psp_context *psp)
 {
 	int ret;
@@ -1056,15 +966,16 @@ static int psp_dtm_load(struct psp_context *psp)
 	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
 	memcpy(psp->fw_pri_buf, psp->ta_dtm_start_addr, psp->ta_dtm_ucode_size);
 
-	psp_prep_dtm_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
-				     psp->dtm_context.dtm_shared_mc_addr,
-				     psp->ta_dtm_ucode_size,
-				     PSP_DTM_SHARED_MEM_SIZE);
+	psp_prep_ta_load_cmd_buf(cmd,
+				 psp->fw_pri_mc_addr,
+				 psp->ta_dtm_ucode_size,
+				 psp->dtm_context.dtm_shared_mc_addr,
+				 PSP_DTM_SHARED_MEM_SIZE);
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
 
 	if (!ret) {
-		psp->dtm_context.dtm_initialized = 1;
+		psp->dtm_context.dtm_initialized = true;
 		psp->dtm_context.session_id = cmd->resp.session_id;
 	}
 
@@ -1102,39 +1013,15 @@ static int psp_dtm_initialize(struct psp_context *psp)
 	return 0;
 }
 
-static void psp_prep_dtm_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
-					   uint32_t ta_cmd_id,
-					   uint32_t dtm_session_id)
-{
-	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
-	cmd->cmd.cmd_invoke_cmd.session_id = dtm_session_id;
-	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
-	/* Note: cmd_invoke_cmd.buf is not used for now */
-}
-
 int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
 {
-	int ret;
-	struct psp_gfx_cmd_resp *cmd;
-
 	/*
 	 * TODO: bypass the loading in sriov for now
 	 */
 	if (amdgpu_sriov_vf(psp->adev))
 		return 0;
 
-	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	psp_prep_dtm_ta_invoke_cmd_buf(cmd, ta_cmd_id,
-				       psp->dtm_context.session_id);
-
-	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
-
-	kfree(cmd);
-
-	return ret;
+	return psp_ta_invoke(psp, ta_cmd_id, psp->dtm_context.session_id);
 }
 
 static int psp_dtm_terminate(struct psp_context *psp)
@@ -1154,7 +1041,7 @@ static int psp_dtm_terminate(struct psp_context *psp)
 	if (ret)
 		return ret;
 
-	psp->dtm_context.dtm_initialized = 0;
+	psp->dtm_context.dtm_initialized = false;
 
 	/* free hdcp shared memory */
 	amdgpu_bo_free_kernel(&psp->dtm_context.dtm_shared_bo,
@@ -1211,45 +1098,6 @@ static int psp_hw_start(struct psp_context *psp)
 		return ret;
 	}
 
-	ret = psp_asd_init(psp);
-	if (ret) {
-		DRM_ERROR("PSP asd init failed!\n");
-		return ret;
-	}
-
-	ret = psp_asd_load(psp);
-	if (ret) {
-		DRM_ERROR("PSP load asd failed!\n");
-		return ret;
-	}
-
-	if (adev->gmc.xgmi.num_physical_nodes > 1) {
-		ret = psp_xgmi_initialize(psp);
-		/* Warning the XGMI seesion initialize failure
-		 * Instead of stop driver initialization
-		 */
-		if (ret)
-			dev_err(psp->adev->dev,
-				"XGMI: Failed to initialize XGMI session\n");
-	}
-
-	if (psp->adev->psp.ta_fw) {
-		ret = psp_ras_initialize(psp);
-		if (ret)
-			dev_err(psp->adev->dev,
-					"RAS: Failed to initialize RAS\n");
-
-		ret = psp_hdcp_initialize(psp);
-		if (ret)
-			dev_err(psp->adev->dev,
-				"HDCP: Failed to initialize HDCP\n");
-
-		ret = psp_dtm_initialize(psp);
-		if (ret)
-			dev_err(psp->adev->dev,
-				"DTM: Failed to initialize DTM\n");
-	}
-
 	return 0;
 }
 
@@ -1329,6 +1177,9 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	case AMDGPU_UCODE_ID_VCN:
 		*type = GFX_FW_TYPE_VCN;
 		break;
+	case AMDGPU_UCODE_ID_VCN1:
+		*type = GFX_FW_TYPE_VCN1;
+		break;
 	case AMDGPU_UCODE_ID_DMCU_ERAM:
 		*type = GFX_FW_TYPE_DMCU_ERAM;
 		break;
@@ -1341,6 +1192,9 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
 	case AMDGPU_UCODE_ID_VCN1_RAM:
 		*type = GFX_FW_TYPE_VCN1_RAM;
 		break;
+	case AMDGPU_UCODE_ID_DMCUB:
+		*type = GFX_FW_TYPE_DMUB;
+		break;
 	case AMDGPU_UCODE_ID_MAXIMUM:
 	default:
 		return -EINVAL;
@@ -1470,7 +1324,8 @@ out:
                     || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G
 	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL
 	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM
-	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM))
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_SMC))
 			/*skip ucode loading in SRIOV VF */
 			continue;
 
@@ -1519,16 +1374,13 @@ static int psp_load_fw(struct amdgpu_device *adev)
 	if (!psp->cmd)
 		return -ENOMEM;
 
-	/* this fw pri bo is not used under SRIOV */
-	if (!amdgpu_sriov_vf(psp->adev)) {
-		ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
-					      AMDGPU_GEM_DOMAIN_GTT,
-					      &psp->fw_pri_bo,
-					      &psp->fw_pri_mc_addr,
-					      &psp->fw_pri_buf);
-		if (ret)
-			goto failed;
-	}
+	ret = amdgpu_bo_create_kernel(adev, PSP_1_MEG, PSP_1_MEG,
+					AMDGPU_GEM_DOMAIN_GTT,
+					&psp->fw_pri_bo,
+					&psp->fw_pri_mc_addr,
+					&psp->fw_pri_buf);
+	if (ret)
+		goto failed;
 
 	ret = amdgpu_bo_create_kernel(adev, PSP_FENCE_BUFFER_SIZE, PAGE_SIZE,
 					AMDGPU_GEM_DOMAIN_VRAM,
@@ -1562,6 +1414,39 @@ skip_memalloc:
 	if (ret)
 		goto failed;
 
+	ret = psp_asd_load(psp);
+	if (ret) {
+		DRM_ERROR("PSP load asd failed!\n");
+		return ret;
+	}
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		ret = psp_xgmi_initialize(psp);
+		/* Warning the XGMI seesion initialize failure
+		 * Instead of stop driver initialization
+		 */
+		if (ret)
+			dev_err(psp->adev->dev,
+				"XGMI: Failed to initialize XGMI session\n");
+	}
+
+	if (psp->adev->psp.ta_fw) {
+		ret = psp_ras_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+					"RAS: Failed to initialize RAS\n");
+
+		ret = psp_hdcp_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"HDCP: Failed to initialize HDCP\n");
+
+		ret = psp_dtm_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"DTM: Failed to initialize DTM\n");
+	}
+
 	return 0;
 
 failed:
@@ -1619,6 +1504,8 @@ static int psp_hw_fini(void *handle)
 		psp_hdcp_terminate(psp);
 	}
 
+	psp_asd_unload(psp);
+
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
 	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
@@ -1627,8 +1514,6 @@ static int psp_hw_fini(void *handle)
 			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
 	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
 			      &psp->fence_buf_mc_addr, &psp->fence_buf);
-	amdgpu_bo_free_kernel(&psp->asd_shared_bo, &psp->asd_shared_mc_addr,
-			      &psp->asd_shared_buf);
 	amdgpu_bo_free_kernel(&psp->cmd_buf_bo, &psp->cmd_buf_mc_addr,
 			      (void **)&psp->cmd_buf_mem);
 
@@ -1704,6 +1589,39 @@ static int psp_resume(void *handle)
 	if (ret)
 		goto failed;
 
+	ret = psp_asd_load(psp);
+	if (ret) {
+		DRM_ERROR("PSP load asd failed!\n");
+		goto failed;
+	}
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		ret = psp_xgmi_initialize(psp);
+		/* Warning the XGMI seesion initialize failure
+		 * Instead of stop driver initialization
+		 */
+		if (ret)
+			dev_err(psp->adev->dev,
+				"XGMI: Failed to initialize XGMI session\n");
+	}
+
+	if (psp->adev->psp.ta_fw) {
+		ret = psp_ras_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+					"RAS: Failed to initialize RAS\n");
+
+		ret = psp_hdcp_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"HDCP: Failed to initialize HDCP\n");
+
+		ret = psp_dtm_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"DTM: Failed to initialize DTM\n");
+	}
+
 	mutex_unlock(&adev->firmware.mutex);
 
 	return 0;
@@ -1758,6 +1676,56 @@ int psp_update_vcn_sram(struct amdgpu_device *adev, int inst_idx,
 	return psp_execute_np_fw_load(&adev->psp, &ucode);
 }
 
+int psp_ring_cmd_submit(struct psp_context *psp,
+			uint64_t cmd_buf_mc_addr,
+			uint64_t fence_mc_addr,
+			int index)
+{
+	unsigned int psp_write_ptr_reg = 0;
+	struct psp_gfx_rb_frame *write_frame;
+	struct psp_ring *ring = &psp->km_ring;
+	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
+	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
+		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
+	struct amdgpu_device *adev = psp->adev;
+	uint32_t ring_size_dw = ring->ring_size / 4;
+	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
+
+	/* KM (GPCOM) prepare write pointer */
+	psp_write_ptr_reg = psp_ring_get_wptr(psp);
+
+	/* Update KM RB frame pointer to new frame */
+	/* write_frame ptr increments by size of rb_frame in bytes */
+	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
+	if ((psp_write_ptr_reg % ring_size_dw) == 0)
+		write_frame = ring_buffer_start;
+	else
+		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
+	/* Check invalid write_frame ptr address */
+	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
+		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
+			  ring_buffer_start, ring_buffer_end, write_frame);
+		DRM_ERROR("write_frame is pointing to address out of bounds\n");
+		return -EINVAL;
+	}
+
+	/* Initialize KM RB frame */
+	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
+
+	/* Update KM RB frame */
+	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
+	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
+	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
+	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
+	write_frame->fence_value = index;
+	amdgpu_asic_flush_hdp(adev, NULL);
+
+	/* Update the write Pointer in DWORDs */
+	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
+	psp_ring_set_wptr(psp, psp_write_ptr_reg);
+	return 0;
+}
+
 static bool psp_check_fw_loading_status(struct amdgpu_device *adev,
 					enum AMDGPU_UCODE_ID ucode_type)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 09c5474ebcc3..3265487b859f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -32,7 +32,6 @@
 
 #define PSP_FENCE_BUFFER_SIZE	0x1000
 #define PSP_CMD_BUFFER_SIZE	0x1000
-#define PSP_ASD_SHARED_MEM_SIZE 0x4000
 #define PSP_XGMI_SHARED_MEM_SIZE 0x4000
 #define PSP_RAS_SHARED_MEM_SIZE 0x4000
 #define PSP_1_MEG		0x100000
@@ -94,9 +93,6 @@ struct psp_funcs
 			    enum psp_ring_type ring_type);
 	int (*ring_destroy)(struct psp_context *psp,
 			    enum psp_ring_type ring_type);
-	int (*cmd_submit)(struct psp_context *psp,
-			  uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			  int index);
 	bool (*compare_sram_data)(struct psp_context *psp,
 				  struct amdgpu_firmware_info *ucode,
 				  enum AMDGPU_UCODE_ID ucode_type);
@@ -116,6 +112,8 @@ struct psp_funcs
 	int (*mem_training_init)(struct psp_context *psp);
 	void (*mem_training_fini)(struct psp_context *psp);
 	int (*mem_training)(struct psp_context *psp, uint32_t ops);
+	uint32_t (*ring_get_wptr)(struct psp_context *psp);
+	void (*ring_set_wptr)(struct psp_context *psp, uint32_t value);
 };
 
 #define AMDGPU_XGMI_MAX_CONNECTED_NODES		64
@@ -131,6 +129,11 @@ struct psp_xgmi_topology_info {
 	struct psp_xgmi_node_info	nodes[AMDGPU_XGMI_MAX_CONNECTED_NODES];
 };
 
+struct psp_asd_context {
+	bool			asd_initialized;
+	uint32_t		session_id;
+};
+
 struct psp_xgmi_context {
 	uint8_t				initialized;
 	uint32_t			session_id;
@@ -199,7 +202,6 @@ struct psp_memory_training_context {
 
 	/*vram offset of the p2c training data*/
 	u64 p2c_train_data_offset;
-	struct amdgpu_bo *p2c_bo;
 
 	/*vram offset of the c2p training data*/
 	u64 c2p_train_data_offset;
@@ -239,15 +241,12 @@ struct psp_context
 	struct amdgpu_bo		*tmr_bo;
 	uint64_t			tmr_mc_addr;
 
-	/* asd firmware and buffer */
+	/* asd firmware */
 	const struct firmware		*asd_fw;
 	uint32_t			asd_fw_version;
 	uint32_t			asd_feature_version;
 	uint32_t			asd_ucode_size;
 	uint8_t				*asd_start_addr;
-	struct amdgpu_bo		*asd_shared_bo;
-	uint64_t			asd_shared_mc_addr;
-	void				*asd_shared_buf;
 
 	/* fence buffer */
 	struct amdgpu_bo		*fence_buf_bo;
@@ -282,6 +281,7 @@ struct psp_context
 	uint32_t			ta_dtm_ucode_size;
 	uint8_t				*ta_dtm_start_addr;
 
+	struct psp_asd_context		asd_context;
 	struct psp_xgmi_context		xgmi_context;
 	struct psp_ras_context		ras;
 	struct psp_hdcp_context 	hdcp_context;
@@ -300,8 +300,6 @@ struct amdgpu_psp_funcs {
 #define psp_ring_create(psp, type) (psp)->funcs->ring_create((psp), (type))
 #define psp_ring_stop(psp, type) (psp)->funcs->ring_stop((psp), (type))
 #define psp_ring_destroy(psp, type) ((psp)->funcs->ring_destroy((psp), (type)))
-#define psp_cmd_submit(psp, cmd_mc, fence_mc, index) \
-		(psp)->funcs->cmd_submit((psp), (cmd_mc), (fence_mc), (index))
 #define psp_compare_sram_data(psp, ucode, type) \
 		(psp)->funcs->compare_sram_data((psp), (ucode), (type))
 #define psp_init_microcode(psp) \
@@ -346,6 +344,9 @@ struct amdgpu_psp_funcs {
 	((psp)->funcs->ras_cure_posion ? \
 	(psp)->funcs->ras_cure_posion(psp, (addr)) : -EINVAL)
 
+#define psp_ring_get_wptr(psp) (psp)->funcs->ring_get_wptr((psp))
+#define psp_ring_set_wptr(psp, value) (psp)->funcs->ring_set_wptr((psp), (value))
+
 extern const struct amd_ip_funcs psp_ip_funcs;
 
 extern const struct amdgpu_ip_block_version psp_v3_1_ip_block;
@@ -372,4 +373,8 @@ int psp_rlc_autoload_start(struct psp_context *psp);
 extern const struct amdgpu_ip_block_version psp_v11_0_ip_block;
 int psp_reg_program(struct psp_context *psp, enum psp_reg_prog_id reg,
 		uint32_t value);
+int psp_ring_cmd_submit(struct psp_context *psp,
+			uint64_t cmd_buf_mc_addr,
+			uint64_t fence_mc_addr,
+			int index);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 404483437bd3..766be7f18282 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -198,9 +198,6 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 	return 0;
 }
 
-static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
-		struct ras_common_if *head);
-
 /**
  * DOC: AMDGPU RAS debugfs control interface
  *
@@ -318,7 +315,7 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 	default:
 		ret = -EINVAL;
 		break;
-	};
+	}
 
 	if (ret)
 		return -EINVAL;
@@ -445,7 +442,7 @@ static struct ras_manager *amdgpu_ras_create_obj(struct amdgpu_device *adev,
 }
 
 /* return an obj equal to head, or the first when head is NULL */
-static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
+struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
 		struct ras_common_if *head)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -689,6 +686,7 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 {
 	struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
 	struct ras_err_data err_data = {0, 0, 0, NULL};
+	int i;
 
 	if (!obj)
 		return -EINVAL;
@@ -703,6 +701,13 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 		if (adev->umc.funcs->query_ras_error_address)
 			adev->umc.funcs->query_ras_error_address(adev, &err_data);
 		break;
+	case AMDGPU_RAS_BLOCK__SDMA:
+		if (adev->sdma.funcs->query_ras_error_count) {
+			for (i = 0; i < adev->sdma.num_instances; i++)
+				adev->sdma.funcs->query_ras_error_count(adev, i,
+									&err_data);
+		}
+		break;
 	case AMDGPU_RAS_BLOCK__GFX:
 		if (adev->gfx.funcs->query_ras_error_count)
 			adev->gfx.funcs->query_ras_error_count(adev, &err_data);
@@ -1314,6 +1319,7 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 	data = con->eh_data;
 	if (!data || data->count == 0) {
 		*bps = NULL;
+		ret = -EINVAL;
 		goto out;
 	}
 
@@ -1347,7 +1353,8 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 	struct amdgpu_ras *ras =
 		container_of(work, struct amdgpu_ras, recovery_work);
 
-	amdgpu_device_gpu_recover(ras->adev, 0);
+	if (amdgpu_device_should_recover_gpu(ras->adev))
+		amdgpu_device_gpu_recover(ras->adev, 0);
 	atomic_set(&ras->in_recovery, 0);
 }
 
@@ -1687,7 +1694,8 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
 	*supported = 0;
 
 	if (amdgpu_sriov_vf(adev) ||
-			adev->asic_type != CHIP_VEGA20)
+	    (adev->asic_type != CHIP_VEGA20 &&
+	     adev->asic_type != CHIP_ARCTURUS))
 		return;
 
 	if (adev->is_atom_fw &&
@@ -1872,7 +1880,7 @@ void amdgpu_ras_resume(struct amdgpu_device *adev)
 		 * See feature_enable_on_boot
 		 */
 		amdgpu_ras_disable_all_features(adev, 1);
-		amdgpu_ras_reset_gpu(adev, 0);
+		amdgpu_ras_reset_gpu(adev);
 	}
 }
 
@@ -1935,6 +1943,6 @@ void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
 		DRM_WARN("RAS event of type ERREVENT_ATHUB_INTERRUPT detected!\n");
 
-		amdgpu_ras_reset_gpu(adev, false);
+		amdgpu_ras_reset_gpu(adev);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index f80fd3428c98..a5fe29a9373e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -494,8 +494,7 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
 
-static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev,
-		bool is_baco)
+static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
@@ -611,6 +610,9 @@ int amdgpu_ras_interrupt_remove_handler(struct amdgpu_device *adev,
 int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev,
 		struct ras_dispatch_if *info);
 
+struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
+		struct ras_common_if *head);
+
 extern atomic_t amdgpu_ras_in_intr;
 
 static inline bool amdgpu_ras_intr_triggered(void)
@@ -618,6 +620,11 @@ static inline bool amdgpu_ras_intr_triggered(void)
 	return !!atomic_read(&amdgpu_ras_in_intr);
 }
 
+static inline void amdgpu_ras_intr_cleared(void)
+{
+	atomic_set(&amdgpu_ras_in_intr, 0);
+}
+
 void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 6010999d9020..a2ee30b16212 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -160,7 +160,7 @@ int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev,
 		struct amdgpu_iv_entry *entry)
 {
 	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
-	amdgpu_ras_reset_gpu(adev, 0);
+	amdgpu_ras_reset_gpu(adev);
 
 	return AMDGPU_RAS_SUCCESS;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index 761ff8be6314..485335267d78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -50,8 +50,18 @@ struct amdgpu_sdma_instance {
 	bool			burst_nop;
 };
 
+struct amdgpu_sdma_ras_funcs {
+	int (*ras_late_init)(struct amdgpu_device *adev,
+			void *ras_ih_info);
+	void (*ras_fini)(struct amdgpu_device *adev);
+	int (*query_ras_error_count)(struct amdgpu_device *adev,
+			uint32_t instance, void *ras_error_status);
+};
+
 struct amdgpu_sdma {
 	struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
+	struct drm_gpu_scheduler    *sdma_sched[AMDGPU_MAX_SDMA_INSTANCES];
+	uint32_t		    num_sdma_sched;
 	struct amdgpu_irq_src	trap_irq;
 	struct amdgpu_irq_src	illegal_inst_irq;
 	struct amdgpu_irq_src	ecc_irq;
@@ -59,6 +69,7 @@ struct amdgpu_sdma {
 	uint32_t                    srbm_soft_reset;
 	bool			has_page_queue;
 	struct ras_common_if	*ras_if;
+	const struct amdgpu_sdma_ras_funcs	*funcs;
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index 95e5e93edd18..a09b6b9c27d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -129,7 +129,8 @@ static void amdgpu_sync_keep_later(struct dma_fence **keep,
  * Tries to add the fence to an existing hash entry. Returns true when an entry
  * was found, false otherwise.
  */
-static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f, bool explicit)
+static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f,
+				  bool explicit)
 {
 	struct amdgpu_sync_entry *e;
 
@@ -151,19 +152,18 @@ static bool amdgpu_sync_add_later(struct amdgpu_sync *sync, struct dma_fence *f,
  * amdgpu_sync_fence - remember to sync to this fence
  *
  * @sync: sync object to add fence to
- * @fence: fence to sync to
+ * @f: fence to sync to
+ * @explicit: if this is an explicit dependency
  *
+ * Add the fence to the sync object.
  */
-int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
-		      struct dma_fence *f, bool explicit)
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+		      bool explicit)
 {
 	struct amdgpu_sync_entry *e;
 
 	if (!f)
 		return 0;
-	if (amdgpu_sync_same_dev(adev, f) &&
-	    amdgpu_sync_get_owner(f) == AMDGPU_FENCE_OWNER_VM)
-		amdgpu_sync_keep_later(&sync->last_vm_update, f);
 
 	if (amdgpu_sync_add_later(sync, f, explicit))
 		return 0;
@@ -180,6 +180,24 @@ int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
 }
 
 /**
+ * amdgpu_sync_vm_fence - remember to sync to this VM fence
+ *
+ * @adev: amdgpu device
+ * @sync: sync object to add fence to
+ * @fence: the VM fence to add
+ *
+ * Add the fence to the sync object and remember it as VM update.
+ */
+int amdgpu_sync_vm_fence(struct amdgpu_sync *sync, struct dma_fence *fence)
+{
+	if (!fence)
+		return 0;
+
+	amdgpu_sync_keep_later(&sync->last_vm_update, fence);
+	return amdgpu_sync_fence(sync, fence, false);
+}
+
+/**
  * amdgpu_sync_resv - sync to a reservation object
  *
  * @sync: sync object to add fences from reservation object to
@@ -204,7 +222,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 
 	/* always sync to the exclusive fence */
 	f = dma_resv_get_excl(resv);
-	r = amdgpu_sync_fence(adev, sync, f, false);
+	r = amdgpu_sync_fence(sync, f, false);
 
 	flist = dma_resv_get_list(resv);
 	if (!flist || r)
@@ -222,13 +240,11 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 			continue;
 
 		if (amdgpu_sync_same_dev(adev, f)) {
-			/* VM updates are only interesting
-			 * for other VM updates and moves.
+			/* VM updates only sync with moves but not with user
+			 * command submissions or KFD evictions fences
 			 */
-			if ((owner != AMDGPU_FENCE_OWNER_UNDEFINED) &&
-			    (fence_owner != AMDGPU_FENCE_OWNER_UNDEFINED) &&
-			    ((owner == AMDGPU_FENCE_OWNER_VM) !=
-			     (fence_owner == AMDGPU_FENCE_OWNER_VM)))
+			if (owner == AMDGPU_FENCE_OWNER_VM &&
+			    fence_owner != AMDGPU_FENCE_OWNER_UNDEFINED)
 				continue;
 
 			/* Ignore fence from the same owner and explicit one as
@@ -239,7 +255,7 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 				continue;
 		}
 
-		r = amdgpu_sync_fence(adev, sync, f, false);
+		r = amdgpu_sync_fence(sync, f, false);
 		if (r)
 			break;
 	}
@@ -340,7 +356,7 @@ int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone)
 	hash_for_each_safe(source->fences, i, tmp, e, node) {
 		f = e->fence;
 		if (!dma_fence_is_signaled(f)) {
-			r = amdgpu_sync_fence(NULL, clone, f, e->explicit);
+			r = amdgpu_sync_fence(clone, f, e->explicit);
 			if (r)
 				return r;
 		} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
index b5f1778a2319..d62c2b81d92b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.h
@@ -40,8 +40,9 @@ struct amdgpu_sync {
 };
 
 void amdgpu_sync_create(struct amdgpu_sync *sync);
-int amdgpu_sync_fence(struct amdgpu_device *adev, struct amdgpu_sync *sync,
-		      struct dma_fence *f, bool explicit);
+int amdgpu_sync_fence(struct amdgpu_sync *sync, struct dma_fence *f,
+		      bool explicit);
+int amdgpu_sync_vm_fence(struct amdgpu_sync *sync, struct dma_fence *fence);
 int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     struct amdgpu_sync *sync,
 		     struct dma_resv *resv,
@@ -49,7 +50,8 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
 		     bool explicit_sync);
 struct dma_fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync,
 				     struct amdgpu_ring *ring);
-struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync, bool *explicit);
+struct dma_fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync,
+					bool *explicit);
 int amdgpu_sync_clone(struct amdgpu_sync *source, struct amdgpu_sync *clone);
 int amdgpu_sync_wait(struct amdgpu_sync *sync, bool intr);
 void amdgpu_sync_free(struct amdgpu_sync *sync);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 2616e2eafdeb..dee446278417 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -41,6 +41,7 @@
 #include <linux/swap.h>
 #include <linux/swiotlb.h>
 #include <linux/dma-buf.h>
+#include <linux/sizes.h>
 
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
@@ -1522,11 +1523,8 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 	struct dma_fence *f;
 	int i;
 
-	/* Don't evict VM page tables while they are busy, otherwise we can't
-	 * cleanly handle page faults.
-	 */
 	if (bo->type == ttm_bo_type_kernel &&
-	    !dma_resv_test_signaled_rcu(bo->base.resv, true))
+	    !amdgpu_vm_evictable(ttm_to_amdgpu_bo(bo)))
 		return false;
 
 	/* If bo is a KFD BO, check if the bo belongs to the current process.
@@ -1717,12 +1715,17 @@ static int amdgpu_ttm_training_reserve_vram_fini(struct amdgpu_device *adev)
 	amdgpu_bo_free_kernel(&ctx->c2p_bo, NULL, NULL);
 	ctx->c2p_bo = NULL;
 
-	amdgpu_bo_free_kernel(&ctx->p2c_bo, NULL, NULL);
-	ctx->p2c_bo = NULL;
-
 	return 0;
 }
 
+static u64 amdgpu_ttm_training_get_c2p_offset(u64 vram_size)
+{
+       if ((vram_size & (SZ_1M - 1)) < (SZ_4K + 1) )
+               vram_size -= SZ_1M;
+
+       return ALIGN(vram_size, SZ_1M);
+}
+
 /**
  * amdgpu_ttm_training_reserve_vram_init - create bo vram reservation from memory training
  *
@@ -1741,7 +1744,7 @@ static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
 		return 0;
 	}
 
-	ctx->c2p_train_data_offset = adev->fw_vram_usage.mem_train_fb_loc;
+	ctx->c2p_train_data_offset = amdgpu_ttm_training_get_c2p_offset(adev->gmc.mc_vram_size);
 	ctx->p2c_train_data_offset = (adev->gmc.mc_vram_size - GDDR6_MEM_TRAINING_OFFSET);
 	ctx->train_data_size = GDDR6_MEM_TRAINING_DATA_SIZE_IN_BYTES;
 
@@ -1751,17 +1754,6 @@ static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
 		  ctx->c2p_train_data_offset);
 
 	ret = amdgpu_bo_create_kernel_at(adev,
-					 ctx->p2c_train_data_offset,
-					 ctx->train_data_size,
-					 AMDGPU_GEM_DOMAIN_VRAM,
-					 &ctx->p2c_bo,
-					 NULL);
-	if (ret) {
-		DRM_ERROR("alloc p2c_bo failed(%d)!\n", ret);
-		goto Err_out;
-	}
-
-	ret = amdgpu_bo_create_kernel_at(adev,
 					 ctx->c2p_train_data_offset,
 					 ctx->train_data_size,
 					 AMDGPU_GEM_DOMAIN_VRAM,
@@ -1769,15 +1761,12 @@ static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
 					 NULL);
 	if (ret) {
 		DRM_ERROR("alloc c2p_bo failed(%d)!\n", ret);
-		goto Err_out;
+		amdgpu_ttm_training_reserve_vram_fini(adev);
+		return ret;
 	}
 
 	ctx->init = PSP_MEM_TRAIN_RESERVE_SUCCESS;
 	return 0;
-
-Err_out:
-	amdgpu_ttm_training_reserve_vram_fini(adev);
-	return ret;
 }
 
 /**
@@ -1990,11 +1979,13 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 
 	if (enable) {
 		struct amdgpu_ring *ring;
-		struct drm_sched_rq *rq;
+		struct drm_gpu_scheduler *sched;
 
 		ring = adev->mman.buffer_funcs_ring;
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-		r = drm_sched_entity_init(&adev->mman.entity, &rq, 1, NULL);
+		sched = &ring->sched;
+		r = drm_sched_entity_init(&adev->mman.entity,
+				          DRM_SCHED_PRIORITY_KERNEL, &sched,
+					  1, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
 				  r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 833fc4b68940..9ef312428231 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -447,6 +447,7 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	const struct common_firmware_header *header = NULL;
 	const struct gfx_firmware_header_v1_0 *cp_hdr = NULL;
 	const struct dmcu_firmware_header_v1_0 *dmcu_hdr = NULL;
+	const struct dmcub_firmware_header_v1_0 *dmcub_hdr = NULL;
 
 	if (NULL == ucode->fw)
 		return 0;
@@ -460,6 +461,7 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	header = (const struct common_firmware_header *)ucode->fw->data;
 	cp_hdr = (const struct gfx_firmware_header_v1_0 *)ucode->fw->data;
 	dmcu_hdr = (const struct dmcu_firmware_header_v1_0 *)ucode->fw->data;
+	dmcub_hdr = (const struct dmcub_firmware_header_v1_0 *)ucode->fw->data;
 
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP ||
 	    (ucode->ucode_id != AMDGPU_UCODE_ID_CP_MEC1 &&
@@ -470,7 +472,8 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM &&
 	     ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM &&
 		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_ERAM &&
-		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV)) {
+		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV &&
+		 ucode->ucode_id != AMDGPU_UCODE_ID_DMCUB)) {
 		ucode->ucode_size = le32_to_cpu(header->ucode_size_bytes);
 
 		memcpy(ucode->kaddr, (void *)((uint8_t *)ucode->fw->data +
@@ -506,6 +509,12 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
 					      le32_to_cpu(header->ucode_array_offset_bytes) +
 					      le32_to_cpu(dmcu_hdr->intv_offset_bytes)),
 		       ucode->ucode_size);
+	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_DMCUB) {
+		ucode->ucode_size = le32_to_cpu(dmcub_hdr->inst_const_bytes);
+		memcpy(ucode->kaddr,
+		       (void *)((uint8_t *)ucode->fw->data +
+				le32_to_cpu(header->ucode_array_offset_bytes)),
+		       ucode->ucode_size);
 	} else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL) {
 		ucode->ucode_size = adev->gfx.rlc.save_restore_list_cntl_size_bytes;
 		memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_cntl,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 914acecda5cf..b0e656409c03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -251,6 +251,13 @@ struct dmcu_firmware_header_v1_0 {
 	uint32_t intv_size_bytes;  /* size of interrupt vectors, in bytes */
 };
 
+/* version_major=1, version_minor=0 */
+struct dmcub_firmware_header_v1_0 {
+	struct common_firmware_header header;
+	uint32_t inst_const_bytes; /* size of instruction region, in bytes */
+	uint32_t bss_data_bytes; /* size of bss/data region, in bytes */
+};
+
 /* header is fixed size */
 union amdgpu_firmware_header {
 	struct common_firmware_header common;
@@ -268,6 +275,7 @@ union amdgpu_firmware_header {
 	struct sdma_firmware_header_v1_1 sdma_v1_1;
 	struct gpu_info_firmware_header_v1_0 gpu_info;
 	struct dmcu_firmware_header_v1_0 dmcu;
+	struct dmcub_firmware_header_v1_0 dmcub;
 	uint8_t raw[0x100];
 };
 
@@ -307,6 +315,7 @@ enum AMDGPU_UCODE_ID {
 	AMDGPU_UCODE_ID_DMCU_INTV,
 	AMDGPU_UCODE_ID_VCN0_RAM,
 	AMDGPU_UCODE_ID_VCN1_RAM,
+	AMDGPU_UCODE_ID_DMCUB,
 	AMDGPU_UCODE_ID_MAXIMUM,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index d4fb9cf27e21..f4d40855147b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -95,13 +95,6 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 
-	/* When “Full RAS” is enabled, the per-IP interrupt sources should
-	 * be disabled and the driver should only look for the aggregated
-	 * interrupt via sync flood
-	 */
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
-		return AMDGPU_RAS_SUCCESS;
-
 	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
 	if (adev->umc.funcs &&
 	    adev->umc.funcs->query_ras_error_count)
@@ -113,6 +106,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 		err_data->err_addr =
 			kcalloc(adev->umc.max_ras_err_cnt_per_query,
 				sizeof(struct eeprom_table_record), GFP_KERNEL);
+
 		/* still call query_ras_error_address to clear error status
 		 * even NOMEM error is encountered
 		 */
@@ -132,7 +126,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 						err_data->err_addr_cnt))
 			DRM_WARN("Failed to add ras bad page!\n");
 
-		amdgpu_ras_reset_gpu(adev, 0);
+		amdgpu_ras_reset_gpu(adev);
 	}
 
 	kfree(err_data->err_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index 3283032a78e5..a615a1eb750b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -21,38 +21,6 @@
 #ifndef __AMDGPU_UMC_H__
 #define __AMDGPU_UMC_H__
 
-/* implement 64 bits REG operations via 32 bits interface */
-#define RREG64_UMC(reg)	(RREG32(reg) | \
-				((uint64_t)RREG32((reg) + 1) << 32))
-#define WREG64_UMC(reg, v)	\
-	do {	\
-		WREG32((reg), lower_32_bits(v));	\
-		WREG32((reg) + 1, upper_32_bits(v));	\
-	} while (0)
-
-/*
- * void (*func)(struct amdgpu_device *adev, struct ras_err_data *err_data,
- *				uint32_t umc_reg_offset, uint32_t channel_index)
- */
-#define amdgpu_umc_for_each_channel(func)	\
-	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;	\
-	uint32_t umc_inst, channel_inst, umc_reg_offset, channel_index;	\
-	for (umc_inst = 0; umc_inst < adev->umc.umc_inst_num; umc_inst++) {	\
-		/* enable the index mode to query eror count per channel */	\
-		adev->umc.funcs->enable_umc_index_mode(adev, umc_inst);	\
-		for (channel_inst = 0;	\
-			channel_inst < adev->umc.channel_inst_num;	\
-			channel_inst++) {	\
-			/* calc the register offset according to channel instance */	\
-			umc_reg_offset = adev->umc.channel_offs * channel_inst;	\
-			/* get channel index of interleaved memory */	\
-			channel_index = adev->umc.channel_idx_tbl[	\
-				umc_inst * adev->umc.channel_inst_num + channel_inst];	\
-			(func)(adev, err_data, umc_reg_offset, channel_index);	\
-		}	\
-	}	\
-	adev->umc.funcs->disable_umc_index_mode(adev);
-
 struct amdgpu_umc_funcs {
 	void (*err_cnt_init)(struct amdgpu_device *adev);
 	int (*ras_late_init)(struct amdgpu_device *adev);
@@ -60,9 +28,6 @@ struct amdgpu_umc_funcs {
 					void *ras_error_status);
 	void (*query_ras_error_address)(struct amdgpu_device *adev,
 					void *ras_error_status);
-	void (*enable_umc_index_mode)(struct amdgpu_device *adev,
-					uint32_t umc_instance);
-	void (*disable_umc_index_mode)(struct amdgpu_device *adev);
 	void (*init_registers)(struct amdgpu_device *adev);
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index e324bfe6c58f..a92f3b18e657 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -330,12 +330,13 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 int amdgpu_uvd_entity_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
+	struct drm_gpu_scheduler *sched;
 	int r;
 
 	ring = &adev->uvd.inst[0].ring;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&adev->uvd.entity, &rq, 1, NULL);
+	sched = &ring->sched;
+	r = drm_sched_entity_init(&adev->uvd.entity, DRM_SCHED_PRIORITY_NORMAL,
+				  &sched, 1, NULL);
 	if (r) {
 		DRM_ERROR("Failed setting up UVD kernel entity.\n");
 		return r;
@@ -349,6 +350,7 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	unsigned size;
 	void *ptr;
 	int i, j;
+	bool in_ras_intr = amdgpu_ras_intr_triggered();
 
 	cancel_delayed_work_sync(&adev->uvd.idle_work);
 
@@ -376,13 +378,15 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 			return -ENOMEM;
 
 		/* re-write 0 since err_event_athub will corrupt VCPU buffer */
-		if (amdgpu_ras_intr_triggered()) {
-			DRM_WARN("UVD VCPU state may lost due to RAS ERREVENT_ATHUB_INTERRUPT\n");
+		if (in_ras_intr)
 			memset(adev->uvd.inst[j].saved_bo, 0, size);
-		} else {
+		else
 			memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
-		}
 	}
+
+	if (in_ras_intr)
+		DRM_WARN("UVD VCPU state may lost due to RAS ERREVENT_ATHUB_INTERRUPT\n");
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 46b590af2fd2..ceb0dbf685f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -240,12 +240,13 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 int amdgpu_vce_entity_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
+	struct drm_gpu_scheduler *sched;
 	int r;
 
 	ring = &adev->vce.ring[0];
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL);
+	sched = &ring->sched;
+	r = drm_sched_entity_init(&adev->vce.entity, DRM_SCHED_PRIORITY_NORMAL,
+				  &sched, 1, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 9d870444d7d6..f96464e2c157 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -28,19 +28,10 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
-#include <drm/drm.h>
-
 #include "amdgpu.h"
 #include "amdgpu_pm.h"
 #include "amdgpu_vcn.h"
 #include "soc15d.h"
-#include "soc15_common.h"
-
-#include "vcn/vcn_1_0_offset.h"
-#include "vcn/vcn_1_0_sh_mask.h"
-
-/* 1 second timeout */
-#define VCN_IDLE_TIMEOUT	msecs_to_jiffies(1000)
 
 /* Firmware Names */
 #define FIRMWARE_RAVEN		"amdgpu/raven_vcn.bin"
@@ -84,6 +75,9 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		break;
 	case CHIP_ARCTURUS:
 		fw_name = FIRMWARE_ARCTURUS;
+		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
+		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
+			adev->vcn.indirect_sram = true;
 		break;
 	case CHIP_RENOIR:
 		fw_name = FIRMWARE_RENOIR;
@@ -174,15 +168,15 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 			dev_err(adev->dev, "(%d) failed to allocate vcn bo\n", r);
 			return r;
 		}
-	}
 
-	if (adev->vcn.indirect_sram) {
-		r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
-			    AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.dpg_sram_bo,
-			    &adev->vcn.dpg_sram_gpu_addr, &adev->vcn.dpg_sram_cpu_addr);
-		if (r) {
-			dev_err(adev->dev, "(%d) failed to allocate DPG bo\n", r);
-			return r;
+		if (adev->vcn.indirect_sram) {
+			r = amdgpu_bo_create_kernel(adev, 64 * 2 * 4, PAGE_SIZE,
+					AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.inst[i].dpg_sram_bo,
+					&adev->vcn.inst[i].dpg_sram_gpu_addr, &adev->vcn.inst[i].dpg_sram_cpu_addr);
+			if (r) {
+				dev_err(adev->dev, "VCN %d (%d) failed to allocate DPG bo\n", i, r);
+				return r;
+			}
 		}
 	}
 
@@ -195,15 +189,14 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 	cancel_delayed_work_sync(&adev->vcn.idle_work);
 
-	if (adev->vcn.indirect_sram) {
-		amdgpu_bo_free_kernel(&adev->vcn.dpg_sram_bo,
-				      &adev->vcn.dpg_sram_gpu_addr,
-				      (void **)&adev->vcn.dpg_sram_cpu_addr);
-	}
-
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
+		if (adev->vcn.indirect_sram) {
+			amdgpu_bo_free_kernel(&adev->vcn.inst[j].dpg_sram_bo,
+						  &adev->vcn.inst[j].dpg_sram_gpu_addr,
+						  (void **)&adev->vcn.inst[j].dpg_sram_cpu_addr);
+		}
 		kvfree(adev->vcn.inst[j].saved_bo);
 
 		amdgpu_bo_free_kernel(&adev->vcn.inst[j].vcpu_bo,
@@ -214,8 +207,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->vcn.inst[j].ring_enc[i]);
-
-		amdgpu_ring_fini(&adev->vcn.inst[j].ring_jpeg);
 	}
 
 	release_firmware(adev->vcn.fw);
@@ -296,6 +287,7 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
+
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 			fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
 		}
@@ -308,26 +300,17 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 			else
 				new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
 
-			if (amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_jpeg))
-				new_state.jpeg = VCN_DPG_STATE__PAUSE;
-			else
-				new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
-
-			adev->vcn.pause_dpg_mode(adev, &new_state);
+			adev->vcn.pause_dpg_mode(adev, j, &new_state);
 		}
 
-		fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_jpeg);
 		fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_dec);
 		fences += fence[j];
 	}
 
 	if (fences == 0) {
 		amdgpu_gfx_off_ctrl(adev, true);
-		if (adev->asic_type < CHIP_ARCTURUS && adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_uvd(adev, false);
-		else
-			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
-							       AMD_PG_STATE_GATE);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+		       AMD_PG_STATE_GATE);
 	} else {
 		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
 	}
@@ -340,11 +323,8 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 
 	if (set_clocks) {
 		amdgpu_gfx_off_ctrl(adev, false);
-		if (adev->asic_type < CHIP_ARCTURUS && adev->pm.dpm_enabled)
-			amdgpu_dpm_enable_uvd(adev, true);
-		else
-			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
-							       AMD_PG_STATE_UNGATE);
+		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+		       AMD_PG_STATE_UNGATE);
 	}
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)	{
@@ -360,17 +340,10 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 		else
 			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
 
-		if (amdgpu_fence_count_emitted(&adev->vcn.inst[ring->me].ring_jpeg))
-			new_state.jpeg = VCN_DPG_STATE__PAUSE;
-		else
-			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
-
 		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
 			new_state.fw_based = VCN_DPG_STATE__PAUSE;
-		else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
-			new_state.jpeg = VCN_DPG_STATE__PAUSE;
 
-		adev->vcn.pause_dpg_mode(adev, &new_state);
+		adev->vcn.pause_dpg_mode(adev, ring->me, &new_state);
 	}
 }
 
@@ -520,9 +493,14 @@ static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 
 int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
+	struct amdgpu_device *adev = ring->adev;
 	struct dma_fence *fence;
 	long r;
 
+	/* temporarily disable ib test for sriov */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	r = amdgpu_vcn_dec_get_create_msg(ring, 1, NULL);
 	if (r)
 		goto error;
@@ -678,10 +656,15 @@ err:
 
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
+	struct amdgpu_device *adev = ring->adev;
 	struct dma_fence *fence = NULL;
 	struct amdgpu_bo *bo = NULL;
 	long r;
 
+	/* temporarily disable ib test for sriov */
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &bo, NULL, NULL);
@@ -708,108 +691,3 @@ error:
 	amdgpu_bo_unref(&bo);
 	return r;
 }
-
-int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t tmp = 0;
-	unsigned i;
-	int r;
-
-	WREG32(adev->vcn.inst[ring->me].external.jpeg_pitch, 0xCAFEDEAD);
-	r = amdgpu_ring_alloc(ring, 3);
-	if (r)
-		return r;
-
-	amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.jpeg_pitch, 0));
-	amdgpu_ring_write(ring, 0xDEADBEEF);
-	amdgpu_ring_commit(ring);
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(adev->vcn.inst[ring->me].external.jpeg_pitch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		udelay(1);
-	}
-
-	if (i >= adev->usec_timeout)
-		r = -ETIMEDOUT;
-
-	return r;
-}
-
-static int amdgpu_vcn_jpeg_set_reg(struct amdgpu_ring *ring, uint32_t handle,
-		struct dma_fence **fence)
-{
-	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_job *job;
-	struct amdgpu_ib *ib;
-	struct dma_fence *f = NULL;
-	const unsigned ib_size_dw = 16;
-	int i, r;
-
-	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
-	if (r)
-		return r;
-
-	ib = &job->ibs[0];
-
-	ib->ptr[0] = PACKETJ(adev->vcn.internal.jpeg_pitch, 0, 0, PACKETJ_TYPE0);
-	ib->ptr[1] = 0xDEADBEEF;
-	for (i = 2; i < 16; i += 2) {
-		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
-		ib->ptr[i+1] = 0;
-	}
-	ib->length_dw = 16;
-
-	r = amdgpu_job_submit_direct(job, ring, &f);
-	if (r)
-		goto err;
-
-	if (fence)
-		*fence = dma_fence_get(f);
-	dma_fence_put(f);
-
-	return 0;
-
-err:
-	amdgpu_job_free(job);
-	return r;
-}
-
-int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t tmp = 0;
-	unsigned i;
-	struct dma_fence *fence = NULL;
-	long r = 0;
-
-	r = amdgpu_vcn_jpeg_set_reg(ring, 1, &fence);
-	if (r)
-		goto error;
-
-	r = dma_fence_wait_timeout(fence, false, timeout);
-	if (r == 0) {
-		r = -ETIMEDOUT;
-		goto error;
-	} else if (r < 0) {
-		goto error;
-	} else {
-		r = 0;
-	}
-
-	for (i = 0; i < adev->usec_timeout; i++) {
-		tmp = RREG32(adev->vcn.inst[ring->me].external.jpeg_pitch);
-		if (tmp == 0xDEADBEEF)
-			break;
-		udelay(1);
-	}
-
-	if (i >= adev->usec_timeout)
-		r = -ETIMEDOUT;
-
-	dma_fence_put(fence);
-error:
-	return r;
-}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index dface275c81a..c4984c5fb2db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -31,6 +31,7 @@
 #define AMDGPU_VCN_MAX_ENC_RINGS	3
 
 #define AMDGPU_MAX_VCN_INSTANCES	2
+#define AMDGPU_MAX_VCN_ENC_RINGS  AMDGPU_VCN_MAX_ENC_RINGS * AMDGPU_MAX_VCN_INSTANCES
 
 #define AMDGPU_VCN_HARVEST_VCN0 (1 << 0)
 #define AMDGPU_VCN_HARVEST_VCN1 (1 << 1)
@@ -56,6 +57,14 @@
 #define VCN_VID_IP_ADDRESS_2_0		0x0
 #define VCN_AON_IP_ADDRESS_2_0		0x30000
 
+#define mmUVD_RBC_XX_IB_REG_CHECK 					0x026b
+#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX 				1
+#define mmUVD_REG_XX_MASK 						0x026c
+#define mmUVD_REG_XX_MASK_BASE_IDX 					1
+
+/* 1 second timeout */
+#define VCN_IDLE_TIMEOUT	msecs_to_jiffies(1000)
+
 #define RREG32_SOC15_DPG_MODE(ip, inst, reg, mask, sram_sel) 				\
 	({	WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_MASK, mask); 			\
 		WREG32_SOC15(ip, inst, mmUVD_DPG_LMA_CTL, 				\
@@ -100,27 +109,27 @@
 		internal_reg_offset >>= 2;							\
 	})
 
-#define RREG32_SOC15_DPG_MODE_2_0(offset, mask_en) 						\
-	({ 											\
-		WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_CTL, 					\
-			(0x0 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT | 				\
-			mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT | 				\
-			offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT)); 			\
-		RREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_DATA); 					\
+#define RREG32_SOC15_DPG_MODE_2_0(inst_idx, offset, mask_en) 					\
+	({											\
+		WREG32_SOC15(VCN, inst, mmUVD_DPG_LMA_CTL, 					\
+			(0x0 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT |				\
+			mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT |				\
+			offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT));			\
+		RREG32_SOC15(VCN, inst_idx, mmUVD_DPG_LMA_DATA);				\
 	})
 
-#define WREG32_SOC15_DPG_MODE_2_0(offset, value, mask_en, indirect)				\
-	do { 											\
-		if (!indirect) { 								\
-			WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_DATA, value); 			\
-			WREG32_SOC15(VCN, 0, mmUVD_DPG_LMA_CTL, 				\
-				(0x1 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT | 			\
-				 mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT | 			\
-				 offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT)); 		\
-		} else { 									\
-			*adev->vcn.dpg_sram_curr_addr++ = offset; 				\
-			*adev->vcn.dpg_sram_curr_addr++ = value; 				\
-		} 										\
+#define WREG32_SOC15_DPG_MODE_2_0(inst_idx, offset, value, mask_en, indirect)			\
+	do {											\
+		if (!indirect) {								\
+			WREG32_SOC15(VCN, inst_idx, mmUVD_DPG_LMA_DATA, value);			\
+			WREG32_SOC15(VCN, inst_idx, mmUVD_DPG_LMA_CTL, 				\
+				(0x1 << UVD_DPG_LMA_CTL__READ_WRITE__SHIFT |			\
+				 mask_en << UVD_DPG_LMA_CTL__MASK_EN__SHIFT |			\
+				 offset << UVD_DPG_LMA_CTL__READ_WRITE_ADDR__SHIFT));		\
+		} else {									\
+			*adev->vcn.inst[inst_idx].dpg_sram_curr_addr++ = offset;		\
+			*adev->vcn.inst[inst_idx].dpg_sram_curr_addr++ = value;			\
+		}										\
 	} while (0)
 
 enum engine_status_constants {
@@ -158,7 +167,6 @@ struct amdgpu_vcn_reg{
 	unsigned	ib_size;
 	unsigned	gp_scratch8;
 	unsigned	scratch9;
-	unsigned	jpeg_pitch;
 };
 
 struct amdgpu_vcn_inst {
@@ -168,9 +176,12 @@ struct amdgpu_vcn_inst {
 	void			*saved_bo;
 	struct amdgpu_ring	ring_dec;
 	struct amdgpu_ring	ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
-	struct amdgpu_ring	ring_jpeg;
 	struct amdgpu_irq_src	irq;
 	struct amdgpu_vcn_reg	external;
+	struct amdgpu_bo	*dpg_sram_bo;
+	void			*dpg_sram_cpu_addr;
+	uint64_t		dpg_sram_gpu_addr;
+	uint32_t		*dpg_sram_curr_addr;
 };
 
 struct amdgpu_vcn {
@@ -182,18 +193,18 @@ struct amdgpu_vcn {
 	struct dpg_pause_state pause_state;
 
 	bool			indirect_sram;
-	struct amdgpu_bo	*dpg_sram_bo;
-	void			*dpg_sram_cpu_addr;
-	uint64_t		dpg_sram_gpu_addr;
-	uint32_t		*dpg_sram_curr_addr;
 
 	uint8_t	num_vcn_inst;
-	struct amdgpu_vcn_inst	inst[AMDGPU_MAX_VCN_INSTANCES];
-	struct amdgpu_vcn_reg	internal;
+	struct amdgpu_vcn_inst	 inst[AMDGPU_MAX_VCN_INSTANCES];
+	struct amdgpu_vcn_reg	 internal;
+	struct drm_gpu_scheduler *vcn_enc_sched[AMDGPU_MAX_VCN_ENC_RINGS];
+	struct drm_gpu_scheduler *vcn_dec_sched[AMDGPU_MAX_VCN_INSTANCES];
+	uint32_t		 num_vcn_enc_sched;
+	uint32_t		 num_vcn_dec_sched;
 
 	unsigned	harvest_config;
 	int (*pause_dpg_mode)(struct amdgpu_device *adev,
-		struct dpg_pause_state *new_state);
+		int inst_idx, struct dpg_pause_state *new_state);
 };
 
 int amdgpu_vcn_sw_init(struct amdgpu_device *adev);
@@ -209,7 +220,4 @@ int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring);
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
-int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring);
-int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout);
-
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index e32ae906d797..103033f96f13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -379,54 +379,3 @@ void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev)
 		}
 	}
 }
-
-static uint32_t parse_clk(char *buf, bool min)
-{
-        char *ptr = buf;
-        uint32_t clk = 0;
-
-        do {
-                ptr = strchr(ptr, ':');
-                if (!ptr)
-                        break;
-                ptr+=2;
-		if (kstrtou32(ptr, 10, &clk))
-			return 0;
-        } while (!min);
-
-        return clk * 100;
-}
-
-uint32_t amdgpu_virt_get_sclk(struct amdgpu_device *adev, bool lowest)
-{
-	char *buf = NULL;
-	uint32_t clk = 0;
-
-	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	adev->virt.ops->get_pp_clk(adev, PP_SCLK, buf);
-	clk = parse_clk(buf, lowest);
-
-	kfree(buf);
-
-	return clk;
-}
-
-uint32_t amdgpu_virt_get_mclk(struct amdgpu_device *adev, bool lowest)
-{
-	char *buf = NULL;
-	uint32_t clk = 0;
-
-	buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	adev->virt.ops->get_pp_clk(adev, PP_MCLK, buf);
-	clk = parse_clk(buf, lowest);
-
-	kfree(buf);
-
-	return clk;
-}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b0b2bdc750df..4d1ac7612967 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -57,8 +57,6 @@ struct amdgpu_virt_ops {
 	int (*reset_gpu)(struct amdgpu_device *adev);
 	int (*wait_reset)(struct amdgpu_device *adev);
 	void (*trans_msg)(struct amdgpu_device *adev, u32 req, u32 data1, u32 data2, u32 data3);
-	int (*get_pp_clk)(struct amdgpu_device *adev, u32 type, char *buf);
-	int (*force_dpm_level)(struct amdgpu_device *adev, u32 level);
 };
 
 /*
@@ -85,8 +83,8 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_GIM_LOAD_UCODES   = 0x2,
 	/* VRAM LOST by GIM */
 	AMDGIM_FEATURE_GIM_FLR_VRAMLOST = 0x4,
-	/* HW PERF SIM in GIM */
-	AMDGIM_FEATURE_HW_PERF_SIMULATION = (1 << 3),
+	/* PP ONE VF MODE in GIM */
+	AMDGIM_FEATURE_PP_ONE_VF = (1 << 4),
 };
 
 struct amd_sriov_msg_pf2vf_info_header {
@@ -257,8 +255,6 @@ struct amdgpu_virt {
 	struct amdgpu_vf_error_buffer   vf_errors;
 	struct amdgpu_virt_fw_reserve	fw_reserve;
 	uint32_t gim_feature;
-	/* protect DPM events to GIM */
-	struct mutex                    dpm_mutex;
 	uint32_t reg_access_mode;
 };
 
@@ -286,8 +282,8 @@ static inline bool is_virtual_machine(void)
 #endif
 }
 
-#define amdgim_is_hwperf(adev) \
-	((adev)->virt.gim_feature & AMDGIM_FEATURE_HW_PERF_SIMULATION)
+#define amdgpu_sriov_is_pp_one_vf(adev) \
+	((adev)->virt.gim_feature & AMDGIM_FEATURE_PP_ONE_VF)
 
 bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev);
 void amdgpu_virt_init_setting(struct amdgpu_device *adev);
@@ -306,6 +302,4 @@ int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
 					unsigned int key,
 					unsigned int chksum);
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
-uint32_t amdgpu_virt_get_sclk(struct amdgpu_device *adev, bool lowest);
-uint32_t amdgpu_virt_get_mclk(struct amdgpu_device *adev, bool lowest);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 598c24505c73..d16231d6a790 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -83,6 +83,32 @@ struct amdgpu_prt_cb {
 };
 
 /**
+ * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS
+ * happens while holding this lock anywhere to prevent deadlocks when
+ * an MMU notifier runs in reclaim-FS context.
+ */
+static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm)
+{
+	mutex_lock(&vm->eviction_lock);
+	vm->saved_flags = memalloc_nofs_save();
+}
+
+static inline int amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm)
+{
+	if (mutex_trylock(&vm->eviction_lock)) {
+		vm->saved_flags = memalloc_nofs_save();
+		return 1;
+	}
+	return 0;
+}
+
+static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm)
+{
+	memalloc_nofs_restore(vm->saved_flags);
+	mutex_unlock(&vm->eviction_lock);
+}
+
+/**
  * amdgpu_vm_level_shift - return the addr shift for each level
  *
  * @adev: amdgpu_device pointer
@@ -562,8 +588,8 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 {
 	entry->priority = 0;
 	entry->tv.bo = &vm->root.base.bo->tbo;
-	/* One for the VM updates, one for TTM and one for the CS job */
-	entry->tv.num_shared = 3;
+	/* One for TTM and one for the CS job */
+	entry->tv.num_shared = 2;
 	entry->user_pages = NULL;
 	list_add(&entry->tv.head, validated);
 }
@@ -656,7 +682,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      void *param)
 {
 	struct amdgpu_vm_bo_base *bo_base, *tmp;
-	int r = 0;
+	int r;
 
 	vm->bulk_moveable &= list_empty(&vm->evicted);
 
@@ -665,7 +691,7 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 		r = validate(param, bo);
 		if (r)
-			break;
+			return r;
 
 		if (bo->tbo.type != ttm_bo_type_kernel) {
 			amdgpu_vm_bo_moved(bo_base);
@@ -678,7 +704,11 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		}
 	}
 
-	return r;
+	amdgpu_vm_eviction_lock(vm);
+	vm->evicting = false;
+	amdgpu_vm_eviction_unlock(vm);
+
+	return 0;
 }
 
 /**
@@ -1555,15 +1585,25 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	if (!(flags & AMDGPU_PTE_VALID))
 		owner = AMDGPU_FENCE_OWNER_KFD;
 
+	amdgpu_vm_eviction_lock(vm);
+	if (vm->evicting) {
+		r = -EBUSY;
+		goto error_unlock;
+	}
+
 	r = vm->update_funcs->prepare(&params, owner, exclusive);
 	if (r)
-		return r;
+		goto error_unlock;
 
 	r = amdgpu_vm_update_ptes(&params, start, last + 1, addr, flags);
 	if (r)
-		return r;
+		goto error_unlock;
+
+	r = vm->update_funcs->commit(&params, fence);
 
-	return vm->update_funcs->commit(&params, fence);
+error_unlock:
+	amdgpu_vm_eviction_unlock(vm);
+	return r;
 }
 
 /**
@@ -2500,6 +2540,41 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 }
 
 /**
+ * amdgpu_vm_evictable - check if we can evict a VM
+ *
+ * @bo: A page table of the VM.
+ *
+ * Check if it is possible to evict a VM.
+ */
+bool amdgpu_vm_evictable(struct amdgpu_bo *bo)
+{
+	struct amdgpu_vm_bo_base *bo_base = bo->vm_bo;
+
+	/* Page tables of a destroyed VM can go away immediately */
+	if (!bo_base || !bo_base->vm)
+		return true;
+
+	/* Don't evict VM page tables while they are busy */
+	if (!dma_resv_test_signaled_rcu(bo->tbo.base.resv, true))
+		return false;
+
+	/* Try to block ongoing updates */
+	if (!amdgpu_vm_eviction_trylock(bo_base->vm))
+		return false;
+
+	/* Don't evict VM page tables while they are updated */
+	if (!dma_fence_is_signaled(bo_base->vm->last_direct) ||
+	    !dma_fence_is_signaled(bo_base->vm->last_delayed)) {
+		amdgpu_vm_eviction_unlock(bo_base->vm);
+		return false;
+	}
+
+	bo_base->vm->evicting = true;
+	amdgpu_vm_eviction_unlock(bo_base->vm);
+	return true;
+}
+
+/**
  * amdgpu_vm_bo_invalidate - mark the bo as invalid
  *
  * @adev: amdgpu_device pointer
@@ -2661,8 +2736,16 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size,
  */
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
 {
-	return dma_resv_wait_timeout_rcu(vm->root.base.bo->tbo.base.resv,
-						   true, true, timeout);
+	timeout = dma_resv_wait_timeout_rcu(vm->root.base.bo->tbo.base.resv,
+					    true, true, timeout);
+	if (timeout <= 0)
+		return timeout;
+
+	timeout = dma_fence_wait_timeout(vm->last_direct, true, timeout);
+	if (timeout <= 0)
+		return timeout;
+
+	return dma_fence_wait_timeout(vm->last_delayed, true, timeout);
 }
 
 /**
@@ -2696,18 +2779,22 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	spin_lock_init(&vm->invalidated_lock);
 	INIT_LIST_HEAD(&vm->freed);
 
+
 	/* create scheduler entities for page table updates */
-	r = drm_sched_entity_init(&vm->direct, adev->vm_manager.vm_pte_rqs,
-				  adev->vm_manager.vm_pte_num_rqs, NULL);
+	r = drm_sched_entity_init(&vm->direct, DRM_SCHED_PRIORITY_NORMAL,
+				  adev->vm_manager.vm_pte_scheds,
+				  adev->vm_manager.vm_pte_num_scheds, NULL);
 	if (r)
 		return r;
 
-	r = drm_sched_entity_init(&vm->delayed, adev->vm_manager.vm_pte_rqs,
-				  adev->vm_manager.vm_pte_num_rqs, NULL);
+	r = drm_sched_entity_init(&vm->delayed, DRM_SCHED_PRIORITY_NORMAL,
+				  adev->vm_manager.vm_pte_scheds,
+				  adev->vm_manager.vm_pte_num_scheds, NULL);
 	if (r)
 		goto error_free_direct;
 
 	vm->pte_support_ats = false;
+	vm->is_compute_context = false;
 
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) {
 		vm->use_cpu_for_update = !!(adev->vm_manager.vm_update_mode &
@@ -2730,6 +2817,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	else
 		vm->update_funcs = &amdgpu_vm_sdma_funcs;
 	vm->last_update = NULL;
+	vm->last_direct = dma_fence_get_stub();
+	vm->last_delayed = dma_fence_get_stub();
+
+	mutex_init(&vm->eviction_lock);
+	vm->evicting = false;
 
 	amdgpu_vm_bo_param(adev, vm, adev->vm_manager.root_level, false, &bp);
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE)
@@ -2780,6 +2872,8 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_delayed:
+	dma_fence_put(vm->last_direct);
+	dma_fence_put(vm->last_delayed);
 	drm_sched_entity_destroy(&vm->delayed);
 
 error_free_direct:
@@ -2893,6 +2987,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		vm->update_funcs = &amdgpu_vm_sdma_funcs;
 	dma_fence_put(vm->last_update);
 	vm->last_update = NULL;
+	vm->is_compute_context = true;
 
 	if (vm->pasid) {
 		unsigned long flags;
@@ -2947,6 +3042,7 @@ void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 	vm->pasid = 0;
+	vm->is_compute_context = false;
 }
 
 /**
@@ -2978,6 +3074,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		vm->pasid = 0;
 	}
 
+	dma_fence_wait(vm->last_direct, false);
+	dma_fence_put(vm->last_direct);
+	dma_fence_wait(vm->last_delayed, false);
+	dma_fence_put(vm->last_delayed);
+
 	list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
 		if (mapping->flags & AMDGPU_PTE_PRT && prt_fini_needed) {
 			amdgpu_vm_prt_fini(adev, vm);
@@ -3194,11 +3295,20 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
 	flags = AMDGPU_PTE_VALID | AMDGPU_PTE_SNOOPED |
 		AMDGPU_PTE_SYSTEM;
 
-	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
+	if (vm->is_compute_context) {
+		/* Intentionally setting invalid PTE flag
+		 * combination to force a no-retry-fault
+		 */
+		flags = AMDGPU_PTE_EXECUTABLE | AMDGPU_PDE_PTE |
+			AMDGPU_PTE_TF;
+		value = 0;
+
+	} else if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
 		/* Redirect the access to the dummy page */
 		value = adev->dummy_page_addr;
 		flags |= AMDGPU_PTE_EXECUTABLE | AMDGPU_PTE_READABLE |
 			AMDGPU_PTE_WRITEABLE;
+
 	} else {
 		/* Let the hw retry silently on the PTE */
 		value = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 4dbbe1b6b413..b4640ab38c95 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -30,6 +30,7 @@
 #include <drm/gpu_scheduler.h>
 #include <drm/drm_file.h>
 #include <drm/ttm/ttm_bo_driver.h>
+#include <linux/sched/mm.h>
 
 #include "amdgpu_sync.h"
 #include "amdgpu_ring.h"
@@ -239,6 +240,13 @@ struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
 	struct rb_root_cached	va;
 
+	/* Lock to prevent eviction while we are updating page tables
+	 * use vm_eviction_lock/unlock(vm)
+	 */
+	struct mutex		eviction_lock;
+	bool			evicting;
+	unsigned int		saved_flags;
+
 	/* BOs who needs a validation */
 	struct list_head	evicted;
 
@@ -266,6 +274,10 @@ struct amdgpu_vm {
 	struct drm_sched_entity	direct;
 	struct drm_sched_entity	delayed;
 
+	/* Last submission to the scheduler entities */
+	struct dma_fence	*last_direct;
+	struct dma_fence	*last_delayed;
+
 	unsigned int		pasid;
 	/* dedicated to vm */
 	struct amdgpu_vmid	*reserved_vmid[AMDGPU_MAX_VMHUBS];
@@ -298,6 +310,8 @@ struct amdgpu_vm {
 	struct ttm_lru_bulk_move lru_bulk_move;
 	/* mark whether can do the bulk move */
 	bool			bulk_moveable;
+	/* Flag to indicate if VM is used for compute */
+	bool			is_compute_context;
 };
 
 struct amdgpu_vm_manager {
@@ -317,8 +331,8 @@ struct amdgpu_vm_manager {
 	u64					vram_base_offset;
 	/* vm pte handling */
 	const struct amdgpu_vm_pte_funcs	*vm_pte_funcs;
-	struct drm_sched_rq			*vm_pte_rqs[AMDGPU_MAX_RINGS];
-	unsigned				vm_pte_num_rqs;
+	struct drm_gpu_scheduler		*vm_pte_scheds[AMDGPU_MAX_RINGS];
+	unsigned				vm_pte_num_scheds;
 	struct amdgpu_ring			*page_fault;
 
 	/* partial resident texture handling */
@@ -376,6 +390,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
 			bool clear);
+bool amdgpu_vm_evictable(struct amdgpu_bo *bo);
 void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 			     struct amdgpu_bo *bo, bool evicted);
 uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 832db59f441e..19b7f80758f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -71,7 +71,7 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
 	p->num_dw_left = ndw;
 
 	/* Wait for moves to be completed */
-	r = amdgpu_sync_fence(p->adev, &p->job->sync, exclusive, false);
+	r = amdgpu_sync_fence(&p->job->sync, exclusive, false);
 	if (r)
 		return r;
 
@@ -95,11 +95,10 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
 static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 				 struct dma_fence **fence)
 {
-	struct amdgpu_bo *root = p->vm->root.base.bo;
 	struct amdgpu_ib *ib = p->job->ibs;
 	struct drm_sched_entity *entity;
+	struct dma_fence *f, *tmp;
 	struct amdgpu_ring *ring;
-	struct dma_fence *f;
 	int r;
 
 	entity = p->direct ? &p->vm->direct : &p->vm->delayed;
@@ -112,7 +111,13 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 	if (r)
 		goto error;
 
-	amdgpu_bo_fence(root, f, true);
+	tmp = dma_fence_get(f);
+	if (p->direct)
+		swap(p->vm->last_direct, tmp);
+	else
+		swap(p->vm->last_delayed, tmp);
+	dma_fence_put(tmp);
+
 	if (fence && !p->direct)
 		swap(*fence, f);
 	dma_fence_put(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 61d13d8b7b20..a97af422575a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -146,16 +146,16 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev,
 	ficaa_pie_ctl_in = AMDGPU_XGMI_SET_FICAA(0x200);
 	ficaa_pie_status_in = AMDGPU_XGMI_SET_FICAA(0x208);
 
-	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_ctl_in);
+	fica_out = adev->df.funcs->get_fica(adev, ficaa_pie_ctl_in);
 	if (fica_out != 0x1f)
 		pr_err("xGMI error counters not enabled!\n");
 
-	fica_out = adev->df_funcs->get_fica(adev, ficaa_pie_status_in);
+	fica_out = adev->df.funcs->get_fica(adev, ficaa_pie_status_in);
 
 	if ((fica_out & 0xffff) == 2)
 		error_count = ((fica_out >> 62) & 0x1) + (fica_out >> 63);
 
-	adev->df_funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);
+	adev->df.funcs->set_fica(adev, ficaa_pie_status_in, 0, 0);
 
 	return snprintf(buf, PAGE_SIZE, "%d\n", error_count);
 }
@@ -261,6 +261,7 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lo
 	INIT_LIST_HEAD(&tmp->device_list);
 	mutex_init(&tmp->hive_lock);
 	mutex_init(&tmp->reset_lock);
+	task_barrier_init(&tmp->tb);
 
 	if (lock)
 		mutex_lock(&tmp->hive_lock);
@@ -290,13 +291,7 @@ int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 
 	dev_dbg(adev->dev, "Set xgmi pstate %d.\n", pstate);
 
-	if (is_support_sw_smu_xgmi(adev))
-		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
-	else if (adev->powerplay.pp_funcs &&
-		 adev->powerplay.pp_funcs->set_xgmi_pstate)
-		ret = adev->powerplay.pp_funcs->set_xgmi_pstate(adev->powerplay.pp_handle,
-								pstate);
-
+	ret = amdgpu_dpm_set_xgmi_pstate(adev, pstate);
 	if (ret) {
 		dev_err(adev->dev,
 			"XGMI: Set pstate failure on device %llx, hive %llx, ret %d",
@@ -408,6 +403,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 	top_info->num_nodes = count;
 	hive->number_devices = count;
 
+	task_barrier_add_task(&hive->tb);
+
 	if (amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_PSP)) {
 		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
 			/* update node list for other device in the hive */
@@ -470,6 +467,7 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		mutex_destroy(&hive->hive_lock);
 		mutex_destroy(&hive->reset_lock);
 	} else {
+		task_barrier_rem_task(&hive->tb);
 		amdgpu_xgmi_sysfs_rem_dev_info(adev, hive);
 		mutex_unlock(&hive->hive_lock);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index bbf504ff7051..74011fbc2251 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -22,6 +22,7 @@
 #ifndef __AMDGPU_XGMI_H__
 #define __AMDGPU_XGMI_H__
 
+#include <drm/task_barrier.h>
 #include "amdgpu_psp.h"
 
 struct amdgpu_hive_info {
@@ -33,6 +34,7 @@ struct amdgpu_hive_info {
 	struct device_attribute dev_attr;
 	struct amdgpu_device *adev;
 	int pstate; /*0 -- low , 1 -- high , -1 unknown*/
+	struct task_barrier tb;
 };
 
 struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
index 6858cde9fc5d..ea702a64f807 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_dp.c
@@ -361,7 +361,6 @@ int amdgpu_atombios_dp_get_panel_mode(struct drm_encoder *encoder,
 			       struct drm_connector *connector)
 {
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
-	struct amdgpu_connector_atom_dig *dig_connector;
 	int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
 	u16 dp_bridge = amdgpu_connector_encoder_get_dp_bridge_encoder_id(connector);
 	u8 tmp;
@@ -369,8 +368,6 @@ int amdgpu_atombios_dp_get_panel_mode(struct drm_encoder *encoder,
 	if (!amdgpu_connector->con_priv)
 		return panel_mode;
 
-	dig_connector = amdgpu_connector->con_priv;
-
 	if (dp_bridge != ENCODER_OBJECT_ID_NONE) {
 		/* DP bridge chips */
 		if (drm_dp_dpcd_readb(&amdgpu_connector->ddc_bus->aux,
@@ -713,7 +710,6 @@ void amdgpu_atombios_dp_link_train(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
-	struct amdgpu_encoder_atom_dig *dig;
 	struct amdgpu_connector *amdgpu_connector;
 	struct amdgpu_connector_atom_dig *dig_connector;
 	struct amdgpu_atombios_dp_link_train_info dp_info;
@@ -721,7 +717,6 @@ void amdgpu_atombios_dp_link_train(struct drm_encoder *encoder,
 
 	if (!amdgpu_encoder->enc_priv)
 		return;
-	dig = amdgpu_encoder->enc_priv;
 
 	amdgpu_connector = to_amdgpu_connector(connector);
 	if (!amdgpu_connector->con_priv)
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
index 980c363b1a0a..b4cc7c55fa16 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c
@@ -76,11 +76,6 @@ static int amdgpu_atombios_i2c_process_i2c_ch(struct amdgpu_i2c_chan *chan,
 		}
 		args.lpI2CDataOut = cpu_to_le16(out);
 	} else {
-		if (num > ATOM_MAX_HW_I2C_READ) {
-			DRM_ERROR("hw i2c: tried to read too many bytes (%d vs 255)\n", num);
-			r = -EINVAL;
-			goto done;
-		}
 		args.ucRegIndex = 0;
 		args.lpI2CDataOut = 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 1befdee9f0f1..006f21ef7ddf 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1310,6 +1310,17 @@ static int cik_asic_pci_config_reset(struct amdgpu_device *adev)
 	return r;
 }
 
+static bool cik_asic_supports_baco(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+		return amdgpu_dpm_is_baco_supported(adev);
+	default:
+		return false;
+	}
+}
+
 static enum amd_reset_method
 cik_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -1349,7 +1360,7 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
-		r = smu7_asic_baco_reset(adev);
+		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = cik_asic_pci_config_reset(adev);
 	}
@@ -1927,6 +1938,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs =
 	.get_pcie_usage = &cik_get_pcie_usage,
 	.need_reset_on_init = &cik_need_reset_on_init,
 	.get_pcie_replay_count = &cik_get_pcie_replay_count,
+	.supports_baco = &cik_asic_supports_baco,
 };
 
 static int cik_common_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.h b/drivers/gpu/drm/amd/amdgpu/cik.h
index 9870bf27870e..f91ab4c246b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.h
+++ b/drivers/gpu/drm/amd/amdgpu/cik.h
@@ -31,7 +31,5 @@ void cik_srbm_select(struct amdgpu_device *adev,
 int cik_set_ip_blocks(struct amdgpu_device *adev);
 
 void legacy_doorbell_index_init(struct amdgpu_device *adev);
-int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap);
-int smu7_asic_baco_reset(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index c45304f1047c..580d3f93d670 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -228,7 +228,7 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
 	u32 extra_bits = vmid & 0xf;
 
 	/* IB packet must end on a 8 DW boundary */
-	cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	cik_sdma_ring_insert_nop(ring, (4 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
 	amdgpu_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
@@ -811,7 +811,7 @@ static void cik_sdma_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1372,16 +1372,14 @@ static const struct amdgpu_vm_pte_funcs cik_sdma_vm_pte_funcs = {
 
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			&adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version cik_sdma_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
index d6221298b477..d6aca1c08068 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
@@ -31,6 +31,9 @@ static u32 df_v1_7_channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
 
 static void df_v1_7_sw_init(struct amdgpu_device *adev)
 {
+	adev->df.hash_status.hash_64k = false;
+	adev->df.hash_status.hash_2m = false;
+	adev->df.hash_status.hash_1g = false;
 }
 
 static void df_v1_7_sw_fini(struct amdgpu_device *adev)
@@ -66,7 +69,7 @@ static u32 df_v1_7_get_hbm_channel_number(struct amdgpu_device *adev)
 {
 	int fb_channel_number;
 
-	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
+	fb_channel_number = adev->df.funcs->get_fb_channel_number(adev);
 
 	return df_v1_7_channel_number[fb_channel_number];
 }
@@ -77,7 +80,7 @@ static void df_v1_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 	u32 tmp;
 
 	/* Put DF on broadcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, true);
+	adev->df.funcs->enable_broadcast_mode(adev, true);
 
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG)) {
 		tmp = RREG32_SOC15(DF, 0, mmDF_PIE_AON0_DfGlobalClkGater);
@@ -92,7 +95,7 @@ static void df_v1_7_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 	}
 
 	/* Exit boradcast mode */
-	adev->df_funcs->enable_broadcast_mode(adev, false);
+	adev->df.funcs->enable_broadcast_mode(adev, false);
 }
 
 static void df_v1_7_get_clockgating_state(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 4043ebcea5de..f51326598a8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -183,6 +183,61 @@ static void df_v3_6_perfmon_wreg(struct amdgpu_device *adev, uint32_t lo_addr,
 	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
 }
 
+/* same as perfmon_wreg but return status on write value check */
+static int df_v3_6_perfmon_arm_with_status(struct amdgpu_device *adev,
+					  uint32_t lo_addr, uint32_t lo_val,
+					  uint32_t hi_addr, uint32_t  hi_val)
+{
+	unsigned long flags, address, data;
+	uint32_t lo_val_rb, hi_val_rb;
+
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
+
+	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
+	WREG32(address, lo_addr);
+	WREG32(data, lo_val);
+	WREG32(address, hi_addr);
+	WREG32(data, hi_val);
+
+	WREG32(address, lo_addr);
+	lo_val_rb = RREG32(data);
+	WREG32(address, hi_addr);
+	hi_val_rb = RREG32(data);
+	spin_unlock_irqrestore(&adev->pcie_idx_lock, flags);
+
+	if (!(lo_val == lo_val_rb && hi_val == hi_val_rb))
+		return -EBUSY;
+
+	return 0;
+}
+
+
+/*
+ * retry arming counters every 100 usecs within 1 millisecond interval.
+ * if retry fails after time out, return error.
+ */
+#define ARM_RETRY_USEC_TIMEOUT	1000
+#define ARM_RETRY_USEC_INTERVAL	100
+static int df_v3_6_perfmon_arm_with_retry(struct amdgpu_device *adev,
+					  uint32_t lo_addr, uint32_t lo_val,
+					  uint32_t hi_addr, uint32_t  hi_val)
+{
+	int countdown = ARM_RETRY_USEC_TIMEOUT;
+
+	while (countdown) {
+
+		if (!df_v3_6_perfmon_arm_with_status(adev, lo_addr, lo_val,
+						     hi_addr, hi_val))
+			break;
+
+		countdown -= ARM_RETRY_USEC_INTERVAL;
+		udelay(ARM_RETRY_USEC_INTERVAL);
+	}
+
+	return countdown > 0 ? 0 : -ETIME;
+}
+
 /* get the number of df counters available */
 static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
 		struct device_attribute *attr,
@@ -207,6 +262,32 @@ static ssize_t df_v3_6_get_df_cntr_avail(struct device *dev,
 /* device attr for available perfmon counters */
 static DEVICE_ATTR(df_cntr_avail, S_IRUGO, df_v3_6_get_df_cntr_avail, NULL);
 
+static void df_v3_6_query_hashes(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	adev->df.hash_status.hash_64k = false;
+	adev->df.hash_status.hash_2m = false;
+	adev->df.hash_status.hash_1g = false;
+
+	if (adev->asic_type != CHIP_ARCTURUS)
+		return;
+
+	/* encoding for hash-enabled on Arcturus */
+	if (adev->df.funcs->get_fb_channel_number(adev) == 0xe) {
+		tmp = RREG32_SOC15(DF, 0, mmDF_CS_UMC_AON0_DfGlobalCtrl);
+		adev->df.hash_status.hash_64k = REG_GET_FIELD(tmp,
+						DF_CS_UMC_AON0_DfGlobalCtrl,
+						GlbHashIntlvCtl64K);
+		adev->df.hash_status.hash_2m = REG_GET_FIELD(tmp,
+						DF_CS_UMC_AON0_DfGlobalCtrl,
+						GlbHashIntlvCtl2M);
+		adev->df.hash_status.hash_1g = REG_GET_FIELD(tmp,
+						DF_CS_UMC_AON0_DfGlobalCtrl,
+						GlbHashIntlvCtl1G);
+	}
+}
+
 /* init perfmons */
 static void df_v3_6_sw_init(struct amdgpu_device *adev)
 {
@@ -218,6 +299,8 @@ static void df_v3_6_sw_init(struct amdgpu_device *adev)
 
 	for (i = 0; i < AMDGPU_MAX_DF_PERFMONS; i++)
 		adev->df_perfmon_config_assign_mask[i] = 0;
+
+	df_v3_6_query_hashes(adev);
 }
 
 static void df_v3_6_sw_fini(struct amdgpu_device *adev)
@@ -256,7 +339,7 @@ static u32 df_v3_6_get_hbm_channel_number(struct amdgpu_device *adev)
 {
 	int fb_channel_number;
 
-	fb_channel_number = adev->df_funcs->get_fb_channel_number(adev);
+	fb_channel_number = adev->df.funcs->get_fb_channel_number(adev);
 	if (fb_channel_number >= ARRAY_SIZE(df_v3_6_channel_number))
 		fb_channel_number = 0;
 
@@ -270,7 +353,7 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 
 	if (adev->cg_flags & AMD_CG_SUPPORT_DF_MGCG) {
 		/* Put DF on broadcast mode */
-		adev->df_funcs->enable_broadcast_mode(adev, true);
+		adev->df.funcs->enable_broadcast_mode(adev, true);
 
 		if (enable) {
 			tmp = RREG32_SOC15(DF, 0,
@@ -289,7 +372,7 @@ static void df_v3_6_update_medium_grain_clock_gating(struct amdgpu_device *adev,
 		}
 
 		/* Exit broadcast mode */
-		adev->df_funcs->enable_broadcast_mode(adev, false);
+		adev->df.funcs->enable_broadcast_mode(adev, false);
 	}
 }
 
@@ -334,20 +417,20 @@ static void df_v3_6_pmc_get_addr(struct amdgpu_device *adev,
 	switch (target_cntr) {
 
 	case 0:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo0 : smnPerfMonCtrLo0;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi0 : smnPerfMonCtrHi0;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo4 : smnPerfMonCtrLo4;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi4 : smnPerfMonCtrHi4;
 		break;
 	case 1:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo1 : smnPerfMonCtrLo1;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi1 : smnPerfMonCtrHi1;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo5 : smnPerfMonCtrLo5;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi5 : smnPerfMonCtrHi5;
 		break;
 	case 2:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo2 : smnPerfMonCtrLo2;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi2 : smnPerfMonCtrHi2;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo6 : smnPerfMonCtrLo6;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi6 : smnPerfMonCtrHi6;
 		break;
 	case 3:
-		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo3 : smnPerfMonCtrLo3;
-		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi3 : smnPerfMonCtrHi3;
+		*lo_base_addr = is_ctrl ? smnPerfMonCtlLo7 : smnPerfMonCtrLo7;
+		*hi_base_addr = is_ctrl ? smnPerfMonCtlHi7 : smnPerfMonCtrHi7;
 		break;
 
 	}
@@ -422,6 +505,44 @@ static int df_v3_6_pmc_add_cntr(struct amdgpu_device *adev,
 	return -ENOSPC;
 }
 
+#define DEFERRED_ARM_MASK	(1 << 31)
+static int df_v3_6_pmc_set_deferred(struct amdgpu_device *adev,
+				    uint64_t config, bool is_deferred)
+{
+	int target_cntr;
+
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
+
+	if (target_cntr < 0)
+		return -EINVAL;
+
+	if (is_deferred)
+		adev->df_perfmon_config_assign_mask[target_cntr] |=
+							DEFERRED_ARM_MASK;
+	else
+		adev->df_perfmon_config_assign_mask[target_cntr] &=
+							~DEFERRED_ARM_MASK;
+
+	return 0;
+}
+
+static bool df_v3_6_pmc_is_deferred(struct amdgpu_device *adev,
+				    uint64_t config)
+{
+	int target_cntr;
+
+	target_cntr = df_v3_6_pmc_config_2_cntr(adev, config);
+
+	/*
+	 * we never get target_cntr < 0 since this funciton is only called in
+	 * pmc_count for now but we should check anyways.
+	 */
+	return (target_cntr >= 0 &&
+			(adev->df_perfmon_config_assign_mask[target_cntr]
+			& DEFERRED_ARM_MASK));
+
+}
+
 /* release performance counter */
 static void df_v3_6_pmc_release_cntr(struct amdgpu_device *adev,
 				     uint64_t config)
@@ -451,29 +572,33 @@ static int df_v3_6_pmc_start(struct amdgpu_device *adev, uint64_t config,
 			     int is_enable)
 {
 	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
-	int ret = 0;
+	int err = 0, ret = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+		if (is_enable)
+			return df_v3_6_pmc_add_cntr(adev, config);
 
 		df_v3_6_reset_perfmon_cntr(adev, config);
 
-		if (is_enable) {
-			ret = df_v3_6_pmc_add_cntr(adev, config);
-		} else {
-			ret = df_v3_6_pmc_get_ctrl_settings(adev,
+		ret = df_v3_6_pmc_get_ctrl_settings(adev,
 					config,
 					&lo_base_addr,
 					&hi_base_addr,
 					&lo_val,
 					&hi_val);
 
-			if (ret)
-				return ret;
+		if (ret)
+			return ret;
 
-			df_v3_6_perfmon_wreg(adev, lo_base_addr, lo_val,
-					hi_base_addr, hi_val);
-		}
+		err = df_v3_6_perfmon_arm_with_retry(adev,
+						     lo_base_addr,
+						     lo_val,
+						     hi_base_addr,
+						     hi_val);
+
+		if (err)
+			ret = df_v3_6_pmc_set_deferred(adev, config, true);
 
 		break;
 	default:
@@ -501,7 +626,7 @@ static int df_v3_6_pmc_stop(struct amdgpu_device *adev, uint64_t config,
 		if (ret)
 			return ret;
 
-		df_v3_6_perfmon_wreg(adev, lo_base_addr, 0, hi_base_addr, 0);
+		df_v3_6_reset_perfmon_cntr(adev, config);
 
 		if (is_disable)
 			df_v3_6_pmc_release_cntr(adev, config);
@@ -518,18 +643,29 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 				  uint64_t config,
 				  uint64_t *count)
 {
-	uint32_t lo_base_addr, hi_base_addr, lo_val, hi_val;
+	uint32_t lo_base_addr, hi_base_addr, lo_val = 0, hi_val = 0;
 	*count = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
-
 		df_v3_6_pmc_get_read_settings(adev, config, &lo_base_addr,
 				      &hi_base_addr);
 
 		if ((lo_base_addr == 0) || (hi_base_addr == 0))
 			return;
 
+		/* rearm the counter or throw away count value on failure */
+		if (df_v3_6_pmc_is_deferred(adev, config)) {
+			int rearm_err = df_v3_6_perfmon_arm_with_status(adev,
+							lo_base_addr, lo_val,
+							hi_base_addr, hi_val);
+
+			if (rearm_err)
+				return;
+
+			df_v3_6_pmc_set_deferred(adev, config, false);
+		}
+
 		df_v3_6_perfmon_rreg(adev, lo_base_addr, &lo_val,
 				hi_base_addr, &hi_val);
 
@@ -542,7 +678,6 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 			 config, lo_base_addr, hi_base_addr, lo_val, hi_val);
 
 		break;
-
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ba9e53a1abc3..874f641de281 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -40,6 +40,7 @@
 #include "ivsrcid/gfx/irqsrcs_gfx_10_1.h"
 
 #include "soc15.h"
+#include "soc15d.h"
 #include "soc15_common.h"
 #include "clearstate_gfx10.h"
 #include "v10_structs.h"
@@ -50,9 +51,6 @@
  * Navi10 has two graphic rings to share each graphic pipe.
  * 1. Primary ring
  * 2. Async ring
- *
- * In bring-up phase, it just used primary ring so set gfx ring number as 1 at
- * first.
  */
 #define GFX10_NUM_GFX_RINGS	2
 #define GFX10_MEC_HPD_SIZE	2048
@@ -123,7 +121,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000800, 0x00000820),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL, 0x001f0000, 0x00070104),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x001f0000, 0x00070104),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000100, 0x00000130),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
@@ -171,7 +169,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0x00000800, 0x00000820),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_SPARE, 0xffffffff, 0xffff3101),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL, 0x001f0000, 0x00070105),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x001f0000, 0x00070105),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ALU_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_ARB_CONFIG, 0x00000133, 0x00000130),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
@@ -348,15 +346,29 @@ static void gfx10_kiq_query_status(struct amdgpu_ring *kiq_ring,
 	amdgpu_ring_write(kiq_ring, upper_32_bits(seq));
 }
 
+static void gfx10_kiq_invalidate_tlbs(struct amdgpu_ring *kiq_ring,
+				uint16_t pasid, uint32_t flush_type,
+				bool all_hub)
+{
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
+			PACKET3_INVALIDATE_TLBS_ALL_HUB(all_hub) |
+			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
+			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(flush_type));
+}
+
 static const struct kiq_pm4_funcs gfx_v10_0_kiq_pm4_funcs = {
 	.kiq_set_resources = gfx10_kiq_set_resources,
 	.kiq_map_queues = gfx10_kiq_map_queues,
 	.kiq_unmap_queues = gfx10_kiq_unmap_queues,
 	.kiq_query_status = gfx10_kiq_query_status,
+	.kiq_invalidate_tlbs = gfx10_kiq_invalidate_tlbs,
 	.set_resources_size = 8,
 	.map_queues_size = 7,
 	.unmap_queues_size = 6,
 	.query_status_size = 7,
+	.invalidate_tlbs_size = 12,
 };
 
 static void gfx_v10_0_set_kiq_pm4_funcs(struct amdgpu_device *adev)
@@ -474,18 +486,10 @@ static int gfx_v10_0_ring_test_ring(struct amdgpu_ring *ring)
 		else
 			udelay(1);
 	}
-	if (i < adev->usec_timeout) {
-		if (amdgpu_emu_mode == 1)
-			DRM_INFO("ring test on %d succeeded in %d msecs\n",
-				 ring->idx, i);
-		else
-			DRM_INFO("ring test on %d succeeded in %d usecs\n",
-				 ring->idx, i);
-	} else {
-		DRM_ERROR("amdgpu: ring %d test failed (scratch(0x%04X)=0x%08X)\n",
-			  ring->idx, scratch, tmp);
-		r = -EINVAL;
-	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
 	amdgpu_gfx_scratch_free(adev, scratch);
 
 	return r;
@@ -535,14 +539,10 @@ static int gfx_v10_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	}
 
 	tmp = RREG32(scratch);
-	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+	if (tmp == 0xDEADBEEF)
 		r = 0;
-	} else {
-		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
-			  scratch, tmp);
+	else
 		r = -EINVAL;
-	}
 err2:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
@@ -591,8 +591,7 @@ static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
 	}
 
 	if (adev->gfx.cp_fw_write_wait == false)
-		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
-			      GRBM requires 1-cycle delay in cp firmware\n");
+		DRM_WARN_ONCE("CP firmware version too old, please update!");
 }
 
 
@@ -617,11 +616,29 @@ static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
 			le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
 }
 
+static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev)
+{
+	bool ret = false;
+
+	switch (adev->pdev->revision) {
+	case 0xc2:
+	case 0xc3:
+		ret = true;
+		break;
+	default:
+		ret = false;
+		break;
+	}
+
+	return ret ;
+}
+
 static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
-		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		if (!gfx_v10_0_navi10_gfxoff_should_enable(adev))
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		break;
 	default:
 		break;
@@ -805,10 +822,11 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_G];
 		info->ucode_id = AMDGPU_UCODE_ID_RLC_G;
 		info->fw = adev->gfx.rlc_fw;
-		header = (const struct common_firmware_header *)info->fw->data;
-		adev->firmware.fw_size +=
-			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
-
+		if (info->fw) {
+			header = (const struct common_firmware_header *)info->fw->data;
+			adev->firmware.fw_size +=
+				ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
+		}
 		if (adev->gfx.rlc.is_rlc_v2_1 &&
 		    adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
 		    adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
@@ -1948,7 +1966,7 @@ static int gfx_v10_0_parse_rlc_toc(struct amdgpu_device *adev)
 		rlc_autoload_info[rlc_toc->id].size = rlc_toc->size * 4;
 
 		rlc_toc++;
-	};
+	}
 
 	return 0;
 }
@@ -3319,8 +3337,11 @@ static int gfx_v10_0_compute_mqd_init(struct amdgpu_ring *ring)
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
-	/* activate the queue */
-	mqd->cp_hqd_active = 1;
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd->cp_hqd_active = 1;
 
 	return 0;
 }
@@ -3591,23 +3612,16 @@ static int gfx_v10_0_cp_resume(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
 		ring = &adev->gfx.gfx_ring[i];
-		DRM_INFO("gfx %d ring me %d pipe %d q %d\n",
-			 i, ring->me, ring->pipe, ring->queue);
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->sched.ready = false;
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
 			return r;
-		}
 	}
 
 	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
 		ring = &adev->gfx.compute_ring[i];
-		ring->sched.ready = true;
-		DRM_INFO("compute ring %d mec %d pipe %d q %d\n",
-			 i, ring->me, ring->pipe, ring->queue);
-		r = amdgpu_ring_test_ring(ring);
+		r = amdgpu_ring_test_helper(ring);
 		if (r)
-			ring->sched.ready = false;
+			return r;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index 7f0a63628c43..31f44d05e606 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -1576,7 +1576,7 @@ static void gfx_v6_0_config_init(struct amdgpu_device *adev)
 static void gfx_v6_0_constants_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config = 0;
-	u32 mc_shared_chmap, mc_arb_ramcfg;
+	u32 mc_arb_ramcfg;
 	u32 sx_debug_1;
 	u32 hdp_host_path_cntl;
 	u32 tmp;
@@ -1678,7 +1678,6 @@ static void gfx_v6_0_constants_init(struct amdgpu_device *adev)
 
 	WREG32(mmBIF_FB_EN, BIF_FB_EN__FB_READ_EN_MASK | BIF_FB_EN__FB_WRITE_EN_MASK);
 
-	mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
 	adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
 	mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index d92e92e5d50b..8f20a5dd44fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4258,7 +4258,7 @@ static int gfx_v7_0_late_init(void *handle)
 static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config;
-	u32 mc_shared_chmap, mc_arb_ramcfg;
+	u32 mc_arb_ramcfg;
 	u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map;
 	u32 tmp;
 
@@ -4335,7 +4335,6 @@ static void gfx_v7_0_gpu_early_init(struct amdgpu_device *adev)
 		break;
 	}
 
-	mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
 	adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
 	mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 52a647d7022d..46f0533ba43f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1677,7 +1677,7 @@ fail:
 static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
 {
 	u32 gb_addr_config;
-	u32 mc_shared_chmap, mc_arb_ramcfg;
+	u32 mc_arb_ramcfg;
 	u32 dimm00_addr_map, dimm01_addr_map, dimm10_addr_map, dimm11_addr_map;
 	u32 tmp;
 	int ret;
@@ -1817,7 +1817,6 @@ static int gfx_v8_0_gpu_early_init(struct amdgpu_device *adev)
 		break;
 	}
 
-	mc_shared_chmap = RREG32(mmMC_SHARED_CHMAP);
 	adev->gfx.config.mc_arb_ramcfg = RREG32(mmMC_ARB_RAMCFG);
 	mc_arb_ramcfg = adev->gfx.config.mc_arb_ramcfg;
 
@@ -4559,8 +4558,11 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
 	mqd->cp_hqd_eop_wptr_mem = RREG32(mmCP_HQD_EOP_WPTR_MEM);
 	mqd->cp_hqd_eop_dones = RREG32(mmCP_HQD_EOP_DONES);
 
-	/* activate the queue */
-	mqd->cp_hqd_active = 1;
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd->cp_hqd_active = 1;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 97105a5bb246..46ab46757b25 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -131,18 +131,6 @@ MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");
 #define mmTCP_CHAN_STEER_5_ARCT								0x0b0c
 #define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX							0
 
-struct ras_gfx_subblock_reg {
-	const char *name;
-	uint32_t hwip;
-	uint32_t inst;
-	uint32_t seg;
-	uint32_t reg_offset;
-	uint32_t sec_count_mask;
-	uint32_t sec_count_shift;
-	uint32_t ded_count_mask;
-	uint32_t ded_count_shift;
-};
-
 enum ta_ras_gfx_subblock {
 	/*CPC*/
 	TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
@@ -751,6 +739,134 @@ static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 static int gfx_v9_0_ras_error_inject(struct amdgpu_device *adev,
 				     void *inject_if);
 
+static void gfx_v9_0_kiq_set_resources(struct amdgpu_ring *kiq_ring,
+				uint64_t queue_mask)
+{
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
+	amdgpu_ring_write(kiq_ring,
+		PACKET3_SET_RESOURCES_VMID_MASK(0) |
+		/* vmid_mask:0* queue_type:0 (KIQ) */
+		PACKET3_SET_RESOURCES_QUEUE_TYPE(0));
+	amdgpu_ring_write(kiq_ring,
+			lower_32_bits(queue_mask));	/* queue mask lo */
+	amdgpu_ring_write(kiq_ring,
+			upper_32_bits(queue_mask));	/* queue mask hi */
+	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
+	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
+	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */
+	amdgpu_ring_write(kiq_ring, 0);	/* gds heap base:0, gds heap size:0 */
+}
+
+static void gfx_v9_0_kiq_map_queues(struct amdgpu_ring *kiq_ring,
+				 struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = kiq_ring->adev;
+	uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
+	uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
+	/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
+	amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+			 PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
+			 PACKET3_MAP_QUEUES_VMID(0) | /* VMID */
+			 PACKET3_MAP_QUEUES_QUEUE(ring->queue) |
+			 PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
+			 PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) |
+			 /*queue_type: normal compute queue */
+			 PACKET3_MAP_QUEUES_QUEUE_TYPE(0) |
+			 /* alloc format: all_on_one_pipe */
+			 PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) |
+			 PACKET3_MAP_QUEUES_ENGINE_SEL(eng_sel) |
+			 /* num_queues: must be 1 */
+			 PACKET3_MAP_QUEUES_NUM_QUEUES(1));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(mqd_addr));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(mqd_addr));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(wptr_addr));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(wptr_addr));
+}
+
+static void gfx_v9_0_kiq_unmap_queues(struct amdgpu_ring *kiq_ring,
+				   struct amdgpu_ring *ring,
+				   enum amdgpu_unmap_queues_action action,
+				   u64 gpu_addr, u64 seq)
+{
+	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
+	amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+			  PACKET3_UNMAP_QUEUES_ACTION(action) |
+			  PACKET3_UNMAP_QUEUES_QUEUE_SEL(0) |
+			  PACKET3_UNMAP_QUEUES_ENGINE_SEL(eng_sel) |
+			  PACKET3_UNMAP_QUEUES_NUM_QUEUES(1));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index));
+
+	if (action == PREEMPT_QUEUES_NO_UNMAP) {
+		amdgpu_ring_write(kiq_ring, lower_32_bits(gpu_addr));
+		amdgpu_ring_write(kiq_ring, upper_32_bits(gpu_addr));
+		amdgpu_ring_write(kiq_ring, seq);
+	} else {
+		amdgpu_ring_write(kiq_ring, 0);
+		amdgpu_ring_write(kiq_ring, 0);
+		amdgpu_ring_write(kiq_ring, 0);
+	}
+}
+
+static void gfx_v9_0_kiq_query_status(struct amdgpu_ring *kiq_ring,
+				   struct amdgpu_ring *ring,
+				   u64 addr,
+				   u64 seq)
+{
+	uint32_t eng_sel = ring->funcs->type == AMDGPU_RING_TYPE_GFX ? 4 : 0;
+
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_QUERY_STATUS, 5));
+	amdgpu_ring_write(kiq_ring,
+			  PACKET3_QUERY_STATUS_CONTEXT_ID(0) |
+			  PACKET3_QUERY_STATUS_INTERRUPT_SEL(0) |
+			  PACKET3_QUERY_STATUS_COMMAND(2));
+	/* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_QUERY_STATUS_DOORBELL_OFFSET(ring->doorbell_index) |
+			PACKET3_QUERY_STATUS_ENG_SEL(eng_sel));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(addr));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(addr));
+	amdgpu_ring_write(kiq_ring, lower_32_bits(seq));
+	amdgpu_ring_write(kiq_ring, upper_32_bits(seq));
+}
+
+static void gfx_v9_0_kiq_invalidate_tlbs(struct amdgpu_ring *kiq_ring,
+				uint16_t pasid, uint32_t flush_type,
+				bool all_hub)
+{
+	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_INVALIDATE_TLBS, 0));
+	amdgpu_ring_write(kiq_ring,
+			PACKET3_INVALIDATE_TLBS_DST_SEL(1) |
+			PACKET3_INVALIDATE_TLBS_ALL_HUB(all_hub) |
+			PACKET3_INVALIDATE_TLBS_PASID(pasid) |
+			PACKET3_INVALIDATE_TLBS_FLUSH_TYPE(flush_type));
+}
+
+static const struct kiq_pm4_funcs gfx_v9_0_kiq_pm4_funcs = {
+	.kiq_set_resources = gfx_v9_0_kiq_set_resources,
+	.kiq_map_queues = gfx_v9_0_kiq_map_queues,
+	.kiq_unmap_queues = gfx_v9_0_kiq_unmap_queues,
+	.kiq_query_status = gfx_v9_0_kiq_query_status,
+	.kiq_invalidate_tlbs = gfx_v9_0_kiq_invalidate_tlbs,
+	.set_resources_size = 8,
+	.map_queues_size = 7,
+	.unmap_queues_size = 6,
+	.query_status_size = 7,
+	.invalidate_tlbs_size = 12,
+};
+
+static void gfx_v9_0_set_kiq_pm4_funcs(struct amdgpu_device *adev)
+{
+	adev->gfx.kiq.pmf = &gfx_v9_0_kiq_pm4_funcs;
+}
+
 static void gfx_v9_0_init_golden_registers(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
@@ -991,8 +1107,7 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 	    (adev->gfx.mec_feature_version < 46) ||
 	    (adev->gfx.pfp_fw_version < 0x000000b7) ||
 	    (adev->gfx.pfp_feature_version < 46))
-		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
-			      GRBM requires 1-cycle delay in cp firmware\n");
+		DRM_WARN_ONCE("CP firmware version too old, please update!");
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
@@ -3119,74 +3234,6 @@ static void gfx_v9_0_kiq_setting(struct amdgpu_ring *ring)
 	WREG32_SOC15_RLC(GC, 0, mmRLC_CP_SCHEDULERS, tmp);
 }
 
-static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
-	uint64_t queue_mask = 0;
-	int r, i;
-
-	for (i = 0; i < AMDGPU_MAX_COMPUTE_QUEUES; ++i) {
-		if (!test_bit(i, adev->gfx.mec.queue_bitmap))
-			continue;
-
-		/* This situation may be hit in the future if a new HW
-		 * generation exposes more than 64 queues. If so, the
-		 * definition of queue_mask needs updating */
-		if (WARN_ON(i >= (sizeof(queue_mask)*8))) {
-			DRM_ERROR("Invalid KCQ enabled: %d\n", i);
-			break;
-		}
-
-		queue_mask |= (1ull << i);
-	}
-
-	r = amdgpu_ring_alloc(kiq_ring, (7 * adev->gfx.num_compute_rings) + 8);
-	if (r) {
-		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
-		return r;
-	}
-
-	/* set resources */
-	amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6));
-	amdgpu_ring_write(kiq_ring, PACKET3_SET_RESOURCES_VMID_MASK(0) |
-			  PACKET3_SET_RESOURCES_QUEUE_TYPE(0));	/* vmid_mask:0 queue_type:0 (KIQ) */
-	amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask));	/* queue mask lo */
-	amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask));	/* queue mask hi */
-	amdgpu_ring_write(kiq_ring, 0);	/* gws mask lo */
-	amdgpu_ring_write(kiq_ring, 0);	/* gws mask hi */
-	amdgpu_ring_write(kiq_ring, 0);	/* oac mask */
-	amdgpu_ring_write(kiq_ring, 0);	/* gds heap base:0, gds heap size:0 */
-	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
-		uint64_t mqd_addr = amdgpu_bo_gpu_offset(ring->mqd_obj);
-		uint64_t wptr_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
-
-		amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_MAP_QUEUES, 5));
-		/* Q_sel:0, vmid:0, vidmem: 1, engine:0, num_Q:1*/
-		amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
-				  PACKET3_MAP_QUEUES_QUEUE_SEL(0) | /* Queue_Sel */
-				  PACKET3_MAP_QUEUES_VMID(0) | /* VMID */
-				  PACKET3_MAP_QUEUES_QUEUE(ring->queue) |
-				  PACKET3_MAP_QUEUES_PIPE(ring->pipe) |
-				  PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) |
-				  PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */
-				  PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */
-				  PACKET3_MAP_QUEUES_ENGINE_SEL(0) | /* engine_sel: compute */
-				  PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */
-		amdgpu_ring_write(kiq_ring, PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index));
-		amdgpu_ring_write(kiq_ring, lower_32_bits(mqd_addr));
-		amdgpu_ring_write(kiq_ring, upper_32_bits(mqd_addr));
-		amdgpu_ring_write(kiq_ring, lower_32_bits(wptr_addr));
-		amdgpu_ring_write(kiq_ring, upper_32_bits(wptr_addr));
-	}
-
-	r = amdgpu_ring_test_helper(kiq_ring);
-	if (r)
-		DRM_ERROR("KCQ enable failed\n");
-
-	return r;
-}
-
 static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -3323,8 +3370,11 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
 	tmp = REG_SET_FIELD(tmp, CP_HQD_IB_CONTROL, MIN_IB_AVAIL_SIZE, 3);
 	mqd->cp_hqd_ib_control = tmp;
 
-	/* activate the queue */
-	mqd->cp_hqd_active = 1;
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd->cp_hqd_active = 1;
 
 	return 0;
 }
@@ -3593,7 +3643,7 @@ static int gfx_v9_0_kcq_resume(struct amdgpu_device *adev)
 			goto done;
 	}
 
-	r = gfx_v9_0_kiq_kcq_enable(adev);
+	r = amdgpu_gfx_enable_kcq(adev);
 done:
 	return r;
 }
@@ -3650,6 +3700,23 @@ static int gfx_v9_0_cp_resume(struct amdgpu_device *adev)
 	return 0;
 }
 
+static void gfx_v9_0_init_tcp_config(struct amdgpu_device *adev)
+{
+	u32 tmp;
+
+	if (adev->asic_type != CHIP_ARCTURUS)
+		return;
+
+	tmp = RREG32_SOC15(GC, 0, mmTCP_ADDR_CONFIG);
+	tmp = REG_SET_FIELD(tmp, TCP_ADDR_CONFIG, ENABLE64KHASH,
+				adev->df.hash_status.hash_64k);
+	tmp = REG_SET_FIELD(tmp, TCP_ADDR_CONFIG, ENABLE2MHASH,
+				adev->df.hash_status.hash_2m);
+	tmp = REG_SET_FIELD(tmp, TCP_ADDR_CONFIG, ENABLE1GHASH,
+				adev->df.hash_status.hash_1g);
+	WREG32_SOC15(GC, 0, mmTCP_ADDR_CONFIG, tmp);
+}
+
 static void gfx_v9_0_cp_enable(struct amdgpu_device *adev, bool enable)
 {
 	if (adev->asic_type != CHIP_ARCTURUS)
@@ -3667,6 +3734,8 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_constants_init(adev);
 
+	gfx_v9_0_init_tcp_config(adev);
+
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -3678,36 +3747,6 @@ static int gfx_v9_0_hw_init(void *handle)
 	return r;
 }
 
-static int gfx_v9_0_kcq_disable(struct amdgpu_device *adev)
-{
-	int r, i;
-	struct amdgpu_ring *kiq_ring = &adev->gfx.kiq.ring;
-
-	r = amdgpu_ring_alloc(kiq_ring, 6 * adev->gfx.num_compute_rings);
-	if (r)
-		DRM_ERROR("Failed to lock KIQ (%d).\n", r);
-
-	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
-		struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
-
-		amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_UNMAP_QUEUES, 4));
-		amdgpu_ring_write(kiq_ring, /* Q_sel: 0, vmid: 0, engine: 0, num_Q: 1 */
-						PACKET3_UNMAP_QUEUES_ACTION(1) | /* RESET_QUEUES */
-						PACKET3_UNMAP_QUEUES_QUEUE_SEL(0) |
-						PACKET3_UNMAP_QUEUES_ENGINE_SEL(0) |
-						PACKET3_UNMAP_QUEUES_NUM_QUEUES(1));
-		amdgpu_ring_write(kiq_ring, PACKET3_UNMAP_QUEUES_DOORBELL_OFFSET0(ring->doorbell_index));
-		amdgpu_ring_write(kiq_ring, 0);
-		amdgpu_ring_write(kiq_ring, 0);
-		amdgpu_ring_write(kiq_ring, 0);
-	}
-	r = amdgpu_ring_test_helper(kiq_ring);
-	if (r)
-		DRM_ERROR("KCQ disable failed\n");
-
-	return r;
-}
-
 static int gfx_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -3719,7 +3758,7 @@ static int gfx_v9_0_hw_fini(void *handle)
 	/* DF freeze and kcq disable will fail */
 	if (!amdgpu_ras_intr_triggered())
 		/* disable KCQ to avoid CPC touch memory not valid anymore */
-		gfx_v9_0_kcq_disable(adev);
+		amdgpu_gfx_disable_kcq(adev);
 
 	if (amdgpu_sriov_vf(adev)) {
 		gfx_v9_0_cp_gfx_enable(adev, false);
@@ -3936,30 +3975,58 @@ static const u32 sgpr_init_compute_shader[] =
 	0xbe800080, 0xbf810000,
 };
 
+/* When below register arrays changed, please update gpr_reg_size,
+  and sec_ded_counter_reg_size in function gfx_v9_0_do_edc_gpr_workarounds,
+  to cover all gfx9 ASICs */
 static const struct soc15_reg_entry vgpr_init_regs[] = {
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x0000000 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 4 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x3f },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x400000 },  /* 64KB LDS */
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0xffffffff },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0xffffffff },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0xffffffff },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x1000000 }, /* CU_GROUP_COUNT=1 */
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 256*2 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 1 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE4), 0xffffffff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE5), 0xffffffff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE6), 0xffffffff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE7), 0xffffffff },
+};
+
+static const struct soc15_reg_entry sgpr1_init_regs[] = {
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x0000000 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 8 },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x100007f }, /* VGPRS=15 (256 logical VGPRs, SGPRS=1 (16 SGPRs, BULKY=1 */
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x400000 },  /* 64KB LDS */
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x240 }, /* (80 GPRS) */
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x0 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE4), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE5), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE6), 0x000000ff },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE7), 0x000000ff },
 };
 
-static const struct soc15_reg_entry sgpr_init_regs[] = {
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0xffffffff },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x1000000 }, /* CU_GROUP_COUNT=1 */
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 256*2 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 1 },
+static const struct soc15_reg_entry sgpr2_init_regs[] = {
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_RESOURCE_LIMITS), 0x0000000 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_X), 0x40 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Y), 8 },
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_NUM_THREAD_Z), 1 },
-   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x340 }, /* SGPRS=13 (112 GPRS) */
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC1), 0x240 }, /* (80 GPRS) */
    { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_PGM_RSRC2), 0x0 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE0), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE1), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE2), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE3), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE4), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE5), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE6), 0x0000ff00 },
+   { SOC15_REG_ENTRY(GC, 0, mmCOMPUTE_STATIC_THREAD_MGMT_SE7), 0x0000ff00 },
 };
 
 static const struct soc15_reg_entry sec_ded_counter_registers[] = {
@@ -3996,6 +4063,7 @@ static const struct soc15_reg_entry sec_ded_counter_registers[] = {
    { SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0, 1, 16},
    { SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT), 0, 1, 2},
    { SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 0, 4, 6},
+   { SOC15_REG_ENTRY(HDP, 0, mmHDP_EDC_CNT), 0, 1, 1},
 };
 
 static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)
@@ -4054,6 +4122,12 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 	unsigned total_size, vgpr_offset, sgpr_offset;
 	u64 gpu_addr;
 
+	int compute_dim_x = adev->gfx.config.max_shader_engines *
+						adev->gfx.config.max_cu_per_sh *
+						adev->gfx.config.max_sh_per_se;
+	int sgpr_work_group_size = 5;
+	int gpr_reg_size = compute_dim_x / 16 + 6;
+
 	/* only support when RAS is enabled */
 	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
 		return 0;
@@ -4063,9 +4137,11 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 		return 0;
 
 	total_size =
-		((ARRAY_SIZE(vgpr_init_regs) * 3) + 4 + 5 + 2) * 4;
+		(gpr_reg_size * 3 + 4 + 5 + 2) * 4; /* VGPRS */
 	total_size +=
-		((ARRAY_SIZE(sgpr_init_regs) * 3) + 4 + 5 + 2) * 4;
+		(gpr_reg_size * 3 + 4 + 5 + 2) * 4; /* SGPRS1 */
+	total_size +=
+		(gpr_reg_size * 3 + 4 + 5 + 2) * 4; /* SGPRS2 */
 	total_size = ALIGN(total_size, 256);
 	vgpr_offset = total_size;
 	total_size += ALIGN(sizeof(vgpr_init_compute_shader), 256);
@@ -4092,7 +4168,7 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
 	/* VGPR */
 	/* write the register state for the compute dispatch */
-	for (i = 0; i < ARRAY_SIZE(vgpr_init_regs); i++) {
+	for (i = 0; i < gpr_reg_size; i++) {
 		ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 1);
 		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(vgpr_init_regs[i])
 								- PACKET3_SET_SH_REG_START;
@@ -4108,7 +4184,35 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
 	/* write dispatch packet */
 	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_DISPATCH_DIRECT, 3);
-	ib.ptr[ib.length_dw++] = 128; /* x */
+	ib.ptr[ib.length_dw++] = compute_dim_x; /* x */
+	ib.ptr[ib.length_dw++] = 1; /* y */
+	ib.ptr[ib.length_dw++] = 1; /* z */
+	ib.ptr[ib.length_dw++] =
+		REG_SET_FIELD(0, COMPUTE_DISPATCH_INITIATOR, COMPUTE_SHADER_EN, 1);
+
+	/* write CS partial flush packet */
+	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_EVENT_WRITE, 0);
+	ib.ptr[ib.length_dw++] = EVENT_TYPE(7) | EVENT_INDEX(4);
+
+	/* SGPR1 */
+	/* write the register state for the compute dispatch */
+	for (i = 0; i < gpr_reg_size; i++) {
+		ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 1);
+		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(sgpr1_init_regs[i])
+								- PACKET3_SET_SH_REG_START;
+		ib.ptr[ib.length_dw++] = sgpr1_init_regs[i].reg_value;
+	}
+	/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */
+	gpu_addr = (ib.gpu_addr + (u64)sgpr_offset) >> 8;
+	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 2);
+	ib.ptr[ib.length_dw++] = SOC15_REG_OFFSET(GC, 0, mmCOMPUTE_PGM_LO)
+							- PACKET3_SET_SH_REG_START;
+	ib.ptr[ib.length_dw++] = lower_32_bits(gpu_addr);
+	ib.ptr[ib.length_dw++] = upper_32_bits(gpu_addr);
+
+	/* write dispatch packet */
+	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_DISPATCH_DIRECT, 3);
+	ib.ptr[ib.length_dw++] = compute_dim_x / 2 * sgpr_work_group_size; /* x */
 	ib.ptr[ib.length_dw++] = 1; /* y */
 	ib.ptr[ib.length_dw++] = 1; /* z */
 	ib.ptr[ib.length_dw++] =
@@ -4118,13 +4222,13 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_EVENT_WRITE, 0);
 	ib.ptr[ib.length_dw++] = EVENT_TYPE(7) | EVENT_INDEX(4);
 
-	/* SGPR */
+	/* SGPR2 */
 	/* write the register state for the compute dispatch */
-	for (i = 0; i < ARRAY_SIZE(sgpr_init_regs); i++) {
+	for (i = 0; i < gpr_reg_size; i++) {
 		ib.ptr[ib.length_dw++] = PACKET3(PACKET3_SET_SH_REG, 1);
-		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(sgpr_init_regs[i])
+		ib.ptr[ib.length_dw++] = SOC15_REG_ENTRY_OFFSET(sgpr2_init_regs[i])
 								- PACKET3_SET_SH_REG_START;
-		ib.ptr[ib.length_dw++] = sgpr_init_regs[i].reg_value;
+		ib.ptr[ib.length_dw++] = sgpr2_init_regs[i].reg_value;
 	}
 	/* write the shader start address: mmCOMPUTE_PGM_LO, mmCOMPUTE_PGM_HI */
 	gpu_addr = (ib.gpu_addr + (u64)sgpr_offset) >> 8;
@@ -4136,7 +4240,7 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
 	/* write dispatch packet */
 	ib.ptr[ib.length_dw++] = PACKET3(PACKET3_DISPATCH_DIRECT, 3);
-	ib.ptr[ib.length_dw++] = 128; /* x */
+	ib.ptr[ib.length_dw++] = compute_dim_x / 2 * sgpr_work_group_size; /* x */
 	ib.ptr[ib.length_dw++] = 1; /* y */
 	ib.ptr[ib.length_dw++] = 1; /* z */
 	ib.ptr[ib.length_dw++] =
@@ -4189,6 +4293,7 @@ static int gfx_v9_0_early_init(void *handle)
 	else
 		adev->gfx.num_gfx_rings = GFX9_NUM_GFX_RINGS;
 	adev->gfx.num_compute_rings = AMDGPU_MAX_COMPUTE_RINGS;
+	gfx_v9_0_set_kiq_pm4_funcs(adev);
 	gfx_v9_0_set_ring_funcs(adev);
 	gfx_v9_0_set_irq_funcs(adev);
 	gfx_v9_0_set_gds_init(adev);
@@ -4202,10 +4307,6 @@ static int gfx_v9_0_ecc_late_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
-	r = amdgpu_gfx_ras_late_init(adev);
-	if (r)
-		return r;
-
 	r = gfx_v9_0_do_edc_gds_workarounds(adev);
 	if (r)
 		return r;
@@ -4215,6 +4316,10 @@ static int gfx_v9_0_ecc_late_init(void *handle)
 	if (r)
 		return r;
 
+	r = amdgpu_gfx_ras_late_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -5440,7 +5545,7 @@ static int gfx_v9_0_priv_inst_irq(struct amdgpu_device *adev,
 }
 
 
-static const struct ras_gfx_subblock_reg ras_subblock_regs[] = {
+static const struct soc15_ras_field_entry gc_ras_fields_vg20[] = {
 	{ "CPC_SCRATCH", SOC15_REG_ENTRY(GC, 0, mmCPC_EDC_SCRATCH_CNT),
 	  SOC15_REG_FIELD(CPC_EDC_SCRATCH_CNT, SEC_COUNT),
 	  SOC15_REG_FIELD(CPC_EDC_SCRATCH_CNT, DED_COUNT)
@@ -6099,29 +6204,29 @@ static int __get_ras_error_count(const struct soc15_reg_entry *reg,
 	uint32_t i;
 	uint32_t sec_cnt, ded_cnt;
 
-	for (i = 0; i < ARRAY_SIZE(ras_subblock_regs); i++) {
-		if(ras_subblock_regs[i].reg_offset != reg->reg_offset ||
-			ras_subblock_regs[i].seg != reg->seg ||
-			ras_subblock_regs[i].inst != reg->inst)
+	for (i = 0; i < ARRAY_SIZE(gc_ras_fields_vg20); i++) {
+		if(gc_ras_fields_vg20[i].reg_offset != reg->reg_offset ||
+			gc_ras_fields_vg20[i].seg != reg->seg ||
+			gc_ras_fields_vg20[i].inst != reg->inst)
 			continue;
 
 		sec_cnt = (value &
-				ras_subblock_regs[i].sec_count_mask) >>
-				ras_subblock_regs[i].sec_count_shift;
+				gc_ras_fields_vg20[i].sec_count_mask) >>
+				gc_ras_fields_vg20[i].sec_count_shift;
 		if (sec_cnt) {
 			DRM_INFO("GFX SubBlock %s, Instance[%d][%d], SEC %d\n",
-				ras_subblock_regs[i].name,
+				gc_ras_fields_vg20[i].name,
 				se_id, inst_id,
 				sec_cnt);
 			*sec_count += sec_cnt;
 		}
 
 		ded_cnt = (value &
-				ras_subblock_regs[i].ded_count_mask) >>
-				ras_subblock_regs[i].ded_count_shift;
+				gc_ras_fields_vg20[i].ded_count_mask) >>
+				gc_ras_fields_vg20[i].ded_count_shift;
 		if (ded_cnt) {
 			DRM_INFO("GFX SubBlock %s, Instance[%d][%d], DED %d\n",
-				ras_subblock_regs[i].name,
+				gc_ras_fields_vg20[i].name,
 				se_id, inst_id,
 				ded_cnt);
 			*ded_count += ded_cnt;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index e91bd7945777..1a2f18b908fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -75,40 +75,45 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 24);
 	WREG32_SOC15_RLC(GC, 0, mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 24);
 
-	/* Program the system aperture low logical page number. */
-	WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
-		     min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
-
-	if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
-		/*
-		 * Raven2 has a HW issue that it is unable to use the vram which
-		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
-		 * workaround that increase system aperture high address (add 1)
-		 * to get rid of the VM fault and hardware hang.
-		 */
-		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max((adev->gmc.fb_end >> 18) + 0x1,
-				 adev->gmc.agp_end >> 18));
-	else
-		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			     max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
-
-	/* Set default page address. */
-	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start
-		+ adev->vm_manager.vram_base_offset;
-	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
-		     (u32)(value >> 12));
-	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
-		     (u32)(value >> 44));
-
-	/* Program "protection fault". */
-	WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
-		     (u32)(adev->dummy_page_addr >> 12));
-	WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
-		     (u32)((u64)adev->dummy_page_addr >> 44));
-
-	WREG32_FIELD15(GC, 0, VM_L2_PROTECTION_FAULT_CNTL2,
-		       ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
+	if (!amdgpu_sriov_vf(adev) || adev->asic_type <= CHIP_VEGA10) {
+		/* Program the system aperture low logical page number. */
+		WREG32_SOC15_RLC(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
+			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
+
+		if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
+			/*
+			* Raven2 has a HW issue that it is unable to use the
+			* vram which is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR.
+			* So here is the workaround that increase system
+			* aperture high address (add 1) to get rid of the VM
+			* fault and hardware hang.
+			*/
+			WREG32_SOC15_RLC(GC, 0,
+					 mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+					 max((adev->gmc.fb_end >> 18) + 0x1,
+					     adev->gmc.agp_end >> 18));
+		else
+			WREG32_SOC15_RLC(
+				GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+				max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
+
+		/* Set default page address. */
+		value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
+			adev->vm_manager.vram_base_offset;
+		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
+			     (u32)(value >> 12));
+		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
+			     (u32)(value >> 44));
+
+		/* Program "protection fault". */
+		WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
+			     (u32)(adev->dummy_page_addr >> 12));
+		WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
+			     (u32)((u64)adev->dummy_page_addr >> 44));
+
+		WREG32_FIELD15(GC, 0, VM_L2_PROTECTION_FAULT_CNTL2,
+			       ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
+	}
 }
 
 static void gfxhub_v1_0_init_tlb_regs(struct amdgpu_device *adev)
@@ -264,7 +269,7 @@ static void gfxhub_v1_0_program_invalidation(struct amdgpu_device *adev)
 
 int gfxhub_v1_0_gart_enable(struct amdgpu_device *adev)
 {
-	if (amdgpu_sriov_vf(adev)) {
+	if (amdgpu_sriov_vf(adev) && adev->asic_type != CHIP_ARCTURUS) {
 		/*
 		 * MC_VM_FB_LOCATION_BASE/TOP is NULL for VF, becuase they are
 		 * VF copy registers so vbios post doesn't program them, for
@@ -280,10 +285,12 @@ int gfxhub_v1_0_gart_enable(struct amdgpu_device *adev)
 	gfxhub_v1_0_init_gart_aperture_regs(adev);
 	gfxhub_v1_0_init_system_aperture_regs(adev);
 	gfxhub_v1_0_init_tlb_regs(adev);
-	gfxhub_v1_0_init_cache_regs(adev);
+	if (!amdgpu_sriov_vf(adev))
+		gfxhub_v1_0_init_cache_regs(adev);
 
 	gfxhub_v1_0_enable_system_domain(adev);
-	gfxhub_v1_0_disable_identity_aperture(adev);
+	if (!amdgpu_sriov_vf(adev))
+		gfxhub_v1_0_disable_identity_aperture(adev);
 	gfxhub_v1_0_setup_vmid_config(adev);
 	gfxhub_v1_0_program_invalidation(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index f5725336a5f2..bbede09983e1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -30,6 +30,8 @@
 #include "hdp/hdp_5_0_0_sh_mask.h"
 #include "gc/gc_10_1_0_sh_mask.h"
 #include "mmhub/mmhub_2_0_0_sh_mask.h"
+#include "athub/athub_2_0_0_sh_mask.h"
+#include "athub/athub_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_sh_mask.h"
 #include "oss/osssys_5_0_0_offset.h"
@@ -37,6 +39,7 @@
 #include "navi10_enum.h"
 
 #include "soc15.h"
+#include "soc15d.h"
 #include "soc15_common.h"
 
 #include "nbio_v2_3.h"
@@ -234,6 +237,19 @@ static bool gmc_v10_0_use_invalidate_semaphore(struct amdgpu_device *adev,
 		(!amdgpu_sriov_vf(adev)));
 }
 
+static bool gmc_v10_0_get_atc_vmid_pasid_mapping_info(
+					struct amdgpu_device *adev,
+					uint8_t vmid, uint16_t *p_pasid)
+{
+	uint32_t value;
+
+	value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+		     + vmid);
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -380,6 +396,63 @@ error_alloc:
 	DRM_ERROR("Error flushing GPU TLB using the SDMA (%d)!\n", r);
 }
 
+/**
+ * gmc_v10_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid, i;
+	signed long r;
+	uint32_t seq;
+	uint16_t queried_pasid;
+	bool ret;
+	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+
+	if (amdgpu_emu_mode == 0 && ring->sched.ready) {
+		spin_lock(&adev->gfx.kiq.ring_lock);
+		amdgpu_ring_alloc(ring, kiq->pmf->invalidate_tlbs_size);
+		kiq->pmf->kiq_invalidate_tlbs(ring,
+					pasid, flush_type, all_hub);
+		amdgpu_fence_emit_polling(ring, &seq);
+		amdgpu_ring_commit(ring);
+		spin_unlock(&adev->gfx.kiq.ring_lock);
+		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		if (r < 1) {
+			DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+			return -ETIME;
+		}
+
+		return 0;
+	}
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		ret = gmc_v10_0_get_atc_vmid_pasid_mapping_info(adev, vmid,
+				&queried_pasid);
+		if (ret	&& queried_pasid == pasid) {
+			if (all_hub) {
+				for (i = 0; i < adev->num_vmhubs; i++)
+					gmc_v10_0_flush_gpu_tlb(adev, vmid,
+							i, 0);
+			} else {
+				gmc_v10_0_flush_gpu_tlb(adev, vmid,
+						AMDGPU_GFXHUB_0, 0);
+			}
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 					     unsigned vmid, uint64_t pd_addr)
 {
@@ -531,6 +604,7 @@ static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev,
 
 static const struct amdgpu_gmc_funcs gmc_v10_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v10_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v10_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v10_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v10_0_emit_pasid_mapping,
 	.map_mtype = gmc_v10_0_map_mtype,
@@ -564,22 +638,18 @@ static int gmc_v10_0_early_init(void *handle)
 static int gmc_v10_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	unsigned vm_inv_eng[AMDGPU_MAX_VMHUBS] = { 4, 4 };
-	unsigned i;
-
-	for(i = 0; i < adev->num_rings; ++i) {
-		struct amdgpu_ring *ring = adev->rings[i];
-		unsigned vmhub = ring->funcs->vmhub;
+	int r;
 
-		ring->vm_inv_eng = vm_inv_eng[vmhub]++;
-		dev_info(adev->dev, "ring %u(%s) uses VM inv eng %u on hub %u\n",
-			 ring->idx, ring->name, ring->vm_inv_eng,
-			 ring->funcs->vmhub);
-	}
+	/*
+	 * Can't free the stolen VGA memory when it might be used for memory
+	 * training again.
+	 */
+	if (!adev->fw_vram_usage.mem_train_support)
+		amdgpu_bo_late_init(adev);
 
-	/* Engine 17 is used for GART flushes */
-	for(i = 0; i < AMDGPU_MAX_VMHUBS; ++i)
-		BUG_ON(vm_inv_eng[i] > 17);
+	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
+	if (r)
+		return r;
 
 	return amdgpu_irq_get(adev, &adev->gmc.vm_fault, 0);
 }
@@ -731,6 +801,10 @@ static int gmc_v10_0_sw_init(void *handle)
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC,
 			      VMC_1_0__SRCID__VM_FAULT,
 			      &adev->gmc.vm_fault);
+
+	if (r)
+		return r;
+
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2,
 			      UTCL2_1_0__SRCID__FAULT,
 			      &adev->gmc.vm_fault);
@@ -743,15 +817,6 @@ static int gmc_v10_0_sw_init(void *handle)
 	 */
 	adev->gmc.mc_mask = 0xffffffffffffULL; /* 48 bit MC */
 
-	/*
-	 * Reserve 8M stolen memory for navi10 like vega10
-	 * TODO: will check if it's really needed on asic.
-	 */
-	if (amdgpu_emu_mode == 1)
-		adev->gmc.stolen_size = 0;
-	else
-		adev->gmc.stolen_size = 9 * 1024 *1024;
-
 	r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(44));
 	if (r) {
 		printk(KERN_WARNING "amdgpu: No suitable DMA available.\n");
@@ -764,6 +829,19 @@ static int gmc_v10_0_sw_init(void *handle)
 
 	adev->gmc.stolen_size = gmc_v10_0_get_vbios_fb_size(adev);
 
+	/*
+	 * In dual GPUs scenario, stolen_size is assigned to zero on the
+	 * secondary GPU, since there is no pre-OS console using that memory.
+	 * Then the bottom region of VRAM was allocated as GTT, unfortunately a
+	 * small region of bottom VRAM was encroached by UMC firmware during
+	 * GDDR6 BIST training, this cause page fault.
+	 * The page fault can be fixed by forcing stolen_size to 3MB, then the
+	 * bottom region of VRAM was allocated as stolen memory, GTT corruption
+	 * avoid.
+	 */
+	adev->gmc.stolen_size = max(adev->gmc.stolen_size,
+				    AMDGPU_STOLEN_BIST_TRAINING_DEFAULT_SIZE);
+
 	/* Memory manager */
 	r = amdgpu_bo_init(adev);
 	if (r)
@@ -803,6 +881,13 @@ static void gmc_v10_0_gart_fini(struct amdgpu_device *adev)
 static int gmc_v10_0_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	void *stolen_vga_buf;
+
+	/*
+	 * Free the stolen memory if it wasn't already freed in late_init
+	 * because of memory training.
+	 */
+	amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, &stolen_vga_buf);
 
 	amdgpu_vm_manager_fini(adev);
 	gmc_v10_0_gart_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index f08e5330642d..19d5b133e1d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -418,6 +418,38 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * gmc_v7_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v7_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid;
+	unsigned int tmp;
+
+	if (adev->in_gpu_reset)
+		return -EIO;
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
+			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
+			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
+			RREG32(mmVM_INVALIDATE_RESPONSE);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -1333,6 +1365,7 @@ static const struct amd_ip_funcs gmc_v7_0_ip_funcs = {
 
 static const struct amdgpu_gmc_funcs gmc_v7_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v7_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v7_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v7_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v7_0_emit_pasid_mapping,
 	.set_prt = gmc_v7_0_set_prt,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 6d96d40fbcb8..27d83204fa2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -620,6 +620,39 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * gmc_v8_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v8_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid;
+	unsigned int tmp;
+
+	if (adev->in_gpu_reset)
+		return -EIO;
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+		if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
+			(tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
+			WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
+			RREG32(mmVM_INVALIDATE_RESPONSE);
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -1700,6 +1733,7 @@ static const struct amd_ip_funcs gmc_v8_0_ip_funcs = {
 
 static const struct amdgpu_gmc_funcs gmc_v8_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v8_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v8_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v8_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v8_0_emit_pasid_mapping,
 	.set_prt = gmc_v8_0_set_prt,
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index a5b68b5e452f..40a496804356 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -38,10 +38,12 @@
 #include "dce/dce_12_0_sh_mask.h"
 #include "vega10_enum.h"
 #include "mmhub/mmhub_1_0_offset.h"
+#include "athub/athub_1_0_sh_mask.h"
 #include "athub/athub_1_0_offset.h"
 #include "oss/osssys_4_0_offset.h"
 
 #include "soc15.h"
+#include "soc15d.h"
 #include "soc15_common.h"
 #include "umc/umc_6_0_sh_mask.h"
 
@@ -207,6 +209,11 @@ static int gmc_v9_0_ecc_interrupt_state(struct amdgpu_device *adev,
 {
 	u32 bits, i, tmp, reg;
 
+	/* Devices newer then VEGA10/12 shall have these programming
+	     sequences performed by PSP BL */
+	if (adev->asic_type >= CHIP_VEGA20)
+		return 0;
+
 	bits = 0x7f;
 
 	switch (state) {
@@ -393,8 +400,10 @@ static void gmc_v9_0_set_irq_funcs(struct amdgpu_device *adev)
 	adev->gmc.vm_fault.num_types = 1;
 	adev->gmc.vm_fault.funcs = &gmc_v9_0_irq_funcs;
 
-	adev->gmc.ecc_irq.num_types = 1;
-	adev->gmc.ecc_irq.funcs = &gmc_v9_0_ecc_funcs;
+	if (!amdgpu_sriov_vf(adev)) {
+		adev->gmc.ecc_irq.num_types = 1;
+		adev->gmc.ecc_irq.funcs = &gmc_v9_0_ecc_funcs;
+	}
 }
 
 static uint32_t gmc_v9_0_get_invalidate_req(unsigned int vmid,
@@ -434,6 +443,18 @@ static bool gmc_v9_0_use_invalidate_semaphore(struct amdgpu_device *adev,
 		   adev->pdev->device == 0x15d8)));
 }
 
+static bool gmc_v9_0_get_atc_vmid_pasid_mapping_info(struct amdgpu_device *adev,
+					uint8_t vmid, uint16_t *p_pasid)
+{
+	uint32_t value;
+
+	value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+		     + vmid);
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
+}
+
 /*
  * GART
  * VMID 0 is the physical GPU addresses as used by the kernel.
@@ -532,6 +553,67 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	DRM_ERROR("Timeout waiting for VM flush ACK!\n");
 }
 
+/**
+ * gmc_v9_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+					uint16_t pasid, uint32_t flush_type,
+					bool all_hub)
+{
+	int vmid, i;
+	signed long r;
+	uint32_t seq;
+	uint16_t queried_pasid;
+	bool ret;
+	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+
+	if (adev->in_gpu_reset)
+		return -EIO;
+
+	if (ring->sched.ready) {
+		spin_lock(&adev->gfx.kiq.ring_lock);
+		amdgpu_ring_alloc(ring, kiq->pmf->invalidate_tlbs_size);
+		kiq->pmf->kiq_invalidate_tlbs(ring,
+					pasid, flush_type, all_hub);
+		amdgpu_fence_emit_polling(ring, &seq);
+		amdgpu_ring_commit(ring);
+		spin_unlock(&adev->gfx.kiq.ring_lock);
+		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
+		if (r < 1) {
+			DRM_ERROR("wait for kiq fence error: %ld.\n", r);
+			return -ETIME;
+		}
+
+		return 0;
+	}
+
+	for (vmid = 1; vmid < 16; vmid++) {
+
+		ret = gmc_v9_0_get_atc_vmid_pasid_mapping_info(adev, vmid,
+				&queried_pasid);
+		if (ret && queried_pasid == pasid) {
+			if (all_hub) {
+				for (i = 0; i < adev->num_vmhubs; i++)
+					gmc_v9_0_flush_gpu_tlb(adev, vmid,
+							i, 0);
+			} else {
+				gmc_v9_0_flush_gpu_tlb(adev, vmid,
+						AMDGPU_GFXHUB_0, 0);
+			}
+			break;
+		}
+	}
+
+	return 0;
+
+}
+
 static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 					    unsigned vmid, uint64_t pd_addr)
 {
@@ -693,6 +775,7 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
 
 static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v9_0_flush_gpu_tlb,
+	.flush_gpu_tlb_pasid = gmc_v9_0_flush_gpu_tlb_pasid,
 	.emit_flush_gpu_tlb = gmc_v9_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
 	.map_mtype = gmc_v9_0_map_mtype,
@@ -715,7 +798,15 @@ static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 		adev->umc.max_ras_err_cnt_per_query = UMC_V6_1_TOTAL_CHANNEL_NUM;
 		adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM;
 		adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM;
-		adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET;
+		adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_VG20;
+		adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0];
+		adev->umc.funcs = &umc_v6_1_funcs;
+		break;
+	case CHIP_ARCTURUS:
+		adev->umc.max_ras_err_cnt_per_query = UMC_V6_1_TOTAL_CHANNEL_NUM;
+		adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM;
+		adev->umc.umc_inst_num = UMC_V6_1_UMC_INSTANCE_NUM;
+		adev->umc.channel_offs = UMC_V6_1_PER_CHANNEL_OFFSET_ARCT;
 		adev->umc.channel_idx_tbl = &umc_v6_1_channel_idx_tbl[0][0];
 		adev->umc.funcs = &umc_v6_1_funcs;
 		break;
@@ -730,6 +821,9 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		adev->mmhub.funcs = &mmhub_v1_0_funcs;
 		break;
+	case CHIP_ARCTURUS:
+		adev->mmhub.funcs = &mmhub_v9_4_funcs;
+		break;
 	default:
 		break;
 	}
@@ -779,36 +873,6 @@ static bool gmc_v9_0_keep_stolen_memory(struct amdgpu_device *adev)
 	}
 }
 
-static int gmc_v9_0_allocate_vm_inv_eng(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *ring;
-	unsigned vm_inv_engs[AMDGPU_MAX_VMHUBS] =
-		{GFXHUB_FREE_VM_INV_ENGS_BITMAP, MMHUB_FREE_VM_INV_ENGS_BITMAP,
-		GFXHUB_FREE_VM_INV_ENGS_BITMAP};
-	unsigned i;
-	unsigned vmhub, inv_eng;
-
-	for (i = 0; i < adev->num_rings; ++i) {
-		ring = adev->rings[i];
-		vmhub = ring->funcs->vmhub;
-
-		inv_eng = ffs(vm_inv_engs[vmhub]);
-		if (!inv_eng) {
-			dev_err(adev->dev, "no VM inv eng for ring %s\n",
-				ring->name);
-			return -EINVAL;
-		}
-
-		ring->vm_inv_eng = inv_eng - 1;
-		vm_inv_engs[vmhub] &= ~(1 << ring->vm_inv_eng);
-
-		dev_info(adev->dev, "ring %s uses VM inv eng %u on hub %u\n",
-			 ring->name, ring->vm_inv_eng, ring->funcs->vmhub);
-	}
-
-	return 0;
-}
-
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -817,7 +881,7 @@ static int gmc_v9_0_late_init(void *handle)
 	if (!gmc_v9_0_keep_stolen_memory(adev))
 		amdgpu_bo_late_init(adev);
 
-	r = gmc_v9_0_allocate_vm_inv_eng(adev);
+	r = amdgpu_gmc_allocate_vm_inv_eng(adev);
 	if (r)
 		return r;
 	/* Check if ecc is available */
@@ -825,11 +889,12 @@ static int gmc_v9_0_late_init(void *handle)
 		switch (adev->asic_type) {
 		case CHIP_VEGA10:
 		case CHIP_VEGA20:
+		case CHIP_ARCTURUS:
 			r = amdgpu_atomfirmware_mem_ecc_supported(adev);
 			if (!r) {
 				DRM_INFO("ECC is not present.\n");
-				if (adev->df_funcs->enable_ecc_force_par_wr_rmw)
-					adev->df_funcs->enable_ecc_force_par_wr_rmw(adev, false);
+				if (adev->df.funcs->enable_ecc_force_par_wr_rmw)
+					adev->df.funcs->enable_ecc_force_par_wr_rmw(adev, false);
 			} else {
 				DRM_INFO("ECC is active.\n");
 			}
@@ -1034,7 +1099,7 @@ static int gmc_v9_0_sw_init(void *handle)
 		else
 			chansize = 128;
 
-		numchan = adev->df_funcs->get_hbm_channel_number(adev);
+		numchan = adev->df.funcs->get_hbm_channel_number(adev);
 		adev->gmc.vram_width = numchan * chansize;
 	}
 
@@ -1100,11 +1165,13 @@ static int gmc_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	/* interrupt sent to DF. */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DF, 0,
-			&adev->gmc.ecc_irq);
-	if (r)
-		return r;
+	if (!amdgpu_sriov_vf(adev)) {
+		/* interrupt sent to DF. */
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DF, 0,
+				      &adev->gmc.ecc_irq);
+		if (r)
+			return r;
+	}
 
 	/* Set the internal MC address mask
 	 * This is the max address of the GPU's
@@ -1290,12 +1357,13 @@ static int gmc_v9_0_hw_init(void *handle)
 	else
 		value = true;
 
-	gfxhub_v1_0_set_fault_enable_default(adev, value);
-	if (adev->asic_type == CHIP_ARCTURUS)
-		mmhub_v9_4_set_fault_enable_default(adev, value);
-	else
-		mmhub_v1_0_set_fault_enable_default(adev, value);
-
+	if (!amdgpu_sriov_vf(adev)) {
+		gfxhub_v1_0_set_fault_enable_default(adev, value);
+		if (adev->asic_type == CHIP_ARCTURUS)
+			mmhub_v9_4_set_fault_enable_default(adev, value);
+		else
+			mmhub_v1_0_set_fault_enable_default(adev, value);
+	}
 	for (i = 0; i < adev->num_vmhubs; ++i)
 		gmc_v9_0_flush_gpu_tlb(adev, 0, i, 0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
index 971c0840358f..e0585e8c6c1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
@@ -24,24 +24,6 @@
 #ifndef __GMC_V9_0_H__
 #define __GMC_V9_0_H__
 
-	/*
-	 * The latest engine allocation on gfx9 is:
-	 * Engine 2, 3: firmware
-	 * Engine 0, 1, 4~16: amdgpu ring,
-	 *                    subject to change when ring number changes
-	 * Engine 17: Gart flushes
-	 */
-#define GFXHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
-#define MMHUB_FREE_VM_INV_ENGS_BITMAP		0x1FFF3
-
 extern const struct amd_ip_funcs gmc_v9_0_ip_funcs;
 extern const struct amdgpu_ip_block_version gmc_v9_0_ip_block;
-
-/* amdgpu_amdkfd*.c */
-void gfxhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t value);
-void mmhub_v1_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
-				uint64_t value);
-void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, int hubid,
-				uint32_t vmid, uint64_t value);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
new file mode 100644
index 000000000000..0debfd9f428c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
@@ -0,0 +1,586 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "soc15.h"
+#include "soc15d.h"
+#include "vcn_v1_0.h"
+
+#include "vcn/vcn_1_0_offset.h"
+#include "vcn/vcn_1_0_sh_mask.h"
+
+static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
+static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+
+static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[(*ptr)++] = 0;
+		ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
+	} else {
+		ring->ring[(*ptr)++] = reg_offset;
+		ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
+	}
+	ring->ring[(*ptr)++] = val;
+}
+
+static void jpeg_v1_0_decode_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	uint32_t reg, reg_offset, val, mask, i;
+
+	// 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
+	reg_offset = (reg << 2);
+	val = lower_32_bits(ring->gpu_addr);
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
+	reg_offset = (reg << 2);
+	val = upper_32_bits(ring->gpu_addr);
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 3rd to 5th: issue MEM_READ commands
+	for (i = 0; i <= 2; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
+		ring->ring[ptr++] = 0;
+	}
+
+	// 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x13;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 7th: program mmUVD_JRBC_RB_REF_DATA
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	mask = 0x1;
+
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = 0x01400200;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = val;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[ptr++] = 0;
+		ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
+	} else {
+		ring->ring[ptr++] = reg_offset;
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
+	}
+	ring->ring[ptr++] = mask;
+
+	//9th to 21st: insert no-op
+	for (i = 0; i <= 12; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ring->ring[ptr++] = 0;
+	}
+
+	//22nd: reset mmUVD_JRBC_RB_RPTR
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_RPTR);
+	reg_offset = (reg << 2);
+	val = 0;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	//23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
+	reg = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x12;
+	jpeg_v1_0_decode_ring_patch_wreg(ring, &ptr, reg_offset, val);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t jpeg_v1_0_decode_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t jpeg_v1_0_decode_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void jpeg_v1_0_decode_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+}
+
+/**
+ * jpeg_v1_0_decode_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+static void jpeg_v1_0_decode_ring_insert_start(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x80010000);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+static void jpeg_v1_0_decode_ring_insert_end(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x00010000);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+static void jpeg_v1_0_decode_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				     unsigned flags)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0xffffffff);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x3fbc);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x1);
+
+	/* emit trap */
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * jpeg_v1_0_decode_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring,
+					struct amdgpu_job *job,
+					struct amdgpu_ib *ib,
+					uint32_t flags)
+{
+	struct amdgpu_device *adev = ring->adev;
+	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, ib->length_dw);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+	amdgpu_ring_write(ring, 0x2);
+}
+
+static void jpeg_v1_0_decode_ring_emit_reg_wait(struct amdgpu_ring *ring,
+					    uint32_t reg, uint32_t val,
+					    uint32_t mask)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, val);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE3));
+	}
+	amdgpu_ring_write(ring, mask);
+}
+
+static void jpeg_v1_0_decode_ring_emit_vm_flush(struct amdgpu_ring *ring,
+		unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+	uint32_t data0, data1, mask;
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for register write */
+	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+	data1 = lower_32_bits(pd_addr);
+	mask = 0xffffffff;
+	jpeg_v1_0_decode_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+static void jpeg_v1_0_decode_ring_emit_wreg(struct amdgpu_ring *ring,
+					uint32_t reg, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+			((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	}
+	amdgpu_ring_write(ring, val);
+}
+
+static void jpeg_v1_0_decode_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
+static int jpeg_v1_0_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static int jpeg_v1_0_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("IH: JPEG decode TRAP\n");
+
+	switch (entry->src_id) {
+	case 126:
+		amdgpu_fence_process(&adev->jpeg.inst->ring_dec);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v1_0_early_init - set function pointers
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Set ring and irq function pointers
+ */
+int jpeg_v1_0_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev->jpeg.num_jpeg_inst = 1;
+
+	jpeg_v1_0_set_dec_ring_funcs(adev);
+	jpeg_v1_0_set_irq_funcs(adev);
+
+	return 0;
+}
+
+/**
+ * jpeg_v1_0_sw_init - sw init for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ */
+int jpeg_v1_0_sw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int r;
+
+	/* JPEG TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->jpeg.inst->irq);
+	if (r)
+		return r;
+
+	ring = &adev->jpeg.inst->ring_dec;
+	sprintf(ring->name, "jpeg_dec");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, 0);
+	if (r)
+		return r;
+
+	adev->jpeg.internal.jpeg_pitch = adev->jpeg.inst->external.jpeg_pitch =
+		SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH);
+
+	return 0;
+}
+
+/**
+ * jpeg_v1_0_sw_fini - sw fini for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * JPEG free up sw allocation
+ */
+void jpeg_v1_0_sw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	amdgpu_ring_fini(&adev->jpeg.inst[0].ring_dec);
+}
+
+/**
+ * jpeg_v1_0_start - start JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the JPEG block
+ */
+void jpeg_v1_0_start(struct amdgpu_device *adev, int mode)
+{
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+
+	if (mode == 0) {
+		WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
+				UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
+		WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR, 0);
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, 0);
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
+	}
+
+	/* initialize wptr */
+	ring->wptr = RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+
+	/* copy patch commands to the jpeg ring */
+	jpeg_v1_0_decode_ring_set_patch_ring(ring,
+		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+}
+
+static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.nop = PACKET0(0x81ff, 0),
+	.support_64bit_ptrs = false,
+	.no_user_fence = true,
+	.vmhub = AMDGPU_MMHUB_0,
+	.extra_dw = 64,
+	.get_rptr = jpeg_v1_0_decode_ring_get_rptr,
+	.get_wptr = jpeg_v1_0_decode_ring_get_wptr,
+	.set_wptr = jpeg_v1_0_decode_ring_set_wptr,
+	.emit_frame_size =
+		6 + 6 + /* hdp invalidate / flush */
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* jpeg_v1_0_decode_ring_emit_vm_flush */
+		26 + 26 + /* jpeg_v1_0_decode_ring_emit_fence x2 vm fence */
+		6,
+	.emit_ib_size = 22, /* jpeg_v1_0_decode_ring_emit_ib */
+	.emit_ib = jpeg_v1_0_decode_ring_emit_ib,
+	.emit_fence = jpeg_v1_0_decode_ring_emit_fence,
+	.emit_vm_flush = jpeg_v1_0_decode_ring_emit_vm_flush,
+	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
+	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
+	.insert_nop = jpeg_v1_0_decode_ring_nop,
+	.insert_start = jpeg_v1_0_decode_ring_insert_start,
+	.insert_end = jpeg_v1_0_decode_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = vcn_v1_0_ring_begin_use,
+	.end_use = amdgpu_vcn_ring_end_use,
+	.emit_wreg = jpeg_v1_0_decode_ring_emit_wreg,
+	.emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->ring_dec.funcs = &jpeg_v1_0_decode_ring_vm_funcs;
+	DRM_INFO("JPEG decode is enabled in VM mode\n");
+}
+
+static const struct amdgpu_irq_src_funcs jpeg_v1_0_irq_funcs = {
+	.set = jpeg_v1_0_set_interrupt_state,
+	.process = jpeg_v1_0_process_interrupt,
+};
+
+static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
new file mode 100644
index 000000000000..bbf33a6a3972
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __JPEG_V1_0_H__
+#define __JPEG_V1_0_H__
+
+int jpeg_v1_0_early_init(void *handle);
+int jpeg_v1_0_sw_init(void *handle);
+void jpeg_v1_0_sw_fini(void *handle);
+void jpeg_v1_0_start(struct amdgpu_device *adev, int mode);
+
+#endif /*__JPEG_V1_0_H__*/
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
new file mode 100644
index 000000000000..a78292d84854
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -0,0 +1,827 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "amdgpu_pm.h"
+#include "soc15.h"
+#include "soc15d.h"
+
+#include "vcn/vcn_2_0_0_offset.h"
+#include "vcn/vcn_2_0_0_sh_mask.h"
+#include "ivsrcid/vcn/irqsrcs_vcn_2_0.h"
+
+#define mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET 			0x1bfff
+#define mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET				0x4029
+#define mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET				0x402a
+#define mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET				0x402b
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ea
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40eb
+#define mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET				0x40cf
+#define mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET				0x40d1
+#define mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET 		0x40e8
+#define mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET		0x40e9
+#define mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET				0x4082
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ec
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40ed
+#define mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET			0x4085
+#define mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET				0x4084
+#define mmUVD_JRBC_STATUS_INTERNAL_OFFSET				0x4089
+#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET				0x401f
+
+#define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR				0x18000
+
+static void jpeg_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev);
+static void jpeg_v2_0_set_irq_funcs(struct amdgpu_device *adev);
+static int jpeg_v2_0_set_powergating_state(void *handle,
+				enum amd_powergating_state state);
+
+/**
+ * jpeg_v2_0_early_init - set function pointers
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Set ring and irq function pointers
+ */
+static int jpeg_v2_0_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	adev->jpeg.num_jpeg_inst = 1;
+
+	jpeg_v2_0_set_dec_ring_funcs(adev);
+	jpeg_v2_0_set_irq_funcs(adev);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_sw_init - sw init for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Load firmware and sw initialization
+ */
+static int jpeg_v2_0_sw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int r;
+
+	/* JPEG TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
+		VCN_2_0__SRCID__JPEG_DECODE, &adev->jpeg.inst->irq);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_sw_init(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	ring = &adev->jpeg.inst->ring_dec;
+	ring->use_doorbell = true;
+	ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1;
+	sprintf(ring->name, "jpeg_dec");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst->irq, 0);
+	if (r)
+		return r;
+
+	adev->jpeg.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
+	adev->jpeg.inst->external.jpeg_pitch = SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_PITCH);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_sw_fini - sw fini for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * JPEG suspend and free up sw allocation
+ */
+static int jpeg_v2_0_sw_fini(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_jpeg_suspend(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_sw_fini(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_0_hw_init - start and test JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ */
+static int jpeg_v2_0_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+	int r;
+
+	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+		(adev->doorbell_index.vcn.vcn_ring0_1 << 1), 0);
+
+	r = amdgpu_ring_test_helper(ring);
+	if (!r)
+		DRM_INFO("JPEG decode initialized successfully.\n");
+
+	return r;
+}
+
+/**
+ * jpeg_v2_0_hw_fini - stop the hardware block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Stop the JPEG block, mark ring as not ready any more
+ */
+static int jpeg_v2_0_hw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+
+	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
+	      RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS))
+		jpeg_v2_0_set_powergating_state(adev, AMD_PG_STATE_GATE);
+
+	ring->sched.ready = false;
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_suspend - suspend JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * HW fini and suspend JPEG block
+ */
+static int jpeg_v2_0_suspend(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = jpeg_v2_0_hw_fini(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_suspend(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_0_resume - resume JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Resume firmware and hw init JPEG block
+ */
+static int jpeg_v2_0_resume(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	r = jpeg_v2_0_hw_init(adev);
+
+	return r;
+}
+
+static int jpeg_v2_0_disable_power_gating(struct amdgpu_device *adev)
+{
+	uint32_t data;
+	int r = 0;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) {
+		data = 1 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
+		WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_PGFSM_CONFIG), data);
+
+		SOC15_WAIT_ON_RREG(JPEG, 0,
+			mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS_UVDJ_PWR_ON,
+			UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
+
+		if (r) {
+			DRM_ERROR("amdgpu: JPEG disable power gating failed\n");
+			return r;
+		}
+	}
+
+	/* Removing the anti hang mechanism to indicate the UVDJ tile is ON */
+	data = RREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS)) & ~0x1;
+	WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS), data);
+
+	return 0;
+}
+
+static int jpeg_v2_0_enable_power_gating(struct amdgpu_device* adev)
+{
+	if (adev->pg_flags & AMD_PG_SUPPORT_JPEG) {
+		uint32_t data;
+		int r = 0;
+
+		data = RREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS));
+		data &= ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK;
+		data |=  0x1; //UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_TILES_OFF;
+		WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JPEG_POWER_STATUS), data);
+
+		data = 2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
+		WREG32(SOC15_REG_OFFSET(JPEG, 0, mmUVD_PGFSM_CONFIG), data);
+
+		SOC15_WAIT_ON_RREG(JPEG, 0, mmUVD_PGFSM_STATUS,
+			(2 << UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT),
+			UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
+
+		if (r) {
+			DRM_ERROR("amdgpu: JPEG enable power gating failed\n");
+			return r;
+		}
+	}
+
+	return 0;
+}
+
+static void jpeg_v2_0_disable_clock_gating(struct amdgpu_device* adev)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_JPEG_MGCG)
+		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data &= ~JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+
+	data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL, data);
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE);
+	data &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
+		| JPEG_CGC_GATE__JPEG2_DEC_MASK
+		| JPEG_CGC_GATE__JPEG_ENC_MASK
+		| JPEG_CGC_GATE__JMCIF_MASK
+		| JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE, data);
+}
+
+static void jpeg_v2_0_enable_clock_gating(struct amdgpu_device* adev)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_JPEG_MGCG)
+		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data |= 0 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+
+	data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_CTRL, data);
+
+	data = RREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE);
+	data |= (JPEG_CGC_GATE__JPEG_DEC_MASK
+		|JPEG_CGC_GATE__JPEG2_DEC_MASK
+		|JPEG_CGC_GATE__JPEG_ENC_MASK
+		|JPEG_CGC_GATE__JMCIF_MASK
+		|JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, 0, mmJPEG_CGC_GATE, data);
+}
+
+/**
+ * jpeg_v2_0_start - start JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the JPEG block
+ */
+static int jpeg_v2_0_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring = &adev->jpeg.inst->ring_dec;
+	int r;
+
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_jpeg(adev, true);
+
+	/* disable power gating */
+	r = jpeg_v2_0_disable_power_gating(adev);
+	if (r)
+		return r;
+
+	/* JPEG disable CGC */
+	jpeg_v2_0_disable_clock_gating(adev);
+
+	WREG32_SOC15(JPEG, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
+
+	/* enable JMI channel */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JMI_CNTL), 0,
+		~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	/* enable System Interrupt for JRBC */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, 0, mmJPEG_SYS_INT_EN),
+		JPEG_SYS_INT_EN__DJRBC_MASK,
+		~JPEG_SYS_INT_EN__DJRBC_MASK);
+
+	WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+	WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+		lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(JPEG, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+		upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR, 0);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, 0);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+	WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
+	ring->wptr = RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_stop - stop JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * stop the JPEG block
+ */
+static int jpeg_v2_0_stop(struct amdgpu_device *adev)
+{
+	int r;
+
+	/* reset JMI */
+	WREG32_P(SOC15_REG_OFFSET(JPEG, 0, mmUVD_JMI_CNTL),
+		UVD_JMI_CNTL__SOFT_RESET_MASK,
+		~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+	/* enable JPEG CGC */
+	jpeg_v2_0_enable_clock_gating(adev);
+
+	/* enable power gating */
+	r = jpeg_v2_0_enable_power_gating(adev);
+	if (r)
+		return r;
+
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_jpeg(adev, false);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_0_dec_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t jpeg_v2_0_dec_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t jpeg_v2_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell)
+		return adev->wb.wb[ring->wptr_offs];
+	else
+		return RREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void jpeg_v2_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell) {
+		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
+	} else {
+		WREG32_SOC15(JPEG, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+	}
+}
+
+/**
+ * jpeg_v2_0_dec_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+void jpeg_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x80010000);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+void jpeg_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x00010000);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+void jpeg_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				unsigned flags)
+{
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
+		0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x3fbc);
+
+	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x1);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
+	amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * jpeg_v2_0_dec_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
+				struct amdgpu_job *job,
+				struct amdgpu_ib *ib,
+				uint32_t flags)
+{
+	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, ib->length_dw);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,	PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x2);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_STATUS_INTERNAL_OFFSET,
+		0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+	amdgpu_ring_write(ring, 0x2);
+}
+
+void jpeg_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
+{
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, val);
+
+	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+			0, 0, PACKETJ_TYPE3));
+	}
+	amdgpu_ring_write(ring, mask);
+}
+
+void jpeg_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+	uint32_t data0, data1, mask;
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for register write */
+	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+	data1 = lower_32_bits(pd_addr);
+	mask = 0xffffffff;
+	jpeg_v2_0_dec_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+void jpeg_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
+{
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
+		0, 0, PACKETJ_TYPE0));
+	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
+			0, 0, PACKETJ_TYPE0));
+	}
+	amdgpu_ring_write(ring, val);
+}
+
+void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
+static bool jpeg_v2_0_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	return ((RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS) &
+		UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
+		UVD_JRBC_STATUS__RB_JOB_DONE_MASK);
+}
+
+static int jpeg_v2_0_wait_for_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret = 0;
+
+	SOC15_WAIT_ON_RREG(JPEG, 0, mmUVD_JRBC_STATUS, UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
+		UVD_JRBC_STATUS__RB_JOB_DONE_MASK, ret);
+
+	return ret;
+}
+
+static int jpeg_v2_0_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+
+	if (enable) {
+		if (jpeg_v2_0_is_idle(handle))
+			return -EBUSY;
+		jpeg_v2_0_enable_clock_gating(adev);
+	} else {
+		jpeg_v2_0_disable_clock_gating(adev);
+	}
+
+	return 0;
+}
+
+static int jpeg_v2_0_set_powergating_state(void *handle,
+					enum amd_powergating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret;
+
+	if (state == adev->jpeg.cur_state)
+		return 0;
+
+	if (state == AMD_PG_STATE_GATE)
+		ret = jpeg_v2_0_stop(adev);
+	else
+		ret = jpeg_v2_0_start(adev);
+
+	if (!ret)
+		adev->jpeg.cur_state = state;
+
+	return ret;
+}
+
+static int jpeg_v2_0_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static int jpeg_v2_0_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("IH: JPEG TRAP\n");
+
+	switch (entry->src_id) {
+	case VCN_2_0__SRCID__JPEG_DECODE:
+		amdgpu_fence_process(&adev->jpeg.inst->ring_dec);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+static const struct amd_ip_funcs jpeg_v2_0_ip_funcs = {
+	.name = "jpeg_v2_0",
+	.early_init = jpeg_v2_0_early_init,
+	.late_init = NULL,
+	.sw_init = jpeg_v2_0_sw_init,
+	.sw_fini = jpeg_v2_0_sw_fini,
+	.hw_init = jpeg_v2_0_hw_init,
+	.hw_fini = jpeg_v2_0_hw_fini,
+	.suspend = jpeg_v2_0_suspend,
+	.resume = jpeg_v2_0_resume,
+	.is_idle = jpeg_v2_0_is_idle,
+	.wait_for_idle = jpeg_v2_0_wait_for_idle,
+	.check_soft_reset = NULL,
+	.pre_soft_reset = NULL,
+	.soft_reset = NULL,
+	.post_soft_reset = NULL,
+	.set_clockgating_state = jpeg_v2_0_set_clockgating_state,
+	.set_powergating_state = jpeg_v2_0_set_powergating_state,
+};
+
+static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.vmhub = AMDGPU_MMHUB_0,
+	.get_rptr = jpeg_v2_0_dec_ring_get_rptr,
+	.get_wptr = jpeg_v2_0_dec_ring_get_wptr,
+	.set_wptr = jpeg_v2_0_dec_ring_set_wptr,
+	.emit_frame_size =
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* jpeg_v2_0_dec_ring_emit_vm_flush */
+		18 + 18 + /* jpeg_v2_0_dec_ring_emit_fence x2 vm fence */
+		8 + 16,
+	.emit_ib_size = 22, /* jpeg_v2_0_dec_ring_emit_ib */
+	.emit_ib = jpeg_v2_0_dec_ring_emit_ib,
+	.emit_fence = jpeg_v2_0_dec_ring_emit_fence,
+	.emit_vm_flush = jpeg_v2_0_dec_ring_emit_vm_flush,
+	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
+	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
+	.insert_nop = jpeg_v2_0_dec_ring_nop,
+	.insert_start = jpeg_v2_0_dec_ring_insert_start,
+	.insert_end = jpeg_v2_0_dec_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_jpeg_ring_begin_use,
+	.end_use = amdgpu_jpeg_ring_end_use,
+	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
+	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+static void jpeg_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->ring_dec.funcs = &jpeg_v2_0_dec_ring_vm_funcs;
+	DRM_INFO("JPEG decode is enabled in VM mode\n");
+}
+
+static const struct amdgpu_irq_src_funcs jpeg_v2_0_irq_funcs = {
+	.set = jpeg_v2_0_set_interrupt_state,
+	.process = jpeg_v2_0_process_interrupt,
+};
+
+static void jpeg_v2_0_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->jpeg.inst->irq.num_types = 1;
+	adev->jpeg.inst->irq.funcs = &jpeg_v2_0_irq_funcs;
+}
+
+const struct amdgpu_ip_block_version jpeg_v2_0_ip_block =
+{
+		.type = AMD_IP_BLOCK_TYPE_JPEG,
+		.major = 2,
+		.minor = 0,
+		.rev = 0,
+		.funcs = &jpeg_v2_0_ip_funcs,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
new file mode 100644
index 000000000000..15a344ed340f
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __JPEG_V2_0_H__
+#define __JPEG_V2_0_H__
+
+void jpeg_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring);
+void jpeg_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring);
+void jpeg_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				unsigned flags);
+void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_job *job,
+				struct amdgpu_ib *ib, uint32_t flags);
+void jpeg_v2_0_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask);
+void jpeg_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned vmid, uint64_t pd_addr);
+void jpeg_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count);
+
+extern const struct amdgpu_ip_block_version jpeg_v2_0_ip_block;
+
+#endif /* __JPEG_V2_0_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
new file mode 100644
index 000000000000..2c58939e6ad0
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -0,0 +1,641 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_jpeg.h"
+#include "soc15.h"
+#include "soc15d.h"
+#include "jpeg_v2_0.h"
+
+#include "vcn/vcn_2_5_offset.h"
+#include "vcn/vcn_2_5_sh_mask.h"
+#include "ivsrcid/vcn/irqsrcs_vcn_2_0.h"
+
+#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET			0x401f
+
+#define JPEG25_MAX_HW_INSTANCES_ARCTURUS			2
+
+static void jpeg_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev);
+static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev);
+static int jpeg_v2_5_set_powergating_state(void *handle,
+				enum amd_powergating_state state);
+
+static int amdgpu_ih_clientid_jpeg[] = {
+	SOC15_IH_CLIENTID_VCN,
+	SOC15_IH_CLIENTID_VCN1
+};
+
+/**
+ * jpeg_v2_5_early_init - set function pointers
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Set ring and irq function pointers
+ */
+static int jpeg_v2_5_early_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		u32 harvest;
+		int i;
+
+		adev->jpeg.num_jpeg_inst = JPEG25_MAX_HW_INSTANCES_ARCTURUS;
+		for (i = 0; i < adev->jpeg.num_jpeg_inst; i++) {
+			harvest = RREG32_SOC15(JPEG, i, mmCC_UVD_HARVESTING);
+			if (harvest & CC_UVD_HARVESTING__UVD_DISABLE_MASK)
+				adev->jpeg.harvest_config |= 1 << i;
+		}
+
+		if (adev->jpeg.harvest_config == (AMDGPU_JPEG_HARVEST_JPEG0 |
+						 AMDGPU_JPEG_HARVEST_JPEG1))
+			return -ENOENT;
+	} else
+		adev->jpeg.num_jpeg_inst = 1;
+
+	jpeg_v2_5_set_dec_ring_funcs(adev);
+	jpeg_v2_5_set_irq_funcs(adev);
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_sw_init - sw init for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Load firmware and sw initialization
+ */
+static int jpeg_v2_5_sw_init(void *handle)
+{
+	struct amdgpu_ring *ring;
+	int i, r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		/* JPEG TRAP */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_jpeg[i],
+				VCN_2_0__SRCID__JPEG_DECODE, &adev->jpeg.inst[i].irq);
+		if (r)
+			return r;
+	}
+
+	r = amdgpu_jpeg_sw_init(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		ring->use_doorbell = true;
+		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + 8 * i;
+		sprintf(ring->name, "jpeg_dec_%d", i);
+		r = amdgpu_ring_init(adev, ring, 512, &adev->jpeg.inst[i].irq, 0);
+		if (r)
+			return r;
+
+		adev->jpeg.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
+		adev->jpeg.inst[i].external.jpeg_pitch = SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_PITCH);
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_sw_fini - sw fini for JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * JPEG suspend and free up sw allocation
+ */
+static int jpeg_v2_5_sw_fini(void *handle)
+{
+	int r;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	r = amdgpu_jpeg_suspend(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_sw_fini(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_5_hw_init - start and test JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ */
+static int jpeg_v2_5_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int i, r;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+			(adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8 * i, i);
+
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
+			return r;
+	}
+
+	DRM_INFO("JPEG decode initialized successfully.\n");
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_hw_fini - stop the hardware block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Stop the JPEG block, mark ring as not ready any more
+ */
+static int jpeg_v2_5_hw_fini(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct amdgpu_ring *ring;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
+		      RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS))
+			jpeg_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
+
+		ring->sched.ready = false;
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_suspend - suspend JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * HW fini and suspend JPEG block
+ */
+static int jpeg_v2_5_suspend(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = jpeg_v2_5_hw_fini(adev);
+	if (r)
+		return r;
+
+	r = amdgpu_jpeg_suspend(adev);
+
+	return r;
+}
+
+/**
+ * jpeg_v2_5_resume - resume JPEG block
+ *
+ * @handle: amdgpu_device pointer
+ *
+ * Resume firmware and hw init JPEG block
+ */
+static int jpeg_v2_5_resume(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = amdgpu_jpeg_resume(adev);
+	if (r)
+		return r;
+
+	r = jpeg_v2_5_hw_init(adev);
+
+	return r;
+}
+
+static void jpeg_v2_5_disable_clock_gating(struct amdgpu_device* adev, int inst)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL);
+	if (adev->cg_flags & AMD_CG_SUPPORT_JPEG_MGCG)
+		data |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		data &= ~JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+
+	data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL, data);
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE);
+	data &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
+		| JPEG_CGC_GATE__JPEG2_DEC_MASK
+		| JPEG_CGC_GATE__JPEG_ENC_MASK
+		| JPEG_CGC_GATE__JMCIF_MASK
+		| JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE, data);
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL);
+	data &= ~(JPEG_CGC_CTRL__JPEG_DEC_MODE_MASK
+		| JPEG_CGC_CTRL__JPEG2_DEC_MODE_MASK
+		| JPEG_CGC_CTRL__JMCIF_MODE_MASK
+		| JPEG_CGC_CTRL__JRBBM_MODE_MASK);
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_CTRL, data);
+}
+
+static void jpeg_v2_5_enable_clock_gating(struct amdgpu_device* adev, int inst)
+{
+	uint32_t data;
+
+	data = RREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE);
+	data |= (JPEG_CGC_GATE__JPEG_DEC_MASK
+		|JPEG_CGC_GATE__JPEG2_DEC_MASK
+		|JPEG_CGC_GATE__JPEG_ENC_MASK
+		|JPEG_CGC_GATE__JMCIF_MASK
+		|JPEG_CGC_GATE__JRBBM_MASK);
+	WREG32_SOC15(JPEG, inst, mmJPEG_CGC_GATE, data);
+}
+
+/**
+ * jpeg_v2_5_start - start JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Setup and start the JPEG block
+ */
+static int jpeg_v2_5_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ring = &adev->jpeg.inst[i].ring_dec;
+		/* disable anti hang mechanism */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS), 0,
+			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+
+		/* JPEG disable CGC */
+		jpeg_v2_5_disable_clock_gating(adev, i);
+
+		/* MJPEG global tiling registers */
+		WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX8_ADDR_CONFIG,
+			adev->gfx.config.gb_addr_config);
+		WREG32_SOC15(JPEG, i, mmJPEG_DEC_GFX10_ADDR_CONFIG,
+			adev->gfx.config.gb_addr_config);
+
+		/* enable JMI channel */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL), 0,
+			~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+		/* enable System Interrupt for JRBC */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmJPEG_SYS_INT_EN),
+			JPEG_SYS_INT_EN__DJRBC_MASK,
+			~JPEG_SYS_INT_EN__DJRBC_MASK);
+
+		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_VMID, 0);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
+			lower_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
+			upper_32_bits(ring->gpu_addr));
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_RPTR, 0);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR, 0);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+		WREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
+		ring->wptr = RREG32_SOC15(JPEG, i, mmUVD_JRBC_RB_WPTR);
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_stop - stop JPEG block
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * stop the JPEG block
+ */
+static int jpeg_v2_5_stop(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		/* reset JMI */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JMI_CNTL),
+			UVD_JMI_CNTL__SOFT_RESET_MASK,
+			~UVD_JMI_CNTL__SOFT_RESET_MASK);
+
+		jpeg_v2_5_enable_clock_gating(adev, i);
+
+		/* enable anti hang mechanism */
+		WREG32_P(SOC15_REG_OFFSET(JPEG, i, mmUVD_JPEG_POWER_STATUS),
+			UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
+			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
+	}
+
+	return 0;
+}
+
+/**
+ * jpeg_v2_5_dec_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t jpeg_v2_5_dec_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * jpeg_v2_5_dec_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t jpeg_v2_5_dec_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell)
+		return adev->wb.wb[ring->wptr_offs];
+	else
+		return RREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * jpeg_v2_5_dec_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void jpeg_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	if (ring->use_doorbell) {
+		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
+	} else {
+		WREG32_SOC15(JPEG, ring->me, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+	}
+}
+
+static bool jpeg_v2_5_is_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i, ret = 1;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		ret &= (((RREG32_SOC15(JPEG, i, mmUVD_JRBC_STATUS) &
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK) ==
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK));
+	}
+
+	return ret;
+}
+
+static int jpeg_v2_5_wait_for_idle(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int i, ret = 0;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		SOC15_WAIT_ON_RREG(JPEG, i, mmUVD_JRBC_STATUS,
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK,
+			UVD_JRBC_STATUS__RB_JOB_DONE_MASK, ret);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int jpeg_v2_5_set_clockgating_state(void *handle,
+					  enum amd_clockgating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		if (enable) {
+			if (jpeg_v2_5_is_idle(handle))
+				return -EBUSY;
+			jpeg_v2_5_enable_clock_gating(adev, i);
+		} else {
+			jpeg_v2_5_disable_clock_gating(adev, i);
+		}
+	}
+
+	return 0;
+}
+
+static int jpeg_v2_5_set_powergating_state(void *handle,
+					  enum amd_powergating_state state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int ret;
+
+	if(state == adev->jpeg.cur_state)
+		return 0;
+
+	if (state == AMD_PG_STATE_GATE)
+		ret = jpeg_v2_5_stop(adev);
+	else
+		ret = jpeg_v2_5_start(adev);
+
+	if(!ret)
+		adev->jpeg.cur_state = state;
+
+	return ret;
+}
+
+static int jpeg_v2_5_set_interrupt_state(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	return 0;
+}
+
+static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	uint32_t ip_instance;
+
+	switch (entry->client_id) {
+	case SOC15_IH_CLIENTID_VCN:
+		ip_instance = 0;
+		break;
+	case SOC15_IH_CLIENTID_VCN1:
+		ip_instance = 1;
+		break;
+	default:
+		DRM_ERROR("Unhandled client id: %d\n", entry->client_id);
+		return 0;
+	}
+
+	DRM_DEBUG("IH: JPEG TRAP\n");
+
+	switch (entry->src_id) {
+	case VCN_2_0__SRCID__JPEG_DECODE:
+		amdgpu_fence_process(&adev->jpeg.inst[ip_instance].ring_dec);
+		break;
+	default:
+		DRM_ERROR("Unhandled interrupt: %d %d\n",
+			  entry->src_id, entry->src_data[0]);
+		break;
+	}
+
+	return 0;
+}
+
+static const struct amd_ip_funcs jpeg_v2_5_ip_funcs = {
+	.name = "jpeg_v2_5",
+	.early_init = jpeg_v2_5_early_init,
+	.late_init = NULL,
+	.sw_init = jpeg_v2_5_sw_init,
+	.sw_fini = jpeg_v2_5_sw_fini,
+	.hw_init = jpeg_v2_5_hw_init,
+	.hw_fini = jpeg_v2_5_hw_fini,
+	.suspend = jpeg_v2_5_suspend,
+	.resume = jpeg_v2_5_resume,
+	.is_idle = jpeg_v2_5_is_idle,
+	.wait_for_idle = jpeg_v2_5_wait_for_idle,
+	.check_soft_reset = NULL,
+	.pre_soft_reset = NULL,
+	.soft_reset = NULL,
+	.post_soft_reset = NULL,
+	.set_clockgating_state = jpeg_v2_5_set_clockgating_state,
+	.set_powergating_state = jpeg_v2_5_set_powergating_state,
+};
+
+static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.vmhub = AMDGPU_MMHUB_1,
+	.get_rptr = jpeg_v2_5_dec_ring_get_rptr,
+	.get_wptr = jpeg_v2_5_dec_ring_get_wptr,
+	.set_wptr = jpeg_v2_5_dec_ring_set_wptr,
+	.emit_frame_size =
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* jpeg_v2_5_dec_ring_emit_vm_flush */
+		18 + 18 + /* jpeg_v2_5_dec_ring_emit_fence x2 vm fence */
+		8 + 16,
+	.emit_ib_size = 22, /* jpeg_v2_5_dec_ring_emit_ib */
+	.emit_ib = jpeg_v2_0_dec_ring_emit_ib,
+	.emit_fence = jpeg_v2_0_dec_ring_emit_fence,
+	.emit_vm_flush = jpeg_v2_0_dec_ring_emit_vm_flush,
+	.test_ring = amdgpu_jpeg_dec_ring_test_ring,
+	.test_ib = amdgpu_jpeg_dec_ring_test_ib,
+	.insert_nop = jpeg_v2_0_dec_ring_nop,
+	.insert_start = jpeg_v2_0_dec_ring_insert_start,
+	.insert_end = jpeg_v2_0_dec_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_jpeg_ring_begin_use,
+	.end_use = amdgpu_jpeg_ring_end_use,
+	.emit_wreg = jpeg_v2_0_dec_ring_emit_wreg,
+	.emit_reg_wait = jpeg_v2_0_dec_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+};
+
+static void jpeg_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		adev->jpeg.inst[i].ring_dec.funcs = &jpeg_v2_5_dec_ring_vm_funcs;
+		adev->jpeg.inst[i].ring_dec.me = i;
+		DRM_INFO("JPEG(%d) JPEG decode is enabled in VM mode\n", i);
+	}
+}
+
+static const struct amdgpu_irq_src_funcs jpeg_v2_5_irq_funcs = {
+	.set = jpeg_v2_5_set_interrupt_state,
+	.process = jpeg_v2_5_process_interrupt,
+};
+
+static void jpeg_v2_5_set_irq_funcs(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
+		if (adev->jpeg.harvest_config & (1 << i))
+			continue;
+
+		adev->jpeg.inst[i].irq.num_types = 1;
+		adev->jpeg.inst[i].irq.funcs = &jpeg_v2_5_irq_funcs;
+	}
+}
+
+const struct amdgpu_ip_block_version jpeg_v2_5_ip_block =
+{
+		.type = AMD_IP_BLOCK_TYPE_JPEG,
+		.major = 2,
+		.minor = 5,
+		.rev = 0,
+		.funcs = &jpeg_v2_5_ip_funcs,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/gp102.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.h
index fde6328c6d71..2b4087c02620 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/gp102.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ * Copyright 2019 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -14,17 +14,16 @@
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
  */
 
-#include "priv.h"
+#ifndef __JPEG_V2_5_H__
+#define __JPEG_V2_5_H__
+
+extern const struct amdgpu_ip_block_version jpeg_v2_5_ip_block;
 
-int
-gp102_nvdec_new(struct nvkm_device *device, int index,
-		struct nvkm_nvdec **pnvdec)
-{
-	return nvkm_nvdec_new_(device, index, pnvdec);
-}
+#endif /* __JPEG_V2_5_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 28105e4af507..adfd8a6171eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -27,17 +27,13 @@
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
 #include "mmhub/mmhub_1_0_default.h"
-#include "mmhub/mmhub_9_4_0_offset.h"
 #include "vega10_enum.h"
-
+#include "soc15.h"
 #include "soc15_common.h"
 
 #define mmDAGB0_CNTL_MISC2_RV 0x008f
 #define mmDAGB0_CNTL_MISC2_RV_BASE_IDX 0
 
-#define EA_EDC_CNT_MASK 0x3
-#define EA_EDC_CNT_SHIFT 0x2
-
 u64 mmhub_v1_0_get_fb_location(struct amdgpu_device *adev)
 {
 	u64 base = RREG32_SOC15(MMHUB, 0, mmMC_VM_FB_LOCATION_BASE);
@@ -564,59 +560,191 @@ void mmhub_v1_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
 
+static const struct soc15_ras_field_entry mmhub_v1_0_ras_fields[] = {
+	{ "MMEA0_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT_VG20, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2_VG20, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT_VG20, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2_VG20, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	}
+};
+
+static const struct soc15_reg_entry mmhub_v1_0_edc_cnt_regs[] = {
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT_VG20), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT_VG20), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20), 0, 0, 0},
+};
+
+static int mmhub_v1_0_get_ras_error_count(const struct soc15_reg_entry *reg,
+	uint32_t value, uint32_t *sec_count, uint32_t *ded_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt, ded_cnt;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v1_0_ras_fields); i++) {
+		if(mmhub_v1_0_ras_fields[i].reg_offset != reg->reg_offset)
+			continue;
+
+		sec_cnt = (value &
+				mmhub_v1_0_ras_fields[i].sec_count_mask) >>
+				mmhub_v1_0_ras_fields[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, SEC %d\n",
+				mmhub_v1_0_ras_fields[i].name,
+				sec_cnt);
+			*sec_count += sec_cnt;
+		}
+
+		ded_cnt = (value &
+				mmhub_v1_0_ras_fields[i].ded_count_mask) >>
+				mmhub_v1_0_ras_fields[i].ded_count_shift;
+		if (ded_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, DED %d\n",
+				mmhub_v1_0_ras_fields[i].name,
+				ded_cnt);
+			*ded_count += ded_cnt;
+		}
+	}
+
+	return 0;
+}
+
 static void mmhub_v1_0_query_ras_error_count(struct amdgpu_device *adev,
 					   void *ras_error_status)
 {
-	int i;
-	uint32_t ea0_edc_cnt, ea0_edc_cnt2;
-	uint32_t ea1_edc_cnt, ea1_edc_cnt2;
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
-
-	/* EDC CNT will be cleared automatically after read */
-	ea0_edc_cnt = RREG32_SOC15(MMHUB, 0, mmMMEA0_EDC_CNT_VG20);
-	ea0_edc_cnt2 = RREG32_SOC15(MMHUB, 0, mmMMEA0_EDC_CNT2_VG20);
-	ea1_edc_cnt = RREG32_SOC15(MMHUB, 0, mmMMEA1_EDC_CNT_VG20);
-	ea1_edc_cnt2 = RREG32_SOC15(MMHUB, 0, mmMMEA1_EDC_CNT2_VG20);
-
-	/* error count of each error type is recorded by 2 bits,
-	 * ce and ue count in EDC_CNT
-	 */
-	for (i = 0; i < 5; i++) {
-		err_data->ce_count += (ea0_edc_cnt & EA_EDC_CNT_MASK);
-		err_data->ce_count += (ea1_edc_cnt & EA_EDC_CNT_MASK);
-		ea0_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		err_data->ue_count += (ea0_edc_cnt & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt & EA_EDC_CNT_MASK);
-		ea0_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt >>= EA_EDC_CNT_SHIFT;
-	}
-	/* successive ue count in EDC_CNT */
-	for (i = 0; i < 5; i++) {
-		err_data->ue_count += (ea0_edc_cnt & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt & EA_EDC_CNT_MASK);
-		ea0_edc_cnt >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt >>= EA_EDC_CNT_SHIFT;
+	uint32_t sec_count = 0, ded_count = 0;
+	uint32_t i;
+	uint32_t reg_value;
+
+	err_data->ue_count = 0;
+	err_data->ce_count = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v1_0_edc_cnt_regs); i++) {
+		reg_value =
+			RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v1_0_edc_cnt_regs[i]));
+		if (reg_value)
+			mmhub_v1_0_get_ras_error_count(&mmhub_v1_0_edc_cnt_regs[i],
+				reg_value, &sec_count, &ded_count);
 	}
 
-	/* ce and ue count in EDC_CNT2 */
-	for (i = 0; i < 3; i++) {
-		err_data->ce_count += (ea0_edc_cnt2 & EA_EDC_CNT_MASK);
-		err_data->ce_count += (ea1_edc_cnt2 & EA_EDC_CNT_MASK);
-		ea0_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		err_data->ue_count += (ea0_edc_cnt2 & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt2 & EA_EDC_CNT_MASK);
-		ea0_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-	}
-	/* successive ue count in EDC_CNT2 */
-	for (i = 0; i < 6; i++) {
-		err_data->ue_count += (ea0_edc_cnt2 & EA_EDC_CNT_MASK);
-		err_data->ue_count += (ea1_edc_cnt2 & EA_EDC_CNT_MASK);
-		ea0_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-		ea1_edc_cnt2 >>= EA_EDC_CNT_SHIFT;
-	}
+	err_data->ce_count += sec_count;
+	err_data->ue_count += ded_count;
 }
 
 const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 66efe2f7bd76..5c42387c9274 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -21,6 +21,7 @@
  *
  */
 #include "amdgpu.h"
+#include "amdgpu_ras.h"
 #include "mmhub_v9_4.h"
 
 #include "mmhub/mmhub_9_4_1_offset.h"
@@ -29,7 +30,7 @@
 #include "athub/athub_1_0_offset.h"
 #include "athub/athub_1_0_sh_mask.h"
 #include "vega10_enum.h"
-
+#include "soc15.h"
 #include "soc15_common.h"
 
 #define MMHUB_NUM_INSTANCES			2
@@ -53,7 +54,7 @@ u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev)
 	return base;
 }
 
-void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, int hubid,
+static void mmhub_v9_4_setup_hubid_vm_pt_regs(struct amdgpu_device *adev, int hubid,
 				uint32_t vmid, uint64_t value)
 {
 	/* two registers distance between mmVML2VC0_VM_CONTEXT0_* to
@@ -79,7 +80,7 @@ static void mmhub_v9_4_init_gart_aperture_regs(struct amdgpu_device *adev,
 {
 	uint64_t pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
-	mmhub_v9_4_setup_vm_pt_regs(adev, hubid, 0, pt_base);
+	mmhub_v9_4_setup_hubid_vm_pt_regs(adev, hubid, 0, pt_base);
 
 	WREG32_SOC15_OFFSET(MMHUB, 0,
 			    mmVML2VC0_VM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
@@ -100,6 +101,16 @@ static void mmhub_v9_4_init_gart_aperture_regs(struct amdgpu_device *adev,
 			    (u32)(adev->gmc.gart_end >> 44));
 }
 
+void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base)
+{
+	int i;
+
+	for (i = 0; i < MMHUB_NUM_INSTANCES; i++)
+		mmhub_v9_4_setup_hubid_vm_pt_regs(adev, i, vmid,
+				page_table_base);
+}
+
 static void mmhub_v9_4_init_system_aperture_regs(struct amdgpu_device *adev,
 					         int hubid)
 {
@@ -117,45 +128,53 @@ static void mmhub_v9_4_init_system_aperture_regs(struct amdgpu_device *adev,
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
 			    adev->gmc.agp_start >> 24);
 
-	/* Program the system aperture low logical page number. */
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_LOW_ADDR,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
+	if (!amdgpu_sriov_vf(adev)) {
+		/* Program the system aperture low logical page number. */
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0, mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_LOW_ADDR,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18);
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0, mmVMSHAREDVC0_MC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18);
 
-	/* Set default page address. */
-	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
-		adev->vm_manager.vram_base_offset;
-	WREG32_SOC15_OFFSET(MMHUB, 0,
+		/* Set default page address. */
+		value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
+			adev->vm_manager.vram_base_offset;
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
 			mmVMSHAREDPF0_MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB,
 			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
 			(u32)(value >> 12));
-	WREG32_SOC15_OFFSET(MMHUB, 0,
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
 			mmVMSHAREDPF0_MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_MSB,
 			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
 			(u32)(value >> 44));
 
-	/* Program "protection fault". */
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    (u32)(adev->dummy_page_addr >> 12));
-	WREG32_SOC15_OFFSET(MMHUB, 0,
-			    mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
-			    (u32)((u64)adev->dummy_page_addr >> 44));
+		/* Program "protection fault". */
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
+			mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_LO32,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			(u32)(adev->dummy_page_addr >> 12));
+		WREG32_SOC15_OFFSET(
+			MMHUB, 0,
+			mmVML2PF0_VM_L2_PROTECTION_FAULT_DEFAULT_ADDR_HI32,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+			(u32)((u64)adev->dummy_page_addr >> 44));
 
-	tmp = RREG32_SOC15_OFFSET(MMHUB, 0,
-				  mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
-				  hubid * MMHUB_INSTANCE_REGISTER_OFFSET);
-	tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
-			    ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
-	WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
-			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
+		tmp = RREG32_SOC15_OFFSET(
+			MMHUB, 0, mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
+			hubid * MMHUB_INSTANCE_REGISTER_OFFSET);
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
+				    ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY, 1);
+		WREG32_SOC15_OFFSET(MMHUB, 0,
+				    mmVML2PF0_VM_L2_PROTECTION_FAULT_CNTL2,
+				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET,
+				    tmp);
+	}
 }
 
 static void mmhub_v9_4_init_tlb_regs(struct amdgpu_device *adev, int hubid)
@@ -313,7 +332,8 @@ static void mmhub_v9_4_setup_vmid_config(struct amdgpu_device *adev, int hubid)
 				    adev->vm_manager.block_size - 9);
 		/* Send no-retry XNACK on fault to suppress VM fault storm. */
 		tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT1_CNTL,
-				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
+				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
+				    !amdgpu_noretry);
 		WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT1_CNTL,
 				    hubid * MMHUB_INSTANCE_REGISTER_OFFSET + i,
 				    tmp);
@@ -356,30 +376,16 @@ int mmhub_v9_4_gart_enable(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < MMHUB_NUM_INSTANCES; i++) {
-		if (amdgpu_sriov_vf(adev)) {
-			/*
-			 * MC_VM_FB_LOCATION_BASE/TOP is NULL for VF, becuase
-			 * they are VF copy registers so vbios post doesn't
-			 * program them, for SRIOV driver need to program them
-			 */
-			WREG32_SOC15_OFFSET(MMHUB, 0,
-				     mmVMSHAREDVC0_MC_VM_FB_LOCATION_BASE,
-				     i * MMHUB_INSTANCE_REGISTER_OFFSET,
-				     adev->gmc.vram_start >> 24);
-			WREG32_SOC15_OFFSET(MMHUB, 0,
-				     mmVMSHAREDVC0_MC_VM_FB_LOCATION_TOP,
-				     i * MMHUB_INSTANCE_REGISTER_OFFSET,
-				     adev->gmc.vram_end >> 24);
-		}
-
 		/* GART Enable. */
 		mmhub_v9_4_init_gart_aperture_regs(adev, i);
 		mmhub_v9_4_init_system_aperture_regs(adev, i);
 		mmhub_v9_4_init_tlb_regs(adev, i);
-		mmhub_v9_4_init_cache_regs(adev, i);
+		if (!amdgpu_sriov_vf(adev))
+			mmhub_v9_4_init_cache_regs(adev, i);
 
 		mmhub_v9_4_enable_system_domain(adev, i);
-		mmhub_v9_4_disable_identity_aperture(adev, i);
+		if (!amdgpu_sriov_vf(adev))
+			mmhub_v9_4_disable_identity_aperture(adev, i);
 		mmhub_v9_4_setup_vmid_config(adev, i);
 		mmhub_v9_4_program_invalidation(adev, i);
 	}
@@ -655,3 +661,253 @@ void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 	if (data & ATCL2_0_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK)
 		*flags |= AMD_CG_SUPPORT_MC_LS;
 }
+
+static const struct soc15_ras_field_entry mmhub_v9_4_ras_fields[] = {
+	{ "MMEA0_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA0_EDC_CNT2, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA0_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, DRAMRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA0_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, DRAMWR_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA0_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, IORD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, IOWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA0_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, IOWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, GMIRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA0_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA0_EDC_CNT3, GMIWR_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_RRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, RRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, RRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_WRET_TAGMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, WRET_TAGMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, WRET_TAGMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, DRAMWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, IORD_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, IOWR_CMDMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT, IOWR_DATAMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIRD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIRD_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIRD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_CMDMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_DATAMEM_SEC_COUNT),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIRD_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2),
+	SOC15_REG_FIELD(MMEA1_EDC_CNT2, GMIWR_PAGEMEM_SED_COUNT),
+	0, 0,
+	},
+	{ "MMEA1_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, DRAMRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, DRAMWR_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_IORD_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, IORD_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_IOWR_CMDMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, IOWR_CMDMEM_DED_COUNT),
+	},
+	{ "MMEA1_IOWR_DATAMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, IOWR_DATAMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIRD_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, GMIRD_PAGEMEM_DED_COUNT),
+	},
+	{ "MMEA1_GMIWR_PAGEMEM", SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3),
+	0, 0,
+	SOC15_REG_FIELD(MMEA1_EDC_CNT3, GMIWR_PAGEMEM_DED_COUNT),
+	}
+};
+
+static const struct soc15_reg_entry mmhub_v9_4_edc_cnt_regs[] = {
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT2), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA0_EDC_CNT3), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT2), 0, 0, 0},
+   { SOC15_REG_ENTRY(MMHUB, 0, mmMMEA1_EDC_CNT3), 0, 0, 0},
+};
+
+static int mmhub_v9_4_get_ras_error_count(const struct soc15_reg_entry *reg,
+	uint32_t value, uint32_t *sec_count, uint32_t *ded_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt, ded_cnt;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_ras_fields); i++) {
+		if(mmhub_v9_4_ras_fields[i].reg_offset != reg->reg_offset)
+			continue;
+
+		sec_cnt = (value &
+				mmhub_v9_4_ras_fields[i].sec_count_mask) >>
+				mmhub_v9_4_ras_fields[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, SEC %d\n",
+				mmhub_v9_4_ras_fields[i].name,
+				sec_cnt);
+			*sec_count += sec_cnt;
+		}
+
+		ded_cnt = (value &
+				mmhub_v9_4_ras_fields[i].ded_count_mask) >>
+				mmhub_v9_4_ras_fields[i].ded_count_shift;
+		if (ded_cnt) {
+			DRM_INFO("MMHUB SubBlock %s, DED %d\n",
+				mmhub_v9_4_ras_fields[i].name,
+				ded_cnt);
+			*ded_count += ded_cnt;
+		}
+	}
+
+	return 0;
+}
+
+static void mmhub_v9_4_query_ras_error_count(struct amdgpu_device *adev,
+					   void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	uint32_t sec_count = 0, ded_count = 0;
+	uint32_t i;
+	uint32_t reg_value;
+
+	err_data->ue_count = 0;
+	err_data->ce_count = 0;
+
+	for (i = 0; i < ARRAY_SIZE(mmhub_v9_4_edc_cnt_regs); i++) {
+		reg_value =
+			RREG32(SOC15_REG_ENTRY_OFFSET(mmhub_v9_4_edc_cnt_regs[i]));
+		if (reg_value)
+			mmhub_v9_4_get_ras_error_count(&mmhub_v9_4_edc_cnt_regs[i],
+				reg_value, &sec_count, &ded_count);
+	}
+
+	err_data->ce_count += sec_count;
+	err_data->ue_count += ded_count;
+}
+
+const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs = {
+	.ras_late_init = amdgpu_mmhub_ras_late_init,
+	.query_ras_error_count = mmhub_v9_4_query_ras_error_count,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
index d435cfcec1a8..1b979773776c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.h
@@ -23,6 +23,8 @@
 #ifndef __MMHUB_V9_4_H__
 #define __MMHUB_V9_4_H__
 
+extern const struct amdgpu_mmhub_funcs mmhub_v9_4_funcs;
+
 u64 mmhub_v9_4_get_fb_location(struct amdgpu_device *adev);
 int mmhub_v9_4_gart_enable(struct amdgpu_device *adev);
 void mmhub_v9_4_gart_disable(struct amdgpu_device *adev);
@@ -32,5 +34,7 @@ void mmhub_v9_4_init(struct amdgpu_device *adev);
 int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
 			       enum amd_clockgating_state state);
 void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags);
+void mmhub_v9_4_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h b/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
index 8af0bddf85e4..20958639b601 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmsch_v1_0.h
@@ -47,6 +47,18 @@ struct mmsch_v1_0_init_header {
 	uint32_t uvd_table_size;
 };
 
+struct mmsch_vf_eng_init_header {
+	uint32_t init_status;
+	uint32_t table_offset;
+	uint32_t table_size;
+};
+
+struct mmsch_v1_1_init_header {
+	uint32_t version;
+	uint32_t total_size;
+	struct mmsch_vf_eng_init_header eng[2];
+};
+
 struct mmsch_v1_0_cmd_direct_reg_header {
 	uint32_t reg_offset   : 28;
 	uint32_t command_type : 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index cc5bf595f9b1..5fd67e1cc2a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -158,82 +158,6 @@ static void xgpu_ai_mailbox_trans_msg (struct amdgpu_device *adev,
 	xgpu_ai_mailbox_set_valid(adev, false);
 }
 
-static int xgpu_ai_get_pp_clk(struct amdgpu_device *adev, u32 type, char *buf)
-{
-        int r = 0;
-        u32 req, val, size;
-
-        if (!amdgim_is_hwperf(adev) || buf == NULL)
-                return -EBADRQC;
-
-        switch(type) {
-        case PP_SCLK:
-                req = IDH_IRQ_GET_PP_SCLK;
-                break;
-        case PP_MCLK:
-                req = IDH_IRQ_GET_PP_MCLK;
-                break;
-        default:
-                return -EBADRQC;
-        }
-
-        mutex_lock(&adev->virt.dpm_mutex);
-
-        xgpu_ai_mailbox_trans_msg(adev, req, 0, 0, 0);
-
-        r = xgpu_ai_poll_msg(adev, IDH_SUCCESS);
-        if (!r && adev->fw_vram_usage.va != NULL) {
-                val = RREG32_NO_KIQ(
-                        SOC15_REG_OFFSET(NBIO, 0,
-                                         mmBIF_BX_PF0_MAILBOX_MSGBUF_RCV_DW1));
-                size = strnlen((((char *)adev->virt.fw_reserve.p_pf2vf) +
-                                val), PAGE_SIZE);
-
-                if (size < PAGE_SIZE)
-                        strcpy(buf,((char *)adev->virt.fw_reserve.p_pf2vf + val));
-                else
-                        size = 0;
-
-                r = size;
-                goto out;
-        }
-
-        r = xgpu_ai_poll_msg(adev, IDH_FAIL);
-        if(r)
-                pr_info("%s DPM request failed",
-                        (type == PP_SCLK)? "SCLK" : "MCLK");
-
-out:
-        mutex_unlock(&adev->virt.dpm_mutex);
-        return r;
-}
-
-static int xgpu_ai_force_dpm_level(struct amdgpu_device *adev, u32 level)
-{
-        int r = 0;
-        u32 req = IDH_IRQ_FORCE_DPM_LEVEL;
-
-        if (!amdgim_is_hwperf(adev))
-                return -EBADRQC;
-
-        mutex_lock(&adev->virt.dpm_mutex);
-        xgpu_ai_mailbox_trans_msg(adev, req, level, 0, 0);
-
-        r = xgpu_ai_poll_msg(adev, IDH_SUCCESS);
-        if (!r)
-                goto out;
-
-        r = xgpu_ai_poll_msg(adev, IDH_FAIL);
-        if (!r)
-                pr_info("DPM request failed");
-        else
-                pr_info("Mailbox is broken");
-
-out:
-        mutex_unlock(&adev->virt.dpm_mutex);
-        return r;
-}
-
 static int xgpu_ai_send_access_requests(struct amdgpu_device *adev,
 					enum idh_request req)
 {
@@ -326,7 +250,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 	 */
 	locked = mutex_trylock(&adev->lock_reset);
 	if (locked)
-		adev->in_gpu_reset = 1;
+		adev->in_gpu_reset = true;
 
 	do {
 		if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -338,7 +262,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
 	if (locked) {
-		adev->in_gpu_reset = 0;
+		adev->in_gpu_reset = false;
 		mutex_unlock(&adev->lock_reset);
 	}
 
@@ -455,6 +379,4 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
 	.reset_gpu = xgpu_ai_request_reset,
 	.wait_reset = NULL,
 	.trans_msg = xgpu_ai_mailbox_trans_msg,
-	.get_pp_clk = xgpu_ai_get_pp_clk,
-	.force_dpm_level = xgpu_ai_force_dpm_level,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
index 077e91a33d62..37dbe0f2142f 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
@@ -35,10 +35,6 @@ enum idh_request {
 	IDH_REL_GPU_FINI_ACCESS,
 	IDH_REQ_GPU_RESET_ACCESS,
 
-	IDH_IRQ_FORCE_DPM_LEVEL = 10,
-	IDH_IRQ_GET_PP_SCLK,
-	IDH_IRQ_GET_PP_MCLK,
-
 	IDH_LOG_VF_ERROR       = 200,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index 0d8767eb7a70..237fa5e16b7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -252,7 +252,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 	 */
 	locked = mutex_trylock(&adev->lock_reset);
 	if (locked)
-		adev->in_gpu_reset = 1;
+		adev->in_gpu_reset = true;
 
 	do {
 		if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
@@ -264,12 +264,16 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
 
 flr_done:
 	if (locked) {
-		adev->in_gpu_reset = 0;
+		adev->in_gpu_reset = false;
 		mutex_unlock(&adev->lock_reset);
 	}
 
 	/* Trigger recovery for world switch failure if no TDR */
-	if (amdgpu_device_should_recover_gpu(adev))
+	if (amdgpu_device_should_recover_gpu(adev)
+		&& (adev->sdma_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->gfx_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->compute_timeout == MAX_SCHEDULE_TIMEOUT ||
+		adev->video_timeout == MAX_SCHEDULE_TIMEOUT))
 		amdgpu_device_gpu_recover(adev, NULL);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 9af73567e716..f737ce459c28 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -110,7 +110,6 @@ static uint32_t navi10_ih_rb_cntl(struct amdgpu_ih_ring *ih, uint32_t ih_rb_cntl
 static int navi10_ih_irq_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ih_ring *ih = &adev->irq.ih;
-	int ret = 0;
 	u32 ih_rb_cntl, ih_doorbell_rtpr, ih_chicken;
 	u32 tmp;
 
@@ -179,7 +178,7 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 	/* enable interrupts */
 	navi10_ih_enable_interrupts(adev);
 
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 0db458f9fafc..65eb378fa035 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -52,6 +52,9 @@
 #define BIF_MMSCH1_DOORBELL_RANGE__OFFSET_MASK          0x00000FFCL
 #define BIF_MMSCH1_DOORBELL_RANGE__SIZE_MASK            0x001F0000L
 
+static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
+					void *ras_error_status);
+
 static void nbio_v7_4_remap_hdp_registers(struct amdgpu_device *adev)
 {
 	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
@@ -314,6 +317,7 @@ static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
 static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev)
 {
 	uint32_t bif_doorbell_intr_cntl;
+	struct ras_manager *obj = amdgpu_ras_find_obj(adev, adev->nbio.ras_if);
 
 	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
 	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
@@ -324,7 +328,18 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 						RAS_CNTLR_INTERRUPT_CLEAR, 1);
 		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
 
-		amdgpu_ras_global_ras_isr(adev);
+		/*
+		 * clear error status after ras_controller_intr according to
+		 * hw team and count ue number for query
+		 */
+		nbio_v7_4_query_ras_error_count(adev, &obj->err_data);
+
+		DRM_WARN("RAS controller interrupt triggered by NBIF error\n");
+
+		/* ras_controller_int is dedicated for nbif ras error,
+		 * not the global interrupt for sync flood
+		 */
+		amdgpu_ras_reset_gpu(adev);
 	}
 }
 
@@ -441,10 +456,8 @@ static int nbio_v7_4_init_ras_controller_interrupt (struct amdgpu_device *adev)
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF,
 			      NBIF_7_4__SRCID__RAS_CONTROLLER_INTERRUPT,
 			      &adev->nbio.ras_controller_irq);
-	if (r)
-		return r;
 
-	return 0;
+	return r;
 }
 
 static int nbio_v7_4_init_ras_err_event_athub_interrupt (struct amdgpu_device *adev)
@@ -461,16 +474,16 @@ static int nbio_v7_4_init_ras_err_event_athub_interrupt (struct amdgpu_device *a
 	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF,
 			      NBIF_7_4__SRCID__ERREVENT_ATHUB_INTERRUPT,
 			      &adev->nbio.ras_err_event_athub_irq);
-	if (r)
-		return r;
 
-	return 0;
+	return r;
 }
 
+#define smnPARITY_ERROR_STATUS_UNCORR_GRP2	0x13a20030
+
 static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 					void *ras_error_status)
 {
-	uint32_t global_sts, central_sts, int_eoi;
+	uint32_t global_sts, central_sts, int_eoi, parity_sts;
 	uint32_t corr, fatal, non_fatal;
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 
@@ -479,6 +492,7 @@ static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 	fatal = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO, ParityErrFatal);
 	non_fatal = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO,
 				ParityErrNonFatal);
+	parity_sts = RREG32_PCIE(smnPARITY_ERROR_STATUS_UNCORR_GRP2);
 
 	if (corr)
 		err_data->ce_count++;
@@ -490,6 +504,11 @@ static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 		/* clear error status register */
 		WREG32_PCIE(smnRAS_GLOBAL_STATUS_LO, global_sts);
 
+		if (fatal)
+			/* clear parity fatal error indication field */
+			WREG32_PCIE(smnPARITY_ERROR_STATUS_UNCORR_GRP2,
+				    parity_sts);
+
 		if (REG_GET_FIELD(central_sts, BIFL_RAS_CENTRAL_STATUS,
 				BIFL_RasContller_Intr_Recv)) {
 			/* clear interrupt status register */
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 0ba66bef5746..2e0f8933410e 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -53,6 +53,7 @@
 #include "gfx_v10_0.h"
 #include "sdma_v5_0.h"
 #include "vcn_v2_0.h"
+#include "jpeg_v2_0.h"
 #include "dce_virtual.h"
 #include "mes_v10_1.h"
 #include "mxgpu_nv.h"
@@ -314,6 +315,16 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev)
 	return ret;
 }
 
+static bool nv_asic_supports_baco(struct amdgpu_device *adev)
+{
+	struct smu_context *smu = &adev->smu;
+
+	if (smu_baco_is_support(smu))
+		return true;
+	else
+		return false;
+}
+
 static enum amd_reset_method
 nv_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -342,7 +353,12 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
-		ret = smu_baco_reset(smu);
+		ret = smu_baco_enter(smu);
+		if (ret)
+			return ret;
+		ret = smu_baco_exit(smu);
+		if (ret)
+			return ret;
 	} else {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
@@ -462,7 +478,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -473,9 +489,10 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		if (adev->enable_mes)
 			amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block);
 		break;
@@ -485,7 +502,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -496,9 +513,10 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
-		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
+		    !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		break;
 	default:
 		return -EINVAL;
@@ -617,6 +635,7 @@ static const struct amdgpu_asic_funcs nv_asic_funcs =
 	.get_pcie_usage = &nv_get_pcie_usage,
 	.need_reset_on_init = &nv_need_reset_on_init,
 	.get_pcie_replay_count = &nv_get_pcie_replay_count,
+	.supports_baco = &nv_asic_supports_baco,
 };
 
 static int nv_common_early_init(void *handle)
@@ -656,10 +675,12 @@ static int nv_common_early_init(void *handle)
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
 			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_ATHUB;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		break;
@@ -676,9 +697,11 @@ static int nv_common_early_init(void *handle)
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
 			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG |
 			AMD_CG_SUPPORT_BIF_MGCG |
 			AMD_CG_SUPPORT_BIF_LS;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
+			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_VCN_DPG;
 		adev->external_rev_id = adev->rev_id + 20;
 		break;
@@ -697,10 +720,18 @@ static int nv_common_early_init(void *handle)
 			AMD_CG_SUPPORT_MC_LS |
 			AMD_CG_SUPPORT_ATHUB_MGCG |
 			AMD_CG_SUPPORT_ATHUB_LS |
-			AMD_CG_SUPPORT_VCN_MGCG;
+			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
+			AMD_PG_SUPPORT_JPEG |
 			AMD_PG_SUPPORT_ATHUB;
+		/* guest vm gets 0xffffffff when reading RCC_DEV0_EPF0_STRAP0,
+		 * as a consequence, the rev_id and external_rev_id are wrong.
+		 * workaround it by hardcoding rev_id to 0 (default value).
+		 */
+		if (amdgpu_sriov_vf(adev))
+			adev->rev_id = 0;
 		adev->external_rev_id = adev->rev_id + 0xa;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 74a9fe8e0cfb..36b65797434e 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -242,6 +242,7 @@ enum psp_gfx_fw_type {
 	GFX_FW_TYPE_SDMA5                           = 55,   /* SDMA5                    MI      */
 	GFX_FW_TYPE_SDMA6                           = 56,   /* SDMA6                    MI      */
 	GFX_FW_TYPE_SDMA7                           = 57,   /* SDMA7                    MI      */
+	GFX_FW_TYPE_VCN1                            = 58,   /* VCN1                     MI      */
 	GFX_FW_TYPE_MAX
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index b345e69ba246..7539104175e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -230,54 +230,6 @@ static int psp_v10_0_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v10_0_cmd_submit(struct psp_context *psp,
-				uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-				int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame * write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v10_0_sram_map(struct amdgpu_device *adev,
 		   unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -407,15 +359,30 @@ static int psp_v10_0_mode1_reset(struct psp_context *psp)
 	return -EINVAL;
 }
 
+static uint32_t psp_v10_0_ring_get_wptr(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	return RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+}
+
+static void psp_v10_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v10_0_funcs = {
 	.init_microcode = psp_v10_0_init_microcode,
 	.ring_init = psp_v10_0_ring_init,
 	.ring_create = psp_v10_0_ring_create,
 	.ring_stop = psp_v10_0_ring_stop,
 	.ring_destroy = psp_v10_0_ring_destroy,
-	.cmd_submit = psp_v10_0_cmd_submit,
 	.compare_sram_data = psp_v10_0_compare_sram_data,
 	.mode1_reset = psp_v10_0_mode1_reset,
+	.ring_get_wptr = psp_v10_0_ring_get_wptr,
+	.ring_set_wptr = psp_v10_0_ring_set_wptr,
 };
 
 void psp_v10_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index ffeaa2f5588d..685dd9754c67 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -43,10 +43,13 @@ MODULE_FIRMWARE("amdgpu/vega20_asd.bin");
 MODULE_FIRMWARE("amdgpu/vega20_ta.bin");
 MODULE_FIRMWARE("amdgpu/navi10_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi10_asd.bin");
+MODULE_FIRMWARE("amdgpu/navi10_ta.bin");
 MODULE_FIRMWARE("amdgpu/navi14_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi14_asd.bin");
+MODULE_FIRMWARE("amdgpu/navi14_ta.bin");
 MODULE_FIRMWARE("amdgpu/navi12_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi12_asd.bin");
+MODULE_FIRMWARE("amdgpu/navi12_ta.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_sos.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_asd.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_ta.bin");
@@ -186,6 +189,31 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
+		err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
+		if (err) {
+			release_firmware(adev->psp.ta_fw);
+			adev->psp.ta_fw = NULL;
+			dev_info(adev->dev,
+				 "psp v11.0: Failed to load firmware \"%s\"\n", fw_name);
+		} else {
+			err = amdgpu_ucode_validate(adev->psp.ta_fw);
+			if (err)
+				goto out2;
+
+			ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data;
+			adev->psp.ta_hdcp_ucode_version = le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
+			adev->psp.ta_hdcp_ucode_size = le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
+			adev->psp.ta_hdcp_start_addr = (uint8_t *)ta_hdr +
+				le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+
+			adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
+
+			adev->psp.ta_dtm_ucode_version = le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
+			adev->psp.ta_dtm_ucode_size = le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
+			adev->psp.ta_dtm_start_addr = (uint8_t *)adev->psp.ta_hdcp_start_addr +
+				le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
+		}
 		break;
 	default:
 		BUG();
@@ -208,6 +236,29 @@ out:
 	return err;
 }
 
+int psp_v11_0_wait_for_bootloader(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	int ret;
+	int retry_loop;
+
+	for (retry_loop = 0; retry_loop < 10; retry_loop++) {
+		/* Wait for bootloader to signify that is
+		    ready having bit 31 of C2PMSG_35 set to 1 */
+		ret = psp_wait_for(psp,
+				   SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
+				   0x80000000,
+				   0x80000000,
+				   false);
+
+		if (ret == 0)
+			return 0;
+	}
+
+	return ret;
+}
+
 static bool psp_v11_0_is_sos_alive(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -233,9 +284,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 		return 0;
 	}
 
-	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 	if (ret)
 		return ret;
 
@@ -251,9 +300,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35,
 	       psp_gfxdrv_command_reg);
 
-	/* Wait for bootloader to signify that is ready having  bit 31 of C2PMSG_35 set to 1*/
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 
 	return ret;
 }
@@ -273,9 +320,7 @@ static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 		return 0;
 	}
 
-	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 	if (ret)
 		return ret;
 
@@ -294,8 +339,7 @@ static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 	/* there might be handshake issue with hardware which needs delay */
 	mdelay(20);
 
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 
 	return ret;
 }
@@ -312,9 +356,7 @@ static int psp_v11_0_bootloader_load_sos(struct psp_context *psp)
 	if (psp_v11_0_is_sos_alive(psp))
 		return 0;
 
-	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
-	ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
-			   0x80000000, 0x80000000, false);
+	ret = psp_v11_0_wait_for_bootloader(psp);
 	if (ret)
 		return ret;
 
@@ -519,63 +561,6 @@ static int psp_v11_0_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v11_0_cmd_submit(struct psp_context *psp,
-			       uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			       int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame *write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	if (psp_v11_0_support_vmr_ring(psp))
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
-	else
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	/* write_frame ptr increments by size of rb_frame in bytes */
-	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_v11_0_support_vmr_ring(psp)) {
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
-	} else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v11_0_sram_map(struct amdgpu_device *adev,
 		  unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -1068,6 +1053,30 @@ static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops)
 	return 0;
 }
 
+static uint32_t psp_v11_0_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v11_0_support_vmr_ring(psp))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+
+	return data;
+}
+
+static void psp_v11_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v11_0_support_vmr_ring(psp)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v11_0_funcs = {
 	.init_microcode = psp_v11_0_init_microcode,
 	.bootloader_load_kdb = psp_v11_0_bootloader_load_kdb,
@@ -1077,7 +1086,6 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.ring_create = psp_v11_0_ring_create,
 	.ring_stop = psp_v11_0_ring_stop,
 	.ring_destroy = psp_v11_0_ring_destroy,
-	.cmd_submit = psp_v11_0_cmd_submit,
 	.compare_sram_data = psp_v11_0_compare_sram_data,
 	.mode1_reset = psp_v11_0_mode1_reset,
 	.xgmi_get_topology_info = psp_v11_0_xgmi_get_topology_info,
@@ -1091,6 +1099,8 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.mem_training_init = psp_v11_0_memory_training_init,
 	.mem_training_fini = psp_v11_0_memory_training_fini,
 	.mem_training = psp_v11_0_memory_training,
+	.ring_get_wptr = psp_v11_0_ring_get_wptr,
+	.ring_set_wptr = psp_v11_0_ring_set_wptr,
 };
 
 void psp_v11_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 8f553f6f92d6..58d8b6d732e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -334,63 +334,6 @@ static int psp_v12_0_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v12_0_cmd_submit(struct psp_context *psp,
-			       uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			       int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame *write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	if (psp_v12_0_support_vmr_ring(psp))
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
-	else
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	/* write_frame ptr increments by size of rb_frame in bytes */
-	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_v12_0_support_vmr_ring(psp)) {
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
-	} else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v12_0_sram_map(struct amdgpu_device *adev,
 		  unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -547,6 +490,30 @@ static int psp_v12_0_mode1_reset(struct psp_context *psp)
 	return 0;
 }
 
+static uint32_t psp_v12_0_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v12_0_support_vmr_ring(psp))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+
+	return data;
+}
+
+static void psp_v12_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v12_0_support_vmr_ring(psp)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101, GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v12_0_funcs = {
 	.init_microcode = psp_v12_0_init_microcode,
 	.bootloader_load_sysdrv = psp_v12_0_bootloader_load_sysdrv,
@@ -555,9 +522,10 @@ static const struct psp_funcs psp_v12_0_funcs = {
 	.ring_create = psp_v12_0_ring_create,
 	.ring_stop = psp_v12_0_ring_stop,
 	.ring_destroy = psp_v12_0_ring_destroy,
-	.cmd_submit = psp_v12_0_cmd_submit,
 	.compare_sram_data = psp_v12_0_compare_sram_data,
 	.mode1_reset = psp_v12_0_mode1_reset,
+	.ring_get_wptr = psp_v12_0_ring_get_wptr,
+	.ring_set_wptr = psp_v12_0_ring_set_wptr,
 };
 
 void psp_v12_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index fdc00938327b..735c43c7daab 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -179,7 +179,7 @@ static bool psp_v3_1_match_version(struct amdgpu_device *adev, uint32_t ver)
 	 * Double check if the latest four legacy versions.
 	 * If yes, it is still the right version.
 	 */
-	for (i = 0; i < sizeof(sos_old_versions) / sizeof(uint32_t); i++) {
+	for (i = 0; i < ARRAY_SIZE(sos_old_versions); i++) {
 		if (sos_old_versions[i] == adev->psp.sos_fw_version)
 			return true;
 	}
@@ -410,65 +410,6 @@ static int psp_v3_1_ring_destroy(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v3_1_cmd_submit(struct psp_context *psp,
-			       uint64_t cmd_buf_mc_addr, uint64_t fence_mc_addr,
-			       int index)
-{
-	unsigned int psp_write_ptr_reg = 0;
-	struct psp_gfx_rb_frame * write_frame = psp->km_ring.ring_mem;
-	struct psp_ring *ring = &psp->km_ring;
-	struct psp_gfx_rb_frame *ring_buffer_start = ring->ring_mem;
-	struct psp_gfx_rb_frame *ring_buffer_end = ring_buffer_start +
-		ring->ring_size / sizeof(struct psp_gfx_rb_frame) - 1;
-	struct amdgpu_device *adev = psp->adev;
-	uint32_t ring_size_dw = ring->ring_size / 4;
-	uint32_t rb_frame_size_dw = sizeof(struct psp_gfx_rb_frame) / 4;
-
-	/* KM (GPCOM) prepare write pointer */
-	if (psp_v3_1_support_vmr_ring(psp))
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
-	else
-		psp_write_ptr_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
-
-	/* Update KM RB frame pointer to new frame */
-	/* write_frame ptr increments by size of rb_frame in bytes */
-	/* psp_write_ptr_reg increments by size of rb_frame in DWORDs */
-	if ((psp_write_ptr_reg % ring_size_dw) == 0)
-		write_frame = ring_buffer_start;
-	else
-		write_frame = ring_buffer_start + (psp_write_ptr_reg / rb_frame_size_dw);
-	/* Check invalid write_frame ptr address */
-	if ((write_frame < ring_buffer_start) || (ring_buffer_end < write_frame)) {
-		DRM_ERROR("ring_buffer_start = %p; ring_buffer_end = %p; write_frame = %p\n",
-			  ring_buffer_start, ring_buffer_end, write_frame);
-		DRM_ERROR("write_frame is pointing to address out of bounds\n");
-		return -EINVAL;
-	}
-
-	/* Initialize KM RB frame */
-	memset(write_frame, 0, sizeof(struct psp_gfx_rb_frame));
-
-	/* Update KM RB frame */
-	write_frame->cmd_buf_addr_hi = upper_32_bits(cmd_buf_mc_addr);
-	write_frame->cmd_buf_addr_lo = lower_32_bits(cmd_buf_mc_addr);
-	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
-	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
-	write_frame->fence_value = index;
-	amdgpu_asic_flush_hdp(adev, NULL);
-
-	/* Update the write Pointer in DWORDs */
-	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
-	if (psp_v3_1_support_vmr_ring(psp)) {
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_write_ptr_reg);
-		/* send interrupt to PSP for SRIOV ring write pointer update */
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
-					GFX_CTRL_CMD_ID_CONSUME_CMD);
-	} else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, psp_write_ptr_reg);
-
-	return 0;
-}
-
 static int
 psp_v3_1_sram_map(struct amdgpu_device *adev,
 		  unsigned int *sram_offset, unsigned int *sram_addr_reg_offset,
@@ -642,6 +583,31 @@ static bool psp_v3_1_support_vmr_ring(struct psp_context *psp)
 	return false;
 }
 
+static uint32_t psp_v3_1_ring_get_wptr(struct psp_context *psp)
+{
+	uint32_t data;
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v3_1_support_vmr_ring(psp))
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102);
+	else
+		data = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67);
+	return data;
+}
+
+static void psp_v3_1_ring_set_wptr(struct psp_context *psp, uint32_t value)
+{
+	struct amdgpu_device *adev = psp->adev;
+
+	if (psp_v3_1_support_vmr_ring(psp)) {
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, value);
+		/* send interrupt to PSP for SRIOV ring write pointer update */
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+			GFX_CTRL_CMD_ID_CONSUME_CMD);
+	} else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_67, value);
+}
+
 static const struct psp_funcs psp_v3_1_funcs = {
 	.init_microcode = psp_v3_1_init_microcode,
 	.bootloader_load_sysdrv = psp_v3_1_bootloader_load_sysdrv,
@@ -650,11 +616,12 @@ static const struct psp_funcs psp_v3_1_funcs = {
 	.ring_create = psp_v3_1_ring_create,
 	.ring_stop = psp_v3_1_ring_stop,
 	.ring_destroy = psp_v3_1_ring_destroy,
-	.cmd_submit = psp_v3_1_cmd_submit,
 	.compare_sram_data = psp_v3_1_compare_sram_data,
 	.smu_reload_quirk = psp_v3_1_smu_reload_quirk,
 	.mode1_reset = psp_v3_1_mode1_reset,
 	.support_vmr_ring = psp_v3_1_support_vmr_ring,
+	.ring_get_wptr = psp_v3_1_ring_get_wptr,
+	.ring_set_wptr = psp_v3_1_ring_set_wptr,
 };
 
 void psp_v3_1_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index a10175838013..7d509a40076f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -255,7 +255,7 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -750,7 +750,7 @@ static void sdma_v2_4_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1260,16 +1260,14 @@ static const struct amdgpu_vm_pte_funcs sdma_v2_4_vm_pte_funcs = {
 
 static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			&adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version sdma_v2_4_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 5f4e2c616241..b6109a99fc43 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -429,7 +429,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v3_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1021,7 +1021,7 @@ static void sdma_v3_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1698,16 +1698,14 @@ static const struct amdgpu_vm_pte_funcs sdma_v3_0_vm_pte_funcs = {
 
 static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			 &adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version sdma_v3_0_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 2f52b7f4d25c..27c7001be1ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -82,6 +82,7 @@ static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev);
 static void sdma_v4_0_set_irq_funcs(struct amdgpu_device *adev);
+static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev);
 
 static const struct soc15_reg_golden golden_settings_sdma_4[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07),
@@ -257,6 +258,105 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x03fbe1fe)
 };
 
+static const struct soc15_ras_field_entry sdma_v4_0_ras_fields[] = {
+	{ "SDMA_UCODE_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_UCODE_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_RB_CMD_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_RB_CMD_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_IB_CMD_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_IB_CMD_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_UTCL1_RD_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_UTCL1_RD_FIFO_SED),
+	0, 0,
+	},
+	{ "SDMA_UTCL1_RDBST_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_UTCL1_RDBST_FIFO_SED),
+	0, 0,
+	},
+	{ "SDMA_DATA_LUT_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_DATA_LUT_FIFO_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF0_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF0_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF1_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF1_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF2_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF2_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF3_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF3_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF4_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF4_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF5_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF5_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF6_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF6_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF7_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF7_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF8_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF8_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF9_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF9_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF10_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF10_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF11_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF11_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF12_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF12_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF13_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF13_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF14_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF14_SED),
+	0, 0,
+	},
+	{ "SDMA_MBANK_DATA_BUF15_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MBANK_DATA_BUF15_SED),
+	0, 0,
+	},
+	{ "SDMA_SPLIT_DAT_BUF_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_SPLIT_DAT_BUF_SED),
+	0, 0,
+	},
+	{ "SDMA_MC_WR_ADDR_FIFO_SED", SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER),
+	SOC15_REG_FIELD(SDMA0_EDC_COUNTER, SDMA_MC_WR_ADDR_FIFO_SED),
+	0, 0,
+	},
+};
+
 static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
 		u32 instance, u32 offset)
 {
@@ -698,7 +798,7 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 
 	/* IB packet must end on a 8 DW boundary */
-	sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	sdma_v4_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -1579,7 +1679,7 @@ static void sdma_v4_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1686,6 +1786,7 @@ static int sdma_v4_0_early_init(void *handle)
 	sdma_v4_0_set_buffer_funcs(adev);
 	sdma_v4_0_set_vm_pte_funcs(adev);
 	sdma_v4_0_set_irq_funcs(adev);
+	sdma_v4_0_set_ras_funcs(adev);
 
 	return 0;
 }
@@ -1700,8 +1801,18 @@ static int sdma_v4_0_late_init(void *handle)
 	struct ras_ih_if ih_info = {
 		.cb = sdma_v4_0_process_ras_data_cb,
 	};
+	int i;
 
-	return amdgpu_sdma_ras_late_init(adev, &ih_info);
+	/* read back edc counter registers to clear the counters */
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {
+		for (i = 0; i < adev->sdma.num_instances; i++)
+			RREG32_SDMA(i, mmSDMA0_EDC_COUNTER);
+	}
+
+	if (adev->sdma.funcs && adev->sdma.funcs->ras_late_init)
+		return adev->sdma.funcs->ras_late_init(adev, &ih_info);
+	else
+		return 0;
 }
 
 static int sdma_v4_0_sw_init(void *handle)
@@ -1773,7 +1884,8 @@ static int sdma_v4_0_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
-	amdgpu_sdma_ras_fini(adev);
+	if (adev->sdma.funcs && adev->sdma.funcs->ras_fini)
+		adev->sdma.funcs->ras_fini(adev);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
@@ -2409,10 +2521,73 @@ static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev)
 			sched = &adev->sdma.instance[i].page.sched;
 		else
 			sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] = sched;
+	}
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
+}
+
+static void sdma_v4_0_get_ras_error_count(uint32_t value,
+					uint32_t instance,
+					uint32_t *sec_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt;
+
+	/* double bits error (multiple bits) error detection is not supported */
+	for (i = 0; i < ARRAY_SIZE(sdma_v4_0_ras_fields); i++) {
+		/* the SDMA_EDC_COUNTER register in each sdma instance
+		 * shares the same sed shift_mask
+		 * */
+		sec_cnt = (value &
+			sdma_v4_0_ras_fields[i].sec_count_mask) >>
+			sdma_v4_0_ras_fields[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("Detected %s in SDMA%d, SED %d\n",
+				sdma_v4_0_ras_fields[i].name,
+				instance, sec_cnt);
+			*sec_count += sec_cnt;
+		}
+	}
+}
+
+static int sdma_v4_0_query_ras_error_count(struct amdgpu_device *adev,
+			uint32_t instance, void *ras_error_status)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+	uint32_t sec_count = 0;
+	uint32_t reg_value = 0;
+
+	reg_value = RREG32_SDMA(instance, mmSDMA0_EDC_COUNTER);
+	/* double bit error is not supported */
+	if (reg_value)
+		sdma_v4_0_get_ras_error_count(reg_value,
+				instance, &sec_count);
+	/* err_data->ce_count should be initialized to 0
+	 * before calling into this function */
+	err_data->ce_count += sec_count;
+	/* double bit error is not supported
+	 * set ue count to 0 */
+	err_data->ue_count = 0;
+
+	return 0;
+};
+
+static const struct amdgpu_sdma_ras_funcs sdma_v4_0_ras_funcs = {
+	.ras_late_init = amdgpu_sdma_ras_late_init,
+	.ras_fini = amdgpu_sdma_ras_fini,
+	.query_ras_error_count = sdma_v4_0_query_ras_error_count,
+};
+
+static void sdma_v4_0_set_ras_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
+		adev->sdma.funcs = &sdma_v4_0_ras_funcs;
+		break;
+	default:
+		break;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version sdma_v4_0_ip_block = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index f4ad2990f973..4c6bf1f8a528 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -382,8 +382,15 @@ static void sdma_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid);
 
-	/* IB packet must end on a 8 DW boundary */
-	sdma_v5_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+	/* An IB packet must end on a 8 DW boundary--the next dword
+	 * must be on a 8-dword boundary. Our IB packet below is 6
+	 * dwords long, thus add x number of NOPs, such that, in
+	 * modular arithmetic,
+	 * wptr + 6 + x = 8k, k >= 0, which in C is,
+	 * (wptr + 6 + x) % 8 = 0.
+	 * The expression below, is a solution of x.
+	 */
+	sdma_v5_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
 
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
 			  SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -907,16 +914,9 @@ static int sdma_v5_0_ring_test_ring(struct amdgpu_ring *ring)
 			udelay(1);
 	}
 
-	if (i < adev->usec_timeout) {
-		if (amdgpu_emu_mode == 1)
-			DRM_INFO("ring test on %d succeeded in %d msecs\n", ring->idx, i);
-		else
-			DRM_INFO("ring test on %d succeeded in %d usecs\n", ring->idx, i);
-	} else {
-		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
-			  ring->idx, tmp);
-		r = -EINVAL;
-	}
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
 	amdgpu_device_wb_free(adev, index);
 
 	return r;
@@ -981,13 +981,10 @@ static int sdma_v5_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		goto err1;
 	}
 	tmp = le32_to_cpu(adev->wb.wb[index]);
-	if (tmp == 0xDEADBEEF) {
-		DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+	if (tmp == 0xDEADBEEF)
 		r = 0;
-	} else {
-		DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
+	else
 		r = -EINVAL;
-	}
 
 err1:
 	amdgpu_ib_free(adev, &ib, NULL);
@@ -1086,10 +1083,10 @@ static void sdma_v5_0_vm_set_pte_pde(struct amdgpu_ib *ib,
 }
 
 /**
- * sdma_v5_0_ring_pad_ib - pad the IB to the required number of dw
- *
+ * sdma_v5_0_ring_pad_ib - pad the IB
  * @ib: indirect buffer to fill with padding
  *
+ * Pad the IB with NOPs to a boundary multiple of 8.
  */
 static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
 {
@@ -1097,7 +1094,7 @@ static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
 	u32 pad_count;
 	int i;
 
-	pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+	pad_count = (-ib->length_dw) & 0x7;
 	for (i = 0; i < pad_count; i++)
 		if (sdma && sdma->burst_nop && (i == 0))
 			ib->ptr[ib->length_dw++] =
@@ -1721,17 +1718,15 @@ static const struct amdgpu_vm_pte_funcs sdma_v5_0_vm_pte_funcs = {
 
 static void sdma_v5_0_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	if (adev->vm_manager.vm_pte_funcs == NULL) {
 		adev->vm_manager.vm_pte_funcs = &sdma_v5_0_vm_pte_funcs;
 		for (i = 0; i < adev->sdma.num_instances; i++) {
-			sched = &adev->sdma.instance[i].ring.sched;
-			adev->vm_manager.vm_pte_rqs[i] =
-				&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+			adev->vm_manager.vm_pte_scheds[i] =
+				&adev->sdma.instance[i].ring.sched;
 		}
-		adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+		adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index f2d70a47a3af..4d415bfdb42f 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -1197,6 +1197,11 @@ static int si_asic_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
+static bool si_asic_supports_baco(struct amdgpu_device *adev)
+{
+	return false;
+}
+
 static enum amd_reset_method
 si_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -1425,6 +1430,7 @@ static const struct amdgpu_asic_funcs si_asic_funcs =
 	.get_pcie_usage = &si_get_pcie_usage,
 	.need_reset_on_init = &si_need_reset_on_init,
 	.get_pcie_replay_count = &si_get_pcie_replay_count,
+	.supports_baco = &si_asic_supports_baco,
 };
 
 static uint32_t si_get_rev_id(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index bdda8b4e03f0..9aac9f9c50bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -834,16 +834,14 @@ static const struct amdgpu_vm_pte_funcs si_dma_vm_pte_funcs = {
 
 static void si_dma_set_vm_pte_funcs(struct amdgpu_device *adev)
 {
-	struct drm_gpu_scheduler *sched;
 	unsigned i;
 
 	adev->vm_manager.vm_pte_funcs = &si_dma_vm_pte_funcs;
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		sched = &adev->sdma.instance[i].ring.sched;
-		adev->vm_manager.vm_pte_rqs[i] =
-			&sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		adev->vm_manager.vm_pte_scheds[i] =
+			&adev->sdma.instance[i].ring.sched;
 	}
-	adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
+	adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
 }
 
 const struct amdgpu_ip_block_version si_dma_ip_block =
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
index c44723c267c9..c902f26cf50d 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v11_0_i2c.c
@@ -234,7 +234,7 @@ static uint32_t smu_v11_0_i2c_transmit(struct i2c_adapter *control,
 	DRM_DEBUG_DRIVER("I2C_Transmit(), address = %x, bytes = %d , data: ",
 		 (uint16_t)address, numbytes);
 
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		print_hex_dump(KERN_INFO, "data: ", DUMP_PREFIX_NONE,
 			       16, 1, data, numbytes, false);
 	}
@@ -388,7 +388,7 @@ static uint32_t smu_v11_0_i2c_receive(struct i2c_adapter *control,
 	DRM_DEBUG_DRIVER("I2C_Receive(), address = %x, bytes = %d, data :",
 		  (uint16_t)address, bytes_received);
 
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		print_hex_dump(KERN_INFO, "data: ", DUMP_PREFIX_NONE,
 			       16, 1, data, bytes_received, false);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8e1640bc07af..317803f6a561 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -67,7 +67,9 @@
 #include "vce_v4_0.h"
 #include "vcn_v1_0.h"
 #include "vcn_v2_0.h"
+#include "jpeg_v2_0.h"
 #include "vcn_v2_5.h"
+#include "jpeg_v2_5.h"
 #include "dce_virtual.h"
 #include "mxgpu_ai.h"
 #include "amdgpu_smu.h"
@@ -477,56 +479,18 @@ static int soc15_asic_mode1_reset(struct amdgpu_device *adev)
 	return ret;
 }
 
-static int soc15_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap)
-{
-	if (is_support_sw_smu(adev)) {
-		struct smu_context *smu = &adev->smu;
-
-		*cap = smu_baco_is_support(smu);
-		return 0;
-	} else {
-		void *pp_handle = adev->powerplay.pp_handle;
-		const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-		if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
-			*cap = false;
-			return -ENOENT;
-		}
-
-		return pp_funcs->get_asic_baco_capability(pp_handle, cap);
-	}
-}
-
 static int soc15_asic_baco_reset(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	int ret = 0;
 
 	/* avoid NBIF got stuck when do RAS recovery in BACO reset */
 	if (ras && ras->supported)
 		adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
 
-	dev_info(adev->dev, "GPU BACO reset\n");
-
-	if (is_support_sw_smu(adev)) {
-		struct smu_context *smu = &adev->smu;
-
-		if (smu_baco_reset(smu))
-			return -EIO;
-	} else {
-		void *pp_handle = adev->powerplay.pp_handle;
-		const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-		if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
-			return -ENOENT;
-
-		/* enter BACO state */
-		if (pp_funcs->set_asic_baco_state(pp_handle, 1))
-			return -EIO;
-
-		/* exit BACO state */
-		if (pp_funcs->set_asic_baco_state(pp_handle, 0))
-			return -EIO;
-	}
+	ret = amdgpu_dpm_baco_reset(adev);
+	if (ret)
+		return ret;
 
 	/* re-enable doorbell interrupt after BACO exit */
 	if (ras && ras->supported)
@@ -535,21 +499,11 @@ static int soc15_asic_baco_reset(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int soc15_mode2_reset(struct amdgpu_device *adev)
-{
-	if (is_support_sw_smu(adev))
-		return smu_mode2_reset(&adev->smu);
-	if (!adev->powerplay.pp_funcs ||
-	    !adev->powerplay.pp_funcs->asic_reset_mode_2)
-		return -ENOENT;
-
-	return adev->powerplay.pp_funcs->asic_reset_mode_2(adev->powerplay.pp_handle);
-}
-
 static enum amd_reset_method
 soc15_asic_reset_method(struct amdgpu_device *adev)
 {
-	bool baco_reset;
+	bool baco_reset = false;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
@@ -557,23 +511,21 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 		return AMD_RESET_METHOD_MODE2;
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
-		soc15_asic_get_baco_capability(adev, &baco_reset);
+	case CHIP_ARCTURUS:
+		baco_reset = amdgpu_dpm_is_baco_supported(adev);
 		break;
 	case CHIP_VEGA20:
 		if (adev->psp.sos_fw_version >= 0x80067)
-			soc15_asic_get_baco_capability(adev, &baco_reset);
-		else
-			baco_reset = false;
-		if (baco_reset) {
-			struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
-			struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+			baco_reset = amdgpu_dpm_is_baco_supported(adev);
 
-			if (hive || (ras && ras->supported))
-				baco_reset = false;
-		}
+		/*
+		 * 1. PMFW version > 0x284300: all cases use baco
+		 * 2. PMFW version <= 0x284300: only sGPU w/o RAS use baco
+		 */
+		if ((ras && ras->supported) && adev->pm.fw_version <= 0x283400)
+			baco_reset = false;
 		break;
 	default:
-		baco_reset = false;
 		break;
 	}
 
@@ -591,7 +543,7 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
-			return soc15_mode2_reset(adev);
+			return amdgpu_dpm_mode2_reset(adev);
 		default:
 			if (!adev->in_suspend)
 				amdgpu_inc_vram_lost(adev);
@@ -599,6 +551,22 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 	}
 }
 
+static bool soc15_supports_baco(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+	case CHIP_VEGA12:
+	case CHIP_ARCTURUS:
+		return amdgpu_dpm_is_baco_supported(adev);
+	case CHIP_VEGA20:
+		if (adev->psp.sos_fw_version >= 0x80067)
+			return amdgpu_dpm_is_baco_supported(adev);
+		return false;
+	default:
+		return false;
+	}
+}
+
 /*static int soc15_set_uvd_clock(struct amdgpu_device *adev, u32 clock,
 			u32 cntl_reg, u32 status_reg)
 {
@@ -709,9 +677,9 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 	}
 
 	if (adev->asic_type == CHIP_VEGA20 || adev->asic_type == CHIP_ARCTURUS)
-		adev->df_funcs = &df_v3_6_funcs;
+		adev->df.funcs = &df_v3_6_funcs;
 	else
-		adev->df_funcs = &df_v1_7_funcs;
+		adev->df.funcs = &df_v1_7_funcs;
 
 	adev->rev_id = soc15_get_rev_id(adev);
 	adev->nbio.funcs->detect_hw_virt(adev);
@@ -746,11 +714,11 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		}
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
-		if (!amdgpu_sriov_vf(adev)) {
-			if (is_support_sw_smu(adev))
+		if (is_support_sw_smu(adev)) {
+			if (!amdgpu_sriov_vf(adev))
 				amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
-			else
-				amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		} else {
+			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
 		}
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -798,11 +766,16 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
-		if (!amdgpu_sriov_vf(adev))
-			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 
-		if (unlikely(adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT))
+		if (amdgpu_sriov_vf(adev)) {
+			if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
+				amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
+		} else {
 			amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
+		}
+		if (!amdgpu_sriov_vf(adev))
+			amdgpu_device_ip_block_add(adev, &jpeg_v2_5_ip_block);
 		break;
 	case CHIP_RENOIR:
 		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
@@ -810,8 +783,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
 		if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
 			amdgpu_device_ip_block_add(adev, &psp_v12_0_ip_block);
-		if (is_support_sw_smu(adev))
-			amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &smu_v12_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
@@ -821,6 +793,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
 #endif
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
+		amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block);
 		break;
 	default:
 		return -EINVAL;
@@ -999,6 +972,7 @@ static const struct amdgpu_asic_funcs soc15_asic_funcs =
 	.get_pcie_usage = &soc15_get_pcie_usage,
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &soc15_get_pcie_replay_count,
+	.supports_baco = &soc15_supports_baco,
 };
 
 static const struct amdgpu_asic_funcs vega20_asic_funcs =
@@ -1007,6 +981,7 @@ static const struct amdgpu_asic_funcs vega20_asic_funcs =
 	.read_bios_from_rom = &soc15_read_bios_from_rom,
 	.read_register = &soc15_read_register,
 	.reset = &soc15_asic_reset,
+	.reset_method = &soc15_asic_reset_method,
 	.set_vga_state = &soc15_vga_set_state,
 	.get_xclk = &soc15_get_xclk,
 	.set_uvd_clocks = &soc15_set_uvd_clocks,
@@ -1019,7 +994,7 @@ static const struct amdgpu_asic_funcs vega20_asic_funcs =
 	.get_pcie_usage = &vega20_get_pcie_usage,
 	.need_reset_on_init = &soc15_need_reset_on_init,
 	.get_pcie_replay_count = &soc15_get_pcie_replay_count,
-	.reset_method = &soc15_asic_reset_method
+	.supports_baco = &soc15_supports_baco,
 };
 
 static int soc15_common_early_init(void *handle)
@@ -1145,9 +1120,7 @@ static int soc15_common_early_init(void *handle)
 				AMD_CG_SUPPORT_SDMA_LS |
 				AMD_CG_SUPPORT_VCN_MGCG;
 
-			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+			adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
 		} else if (adev->pdev->device == 0x15d8) {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
@@ -1190,9 +1163,7 @@ static int soc15_common_early_init(void *handle)
 				AMD_CG_SUPPORT_SDMA_LS |
 				AMD_CG_SUPPORT_VCN_MGCG;
 
-			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
-				AMD_PG_SUPPORT_VCN |
-				AMD_PG_SUPPORT_VCN_DPG;
+			adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
 		}
 		break;
 	case CHIP_ARCTURUS:
@@ -1208,7 +1179,9 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_SDMA_LS |
 			AMD_CG_SUPPORT_MC_MGCG |
 			AMD_CG_SUPPORT_MC_LS |
-			AMD_CG_SUPPORT_IH_CG;
+			AMD_CG_SUPPORT_IH_CG |
+			AMD_CG_SUPPORT_VCN_MGCG |
+			AMD_CG_SUPPORT_JPEG_MGCG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x32;
 		break;
@@ -1229,12 +1202,14 @@ static int soc15_common_early_init(void *handle)
 				 AMD_CG_SUPPORT_HDP_LS |
 				 AMD_CG_SUPPORT_ROM_MGCG |
 				 AMD_CG_SUPPORT_VCN_MGCG |
+				 AMD_CG_SUPPORT_JPEG_MGCG |
 				 AMD_CG_SUPPORT_IH_CG |
 				 AMD_CG_SUPPORT_ATHUB_LS |
 				 AMD_CG_SUPPORT_ATHUB_MGCG |
 				 AMD_CG_SUPPORT_DF_MGCG;
 		adev->pg_flags = AMD_PG_SUPPORT_SDMA |
 				 AMD_PG_SUPPORT_VCN |
+				 AMD_PG_SUPPORT_JPEG |
 				 AMD_PG_SUPPORT_VCN_DPG;
 		adev->external_rev_id = adev->rev_id + 0x91;
 		break;
@@ -1272,7 +1247,7 @@ static int soc15_common_sw_init(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_add_irq_id(adev);
 
-	adev->df_funcs->sw_init(adev);
+	adev->df.funcs->sw_init(adev);
 
 	return 0;
 }
@@ -1282,7 +1257,7 @@ static int soc15_common_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_nbio_ras_fini(adev);
-	adev->df_funcs->sw_fini(adev);
+	adev->df.funcs->sw_fini(adev);
 	return 0;
 }
 
@@ -1503,7 +1478,7 @@ static int soc15_common_set_clockgating_state(void *handle,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_rom_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		adev->df_funcs->update_medium_grain_clock_gating(adev,
+		adev->df.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		break;
 	case CHIP_RAVEN:
@@ -1561,7 +1536,7 @@ static void soc15_common_get_clockgating_state(void *handle, u32 *flags)
 	if (!(data & CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE0_MASK))
 		*flags |= AMD_CG_SUPPORT_ROM_MGCG;
 
-	adev->df_funcs->get_clockgating_state(adev, flags);
+	adev->df.funcs->get_clockgating_state(adev, flags);
 }
 
 static int soc15_common_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index 57af489a5de3..d0fb7a67c1a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -60,6 +60,18 @@ struct soc15_allowed_register_entry {
 	bool grbm_indexed;
 };
 
+struct soc15_ras_field_entry {
+	const char *name;
+	uint32_t hwip;
+	uint32_t inst;
+	uint32_t seg;
+	uint32_t reg_offset;
+	uint32_t sec_count_mask;
+	uint32_t sec_count_shift;
+	uint32_t ded_count_mask;
+	uint32_t ded_count_shift;
+};
+
 #define SOC15_REG_ENTRY(ip, inst, reg)	ip##_HWIP, inst, reg##_BASE_IDX, reg
 
 #define SOC15_REG_ENTRY_OFFSET(entry)	(adev->reg_offset[entry.hwip][entry.inst][entry.seg] + entry.reg_offset)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15_common.h b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
index 839f186e1182..19e870c79896 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15_common.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15_common.h
@@ -52,6 +52,7 @@
 		uint32_t old_ = 0;	\
 		uint32_t tmp_ = RREG32(adev->reg_offset[ip##_HWIP][inst][reg##_BASE_IDX] + reg); \
 		uint32_t loop = adev->usec_timeout;		\
+		ret = 0;					\
 		while ((tmp_ & (mask)) != (expected_value)) {	\
 			if (old_ != tmp_) {			\
 				loop = adev->usec_timeout;	\
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
index 47c4b96b14d1..793bf70e64b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
@@ -28,19 +28,24 @@
 #include "rsmu/rsmu_0_0_2_sh_mask.h"
 #include "umc/umc_6_1_1_offset.h"
 #include "umc/umc_6_1_1_sh_mask.h"
+#include "umc/umc_6_1_2_offset.h"
 
-#define smnMCA_UMC0_MCUMC_ADDRT0	0x50f10
+#define UMC_6_INST_DIST			0x40000
 
 /*
  * (addr / 256) * 8192, the higher 26 bits in ErrorAddr
  * is the index of 8KB block
  */
-#define ADDR_OF_8KB_BLOCK(addr)		(((addr) & ~0xffULL) << 5)
+#define ADDR_OF_8KB_BLOCK(addr)			(((addr) & ~0xffULL) << 5)
 /* channel index is the index of 256B block */
 #define ADDR_OF_256B_BLOCK(channel_index)	((channel_index) << 8)
 /* offset in 256B block */
 #define OFFSET_IN_256B_BLOCK(addr)		((addr) & 0xffULL)
 
+#define LOOP_UMC_INST(umc_inst) for ((umc_inst) = 0; (umc_inst) < adev->umc.umc_inst_num; (umc_inst)++)
+#define LOOP_UMC_CH_INST(ch_inst) for ((ch_inst) = 0; (ch_inst) < adev->umc.channel_inst_num; (ch_inst)++)
+#define LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) LOOP_UMC_INST((umc_inst)) LOOP_UMC_CH_INST((ch_inst))
+
 const uint32_t
 	umc_v6_1_channel_idx_tbl[UMC_V6_1_UMC_INSTANCE_NUM][UMC_V6_1_CHANNEL_INSTANCE_NUM] = {
 		{2, 18, 11, 27},	{4, 20, 13, 29},
@@ -49,24 +54,10 @@ const uint32_t
 		{9, 25, 0, 16},		{15, 31, 6, 22}
 };
 
-static void umc_v6_1_enable_umc_index_mode(struct amdgpu_device *adev,
-					   uint32_t umc_instance)
+static void umc_v6_1_enable_umc_index_mode(struct amdgpu_device *adev)
 {
-	uint32_t rsmu_umc_index;
-
-	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
-			mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
-	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
-			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+	WREG32_FIELD15(RSMU, 0, RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
 			RSMU_UMC_INDEX_MODE_EN, 1);
-	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
-			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-			RSMU_UMC_INDEX_INSTANCE, umc_instance);
-	rsmu_umc_index = REG_SET_FIELD(rsmu_umc_index,
-			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-			RSMU_UMC_INDEX_WREN, 1 << umc_instance);
-	WREG32_SOC15(RSMU, 0, mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-				rsmu_umc_index);
 }
 
 static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
@@ -75,15 +66,23 @@ static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
 			RSMU_UMC_INDEX_MODE_EN, 0);
 }
 
-static uint32_t umc_v6_1_get_umc_inst(struct amdgpu_device *adev)
+static uint32_t umc_v6_1_get_umc_index_mode_state(struct amdgpu_device *adev)
 {
 	uint32_t rsmu_umc_index;
 
 	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
-				mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+			mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+
 	return REG_GET_FIELD(rsmu_umc_index,
-				RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
-				RSMU_UMC_INDEX_INSTANCE);
+			RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+			RSMU_UMC_INDEX_MODE_EN);
+}
+
+static inline uint32_t get_umc_6_reg_offset(struct amdgpu_device *adev,
+					    uint32_t umc_inst,
+					    uint32_t ch_inst)
+{
+	return adev->umc.channel_offs*ch_inst + UMC_6_INST_DIST*umc_inst;
 }
 
 static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
@@ -95,39 +94,50 @@ static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
 	uint64_t mc_umc_status;
 	uint32_t mc_umc_status_addr;
 
-	ecc_err_cnt_sel_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
-	ecc_err_cnt_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
-	mc_umc_status_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel_ARCT);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt_ARCT);
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	}
 
 	/* select the lower chip and check the error count */
-	ecc_err_cnt_sel = RREG32(ecc_err_cnt_sel_addr + umc_reg_offset);
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 0);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
-	ecc_err_cnt = RREG32(ecc_err_cnt_addr + umc_reg_offset);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
 	*error_count +=
 		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
 		 UMC_V6_1_CE_CNT_INIT);
 	/* clear the lower chip err count */
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 
 	/* select the higher chip and check the err counter */
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 1);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
-	ecc_err_cnt = RREG32(ecc_err_cnt_addr + umc_reg_offset);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	ecc_err_cnt = RREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4);
 	*error_count +=
 		(REG_GET_FIELD(ecc_err_cnt, UMCCH0_0_EccErrCnt, EccErrCnt) -
 		 UMC_V6_1_CE_CNT_INIT);
 	/* clear the higher chip err count */
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 
 	/* check for SRAM correctable error
 	  MCUMC_STATUS is a 64 bit register */
-	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
 	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, ErrorCodeExt) == 6 &&
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)
@@ -141,11 +151,18 @@ static void umc_v6_1_querry_uncorrectable_error_count(struct amdgpu_device *adev
 	uint64_t mc_umc_status;
 	uint32_t mc_umc_status_addr;
 
-	mc_umc_status_addr =
-                SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	}
 
 	/* check the MCUMC_STATUS */
-	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
 	if ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) &&
 	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 ||
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
@@ -155,49 +172,78 @@ static void umc_v6_1_querry_uncorrectable_error_count(struct amdgpu_device *adev
 		*error_count += 1;
 }
 
-static void umc_v6_1_query_error_count(struct amdgpu_device *adev,
-					   struct ras_err_data *err_data, uint32_t umc_reg_offset,
-					   uint32_t channel_index)
-{
-	umc_v6_1_query_correctable_error_count(adev, umc_reg_offset,
-						   &(err_data->ce_count));
-	umc_v6_1_querry_uncorrectable_error_count(adev, umc_reg_offset,
-						  &(err_data->ue_count));
-}
-
 static void umc_v6_1_query_ras_error_count(struct amdgpu_device *adev,
 					   void *ras_error_status)
 {
-	amdgpu_umc_for_each_channel(umc_v6_1_query_error_count);
+	struct ras_err_data* err_data = (struct ras_err_data*)ras_error_status;
+
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	uint32_t rsmu_umc_index_state = umc_v6_1_get_umc_index_mode_state(adev);
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_disable_umc_index_mode(adev);
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_6_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v6_1_query_correctable_error_count(adev,
+						       umc_reg_offset,
+						       &(err_data->ce_count));
+		umc_v6_1_querry_uncorrectable_error_count(adev,
+							  umc_reg_offset,
+							  &(err_data->ue_count));
+	}
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_enable_umc_index_mode(adev);
 }
 
 static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 					 struct ras_err_data *err_data,
-					 uint32_t umc_reg_offset, uint32_t channel_index)
+					 uint32_t umc_reg_offset,
+					 uint32_t ch_inst,
+					 uint32_t umc_inst)
 {
 	uint32_t lsb, mc_umc_status_addr;
-	uint64_t mc_umc_status, err_addr, retired_page;
+	uint64_t mc_umc_status, err_addr, retired_page, mc_umc_addrt0;
 	struct eeprom_table_record *err_rec;
-
-	mc_umc_status_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+	uint32_t channel_index = adev->umc.channel_idx_tbl[umc_inst * adev->umc.channel_inst_num + ch_inst];
+
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT);
+		mc_umc_addrt0 =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		mc_umc_status_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
+		mc_umc_addrt0 =
+			SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_ADDRT0);
+	}
 
 	/* skip error address process if -ENOMEM */
 	if (!err_data->err_addr) {
 		/* clear umc status */
-		WREG64_UMC(mc_umc_status_addr + umc_reg_offset, 0x0ULL);
+		WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL);
 		return;
 	}
 
 	err_rec = &err_data->err_addr[err_data->err_addr_cnt];
-	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
+	mc_umc_status = RREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4);
 
 	/* calculate error address if ue/ce error is detected */
 	if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1 &&
 	    (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC) == 1 ||
 	    REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, CECC) == 1)) {
-		err_addr = RREG64_PCIE(smnMCA_UMC0_MCUMC_ADDRT0 + umc_reg_offset * 4);
 
+		err_addr = RREG64_PCIE((mc_umc_addrt0 + umc_reg_offset) * 4);
 		/* the lowest lsb bits should be ignored */
 		lsb = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, LSB);
 		err_addr = REG_GET_FIELD(err_addr, MCA_UMC_UMC0_MCUMC_ADDRT0, ErrorAddr);
@@ -218,57 +264,105 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 			err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
 			err_rec->cu = 0;
 			err_rec->mem_channel = channel_index;
-			err_rec->mcumc_id = umc_v6_1_get_umc_inst(adev);
+			err_rec->mcumc_id = umc_inst;
 
 			err_data->err_addr_cnt++;
 		}
 	}
 
 	/* clear umc status */
-	WREG64_UMC(mc_umc_status_addr + umc_reg_offset, 0x0ULL);
+	WREG64_PCIE((mc_umc_status_addr + umc_reg_offset) * 4, 0x0ULL);
 }
 
 static void umc_v6_1_query_ras_error_address(struct amdgpu_device *adev,
 					     void *ras_error_status)
 {
-	amdgpu_umc_for_each_channel(umc_v6_1_query_error_address);
+	struct ras_err_data* err_data = (struct ras_err_data*)ras_error_status;
+
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	uint32_t rsmu_umc_index_state = umc_v6_1_get_umc_index_mode_state(adev);
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_disable_umc_index_mode(adev);
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_6_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v6_1_query_error_address(adev,
+					     err_data,
+					     umc_reg_offset,
+					     ch_inst,
+					     umc_inst);
+	}
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_enable_umc_index_mode(adev);
 }
 
 static void umc_v6_1_err_cnt_init_per_channel(struct amdgpu_device *adev,
-					 struct ras_err_data *err_data,
-					 uint32_t umc_reg_offset, uint32_t channel_index)
+					      uint32_t umc_reg_offset)
 {
 	uint32_t ecc_err_cnt_sel, ecc_err_cnt_sel_addr;
 	uint32_t ecc_err_cnt_addr;
 
-	ecc_err_cnt_sel_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
-	ecc_err_cnt_addr =
-		SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		/* UMC 6_1_2 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel_ARCT);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt_ARCT);
+	} else {
+		/* UMC 6_1_1 registers */
+		ecc_err_cnt_sel_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCntSel);
+		ecc_err_cnt_addr =
+			SOC15_REG_OFFSET(UMC, 0, mmUMCCH0_0_EccErrCnt);
+	}
 
 	/* select the lower chip and check the error count */
-	ecc_err_cnt_sel = RREG32(ecc_err_cnt_sel_addr + umc_reg_offset);
+	ecc_err_cnt_sel = RREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4);
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 0);
 	/* set ce error interrupt type to APIC based interrupt */
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrInt, 0x1);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
 	/* set error count to initial value */
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 
 	/* select the higher chip and check the err counter */
 	ecc_err_cnt_sel = REG_SET_FIELD(ecc_err_cnt_sel, UMCCH0_0_EccErrCntSel,
 					EccErrCntCsSel, 1);
-	WREG32(ecc_err_cnt_sel_addr + umc_reg_offset, ecc_err_cnt_sel);
-	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
+	WREG32_PCIE((ecc_err_cnt_sel_addr + umc_reg_offset) * 4, ecc_err_cnt_sel);
+	WREG32_PCIE((ecc_err_cnt_addr + umc_reg_offset) * 4, UMC_V6_1_CE_CNT_INIT);
 }
 
 static void umc_v6_1_err_cnt_init(struct amdgpu_device *adev)
 {
-	void *ras_error_status = NULL;
+	uint32_t umc_inst        = 0;
+	uint32_t ch_inst         = 0;
+	uint32_t umc_reg_offset  = 0;
+
+	uint32_t rsmu_umc_index_state = umc_v6_1_get_umc_index_mode_state(adev);
+
+	if (rsmu_umc_index_state)
+		umc_v6_1_disable_umc_index_mode(adev);
+
+	LOOP_UMC_INST_AND_CH(umc_inst, ch_inst) {
+		umc_reg_offset = get_umc_6_reg_offset(adev,
+						      umc_inst,
+						      ch_inst);
+
+		umc_v6_1_err_cnt_init_per_channel(adev, umc_reg_offset);
+	}
 
-	amdgpu_umc_for_each_channel(umc_v6_1_err_cnt_init_per_channel);
+	if (rsmu_umc_index_state)
+		umc_v6_1_enable_umc_index_mode(adev);
 }
 
 const struct amdgpu_umc_funcs umc_v6_1_funcs = {
@@ -276,6 +370,4 @@ const struct amdgpu_umc_funcs umc_v6_1_funcs = {
 	.ras_late_init = amdgpu_umc_ras_late_init,
 	.query_ras_error_count = umc_v6_1_query_ras_error_count,
 	.query_ras_error_address = umc_v6_1_query_ras_error_address,
-	.enable_umc_index_mode = umc_v6_1_enable_umc_index_mode,
-	.disable_umc_index_mode = umc_v6_1_disable_umc_index_mode,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h
index dab9cbd292c5..0ce1d323cfdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.h
@@ -35,7 +35,8 @@
 /* total channel instances in one umc block */
 #define UMC_V6_1_TOTAL_CHANNEL_NUM	(UMC_V6_1_CHANNEL_INSTANCE_NUM * UMC_V6_1_UMC_INSTANCE_NUM)
 /* UMC regiser per channel offset */
-#define UMC_V6_1_PER_CHANNEL_OFFSET		0x800
+#define UMC_V6_1_PER_CHANNEL_OFFSET_VG20	0x800
+#define UMC_V6_1_PER_CHANNEL_OFFSET_ARCT	0x400
 
 /* EccErrCnt max value */
 #define UMC_V6_1_CE_CNT_MAX		0xffff
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index b4f84a820a44..e654938f6cca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -25,6 +25,7 @@
 
 #include "amdgpu.h"
 #include "amdgpu_vcn.h"
+#include "amdgpu_pm.h"
 #include "soc15.h"
 #include "soc15d.h"
 #include "soc15_common.h"
@@ -36,21 +37,22 @@
 #include "mmhub/mmhub_9_1_sh_mask.h"
 
 #include "ivsrcid/vcn/irqsrcs_vcn_1_0.h"
+#include "jpeg_v1_0.h"
 
-#define mmUVD_RBC_XX_IB_REG_CHECK				0x05ab
-#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX	1
-#define mmUVD_REG_XX_MASK							0x05ac
-#define mmUVD_REG_XX_MASK_BASE_IDX				1
+#define mmUVD_RBC_XX_IB_REG_CHECK_1_0		0x05ab
+#define mmUVD_RBC_XX_IB_REG_CHECK_1_0_BASE_IDX	1
+#define mmUVD_REG_XX_MASK_1_0			0x05ac
+#define mmUVD_REG_XX_MASK_1_0_BASE_IDX		1
 
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
-static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr);
 static int vcn_v1_0_set_powergating_state(void *handle, enum amd_powergating_state state);
 static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state);
+				int inst_idx, struct dpg_pause_state *new_state);
+
+static void vcn_v1_0_idle_work_handler(struct work_struct *work);
 
 /**
  * vcn_v1_0_early_init - set function pointers
@@ -68,9 +70,10 @@ static int vcn_v1_0_early_init(void *handle)
 
 	vcn_v1_0_set_dec_ring_funcs(adev);
 	vcn_v1_0_set_enc_ring_funcs(adev);
-	vcn_v1_0_set_jpeg_ring_funcs(adev);
 	vcn_v1_0_set_irq_funcs(adev);
 
+	jpeg_v1_0_early_init(handle);
+
 	return 0;
 }
 
@@ -101,15 +104,13 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
-	/* VCN JPEG TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->vcn.inst->irq);
-	if (r)
-		return r;
-
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
 		return r;
 
+	/* Override the work func */
+	adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler;
+
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		const struct common_firmware_header *hdr;
 		hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
@@ -149,17 +150,11 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	sprintf(ring->name, "vcn_jpeg");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
-	if (r)
-		return r;
-
 	adev->vcn.pause_dpg_mode = vcn_v1_0_pause_dpg_mode;
-	adev->vcn.internal.jpeg_pitch = adev->vcn.inst->external.jpeg_pitch =
-		SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
 
-	return 0;
+	r = jpeg_v1_0_sw_init(handle);
+
+	return r;
 }
 
 /**
@@ -178,6 +173,8 @@ static int vcn_v1_0_sw_fini(void *handle)
 	if (r)
 		return r;
 
+	jpeg_v1_0_sw_fini(handle);
+
 	r = amdgpu_vcn_sw_fini(adev);
 
 	return r;
@@ -207,7 +204,7 @@ static int vcn_v1_0_hw_init(void *handle)
 			goto done;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
+	ring = &adev->jpeg.inst->ring_dec;
 	r = amdgpu_ring_test_helper(ring);
 	if (r)
 		goto done;
@@ -838,9 +835,9 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 
 	vcn_v1_0_mc_resume_spg_mode(adev);
 
-	WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK, 0x10);
-	WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK,
-		RREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK) | 0x3);
+	WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK_1_0, 0x10);
+	WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0,
+		RREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0) | 0x3);
 
 	/* enable VCPU clock */
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CNTL, UVD_VCPU_CNTL__CLK_EN_MASK);
@@ -947,22 +944,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
-			UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
-
-	/* initialize wptr */
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
-	/* copy patch commands to the jpeg ring */
-	vcn_v1_0_jpeg_ring_set_patch_ring(ring,
-		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+	jpeg_v1_0_start(adev, 0);
 
 	return 0;
 }
@@ -1106,13 +1088,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), 0,
 			~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
 
-	/* initialize JPEG wptr */
-	ring = &adev->vcn.inst->ring_jpeg;
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
-	/* copy patch commands to the jpeg ring */
-	vcn_v1_0_jpeg_ring_set_patch_ring(ring,
-		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+	jpeg_v1_0_start(adev, 1);
 
 	return 0;
 }
@@ -1223,7 +1199,7 @@ static int vcn_v1_0_stop(struct amdgpu_device *adev)
 }
 
 static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state)
+				int inst_idx, struct dpg_pause_state *new_state)
 {
 	int ret_code;
 	uint32_t reg_data = 0;
@@ -1316,7 +1292,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
 							UVD_DPG_PAUSE__JPEG_PAUSE_DPG_ACK_MASK, ret_code);
 
 				/* Restore */
-				ring = &adev->vcn.inst->ring_jpeg;
+				ring = &adev->jpeg.inst->ring_dec;
 				WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
 				WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL,
 							UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
@@ -1716,389 +1692,6 @@ static void vcn_v1_0_enc_ring_emit_wreg(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
-
-/**
- * vcn_v1_0_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v1_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v1_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v1_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-}
-
-/**
- * vcn_v1_0_jpeg_ring_insert_start - insert a start command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a start command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x80010000);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_insert_end - insert a end command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a end command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x00010000);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_emit_fence - emit an fence & trap command
- *
- * @ring: amdgpu_ring pointer
- * @fence: fence to emit
- *
- * Write a fence and a trap command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				     unsigned flags)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x8);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
-	amdgpu_ring_write(ring, 0xffffffff);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x3fbc);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x1);
-
-	/* emit trap */
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
-	amdgpu_ring_write(ring, 0);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_emit_ib - execute indirect buffer
- *
- * @ring: amdgpu_ring pointer
- * @ib: indirect buffer to execute
- *
- * Write ring commands to execute the indirect buffer.
- */
-static void vcn_v1_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
-					struct amdgpu_job *job,
-					struct amdgpu_ib *ib,
-					uint32_t flags)
-{
-	struct amdgpu_device *adev = ring->adev;
-	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, ib->length_dw);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,
-		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x2);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
-	amdgpu_ring_write(ring, 0x2);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
-					    uint32_t reg, uint32_t val,
-					    uint32_t mask)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, val);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,
-			PACKETJ(0, 0, 0, PACKETJ_TYPE3));
-	}
-	amdgpu_ring_write(ring, mask);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-		unsigned vmid, uint64_t pd_addr)
-{
-	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t data0, data1, mask;
-
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
-
-	/* wait for register write */
-	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
-	data1 = lower_32_bits(pd_addr);
-	mask = 0xffffffff;
-	vcn_v1_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
-					uint32_t reg, uint32_t val)
-{
-	struct amdgpu_device *adev = ring->adev;
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring,
-		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-			((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,
-			PACKETJ(0, 0, 0, PACKETJ_TYPE0));
-	}
-	amdgpu_ring_write(ring, val);
-}
-
-static void vcn_v1_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
-{
-	int i;
-
-	WARN_ON(ring->wptr % 2 || count % 2);
-
-	for (i = 0; i < count / 2; i++) {
-		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
-		amdgpu_ring_write(ring, 0);
-	}
-}
-
-static void vcn_v1_0_jpeg_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
-{
-	struct amdgpu_device *adev = ring->adev;
-	ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		ring->ring[(*ptr)++] = 0;
-		ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
-	} else {
-		ring->ring[(*ptr)++] = reg_offset;
-		ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
-	}
-	ring->ring[(*ptr)++] = val;
-}
-
-static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	uint32_t reg, reg_offset, val, mask, i;
-
-	// 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
-	reg_offset = (reg << 2);
-	val = lower_32_bits(ring->gpu_addr);
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
-	reg_offset = (reg << 2);
-	val = upper_32_bits(ring->gpu_addr);
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 3rd to 5th: issue MEM_READ commands
-	for (i = 0; i <= 2; i++) {
-		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
-		ring->ring[ptr++] = 0;
-	}
-
-	// 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
-	reg_offset = (reg << 2);
-	val = 0x13;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 7th: program mmUVD_JRBC_RB_REF_DATA
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA);
-	reg_offset = (reg << 2);
-	val = 0x1;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	// 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
-	reg_offset = (reg << 2);
-	val = 0x1;
-	mask = 0x1;
-
-	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
-	ring->ring[ptr++] = 0x01400200;
-	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
-	ring->ring[ptr++] = val;
-	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
-	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
-		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
-		ring->ring[ptr++] = 0;
-		ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
-	} else {
-		ring->ring[ptr++] = reg_offset;
-		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
-	}
-	ring->ring[ptr++] = mask;
-
-	//9th to 21st: insert no-op
-	for (i = 0; i <= 12; i++) {
-		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
-		ring->ring[ptr++] = 0;
-	}
-
-	//22nd: reset mmUVD_JRBC_RB_RPTR
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_RPTR);
-	reg_offset = (reg << 2);
-	val = 0;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
-	//23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
-	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
-	reg_offset = (reg << 2);
-	val = 0x12;
-	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-}
-
 static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
@@ -2123,9 +1716,6 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
 	case 120:
 		amdgpu_fence_process(&adev->vcn.inst->ring_enc[1]);
 		break;
-	case 126:
-		amdgpu_fence_process(&adev->vcn.inst->ring_jpeg);
-		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -2174,6 +1764,86 @@ static int vcn_v1_0_set_powergating_state(void *handle,
 	return ret;
 }
 
+static void vcn_v1_0_idle_work_handler(struct work_struct *work)
+{
+	struct amdgpu_device *adev =
+		container_of(work, struct amdgpu_device, vcn.idle_work.work);
+	unsigned int fences = 0, i;
+
+	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+		fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		struct dpg_pause_state new_state;
+
+		if (fences)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+		if (amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec))
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
+
+		adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+	}
+
+	fences += amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec);
+	fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_dec);
+
+	if (fences == 0) {
+		amdgpu_gfx_off_ctrl(adev, true);
+		if (adev->pm.dpm_enabled)
+			amdgpu_dpm_enable_uvd(adev, false);
+		else
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+			       AMD_PG_STATE_GATE);
+	} else {
+		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+	}
+}
+
+void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+
+	if (set_clocks) {
+		amdgpu_gfx_off_ctrl(adev, false);
+		if (adev->pm.dpm_enabled)
+			amdgpu_dpm_enable_uvd(adev, true);
+		else
+			amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+			       AMD_PG_STATE_UNGATE);
+	}
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		struct dpg_pause_state new_state;
+		unsigned int fences = 0, i;
+
+		for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+			fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
+
+		if (fences)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+		if (amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec))
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+		else
+			new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
+
+		if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+			new_state.fw_based = VCN_DPG_STATE__PAUSE;
+		else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
+			new_state.jpeg = VCN_DPG_STATE__PAUSE;
+
+		adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+	}
+}
+
 static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
 	.name = "vcn_v1_0",
 	.early_init = vcn_v1_0_early_init,
@@ -2220,7 +1890,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
 	.insert_start = vcn_v1_0_dec_ring_insert_start,
 	.insert_end = vcn_v1_0_dec_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
+	.begin_use = vcn_v1_0_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
 	.emit_wreg = vcn_v1_0_dec_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait,
@@ -2252,48 +1922,13 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.insert_nop = amdgpu_ring_insert_nop,
 	.insert_end = vcn_v1_0_enc_ring_insert_end,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
+	.begin_use = vcn_v1_0_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
 	.emit_wreg = vcn_v1_0_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
-	.type = AMDGPU_RING_TYPE_VCN_JPEG,
-	.align_mask = 0xf,
-	.nop = PACKET0(0x81ff, 0),
-	.support_64bit_ptrs = false,
-	.no_user_fence = true,
-	.vmhub = AMDGPU_MMHUB_0,
-	.extra_dw = 64,
-	.get_rptr = vcn_v1_0_jpeg_ring_get_rptr,
-	.get_wptr = vcn_v1_0_jpeg_ring_get_wptr,
-	.set_wptr = vcn_v1_0_jpeg_ring_set_wptr,
-	.emit_frame_size =
-		6 + 6 + /* hdp invalidate / flush */
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
-		8 + /* vcn_v1_0_jpeg_ring_emit_vm_flush */
-		26 + 26 + /* vcn_v1_0_jpeg_ring_emit_fence x2 vm fence */
-		6,
-	.emit_ib_size = 22, /* vcn_v1_0_jpeg_ring_emit_ib */
-	.emit_ib = vcn_v1_0_jpeg_ring_emit_ib,
-	.emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
-	.emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
-	.insert_nop = vcn_v1_0_jpeg_ring_nop,
-	.insert_start = vcn_v1_0_jpeg_ring_insert_start,
-	.insert_end = vcn_v1_0_jpeg_ring_insert_end,
-	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v1_0_jpeg_ring_emit_wreg,
-	.emit_reg_wait = vcn_v1_0_jpeg_ring_emit_reg_wait,
-	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	adev->vcn.inst->ring_dec.funcs = &vcn_v1_0_dec_ring_vm_funcs;
@@ -2310,12 +1945,6 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
-static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
-	adev->vcn.inst->ring_jpeg.funcs = &vcn_v1_0_jpeg_ring_vm_funcs;
-	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
-}
-
 static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 	.set = vcn_v1_0_set_interrupt_state,
 	.process = vcn_v1_0_process_interrupt,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
index 2a497a7a4840..f67d7391fc21 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
@@ -24,6 +24,8 @@
 #ifndef __VCN_V1_0_H__
 #define __VCN_V1_0_H__
 
+void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
+
 extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 38f787a560cb..f4db8af6536b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -47,39 +47,13 @@
 #define mmUVD_LMI_RBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET		0x5a7
 #define mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET			0x1e2
 
-#define mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET 			0x1bfff
-#define mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET				0x4029
-#define mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET				0x402a
-#define mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET				0x402b
-#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ea
-#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40eb
-#define mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET				0x40cf
-#define mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET				0x40d1
-#define mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET 		0x40e8
-#define mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET		0x40e9
-#define mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET				0x4082
-#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET		0x40ec
-#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x40ed
-#define mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET			0x4085
-#define mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET				0x4084
-#define mmUVD_JRBC_STATUS_INTERNAL_OFFSET				0x4089
-#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET				0x401f
-
-#define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR				0x18000
-
-#define mmUVD_RBC_XX_IB_REG_CHECK 					0x026b
-#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX 				1
-#define mmUVD_REG_XX_MASK 						0x026c
-#define mmUVD_REG_XX_MASK_BASE_IDX 					1
-
 static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v2_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev);
 static int vcn_v2_0_set_powergating_state(void *handle,
 				enum amd_powergating_state state);
 static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state);
+				int inst_idx, struct dpg_pause_state *new_state);
 
 /**
  * vcn_v2_0_early_init - set function pointers
@@ -97,7 +71,6 @@ static int vcn_v2_0_early_init(void *handle)
 
 	vcn_v2_0_set_dec_ring_funcs(adev);
 	vcn_v2_0_set_enc_ring_funcs(adev);
-	vcn_v2_0_set_jpeg_ring_funcs(adev);
 	vcn_v2_0_set_irq_funcs(adev);
 
 	return 0;
@@ -132,12 +105,6 @@ static int vcn_v2_0_sw_init(void *handle)
 			return r;
 	}
 
-	/* VCN JPEG TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN,
-			      VCN_2_0__SRCID__JPEG_DECODE, &adev->vcn.inst->irq);
-	if (r)
-		return r;
-
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
 		return r;
@@ -194,19 +161,8 @@ static int vcn_v2_0_sw_init(void *handle)
 			return r;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	ring->use_doorbell = true;
-	ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1;
-	sprintf(ring->name, "vcn_jpeg");
-	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
-	if (r)
-		return r;
-
 	adev->vcn.pause_dpg_mode = vcn_v2_0_pause_dpg_mode;
 
-	adev->vcn.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
-	adev->vcn.inst->external.jpeg_pitch = SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
-
 	return 0;
 }
 
@@ -258,11 +214,6 @@ static int vcn_v2_0_hw_init(void *handle)
 			goto done;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	r = amdgpu_ring_test_helper(ring);
-	if (r)
-		goto done;
-
 done:
 	if (!r)
 		DRM_INFO("VCN decode and encode initialized successfully(under %s).\n",
@@ -296,9 +247,6 @@ static int vcn_v2_0_hw_fini(void *handle)
 		ring->sched.ready = false;
 	}
 
-	ring = &adev->vcn.inst->ring_jpeg;
-	ring->sched.ready = false;
-
 	return 0;
 }
 
@@ -393,7 +341,6 @@ static void vcn_v2_0_mc_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE);
 
 	WREG32_SOC15(UVD, 0, mmUVD_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
-	WREG32_SOC15(UVD, 0, mmJPEG_DEC_GFX10_ADDR_CONFIG, adev->gfx.config.gb_addr_config);
 }
 
 static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirect)
@@ -404,88 +351,88 @@ static void vcn_v2_0_mc_resume_dpg_mode(struct amdgpu_device *adev, bool indirec
 	/* cache window 0: fw */
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 		if (!indirect) {
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
 				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo), 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
 				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi), 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
 		} else {
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), 0, 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), 0, 0, indirect);
-			WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+			WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 				UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
 		}
 		offset = 0;
 	} else {
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
 			lower_32_bits(adev->vcn.inst->gpu_addr), 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
 			upper_32_bits(adev->vcn.inst->gpu_addr), 0, indirect);
 		offset = size;
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET0),
 			AMDGPU_UVD_FIRMWARE_OFFSET >> 3, 0, indirect);
 	}
 
 	if (!indirect)
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_SIZE0), size, 0, indirect);
 	else
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_SIZE0), 0, 0, indirect);
 
 	/* cache window 1: stack */
 	if (!indirect) {
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
 			lower_32_bits(adev->vcn.inst->gpu_addr + offset), 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
 			upper_32_bits(adev->vcn.inst->gpu_addr + offset), 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
 	} else {
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), 0, 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), 0, 0, indirect);
-		WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+		WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 			UVD, 0, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
 	}
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE, 0, indirect);
 
 	/* cache window 2: context */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
 		lower_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
 		upper_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_OFFSET2), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE, 0, indirect);
 
 	/* non-cache window */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_NONCACHE_SIZE0), 0, 0, indirect);
 
 	/* VCN global tiling registers */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
 }
 
@@ -631,146 +578,23 @@ static void vcn_v2_0_clock_gating_dpg_mode(struct amdgpu_device *adev,
 		 UVD_CGC_CTRL__WCB_MODE_MASK |
 		 UVD_CGC_CTRL__VCPU_MODE_MASK |
 		 UVD_CGC_CTRL__SCPU_MODE_MASK);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_CGC_CTRL), reg_data, sram_sel, indirect);
 
 	/* turn off clock gating */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_CGC_GATE), 0, sram_sel, indirect);
 
 	/* turn on SUVD clock gating */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_SUVD_CGC_GATE), 1, sram_sel, indirect);
 
 	/* turn on sw mode in UVD_SUVD_CGC_CTRL */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_SUVD_CGC_CTRL), 0, sram_sel, indirect);
 }
 
 /**
- * jpeg_v2_0_start - start JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * Setup and start the JPEG block
- */
-static int jpeg_v2_0_start(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *ring = &adev->vcn.inst->ring_jpeg;
-	uint32_t tmp;
-	int r = 0;
-
-	/* disable power gating */
-	tmp = 1 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_PGFSM_CONFIG), tmp);
-
-	SOC15_WAIT_ON_RREG(VCN, 0,
-		mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS_UVDJ_PWR_ON,
-		UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
-
-	if (r) {
-		DRM_ERROR("amdgpu: JPEG disable power gating failed\n");
-		return r;
-	}
-
-	/* Removing the anti hang mechanism to indicate the UVDJ tile is ON */
-	tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS)) & ~0x1;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS), tmp);
-
-	/* JPEG disable CGC */
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL);
-	tmp |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-	tmp |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-	tmp |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL, tmp);
-
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE);
-	tmp &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
-		| JPEG_CGC_GATE__JPEG2_DEC_MASK
-		| JPEG_CGC_GATE__JPEG_ENC_MASK
-		| JPEG_CGC_GATE__JMCIF_MASK
-		| JPEG_CGC_GATE__JRBBM_MASK);
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE, tmp);
-
-	/* enable JMI channel */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_JMI_CNTL), 0,
-		~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-	/* enable System Interrupt for JRBC */
-	WREG32_P(SOC15_REG_OFFSET(VCN, 0, mmJPEG_SYS_INT_EN),
-		JPEG_SYS_INT_EN__DJRBC_MASK,
-		~JPEG_SYS_INT_EN__DJRBC_MASK);
-
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-		lower_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-		upper_32_bits(ring->gpu_addr));
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
-	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
-	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
-	return 0;
-}
-
-/**
- * jpeg_v2_0_stop - stop JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * stop the JPEG block
- */
-static int jpeg_v2_0_stop(struct amdgpu_device *adev)
-{
-	uint32_t tmp;
-	int r = 0;
-
-	/* reset JMI */
-	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_JMI_CNTL),
-		UVD_JMI_CNTL__SOFT_RESET_MASK,
-		~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-	/* enable JPEG CGC */
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL);
-	tmp |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-	tmp |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-	tmp |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_CTRL, tmp);
-
-
-	tmp = RREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE);
-	tmp |= (JPEG_CGC_GATE__JPEG_DEC_MASK
-		|JPEG_CGC_GATE__JPEG2_DEC_MASK
-		|JPEG_CGC_GATE__JPEG_ENC_MASK
-		|JPEG_CGC_GATE__JMCIF_MASK
-		|JPEG_CGC_GATE__JRBBM_MASK);
-	WREG32_SOC15(VCN, 0, mmJPEG_CGC_GATE, tmp);
-
-	/* enable power gating */
-	tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS));
-	tmp &= ~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK;
-	tmp |=  0x1; //UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_TILES_OFF;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_POWER_STATUS), tmp);
-
-	tmp = 2 << UVD_PGFSM_CONFIG__UVDJ_PWR_CONFIG__SHIFT;
-	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_PGFSM_CONFIG), tmp);
-
-	SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS,
-		(2 << UVD_PGFSM_STATUS__UVDJ_PWR_STATUS__SHIFT),
-		UVD_PGFSM_STATUS__UVDJ_PWR_STATUS_MASK, r);
-
-	if (r) {
-		DRM_ERROR("amdgpu: JPEG enable power gating failed\n");
-		return r;
-	}
-
-	return r;
-}
-
-/**
  * vcn_v2_0_enable_clock_gating - enable VCN clock gating
  *
  * @adev: amdgpu_device pointer
@@ -930,7 +754,7 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	WREG32_SOC15(UVD, 0, mmUVD_POWER_STATUS, tmp);
 
 	if (indirect)
-		adev->vcn.dpg_sram_curr_addr = (uint32_t*)adev->vcn.dpg_sram_cpu_addr;
+		adev->vcn.inst->dpg_sram_curr_addr = (uint32_t*)adev->vcn.inst->dpg_sram_cpu_addr;
 
 	/* enable clock gating */
 	vcn_v2_0_clock_gating_dpg_mode(adev, 0, indirect);
@@ -939,11 +763,11 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
 	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
 	tmp |= UVD_VCPU_CNTL__MIF_WR_LOW_THRESHOLD_BP_MASK;
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_VCPU_CNTL), tmp, 0, indirect);
 
 	/* disable master interupt */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MASTINT_EN), 0, 0, indirect);
 
 	/* setup mmUVD_LMI_CTRL */
@@ -955,28 +779,28 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
 		(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
 		0x00100000L);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_CTRL), tmp, 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_CNTL),
 		0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT, 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_SET_MUXA0),
 		((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
 		 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
 		 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)), 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_SET_MUXB0),
 		((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
 		 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
 		 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
 		 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)), 0, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MPC_SET_MUX),
 		((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
 		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
@@ -984,29 +808,29 @@ static int vcn_v2_0_start_dpg_mode(struct amdgpu_device *adev, bool indirect)
 
 	vcn_v2_0_mc_resume_dpg_mode(adev, indirect);
 
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK), 0x3, 0, indirect);
 
 	/* release VCPU reset to boot */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_SOFT_RESET), 0, 0, indirect);
 
 	/* enable LMI MC and UMC channels */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_LMI_CTRL2),
 		0x1F << UVD_LMI_CTRL2__RE_OFLD_MIF_WR_REQ_NUM__SHIFT, 0, indirect);
 
 	/* enable master interrupt */
-	WREG32_SOC15_DPG_MODE_2_0(SOC15_DPG_MODE_OFFSET_2_0(
+	WREG32_SOC15_DPG_MODE_2_0(0, SOC15_DPG_MODE_OFFSET_2_0(
 		UVD, 0, mmUVD_MASTINT_EN),
 		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
 
 	if (indirect)
-		psp_update_vcn_sram(adev, 0, adev->vcn.dpg_sram_gpu_addr,
-				    (uint32_t)((uintptr_t)adev->vcn.dpg_sram_curr_addr -
-					       (uintptr_t)adev->vcn.dpg_sram_cpu_addr));
+		psp_update_vcn_sram(adev, 0, adev->vcn.inst->dpg_sram_gpu_addr,
+				    (uint32_t)((uintptr_t)adev->vcn.inst->dpg_sram_curr_addr -
+					       (uintptr_t)adev->vcn.inst->dpg_sram_cpu_addr));
 
 	/* force RBC into idle state */
 	rb_bufsz = order_base_2(ring->ring_size);
@@ -1052,12 +876,8 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_uvd(adev, true);
 
-	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
-		r = vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram);
-		if (r)
-			return r;
-		goto jpeg;
-	}
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		return vcn_v2_0_start_dpg_mode(adev, adev->vcn.indirect_sram);
 
 	vcn_v2_0_disable_static_power_gating(adev);
 
@@ -1209,10 +1029,7 @@ static int vcn_v2_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
 
-jpeg:
-	r = jpeg_v2_0_start(adev);
-
-	return r;
+	return 0;
 }
 
 static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev)
@@ -1231,9 +1048,6 @@ static int vcn_v2_0_stop_dpg_mode(struct amdgpu_device *adev)
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2);
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code);
 
-	tmp = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_JRBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
-
 	tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
 	SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
 
@@ -1252,10 +1066,6 @@ static int vcn_v2_0_stop(struct amdgpu_device *adev)
 	uint32_t tmp;
 	int r;
 
-	r = jpeg_v2_0_stop(adev);
-	if (r)
-		return r;
-
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
 		r = vcn_v2_0_stop_dpg_mode(adev);
 		if (r)
@@ -1320,7 +1130,7 @@ power_off:
 }
 
 static int vcn_v2_0_pause_dpg_mode(struct amdgpu_device *adev,
-				struct dpg_pause_state *new_state)
+				int inst_idx, struct dpg_pause_state *new_state)
 {
 	struct amdgpu_ring *ring;
 	uint32_t reg_data = 0;
@@ -1781,272 +1591,6 @@ void vcn_v2_0_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_
 	amdgpu_ring_write(ring, val);
 }
 
-/**
- * vcn_v2_0_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v2_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v2_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
-	else
-		return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v2_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
-		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
-	} else {
-		WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-	}
-}
-
-/**
- * vcn_v2_0_jpeg_ring_insert_start - insert a start command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a start command to the ring.
- */
-void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x80010000);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_insert_end - insert a end command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a end command to the ring.
- */
-void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
-{
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x68e04);
-
-	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x00010000);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_emit_fence - emit an fence & trap command
- *
- * @ring: amdgpu_ring pointer
- * @fence: fence to emit
- *
- * Write a fence and a trap command to the ring.
- */
-void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				unsigned flags)
-{
-	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_GPCOM_DATA0_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_DATA1_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, seq);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x8);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JPEG_GPCOM_CMD_INTERNAL_OFFSET,
-		0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x3fbc);
-
-	amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x1);
-
-	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
-	amdgpu_ring_write(ring, 0);
-}
-
-/**
- * vcn_v2_0_jpeg_ring_emit_ib - execute indirect buffer
- *
- * @ring: amdgpu_ring pointer
- * @ib: indirect buffer to execute
- *
- * Write ring commands to execute the indirect buffer.
- */
-void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
-				struct amdgpu_job *job,
-				struct amdgpu_ib *ib,
-				uint32_t flags)
-{
-	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_IB_SIZE_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, ib->length_dw);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
-
-	amdgpu_ring_write(ring,	PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
-	amdgpu_ring_write(ring, 0);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x2);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_STATUS_INTERNAL_OFFSET,
-		0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
-	amdgpu_ring_write(ring, 0x2);
-}
-
-void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
-				uint32_t val, uint32_t mask)
-{
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, 0x01400200);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_RB_REF_DATA_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	amdgpu_ring_write(ring, val);
-
-	amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-			0, 0, PACKETJ_TYPE3));
-	}
-	amdgpu_ring_write(ring, mask);
-}
-
-void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				unsigned vmid, uint64_t pd_addr)
-{
-	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
-	uint32_t data0, data1, mask;
-
-	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
-
-	/* wait for register write */
-	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
-	data1 = lower_32_bits(pd_addr);
-	mask = 0xffffffff;
-	vcn_v2_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
-}
-
-void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
-{
-	uint32_t reg_offset = (reg << 2);
-
-	amdgpu_ring_write(ring,	PACKETJ(mmUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
-		0, 0, PACKETJ_TYPE0));
-	if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
-		amdgpu_ring_write(ring, 0);
-		amdgpu_ring_write(ring,
-			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
-	} else {
-		amdgpu_ring_write(ring, reg_offset);
-		amdgpu_ring_write(ring,	PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
-			0, 0, PACKETJ_TYPE0));
-	}
-	amdgpu_ring_write(ring, val);
-}
-
-void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
-{
-	int i;
-
-	WARN_ON(ring->wptr % 2 || count % 2);
-
-	for (i = 0; i < count / 2; i++) {
-		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
-		amdgpu_ring_write(ring, 0);
-	}
-}
-
 static int vcn_v2_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
@@ -2071,9 +1615,6 @@ static int vcn_v2_0_process_interrupt(struct amdgpu_device *adev,
 	case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY:
 		amdgpu_fence_process(&adev->vcn.inst->ring_enc[1]);
 		break;
-	case VCN_2_0__SRCID__JPEG_DECODE:
-		amdgpu_fence_process(&adev->vcn.inst->ring_jpeg);
-		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -2219,36 +1760,6 @@ static const struct amdgpu_ring_funcs vcn_v2_0_enc_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-static const struct amdgpu_ring_funcs vcn_v2_0_jpeg_ring_vm_funcs = {
-	.type = AMDGPU_RING_TYPE_VCN_JPEG,
-	.align_mask = 0xf,
-	.vmhub = AMDGPU_MMHUB_0,
-	.get_rptr = vcn_v2_0_jpeg_ring_get_rptr,
-	.get_wptr = vcn_v2_0_jpeg_ring_get_wptr,
-	.set_wptr = vcn_v2_0_jpeg_ring_set_wptr,
-	.emit_frame_size =
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
-		8 + /* vcn_v2_0_jpeg_ring_emit_vm_flush */
-		18 + 18 + /* vcn_v2_0_jpeg_ring_emit_fence x2 vm fence */
-		8 + 16,
-	.emit_ib_size = 22, /* vcn_v2_0_jpeg_ring_emit_ib */
-	.emit_ib = vcn_v2_0_jpeg_ring_emit_ib,
-	.emit_fence = vcn_v2_0_jpeg_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_jpeg_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
-	.insert_nop = vcn_v2_0_jpeg_ring_nop,
-	.insert_start = vcn_v2_0_jpeg_ring_insert_start,
-	.insert_end = vcn_v2_0_jpeg_ring_insert_end,
-	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_jpeg_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_jpeg_ring_emit_reg_wait,
-	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
 static void vcn_v2_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	adev->vcn.inst->ring_dec.funcs = &vcn_v2_0_dec_ring_vm_funcs;
@@ -2265,12 +1776,6 @@ static void vcn_v2_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
-static void vcn_v2_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
-	adev->vcn.inst->ring_jpeg.funcs = &vcn_v2_0_jpeg_ring_vm_funcs;
-	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
-}
-
 static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = {
 	.set = vcn_v2_0_set_interrupt_state,
 	.process = vcn_v2_0_process_interrupt,
@@ -2278,7 +1783,7 @@ static const struct amdgpu_irq_src_funcs vcn_v2_0_irq_funcs = {
 
 static void vcn_v2_0_set_irq_funcs(struct amdgpu_device *adev)
 {
-	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 2;
+	adev->vcn.inst->irq.num_types = adev->vcn.num_enc_rings + 1;
 	adev->vcn.inst->irq.funcs = &vcn_v2_0_irq_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h
index 8467292f32e5..ef749b02ded9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.h
@@ -49,19 +49,6 @@ extern void vcn_v2_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
 				unsigned int vmid, uint64_t pd_addr);
 extern void vcn_v2_0_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
 
-extern void vcn_v2_0_jpeg_ring_insert_start(struct amdgpu_ring *ring);
-extern void vcn_v2_0_jpeg_ring_insert_end(struct amdgpu_ring *ring);
-extern void vcn_v2_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
-				unsigned flags);
-extern void vcn_v2_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_job *job,
-				struct amdgpu_ib *ib, uint32_t flags);
-extern void vcn_v2_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
-				uint32_t val, uint32_t mask);
-extern void vcn_v2_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
-				unsigned vmid, uint64_t pd_addr);
-extern void vcn_v2_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
-extern void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count);
-
 extern const struct amdgpu_ip_block_version vcn_v2_0_ip_block;
 
 #endif /* __VCN_V2_0_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 93edf9193a7b..c8b63d57a541 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -29,6 +29,7 @@
 #include "soc15.h"
 #include "soc15d.h"
 #include "vcn_v2_0.h"
+#include "mmsch_v1_0.h"
 
 #include "vcn/vcn_2_5_offset.h"
 #include "vcn/vcn_2_5_sh_mask.h"
@@ -47,16 +48,16 @@
 #define mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET 	0x3b5
 #define mmUVD_RBC_IB_SIZE_INTERNAL_OFFSET			0x25c
 
-#define mmUVD_JPEG_PITCH_INTERNAL_OFFSET			0x401f
-
-#define VCN25_MAX_HW_INSTANCES_ARCTURUS				2
+#define VCN25_MAX_HW_INSTANCES_ARCTURUS			2
 
 static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v2_5_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev);
 static int vcn_v2_5_set_powergating_state(void *handle,
 				enum amd_powergating_state state);
+static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev,
+				int inst_idx, struct dpg_pause_state *new_state);
+static int vcn_v2_5_sriov_start(struct amdgpu_device *adev);
 
 static int amdgpu_ih_clientid_vcns[] = {
 	SOC15_IH_CLIENTID_VCN,
@@ -91,11 +92,16 @@ static int vcn_v2_5_early_init(void *handle)
 	} else
 		adev->vcn.num_vcn_inst = 1;
 
-	adev->vcn.num_enc_rings = 2;
+	if (amdgpu_sriov_vf(adev)) {
+		adev->vcn.num_vcn_inst = 2;
+		adev->vcn.harvest_config = 0;
+		adev->vcn.num_enc_rings = 1;
+	} else {
+		adev->vcn.num_enc_rings = 2;
+	}
 
 	vcn_v2_5_set_dec_ring_funcs(adev);
 	vcn_v2_5_set_enc_ring_funcs(adev);
-	vcn_v2_5_set_jpeg_ring_funcs(adev);
 	vcn_v2_5_set_irq_funcs(adev);
 
 	return 0;
@@ -130,12 +136,6 @@ static int vcn_v2_5_sw_init(void *handle)
 			if (r)
 				return r;
 		}
-
-		/* VCN JPEG TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[j],
-				VCN_2_0__SRCID__JPEG_DECODE, &adev->vcn.inst[j].irq);
-		if (r)
-			return r;
 	}
 
 	r = amdgpu_vcn_sw_init(adev);
@@ -184,12 +184,11 @@ static int vcn_v2_5_sw_init(void *handle)
 		adev->vcn.internal.nop = mmUVD_NO_OP_INTERNAL_OFFSET;
 		adev->vcn.inst[j].external.nop = SOC15_REG_OFFSET(UVD, j, mmUVD_NO_OP);
 
-		adev->vcn.internal.jpeg_pitch = mmUVD_JPEG_PITCH_INTERNAL_OFFSET;
-		adev->vcn.inst[j].external.jpeg_pitch = SOC15_REG_OFFSET(UVD, j, mmUVD_JPEG_PITCH);
-
 		ring = &adev->vcn.inst[j].ring_dec;
 		ring->use_doorbell = true;
-		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 8*j;
+
+		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+				(amdgpu_sriov_vf(adev) ? 2*j : 8*j);
 		sprintf(ring->name, "vcn_dec_%d", j);
 		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0);
 		if (r)
@@ -198,22 +197,26 @@ static int vcn_v2_5_sw_init(void *handle)
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 			ring = &adev->vcn.inst[j].ring_enc[i];
 			ring->use_doorbell = true;
-			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 2 + i + 8*j;
+
+			ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+					(amdgpu_sriov_vf(adev) ? (1 + i + 2*j) : (2 + i + 8*j));
+
 			sprintf(ring->name, "vcn_enc_%d.%d", j, i);
 			r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0);
 			if (r)
 				return r;
 		}
+	}
 
-		ring = &adev->vcn.inst[j].ring_jpeg;
-		ring->use_doorbell = true;
-		ring->doorbell_index = (adev->doorbell_index.vcn.vcn_ring0_1 << 1) + 1 + 8*j;
-		sprintf(ring->name, "vcn_jpeg_%d", j);
-		r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst[j].irq, 0);
+	if (amdgpu_sriov_vf(adev)) {
+		r = amdgpu_virt_alloc_mm_table(adev);
 		if (r)
 			return r;
 	}
 
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		adev->vcn.pause_dpg_mode = vcn_v2_5_pause_dpg_mode;
+
 	return 0;
 }
 
@@ -229,6 +232,9 @@ static int vcn_v2_5_sw_fini(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_free_mm_table(adev);
+
 	r = amdgpu_vcn_suspend(adev);
 	if (r)
 		return r;
@@ -249,35 +255,44 @@ static int vcn_v2_5_hw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring;
-	int i, j, r;
+	int i, j, r = 0;
+
+	if (amdgpu_sriov_vf(adev))
+		r = vcn_v2_5_sriov_start(adev);
 
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
 			continue;
-		ring = &adev->vcn.inst[j].ring_dec;
 
-		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
-						     ring->doorbell_index, j);
+		if (amdgpu_sriov_vf(adev)) {
+			adev->vcn.inst[j].ring_enc[0].sched.ready = true;
+			adev->vcn.inst[j].ring_enc[1].sched.ready = false;
+			adev->vcn.inst[j].ring_enc[2].sched.ready = false;
+			adev->vcn.inst[j].ring_dec.sched.ready = true;
+		} else {
 
-		r = amdgpu_ring_test_helper(ring);
-		if (r)
-			goto done;
+			ring = &adev->vcn.inst[j].ring_dec;
+
+			adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+						     ring->doorbell_index, j);
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-			ring = &adev->vcn.inst[j].ring_enc[i];
 			r = amdgpu_ring_test_helper(ring);
 			if (r)
 				goto done;
-		}
 
-		ring = &adev->vcn.inst[j].ring_jpeg;
-		r = amdgpu_ring_test_helper(ring);
-		if (r)
-			goto done;
+			for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+				ring = &adev->vcn.inst[j].ring_enc[i];
+				r = amdgpu_ring_test_helper(ring);
+				if (r)
+					goto done;
+			}
+		}
 	}
+
 done:
 	if (!r)
-		DRM_INFO("VCN decode and encode initialized successfully.\n");
+		DRM_INFO("VCN decode and encode initialized successfully(under %s).\n",
+			(adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)?"DPG Mode":"SPG Mode");
 
 	return r;
 }
@@ -300,7 +315,9 @@ static int vcn_v2_5_hw_fini(void *handle)
 			continue;
 		ring = &adev->vcn.inst[i].ring_dec;
 
-		if (RREG32_SOC15(VCN, i, mmUVD_STATUS))
+		if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
+		    (adev->vcn.cur_state != AMD_PG_STATE_GATE &&
+		     RREG32_SOC15(VCN, i, mmUVD_STATUS)))
 			vcn_v2_5_set_powergating_state(adev, AMD_PG_STATE_GATE);
 
 		ring->sched.ready = false;
@@ -309,9 +326,6 @@ static int vcn_v2_5_hw_fini(void *handle)
 			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->sched.ready = false;
 		}
-
-		ring = &adev->vcn.inst[i].ring_jpeg;
-		ring->sched.ready = false;
 	}
 
 	return 0;
@@ -378,9 +392,9 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
 		/* cache window 0: fw */
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo));
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo));
 			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
-				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi));
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi));
 			WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
 			offset = 0;
 		} else {
@@ -412,6 +426,99 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
 	}
 }
 
+static void vcn_v2_5_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
+{
+	uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+	uint32_t offset;
+
+	/* cache window 0: fw */
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+		if (!indirect) {
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + inst_idx].tmr_mc_addr_lo), 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + inst_idx].tmr_mc_addr_hi), 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
+		} else {
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW), 0, 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH), 0, 0, indirect);
+			WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+				UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET0), 0, 0, indirect);
+		}
+		offset = 0;
+	} else {
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr), 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr), 0, indirect);
+		offset = size;
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET0),
+			AMDGPU_UVD_FIRMWARE_OFFSET >> 3, 0, indirect);
+	}
+
+	if (!indirect)
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE0), size, 0, indirect);
+	else
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE0), 0, 0, indirect);
+
+	/* cache window 1: stack */
+	if (!indirect) {
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset), 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset), 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
+	} else {
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW), 0, 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH), 0, 0, indirect);
+		WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+			UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET1), 0, 0, indirect);
+	}
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE1), AMDGPU_VCN_STACK_SIZE, 0, indirect);
+
+	/* cache window 2: context */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
+		lower_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
+		upper_32_bits(adev->vcn.inst[inst_idx].gpu_addr + offset + AMDGPU_VCN_STACK_SIZE), 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CACHE_OFFSET2), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CACHE_SIZE2), AMDGPU_VCN_CONTEXT_SIZE, 0, indirect);
+
+	/* non-cache window */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_LOW), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_VCPU_NC0_64BIT_BAR_HIGH), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_NONCACHE_OFFSET0), 0, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_NONCACHE_SIZE0), 0, 0, indirect);
+
+	/* VCN global tiling registers */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_GFX8_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect);
+}
+
 /**
  * vcn_v2_5_disable_clock_gating - disable VCN clock gating
  *
@@ -530,6 +637,54 @@ static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev)
 	}
 }
 
+static void vcn_v2_5_clock_gating_dpg_mode(struct amdgpu_device *adev,
+		uint8_t sram_sel, int inst_idx, uint8_t indirect)
+{
+	uint32_t reg_data = 0;
+
+	/* enable sw clock gating control */
+	if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
+		reg_data = 1 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	else
+		reg_data = 0 << UVD_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
+	reg_data |= 1 << UVD_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
+	reg_data |= 4 << UVD_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
+	reg_data &= ~(UVD_CGC_CTRL__UDEC_RE_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_CM_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_IT_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_DB_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_MP_MODE_MASK |
+		 UVD_CGC_CTRL__SYS_MODE_MASK |
+		 UVD_CGC_CTRL__UDEC_MODE_MASK |
+		 UVD_CGC_CTRL__MPEG2_MODE_MASK |
+		 UVD_CGC_CTRL__REGS_MODE_MASK |
+		 UVD_CGC_CTRL__RBC_MODE_MASK |
+		 UVD_CGC_CTRL__LMI_MC_MODE_MASK |
+		 UVD_CGC_CTRL__LMI_UMC_MODE_MASK |
+		 UVD_CGC_CTRL__IDCT_MODE_MASK |
+		 UVD_CGC_CTRL__MPRD_MODE_MASK |
+		 UVD_CGC_CTRL__MPC_MODE_MASK |
+		 UVD_CGC_CTRL__LBSI_MODE_MASK |
+		 UVD_CGC_CTRL__LRBBM_MODE_MASK |
+		 UVD_CGC_CTRL__WCB_MODE_MASK |
+		 UVD_CGC_CTRL__VCPU_MODE_MASK |
+		 UVD_CGC_CTRL__MMSCH_MODE_MASK);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_CGC_CTRL), reg_data, sram_sel, indirect);
+
+	/* turn off clock gating */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_CGC_GATE), 0, sram_sel, indirect);
+
+	/* turn on SUVD clock gating */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_SUVD_CGC_GATE), 1, sram_sel, indirect);
+
+	/* turn on sw mode in UVD_SUVD_CGC_CTRL */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_SUVD_CGC_CTRL), 0, sram_sel, indirect);
+}
+
 /**
  * vcn_v2_5_enable_clock_gating - enable VCN clock gating
  *
@@ -592,111 +747,134 @@ static void vcn_v2_5_enable_clock_gating(struct amdgpu_device *adev)
 	}
 }
 
-/**
- * jpeg_v2_5_start - start JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * Setup and start the JPEG block
- */
-static int jpeg_v2_5_start(struct amdgpu_device *adev)
+static int vcn_v2_5_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, bool indirect)
 {
 	struct amdgpu_ring *ring;
-	uint32_t tmp;
-	int i;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		ring = &adev->vcn.inst[i].ring_jpeg;
-		/* disable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JPEG_POWER_STATUS), 0,
-			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-
-		/* JPEG disable CGC */
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL);
-		tmp |= 1 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
-		tmp |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
-		tmp |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL, tmp);
-
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_GATE);
-		tmp &= ~(JPEG_CGC_GATE__JPEG_DEC_MASK
-			| JPEG_CGC_GATE__JPEG2_DEC_MASK
-			| JPEG_CGC_GATE__JMCIF_MASK
-			| JPEG_CGC_GATE__JRBBM_MASK);
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_GATE, tmp);
-
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL);
-		tmp &= ~(JPEG_CGC_CTRL__JPEG_DEC_MODE_MASK
-			| JPEG_CGC_CTRL__JPEG2_DEC_MODE_MASK
-			| JPEG_CGC_CTRL__JMCIF_MODE_MASK
-			| JPEG_CGC_CTRL__JRBBM_MODE_MASK);
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_CTRL, tmp);
-
-		/* MJPEG global tiling registers */
-		WREG32_SOC15(UVD, i, mmJPEG_DEC_GFX8_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-		WREG32_SOC15(UVD, i, mmJPEG_DEC_GFX10_ADDR_CONFIG,
-			adev->gfx.config.gb_addr_config);
-
-		/* enable JMI channel */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JMI_CNTL), 0,
-			~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		/* enable System Interrupt for JRBC */
-		WREG32_P(SOC15_REG_OFFSET(VCN, i, mmJPEG_SYS_INT_EN),
-			JPEG_SYS_INT_EN__DJRBC_MASK,
-			~JPEG_SYS_INT_EN__DJRBC_MASK);
-
-		WREG32_SOC15(UVD, i, mmUVD_LMI_JRBC_RB_VMID, 0);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
-		WREG32_SOC15(UVD, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW,
-			lower_32_bits(ring->gpu_addr));
-		WREG32_SOC15(UVD, i, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH,
-			upper_32_bits(ring->gpu_addr));
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_RPTR, 0);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_WPTR, 0);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_CNTL, 0x00000002L);
-		WREG32_SOC15(UVD, i, mmUVD_JRBC_RB_SIZE, ring->ring_size / 4);
-		ring->wptr = RREG32_SOC15(UVD, i, mmUVD_JRBC_RB_WPTR);
-	}
-
-	return 0;
-}
-
-/**
- * jpeg_v2_5_stop - stop JPEG block
- *
- * @adev: amdgpu_device pointer
- *
- * stop the JPEG block
- */
-static int jpeg_v2_5_stop(struct amdgpu_device *adev)
-{
-	uint32_t tmp;
-	int i;
+	uint32_t rb_bufsz, tmp;
 
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		/* reset JMI */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JMI_CNTL),
-			UVD_JMI_CNTL__SOFT_RESET_MASK,
-			~UVD_JMI_CNTL__SOFT_RESET_MASK);
-
-		tmp = RREG32_SOC15(VCN, i, mmJPEG_CGC_GATE);
-		tmp |= (JPEG_CGC_GATE__JPEG_DEC_MASK
-			|JPEG_CGC_GATE__JPEG2_DEC_MASK
-			|JPEG_CGC_GATE__JMCIF_MASK
-			|JPEG_CGC_GATE__JRBBM_MASK);
-		WREG32_SOC15(VCN, i, mmJPEG_CGC_GATE, tmp);
-
-		/* enable anti hang mechanism */
-		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_JPEG_POWER_STATUS),
-			UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK,
-			~UVD_JPEG_POWER_STATUS__JPEG_POWER_STATUS_MASK);
-	}
+	/* disable register anti-hang mechanism */
+	WREG32_P(SOC15_REG_OFFSET(UVD, inst_idx, mmUVD_POWER_STATUS), 1,
+		~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
+	/* enable dynamic power gating mode */
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_POWER_STATUS);
+	tmp |= UVD_POWER_STATUS__UVD_PG_MODE_MASK;
+	tmp |= UVD_POWER_STATUS__UVD_PG_EN_MASK;
+	WREG32_SOC15(UVD, inst_idx, mmUVD_POWER_STATUS, tmp);
+
+	if (indirect)
+		adev->vcn.inst[inst_idx].dpg_sram_curr_addr = (uint32_t*)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr;
+
+	/* enable clock gating */
+	vcn_v2_5_clock_gating_dpg_mode(adev, 0, inst_idx, indirect);
+
+	/* enable VCPU clock */
+	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
+	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
+	tmp |= UVD_VCPU_CNTL__BLK_RST_MASK;
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CNTL), tmp, 0, indirect);
+
+	/* disable master interupt */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MASTINT_EN), 0, 0, indirect);
+
+	/* setup mmUVD_LMI_CTRL */
+	tmp = (0x8 | UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
+		UVD_LMI_CTRL__REQ_MODE_MASK |
+		UVD_LMI_CTRL__CRC_RESET_MASK |
+		UVD_LMI_CTRL__MASK_MC_URGENT_MASK |
+		UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
+		UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK |
+		(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
+		0x00100000L);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_CTRL), tmp, 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_CNTL),
+		0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT, 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_SET_MUXA0),
+		((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
+		 (0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
+		 (0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
+		 (0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)), 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_SET_MUXB0),
+		((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
+		 (0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
+		 (0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
+		 (0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)), 0, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MPC_SET_MUX),
+		((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
+		 (0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
+		 (0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0, indirect);
+
+	vcn_v2_5_mc_resume_dpg_mode(adev, inst_idx, indirect);
+
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_REG_XX_MASK), 0x10, 0, indirect);
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_RBC_XX_IB_REG_CHECK), 0x3, 0, indirect);
+
+	/* enable LMI MC and UMC channels */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_LMI_CTRL2), 0, 0, indirect);
+
+	/* unblock VCPU register access */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_RB_ARB_CTRL), 0, 0, indirect);
+
+	tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
+	tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_VCPU_CNTL), tmp, 0, indirect);
+
+	/* enable master interrupt */
+	WREG32_SOC15_DPG_MODE_2_0(inst_idx, SOC15_DPG_MODE_OFFSET_2_0(
+		UVD, inst_idx, mmUVD_MASTINT_EN),
+		UVD_MASTINT_EN__VCPU_EN_MASK, 0, indirect);
+
+	if (indirect)
+		psp_update_vcn_sram(adev, inst_idx, adev->vcn.inst[inst_idx].dpg_sram_gpu_addr,
+				    (uint32_t)((uintptr_t)adev->vcn.inst[inst_idx].dpg_sram_curr_addr -
+					       (uintptr_t)adev->vcn.inst[inst_idx].dpg_sram_cpu_addr));
+
+	ring = &adev->vcn.inst[inst_idx].ring_dec;
+	/* force RBC into idle state */
+	rb_bufsz = order_base_2(ring->ring_size);
+	tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+	tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_CNTL, tmp);
+
+	/* set the write pointer delay */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR_CNTL, 0);
+
+	/* set the wb address */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_RPTR_ADDR,
+		(upper_32_bits(ring->gpu_addr) >> 2));
+
+	/* programm the RB_BASE for ring buffer */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
+		lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(UVD, inst_idx, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
+		upper_32_bits(ring->gpu_addr));
+
+	/* Initialize the ring buffer's read and write pointers */
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_RPTR, 0);
+
+	WREG32_SOC15(UVD, inst_idx, mmUVD_SCRATCH2, 0);
+
+	ring->wptr = RREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_RPTR);
+	WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR,
+		lower_32_bits(ring->wptr));
 
 	return 0;
 }
@@ -713,6 +891,9 @@ static int vcn_v2_5_start(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+			return vcn_v2_5_start_dpg_mode(adev, i, adev->vcn.indirect_sram);
+
 		/* disable register anti-hang mechanism */
 		WREG32_P(SOC15_REG_OFFSET(UVD, i, mmUVD_POWER_STATUS), 0,
 			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
@@ -874,23 +1055,251 @@ static int vcn_v2_5_start(struct amdgpu_device *adev)
 		WREG32_SOC15(UVD, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 		WREG32_SOC15(UVD, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
 	}
-	r = jpeg_v2_5_start(adev);
 
-	return r;
+	return 0;
 }
 
-static int vcn_v2_5_stop(struct amdgpu_device *adev)
+static int vcn_v2_5_mmsch_start(struct amdgpu_device *adev,
+				struct amdgpu_mm_table *table)
+{
+	uint32_t data = 0, loop = 0, size = 0;
+	uint64_t addr = table->gpu_addr;
+	struct mmsch_v1_1_init_header *header = NULL;;
+
+	header = (struct mmsch_v1_1_init_header *)table->cpu_addr;
+	size = header->total_size;
+
+	/*
+	 * 1, write to vce_mmsch_vf_ctx_addr_lo/hi register with GPU mc addr of
+	 *  memory descriptor location
+	 */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_CTX_ADDR_LO, lower_32_bits(addr));
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_CTX_ADDR_HI, upper_32_bits(addr));
+
+	/* 2, update vmid of descriptor */
+	data = RREG32_SOC15(UVD, 0, mmMMSCH_VF_VMID);
+	data &= ~MMSCH_VF_VMID__VF_CTX_VMID_MASK;
+	/* use domain0 for MM scheduler */
+	data |= (0 << MMSCH_VF_VMID__VF_CTX_VMID__SHIFT);
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_VMID, data);
+
+	/* 3, notify mmsch about the size of this descriptor */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_CTX_SIZE, size);
+
+	/* 4, set resp to zero */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_RESP, 0);
+
+	/*
+	 * 5, kick off the initialization and wait until
+	 * VCE_MMSCH_VF_MAILBOX_RESP becomes non-zero
+	 */
+	WREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_HOST, 0x10000001);
+
+	data = RREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_RESP);
+	loop = 10;
+	while ((data & 0x10000002) != 0x10000002) {
+		udelay(100);
+		data = RREG32_SOC15(UVD, 0, mmMMSCH_VF_MAILBOX_RESP);
+		loop--;
+		if (!loop)
+			break;
+	}
+
+	if (!loop) {
+		dev_err(adev->dev,
+			"failed to init MMSCH, mmMMSCH_VF_MAILBOX_RESP = %x\n",
+			data);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int vcn_v2_5_sriov_start(struct amdgpu_device *adev)
+{
+	struct amdgpu_ring *ring;
+	uint32_t offset, size, tmp, i, rb_bufsz;
+	uint32_t table_size = 0;
+	struct mmsch_v1_0_cmd_direct_write direct_wt = { { 0 } };
+	struct mmsch_v1_0_cmd_direct_read_modify_write direct_rd_mod_wt = { { 0 } };
+	struct mmsch_v1_0_cmd_direct_polling direct_poll = { { 0 } };
+	struct mmsch_v1_0_cmd_end end = { { 0 } };
+	uint32_t *init_table = adev->virt.mm_table.cpu_addr;
+	struct mmsch_v1_1_init_header *header = (struct mmsch_v1_1_init_header *)init_table;
+
+	direct_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_WRITE;
+	direct_rd_mod_wt.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_READ_MODIFY_WRITE;
+	direct_poll.cmd_header.command_type = MMSCH_COMMAND__DIRECT_REG_POLLING;
+	end.cmd_header.command_type = MMSCH_COMMAND__END;
+
+	header->version = MMSCH_VERSION;
+	header->total_size = sizeof(struct mmsch_v1_1_init_header) >> 2;
+	init_table += header->total_size;
+
+	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+		header->eng[i].table_offset = header->total_size;
+		header->eng[i].init_status = 0;
+		header->eng[i].table_size = 0;
+
+		table_size = 0;
+
+		MMSCH_V1_0_INSERT_DIRECT_RD_MOD_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_STATUS),
+			~UVD_STATUS__UVD_BUSY, UVD_STATUS__UVD_BUSY);
+
+		size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
+		/* mc resume*/
+		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_lo);
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				adev->firmware.ucode[AMDGPU_UCODE_ID_VCN + i].tmr_mc_addr_hi);
+			offset = 0;
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0), 0);
+		} else {
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+				lower_32_bits(adev->vcn.inst[i].gpu_addr));
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i,
+					mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+				upper_32_bits(adev->vcn.inst[i].gpu_addr));
+			offset = size;
+			MMSCH_V1_0_INSERT_DIRECT_WT(
+				SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0),
+				AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+		}
+
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE0),
+			size);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET1),
+			0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE1),
+			AMDGPU_VCN_STACK_SIZE);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW),
+			lower_32_bits(adev->vcn.inst[i].gpu_addr + offset +
+				AMDGPU_VCN_STACK_SIZE));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH),
+			upper_32_bits(adev->vcn.inst[i].gpu_addr + offset +
+				AMDGPU_VCN_STACK_SIZE));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET2),
+			0);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE2),
+			AMDGPU_VCN_CONTEXT_SIZE);
+
+		ring = &adev->vcn.inst[i].ring_enc[0];
+		ring->wptr = 0;
+
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_LO),
+			lower_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RB_BASE_HI),
+			upper_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RB_SIZE),
+			ring->ring_size / 4);
+
+		ring = &adev->vcn.inst[i].ring_dec;
+		ring->wptr = 0;
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_RBC_RB_64BIT_BAR_LOW),
+			lower_32_bits(ring->gpu_addr));
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i,
+				mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH),
+			upper_32_bits(ring->gpu_addr));
+
+		/* force RBC into idle state */
+		rb_bufsz = order_base_2(ring->ring_size);
+		tmp = REG_SET_FIELD(0, UVD_RBC_RB_CNTL, RB_BUFSZ, rb_bufsz);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_BLKSZ, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_FETCH, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_NO_UPDATE, 1);
+		tmp = REG_SET_FIELD(tmp, UVD_RBC_RB_CNTL, RB_RPTR_WR_EN, 1);
+		MMSCH_V1_0_INSERT_DIRECT_WT(
+			SOC15_REG_OFFSET(UVD, i, mmUVD_RBC_RB_CNTL), tmp);
+
+		/* add end packet */
+		memcpy((void *)init_table, &end, sizeof(struct mmsch_v1_0_cmd_end));
+		table_size += sizeof(struct mmsch_v1_0_cmd_end) / 4;
+		init_table += sizeof(struct mmsch_v1_0_cmd_end) / 4;
+
+		/* refine header */
+		header->eng[i].table_size = table_size;
+		header->total_size += table_size;
+	}
+
+	return vcn_v2_5_mmsch_start(adev, &adev->virt.mm_table);
+}
+
+static int vcn_v2_5_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 {
+	int ret_code = 0;
 	uint32_t tmp;
-	int i, r;
 
-	r = jpeg_v2_5_stop(adev);
-	if (r)
-		return r;
+	/* Wait for power status to be 1 */
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, 1,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+
+	/* wait for read ptr to be equal to write ptr */
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR);
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR2);
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code);
+
+	tmp = RREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+
+	SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, 1,
+		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+
+	/* disable dynamic power gating mode */
+	WREG32_P(SOC15_REG_OFFSET(UVD, inst_idx, mmUVD_POWER_STATUS), 0,
+			~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
+
+	return 0;
+}
+
+static int vcn_v2_5_stop(struct amdgpu_device *adev)
+{
+	uint32_t tmp;
+	int i, r = 0;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
+
+		if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+			r = vcn_v2_5_stop_dpg_mode(adev, i);
+			goto power_off;
+		}
+
 		/* wait for vcn idle */
 		SOC15_WAIT_ON_RREG(VCN, i, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7, r);
 		if (r)
@@ -940,12 +1349,74 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev)
 			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
 	}
 
+power_off:
 	if (adev->pm.dpm_enabled)
 		amdgpu_dpm_enable_uvd(adev, false);
 
 	return 0;
 }
 
+static int vcn_v2_5_pause_dpg_mode(struct amdgpu_device *adev,
+				int inst_idx, struct dpg_pause_state *new_state)
+{
+	struct amdgpu_ring *ring;
+	uint32_t reg_data = 0;
+	int ret_code;
+
+	/* pause/unpause if state is changed */
+	if (adev->vcn.pause_state.fw_based != new_state->fw_based) {
+		DRM_DEBUG("dpg pause state changed %d -> %d",
+			adev->vcn.pause_state.fw_based,	new_state->fw_based);
+		reg_data = RREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE) &
+			(~UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
+
+		if (new_state->fw_based == VCN_DPG_STATE__PAUSE) {
+			ret_code = 0;
+			SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS, 0x1,
+				UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+
+			if (!ret_code) {
+				/* pause DPG */
+				reg_data |= UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+				WREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE, reg_data);
+
+				/* wait for ACK */
+				SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_DPG_PAUSE,
+					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
+					   UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code);
+
+				/* Restore */
+				ring = &adev->vcn.inst[inst_idx].ring_enc[0];
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+
+				ring = &adev->vcn.inst[inst_idx].ring_enc[1];
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4);
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+
+				WREG32_SOC15(UVD, inst_idx, mmUVD_RBC_RB_WPTR,
+					   RREG32_SOC15(UVD, inst_idx, mmUVD_SCRATCH2) & 0x7FFFFFFF);
+
+				SOC15_WAIT_ON_RREG(UVD, inst_idx, mmUVD_POWER_STATUS,
+					   0x0, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+			}
+		} else {
+			/* unpause dpg, no need to wait */
+			reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
+			WREG32_SOC15(UVD, inst_idx, mmUVD_DPG_PAUSE, reg_data);
+		}
+		adev->vcn.pause_state.fw_based = new_state->fw_based;
+	}
+
+	return 0;
+}
+
 /**
  * vcn_v2_5_dec_ring_get_rptr - get read pointer
  *
@@ -988,6 +1459,10 @@ static void vcn_v2_5_dec_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
+		WREG32_SOC15(UVD, ring->me, mmUVD_SCRATCH2,
+			lower_32_bits(ring->wptr) | 0x80000000);
+
 	if (ring->use_doorbell) {
 		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
 		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
@@ -1125,86 +1600,6 @@ static const struct amdgpu_ring_funcs vcn_v2_5_enc_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-/**
- * vcn_v2_5_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v2_5_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	return RREG32_SOC15(UVD, ring->me, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v2_5_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v2_5_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell)
-		return adev->wb.wb[ring->wptr_offs];
-	else
-		return RREG32_SOC15(UVD, ring->me, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v2_5_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v2_5_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
-	struct amdgpu_device *adev = ring->adev;
-
-	if (ring->use_doorbell) {
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
-		WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
-	} else {
-		WREG32_SOC15(UVD, ring->me, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-	}
-}
-
-static const struct amdgpu_ring_funcs vcn_v2_5_jpeg_ring_vm_funcs = {
-	.type = AMDGPU_RING_TYPE_VCN_JPEG,
-	.align_mask = 0xf,
-	.vmhub = AMDGPU_MMHUB_1,
-	.get_rptr = vcn_v2_5_jpeg_ring_get_rptr,
-	.get_wptr = vcn_v2_5_jpeg_ring_get_wptr,
-	.set_wptr = vcn_v2_5_jpeg_ring_set_wptr,
-	.emit_frame_size =
-		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
-		8 + /* vcn_v2_0_jpeg_ring_emit_vm_flush */
-		18 + 18 + /* vcn_v2_0_jpeg_ring_emit_fence x2 vm fence */
-		8 + 16,
-	.emit_ib_size = 22, /* vcn_v2_0_jpeg_ring_emit_ib */
-	.emit_ib = vcn_v2_0_jpeg_ring_emit_ib,
-	.emit_fence = vcn_v2_0_jpeg_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_jpeg_ring_emit_vm_flush,
-	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
-	.insert_nop = vcn_v2_0_jpeg_ring_nop,
-	.insert_start = vcn_v2_0_jpeg_ring_insert_start,
-	.insert_end = vcn_v2_0_jpeg_ring_insert_end,
-	.pad_ib = amdgpu_ring_generic_pad_ib,
-	.begin_use = amdgpu_vcn_ring_begin_use,
-	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_jpeg_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_jpeg_ring_emit_reg_wait,
-	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
 static void vcn_v2_5_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
@@ -1233,19 +1628,6 @@ static void vcn_v2_5_set_enc_ring_funcs(struct amdgpu_device *adev)
 	}
 }
 
-static void vcn_v2_5_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
-	int i;
-
-	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-		if (adev->vcn.harvest_config & (1 << i))
-			continue;
-		adev->vcn.inst[i].ring_jpeg.funcs = &vcn_v2_5_jpeg_ring_vm_funcs;
-		adev->vcn.inst[i].ring_jpeg.me = i;
-		DRM_INFO("VCN(%d) jpeg decode is enabled in VM mode\n", i);
-	}
-}
-
 static bool vcn_v2_5_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1283,6 +1665,9 @@ static int vcn_v2_5_set_clockgating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	if (enable) {
 		if (vcn_v2_5_is_idle(handle))
 			return -EBUSY;
@@ -1300,6 +1685,9 @@ static int vcn_v2_5_set_powergating_state(void *handle,
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int ret;
 
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
 	if(state == adev->vcn.cur_state)
 		return 0;
 
@@ -1352,9 +1740,6 @@ static int vcn_v2_5_process_interrupt(struct amdgpu_device *adev,
 	case VCN_2_0__SRCID__UVD_ENC_LOW_LATENCY:
 		amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[1]);
 		break;
-	case VCN_2_0__SRCID__JPEG_DECODE:
-		amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_jpeg);
-		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -1376,7 +1761,7 @@ static void vcn_v2_5_set_irq_funcs(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
-		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 2;
+		adev->vcn.inst[i].irq.num_types = adev->vcn.num_enc_rings + 1;
 		adev->vcn.inst[i].irq.funcs = &vcn_v2_5_irq_funcs;
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 5cb7e231de5f..d9e331084ea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -234,16 +234,9 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE_HI, (ih->gpu_addr >> 40) & 0xff);
 
 	ih_rb_cntl = RREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL);
-	ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN);
 	ih_rb_cntl = vega10_ih_rb_cntl(ih, ih_rb_cntl);
-	if (adev->irq.ih.use_bus_addr) {
-		ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN, MC_SPACE_GPA_ENABLE, 1);
-	} else {
-		ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN, MC_SPACE_FBPA_ENABLE, 1);
-	}
 	ih_rb_cntl = REG_SET_FIELD(ih_rb_cntl, IH_RB_CNTL, RPTR_REARM,
 				   !!adev->irq.msi_enabled);
-
 	if (amdgpu_sriov_vf(adev)) {
 		if (psp_reg_program(&adev->psp, PSP_REG_IH_RB_CNTL, ih_rb_cntl)) {
 			DRM_ERROR("PSP program IH_RB_CNTL failed!\n");
@@ -253,10 +246,19 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 		WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
 	}
 
-	if ((adev->asic_type == CHIP_ARCTURUS
-		&& adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT)
-		|| adev->asic_type == CHIP_RENOIR)
+	if ((adev->asic_type == CHIP_ARCTURUS &&
+	     adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) ||
+	    adev->asic_type == CHIP_RENOIR) {
+		ih_chicken = RREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN);
+		if (adev->irq.ih.use_bus_addr) {
+			ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
+						   MC_SPACE_GPA_ENABLE, 1);
+		} else {
+			ih_chicken = REG_SET_FIELD(ih_chicken, IH_CHICKEN,
+						   MC_SPACE_FBPA_ENABLE, 1);
+		}
 		WREG32_SOC15(OSSSYS, 0, mmIH_CHICKEN, ih_chicken);
+	}
 
 	/* set the writeback address whether it's enabled or not */
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_WPTR_ADDR_LO,
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index f1b171e30774..78b35901643b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -689,40 +689,6 @@ static int vi_gpu_pci_config_reset(struct amdgpu_device *adev)
 	return -EINVAL;
 }
 
-int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap)
-{
-	void *pp_handle = adev->powerplay.pp_handle;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
-		*cap = false;
-		return -ENOENT;
-	}
-
-	return pp_funcs->get_asic_baco_capability(pp_handle, cap);
-}
-
-int smu7_asic_baco_reset(struct amdgpu_device *adev)
-{
-	void *pp_handle = adev->powerplay.pp_handle;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
-		return -ENOENT;
-
-	/* enter BACO state */
-	if (pp_funcs->set_asic_baco_state(pp_handle, 1))
-		return -EIO;
-
-	/* exit BACO state */
-	if (pp_funcs->set_asic_baco_state(pp_handle, 0))
-		return -EIO;
-
-	dev_info(adev->dev, "GPU BACO reset\n");
-
-	return 0;
-}
-
 /**
  * vi_asic_pci_config_reset - soft reset GPU
  *
@@ -745,6 +711,21 @@ static int vi_asic_pci_config_reset(struct amdgpu_device *adev)
 	return r;
 }
 
+static bool vi_asic_supports_baco(struct amdgpu_device *adev)
+{
+	switch (adev->asic_type) {
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_TOPAZ:
+		return amdgpu_dpm_is_baco_supported(adev);
+	default:
+		return false;
+	}
+}
+
 static enum amd_reset_method
 vi_asic_reset_method(struct amdgpu_device *adev)
 {
@@ -757,7 +738,7 @@ vi_asic_reset_method(struct amdgpu_device *adev)
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
 	case CHIP_TOPAZ:
-		smu7_asic_get_baco_capability(adev, &baco_reset);
+		baco_reset = amdgpu_dpm_is_baco_supported(adev);
 		break;
 	default:
 		baco_reset = false;
@@ -786,7 +767,7 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
 		if (!adev->in_suspend)
 			amdgpu_inc_vram_lost(adev);
-		r = smu7_asic_baco_reset(adev);
+		r = amdgpu_dpm_baco_reset(adev);
 	} else {
 		r = vi_asic_pci_config_reset(adev);
 	}
@@ -1119,6 +1100,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs =
 	.get_pcie_usage = &vi_get_pcie_usage,
 	.need_reset_on_init = &vi_need_reset_on_init,
 	.get_pcie_replay_count = &vi_get_pcie_replay_count,
+	.supports_baco = &vi_asic_supports_baco,
 };
 
 #define CZ_REV_BRISTOL(rev)	 \
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.h b/drivers/gpu/drm/amd/amdgpu/vi.h
index 40d4174913a4..defb4aaf929a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.h
+++ b/drivers/gpu/drm/amd/amdgpu/vi.h
@@ -31,7 +31,5 @@ void vi_srbm_select(struct amdgpu_device *adev,
 int vi_set_ip_blocks(struct amdgpu_device *adev);
 
 void legacy_doorbell_index_init(struct amdgpu_device *adev);
-int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap);
-int smu7_asic_baco_reset(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/Makefile b/drivers/gpu/drm/amd/amdkfd/Makefile
index 48155060a57c..61474627a32c 100644
--- a/drivers/gpu/drm/amd/amdkfd/Makefile
+++ b/drivers/gpu/drm/amd/amdkfd/Makefile
@@ -38,11 +38,9 @@ AMDKFD_FILES	:= $(AMDKFD_PATH)/kfd_module.o \
 		$(AMDKFD_PATH)/kfd_mqd_manager_v9.o \
 		$(AMDKFD_PATH)/kfd_mqd_manager_v10.o \
 		$(AMDKFD_PATH)/kfd_kernel_queue.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_cik.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_vi.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_v9.o \
-		$(AMDKFD_PATH)/kfd_kernel_queue_v10.o \
 		$(AMDKFD_PATH)/kfd_packet_manager.o \
+		$(AMDKFD_PATH)/kfd_packet_manager_vi.o \
+		$(AMDKFD_PATH)/kfd_packet_manager_v9.o \
 		$(AMDKFD_PATH)/kfd_process_queue_manager.o \
 		$(AMDKFD_PATH)/kfd_device_queue_manager.o \
 		$(AMDKFD_PATH)/kfd_device_queue_manager_cik.o \
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 1544007af34a..3f0300e53727 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -42,6 +42,7 @@
 
 static long kfd_ioctl(struct file *, unsigned int, unsigned long);
 static int kfd_open(struct inode *, struct file *);
+static int kfd_release(struct inode *, struct file *);
 static int kfd_mmap(struct file *, struct vm_area_struct *);
 
 static const char kfd_dev_name[] = "kfd";
@@ -51,6 +52,7 @@ static const struct file_operations kfd_fops = {
 	.unlocked_ioctl = kfd_ioctl,
 	.compat_ioctl = compat_ptr_ioctl,
 	.open = kfd_open,
+	.release = kfd_release,
 	.mmap = kfd_mmap,
 };
 
@@ -124,8 +126,13 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
-	if (kfd_is_locked())
+	if (kfd_is_locked()) {
+		kfd_unref_process(process);
 		return -EAGAIN;
+	}
+
+	/* filep now owns the reference returned by kfd_create_process */
+	filep->private_data = process;
 
 	dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n",
 		process->pasid, process->is_32bit_user_mode);
@@ -133,6 +140,16 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	return 0;
 }
 
+static int kfd_release(struct inode *inode, struct file *filep)
+{
+	struct kfd_process *process = filep->private_data;
+
+	if (process)
+		kfd_unref_process(process);
+
+	return 0;
+}
+
 static int kfd_ioctl_get_version(struct file *filep, struct kfd_process *p,
 					void *data)
 {
@@ -258,6 +275,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	unsigned int queue_id;
 	struct kfd_process_device *pdd;
 	struct queue_properties q_properties;
+	uint32_t doorbell_offset_in_process = 0;
 
 	memset(&q_properties, 0, sizeof(struct queue_properties));
 
@@ -286,7 +304,8 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 			p->pasid,
 			dev->id);
 
-	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id);
+	err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id,
+			&doorbell_offset_in_process);
 	if (err != 0)
 		goto err_create_queue;
 
@@ -296,14 +315,11 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 	/* Return gpu_id as doorbell offset for mmap usage */
 	args->doorbell_offset = KFD_MMAP_TYPE_DOORBELL;
 	args->doorbell_offset |= KFD_MMAP_GPU_ID(args->gpu_id);
-	args->doorbell_offset <<= PAGE_SHIFT;
 	if (KFD_IS_SOC15(dev->device_info->asic_family))
-		/* On SOC15 ASICs, doorbell allocation must be
-		 * per-device, and independent from the per-process
-		 * queue_id. Return the doorbell offset within the
-		 * doorbell aperture to user mode.
+		/* On SOC15 ASICs, include the doorbell offset within the
+		 * process doorbell frame, which is 2 pages.
 		 */
-		args->doorbell_offset |= q_properties.doorbell_off;
+		args->doorbell_offset |= doorbell_offset_in_process;
 
 	mutex_unlock(&p->mutex);
 
@@ -1312,10 +1328,9 @@ static int kfd_ioctl_alloc_memory_of_gpu(struct file *filep,
 	/* MMIO is mapped through kfd device
 	 * Generate a kfd mmap offset
 	 */
-	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) {
-		args->mmap_offset = KFD_MMAP_TYPE_MMIO | KFD_MMAP_GPU_ID(args->gpu_id);
-		args->mmap_offset <<= PAGE_SHIFT;
-	}
+	if (flags & KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)
+		args->mmap_offset = KFD_MMAP_TYPE_MMIO
+					| KFD_MMAP_GPU_ID(args->gpu_id);
 
 	return 0;
 
@@ -1803,9 +1818,14 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 
 	dev_dbg(kfd_device, "ioctl cmd 0x%x (#0x%x), arg 0x%lx\n", cmd, nr, arg);
 
-	process = kfd_get_process(current);
-	if (IS_ERR(process)) {
-		dev_dbg(kfd_device, "no process\n");
+	/* Get the process struct from the filep. Only the process
+	 * that opened /dev/kfd can use the file descriptor. Child
+	 * processes need to create their own KFD device context.
+	 */
+	process = filep->private_data;
+	if (process->lead_thread != current->group_leader) {
+		dev_dbg(kfd_device, "Using KFD FD in wrong process\n");
+		retcode = -EBADF;
 		goto err_i1;
 	}
 
@@ -1899,20 +1919,19 @@ static int kfd_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct kfd_process *process;
 	struct kfd_dev *dev = NULL;
-	unsigned long vm_pgoff;
+	unsigned long mmap_offset;
 	unsigned int gpu_id;
 
 	process = kfd_get_process(current);
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
-	vm_pgoff = vma->vm_pgoff;
-	vma->vm_pgoff = KFD_MMAP_OFFSET_VALUE_GET(vm_pgoff);
-	gpu_id = KFD_MMAP_GPU_ID_GET(vm_pgoff);
+	mmap_offset = vma->vm_pgoff << PAGE_SHIFT;
+	gpu_id = KFD_MMAP_GET_GPU_ID(mmap_offset);
 	if (gpu_id)
 		dev = kfd_device_by_id(gpu_id);
 
-	switch (vm_pgoff & KFD_MMAP_TYPE_MASK) {
+	switch (mmap_offset & KFD_MMAP_TYPE_MASK) {
 	case KFD_MMAP_TYPE_DOORBELL:
 		if (!dev)
 			return -ENODEV;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index d59f2cd056c6..27bcc5b472f6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -72,11 +72,11 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 	 * The receive packet buff will be sitting on the Indirect Buffer
 	 * and in the PQ we put the IB packet + sync packet(s).
 	 */
-	status = kq->ops.acquire_packet_buffer(kq,
+	status = kq_acquire_packet_buffer(kq,
 				pq_packets_size_in_bytes / sizeof(uint32_t),
 				&ib_packet_buff);
 	if (status) {
-		pr_err("acquire_packet_buffer failed\n");
+		pr_err("kq_acquire_packet_buffer failed\n");
 		return status;
 	}
 
@@ -115,7 +115,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	if (status) {
 		pr_err("Failed to allocate GART memory\n");
-		kq->ops.rollback_packet(kq);
+		kq_rollback_packet(kq);
 		return status;
 	}
 
@@ -151,7 +151,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	rm_packet->data_lo = QUEUESTATE__ACTIVE;
 
-	kq->ops.submit_packet(kq);
+	kq_submit_packet(kq);
 
 	/* Wait till CP writes sync code: */
 	status = amdkfd_fence_wait_timeout(
@@ -185,7 +185,7 @@ static int dbgdev_register_diq(struct kfd_dbgdev *dbgdev)
 	properties.type = KFD_QUEUE_TYPE_DIQ;
 
 	status = pqm_create_queue(dbgdev->pqm, dbgdev->dev, NULL,
-				&properties, &qid);
+				&properties, &qid, NULL);
 
 	if (status) {
 		pr_err("Failed to create DIQ\n");
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 15c523027285..511712c2e382 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -93,7 +93,7 @@ void kfd_debugfs_init(void)
 			    kfd_debugfs_hqds_by_device, &kfd_debugfs_fops);
 	debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 			    kfd_debugfs_rls_by_device, &kfd_debugfs_fops);
-	debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+	debugfs_create_file("hang_hws", S_IFREG | 0200, debugfs_root,
 			    NULL, &kfd_debugfs_hang_hws_fops);
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 4fa8834ce7cb..2a9e40131735 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -728,6 +728,9 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
 		return 0;
+
+	kfd->dqm->ops.pre_reset(kfd->dqm);
+
 	kgd2kfd_suspend(kfd);
 
 	kfd_signal_reset_event(kfd);
@@ -742,7 +745,7 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 
 int kgd2kfd_post_reset(struct kfd_dev *kfd)
 {
-	int ret, count;
+	int ret;
 
 	if (!kfd->init_complete)
 		return 0;
@@ -750,7 +753,7 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 	ret = kfd_resume(kfd);
 	if (ret)
 		return ret;
-	count = atomic_dec_return(&kfd_locked);
+	atomic_dec(&kfd_locked);
 
 	atomic_set(&kfd->sram_ecc_flag, 0);
 
@@ -822,6 +825,21 @@ dqm_start_error:
 	return err;
 }
 
+static inline void kfd_queue_work(struct workqueue_struct *wq,
+				  struct work_struct *work)
+{
+	int cpu, new_cpu;
+
+	cpu = new_cpu = smp_processor_id();
+	do {
+		new_cpu = cpumask_next(new_cpu, cpu_online_mask) % nr_cpu_ids;
+		if (cpu_to_node(new_cpu) == numa_node_id())
+			break;
+	} while (cpu != new_cpu);
+
+	queue_work_on(new_cpu, wq, work);
+}
+
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
@@ -844,7 +862,7 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 				   patched_ihre, &is_patched)
 	    && enqueue_ih_ring_entry(kfd,
 				     is_patched ? patched_ihre : ih_ring_entry))
-		queue_work(kfd->ih_wq, &kfd->interrupt_work);
+		kfd_queue_work(kfd->ih_wq, &kfd->interrupt_work);
 
 	spin_unlock_irqrestore(&kfd->interrupt_lock, flags);
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 984c2f2b24b6..2870553a2ce0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -170,7 +170,7 @@ static int allocate_doorbell(struct qcm_process_device *qpd, struct queue *q)
 	}
 
 	q->properties.doorbell_off =
-		kfd_doorbell_id_to_offset(dev, q->process,
+		kfd_get_doorbell_dw_offset_in_bar(dev, q->process,
 					  q->doorbell_id);
 
 	return 0;
@@ -930,11 +930,11 @@ static void uninitialize(struct device_queue_manager *dqm)
 	for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++)
 		kfree(dqm->mqd_mgrs[i]);
 	mutex_destroy(&dqm->lock_hidden);
-	kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem);
 }
 
 static int start_nocpsch(struct device_queue_manager *dqm)
 {
+	pr_info("SW scheduler is used");
 	init_interrupts(dqm);
 	
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
@@ -947,12 +947,19 @@ static int start_nocpsch(struct device_queue_manager *dqm)
 static int stop_nocpsch(struct device_queue_manager *dqm)
 {
 	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
-		pm_uninit(&dqm->packets);
+		pm_uninit(&dqm->packets, false);
 	dqm->sched_running = false;
 
 	return 0;
 }
 
+static void pre_reset(struct device_queue_manager *dqm)
+{
+	dqm_lock(dqm);
+	dqm->is_resetting = true;
+	dqm_unlock(dqm);
+}
+
 static int allocate_sdma_queue(struct device_queue_manager *dqm,
 				struct queue *q)
 {
@@ -1100,6 +1107,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	dqm_lock(dqm);
 	/* clear hang status when driver try to start the hw scheduler */
 	dqm->is_hws_hang = false;
+	dqm->is_resetting = false;
 	dqm->sched_running = true;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	dqm_unlock(dqm);
@@ -1107,20 +1115,24 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	return 0;
 fail_allocate_vidmem:
 fail_set_sched_resources:
-	pm_uninit(&dqm->packets);
+	pm_uninit(&dqm->packets, false);
 fail_packet_manager_init:
 	return retval;
 }
 
 static int stop_cpsch(struct device_queue_manager *dqm)
 {
+	bool hanging;
+
 	dqm_lock(dqm);
-	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	if (!dqm->is_hws_hang)
+		unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	hanging = dqm->is_hws_hang || dqm->is_resetting;
 	dqm->sched_running = false;
 	dqm_unlock(dqm);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
-	pm_uninit(&dqm->packets);
+	pm_uninit(&dqm->packets, hanging);
 
 	return 0;
 }
@@ -1352,8 +1364,17 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 	/* should be timed out */
 	retval = amdkfd_fence_wait_timeout(dqm->fence_addr, KFD_FENCE_COMPLETED,
 				queue_preemption_timeout_ms);
-	if (retval)
+	if (retval) {
+		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
+		dqm->is_hws_hang = true;
+		/* It's possible we're detecting a HWS hang in the
+		 * middle of a GPU reset. No need to schedule another
+		 * reset in this case.
+		 */
+		if (!dqm->is_resetting)
+			schedule_work(&dqm->hw_exception_work);
 		return retval;
+	}
 
 	pm_release_ib(&dqm->packets);
 	dqm->active_runlist = false;
@@ -1371,12 +1392,8 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm,
 	if (dqm->is_hws_hang)
 		return -EIO;
 	retval = unmap_queues_cpsch(dqm, filter, filter_param);
-	if (retval) {
-		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
-		dqm->is_hws_hang = true;
-		schedule_work(&dqm->hw_exception_work);
+	if (retval)
 		return retval;
-	}
 
 	return map_queues_cpsch(dqm);
 }
@@ -1595,7 +1612,7 @@ static int get_wave_state(struct device_queue_manager *dqm,
 		goto dqm_unlock;
 	}
 
-	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_COMPUTE];
+	mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_CP];
 
 	if (!mqd_mgr->get_wave_state) {
 		r = -EINVAL;
@@ -1770,6 +1787,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		dqm->ops.initialize = initialize_cpsch;
 		dqm->ops.start = start_cpsch;
 		dqm->ops.stop = stop_cpsch;
+		dqm->ops.pre_reset = pre_reset;
 		dqm->ops.destroy_queue = destroy_queue_cpsch;
 		dqm->ops.update_queue = update_queue;
 		dqm->ops.register_process = register_process;
@@ -1788,6 +1806,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 		/* initialize dqm for no cp scheduling */
 		dqm->ops.start = start_nocpsch;
 		dqm->ops.stop = stop_nocpsch;
+		dqm->ops.pre_reset = pre_reset;
 		dqm->ops.create_queue = create_queue_nocpsch;
 		dqm->ops.destroy_queue = destroy_queue_nocpsch;
 		dqm->ops.update_queue = update_queue;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index a8c37e6da027..871d3b628d2d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -104,6 +104,7 @@ struct device_queue_manager_ops {
 	int	(*initialize)(struct device_queue_manager *dqm);
 	int	(*start)(struct device_queue_manager *dqm);
 	int	(*stop)(struct device_queue_manager *dqm);
+	void	(*pre_reset)(struct device_queue_manager *dqm);
 	void	(*uninitialize)(struct device_queue_manager *dqm);
 	int	(*create_kernel_queue)(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
@@ -190,7 +191,6 @@ struct device_queue_manager {
 	/* the pasid mapping for each kfd vmid */
 	uint16_t		vmid_pasid[VMID_NUM];
 	uint64_t		pipelines_addr;
-	struct kfd_mem_obj	*pipeline_mem;
 	uint64_t		fence_gpu_addr;
 	unsigned int		*fence_addr;
 	struct kfd_mem_obj	*fence_mem;
@@ -199,6 +199,7 @@ struct device_queue_manager {
 
 	/* hw exception  */
 	bool			is_hws_hang;
+	bool			is_resetting;
 	struct work_struct	hw_exception_work;
 	struct kfd_mem_obj	hiq_sdma_mqd;
 	bool			sched_running;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index ebe79bf00145..8e0c00b9555e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -91,7 +91,7 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	kfd->doorbell_base = kfd->shared_resources.doorbell_physical_address +
 				doorbell_start_offset;
 
-	kfd->doorbell_id_offset = doorbell_start_offset / sizeof(u32);
+	kfd->doorbell_base_dw_offset = doorbell_start_offset / sizeof(u32);
 
 	kfd->doorbell_kernel_ptr = ioremap(kfd->doorbell_base,
 					   kfd_doorbell_process_slice(kfd));
@@ -103,8 +103,8 @@ int kfd_doorbell_init(struct kfd_dev *kfd)
 	pr_debug("doorbell base           == 0x%08lX\n",
 			(uintptr_t)kfd->doorbell_base);
 
-	pr_debug("doorbell_id_offset      == 0x%08lX\n",
-			kfd->doorbell_id_offset);
+	pr_debug("doorbell_base_dw_offset      == 0x%08lX\n",
+			kfd->doorbell_base_dw_offset);
 
 	pr_debug("doorbell_process_limit  == 0x%08lX\n",
 			doorbell_process_limit);
@@ -185,7 +185,7 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	 * Calculating the kernel doorbell offset using the first
 	 * doorbell page.
 	 */
-	*doorbell_off = kfd->doorbell_id_offset + inx;
+	*doorbell_off = kfd->doorbell_base_dw_offset + inx;
 
 	pr_debug("Get kernel queue doorbell\n"
 			"     doorbell offset   == 0x%08X\n"
@@ -225,17 +225,17 @@ void write_kernel_doorbell64(void __iomem *db, u64 value)
 	}
 }
 
-unsigned int kfd_doorbell_id_to_offset(struct kfd_dev *kfd,
+unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
 					struct kfd_process *process,
 					unsigned int doorbell_id)
 {
 	/*
-	 * doorbell_id_offset accounts for doorbells taken by KGD.
+	 * doorbell_base_dw_offset accounts for doorbells taken by KGD.
 	 * index * kfd_doorbell_process_slice/sizeof(u32) adjusts to
 	 * the process's doorbells. The offset returned is in dword
 	 * units regardless of the ASIC-dependent doorbell size.
 	 */
-	return kfd->doorbell_id_offset +
+	return kfd->doorbell_base_dw_offset +
 		process->doorbell_index
 		* kfd_doorbell_process_slice(kfd) / sizeof(u32) +
 		doorbell_id * kfd->device_info->doorbell_size / sizeof(u32);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 908081c85de1..1f8365575b12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -346,7 +346,6 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		ret = create_signal_event(devkfd, p, ev);
 		if (!ret) {
 			*event_page_offset = KFD_MMAP_TYPE_EVENTS;
-			*event_page_offset <<= PAGE_SHIFT;
 			*event_slot_index = ev->event_id;
 		}
 		break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 193e2835bd4d..8d871514671e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -62,9 +62,6 @@ int kfd_iommu_device_init(struct kfd_dev *kfd)
 	struct amd_iommu_device_info iommu_info;
 	unsigned int pasid_limit;
 	int err;
-	struct kfd_topology_device *top_dev;
-
-	top_dev = kfd_topology_device_by_id(kfd->id);
 
 	if (!kfd->device_info->needs_iommu_device)
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 11d244891393..bae706462f96 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -34,7 +34,10 @@
 
 #define PM4_COUNT_ZERO (((1 << 15) - 1) << 16)
 
-static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
+/* Initialize a kernel queue, including allocations of GART memory
+ * needed for the queue.
+ */
+static bool kq_initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		enum kfd_queue_type type, unsigned int queue_size)
 {
 	struct queue_properties prop;
@@ -87,9 +90,17 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->pq_kernel_addr = kq->pq->cpu_ptr;
 	kq->pq_gpu_addr = kq->pq->gpu_addr;
 
-	retval = kq->ops_asic_specific.initialize(kq, dev, type, queue_size);
-	if (!retval)
-		goto err_eop_allocate_vidmem;
+	/* For CIK family asics, kq->eop_mem is not needed */
+	if (dev->device_info->asic_family > CHIP_MULLINS) {
+		retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
+		if (retval != 0)
+			goto err_eop_allocate_vidmem;
+
+		kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
+		kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
+
+		memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
+	}
 
 	retval = kfd_gtt_sa_allocate(dev, sizeof(*kq->rptr_kernel),
 					&kq->rptr_mem);
@@ -183,9 +194,10 @@ err_get_kernel_doorbell:
 
 }
 
-static void uninitialize(struct kernel_queue *kq)
+/* Uninitialize a kernel queue and free all its memory usages. */
+static void kq_uninitialize(struct kernel_queue *kq, bool hanging)
 {
-	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
+	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ && !hanging)
 		kq->mqd_mgr->destroy_mqd(kq->mqd_mgr,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
@@ -200,14 +212,19 @@ static void uninitialize(struct kernel_queue *kq)
 
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
-	kq->ops_asic_specific.uninitialize(kq);
+
+	/* For CIK family asics, kq->eop_mem is Null, kfd_gtt_sa_free()
+	 * is able to handle NULL properly.
+	 */
+	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
+
 	kfd_gtt_sa_free(kq->dev, kq->pq);
 	kfd_release_kernel_doorbell(kq->dev,
 					kq->queue->properties.doorbell_ptr);
 	uninit_queue(kq->queue);
 }
 
-static int acquire_packet_buffer(struct kernel_queue *kq,
+int kq_acquire_packet_buffer(struct kernel_queue *kq,
 		size_t packet_size_in_dwords, unsigned int **buffer_ptr)
 {
 	size_t available_size;
@@ -268,7 +285,7 @@ err_no_space:
 	return -ENOMEM;
 }
 
-static void submit_packet(struct kernel_queue *kq)
+void kq_submit_packet(struct kernel_queue *kq)
 {
 #ifdef DEBUG
 	int i;
@@ -280,11 +297,18 @@ static void submit_packet(struct kernel_queue *kq)
 	}
 	pr_debug("\n");
 #endif
-
-	kq->ops_asic_specific.submit_packet(kq);
+	if (kq->dev->device_info->doorbell_size == 8) {
+		*kq->wptr64_kernel = kq->pending_wptr64;
+		write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
+					kq->pending_wptr64);
+	} else {
+		*kq->wptr_kernel = kq->pending_wptr;
+		write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
+					kq->pending_wptr);
+	}
 }
 
-static void rollback_packet(struct kernel_queue *kq)
+void kq_rollback_packet(struct kernel_queue *kq)
 {
 	if (kq->dev->device_info->doorbell_size == 8) {
 		kq->pending_wptr64 = *kq->wptr64_kernel;
@@ -304,60 +328,18 @@ struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 	if (!kq)
 		return NULL;
 
-	kq->ops.initialize = initialize;
-	kq->ops.uninitialize = uninitialize;
-	kq->ops.acquire_packet_buffer = acquire_packet_buffer;
-	kq->ops.submit_packet = submit_packet;
-	kq->ops.rollback_packet = rollback_packet;
-
-	switch (dev->device_info->asic_family) {
-	case CHIP_CARRIZO:
-	case CHIP_TONGA:
-	case CHIP_FIJI:
-	case CHIP_POLARIS10:
-	case CHIP_POLARIS11:
-	case CHIP_POLARIS12:
-	case CHIP_VEGAM:
-		kernel_queue_init_vi(&kq->ops_asic_specific);
-		break;
-
-	case CHIP_KAVERI:
-	case CHIP_HAWAII:
-		kernel_queue_init_cik(&kq->ops_asic_specific);
-		break;
-
-	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_VEGA20:
-	case CHIP_RAVEN:
-	case CHIP_RENOIR:
-	case CHIP_ARCTURUS:
-		kernel_queue_init_v9(&kq->ops_asic_specific);
-		break;
-	case CHIP_NAVI10:
-	case CHIP_NAVI12:
-	case CHIP_NAVI14:
-		kernel_queue_init_v10(&kq->ops_asic_specific);
-		break;
-	default:
-		WARN(1, "Unexpected ASIC family %u",
-		     dev->device_info->asic_family);
-		goto out_free;
-	}
-
-	if (kq->ops.initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE))
+	if (kq_initialize(kq, dev, type, KFD_KERNEL_QUEUE_SIZE))
 		return kq;
 
 	pr_err("Failed to init kernel queue\n");
 
-out_free:
 	kfree(kq);
 	return NULL;
 }
 
-void kernel_queue_uninit(struct kernel_queue *kq)
+void kernel_queue_uninit(struct kernel_queue *kq, bool hanging)
 {
-	kq->ops.uninitialize(kq);
+	kq_uninitialize(kq, hanging);
 	kfree(kq);
 }
 
@@ -377,7 +359,7 @@ static __attribute__((unused)) void test_kq(struct kfd_dev *dev)
 		return;
 	}
 
-	retval = kq->ops.acquire_packet_buffer(kq, 5, &buffer);
+	retval = kq_acquire_packet_buffer(kq, 5, &buffer);
 	if (unlikely(retval != 0)) {
 		pr_err("  Failed to acquire packet buffer\n");
 		pr_err("Kernel queue test failed\n");
@@ -385,7 +367,7 @@ static __attribute__((unused)) void test_kq(struct kfd_dev *dev)
 	}
 	for (i = 0; i < 5; i++)
 		buffer[i] = kq->nop_packet;
-	kq->ops.submit_packet(kq);
+	kq_submit_packet(kq);
 
 	pr_err("Ending kernel queue test\n");
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
index 365fc674fea4..f4cfe9f1871c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
@@ -29,45 +29,28 @@
 #include "kfd_priv.h"
 
 /**
- * struct kernel_queue_ops
- *
- * @initialize: Initialize a kernel queue, including allocations of GART memory
- * needed for the queue.
- *
- * @uninitialize: Uninitialize a kernel queue and free all its memory usages.
- *
- * @acquire_packet_buffer: Returns a pointer to the location in the kernel
+ * kq_acquire_packet_buffer: Returns a pointer to the location in the kernel
  * queue ring buffer where the calling function can write its packet. It is
  * Guaranteed that there is enough space for that packet. It also updates the
  * pending write pointer to that location so subsequent calls to
  * acquire_packet_buffer will get a correct write pointer
  *
- * @submit_packet: Update the write pointer and doorbell of a kernel queue.
- *
- * @sync_with_hw: Wait until the write pointer and the read pointer of a kernel
- * queue are equal, which means the CP has read all the submitted packets.
+ * kq_submit_packet: Update the write pointer and doorbell of a kernel queue.
  *
- * @rollback_packet: This routine is called if we failed to build an acquired
+ * kq_rollback_packet: This routine is called if we failed to build an acquired
  * packet for some reason. It just overwrites the pending wptr with the current
  * one
  *
  */
-struct kernel_queue_ops {
-	bool	(*initialize)(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-	void	(*uninitialize)(struct kernel_queue *kq);
-	int	(*acquire_packet_buffer)(struct kernel_queue *kq,
-					size_t packet_size_in_dwords,
-					unsigned int **buffer_ptr);
 
-	void	(*submit_packet)(struct kernel_queue *kq);
-	void	(*rollback_packet)(struct kernel_queue *kq);
-};
+int kq_acquire_packet_buffer(struct kernel_queue *kq,
+				size_t packet_size_in_dwords,
+				unsigned int **buffer_ptr);
+void kq_submit_packet(struct kernel_queue *kq);
+void kq_rollback_packet(struct kernel_queue *kq);
 
-struct kernel_queue {
-	struct kernel_queue_ops ops;
-	struct kernel_queue_ops ops_asic_specific;
 
+struct kernel_queue {
 	/* data */
 	struct kfd_dev		*dev;
 	struct mqd_manager	*mqd_mgr;
@@ -99,9 +82,4 @@ struct kernel_queue {
 	struct list_head	list;
 };
 
-void kernel_queue_init_cik(struct kernel_queue_ops *ops);
-void kernel_queue_init_vi(struct kernel_queue_ops *ops);
-void kernel_queue_init_v9(struct kernel_queue_ops *ops);
-void kernel_queue_init_v10(struct kernel_queue_ops *ops);
-
 #endif /* KFD_KERNEL_QUEUE_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c
deleted file mode 100644
index aed32ab7102e..000000000000
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v10.c
+++ /dev/null
@@ -1,348 +0,0 @@
-/*
- * Copyright 2018 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include "kfd_kernel_queue.h"
-#include "kfd_device_queue_manager.h"
-#include "kfd_pm4_headers_ai.h"
-#include "kfd_pm4_opcodes.h"
-#include "gc/gc_10_1_0_sh_mask.h"
-
-static bool initialize_v10(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_v10(struct kernel_queue *kq);
-static void submit_packet_v10(struct kernel_queue *kq);
-
-void kernel_queue_init_v10(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_v10;
-	ops->uninitialize = uninitialize_v10;
-	ops->submit_packet = submit_packet_v10;
-}
-
-static bool initialize_v10(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
-{
-	int retval;
-
-	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
-	if (retval != 0)
-		return false;
-
-	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
-	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
-
-	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
-
-	return true;
-}
-
-static void uninitialize_v10(struct kernel_queue *kq)
-{
-	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
-}
-
-static void submit_packet_v10(struct kernel_queue *kq)
-{
-	*kq->wptr64_kernel = kq->pending_wptr64;
-	write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr64);
-}
-
-static int pm_map_process_v10(struct packet_manager *pm,
-		uint32_t *buffer, struct qcm_process_device *qpd)
-{
-	struct pm4_mes_map_process *packet;
-	uint64_t vm_page_table_base_addr = qpd->page_table_base;
-
-	packet = (struct pm4_mes_map_process *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_map_process));
-
-	packet->header.u32All = pm_build_pm4_header(IT_MAP_PROCESS,
-					sizeof(struct pm4_mes_map_process));
-	packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
-	packet->bitfields2.process_quantum = 1;
-	packet->bitfields2.pasid = qpd->pqm->process->pasid;
-	packet->bitfields14.gds_size = qpd->gds_size;
-	packet->bitfields14.num_gws = qpd->num_gws;
-	packet->bitfields14.num_oac = qpd->num_oac;
-	packet->bitfields14.sdma_enable = 1;
-
-	packet->bitfields14.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
-
-	packet->sh_mem_config = qpd->sh_mem_config;
-	packet->sh_mem_bases = qpd->sh_mem_bases;
-	if (qpd->tba_addr) {
-		packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
-		packet->sq_shader_tba_hi = (1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT) |
-			upper_32_bits(qpd->tba_addr >> 8);
-		packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
-		packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
-	}
-
-	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
-	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
-
-	packet->vm_context_page_table_base_addr_lo32 =
-			lower_32_bits(vm_page_table_base_addr);
-	packet->vm_context_page_table_base_addr_hi32 =
-			upper_32_bits(vm_page_table_base_addr);
-
-	return 0;
-}
-
-static int pm_runlist_v10(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t ib, size_t ib_size_in_dwords, bool chain)
-{
-	struct pm4_mes_runlist *packet;
-
-	int concurrent_proc_cnt = 0;
-	struct kfd_dev *kfd = pm->dqm->dev;
-
-	/* Determine the number of processes to map together to HW:
-	 * it can not exceed the number of VMIDs available to the
-	 * scheduler, and it is determined by the smaller of the number
-	 * of processes in the runlist and kfd module parameter
-	 * hws_max_conc_proc.
-	 * Note: the arbitration between the number of VMIDs and
-	 * hws_max_conc_proc has been done in
-	 * kgd2kfd_device_init().
-	 */
-	concurrent_proc_cnt = min(pm->dqm->processes_count,
-			kfd->max_proc_per_quantum);
-
-
-	packet = (struct pm4_mes_runlist *)buffer;
-
-	memset(buffer, 0, sizeof(struct pm4_mes_runlist));
-	packet->header.u32All = pm_build_pm4_header(IT_RUN_LIST,
-						sizeof(struct pm4_mes_runlist));
-
-	packet->bitfields4.ib_size = ib_size_in_dwords;
-	packet->bitfields4.chain = chain ? 1 : 0;
-	packet->bitfields4.offload_polling = 0;
-	packet->bitfields4.valid = 1;
-	packet->bitfields4.process_cnt = concurrent_proc_cnt;
-	packet->ordinal2 = lower_32_bits(ib);
-	packet->ib_base_hi = upper_32_bits(ib);
-
-	return 0;
-}
-
-static int pm_map_queues_v10(struct packet_manager *pm, uint32_t *buffer,
-		struct queue *q, bool is_static)
-{
-	struct pm4_mes_map_queues *packet;
-	bool use_static = is_static;
-
-	packet = (struct pm4_mes_map_queues *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
-
-	packet->header.u32All = pm_build_pm4_header(IT_MAP_QUEUES,
-					sizeof(struct pm4_mes_map_queues));
-	packet->bitfields2.num_queues = 1;
-	packet->bitfields2.queue_sel =
-		queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
-
-	packet->bitfields2.engine_sel =
-		engine_sel__mes_map_queues__compute_vi;
-	packet->bitfields2.queue_type =
-		queue_type__mes_map_queues__normal_compute_vi;
-
-	switch (q->properties.type) {
-	case KFD_QUEUE_TYPE_COMPUTE:
-		if (use_static)
-			packet->bitfields2.queue_type =
-		queue_type__mes_map_queues__normal_latency_static_queue_vi;
-		break;
-	case KFD_QUEUE_TYPE_DIQ:
-		packet->bitfields2.queue_type =
-			queue_type__mes_map_queues__debug_interface_queue_vi;
-		break;
-	case KFD_QUEUE_TYPE_SDMA:
-	case KFD_QUEUE_TYPE_SDMA_XGMI:
-		packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
-				engine_sel__mes_map_queues__sdma0_vi;
-		use_static = false; /* no static queues under SDMA */
-		break;
-	default:
-		WARN(1, "queue type %d\n", q->properties.type);
-		return -EINVAL;
-	}
-	packet->bitfields3.doorbell_offset =
-			q->properties.doorbell_off;
-
-	packet->mqd_addr_lo =
-			lower_32_bits(q->gart_mqd_addr);
-
-	packet->mqd_addr_hi =
-			upper_32_bits(q->gart_mqd_addr);
-
-	packet->wptr_addr_lo =
-			lower_32_bits((uint64_t)q->properties.write_ptr);
-
-	packet->wptr_addr_hi =
-			upper_32_bits((uint64_t)q->properties.write_ptr);
-
-	return 0;
-}
-
-static int pm_unmap_queues_v10(struct packet_manager *pm, uint32_t *buffer,
-			enum kfd_queue_type type,
-			enum kfd_unmap_queues_filter filter,
-			uint32_t filter_param, bool reset,
-			unsigned int sdma_engine)
-{
-	struct pm4_mes_unmap_queues *packet;
-
-	packet = (struct pm4_mes_unmap_queues *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
-
-	packet->header.u32All = pm_build_pm4_header(IT_UNMAP_QUEUES,
-					sizeof(struct pm4_mes_unmap_queues));
-	switch (type) {
-	case KFD_QUEUE_TYPE_COMPUTE:
-	case KFD_QUEUE_TYPE_DIQ:
-		packet->bitfields2.engine_sel =
-			engine_sel__mes_unmap_queues__compute;
-		break;
-	case KFD_QUEUE_TYPE_SDMA:
-	case KFD_QUEUE_TYPE_SDMA_XGMI:
-		packet->bitfields2.engine_sel =
-			engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
-		break;
-	default:
-		WARN(1, "queue type %d\n", type);
-		break;
-	}
-
-	if (reset)
-		packet->bitfields2.action =
-			action__mes_unmap_queues__reset_queues;
-	else
-		packet->bitfields2.action =
-			action__mes_unmap_queues__preempt_queues;
-
-	switch (filter) {
-	case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
-		packet->bitfields2.num_queues = 1;
-		packet->bitfields3b.doorbell_offset0 = filter_param;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
-		packet->bitfields3a.pasid = filter_param;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__unmap_all_queues;
-		break;
-	case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
-		/* in this case, we do not preempt static queues */
-		packet->bitfields2.queue_sel =
-			queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
-		break;
-	default:
-		WARN(1, "filter %d\n", filter);
-		break;
-	}
-
-	return 0;
-
-}
-
-static int pm_query_status_v10(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
-{
-	struct pm4_mes_query_status *packet;
-
-	packet = (struct pm4_mes_query_status *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mes_query_status));
-
-
-	packet->header.u32All = pm_build_pm4_header(IT_QUERY_STATUS,
-					sizeof(struct pm4_mes_query_status));
-
-	packet->bitfields2.context_id = 0;
-	packet->bitfields2.interrupt_sel =
-			interrupt_sel__mes_query_status__completion_status;
-	packet->bitfields2.command =
-			command__mes_query_status__fence_only_after_write_ack;
-
-	packet->addr_hi = upper_32_bits((uint64_t)fence_address);
-	packet->addr_lo = lower_32_bits((uint64_t)fence_address);
-	packet->data_hi = upper_32_bits((uint64_t)fence_value);
-	packet->data_lo = lower_32_bits((uint64_t)fence_value);
-
-	return 0;
-}
-
-
-static int pm_release_mem_v10(uint64_t gpu_addr, uint32_t *buffer)
-{
-	struct pm4_mec_release_mem *packet;
-
-	WARN_ON(!buffer);
-
-	packet = (struct pm4_mec_release_mem *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mec_release_mem));
-
-	packet->header.u32All = pm_build_pm4_header(IT_RELEASE_MEM,
-					sizeof(struct pm4_mec_release_mem));
-
-	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
-	packet->bitfields2.event_index = event_index__mec_release_mem__end_of_pipe;
-	packet->bitfields2.tcl1_action_ena = 1;
-	packet->bitfields2.tc_action_ena = 1;
-	packet->bitfields2.cache_policy = cache_policy__mec_release_mem__lru;
-
-	packet->bitfields3.data_sel = data_sel__mec_release_mem__send_32_bit_low;
-	packet->bitfields3.int_sel =
-		int_sel__mec_release_mem__send_interrupt_after_write_confirm;
-
-	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
-	packet->address_hi = upper_32_bits(gpu_addr);
-
-	packet->data_lo = 0;
-
-	return sizeof(struct pm4_mec_release_mem) / sizeof(unsigned int);
-}
-
-const struct packet_manager_funcs kfd_v10_pm_funcs = {
-	.map_process			= pm_map_process_v10,
-	.runlist			= pm_runlist_v10,
-	.set_resources			= pm_set_resources_vi,
-	.map_queues			= pm_map_queues_v10,
-	.unmap_queues			= pm_unmap_queues_v10,
-	.query_status			= pm_query_status_v10,
-	.release_mem			= pm_release_mem_v10,
-	.map_process_size		= sizeof(struct pm4_mes_map_process),
-	.runlist_size			= sizeof(struct pm4_mes_runlist),
-	.set_resources_size		= sizeof(struct pm4_mes_set_resources),
-	.map_queues_size		= sizeof(struct pm4_mes_map_queues),
-	.unmap_queues_size		= sizeof(struct pm4_mes_unmap_queues),
-	.query_status_size		= sizeof(struct pm4_mes_query_status),
-	.release_mem_size		= sizeof(struct pm4_mec_release_mem)
-};
-
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 28876aceb14b..19f0fe547c57 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -374,7 +374,6 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
 		mqd->free_mqd = free_mqd;
@@ -401,7 +400,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 #endif
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
@@ -442,7 +441,7 @@ struct mqd_manager *mqd_manager_init_cik_hawaii(enum KFD_MQD_TYPE type,
 	mqd = mqd_manager_init_cik(type, dev);
 	if (!mqd)
 		return NULL;
-	if ((type == KFD_MQD_TYPE_CP) || (type == KFD_MQD_TYPE_COMPUTE))
+	if (type == KFD_MQD_TYPE_CP)
 		mqd->update_mqd = update_mqd_hawaii;
 	return mqd;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 4a236b2c2354..d1d68a51bfb8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -66,6 +66,12 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 		m->compute_static_thread_mgmt_se3);
 }
 
+static void set_priority(struct v10_compute_mqd *m, struct queue_properties *q)
+{
+	m->cp_hqd_pipe_priority = pipe_priority_map[q->priority];
+	m->cp_hqd_queue_priority = q->priority;
+}
+
 static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
 		struct queue_properties *q)
 {
@@ -109,9 +115,6 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_QUANTUM__QUANTUM_SCALE__SHIFT |
 			10 << CP_HQD_QUANTUM__QUANTUM_DURATION__SHIFT;
 
-	m->cp_hqd_pipe_priority = 1;
-	m->cp_hqd_queue_priority = 15;
-
 	if (q->format == KFD_QUEUE_FORMAT_AQL) {
 		m->cp_hqd_aql_control =
 			1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT;
@@ -150,6 +153,14 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 	return r;
 }
 
+static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->kgd, mqd, pipe_id,
+					      queue_id, p->doorbell_off);
+}
+
 static void update_mqd(struct mqd_manager *mm, void *mqd,
 		      struct queue_properties *q)
 {
@@ -208,11 +219,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 		m->cp_hqd_ctx_save_control = 0;
 
 	update_cu_mask(mm, mqd, q);
+	set_priority(m, q);
 
-	q->is_active = (q->queue_size > 0 &&
-			q->queue_address != 0 &&
-			q->queue_percent > 0 &&
-			!q->is_evicted);
+	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
 static int destroy_mqd(struct mqd_manager *mm, void *mqd,
@@ -247,18 +256,22 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 {
 	struct v10_compute_mqd *m;
 
-	/* Control stack is located one page after MQD. */
-	void *mqd_ctl_stack = (void *)((uintptr_t)mqd + PAGE_SIZE);
-
 	m = get_mqd(mqd);
 
+	/* Control stack is written backwards, while workgroup context data
+	 * is written forwards. Both starts from m->cp_hqd_cntl_stack_size.
+	 * Current position is at m->cp_hqd_cntl_stack_offset and
+	 * m->cp_hqd_wg_state_offset, respectively.
+	 */
 	*ctl_stack_used_size = m->cp_hqd_cntl_stack_size -
 		m->cp_hqd_cntl_stack_offset;
 	*save_area_used_size = m->cp_hqd_wg_state_offset -
 		m->cp_hqd_cntl_stack_size;
 
-	if (copy_to_user(ctl_stack, mqd_ctl_stack, m->cp_hqd_cntl_stack_size))
-		return -EFAULT;
+	/* Control stack is not copied to user mode for GFXv10 because
+	 * it's part of the context save area that is already
+	 * accessible to user mode
+	 */
 
 	return 0;
 }
@@ -277,18 +290,6 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_PQ_CONTROL__KMD_QUEUE__SHIFT;
 }
 
-static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
-			struct queue_properties *q)
-{
-	struct v10_compute_mqd *m;
-
-	update_mqd(mm, mqd, q);
-
-	/* TODO: what's the point? update_mqd already does this. */
-	m = get_mqd(mqd);
-	m->cp_hqd_vmid = q->vmid;
-}
-
 static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -340,11 +341,7 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
 	m->sdma_queue_id = q->sdma_queue_id;
 	m->sdmax_rlcx_dummy_reg = SDMA_RLC_DUMMY_DEFAULT;
 
-
-	q->is_active = (q->queue_size > 0 &&
-			q->queue_address != 0 &&
-			q->queue_percent > 0 &&
-			!q->is_evicted);
+	q->is_active = QUEUE_IS_ACTIVE(*q);
 }
 
 /*
@@ -392,7 +389,7 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
@@ -400,7 +397,6 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		pr_debug("%s@%i\n", __func__, __LINE__);
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
@@ -421,8 +417,8 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_hiq_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->load_mqd = hiq_load_mqd_kiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
@@ -432,11 +428,11 @@ struct mqd_manager *mqd_manager_init_v10(enum KFD_MQD_TYPE type,
 		pr_debug("%s@%i\n", __func__, __LINE__);
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v10_compute_mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index d3380c5bdbde..436b7f518979 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -92,7 +92,7 @@ static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
 	 * instead of sub-allocation function.
 	 */
 	if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) {
-		mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
+		mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
 		if (!mqd_mem_obj)
 			return NULL;
 		retval = amdgpu_amdkfd_alloc_gtt_mem(kfd->kgd,
@@ -191,6 +191,14 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 					  wptr_shift, 0, mms);
 }
 
+static int hiq_load_mqd_kiq(struct mqd_manager *mm, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    struct queue_properties *p, struct mm_struct *mms)
+{
+	return mm->dev->kfd2kgd->hiq_mqd_load(mm->dev->kgd, mqd, pipe_id,
+					      queue_id, p->doorbell_off);
+}
+
 static void update_mqd(struct mqd_manager *mm, void *mqd,
 		      struct queue_properties *q)
 {
@@ -302,7 +310,8 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 
 	*ctl_stack_used_size = m->cp_hqd_cntl_stack_size -
 		m->cp_hqd_cntl_stack_offset;
-	*save_area_used_size = m->cp_hqd_wg_state_offset;
+	*save_area_used_size = m->cp_hqd_wg_state_offset -
+		m->cp_hqd_cntl_stack_size;
 
 	if (copy_to_user(ctl_stack, mqd_ctl_stack, m->cp_hqd_cntl_stack_size))
 		return -EFAULT;
@@ -324,18 +333,6 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_PQ_CONTROL__KMD_QUEUE__SHIFT;
 }
 
-static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
-			struct queue_properties *q)
-{
-	struct v9_mqd *m;
-
-	update_mqd(mm, mqd, q);
-
-	/* TODO: what's the point? update_mqd already does this. */
-	m = get_mqd(mqd);
-	m->cp_hqd_vmid = q->vmid;
-}
-
 static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj *mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -443,7 +440,6 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
 		mqd->free_mqd = free_mqd;
@@ -461,8 +457,8 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 		mqd->allocate_mqd = allocate_hiq_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd_hiq_sdma;
-		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->load_mqd = hiq_load_mqd_kiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v9_mqd);
@@ -471,11 +467,11 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 #endif
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
-		mqd->update_mqd = update_mqd_hiq;
+		mqd->update_mqd = update_mqd;
 		mqd->destroy_mqd = destroy_mqd;
 		mqd->is_occupied = is_occupied;
 		mqd->mqd_size = sizeof(struct v9_mqd);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 7d144f56f421..a5e8ff1e5945 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -312,11 +312,7 @@ static void init_mqd_hiq(struct mqd_manager *mm, void **mqd,
 static void update_mqd_hiq(struct mqd_manager *mm, void *mqd,
 			struct queue_properties *q)
 {
-	struct vi_mqd *m;
 	__update_mqd(mm, mqd, q, MTYPE_UC, 0);
-
-	m = get_mqd(mqd);
-	m->cp_hqd_vmid = q->vmid;
 }
 
 static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
@@ -425,7 +421,6 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 
 	switch (type) {
 	case KFD_MQD_TYPE_CP:
-	case KFD_MQD_TYPE_COMPUTE:
 		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd;
 		mqd->free_mqd = free_mqd;
@@ -453,7 +448,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 #endif
 		break;
 	case KFD_MQD_TYPE_DIQ:
-		mqd->allocate_mqd = allocate_hiq_mqd;
+		mqd->allocate_mqd = allocate_mqd;
 		mqd->init_mqd = init_mqd_hiq;
 		mqd->free_mqd = free_mqd;
 		mqd->load_mqd = load_mqd;
@@ -494,7 +489,7 @@ struct mqd_manager *mqd_manager_init_vi_tonga(enum KFD_MQD_TYPE type,
 	mqd = mqd_manager_init_vi(type, dev);
 	if (!mqd)
 		return NULL;
-	if ((type == KFD_MQD_TYPE_CP) || (type == KFD_MQD_TYPE_COMPUTE))
+	if (type == KFD_MQD_TYPE_CP)
 		mqd->update_mqd = update_mqd_tonga;
 	return mqd;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 83ef4b3dd2fb..dc406e6dee23 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -241,12 +241,10 @@ int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
 	case CHIP_ARCTURUS:
-		pm->pmf = &kfd_v9_pm_funcs;
-		break;
 	case CHIP_NAVI10:
 	case CHIP_NAVI12:
 	case CHIP_NAVI14:
-		pm->pmf = &kfd_v10_pm_funcs;
+		pm->pmf = &kfd_v9_pm_funcs;
 		break;
 	default:
 		WARN(1, "Unexpected ASIC family %u",
@@ -266,10 +264,10 @@ int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 	return 0;
 }
 
-void pm_uninit(struct packet_manager *pm)
+void pm_uninit(struct packet_manager *pm, bool hanging)
 {
 	mutex_destroy(&pm->lock);
-	kernel_queue_uninit(pm->priv_queue);
+	kernel_queue_uninit(pm->priv_queue, hanging);
 }
 
 int pm_send_set_resources(struct packet_manager *pm,
@@ -280,7 +278,7 @@ int pm_send_set_resources(struct packet_manager *pm,
 
 	size = pm->pmf->set_resources_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 					size / sizeof(uint32_t),
 					(unsigned int **)&buffer);
 	if (!buffer) {
@@ -291,9 +289,9 @@ int pm_send_set_resources(struct packet_manager *pm,
 
 	retval = pm->pmf->set_resources(pm, buffer, res);
 	if (!retval)
-		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+		kq_submit_packet(pm->priv_queue);
 	else
-		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+		kq_rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -318,7 +316,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 	packet_size_dwords = pm->pmf->runlist_size / sizeof(uint32_t);
 	mutex_lock(&pm->lock);
 
-	retval = pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	retval = kq_acquire_packet_buffer(pm->priv_queue,
 					packet_size_dwords, &rl_buffer);
 	if (retval)
 		goto fail_acquire_packet_buffer;
@@ -328,14 +326,14 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 	if (retval)
 		goto fail_create_runlist;
 
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	kq_submit_packet(pm->priv_queue);
 
 	mutex_unlock(&pm->lock);
 
 	return retval;
 
 fail_create_runlist:
-	pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+	kq_rollback_packet(pm->priv_queue);
 fail_acquire_packet_buffer:
 	mutex_unlock(&pm->lock);
 fail_create_runlist_ib:
@@ -354,7 +352,7 @@ int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 
 	size = pm->pmf->query_status_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 			size / sizeof(uint32_t), (unsigned int **)&buffer);
 	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
@@ -364,9 +362,9 @@ int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
 
 	retval = pm->pmf->query_status(pm, buffer, fence_address, fence_value);
 	if (!retval)
-		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+		kq_submit_packet(pm->priv_queue);
 	else
-		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+		kq_rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -383,7 +381,7 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 
 	size = pm->pmf->unmap_queues_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 			size / sizeof(uint32_t), (unsigned int **)&buffer);
 	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
@@ -394,9 +392,9 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 	retval = pm->pmf->unmap_queues(pm, buffer, type, filter, filter_param,
 				       reset, sdma_engine);
 	if (!retval)
-		pm->priv_queue->ops.submit_packet(pm->priv_queue);
+		kq_submit_packet(pm->priv_queue);
 	else
-		pm->priv_queue->ops.rollback_packet(pm->priv_queue);
+		kq_rollback_packet(pm->priv_queue);
 
 out:
 	mutex_unlock(&pm->lock);
@@ -441,7 +439,7 @@ int pm_debugfs_hang_hws(struct packet_manager *pm)
 
 	size = pm->pmf->query_status_size;
 	mutex_lock(&pm->lock);
-	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+	kq_acquire_packet_buffer(pm->priv_queue,
 			size / sizeof(uint32_t), (unsigned int **)&buffer);
 	if (!buffer) {
 		pr_err("Failed to allocate buffer on kernel queue\n");
@@ -449,7 +447,7 @@ int pm_debugfs_hang_hws(struct packet_manager *pm)
 		goto out;
 	}
 	memset(buffer, 0x55, size);
-	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+	kq_submit_packet(pm->priv_queue);
 
 	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
 		buffer[0], buffer[1], buffer[2], buffer[3],
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 9a4bafb2e175..2de01009f1b6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -25,47 +25,7 @@
 #include "kfd_device_queue_manager.h"
 #include "kfd_pm4_headers_ai.h"
 #include "kfd_pm4_opcodes.h"
-
-static bool initialize_v9(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_v9(struct kernel_queue *kq);
-static void submit_packet_v9(struct kernel_queue *kq);
-
-void kernel_queue_init_v9(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_v9;
-	ops->uninitialize = uninitialize_v9;
-	ops->submit_packet = submit_packet_v9;
-}
-
-static bool initialize_v9(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
-{
-	int retval;
-
-	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
-	if (retval)
-		return false;
-
-	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
-	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
-
-	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
-
-	return true;
-}
-
-static void uninitialize_v9(struct kernel_queue *kq)
-{
-	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
-}
-
-static void submit_packet_v9(struct kernel_queue *kq)
-{
-	*kq->wptr64_kernel = kq->pending_wptr64;
-	write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr64);
-}
+#include "gc/gc_10_1_0_sh_mask.h"
 
 static int pm_map_process_v9(struct packet_manager *pm,
 		uint32_t *buffer, struct qcm_process_device *qpd)
@@ -90,10 +50,17 @@ static int pm_map_process_v9(struct packet_manager *pm,
 
 	packet->sh_mem_config = qpd->sh_mem_config;
 	packet->sh_mem_bases = qpd->sh_mem_bases;
-	packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
-	packet->sq_shader_tba_hi = upper_32_bits(qpd->tba_addr >> 8);
-	packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
-	packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
+	if (qpd->tba_addr) {
+		packet->sq_shader_tba_lo = lower_32_bits(qpd->tba_addr >> 8);
+		/* On GFX9, unlike GFX10, bit TRAP_EN of SQ_SHADER_TBA_HI is
+		 * not defined, so setting it won't do any harm.
+		 */
+		packet->sq_shader_tba_hi = upper_32_bits(qpd->tba_addr >> 8)
+				| 1 << SQ_SHADER_TBA_HI__TRAP_EN__SHIFT;
+
+		packet->sq_shader_tma_lo = lower_32_bits(qpd->tma_addr >> 8);
+		packet->sq_shader_tma_hi = upper_32_bits(qpd->tma_addr >> 8);
+	}
 
 	packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
 	packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
@@ -341,35 +308,6 @@ static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
 	return 0;
 }
 
-
-static int pm_release_mem_v9(uint64_t gpu_addr, uint32_t *buffer)
-{
-	struct pm4_mec_release_mem *packet;
-
-	packet = (struct pm4_mec_release_mem *)buffer;
-	memset(buffer, 0, sizeof(struct pm4_mec_release_mem));
-
-	packet->header.u32All = pm_build_pm4_header(IT_RELEASE_MEM,
-					sizeof(struct pm4_mec_release_mem));
-
-	packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
-	packet->bitfields2.event_index = event_index__mec_release_mem__end_of_pipe;
-	packet->bitfields2.tcl1_action_ena = 1;
-	packet->bitfields2.tc_action_ena = 1;
-	packet->bitfields2.cache_policy = cache_policy__mec_release_mem__lru;
-
-	packet->bitfields3.data_sel = data_sel__mec_release_mem__send_32_bit_low;
-	packet->bitfields3.int_sel =
-		int_sel__mec_release_mem__send_interrupt_after_write_confirm;
-
-	packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
-	packet->address_hi = upper_32_bits(gpu_addr);
-
-	packet->data_lo = 0;
-
-	return 0;
-}
-
 const struct packet_manager_funcs kfd_v9_pm_funcs = {
 	.map_process		= pm_map_process_v9,
 	.runlist		= pm_runlist_v9,
@@ -377,12 +315,12 @@ const struct packet_manager_funcs kfd_v9_pm_funcs = {
 	.map_queues		= pm_map_queues_v9,
 	.unmap_queues		= pm_unmap_queues_v9,
 	.query_status		= pm_query_status_v9,
-	.release_mem		= pm_release_mem_v9,
+	.release_mem		= NULL,
 	.map_process_size	= sizeof(struct pm4_mes_map_process),
 	.runlist_size		= sizeof(struct pm4_mes_runlist),
 	.set_resources_size	= sizeof(struct pm4_mes_set_resources),
 	.map_queues_size	= sizeof(struct pm4_mes_map_queues),
 	.unmap_queues_size	= sizeof(struct pm4_mes_unmap_queues),
 	.query_status_size	= sizeof(struct pm4_mes_query_status),
-	.release_mem_size	= sizeof(struct pm4_mec_release_mem)
+	.release_mem_size	= 0,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
index 2adaf40027eb..bed4d0ccb6b1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c
@@ -26,47 +26,6 @@
 #include "kfd_pm4_headers_vi.h"
 #include "kfd_pm4_opcodes.h"
 
-static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_vi(struct kernel_queue *kq);
-static void submit_packet_vi(struct kernel_queue *kq);
-
-void kernel_queue_init_vi(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_vi;
-	ops->uninitialize = uninitialize_vi;
-	ops->submit_packet = submit_packet_vi;
-}
-
-static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
-{
-	int retval;
-
-	retval = kfd_gtt_sa_allocate(dev, PAGE_SIZE, &kq->eop_mem);
-	if (retval != 0)
-		return false;
-
-	kq->eop_gpu_addr = kq->eop_mem->gpu_addr;
-	kq->eop_kernel_addr = kq->eop_mem->cpu_ptr;
-
-	memset(kq->eop_kernel_addr, 0, PAGE_SIZE);
-
-	return true;
-}
-
-static void uninitialize_vi(struct kernel_queue *kq)
-{
-	kfd_gtt_sa_free(kq->dev, kq->eop_mem);
-}
-
-static void submit_packet_vi(struct kernel_queue *kq)
-{
-	*kq->wptr_kernel = kq->pending_wptr;
-	write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr);
-}
-
 unsigned int pm_build_pm4_header(unsigned int opcode, size_t packet_size)
 {
 	union PM4_MES_TYPE_3_HEADER header;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 060a9e8b301e..6af1b5881f43 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -59,24 +59,21 @@
  * NOTE: struct vm_area_struct.vm_pgoff uses offset in pages. Hence, these
  *  defines are w.r.t to PAGE_SIZE
  */
-#define KFD_MMAP_TYPE_SHIFT	(62 - PAGE_SHIFT)
+#define KFD_MMAP_TYPE_SHIFT	62
 #define KFD_MMAP_TYPE_MASK	(0x3ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_DOORBELL	(0x3ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_EVENTS	(0x2ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_RESERVED_MEM	(0x1ULL << KFD_MMAP_TYPE_SHIFT)
 #define KFD_MMAP_TYPE_MMIO	(0x0ULL << KFD_MMAP_TYPE_SHIFT)
 
-#define KFD_MMAP_GPU_ID_SHIFT (46 - PAGE_SHIFT)
+#define KFD_MMAP_GPU_ID_SHIFT 46
 #define KFD_MMAP_GPU_ID_MASK (((1ULL << KFD_GPU_ID_HASH_WIDTH) - 1) \
 				<< KFD_MMAP_GPU_ID_SHIFT)
 #define KFD_MMAP_GPU_ID(gpu_id) ((((uint64_t)gpu_id) << KFD_MMAP_GPU_ID_SHIFT)\
 				& KFD_MMAP_GPU_ID_MASK)
-#define KFD_MMAP_GPU_ID_GET(offset)    ((offset & KFD_MMAP_GPU_ID_MASK) \
+#define KFD_MMAP_GET_GPU_ID(offset)    ((offset & KFD_MMAP_GPU_ID_MASK) \
 				>> KFD_MMAP_GPU_ID_SHIFT)
 
-#define KFD_MMAP_OFFSET_VALUE_MASK	(0x3FFFFFFFFFFFULL >> PAGE_SHIFT)
-#define KFD_MMAP_OFFSET_VALUE_GET(offset) (offset & KFD_MMAP_OFFSET_VALUE_MASK)
-
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
  * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot
@@ -238,9 +235,10 @@ struct kfd_dev {
 					 * KFD. It is aligned for mapping
 					 * into user mode
 					 */
-	size_t doorbell_id_offset;	/* Doorbell offset (from KFD doorbell
-					 * to HW doorbell, GFX reserved some
-					 * at the start)
+	size_t doorbell_base_dw_offset;	/* Offset from the start of the PCI
+					 * doorbell BAR to the first KFD
+					 * doorbell in dwords. GFX reserves
+					 * the segment before this offset.
 					 */
 	u32 __iomem *doorbell_kernel_ptr; /* This is a pointer for a doorbells
 					   * page used by kernel queue
@@ -510,8 +508,7 @@ struct queue {
  * Please read the kfd_mqd_manager.h description.
  */
 enum KFD_MQD_TYPE {
-	KFD_MQD_TYPE_COMPUTE = 0,	/* for no cp scheduling */
-	KFD_MQD_TYPE_HIQ,		/* for hiq */
+	KFD_MQD_TYPE_HIQ = 0,		/* for hiq */
 	KFD_MQD_TYPE_CP,		/* for cp queues and diq */
 	KFD_MQD_TYPE_SDMA,		/* for sdma queues */
 	KFD_MQD_TYPE_DIQ,		/* for diq */
@@ -818,7 +815,7 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr);
 u32 read_kernel_doorbell(u32 __iomem *db);
 void write_kernel_doorbell(void __iomem *db, u32 value);
 void write_kernel_doorbell64(void __iomem *db, u64 value);
-unsigned int kfd_doorbell_id_to_offset(struct kfd_dev *kfd,
+unsigned int kfd_get_doorbell_dw_offset_in_bar(struct kfd_dev *kfd,
 					struct kfd_process *process,
 					unsigned int doorbell_id);
 phys_addr_t kfd_get_process_doorbells(struct kfd_dev *dev,
@@ -886,7 +883,7 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev);
 void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
-void kernel_queue_uninit(struct kernel_queue *kq);
+void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
 int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
 
 /* Process Queue Manager */
@@ -904,7 +901,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct kfd_dev *dev,
 			    struct file *f,
 			    struct queue_properties *properties,
-			    unsigned int *qid);
+			    unsigned int *qid,
+			    uint32_t *p_doorbell_offset_in_process);
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 			struct queue_properties *p);
@@ -972,10 +970,9 @@ struct packet_manager_funcs {
 
 extern const struct packet_manager_funcs kfd_vi_pm_funcs;
 extern const struct packet_manager_funcs kfd_v9_pm_funcs;
-extern const struct packet_manager_funcs kfd_v10_pm_funcs;
 
 int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm);
-void pm_uninit(struct packet_manager *pm);
+void pm_uninit(struct packet_manager *pm, bool hanging);
 int pm_send_set_resources(struct packet_manager *pm,
 				struct scheduling_resources *res);
 int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues);
@@ -991,9 +988,6 @@ void pm_release_ib(struct packet_manager *pm);
 
 /* Following PM funcs can be shared among VI and AI */
 unsigned int pm_build_pm4_header(unsigned int opcode, size_t packet_size);
-int pm_set_resources_vi(struct packet_manager *pm, uint32_t *buffer,
-			struct scheduling_resources *res);
-
 
 uint64_t kfd_get_number_elems(struct kfd_dev *kfd);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 10f9af5784f2..25b90f70aecd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -32,6 +32,7 @@
 #include <linux/mman.h>
 #include <linux/file.h>
 #include "amdgpu_amdkfd.h"
+#include "amdgpu.h"
 
 struct mm_struct;
 
@@ -324,6 +325,8 @@ struct kfd_process *kfd_create_process(struct file *filep)
 					(int)process->lead_thread->pid);
 	}
 out:
+	if (!IS_ERR(process))
+		kref_get(&process->ref);
 	mutex_unlock(&kfd_processes_mutex);
 
 	return process;
@@ -560,8 +563,7 @@ static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep)
 		if (!dev->cwsr_enabled || qpd->cwsr_kaddr || qpd->cwsr_base)
 			continue;
 
-		offset = (KFD_MMAP_TYPE_RESERVED_MEM | KFD_MMAP_GPU_ID(dev->id))
-			<< PAGE_SHIFT;
+		offset = KFD_MMAP_TYPE_RESERVED_MEM | KFD_MMAP_GPU_ID(dev->id);
 		qpd->tba_addr = (int64_t)vm_mmap(filep, 0,
 			KFD_CWSR_TBA_TMA_SIZE, PROT_READ | PROT_EXEC,
 			MAP_SHARED, offset);
@@ -1151,16 +1153,17 @@ int kfd_reserved_mem_mmap(struct kfd_dev *dev, struct kfd_process *process,
 void kfd_flush_tlb(struct kfd_process_device *pdd)
 {
 	struct kfd_dev *dev = pdd->dev;
-	const struct kfd2kgd_calls *f2g = dev->kfd2kgd;
 
 	if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS) {
 		/* Nothing to flush until a VMID is assigned, which
 		 * only happens when the first queue is created.
 		 */
 		if (pdd->qpd.vmid)
-			f2g->invalidate_tlbs_vmid(dev->kgd, pdd->qpd.vmid);
+			amdgpu_amdkfd_flush_gpu_tlb_vmid(dev->kgd,
+							pdd->qpd.vmid);
 	} else {
-		f2g->invalidate_tlbs(dev->kgd, pdd->process->pasid);
+		amdgpu_amdkfd_flush_gpu_tlb_pasid(dev->kgd,
+						pdd->process->pasid);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 2659d226c056..31fcd1b51f00 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -162,7 +162,7 @@ void pqm_uninit(struct process_queue_manager *pqm)
 	pqm->queue_slot_bitmap = NULL;
 }
 
-static int create_cp_queue(struct process_queue_manager *pqm,
+static int init_user_queue(struct process_queue_manager *pqm,
 				struct kfd_dev *dev, struct queue **q,
 				struct queue_properties *q_properties,
 				struct file *f, unsigned int qid)
@@ -192,7 +192,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			    struct kfd_dev *dev,
 			    struct file *f,
 			    struct queue_properties *properties,
-			    unsigned int *qid)
+			    unsigned int *qid,
+			    uint32_t *p_doorbell_offset_in_process)
 {
 	int retval;
 	struct kfd_process_device *pdd;
@@ -250,7 +251,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		}
 
-		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+		retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -271,7 +272,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 			goto err_create_queue;
 		}
 
-		retval = create_cp_queue(pqm, dev, &q, properties, f, *qid);
+		retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
 		if (retval != 0)
 			goto err_create_queue;
 		pqn->q = q;
@@ -303,12 +304,15 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		goto err_create_queue;
 	}
 
-	if (q)
+	if (q && p_doorbell_offset_in_process)
 		/* Return the doorbell offset within the doorbell page
 		 * to the caller so it can be passed up to user mode
 		 * (in bytes).
+		 * There are always 1024 doorbells per process, so in case
+		 * of 8-byte doorbells, there are two doorbell pages per
+		 * process.
 		 */
-		properties->doorbell_off =
+		*p_doorbell_offset_in_process =
 			(q->properties.doorbell_off * sizeof(uint32_t)) &
 			(kfd_doorbell_process_slice(dev) - 1);
 
@@ -370,7 +374,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 		/* destroy kernel queue (DIQ) */
 		dqm = pqn->kq->dev->dqm;
 		dqm->ops.destroy_kernel_queue(dqm, pqn->kq, &pdd->qpd);
-		kernel_queue_uninit(pqn->kq);
+		kernel_queue_uninit(pqn->kq, false);
 	}
 
 	if (pqn->q) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 69bd0628fdc6..203c823d65f1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -486,6 +486,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.num_sdma_engines);
 	sysfs_show_32bit_prop(buffer, "num_sdma_xgmi_engines",
 			dev->node_props.num_sdma_xgmi_engines);
+	sysfs_show_32bit_prop(buffer, "num_sdma_queues_per_engine",
+			dev->node_props.num_sdma_queues_per_engine);
+	sysfs_show_32bit_prop(buffer, "num_cp_queues",
+			dev->node_props.num_cp_queues);
 
 	if (dev->gpu) {
 		log_max_watch_addr =
@@ -1309,9 +1313,12 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	dev->node_props.num_sdma_engines = gpu->device_info->num_sdma_engines;
 	dev->node_props.num_sdma_xgmi_engines =
 				gpu->device_info->num_xgmi_sdma_engines;
+	dev->node_props.num_sdma_queues_per_engine =
+				gpu->device_info->num_sdma_queues_per_engine;
 	dev->node_props.num_gws = (hws_gws_support &&
 		dev->gpu->dqm->sched_policy != KFD_SCHED_POLICY_NO_HWS) ?
 		amdgpu_amdkfd_get_num_gws(dev->gpu->kgd) : 0;
+	dev->node_props.num_cp_queues = get_queues_num(dev->gpu->dqm);
 
 	kfd_fill_mem_clk_max_info(dev);
 	kfd_fill_iolink_non_crat_info(dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index 15843e0fc756..74e9b1682af8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -81,6 +81,8 @@ struct kfd_node_properties {
 	int32_t  drm_render_minor;
 	uint32_t num_sdma_engines;
 	uint32_t num_sdma_xgmi_engines;
+	uint32_t num_sdma_queues_per_engine;
+	uint32_t num_cp_queues;
 	char name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE];
 };
 
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index ae161fe86ebb..87858bc57e64 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,43 +6,16 @@ config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
 	select SND_HDA_COMPONENT if SND_HDA_CORE
-	select DRM_AMD_DC_DCN1_0 if X86 && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+	select DRM_AMD_DC_DCN if (X86 || PPC64) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_DCN1_0
+config DRM_AMD_DC_DCN
 	def_bool n
 	help
-	  RV family support for display engine
-
-config DRM_AMD_DC_DCN2_0
-	bool "DCN 2.0 family"
-	default y
-	depends on DRM_AMD_DC && X86
-	depends on DRM_AMD_DC_DCN1_0
-	help
-	  Choose this option if you want to have
-	  Navi support for display engine
-
-config DRM_AMD_DC_DCN2_1
-	bool "DCN 2.1 family"
-	depends on DRM_AMD_DC && X86
-	depends on DRM_AMD_DC_DCN2_0
-	help
-	  Choose this option if you want to have
-	  Renoir support for display engine
-
-config DRM_AMD_DC_DSC_SUPPORT
-	bool "DSC support"
-	default y
-	depends on DRM_AMD_DC && X86
-	depends on DRM_AMD_DC_DCN1_0
-	depends on DRM_AMD_DC_DCN2_0
-	help
-	  Choose this option if you want to have
-	  Dynamic Stream Compression support
+	  Raven, Navi and Renoir family support for display engine
 
 config DRM_AMD_DC_HDCP
 	bool "Enable HDCP support in DC"
diff --git a/drivers/gpu/drm/amd/display/Makefile b/drivers/gpu/drm/amd/display/Makefile
index 36b3d6a5d04d..2633de77de5e 100644
--- a/drivers/gpu/drm/amd/display/Makefile
+++ b/drivers/gpu/drm/amd/display/Makefile
@@ -34,6 +34,8 @@ subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/freesync
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/color
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/info_packet
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/power
+subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dmub/inc
+
 ifdef CONFIG_DRM_AMD_DC_HDCP
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/hdcp
 endif
@@ -41,7 +43,7 @@ endif
 #TODO: remove when Timing Sync feature is complete
 subdir-ccflags-y += -DBUILD_FEATURE_TIMING_SYNC=0
 
-DAL_LIBS = amdgpu_dm dc	modules/freesync modules/color modules/info_packet modules/power
+DAL_LIBS = amdgpu_dm dc	modules/freesync modules/color modules/info_packet modules/power dmub/src
 
 ifdef CONFIG_DRM_AMD_DC_HDCP
 DAL_LIBS += modules/hdcp
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 803e59d97411..9402374d2466 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -30,6 +30,10 @@
 #include "dc.h"
 #include "dc/inc/core_types.h"
 #include "dal_asic_id.h"
+#include "dmub/inc/dmub_srv.h"
+#include "dc/inc/hw/dmcu.h"
+#include "dc/inc/hw/abm.h"
+#include "dc/dc_dmub_srv.h"
 
 #include "vid.h"
 #include "amdgpu.h"
@@ -39,6 +43,7 @@
 #include "amdgpu_dm.h"
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 #include "amdgpu_dm_hdcp.h"
+#include <drm/drm_hdcp.h>
 #endif
 #include "amdgpu_pm.h"
 
@@ -72,7 +77,7 @@
 #include <drm/drm_audio_component.h>
 #include <drm/drm_hdcp.h>
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "ivsrcid/dcn/irqsrcs_dcn_1_0.h"
 
 #include "dcn/dcn_1_0_offset.h"
@@ -87,9 +92,18 @@
 #include "modules/power/power_helpers.h"
 #include "modules/inc/mod_info_packet.h"
 
+#define FIRMWARE_RENOIR_DMUB "amdgpu/renoir_dmcub.bin"
+MODULE_FIRMWARE(FIRMWARE_RENOIR_DMUB);
+
 #define FIRMWARE_RAVEN_DMCU		"amdgpu/raven_dmcu.bin"
 MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU);
 
+/* Number of bytes in PSP header for firmware. */
+#define PSP_HEADER_BYTES 0x100
+
+/* Number of bytes in PSP footer for firmware. */
+#define PSP_FOOTER_BYTES 0x100
+
 /**
  * DOC: overview
  *
@@ -478,6 +492,70 @@ static void dm_crtc_high_irq(void *interrupt_params)
 	}
 }
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+/**
+ * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs
+ * @interrupt params - interrupt parameters
+ *
+ * Notify DRM's vblank event handler at VSTARTUP
+ *
+ * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which:
+ * * We are close enough to VUPDATE - the point of no return for hw
+ * * We are in the fixed portion of variable front porch when vrr is enabled
+ * * We are before VUPDATE, where double-buffered vrr registers are swapped
+ *
+ * It is therefore the correct place to signal vblank, send user flip events,
+ * and update VRR.
+ */
+static void dm_dcn_crtc_high_irq(void *interrupt_params)
+{
+	struct common_irq_params *irq_params = interrupt_params;
+	struct amdgpu_device *adev = irq_params->adev;
+	struct amdgpu_crtc *acrtc;
+	struct dm_crtc_state *acrtc_state;
+	unsigned long flags;
+
+	acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK);
+
+	if (!acrtc)
+		return;
+
+	acrtc_state = to_dm_crtc_state(acrtc->base.state);
+
+	DRM_DEBUG_DRIVER("crtc:%d, vupdate-vrr:%d\n", acrtc->crtc_id,
+				amdgpu_dm_vrr_active(acrtc_state));
+
+	amdgpu_dm_crtc_handle_crc_irq(&acrtc->base);
+	drm_crtc_handle_vblank(&acrtc->base);
+
+	spin_lock_irqsave(&adev->ddev->event_lock, flags);
+
+	if (acrtc_state->vrr_params.supported &&
+	    acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) {
+		mod_freesync_handle_v_update(
+		adev->dm.freesync_module,
+		acrtc_state->stream,
+		&acrtc_state->vrr_params);
+
+		dc_stream_adjust_vmin_vmax(
+			adev->dm.dc,
+			acrtc_state->stream,
+			&acrtc_state->vrr_params.adjust);
+	}
+
+	if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED) {
+		if (acrtc->event) {
+			drm_crtc_send_vblank_event(&acrtc->base, acrtc->event);
+			acrtc->event = NULL;
+			drm_crtc_vblank_put(&acrtc->base);
+		}
+		acrtc->pflip_status = AMDGPU_FLIP_NONE;
+	}
+
+	spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
+}
+#endif
+
 static int dm_set_clockgating_state(void *handle,
 		  enum amd_clockgating_state state)
 {
@@ -667,12 +745,126 @@ void amdgpu_dm_audio_eld_notify(struct amdgpu_device *adev, int pin)
 	}
 }
 
+static int dm_dmub_hw_init(struct amdgpu_device *adev)
+{
+	const struct dmcub_firmware_header_v1_0 *hdr;
+	struct dmub_srv *dmub_srv = adev->dm.dmub_srv;
+	struct dmub_srv_fb_info *fb_info = adev->dm.dmub_fb_info;
+	const struct firmware *dmub_fw = adev->dm.dmub_fw;
+	struct dmcu *dmcu = adev->dm.dc->res_pool->dmcu;
+	struct abm *abm = adev->dm.dc->res_pool->abm;
+	struct dmub_srv_hw_params hw_params;
+	enum dmub_status status;
+	const unsigned char *fw_inst_const, *fw_bss_data;
+	uint32_t i, fw_inst_const_size, fw_bss_data_size;
+	bool has_hw_support;
+
+	if (!dmub_srv)
+		/* DMUB isn't supported on the ASIC. */
+		return 0;
+
+	if (!fb_info) {
+		DRM_ERROR("No framebuffer info for DMUB service.\n");
+		return -EINVAL;
+	}
+
+	if (!dmub_fw) {
+		/* Firmware required for DMUB support. */
+		DRM_ERROR("No firmware provided for DMUB.\n");
+		return -EINVAL;
+	}
+
+	status = dmub_srv_has_hw_support(dmub_srv, &has_hw_support);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error checking HW support for DMUB: %d\n", status);
+		return -EINVAL;
+	}
+
+	if (!has_hw_support) {
+		DRM_INFO("DMUB unsupported on ASIC\n");
+		return 0;
+	}
+
+	hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data;
+
+	fw_inst_const = dmub_fw->data +
+			le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
+			PSP_HEADER_BYTES;
+
+	fw_bss_data = dmub_fw->data +
+		      le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
+		      le32_to_cpu(hdr->inst_const_bytes);
+
+	/* Copy firmware and bios info into FB memory. */
+	fw_inst_const_size = le32_to_cpu(hdr->inst_const_bytes) -
+			     PSP_HEADER_BYTES - PSP_FOOTER_BYTES;
+
+	fw_bss_data_size = le32_to_cpu(hdr->bss_data_bytes);
+
+	memcpy(fb_info->fb[DMUB_WINDOW_0_INST_CONST].cpu_addr, fw_inst_const,
+	       fw_inst_const_size);
+	memcpy(fb_info->fb[DMUB_WINDOW_2_BSS_DATA].cpu_addr, fw_bss_data,
+	       fw_bss_data_size);
+	memcpy(fb_info->fb[DMUB_WINDOW_3_VBIOS].cpu_addr, adev->bios,
+	       adev->bios_size);
+
+	/* Reset regions that need to be reset. */
+	memset(fb_info->fb[DMUB_WINDOW_4_MAILBOX].cpu_addr, 0,
+	fb_info->fb[DMUB_WINDOW_4_MAILBOX].size);
+
+	memset(fb_info->fb[DMUB_WINDOW_5_TRACEBUFF].cpu_addr, 0,
+	       fb_info->fb[DMUB_WINDOW_5_TRACEBUFF].size);
+
+	memset(fb_info->fb[DMUB_WINDOW_6_FW_STATE].cpu_addr, 0,
+	       fb_info->fb[DMUB_WINDOW_6_FW_STATE].size);
+
+	/* Initialize hardware. */
+	memset(&hw_params, 0, sizeof(hw_params));
+	hw_params.fb_base = adev->gmc.fb_start;
+	hw_params.fb_offset = adev->gmc.aper_base;
+
+	if (dmcu)
+		hw_params.psp_version = dmcu->psp_version;
+
+	for (i = 0; i < fb_info->num_fb; ++i)
+		hw_params.fb[i] = &fb_info->fb[i];
+
+	status = dmub_srv_hw_init(dmub_srv, &hw_params);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error initializing DMUB HW: %d\n", status);
+		return -EINVAL;
+	}
+
+	/* Wait for firmware load to finish. */
+	status = dmub_srv_wait_for_auto_load(dmub_srv, 100000);
+	if (status != DMUB_STATUS_OK)
+		DRM_WARN("Wait for DMUB auto-load failed: %d\n", status);
+
+	/* Init DMCU and ABM if available. */
+	if (dmcu && abm) {
+		dmcu->funcs->dmcu_init(dmcu);
+		abm->dmcu_is_running = dmcu->funcs->is_dmcu_initialized(dmcu);
+	}
+
+	adev->dm.dc->ctx->dmub_srv = dc_dmub_srv_create(adev->dm.dc, dmub_srv);
+	if (!adev->dm.dc->ctx->dmub_srv) {
+		DRM_ERROR("Couldn't allocate DC DMUB server!\n");
+		return -ENOMEM;
+	}
+
+	DRM_INFO("DMUB hardware initialized: version=0x%08X\n",
+		 adev->dm.dmcub_fw_version);
+
+	return 0;
+}
+
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	struct dc_callback_init init_params;
 #endif
+	int r;
 
 	adev->dm.ddev = adev->ddev;
 	adev->dm.adev = adev;
@@ -714,13 +906,16 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.dce_environment = DCE_ENV_PRODUCTION_DRV;
 
-	/*
-	 * TODO debug why this doesn't work on Raven
-	 */
-	if (adev->flags & AMD_IS_APU &&
-	    adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type < CHIP_RAVEN)
+	switch (adev->asic_type) {
+	case CHIP_CARRIZO:
+	case CHIP_STONEY:
+	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 		init_data.flags.gpu_vm_support = true;
+		break;
+	default:
+		break;
+	}
 
 	if (amdgpu_dc_feature_mask & DC_FBC_MASK)
 		init_data.flags.fbc_support = true;
@@ -733,9 +928,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.flags.power_down_display_on_boot = true;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	init_data.soc_bounding_box = adev->dm.soc_bounding_box;
-#endif
 
 	/* Display Core create. */
 	adev->dm.dc = dc_create(&init_data);
@@ -749,6 +942,12 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	dc_hardware_init(adev->dm.dc);
 
+	r = dm_dmub_hw_init(adev);
+	if (r) {
+		DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
+		goto error;
+	}
+
 	adev->dm.freesync_module = mod_freesync_create(adev->dm.dc);
 	if (!adev->dm.freesync_module) {
 		DRM_ERROR(
@@ -821,6 +1020,15 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 	if (adev->dm.dc)
 		dc_deinit_callbacks(adev->dm.dc);
 #endif
+	if (adev->dm.dc->ctx->dmub_srv) {
+		dc_dmub_srv_destroy(&adev->dm.dc->ctx->dmub_srv);
+		adev->dm.dc->ctx->dmub_srv = NULL;
+	}
+
+	if (adev->dm.dmub_bo)
+		amdgpu_bo_free_kernel(&adev->dm.dmub_bo,
+				      &adev->dm.dmub_bo_gpu_addr,
+				      &adev->dm.dmub_bo_cpu_addr);
 
 	/* DC Destroy TODO: Replace destroy DAL */
 	if (adev->dm.dc)
@@ -932,9 +1140,160 @@ static int load_dmcu_fw(struct amdgpu_device *adev)
 	return 0;
 }
 
+static uint32_t amdgpu_dm_dmub_reg_read(void *ctx, uint32_t address)
+{
+	struct amdgpu_device *adev = ctx;
+
+	return dm_read_reg(adev->dm.dc->ctx, address);
+}
+
+static void amdgpu_dm_dmub_reg_write(void *ctx, uint32_t address,
+				     uint32_t value)
+{
+	struct amdgpu_device *adev = ctx;
+
+	return dm_write_reg(adev->dm.dc->ctx, address, value);
+}
+
+static int dm_dmub_sw_init(struct amdgpu_device *adev)
+{
+	struct dmub_srv_create_params create_params;
+	struct dmub_srv_region_params region_params;
+	struct dmub_srv_region_info region_info;
+	struct dmub_srv_fb_params fb_params;
+	struct dmub_srv_fb_info *fb_info;
+	struct dmub_srv *dmub_srv;
+	const struct dmcub_firmware_header_v1_0 *hdr;
+	const char *fw_name_dmub;
+	enum dmub_asic dmub_asic;
+	enum dmub_status status;
+	int r;
+
+	switch (adev->asic_type) {
+	case CHIP_RENOIR:
+		dmub_asic = DMUB_ASIC_DCN21;
+		fw_name_dmub = FIRMWARE_RENOIR_DMUB;
+		break;
+
+	default:
+		/* ASIC doesn't support DMUB. */
+		return 0;
+	}
+
+	r = request_firmware_direct(&adev->dm.dmub_fw, fw_name_dmub, adev->dev);
+	if (r) {
+		DRM_ERROR("DMUB firmware loading failed: %d\n", r);
+		return 0;
+	}
+
+	r = amdgpu_ucode_validate(adev->dm.dmub_fw);
+	if (r) {
+		DRM_ERROR("Couldn't validate DMUB firmware: %d\n", r);
+		return 0;
+	}
+
+	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+		DRM_WARN("Only PSP firmware loading is supported for DMUB\n");
+		return 0;
+	}
+
+	hdr = (const struct dmcub_firmware_header_v1_0 *)adev->dm.dmub_fw->data;
+	adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].ucode_id =
+		AMDGPU_UCODE_ID_DMCUB;
+	adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].fw = adev->dm.dmub_fw;
+	adev->firmware.fw_size +=
+		ALIGN(le32_to_cpu(hdr->inst_const_bytes), PAGE_SIZE);
+
+	adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version);
+
+	DRM_INFO("Loading DMUB firmware via PSP: version=0x%08X\n",
+		 adev->dm.dmcub_fw_version);
+
+	adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL);
+	dmub_srv = adev->dm.dmub_srv;
+
+	if (!dmub_srv) {
+		DRM_ERROR("Failed to allocate DMUB service!\n");
+		return -ENOMEM;
+	}
+
+	memset(&create_params, 0, sizeof(create_params));
+	create_params.user_ctx = adev;
+	create_params.funcs.reg_read = amdgpu_dm_dmub_reg_read;
+	create_params.funcs.reg_write = amdgpu_dm_dmub_reg_write;
+	create_params.asic = dmub_asic;
+
+	/* Create the DMUB service. */
+	status = dmub_srv_create(dmub_srv, &create_params);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error creating DMUB service: %d\n", status);
+		return -EINVAL;
+	}
+
+	/* Calculate the size of all the regions for the DMUB service. */
+	memset(&region_params, 0, sizeof(region_params));
+
+	region_params.inst_const_size = le32_to_cpu(hdr->inst_const_bytes) -
+					PSP_HEADER_BYTES - PSP_FOOTER_BYTES;
+	region_params.bss_data_size = le32_to_cpu(hdr->bss_data_bytes);
+	region_params.vbios_size = adev->bios_size;
+	region_params.fw_bss_data =
+		adev->dm.dmub_fw->data +
+		le32_to_cpu(hdr->header.ucode_array_offset_bytes) +
+		le32_to_cpu(hdr->inst_const_bytes);
+
+	status = dmub_srv_calc_region_info(dmub_srv, &region_params,
+					   &region_info);
+
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error calculating DMUB region info: %d\n", status);
+		return -EINVAL;
+	}
+
+	/*
+	 * Allocate a framebuffer based on the total size of all the regions.
+	 * TODO: Move this into GART.
+	 */
+	r = amdgpu_bo_create_kernel(adev, region_info.fb_size, PAGE_SIZE,
+				    AMDGPU_GEM_DOMAIN_VRAM, &adev->dm.dmub_bo,
+				    &adev->dm.dmub_bo_gpu_addr,
+				    &adev->dm.dmub_bo_cpu_addr);
+	if (r)
+		return r;
+
+	/* Rebase the regions on the framebuffer address. */
+	memset(&fb_params, 0, sizeof(fb_params));
+	fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr;
+	fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr;
+	fb_params.region_info = &region_info;
+
+	adev->dm.dmub_fb_info =
+		kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL);
+	fb_info = adev->dm.dmub_fb_info;
+
+	if (!fb_info) {
+		DRM_ERROR(
+			"Failed to allocate framebuffer info for DMUB service!\n");
+		return -ENOMEM;
+	}
+
+	status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info);
+	if (status != DMUB_STATUS_OK) {
+		DRM_ERROR("Error calculating DMUB FB info: %d\n", status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dm_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r;
+
+	r = dm_dmub_sw_init(adev);
+	if (r)
+		return r;
 
 	return load_dmcu_fw(adev);
 }
@@ -943,6 +1302,19 @@ static int dm_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	kfree(adev->dm.dmub_fb_info);
+	adev->dm.dmub_fb_info = NULL;
+
+	if (adev->dm.dmub_srv) {
+		dmub_srv_destroy(adev->dm.dmub_srv);
+		adev->dm.dmub_srv = NULL;
+	}
+
+	if (adev->dm.dmub_fw) {
+		release_firmware(adev->dm.dmub_fw);
+		adev->dm.dmub_fw = NULL;
+	}
+
 	if(adev->dm.fw_dmcu) {
 		release_firmware(adev->dm.fw_dmcu);
 		adev->dm.fw_dmcu = NULL;
@@ -1235,7 +1607,7 @@ static int dm_resume(void *handle)
 	struct dm_plane_state *dm_new_plane_state;
 	struct dm_atomic_state *dm_state = to_dm_atomic_state(dm->atomic_obj.state);
 	enum dc_connection_type new_connection_type = dc_connection_none;
-	int i;
+	int i, r;
 
 	/* Recreate dc_state - DC invalidates it when setting power state to S3. */
 	dc_release_state(dm_state->context);
@@ -1243,6 +1615,11 @@ static int dm_resume(void *handle)
 	/* TODO: Remove dc_state->dccg, use dc->dccg directly. */
 	dc_resource_state_construct(dm->dc, dm_state->context);
 
+	/* Before powering on DC we need to re-initialize DMUB. */
+	r = dm_dmub_hw_init(adev);
+	if (r)
+		DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
+
 	/* power on hardware */
 	dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D0);
 
@@ -1868,7 +2245,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 	return 0;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 /* Register IRQ sources and initialize IRQ callbacks */
 static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 {
@@ -1914,35 +2291,7 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 		c_irq_params->irq_src = int_params.irq_source;
 
 		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_crtc_high_irq, c_irq_params);
-	}
-
-	/* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to
-	 * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx
-	 * to trigger at end of each vblank, regardless of state of the lock,
-	 * matching DCE behaviour.
-	 */
-	for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT;
-	     i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1;
-	     i++) {
-		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq);
-
-		if (r) {
-			DRM_ERROR("Failed to add vupdate irq id!\n");
-			return r;
-		}
-
-		int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT;
-		int_params.irq_source =
-			dc_interrupt_to_irq_source(dc, i, 0);
-
-		c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1];
-
-		c_irq_params->adev = adev;
-		c_irq_params->irq_src = int_params.irq_source;
-
-		amdgpu_dm_irq_register_interrupt(adev, &int_params,
-				dm_vupdate_high_irq, c_irq_params);
+				dm_dcn_crtc_high_irq, c_irq_params);
 	}
 
 	/* Use GRPH_PFLIP interrupt */
@@ -2457,16 +2806,12 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case CHIP_RAVEN:
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case CHIP_NAVI12:
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case CHIP_RENOIR:
-#endif
 		if (dcn10_register_irq_handlers(dm->adev)) {
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
 			goto fail;
@@ -2612,14 +2957,13 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_hpd = 6;
 		adev->mode_info.num_dig = 6;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case CHIP_RAVEN:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
 		adev->mode_info.num_dig = 4;
 		break;
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case CHIP_NAVI10:
 	case CHIP_NAVI12:
 		adev->mode_info.num_crtc = 6;
@@ -2631,14 +2975,11 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_hpd = 5;
 		adev->mode_info.num_dig = 5;
 		break;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case CHIP_RENOIR:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
 		adev->mode_info.num_dig = 4;
 		break;
-#endif
 	default:
 		DRM_ERROR("Unsupported ASIC type: 0x%X\n", adev->asic_type);
 		return -EINVAL;
@@ -2931,14 +3272,10 @@ fill_plane_buffer_attributes(struct amdgpu_device *adev,
 	if (adev->asic_type == CHIP_VEGA10 ||
 	    adev->asic_type == CHIP_VEGA12 ||
 	    adev->asic_type == CHIP_VEGA20 ||
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	    adev->asic_type == CHIP_NAVI10 ||
 	    adev->asic_type == CHIP_NAVI14 ||
 	    adev->asic_type == CHIP_NAVI12 ||
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	    adev->asic_type == CHIP_RENOIR ||
-#endif
 	    adev->asic_type == CHIP_RAVEN) {
 		/* Fill GFX9 params */
 		tiling_info->gfx9.num_pipes =
@@ -3256,12 +3593,26 @@ static void update_stream_scaling_settings(const struct drm_display_mode *mode,
 
 static enum dc_color_depth
 convert_color_depth_from_display_info(const struct drm_connector *connector,
-				      const struct drm_connector_state *state)
+				      const struct drm_connector_state *state,
+				      bool is_y420)
 {
-	uint8_t bpc = (uint8_t)connector->display_info.bpc;
+	uint8_t bpc;
 
-	/* Assume 8 bpc by default if no bpc is specified. */
-	bpc = bpc ? bpc : 8;
+	if (is_y420) {
+		bpc = 8;
+
+		/* Cap display bpc based on HDMI 2.0 HF-VSDB */
+		if (connector->display_info.hdmi.y420_dc_modes & DRM_EDID_YCBCR420_DC_48)
+			bpc = 16;
+		else if (connector->display_info.hdmi.y420_dc_modes & DRM_EDID_YCBCR420_DC_36)
+			bpc = 12;
+		else if (connector->display_info.hdmi.y420_dc_modes & DRM_EDID_YCBCR420_DC_30)
+			bpc = 10;
+	} else {
+		bpc = (uint8_t)connector->display_info.bpc;
+		/* Assume 8 bpc by default if no bpc is specified. */
+		bpc = bpc ? bpc : 8;
+	}
 
 	if (!state)
 		state = connector->state;
@@ -3427,7 +3778,8 @@ static void fill_stream_properties_from_drm_display_mode(
 
 	timing_out->timing_3d_format = TIMING_3D_FORMAT_NONE;
 	timing_out->display_color_depth = convert_color_depth_from_display_info(
-		connector, connector_state);
+		connector, connector_state,
+		(timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420));
 	timing_out->scan_type = SCANNING_TYPE_NODATA;
 	timing_out->hdmi_vic = 0;
 
@@ -3645,10 +3997,10 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 	bool scale = dm_state ? (dm_state->scaling != RMX_OFF) : false;
 	int mode_refresh;
 	int preferred_refresh = 0;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	struct dsc_dec_dpcd_caps dsc_caps;
-	uint32_t link_bandwidth_kbps;
 #endif
+	uint32_t link_bandwidth_kbps;
 
 	struct dc_sink *sink = NULL;
 	if (aconnector == NULL) {
@@ -3723,16 +4075,19 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		fill_stream_properties_from_drm_display_mode(stream,
 			&mode, &aconnector->base, con_state, old_stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	stream->timing.flags.DSC = 0;
 
 	if (aconnector->dc_link && sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT) {
-		dc_dsc_parse_dsc_dpcd(aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.raw,
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		dc_dsc_parse_dsc_dpcd(aconnector->dc_link->ctx->dc,
+				      aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.raw,
 				      aconnector->dc_link->dpcd_caps.dsc_caps.dsc_ext_caps.raw,
 				      &dsc_caps);
+#endif
 		link_bandwidth_kbps = dc_link_bandwidth_kbps(aconnector->dc_link,
 							     dc_link_get_link_cap(aconnector->dc_link));
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (dsc_caps.is_dsc_supported)
 			if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc->res_pool->dscs[0],
 						  &dsc_caps,
@@ -3741,8 +4096,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 						  &stream->timing,
 						  &stream->timing.dsc_cfg))
 				stream->timing.flags.DSC = 1;
-	}
 #endif
+	}
 
 	update_stream_scaling_settings(&mode, dm_state, stream);
 
@@ -3762,7 +4117,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 			struct dmcu *dmcu = core_dc->res_pool->dmcu;
 
 			stream->psr_version = dmcu->dmcu_version.psr_version;
-			mod_build_vsc_infopacket(stream, &stream->vsc_infopacket);
+			mod_build_vsc_infopacket(stream,
+					&stream->vsc_infopacket,
+					&stream->use_vsc_sdp_for_colorimetry);
 		}
 	}
 finish:
@@ -3853,6 +4210,10 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int rc;
 
+	/* Do not set vupdate for DCN hardware */
+	if (adev->family > AMDGPU_FAMILY_AI)
+		return 0;
+
 	irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst;
 
 	rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY;
@@ -4096,7 +4457,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector)
 		state->underscan_hborder = 0;
 		state->underscan_vborder = 0;
 		state->base.max_requested_bpc = 8;
-
+		state->vcpi_slots = 0;
+		state->pbn = 0;
 		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
 			state->abm_level = amdgpu_dm_abm_level;
 
@@ -4124,7 +4486,8 @@ amdgpu_dm_connector_atomic_duplicate_state(struct drm_connector *connector)
 	new_state->underscan_enable = state->underscan_enable;
 	new_state->underscan_hborder = state->underscan_hborder;
 	new_state->underscan_vborder = state->underscan_vborder;
-
+	new_state->vcpi_slots = state->vcpi_slots;
+	new_state->pbn = state->pbn;
 	return &new_state->base;
 }
 
@@ -4521,10 +4884,69 @@ static void dm_encoder_helper_disable(struct drm_encoder *encoder)
 
 }
 
+static int convert_dc_color_depth_into_bpc (enum dc_color_depth display_color_depth)
+{
+	switch (display_color_depth) {
+		case COLOR_DEPTH_666:
+			return 6;
+		case COLOR_DEPTH_888:
+			return 8;
+		case COLOR_DEPTH_101010:
+			return 10;
+		case COLOR_DEPTH_121212:
+			return 12;
+		case COLOR_DEPTH_141414:
+			return 14;
+		case COLOR_DEPTH_161616:
+			return 16;
+		default:
+			break;
+		}
+	return 0;
+}
+
 static int dm_encoder_helper_atomic_check(struct drm_encoder *encoder,
 					  struct drm_crtc_state *crtc_state,
 					  struct drm_connector_state *conn_state)
 {
+	struct drm_atomic_state *state = crtc_state->state;
+	struct drm_connector *connector = conn_state->connector;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct dm_connector_state *dm_new_connector_state = to_dm_connector_state(conn_state);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->adjusted_mode;
+	struct drm_dp_mst_topology_mgr *mst_mgr;
+	struct drm_dp_mst_port *mst_port;
+	enum dc_color_depth color_depth;
+	int clock, bpp = 0;
+	bool is_y420 = false;
+
+	if (!aconnector->port || !aconnector->dc_sink)
+		return 0;
+
+	mst_port = aconnector->port;
+	mst_mgr = &aconnector->mst_port->mst_mgr;
+
+	if (!crtc_state->connectors_changed && !crtc_state->mode_changed)
+		return 0;
+
+	if (!state->duplicated) {
+		is_y420 = drm_mode_is_420_also(&connector->display_info, adjusted_mode) &&
+				aconnector->force_yuv420_output;
+		color_depth = convert_color_depth_from_display_info(connector, conn_state,
+								    is_y420);
+		bpp = convert_dc_color_depth_into_bpc(color_depth) * 3;
+		clock = adjusted_mode->clock;
+		dm_new_connector_state->pbn = drm_dp_calc_pbn_mode(clock, bpp, false);
+	}
+	dm_new_connector_state->vcpi_slots = drm_dp_atomic_find_vcpi_slots(state,
+									   mst_mgr,
+									   mst_port,
+									   dm_new_connector_state->pbn,
+									   0);
+	if (dm_new_connector_state->vcpi_slots < 0) {
+		DRM_DEBUG_ATOMIC("failed finding vcpi slots: %d\n", (int)dm_new_connector_state->vcpi_slots);
+		return dm_new_connector_state->vcpi_slots;
+	}
 	return 0;
 }
 
@@ -4533,6 +4955,71 @@ const struct drm_encoder_helper_funcs amdgpu_dm_encoder_helper_funcs = {
 	.atomic_check = dm_encoder_helper_atomic_check
 };
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
+					    struct dc_state *dc_state)
+{
+	struct dc_stream_state *stream = NULL;
+	struct drm_connector *connector;
+	struct drm_connector_state *new_con_state, *old_con_state;
+	struct amdgpu_dm_connector *aconnector;
+	struct dm_connector_state *dm_conn_state;
+	int i, j, clock, bpp;
+	int vcpi, pbn_div, pbn = 0;
+
+	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
+
+		aconnector = to_amdgpu_dm_connector(connector);
+
+		if (!aconnector->port)
+			continue;
+
+		if (!new_con_state || !new_con_state->crtc)
+			continue;
+
+		dm_conn_state = to_dm_connector_state(new_con_state);
+
+		for (j = 0; j < dc_state->stream_count; j++) {
+			stream = dc_state->streams[j];
+			if (!stream)
+				continue;
+
+			if ((struct amdgpu_dm_connector*)stream->dm_stream_context == aconnector)
+				break;
+
+			stream = NULL;
+		}
+
+		if (!stream)
+			continue;
+
+		if (stream->timing.flags.DSC != 1) {
+			drm_dp_mst_atomic_enable_dsc(state,
+						     aconnector->port,
+						     dm_conn_state->pbn,
+						     0,
+						     false);
+			continue;
+		}
+
+		pbn_div = dm_mst_get_pbn_divider(stream->link);
+		bpp = stream->timing.dsc_cfg.bits_per_pixel;
+		clock = stream->timing.pix_clk_100hz / 10;
+		pbn = drm_dp_calc_pbn_mode(clock, bpp, true);
+		vcpi = drm_dp_mst_atomic_enable_dsc(state,
+						    aconnector->port,
+						    pbn, pbn_div,
+						    true);
+		if (vcpi < 0)
+			return vcpi;
+
+		dm_conn_state->pbn = pbn;
+		dm_conn_state->vcpi_slots = vcpi;
+	}
+	return 0;
+}
+#endif
+
 static void dm_drm_plane_reset(struct drm_plane *plane)
 {
 	struct dm_plane_state *amdgpu_state = NULL;
@@ -5195,9 +5682,9 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 
 	drm_connector_attach_max_bpc_property(&aconnector->base, 8, 16);
 
-	/* This defaults to the max in the range, but we want 8bpc. */
-	aconnector->base.state->max_bpc = 8;
-	aconnector->base.state->max_requested_bpc = 8;
+	/* This defaults to the max in the range, but we want 8bpc for non-edp. */
+	aconnector->base.state->max_bpc = (connector_type == DRM_MODE_CONNECTOR_eDP) ? 16 : 8;
+	aconnector->base.state->max_requested_bpc = aconnector->base.state->max_bpc;
 
 	if (connector_type == DRM_MODE_CONNECTOR_eDP &&
 	    dc_is_dmcu_initialized(adev->dm.dc)) {
@@ -5216,7 +5703,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 			&aconnector->base);
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 		if (adev->asic_type >= CHIP_RAVEN)
-			drm_connector_attach_content_protection_property(&aconnector->base, false);
+			drm_connector_attach_content_protection_property(&aconnector->base, true);
 #endif
 	}
 }
@@ -5325,11 +5812,12 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 
 	connector_type = to_drm_connector_type(link->connector_signal);
 
-	res = drm_connector_init(
+	res = drm_connector_init_with_ddc(
 			dm->ddev,
 			&aconnector->base,
 			&amdgpu_dm_connector_funcs,
-			connector_type);
+			connector_type,
+			&i2c->base);
 
 	if (res) {
 		DRM_ERROR("connector_init failed\n");
@@ -5467,6 +5955,12 @@ static bool is_content_protection_different(struct drm_connector_state *state,
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
+	if (old_state->hdcp_content_type != state->hdcp_content_type &&
+	    state->content_protection != DRM_MODE_CONTENT_PROTECTION_UNDESIRED) {
+		state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+		return true;
+	}
+
 	/* CP is being re enabled, ignore this */
 	if (old_state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED &&
 	    state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) {
@@ -5495,17 +5989,6 @@ static bool is_content_protection_different(struct drm_connector_state *state,
 	return false;
 }
 
-static void update_content_protection(struct drm_connector_state *state, const struct drm_connector *connector,
-				      struct hdcp_workqueue *hdcp_w)
-{
-	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-
-	if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED)
-		hdcp_add_display(hdcp_w, aconnector->dc_link->link_index, aconnector);
-	else if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED)
-		hdcp_remove_display(hdcp_w, aconnector->dc_link->link_index, aconnector->base.index);
-
-}
 #endif
 static void remove_stream(struct amdgpu_device *adev,
 			  struct amdgpu_crtc *acrtc,
@@ -6475,7 +6958,11 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		}
 
 		if (is_content_protection_different(new_con_state, old_con_state, connector, adev->dm.hdcp_workqueue))
-			update_content_protection(new_con_state, connector, adev->dm.hdcp_workqueue);
+			hdcp_update_display(
+				adev->dm.hdcp_workqueue, aconnector->dc_link->link_index, aconnector,
+				new_con_state->hdcp_content_type,
+				new_con_state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED ? true
+													 : false);
 	}
 #endif
 
@@ -7265,7 +7752,7 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 	int i, j, num_plane, ret = 0;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
 	struct dm_plane_state *new_dm_plane_state, *old_dm_plane_state;
-	struct drm_crtc *new_plane_crtc, *old_plane_crtc;
+	struct drm_crtc *new_plane_crtc;
 	struct drm_plane *plane;
 
 	struct drm_crtc *crtc;
@@ -7311,7 +7798,6 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 			uint64_t tiling_flags;
 
 			new_plane_crtc = new_plane_state->crtc;
-			old_plane_crtc = old_plane_state->crtc;
 			new_dm_plane_state = to_dm_plane_state(new_plane_state);
 			old_dm_plane_state = to_dm_plane_state(old_plane_state);
 
@@ -7412,6 +7898,29 @@ cleanup:
 	return ret;
 }
 
+static int add_affected_mst_dsc_crtcs(struct drm_atomic_state *state, struct drm_crtc *crtc)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct amdgpu_dm_connector *aconnector = NULL;
+	int i;
+	for_each_new_connector_in_state(state, connector, conn_state, i) {
+		if (conn_state->crtc != crtc)
+			continue;
+
+		aconnector = to_amdgpu_dm_connector(connector);
+		if (!aconnector->port || !aconnector->mst_port)
+			aconnector = NULL;
+		else
+			break;
+	}
+
+	if (!aconnector)
+		return 0;
+
+	return drm_dp_mst_add_affected_dsc_crtcs(state, &aconnector->mst_port->mst_mgr);
+}
+
 /**
  * amdgpu_dm_atomic_check() - Atomic check implementation for AMDgpu DM.
  * @dev: The DRM device
@@ -7464,6 +7973,16 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 	if (ret)
 		goto fail;
 
+	if (adev->asic_type >= CHIP_NAVI10) {
+		for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+			if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
+				ret = add_affected_mst_dsc_crtcs(state, crtc);
+				if (ret)
+					goto fail;
+			}
+		}
+	}
+
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 		if (!drm_atomic_crtc_needs_modeset(new_crtc_state) &&
 		    !new_crtc_state->color_mgmt_changed &&
@@ -7635,6 +8154,15 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		if (ret)
 			goto fail;
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+		if (!compute_mst_dsc_configs_for_state(state, dm_state->context))
+			goto fail;
+
+		ret = dm_update_mst_vcpi_slots_for_dsc(state, dm_state->context);
+		if (ret)
+			goto fail;
+#endif
+
 		if (dc_validate_global_state(dc, dm_state->context, false) != DC_OK) {
 			ret = -EINVAL;
 			goto fail;
@@ -7663,6 +8191,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 				dc_retain_state(old_dm_state->context);
 		}
 	}
+	/* Perform validation of MST topology in the state*/
+	ret = drm_dp_mst_atomic_check(state);
+	if (ret)
+		goto fail;
 
 	/* Store the overall update type for use later in atomic check. */
 	for_each_new_crtc_in_state (state, crtc, new_crtc_state, i) {
@@ -7861,17 +8393,37 @@ static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)
 bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
 {
 	struct dc_link *link = stream->link;
-	struct dc_static_screen_events triggers = {0};
+	unsigned int vsync_rate_hz = 0;
+	struct dc_static_screen_params params = {0};
+	/* Calculate number of static frames before generating interrupt to
+	 * enter PSR.
+	 */
+	unsigned int frame_time_microsec = 1000000 / vsync_rate_hz;
+	// Init fail safe of 2 frames static
+	unsigned int num_frames_static = 2;
 
 	DRM_DEBUG_DRIVER("Enabling psr...\n");
 
-	triggers.cursor_update = true;
-	triggers.overlay_update = true;
-	triggers.surface_update = true;
+	vsync_rate_hz = div64_u64(div64_u64((
+			stream->timing.pix_clk_100hz * 100),
+			stream->timing.v_total),
+			stream->timing.h_total);
+
+	/* Round up
+	 * Calculate number of frames such that at least 30 ms of time has
+	 * passed.
+	 */
+	if (vsync_rate_hz != 0)
+		num_frames_static = (30000 / frame_time_microsec) + 1;
+
+	params.triggers.cursor_update = true;
+	params.triggers.overlay_update = true;
+	params.triggers.surface_update = true;
+	params.num_frames = num_frames_static;
 
-	dc_stream_set_static_screen_events(link->ctx->dc,
+	dc_stream_set_static_screen_params(link->ctx->dc,
 					   &stream, 1,
-					   &triggers);
+					   &params);
 
 	return dc_link_set_psr_allow_active(link, true, false);
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 77c5166e6b08..7ea9acb0358d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -57,6 +57,8 @@ struct amdgpu_device;
 struct drm_device;
 struct amdgpu_dm_irq_handler_data;
 struct dc;
+struct amdgpu_bo;
+struct dmub_srv;
 
 struct common_irq_params {
 	struct amdgpu_device *adev;
@@ -122,6 +124,57 @@ struct amdgpu_display_manager {
 	struct dc *dc;
 
 	/**
+	 * @dmub_srv:
+	 *
+	 * DMUB service, used for controlling the DMUB on hardware
+	 * that supports it. The pointer to the dmub_srv will be
+	 * NULL on hardware that does not support it.
+	 */
+	struct dmub_srv *dmub_srv;
+
+	/**
+	 * @dmub_fb_info:
+	 *
+	 * Framebuffer regions for the DMUB.
+	 */
+	struct dmub_srv_fb_info *dmub_fb_info;
+
+	/**
+	 * @dmub_fw:
+	 *
+	 * DMUB firmware, required on hardware that has DMUB support.
+	 */
+	const struct firmware *dmub_fw;
+
+	/**
+	 * @dmub_bo:
+	 *
+	 * Buffer object for the DMUB.
+	 */
+	struct amdgpu_bo *dmub_bo;
+
+	/**
+	 * @dmub_bo_gpu_addr:
+	 *
+	 * GPU virtual address for the DMUB buffer object.
+	 */
+	u64 dmub_bo_gpu_addr;
+
+	/**
+	 * @dmub_bo_cpu_addr:
+	 *
+	 * CPU address for the DMUB buffer object.
+	 */
+	void *dmub_bo_cpu_addr;
+
+	/**
+	 * @dmcub_fw_version:
+	 *
+	 * DMCUB firmware version.
+	 */
+	uint32_t dmcub_fw_version;
+
+	/**
 	 * @cgs_device:
 	 *
 	 * The Common Graphics Services device. It provides an interface for
@@ -241,7 +294,6 @@ struct amdgpu_display_manager {
 
 	const struct firmware *fw_dmcu;
 	uint32_t dmcu_fw_version;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	/**
 	 * @soc_bounding_box:
 	 *
@@ -249,7 +301,6 @@ struct amdgpu_display_manager {
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#endif
 };
 
 struct amdgpu_dm_connector {
@@ -279,6 +330,7 @@ struct amdgpu_dm_connector {
 	struct drm_dp_mst_port *port;
 	struct amdgpu_dm_connector *mst_port;
 	struct amdgpu_encoder *mst_encoder;
+	struct drm_dp_aux *dsc_aux;
 
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
 	struct amdgpu_i2c_adapter *i2c;
@@ -359,6 +411,8 @@ struct dm_connector_state {
 	bool underscan_enable;
 	bool freesync_capable;
 	uint8_t abm_level;
+	int vcpi_slots;
+	uint64_t pbn;
 };
 
 #define to_dm_connector_state(x)\
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index bdb37e611015..f81d3439ee8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -657,6 +657,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	dc_link_set_test_pattern(
 		link,
 		test_pattern,
+		DP_TEST_PATTERN_COLOR_SPACE_RGB,
 		&link_training_settings,
 		custom_pattern,
 		10);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 77181ddf6c8e..ae329335dfcc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -85,42 +85,54 @@ static void process_output(struct hdcp_workqueue *hdcp_work)
 		schedule_delayed_work(&hdcp_work->watchdog_timer_dwork,
 				      msecs_to_jiffies(output.watchdog_timer_delay));
 
+	schedule_delayed_work(&hdcp_work->property_validate_dwork, msecs_to_jiffies(0));
 }
 
-void hdcp_add_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index, struct amdgpu_dm_connector *aconnector)
+void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
+			 unsigned int link_index,
+			 struct amdgpu_dm_connector *aconnector,
+			 uint8_t content_type,
+			 bool enable_encryption)
 {
 	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
 	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
 	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
+	struct mod_hdcp_display_query query;
 
 	mutex_lock(&hdcp_w->mutex);
 	hdcp_w->aconnector = aconnector;
 
-	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
-
-	schedule_delayed_work(&hdcp_w->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
-
-	process_output(hdcp_w);
+	query.display = NULL;
+	mod_hdcp_query_display(&hdcp_w->hdcp, aconnector->base.index, &query);
 
-	mutex_unlock(&hdcp_w->mutex);
+	if (query.display != NULL) {
+		memcpy(display, query.display, sizeof(struct mod_hdcp_display));
+		mod_hdcp_remove_display(&hdcp_w->hdcp, aconnector->base.index, &hdcp_w->output);
 
-}
+		hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
 
-void hdcp_remove_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index,  unsigned int display_index)
-{
-	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
+		if (enable_encryption) {
+			display->adjust.disable = 0;
+			if (content_type == DRM_MODE_HDCP_CONTENT_TYPE0)
+				hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
+			else if (content_type == DRM_MODE_HDCP_CONTENT_TYPE1)
+				hdcp_w->link.adjust.hdcp2.force_type = MOD_HDCP_FORCE_TYPE_1;
 
-	mutex_lock(&hdcp_w->mutex);
+			schedule_delayed_work(&hdcp_w->property_validate_dwork,
+					      msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
+		} else {
+			display->adjust.disable = 1;
+			hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+			cancel_delayed_work(&hdcp_w->property_validate_dwork);
+		}
 
-	mod_hdcp_remove_display(&hdcp_w->hdcp, display_index, &hdcp_w->output);
+		display->state = MOD_HDCP_DISPLAY_ACTIVE;
+	}
 
-	cancel_delayed_work(&hdcp_w->property_validate_dwork);
-	hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
 
 	process_output(hdcp_w);
-
 	mutex_unlock(&hdcp_w->mutex);
-
 }
 
 void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index)
@@ -190,10 +202,16 @@ static void event_property_update(struct work_struct *work)
 		}
 	}
 
-	if (hdcp_work->encryption_status == MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON)
-		drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
-	else
+	if (hdcp_work->encryption_status != MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF) {
+		if (aconnector->base.state->hdcp_content_type == DRM_MODE_HDCP_CONTENT_TYPE0 &&
+		    hdcp_work->encryption_status <= MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON)
+			drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
+		else if (aconnector->base.state->hdcp_content_type == DRM_MODE_HDCP_CONTENT_TYPE1 &&
+			 hdcp_work->encryption_status == MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON)
+			drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
+	} else {
 		drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_DESIRED);
+	}
 
 
 	mutex_unlock(&hdcp_work->mutex);
@@ -207,6 +225,9 @@ static void event_property_validate(struct work_struct *work)
 	struct mod_hdcp_display_query query;
 	struct amdgpu_dm_connector *aconnector = hdcp_work->aconnector;
 
+	if (!aconnector)
+		return;
+
 	mutex_lock(&hdcp_work->mutex);
 
 	query.encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
@@ -217,8 +238,6 @@ static void event_property_validate(struct work_struct *work)
 		schedule_work(&hdcp_work->property_update_work);
 	}
 
-	schedule_delayed_work(&hdcp_work->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
-
 	mutex_unlock(&hdcp_work->mutex);
 }
 
@@ -294,8 +313,10 @@ static void update_config(void *handle, struct cp_psp_stream_config *config)
 	link->dig_be = config->link_enc_inst;
 	link->ddc_line = aconnector->dc_link->ddc_hw_inst + 1;
 	link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw;
-	link->adjust.hdcp2.disable = 1;
+	display->adjust.disable = 1;
+	link->adjust.auth_delay = 2;
 
+	hdcp_update_display(hdcp_work, link_index, aconnector, DRM_MODE_HDCP_CONTENT_TYPE0, false);
 }
 
 struct hdcp_workqueue *hdcp_create_workqueue(void *psp_context, struct cp_psp *cp_psp, struct dc *dc)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
index d3ba505d0696..6abde86bce4a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
@@ -54,9 +54,12 @@ struct hdcp_workqueue {
 	uint8_t max_link;
 };
 
-void hdcp_add_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index,
-		      struct amdgpu_dm_connector *aconnector);
-void hdcp_remove_display(struct hdcp_workqueue *work, unsigned int link_index, unsigned int display_index);
+void hdcp_update_display(struct hdcp_workqueue *hdcp_work,
+			 unsigned int link_index,
+			 struct amdgpu_dm_connector *aconnector,
+			 uint8_t content_type,
+			 bool enable_encryption);
+
 void hdcp_reset_display(struct hdcp_workqueue *work, unsigned int link_index);
 void hdcp_handle_cpirq(struct hdcp_workqueue *work, unsigned int link_index);
 void hdcp_destroy(struct hdcp_workqueue *work);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 11e5784aa62a..069b7a6f5597 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -37,6 +37,7 @@
 #include "dc.h"
 #include "amdgpu_dm.h"
 #include "amdgpu_dm_irq.h"
+#include "amdgpu_dm_mst_types.h"
 
 #include "dm_helpers.h"
 
@@ -97,8 +98,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 			(struct edid *) edid->raw_edid);
 
 	sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads);
-	if (sad_count < 0)
-		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
 	if (sad_count <= 0)
 		return result;
 
@@ -182,19 +181,22 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
 		bool enable)
 {
 	struct amdgpu_dm_connector *aconnector;
+	struct dm_connector_state *dm_conn_state;
 	struct drm_dp_mst_topology_mgr *mst_mgr;
 	struct drm_dp_mst_port *mst_port;
-	int slots = 0;
 	bool ret;
-	int clock;
-	int bpp = 0;
-	int pbn = 0;
 
 	aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+	/* Accessing the connector state is required for vcpi_slots allocation
+	 * and directly relies on behaviour in commit check
+	 * that blocks before commit guaranteeing that the state
+	 * is not gonna be swapped while still in use in commit tail */
 
 	if (!aconnector || !aconnector->mst_port)
 		return false;
 
+	dm_conn_state = to_dm_connector_state(aconnector->base.state);
+
 	mst_mgr = &aconnector->mst_port->mst_mgr;
 
 	if (!mst_mgr->mst_state)
@@ -203,42 +205,10 @@ bool dm_helpers_dp_mst_write_payload_allocation_table(
 	mst_port = aconnector->port;
 
 	if (enable) {
-		clock = stream->timing.pix_clk_100hz / 10;
-
-		switch (stream->timing.display_color_depth) {
-
-		case COLOR_DEPTH_666:
-			bpp = 6;
-			break;
-		case COLOR_DEPTH_888:
-			bpp = 8;
-			break;
-		case COLOR_DEPTH_101010:
-			bpp = 10;
-			break;
-		case COLOR_DEPTH_121212:
-			bpp = 12;
-			break;
-		case COLOR_DEPTH_141414:
-			bpp = 14;
-			break;
-		case COLOR_DEPTH_161616:
-			bpp = 16;
-			break;
-		default:
-			ASSERT(bpp != 0);
-			break;
-		}
-
-		bpp = bpp * 3;
-
-		/* TODO need to know link rate */
-
-		pbn = drm_dp_calc_pbn_mode(clock, bpp);
-
-		slots = drm_dp_find_vcpi_slots(mst_mgr, pbn);
-		ret = drm_dp_mst_allocate_vcpi(mst_mgr, mst_port, pbn, slots);
 
+		ret = drm_dp_mst_allocate_vcpi(mst_mgr, mst_port,
+					       dm_conn_state->pbn,
+					       dm_conn_state->vcpi_slots);
 		if (!ret)
 			return false;
 
@@ -540,7 +510,6 @@ bool dm_helpers_submit_i2c(
 
 	return result;
 }
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dm_helpers_dp_write_dsc_enable(
 		struct dc_context *ctx,
 		const struct dc_stream_state *stream,
@@ -548,10 +517,25 @@ bool dm_helpers_dp_write_dsc_enable(
 )
 {
 	uint8_t enable_dsc = enable ? 1 : 0;
+	struct amdgpu_dm_connector *aconnector;
+
+	if (!stream)
+		return false;
+
+	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+
+		if (!aconnector->dsc_aux)
+			return false;
+
+		return (drm_dp_dpcd_write(aconnector->dsc_aux, DP_DSC_ENABLE, &enable_dsc, 1) >= 0);
+	}
+
+	if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT)
+		return dm_helpers_dp_write_dpcd(ctx, stream->link, DP_DSC_ENABLE, &enable_dsc, 1);
 
-	return dm_helpers_dp_write_dpcd(ctx, stream->sink->link, DP_DSC_ENABLE, &enable_dsc, 1);
+	return false;
 }
-#endif
 
 bool dm_helpers_is_dp_sink_present(struct dc_link *link)
 {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 64445c4cc4c2..cbcf504f73a5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -111,17 +111,12 @@ static void init_handler_common_data(struct amdgpu_dm_irq_handler_data *hcd,
  */
 static void dm_irq_work_func(struct work_struct *work)
 {
-	struct list_head *entry;
 	struct irq_list_head *irq_list_head =
 		container_of(work, struct irq_list_head, work);
 	struct list_head *handler_list = &irq_list_head->head;
 	struct amdgpu_dm_irq_handler_data *handler_data;
 
-	list_for_each(entry, handler_list) {
-		handler_data = list_entry(entry,
-					  struct amdgpu_dm_irq_handler_data,
-					  list);
-
+	list_for_each_entry(handler_data, handler_list, list) {
 		DRM_DEBUG_KMS("DM_IRQ: work_func: for dal_src=%d\n",
 				handler_data->irq_source);
 
@@ -528,19 +523,13 @@ static void amdgpu_dm_irq_immediate_work(struct amdgpu_device *adev,
 					 enum dc_irq_source irq_source)
 {
 	struct amdgpu_dm_irq_handler_data *handler_data;
-	struct list_head *entry;
 	unsigned long irq_table_flags;
 
 	DM_IRQ_TABLE_LOCK(adev, irq_table_flags);
 
-	list_for_each(
-		entry,
-		&adev->dm.irq_handler_list_high_tab[irq_source]) {
-
-		handler_data = list_entry(entry,
-					  struct amdgpu_dm_irq_handler_data,
-					  list);
-
+	list_for_each_entry(handler_data,
+			    &adev->dm.irq_handler_list_high_tab[irq_source],
+			    list) {
 		/* Call a subcomponent which registered for immediate
 		 * interrupt notification */
 		handler_data->handler(handler_data->handler_arg);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 2bf8534c18fb..96b391e4b3e7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -25,6 +25,7 @@
 
 #include <linux/version.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_dp_mst_helper.h>
 #include "dm_services.h"
 #include "amdgpu.h"
 #include "amdgpu_dm.h"
@@ -39,6 +40,12 @@
 #if defined(CONFIG_DEBUG_FS)
 #include "amdgpu_dm_debugfs.h"
 #endif
+
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+#include "dc/dcn20/dcn20_resource.h"
+#endif
+
 /* #define TRACE_DPCD */
 
 #ifdef TRACE_DPCD
@@ -180,6 +187,30 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
 	.early_unregister = amdgpu_dm_mst_connector_early_unregister,
 };
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector)
+{
+	struct dc_sink *dc_sink = aconnector->dc_sink;
+	struct drm_dp_mst_port *port = aconnector->port;
+	u8 dsc_caps[16] = { 0 };
+
+	aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port);
+
+	if (!aconnector->dsc_aux)
+		return false;
+
+	if (drm_dp_dpcd_read(aconnector->dsc_aux, DP_DSC_SUPPORT, dsc_caps, 16) < 0)
+		return false;
+
+	if (!dc_dsc_parse_dsc_dpcd(aconnector->dc_link->ctx->dc,
+				   dsc_caps, NULL,
+				   &dc_sink->sink_dsc_caps.dsc_dec_caps))
+		return false;
+
+	return true;
+}
+#endif
+
 static int dm_dp_mst_get_modes(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
@@ -222,10 +253,16 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		/* dc_link_add_remote_sink returns a new reference */
 		aconnector->dc_sink = dc_sink;
 
-		if (aconnector->dc_sink)
+		if (aconnector->dc_sink) {
 			amdgpu_dm_update_freesync_caps(
 					connector, aconnector->edid);
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+			if (!validate_dsc_caps_on_connector(aconnector))
+				memset(&aconnector->dc_sink->sink_dsc_caps,
+				       0, sizeof(aconnector->dc_sink->sink_dsc_caps));
+#endif
+		}
 	}
 
 	drm_connector_update_edid_property(
@@ -254,11 +291,43 @@ dm_dp_mst_detect(struct drm_connector *connector,
 				      aconnector->port);
 }
 
+static int dm_dp_mst_atomic_check(struct drm_connector *connector,
+				struct drm_atomic_state *state)
+{
+	struct drm_connector_state *new_conn_state =
+			drm_atomic_get_new_connector_state(state, connector);
+	struct drm_connector_state *old_conn_state =
+			drm_atomic_get_old_connector_state(state, connector);
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_dp_mst_topology_mgr *mst_mgr;
+	struct drm_dp_mst_port *mst_port;
+
+	mst_port = aconnector->port;
+	mst_mgr = &aconnector->mst_port->mst_mgr;
+
+	if (!old_conn_state->crtc)
+		return 0;
+
+	if (new_conn_state->crtc) {
+		new_crtc_state = drm_atomic_get_new_crtc_state(state, new_conn_state->crtc);
+		if (!new_crtc_state ||
+		    !drm_atomic_crtc_needs_modeset(new_crtc_state) ||
+		    new_crtc_state->enable)
+			return 0;
+		}
+
+	return drm_dp_atomic_release_vcpi_slots(state,
+						mst_mgr,
+						mst_port);
+}
+
 static const struct drm_connector_helper_funcs dm_dp_mst_connector_helper_funcs = {
 	.get_modes = dm_dp_mst_get_modes,
 	.mode_valid = amdgpu_dm_connector_mode_valid,
 	.atomic_best_encoder = dm_mst_atomic_best_encoder,
 	.detect_ctx = dm_dp_mst_detect,
+	.atomic_check = dm_dp_mst_atomic_check,
 };
 
 static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder)
@@ -434,3 +503,384 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 		aconnector->connector_id);
 }
 
+int dm_mst_get_pbn_divider(struct dc_link *link)
+{
+	if (!link)
+		return 0;
+
+	return dc_link_bandwidth_kbps(link,
+			dc_link_get_link_cap(link)) / (8 * 1000 * 54);
+}
+
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+
+struct dsc_mst_fairness_params {
+	struct dc_crtc_timing *timing;
+	struct dc_sink *sink;
+	struct dc_dsc_bw_range bw_range;
+	bool compression_possible;
+	struct drm_dp_mst_port *port;
+};
+
+struct dsc_mst_fairness_vars {
+	int pbn;
+	bool dsc_enabled;
+	int bpp_x16;
+};
+
+static int kbps_to_peak_pbn(int kbps)
+{
+	u64 peak_kbps = kbps;
+
+	peak_kbps *= 1006;
+	peak_kbps = div_u64(peak_kbps, 1000);
+	return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000));
+}
+
+static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params,
+		struct dsc_mst_fairness_vars *vars,
+		int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		memset(&params[i].timing->dsc_cfg, 0, sizeof(params[i].timing->dsc_cfg));
+		if (vars[i].dsc_enabled && dc_dsc_compute_config(
+					params[i].sink->ctx->dc->res_pool->dscs[0],
+					&params[i].sink->sink_dsc_caps.dsc_dec_caps,
+					params[i].sink->ctx->dc->debug.dsc_min_slice_height_override,
+					0,
+					params[i].timing,
+					&params[i].timing->dsc_cfg)) {
+			params[i].timing->flags.DSC = 1;
+			params[i].timing->dsc_cfg.bits_per_pixel = vars[i].bpp_x16;
+		} else {
+			params[i].timing->flags.DSC = 0;
+		}
+	}
+}
+
+static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn)
+{
+	struct dc_dsc_config dsc_config;
+	u64 kbps;
+
+	kbps = div_u64((u64)pbn * 994 * 8 * 54, 64);
+	dc_dsc_compute_config(
+			param.sink->ctx->dc->res_pool->dscs[0],
+			&param.sink->sink_dsc_caps.dsc_dec_caps,
+			param.sink->ctx->dc->debug.dsc_min_slice_height_override,
+			(int) kbps, param.timing, &dsc_config);
+
+	return dsc_config.bits_per_pixel;
+}
+
+static void increase_dsc_bpp(struct drm_atomic_state *state,
+			     struct dc_link *dc_link,
+			     struct dsc_mst_fairness_params *params,
+			     struct dsc_mst_fairness_vars *vars,
+			     int count)
+{
+	int i;
+	bool bpp_increased[MAX_PIPES];
+	int initial_slack[MAX_PIPES];
+	int min_initial_slack;
+	int next_index;
+	int remaining_to_increase = 0;
+	int pbn_per_timeslot;
+	int link_timeslots_used;
+	int fair_pbn_alloc;
+
+	for (i = 0; i < count; i++) {
+		if (vars[i].dsc_enabled) {
+			initial_slack[i] = kbps_to_peak_pbn(params[i].bw_range.max_kbps) - vars[i].pbn;
+			bpp_increased[i] = false;
+			remaining_to_increase += 1;
+		} else {
+			initial_slack[i] = 0;
+			bpp_increased[i] = true;
+		}
+	}
+
+	pbn_per_timeslot = dc_link_bandwidth_kbps(dc_link,
+			dc_link_get_link_cap(dc_link)) / (8 * 1000 * 54);
+
+	while (remaining_to_increase) {
+		next_index = -1;
+		min_initial_slack = -1;
+		for (i = 0; i < count; i++) {
+			if (!bpp_increased[i]) {
+				if (min_initial_slack == -1 || min_initial_slack > initial_slack[i]) {
+					min_initial_slack = initial_slack[i];
+					next_index = i;
+				}
+			}
+		}
+
+		if (next_index == -1)
+			break;
+
+		link_timeslots_used = 0;
+
+		for (i = 0; i < count; i++)
+			link_timeslots_used += DIV_ROUND_UP(vars[i].pbn, pbn_per_timeslot);
+
+		fair_pbn_alloc = (63 - link_timeslots_used) / remaining_to_increase * pbn_per_timeslot;
+
+		if (initial_slack[next_index] > fair_pbn_alloc) {
+			vars[next_index].pbn += fair_pbn_alloc;
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[next_index].port->mgr,
+							  params[next_index].port,
+							  vars[next_index].pbn,\
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return;
+			if (!drm_dp_mst_atomic_check(state)) {
+				vars[next_index].bpp_x16 = bpp_x16_from_pbn(params[next_index], vars[next_index].pbn);
+			} else {
+				vars[next_index].pbn -= fair_pbn_alloc;
+				if (drm_dp_atomic_find_vcpi_slots(state,
+								  params[next_index].port->mgr,
+								  params[next_index].port,
+								  vars[next_index].pbn,
+								  dm_mst_get_pbn_divider(dc_link)) < 0)
+					return;
+			}
+		} else {
+			vars[next_index].pbn += initial_slack[next_index];
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[next_index].port->mgr,
+							  params[next_index].port,
+							  vars[next_index].pbn,
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return;
+			if (!drm_dp_mst_atomic_check(state)) {
+				vars[next_index].bpp_x16 = params[next_index].bw_range.max_target_bpp_x16;
+			} else {
+				vars[next_index].pbn -= initial_slack[next_index];
+				if (drm_dp_atomic_find_vcpi_slots(state,
+								  params[next_index].port->mgr,
+								  params[next_index].port,
+								  vars[next_index].pbn,
+								  dm_mst_get_pbn_divider(dc_link)) < 0)
+					return;
+			}
+		}
+
+		bpp_increased[next_index] = true;
+		remaining_to_increase--;
+	}
+}
+
+static void try_disable_dsc(struct drm_atomic_state *state,
+			    struct dc_link *dc_link,
+			    struct dsc_mst_fairness_params *params,
+			    struct dsc_mst_fairness_vars *vars,
+			    int count)
+{
+	int i;
+	bool tried[MAX_PIPES];
+	int kbps_increase[MAX_PIPES];
+	int max_kbps_increase;
+	int next_index;
+	int remaining_to_try = 0;
+
+	for (i = 0; i < count; i++) {
+		if (vars[i].dsc_enabled && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16) {
+			kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps;
+			tried[i] = false;
+			remaining_to_try += 1;
+		} else {
+			kbps_increase[i] = 0;
+			tried[i] = true;
+		}
+	}
+
+	while (remaining_to_try) {
+		next_index = -1;
+		max_kbps_increase = -1;
+		for (i = 0; i < count; i++) {
+			if (!tried[i]) {
+				if (max_kbps_increase == -1 || max_kbps_increase < kbps_increase[i]) {
+					max_kbps_increase = kbps_increase[i];
+					next_index = i;
+				}
+			}
+		}
+
+		if (next_index == -1)
+			break;
+
+		vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps);
+		if (drm_dp_atomic_find_vcpi_slots(state,
+						  params[next_index].port->mgr,
+						  params[next_index].port,
+						  vars[next_index].pbn,
+						  0) < 0)
+			return;
+
+		if (!drm_dp_mst_atomic_check(state)) {
+			vars[next_index].dsc_enabled = false;
+			vars[next_index].bpp_x16 = 0;
+		} else {
+			vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.max_kbps);
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[next_index].port->mgr,
+							  params[next_index].port,
+							  vars[next_index].pbn,
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return;
+		}
+
+		tried[next_index] = true;
+		remaining_to_try--;
+	}
+}
+
+static bool compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
+					     struct dc_state *dc_state,
+					     struct dc_link *dc_link)
+{
+	int i;
+	struct dc_stream_state *stream;
+	struct dsc_mst_fairness_params params[MAX_PIPES];
+	struct dsc_mst_fairness_vars vars[MAX_PIPES];
+	struct amdgpu_dm_connector *aconnector;
+	int count = 0;
+
+	memset(params, 0, sizeof(params));
+
+	/* Set up params */
+	for (i = 0; i < dc_state->stream_count; i++) {
+		struct dc_dsc_policy dsc_policy = {0};
+
+		stream = dc_state->streams[i];
+
+		if (stream->link != dc_link)
+			continue;
+
+		stream->timing.flags.DSC = 0;
+
+		params[count].timing = &stream->timing;
+		params[count].sink = stream->sink;
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+		params[count].port = aconnector->port;
+		params[count].compression_possible = stream->sink->sink_dsc_caps.dsc_dec_caps.is_dsc_supported;
+		dc_dsc_get_policy_for_timing(params[count].timing, &dsc_policy);
+		if (!dc_dsc_compute_bandwidth_range(
+				stream->sink->ctx->dc->res_pool->dscs[0],
+				stream->sink->ctx->dc->debug.dsc_min_slice_height_override,
+				dsc_policy.min_target_bpp,
+				dsc_policy.max_target_bpp,
+				&stream->sink->sink_dsc_caps.dsc_dec_caps,
+				&stream->timing, &params[count].bw_range))
+			params[count].bw_range.stream_kbps = dc_bandwidth_in_kbps_from_timing(&stream->timing);
+
+		count++;
+	}
+	/* Try no compression */
+	for (i = 0; i < count; i++) {
+		vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+		vars[i].dsc_enabled = false;
+		vars[i].bpp_x16 = 0;
+		if (drm_dp_atomic_find_vcpi_slots(state,
+						 params[i].port->mgr,
+						 params[i].port,
+						 vars[i].pbn,
+						 0) < 0)
+			return false;
+	}
+	if (!drm_dp_mst_atomic_check(state)) {
+		set_dsc_configs_from_fairness_vars(params, vars, count);
+		return true;
+	}
+
+	/* Try max compression */
+	for (i = 0; i < count; i++) {
+		if (params[i].compression_possible) {
+			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps);
+			vars[i].dsc_enabled = true;
+			vars[i].bpp_x16 = params[i].bw_range.min_target_bpp_x16;
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[i].port->mgr,
+							  params[i].port,
+							  vars[i].pbn,
+							  dm_mst_get_pbn_divider(dc_link)) < 0)
+				return false;
+		} else {
+			vars[i].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps);
+			vars[i].dsc_enabled = false;
+			vars[i].bpp_x16 = 0;
+			if (drm_dp_atomic_find_vcpi_slots(state,
+							  params[i].port->mgr,
+							  params[i].port,
+							  vars[i].pbn,
+							  0) < 0)
+				return false;
+		}
+	}
+	if (drm_dp_mst_atomic_check(state))
+		return false;
+
+	/* Optimize degree of compression */
+	increase_dsc_bpp(state, dc_link, params, vars, count);
+
+	try_disable_dsc(state, dc_link, params, vars, count);
+
+	set_dsc_configs_from_fairness_vars(params, vars, count);
+
+	return true;
+}
+
+bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
+				       struct dc_state *dc_state)
+{
+	int i, j;
+	struct dc_stream_state *stream;
+	bool computed_streams[MAX_PIPES];
+	struct amdgpu_dm_connector *aconnector;
+
+	for (i = 0; i < dc_state->stream_count; i++)
+		computed_streams[i] = false;
+
+	for (i = 0; i < dc_state->stream_count; i++) {
+		stream = dc_state->streams[i];
+
+		if (stream->signal != SIGNAL_TYPE_DISPLAY_PORT_MST)
+			continue;
+
+		aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
+
+		if (!aconnector || !aconnector->dc_sink)
+			continue;
+
+		if (!aconnector->dc_sink->sink_dsc_caps.dsc_dec_caps.is_dsc_supported)
+			continue;
+
+		if (computed_streams[i])
+			continue;
+
+		mutex_lock(&aconnector->mst_mgr.lock);
+		if (!compute_mst_dsc_configs_for_link(state, dc_state, stream->link)) {
+			mutex_unlock(&aconnector->mst_mgr.lock);
+			return false;
+		}
+		mutex_unlock(&aconnector->mst_mgr.lock);
+
+		for (j = 0; j < dc_state->stream_count; j++) {
+			if (dc_state->streams[j]->link == stream->link)
+				computed_streams[j] = true;
+		}
+	}
+
+	for (i = 0; i < dc_state->stream_count; i++) {
+		stream = dc_state->streams[i];
+
+		if (stream->timing.flags.DSC == 1)
+			dcn20_add_dsc_to_stream_resource(stream->ctx->dc, dc_state, stream);
+	}
+
+	return true;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index 2da851b40042..d6813ce67bbd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -29,7 +29,14 @@
 struct amdgpu_display_manager;
 struct amdgpu_dm_connector;
 
+int dm_mst_get_pbn_divider(struct dc_link *link);
+
 void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 				       struct amdgpu_dm_connector *aconnector);
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
+				       struct dc_state *dc_state);
+#endif
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 778f186b3a05..a2e1a73f66b8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -892,7 +892,6 @@ enum pp_smu_status pp_nv_get_uclk_dpm_states(struct pp_smu *pp,
 	return PP_SMU_RESULT_FAIL;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 enum pp_smu_status pp_rn_get_dpm_clock_table(
 		struct pp_smu *pp, struct dpm_clocks *clock_table)
 {
@@ -974,7 +973,6 @@ enum pp_smu_status pp_rn_set_wm_ranges(struct pp_smu *pp,
 
 	return PP_SMU_RESULT_OK;
 }
-#endif
 
 void dm_pp_get_funcs(
 		struct dc_context *ctx,
@@ -996,7 +994,6 @@ void dm_pp_get_funcs(
 		funcs->rv_funcs.set_hard_min_fclk_by_freq =
 				pp_rv_set_hard_min_fclk_by_freq;
 		break;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	case DCN_VERSION_2_0:
 		funcs->ctx.ver = PP_SMU_VER_NV;
 		funcs->nv_funcs.pp_smu.dm = ctx;
@@ -1019,16 +1016,13 @@ void dm_pp_get_funcs(
 		funcs->nv_funcs.get_uclk_dpm_states = pp_nv_get_uclk_dpm_states;
 		funcs->nv_funcs.set_pstate_handshake_support = pp_nv_set_pstate_handshake_support;
 		break;
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	case DCN_VERSION_2_1:
 		funcs->ctx.ver = PP_SMU_VER_RN;
 		funcs->rn_funcs.pp_smu.dm = ctx;
 		funcs->rn_funcs.set_wm_ranges = pp_rn_set_wm_ranges;
 		funcs->rn_funcs.get_dpm_clock_table = pp_rn_get_dpm_clock_table;
 		break;
-#endif
 	default:
 		DRM_ERROR("smu version is not supported !\n");
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index a160512a2f04..6e3dddc73246 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -25,19 +25,10 @@
 
 DC_LIBS = basics bios calcs clk_mgr dce gpio irq virtual
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 DC_LIBS += dcn20
-endif
-
-
-ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DC_LIBS += dsc
-endif
-
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
 DC_LIBS += dcn10 dml
-endif
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 DC_LIBS += dcn21
 endif
 
@@ -59,7 +50,7 @@ include $(AMD_DC)
 DISPLAY_CORE = dc.o dc_link.o dc_resource.o dc_hw_sequencer.o dc_sink.o \
 dc_surface.o dc_link_hwss.o dc_link_dp.o dc_link_ddc.o dc_debug.o dc_stream.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 DISPLAY_CORE += dc_vm_helper.o
 endif
 
@@ -70,5 +61,6 @@ AMD_DM_REG_UPDATE = $(addprefix $(AMDDALPATH)/dc/,dc_helper.o)
 AMD_DISPLAY_FILES += $(AMD_DISPLAY_CORE)
 AMD_DISPLAY_FILES += $(AMD_DM_REG_UPDATE)
 
-
-
+DC_DMUB += dc_dmub_srv.o
+AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB))
+AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB)
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index a50a76471107..7ad0cad0f4ef 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/basics/Makefile
@@ -25,7 +25,7 @@
 # subcomponents.
 
 BASICS = conversion.o fixpt31_32.o \
-	log_helpers.o vector.o
+	log_helpers.o vector.o dc_common.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/dc_common.c b/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
new file mode 100644
index 000000000000..b2fc4f8e6482
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/basics/dc_common.c
@@ -0,0 +1,101 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "core_types.h"
+#include "dc_common.h"
+#include "basics/conversion.h"
+
+bool is_rgb_cspace(enum dc_color_space output_color_space)
+{
+	switch (output_color_space) {
+	case COLOR_SPACE_SRGB:
+	case COLOR_SPACE_SRGB_LIMITED:
+	case COLOR_SPACE_2020_RGB_FULLRANGE:
+	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
+	case COLOR_SPACE_ADOBERGB:
+		return true;
+	case COLOR_SPACE_YCBCR601:
+	case COLOR_SPACE_YCBCR709:
+	case COLOR_SPACE_YCBCR601_LIMITED:
+	case COLOR_SPACE_YCBCR709_LIMITED:
+	case COLOR_SPACE_2020_YCBCR:
+		return false;
+	default:
+		/* Add a case to switch */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+}
+
+bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
+		return true;
+	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
+		return true;
+	return false;
+}
+
+bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
+		return true;
+	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
+		return true;
+	return false;
+}
+
+bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
+{
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
+		return true;
+	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
+		return true;
+	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
+		return true;
+	return false;
+}
+
+void build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
+		const struct dc_plane_state *plane_state)
+{
+	if (plane_state->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN
+			&& plane_state->format != SURFACE_PIXEL_FORMAT_INVALID
+			&& plane_state->input_csc_color_matrix.enable_adjustment
+			&& plane_state->coeff_reduction_factor.value != 0) {
+		bias_and_scale->scale_blue = fixed_point_to_int_frac(
+			dc_fixpt_mul(plane_state->coeff_reduction_factor,
+					dc_fixpt_from_fraction(256, 255)),
+				2,
+				13);
+		bias_and_scale->scale_red = bias_and_scale->scale_blue;
+		bias_and_scale->scale_green = bias_and_scale->scale_blue;
+	} else {
+		bias_and_scale->scale_blue = 0x2000;
+		bias_and_scale->scale_red = 0x2000;
+		bias_and_scale->scale_green = 0x2000;
+	}
+}
+
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.h b/drivers/gpu/drm/amd/display/dc/basics/dc_common.h
index 8bdfb3e5cd1c..7c0cbf47e8ce 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.h
+++ b/drivers/gpu/drm/amd/display/dc/basics/dc_common.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -14,23 +14,29 @@
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
  */
 
-#ifndef __NVKM_SECBOOT_ACR_R367_H__
-#define __NVKM_SECBOOT_ACR_R367_H__
+#ifndef __DAL_DC_COMMON_H__
+#define __DAL_DC_COMMON_H__
+
+#include "core_types.h"
+
+bool is_rgb_cspace(enum dc_color_space output_color_space);
+
+bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
+
+bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
 
-#include "acr_r352.h"
+bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
 
-void acr_r367_fixup_hs_desc(struct acr_r352 *, struct nvkm_secboot *, void *);
+void build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
+		const struct dc_plane_state *plane_state);
 
-struct ls_ucode_img *acr_r367_ls_ucode_img_load(const struct acr_r352 *,
-						const struct nvkm_secboot *,
-						enum nvkm_secboot_falcon);
-int acr_r367_ls_fill_headers(struct acr_r352 *, struct list_head *);
-int acr_r367_ls_write_wpr(struct acr_r352 *, struct list_head *,
-			  struct nvkm_gpuobj *, u64);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index 823843cd2613..008d4d11339d 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -111,7 +111,7 @@ struct dc_bios *bios_parser_create(
 	return NULL;
 }
 
-static void destruct(struct bios_parser *bp)
+static void bios_parser_destruct(struct bios_parser *bp)
 {
 	kfree(bp->base.bios_local_image);
 	kfree(bp->base.integrated_info);
@@ -126,7 +126,7 @@ static void bios_parser_destroy(struct dc_bios **dcb)
 		return;
 	}
 
-	destruct(bp);
+	bios_parser_destruct(bp);
 
 	kfree(bp);
 	*dcb = NULL;
@@ -2189,7 +2189,7 @@ static uint32_t get_support_mask_for_device_id(struct device_id device_id)
 		break;
 	default:
 		break;
-	};
+	}
 
 	/* Unidentified device ID, return empty support mask. */
 	return 0;
@@ -2739,7 +2739,6 @@ static enum bp_result bios_get_board_layout_info(
 	struct board_layout_info *board_layout_info)
 {
 	unsigned int i;
-	struct bios_parser *bp;
 	enum bp_result record_result;
 
 	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
@@ -2748,7 +2747,6 @@ static enum bp_result bios_get_board_layout_info(
 		0, 0
 	};
 
-	bp = BP_FROM_DCB(dcb);
 	if (board_layout_info == NULL) {
 		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
 		return BP_RESULT_BADINPUT;
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index 5c3fcaa47410..2f1c9584ac32 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -111,7 +111,7 @@ static struct atom_encoder_caps_record *get_encoder_cap_record(
 
 #define DATA_TABLES(table) (bp->master_data_tbl->listOfdatatables.table)
 
-static void destruct(struct bios_parser *bp)
+static void bios_parser2_destruct(struct bios_parser *bp)
 {
 	kfree(bp->base.bios_local_image);
 	kfree(bp->base.integrated_info);
@@ -126,7 +126,7 @@ static void firmware_parser_destroy(struct dc_bios **dcb)
 		return;
 	}
 
-	destruct(bp);
+	bios_parser2_destruct(bp);
 
 	kfree(bp);
 	*dcb = NULL;
@@ -294,11 +294,21 @@ static enum bp_result bios_parser_get_i2c_info(struct dc_bios *dcb,
 	struct atom_display_object_path_v2 *object;
 	struct atom_common_record_header *header;
 	struct atom_i2c_record *record;
+	struct atom_i2c_record dummy_record = {0};
 	struct bios_parser *bp = BP_FROM_DCB(dcb);
 
 	if (!info)
 		return BP_RESULT_BADINPUT;
 
+	if (id.type == OBJECT_TYPE_GENERIC) {
+		dummy_record.i2c_id = id.id;
+
+		if (get_gpio_i2c_info(bp, &dummy_record, info) == BP_RESULT_OK)
+			return BP_RESULT_OK;
+		else
+			return BP_RESULT_NORECORD;
+	}
+
 	object = get_bios_object(bp, id);
 
 	if (!object)
@@ -341,6 +351,7 @@ static enum bp_result get_gpio_i2c_info(
 	struct atom_gpio_pin_lut_v2_1 *header;
 	uint32_t count = 0;
 	unsigned int table_index = 0;
+	bool find_valid = false;
 
 	if (!info)
 		return BP_RESULT_BADINPUT;
@@ -368,33 +379,28 @@ static enum bp_result get_gpio_i2c_info(
 			- sizeof(struct atom_common_table_header))
 				/ sizeof(struct atom_gpio_pin_assignment);
 
-	table_index = record->i2c_id  & I2C_HW_LANE_MUX;
-
-	if (count < table_index) {
-		bool find_valid = false;
-
-		for (table_index = 0; table_index < count; table_index++) {
-			if (((record->i2c_id & I2C_HW_CAP) == (
-			header->gpio_pin[table_index].gpio_id &
-							I2C_HW_CAP)) &&
-			((record->i2c_id & I2C_HW_ENGINE_ID_MASK)  ==
-			(header->gpio_pin[table_index].gpio_id &
-						I2C_HW_ENGINE_ID_MASK)) &&
-			((record->i2c_id & I2C_HW_LANE_MUX) ==
-			(header->gpio_pin[table_index].gpio_id &
-							I2C_HW_LANE_MUX))) {
-				/* still valid */
-				find_valid = true;
-				break;
-			}
+	for (table_index = 0; table_index < count; table_index++) {
+		if (((record->i2c_id & I2C_HW_CAP) == (
+		header->gpio_pin[table_index].gpio_id &
+						I2C_HW_CAP)) &&
+		((record->i2c_id & I2C_HW_ENGINE_ID_MASK)  ==
+		(header->gpio_pin[table_index].gpio_id &
+					I2C_HW_ENGINE_ID_MASK)) &&
+		((record->i2c_id & I2C_HW_LANE_MUX) ==
+		(header->gpio_pin[table_index].gpio_id &
+						I2C_HW_LANE_MUX))) {
+			/* still valid */
+			find_valid = true;
+			break;
 		}
-		/* If we don't find the entry that we are looking for then
-		 *  we will return BP_Result_BadBiosTable.
-		 */
-		if (find_valid == false)
-			return BP_RESULT_BADBIOSTABLE;
 	}
 
+	/* If we don't find the entry that we are looking for then
+	 *  we will return BP_Result_BadBiosTable.
+	 */
+	if (find_valid == false)
+		return BP_RESULT_BADBIOSTABLE;
+
 	/* get the GPIO_I2C_INFO */
 	info->i2c_hw_assist = (record->i2c_id & I2C_HW_CAP) ? true : false;
 	info->i2c_line = record->i2c_id & I2C_HW_LANE_MUX;
@@ -828,6 +834,7 @@ static enum bp_result bios_parser_get_spread_spectrum_info(
 		case 1:
 			return get_ss_info_v4_1(bp, signal, index, ss_info);
 		case 2:
+		case 3:
 			return get_ss_info_v4_2(bp, signal, index, ss_info);
 		default:
 			break;
@@ -986,7 +993,7 @@ static uint32_t get_support_mask_for_device_id(struct device_id device_id)
 		break;
 	default:
 		break;
-	};
+	}
 
 	/* Unidentified device ID, return empty support mask. */
 	return 0;
@@ -1205,6 +1212,8 @@ static enum bp_result get_firmware_info_v3_1(
 				bp->cmd_tbl.get_smu_clock_info(bp, SMU9_SYSPLL0_ID) * 10;
 	}
 
+	info->oem_i2c_present = false;
+
 	return BP_RESULT_OK;
 }
 
@@ -1283,6 +1292,13 @@ static enum bp_result get_firmware_info_v3_2(
 					bp->cmd_tbl.get_smu_clock_info(bp, SMU11_SYSPLL3_0_ID) * 10;
 	}
 
+	if (firmware_info->board_i2c_feature_id == 0x2) {
+		info->oem_i2c_present = true;
+		info->oem_i2c_obj_id = firmware_info->board_i2c_feature_gpio_id;
+	} else {
+		info->oem_i2c_present = false;
+	}
+
 	return BP_RESULT_OK;
 }
 
@@ -1402,10 +1418,8 @@ static enum bp_result get_integrated_info_v11(
 	info->ma_channel_number = info_v11->umachannelnumber;
 	info->lvds_ss_percentage =
 	le16_to_cpu(info_v11->lvds_ss_percentage);
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	info->dp_ss_control =
 	le16_to_cpu(info_v11->reserved1);
-#endif
 	info->lvds_sspread_rate_in_10hz =
 	le16_to_cpu(info_v11->lvds_ss_rate_10hz);
 	info->hdmi_ss_percentage =
@@ -1826,7 +1840,6 @@ static enum bp_result bios_get_board_layout_info(
 	struct board_layout_info *board_layout_info)
 {
 	unsigned int i;
-	struct bios_parser *bp;
 	enum bp_result record_result;
 
 	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
@@ -1835,7 +1848,6 @@ static enum bp_result bios_get_board_layout_info(
 		0, 0
 	};
 
-	bp = BP_FROM_DCB(dcb);
 	if (board_layout_info == NULL) {
 		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
 		return BP_RESULT_BADINPUT;
@@ -1915,7 +1927,7 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.get_board_layout_info = bios_get_board_layout_info,
 };
 
-static bool bios_parser_construct(
+static bool bios_parser2_construct(
 	struct bios_parser *bp,
 	struct bp_init_data *init,
 	enum dce_version dce_version)
@@ -2008,7 +2020,7 @@ struct dc_bios *firmware_parser_create(
 	if (!bp)
 		return NULL;
 
-	if (bios_parser_construct(bp, init, dce_version))
+	if (bios_parser2_construct(bp, init, dce_version))
 		return &bp->base;
 
 	kfree(bp);
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index bb2e8105e6ab..2cb7a4288cb7 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -37,6 +37,8 @@
 #include "bios_parser_types_internal2.h"
 #include "amdgpu.h"
 
+#include "dc_dmub_srv.h"
+#include "dc.h"
 
 #define DC_LOGGER \
 	bp->base.ctx->logger
@@ -103,6 +105,21 @@ static void init_dig_encoder_control(struct bios_parser *bp)
 	}
 }
 
+static void encoder_control_dmcub(
+		struct dc_dmub_srv *dmcub,
+		struct dig_encoder_stream_setup_parameters_v1_5 *dig)
+{
+	struct dmub_rb_cmd_digx_encoder_control encoder_control = { 0 };
+
+	encoder_control.header.type = DMUB_CMD__VBIOS;
+	encoder_control.header.sub_type = DMUB_CMD__VBIOS_DIGX_ENCODER_CONTROL;
+	encoder_control.encoder_control.dig.stream_param = *dig;
+
+	dc_dmub_srv_cmd_queue(dmcub, &encoder_control.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
+
 static enum bp_result encoder_control_digx_v1_5(
 	struct bios_parser *bp,
 	struct bp_encoder_control *cntl)
@@ -155,6 +172,12 @@ static enum bp_result encoder_control_digx_v1_5(
 			break;
 		}
 
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		encoder_control_dmcub(bp->base.ctx->dmub_srv, &params);
+		return BP_RESULT_OK;
+	}
+
 	if (EXEC_BIOS_CMD_TABLE(digxencodercontrol, params))
 		result = BP_RESULT_OK;
 
@@ -191,6 +214,22 @@ static void init_transmitter_control(struct bios_parser *bp)
 	}
 }
 
+static void transmitter_control_dmcub(
+		struct dc_dmub_srv *dmcub,
+		struct dig_transmitter_control_parameters_v1_6 *dig)
+{
+	struct dmub_rb_cmd_dig1_transmitter_control transmitter_control;
+
+	transmitter_control.header.type = DMUB_CMD__VBIOS;
+	transmitter_control.header.sub_type =
+		DMUB_CMD__VBIOS_DIG1_TRANSMITTER_CONTROL;
+	transmitter_control.transmitter_control.dig = *dig;
+
+	dc_dmub_srv_cmd_queue(dmcub, &transmitter_control.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
+
 static enum bp_result transmitter_control_v1_6(
 	struct bios_parser *bp,
 	struct bp_transmitter_control *cntl)
@@ -222,6 +261,11 @@ static enum bp_result transmitter_control_v1_6(
 		__func__, ps.param.symclk_10khz);
 	}
 
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		transmitter_control_dmcub(bp->base.ctx->dmub_srv, &ps.param);
+		return BP_RESULT_OK;
+	}
 
 /*color_depth not used any more, driver has deep color factor in the Phyclk*/
 	if (EXEC_BIOS_CMD_TABLE(dig1transmittercontrol, ps))
@@ -255,7 +299,20 @@ static void init_set_pixel_clock(struct bios_parser *bp)
 	}
 }
 
+static void set_pixel_clock_dmcub(
+		struct dc_dmub_srv *dmcub,
+		struct set_pixel_clock_parameter_v1_7 *clk)
+{
+	struct dmub_rb_cmd_set_pixel_clock pixel_clock = { 0 };
+
+	pixel_clock.header.type = DMUB_CMD__VBIOS;
+	pixel_clock.header.sub_type = DMUB_CMD__VBIOS_SET_PIXEL_CLOCK;
+	pixel_clock.pixel_clock.clk = *clk;
 
+	dc_dmub_srv_cmd_queue(dmcub, &pixel_clock.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
 
 static enum bp_result set_pixel_clock_v7(
 	struct bios_parser *bp,
@@ -331,6 +388,12 @@ static enum bp_result set_pixel_clock_v7(
 		if (bp_params->signal_type == SIGNAL_TYPE_DVI_DUAL_LINK)
 			clk.miscinfo |= PIXEL_CLOCK_V7_MISC_DVI_DUALLINK_EN;
 
+		if (bp->base.ctx->dc->ctx->dmub_srv &&
+		    bp->base.ctx->dc->debug.dmub_command_table) {
+			set_pixel_clock_dmcub(bp->base.ctx->dmub_srv, &clk);
+			return BP_RESULT_OK;
+		}
+
 		if (EXEC_BIOS_CMD_TABLE(setpixelclock, clk))
 			result = BP_RESULT_OK;
 	}
@@ -585,6 +648,21 @@ static void init_enable_disp_power_gating(
 	}
 }
 
+static void enable_disp_power_gating_dmcub(
+	struct dc_dmub_srv *dmcub,
+	struct enable_disp_power_gating_parameters_v2_1 *pwr)
+{
+	struct dmub_rb_cmd_enable_disp_power_gating power_gating;
+
+	power_gating.header.type = DMUB_CMD__VBIOS;
+	power_gating.header.sub_type = DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING;
+	power_gating.power_gating.pwr = *pwr;
+
+	dc_dmub_srv_cmd_queue(dmcub, &power_gating.header);
+	dc_dmub_srv_cmd_execute(dmcub);
+	dc_dmub_srv_wait_idle(dmcub);
+}
+
 static enum bp_result enable_disp_power_gating_v2_1(
 	struct bios_parser *bp,
 	enum controller_id crtc_id,
@@ -604,6 +682,13 @@ static enum bp_result enable_disp_power_gating_v2_1(
 	ps.param.enable =
 		bp->cmd_helper->disp_power_gating_action_to_atom(action);
 
+	if (bp->base.ctx->dc->ctx->dmub_srv &&
+	    bp->base.ctx->dc->debug.dmub_command_table) {
+		enable_disp_power_gating_dmcub(bp->base.ctx->dmub_srv,
+					       &ps.param);
+		return BP_RESULT_OK;
+	}
+
 	if (EXEC_BIOS_CMD_TABLE(enabledisppowergating, ps.param))
 		result = BP_RESULT_OK;
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index db153ddf0fee..7388c987c595 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -55,23 +55,19 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 	case DCE_VERSION_11_22:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
 #endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#endif
 	case DCE_VERSION_12_0:
 	case DCE_VERSION_12_1:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 26c6d735cdc7..4674aca8f206 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -1,5 +1,6 @@
 #
 # Copyright 2017 Advanced Micro Devices, Inc.
+# Copyright 2019 Raptor Engineering, LLC
 #
 # Permission is hereby granted, free of charge, to any person obtaining a
 # copy of this software and associated documentation files (the "Software"),
@@ -24,7 +25,13 @@
 # It calculates Bandwidth and Watermarks values for HW programming
 #
 
+ifdef CONFIG_X86
 calcs_ccflags := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+calcs_ccflags := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -32,6 +39,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -40,6 +48,7 @@ calcs_ccflags += -mpreferred-stack-boundary=4
 else
 calcs_ccflags += -msse2
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calcs.o := $(calcs_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_auto.o := $(calcs_ccflags)
@@ -47,7 +56,7 @@ CFLAGS_$(AMDDALPATH)/dc/calcs/dcn_calc_math.o := $(calcs_ccflags) -Wno-tautologi
 
 BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 BW_CALCS += dcn_calcs.o dcn_calc_math.o dcn_calc_auto.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
index a1d49256fab7..5d081c42e81b 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -154,14 +154,14 @@ static void calculate_bandwidth(
 
 
 
-	if (data->d0_underlay_mode == bw_def_none) { d0_underlay_enable = 0; }
-	else {
-		d0_underlay_enable = 1;
-	}
-	if (data->d1_underlay_mode == bw_def_none) { d1_underlay_enable = 0; }
-	else {
-		d1_underlay_enable = 1;
-	}
+	if (data->d0_underlay_mode == bw_def_none)
+		d0_underlay_enable = false;
+	else
+		d0_underlay_enable = true;
+	if (data->d1_underlay_mode == bw_def_none)
+		d1_underlay_enable = false;
+	else
+		d1_underlay_enable = true;
 	data->number_of_underlay_surfaces = d0_underlay_enable + d1_underlay_enable;
 	switch (data->underlay_surface_type) {
 	case bw_def_420:
@@ -286,8 +286,8 @@ static void calculate_bandwidth(
 	data->cursor_width_pixels[2] = bw_int_to_fixed(0);
 	data->cursor_width_pixels[3] = bw_int_to_fixed(0);
 	/* graphics surface parameters from spreadsheet*/
-	fbc_enabled = 0;
-	lpt_enabled = 0;
+	fbc_enabled = false;
+	lpt_enabled = false;
 	for (i = 4; i <= maximum_number_of_surfaces - 3; i++) {
 		if (i < data->number_of_displays + 4) {
 			if (i == 4 && data->d0_underlay_mode == bw_def_underlay_only) {
@@ -338,9 +338,9 @@ static void calculate_bandwidth(
 			data->access_one_channel_only[i] = 0;
 		}
 		if (data->fbc_en[i] == 1) {
-			fbc_enabled = 1;
+			fbc_enabled = true;
 			if (data->lpt_en[i] == 1) {
-				lpt_enabled = 1;
+				lpt_enabled = true;
 			}
 		}
 		data->cursor_width_pixels[i] = bw_int_to_fixed(vbios->cursor_width);
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 9b2cb57bf2ba..a27d84ca15a5 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -53,13 +54,9 @@
  * remain as-is as it provides us with a guarantee from HW that it is correct.
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 /* Defaults from spreadsheet rev#247.
  * RV2 delta: dram_clock_change_latency, max_num_dpp
  */
-#else
-/* Defaults from spreadsheet rev#247 */
-#endif
 const struct dcn_soc_bounding_box dcn10_soc_defaults = {
 		/* latencies */
 		.sr_exit_time = 17, /*us*/
@@ -626,7 +623,7 @@ static bool dcn_bw_apply_registry_override(struct dc *dc)
 {
 	bool updated = false;
 
-	kernel_fpu_begin();
+	DC_FP_START();
 	if ((int)(dc->dcn_soc->sr_exit_time * 1000) != dc->debug.sr_exit_time_ns
 			&& dc->debug.sr_exit_time_ns) {
 		updated = true;
@@ -662,7 +659,7 @@ static bool dcn_bw_apply_registry_override(struct dc *dc)
 		dc->dcn_soc->dram_clock_change_latency =
 				dc->debug.dram_clock_change_latency_ns / 1000.0;
 	}
-	kernel_fpu_end();
+	DC_FP_END();
 
 	return updated;
 }
@@ -708,8 +705,8 @@ static void hack_bounding_box(struct dcn_bw_internal_vars *v,
 
 unsigned int get_highest_allowed_voltage_level(uint32_t hw_internal_rev)
 {
-	/* for dali, the highest voltage level we want is 0 */
-	if (ASICREV_IS_DALI(hw_internal_rev))
+	/* for dali & pollock, the highest voltage level we want is 0 */
+	if (ASICREV_IS_POLLOCK(hw_internal_rev) || ASICREV_IS_DALI(hw_internal_rev))
 		return 0;
 
 	/* we are ok with all levels */
@@ -742,7 +739,7 @@ bool dcn_validate_bandwidth(
 		dcn_bw_sync_calcs_and_dml(dc);
 
 	memset(v, 0, sizeof(*v));
-	kernel_fpu_begin();
+	DC_FP_START();
 
 	v->sr_exit_time = dc->dcn_soc->sr_exit_time;
 	v->sr_enter_plus_exit_time = dc->dcn_soc->sr_enter_plus_exit_time;
@@ -1275,7 +1272,7 @@ bool dcn_validate_bandwidth(
 	bw_limit = dc->dcn_soc->percent_disp_bw_limit * v->fabric_and_dram_bandwidth_vmax0p9;
 	bw_limit_pass = (v->total_data_read_bandwidth / 1000.0) < bw_limit;
 
-	kernel_fpu_end();
+	DC_FP_END();
 
 	PERFORMANCE_TRACE_END();
 	BW_VAL_TRACE_FINISH();
@@ -1443,7 +1440,7 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	res = dm_pp_get_clock_levels_by_type_with_voltage(
 			ctx, DM_PP_CLOCK_TYPE_FCLK, &fclks);
 
-	kernel_fpu_begin();
+	DC_FP_START();
 
 	if (res)
 		res = verify_clock_values(&fclks);
@@ -1463,12 +1460,12 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	} else
 		BREAK_TO_DEBUGGER();
 
-	kernel_fpu_end();
+	DC_FP_END();
 
 	res = dm_pp_get_clock_levels_by_type_with_voltage(
 			ctx, DM_PP_CLOCK_TYPE_DCFCLK, &dcfclks);
 
-	kernel_fpu_begin();
+	DC_FP_START();
 
 	if (res)
 		res = verify_clock_values(&dcfclks);
@@ -1481,7 +1478,7 @@ void dcn_bw_update_from_pplib(struct dc *dc)
 	} else
 		BREAK_TO_DEBUGGER();
 
-	kernel_fpu_end();
+	DC_FP_END();
 }
 
 void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
@@ -1496,11 +1493,11 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	if (!pp || !pp->set_wm_ranges)
 		return;
 
-	kernel_fpu_begin();
+	DC_FP_START();
 	min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32;
 	min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000;
 	socclk_khz = dc->dcn_soc->socclk * 1000;
-	kernel_fpu_end();
+	DC_FP_END();
 
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
 	 * depending on DPM state they are in. And update BW MGR GFX Engine and
@@ -1551,7 +1548,7 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 
 void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 {
-	kernel_fpu_begin();
+	DC_FP_START();
 	DC_LOG_BANDWIDTH_CALCS("sr_exit_time: %f ns\n"
 			"sr_enter_plus_exit_time: %f ns\n"
 			"urgent_latency: %f ns\n"
@@ -1740,5 +1737,5 @@ void dcn_bw_sync_calcs_and_dml(struct dc *dc)
 	dc->dml.ip.bug_forcing_LC_req_same_size_fixed =
 		dc->dcn_ip->bug_forcing_luma_and_chroma_request_to_same_size_fixed == dcn_bw_yes;
 	dc->dml.ip.dcfclk_cstate_latency = dc->dcn_ip->dcfclk_cstate_latency;
-	kernel_fpu_end();
+	DC_FP_END();
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
index b864869cc7e3..3cd283195091 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile
@@ -63,7 +63,7 @@ CLK_MGR_DCE120 = dce120_clk_mgr.o
 AMD_DAL_CLK_MGR_DCE120 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dce120/,$(CLK_MGR_DCE120))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCE120)
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 ###############################################################################
 # DCN10
 ###############################################################################
@@ -72,9 +72,7 @@ CLK_MGR_DCN10 = rv1_clk_mgr.o rv1_clk_mgr_vbios_smu.o rv2_clk_mgr.o
 AMD_DAL_CLK_MGR_DCN10 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn10/,$(CLK_MGR_DCN10))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN10)
-endif
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
 ###############################################################################
 # DCN20
 ###############################################################################
@@ -83,9 +81,7 @@ CLK_MGR_DCN20 = dcn20_clk_mgr.o
 AMD_DAL_CLK_MGR_DCN20 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn20/,$(CLK_MGR_DCN20))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN20)
-endif
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 ###############################################################################
 # DCN21
 ###############################################################################
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index 8828dd9c3783..a78e5c74c79c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -37,9 +37,7 @@
 #include "dcn10/rv1_clk_mgr.h"
 #include "dcn10/rv2_clk_mgr.h"
 #include "dcn20/dcn20_clk_mgr.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/rn_clk_mgr.h"
-#endif
 
 
 int clk_mgr_helper_get_active_display_cnt(
@@ -134,14 +132,19 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			dce120_clk_mgr_construct(ctx, clk_mgr);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case FAMILY_RV:
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+		if (ASICREV_IS_DALI(asic_id.hw_internal_rev) ||
+				ASICREV_IS_POLLOCK(asic_id.hw_internal_rev)) {
+			/* TEMP: this check has to come before ASICREV_IS_RENOIR */
+			/* which also incorrectly returns true for Dali/Pollock*/
+			rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
+			break;
+		}
 		if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev)) {
 			rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 			break;
 		}
-#endif	/* DCN2_1 */
 		if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) {
 			rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu);
 			break;
@@ -152,13 +155,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 			break;
 		}
 		break;
-#endif	/* Family RV */
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case FAMILY_NV:
 		dcn20_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg);
 		break;
-#endif /* Family NV */
+#endif	/* Family RV and NV*/
 
 	default:
 		ASSERT(0); /* Unknown Asic */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
index a6c46e903ff9..d031bd3d3072 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
@@ -72,8 +72,8 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz)
 	struct clk_mgr_internal *clk_mgr_dce = TO_CLK_MGR_INTERNAL(clk_mgr_base);
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk_mgr_base->ctx->dc_bios;
-	struct dc *core_dc = clk_mgr_base->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr_base->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	int actual_clock = requested_clk_khz;
 	/* Prepare to program display clock*/
 	memset(&dce_clk_params, 0, sizeof(dce_clk_params));
@@ -110,7 +110,7 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz)
 
 	bp->funcs->set_dce_clock(bp, &dce_clk_params);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr_dce->dfs_bypass_disp_clk != actual_clock)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
@@ -126,8 +126,8 @@ int dce112_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_clk_khz)
 {
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk_mgr->base.ctx->dc_bios;
-	struct dc *core_dc = clk_mgr->base.ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr->base.ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	int actual_clock = requested_clk_khz;
 	/* Prepare to program display clock*/
 	memset(&dce_clk_params, 0, sizeof(dce_clk_params));
@@ -152,7 +152,7 @@ int dce112_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_clk_khz)
 		clk_mgr->cur_min_clks_state = DM_PP_CLOCKS_STATE_NOMINAL;
 
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr->dfs_bypass_disp_clk != actual_clock)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
index 1897e91c8ccb..97b7f32294fd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr_vbios_smu.c
@@ -88,8 +88,8 @@ int rv1_vbios_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, unsigned
 int rv1_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispclk_khz)
 {
 	int actual_dispclk_set_mhz = -1;
-	struct dc *core_dc = clk_mgr->base.ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr->base.ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	/*  Unit of SMU msg parameter is Mhz */
 	actual_dispclk_set_mhz = rv1_vbios_smu_send_msg_with_param(
@@ -100,7 +100,7 @@ int rv1_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_di
 	/* Actual dispclk set is returned in the parameter register */
 	actual_dispclk_set_mhz = REG_READ(MP1_SMN_C2PMSG_83) * 1000;
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr->dfs_bypass_disp_clk != actual_dispclk_set_mhz)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 25d7b7c6681c..495f01e9f2ca 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -27,6 +27,7 @@
 #include "clk_mgr_internal.h"
 
 #include "dce100/dce_clk_mgr.h"
+#include "dcn20_clk_mgr.h"
 #include "reg_helper.h"
 #include "core_types.h"
 #include "dm_helpers.h"
@@ -100,13 +101,13 @@ uint32_t dentist_get_did_from_divider(int divider)
 }
 
 void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
-		struct dc_state *context)
+		struct dc_state *context, bool safe_to_lower)
 {
 	int i;
 
 	clk_mgr->dccg->ref_dppclk = clk_mgr->base.clks.dppclk_khz;
 	for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) {
-		int dpp_inst, dppclk_khz;
+		int dpp_inst, dppclk_khz, prev_dppclk_khz;
 
 		/* Loop index will match dpp->inst if resource exists,
 		 * and we want to avoid dependency on dpp object
@@ -114,8 +115,12 @@ void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
 		dpp_inst = i;
 		dppclk_khz = context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
 
-		clk_mgr->dccg->funcs->update_dpp_dto(
-				clk_mgr->dccg, dpp_inst, dppclk_khz);
+		prev_dppclk_khz = clk_mgr->base.ctx->dc->current_state->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
+
+		if (safe_to_lower || prev_dppclk_khz < dppclk_khz) {
+			clk_mgr->dccg->funcs->update_dpp_dto(
+							clk_mgr->dccg, dpp_inst, dppclk_khz);
+		}
 	}
 }
 
@@ -161,6 +166,9 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 		dc->debug.force_clock_mode & 0x1) {
 		//this is from resume or boot up, if forced_clock cfg option used, we bypass program dispclk and DPPCLK, but need set them for S3.
 		force_reset = true;
+
+		dcn2_read_clocks_from_hw_dentist(clk_mgr_base);
+
 		//force_clock_mode 0x1:  force reset the clock even it is the same clock as long as it is in Passive level.
 	}
 	display_count = clk_mgr_helper_get_active_display_cnt(dc, context);
@@ -240,7 +248,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) {
 		if (dpp_clock_lowered) {
 			// if clock is being lowered, increase DTO before lowering refclk
-			dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+			dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 			dcn20_update_clocks_update_dentist(clk_mgr);
 		} else {
 			// if clock is being raised, increase refclk before lowering DTO
@@ -248,7 +256,7 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 				dcn20_update_clocks_update_dentist(clk_mgr);
 			// always update dtos unless clock is lowered and not safe to lower
 			if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
-				dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+				dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 		}
 	}
 
@@ -339,6 +347,32 @@ void dcn2_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 	}
 }
 
+
+void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	uint32_t dispclk_wdivider;
+	uint32_t dppclk_wdivider;
+	int disp_divider;
+	int dpp_divider;
+
+	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, &dispclk_wdivider);
+	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, &dppclk_wdivider);
+
+	disp_divider = dentist_get_divider_from_did(dispclk_wdivider);
+	dpp_divider = dentist_get_divider_from_did(dispclk_wdivider);
+
+	if (disp_divider && dpp_divider) {
+		/* Calculate the current DFS clock, in kHz.*/
+		clk_mgr_base->clks.dispclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+			* clk_mgr->base.dentist_vco_freq_khz) / disp_divider;
+
+		clk_mgr_base->clks.dppclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+				* clk_mgr->base.dentist_vco_freq_khz) / dpp_divider;
+	}
+
+}
+
 void dcn2_get_clock(struct clk_mgr *clk_mgr,
 		struct dc_state *context,
 			enum dc_clock_type clock_type,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
index c9fd824f3c23..0b9c045b0c8e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
@@ -34,7 +34,7 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr,
 			struct dc_state *context,
 			bool safe_to_lower);
 void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
-		struct dc_state *context);
+		struct dc_state *context, bool safe_to_lower);
 
 void dcn2_init_clocks(struct clk_mgr *clk_mgr);
 
@@ -51,4 +51,8 @@ void dcn2_get_clock(struct clk_mgr *clk_mgr,
 			struct dc_clock_config *clock_cfg);
 
 void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr);
+
+void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base);
+
+
 #endif //__DCN20_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 35c55e54eac0..7ae4c06232dd 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -59,14 +59,16 @@ int rn_get_active_display_cnt_wa(
 		struct dc_state *context)
 {
 	int i, display_count;
-	bool hdmi_present = false;
+	bool tmds_present = false;
 
 	display_count = 0;
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_stream_state *stream = context->streams[i];
 
-		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
-			hdmi_present = true;
+		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A ||
+				stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK ||
+				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+			tmds_present = true;
 	}
 
 	for (i = 0; i < dc->link_count; i++) {
@@ -85,7 +87,7 @@ int rn_get_active_display_cnt_wa(
 	}
 
 	/* WA for hang on HDMI after display off back back on*/
-	if (display_count == 0 && hdmi_present)
+	if (display_count == 0 && tmds_present)
 		display_count = 1;
 
 	return display_count;
@@ -164,16 +166,16 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 	}
 
 	if (dpp_clock_lowered) {
-		// if clock is being lowered, increase DTO before lowering refclk
-		dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+		// increase per DPP DTO before lowering global dppclk
+		dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 		rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz);
 	} else {
-		// if clock is being raised, increase refclk before lowering DTO
+		// increase global DPPCLK before lowering per DPP DTO
 		if (update_dppclk || update_dispclk)
 			rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz);
 		// always update dtos unless clock is lowered and not safe to lower
 		if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
-			dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+			dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower);
 	}
 
 	if (update_dispclk &&
@@ -409,7 +411,7 @@ void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_smu_wm_ra
 			continue;
 
 		ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst;
-		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;;
+		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;
 		/* We will not select WM based on dcfclk, so leave it as unconstrained */
 		ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
 		ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
@@ -578,33 +580,33 @@ struct wm_table lpddr4_wm_table = {
 		{
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 5.32,
+			.sr_enter_plus_exit_time_us = 6.38,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 9.82,
+			.sr_enter_plus_exit_time_us = 11.196,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 9.89,
+			.sr_enter_plus_exit_time_us = 11.24,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 23.84,
-			.sr_exit_time_us = 12.5,
-			.sr_enter_plus_exit_time_us = 17.0,
+			.pstate_latency_us = 11.65333,
+			.sr_exit_time_us = 9.748,
+			.sr_enter_plus_exit_time_us = 11.102,
 			.valid = true,
 		},
 	}
@@ -691,7 +693,6 @@ void rn_clk_mgr_construct(
 {
 	struct dc_debug_options *debug = &ctx->dc->debug;
 	struct dpm_clocks clock_table = { 0 };
-	struct clk_state_registers_and_bypass s = { 0 };
 
 	clk_mgr->base.ctx = ctx;
 	clk_mgr->base.funcs = &dcn21_funcs;
@@ -711,7 +712,6 @@ void rn_clk_mgr_construct(
 	if (IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) {
 		dcn21_funcs.update_clocks = dcn2_update_clocks_fpga;
 		clk_mgr->base.dentist_vco_freq_khz = 3600000;
-		clk_mgr->base.dprefclk_khz = 600000;
 	} else {
 		struct clk_log_info log_info = {0};
 
@@ -722,24 +722,16 @@ void rn_clk_mgr_construct(
 		if (clk_mgr->base.dentist_vco_freq_khz == 0)
 			clk_mgr->base.dentist_vco_freq_khz = 3600000;
 
-		rn_dump_clk_registers(&s, &clk_mgr->base, &log_info);
-		/* Convert dprefclk units from MHz to KHz */
-		/* Value already divided by 10, some resolution lost */
-		clk_mgr->base.dprefclk_khz = s.dprefclk * 1000;
-
-		/* in case we don't get a value from the register, use default */
-		if (clk_mgr->base.dprefclk_khz == 0) {
-			ASSERT(clk_mgr->base.dprefclk_khz == 600000);
-			clk_mgr->base.dprefclk_khz = 600000;
-		}
-
 		if (ctx->dc_bios->integrated_info->memory_type == LpDdr4MemType) {
 			rn_bw_params.wm_table = lpddr4_wm_table;
 		} else {
 			rn_bw_params.wm_table = ddr4_wm_table;
 		}
+		/* Saved clocks configured at boot for debug purposes */
+		rn_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info);
 	}
 
+	clk_mgr->base.dprefclk_khz = 600000;
 	dce_clock_read_ss_info(clk_mgr);
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
index cb7c0e8b7e1b..6878aedf1d3e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
@@ -82,8 +82,8 @@ int rn_vbios_smu_get_smu_version(struct clk_mgr_internal *clk_mgr)
 int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dispclk_khz)
 {
 	int actual_dispclk_set_mhz = -1;
-	struct dc *core_dc = clk_mgr->base.ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc *dc = clk_mgr->base.ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	/*  Unit of SMU msg parameter is Mhz */
 	actual_dispclk_set_mhz = rn_vbios_smu_send_msg_with_param(
@@ -91,7 +91,7 @@ int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dis
 			VBIOSSMC_MSG_SetDispclkFreq,
 			requested_dispclk_khz / 1000);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 			if (clk_mgr->dfs_bypass_disp_clk != actual_dispclk_set_mhz)
 				dmcu->funcs->set_psr_wait_loop(dmcu,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 32f31bf91915..6c797fac189d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -58,21 +58,21 @@
 #include "hubp.h"
 
 #include "dc_link_dp.h"
+#include "dc_dmub_srv.h"
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #include "vm_helper.h"
-#endif
 
 #include "dce/dce_i2c.h"
 
+#define CTX \
+	dc->ctx
+
 #define DC_LOGGER \
 	dc->ctx->logger
 
-const static char DC_BUILD_ID[] = "production-build";
+static const char DC_BUILD_ID[] = "production-build";
 
 /**
  * DOC: Overview
@@ -287,7 +287,6 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 		struct pipe_ctx *pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe->stream == stream && pipe->stream_res.tg) {
-			pipe->stream->adjust = *adjust;
 			dc->hwss.set_drr(&pipe,
 					1,
 					adjust->v_total_min,
@@ -511,10 +510,10 @@ bool dc_stream_program_csc_matrix(struct dc *dc, struct dc_stream_state *stream)
 	return ret;
 }
 
-void dc_stream_set_static_screen_events(struct dc *dc,
+void dc_stream_set_static_screen_params(struct dc *dc,
 		struct dc_stream_state **streams,
 		int num_streams,
-		const struct dc_static_screen_events *events)
+		const struct dc_static_screen_params *params)
 {
 	int i = 0;
 	int j = 0;
@@ -533,10 +532,10 @@ void dc_stream_set_static_screen_events(struct dc *dc,
 		}
 	}
 
-	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events);
+	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, params);
 }
 
-static void destruct(struct dc *dc)
+static void dc_destruct(struct dc *dc)
 {
 	if (dc->current_state) {
 		dc_release_state(dc->current_state);
@@ -569,7 +568,7 @@ static void destruct(struct dc *dc)
 	kfree(dc->bw_dceip);
 	dc->bw_dceip = NULL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	kfree(dc->dcn_soc);
 	dc->dcn_soc = NULL;
 
@@ -577,28 +576,58 @@ static void destruct(struct dc *dc)
 	dc->dcn_ip = NULL;
 
 #endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	kfree(dc->vm_helper);
 	dc->vm_helper = NULL;
 
-#endif
 }
 
-static bool construct(struct dc *dc,
+static bool dc_construct_ctx(struct dc *dc,
+		const struct dc_init_data *init_params)
+{
+	struct dc_context *dc_ctx;
+	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
+
+	dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL);
+	if (!dc_ctx)
+		return false;
+
+	dc_ctx->cgs_device = init_params->cgs_device;
+	dc_ctx->driver_context = init_params->driver;
+	dc_ctx->dc = dc;
+	dc_ctx->asic_id = init_params->asic_id;
+	dc_ctx->dc_sink_id_count = 0;
+	dc_ctx->dc_stream_id_count = 0;
+	dc_ctx->dce_environment = init_params->dce_environment;
+
+	/* Create logger */
+
+	dc_version = resource_parse_asic_id(init_params->asic_id);
+	dc_ctx->dce_version = dc_version;
+
+	dc_ctx->perf_trace = dc_perf_trace_create();
+	if (!dc_ctx->perf_trace) {
+		ASSERT_CRITICAL(false);
+		return false;
+	}
+
+	dc->ctx = dc_ctx;
+
+	return true;
+}
+
+static bool dc_construct(struct dc *dc,
 		const struct dc_init_data *init_params)
 {
 	struct dc_context *dc_ctx;
 	struct bw_calcs_dceip *dc_dceip;
 	struct bw_calcs_vbios *dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 #endif
 
-	enum dce_version dc_version = DCE_VERSION_UNKNOWN;
 	dc->config = init_params->flags;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	// Allocate memory for the vm_helper
 	dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL);
 	if (!dc->vm_helper) {
@@ -606,7 +635,6 @@ static bool construct(struct dc *dc,
 		goto fail;
 	}
 
-#endif
 	memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides));
 
 	dc_dceip = kzalloc(sizeof(*dc_dceip), GFP_KERNEL);
@@ -624,7 +652,7 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->bw_vbios = dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	dcn_soc = kzalloc(sizeof(*dcn_soc), GFP_KERNEL);
 	if (!dcn_soc) {
 		dm_error("%s: failed to create dcn_soc\n", __func__);
@@ -640,31 +668,15 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->dcn_ip = dcn_ip;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	dc->soc_bounding_box = init_params->soc_bounding_box;
 #endif
-#endif
 
-	dc_ctx = kzalloc(sizeof(*dc_ctx), GFP_KERNEL);
-	if (!dc_ctx) {
+	if (!dc_construct_ctx(dc, init_params)) {
 		dm_error("%s: failed to create ctx\n", __func__);
 		goto fail;
 	}
 
-	dc_ctx->cgs_device = init_params->cgs_device;
-	dc_ctx->driver_context = init_params->driver;
-	dc_ctx->dc = dc;
-	dc_ctx->asic_id = init_params->asic_id;
-	dc_ctx->dc_sink_id_count = 0;
-	dc_ctx->dc_stream_id_count = 0;
-	dc->ctx = dc_ctx;
-
-	/* Create logger */
-
-	dc_ctx->dce_environment = init_params->dce_environment;
-
-	dc_version = resource_parse_asic_id(init_params->asic_id);
-	dc_ctx->dce_version = dc_version;
+        dc_ctx = dc->ctx;
 
 	/* Resource should construct all asic specific resources.
 	 * This should be the only place where we need to parse the asic id
@@ -679,7 +691,7 @@ static bool construct(struct dc *dc,
 		bp_init_data.bios = init_params->asic_id.atombios_base_address;
 
 		dc_ctx->dc_bios = dal_bios_parser_create(
-				&bp_init_data, dc_version);
+				&bp_init_data, dc_ctx->dce_version);
 
 		if (!dc_ctx->dc_bios) {
 			ASSERT_CRITICAL(false);
@@ -687,17 +699,13 @@ static bool construct(struct dc *dc,
 		}
 
 		dc_ctx->created_bios = true;
-		}
-
-	dc_ctx->perf_trace = dc_perf_trace_create();
-	if (!dc_ctx->perf_trace) {
-		ASSERT_CRITICAL(false);
-		goto fail;
 	}
 
+
+
 	/* Create GPIO service */
 	dc_ctx->gpio_service = dal_gpio_service_create(
-			dc_version,
+			dc_ctx->dce_version,
 			dc_ctx->dce_environment,
 			dc_ctx);
 
@@ -706,7 +714,7 @@ static bool construct(struct dc *dc,
 		goto fail;
 	}
 
-	dc->res_pool = dc_create_resource_pool(dc, init_params, dc_version);
+	dc->res_pool = dc_create_resource_pool(dc, init_params, dc_ctx->dce_version);
 	if (!dc->res_pool)
 		goto fail;
 
@@ -714,10 +722,8 @@ static bool construct(struct dc *dc,
 	if (!dc->clk_mgr)
 		goto fail;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	if (dc->res_pool->funcs->update_bw_bounding_box)
 		dc->res_pool->funcs->update_bw_bounding_box(dc, dc->clk_mgr->bw_params);
-#endif
 
 	/* Creation of current_state must occur after dc->dml
 	 * is initialized in dc_create_resource_pool because
@@ -739,12 +745,9 @@ static bool construct(struct dc *dc,
 	return true;
 
 fail:
-
-	destruct(dc);
 	return false;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static bool disable_all_writeback_pipes_for_stream(
 		const struct dc *dc,
 		struct dc_stream_state *stream,
@@ -757,7 +760,6 @@ static bool disable_all_writeback_pipes_for_stream(
 
 	return true;
 }
-#endif
 
 static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 {
@@ -783,16 +785,12 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 		}
 		if (should_disable && old_stream) {
 			dc_rem_all_planes_for_stream(dc, old_stream, dangling_context);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 			disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context);
-#endif
 			if (dc->hwss.apply_ctx_for_surface)
 				dc->hwss.apply_ctx_for_surface(dc, old_stream, 0, dangling_context);
 		}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (dc->hwss.program_front_end_for_ctx)
 			dc->hwss.program_front_end_for_ctx(dc, dangling_context);
-#endif
 	}
 
 	current_ctx = dc->current_state;
@@ -800,6 +798,33 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 	dc_release_state(current_ctx);
 }
 
+static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context)
+{
+	int i;
+	int count = 0;
+	struct pipe_ctx *pipe;
+	PERF_TRACE();
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (!pipe->plane_state)
+			continue;
+
+		/* Timeout 100 ms */
+		while (count < 100000) {
+			/* Must set to false to start with, due to OR in update function */
+			pipe->plane_state->status.is_flip_pending = false;
+			dc->hwss.update_pending_status(pipe);
+			if (!pipe->plane_state->status.is_flip_pending)
+				break;
+			udelay(1);
+			count++;
+		}
+		ASSERT(!pipe->plane_state->status.is_flip_pending);
+	}
+	PERF_TRACE();
+}
+
 /*******************************************************************************
  * Public functions
  ******************************************************************************/
@@ -812,26 +837,38 @@ struct dc *dc_create(const struct dc_init_data *init_params)
 	if (NULL == dc)
 		goto alloc_fail;
 
-	if (false == construct(dc, init_params))
-		goto construct_fail;
+	if (init_params->dce_environment == DCE_ENV_VIRTUAL_HW) {
+		if (false == dc_construct_ctx(dc, init_params)) {
+			dc_destruct(dc);
+			goto construct_fail;
+		}
+	} else {
+		if (false == dc_construct(dc, init_params)) {
+			dc_destruct(dc);
+			goto construct_fail;
+		}
+
+		full_pipe_count = dc->res_pool->pipe_count;
+		if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE)
+			full_pipe_count--;
+		dc->caps.max_streams = min(
+				full_pipe_count,
+				dc->res_pool->stream_enc_count);
 
-	full_pipe_count = dc->res_pool->pipe_count;
-	if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE)
-		full_pipe_count--;
-	dc->caps.max_streams = min(
-			full_pipe_count,
-			dc->res_pool->stream_enc_count);
+		dc->optimize_seamless_boot_streams = 0;
+		dc->caps.max_links = dc->link_count;
+		dc->caps.max_audios = dc->res_pool->audio_count;
+		dc->caps.linear_pitch_alignment = 64;
 
-	dc->caps.max_links = dc->link_count;
-	dc->caps.max_audios = dc->res_pool->audio_count;
-	dc->caps.linear_pitch_alignment = 64;
+		dc->caps.max_dp_protocol_version = DP_VERSION_1_4;
+
+		if (dc->res_pool->dmcu != NULL)
+			dc->versions.dmcu_version = dc->res_pool->dmcu->dmcu_version;
+	}
 
 	/* Populate versioning information */
 	dc->versions.dc_ver = DC_VER;
 
-	if (dc->res_pool->dmcu != NULL)
-		dc->versions.dmcu_version = dc->res_pool->dmcu->dmcu_version;
-
 	dc->build_id = DC_BUILD_ID;
 
 	DC_LOG_DC("Display Core initialized\n");
@@ -849,7 +886,8 @@ alloc_fail:
 
 void dc_hardware_init(struct dc *dc)
 {
-	dc->hwss.init_hw(dc);
+	if (dc->ctx->dce_environment != DCE_ENV_VIRTUAL_HW)
+		dc->hwss.init_hw(dc);
 }
 
 void dc_init_callbacks(struct dc *dc,
@@ -869,7 +907,7 @@ void dc_deinit_callbacks(struct dc *dc)
 
 void dc_destroy(struct dc **dc)
 {
-	destruct(*dc);
+	dc_destruct(*dc);
 	kfree(*dc);
 	*dc = NULL;
 }
@@ -1163,10 +1201,10 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	for (i = 0; i < context->stream_count; i++) {
 		if (context->streams[i]->apply_seamless_boot_optimization)
-			dc->optimize_seamless_boot = true;
+			dc->optimize_seamless_boot_streams++;
 	}
 
-	if (!dc->optimize_seamless_boot)
+	if (dc->optimize_seamless_boot_streams == 0)
 		dc->hwss.prepare_bandwidth(dc, context);
 
 	/* re-program planes for existing stream, in case we need to
@@ -1182,10 +1220,6 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 				context->stream_status[i].plane_count,
 				context); /* use new pipe config in new context */
 		}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	if (dc->hwss.program_front_end_for_ctx)
-		dc->hwss.program_front_end_for_ctx(dc, context);
-#endif
 
 	/* Program hardware */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -1204,10 +1238,8 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	}
 
 	/* Program all planes within new context*/
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (dc->hwss.program_front_end_for_ctx)
 		dc->hwss.program_front_end_for_ctx(dc, context);
-#endif
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_link *link = context->streams[i]->link;
 
@@ -1245,6 +1277,13 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
+	if (dc->optimize_seamless_boot_streams == 0) {
+		/* Must wait for no flips to be pending before doing optimize bw */
+		wait_for_no_pipes_pending(dc, context);
+		/* pplib is notified if disp_num changed */
+		dc->hwss.optimize_bandwidth(dc, context);
+	}
+
 	for (i = 0; i < context->stream_count; i++)
 		context->streams[i]->mode_changed = false;
 
@@ -1279,12 +1318,18 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	return (result == DC_OK);
 }
 
+bool dc_is_hw_initialized(struct dc *dc)
+{
+	struct dc_bios *dcb = dc->ctx->dc_bios;
+	return dcb->funcs->is_accelerated_mode(dcb);
+}
+
 bool dc_post_update_surfaces_to_stream(struct dc *dc)
 {
 	int i;
 	struct dc_state *context = dc->current_state;
 
-	if (!dc->optimized_required || dc->optimize_seamless_boot)
+	if (!dc->optimized_required || dc->optimize_seamless_boot_streams > 0)
 		return true;
 
 	post_surface_trace(dc);
@@ -1313,7 +1358,7 @@ struct dc_state *dc_create_state(struct dc *dc)
 	 * initialize and obtain IP and SOC the base DML instance from DC is
 	 * initially copied into every context
 	 */
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	memcpy(&context->bw_ctx.dml, &dc->dml, sizeof(struct display_mode_lib));
 #endif
 
@@ -1486,11 +1531,6 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa
 		elevate_update_type(&update_type, UPDATE_TYPE_MED);
 	}
 
-	if (u->plane_info->sdr_white_level != u->surface->sdr_white_level) {
-		update_flags->bits.sdr_white_level = 1;
-		elevate_update_type(&update_type, UPDATE_TYPE_MED);
-	}
-
 	if (u->plane_info->dcc.enable != u->surface->dcc.enable
 			|| u->plane_info->dcc.independent_64b_blks != u->surface->dcc.independent_64b_blks
 			|| u->plane_info->dcc.meta_pitch != u->surface->dcc.meta_pitch) {
@@ -1508,7 +1548,6 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa
 	}
 
 	if (u->plane_info->plane_size.surface_pitch != u->surface->plane_size.surface_pitch
-			|| u->plane_info->plane_size.surface_pitch != u->surface->plane_size.surface_pitch
 			|| u->plane_info->plane_size.chroma_pitch != u->surface->plane_size.chroma_pitch) {
 		update_flags->bits.plane_size_change = 1;
 		elevate_update_type(&update_type, UPDATE_TYPE_MED);
@@ -1547,7 +1586,10 @@ static enum surface_update_type get_scaling_info_update_type(
 	if (u->scaling_info->clip_rect.width != u->surface->clip_rect.width
 			|| u->scaling_info->clip_rect.height != u->surface->clip_rect.height
 			|| u->scaling_info->dst_rect.width != u->surface->dst_rect.width
-			|| u->scaling_info->dst_rect.height != u->surface->dst_rect.height) {
+			|| u->scaling_info->dst_rect.height != u->surface->dst_rect.height
+			|| u->scaling_info->scaling_quality.integer_scaling !=
+				u->surface->scaling_quality.integer_scaling
+			) {
 		update_flags->bits.scaling_change = 1;
 
 		if ((u->scaling_info->dst_rect.width < u->surface->dst_rect.width
@@ -1563,7 +1605,7 @@ static enum surface_update_type get_scaling_info_update_type(
 
 		update_flags->bits.scaling_change = 1;
 		if (u->scaling_info->src_rect.width > u->surface->src_rect.width
-				&& u->scaling_info->src_rect.height > u->surface->src_rect.height)
+				|| u->scaling_info->src_rect.height > u->surface->src_rect.height)
 			/* Making src rect bigger requires a bandwidth change */
 			update_flags->bits.clock_change = 1;
 	}
@@ -1577,11 +1619,11 @@ static enum surface_update_type get_scaling_info_update_type(
 		update_flags->bits.position_change = 1;
 
 	if (update_flags->bits.clock_change
-			|| update_flags->bits.bandwidth_change)
+			|| update_flags->bits.bandwidth_change
+			|| update_flags->bits.scaling_change)
 		return UPDATE_TYPE_FULL;
 
-	if (update_flags->bits.scaling_change
-			|| update_flags->bits.position_change)
+	if (update_flags->bits.position_change)
 		return UPDATE_TYPE_MED;
 
 	return UPDATE_TYPE_FAST;
@@ -1635,6 +1677,12 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 			update_flags->bits.gamma_change = 1;
 	}
 
+	if (u->hdr_mult.value)
+		if (u->hdr_mult.value != u->surface->hdr_mult.value) {
+			update_flags->bits.hdr_mult = 1;
+			elevate_update_type(&overall_type, UPDATE_TYPE_MED);
+		}
+
 	if (update_flags->bits.in_transfer_func_change) {
 		type = UPDATE_TYPE_MED;
 		elevate_update_type(&overall_type, type);
@@ -1668,7 +1716,8 @@ static enum surface_update_type check_update_surfaces_for_stream(
 		union stream_update_flags *su_flags = &stream_update->stream->update_flags;
 
 		if ((stream_update->src.height != 0 && stream_update->src.width != 0) ||
-				(stream_update->dst.height != 0 && stream_update->dst.width != 0))
+			(stream_update->dst.height != 0 && stream_update->dst.width != 0) ||
+			stream_update->integer_scaling_update)
 			su_flags->bits.scaling = 1;
 
 		if (stream_update->out_transfer_func)
@@ -1683,15 +1732,16 @@ static enum surface_update_type check_update_surfaces_for_stream(
 		if (stream_update->gamut_remap)
 			su_flags->bits.gamut_remap = 1;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (stream_update->wb_update)
 			su_flags->bits.wb_update = 1;
-#endif
 		if (su_flags->raw != 0)
 			overall_type = UPDATE_TYPE_FULL;
 
 		if (stream_update->output_csc_transform || stream_update->output_color_space)
 			su_flags->bits.out_csc = 1;
+
+		if (stream_update->dsc_config)
+			overall_type = UPDATE_TYPE_FULL;
 	}
 
 	for (i = 0 ; i < surface_count; i++) {
@@ -1817,8 +1867,6 @@ static void copy_surface_update_to_plane(
 				srf_update->plane_info->global_alpha_value;
 		surface->dcc =
 				srf_update->plane_info->dcc;
-		surface->sdr_white_level =
-				srf_update->plane_info->sdr_white_level;
 		surface->layer_index =
 				srf_update->plane_info->layer_index;
 	}
@@ -1851,7 +1899,6 @@ static void copy_surface_update_to_plane(
 			sizeof(struct dc_transfer_func_distributed_points));
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (srf_update->func_shaper &&
 			(surface->in_shaper_func !=
 			srf_update->func_shaper))
@@ -1864,13 +1911,16 @@ static void copy_surface_update_to_plane(
 		memcpy(surface->lut3d_func, srf_update->lut3d_func,
 		sizeof(*surface->lut3d_func));
 
+	if (srf_update->hdr_mult.value)
+		surface->hdr_mult =
+				srf_update->hdr_mult;
+
 	if (srf_update->blend_tf &&
 			(surface->blend_tf !=
 			srf_update->blend_tf))
 		memcpy(surface->blend_tf, srf_update->blend_tf,
 		sizeof(*surface->blend_tf));
 
-#endif
 	if (srf_update->input_csc_color_matrix)
 		surface->input_csc_color_matrix =
 			*srf_update->input_csc_color_matrix;
@@ -1883,8 +1933,10 @@ static void copy_surface_update_to_plane(
 static void copy_stream_update_to_stream(struct dc *dc,
 					 struct dc_state *context,
 					 struct dc_stream_state *stream,
-					 const struct dc_stream_update *update)
+					 struct dc_stream_update *update)
 {
+	struct dc_context *dc_ctx = dc->ctx;
+
 	if (update == NULL || stream == NULL)
 		return;
 
@@ -1945,7 +1997,6 @@ static void copy_stream_update_to_stream(struct dc *dc,
 
 	if (update->dither_option)
 		stream->dither_option = *update->dither_option;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* update current stream with writeback info */
 	if (update->wb_update) {
 		int i;
@@ -1956,23 +2007,32 @@ static void copy_stream_update_to_stream(struct dc *dc,
 			stream->writeback_info[i] =
 				update->wb_update->writeback_info[i];
 	}
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 	if (update->dsc_config) {
 		struct dc_dsc_config old_dsc_cfg = stream->timing.dsc_cfg;
 		uint32_t old_dsc_enabled = stream->timing.flags.DSC;
 		uint32_t enable_dsc = (update->dsc_config->num_slices_h != 0 &&
 				       update->dsc_config->num_slices_v != 0);
 
-		stream->timing.dsc_cfg = *update->dsc_config;
-		stream->timing.flags.DSC = enable_dsc;
-		if (!dc->res_pool->funcs->validate_bandwidth(dc, context,
-							     true)) {
-			stream->timing.dsc_cfg = old_dsc_cfg;
-			stream->timing.flags.DSC = old_dsc_enabled;
+		/* Use temporarry context for validating new DSC config */
+		struct dc_state *dsc_validate_context = dc_create_state(dc);
+
+		if (dsc_validate_context) {
+			dc_resource_state_copy_construct(dc->current_state, dsc_validate_context);
+
+			stream->timing.dsc_cfg = *update->dsc_config;
+			stream->timing.flags.DSC = enable_dsc;
+			if (!dc->res_pool->funcs->validate_bandwidth(dc, dsc_validate_context, true)) {
+				stream->timing.dsc_cfg = old_dsc_cfg;
+				stream->timing.flags.DSC = old_dsc_enabled;
+				update->dsc_config = NULL;
+			}
+
+			dc_release_state(dsc_validate_context);
+		} else {
+			DC_ERROR("Failed to allocate new validate context for DSC change\n");
+			update->dsc_config = NULL;
 		}
 	}
-#endif
 }
 
 static void commit_planes_do_stream_update(struct dc *dc,
@@ -1992,11 +2052,11 @@ static void commit_planes_do_stream_update(struct dc *dc,
 
 			if (stream_update->periodic_interrupt0 &&
 					dc->hwss.setup_periodic_interrupt)
-				dc->hwss.setup_periodic_interrupt(pipe_ctx, VLINE0);
+				dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE0);
 
 			if (stream_update->periodic_interrupt1 &&
 					dc->hwss.setup_periodic_interrupt)
-				dc->hwss.setup_periodic_interrupt(pipe_ctx, VLINE1);
+				dc->hwss.setup_periodic_interrupt(dc, pipe_ctx, VLINE1);
 
 			if ((stream_update->hdr_static_metadata && !stream->use_dynamic_meta) ||
 					stream_update->vrr_infopacket ||
@@ -2006,6 +2066,12 @@ static void commit_planes_do_stream_update(struct dc *dc,
 				dc->hwss.update_info_frame(pipe_ctx);
 			}
 
+			if (stream_update->hdr_static_metadata &&
+					stream->use_dynamic_meta &&
+					dc->hwss.set_dmdata_attributes &&
+					pipe_ctx->stream->dmdata_address.quad_part != 0)
+				dc->hwss.set_dmdata_attributes(pipe_ctx);
+
 			if (stream_update->gamut_remap)
 				dc_stream_set_gamut_remap(dc, stream);
 
@@ -2013,31 +2079,25 @@ static void commit_planes_do_stream_update(struct dc *dc,
 				dc_stream_program_csc_matrix(dc, stream);
 
 			if (stream_update->dither_option) {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 				struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe;
-#endif
 				resource_build_bit_depth_reduction_params(pipe_ctx->stream,
 									&pipe_ctx->stream->bit_depth_params);
 				pipe_ctx->stream_res.opp->funcs->opp_program_fmt(pipe_ctx->stream_res.opp,
 						&stream->bit_depth_params,
 						&stream->clamping);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 				while (odm_pipe) {
 					odm_pipe->stream_res.opp->funcs->opp_program_fmt(odm_pipe->stream_res.opp,
 							&stream->bit_depth_params,
 							&stream->clamping);
 					odm_pipe = odm_pipe->next_odm_pipe;
 				}
-#endif
 			}
 
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 			if (stream_update->dsc_config && dc->hwss.pipe_control_lock_global) {
 				dc->hwss.pipe_control_lock_global(dc, pipe_ctx, true);
 				dp_update_dsc_config(pipe_ctx);
 				dc->hwss.pipe_control_lock_global(dc, pipe_ctx, false);
 			}
-#endif
 			/* Full fe update*/
 			if (update_type == UPDATE_TYPE_FAST)
 				continue;
@@ -2053,7 +2113,7 @@ static void commit_planes_do_stream_update(struct dc *dc,
 
 					dc->hwss.optimize_bandwidth(dc, dc->current_state);
 				} else {
-					if (!dc->optimize_seamless_boot)
+					if (dc->optimize_seamless_boot_streams == 0)
 						dc->hwss.prepare_bandwidth(dc, dc->current_state);
 
 					core_link_enable_stream(dc->current_state, pipe_ctx);
@@ -2094,7 +2154,7 @@ static void commit_planes_for_stream(struct dc *dc,
 	int i, j;
 	struct pipe_ctx *top_pipe_to_program = NULL;
 
-	if (dc->optimize_seamless_boot && surface_count > 0) {
+	if (dc->optimize_seamless_boot_streams > 0 && surface_count > 0) {
 		/* Optimize seamless boot flag keeps clocks and watermarks high until
 		 * first flip. After first flip, optimization is required to lower
 		 * bandwidth. Important to note that it is expected UEFI will
@@ -2103,12 +2163,14 @@ static void commit_planes_for_stream(struct dc *dc,
 		 */
 		if (stream->apply_seamless_boot_optimization) {
 			stream->apply_seamless_boot_optimization = false;
-			dc->optimize_seamless_boot = false;
-			dc->optimized_required = true;
+			dc->optimize_seamless_boot_streams--;
+
+			if (dc->optimize_seamless_boot_streams == 0)
+				dc->optimized_required = true;
 		}
 	}
 
-	if (update_type == UPDATE_TYPE_FULL && !dc->optimize_seamless_boot) {
+	if (update_type == UPDATE_TYPE_FULL && dc->optimize_seamless_boot_streams == 0) {
 		dc->hwss.prepare_bandwidth(dc, context);
 		context_clock_trace(dc, context);
 	}
@@ -2124,15 +2186,12 @@ static void commit_planes_for_stream(struct dc *dc,
 		 */
 		if (dc->hwss.apply_ctx_for_surface)
 			dc->hwss.apply_ctx_for_surface(dc, stream, 0, context);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (dc->hwss.program_front_end_for_ctx)
 			dc->hwss.program_front_end_for_ctx(dc, context);
-#endif
 
 		return;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (!IS_DIAG_DC(dc->ctx->dce_environment)) {
 		for (i = 0; i < surface_count; i++) {
 			struct dc_plane_state *plane_state = srf_updates[i].surface;
@@ -2154,7 +2213,6 @@ static void commit_planes_for_stream(struct dc *dc,
 			}
 		}
 	}
-#endif
 
 	// Update Type FULL, Surface updates
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
@@ -2175,7 +2233,6 @@ static void commit_planes_for_stream(struct dc *dc,
 			if (update_type == UPDATE_TYPE_FAST)
 				continue;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 			ASSERT(!pipe_ctx->plane_state->triplebuffer_flips);
 
 			if (dc->hwss.program_triplebuffer != NULL &&
@@ -2184,7 +2241,6 @@ static void commit_planes_for_stream(struct dc *dc,
 				dc->hwss.program_triplebuffer(
 					dc, pipe_ctx, pipe_ctx->plane_state->triplebuffer_flips);
 			}
-#endif
 			stream_status =
 				stream_get_status(context, pipe_ctx->stream);
 
@@ -2193,10 +2249,24 @@ static void commit_planes_for_stream(struct dc *dc,
 					dc, pipe_ctx->stream, stream_status->plane_count, context);
 		}
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	if (dc->hwss.program_front_end_for_ctx && update_type != UPDATE_TYPE_FAST)
+	if (dc->hwss.program_front_end_for_ctx && update_type != UPDATE_TYPE_FAST) {
 		dc->hwss.program_front_end_for_ctx(dc, context);
+#ifdef CONFIG_DRM_AMD_DC_DCN
+		if (dc->debug.validate_dml_output) {
+			for (i = 0; i < dc->res_pool->pipe_count; i++) {
+				struct pipe_ctx cur_pipe = context->res_ctx.pipe_ctx[i];
+				if (cur_pipe.stream == NULL)
+					continue;
+
+				cur_pipe.plane_res.hubp->funcs->validate_dml_output(
+						cur_pipe.plane_res.hubp, dc->ctx,
+						&context->res_ctx.pipe_ctx[i].rq_regs,
+						&context->res_ctx.pipe_ctx[i].dlg_regs,
+						&context->res_ctx.pipe_ctx[i].ttu_regs);
+			}
+		}
 #endif
+	}
 
 	// Update Type FAST, Surface updates
 	if (update_type == UPDATE_TYPE_FAST) {
@@ -2206,7 +2276,6 @@ static void commit_planes_for_stream(struct dc *dc,
 		 */
 		dc->hwss.pipe_control_lock(dc, top_pipe_to_program, true);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (dc->hwss.set_flip_control_gsl)
 			for (i = 0; i < surface_count; i++) {
 				struct dc_plane_state *plane_state = srf_updates[i].surface;
@@ -2225,7 +2294,6 @@ static void commit_planes_for_stream(struct dc *dc,
 							plane_state->flip_immediate);
 				}
 			}
-#endif
 		/* Perform requested Updates */
 		for (i = 0; i < surface_count; i++) {
 			struct dc_plane_state *plane_state = srf_updates[i].surface;
@@ -2238,7 +2306,6 @@ static void commit_planes_for_stream(struct dc *dc,
 
 				if (pipe_ctx->plane_state != plane_state)
 					continue;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 				/*program triple buffer after lock based on flip type*/
 				if (dc->hwss.program_triplebuffer != NULL &&
 					!dc->debug.disable_tri_buf) {
@@ -2246,7 +2313,6 @@ static void commit_planes_for_stream(struct dc *dc,
 					dc->hwss.program_triplebuffer(
 						dc, pipe_ctx, plane_state->triplebuffer_flips);
 				}
-#endif
 				if (srf_updates[i].flip_addr)
 					dc->hwss.update_plane_addr(dc, pipe_ctx);
 			}
@@ -2407,14 +2473,15 @@ void dc_set_power_state(
 	case DC_ACPI_CM_POWER_STATE_D0:
 		dc_resource_state_construct(dc, dc->current_state);
 
+		if (dc->ctx->dmub_srv)
+			dc_dmub_srv_wait_phy_init(dc->ctx->dmub_srv);
+
 		dc->hwss.init_hw(dc);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		if (dc->hwss.init_sys_ctx != NULL &&
 			dc->vm_pa_config.valid) {
 			dc->hwss.init_sys_ctx(dc->hwseq, dc, &dc->vm_pa_config);
 		}
-#endif
 
 		break;
 	default:
@@ -2494,6 +2561,17 @@ bool dc_submit_i2c(
 		cmd);
 }
 
+bool dc_submit_i2c_oem(
+		struct dc *dc,
+		struct i2c_command *cmd)
+{
+	struct ddc_service *ddc = dc->res_pool->oem_device;
+	return dce_i2c_submit_command(
+		dc->res_pool,
+		ddc->ddc_pin,
+		cmd);
+}
+
 static bool link_add_remote_sink_helper(struct dc_link *dc_link, struct dc_sink *sink)
 {
 	if (dc_link->sink_count >= MAX_SINKS_PER_LINK) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index b9227d5de3a3..502ed3c7959d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -33,7 +33,6 @@
 
 #include "core_status.h"
 #include "core_types.h"
-#include "hw_sequencer.h"
 
 #include "resource.h"
 
@@ -310,14 +309,13 @@ void context_timing_trace(
 		struct resource_context *res_ctx)
 {
 	int i;
-	struct dc  *core_dc = dc;
 	int h_pos[MAX_PIPES] = {0}, v_pos[MAX_PIPES] = {0};
 	struct crtc_position position;
-	unsigned int underlay_idx = core_dc->res_pool->underlay_pipe_index;
+	unsigned int underlay_idx = dc->res_pool->underlay_pipe_index;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
 		/* get_position() returns CRTC vertical/horizontal counter
 		 * hence not applicable for underlay pipe
@@ -329,7 +327,7 @@ void context_timing_trace(
 		h_pos[i] = position.horizontal_count;
 		v_pos[i] = position.vertical_count;
 	}
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[i];
 
 		if (pipe_ctx->stream == NULL || pipe_ctx->pipe_idx == underlay_idx)
@@ -347,7 +345,7 @@ void context_clock_trace(
 		struct dc *dc,
 		struct dc_state *context)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	DC_LOGGER_INIT(dc->ctx->logger);
 	CLOCK_TRACE("Current: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 4619f94f0ac7..260c0b62d37d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -45,6 +45,7 @@
 #include "dpcd_defs.h"
 #include "dmcu.h"
 #include "hw/clk_mgr.h"
+#include "../dce/dmub_psr.h"
 
 #define DC_LOGGER_INIT(logger)
 
@@ -74,7 +75,7 @@ enum {
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
-static void destruct(struct dc_link *link)
+static void dc_link_destruct(struct dc_link *link)
 {
 	int i;
 
@@ -1244,7 +1245,7 @@ static enum transmitter translate_encoder_to_transmitter(
 	}
 }
 
-static bool construct(
+static bool dc_link_construct(
 	struct dc_link *link,
 	const struct link_init_data *init_params)
 {
@@ -1446,7 +1447,7 @@ struct dc_link *link_create(const struct link_init_data *init_params)
 	if (NULL == link)
 		goto alloc_fail;
 
-	if (false == construct(link, init_params))
+	if (false == dc_link_construct(link, init_params))
 		goto construct_fail;
 
 	return link;
@@ -1460,7 +1461,7 @@ alloc_fail:
 
 void link_destroy(struct dc_link **link)
 {
-	destruct(*link);
+	dc_link_destruct(*link);
 	kfree(*link);
 	*link = NULL;
 }
@@ -1495,10 +1496,7 @@ static enum dc_status enable_link_dp(
 	bool skip_video_pattern;
 	struct dc_link *link = stream->link;
 	struct dc_link_settings link_settings = {0};
-	enum dp_panel_mode panel_mode;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool fec_enable;
-#endif
 	int i;
 	bool apply_seamless_boot_optimization = false;
 
@@ -1514,15 +1512,6 @@ static enum dc_status enable_link_dp(
 	decide_link_settings(stream, &link_settings);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_EDP) {
-		/* If link settings are different than current and link already enabled
-		 * then need to disable before programming to new rate.
-		 */
-		if (link->link_status.link_active &&
-			(link->cur_link_settings.lane_count != link_settings.lane_count ||
-			 link->cur_link_settings.link_rate != link_settings.link_rate)) {
-			dp_disable_link_phy(link, pipe_ctx->stream->signal);
-		}
-
 		/*in case it is not on*/
 		link->dc->hwss.edp_power_control(link, true);
 		link->dc->hwss.edp_wait_for_hpd_ready(link, true);
@@ -1533,50 +1522,29 @@ static enum dc_status enable_link_dp(
 	if (state->clk_mgr && !apply_seamless_boot_optimization)
 		state->clk_mgr->funcs->update_clocks(state->clk_mgr, state, false);
 
-	dp_enable_link_phy(
-		link,
-		pipe_ctx->stream->signal,
-		pipe_ctx->clock_source->id,
-		&link_settings);
-
-	if (stream->sink_patches.dppowerup_delay > 0) {
-		int delay_dp_power_up_in_ms = stream->sink_patches.dppowerup_delay;
-
-		msleep(delay_dp_power_up_in_ms);
-	}
-
-	panel_mode = dp_get_panel_mode(link);
-	dp_set_panel_mode(link, panel_mode);
-
 	skip_video_pattern = true;
 
 	if (link_settings.link_rate == LINK_RATE_LOW)
 			skip_video_pattern = false;
 
-	if (link->aux_access_disabled) {
-		dc_link_dp_perform_link_training_skip_aux(link, &link_settings);
-
-		link->cur_link_settings = link_settings;
-		status = DC_OK;
-	} else if (perform_link_training_with_retries(
-			link,
+	if (perform_link_training_with_retries(
 			&link_settings,
 			skip_video_pattern,
-			LINK_TRAINING_ATTEMPTS)) {
+			LINK_TRAINING_ATTEMPTS,
+			pipe_ctx,
+			pipe_ctx->stream->signal)) {
 		link->cur_link_settings = link_settings;
 		status = DC_OK;
 	}
 	else
 		status = DC_FAIL_DP_LINK_TRAINING;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (link->preferred_training_settings.fec_enable != NULL)
 		fec_enable = *link->preferred_training_settings.fec_enable;
 	else
 		fec_enable = true;
 
 	dp_set_fec_enable(link, fec_enable);
-#endif
 	return status;
 }
 
@@ -2063,6 +2031,45 @@ static void write_i2c_redriver_setting(
 		ASSERT(i2c_success);
 }
 
+static void disable_link(struct dc_link *link, enum signal_type signal)
+{
+	/*
+	 * TODO: implement call for dp_set_hw_test_pattern
+	 * it is needed for compliance testing
+	 */
+
+	/* Here we need to specify that encoder output settings
+	 * need to be calculated as for the set mode,
+	 * it will lead to querying dynamic link capabilities
+	 * which should be done before enable output
+	 */
+
+	if (dc_is_dp_signal(signal)) {
+		/* SST DP, eDP */
+		if (dc_is_dp_sst_signal(signal))
+			dp_disable_link_phy(link, signal);
+		else
+			dp_disable_link_phy_mst(link, signal);
+
+		if (dc_is_dp_sst_signal(signal) ||
+				link->mst_stream_alloc_table.stream_count == 0) {
+			dp_set_fec_enable(link, false);
+			dp_set_fec_ready(link, false);
+		}
+	} else {
+		if (signal != SIGNAL_TYPE_VIRTUAL)
+			link->link_enc->funcs->disable_output(link->link_enc, signal);
+	}
+
+	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+		/* MST disable link only when no stream use the link */
+		if (link->mst_stream_alloc_table.stream_count <= 0)
+			link->link_status.link_active = false;
+	} else {
+		link->link_status.link_active = false;
+	}
+}
+
 static void enable_link_hdmi(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
@@ -2147,6 +2154,19 @@ static enum dc_status enable_link(
 		struct pipe_ctx *pipe_ctx)
 {
 	enum dc_status status = DC_ERROR_UNEXPECTED;
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->link;
+
+	/* There's some scenarios where driver is unloaded with display
+	 * still enabled. When driver is reloaded, it may cause a display
+	 * to not light up if there is a mismatch between old and new
+	 * link settings. Need to call disable first before enabling at
+	 * new link settings.
+	 */
+	if (link->link_status.link_active) {
+		disable_link(link, pipe_ctx->stream->signal);
+	}
+
 	switch (pipe_ctx->stream->signal) {
 	case SIGNAL_TYPE_DISPLAY_PORT:
 		status = enable_link_dp(state, pipe_ctx);
@@ -2181,46 +2201,6 @@ static enum dc_status enable_link(
 	return status;
 }
 
-static void disable_link(struct dc_link *link, enum signal_type signal)
-{
-	/*
-	 * TODO: implement call for dp_set_hw_test_pattern
-	 * it is needed for compliance testing
-	 */
-
-	/* here we need to specify that encoder output settings
-	 * need to be calculated as for the set mode,
-	 * it will lead to querying dynamic link capabilities
-	 * which should be done before enable output */
-
-	if (dc_is_dp_signal(signal)) {
-		/* SST DP, eDP */
-		if (dc_is_dp_sst_signal(signal))
-			dp_disable_link_phy(link, signal);
-		else
-			dp_disable_link_phy_mst(link, signal);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-
-		if (dc_is_dp_sst_signal(signal) ||
-				link->mst_stream_alloc_table.stream_count == 0) {
-			dp_set_fec_enable(link, false);
-			dp_set_fec_ready(link, false);
-		}
-#endif
-	} else {
-		if (signal != SIGNAL_TYPE_VIRTUAL)
-			link->link_enc->funcs->disable_output(link->link_enc, signal);
-	}
-
-	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
-		/* MST disable link only when no stream use the link */
-		if (link->mst_stream_alloc_table.stream_count <= 0)
-			link->link_status.link_active = false;
-	} else {
-		link->link_status.link_active = false;
-	}
-}
-
 static uint32_t get_timing_pixel_clock_100hz(const struct dc_crtc_timing *timing)
 {
 
@@ -2357,9 +2337,9 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 		uint32_t backlight_pwm_u16_16,
 		uint32_t frame_ramp)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct abm *abm = core_dc->res_pool->abm;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct abm *abm = dc->res_pool->abm;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 	unsigned int controller_id = 0;
 	bool use_smooth_brightness = true;
 	int i;
@@ -2377,22 +2357,22 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 
 	if (dc_is_embedded_signal(link->connector_signal)) {
 		for (i = 0; i < MAX_PIPES; i++) {
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream) {
-				if (core_dc->current_state->res_ctx.
+			if (dc->current_state->res_ctx.pipe_ctx[i].stream) {
+				if (dc->current_state->res_ctx.
 						pipe_ctx[i].stream->link
 						== link) {
 					/* DMCU -1 for all controller id values,
 					 * therefore +1 here
 					 */
 					controller_id =
-						core_dc->current_state->
+						dc->current_state->
 						res_ctx.pipe_ctx[i].stream_res.tg->inst +
 						1;
 
 					/* Disable brightness ramping when the display is blanked
 					 * as it can hang the DMCU
 					 */
-					if (core_dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL)
+					if (dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL)
 						frame_ramp = 0;
 				}
 			}
@@ -2410,8 +2390,8 @@ bool dc_link_set_backlight_level(const struct dc_link *link,
 
 bool dc_link_set_abm_disable(const struct dc_link *link)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct abm *abm = core_dc->res_pool->abm;
+	struct dc  *dc = link->ctx->dc;
+	struct abm *abm = dc->res_pool->abm;
 
 	if ((abm == NULL) || (abm->funcs->set_backlight_level_pwm == NULL))
 		return false;
@@ -2423,12 +2403,13 @@ bool dc_link_set_abm_disable(const struct dc_link *link)
 
 bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool wait)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+	struct dmub_psr *psr = dc->res_pool->psr;
 
-
-
-	if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled)
+	if ((psr != NULL) && link->psr_feature_enabled)
+		psr->funcs->set_psr_enable(psr, allow_active);
+	else if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled)
 		dmcu->funcs->set_psr_enable(dmcu, allow_active, wait);
 
 	link->psr_allow_active = allow_active;
@@ -2438,10 +2419,13 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool
 
 bool dc_link_get_psr_state(const struct dc_link *link, uint32_t *psr_state)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+	struct dmub_psr *psr = dc->res_pool->psr;
 
-	if (dmcu != NULL && link->psr_feature_enabled)
+	if (psr != NULL && link->psr_feature_enabled)
+		psr->funcs->get_psr_state(psr_state);
+	else if (dmcu != NULL && link->psr_feature_enabled)
 		dmcu->funcs->get_psr_state(dmcu, psr_state);
 
 	return true;
@@ -2486,8 +2470,9 @@ bool dc_link_setup_psr(struct dc_link *link,
 		const struct dc_stream_state *stream, struct psr_config *psr_config,
 		struct psr_context *psr_context)
 {
-	struct dc *core_dc;
+	struct dc *dc;
 	struct dmcu *dmcu;
+	struct dmub_psr *psr;
 	int i;
 	/* updateSinkPsrDpcdConfig*/
 	union dpcd_psr_configuration psr_configuration;
@@ -2497,10 +2482,11 @@ bool dc_link_setup_psr(struct dc_link *link,
 	if (!link)
 		return false;
 
-	core_dc = link->ctx->dc;
-	dmcu = core_dc->res_pool->dmcu;
+	dc = link->ctx->dc;
+	dmcu = dc->res_pool->dmcu;
+	psr = dc->res_pool->psr;
 
-	if (!dmcu)
+	if (!dmcu && !psr)
 		return false;
 
 
@@ -2537,13 +2523,13 @@ bool dc_link_setup_psr(struct dc_link *link,
 	psr_context->engineId = link->link_enc->preferred_engine;
 
 	for (i = 0; i < MAX_PIPES; i++) {
-		if (core_dc->current_state->res_ctx.pipe_ctx[i].stream
+		if (dc->current_state->res_ctx.pipe_ctx[i].stream
 				== stream) {
 			/* dmcu -1 for all controller id values,
 			 * therefore +1 here
 			 */
 			psr_context->controllerId =
-				core_dc->current_state->res_ctx.
+				dc->current_state->res_ctx.
 				pipe_ctx[i].stream_res.tg->inst + 1;
 			break;
 		}
@@ -2556,7 +2542,7 @@ bool dc_link_setup_psr(struct dc_link *link,
 		transmitter_to_phy_id(link->link_enc->transmitter);
 
 	psr_context->crtcTimingVerticalTotal = stream->timing.v_total;
-	psr_context->vsyncRateHz = div64_u64(div64_u64((stream->
+	psr_context->vsync_rate_hz = div64_u64(div64_u64((stream->
 					timing.pix_clk_100hz * 100),
 					stream->timing.v_total),
 					stream->timing.h_total);
@@ -2586,7 +2572,7 @@ bool dc_link_setup_psr(struct dc_link *link,
 
 	psr_context->psr_level.u32all = 0;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	/*skip power down the single pipe since it blocks the cstate*/
 	if (ASICREV_IS_RAVEN(link->ctx->asic_id.hw_internal_rev))
 		psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true;
@@ -2609,7 +2595,10 @@ bool dc_link_setup_psr(struct dc_link *link,
 	 */
 	psr_context->frame_delay = 0;
 
-	link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context);
+	if (psr)
+		link->psr_feature_enabled = psr->funcs->setup_psr(psr, link, psr_context);
+	else
+		link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context);
 
 	/* psr_enabled == 0 indicates setup_psr did not succeed, but this
 	 * should not happen since firmware should be running at this point
@@ -2644,28 +2633,13 @@ static struct fixed31_32 get_pbn_per_slot(struct dc_stream_state *stream)
 	return dc_fixpt_div_int(mbytes_per_sec, 54);
 }
 
-static int get_color_depth(enum dc_color_depth color_depth)
-{
-	switch (color_depth) {
-	case COLOR_DEPTH_666: return 6;
-	case COLOR_DEPTH_888: return 8;
-	case COLOR_DEPTH_101010: return 10;
-	case COLOR_DEPTH_121212: return 12;
-	case COLOR_DEPTH_141414: return 14;
-	case COLOR_DEPTH_161616: return 16;
-	default: return 0;
-	}
-}
-
 static struct fixed31_32 get_pbn_from_timing(struct pipe_ctx *pipe_ctx)
 {
-	uint32_t bpc;
 	uint64_t kbps;
 	struct fixed31_32 peak_kbps;
 	uint32_t numerator;
 	uint32_t denominator;
 
-	bpc = get_color_depth(pipe_ctx->stream_res.pix_clk_params.color_depth);
 	kbps = dc_bandwidth_in_kbps_from_timing(&pipe_ctx->stream->timing);
 
 	/*
@@ -2899,6 +2873,39 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
 
 	return DC_OK;
 }
+
+enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link)
+{
+	int i;
+	struct pipe_ctx *pipe_ctx;
+
+	// Clear all of MST payload then reallocate
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
+				pipe_ctx->stream->dpms_off == false &&
+				pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+			deallocate_mst_payload(pipe_ctx);
+		}
+	}
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+		if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
+				pipe_ctx->stream->dpms_off == false &&
+				pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+			/* enable/disable PHY will clear connection between BE and FE
+			 * need to restore it.
+			 */
+			link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
+									pipe_ctx->stream_res.stream_enc->id, true);
+			dc_link_allocate_mst_payload(pipe_ctx);
+		}
+	}
+
+	return DC_OK;
+}
+
 #if defined(CONFIG_DRM_AMD_DC_HDCP)
 static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off)
 {
@@ -2922,12 +2929,12 @@ void core_link_enable_stream(
 		struct dc_state *state,
 		struct pipe_ctx *pipe_ctx)
 {
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_status status;
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment) &&
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) &&
 			dc_is_virtual_signal(pipe_ctx->stream->signal))
 		return;
 
@@ -2946,6 +2953,7 @@ void core_link_enable_stream(
 			pipe_ctx->stream_res.stream_enc,
 			&stream->timing,
 			stream->output_color_space,
+			stream->use_vsc_sdp_for_colorimetry,
 			stream->link->dpcd_caps.dprx_feature.bits.SST_SPLIT_SDP_CAP);
 
 	if (dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal))
@@ -2969,14 +2977,14 @@ void core_link_enable_stream(
 			pipe_ctx->stream_res.stream_enc,
 			&stream->timing);
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		bool apply_edp_fast_boot_optimization =
 			pipe_ctx->stream->apply_edp_fast_boot_optimization;
 
 		pipe_ctx->stream->apply_edp_fast_boot_optimization = false;
 
 		resource_build_info_frame(pipe_ctx);
-		core_dc->hwss.update_info_frame(pipe_ctx);
+		dc->hwss.update_info_frame(pipe_ctx);
 
 		/* Do not touch link on seamless boot optimization. */
 		if (pipe_ctx->stream->apply_seamless_boot_optimization) {
@@ -3019,7 +3027,7 @@ void core_link_enable_stream(
 			}
 		}
 
-		core_dc->hwss.enable_audio_stream(pipe_ctx);
+		dc->hwss.enable_audio_stream(pipe_ctx);
 
 		/* turn off otg test pattern if enable */
 		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
@@ -3027,28 +3035,24 @@ void core_link_enable_stream(
 					CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 					COLOR_DEPTH_UNDEFINED);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		if (pipe_ctx->stream->timing.flags.DSC) {
 			if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
 					dc_is_virtual_signal(pipe_ctx->stream->signal))
 				dp_set_dsc_enable(pipe_ctx, true);
 		}
-#endif
-		core_dc->hwss.enable_stream(pipe_ctx);
+		dc->hwss.enable_stream(pipe_ctx);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		/* Set DPS PPS SDP (AKA "info frames") */
 		if (pipe_ctx->stream->timing.flags.DSC) {
 			if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
 					dc_is_virtual_signal(pipe_ctx->stream->signal))
 				dp_set_dsc_pps_sdp(pipe_ctx, true);
 		}
-#endif
 
 		if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 			dc_link_allocate_mst_payload(pipe_ctx);
 
-		core_dc->hwss.unblank_stream(pipe_ctx,
+		dc->hwss.unblank_stream(pipe_ctx,
 			&pipe_ctx->stream->link->cur_link_settings);
 
 		if (dc_is_dp_signal(pipe_ctx->stream->signal))
@@ -3056,24 +3060,21 @@ void core_link_enable_stream(
 #if defined(CONFIG_DRM_AMD_DC_HDCP)
 		update_psp_stream_config(pipe_ctx, false);
 #endif
-	}
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-	else { // if (IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment))
+	} else { // if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		if (dc_is_dp_signal(pipe_ctx->stream->signal) ||
 				dc_is_virtual_signal(pipe_ctx->stream->signal))
 			dp_set_dsc_enable(pipe_ctx, true);
 
 	}
-#endif
 }
 
 void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 {
-	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc  *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->sink->link;
 
-	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment) &&
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) &&
 			dc_is_virtual_signal(pipe_ctx->stream->signal))
 		return;
 
@@ -3081,7 +3082,7 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 	update_psp_stream_config(pipe_ctx, true);
 #endif
 
-	core_dc->hwss.blank_stream(pipe_ctx);
+	dc->hwss.blank_stream(pipe_ctx);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
@@ -3110,25 +3111,23 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 			write_i2c_redriver_setting(pipe_ctx, false);
 		}
 	}
-	core_dc->hwss.disable_stream(pipe_ctx);
+	dc->hwss.disable_stream(pipe_ctx);
 
 	disable_link(pipe_ctx->stream->link, pipe_ctx->stream->signal);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (pipe_ctx->stream->timing.flags.DSC) {
 		if (dc_is_dp_signal(pipe_ctx->stream->signal))
 			dp_set_dsc_enable(pipe_ctx, false);
 	}
-#endif
 }
 
 void core_link_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 {
-	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc  *dc = pipe_ctx->stream->ctx->dc;
 
 	if (!dc_is_hdmi_signal(pipe_ctx->stream->signal))
 		return;
 
-	core_dc->hwss.set_avmute(pipe_ctx, enable);
+	dc->hwss.set_avmute(pipe_ctx, enable);
 }
 
 /**
@@ -3186,13 +3185,11 @@ uint32_t dc_bandwidth_in_kbps_from_timing(
 	uint32_t bits_per_channel = 0;
 	uint32_t kbps;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (timing->flags.DSC) {
 		kbps = (timing->pix_clk_100hz * timing->dsc_cfg.bits_per_pixel);
 		kbps = kbps / 160 + ((kbps % 160) ? 1 : 0);
 		return kbps;
 	}
-#endif
 
 	switch (timing->display_color_depth) {
 	case COLOR_DEPTH_666:
@@ -3345,6 +3342,7 @@ void dc_link_disable_hpd(const struct dc_link *link)
 
 void dc_link_set_test_pattern(struct dc_link *link,
 			      enum dp_test_pattern test_pattern,
+			      enum dp_test_pattern_color_space test_pattern_color_space,
 			      const struct link_training_settings *p_link_settings,
 			      const unsigned char *p_custom_pattern,
 			      unsigned int cust_pattern_size)
@@ -3353,6 +3351,7 @@ void dc_link_set_test_pattern(struct dc_link *link,
 		dc_link_dp_set_test_pattern(
 			link,
 			test_pattern,
+			test_pattern_color_space,
 			p_link_settings,
 			p_custom_pattern,
 			cust_pattern_size);
@@ -3368,7 +3367,6 @@ uint32_t dc_link_bandwidth_kbps(
 	link_bw_kbps *= 8;   /* 8 bits per byte*/
 	link_bw_kbps *= link_setting->lane_count;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) {
 		/* Account for FEC overhead.
 		 * We have to do it based on caps,
@@ -3393,7 +3391,6 @@ uint32_t dc_link_bandwidth_kbps(
 		link_bw_kbps = mul_u64_u32_shr(BIT_ULL(32) * 970LL / 1000,
 					       link_bw_kbps, 32);
 	}
-#endif
 
 	return link_bw_kbps;
 
@@ -3407,3 +3404,10 @@ const struct dc_link_settings *dc_link_get_link_cap(
 		return &link->preferred_link_setting;
 	return &link->verified_link_cap;
 }
+
+void dc_link_overwrite_extended_receiver_cap(
+		struct dc_link *link)
+{
+	dp_overwrite_extended_receiver_cap(link);
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 81789191d4ec..a49c10d5df26 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -187,7 +187,7 @@ void dal_ddc_i2c_payloads_add(
 
 }
 
-static void construct(
+static void ddc_service_construct(
 	struct ddc_service *ddc_service,
 	struct ddc_service_init_data *init_data)
 {
@@ -206,7 +206,10 @@ static void construct(
 		ddc_service->ddc_pin = NULL;
 	} else {
 		hw_info.ddc_channel = i2c_info.i2c_line;
-		hw_info.hw_supported = i2c_info.i2c_hw_assist;
+		if (ddc_service->link != NULL)
+			hw_info.hw_supported = i2c_info.i2c_hw_assist;
+		else
+			hw_info.hw_supported = false;
 
 		ddc_service->ddc_pin = dal_gpio_create_ddc(
 			gpio_service,
@@ -236,11 +239,11 @@ struct ddc_service *dal_ddc_service_create(
 	if (!ddc_service)
 		return NULL;
 
-	construct(ddc_service, init_data);
+	ddc_service_construct(ddc_service, init_data);
 	return ddc_service;
 }
 
-static void destruct(struct ddc_service *ddc)
+static void ddc_service_destruct(struct ddc_service *ddc)
 {
 	if (ddc->ddc_pin)
 		dal_gpio_destroy_ddc(&ddc->ddc_pin);
@@ -252,7 +255,7 @@ void dal_ddc_service_destroy(struct ddc_service **ddc)
 		BREAK_TO_DEBUGGER();
 		return;
 	}
-	destruct(*ddc);
+	ddc_service_destruct(*ddc);
 	kfree(*ddc);
 	*ddc = NULL;
 }
@@ -587,7 +590,7 @@ bool dal_ddc_submit_aux_command(struct ddc_service *ddc,
 		struct aux_payload *payload)
 {
 	uint32_t retrieved = 0;
-	bool ret = 0;
+	bool ret = false;
 
 	if (!ddc)
 		return false;
@@ -647,17 +650,16 @@ bool dc_link_aux_transfer_with_retries(struct ddc_service *ddc,
 }
 
 
-enum dc_status dc_link_aux_configure_timeout(struct ddc_service *ddc,
+uint32_t dc_link_aux_configure_timeout(struct ddc_service *ddc,
 		uint32_t timeout)
 {
-	enum dc_status status = DC_OK;
+	uint32_t prev_timeout = 0;
 	struct ddc *ddc_pin = ddc->ddc_pin;
 
-	if (ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout == NULL)
-		return DC_ERROR_UNEXPECTED;
-	if (!ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout(ddc, timeout))
-		status = DC_ERROR_UNEXPECTED;
-	return status;
+	if (ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout)
+		prev_timeout =
+				ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout(ddc, timeout);
+	return prev_timeout;
 }
 
 /*test only function*/
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 504055fc70e8..6ab298c65247 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -4,12 +4,8 @@
 #include "dc_link_dp.h"
 #include "dm_helpers.h"
 #include "opp.h"
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "resource.h"
-#endif
 
 #include "inc/core_types.h"
 #include "link_hwss.h"
@@ -21,6 +17,9 @@
 #define DC_LOGGER \
 	link->ctx->logger
 
+
+#define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE   0x50
+
 /* maximum pre emphasis level allowed for each voltage swing level*/
 static const enum dc_pre_emphasis voltage_swing_to_pre_emphasis[] = {
 		PRE_EMPHASIS_LEVEL3,
@@ -221,19 +220,31 @@ static enum dpcd_training_patterns
 	return dpcd_tr_pattern;
 }
 
+static inline bool is_repeater(struct dc_link *link, uint32_t offset)
+{
+	return (!link->is_lttpr_mode_transparent && offset != 0);
+}
+
 static void dpcd_set_lt_pattern_and_lane_settings(
 	struct dc_link *link,
 	const struct link_training_settings *lt_settings,
-	enum dc_dp_training_pattern pattern)
+	enum dc_dp_training_pattern pattern,
+	uint32_t offset)
 {
 	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = { { {0} } };
-	const uint32_t dpcd_base_lt_offset =
-	DP_TRAINING_PATTERN_SET;
+
+	uint32_t dpcd_base_lt_offset;
+
 	uint8_t dpcd_lt_buffer[5] = {0};
 	union dpcd_training_pattern dpcd_pattern = { {0} };
 	uint32_t lane;
 	uint32_t size_in_bytes;
 	bool edp_workaround = false; /* TODO link_prop.INTERNAL */
+	dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET;
+
+	if (is_repeater(link, offset))
+		dpcd_base_lt_offset = DP_TRAINING_PATTERN_SET_PHY_REPEATER1 +
+			((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
 
 	/*****************************************************************
 	* DpcdAddress_TrainingPatternSet
@@ -241,14 +252,21 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 	dpcd_pattern.v1_4.TRAINING_PATTERN_SET =
 		dc_dp_training_pattern_to_dpcd_training_pattern(link, pattern);
 
-	dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - dpcd_base_lt_offset]
+	dpcd_lt_buffer[DP_TRAINING_PATTERN_SET - DP_TRAINING_PATTERN_SET]
 		= dpcd_pattern.raw;
 
-	DC_LOG_HW_LINK_TRAINING("%s\n %x pattern = %x\n",
-		__func__,
-		DP_TRAINING_PATTERN_SET,
-		dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
-
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n 0x%X pattern = %x\n",
+			__func__,
+			offset,
+			dpcd_base_lt_offset,
+			dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s\n 0x%X pattern = %x\n",
+			__func__,
+			dpcd_base_lt_offset,
+			dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
+	}
 	/*****************************************************************
 	* DpcdAddress_Lane0Set -> DpcdAddress_Lane3Set
 	*****************************************************************/
@@ -268,24 +286,35 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 		PRE_EMPHASIS_MAX_LEVEL ? 1 : 0);
 	}
 
-	/* concatinate everything into one buffer*/
+	/* concatenate everything into one buffer*/
 
 	size_in_bytes = lt_settings->link_settings.lane_count * sizeof(dpcd_lane[0]);
 
 	 // 0x00103 - 0x00102
 	memmove(
-		&dpcd_lt_buffer[DP_TRAINING_LANE0_SET - dpcd_base_lt_offset],
+		&dpcd_lt_buffer[DP_TRAINING_LANE0_SET - DP_TRAINING_PATTERN_SET],
 		dpcd_lane,
 		size_in_bytes);
 
-	DC_LOG_HW_LINK_TRAINING("%s:\n %x VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
-		__func__,
-		DP_TRAINING_LANE0_SET,
-		dpcd_lane[0].bits.VOLTAGE_SWING_SET,
-		dpcd_lane[0].bits.PRE_EMPHASIS_SET,
-		dpcd_lane[0].bits.MAX_SWING_REACHED,
-		dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
-
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n"
+				" 0x%X VS set = %x PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			offset,
+			dpcd_base_lt_offset,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			dpcd_base_lt_offset,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	}
 	if (edp_workaround) {
 		/* for eDP write in 2 parts because the 5-byte burst is
 		* causing issues on some eDP panels (EPR#366724)
@@ -495,8 +524,12 @@ static void get_lane_status_and_drive_settings(
 	const struct link_training_settings *link_training_setting,
 	union lane_status *ln_status,
 	union lane_align_status_updated *ln_status_updated,
-	struct link_training_settings *req_settings)
+	struct link_training_settings *req_settings,
+	uint32_t offset)
 {
+	unsigned int lane01_status_address = DP_LANE0_1_STATUS;
+	uint8_t lane_adjust_offset = 4;
+	unsigned int lane01_adjust_address;
 	uint8_t dpcd_buf[6] = {0};
 	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } };
 	struct link_training_settings request_settings = { {0} };
@@ -504,9 +537,16 @@ static void get_lane_status_and_drive_settings(
 
 	memset(req_settings, '\0', sizeof(struct link_training_settings));
 
+	if (is_repeater(link, offset)) {
+		lane01_status_address =
+				DP_LANE0_1_STATUS_PHY_REPEATER1 +
+				((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
+		lane_adjust_offset = 3;
+	}
+
 	core_link_read_dpcd(
 		link,
-		DP_LANE0_1_STATUS,
+		lane01_status_address,
 		(uint8_t *)(dpcd_buf),
 		sizeof(dpcd_buf));
 
@@ -517,22 +557,47 @@ static void get_lane_status_and_drive_settings(
 		ln_status[lane].raw =
 			get_nibble_at_index(&dpcd_buf[0], lane);
 		dpcd_lane_adjust[lane].raw =
-			get_nibble_at_index(&dpcd_buf[4], lane);
+			get_nibble_at_index(&dpcd_buf[lane_adjust_offset], lane);
 	}
 
 	ln_status_updated->raw = dpcd_buf[2];
 
-	DC_LOG_HW_LINK_TRAINING("%s:\n%x Lane01Status = %x\n %x Lane23Status = %x\n ",
-		__func__,
-		DP_LANE0_1_STATUS, dpcd_buf[0],
-		DP_LANE2_3_STATUS, dpcd_buf[1]);
-
-	DC_LOG_HW_LINK_TRAINING("%s:\n %x Lane01AdjustRequest = %x\n %x Lane23AdjustRequest = %x\n",
-		__func__,
-		DP_ADJUST_REQUEST_LANE0_1,
-		dpcd_buf[4],
-		DP_ADJUST_REQUEST_LANE2_3,
-		dpcd_buf[5]);
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n"
+				" 0x%X Lane01Status = %x\n 0x%X Lane23Status = %x\n ",
+			__func__,
+			offset,
+			lane01_status_address, dpcd_buf[0],
+			lane01_status_address + 1, dpcd_buf[1]);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X Lane01Status = %x\n 0x%X Lane23Status = %x\n ",
+			__func__,
+			lane01_status_address, dpcd_buf[0],
+			lane01_status_address + 1, dpcd_buf[1]);
+	}
+	lane01_adjust_address = DP_ADJUST_REQUEST_LANE0_1;
+
+	if (is_repeater(link, offset))
+		lane01_adjust_address = DP_ADJUST_REQUEST_LANE0_1_PHY_REPEATER1 +
+				((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
+
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s:\n LTTPR Repeater ID: %d\n"
+				" 0x%X Lane01AdjustRequest = %x\n 0x%X Lane23AdjustRequest = %x\n",
+					__func__,
+					offset,
+					lane01_adjust_address,
+					dpcd_buf[lane_adjust_offset],
+					lane01_adjust_address + 1,
+					dpcd_buf[lane_adjust_offset + 1]);
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s:\n 0x%X Lane01AdjustRequest = %x\n 0x%X Lane23AdjustRequest = %x\n",
+			__func__,
+			lane01_adjust_address,
+			dpcd_buf[lane_adjust_offset],
+			lane01_adjust_address + 1,
+			dpcd_buf[lane_adjust_offset + 1]);
+	}
 
 	/*copy to req_settings*/
 	request_settings.link_settings.lane_count =
@@ -571,10 +636,18 @@ static void get_lane_status_and_drive_settings(
 
 static void dpcd_set_lane_settings(
 	struct dc_link *link,
-	const struct link_training_settings *link_training_setting)
+	const struct link_training_settings *link_training_setting,
+	uint32_t offset)
 {
 	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = {{{0}}};
 	uint32_t lane;
+	unsigned int lane0_set_address;
+
+	lane0_set_address = DP_TRAINING_LANE0_SET;
+
+	if (is_repeater(link, offset))
+		lane0_set_address = DP_TRAINING_LANE0_SET_PHY_REPEATER1 +
+		((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
 
 	for (lane = 0; lane <
 		(uint32_t)(link_training_setting->
@@ -597,7 +670,7 @@ static void dpcd_set_lane_settings(
 	}
 
 	core_link_write_dpcd(link,
-		DP_TRAINING_LANE0_SET,
+		lane0_set_address,
 		(uint8_t *)(dpcd_lane),
 		link_training_setting->link_settings.lane_count);
 
@@ -620,14 +693,26 @@ static void dpcd_set_lane_settings(
 	}
 	*/
 
-	DC_LOG_HW_LINK_TRAINING("%s\n %x VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
-		__func__,
-		DP_TRAINING_LANE0_SET,
-		dpcd_lane[0].bits.VOLTAGE_SWING_SET,
-		dpcd_lane[0].bits.PRE_EMPHASIS_SET,
-		dpcd_lane[0].bits.MAX_SWING_REACHED,
-		dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	if (is_repeater(link, offset)) {
+		DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Repeater ID: %d\n"
+				" 0x%X VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			offset,
+			lane0_set_address,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
 
+	} else {
+		DC_LOG_HW_LINK_TRAINING("%s\n 0x%X VS set = %x  PE set = %x max VS Reached = %x  max PE Reached = %x\n",
+			__func__,
+			lane0_set_address,
+			dpcd_lane[0].bits.VOLTAGE_SWING_SET,
+			dpcd_lane[0].bits.PRE_EMPHASIS_SET,
+			dpcd_lane[0].bits.MAX_SWING_REACHED,
+			dpcd_lane[0].bits.MAX_PRE_EMPHASIS_REACHED);
+	}
 	link->cur_lane_setting = link_training_setting->lane_settings[0];
 
 }
@@ -647,17 +732,6 @@ static bool is_max_vs_reached(
 
 }
 
-void dc_link_dp_set_drive_settings(
-	struct dc_link *link,
-	struct link_training_settings *lt_settings)
-{
-	/* program ASIC PHY settings*/
-	dp_set_hw_lane_settings(link, lt_settings);
-
-	/* Notify DP sink the PHY settings from source */
-	dpcd_set_lane_settings(link, lt_settings);
-}
-
 static bool perform_post_lt_adj_req_sequence(
 	struct dc_link *link,
 	struct link_training_settings *lt_settings)
@@ -690,7 +764,8 @@ static bool perform_post_lt_adj_req_sequence(
 			lt_settings,
 			dpcd_lane_status,
 			&dpcd_lane_status_updated,
-			&req_settings);
+			&req_settings,
+			DPRX);
 
 			if (dpcd_lane_status_updated.bits.
 					POST_LT_ADJ_REQ_IN_PROGRESS == 0)
@@ -747,6 +822,31 @@ static bool perform_post_lt_adj_req_sequence(
 
 }
 
+/* Only used for channel equalization */
+static uint32_t translate_training_aux_read_interval(uint32_t dpcd_aux_read_interval)
+{
+	unsigned int aux_rd_interval_us = 400;
+
+	switch (dpcd_aux_read_interval) {
+	case 0x01:
+		aux_rd_interval_us = 400;
+		break;
+	case 0x02:
+		aux_rd_interval_us = 4000;
+		break;
+	case 0x03:
+		aux_rd_interval_us = 8000;
+		break;
+	case 0x04:
+		aux_rd_interval_us = 16000;
+		break;
+	default:
+		break;
+	}
+
+	return aux_rd_interval_us;
+}
+
 static enum link_training_result get_cr_failure(enum dc_lane_count ln_count,
 					union lane_status *dpcd_lane_status)
 {
@@ -765,37 +865,55 @@ static enum link_training_result get_cr_failure(enum dc_lane_count ln_count,
 
 static enum link_training_result perform_channel_equalization_sequence(
 	struct dc_link *link,
-	struct link_training_settings *lt_settings)
+	struct link_training_settings *lt_settings,
+	uint32_t offset)
 {
 	struct link_training_settings req_settings;
 	enum dc_dp_training_pattern tr_pattern;
 	uint32_t retries_ch_eq;
+	uint32_t wait_time_microsec;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	union lane_align_status_updated dpcd_lane_status_updated = { {0} };
 	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } };
 
+	/* Note: also check that TPS4 is a supported feature*/
+
 	tr_pattern = lt_settings->pattern_for_eq;
 
-	dp_set_hw_training_pattern(link, tr_pattern);
+	if (is_repeater(link, offset))
+		tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_4;
+
+	dp_set_hw_training_pattern(link, tr_pattern, offset);
 
 	for (retries_ch_eq = 0; retries_ch_eq <= LINK_TRAINING_MAX_RETRY_COUNT;
 		retries_ch_eq++) {
 
-		dp_set_hw_lane_settings(link, lt_settings);
+		dp_set_hw_lane_settings(link, lt_settings, offset);
 
 		/* 2. update DPCD*/
 		if (!retries_ch_eq)
 			/* EPR #361076 - write as a 5-byte burst,
-			 * but only for the 1-st iteration*/
+			 * but only for the 1-st iteration
+			 */
+
 			dpcd_set_lt_pattern_and_lane_settings(
 				link,
 				lt_settings,
-				tr_pattern);
+				tr_pattern, offset);
 		else
-			dpcd_set_lane_settings(link, lt_settings);
+			dpcd_set_lane_settings(link, lt_settings, offset);
 
 		/* 3. wait for receiver to lock-on*/
-		wait_for_training_aux_rd_interval(link, lt_settings->eq_pattern_time);
+		wait_time_microsec = lt_settings->eq_pattern_time;
+
+		if (is_repeater(link, offset))
+			wait_time_microsec =
+					translate_training_aux_read_interval(
+						link->dpcd_caps.lttpr_caps.aux_rd_interval[offset - 1]);
+
+		wait_for_training_aux_rd_interval(
+				link,
+				wait_time_microsec);
 
 		/* 4. Read lane status and requested
 		 * drive settings as set by the sink*/
@@ -805,7 +923,8 @@ static enum link_training_result perform_channel_equalization_sequence(
 			lt_settings,
 			dpcd_lane_status,
 			&dpcd_lane_status_updated,
-			&req_settings);
+			&req_settings,
+			offset);
 
 		/* 5. check CR done*/
 		if (!is_cr_done(lane_count, dpcd_lane_status))
@@ -824,13 +943,16 @@ static enum link_training_result perform_channel_equalization_sequence(
 	return LINK_TRAINING_EQ_FAIL_EQ;
 
 }
+#define TRAINING_AUX_RD_INTERVAL 100 //us
 
 static enum link_training_result perform_clock_recovery_sequence(
 	struct dc_link *link,
-	struct link_training_settings *lt_settings)
+	struct link_training_settings *lt_settings,
+	uint32_t offset)
 {
 	uint32_t retries_cr;
 	uint32_t retry_count;
+	uint32_t wait_time_microsec;
 	struct link_training_settings req_settings;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
 	enum dc_dp_training_pattern tr_pattern = DP_TRAINING_PATTERN_SEQUENCE_1;
@@ -840,7 +962,7 @@ static enum link_training_result perform_clock_recovery_sequence(
 	retries_cr = 0;
 	retry_count = 0;
 
-	dp_set_hw_training_pattern(link, tr_pattern);
+	dp_set_hw_training_pattern(link, tr_pattern, offset);
 
 	/* najeeb - The synaptics MST hub can put the LT in
 	* infinite loop by switching the VS
@@ -857,7 +979,8 @@ static enum link_training_result perform_clock_recovery_sequence(
 		/* 1. call HWSS to set lane settings*/
 		dp_set_hw_lane_settings(
 				link,
-				lt_settings);
+				lt_settings,
+				offset);
 
 		/* 2. update DPCD of the receiver*/
 		if (!retries_cr)
@@ -866,16 +989,23 @@ static enum link_training_result perform_clock_recovery_sequence(
 			dpcd_set_lt_pattern_and_lane_settings(
 					link,
 					lt_settings,
-					tr_pattern);
+					tr_pattern,
+					offset);
 		else
 			dpcd_set_lane_settings(
 					link,
-					lt_settings);
+					lt_settings,
+					offset);
 
 		/* 3. wait receiver to lock-on*/
+		wait_time_microsec = lt_settings->cr_pattern_time;
+
+		if (!link->is_lttpr_mode_transparent)
+			wait_time_microsec = TRAINING_AUX_RD_INTERVAL;
+
 		wait_for_training_aux_rd_interval(
 				link,
-				lt_settings->cr_pattern_time);
+				wait_time_microsec);
 
 		/* 4. Read lane status and requested drive
 		* settings as set by the sink
@@ -885,7 +1015,8 @@ static enum link_training_result perform_clock_recovery_sequence(
 				lt_settings,
 				dpcd_lane_status,
 				&dpcd_lane_status_updated,
-				&req_settings);
+				&req_settings,
+				offset);
 
 		/* 5. check CR done*/
 		if (is_cr_done(lane_count, dpcd_lane_status))
@@ -1054,6 +1185,102 @@ static void initialize_training_settings(
 		lt_settings->enhanced_framing = 1;
 }
 
+static uint8_t convert_to_count(uint8_t lttpr_repeater_count)
+{
+	switch (lttpr_repeater_count) {
+	case 0x80: // 1 lttpr repeater
+		return 1;
+	case 0x40: // 2 lttpr repeaters
+		return 2;
+	case 0x20: // 3 lttpr repeaters
+		return 3;
+	case 0x10: // 4 lttpr repeaters
+		return 4;
+	case 0x08: // 5 lttpr repeaters
+		return 5;
+	case 0x04: // 6 lttpr repeaters
+		return 6;
+	case 0x02: // 7 lttpr repeaters
+		return 7;
+	case 0x01: // 8 lttpr repeaters
+		return 8;
+	default:
+		break;
+	}
+	return 0; // invalid value
+}
+
+static void configure_lttpr_mode(struct dc_link *link)
+{
+	/* aux timeout is already set to extended */
+	/* RESET/SET lttpr mode to enable non transparent mode */
+	uint8_t repeater_cnt;
+	uint32_t aux_interval_address;
+	uint8_t repeater_id;
+	enum dc_status result = DC_ERROR_UNEXPECTED;
+	uint8_t repeater_mode = DP_PHY_REPEATER_MODE_TRANSPARENT;
+
+	DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Transparent Mode\n", __func__);
+	result = core_link_write_dpcd(link,
+			DP_PHY_REPEATER_MODE,
+			(uint8_t *)&repeater_mode,
+			sizeof(repeater_mode));
+
+	if (result == DC_OK) {
+		link->dpcd_caps.lttpr_caps.mode = repeater_mode;
+	}
+
+	if (!link->is_lttpr_mode_transparent) {
+
+		DC_LOG_HW_LINK_TRAINING("%s\n Set LTTPR to Non Transparent Mode\n", __func__);
+
+		repeater_mode = DP_PHY_REPEATER_MODE_NON_TRANSPARENT;
+		result = core_link_write_dpcd(link,
+				DP_PHY_REPEATER_MODE,
+				(uint8_t *)&repeater_mode,
+				sizeof(repeater_mode));
+
+		if (result == DC_OK) {
+			link->dpcd_caps.lttpr_caps.mode = repeater_mode;
+		}
+
+		repeater_cnt = convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+		for (repeater_id = repeater_cnt; repeater_id > 0; repeater_id--) {
+			aux_interval_address = DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 +
+						((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (repeater_id - 1));
+			core_link_read_dpcd(
+				link,
+				aux_interval_address,
+				(uint8_t *)&link->dpcd_caps.lttpr_caps.aux_rd_interval[repeater_id - 1],
+				sizeof(link->dpcd_caps.lttpr_caps.aux_rd_interval[repeater_id - 1]));
+			link->dpcd_caps.lttpr_caps.aux_rd_interval[repeater_id - 1] &= 0x7F;
+		}
+	}
+}
+
+static void repeater_training_done(struct dc_link *link, uint32_t offset)
+{
+	union dpcd_training_pattern dpcd_pattern = { {0} };
+
+	const uint32_t dpcd_base_lt_offset =
+			DP_TRAINING_PATTERN_SET_PHY_REPEATER1 +
+				((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (offset - 1));
+	/* Set training not in progress*/
+	dpcd_pattern.v1_4.TRAINING_PATTERN_SET = DPCD_TRAINING_PATTERN_VIDEOIDLE;
+
+	core_link_write_dpcd(
+		link,
+		dpcd_base_lt_offset,
+		&dpcd_pattern.raw,
+		1);
+
+	DC_LOG_HW_LINK_TRAINING("%s\n LTTPR Id: %d 0x%X pattern = %x\n",
+		__func__,
+		offset,
+		dpcd_base_lt_offset,
+		dpcd_pattern.v1_4.TRAINING_PATTERN_SET);
+}
+
 static void print_status_message(
 	struct dc_link *link,
 	const struct link_training_settings *lt_settings,
@@ -1133,6 +1360,17 @@ static void print_status_message(
 				lt_spread);
 }
 
+void dc_link_dp_set_drive_settings(
+	struct dc_link *link,
+	struct link_training_settings *lt_settings)
+{
+	/* program ASIC PHY settings*/
+	dp_set_hw_lane_settings(link, lt_settings, DPRX);
+
+	/* Notify DP sink the PHY settings from source */
+	dpcd_set_lane_settings(link, lt_settings, DPRX);
+}
+
 bool dc_link_dp_perform_link_training_skip_aux(
 	struct dc_link *link,
 	const struct dc_link_settings *link_setting)
@@ -1149,10 +1387,10 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	/* 1. Perform_clock_recovery_sequence. */
 
 	/* transmit training pattern for clock recovery */
-	dp_set_hw_training_pattern(link, pattern_for_cr);
+	dp_set_hw_training_pattern(link, pattern_for_cr, DPRX);
 
 	/* call HWSS to set lane settings*/
-	dp_set_hw_lane_settings(link, &lt_settings);
+	dp_set_hw_lane_settings(link, &lt_settings, DPRX);
 
 	/* wait receiver to lock-on*/
 	wait_for_training_aux_rd_interval(link, lt_settings.cr_pattern_time);
@@ -1160,10 +1398,10 @@ bool dc_link_dp_perform_link_training_skip_aux(
 	/* 2. Perform_channel_equalization_sequence. */
 
 	/* transmit training pattern for channel equalization. */
-	dp_set_hw_training_pattern(link, lt_settings.pattern_for_eq);
+	dp_set_hw_training_pattern(link, lt_settings.pattern_for_eq, DPRX);
 
 	/* call HWSS to set lane settings*/
-	dp_set_hw_lane_settings(link, &lt_settings);
+	dp_set_hw_lane_settings(link, &lt_settings, DPRX);
 
 	/* wait receiver to lock-on. */
 	wait_for_training_aux_rd_interval(link, lt_settings.eq_pattern_time);
@@ -1185,9 +1423,10 @@ enum link_training_result dc_link_dp_perform_link_training(
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
 	struct link_training_settings lt_settings;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+
 	bool fec_enable;
-#endif
+	uint8_t repeater_cnt;
+	uint8_t repeater_id;
 
 	initialize_training_settings(
 			link,
@@ -1198,23 +1437,47 @@ enum link_training_result dc_link_dp_perform_link_training(
 	/* 1. set link rate, lane count and spread. */
 	dpcd_set_link_settings(link, &lt_settings);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (link->preferred_training_settings.fec_enable != NULL)
 		fec_enable = *link->preferred_training_settings.fec_enable;
 	else
 		fec_enable = true;
 
 	dp_set_fec_ready(link, fec_enable);
-#endif
 
+	if (!link->is_lttpr_mode_transparent) {
+		/* Configure lttpr mode */
+		configure_lttpr_mode(link);
+
+		/* 2. perform link training (set link training done
+		 *  to false is done as well)
+		 */
+		repeater_cnt = convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+
+		for (repeater_id = repeater_cnt; (repeater_id > 0 && status == LINK_TRAINING_SUCCESS);
+				repeater_id--) {
+			status = perform_clock_recovery_sequence(link, &lt_settings, repeater_id);
+
+			if (status != LINK_TRAINING_SUCCESS)
+				break;
+
+			status = perform_channel_equalization_sequence(link,
+					&lt_settings,
+					repeater_id);
+
+			if (status != LINK_TRAINING_SUCCESS)
+				break;
+
+			repeater_training_done(link, repeater_id);
+		}
+	}
 
-	/* 2. perform link training (set link training done
-	 *  to false is done as well)
-	 */
-	status = perform_clock_recovery_sequence(link, &lt_settings);
+	if (status == LINK_TRAINING_SUCCESS) {
+		status = perform_clock_recovery_sequence(link, &lt_settings, DPRX);
 	if (status == LINK_TRAINING_SUCCESS) {
 		status = perform_channel_equalization_sequence(link,
-				&lt_settings);
+					&lt_settings,
+					DPRX);
+		}
 	}
 
 	if ((status == LINK_TRAINING_SUCCESS) || !skip_video_pattern) {
@@ -1233,23 +1496,58 @@ enum link_training_result dc_link_dp_perform_link_training(
 }
 
 bool perform_link_training_with_retries(
-	struct dc_link *link,
 	const struct dc_link_settings *link_setting,
 	bool skip_video_pattern,
-	int attempts)
+	int attempts,
+	struct pipe_ctx *pipe_ctx,
+	enum signal_type signal)
 {
 	uint8_t j;
 	uint8_t delay_between_attempts = LINK_TRAINING_RETRY_DELAY;
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->link;
+	enum dp_panel_mode panel_mode = dp_get_panel_mode(link);
 
 	for (j = 0; j < attempts; ++j) {
 
-		if (dc_link_dp_perform_link_training(
+		dp_enable_link_phy(
+			link,
+			signal,
+			pipe_ctx->clock_source->id,
+			link_setting);
+
+		if (stream->sink_patches.dppowerup_delay > 0) {
+			int delay_dp_power_up_in_ms = stream->sink_patches.dppowerup_delay;
+
+			msleep(delay_dp_power_up_in_ms);
+		}
+
+		dp_set_panel_mode(link, panel_mode);
+
+		/* We need to do this before the link training to ensure the idle pattern in SST
+		 * mode will be sent right after the link training
+		 */
+		link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
+								pipe_ctx->stream_res.stream_enc->id, true);
+
+		if (link->aux_access_disabled) {
+			dc_link_dp_perform_link_training_skip_aux(link, link_setting);
+			return true;
+		} else if (dc_link_dp_perform_link_training(
 				link,
 				link_setting,
 				skip_video_pattern) == LINK_TRAINING_SUCCESS)
 			return true;
 
+		/* latest link training still fail, skip delay and keep PHY on
+		 */
+		if (j == (attempts - 1))
+			break;
+
+		dp_disable_link_phy(link, signal);
+
 		msleep(delay_between_attempts);
+
 		delay_between_attempts += LINK_TRAINING_RETRY_DELAY;
 	}
 
@@ -1321,9 +1619,7 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	enum link_training_result lt_status = LINK_TRAINING_SUCCESS;
 	enum dp_panel_mode panel_mode = DP_PANEL_MODE_DEFAULT;
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool fec_enable = false;
-#endif
 
 	initialize_training_settings(
 		link,
@@ -1343,11 +1639,9 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	dp_enable_link_phy(link, link->connector_signal,
 		dp_cs_id, link_settings);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Set FEC enable */
 	fec_enable = lt_overrides->fec_enable && *lt_overrides->fec_enable;
 	dp_set_fec_ready(link, fec_enable);
-#endif
 
 	if (lt_overrides->alternate_scrambler_reset) {
 		if (*lt_overrides->alternate_scrambler_reset)
@@ -1367,10 +1661,11 @@ enum link_training_result dc_link_dp_sync_lt_attempt(
 	/* 2. perform link training (set link training done
 	 *  to false is done as well)
 	 */
-	lt_status = perform_clock_recovery_sequence(link, &lt_settings);
+	lt_status = perform_clock_recovery_sequence(link, &lt_settings, DPRX);
 	if (lt_status == LINK_TRAINING_SUCCESS) {
 		lt_status = perform_channel_equalization_sequence(link,
-						&lt_settings);
+						&lt_settings,
+						DPRX);
 	}
 
 	/* 3. Sync LT must skip TRAINING_PATTERN_SET:0 (video pattern)*/
@@ -1387,9 +1682,7 @@ bool dc_link_dp_sync_lt_end(struct dc_link *link, bool link_down)
 	 */
 	if (link_down == true) {
 		dp_disable_link_phy(link, link->connector_signal);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		dp_set_fec_ready(link, false);
-#endif
 	}
 
 	link->sync_lt_in_progress = false;
@@ -1423,6 +1716,22 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 			max_link_cap.link_spread)
 		max_link_cap.link_spread =
 				link->reported_link_cap.link_spread;
+	/*
+	 * account for lttpr repeaters cap
+	 * notes: repeaters do not snoop in the DPRX Capabilities addresses (3.6.3).
+	 */
+	if (!link->is_lttpr_mode_transparent) {
+		if (link->dpcd_caps.lttpr_caps.max_lane_count < max_link_cap.lane_count)
+			max_link_cap.lane_count = link->dpcd_caps.lttpr_caps.max_lane_count;
+
+		if (link->dpcd_caps.lttpr_caps.max_link_rate < max_link_cap.link_rate)
+			max_link_cap.link_rate = link->dpcd_caps.lttpr_caps.max_link_rate;
+
+		DC_LOG_HW_LINK_TRAINING("%s\n Training with LTTPR,  max_lane count %d max_link rate %d \n",
+						__func__,
+						max_link_cap.lane_count,
+						max_link_cap.link_rate);
+	}
 	return max_link_cap;
 }
 
@@ -1568,6 +1877,13 @@ bool dp_verify_link_cap(
 
 	max_link_cap = get_max_link_cap(link);
 
+	/* Grant extended timeout request */
+	if (!link->is_lttpr_mode_transparent && link->dpcd_caps.lttpr_caps.max_ext_timeout > 0) {
+		uint8_t grant = link->dpcd_caps.lttpr_caps.max_ext_timeout & 0x80;
+
+		core_link_write_dpcd(link, DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT, &grant, sizeof(grant));
+	}
+
 	/* TODO implement override and monitor patch later */
 
 	/* try to train the link from high to low to
@@ -1576,6 +1892,16 @@ bool dp_verify_link_cap(
 	/* disable PHY done possible by BIOS, will be done by driver itself */
 	dp_disable_link_phy(link, link->connector_signal);
 
+	/* Temporary Renoir-specific workaround for SWDEV-215184;
+	 * PHY will sometimes be in bad state on hotplugging display from certain USB-C dongle,
+	 * so add extra cycle of enabling and disabling the PHY before first link training.
+	 */
+	if (link->link_enc->features.flags.bits.DP_IS_USB_C &&
+			link->dc->debug.usbc_combo_phy_reset_wa) {
+		dp_enable_link_phy(link, link->connector_signal, dp_cs_id, cur);
+		dp_disable_link_phy(link, link->connector_signal);
+	}
+
 	dp_cs_id = get_clock_source_id(link);
 
 	/* link training starts with the maximum common settings
@@ -2280,6 +2606,7 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link)
 	dc_link_dp_set_test_pattern(
 		link,
 		test_pattern,
+		DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED,
 		&link_training_settings,
 		test_80_bit_pattern,
 		(DP_TEST_80BIT_CUSTOM_PATTERN_79_72 -
@@ -2291,6 +2618,8 @@ static void dp_test_send_link_test_pattern(struct dc_link *link)
 	union link_test_pattern dpcd_test_pattern;
 	union test_misc dpcd_test_params;
 	enum dp_test_pattern test_pattern;
+	enum dp_test_pattern_color_space test_pattern_color_space =
+			DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED;
 
 	memset(&dpcd_test_pattern, 0, sizeof(dpcd_test_pattern));
 	memset(&dpcd_test_params, 0, sizeof(dpcd_test_params));
@@ -2325,14 +2654,105 @@ static void dp_test_send_link_test_pattern(struct dc_link *link)
 	break;
 	}
 
+	test_pattern_color_space = dpcd_test_params.bits.YCBCR_COEFS ?
+			DP_TEST_PATTERN_COLOR_SPACE_YCBCR709 :
+			DP_TEST_PATTERN_COLOR_SPACE_YCBCR601;
+
 	dc_link_dp_set_test_pattern(
 			link,
 			test_pattern,
+			test_pattern_color_space,
 			NULL,
 			NULL,
 			0);
 }
 
+static void dp_test_get_audio_test_data(struct dc_link *link, bool disable_video)
+{
+	union audio_test_mode            dpcd_test_mode = {0};
+	struct audio_test_pattern_type   dpcd_pattern_type = {0};
+	union audio_test_pattern_period  dpcd_pattern_period[AUDIO_CHANNELS_COUNT] = {0};
+	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_AUDIO_OPERATOR_DEFINED;
+
+	struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
+	struct pipe_ctx *pipe_ctx = &pipes[0];
+	unsigned int channel_count;
+	unsigned int channel = 0;
+	unsigned int modes = 0;
+	unsigned int sampling_rate_in_hz = 0;
+
+	// get audio test mode and test pattern parameters
+	core_link_read_dpcd(
+		link,
+		DP_TEST_AUDIO_MODE,
+		&dpcd_test_mode.raw,
+		sizeof(dpcd_test_mode));
+
+	core_link_read_dpcd(
+		link,
+		DP_TEST_AUDIO_PATTERN_TYPE,
+		&dpcd_pattern_type.value,
+		sizeof(dpcd_pattern_type));
+
+	channel_count = dpcd_test_mode.bits.channel_count + 1;
+
+	// read pattern periods for requested channels when sawTooth pattern is requested
+	if (dpcd_pattern_type.value == AUDIO_TEST_PATTERN_SAWTOOTH ||
+			dpcd_pattern_type.value == AUDIO_TEST_PATTERN_OPERATOR_DEFINED) {
+
+		test_pattern = (dpcd_pattern_type.value == AUDIO_TEST_PATTERN_SAWTOOTH) ?
+				DP_TEST_PATTERN_AUDIO_SAWTOOTH : DP_TEST_PATTERN_AUDIO_OPERATOR_DEFINED;
+		// read period for each channel
+		for (channel = 0; channel < channel_count; channel++) {
+			core_link_read_dpcd(
+							link,
+							DP_TEST_AUDIO_PERIOD_CH1 + channel,
+							&dpcd_pattern_period[channel].raw,
+							sizeof(dpcd_pattern_period[channel]));
+		}
+	}
+
+	// translate sampling rate
+	switch (dpcd_test_mode.bits.sampling_rate) {
+	case AUDIO_SAMPLING_RATE_32KHZ:
+		sampling_rate_in_hz = 32000;
+		break;
+	case AUDIO_SAMPLING_RATE_44_1KHZ:
+		sampling_rate_in_hz = 44100;
+		break;
+	case AUDIO_SAMPLING_RATE_48KHZ:
+		sampling_rate_in_hz = 48000;
+		break;
+	case AUDIO_SAMPLING_RATE_88_2KHZ:
+		sampling_rate_in_hz = 88200;
+		break;
+	case AUDIO_SAMPLING_RATE_96KHZ:
+		sampling_rate_in_hz = 96000;
+		break;
+	case AUDIO_SAMPLING_RATE_176_4KHZ:
+		sampling_rate_in_hz = 176400;
+		break;
+	case AUDIO_SAMPLING_RATE_192KHZ:
+		sampling_rate_in_hz = 192000;
+		break;
+	default:
+		sampling_rate_in_hz = 0;
+		break;
+	}
+
+	link->audio_test_data.flags.test_requested = 1;
+	link->audio_test_data.flags.disable_video = disable_video;
+	link->audio_test_data.sampling_rate = sampling_rate_in_hz;
+	link->audio_test_data.channel_count = channel_count;
+	link->audio_test_data.pattern_type = test_pattern;
+
+	if (test_pattern == DP_TEST_PATTERN_AUDIO_SAWTOOTH) {
+		for (modes = 0; modes < pipe_ctx->stream->audio_info.mode_count; modes++) {
+			link->audio_test_data.pattern_period[modes] = dpcd_pattern_period[modes].bits.pattern_period;
+		}
+	}
+}
+
 static void handle_automated_test(struct dc_link *link)
 {
 	union test_request test_request;
@@ -2362,6 +2782,12 @@ static void handle_automated_test(struct dc_link *link)
 		dp_test_send_link_test_pattern(link);
 		test_response.bits.ACK = 1;
 	}
+
+	if (test_request.bits.AUDIO_TEST_PATTERN) {
+		dp_test_get_audio_test_data(link, test_request.bits.TEST_AUDIO_DISABLED_VIDEO);
+		test_response.bits.ACK = 1;
+	}
+
 	if (test_request.bits.PHY_TEST_PATTERN) {
 		dp_test_send_phy_test_pattern(link);
 		test_response.bits.ACK = 1;
@@ -2381,9 +2807,9 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 	union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } };
 	union device_service_irq device_service_clear = { { 0 } };
 	enum dc_status result;
-
 	bool status = false;
 	struct pipe_ctx *pipe_ctx;
+	struct dc_link_settings previous_link_settings;
 	int i;
 
 	if (out_link_loss)
@@ -2447,29 +2873,37 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 	/* For now we only handle 'Downstream port status' case.
 	 * If we got sink count changed it means
 	 * Downstream port status changed,
-	 * then DM should call DC to do the detection. */
-	if (hpd_rx_irq_check_link_loss_status(
-		link,
-		&hpd_irq_dpcd_data)) {
+	 * then DM should call DC to do the detection.
+	 * NOTE: Do not handle link loss on eDP since it is internal link*/
+	if ((link->connector_signal != SIGNAL_TYPE_EDP) &&
+		hpd_rx_irq_check_link_loss_status(
+			link,
+			&hpd_irq_dpcd_data)) {
 		/* Connectivity log: link loss */
 		CONN_DATA_LINK_LOSS(link,
 					hpd_irq_dpcd_data.raw,
 					sizeof(hpd_irq_dpcd_data),
 					"Status: ");
 
-		perform_link_training_with_retries(link,
-			&link->cur_link_settings,
-			true, LINK_TRAINING_ATTEMPTS);
-
 		for (i = 0; i < MAX_PIPES; i++) {
 			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
-			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
-					pipe_ctx->stream->dpms_off == false &&
-					pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
-				dc_link_allocate_mst_payload(pipe_ctx);
-			}
+			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link)
+				break;
 		}
 
+		if (pipe_ctx == NULL || pipe_ctx->stream == NULL)
+			return false;
+
+		previous_link_settings = link->cur_link_settings;
+
+		perform_link_training_with_retries(&previous_link_settings,
+			true, LINK_TRAINING_ATTEMPTS,
+			pipe_ctx,
+			pipe_ctx->stream->signal);
+
+		if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
+			dc_link_reallocate_mst_payload(link);
+
 		status = false;
 		if (out_link_loss)
 			*out_link_loss = true;
@@ -2697,7 +3131,6 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 		int length)
 {
 	int retry = 0;
-	union dp_downstream_port_present ds_port = { 0 };
 
 	if (!link->dpcd_caps.dpcd_rev.raw) {
 		do {
@@ -2710,9 +3143,6 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 		} while (retry++ < 4 && !link->dpcd_caps.dpcd_rev.raw);
 	}
 
-	ds_port.byte = dpcd_data[DP_DOWNSTREAMPORT_PRESENT -
-				 DP_DPCD_REV];
-
 	if (link->dpcd_caps.dongle_type == DISPLAY_DONGLE_DP_VGA_CONVERTER) {
 		switch (link->dpcd_caps.branch_dev_id) {
 		/* 0010FA active dongles (DP-VGA, DP-DLDVI converters) power down
@@ -2737,7 +3167,11 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 
 static bool retrieve_link_cap(struct dc_link *link)
 {
-	uint8_t dpcd_data[DP_ADAPTER_CAP - DP_DPCD_REV + 1];
+	/* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16,
+	 * which means size 16 will be good for both of those DPCD register block reads
+	 */
+	uint8_t dpcd_data[16];
+	uint8_t lttpr_dpcd_data[6];
 
 	/*Only need to read 1 byte starting from DP_DPRX_FEATURE_ENUMERATION_LIST.
 	 */
@@ -2753,7 +3187,19 @@ static bool retrieve_link_cap(struct dc_link *link)
 	int i;
 	struct dp_sink_hw_fw_revision dp_hw_fw_revision;
 
+	/* Set default timeout to 3.2ms and read LTTPR capabilities */
+	bool ext_timeout_support = link->dc->caps.extended_aux_timeout_support &&
+			!link->dc->config.disable_extended_timeout_support;
+
+	link->is_lttpr_mode_transparent = true;
+
+	if (ext_timeout_support) {
+		dc_link_aux_configure_timeout(link->ddc,
+					LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD);
+	}
+
 	memset(dpcd_data, '\0', sizeof(dpcd_data));
+	memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data));
 	memset(&down_strm_port_count,
 		'\0', sizeof(union down_stream_port_count));
 	memset(&edp_config_cap, '\0',
@@ -2785,6 +3231,52 @@ static bool retrieve_link_cap(struct dc_link *link)
 		return false;
 	}
 
+	if (ext_timeout_support) {
+
+		status = core_link_read_dpcd(
+				link,
+				DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV,
+				lttpr_dpcd_data,
+				sizeof(lttpr_dpcd_data));
+
+		link->dpcd_caps.lttpr_caps.revision.raw =
+				lttpr_dpcd_data[DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.max_link_rate =
+				lttpr_dpcd_data[DP_MAX_LINK_RATE_PHY_REPEATER -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.phy_repeater_cnt =
+				lttpr_dpcd_data[DP_PHY_REPEATER_CNT -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.max_lane_count =
+				lttpr_dpcd_data[DP_MAX_LANE_COUNT_PHY_REPEATER -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.mode =
+				lttpr_dpcd_data[DP_PHY_REPEATER_MODE -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		link->dpcd_caps.lttpr_caps.max_ext_timeout =
+				lttpr_dpcd_data[DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT -
+								DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+
+		if (link->dpcd_caps.lttpr_caps.phy_repeater_cnt > 0 &&
+				link->dpcd_caps.lttpr_caps.max_lane_count > 0 &&
+				link->dpcd_caps.lttpr_caps.max_lane_count <= 4 &&
+				link->dpcd_caps.lttpr_caps.revision.raw >= 0x14) {
+			link->is_lttpr_mode_transparent = false;
+		} else {
+			/*No lttpr reset timeout to its default value*/
+			link->is_lttpr_mode_transparent = true;
+			dc_link_aux_configure_timeout(link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD);
+		}
+
+		CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: ");
+	}
+
 	{
 		union training_aux_rd_interval aux_rd_interval;
 
@@ -2792,7 +3284,7 @@ static bool retrieve_link_cap(struct dc_link *link)
 			dpcd_data[DP_TRAINING_AUX_RD_INTERVAL];
 
 		link->dpcd_caps.ext_receiver_cap_field_present =
-				aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1 ? true:false;
+				aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1;
 
 		if (aux_rd_interval.bits.EXT_RECEIVER_CAP_FIELD_PRESENT == 1) {
 			uint8_t ext_cap_data[16];
@@ -2923,7 +3415,6 @@ static bool retrieve_link_cap(struct dc_link *link)
 		dp_hw_fw_revision.ieee_fw_rev,
 		sizeof(dp_hw_fw_revision.ieee_fw_rev));
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	memset(&link->dpcd_caps.dsc_caps, '\0',
 			sizeof(link->dpcd_caps.dsc_caps));
 	memset(&link->dpcd_caps.fec_cap, '\0', sizeof(link->dpcd_caps.fec_cap));
@@ -2945,7 +3436,6 @@ static bool retrieve_link_cap(struct dc_link *link)
 				link->dpcd_caps.dsc_caps.dsc_ext_caps.raw,
 				sizeof(link->dpcd_caps.dsc_caps.dsc_ext_caps.raw));
 	}
-#endif
 
 	/* Connectivity log: detection */
 	CONN_DATA_DETECT(link, dpcd_data, sizeof(dpcd_data), "Rx Caps: ");
@@ -2953,6 +3443,68 @@ static bool retrieve_link_cap(struct dc_link *link)
 	return true;
 }
 
+bool dp_overwrite_extended_receiver_cap(struct dc_link *link)
+{
+	uint8_t dpcd_data[16];
+	uint32_t read_dpcd_retry_cnt = 3;
+	enum dc_status status = DC_ERROR_UNEXPECTED;
+	union dp_downstream_port_present ds_port = { 0 };
+	union down_stream_port_count down_strm_port_count;
+	union edp_configuration_cap edp_config_cap;
+
+	int i;
+
+	for (i = 0; i < read_dpcd_retry_cnt; i++) {
+		status = core_link_read_dpcd(
+				link,
+				DP_DPCD_REV,
+				dpcd_data,
+				sizeof(dpcd_data));
+		if (status == DC_OK)
+			break;
+	}
+
+	link->dpcd_caps.dpcd_rev.raw =
+		dpcd_data[DP_DPCD_REV - DP_DPCD_REV];
+
+	if (dpcd_data[DP_MAX_LANE_COUNT - DP_DPCD_REV] == 0)
+		return false;
+
+	ds_port.byte = dpcd_data[DP_DOWNSTREAMPORT_PRESENT -
+			DP_DPCD_REV];
+
+	get_active_converter_info(ds_port.byte, link);
+
+	down_strm_port_count.raw = dpcd_data[DP_DOWN_STREAM_PORT_COUNT -
+			DP_DPCD_REV];
+
+	link->dpcd_caps.allow_invalid_MSA_timing_param =
+		down_strm_port_count.bits.IGNORE_MSA_TIMING_PARAM;
+
+	link->dpcd_caps.max_ln_count.raw = dpcd_data[
+		DP_MAX_LANE_COUNT - DP_DPCD_REV];
+
+	link->dpcd_caps.max_down_spread.raw = dpcd_data[
+		DP_MAX_DOWNSPREAD - DP_DPCD_REV];
+
+	link->reported_link_cap.lane_count =
+		link->dpcd_caps.max_ln_count.bits.MAX_LANE_COUNT;
+	link->reported_link_cap.link_rate = dpcd_data[
+		DP_MAX_LINK_RATE - DP_DPCD_REV];
+	link->reported_link_cap.link_spread =
+		link->dpcd_caps.max_down_spread.bits.MAX_DOWN_SPREAD ?
+		LINK_SPREAD_05_DOWNSPREAD_30KHZ : LINK_SPREAD_DISABLED;
+
+	edp_config_cap.raw = dpcd_data[
+		DP_EDP_CONFIGURATION_CAP - DP_DPCD_REV];
+	link->dpcd_caps.panel_mode_edp =
+		edp_config_cap.bits.ALT_SCRAMBLER_RESET;
+	link->dpcd_caps.dpcd_display_control_capable =
+		edp_config_cap.bits.DPCD_DISPLAY_CONTROL_CAPABLE;
+
+	return true;
+}
+
 bool detect_dp_sink_caps(struct dc_link *link)
 {
 	return retrieve_link_cap(link);
@@ -3067,21 +3619,20 @@ static bool is_dp_phy_pattern(enum dp_test_pattern test_pattern)
 
 static void set_crtc_test_pattern(struct dc_link *link,
 				struct pipe_ctx *pipe_ctx,
-				enum dp_test_pattern test_pattern)
+				enum dp_test_pattern test_pattern,
+				enum dp_test_pattern_color_space test_pattern_color_space)
 {
 	enum controller_dp_test_pattern controller_test_pattern;
 	enum dc_color_depth color_depth = pipe_ctx->
 		stream->timing.display_color_depth;
 	struct bit_depth_reduction_params params;
 	struct output_pixel_processor *opp = pipe_ctx->stream_res.opp;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	int width = pipe_ctx->stream->timing.h_addressable +
 		pipe_ctx->stream->timing.h_border_left +
 		pipe_ctx->stream->timing.h_border_right;
 	int height = pipe_ctx->stream->timing.v_addressable +
 		pipe_ctx->stream->timing.v_border_bottom +
 		pipe_ctx->stream->timing.v_border_top;
-#endif
 
 	memset(&params, 0, sizeof(params));
 
@@ -3125,10 +3676,29 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
 			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				controller_test_pattern, color_depth);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		else if (opp->funcs->opp_set_disp_pattern_generator) {
 			struct pipe_ctx *odm_pipe;
+			enum controller_dp_color_space controller_color_space;
 			int opp_cnt = 1;
+			uint8_t count = 0;
+
+			switch (test_pattern_color_space) {
+			case DP_TEST_PATTERN_COLOR_SPACE_RGB:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_RGB;
+				break;
+			case DP_TEST_PATTERN_COLOR_SPACE_YCBCR601:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_YCBCR601;
+				break;
+			case DP_TEST_PATTERN_COLOR_SPACE_YCBCR709:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_YCBCR709;
+				break;
+			case DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED:
+			default:
+				controller_color_space = CONTROLLER_DP_COLOR_SPACE_UDEFINED;
+				DC_LOG_ERROR("%s: Color space must be defined for test pattern", __func__);
+				ASSERT(0);
+				break;
+			}
 
 			for (odm_pipe = pipe_ctx->next_odm_pipe; odm_pipe; odm_pipe = odm_pipe->next_odm_pipe)
 				opp_cnt++;
@@ -3141,6 +3711,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 				odm_opp->funcs->opp_program_bit_depth_reduction(odm_opp, &params);
 				odm_opp->funcs->opp_set_disp_pattern_generator(odm_opp,
 					controller_test_pattern,
+					controller_color_space,
 					color_depth,
 					NULL,
 					width,
@@ -3148,12 +3719,18 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			}
 			opp->funcs->opp_set_disp_pattern_generator(opp,
 				controller_test_pattern,
+				controller_color_space,
 				color_depth,
 				NULL,
 				width,
 				height);
+			/* wait for dpg to blank pixel data with test pattern */
+			for (count = 0; count < 1000; count++)
+				if (opp->funcs->dpg_is_blanked(opp))
+					break;
+				else
+					udelay(100);
 		}
-#endif
 	}
 	break;
 	case DP_TEST_PATTERN_VIDEO_MODE:
@@ -3166,7 +3743,6 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 				color_depth);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		else if (opp->funcs->opp_set_disp_pattern_generator) {
 			struct pipe_ctx *odm_pipe;
 			int opp_cnt = 1;
@@ -3181,6 +3757,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 				odm_opp->funcs->opp_program_bit_depth_reduction(odm_opp, &params);
 				odm_opp->funcs->opp_set_disp_pattern_generator(odm_opp,
 					CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+					CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 					color_depth,
 					NULL,
 					width,
@@ -3188,12 +3765,12 @@ static void set_crtc_test_pattern(struct dc_link *link,
 			}
 			opp->funcs->opp_set_disp_pattern_generator(opp,
 				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+				CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 				color_depth,
 				NULL,
 				width,
 				height);
 		}
-#endif
 	}
 	break;
 
@@ -3205,6 +3782,7 @@ static void set_crtc_test_pattern(struct dc_link *link,
 bool dc_link_dp_set_test_pattern(
 	struct dc_link *link,
 	enum dp_test_pattern test_pattern,
+	enum dp_test_pattern_color_space test_pattern_color_space,
 	const struct link_training_settings *p_link_settings,
 	const unsigned char *p_custom_pattern,
 	unsigned int cust_pattern_size)
@@ -3233,7 +3811,7 @@ bool dc_link_dp_set_test_pattern(
 	if (link->test_pattern_enabled && test_pattern ==
 			DP_TEST_PATTERN_VIDEO_MODE) {
 		/* Set CRTC Test Pattern */
-		set_crtc_test_pattern(link, pipe_ctx, test_pattern);
+		set_crtc_test_pattern(link, pipe_ctx, test_pattern, test_pattern_color_space);
 		dp_set_hw_test_pattern(link, test_pattern,
 				(uint8_t *)p_custom_pattern,
 				(uint32_t)cust_pattern_size);
@@ -3256,8 +3834,8 @@ bool dc_link_dp_set_test_pattern(
 	if (is_dp_phy_pattern(test_pattern)) {
 		/* Set DPCD Lane Settings before running test pattern */
 		if (p_link_settings != NULL) {
-			dp_set_hw_lane_settings(link, p_link_settings);
-			dpcd_set_lane_settings(link, p_link_settings);
+			dp_set_hw_lane_settings(link, p_link_settings, DPRX);
+			dpcd_set_lane_settings(link, p_link_settings, DPRX);
 		}
 
 		/* Blank stream if running test pattern */
@@ -3348,7 +3926,7 @@ bool dc_link_dp_set_test_pattern(
 		}
 	} else {
 	/* CRTC Patterns */
-		set_crtc_test_pattern(link, pipe_ctx, test_pattern);
+		set_crtc_test_pattern(link, pipe_ctx, test_pattern, test_pattern_color_space);
 		/* Set Test Pattern state */
 		link->test_pattern_enabled = true;
 	}
@@ -3468,7 +4046,6 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link)
 	return DP_PANEL_MODE_DEFAULT;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 void dp_set_fec_ready(struct dc_link *link, bool ready)
 {
 	/* FEC has to be "set ready" before the link training.
@@ -3538,5 +4115,4 @@ void dp_set_fec_enable(struct dc_link *link, bool enable)
 		}
 	}
 }
-#endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index a519dbc5ecb6..ddb855045767 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -12,12 +12,38 @@
 #include "dc_link_ddc.h"
 #include "dm_helpers.h"
 #include "dpcd_defs.h"
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "resource.h"
-#endif
+
+static uint8_t convert_to_count(uint8_t lttpr_repeater_count)
+{
+	switch (lttpr_repeater_count) {
+	case 0x80: // 1 lttpr repeater
+		return 1;
+	case 0x40: // 2 lttpr repeaters
+		return 2;
+	case 0x20: // 3 lttpr repeaters
+		return 3;
+	case 0x10: // 4 lttpr repeaters
+		return 4;
+	case 0x08: // 5 lttpr repeaters
+		return 5;
+	case 0x04: // 6 lttpr repeaters
+		return 6;
+	case 0x02: // 7 lttpr repeaters
+		return 7;
+	case 0x01: // 8 lttpr repeaters
+		return 8;
+	default:
+		break;
+	}
+	return 0; // invalid value
+}
+
+static inline bool is_immediate_downstream(struct dc_link *link, uint32_t offset)
+{
+	return (convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == offset);
+}
 
 enum dc_status core_link_read_dpcd(
 	struct dc_link *link,
@@ -69,8 +95,8 @@ void dp_enable_link_phy(
 	const struct dc_link_settings *link_settings)
 {
 	struct link_encoder *link_enc = link->link_enc;
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	struct pipe_ctx *pipes =
 			link->dc->current_state->res_ctx.pipe_ctx;
@@ -147,15 +173,20 @@ bool edp_receiver_ready_T9(struct dc_link *link)
 }
 bool edp_receiver_ready_T7(struct dc_link *link)
 {
-	unsigned int tries = 0;
 	unsigned char sinkstatus = 0;
 	unsigned char edpRev = 0;
 	enum dc_status result = DC_OK;
 
+	/* use absolute time stamp to constrain max T7*/
+	unsigned long long enter_timestamp = 0;
+	unsigned long long finish_timestamp = 0;
+	unsigned long long time_taken_in_ns = 0;
+
 	result = core_link_read_dpcd(link, DP_EDP_DPCD_REV, &edpRev, sizeof(edpRev));
 	if (result == DC_OK && edpRev < DP_EDP_12)
 		return true;
 	/* start from eDP version 1.2, SINK_STAUS indicate the sink is ready.*/
+	enter_timestamp = dm_get_timestamp(link->ctx);
 	do {
 		sinkstatus = 0;
 		result = core_link_read_dpcd(link, DP_SINK_STATUS, &sinkstatus, sizeof(sinkstatus));
@@ -163,8 +194,10 @@ bool edp_receiver_ready_T7(struct dc_link *link)
 			break;
 		if (result != DC_OK)
 			break;
-		udelay(25); //MAx T7 is 50ms
-	} while (++tries < 300);
+		udelay(25);
+		finish_timestamp = dm_get_timestamp(link->ctx);
+		time_taken_in_ns = dm_get_elapse_time_in_ns(link->ctx, finish_timestamp, enter_timestamp);
+	} while (time_taken_in_ns < 50 * 1000000); //MAx T7 is 50ms
 
 	if (link->local_sink->edid_caps.panel_patch.extra_t7_ms > 0)
 		udelay(link->local_sink->edid_caps.panel_patch.extra_t7_ms * 1000);
@@ -174,8 +207,8 @@ bool edp_receiver_ready_T7(struct dc_link *link)
 
 void dp_disable_link_phy(struct dc_link *link, enum signal_type signal)
 {
-	struct dc  *core_dc = link->ctx->dc;
-	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+	struct dc  *dc = link->ctx->dc;
+	struct dmcu *dmcu = dc->res_pool->dmcu;
 
 	if (!link->wa_flags.dp_keep_receiver_powered)
 		dp_receiver_power_ctrl(link, false);
@@ -212,7 +245,8 @@ void dp_disable_link_phy_mst(struct dc_link *link, enum signal_type signal)
 
 bool dp_set_hw_training_pattern(
 	struct dc_link *link,
-	enum dc_dp_training_pattern pattern)
+	enum dc_dp_training_pattern pattern,
+	uint32_t offset)
 {
 	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
 
@@ -240,10 +274,14 @@ bool dp_set_hw_training_pattern(
 
 void dp_set_hw_lane_settings(
 	struct dc_link *link,
-	const struct link_training_settings *link_settings)
+	const struct link_training_settings *link_settings,
+	uint32_t offset)
 {
 	struct link_encoder *encoder = link->link_enc;
 
+	if (!link->is_lttpr_mode_transparent && !is_immediate_downstream(link, offset))
+		return;
+
 	/* call Encoder to set lane settings */
 	encoder->funcs->dp_set_lane_settings(encoder, link_settings);
 }
@@ -302,20 +340,12 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 			memset(&link->cur_link_settings, 0,
 				sizeof(link->cur_link_settings));
 
-			link->link_enc->funcs->enable_dp_output(
-						link->link_enc,
-						link_setting,
-						pipes[i].clock_source->id);
-			link->cur_link_settings = *link_setting;
-
-			dp_receiver_power_ctrl(link, true);
-
 			perform_link_training_with_retries(
-					link,
 					link_setting,
 					skip_video_pattern,
-					LINK_TRAINING_ATTEMPTS);
-
+					LINK_TRAINING_ATTEMPTS,
+					&pipes[i],
+					SIGNAL_TYPE_DISPLAY_PORT);
 
 			link->dc->hwss.enable_stream(&pipes[i]);
 
@@ -339,7 +369,6 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define DC_LOGGER \
 	dsc->ctx->logger
 static void dsc_optc_config_log(struct display_stream_compressor *dsc,
@@ -365,14 +394,14 @@ static void dsc_optc_config_log(struct display_stream_compressor *dsc,
 
 static bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable)
 {
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	bool result = false;
 
-	if (IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment))
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		result = true;
 	else
-		result = dm_helpers_dp_write_dsc_enable(core_dc->ctx, stream, enable);
+		result = dm_helpers_dp_write_dsc_enable(dc->ctx, stream, enable);
 	return result;
 }
 
@@ -382,7 +411,7 @@ static bool dp_set_dsc_on_rx(struct pipe_ctx *pipe_ctx, bool enable)
 void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 1;
@@ -418,7 +447,7 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 		optc_dsc_mode = dsc_optc_cfg.is_pixel_format_444 ? OPTC_DSC_ENABLED_444 : OPTC_DSC_ENABLED_NATIVE_SUBSAMPLED;
 
 		/* Enable DSC in encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			DC_LOG_DSC("Setting stream encoder DSC config for engine %d:", (int)pipe_ctx->stream_res.stream_enc->id);
 			dsc_optc_config_log(dsc, &dsc_optc_cfg);
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config(pipe_ctx->stream_res.stream_enc,
@@ -443,7 +472,7 @@ void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
 				OPTC_DSC_DISABLED, 0, 0);
 
 		/* disable DSC in stream encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_config(
 					pipe_ctx->stream_res.stream_enc,
 					OPTC_DSC_DISABLED, 0, 0);
@@ -486,7 +515,7 @@ out:
 bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 {
 	struct display_stream_compressor *dsc = pipe_ctx->stream_res.dsc;
-	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 
 	if (!pipe_ctx->stream->timing.flags.DSC || !dsc)
@@ -496,6 +525,9 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 		struct dsc_config dsc_cfg;
 		uint8_t dsc_packed_pps[128];
 
+		memset(&dsc_cfg, 0, sizeof(dsc_cfg));
+		memset(dsc_packed_pps, 0, 128);
+
 		/* Enable DSC hw block */
 		dsc_cfg.pic_width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right;
 		dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom;
@@ -505,7 +537,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 
 		DC_LOG_DSC(" ");
 		dsc->funcs->dsc_get_packed_pps(dsc, &dsc_cfg, &dsc_packed_pps[0]);
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			DC_LOG_DSC("Setting stream encoder DSC PPS SDP for engine %d\n", (int)pipe_ctx->stream_res.stream_enc->id);
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
 									pipe_ctx->stream_res.stream_enc,
@@ -514,7 +546,7 @@ bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable)
 		}
 	} else {
 		/* disable DSC PPS in stream encoder */
-		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
+		if (dc_is_dp_signal(stream->signal) && !IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 			pipe_ctx->stream_res.stream_enc->funcs->dp_set_dsc_pps_info_packet(
 						pipe_ctx->stream_res.stream_enc, false, NULL);
 		}
@@ -537,5 +569,4 @@ bool dp_update_dsc_config(struct pipe_ctx *pipe_ctx)
 	dp_set_dsc_pps_sdp(pipe_ctx, true);
 	return true;
 }
-#endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 37698305a2dc..a0eb9e533a61 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -46,15 +46,11 @@
 #include "dce100/dce100_resource.h"
 #include "dce110/dce110_resource.h"
 #include "dce112/dce112_resource.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/dcn10_resource.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/dcn20_resource.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/dcn21_resource.h"
-#endif
 #include "dce120/dce120_resource.h"
 
 #define DC_LOGGER_INIT(logger)
@@ -99,23 +95,19 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 		else
 			dc_version = DCE_VERSION_12_0;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case FAMILY_RV:
 		dc_version = DCN_VERSION_1_0;
 		if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_1_01;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 		if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev))
 			dc_version = DCN_VERSION_2_1;
-#endif
 		break;
 #endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case FAMILY_NV:
 		dc_version = DCN_VERSION_2_0;
 		break;
-#endif
 	default:
 		dc_version = DCE_VERSION_UNKNOWN;
 		break;
@@ -162,20 +154,16 @@ struct resource_pool *dc_create_resource_pool(struct dc  *dc,
 				init_data->num_virtual_links, dc);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		res_pool = dcn10_create_resource_pool(init_data, dc);
 		break;
-#endif
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		res_pool = dcn20_create_resource_pool(init_data, dc);
 		break;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		res_pool = dcn21_create_resource_pool(init_data, dc);
 		break;
@@ -951,44 +939,44 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx)
 	data->inits.v_c_bot = dc_fixpt_add(data->inits.v_c, data->ratios.vert_c);
 
 }
-static bool are_rects_integer_multiples(struct rect src, struct rect dest)
-{
-	if (dest.width  >= src.width  && dest.width  % src.width  == 0 &&
-		dest.height >= src.height && dest.height % src.height == 0)
-		return true;
-
-	return false;
-}
 
-static void calculate_integer_scaling(struct pipe_ctx *pipe_ctx)
+/*
+ * When handling 270 rotation in mixed SLS mode, we have
+ * stream->timing.h_border_left that is non zero.  If we are doing
+ * pipe-splitting, this h_border_left value gets added to recout.x and when it
+ * calls calculate_inits_and_adj_vp() and
+ * adjust_vp_and_init_for_seamless_clip(), it can cause viewport.height for a
+ * pipe to be incorrect.
+ *
+ * To fix this, instead of using stream->timing.h_border_left, we can use
+ * stream->dst.x to represent the border instead.  So we will set h_border_left
+ * to 0 and shift the appropriate amount in stream->dst.x.  We will then
+ * perform all calculations in resource_build_scaling_params() based on this
+ * and then restore the h_border_left and stream->dst.x to their original
+ * values.
+ *
+ * shift_border_left_to_dst() will shift the amount of h_border_left to
+ * stream->dst.x and set h_border_left to 0.  restore_border_left_from_dst()
+ * will restore h_border_left and stream->dst.x back to their original values
+ * We also need to make sure pipe_ctx->plane_res.scl_data.h_active uses the
+ * original h_border_left value in its calculation.
+ */
+int shift_border_left_to_dst(struct pipe_ctx *pipe_ctx)
 {
-	if (!pipe_ctx->plane_state->scaling_quality.integer_scaling)
-		return;
-
-	//for Centered Mode
-	if (pipe_ctx->stream->dst.width  == pipe_ctx->stream->src.width &&
-		pipe_ctx->stream->dst.height == pipe_ctx->stream->src.height) {
-		// calculate maximum # of replication of src onto addressable
-		unsigned int integer_multiple = min(
-				pipe_ctx->stream->timing.h_addressable / pipe_ctx->stream->src.width,
-				pipe_ctx->stream->timing.v_addressable  / pipe_ctx->stream->src.height);
-
-		//scale dst
-		pipe_ctx->stream->dst.width  = integer_multiple * pipe_ctx->stream->src.width;
-		pipe_ctx->stream->dst.height = integer_multiple * pipe_ctx->stream->src.height;
+	int store_h_border_left = pipe_ctx->stream->timing.h_border_left;
 
-		//center dst onto addressable
-		pipe_ctx->stream->dst.x = (pipe_ctx->stream->timing.h_addressable - pipe_ctx->stream->dst.width)/2;
-		pipe_ctx->stream->dst.y = (pipe_ctx->stream->timing.v_addressable - pipe_ctx->stream->dst.height)/2;
+	if (store_h_border_left) {
+		pipe_ctx->stream->timing.h_border_left = 0;
+		pipe_ctx->stream->dst.x += store_h_border_left;
 	}
+	return store_h_border_left;
+}
 
-	//disable taps if src & dst are integer ratio
-	if (are_rects_integer_multiples(pipe_ctx->stream->src, pipe_ctx->stream->dst)) {
-		pipe_ctx->plane_state->scaling_quality.v_taps = 1;
-		pipe_ctx->plane_state->scaling_quality.h_taps = 1;
-		pipe_ctx->plane_state->scaling_quality.v_taps_c = 1;
-		pipe_ctx->plane_state->scaling_quality.h_taps_c = 1;
-	}
+void restore_border_left_from_dst(struct pipe_ctx *pipe_ctx,
+                                  int store_h_border_left)
+{
+	pipe_ctx->stream->dst.x -= store_h_border_left;
+	pipe_ctx->stream->timing.h_border_left = store_h_border_left;
 }
 
 bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
@@ -996,6 +984,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
 	bool res = false;
+	int store_h_border_left = shift_border_left_to_dst(pipe_ctx);
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 	/* Important: scaling ratio calculation requires pixel format,
 	 * lb depth calculation requires recout and taps require scaling ratios.
@@ -1004,14 +993,18 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.format = convert_pixel_format_to_dalsurface(
 			pipe_ctx->plane_state->format);
 
-	calculate_integer_scaling(pipe_ctx);
-
 	calculate_scaling_ratios(pipe_ctx);
 
 	calculate_viewport(pipe_ctx);
 
-	if (pipe_ctx->plane_res.scl_data.viewport.height < 16 || pipe_ctx->plane_res.scl_data.viewport.width < 16)
+	if (pipe_ctx->plane_res.scl_data.viewport.height < 16 ||
+		pipe_ctx->plane_res.scl_data.viewport.width < 16) {
+		if (store_h_border_left) {
+			restore_border_left_from_dst(pipe_ctx,
+				store_h_border_left);
+		}
 		return false;
+	}
 
 	calculate_recout(pipe_ctx);
 
@@ -1024,8 +1017,10 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.recout.x += timing->h_border_left;
 	pipe_ctx->plane_res.scl_data.recout.y += timing->v_border_top;
 
-	pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable + timing->h_border_left + timing->h_border_right;
-	pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
+	pipe_ctx->plane_res.scl_data.h_active = timing->h_addressable +
+		store_h_border_left + timing->h_border_right;
+	pipe_ctx->plane_res.scl_data.v_active = timing->v_addressable +
+		timing->v_border_top + timing->v_border_bottom;
 
 	/* Taps calculations */
 	if (pipe_ctx->plane_res.xfm != NULL)
@@ -1072,6 +1067,9 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 				plane_state->dst_rect.x,
 				plane_state->dst_rect.y);
 
+	if (store_h_border_left)
+		restore_border_left_from_dst(pipe_ctx, store_h_border_left);
+
 	return res;
 }
 
@@ -1217,7 +1215,7 @@ static struct pipe_ctx *acquire_free_pipe_for_head(
 	return pool->funcs->acquire_idle_pipe_for_layer(context, pool, head_pipe->stream);
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 static int acquire_first_split_pipe(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -1298,7 +1296,7 @@ bool dc_add_plane_to_context(
 
 		free_pipe = acquire_free_pipe_for_head(context, pool, head_pipe);
 
-	#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+	#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (!free_pipe) {
 			int pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 			if (pipe_idx >= 0)
@@ -1891,7 +1889,7 @@ static int acquire_resource_from_hw_enabled_state(
 	inst = link->link_enc->funcs->get_dig_frontend(link->link_enc);
 
 	if (inst == ENGINE_ID_UNKNOWN)
-		return false;
+		return -1;
 
 	for (i = 0; i < pool->stream_enc_count; i++) {
 		if (pool->stream_enc[i]->id == inst) {
@@ -1903,10 +1901,10 @@ static int acquire_resource_from_hw_enabled_state(
 
 	// tg_inst not found
 	if (i == pool->stream_enc_count)
-		return false;
+		return -1;
 
 	if (tg_inst >= pool->timing_generator_count)
-		return false;
+		return -1;
 
 	if (!res_ctx->pipe_ctx[tg_inst].stream) {
 		struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[tg_inst];
@@ -1919,8 +1917,26 @@ static int acquire_resource_from_hw_enabled_state(
 		pipe_ctx->plane_res.dpp = pool->dpps[tg_inst];
 		pipe_ctx->stream_res.opp = pool->opps[tg_inst];
 
-		if (pool->dpps[tg_inst])
+		if (pool->dpps[tg_inst]) {
 			pipe_ctx->plane_res.mpcc_inst = pool->dpps[tg_inst]->inst;
+
+			// Read DPP->MPCC->OPP Pipe from HW State
+			if (pool->mpc->funcs->read_mpcc_state) {
+				struct mpcc_state s = {0};
+
+				pool->mpc->funcs->read_mpcc_state(pool->mpc, pipe_ctx->plane_res.mpcc_inst, &s);
+
+				if (s.dpp_id < MAX_MPCC)
+					pool->mpc->mpcc_array[pipe_ctx->plane_res.mpcc_inst].dpp_id = s.dpp_id;
+
+				if (s.bot_mpcc_id < MAX_MPCC)
+					pool->mpc->mpcc_array[pipe_ctx->plane_res.mpcc_inst].mpcc_bot =
+							&pool->mpc->mpcc_array[s.bot_mpcc_id];
+
+				if (s.opp_id < MAX_OPP)
+					pipe_ctx->stream_res.opp->mpc_tree_params.opp_id = s.opp_id;
+			}
+		}
 		pipe_ctx->pipe_idx = tg_inst;
 
 		pipe_ctx->stream = stream;
@@ -1972,7 +1988,7 @@ enum dc_status resource_map_pool_resources(
 		/* acquire new resources */
 		pipe_idx = acquire_first_free_pipe(&context->res_ctx, pool, stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	if (pipe_idx < 0)
 		pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 #endif
@@ -2050,6 +2066,13 @@ void dc_resource_state_construct(
 	dst_ctx->clk_mgr = dc->clk_mgr;
 }
 
+
+bool dc_resource_is_dsc_encoding_supported(const struct dc *dc)
+{
+	return dc->res_pool->res_cap->num_dsc > 0;
+}
+
+
 /**
  * dc_validate_global_state() - Determine if HW can support a given state
  * Checks HW resource availability and bandwidth requirement.
@@ -2306,7 +2329,7 @@ static void set_avi_info_frame(
 		if (color_space == COLOR_SPACE_SRGB ||
 			color_space == COLOR_SPACE_2020_RGB_FULLRANGE) {
 			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_FULL_RANGE;
-			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_FULL_RANGE;
+			hdmi_info.bits.YQ0_YQ1 = YYC_QUANTIZATION_LIMITED_RANGE;
 		} else if (color_space == COLOR_SPACE_SRGB_LIMITED ||
 					color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE) {
 			hdmi_info.bits.Q0_Q1   = RGB_QUANTIZATION_LIMITED_RANGE;
@@ -2772,9 +2795,8 @@ void resource_build_bit_depth_reduction_params(struct dc_stream_state *stream,
 
 enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream)
 {
-	struct dc  *core_dc = dc;
 	struct dc_link *link = stream->link;
-	struct timing_generator *tg = core_dc->res_pool->timing_generators[0];
+	struct timing_generator *tg = dc->res_pool->timing_generators[0];
 	enum dc_status res = DC_OK;
 
 	calculate_phy_pix_clks(stream);
@@ -2837,3 +2859,48 @@ unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format)
 		return -1;
 	}
 }
+static unsigned int get_max_audio_sample_rate(struct audio_mode *modes)
+{
+	if (modes) {
+		if (modes->sample_rates.rate.RATE_192)
+			return 192000;
+		if (modes->sample_rates.rate.RATE_176_4)
+			return 176400;
+		if (modes->sample_rates.rate.RATE_96)
+			return 96000;
+		if (modes->sample_rates.rate.RATE_88_2)
+			return 88200;
+		if (modes->sample_rates.rate.RATE_48)
+			return 48000;
+		if (modes->sample_rates.rate.RATE_44_1)
+			return 44100;
+		if (modes->sample_rates.rate.RATE_32)
+			return 32000;
+	}
+	/*original logic when no audio info*/
+	return 441000;
+}
+
+void get_audio_check(struct audio_info *aud_modes,
+	struct audio_check *audio_chk)
+{
+	unsigned int i;
+	unsigned int max_sample_rate = 0;
+
+	if (aud_modes) {
+		audio_chk->audio_packet_type = 0x2;/*audio sample packet AP = .25 for layout0, 1 for layout1*/
+
+		audio_chk->max_audiosample_rate = 0;
+		for (i = 0; i < aud_modes->mode_count; i++) {
+			max_sample_rate = get_max_audio_sample_rate(&aud_modes->modes[i]);
+			if (audio_chk->max_audiosample_rate < max_sample_rate)
+				audio_chk->max_audiosample_rate = max_sample_rate;
+			/*dts takes the same as type 2: AP = 0.25*/
+		}
+		/*check which one take more bandwidth*/
+		if (audio_chk->max_audiosample_rate > 192000)
+			audio_chk->audio_packet_type = 0x9;/*AP =1*/
+		audio_chk->acat = 0;/*not support*/
+	}
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
index 5cbfdf1c4b11..a249a0e5edd0 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
@@ -33,7 +33,7 @@
  * Private functions
  ******************************************************************************/
 
-static void destruct(struct dc_sink *sink)
+static void dc_sink_destruct(struct dc_sink *sink)
 {
 	if (sink->dc_container_id) {
 		kfree(sink->dc_container_id);
@@ -41,7 +41,7 @@ static void destruct(struct dc_sink *sink)
 	}
 }
 
-static bool construct(struct dc_sink *sink, const struct dc_sink_init_data *init_params)
+static bool dc_sink_construct(struct dc_sink *sink, const struct dc_sink_init_data *init_params)
 {
 
 	struct dc_link *link = init_params->link;
@@ -75,7 +75,7 @@ void dc_sink_retain(struct dc_sink *sink)
 static void dc_sink_free(struct kref *kref)
 {
 	struct dc_sink *sink = container_of(kref, struct dc_sink, refcount);
-	destruct(sink);
+	dc_sink_destruct(sink);
 	kfree(sink);
 }
 
@@ -91,7 +91,7 @@ struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params)
 	if (NULL == sink)
 		goto alloc_fail;
 
-	if (false == construct(sink, init_params))
+	if (false == dc_sink_construct(sink, init_params))
 		goto construct_fail;
 
 	kref_init(&sink->refcount);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index bb09243758fe..6ddbb00ed37a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -27,14 +27,12 @@
 #include <linux/slab.h>
 
 #include "dm_services.h"
+#include "basics/dc_common.h"
 #include "dc.h"
 #include "core_types.h"
 #include "resource.h"
 #include "ipp.h"
 #include "timing_generator.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-#include "dcn10/dcn10_hw_sequencer.h"
-#endif
 
 #define DC_LOGGER dc->ctx->logger
 
@@ -58,7 +56,7 @@ void update_stream_signal(struct dc_stream_state *stream, struct dc_sink *sink)
 	}
 }
 
-static void construct(struct dc_stream_state *stream,
+static void dc_stream_construct(struct dc_stream_state *stream,
 	struct dc_sink *dc_sink_data)
 {
 	uint32_t i = 0;
@@ -108,7 +106,6 @@ static void construct(struct dc_stream_state *stream,
 	/* EDID CAP translation for HDMI 2.0 */
 	stream->timing.flags.LTE_340MCSC_SCRAMBLE = dc_sink_data->edid_caps.lte_340mcsc_scramble;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	memset(&stream->timing.dsc_cfg, 0, sizeof(stream->timing.dsc_cfg));
 	stream->timing.dsc_cfg.num_slices_h = 0;
 	stream->timing.dsc_cfg.num_slices_v = 0;
@@ -117,7 +114,6 @@ static void construct(struct dc_stream_state *stream,
 	stream->timing.dsc_cfg.linebuf_depth = 9;
 	stream->timing.dsc_cfg.version_minor = 2;
 	stream->timing.dsc_cfg.ycbcr422_simple = 0;
-#endif
 
 	update_stream_signal(stream, dc_sink_data);
 
@@ -129,7 +125,7 @@ static void construct(struct dc_stream_state *stream,
 	stream->ctx->dc_stream_id_count++;
 }
 
-static void destruct(struct dc_stream_state *stream)
+static void dc_stream_destruct(struct dc_stream_state *stream)
 {
 	dc_sink_release(stream->sink);
 	if (stream->out_transfer_func != NULL) {
@@ -147,7 +143,7 @@ static void dc_stream_free(struct kref *kref)
 {
 	struct dc_stream_state *stream = container_of(kref, struct dc_stream_state, refcount);
 
-	destruct(stream);
+	dc_stream_destruct(stream);
 	kfree(stream);
 }
 
@@ -170,7 +166,7 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (stream == NULL)
 		return NULL;
 
-	construct(stream, sink);
+	dc_stream_construct(stream, sink);
 
 	kref_init(&stream->refcount);
 
@@ -237,7 +233,7 @@ struct dc_stream_status *dc_stream_get_status(
 
 static void delay_cursor_until_vupdate(struct pipe_ctx *pipe_ctx, struct dc *dc)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	unsigned int vupdate_line;
 	unsigned int lines_to_vupdate, us_to_vupdate, vpos, nvpos;
 	struct dc_stream_state *stream = pipe_ctx->stream;
@@ -246,7 +242,7 @@ static void delay_cursor_until_vupdate(struct pipe_ctx *pipe_ctx, struct dc *dc)
 	if (stream->ctx->asic_id.chip_family == FAMILY_RV &&
 			ASICREV_IS_RAVEN(stream->ctx->asic_id.hw_internal_rev)) {
 
-		vupdate_line = get_vupdate_offset_from_vsync(pipe_ctx);
+		vupdate_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 		if (!dc_stream_get_crtc_position(dc, &stream, 1, &vpos, &nvpos))
 			return;
 
@@ -272,7 +268,7 @@ bool dc_stream_set_cursor_attributes(
 	const struct dc_cursor_attributes *attributes)
 {
 	int i;
-	struct dc  *core_dc;
+	struct dc  *dc;
 	struct resource_context *res_ctx;
 	struct pipe_ctx *pipe_to_program = NULL;
 
@@ -290,8 +286,8 @@ bool dc_stream_set_cursor_attributes(
 		return false;
 	}
 
-	core_dc = stream->ctx->dc;
-	res_ctx = &core_dc->current_state->res_ctx;
+	dc = stream->ctx->dc;
+	res_ctx = &dc->current_state->res_ctx;
 	stream->cursor_attributes = *attributes;
 
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -303,17 +299,17 @@ bool dc_stream_set_cursor_attributes(
 		if (!pipe_to_program) {
 			pipe_to_program = pipe_ctx;
 
-			delay_cursor_until_vupdate(pipe_ctx, core_dc);
-			core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, true);
+			delay_cursor_until_vupdate(pipe_ctx, dc);
+			dc->hwss.pipe_control_lock(dc, pipe_to_program, true);
 		}
 
-		core_dc->hwss.set_cursor_attribute(pipe_ctx);
-		if (core_dc->hwss.set_cursor_sdr_white_level)
-			core_dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+		dc->hwss.set_cursor_attribute(pipe_ctx);
+		if (dc->hwss.set_cursor_sdr_white_level)
+			dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
 	}
 
 	if (pipe_to_program)
-		core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, false);
+		dc->hwss.pipe_control_lock(dc, pipe_to_program, false);
 
 	return true;
 }
@@ -323,7 +319,7 @@ bool dc_stream_set_cursor_position(
 	const struct dc_cursor_position *position)
 {
 	int i;
-	struct dc  *core_dc;
+	struct dc  *dc;
 	struct resource_context *res_ctx;
 	struct pipe_ctx *pipe_to_program = NULL;
 
@@ -337,8 +333,8 @@ bool dc_stream_set_cursor_position(
 		return false;
 	}
 
-	core_dc = stream->ctx->dc;
-	res_ctx = &core_dc->current_state->res_ctx;
+	dc = stream->ctx->dc;
+	res_ctx = &dc->current_state->res_ctx;
 	stream->cursor_position = *position;
 
 	for (i = 0; i < MAX_PIPES; i++) {
@@ -354,20 +350,19 @@ bool dc_stream_set_cursor_position(
 		if (!pipe_to_program) {
 			pipe_to_program = pipe_ctx;
 
-			delay_cursor_until_vupdate(pipe_ctx, core_dc);
-			core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, true);
+			delay_cursor_until_vupdate(pipe_ctx, dc);
+			dc->hwss.pipe_control_lock(dc, pipe_to_program, true);
 		}
 
-		core_dc->hwss.set_cursor_position(pipe_ctx);
+		dc->hwss.set_cursor_position(pipe_ctx);
 	}
 
 	if (pipe_to_program)
-		core_dc->hwss.pipe_control_lock(core_dc, pipe_to_program, false);
+		dc->hwss.pipe_control_lock(dc, pipe_to_program, false);
 
 	return true;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dc_stream_add_writeback(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_writeback_info *wb_info)
@@ -411,25 +406,30 @@ bool dc_stream_add_writeback(struct dc *dc,
 		stream->writeback_info[stream->num_wb_info++] = *wb_info;
 	}
 
-	if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
-		dm_error("DC: update_bandwidth failed!\n");
-		return false;
-	}
-
-	/* enable writeback */
 	if (dc->hwss.enable_writeback) {
 		struct dc_stream_status *stream_status = dc_stream_get_status(stream);
 		struct dwbc *dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst];
+		dwb->otg_inst = stream_status->primary_otg_inst;
+	}
+	if (IS_DIAG_DC(dc->ctx->dce_environment)) {
+		if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
+			dm_error("DC: update_bandwidth failed!\n");
+			return false;
+		}
 
-		if (dwb->funcs->is_enabled(dwb)) {
-			/* writeback pipe already enabled, only need to update */
-			dc->hwss.update_writeback(dc, stream_status, wb_info, dc->current_state);
-		} else {
-			/* Enable writeback pipe from scratch*/
-			dc->hwss.enable_writeback(dc, stream_status, wb_info, dc->current_state);
+		/* enable writeback */
+		if (dc->hwss.enable_writeback) {
+			struct dwbc *dwb = dc->res_pool->dwbc[wb_info->dwb_pipe_inst];
+
+			if (dwb->funcs->is_enabled(dwb)) {
+				/* writeback pipe already enabled, only need to update */
+				dc->hwss.update_writeback(dc, wb_info, dc->current_state);
+			} else {
+				/* Enable writeback pipe from scratch*/
+				dc->hwss.enable_writeback(dc, wb_info, dc->current_state);
+			}
 		}
 	}
-
 	return true;
 }
 
@@ -468,26 +468,35 @@ bool dc_stream_remove_writeback(struct dc *dc,
 	}
 	stream->num_wb_info = j;
 
-	/* recalculate and apply DML parameters */
-	if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
-		dm_error("DC: update_bandwidth failed!\n");
-		return false;
-	}
-
-	/* disable writeback */
-	if (dc->hwss.disable_writeback)
-		dc->hwss.disable_writeback(dc, dwb_pipe_inst);
+	if (IS_DIAG_DC(dc->ctx->dce_environment)) {
+		/* recalculate and apply DML parameters */
+		if (!dc->hwss.update_bandwidth(dc, dc->current_state)) {
+			dm_error("DC: update_bandwidth failed!\n");
+			return false;
+		}
 
+		/* disable writeback */
+		if (dc->hwss.disable_writeback)
+			dc->hwss.disable_writeback(dc, dwb_pipe_inst);
+	}
 	return true;
 }
-#endif
 
+bool dc_stream_warmup_writeback(struct dc *dc,
+		int num_dwb,
+		struct dc_writeback_info *wb_info)
+{
+	if (dc->hwss.mmhubbub_warmup)
+		return dc->hwss.mmhubbub_warmup(dc, num_dwb, wb_info);
+	else
+		return false;
+}
 uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream)
 {
 	uint8_t i;
-	struct dc  *core_dc = stream->ctx->dc;
+	struct dc  *dc = stream->ctx->dc;
 	struct resource_context *res_ctx =
-		&core_dc->current_state->res_ctx;
+		&dc->current_state->res_ctx;
 
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg;
@@ -544,9 +553,9 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 {
 	uint8_t i;
 	bool ret = false;
-	struct dc  *core_dc = stream->ctx->dc;
+	struct dc  *dc = stream->ctx->dc;
 	struct resource_context *res_ctx =
-		&core_dc->current_state->res_ctx;
+		&dc->current_state->res_ctx;
 
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg;
@@ -567,10 +576,8 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 	return ret;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream)
 {
-	bool status = true;
 	struct pipe_ctx *pipe = NULL;
 	int i;
 
@@ -586,8 +593,7 @@ bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream)
 	if (i == MAX_PIPES)
 		return true;
 
-	status = dc->hwss.dmdata_status_done(pipe);
-	return status;
+	return dc->hwss.dmdata_status_done(pipe);
 }
 
 bool dc_stream_set_dynamic_metadata(struct dc *dc,
@@ -630,7 +636,6 @@ bool dc_stream_set_dynamic_metadata(struct dc *dc,
 
 	return true;
 }
-#endif
 
 void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index b9d6a5bd8522..ea1229a3e2b2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -37,7 +37,7 @@
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
-static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state)
+static void dc_plane_construct(struct dc_context *ctx, struct dc_plane_state *plane_state)
 {
 	plane_state->ctx = ctx;
 
@@ -50,7 +50,6 @@ static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state
 		plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
 		plane_state->in_transfer_func->ctx = ctx;
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	plane_state->in_shaper_func = dc_create_transfer_func();
 	if (plane_state->in_shaper_func != NULL) {
 		plane_state->in_shaper_func->type = TF_TYPE_BYPASS;
@@ -67,10 +66,9 @@ static void construct(struct dc_context *ctx, struct dc_plane_state *plane_state
 		plane_state->blend_tf->ctx = ctx;
 	}
 
-#endif
 }
 
-static void destruct(struct dc_plane_state *plane_state)
+static void dc_plane_destruct(struct dc_plane_state *plane_state)
 {
 	if (plane_state->gamma_correction != NULL) {
 		dc_gamma_release(&plane_state->gamma_correction);
@@ -80,7 +78,6 @@ static void destruct(struct dc_plane_state *plane_state)
 				plane_state->in_transfer_func);
 		plane_state->in_transfer_func = NULL;
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	if (plane_state->in_shaper_func != NULL) {
 		dc_transfer_func_release(
 				plane_state->in_shaper_func);
@@ -97,7 +94,6 @@ static void destruct(struct dc_plane_state *plane_state)
 		plane_state->blend_tf = NULL;
 	}
 
-#endif
 }
 
 /*******************************************************************************
@@ -112,16 +108,14 @@ void enable_surface_flip_reporting(struct dc_plane_state *plane_state,
 
 struct dc_plane_state *dc_create_plane_state(struct dc *dc)
 {
-	struct dc *core_dc = dc;
-
 	struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state),
-						      GFP_KERNEL);
+							GFP_KERNEL);
 
 	if (NULL == plane_state)
 		return NULL;
 
 	kref_init(&plane_state->refcount);
-	construct(core_dc->ctx, plane_state);
+	dc_plane_construct(dc->ctx, plane_state);
 
 	return plane_state;
 }
@@ -141,7 +135,7 @@ const struct dc_plane_status *dc_plane_get_status(
 		const struct dc_plane_state *plane_state)
 {
 	const struct dc_plane_status *plane_status;
-	struct dc  *core_dc;
+	struct dc  *dc;
 	int i;
 
 	if (!plane_state ||
@@ -152,15 +146,15 @@ const struct dc_plane_status *dc_plane_get_status(
 	}
 
 	plane_status = &plane_state->status;
-	core_dc = plane_state->ctx->dc;
+	dc = plane_state->ctx->dc;
 
-	if (core_dc->current_state == NULL)
+	if (dc->current_state == NULL)
 		return NULL;
 
 	/* Find the current plane state and set its pending bit to false */
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx =
-				&core_dc->current_state->res_ctx.pipe_ctx[i];
+				&dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe_ctx->plane_state != plane_state)
 			continue;
@@ -170,14 +164,14 @@ const struct dc_plane_status *dc_plane_get_status(
 		break;
 	}
 
-	for (i = 0; i < core_dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx =
-				&core_dc->current_state->res_ctx.pipe_ctx[i];
+				&dc->current_state->res_ctx.pipe_ctx[i];
 
 		if (pipe_ctx->plane_state != plane_state)
 			continue;
 
-		core_dc->hwss.update_pending_status(pipe_ctx);
+		dc->hwss.update_pending_status(pipe_ctx);
 	}
 
 	return plane_status;
@@ -191,7 +185,7 @@ void dc_plane_state_retain(struct dc_plane_state *plane_state)
 static void dc_plane_state_free(struct kref *kref)
 {
 	struct dc_plane_state *plane_state = container_of(kref, struct dc_plane_state, refcount);
-	destruct(plane_state);
+	dc_plane_destruct(plane_state);
 	kvfree(plane_state);
 }
 
@@ -262,7 +256,6 @@ alloc_fail:
 	return NULL;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static void dc_3dlut_func_free(struct kref *kref)
 {
 	struct dc_3dlut *lut = container_of(kref, struct dc_3dlut, refcount);
@@ -296,6 +289,5 @@ void dc_3dlut_func_retain(struct dc_3dlut *lut)
 {
 	kref_get(&lut->refcount);
 }
-#endif
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 0416a17b0897..3fa85a54360f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -39,7 +39,7 @@
 #include "inc/hw/dmcu.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.2.56"
+#define DC_VER "3.2.68"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -54,6 +54,10 @@ struct dc_versions {
 	struct dmcu_version dmcu_version;
 };
 
+enum dp_protocol_version {
+	DP_VERSION_1_4,
+};
+
 enum dc_plane_type {
 	DC_PLANE_TYPE_INVALID,
 	DC_PLANE_TYPE_DCE_RGB,
@@ -112,17 +116,15 @@ struct dc_caps {
 	bool disable_dp_clk_share;
 	bool psp_setup_panel_mode;
 	bool extended_aux_timeout_support;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
+	bool dmcub_support;
 	bool hw_3d_lut;
-#endif
+	enum dp_protocol_version max_dp_protocol_version;
 	struct dc_plane_cap planes[MAX_PLANES];
 };
 
 struct dc_bug_wa {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool no_connect_phy_config;
 	bool dedcn20_305_wa;
-#endif
 	bool skip_clock_update;
 };
 
@@ -155,11 +157,14 @@ struct dc_surface_dcc_cap {
 	bool const_color_support;
 };
 
-struct dc_static_screen_events {
-	bool force_trigger;
-	bool cursor_update;
-	bool surface_update;
-	bool overlay_update;
+struct dc_static_screen_params {
+	struct {
+		bool force_trigger;
+		bool cursor_update;
+		bool surface_update;
+		bool overlay_update;
+	} triggers;
+	unsigned int num_frames;
 };
 
 
@@ -363,10 +368,10 @@ struct dc_debug_options {
 	bool disable_dfs_bypass;
 	bool disable_dpp_power_gate;
 	bool disable_hubp_power_gate;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool disable_dsc_power_gate;
 	int dsc_min_slice_height_override;
-#endif
+	int dsc_bpp_increment_div;
+	bool native422_support;
 	bool disable_pplib_wm_range;
 	enum wm_report_mode pplib_wm_report_mode;
 	unsigned int min_disp_clk_khz;
@@ -401,22 +406,25 @@ struct dc_debug_options {
 	unsigned int force_odm_combine; //bit vector based on otg inst
 	unsigned int force_fclk_khz;
 	bool disable_tri_buf;
+	bool dmub_offload_enabled;
+	bool dmcub_emulation;
+	bool dmub_command_table; /* for testing only */
 	struct dc_bw_validation_profile bw_val_profile;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool disable_fec;
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	bool disable_48mhz_pwrdwn;
-#endif
 	/* This forces a hard min on the DCFCLK requested to SMU/PP
 	 * watermarks are not affected.
 	 */
 	unsigned int force_min_dcfclk_mhz;
 	bool disable_timing_sync;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool cm_in_bypass;
-#endif
 	int force_clock_mode;/*every mode change.*/
+
+	bool nv12_iflip_vm_wa;
+	bool disable_dram_clock_change_vactive_support;
+	bool validate_dml_output;
+	bool enable_dmcub_surface_flip;
+	bool usbc_combo_phy_reset_wa;
 };
 
 struct dc_debug_data {
@@ -425,7 +433,6 @@ struct dc_debug_data {
 	uint32_t auxErrorCount;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct dc_phy_addr_space_config {
 	struct {
 		uint64_t start_addr;
@@ -455,7 +462,6 @@ struct dc_virtual_addr_space_config {
 	uint32_t	page_table_block_size_in_bytes;
 	uint8_t		page_table_depth; // 1 = 1 level, 2 = 2 level, etc.  0 = invalid
 };
-#endif
 
 struct dc_bounding_box_overrides {
 	int sr_exit_time_ns;
@@ -483,9 +489,7 @@ struct dc {
 	struct dc_bounding_box_overrides bb_overrides;
 	struct dc_bug_wa work_arounds;
 	struct dc_context *ctx;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct dc_phy_addr_space_config vm_pa_config;
-#endif
 
 	uint8_t link_count;
 	struct dc_link *links[MAX_PIPES * 2];
@@ -501,7 +505,7 @@ struct dc {
 	/* Inputs into BW and WM calculations. */
 	struct bw_calcs_dceip *bw_dceip;
 	struct bw_calcs_vbios *bw_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 	struct display_mode_lib dml;
@@ -515,7 +519,7 @@ struct dc {
 	bool optimized_required;
 
 	/* Require to maintain clocks and bandwidth for UEFI enabled HW */
-	bool optimize_seamless_boot;
+	int optimize_seamless_boot_streams;
 
 	/* FBC compressor */
 	struct compressor *fbc_compressor;
@@ -523,10 +527,8 @@ struct dc {
 	struct dc_debug_data debug_data;
 
 	const char *build_id;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct vm_helper *vm_helper;
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#endif
 };
 
 enum frame_buffer_mode {
@@ -558,15 +560,16 @@ struct dc_init_data {
 	struct dc_bios *vbios_override;
 	enum dce_environment dce_environment;
 
+	struct dmub_offload_funcs *dmub_if;
+	struct dc_reg_helper_state *dmub_offload;
+
 	struct dc_config flags;
 	uint32_t log_mask;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	/**
 	 * gpu_info FW provided soc bounding box struct or 0 if not
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#endif
 };
 
 struct dc_callback_init {
@@ -581,11 +584,9 @@ struct dc *dc_create(const struct dc_init_data *init_params);
 void dc_hardware_init(struct dc *dc);
 
 int dc_get_vmid_use_vector(struct dc *dc);
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 void dc_setup_vm_context(struct dc *dc, struct dc_virtual_addr_space_config *va_config, int vmid);
 /* Returns the number of vmids supported */
 int dc_setup_system_context(struct dc *dc, struct dc_phy_addr_space_config *pa_config);
-#endif
 void dc_init_callbacks(struct dc *dc,
 		const struct dc_callback_init *init_params);
 void dc_deinit_callbacks(struct dc *dc);
@@ -661,7 +662,6 @@ struct dc_transfer_func {
 	};
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 union dc_3dlut_state {
 	struct {
@@ -680,12 +680,11 @@ union dc_3dlut_state {
 struct dc_3dlut {
 	struct kref refcount;
 	struct tetrahedral_params lut_3d;
-	uint32_t hdr_multiplier;
+	struct fixed31_32 hdr_multiplier;
 	bool initialized; /*remove after diag fix*/
 	union dc_3dlut_state state;
 	struct dc_context *ctx;
 };
-#endif
 /*
  * This structure is filled in by dc_surface_get_status and contains
  * the last requested address and the currently active address so the called
@@ -708,7 +707,7 @@ union surface_update_flags {
 		uint32_t horizontal_mirror_change:1;
 		uint32_t per_pixel_alpha_change:1;
 		uint32_t global_alpha_change:1;
-		uint32_t sdr_white_level:1;
+		uint32_t hdr_mult:1;
 		uint32_t rotation_change:1;
 		uint32_t swizzle_change:1;
 		uint32_t scaling_change:1;
@@ -736,9 +735,7 @@ union surface_update_flags {
 struct dc_plane_state {
 	struct dc_plane_address address;
 	struct dc_plane_flip_time time;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool triplebuffer_flips;
-#endif
 	struct scaling_taps scaling_quality;
 	struct rect src_rect;
 	struct rect dst_rect;
@@ -754,18 +751,16 @@ struct dc_plane_state {
 	struct dc_bias_and_scale *bias_and_scale;
 	struct dc_csc_transform input_csc_color_matrix;
 	struct fixed31_32 coeff_reduction_factor;
-	uint32_t sdr_white_level;
+	struct fixed31_32 hdr_mult;
 
 	// TODO: No longer used, remove
 	struct dc_hdr_static_metadata hdr_static_ctx;
 
 	enum dc_color_space color_space;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dc_3dlut *lut3d_func;
 	struct dc_transfer_func *in_shaper_func;
 	struct dc_transfer_func *blend_tf;
-#endif
 
 	enum surface_pixel_format format;
 	enum dc_rotation_angle rotation;
@@ -801,7 +796,6 @@ struct dc_plane_info {
 	enum dc_rotation_angle rotation;
 	enum plane_stereo_format stereo_format;
 	enum dc_color_space color_space;
-	unsigned int sdr_white_level;
 	bool horizontal_mirror;
 	bool visible;
 	bool per_pixel_alpha;
@@ -825,7 +819,7 @@ struct dc_surface_update {
 	const struct dc_flip_addrs *flip_addr;
 	const struct dc_plane_info *plane_info;
 	const struct dc_scaling_info *scaling_info;
-
+	struct fixed31_32 hdr_mult;
 	/* following updates require alloc/sleep/spin that is not isr safe,
 	 * null means no updates
 	 */
@@ -834,11 +828,9 @@ struct dc_surface_update {
 
 	const struct dc_csc_transform *input_csc_color_matrix;
 	const struct fixed31_32 *coeff_reduction_factor;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	const struct dc_transfer_func *func_shaper;
 	const struct dc_3dlut *lut3d_func;
 	const struct dc_transfer_func *blend_tf;
-#endif
 };
 
 /*
@@ -859,11 +851,9 @@ void dc_transfer_func_retain(struct dc_transfer_func *dc_tf);
 void dc_transfer_func_release(struct dc_transfer_func *dc_tf);
 struct dc_transfer_func *dc_create_transfer_func(void);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_3dlut *dc_create_3dlut_func(void);
 void dc_3dlut_func_release(struct dc_3dlut *lut);
 void dc_3dlut_func_retain(struct dc_3dlut *lut);
-#endif
 /*
  * This structure holds a surface address.  There could be multiple addresses
  * in cases such as Stereo 3D, Planar YUV, etc.  Other per-flip attributes such
@@ -925,6 +915,8 @@ void dc_resource_state_copy_construct_current(
 
 void dc_resource_state_destruct(struct dc_state *context);
 
+bool dc_resource_is_dsc_encoding_supported(const struct dc *dc);
+
 /*
  * TODO update to make it about validation sets
  * Set up streams and links associated to drive sinks
@@ -980,10 +972,10 @@ struct dpcd_caps {
 	bool panel_mode_edp;
 	bool dpcd_display_control_capable;
 	bool ext_receiver_cap_field_present;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	union dpcd_fec_capability fec_cap;
 	struct dpcd_dsc_capabilities dsc_caps;
-#endif
+	struct dc_lttpr_caps lttpr_caps;
+
 };
 
 #include "dc_link.h"
@@ -1004,14 +996,12 @@ struct dc_container_id {
 };
 
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct dc_sink_dsc_caps {
 	// 'true' if these are virtual DPCD's DSC caps (immediately upstream of sink in MST topology),
 	// 'false' if they are sink's DSC caps
 	bool is_virtual_dpcd_dsc;
 	struct dsc_dec_dpcd_caps dsc_dec_caps;
 };
-#endif
 
 /*
  * The sink structure contains EDID and other display device properties
@@ -1026,9 +1016,7 @@ struct dc_sink {
 	struct stereo_3d_features features_3d[TIMING_3D_FORMAT_MAX];
 	bool converter_disable_audio;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dc_sink_dsc_caps sink_dsc_caps;
-#endif
 
 	/* private to DC core */
 	struct dc_link *link;
@@ -1086,13 +1074,12 @@ unsigned int dc_get_current_backlight_pwm(struct dc *dc);
 unsigned int dc_get_target_backlight_pwm(struct dc *dc);
 
 bool dc_is_dmcu_initialized(struct dc *dc);
+bool dc_is_hw_initialized(struct dc *dc);
 
 enum dc_status dc_set_clock(struct dc *dc, enum dc_clock_type clock_type, uint32_t clk_khz, uint32_t stepping);
 void dc_get_clock(struct dc *dc, enum dc_clock_type clock_type, struct dc_clock_config *clock_cfg);
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 /*******************************************************************************
  * DSC Interfaces
  ******************************************************************************/
 #include "dc_dsc.h"
-#endif
 #endif /* DC_INTERFACE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
new file mode 100644
index 000000000000..59c298a6484f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -0,0 +1,134 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dc.h"
+#include "dc_dmub_srv.h"
+#include "../dmub/inc/dmub_srv.h"
+
+static void dc_dmub_srv_construct(struct dc_dmub_srv *dc_srv, struct dc *dc,
+				  struct dmub_srv *dmub)
+{
+	dc_srv->dmub = dmub;
+	dc_srv->ctx = dc->ctx;
+}
+
+struct dc_dmub_srv *dc_dmub_srv_create(struct dc *dc, struct dmub_srv *dmub)
+{
+	struct dc_dmub_srv *dc_srv =
+		kzalloc(sizeof(struct dc_dmub_srv), GFP_KERNEL);
+
+	if (dc_srv == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dc_dmub_srv_construct(dc_srv, dc, dmub);
+
+	return dc_srv;
+}
+
+void dc_dmub_srv_destroy(struct dc_dmub_srv **dmub_srv)
+{
+	if (*dmub_srv) {
+		kfree(*dmub_srv);
+		*dmub_srv = NULL;
+	}
+}
+
+void dc_dmub_srv_cmd_queue(struct dc_dmub_srv *dc_dmub_srv,
+			   struct dmub_cmd_header *cmd)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_cmd_queue(dmub, cmd);
+	if (status == DMUB_STATUS_OK)
+		return;
+
+	if (status != DMUB_STATUS_QUEUE_FULL)
+		goto error;
+
+	/* Execute and wait for queue to become empty again. */
+	dc_dmub_srv_cmd_execute(dc_dmub_srv);
+	dc_dmub_srv_wait_idle(dc_dmub_srv);
+
+	/* Requeue the command. */
+	status = dmub_srv_cmd_queue(dmub, cmd);
+	if (status == DMUB_STATUS_OK)
+		return;
+
+error:
+	DC_ERROR("Error queuing DMUB command: status=%d\n", status);
+}
+
+void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_cmd_execute(dmub);
+	if (status != DMUB_STATUS_OK)
+		DC_ERROR("Error starting DMUB execution: status=%d\n", status);
+}
+
+void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	status = dmub_srv_wait_for_idle(dmub, 100000);
+	if (status != DMUB_STATUS_OK)
+		DC_ERROR("Error waiting for DMUB idle: status=%d\n", status);
+}
+
+void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv)
+{
+	struct dmub_srv *dmub = dc_dmub_srv->dmub;
+	struct dc_context *dc_ctx = dc_dmub_srv->ctx;
+	enum dmub_status status;
+
+	for (;;) {
+		/* Wait up to a second for PHY init. */
+		status = dmub_srv_wait_for_phy_init(dmub, 1000000);
+		if (status == DMUB_STATUS_OK)
+			/* Initialization OK */
+			break;
+
+		DC_ERROR("DMCUB PHY init failed: status=%d\n", status);
+		ASSERT(0);
+
+		if (status != DMUB_STATUS_TIMEOUT)
+			/*
+			 * Server likely initialized or we don't have
+			 * DMCUB HW support - this won't end.
+			 */
+			break;
+
+		/* Continue spinning so we don't hang the ASIC. */
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
new file mode 100644
index 000000000000..754b6077539c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_DC_SRV_H_
+#define _DMUB_DC_SRV_H_
+
+#include "os_types.h"
+#include "../dmub/inc/dmub_cmd.h"
+
+struct dmub_srv;
+struct dmub_cmd_header;
+
+struct dc_reg_helper_state {
+	bool gather_in_progress;
+	uint32_t same_addr_count;
+	bool should_burst_write;
+	union dmub_rb_cmd cmd_data;
+	unsigned int reg_seq_count;
+};
+
+struct dc_dmub_srv {
+	struct dmub_srv *dmub;
+	struct dc_reg_helper_state reg_helper_offload;
+
+	struct dc_context *ctx;
+	void *dm;
+};
+
+void dc_dmub_srv_cmd_queue(struct dc_dmub_srv *dc_dmub_srv,
+			   struct dmub_cmd_header *cmd);
+
+void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv);
+
+void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv);
+
+void dc_dmub_srv_wait_phy_init(struct dc_dmub_srv *dc_dmub_srv);
+
+#endif /* _DMUB_DC_SRV_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index ef79a686e4c2..dfe4472c9e40 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -129,9 +129,7 @@ struct dc_link_training_overrides {
 	bool *alternate_scrambler_reset;
 	bool *enhanced_framing;
 	bool *mst_enable;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool *fec_enable;
-#endif
 };
 
 union dpcd_rev {
@@ -471,13 +469,13 @@ union training_aux_rd_interval {
 /* Automated test structures */
 union test_request {
 	struct {
-	uint8_t LINK_TRAINING         :1;
-	uint8_t LINK_TEST_PATTRN      :1;
-	uint8_t EDID_READ             :1;
-	uint8_t PHY_TEST_PATTERN      :1;
-	uint8_t AUDIO_TEST_PATTERN    :1;
-	uint8_t RESERVED              :1;
-	uint8_t TEST_STEREO_3D        :1;
+	uint8_t LINK_TRAINING                :1;
+	uint8_t LINK_TEST_PATTRN             :1;
+	uint8_t EDID_READ                    :1;
+	uint8_t PHY_TEST_PATTERN             :1;
+	uint8_t RESERVED                     :1;
+	uint8_t AUDIO_TEST_PATTERN           :1;
+	uint8_t TEST_AUDIO_DISABLED_VIDEO    :1;
 	} bits;
 	uint8_t raw;
 };
@@ -524,19 +522,52 @@ union link_test_pattern {
 
 union test_misc {
 	struct dpcd_test_misc_bits {
-		unsigned char SYNC_CLOCK :1;
+		unsigned char SYNC_CLOCK  :1;
 		/* dpcd_test_color_format */
-		unsigned char CLR_FORMAT :2;
+		unsigned char CLR_FORMAT  :2;
 		/* dpcd_test_dyn_range */
-		unsigned char DYN_RANGE  :1;
-		unsigned char YCBCR      :1;
+		unsigned char DYN_RANGE   :1;
+		unsigned char YCBCR_COEFS :1;
 		/* dpcd_test_bit_depth */
-		unsigned char BPC        :3;
+		unsigned char BPC         :3;
 	} bits;
 	unsigned char raw;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+union audio_test_mode {
+	struct {
+		unsigned char sampling_rate   :4;
+		unsigned char channel_count   :4;
+	} bits;
+	unsigned char raw;
+};
+
+union audio_test_pattern_period {
+	struct {
+		unsigned char pattern_period   :4;
+		unsigned char reserved         :4;
+	} bits;
+	unsigned char raw;
+};
+
+struct audio_test_pattern_type {
+	unsigned char value;
+};
+
+struct dp_audio_test_data_flags {
+	uint8_t test_requested  :1;
+	uint8_t disable_video   :1;
+};
+
+struct dp_audio_test_data {
+
+	struct dp_audio_test_data_flags flags;
+	uint8_t sampling_rate;
+	uint8_t channel_count;
+	uint8_t pattern_type;
+	uint8_t pattern_period[8];
+};
+
 /* FEC capability DPCD register field bits-*/
 union dpcd_fec_capability {
 	struct {
@@ -661,6 +692,5 @@ struct dpcd_dsc_capabilities {
 	union dpcd_dsc_ext_capabilities dsc_ext_caps;
 };
 
-#endif /* CONFIG_DRM_AMD_DC_DSC_SUPPORT */
 
 #endif /* DC_DP_TYPES_H */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
index 0ed2962add5a..3800340a5b4f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
@@ -1,4 +1,3 @@
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #ifndef DC_DSC_H_
 #define DC_DSC_H_
 /*
@@ -42,21 +41,28 @@ struct dc_dsc_bw_range {
 
 struct display_stream_compressor {
 	const struct dsc_funcs *funcs;
-#ifndef AMD_EDID_UTILITY
 	struct dc_context *ctx;
 	int inst;
-#endif
 };
 
-bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data,
+struct dc_dsc_policy {
+	bool use_min_slices_h;
+	int max_slices_h; // Maximum available if 0
+	int min_slice_height; // Must not be less than 8
+	uint32_t max_target_bpp;
+	uint32_t min_target_bpp;
+};
+
+bool dc_dsc_parse_dsc_dpcd(const struct dc *dc,
+		const uint8_t *dpcd_dsc_basic_data,
 		const uint8_t *dpcd_dsc_ext_data,
 		struct dsc_dec_dpcd_caps *dsc_sink_caps);
 
 bool dc_dsc_compute_bandwidth_range(
 		const struct display_stream_compressor *dsc,
 		const uint32_t dsc_min_slice_height_override,
-		const uint32_t min_kbps,
-		const uint32_t max_kbps,
+		const uint32_t min_bpp,
+		const uint32_t max_bpp,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
 		const struct dc_crtc_timing *timing,
 		struct dc_dsc_bw_range *range);
@@ -68,5 +74,10 @@ bool dc_dsc_compute_config(
 		uint32_t target_bandwidth_kbps,
 		const struct dc_crtc_timing *timing,
 		struct dc_dsc_config *dsc_cfg);
-#endif
+
+void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing,
+		struct dc_dsc_policy *policy);
+
+void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index 30b2f9edd42f..737048d8a96c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -32,6 +32,74 @@
 #include "dm_services.h"
 #include <stdarg.h>
 
+#include "dc.h"
+#include "dc_dmub_srv.h"
+
+static inline void submit_dmub_read_modify_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	bool gather = false;
+
+	offload->should_burst_write =
+			(offload->same_addr_count == (DMUB_READ_MODIFY_WRITE_SEQ__MAX - 1));
+	cmd_buf->header.payload_bytes =
+			sizeof(struct dmub_cmd_read_modify_write_sequence) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+	offload->same_addr_count = 0;
+}
+
+static inline void submit_dmub_burst_write(
+	struct dc_reg_helper_state *offload,
+	const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+	bool gather = false;
+
+	cmd_buf->header.payload_bytes =
+			sizeof(uint32_t) * offload->reg_seq_count;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+
+	offload->reg_seq_count = 0;
+}
+
+static inline void submit_dmub_reg_wait(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+	bool gather = false;
+
+	gather = ctx->dmub_srv->reg_helper_offload.gather_in_progress;
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = false;
+
+	dc_dmub_srv_cmd_queue(ctx->dmub_srv, &cmd_buf->header);
+
+	memset(cmd_buf, 0, sizeof(*cmd_buf));
+	offload->reg_seq_count = 0;
+
+	ctx->dmub_srv->reg_helper_offload.gather_in_progress = gather;
+}
+
 struct dc_reg_value_masks {
 	uint32_t value;
 	uint32_t mask;
@@ -77,6 +145,100 @@ static void set_reg_field_values(struct dc_reg_value_masks *field_value_mask,
 	}
 }
 
+static void dmub_flush_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_read_modify_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static void dmub_flush_burst_write_buffer_execute(
+		struct dc_reg_helper_state *offload,
+		const struct dc_context *ctx)
+{
+	submit_dmub_burst_write(offload, ctx);
+	dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+}
+
+static bool dmub_reg_value_burst_set_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t reg_val)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_burst_write *cmd_buf = &offload->cmd_data.burst_write;
+
+	/* flush command if buffer is full */
+	if (offload->reg_seq_count == DMUB_BURST_WRITE_VALUES__MAX)
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+
+	if (offload->cmd_data.cmd_common.header.type == DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			addr != cmd_buf->addr) {
+		dmub_flush_burst_write_buffer_execute(offload, ctx);
+		return false;
+	}
+
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_BURST_WRITE;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->addr = addr;
+	cmd_buf->write_values[offload->reg_seq_count] = reg_val;
+	offload->reg_seq_count++;
+
+	return true;
+}
+
+static uint32_t dmub_reg_value_pack(const struct dc_context *ctx, uint32_t addr,
+		struct dc_reg_value_masks *field_value_mask)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_read_modify_write *cmd_buf = &offload->cmd_data.read_modify_write;
+	struct dmub_cmd_read_modify_write_sequence *seq;
+
+	/* flush command if buffer is full */
+	if (offload->cmd_data.cmd_common.header.type != DMUB_CMD__REG_SEQ_BURST_WRITE &&
+			offload->reg_seq_count == DMUB_READ_MODIFY_WRITE_SEQ__MAX)
+		dmub_flush_buffer_execute(offload, ctx);
+
+	if (offload->should_burst_write) {
+		if (dmub_reg_value_burst_set_pack(ctx, addr, field_value_mask->value))
+			return field_value_mask->value;
+		else
+			offload->should_burst_write = false;
+	}
+
+	/* pack commands */
+	cmd_buf->header.type = DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE;
+	cmd_buf->header.sub_type = 0;
+	seq = &cmd_buf->seq[offload->reg_seq_count];
+
+	if (offload->reg_seq_count) {
+		if (cmd_buf->seq[offload->reg_seq_count - 1].addr == addr)
+			offload->same_addr_count++;
+		else
+			offload->same_addr_count = 0;
+	}
+
+	seq->addr = addr;
+	seq->modify_mask = field_value_mask->mask;
+	seq->modify_value = field_value_mask->value;
+	offload->reg_seq_count++;
+
+	return field_value_mask->value;
+}
+
+static void dmub_reg_wait_done_pack(const struct dc_context *ctx, uint32_t addr,
+		uint32_t mask, uint32_t shift, uint32_t condition_value, uint32_t time_out_us)
+{
+	struct dc_reg_helper_state *offload = &ctx->dmub_srv->reg_helper_offload;
+	struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait;
+
+	cmd_buf->header.type = DMUB_CMD__REG_REG_WAIT;
+	cmd_buf->header.sub_type = 0;
+	cmd_buf->reg_wait.addr = addr;
+	cmd_buf->reg_wait.condition_field_value = mask & (condition_value << shift);
+	cmd_buf->reg_wait.mask = mask;
+	cmd_buf->reg_wait.time_out_us = time_out_us;
+}
+
 uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
@@ -93,6 +255,11 @@ uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 
 	va_end(ap);
 
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress)
+		return dmub_reg_value_pack(ctx, addr, &field_value_mask);
+		/* todo: return void so we can decouple code running in driver from register states */
+
 	/* mmio write directly */
 	reg_val = dm_read_reg(ctx, addr);
 	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
@@ -118,6 +285,13 @@ uint32_t generic_reg_set_ex(const struct dc_context *ctx,
 
 	/* mmio write directly */
 	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		return dmub_reg_value_burst_set_pack(ctx, addr, reg_val);
+		/* todo: return void so we can decouple code running in driver from register states */
+	}
+
 	dm_write_reg(ctx, addr, reg_val);
 	return reg_val;
 }
@@ -134,6 +308,14 @@ uint32_t dm_read_reg_func(
 		return 0;
 	}
 #endif
+
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress &&
+	    !ctx->dmub_srv->reg_helper_offload.should_burst_write) {
+		ASSERT(false);
+		return 0;
+	}
+
 	value = cgs_read_register(ctx->cgs_device, address);
 	trace_amdgpu_dc_rreg(&ctx->perf_trace->read_count, address, value);
 
@@ -299,7 +481,19 @@ void generic_reg_wait(const struct dc_context *ctx,
 	uint32_t reg_val;
 	int i;
 
-	/* something is terribly wrong if time out is > 200ms. (5Hz) */
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		dmub_reg_wait_done_pack(ctx, addr, mask, shift, condition_value,
+				delay_between_poll_us * time_out_num_tries);
+		return;
+	}
+
+	/*
+	 * Something is terribly wrong if time out is > 3000ms.
+	 * 3000ms is the maximum time needed for SMU to pass values back.
+	 * This value comes from experiments.
+	 *
+	 */
 	ASSERT(delay_between_poll_us * time_out_num_tries <= 3000000);
 
 	for (i = 0; i <= time_out_num_tries; i++) {
@@ -346,12 +540,48 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
 {
 	uint32_t value = 0;
 
+	// when reg read, there should not be any offload.
+	if (ctx->dmub_srv &&
+	    ctx->dmub_srv->reg_helper_offload.gather_in_progress) {
+		ASSERT(false);
+	}
+
 	dm_write_reg(ctx, addr_index, index);
 	value = dm_read_reg(ctx, addr_data);
 
 	return value;
 }
 
+uint32_t generic_indirect_reg_get(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...)
+{
+	uint32_t shift, mask, *field_value;
+	uint32_t value = 0;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	value = generic_read_indirect_reg(ctx, addr_index, addr_data, index);
+	*field_value1 = get_reg_field_value_ex(value, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t *);
+
+		*field_value = get_reg_field_value_ex(value, mask, shift);
+		i++;
+	}
+
+	va_end(ap);
+
+	return value;
+}
 
 uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
@@ -382,3 +612,68 @@ uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 
 	return reg_val;
 }
+
+void reg_sequence_start_gather(const struct dc_context *ctx)
+{
+	/* if reg sequence is supported and enabled, set flag to
+	 * indicate we want to have REG_SET, REG_UPDATE macro build
+	 * reg sequence command buffer rather than MMIO directly.
+	 */
+
+	if (ctx->dmub_srv && ctx->dc->debug.dmub_offload_enabled) {
+		struct dc_reg_helper_state *offload =
+			&ctx->dmub_srv->reg_helper_offload;
+
+		/* caller sequence mismatch.  need to debug caller.  offload will not work!!! */
+		ASSERT(!offload->gather_in_progress);
+
+		offload->gather_in_progress = true;
+	}
+}
+
+void reg_sequence_start_execute(const struct dc_context *ctx)
+{
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload && offload->gather_in_progress) {
+		offload->gather_in_progress = false;
+		offload->should_burst_write = false;
+		switch (offload->cmd_data.cmd_common.header.type) {
+		case DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE:
+			submit_dmub_read_modify_write(offload, ctx);
+			break;
+		case DMUB_CMD__REG_REG_WAIT:
+			submit_dmub_reg_wait(offload, ctx);
+			break;
+		case DMUB_CMD__REG_SEQ_BURST_WRITE:
+			submit_dmub_burst_write(offload, ctx);
+			break;
+		default:
+			return;
+		}
+
+		dc_dmub_srv_cmd_execute(ctx->dmub_srv);
+	}
+}
+
+void reg_sequence_wait_done(const struct dc_context *ctx)
+{
+	/* callback to DM to poll for last submission done*/
+	struct dc_reg_helper_state *offload;
+
+	if (!ctx->dmub_srv)
+		return;
+
+	offload = &ctx->dmub_srv->reg_helper_offload;
+
+	if (offload &&
+	    ctx->dc->debug.dmub_offload_enabled &&
+	    !ctx->dc->debug.dmcub_emulation) {
+		dc_dmub_srv_wait_idle(ctx->dmub_srv);
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index e0856bb8511f..25c50bcab9e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -26,8 +26,6 @@
 #ifndef DC_HW_TYPES_H
 #define DC_HW_TYPES_H
 
-#ifndef AMD_EDID_UTILITY
-
 #include "os_types.h"
 #include "fixed31_32.h"
 #include "signal_types.h"
@@ -167,12 +165,10 @@ enum surface_pixel_format {
 	/*swaped & float*/
 	SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F,
 	/*grow graphics here if necessary */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX,
 	SURFACE_PIXEL_FORMAT_GRPH_BGR101111_FIX,
 	SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FLOAT,
 	SURFACE_PIXEL_FORMAT_GRPH_BGR101111_FLOAT,
-#endif
 	SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr =
 		SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
@@ -180,10 +176,8 @@ enum surface_pixel_format {
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb,
 		SURFACE_PIXEL_FORMAT_SUBSAMPLE_END,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SURFACE_PIXEL_FORMAT_VIDEO_ACrYCb2101010,
 	SURFACE_PIXEL_FORMAT_VIDEO_CrYCbA1010102,
-#endif
 	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_INVALID
 
@@ -222,12 +216,10 @@ enum tile_split_values {
 	DC_ROTATED_MICRO_TILING = 0x3,
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 enum tripleBuffer_enable {
 	DC_TRIPLEBUFFER_DISABLE = 0x0,
 	DC_TRIPLEBUFFER_ENABLE = 0x1,
 };
-#endif
 
 /* TODO: These values come from hardware spec. We need to readdress this
  * if they ever change.
@@ -427,13 +419,11 @@ struct dc_csc_transform {
 	bool enable_adjustment;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct dc_rgb_fixed {
 	struct fixed31_32 red;
 	struct fixed31_32 green;
 	struct fixed31_32 blue;
 };
-#endif
 
 struct dc_gamma {
 	struct kref refcount;
@@ -468,10 +458,8 @@ enum dc_cursor_color_format {
 	CURSOR_MODE_COLOR_1BIT_AND,
 	CURSOR_MODE_COLOR_PRE_MULTIPLIED_ALPHA,
 	CURSOR_MODE_COLOR_UN_PRE_MULTIPLIED_ALPHA,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	CURSOR_MODE_COLOR_64BIT_FP_PRE_MULTIPLIED,
 	CURSOR_MODE_COLOR_64BIT_FP_UN_PRE_MULTIPLIED
-#endif
 };
 
 /*
@@ -594,8 +582,6 @@ struct scaling_taps {
 	bool integer_scaling;
 };
 
-#endif /* AMD_EDID_UTILITY */
-
 enum dc_timing_standard {
 	DC_TIMING_STANDARD_UNDEFINED,
 	DC_TIMING_STANDARD_DMT,
@@ -626,10 +612,8 @@ enum dc_color_depth {
 	COLOR_DEPTH_121212,
 	COLOR_DEPTH_141414,
 	COLOR_DEPTH_161616,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	COLOR_DEPTH_999,
 	COLOR_DEPTH_111111,
-#endif
 	COLOR_DEPTH_COUNT
 };
 
@@ -690,9 +674,7 @@ struct dc_crtc_timing_flags {
 	 * rates less than or equal to 340Mcsc */
 	uint32_t LTE_340MCSC_SCRAMBLE:1;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	uint32_t DSC : 1; /* Use DSC with this timing */
-#endif
 };
 
 enum dc_timing_3d_format {
@@ -717,7 +699,6 @@ enum dc_timing_3d_format {
 	TIMING_3D_FORMAT_MAX,
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct dc_dsc_config {
 	uint32_t num_slices_h; /* Number of DSC slices - horizontal */
 	uint32_t num_slices_v; /* Number of DSC slices - vertical */
@@ -728,7 +709,6 @@ struct dc_dsc_config {
 	bool ycbcr422_simple; /* Tell DSC engine to convert YCbCr 4:2:2 to 'YCbCr 4:2:2 simple'. */
 	int32_t rc_buffer_size; /* DSC RC buffer block size in bytes */
 };
-#endif
 struct dc_crtc_timing {
 	uint32_t h_total;
 	uint32_t h_border_left;
@@ -755,13 +735,9 @@ struct dc_crtc_timing {
 	enum scanning_type scan_type;
 
 	struct dc_crtc_timing_flags flags;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dc_dsc_config dsc_cfg;
-#endif
 };
 
-#ifndef AMD_EDID_UTILITY
-
 enum trigger_delay {
 	TRIGGER_DELAY_NEXT_PIXEL = 0,
 	TRIGGER_DELAY_NEXT_LINE,
@@ -796,7 +772,6 @@ enum vram_type {
 	VIDEO_MEMORY_TYPE_GDDR6  = 6,
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 enum dwb_cnv_out_bpc {
 	DWB_CNV_OUT_BPC_8BPC  = 0,
 	DWB_CNV_OUT_BPC_10BPC = 1,
@@ -847,7 +822,6 @@ struct mcif_buf_params {
 	unsigned int		swlock;
 };
 
-#endif
 
 #define MAX_TG_COLOR_VALUE 0x3FF
 struct tg_color {
@@ -857,7 +831,5 @@ struct tg_color {
 	uint16_t color_b_cb;
 };
 
-#endif /* AMD_EDID_UTILITY */
-
 #endif /* DC_HW_TYPES_H */
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index f24fd19ed93d..d25603128394 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -29,13 +29,11 @@
 #include "dc_types.h"
 #include "grph_object_defs.h"
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 enum dc_link_fec_state {
 	dc_link_fec_not_ready,
 	dc_link_fec_ready,
 	dc_link_fec_enabled
 };
-#endif
 struct dc_link_status {
 	bool link_active;
 	struct dpcd_caps *dpcd_caps;
@@ -85,6 +83,7 @@ struct dc_link {
 	bool link_state_valid;
 	bool aux_access_disabled;
 	bool sync_lt_in_progress;
+	bool is_lttpr_mode_transparent;
 
 	/* caps is the same as reported_link_cap. link_traing use
 	 * reported_link_cap. Will clean up.  TODO
@@ -95,6 +94,7 @@ struct dc_link {
 	struct dc_lane_settings cur_lane_setting;
 	struct dc_link_settings preferred_link_setting;
 	struct dc_link_training_overrides preferred_training_settings;
+	struct dp_audio_test_data audio_test_data;
 
 	uint8_t ddc_hw_inst;
 
@@ -133,6 +133,7 @@ struct dc_link {
 	struct link_flags {
 		bool dp_keep_receiver_powered;
 		bool dp_skip_DID2;
+		bool dp_skip_reset_segment;
 	} wa_flags;
 	struct link_mst_stream_allocation_table mst_stream_alloc_table;
 
@@ -140,9 +141,7 @@ struct dc_link {
 
 	struct link_trace link_trace;
 	struct gpio *hpd_gpio;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	enum dc_link_fec_state fec_state;
-#endif
 };
 
 const struct dc_link_status *dc_link_get_status(const struct dc_link *dc_link);
@@ -206,6 +205,7 @@ enum dc_detect_reason {
 bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
 bool dc_link_get_hpd_state(struct dc_link *dc_link);
 enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx);
+enum dc_status dc_link_reallocate_mst_payload(struct dc_link *link);
 
 /* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt).
  * Return:
@@ -259,6 +259,7 @@ void dc_link_dp_disable_hpd(const struct dc_link *link);
 bool dc_link_dp_set_test_pattern(
 	struct dc_link *link,
 	enum dp_test_pattern test_pattern,
+	enum dp_test_pattern_color_space test_pattern_color_space,
 	const struct link_training_settings *p_link_settings,
 	const unsigned char *p_custom_pattern,
 	unsigned int cust_pattern_size);
@@ -290,6 +291,7 @@ void dc_link_enable_hpd(const struct dc_link *link);
 void dc_link_disable_hpd(const struct dc_link *link);
 void dc_link_set_test_pattern(struct dc_link *link,
 			enum dp_test_pattern test_pattern,
+			enum dp_test_pattern_color_space test_pattern_color_space,
 			const struct link_training_settings *p_link_settings,
 			const unsigned char *p_custom_pattern,
 			unsigned int cust_pattern_size);
@@ -300,11 +302,18 @@ uint32_t dc_link_bandwidth_kbps(
 const struct dc_link_settings *dc_link_get_link_cap(
 		const struct dc_link *link);
 
+void dc_link_overwrite_extended_receiver_cap(
+		struct dc_link *link);
+
 bool dc_submit_i2c(
 		struct dc *dc,
 		uint32_t link_index,
 		struct i2c_command *cmd);
 
+bool dc_submit_i2c_oem(
+		struct dc *dc,
+		struct i2c_command *cmd);
+
 uint32_t dc_bandwidth_in_kbps_from_timing(
 	const struct dc_crtc_timing *timing);
 #endif /* DC_LINK_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index fdb6adc37857..92096de79dec 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -52,7 +52,6 @@ struct freesync_context {
 	bool dummy;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 enum hubp_dmdata_mode {
 	DMDATA_SW_MODE,
 	DMDATA_HW_MODE
@@ -82,9 +81,7 @@ struct dc_dmdata_attributes {
 	/* An unbounded array of uint32s, represents software dmdata to be loaded */
 	uint32_t *dmdata_sw_data;
 };
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_writeback_info {
 	bool wb_enabled;
 	int dwb_pipe_inst;
@@ -96,7 +93,6 @@ struct dc_writeback_update {
 	unsigned int num_wb_info;
 	struct dc_writeback_info writeback_info[MAX_DWB_PIPES];
 };
-#endif
 
 enum vertical_interrupt_ref_point {
 	START_V_UPDATE = 0,
@@ -121,9 +117,7 @@ union stream_update_flags {
 		uint32_t abm_level:1;
 		uint32_t dpms_off:1;
 		uint32_t gamut_remap:1;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		uint32_t wb_update:1;
-#endif
 	} bits;
 
 	uint32_t raw;
@@ -164,6 +158,7 @@ struct dc_stream_state {
 
 	enum view_3d_format view_format;
 
+	bool use_vsc_sdp_for_colorimetry;
 	bool ignore_msa_timing_param;
 	bool converter_disable_audio;
 	uint8_t qs_bit;
@@ -203,11 +198,9 @@ struct dc_stream_state {
 
 	struct crtc_trigger_info triggered_crtc_reset;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* writeback */
 	unsigned int num_wb_info;
 	struct dc_writeback_info writeback_info[MAX_DWB_PIPES];
-#endif
 	/* Computed state bits */
 	bool mode_changed : 1;
 
@@ -226,9 +219,7 @@ struct dc_stream_state {
 	bool apply_seamless_boot_optimization;
 
 	uint32_t stream_id;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool is_dsc_enabled;
-#endif
 	union stream_update_flags update_flags;
 };
 
@@ -251,6 +242,7 @@ struct dc_stream_update {
 	struct dc_info_packet *vsp_infopacket;
 
 	bool *dpms_off;
+	bool integer_scaling_update;
 
 	struct colorspace_transform *gamut_remap;
 	enum dc_color_space *output_color_space;
@@ -258,12 +250,8 @@ struct dc_stream_update {
 
 	struct dc_csc_transform *output_csc_transform;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dc_writeback_update *wb_update;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 	struct dc_dsc_config *dsc_config;
-#endif
 };
 
 bool dc_is_stream_unchanged(
@@ -353,18 +341,23 @@ bool dc_add_all_planes_for_stream(
 		int plane_count,
 		struct dc_state *context);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dc_stream_add_writeback(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_writeback_info *wb_info);
+
 bool dc_stream_remove_writeback(struct dc *dc,
 		struct dc_stream_state *stream,
 		uint32_t dwb_pipe_inst);
+
+bool dc_stream_warmup_writeback(struct dc *dc,
+		int num_dwb,
+		struct dc_writeback_info *wb_info);
+
 bool dc_stream_dmdata_status_done(struct dc *dc, struct dc_stream_state *stream);
+
 bool dc_stream_set_dynamic_metadata(struct dc *dc,
 		struct dc_stream_state *stream,
 		struct dc_dmdata_attributes *dmdata_attr);
-#endif
 
 enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream);
 
@@ -446,10 +439,10 @@ bool dc_stream_get_crc(struct dc *dc,
 		       uint32_t *g_y,
 		       uint32_t *b_cb);
 
-void dc_stream_set_static_screen_events(struct dc *dc,
+void dc_stream_set_static_screen_params(struct dc *dc,
 					struct dc_stream_state **stream,
 					int num_streams,
-					const struct dc_static_screen_events *events);
+					const struct dc_static_screen_params *params);
 
 void dc_stream_set_dyn_expansion(struct dc *dc, struct dc_stream_state *stream,
 		enum dc_dynamic_expansion option);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index d9be8fc3889f..e59532d98cb4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -25,7 +25,6 @@
 #ifndef DC_TYPES_H_
 #define DC_TYPES_H_
 
-#ifndef AMD_EDID_UTILITY
 /* AND EdidUtility only needs a portion
  * of this file, including the rest only
  * causes additional issues.
@@ -48,6 +47,7 @@ struct dc_stream_state;
 struct dc_link;
 struct dc_sink;
 struct dal;
+struct dc_dmub_srv;
 
 /********************************
  * Environment definitions
@@ -60,7 +60,12 @@ enum dce_environment {
 	DCE_ENV_FPGA_MAXIMUS,
 	/* Emulation on real HW or on FPGA. Used by Diagnostics, enforces
 	 * requirements of Diagnostics team. */
-	DCE_ENV_DIAG
+	DCE_ENV_DIAG,
+	/*
+	 * Guest VM system, DC HW may exist but is not virtualized and
+	 * should not be used.  SW support for VDI only.
+	 */
+	DCE_ENV_VIRTUAL_HW
 };
 
 /* Note: use these macro definitions instead of direct comparison! */
@@ -109,6 +114,8 @@ struct dc_context {
 	uint32_t dc_sink_id_count;
 	uint32_t dc_stream_id_count;
 	uint64_t fbc_gpu_addr;
+	struct dc_dmub_srv *dmub_srv;
+
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	struct cp_psp cp_psp;
 #endif
@@ -119,6 +126,7 @@ struct dc_context {
 #define DC_EDID_BLOCK_SIZE 128
 #define MAX_SURFACE_NUM 4
 #define NUM_PIXEL_FORMATS 10
+#define MAX_REPEATER_CNT 8
 
 #include "dc_ddc_types.h"
 
@@ -221,6 +229,7 @@ struct dc_panel_patch {
 	unsigned int extra_t12_ms;
 	unsigned int extra_delay_backlight_off;
 	unsigned int extra_t7_ms;
+	unsigned int manage_secondary_link;
 };
 
 struct dc_edid_caps {
@@ -402,6 +411,30 @@ enum dpcd_downstream_port_max_bpc {
 	DOWN_STREAM_MAX_12BPC,
 	DOWN_STREAM_MAX_16BPC
 };
+
+
+enum link_training_offset {
+	DPRX                = 0,
+	LTTPR_PHY_REPEATER1 = 1,
+	LTTPR_PHY_REPEATER2 = 2,
+	LTTPR_PHY_REPEATER3 = 3,
+	LTTPR_PHY_REPEATER4 = 4,
+	LTTPR_PHY_REPEATER5 = 5,
+	LTTPR_PHY_REPEATER6 = 6,
+	LTTPR_PHY_REPEATER7 = 7,
+	LTTPR_PHY_REPEATER8 = 8
+};
+
+struct dc_lttpr_caps {
+	union dpcd_rev revision;
+	uint8_t mode;
+	uint8_t max_lane_count;
+	uint8_t max_link_rate;
+	uint8_t phy_repeater_cnt;
+	uint8_t max_ext_timeout;
+	uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1];
+};
+
 struct dc_dongle_caps {
 	/* dongle type (DP converter, CV smart dongle) */
 	enum display_dongle_type dongle_type;
@@ -440,7 +473,6 @@ enum display_content_type {
 	DISPLAY_CONTENT_TYPE_GAME = 8
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 /* writeback */
 struct dwb_stereo_params {
 	bool				stereo_enabled;		/* false: normal mode, true: 3D stereo */
@@ -471,7 +503,6 @@ struct dc_dwb_params {
 	enum dwb_subsample_position	subsample_position;
 	struct dc_transfer_func *out_transfer_func;
 };
-#endif
 
 /* audio*/
 
@@ -573,15 +604,17 @@ struct audio_info {
 	/* this field must be last in this struct */
 	struct audio_mode modes[DC_MAX_AUDIO_DESC_COUNT];
 };
-
+struct audio_check {
+	unsigned int audio_packet_type;
+	unsigned int max_audiosample_rate;
+	unsigned int acat;
+};
 enum dc_infoframe_type {
 	DC_HDMI_INFOFRAME_TYPE_VENDOR = 0x81,
 	DC_HDMI_INFOFRAME_TYPE_AVI = 0x82,
 	DC_HDMI_INFOFRAME_TYPE_SPD = 0x83,
 	DC_HDMI_INFOFRAME_TYPE_AUDIO = 0x84,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DC_DP_INFOFRAME_TYPE_PPS = 0x10,
-#endif
 };
 
 struct dc_info_packet {
@@ -696,7 +729,7 @@ struct psr_context {
 	/* The VSync rate in Hz used to calculate the
 	 * step size for smooth brightness feature
 	 */
-	unsigned int vsyncRateHz;
+	unsigned int vsync_rate_hz;
 	unsigned int skipPsrWaitForPllLock;
 	unsigned int numberOfControllers;
 	/* Unused, for future use. To indicate that first changed frame from
@@ -757,10 +790,6 @@ struct dc_clock_config {
 	uint32_t current_clock_khz;/*current clock in use*/
 };
 
-#endif /*AMD_EDID_UTILITY*/
-//AMD EDID UTILITY does not need any of the above structures
-
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* DSC DPCD capabilities */
 union dsc_slice_caps1 {
 	struct {
@@ -830,6 +859,5 @@ struct dsc_dec_dpcd_caps {
 	uint32_t branch_overall_throughput_1_mps; /* In MPs */
 	uint32_t branch_max_line_width;
 };
-#endif
 
 #endif /* DC_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
index 7ba7e6f722f6..ba0caaffa24b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
@@ -67,7 +67,6 @@
 	SRI(DC_ABM1_HGLS_REG_READ_PROGRESS, ABM, id), \
 	NBIO_SR(BIOS_SCRATCH_2)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define ABM_DCN20_REG_LIST() \
 	ABM_COMMON_REG_LIST_DCE_BASE(), \
 	SR(DC_ABM1_HG_SAMPLE_RATE), \
@@ -81,7 +80,6 @@
 	SR(DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES), \
 	SR(DC_ABM1_HGLS_REG_READ_PROGRESS), \
 	NBIO_SR(BIOS_SCRATCH_2)
-#endif
 
 #define ABM_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -163,9 +161,7 @@
 	ABM_SF(ABM0_DC_ABM1_HGLS_REG_READ_PROGRESS, \
 			ABM1_BL_REG_READ_MISSED_FRAME_CLEAR, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define ABM_MASK_SH_LIST_DCN20(mask_sh) ABM_MASK_SH_LIST_DCE110(mask_sh)
-#endif
 
 #define ABM_REG_FIELD_LIST(type) \
 	type ABM1_HG_NUM_OF_BINS_SEL; \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 793c0cec407f..f1a5d2c6aa37 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -60,12 +60,14 @@ enum {
 	AUX_DEFER_RETRY_COUNTER = 6
 };
 
-#define TIME_OUT_INCREMENT      1016
-#define TIME_OUT_MULTIPLIER_8 	8
-#define TIME_OUT_MULTIPLIER_16  16
-#define TIME_OUT_MULTIPLIER_32  32
-#define TIME_OUT_MULTIPLIER_64  64
-#define MAX_TIMEOUT_LENGTH      127
+#define TIME_OUT_INCREMENT        1016
+#define TIME_OUT_MULTIPLIER_8     8
+#define TIME_OUT_MULTIPLIER_16    16
+#define TIME_OUT_MULTIPLIER_32    32
+#define TIME_OUT_MULTIPLIER_64    64
+#define MAX_TIMEOUT_LENGTH        127
+#define DEFAULT_AUX_ENGINE_MULT   0
+#define DEFAULT_AUX_ENGINE_LENGTH 69
 
 static void release_engine(
 	struct dce_aux *engine)
@@ -427,11 +429,14 @@ void dce110_engine_destroy(struct dce_aux **engine)
 
 }
 
-static bool dce_aux_configure_timeout(struct ddc_service *ddc,
+static uint32_t dce_aux_configure_timeout(struct ddc_service *ddc,
 		uint32_t timeout_in_us)
 {
 	uint32_t multiplier = 0;
 	uint32_t length = 0;
+	uint32_t prev_length = 0;
+	uint32_t prev_mult = 0;
+	uint32_t prev_timeout_val = 0;
 	struct ddc *ddc_pin = ddc->ddc_pin;
 	struct dce_aux *aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
 	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(aux_engine);
@@ -440,7 +445,10 @@ static bool dce_aux_configure_timeout(struct ddc_service *ddc,
 	aux110->polling_timeout_period = timeout_in_us * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER;
 
 	/* 2-Update aux timeout period length and multiplier */
-	if (timeout_in_us <= TIME_OUT_INCREMENT) {
+	if (timeout_in_us == 0) {
+		multiplier = DEFAULT_AUX_ENGINE_MULT;
+		length = DEFAULT_AUX_ENGINE_LENGTH;
+	} else if (timeout_in_us <= TIME_OUT_INCREMENT) {
 		multiplier = 0;
 		length = timeout_in_us/TIME_OUT_MULTIPLIER_8;
 		if (timeout_in_us % TIME_OUT_MULTIPLIER_8 != 0)
@@ -464,9 +472,29 @@ static bool dce_aux_configure_timeout(struct ddc_service *ddc,
 
 	length = (length < MAX_TIMEOUT_LENGTH) ? length : MAX_TIMEOUT_LENGTH;
 
+	REG_GET_2(AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, &prev_length, AUX_RX_TIMEOUT_LEN_MUL, &prev_mult);
+
+	switch (prev_mult) {
+	case 0:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_8;
+		break;
+	case 1:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_16;
+		break;
+	case 2:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_32;
+		break;
+	case 3:
+		prev_timeout_val = prev_length * TIME_OUT_MULTIPLIER_64;
+		break;
+	default:
+		prev_timeout_val = DEFAULT_AUX_ENGINE_LENGTH * TIME_OUT_MULTIPLIER_8;
+		break;
+	}
+
 	REG_UPDATE_SEQ_2(AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, length, AUX_RX_TIMEOUT_LEN_MUL, multiplier);
 
-	return true;
+	return prev_timeout_val;
 }
 
 static struct dce_aux_funcs aux_functions = {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index b4b2c79a8073..382465862f29 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -30,7 +30,6 @@
 #include "inc/hw/aux_engine.h"
 
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define AUX_COMMON_REG_LIST0(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
 	SRI(AUX_ARB_CONTROL, DP_AUX, id), \
@@ -39,7 +38,6 @@
 	SRI(AUX_INTERRUPT_CONTROL, DP_AUX, id), \
 	SRI(AUX_DPHY_RX_CONTROL1, DP_AUX, id), \
 	SRI(AUX_SW_STATUS, DP_AUX, id)
-#endif
 
 #define AUX_COMMON_REG_LIST(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
@@ -311,7 +309,7 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *cmd);
 
 struct dce_aux_funcs {
-	bool (*configure_timeout)
+	uint32_t (*configure_timeout)
 		(struct ddc_service *ddc,
 		 uint32_t timeout);
 	void (*destroy)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index f787a6b94781..2e992fbc0d71 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -905,7 +905,7 @@ static bool dce112_program_pix_clk(
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (IS_FPGA_MAXIMUS_DC(clock_source->ctx->dce_environment)) {
 		unsigned int inst = pix_clk_params->controller_id - CONTROLLER_ID_D0;
 		unsigned dp_dto_ref_100hz = 7000000;
@@ -1004,7 +1004,6 @@ static bool get_pixel_clk_frequency_100hz(
 	return false;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /* this table is use to find *1.001 and /1.001 pixel rates from non-precise pixel rate */
 struct pixel_rate_range_table_entry {
@@ -1064,7 +1063,6 @@ static const struct clock_source_funcs dcn20_clk_src_funcs = {
 	.get_pix_clk_dividers = dce112_get_pix_clk_dividers,
 	.get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz
 };
-#endif
 
 /*****************************************/
 /* Constructor                           */
@@ -1435,7 +1433,6 @@ bool dce112_clk_src_construct(
 	return true;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dcn20_clk_src_construct(
 	struct dce110_clk_src *clk_src,
 	struct dc_context *ctx,
@@ -1451,4 +1448,3 @@ bool dcn20_clk_src_construct(
 
 	return ret;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
index 43c1bf60b83c..51bd25079606 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
@@ -55,7 +55,6 @@
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_DCCG_DEEP_COLOR_CNTL, mask_sh),\
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_PIXCLK_DOUBLE_RATE_ENABLE, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define CS_COMMON_REG_LIST_DCN2_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
 		SRII(PHASE, DP_DTO, 0),\
@@ -76,9 +75,7 @@
 		SRII(PIXEL_RATE_CNTL, OTG, 3),\
 		SRII(PIXEL_RATE_CNTL, OTG, 4),\
 		SRII(PIXEL_RATE_CNTL, OTG, 5)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define CS_COMMON_REG_LIST_DCN2_1(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
 		SRII(PHASE, DP_DTO, 0),\
@@ -93,17 +90,14 @@
 		SRII(PIXEL_RATE_CNTL, OTG, 1),\
 		SRII(PIXEL_RATE_CNTL, OTG, 2),\
 		SRII(PIXEL_RATE_CNTL, OTG, 3)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define CS_COMMON_MASK_SH_LIST_DCN2_0(mask_sh)\
 	CS_SF(DP_DTO0_PHASE, DP_DTO0_PHASE, mask_sh),\
 	CS_SF(DP_DTO0_MODULO, DP_DTO0_MODULO, mask_sh),\
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_DCCG_DEEP_COLOR_CNTL, mask_sh),\
 	CS_SF(OTG0_PIXEL_RATE_CNTL, DP_DTO0_ENABLE, mask_sh)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 
 #define CS_COMMON_REG_LIST_DCN1_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
@@ -201,7 +195,6 @@ bool dce112_clk_src_construct(
 	const struct dce110_clk_src_shift *cs_shift,
 	const struct dce110_clk_src_mask *cs_mask);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 bool dcn20_clk_src_construct(
 	struct dce110_clk_src *clk_src,
 	struct dc_context *ctx,
@@ -210,6 +203,5 @@ bool dcn20_clk_src_construct(
 	const struct dce110_clk_src_regs *regs,
 	const struct dce110_clk_src_shift *cs_shift,
 	const struct dce110_clk_src_mask *cs_mask);
-#endif
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index ba995d3f2318..30d953acd016 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -59,6 +59,12 @@
 #define MCP_BL_SET_PWM_FRAC 0x6A  /* Enable or disable Fractional PWM */
 #define MASTER_COMM_CNTL_REG__MASTER_COMM_INTERRUPT_MASK   0x00000001L
 
+// PSP FW version
+#define mmMP0_SMN_C2PMSG_58				0x1607A
+
+//Register access policy version
+#define mmMP0_SMN_C2PMSG_91				0x1609B
+
 static bool dce_dmcu_init(struct dmcu *dmcu)
 {
 	// Do nothing
@@ -318,7 +324,7 @@ static void dce_get_psr_wait_loop(
 	return;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 static void dcn10_get_dmcu_version(struct dmcu *dmcu)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
@@ -373,6 +379,7 @@ static bool dcn10_dmcu_init(struct dmcu *dmcu)
 	const struct dc_config *config = &dmcu->ctx->dc->config;
 	bool status = false;
 
+	PERF_TRACE();
 	/*  Definition of DC_DMCU_SCRATCH
 	 *  0 : firmare not loaded
 	 *  1 : PSP load DMCU FW but not initialized
@@ -429,9 +436,21 @@ static bool dcn10_dmcu_init(struct dmcu *dmcu)
 		break;
 	}
 
+	PERF_TRACE();
 	return status;
 }
 
+static bool dcn21_dmcu_init(struct dmcu *dmcu)
+{
+	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
+	uint32_t dmcub_psp_version = REG_READ(DMCUB_SCRATCH15);
+
+	if (dmcu->auto_load_dmcu && dmcub_psp_version == 0) {
+		return false;
+	}
+
+	return dcn10_dmcu_init(dmcu);
+}
 
 static bool dcn10_dmcu_load_iram(struct dmcu *dmcu,
 		unsigned int start_offset,
@@ -518,9 +537,6 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	if (dmcu->dmcu_state != DMCU_RUNNING)
 		return;
 
-	dcn10_get_dmcu_psr_state(dmcu, &psr_state);
-	if (psr_state == 0 && !enable)
-		return;
 	/* waitDMCUReadyForCmd */
 	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0,
 				dmcu_wait_reg_ready_interval,
@@ -727,9 +743,7 @@ static bool dcn10_is_dmcu_initialized(struct dmcu *dmcu)
 	return true;
 }
 
-#endif //(CONFIG_DRM_AMD_DC_DCN1_0)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 static bool dcn20_lock_phy(struct dmcu *dmcu)
 {
@@ -777,7 +791,7 @@ static bool dcn20_unlock_phy(struct dmcu *dmcu)
 	return true;
 }
 
-#endif //(CONFIG_DRM_AMD_DC_DCN2_0)
+#endif //(CONFIG_DRM_AMD_DC_DCN)
 
 static const struct dmcu_funcs dce_funcs = {
 	.dmcu_init = dce_dmcu_init,
@@ -790,7 +804,7 @@ static const struct dmcu_funcs dce_funcs = {
 	.is_dmcu_initialized = dce_is_dmcu_initialized
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 static const struct dmcu_funcs dcn10_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -801,9 +815,7 @@ static const struct dmcu_funcs dcn10_funcs = {
 	.get_psr_wait_loop = dcn10_get_psr_wait_loop,
 	.is_dmcu_initialized = dcn10_is_dmcu_initialized
 };
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static const struct dmcu_funcs dcn20_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -816,6 +828,19 @@ static const struct dmcu_funcs dcn20_funcs = {
 	.lock_phy = dcn20_lock_phy,
 	.unlock_phy = dcn20_unlock_phy
 };
+
+static const struct dmcu_funcs dcn21_funcs = {
+	.dmcu_init = dcn21_dmcu_init,
+	.load_iram = dcn10_dmcu_load_iram,
+	.set_psr_enable = dcn10_dmcu_set_psr_enable,
+	.setup_psr = dcn10_dmcu_setup_psr,
+	.get_psr_state = dcn10_get_dmcu_psr_state,
+	.set_psr_wait_loop = dcn10_psr_wait_loop,
+	.get_psr_wait_loop = dcn10_get_psr_wait_loop,
+	.is_dmcu_initialized = dcn10_is_dmcu_initialized,
+	.lock_phy = dcn20_lock_phy,
+	.unlock_phy = dcn20_unlock_phy
+};
 #endif
 
 static void dce_dmcu_construct(
@@ -836,6 +861,26 @@ static void dce_dmcu_construct(
 	dmcu_dce->dmcu_mask = dmcu_mask;
 }
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static void dcn21_dmcu_construct(
+		struct dce_dmcu *dmcu_dce,
+		struct dc_context *ctx,
+		const struct dce_dmcu_registers *regs,
+		const struct dce_dmcu_shift *dmcu_shift,
+		const struct dce_dmcu_mask *dmcu_mask)
+{
+	uint32_t psp_version = 0;
+
+	dce_dmcu_construct(dmcu_dce, ctx, regs, dmcu_shift, dmcu_mask);
+
+	if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) {
+		psp_version = dm_read_reg(ctx, mmMP0_SMN_C2PMSG_58);
+		dmcu_dce->base.auto_load_dmcu = ((psp_version & 0x00FF00FF) > 0x00110029);
+		dmcu_dce->base.psp_version = psp_version;
+	}
+}
+#endif
+
 struct dmcu *dce_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
@@ -857,7 +902,7 @@ struct dmcu *dce_dmcu_create(
 	return &dmcu_dce->base;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 struct dmcu *dcn10_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
@@ -878,9 +923,7 @@ struct dmcu *dcn10_dmcu_create(
 
 	return &dmcu_dce->base;
 }
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dmcu *dcn20_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
@@ -901,6 +944,27 @@ struct dmcu *dcn20_dmcu_create(
 
 	return &dmcu_dce->base;
 }
+
+struct dmcu *dcn21_dmcu_create(
+	struct dc_context *ctx,
+	const struct dce_dmcu_registers *regs,
+	const struct dce_dmcu_shift *dmcu_shift,
+	const struct dce_dmcu_mask *dmcu_mask)
+{
+	struct dce_dmcu *dmcu_dce = kzalloc(sizeof(*dmcu_dce), GFP_KERNEL);
+
+	if (dmcu_dce == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dcn21_dmcu_construct(
+		dmcu_dce, ctx, regs, dmcu_shift, dmcu_mask);
+
+	dmcu_dce->base.funcs = &dcn21_funcs;
+
+	return &dmcu_dce->base;
+}
 #endif
 
 void dce_dmcu_destroy(struct dmcu **dmcu)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
index cc8587683b4b..5e044c2d3d6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.h
@@ -71,6 +71,10 @@
 	DMCU_COMMON_REG_LIST_DCE_BASE(), \
 	SR(DMU_MEM_PWR_CNTL)
 
+#define DMCU_DCN20_REG_LIST()\
+	DMCU_DCN10_REG_LIST(), \
+	SR(DMCUB_SCRATCH15)
+
 #define DMCU_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -175,6 +179,7 @@ struct dce_dmcu_registers {
 	uint32_t DMCU_INTERRUPT_TO_UC_EN_MASK;
 	uint32_t SMU_INTERRUPT_CONTROL;
 	uint32_t DC_DMCU_SCRATCH;
+	uint32_t DMCUB_SCRATCH15;
 };
 
 struct dce_dmcu {
@@ -261,13 +266,17 @@ struct dmcu *dcn10_dmcu_create(
 	const struct dce_dmcu_shift *dmcu_shift,
 	const struct dce_dmcu_mask *dmcu_mask);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dmcu *dcn20_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
 	const struct dce_dmcu_shift *dmcu_shift,
 	const struct dce_dmcu_mask *dmcu_mask);
-#endif
+
+struct dmcu *dcn21_dmcu_create(
+	struct dc_context *ctx,
+	const struct dce_dmcu_registers *regs,
+	const struct dce_dmcu_shift *dmcu_shift,
+	const struct dce_dmcu_mask *dmcu_mask);
 
 void dce_dmcu_destroy(struct dmcu **dmcu);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
index 0275d6d60da4..e1c5839a80dc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.c
@@ -25,7 +25,7 @@
 
 #include "dce_hwseq.h"
 #include "reg_helper.h"
-#include "hw_sequencer.h"
+#include "hw_sequencer_private.h"
 #include "core_types.h"
 
 #define CTX \
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 32d145a0d6fc..c5aa1f48593a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -25,7 +25,7 @@
 #ifndef __DCE_HWSEQ_H__
 #define __DCE_HWSEQ_H__
 
-#include "hw_sequencer.h"
+#include "dc_types.h"
 
 #define BL_REG_LIST()\
 	SR(LVTMA_PWRSEQ_CNTL), \
@@ -210,7 +210,6 @@
 	SR(DC_IP_REQUEST_CNTL), \
 	BL_REG_LIST()
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define HWSEQ_DCN2_REG_LIST()\
 	HWSEQ_DCN_REG_LIST(), \
 	HSWEQ_DCN_PIXEL_RATE_REG_LIST(OTG, 0), \
@@ -276,9 +275,7 @@
 	SR(D6VGA_CONTROL), \
 	SR(DC_IP_REQUEST_CNTL), \
 	BL_REG_LIST()
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define HWSEQ_DCN21_REG_LIST()\
 	HWSEQ_DCN_REG_LIST(), \
 	HSWEQ_DCN_PIXEL_RATE_REG_LIST(OTG, 0), \
@@ -329,7 +326,6 @@
 	SR(D6VGA_CONTROL), \
 	SR(DC_IP_REQUEST_CNTL), \
 	BL_REG_LIST()
-#endif
 
 struct dce_hwseq_registers {
 
@@ -577,7 +573,6 @@ struct dce_hwseq_registers {
 	HWS_SF(, VGA_TEST_CONTROL, VGA_TEST_RENDER_START, mask_sh),\
 	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define HWSEQ_DCN2_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
@@ -637,9 +632,7 @@ struct dce_hwseq_registers {
 	HWS_SF(, DOMAIN21_PG_STATUS, DOMAIN21_PGFSM_PWR_STATUS, mask_sh), \
 	HWS_SF(, DC_IP_REQUEST_CNTL, IP_REQUEST_EN, mask_sh), \
 	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh)
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define HWSEQ_DCN21_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
@@ -682,7 +675,6 @@ struct dce_hwseq_registers {
 	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh), \
 	HWS_SF(, LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh)
-#endif
 
 #define HWSEQ_REG_FIELD_LIST(type) \
 	type DCFE_CLOCK_ENABLE; \
@@ -800,8 +792,7 @@ struct dce_hwseq_registers {
 	type D2VGA_MODE_ENABLE; \
 	type D3VGA_MODE_ENABLE; \
 	type D4VGA_MODE_ENABLE; \
-	type AZALIA_AUDIO_DTO_MODULE;\
-	type HPO_HDMISTREAMCLK_GATE_DIS;
+	type AZALIA_AUDIO_DTO_MODULE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
@@ -820,6 +811,10 @@ enum blnd_mode {
 	BLND_MODE_BLENDING,/* Alpha blending - blend 'current' and 'other' */
 };
 
+struct dce_hwseq;
+struct pipe_ctx;
+struct clock_source;
+
 void dce_enable_fe_clock(struct dce_hwseq *hwss,
 		unsigned int inst, bool enable);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c
index 35a75398fcb4..dd41736bb5c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c.c
@@ -31,7 +31,7 @@ bool dce_i2c_submit_command(
 	struct i2c_command *cmd)
 {
 	struct dce_i2c_hw *dce_i2c_hw;
-	struct dce_i2c_sw *dce_i2c_sw;
+	struct dce_i2c_sw dce_i2c_sw = {0};
 
 	if (!ddc) {
 		BREAK_TO_DEBUGGER();
@@ -43,18 +43,15 @@ bool dce_i2c_submit_command(
 		return false;
 	}
 
-	/* The software engine is only available on dce8 */
-	dce_i2c_sw = dce_i2c_acquire_i2c_sw_engine(pool, ddc);
-
-	if (!dce_i2c_sw) {
-		dce_i2c_hw = acquire_i2c_hw_engine(pool, ddc);
-
-		if (!dce_i2c_hw)
-			return false;
+	dce_i2c_hw = acquire_i2c_hw_engine(pool, ddc);
 
+	if (dce_i2c_hw)
 		return dce_i2c_submit_command_hw(pool, ddc, cmd, dce_i2c_hw);
-	}
 
-	return dce_i2c_submit_command_sw(pool, ddc, cmd, dce_i2c_sw);
+	dce_i2c_sw.ctx = ddc->ctx;
+	if (dce_i2c_engine_acquire_sw(&dce_i2c_sw, ddc)) {
+		return dce_i2c_submit_command_sw(pool, ddc, cmd, &dce_i2c_sw);
+	}
 
+	return false;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
index aad7b52165be..1cd4d8fc361f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c
@@ -296,9 +296,7 @@ static bool setup_engine(
 	struct dce_i2c_hw *dce_i2c_hw)
 {
 	uint32_t i2c_setup_limit = I2C_SETUP_TIME_LIMIT_DCE;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t  reset_length = 0;
-#endif
 	/* we have checked I2c not used by DMCU, set SW use I2C REQ to 1 to indicate SW using it*/
 	REG_UPDATE(DC_I2C_ARBITRATION, DC_I2C_SW_USE_I2C_REG_REQ, 1);
 
@@ -322,14 +320,12 @@ static bool setup_engine(
 		REG_UPDATE_N(SETUP, 2,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), i2c_setup_limit,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	} else {
 		reset_length = dce_i2c_hw->send_reset_length;
 		REG_UPDATE_N(SETUP, 3,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), i2c_setup_limit,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_SEND_RESET_LENGTH), reset_length,
 			     FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-#endif
 	}
 	/* Program HW priority
 	 * set to High - interrupt software I2C at any time
@@ -705,7 +701,6 @@ void dcn1_i2c_hw_construct(
 	dce_i2c_hw->setup_limit = I2C_SETUP_TIME_LIMIT_DCN;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn2_i2c_hw_construct(
 	struct dce_i2c_hw *dce_i2c_hw,
 	struct dc_context *ctx,
@@ -724,4 +719,3 @@ void dcn2_i2c_hw_construct(
 	if (ctx->dc->debug.scl_reset_length10)
 		dce_i2c_hw->send_reset_length = I2C_SEND_RESET_LENGTH_10;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h
index cb0234e5d597..d4b2037f7d74 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h
@@ -177,9 +177,7 @@ struct dce_i2c_shift {
 	uint8_t DC_I2C_INDEX;
 	uint8_t DC_I2C_INDEX_WRITE;
 	uint8_t XTAL_REF_DIV;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint8_t DC_I2C_DDC1_SEND_RESET_LENGTH;
-#endif
 	uint8_t DC_I2C_REG_RW_CNTL_STATUS;
 };
 
@@ -220,17 +218,13 @@ struct dce_i2c_mask {
 	uint32_t DC_I2C_INDEX;
 	uint32_t DC_I2C_INDEX_WRITE;
 	uint32_t XTAL_REF_DIV;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t DC_I2C_DDC1_SEND_RESET_LENGTH;
-#endif
 	uint32_t DC_I2C_REG_RW_CNTL_STATUS;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define I2C_COMMON_MASK_SH_LIST_DCN2(mask_sh)\
 	I2C_COMMON_MASK_SH_LIST_DCE110(mask_sh),\
 	I2C_SF(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_SEND_RESET_LENGTH, mask_sh)
-#endif
 
 struct dce_i2c_registers {
 	uint32_t SETUP;
@@ -312,7 +306,6 @@ void dcn1_i2c_hw_construct(
 	const struct dce_i2c_shift *shifts,
 	const struct dce_i2c_mask *masks);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn2_i2c_hw_construct(
 	struct dce_i2c_hw *dce_i2c_hw,
 	struct dc_context *ctx,
@@ -320,7 +313,6 @@ void dcn2_i2c_hw_construct(
 	const struct dce_i2c_registers *regs,
 	const struct dce_i2c_shift *shifts,
 	const struct dce_i2c_mask *masks);
-#endif
 
 bool dce_i2c_submit_command_hw(
 	struct resource_pool *pool,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
index a5a11c251e25..87d8428df6c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.c
@@ -73,31 +73,6 @@ static void release_engine_dce_sw(
 	dce_i2c_sw->ddc = NULL;
 }
 
-static bool get_hw_supported_ddc_line(
-	struct ddc *ddc,
-	enum gpio_ddc_line *line)
-{
-	enum gpio_ddc_line line_found;
-
-	*line = GPIO_DDC_LINE_UNKNOWN;
-
-	if (!ddc) {
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-
-	if (!ddc->hw_info.hw_supported)
-		return false;
-
-	line_found = dal_ddc_get_line(ddc);
-
-	if (line_found >= GPIO_DDC_LINE_COUNT)
-		return false;
-
-	*line = line_found;
-
-	return true;
-}
 static bool wait_for_scl_high_sw(
 	struct dc_context *ctx,
 	struct ddc *ddc,
@@ -524,21 +499,3 @@ bool dce_i2c_submit_command_sw(
 
 	return result;
 }
-struct dce_i2c_sw *dce_i2c_acquire_i2c_sw_engine(
-	struct resource_pool *pool,
-	struct ddc *ddc)
-{
-	enum gpio_ddc_line line;
-	struct dce_i2c_sw *engine = NULL;
-
-	if (get_hw_supported_ddc_line(ddc, &line))
-		engine = pool->sw_i2cs[line];
-
-	if (!engine)
-		return NULL;
-
-	if (!dce_i2c_engine_acquire_sw(engine, ddc))
-		return NULL;
-
-	return engine;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h
index 5bbcdd455614..019fc47bb767 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_sw.h
@@ -49,9 +49,9 @@ bool dce_i2c_submit_command_sw(
 	struct i2c_command *cmd,
 	struct dce_i2c_sw *dce_i2c_sw);
 
-struct dce_i2c_sw *dce_i2c_acquire_i2c_sw_engine(
-	struct resource_pool *pool,
-	struct ddc *ddc);
+bool dce_i2c_engine_acquire_sw(
+	struct dce_i2c_sw *dce_i2c_sw,
+	struct ddc *ddc_handle);
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 6ed922a3c1cd..451574971b96 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -137,7 +137,7 @@ static void dce110_update_generic_info_packet(
 			AFMT_GENERIC0_UPDATE, (packet_index == 0),
 			AFMT_GENERIC2_UPDATE, (packet_index == 2));
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (REG(AFMT_VBI_PACKET_CONTROL1)) {
 		switch (packet_index) {
 		case 0:
@@ -231,7 +231,7 @@ static void dce110_update_hdmi_info_packet(
 				HDMI_GENERIC1_SEND, send,
 				HDMI_GENERIC1_LINE, line);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case 4:
 		if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 			REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
@@ -275,9 +275,10 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	uint32_t h_active_start;
 	uint32_t v_active_start;
 	uint32_t misc0 = 0;
@@ -329,7 +330,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		if (enc110->se_mask->DP_VID_M_DOUBLE_VALUE_EN)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_M_DOUBLE_VALUE_EN, 1);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (enc110->se_mask->DP_VID_N_MUL)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 #endif
@@ -340,7 +341,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (REG(DP_MSA_MISC))
 		misc1 = REG_READ(DP_MSA_MISC);
 #endif
@@ -374,7 +375,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	/* set dynamic range and YCbCr range */
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	switch (hw_crtc_timing.display_color_depth) {
 	case COLOR_DEPTH_666:
 		colorimetry_bpc = 0;
@@ -454,7 +455,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				DP_DYN_RANGE, dynamic_range_rgb,
 				DP_YCBCR_RANGE, dynamic_range_ycbcr);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		if (REG(DP_MSA_COLORIMETRY))
 			REG_SET(DP_MSA_COLORIMETRY, 0, DP_MSA_MISC0, misc0);
 
@@ -489,7 +490,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				hw_crtc_timing.v_front_porch;
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 		/* start at begining of left border */
 		if (REG(DP_MSA_TIMING_PARAM2))
 			REG_SET_2(DP_MSA_TIMING_PARAM2, 0,
@@ -786,7 +787,7 @@ static void dce110_stream_encoder_update_hdmi_info_packets(
 		dce110_update_hdmi_info_packet(enc110, 3, &info_frame->hdrsmd);
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	if (enc110->se_mask->HDMI_DB_DISABLE) {
 		/* for bring up, disable dp double  TODO */
 		if (REG(HDMI_DB_CONTROL))
@@ -824,7 +825,7 @@ static void dce110_stream_encoder_stop_hdmi_info_packets(
 		HDMI_GENERIC1_LINE, 0,
 		HDMI_GENERIC1_SEND, 0);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* stop generic packets 2 & 3 on HDMI */
 	if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 		REG_SET_6(HDMI_GENERIC_PACKET_CONTROL2, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
new file mode 100644
index 000000000000..225955ec6d39
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dmub_psr.h"
+#include "dc.h"
+#include "dc_dmub_srv.h"
+#include "../../dmub/inc/dmub_srv.h"
+#include "dmub_fw_state.h"
+#include "core_types.h"
+#include "ipp.h"
+
+#define MAX_PIPES 6
+
+/**
+ * Get PSR state from firmware.
+ */
+static void dmub_get_psr_state(uint32_t *psr_state)
+{
+	// Not yet implemented
+	// Trigger GPINT interrupt from firmware
+}
+
+/**
+ * Enable/Disable PSR.
+ */
+static void dmub_set_psr_enable(struct dmub_psr *dmub, bool enable)
+{
+	union dmub_rb_cmd cmd;
+	struct dc_context *dc = dmub->ctx;
+
+	cmd.psr_enable.header.type = DMUB_CMD__PSR;
+
+	if (enable)
+		cmd.psr_enable.header.sub_type = DMUB_CMD__PSR_ENABLE;
+	else
+		cmd.psr_enable.header.sub_type = DMUB_CMD__PSR_DISABLE;
+
+	cmd.psr_enable.header.payload_bytes = 0; // Send header only
+
+	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_enable.header);
+	dc_dmub_srv_cmd_execute(dc->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->dmub_srv);
+}
+
+/**
+ * Set PSR level.
+ */
+static void dmub_set_psr_level(struct dmub_psr *dmub, uint16_t psr_level)
+{
+	union dmub_rb_cmd cmd;
+	uint32_t psr_state = 0;
+	struct dc_context *dc = dmub->ctx;
+
+	dmub_get_psr_state(&psr_state);
+
+	if (psr_state == 0)
+		return;
+
+	cmd.psr_set_level.header.type = DMUB_CMD__PSR;
+	cmd.psr_set_level.header.sub_type = DMUB_CMD__PSR_SET_LEVEL;
+	cmd.psr_set_level.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_level_data);
+	cmd.psr_set_level.psr_set_level_data.psr_level = psr_level;
+
+	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_set_level.header);
+	dc_dmub_srv_cmd_execute(dc->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->dmub_srv);
+}
+
+/**
+ * Setup PSR by programming phy registers and sending psr hw context values to firmware.
+ */
+static bool dmub_setup_psr(struct dmub_psr *dmub,
+		struct dc_link *link,
+		struct psr_context *psr_context)
+{
+	union dmub_rb_cmd cmd;
+	struct dc_context *dc = dmub->ctx;
+	struct dmub_cmd_psr_copy_settings_data *copy_settings_data
+		= &cmd.psr_copy_settings.psr_copy_settings_data;
+	struct pipe_ctx *pipe_ctx = NULL;
+	struct resource_context *res_ctx = &link->ctx->dc->current_state->res_ctx;
+
+	for (int i = 0; i < MAX_PIPES; i++) {
+		if (res_ctx &&
+				res_ctx->pipe_ctx[i].stream &&
+				res_ctx->pipe_ctx[i].stream->link &&
+				res_ctx->pipe_ctx[i].stream->link == link &&
+				res_ctx->pipe_ctx[i].stream->link->connector_signal == SIGNAL_TYPE_EDP) {
+			pipe_ctx = &res_ctx->pipe_ctx[i];
+			break;
+		}
+	}
+
+	if (!pipe_ctx ||
+			!&pipe_ctx->plane_res ||
+			!&pipe_ctx->stream_res)
+		return false;
+
+	// Program DP DPHY fast training registers
+	link->link_enc->funcs->psr_program_dp_dphy_fast_training(link->link_enc,
+			psr_context->psrExitLinkTrainingRequired);
+
+	// Program DP_SEC_CNTL1 register to set transmission GPS0 line num and priority to high
+	link->link_enc->funcs->psr_program_secondary_packet(link->link_enc,
+			psr_context->sdpTransmitLineNumDeadline);
+
+	cmd.psr_copy_settings.header.type = DMUB_CMD__PSR;
+	cmd.psr_copy_settings.header.sub_type = DMUB_CMD__PSR_COPY_SETTINGS;
+	cmd.psr_copy_settings.header.payload_bytes = sizeof(struct dmub_cmd_psr_copy_settings_data);
+
+	// Hw insts
+	copy_settings_data->dpphy_inst				= psr_context->phyType;
+	copy_settings_data->aux_inst				= psr_context->channel;
+	copy_settings_data->digfe_inst				= psr_context->engineId;
+	copy_settings_data->digbe_inst				= psr_context->transmitterId;
+
+	copy_settings_data->mpcc_inst				= pipe_ctx->plane_res.mpcc_inst;
+
+	if (pipe_ctx->plane_res.hubp)
+		copy_settings_data->hubp_inst			= pipe_ctx->plane_res.hubp->inst;
+	else
+		copy_settings_data->hubp_inst			= 0;
+	if (pipe_ctx->plane_res.dpp)
+		copy_settings_data->dpp_inst			= pipe_ctx->plane_res.dpp->inst;
+	else
+		copy_settings_data->dpp_inst			= 0;
+	if (pipe_ctx->stream_res.opp)
+		copy_settings_data->opp_inst			= pipe_ctx->stream_res.opp->inst;
+	else
+		copy_settings_data->opp_inst			= 0;
+	if (pipe_ctx->stream_res.tg)
+		copy_settings_data->otg_inst			= pipe_ctx->stream_res.tg->inst;
+	else
+		copy_settings_data->otg_inst			= 0;
+
+	// Misc
+	copy_settings_data->psr_level				= psr_context->psr_level.u32all;
+	copy_settings_data->hyst_frames				= psr_context->timehyst_frames;
+	copy_settings_data->hyst_lines				= psr_context->hyst_lines;
+	copy_settings_data->phy_type				= psr_context->phyType;
+	copy_settings_data->aux_repeat				= psr_context->aux_repeats;
+	copy_settings_data->smu_optimizations_en	= psr_context->allow_smu_optimizations;
+	copy_settings_data->skip_wait_for_pll_lock	= psr_context->skipPsrWaitForPllLock;
+	copy_settings_data->frame_delay				= psr_context->frame_delay;
+	copy_settings_data->smu_phy_id				= psr_context->smuPhyId;
+	copy_settings_data->num_of_controllers		= psr_context->numberOfControllers;
+	copy_settings_data->frame_cap_ind			= psr_context->psrFrameCaptureIndicationReq;
+	copy_settings_data->phy_num					= psr_context->frame_delay & 0x7;
+	copy_settings_data->link_rate				= psr_context->frame_delay & 0xF;
+
+	dc_dmub_srv_cmd_queue(dc->dmub_srv, &cmd.psr_copy_settings.header);
+	dc_dmub_srv_cmd_execute(dc->dmub_srv);
+	dc_dmub_srv_wait_idle(dc->dmub_srv);
+
+	return true;
+}
+
+static const struct dmub_psr_funcs psr_funcs = {
+	.set_psr_enable			= dmub_set_psr_enable,
+	.setup_psr				= dmub_setup_psr,
+	.get_psr_state			= dmub_get_psr_state,
+	.set_psr_level			= dmub_set_psr_level,
+};
+
+/**
+ * Construct PSR object.
+ */
+static void dmub_psr_construct(struct dmub_psr *psr, struct dc_context *ctx)
+{
+	psr->ctx = ctx;
+	psr->funcs = &psr_funcs;
+}
+
+/**
+ * Allocate and initialize PSR object.
+ */
+struct dmub_psr *dmub_psr_create(struct dc_context *ctx)
+{
+	struct dmub_psr *psr = kzalloc(sizeof(struct dmub_psr), GFP_KERNEL);
+
+	if (psr == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	dmub_psr_construct(psr, ctx);
+
+	return psr;
+}
+
+/**
+ * Deallocate PSR object.
+ */
+void dmub_psr_destroy(struct dmub_psr **dmub)
+{
+	kfree(dmub);
+	*dmub = NULL;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
new file mode 100644
index 000000000000..229958de3035
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright 2012-16 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_PSR_H_
+#define _DMUB_PSR_H_
+
+#include "os_types.h"
+
+struct dmub_psr {
+	struct dc_context *ctx;
+	const struct dmub_psr_funcs *funcs;
+};
+
+struct dmub_psr_funcs {
+	void (*set_psr_enable)(struct dmub_psr *dmub, bool enable);
+	bool (*setup_psr)(struct dmub_psr *dmub, struct dc_link *link, struct psr_context *psr_context);
+	void (*get_psr_state)(uint32_t *psr_state);
+	void (*set_psr_level)(struct dmub_psr *dmub, uint16_t psr_level);
+};
+
+struct dmub_psr *dmub_psr_create(struct dc_context *ctx);
+void dmub_psr_destroy(struct dmub_psr **dmub);
+
+
+#endif /* _DCE_DMUB_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index 799d36299c9b..753cb8edd996 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -26,7 +26,6 @@
 #include "dc.h"
 #include "core_types.h"
 #include "clk_mgr.h"
-#include "hw_sequencer.h"
 #include "dce100_hw_sequencer.h"
 #include "resource.h"
 
@@ -136,7 +135,7 @@ void dce100_hw_sequencer_construct(struct dc *dc)
 {
 	dce110_hw_sequencer_construct(dc);
 
-	dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce100_enable_display_power_gating;
 	dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth;
 	dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
index a6b80fdaa666..34518da20009 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE100_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 struct dc_state;
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index a5e122c721ec..8f78bf9abbca 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -725,7 +725,7 @@ void dce100_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce100_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -885,7 +885,7 @@ static void dce100_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce100_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -950,7 +950,7 @@ static const struct resource_funcs dce100_res_pool_funcs = {
 	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
 };
 
-static bool construct(
+static bool dce100_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc  *dc,
 	struct dce110_resource_pool *pool)
@@ -1122,7 +1122,7 @@ static bool construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce100_resource_destruct(pool);
 
 	return false;
 }
@@ -1137,7 +1137,7 @@ struct resource_pool *dce100_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool))
+	if (dce100_resource_construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index f0e837d14000..5b689273ff44 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -61,6 +61,8 @@
 
 #include "atomfirmware.h"
 
+#define GAMMA_HW_POINTS_NUM 256
+
 /*
  * All values are in milliseconds;
  * For eDP, after power-up/power/down,
@@ -268,7 +270,7 @@ static void build_prescale_params(struct ipp_prescale_params *prescale_params,
 }
 
 static bool
-dce110_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
+dce110_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 			       const struct dc_plane_state *plane_state)
 {
 	struct input_pixel_processor *ipp = pipe_ctx->plane_res.ipp;
@@ -596,7 +598,7 @@ dce110_translate_regamma_to_hw_format(const struct dc_transfer_func *output_tf,
 }
 
 static bool
-dce110_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
+dce110_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream)
 {
 	struct transform *xfm = pipe_ctx->plane_res.xfm;
@@ -651,10 +653,9 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx)
 {
 	enum dc_lane_count lane_count =
 		pipe_ctx->stream->link->cur_link_settings.lane_count;
-
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
 	struct dc_link *link = pipe_ctx->stream->link;
-
+	const struct dc *dc = link->dc;
 
 	uint32_t active_total_with_borders;
 	uint32_t early_control = 0;
@@ -667,7 +668,7 @@ void dce110_enable_stream(struct pipe_ctx *pipe_ctx)
 	link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
 						    pipe_ctx->stream_res.stream_enc->id, true);
 
-	link->dc->hwss.update_info_frame(pipe_ctx);
+	dc->hwss.update_info_frame(pipe_ctx);
 
 	/* enable early control to avoid corruption on DP monitor*/
 	active_total_with_borders =
@@ -943,15 +944,15 @@ void dce110_edp_backlight_control(
 void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 {
 	/* notify audio driver for audio modes of monitor */
-	struct dc *core_dc;
+	struct dc *dc;
 	struct clk_mgr *clk_mgr;
 	unsigned int i, num_audio = 1;
 
 	if (!pipe_ctx->stream)
 		return;
 
-	core_dc = pipe_ctx->stream->ctx->dc;
-	clk_mgr = core_dc->clk_mgr;
+	dc = pipe_ctx->stream->ctx->dc;
+	clk_mgr = dc->clk_mgr;
 
 	if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == true)
 		return;
@@ -959,7 +960,7 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream_res.audio) {
 		for (i = 0; i < MAX_PIPES; i++) {
 			/*current_state not updated yet*/
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
+			if (dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
 				num_audio++;
 		}
 
@@ -1047,6 +1048,7 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 	struct encoder_unblank_param params = { { 0 } };
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 
 	/* only 3 items below are used by unblank */
 	params.timing = pipe_ctx->stream->timing;
@@ -1056,7 +1058,7 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 		pipe_ctx->stream_res.stream_enc->funcs->dp_unblank(pipe_ctx->stream_res.stream_enc, &params);
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, true);
+		hws->funcs.edp_backlight_control(link, true);
 	}
 }
 
@@ -1064,9 +1066,10 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, false);
+		hws->funcs.edp_backlight_control(link, false);
 		dc_link_set_abm_disable(link);
 	}
 
@@ -1223,7 +1226,7 @@ static void program_scaler(const struct dc *dc,
 {
 	struct tg_color color = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	/* TOFPGA */
 	if (pipe_ctx->plane_res.xfm->funcs->transform_set_pixel_storage_depth == NULL)
 		return;
@@ -1322,12 +1325,11 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct drr_params params = {0};
 	unsigned int event_triggers = 0;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct pipe_ctx *odm_pipe = pipe_ctx->next_odm_pipe;
-#endif
+	struct dce_hwseq *hws = dc->hwseq;
 
-	if (dc->hwss.disable_stream_gating) {
-		dc->hwss.disable_stream_gating(dc, pipe_ctx);
+	if (hws->funcs.disable_stream_gating) {
+		hws->funcs.disable_stream_gating(dc, pipe_ctx);
 	}
 
 	if (pipe_ctx->stream_res.audio != NULL) {
@@ -1357,10 +1359,10 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	/*  */
 	/* Do not touch stream timing on seamless boot optimization. */
 	if (!pipe_ctx->stream->apply_seamless_boot_optimization)
-		dc->hwss.enable_stream_timing(pipe_ctx, context, dc);
+		hws->funcs.enable_stream_timing(pipe_ctx, context, dc);
 
-	if (dc->hwss.setup_vupdate_interrupt)
-		dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+	if (hws->funcs.setup_vupdate_interrupt)
+		hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
@@ -1371,9 +1373,13 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	// DRR should set trigger event to monitor surface update event
 	if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0)
 		event_triggers = 0x80;
+	/* Event triggers and num frames initialized for DRR, but can be
+	 * later updated for PSR use. Note DRR trigger events are generated
+	 * regardless of whether num frames met.
+	 */
 	if (pipe_ctx->stream_res.tg->funcs->set_static_screen_control)
 		pipe_ctx->stream_res.tg->funcs->set_static_screen_control(
-				pipe_ctx->stream_res.tg, event_triggers);
+				pipe_ctx->stream_res.tg, event_triggers, 2);
 
 	if (!dc_is_virtual_signal(pipe_ctx->stream->signal))
 		pipe_ctx->stream_res.stream_enc->funcs->dig_connect_to_otg(
@@ -1390,7 +1396,6 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 		pipe_ctx->stream_res.opp,
 		&stream->bit_depth_params,
 		&stream->clamping);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	while (odm_pipe) {
 		odm_pipe->stream_res.opp->funcs->opp_set_dyn_expansion(
 				odm_pipe->stream_res.opp,
@@ -1404,7 +1409,6 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 				&stream->clamping);
 		odm_pipe = odm_pipe->next_odm_pipe;
 	}
-#endif
 
 	if (!stream->dpms_off)
 		core_link_enable_stream(context, pipe_ctx);
@@ -1438,6 +1442,9 @@ static void power_down_encoders(struct dc *dc)
 			if (!dc->links[i]->wa_flags.dp_keep_receiver_powered)
 				dp_receiver_power_ctrl(dc->links[i], false);
 
+		if (signal != SIGNAL_TYPE_EDP)
+			signal = SIGNAL_TYPE_NONE;
+
 		dc->links[i]->link_enc->funcs->disable_output(
 				dc->links[i]->link_enc, signal);
 	}
@@ -1552,9 +1559,10 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 	bool can_apply_edp_fast_boot = false;
 	bool can_apply_seamless_boot = false;
 	bool keep_edp_vdd_on = false;
+	struct dce_hwseq *hws = dc->hwseq;
 
-	if (dc->hwss.init_pipes)
-		dc->hwss.init_pipes(dc, context);
+	if (hws->funcs.init_pipes)
+		hws->funcs.init_pipes(dc, context);
 
 	edp_stream = get_edp_stream(context);
 
@@ -1591,7 +1599,7 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 	if (!can_apply_edp_fast_boot && !can_apply_seamless_boot) {
 		if (edp_link_with_sink && !keep_edp_vdd_on) {
 			/*turn off backlight before DP_blank and encoder powered down*/
-			dc->hwss.edp_backlight_control(edp_link_with_sink, false);
+			hws->funcs.edp_backlight_control(edp_link_with_sink, false);
 		}
 		/*resume from S3, no vbios posting, no need to power down again*/
 		power_down_all_hw_blocks(dc);
@@ -1702,6 +1710,8 @@ static void set_drr(struct pipe_ctx **pipe_ctx,
 	struct drr_params params = {0};
 	// DRR should set trigger event to monitor surface update event
 	unsigned int event_triggers = 0x80;
+	// Note DRR trigger events are generated regardless of whether num frames met.
+	unsigned int num_frames = 2;
 
 	params.vertical_total_max = vmax;
 	params.vertical_total_min = vmin;
@@ -1717,7 +1727,7 @@ static void set_drr(struct pipe_ctx **pipe_ctx,
 		if (vmax != 0 && vmin != 0)
 			pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(
 					pipe_ctx[i]->stream_res.tg,
-					event_triggers);
+					event_triggers, num_frames);
 	}
 }
 
@@ -1734,30 +1744,31 @@ static void get_position(struct pipe_ctx **pipe_ctx,
 }
 
 static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
-		int num_pipes, const struct dc_static_screen_events *events)
+		int num_pipes, const struct dc_static_screen_params *params)
 {
 	unsigned int i;
-	unsigned int value = 0;
+	unsigned int triggers = 0;
 
-	if (events->overlay_update)
-		value |= 0x100;
-	if (events->surface_update)
-		value |= 0x80;
-	if (events->cursor_update)
-		value |= 0x2;
-	if (events->force_trigger)
-		value |= 0x1;
+	if (params->triggers.overlay_update)
+		triggers |= 0x100;
+	if (params->triggers.surface_update)
+		triggers |= 0x80;
+	if (params->triggers.cursor_update)
+		triggers |= 0x2;
+	if (params->triggers.force_trigger)
+		triggers |= 0x1;
 
 	if (num_pipes) {
 		struct dc *dc = pipe_ctx[0]->stream->ctx->dc;
 
 		if (dc->fbc_compressor)
-			value |= 0x84;
+			triggers |= 0x84;
 	}
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
-			set_static_screen_control(pipe_ctx[i]->stream_res.tg, value);
+			set_static_screen_control(pipe_ctx[i]->stream_res.tg,
+					triggers, params->num_frames);
 }
 
 /*
@@ -2006,13 +2017,14 @@ enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dc_bios *dcb = dc->ctx->dc_bios;
 	enum dc_status status;
 	int i;
 
 	/* Reset old context */
 	/* look up the targets that have been removed since last commit */
-	dc->hwss.reset_hw_ctx_wrap(dc, context);
+	hws->funcs.reset_hw_ctx_wrap(dc, context);
 
 	/* Skip applying if no targets */
 	if (context->stream_count <= 0)
@@ -2037,7 +2049,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 			continue;
 		}
 
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc, i, dc->ctx->dc_bios,
 				PIPE_GATING_CONTROL_DISABLE);
 	}
@@ -2346,19 +2358,20 @@ static void init_hw(struct dc *dc)
 	struct transform *xfm;
 	struct abm *abm;
 	struct dmcu *dmcu;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	bp = dc->ctx->dc_bios;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		xfm = dc->res_pool->transforms[i];
 		xfm->funcs->transform_reset(xfm);
 
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc, i, bp,
 				PIPE_GATING_CONTROL_INIT);
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc, i, bp,
 				PIPE_GATING_CONTROL_DISABLE);
-		dc->hwss.enable_display_pipe_clock_gating(
+		hws->funcs.enable_display_pipe_clock_gating(
 			dc->ctx,
 			true);
 	}
@@ -2444,6 +2457,8 @@ static void dce110_program_front_end_for_pipe(
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
 	unsigned int i;
+	struct dce_hwseq *hws = dc->hwseq;
+
 	DC_LOGGER_INIT();
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
 
@@ -2502,10 +2517,10 @@ static void dce110_program_front_end_for_pipe(
 	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
 			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
 			pipe_ctx->plane_state->update_flags.bits.gamma_change)
-		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	if (pipe_ctx->plane_state->update_flags.bits.full_update)
-		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	DC_LOG_SURFACE(
 			"Pipe:%d %p: addr hi:0x%x, "
@@ -2608,6 +2623,7 @@ static void dce110_apply_ctx_for_surface(
 
 static void dce110_power_down_fe(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	int fe_idx = pipe_ctx->plane_res.mi ?
 		pipe_ctx->plane_res.mi->inst : pipe_ctx->pipe_idx;
 
@@ -2615,7 +2631,7 @@ static void dce110_power_down_fe(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	if (dc->current_state->res_ctx.pipe_ctx[fe_idx].stream)
 		return;
 
-	dc->hwss.enable_display_power_gating(
+	hws->funcs.enable_display_power_gating(
 		dc, fe_idx, dc->ctx->dc_bios, PIPE_GATING_CONTROL_ENABLE);
 
 	dc->res_pool->transforms[fe_idx]->funcs->transform_reset(
@@ -2704,14 +2720,10 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.program_gamut_remap = program_gamut_remap,
 	.program_output_csc = program_output_csc,
 	.init_hw = init_hw,
-	.init_pipes = init_pipes,
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dce110_apply_ctx_for_surface,
 	.update_plane_addr = update_plane_addr,
 	.update_pending_status = dce110_update_pending_status,
-	.set_input_transfer_func = dce110_set_input_transfer_func,
-	.set_output_transfer_func = dce110_set_output_transfer_func,
-	.power_down = dce110_power_down,
 	.enable_accelerated_mode = dce110_enable_accelerated_mode,
 	.enable_timing_synchronization = dce110_enable_timing_synchronization,
 	.enable_per_frame_crtc_position_reset = dce110_enable_per_frame_crtc_position_reset,
@@ -2722,8 +2734,6 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.blank_stream = dce110_blank_stream,
 	.enable_audio_stream = dce110_enable_audio_stream,
 	.disable_audio_stream = dce110_disable_audio_stream,
-	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
-	.enable_display_power_gating = dce110_enable_display_power_gating,
 	.disable_plane = dce110_power_down_fe,
 	.pipe_control_lock = dce_pipe_control_lock,
 	.prepare_bandwidth = dce110_prepare_bandwidth,
@@ -2731,22 +2741,33 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.set_drr = set_drr,
 	.get_position = get_position,
 	.set_static_screen_control = set_static_screen_control,
-	.reset_hw_ctx_wrap = dce110_reset_hw_ctx_wrap,
-	.enable_stream_timing = dce110_enable_stream_timing,
-	.disable_stream_gating = NULL,
-	.enable_stream_gating = NULL,
 	.setup_stereo = NULL,
 	.set_avmute = dce110_set_avmute,
 	.wait_for_mpcc_disconnect = dce110_wait_for_mpcc_disconnect,
-	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dce110_set_cursor_position,
 	.set_cursor_attribute = dce110_set_cursor_attribute
 };
 
+static const struct hwseq_private_funcs dce110_private_funcs = {
+	.init_pipes = init_pipes,
+	.update_plane_addr = update_plane_addr,
+	.set_input_transfer_func = dce110_set_input_transfer_func,
+	.set_output_transfer_func = dce110_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
+	.enable_display_power_gating = dce110_enable_display_power_gating,
+	.reset_hw_ctx_wrap = dce110_reset_hw_ctx_wrap,
+	.enable_stream_timing = dce110_enable_stream_timing,
+	.disable_stream_gating = NULL,
+	.enable_stream_gating = NULL,
+	.edp_backlight_control = dce110_edp_backlight_control,
+};
+
 void dce110_hw_sequencer_construct(struct dc *dc)
 {
 	dc->hwss = dce110_funcs;
+	dc->hwseq->funcs = dce110_private_funcs;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index 2f9b7dbdf415..26a9c14a58b1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -27,8 +27,8 @@
 #define __DC_HWSS_DCE110_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
-#define GAMMA_HW_POINTS_NUM 256
 struct dc;
 struct dc_state;
 struct dm_pp_display_configuration;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 83a4dbf6d76e..bf14e9ab040c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -782,7 +782,7 @@ void dce110_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce110_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1097,6 +1097,7 @@ static struct pipe_ctx *dce110_acquire_underlay(
 		struct dc_stream_state *stream)
 {
 	struct dc *dc = stream->ctx->dc;
+	struct dce_hwseq *hws = dc->hwseq;
 	struct resource_context *res_ctx = &context->res_ctx;
 	unsigned int underlay_idx = pool->underlay_pipe_index;
 	struct pipe_ctx *pipe_ctx = &res_ctx->pipe_ctx[underlay_idx];
@@ -1117,7 +1118,7 @@ static struct pipe_ctx *dce110_acquire_underlay(
 		struct tg_color black_color = {0};
 		struct dc_bios *dcb = dc->ctx->dc_bios;
 
-		dc->hwss.enable_display_power_gating(
+		hws->funcs.enable_display_power_gating(
 				dc,
 				pipe_ctx->stream_res.tg->inst,
 				dcb, PIPE_GATING_CONTROL_DISABLE);
@@ -1161,7 +1162,7 @@ static void dce110_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce110_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1313,7 +1314,7 @@ const struct resource_caps *dce110_resource_cap(
 		return &carrizo_resource_cap;
 }
 
-static bool construct(
+static bool dce110_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool,
@@ -1492,7 +1493,7 @@ static bool construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce110_resource_destruct(pool);
 	return false;
 }
 
@@ -1507,7 +1508,7 @@ struct resource_pool *dce110_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool, asic_id))
+	if (dce110_resource_construct(num_virtual_links, dc, pool, asic_id))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
index 5f7c2c5641c4..1ea7db8eeb98 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.c
@@ -469,22 +469,27 @@ void dce110_timing_generator_set_drr(
 
 void dce110_timing_generator_set_static_screen_control(
 	struct timing_generator *tg,
-	uint32_t value)
+	uint32_t event_triggers,
+	uint32_t num_frames)
 {
 	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
 	uint32_t static_screen_cntl = 0;
 	uint32_t addr = 0;
 
+	// By register spec, it only takes 8 bit value
+	if (num_frames > 0xFF)
+		num_frames = 0xFF;
+
 	addr = CRTC_REG(mmCRTC_STATIC_SCREEN_CONTROL);
 	static_screen_cntl = dm_read_reg(tg->ctx, addr);
 
 	set_reg_field_value(static_screen_cntl,
-				value,
+				event_triggers,
 				CRTC_STATIC_SCREEN_CONTROL,
 				CRTC_STATIC_SCREEN_EVENT_MASK);
 
 	set_reg_field_value(static_screen_cntl,
-				2,
+				num_frames,
 				CRTC_STATIC_SCREEN_CONTROL,
 				CRTC_STATIC_SCREEN_FRAME_COUNT);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
index 768ccf27ada9..d8a5ed7b485d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_timing_generator.h
@@ -231,7 +231,8 @@ void dce110_timing_generator_set_drr(
 
 void dce110_timing_generator_set_static_screen_control(
 	struct timing_generator *tg,
-	uint32_t value);
+	uint32_t event_triggers,
+	uint32_t num_frames);
 
 void dce110_timing_generator_get_crtc_scanoutpos(
 	struct timing_generator *tg,
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c
index 1e4a7c13f0ed..19873ee1f78d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.c
@@ -158,6 +158,6 @@ void dce112_hw_sequencer_construct(struct dc *dc)
 	 * structure
 	 */
 	dce110_hw_sequencer_construct(dc);
-	dc->hwss.enable_display_power_gating = dce112_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce112_enable_display_power_gating;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h
index e646f4a37fa2..943f1b2c5b2f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE112_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 97dcc5d0862b..700ad8b3e54b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -744,7 +744,7 @@ void dce112_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce112_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1013,7 +1013,7 @@ static void dce112_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce112_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1186,7 +1186,7 @@ const struct resource_caps *dce112_resource_cap(
 		return &polaris_10_resource_cap;
 }
 
-static bool construct(
+static bool dce112_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool)
@@ -1372,7 +1372,7 @@ static bool construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce112_resource_destruct(pool);
 	return false;
 }
 
@@ -1386,7 +1386,7 @@ struct resource_pool *dce112_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool))
+	if (dce112_resource_construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
index 1ca30928025e..66a13aa39c95 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
@@ -265,7 +265,7 @@ void dce120_hw_sequencer_construct(struct dc *dc)
 	 * structure
 	 */
 	dce110_hw_sequencer_construct(dc);
-	dc->hwss.enable_display_power_gating = dce120_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce120_enable_display_power_gating;
 	dc->hwss.update_dchub = dce120_update_dchub;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h
index c51afbd0b012..bc024534732f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE120_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 63543f6918ff..53ab88ef71f5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -63,8 +63,8 @@
 #include "soc15_hw_ip.h"
 #include "vega10_ip_offset.h"
 #include "nbio/nbio_6_1_offset.h"
-#include "mmhub/mmhub_9_4_0_offset.h"
-#include "mmhub/mmhub_9_4_0_sh_mask.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
 #include "reg_helper.h"
 
 #include "dce100/dce100_resource.h"
@@ -587,7 +587,7 @@ static void dce120_transform_destroy(struct transform **xfm)
 	*xfm = NULL;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce120_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -872,7 +872,7 @@ static void dce120_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce120_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1024,7 +1024,7 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 	return value;
 }
 
-static bool construct(
+static bool dce120_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dce110_resource_pool *pool)
@@ -1237,7 +1237,7 @@ controller_create_fail:
 clk_src_create_fail:
 res_create_fail:
 
-	destruct(pool);
+	dce120_resource_destruct(pool);
 
 	return false;
 }
@@ -1252,7 +1252,7 @@ struct resource_pool *dce120_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(num_virtual_links, dc, pool))
+	if (dce120_resource_construct(num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
index 098e56962f2a..82bc4e192bbf 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c
@@ -819,13 +819,18 @@ void dce120_tg_set_colors(struct timing_generator *tg,
 
 static void dce120_timing_generator_set_static_screen_control(
 	struct timing_generator *tg,
-	uint32_t value)
+	uint32_t event_triggers,
+	uint32_t num_frames)
 {
 	struct dce110_timing_generator *tg110 = DCE110TG_FROM_TG(tg);
 
+	// By register spec, it only takes 8 bit value
+	if (num_frames > 0xFF)
+		num_frames = 0xFF;
+
 	CRTC_REG_UPDATE_2(CRTC0_CRTC_STATIC_SCREEN_CONTROL,
-			CRTC_STATIC_SCREEN_EVENT_MASK, value,
-			CRTC_STATIC_SCREEN_FRAME_COUNT, 2);
+			CRTC_STATIC_SCREEN_EVENT_MASK, event_triggers,
+			CRTC_STATIC_SCREEN_FRAME_COUNT, num_frames);
 }
 
 void dce120_timing_generator_set_test_pattern(
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
index c4543178ba20..893261c81854 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c
@@ -74,7 +74,7 @@ void dce80_hw_sequencer_construct(struct dc *dc)
 {
 	dce110_hw_sequencer_construct(dc);
 
-	dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating;
+	dc->hwseq->funcs.enable_display_power_gating = dce100_enable_display_power_gating;
 	dc->hwss.pipe_control_lock = dce_pipe_control_lock;
 	dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth;
 	dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth;
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h
index 7a1b31def66f..e43af832d00c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.h
@@ -27,6 +27,7 @@
 #define __DC_HWSS_DCE80_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 3e8d4b49f279..2ad5c28c6e66 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -773,7 +773,7 @@ static struct input_pixel_processor *dce80_ipp_create(
 	return &ipp->base;
 }
 
-static void destruct(struct dce110_resource_pool *pool)
+static void dce80_resource_destruct(struct dce110_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -901,7 +901,7 @@ static void dce80_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
 
-	destruct(dce110_pool);
+	dce80_resource_destruct(dce110_pool);
 	kfree(dce110_pool);
 	*pool = NULL;
 }
@@ -1093,7 +1093,7 @@ static bool dce80_construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce80_resource_destruct(pool);
 	return false;
 }
 
@@ -1290,7 +1290,7 @@ static bool dce81_construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce80_resource_destruct(pool);
 	return false;
 }
 
@@ -1483,7 +1483,7 @@ static bool dce83_construct(
 	return true;
 
 res_create_fail:
-	destruct(pool);
+	dce80_resource_destruct(pool);
 	return false;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
index 032f872be89c..62ad1a11bff9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/Makefile
@@ -22,7 +22,8 @@
 #
 # Makefile for DCN.
 
-DCN10 = dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o dcn10_hw_sequencer_debug.o \
+DCN10 = dcn10_init.o dcn10_resource.o dcn10_ipp.o dcn10_hw_sequencer.o \
+		dcn10_hw_sequencer_debug.o \
 		dcn10_dpp.o dcn10_opp.o dcn10_optc.o \
 		dcn10_hubp.o dcn10_mpc.o \
 		dcn10_dpp_dscl.o dcn10_dpp_cm.o dcn10_cm_common.o \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index 997e9582edc7..0e682b5aa3eb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -290,12 +290,8 @@ void dpp1_cnv_setup (
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
 		struct dc_csc_transform input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		enum dc_color_space input_color_space,
 		struct cnv_alpha_2bit_lut *alpha_2bit_lut)
-#else
-		enum dc_color_space input_color_space)
-#endif
 {
 	uint32_t pixel_format;
 	uint32_t alpha_en;
@@ -542,11 +538,9 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.set_optional_cursor_attributes = dpp1_cnv_set_optional_cursor_attributes,
 		.dpp_dppclk_control = dpp1_dppclk_control,
 		.dpp_set_hdr_multiplier = dpp1_set_hdr_multiplier,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		.dpp_program_blnd_lut = NULL,
 		.dpp_program_shaper_lut = NULL,
 		.dpp_program_3dlut = NULL
-#endif
 };
 
 static struct dpp_caps dcn10_dpp_cap = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
index 1d4a7d640334..2edf566b3a72 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -1486,12 +1486,8 @@ void dpp1_cnv_setup (
 		enum surface_pixel_format format,
 		enum expansion_mode mode,
 		struct dc_csc_transform input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		enum dc_color_space input_color_space,
 		struct cnv_alpha_2bit_lut *alpha_2bit_lut);
-#else
-		enum dc_color_space input_color_space);
-#endif
 
 void dpp1_full_bypass(struct dpp *dpp_base);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
index aa0c7a7d13a0..4d3f7d5e1473 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_cm.c
@@ -88,26 +88,6 @@ enum dscl_mode_sel {
 	DSCL_MODE_DSCL_BYPASS = 6
 };
 
-static const struct dpp_input_csc_matrix dpp_input_csc_matrix[] = {
-	{COLOR_SPACE_SRGB,
-		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
-	{COLOR_SPACE_SRGB_LIMITED,
-		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
-	{COLOR_SPACE_YCBCR601,
-		{0x2cdd, 0x2000, 0, 0xe991, 0xe926, 0x2000, 0xf4fd, 0x10ef,
-						0, 0x2000, 0x38b4, 0xe3a6} },
-	{COLOR_SPACE_YCBCR601_LIMITED,
-		{0x3353, 0x2568, 0, 0xe400, 0xe5dc, 0x2568, 0xf367, 0x1108,
-						0, 0x2568, 0x40de, 0xdd3a} },
-	{COLOR_SPACE_YCBCR709,
-		{0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0,
-						0x2000, 0x3b61, 0xe24f} },
-
-	{COLOR_SPACE_YCBCR709_LIMITED,
-		{0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0,
-						0x2568, 0x43ee, 0xdbb2} }
-};
-
 static void program_gamut_remap(
 		struct dcn10_dpp *dpp,
 		const uint16_t *regval,
@@ -352,6 +332,8 @@ void dpp1_cm_program_regamma_lut(struct dpp *dpp_base,
 	uint32_t i;
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
 
+	REG_SEQ_START();
+
 	for (i = 0 ; i < num; i++) {
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].red_reg);
 		REG_SET(CM_RGAM_LUT_DATA, 0, CM_RGAM_LUT_DATA, rgb[i].green_reg);
@@ -626,10 +608,16 @@ void dpp1_set_degamma(
 	case IPP_DEGAMMA_MODE_HW_xvYCC:
 		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 2);
 			break;
+	case IPP_DEGAMMA_MODE_USER_PWL:
+		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 3);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
 	}
+
+	REG_SEQ_SUBMIT();
+	REG_SEQ_WAIT_DONE();
 }
 
 void dpp1_degamma_ram_select(
@@ -731,10 +719,8 @@ void dpp1_full_bypass(struct dpp *dpp_base)
 	/* COLOR_KEYER_CONTROL.COLOR_KEYER_EN = 0 this should be default */
 	if (dpp->tf_mask->CM_BYPASS_EN)
 		REG_SET(CM_CONTROL, 0, CM_BYPASS_EN, 1);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	else
 		REG_SET(CM_CONTROL, 0, CM_BYPASS, 1);
-#endif
 
 	/* Setting degamma bypass for now */
 	REG_SET(CM_DGAM_CONTROL, 0, CM_DGAM_LUT_MODE, 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index d67e0abeee93..fce37c527a0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -218,14 +218,12 @@ static void dpp1_dscl_set_lb(
 			INTERLEAVE_EN, lb_params->interleave_en, /* Interleave source enable */
 			LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	else {
 		/* DSCL caps: pixel data processed in float format */
 		REG_SET_2(LB_DATA_FORMAT, 0,
 			INTERLEAVE_EN, lb_params->interleave_en, /* Interleave source enable */
 			LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
 	}
-#endif
 
 	REG_SET_2(LB_MEMORY_CTRL, 0,
 		MEMORY_CONFIG, mem_size_config,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c
index 374cc9acda3b..b6391a5ead78 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.c
@@ -23,7 +23,7 @@
  *
  */
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 
 #include "reg_helper.h"
 #include "resource.h"
@@ -109,9 +109,7 @@ const struct dwbc_funcs dcn10_dwbc_funcs = {
 	.update				= NULL,
 	.set_stereo			= NULL,
 	.set_new_content		= NULL,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	.set_warmup			= NULL,
-#endif
 	.dwb_set_scaler			= NULL,
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h
index c175edd0bae7..d56ea7c8171e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dwb.h
@@ -24,7 +24,7 @@
 #ifndef __DC_DWBC_DCN10_H__
 #define __DC_DWBC_DCN10_H__
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 
 /* DCN */
 #define BASE_INNER(seg) \
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index a02c10e23e0d..f36a0d8cedfe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -930,6 +930,9 @@ static bool hubbub1_get_dcc_compression_cap(struct hubbub *hubbub,
 		output->grph.rgb.max_compressed_blk_size = 64;
 		output->grph.rgb.independent_64b_blks = true;
 		break;
+	default:
+		ASSERT(false);
+		break;
 	}
 
 	output->capable = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index 69d903d68661..af57751253de 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -121,7 +121,6 @@ struct dcn_hubbub_registers {
 	uint32_t DCN_VM_AGP_BASE;
 	uint32_t DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_MSB;
 	uint32_t DCN_VM_PROTECTION_FAULT_DEFAULT_ADDR_LSB;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_A;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_B;
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_NOM_C;
@@ -140,7 +139,6 @@ struct dcn_hubbub_registers {
 	uint32_t DCHVM_CLK_CTRL;
 	uint32_t DCHVM_RIOMMU_CTRL0;
 	uint32_t DCHVM_RIOMMU_STAT0;
-#endif
 };
 
 /* set field name */
@@ -232,7 +230,6 @@ struct dcn_hubbub_registers {
 		type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C;\
 		type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define HUBBUB_HVM_REG_FIELD_LIST(type) \
 		type DCHUBBUB_ARB_MIN_REQ_OUTSTAND_COMMIT_THRESHOLD;\
 		type DCHUBBUB_ARB_VM_ROW_URGENCY_WATERMARK_A;\
@@ -278,22 +275,17 @@ struct dcn_hubbub_registers {
 		type HOSTVM_POWERSTATUS; \
 		type RIOMMU_ACTIVE; \
 		type HOSTVM_PREFETCH_DONE
-#endif
 
 struct dcn_hubbub_shift {
 	DCN_HUBBUB_REG_FIELD_LIST(uint8_t);
 	HUBBUB_STUTTER_REG_FIELD_LIST(uint8_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	HUBBUB_HVM_REG_FIELD_LIST(uint8_t);
-#endif
 };
 
 struct dcn_hubbub_mask {
 	DCN_HUBBUB_REG_FIELD_LIST(uint32_t);
 	HUBBUB_STUTTER_REG_FIELD_LIST(uint32_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	HUBBUB_HVM_REG_FIELD_LIST(uint32_t);
-#endif
 };
 
 struct dc;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 14d1be6c66e6..31b64733d693 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -306,7 +306,6 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 12);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX:
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 112);
@@ -327,7 +326,6 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 119);
 		break;
-#endif
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
@@ -1014,6 +1012,9 @@ void hubp1_read_state_common(struct hubp *hubp)
 			HUBP_TTU_DISABLE, &s->ttu_disable,
 			HUBP_UNDERFLOW_STATUS, &s->underflow_status);
 
+	REG_GET(HUBP_CLK_CNTL,
+			HUBP_CLOCK_ENABLE, &s->clock_en);
+
 	REG_GET(DCN_GLOBAL_TTU_CNTL,
 			MIN_TTU_VBLANK, &s->min_ttu_vblank);
 
@@ -1248,10 +1249,8 @@ static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_get_underflow_status = hubp1_get_underflow_status,
 	.hubp_init = hubp1_init,
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	.dmdata_set_attributes = NULL,
 	.dmdata_load = NULL,
-#endif
 };
 
 /*****************************************/
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index ae70d9c0aa1d..780af5b3c16f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -670,6 +670,7 @@ struct dcn_hubp_state {
 	uint32_t sw_mode;
 	uint32_t dcc_en;
 	uint32_t blank_en;
+	uint32_t clock_en;
 	uint32_t underflow_status;
 	uint32_t ttu_disable;
 	uint32_t min_ttu_vblank;
@@ -728,13 +729,11 @@ void hubp1_dcc_control(struct hubp *hubp,
 		bool enable,
 		enum hubp_ind_block_size independent_64b_blks);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 bool hubp1_program_surface_flip_and_addr(
 	struct hubp *hubp,
 	const struct dc_plane_address *address,
 	bool flip_immediate);
 
-#endif
 bool hubp1_is_flip_pending(struct hubp *hubp);
 
 void hubp1_cursor_set_attributes(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index eb91432621ab..f2127afb37b2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -25,17 +25,18 @@
 
 #include <linux/delay.h>
 #include "dm_services.h"
+#include "basics/dc_common.h"
 #include "core_types.h"
 #include "resource.h"
 #include "custom_float.h"
 #include "dcn10_hw_sequencer.h"
-#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10_hw_sequencer_debug.h"
 #include "dce/dce_hwseq.h"
 #include "abm.h"
 #include "dmcu.h"
 #include "dcn10_optc.h"
-#include "dcn10/dcn10_dpp.h"
-#include "dcn10/dcn10_mpc.h"
+#include "dcn10_dpp.h"
+#include "dcn10_mpc.h"
 #include "timing_generator.h"
 #include "opp.h"
 #include "ipp.h"
@@ -49,9 +50,7 @@
 #include "clk_mgr.h"
 
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dsc.h"
-#endif
 
 #define DC_LOGGER_INIT(logger)
 
@@ -68,6 +67,8 @@
 #define DTN_INFO_MICRO_SEC(ref_cycle) \
 	print_microsec(dc_ctx, log_ctx, ref_cycle)
 
+#define GAMMA_HW_POINTS_NUM 256
+
 void print_microsec(struct dc_context *dc_ctx,
 	struct dc_log_buffer_ctx *log_ctx,
 	uint32_t ref_cycle)
@@ -81,6 +82,33 @@ void print_microsec(struct dc_context *dc_ctx,
 			us_x10 % frac);
 }
 
+static void dcn10_lock_all_pipes(struct dc *dc,
+	struct dc_state *context,
+	bool lock)
+{
+	struct pipe_ctx *pipe_ctx;
+	struct timing_generator *tg;
+	int i;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe_ctx = &context->res_ctx.pipe_ctx[i];
+		tg = pipe_ctx->stream_res.tg;
+		/*
+		 * Only lock the top pipe's tg to prevent redundant
+		 * (un)locking. Also skip if pipe is disabled.
+		 */
+		if (pipe_ctx->top_pipe ||
+		    !pipe_ctx->stream || !pipe_ctx->plane_state ||
+		    !tg->funcs->is_tg_enabled(tg))
+			continue;
+
+		if (lock)
+			tg->funcs->lock(tg);
+		else
+			tg->funcs->unlock(tg);
+	}
+}
+
 static void log_mpc_crc(struct dc *dc,
 	struct dc_log_buffer_ctx *log_ctx)
 {
@@ -129,9 +157,8 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 	struct resource_pool *pool = dc->res_pool;
 	int i;
 
-	DTN_INFO("HUBP:  format  addr_hi  width  height"
-			"  rot  mir  sw_mode  dcc_en  blank_en  ttu_dis  underflow"
-			"   min_ttu_vblank       qos_low_wm      qos_high_wm\n");
+	DTN_INFO(
+		"HUBP:  format  addr_hi  width  height  rot  mir  sw_mode  dcc_en  blank_en  clock_en  ttu_dis  underflow   min_ttu_vblank       qos_low_wm      qos_high_wm\n");
 	for (i = 0; i < pool->pipe_count; i++) {
 		struct hubp *hubp = pool->hubps[i];
 		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(hubp)->state);
@@ -139,8 +166,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 		hubp->funcs->hubp_read_state(hubp);
 
 		if (!s->blank_en) {
-			DTN_INFO("[%2d]:  %5xh  %6xh  %5d  %6d  %2xh  %2xh  %6xh"
-					"  %6d  %8d  %7d  %8xh",
+			DTN_INFO("[%2d]:  %5xh  %6xh  %5d  %6d  %2xh  %2xh  %6xh  %6d  %8d  %8d  %7d  %8xh",
 					hubp->inst,
 					s->pixel_format,
 					s->inuse_addr_hi,
@@ -151,6 +177,7 @@ static void dcn10_log_hubp_states(struct dc *dc, void *log_ctx)
 					s->sw_mode,
 					s->dcc_en,
 					s->blank_en,
+					s->clock_en,
 					s->ttu_disable,
 					s->underflow_status);
 			DTN_INFO_MICRO_SEC(s->min_ttu_vblank);
@@ -308,21 +335,31 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
-	DTN_INFO("OTG:  v_bs  v_be  v_ss  v_se  vpol  vmax  vmin  vmax_sel  vmin_sel"
-			"  h_bs  h_be  h_ss  h_se  hpol  htot  vtot  underflow\n");
+	DTN_INFO("OTG:  v_bs  v_be  v_ss  v_se  vpol  vmax  vmin  vmax_sel  vmin_sel  h_bs  h_be  h_ss  h_se  hpol  htot  vtot  underflow blank_en\n");
 
 	for (i = 0; i < pool->timing_generator_count; i++) {
 		struct timing_generator *tg = pool->timing_generators[i];
 		struct dcn_otg_state s = {0};
-
+		/* Read shared OTG state registers for all DCNx */
 		optc1_read_otg_state(DCN10TG_FROM_TG(tg), &s);
 
+		/*
+		 * For DCN2 and greater, a register on the OPP is used to
+		 * determine if the CRTC is blanked instead of the OTG. So use
+		 * dpg_is_blanked() if exists, otherwise fallback on otg.
+		 *
+		 * TODO: Implement DCN-specific read_otg_state hooks.
+		 */
+		if (pool->opps[i]->funcs->dpg_is_blanked)
+			s.blank_enabled = pool->opps[i]->funcs->dpg_is_blanked(pool->opps[i]);
+		else
+			s.blank_enabled = tg->funcs->is_blanked(tg);
+
 		//only print if OTG master is enabled
 		if ((s.otg_enabled & 1) == 0)
 			continue;
 
-		DTN_INFO("[%d]: %5d %5d %5d %5d %5d %5d %5d %9d %9d %5d %5d %5d"
-				" %5d %5d %5d %5d  %9d\n",
+		DTN_INFO("[%d]: %5d %5d %5d %5d %5d %5d %5d %9d %9d %5d %5d %5d %5d %5d %5d %5d  %9d %8d\n",
 				tg->inst,
 				s.v_blank_start,
 				s.v_blank_end,
@@ -340,7 +377,8 @@ void dcn10_log_hw_state(struct dc *dc,
 				s.h_sync_a_pol,
 				s.h_total,
 				s.v_total,
-				s.underflow_occurred_status);
+				s.underflow_occurred_status,
+				s.blank_enabled);
 
 		// Clear underflow for debug purposes
 		// We want to keep underflow sticky bit on for the longevity tests outside of test environment.
@@ -350,7 +388,6 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DTN_INFO("DSC: CLOCK_EN  SLICE_WIDTH  Bytes_pp\n");
 	for (i = 0; i < pool->res_cap->num_dsc; i++) {
 		struct display_stream_compressor *dsc = pool->dscs[i];
@@ -387,7 +424,7 @@ void dcn10_log_hw_state(struct dc *dc,
 	}
 	DTN_INFO("\n");
 
-	DTN_INFO("L_ENC: DPHY_FEC_EN  DPHY_FEC_READY_SHADOW  DPHY_FEC_ACTIVE_STATUS\n");
+	DTN_INFO("L_ENC: DPHY_FEC_EN  DPHY_FEC_READY_SHADOW  DPHY_FEC_ACTIVE_STATUS  DP_LINK_TRAINING_COMPLETE\n");
 	for (i = 0; i < dc->link_count; i++) {
 		struct link_encoder *lenc = dc->links[i]->link_enc;
 
@@ -395,16 +432,16 @@ void dcn10_log_hw_state(struct dc *dc,
 
 		if (lenc->funcs->read_state) {
 			lenc->funcs->read_state(lenc, &s);
-			DTN_INFO("[%-3d]: %-12d %-22d %-22d\n",
+			DTN_INFO("[%-3d]: %-12d %-22d %-22d %-25d\n",
 				i,
 				s.dphy_fec_en,
 				s.dphy_fec_ready_shadow,
-				s.dphy_fec_active_status);
+				s.dphy_fec_active_status,
+				s.dp_link_training_complete);
 			DTN_INFO("\n");
 		}
 	}
 	DTN_INFO("\n");
-#endif
 
 	DTN_INFO("\nCALCULATED Clocks: dcfclk_khz:%d  dcfclk_deep_sleep_khz:%d  dispclk_khz:%d\n"
 		"dppclk_khz:%d  max_supported_dppclk_khz:%d  fclk_khz:%d  socclk_khz:%d\n\n",
@@ -438,14 +475,14 @@ bool dcn10_did_underflow_occur(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	return false;
 }
 
-static void dcn10_enable_power_gating_plane(
+void dcn10_enable_power_gating_plane(
 	struct dce_hwseq *hws,
 	bool enable)
 {
-	bool force_on = 1; /* disable power gating */
+	bool force_on = true; /* disable power gating */
 
 	if (enable)
-		force_on = 0;
+		force_on = false;
 
 	/* DCHUBP0/1/2/3 */
 	REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN0_POWER_FORCEON, force_on);
@@ -460,7 +497,7 @@ static void dcn10_enable_power_gating_plane(
 	REG_UPDATE(DOMAIN7_PG_CONFIG, DOMAIN7_POWER_FORCEON, force_on);
 }
 
-static void dcn10_disable_vga(
+void dcn10_disable_vga(
 	struct dce_hwseq *hws)
 {
 	unsigned int in_vga1_mode = 0;
@@ -493,7 +530,7 @@ static void dcn10_disable_vga(
 	REG_UPDATE(VGA_TEST_CONTROL, VGA_TEST_RENDER_START, 1);
 }
 
-static void dcn10_dpp_pg_control(
+void dcn10_dpp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dpp_inst,
 		bool power_on)
@@ -545,7 +582,7 @@ static void dcn10_dpp_pg_control(
 	}
 }
 
-static void dcn10_hubp_pg_control(
+void dcn10_hubp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int hubp_inst,
 		bool power_on)
@@ -605,8 +642,8 @@ static void power_on_plane(
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		hws->ctx->dc->hwss.dpp_pg_control(hws, plane_id, true);
-		hws->ctx->dc->hwss.hubp_pg_control(hws, plane_id, true);
+		hws->funcs.dpp_pg_control(hws, plane_id, true);
+		hws->funcs.hubp_pg_control(hws, plane_id, true);
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
 		DC_LOG_DEBUG(
@@ -627,7 +664,7 @@ static void undo_DEGVIDCN10_253_wa(struct dc *dc)
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 1);
 
-	dc->hwss.hubp_pg_control(hws, 0, false);
+	hws->funcs.hubp_pg_control(hws, 0, false);
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 0);
 
@@ -656,7 +693,7 @@ static void apply_DEGVIDCN10_253_wa(struct dc *dc)
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 1);
 
-	dc->hwss.hubp_pg_control(hws, 0, true);
+	hws->funcs.hubp_pg_control(hws, 0, true);
 	REG_SET(DC_IP_REQUEST_CNTL, 0,
 			IP_REQUEST_EN, 0);
 
@@ -664,16 +701,16 @@ static void apply_DEGVIDCN10_253_wa(struct dc *dc)
 	hws->wa_state.DEGVIDCN10_253_applied = true;
 }
 
-static void dcn10_bios_golden_init(struct dc *dc)
+void dcn10_bios_golden_init(struct dc *dc)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dc_bios *bp = dc->ctx->dc_bios;
 	int i;
 	bool allow_self_fresh_force_enable = true;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
-	if (dc->hwss.s0i3_golden_init_wa && dc->hwss.s0i3_golden_init_wa(dc))
+	if (hws->funcs.s0i3_golden_init_wa && hws->funcs.s0i3_golden_init_wa(dc))
 		return;
-#endif
+
 	if (dc->res_pool->hubbub->funcs->is_allow_self_refresh_enabled)
 		allow_self_fresh_force_enable =
 				dc->res_pool->hubbub->funcs->is_allow_self_refresh_enabled(dc->res_pool->hubbub);
@@ -732,7 +769,7 @@ static void false_optc_underflow_wa(
 		tg->funcs->clear_optc_underflow(tg);
 }
 
-static enum dc_status dcn10_enable_stream_timing(
+enum dc_status dcn10_enable_stream_timing(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context,
 		struct dc *dc)
@@ -823,6 +860,7 @@ static void dcn10_reset_back_end_for_pipe(
 		struct dc_state *context)
 {
 	int i;
+	struct dc_link *link;
 	DC_LOGGER_INIT(dc->ctx->logger);
 	if (pipe_ctx->stream_res.stream_enc == NULL) {
 		pipe_ctx->stream = NULL;
@@ -830,8 +868,14 @@ static void dcn10_reset_back_end_for_pipe(
 	}
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		/* DPMS may already disable */
-		if (!pipe_ctx->stream->dpms_off)
+		link = pipe_ctx->stream->link;
+		/* DPMS may already disable or */
+		/* dpms_off status is incorrect due to fastboot
+		 * feature. When system resume from S4 with second
+		 * screen only, the dpms_off would be true but
+		 * VBIOS lit up eDP, so check link status too.
+		 */
+		if (!pipe_ctx->stream->dpms_off || link->link_status.link_active)
 			core_link_disable_stream(pipe_ctx);
 		else if (pipe_ctx->stream_res.audio)
 			dc->hwss.disable_audio_stream(pipe_ctx);
@@ -978,8 +1022,9 @@ void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 }
 
 /* trigger HW to start disconnect plane from stream on the next vsync */
-void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	int dpp_id = pipe_ctx->plane_res.dpp->inst;
 	struct mpc *mpc = dc->res_pool->mpc;
@@ -1004,10 +1049,10 @@ void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		hubp->funcs->hubp_disconnect(hubp);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
-static void dcn10_plane_atomic_power_down(struct dc *dc,
+void dcn10_plane_atomic_power_down(struct dc *dc,
 		struct dpp *dpp,
 		struct hubp *hubp)
 {
@@ -1017,8 +1062,8 @@ static void dcn10_plane_atomic_power_down(struct dc *dc,
 	if (REG(DC_IP_REQUEST_CNTL)) {
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 1);
-		dc->hwss.dpp_pg_control(hws, dpp->inst, false);
-		dc->hwss.hubp_pg_control(hws, hubp->inst, false);
+		hws->funcs.dpp_pg_control(hws, dpp->inst, false);
+		hws->funcs.hubp_pg_control(hws, hubp->inst, false);
 		dpp->funcs->dpp_reset(dpp);
 		REG_SET(DC_IP_REQUEST_CNTL, 0,
 				IP_REQUEST_EN, 0);
@@ -1030,8 +1075,9 @@ static void dcn10_plane_atomic_power_down(struct dc *dc,
 /* disable HW used by plane.
  * note:  cannot disable until disconnect is complete
  */
-static void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	int opp_id = hubp->opp_id;
@@ -1050,7 +1096,7 @@ static void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	hubp->power_gated = true;
 	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
-	dc->hwss.plane_atomic_power_down(dc,
+	hws->funcs.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
 			pipe_ctx->plane_res.hubp);
 
@@ -1062,14 +1108,15 @@ static void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_state = NULL;
 }
 
-static void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (!pipe_ctx->plane_res.hubp || pipe_ctx->plane_res.hubp->power_gated)
 		return;
 
-	dc->hwss.plane_atomic_disable(dc, pipe_ctx);
+	hws->funcs.plane_atomic_disable(dc, pipe_ctx);
 
 	apply_DEGVIDCN10_253_wa(dc);
 
@@ -1077,9 +1124,10 @@ static void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx)
 					pipe_ctx->pipe_idx);
 }
 
-static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
+void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 	bool can_apply_seamless_boot = false;
 
 	for (i = 0; i < context->stream_count; i++) {
@@ -1104,8 +1152,8 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		 * command table.
 		 */
 		if (tg->funcs->is_tg_enabled(tg)) {
-			if (dc->hwss.init_blank != NULL) {
-				dc->hwss.init_blank(dc, tg);
+			if (hws->funcs.init_blank != NULL) {
+				hws->funcs.init_blank(dc, tg);
 				tg->funcs->lock(tg);
 			} else {
 				tg->funcs->lock(tg);
@@ -1115,7 +1163,8 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		}
 	}
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	/* num_opp will be equal to number of mpcc */
+	for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
 		/* Cannot reset the MPC mux if seamless boot */
@@ -1139,8 +1188,14 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		if (can_apply_seamless_boot &&
 			pipe_ctx->stream != NULL &&
 			pipe_ctx->stream_res.tg->funcs->is_tg_enabled(
-				pipe_ctx->stream_res.tg))
+				pipe_ctx->stream_res.tg)) {
+			// Enable double buffering for OTG_BLANK no matter if
+			// seamless boot is enabled or not to suppress global sync
+			// signals when OTG blanked. This is to prevent pipe from
+			// requesting data while in PSR.
+			tg->funcs->tg_init(tg);
 			continue;
+		}
 
 		/* Disable on the current state so the new one isn't cleared. */
 		pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
@@ -1162,7 +1217,7 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 		dc->res_pool->opps[i]->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 		pipe_ctx->stream_res.opp = dc->res_pool->opps[i];
 
-		dc->hwss.plane_atomic_disconnect(dc, pipe_ctx);
+		hws->funcs.plane_atomic_disconnect(dc, pipe_ctx);
 
 		if (tg->funcs->is_tg_enabled(tg))
 			tg->funcs->unlock(tg);
@@ -1176,7 +1231,7 @@ static void dcn10_init_pipes(struct dc *dc, struct dc_state *context)
 	}
 }
 
-static void dcn10_init_hw(struct dc *dc)
+void dcn10_init_hw(struct dc *dc)
 {
 	int i;
 	struct abm *abm = dc->res_pool->abm;
@@ -1208,15 +1263,15 @@ static void dcn10_init_hw(struct dc *dc)
 		}
 
 		//Enable ability to power gate / don't force power on permanently
-		dc->hwss.enable_power_gating_plane(hws, true);
+		hws->funcs.enable_power_gating_plane(hws, true);
 
 		return;
 	}
 
 	if (!dcb->funcs->is_accelerated_mode(dcb))
-		dc->hwss.disable_vga(dc->hwseq);
+		hws->funcs.disable_vga(dc->hwseq);
 
-	dc->hwss.bios_golden_init(dc);
+	hws->funcs.bios_golden_init(dc);
 	if (dc->ctx->dc_bios->fw_info_valid) {
 		res_pool->ref_clocks.xtalin_clock_inKhz =
 				dc->ctx->dc_bios->fw_info.pll_info.crystal_frequency;
@@ -1258,11 +1313,9 @@ static void dcn10_init_hw(struct dc *dc)
 	}
 
 	/* Power gate DSCs */
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < res_pool->res_cap->num_dsc; i++)
-		if (dc->hwss.dsc_pg_control != NULL)
-			dc->hwss.dsc_pg_control(hws, res_pool->dscs[i]->inst, false);
-#endif
+		if (hws->funcs.dsc_pg_control != NULL)
+			hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false);
 
 	/* If taking control over from VBIOS, we may want to optimize our first
 	 * mode set, so we need to skip powering down pipes until we know which
@@ -1271,7 +1324,7 @@ static void dcn10_init_hw(struct dc *dc)
 	 * everything down.
 	 */
 	if (dcb->funcs->is_accelerated_mode(dcb) || dc->config.power_down_display_on_boot) {
-		dc->hwss.init_pipes(dc, dc->current_state);
+		hws->funcs.init_pipes(dc, dc->current_state);
 	}
 
 	for (i = 0; i < res_pool->audio_count; i++) {
@@ -1285,7 +1338,7 @@ static void dcn10_init_hw(struct dc *dc)
 		abm->funcs->abm_init(abm);
 	}
 
-	if (dmcu != NULL)
+	if (dmcu != NULL && !dmcu->auto_load_dmcu)
 		dmcu->funcs->dmcu_init(dmcu);
 
 	if (abm != NULL && dmcu != NULL)
@@ -1303,18 +1356,19 @@ static void dcn10_init_hw(struct dc *dc)
 		REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0);
 	}
 
-	dc->hwss.enable_power_gating_plane(dc->hwseq, true);
+	hws->funcs.enable_power_gating_plane(dc->hwseq, true);
 
 	if (dc->clk_mgr->funcs->notify_wm_ranges)
 		dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr);
 
 }
 
-static void dcn10_reset_hw_ctx_wrap(
+void dcn10_reset_hw_ctx_wrap(
 		struct dc *dc,
 		struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	/* Reset Back End*/
 	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
@@ -1333,8 +1387,8 @@ static void dcn10_reset_hw_ctx_wrap(
 			struct clock_source *old_clk = pipe_ctx_old->clock_source;
 
 			dcn10_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
-			if (dc->hwss.enable_stream_gating)
-				dc->hwss.enable_stream_gating(dc, pipe_ctx);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
@@ -1367,9 +1421,7 @@ static bool patch_address_for_sbs_tb_stereo(
 	return false;
 }
 
-
-
-static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	bool addr_patched = false;
 	PHYSICAL_ADDRESS_LOC addr;
@@ -1394,8 +1446,8 @@ static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_c
 		pipe_ctx->plane_state->address.grph_stereo.left_addr = addr;
 }
 
-static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
-					  const struct dc_plane_state *plane_state)
+bool dcn10_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state)
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	const struct dc_transfer_func *tf = NULL;
@@ -1427,6 +1479,11 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 			break;
 		case TRANSFER_FUNCTION_PQ:
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_USER_PWL);
+			cm_helper_translate_curve_to_degamma_hw_format(tf, &dpp_base->degamma_params);
+			dpp_base->funcs->dpp_program_degamma_pwl(dpp_base, &dpp_base->degamma_params);
+			result = true;
+			break;
 		default:
 			result = false;
 			break;
@@ -1472,9 +1529,8 @@ static void log_tf(struct dc_context *ctx,
 	}
 }
 
-static bool
-dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
-			       const struct dc_stream_state *stream)
+bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream)
 {
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 
@@ -1510,11 +1566,13 @@ dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
 	return true;
 }
 
-static void dcn10_pipe_control_lock(
+void dcn10_pipe_control_lock(
 	struct dc *dc,
 	struct pipe_ctx *pipe,
 	bool lock)
 {
+	struct dce_hwseq *hws = dc->hwseq;
+
 	/* use TG master update lock to lock everything on the TG
 	 * therefore only top pipe need to lock
 	 */
@@ -1522,7 +1580,7 @@ static void dcn10_pipe_control_lock(
 		return;
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (lock)
 		pipe->stream_res.tg->funcs->lock(pipe->stream_res.tg);
@@ -1530,7 +1588,7 @@ static void dcn10_pipe_control_lock(
 		pipe->stream_res.tg->funcs->unlock(pipe->stream_res.tg);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
 static bool wait_for_reset_trigger_to_occur(
@@ -1570,7 +1628,7 @@ static bool wait_for_reset_trigger_to_occur(
 	return rc;
 }
 
-static void dcn10_enable_timing_synchronization(
+void dcn10_enable_timing_synchronization(
 	struct dc *dc,
 	int group_index,
 	int group_size,
@@ -1600,7 +1658,7 @@ static void dcn10_enable_timing_synchronization(
 	DC_SYNC_INFO("Sync complete\n");
 }
 
-static void dcn10_enable_per_frame_crtc_position_reset(
+void dcn10_enable_per_frame_crtc_position_reset(
 	struct dc *dc,
 	int group_size,
 	struct pipe_ctx *grouped_pipes[])
@@ -1625,10 +1683,10 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 }
 
 /*static void print_rq_dlg_ttu(
-		struct dc *core_dc,
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx)
 {
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\n============== DML TTU Output parameters [%d] ==============\n"
 			"qos_level_low_wm: %d, \n"
 			"qos_level_high_wm: %d, \n"
@@ -1658,7 +1716,7 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 			pipe_ctx->ttu_regs.refcyc_per_req_delivery_pre_c
 			);
 
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\n============== DML DLG Output parameters [%d] ==============\n"
 			"refcyc_h_blank_end: %d, \n"
 			"dlg_vblank_end: %d, \n"
@@ -1693,7 +1751,7 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 			pipe_ctx->dlg_regs.refcyc_per_pte_group_nom_l
 			);
 
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\ndst_y_per_meta_row_nom_l: %d, \n"
 			"refcyc_per_meta_chunk_nom_l: %d, \n"
 			"refcyc_per_line_delivery_pre_l: %d, \n"
@@ -1723,7 +1781,7 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 			pipe_ctx->dlg_regs.refcyc_per_line_delivery_c
 			);
 
-	DC_LOG_BANDWIDTH_CALCS(core_dc->ctx->logger,
+	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
 			"\n============== DML RQ Output parameters [%d] ==============\n"
 			"chunk_size: %d \n"
 			"min_chunk_size: %d \n"
@@ -1838,7 +1896,7 @@ static void dcn10_enable_plane(
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 
 	undo_DEGVIDCN10_253_wa(dc);
@@ -1895,11 +1953,11 @@ static void dcn10_enable_plane(
 		dcn10_program_pte_vm(hws, pipe_ctx->plane_res.hubp);
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 }
 
-static void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx)
+void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx)
 {
 	int i = 0;
 	struct dpp_grph_csc_adjustment adjust;
@@ -1947,7 +2005,7 @@ static void dcn10_set_csc_adjustment_rgb_mpo_fix(struct pipe_ctx *pipe_ctx, uint
 	matrix[11] = rgb_bias;
 }
 
-static void dcn10_program_output_csc(struct dc *dc,
+void dcn10_program_output_csc(struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum dc_color_space colorspace,
 		uint16_t *matrix,
@@ -1979,57 +2037,6 @@ static void dcn10_program_output_csc(struct dc *dc,
 	}
 }
 
-bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
-{
-	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
-		return true;
-	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
-		return true;
-	return false;
-}
-
-bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
-{
-	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
-		return true;
-	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
-		return true;
-	return false;
-}
-
-bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx)
-{
-	if (pipe_ctx->plane_state && pipe_ctx->plane_state->visible)
-		return true;
-	if (pipe_ctx->top_pipe && is_upper_pipe_tree_visible(pipe_ctx->top_pipe))
-		return true;
-	if (pipe_ctx->bottom_pipe && is_lower_pipe_tree_visible(pipe_ctx->bottom_pipe))
-		return true;
-	return false;
-}
-
-bool is_rgb_cspace(enum dc_color_space output_color_space)
-{
-	switch (output_color_space) {
-	case COLOR_SPACE_SRGB:
-	case COLOR_SPACE_SRGB_LIMITED:
-	case COLOR_SPACE_2020_RGB_FULLRANGE:
-	case COLOR_SPACE_2020_RGB_LIMITEDRANGE:
-	case COLOR_SPACE_ADOBERGB:
-		return true;
-	case COLOR_SPACE_YCBCR601:
-	case COLOR_SPACE_YCBCR709:
-	case COLOR_SPACE_YCBCR601_LIMITED:
-	case COLOR_SPACE_YCBCR709_LIMITED:
-	case COLOR_SPACE_2020_YCBCR:
-		return false;
-	default:
-		/* Add a case to switch */
-		BREAK_TO_DEBUGGER();
-		return false;
-	}
-}
-
 void dcn10_get_surface_visual_confirm_color(
 		const struct pipe_ctx *pipe_ctx,
 		struct tg_color *color)
@@ -2103,70 +2110,7 @@ void dcn10_get_hdr_visual_confirm_color(
 	}
 }
 
-static uint16_t fixed_point_to_int_frac(
-	struct fixed31_32 arg,
-	uint8_t integer_bits,
-	uint8_t fractional_bits)
-{
-	int32_t numerator;
-	int32_t divisor = 1 << fractional_bits;
-
-	uint16_t result;
-
-	uint16_t d = (uint16_t)dc_fixpt_floor(
-		dc_fixpt_abs(
-			arg));
-
-	if (d <= (uint16_t)(1 << integer_bits) - (1 / (uint16_t)divisor))
-		numerator = (uint16_t)dc_fixpt_floor(
-			dc_fixpt_mul_int(
-				arg,
-				divisor));
-	else {
-		numerator = dc_fixpt_floor(
-			dc_fixpt_sub(
-				dc_fixpt_from_int(
-					1LL << integer_bits),
-				dc_fixpt_recip(
-					dc_fixpt_from_int(
-						divisor))));
-	}
-
-	if (numerator >= 0)
-		result = (uint16_t)numerator;
-	else
-		result = (uint16_t)(
-		(1 << (integer_bits + fractional_bits + 1)) + numerator);
-
-	if ((result != 0) && dc_fixpt_lt(
-		arg, dc_fixpt_zero))
-		result |= 1 << (integer_bits + fractional_bits);
-
-	return result;
-}
-
-void dcn10_build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
-		const struct dc_plane_state *plane_state)
-{
-	if (plane_state->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN
-			&& plane_state->format != SURFACE_PIXEL_FORMAT_INVALID
-			&& plane_state->input_csc_color_matrix.enable_adjustment
-			&& plane_state->coeff_reduction_factor.value != 0) {
-		bias_and_scale->scale_blue = fixed_point_to_int_frac(
-			dc_fixpt_mul(plane_state->coeff_reduction_factor,
-					dc_fixpt_from_fraction(256, 255)),
-				2,
-				13);
-		bias_and_scale->scale_red = bias_and_scale->scale_blue;
-		bias_and_scale->scale_green = bias_and_scale->scale_blue;
-	} else {
-		bias_and_scale->scale_blue = 0x2000;
-		bias_and_scale->scale_red = 0x2000;
-		bias_and_scale->scale_green = 0x2000;
-	}
-}
-
-static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
+static void dcn10_update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 {
 	struct dc_bias_and_scale bns_params = {0};
 
@@ -2175,21 +2119,18 @@ static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 			plane_state->format,
 			EXPANSION_MODE_ZERO,
 			plane_state->input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 			plane_state->color_space,
 			NULL);
-#else
-			plane_state->color_space);
-#endif
 
 	//set scale and bias registers
-	dcn10_build_prescale_params(&bns_params, plane_state);
+	build_prescale_params(&bns_params, plane_state);
 	if (dpp->funcs->dpp_program_bias_and_scale)
 		dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 }
 
-static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct mpcc_blnd_cfg blnd_cfg = {{0}};
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
@@ -2199,10 +2140,10 @@ static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params);
 
 	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
-		dcn10_get_hdr_visual_confirm_color(
+		hws->funcs.get_hdr_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
-		dcn10_get_surface_visual_confirm_color(
+		hws->funcs.get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else {
 		color_space_to_black_color(
@@ -2284,11 +2225,12 @@ static void update_scaler(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);
 }
 
-void update_dchubp_dpp(
+static void dcn10_update_dchubp_dpp(
 	struct dc *dc,
 	struct pipe_ctx *pipe_ctx,
 	struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
@@ -2342,12 +2284,12 @@ void update_dchubp_dpp(
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.bpp_change)
-		update_dpp(dpp, plane_state);
+		dcn10_update_dpp(dpp, plane_state);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
 		plane_state->update_flags.bits.global_alpha_change)
-		dc->hwss.update_mpcc(dc, pipe_ctx);
+		hws->funcs.update_mpcc(dc, pipe_ctx);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
@@ -2407,13 +2349,13 @@ void update_dchubp_dpp(
 
 	hubp->power_gated = false;
 
-	dc->hwss.update_plane_addr(dc, pipe_ctx);
+	hws->funcs.update_plane_addr(dc, pipe_ctx);
 
 	if (is_pipe_tree_visible(pipe_ctx))
 		hubp->funcs->set_blank(hubp, false);
 }
 
-static void dcn10_blank_pixel_data(
+void dcn10_blank_pixel_data(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		bool blank)
@@ -2456,10 +2398,9 @@ static void dcn10_blank_pixel_data(
 	}
 }
 
-void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
+void dcn10_set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 {
-	struct fixed31_32 multiplier = dc_fixpt_from_fraction(
-			pipe_ctx->plane_state->sdr_white_level, 80);
+	struct fixed31_32 multiplier = pipe_ctx->plane_state->hdr_mult;
 	uint32_t hw_mult = 0x1f000; // 1.0 default multiplier
 	struct custom_float_format fmt;
 
@@ -2467,7 +2408,8 @@ void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 	fmt.mantissa_bits = 12;
 	fmt.sign = true;
 
-	if (pipe_ctx->plane_state->sdr_white_level > 80)
+
+	if (!dc_fixpt_eq(multiplier, dc_fixpt_from_int(0))) // check != 0
 		convert_to_custom_float_format(multiplier, &fmt, &hw_mult);
 
 	pipe_ctx->plane_res.dpp->funcs->dpp_set_hdr_multiplier(
@@ -2479,17 +2421,19 @@ void dcn10_program_pipe(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
+
 	if (pipe_ctx->plane_state->update_flags.bits.full_update)
 		dcn10_enable_plane(dc, pipe_ctx, context);
 
-	update_dchubp_dpp(dc, pipe_ctx, context);
+	dcn10_update_dchubp_dpp(dc, pipe_ctx, context);
 
-	set_hdr_multiplier(pipe_ctx);
+	hws->funcs.set_hdr_multiplier(pipe_ctx);
 
 	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
 			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
 			pipe_ctx->plane_state->update_flags.bits.gamma_change)
-		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
 	 * only do gamma programming for full update.
@@ -2498,14 +2442,16 @@ void dcn10_program_pipe(
 	 * doing heavy calculation and programming
 	 */
 	if (pipe_ctx->plane_state->update_flags.bits.full_update)
-		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 }
 
-static void program_all_pipe_in_tree(
+static void dcn10_program_all_pipe_in_tree(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
+
 	if (pipe_ctx->top_pipe == NULL) {
 		bool blank = !is_pipe_tree_visible(pipe_ctx);
 
@@ -2519,20 +2465,20 @@ static void program_all_pipe_in_tree(
 		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-		if (dc->hwss.setup_vupdate_interrupt)
-			dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+		if (hws->funcs.setup_vupdate_interrupt)
+			hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 
-		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+		hws->funcs.blank_pixel_data(dc, pipe_ctx, blank);
 	}
 
 	if (pipe_ctx->plane_state != NULL)
-		dcn10_program_pipe(dc, pipe_ctx, context);
+		hws->funcs.program_pipe(dc, pipe_ctx, context);
 
 	if (pipe_ctx->bottom_pipe != NULL && pipe_ctx->bottom_pipe != pipe_ctx)
-		program_all_pipe_in_tree(dc, pipe_ctx->bottom_pipe, context);
+		dcn10_program_all_pipe_in_tree(dc, pipe_ctx->bottom_pipe, context);
 }
 
-struct pipe_ctx *find_top_pipe_for_stream(
+static struct pipe_ctx *dcn10_find_top_pipe_for_stream(
 		struct dc *dc,
 		struct dc_state *context,
 		const struct dc_stream_state *stream)
@@ -2556,19 +2502,20 @@ struct pipe_ctx *find_top_pipe_for_stream(
 	return NULL;
 }
 
-static void dcn10_apply_ctx_for_surface(
+void dcn10_apply_ctx_for_surface(
 		struct dc *dc,
 		const struct dc_stream_state *stream,
 		int num_planes,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	int i;
 	struct timing_generator *tg;
 	uint32_t underflow_check_delay_us;
 	bool removed_pipe[4] = { false };
 	bool interdependent_update = false;
 	struct pipe_ctx *top_pipe_to_program =
-			find_top_pipe_for_stream(dc, context, stream);
+			dcn10_find_top_pipe_for_stream(dc, context, stream);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
 	if (!top_pipe_to_program)
@@ -2581,23 +2528,23 @@ static void dcn10_apply_ctx_for_surface(
 
 	underflow_check_delay_us = dc->debug.underflow_assert_delay_us;
 
-	if (underflow_check_delay_us != 0xFFFFFFFF && dc->hwss.did_underflow_occur)
-		ASSERT(dc->hwss.did_underflow_occur(dc, top_pipe_to_program));
+	if (underflow_check_delay_us != 0xFFFFFFFF && hws->funcs.did_underflow_occur)
+		ASSERT(hws->funcs.did_underflow_occur(dc, top_pipe_to_program));
 
 	if (interdependent_update)
-		lock_all_pipes(dc, context, true);
+		dcn10_lock_all_pipes(dc, context, true);
 	else
 		dcn10_pipe_control_lock(dc, top_pipe_to_program, true);
 
 	if (underflow_check_delay_us != 0xFFFFFFFF)
 		udelay(underflow_check_delay_us);
 
-	if (underflow_check_delay_us != 0xFFFFFFFF && dc->hwss.did_underflow_occur)
-		ASSERT(dc->hwss.did_underflow_occur(dc, top_pipe_to_program));
+	if (underflow_check_delay_us != 0xFFFFFFFF && hws->funcs.did_underflow_occur)
+		ASSERT(hws->funcs.did_underflow_occur(dc, top_pipe_to_program));
 
 	if (num_planes == 0) {
 		/* OTG blank before remove all front end */
-		dc->hwss.blank_pixel_data(dc, top_pipe_to_program, true);
+		hws->funcs.blank_pixel_data(dc, top_pipe_to_program, true);
 	}
 
 	/* Disconnect unused mpcc */
@@ -2623,7 +2570,7 @@ static void dcn10_apply_ctx_for_surface(
 		    old_pipe_ctx->plane_state &&
 		    old_pipe_ctx->stream_res.tg == tg) {
 
-			dc->hwss.plane_atomic_disconnect(dc, old_pipe_ctx);
+			hws->funcs.plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
 			DC_LOG_DC("Reset mpcc for pipe %d\n",
@@ -2632,13 +2579,11 @@ static void dcn10_apply_ctx_for_surface(
 	}
 
 	if (num_planes > 0)
-		program_all_pipe_in_tree(dc, top_pipe_to_program, context);
+		dcn10_program_all_pipe_in_tree(dc, top_pipe_to_program, context);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* Program secondary blending tree and writeback pipes */
-	if ((stream->num_wb_info > 0) && (dc->hwss.program_all_writeback_pipes_in_tree))
-		dc->hwss.program_all_writeback_pipes_in_tree(dc, stream, context);
-#endif
+	if ((stream->num_wb_info > 0) && (hws->funcs.program_all_writeback_pipes_in_tree))
+		hws->funcs.program_all_writeback_pipes_in_tree(dc, stream, context);
 	if (interdependent_update)
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
@@ -2654,7 +2599,7 @@ static void dcn10_apply_ctx_for_surface(
 		}
 
 	if (interdependent_update)
-		lock_all_pipes(dc, context, false);
+		dcn10_lock_all_pipes(dc, context, false);
 	else
 		dcn10_pipe_control_lock(dc, top_pipe_to_program, false);
 
@@ -2691,14 +2636,15 @@ static void dcn10_stereo_hw_frame_pack_wa(struct dc *dc, struct dc_state *contex
 	}
 }
 
-static void dcn10_prepare_bandwidth(
+void dcn10_prepare_bandwidth(
 		struct dc *dc,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (context->stream_count == 0)
@@ -2720,17 +2666,18 @@ static void dcn10_prepare_bandwidth(
 		dcn_bw_notify_pplib_of_wm_ranges(dc);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
-static void dcn10_optimize_bandwidth(
+void dcn10_optimize_bandwidth(
 		struct dc *dc,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubbub *hubbub = dc->res_pool->hubbub;
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
 		if (context->stream_count == 0)
@@ -2752,10 +2699,10 @@ static void dcn10_optimize_bandwidth(
 		dcn_bw_notify_pplib_of_wm_ranges(dc);
 
 	if (dc->debug.sanity_checks)
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
-static void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
+void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 		int num_pipes, unsigned int vmin, unsigned int vmax,
 		unsigned int vmid, unsigned int vmid_frame_number)
 {
@@ -2763,6 +2710,8 @@ static void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 	struct drr_params params = {0};
 	// DRR set trigger event mapped to OTG_TRIG_A (bit 11) for manual control flow
 	unsigned int event_triggers = 0x800;
+	// Note DRR trigger events are generated regardless of whether num frames met.
+	unsigned int num_frames = 2;
 
 	params.vertical_total_max = vmax;
 	params.vertical_total_min = vmin;
@@ -2779,11 +2728,11 @@ static void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
 		if (vmax != 0 && vmin != 0)
 			pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(
 					pipe_ctx[i]->stream_res.tg,
-					event_triggers);
+					event_triggers, num_frames);
 	}
 }
 
-static void dcn10_get_position(struct pipe_ctx **pipe_ctx,
+void dcn10_get_position(struct pipe_ctx **pipe_ctx,
 		int num_pipes,
 		struct crtc_position *position)
 {
@@ -2795,22 +2744,23 @@ static void dcn10_get_position(struct pipe_ctx **pipe_ctx,
 		pipe_ctx[i]->stream_res.tg->funcs->get_position(pipe_ctx[i]->stream_res.tg, position);
 }
 
-static void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx,
-		int num_pipes, const struct dc_static_screen_events *events)
+void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params)
 {
 	unsigned int i;
-	unsigned int value = 0;
+	unsigned int triggers = 0;
 
-	if (events->surface_update)
-		value |= 0x80;
-	if (events->cursor_update)
-		value |= 0x2;
-	if (events->force_trigger)
-		value |= 0x1;
+	if (params->triggers.surface_update)
+		triggers |= 0x80;
+	if (params->triggers.cursor_update)
+		triggers |= 0x2;
+	if (params->triggers.force_trigger)
+		triggers |= 0x1;
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
-			set_static_screen_control(pipe_ctx[i]->stream_res.tg, value);
+			set_static_screen_control(pipe_ctx[i]->stream_res.tg,
+					triggers, params->num_frames);
 }
 
 static void dcn10_config_stereo_parameters(
@@ -2850,7 +2800,7 @@ static void dcn10_config_stereo_parameters(
 	return;
 }
 
-static void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc)
+void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc)
 {
 	struct crtc_stereo_flags flags = { 0 };
 	struct dc_stream_state *stream = pipe_ctx->stream;
@@ -2889,15 +2839,16 @@ static struct hubp *get_hubp_by_inst(struct resource_pool *res_pool, int mpcc_in
 	return NULL;
 }
 
-static void dcn10_wait_for_mpcc_disconnect(
+void dcn10_wait_for_mpcc_disconnect(
 		struct dc *dc,
 		struct resource_pool *res_pool,
 		struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	int mpcc_inst;
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 
 	if (!pipe_ctx->stream_res.opp)
@@ -2914,12 +2865,12 @@ static void dcn10_wait_for_mpcc_disconnect(
 	}
 
 	if (dc->debug.sanity_checks) {
-		dcn10_verify_allow_pstate_change_high(dc);
+		hws->funcs.verify_allow_pstate_change_high(dc);
 	}
 
 }
 
-static bool dcn10_dummy_display_power_gating(
+bool dcn10_dummy_display_power_gating(
 	struct dc *dc,
 	uint8_t controller_id,
 	struct dc_bios *dcb,
@@ -2928,7 +2879,7 @@ static bool dcn10_dummy_display_power_gating(
 	return true;
 }
 
-static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
+void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
@@ -2952,7 +2903,7 @@ static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
+void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
 {
 	struct hubbub *hubbub = hws->ctx->dc->res_pool->hubbub;
 
@@ -2960,7 +2911,7 @@ static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh
 	hubbub->funcs->update_dchub(hubbub, dh_data);
 }
 
-static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
+void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_cursor_position pos_cpy = pipe_ctx->stream->cursor_position;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
@@ -2974,15 +2925,32 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.rotation = pipe_ctx->plane_state->rotation,
 		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
-	uint32_t x_plane = pipe_ctx->plane_state->dst_rect.x;
-	uint32_t y_plane = pipe_ctx->plane_state->dst_rect.y;
-	uint32_t x_offset = min(x_plane, pos_cpy.x);
-	uint32_t y_offset = min(y_plane, pos_cpy.y);
+	bool pipe_split_on = (pipe_ctx->top_pipe != NULL) ||
+		(pipe_ctx->bottom_pipe != NULL);
+
+	int x_plane = pipe_ctx->plane_state->dst_rect.x;
+	int y_plane = pipe_ctx->plane_state->dst_rect.y;
+	int x_pos = pos_cpy.x;
+	int y_pos = pos_cpy.y;
+
+	// translate cursor from stream space to plane space
+	x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width /
+			pipe_ctx->plane_state->dst_rect.width;
+	y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height /
+			pipe_ctx->plane_state->dst_rect.height;
 
-	pos_cpy.x -= x_offset;
-	pos_cpy.y -= y_offset;
-	pos_cpy.x_hotspot += (x_plane - x_offset);
-	pos_cpy.y_hotspot += (y_plane - y_offset);
+	if (x_pos < 0) {
+		pos_cpy.x_hotspot -= x_pos;
+		x_pos = 0;
+	}
+
+	if (y_pos < 0) {
+		pos_cpy.y_hotspot -= y_pos;
+		y_pos = 0;
+	}
+
+	pos_cpy.x = (uint32_t)x_pos;
+	pos_cpy.y = (uint32_t)y_pos;
 
 	if (pipe_ctx->plane_state->address.type
 			== PLN_ADDR_TYPE_VIDEO_PROGRESSIVE)
@@ -2991,6 +2959,7 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	// Swap axis and mirror horizontally
 	if (param.rotation == ROTATION_ANGLE_90) {
 		uint32_t temp_x = pos_cpy.x;
+
 		pos_cpy.x = pipe_ctx->plane_res.scl_data.viewport.width -
 				(pos_cpy.y - pipe_ctx->plane_res.scl_data.viewport.x) + pipe_ctx->plane_res.scl_data.viewport.x;
 		pos_cpy.y = temp_x;
@@ -2998,26 +2967,44 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	// Swap axis and mirror vertically
 	else if (param.rotation == ROTATION_ANGLE_270) {
 		uint32_t temp_y = pos_cpy.y;
-		if (pos_cpy.x >  pipe_ctx->plane_res.scl_data.viewport.height) {
-			pos_cpy.x = pos_cpy.x - pipe_ctx->plane_res.scl_data.viewport.height;
-			pos_cpy.y = pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.x;
-		} else {
-			pos_cpy.y = 2 * pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.x;
-		}
+		int viewport_height =
+			pipe_ctx->plane_res.scl_data.viewport.height;
+
+		if (pipe_split_on) {
+			if (pos_cpy.x > viewport_height) {
+				pos_cpy.x = pos_cpy.x - viewport_height;
+				pos_cpy.y = viewport_height - pos_cpy.x;
+			} else {
+				pos_cpy.y = 2 * viewport_height - pos_cpy.x;
+			}
+		} else
+			pos_cpy.y = viewport_height - pos_cpy.x;
 		pos_cpy.x = temp_y;
 	}
 	// Mirror horizontally and vertically
 	else if (param.rotation == ROTATION_ANGLE_180) {
-		if (pos_cpy.x >= pipe_ctx->plane_res.scl_data.viewport.width + pipe_ctx->plane_res.scl_data.viewport.x) {
-			pos_cpy.x = 2 * pipe_ctx->plane_res.scl_data.viewport.width
-					- pos_cpy.x + 2 * pipe_ctx->plane_res.scl_data.viewport.x;
-		} else {
-			uint32_t temp_x = pos_cpy.x;
-			pos_cpy.x = 2 * pipe_ctx->plane_res.scl_data.viewport.x - pos_cpy.x;
-			if (temp_x >= pipe_ctx->plane_res.scl_data.viewport.x + (int)hubp->curs_attr.width
-					|| pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) {
-				pos_cpy.x = temp_x + pipe_ctx->plane_res.scl_data.viewport.width;
+		int viewport_width =
+			pipe_ctx->plane_res.scl_data.viewport.width;
+		int viewport_x =
+			pipe_ctx->plane_res.scl_data.viewport.x;
+
+		if (pipe_split_on) {
+			if (pos_cpy.x >= viewport_width + viewport_x) {
+				pos_cpy.x = 2 * viewport_width
+						- pos_cpy.x + 2 * viewport_x;
+			} else {
+				uint32_t temp_x = pos_cpy.x;
+
+				pos_cpy.x = 2 * viewport_x - pos_cpy.x;
+				if (temp_x >= viewport_x +
+					(int)hubp->curs_attr.width || pos_cpy.x
+					<= (int)hubp->curs_attr.width +
+					pipe_ctx->plane_state->src_rect.x) {
+					pos_cpy.x = temp_x + viewport_width;
+				}
 			}
+		} else {
+			pos_cpy.x = viewport_width - pos_cpy.x + 2 * viewport_x;
 		}
 		pos_cpy.y = pipe_ctx->plane_res.scl_data.viewport.height - pos_cpy.y;
 	}
@@ -3026,7 +3013,7 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	dpp->funcs->set_cursor_position(dpp, &pos_cpy, &param, hubp->curs_attr.width, hubp->curs_attr.height);
 }
 
-static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
+void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_cursor_attributes *attributes = &pipe_ctx->stream->cursor_attributes;
 
@@ -3036,7 +3023,7 @@ static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 		pipe_ctx->plane_res.dpp, attributes);
 }
 
-static void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
+void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
 {
 	uint32_t sdr_white_level = pipe_ctx->stream->cursor_attributes.sdr_white_level;
 	struct fixed31_32 multiplier;
@@ -3063,12 +3050,12 @@ static void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, &opt_attr);
 }
 
-/**
-* apply_front_porch_workaround  TODO FPGA still need?
-*
-* This is a workaround for a bug that has existed since R5xx and has not been
-* fixed keep Front porch at minimum 2 for Interlaced mode or 1 for progressive.
-*/
+/*
+ * apply_front_porch_workaround  TODO FPGA still need?
+ *
+ * This is a workaround for a bug that has existed since R5xx and has not been
+ * fixed keep Front porch at minimum 2 for Interlaced mode or 1 for progressive.
+ */
 static void apply_front_porch_workaround(
 	struct dc_crtc_timing *timing)
 {
@@ -3081,7 +3068,7 @@ static void apply_front_porch_workaround(
 	}
 }
 
-int get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
+int dcn10_get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
 {
 	const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing;
 	struct dc_crtc_timing patched_crtc_timing;
@@ -3110,34 +3097,8 @@ int get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx)
 	return vertical_line_start;
 }
 
-void lock_all_pipes(struct dc *dc,
-	struct dc_state *context,
-	bool lock)
-{
-	struct pipe_ctx *pipe_ctx;
-	struct timing_generator *tg;
-	int i;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		pipe_ctx = &context->res_ctx.pipe_ctx[i];
-		tg = pipe_ctx->stream_res.tg;
-		/*
-		 * Only lock the top pipe's tg to prevent redundant
-		 * (un)locking. Also skip if pipe is disabled.
-		 */
-		if (pipe_ctx->top_pipe ||
-		    !pipe_ctx->stream || !pipe_ctx->plane_state ||
-		    !tg->funcs->is_tg_enabled(tg))
-			continue;
-
-		if (lock)
-			tg->funcs->lock(tg);
-		else
-			tg->funcs->unlock(tg);
-	}
-}
-
-static void calc_vupdate_position(
+static void dcn10_calc_vupdate_position(
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		uint32_t *start_line,
 		uint32_t *end_line)
@@ -3145,7 +3106,7 @@ static void calc_vupdate_position(
 	const struct dc_crtc_timing *dc_crtc_timing = &pipe_ctx->stream->timing;
 	int vline_int_offset_from_vupdate =
 			pipe_ctx->stream->periodic_interrupt0.lines_offset;
-	int vupdate_offset_from_vsync = get_vupdate_offset_from_vsync(pipe_ctx);
+	int vupdate_offset_from_vsync = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 	int start_position;
 
 	if (vline_int_offset_from_vupdate > 0)
@@ -3166,7 +3127,8 @@ static void calc_vupdate_position(
 		*end_line = 2;
 }
 
-static void cal_vline_position(
+static void dcn10_cal_vline_position(
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum vline_select vline,
 		uint32_t *start_line,
@@ -3181,7 +3143,8 @@ static void cal_vline_position(
 
 	switch (ref_point) {
 	case START_V_UPDATE:
-		calc_vupdate_position(
+		dcn10_calc_vupdate_position(
+				dc,
 				pipe_ctx,
 				start_line,
 				end_line);
@@ -3195,7 +3158,8 @@ static void cal_vline_position(
 	}
 }
 
-static void dcn10_setup_periodic_interrupt(
+void dcn10_setup_periodic_interrupt(
+		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum vline_select vline)
 {
@@ -3205,7 +3169,7 @@ static void dcn10_setup_periodic_interrupt(
 		uint32_t start_line = 0;
 		uint32_t end_line = 0;
 
-		cal_vline_position(pipe_ctx, vline, &start_line, &end_line);
+		dcn10_cal_vline_position(dc, pipe_ctx, vline, &start_line, &end_line);
 
 		tg->funcs->setup_vertical_interrupt0(tg, start_line, end_line);
 
@@ -3216,10 +3180,10 @@ static void dcn10_setup_periodic_interrupt(
 	}
 }
 
-static void dcn10_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx)
+void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
-	int start_line = get_vupdate_offset_from_vsync(pipe_ctx);
+	int start_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 
 	if (start_line < 0) {
 		ASSERT(0);
@@ -3230,12 +3194,13 @@ static void dcn10_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx)
 		tg->funcs->setup_vertical_interrupt2(tg, start_line);
 }
 
-static void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
+void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
 		struct dc_link_settings *link_settings)
 {
 	struct encoder_unblank_param params = { { 0 } };
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 
 	/* only 3 items below are used by unblank */
 	params.timing = pipe_ctx->stream->timing;
@@ -3249,11 +3214,11 @@ static void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
 	}
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, true);
+		hws->funcs.edp_backlight_control(link, true);
 	}
 }
 
-static void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
+void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
 				const uint8_t *custom_sdp_message,
 				unsigned int sdp_message_size)
 {
@@ -3264,7 +3229,7 @@ static void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
 				sdp_message_size);
 	}
 }
-static enum dc_status dcn10_set_clock(struct dc *dc,
+enum dc_status dcn10_set_clock(struct dc *dc,
 			enum dc_clock_type clock_type,
 			uint32_t clk_khz,
 			uint32_t stepping)
@@ -3304,7 +3269,7 @@ static enum dc_status dcn10_set_clock(struct dc *dc,
 
 }
 
-static void dcn10_get_clock(struct dc *dc,
+void dcn10_get_clock(struct dc *dc,
 			enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg)
 {
@@ -3314,77 +3279,3 @@ static void dcn10_get_clock(struct dc *dc,
 				dc->clk_mgr->funcs->get_clock(dc->clk_mgr, context, clock_type, clock_cfg);
 
 }
-
-static const struct hw_sequencer_funcs dcn10_funcs = {
-	.program_gamut_remap = dcn10_program_gamut_remap,
-	.init_hw = dcn10_init_hw,
-	.init_pipes = dcn10_init_pipes,
-	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
-	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
-	.update_plane_addr = dcn10_update_plane_addr,
-	.plane_atomic_disconnect = hwss1_plane_atomic_disconnect,
-	.update_dchub = dcn10_update_dchub,
-	.update_mpcc = dcn10_update_mpcc,
-	.update_pending_status = dcn10_update_pending_status,
-	.set_input_transfer_func = dcn10_set_input_transfer_func,
-	.set_output_transfer_func = dcn10_set_output_transfer_func,
-	.program_output_csc = dcn10_program_output_csc,
-	.power_down = dce110_power_down,
-	.enable_accelerated_mode = dce110_enable_accelerated_mode,
-	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
-	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
-	.update_info_frame = dce110_update_info_frame,
-	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
-	.enable_stream = dce110_enable_stream,
-	.disable_stream = dce110_disable_stream,
-	.unblank_stream = dcn10_unblank_stream,
-	.blank_stream = dce110_blank_stream,
-	.enable_audio_stream = dce110_enable_audio_stream,
-	.disable_audio_stream = dce110_disable_audio_stream,
-	.enable_display_power_gating = dcn10_dummy_display_power_gating,
-	.disable_plane = dcn10_disable_plane,
-	.blank_pixel_data = dcn10_blank_pixel_data,
-	.pipe_control_lock = dcn10_pipe_control_lock,
-	.prepare_bandwidth = dcn10_prepare_bandwidth,
-	.optimize_bandwidth = dcn10_optimize_bandwidth,
-	.reset_hw_ctx_wrap = dcn10_reset_hw_ctx_wrap,
-	.enable_stream_timing = dcn10_enable_stream_timing,
-	.set_drr = dcn10_set_drr,
-	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
-	.setup_stereo = dcn10_setup_stereo,
-	.set_avmute = dce110_set_avmute,
-	.log_hw_state = dcn10_log_hw_state,
-	.get_hw_state = dcn10_get_hw_state,
-	.clear_status_bits = dcn10_clear_status_bits,
-	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
-	.edp_backlight_control = dce110_edp_backlight_control,
-	.edp_power_control = dce110_edp_power_control,
-	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
-	.set_cursor_position = dcn10_set_cursor_position,
-	.set_cursor_attribute = dcn10_set_cursor_attribute,
-	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
-	.disable_stream_gating = NULL,
-	.enable_stream_gating = NULL,
-	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
-	.setup_vupdate_interrupt = dcn10_setup_vupdate_interrupt,
-	.set_clock = dcn10_set_clock,
-	.get_clock = dcn10_get_clock,
-	.did_underflow_occur = dcn10_did_underflow_occur,
-	.init_blank = NULL,
-	.disable_vga = dcn10_disable_vga,
-	.bios_golden_init = dcn10_bios_golden_init,
-	.plane_atomic_disable = dcn10_plane_atomic_disable,
-	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
-	.enable_power_gating_plane = dcn10_enable_power_gating_plane,
-	.dpp_pg_control = dcn10_dpp_pg_control,
-	.hubp_pg_control = dcn10_hubp_pg_control,
-	.dsc_pg_control = NULL,
-};
-
-
-void dcn10_hw_sequencer_construct(struct dc *dc)
-{
-	dc->hwss = dcn10_funcs;
-}
-
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index d3616b1948cc..4d20f6586bb5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -27,68 +27,160 @@
 #define __DC_HWSS_DCN10_H__
 
 #include "core_types.h"
+#include "hw_sequencer_private.h"
 
 struct dc;
 
 void dcn10_hw_sequencer_construct(struct dc *dc);
-extern void fill_display_configs(
-	const struct dc_state *context,
-	struct dm_pp_display_configuration *pp_display_cfg);
-
-bool is_rgb_cspace(enum dc_color_space output_color_space);
-
-void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-void dcn10_verify_allow_pstate_change_high(struct dc *dc);
 
+int dcn10_get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx);
+void dcn10_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+enum dc_status dcn10_enable_stream_timing(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
+void dcn10_optimize_bandwidth(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_prepare_bandwidth(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_pipe_control_lock(
+	struct dc *dc,
+	struct pipe_ctx *pipe,
+	bool lock);
+void dcn10_blank_pixel_data(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		bool blank);
+void dcn10_unblank_stream(struct pipe_ctx *pipe_ctx,
+		struct dc_link_settings *link_settings);
+void dcn10_program_output_csc(struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		enum dc_color_space colorspace,
+		uint16_t *matrix,
+		int opp_id);
+bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream);
+bool dcn10_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_apply_ctx_for_surface(
+		struct dc *dc,
+		const struct dc_stream_state *stream,
+		int num_planes,
+		struct dc_state *context);
+void dcn10_hubp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int hubp_inst,
+		bool power_on);
+void dcn10_dpp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dpp_inst,
+		bool power_on);
+void dcn10_enable_power_gating_plane(
+	struct dce_hwseq *hws,
+	bool enable);
+void dcn10_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_disable_vga(
+	struct dce_hwseq *hws);
 void dcn10_program_pipe(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context);
-
-void dcn10_get_hw_state(
+void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx);
+void dcn10_init_hw(struct dc *dc);
+void dcn10_init_pipes(struct dc *dc, struct dc_state *context);
+enum dc_status dce110_apply_ctx_to_hw(
+		struct dc *dc,
+		struct dc_state *context);
+void dcn10_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data);
+void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx);
+void dce110_power_down(struct dc *dc);
+void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context);
+void dcn10_enable_timing_synchronization(
+		struct dc *dc,
+		int group_index,
+		int group_size,
+		struct pipe_ctx *grouped_pipes[]);
+void dcn10_enable_per_frame_crtc_position_reset(
+		struct dc *dc,
+		int group_size,
+		struct pipe_ctx *grouped_pipes[]);
+void dce110_update_info_frame(struct pipe_ctx *pipe_ctx);
+void dcn10_send_immediate_sdp_message(struct pipe_ctx *pipe_ctx,
+		const uint8_t *custom_sdp_message,
+		unsigned int sdp_message_size);
+void dce110_blank_stream(struct pipe_ctx *pipe_ctx);
+void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx);
+void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx);
+bool dcn10_dummy_display_power_gating(
 		struct dc *dc,
-		char *pBuf, unsigned int bufSize,
+		uint8_t controller_id,
+		struct dc_bios *dcb,
+		enum pipe_gating_control power_gating);
+void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
+		int num_pipes, unsigned int vmin, unsigned int vmax,
+		unsigned int vmid, unsigned int vmid_frame_number);
+void dcn10_get_position(struct pipe_ctx **pipe_ctx,
+		int num_pipes,
+		struct crtc_position *position);
+void dcn10_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params);
+void dcn10_setup_stereo(struct pipe_ctx *pipe_ctx, struct dc *dc);
+void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
+void dcn10_log_hw_state(struct dc *dc,
+		struct dc_log_buffer_ctx *log_ctx);
+void dcn10_get_hw_state(struct dc *dc,
+		char *pBuf,
+		unsigned int bufSize,
 		unsigned int mask);
-
 void dcn10_clear_status_bits(struct dc *dc, unsigned int mask);
-
-bool is_lower_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
-
-bool is_upper_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
-
-bool is_pipe_tree_visible(struct pipe_ctx *pipe_ctx);
-
-void dcn10_program_pte_vm(struct dce_hwseq *hws, struct hubp *hubp);
-
-void set_hdr_multiplier(struct pipe_ctx *pipe_ctx);
-
+void dcn10_wait_for_mpcc_disconnect(
+		struct dc *dc,
+		struct resource_pool *res_pool,
+		struct pipe_ctx *pipe_ctx);
+void dce110_edp_backlight_control(
+		struct dc_link *link,
+		bool enable);
+void dce110_edp_power_control(
+		struct dc_link *link,
+		bool power_up);
+void dce110_edp_wait_for_hpd_ready(
+		struct dc_link *link,
+		bool power_up);
+void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx);
+void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx);
+void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx);
+void dcn10_setup_periodic_interrupt(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		enum vline_select vline);
+enum dc_status dcn10_set_clock(struct dc *dc,
+		enum dc_clock_type clock_type,
+		uint32_t clk_khz,
+		uint32_t stepping);
+void dcn10_get_clock(struct dc *dc,
+		enum dc_clock_type clock_type,
+		struct dc_clock_config *clock_cfg);
+bool dcn10_did_underflow_occur(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn10_bios_golden_init(struct dc *dc);
+void dcn10_plane_atomic_power_down(struct dc *dc,
+		struct dpp *dpp,
+		struct hubp *hubp);
 void dcn10_get_surface_visual_confirm_color(
 		const struct pipe_ctx *pipe_ctx,
 		struct tg_color *color);
-
 void dcn10_get_hdr_visual_confirm_color(
 		struct pipe_ctx *pipe_ctx,
 		struct tg_color *color);
-
-bool dcn10_did_underflow_occur(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-void update_dchubp_dpp(
-	struct dc *dc,
-	struct pipe_ctx *pipe_ctx,
-	struct dc_state *context);
-
-struct pipe_ctx *find_top_pipe_for_stream(
-		struct dc *dc,
-		struct dc_state *context,
-		const struct dc_stream_state *stream);
-
-int get_vupdate_offset_from_vsync(struct pipe_ctx *pipe_ctx);
-
-void dcn10_build_prescale_params(struct  dc_bias_and_scale *bias_and_scale,
-		const struct dc_plane_state *plane_state);
-void lock_all_pipes(struct dc *dc,
-	struct dc_state *context,
-	bool lock);
+void dcn10_set_hdr_multiplier(struct pipe_ctx *pipe_ctx);
+void dcn10_verify_allow_pstate_change_high(struct dc *dc);
 
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.h
new file mode 100644
index 000000000000..596f95c22e85
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer_debug.h
@@ -0,0 +1,43 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HWSS_DCN10_DEBUG_H__
+#define __DC_HWSS_DCN10_DEBUG_H__
+
+#include "core_types.h"
+
+struct dc;
+
+void dcn10_clear_status_bits(struct dc *dc, unsigned int mask);
+
+void dcn10_log_hw_state(struct dc *dc,
+		struct dc_log_buffer_ctx *log_ctx);
+
+void dcn10_get_hw_state(struct dc *dc,
+		char *pBuf,
+		unsigned int bufSize,
+		unsigned int mask);
+
+#endif /* __DC_HWSS_DCN10_DEBUG_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
new file mode 100644
index 000000000000..e7e5352ec424
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hw_sequencer_private.h"
+#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10_hw_sequencer.h"
+
+static const struct hw_sequencer_funcs dcn10_funcs = {
+	.program_gamut_remap = dcn10_program_gamut_remap,
+	.init_hw = dcn10_init_hw,
+	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
+	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
+	.update_plane_addr = dcn10_update_plane_addr,
+	.update_dchub = dcn10_update_dchub,
+	.update_pending_status = dcn10_update_pending_status,
+	.program_output_csc = dcn10_program_output_csc,
+	.enable_accelerated_mode = dce110_enable_accelerated_mode,
+	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
+	.update_info_frame = dce110_update_info_frame,
+	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
+	.enable_stream = dce110_enable_stream,
+	.disable_stream = dce110_disable_stream,
+	.unblank_stream = dcn10_unblank_stream,
+	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
+	.disable_plane = dcn10_disable_plane,
+	.pipe_control_lock = dcn10_pipe_control_lock,
+	.prepare_bandwidth = dcn10_prepare_bandwidth,
+	.optimize_bandwidth = dcn10_optimize_bandwidth,
+	.set_drr = dcn10_set_drr,
+	.get_position = dcn10_get_position,
+	.set_static_screen_control = dcn10_set_static_screen_control,
+	.setup_stereo = dcn10_setup_stereo,
+	.set_avmute = dce110_set_avmute,
+	.log_hw_state = dcn10_log_hw_state,
+	.get_hw_state = dcn10_get_hw_state,
+	.clear_status_bits = dcn10_clear_status_bits,
+	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_power_control = dce110_edp_power_control,
+	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
+	.set_clock = dcn10_set_clock,
+	.get_clock = dcn10_get_clock,
+	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+};
+
+static const struct hwseq_private_funcs dcn10_private_funcs = {
+	.init_pipes = dcn10_init_pipes,
+	.update_plane_addr = dcn10_update_plane_addr,
+	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
+	.program_pipe = dcn10_program_pipe,
+	.update_mpcc = dcn10_update_mpcc,
+	.set_input_transfer_func = dcn10_set_input_transfer_func,
+	.set_output_transfer_func = dcn10_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_power_gating = dcn10_dummy_display_power_gating,
+	.blank_pixel_data = dcn10_blank_pixel_data,
+	.reset_hw_ctx_wrap = dcn10_reset_hw_ctx_wrap,
+	.enable_stream_timing = dcn10_enable_stream_timing,
+	.edp_backlight_control = dce110_edp_backlight_control,
+	.disable_stream_gating = NULL,
+	.enable_stream_gating = NULL,
+	.setup_vupdate_interrupt = dcn10_setup_vupdate_interrupt,
+	.did_underflow_occur = dcn10_did_underflow_occur,
+	.init_blank = NULL,
+	.disable_vga = dcn10_disable_vga,
+	.bios_golden_init = dcn10_bios_golden_init,
+	.plane_atomic_disable = dcn10_plane_atomic_disable,
+	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
+	.enable_power_gating_plane = dcn10_enable_power_gating_plane,
+	.dpp_pg_control = dcn10_dpp_pg_control,
+	.hubp_pg_control = dcn10_hubp_pg_control,
+	.dsc_pg_control = NULL,
+	.get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color,
+	.get_hdr_visual_confirm_color = dcn10_get_hdr_visual_confirm_color,
+	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
+	.verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high,
+};
+
+void dcn10_hw_sequencer_construct(struct dc *dc)
+{
+	dc->hwss = dcn10_funcs;
+	dc->hwseq->funcs = dcn10_private_funcs;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.h
new file mode 100644
index 000000000000..8c6fd7b844a4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_DCN10_INIT_H__
+#define __DC_DCN10_INIT_H__
+
+struct dc;
+
+void dcn10_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_DCN10_INIT_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c
index 0fb9e440cb9d..f05371c1fc36 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.c
@@ -53,11 +53,9 @@ static const struct ipp_funcs dcn10_ipp_funcs = {
 	.ipp_destroy			= dcn10_ipp_destroy
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 static const struct ipp_funcs dcn20_ipp_funcs = {
 	.ipp_destroy			= dcn10_ipp_destroy
 };
-#endif
 
 void dcn10_ipp_construct(
 	struct dcn10_ipp *ippn10,
@@ -76,7 +74,6 @@ void dcn10_ipp_construct(
 	ippn10->ipp_mask = ipp_mask;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn20_ipp_construct(
 	struct dcn10_ipp *ippn10,
 	struct dc_context *ctx,
@@ -93,4 +90,3 @@ void dcn20_ipp_construct(
 	ippn10->ipp_shift = ipp_shift;
 	ippn10->ipp_mask = ipp_mask;
 }
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h
index cfa24459242b..f0e0d07b0311 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_ipp.h
@@ -49,7 +49,6 @@
 	SRI(CURSOR_HOT_SPOT, CURSOR, id), \
 	SRI(CURSOR_DST_OFFSET, CURSOR, id)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define IPP_REG_LIST_DCN20(id) \
 	IPP_REG_LIST_DCN(id), \
 	SRI(CURSOR_SETTINGS, HUBPREQ, id), \
@@ -60,7 +59,6 @@
 	SRI(CURSOR_POSITION, CURSOR0_, id), \
 	SRI(CURSOR_HOT_SPOT, CURSOR0_, id), \
 	SRI(CURSOR_DST_OFFSET, CURSOR0_, id)
-#endif
 
 #define CURSOR0_CURSOR_CONTROL__CURSOR_2X_MAGNIFY__SHIFT	0x4
 #define CURSOR0_CURSOR_CONTROL__CURSOR_2X_MAGNIFY_MASK		0x00000010L
@@ -105,7 +103,6 @@
 	IPP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh), \
 	IPP_SF(CNVC_CFG0_FORMAT_CONTROL, OUTPUT_FP, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define IPP_MASK_SH_LIST_DCN20(mask_sh) \
 	IPP_MASK_SH_LIST_DCN(mask_sh), \
 	IPP_SF(HUBPREQ0_CURSOR_SETTINGS, CURSOR0_DST_Y_OFFSET, mask_sh), \
@@ -124,7 +121,6 @@
 	IPP_SF(CURSOR0_0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
 	IPP_SF(CURSOR0_0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
 	IPP_SF(CURSOR0_0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh)
-#endif
 
 #define IPP_DCN10_REG_FIELD_LIST(type) \
 	type CNVC_SURFACE_PIXEL_FORMAT; \
@@ -196,13 +192,11 @@ void dcn10_ipp_construct(struct dcn10_ipp *ippn10,
 	const struct dcn10_ipp_shift *ipp_shift,
 	const struct dcn10_ipp_mask *ipp_mask);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 void dcn20_ipp_construct(struct dcn10_ipp *ippn10,
 	struct dc_context *ctx,
 	int inst,
 	const struct dcn10_ipp_registers *regs,
 	const struct dcn10_ipp_shift *ipp_shift,
 	const struct dcn10_ipp_mask *ipp_mask);
-#endif
 
 #endif /* _DCN10_IPP_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index 88fcc395adf5..eb13589b9a81 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -72,9 +72,7 @@
 struct dcn10_link_enc_aux_registers {
 	uint32_t AUX_CONTROL;
 	uint32_t AUX_DPHY_RX_CONTROL0;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	uint32_t AUX_DPHY_TX_CONTROL;
-#endif
 };
 
 struct dcn10_link_enc_hpd_registers {
@@ -106,7 +104,6 @@ struct dcn10_link_enc_registers {
 	uint32_t DP_DPHY_HBR2_PATTERN_CONTROL;
 	uint32_t DP_SEC_CNTL1;
 	uint32_t TMDS_CTL_BITS;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* DCCG  */
 	uint32_t CLOCK_ENABLE;
 	/* DIG */
@@ -127,6 +124,26 @@ struct dcn10_link_enc_registers {
 	uint32_t RDPCSTX_PHY_CNTL13;
 	uint32_t RDPCSTX_PHY_CNTL14;
 	uint32_t RDPCSTX_PHY_CNTL15;
+	uint32_t RDPCSTX_CNTL;
+	uint32_t RDPCSTX_CLOCK_CNTL;
+	uint32_t RDPCSTX_PHY_CNTL0;
+	uint32_t RDPCSTX_PHY_CNTL2;
+	uint32_t RDPCSTX_PLL_UPDATE_DATA;
+	uint32_t RDPCS_TX_CR_ADDR;
+	uint32_t RDPCS_TX_CR_DATA;
+	uint32_t DPCSTX_TX_CLOCK_CNTL;
+	uint32_t DPCSTX_TX_CNTL;
+	uint32_t RDPCSTX_INTERRUPT_CONTROL;
+	uint32_t RDPCSTX_PHY_FUSE0;
+	uint32_t RDPCSTX_PHY_FUSE1;
+	uint32_t RDPCSTX_PHY_FUSE2;
+	uint32_t RDPCSTX_PHY_FUSE3;
+	uint32_t RDPCSTX_PHY_RX_LD_VAL;
+	uint32_t DPCSTX_DEBUG_CONFIG;
+	uint32_t RDPCSTX_DEBUG_CONFIG;
+	uint32_t RDPCSTX0_RDPCSTX_SCRATCH;
+	uint32_t RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG;
+	uint32_t DCIO_SOFT_RESET;
 	/* indirect registers */
 	uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_2;
 	uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_3;
@@ -136,7 +153,6 @@ struct dcn10_link_enc_registers {
 	uint32_t RAWLANE2_DIG_PCS_XF_RX_OVRD_IN_3;
 	uint32_t RAWLANE3_DIG_PCS_XF_RX_OVRD_IN_2;
 	uint32_t RAWLANE3_DIG_PCS_XF_RX_OVRD_IN_3;
-#endif
 };
 
 #define LE_SF(reg_name, field_name, post_fix)\
@@ -242,7 +258,6 @@ struct dcn10_link_enc_registers {
 	type AUX_LS_READ_EN;\
 	type AUX_RX_RECEIVE_WINDOW
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 #define DCN20_LINK_ENCODER_DPCS_REG_FIELD_LIST(type) \
 		type RDPCS_PHY_DP_TX0_DATA_EN;\
@@ -423,20 +438,15 @@ struct dcn10_link_enc_registers {
 	type AUX_TX_PRECHARGE_SYMBOLS; \
 	type AUX_MODE_DET_CHECK_DELAY;\
 	type DPCS_DBG_CBUS_DIS
-#endif
 
 struct dcn10_link_enc_shift {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	DCN20_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
-#endif
 };
 
 struct dcn10_link_enc_mask {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint32_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	DCN20_LINK_ENCODER_REG_FIELD_LIST(uint32_t);
-#endif
 };
 
 struct dcn10_link_encoder {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 8b2f29f6dabd..04f863499cfb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -42,20 +42,27 @@ void mpc1_set_bg_color(struct mpc *mpc,
 		int mpcc_id)
 {
 	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+	struct mpcc *bottommost_mpcc = mpc1_get_mpcc(mpc, mpcc_id);
+	uint32_t bg_r_cr, bg_g_y, bg_b_cb;
+
+	/* find bottommost mpcc. */
+	while (bottommost_mpcc->mpcc_bot) {
+		bottommost_mpcc = bottommost_mpcc->mpcc_bot;
+	}
 
 	/* mpc color is 12 bit.  tg_color is 10 bit */
 	/* todo: might want to use 16 bit to represent color and have each
 	 * hw block translate to correct color depth.
 	 */
-	uint32_t bg_r_cr = bg_color->color_r_cr << 2;
-	uint32_t bg_g_y = bg_color->color_g_y << 2;
-	uint32_t bg_b_cb = bg_color->color_b_cb << 2;
+	bg_r_cr = bg_color->color_r_cr << 2;
+	bg_g_y = bg_color->color_g_y << 2;
+	bg_b_cb = bg_color->color_b_cb << 2;
 
-	REG_SET(MPCC_BG_R_CR[mpcc_id], 0,
+	REG_SET(MPCC_BG_R_CR[bottommost_mpcc->mpcc_id], 0,
 			MPCC_BG_R_CR, bg_r_cr);
-	REG_SET(MPCC_BG_G_Y[mpcc_id], 0,
+	REG_SET(MPCC_BG_G_Y[bottommost_mpcc->mpcc_id], 0,
 			MPCC_BG_G_Y, bg_g_y);
-	REG_SET(MPCC_BG_B_CB[mpcc_id], 0,
+	REG_SET(MPCC_BG_B_CB[bottommost_mpcc->mpcc_id], 0,
 			MPCC_BG_B_CB, bg_b_cb);
 }
 
@@ -457,12 +464,10 @@ static const struct mpc_funcs dcn10_mpc_funcs = {
 	.assert_mpcc_idle_before_connect = mpc1_assert_mpcc_idle_before_connect,
 	.init_mpcc_list_from_hw = mpc1_init_mpcc_list_from_hw,
 	.update_blending = mpc1_update_blending,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	.set_denorm = NULL,
 	.set_denorm_clamp = NULL,
 	.set_output_csc = NULL,
 	.set_output_gamma = NULL,
-#endif
 };
 
 void dcn10_mpc_construct(struct dcn10_mpc *mpc10,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
index 0a9ad692f541..d79718fde5a6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -373,11 +373,9 @@ void opp1_program_oppbuf(
 	 */
 	REG_UPDATE(OPPBUF_CONTROL, OPPBUF_PIXEL_REPETITION, oppbuf->pixel_repetition);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* Controls the number of padded pixels at the end of a segment */
 	if (REG(OPPBUF_CONTROL1))
 		REG_UPDATE(OPPBUF_CONTROL1, OPPBUF_NUM_SEGMENT_PADDED_PIXELS, oppbuf->num_segment_padded_pixels);
-#endif
 }
 
 void opp1_pipe_clock_control(struct output_pixel_processor *opp, bool enable)
@@ -404,9 +402,8 @@ static const struct opp_funcs dcn10_opp_funcs = {
 		.opp_program_bit_depth_reduction = opp1_program_bit_depth_reduction,
 		.opp_program_stereo = opp1_program_stereo,
 		.opp_pipe_clock_control = opp1_pipe_clock_control,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		.opp_set_disp_pattern_generator = NULL,
-#endif
+		.dpg_is_blanked = NULL,
 		.opp_destroy = opp1_destroy
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index dabccbd49ad4..a9a43b397db9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -457,11 +457,16 @@ static bool optc1_enable_crtc(struct timing_generator *optc)
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 1);
 
+	REG_SEQ_START();
+
 	/* Enable CRTC */
 	REG_UPDATE_2(OTG_CONTROL,
 			OTG_DISABLE_POINT_CNTL, 3,
 			OTG_MASTER_EN, 1);
 
+	REG_SEQ_SUBMIT();
+	REG_SEQ_WAIT_DONE();
+
 	return true;
 }
 
@@ -784,21 +789,26 @@ void optc1_set_early_control(
 
 void optc1_set_static_screen_control(
 	struct timing_generator *optc,
-	uint32_t value)
+	uint32_t event_triggers,
+	uint32_t num_frames)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
+	// By register spec, it only takes 8 bit value
+	if (num_frames > 0xFF)
+		num_frames = 0xFF;
+
 	/* Bit 8 is no longer applicable in RV for PSR case,
 	 * set bit 8 to 0 if given
 	 */
-	if ((value & STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN)
+	if ((event_triggers & STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN)
 			!= 0)
-		value = value &
+		event_triggers = event_triggers &
 		~STATIC_SCREEN_EVENT_MASK_RANGETIMING_DOUBLE_BUFFER_UPDATE_EN;
 
 	REG_SET_2(OTG_STATIC_SCREEN_CONTROL, 0,
-			OTG_STATIC_SCREEN_EVENT_MASK, value,
-			OTG_STATIC_SCREEN_FRAME_COUNT, 2);
+			OTG_STATIC_SCREEN_EVENT_MASK, event_triggers,
+			OTG_STATIC_SCREEN_FRAME_COUNT, num_frames);
 }
 
 void optc1_setup_manual_trigger(struct timing_generator *optc)
@@ -1497,7 +1507,6 @@ void dcn10_timing_generator_init(struct optc *optc1)
 	optc1->min_v_sync_width = 1;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* "Containter" vs. "pixel" is a concept within HW blocks, mostly those closer to the back-end. It works like this:
  *
  * - In most of the formats (RGB or YCbCr 4:4:4, 4:2:2 uncompressed and DSC 4:2:2 Simple) pixel rate is the same as
@@ -1510,15 +1519,12 @@ void dcn10_timing_generator_init(struct optc *optc1)
  *   to it) and has to be treated the same as 4:2:0, i.e. target containter rate has to be halved in this case as well.
  *
  */
-#endif
 bool optc1_is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
 {
 	bool two_pix = timing->pixel_encoding == PIXEL_ENCODING_YCBCR420;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	two_pix = two_pix || (timing->flags.DSC && timing->pixel_encoding == PIXEL_ENCODING_YCBCR422
 			&& !timing->dsc_cfg.ycbcr422_simple);
-#endif
 	return two_pix;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index c8d795b335ba..f277656d5464 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -165,13 +165,11 @@ struct dcn_optc_registers {
 	uint32_t OTG_CRC0_WINDOWB_X_CONTROL;
 	uint32_t OTG_CRC0_WINDOWB_Y_CONTROL;
 	uint32_t GSL_SOURCE_SELECT;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	uint32_t DWB_SOURCE_SELECT;
 	uint32_t OTG_DSC_START_POSITION;
 	uint32_t OPTC_DATA_FORMAT_CONTROL;
 	uint32_t OPTC_BYTES_PER_PIXEL;
 	uint32_t OPTC_WIDTH_CONTROL;
-#endif
 };
 
 #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\
@@ -456,7 +454,6 @@ struct dcn_optc_registers {
 	type MANUAL_FLOW_CONTROL;\
 	type MANUAL_FLOW_CONTROL_SEL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #define TG_REG_FIELD_LIST(type) \
 	TG_REG_FIELD_LIST_DCN1_0(type)\
@@ -479,12 +476,6 @@ struct dcn_optc_registers {
 	type OPTC_DWB0_SOURCE_SELECT;\
 	type OPTC_DWB1_SOURCE_SELECT;
 
-#else
-
-#define TG_REG_FIELD_LIST(type) \
-	TG_REG_FIELD_LIST_DCN1_0(type)
-
-#endif
 
 
 struct dcn_optc_shift {
@@ -542,6 +533,7 @@ struct dcn_otg_state {
 	uint32_t h_total;
 	uint32_t underflow_occurred_status;
 	uint32_t otg_enabled;
+	uint32_t blank_enabled;
 };
 
 void optc1_read_otg_state(struct optc *optc1,
@@ -633,7 +625,8 @@ void optc1_set_drr(
 
 void optc1_set_static_screen_control(
 	struct timing_generator *optc,
-	uint32_t value);
+	uint32_t event_triggers,
+	uint32_t num_frames);
 
 void optc1_program_stereo(struct timing_generator *optc,
 	const struct dc_crtc_timing *timing, struct crtc_stereo_flags *flags);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 15640aedd664..3b71898e859e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -28,6 +28,8 @@
 #include "dm_services.h"
 #include "dc.h"
 
+#include "dcn10_init.h"
+
 #include "resource.h"
 #include "include/irq_service_interface.h"
 #include "dcn10_resource.h"
@@ -919,7 +921,7 @@ static struct pp_smu_funcs *dcn10_pp_smu_create(struct dc_context *ctx)
 	return pp_smu;
 }
 
-static void destruct(struct dcn10_resource_pool *pool)
+static void dcn10_resource_destruct(struct dcn10_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1166,7 +1168,7 @@ static void dcn10_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn10_resource_pool *dcn10_pool = TO_DCN10_RES_POOL(*pool);
 
-	destruct(dcn10_pool);
+	dcn10_resource_destruct(dcn10_pool);
 	kfree(dcn10_pool);
 	*pool = NULL;
 }
@@ -1305,7 +1307,7 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 	return value;
 }
 
-static bool construct(
+static bool dcn10_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dcn10_resource_pool *pool)
@@ -1592,7 +1594,7 @@ static bool construct(
 
 fail:
 
-	destruct(pool);
+	dcn10_resource_destruct(pool);
 
 	return false;
 }
@@ -1607,7 +1609,7 @@ struct resource_pool *dcn10_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(init_data->num_virtual_links, dc, pool))
+	if (dcn10_resource_construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
 	kfree(pool);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 06e5bbb4545c..376c4264d295 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -247,6 +247,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting)
 {
 	uint32_t h_active_start;
@@ -312,10 +313,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	 * Pixel Encoding/Colorimetry Format and that a Sink device shall ignore MISC1, bit 7,
 	 * and MISC0, bits 7:1 (MISC1, bit 7, and MISC0, bits 7:1, become "don't care").
 	 */
-	if ((hw_crtc_timing.pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
-			(output_color_space == COLOR_SPACE_2020_YCBCR) ||
-			(output_color_space == COLOR_SPACE_2020_RGB_FULLRANGE) ||
-			(output_color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE))
+	if (use_vsc_sdp_for_colorimetry)
 		misc1 = misc1 | 0x40;
 	else
 		misc1 = misc1 & ~0x40;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
index c9cbc21d121e..f9b9e221c698 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -163,14 +163,12 @@ struct dcn10_stream_enc_registers {
 	uint32_t DP_MSA_TIMING_PARAM3;
 	uint32_t DP_MSA_TIMING_PARAM4;
 	uint32_t HDMI_DB_CONTROL;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t DP_DSC_CNTL;
 	uint32_t DP_DSC_BYTES_PER_PIXEL;
 	uint32_t DME_CONTROL;
 	uint32_t DP_SEC_METADATA_TRANSMISSION;
 	uint32_t HDMI_METADATA_PACKET_CONTROL;
 	uint32_t DP_SEC_FRAMING4;
-#endif
 	uint32_t DIG_CLOCK_PATTERN;
 };
 
@@ -466,7 +464,6 @@ struct dcn10_stream_enc_registers {
 	type DIG_SOURCE_SELECT;\
 	type DIG_CLOCK_PATTERN
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define SE_REG_FIELD_LIST_DCN2_0(type) \
 	type DP_DSC_MODE;\
 	type DP_DSC_SLICE_WIDTH;\
@@ -485,20 +482,15 @@ struct dcn10_stream_enc_registers {
 	type DOLBY_VISION_EN;\
 	type DP_PIXEL_COMBINE;\
 	type DP_SST_SDP_SPLITTING
-#endif
 
 struct dcn10_stream_encoder_shift {
 	SE_REG_FIELD_LIST_DCN1_0(uint8_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SE_REG_FIELD_LIST_DCN2_0(uint8_t);
-#endif
 };
 
 struct dcn10_stream_encoder_mask {
 	SE_REG_FIELD_LIST_DCN1_0(uint32_t);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	SE_REG_FIELD_LIST_DCN2_0(uint32_t);
-#endif
 };
 
 struct dcn10_stream_encoder {
@@ -526,6 +518,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting);
 
 void enc1_stream_encoder_hdmi_set_stream_attribute(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index 10b47986526b..5fcaf78334ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -2,16 +2,20 @@
 #
 # Makefile for DCN.
 
-DCN20 = dcn20_resource.o dcn20_hwseq.o dcn20_dpp.o dcn20_dpp_cm.o dcn20_hubp.o \
+DCN20 = dcn20_resource.o dcn20_init.o dcn20_hwseq.o dcn20_dpp.o dcn20_dpp_cm.o dcn20_hubp.o \
 		dcn20_mpc.o dcn20_opp.o dcn20_hubbub.o dcn20_optc.o dcn20_mmhubbub.o \
 		dcn20_stream_encoder.o dcn20_link_encoder.o dcn20_dccg.o \
 		dcn20_vmid.o dcn20_dwb.o dcn20_dwb_scl.o
 
-ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DCN20 += dcn20_dsc.o
-endif
 
+ifdef CONFIG_X86
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -19,6 +23,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -27,6 +32,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
 else
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
 endif
+endif
 
 AMD_DAL_DCN20 = $(addprefix $(AMDDALPATH)/dc/dcn20/,$(DCN20))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
index 1e1151356e60..50bffbfdd394 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
@@ -50,20 +50,20 @@ void dccg2_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk)
 
 	if (dccg->ref_dppclk && req_dppclk) {
 		int ref_dppclk = dccg->ref_dppclk;
+		int modulo, phase;
 
-		ASSERT(req_dppclk <= ref_dppclk);
-		/* need to clamp to 8 bits */
-		if (ref_dppclk > 0xff) {
-			int divider = (ref_dppclk + 0xfe) / 0xff;
+		// phase / modulo = dpp pipe clk / dpp global clk
+		modulo = 0xff;   // use FF at the end
+		phase = ((modulo * req_dppclk) + ref_dppclk - 1) / ref_dppclk;
 
-			ref_dppclk /= divider;
-			req_dppclk = (req_dppclk + divider - 1) / divider;
-			if (req_dppclk > ref_dppclk)
-				req_dppclk = ref_dppclk;
+		if (phase > 0xff) {
+			ASSERT(false);
+			phase = 0xff;
 		}
+
 		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
-				DPPCLK0_DTO_PHASE, req_dppclk,
-				DPPCLK0_DTO_MODULO, ref_dppclk);
+				DPPCLK0_DTO_PHASE, phase,
+				DPPCLK0_DTO_MODULO, modulo);
 		REG_UPDATE(DPPCLK_DTO_CTRL,
 				DPPCLK_DTO_ENABLE[dpp_inst], 1);
 	} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
index 4d7e45892f08..13e057d7ee93 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
@@ -104,7 +104,7 @@ static void dpp2_cnv_setup (
 	uint32_t pixel_format = 0;
 	uint32_t alpha_en = 1;
 	enum dc_color_space color_space = COLOR_SPACE_SRGB;
-	enum dcn10_input_csc_select select = INPUT_CSC_SELECT_BYPASS;
+	enum dcn20_input_csc_select select = DCN2_ICSC_SELECT_BYPASS;
 	bool force_disable_cursor = false;
 	struct out_csc_color_matrix tbl_entry;
 	uint32_t is_2bit = 0;
@@ -145,25 +145,25 @@ static void dpp2_cnv_setup (
 		force_disable_cursor = false;
 		pixel_format = 65;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb:
 		force_disable_cursor = true;
 		pixel_format = 64;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr:
 		force_disable_cursor = true;
 		pixel_format = 67;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb:
 		force_disable_cursor = true;
 		pixel_format = 66;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
 		pixel_format = 22;
@@ -177,7 +177,7 @@ static void dpp2_cnv_setup (
 	case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888:
 		pixel_format = 12;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX:
 		pixel_format = 112;
@@ -188,13 +188,13 @@ static void dpp2_cnv_setup (
 	case SURFACE_PIXEL_FORMAT_VIDEO_ACrYCb2101010:
 		pixel_format = 114;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		is_2bit = 1;
 		break;
 	case SURFACE_PIXEL_FORMAT_VIDEO_CrYCbA1010102:
 		pixel_format = 115;
 		color_space = COLOR_SPACE_YCBCR709;
-		select = INPUT_CSC_SELECT_ICSC;
+		select = DCN2_ICSC_SELECT_ICSC_A;
 		is_2bit = 1;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FLOAT:
@@ -227,13 +227,13 @@ static void dpp2_cnv_setup (
 		tbl_entry.color_space = input_color_space;
 
 		if (color_space >= COLOR_SPACE_YCBCR601)
-			select = INPUT_CSC_SELECT_ICSC;
+			select = DCN2_ICSC_SELECT_ICSC_A;
 		else
-			select = INPUT_CSC_SELECT_BYPASS;
+			select = DCN2_ICSC_SELECT_BYPASS;
 
-		dpp1_program_input_csc(dpp_base, color_space, select, &tbl_entry);
+		dpp2_program_input_csc(dpp_base, color_space, select, &tbl_entry);
 	} else
-	dpp1_program_input_csc(dpp_base, color_space, select, NULL);
+	dpp2_program_input_csc(dpp_base, color_space, select, NULL);
 
 	if (force_disable_cursor) {
 		REG_UPDATE(CURSOR_CONTROL,
@@ -458,7 +458,7 @@ static struct dpp_funcs dcn20_dpp_funcs = {
 	.dpp_reset = dpp_reset,
 	.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
 	.dpp_get_optimal_number_of_taps = dpp1_get_optimal_number_of_taps,
-	.dpp_set_gamut_remap = dpp1_cm_set_gamut_remap,
+	.dpp_set_gamut_remap = dpp2_cm_set_gamut_remap,
 	.dpp_set_csc_adjustment = NULL,
 	.dpp_set_csc_default = NULL,
 	.dpp_program_regamma_pwl = oppn20_dummy_program_regamma_pwl,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
index 5b03b737b1d6..27610251c57f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
@@ -150,6 +150,16 @@
 	SRI(CM_SHAPER_RAMA_REGION_32_33, CM, id), \
 	SRI(CM_SHAPER_LUT_INDEX, CM, id)
 
+#define TF_REG_LIST_DCN20_COMMON_APPEND(id) \
+	SRI(CM_GAMUT_REMAP_B_C11_C12, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C13_C14, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C21_C22, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C23_C24, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C31_C32, CM, id),\
+	SRI(CM_GAMUT_REMAP_B_C33_C34, CM, id),\
+	SRI(CM_ICSC_B_C11_C12, CM, id), \
+	SRI(CM_ICSC_B_C33_C34, CM, id)
+
 #define TF_REG_LIST_DCN20(id) \
 	TF_REG_LIST_DCN(id), \
 	TF_REG_LIST_DCN20_COMMON(id), \
@@ -572,10 +582,29 @@
 	TF_SF(DSCL0_OBUF_MEM_PWR_CTRL, OBUF_MEM_PWR_FORCE, mask_sh),\
 	TF_SF(DSCL0_DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, mask_sh)
 
+/* DPP CM debug status register:
+ *
+ *		Status index including current ICSC, Gamut Remap Mode is 9
+ *			ICSC Mode: [4..3]
+ *			Gamut Remap Mode: [10..9]
+ */
+#define CM_TEST_DEBUG_DATA_STATUS_IDX 9
+
+#define TF_DEBUG_REG_LIST_SH_DCN20 \
+	TF_DEBUG_REG_LIST_SH_DCN10, \
+	.CM_TEST_DEBUG_DATA_ICSC_MODE = 3, \
+	.CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE = 9
+
+#define TF_DEBUG_REG_LIST_MASK_DCN20 \
+	TF_DEBUG_REG_LIST_MASK_DCN10, \
+	.CM_TEST_DEBUG_DATA_ICSC_MODE = 0x18, \
+	.CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE = 0x600
 
 #define TF_REG_FIELD_LIST_DCN2_0(type) \
 	TF_REG_FIELD_LIST(type) \
 	type CM_BLNDGAM_LUT_DATA; \
+	type CM_TEST_DEBUG_DATA_ICSC_MODE; \
+	type CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE; \
 	type FORMAT_CNV16; \
 	type CNVC_BYPASS_MSB_ALIGN; \
 	type CLAMP_POSITIVE; \
@@ -630,11 +659,22 @@ struct dcn2_dpp_mask {
 	uint32_t COLOR_KEYER_RED; \
 	uint32_t COLOR_KEYER_GREEN; \
 	uint32_t COLOR_KEYER_BLUE; \
-	uint32_t OBUF_MEM_PWR_CTRL;\
+	uint32_t OBUF_MEM_PWR_CTRL; \
 	uint32_t DSCL_MEM_PWR_CTRL
 
+#define DPP_DCN2_REG_VARIABLE_LIST_CM_APPEND \
+	uint32_t CM_GAMUT_REMAP_B_C11_C12; \
+	uint32_t CM_GAMUT_REMAP_B_C13_C14; \
+	uint32_t CM_GAMUT_REMAP_B_C21_C22; \
+	uint32_t CM_GAMUT_REMAP_B_C23_C24; \
+	uint32_t CM_GAMUT_REMAP_B_C31_C32; \
+	uint32_t CM_GAMUT_REMAP_B_C33_C34; \
+	uint32_t CM_ICSC_B_C11_C12; \
+	uint32_t CM_ICSC_B_C33_C34
+
 struct dcn2_dpp_registers {
 	DPP_DCN2_REG_VARIABLE_LIST;
+	DPP_DCN2_REG_VARIABLE_LIST_CM_APPEND;
 };
 
 struct dcn20_dpp {
@@ -656,6 +696,18 @@ struct dcn20_dpp {
 	struct pwl_params pwl_data;
 };
 
+enum dcn20_input_csc_select {
+	DCN2_ICSC_SELECT_BYPASS = 0,
+	DCN2_ICSC_SELECT_ICSC_A = 1,
+	DCN2_ICSC_SELECT_ICSC_B = 2
+};
+
+enum dcn20_gamut_remap_select {
+	DCN2_GAMUT_REMAP_BYPASS = 0,
+	DCN2_GAMUT_REMAP_COEF_A = 1,
+	DCN2_GAMUT_REMAP_COEF_B = 2
+};
+
 void dpp20_read_state(struct dpp *dpp_base,
 		struct dcn_dpp_state *s);
 
@@ -667,6 +719,16 @@ void dpp2_set_degamma(
 		struct dpp *dpp_base,
 		enum ipp_degamma_mode mode);
 
+void dpp2_cm_set_gamut_remap(
+	struct dpp *dpp_base,
+	const struct dpp_grph_csc_adjustment *adjust);
+
+void dpp2_program_input_csc(
+		struct dpp *dpp_base,
+		enum dc_color_space color_space,
+		enum dcn20_input_csc_select input_select,
+		const struct out_csc_color_matrix *tbl_entry);
+
 bool dpp20_program_blnd_lut(
 	struct dpp *dpp_base, const struct pwl_params *params);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c
index 2d112c316424..8dc3d1f73984 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp_cm.c
@@ -36,6 +36,9 @@
 #define REG(reg)\
 	dpp->tf_regs->reg
 
+#define IND_REG(index) \
+	(index)
+
 #define CTX \
 	dpp->base.ctx
 
@@ -44,9 +47,6 @@
 	dpp->tf_shift->field_name, dpp->tf_mask->field_name
 
 
-
-
-
 static void dpp2_enable_cm_block(
 		struct dpp *dpp_base)
 {
@@ -149,12 +149,164 @@ void dpp2_set_degamma(
 	case IPP_DEGAMMA_MODE_HW_xvYCC:
 		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 2);
 			break;
+	case IPP_DEGAMMA_MODE_USER_PWL:
+		REG_UPDATE(CM_DGAM_CONTROL, CM_DGAM_LUT_MODE, 3);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
 	}
 }
 
+static void program_gamut_remap(
+		struct dcn20_dpp *dpp,
+		const uint16_t *regval,
+		enum dcn20_gamut_remap_select select)
+{
+	uint32_t cur_select = 0;
+	struct color_matrices_reg gam_regs;
+
+	if (regval == NULL || select == DCN2_GAMUT_REMAP_BYPASS) {
+		REG_SET(CM_GAMUT_REMAP_CONTROL, 0,
+				CM_GAMUT_REMAP_MODE, 0);
+		return;
+	}
+
+	/* determine which gamut_remap coefficients (A or B) we are using
+	 * currently. select the alternate set to double buffer
+	 * the update so gamut_remap is updated on frame boundary
+	 */
+	IX_REG_GET(CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_DATA,
+					CM_TEST_DEBUG_DATA_STATUS_IDX,
+					CM_TEST_DEBUG_DATA_GAMUT_REMAP_MODE, &cur_select);
+
+	/* value stored in dbg reg will be 1 greater than mode we want */
+	if (cur_select != DCN2_GAMUT_REMAP_COEF_A)
+		select = DCN2_GAMUT_REMAP_COEF_A;
+	else
+		select = DCN2_GAMUT_REMAP_COEF_B;
+
+	gam_regs.shifts.csc_c11 = dpp->tf_shift->CM_GAMUT_REMAP_C11;
+	gam_regs.masks.csc_c11  = dpp->tf_mask->CM_GAMUT_REMAP_C11;
+	gam_regs.shifts.csc_c12 = dpp->tf_shift->CM_GAMUT_REMAP_C12;
+	gam_regs.masks.csc_c12 = dpp->tf_mask->CM_GAMUT_REMAP_C12;
+
+	if (select == DCN2_GAMUT_REMAP_COEF_A) {
+		gam_regs.csc_c11_c12 = REG(CM_GAMUT_REMAP_C11_C12);
+		gam_regs.csc_c33_c34 = REG(CM_GAMUT_REMAP_C33_C34);
+	} else {
+		gam_regs.csc_c11_c12 = REG(CM_GAMUT_REMAP_B_C11_C12);
+		gam_regs.csc_c33_c34 = REG(CM_GAMUT_REMAP_B_C33_C34);
+	}
+
+	cm_helper_program_color_matrices(
+				dpp->base.ctx,
+				regval,
+				&gam_regs);
+
+	REG_SET(
+			CM_GAMUT_REMAP_CONTROL, 0,
+			CM_GAMUT_REMAP_MODE, select);
+
+}
+
+void dpp2_cm_set_gamut_remap(
+	struct dpp *dpp_base,
+	const struct dpp_grph_csc_adjustment *adjust)
+{
+	struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base);
+	int i = 0;
+
+	if (adjust->gamut_adjust_type != GRAPHICS_GAMUT_ADJUST_TYPE_SW)
+		/* Bypass if type is bypass or hw */
+		program_gamut_remap(dpp, NULL, DCN2_GAMUT_REMAP_BYPASS);
+	else {
+		struct fixed31_32 arr_matrix[12];
+		uint16_t arr_reg_val[12];
+
+		for (i = 0; i < 12; i++)
+			arr_matrix[i] = adjust->temperature_matrix[i];
+
+		convert_float_matrix(
+			arr_reg_val, arr_matrix, 12);
+
+		program_gamut_remap(dpp, arr_reg_val, DCN2_GAMUT_REMAP_COEF_A);
+	}
+}
+
+void dpp2_program_input_csc(
+		struct dpp *dpp_base,
+		enum dc_color_space color_space,
+		enum dcn20_input_csc_select input_select,
+		const struct out_csc_color_matrix *tbl_entry)
+{
+	struct dcn20_dpp *dpp = TO_DCN20_DPP(dpp_base);
+	int i;
+	int arr_size = sizeof(dpp_input_csc_matrix)/sizeof(struct dpp_input_csc_matrix);
+	const uint16_t *regval = NULL;
+	uint32_t cur_select = 0;
+	enum dcn20_input_csc_select select;
+	struct color_matrices_reg icsc_regs;
+
+	if (input_select == DCN2_ICSC_SELECT_BYPASS) {
+		REG_SET(CM_ICSC_CONTROL, 0, CM_ICSC_MODE, 0);
+		return;
+	}
+
+	if (tbl_entry == NULL) {
+		for (i = 0; i < arr_size; i++)
+			if (dpp_input_csc_matrix[i].color_space == color_space) {
+				regval = dpp_input_csc_matrix[i].regval;
+				break;
+			}
+
+		if (regval == NULL) {
+			BREAK_TO_DEBUGGER();
+			return;
+		}
+	} else {
+		regval = tbl_entry->regval;
+	}
+
+	/* determine which CSC coefficients (A or B) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	IX_REG_GET(CM_TEST_DEBUG_INDEX, CM_TEST_DEBUG_DATA,
+					CM_TEST_DEBUG_DATA_STATUS_IDX,
+					CM_TEST_DEBUG_DATA_ICSC_MODE, &cur_select);
+
+	if (cur_select != DCN2_ICSC_SELECT_ICSC_A)
+		select = DCN2_ICSC_SELECT_ICSC_A;
+	else
+		select = DCN2_ICSC_SELECT_ICSC_B;
+
+	icsc_regs.shifts.csc_c11 = dpp->tf_shift->CM_ICSC_C11;
+	icsc_regs.masks.csc_c11  = dpp->tf_mask->CM_ICSC_C11;
+	icsc_regs.shifts.csc_c12 = dpp->tf_shift->CM_ICSC_C12;
+	icsc_regs.masks.csc_c12 = dpp->tf_mask->CM_ICSC_C12;
+
+	if (select == DCN2_ICSC_SELECT_ICSC_A) {
+
+		icsc_regs.csc_c11_c12 = REG(CM_ICSC_C11_C12);
+		icsc_regs.csc_c33_c34 = REG(CM_ICSC_C33_C34);
+
+	} else {
+
+		icsc_regs.csc_c11_c12 = REG(CM_ICSC_B_C11_C12);
+		icsc_regs.csc_c33_c34 = REG(CM_ICSC_B_C33_C34);
+
+	}
+
+	cm_helper_program_color_matrices(
+			dpp->base.ctx,
+			regval,
+			&icsc_regs);
+
+	REG_SET(CM_ICSC_CONTROL, 0,
+				CM_ICSC_MODE, select);
+}
+
 static void dpp20_power_on_blnd_lut(
 	struct dpp *dpp_base,
 	bool power_on)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
index 63eb377ed9c0..6bdfee20b6a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "reg_helper.h"
 #include "dcn20_dsc.h"
 #include "dsc/dscc_types.h"
@@ -207,6 +206,9 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str
 	struct dsc_reg_values dsc_reg_vals;
 	struct dsc_optc_config dsc_optc_cfg;
 
+	memset(&dsc_reg_vals, 0, sizeof(dsc_reg_vals));
+	memset(&dsc_optc_cfg, 0, sizeof(dsc_optc_cfg));
+
 	DC_LOG_DSC("Getting packed DSC PPS for DSC Config:");
 	dsc_config_log(dsc, dsc_cfg);
 	DC_LOG_DSC("DSC Picture Parameter Set (PPS):");
@@ -222,9 +224,18 @@ static bool dsc2_get_packed_pps(struct display_stream_compressor *dsc, const str
 static void dsc2_enable(struct display_stream_compressor *dsc, int opp_pipe)
 {
 	struct dcn20_dsc *dsc20 = TO_DCN20_DSC(dsc);
+	int dsc_clock_en;
+	int dsc_fw_config;
+	int enabled_opp_pipe;
+
+	DC_LOG_DSC("enable DSC %d at opp pipe %d", dsc->inst, opp_pipe);
 
-	/* TODO Check if DSC alreay in use? */
-	DC_LOG_DSC("enable DSC at opp pipe %d", opp_pipe);
+	REG_GET(DSC_TOP_CONTROL, DSC_CLOCK_EN, &dsc_clock_en);
+	REG_GET_2(DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, &dsc_fw_config, DSCRM_DSC_OPP_PIPE_SOURCE, &enabled_opp_pipe);
+	if ((dsc_clock_en || dsc_fw_config) && enabled_opp_pipe != opp_pipe) {
+		DC_LOG_DSC("ERROR: DSC %d at opp pipe %d already enabled!", dsc->inst, enabled_opp_pipe);
+		ASSERT(0);
+	}
 
 	REG_UPDATE(DSC_TOP_CONTROL,
 		DSC_CLOCK_EN, 1);
@@ -238,8 +249,18 @@ static void dsc2_enable(struct display_stream_compressor *dsc, int opp_pipe)
 static void dsc2_disable(struct display_stream_compressor *dsc)
 {
 	struct dcn20_dsc *dsc20 = TO_DCN20_DSC(dsc);
+	int dsc_clock_en;
+	int dsc_fw_config;
+	int enabled_opp_pipe;
 
-	DC_LOG_DSC("disable DSC");
+	DC_LOG_DSC("disable DSC %d", dsc->inst);
+
+	REG_GET(DSC_TOP_CONTROL, DSC_CLOCK_EN, &dsc_clock_en);
+	REG_GET_2(DSCRM_DSC_FORWARD_CONFIG, DSCRM_DSC_FORWARD_EN, &dsc_fw_config, DSCRM_DSC_OPP_PIPE_SOURCE, &enabled_opp_pipe);
+	if (!dsc_clock_en || !dsc_fw_config) {
+		DC_LOG_DSC("ERROR: DSC %d at opp pipe %d already disabled!", dsc->inst, enabled_opp_pipe);
+		ASSERT(0);
+	}
 
 	REG_UPDATE(DSCRM_DSC_FORWARD_CONFIG,
 		DSCRM_DSC_FORWARD_EN, 0);
@@ -715,4 +736,3 @@ static void dsc_write_to_registers(struct display_stream_compressor *dsc, const
 	}
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
index 4e2fb38390a4..9855a7ed0387 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.h
@@ -21,7 +21,6 @@
  * Authors: AMD
  *
  */
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #ifndef __DCN20_DSC_H__
 #define __DCN20_DSC_H__
 
@@ -572,4 +571,3 @@ void dsc2_construct(struct dcn20_dsc *dsc,
 
 #endif
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
index 8b8438566101..9235f7d29454 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
@@ -293,6 +293,9 @@ bool hubbub2_get_dcc_compression_cap(struct hubbub *hubbub,
 		output->grph.rgb.max_compressed_blk_size = 64;
 		output->grph.rgb.independent_64b_blks = true;
 		break;
+	default:
+		ASSERT(false);
+		break;
 	}
 	output->capable = true;
 	output->const_color_support = true;
@@ -601,7 +604,8 @@ static const struct hubbub_funcs hubbub2_funcs = {
 	.wm_read_state = hubbub2_wm_read_state,
 	.get_dchub_ref_freq = hubbub2_get_dchub_ref_freq,
 	.program_watermarks = hubbub2_program_watermarks,
-	.allow_self_refresh_control = hubbub1_allow_self_refresh_control
+	.is_allow_self_refresh_enabled = hubbub1_is_allow_self_refresh_enabled,
+	.allow_self_refresh_control = hubbub1_allow_self_refresh_control,
 };
 
 void hubbub2_construct(struct dcn20_hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 69e2aae42394..84d7ac5dd206 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -30,6 +30,8 @@
 #include "reg_helper.h"
 #include "basics/conversion.h"
 
+#define DC_LOGGER_INIT(logger)
+
 #define REG(reg)\
 	hubp2->hubp_regs->reg
 
@@ -483,7 +485,6 @@ void hubp2_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 12);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX:
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 112);
@@ -504,7 +505,6 @@ void hubp2_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 119);
 		break;
-#endif
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
@@ -1204,6 +1204,9 @@ void hubp2_read_state_common(struct hubp *hubp)
 			HUBP_TTU_DISABLE, &s->ttu_disable,
 			HUBP_UNDERFLOW_STATUS, &s->underflow_status);
 
+	REG_GET(HUBP_CLK_CNTL,
+			HUBP_CLOCK_ENABLE, &s->clock_en);
+
 	REG_GET(DCN_GLOBAL_TTU_CNTL,
 			MIN_TTU_VBLANK, &s->min_ttu_vblank);
 
@@ -1243,6 +1246,314 @@ void hubp2_read_state(struct hubp *hubp)
 
 }
 
+void hubp2_validate_dml_output(struct hubp *hubp,
+		struct dc_context *ctx,
+		struct _vcs_dpi_display_rq_regs_st *dml_rq_regs,
+		struct _vcs_dpi_display_dlg_regs_st *dml_dlg_attr,
+		struct _vcs_dpi_display_ttu_regs_st *dml_ttu_attr)
+{
+	struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp);
+	struct _vcs_dpi_display_rq_regs_st rq_regs = {0};
+	struct _vcs_dpi_display_dlg_regs_st dlg_attr = {0};
+	struct _vcs_dpi_display_ttu_regs_st ttu_attr = {0};
+	DC_LOGGER_INIT(ctx->logger);
+	DC_LOG_DEBUG("DML Validation | Running Validation");
+
+	/* Requestor Regs */
+	REG_GET(HUBPRET_CONTROL,
+		DET_BUF_PLANE1_BASE_ADDRESS, &rq_regs.plane1_base_address);
+	REG_GET_4(DCN_EXPANSION_MODE,
+		DRQ_EXPANSION_MODE, &rq_regs.drq_expansion_mode,
+		PRQ_EXPANSION_MODE, &rq_regs.prq_expansion_mode,
+		MRQ_EXPANSION_MODE, &rq_regs.mrq_expansion_mode,
+		CRQ_EXPANSION_MODE, &rq_regs.crq_expansion_mode);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG,
+		CHUNK_SIZE, &rq_regs.rq_regs_l.chunk_size,
+		MIN_CHUNK_SIZE, &rq_regs.rq_regs_l.min_chunk_size,
+		META_CHUNK_SIZE, &rq_regs.rq_regs_l.meta_chunk_size,
+		MIN_META_CHUNK_SIZE, &rq_regs.rq_regs_l.min_meta_chunk_size,
+		DPTE_GROUP_SIZE, &rq_regs.rq_regs_l.dpte_group_size,
+		MPTE_GROUP_SIZE, &rq_regs.rq_regs_l.mpte_group_size,
+		SWATH_HEIGHT, &rq_regs.rq_regs_l.swath_height,
+		PTE_ROW_HEIGHT_LINEAR, &rq_regs.rq_regs_l.pte_row_height_linear);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG_C,
+		CHUNK_SIZE_C, &rq_regs.rq_regs_c.chunk_size,
+		MIN_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_chunk_size,
+		META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.meta_chunk_size,
+		MIN_META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_meta_chunk_size,
+		DPTE_GROUP_SIZE_C, &rq_regs.rq_regs_c.dpte_group_size,
+		MPTE_GROUP_SIZE_C, &rq_regs.rq_regs_c.mpte_group_size,
+		SWATH_HEIGHT_C, &rq_regs.rq_regs_c.swath_height,
+		PTE_ROW_HEIGHT_LINEAR_C, &rq_regs.rq_regs_c.pte_row_height_linear);
+
+	if (rq_regs.plane1_base_address != dml_rq_regs->plane1_base_address)
+		DC_LOG_DEBUG("DML Validation | HUBPRET_CONTROL:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->plane1_base_address, rq_regs.plane1_base_address);
+	if (rq_regs.drq_expansion_mode != dml_rq_regs->drq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->drq_expansion_mode, rq_regs.drq_expansion_mode);
+	if (rq_regs.prq_expansion_mode != dml_rq_regs->prq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:MRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->prq_expansion_mode, rq_regs.prq_expansion_mode);
+	if (rq_regs.mrq_expansion_mode != dml_rq_regs->mrq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->mrq_expansion_mode, rq_regs.mrq_expansion_mode);
+	if (rq_regs.crq_expansion_mode != dml_rq_regs->crq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:CRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->crq_expansion_mode, rq_regs.crq_expansion_mode);
+
+	if (rq_regs.rq_regs_l.chunk_size != dml_rq_regs->rq_regs_l.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.chunk_size, rq_regs.rq_regs_l.chunk_size);
+	if (rq_regs.rq_regs_l.min_chunk_size != dml_rq_regs->rq_regs_l.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_chunk_size, rq_regs.rq_regs_l.min_chunk_size);
+	if (rq_regs.rq_regs_l.meta_chunk_size != dml_rq_regs->rq_regs_l.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.meta_chunk_size, rq_regs.rq_regs_l.meta_chunk_size);
+	if (rq_regs.rq_regs_l.min_meta_chunk_size != dml_rq_regs->rq_regs_l.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs.rq_regs_l.min_meta_chunk_size);
+	if (rq_regs.rq_regs_l.dpte_group_size != dml_rq_regs->rq_regs_l.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:DPTE_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.dpte_group_size, rq_regs.rq_regs_l.dpte_group_size);
+	if (rq_regs.rq_regs_l.mpte_group_size != dml_rq_regs->rq_regs_l.mpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MPTE_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.mpte_group_size, rq_regs.rq_regs_l.mpte_group_size);
+	if (rq_regs.rq_regs_l.swath_height != dml_rq_regs->rq_regs_l.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:SWATH_HEIGHT - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.swath_height, rq_regs.rq_regs_l.swath_height);
+	if (rq_regs.rq_regs_l.pte_row_height_linear != dml_rq_regs->rq_regs_l.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:PTE_ROW_HEIGHT_LINEAR - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.pte_row_height_linear, rq_regs.rq_regs_l.pte_row_height_linear);
+
+	if (rq_regs.rq_regs_c.chunk_size != dml_rq_regs->rq_regs_c.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.chunk_size, rq_regs.rq_regs_c.chunk_size);
+	if (rq_regs.rq_regs_c.min_chunk_size != dml_rq_regs->rq_regs_c.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_chunk_size, rq_regs.rq_regs_c.min_chunk_size);
+	if (rq_regs.rq_regs_c.meta_chunk_size != dml_rq_regs->rq_regs_c.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.meta_chunk_size, rq_regs.rq_regs_c.meta_chunk_size);
+	if (rq_regs.rq_regs_c.min_meta_chunk_size != dml_rq_regs->rq_regs_c.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_meta_chunk_size, rq_regs.rq_regs_c.min_meta_chunk_size);
+	if (rq_regs.rq_regs_c.dpte_group_size != dml_rq_regs->rq_regs_c.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:DPTE_GROUP_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.dpte_group_size, rq_regs.rq_regs_c.dpte_group_size);
+	if (rq_regs.rq_regs_c.mpte_group_size != dml_rq_regs->rq_regs_c.mpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MPTE_GROUP_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.mpte_group_size, rq_regs.rq_regs_c.mpte_group_size);
+	if (rq_regs.rq_regs_c.swath_height != dml_rq_regs->rq_regs_c.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:SWATH_HEIGHT_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.swath_height, rq_regs.rq_regs_c.swath_height);
+	if (rq_regs.rq_regs_c.pte_row_height_linear != dml_rq_regs->rq_regs_c.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:PTE_ROW_HEIGHT_LINEAR_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.pte_row_height_linear, rq_regs.rq_regs_c.pte_row_height_linear);
+
+	/* DLG - Per hubp */
+	REG_GET_2(BLANK_OFFSET_0,
+		REFCYC_H_BLANK_END, &dlg_attr.refcyc_h_blank_end,
+		DLG_V_BLANK_END, &dlg_attr.dlg_vblank_end);
+	REG_GET(BLANK_OFFSET_1,
+		MIN_DST_Y_NEXT_START, &dlg_attr.min_dst_y_next_start);
+	REG_GET(DST_DIMENSIONS,
+		REFCYC_PER_HTOTAL, &dlg_attr.refcyc_per_htotal);
+	REG_GET_2(DST_AFTER_SCALER,
+		REFCYC_X_AFTER_SCALER, &dlg_attr.refcyc_x_after_scaler,
+		DST_Y_AFTER_SCALER, &dlg_attr.dst_y_after_scaler);
+	REG_GET(REF_FREQ_TO_PIX_FREQ,
+		REF_FREQ_TO_PIX_FREQ, &dlg_attr.ref_freq_to_pix_freq);
+
+	if (dlg_attr.refcyc_h_blank_end != dml_dlg_attr->refcyc_h_blank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:REFCYC_H_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_h_blank_end, dlg_attr.refcyc_h_blank_end);
+	if (dlg_attr.dlg_vblank_end != dml_dlg_attr->dlg_vblank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:DLG_V_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dlg_vblank_end, dlg_attr.dlg_vblank_end);
+	if (dlg_attr.min_dst_y_next_start != dml_dlg_attr->min_dst_y_next_start)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_1:MIN_DST_Y_NEXT_START - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->min_dst_y_next_start, dlg_attr.min_dst_y_next_start);
+	if (dlg_attr.refcyc_per_htotal != dml_dlg_attr->refcyc_per_htotal)
+		DC_LOG_DEBUG("DML Validation | DST_DIMENSIONS:REFCYC_PER_HTOTAL - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_htotal, dlg_attr.refcyc_per_htotal);
+	if (dlg_attr.refcyc_x_after_scaler != dml_dlg_attr->refcyc_x_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:REFCYC_X_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_x_after_scaler, dlg_attr.refcyc_x_after_scaler);
+	if (dlg_attr.dst_y_after_scaler != dml_dlg_attr->dst_y_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:DST_Y_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_after_scaler, dlg_attr.dst_y_after_scaler);
+	if (dlg_attr.ref_freq_to_pix_freq != dml_dlg_attr->ref_freq_to_pix_freq)
+		DC_LOG_DEBUG("DML Validation | REF_FREQ_TO_PIX_FREQ:REF_FREQ_TO_PIX_FREQ - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->ref_freq_to_pix_freq, dlg_attr.ref_freq_to_pix_freq);
+
+	/* DLG - Per luma/chroma */
+	REG_GET(VBLANK_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_VBLANK_L, &dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (REG(NOM_PARAMETERS_0))
+		REG_GET(NOM_PARAMETERS_0,
+			DST_Y_PER_PTE_ROW_NOM_L, &dlg_attr.dst_y_per_pte_row_nom_l);
+	if (REG(NOM_PARAMETERS_1))
+		REG_GET(NOM_PARAMETERS_1,
+			REFCYC_PER_PTE_GROUP_NOM_L, &dlg_attr.refcyc_per_pte_group_nom_l);
+	REG_GET(NOM_PARAMETERS_4,
+		DST_Y_PER_META_ROW_NOM_L, &dlg_attr.dst_y_per_meta_row_nom_l);
+	REG_GET(NOM_PARAMETERS_5,
+		REFCYC_PER_META_CHUNK_NOM_L, &dlg_attr.refcyc_per_meta_chunk_nom_l);
+	REG_GET_2(PER_LINE_DELIVERY,
+		REFCYC_PER_LINE_DELIVERY_L, &dlg_attr.refcyc_per_line_delivery_l,
+		REFCYC_PER_LINE_DELIVERY_C, &dlg_attr.refcyc_per_line_delivery_c);
+	REG_GET_2(PER_LINE_DELIVERY_PRE,
+		REFCYC_PER_LINE_DELIVERY_PRE_L, &dlg_attr.refcyc_per_line_delivery_pre_l,
+		REFCYC_PER_LINE_DELIVERY_PRE_C, &dlg_attr.refcyc_per_line_delivery_pre_c);
+	REG_GET(VBLANK_PARAMETERS_2,
+		REFCYC_PER_PTE_GROUP_VBLANK_C, &dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (REG(NOM_PARAMETERS_2))
+		REG_GET(NOM_PARAMETERS_2,
+			DST_Y_PER_PTE_ROW_NOM_C, &dlg_attr.dst_y_per_pte_row_nom_c);
+	if (REG(NOM_PARAMETERS_3))
+		REG_GET(NOM_PARAMETERS_3,
+			REFCYC_PER_PTE_GROUP_NOM_C, &dlg_attr.refcyc_per_pte_group_nom_c);
+	REG_GET(NOM_PARAMETERS_6,
+		DST_Y_PER_META_ROW_NOM_C, &dlg_attr.dst_y_per_meta_row_nom_c);
+	REG_GET(NOM_PARAMETERS_7,
+		REFCYC_PER_META_CHUNK_NOM_C, &dlg_attr.refcyc_per_meta_chunk_nom_c);
+	REG_GET(VBLANK_PARAMETERS_3,
+			REFCYC_PER_META_CHUNK_VBLANK_L, &dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	REG_GET(VBLANK_PARAMETERS_4,
+			REFCYC_PER_META_CHUNK_VBLANK_C, &dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	if (dlg_attr.refcyc_per_pte_group_vblank_l != dml_dlg_attr->refcyc_per_pte_group_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_1:REFCYC_PER_PTE_GROUP_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_l, dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (dlg_attr.dst_y_per_pte_row_nom_l != dml_dlg_attr->dst_y_per_pte_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_0:DST_Y_PER_PTE_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_l, dlg_attr.dst_y_per_pte_row_nom_l);
+	if (dlg_attr.refcyc_per_pte_group_nom_l != dml_dlg_attr->refcyc_per_pte_group_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_1:REFCYC_PER_PTE_GROUP_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_l, dlg_attr.refcyc_per_pte_group_nom_l);
+	if (dlg_attr.dst_y_per_meta_row_nom_l != dml_dlg_attr->dst_y_per_meta_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_4:DST_Y_PER_META_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_l, dlg_attr.dst_y_per_meta_row_nom_l);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_l != dml_dlg_attr->refcyc_per_meta_chunk_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_5:REFCYC_PER_META_CHUNK_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_l, dlg_attr.refcyc_per_meta_chunk_nom_l);
+	if (dlg_attr.refcyc_per_line_delivery_l != dml_dlg_attr->refcyc_per_line_delivery_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_l, dlg_attr.refcyc_per_line_delivery_l);
+	if (dlg_attr.refcyc_per_line_delivery_c != dml_dlg_attr->refcyc_per_line_delivery_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_c, dlg_attr.refcyc_per_line_delivery_c);
+	if (dlg_attr.refcyc_per_pte_group_vblank_c != dml_dlg_attr->refcyc_per_pte_group_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_2:REFCYC_PER_PTE_GROUP_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_c, dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (dlg_attr.dst_y_per_pte_row_nom_c != dml_dlg_attr->dst_y_per_pte_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_2:DST_Y_PER_PTE_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_c, dlg_attr.dst_y_per_pte_row_nom_c);
+	if (dlg_attr.refcyc_per_pte_group_nom_c != dml_dlg_attr->refcyc_per_pte_group_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_3:REFCYC_PER_PTE_GROUP_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_c, dlg_attr.refcyc_per_pte_group_nom_c);
+	if (dlg_attr.dst_y_per_meta_row_nom_c != dml_dlg_attr->dst_y_per_meta_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_6:DST_Y_PER_META_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_c, dlg_attr.dst_y_per_meta_row_nom_c);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_c != dml_dlg_attr->refcyc_per_meta_chunk_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_7:REFCYC_PER_META_CHUNK_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_c, dlg_attr.refcyc_per_meta_chunk_nom_c);
+	if (dlg_attr.refcyc_per_line_delivery_pre_l != dml_dlg_attr->refcyc_per_line_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_l, dlg_attr.refcyc_per_line_delivery_pre_l);
+	if (dlg_attr.refcyc_per_line_delivery_pre_c != dml_dlg_attr->refcyc_per_line_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_c, dlg_attr.refcyc_per_line_delivery_pre_c);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_l != dml_dlg_attr->refcyc_per_meta_chunk_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_3:REFCYC_PER_META_CHUNK_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_l, dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_c != dml_dlg_attr->refcyc_per_meta_chunk_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_4:REFCYC_PER_META_CHUNK_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_c, dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	/* TTU - per hubp */
+	REG_GET_2(DCN_TTU_QOS_WM,
+		QoS_LEVEL_LOW_WM, &ttu_attr.qos_level_low_wm,
+		QoS_LEVEL_HIGH_WM, &ttu_attr.qos_level_high_wm);
+
+	if (ttu_attr.qos_level_low_wm != dml_ttu_attr->qos_level_low_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_LOW_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_low_wm, ttu_attr.qos_level_low_wm);
+	if (ttu_attr.qos_level_high_wm != dml_ttu_attr->qos_level_high_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_HIGH_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_high_wm, ttu_attr.qos_level_high_wm);
+
+	/* TTU - per luma/chroma */
+	/* Assumed surf0 is luma and 1 is chroma */
+	REG_GET_3(DCN_SURF0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_l,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_l,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_l);
+	REG_GET_3(DCN_SURF1_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_c,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_c,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_c);
+	REG_GET_3(DCN_CUR0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_cur0,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_cur0,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_cur0);
+	REG_GET(FLIP_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_FLIP_L, &dlg_attr.refcyc_per_pte_group_flip_l);
+	REG_GET(DCN_CUR0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	REG_GET(DCN_CUR1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	REG_GET(DCN_SURF0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_l);
+	REG_GET(DCN_SURF1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_c);
+
+	if (ttu_attr.refcyc_per_req_delivery_l != dml_ttu_attr->refcyc_per_req_delivery_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_l, ttu_attr.refcyc_per_req_delivery_l);
+	if (ttu_attr.qos_level_fixed_l != dml_ttu_attr->qos_level_fixed_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_l, ttu_attr.qos_level_fixed_l);
+	if (ttu_attr.qos_ramp_disable_l != dml_ttu_attr->qos_ramp_disable_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_l, ttu_attr.qos_ramp_disable_l);
+	if (ttu_attr.refcyc_per_req_delivery_c != dml_ttu_attr->refcyc_per_req_delivery_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_c, ttu_attr.refcyc_per_req_delivery_c);
+	if (ttu_attr.qos_level_fixed_c != dml_ttu_attr->qos_level_fixed_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_c, ttu_attr.qos_level_fixed_c);
+	if (ttu_attr.qos_ramp_disable_c != dml_ttu_attr->qos_ramp_disable_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_c, ttu_attr.qos_ramp_disable_c);
+	if (ttu_attr.refcyc_per_req_delivery_cur0 != dml_ttu_attr->refcyc_per_req_delivery_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_cur0, ttu_attr.refcyc_per_req_delivery_cur0);
+	if (ttu_attr.qos_level_fixed_cur0 != dml_ttu_attr->qos_level_fixed_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_cur0, ttu_attr.qos_level_fixed_cur0);
+	if (ttu_attr.qos_ramp_disable_cur0 != dml_ttu_attr->qos_ramp_disable_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_cur0, ttu_attr.qos_ramp_disable_cur0);
+	if (dlg_attr.refcyc_per_pte_group_flip_l != dml_dlg_attr->refcyc_per_pte_group_flip_l)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_1:REFCYC_PER_PTE_GROUP_FLIP_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_flip_l, dlg_attr.refcyc_per_pte_group_flip_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur0 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur0, ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur1 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur1)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur1, ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	if (ttu_attr.refcyc_per_req_delivery_pre_l != dml_ttu_attr->refcyc_per_req_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_l, ttu_attr.refcyc_per_req_delivery_pre_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_c != dml_ttu_attr->refcyc_per_req_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_c, ttu_attr.refcyc_per_req_delivery_pre_c);
+}
+
 static struct hubp_funcs dcn20_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
@@ -1266,6 +1577,7 @@ static struct hubp_funcs dcn20_hubp_funcs = {
 	.hubp_clear_underflow = hubp2_clear_underflow,
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp1_init,
+	.validate_dml_output = hubp2_validate_dml_output,
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h
index d5c8615af45e..8c04a3606a54 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h
@@ -148,7 +148,6 @@
 	uint32_t VMID_SETTINGS_0
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define DCN21_HUBP_REG_COMMON_VARIABLE_LIST \
 	DCN2_HUBP_REG_COMMON_VARIABLE_LIST; \
 	uint32_t FLIP_PARAMETERS_3;\
@@ -157,7 +156,6 @@
 	uint32_t FLIP_PARAMETERS_6;\
 	uint32_t VBLANK_PARAMETERS_5;\
 	uint32_t VBLANK_PARAMETERS_6
-#endif
 
 #define DCN2_HUBP_REG_FIELD_VARIABLE_LIST(type) \
 	DCN_HUBP_REG_FIELD_BASE_LIST(type); \
@@ -184,7 +182,6 @@
 	type SURFACE_TRIPLE_BUFFER_ENABLE;\
 	type VMID
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 #define DCN21_HUBP_REG_FIELD_VARIABLE_LIST(type) \
 	DCN2_HUBP_REG_FIELD_VARIABLE_LIST(type);\
 	type REFCYC_PER_VM_GROUP_FLIP;\
@@ -194,31 +191,18 @@
 	type REFCYC_PER_PTE_GROUP_FLIP_C; \
 	type REFCYC_PER_META_CHUNK_FLIP_C; \
 	type VM_GROUP_SIZE
-#endif
 
 
 struct dcn_hubp2_registers {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN21_HUBP_REG_COMMON_VARIABLE_LIST;
-#else
-	DCN2_HUBP_REG_COMMON_VARIABLE_LIST;
-#endif
 };
 
 struct dcn_hubp2_shift {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN21_HUBP_REG_FIELD_VARIABLE_LIST(uint8_t);
-#else
-	DCN2_HUBP_REG_FIELD_VARIABLE_LIST(uint8_t);
-#endif
 };
 
 struct dcn_hubp2_mask {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN21_HUBP_REG_FIELD_VARIABLE_LIST(uint32_t);
-#else
-	DCN2_HUBP_REG_FIELD_VARIABLE_LIST(uint32_t);
-#endif
 };
 
 struct dcn20_hubp {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index ac8c18fadefc..cfbbaffa8654 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -25,17 +25,15 @@
 #include <linux/delay.h>
 
 #include "dm_services.h"
+#include "basics/dc_common.h"
 #include "dm_helpers.h"
 #include "core_types.h"
 #include "resource.h"
-#include "dcn20/dcn20_resource.h"
-#include "dce110/dce110_hw_sequencer.h"
-#include "dcn10/dcn10_hw_sequencer.h"
+#include "dcn20_resource.h"
 #include "dcn20_hwseq.h"
 #include "dce/dce_hwseq.h"
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-#include "dcn20/dcn20_dsc.h"
-#endif
+#include "dcn20_dsc.h"
+#include "dcn20_optc.h"
 #include "abm.h"
 #include "clk_mgr.h"
 #include "dmcu.h"
@@ -45,10 +43,9 @@
 #include "ipp.h"
 #include "mpc.h"
 #include "mcif_wb.h"
+#include "dchubbub.h"
 #include "reg_helper.h"
 #include "dcn10/dcn10_cm_common.h"
-#include "dcn10/dcn10_hubbub.h"
-#include "dcn10/dcn10_optc.h"
 #include "dc_link_dp.h"
 #include "vm_helper.h"
 #include "dccg.h"
@@ -64,14 +61,132 @@
 #define FN(reg_name, field_name) \
 	hws->shifts->field_name, hws->masks->field_name
 
-static void dcn20_enable_power_gating_plane(
+static int find_free_gsl_group(const struct dc *dc)
+{
+	if (dc->res_pool->gsl_groups.gsl_0 == 0)
+		return 1;
+	if (dc->res_pool->gsl_groups.gsl_1 == 0)
+		return 2;
+	if (dc->res_pool->gsl_groups.gsl_2 == 0)
+		return 3;
+
+	return 0;
+}
+
+/* NOTE: This is not a generic setup_gsl function (hence the suffix as_lock)
+ * This is only used to lock pipes in pipe splitting case with immediate flip
+ * Ordinary MPC/OTG locks suppress VUPDATE which doesn't help with immediate,
+ * so we get tearing with freesync since we cannot flip multiple pipes
+ * atomically.
+ * We use GSL for this:
+ * - immediate flip: find first available GSL group if not already assigned
+ *                   program gsl with that group, set current OTG as master
+ *                   and always us 0x4 = AND of flip_ready from all pipes
+ * - vsync flip: disable GSL if used
+ *
+ * Groups in stream_res are stored as +1 from HW registers, i.e.
+ * gsl_0 <=> pipe_ctx->stream_res.gsl_group == 1
+ * Using a magic value like -1 would require tracking all inits/resets
+ */
+static void dcn20_setup_gsl_group_as_lock(
+		const struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		bool enable)
+{
+	struct gsl_params gsl;
+	int group_idx;
+
+	memset(&gsl, 0, sizeof(struct gsl_params));
+
+	if (enable) {
+		/* return if group already assigned since GSL was set up
+		 * for vsync flip, we would unassign so it can't be "left over"
+		 */
+		if (pipe_ctx->stream_res.gsl_group > 0)
+			return;
+
+		group_idx = find_free_gsl_group(dc);
+		ASSERT(group_idx != 0);
+		pipe_ctx->stream_res.gsl_group = group_idx;
+
+		/* set gsl group reg field and mark resource used */
+		switch (group_idx) {
+		case 1:
+			gsl.gsl0_en = 1;
+			dc->res_pool->gsl_groups.gsl_0 = 1;
+			break;
+		case 2:
+			gsl.gsl1_en = 1;
+			dc->res_pool->gsl_groups.gsl_1 = 1;
+			break;
+		case 3:
+			gsl.gsl2_en = 1;
+			dc->res_pool->gsl_groups.gsl_2 = 1;
+			break;
+		default:
+			BREAK_TO_DEBUGGER();
+			return; // invalid case
+		}
+		gsl.gsl_master_en = 1;
+	} else {
+		group_idx = pipe_ctx->stream_res.gsl_group;
+		if (group_idx == 0)
+			return; // if not in use, just return
+
+		pipe_ctx->stream_res.gsl_group = 0;
+
+		/* unset gsl group reg field and mark resource free */
+		switch (group_idx) {
+		case 1:
+			gsl.gsl0_en = 0;
+			dc->res_pool->gsl_groups.gsl_0 = 0;
+			break;
+		case 2:
+			gsl.gsl1_en = 0;
+			dc->res_pool->gsl_groups.gsl_1 = 0;
+			break;
+		case 3:
+			gsl.gsl2_en = 0;
+			dc->res_pool->gsl_groups.gsl_2 = 0;
+			break;
+		default:
+			BREAK_TO_DEBUGGER();
+			return;
+		}
+		gsl.gsl_master_en = 0;
+	}
+
+	/* at this point we want to program whether it's to enable or disable */
+	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL &&
+		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL) {
+		pipe_ctx->stream_res.tg->funcs->set_gsl(
+			pipe_ctx->stream_res.tg,
+			&gsl);
+
+		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
+			pipe_ctx->stream_res.tg, group_idx,	enable ? 4 : 0);
+	} else
+		BREAK_TO_DEBUGGER();
+}
+
+void dcn20_set_flip_control_gsl(
+		struct pipe_ctx *pipe_ctx,
+		bool flip_immediate)
+{
+	if (pipe_ctx && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl)
+		pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl(
+				pipe_ctx->plane_res.hubp, flip_immediate);
+
+}
+
+void dcn20_enable_power_gating_plane(
 	struct dce_hwseq *hws,
 	bool enable)
 {
-	bool force_on = 1; /* disable power gating */
+	bool force_on = true; /* disable power gating */
 
 	if (enable)
-		force_on = 0;
+		force_on = false;
 
 	/* DCHUBP0/1/2/3/4/5 */
 	REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN0_POWER_FORCEON, force_on);
@@ -128,44 +243,6 @@ void dcn20_dccg_init(struct dce_hwseq *hws)
 	/* This value is dependent on the hardware pipeline delay so set once per SOC */
 	REG_WRITE(DISPCLK_FREQ_CHANGE_CNTL, 0x801003c);
 }
-void dcn20_display_init(struct dc *dc)
-{
-	struct dce_hwseq *hws = dc->hwseq;
-
-	/* RBBMIF
-	 * disable RBBMIF timeout detection for all clients
-	 * Ensure RBBMIF does not drop register accesses due to the per-client timeout
-	 */
-	REG_WRITE(RBBMIF_TIMEOUT_DIS, 0xFFFFFFFF);
-	REG_WRITE(RBBMIF_TIMEOUT_DIS_2, 0xFFFFFFFF);
-
-	/* DCCG */
-	dcn20_dccg_init(hws);
-
-	REG_UPDATE(DC_MEM_GLOBAL_PWR_REQ_CNTL, DC_MEM_GLOBAL_PWR_REQ_DIS, 0);
-
-	/* DCHUB/MMHUBBUB
-	 * set global timer refclk divider
-	 * 100Mhz refclk -> 2
-	 * 27Mhz refclk ->  1
-	 * 48Mhz refclk ->  1
-	 */
-	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2);
-	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
-	REG_WRITE(REFCLK_CNTL, 0);
-
-	/* OPTC
-	 * OTG_CONTROL.OTG_DISABLE_POINT_CNTL = 0x3; will be set during optc2_enable_crtc
-	 */
-
-	/* AZ
-	 * default value is 0x64 for 100Mhz ref clock, if the ref clock is 100Mhz, no need to program this regiser,
-	 * if not, it should be programmed according to the ref clock
-	 */
-	REG_UPDATE(AZALIA_AUDIO_DTO, AZALIA_AUDIO_DTO_MODULE, 0x64);
-	/* Enable controller clock gating */
-	REG_WRITE(AZALIA_CONTROLLER_CLOCK_GATING, 0x1);
-}
 
 void dcn20_disable_vga(
 	struct dce_hwseq *hws)
@@ -178,15 +255,15 @@ void dcn20_disable_vga(
 	REG_WRITE(D6VGA_CONTROL, 0);
 }
 
-void dcn20_program_tripleBuffer(
+void dcn20_program_triple_buffer(
 	const struct dc *dc,
 	struct pipe_ctx *pipe_ctx,
-	bool enableTripleBuffer)
+	bool enable_triple_buffer)
 {
 	if (pipe_ctx->plane_res.hubp && pipe_ctx->plane_res.hubp->funcs) {
 		pipe_ctx->plane_res.hubp->funcs->hubp_enable_tripleBuffer(
 			pipe_ctx->plane_res.hubp,
-			enableTripleBuffer);
+			enable_triple_buffer);
 	}
 }
 
@@ -195,6 +272,7 @@ void dcn20_init_blank(
 		struct dc *dc,
 		struct timing_generator *tg)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	enum dc_color_space color_space;
 	struct tg_color black_color = {0};
 	struct output_pixel_processor *opp = NULL;
@@ -225,6 +303,7 @@ void dcn20_init_blank(
 	opp->funcs->opp_set_disp_pattern_generator(
 			opp,
 			CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR,
+			CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 			COLOR_DEPTH_UNDEFINED,
 			&black_color,
 			otg_active_width,
@@ -234,17 +313,17 @@ void dcn20_init_blank(
 		bottom_opp->funcs->opp_set_disp_pattern_generator(
 				bottom_opp,
 				CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR,
+				CONTROLLER_DP_COLOR_SPACE_UDEFINED,
 				COLOR_DEPTH_UNDEFINED,
 				&black_color,
 				otg_active_width,
 				otg_active_height);
 	}
 
-	dcn20_hwss_wait_for_blank_complete(opp);
+	hws->funcs.wait_for_blank_complete(opp);
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-static void dcn20_dsc_pg_control(
+void dcn20_dsc_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dsc_inst,
 		bool power_on)
@@ -320,9 +399,8 @@ static void dcn20_dsc_pg_control(
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0);
 }
-#endif
 
-static void dcn20_dpp_pg_control(
+void dcn20_dpp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int dpp_inst,
 		bool power_on)
@@ -396,7 +474,7 @@ static void dcn20_dpp_pg_control(
 }
 
 
-static void dcn20_hubp_pg_control(
+void dcn20_hubp_pg_control(
 		struct dce_hwseq *hws,
 		unsigned int hubp_inst,
 		bool power_on)
@@ -473,8 +551,9 @@ static void dcn20_hubp_pg_control(
 /* disable HW used by plane.
  * note:  cannot disable until disconnect is complete
  */
-static void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 
@@ -495,7 +574,7 @@ static void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	hubp->power_gated = true;
 	dc->optimized_required = false; /* We're powering off, no need to optimize */
 
-	dc->hwss.plane_atomic_power_down(dc,
+	hws->funcs.plane_atomic_power_down(dc,
 			pipe_ctx->plane_res.dpp,
 			pipe_ctx->plane_res.hubp);
 
@@ -526,6 +605,7 @@ enum dc_status dcn20_enable_stream_timing(
 		struct dc_state *context,
 		struct dc *dc)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct drr_params params = {0};
 	unsigned int event_triggers = 0;
@@ -585,7 +665,7 @@ enum dc_status dcn20_enable_stream_timing(
 			pipe_ctx->stream_res.opp,
 			true);
 
-	dc->hwss.blank_pixel_data(dc, pipe_ctx, true);
+	hws->funcs.blank_pixel_data(dc, pipe_ctx, true);
 
 	/* VTG is  within DCHUB command block. DCFCLK is always on */
 	if (false == pipe_ctx->stream_res.tg->funcs->enable_crtc(pipe_ctx->stream_res.tg)) {
@@ -593,7 +673,7 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
-	dcn20_hwss_wait_for_blank_complete(pipe_ctx->stream_res.opp);
+	hws->funcs.wait_for_blank_complete(pipe_ctx->stream_res.opp);
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
@@ -606,9 +686,13 @@ enum dc_status dcn20_enable_stream_timing(
 	// DRR should set trigger event to monitor surface update event
 	if (stream->adjust.v_total_min != 0 && stream->adjust.v_total_max != 0)
 		event_triggers = 0x80;
+	/* Event triggers and num frames initialized for DRR, but can be
+	 * later updated for PSR use. Note DRR trigger events are generated
+	 * regardless of whether num frames met.
+	 */
 	if (pipe_ctx->stream_res.tg->funcs->set_static_screen_control)
 		pipe_ctx->stream_res.tg->funcs->set_static_screen_control(
-				pipe_ctx->stream_res.tg, event_triggers);
+				pipe_ctx->stream_res.tg, event_triggers, 2);
 
 	/* TODO program crtc source select for non-virtual signal*/
 	/* TODO program FMT */
@@ -649,7 +733,7 @@ void dcn20_program_output_csc(struct dc *dc,
 	}
 }
 
-bool dcn20_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
+bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 				const struct dc_stream_state *stream)
 {
 	int mpcc_id = pipe_ctx->plane_res.hubp->inst;
@@ -736,20 +820,14 @@ bool dcn20_set_shaper_3dlut(
 	else
 		result = dpp_base->funcs->dpp_program_3dlut(dpp_base, NULL);
 
-	if (plane_state->lut3d_func &&
-		plane_state->lut3d_func->state.bits.initialized == 1 &&
-		plane_state->lut3d_func->hdr_multiplier != 0)
-		dpp_base->funcs->dpp_set_hdr_multiplier(dpp_base,
-				plane_state->lut3d_func->hdr_multiplier);
-	else
-		dpp_base->funcs->dpp_set_hdr_multiplier(dpp_base, 0x1f000);
-
 	return result;
 }
 
-bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
-					  const struct dc_plane_state *plane_state)
+bool dcn20_set_input_transfer_func(struct dc *dc,
+				struct pipe_ctx *pipe_ctx,
+				const struct dc_plane_state *plane_state)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
 	const struct dc_transfer_func *tf = NULL;
 	bool result = true;
@@ -758,8 +836,8 @@ bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	if (dpp_base == NULL || plane_state == NULL)
 		return false;
 
-	dcn20_set_shaper_3dlut(pipe_ctx, plane_state);
-	dcn20_set_blend_lut(pipe_ctx, plane_state);
+	hws->funcs.set_shaper_3dlut(pipe_ctx, plane_state);
+	hws->funcs.set_blend_lut(pipe_ctx, plane_state);
 
 	if (plane_state->in_transfer_func)
 		tf = plane_state->in_transfer_func;
@@ -804,6 +882,11 @@ bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 					IPP_DEGAMMA_MODE_BYPASS);
 			break;
 		case TRANSFER_FUNCTION_PQ:
+			dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_USER_PWL);
+			cm_helper_translate_curve_to_degamma_hw_format(tf, &dpp_base->degamma_params);
+			dpp_base->funcs->dpp_program_degamma_pwl(dpp_base, &dpp_base->degamma_params);
+			result = true;
+			break;
 		default:
 			result = false;
 			break;
@@ -824,7 +907,7 @@ bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	return result;
 }
 
-static void dcn20_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx)
+void dcn20_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx)
 {
 	struct pipe_ctx *odm_pipe;
 	int opp_cnt = 1;
@@ -855,12 +938,16 @@ void dcn20_blank_pixel_data(
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	enum dc_color_space color_space = stream->output_color_space;
 	enum controller_dp_test_pattern test_pattern = CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR;
+	enum controller_dp_color_space test_pattern_color_space = CONTROLLER_DP_COLOR_SPACE_UDEFINED;
 	struct pipe_ctx *odm_pipe;
 	int odm_cnt = 1;
 
 	int width = stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right;
 	int height = stream->timing.v_addressable + stream->timing.v_border_bottom + stream->timing.v_border_top;
 
+	if (stream->link->test_pattern_enabled)
+		return;
+
 	/* get opp dpg blank color */
 	color_space_to_black_color(dc, color_space, &black_color);
 
@@ -873,8 +960,10 @@ void dcn20_blank_pixel_data(
 		if (stream_res->abm)
 			stream_res->abm->funcs->set_abm_immediate_disable(stream_res->abm);
 
-		if (dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE)
+		if (dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 			test_pattern = CONTROLLER_DP_TEST_PATTERN_COLORSQUARES;
+			test_pattern_color_space = CONTROLLER_DP_COLOR_SPACE_RGB;
+		}
 	} else {
 		test_pattern = CONTROLLER_DP_TEST_PATTERN_VIDEOMODE;
 	}
@@ -882,6 +971,7 @@ void dcn20_blank_pixel_data(
 	stream_res->opp->funcs->opp_set_disp_pattern_generator(
 			stream_res->opp,
 			test_pattern,
+			test_pattern_color_space,
 			stream->timing.display_color_depth,
 			&black_color,
 			width,
@@ -892,6 +982,7 @@ void dcn20_blank_pixel_data(
 				odm_pipe->stream_res.opp,
 				dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE && blank ?
 						CONTROLLER_DP_TEST_PATTERN_COLORRAMP : test_pattern,
+				test_pattern_color_space,
 				stream->timing.display_color_depth,
 				&black_color,
 				width,
@@ -1217,9 +1308,11 @@ static void dcn20_update_dchubp_dpp(
 	struct pipe_ctx *pipe_ctx,
 	struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
+	bool viewport_changed = false;
 
 	if (pipe_ctx->update_flags.bits.dppclk)
 		dpp->funcs->dpp_dppclk_control(dpp, false, true);
@@ -1261,7 +1354,7 @@ static void dcn20_update_dchubp_dpp(
 
 		if (dpp->funcs->dpp_program_bias_and_scale) {
 			//TODO :for CNVC set scale and bias registers if necessary
-			dcn10_build_prescale_params(&bns_params, plane_state);
+			build_prescale_params(&bns_params, plane_state);
 			dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 		}
 	}
@@ -1269,19 +1362,19 @@ static void dcn20_update_dchubp_dpp(
 	if (pipe_ctx->update_flags.bits.mpcc
 			|| plane_state->update_flags.bits.global_alpha_change
 			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
-		/* Need mpcc to be idle if changing opp */
-		if (pipe_ctx->update_flags.bits.opp_changed) {
-			struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
-			int mpcc_inst;
-
-			for (mpcc_inst = 0; mpcc_inst < MAX_PIPES; mpcc_inst++) {
-				if (!old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst])
-					continue;
+		// MPCC inst is equal to pipe index in practice
+		int mpcc_inst = hubp->inst;
+		int opp_inst;
+		int opp_count = dc->res_pool->pipe_count;
+
+		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
+			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
 				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
-				old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst] = false;
+				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
+				break;
 			}
 		}
-		dc->hwss.update_mpcc(dc, pipe_ctx);
+		hws->funcs.update_mpcc(dc, pipe_ctx);
 	}
 
 	if (pipe_ctx->update_flags.bits.scaler ||
@@ -1298,14 +1391,18 @@ static void dcn20_update_dchubp_dpp(
 
 	if (pipe_ctx->update_flags.bits.viewport ||
 			(context == dc->current_state && plane_state->update_flags.bits.scaling_change) ||
-			(context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling))
+			(context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling)) {
+
 		hubp->funcs->mem_program_viewport(
 			hubp,
 			&pipe_ctx->plane_res.scl_data.viewport,
 			&pipe_ctx->plane_res.scl_data.viewport_c);
+		viewport_changed = true;
+	}
 
 	/* Any updates are handled in dc interface, just need to apply existing for plane enable */
-	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed)
+	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed ||
+			pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport)
 			&& pipe_ctx->stream->cursor_attributes.address.quad_part != 0) {
 		dc->hwss.set_cursor_position(pipe_ctx);
 		dc->hwss.set_cursor_attribute(pipe_ctx);
@@ -1355,8 +1452,13 @@ static void dcn20_update_dchubp_dpp(
 		hubp->power_gated = false;
 	}
 
+	if (hubp->funcs->apply_PLAT_54186_wa && viewport_changed)
+		hubp->funcs->apply_PLAT_54186_wa(hubp, &plane_state->address);
+
 	if (pipe_ctx->update_flags.bits.enable || plane_state->update_flags.bits.addr_update)
-		dc->hwss.update_plane_addr(dc, pipe_ctx);
+		hws->funcs.update_plane_addr(dc, pipe_ctx);
+
+
 
 	if (pipe_ctx->update_flags.bits.enable)
 		hubp->funcs->set_blank(hubp, false);
@@ -1368,10 +1470,11 @@ static void dcn20_program_pipe(
 		struct pipe_ctx *pipe_ctx,
 		struct dc_state *context)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	/* Only need to unblank on top pipe */
 	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.abm_level)
 			&& !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe)
-		dc->hwss.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
+		hws->funcs.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
 
 	if (pipe_ctx->update_flags.bits.global_sync) {
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
@@ -1384,12 +1487,12 @@ static void dcn20_program_pipe(
 		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-		if (dc->hwss.setup_vupdate_interrupt)
-			dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+		if (hws->funcs.setup_vupdate_interrupt)
+			hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 	}
 
 	if (pipe_ctx->update_flags.bits.odm)
-		dc->hwss.update_odm(dc, context, pipe_ctx);
+		hws->funcs.update_odm(dc, context, pipe_ctx);
 
 	if (pipe_ctx->update_flags.bits.enable)
 		dcn20_enable_plane(dc, pipe_ctx, context);
@@ -1398,20 +1501,20 @@ static void dcn20_program_pipe(
 		dcn20_update_dchubp_dpp(dc, pipe_ctx, context);
 
 	if (pipe_ctx->update_flags.bits.enable
-			|| pipe_ctx->plane_state->update_flags.bits.sdr_white_level)
-		set_hdr_multiplier(pipe_ctx);
+			|| pipe_ctx->plane_state->update_flags.bits.hdr_mult)
+		hws->funcs.set_hdr_multiplier(pipe_ctx);
 
 	if (pipe_ctx->update_flags.bits.enable ||
 			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
 			pipe_ctx->plane_state->update_flags.bits.gamma_change)
-		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
 	 * only do gamma programming for powering on, internal memcmp to avoid
 	 * updating on slave planes
 	 */
 	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.out_tf)
-		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	/* If the pipe has been enabled or has a different opp, we
 	 * should reprogram the fmt. This deals with cases where
@@ -1445,12 +1548,13 @@ static bool does_pipe_need_lock(struct pipe_ctx *pipe)
 	return false;
 }
 
-static void dcn20_program_front_end_for_ctx(
+void dcn20_program_front_end_for_ctx(
 		struct dc *dc,
 		struct dc_state *context)
 {
 	const unsigned int TIMEOUT_FOR_PIPE_ENABLE_MS = 100;
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 	bool pipe_locked[MAX_PIPES] = {false};
 	DC_LOGGER_INIT(dc->ctx->logger);
 
@@ -1482,13 +1586,13 @@ static void dcn20_program_front_end_for_ctx(
 				&& !context->res_ctx.pipe_ctx[i].top_pipe
 				&& !context->res_ctx.pipe_ctx[i].prev_odm_pipe
 				&& context->res_ctx.pipe_ctx[i].stream)
-			dc->hwss.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
+			hws->funcs.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
 
 	/* Disconnect mpcc */
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable
 				|| context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) {
-			dc->hwss.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
+			hws->funcs.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 			DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
 		}
 
@@ -1508,8 +1612,8 @@ static void dcn20_program_front_end_for_ctx(
 			pipe = &context->res_ctx.pipe_ctx[i];
 			if (!pipe->prev_odm_pipe && pipe->stream->num_wb_info > 0
 					&& (pipe->update_flags.raw || pipe->plane_state->update_flags.raw || pipe->stream->update_flags.raw)
-					&& dc->hwss.program_all_writeback_pipes_in_tree)
-				dc->hwss.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
+					&& hws->funcs.program_all_writeback_pipes_in_tree)
+				hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 		}
 	}
 
@@ -1541,9 +1645,9 @@ static void dcn20_program_front_end_for_ctx(
 			struct hubp *hubp = pipe->plane_res.hubp;
 			int j = 0;
 
-			for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS
+			for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS*1000
 					&& hubp->funcs->hubp_is_flip_pending(hubp); j++)
-				msleep(1);
+				mdelay(1);
 		}
 	}
 
@@ -1594,6 +1698,7 @@ bool dcn20_update_bandwidth(
 		struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	/* recalculate DML parameters */
 	if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false))
@@ -1623,10 +1728,10 @@ bool dcn20_update_bandwidth(
 					pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
 			if (pipe_ctx->prev_odm_pipe == NULL)
-				dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+				hws->funcs.blank_pixel_data(dc, pipe_ctx, blank);
 
-			if (dc->hwss.setup_vupdate_interrupt)
-				dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+			if (hws->funcs.setup_vupdate_interrupt)
+				hws->funcs.setup_vupdate_interrupt(dc, pipe_ctx);
 		}
 
 		pipe_ctx->plane_res.hubp->funcs->hubp_setup(
@@ -1640,9 +1745,8 @@ bool dcn20_update_bandwidth(
 	return true;
 }
 
-static void dcn20_enable_writeback(
+void dcn20_enable_writeback(
 		struct dc *dc,
-		const struct dc_stream_status *stream_status,
 		struct dc_writeback_info *wb_info,
 		struct dc_state *context)
 {
@@ -1656,8 +1760,7 @@ static void dcn20_enable_writeback(
 	mcif_wb = dc->res_pool->mcif_wb[wb_info->dwb_pipe_inst];
 
 	/* set the OPTC source mux */
-	ASSERT(stream_status->primary_otg_inst < MAX_PIPES);
-	optc = dc->res_pool->timing_generators[stream_status->primary_otg_inst];
+	optc = dc->res_pool->timing_generators[dwb->otg_inst];
 	optc->funcs->set_dwb_source(optc, wb_info->dwb_pipe_inst);
 	/* set MCIF_WB buffer and arbitration configuration */
 	mcif_wb->funcs->config_mcif_buf(mcif_wb, &wb_info->mcif_buf_params, wb_info->dwb_params.dest_height);
@@ -1684,7 +1787,7 @@ void dcn20_disable_writeback(
 	mcif_wb->funcs->disable_mcif(mcif_wb);
 }
 
-bool dcn20_hwss_wait_for_blank_complete(
+bool dcn20_wait_for_blank_complete(
 		struct output_pixel_processor *opp)
 {
 	int counter;
@@ -1713,9 +1816,8 @@ bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx)
 	return hubp->funcs->dmdata_status_done(hubp);
 }
 
-static void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (pipe_ctx->stream_res.dsc) {
@@ -1727,12 +1829,10 @@ static void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx
 			odm_pipe = odm_pipe->next_odm_pipe;
 		}
 	}
-#endif
 }
 
-static void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct dce_hwseq *hws = dc->hwseq;
 
 	if (pipe_ctx->stream_res.dsc) {
@@ -1744,7 +1844,6 @@ static void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx)
 			odm_pipe = odm_pipe->next_odm_pipe;
 		}
 	}
-#endif
 }
 
 void dcn20_set_dmdata_attributes(struct pipe_ctx *pipe_ctx)
@@ -1767,12 +1866,7 @@ void dcn20_set_dmdata_attributes(struct pipe_ctx *pipe_ctx)
 	hubp->funcs->dmdata_set_attributes(hubp, &attr);
 }
 
-void dcn20_disable_stream(struct pipe_ctx *pipe_ctx)
-{
-	dce110_disable_stream(pipe_ctx);
-}
-
-static void dcn20_init_vm_ctx(
+void dcn20_init_vm_ctx(
 		struct dce_hwseq *hws,
 		struct dc *dc,
 		struct dc_virtual_addr_space_config *va_config,
@@ -1794,7 +1888,7 @@ static void dcn20_init_vm_ctx(
 	dc->res_pool->hubbub->funcs->init_vm_ctx(dc->res_pool->hubbub, &config, vmid);
 }
 
-static int dcn20_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
+int dcn20_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
 {
 	struct dcn_hubbub_phys_addr_config config;
 
@@ -1838,8 +1932,7 @@ static bool patch_address_for_sbs_tb_stereo(
 	return false;
 }
 
-
-static void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	bool addr_patched = false;
 	PHYSICAL_ADDRESS_LOC addr;
@@ -1873,6 +1966,7 @@ void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
 	struct encoder_unblank_param params = { { 0 } };
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
+	struct dce_hwseq *hws = link->dc->hwseq;
 	struct pipe_ctx *odm_pipe;
 
 	params.opp_cnt = 1;
@@ -1885,7 +1979,7 @@ void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
 	params.link_settings.link_rate = link_settings->link_rate;
 
 	if (dc_is_dp_signal(pipe_ctx->stream->signal)) {
-		if (optc1_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1)
+		if (optc2_is_two_pixels_per_containter(&stream->timing) || params.opp_cnt > 1)
 			params.timing.pix_clk_100hz /= 2;
 		pipe_ctx->stream_res.stream_enc->funcs->dp_set_odm_combine(
 				pipe_ctx->stream_res.stream_enc, params.opp_cnt > 1);
@@ -1893,14 +1987,14 @@ void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
 	}
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		link->dc->hwss.edp_backlight_control(link, true);
+		hws->funcs.edp_backlight_control(link, true);
 	}
 }
 
-void dcn20_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx)
+void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
-	int start_line = get_vupdate_offset_from_vsync(pipe_ctx);
+	int start_line = dc->hwss.get_vupdate_offset_from_vsync(pipe_ctx);
 
 	if (start_line < 0)
 		start_line = 0;
@@ -1915,6 +2009,7 @@ static void dcn20_reset_back_end_for_pipe(
 		struct dc_state *context)
 {
 	int i;
+	struct dc_link *link;
 	DC_LOGGER_INIT(dc->ctx->logger);
 	if (pipe_ctx->stream_res.stream_enc == NULL) {
 		pipe_ctx->stream = NULL;
@@ -1922,8 +2017,14 @@ static void dcn20_reset_back_end_for_pipe(
 	}
 
 	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		/* DPMS may already disable */
-		if (!pipe_ctx->stream->dpms_off)
+		link = pipe_ctx->stream->link;
+		/* DPMS may already disable or */
+		/* dpms_off status is incorrect due to fastboot
+		 * feature. When system resume from S4 with second
+		 * screen only, the dpms_off would be true but
+		 * VBIOS lit up eDP, so check link status too.
+		 */
+		if (!pipe_ctx->stream->dpms_off || link->link_status.link_active)
 			core_link_disable_stream(pipe_ctx);
 		else if (pipe_ctx->stream_res.audio)
 			dc->hwss.disable_audio_stream(pipe_ctx);
@@ -1943,11 +2044,9 @@ static void dcn20_reset_back_end_for_pipe(
 			}
 		}
 	}
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	else if (pipe_ctx->stream_res.dsc) {
 		dp_set_dsc_enable(pipe_ctx, false);
 	}
-#endif
 
 	/* by upper caller loop, parent pipe: pipe0, will be reset last.
 	 * back end share by all pipes and will be disable only when disable
@@ -1978,11 +2077,12 @@ static void dcn20_reset_back_end_for_pipe(
 					pipe_ctx->pipe_idx, pipe_ctx->stream_res.tg->inst);
 }
 
-static void dcn20_reset_hw_ctx_wrap(
+void dcn20_reset_hw_ctx_wrap(
 		struct dc *dc,
 		struct dc_state *context)
 {
 	int i;
+	struct dce_hwseq *hws = dc->hwseq;
 
 	/* Reset Back End*/
 	for (i = dc->res_pool->pipe_count - 1; i >= 0 ; i--) {
@@ -2001,8 +2101,8 @@ static void dcn20_reset_hw_ctx_wrap(
 			struct clock_source *old_clk = pipe_ctx_old->clock_source;
 
 			dcn20_reset_back_end_for_pipe(dc, pipe_ctx_old, dc->current_state);
-			if (dc->hwss.enable_stream_gating)
-				dc->hwss.enable_stream_gating(dc, pipe_ctx);
+			if (hws->funcs.enable_stream_gating)
+				hws->funcs.enable_stream_gating(dc, pipe_ctx);
 			if (old_clk)
 				old_clk->funcs->cs_power_down(old_clk);
 		}
@@ -2031,8 +2131,9 @@ void dcn20_get_mpctree_visual_confirm_color(
 	*color = pipe_colors[top_pipe->pipe_idx];
 }
 
-static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
+	struct dce_hwseq *hws = dc->hwseq;
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct mpcc_blnd_cfg blnd_cfg = { {0} };
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha;
@@ -2043,10 +2144,10 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 
 	// input to MPCC is always RGB, by default leave black_color at 0
 	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
-		dcn10_get_hdr_visual_confirm_color(
+		hws->funcs.get_hdr_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
-		dcn10_get_surface_visual_confirm_color(
+		hws->funcs.get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_MPCTREE) {
 		dcn20_get_mpctree_visual_confirm_color(
@@ -2083,12 +2184,6 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	 */
 	mpcc_id = hubp->inst;
 
-	/* If there is no full update, don't need to touch MPC tree*/
-	if (!pipe_ctx->plane_state->update_flags.bits.full_update) {
-		mpc->funcs->update_blending(mpc, &blnd_cfg, mpcc_id);
-		return;
-	}
-
 	/* check if this MPCC is already being used */
 	new_mpcc = mpc->funcs->get_mpcc_for_dpp(mpc_tree_params, mpcc_id);
 	/* remove MPCC if being used */
@@ -2113,125 +2208,7 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	hubp->mpcc_id = mpcc_id;
 }
 
-static int find_free_gsl_group(const struct dc *dc)
-{
-	if (dc->res_pool->gsl_groups.gsl_0 == 0)
-		return 1;
-	if (dc->res_pool->gsl_groups.gsl_1 == 0)
-		return 2;
-	if (dc->res_pool->gsl_groups.gsl_2 == 0)
-		return 3;
-
-	return 0;
-}
-
-/* NOTE: This is not a generic setup_gsl function (hence the suffix as_lock)
- * This is only used to lock pipes in pipe splitting case with immediate flip
- * Ordinary MPC/OTG locks suppress VUPDATE which doesn't help with immediate,
- * so we get tearing with freesync since we cannot flip multiple pipes
- * atomically.
- * We use GSL for this:
- * - immediate flip: find first available GSL group if not already assigned
- *                   program gsl with that group, set current OTG as master
- *                   and always us 0x4 = AND of flip_ready from all pipes
- * - vsync flip: disable GSL if used
- *
- * Groups in stream_res are stored as +1 from HW registers, i.e.
- * gsl_0 <=> pipe_ctx->stream_res.gsl_group == 1
- * Using a magic value like -1 would require tracking all inits/resets
- */
-void dcn20_setup_gsl_group_as_lock(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool enable)
-{
-	struct gsl_params gsl;
-	int group_idx;
-
-	memset(&gsl, 0, sizeof(struct gsl_params));
-
-	if (enable) {
-		/* return if group already assigned since GSL was set up
-		 * for vsync flip, we would unassign so it can't be "left over"
-		 */
-		if (pipe_ctx->stream_res.gsl_group > 0)
-			return;
-
-		group_idx = find_free_gsl_group(dc);
-		ASSERT(group_idx != 0);
-		pipe_ctx->stream_res.gsl_group = group_idx;
-
-		/* set gsl group reg field and mark resource used */
-		switch (group_idx) {
-		case 1:
-			gsl.gsl0_en = 1;
-			dc->res_pool->gsl_groups.gsl_0 = 1;
-			break;
-		case 2:
-			gsl.gsl1_en = 1;
-			dc->res_pool->gsl_groups.gsl_1 = 1;
-			break;
-		case 3:
-			gsl.gsl2_en = 1;
-			dc->res_pool->gsl_groups.gsl_2 = 1;
-			break;
-		default:
-			BREAK_TO_DEBUGGER();
-			return; // invalid case
-		}
-		gsl.gsl_master_en = 1;
-	} else {
-		group_idx = pipe_ctx->stream_res.gsl_group;
-		if (group_idx == 0)
-			return; // if not in use, just return
-
-		pipe_ctx->stream_res.gsl_group = 0;
-
-		/* unset gsl group reg field and mark resource free */
-		switch (group_idx) {
-		case 1:
-			gsl.gsl0_en = 0;
-			dc->res_pool->gsl_groups.gsl_0 = 0;
-			break;
-		case 2:
-			gsl.gsl1_en = 0;
-			dc->res_pool->gsl_groups.gsl_1 = 0;
-			break;
-		case 3:
-			gsl.gsl2_en = 0;
-			dc->res_pool->gsl_groups.gsl_2 = 0;
-			break;
-		default:
-			BREAK_TO_DEBUGGER();
-			return;
-		}
-		gsl.gsl_master_en = 0;
-	}
-
-	/* at this point we want to program whether it's to enable or disable */
-	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL &&
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL) {
-		pipe_ctx->stream_res.tg->funcs->set_gsl(
-			pipe_ctx->stream_res.tg,
-			&gsl);
-
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
-			pipe_ctx->stream_res.tg, group_idx,	enable ? 4 : 0);
-	} else
-		BREAK_TO_DEBUGGER();
-}
-
-static void dcn20_set_flip_control_gsl(
-		struct pipe_ctx *pipe_ctx,
-		bool flip_immediate)
-{
-	if (pipe_ctx && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl)
-		pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_control_surface_gsl(
-				pipe_ctx->plane_res.hubp, flip_immediate);
-
-}
-
-static void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
+void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 {
 	enum dc_lane_count lane_count =
 		pipe_ctx->stream->link->cur_link_settings.lane_count;
@@ -2279,7 +2256,7 @@ static void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-static void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
+void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state    *stream     = pipe_ctx->stream;
 	struct hubp               *hubp       = pipe_ctx->plane_res.hubp;
@@ -2305,7 +2282,7 @@ static void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx)
 						hubp->inst, mode);
 }
 
-static void dcn20_fpga_init_hw(struct dc *dc)
+void dcn20_fpga_init_hw(struct dc *dc)
 {
 	int i, j;
 	struct dce_hwseq *hws = dc->hwseq;
@@ -2320,13 +2297,13 @@ static void dcn20_fpga_init_hw(struct dc *dc)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);
 
 	//Enable ability to power gate / don't force power on permanently
-	dc->hwss.enable_power_gating_plane(hws, true);
+	hws->funcs.enable_power_gating_plane(hws, true);
 
 	// Specific to FPGA dccg and registers
 	REG_WRITE(RBBMIF_TIMEOUT_DIS, 0xFFFFFFFF);
 	REG_WRITE(RBBMIF_TIMEOUT_DIS_2, 0xFFFFFFFF);
 
-	dcn20_dccg_init(hws);
+	hws->funcs.dccg_init(hws);
 
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, 2);
 	REG_UPDATE(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, 1);
@@ -2390,7 +2367,7 @@ static void dcn20_fpga_init_hw(struct dc *dc)
 		dc->res_pool->opps[i]->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 		pipe_ctx->stream_res.opp = dc->res_pool->opps[i];
 		/*to do*/
-		hwss1_plane_atomic_disconnect(dc, pipe_ctx);
+		hws->funcs.plane_atomic_disconnect(dc, pipe_ctx);
 	}
 
 	/* initialize DWB pointer to MCIF_WB */
@@ -2419,57 +2396,3 @@ static void dcn20_fpga_init_hw(struct dc *dc)
 		tg->funcs->tg_init(tg);
 	}
 }
-
-void dcn20_hw_sequencer_construct(struct dc *dc)
-{
-	dcn10_hw_sequencer_construct(dc);
-	dc->hwss.unblank_stream = dcn20_unblank_stream;
-	dc->hwss.update_plane_addr = dcn20_update_plane_addr;
-	dc->hwss.enable_stream_timing = dcn20_enable_stream_timing;
-	dc->hwss.program_triplebuffer = dcn20_program_tripleBuffer;
-	dc->hwss.set_input_transfer_func = dcn20_set_input_transfer_func;
-	dc->hwss.set_output_transfer_func = dcn20_set_output_transfer_func;
-	dc->hwss.apply_ctx_for_surface = NULL;
-	dc->hwss.program_front_end_for_ctx = dcn20_program_front_end_for_ctx;
-	dc->hwss.pipe_control_lock = dcn20_pipe_control_lock;
-	dc->hwss.pipe_control_lock_global = dcn20_pipe_control_lock_global;
-	dc->hwss.optimize_bandwidth = dcn20_optimize_bandwidth;
-	dc->hwss.prepare_bandwidth = dcn20_prepare_bandwidth;
-	dc->hwss.update_bandwidth = dcn20_update_bandwidth;
-	dc->hwss.enable_writeback = dcn20_enable_writeback;
-	dc->hwss.disable_writeback = dcn20_disable_writeback;
-	dc->hwss.program_output_csc = dcn20_program_output_csc;
-	dc->hwss.update_odm = dcn20_update_odm;
-	dc->hwss.blank_pixel_data = dcn20_blank_pixel_data;
-	dc->hwss.dmdata_status_done = dcn20_dmdata_status_done;
-	dc->hwss.program_dmdata_engine = dcn20_program_dmdata_engine;
-	dc->hwss.enable_stream = dcn20_enable_stream;
-	dc->hwss.disable_stream = dcn20_disable_stream;
-	dc->hwss.init_sys_ctx = dcn20_init_sys_ctx;
-	dc->hwss.init_vm_ctx = dcn20_init_vm_ctx;
-	dc->hwss.disable_stream_gating = dcn20_disable_stream_gating;
-	dc->hwss.enable_stream_gating = dcn20_enable_stream_gating;
-	dc->hwss.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt;
-	dc->hwss.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap;
-	dc->hwss.update_mpcc = dcn20_update_mpcc;
-	dc->hwss.set_flip_control_gsl = dcn20_set_flip_control_gsl;
-	dc->hwss.init_blank = dcn20_init_blank;
-	dc->hwss.disable_plane = dcn20_disable_plane;
-	dc->hwss.plane_atomic_disable = dcn20_plane_atomic_disable;
-	dc->hwss.enable_power_gating_plane = dcn20_enable_power_gating_plane;
-	dc->hwss.dpp_pg_control = dcn20_dpp_pg_control;
-	dc->hwss.hubp_pg_control = dcn20_hubp_pg_control;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-	dc->hwss.dsc_pg_control = dcn20_dsc_pg_control;
-#else
-	dc->hwss.dsc_pg_control = NULL;
-#endif
-	dc->hwss.disable_vga = dcn20_disable_vga;
-
-	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
-		dc->hwss.init_hw = dcn20_fpga_init_hw;
-		dc->hwss.init_pipes = NULL;
-	}
-
-
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
index 3098f1049ed7..02c9be5ebd47 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
@@ -26,90 +26,112 @@
 #ifndef __DC_HWSS_DCN20_H__
 #define __DC_HWSS_DCN20_H__
 
-struct dc;
+#include "hw_sequencer_private.h"
 
-void dcn20_hw_sequencer_construct(struct dc *dc);
-
-enum dc_status dcn20_enable_stream_timing(
-		struct pipe_ctx *pipe_ctx,
-		struct dc_state *context,
-		struct dc *dc);
-
-void dcn20_blank_pixel_data(
+bool dcn20_set_blend_lut(
+	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
+bool dcn20_set_shaper_3dlut(
+	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
+void dcn20_program_front_end_for_ctx(
 		struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool blank);
-
+		struct dc_state *context);
+void dcn20_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx);
+bool dcn20_set_input_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			const struct dc_stream_state *stream);
 void dcn20_program_output_csc(struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
 		enum dc_color_space colorspace,
 		uint16_t *matrix,
 		int opp_id);
-
+void dcn20_enable_stream(struct pipe_ctx *pipe_ctx);
+void dcn20_unblank_stream(struct pipe_ctx *pipe_ctx,
+		struct dc_link_settings *link_settings);
+void dcn20_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_blank_pixel_data(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		bool blank);
+void dcn20_pipe_control_lock(
+	struct dc *dc,
+	struct pipe_ctx *pipe,
+	bool lock);
+void dcn20_pipe_control_lock_global(
+		struct dc *dc,
+		struct pipe_ctx *pipe,
+		bool lock);
 void dcn20_prepare_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
-
 void dcn20_optimize_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
-
 bool dcn20_update_bandwidth(
 		struct dc *dc,
 		struct dc_state *context);
-
+void dcn20_reset_hw_ctx_wrap(
+		struct dc *dc,
+		struct dc_state *context);
+enum dc_status dcn20_enable_stream_timing(
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context,
+		struct dc *dc);
+void dcn20_disable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_enable_stream_gating(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_setup_vupdate_interrupt(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_init_blank(
+		struct dc *dc,
+		struct timing_generator *tg);
+void dcn20_disable_vga(
+	struct dce_hwseq *hws);
+void dcn20_plane_atomic_disable(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_enable_power_gating_plane(
+	struct dce_hwseq *hws,
+	bool enable);
+void dcn20_dpp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dpp_inst,
+		bool power_on);
+void dcn20_hubp_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int hubp_inst,
+		bool power_on);
+void dcn20_program_triple_buffer(
+	const struct dc *dc,
+	struct pipe_ctx *pipe_ctx,
+	bool enable_triple_buffer);
+void dcn20_enable_writeback(
+		struct dc *dc,
+		struct dc_writeback_info *wb_info,
+		struct dc_state *context);
 void dcn20_disable_writeback(
 		struct dc *dc,
 		unsigned int dwb_pipe_inst);
-
-bool dcn20_hwss_wait_for_blank_complete(
-		struct output_pixel_processor *opp);
-
-bool dcn20_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
-			const struct dc_stream_state *stream);
-
-bool dcn20_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
-			const struct dc_plane_state *plane_state);
-
+void dcn20_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx);
 bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx);
-
+void dcn20_program_dmdata_engine(struct pipe_ctx *pipe_ctx);
 void dcn20_set_dmdata_attributes(struct pipe_ctx *pipe_ctx);
-
-void dcn20_disable_stream(struct pipe_ctx *pipe_ctx);
-
-void dcn20_program_tripleBuffer(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool enableTripleBuffer);
-
-void dcn20_setup_vupdate_interrupt(struct pipe_ctx *pipe_ctx);
-
-void dcn20_pipe_control_lock_global(
+void dcn20_init_vm_ctx(
+		struct dce_hwseq *hws,
 		struct dc *dc,
-		struct pipe_ctx *pipe,
-		bool lock);
-void dcn20_setup_gsl_group_as_lock(const struct dc *dc,
-				struct pipe_ctx *pipe_ctx,
-				bool enable);
-void dcn20_dccg_init(struct dce_hwseq *hws);
-void dcn20_init_blank(
-	   struct dc *dc,
-	   struct timing_generator *tg);
-void dcn20_display_init(struct dc *dc);
-void dcn20_pipe_control_lock(
-	struct dc *dc,
-	struct pipe_ctx *pipe,
-	bool lock);
-void dcn20_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
-void dcn20_enable_plane(
-	struct dc *dc,
-	struct pipe_ctx *pipe_ctx,
-	struct dc_state *context);
-bool dcn20_set_blend_lut(
-	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
-bool dcn20_set_shaper_3dlut(
-	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
-void dcn20_get_mpctree_visual_confirm_color(
+		struct dc_virtual_addr_space_config *va_config,
+		int vmid);
+void dcn20_set_flip_control_gsl(
 		struct pipe_ctx *pipe_ctx,
-		struct tg_color *color);
+		bool flip_immediate);
+void dcn20_dsc_pg_control(
+		struct dce_hwseq *hws,
+		unsigned int dsc_inst,
+		bool power_on);
+void dcn20_fpga_init_hw(struct dc *dc);
+bool dcn20_wait_for_blank_complete(
+		struct output_pixel_processor *opp);
+void dcn20_dccg_init(struct dce_hwseq *hws);
+int dcn20_init_sys_ctx(struct dce_hwseq *hws,
+		struct dc *dc,
+		struct dc_phy_addr_space_config *pa_config);
+
 #endif /* __DC_HWSS_DCN20_H__ */
+
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
new file mode 100644
index 000000000000..d51e02fdab4d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.c
@@ -0,0 +1,133 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10/dcn10_hw_sequencer.h"
+#include "dcn20_hwseq.h"
+
+static const struct hw_sequencer_funcs dcn20_funcs = {
+	.program_gamut_remap = dcn10_program_gamut_remap,
+	.init_hw = dcn10_init_hw,
+	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
+	.apply_ctx_for_surface = NULL,
+	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.update_dchub = dcn10_update_dchub,
+	.update_pending_status = dcn10_update_pending_status,
+	.program_output_csc = dcn20_program_output_csc,
+	.enable_accelerated_mode = dce110_enable_accelerated_mode,
+	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
+	.update_info_frame = dce110_update_info_frame,
+	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
+	.enable_stream = dcn20_enable_stream,
+	.disable_stream = dce110_disable_stream,
+	.unblank_stream = dcn20_unblank_stream,
+	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
+	.disable_plane = dcn20_disable_plane,
+	.pipe_control_lock = dcn20_pipe_control_lock,
+	.pipe_control_lock_global = dcn20_pipe_control_lock_global,
+	.prepare_bandwidth = dcn20_prepare_bandwidth,
+	.optimize_bandwidth = dcn20_optimize_bandwidth,
+	.update_bandwidth = dcn20_update_bandwidth,
+	.set_drr = dcn10_set_drr,
+	.get_position = dcn10_get_position,
+	.set_static_screen_control = dcn10_set_static_screen_control,
+	.setup_stereo = dcn10_setup_stereo,
+	.set_avmute = dce110_set_avmute,
+	.log_hw_state = dcn10_log_hw_state,
+	.get_hw_state = dcn10_get_hw_state,
+	.clear_status_bits = dcn10_clear_status_bits,
+	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_power_control = dce110_edp_power_control,
+	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
+	.set_clock = dcn10_set_clock,
+	.get_clock = dcn10_get_clock,
+	.program_triplebuffer = dcn20_program_triple_buffer,
+	.enable_writeback = dcn20_enable_writeback,
+	.disable_writeback = dcn20_disable_writeback,
+	.dmdata_status_done = dcn20_dmdata_status_done,
+	.program_dmdata_engine = dcn20_program_dmdata_engine,
+	.set_dmdata_attributes = dcn20_set_dmdata_attributes,
+	.init_sys_ctx = dcn20_init_sys_ctx,
+	.init_vm_ctx = dcn20_init_vm_ctx,
+	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
+	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+};
+
+static const struct hwseq_private_funcs dcn20_private_funcs = {
+	.init_pipes = dcn10_init_pipes,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
+	.update_mpcc = dcn20_update_mpcc,
+	.set_input_transfer_func = dcn20_set_input_transfer_func,
+	.set_output_transfer_func = dcn20_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_power_gating = dcn10_dummy_display_power_gating,
+	.blank_pixel_data = dcn20_blank_pixel_data,
+	.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap,
+	.enable_stream_timing = dcn20_enable_stream_timing,
+	.edp_backlight_control = dce110_edp_backlight_control,
+	.disable_stream_gating = dcn20_disable_stream_gating,
+	.enable_stream_gating = dcn20_enable_stream_gating,
+	.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt,
+	.did_underflow_occur = dcn10_did_underflow_occur,
+	.init_blank = dcn20_init_blank,
+	.disable_vga = dcn20_disable_vga,
+	.bios_golden_init = dcn10_bios_golden_init,
+	.plane_atomic_disable = dcn20_plane_atomic_disable,
+	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
+	.enable_power_gating_plane = dcn20_enable_power_gating_plane,
+	.dpp_pg_control = dcn20_dpp_pg_control,
+	.hubp_pg_control = dcn20_hubp_pg_control,
+	.dsc_pg_control = NULL,
+	.update_odm = dcn20_update_odm,
+	.dsc_pg_control = dcn20_dsc_pg_control,
+	.get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color,
+	.get_hdr_visual_confirm_color = dcn10_get_hdr_visual_confirm_color,
+	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
+	.verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high,
+	.wait_for_blank_complete = dcn20_wait_for_blank_complete,
+	.dccg_init = dcn20_dccg_init,
+	.set_blend_lut = dcn20_set_blend_lut,
+	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
+};
+
+void dcn20_hw_sequencer_construct(struct dc *dc)
+{
+	dc->hwss = dcn20_funcs;
+	dc->hwseq->funcs = dcn20_private_funcs;
+
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		dc->hwss.init_hw = dcn20_fpga_init_hw;
+		dc->hwseq->funcs.init_pipes = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.h
new file mode 100644
index 000000000000..12277797cd71
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_init.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_DCN20_INIT_H__
+#define __DC_DCN20_INIT_H__
+
+struct dc;
+
+void dcn20_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_DCN20_INIT_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
index e476f27aa3a9..e4ac73035c84 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c
@@ -168,10 +168,8 @@ static struct mpll_cfg dcn2_mpll_cfg[] = {
 void enc2_fec_set_enable(struct link_encoder *enc, bool enable)
 {
 	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DC_LOG_DSC("%s FEC at link encoder inst %d",
 			enable ? "Enabling" : "Disabling", enc->id.enum_id);
-#endif
 	REG_UPDATE(DP_DPHY_CNTL, DPHY_FEC_EN, enable);
 }
 
@@ -192,7 +190,6 @@ bool enc2_fec_is_active(struct link_encoder *enc)
 	return (active != 0);
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* this function reads dsc related register fields to be logged later in dcn10_log_hw_state
  * into a dcn_dsc_state struct.
  */
@@ -203,8 +200,8 @@ void link_enc2_read_state(struct link_encoder *enc, struct link_enc_state *s)
 	REG_GET(DP_DPHY_CNTL, DPHY_FEC_EN, &s->dphy_fec_en);
 	REG_GET(DP_DPHY_CNTL, DPHY_FEC_READY_SHADOW, &s->dphy_fec_ready_shadow);
 	REG_GET(DP_DPHY_CNTL, DPHY_FEC_ACTIVE_STATUS, &s->dphy_fec_active_status);
+	REG_GET(DP_LINK_CNTL, DP_LINK_TRAINING_COMPLETE, &s->dp_link_training_complete);
 }
-#endif
 
 static bool update_cfg_data(
 		struct dcn10_link_encoder *enc10,
@@ -315,9 +312,7 @@ void enc2_hw_init(struct link_encoder *enc)
 }
 
 static const struct link_encoder_funcs dcn20_link_enc_funcs = {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.read_state = link_enc2_read_state,
-#endif
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
 	.hw_init = enc2_hw_init,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
index 0c98a0bbbd14..8cab8107fd94 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
@@ -33,7 +33,142 @@
 	SRI(AUX_DPHY_TX_CONTROL, DP_AUX, id)
 
 #define UNIPHY_MASK_SH_LIST(mask_sh)\
-	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_LINK_ENABLE, mask_sh)
+	LE_SF(SYMCLKA_CLOCK_ENABLE, SYMCLKA_CLOCK_ENABLE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_LINK_ENABLE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL1_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL2_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL3_XBAR_SOURCE, mask_sh)
+
+#define DPCS_MASK_SH_LIST(mask_sh)\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_CLK_RDY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_DATA_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX0_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX1_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX2_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL4, RDPCS_PHY_DP_TX3_TERM_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_DP_MPLLB_MULTIPLIER, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX0_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX0_RATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX1_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX1_RATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX2_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX3_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_QUOT, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL7, RDPCS_PHY_DP_MPLLB_FRACN_DEN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL8, RDPCS_PHY_DP_MPLLB_SSC_PEAK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL9, RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL9, RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL10, RDPCS_PHY_DP_MPLLB_FRACN_REM, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_DP_REF_CLK_MPLLB_DIV, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL11, RDPCS_PHY_HDMI_MPLLB_HDMI_DIV, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_SSC_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_TX_CLK_DIV, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL12, RDPCS_PHY_DP_MPLLB_STATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL13, RDPCS_PHY_DP_MPLLB_DIV_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL13, RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL14, RDPCS_PHY_DP_MPLLB_FRACN_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL14, RDPCS_PHY_DP_MPLLB_PMIX_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE0_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE1_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE2_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_LANE3_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CNTL, RDPCS_TX_FIFO_RD_START_DELAY, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_EXT_REFCLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_BYPASS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SRAMCLK_CLOCK_ON, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_CLOCK_ON, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_GATE_DIS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_SYMCLK_DIV2_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_REQ, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX0_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX1_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX2_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL3, RDPCS_PHY_DP_TX3_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_RESET, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_CR_MUX_SEL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_REF_RANGE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_BYPASS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_EXT_LD_DONE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_HDMIMODE_ENABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_SRAM_INIT_DONE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL2, RDPCS_PHY_DP4_POR, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA, RDPCS_PLL_UPDATE_DATA, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_REG_FIFO_ERROR_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_TX_FIFO_ERROR_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_DPALT_DISABLE_TOGGLE_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL, RDPCS_DPALT_4LANE_TOGGLE_MASK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCS_TX_CR_ADDR, RDPCS_TX_CR_ADDR, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCS_TX_CR_DATA, RDPCS_TX_CR_DATA, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_V2I, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_FREQ_VCO, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_MPLLB_CP_INT, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_MPLLB_CP_PROP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_FINETUNE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_RANGE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_POST, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_CLOCK_ON, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_GATE_DIS, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CLOCK_CNTL, DPCS_SYMCLK_EN, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_SWAP, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_FIFO_EN, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_FIFO_RD_START_DELAY, mask_sh),\
+	LE_SF(DPCSTX0_DPCSTX_DEBUG_CONFIG, DPCS_DBG_CBUS_DIS, mask_sh)
+
+#define DPCS_DCN2_MASK_SH_LIST(mask_sh)\
+	DPCS_MASK_SH_LIST(mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL, RDPCS_PHY_RX_REF_LD_VAL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL, RDPCS_PHY_RX_VCO_LD_VAL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE_ACK, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX0_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX1_PSTATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX0_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_TX1_MPLL_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_REF_CLK_EN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX2_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX2_RATE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX3_WIDTH, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL5, RDPCS_PHY_DP_TX3_RATE, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYA_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh)
 
 #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\
 	LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\
@@ -63,6 +198,49 @@
 	SRI(CLOCK_ENABLE, SYMCLK, id), \
 	SRI(CHANNEL_XBAR_CNTL, UNIPHY, id)
 
+#define DPCS_DCN2_CMN_REG_LIST(id) \
+	SRI(DIG_LANE_ENABLE, DIG, id), \
+	SRI(TMDS_CTL_BITS, DIG, id), \
+	SRI(RDPCSTX_PHY_CNTL3, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL4, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL5, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL6, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL7, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL8, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL9, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL10, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL11, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL12, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL13, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL14, RDPCSTX, id), \
+	SRI(RDPCSTX_CNTL, RDPCSTX, id), \
+	SRI(RDPCSTX_CLOCK_CNTL, RDPCSTX, id), \
+	SRI(RDPCSTX_INTERRUPT_CONTROL, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL0, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_CNTL2, RDPCSTX, id), \
+	SRI(RDPCSTX_PLL_UPDATE_DATA, RDPCSTX, id), \
+	SRI(RDPCS_TX_CR_ADDR, RDPCSTX, id), \
+	SRI(RDPCS_TX_CR_DATA, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE0, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE1, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE2, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE3, RDPCSTX, id), \
+	SRI(DPCSTX_TX_CLOCK_CNTL, DPCSTX, id), \
+	SRI(DPCSTX_TX_CNTL, DPCSTX, id), \
+	SRI(DPCSTX_DEBUG_CONFIG, DPCSTX, id), \
+	SRI(RDPCSTX_DEBUG_CONFIG, RDPCSTX, id), \
+	SR(RDPCSTX0_RDPCSTX_SCRATCH)
+
+
+#define DPCS_DCN2_REG_LIST(id) \
+	DPCS_DCN2_CMN_REG_LIST(id), \
+	SRI(RDPCSTX_PHY_RX_LD_VAL, RDPCSTX, id),\
+	SRI(RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCSTX, id)
+
+#define LE_DCN2_REG_LIST(id) \
+		LE_DCN10_REG_LIST(id), \
+		SR(DCIO_SOFT_RESET)
+
 struct mpll_cfg {
 	uint32_t mpllb_ana_v2i;
 	uint32_t mpllb_ana_freq_vco;
@@ -158,9 +336,7 @@ void enc2_fec_set_ready(struct link_encoder *enc, bool ready);
 bool enc2_fec_is_active(struct link_encoder *enc);
 void enc2_hw_init(struct link_encoder *enc);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 void link_enc2_read_state(struct link_encoder *enc, struct link_enc_state *s);
-#endif
 
 void dcn20_link_encoder_enable_dp_output(
 	struct link_encoder *enc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
index 5a188b2bc033..de9c857ab3e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.c
@@ -33,6 +33,9 @@
 #define REG(reg)\
 	mpc20->mpc_regs->reg
 
+#define IND_REG(index) \
+	(index)
+
 #define CTX \
 	mpc20->base.ctx
 
@@ -132,19 +135,33 @@ void mpc2_set_output_csc(
 		const uint16_t *regval,
 		enum mpc_output_csc_mode ocsc_mode)
 {
+	uint32_t cur_mode;
 	struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc);
 	struct color_matrices_reg ocsc_regs;
 
-	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
-
-	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE)
+	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) {
+		REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 		return;
+	}
 
 	if (regval == NULL) {
 		BREAK_TO_DEBUGGER();
 		return;
 	}
 
+	/* determine which CSC coefficients (A or B) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	IX_REG_GET(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_DATA,
+						MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX,
+						MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE, &cur_mode);
+
+	if (cur_mode != MPC_OUTPUT_CSC_COEF_A)
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_A;
+	else
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_B;
+
 	ocsc_regs.shifts.csc_c11 = mpc20->mpc_shift->MPC_OCSC_C11_A;
 	ocsc_regs.masks.csc_c11  = mpc20->mpc_mask->MPC_OCSC_C11_A;
 	ocsc_regs.shifts.csc_c12 = mpc20->mpc_shift->MPC_OCSC_C12_A;
@@ -157,10 +174,13 @@ void mpc2_set_output_csc(
 		ocsc_regs.csc_c11_c12 = REG(CSC_C11_C12_B[opp_id]);
 		ocsc_regs.csc_c33_c34 = REG(CSC_C33_C34_B[opp_id]);
 	}
+
 	cm_helper_program_color_matrices(
 			mpc20->base.ctx,
 			regval,
 			&ocsc_regs);
+
+	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 }
 
 void mpc2_set_ocsc_default(
@@ -169,14 +189,16 @@ void mpc2_set_ocsc_default(
 		enum dc_color_space color_space,
 		enum mpc_output_csc_mode ocsc_mode)
 {
+	uint32_t cur_mode;
 	struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc);
 	uint32_t arr_size;
 	struct color_matrices_reg ocsc_regs;
 	const uint16_t *regval = NULL;
 
-	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
-	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE)
+	if (ocsc_mode == MPC_OUTPUT_CSC_DISABLE) {
+		REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 		return;
+	}
 
 	regval = find_color_matrix(color_space, &arr_size);
 
@@ -185,6 +207,19 @@ void mpc2_set_ocsc_default(
 		return;
 	}
 
+	/* determine which CSC coefficients (A or B) we are using
+	 * currently.  select the alternate set to double buffer
+	 * the CSC update so CSC is updated on frame boundary
+	 */
+	IX_REG_GET(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_DATA,
+						MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX,
+						MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE, &cur_mode);
+
+	if (cur_mode != MPC_OUTPUT_CSC_COEF_A)
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_A;
+	else
+		ocsc_mode = MPC_OUTPUT_CSC_COEF_B;
+
 	ocsc_regs.shifts.csc_c11 = mpc20->mpc_shift->MPC_OCSC_C11_A;
 	ocsc_regs.masks.csc_c11  = mpc20->mpc_mask->MPC_OCSC_C11_A;
 	ocsc_regs.shifts.csc_c12 = mpc20->mpc_shift->MPC_OCSC_C12_A;
@@ -203,6 +238,8 @@ void mpc2_set_ocsc_default(
 			mpc20->base.ctx,
 			regval,
 			&ocsc_regs);
+
+	REG_SET(CSC_MODE[opp_id], 0, MPC_OCSC_MODE, ocsc_mode);
 }
 
 static void mpc2_ogam_get_reg_field(
@@ -345,6 +382,9 @@ static void mpc20_program_ogam_pwl(
 	uint32_t i;
 	struct dcn20_mpc *mpc20 = TO_DCN20_MPC(mpc);
 
+	PERF_TRACE();
+	REG_SEQ_START();
+
 	for (i = 0 ; i < num; i++) {
 		REG_SET(MPCC_OGAM_LUT_DATA[mpcc_id], 0, MPCC_OGAM_LUT_DATA, rgb[i].red_reg);
 		REG_SET(MPCC_OGAM_LUT_DATA[mpcc_id], 0, MPCC_OGAM_LUT_DATA, rgb[i].green_reg);
@@ -463,6 +503,11 @@ void mpc2_assert_mpcc_idle_before_connect(struct mpc *mpc, int mpcc_id)
 		ASSERT(!mpc_disabled);
 		ASSERT(!mpc_idle);
 	}
+
+	REG_SEQ_SUBMIT();
+	PERF_TRACE();
+	REG_SEQ_WAIT_DONE();
+	PERF_TRACE();
 }
 
 static void mpc2_init_mpcc(struct mpcc *mpcc, int mpcc_inst)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
index 9f53192da2dc..c78fd5123497 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_mpc.h
@@ -80,6 +80,10 @@
 	SRII(DENORM_CLAMP_G_Y, MPC_OUT, inst),\
 	SRII(DENORM_CLAMP_B_CB, MPC_OUT, inst)
 
+#define MPC_DBG_REG_LIST_DCN2_0() \
+	SR(MPC_OCSC_TEST_DEBUG_DATA),\
+	SR(MPC_OCSC_TEST_DEBUG_INDEX)
+
 #define MPC_REG_VARIABLE_LIST_DCN2_0 \
 	MPC_COMMON_REG_VARIABLE_LIST \
 	uint32_t MPCC_TOP_GAIN[MAX_MPCC]; \
@@ -118,6 +122,8 @@
 	uint32_t MPCC_OGAM_LUT_RAM_CONTROL[MAX_MPCC];\
 	uint32_t MPCC_OGAM_LUT_DATA[MAX_MPCC];\
 	uint32_t MPCC_OGAM_MODE[MAX_MPCC];\
+	uint32_t MPC_OCSC_TEST_DEBUG_DATA;\
+	uint32_t MPC_OCSC_TEST_DEBUG_INDEX;\
 	uint32_t CSC_MODE[MAX_OPP]; \
 	uint32_t CSC_C11_C12_A[MAX_OPP]; \
 	uint32_t CSC_C33_C34_A[MAX_OPP]; \
@@ -134,6 +140,7 @@
 	SF(MPCC0_MPCC_TOP_GAIN, MPCC_TOP_GAIN, mask_sh),\
 	SF(MPCC0_MPCC_BOT_GAIN_INSIDE, MPCC_BOT_GAIN_INSIDE, mask_sh),\
 	SF(MPCC0_MPCC_BOT_GAIN_OUTSIDE, MPCC_BOT_GAIN_OUTSIDE, mask_sh),\
+	SF(MPC_OCSC_TEST_DEBUG_INDEX, MPC_OCSC_TEST_DEBUG_INDEX, mask_sh),\
 	SF(MPC_OUT0_CSC_MODE, MPC_OCSC_MODE, mask_sh),\
 	SF(MPC_OUT0_CSC_C11_C12_A, MPC_OCSC_C11_A, mask_sh),\
 	SF(MPC_OUT0_CSC_C11_C12_A, MPC_OCSC_C12_A, mask_sh),\
@@ -174,6 +181,19 @@
 	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MAX_B_CB, mask_sh),\
 	SF(MPC_OUT0_DENORM_CLAMP_B_CB, MPC_OUT_DENORM_CLAMP_MIN_B_CB, mask_sh)
 
+/*
+ *	DCN2 MPC_OCSC debug status register:
+ *
+ *		Status index including current OCSC Mode is 1
+ *			OCSC Mode: [1..0]
+ */
+#define MPC_OCSC_TEST_DEBUG_DATA_STATUS_IDX 1
+
+#define MPC_DEBUG_REG_LIST_SH_DCN20 \
+	.MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE = 0
+
+#define MPC_DEBUG_REG_LIST_MASK_DCN20 \
+	.MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE = 0x3
 
 #define MPC_REG_FIELD_LIST_DCN2_0(type) \
 	MPC_REG_FIELD_LIST(type)\
@@ -182,6 +202,8 @@
 	type MPCC_TOP_GAIN;\
 	type MPCC_BOT_GAIN_INSIDE;\
 	type MPCC_BOT_GAIN_OUTSIDE;\
+	type MPC_OCSC_TEST_DEBUG_DATA_OCSC_MODE;\
+	type MPC_OCSC_TEST_DEBUG_INDEX;\
 	type MPC_OCSC_MODE;\
 	type MPC_OCSC_C11_A;\
 	type MPC_OCSC_C12_A;\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
index 40164ed015ea..023cc71fad0f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c
@@ -41,6 +41,7 @@
 void opp2_set_disp_pattern_generator(
 		struct output_pixel_processor *opp,
 		enum controller_dp_test_pattern test_pattern,
+		enum controller_dp_color_space color_space,
 		enum dc_color_depth color_depth,
 		const struct tg_color *solid_color,
 		int width,
@@ -100,9 +101,22 @@ void opp2_set_disp_pattern_generator(
 				TEST_PATTERN_DYN_RANGE_CEA :
 				TEST_PATTERN_DYN_RANGE_VESA);
 
+		switch (color_space) {
+		case CONTROLLER_DP_COLOR_SPACE_YCBCR601:
+			mode = TEST_PATTERN_MODE_COLORSQUARES_YCBCR601;
+		break;
+		case CONTROLLER_DP_COLOR_SPACE_YCBCR709:
+			mode = TEST_PATTERN_MODE_COLORSQUARES_YCBCR709;
+		break;
+		case CONTROLLER_DP_COLOR_SPACE_RGB:
+		default:
+			mode = TEST_PATTERN_MODE_COLORSQUARES_RGB;
+		break;
+		}
+
 		REG_UPDATE_6(DPG_CONTROL,
 			DPG_EN, 1,
-			DPG_MODE, TEST_PATTERN_MODE_COLORSQUARES_RGB,
+			DPG_MODE, mode,
 			DPG_DYNAMIC_RANGE, dyn_range,
 			DPG_BIT_DEPTH, bit_depth,
 			DPG_VRES, 6,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
index abd8de9a78f8..4093bec172c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h
@@ -140,6 +140,7 @@ void dcn20_opp_construct(struct dcn20_opp *oppn20,
 void opp2_set_disp_pattern_generator(
 	struct output_pixel_processor *opp,
 	enum controller_dp_test_pattern test_pattern,
+	enum controller_dp_color_space color_space,
 	enum dc_color_depth color_depth,
 	const struct tg_color *solid_color,
 	int width,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index 3b613fb93ef8..d875b0c38fde 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -59,11 +59,16 @@ bool optc2_enable_crtc(struct timing_generator *optc)
 	REG_UPDATE(CONTROL,
 			VTG0_ENABLE, 1);
 
+	REG_SEQ_START();
+
 	/* Enable CRTC */
 	REG_UPDATE_2(OTG_CONTROL,
 			OTG_DISABLE_POINT_CNTL, 3,
 			OTG_MASTER_EN, 1);
 
+	REG_SEQ_SUBMIT();
+	REG_SEQ_WAIT_DONE();
+
 	return true;
 }
 
@@ -167,7 +172,6 @@ void optc2_set_gsl_source_select(
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* DSC encoder frame start controls: x = h position, line_num = # of lines from vstartup */
 void optc2_set_dsc_encoder_frame_start(struct timing_generator *optc,
 					int x_position,
@@ -201,13 +205,12 @@ void optc2_set_dsc_config(struct timing_generator *optc,
 	REG_UPDATE(OPTC_WIDTH_CONTROL,
 		OPTC_DSC_SLICE_WIDTH, dsc_slice_width);
 }
-#endif
 
-/**
- * PTI i think is already done somewhere else for 2ka
- * (opp?, please double check.
- * OPTC side only has 1 register to set for PTI_ENABLE)
- */
+/*TEMP: Need to figure out inheritance model here.*/
+bool optc2_is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
+{
+	return optc1_is_two_pixels_per_containter(timing);
+}
 
 void optc2_set_odm_bypass(struct timing_generator *optc,
 		const struct dc_crtc_timing *dc_crtc_timing)
@@ -221,7 +224,7 @@ void optc2_set_odm_bypass(struct timing_generator *optc,
 			OPTC_SEG1_SRC_SEL, 0xf);
 	REG_WRITE(OTG_H_TIMING_CNTL, 0);
 
-	h_div_2 = optc1_is_two_pixels_per_containter(dc_crtc_timing);
+	h_div_2 = optc2_is_two_pixels_per_containter(dc_crtc_timing);
 	REG_UPDATE(OTG_H_TIMING_CNTL,
 			OTG_H_TIMING_DIV_BY2, h_div_2);
 	REG_SET(OPTC_MEMORY_CONFIG, 0,
@@ -233,12 +236,13 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 		struct dc_crtc_timing *timing)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
-	/* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192 */
 	int mpcc_hactive = (timing->h_addressable + timing->h_border_left + timing->h_border_right)
 			/ opp_cnt;
-	int memory_mask = mpcc_hactive <= 2560 ? 0x3 : 0xf;
+	uint32_t memory_mask;
 	uint32_t data_fmt = 0;
 
+	ASSERT(opp_cnt == 2);
+
 	/* TODO: In pseudocode but does not affect maximus, delete comment if we dont need on asic
 	 * REG_SET(OTG_GLOBAL_CONTROL2, 0, GLOBAL_UPDATE_LOCK_EN, 1);
 	 * Program OTG register MASTER_UPDATE_LOCK_DB_X/Y to the position before DP frame start
@@ -246,9 +250,17 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 	 *		MASTER_UPDATE_LOCK_DB_X, 160,
 	 *		MASTER_UPDATE_LOCK_DB_Y, 240);
 	 */
+
+	/* 2 pieces of memory required for up to 5120 displays, 4 for up to 8192,
+	 * however, for ODM combine we can simplify by always using 4.
+	 * To make sure there's no overlap, each instance "reserves" 2 memories and
+	 * they are uniquely combined here.
+	 */
+	memory_mask = 0x3 << (opp_id[0] * 2) | 0x3 << (opp_id[1] * 2);
+
 	if (REG(OPTC_MEMORY_CONFIG))
 		REG_SET(OPTC_MEMORY_CONFIG, 0,
-			OPTC_MEM_SEL, memory_mask << (optc->inst * 4));
+			OPTC_MEM_SEL, memory_mask);
 
 	if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
 		data_fmt = 1;
@@ -257,7 +269,6 @@ void optc2_set_odm_combine(struct timing_generator *optc, int *opp_id, int opp_c
 
 	REG_UPDATE(OPTC_DATA_FORMAT_CONTROL, OPTC_DATA_FORMAT, data_fmt);
 
-	ASSERT(opp_cnt == 2);
 	REG_SET_3(OPTC_DATA_SOURCE_SELECT, 0,
 			OPTC_NUM_OF_INPUT_SEGMENT, 1,
 			OPTC_SEG0_SRC_SEL, opp_id[0],
@@ -379,14 +390,8 @@ void optc2_setup_manual_trigger(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
 
-	REG_SET(OTG_MANUAL_FLOW_CONTROL, 0,
-			MANUAL_FLOW_CONTROL, 1);
-
-	REG_SET(OTG_GLOBAL_CONTROL2, 0,
-			MANUAL_FLOW_CONTROL_SEL, optc->inst);
-
 	REG_SET_8(OTG_TRIGA_CNTL, 0,
-			OTG_TRIGA_SOURCE_SELECT, 22,
+			OTG_TRIGA_SOURCE_SELECT, 21,
 			OTG_TRIGA_SOURCE_PIPE_SELECT, optc->inst,
 			OTG_TRIGA_RISING_EDGE_DETECT_CNTL, 1,
 			OTG_TRIGA_FALLING_EDGE_DETECT_CNTL, 0,
@@ -448,9 +453,7 @@ static struct timing_generator_funcs dcn20_tg_funcs = {
 		.setup_global_swap_lock = NULL,
 		.get_crc = optc1_get_crc,
 		.configure_crc = optc1_configure_crc,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.set_dsc_config = optc2_set_dsc_config,
-#endif
 		.set_dwb_source = optc2_set_dwb_source,
 		.set_odm_bypass = optc2_set_odm_bypass,
 		.set_odm_combine = optc2_set_odm_combine,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h
index 32a58431fd09..239cc40ae474 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.h
@@ -86,12 +86,10 @@ void optc2_set_gsl_source_select(struct timing_generator *optc,
 		int group_idx,
 		uint32_t gsl_ready_signal);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 void optc2_set_dsc_config(struct timing_generator *optc,
 					enum optc_dsc_mode dsc_mode,
 					uint32_t dsc_bytes_per_pixel,
 					uint32_t dsc_slice_width);
-#endif
 
 void optc2_set_odm_bypass(struct timing_generator *optc,
 		const struct dc_crtc_timing *dc_crtc_timing);
@@ -108,6 +106,7 @@ void optc2_triplebuffer_lock(struct timing_generator *optc);
 void optc2_triplebuffer_unlock(struct timing_generator *optc);
 void optc2_lock_doublebuffer_disable(struct timing_generator *optc);
 void optc2_lock_doublebuffer_enable(struct timing_generator *optc);
+void optc2_setup_manual_trigger(struct timing_generator *optc);
 void optc2_program_manual_trigger(struct timing_generator *optc);
-
+bool optc2_is_two_pixels_per_containter(const struct dc_crtc_timing *timing);
 #endif /* __DC_OPTC_DCN20_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 23ff2f1c75b5..85f90f3e24cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1,5 +1,6 @@
 /*
 * Copyright 2016 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -28,6 +29,8 @@
 #include "dm_services.h"
 #include "dc.h"
 
+#include "dcn20_init.h"
+
 #include "resource.h"
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
@@ -45,9 +48,7 @@
 #include "dcn10/dcn10_resource.h"
 #include "dcn20_opp.h"
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dcn20_dsc.h"
-#endif
 
 #include "dcn20_link_encoder.h"
 #include "dcn20_stream_encoder.h"
@@ -59,11 +60,14 @@
 #include "dml/display_mode_vba.h"
 #include "dcn20_dccg.h"
 #include "dcn20_vmid.h"
+#include "dc_link_ddc.h"
 
 #include "navi10_ip_offset.h"
 
 #include "dcn/dcn_2_0_0_offset.h"
 #include "dcn/dcn_2_0_0_sh_mask.h"
+#include "dpcs/dpcs_2_0_0_offset.h"
+#include "dpcs/dpcs_2_0_0_sh_mask.h"
 
 #include "nbio/nbio_2_3_offset.h"
 
@@ -82,8 +86,6 @@
 
 #include "amdgpu_socbb.h"
 
-/* NV12 SOC BB is currently in FW, mark SW bounding box invalid. */
-#define SOC_BOUNDING_BOX_VALID false
 #define DC_LOGGER_INIT(logger)
 
 struct _vcs_dpi_ip_params_st dcn2_0_ip = {
@@ -94,11 +96,7 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = {
 	.hostvm_max_page_table_levels = 4,
 	.hostvm_cached_page_table_levels = 0,
 	.pte_group_size_bytes = 2048,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.num_dsc = 6,
-#else
-	.num_dsc = 0,
-#endif
 	.rob_buffer_size_kbytes = 168,
 	.det_buffer_size_kbytes = 164,
 	.dpte_buffer_size_in_pte_reqs_luma = 84,
@@ -553,6 +551,7 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
 [id] = {\
 	LE_DCN10_REG_LIST(id), \
 	UNIPHY_DCN2_REG_LIST(phyid), \
+	DPCS_DCN2_REG_LIST(id), \
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
 }
 
@@ -566,11 +565,13 @@ static const struct dcn10_link_enc_registers link_enc_regs[] = {
 };
 
 static const struct dcn10_link_enc_shift le_shift = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT),\
+	DPCS_DCN2_MASK_SH_LIST(__SHIFT)
 };
 
 static const struct dcn10_link_enc_mask le_mask = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK),\
+	DPCS_DCN2_MASK_SH_LIST(_MASK)
 };
 
 #define ipp_regs(id)\
@@ -637,6 +638,7 @@ static const struct dce110_aux_registers aux_engine_regs[] = {
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN20(id),\
+	TF_REG_LIST_DCN20_COMMON_APPEND(id),\
 }
 
 static const struct dcn2_dpp_registers tf_regs[] = {
@@ -650,12 +652,12 @@ static const struct dcn2_dpp_registers tf_regs[] = {
 
 static const struct dcn2_dpp_shift tf_shift = {
 		TF_REG_LIST_SH_MASK_DCN20(__SHIFT),
-		TF_DEBUG_REG_LIST_SH_DCN10
+		TF_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn2_dpp_mask tf_mask = {
 		TF_REG_LIST_SH_MASK_DCN20(_MASK),
-		TF_DEBUG_REG_LIST_MASK_DCN10
+		TF_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define dwbc_regs_dcn2(id)\
@@ -705,14 +707,17 @@ static const struct dcn20_mpc_registers mpc_regs = {
 		MPC_OUT_MUX_REG_LIST_DCN2_0(3),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(4),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(5),
+		MPC_DBG_REG_LIST_DCN2_0()
 };
 
 static const struct dcn20_mpc_shift mpc_shift = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT),
+	MPC_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn20_mpc_mask mpc_mask = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK),
+	MPC_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define tg_regs(id)\
@@ -838,7 +843,6 @@ static int map_transmitter_id_to_phy_instance(
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define dsc_regsDCN20(id)\
 [id] = {\
 	DSC_REG_LIST_DCN20(id)\
@@ -860,7 +864,6 @@ static const struct dcn20_dsc_shift dsc_shift = {
 static const struct dcn20_dsc_mask dsc_mask = {
 	DSC_REG_LIST_SH_MASK_DCN20(_MASK)
 };
-#endif
 
 static const struct dccg_registers dccg_regs = {
 		DCCG_REG_LIST_DCN2()
@@ -884,9 +887,7 @@ static const struct resource_caps res_cap_nv10 = {
 		.num_dwb = 1,
 		.num_ddc = 6,
 		.num_vmid = 16,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 6,
-#endif
 };
 
 static const struct dc_plane_cap plane_cap = {
@@ -923,9 +924,7 @@ static const struct resource_caps res_cap_nv14 = {
 		.num_dwb = 1,
 		.num_ddc = 5,
 		.num_vmid = 16,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 5,
-#endif
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
@@ -1284,7 +1283,6 @@ void dcn20_clock_source_destroy(struct clock_source **clk_src)
 	*clk_src = NULL;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 struct display_stream_compressor *dcn20_dsc_create(
 	struct dc_context *ctx, uint32_t inst)
@@ -1307,9 +1305,8 @@ void dcn20_dsc_destroy(struct display_stream_compressor **dsc)
 	*dsc = NULL;
 }
 
-#endif
 
-static void destruct(struct dcn20_resource_pool *pool)
+static void dcn20_resource_destruct(struct dcn20_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -1320,12 +1317,10 @@ static void destruct(struct dcn20_resource_pool *pool)
 		}
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		if (pool->base.dscs[i] != NULL)
 			dcn20_dsc_destroy(&pool->base.dscs[i]);
 	}
-#endif
 
 	if (pool->base.mpc != NULL) {
 		kfree(TO_DCN20_MPC(pool->base.mpc));
@@ -1418,6 +1413,8 @@ static void destruct(struct dcn20_resource_pool *pool)
 	if (pool->base.pp_smu != NULL)
 		dcn20_pp_smu_destroy(&pool->base.pp_smu);
 
+	if (pool->base.oem_device != NULL)
+		dal_ddc_service_destroy(&pool->base.oem_device);
 }
 
 struct hubp *dcn20_hubp_create(
@@ -1468,7 +1465,7 @@ static void get_pixel_clock_parameters(
 
 	if (opp_cnt == 4)
 		pixel_clk_params->requested_pix_clk_100hz /= 4;
-	else if (optc1_is_two_pixels_per_containter(&stream->timing) || opp_cnt == 2)
+	else if (optc2_is_two_pixels_per_containter(&stream->timing) || opp_cnt == 2)
 		pixel_clk_params->requested_pix_clk_100hz /= 2;
 
 	if (stream->timing.timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING)
@@ -1534,7 +1531,6 @@ enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state
 	return status;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 static void acquire_dsc(struct resource_context *res_ctx,
 			const struct resource_pool *pool,
@@ -1575,11 +1571,9 @@ static void release_dsc(struct resource_context *res_ctx,
 		}
 }
 
-#endif
 
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-static enum dc_status add_dsc_to_stream_resource(struct dc *dc,
+enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc,
 		struct dc_state *dc_ctx,
 		struct dc_stream_state *dc_stream)
 {
@@ -1594,11 +1588,13 @@ static enum dc_status add_dsc_to_stream_resource(struct dc *dc,
 		if (pipe_ctx->stream != dc_stream)
 			continue;
 
+		if (pipe_ctx->stream_res.dsc)
+			continue;
+
 		acquire_dsc(&dc_ctx->res_ctx, pool, &pipe_ctx->stream_res.dsc, i);
 
 		/* The number of DSCs can be less than the number of pipes */
 		if (!pipe_ctx->stream_res.dsc) {
-			dm_output_to_console("No DSCs available\n");
 			result = DC_NO_DSC_RESOURCE;
 		}
 
@@ -1630,7 +1626,6 @@ static enum dc_status remove_dsc_from_stream_resource(struct dc *dc,
 	else
 		return DC_OK;
 }
-#endif
 
 
 enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream)
@@ -1642,11 +1637,9 @@ enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx,
 	if (result == DC_OK)
 		result = resource_map_phy_clock_resources(dc, new_ctx, dc_stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Get a DSC if required and available */
 	if (result == DC_OK && dc_stream->timing.flags.DSC)
-		result = add_dsc_to_stream_resource(dc, new_ctx, dc_stream);
-#endif
+		result = dcn20_add_dsc_to_stream_resource(dc, new_ctx, dc_stream);
 
 	if (result == DC_OK)
 		result = dcn20_build_mapped_resource(dc, new_ctx, dc_stream);
@@ -1659,9 +1652,7 @@ enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_
 {
 	enum dc_status result = DC_OK;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	result = remove_dsc_from_stream_resource(dc, new_ctx, dc_stream);
-#endif
 
 	return result;
 }
@@ -1744,9 +1735,7 @@ bool dcn20_split_stream_for_odm(
 	next_odm_pipe->plane_res.xfm = pool->transforms[next_odm_pipe->pipe_idx];
 	next_odm_pipe->plane_res.dpp = pool->dpps[next_odm_pipe->pipe_idx];
 	next_odm_pipe->plane_res.mpcc_inst = pool->dpps[next_odm_pipe->pipe_idx]->inst;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	next_odm_pipe->stream_res.dsc = NULL;
-#endif
 	if (prev_odm_pipe->next_odm_pipe && prev_odm_pipe->next_odm_pipe != next_odm_pipe) {
 		next_odm_pipe->next_odm_pipe = prev_odm_pipe->next_odm_pipe;
 		next_odm_pipe->next_odm_pipe->prev_odm_pipe = next_odm_pipe;
@@ -1792,14 +1781,12 @@ bool dcn20_split_stream_for_odm(
 		sd->recout.x = 0;
 	}
 	next_odm_pipe->stream_res.opp = pool->opps[next_odm_pipe->pipe_idx];
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	if (next_odm_pipe->stream->timing.flags.DSC == 1) {
 		acquire_dsc(res_ctx, pool, &next_odm_pipe->stream_res.dsc, next_odm_pipe->pipe_idx);
 		ASSERT(next_odm_pipe->stream_res.dsc);
 		if (next_odm_pipe->stream_res.dsc == NULL)
 			return false;
 	}
-#endif
 
 	return true;
 }
@@ -1823,9 +1810,7 @@ void dcn20_split_stream_for_mpc(
 	secondary_pipe->plane_res.xfm = pool->transforms[secondary_pipe->pipe_idx];
 	secondary_pipe->plane_res.dpp = pool->dpps[secondary_pipe->pipe_idx];
 	secondary_pipe->plane_res.mpcc_inst = pool->dpps[secondary_pipe->pipe_idx]->inst;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	secondary_pipe->stream_res.dsc = NULL;
-#endif
 	if (primary_pipe->bottom_pipe && primary_pipe->bottom_pipe != secondary_pipe) {
 		ASSERT(!secondary_pipe->bottom_pipe);
 		secondary_pipe->bottom_pipe = primary_pipe->bottom_pipe;
@@ -1876,11 +1861,28 @@ void dcn20_populate_dml_writeback_from_context(
 
 }
 
+static int get_num_odm_heads(struct pipe_ctx *pipe)
+{
+	int odm_head_count = 0;
+	struct pipe_ctx *next_pipe = pipe->next_odm_pipe;
+	while (next_pipe) {
+		odm_head_count++;
+		next_pipe = next_pipe->next_odm_pipe;
+	}
+	pipe = pipe->prev_odm_pipe;
+	while (pipe) {
+		odm_head_count++;
+		pipe = pipe->prev_odm_pipe;
+	}
+	return odm_head_count ? odm_head_count + 1 : 0;
+}
+
 int dcn20_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes)
 {
 	int pipe_cnt, i;
 	bool synchronized_vblank = true;
+	struct resource_context *res_ctx = &context->res_ctx;
 
 	for (i = 0, pipe_cnt = -1; i < dc->res_pool->pipe_count; i++) {
 		if (!res_ctx->pipe_ctx[i].stream)
@@ -1900,25 +1902,30 @@ int dcn20_populate_dml_pipes_from_context(
 
 	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 		struct dc_crtc_timing *timing = &res_ctx->pipe_ctx[i].stream->timing;
+		unsigned int v_total;
+		unsigned int front_porch;
 		int output_bpc;
 
 		if (!res_ctx->pipe_ctx[i].stream)
 			continue;
+
+		v_total = timing->v_total;
+		front_porch = timing->v_front_porch;
 		/* todo:
 		pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = 0;
 		pipes[pipe_cnt].pipe.src.dcc = 0;
 		pipes[pipe_cnt].pipe.src.vm = 0;*/
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+		pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0;
+
 		pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC;
 		/* todo: rotation?*/
 		pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h;
-#endif
 		if (res_ctx->pipe_ctx[i].stream->use_dynamic_meta) {
 			pipes[pipe_cnt].pipe.src.dynamic_metadata_enable = true;
 			/* 1/2 vblank */
 			pipes[pipe_cnt].pipe.src.dynamic_metadata_lines_before_active =
-				(timing->v_total - timing->v_addressable
+				(v_total - timing->v_addressable
 					- timing->v_border_top - timing->v_border_bottom) / 2;
 			/* 36 bytes dp, 32 hdmi */
 			pipes[pipe_cnt].pipe.src.dynamic_metadata_xmit_bytes =
@@ -1932,13 +1939,13 @@ int dcn20_populate_dml_pipes_from_context(
 				- timing->h_addressable
 				- timing->h_border_left
 				- timing->h_border_right;
-		pipes[pipe_cnt].pipe.dest.vblank_start = timing->v_total - timing->v_front_porch;
+		pipes[pipe_cnt].pipe.dest.vblank_start = v_total - front_porch;
 		pipes[pipe_cnt].pipe.dest.vblank_end = pipes[pipe_cnt].pipe.dest.vblank_start
 				- timing->v_addressable
 				- timing->v_border_top
 				- timing->v_border_bottom;
 		pipes[pipe_cnt].pipe.dest.htotal = timing->h_total;
-		pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total;
+		pipes[pipe_cnt].pipe.dest.vtotal = v_total;
 		pipes[pipe_cnt].pipe.dest.hactive = timing->h_addressable;
 		pipes[pipe_cnt].pipe.dest.vactive = timing->v_addressable;
 		pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE;
@@ -1949,8 +1956,13 @@ int dcn20_populate_dml_pipes_from_context(
 		pipes[pipe_cnt].dout.dp_lanes = 4;
 		pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min;
 		pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max;
-		pipes[pipe_cnt].pipe.dest.odm_combine = res_ctx->pipe_ctx[i].prev_odm_pipe
-							|| res_ctx->pipe_ctx[i].next_odm_pipe;
+		switch (get_num_odm_heads(&res_ctx->pipe_ctx[i])) {
+		case 2:
+			pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_2to1;
+			break;
+		default:
+			pipes[pipe_cnt].pipe.dest.odm_combine = dm_odm_combine_mode_disabled;
+		}
 		pipes[pipe_cnt].pipe.src.hsplit_grp = res_ctx->pipe_ctx[i].pipe_idx;
 		if (res_ctx->pipe_ctx[i].top_pipe && res_ctx->pipe_ctx[i].top_pipe->plane_state
 				== res_ctx->pipe_ctx[i].plane_state)
@@ -2001,14 +2013,12 @@ int dcn20_populate_dml_pipes_from_context(
 		case COLOR_DEPTH_161616:
 			output_bpc = 16;
 			break;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 		case COLOR_DEPTH_999:
 			output_bpc = 9;
 			break;
 		case COLOR_DEPTH_111111:
 			output_bpc = 11;
 			break;
-#endif
 		default:
 			output_bpc = 8;
 			break;
@@ -2036,10 +2046,8 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].dout.output_bpp = output_bpc * 3;
 		}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC)
 			pipes[pipe_cnt].dout.output_bpp = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.bits_per_pixel / 16.0;
-#endif
 
 		/* todo: default max for now, until there is logic reflecting this in dc*/
 		pipes[pipe_cnt].dout.output_bpc = 12;
@@ -2063,6 +2071,10 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.src.viewport_height = timing->v_addressable;
 			if (pipes[pipe_cnt].pipe.src.viewport_height > 1080)
 				pipes[pipe_cnt].pipe.src.viewport_height = 1080;
+			pipes[pipe_cnt].pipe.src.surface_height_y = pipes[pipe_cnt].pipe.src.viewport_height;
+			pipes[pipe_cnt].pipe.src.surface_width_y = pipes[pipe_cnt].pipe.src.viewport_width;
+			pipes[pipe_cnt].pipe.src.surface_height_c = pipes[pipe_cnt].pipe.src.viewport_height;
+			pipes[pipe_cnt].pipe.src.surface_width_c = pipes[pipe_cnt].pipe.src.viewport_width;
 			pipes[pipe_cnt].pipe.src.data_pitch = ((pipes[pipe_cnt].pipe.src.viewport_width + 63) / 64) * 64; /* linear sw only */
 			pipes[pipe_cnt].pipe.src.source_format = dm_444_32;
 			pipes[pipe_cnt].pipe.dest.recout_width = pipes[pipe_cnt].pipe.src.viewport_width; /*vp_width/hratio*/
@@ -2077,8 +2089,8 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.scale_taps.vtaps = 1;
 			pipes[pipe_cnt].pipe.src.is_hsplit = 0;
 			pipes[pipe_cnt].pipe.dest.odm_combine = 0;
-			pipes[pipe_cnt].pipe.dest.vtotal_min = timing->v_total;
-			pipes[pipe_cnt].pipe.dest.vtotal_max = timing->v_total;
+			pipes[pipe_cnt].pipe.dest.vtotal_min = v_total;
+			pipes[pipe_cnt].pipe.dest.vtotal_max = v_total;
 		} else {
 			struct dc_plane_state *pln = res_ctx->pipe_ctx[i].plane_state;
 			struct scaler_data *scl = &res_ctx->pipe_ctx[i].plane_res.scl_data;
@@ -2096,6 +2108,10 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.src.viewport_width_c = scl->viewport_c.width;
 			pipes[pipe_cnt].pipe.src.viewport_height = scl->viewport.height;
 			pipes[pipe_cnt].pipe.src.viewport_height_c = scl->viewport_c.height;
+			pipes[pipe_cnt].pipe.src.surface_width_y = pln->plane_size.surface_size.width;
+			pipes[pipe_cnt].pipe.src.surface_height_y = pln->plane_size.surface_size.height;
+			pipes[pipe_cnt].pipe.src.surface_width_c = pln->plane_size.chroma_size.width;
+			pipes[pipe_cnt].pipe.src.surface_height_c = pln->plane_size.chroma_size.height;
 			if (pln->format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
 				pipes[pipe_cnt].pipe.src.data_pitch = pln->plane_size.surface_pitch;
 				pipes[pipe_cnt].pipe.src.data_pitch_c = pln->plane_size.chroma_pitch;
@@ -2261,7 +2277,6 @@ void dcn20_set_mcif_arb_params(
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
 {
 	int i;
@@ -2295,7 +2310,6 @@ bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
 	}
 	return true;
 }
-#endif
 
 struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 		struct resource_context *res_ctx,
@@ -2398,10 +2412,8 @@ void dcn20_merge_pipes_for_validate(
 			odm_pipe->bottom_pipe = NULL;
 			odm_pipe->prev_odm_pipe = NULL;
 			odm_pipe->next_odm_pipe = NULL;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 			if (odm_pipe->stream_res.dsc)
 				release_dsc(&context->res_ctx, dc->res_pool, &odm_pipe->stream_res.dsc);
-#endif
 			/* Clear plane_res and stream_res */
 			memset(&odm_pipe->plane_res, 0, sizeof(odm_pipe->plane_res));
 			memset(&odm_pipe->stream_res, 0, sizeof(odm_pipe->stream_res));
@@ -2513,7 +2525,7 @@ int dcn20_validate_apply_pipe_split_flags(
 			split[i] = true;
 		if (dc->debug.force_odm_combine & (1 << pipe->stream_res.tg->inst)) {
 			split[i] = true;
-			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = true;
+			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = dm_odm_combine_mode_2to1;
 		}
 		context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx] =
 			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx];
@@ -2544,7 +2556,7 @@ bool dcn20_fast_validate_bw(
 
 	dcn20_merge_pipes_for_validate(dc, context);
 
-	pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, &context->res_ctx, pipes);
+	pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes);
 
 	*pipe_cnt_out = pipe_cnt;
 
@@ -2621,14 +2633,12 @@ bool dcn20_fast_validate_bw(
 			ASSERT(0);
 		}
 	}
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Actual dsc count per stream dsc validation*/
 	if (!dcn20_validate_dsc(dc, context)) {
 		context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states] =
 				DML_FAIL_DSC_VALIDATION_FAILURE;
 		goto validate_fail;
 	}
-#endif
 
 	*vlevel_out = vlevel;
 
@@ -2692,10 +2702,10 @@ static void dcn20_calculate_wm(
 	if (pipe_cnt != pipe_idx) {
 		if (dc->res_pool->funcs->populate_dml_pipes)
 			pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 		else
 			pipe_cnt = dcn20_populate_dml_pipes_from_context(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 	}
 
 	*out_pipe_cnt = pipe_cnt;
@@ -2715,11 +2725,9 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 
 	if (vlevel < 2) {
 		pipes[0].clks_cfg.voltage = 2;
@@ -2731,10 +2739,8 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 
 	if (vlevel < 3) {
 		pipes[0].clks_cfg.voltage = 3;
@@ -2746,10 +2752,8 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 
 	pipes[0].clks_cfg.voltage = vlevel;
 	pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz;
@@ -2759,10 +2763,8 @@ static void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-#endif
 }
 
 void dcn20_calculate_dlg_params(
@@ -2928,11 +2930,19 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 	bool voltage_supported = false;
 	bool full_pstate_supported = false;
 	bool dummy_pstate_supported = false;
-	double p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
+	double p_state_latency_us;
 
-	if (fast_validate)
-		return dcn20_validate_bandwidth_internal(dc, context, true);
+	DC_FP_START();
+	p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
+	context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
+		dc->debug.disable_dram_clock_change_vactive_support;
 
+	if (fast_validate) {
+		voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true);
+
+		DC_FP_END();
+		return voltage_supported;
+	}
 
 	// Best case, we support full UCLK switch latency
 	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
@@ -2940,7 +2950,7 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 
 	if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 ||
 		(voltage_supported && full_pstate_supported)) {
-		context->bw_ctx.bw.dcn.clk.p_state_change_support = true;
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported;
 		goto restore_dml_state;
 	}
 
@@ -2961,6 +2971,7 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 restore_dml_state:
 	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
 
+	DC_FP_END();
 	return voltage_supported;
 }
 
@@ -3005,7 +3016,7 @@ static void dcn20_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn20_resource_pool *dcn20_pool = TO_DCN20_RES_POOL(*pool);
 
-	destruct(dcn20_pool);
+	dcn20_resource_destruct(dcn20_pool);
 	kfree(dcn20_pool);
 	*pool = NULL;
 }
@@ -3252,7 +3263,6 @@ void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 
 void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb)
 {
-	kernel_fpu_begin();
 	if ((int)(bb->sr_exit_time_us * 1000) != dc->bb_overrides.sr_exit_time_ns
 			&& dc->bb_overrides.sr_exit_time_ns) {
 		bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0;
@@ -3276,7 +3286,6 @@ void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st
 		bb->dram_clock_change_latency_us =
 				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
 	}
-	kernel_fpu_end();
 }
 
 static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb(
@@ -3318,12 +3327,13 @@ static bool init_soc_bounding_box(struct dc *dc,
 
 	DC_LOGGER_INIT(dc->ctx->logger);
 
-	if (!bb && !SOC_BOUNDING_BOX_VALID) {
+	/* TODO: upstream NV12 bounding box when its launched */
+	if (!bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		DC_LOG_ERROR("%s: not valid soc bounding box/n", __func__);
 		return false;
 	}
 
-	if (bb && !SOC_BOUNDING_BOX_VALID) {
+	if (bb && ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev)) {
 		int i;
 
 		dcn2_0_nv12_soc.sr_exit_time_us =
@@ -3465,7 +3475,7 @@ static bool init_soc_bounding_box(struct dc *dc,
 	return true;
 }
 
-static bool construct(
+static bool dcn20_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dcn20_resource_pool *pool)
@@ -3473,6 +3483,7 @@ static bool construct(
 	int i;
 	struct dc_context *ctx = dc->ctx;
 	struct irq_service_init_data init_data;
+	struct ddc_service_init_data ddc_init_data;
 	struct _vcs_dpi_soc_bounding_box_st *loaded_bb =
 			get_asic_rev_soc_bb(ctx->asic_id.hw_internal_rev);
 	struct _vcs_dpi_ip_params_st *loaded_ip =
@@ -3480,6 +3491,8 @@ static bool construct(
 	enum dml_project dml_project_version =
 			get_dml_project_version(ctx->asic_id.hw_internal_rev);
 
+	DC_FP_START();
+
 	ctx->dc_bios->regs = &bios_regs;
 	pool->base.funcs = &dcn20_res_pool_funcs;
 
@@ -3732,7 +3745,6 @@ static bool construct(
 		goto create_fail;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		pool->base.dscs[i] = dcn20_dsc_create(ctx, i);
 		if (pool->base.dscs[i] == NULL) {
@@ -3741,7 +3753,6 @@ static bool construct(
 			goto create_fail;
 		}
 	}
-#endif
 
 	if (!dcn20_dwbc_create(ctx, &pool->base)) {
 		BREAK_TO_DEBUGGER();
@@ -3768,11 +3779,24 @@ static bool construct(
 
 	dc->cap_funcs = cap_funcs;
 
+	if (dc->ctx->dc_bios->fw_info.oem_i2c_present) {
+		ddc_init_data.ctx = dc->ctx;
+		ddc_init_data.link = NULL;
+		ddc_init_data.id.id = dc->ctx->dc_bios->fw_info.oem_i2c_obj_id;
+		ddc_init_data.id.enum_id = 0;
+		ddc_init_data.id.type = OBJECT_TYPE_GENERIC;
+		pool->base.oem_device = dal_ddc_service_create(&ddc_init_data);
+	} else {
+		pool->base.oem_device = NULL;
+	}
+
+	DC_FP_END();
 	return true;
 
 create_fail:
 
-	destruct(pool);
+	DC_FP_END();
+	dcn20_resource_destruct(pool);
 
 	return false;
 }
@@ -3787,7 +3811,7 @@ struct resource_pool *dcn20_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(init_data->num_virtual_links, dc, pool))
+	if (dcn20_resource_construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
 	BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
index fef473d68a4a..f5893840b79b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
@@ -50,7 +50,7 @@ unsigned int dcn20_calc_max_scaled_time(
 		enum mmhubbub_wbif_mode mode,
 		unsigned int urgent_watermark);
 int dcn20_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes);
 struct pipe_ctx *dcn20_acquire_idle_pipe_for_layer(
 		struct dc_state *state,
 		const struct resource_pool *pool,
@@ -127,9 +127,7 @@ int dcn20_validate_apply_pipe_split_flags(
 		struct dc_state *context,
 		int vlevel,
 		bool *split);
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx);
-#endif
 void dcn20_split_stream_for_mpc(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -159,6 +157,7 @@ void dcn20_calculate_dlg_params(
 
 enum dc_status dcn20_build_mapped_resource(const struct dc *dc, struct dc_state *context, struct dc_stream_state *stream);
 enum dc_status dcn20_add_stream_to_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream);
+enum dc_status dcn20_add_dsc_to_stream_resource(struct dc *dc, struct dc_state *dc_ctx, struct dc_stream_state *dc_stream);
 enum dc_status dcn20_remove_stream_from_ctx(struct dc *dc, struct dc_state *new_ctx, struct dc_stream_state *dc_stream);
 enum dc_status dcn20_get_default_swizzle_mode(struct dc_plane_state *plane_state);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
index fcb3877b4fcb..9b70a1e7b962 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
@@ -205,7 +205,6 @@ static void enc2_stream_encoder_stop_hdmi_info_packets(
 		HDMI_GENERIC7_LINE, 0);
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 /* Update GSP7 SDP 128 byte long */
 static void enc2_update_gsp7_128_info_packet(
@@ -360,7 +359,6 @@ static void enc2_read_state(struct stream_encoder *enc, struct enc_state *s)
 		REG_GET(DP_SEC_CNTL, DP_SEC_STREAM_ENABLE, &s->sec_stream_enable);
 	}
 }
-#endif
 
 /* Set Dynamic Metadata-configuration.
  *   enable_dme:         TRUE: enables Dynamic Metadata Enfine, FALSE: disables DME
@@ -440,10 +438,8 @@ static bool is_two_pixels_per_containter(const struct dc_crtc_timing *timing)
 {
 	bool two_pix = timing->pixel_encoding == PIXEL_ENCODING_YCBCR420;
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	two_pix = two_pix || (timing->flags.DSC && timing->pixel_encoding == PIXEL_ENCODING_YCBCR422
 			&& !timing->dsc_cfg.ycbcr422_simple);
-#endif
 	return two_pix;
 }
 
@@ -541,11 +537,16 @@ void enc2_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting)
 {
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	enc1_stream_encoder_dp_set_stream_attribute(enc, crtc_timing, output_color_space, enable_sdp_splitting);
+	enc1_stream_encoder_dp_set_stream_attribute(enc,
+			crtc_timing,
+			output_color_space,
+			use_vsc_sdp_for_colorimetry,
+			enable_sdp_splitting);
 
 	REG_UPDATE(DP_SEC_FRAMING4,
 		DP_SST_SDP_SPLITTING, enable_sdp_splitting);
@@ -568,6 +569,8 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = {
 		enc2_stream_encoder_stop_hdmi_info_packets,
 	.update_dp_info_packets =
 		enc2_stream_encoder_update_dp_info_packets,
+	.send_immediate_sdp_message =
+		enc1_stream_encoder_send_immediate_sdp_message,
 	.stop_dp_info_packets =
 		enc1_stream_encoder_stop_dp_info_packets,
 	.dp_blank =
@@ -590,11 +593,9 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = {
 	.dp_get_pixel_format =
 		enc1_stream_encoder_dp_get_pixel_format,
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.enc_read_state = enc2_read_state,
 	.dp_set_dsc_config = enc2_dp_set_dsc_config,
 	.dp_set_dsc_pps_info_packet = enc2_dp_set_dsc_pps_info_packet,
-#endif
 	.set_dynamic_metadata = enc2_set_dynamic_metadata,
 	.hdmi_reset_stream_attribute = enc1_reset_hdmi_stream_attribute,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h
index 3f94a9f13c4a..d2a805bd4573 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h
@@ -98,6 +98,7 @@ void enc2_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting);
 
 void enc2_stream_encoder_dp_unblank(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 5b8c17564bc1..07684d3e375a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -2,9 +2,16 @@
 #
 # Makefile for DCN21.
 
-DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o dcn21_hwseq.o dcn21_link_encoder.o
+DCN21 = dcn21_init.o dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o \
+	 dcn21_hwseq.o dcn21_link_encoder.o
 
+ifdef CONFIG_X86
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -12,6 +19,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -20,6 +28,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
 else
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
 endif
+endif
 
 AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
index 2f5a5867e674..da63fc53cc4a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
@@ -29,6 +29,10 @@
 #include "dm_services.h"
 #include "reg_helper.h"
 
+#include "dc_dmub_srv.h"
+
+#define DC_LOGGER_INIT(logger)
+
 #define REG(reg)\
 	hubp21->hubp_regs->reg
 
@@ -164,6 +168,158 @@ static void hubp21_setup(
 
 }
 
+void hubp21_set_viewport(
+	struct hubp *hubp,
+	const struct rect *viewport,
+	const struct rect *viewport_c)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+
+	REG_SET_2(DCSURF_PRI_VIEWPORT_DIMENSION, 0,
+		  PRI_VIEWPORT_WIDTH, viewport->width,
+		  PRI_VIEWPORT_HEIGHT, viewport->height);
+
+	REG_SET_2(DCSURF_PRI_VIEWPORT_START, 0,
+		  PRI_VIEWPORT_X_START, viewport->x,
+		  PRI_VIEWPORT_Y_START, viewport->y);
+
+	/*for stereo*/
+	REG_SET_2(DCSURF_SEC_VIEWPORT_DIMENSION, 0,
+		  SEC_VIEWPORT_WIDTH, viewport->width,
+		  SEC_VIEWPORT_HEIGHT, viewport->height);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_START, 0,
+		  SEC_VIEWPORT_X_START, viewport->x,
+		  SEC_VIEWPORT_Y_START, viewport->y);
+
+	/* DC supports NV12 only at the moment */
+	REG_SET_2(DCSURF_PRI_VIEWPORT_DIMENSION_C, 0,
+		  PRI_VIEWPORT_WIDTH_C, viewport_c->width,
+		  PRI_VIEWPORT_HEIGHT_C, viewport_c->height);
+
+	REG_SET_2(DCSURF_PRI_VIEWPORT_START_C, 0,
+		  PRI_VIEWPORT_X_START_C, viewport_c->x,
+		  PRI_VIEWPORT_Y_START_C, viewport_c->y);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_DIMENSION_C, 0,
+		  SEC_VIEWPORT_WIDTH_C, viewport_c->width,
+		  SEC_VIEWPORT_HEIGHT_C, viewport_c->height);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_START_C, 0,
+		  SEC_VIEWPORT_X_START_C, viewport_c->x,
+		  SEC_VIEWPORT_Y_START_C, viewport_c->y);
+}
+
+static void hubp21_apply_PLAT_54186_wa(
+		struct hubp *hubp,
+		const struct dc_plane_address *address)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct dc_debug_options *debug = &hubp->ctx->dc->debug;
+	unsigned int chroma_bpe = 2;
+	unsigned int luma_addr_high_part = 0;
+	unsigned int row_height = 0;
+	unsigned int chroma_pitch = 0;
+	unsigned int viewport_c_height = 0;
+	unsigned int viewport_c_width = 0;
+	unsigned int patched_viewport_height = 0;
+	unsigned int patched_viewport_width = 0;
+	unsigned int rotation_angle = 0;
+	unsigned int pix_format = 0;
+	unsigned int h_mirror_en = 0;
+	unsigned int tile_blk_size = 64 * 1024; /* 64KB for 64KB SW, 4KB for 4KB SW */
+
+
+	if (!debug->nv12_iflip_vm_wa)
+		return;
+
+	REG_GET(DCHUBP_REQ_SIZE_CONFIG_C,
+		PTE_ROW_HEIGHT_LINEAR_C, &row_height);
+
+	REG_GET_2(DCSURF_PRI_VIEWPORT_DIMENSION_C,
+			PRI_VIEWPORT_WIDTH_C, &viewport_c_width,
+			PRI_VIEWPORT_HEIGHT_C, &viewport_c_height);
+
+	REG_GET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C,
+			PRIMARY_SURFACE_ADDRESS_HIGH_C, &luma_addr_high_part);
+
+	REG_GET(DCSURF_SURFACE_PITCH_C,
+			PITCH_C, &chroma_pitch);
+
+	chroma_pitch += 1;
+
+	REG_GET_3(DCSURF_SURFACE_CONFIG,
+			SURFACE_PIXEL_FORMAT, &pix_format,
+			ROTATION_ANGLE, &rotation_angle,
+			H_MIRROR_EN, &h_mirror_en);
+
+	/* reset persistent cached data */
+	hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+	/* apply wa only for NV12 surface with scatter gather enabled with viewport > 512 along
+	 * the vertical direction*/
+	if (address->type != PLN_ADDR_TYPE_VIDEO_PROGRESSIVE ||
+			address->video_progressive.luma_addr.high_part == 0xf4)
+		return;
+
+	if ((rotation_angle == 0 || rotation_angle == 180)
+			&& viewport_c_height <= 512)
+		return;
+
+	if ((rotation_angle == 90 || rotation_angle == 270)
+				&& viewport_c_width <= 512)
+		return;
+
+	switch (rotation_angle) {
+	case 0: /* 0 degree rotation */
+		row_height = 128;
+		patched_viewport_height = (viewport_c_height / row_height + 1) * row_height + 1;
+		patched_viewport_width = viewport_c_width;
+		hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+		break;
+	case 2: /* 180 degree rotation */
+		row_height = 128;
+		patched_viewport_height = viewport_c_height + row_height;
+		patched_viewport_width = viewport_c_width;
+		hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - chroma_pitch * row_height * chroma_bpe;
+		break;
+	case 1: /* 90 degree rotation */
+		row_height = 256;
+		if (h_mirror_en) {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+		} else {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - tile_blk_size;
+		}
+		break;
+	case 3:	/* 270 degree rotation */
+		row_height = 256;
+		if (h_mirror_en) {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0 - tile_blk_size;
+		} else {
+			patched_viewport_height = viewport_c_height;
+			patched_viewport_width = viewport_c_width + row_height;
+			hubp21->PLAT_54186_wa_chroma_addr_offset = 0;
+		}
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
+
+	/* catch cases where viewport keep growing */
+	ASSERT(patched_viewport_height && patched_viewport_height < 5000);
+	ASSERT(patched_viewport_width && patched_viewport_width < 5000);
+
+	REG_UPDATE_2(DCSURF_PRI_VIEWPORT_DIMENSION_C,
+			PRI_VIEWPORT_WIDTH_C, patched_viewport_width,
+			PRI_VIEWPORT_HEIGHT_C, patched_viewport_height);
+}
+
 void hubp21_set_vm_system_aperture_settings(struct hubp *hubp,
 		struct vm_system_aperture_param *apt)
 {
@@ -191,6 +347,562 @@ void hubp21_set_vm_system_aperture_settings(struct hubp *hubp,
 			SYSTEM_ACCESS_MODE, 0x3);
 }
 
+void hubp21_validate_dml_output(struct hubp *hubp,
+		struct dc_context *ctx,
+		struct _vcs_dpi_display_rq_regs_st *dml_rq_regs,
+		struct _vcs_dpi_display_dlg_regs_st *dml_dlg_attr,
+		struct _vcs_dpi_display_ttu_regs_st *dml_ttu_attr)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct _vcs_dpi_display_rq_regs_st rq_regs = {0};
+	struct _vcs_dpi_display_dlg_regs_st dlg_attr = {0};
+	struct _vcs_dpi_display_ttu_regs_st ttu_attr = {0};
+	DC_LOGGER_INIT(ctx->logger);
+	DC_LOG_DEBUG("DML Validation | Running Validation");
+
+	/* Requester - Per hubp */
+	REG_GET(HUBPRET_CONTROL,
+		DET_BUF_PLANE1_BASE_ADDRESS, &rq_regs.plane1_base_address);
+	REG_GET_4(DCN_EXPANSION_MODE,
+		DRQ_EXPANSION_MODE, &rq_regs.drq_expansion_mode,
+		PRQ_EXPANSION_MODE, &rq_regs.prq_expansion_mode,
+		MRQ_EXPANSION_MODE, &rq_regs.mrq_expansion_mode,
+		CRQ_EXPANSION_MODE, &rq_regs.crq_expansion_mode);
+	REG_GET_8(DCHUBP_REQ_SIZE_CONFIG,
+		CHUNK_SIZE, &rq_regs.rq_regs_l.chunk_size,
+		MIN_CHUNK_SIZE, &rq_regs.rq_regs_l.min_chunk_size,
+		META_CHUNK_SIZE, &rq_regs.rq_regs_l.meta_chunk_size,
+		MIN_META_CHUNK_SIZE, &rq_regs.rq_regs_l.min_meta_chunk_size,
+		DPTE_GROUP_SIZE, &rq_regs.rq_regs_l.dpte_group_size,
+		VM_GROUP_SIZE, &rq_regs.rq_regs_l.mpte_group_size,
+		SWATH_HEIGHT, &rq_regs.rq_regs_l.swath_height,
+		PTE_ROW_HEIGHT_LINEAR, &rq_regs.rq_regs_l.pte_row_height_linear);
+	REG_GET_7(DCHUBP_REQ_SIZE_CONFIG_C,
+		CHUNK_SIZE_C, &rq_regs.rq_regs_c.chunk_size,
+		MIN_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_chunk_size,
+		META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.meta_chunk_size,
+		MIN_META_CHUNK_SIZE_C, &rq_regs.rq_regs_c.min_meta_chunk_size,
+		DPTE_GROUP_SIZE_C, &rq_regs.rq_regs_c.dpte_group_size,
+		SWATH_HEIGHT_C, &rq_regs.rq_regs_c.swath_height,
+		PTE_ROW_HEIGHT_LINEAR_C, &rq_regs.rq_regs_c.pte_row_height_linear);
+
+	if (rq_regs.plane1_base_address != dml_rq_regs->plane1_base_address)
+		DC_LOG_DEBUG("DML Validation | HUBPRET_CONTROL:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->plane1_base_address, rq_regs.plane1_base_address);
+	if (rq_regs.drq_expansion_mode != dml_rq_regs->drq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->drq_expansion_mode, rq_regs.drq_expansion_mode);
+	if (rq_regs.prq_expansion_mode != dml_rq_regs->prq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:MRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->prq_expansion_mode, rq_regs.prq_expansion_mode);
+	if (rq_regs.mrq_expansion_mode != dml_rq_regs->mrq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:DET_BUF_PLANE1_BASE_ADDRESS - Expected: %u  Actual: %u\n",
+				dml_rq_regs->mrq_expansion_mode, rq_regs.mrq_expansion_mode);
+	if (rq_regs.crq_expansion_mode != dml_rq_regs->crq_expansion_mode)
+		DC_LOG_DEBUG("DML Validation | DCN_EXPANSION_MODE:CRQ_EXPANSION_MODE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->crq_expansion_mode, rq_regs.crq_expansion_mode);
+
+	if (rq_regs.rq_regs_l.chunk_size != dml_rq_regs->rq_regs_l.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.chunk_size, rq_regs.rq_regs_l.chunk_size);
+	if (rq_regs.rq_regs_l.min_chunk_size != dml_rq_regs->rq_regs_l.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_chunk_size, rq_regs.rq_regs_l.min_chunk_size);
+	if (rq_regs.rq_regs_l.meta_chunk_size != dml_rq_regs->rq_regs_l.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.meta_chunk_size, rq_regs.rq_regs_l.meta_chunk_size);
+	if (rq_regs.rq_regs_l.min_meta_chunk_size != dml_rq_regs->rq_regs_l.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:MIN_META_CHUNK_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs.rq_regs_l.min_meta_chunk_size);
+	if (rq_regs.rq_regs_l.dpte_group_size != dml_rq_regs->rq_regs_l.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:DPTE_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.dpte_group_size, rq_regs.rq_regs_l.dpte_group_size);
+	if (rq_regs.rq_regs_l.mpte_group_size != dml_rq_regs->rq_regs_l.mpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:VM_GROUP_SIZE - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.mpte_group_size, rq_regs.rq_regs_l.mpte_group_size);
+	if (rq_regs.rq_regs_l.swath_height != dml_rq_regs->rq_regs_l.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:SWATH_HEIGHT - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.swath_height, rq_regs.rq_regs_l.swath_height);
+	if (rq_regs.rq_regs_l.pte_row_height_linear != dml_rq_regs->rq_regs_l.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG_C:PTE_ROW_HEIGHT_LINEAR - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_l.pte_row_height_linear, rq_regs.rq_regs_l.pte_row_height_linear);
+
+	if (rq_regs.rq_regs_c.chunk_size != dml_rq_regs->rq_regs_c.chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.chunk_size, rq_regs.rq_regs_c.chunk_size);
+	if (rq_regs.rq_regs_c.min_chunk_size != dml_rq_regs->rq_regs_c.min_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_chunk_size, rq_regs.rq_regs_c.min_chunk_size);
+	if (rq_regs.rq_regs_c.meta_chunk_size != dml_rq_regs->rq_regs_c.meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.meta_chunk_size, rq_regs.rq_regs_c.meta_chunk_size);
+	if (rq_regs.rq_regs_c.min_meta_chunk_size != dml_rq_regs->rq_regs_c.min_meta_chunk_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:MIN_META_CHUNK_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.min_meta_chunk_size, rq_regs.rq_regs_c.min_meta_chunk_size);
+	if (rq_regs.rq_regs_c.dpte_group_size != dml_rq_regs->rq_regs_c.dpte_group_size)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:DPTE_GROUP_SIZE_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.dpte_group_size, rq_regs.rq_regs_c.dpte_group_size);
+	if (rq_regs.rq_regs_c.swath_height != dml_rq_regs->rq_regs_c.swath_height)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:SWATH_HEIGHT_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.swath_height, rq_regs.rq_regs_c.swath_height);
+	if (rq_regs.rq_regs_c.pte_row_height_linear != dml_rq_regs->rq_regs_c.pte_row_height_linear)
+		DC_LOG_DEBUG("DML Validation | DCHUBP_REQ_SIZE_CONFIG:PTE_ROW_HEIGHT_LINEAR_C - Expected: %u  Actual: %u\n",
+				dml_rq_regs->rq_regs_c.pte_row_height_linear, rq_regs.rq_regs_c.pte_row_height_linear);
+
+
+	/* DLG - Per hubp */
+	REG_GET_2(BLANK_OFFSET_0,
+		REFCYC_H_BLANK_END, &dlg_attr.refcyc_h_blank_end,
+		DLG_V_BLANK_END, &dlg_attr.dlg_vblank_end);
+	REG_GET(BLANK_OFFSET_1,
+		MIN_DST_Y_NEXT_START, &dlg_attr.min_dst_y_next_start);
+	REG_GET(DST_DIMENSIONS,
+		REFCYC_PER_HTOTAL, &dlg_attr.refcyc_per_htotal);
+	REG_GET_2(DST_AFTER_SCALER,
+		REFCYC_X_AFTER_SCALER, &dlg_attr.refcyc_x_after_scaler,
+		DST_Y_AFTER_SCALER, &dlg_attr.dst_y_after_scaler);
+	REG_GET(REF_FREQ_TO_PIX_FREQ,
+		REF_FREQ_TO_PIX_FREQ, &dlg_attr.ref_freq_to_pix_freq);
+
+	if (dlg_attr.refcyc_h_blank_end != dml_dlg_attr->refcyc_h_blank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:REFCYC_H_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_h_blank_end, dlg_attr.refcyc_h_blank_end);
+	if (dlg_attr.dlg_vblank_end != dml_dlg_attr->dlg_vblank_end)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_0:DLG_V_BLANK_END - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dlg_vblank_end, dlg_attr.dlg_vblank_end);
+	if (dlg_attr.min_dst_y_next_start != dml_dlg_attr->min_dst_y_next_start)
+		DC_LOG_DEBUG("DML Validation | BLANK_OFFSET_1:MIN_DST_Y_NEXT_START - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->min_dst_y_next_start, dlg_attr.min_dst_y_next_start);
+	if (dlg_attr.refcyc_per_htotal != dml_dlg_attr->refcyc_per_htotal)
+		DC_LOG_DEBUG("DML Validation | DST_DIMENSIONS:REFCYC_PER_HTOTAL - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_htotal, dlg_attr.refcyc_per_htotal);
+	if (dlg_attr.refcyc_x_after_scaler != dml_dlg_attr->refcyc_x_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:REFCYC_X_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_x_after_scaler, dlg_attr.refcyc_x_after_scaler);
+	if (dlg_attr.dst_y_after_scaler != dml_dlg_attr->dst_y_after_scaler)
+		DC_LOG_DEBUG("DML Validation | DST_AFTER_SCALER:DST_Y_AFTER_SCALER - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_after_scaler, dlg_attr.dst_y_after_scaler);
+	if (dlg_attr.ref_freq_to_pix_freq != dml_dlg_attr->ref_freq_to_pix_freq)
+		DC_LOG_DEBUG("DML Validation | REF_FREQ_TO_PIX_FREQ:REF_FREQ_TO_PIX_FREQ - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->ref_freq_to_pix_freq, dlg_attr.ref_freq_to_pix_freq);
+
+	/* DLG - Per luma/chroma */
+	REG_GET(VBLANK_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_VBLANK_L, &dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (REG(NOM_PARAMETERS_0))
+		REG_GET(NOM_PARAMETERS_0,
+			DST_Y_PER_PTE_ROW_NOM_L, &dlg_attr.dst_y_per_pte_row_nom_l);
+	if (REG(NOM_PARAMETERS_1))
+		REG_GET(NOM_PARAMETERS_1,
+			REFCYC_PER_PTE_GROUP_NOM_L, &dlg_attr.refcyc_per_pte_group_nom_l);
+	REG_GET(NOM_PARAMETERS_4,
+		DST_Y_PER_META_ROW_NOM_L, &dlg_attr.dst_y_per_meta_row_nom_l);
+	REG_GET(NOM_PARAMETERS_5,
+		REFCYC_PER_META_CHUNK_NOM_L, &dlg_attr.refcyc_per_meta_chunk_nom_l);
+	REG_GET_2(PER_LINE_DELIVERY,
+		REFCYC_PER_LINE_DELIVERY_L, &dlg_attr.refcyc_per_line_delivery_l,
+		REFCYC_PER_LINE_DELIVERY_C, &dlg_attr.refcyc_per_line_delivery_c);
+	REG_GET_2(PER_LINE_DELIVERY_PRE,
+		REFCYC_PER_LINE_DELIVERY_PRE_L, &dlg_attr.refcyc_per_line_delivery_pre_l,
+		REFCYC_PER_LINE_DELIVERY_PRE_C, &dlg_attr.refcyc_per_line_delivery_pre_c);
+	REG_GET(VBLANK_PARAMETERS_2,
+		REFCYC_PER_PTE_GROUP_VBLANK_C, &dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (REG(NOM_PARAMETERS_2))
+		REG_GET(NOM_PARAMETERS_2,
+			DST_Y_PER_PTE_ROW_NOM_C, &dlg_attr.dst_y_per_pte_row_nom_c);
+	if (REG(NOM_PARAMETERS_3))
+		REG_GET(NOM_PARAMETERS_3,
+			REFCYC_PER_PTE_GROUP_NOM_C, &dlg_attr.refcyc_per_pte_group_nom_c);
+	REG_GET(NOM_PARAMETERS_6,
+		DST_Y_PER_META_ROW_NOM_C, &dlg_attr.dst_y_per_meta_row_nom_c);
+	REG_GET(NOM_PARAMETERS_7,
+		REFCYC_PER_META_CHUNK_NOM_C, &dlg_attr.refcyc_per_meta_chunk_nom_c);
+	REG_GET(VBLANK_PARAMETERS_3,
+			REFCYC_PER_META_CHUNK_VBLANK_L, &dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	REG_GET(VBLANK_PARAMETERS_4,
+			REFCYC_PER_META_CHUNK_VBLANK_C, &dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	if (dlg_attr.refcyc_per_pte_group_vblank_l != dml_dlg_attr->refcyc_per_pte_group_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_1:REFCYC_PER_PTE_GROUP_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_l, dlg_attr.refcyc_per_pte_group_vblank_l);
+	if (dlg_attr.dst_y_per_pte_row_nom_l != dml_dlg_attr->dst_y_per_pte_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_0:DST_Y_PER_PTE_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_l, dlg_attr.dst_y_per_pte_row_nom_l);
+	if (dlg_attr.refcyc_per_pte_group_nom_l != dml_dlg_attr->refcyc_per_pte_group_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_1:REFCYC_PER_PTE_GROUP_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_l, dlg_attr.refcyc_per_pte_group_nom_l);
+	if (dlg_attr.dst_y_per_meta_row_nom_l != dml_dlg_attr->dst_y_per_meta_row_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_4:DST_Y_PER_META_ROW_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_l, dlg_attr.dst_y_per_meta_row_nom_l);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_l != dml_dlg_attr->refcyc_per_meta_chunk_nom_l)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_5:REFCYC_PER_META_CHUNK_NOM_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_l, dlg_attr.refcyc_per_meta_chunk_nom_l);
+	if (dlg_attr.refcyc_per_line_delivery_l != dml_dlg_attr->refcyc_per_line_delivery_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_l, dlg_attr.refcyc_per_line_delivery_l);
+	if (dlg_attr.refcyc_per_line_delivery_c != dml_dlg_attr->refcyc_per_line_delivery_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY:REFCYC_PER_LINE_DELIVERY_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_c, dlg_attr.refcyc_per_line_delivery_c);
+	if (dlg_attr.refcyc_per_pte_group_vblank_c != dml_dlg_attr->refcyc_per_pte_group_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_2:REFCYC_PER_PTE_GROUP_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_vblank_c, dlg_attr.refcyc_per_pte_group_vblank_c);
+	if (dlg_attr.dst_y_per_pte_row_nom_c != dml_dlg_attr->dst_y_per_pte_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_2:DST_Y_PER_PTE_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_pte_row_nom_c, dlg_attr.dst_y_per_pte_row_nom_c);
+	if (dlg_attr.refcyc_per_pte_group_nom_c != dml_dlg_attr->refcyc_per_pte_group_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_3:REFCYC_PER_PTE_GROUP_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_nom_c, dlg_attr.refcyc_per_pte_group_nom_c);
+	if (dlg_attr.dst_y_per_meta_row_nom_c != dml_dlg_attr->dst_y_per_meta_row_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_6:DST_Y_PER_META_ROW_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->dst_y_per_meta_row_nom_c, dlg_attr.dst_y_per_meta_row_nom_c);
+	if (dlg_attr.refcyc_per_meta_chunk_nom_c != dml_dlg_attr->refcyc_per_meta_chunk_nom_c)
+		DC_LOG_DEBUG("DML Validation | NOM_PARAMETERS_7:REFCYC_PER_META_CHUNK_NOM_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_nom_c, dlg_attr.refcyc_per_meta_chunk_nom_c);
+	if (dlg_attr.refcyc_per_line_delivery_pre_l != dml_dlg_attr->refcyc_per_line_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_l, dlg_attr.refcyc_per_line_delivery_pre_l);
+	if (dlg_attr.refcyc_per_line_delivery_pre_c != dml_dlg_attr->refcyc_per_line_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | PER_LINE_DELIVERY_PRE:REFCYC_PER_LINE_DELIVERY_PRE_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_line_delivery_pre_c, dlg_attr.refcyc_per_line_delivery_pre_c);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_l != dml_dlg_attr->refcyc_per_meta_chunk_vblank_l)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_3:REFCYC_PER_META_CHUNK_VBLANK_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_l, dlg_attr.refcyc_per_meta_chunk_vblank_l);
+	if (dlg_attr.refcyc_per_meta_chunk_vblank_c != dml_dlg_attr->refcyc_per_meta_chunk_vblank_c)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_4:REFCYC_PER_META_CHUNK_VBLANK_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_vblank_c, dlg_attr.refcyc_per_meta_chunk_vblank_c);
+
+	/* TTU - per hubp */
+	REG_GET_2(DCN_TTU_QOS_WM,
+		QoS_LEVEL_LOW_WM, &ttu_attr.qos_level_low_wm,
+		QoS_LEVEL_HIGH_WM, &ttu_attr.qos_level_high_wm);
+
+	if (ttu_attr.qos_level_low_wm != dml_ttu_attr->qos_level_low_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_LOW_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_low_wm, ttu_attr.qos_level_low_wm);
+	if (ttu_attr.qos_level_high_wm != dml_ttu_attr->qos_level_high_wm)
+		DC_LOG_DEBUG("DML Validation | DCN_TTU_QOS_WM:QoS_LEVEL_HIGH_WM - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_high_wm, ttu_attr.qos_level_high_wm);
+
+	/* TTU - per luma/chroma */
+	/* Assumed surf0 is luma and 1 is chroma */
+	REG_GET_3(DCN_SURF0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_l,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_l,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_l);
+	REG_GET_3(DCN_SURF1_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_c,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_c,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_c);
+	REG_GET_3(DCN_CUR0_TTU_CNTL0,
+		REFCYC_PER_REQ_DELIVERY, &ttu_attr.refcyc_per_req_delivery_cur0,
+		QoS_LEVEL_FIXED, &ttu_attr.qos_level_fixed_cur0,
+		QoS_RAMP_DISABLE, &ttu_attr.qos_ramp_disable_cur0);
+	REG_GET(FLIP_PARAMETERS_1,
+		REFCYC_PER_PTE_GROUP_FLIP_L, &dlg_attr.refcyc_per_pte_group_flip_l);
+	REG_GET(DCN_CUR0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	REG_GET(DCN_CUR1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	REG_GET(DCN_SURF0_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_l);
+	REG_GET(DCN_SURF1_TTU_CNTL1,
+			REFCYC_PER_REQ_DELIVERY_PRE, &ttu_attr.refcyc_per_req_delivery_pre_c);
+
+	if (ttu_attr.refcyc_per_req_delivery_l != dml_ttu_attr->refcyc_per_req_delivery_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_l, ttu_attr.refcyc_per_req_delivery_l);
+	if (ttu_attr.qos_level_fixed_l != dml_ttu_attr->qos_level_fixed_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_l, ttu_attr.qos_level_fixed_l);
+	if (ttu_attr.qos_ramp_disable_l != dml_ttu_attr->qos_ramp_disable_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_l, ttu_attr.qos_ramp_disable_l);
+	if (ttu_attr.refcyc_per_req_delivery_c != dml_ttu_attr->refcyc_per_req_delivery_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_c, ttu_attr.refcyc_per_req_delivery_c);
+	if (ttu_attr.qos_level_fixed_c != dml_ttu_attr->qos_level_fixed_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_c, ttu_attr.qos_level_fixed_c);
+	if (ttu_attr.qos_ramp_disable_c != dml_ttu_attr->qos_ramp_disable_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_c, ttu_attr.qos_ramp_disable_c);
+	if (ttu_attr.refcyc_per_req_delivery_cur0 != dml_ttu_attr->refcyc_per_req_delivery_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:REFCYC_PER_REQ_DELIVERY - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_cur0, ttu_attr.refcyc_per_req_delivery_cur0);
+	if (ttu_attr.qos_level_fixed_cur0 != dml_ttu_attr->qos_level_fixed_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_LEVEL_FIXED - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_level_fixed_cur0, ttu_attr.qos_level_fixed_cur0);
+	if (ttu_attr.qos_ramp_disable_cur0 != dml_ttu_attr->qos_ramp_disable_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL0:QoS_RAMP_DISABLE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->qos_ramp_disable_cur0, ttu_attr.qos_ramp_disable_cur0);
+	if (dlg_attr.refcyc_per_pte_group_flip_l != dml_dlg_attr->refcyc_per_pte_group_flip_l)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_1:REFCYC_PER_PTE_GROUP_FLIP_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_flip_l, dlg_attr.refcyc_per_pte_group_flip_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur0 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur0)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur0, ttu_attr.refcyc_per_req_delivery_pre_cur0);
+	if (ttu_attr.refcyc_per_req_delivery_pre_cur1 != dml_ttu_attr->refcyc_per_req_delivery_pre_cur1)
+		DC_LOG_DEBUG("DML Validation | DCN_CUR1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_cur1, ttu_attr.refcyc_per_req_delivery_pre_cur1);
+	if (ttu_attr.refcyc_per_req_delivery_pre_l != dml_ttu_attr->refcyc_per_req_delivery_pre_l)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF0_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_l, ttu_attr.refcyc_per_req_delivery_pre_l);
+	if (ttu_attr.refcyc_per_req_delivery_pre_c != dml_ttu_attr->refcyc_per_req_delivery_pre_c)
+		DC_LOG_DEBUG("DML Validation | DCN_SURF1_TTU_CNTL1:REFCYC_PER_REQ_DELIVERY_PRE - Expected: %u  Actual: %u\n",
+				dml_ttu_attr->refcyc_per_req_delivery_pre_c, ttu_attr.refcyc_per_req_delivery_pre_c);
+
+	/* Host VM deadline regs */
+	REG_GET(VBLANK_PARAMETERS_5,
+		REFCYC_PER_VM_GROUP_VBLANK, &dlg_attr.refcyc_per_vm_group_vblank);
+	REG_GET(VBLANK_PARAMETERS_6,
+		REFCYC_PER_VM_REQ_VBLANK, &dlg_attr.refcyc_per_vm_req_vblank);
+	REG_GET(FLIP_PARAMETERS_3,
+		REFCYC_PER_VM_GROUP_FLIP, &dlg_attr.refcyc_per_vm_group_flip);
+	REG_GET(FLIP_PARAMETERS_4,
+		REFCYC_PER_VM_REQ_FLIP, &dlg_attr.refcyc_per_vm_req_flip);
+	REG_GET(FLIP_PARAMETERS_5,
+		REFCYC_PER_PTE_GROUP_FLIP_C, &dlg_attr.refcyc_per_pte_group_flip_c);
+	REG_GET(FLIP_PARAMETERS_6,
+		REFCYC_PER_META_CHUNK_FLIP_C, &dlg_attr.refcyc_per_meta_chunk_flip_c);
+	REG_GET(FLIP_PARAMETERS_2,
+		REFCYC_PER_META_CHUNK_FLIP_L, &dlg_attr.refcyc_per_meta_chunk_flip_l);
+
+	if (dlg_attr.refcyc_per_vm_group_vblank != dml_dlg_attr->refcyc_per_vm_group_vblank)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_5:REFCYC_PER_VM_GROUP_VBLANK - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_group_vblank, dlg_attr.refcyc_per_vm_group_vblank);
+	if (dlg_attr.refcyc_per_vm_req_vblank != dml_dlg_attr->refcyc_per_vm_req_vblank)
+		DC_LOG_DEBUG("DML Validation | VBLANK_PARAMETERS_6:REFCYC_PER_VM_REQ_VBLANK - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_req_vblank, dlg_attr.refcyc_per_vm_req_vblank);
+	if (dlg_attr.refcyc_per_vm_group_flip != dml_dlg_attr->refcyc_per_vm_group_flip)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_3:REFCYC_PER_VM_GROUP_FLIP - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_group_flip, dlg_attr.refcyc_per_vm_group_flip);
+	if (dlg_attr.refcyc_per_vm_req_flip != dml_dlg_attr->refcyc_per_vm_req_flip)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_4:REFCYC_PER_VM_REQ_FLIP - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_vm_req_flip, dlg_attr.refcyc_per_vm_req_flip);
+	if (dlg_attr.refcyc_per_pte_group_flip_c != dml_dlg_attr->refcyc_per_pte_group_flip_c)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_5:REFCYC_PER_PTE_GROUP_FLIP_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_pte_group_flip_c, dlg_attr.refcyc_per_pte_group_flip_c);
+	if (dlg_attr.refcyc_per_meta_chunk_flip_c != dml_dlg_attr->refcyc_per_meta_chunk_flip_c)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_6:REFCYC_PER_META_CHUNK_FLIP_C - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_flip_c, dlg_attr.refcyc_per_meta_chunk_flip_c);
+	if (dlg_attr.refcyc_per_meta_chunk_flip_l != dml_dlg_attr->refcyc_per_meta_chunk_flip_l)
+		DC_LOG_DEBUG("DML Validation | FLIP_PARAMETERS_2:REFCYC_PER_META_CHUNK_FLIP_L - Expected: %u  Actual: %u\n",
+				dml_dlg_attr->refcyc_per_meta_chunk_flip_l, dlg_attr.refcyc_per_meta_chunk_flip_l);
+}
+
+static void program_surface_flip_and_addr(struct hubp *hubp, struct surface_flip_registers *flip_regs)
+{
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+
+	REG_UPDATE_3(DCSURF_FLIP_CONTROL,
+					SURFACE_FLIP_TYPE, flip_regs->immediate,
+					SURFACE_FLIP_MODE_FOR_STEREOSYNC, flip_regs->grph_stereo,
+					SURFACE_FLIP_IN_STEREOSYNC, flip_regs->grph_stereo);
+
+	REG_UPDATE(VMID_SETTINGS_0,
+				VMID, flip_regs->vmid);
+
+	REG_UPDATE_8(DCSURF_SURFACE_CONTROL,
+			PRIMARY_SURFACE_TMZ, flip_regs->tmz_surface,
+			PRIMARY_SURFACE_TMZ_C, flip_regs->tmz_surface,
+			PRIMARY_META_SURFACE_TMZ, flip_regs->tmz_surface,
+			PRIMARY_META_SURFACE_TMZ_C, flip_regs->tmz_surface,
+			SECONDARY_SURFACE_TMZ, flip_regs->tmz_surface,
+			SECONDARY_SURFACE_TMZ_C, flip_regs->tmz_surface,
+			SECONDARY_META_SURFACE_TMZ, flip_regs->tmz_surface,
+			SECONDARY_META_SURFACE_TMZ_C, flip_regs->tmz_surface);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, 0,
+			PRIMARY_META_SURFACE_ADDRESS_HIGH_C,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, 0,
+			PRIMARY_META_SURFACE_ADDRESS_C,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_C);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH, 0,
+			PRIMARY_META_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_PRIMARY_META_SURFACE_ADDRESS, 0,
+			PRIMARY_META_SURFACE_ADDRESS,
+			flip_regs->DCSURF_PRIMARY_META_SURFACE_ADDRESS);
+
+	REG_SET(DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH, 0,
+			SECONDARY_META_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_SECONDARY_META_SURFACE_ADDRESS, 0,
+			SECONDARY_META_SURFACE_ADDRESS,
+			flip_regs->DCSURF_SECONDARY_META_SURFACE_ADDRESS);
+
+
+	REG_SET(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, 0,
+			SECONDARY_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_SECONDARY_SURFACE_ADDRESS, 0,
+			SECONDARY_SURFACE_ADDRESS,
+			flip_regs->DCSURF_SECONDARY_SURFACE_ADDRESS);
+
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, 0,
+			PRIMARY_SURFACE_ADDRESS_HIGH_C,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C);
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_C, 0,
+			PRIMARY_SURFACE_ADDRESS_C,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_C);
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, 0,
+			PRIMARY_SURFACE_ADDRESS_HIGH,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH);
+
+	REG_SET(DCSURF_PRIMARY_SURFACE_ADDRESS, 0,
+			PRIMARY_SURFACE_ADDRESS,
+			flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS);
+}
+
+void dmcub_PLAT_54186_wa(struct hubp *hubp, struct surface_flip_registers *flip_regs)
+{
+	struct dc_dmub_srv *dmcub = hubp->ctx->dmub_srv;
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct dmub_rb_cmd_PLAT_54186_wa PLAT_54186_wa = { 0 };
+
+	PLAT_54186_wa.header.type = DMUB_CMD__PLAT_54186_WA;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_C = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_C;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
+	PLAT_54186_wa.flip.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C = flip_regs->DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
+	PLAT_54186_wa.flip.flip_params.grph_stereo = flip_regs->grph_stereo;
+	PLAT_54186_wa.flip.flip_params.hubp_inst = hubp->inst;
+	PLAT_54186_wa.flip.flip_params.immediate = flip_regs->immediate;
+	PLAT_54186_wa.flip.flip_params.tmz_surface = flip_regs->tmz_surface;
+	PLAT_54186_wa.flip.flip_params.vmid = flip_regs->vmid;
+
+	PERF_TRACE();  // TODO: remove after performance is stable.
+	dc_dmub_srv_cmd_queue(dmcub, &PLAT_54186_wa.header);
+	PERF_TRACE();  // TODO: remove after performance is stable.
+	dc_dmub_srv_cmd_execute(dmcub);
+	PERF_TRACE();  // TODO: remove after performance is stable.
+	dc_dmub_srv_wait_idle(dmcub);
+	PERF_TRACE();  // TODO: remove after performance is stable.
+}
+
+bool hubp21_program_surface_flip_and_addr(
+		struct hubp *hubp,
+		const struct dc_plane_address *address,
+		bool flip_immediate)
+{
+	struct dc_debug_options *debug = &hubp->ctx->dc->debug;
+	struct dcn21_hubp *hubp21 = TO_DCN21_HUBP(hubp);
+	struct surface_flip_registers flip_regs = { 0 };
+
+	flip_regs.vmid = address->vmid;
+
+	switch (address->type) {
+	case PLN_ADDR_TYPE_GRAPHICS:
+		if (address->grph.addr.quad_part == 0) {
+			BREAK_TO_DEBUGGER();
+			break;
+		}
+
+		if (address->grph.meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS =
+					address->grph.meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH =
+					address->grph.meta_addr.high_part;
+		}
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS =
+				address->grph.addr.low_part;
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH =
+				address->grph.addr.high_part;
+		break;
+	case PLN_ADDR_TYPE_VIDEO_PROGRESSIVE:
+		if (address->video_progressive.luma_addr.quad_part == 0
+				|| address->video_progressive.chroma_addr.quad_part == 0)
+			break;
+
+		if (address->video_progressive.luma_meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS =
+					address->video_progressive.luma_meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH =
+					address->video_progressive.luma_meta_addr.high_part;
+
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_C =
+					address->video_progressive.chroma_meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C =
+					address->video_progressive.chroma_meta_addr.high_part;
+		}
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS =
+				address->video_progressive.luma_addr.low_part;
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH =
+				address->video_progressive.luma_addr.high_part;
+
+		if (debug->nv12_iflip_vm_wa) {
+			flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_C =
+					address->video_progressive.chroma_addr.low_part + hubp21->PLAT_54186_wa_chroma_addr_offset;
+		} else
+			flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_C =
+					address->video_progressive.chroma_addr.low_part;
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C =
+				address->video_progressive.chroma_addr.high_part;
+
+		break;
+	case PLN_ADDR_TYPE_GRPH_STEREO:
+		if (address->grph_stereo.left_addr.quad_part == 0)
+			break;
+		if (address->grph_stereo.right_addr.quad_part == 0)
+			break;
+
+		flip_regs.grph_stereo = true;
+
+		if (address->grph_stereo.right_meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_SECONDARY_META_SURFACE_ADDRESS =
+					address->grph_stereo.right_meta_addr.low_part;
+			flip_regs.DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH =
+					address->grph_stereo.right_meta_addr.high_part;
+		}
+
+		if (address->grph_stereo.left_meta_addr.quad_part != 0) {
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS =
+					address->grph_stereo.left_meta_addr.low_part;
+			flip_regs.DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH =
+					address->grph_stereo.left_meta_addr.high_part;
+		}
+
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS =
+				address->grph_stereo.left_addr.low_part;
+		flip_regs.DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH =
+				address->grph_stereo.left_addr.high_part;
+
+		flip_regs.DCSURF_SECONDARY_SURFACE_ADDRESS =
+				address->grph_stereo.right_addr.low_part;
+		flip_regs.DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH =
+				address->grph_stereo.right_addr.high_part;
+
+		break;
+	default:
+		BREAK_TO_DEBUGGER();
+		break;
+	}
+
+	flip_regs.tmz_surface = address->tmz_surface;
+	flip_regs.immediate = flip_immediate;
+
+	if (hubp->ctx->dc->debug.enable_dmcub_surface_flip && address->type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE)
+		dmcub_PLAT_54186_wa(hubp, &flip_regs);
+	else
+		program_surface_flip_and_addr(hubp, &flip_regs);
+
+	hubp->request_address = *address;
+
+	return true;
+}
+
 void hubp21_init(struct hubp *hubp)
 {
 	// DEDCN21-133: Inconsistent row starting line for flip between DPTE and Meta
@@ -203,7 +915,7 @@ void hubp21_init(struct hubp *hubp)
 static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
-	.hubp_program_surface_flip_and_addr = hubp2_program_surface_flip_and_addr,
+	.hubp_program_surface_flip_and_addr = hubp21_program_surface_flip_and_addr,
 	.hubp_program_surface_config = hubp1_program_surface_config,
 	.hubp_is_flip_pending = hubp1_is_flip_pending,
 	.hubp_setup = hubp21_setup,
@@ -211,7 +923,8 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_set_vm_system_aperture_settings = hubp21_set_vm_system_aperture_settings,
 	.set_blank = hubp1_set_blank,
 	.dcc_control = hubp1_dcc_control,
-	.mem_program_viewport = min_set_viewport,
+	.mem_program_viewport = hubp21_set_viewport,
+	.apply_PLAT_54186_wa = hubp21_apply_PLAT_54186_wa,
 	.set_cursor_attributes	= hubp2_cursor_set_attributes,
 	.set_cursor_position	= hubp1_cursor_set_position,
 	.hubp_clk_cntl = hubp1_clk_cntl,
@@ -223,6 +936,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_clear_underflow = hubp1_clear_underflow,
 	.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
 	.hubp_init = hubp21_init,
+	.validate_dml_output = hubp21_validate_dml_output,
 };
 
 bool hubp21_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h
index aeda719a2a13..9873b6cbc5ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.h
@@ -108,6 +108,7 @@ struct dcn21_hubp {
 	const struct dcn_hubp2_registers *hubp_regs;
 	const struct dcn_hubp2_shift *hubp_shift;
 	const struct dcn_hubp2_mask *hubp_mask;
+	int PLAT_54186_wa_chroma_addr_offset;
 };
 
 bool hubp21_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
index b25215cadf85..081ad8e43d58 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
@@ -28,7 +28,7 @@
 #include "core_types.h"
 #include "resource.h"
 #include "dce/dce_hwseq.h"
-#include "dcn20/dcn20_hwseq.h"
+#include "dcn21_hwseq.h"
 #include "vmid.h"
 #include "reg_helper.h"
 #include "hw/clk_mgr.h"
@@ -61,7 +61,7 @@ static void mmhub_update_page_table_config(struct dcn_hubbub_phys_addr_config *c
 
 }
 
-static int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
+int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
 {
 	struct dcn_hubbub_phys_addr_config config;
 
@@ -82,7 +82,7 @@ static int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_ph
 
 // work around for Renoir s0i3, if register is programmed, bypass golden init.
 
-static bool dcn21_s0i3_golden_init_wa(struct dc *dc)
+bool dcn21_s0i3_golden_init_wa(struct dc *dc)
 {
 	struct dce_hwseq *hws = dc->hwseq;
 	uint32_t value = 0;
@@ -112,11 +112,3 @@ void dcn21_optimize_pwr_state(
 			true);
 }
 
-void dcn21_hw_sequencer_construct(struct dc *dc)
-{
-	dcn20_hw_sequencer_construct(dc);
-	dc->hwss.init_sys_ctx = dcn21_init_sys_ctx;
-	dc->hwss.s0i3_golden_init_wa = dcn21_s0i3_golden_init_wa;
-	dc->hwss.optimize_pwr_state = dcn21_optimize_pwr_state;
-	dc->hwss.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
index be67b62e6fb1..182736096123 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
@@ -26,8 +26,22 @@
 #ifndef __DC_HWSS_DCN21_H__
 #define __DC_HWSS_DCN21_H__
 
+#include "hw_sequencer_private.h"
+
 struct dc;
 
-void dcn21_hw_sequencer_construct(struct dc *dc);
+int dcn21_init_sys_ctx(struct dce_hwseq *hws,
+		struct dc *dc,
+		struct dc_phy_addr_space_config *pa_config);
+
+bool dcn21_s0i3_golden_init_wa(struct dc *dc);
+
+void dcn21_exit_optimized_pwr_state(
+		const struct dc *dc,
+		struct dc_state *context);
+
+void dcn21_optimize_pwr_state(
+		const struct dc *dc,
+		struct dc_state *context);
 
 #endif /* __DC_HWSS_DCN21_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
new file mode 100644
index 000000000000..4861aa5c59ae
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.c
@@ -0,0 +1,142 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dce110/dce110_hw_sequencer.h"
+#include "dcn10/dcn10_hw_sequencer.h"
+#include "dcn20/dcn20_hwseq.h"
+#include "dcn21_hwseq.h"
+
+static const struct hw_sequencer_funcs dcn21_funcs = {
+	.program_gamut_remap = dcn10_program_gamut_remap,
+	.init_hw = dcn10_init_hw,
+	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
+	.apply_ctx_for_surface = NULL,
+	.program_front_end_for_ctx = dcn20_program_front_end_for_ctx,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.update_dchub = dcn10_update_dchub,
+	.update_pending_status = dcn10_update_pending_status,
+	.program_output_csc = dcn20_program_output_csc,
+	.enable_accelerated_mode = dce110_enable_accelerated_mode,
+	.enable_timing_synchronization = dcn10_enable_timing_synchronization,
+	.enable_per_frame_crtc_position_reset = dcn10_enable_per_frame_crtc_position_reset,
+	.update_info_frame = dce110_update_info_frame,
+	.send_immediate_sdp_message = dcn10_send_immediate_sdp_message,
+	.enable_stream = dcn20_enable_stream,
+	.disable_stream = dce110_disable_stream,
+	.unblank_stream = dcn20_unblank_stream,
+	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
+	.disable_plane = dcn20_disable_plane,
+	.pipe_control_lock = dcn20_pipe_control_lock,
+	.pipe_control_lock_global = dcn20_pipe_control_lock_global,
+	.prepare_bandwidth = dcn20_prepare_bandwidth,
+	.optimize_bandwidth = dcn20_optimize_bandwidth,
+	.update_bandwidth = dcn20_update_bandwidth,
+	.set_drr = dcn10_set_drr,
+	.get_position = dcn10_get_position,
+	.set_static_screen_control = dcn10_set_static_screen_control,
+	.setup_stereo = dcn10_setup_stereo,
+	.set_avmute = dce110_set_avmute,
+	.log_hw_state = dcn10_log_hw_state,
+	.get_hw_state = dcn10_get_hw_state,
+	.clear_status_bits = dcn10_clear_status_bits,
+	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_power_control = dce110_edp_power_control,
+	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.setup_periodic_interrupt = dcn10_setup_periodic_interrupt,
+	.set_clock = dcn10_set_clock,
+	.get_clock = dcn10_get_clock,
+	.program_triplebuffer = dcn20_program_triple_buffer,
+	.enable_writeback = dcn20_enable_writeback,
+	.disable_writeback = dcn20_disable_writeback,
+	.dmdata_status_done = dcn20_dmdata_status_done,
+	.program_dmdata_engine = dcn20_program_dmdata_engine,
+	.set_dmdata_attributes = dcn20_set_dmdata_attributes,
+	.init_sys_ctx = dcn21_init_sys_ctx,
+	.init_vm_ctx = dcn20_init_vm_ctx,
+	.set_flip_control_gsl = dcn20_set_flip_control_gsl,
+	.optimize_pwr_state = dcn21_optimize_pwr_state,
+	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
+	.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
+	.set_cursor_position = dcn10_set_cursor_position,
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level,
+	.optimize_pwr_state = dcn21_optimize_pwr_state,
+	.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
+};
+
+static const struct hwseq_private_funcs dcn21_private_funcs = {
+	.init_pipes = dcn10_init_pipes,
+	.update_plane_addr = dcn20_update_plane_addr,
+	.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
+	.update_mpcc = dcn20_update_mpcc,
+	.set_input_transfer_func = dcn20_set_input_transfer_func,
+	.set_output_transfer_func = dcn20_set_output_transfer_func,
+	.power_down = dce110_power_down,
+	.enable_display_power_gating = dcn10_dummy_display_power_gating,
+	.blank_pixel_data = dcn20_blank_pixel_data,
+	.reset_hw_ctx_wrap = dcn20_reset_hw_ctx_wrap,
+	.enable_stream_timing = dcn20_enable_stream_timing,
+	.edp_backlight_control = dce110_edp_backlight_control,
+	.disable_stream_gating = dcn20_disable_stream_gating,
+	.enable_stream_gating = dcn20_enable_stream_gating,
+	.setup_vupdate_interrupt = dcn20_setup_vupdate_interrupt,
+	.did_underflow_occur = dcn10_did_underflow_occur,
+	.init_blank = dcn20_init_blank,
+	.disable_vga = dcn20_disable_vga,
+	.bios_golden_init = dcn10_bios_golden_init,
+	.plane_atomic_disable = dcn20_plane_atomic_disable,
+	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
+	.enable_power_gating_plane = dcn20_enable_power_gating_plane,
+	.dpp_pg_control = dcn20_dpp_pg_control,
+	.hubp_pg_control = dcn20_hubp_pg_control,
+	.dsc_pg_control = NULL,
+	.update_odm = dcn20_update_odm,
+	.dsc_pg_control = dcn20_dsc_pg_control,
+	.get_surface_visual_confirm_color = dcn10_get_surface_visual_confirm_color,
+	.get_hdr_visual_confirm_color = dcn10_get_hdr_visual_confirm_color,
+	.set_hdr_multiplier = dcn10_set_hdr_multiplier,
+	.verify_allow_pstate_change_high = dcn10_verify_allow_pstate_change_high,
+	.s0i3_golden_init_wa = dcn21_s0i3_golden_init_wa,
+	.wait_for_blank_complete = dcn20_wait_for_blank_complete,
+	.dccg_init = dcn20_dccg_init,
+	.set_blend_lut = dcn20_set_blend_lut,
+	.set_shaper_3dlut = dcn20_set_shaper_3dlut,
+};
+
+void dcn21_hw_sequencer_construct(struct dc *dc)
+{
+	dc->hwss = dcn21_funcs;
+	dc->hwseq->funcs = dcn21_private_funcs;
+
+	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		dc->hwss.init_hw = dcn20_fpga_init_hw;
+		dc->hwseq->funcs.init_pipes = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.h
new file mode 100644
index 000000000000..3ed24292648a
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_init.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_DCN21_INIT_H__
+#define __DC_DCN21_INIT_H__
+
+struct dc;
+
+void dcn21_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_DCN20_INIT_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
index e8a504ca5890..e45683ac871a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
@@ -323,9 +323,7 @@ void dcn21_link_encoder_disable_output(
 
 
 static const struct link_encoder_funcs dcn21_link_enc_funcs = {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.read_state = link_enc2_read_state,
-#endif
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
 	.hw_init = enc2_hw_init,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
index 1d7a1a51f13d..033d5d76f195 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
@@ -33,6 +33,45 @@ struct dcn21_link_encoder {
 	struct dpcssys_phy_seq_cfg phy_seq_cfg;
 };
 
+#define DPCS_DCN21_MASK_SH_LIST(mask_sh)\
+	DPCS_DCN2_MASK_SH_LIST(mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_MPLLB_CP_PROP_GS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_RX_VREF_CTRL, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_MPLLB_CP_INT_GS, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCS_DMCU_DPALT_DIS_BLOCK_REG, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_SUP_PRE_HP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX0_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX1_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX2_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL15, RDPCS_PHY_DP_TX3_VREGDRV_BYP, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE0, RDPCS_PHY_DP_TX0_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE1, RDPCS_PHY_DP_TX1_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE2, RDPCS_PHY_DP_TX2_EQ_POST, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_MAIN, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_FINETUNE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DCO_RANGE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_PRE, mask_sh),\
+	LE_SF(RDPCSTX0_RDPCSTX_PHY_FUSE3, RDPCS_PHY_DP_TX3_EQ_POST, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYA_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\
+	LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh)
+
+#define DPCS_DCN21_REG_LIST(id) \
+	DPCS_DCN2_REG_LIST(id),\
+	SRI(RDPCSTX_PHY_CNTL15, RDPCSTX, id),\
+	SRI(RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG, RDPCSTX, id)
+
 #define LINK_ENCODER_MASK_SH_LIST_DCN21(mask_sh)\
 	LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh),\
 	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index b29b2c99a564..1d741bca2211 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -1,5 +1,6 @@
 /*
 * Copyright 2018 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -28,6 +29,8 @@
 #include "dm_services.h"
 #include "dc.h"
 
+#include "dcn21_init.h"
+
 #include "resource.h"
 #include "include/irq_service_interface.h"
 #include "dcn20/dcn20_resource.h"
@@ -60,6 +63,8 @@
 
 #include "dcn20/dcn20_dwb.h"
 #include "dcn20/dcn20_mmhubbub.h"
+#include "dpcs/dpcs_2_1_0_offset.h"
+#include "dpcs/dpcs_2_1_0_sh_mask.h"
 
 #include "renoir_ip_offset.h"
 #include "dcn/dcn_2_1_0_offset.h"
@@ -78,6 +83,7 @@
 #include "dcn21_resource.h"
 #include "vm_helper.h"
 #include "dcn20/dcn20_vmid.h"
+#include "../dce/dmub_psr.h"
 
 #define SOC_BOUNDING_BOX_VALID false
 #define DC_LOGGER_INIT(logger)
@@ -90,11 +96,7 @@ struct _vcs_dpi_ip_params_st dcn2_1_ip = {
 	.gpuvm_max_page_table_levels = 1,
 	.hostvm_max_page_table_levels = 4,
 	.hostvm_cached_page_table_levels = 2,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.num_dsc = 3,
-#else
-	.num_dsc = 0,
-#endif
 	.rob_buffer_size_kbytes = 168,
 	.det_buffer_size_kbytes = 164,
 	.dpte_buffer_size_in_pte_reqs_luma = 44,
@@ -352,7 +354,7 @@ static const struct bios_registers bios_regs = {
 };
 
 static const struct dce_dmcu_registers dmcu_regs = {
-		DMCU_DCN10_REG_LIST()
+		DMCU_DCN20_REG_LIST()
 };
 
 static const struct dce_dmcu_shift dmcu_shift = {
@@ -375,20 +377,6 @@ static const struct dce_abm_mask abm_mask = {
 		ABM_MASK_SH_LIST_DCN20(_MASK)
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DMUB
-static const struct dcn21_dmcub_registers dmcub_regs = {
-		DMCUB_REG_LIST_DCN()
-};
-
-static const struct dcn21_dmcub_shift dmcub_shift = {
-		DMCUB_COMMON_MASK_SH_LIST_BASE(__SHIFT)
-};
-
-static const struct dcn21_dmcub_mask dmcub_mask = {
-		DMCUB_COMMON_MASK_SH_LIST_BASE(_MASK)
-};
-#endif
-
 #define audio_regs(id)\
 [id] = {\
 		AUD_COMMON_REG_LIST(id)\
@@ -478,15 +466,18 @@ static const struct dcn20_mpc_registers mpc_regs = {
 		MPC_OUT_MUX_REG_LIST_DCN2_0(0),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(1),
 		MPC_OUT_MUX_REG_LIST_DCN2_0(2),
-		MPC_OUT_MUX_REG_LIST_DCN2_0(3)
+		MPC_OUT_MUX_REG_LIST_DCN2_0(3),
+		MPC_DBG_REG_LIST_DCN2_0()
 };
 
 static const struct dcn20_mpc_shift mpc_shift = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(__SHIFT),
+	MPC_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn20_mpc_mask mpc_mask = {
-	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK)
+	MPC_COMMON_MASK_SH_LIST_DCN2_0(_MASK),
+	MPC_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define hubp_regs(id)\
@@ -554,7 +545,6 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define dsc_regsDCN20(id)\
 [id] = {\
 	DSC_REG_LIST_DCN20(id)\
@@ -576,7 +566,6 @@ static const struct dcn20_dsc_shift dsc_shift = {
 static const struct dcn20_dsc_mask dsc_mask = {
 	DSC_REG_LIST_SH_MASK_DCN20(_MASK)
 };
-#endif
 
 #define ipp_regs(id)\
 [id] = {\
@@ -623,6 +612,7 @@ static const struct dce110_aux_registers aux_engine_regs[] = {
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN20(id),\
+	TF_REG_LIST_DCN20_COMMON_APPEND(id),\
 }
 
 static const struct dcn2_dpp_registers tf_regs[] = {
@@ -633,11 +623,13 @@ static const struct dcn2_dpp_registers tf_regs[] = {
 };
 
 static const struct dcn2_dpp_shift tf_shift = {
-		TF_REG_LIST_SH_MASK_DCN20(__SHIFT)
+		TF_REG_LIST_SH_MASK_DCN20(__SHIFT),
+		TF_DEBUG_REG_LIST_SH_DCN20
 };
 
 static const struct dcn2_dpp_mask tf_mask = {
-		TF_REG_LIST_SH_MASK_DCN20(_MASK)
+		TF_REG_LIST_SH_MASK_DCN20(_MASK),
+		TF_DEBUG_REG_LIST_MASK_DCN20
 };
 
 #define stream_enc_regs(id)\
@@ -672,7 +664,7 @@ static const struct dcn10_stream_encoder_mask se_mask = {
 static void dcn21_pp_smu_destroy(struct pp_smu_funcs **pp_smu);
 
 static int dcn21_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes);
 
 static struct input_pixel_processor *dcn21_ipp_create(
 	struct dc_context *ctx, uint32_t inst)
@@ -773,9 +765,7 @@ static const struct resource_caps res_cap_rn = {
 		.num_dwb = 1,
 		.num_ddc = 5,
 		.num_vmid = 1,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 3,
-#endif
 };
 
 #ifdef DIAGS_BUILD
@@ -800,9 +790,7 @@ static const struct resource_caps res_cap_rn_FPGA_2pipe_dsc = {
 		.num_pll = 4,
 		.num_dwb = 1,
 		.num_ddc = 4,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 2,
-#endif
 };
 #endif
 
@@ -847,6 +835,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.scl_reset_length10 = true,
 		.sanity_checks = true,
 		.disable_48mhz_pwrdwn = false,
+		.nv12_iflip_vm_wa = true,
+		.usbc_combo_phy_reset_wa = true
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
@@ -869,7 +859,7 @@ enum dcn20_clk_src_array_id {
 	DCN20_CLK_SRC_TOTAL_DCN21
 };
 
-static void destruct(struct dcn21_resource_pool *pool)
+static void dcn21_resource_destruct(struct dcn21_resource_pool *pool)
 {
 	unsigned int i;
 
@@ -880,12 +870,10 @@ static void destruct(struct dcn21_resource_pool *pool)
 		}
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		if (pool->base.dscs[i] != NULL)
 			dcn20_dsc_destroy(&pool->base.dscs[i]);
 	}
-#endif
 
 	if (pool->base.mpc != NULL) {
 		kfree(TO_DCN20_MPC(pool->base.mpc));
@@ -972,11 +960,6 @@ static void destruct(struct dcn21_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-#ifdef CONFIG_DRM_AMD_DC_DMUB
-	if (pool->base.dmcub != NULL)
-		dcn21_dmcub_destroy(&pool->base.dmcub);
-#endif
-
 	if (pool->base.dccg != NULL)
 		dcn_dccg_destroy(&pool->base.dccg);
 
@@ -1010,11 +993,9 @@ static void calculate_wm_set_for_vlevel(
 	wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000;
 	wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000;
 	wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000;
 	wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000;
 	wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000;
-#endif
 	dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached;
 
 }
@@ -1023,7 +1004,8 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 {
 	int i;
 
-	kernel_fpu_begin();
+	DC_FP_START();
+
 	if (dc->bb_overrides.sr_exit_time_ns) {
 		for (i = 0; i < WM_SET_COUNT; i++) {
 			  dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us =
@@ -1049,7 +1031,7 @@ static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 		}
 	}
 
-	kernel_fpu_end();
+	DC_FP_END();
 }
 
 void dcn21_calculate_wm(
@@ -1099,10 +1081,10 @@ void dcn21_calculate_wm(
 	if (pipe_cnt != pipe_idx) {
 		if (dc->res_pool->funcs->populate_dml_pipes)
 			pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 		else
 			pipe_cnt = dcn21_populate_dml_pipes_from_context(dc,
-				&context->res_ctx, pipes);
+				context, pipes);
 	}
 
 	*out_pipe_cnt = pipe_cnt;
@@ -1192,7 +1174,7 @@ static void dcn21_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dcn21_resource_pool *dcn21_pool = TO_DCN21_RES_POOL(*pool);
 
-	destruct(dcn21_pool);
+	dcn21_resource_destruct(dcn21_pool);
 	kfree(dcn21_pool);
 	*pool = NULL;
 }
@@ -1331,7 +1313,6 @@ static void read_dce_straps(
 
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 
 struct display_stream_compressor *dcn21_dsc_create(
 	struct dc_context *ctx, uint32_t inst)
@@ -1347,16 +1328,9 @@ struct display_stream_compressor *dcn21_dsc_create(
 	dsc2_construct(dsc, ctx, inst, &dsc_regs[inst], &dsc_shift, &dsc_mask);
 	return &dsc->base;
 }
-#endif
 
 static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
 {
-	/*
-	TODO: Fix this function to calcualte correct values.
-	There are known issues with this function currently
-	that will need to be investigated. Use hardcoded known good values for now.
-
-
 	struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool);
 	struct clk_limit_table *clk_table = &bw_params->clk_table;
 	int i;
@@ -1371,11 +1345,14 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 		dcn2_1_soc.clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
 		dcn2_1_soc.clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
 		dcn2_1_soc.clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-		dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 16 / 1000;
+		dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 2;
 	}
-	dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - i];
+	dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - 1];
 	dcn2_1_soc.num_states = i;
-	*/
+
+	// diags does not retrieve proper values from SMU, do not update DML instance for diags
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment) && !IS_DIAG_DC(dc->ctx->dce_environment))
+		dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21);
 }
 
 /* Temporary Place holder until we can get them from fuse */
@@ -1529,8 +1506,9 @@ static const struct encoder_feature_support link_enc_feature = {
 
 #define link_regs(id, phyid)\
 [id] = {\
-	LE_DCN10_REG_LIST(id), \
+	LE_DCN2_REG_LIST(id), \
 	UNIPHY_DCN2_REG_LIST(phyid), \
+	DPCS_DCN21_REG_LIST(id), \
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
 }
 
@@ -1569,11 +1547,13 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
 };
 
 static const struct dcn10_link_enc_shift le_shift = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT),\
+	DPCS_DCN21_MASK_SH_LIST(__SHIFT)
 };
 
 static const struct dcn10_link_enc_mask le_mask = {
-	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK)
+	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK),\
+	DPCS_DCN21_MASK_SH_LIST(_MASK)
 };
 
 static int map_transmitter_id_to_phy_instance(
@@ -1639,10 +1619,11 @@ static uint32_t read_pipe_fuses(struct dc_context *ctx)
 }
 
 static int dcn21_populate_dml_pipes_from_context(
-		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
+		struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes)
 {
-	uint32_t pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, res_ctx, pipes);
+	uint32_t pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, context, pipes);
 	int i;
+	struct resource_context *res_ctx = &context->res_ctx;
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 
@@ -1671,7 +1652,7 @@ static struct resource_funcs dcn21_res_pool_funcs = {
 	.update_bw_bounding_box = update_bw_bounding_box
 };
 
-static bool construct(
+static bool dcn21_resource_construct(
 	uint8_t num_virtual_links,
 	struct dc *dc,
 	struct dcn21_resource_pool *pool)
@@ -1711,6 +1692,7 @@ static bool construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.extended_aux_timeout_support = true;
+	dc->caps.dmcub_support = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
@@ -1760,7 +1742,7 @@ static bool construct(
 		goto create_fail;
 	}
 
-	pool->base.dmcu = dcn20_dmcu_create(ctx,
+	pool->base.dmcu = dcn21_dmcu_create(ctx,
 			&dmcu_regs,
 			&dmcu_shift,
 			&dmcu_mask);
@@ -1770,6 +1752,10 @@ static bool construct(
 		goto create_fail;
 	}
 
+	// Leave as NULL to not affect current dmcu psr programming sequence
+	// Will be uncommented when functionality is confirmed to be working
+	pool->base.psr = NULL;
+
 	pool->base.abm = dce_abm_create(ctx,
 			&abm_regs,
 			&abm_shift,
@@ -1780,18 +1766,6 @@ static bool construct(
 		goto create_fail;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DMUB
-	pool->base.dmcub = dcn21_dmcub_create(ctx,
-			&dmcub_regs,
-			&dmcub_shift,
-			&dmcub_mask);
-	if (pool->base.dmcub == NULL) {
-		dm_error("DC: failed to create dmcub!\n");
-		BREAK_TO_DEBUGGER();
-		goto create_fail;
-	}
-#endif
-
 	pool->base.pp_smu = dcn21_pp_smu_create(ctx);
 
 	num_pipes = dcn2_1_ip.max_num_dpp;
@@ -1818,41 +1792,41 @@ static bool construct(
 		if ((pipe_fuses & (1 << i)) != 0)
 			continue;
 
-		pool->base.hubps[i] = dcn21_hubp_create(ctx, i);
-		if (pool->base.hubps[i] == NULL) {
+		pool->base.hubps[j] = dcn21_hubp_create(ctx, i);
+		if (pool->base.hubps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create memory input!\n");
 			goto create_fail;
 		}
 
-		pool->base.ipps[i] = dcn21_ipp_create(ctx, i);
-		if (pool->base.ipps[i] == NULL) {
+		pool->base.ipps[j] = dcn21_ipp_create(ctx, i);
+		if (pool->base.ipps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create input pixel processor!\n");
 			goto create_fail;
 		}
 
-		pool->base.dpps[i] = dcn21_dpp_create(ctx, i);
-		if (pool->base.dpps[i] == NULL) {
+		pool->base.dpps[j] = dcn21_dpp_create(ctx, i);
+		if (pool->base.dpps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create dpps!\n");
 			goto create_fail;
 		}
 
-		pool->base.opps[i] = dcn21_opp_create(ctx, i);
-		if (pool->base.opps[i] == NULL) {
+		pool->base.opps[j] = dcn21_opp_create(ctx, i);
+		if (pool->base.opps[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
 			goto create_fail;
 		}
 
-		pool->base.timing_generators[i] = dcn21_timing_generator_create(
+		pool->base.timing_generators[j] = dcn21_timing_generator_create(
 				ctx, i);
-		if (pool->base.timing_generators[i] == NULL) {
+		if (pool->base.timing_generators[j] == NULL) {
 			BREAK_TO_DEBUGGER();
 			dm_error("DC: failed to create tg!\n");
 			goto create_fail;
@@ -1896,7 +1870,6 @@ static bool construct(
 		goto create_fail;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	for (i = 0; i < pool->base.res_cap->num_dsc; i++) {
 		pool->base.dscs[i] = dcn21_dsc_create(ctx, i);
 		if (pool->base.dscs[i] == NULL) {
@@ -1905,7 +1878,6 @@ static bool construct(
 			goto create_fail;
 		}
 	}
-#endif
 
 	if (!dcn20_dwbc_create(ctx, &pool->base)) {
 		BREAK_TO_DEBUGGER();
@@ -1936,7 +1908,7 @@ static bool construct(
 
 create_fail:
 
-	destruct(pool);
+	dcn21_resource_destruct(pool);
 
 	return false;
 }
@@ -1951,7 +1923,7 @@ struct resource_pool *dcn21_create_resource_pool(
 	if (!pool)
 		return NULL;
 
-	if (construct(init_data->num_virtual_links, dc, pool))
+	if (dcn21_resource_construct(init_data->num_virtual_links, dc, pool))
 		return &pool->base;
 
 	BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index 94b75e942607..8bde1d688f2e 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -118,13 +118,11 @@ bool dm_helpers_submit_i2c(
 		const struct dc_link *link,
 		struct i2c_command *cmd);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 bool dm_helpers_dp_write_dsc_enable(
 		struct dc_context *ctx,
 		const struct dc_stream_state *stream,
 		bool enable
 );
-#endif
 bool dm_helpers_is_dp_sink_present(
 		struct dc_link *link);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
index ef7df9ef6d7e..ae608c329366 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -41,12 +41,8 @@ enum pp_smu_ver {
 	 */
 	PP_SMU_UNSUPPORTED,
 	PP_SMU_VER_RV,
-#ifndef CONFIG_TRIM_DRM_AMD_DC_DCN2_0
 	PP_SMU_VER_NV,
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	PP_SMU_VER_RN,
-#endif
 
 	PP_SMU_VER_MAX
 };
@@ -143,7 +139,6 @@ struct pp_smu_funcs_rv {
 	void (*set_pme_wa_enable)(struct pp_smu *pp);
 };
 
-#ifndef CONFIG_TRIM_DRM_AMD_DC_DCN2_0
 /* Used by pp_smu_funcs_nv.set_voltage_by_freq
  *
  */
@@ -247,7 +242,6 @@ struct pp_smu_funcs_nv {
 	enum pp_smu_status (*set_pstate_handshake_support)(struct pp_smu *pp,
 			BOOLEAN pstate_handshake_supported);
 };
-#endif
 
 #define PP_SMU_NUM_SOCCLK_DPM_LEVELS  8
 #define PP_SMU_NUM_DCFCLK_DPM_LEVELS  8
@@ -291,12 +285,8 @@ struct pp_smu_funcs {
 	struct pp_smu ctx;
 	union {
 		struct pp_smu_funcs_rv rv_funcs;
-#ifndef CONFIG_TRIM_DRM_AMD_DC_DCN2_0
 		struct pp_smu_funcs_nv nv_funcs;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 		struct pp_smu_funcs_rn rn_funcs;
-#endif
 
 	};
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 1a0429744630..968ff1fef486 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -40,6 +40,9 @@
 
 #undef DEPRECATED
 
+struct dmub_srv;
+struct dc_dmub_srv;
+
 irq_handler_idx dm_register_interrupt(
 	struct dc_context *ctx,
 	struct dc_interrupt_params *int_params,
@@ -139,6 +142,13 @@ uint32_t generic_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1, ...);
 
+struct dc_dmub_srv *dc_dmub_srv_create(struct dc *dc, struct dmub_srv *dmub);
+void dc_dmub_srv_destroy(struct dc_dmub_srv **dmub_srv);
+
+void reg_sequence_start_gather(const struct dc_context *ctx);
+void reg_sequence_start_execute(const struct dc_context *ctx);
+void reg_sequence_wait_done(const struct dc_context *ctx);
+
 #define FD(reg_field)	reg_field ## __SHIFT, \
 						reg_field ## _MASK
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
index a3d1be20dd9d..b52ba6ffabe1 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
@@ -220,6 +220,7 @@ struct dm_bl_data_point {
 };
 
 /* Total size of the structure should not exceed 256 bytes */
+#define BL_DATA_POINTS 99
 struct dm_acpi_atif_backlight_caps {
 	uint16_t size; /* Bytes 0-1 (2 bytes) */
 	uint16_t flags; /* Byted 2-3 (2 bytes) */
@@ -229,7 +230,7 @@ struct dm_acpi_atif_backlight_caps {
 	uint8_t  min_input_signal; /* Byte 7 */
 	uint8_t  max_input_signal; /* Byte 8 */
 	uint8_t  num_data_points; /* Byte 9 */
-	struct dm_bl_data_point data_points[99]; /* Bytes 10-207 (198 bytes)*/
+	struct dm_bl_data_point data_points[BL_DATA_POINTS]; /* Bytes 10-207 (198 bytes)*/
 };
 
 enum dm_acpi_display_type {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 8df251626e22..7ee8b8460a9b 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -1,5 +1,6 @@
 #
 # Copyright 2017 Advanced Micro Devices, Inc.
+# Copyright 2019 Raptor Engineering, LLC
 #
 # Permission is hereby granted, free of charge, to any person obtaining a
 # copy of this software and associated documentation files (the "Software"),
@@ -24,7 +25,13 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
+ifdef CONFIG_X86
 dml_ccflags := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+dml_ccflags := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -32,6 +39,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -40,17 +48,16 @@ dml_ccflags += -mpreferred-stack-boundary=4
 else
 dml_ccflags += -msse2
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags)
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags)
-endif
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags)
 endif
@@ -61,11 +68,9 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dml_common_defs.o := $(dml_ccflags)
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
 	dml_common_defs.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_20.o
 DML += dcn20/display_rq_dlg_calc_20v2.o dcn20/display_mode_vba_20v2.o
-endif
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 DML += dcn21/display_rq_dlg_calc_21.o dcn21/display_mode_vba_21.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 6c6c486b774a..e7a8ac7a1f22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -937,7 +937,7 @@ static unsigned int CalculateVMAndRowBytes(
 		*MetaRowByte = 0;
 	}
 
-	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) {
+	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) {
 		MacroTileSizeBytes = 256;
 		MacroTileHeight = BlockHeight256Bytes;
 	} else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x
@@ -1335,11 +1335,11 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 		else
 			mode_lib->vba.SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k];
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true)
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 			MainPlaneDoesODMCombine = true;
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j)
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true)
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 				MainPlaneDoesODMCombine = true;
 
 		if (MainPlaneDoesODMCombine == true)
@@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
@@ -2847,12 +2848,12 @@ static void dml20_DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 			SwathWidth = mode_lib->vba.ViewportHeight[k];
 		}
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true) {
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 			MainPlaneDoesODMCombine = true;
 		}
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) {
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true) {
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 				MainPlaneDoesODMCombine = true;
 			}
 		}
@@ -3347,7 +3348,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 										== dm_420_10))
 				|| (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl
 						|| mode_lib->vba.SurfaceTiling[k]
-								== dm_sw_gfx7_2d_thin_lvp)
+								== dm_sw_gfx7_2d_thin_l_vp)
 						&& !((mode_lib->vba.SourcePixelFormat[k]
 								== dm_444_64
 								|| mode_lib->vba.SourcePixelFormat[k]
@@ -3445,10 +3446,10 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->FabricAndDRAMBandwidthPerState[i] * 1000)
 				* locals->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100;
 
-		locals->ReturnBWPerState[i] = locals->ReturnBWToDCNPerState;
+		locals->ReturnBWPerState[i][0] = locals->ReturnBWToDCNPerState;
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3459,7 +3460,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3471,7 +3472,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->DCFCLKPerState[i], locals->FabricAndDRAMBandwidthPerState[i] * 1000);
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3482,7 +3483,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3520,12 +3521,12 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i] =
 				(mode_lib->vba.RoundTripPingLatencyCycles + 32.0) / mode_lib->vba.DCFCLKPerState[i]
-				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i];
-		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i]
+				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0];
+		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0]
 				> locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) {
-			locals->ROBSupport[i] = true;
+			locals->ROBSupport[i][0] = true;
 		} else {
-			locals->ROBSupport[i] = false;
+			locals->ROBSupport[i][0] = false;
 		}
 	}
 	/*Writeback Mode Support Check*/
@@ -3902,7 +3903,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity
 						&& locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]
-						&& locals->ODMCombineEnablePerState[i][k] == false) {
+						&& locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->NoOfDPP[i][j][k] = 1;
 					locals->RequiredDPPCLK[i][j][k] =
 						locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
@@ -3991,16 +3992,16 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	/*Viewport Size Check*/
 
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->ViewportSizeSupport[i] = true;
+		locals->ViewportSizeSupport[i][0] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (locals->ODMCombineEnablePerState[i][k] == true) {
+			if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 				if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			} else {
 				if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			}
 		}
@@ -4182,8 +4183,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						mode_lib->vba.DSCFormatFactor = 1;
 					}
 					if (locals->RequiresDSC[i][k] == true) {
-						if (locals->ODMCombineEnablePerState[i][k]
-								== true) {
+						if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 							if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor
 									> (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) {
 								locals->DSCCLKRequiredMoreThanSupported[i] =
@@ -4206,7 +4206,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 		mode_lib->vba.TotalDSCUnitsRequired = 0.0;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (locals->RequiresDSC[i][k] == true) {
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					mode_lib->vba.TotalDSCUnitsRequired =
 							mode_lib->vba.TotalDSCUnitsRequired + 2.0;
 				} else {
@@ -4248,7 +4248,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.bpp = locals->OutputBppPerState[i][k];
 			}
 			if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) {
-				if (locals->ODMCombineEnablePerState[i][k] == false) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->DSCDelayPerState[i][k] =
 							dscceComputeDelay(
 									mode_lib->vba.DSCInputBitPerComponent[k],
@@ -4291,7 +4291,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		for (j = 0; j < 2; j++) {
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				if (locals->ODMCombineEnablePerState[i][k] == true)
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1)
 					locals->SwathWidthYPerState[i][j][k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(locals->HActive[k] / 2 * locals->HRatio[k]));
 				else
 					locals->SwathWidthYPerState[i][j][k] = locals->SwathWidthYSingleDPP[k] / locals->NoOfDPP[i][j][k];
@@ -4344,28 +4344,28 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 
 				locals->EffectiveDETLBLinesLuma = dml_floor(locals->LinesInDETLuma +  dml_min(
 						locals->LinesInDETLuma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETY[k] *
-						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesLuma),
 						locals->SwathHeightYPerState[i][j][k]);
 
 				locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min(
 						locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] *
-						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesChroma),
 						locals->SwathHeightCPerState[i][j][k]);
 
 				if (locals->BytePerPixelInDETC[k] == 0) {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 							/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]);
+								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]);
 				} else {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min(
 						locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 						/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]),
+						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]),
 							locals->EffectiveDETLBLinesChroma * (locals->HTotal[k] / locals->PixelClock[k]) / (locals->VRatio[k] / 2) -
 							locals->EffectiveDETLBLinesChroma * locals->SwathWidthYPerState[i][j][k] / 2 *
-							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]));
+							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]));
 				}
 			}
 		}
@@ -4405,14 +4405,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->SwathHeightYThisState[k] = locals->SwathHeightYPerState[i][j][k];
 				locals->SwathHeightCThisState[k] = locals->SwathHeightCPerState[i][j][k];
 				locals->SwathWidthYThisState[k] = locals->SwathWidthYPerState[i][j][k];
-				mode_lib->vba.ProjectedDCFCLKDeepSleep = dml_max(
-						mode_lib->vba.ProjectedDCFCLKDeepSleep,
+				mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max(
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 						mode_lib->vba.PixelClock[k] / 16.0);
 				if (mode_lib->vba.BytePerPixelInDETC[k] == 0.0) {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4422,9 +4422,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4435,9 +4435,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					}
 				} else {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4447,9 +4447,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4459,9 +4459,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.RequiredDPPCLK[i][j][k]);
 					}
 					if (mode_lib->vba.VRatio[k] / 2.0 <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4472,9 +4472,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4510,7 +4510,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						&mode_lib->vba.PTEBufferSizeNotExceededY[i][j][k],
 						&mode_lib->vba.dpte_row_height[k],
 						&mode_lib->vba.meta_row_height[k]);
-				mode_lib->vba.PrefetchLinesY[k] = CalculatePrefetchSourceLines(
+				mode_lib->vba.PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines(
 						mode_lib,
 						mode_lib->vba.VRatio[k],
 						mode_lib->vba.vtaps[k],
@@ -4549,7 +4549,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							&mode_lib->vba.PTEBufferSizeNotExceededC[i][j][k],
 							&mode_lib->vba.dpte_row_height_chroma[k],
 							&mode_lib->vba.meta_row_height_chroma[k]);
-					mode_lib->vba.PrefetchLinesC[k] = CalculatePrefetchSourceLines(
+					mode_lib->vba.PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines(
 							mode_lib,
 							mode_lib->vba.VRatio[k] / 2.0,
 							mode_lib->vba.VTAPsChroma[k],
@@ -4563,14 +4563,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0;
 					mode_lib->vba.MetaRowBytesC = 0.0;
 					mode_lib->vba.DPTEBytesPerRowC = 0.0;
-					locals->PrefetchLinesC[k] = 0.0;
+					locals->PrefetchLinesC[0][0][k] = 0.0;
 					locals->PTEBufferSizeNotExceededC[i][j][k] = true;
 					locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma;
 				}
-				locals->PDEAndMetaPTEBytesPerFrame[k] =
+				locals->PDEAndMetaPTEBytesPerFrame[0][0][k] =
 						mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC;
-				locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
-				locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
+				locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
+				locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
 
 				CalculateActiveRowBandwidth(
 						mode_lib->vba.GPUVMEnable,
@@ -4597,14 +4597,14 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									+ mode_lib->vba.TotalNumberOfDCCActiveDPP[i][j]
 											* mode_lib->vba.MetaChunkSize)
 									* 1024.0
-									/ mode_lib->vba.ReturnBWPerState[i];
+									/ mode_lib->vba.ReturnBWPerState[i][0];
 			if (mode_lib->vba.GPUVMEnable == true) {
 				mode_lib->vba.ExtraLatency = mode_lib->vba.ExtraLatency
 						+ mode_lib->vba.TotalNumberOfActiveDPP[i][j]
 								* mode_lib->vba.PTEGroupSize
-								/ mode_lib->vba.ReturnBWPerState[i];
+								/ mode_lib->vba.ReturnBWPerState[i][0];
 			}
-			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep;
+			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if (mode_lib->vba.BlendingAndTiming[k] == k) {
@@ -4654,7 +4654,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			}
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
+				locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
 					- dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0));
 			}
 
@@ -4699,7 +4699,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									mode_lib->vba.RequiredDPPCLK[i][j][k],
 									mode_lib->vba.RequiredDISPCLK[i][j],
 									mode_lib->vba.PixelClock[k],
-									mode_lib->vba.ProjectedDCFCLKDeepSleep,
+									mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 									mode_lib->vba.DSCDelayPerState[i][k],
 									mode_lib->vba.NoOfDPP[i][j][k],
 									mode_lib->vba.ScalerEnabled[k],
@@ -4717,7 +4717,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 											- mode_lib->vba.VActive[k],
 									mode_lib->vba.HTotal[k],
 									mode_lib->vba.MaxInterDCNTileRepeaters,
-									mode_lib->vba.MaximumVStartup[k],
+									mode_lib->vba.MaximumVStartup[0][0][k],
 									mode_lib->vba.GPUVMMaxPageTableLevels,
 									mode_lib->vba.GPUVMEnable,
 									mode_lib->vba.DynamicMetadataEnable[k],
@@ -4727,15 +4727,15 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									mode_lib->vba.UrgentLatencyPixelDataOnly,
 									mode_lib->vba.ExtraLatency,
 									mode_lib->vba.TimeCalc,
-									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-									mode_lib->vba.MetaRowBytes[k],
-									mode_lib->vba.DPTEBytesPerRow[k],
-									mode_lib->vba.PrefetchLinesY[k],
+									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+									mode_lib->vba.MetaRowBytes[0][0][k],
+									mode_lib->vba.DPTEBytesPerRow[0][0][k],
+									mode_lib->vba.PrefetchLinesY[0][0][k],
 									mode_lib->vba.SwathWidthYPerState[i][j][k],
 									mode_lib->vba.BytePerPixelInDETY[k],
 									mode_lib->vba.PrefillY[k],
 									mode_lib->vba.MaxNumSwY[k],
-									mode_lib->vba.PrefetchLinesC[k],
+									mode_lib->vba.PrefetchLinesC[0][0][k],
 									mode_lib->vba.BytePerPixelInDETC[k],
 									mode_lib->vba.PrefillC[k],
 									mode_lib->vba.MaxNumSwC[k],
@@ -4766,19 +4766,19 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				locals->prefetch_vm_bw_valid = true;
 				locals->prefetch_row_bw_valid = true;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					if (locals->PDEAndMetaPTEBytesPerFrame[k] == 0)
+					if (locals->PDEAndMetaPTEBytesPerFrame[0][0][k] == 0)
 						locals->prefetch_vm_bw[k] = 0;
 					else if (locals->LinesForMetaPTE[k] > 0)
-						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[k]
+						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[0][0][k]
 							/ (locals->LinesForMetaPTE[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_vm_bw[k] = 0;
 						locals->prefetch_vm_bw_valid = false;
 					}
-					if (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k] == 0)
+					if (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k] == 0)
 						locals->prefetch_row_bw[k] = 0;
 					else if (locals->LinesForMetaAndDPTERow[k] > 0)
-						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k])
+						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k])
 							/ (locals->LinesForMetaAndDPTERow[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_row_bw[k] = 0;
@@ -4797,13 +4797,13 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 											mode_lib->vba.RequiredPrefetchPixelDataBWLuma[i][j][k])
 											+ mode_lib->vba.meta_row_bw[k] + mode_lib->vba.dpte_row_bw[k]);
 				}
-				locals->BandwidthWithoutPrefetchSupported[i] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]) {
-					locals->BandwidthWithoutPrefetchSupported[i] = false;
+				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
+				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]) {
+					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]) {
+				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]) {
 					locals->PrefetchSupported[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4828,7 +4828,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			if (mode_lib->vba.PrefetchSupported[i][j] == true
 					&& mode_lib->vba.VRatioInPrefetchSupported[i][j] == true) {
 				mode_lib->vba.BandwidthAvailableForImmediateFlip =
-						mode_lib->vba.ReturnBWPerState[i];
+						mode_lib->vba.ReturnBWPerState[i][0];
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.BandwidthAvailableForImmediateFlip =
 							mode_lib->vba.BandwidthAvailableForImmediateFlip
@@ -4842,9 +4842,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					if ((mode_lib->vba.SourcePixelFormat[k] != dm_420_8
 							&& mode_lib->vba.SourcePixelFormat[k] != dm_420_10)) {
 						mode_lib->vba.ImmediateFlipBytes[k] =
-								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k]
-										+ mode_lib->vba.MetaRowBytes[k]
-										+ mode_lib->vba.DPTEBytesPerRow[k];
+								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k]
+										+ mode_lib->vba.MetaRowBytes[0][0][k]
+										+ mode_lib->vba.DPTEBytesPerRow[0][0][k];
 					}
 				}
 				mode_lib->vba.TotImmediateFlipBytes = 0.0;
@@ -4872,9 +4872,9 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 									/ mode_lib->vba.PixelClock[k],
 							mode_lib->vba.VRatio[k],
 							mode_lib->vba.Tno_bw[k],
-							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-							mode_lib->vba.MetaRowBytes[k],
-							mode_lib->vba.DPTEBytesPerRow[k],
+							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+							mode_lib->vba.MetaRowBytes[0][0][k],
+							mode_lib->vba.DPTEBytesPerRow[0][0][k],
 							mode_lib->vba.DCCEnable[k],
 							mode_lib->vba.dpte_row_height[k],
 							mode_lib->vba.meta_row_height[k],
@@ -4899,7 +4899,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				mode_lib->vba.ImmediateFlipSupportedForState[i][j] = true;
 				if (mode_lib->vba.total_dcn_read_bw_with_flip
-						> mode_lib->vba.ReturnBWPerState[i]) {
+						> mode_lib->vba.ReturnBWPerState[i][0]) {
 					mode_lib->vba.ImmediateFlipSupportedForState[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4918,13 +4918,13 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; k++)
 		mode_lib->vba.MaxTotalVActiveRDBandwidth = mode_lib->vba.MaxTotalVActiveRDBandwidth + mode_lib->vba.ReadBandwidth[k];
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(mode_lib->vba.ReturnBusWidth *
+		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(mode_lib->vba.ReturnBusWidth *
 				mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.FabricAndDRAMBandwidthPerState[i] * 1000) *
 				mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100;
-		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i])
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = true;
+		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0])
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = true;
 		else
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = false;
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = false;
 	}
 
 	/*PTE Buffer Size Check*/
@@ -5012,7 +5012,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_SCALE_RATIO_TAP;
 			} else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) {
 				status = DML_FAIL_SOURCE_PIXEL_FORMAT;
-			} else if (locals->ViewportSizeSupport[i] != true) {
+			} else if (locals->ViewportSizeSupport[i][0] != true) {
 				status = DML_FAIL_VIEWPORT_SIZE;
 			} else if (locals->DIOSupport[i] != true) {
 				status = DML_FAIL_DIO_SUPPORT;
@@ -5022,7 +5022,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_DSC_CLK_REQUIRED;
 			} else if (locals->UrgentLatencySupport[i][j] != true) {
 				status = DML_FAIL_URGENT_LATENCY;
-			} else if (locals->ROBSupport[i] != true) {
+			} else if (locals->ROBSupport[i][0] != true) {
 				status = DML_FAIL_REORDERING_BUFFER;
 			} else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) {
 				status = DML_FAIL_DISPCLK_DPPCLK;
@@ -5042,7 +5042,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_PITCH_SUPPORT;
 			} else if (locals->PrefetchSupported[i][j] != true) {
 				status = DML_FAIL_PREFETCH_SUPPORT;
-			} else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) {
+			} else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) {
 				status = DML_FAIL_TOTAL_V_ACTIVE_BW;
 			} else if (locals->VRatioInPrefetchSupported[i][j] != true) {
 				status = DML_FAIL_V_RATIO_PREFETCH;
@@ -5088,7 +5088,7 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel];
-	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	mode_lib->vba.FabricAndDRAMBandwidth = locals->FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel];
 	for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 		if (mode_lib->vba.BlendingAndTiming[k] == k) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 3c70dd577292..22f3b5a4b3b9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -997,7 +997,7 @@ static unsigned int CalculateVMAndRowBytes(
 		*MetaRowByte = 0;
 	}
 
-	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) {
+	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) {
 		MacroTileSizeBytes = 256;
 		MacroTileHeight = BlockHeight256Bytes;
 	} else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x
@@ -1395,11 +1395,11 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 		else
 			mode_lib->vba.SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k];
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true)
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 			MainPlaneDoesODMCombine = true;
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j)
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true)
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 				MainPlaneDoesODMCombine = true;
 
 		if (MainPlaneDoesODMCombine == true)
@@ -2611,9 +2611,13 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+	if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
 		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
+	} else if (mode_lib->vba.DummyPStateCheck &&
+			mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
 		if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
 			mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vblank;
@@ -2881,12 +2885,12 @@ static void dml20v2_DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 			SwathWidth = mode_lib->vba.ViewportHeight[k];
 		}
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true) {
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 			MainPlaneDoesODMCombine = true;
 		}
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) {
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true) {
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 				MainPlaneDoesODMCombine = true;
 			}
 		}
@@ -3381,7 +3385,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 										== dm_420_10))
 				|| (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl
 						|| mode_lib->vba.SurfaceTiling[k]
-								== dm_sw_gfx7_2d_thin_lvp)
+								== dm_sw_gfx7_2d_thin_l_vp)
 						&& !((mode_lib->vba.SourcePixelFormat[k]
 								== dm_444_64
 								|| mode_lib->vba.SourcePixelFormat[k]
@@ -3479,10 +3483,10 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->FabricAndDRAMBandwidthPerState[i] * 1000)
 				* locals->PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100;
 
-		locals->ReturnBWPerState[i] = locals->ReturnBWToDCNPerState;
+		locals->ReturnBWPerState[i][0] = locals->ReturnBWToDCNPerState;
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3493,7 +3497,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3505,7 +3509,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->DCFCLKPerState[i], locals->FabricAndDRAMBandwidthPerState[i] * 1000);
 
 		if (locals->DCCEnabledInAnyPlane == true && locals->ReturnBWToDCNPerState > locals->DCFCLKPerState[i] * locals->ReturnBusWidth / 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 					locals->ReturnBWToDCNPerState * 4 * (1 - locals->UrgentLatency /
 					((locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 					/ (locals->ReturnBWToDCNPerState - locals->DCFCLKPerState[i]
@@ -3516,7 +3520,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				+ (locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024);
 
 		if (locals->DCCEnabledInAnyPlane && locals->CriticalPoint > 1 && locals->CriticalPoint < 4) {
-			locals->ReturnBWPerState[i] = dml_min(locals->ReturnBWPerState[i],
+			locals->ReturnBWPerState[i][0] = dml_min(locals->ReturnBWPerState[i][0],
 				4 * locals->ReturnBWToDCNPerState *
 				(locals->ROBBufferSizeInKByte - locals->PixelChunkSizeInKByte) * 1024
 				* locals->ReturnBusWidth * locals->DCFCLKPerState[i] * locals->UrgentLatency /
@@ -3554,12 +3558,12 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i] =
 				(mode_lib->vba.RoundTripPingLatencyCycles + 32.0) / mode_lib->vba.DCFCLKPerState[i]
-				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i];
-		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i]
+				+ locals->UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0];
+		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0]
 				> locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) {
-			locals->ROBSupport[i] = true;
+			locals->ROBSupport[i][0] = true;
 		} else {
-			locals->ROBSupport[i] = false;
+			locals->ROBSupport[i][0] = false;
 		}
 	}
 	/*Writeback Mode Support Check*/
@@ -3942,7 +3946,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				}
 				if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity
 						&& locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]
-						&& locals->ODMCombineEnablePerState[i][k] == false) {
+						&& locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->NoOfDPP[i][j][k] = 1;
 					locals->RequiredDPPCLK[i][j][k] =
 						locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
@@ -4031,16 +4035,16 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	/*Viewport Size Check*/
 
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->ViewportSizeSupport[i] = true;
+		locals->ViewportSizeSupport[i][0] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (locals->ODMCombineEnablePerState[i][k] == true) {
+			if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 				if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			} else {
 				if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			}
 		}
@@ -4222,8 +4226,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						mode_lib->vba.DSCFormatFactor = 1;
 					}
 					if (locals->RequiresDSC[i][k] == true) {
-						if (locals->ODMCombineEnablePerState[i][k]
-								== true) {
+						if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 							if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor
 									> (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) {
 								locals->DSCCLKRequiredMoreThanSupported[i] =
@@ -4246,7 +4249,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 		mode_lib->vba.TotalDSCUnitsRequired = 0.0;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (locals->RequiresDSC[i][k] == true) {
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					mode_lib->vba.TotalDSCUnitsRequired =
 							mode_lib->vba.TotalDSCUnitsRequired + 2.0;
 				} else {
@@ -4288,7 +4291,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				mode_lib->vba.bpp = locals->OutputBppPerState[i][k];
 			}
 			if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) {
-				if (locals->ODMCombineEnablePerState[i][k] == false) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->DSCDelayPerState[i][k] =
 							dscceComputeDelay(
 									mode_lib->vba.DSCInputBitPerComponent[k],
@@ -4331,7 +4334,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		for (j = 0; j < 2; j++) {
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				if (locals->ODMCombineEnablePerState[i][k] == true)
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1)
 					locals->SwathWidthYPerState[i][j][k] = dml_min(locals->SwathWidthYSingleDPP[k], dml_round(locals->HActive[k] / 2 * locals->HRatio[k]));
 				else
 					locals->SwathWidthYPerState[i][j][k] = locals->SwathWidthYSingleDPP[k] / locals->NoOfDPP[i][j][k];
@@ -4384,28 +4387,28 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 
 				locals->EffectiveDETLBLinesLuma = dml_floor(locals->LinesInDETLuma +  dml_min(
 						locals->LinesInDETLuma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETY[k] *
-						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesLuma),
 						locals->SwathHeightYPerState[i][j][k]);
 
 				locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min(
 						locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] *
-						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i],
+						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesChroma),
 						locals->SwathHeightCPerState[i][j][k]);
 
 				if (locals->BytePerPixelInDETC[k] == 0) {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 							/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]);
+								dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]);
 				} else {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = dml_min(
 						locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
 						/ locals->VRatio[k] - locals->EffectiveDETLBLinesLuma * locals->SwathWidthYPerState[i][j][k] *
-						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]),
+						dml_ceil(locals->BytePerPixelInDETY[k], 1) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]),
 							locals->EffectiveDETLBLinesChroma * (locals->HTotal[k] / locals->PixelClock[k]) / (locals->VRatio[k] / 2) -
 							locals->EffectiveDETLBLinesChroma * locals->SwathWidthYPerState[i][j][k] / 2 *
-							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i] / locals->NoOfDPP[i][j][k]));
+							dml_ceil(locals->BytePerPixelInDETC[k], 2) / (locals->ReturnBWPerState[i][0] / locals->NoOfDPP[i][j][k]));
 				}
 			}
 		}
@@ -4450,14 +4453,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->SwathHeightYThisState[k] = locals->SwathHeightYPerState[i][j][k];
 				locals->SwathHeightCThisState[k] = locals->SwathHeightCPerState[i][j][k];
 				locals->SwathWidthYThisState[k] = locals->SwathWidthYPerState[i][j][k];
-				mode_lib->vba.ProjectedDCFCLKDeepSleep = dml_max(
-						mode_lib->vba.ProjectedDCFCLKDeepSleep,
+				mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] = dml_max(
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 						mode_lib->vba.PixelClock[k] / 16.0);
 				if (mode_lib->vba.BytePerPixelInDETC[k] == 0.0) {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4467,9 +4470,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4480,9 +4483,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 					}
 				} else {
 					if (mode_lib->vba.VRatio[k] <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4492,9 +4495,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETY[k],
@@ -4504,9 +4507,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.RequiredDPPCLK[i][j][k]);
 					}
 					if (mode_lib->vba.VRatio[k] / 2.0 <= 1.0) {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4517,9 +4520,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 												* mode_lib->vba.PixelClock[k]
 												/ mode_lib->vba.NoOfDPP[i][j][k]);
 					} else {
-						mode_lib->vba.ProjectedDCFCLKDeepSleep =
+						mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0] =
 								dml_max(
-										mode_lib->vba.ProjectedDCFCLKDeepSleep,
+										mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 										1.1
 												* dml_ceil(
 														mode_lib->vba.BytePerPixelInDETC[k],
@@ -4555,7 +4558,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						&mode_lib->vba.PTEBufferSizeNotExceededY[i][j][k],
 						&mode_lib->vba.dpte_row_height[k],
 						&mode_lib->vba.meta_row_height[k]);
-				mode_lib->vba.PrefetchLinesY[k] = CalculatePrefetchSourceLines(
+				mode_lib->vba.PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines(
 						mode_lib,
 						mode_lib->vba.VRatio[k],
 						mode_lib->vba.vtaps[k],
@@ -4594,7 +4597,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 							&mode_lib->vba.PTEBufferSizeNotExceededC[i][j][k],
 							&mode_lib->vba.dpte_row_height_chroma[k],
 							&mode_lib->vba.meta_row_height_chroma[k]);
-					mode_lib->vba.PrefetchLinesC[k] = CalculatePrefetchSourceLines(
+					mode_lib->vba.PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines(
 							mode_lib,
 							mode_lib->vba.VRatio[k] / 2.0,
 							mode_lib->vba.VTAPsChroma[k],
@@ -4608,14 +4611,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 					mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0;
 					mode_lib->vba.MetaRowBytesC = 0.0;
 					mode_lib->vba.DPTEBytesPerRowC = 0.0;
-					locals->PrefetchLinesC[k] = 0.0;
+					locals->PrefetchLinesC[0][0][k] = 0.0;
 					locals->PTEBufferSizeNotExceededC[i][j][k] = true;
 					locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma;
 				}
-				locals->PDEAndMetaPTEBytesPerFrame[k] =
+				locals->PDEAndMetaPTEBytesPerFrame[0][0][k] =
 						mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC;
-				locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
-				locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
+				locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
+				locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
 
 				CalculateActiveRowBandwidth(
 						mode_lib->vba.GPUVMEnable,
@@ -4642,14 +4645,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									+ mode_lib->vba.TotalNumberOfDCCActiveDPP[i][j]
 											* mode_lib->vba.MetaChunkSize)
 									* 1024.0
-									/ mode_lib->vba.ReturnBWPerState[i];
+									/ mode_lib->vba.ReturnBWPerState[i][0];
 			if (mode_lib->vba.GPUVMEnable == true) {
 				mode_lib->vba.ExtraLatency = mode_lib->vba.ExtraLatency
 						+ mode_lib->vba.TotalNumberOfActiveDPP[i][j]
 								* mode_lib->vba.PTEGroupSize
-								/ mode_lib->vba.ReturnBWPerState[i];
+								/ mode_lib->vba.ReturnBWPerState[i][0];
 			}
-			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep;
+			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if (mode_lib->vba.BlendingAndTiming[k] == k) {
@@ -4699,7 +4702,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 			}
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
+				locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
 					- dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0));
 			}
 
@@ -4739,7 +4742,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						mode_lib->vba.XFCRemoteSurfaceFlipDelay = 0.0;
 					}
 
-					CalculateDelayAfterScaler(mode_lib, mode_lib->vba.ReturnBWPerState[i], mode_lib->vba.ReadBandwidthLuma[k], mode_lib->vba.ReadBandwidthChroma[k], mode_lib->vba.MaxTotalVActiveRDBandwidth,
+					CalculateDelayAfterScaler(mode_lib, mode_lib->vba.ReturnBWPerState[i][0], mode_lib->vba.ReadBandwidthLuma[k], mode_lib->vba.ReadBandwidthChroma[k], mode_lib->vba.MaxTotalVActiveRDBandwidth,
 						mode_lib->vba.DisplayPipeLineDeliveryTimeLuma[k], mode_lib->vba.DisplayPipeLineDeliveryTimeChroma[k],
 						mode_lib->vba.RequiredDPPCLK[i][j][k], mode_lib->vba.RequiredDISPCLK[i][j], mode_lib->vba.PixelClock[k], mode_lib->vba.DSCDelayPerState[i][k], mode_lib->vba.NoOfDPP[i][j][k], mode_lib->vba.ScalerEnabled[k], mode_lib->vba.NumberOfCursors[k],
 						mode_lib->vba.DPPCLKDelaySubtotal, mode_lib->vba.DPPCLKDelaySCL, mode_lib->vba.DPPCLKDelaySCLLBOnly, mode_lib->vba.DPPCLKDelayCNVCFormater, mode_lib->vba.DPPCLKDelayCNVCCursor, mode_lib->vba.DISPCLKDelaySubtotal,
@@ -4753,14 +4756,14 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									mode_lib->vba.RequiredDPPCLK[i][j][k],
 									mode_lib->vba.RequiredDISPCLK[i][j],
 									mode_lib->vba.PixelClock[k],
-									mode_lib->vba.ProjectedDCFCLKDeepSleep,
+									mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 									mode_lib->vba.NoOfDPP[i][j][k],
 									mode_lib->vba.NumberOfCursors[k],
 									mode_lib->vba.VTotal[k]
 											- mode_lib->vba.VActive[k],
 									mode_lib->vba.HTotal[k],
 									mode_lib->vba.MaxInterDCNTileRepeaters,
-									mode_lib->vba.MaximumVStartup[k],
+									mode_lib->vba.MaximumVStartup[0][0][k],
 									mode_lib->vba.GPUVMMaxPageTableLevels,
 									mode_lib->vba.GPUVMEnable,
 									mode_lib->vba.DynamicMetadataEnable[k],
@@ -4770,15 +4773,15 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									mode_lib->vba.UrgentLatencyPixelDataOnly,
 									mode_lib->vba.ExtraLatency,
 									mode_lib->vba.TimeCalc,
-									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-									mode_lib->vba.MetaRowBytes[k],
-									mode_lib->vba.DPTEBytesPerRow[k],
-									mode_lib->vba.PrefetchLinesY[k],
+									mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+									mode_lib->vba.MetaRowBytes[0][0][k],
+									mode_lib->vba.DPTEBytesPerRow[0][0][k],
+									mode_lib->vba.PrefetchLinesY[0][0][k],
 									mode_lib->vba.SwathWidthYPerState[i][j][k],
 									mode_lib->vba.BytePerPixelInDETY[k],
 									mode_lib->vba.PrefillY[k],
 									mode_lib->vba.MaxNumSwY[k],
-									mode_lib->vba.PrefetchLinesC[k],
+									mode_lib->vba.PrefetchLinesC[0][0][k],
 									mode_lib->vba.BytePerPixelInDETC[k],
 									mode_lib->vba.PrefillC[k],
 									mode_lib->vba.MaxNumSwC[k],
@@ -4808,19 +4811,19 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				locals->prefetch_vm_bw_valid = true;
 				locals->prefetch_row_bw_valid = true;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					if (locals->PDEAndMetaPTEBytesPerFrame[k] == 0)
+					if (locals->PDEAndMetaPTEBytesPerFrame[0][0][k] == 0)
 						locals->prefetch_vm_bw[k] = 0;
 					else if (locals->LinesForMetaPTE[k] > 0)
-						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[k]
+						locals->prefetch_vm_bw[k] = locals->PDEAndMetaPTEBytesPerFrame[0][0][k]
 							/ (locals->LinesForMetaPTE[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_vm_bw[k] = 0;
 						locals->prefetch_vm_bw_valid = false;
 					}
-					if (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k] == 0)
+					if (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k] == 0)
 						locals->prefetch_row_bw[k] = 0;
 					else if (locals->LinesForMetaAndDPTERow[k] > 0)
-						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k])
+						locals->prefetch_row_bw[k] = (locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k])
 							/ (locals->LinesForMetaAndDPTERow[k] * locals->HTotal[k] / locals->PixelClock[k]);
 					else {
 						locals->prefetch_row_bw[k] = 0;
@@ -4839,13 +4842,13 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 											mode_lib->vba.RequiredPrefetchPixelDataBWLuma[i][j][k])
 											+ mode_lib->vba.meta_row_bw[k] + mode_lib->vba.dpte_row_bw[k]);
 				}
-				locals->BandwidthWithoutPrefetchSupported[i] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]) {
-					locals->BandwidthWithoutPrefetchSupported[i] = false;
+				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
+				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]) {
+					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]) {
+				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]) {
 					locals->PrefetchSupported[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4870,7 +4873,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 			if (mode_lib->vba.PrefetchSupported[i][j] == true
 					&& mode_lib->vba.VRatioInPrefetchSupported[i][j] == true) {
 				mode_lib->vba.BandwidthAvailableForImmediateFlip =
-						mode_lib->vba.ReturnBWPerState[i];
+						mode_lib->vba.ReturnBWPerState[i][0];
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.BandwidthAvailableForImmediateFlip =
 							mode_lib->vba.BandwidthAvailableForImmediateFlip
@@ -4884,9 +4887,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 					if ((mode_lib->vba.SourcePixelFormat[k] != dm_420_8
 							&& mode_lib->vba.SourcePixelFormat[k] != dm_420_10)) {
 						mode_lib->vba.ImmediateFlipBytes[k] =
-								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k]
-										+ mode_lib->vba.MetaRowBytes[k]
-										+ mode_lib->vba.DPTEBytesPerRow[k];
+								mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k]
+										+ mode_lib->vba.MetaRowBytes[0][0][k]
+										+ mode_lib->vba.DPTEBytesPerRow[0][0][k];
 					}
 				}
 				mode_lib->vba.TotImmediateFlipBytes = 0.0;
@@ -4914,9 +4917,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 									/ mode_lib->vba.PixelClock[k],
 							mode_lib->vba.VRatio[k],
 							mode_lib->vba.Tno_bw[k],
-							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[k],
-							mode_lib->vba.MetaRowBytes[k],
-							mode_lib->vba.DPTEBytesPerRow[k],
+							mode_lib->vba.PDEAndMetaPTEBytesPerFrame[0][0][k],
+							mode_lib->vba.MetaRowBytes[0][0][k],
+							mode_lib->vba.DPTEBytesPerRow[0][0][k],
 							mode_lib->vba.DCCEnable[k],
 							mode_lib->vba.dpte_row_height[k],
 							mode_lib->vba.meta_row_height[k],
@@ -4941,7 +4944,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				}
 				mode_lib->vba.ImmediateFlipSupportedForState[i][j] = true;
 				if (mode_lib->vba.total_dcn_read_bw_with_flip
-						> mode_lib->vba.ReturnBWPerState[i]) {
+						> mode_lib->vba.ReturnBWPerState[i][0]) {
 					mode_lib->vba.ImmediateFlipSupportedForState[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4957,13 +4960,13 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 
 	/*Vertical Active BW support*/
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(mode_lib->vba.ReturnBusWidth *
+		mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(mode_lib->vba.ReturnBusWidth *
 				mode_lib->vba.DCFCLKPerState[i], mode_lib->vba.FabricAndDRAMBandwidthPerState[i] * 1000) *
 				mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation / 100;
-		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i])
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = true;
+		if (mode_lib->vba.MaxTotalVActiveRDBandwidth <= mode_lib->vba.MaxTotalVerticalActiveAvailableBandwidth[i][0])
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = true;
 		else
-			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i] = false;
+			mode_lib->vba.TotalVerticalActiveBandwidthSupport[i][0] = false;
 	}
 
 	/*PTE Buffer Size Check*/
@@ -5051,7 +5054,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				status = DML_FAIL_SCALE_RATIO_TAP;
 			} else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) {
 				status = DML_FAIL_SOURCE_PIXEL_FORMAT;
-			} else if (locals->ViewportSizeSupport[i] != true) {
+			} else if (locals->ViewportSizeSupport[i][0] != true) {
 				status = DML_FAIL_VIEWPORT_SIZE;
 			} else if (locals->DIOSupport[i] != true) {
 				status = DML_FAIL_DIO_SUPPORT;
@@ -5061,7 +5064,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				status = DML_FAIL_DSC_CLK_REQUIRED;
 			} else if (locals->UrgentLatencySupport[i][j] != true) {
 				status = DML_FAIL_URGENT_LATENCY;
-			} else if (locals->ROBSupport[i] != true) {
+			} else if (locals->ROBSupport[i][0] != true) {
 				status = DML_FAIL_REORDERING_BUFFER;
 			} else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) {
 				status = DML_FAIL_DISPCLK_DPPCLK;
@@ -5081,7 +5084,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				status = DML_FAIL_PITCH_SUPPORT;
 			} else if (locals->PrefetchSupported[i][j] != true) {
 				status = DML_FAIL_PREFETCH_SUPPORT;
-			} else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) {
+			} else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) {
 				status = DML_FAIL_TOTAL_V_ACTIVE_BW;
 			} else if (locals->VRatioInPrefetchSupported[i][j] != true) {
 				status = DML_FAIL_V_RATIO_PREFETCH;
@@ -5127,7 +5130,7 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 	mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel];
-	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	mode_lib->vba.FabricAndDRAMBandwidth = locals->FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel];
 	for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 		if (mode_lib->vba.BlendingAndTiming[k] == k) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
index 2c7455e22a65..ca807846032f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
@@ -107,10 +107,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
-	bool ret_val = 0;
+	bool ret_val = false;
 
 	if ((source_format == dm_420_8) || (source_format == dm_420_10))
-		ret_val = 1;
+		ret_val = true;
 
 	return ret_val;
 }
@@ -240,8 +240,8 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 	unsigned int swath_bytes_c = 0;
 	unsigned int full_swath_bytes_packed_l = 0;
 	unsigned int full_swath_bytes_packed_c = 0;
-	bool req128_l = 0;
-	bool req128_c = 0;
+	bool req128_l = false;
+	bool req128_c = false;
 	bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear);
 	bool surf_vert = (pipe_src_param.source_scan == dm_vert);
 	unsigned int log2_swath_height_l = 0;
@@ -264,13 +264,13 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request
-			req128_l = 0;
-			req128_c = 0;
+			req128_l = false;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		} else { //128b request (for luma only for yuv420 8bpc)
-			req128_l = 1;
-			req128_c = 0;
+			req128_l = true;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l / 2;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		}
@@ -280,9 +280,9 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes)
-			req128_l = 0;
+			req128_l = false;
 		else
-			req128_l = 1;
+			req128_l = true;
 
 		swath_bytes_l = total_swath_bytes;
 		swath_bytes_c = 0;
@@ -670,7 +670,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib,
 		const display_pipe_source_params_st pipe_src_param,
 		bool is_chroma)
 {
-	bool mode_422 = 0;
+	bool mode_422 = false;
 	unsigned int vp_width = 0;
 	unsigned int vp_height = 0;
 	unsigned int data_pitch = 0;
@@ -929,8 +929,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	min_dst_y_ttu_vblank = min_ttu_vblank * pclk_freq_in_mhz / (double) htotal;
 	dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start;
 
-	disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start
-			+ min_dst_y_ttu_vblank) * dml_pow(2, 2));
+	disp_dlg_regs->min_dst_y_next_start = (unsigned int) ((double) dlg_vblank_start * dml_pow(2, 2));
 	ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int) dml_pow(2, 18));
 
 	dml_print("DML_DLG: %s: min_dcfclk_mhz                         = %3.2f\n",
@@ -959,7 +958,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	// Source
 //             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class)(src->source_format));
-	mode_422 = 0; // TODO
+	mode_422 = false; // TODO
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
index 1e6aeb1bd2bf..287b7a0ad108 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
@@ -107,10 +107,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
-	bool ret_val = 0;
+	bool ret_val = false;
 
 	if ((source_format == dm_420_8) || (source_format == dm_420_10))
-		ret_val = 1;
+		ret_val = true;
 
 	return ret_val;
 }
@@ -240,8 +240,8 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 	unsigned int swath_bytes_c = 0;
 	unsigned int full_swath_bytes_packed_l = 0;
 	unsigned int full_swath_bytes_packed_c = 0;
-	bool req128_l = 0;
-	bool req128_c = 0;
+	bool req128_l = false;
+	bool req128_c = false;
 	bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear);
 	bool surf_vert = (pipe_src_param.source_scan == dm_vert);
 	unsigned int log2_swath_height_l = 0;
@@ -264,13 +264,13 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request
-			req128_l = 0;
-			req128_c = 0;
+			req128_l = false;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		} else { //128b request (for luma only for yuv420 8bpc)
-			req128_l = 1;
-			req128_c = 0;
+			req128_l = true;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l / 2;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		}
@@ -280,9 +280,9 @@ static void handle_det_buf_split(struct display_mode_lib *mode_lib,
 		total_swath_bytes = 2 * full_swath_bytes_packed_l;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes)
-			req128_l = 0;
+			req128_l = false;
 		else
-			req128_l = 1;
+			req128_l = true;
 
 		swath_bytes_l = total_swath_bytes;
 		swath_bytes_c = 0;
@@ -670,7 +670,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib,
 		const display_pipe_source_params_st pipe_src_param,
 		bool is_chroma)
 {
-	bool mode_422 = 0;
+	bool mode_422 = false;
 	unsigned int vp_width = 0;
 	unsigned int vp_height = 0;
 	unsigned int data_pitch = 0;
@@ -959,7 +959,7 @@ static void dml20v2_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	// Source
 //             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class)(src->source_format));
-	mode_422 = 0; // TODO
+	mode_422 = false; // TODO
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index ba77957aefe3..af35b3bea909 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #include "../display_mode_lib.h"
 #include "../dml_inline_defs.h"
@@ -198,7 +197,7 @@ static unsigned int CalculateVMAndRowBytes(
 		unsigned int *meta_row_width,
 		unsigned int *meta_row_height,
 		unsigned int *vm_group_bytes,
-		long         *dpte_group_bytes,
+		unsigned int *dpte_group_bytes,
 		unsigned int *PixelPTEReqWidth,
 		unsigned int *PixelPTEReqHeight,
 		unsigned int *PTERequestSize,
@@ -296,7 +295,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		double UrgentOutOfOrderReturn,
 		double ReturnBW,
 		bool GPUVMEnable,
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
@@ -310,13 +309,13 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		int DPPPerPlane[],
 		bool DCCEnable[],
 		double DPPCLK[],
-		unsigned int SwathWidthSingleDPPY[],
+		double SwathWidthSingleDPPY[],
 		unsigned int SwathHeightY[],
 		double ReadBandwidthPlaneLuma[],
 		unsigned int SwathHeightC[],
 		double ReadBandwidthPlaneChroma[],
 		unsigned int LBBitPerPixel[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		double HRatio[],
 		unsigned int vtaps[],
 		unsigned int VTAPsChroma[],
@@ -345,7 +344,7 @@ static void CalculateDCFCLKDeepSleep(
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
 		double VRatio[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		int DPPPerPlane[],
 		double HRatio[],
 		double PixelClock[],
@@ -436,7 +435,7 @@ static void CalculateMetaAndPTETimes(
 		unsigned int           meta_row_height[],
 		unsigned int           meta_req_width[],
 		unsigned int           meta_req_height[],
-		long                   dpte_group_bytes[],
+		int                   dpte_group_bytes[],
 		unsigned int           PTERequestSizeY[],
 		unsigned int           PTERequestSizeC[],
 		unsigned int           PixelPTEReqWidthY[],
@@ -478,7 +477,7 @@ static double CalculateExtraLatency(
 		bool HostVMEnable,
 		int NumberOfActivePlanes,
 		int NumberOfDPP[],
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
 		int HostVMMaxPageTableLevels,
@@ -1281,7 +1280,7 @@ static unsigned int CalculateVMAndRowBytes(
 		unsigned int *meta_row_width,
 		unsigned int *meta_row_height,
 		unsigned int *vm_group_bytes,
-		long         *dpte_group_bytes,
+		unsigned int *dpte_group_bytes,
 		unsigned int *PixelPTEReqWidth,
 		unsigned int *PixelPTEReqHeight,
 		unsigned int *PTERequestSize,
@@ -1339,7 +1338,7 @@ static unsigned int CalculateVMAndRowBytes(
 		*MetaRowByte = 0;
 	}
 
-	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_lvp) {
+	if (SurfaceTiling == dm_sw_linear || SurfaceTiling == dm_sw_gfx7_2d_thin_gl || SurfaceTiling == dm_sw_gfx7_2d_thin_l_vp) {
 		MacroTileSizeBytes = 256;
 		MacroTileHeight = BlockHeight256Bytes;
 	} else if (SurfaceTiling == dm_sw_4kb_s || SurfaceTiling == dm_sw_4kb_s_x
@@ -1684,11 +1683,11 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 		else
 			locals->SwathWidthSingleDPPY[k] = mode_lib->vba.ViewportHeight[k];
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true)
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 			MainPlaneDoesODMCombine = true;
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j)
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true)
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1)
 				MainPlaneDoesODMCombine = true;
 
 		if (MainPlaneDoesODMCombine == true)
@@ -2941,12 +2940,12 @@ static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib)
 			SwathWidth = mode_lib->vba.ViewportHeight[k];
 		}
 
-		if (mode_lib->vba.ODMCombineEnabled[k] == true) {
+		if (mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 			MainPlaneDoesODMCombine = true;
 		}
 		for (j = 0; j < mode_lib->vba.NumberOfActivePlanes; ++j) {
 			if (mode_lib->vba.BlendingAndTiming[k] == j
-					&& mode_lib->vba.ODMCombineEnabled[j] == true) {
+					&& mode_lib->vba.ODMCombineEnabled[k] == dm_odm_combine_mode_2to1) {
 				MainPlaneDoesODMCombine = true;
 			}
 		}
@@ -3454,7 +3453,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 										== dm_420_10))
 				|| (((mode_lib->vba.SurfaceTiling[k] == dm_sw_gfx7_2d_thin_gl
 						|| mode_lib->vba.SurfaceTiling[k]
-								== dm_sw_gfx7_2d_thin_lvp)
+								== dm_sw_gfx7_2d_thin_l_vp)
 						&& !((mode_lib->vba.SourcePixelFormat[k]
 								== dm_444_64
 								|| mode_lib->vba.SourcePixelFormat[k]
@@ -3543,17 +3542,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 		}
 	}
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->IdealSDPPortBandwidthPerState[i] = dml_min3(
+		locals->IdealSDPPortBandwidthPerState[i][0] = dml_min3(
 				mode_lib->vba.ReturnBusWidth * mode_lib->vba.DCFCLKPerState[i],
 				mode_lib->vba.DRAMSpeedPerState[i] * mode_lib->vba.NumberOfChannels
 						* mode_lib->vba.DRAMChannelWidth,
 				mode_lib->vba.FabricClockPerState[i]
 						* mode_lib->vba.FabricDatapathToDCNDataReturn);
 		if (mode_lib->vba.HostVMEnable == false) {
-			locals->ReturnBWPerState[i] = locals->IdealSDPPortBandwidthPerState[i]
+			locals->ReturnBWPerState[i][0] = locals->IdealSDPPortBandwidthPerState[i][0]
 					* mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelDataOnly / 100.0;
 		} else {
-			locals->ReturnBWPerState[i] = locals->IdealSDPPortBandwidthPerState[i]
+			locals->ReturnBWPerState[i][0] = locals->IdealSDPPortBandwidthPerState[i][0]
 					* mode_lib->vba.PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData / 100.0;
 		}
 	}
@@ -3590,12 +3589,12 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				+ dml_max3(mode_lib->vba.UrgentOutOfOrderReturnPerChannelPixelDataOnly,
 						mode_lib->vba.UrgentOutOfOrderReturnPerChannelPixelMixedWithVMData,
 						mode_lib->vba.UrgentOutOfOrderReturnPerChannelVMDataOnly)
-					* mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i];
-		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i]
+					* mode_lib->vba.NumberOfChannels / locals->ReturnBWPerState[i][0];
+		if ((mode_lib->vba.ROBBufferSizeInKByte - mode_lib->vba.PixelChunkSizeInKByte) * 1024.0 / locals->ReturnBWPerState[i][0]
 				> locals->UrgentRoundTripAndOutOfOrderLatencyPerState[i]) {
-			locals->ROBSupport[i] = true;
+			locals->ROBSupport[i][0] = true;
 		} else {
-			locals->ROBSupport[i] = false;
+			locals->ROBSupport[i][0] = false;
 		}
 	}
 	/*Writeback Mode Support Check*/
@@ -3983,7 +3982,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				if (locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) <= mode_lib->vba.MaxDppclkRoundedDownToDFSGranularity
 						&& locals->SwathWidthYSingleDPP[k] <= locals->MaximumSwathWidth[k]
-						&& locals->ODMCombineEnablePerState[i][k] == false) {
+						&& locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->NoOfDPP[i][j][k] = 1;
 					locals->RequiredDPPCLK[i][j][k] =
 						locals->MinDPPCLKUsingSingleDPP[k] * (1.0 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
@@ -4072,16 +4071,16 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	/*Viewport Size Check*/
 
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
-		locals->ViewportSizeSupport[i] = true;
+		locals->ViewportSizeSupport[i][0] = true;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			if (locals->ODMCombineEnablePerState[i][k] == true) {
+			if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 				if (dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]))
 						> locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			} else {
 				if (locals->SwathWidthYSingleDPP[k] / 2.0 > locals->MaximumSwathWidth[k]) {
-					locals->ViewportSizeSupport[i] = false;
+					locals->ViewportSizeSupport[i][0] = false;
 				}
 			}
 		}
@@ -4122,11 +4121,11 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	}
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-			locals->RequiresDSC[i][k] = 0;
+			locals->RequiresDSC[i][k] = false;
 			locals->RequiresFEC[i][k] = 0;
 			if (mode_lib->vba.BlendingAndTiming[k] == k) {
 				if (mode_lib->vba.Output[k] == dm_hdmi) {
-					locals->RequiresDSC[i][k] = 0;
+					locals->RequiresDSC[i][k] = false;
 					locals->RequiresFEC[i][k] = 0;
 					locals->OutputBppPerState[i][k] = TruncToValidBPP(
 							dml_min(600.0, mode_lib->vba.PHYCLKPerState[i]) / mode_lib->vba.PixelClockBackEnd[k] * 24,
@@ -4270,8 +4269,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						mode_lib->vba.DSCFormatFactor = 1;
 					}
 					if (locals->RequiresDSC[i][k] == true) {
-						if (locals->ODMCombineEnablePerState[i][k]
-								== true) {
+						if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 							if (mode_lib->vba.PixelClockBackEnd[k] / 6.0 / mode_lib->vba.DSCFormatFactor
 									> (1.0 - mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0) * mode_lib->vba.MaxDSCCLK[i]) {
 								locals->DSCCLKRequiredMoreThanSupported[i] =
@@ -4294,7 +4292,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 		mode_lib->vba.TotalDSCUnitsRequired = 0.0;
 		for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 			if (locals->RequiresDSC[i][k] == true) {
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					mode_lib->vba.TotalDSCUnitsRequired =
 							mode_lib->vba.TotalDSCUnitsRequired + 2.0;
 				} else {
@@ -4336,7 +4334,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.bpp = locals->OutputBppPerState[i][k];
 			}
 			if (locals->RequiresDSC[i][k] == true && mode_lib->vba.bpp != 0.0) {
-				if (locals->ODMCombineEnablePerState[i][k] == false) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_disabled) {
 					locals->DSCDelayPerState[i][k] =
 							dscceComputeDelay(
 									mode_lib->vba.DSCInputBitPerComponent[k],
@@ -4400,7 +4398,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				locals->RequiredDPPCLKThisState[k] = locals->RequiredDPPCLK[i][j][k];
 				locals->NoOfDPPThisState[k]        = locals->NoOfDPP[i][j][k];
-				if (locals->ODMCombineEnablePerState[i][k] == true) {
+				if (locals->ODMCombineEnablePerState[i][k] == dm_odm_combine_mode_2to1) {
 					locals->SwathWidthYThisState[k] =
 						dml_min(locals->SwathWidthYSingleDPP[k], dml_round(mode_lib->vba.HActive[k] / 2.0 * mode_lib->vba.HRatio[k]));
 				} else {
@@ -4452,7 +4450,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					locals->PSCL_FACTOR,
 					locals->PSCL_FACTOR_CHROMA,
 					locals->RequiredDPPCLKThisState,
-					&mode_lib->vba.ProjectedDCFCLKDeepSleep);
+					&mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0]);
 
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if ((mode_lib->vba.SourcePixelFormat[k] != dm_444_64
@@ -4497,7 +4495,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							locals->PTERequestSizeC,
 							locals->dpde0_bytes_per_frame_ub_c,
 							locals->meta_pte_bytes_per_frame_ub_c);
-					locals->PrefetchLinesC[k] = CalculatePrefetchSourceLines(
+					locals->PrefetchLinesC[0][0][k] = CalculatePrefetchSourceLines(
 							mode_lib,
 							mode_lib->vba.VRatio[k]/2,
 							mode_lib->vba.VTAPsChroma[k],
@@ -4512,7 +4510,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.PDEAndMetaPTEBytesPerFrameC = 0.0;
 					mode_lib->vba.MetaRowBytesC = 0.0;
 					mode_lib->vba.DPTEBytesPerRowC = 0.0;
-					locals->PrefetchLinesC[k] = 0.0;
+					locals->PrefetchLinesC[0][0][k] = 0.0;
 					locals->PTEBufferSizeNotExceededC[i][j][k] = true;
 					locals->PTEBufferSizeInRequestsForLuma = mode_lib->vba.PTEBufferSizeInRequestsLuma + mode_lib->vba.PTEBufferSizeInRequestsChroma;
 				}
@@ -4553,7 +4551,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						locals->PTERequestSizeY,
 						locals->dpde0_bytes_per_frame_ub_l,
 						locals->meta_pte_bytes_per_frame_ub_l);
-				locals->PrefetchLinesY[k] = CalculatePrefetchSourceLines(
+				locals->PrefetchLinesY[0][0][k] = CalculatePrefetchSourceLines(
 						mode_lib,
 						mode_lib->vba.VRatio[k],
 						mode_lib->vba.vtaps[k],
@@ -4563,10 +4561,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						mode_lib->vba.ViewportYStartY[k],
 						&locals->PrefillY[k],
 						&locals->MaxNumSwY[k]);
-				locals->PDEAndMetaPTEBytesPerFrame[k] =
+				locals->PDEAndMetaPTEBytesPerFrame[0][0][k] =
 						mode_lib->vba.PDEAndMetaPTEBytesPerFrameY + mode_lib->vba.PDEAndMetaPTEBytesPerFrameC;
-				locals->MetaRowBytes[k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
-				locals->DPTEBytesPerRow[k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
+				locals->MetaRowBytes[0][0][k] = mode_lib->vba.MetaRowBytesY + mode_lib->vba.MetaRowBytesC;
+				locals->DPTEBytesPerRow[0][0][k] = mode_lib->vba.DPTEBytesPerRowY + mode_lib->vba.DPTEBytesPerRowC;
 
 				CalculateActiveRowBandwidth(
 						mode_lib->vba.GPUVMEnable,
@@ -4592,7 +4590,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.PixelChunkSizeInKByte,
 					locals->TotalNumberOfDCCActiveDPP[i][j],
 					mode_lib->vba.MetaChunkSize,
-					locals->ReturnBWPerState[i],
+					locals->ReturnBWPerState[i][0],
 					mode_lib->vba.GPUVMEnable,
 					mode_lib->vba.HostVMEnable,
 					mode_lib->vba.NumberOfActivePlanes,
@@ -4603,7 +4601,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.HostVMMaxPageTableLevels,
 					mode_lib->vba.HostVMCachedPageTableLevels);
 
-			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep;
+			mode_lib->vba.TimeCalc = 24.0 / mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 				if (mode_lib->vba.BlendingAndTiming[k] == k) {
 					if (mode_lib->vba.WritebackEnable[k] == true) {
@@ -4645,15 +4643,15 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					}
 				}
 			}
-			mode_lib->vba.MaxMaxVStartup = 0;
+			mode_lib->vba.MaxMaxVStartup[0][0] = 0;
 			for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-				locals->MaximumVStartup[k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
+				locals->MaximumVStartup[0][0][k] = mode_lib->vba.VTotal[k] - mode_lib->vba.VActive[k]
 					- dml_max(1.0, dml_ceil(locals->WritebackDelay[i][k] / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]), 1.0));
-				mode_lib->vba.MaxMaxVStartup = dml_max(mode_lib->vba.MaxMaxVStartup, locals->MaximumVStartup[k]);
+				mode_lib->vba.MaxMaxVStartup[0][0] = dml_max(mode_lib->vba.MaxMaxVStartup[0][0], locals->MaximumVStartup[0][0][k]);
 			}
 
 			mode_lib->vba.NextPrefetchMode = mode_lib->vba.MinPrefetchMode;
-			mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup;
+			mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup[0][0];
 			do {
 				mode_lib->vba.PrefetchMode[i][j] = mode_lib->vba.NextPrefetchMode;
 				mode_lib->vba.MaxVStartup = mode_lib->vba.NextMaxVStartup;
@@ -4694,7 +4692,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					myPipe.DPPCLK = locals->RequiredDPPCLK[i][j][k];
 					myPipe.DISPCLK = locals->RequiredDISPCLK[i][j];
 					myPipe.PixelClock = mode_lib->vba.PixelClock[k];
-					myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep;
+					myPipe.DCFCLKDeepSleep = mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0];
 					myPipe.DPPPerPlane = locals->NoOfDPP[i][j][k];
 					myPipe.ScalerEnabled = mode_lib->vba.ScalerEnabled[k];
 					myPipe.SourceScan = mode_lib->vba.SourceScan[k];
@@ -4728,8 +4726,8 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							locals->SwathWidthYThisState[k] / mode_lib->vba.HRatio[k],
 							mode_lib->vba.OutputFormat[k],
 							mode_lib->vba.MaxInterDCNTileRepeaters,
-							dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[k]),
-							locals->MaximumVStartup[k],
+							dml_min(mode_lib->vba.MaxVStartup, locals->MaximumVStartup[0][0][k]),
+							locals->MaximumVStartup[0][0][k],
 							mode_lib->vba.GPUVMMaxPageTableLevels,
 							mode_lib->vba.GPUVMEnable,
 							&myHostVM,
@@ -4740,15 +4738,15 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							mode_lib->vba.UrgentLatency,
 							mode_lib->vba.ExtraLatency,
 							mode_lib->vba.TimeCalc,
-							locals->PDEAndMetaPTEBytesPerFrame[k],
-							locals->MetaRowBytes[k],
-							locals->DPTEBytesPerRow[k],
-							locals->PrefetchLinesY[k],
+							locals->PDEAndMetaPTEBytesPerFrame[0][0][k],
+							locals->MetaRowBytes[0][0][k],
+							locals->DPTEBytesPerRow[0][0][k],
+							locals->PrefetchLinesY[0][0][k],
 							locals->SwathWidthYThisState[k],
 							locals->BytePerPixelInDETY[k],
 							locals->PrefillY[k],
 							locals->MaxNumSwY[k],
-							locals->PrefetchLinesC[k],
+							locals->PrefetchLinesC[0][0][k],
 							locals->BytePerPixelInDETC[k],
 							locals->PrefillC[k],
 							locals->MaxNumSwC[k],
@@ -4837,14 +4835,14 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						+ locals->RequiredPrefetchPixelDataBWChroma[i][j][k] * locals->UrgentBurstFactorChromaPre[k]
 						+ locals->cursor_bw_pre[k] * locals->UrgentBurstFactorCursorPre[k]);
 				}
-				locals->BandwidthWithoutPrefetchSupported[i] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i]
+				locals->BandwidthWithoutPrefetchSupported[i][0] = true;
+				if (mode_lib->vba.MaximumReadBandwidthWithoutPrefetch > locals->ReturnBWPerState[i][0]
 						|| locals->NotEnoughUrgentLatencyHiding == 1) {
-					locals->BandwidthWithoutPrefetchSupported[i] = false;
+					locals->BandwidthWithoutPrefetchSupported[i][0] = false;
 				}
 
 				locals->PrefetchSupported[i][j] = true;
-				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i]
+				if (mode_lib->vba.MaximumReadBandwidthWithPrefetch > locals->ReturnBWPerState[i][0]
 						|| locals->NotEnoughUrgentLatencyHiding == 1
 						|| locals->NotEnoughUrgentLatencyHidingPre == 1) {
 					locals->PrefetchSupported[i][j] = false;
@@ -4873,17 +4871,17 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 
 				if (mode_lib->vba.MaxVStartup <= 13 || mode_lib->vba.AnyLinesForVMOrRowTooLarge == false) {
-					mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup;
+					mode_lib->vba.NextMaxVStartup = mode_lib->vba.MaxMaxVStartup[0][0];
 					mode_lib->vba.NextPrefetchMode = mode_lib->vba.NextPrefetchMode + 1;
 				} else {
 					mode_lib->vba.NextMaxVStartup = mode_lib->vba.NextMaxVStartup - 1;
 				}
 			} while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true)
-					&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup
+					&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0]
 						|| mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode));
 
 			if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) {
-				mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i];
+				mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0];
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.BandwidthAvailableForImmediateFlip = mode_lib->vba.BandwidthAvailableForImmediateFlip
 						- dml_max(locals->ReadBandwidthLuma[k] * locals->UrgentBurstFactorLuma[k]
@@ -4896,7 +4894,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.TotImmediateFlipBytes = 0.0;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 					mode_lib->vba.TotImmediateFlipBytes = mode_lib->vba.TotImmediateFlipBytes
-						+ locals->PDEAndMetaPTEBytesPerFrame[k] + locals->MetaRowBytes[k] + locals->DPTEBytesPerRow[k];
+						+ locals->PDEAndMetaPTEBytesPerFrame[0][0][k] + locals->MetaRowBytes[0][0][k] + locals->DPTEBytesPerRow[0][0][k];
 				}
 
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4911,9 +4909,9 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							mode_lib->vba.HostVMMaxPageTableLevels,
 							mode_lib->vba.HostVMCachedPageTableLevels,
 							mode_lib->vba.GPUVMEnable,
-							locals->PDEAndMetaPTEBytesPerFrame[k],
-							locals->MetaRowBytes[k],
-							locals->DPTEBytesPerRow[k],
+							locals->PDEAndMetaPTEBytesPerFrame[0][0][k],
+							locals->MetaRowBytes[0][0][k],
+							locals->DPTEBytesPerRow[0][0][k],
 							mode_lib->vba.BandwidthAvailableForImmediateFlip,
 							mode_lib->vba.TotImmediateFlipBytes,
 							mode_lib->vba.SourcePixelFormat[k],
@@ -4944,7 +4942,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				}
 				locals->ImmediateFlipSupportedForState[i][j] = true;
 				if (mode_lib->vba.total_dcn_read_bw_with_flip
-						> locals->ReturnBWPerState[i]) {
+						> locals->ReturnBWPerState[i][0]) {
 					locals->ImmediateFlipSupportedForState[i][j] = false;
 				}
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
@@ -4971,7 +4969,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.WritebackInterfaceChromaBufferSize,
 					mode_lib->vba.DCFCLKPerState[i],
 					mode_lib->vba.UrgentOutOfOrderReturnPerChannel * mode_lib->vba.NumberOfChannels,
-					locals->ReturnBWPerState[i],
+					locals->ReturnBWPerState[i][0],
 					mode_lib->vba.GPUVMEnable,
 					locals->dpte_group_bytes,
 					mode_lib->vba.MetaChunkSize,
@@ -4983,7 +4981,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 					mode_lib->vba.DRAMClockChangeLatency,
 					mode_lib->vba.SRExitTime,
 					mode_lib->vba.SREnterPlusExitTime,
-					mode_lib->vba.ProjectedDCFCLKDeepSleep,
+					mode_lib->vba.ProjectedDCFCLKDeepSleep[0][0],
 					locals->NoOfDPPThisState,
 					mode_lib->vba.DCCEnable,
 					locals->RequiredDPPCLKThisState,
@@ -5026,8 +5024,8 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				MaxTotalVActiveRDBandwidth = MaxTotalVActiveRDBandwidth + locals->ReadBandwidth[k];
 		}
 		for (i = 0; i <= mode_lib->vba.soc.num_states; ++i) {
-			locals->MaxTotalVerticalActiveAvailableBandwidth[i] = dml_min(
-				locals->IdealSDPPortBandwidthPerState[i] *
+			locals->MaxTotalVerticalActiveAvailableBandwidth[i][0] = dml_min(
+				locals->IdealSDPPortBandwidthPerState[i][0] *
 				mode_lib->vba.MaxAveragePercentOfIdealSDPPortBWDisplayCanUseInNormalSystemOperation
 				/ 100.0, mode_lib->vba.DRAMSpeedPerState[i] *
 				mode_lib->vba.NumberOfChannels *
@@ -5035,10 +5033,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.MaxAveragePercentOfIdealDRAMBWDisplayCanUseInNormalSystemOperation
 				/ 100.0);
 
-			if (MaxTotalVActiveRDBandwidth <= locals->MaxTotalVerticalActiveAvailableBandwidth[i]) {
-				locals->TotalVerticalActiveBandwidthSupport[i] = true;
+			if (MaxTotalVActiveRDBandwidth <= locals->MaxTotalVerticalActiveAvailableBandwidth[i][0]) {
+				locals->TotalVerticalActiveBandwidthSupport[i][0] = true;
 			} else {
-				locals->TotalVerticalActiveBandwidthSupport[i] = false;
+				locals->TotalVerticalActiveBandwidthSupport[i][0] = false;
 			}
 		}
 	}
@@ -5117,7 +5115,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_SCALE_RATIO_TAP;
 			} else if (mode_lib->vba.SourceFormatPixelAndScanSupport != true) {
 				status = DML_FAIL_SOURCE_PIXEL_FORMAT;
-			} else if (locals->ViewportSizeSupport[i] != true) {
+			} else if (locals->ViewportSizeSupport[i][0] != true) {
 				status = DML_FAIL_VIEWPORT_SIZE;
 			} else if (locals->DIOSupport[i] != true) {
 				status = DML_FAIL_DIO_SUPPORT;
@@ -5125,7 +5123,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_NOT_ENOUGH_DSC;
 			} else if (locals->DSCCLKRequiredMoreThanSupported[i] != false) {
 				status = DML_FAIL_DSC_CLK_REQUIRED;
-			} else if (locals->ROBSupport[i] != true) {
+			} else if (locals->ROBSupport[i][0] != true) {
 				status = DML_FAIL_REORDERING_BUFFER;
 			} else if (locals->DISPCLK_DPPCLK_Support[i][j] != true) {
 				status = DML_FAIL_DISPCLK_DPPCLK;
@@ -5143,7 +5141,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				status = DML_FAIL_CURSOR_SUPPORT;
 			} else if (mode_lib->vba.PitchSupport != true) {
 				status = DML_FAIL_PITCH_SUPPORT;
-			} else if (locals->TotalVerticalActiveBandwidthSupport[i] != true) {
+			} else if (locals->TotalVerticalActiveBandwidthSupport[i][0] != true) {
 				status = DML_FAIL_TOTAL_V_ACTIVE_BW;
 			} else if (locals->PTEBufferSizeNotExceeded[i][j] != true) {
 				status = DML_FAIL_PTE_BUFFER_SIZE;
@@ -5199,13 +5197,13 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 	mode_lib->vba.DRAMSpeed = mode_lib->vba.DRAMSpeedPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.FabricClock = mode_lib->vba.FabricClockPerState[mode_lib->vba.VoltageLevel];
 	mode_lib->vba.SOCCLK = mode_lib->vba.SOCCLKPerState[mode_lib->vba.VoltageLevel];
-	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = locals->ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
 		if (mode_lib->vba.BlendingAndTiming[k] == k) {
 			mode_lib->vba.ODMCombineEnabled[k] =
 					locals->ODMCombineEnablePerState[mode_lib->vba.VoltageLevel][k];
 		} else {
-			mode_lib->vba.ODMCombineEnabled[k] = 0;
+			mode_lib->vba.ODMCombineEnabled[k] = false;
 		}
 		mode_lib->vba.DSCEnabled[k] =
 				locals->RequiresDSC[mode_lib->vba.VoltageLevel][k];
@@ -5228,7 +5226,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		double UrgentOutOfOrderReturn,
 		double ReturnBW,
 		bool GPUVMEnable,
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		unsigned int MetaChunkSize,
 		double UrgentLatency,
 		double ExtraLatency,
@@ -5242,13 +5240,13 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 		int DPPPerPlane[],
 		bool DCCEnable[],
 		double DPPCLK[],
-		unsigned int SwathWidthSingleDPPY[],
+		double SwathWidthSingleDPPY[],
 		unsigned int SwathHeightY[],
 		double ReadBandwidthPlaneLuma[],
 		unsigned int SwathHeightC[],
 		double ReadBandwidthPlaneChroma[],
 		unsigned int LBBitPerPixel[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		double HRatio[],
 		unsigned int vtaps[],
 		unsigned int VTAPsChroma[],
@@ -5504,7 +5502,7 @@ static void CalculateDCFCLKDeepSleep(
 		double BytePerPixelDETY[],
 		double BytePerPixelDETC[],
 		double VRatio[],
-		unsigned int SwathWidthY[],
+		double SwathWidthY[],
 		int DPPPerPlane[],
 		double HRatio[],
 		double PixelClock[],
@@ -5832,7 +5830,7 @@ static void CalculateMetaAndPTETimes(
 		unsigned int meta_row_height[],
 		unsigned int meta_req_width[],
 		unsigned int meta_req_height[],
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		unsigned int PTERequestSizeY[],
 		unsigned int PTERequestSizeC[],
 		unsigned int PixelPTEReqWidthY[],
@@ -6088,7 +6086,7 @@ static double CalculateExtraLatency(
 		bool HostVMEnable,
 		int NumberOfActivePlanes,
 		int NumberOfDPP[],
-		long dpte_group_bytes[],
+		int dpte_group_bytes[],
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyPixelMixedWithVMData,
 		double PercentOfIdealDRAMFabricAndSDPPortBWReceivedAfterUrgLatencyVMDataOnly,
 		int HostVMMaxPageTableLevels,
@@ -6126,4 +6124,3 @@ static double CalculateExtraLatency(
 	return CalculateExtraLatency;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
index a1f207cbb966..a38baa73d484 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #include "../display_mode_lib.h"
 #include "../display_mode_vba.h"
@@ -83,10 +82,10 @@ static unsigned int get_bytes_per_element(enum source_format_class source_format
 
 static bool is_dual_plane(enum source_format_class source_format)
 {
-	bool ret_val = 0;
+	bool ret_val = false;
 
 	if ((source_format == dm_420_8) || (source_format == dm_420_10))
-		ret_val = 1;
+		ret_val = true;
 
 	return ret_val;
 }
@@ -223,8 +222,8 @@ static void handle_det_buf_split(
 	unsigned int swath_bytes_c = 0;
 	unsigned int full_swath_bytes_packed_l = 0;
 	unsigned int full_swath_bytes_packed_c = 0;
-	bool req128_l = 0;
-	bool req128_c = 0;
+	bool req128_l = false;
+	bool req128_c = false;
 	bool surf_linear = (pipe_src_param.sw_mode == dm_sw_linear);
 	bool surf_vert = (pipe_src_param.source_scan == dm_vert);
 	unsigned int log2_swath_height_l = 0;
@@ -249,13 +248,13 @@ static void handle_det_buf_split(
 		total_swath_bytes = 2 * full_swath_bytes_packed_l + 2 * full_swath_bytes_packed_c;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes) { //full 256b request
-			req128_l = 0;
-			req128_c = 0;
+			req128_l = false;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		} else { //128b request (for luma only for yuv420 8bpc)
-			req128_l = 1;
-			req128_c = 0;
+			req128_l = true;
+			req128_c = false;
 			swath_bytes_l = full_swath_bytes_packed_l / 2;
 			swath_bytes_c = full_swath_bytes_packed_c;
 		}
@@ -265,9 +264,9 @@ static void handle_det_buf_split(
 		total_swath_bytes = 2 * full_swath_bytes_packed_l;
 
 		if (total_swath_bytes <= detile_buf_size_in_bytes)
-			req128_l = 0;
+			req128_l = false;
 		else
-			req128_l = 1;
+			req128_l = true;
 
 		swath_bytes_l = total_swath_bytes;
 		swath_bytes_c = 0;
@@ -680,7 +679,7 @@ static void get_surf_rq_param(
 		const display_pipe_params_st pipe_param,
 		bool is_chroma)
 {
-	bool mode_422 = 0;
+	bool mode_422 = false;
 	unsigned int vp_width = 0;
 	unsigned int vp_height = 0;
 	unsigned int data_pitch = 0;
@@ -1011,7 +1010,7 @@ static void dml_rq_dlg_get_dlg_params(
 	// Source
 	//             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class) (src->source_format));
-	mode_422 = 0; // FIXME
+	mode_422 = false; // FIXME
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 						    //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 						    //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
@@ -1523,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params(
 
 	disp_dlg_regs->refcyc_per_vm_group_vblank   = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
 	disp_dlg_regs->refcyc_per_vm_group_flip     = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
-	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;;
-	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;;
+	disp_dlg_regs->refcyc_per_vm_req_vblank     = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
+	disp_dlg_regs->refcyc_per_vm_req_flip       = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz;
 
 	// Clamp to max for now
 	if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23))
@@ -1820,4 +1819,3 @@ static void calculate_ttu_cursor(
 	}
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
index 1c97083b8d0b..bfc2f39bd1ef 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_enums.h
@@ -85,7 +85,7 @@ enum dm_swizzle_mode {
 	dm_sw_var_s_x = 29,
 	dm_sw_var_d_x = 30,
 	dm_sw_64kb_r_x,
-	dm_sw_gfx7_2d_thin_lvp,
+	dm_sw_gfx7_2d_thin_l_vp,
 	dm_sw_gfx7_2d_thin_gl,
 };
 enum lb_depth {
@@ -119,6 +119,10 @@ enum mpc_combine_affinity {
 	dm_mpc_never
 };
 
+enum RequestType {
+	REQ_256Bytes, REQ_128BytesNonContiguous, REQ_128BytesContiguous, REQ_NA
+};
+
 enum self_refresh_affinity {
 	dm_try_to_allow_self_refresh_and_mclk_switch,
 	dm_allow_self_refresh_and_mclk_switch,
@@ -135,9 +139,7 @@ enum dm_validation_status {
 	DML_FAIL_DIO_SUPPORT,
 	DML_FAIL_NOT_ENOUGH_DSC,
 	DML_FAIL_DSC_CLK_REQUIRED,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	DML_FAIL_DSC_VALIDATION_FAILURE,
-#endif
 	DML_FAIL_URGENT_LATENCY,
 	DML_FAIL_REORDERING_BUFFER,
 	DML_FAIL_DISPCLK_DPPCLK,
@@ -167,4 +169,16 @@ enum odm_combine_mode {
 	dm_odm_combine_mode_4to1,
 };
 
+enum odm_combine_policy {
+	dm_odm_combine_policy_dal,
+	dm_odm_combine_policy_none,
+	dm_odm_combine_policy_2to1,
+	dm_odm_combine_policy_4to1,
+};
+
+enum immediate_flip_requirement {
+	dm_immediate_flip_not_required,
+	dm_immediate_flip_required,
+};
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index 704efefdcba8..2689401a03a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -25,18 +25,13 @@
 
 #include "display_mode_lib.h"
 #include "dc_features.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/display_mode_vba_20.h"
 #include "dcn20/display_rq_dlg_calc_20.h"
 #include "dcn20/display_mode_vba_20v2.h"
 #include "dcn20/display_rq_dlg_calc_20v2.h"
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 #include "dcn21/display_mode_vba_21.h"
 #include "dcn21/display_rq_dlg_calc_21.h"
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 const struct dml_funcs dml20_funcs = {
 	.validate = dml20_ModeSupportAndSystemConfigurationFull,
 	.recalculate = dml20_recalculate,
@@ -50,16 +45,13 @@ const struct dml_funcs dml20v2_funcs = {
 	.rq_dlg_get_dlg_reg = dml20v2_rq_dlg_get_dlg_reg,
 	.rq_dlg_get_rq_reg = dml20v2_rq_dlg_get_rq_reg
 };
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 const struct dml_funcs dml21_funcs = {
         .validate = dml21_ModeSupportAndSystemConfigurationFull,
         .recalculate = dml21_recalculate,
         .rq_dlg_get_dlg_reg = dml21_rq_dlg_get_dlg_reg,
         .rq_dlg_get_rq_reg = dml21_rq_dlg_get_rq_reg
 };
-#endif
 
 void dml_init_instance(struct display_mode_lib *lib,
 		const struct _vcs_dpi_soc_bounding_box_st *soc_bb,
@@ -70,19 +62,15 @@ void dml_init_instance(struct display_mode_lib *lib,
 	lib->ip = *ip_params;
 	lib->project = project;
 	switch (project) {
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	case DML_PROJECT_NAVI10:
 		lib->funcs = dml20_funcs;
 		break;
 	case DML_PROJECT_NAVI10v2:
 		lib->funcs = dml20v2_funcs;
 		break;
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
         case DML_PROJECT_DCN21:
                 lib->funcs = dml21_funcs;
                 break;
-#endif
 
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index d8c59aa356b6..cf2758ca5b02 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -27,20 +27,14 @@
 
 
 #include "dml_common_defs.h"
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #include "display_mode_vba.h"
-#endif
 
 enum dml_project {
 	DML_PROJECT_UNDEFINED,
 	DML_PROJECT_RAVEN1,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	DML_PROJECT_NAVI10,
 	DML_PROJECT_NAVI10v2,
-#endif
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	DML_PROJECT_DCN21,
-#endif
 };
 
 struct display_mode_lib;
@@ -70,9 +64,7 @@ struct display_mode_lib {
 	struct _vcs_dpi_ip_params_st ip;
 	struct _vcs_dpi_soc_bounding_box_st soc;
 	enum dml_project project;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct vba_vars_st vba;
-#endif
 	struct dal_logger *logger;
 	struct dml_funcs funcs;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index cfacd6027467..658f81e757e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -63,6 +63,7 @@ struct _vcs_dpi_voltage_scaling_st {
 	double dispclk_mhz;
 	double phyclk_mhz;
 	double dppclk_mhz;
+	double dtbclk_mhz;
 };
 
 struct _vcs_dpi_soc_bounding_box_st {
@@ -99,6 +100,7 @@ struct _vcs_dpi_soc_bounding_box_st {
 	unsigned int num_chans;
 	unsigned int vmm_page_size_bytes;
 	unsigned int hostvm_min_page_size_bytes;
+	unsigned int gpuvm_min_page_size_bytes;
 	double dram_clock_change_latency_us;
 	double dummy_pstate_latency_us;
 	double writeback_dram_clock_change_latency_us;
@@ -112,6 +114,7 @@ struct _vcs_dpi_soc_bounding_box_st {
 	bool do_urgent_latency_adjustment;
 	double urgent_latency_adjustment_fabric_clock_component_us;
 	double urgent_latency_adjustment_fabric_clock_reference_mhz;
+	bool disable_dram_clock_change_vactive_support;
 };
 
 struct _vcs_dpi_ip_params_st {
@@ -145,7 +148,6 @@ struct _vcs_dpi_ip_params_st {
 	unsigned int writeback_interface_buffer_size_kbytes;
 	unsigned int writeback_line_buffer_buffer_size;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	unsigned int writeback_10bpc420_supported;
 	double writeback_max_hscl_ratio;
 	double writeback_max_vscl_ratio;
@@ -155,7 +157,6 @@ struct _vcs_dpi_ip_params_st {
 	unsigned int writeback_max_vscl_taps;
 	unsigned int writeback_line_buffer_luma_buffer_size;
 	unsigned int writeback_line_buffer_chroma_buffer_size;
-#endif
 
 	unsigned int max_page_table_levels;
 	unsigned int max_num_dpp;
@@ -214,6 +215,7 @@ struct _vcs_dpi_display_pipe_source_params_st {
 	int source_format;
 	unsigned char dcc;
 	unsigned int dcc_rate;
+	unsigned int dcc_rate_chroma;
 	unsigned char dcc_use_global;
 	unsigned char vm;
 	bool gpuvm;    // gpuvm enabled
@@ -225,6 +227,10 @@ struct _vcs_dpi_display_pipe_source_params_st {
 	int source_scan;
 	int sw_mode;
 	int macro_tile_size;
+	unsigned int surface_width_y;
+	unsigned int surface_height_y;
+	unsigned int surface_width_c;
+	unsigned int surface_height_c;
 	unsigned int viewport_width;
 	unsigned int viewport_height;
 	unsigned int viewport_y_y;
@@ -277,6 +283,7 @@ struct _vcs_dpi_display_output_params_st {
 	int output_type;
 	int output_format;
 	int dsc_slices;
+	int max_audio_sample_rate;
 	struct writeback_st wb;
 };
 
@@ -322,7 +329,7 @@ struct _vcs_dpi_display_pipe_dest_params_st {
 	double pixel_rate_mhz;
 	unsigned char synchronized_vblank_all_planes;
 	unsigned char otg_inst;
-	unsigned char odm_combine;
+	unsigned int odm_combine;
 	unsigned char use_maximum_vstartup;
 	unsigned int vtotal_max;
 	unsigned int vtotal_min;
@@ -401,6 +408,7 @@ struct _vcs_dpi_display_rq_misc_params_st {
 struct _vcs_dpi_display_rq_params_st {
 	unsigned char yuv420;
 	unsigned char yuv420_10bpc;
+	unsigned char rgbe_alpha;
 	display_rq_misc_params_st misc;
 	display_rq_sizing_params_st sizing;
 	display_rq_dlg_params_st dlg;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index 7f9a5621922f..b3c96d9b472f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #include "display_mode_lib.h"
 #include "display_mode_vba.h"
@@ -222,13 +221,17 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib)
 	mode_lib->vba.SRExitTime = soc->sr_exit_time_us;
 	mode_lib->vba.SREnterPlusExitTime = soc->sr_enter_plus_exit_time_us;
 	mode_lib->vba.DRAMClockChangeLatency = soc->dram_clock_change_latency_us;
+	mode_lib->vba.DummyPStateCheck = soc->dram_clock_change_latency_us == soc->dummy_pstate_latency_us;
+	mode_lib->vba.DRAMClockChangeSupportsVActive = !soc->disable_dram_clock_change_vactive_support ||
+			mode_lib->vba.DummyPStateCheck;
+
 	mode_lib->vba.Downspreading = soc->downspread_percent;
 	mode_lib->vba.DRAMChannelWidth = soc->dram_channel_width_bytes;   // new!
 	mode_lib->vba.FabricDatapathToDCNDataReturn = soc->fabric_datapath_to_dcn_data_return_bytes; // new!
 	mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading = soc->dcn_downspread_percent;   // new
 	mode_lib->vba.DISPCLKDPPCLKVCOSpeed = soc->dispclk_dppclk_vco_speed_mhz;   // new
 	mode_lib->vba.VMMPageSize = soc->vmm_page_size_bytes;
-	mode_lib->vba.GPUVMMinPageSize = soc->vmm_page_size_bytes / 1024;
+	mode_lib->vba.GPUVMMinPageSize = soc->gpuvm_min_page_size_bytes / 1024;
 	mode_lib->vba.HostVMMinPageSize = soc->hostvm_min_page_size_bytes / 1024;
 	// Set the voltage scaling clocks as the defaults. Most of these will
 	// be set to different values by the test
@@ -261,7 +264,10 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib)
 		mode_lib->vba.DRAMSpeedPerState[i] = soc->clock_limits[i].dram_speed_mts;
 		//mode_lib->vba.DRAMSpeedPerState[i] = soc->clock_limits[i].dram_speed_mhz;
 		mode_lib->vba.MaxDispclk[i] = soc->clock_limits[i].dispclk_mhz;
+		mode_lib->vba.DTBCLKPerState[i] = soc->clock_limits[i].dtbclk_mhz;
 	}
+	mode_lib->vba.MinVoltageLevel = 0;
+	mode_lib->vba.MaxVoltageLevel = mode_lib->vba.soc.num_states;
 
 	mode_lib->vba.DoUrgentLatencyAdjustment =
 		soc->do_urgent_latency_adjustment;
@@ -303,8 +309,6 @@ static void fetch_ip_params(struct display_mode_lib *mode_lib)
 
 	mode_lib->vba.WritebackInterfaceBufferSize = ip->writeback_interface_buffer_size_kbytes;
 	mode_lib->vba.WritebackLineBufferSize = ip->writeback_line_buffer_buffer_size;
-	mode_lib->vba.MinVoltageLevel = 0;
-	mode_lib->vba.MaxVoltageLevel = 5;
 
 	mode_lib->vba.WritebackChromaLineBufferWidth =
 			ip->writeback_chroma_line_buffer_width_pixels;
@@ -420,8 +424,8 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 						ip->dcc_supported : src->dcc && ip->dcc_supported;
 		mode_lib->vba.DCCRate[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate;
 		/* TODO: Needs to be set based on src->dcc_rate_luma/chroma */
-		mode_lib->vba.DCCRateLuma[mode_lib->vba.NumberOfActivePlanes] = 0;
-		mode_lib->vba.DCCRateChroma[mode_lib->vba.NumberOfActivePlanes] = 0;
+		mode_lib->vba.DCCRateLuma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate;
+		mode_lib->vba.DCCRateChroma[mode_lib->vba.NumberOfActivePlanes] = src->dcc_rate_chroma;
 
 		mode_lib->vba.SourcePixelFormat[mode_lib->vba.NumberOfActivePlanes] =
 				(enum source_format_class) (src->source_format);
@@ -433,8 +437,6 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 				dst->recout_width; // TODO: or should this be full_recout_width???...maybe only when in hsplit mode?
 		mode_lib->vba.ODMCombineEnabled[mode_lib->vba.NumberOfActivePlanes] =
 				dst->odm_combine;
-		mode_lib->vba.ODMCombineTypeEnabled[mode_lib->vba.NumberOfActivePlanes] =
-				dst->odm_combine;
 		mode_lib->vba.OutputFormat[mode_lib->vba.NumberOfActivePlanes] =
 				(enum output_format_class) (dout->output_format);
 		mode_lib->vba.OutputBpp[mode_lib->vba.NumberOfActivePlanes] =
@@ -451,7 +453,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 				dout->dp_lanes;
 		/* TODO: Needs to be set based on dout->audio.audio_sample_rate_khz/sample_layout */
 		mode_lib->vba.AudioSampleRate[mode_lib->vba.NumberOfActivePlanes] =
-			44.1 * 1000;
+			dout->max_audio_sample_rate;
 		mode_lib->vba.AudioSampleLayout[mode_lib->vba.NumberOfActivePlanes] =
 			1;
 		mode_lib->vba.DRAMClockChangeLatencyOverride = 0.0;
@@ -587,6 +589,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 			for (k = j + 1; k < mode_lib->vba.cache_num_pipes; ++k) {
 				display_pipe_source_params_st *src_k = &pipes[k].pipe.src;
 				display_pipe_dest_params_st *dst_k = &pipes[k].pipe.dest;
+				display_output_params_st *dout_k = &pipes[j].dout;
 
 				if (src_k->is_hsplit && !visited[k]
 						&& src->hsplit_grp == src_k->hsplit_grp) {
@@ -597,12 +600,18 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 							== dm_horz) {
 						mode_lib->vba.ViewportWidth[mode_lib->vba.NumberOfActivePlanes] +=
 								src_k->viewport_width;
+						mode_lib->vba.ViewportWidthChroma[mode_lib->vba.NumberOfActivePlanes] +=
+								src_k->viewport_width;
 						mode_lib->vba.ScalerRecoutWidth[mode_lib->vba.NumberOfActivePlanes] +=
 								dst_k->recout_width;
 					} else {
 						mode_lib->vba.ViewportHeight[mode_lib->vba.NumberOfActivePlanes] +=
 								src_k->viewport_height;
+						mode_lib->vba.ViewportHeightChroma[mode_lib->vba.NumberOfActivePlanes] +=
+								src_k->viewport_height;
 					}
+					mode_lib->vba.NumberOfDSCSlices[mode_lib->vba.NumberOfActivePlanes] +=
+							dout_k->dsc_slices;
 
 					visited[k] = true;
 				}
@@ -808,7 +817,9 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib)
 	unsigned int total_pipes = 0;
 
 	mode_lib->vba.VoltageLevel = mode_lib->vba.cache_pipes[0].clks_cfg.voltage;
-	mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel];
+	mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb];
+	if (mode_lib->vba.ReturnBW == 0)
+		mode_lib->vba.ReturnBW = mode_lib->vba.ReturnBWPerState[mode_lib->vba.VoltageLevel][0];
 	mode_lib->vba.FabricAndDRAMBandwidth = mode_lib->vba.FabricAndDRAMBandwidthPerState[mode_lib->vba.VoltageLevel];
 
 	fetch_socbb_params(mode_lib);
@@ -858,4 +869,3 @@ double CalculateWriteBackDISPCLK(
 	return CalculateWriteBackDISPCLK;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 1540ffbe3979..e7a44df676ca 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -23,7 +23,6 @@
  *
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 
 #ifndef __DML2_DISPLAY_MODE_VBA_H__
 #define __DML2_DISPLAY_MODE_VBA_H__
@@ -155,7 +154,10 @@ struct vba_vars_st {
 	double UrgentLatencySupportUsChroma;
 	unsigned int DSCFormatFactor;
 
+	bool DummyPStateCheck;
+	bool DRAMClockChangeSupportsVActive;
 	bool PrefetchModeSupported;
+	bool PrefetchAndImmediateFlipSupported;
 	enum self_refresh_affinity AllowDRAMSelfRefreshOrDRAMClockChangeInVblank; // Mode Support only
 	double XFCRemoteSurfaceFlipDelay;
 	double TInitXFill;
@@ -317,8 +319,7 @@ struct vba_vars_st {
 	unsigned int DynamicMetadataTransmittedBytes[DC__NUM_DPP__MAX];
 	double DCCRate[DC__NUM_DPP__MAX];
 	double AverageDCCCompressionRate;
-	bool ODMCombineEnabled[DC__NUM_DPP__MAX];
-	enum odm_combine_mode ODMCombineTypeEnabled[DC__NUM_DPP__MAX];
+	enum odm_combine_mode ODMCombineEnabled[DC__NUM_DPP__MAX];
 	double OutputBpp[DC__NUM_DPP__MAX];
 	bool DSCEnabled[DC__NUM_DPP__MAX];
 	unsigned int DSCInputBitPerComponent[DC__NUM_DPP__MAX];
@@ -346,6 +347,7 @@ struct vba_vars_st {
 	unsigned int EffectiveLBLatencyHidingSourceLinesChroma;
 	double BandwidthAvailableForImmediateFlip;
 	unsigned int PrefetchMode[DC__VOLTAGE_STATES + 1][2];
+	unsigned int PrefetchModePerState[DC__VOLTAGE_STATES + 1][2];
 	unsigned int MinPrefetchMode;
 	unsigned int MaxPrefetchMode;
 	bool AnyLinesForVMOrRowTooLarge;
@@ -395,6 +397,7 @@ struct vba_vars_st {
 	bool WritebackLumaAndChromaScalingSupported;
 	bool Cursor64BppSupport;
 	double DCFCLKPerState[DC__VOLTAGE_STATES + 1];
+	double DCFCLKState[DC__VOLTAGE_STATES + 1][2];
 	double FabricClockPerState[DC__VOLTAGE_STATES + 1];
 	double SOCCLKPerState[DC__VOLTAGE_STATES + 1];
 	double PHYCLKPerState[DC__VOLTAGE_STATES + 1];
@@ -443,7 +446,7 @@ struct vba_vars_st {
 	double OutputLinkDPLanes[DC__NUM_DPP__MAX];
 	double ForcedOutputLinkBPP[DC__NUM_DPP__MAX]; // Mode Support only
 	double ImmediateFlipBW[DC__NUM_DPP__MAX];
-	double MaxMaxVStartup;
+	double MaxMaxVStartup[DC__VOLTAGE_STATES + 1][2];
 
 	double WritebackLumaVExtra;
 	double WritebackChromaVExtra;
@@ -470,7 +473,7 @@ struct vba_vars_st {
 	double RoundedUpMaxSwathSizeBytesC;
 	double EffectiveDETLBLinesLuma;
 	double EffectiveDETLBLinesChroma;
-	double ProjectedDCFCLKDeepSleep;
+	double ProjectedDCFCLKDeepSleep[DC__VOLTAGE_STATES + 1][2];
 	double PDEAndMetaPTEBytesPerFrameY;
 	double PDEAndMetaPTEBytesPerFrameC;
 	unsigned int MetaRowBytesY;
@@ -488,12 +491,11 @@ struct vba_vars_st {
 	double FractionOfUrgentBandwidthImmediateFlip; // Mode Support debugging output
 
 	/* ms locals */
-	double IdealSDPPortBandwidthPerState[DC__VOLTAGE_STATES + 1];
+	double IdealSDPPortBandwidthPerState[DC__VOLTAGE_STATES + 1][2];
 	unsigned int NoOfDPP[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	int NoOfDPPThisState[DC__NUM_DPP__MAX];
-	bool ODMCombineEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
-	enum odm_combine_mode ODMCombineTypeEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
-	unsigned int SwathWidthYThisState[DC__NUM_DPP__MAX];
+	enum odm_combine_mode ODMCombineEnablePerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
+	double SwathWidthYThisState[DC__NUM_DPP__MAX];
 	unsigned int SwathHeightCPerState[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	unsigned int SwathHeightYThisState[DC__NUM_DPP__MAX];
 	unsigned int SwathHeightCThisState[DC__NUM_DPP__MAX];
@@ -505,7 +507,7 @@ struct vba_vars_st {
 	double RequiredDPPCLKThisState[DC__NUM_DPP__MAX];
 	bool PTEBufferSizeNotExceededY[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	bool PTEBufferSizeNotExceededC[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
-	bool BandwidthWithoutPrefetchSupported[DC__VOLTAGE_STATES + 1];
+	bool BandwidthWithoutPrefetchSupported[DC__VOLTAGE_STATES + 1][2];
 	bool PrefetchSupported[DC__VOLTAGE_STATES + 1][2];
 	bool VRatioInPrefetchSupported[DC__VOLTAGE_STATES + 1][2];
 	double RequiredDISPCLK[DC__VOLTAGE_STATES + 1][2];
@@ -514,22 +516,22 @@ struct vba_vars_st {
 	unsigned int TotalNumberOfActiveDPP[DC__VOLTAGE_STATES + 1][2];
 	unsigned int TotalNumberOfDCCActiveDPP[DC__VOLTAGE_STATES + 1][2];
 	bool ModeSupport[DC__VOLTAGE_STATES + 1][2];
-	double ReturnBWPerState[DC__VOLTAGE_STATES + 1];
+	double ReturnBWPerState[DC__VOLTAGE_STATES + 1][2];
 	bool DIOSupport[DC__VOLTAGE_STATES + 1];
 	bool NotEnoughDSCUnits[DC__VOLTAGE_STATES + 1];
 	bool DSCCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES + 1];
 	bool DTBCLKRequiredMoreThanSupported[DC__VOLTAGE_STATES + 1];
 	double UrgentRoundTripAndOutOfOrderLatencyPerState[DC__VOLTAGE_STATES + 1];
-	bool ROBSupport[DC__VOLTAGE_STATES + 1];
+	bool ROBSupport[DC__VOLTAGE_STATES + 1][2];
 	bool PTEBufferSizeNotExceeded[DC__VOLTAGE_STATES + 1][2];
-	bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES + 1];
-	double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES + 1];
+	bool TotalVerticalActiveBandwidthSupport[DC__VOLTAGE_STATES + 1][2];
+	double MaxTotalVerticalActiveAvailableBandwidth[DC__VOLTAGE_STATES + 1][2];
 	double PrefetchBW[DC__NUM_DPP__MAX];
-	double PDEAndMetaPTEBytesPerFrame[DC__NUM_DPP__MAX];
-	double MetaRowBytes[DC__NUM_DPP__MAX];
-	double DPTEBytesPerRow[DC__NUM_DPP__MAX];
-	double PrefetchLinesY[DC__NUM_DPP__MAX];
-	double PrefetchLinesC[DC__NUM_DPP__MAX];
+	double PDEAndMetaPTEBytesPerFrame[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double MetaRowBytes[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double DPTEBytesPerRow[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double PrefetchLinesY[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double PrefetchLinesC[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	unsigned int MaxNumSwY[DC__NUM_DPP__MAX];
 	unsigned int MaxNumSwC[DC__NUM_DPP__MAX];
 	double PrefillY[DC__NUM_DPP__MAX];
@@ -538,7 +540,7 @@ struct vba_vars_st {
 	double LinesForMetaPTE[DC__NUM_DPP__MAX];
 	double LinesForMetaAndDPTERow[DC__NUM_DPP__MAX];
 	double MinDPPCLKUsingSingleDPP[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthYSingleDPP[DC__NUM_DPP__MAX];
+	double SwathWidthYSingleDPP[DC__NUM_DPP__MAX];
 	double BytePerPixelInDETY[DC__NUM_DPP__MAX];
 	double BytePerPixelInDETC[DC__NUM_DPP__MAX];
 	bool RequiresDSC[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
@@ -546,7 +548,7 @@ struct vba_vars_st {
 	double RequiresFEC[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
 	double OutputBppPerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
 	double DSCDelayPerState[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
-	bool ViewportSizeSupport[DC__VOLTAGE_STATES + 1];
+	bool ViewportSizeSupport[DC__VOLTAGE_STATES + 1][2];
 	unsigned int Read256BlockHeightY[DC__NUM_DPP__MAX];
 	unsigned int Read256BlockWidthY[DC__NUM_DPP__MAX];
 	unsigned int Read256BlockHeightC[DC__NUM_DPP__MAX];
@@ -561,7 +563,7 @@ struct vba_vars_st {
 	double WriteBandwidth[DC__NUM_DPP__MAX];
 	double PSCL_FACTOR[DC__NUM_DPP__MAX];
 	double PSCL_FACTOR_CHROMA[DC__NUM_DPP__MAX];
-	double MaximumVStartup[DC__NUM_DPP__MAX];
+	double MaximumVStartup[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	unsigned int MacroTileWidthY[DC__NUM_DPP__MAX];
 	unsigned int MacroTileWidthC[DC__NUM_DPP__MAX];
 	double AlignedDCCMetaPitch[DC__NUM_DPP__MAX];
@@ -578,7 +580,7 @@ struct vba_vars_st {
 	bool ImmediateFlipSupportedForState[DC__VOLTAGE_STATES + 1][2];
 	double WritebackDelay[DC__VOLTAGE_STATES + 1][DC__NUM_DPP__MAX];
 	unsigned int vm_group_bytes[DC__NUM_DPP__MAX];
-	long dpte_group_bytes[DC__NUM_DPP__MAX];
+	unsigned int dpte_group_bytes[DC__NUM_DPP__MAX];
 	unsigned int dpte_row_height[DC__NUM_DPP__MAX];
 	unsigned int meta_req_height[DC__NUM_DPP__MAX];
 	unsigned int meta_req_width[DC__NUM_DPP__MAX];
@@ -604,14 +606,14 @@ struct vba_vars_st {
 	double UrgentBurstFactorChroma[DC__NUM_DPP__MAX];
 	double UrgentBurstFactorChromaPre[DC__NUM_DPP__MAX];
 
+
 	bool           MPCCombine[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
 	double         SwathWidthCSingleDPP[DC__NUM_DPP__MAX];
 	double         MaximumSwathWidthInLineBufferLuma;
 	double         MaximumSwathWidthInLineBufferChroma;
 	double         MaximumSwathWidthLuma[DC__NUM_DPP__MAX];
 	double         MaximumSwathWidthChroma[DC__NUM_DPP__MAX];
-	bool odm_combine_dummy[DC__NUM_DPP__MAX];
-	enum odm_combine_mode odm_combine_mode_dummy[DC__NUM_DPP__MAX];
+	enum odm_combine_mode odm_combine_dummy[DC__NUM_DPP__MAX];
 	double         dummy1[DC__NUM_DPP__MAX];
 	double         dummy2[DC__NUM_DPP__MAX];
 	double         dummy3[DC__NUM_DPP__MAX];
@@ -621,9 +623,9 @@ struct vba_vars_st {
 	double         dummy7[DC__NUM_DPP__MAX];
 	double         dummy8[DC__NUM_DPP__MAX];
 	unsigned int        dummyinteger1ms[DC__NUM_DPP__MAX];
-	unsigned int        dummyinteger2ms[DC__NUM_DPP__MAX];
+	double        dummyinteger2ms[DC__NUM_DPP__MAX];
 	unsigned int        dummyinteger3[DC__NUM_DPP__MAX];
-	unsigned int        dummyinteger4;
+	unsigned int        dummyinteger4[DC__NUM_DPP__MAX];
 	unsigned int        dummyinteger5;
 	unsigned int        dummyinteger6;
 	unsigned int        dummyinteger7;
@@ -636,7 +638,6 @@ struct vba_vars_st {
 	unsigned int        dummyintegerarr2[DC__NUM_DPP__MAX];
 	unsigned int        dummyintegerarr3[DC__NUM_DPP__MAX];
 	unsigned int        dummyintegerarr4[DC__NUM_DPP__MAX];
-	long                dummylongarr1[DC__NUM_DPP__MAX];
 	bool           dummysinglestring;
 	bool           SingleDPPViewportSizeSupportPerPlane[DC__NUM_DPP__MAX];
 	double         PlaneRequiredDISPCLKWithODMCombine2To1;
@@ -644,20 +645,19 @@ struct vba_vars_st {
 	unsigned int   TotalNumberOfSingleDPPPlanes[DC__VOLTAGE_STATES + 1][2];
 	bool           LinkDSCEnable;
 	bool           ODMCombine4To1SupportCheckOK[DC__VOLTAGE_STATES + 1];
-	bool ODMCombineEnableThisState[DC__NUM_DPP__MAX];
-	enum odm_combine_mode ODMCombineEnableTypeThisState[DC__NUM_DPP__MAX];
-	unsigned int   SwathWidthCThisState[DC__NUM_DPP__MAX];
+	enum odm_combine_mode ODMCombineEnableThisState[DC__NUM_DPP__MAX];
+	double   SwathWidthCThisState[DC__NUM_DPP__MAX];
 	bool           ViewportSizeSupportPerPlane[DC__NUM_DPP__MAX];
 	double         AlignedDCCMetaPitchY[DC__NUM_DPP__MAX];
 	double         AlignedDCCMetaPitchC[DC__NUM_DPP__MAX];
 
 	unsigned int NotEnoughUrgentLatencyHiding;
 	unsigned int NotEnoughUrgentLatencyHidingPre;
-	long PTEBufferSizeInRequestsForLuma;
-	long PTEBufferSizeInRequestsForChroma;
+	int PTEBufferSizeInRequestsForLuma;
+	int PTEBufferSizeInRequestsForChroma;
 
 	// Missing from VBA
-	long dpte_group_bytes_chroma;
+	int dpte_group_bytes_chroma;
 	unsigned int vm_group_bytes_chroma;
 	double dst_x_after_scaler;
 	double dst_y_after_scaler;
@@ -682,8 +682,8 @@ struct vba_vars_st {
 	double MinTTUVBlank[DC__NUM_DPP__MAX];
 	double BytePerPixelDETY[DC__NUM_DPP__MAX];
 	double BytePerPixelDETC[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthY[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthSingleDPPY[DC__NUM_DPP__MAX];
+	double SwathWidthY[DC__NUM_DPP__MAX];
+	double SwathWidthSingleDPPY[DC__NUM_DPP__MAX];
 	double CursorRequestDeliveryTime[DC__NUM_DPP__MAX];
 	double CursorRequestDeliveryTimePrefetch[DC__NUM_DPP__MAX];
 	double ReadBandwidthPlaneLuma[DC__NUM_DPP__MAX];
@@ -759,8 +759,8 @@ struct vba_vars_st {
 	double LinesInDETY[DC__NUM_DPP__MAX];
 	double LinesInDETYRoundedDownToSwath[DC__NUM_DPP__MAX];
 
-	unsigned int SwathWidthSingleDPPC[DC__NUM_DPP__MAX];
-	unsigned int SwathWidthC[DC__NUM_DPP__MAX];
+	double SwathWidthSingleDPPC[DC__NUM_DPP__MAX];
+	double SwathWidthC[DC__NUM_DPP__MAX];
 	unsigned int BytePerPixelY[DC__NUM_DPP__MAX];
 	unsigned int BytePerPixelC[DC__NUM_DPP__MAX];
 	long dummyinteger1;
@@ -778,6 +778,7 @@ struct vba_vars_st {
 	unsigned int DCCCMaxCompressedBlock[DC__NUM_DPP__MAX];
 	unsigned int DCCCIndependent64ByteBlock[DC__NUM_DPP__MAX];
 	double VStartupMargin;
+	bool NotEnoughTimeForDynamicMetadata;
 
 	/* Missing from VBA */
 	unsigned int MaximumMaxVStartupLines;
@@ -813,7 +814,7 @@ struct vba_vars_st {
 	unsigned int ViewportHeightChroma[DC__NUM_DPP__MAX];
 	double HRatioChroma[DC__NUM_DPP__MAX];
 	double VRatioChroma[DC__NUM_DPP__MAX];
-	long WritebackSourceWidth[DC__NUM_DPP__MAX];
+	int WritebackSourceWidth[DC__NUM_DPP__MAX];
 
 	bool ModeIsSupported;
 	bool ODMCombine4To1Supported;
@@ -849,6 +850,58 @@ struct vba_vars_st {
 	unsigned int MaxNumHDMIFRLOutputs;
 	int    AudioSampleRate[DC__NUM_DPP__MAX];
 	int    AudioSampleLayout[DC__NUM_DPP__MAX];
+
+	int PercentMarginOverMinimumRequiredDCFCLK;
+	bool DynamicMetadataSupported[DC__VOLTAGE_STATES + 1][2];
+	enum immediate_flip_requirement ImmediateFlipRequirement;
+	double DETBufferSizeYThisState[DC__NUM_DPP__MAX];
+	double DETBufferSizeCThisState[DC__NUM_DPP__MAX];
+	bool NoUrgentLatencyHiding[DC__NUM_DPP__MAX];
+	bool NoUrgentLatencyHidingPre[DC__NUM_DPP__MAX];
+	int swath_width_luma_ub_this_state[DC__NUM_DPP__MAX];
+	int swath_width_chroma_ub_this_state[DC__NUM_DPP__MAX];
+	double UrgLatency[DC__VOLTAGE_STATES + 1];
+	double VActiveCursorBandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double VActivePixelBandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	bool NoTimeForPrefetch[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	bool NoTimeForDynamicMetadata[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double dpte_row_bandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double meta_row_bandwidth[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double DETBufferSizeYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double DETBufferSizeCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	int swath_width_luma_ub_all_states[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	int swath_width_chroma_ub_all_states[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	bool NotUrgentLatencyHiding[DC__VOLTAGE_STATES + 1][2];
+	unsigned int SwathHeightYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	unsigned int SwathHeightCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	unsigned int SwathWidthYAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	unsigned int SwathWidthCAllStates[DC__VOLTAGE_STATES + 1][2][DC__NUM_DPP__MAX];
+	double TotalDPTERowBandwidth[DC__VOLTAGE_STATES + 1][2];
+	double TotalMetaRowBandwidth[DC__VOLTAGE_STATES + 1][2];
+	double TotalVActiveCursorBandwidth[DC__VOLTAGE_STATES + 1][2];
+	double TotalVActivePixelBandwidth[DC__VOLTAGE_STATES + 1][2];
+	bool UseMinimumRequiredDCFCLK;
+	double WritebackDelayTime[DC__NUM_DPP__MAX];
+	unsigned int DCCYIndependentBlock[DC__NUM_DPP__MAX];
+	unsigned int DCCCIndependentBlock[DC__NUM_DPP__MAX];
+	unsigned int dummyinteger15;
+	unsigned int dummyinteger16;
+	unsigned int dummyinteger17;
+	unsigned int dummyinteger18;
+	unsigned int dummyinteger19;
+	unsigned int dummyinteger20;
+	unsigned int dummyinteger21;
+	unsigned int dummyinteger22;
+	unsigned int dummyinteger23;
+	unsigned int dummyinteger24;
+	unsigned int dummyinteger25;
+	unsigned int dummyinteger26;
+	unsigned int dummyinteger27;
+	unsigned int dummyinteger28;
+	unsigned int dummyinteger29;
+	bool dummystring[DC__NUM_DPP__MAX];
+	double BPP;
+	enum odm_combine_policy ODMCombinePolicy;
 };
 
 bool CalculateMinAndMaxPrefetchMode(
@@ -870,4 +923,3 @@ double CalculateWriteBackDISPCLK(
 		unsigned int WritebackChromaLineBufferWidth);
 
 #endif /* _DML2_DISPLAY_MODE_VBA_H_ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
index b953b02a1512..723af0b2dda0 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_common_defs.c
@@ -24,7 +24,7 @@
  */
 
 #include "dml_common_defs.h"
-#include "../calcs/dcn_calc_math.h"
+#include "dcn_calc_math.h"
 
 #include "dml_inline_defs.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
index eca140da13d8..ded71ea82413 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h
@@ -27,7 +27,7 @@
 #define __DML_INLINE_DEFS_H__
 
 #include "dml_common_defs.h"
-#include "../calcs/dcn_calc_math.h"
+#include "dcn_calc_math.h"
 #include "dml_logger.h"
 
 static inline double dml_min(double a, double b)
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index 641ffb7cfaed..3f66868df171 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -2,7 +2,13 @@
 #
 # Makefile for the 'dsc' sub-component of DAL.
 
+ifdef CONFIG_X86
 dsc_ccflags := -mhard-float -msse
+endif
+
+ifdef CONFIG_PPC64
+dsc_ccflags := -mhard-float -maltivec
+endif
 
 ifdef CONFIG_CC_IS_GCC
 ifeq ($(call cc-ifversion, -lt, 0701, y), y)
@@ -10,6 +16,7 @@ IS_OLD_GCC = 1
 endif
 endif
 
+ifdef CONFIG_X86
 ifdef IS_OLD_GCC
 # Stack alignment mismatch, proceed with caution.
 # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
@@ -18,6 +25,7 @@ dsc_ccflags += -mpreferred-stack-boundary=4
 else
 dsc_ccflags += -msse2
 endif
+endif
 
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc.o := $(dsc_ccflags)
 CFLAGS_$(AMDDALPATH)/dc/dsc/rc_calc_dpi.o := $(dsc_ccflags)
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index e60f760585e4..8b78fcbfe746 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -22,30 +22,16 @@
  * Author: AMD
  */
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #include "dc_hw_types.h"
 #include "dsc.h"
 #include <drm/drm_dp_helper.h>
-
-struct dc_dsc_policy {
-	bool use_min_slices_h;
-	int max_slices_h; // Maximum available if 0
-	int min_sice_height; // Must not be less than 8
-	int max_target_bpp;
-	int min_target_bpp; // Minimum target bits per pixel
-};
-
-const struct dc_dsc_policy dsc_policy = {
-	.use_min_slices_h = true, // DSC Policy: Use minimum number of slices that fits the pixel clock
-	.max_slices_h = 0, // DSC Policy: Use max available slices (in our case 4 for or 8, depending on the mode)
-	.min_sice_height = 108, // DSC Policy: Use slice height recommended by VESA DSC Spreadsheet user guide
-	.max_target_bpp = 16,
-	.min_target_bpp = 8,
-};
-
+#include "dc.h"
 
 /* This module's internal functions */
 
+/* default DSC policy target bitrate limit is 16bpp */
+static uint32_t dsc_policy_max_target_bpp_limit = 16;
+
 static uint32_t dc_dsc_bandwidth_in_kbps_from_timing(
 	const struct dc_crtc_timing *timing)
 {
@@ -237,8 +223,11 @@ static void get_dsc_enc_caps(
 	// This is a static HW query, so we can use any DSC
 
 	memset(dsc_enc_caps, 0, sizeof(struct dsc_enc_caps));
-	if (dsc)
+	if (dsc) {
 		dsc->funcs->dsc_get_enc_caps(dsc_enc_caps, pixel_clock_100Hz);
+		if (dsc->ctx->dc->debug.native422_support)
+			dsc_enc_caps->color_formats.bits.YCBCR_NATIVE_422 = 1;
+	}
 }
 
 /* Returns 'false' if no intersection was found for at least one capablity.
@@ -578,9 +567,11 @@ static bool setup_dsc_config(
 	bool is_dsc_possible = false;
 	int pic_height;
 	int slice_height;
+	struct dc_dsc_policy policy;
 
 	memset(dsc_cfg, 0, sizeof(struct dc_dsc_config));
 
+	dc_dsc_get_policy_for_timing(timing, &policy);
 	pic_width = timing->h_addressable + timing->h_border_left + timing->h_border_right;
 	pic_height = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
 
@@ -596,7 +587,12 @@ static bool setup_dsc_config(
 		goto done;
 
 	if (target_bandwidth_kbps > 0) {
-		is_dsc_possible = decide_dsc_target_bpp_x16(&dsc_policy, &dsc_common_caps, target_bandwidth_kbps, timing, &target_bpp);
+		is_dsc_possible = decide_dsc_target_bpp_x16(
+				&policy,
+				&dsc_common_caps,
+				target_bandwidth_kbps,
+				timing,
+				&target_bpp);
 		dsc_cfg->bits_per_pixel = target_bpp;
 	}
 	if (!is_dsc_possible)
@@ -698,20 +694,20 @@ static bool setup_dsc_config(
 	if (!is_dsc_possible)
 		goto done;
 
-	if (dsc_policy.use_min_slices_h) {
+	if (policy.use_min_slices_h) {
 		if (min_slices_h > 0)
 			num_slices_h = min_slices_h;
 		else if (max_slices_h > 0) { // Fall back to max slices if min slices is not working out
-			if (dsc_policy.max_slices_h)
-				num_slices_h = min(dsc_policy.max_slices_h, max_slices_h);
+			if (policy.max_slices_h)
+				num_slices_h = min(policy.max_slices_h, max_slices_h);
 			else
 				num_slices_h = max_slices_h;
 		} else
 			is_dsc_possible = false;
 	} else {
 		if (max_slices_h > 0) {
-			if (dsc_policy.max_slices_h)
-				num_slices_h = min(dsc_policy.max_slices_h, max_slices_h);
+			if (policy.max_slices_h)
+				num_slices_h = min(policy.max_slices_h, max_slices_h);
 			else
 				num_slices_h = max_slices_h;
 		} else if (min_slices_h > 0) // Fall back to min slices if max slices is not possible
@@ -733,7 +729,7 @@ static bool setup_dsc_config(
 	// Slice height (i.e. number of slices per column): start with policy and pick the first one that height is divisible by.
 	// For 4:2:0 make sure the slice height is divisible by 2 as well.
 	if (min_slice_height_override == 0)
-		slice_height = min(dsc_policy.min_sice_height, pic_height);
+		slice_height = min(policy.min_slice_height, pic_height);
 	else
 		slice_height = min(min_slice_height_override, pic_height);
 
@@ -764,7 +760,7 @@ done:
 	return is_dsc_possible;
 }
 
-bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps)
+bool dc_dsc_parse_dsc_dpcd(const struct dc *dc, const uint8_t *dpcd_dsc_basic_data, const uint8_t *dpcd_dsc_ext_data, struct dsc_dec_dpcd_caps *dsc_sink_caps)
 {
 	if (!dpcd_dsc_basic_data)
 		return false;
@@ -817,6 +813,23 @@ bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dp
 	if (!dsc_bpp_increment_div_from_dpcd(dpcd_dsc_basic_data[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT], &dsc_sink_caps->bpp_increment_div))
 		return false;
 
+	if (dc->debug.dsc_bpp_increment_div) {
+		/* dsc_bpp_increment_div should onl be 1, 2, 4, 8 or 16, but rather than rejecting invalid values,
+		 * we'll accept all and get it into range. This also makes the above check against 0 redundant,
+		 * but that one stresses out the override will be only used if it's not 0.
+		 */
+		if (dc->debug.dsc_bpp_increment_div >= 1)
+			dsc_sink_caps->bpp_increment_div = 1;
+		if (dc->debug.dsc_bpp_increment_div >= 2)
+			dsc_sink_caps->bpp_increment_div = 2;
+		if (dc->debug.dsc_bpp_increment_div >= 4)
+			dsc_sink_caps->bpp_increment_div = 4;
+		if (dc->debug.dsc_bpp_increment_div >= 8)
+			dsc_sink_caps->bpp_increment_div = 8;
+		if (dc->debug.dsc_bpp_increment_div >= 16)
+			dsc_sink_caps->bpp_increment_div = 16;
+	}
+
 	/* Extended caps */
 	if (dpcd_dsc_ext_data == NULL) { // Extended DPCD DSC data can be null, e.g. because it doesn't apply to SST
 		dsc_sink_caps->branch_overall_throughput_0_mps = 0;
@@ -903,4 +916,67 @@ bool dc_dsc_compute_config(
 			timing, dsc_min_slice_height_override, dsc_cfg);
 	return is_dsc_possible;
 }
-#endif /* CONFIG_DRM_AMD_DC_DSC_SUPPORT */
+
+void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing, struct dc_dsc_policy *policy)
+{
+	uint32_t bpc = 0;
+
+	policy->min_target_bpp = 0;
+	policy->max_target_bpp = 0;
+
+	/* DSC Policy: Use minimum number of slices that fits the pixel clock */
+	policy->use_min_slices_h = true;
+
+	/* DSC Policy: Use max available slices
+	 * (in our case 4 for or 8, depending on the mode)
+	 */
+	policy->max_slices_h = 0;
+
+	/* DSC Policy: Use slice height recommended
+	 * by VESA DSC Spreadsheet user guide
+	 */
+	policy->min_slice_height = 108;
+
+	/* DSC Policy: follow DP specs with an internal upper limit to 16 bpp
+	 * for better interoperability
+	 */
+	switch (timing->display_color_depth) {
+	case COLOR_DEPTH_888:
+		bpc = 8;
+		break;
+	case COLOR_DEPTH_101010:
+		bpc = 10;
+		break;
+	case COLOR_DEPTH_121212:
+		bpc = 12;
+		break;
+	default:
+		return;
+	}
+	switch (timing->pixel_encoding) {
+	case PIXEL_ENCODING_RGB:
+	case PIXEL_ENCODING_YCBCR444:
+	case PIXEL_ENCODING_YCBCR422: /* assume no YCbCr422 native support */
+		/* DP specs limits to 8 */
+		policy->min_target_bpp = 8;
+		/* DP specs limits to 3 x bpc */
+		policy->max_target_bpp = 3 * bpc;
+		break;
+	case PIXEL_ENCODING_YCBCR420:
+		/* DP specs limits to 6 */
+		policy->min_target_bpp = 6;
+		/* DP specs limits to 1.5 x bpc assume bpc is an even number */
+		policy->max_target_bpp = bpc * 3 / 2;
+		break;
+	default:
+		return;
+	}
+	/* internal upper limit, default 16 bpp */
+	if (policy->max_target_bpp > dsc_policy_max_target_bpp_limit)
+		policy->max_target_bpp = dsc_policy_max_target_bpp_limit;
+}
+
+void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit)
+{
+	dsc_policy_max_target_bpp_limit = limit;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h b/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h
index 020ad8f685ea..9f70e87b3ecb 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dscc_types.h
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -51,4 +50,3 @@ int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_par
 
 #endif
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h b/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h
index f66d006eac5d..e5fac9f4181d 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/qp_tables.h
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -703,4 +702,3 @@ const qp_table   qp_table_422_8bpc_max = {
 	{  16, { 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2, 3, 4} }
 };
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
index 76c4b12d6824..03ae15946c6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -252,4 +251,3 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 	rc->rc_buf_thresh[13] = 8064;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
index f1d6e793bc61..b6b1f09c2009 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.h
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 /*
  * Copyright 2017 Advanced Micro Devices, Inc.
@@ -82,4 +81,3 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 
 #endif
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
index 73172fd0b529..1f6e63b71456 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc_dpi.c
@@ -1,4 +1,3 @@
-#if defined(CONFIG_DRM_AMD_DC_DSC_SUPPORT)
 /*
  * Copyright 2012-17 Advanced Micro Devices, Inc.
  *
@@ -144,4 +143,3 @@ int dscc_compute_dsc_parameters(const struct drm_dsc_config *pps, struct dsc_par
 	return ret;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index b3062275711e..202baa210cc8 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -61,26 +61,25 @@ AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCE120)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 GPIO_DCN10 = hw_translate_dcn10.o hw_factory_dcn10.o
 
 AMD_DAL_GPIO_DCN10 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn10/,$(GPIO_DCN10))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCN10)
-endif
 
 ###############################################################################
 # DCN 2
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
 GPIO_DCN20 = hw_translate_dcn20.o hw_factory_dcn20.o
 
 AMD_DAL_GPIO_DCN20 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn20/,$(GPIO_DCN20))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCN20)
-endif
 
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
+###############################################################################
+# DCN 21
+###############################################################################
 GPIO_DCN21 = hw_translate_dcn21.o hw_factory_dcn21.o
 
 AMD_DAL_GPIO_DCN21 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn21/,$(GPIO_DCN21))
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
index 43a440385b43..83f798cb8b21 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.c
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dm_services.h"
 #include "include/gpio_types.h"
 #include "../hw_factory.h"
@@ -110,6 +109,12 @@ static const struct ddc_registers ddc_data_regs_dcn[] = {
 	ddc_data_regs_dcn2(4),
 	ddc_data_regs_dcn2(5),
 	ddc_data_regs_dcn2(6),
+	{
+			DDC_GPIO_VGA_REG_LIST(DATA),
+			.ddc_setup = 0,
+			.phy_aux_cntl = 0,
+			.dc_gpio_aux_ctrl_5 = 0
+	}
 };
 
 static const struct ddc_registers ddc_clk_regs_dcn[] = {
@@ -119,6 +124,12 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = {
 	ddc_clk_regs_dcn2(4),
 	ddc_clk_regs_dcn2(5),
 	ddc_clk_regs_dcn2(6),
+	{
+			DDC_GPIO_VGA_REG_LIST(CLK),
+			.ddc_setup = 0,
+			.phy_aux_cntl = 0,
+			.dc_gpio_aux_ctrl_5 = 0
+	}
 };
 
 static const struct ddc_sh_mask ddc_shift[] = {
@@ -246,4 +257,3 @@ void dal_hw_factory_dcn20_init(struct hw_factory *factory)
 	factory->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h
index 43a4ce7aa3bf..0fd9b315bd7a 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_factory_dcn20.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #ifndef __DAL_HW_FACTORY_DCN20_H__
 #define __DAL_HW_FACTORY_DCN20_H__
 
@@ -30,4 +29,3 @@
 void dal_hw_factory_dcn20_init(struct hw_factory *factory);
 
 #endif /* __DAL_HW_FACTORY_DCN20_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c
index 915e896e0e91..52ba62b3b5e4 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.c
@@ -26,7 +26,6 @@
 /*
  * Pre-requisites: headers required by header of this unit
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "hw_translate_dcn20.h"
 
 #include "dm_services.h"
@@ -379,4 +378,3 @@ void dal_hw_translate_dcn20_init(struct hw_translate *tr)
 	tr->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h
index 01f52c7bed86..5f7a35530e26 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn20/hw_translate_dcn20.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #ifndef __DAL_HW_TRANSLATE_DCN20_H__
 #define __DAL_HW_TRANSLATE_DCN20_H__
 
@@ -32,4 +31,3 @@ struct hw_translate;
 void dal_hw_translate_dcn20_init(struct hw_translate *tr);
 
 #endif /* __DAL_HW_TRANSLATE_DCN20_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
index 8572678f8d4f..907c5911eb9e 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.c
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dm_services.h"
 #include "include/gpio_types.h"
 #include "../hw_factory.h"
@@ -239,4 +238,3 @@ void dal_hw_factory_dcn21_init(struct hw_factory *factory)
 	factory->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h
index 2443f9e7afbf..4949e0c7fa06 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_factory_dcn21.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #ifndef __DAL_HW_FACTORY_DCN21_H__
 #define __DAL_HW_FACTORY_DCN21_H__
 
@@ -30,4 +29,3 @@
 void dal_hw_factory_dcn21_init(struct hw_factory *factory);
 
 #endif /* __DAL_HW_FACTORY_DCN20_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
index fbb58fb8c318..291966efe63d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.c
@@ -26,7 +26,6 @@
 /*
  * Pre-requisites: headers required by header of this unit
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "hw_translate_dcn21.h"
 
 #include "dm_services.h"
@@ -382,4 +381,3 @@ void dal_hw_translate_dcn21_init(struct hw_translate *tr)
 	tr->funcs = &funcs;
 }
 
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h
index 2bfaac24c574..9462b0a65200 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn21/hw_translate_dcn21.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #ifndef __DAL_HW_TRANSLATE_DCN21_H__
 #define __DAL_HW_TRANSLATE_DCN21_H__
 
@@ -32,4 +31,3 @@ struct hw_translate;
 void dal_hw_translate_dcn21_init(struct hw_translate *tr);
 
 #endif /* __DAL_HW_TRANSLATE_DCN21_H__ */
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
index f91e85b04956..308a543178a5 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
@@ -48,13 +48,11 @@
 	DDC_GPIO_REG_LIST(cd,id),\
 	.ddc_setup = REG(DC_I2C_DDC ## id ## _SETUP)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	#define DDC_REG_LIST_DCN2(cd, id) \
 	DDC_GPIO_REG_LIST(cd, id),\
 	.ddc_setup = REG(DC_I2C_DDC ## id ## _SETUP),\
 	.phy_aux_cntl = REG(PHY_AUX_CNTL), \
 	.dc_gpio_aux_ctrl_5 = REG(DC_GPIO_AUX_CTRL_5)
-#endif
 
 #define DDC_GPIO_VGA_REG_LIST_ENTRY(type,cd)\
 	.type ## _reg =   REG(DC_GPIO_DDCVGA_ ## type),\
@@ -90,13 +88,11 @@
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define DDC_I2C_REG_LIST_DCN2(cd) \
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0,\
 	.phy_aux_cntl = REG(PHY_AUX_CNTL), \
 	.dc_gpio_aux_ctrl_5 = REG(DC_GPIO_AUX_CTRL_5)
-#endif
 #define DDC_MASK_SH_LIST_COMMON(mask_sh) \
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE, mask_sh),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_ENABLE, mask_sh),\
@@ -110,22 +106,18 @@
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SDA_PD_DIS, mask_sh),\
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SCL_PD_DIS, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define DDC_MASK_SH_LIST_DCN2(mask_sh, cd) \
 	{DDC_MASK_SH_LIST_COMMON(mask_sh),\
 	0,\
 	0,\
 	(PHY_AUX_CNTL__AUX## cd ##_PAD_RXSEL## mask_sh),\
 	(DC_GPIO_AUX_CTRL_5__DDC_PAD## cd ##_I2CMODE## mask_sh)}
-#endif
 
 struct ddc_registers {
 	struct gpio_registers gpio;
 	uint32_t ddc_setup;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t phy_aux_cntl;
 	uint32_t dc_gpio_aux_ctrl_5;
-#endif
 };
 
 struct ddc_sh_mask {
@@ -140,11 +132,9 @@ struct ddc_sh_mask {
 	/* i2cpad_mask */
 	uint32_t DC_GPIO_SDA_PD_DIS;
 	uint32_t DC_GPIO_SCL_PD_DIS;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	//phy_aux_cntl
 	uint32_t AUX_PAD_RXSEL;
 	uint32_t DDC_PAD_I2CMODE;
-#endif
 };
 
 
@@ -180,7 +170,6 @@ struct ddc_sh_mask {
 {\
 	DDC_I2C_REG_LIST(SCL)\
 }
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define ddc_data_regs_dcn2(id) \
 {\
 	DDC_REG_LIST_DCN2(DATA, id)\
@@ -200,7 +189,6 @@ struct ddc_sh_mask {
 {\
 	DDC_REG_LIST_DCN2(SCL)\
 }
-#endif
 
 
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_GPIO_DDC_REGS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
index 1c12961f6472..1ae153eab31d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c
@@ -48,18 +48,18 @@
 
 struct gpio;
 
-static void destruct(
+static void dal_hw_ddc_destruct(
 	struct hw_ddc *pin)
 {
 	dal_hw_gpio_destruct(&pin->base);
 }
 
-static void destroy(
+static void dal_hw_ddc_destroy(
 	struct hw_gpio_pin **ptr)
 {
 	struct hw_ddc *pin = HW_DDC_FROM_BASE(*ptr);
 
-	destruct(pin);
+	dal_hw_ddc_destruct(pin);
 
 	kfree(pin);
 
@@ -150,7 +150,6 @@ static enum gpio_result set_config(
 					AUX_PAD1_MODE, 0);
 		}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (ddc->regs->dc_gpio_aux_ctrl_5 != 0) {
 				REG_UPDATE(dc_gpio_aux_ctrl_5, DDC_PAD_I2CMODE, 1);
 		}
@@ -158,7 +157,6 @@ static enum gpio_result set_config(
 		if (ddc->regs->phy_aux_cntl != 0) {
 				REG_UPDATE(phy_aux_cntl, AUX_PAD_RXSEL, 1);
 		}
-#endif
 		return GPIO_RESULT_OK;
 	case GPIO_DDC_CONFIG_TYPE_MODE_AUX:
 		/* set the AUX pad mode */
@@ -166,12 +164,10 @@ static enum gpio_result set_config(
 			REG_SET(gpio.MASK_reg, regval,
 					AUX_PAD1_MODE, 1);
 		}
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (ddc->regs->dc_gpio_aux_ctrl_5 != 0) {
 			REG_UPDATE(dc_gpio_aux_ctrl_5,
 					DDC_PAD_I2CMODE, 0);
 		}
-#endif
 
 		return GPIO_RESULT_OK;
 	case GPIO_DDC_CONFIG_TYPE_POLL_FOR_CONNECT:
@@ -211,7 +207,7 @@ static enum gpio_result set_config(
 }
 
 static const struct hw_gpio_pin_funcs funcs = {
-	.destroy = destroy,
+	.destroy = dal_hw_ddc_destroy,
 	.open = dal_hw_gpio_open,
 	.get_value = dal_hw_gpio_get_value,
 	.set_value = dal_hw_gpio_set_value,
@@ -220,7 +216,7 @@ static const struct hw_gpio_pin_funcs funcs = {
 	.close = dal_hw_gpio_close,
 };
 
-static void construct(
+static void dal_hw_ddc_construct(
 	struct hw_ddc *ddc,
 	enum gpio_id id,
 	uint32_t en,
@@ -247,7 +243,7 @@ void dal_hw_ddc_init(
 		return;
 	}
 
-	construct(*hw_ddc, id, en, ctx);
+	dal_hw_ddc_construct(*hw_ddc, id, en, ctx);
 }
 
 struct hw_gpio_pin *dal_hw_ddc_get_pin(struct gpio *gpio)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index fa9f1d055ec8..d2d36d48caaa 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -45,15 +45,11 @@
 #include "dce80/hw_factory_dce80.h"
 #include "dce110/hw_factory_dce110.h"
 #include "dce120/hw_factory_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/hw_factory_dcn10.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/hw_factory_dcn20.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/hw_factory_dcn21.h"
-#endif
 
 #include "diagnostics/hw_factory_diag.h"
 
@@ -90,19 +86,15 @@ bool dal_hw_factory_init(
 	case DCE_VERSION_12_1:
 		dal_hw_factory_dce120_init(factory);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		dal_hw_factory_dcn10_init(factory);
 		return true;
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		dal_hw_factory_dcn20_init(factory);
 		return true;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		dal_hw_factory_dcn21_init(factory);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c
index 69b899741f6d..f9e847e6555d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_generic.c
@@ -46,22 +46,13 @@
 
 struct gpio;
 
-static void dal_hw_generic_construct(
-	struct hw_generic *pin,
-	enum gpio_id id,
-	uint32_t en,
-	struct dc_context *ctx)
-{
-	dal_hw_gpio_construct(&pin->base, id, en, ctx);
-}
-
 static void dal_hw_generic_destruct(
 	struct hw_generic *pin)
 {
 	dal_hw_gpio_destruct(&pin->base);
 }
 
-static void destroy(
+static void dal_hw_generic_destroy(
 	struct hw_gpio_pin **ptr)
 {
 	struct hw_generic *generic = HW_GENERIC_FROM_BASE(*ptr);
@@ -90,7 +81,7 @@ static enum gpio_result set_config(
 }
 
 static const struct hw_gpio_pin_funcs funcs = {
-	.destroy = destroy,
+	.destroy = dal_hw_generic_destroy,
 	.open = dal_hw_gpio_open,
 	.get_value = dal_hw_gpio_get_value,
 	.set_value = dal_hw_gpio_set_value,
@@ -99,14 +90,14 @@ static const struct hw_gpio_pin_funcs funcs = {
 	.close = dal_hw_gpio_close,
 };
 
-static void construct(
-	struct hw_generic *generic,
+static void dal_hw_generic_construct(
+	struct hw_generic *pin,
 	enum gpio_id id,
 	uint32_t en,
 	struct dc_context *ctx)
 {
-	dal_hw_generic_construct(generic, id, en, ctx);
-	generic->base.base.funcs = &funcs;
+	dal_hw_gpio_construct(&pin->base, id, en, ctx);
+	pin->base.base.funcs = &funcs;
 }
 
 void dal_hw_generic_init(
@@ -126,7 +117,7 @@ void dal_hw_generic_init(
 		return;
 	}
 
-	construct(*hw_generic, id, en, ctx);
+	dal_hw_generic_construct(*hw_generic, id, en, ctx);
 }
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c
index 00c9bcf660a3..692f29de7797 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_hpd.c
@@ -46,34 +46,18 @@
 
 struct gpio;
 
-static void dal_hw_hpd_construct(
-	struct hw_hpd *pin,
-	enum gpio_id id,
-	uint32_t en,
-	struct dc_context *ctx)
-{
-	dal_hw_gpio_construct(&pin->base, id, en, ctx);
-}
-
 static void dal_hw_hpd_destruct(
 	struct hw_hpd *pin)
 {
 	dal_hw_gpio_destruct(&pin->base);
 }
 
-
-static void destruct(
-	struct hw_hpd *hpd)
-{
-	dal_hw_hpd_destruct(hpd);
-}
-
-static void destroy(
+static void dal_hw_hpd_destroy(
 	struct hw_gpio_pin **ptr)
 {
 	struct hw_hpd *hpd = HW_HPD_FROM_BASE(*ptr);
 
-	destruct(hpd);
+	dal_hw_hpd_destruct(hpd);
 
 	kfree(hpd);
 
@@ -120,7 +104,7 @@ static enum gpio_result set_config(
 }
 
 static const struct hw_gpio_pin_funcs funcs = {
-	.destroy = destroy,
+	.destroy = dal_hw_hpd_destroy,
 	.open = dal_hw_gpio_open,
 	.get_value = get_value,
 	.set_value = dal_hw_gpio_set_value,
@@ -129,14 +113,14 @@ static const struct hw_gpio_pin_funcs funcs = {
 	.close = dal_hw_gpio_close,
 };
 
-static void construct(
-	struct hw_hpd *hpd,
+static void dal_hw_hpd_construct(
+	struct hw_hpd *pin,
 	enum gpio_id id,
 	uint32_t en,
 	struct dc_context *ctx)
 {
-	dal_hw_hpd_construct(hpd, id, en, ctx);
-	hpd->base.base.funcs = &funcs;
+	dal_hw_gpio_construct(&pin->base, id, en, ctx);
+	pin->base.base.funcs = &funcs;
 }
 
 void dal_hw_hpd_init(
@@ -156,7 +140,7 @@ void dal_hw_hpd_init(
 		return;
 	}
 
-	construct(*hw_hpd, id, en, ctx);
+	dal_hw_hpd_construct(*hw_hpd, id, en, ctx);
 }
 
 struct hw_gpio_pin *dal_hw_hpd_get_pin(struct gpio *gpio)
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index f2046f55d6a8..5d396657a1ee 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -43,15 +43,11 @@
 #include "dce80/hw_translate_dce80.h"
 #include "dce110/hw_translate_dce110.h"
 #include "dce120/hw_translate_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/hw_translate_dcn10.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dcn20/hw_translate_dcn20.h"
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #include "dcn21/hw_translate_dcn21.h"
-#endif
 
 #include "diagnostics/hw_translate_diag.h"
 
@@ -85,19 +81,15 @@ bool dal_hw_translate_init(
 	case DCE_VERSION_12_1:
 		dal_hw_translate_dce120_init(translate);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	case DCN_VERSION_1_0:
 	case DCN_VERSION_1_01:
 		dal_hw_translate_dcn10_init(translate);
 		return true;
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	case DCN_VERSION_2_0:
 		dal_hw_translate_dcn20_init(translate);
 		return true;
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	case DCN_VERSION_2_1:
 		dal_hw_translate_dcn21_init(translate);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_status.h b/drivers/gpu/drm/amd/display/dc/inc/core_status.h
index fd39e2abe2ed..4ead89dd7c41 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_status.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_status.h
@@ -43,10 +43,8 @@ enum dc_status {
 	DC_FAIL_BANDWIDTH_VALIDATE = 13, /* BW and Watermark validation */
 	DC_FAIL_SCALING = 14,
 	DC_FAIL_DP_LINK_TRAINING = 15,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	DC_FAIL_DSC_VALIDATE = 16,
 	DC_NO_DSC_RESOURCE = 17,
-#endif
 	DC_FAIL_UNSUPPORTED_1 = 18,
 	DC_FAIL_CLK_EXCEED_MAX = 21,
 	DC_FAIL_CLK_BELOW_MIN = 22, /*THIS IS MIN PER IP*/
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index a831079607cd..f285b76888fb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -33,13 +33,11 @@
 #include "dc_bios_types.h"
 #include "mem_input.h"
 #include "hubp.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "mpc.h"
 #endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #include "dwb.h"
 #include "mcif_wb.h"
-#endif
 
 #define MAX_CLOCK_SOURCES 7
 
@@ -89,9 +87,7 @@ void core_link_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
 struct resource_pool;
 struct dc_state;
 struct resource_context;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 struct clk_bw_params;
-#endif
 
 struct resource_funcs {
 	void (*destroy)(struct resource_pool **pool);
@@ -105,7 +101,7 @@ struct resource_funcs {
 
 	int (*populate_dml_pipes)(
 		struct dc *dc,
-		struct resource_context *res_ctx,
+		struct dc_state *context,
 		display_e2e_pipe_params_st *pipes);
 
 	enum dc_status (*validate_global)(
@@ -135,7 +131,6 @@ struct resource_funcs {
 			struct resource_context *res_ctx,
 			const struct resource_pool *pool,
 			struct dc_stream_state *stream);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*populate_dml_writeback_from_context)(
 			struct dc *dc,
 			struct resource_context *res_ctx,
@@ -146,12 +141,9 @@ struct resource_funcs {
 			struct dc_state *context,
 			display_e2e_pipe_params_st *pipes,
 			int pipe_cnt);
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	void (*update_bw_bounding_box)(
 			struct dc *dc,
 			struct clk_bw_params *bw_params);
-#endif
 
 };
 
@@ -180,7 +172,6 @@ struct resource_pool {
 	struct dce_i2c_sw *sw_i2cs[MAX_PIPES];
 	bool i2c_hw_buffer_in_use;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dwbc *dwbc[MAX_DWB_PIPES];
 	struct mcif_wb *mcif_wb[MAX_DWB_PIPES];
 	struct {
@@ -188,11 +179,8 @@ struct resource_pool {
 		unsigned int gsl_1:1;
 		unsigned int gsl_2:1;
 	} gsl_groups;
-#endif
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct display_stream_compressor *dscs[MAX_PIPES];
-#endif
 
 	unsigned int pipe_count;
 	unsigned int underlay_pipe_index;
@@ -206,9 +194,7 @@ struct resource_pool {
 	unsigned int timing_generator_count;
 	unsigned int mpcc_count;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	unsigned int writeback_pipe_count;
-#endif
 	/*
 	 * reserved clock source for DP
 	 */
@@ -226,9 +212,12 @@ struct resource_pool {
 
 	struct abm *abm;
 	struct dmcu *dmcu;
+	struct dmub_psr *psr;
 
 	const struct resource_funcs *funcs;
 	const struct resource_caps *res_cap;
+
+	struct ddc_service *oem_device;
 };
 
 struct dcn_fe_bandwidth {
@@ -238,9 +227,7 @@ struct dcn_fe_bandwidth {
 
 struct stream_resource {
 	struct output_pixel_processor *opp;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	struct display_stream_compressor *dsc;
-#endif
 	struct timing_generator *tg;
 	struct stream_encoder *stream_enc;
 	struct audio *audio;
@@ -249,12 +236,10 @@ struct stream_resource {
 	struct encoder_info_frame encoder_info_frame;
 
 	struct abm *abm;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* There are only (num_pipes+1)/2 groups. 0 means unassigned,
 	 * otherwise it's using group number 'gsl_group-1'
 	 */
 	uint8_t gsl_group;
-#endif
 };
 
 struct plane_resource {
@@ -306,17 +291,15 @@ struct pipe_ctx {
 	struct pipe_ctx *next_odm_pipe;
 	struct pipe_ctx *prev_odm_pipe;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct _vcs_dpi_display_dlg_regs_st dlg_regs;
 	struct _vcs_dpi_display_ttu_regs_st ttu_regs;
 	struct _vcs_dpi_display_rq_regs_st rq_regs;
 	struct _vcs_dpi_display_pipe_dest_params_st pipe_dlg_param;
 #endif
 	union pipe_update_flags update_flags;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct dwbc *dwbc;
 	struct mcif_wb *mcif_wb;
-#endif
 };
 
 struct resource_context {
@@ -325,9 +308,7 @@ struct resource_context {
 	bool is_audio_acquired[MAX_PIPES];
 	uint8_t clock_source_ref_count[MAX_CLOCK_SOURCES];
 	uint8_t dp_clock_source_ref_count;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	bool is_dsc_acquired[MAX_PIPES];
-#endif
 };
 
 struct dce_bw_output {
@@ -347,18 +328,14 @@ struct dce_bw_output {
 	int blackout_recovery_time_us;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dcn_bw_writeback {
 	struct mcif_arb_params mcif_wb_arb[MAX_DWB_PIPES];
 };
-#endif
 
 struct dcn_bw_output {
 	struct dc_clocks clk;
 	struct dcn_watermark_set watermarks;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dcn_bw_writeback bw_writeback;
-#endif
 };
 
 union bw_output {
@@ -392,7 +369,7 @@ struct dc_state {
 
 	/* Note: these are big structures, do *not* put on stack! */
 	struct dm_pp_display_configuration pp_display_cfg;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_DRM_AMD_DC_DCN
 	struct dcn_bw_internal_vars dcn_bw_vars;
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 14716ba35662..de2d160114db 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -105,7 +105,7 @@ int dc_link_aux_transfer_raw(struct ddc_service *ddc,
 bool dc_link_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *payload);
 
-enum dc_status dc_link_aux_configure_timeout(struct ddc_service *ddc,
+uint32_t dc_link_aux_configure_timeout(struct ddc_service *ddc,
 		uint32_t timeout);
 
 void dal_ddc_service_write_scdc_data(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index 045138dbdccb..8b1f0ce6c2a7 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -28,8 +28,8 @@
 
 #define LINK_TRAINING_ATTEMPTS 4
 #define LINK_TRAINING_RETRY_DELAY 50 /* ms */
-#define LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD 32000 /*us*/
-#define LINK_AUX_DEFAULT_TIMEOUT_PERIOD 400 /*us*/
+#define LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD 3200 /*us*/
+#define LINK_AUX_DEFAULT_TIMEOUT_PERIOD 552 /*us*/
 
 struct dc_link;
 struct dc_stream_state;
@@ -57,10 +57,11 @@ void decide_link_settings(
 	struct dc_link_settings *link_setting);
 
 bool perform_link_training_with_retries(
-	struct dc_link *link,
 	const struct dc_link_settings *link_setting,
 	bool skip_video_pattern,
-	int attempts);
+	int attempts,
+	struct pipe_ctx *pipe_ctx,
+	enum signal_type signal);
 
 bool is_mst_supported(struct dc_link *link);
 
@@ -75,13 +76,13 @@ void dp_enable_mst_on_sink(struct dc_link *link, bool enable);
 enum dp_panel_mode dp_get_panel_mode(struct dc_link *link);
 void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode);
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+bool dp_overwrite_extended_receiver_cap(struct dc_link *link);
+
 void dp_set_fec_ready(struct dc_link *link, bool ready);
 void dp_set_fec_enable(struct dc_link *link, bool enable);
 bool dp_set_dsc_enable(struct pipe_ctx *pipe_ctx, bool enable);
 bool dp_set_dsc_pps_sdp(struct pipe_ctx *pipe_ctx, bool enable);
 void dp_set_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable);
 bool dp_update_dsc_config(struct pipe_ctx *pipe_ctx);
-#endif
 
 #endif /* __DC_LINK_DP_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h
index 45a07eeffbb6..45a07eeffbb6 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calc_math.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calc_math.h
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 026e6a2a2c44..ac530c057ddd 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -31,7 +31,6 @@
 #define DCN_MINIMUM_DISPCLK_Khz 100000
 #define DCN_MINIMUM_DPPCLK_Khz 100000
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 /* Constants */
 #define DDR4_DRAM_WIDTH   64
 #define WM_A 0
@@ -39,12 +38,10 @@
 #define WM_C 2
 #define WM_D 3
 #define WM_SET_COUNT 4
-#endif
 
 #define DCN_MINIMUM_DISPCLK_Khz 100000
 #define DCN_MINIMUM_DPPCLK_Khz 100000
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
 /* Will these bw structures be ASIC specific? */
 
 #define MAX_NUM_DPM_LVL		8
@@ -154,7 +151,6 @@ struct clk_bw_params {
 	struct clk_limit_table clk_table;
 	struct wm_table wm_table;
 };
-#endif
 /* Public interfaces */
 
 struct clk_states {
@@ -195,9 +191,8 @@ struct clk_mgr {
 	bool psr_allow_active_cache;
 	int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes
 	int dentist_vco_freq_khz;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_1
+	struct clk_state_registers_and_bypass boot_snapshot;
 	struct clk_bw_params *bw_params;
-#endif
 };
 
 /* forward declarations */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index a17a77192690..862952c0286a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -96,12 +96,10 @@ enum dentist_divider_range {
 	.MP1_SMN_C2PMSG_83 = mmMP1_SMN_C2PMSG_83, \
 	.MP1_SMN_C2PMSG_67 = mmMP1_SMN_C2PMSG_67
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define CLK_REG_LIST_NV10() \
 	SR(DENTIST_DISPCLK_CNTL), \
 	CLK_SRI(CLK3_CLK_PLL_REQ, CLK3, 0), \
 	CLK_SRI(CLK3_CLK2_DFS_CNTL, CLK3, 0)
-#endif
 
 #define CLK_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -120,7 +118,6 @@ enum dentist_divider_range {
 	CLK_SF(MP1_SMN_C2PMSG_83, CONTENT, mask_sh),\
 	CLK_SF(MP1_SMN_C2PMSG_91, CONTENT, mask_sh),
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define CLK_COMMON_MASK_SH_LIST_DCN20_BASE(mask_sh) \
 	CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh),\
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, mask_sh),\
@@ -130,7 +127,6 @@ enum dentist_divider_range {
 	CLK_COMMON_MASK_SH_LIST_DCN20_BASE(mask_sh),\
 	CLK_SF(CLK3_0_CLK3_CLK_PLL_REQ, FbMult_int, mask_sh),\
 	CLK_SF(CLK3_0_CLK3_CLK_PLL_REQ, FbMult_frac, mask_sh)
-#endif
 
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
@@ -143,30 +139,24 @@ enum dentist_divider_range {
  ****************** Clock Manager Private Structures ***********************************
  ***************************************************************************************
  */
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define CLK20_REG_FIELD_LIST(type) \
 	type DENTIST_DPPCLK_WDIVIDER; \
 	type DENTIST_DPPCLK_CHG_DONE; \
 	type FbMult_int; \
 	type FbMult_frac;
-#endif
 
 #define VBIOS_SMU_REG_FIELD_LIST(type) \
 	type CONTENT;
 
 struct clk_mgr_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	CLK20_REG_FIELD_LIST(uint8_t)
-#endif
 	VBIOS_SMU_REG_FIELD_LIST(uint32_t)
 };
 
 struct clk_mgr_mask {
 	CLK_REG_FIELD_LIST(uint32_t)
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	CLK20_REG_FIELD_LIST(uint32_t)
-#endif
 	VBIOS_SMU_REG_FIELD_LIST(uint32_t)
 };
 
@@ -174,10 +164,8 @@ struct clk_mgr_registers {
 	uint32_t DPREFCLK_CNTL;
 	uint32_t DENTIST_DISPCLK_CNTL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	uint32_t CLK3_CLK2_DFS_CNTL;
 	uint32_t CLK3_CLK_PLL_REQ;
-#endif
 
 	uint32_t MP1_SMN_C2PMSG_67;
 	uint32_t MP1_SMN_C2PMSG_83;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index c81a17aeaa25..c0dc1d0f5cae 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -52,7 +52,6 @@ struct dcn_hubbub_wm {
 	struct dcn_hubbub_wm_set sets[4];
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 enum dcn_hubbub_page_table_depth {
 	DCN_PAGE_TABLE_DEPTH_1_LEVEL,
 	DCN_PAGE_TABLE_DEPTH_2_LEVEL,
@@ -101,13 +100,11 @@ struct hubbub_addr_config {
 	} default_addrs;
 };
 
-#endif
 struct hubbub_funcs {
 	void (*update_dchub)(
 			struct hubbub *hubbub,
 			struct dchub_init_data *dh_data);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	int (*init_dchub_sys_ctx)(
 			struct hubbub *hubbub,
 			struct dcn_hubbub_phys_addr_config *pa_config);
@@ -116,7 +113,6 @@ struct hubbub_funcs {
 			struct dcn_hubbub_virt_addr_config *va_config,
 			int vmid);
 
-#endif
 	bool (*get_dcc_compression_cap)(struct hubbub *hubbub,
 			const struct dc_dcc_surface_param *input,
 			struct dc_surface_dcc_cap *output);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
index c68f0ce346c7..5315f1f86b21 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
@@ -52,6 +52,8 @@ struct dmcu {
 	enum dmcu_state dmcu_state;
 	struct dmcu_version dmcu_version;
 	unsigned int cached_wait_loop_number;
+	uint32_t psp_version;
+	bool auto_load_dmcu;
 };
 
 struct dmcu_funcs {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 474c7194a9f8..45ef390ae052 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -36,14 +36,10 @@ struct dpp {
 	struct dpp_caps *caps;
 	struct pwl_params regamma_params;
 	struct pwl_params degamma_params;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dpp_cursor_attributes cur_attr;
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct pwl_params shaper_params;
 	bool cm_bypass_mode;
-#endif
 };
 
 struct dpp_input_csc_matrix {
@@ -51,12 +47,31 @@ struct dpp_input_csc_matrix {
 	uint16_t regval[12];
 };
 
+static const struct dpp_input_csc_matrix dpp_input_csc_matrix[] = {
+	{COLOR_SPACE_SRGB,
+		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
+	{COLOR_SPACE_SRGB_LIMITED,
+		{0x2000, 0, 0, 0, 0, 0x2000, 0, 0, 0, 0, 0x2000, 0} },
+	{COLOR_SPACE_YCBCR601,
+		{0x2cdd, 0x2000, 0, 0xe991, 0xe926, 0x2000, 0xf4fd, 0x10ef,
+						0, 0x2000, 0x38b4, 0xe3a6} },
+	{COLOR_SPACE_YCBCR601_LIMITED,
+		{0x3353, 0x2568, 0, 0xe400, 0xe5dc, 0x2568, 0xf367, 0x1108,
+						0, 0x2568, 0x40de, 0xdd3a} },
+	{COLOR_SPACE_YCBCR709,
+		{0x3265, 0x2000, 0, 0xe6ce, 0xf105, 0x2000, 0xfa01, 0xa7d, 0,
+						0x2000, 0x3b61, 0xe24f} },
+
+	{COLOR_SPACE_YCBCR709_LIMITED,
+		{0x39a6, 0x2568, 0, 0xe0d6, 0xeedd, 0x2568, 0xf925, 0x9a8, 0,
+						0x2568, 0x43ee, 0xdbb2} }
+};
+
 struct dpp_grph_csc_adjustment {
 	struct fixed31_32 temperature_matrix[CSC_TEMPERATURE_MATRIX_SIZE];
 	enum graphics_gamut_adjust_type gamut_adjust_type;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct cnv_color_keyer_params {
 	int color_keyer_en;
 	int color_keyer_mode;
@@ -82,7 +97,6 @@ struct cnv_alpha_2bit_lut {
 	int lut2;
 	int lut3;
 };
-#endif
 
 struct dcn_dpp_state {
 	uint32_t is_enabled;
@@ -190,12 +204,8 @@ struct dpp_funcs {
 			enum surface_pixel_format format,
 			enum expansion_mode mode,
 			struct dc_csc_transform input_csc_color_matrix,
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 			enum dc_color_space input_color_space,
 			struct cnv_alpha_2bit_lut *alpha_2bit_lut);
-#else
-			enum dc_color_space input_color_space);
-#endif
 
 	void (*dpp_full_bypass)(struct dpp *dpp_base);
 
@@ -224,7 +234,6 @@ struct dpp_funcs {
 			bool dppclk_div,
 			bool enable);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool (*dpp_program_blnd_lut)(
 			struct dpp *dpp,
 			const struct pwl_params *params);
@@ -237,7 +246,6 @@ struct dpp_funcs {
 	void (*dpp_cnv_set_alpha_keyer)(
 			struct dpp *dpp_base,
 			struct cnv_color_keyer_params *color_keyer);
-#endif
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
index c6ff3d78b435..c59740084ebc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
@@ -22,7 +22,6 @@
  * Authors: AMD
  *
  */
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #ifndef __DAL_DSC_H__
 #define __DAL_DSC_H__
 
@@ -98,4 +97,3 @@ struct dsc_funcs {
 };
 
 #endif
-#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h
index ff1a07b35c85..459f95f52486 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dwb.h
@@ -51,20 +51,15 @@ enum dwb_source {
 	dwb_src_otg3,		/* for DCN1.x/DCN2.x */
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 /* DCN1.x, DCN2.x support 2 pipes */
-#else
-/* DCN1.x supports 2 pipes */
-#endif
 enum dwb_pipe {
 	dwb_pipe0 = 0,
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	dwb_pipe1,
 #endif
 	dwb_pipe_max_num,
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 enum dwb_frame_capture_enable {
 	DWB_FRAME_CAPTURE_DISABLE = 0,
 	DWB_FRAME_CAPTURE_ENABLE = 1,
@@ -77,9 +72,7 @@ enum wbscl_coef_filter_type_sel {
 	WBSCL_COEF_CHROMA_HORZ_FILTER = 3
 };
 
-#endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dwb_warmup_params {
 	bool	warmup_en;	/* false: normal mode, true: enable pattern generator */
 	bool	warmup_mode;	/* false: 420, true: 444 */
@@ -88,7 +81,6 @@ struct dwb_warmup_params {
 	int	warmup_width;	/* Pattern width (pixels) */
 	int	warmup_height;	/* Pattern height (lines) */
 };
-#endif
 
 struct dwb_caps {
 	enum dce_version hw_version;	/* DCN engine version. */
@@ -121,7 +113,8 @@ struct dwbc {
 	int wb_src_plane_inst;/*hubp, mpcc, inst*/
 	bool update_privacymask;
 	uint32_t mask_id;
-
+        int otg_inst;
+        bool mvc_cfg;
 };
 
 struct dwbc_funcs {
@@ -150,13 +143,11 @@ struct dwbc_funcs {
 		struct dwbc *dwbc,
 		bool is_new_content);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 	void (*set_warmup)(
 		struct dwbc *dwbc,
 		struct dwb_warmup_params *warmup_params);
 
-#endif
 
 	bool (*get_dwb_status)(
 		struct dwbc *dwbc);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 809b62b51a43..2cb8466e657b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -38,9 +38,7 @@ enum cursor_pitch {
 };
 
 enum cursor_lines_per_chunk {
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	CURSOR_LINE_PER_CHUNK_1 = 0, /* new for DCN2 */
-#endif
 	CURSOR_LINE_PER_CHUNK_2 = 1,
 	CURSOR_LINE_PER_CHUNK_4,
 	CURSOR_LINE_PER_CHUNK_8,
@@ -65,6 +63,26 @@ struct hubp {
 	bool power_gated;
 };
 
+struct surface_flip_registers {
+	uint32_t DCSURF_SURFACE_CONTROL;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C;
+	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_C;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C;
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS;
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS;
+	bool tmz_surface;
+	bool immediate;
+	uint8_t vmid;
+	bool grph_stereo;
+};
+
 struct hubp_funcs {
 	void (*hubp_setup)(
 			struct hubp *hubp,
@@ -86,6 +104,9 @@ struct hubp_funcs {
 			const struct rect *viewport,
 			const struct rect *viewport_c);
 
+	void (*apply_PLAT_54186_wa)(struct hubp *hubp,
+			const struct dc_plane_address *address);
+
 	bool (*hubp_program_surface_flip_and_addr)(
 		struct hubp *hubp,
 		const struct dc_plane_address *address,
@@ -139,7 +160,6 @@ struct hubp_funcs {
 	unsigned int (*hubp_get_underflow_status)(struct hubp *hubp);
 	void (*hubp_init)(struct hubp *hubp);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*dmdata_set_attributes)(
 			struct hubp *hubp,
 			const struct dc_dmdata_attributes *attr);
@@ -159,7 +179,13 @@ struct hubp_funcs {
 	void (*hubp_set_flip_control_surface_gsl)(
 		struct hubp *hubp,
 		bool enable);
-#endif
+
+	void (*validate_dml_output)(
+			struct hubp *hubp,
+			struct dc_context *ctx,
+			struct _vcs_dpi_display_rq_regs_st *dml_rq_regs,
+			struct _vcs_dpi_display_dlg_regs_st *dml_dlg_attr,
+			struct _vcs_dpi_display_ttu_regs_st *dml_ttu_attr);
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
index f82365e2d03c..75d419081e76 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hw_shared.h
@@ -36,9 +36,7 @@
 
 #define MAX_AUDIOS 7
 #define MAX_PIPES 6
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define MAX_DWB_PIPES	1
-#endif
 
 struct gamma_curve {
 	uint32_t offset;
@@ -81,7 +79,6 @@ struct pwl_result_data {
 	uint32_t delta_blue_reg;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_rgb {
 	uint32_t red;
 	uint32_t green;
@@ -110,7 +107,6 @@ struct tetrahedral_params {
 	bool use_12bits;
 
 };
-#endif
 
 /* arr_curve_points - regamma regions/segments specification
  * arr_points - beginning and end point specified separately (only one on DCE)
@@ -195,13 +191,11 @@ enum opp_regamma {
 	OPP_REGAMMA_USER
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 enum optc_dsc_mode {
 	OPTC_DSC_DISABLED = 0,
 	OPTC_DSC_ENABLED_444 = 1, /* 'RGB 444' or 'Simple YCbCr 4:2:2' (4:2:2 upsampled to 4:4:4) */
 	OPTC_DSC_ENABLED_NATIVE_SUBSAMPLED = 2 /* Native 4:2:2 or 4:2:0 */
 };
-#endif
 
 struct dc_bias_and_scale {
 	uint16_t scale_red;
@@ -224,12 +218,8 @@ enum test_pattern_mode {
 	TEST_PATTERN_MODE_VERTICALBARS,
 	TEST_PATTERN_MODE_HORIZONTALBARS,
 	TEST_PATTERN_MODE_SINGLERAMP_RGB,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	TEST_PATTERN_MODE_DUALRAMP_RGB,
 	TEST_PATTERN_MODE_XR_BIAS_RGB
-#else
-	TEST_PATTERN_MODE_DUALRAMP_RGB
-#endif
 };
 
 enum test_pattern_color_format {
@@ -255,6 +245,13 @@ enum controller_dp_test_pattern {
 	CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR
 };
 
+enum controller_dp_color_space {
+	CONTROLLER_DP_COLOR_SPACE_RGB,
+	CONTROLLER_DP_COLOR_SPACE_YCBCR601,
+	CONTROLLER_DP_COLOR_SPACE_YCBCR709,
+	CONTROLLER_DP_COLOR_SPACE_UDEFINED
+};
+
 enum dc_lut_mode {
 	LUT_BYPASS,
 	LUT_RAM_A,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
index b21909216fb6..fb748f082c56 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
@@ -113,26 +113,21 @@ struct link_encoder {
 	struct encoder_feature_support features;
 	enum transmitter transmitter;
 	enum hpd_source_id hpd_source;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	bool usbc_combo_phy;
-#endif
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct link_enc_state {
 
 		uint32_t dphy_fec_en;
 		uint32_t dphy_fec_ready_shadow;
 		uint32_t dphy_fec_active_status;
+		uint32_t dp_link_training_complete;
 
 };
-#endif
 
 struct link_encoder_funcs {
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*read_state)(
 			struct link_encoder *enc, struct link_enc_state *s);
-#endif
 	bool (*validate_output_with_stream)(
 		struct link_encoder *enc, const struct dc_stream_state *stream);
 	void (*hw_init)(struct link_encoder *enc);
@@ -174,7 +169,6 @@ struct link_encoder_funcs {
 	unsigned int (*get_dig_frontend)(struct link_encoder *enc);
 	void (*destroy)(struct link_encoder **enc);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*fec_set_enable)(struct link_encoder *enc,
 		bool enable);
 
@@ -182,7 +176,6 @@ struct link_encoder_funcs {
 		bool ready);
 
 	bool (*fec_is_active)(struct link_encoder *enc);
-#endif
 	bool (*is_in_alt_mode) (struct link_encoder *enc);
 
 	void (*get_max_link_cap)(struct link_encoder *enc,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
index 67b610d6d91f..2e2310f1901a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
@@ -40,11 +40,9 @@ struct cstate_pstate_watermarks_st {
 struct dcn_watermarks {
 	uint32_t pte_meta_urgent_ns;
 	uint32_t urgent_ns;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	uint32_t frac_urg_bw_nom;
 	uint32_t frac_urg_bw_flip;
 	int32_t urgent_latency_ns;
-#endif
 	struct cstate_pstate_watermarks_st cstate_pstate;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
index 58826be81395..094afc4c8173 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mpc.h
@@ -31,9 +31,7 @@
 #define MAX_MPCC 6
 #define MAX_OPP 6
 
-#if   defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define MAX_DWB		1
-#endif
 
 enum mpc_output_csc_mode {
 	MPC_OUTPUT_CSC_DISABLE = 0,
@@ -66,14 +64,12 @@ struct mpcc_blnd_cfg {
 	int global_alpha;
 	bool overlap_only;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	/* MPCC top/bottom gain settings */
 	int bottom_gain_mode;
 	int background_color_bpc;
 	int top_gain;
 	int bottom_inside_gain;
 	int bottom_outside_gain;
-#endif
 };
 
 struct mpcc_sm_cfg {
@@ -90,7 +86,6 @@ struct mpcc_sm_cfg {
 	int force_next_field_polarity;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct mpc_denorm_clamp {
 	int clamp_max_r_cr;
 	int clamp_min_r_cr;
@@ -99,7 +94,6 @@ struct mpc_denorm_clamp {
 	int clamp_max_b_cb;
 	int clamp_min_b_cb;
 };
-#endif
 
 /*
  * MPCC connection and blending configuration for a single MPCC instance.
@@ -126,10 +120,8 @@ struct mpc {
 	struct dc_context *ctx;
 
 	struct mpcc mpcc_array[MAX_MPCC];
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct pwl_params blender_params;
 	bool cm_bypass_mode;
-#endif
 };
 
 struct mpcc_state {
@@ -230,7 +222,6 @@ struct mpc_funcs {
 		struct mpc *mpc,
 		struct mpc_tree *tree);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*set_denorm)(struct mpc *mpc,
 			int opp_id,
 			enum dc_color_depth output_depth);
@@ -258,7 +249,6 @@ struct mpc_funcs {
 			struct mpc *mpc,
 			int mpcc_id,
 			bool power_on);
-#endif
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index 18def2b6fafe..7575564b2265 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -263,9 +263,7 @@ struct oppbuf_params {
 	enum oppbuf_display_segmentation mso_segmentation;
 	uint32_t mso_overlap_pixel_num;
 	uint32_t pixel_repetition;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	uint32_t num_segment_padded_pixels;
-#endif
 };
 
 struct opp_funcs {
@@ -305,10 +303,10 @@ struct opp_funcs {
 			struct output_pixel_processor *opp,
 			bool enable);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*opp_set_disp_pattern_generator)(
 			struct output_pixel_processor *opp,
 			enum controller_dp_test_pattern test_pattern,
+			enum controller_dp_color_space color_space,
 			enum dc_color_depth color_depth,
 			const struct tg_color *solid_color,
 			int width,
@@ -324,7 +322,6 @@ struct opp_funcs {
 	void (*opp_program_left_edge_extra_pixel)(
 			struct output_pixel_processor *opp,
 			bool count);
-#endif
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
index 6305e388612a..351b387ad606 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
@@ -65,13 +65,11 @@ struct audio_clock_info {
 	uint32_t cts_48khz;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 enum dynamic_metadata_mode {
 	dmdata_dp,
 	dmdata_hdmi,
 	dmdata_dolby_vision
 };
-#endif
 
 struct encoder_info_frame {
 	/* auxiliary video information */
@@ -90,9 +88,7 @@ struct encoder_info_frame {
 struct encoder_unblank_param {
 	struct dc_link_settings link_settings;
 	struct dc_crtc_timing timing;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	int opp_cnt;
-#endif
 };
 
 struct encoder_set_dp_phy_pattern_param {
@@ -109,7 +105,6 @@ struct stream_encoder {
 	enum engine_id id;
 };
 
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct enc_state {
 	uint32_t dsc_mode;  // DISABLED  0; 1 or 2 indicate enabled state.
 	uint32_t dsc_slice_width;
@@ -119,13 +114,13 @@ struct enc_state {
 	uint32_t sec_gsp_pps_enable;
 	uint32_t sec_stream_enable;
 };
-#endif
 
 struct stream_encoder_funcs {
 	void (*dp_set_stream_attribute)(
 		struct stream_encoder *enc,
 		struct dc_crtc_timing *crtc_timing,
 		enum dc_color_space output_color_space,
+		bool use_vsc_sdp_for_colorimetry,
 		uint32_t enable_sdp_splitting);
 
 	void (*hdmi_set_stream_attribute)(
@@ -219,8 +214,6 @@ struct stream_encoder_funcs {
 		enum dc_pixel_encoding *encoding,
 		enum dc_color_depth *depth);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*enc_read_state)(struct stream_encoder *enc, struct enc_state *s);
 
 	void (*dp_set_dsc_config)(
@@ -232,7 +225,6 @@ struct stream_encoder_funcs {
 	void (*dp_set_dsc_pps_info_packet)(struct stream_encoder *enc,
 				bool enable,
 				uint8_t *dsc_packed_pps);
-#endif
 
 	void (*set_dynamic_metadata)(struct stream_encoder *enc,
 			bool enable,
@@ -242,7 +234,6 @@ struct stream_encoder_funcs {
 	void (*dp_set_odm_combine)(
 		struct stream_encoder *enc,
 		bool odm_combine);
-#endif
 };
 
 #endif /* STREAM_ENCODER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 27c73caf74ee..e5e7d94026fc 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -195,10 +195,8 @@ struct timing_generator_funcs {
 	void (*lock)(struct timing_generator *tg);
 	void (*lock_doublebuffer_disable)(struct timing_generator *tg);
 	void (*lock_doublebuffer_enable)(struct timing_generator *tg);
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void(*triplebuffer_unlock)(struct timing_generator *tg);
 	void(*triplebuffer_lock)(struct timing_generator *tg);
-#endif
 	void (*enable_reset_trigger)(struct timing_generator *tg,
 				     int source_tg_inst);
 	void (*enable_crtc_reset)(struct timing_generator *tg,
@@ -210,7 +208,8 @@ struct timing_generator_funcs {
 					bool enable, const struct dc_crtc_timing *timing);
 	void (*set_drr)(struct timing_generator *tg, const struct drr_params *params);
 	void (*set_static_screen_control)(struct timing_generator *tg,
-							uint32_t value);
+						uint32_t event_triggers,
+						uint32_t num_frames);
 	void (*set_test_pattern)(
 		struct timing_generator *tg,
 		enum controller_dp_test_pattern test_pattern,
@@ -235,7 +234,6 @@ struct timing_generator_funcs {
 	bool (*is_optc_underflow_occurred)(struct timing_generator *tg);
 	void (*clear_optc_underflow)(struct timing_generator *tg);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	void (*set_dwb_source)(struct timing_generator *optc,
 		uint32_t dwb_pipe_inst);
 
@@ -243,7 +241,6 @@ struct timing_generator_funcs {
 			uint32_t *num_of_input_segments,
 			uint32_t *seg0_src_sel,
 			uint32_t *seg1_src_sel);
-#endif
 
 	/**
 	 * Configure CRCs for the given timing generator. Return false if TG is
@@ -267,13 +264,10 @@ struct timing_generator_funcs {
 	void (*set_vtg_params)(struct timing_generator *optc,
 			const struct dc_crtc_timing *dc_crtc_timing);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*set_dsc_config)(struct timing_generator *optc,
 			       enum optc_dsc_mode dsc_mode,
 			       uint32_t dsc_bytes_per_pixel,
 			       uint32_t dsc_slice_width);
-#endif
 	void (*set_odm_bypass)(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing);
 	void (*set_odm_combine)(struct timing_generator *optc, int *opp_id, int opp_cnt,
 			struct dc_crtc_timing *timing);
@@ -281,7 +275,6 @@ struct timing_generator_funcs {
 	void (*set_gsl_source_select)(struct timing_generator *optc,
 			int group_idx,
 			uint32_t gsl_ready_signal);
-#endif
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index d39c1e11def5..209118f9f193 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -32,326 +32,160 @@
 #include "inc/hw/link_encoder.h"
 #include "core_status.h"
 
-enum pipe_gating_control {
-	PIPE_GATING_CONTROL_DISABLE = 0,
-	PIPE_GATING_CONTROL_ENABLE,
-	PIPE_GATING_CONTROL_INIT
-};
-
 enum vline_select {
 	VLINE0,
 	VLINE1
 };
 
-struct dce_hwseq_wa {
-	bool blnd_crtc_trigger;
-	bool DEGVIDCN10_253;
-	bool false_optc_underflow;
-	bool DEGVIDCN10_254;
-	bool DEGVIDCN21;
-};
-
-struct hwseq_wa_state {
-	bool DEGVIDCN10_253_applied;
-};
-
-struct dce_hwseq {
-	struct dc_context *ctx;
-	const struct dce_hwseq_registers *regs;
-	const struct dce_hwseq_shift *shifts;
-	const struct dce_hwseq_mask *masks;
-	struct dce_hwseq_wa wa;
-	struct hwseq_wa_state wa_state;
-};
-
 struct pipe_ctx;
 struct dc_state;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_stream_status;
 struct dc_writeback_info;
-#endif
 struct dchub_init_data;
-struct dc_static_screen_events;
+struct dc_static_screen_params;
 struct resource_pool;
-struct resource_context;
-struct stream_resource;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 struct dc_phy_addr_space_config;
 struct dc_virtual_addr_space_config;
-#endif
-struct hubp;
 struct dpp;
+struct dce_hwseq;
 
 struct hw_sequencer_funcs {
+	/* Embedded Display Related */
+	void (*edp_power_control)(struct dc_link *link, bool enable);
+	void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up);
 
-	void (*disable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*enable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
+	/* Pipe Programming Related */
 	void (*init_hw)(struct dc *dc);
-
-	void (*init_pipes)(struct dc *dc, struct dc_state *context);
-
-	enum dc_status (*apply_ctx_to_hw)(
-			struct dc *dc, struct dc_state *context);
-
-	void (*reset_hw_ctx_wrap)(
-			struct dc *dc, struct dc_state *context);
-
-	void (*apply_ctx_for_surface)(
-			struct dc *dc,
+	void (*enable_accelerated_mode)(struct dc *dc,
+			struct dc_state *context);
+	enum dc_status (*apply_ctx_to_hw)(struct dc *dc,
+			struct dc_state *context);
+	void (*disable_plane)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*apply_ctx_for_surface)(struct dc *dc,
 			const struct dc_stream_state *stream,
-			int num_planes,
+			int num_planes, struct dc_state *context);
+	void (*program_front_end_for_ctx)(struct dc *dc,
 			struct dc_state *context);
-
-	void (*program_gamut_remap)(
+	void (*update_plane_addr)(const struct dc *dc,
 			struct pipe_ctx *pipe_ctx);
-
-	void (*program_output_csc)(struct dc *dc,
-			struct pipe_ctx *pipe_ctx,
-			enum dc_color_space colorspace,
-			uint16_t *matrix,
-			int opp_id);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	void (*program_front_end_for_ctx)(
-			struct dc *dc,
-			struct dc_state *context);
-	void (*program_triplebuffer)(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		bool enableTripleBuffer);
-	void (*set_flip_control_gsl)(
-		struct pipe_ctx *pipe_ctx,
-		bool flip_immediate);
-#endif
-
-	void (*update_plane_addr)(
-		const struct dc *dc,
-		struct pipe_ctx *pipe_ctx);
-
-	void (*plane_atomic_disconnect)(
-		struct dc *dc,
-		struct pipe_ctx *pipe_ctx);
-
-	void (*update_dchub)(
-		struct dce_hwseq *hws,
-		struct dchub_init_data *dh_data);
-
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-	int (*init_sys_ctx)(
-			struct dce_hwseq *hws,
-			struct dc *dc,
-			struct dc_phy_addr_space_config *pa_config);
-	void (*init_vm_ctx)(
-			struct dce_hwseq *hws,
-			struct dc *dc,
-			struct dc_virtual_addr_space_config *va_config,
-			int vmid);
-#endif
-	void (*update_mpcc)(
-		struct dc *dc,
-		struct pipe_ctx *pipe_ctx);
-
-	void (*update_pending_status)(
+	void (*update_dchub)(struct dce_hwseq *hws,
+			struct dchub_init_data *dh_data);
+	void (*wait_for_mpcc_disconnect)(struct dc *dc,
+			struct resource_pool *res_pool,
 			struct pipe_ctx *pipe_ctx);
-
-	bool (*set_input_transfer_func)(
-				struct pipe_ctx *pipe_ctx,
-				const struct dc_plane_state *plane_state);
-
-	bool (*set_output_transfer_func)(
-				struct pipe_ctx *pipe_ctx,
-				const struct dc_stream_state *stream);
-
-	void (*power_down)(struct dc *dc);
-
-	void (*enable_accelerated_mode)(struct dc *dc, struct dc_state *context);
-
-	void (*enable_timing_synchronization)(
-			struct dc *dc,
-			int group_index,
-			int group_size,
-			struct pipe_ctx *grouped_pipes[]);
-
-	void (*enable_per_frame_crtc_position_reset)(
-			struct dc *dc,
-			int group_size,
+	void (*program_triplebuffer)(const struct dc *dc,
+		struct pipe_ctx *pipe_ctx, bool enableTripleBuffer);
+	void (*update_pending_status)(struct pipe_ctx *pipe_ctx);
+
+	/* Pipe Lock Related */
+	void (*pipe_control_lock_global)(struct dc *dc,
+			struct pipe_ctx *pipe, bool lock);
+	void (*pipe_control_lock)(struct dc *dc,
+			struct pipe_ctx *pipe, bool lock);
+	void (*set_flip_control_gsl)(struct pipe_ctx *pipe_ctx,
+			bool flip_immediate);
+
+	/* Timing Related */
+	void (*get_position)(struct pipe_ctx **pipe_ctx, int num_pipes,
+			struct crtc_position *position);
+	int (*get_vupdate_offset_from_vsync)(struct pipe_ctx *pipe_ctx);
+	void (*enable_per_frame_crtc_position_reset)(struct dc *dc,
+			int group_size, struct pipe_ctx *grouped_pipes[]);
+	void (*enable_timing_synchronization)(struct dc *dc,
+			int group_index, int group_size,
 			struct pipe_ctx *grouped_pipes[]);
+	void (*setup_periodic_interrupt)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			enum vline_select vline);
+	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
+			unsigned int vmin, unsigned int vmax,
+			unsigned int vmid, unsigned int vmid_frame_number);
+	void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx,
+			int num_pipes,
+			const struct dc_static_screen_params *events);
 
-	void (*enable_display_pipe_clock_gating)(
-					struct dc_context *ctx,
-					bool clock_gating);
-
-	bool (*enable_display_power_gating)(
-					struct dc *dc,
-					uint8_t controller_id,
-					struct dc_bios *dcb,
-					enum pipe_gating_control power_gating);
-
-	void (*disable_plane)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*update_info_frame)(struct pipe_ctx *pipe_ctx);
-
-	void (*send_immediate_sdp_message)(
-				struct pipe_ctx *pipe_ctx,
-				const uint8_t *custom_sdp_message,
-				unsigned int sdp_message_size);
-
+	/* Stream Related */
 	void (*enable_stream)(struct pipe_ctx *pipe_ctx);
-
 	void (*disable_stream)(struct pipe_ctx *pipe_ctx);
-
+	void (*blank_stream)(struct pipe_ctx *pipe_ctx);
 	void (*unblank_stream)(struct pipe_ctx *pipe_ctx,
 			struct dc_link_settings *link_settings);
 
-	void (*blank_stream)(struct pipe_ctx *pipe_ctx);
-
-	void (*enable_audio_stream)(struct pipe_ctx *pipe_ctx);
+	/* Bandwidth Related */
+	void (*prepare_bandwidth)(struct dc *dc, struct dc_state *context);
+	bool (*update_bandwidth)(struct dc *dc, struct dc_state *context);
+	void (*optimize_bandwidth)(struct dc *dc, struct dc_state *context);
 
-	void (*disable_audio_stream)(struct pipe_ctx *pipe_ctx);
-
-	void (*pipe_control_lock)(
-				struct dc *dc,
-				struct pipe_ctx *pipe,
-				bool lock);
-
-	void (*pipe_control_lock_global)(
-				struct dc *dc,
-				struct pipe_ctx *pipe,
-				bool lock);
-	void (*blank_pixel_data)(
-			struct dc *dc,
+	/* Infopacket Related */
+	void (*set_avmute)(struct pipe_ctx *pipe_ctx, bool enable);
+	void (*send_immediate_sdp_message)(
 			struct pipe_ctx *pipe_ctx,
-			bool blank);
-
-	void (*prepare_bandwidth)(
-			struct dc *dc,
-			struct dc_state *context);
-	void (*optimize_bandwidth)(
-			struct dc *dc,
-			struct dc_state *context);
-
-	void (*exit_optimized_pwr_state)(
-			const struct dc *dc,
-			struct dc_state *context);
-	void (*optimize_pwr_state)(
-			const struct dc *dc,
-			struct dc_state *context);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	bool (*update_bandwidth)(
-			struct dc *dc,
-			struct dc_state *context);
+			const uint8_t *custom_sdp_message,
+			unsigned int sdp_message_size);
+	void (*update_info_frame)(struct pipe_ctx *pipe_ctx);
+	void (*set_dmdata_attributes)(struct pipe_ctx *pipe);
 	void (*program_dmdata_engine)(struct pipe_ctx *pipe_ctx);
 	bool (*dmdata_status_done)(struct pipe_ctx *pipe_ctx);
-#endif
-
-	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
-			unsigned int vmin, unsigned int vmax,
-			unsigned int vmid, unsigned int vmid_frame_number);
-
-	void (*get_position)(struct pipe_ctx **pipe_ctx, int num_pipes,
-			struct crtc_position *position);
-
-	void (*set_static_screen_control)(struct pipe_ctx **pipe_ctx,
-			int num_pipes, const struct dc_static_screen_events *events);
-
-	enum dc_status (*enable_stream_timing)(
-			struct pipe_ctx *pipe_ctx,
-			struct dc_state *context,
-			struct dc *dc);
-
-	void (*setup_stereo)(
-			struct pipe_ctx *pipe_ctx,
-			struct dc *dc);
-
-	void (*set_avmute)(struct pipe_ctx *pipe_ctx, bool enable);
-
-	void (*log_hw_state)(struct dc *dc,
-		struct dc_log_buffer_ctx *log_ctx);
-	void (*get_hw_state)(struct dc *dc, char *pBuf, unsigned int bufSize, unsigned int mask);
-	void (*clear_status_bits)(struct dc *dc, unsigned int mask);
-
-	void (*wait_for_mpcc_disconnect)(struct dc *dc,
-			struct resource_pool *res_pool,
-			struct pipe_ctx *pipe_ctx);
-
-	void (*edp_power_control)(
-			struct dc_link *link,
-			bool enable);
-	void (*edp_backlight_control)(
-			struct dc_link *link,
-			bool enable);
-	void (*edp_wait_for_hpd_ready)(struct dc_link *link, bool power_up);
 
+	/* Cursor Related */
 	void (*set_cursor_position)(struct pipe_ctx *pipe);
 	void (*set_cursor_attribute)(struct pipe_ctx *pipe);
 	void (*set_cursor_sdr_white_level)(struct pipe_ctx *pipe);
 
-	void (*setup_periodic_interrupt)(struct pipe_ctx *pipe_ctx, enum vline_select vline);
-	void (*setup_vupdate_interrupt)(struct pipe_ctx *pipe_ctx);
-	bool (*did_underflow_occur)(struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*init_blank)(struct dc *dc, struct timing_generator *tg);
-	void (*disable_vga)(struct dce_hwseq *hws);
-	void (*bios_golden_init)(struct dc *dc);
-	void (*plane_atomic_power_down)(struct dc *dc,
-			struct dpp *dpp,
-			struct hubp *hubp);
-
-	void (*plane_atomic_disable)(
-			struct dc *dc, struct pipe_ctx *pipe_ctx);
-
-	void (*enable_power_gating_plane)(
-		struct dce_hwseq *hws,
-		bool enable);
-
-	void (*dpp_pg_control)(
-			struct dce_hwseq *hws,
-			unsigned int dpp_inst,
-			bool power_on);
-
-	void (*hubp_pg_control)(
-			struct dce_hwseq *hws,
-			unsigned int hubp_inst,
-			bool power_on);
-
-	void (*dsc_pg_control)(
-			struct dce_hwseq *hws,
-			unsigned int dsc_inst,
-			bool power_on);
-
+	/* Colour Related */
+	void (*program_gamut_remap)(struct pipe_ctx *pipe_ctx);
+	void (*program_output_csc)(struct dc *dc, struct pipe_ctx *pipe_ctx,
+			enum dc_color_space colorspace,
+			uint16_t *matrix, int opp_id);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
-	void (*update_odm)(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx);
-	void (*program_all_writeback_pipes_in_tree)(
+	/* VM Related */
+	int (*init_sys_ctx)(struct dce_hwseq *hws,
 			struct dc *dc,
-			const struct dc_stream_state *stream,
-			struct dc_state *context);
+			struct dc_phy_addr_space_config *pa_config);
+	void (*init_vm_ctx)(struct dce_hwseq *hws,
+			struct dc *dc,
+			struct dc_virtual_addr_space_config *va_config,
+			int vmid);
+
+	/* Writeback Related */
 	void (*update_writeback)(struct dc *dc,
-			const struct dc_stream_status *stream_status,
 			struct dc_writeback_info *wb_info,
 			struct dc_state *context);
 	void (*enable_writeback)(struct dc *dc,
-			const struct dc_stream_status *stream_status,
 			struct dc_writeback_info *wb_info,
 			struct dc_state *context);
 	void (*disable_writeback)(struct dc *dc,
 			unsigned int dwb_pipe_inst);
-#endif
-	enum dc_status (*set_clock)(struct dc *dc,
-			enum dc_clock_type clock_type,
-			uint32_t clk_khz,
-			uint32_t stepping);
 
-	void (*get_clock)(struct dc *dc,
+	bool (*mmhubbub_warmup)(struct dc *dc,
+			unsigned int num_dwb,
+			struct dc_writeback_info *wb_info);
+
+	/* Clock Related */
+	enum dc_status (*set_clock)(struct dc *dc,
 			enum dc_clock_type clock_type,
+			uint32_t clk_khz, uint32_t stepping);
+	void (*get_clock)(struct dc *dc, enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg);
+	void (*optimize_pwr_state)(const struct dc *dc,
+			struct dc_state *context);
+	void (*exit_optimized_pwr_state)(const struct dc *dc,
+			struct dc_state *context);
+
+	/* Audio Related */
+	void (*enable_audio_stream)(struct pipe_ctx *pipe_ctx);
+	void (*disable_audio_stream)(struct pipe_ctx *pipe_ctx);
+
+	/* Stereo 3D Related */
+	void (*setup_stereo)(struct pipe_ctx *pipe_ctx, struct dc *dc);
+
+	/* HW State Logging Related */
+	void (*log_hw_state)(struct dc *dc, struct dc_log_buffer_ctx *log_ctx);
+	void (*get_hw_state)(struct dc *dc, char *pBuf,
+			unsigned int bufSize, unsigned int mask);
+	void (*clear_status_bits)(struct dc *dc, unsigned int mask);
+
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
-	bool (*s0i3_golden_init_wa)(struct dc *dc);
-#endif
 };
 
 void color_space_to_black_color(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
new file mode 100644
index 000000000000..ecf566378ccd
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -0,0 +1,156 @@
+/*
+ * Copyright 2015 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HW_SEQUENCER_PRIVATE_H__
+#define __DC_HW_SEQUENCER_PRIVATE_H__
+
+#include "dc_types.h"
+
+enum pipe_gating_control {
+	PIPE_GATING_CONTROL_DISABLE = 0,
+	PIPE_GATING_CONTROL_ENABLE,
+	PIPE_GATING_CONTROL_INIT
+};
+
+struct dce_hwseq_wa {
+	bool blnd_crtc_trigger;
+	bool DEGVIDCN10_253;
+	bool false_optc_underflow;
+	bool DEGVIDCN10_254;
+	bool DEGVIDCN21;
+};
+
+struct hwseq_wa_state {
+	bool DEGVIDCN10_253_applied;
+};
+
+struct pipe_ctx;
+struct dc_state;
+struct dc_stream_status;
+struct dc_writeback_info;
+struct dchub_init_data;
+struct dc_static_screen_params;
+struct resource_pool;
+struct resource_context;
+struct stream_resource;
+struct dc_phy_addr_space_config;
+struct dc_virtual_addr_space_config;
+struct hubp;
+struct dpp;
+struct dce_hwseq;
+struct timing_generator;
+struct tg_color;
+struct output_pixel_processor;
+
+struct hwseq_private_funcs {
+
+	void (*disable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*enable_stream_gating)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*init_pipes)(struct dc *dc, struct dc_state *context);
+	void (*reset_hw_ctx_wrap)(struct dc *dc, struct dc_state *context);
+	void (*update_plane_addr)(const struct dc *dc,
+			struct pipe_ctx *pipe_ctx);
+	void (*plane_atomic_disconnect)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx);
+	void (*update_mpcc)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	bool (*set_input_transfer_func)(struct dc *dc,
+				struct pipe_ctx *pipe_ctx,
+				const struct dc_plane_state *plane_state);
+	bool (*set_output_transfer_func)(struct dc *dc,
+				struct pipe_ctx *pipe_ctx,
+				const struct dc_stream_state *stream);
+	void (*power_down)(struct dc *dc);
+	void (*enable_display_pipe_clock_gating)(struct dc_context *ctx,
+					bool clock_gating);
+	bool (*enable_display_power_gating)(struct dc *dc,
+					uint8_t controller_id,
+					struct dc_bios *dcb,
+					enum pipe_gating_control power_gating);
+	void (*blank_pixel_data)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			bool blank);
+	enum dc_status (*enable_stream_timing)(
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context,
+			struct dc *dc);
+	void (*edp_backlight_control)(struct dc_link *link,
+			bool enable);
+	void (*setup_vupdate_interrupt)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx);
+	bool (*did_underflow_occur)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*init_blank)(struct dc *dc, struct timing_generator *tg);
+	void (*disable_vga)(struct dce_hwseq *hws);
+	void (*bios_golden_init)(struct dc *dc);
+	void (*plane_atomic_power_down)(struct dc *dc,
+			struct dpp *dpp,
+			struct hubp *hubp);
+	void (*plane_atomic_disable)(struct dc *dc, struct pipe_ctx *pipe_ctx);
+	void (*enable_power_gating_plane)(struct dce_hwseq *hws,
+		bool enable);
+	void (*dpp_pg_control)(struct dce_hwseq *hws,
+			unsigned int dpp_inst,
+			bool power_on);
+	void (*hubp_pg_control)(struct dce_hwseq *hws,
+			unsigned int hubp_inst,
+			bool power_on);
+	void (*dsc_pg_control)(struct dce_hwseq *hws,
+			unsigned int dsc_inst,
+			bool power_on);
+	void (*update_odm)(struct dc *dc, struct dc_state *context,
+			struct pipe_ctx *pipe_ctx);
+	void (*program_all_writeback_pipes_in_tree)(struct dc *dc,
+			const struct dc_stream_state *stream,
+			struct dc_state *context);
+	bool (*s0i3_golden_init_wa)(struct dc *dc);
+	void (*get_surface_visual_confirm_color)(
+			const struct pipe_ctx *pipe_ctx,
+			struct tg_color *color);
+	void (*get_hdr_visual_confirm_color)(struct pipe_ctx *pipe_ctx,
+			struct tg_color *color);
+	void (*set_hdr_multiplier)(struct pipe_ctx *pipe_ctx);
+	void (*verify_allow_pstate_change_high)(struct dc *dc);
+	void (*program_pipe)(struct dc *dc,
+			struct pipe_ctx *pipe_ctx,
+			struct dc_state *context);
+	bool (*wait_for_blank_complete)(struct output_pixel_processor *opp);
+	void (*dccg_init)(struct dce_hwseq *hws);
+	bool (*set_blend_lut)(struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+	bool (*set_shaper_3dlut)(struct pipe_ctx *pipe_ctx,
+			const struct dc_plane_state *plane_state);
+};
+
+struct dce_hwseq {
+	struct dc_context *ctx;
+	const struct dce_hwseq_registers *regs;
+	const struct dce_hwseq_shift *shifts;
+	const struct dce_hwseq_mask *masks;
+	struct dce_hwseq_wa wa;
+	struct hwseq_wa_state wa_state;
+	struct hwseq_private_funcs funcs;
+
+};
+
+#endif /* __DC_HW_SEQUENCER_PRIVATE_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h
index 4eff5d38a2f9..9af7ee5bc8ee 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h
@@ -60,11 +60,13 @@ void dp_disable_link_phy_mst(struct dc_link *link, enum signal_type signal);
 
 bool dp_set_hw_training_pattern(
 	struct dc_link *link,
-	enum dc_dp_training_pattern pattern);
+	enum dc_dp_training_pattern pattern,
+	uint32_t offset);
 
 void dp_set_hw_lane_settings(
 	struct dc_link *link,
-	const struct link_training_settings *link_settings);
+	const struct link_training_settings *link_settings,
+	uint32_t offset);
 
 void dp_set_hw_test_pattern(
 	struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
index 8503d9cc4763..2470405e996b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
@@ -458,7 +458,14 @@ uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
 #define IX_REG_READ(index_reg_name, data_reg_name, index) \
 		generic_read_indirect_reg(CTX, REG(index_reg_name), REG(data_reg_name), IND_REG(index))
 
+#define IX_REG_GET_N(index_reg_name, data_reg_name, index, n, ...) \
+		generic_indirect_reg_get(CTX, REG(index_reg_name), REG(data_reg_name), \
+				IND_REG(index), \
+				n, __VA_ARGS__)
 
+#define IX_REG_GET(index_reg_name, data_reg_name, index, field, val) \
+		IX_REG_GET_N(index_reg_name, data_reg_name, index, 1, \
+				FN(data_reg_name, field), val)
 
 #define IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, n, ...)	\
 		generic_indirect_reg_update_ex(CTX, \
@@ -479,10 +486,35 @@ uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
 		uint32_t index);
 
+uint32_t generic_indirect_reg_get(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t *field_value1,
+		...);
+
 uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
 		uint32_t addr_index, uint32_t addr_data,
 		uint32_t index, uint32_t reg_val, int n,
 		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
 		...);
 
+/* register offload macros
+ *
+ * instead of MMIO to register directly, in some cases we want
+ * to gather register sequence and execute the register sequence
+ * from another thread so we optimize time required for lengthy ops
+ */
+
+/* start gathering register sequence */
+#define REG_SEQ_START() \
+	reg_sequence_start_gather(CTX)
+
+/* start execution of register sequence gathered since REG_SEQ_START */
+#define REG_SEQ_SUBMIT() \
+	reg_sequence_start_execute(CTX)
+
+/* wait for the last REG_SEQ_SUBMIT to finish */
+#define REG_SEQ_WAIT_DONE() \
+	reg_sequence_wait_done(CTX)
+
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_REG_HELPER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index bef224bf803e..5ae8ada154ef 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -46,12 +46,8 @@ struct resource_caps {
 	int num_pll;
 	int num_dwb;
 	int num_ddc;
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	int num_vmid;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	int num_dsc;
-#endif
-#endif
 };
 
 struct resource_straps {
@@ -181,4 +177,6 @@ void update_audio_usage(
 
 unsigned int resource_pixel_format_to_bpp(enum surface_pixel_format format);
 
+void get_audio_check(struct audio_info *aud_modes,
+	struct audio_check *aud_chk);
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index ea75420fc876..0f682ac53bb2 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -60,27 +60,23 @@ AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCE12)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_DRM_AMD_DC_DCN
 IRQ_DCN1 = irq_service_dcn10.o
 
 AMD_DAL_IRQ_DCN1 = $(addprefix $(AMDDALPATH)/dc/irq/dcn10/,$(IRQ_DCN1))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCN1)
-endif
 ###############################################################################
 # DCN 20
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN2_0
 IRQ_DCN2 = irq_service_dcn20.o
 
 AMD_DAL_IRQ_DCN2 = $(addprefix $(AMDDALPATH)/dc/irq/dcn20/,$(IRQ_DCN2))
 
 AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCN2)
-endif
 ###############################################################################
 # DCN 21
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN2_1
 IRQ_DCN21 = irq_service_dcn21.o
 
 AMD_DAL_IRQ_DCN21= $(addprefix $(AMDDALPATH)/dc/irq/dcn21/,$(IRQ_DCN21))
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c
index 1a581c464345..378cc11aa047 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce110/irq_service_dce110.c
@@ -204,7 +204,7 @@ bool dce110_vblank_set(struct irq_service *irq_service,
 		       bool enable)
 {
 	struct dc_context *dc_ctx = irq_service->ctx;
-	struct dc *core_dc = irq_service->ctx->dc;
+	struct dc *dc = irq_service->ctx->dc;
 	enum dc_irq_source dal_irq_src =
 			dc_interrupt_to_irq_source(irq_service->ctx->dc,
 						   info->src_id,
@@ -212,7 +212,7 @@ bool dce110_vblank_set(struct irq_service *irq_service,
 	uint8_t pipe_offset = dal_irq_src - IRQ_TYPE_VBLANK;
 
 	struct timing_generator *tg =
-			core_dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg;
+			dc->current_state->res_ctx.pipe_ctx[pipe_offset].stream_res.tg;
 
 	if (enable) {
 		if (!tg || !tg->funcs->arm_vert_intr(tg, 2)) {
@@ -403,7 +403,7 @@ static const struct irq_service_funcs irq_service_funcs_dce110 = {
 		.to_dal_irq_source = to_dal_irq_source_dce110
 };
 
-static void construct(struct irq_service *irq_service,
+static void dce110_irq_construct(struct irq_service *irq_service,
 		      struct irq_service_init_data *init_data)
 {
 	dal_irq_service_construct(irq_service, init_data);
@@ -421,6 +421,6 @@ dal_irq_service_dce110_create(struct irq_service_init_data *init_data)
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dce110_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c b/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
index 15380336cb51..2fe4703395f3 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce120/irq_service_dce120.c
@@ -273,7 +273,7 @@ static const struct irq_service_funcs irq_service_funcs_dce120 = {
 		.to_dal_irq_source = to_dal_irq_source_dce110
 };
 
-static void construct(
+static void dce120_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -292,6 +292,6 @@ struct irq_service *dal_irq_service_dce120_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dce120_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c b/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c
index 281fee8ad1e5..17e426b80a00 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dce80/irq_service_dce80.c
@@ -283,7 +283,7 @@ static const struct irq_service_funcs irq_service_funcs_dce80 = {
 		.to_dal_irq_source = to_dal_irq_source_dce110
 };
 
-static void construct(
+static void dce80_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -302,7 +302,7 @@ struct irq_service *dal_irq_service_dce80_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dce80_irq_construct(irq_service, init_data);
 	return irq_service;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c b/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
index cc8e7dedccce..f956b3bde680 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn10/irq_service_dcn10.c
@@ -355,7 +355,7 @@ static const struct irq_service_funcs irq_service_funcs_dcn10 = {
 		.to_dal_irq_source = to_dal_irq_source_dcn10
 };
 
-static void construct(
+static void dcn10_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -374,6 +374,6 @@ struct irq_service *dal_irq_service_dcn10_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dcn10_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
index 5db29bf582d3..2a1fea501f8c 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c
@@ -359,7 +359,7 @@ static const struct irq_service_funcs irq_service_funcs_dcn20 = {
 		.to_dal_irq_source = to_dal_irq_source_dcn20
 };
 
-static void construct(
+static void dcn20_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -378,6 +378,6 @@ struct irq_service *dal_irq_service_dcn20_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dcn20_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index cbe7818529bb..1b971265418b 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -350,7 +350,7 @@ static const struct irq_service_funcs irq_service_funcs_dcn21 = {
 		.to_dal_irq_source = to_dal_irq_source_dcn21
 };
 
-static void construct(
+static void dcn21_irq_construct(
 	struct irq_service *irq_service,
 	struct irq_service_init_data *init_data)
 {
@@ -369,6 +369,6 @@ struct irq_service *dal_irq_service_dcn21_create(
 	if (!irq_service)
 		return NULL;
 
-	construct(irq_service, init_data);
+	dcn21_irq_construct(irq_service, init_data);
 	return irq_service;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 0878550a8178..33053b9fe6bd 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -38,7 +38,7 @@
 #include "dce120/irq_service_dce120.h"
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 #include "dcn10/irq_service_dcn10.h"
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index 30ec80ac6fc8..c34eba19860a 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -1,5 +1,6 @@
 /*
  * Copyright 2012-16 Advanced Micro Devices, Inc.
+ * Copyright 2019 Raptor Engineering, LLC
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -29,6 +30,7 @@
 #include <linux/kgdb.h>
 #include <linux/kref.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 
 #include <asm/byteorder.h>
 
@@ -48,8 +50,39 @@
 
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+#if defined(CONFIG_X86)
 #include <asm/fpu/api.h>
+#define DC_FP_START() kernel_fpu_begin()
+#define DC_FP_END() kernel_fpu_end()
+#elif defined(CONFIG_PPC64)
+#include <asm/switch_to.h>
+#include <asm/cputable.h>
+#define DC_FP_START() { \
+	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
+		preempt_disable(); \
+		enable_kernel_vsx(); \
+	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
+		preempt_disable(); \
+		enable_kernel_altivec(); \
+	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
+		preempt_disable(); \
+		enable_kernel_fp(); \
+	} \
+}
+#define DC_FP_END() { \
+	if (cpu_has_feature(CPU_FTR_VSX_COMP)) { \
+		disable_kernel_vsx(); \
+		preempt_enable(); \
+	} else if (cpu_has_feature(CPU_FTR_ALTIVEC_COMP)) { \
+		disable_kernel_altivec(); \
+		preempt_enable(); \
+	} else if (!cpu_has_feature(CPU_FTR_FPU_UNAVAILABLE)) { \
+		disable_kernel_fp(); \
+		preempt_enable(); \
+	} \
+}
+#endif
 #endif
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
index ff664bdb1482..b8040da94b9d 100644
--- a/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/virtual/virtual_stream_encoder.c
@@ -32,6 +32,7 @@ static void virtual_stream_encoder_dp_set_stream_attribute(
 	struct stream_encoder *enc,
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space,
+	bool use_vsc_sdp_for_colorimetry,
 	uint32_t enable_sdp_splitting) {}
 
 static void virtual_stream_encoder_hdmi_set_stream_attribute(
@@ -81,22 +82,14 @@ static void virtual_stream_encoder_reset_hdmi_stream_attribute(
 		struct stream_encoder *enc)
 {}
 
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 static void virtual_enc_dp_set_odm_combine(
 	struct stream_encoder *enc,
 	bool odm_combine)
 {}
-#endif
-#endif
 
 static const struct stream_encoder_funcs virtual_str_enc_funcs = {
-#ifdef CONFIG_DRM_AMD_DC_DCN2_0
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.dp_set_odm_combine =
 		virtual_enc_dp_set_odm_combine,
-#endif
-#endif
 	.dp_set_stream_attribute =
 		virtual_stream_encoder_dp_set_stream_attribute,
 	.hdmi_set_stream_attribute =
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
new file mode 100644
index 000000000000..cd9532b4f14d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -0,0 +1,289 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_CMD_H_
+#define _DMUB_CMD_H_
+
+#include "dmub_types.h"
+#include "dmub_cmd_dal.h"
+#include "dmub_cmd_vbios.h"
+#include "atomfirmware.h"
+
+#define DMUB_RB_CMD_SIZE 64
+#define DMUB_RB_MAX_ENTRY 128
+#define DMUB_RB_SIZE (DMUB_RB_CMD_SIZE * DMUB_RB_MAX_ENTRY)
+#define REG_SET_MASK 0xFFFF
+
+
+/*
+ * Command IDs should be treated as stable ABI.
+ * Do not reuse or modify IDs.
+ */
+
+enum dmub_cmd_type {
+	DMUB_CMD__NULL = 0,
+	DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE = 1,
+	DMUB_CMD__REG_SEQ_FIELD_UPDATE_SEQ = 2,
+	DMUB_CMD__REG_SEQ_BURST_WRITE = 3,
+	DMUB_CMD__REG_REG_WAIT = 4,
+	DMUB_CMD__PLAT_54186_WA = 5,
+	DMUB_CMD__PSR = 64,
+	DMUB_CMD__VBIOS = 128,
+};
+
+#pragma pack(push, 1)
+
+struct dmub_cmd_header {
+	unsigned int type : 8;
+	unsigned int sub_type : 8;
+	unsigned int reserved0 : 8;
+	unsigned int payload_bytes : 6;  /* up to 60 bytes */
+	unsigned int reserved1 : 2;
+};
+
+/*
+ * Read modify write
+ *
+ * 60 payload bytes can hold up to 5 sets of read modify writes,
+ * each take 3 dwords.
+ *
+ * number of sequences = header.payload_bytes / sizeof(struct dmub_cmd_read_modify_write_sequence)
+ *
+ * modify_mask = 0xffff'ffff means all fields are going to be updated.  in this case
+ * command parser will skip the read and we can use modify_mask = 0xffff'ffff as reg write
+ */
+struct dmub_cmd_read_modify_write_sequence {
+	uint32_t addr;
+	uint32_t modify_mask;
+	uint32_t modify_value;
+};
+
+#define DMUB_READ_MODIFY_WRITE_SEQ__MAX		5
+struct dmub_rb_cmd_read_modify_write {
+	struct dmub_cmd_header header;  // type = DMUB_CMD__REG_SEQ_READ_MODIFY_WRITE
+	struct dmub_cmd_read_modify_write_sequence seq[DMUB_READ_MODIFY_WRITE_SEQ__MAX];
+};
+
+/*
+ * Update a register with specified masks and values sequeunce
+ *
+ * 60 payload bytes can hold address + up to 7 sets of mask/value combo, each take 2 dword
+ *
+ * number of field update sequence = (header.payload_bytes - sizeof(addr)) / sizeof(struct read_modify_write_sequence)
+ *
+ *
+ * USE CASE:
+ *   1. auto-increment register where additional read would update pointer and produce wrong result
+ *   2. toggle a bit without read in the middle
+ */
+
+struct dmub_cmd_reg_field_update_sequence {
+	uint32_t modify_mask;  // 0xffff'ffff to skip initial read
+	uint32_t modify_value;
+};
+
+#define DMUB_REG_FIELD_UPDATE_SEQ__MAX		7
+
+struct dmub_rb_cmd_reg_field_update_sequence {
+	struct dmub_cmd_header header;
+	uint32_t addr;
+	struct dmub_cmd_reg_field_update_sequence seq[DMUB_REG_FIELD_UPDATE_SEQ__MAX];
+};
+
+
+/*
+ * Burst write
+ *
+ * support use case such as writing out LUTs.
+ *
+ * 60 payload bytes can hold up to 14 values to write to given address
+ *
+ * number of payload = header.payload_bytes / sizeof(struct read_modify_write_sequence)
+ */
+#define DMUB_BURST_WRITE_VALUES__MAX  14
+struct dmub_rb_cmd_burst_write {
+	struct dmub_cmd_header header;  // type = DMUB_CMD__REG_SEQ_BURST_WRITE
+	uint32_t addr;
+	uint32_t write_values[DMUB_BURST_WRITE_VALUES__MAX];
+};
+
+
+struct dmub_rb_cmd_common {
+	struct dmub_cmd_header header;
+	uint8_t cmd_buffer[DMUB_RB_CMD_SIZE - sizeof(struct dmub_cmd_header)];
+};
+
+struct dmub_cmd_reg_wait_data {
+	uint32_t addr;
+	uint32_t mask;
+	uint32_t condition_field_value;
+	uint32_t time_out_us;
+};
+
+struct dmub_rb_cmd_reg_wait {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_reg_wait_data reg_wait;
+};
+
+#ifndef PHYSICAL_ADDRESS_LOC
+#define PHYSICAL_ADDRESS_LOC union large_integer
+#endif
+
+struct dmub_cmd_PLAT_54186_wa {
+	uint32_t DCSURF_SURFACE_CONTROL;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C;
+	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C;
+	struct {
+		uint8_t hubp_inst : 4;
+		uint8_t tmz_surface : 1;
+		uint8_t immediate :1;
+		uint8_t vmid : 4;
+		uint8_t grph_stereo : 1;
+		uint32_t reserved : 21;
+	} flip_params;
+	uint32_t reserved[9];
+};
+
+struct dmub_rb_cmd_PLAT_54186_wa {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_PLAT_54186_wa flip;
+};
+
+struct dmub_cmd_digx_encoder_control_data {
+	union dig_encoder_control_parameters_v1_5 dig;
+};
+
+struct dmub_rb_cmd_digx_encoder_control {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_digx_encoder_control_data encoder_control;
+};
+
+struct dmub_cmd_set_pixel_clock_data {
+	struct set_pixel_clock_parameter_v1_7 clk;
+};
+
+struct dmub_rb_cmd_set_pixel_clock {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_set_pixel_clock_data pixel_clock;
+};
+
+struct dmub_cmd_enable_disp_power_gating_data {
+	struct enable_disp_power_gating_parameters_v2_1 pwr;
+};
+
+struct dmub_rb_cmd_enable_disp_power_gating {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_enable_disp_power_gating_data power_gating;
+};
+
+struct dmub_cmd_dig1_transmitter_control_data {
+	struct dig_transmitter_control_parameters_v1_6 dig;
+};
+
+struct dmub_rb_cmd_dig1_transmitter_control {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_dig1_transmitter_control_data transmitter_control;
+};
+
+struct dmub_rb_cmd_dpphy_init {
+	struct dmub_cmd_header header;
+	uint8_t reserved[60];
+};
+
+struct dmub_cmd_psr_copy_settings_data {
+	uint16_t psr_level;
+	uint8_t hubp_inst;
+	uint8_t dpp_inst;
+	uint8_t mpcc_inst;
+	uint8_t opp_inst;
+	uint8_t otg_inst;
+	uint8_t digfe_inst;
+	uint8_t digbe_inst;
+	uint8_t dpphy_inst;
+	uint8_t aux_inst;
+	uint8_t hyst_frames;
+	uint8_t hyst_lines;
+	uint8_t phy_num;
+	uint8_t phy_type;
+	uint8_t aux_repeat;
+	uint8_t smu_optimizations_en;
+	uint8_t skip_wait_for_pll_lock;
+	uint8_t frame_delay;
+	uint8_t smu_phy_id;
+	uint8_t num_of_controllers;
+	uint8_t link_rate;
+	uint8_t frame_cap_ind;
+};
+
+struct dmub_rb_cmd_psr_copy_settings {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_psr_copy_settings_data psr_copy_settings_data;
+};
+
+struct dmub_cmd_psr_set_level_data {
+	uint16_t psr_level;
+};
+
+struct dmub_rb_cmd_psr_set_level {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_psr_set_level_data psr_set_level_data;
+};
+
+struct dmub_rb_cmd_psr_enable {
+	struct dmub_cmd_header header;
+};
+
+struct dmub_cmd_psr_setup_data {
+	enum psr_version version; // PSR version 1 or 2
+};
+
+struct dmub_rb_cmd_psr_setup {
+	struct dmub_cmd_header header;
+	struct dmub_cmd_psr_setup_data psr_setup_data;
+};
+
+union dmub_rb_cmd {
+	struct dmub_rb_cmd_read_modify_write read_modify_write;
+	struct dmub_rb_cmd_reg_field_update_sequence reg_field_update_seq;
+	struct dmub_rb_cmd_burst_write burst_write;
+	struct dmub_rb_cmd_reg_wait reg_wait;
+	struct dmub_rb_cmd_common cmd_common;
+	struct dmub_rb_cmd_digx_encoder_control digx_encoder_control;
+	struct dmub_rb_cmd_set_pixel_clock set_pixel_clock;
+	struct dmub_rb_cmd_enable_disp_power_gating enable_disp_power_gating;
+	struct dmub_rb_cmd_dpphy_init dpphy_init;
+	struct dmub_rb_cmd_dig1_transmitter_control dig1_transmitter_control;
+	struct dmub_rb_cmd_psr_enable psr_enable;
+	struct dmub_rb_cmd_psr_copy_settings psr_copy_settings;
+	struct dmub_rb_cmd_psr_set_level psr_set_level;
+	struct dmub_rb_cmd_PLAT_54186_wa PLAT_54186_wa;
+	struct dmub_rb_cmd_psr_setup psr_setup;
+};
+
+#pragma pack(pop)
+
+#endif /* _DMUB_CMD_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h
new file mode 100644
index 000000000000..7b69eb37f762
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_dal.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_CMD_DAL_H_
+#define _DMUB_CMD_DAL_H_
+
+/*
+ * Command IDs should be treated as stable ABI.
+ * Do not reuse or modify IDs.
+ */
+
+enum dmub_cmd_psr_type {
+	DMUB_CMD__PSR_SETUP		= 0,
+	DMUB_CMD__PSR_COPY_SETTINGS	= 1,
+	DMUB_CMD__PSR_ENABLE		= 2,
+	DMUB_CMD__PSR_DISABLE		= 3,
+	DMUB_CMD__PSR_SET_LEVEL		= 4,
+};
+
+enum psr_version {
+	PSR_VERSION_1			= 0x10, // PSR Version 1
+	PSR_VERSION_2			= 0x20, // PSR Version 2, includes selective update
+	PSR_VERSION_2_Y_COORD		= 0x21, // PSR Version 2, includes Y-coordinate support for SU
+};
+
+#endif /* _DMUB_CMD_DAL_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_vbios.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_vbios.h
new file mode 100644
index 000000000000..b6deb8e2590f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd_vbios.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_CMD_VBIOS_H_
+#define _DMUB_CMD_VBIOS_H_
+
+/*
+ * Command IDs should be treated as stable ABI.
+ * Do not reuse or modify IDs.
+ */
+
+enum dmub_cmd_vbios_type {
+	DMUB_CMD__VBIOS_DIGX_ENCODER_CONTROL = 0,
+	DMUB_CMD__VBIOS_DIG1_TRANSMITTER_CONTROL = 1,
+	DMUB_CMD__VBIOS_SET_PIXEL_CLOCK = 2,
+	DMUB_CMD__VBIOS_ENABLE_DISP_POWER_GATING = 3,
+};
+
+#endif /* _DMUB_CMD_VBIOS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h
new file mode 100644
index 000000000000..242ec257998c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_fw_meta.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+#ifndef _DMUB_META_H_
+#define _DMUB_META_H_
+
+#include "dmub_types.h"
+
+#pragma pack(push, 1)
+
+/* Magic value for identifying dmub_fw_meta_info */
+#define DMUB_FW_META_MAGIC 0x444D5542
+
+/* Offset from the end of the file to the dmub_fw_meta_info */
+#define DMUB_FW_META_OFFSET 0x24
+
+/**
+ * struct dmub_fw_meta_info - metadata associated with fw binary
+ *
+ * NOTE: This should be considered a stable API. Fields should
+ *       not be repurposed or reordered. New fields should be
+ *       added instead to extend the structure.
+ *
+ * @magic_value: magic value identifying DMUB firmware meta info
+ * @fw_region_size: size of the firmware state region
+ * @trace_buffer_size: size of the tracebuffer region
+ */
+struct dmub_fw_meta_info {
+	uint32_t magic_value;
+	uint32_t fw_region_size;
+	uint32_t trace_buffer_size;
+};
+
+/* Ensure that the structure remains 64 bytes. */
+union dmub_fw_meta {
+	struct dmub_fw_meta_info info;
+	uint8_t reserved[64];
+};
+
+#pragma pack(pop)
+
+#endif /* _DMUB_META_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h
new file mode 100644
index 000000000000..df875fdd2ab0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_rb.h
@@ -0,0 +1,154 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_RB_H_
+#define _DMUB_RB_H_
+
+#include "dmub_types.h"
+#include "dmub_cmd.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+struct dmub_cmd_header;
+
+struct dmub_rb_init_params {
+	void *ctx;
+	void *base_address;
+	uint32_t capacity;
+};
+
+struct dmub_rb {
+	void *base_address;
+	uint32_t data_count;
+	uint32_t rptr;
+	uint32_t wrpt;
+	uint32_t capacity;
+
+	void *ctx;
+	void *dmub;
+};
+
+
+static inline bool dmub_rb_empty(struct dmub_rb *rb)
+{
+	return (rb->wrpt == rb->rptr);
+}
+
+static inline bool dmub_rb_full(struct dmub_rb *rb)
+{
+	uint32_t data_count;
+
+	if (rb->wrpt >= rb->rptr)
+		data_count = rb->wrpt - rb->rptr;
+	else
+		data_count = rb->capacity - (rb->rptr - rb->wrpt);
+
+	return (data_count == (rb->capacity - DMUB_RB_CMD_SIZE));
+}
+
+static inline bool dmub_rb_push_front(struct dmub_rb *rb,
+				      const struct dmub_cmd_header *cmd)
+{
+	uint64_t volatile *dst = (uint64_t volatile *)(rb->base_address) + rb->wrpt / sizeof(uint64_t);
+	const uint64_t *src = (const uint64_t *)cmd;
+	int i;
+
+	if (dmub_rb_full(rb))
+		return false;
+
+	// copying data
+	for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
+		*dst++ = *src++;
+
+	rb->wrpt += DMUB_RB_CMD_SIZE;
+
+	if (rb->wrpt >= rb->capacity)
+		rb->wrpt %= rb->capacity;
+
+	return true;
+}
+
+static inline bool dmub_rb_front(struct dmub_rb *rb,
+				 struct dmub_cmd_header *cmd)
+{
+	uint8_t *rd_ptr = (uint8_t *)rb->base_address + rb->rptr;
+
+	if (dmub_rb_empty(rb))
+		return false;
+
+	dmub_memcpy(cmd, rd_ptr, DMUB_RB_CMD_SIZE);
+
+	return true;
+}
+
+static inline bool dmub_rb_pop_front(struct dmub_rb *rb)
+{
+	if (dmub_rb_empty(rb))
+		return false;
+
+	rb->rptr += DMUB_RB_CMD_SIZE;
+
+	if (rb->rptr >= rb->capacity)
+		rb->rptr %= rb->capacity;
+
+	return true;
+}
+
+static inline void dmub_rb_flush_pending(const struct dmub_rb *rb)
+{
+	uint32_t rptr = rb->rptr;
+	uint32_t wptr = rb->wrpt;
+
+	while (rptr != wptr) {
+		uint64_t volatile *data = (uint64_t volatile *)rb->base_address + rptr / sizeof(uint64_t);
+		//uint64_t volatile *p = (uint64_t volatile *)data;
+		uint64_t temp;
+		int i;
+
+		for (i = 0; i < DMUB_RB_CMD_SIZE / sizeof(uint64_t); i++)
+			temp = *data++;
+
+		rptr += DMUB_RB_CMD_SIZE;
+		if (rptr >= rb->capacity)
+			rptr %= rb->capacity;
+	}
+}
+
+static inline void dmub_rb_init(struct dmub_rb *rb,
+				struct dmub_rb_init_params *init_params)
+{
+	rb->base_address = init_params->base_address;
+	rb->capacity = init_params->capacity;
+	rb->rptr = 0;
+	rb->wrpt = 0;
+}
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _DMUB_RB_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h
new file mode 100644
index 000000000000..8e23a7017588
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_srv.h
@@ -0,0 +1,506 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_SRV_H_
+#define _DMUB_SRV_H_
+
+/**
+ * DOC: DMUB interface and operation
+ *
+ * DMUB is the interface to the display DMCUB microcontroller on DCN hardware.
+ * It delegates hardware initialization and command submission to the
+ * microcontroller. DMUB is the shortname for DMCUB.
+ *
+ * This interface is not thread-safe. Ensure that all access to the interface
+ * is properly synchronized by the caller.
+ *
+ * Initialization and usage of the DMUB service should be done in the
+ * steps given below:
+ *
+ * 1. dmub_srv_create()
+ * 2. dmub_srv_has_hw_support()
+ * 3. dmub_srv_calc_region_info()
+ * 4. dmub_srv_hw_init()
+ *
+ * The call to dmub_srv_create() is required to use the server.
+ *
+ * The calls to dmub_srv_has_hw_support() and dmub_srv_calc_region_info()
+ * are helpers to query cache window size and allocate framebuffer(s)
+ * for the cache windows.
+ *
+ * The call to dmub_srv_hw_init() programs the DMCUB registers to prepare
+ * for command submission. Commands can be queued via dmub_srv_cmd_queue()
+ * and executed via dmub_srv_cmd_execute().
+ *
+ * If the queue is full the dmub_srv_wait_for_idle() call can be used to
+ * wait until the queue has been cleared.
+ *
+ * Destroying the DMUB service can be done by calling dmub_srv_destroy().
+ * This does not clear DMUB hardware state, only software state.
+ *
+ * The interface is intended to be standalone and should not depend on any
+ * other component within DAL.
+ */
+
+#include "dmub_types.h"
+#include "dmub_cmd.h"
+#include "dmub_rb.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Forward declarations */
+struct dmub_srv;
+struct dmub_cmd_header;
+struct dmub_srv_common_regs;
+
+/* enum dmub_status - return code for dmcub functions */
+enum dmub_status {
+	DMUB_STATUS_OK = 0,
+	DMUB_STATUS_NO_CTX,
+	DMUB_STATUS_QUEUE_FULL,
+	DMUB_STATUS_TIMEOUT,
+	DMUB_STATUS_INVALID,
+};
+
+/* enum dmub_asic - dmub asic identifier */
+enum dmub_asic {
+	DMUB_ASIC_NONE = 0,
+	DMUB_ASIC_DCN20,
+	DMUB_ASIC_DCN21,
+	DMUB_ASIC_MAX,
+};
+
+/* enum dmub_window_id - dmub window identifier */
+enum dmub_window_id {
+	DMUB_WINDOW_0_INST_CONST = 0,
+	DMUB_WINDOW_1_STACK,
+	DMUB_WINDOW_2_BSS_DATA,
+	DMUB_WINDOW_3_VBIOS,
+	DMUB_WINDOW_4_MAILBOX,
+	DMUB_WINDOW_5_TRACEBUFF,
+	DMUB_WINDOW_6_FW_STATE,
+	DMUB_WINDOW_7_RESERVED,
+	DMUB_WINDOW_TOTAL,
+};
+
+/**
+ * struct dmub_region - dmub hw memory region
+ * @base: base address for region, must be 256 byte aligned
+ * @top: top address for region
+ */
+struct dmub_region {
+	uint32_t base;
+	uint32_t top;
+};
+
+/**
+ * struct dmub_window - dmub hw cache window
+ * @off: offset to the fb memory in gpu address space
+ * @r: region in uc address space for cache window
+ */
+struct dmub_window {
+	union dmub_addr offset;
+	struct dmub_region region;
+};
+
+/**
+ * struct dmub_fb - defines a dmub framebuffer memory region
+ * @cpu_addr: cpu virtual address for the region, NULL if invalid
+ * @gpu_addr: gpu virtual address for the region, NULL if invalid
+ * @size: size of the region in bytes, zero if invalid
+ */
+struct dmub_fb {
+	void *cpu_addr;
+	uint64_t gpu_addr;
+	uint32_t size;
+};
+
+/**
+ * struct dmub_srv_region_params - params used for calculating dmub regions
+ * @inst_const_size: size of the fw inst const section
+ * @bss_data_size: size of the fw bss data section
+ * @vbios_size: size of the vbios data
+ * @fw_bss_data: raw firmware bss data section
+ */
+struct dmub_srv_region_params {
+	uint32_t inst_const_size;
+	uint32_t bss_data_size;
+	uint32_t vbios_size;
+	const uint8_t *fw_bss_data;
+};
+
+/**
+ * struct dmub_srv_region_info - output region info from the dmub service
+ * @fb_size: required minimum fb size for all regions, aligned to 4096 bytes
+ * @num_regions: number of regions used by the dmub service
+ * @regions: region info
+ *
+ * The regions are aligned such that they can be all placed within the
+ * same framebuffer but they can also be placed into different framebuffers.
+ *
+ * The size of each region can be calculated by the caller:
+ * size = reg.top - reg.base
+ *
+ * Care must be taken when performing custom allocations to ensure that each
+ * region base address is 256 byte aligned.
+ */
+struct dmub_srv_region_info {
+	uint32_t fb_size;
+	uint8_t num_regions;
+	struct dmub_region regions[DMUB_WINDOW_TOTAL];
+};
+
+/**
+ * struct dmub_srv_fb_params - parameters used for driver fb setup
+ * @region_info: region info calculated by dmub service
+ * @cpu_addr: base cpu address for the framebuffer
+ * @gpu_addr: base gpu virtual address for the framebuffer
+ */
+struct dmub_srv_fb_params {
+	const struct dmub_srv_region_info *region_info;
+	void *cpu_addr;
+	uint64_t gpu_addr;
+};
+
+/**
+ * struct dmub_srv_fb_info - output fb info from the dmub service
+ * @num_fbs: number of required dmub framebuffers
+ * @fbs: fb data for each region
+ *
+ * Output from the dmub service helper that can be used by the
+ * driver to prepare dmub_fb that can be passed into the dmub
+ * hw init service.
+ *
+ * Assumes that all regions are within the same framebuffer
+ * and have been setup according to the region_info generated
+ * by the dmub service.
+ */
+struct dmub_srv_fb_info {
+	uint8_t num_fb;
+	struct dmub_fb fb[DMUB_WINDOW_TOTAL];
+};
+
+/**
+ * struct dmub_srv_base_funcs - Driver specific base callbacks
+ */
+struct dmub_srv_base_funcs {
+	/**
+	 * @reg_read:
+	 *
+	 * Hook for reading a register.
+	 *
+	 * Return: The 32-bit register value from the given address.
+	 */
+	uint32_t (*reg_read)(void *ctx, uint32_t address);
+
+	/**
+	 * @reg_write:
+	 *
+	 * Hook for writing a value to the register specified by address.
+	 */
+	void (*reg_write)(void *ctx, uint32_t address, uint32_t value);
+};
+
+/**
+ * struct dmub_srv_hw_funcs - hardware sequencer funcs for dmub
+ */
+struct dmub_srv_hw_funcs {
+	/* private: internal use only */
+
+	void (*reset)(struct dmub_srv *dmub);
+
+	void (*reset_release)(struct dmub_srv *dmub);
+
+	void (*backdoor_load)(struct dmub_srv *dmub,
+			      const struct dmub_window *cw0,
+			      const struct dmub_window *cw1);
+
+	void (*setup_windows)(struct dmub_srv *dmub,
+			      const struct dmub_window *cw2,
+			      const struct dmub_window *cw3,
+			      const struct dmub_window *cw4,
+			      const struct dmub_window *cw5,
+			      const struct dmub_window *cw6);
+
+	void (*setup_mailbox)(struct dmub_srv *dmub,
+			      const struct dmub_region *inbox1);
+
+	uint32_t (*get_inbox1_rptr)(struct dmub_srv *dmub);
+
+	void (*set_inbox1_wptr)(struct dmub_srv *dmub, uint32_t wptr_offset);
+
+	bool (*is_supported)(struct dmub_srv *dmub);
+
+	bool (*is_hw_init)(struct dmub_srv *dmub);
+
+	bool (*is_phy_init)(struct dmub_srv *dmub);
+
+	bool (*is_auto_load_done)(struct dmub_srv *dmub);
+};
+
+/**
+ * struct dmub_srv_create_params - params for dmub service creation
+ * @base_funcs: driver supplied base routines
+ * @hw_funcs: optional overrides for hw funcs
+ * @user_ctx: context data for callback funcs
+ * @asic: driver supplied asic
+ * @is_virtual: false for hw support only
+ */
+struct dmub_srv_create_params {
+	struct dmub_srv_base_funcs funcs;
+	struct dmub_srv_hw_funcs *hw_funcs;
+	void *user_ctx;
+	enum dmub_asic asic;
+	bool is_virtual;
+};
+
+/*
+ * struct dmub_srv_hw_params - params for dmub hardware initialization
+ * @fb: framebuffer info for each region
+ * @fb_base: base of the framebuffer aperture
+ * @fb_offset: offset of the framebuffer aperture
+ * @psp_version: psp version to pass for DMCU init
+ * @load_inst_const: true if DMUB should load inst const fw
+ */
+struct dmub_srv_hw_params {
+	struct dmub_fb *fb[DMUB_WINDOW_TOTAL];
+	uint64_t fb_base;
+	uint64_t fb_offset;
+	uint32_t psp_version;
+	bool load_inst_const;
+};
+
+/**
+ * struct dmub_srv - software state for dmcub
+ * @asic: dmub asic identifier
+ * @user_ctx: user provided context for the dmub_srv
+ * @is_virtual: false if hardware support only
+ * @fw_state: dmub firmware state pointer
+ */
+struct dmub_srv {
+	enum dmub_asic asic;
+	void *user_ctx;
+	bool is_virtual;
+	volatile const struct dmub_fw_state *fw_state;
+
+	/* private: internal use only */
+	const struct dmub_srv_common_regs *regs;
+
+	struct dmub_srv_base_funcs funcs;
+	struct dmub_srv_hw_funcs hw_funcs;
+	struct dmub_rb inbox1_rb;
+
+	bool sw_init;
+	bool hw_init;
+
+	uint64_t fb_base;
+	uint64_t fb_offset;
+	uint32_t psp_version;
+};
+
+/**
+ * dmub_srv_create() - creates the DMUB service.
+ * @dmub: the dmub service
+ * @params: creation parameters for the service
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_create(struct dmub_srv *dmub,
+				 const struct dmub_srv_create_params *params);
+
+/**
+ * dmub_srv_destroy() - destroys the DMUB service.
+ * @dmub: the dmub service
+ */
+void dmub_srv_destroy(struct dmub_srv *dmub);
+
+/**
+ * dmub_srv_calc_region_info() - retreives region info from the dmub service
+ * @dmub: the dmub service
+ * @params: parameters used to calculate region locations
+ * @info_out: the output region info from dmub
+ *
+ * Calculates the base and top address for all relevant dmub regions
+ * using the parameters given (if any).
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status
+dmub_srv_calc_region_info(struct dmub_srv *dmub,
+			  const struct dmub_srv_region_params *params,
+			  struct dmub_srv_region_info *out);
+
+/**
+ * dmub_srv_calc_region_info() - retreives fb info from the dmub service
+ * @dmub: the dmub service
+ * @params: parameters used to calculate fb locations
+ * @info_out: the output fb info from dmub
+ *
+ * Calculates the base and top address for all relevant dmub regions
+ * using the parameters given (if any).
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_fb_params *params,
+				       struct dmub_srv_fb_info *out);
+
+/**
+ * dmub_srv_has_hw_support() - returns hw support state for dmcub
+ * @dmub: the dmub service
+ * @is_supported: hw support state
+ *
+ * Queries the hardware for DMCUB support and returns the result.
+ *
+ * Can be called before dmub_srv_hw_init().
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_has_hw_support(struct dmub_srv *dmub,
+					 bool *is_supported);
+
+/**
+ * dmub_srv_is_hw_init() - returns hardware init state
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_is_hw_init(struct dmub_srv *dmub, bool *is_hw_init);
+
+/**
+ * dmub_srv_hw_init() - initializes the underlying DMUB hardware
+ * @dmub: the dmub service
+ * @params: params for hardware initialization
+ *
+ * Resets the DMUB hardware and performs backdoor loading of the
+ * required cache regions based on the input framebuffer regions.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_NO_CTX - dmcub context not initialized
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub,
+				  const struct dmub_srv_hw_params *params);
+
+/**
+ * dmub_srv_cmd_queue() - queues a command to the DMUB
+ * @dmub: the dmub service
+ * @cmd: the command to queue
+ *
+ * Queues a command to the DMUB service but does not begin execution
+ * immediately.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_QUEUE_FULL - no remaining room in queue
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub,
+				    const struct dmub_cmd_header *cmd);
+
+/**
+ * dmub_srv_cmd_execute() - Executes a queued sequence to the dmub
+ * @dmub: the dmub service
+ *
+ * Begins execution of queued commands on the dmub.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_cmd_execute(struct dmub_srv *dmub);
+
+/**
+ * dmub_srv_wait_for_auto_load() - Waits for firmware auto load to complete
+ * @dmub: the dmub service
+ * @timeout_us: the maximum number of microseconds to wait
+ *
+ * Waits until firmware has been autoloaded by the DMCUB. The maximum
+ * wait time is given in microseconds to prevent spinning forever.
+ *
+ * On ASICs without firmware autoload support this function will return
+ * immediately.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_TIMEOUT - wait for phy init timed out
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_wait_for_auto_load(struct dmub_srv *dmub,
+					     uint32_t timeout_us);
+
+/**
+ * dmub_srv_wait_for_phy_init() - Waits for DMUB PHY init to complete
+ * @dmub: the dmub service
+ * @timeout_us: the maximum number of microseconds to wait
+ *
+ * Waits until the PHY has been initialized by the DMUB. The maximum
+ * wait time is given in microseconds to prevent spinning forever.
+ *
+ * On ASICs without PHY init support this function will return
+ * immediately.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_TIMEOUT - wait for phy init timed out
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_wait_for_phy_init(struct dmub_srv *dmub,
+					    uint32_t timeout_us);
+
+/**
+ * dmub_srv_wait_for_idle() - Waits for the DMUB to be idle
+ * @dmub: the dmub service
+ * @timeout_us: the maximum number of microseconds to wait
+ *
+ * Waits until the DMUB buffer is empty and all commands have
+ * finished processing. The maximum wait time is given in
+ * microseconds to prevent spinning forever.
+ *
+ * Return:
+ *   DMUB_STATUS_OK - success
+ *   DMUB_STATUS_TIMEOUT - wait for buffer to flush timed out
+ *   DMUB_STATUS_INVALID - unspecified error
+ */
+enum dmub_status dmub_srv_wait_for_idle(struct dmub_srv *dmub,
+					uint32_t timeout_us);
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _DMUB_SRV_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_trace_buffer.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_trace_buffer.h
new file mode 100644
index 000000000000..6b3ee42db350
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_trace_buffer.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+#ifndef _DMUB_TRACE_BUFFER_H_
+#define _DMUB_TRACE_BUFFER_H_
+
+#include "dmub_types.h"
+
+#define LOAD_DMCU_FW	1
+#define LOAD_PHY_FW	2
+
+
+enum dmucb_trace_code {
+	DMCUB__UNKNOWN,
+	DMCUB__MAIN_BEGIN,
+	DMCUB__PHY_INIT_BEGIN,
+	DMCUB__PHY_FW_SRAM_LOAD_BEGIN,
+	DMCUB__PHY_FW_SRAM_LOAD_END,
+	DMCUB__PHY_INIT_POLL_DONE,
+	DMCUB__PHY_INIT_END,
+	DMCUB__DMCU_ERAM_LOAD_BEGIN,
+	DMCUB__DMCU_ERAM_LOAD_END,
+	DMCUB__DMCU_ISR_LOAD_BEGIN,
+	DMCUB__DMCU_ISR_LOAD_END,
+	DMCUB__MAIN_IDLE,
+	DMCUB__PERF_TRACE,
+	DMCUB__PG_DONE,
+};
+
+struct dmcub_trace_buf_entry {
+	enum dmucb_trace_code trace_code;
+	uint32_t tick_count;
+	uint32_t param0;
+	uint32_t param1;
+};
+
+#define TRACE_BUF_SIZE (1024) //1 kB
+#define PERF_TRACE_MAX_ENTRY ((TRACE_BUF_SIZE - 8)/sizeof(struct dmcub_trace_buf_entry))
+
+
+struct dmcub_trace_buf {
+	uint32_t entry_count;
+	uint32_t clk_freq;
+	struct dmcub_trace_buf_entry entries[PERF_TRACE_MAX_ENTRY];
+};
+
+
+#endif /* _DMUB_TRACE_BUFFER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_types.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_types.h
new file mode 100644
index 000000000000..41d524b0db2f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_types.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_TYPES_H_
+#define _DMUB_TYPES_H_
+
+/* Basic type definitions. */
+#include <asm/byteorder.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/delay.h>
+#include <stdarg.h>
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#ifndef dmub_memcpy
+#define dmub_memcpy(dest, source, bytes) memcpy((dest), (source), (bytes))
+#endif
+
+#ifndef dmub_memset
+#define dmub_memset(dest, val, bytes) memset((dest), (val), (bytes))
+#endif
+
+#ifndef dmub_udelay
+#define dmub_udelay(microseconds) udelay(microseconds)
+#endif
+
+union dmub_addr {
+	struct {
+		uint32_t low_part;
+		uint32_t high_part;
+	} u;
+	uint64_t quad_part;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _DMUB_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/Makefile b/drivers/gpu/drm/amd/display/dmub/src/Makefile
new file mode 100644
index 000000000000..e08dfeea24b0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/Makefile
@@ -0,0 +1,27 @@
+#
+# Copyright 2019 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+
+DMUB = dmub_srv.o dmub_reg.o dmub_dcn20.o dmub_dcn21.o
+
+AMD_DAL_DMUB = $(addprefix $(AMDDALPATH)/dmub/src/,$(DMUB))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_DMUB)
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c
new file mode 100644
index 000000000000..cd51c6138894
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "../inc/dmub_srv.h"
+#include "dmub_reg.h"
+#include "dmub_dcn20.h"
+
+#include "dcn/dcn_2_0_0_offset.h"
+#include "dcn/dcn_2_0_0_sh_mask.h"
+#include "soc15_hw_ip.h"
+#include "vega10_ip_offset.h"
+
+#define BASE_INNER(seg) DCN_BASE__INST0_SEG##seg
+#define CTX dmub
+#define REGS dmub->regs
+
+/* Registers. */
+
+const struct dmub_srv_common_regs dmub_srv_dcn20_regs = {
+#define DMUB_SR(reg) REG_OFFSET(reg),
+	{ DMUB_COMMON_REGS() },
+#undef DMUB_SR
+
+#define DMUB_SF(reg, field) FD_MASK(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+
+#define DMUB_SF(reg, field) FD_SHIFT(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+};
+
+/* Shared functions. */
+
+static inline void dmub_dcn20_translate_addr(const union dmub_addr *addr_in,
+					     uint64_t fb_base,
+					     uint64_t fb_offset,
+					     union dmub_addr *addr_out)
+{
+	addr_out->quad_part = addr_in->quad_part - fb_base + fb_offset;
+}
+
+void dmub_dcn20_reset(struct dmub_srv *dmub)
+{
+	REG_UPDATE(DMCUB_CNTL, DMCUB_SOFT_RESET, 1);
+	REG_UPDATE(DMCUB_CNTL, DMCUB_ENABLE, 0);
+	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 1);
+}
+
+void dmub_dcn20_reset_release(struct dmub_srv *dmub)
+{
+	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0);
+	REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF);
+	REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1);
+	REG_UPDATE(DMCUB_CNTL, DMCUB_SOFT_RESET, 0);
+}
+
+void dmub_dcn20_backdoor_load(struct dmub_srv *dmub,
+			      const struct dmub_window *cw0,
+			      const struct dmub_window *cw1)
+{
+	union dmub_addr offset;
+	uint64_t fb_base = dmub->fb_base, fb_offset = dmub->fb_offset;
+
+	REG_UPDATE(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 1);
+	REG_UPDATE_2(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE, 0x3,
+		     DMCUB_MEM_WRITE_SPACE, 0x3);
+
+	dmub_dcn20_translate_addr(&cw0->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW0_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW0_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW0_BASE_ADDRESS, cw0->region.base);
+	REG_SET_2(DMCUB_REGION3_CW0_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW0_TOP_ADDRESS, cw0->region.top,
+		  DMCUB_REGION3_CW0_ENABLE, 1);
+
+	dmub_dcn20_translate_addr(&cw1->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW1_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW1_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW1_BASE_ADDRESS, cw1->region.base);
+	REG_SET_2(DMCUB_REGION3_CW1_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW1_TOP_ADDRESS, cw1->region.top,
+		  DMCUB_REGION3_CW1_ENABLE, 1);
+
+	REG_UPDATE_2(DMCUB_SEC_CNTL, DMCUB_SEC_RESET, 0, DMCUB_MEM_UNIT_ID,
+		     0x20);
+}
+
+void dmub_dcn20_setup_windows(struct dmub_srv *dmub,
+			      const struct dmub_window *cw2,
+			      const struct dmub_window *cw3,
+			      const struct dmub_window *cw4,
+			      const struct dmub_window *cw5,
+			      const struct dmub_window *cw6)
+{
+	union dmub_addr offset;
+	uint64_t fb_base = dmub->fb_base, fb_offset = dmub->fb_offset;
+
+	dmub_dcn20_translate_addr(&cw2->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW2_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW2_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW2_BASE_ADDRESS, cw2->region.base);
+	REG_SET_2(DMCUB_REGION3_CW2_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW2_TOP_ADDRESS, cw2->region.top,
+		  DMCUB_REGION3_CW2_ENABLE, 1);
+
+	dmub_dcn20_translate_addr(&cw3->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW3_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW3_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW3_BASE_ADDRESS, cw3->region.base);
+	REG_SET_2(DMCUB_REGION3_CW3_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW3_TOP_ADDRESS, cw3->region.top,
+		  DMCUB_REGION3_CW3_ENABLE, 1);
+
+	/* TODO: Move this to CW4. */
+	dmub_dcn20_translate_addr(&cw4->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION4_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION4_OFFSET_HIGH, offset.u.high_part);
+	REG_SET_2(DMCUB_REGION4_TOP_ADDRESS, 0, DMCUB_REGION4_TOP_ADDRESS,
+		  cw4->region.top - cw4->region.base - 1, DMCUB_REGION4_ENABLE,
+		  1);
+
+	dmub_dcn20_translate_addr(&cw5->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW5_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW5_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW5_BASE_ADDRESS, cw5->region.base);
+	REG_SET_2(DMCUB_REGION3_CW5_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW5_TOP_ADDRESS, cw5->region.top,
+		  DMCUB_REGION3_CW5_ENABLE, 1);
+
+	dmub_dcn20_translate_addr(&cw6->offset, fb_base, fb_offset, &offset);
+
+	REG_WRITE(DMCUB_REGION3_CW6_OFFSET, offset.u.low_part);
+	REG_WRITE(DMCUB_REGION3_CW6_OFFSET_HIGH, offset.u.high_part);
+	REG_WRITE(DMCUB_REGION3_CW6_BASE_ADDRESS, cw6->region.base);
+	REG_SET_2(DMCUB_REGION3_CW6_TOP_ADDRESS, 0,
+		  DMCUB_REGION3_CW6_TOP_ADDRESS, cw6->region.top,
+		  DMCUB_REGION3_CW6_ENABLE, 1);
+}
+
+void dmub_dcn20_setup_mailbox(struct dmub_srv *dmub,
+			      const struct dmub_region *inbox1)
+{
+	/* TODO: Use CW4 instead of region 4. */
+
+	REG_WRITE(DMCUB_INBOX1_BASE_ADDRESS, 0x80000000);
+	REG_WRITE(DMCUB_INBOX1_SIZE, inbox1->top - inbox1->base);
+	REG_WRITE(DMCUB_INBOX1_RPTR, 0);
+	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
+}
+
+uint32_t dmub_dcn20_get_inbox1_rptr(struct dmub_srv *dmub)
+{
+	return REG_READ(DMCUB_INBOX1_RPTR);
+}
+
+void dmub_dcn20_set_inbox1_wptr(struct dmub_srv *dmub, uint32_t wptr_offset)
+{
+	REG_WRITE(DMCUB_INBOX1_WPTR, wptr_offset);
+}
+
+bool dmub_dcn20_is_hw_init(struct dmub_srv *dmub)
+{
+	return REG_READ(DMCUB_REGION3_CW2_BASE_ADDRESS) != 0;
+}
+
+bool dmub_dcn20_is_supported(struct dmub_srv *dmub)
+{
+	uint32_t supported = 0;
+
+	REG_GET(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE, &supported);
+
+	return supported;
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h
new file mode 100644
index 000000000000..53bfd4da69ad
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h
@@ -0,0 +1,182 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_DCN20_H_
+#define _DMUB_DCN20_H_
+
+#include "../inc/dmub_types.h"
+
+struct dmub_srv;
+
+/* DCN20 register definitions. */
+
+#define DMUB_COMMON_REGS() \
+	DMUB_SR(DMCUB_CNTL) \
+	DMUB_SR(DMCUB_MEM_CNTL) \
+	DMUB_SR(DMCUB_SEC_CNTL) \
+	DMUB_SR(DMCUB_INBOX1_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_INBOX1_SIZE) \
+	DMUB_SR(DMCUB_INBOX1_RPTR) \
+	DMUB_SR(DMCUB_INBOX1_WPTR) \
+	DMUB_SR(DMCUB_REGION3_CW0_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW1_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW2_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW3_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW4_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW5_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW6_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW7_OFFSET) \
+	DMUB_SR(DMCUB_REGION3_CW0_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW1_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW2_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW3_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW4_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW5_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW6_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW7_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION3_CW0_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW1_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW2_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW3_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW4_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW5_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW6_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW7_BASE_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW0_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW1_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW2_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW3_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW4_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW5_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW6_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION3_CW7_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_REGION4_OFFSET) \
+	DMUB_SR(DMCUB_REGION4_OFFSET_HIGH) \
+	DMUB_SR(DMCUB_REGION4_TOP_ADDRESS) \
+	DMUB_SR(DMCUB_SCRATCH0) \
+	DMUB_SR(DMCUB_SCRATCH1) \
+	DMUB_SR(DMCUB_SCRATCH2) \
+	DMUB_SR(DMCUB_SCRATCH3) \
+	DMUB_SR(DMCUB_SCRATCH4) \
+	DMUB_SR(DMCUB_SCRATCH5) \
+	DMUB_SR(DMCUB_SCRATCH6) \
+	DMUB_SR(DMCUB_SCRATCH7) \
+	DMUB_SR(DMCUB_SCRATCH8) \
+	DMUB_SR(DMCUB_SCRATCH9) \
+	DMUB_SR(DMCUB_SCRATCH10) \
+	DMUB_SR(DMCUB_SCRATCH11) \
+	DMUB_SR(DMCUB_SCRATCH12) \
+	DMUB_SR(DMCUB_SCRATCH13) \
+	DMUB_SR(DMCUB_SCRATCH14) \
+	DMUB_SR(DMCUB_SCRATCH15) \
+	DMUB_SR(CC_DC_PIPE_DIS) \
+	DMUB_SR(MMHUBBUB_SOFT_RESET)
+
+#define DMUB_COMMON_FIELDS() \
+	DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \
+	DMUB_SF(DMCUB_CNTL, DMCUB_SOFT_RESET) \
+	DMUB_SF(DMCUB_CNTL, DMCUB_TRACEPORT_EN) \
+	DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_READ_SPACE) \
+	DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_WRITE_SPACE) \
+	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET) \
+	DMUB_SF(DMCUB_SEC_CNTL, DMCUB_MEM_UNIT_ID) \
+	DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW2_TOP_ADDRESS, DMCUB_REGION3_CW2_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW2_TOP_ADDRESS, DMCUB_REGION3_CW2_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW3_TOP_ADDRESS, DMCUB_REGION3_CW3_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW3_TOP_ADDRESS, DMCUB_REGION3_CW3_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW4_TOP_ADDRESS, DMCUB_REGION3_CW4_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW4_TOP_ADDRESS, DMCUB_REGION3_CW4_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW5_TOP_ADDRESS, DMCUB_REGION3_CW5_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW5_TOP_ADDRESS, DMCUB_REGION3_CW5_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE) \
+	DMUB_SF(DMCUB_REGION3_CW7_TOP_ADDRESS, DMCUB_REGION3_CW7_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION3_CW7_TOP_ADDRESS, DMCUB_REGION3_CW7_ENABLE) \
+	DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_TOP_ADDRESS) \
+	DMUB_SF(DMCUB_REGION4_TOP_ADDRESS, DMCUB_REGION4_ENABLE) \
+	DMUB_SF(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE) \
+	DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET)
+
+struct dmub_srv_common_reg_offset {
+#define DMUB_SR(reg) uint32_t reg;
+	DMUB_COMMON_REGS()
+#undef DMUB_SR
+};
+
+struct dmub_srv_common_reg_shift {
+#define DMUB_SF(reg, field) uint8_t reg##__##field;
+	DMUB_COMMON_FIELDS()
+#undef DMUB_SF
+};
+
+struct dmub_srv_common_reg_mask {
+#define DMUB_SF(reg, field) uint32_t reg##__##field;
+	DMUB_COMMON_FIELDS()
+#undef DMUB_SF
+};
+
+struct dmub_srv_common_regs {
+	const struct dmub_srv_common_reg_offset offset;
+	const struct dmub_srv_common_reg_mask mask;
+	const struct dmub_srv_common_reg_shift shift;
+};
+
+extern const struct dmub_srv_common_regs dmub_srv_dcn20_regs;
+
+/* Hardware functions. */
+
+void dmub_dcn20_init(struct dmub_srv *dmub);
+
+void dmub_dcn20_reset(struct dmub_srv *dmub);
+
+void dmub_dcn20_reset_release(struct dmub_srv *dmub);
+
+void dmub_dcn20_backdoor_load(struct dmub_srv *dmub,
+			      const struct dmub_window *cw0,
+			      const struct dmub_window *cw1);
+
+void dmub_dcn20_setup_windows(struct dmub_srv *dmub,
+			      const struct dmub_window *cw2,
+			      const struct dmub_window *cw3,
+			      const struct dmub_window *cw4,
+			      const struct dmub_window *cw5,
+			      const struct dmub_window *cw6);
+
+void dmub_dcn20_setup_mailbox(struct dmub_srv *dmub,
+			      const struct dmub_region *inbox1);
+
+uint32_t dmub_dcn20_get_inbox1_rptr(struct dmub_srv *dmub);
+
+void dmub_dcn20_set_inbox1_wptr(struct dmub_srv *dmub, uint32_t wptr_offset);
+
+bool dmub_dcn20_is_hw_init(struct dmub_srv *dmub);
+
+bool dmub_dcn20_is_supported(struct dmub_srv *dmub);
+
+#endif /* _DMUB_DCN20_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c
new file mode 100644
index 000000000000..5bed9fcd6b5c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "../inc/dmub_srv.h"
+#include "dmub_reg.h"
+#include "dmub_dcn21.h"
+
+#include "dcn/dcn_2_1_0_offset.h"
+#include "dcn/dcn_2_1_0_sh_mask.h"
+#include "renoir_ip_offset.h"
+
+#define BASE_INNER(seg) DMU_BASE__INST0_SEG##seg
+#define CTX dmub
+#define REGS dmub->regs
+
+/* Registers. */
+
+const struct dmub_srv_common_regs dmub_srv_dcn21_regs = {
+#define DMUB_SR(reg) REG_OFFSET(reg),
+	{ DMUB_COMMON_REGS() },
+#undef DMUB_SR
+
+#define DMUB_SF(reg, field) FD_MASK(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+
+#define DMUB_SF(reg, field) FD_SHIFT(reg, field),
+	{ DMUB_COMMON_FIELDS() },
+#undef DMUB_SF
+};
+
+/* Shared functions. */
+
+bool dmub_dcn21_is_auto_load_done(struct dmub_srv *dmub)
+{
+	return (REG_READ(DMCUB_SCRATCH0) == 3);
+}
+
+bool dmub_dcn21_is_phy_init(struct dmub_srv *dmub)
+{
+	return REG_READ(DMCUB_SCRATCH10) == 0;
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h
new file mode 100644
index 000000000000..2bbea237137b
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_DCN21_H_
+#define _DMUB_DCN21_H_
+
+#include "dmub_dcn20.h"
+
+/* Registers. */
+
+extern const struct dmub_srv_common_regs dmub_srv_dcn21_regs;
+
+/* Hardware functions. */
+
+bool dmub_dcn21_is_auto_load_done(struct dmub_srv *dmub);
+
+bool dmub_dcn21_is_phy_init(struct dmub_srv *dmub);
+
+#endif /* _DMUB_DCN21_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.c
new file mode 100644
index 000000000000..4094eca212f0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dmub_reg.h"
+#include "../inc/dmub_srv.h"
+
+struct dmub_reg_value_masks {
+	uint32_t value;
+	uint32_t mask;
+};
+
+static inline void
+set_reg_field_value_masks(struct dmub_reg_value_masks *field_value_mask,
+			  uint32_t value, uint32_t mask, uint8_t shift)
+{
+	field_value_mask->value =
+		(field_value_mask->value & ~mask) | (mask & (value << shift));
+	field_value_mask->mask = field_value_mask->mask | mask;
+}
+
+static void set_reg_field_values(struct dmub_reg_value_masks *field_value_mask,
+				 uint32_t addr, int n, uint8_t shift1,
+				 uint32_t mask1, uint32_t field_value1,
+				 va_list ap)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	/* gather all bits value/mask getting updated in this register */
+	set_reg_field_value_masks(field_value_mask, field_value1, mask1,
+				  shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		set_reg_field_value_masks(field_value_mask, field_value, mask,
+					  shift);
+		i++;
+	}
+}
+
+static inline uint32_t get_reg_field_value_ex(uint32_t reg_value, uint32_t mask,
+					      uint8_t shift)
+{
+	return (mask & reg_value) >> shift;
+}
+
+void dmub_reg_update(struct dmub_srv *srv, uint32_t addr, int n, uint8_t shift1,
+		     uint32_t mask1, uint32_t field_value1, ...)
+{
+	struct dmub_reg_value_masks field_value_mask = { 0 };
+	uint32_t reg_val;
+	va_list ap;
+
+	va_start(ap, field_value1);
+	set_reg_field_values(&field_value_mask, addr, n, shift1, mask1,
+			     field_value1, ap);
+	va_end(ap);
+
+	reg_val = srv->funcs.reg_read(srv->user_ctx, addr);
+	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+	srv->funcs.reg_write(srv->user_ctx, addr, reg_val);
+}
+
+void dmub_reg_set(struct dmub_srv *srv, uint32_t addr, uint32_t reg_val, int n,
+		  uint8_t shift1, uint32_t mask1, uint32_t field_value1, ...)
+{
+	struct dmub_reg_value_masks field_value_mask = { 0 };
+	va_list ap;
+
+	va_start(ap, field_value1);
+	set_reg_field_values(&field_value_mask, addr, n, shift1, mask1,
+			     field_value1, ap);
+	va_end(ap);
+
+	reg_val = (reg_val & ~field_value_mask.mask) | field_value_mask.value;
+	srv->funcs.reg_write(srv->user_ctx, addr, reg_val);
+}
+
+void dmub_reg_get(struct dmub_srv *srv, uint32_t addr, uint8_t shift,
+		  uint32_t mask, uint32_t *field_value)
+{
+	uint32_t reg_val = srv->funcs.reg_read(srv->user_ctx, addr);
+	*field_value = get_reg_field_value_ex(reg_val, mask, shift);
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h
new file mode 100644
index 000000000000..c1f4030929a4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_reg.h
@@ -0,0 +1,124 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef _DMUB_REG_H_
+#define _DMUB_REG_H_
+
+#include "../inc/dmub_types.h"
+
+struct dmub_srv;
+
+/* Register offset and field lookup. */
+
+#define BASE(seg) BASE_INNER(seg)
+
+#define REG_OFFSET(reg_name) (BASE(mm##reg_name##_BASE_IDX) + mm##reg_name)
+
+#define FD_SHIFT(reg_name, field) reg_name##__##field##__SHIFT
+
+#define FD_MASK(reg_name, field) reg_name##__##field##_MASK
+
+#define REG(reg) (REGS)->offset.reg
+
+#define FD(reg_field) (REGS)->shift.reg_field, (REGS)->mask.reg_field
+
+#define FN(reg_name, field) FD(reg_name##__##field)
+
+/* Register reads and writes. */
+
+#define REG_READ(reg) ((CTX)->funcs.reg_read((CTX)->user_ctx, REG(reg)))
+
+#define REG_WRITE(reg, val) \
+	((CTX)->funcs.reg_write((CTX)->user_ctx, REG(reg), (val)))
+
+/* Register field setting. */
+
+#define REG_SET_N(reg_name, n, initial_val, ...) \
+	dmub_reg_set(CTX, REG(reg_name), initial_val, n, __VA_ARGS__)
+
+#define REG_SET(reg_name, initial_val, field, val) \
+		REG_SET_N(reg_name, 1, initial_val, \
+				FN(reg_name, field), val)
+
+#define REG_SET_2(reg, init_value, f1, v1, f2, v2) \
+		REG_SET_N(reg, 2, init_value, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2)
+
+#define REG_SET_3(reg, init_value, f1, v1, f2, v2, f3, v3) \
+		REG_SET_N(reg, 3, init_value, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3)
+
+#define REG_SET_4(reg, init_value, f1, v1, f2, v2, f3, v3, f4, v4) \
+		REG_SET_N(reg, 4, init_value, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3, \
+				FN(reg, f4), v4)
+
+/* Register field updating. */
+
+#define REG_UPDATE_N(reg_name, n, ...)\
+		dmub_reg_update(CTX, REG(reg_name), n, __VA_ARGS__)
+
+#define REG_UPDATE(reg_name, field, val)	\
+		REG_UPDATE_N(reg_name, 1, \
+				FN(reg_name, field), val)
+
+#define REG_UPDATE_2(reg, f1, v1, f2, v2)	\
+		REG_UPDATE_N(reg, 2,\
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+#define REG_UPDATE_3(reg, f1, v1, f2, v2, f3, v3) \
+		REG_UPDATE_N(reg, 3, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3)
+
+#define REG_UPDATE_4(reg, f1, v1, f2, v2, f3, v3, f4, v4) \
+		REG_UPDATE_N(reg, 4, \
+				FN(reg, f1), v1, \
+				FN(reg, f2), v2, \
+				FN(reg, f3), v3, \
+				FN(reg, f4), v4)
+
+/* Register field getting. */
+
+#define REG_GET(reg_name, field, val) \
+	dmub_reg_get(CTX, REG(reg_name), FN(reg_name, field), val)
+
+void dmub_reg_set(struct dmub_srv *srv, uint32_t addr, uint32_t reg_val, int n,
+		  uint8_t shift1, uint32_t mask1, uint32_t field_value1, ...);
+
+void dmub_reg_update(struct dmub_srv *srv, uint32_t addr, int n, uint8_t shift1,
+		     uint32_t mask1, uint32_t field_value1, ...);
+
+void dmub_reg_get(struct dmub_srv *srv, uint32_t addr, uint8_t shift,
+		  uint32_t mask, uint32_t *field_value);
+
+#endif /* _DMUB_REG_H_ */
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
new file mode 100644
index 000000000000..dee676335d73
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -0,0 +1,505 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "../inc/dmub_srv.h"
+#include "dmub_dcn20.h"
+#include "dmub_dcn21.h"
+#include "dmub_fw_meta.h"
+#include "os_types.h"
+/*
+ * Note: the DMUB service is standalone. No additional headers should be
+ * added below or above this line unless they reside within the DMUB
+ * folder.
+ */
+
+/* Alignment for framebuffer memory. */
+#define DMUB_FB_ALIGNMENT (1024 * 1024)
+
+/* Stack size. */
+#define DMUB_STACK_SIZE (128 * 1024)
+
+/* Context size. */
+#define DMUB_CONTEXT_SIZE (512 * 1024)
+
+/* Mailbox size */
+#define DMUB_MAILBOX_SIZE (DMUB_RB_SIZE)
+
+/* Default state size if meta is absent. */
+#define DMUB_FW_STATE_SIZE (1024)
+
+/* Default tracebuffer size if meta is absent. */
+#define DMUB_TRACE_BUFFER_SIZE (1024)
+
+/* Number of windows in use. */
+#define DMUB_NUM_WINDOWS (DMUB_WINDOW_6_FW_STATE + 1)
+/* Base addresses. */
+
+#define DMUB_CW0_BASE (0x60000000)
+#define DMUB_CW1_BASE (0x61000000)
+#define DMUB_CW3_BASE (0x63000000)
+#define DMUB_CW5_BASE (0x65000000)
+#define DMUB_CW6_BASE (0x66000000)
+
+static inline uint32_t dmub_align(uint32_t val, uint32_t factor)
+{
+	return (val + factor - 1) / factor * factor;
+}
+
+static void dmub_flush_buffer_mem(const struct dmub_fb *fb)
+{
+	const uint8_t *base = (const uint8_t *)fb->cpu_addr;
+	uint8_t buf[64];
+	uint32_t pos, end;
+
+	/**
+	 * Read 64-byte chunks since we don't want to store a
+	 * large temporary buffer for this purpose.
+	 */
+	end = fb->size / sizeof(buf) * sizeof(buf);
+
+	for (pos = 0; pos < end; pos += sizeof(buf))
+		dmub_memcpy(buf, base + pos, sizeof(buf));
+
+	/* Read anything leftover into the buffer. */
+	if (end < fb->size)
+		dmub_memcpy(buf, base + pos, fb->size - end);
+}
+
+static const struct dmub_fw_meta_info *
+dmub_get_fw_meta_info(const uint8_t *fw_bss_data, uint32_t fw_bss_data_size)
+{
+	const union dmub_fw_meta *meta;
+
+	if (fw_bss_data == NULL)
+		return NULL;
+
+	if (fw_bss_data_size < sizeof(union dmub_fw_meta) + DMUB_FW_META_OFFSET)
+		return NULL;
+
+	meta = (const union dmub_fw_meta *)(fw_bss_data + fw_bss_data_size -
+					    DMUB_FW_META_OFFSET -
+					    sizeof(union dmub_fw_meta));
+
+	if (meta->info.magic_value != DMUB_FW_META_MAGIC)
+		return NULL;
+
+	return &meta->info;
+}
+
+static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic)
+{
+	struct dmub_srv_hw_funcs *funcs = &dmub->hw_funcs;
+
+	switch (asic) {
+	case DMUB_ASIC_DCN20:
+	case DMUB_ASIC_DCN21:
+		dmub->regs = &dmub_srv_dcn20_regs;
+
+		funcs->reset = dmub_dcn20_reset;
+		funcs->reset_release = dmub_dcn20_reset_release;
+		funcs->backdoor_load = dmub_dcn20_backdoor_load;
+		funcs->setup_windows = dmub_dcn20_setup_windows;
+		funcs->setup_mailbox = dmub_dcn20_setup_mailbox;
+		funcs->get_inbox1_rptr = dmub_dcn20_get_inbox1_rptr;
+		funcs->set_inbox1_wptr = dmub_dcn20_set_inbox1_wptr;
+		funcs->is_supported = dmub_dcn20_is_supported;
+		funcs->is_hw_init = dmub_dcn20_is_hw_init;
+
+		if (asic == DMUB_ASIC_DCN21) {
+			dmub->regs = &dmub_srv_dcn21_regs;
+
+			funcs->is_auto_load_done = dmub_dcn21_is_auto_load_done;
+			funcs->is_phy_init = dmub_dcn21_is_phy_init;
+		}
+		break;
+
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+enum dmub_status dmub_srv_create(struct dmub_srv *dmub,
+				 const struct dmub_srv_create_params *params)
+{
+	enum dmub_status status = DMUB_STATUS_OK;
+
+	dmub_memset(dmub, 0, sizeof(*dmub));
+
+	dmub->funcs = params->funcs;
+	dmub->user_ctx = params->user_ctx;
+	dmub->asic = params->asic;
+	dmub->is_virtual = params->is_virtual;
+
+	/* Setup asic dependent hardware funcs. */
+	if (!dmub_srv_hw_setup(dmub, params->asic)) {
+		status = DMUB_STATUS_INVALID;
+		goto cleanup;
+	}
+
+	/* Override (some) hardware funcs based on user params. */
+	if (params->hw_funcs) {
+		if (params->hw_funcs->get_inbox1_rptr)
+			dmub->hw_funcs.get_inbox1_rptr =
+				params->hw_funcs->get_inbox1_rptr;
+
+		if (params->hw_funcs->set_inbox1_wptr)
+			dmub->hw_funcs.set_inbox1_wptr =
+				params->hw_funcs->set_inbox1_wptr;
+
+		if (params->hw_funcs->is_supported)
+			dmub->hw_funcs.is_supported =
+				params->hw_funcs->is_supported;
+	}
+
+	/* Sanity checks for required hw func pointers. */
+	if (!dmub->hw_funcs.get_inbox1_rptr ||
+	    !dmub->hw_funcs.set_inbox1_wptr) {
+		status = DMUB_STATUS_INVALID;
+		goto cleanup;
+	}
+
+cleanup:
+	if (status == DMUB_STATUS_OK)
+		dmub->sw_init = true;
+	else
+		dmub_srv_destroy(dmub);
+
+	return status;
+}
+
+void dmub_srv_destroy(struct dmub_srv *dmub)
+{
+	dmub_memset(dmub, 0, sizeof(*dmub));
+}
+
+enum dmub_status
+dmub_srv_calc_region_info(struct dmub_srv *dmub,
+			  const struct dmub_srv_region_params *params,
+			  struct dmub_srv_region_info *out)
+{
+	struct dmub_region *inst = &out->regions[DMUB_WINDOW_0_INST_CONST];
+	struct dmub_region *stack = &out->regions[DMUB_WINDOW_1_STACK];
+	struct dmub_region *data = &out->regions[DMUB_WINDOW_2_BSS_DATA];
+	struct dmub_region *bios = &out->regions[DMUB_WINDOW_3_VBIOS];
+	struct dmub_region *mail = &out->regions[DMUB_WINDOW_4_MAILBOX];
+	struct dmub_region *trace_buff = &out->regions[DMUB_WINDOW_5_TRACEBUFF];
+	struct dmub_region *fw_state = &out->regions[DMUB_WINDOW_6_FW_STATE];
+	const struct dmub_fw_meta_info *fw_info;
+	uint32_t fw_state_size = DMUB_FW_STATE_SIZE;
+	uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	memset(out, 0, sizeof(*out));
+
+	out->num_regions = DMUB_NUM_WINDOWS;
+
+	inst->base = 0x0;
+	inst->top = inst->base + params->inst_const_size;
+
+	data->base = dmub_align(inst->top, 256);
+	data->top = data->base + params->bss_data_size;
+
+	/*
+	 * All cache windows below should be aligned to the size
+	 * of the DMCUB cache line, 64 bytes.
+	 */
+
+	stack->base = dmub_align(data->top, 256);
+	stack->top = stack->base + DMUB_STACK_SIZE + DMUB_CONTEXT_SIZE;
+
+	bios->base = dmub_align(stack->top, 256);
+	bios->top = bios->base + params->vbios_size;
+
+	mail->base = dmub_align(bios->top, 256);
+	mail->top = mail->base + DMUB_MAILBOX_SIZE;
+
+	fw_info = dmub_get_fw_meta_info(params->fw_bss_data,
+					params->bss_data_size);
+
+	if (fw_info) {
+		fw_state_size = fw_info->fw_region_size;
+		trace_buffer_size = fw_info->trace_buffer_size;
+	}
+
+	trace_buff->base = dmub_align(mail->top, 256);
+	trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64);
+
+	fw_state->base = dmub_align(trace_buff->top, 256);
+	fw_state->top = fw_state->base + dmub_align(fw_state_size, 64);
+
+	out->fb_size = dmub_align(fw_state->top, 4096);
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub,
+				       const struct dmub_srv_fb_params *params,
+				       struct dmub_srv_fb_info *out)
+{
+	uint8_t *cpu_base;
+	uint64_t gpu_base;
+	uint32_t i;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	memset(out, 0, sizeof(*out));
+
+	if (params->region_info->num_regions != DMUB_NUM_WINDOWS)
+		return DMUB_STATUS_INVALID;
+
+	cpu_base = (uint8_t *)params->cpu_addr;
+	gpu_base = params->gpu_addr;
+
+	for (i = 0; i < DMUB_NUM_WINDOWS; ++i) {
+		const struct dmub_region *reg =
+			&params->region_info->regions[i];
+
+		out->fb[i].cpu_addr = cpu_base + reg->base;
+		out->fb[i].gpu_addr = gpu_base + reg->base;
+		out->fb[i].size = reg->top - reg->base;
+	}
+
+	out->num_fb = DMUB_NUM_WINDOWS;
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_has_hw_support(struct dmub_srv *dmub,
+					 bool *is_supported)
+{
+	*is_supported = false;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (dmub->hw_funcs.is_supported)
+		*is_supported = dmub->hw_funcs.is_supported(dmub);
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_is_hw_init(struct dmub_srv *dmub, bool *is_hw_init)
+{
+	*is_hw_init = false;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (dmub->hw_funcs.is_hw_init)
+		*is_hw_init = dmub->hw_funcs.is_hw_init(dmub);
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub,
+				  const struct dmub_srv_hw_params *params)
+{
+	struct dmub_fb *inst_fb = params->fb[DMUB_WINDOW_0_INST_CONST];
+	struct dmub_fb *stack_fb = params->fb[DMUB_WINDOW_1_STACK];
+	struct dmub_fb *data_fb = params->fb[DMUB_WINDOW_2_BSS_DATA];
+	struct dmub_fb *bios_fb = params->fb[DMUB_WINDOW_3_VBIOS];
+	struct dmub_fb *mail_fb = params->fb[DMUB_WINDOW_4_MAILBOX];
+	struct dmub_fb *tracebuff_fb = params->fb[DMUB_WINDOW_5_TRACEBUFF];
+	struct dmub_fb *fw_state_fb = params->fb[DMUB_WINDOW_6_FW_STATE];
+
+	struct dmub_rb_init_params rb_params;
+	struct dmub_window cw0, cw1, cw2, cw3, cw4, cw5, cw6;
+	struct dmub_region inbox1;
+
+	if (!dmub->sw_init)
+		return DMUB_STATUS_INVALID;
+
+	dmub->fb_base = params->fb_base;
+	dmub->fb_offset = params->fb_offset;
+	dmub->psp_version = params->psp_version;
+
+	if (inst_fb && data_fb) {
+		cw0.offset.quad_part = inst_fb->gpu_addr;
+		cw0.region.base = DMUB_CW0_BASE;
+		cw0.region.top = cw0.region.base + inst_fb->size - 1;
+
+		cw1.offset.quad_part = stack_fb->gpu_addr;
+		cw1.region.base = DMUB_CW1_BASE;
+		cw1.region.top = cw1.region.base + stack_fb->size - 1;
+
+		/**
+		 * Read back all the instruction memory so we don't hang the
+		 * DMCUB when backdoor loading if the write from x86 hasn't been
+		 * flushed yet. This only occurs in backdoor loading.
+		 */
+		dmub_flush_buffer_mem(inst_fb);
+
+		if (params->load_inst_const && dmub->hw_funcs.backdoor_load)
+			dmub->hw_funcs.backdoor_load(dmub, &cw0, &cw1);
+	}
+
+	if (dmub->hw_funcs.reset)
+		dmub->hw_funcs.reset(dmub);
+
+	if (inst_fb && data_fb && bios_fb && mail_fb && tracebuff_fb &&
+	    fw_state_fb) {
+		cw2.offset.quad_part = data_fb->gpu_addr;
+		cw2.region.base = DMUB_CW0_BASE + inst_fb->size;
+		cw2.region.top = cw2.region.base + data_fb->size;
+
+		cw3.offset.quad_part = bios_fb->gpu_addr;
+		cw3.region.base = DMUB_CW3_BASE;
+		cw3.region.top = cw3.region.base + bios_fb->size;
+
+		cw4.offset.quad_part = mail_fb->gpu_addr;
+		cw4.region.base = cw3.region.top + 1;
+		cw4.region.top = cw4.region.base + mail_fb->size;
+
+		inbox1.base = cw4.region.base;
+		inbox1.top = cw4.region.top;
+
+		cw5.offset.quad_part = tracebuff_fb->gpu_addr;
+		cw5.region.base = DMUB_CW5_BASE;
+		cw5.region.top = cw5.region.base + tracebuff_fb->size;
+
+		cw6.offset.quad_part = fw_state_fb->gpu_addr;
+		cw6.region.base = DMUB_CW6_BASE;
+		cw6.region.top = cw6.region.base + fw_state_fb->size;
+
+		dmub->fw_state = fw_state_fb->cpu_addr;
+
+		if (dmub->hw_funcs.setup_windows)
+			dmub->hw_funcs.setup_windows(dmub, &cw2, &cw3, &cw4,
+						     &cw5, &cw6);
+
+		if (dmub->hw_funcs.setup_mailbox)
+			dmub->hw_funcs.setup_mailbox(dmub, &inbox1);
+	}
+
+	if (mail_fb) {
+		dmub_memset(&rb_params, 0, sizeof(rb_params));
+		rb_params.ctx = dmub;
+		rb_params.base_address = mail_fb->cpu_addr;
+		rb_params.capacity = DMUB_RB_SIZE;
+
+		dmub_rb_init(&dmub->inbox1_rb, &rb_params);
+	}
+
+	if (dmub->hw_funcs.reset_release)
+		dmub->hw_funcs.reset_release(dmub);
+
+	dmub->hw_init = true;
+
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub,
+				    const struct dmub_cmd_header *cmd)
+{
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (dmub_rb_push_front(&dmub->inbox1_rb, cmd))
+		return DMUB_STATUS_OK;
+
+	return DMUB_STATUS_QUEUE_FULL;
+}
+
+enum dmub_status dmub_srv_cmd_execute(struct dmub_srv *dmub)
+{
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	/**
+	 * Read back all the queued commands to ensure that they've
+	 * been flushed to framebuffer memory. Otherwise DMCUB might
+	 * read back stale, fully invalid or partially invalid data.
+	 */
+	dmub_rb_flush_pending(&dmub->inbox1_rb);
+
+	dmub->hw_funcs.set_inbox1_wptr(dmub, dmub->inbox1_rb.wrpt);
+	return DMUB_STATUS_OK;
+}
+
+enum dmub_status dmub_srv_wait_for_auto_load(struct dmub_srv *dmub,
+					     uint32_t timeout_us)
+{
+	uint32_t i;
+
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (!dmub->hw_funcs.is_auto_load_done)
+		return DMUB_STATUS_OK;
+
+	for (i = 0; i <= timeout_us; i += 100) {
+		if (dmub->hw_funcs.is_auto_load_done(dmub))
+			return DMUB_STATUS_OK;
+
+		udelay(100);
+	}
+
+	return DMUB_STATUS_TIMEOUT;
+}
+
+enum dmub_status dmub_srv_wait_for_phy_init(struct dmub_srv *dmub,
+					    uint32_t timeout_us)
+{
+	uint32_t i = 0;
+
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	if (!dmub->hw_funcs.is_phy_init)
+		return DMUB_STATUS_OK;
+
+	for (i = 0; i <= timeout_us; i += 10) {
+		if (dmub->hw_funcs.is_phy_init(dmub))
+			return DMUB_STATUS_OK;
+
+		udelay(10);
+	}
+
+	return DMUB_STATUS_TIMEOUT;
+}
+
+enum dmub_status dmub_srv_wait_for_idle(struct dmub_srv *dmub,
+					uint32_t timeout_us)
+{
+	uint32_t i;
+
+	if (!dmub->hw_init)
+		return DMUB_STATUS_INVALID;
+
+	for (i = 0; i <= timeout_us; ++i) {
+		dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub);
+		if (dmub_rb_empty(&dmub->inbox1_rb))
+			return DMUB_STATUS_OK;
+
+		udelay(1);
+	}
+
+	return DMUB_STATUS_TIMEOUT;
+}
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 1be6c44fd32f..a2903985b9e8 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -134,23 +134,34 @@
 #define PICASSO_A0 0x41
 /* DCN1_01 */
 #define RAVEN2_A0 0x81
+#define RAVEN2_15D8_REV_94 0x94
+#define RAVEN2_15D8_REV_95 0x95
+#define RAVEN2_15D8_REV_E3 0xE3
+#define RAVEN2_15D8_REV_E4 0xE4
+#define RAVEN2_15D8_REV_E9 0xE9
+#define RAVEN2_15D8_REV_EA 0xEA
+#define RAVEN2_15D8_REV_EB 0xEB
 #define RAVEN1_F0 0xF0
 #define RAVEN_UNKNOWN 0xFF
-
-#define PICASSO_15D8_REV_E3 0xE3
-#define PICASSO_15D8_REV_E4 0xE4
-
+#ifndef ASICREV_IS_RAVEN
 #define ASICREV_IS_RAVEN(eChipRev) ((eChipRev >= RAVEN_A0) && eChipRev < RAVEN_UNKNOWN)
-#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
-#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < PICASSO_15D8_REV_E3))
-#define ASICREV_IS_DALI(eChipRev) ((eChipRev >= PICASSO_15D8_REV_E3) && (eChipRev < RAVEN1_F0))
+#endif
 
+#define ASICREV_IS_PICASSO(eChipRev) ((eChipRev >= PICASSO_A0) && (eChipRev < RAVEN2_A0))
+#ifndef ASICREV_IS_RAVEN2
+#define ASICREV_IS_RAVEN2(eChipRev) ((eChipRev >= RAVEN2_A0) && (eChipRev < RAVEN1_F0))
+#endif
 #define ASICREV_IS_RV1_F0(eChipRev) ((eChipRev >= RAVEN1_F0) && (eChipRev < RAVEN_UNKNOWN))
-
+#define ASICREV_IS_DALI(eChipRev) ((eChipRev == RAVEN2_15D8_REV_E3) \
+		|| (eChipRev == RAVEN2_15D8_REV_E4))
+#define ASICREV_IS_POLLOCK(eChipRev) (eChipRev == RAVEN2_15D8_REV_94 \
+		|| eChipRev == RAVEN2_15D8_REV_95 \
+			|| eChipRev == RAVEN2_15D8_REV_E9 \
+				|| eChipRev == RAVEN2_15D8_REV_EA \
+					|| eChipRev == RAVEN2_15D8_REV_EB)
 
 #define FAMILY_RV 142 /* DCN 1*/
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 
 #define FAMILY_NV 143 /* DCN 2*/
 
@@ -164,12 +175,9 @@ enum {
 #define ASICREV_IS_NAVI10_P(eChipRev)        (eChipRev < NV_NAVI12_P_A0)
 #define ASICREV_IS_NAVI12_P(eChipRev)        ((eChipRev >= NV_NAVI12_P_A0) && (eChipRev < NV_NAVI14_M_A0))
 #define ASICREV_IS_NAVI14_M(eChipRev)        ((eChipRev >= NV_NAVI14_M_A0) && (eChipRev < NV_UNKNOWN))
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 #define RENOIR_A0 0x91
 #define DEVICE_ID_RENOIR_1636 0x1636   // Renoir
 #define ASICREV_IS_RENOIR(eChipRev) ((eChipRev >= RENOIR_A0) && (eChipRev < 0xFF))
-#endif
 
 /*
  * ASIC chip ID
diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h
index fcc42372b6cf..0b6859189ca7 100644
--- a/drivers/gpu/drm/amd/display/include/dal_types.h
+++ b/drivers/gpu/drm/amd/display/include/dal_types.h
@@ -46,12 +46,8 @@ enum dce_version {
 	DCE_VERSION_MAX,
 	DCN_VERSION_1_0,
 	DCN_VERSION_1_01,
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	DCN_VERSION_2_0,
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	DCN_VERSION_2_1,
-#endif
 	DCN_VERSION_MAX
 };
 
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
index f312834fef50..d51de94e4bc3 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
@@ -178,7 +178,8 @@ struct dc_firmware_info {
 	uint32_t default_engine_clk; /* in KHz */
 	uint32_t dp_phy_ref_clk; /* in KHz - DCE12 only */
 	uint32_t i2c_engine_ref_clk; /* in KHz - DCE12 only */
-
+	bool oem_i2c_present;
+	uint8_t oem_i2c_obj_id;
 
 };
 
diff --git a/drivers/gpu/drm/amd/display/include/link_service_types.h b/drivers/gpu/drm/amd/display/include/link_service_types.h
index 876b0b3e1a9c..4869d4562e4d 100644
--- a/drivers/gpu/drm/amd/display/include/link_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/link_service_types.h
@@ -123,6 +123,13 @@ enum dp_test_pattern {
 	DP_TEST_PATTERN_UNSUPPORTED
 };
 
+enum dp_test_pattern_color_space {
+	DP_TEST_PATTERN_COLOR_SPACE_RGB,
+	DP_TEST_PATTERN_COLOR_SPACE_YCBCR601,
+	DP_TEST_PATTERN_COLOR_SPACE_YCBCR709,
+	DP_TEST_PATTERN_COLOR_SPACE_UNDEFINED
+};
+
 enum dp_panel_mode {
 	/* not required */
 	DP_PANEL_MODE_DEFAULT,
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index 2b219cdb13ad..89a709267019 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -66,12 +66,8 @@
 #define DC_LOG_GAMMA(...) pr_debug("[GAMMA]:"__VA_ARGS__)
 #define DC_LOG_ALL_GAMMA(...) pr_debug("[GAMMA]:"__VA_ARGS__)
 #define DC_LOG_ALL_TF_CHANNELS(...) pr_debug("[GAMMA]:"__VA_ARGS__)
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define DC_LOG_DSC(...) DRM_DEBUG_KMS(__VA_ARGS__)
-#endif
-#if defined(CONFIG_DRM_AMD_DC_DCN3_0) || defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #define DC_LOG_DWB(...) DRM_DEBUG_KMS(__VA_ARGS__)
-#endif
 
 struct dal_logger;
 
@@ -116,9 +112,7 @@ enum dc_log_type {
 	LOG_PERF_TRACE,
 	LOG_DISPLAYSTATS,
 	LOG_HDMI_RETIMER_REDRIVER,
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	LOG_DSC,
-#endif
 	LOG_DWB,
 	LOG_GAMMA_DEBUG,
 	LOG_MAX_HW_POINTS,
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 1de4805cb8c7..1b278c42809a 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -154,6 +154,7 @@ static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 
 	struct fixed31_32 l_pow_m1;
 	struct fixed31_32 base, div;
+	struct fixed31_32 base2;
 
 
 	if (dc_fixpt_lt(in_x, dc_fixpt_zero))
@@ -163,13 +164,15 @@ static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 			dc_fixpt_div(dc_fixpt_one, m2));
 	base = dc_fixpt_sub(l_pow_m1, c1);
 
-	if (dc_fixpt_lt(base, dc_fixpt_zero))
-		base = dc_fixpt_zero;
-
 	div = dc_fixpt_sub(c2, dc_fixpt_mul(c3, l_pow_m1));
 
-	*out_y = dc_fixpt_pow(dc_fixpt_div(base, div),
-			dc_fixpt_div(dc_fixpt_one, m1));
+	base2 = dc_fixpt_div(base, div);
+	//avoid complex numbers
+	if (dc_fixpt_lt(base2, dc_fixpt_zero))
+		base2 = dc_fixpt_sub(dc_fixpt_zero, base2);
+
+
+	*out_y = dc_fixpt_pow(base2, dc_fixpt_div(dc_fixpt_one, m1));
 
 }
 
@@ -361,8 +364,10 @@ static struct fixed31_32 translate_from_linear_space(
 			scratch_2 = dc_fixpt_mul(gamma_of_2,
 					pow_buffer[pow_buffer_ptr%16]);
 
-		pow_buffer[pow_buffer_ptr%16] = scratch_2;
-		pow_buffer_ptr++;
+		if (pow_buffer_ptr != -1) {
+			pow_buffer[pow_buffer_ptr%16] = scratch_2;
+			pow_buffer_ptr++;
+		}
 
 		scratch_1 = dc_fixpt_mul(scratch_1, scratch_2);
 		scratch_1 = dc_fixpt_sub(scratch_1, args->a2);
@@ -937,7 +942,6 @@ static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma,
 	struct fixed31_32 max_display;
 	struct fixed31_32 min_display;
 	struct fixed31_32 max_content;
-	struct fixed31_32 min_content;
 	struct fixed31_32 clip = dc_fixpt_one;
 	struct fixed31_32 output;
 	bool use_eetf = false;
@@ -951,7 +955,6 @@ static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma,
 	max_display = dc_fixpt_from_int(fs_params->max_display);
 	min_display = dc_fixpt_from_fraction(fs_params->min_display, 10000);
 	max_content = dc_fixpt_from_int(fs_params->max_content);
-	min_content = dc_fixpt_from_fraction(fs_params->min_content, 10000);
 	sdr_white_level = dc_fixpt_from_int(fs_params->sdr_white_level);
 
 	if (fs_params->min_display > 1000) // cap at 0.1 at the bottom
@@ -2000,10 +2003,28 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
 	tf_pts->x_point_at_y1_green = 1;
 	tf_pts->x_point_at_y1_blue = 1;
 
-	map_regamma_hw_to_x_user(ramp, coeff, rgb_user,
-			coordinates_x, axis_x, curve,
-			MAX_HW_POINTS, tf_pts,
-			mapUserRamp && ramp && ramp->type == GAMMA_RGB_256);
+	if (input_tf->tf == TRANSFER_FUNCTION_PQ) {
+		/* just copy current rgb_regamma into  tf_pts */
+		struct pwl_float_data_ex *curvePt = curve;
+		int i = 0;
+
+		while (i <= MAX_HW_POINTS) {
+			tf_pts->red[i]   = curvePt->r;
+			tf_pts->green[i] = curvePt->g;
+			tf_pts->blue[i]  = curvePt->b;
+			++curvePt;
+			++i;
+		}
+	} else {
+		//clamps to 0-1
+		map_regamma_hw_to_x_user(ramp, coeff, rgb_user,
+				coordinates_x, axis_x, curve,
+				MAX_HW_POINTS, tf_pts,
+				mapUserRamp && ramp && ramp->type == GAMMA_RGB_256);
+	}
+
+
+
 	if (ramp->type == GAMMA_CUSTOM)
 		apply_lut_1d(ramp, MAX_HW_POINTS, tf_pts);
 
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 5437b50e9f90..6e5ecefe7d9d 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -37,8 +37,8 @@
 #define STATIC_SCREEN_RAMP_DELTA_REFRESH_RATE_PER_FRAME ((1000 / 60) * 65)
 /* Number of elements in the render times cache array */
 #define RENDER_TIMES_MAX_COUNT 10
-/* Threshold to exit BTR (to avoid frequent enter-exits at the lower limit) */
-#define BTR_EXIT_MARGIN 2000
+/* Threshold to exit/exit BTR (to avoid frequent enter-exits at the lower limit) */
+#define BTR_MAX_MARGIN 2500
 /* Threshold to change BTR multiplier (to avoid frequent changes) */
 #define BTR_DRIFT_MARGIN 2000
 /*Threshold to exit fixed refresh rate*/
@@ -122,7 +122,7 @@ static unsigned int calc_v_total_from_refresh(
 		const struct dc_stream_state *stream,
 		unsigned int refresh_in_uhz)
 {
-	unsigned int v_total = stream->timing.v_total;
+	unsigned int v_total;
 	unsigned int frame_duration_in_ns;
 
 	frame_duration_in_ns =
@@ -254,24 +254,22 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 	unsigned int delta_from_mid_point_in_us_1 = 0xFFFFFFFF;
 	unsigned int delta_from_mid_point_in_us_2 = 0xFFFFFFFF;
 	unsigned int frames_to_insert = 0;
-	unsigned int min_frame_duration_in_ns = 0;
-	unsigned int max_render_time_in_us = in_out_vrr->max_duration_in_us;
 	unsigned int delta_from_mid_point_delta_in_us;
-
-	min_frame_duration_in_ns = ((unsigned int) (div64_u64(
-		(1000000000ULL * 1000000),
-		in_out_vrr->max_refresh_in_uhz)));
+	unsigned int max_render_time_in_us =
+			in_out_vrr->max_duration_in_us - in_out_vrr->btr.margin_in_us;
 
 	/* Program BTR */
-	if (last_render_time_in_us + BTR_EXIT_MARGIN < max_render_time_in_us) {
+	if ((last_render_time_in_us + in_out_vrr->btr.margin_in_us / 2) < max_render_time_in_us) {
 		/* Exit Below the Range */
 		if (in_out_vrr->btr.btr_active) {
 			in_out_vrr->btr.frame_counter = 0;
 			in_out_vrr->btr.btr_active = false;
 		}
-	} else if (last_render_time_in_us > max_render_time_in_us) {
+	} else if (last_render_time_in_us > (max_render_time_in_us + in_out_vrr->btr.margin_in_us / 2)) {
 		/* Enter Below the Range */
-		in_out_vrr->btr.btr_active = true;
+		if (!in_out_vrr->btr.btr_active) {
+			in_out_vrr->btr.btr_active = true;
+		}
 	}
 
 	/* BTR set to "not active" so disengage */
@@ -327,7 +325,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		/* Choose number of frames to insert based on how close it
 		 * can get to the mid point of the variable range.
 		 */
-		if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) {
+		if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us &&
+				(delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 ||
+						mid_point_frames_floor < 2)) {
 			frames_to_insert = mid_point_frames_ceil;
 			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 -
 					delta_from_mid_point_in_us_1;
@@ -343,7 +343,7 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		if (in_out_vrr->btr.frames_to_insert != 0 &&
 				delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) {
 			if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) <
-					in_out_vrr->max_duration_in_us) &&
+					max_render_time_in_us) &&
 				((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) >
 					in_out_vrr->min_duration_in_us))
 				frames_to_insert = in_out_vrr->btr.frames_to_insert;
@@ -796,6 +796,11 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 		refresh_range = in_out_vrr->max_refresh_in_uhz -
 				in_out_vrr->min_refresh_in_uhz;
 
+		in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us -
+				2 * in_out_vrr->min_duration_in_us;
+		if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN)
+			in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN;
+
 		in_out_vrr->supported = true;
 	}
 
@@ -811,6 +816,9 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 	in_out_vrr->btr.inserted_duration_in_us = 0;
 	in_out_vrr->btr.frames_to_insert = 0;
 	in_out_vrr->btr.frame_counter = 0;
+	in_out_vrr->fixed.fixed_active = false;
+	in_out_vrr->fixed.target_refresh_in_uhz = 0;
+
 	in_out_vrr->btr.mid_point_in_us =
 				(in_out_vrr->min_duration_in_us +
 				 in_out_vrr->max_duration_in_us) / 2;
@@ -826,6 +834,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 		in_out_vrr->adjust.v_total_max = stream->timing.v_total;
 	} else if (in_out_vrr->state == VRR_STATE_ACTIVE_VARIABLE &&
 			refresh_range >= MIN_REFRESH_RANGE_IN_US) {
+
 		in_out_vrr->adjust.v_total_min =
 			calc_v_total_from_refresh(stream,
 				in_out_vrr->max_refresh_in_uhz);
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/Makefile b/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
index 1c3c6d47973a..904424da01b5 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
@@ -24,7 +24,8 @@
 #
 
 HDCP = hdcp_ddc.o hdcp_log.o hdcp_psp.o hdcp.o \
-		hdcp1_execution.o hdcp1_transition.o
+		hdcp1_execution.o hdcp1_transition.o \
+		hdcp2_execution.o hdcp2_transition.o
 
 AMD_DAL_HDCP = $(addprefix $(AMDDALPATH)/modules/hdcp/,$(HDCP))
 #$(info ************  DAL-HDCP_MAKEFILE ************)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
index d7ac445dec6f..8aa528e874c4 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
@@ -37,24 +37,52 @@ static void push_error_status(struct mod_hdcp *hdcp,
 		HDCP_ERROR_TRACE(hdcp, status);
 	}
 
-	hdcp->connection.hdcp1_retry_count++;
+	if (is_hdcp1(hdcp)) {
+		hdcp->connection.hdcp1_retry_count++;
+	} else if (is_hdcp2(hdcp)) {
+		hdcp->connection.hdcp2_retry_count++;
+	}
 }
 
 static uint8_t is_cp_desired_hdcp1(struct mod_hdcp *hdcp)
 {
-	int i, display_enabled = 0;
+	int i, is_auth_needed = 0;
 
-	/* if all displays on the link are disabled, hdcp is not desired */
+	/* if all displays on the link don't need authentication,
+	 * hdcp is not desired
+	 */
 	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
 		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_INACTIVE &&
 				!hdcp->connection.displays[i].adjust.disable) {
-			display_enabled = 1;
+			is_auth_needed = 1;
 			break;
 		}
 	}
 
 	return (hdcp->connection.hdcp1_retry_count < MAX_NUM_OF_ATTEMPTS) &&
-			display_enabled && !hdcp->connection.link.adjust.hdcp1.disable;
+			is_auth_needed &&
+			!hdcp->connection.link.adjust.hdcp1.disable;
+}
+
+static uint8_t is_cp_desired_hdcp2(struct mod_hdcp *hdcp)
+{
+	int i, is_auth_needed = 0;
+
+	/* if all displays on the link don't need authentication,
+	 * hdcp is not desired
+	 */
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_INACTIVE &&
+				!hdcp->connection.displays[i].adjust.disable) {
+			is_auth_needed = 1;
+			break;
+		}
+	}
+
+	return (hdcp->connection.hdcp2_retry_count < MAX_NUM_OF_ATTEMPTS) &&
+			is_auth_needed &&
+			!hdcp->connection.link.adjust.hdcp2.disable &&
+			!hdcp->connection.is_hdcp2_revoked;
 }
 
 static enum mod_hdcp_status execution(struct mod_hdcp *hdcp,
@@ -82,6 +110,11 @@ static enum mod_hdcp_status execution(struct mod_hdcp *hdcp,
 	} else if (is_in_hdcp1_dp_states(hdcp)) {
 		status = mod_hdcp_hdcp1_dp_execution(hdcp,
 				event_ctx, &input->hdcp1);
+	} else if (is_in_hdcp2_states(hdcp)) {
+		status = mod_hdcp_hdcp2_execution(hdcp, event_ctx, &input->hdcp2);
+	} else if (is_in_hdcp2_dp_states(hdcp)) {
+		status = mod_hdcp_hdcp2_dp_execution(hdcp,
+				event_ctx, &input->hdcp2);
 	}
 out:
 	return status;
@@ -99,7 +132,10 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 
 	if (is_in_initialized_state(hdcp)) {
 		if (is_dp_hdcp(hdcp))
-			if (is_cp_desired_hdcp1(hdcp)) {
+			if (is_cp_desired_hdcp2(hdcp)) {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, D2_A0_DETERMINE_RX_HDCP_CAPABLE);
+			} else if (is_cp_desired_hdcp1(hdcp)) {
 				callback_in_ms(0, output);
 				set_state_id(hdcp, output, D1_A0_DETERMINE_RX_HDCP_CAPABLE);
 			} else {
@@ -107,7 +143,10 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 				set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
 			}
 		else if (is_hdmi_dvi_sl_hdcp(hdcp))
-			if (is_cp_desired_hdcp1(hdcp)) {
+			if (is_cp_desired_hdcp2(hdcp)) {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H2_A0_KNOWN_HDCP2_CAPABLE_RX);
+			} else if (is_cp_desired_hdcp1(hdcp)) {
 				callback_in_ms(0, output);
 				set_state_id(hdcp, output, H1_A0_WAIT_FOR_ACTIVE_RX);
 			} else {
@@ -126,6 +165,12 @@ static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
 	} else if (is_in_hdcp1_dp_states(hdcp)) {
 		status = mod_hdcp_hdcp1_dp_transition(hdcp,
 				event_ctx, &input->hdcp1, output);
+	} else if (is_in_hdcp2_states(hdcp)) {
+		status = mod_hdcp_hdcp2_transition(hdcp,
+				event_ctx, &input->hdcp2, output);
+	} else if (is_in_hdcp2_dp_states(hdcp)) {
+		status = mod_hdcp_hdcp2_dp_transition(hdcp,
+				event_ctx, &input->hdcp2, output);
 	} else {
 		status = MOD_HDCP_STATUS_INVALID_STATE;
 	}
@@ -139,9 +184,13 @@ static enum mod_hdcp_status reset_authentication(struct mod_hdcp *hdcp,
 	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
 
 	if (is_hdcp1(hdcp)) {
-		if (hdcp->auth.trans_input.hdcp1.create_session != UNKNOWN)
+		if (hdcp->auth.trans_input.hdcp1.create_session != UNKNOWN) {
+			/* TODO - update psp to unify create session failure
+			 * recovery between hdcp1 and 2.
+			 */
 			mod_hdcp_hdcp1_destroy_session(hdcp);
 
+		}
 		if (hdcp->auth.trans_input.hdcp1.add_topology == PASS) {
 			status = mod_hdcp_remove_display_topology(hdcp);
 			if (status != MOD_HDCP_STATUS_SUCCESS) {
@@ -154,6 +203,27 @@ static enum mod_hdcp_status reset_authentication(struct mod_hdcp *hdcp,
 		memset(&hdcp->auth, 0, sizeof(struct mod_hdcp_authentication));
 		memset(&hdcp->state, 0, sizeof(struct mod_hdcp_state));
 		set_state_id(hdcp, output, HDCP_INITIALIZED);
+	} else if (is_hdcp2(hdcp)) {
+		if (hdcp->auth.trans_input.hdcp2.create_session == PASS) {
+			status = mod_hdcp_hdcp2_destroy_session(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS) {
+				output->callback_needed = 0;
+				output->watchdog_timer_needed = 0;
+				goto out;
+			}
+		}
+		if (hdcp->auth.trans_input.hdcp2.add_topology == PASS) {
+			status = mod_hdcp_remove_display_topology(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS) {
+				output->callback_needed = 0;
+				output->watchdog_timer_needed = 0;
+				goto out;
+			}
+		}
+		HDCP_TOP_RESET_AUTH_TRACE(hdcp);
+		memset(&hdcp->auth, 0, sizeof(struct mod_hdcp_authentication));
+		memset(&hdcp->state, 0, sizeof(struct mod_hdcp_state));
+		set_state_id(hdcp, output, HDCP_INITIALIZED);
 	} else if (is_in_cp_not_desired_state(hdcp)) {
 		status = mod_hdcp_remove_display_topology(hdcp);
 		if (status != MOD_HDCP_STATUS_SUCCESS) {
@@ -347,7 +417,20 @@ enum mod_hdcp_status mod_hdcp_query_display(struct mod_hdcp *hdcp,
 	query->trace = &hdcp->connection.trace;
 	query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
 
-	mod_hdcp_hdcp1_get_link_encryption_status(hdcp, &query->encryption_status);
+	if (is_display_encryption_enabled(display)) {
+		if (is_hdcp1(hdcp)) {
+			query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON;
+		} else if (is_hdcp2(hdcp)) {
+			if (query->link->adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0)
+				query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON;
+			else if (query->link->adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_1)
+				query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON;
+			else
+				query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_ON;
+		}
+	} else {
+		query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+	}
 
 out:
 	return status;
@@ -420,7 +503,7 @@ enum mod_hdcp_operation_mode mod_hdcp_signal_type_to_operation_mode(
 		break;
 	default:
 		break;
-	};
+	}
 
 	return mode;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
index 5664bc0b5bd0..f98d3d9ecb6d 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
@@ -29,32 +29,8 @@
 #include "mod_hdcp.h"
 #include "hdcp_log.h"
 
-#define BCAPS_READY_MASK				0x20
-#define BCAPS_REPEATER_MASK				0x40
-#define BSTATUS_DEVICE_COUNT_MASK			0X007F
-#define BSTATUS_MAX_DEVS_EXCEEDED_MASK			0x0080
-#define BSTATUS_MAX_CASCADE_EXCEEDED_MASK		0x0800
-#define BCAPS_HDCP_CAPABLE_MASK_DP			0x01
-#define BCAPS_REPEATER_MASK_DP				0x02
-#define BSTATUS_READY_MASK_DP				0x01
-#define BSTATUS_R0_P_AVAILABLE_MASK_DP			0x02
-#define BSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP		0x04
-#define BSTATUS_REAUTH_REQUEST_MASK_DP			0x08
-#define BINFO_DEVICE_COUNT_MASK_DP			0X007F
-#define BINFO_MAX_DEVS_EXCEEDED_MASK_DP			0x0080
-#define BINFO_MAX_CASCADE_EXCEEDED_MASK_DP		0x0800
-
-#define RXSTATUS_MSG_SIZE_MASK				0x03FF
-#define RXSTATUS_READY_MASK				0x0400
-#define RXSTATUS_REAUTH_REQUEST_MASK			0x0800
-#define RXIDLIST_DEVICE_COUNT_LOWER_MASK		0xf0
-#define RXIDLIST_DEVICE_COUNT_UPPER_MASK		0x01
-#define RXCAPS_BYTE0_HDCP_CAPABLE_MASK_DP		0x02
-#define RXSTATUS_READY_MASK_DP				0x0001
-#define RXSTATUS_H_P_AVAILABLE_MASK_DP			0x0002
-#define RXSTATUS_PAIRING_AVAILABLE_MASK_DP		0x0004
-#define RXSTATUS_REAUTH_REQUEST_MASK_DP			0x0008
-#define RXSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP		0x0010
+#include <drm/drm_hdcp.h>
+#include <drm/drm_dp_helper.h>
 
 enum mod_hdcp_trans_input_result {
 	UNKNOWN = 0,
@@ -92,8 +68,52 @@ struct mod_hdcp_transition_input_hdcp1 {
 	uint8_t stream_encryption_dp;
 };
 
+struct mod_hdcp_transition_input_hdcp2 {
+	uint8_t hdcp2version_read;
+	uint8_t hdcp2_capable_check;
+	uint8_t add_topology;
+	uint8_t create_session;
+	uint8_t ake_init_prepare;
+	uint8_t ake_init_write;
+	uint8_t rxstatus_read;
+	uint8_t ake_cert_available;
+	uint8_t ake_cert_read;
+	uint8_t ake_cert_validation;
+	uint8_t stored_km_write;
+	uint8_t no_stored_km_write;
+	uint8_t h_prime_available;
+	uint8_t h_prime_read;
+	uint8_t pairing_available;
+	uint8_t pairing_info_read;
+	uint8_t h_prime_validation;
+	uint8_t lc_init_prepare;
+	uint8_t lc_init_write;
+	uint8_t l_prime_available_poll;
+	uint8_t l_prime_read;
+	uint8_t l_prime_validation;
+	uint8_t eks_prepare;
+	uint8_t eks_write;
+	uint8_t enable_encryption;
+	uint8_t reauth_request_check;
+	uint8_t rx_id_list_read;
+	uint8_t device_count_check;
+	uint8_t rx_id_list_validation;
+	uint8_t repeater_auth_ack_write;
+	uint8_t prepare_stream_manage;
+	uint8_t stream_manage_write;
+	uint8_t stream_ready_available;
+	uint8_t stream_ready_read;
+	uint8_t stream_ready_validation;
+
+	uint8_t rx_caps_read_dp;
+	uint8_t content_stream_type_write;
+	uint8_t link_integrity_check_dp;
+	uint8_t stream_encryption_dp;
+};
+
 union mod_hdcp_transition_input {
 	struct mod_hdcp_transition_input_hdcp1 hdcp1;
+	struct mod_hdcp_transition_input_hdcp2 hdcp2;
 };
 
 struct mod_hdcp_message_hdcp1 {
@@ -111,8 +131,33 @@ struct mod_hdcp_message_hdcp1 {
 	uint16_t	binfo_dp;
 };
 
+struct mod_hdcp_message_hdcp2 {
+	uint8_t		hdcp2version_hdmi;
+	uint8_t		rxcaps_dp[3];
+	uint8_t		rxstatus[2];
+
+	uint8_t		ake_init[12];
+	uint8_t		ake_cert[534];
+	uint8_t		ake_no_stored_km[129];
+	uint8_t		ake_stored_km[33];
+	uint8_t		ake_h_prime[33];
+	uint8_t		ake_pairing_info[17];
+	uint8_t		lc_init[9];
+	uint8_t		lc_l_prime[33];
+	uint8_t		ske_eks[25];
+	uint8_t		rx_id_list[177]; // 22 + 5 * 31
+	uint16_t	rx_id_list_size;
+	uint8_t		repeater_auth_ack[17];
+	uint8_t		repeater_auth_stream_manage[68]; // 6 + 2 * 31
+	uint16_t	stream_manage_size;
+	uint8_t		repeater_auth_stream_ready[33];
+	uint8_t		rxstatus_dp;
+	uint8_t		content_stream_type_dp[2];
+};
+
 union mod_hdcp_message {
 	struct mod_hdcp_message_hdcp1 hdcp1;
+	struct mod_hdcp_message_hdcp2 hdcp2;
 };
 
 struct mod_hdcp_auth_counters {
@@ -125,8 +170,10 @@ struct mod_hdcp_connection {
 	struct mod_hdcp_display displays[MAX_NUM_OF_DISPLAYS];
 	uint8_t is_repeater;
 	uint8_t is_km_stored;
+	uint8_t is_hdcp2_revoked;
 	struct mod_hdcp_trace trace;
 	uint8_t hdcp1_retry_count;
+	uint8_t hdcp2_retry_count;
 };
 
 /* contains values per authentication cycle */
@@ -194,6 +241,50 @@ enum mod_hdcp_hdcp1_dp_state_id {
 	HDCP1_DP_STATE_END = D1_A7_READ_KSV_LIST,
 };
 
+enum mod_hdcp_hdcp2_state_id {
+	HDCP2_STATE_START = HDCP1_DP_STATE_END,
+	H2_A0_KNOWN_HDCP2_CAPABLE_RX,
+	H2_A1_SEND_AKE_INIT,
+	H2_A1_VALIDATE_AKE_CERT,
+	H2_A1_SEND_NO_STORED_KM,
+	H2_A1_READ_H_PRIME,
+	H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME,
+	H2_A1_SEND_STORED_KM,
+	H2_A1_VALIDATE_H_PRIME,
+	H2_A2_LOCALITY_CHECK,
+	H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER,
+	H2_ENABLE_ENCRYPTION,
+	H2_A5_AUTHENTICATED,
+	H2_A6_WAIT_FOR_RX_ID_LIST,
+	H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK,
+	H2_A9_SEND_STREAM_MANAGEMENT,
+	H2_A9_VALIDATE_STREAM_READY,
+	HDCP2_STATE_END = H2_A9_VALIDATE_STREAM_READY,
+};
+
+enum mod_hdcp_hdcp2_dp_state_id {
+	HDCP2_DP_STATE_START = HDCP2_STATE_END,
+	D2_A0_DETERMINE_RX_HDCP_CAPABLE,
+	D2_A1_SEND_AKE_INIT,
+	D2_A1_VALIDATE_AKE_CERT,
+	D2_A1_SEND_NO_STORED_KM,
+	D2_A1_READ_H_PRIME,
+	D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME,
+	D2_A1_SEND_STORED_KM,
+	D2_A1_VALIDATE_H_PRIME,
+	D2_A2_LOCALITY_CHECK,
+	D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER,
+	D2_SEND_CONTENT_STREAM_TYPE,
+	D2_ENABLE_ENCRYPTION,
+	D2_A5_AUTHENTICATED,
+	D2_A6_WAIT_FOR_RX_ID_LIST,
+	D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK,
+	D2_A9_SEND_STREAM_MANAGEMENT,
+	D2_A9_VALIDATE_STREAM_READY,
+	HDCP2_DP_STATE_END = D2_A9_VALIDATE_STREAM_READY,
+	HDCP_STATE_END = HDCP2_DP_STATE_END,
+};
+
 /* hdcp1 executions and transitions */
 typedef enum mod_hdcp_status (*mod_hdcp_action)(struct mod_hdcp *hdcp);
 uint8_t mod_hdcp_execute_and_set(
@@ -214,6 +305,22 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
 	struct mod_hdcp_transition_input_hdcp1 *input,
 	struct mod_hdcp_output *output);
 
+/* hdcp2 executions and transitions */
+enum mod_hdcp_status mod_hdcp_hdcp2_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input);
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input);
+enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input,
+	struct mod_hdcp_output *output);
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input,
+	struct mod_hdcp_output *output);
+
 /* log functions */
 void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size,
 		uint8_t *buf, uint32_t buf_size);
@@ -234,6 +341,25 @@ enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(
 enum mod_hdcp_status mod_hdcp_hdcp1_link_maintenance(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *hdcp,
 							       enum mod_hdcp_encryption_status *encryption_status);
+enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_ake_init(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_ake_cert(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_h_prime(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_lc_init(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_l_prime(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_eks(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_rx_id_list(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_stream_management(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp2_get_link_encryption_status(struct mod_hdcp *hdcp,
+							       enum mod_hdcp_encryption_status *encryption_status);
+
 /* ddc functions */
 enum mod_hdcp_status mod_hdcp_read_bksv(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_bcaps(struct mod_hdcp *hdcp);
@@ -245,6 +371,7 @@ enum mod_hdcp_status mod_hdcp_read_binfo(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_aksv(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_ainfo(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_write_an(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_hdcp2version(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_rxcaps(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_rxstatus(struct mod_hdcp *hdcp);
 enum mod_hdcp_status mod_hdcp_read_ake_cert(struct mod_hdcp *hdcp);
@@ -308,11 +435,28 @@ static inline uint8_t is_in_hdcp1_dp_states(struct mod_hdcp *hdcp)
 			current_state(hdcp) <= HDCP1_DP_STATE_END);
 }
 
+static inline uint8_t is_in_hdcp2_states(struct mod_hdcp *hdcp)
+{
+	return (current_state(hdcp) > HDCP2_STATE_START &&
+			current_state(hdcp) <= HDCP2_STATE_END);
+}
+
+static inline uint8_t is_in_hdcp2_dp_states(struct mod_hdcp *hdcp)
+{
+	return (current_state(hdcp) > HDCP2_DP_STATE_START &&
+			current_state(hdcp) <= HDCP2_DP_STATE_END);
+}
+
 static inline uint8_t is_hdcp1(struct mod_hdcp *hdcp)
 {
 	return (is_in_hdcp1_states(hdcp) || is_in_hdcp1_dp_states(hdcp));
 }
 
+static inline uint8_t is_hdcp2(struct mod_hdcp *hdcp)
+{
+	return (is_in_hdcp2_states(hdcp) || is_in_hdcp2_dp_states(hdcp));
+}
+
 static inline uint8_t is_in_cp_not_desired_state(struct mod_hdcp *hdcp)
 {
 	return current_state(hdcp) == HDCP_CP_NOT_DESIRED;
@@ -437,6 +581,7 @@ static inline struct mod_hdcp_display *get_empty_display_container(
 static inline void reset_retry_counts(struct mod_hdcp *hdcp)
 {
 	hdcp->connection.hdcp1_retry_count = 0;
+	hdcp->connection.hdcp2_retry_count = 0;
 }
 
 #endif /* HDCP_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
index 3db4a7da414f..04845e43df15 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
@@ -27,9 +27,11 @@
 
 static inline enum mod_hdcp_status validate_bksv(struct mod_hdcp *hdcp)
 {
-	uint64_t n = *(uint64_t *)hdcp->auth.msg.hdcp1.bksv;
+	uint64_t n = 0;
 	uint8_t count = 0;
 
+	memcpy(&n, hdcp->auth.msg.hdcp1.bksv, sizeof(uint64_t));
+
 	while (n) {
 		count++;
 		n &= (n - 1);
@@ -41,17 +43,17 @@ static inline enum mod_hdcp_status validate_bksv(struct mod_hdcp *hdcp)
 static inline enum mod_hdcp_status check_ksv_ready(struct mod_hdcp *hdcp)
 {
 	if (is_dp_hdcp(hdcp))
-		return (hdcp->auth.msg.hdcp1.bstatus & BSTATUS_READY_MASK_DP) ?
+		return (hdcp->auth.msg.hdcp1.bstatus & DP_BSTATUS_READY) ?
 				MOD_HDCP_STATUS_SUCCESS :
 				MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY;
-	return (hdcp->auth.msg.hdcp1.bcaps & BCAPS_READY_MASK) ?
+	return (hdcp->auth.msg.hdcp1.bcaps & DRM_HDCP_DDC_BCAPS_KSV_FIFO_READY) ?
 			MOD_HDCP_STATUS_SUCCESS :
 			MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY;
 }
 
 static inline enum mod_hdcp_status check_hdcp_capable_dp(struct mod_hdcp *hdcp)
 {
-	return (hdcp->auth.msg.hdcp1.bcaps & BCAPS_HDCP_CAPABLE_MASK_DP) ?
+	return (hdcp->auth.msg.hdcp1.bcaps & DP_BCAPS_HDCP_CAPABLE) ?
 			MOD_HDCP_STATUS_SUCCESS :
 			MOD_HDCP_STATUS_HDCP1_NOT_CAPABLE;
 }
@@ -61,7 +63,7 @@ static inline enum mod_hdcp_status check_r0p_available_dp(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status;
 	if (is_dp_hdcp(hdcp)) {
 		status = (hdcp->auth.msg.hdcp1.bstatus &
-				BSTATUS_R0_P_AVAILABLE_MASK_DP) ?
+				DP_BSTATUS_R0_PRIME_READY) ?
 			MOD_HDCP_STATUS_SUCCESS :
 			MOD_HDCP_STATUS_HDCP1_R0_PRIME_PENDING;
 	} else {
@@ -74,7 +76,7 @@ static inline enum mod_hdcp_status check_link_integrity_dp(
 		struct mod_hdcp *hdcp)
 {
 	return (hdcp->auth.msg.hdcp1.bstatus &
-			BSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP) ?
+			DP_BSTATUS_LINK_FAILURE) ?
 			MOD_HDCP_STATUS_HDCP1_LINK_INTEGRITY_FAILURE :
 			MOD_HDCP_STATUS_SUCCESS;
 }
@@ -82,7 +84,7 @@ static inline enum mod_hdcp_status check_link_integrity_dp(
 static inline enum mod_hdcp_status check_no_reauthentication_request_dp(
 		struct mod_hdcp *hdcp)
 {
-	return (hdcp->auth.msg.hdcp1.bstatus & BSTATUS_REAUTH_REQUEST_MASK_DP) ?
+	return (hdcp->auth.msg.hdcp1.bstatus & DP_BSTATUS_REAUTH_REQ) ?
 			MOD_HDCP_STATUS_HDCP1_REAUTH_REQUEST_ISSUED :
 			MOD_HDCP_STATUS_SUCCESS;
 }
@@ -92,15 +94,13 @@ static inline enum mod_hdcp_status check_no_max_cascade(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status;
 
 	if (is_dp_hdcp(hdcp))
-		status = (hdcp->auth.msg.hdcp1.binfo_dp &
-				BINFO_MAX_CASCADE_EXCEEDED_MASK_DP) ?
-			MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE :
-			MOD_HDCP_STATUS_SUCCESS;
+		status = DRM_HDCP_MAX_CASCADE_EXCEEDED(hdcp->auth.msg.hdcp1.binfo_dp >> 8)
+				 ? MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE
+				 : MOD_HDCP_STATUS_SUCCESS;
 	else
-		status = (hdcp->auth.msg.hdcp1.bstatus &
-				BSTATUS_MAX_CASCADE_EXCEEDED_MASK) ?
-				MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE :
-				MOD_HDCP_STATUS_SUCCESS;
+		status = DRM_HDCP_MAX_CASCADE_EXCEEDED(hdcp->auth.msg.hdcp1.bstatus >> 8)
+				 ? MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE
+				 : MOD_HDCP_STATUS_SUCCESS;
 	return status;
 }
 
@@ -109,13 +109,11 @@ static inline enum mod_hdcp_status check_no_max_devs(struct mod_hdcp *hdcp)
 	enum mod_hdcp_status status;
 
 	if (is_dp_hdcp(hdcp))
-		status = (hdcp->auth.msg.hdcp1.binfo_dp &
-				BINFO_MAX_DEVS_EXCEEDED_MASK_DP) ?
+		status = DRM_HDCP_MAX_DEVICE_EXCEEDED(hdcp->auth.msg.hdcp1.binfo_dp) ?
 				MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE :
 				MOD_HDCP_STATUS_SUCCESS;
 	else
-		status = (hdcp->auth.msg.hdcp1.bstatus &
-				BSTATUS_MAX_DEVS_EXCEEDED_MASK) ?
+		status = DRM_HDCP_MAX_DEVICE_EXCEEDED(hdcp->auth.msg.hdcp1.bstatus) ?
 				MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE :
 				MOD_HDCP_STATUS_SUCCESS;
 	return status;
@@ -124,8 +122,8 @@ static inline enum mod_hdcp_status check_no_max_devs(struct mod_hdcp *hdcp)
 static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
 {
 	return is_dp_hdcp(hdcp) ?
-			(hdcp->auth.msg.hdcp1.binfo_dp & BINFO_DEVICE_COUNT_MASK_DP) :
-			(hdcp->auth.msg.hdcp1.bstatus & BSTATUS_DEVICE_COUNT_MASK);
+			DRM_HDCP_NUM_DOWNSTREAM(hdcp->auth.msg.hdcp1.binfo_dp) :
+			DRM_HDCP_NUM_DOWNSTREAM(hdcp->auth.msg.hdcp1.bstatus);
 }
 
 static inline enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
index 136b8011ff3f..21ebc62bb9d9 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
@@ -67,11 +67,19 @@ enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp,
 		break;
 	case H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER:
 		if (input->bcaps_read != PASS ||
-				input->r0p_read != PASS ||
-				input->rx_validation != PASS ||
-				(!conn->is_repeater && input->encryption != PASS)) {
+				input->r0p_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->rx_validation != PASS) {
 			/* 1A-06: consider invalid r0' a failure */
 			/* 1A-08: consider bksv listed in SRM a failure */
+			/*
+			 * some slow RX will fail rx validation when it is
+			 * not ready. give it more time to react before retry.
+			 */
+			fail_and_restart_in_ms(1000, &status, output);
+			break;
+		} else if (!conn->is_repeater && input->encryption != PASS) {
 			fail_and_restart_in_ms(0, &status, output);
 			break;
 		}
@@ -212,7 +220,11 @@ enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
 				 * after 3 attempts.
 				 * 1A-08: consider bksv listed in SRM a failure
 				 */
-				fail_and_restart_in_ms(0, &status, output);
+				/*
+				 * some slow RX will fail rx validation when it is
+				 * not ready. give it more time to react before retry.
+				 */
+				fail_and_restart_in_ms(1000, &status, output);
 			}
 			break;
 		} else if ((!conn->is_repeater && input->encryption != PASS) ||
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
new file mode 100644
index 000000000000..f730b94ac3c0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_execution.c
@@ -0,0 +1,886 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/delay.h>
+
+#include "hdcp.h"
+
+static inline enum mod_hdcp_status check_receiver_id_list_ready(struct mod_hdcp *hdcp)
+{
+	uint8_t is_ready = 0;
+
+	if (is_dp_hdcp(hdcp))
+		is_ready = HDCP_2_2_DP_RXSTATUS_READY(hdcp->auth.msg.hdcp2.rxstatus_dp) ? 1 : 0;
+	else
+		is_ready = (HDCP_2_2_HDMI_RXSTATUS_READY(hdcp->auth.msg.hdcp2.rxstatus[0]) &&
+				(HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+						hdcp->auth.msg.hdcp2.rxstatus[0])) ? 1 : 0;
+	return is_ready ? MOD_HDCP_STATUS_SUCCESS :
+			MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY;
+}
+
+static inline enum mod_hdcp_status check_hdcp2_capable(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = (hdcp->auth.msg.hdcp2.rxcaps_dp[2] & HDCP_2_2_RX_CAPS_VERSION_VAL) &&
+				HDCP_2_2_DP_HDCP_CAPABLE(hdcp->auth.msg.hdcp2.rxcaps_dp[0]) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE;
+	else
+		status = (hdcp->auth.msg.hdcp2.hdcp2version_hdmi & HDCP_2_2_HDMI_SUPPORT_MASK) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE;
+	return status;
+}
+
+static inline enum mod_hdcp_status check_reauthentication_request(
+		struct mod_hdcp *hdcp)
+{
+	uint8_t ret = 0;
+
+	if (is_dp_hdcp(hdcp))
+		ret = HDCP_2_2_DP_RXSTATUS_REAUTH_REQ(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+				MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST :
+				MOD_HDCP_STATUS_SUCCESS;
+	else
+		ret = HDCP_2_2_HDMI_RXSTATUS_REAUTH_REQ(hdcp->auth.msg.hdcp2.rxstatus[0]) ?
+				MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST :
+				MOD_HDCP_STATUS_SUCCESS;
+	return ret;
+}
+
+static inline enum mod_hdcp_status check_link_integrity_failure_dp(
+		struct mod_hdcp *hdcp)
+{
+	return HDCP_2_2_DP_RXSTATUS_LINK_FAILED(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+			MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static enum mod_hdcp_status check_ake_cert_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint16_t size;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+	} else {
+		status = mod_hdcp_read_rxstatus(hdcp);
+		if (status == MOD_HDCP_STATUS_SUCCESS) {
+			size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+			       hdcp->auth.msg.hdcp2.rxstatus[0];
+			status = (size == sizeof(hdcp->auth.msg.hdcp2.ake_cert)) ?
+					MOD_HDCP_STATUS_SUCCESS :
+					MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING;
+		}
+	}
+	return status;
+}
+
+static enum mod_hdcp_status check_h_prime_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+
+	status = mod_hdcp_read_rxstatus(hdcp);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = HDCP_2_2_DP_RXSTATUS_H_PRIME(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING;
+	} else {
+		size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+		       hdcp->auth.msg.hdcp2.rxstatus[0];
+		status = (size == sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status check_pairing_info_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+
+	status = mod_hdcp_read_rxstatus(hdcp);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = HDCP_2_2_DP_RXSTATUS_PAIRING(hdcp->auth.msg.hdcp2.rxstatus_dp) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING;
+	} else {
+		size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+		       hdcp->auth.msg.hdcp2.rxstatus[0];
+		status = (size == sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status poll_l_prime_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+	uint16_t max_wait = 20; // units of ms
+	uint16_t num_polls = 5;
+	uint16_t wait_time = max_wait / num_polls;
+
+	if (is_dp_hdcp(hdcp))
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	else
+		for (; num_polls; num_polls--) {
+			msleep(wait_time);
+
+			status = mod_hdcp_read_rxstatus(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS)
+				break;
+
+			size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+			       hdcp->auth.msg.hdcp2.rxstatus[0];
+			status = (size == sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)) ?
+					MOD_HDCP_STATUS_SUCCESS :
+					MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING;
+			if (status == MOD_HDCP_STATUS_SUCCESS)
+				break;
+		}
+	return status;
+}
+
+static enum mod_hdcp_status check_stream_ready_available(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	uint8_t size;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	} else {
+		status = mod_hdcp_read_rxstatus(hdcp);
+		if (status != MOD_HDCP_STATUS_SUCCESS)
+			goto out;
+		size = HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+		       hdcp->auth.msg.hdcp2.rxstatus[0];
+		status = (size == sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING;
+	}
+out:
+	return status;
+}
+
+static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
+{
+	return HDCP_2_2_DEV_COUNT_LO(hdcp->auth.msg.hdcp2.rx_id_list[2]) +
+			(HDCP_2_2_DEV_COUNT_HI(hdcp->auth.msg.hdcp2.rx_id_list[1]) << 4);
+}
+
+static enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
+{
+	/* device count must be greater than or equal to tracked hdcp displays */
+	return (get_device_count(hdcp) < get_added_display_count(hdcp)) ?
+			MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static uint8_t process_rxstatus(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input,
+		enum mod_hdcp_status *status)
+{
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_rxstatus,
+			&input->rxstatus_read, status,
+			hdcp, "rxstatus_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_reauthentication_request,
+			&input->reauth_request_check, status,
+			hdcp, "reauth_request_check"))
+		goto out;
+	if (is_dp_hdcp(hdcp)) {
+		if (!mod_hdcp_execute_and_set(check_link_integrity_failure_dp,
+				&input->link_integrity_check_dp, status,
+				hdcp, "link_integrity_check_dp"))
+			goto out;
+	}
+	if (hdcp->connection.is_repeater)
+		if (check_receiver_id_list_ready(hdcp) ==
+				MOD_HDCP_STATUS_SUCCESS) {
+			HDCP_INPUT_PASS_TRACE(hdcp, "rx_id_list_ready");
+			event_ctx->rx_id_list_ready = 1;
+			if (is_dp_hdcp(hdcp))
+				hdcp->auth.msg.hdcp2.rx_id_list_size =
+						sizeof(hdcp->auth.msg.hdcp2.rx_id_list);
+			else
+				hdcp->auth.msg.hdcp2.rx_id_list_size =
+					HDCP_2_2_HDMI_RXSTATUS_MSG_SZ_HI(hdcp->auth.msg.hdcp2.rxstatus[1]) << 8 |
+					hdcp->auth.msg.hdcp2.rxstatus[0];
+		}
+out:
+	return (*status == MOD_HDCP_STATUS_SUCCESS);
+}
+
+static enum mod_hdcp_status known_hdcp2_capable_rx(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_hdcp2version,
+			&input->hdcp2version_read, &status,
+			hdcp, "hdcp2version_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_hdcp2_capable,
+			&input->hdcp2_capable_check, &status,
+			hdcp, "hdcp2_capable"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_ake_init(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_add_display_topology,
+			&input->add_topology, &status,
+			hdcp, "add_topology"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_create_session,
+			&input->create_session, &status,
+			hdcp, "create_session"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_ake_init,
+			&input->ake_init_prepare, &status,
+			hdcp, "ake_init_prepare"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_ake_init,
+			&input->ake_init_write, &status,
+			hdcp, "ake_init_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status validate_ake_cert(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp))
+		if (!mod_hdcp_execute_and_set(check_ake_cert_available,
+				&input->ake_cert_available, &status,
+				hdcp, "ake_cert_available"))
+			goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_ake_cert,
+			&input->ake_cert_read, &status,
+			hdcp, "ake_cert_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_ake_cert,
+			&input->ake_cert_validation, &status,
+			hdcp, "ake_cert_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_no_stored_km(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_no_stored_km,
+			&input->no_stored_km_write, &status,
+			hdcp, "no_stored_km_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status read_h_prime(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(check_h_prime_available,
+			&input->h_prime_available, &status,
+			hdcp, "h_prime_available"))
+		goto out;
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_h_prime,
+			&input->h_prime_read, &status,
+			hdcp, "h_prime_read"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status read_pairing_info_and_validate_h_prime(
+		struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(check_pairing_info_available,
+			&input->pairing_available, &status,
+			hdcp, "pairing_available"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_pairing_info,
+			&input->pairing_info_read, &status,
+			hdcp, "pairing_info_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_h_prime,
+			&input->h_prime_validation, &status,
+			hdcp, "h_prime_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_stored_km(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_stored_km,
+			&input->stored_km_write, &status,
+			hdcp, "stored_km_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status validate_h_prime(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(check_h_prime_available,
+			&input->h_prime_available, &status,
+			hdcp, "h_prime_available"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_h_prime,
+			&input->h_prime_read, &status,
+			hdcp, "h_prime_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_h_prime,
+			&input->h_prime_validation, &status,
+			hdcp, "h_prime_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status locality_check(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_lc_init,
+			&input->lc_init_prepare, &status,
+			hdcp, "lc_init_prepare"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_lc_init,
+			&input->lc_init_write, &status,
+			 hdcp, "lc_init_write"))
+		goto out;
+	if (is_dp_hdcp(hdcp))
+		msleep(16);
+	else
+		if (!mod_hdcp_execute_and_set(poll_l_prime_available,
+				&input->l_prime_available_poll, &status,
+				hdcp, "l_prime_available_poll"))
+			goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_l_prime,
+			&input->l_prime_read, &status,
+			hdcp, "l_prime_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_l_prime,
+			&input->l_prime_validation, &status,
+			hdcp, "l_prime_validation"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status exchange_ks_and_test_for_repeater(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_eks,
+			&input->eks_prepare, &status,
+			hdcp, "eks_prepare"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_eks,
+			&input->eks_write, &status,
+			hdcp, "eks_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status enable_encryption(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp)) {
+		if (!process_rxstatus(hdcp, event_ctx, input, &status))
+			goto out;
+		if (event_ctx->rx_id_list_ready)
+			goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_enable_encryption,
+			&input->enable_encryption, &status,
+			hdcp, "enable_encryption"))
+		goto out;
+	if (is_dp_mst_hdcp(hdcp)) {
+		if (!mod_hdcp_execute_and_set(
+				mod_hdcp_hdcp2_enable_dp_stream_encryption,
+				&input->stream_encryption_dp, &status,
+				hdcp, "stream_encryption_dp"))
+			goto out;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!process_rxstatus(hdcp, event_ctx, input, &status))
+		goto out;
+	if (event_ctx->rx_id_list_ready)
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status wait_for_rx_id_list(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!process_rxstatus(hdcp, event_ctx, input, &status))
+		goto out;
+	if (!event_ctx->rx_id_list_ready) {
+		status = MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY;
+		goto out;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status verify_rx_id_list_and_send_ack(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_rx_id_list,
+			&input->rx_id_list_read,
+			&status, hdcp, "receiver_id_list_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_device_count,
+			&input->device_count_check,
+			&status, hdcp, "device_count_check"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_rx_id_list,
+			&input->rx_id_list_validation,
+			&status, hdcp, "rx_id_list_validation"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_repeater_auth_ack,
+			&input->repeater_auth_ack_write,
+			&status, hdcp, "repeater_auth_ack_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_stream_management(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp)) {
+		if (!process_rxstatus(hdcp, event_ctx, input, &status))
+			goto out;
+		if (event_ctx->rx_id_list_ready)
+			goto out;
+	}
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_prepare_stream_management,
+			&input->prepare_stream_manage,
+			&status, hdcp, "prepare_stream_manage"))
+		goto out;
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_stream_manage,
+			&input->stream_manage_write,
+			&status, hdcp, "stream_manage_write"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status validate_stream_ready(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+	if (event_ctx->event == MOD_HDCP_EVENT_CPIRQ) {
+		process_rxstatus(hdcp, event_ctx, input, &status);
+		goto out;
+	}
+
+	if (is_hdmi_dvi_sl_hdcp(hdcp)) {
+		if (!process_rxstatus(hdcp, event_ctx, input, &status))
+			goto out;
+		if (event_ctx->rx_id_list_ready) {
+			goto out;
+		}
+	}
+	if (is_hdmi_dvi_sl_hdcp(hdcp))
+		if (!mod_hdcp_execute_and_set(check_stream_ready_available,
+				&input->stream_ready_available,
+				&status, hdcp, "stream_ready_available"))
+			goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_stream_ready,
+			&input->stream_ready_read,
+			&status, hdcp, "stream_ready_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp2_validate_stream_ready,
+			&input->stream_ready_validation,
+			&status, hdcp, "stream_ready_validation"))
+		goto out;
+
+out:
+	return status;
+}
+
+static enum mod_hdcp_status determine_rx_hdcp_capable_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_rxcaps,
+			&input->rx_caps_read_dp,
+			&status, hdcp, "rx_caps_read_dp"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_hdcp2_capable,
+			&input->hdcp2_capable_check, &status,
+			hdcp, "hdcp2_capable_check"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status send_content_stream_type_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!process_rxstatus(hdcp, event_ctx, input, &status))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_content_type,
+			&input->content_stream_type_write, &status,
+			hdcp, "content_stream_type_write"))
+		goto out;
+out:
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	switch (current_state(hdcp)) {
+	case H2_A0_KNOWN_HDCP2_CAPABLE_RX:
+		status = known_hdcp2_capable_rx(hdcp, event_ctx, input);
+		break;
+	case H2_A1_SEND_AKE_INIT:
+		status = send_ake_init(hdcp, event_ctx, input);
+		break;
+	case H2_A1_VALIDATE_AKE_CERT:
+		status = validate_ake_cert(hdcp, event_ctx, input);
+		break;
+	case H2_A1_SEND_NO_STORED_KM:
+		status = send_no_stored_km(hdcp, event_ctx, input);
+		break;
+	case H2_A1_READ_H_PRIME:
+		status = read_h_prime(hdcp, event_ctx, input);
+		break;
+	case H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		status = read_pairing_info_and_validate_h_prime(hdcp,
+				event_ctx, input);
+		break;
+	case H2_A1_SEND_STORED_KM:
+		status = send_stored_km(hdcp, event_ctx, input);
+		break;
+	case H2_A1_VALIDATE_H_PRIME:
+		status = validate_h_prime(hdcp, event_ctx, input);
+		break;
+	case H2_A2_LOCALITY_CHECK:
+		status = locality_check(hdcp, event_ctx, input);
+		break;
+	case H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		status = exchange_ks_and_test_for_repeater(hdcp, event_ctx, input);
+		break;
+	case H2_ENABLE_ENCRYPTION:
+		status = enable_encryption(hdcp, event_ctx, input);
+		break;
+	case H2_A5_AUTHENTICATED:
+		status = authenticated(hdcp, event_ctx, input);
+		break;
+	case H2_A6_WAIT_FOR_RX_ID_LIST:
+		status = wait_for_rx_id_list(hdcp, event_ctx, input);
+		break;
+	case H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		status = verify_rx_id_list_and_send_ack(hdcp, event_ctx, input);
+		break;
+	case H2_A9_SEND_STREAM_MANAGEMENT:
+		status = send_stream_management(hdcp, event_ctx, input);
+		break;
+	case H2_A9_VALIDATE_STREAM_READY:
+		status = validate_stream_ready(hdcp, event_ctx, input);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		break;
+	}
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp2 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	switch (current_state(hdcp)) {
+	case D2_A0_DETERMINE_RX_HDCP_CAPABLE:
+		status = determine_rx_hdcp_capable_dp(hdcp, event_ctx, input);
+		break;
+	case D2_A1_SEND_AKE_INIT:
+		status = send_ake_init(hdcp, event_ctx, input);
+		break;
+	case D2_A1_VALIDATE_AKE_CERT:
+		status = validate_ake_cert(hdcp, event_ctx, input);
+		break;
+	case D2_A1_SEND_NO_STORED_KM:
+		status = send_no_stored_km(hdcp, event_ctx, input);
+		break;
+	case D2_A1_READ_H_PRIME:
+		status = read_h_prime(hdcp, event_ctx, input);
+		break;
+	case D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		status = read_pairing_info_and_validate_h_prime(hdcp,
+				event_ctx, input);
+		break;
+	case D2_A1_SEND_STORED_KM:
+		status = send_stored_km(hdcp, event_ctx, input);
+		break;
+	case D2_A1_VALIDATE_H_PRIME:
+		status = validate_h_prime(hdcp, event_ctx, input);
+		break;
+	case D2_A2_LOCALITY_CHECK:
+		status = locality_check(hdcp, event_ctx, input);
+		break;
+	case D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		status = exchange_ks_and_test_for_repeater(hdcp,
+				event_ctx, input);
+		break;
+	case D2_SEND_CONTENT_STREAM_TYPE:
+		status = send_content_stream_type_dp(hdcp, event_ctx, input);
+		break;
+	case D2_ENABLE_ENCRYPTION:
+		status = enable_encryption(hdcp, event_ctx, input);
+		break;
+	case D2_A5_AUTHENTICATED:
+		status = authenticated(hdcp, event_ctx, input);
+		break;
+	case D2_A6_WAIT_FOR_RX_ID_LIST:
+		status = wait_for_rx_id_list(hdcp, event_ctx, input);
+		break;
+	case D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		status = verify_rx_id_list_and_send_ack(hdcp, event_ctx, input);
+		break;
+	case D2_A9_SEND_STREAM_MANAGEMENT:
+		status = send_stream_management(hdcp, event_ctx, input);
+		break;
+	case D2_A9_VALIDATE_STREAM_READY:
+		status = validate_stream_ready(hdcp, event_ctx, input);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		break;
+	}
+
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
new file mode 100644
index 000000000000..8cae3e3aacd5
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp2_transition.c
@@ -0,0 +1,679 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hdcp.h"
+
+enum mod_hdcp_status mod_hdcp_hdcp2_transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_connection *conn = &hdcp->connection;
+	struct mod_hdcp_link_adjustment *adjust = &hdcp->connection.link.adjust;
+
+	switch (current_state(hdcp)) {
+	case H2_A0_KNOWN_HDCP2_CAPABLE_RX:
+		if (input->hdcp2version_read != PASS ||
+				input->hdcp2_capable_check != PASS) {
+			adjust->hdcp2.disable = 1;
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, HDCP_INITIALIZED);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A1_SEND_AKE_INIT);
+		}
+		break;
+	case H2_A1_SEND_AKE_INIT:
+		if (input->add_topology != PASS ||
+				input->create_session != PASS ||
+				input->ake_init_prepare != PASS) {
+			/* out of sync with psp state */
+			adjust->hdcp2.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->ake_init_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 100, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_VALIDATE_AKE_CERT);
+		break;
+	case H2_A1_VALIDATE_AKE_CERT:
+		if (input->ake_cert_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-08: consider ake timeout a failure */
+				/* some hdmi receivers are not ready for HDCP
+				 * immediately after video becomes active,
+				 * delay 1s before retry on first HDCP message
+				 * timeout.
+				 */
+				fail_and_restart_in_ms(1000, &status, output);
+			} else {
+				/* continue ake cert polling*/
+				callback_in_ms(10, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->ake_cert_read != PASS ||
+				input->ake_cert_validation != PASS) {
+			/*
+			 * 1A-09: consider invalid ake cert a failure
+			 * 1A-10: consider receiver id listed in SRM a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_km_stored &&
+				!adjust->hdcp2.force_no_stored_km) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A1_SEND_STORED_KM);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A1_SEND_NO_STORED_KM);
+		}
+		break;
+	case H2_A1_SEND_NO_STORED_KM:
+		if (input->no_stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (adjust->hdcp2.increase_h_prime_timeout)
+			set_watchdog_in_ms(hdcp, 2000, output);
+		else
+			set_watchdog_in_ms(hdcp, 1000, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_READ_H_PRIME);
+		break;
+	case H2_A1_READ_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-11-3: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			} else {
+				/* continue h' polling */
+				callback_in_ms(100, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME);
+		break;
+	case H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		if (input->pairing_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-12: consider pairing info timeout
+				 * a failure
+				 */
+				fail_and_restart_in_ms(0, &status, output);
+			} else {
+				/* continue pairing info polling */
+				callback_in_ms(20, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->pairing_info_read != PASS ||
+				input->h_prime_validation != PASS) {
+			/* 1A-11-1: consider invalid h' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A2_LOCALITY_CHECK);
+		break;
+	case H2_A1_SEND_STORED_KM:
+		if (input->stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A1_VALIDATE_H_PRIME);
+		break;
+	case H2_A1_VALIDATE_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1A-11-2: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			} else {
+				/* continue h' polling */
+				callback_in_ms(20, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->h_prime_validation != PASS) {
+			/* 1A-11-1: consider invalid h' a failure */
+			adjust->hdcp2.force_no_stored_km = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A2_LOCALITY_CHECK);
+		break;
+	case H2_A2_LOCALITY_CHECK:
+		if (hdcp->state.stay_count > 10 ||
+				input->lc_init_prepare != PASS ||
+				input->lc_init_write != PASS ||
+				input->l_prime_available_poll != PASS ||
+				input->l_prime_read != PASS) {
+			/*
+			 * 1A-05: consider disconnection after LC init a failure
+			 * 1A-13-1: consider invalid l' a failure
+			 * 1A-13-2: consider l' timeout a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->l_prime_validation != PASS) {
+			callback_in_ms(0, output);
+			increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER);
+		break;
+	case H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		if (input->eks_prepare != PASS ||
+				input->eks_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_repeater) {
+			set_watchdog_in_ms(hdcp, 3000, output);
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A6_WAIT_FOR_RX_ID_LIST);
+		} else {
+			/* some CTS equipment requires a delay GREATER than
+			 * 200 ms, so delay 210 ms instead of 200 ms
+			 */
+			callback_in_ms(210, output);
+			set_state_id(hdcp, output, H2_ENABLE_ENCRYPTION);
+		}
+		break;
+	case H2_ENABLE_ENCRYPTION:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			/*
+			 * 1A-07: restart hdcp on REAUTH_REQ
+			 * 1B-08: restart hdcp on REAUTH_REQ
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->enable_encryption != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A5_AUTHENTICATED);
+		HDCP_FULL_DDC_TRACE(hdcp);
+		break;
+	case H2_A5_AUTHENTICATED:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		}
+		callback_in_ms(500, output);
+		increment_stay_counter(hdcp);
+		break;
+	case H2_A6_WAIT_FOR_RX_ID_LIST:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (!event_ctx->rx_id_list_ready) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1B-02: consider rx id list timeout a failure */
+				/* some CTS equipment's actual timeout
+				 * measurement is slightly greater than 3000 ms.
+				 * Delay 100 ms to ensure it is fully timeout
+				 * before re-authentication.
+				 */
+				fail_and_restart_in_ms(100, &status, output);
+			} else {
+				callback_in_ms(300, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+		break;
+	case H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->rx_id_list_read != PASS ||
+				input->device_count_check != PASS ||
+				input->rx_id_list_validation != PASS ||
+				input->repeater_auth_ack_write != PASS) {
+			/* 1B-03: consider invalid v' a failure
+			 * 1B-04: consider MAX_DEVS_EXCEEDED a failure
+			 * 1B-05: consider MAX_CASCADE_EXCEEDED a failure
+			 * 1B-06: consider invalid seq_num_V a failure
+			 * 1B-09: consider seq_num_V rollover a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A9_SEND_STREAM_MANAGEMENT);
+		break;
+	case H2_A9_SEND_STREAM_MANAGEMENT:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->prepare_stream_manage != PASS ||
+				input->stream_manage_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 100, output);
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H2_A9_VALIDATE_STREAM_READY);
+		break;
+	case H2_A9_VALIDATE_STREAM_READY:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->stream_ready_available != PASS) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1B-10-2: restart content stream management on
+				 * stream ready timeout
+				 */
+				hdcp->auth.count.stream_management_retry_count++;
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H2_A9_SEND_STREAM_MANAGEMENT);
+			} else {
+				callback_in_ms(10, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		} else if (input->stream_ready_read != PASS ||
+				input->stream_ready_validation != PASS) {
+			/*
+			 * 1B-10-1: restart content stream management
+			 * on invalid M'
+			 */
+			if (hdcp->auth.count.stream_management_retry_count > 10) {
+				fail_and_restart_in_ms(0, &status, output);
+			} else {
+				hdcp->auth.count.stream_management_retry_count++;
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H2_A9_SEND_STREAM_MANAGEMENT);
+			}
+			break;
+		}
+		callback_in_ms(200, output);
+		set_state_id(hdcp, output, H2_ENABLE_ENCRYPTION);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		fail_and_restart_in_ms(0, &status, output);
+		break;
+	}
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_dp_transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp2 *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_connection *conn = &hdcp->connection;
+	struct mod_hdcp_link_adjustment *adjust = &hdcp->connection.link.adjust;
+
+	switch (current_state(hdcp)) {
+	case D2_A0_DETERMINE_RX_HDCP_CAPABLE:
+		if (input->rx_caps_read_dp != PASS ||
+				input->hdcp2_capable_check != PASS) {
+			adjust->hdcp2.disable = 1;
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, HDCP_INITIALIZED);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A1_SEND_AKE_INIT);
+		}
+		break;
+	case D2_A1_SEND_AKE_INIT:
+		if (input->add_topology != PASS ||
+				input->create_session != PASS ||
+				input->ake_init_prepare != PASS) {
+			/* out of sync with psp state */
+			adjust->hdcp2.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->ake_init_write != PASS) {
+			/* possibly display not ready */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(100, output);
+		set_state_id(hdcp, output, D2_A1_VALIDATE_AKE_CERT);
+		break;
+	case D2_A1_VALIDATE_AKE_CERT:
+		if (input->ake_cert_read != PASS ||
+				input->ake_cert_validation != PASS) {
+			/*
+			 * 1A-08: consider invalid ake cert a failure
+			 * 1A-09: consider receiver id listed in SRM a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_km_stored &&
+				!adjust->hdcp2.force_no_stored_km) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A1_SEND_STORED_KM);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A1_SEND_NO_STORED_KM);
+		}
+		break;
+	case D2_A1_SEND_NO_STORED_KM:
+		if (input->no_stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (adjust->hdcp2.increase_h_prime_timeout)
+			set_watchdog_in_ms(hdcp, 2000, output);
+		else
+			set_watchdog_in_ms(hdcp, 1000, output);
+		set_state_id(hdcp, output, D2_A1_READ_H_PRIME);
+		break;
+	case D2_A1_READ_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/* 1A-10-3: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		set_state_id(hdcp, output, D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME);
+		break;
+	case D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		if (input->pairing_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/*
+				 * 1A-11: consider pairing info timeout
+				 * a failure
+				 */
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		} else if (input->pairing_info_read != PASS ||
+				input->h_prime_validation != PASS) {
+			/* 1A-10-1: consider invalid h' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A2_LOCALITY_CHECK);
+		break;
+	case D2_A1_SEND_STORED_KM:
+		if (input->stored_km_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 200, output);
+		set_state_id(hdcp, output, D2_A1_VALIDATE_H_PRIME);
+		break;
+	case D2_A1_VALIDATE_H_PRIME:
+		if (input->h_prime_available != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/* 1A-10-2: consider h' timeout a failure */
+				fail_and_restart_in_ms(1000, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		} else if (input->h_prime_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->h_prime_validation != PASS) {
+			/* 1A-10-1: consider invalid h' a failure */
+			adjust->hdcp2.force_no_stored_km = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A2_LOCALITY_CHECK);
+		break;
+	case D2_A2_LOCALITY_CHECK:
+		if (hdcp->state.stay_count > 10 ||
+				input->lc_init_prepare != PASS ||
+				input->lc_init_write != PASS ||
+				input->l_prime_read != PASS) {
+			/* 1A-12: consider invalid l' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->l_prime_validation != PASS) {
+			callback_in_ms(0, output);
+			increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER);
+		break;
+	case D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		if (input->eks_prepare != PASS ||
+				input->eks_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_repeater) {
+			set_watchdog_in_ms(hdcp, 3000, output);
+			set_state_id(hdcp, output, D2_A6_WAIT_FOR_RX_ID_LIST);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_SEND_CONTENT_STREAM_TYPE);
+		}
+		break;
+	case D2_SEND_CONTENT_STREAM_TYPE:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS ||
+				input->content_stream_type_write != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(210, output);
+		set_state_id(hdcp, output, D2_ENABLE_ENCRYPTION);
+		break;
+	case D2_ENABLE_ENCRYPTION:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			/*
+			 * 1A-07: restart hdcp on REAUTH_REQ
+			 * 1B-08: restart hdcp on REAUTH_REQ
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->enable_encryption != PASS ||
+				(is_dp_mst_hdcp(hdcp) && input->stream_encryption_dp != PASS)) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_state_id(hdcp, output, D2_A5_AUTHENTICATED);
+		HDCP_FULL_DDC_TRACE(hdcp);
+		break;
+	case D2_A5_AUTHENTICATED:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->link_integrity_check_dp != PASS) {
+			if (hdcp->connection.hdcp2_retry_count >= 1)
+				adjust->hdcp2.force_type = MOD_HDCP_FORCE_TYPE_0;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready && conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		}
+		increment_stay_counter(hdcp);
+		break;
+	case D2_A6_WAIT_FOR_RX_ID_LIST:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (!event_ctx->rx_id_list_ready) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				/* 1B-02: consider rx id list timeout a failure */
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+		break;
+	case D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS ||
+				input->rx_id_list_read != PASS ||
+				input->device_count_check != PASS ||
+				input->rx_id_list_validation != PASS ||
+				input->repeater_auth_ack_write != PASS) {
+			/*
+			 * 1B-03: consider invalid v' a failure
+			 * 1B-04: consider MAX_DEVS_EXCEEDED a failure
+			 * 1B-05: consider MAX_CASCADE_EXCEEDED a failure
+			 * 1B-06: consider invalid seq_num_V a failure
+			 * 1B-09: consider seq_num_V rollover a failure
+			 */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D2_A9_SEND_STREAM_MANAGEMENT);
+		break;
+	case D2_A9_SEND_STREAM_MANAGEMENT:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->prepare_stream_manage != PASS ||
+				input->stream_manage_write != PASS) {
+			if (event_ctx->event == MOD_HDCP_EVENT_CALLBACK)
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(100, output);
+		set_state_id(hdcp, output, D2_A9_VALIDATE_STREAM_READY);
+		break;
+	case D2_A9_VALIDATE_STREAM_READY:
+		if (input->rxstatus_read != PASS ||
+				input->reauth_request_check != PASS ||
+				input->link_integrity_check_dp != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (event_ctx->rx_id_list_ready) {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK);
+			break;
+		} else if (input->stream_ready_read != PASS ||
+				input->stream_ready_validation != PASS) {
+			/*
+			 * 1B-10-1: restart content stream management
+			 * on invalid M'
+			 * 1B-10-2: consider stream ready timeout a failure
+			 */
+			if (hdcp->auth.count.stream_management_retry_count > 10) {
+				fail_and_restart_in_ms(0, &status, output);
+			} else if (event_ctx->event == MOD_HDCP_EVENT_CALLBACK) {
+				hdcp->auth.count.stream_management_retry_count++;
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, D2_A9_SEND_STREAM_MANAGEMENT);
+			} else {
+				increment_stay_counter(hdcp);
+			}
+			break;
+		}
+		callback_in_ms(200, output);
+		set_state_id(hdcp, output, D2_ENABLE_ENCRYPTION);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		fail_and_restart_in_ms(0, &status, output);
+		break;
+	}
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
index e7baae059b85..ff9d54812e62 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
@@ -51,6 +51,26 @@ enum mod_hdcp_ddc_message_id {
 	MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO,
 	MOD_HDCP_MESSAGE_ID_READ_BINFO,
 
+	/* HDCP 2.2 */
+
+	MOD_HDCP_MESSAGE_ID_HDCP2VERSION,
+	MOD_HDCP_MESSAGE_ID_RX_CAPS,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+	MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+	MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+	MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+	MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT,
+	MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+	MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+	MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+	MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+	MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+	MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+	MOD_HDCP_MESSAGE_ID_READ_RXSTATUS,
+	MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE,
+
 	MOD_HDCP_MESSAGE_ID_MAX
 };
 
@@ -70,6 +90,22 @@ static const uint8_t hdcp_i2c_offsets[] = {
 	[MOD_HDCP_MESSAGE_ID_READ_BSTATUS] = 0x41,
 	[MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x43,
 	[MOD_HDCP_MESSAGE_ID_READ_BINFO] = 0xFF,
+	[MOD_HDCP_MESSAGE_ID_HDCP2VERSION] = 0x50,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = 0x60,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = 0x80,
+	[MOD_HDCP_MESSAGE_ID_READ_RXSTATUS] = 0x70,
+	[MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE] = 0x0
 };
 
 static const uint32_t hdcp_dpcd_addrs[] = {
@@ -88,6 +124,22 @@ static const uint32_t hdcp_dpcd_addrs[] = {
 	[MOD_HDCP_MESSAGE_ID_READ_BSTATUS] = 0x68029,
 	[MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x6802c,
 	[MOD_HDCP_MESSAGE_ID_READ_BINFO] = 0x6802a,
+	[MOD_HDCP_MESSAGE_ID_RX_CAPS] = 0x6921d,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT] = 0x69000,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = 0x6900b,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = 0x69220,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = 0x692a0,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = 0x692c0,
+	[MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = 0x692e0,
+	[MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT] = 0x692f0,
+	[MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = 0x692f8,
+	[MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = 0x69318,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = 0x69330,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = 0x693e0,
+	[MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = 0x693f0,
+	[MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = 0x69473,
+	[MOD_HDCP_MESSAGE_ID_READ_RXSTATUS] = 0x69493,
+	[MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE] = 0x69494
 };
 
 static enum mod_hdcp_status read(struct mod_hdcp *hdcp,
@@ -303,3 +355,277 @@ enum mod_hdcp_status mod_hdcp_write_an(struct mod_hdcp *hdcp)
 			hdcp->auth.msg.hdcp1.an,
 			sizeof(hdcp->auth.msg.hdcp1.an));
 }
+
+enum mod_hdcp_status mod_hdcp_read_hdcp2version(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	else
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_HDCP2VERSION,
+				&hdcp->auth.msg.hdcp2.hdcp2version_hdmi,
+				sizeof(hdcp->auth.msg.hdcp2.hdcp2version_hdmi));
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_rxcaps(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (!is_dp_hdcp(hdcp))
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	else
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_RX_CAPS,
+				hdcp->auth.msg.hdcp2.rxcaps_dp,
+				sizeof(hdcp->auth.msg.hdcp2.rxcaps_dp));
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_rxstatus(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_RXSTATUS,
+				&hdcp->auth.msg.hdcp2.rxstatus_dp,
+				1);
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_RXSTATUS,
+					(uint8_t *)&hdcp->auth.msg.hdcp2.rxstatus,
+					sizeof(hdcp->auth.msg.hdcp2.rxstatus));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_ake_cert(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.ake_cert[0] = 3;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+				hdcp->auth.msg.hdcp2.ake_cert+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_cert)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+					hdcp->auth.msg.hdcp2.ake_cert,
+					sizeof(hdcp->auth.msg.hdcp2.ake_cert));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_h_prime(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.ake_h_prime[0] = 7;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+				hdcp->auth.msg.hdcp2.ake_h_prime+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+				hdcp->auth.msg.hdcp2.ake_h_prime,
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_pairing_info(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.ake_pairing_info[0] = 8;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+				hdcp->auth.msg.hdcp2.ake_pairing_info+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+				hdcp->auth.msg.hdcp2.ake_pairing_info,
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_l_prime(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.lc_l_prime[0] = 10;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+				hdcp->auth.msg.hdcp2.lc_l_prime+1,
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+				hdcp->auth.msg.hdcp2.lc_l_prime,
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_rx_id_list(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.rx_id_list[0] = 12;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+				hdcp->auth.msg.hdcp2.rx_id_list+1,
+				sizeof(hdcp->auth.msg.hdcp2.rx_id_list)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+				hdcp->auth.msg.hdcp2.rx_id_list,
+				hdcp->auth.msg.hdcp2.rx_id_list_size);
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_stream_ready(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp)) {
+		hdcp->auth.msg.hdcp2.repeater_auth_stream_ready[0] = 17;
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready+1,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)-1);
+
+	} else {
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready));
+	}
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_ake_init(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+				hdcp->auth.msg.hdcp2.ake_init+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_init)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+					hdcp->auth.msg.hdcp2.ake_init,
+					sizeof(hdcp->auth.msg.hdcp2.ake_init));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_no_stored_km(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+				hdcp->auth.msg.hdcp2.ake_no_stored_km+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+			hdcp->auth.msg.hdcp2.ake_no_stored_km,
+			sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_stored_km(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+				hdcp->auth.msg.hdcp2.ake_stored_km+1,
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+				hdcp->auth.msg.hdcp2.ake_stored_km,
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_lc_init(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT,
+				hdcp->auth.msg.hdcp2.lc_init+1,
+				sizeof(hdcp->auth.msg.hdcp2.lc_init)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_LC_INIT,
+				hdcp->auth.msg.hdcp2.lc_init,
+				sizeof(hdcp->auth.msg.hdcp2.lc_init));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_eks(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp,
+				MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+				hdcp->auth.msg.hdcp2.ske_eks+1,
+				sizeof(hdcp->auth.msg.hdcp2.ske_eks)-1);
+	else
+		status = write(hdcp,
+			MOD_HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+			hdcp->auth.msg.hdcp2.ske_eks,
+			sizeof(hdcp->auth.msg.hdcp2.ske_eks));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_repeater_auth_ack(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+				hdcp->auth.msg.hdcp2.repeater_auth_ack+1,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack)-1);
+	else
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+				hdcp->auth.msg.hdcp2.repeater_auth_ack,
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_stream_manage(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp,
+				MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage+1,
+				hdcp->auth.msg.hdcp2.stream_manage_size-1);
+	else
+		status = write(hdcp,
+				MOD_HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage,
+				hdcp->auth.msg.hdcp2.stream_manage_size);
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE,
+				hdcp->auth.msg.hdcp2.content_stream_type_dp+1,
+				sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp)-1);
+	else
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
index 3982ced5f969..724ebcee9a19 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
@@ -116,6 +116,58 @@ char *mod_hdcp_status_to_str(int32_t status)
 		return "MOD_HDCP_STATUS_DDC_FAILURE";
 	case MOD_HDCP_STATUS_INVALID_OPERATION:
 		return "MOD_HDCP_STATUS_INVALID_OPERATION";
+	case MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE:
+		return "MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE";
+	case MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_AKE_CERT_REVOKED:
+		return "MOD_HDCP_STATUS_HDCP2_AKE_CERT_REVOKED";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED:
+		return "MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED";
+	case MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY:
+		return "MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY";
+	case MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION:
+		return "MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION";
+	case MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING:
+		return "MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING";
+	case MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST:
+		return "MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST";
+	case MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE";
+	case MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE";
 	default:
 		return "MOD_HDCP_STATUS_UNKNOWN";
 	}
@@ -156,6 +208,72 @@ char *mod_hdcp_state_id_to_str(int32_t id)
 		return "D1_A6_WAIT_FOR_READY";
 	case D1_A7_READ_KSV_LIST:
 		return "D1_A7_READ_KSV_LIST";
+	case H2_A0_KNOWN_HDCP2_CAPABLE_RX:
+		return "H2_A0_KNOWN_HDCP2_CAPABLE_RX";
+	case H2_A1_SEND_AKE_INIT:
+		return "H2_A1_SEND_AKE_INIT";
+	case H2_A1_VALIDATE_AKE_CERT:
+		return "H2_A1_VALIDATE_AKE_CERT";
+	case H2_A1_SEND_NO_STORED_KM:
+		return "H2_A1_SEND_NO_STORED_KM";
+	case H2_A1_READ_H_PRIME:
+		return "H2_A1_READ_H_PRIME";
+	case H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		return "H2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME";
+	case H2_A1_SEND_STORED_KM:
+		return "H2_A1_SEND_STORED_KM";
+	case H2_A1_VALIDATE_H_PRIME:
+		return "H2_A1_VALIDATE_H_PRIME";
+	case H2_A2_LOCALITY_CHECK:
+		return "H2_A2_LOCALITY_CHECK";
+	case H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		return "H2_A3_EXCHANGE_KS_AND_TEST_FOR_REPEATER";
+	case H2_ENABLE_ENCRYPTION:
+		return "H2_ENABLE_ENCRYPTION";
+	case H2_A5_AUTHENTICATED:
+		return "H2_A5_AUTHENTICATED";
+	case H2_A6_WAIT_FOR_RX_ID_LIST:
+		return "H2_A6_WAIT_FOR_RX_ID_LIST";
+	case H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		return "H2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK";
+	case H2_A9_SEND_STREAM_MANAGEMENT:
+		return "H2_A9_SEND_STREAM_MANAGEMENT";
+	case H2_A9_VALIDATE_STREAM_READY:
+		return "H2_A9_VALIDATE_STREAM_READY";
+	case D2_A0_DETERMINE_RX_HDCP_CAPABLE:
+		return "D2_A0_DETERMINE_RX_HDCP_CAPABLE";
+	case D2_A1_SEND_AKE_INIT:
+		return "D2_A1_SEND_AKE_INIT";
+	case D2_A1_VALIDATE_AKE_CERT:
+		return "D2_A1_VALIDATE_AKE_CERT";
+	case D2_A1_SEND_NO_STORED_KM:
+		return "D2_A1_SEND_NO_STORED_KM";
+	case D2_A1_READ_H_PRIME:
+		return "D2_A1_READ_H_PRIME";
+	case D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME:
+		return "D2_A1_READ_PAIRING_INFO_AND_VALIDATE_H_PRIME";
+	case D2_A1_SEND_STORED_KM:
+		return "D2_A1_SEND_STORED_KM";
+	case D2_A1_VALIDATE_H_PRIME:
+		return "D2_A1_VALIDATE_H_PRIME";
+	case D2_A2_LOCALITY_CHECK:
+		return "D2_A2_LOCALITY_CHECK";
+	case D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER:
+		return "D2_A34_EXCHANGE_KS_AND_TEST_FOR_REPEATER";
+	case D2_SEND_CONTENT_STREAM_TYPE:
+		return "D2_SEND_CONTENT_STREAM_TYPE";
+	case D2_ENABLE_ENCRYPTION:
+		return "D2_ENABLE_ENCRYPTION";
+	case D2_A5_AUTHENTICATED:
+		return "D2_A5_AUTHENTICATED";
+	case D2_A6_WAIT_FOR_RX_ID_LIST:
+		return "D2_A6_WAIT_FOR_RX_ID_LIST";
+	case D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK:
+		return "D2_A78_VERIFY_RX_ID_LIST_AND_SEND_ACK";
+	case D2_A9_SEND_STREAM_MANAGEMENT:
+		return "D2_A9_SEND_STREAM_MANAGEMENT";
+	case D2_A9_VALIDATE_STREAM_READY:
+		return "D2_A9_VALIDATE_STREAM_READY";
 	default:
 		return "UNKNOWN_STATE_ID";
 	};
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
index 2fd0e0a893ef..ff91373ebada 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
@@ -27,7 +27,7 @@
 #define MOD_HDCP_LOG_H_
 
 #ifdef CONFIG_DRM_AMD_DC_HDCP
-#define HDCP_LOG_ERR(hdcp, ...) DRM_ERROR(__VA_ARGS__)
+#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__)
 #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
 #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__)
@@ -37,7 +37,7 @@
 /* default logs */
 #define HDCP_ERROR_TRACE(hdcp, status) \
 		HDCP_LOG_ERR(hdcp, \
-			"[Link %d] ERROR %s IN STATE %s", \
+			"[Link %d] WARNING %s IN STATE %s", \
 			hdcp->config.index, \
 			mod_hdcp_status_to_str(status), \
 			mod_hdcp_state_id_to_str(hdcp->state.id))
@@ -45,6 +45,10 @@
 		HDCP_LOG_VER(hdcp, \
 			"[Link %d] HDCP 1.4 enabled on display %d", \
 			hdcp->config.index, displayIndex)
+#define HDCP_HDCP2_ENABLED_TRACE(hdcp, displayIndex) \
+		HDCP_LOG_VER(hdcp, \
+			"[Link %d] HDCP 2.2 enabled on display %d", \
+			hdcp->config.index, displayIndex)
 /* state machine logs */
 #define HDCP_REMOVE_DISPLAY_TRACE(hdcp, displayIndex) \
 		HDCP_LOG_FSM(hdcp, \
@@ -93,26 +97,73 @@
 				hdcp->buf); \
 } while (0)
 #define HDCP_FULL_DDC_TRACE(hdcp) do { \
-	HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv, \
-			sizeof(hdcp->auth.msg.hdcp1.bksv)); \
-	HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps, \
-			sizeof(hdcp->auth.msg.hdcp1.bcaps)); \
-	HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an, \
-			sizeof(hdcp->auth.msg.hdcp1.an)); \
-	HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv, \
-			sizeof(hdcp->auth.msg.hdcp1.aksv)); \
-	HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo, \
-			sizeof(hdcp->auth.msg.hdcp1.ainfo)); \
-	HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'", \
-			(uint8_t *)&hdcp->auth.msg.hdcp1.r0p, \
-			sizeof(hdcp->auth.msg.hdcp1.r0p)); \
-	HDCP_DDC_READ_TRACE(hdcp, "BINFO", \
-			(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp, \
-			sizeof(hdcp->auth.msg.hdcp1.binfo_dp)); \
-	HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist, \
-			hdcp->auth.msg.hdcp1.ksvlist_size); \
-	HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp, \
-			sizeof(hdcp->auth.msg.hdcp1.vp)); \
+	if (is_hdcp1(hdcp)) { \
+		HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv, \
+				sizeof(hdcp->auth.msg.hdcp1.bksv)); \
+		HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps, \
+				sizeof(hdcp->auth.msg.hdcp1.bcaps)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an, \
+				sizeof(hdcp->auth.msg.hdcp1.an)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv, \
+				sizeof(hdcp->auth.msg.hdcp1.aksv)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo, \
+				sizeof(hdcp->auth.msg.hdcp1.ainfo)); \
+		HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'", \
+				(uint8_t *)&hdcp->auth.msg.hdcp1.r0p, \
+				sizeof(hdcp->auth.msg.hdcp1.r0p)); \
+		HDCP_DDC_READ_TRACE(hdcp, "BINFO", \
+				(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp, \
+				sizeof(hdcp->auth.msg.hdcp1.binfo_dp)); \
+		HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist, \
+				hdcp->auth.msg.hdcp1.ksvlist_size); \
+		HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp, \
+				sizeof(hdcp->auth.msg.hdcp1.vp)); \
+	} else { \
+		HDCP_DDC_READ_TRACE(hdcp, "HDCP2Version", \
+				&hdcp->auth.msg.hdcp2.hdcp2version_hdmi, \
+				sizeof(hdcp->auth.msg.hdcp2.hdcp2version_hdmi)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Caps", hdcp->auth.msg.hdcp2.rxcaps_dp, \
+				sizeof(hdcp->auth.msg.hdcp2.rxcaps_dp)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "AKE Init", hdcp->auth.msg.hdcp2.ake_init, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_init)); \
+		HDCP_DDC_READ_TRACE(hdcp, "AKE Cert", hdcp->auth.msg.hdcp2.ake_cert, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_cert)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Stored KM", \
+				hdcp->auth.msg.hdcp2.ake_stored_km, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_stored_km)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "No Stored KM", \
+				hdcp->auth.msg.hdcp2.ake_no_stored_km, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)); \
+		HDCP_DDC_READ_TRACE(hdcp, "H'", hdcp->auth.msg.hdcp2.ake_h_prime, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Pairing Info", \
+				hdcp->auth.msg.hdcp2.ake_pairing_info, \
+				sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "LC Init", hdcp->auth.msg.hdcp2.lc_init, \
+				sizeof(hdcp->auth.msg.hdcp2.lc_init)); \
+		HDCP_DDC_READ_TRACE(hdcp, "L'", hdcp->auth.msg.hdcp2.lc_l_prime, \
+				sizeof(hdcp->auth.msg.hdcp2.lc_l_prime)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Exchange KS", hdcp->auth.msg.hdcp2.ske_eks, \
+				sizeof(hdcp->auth.msg.hdcp2.ske_eks)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Status", \
+				(uint8_t *)&hdcp->auth.msg.hdcp2.rxstatus, \
+				sizeof(hdcp->auth.msg.hdcp2.rxstatus)); \
+		HDCP_DDC_READ_TRACE(hdcp, "Rx Id List", \
+				hdcp->auth.msg.hdcp2.rx_id_list, \
+				hdcp->auth.msg.hdcp2.rx_id_list_size); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Rx Id List Ack", \
+				hdcp->auth.msg.hdcp2.repeater_auth_ack, \
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Management", \
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_manage, \
+				hdcp->auth.msg.hdcp2.stream_manage_size); \
+		HDCP_DDC_READ_TRACE(hdcp, "Stream Ready", \
+				hdcp->auth.msg.hdcp2.repeater_auth_stream_ready, \
+				sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready)); \
+		HDCP_DDC_WRITE_TRACE(hdcp, "Content Stream Type", \
+				hdcp->auth.msg.hdcp2.content_stream_type_dp, \
+				sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp)); \
+	} \
 } while (0)
 #define HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, i) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\tadd display %d", \
@@ -123,6 +174,9 @@
 #define HDCP_TOP_HDCP1_DESTROY_SESSION_TRACE(hdcp) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\tdestroy hdcp1 session", \
 				hdcp->config.index)
+#define HDCP_TOP_HDCP2_DESTROY_SESSION_TRACE(hdcp) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\tdestroy hdcp2 session", \
+				hdcp->config.index)
 #define HDCP_TOP_RESET_AUTH_TRACE(hdcp) \
 		HDCP_LOG_TOP(hdcp, "[Link %d]\treset authentication", hdcp->config.index)
 #define HDCP_TOP_RESET_CONN_TRACE(hdcp) \
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index 646d909bbc37..7911dc157d5a 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -31,6 +31,19 @@
 #include "amdgpu.h"
 #include "hdcp_psp.h"
 
+static void hdcp2_message_init(struct mod_hdcp *hdcp,
+			       struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *in)
+{
+	in->session_handle = hdcp->auth.id;
+	in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->prepare.msg2_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg1_desc.msg_size = 0;
+	in->process.msg2_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg2_desc.msg_size = 0;
+	in->process.msg3_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE;
+	in->process.msg3_desc.msg_size = 0;
+}
 enum mod_hdcp_status mod_hdcp_remove_display_topology(struct mod_hdcp *hdcp)
 {
 
@@ -42,7 +55,7 @@ enum mod_hdcp_status mod_hdcp_remove_display_topology(struct mod_hdcp *hdcp)
 	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
 
 	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
-		if (hdcp->connection.displays[i].state == MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED) {
+		if (is_display_added(&(hdcp->connection.displays[i]))) {
 
 			memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
 
@@ -96,7 +109,7 @@ enum mod_hdcp_status mod_hdcp_add_display_topology(struct mod_hdcp *hdcp)
 			dtm_cmd->dtm_in_message.topology_update_v2.dig_fe = display->dig_fe;
 			dtm_cmd->dtm_in_message.topology_update_v2.dp_mst_vcid = display->vc_id;
 			dtm_cmd->dtm_in_message.topology_update_v2.max_hdcp_supported_version =
-				TA_DTM_HDCP_VERSION_MAX_SUPPORTED__1_x;
+				TA_DTM_HDCP_VERSION_MAX_SUPPORTED__2_2;
 			dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE;
 
 			psp_dtm_invoke(psp, dtm_cmd->cmd_id);
@@ -132,10 +145,11 @@ enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp)
 
 	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
 
+	hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle;
+
 	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
 		return MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE;
 
-	hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle;
 	hdcp->auth.msg.hdcp1.ainfo = hdcp_cmd->out_msg.hdcp1_create_session.ainfo_primary;
 	memcpy(hdcp->auth.msg.hdcp1.aksv, hdcp_cmd->out_msg.hdcp1_create_session.aksv_primary,
 		sizeof(hdcp->auth.msg.hdcp1.aksv));
@@ -326,3 +340,493 @@ enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *
 	return MOD_HDCP_STATUS_SUCCESS;
 }
 
+enum mod_hdcp_status mod_hdcp_hdcp2_create_session(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct mod_hdcp_display *display = get_first_added_display(hdcp);
+
+	if (!psp->hdcp_context.hdcp_initialized) {
+		DRM_ERROR("Failed to create hdcp session, HDCP TA is not initialized");
+		return MOD_HDCP_STATUS_FAILURE;
+	}
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
+	hdcp_cmd->in_msg.hdcp2_create_session_v2.display_handle = display->index;
+
+	if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_0)
+		hdcp_cmd->in_msg.hdcp2_create_session_v2.negotiate_content_type =
+			TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE0;
+	else if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_1)
+		hdcp_cmd->in_msg.hdcp2_create_session_v2.negotiate_content_type =
+			TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE1;
+	else if (hdcp->connection.link.adjust.hdcp2.force_type == MOD_HDCP_FORCE_TYPE_MAX)
+		hdcp_cmd->in_msg.hdcp2_create_session_v2.negotiate_content_type =
+			TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__MAX_SUPPORTED;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_CREATE_SESSION_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE;
+
+	hdcp->auth.id = hdcp_cmd->out_msg.hdcp2_create_session_v2.session_handle;
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_destroy_session(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp2_destroy_session.session_handle = hdcp->auth.id;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_DESTROY_SESSION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE;
+
+	HDCP_TOP_HDCP2_DESTROY_SESSION_TRACE(hdcp);
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_ake_init(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__AKE_INIT;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE;
+
+	memcpy(&hdcp->auth.msg.hdcp2.ake_init[0], &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.ake_init));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_ake_cert(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__AKE_SEND_CERT;
+	msg_in->process.msg1_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_CERT;
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.ake_cert,
+	       sizeof(hdcp->auth.msg.hdcp2.ake_cert));
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__AKE_NO_STORED_KM;
+	msg_in->prepare.msg2_id = TA_HDCP_HDCP2_MSG_ID__AKE_STORED_KM;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.ake_no_stored_km, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km));
+
+	memcpy(hdcp->auth.msg.hdcp2.ake_stored_km,
+	       &msg_out->prepare.transmitter_message[sizeof(hdcp->auth.msg.hdcp2.ake_no_stored_km)],
+	       sizeof(hdcp->auth.msg.hdcp2.ake_stored_km));
+
+	if (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS) {
+		hdcp->connection.is_km_stored = msg_out->process.is_km_stored ? 1 : 0;
+		hdcp->connection.is_repeater = msg_out->process.is_repeater ? 1 : 0;
+		return MOD_HDCP_STATUS_SUCCESS;
+	}
+
+	return MOD_HDCP_STATUS_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_h_prime(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__AKE_SEND_H_PRIME;
+	msg_in->process.msg1_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_H_PRIME;
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.ake_h_prime,
+	       sizeof(hdcp->auth.msg.hdcp2.ake_h_prime));
+
+	if (!hdcp->connection.is_km_stored) {
+		msg_in->process.msg2_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__AKE_SEND_PAIRING_INFO;
+		msg_in->process.msg2_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_PAIRING_INFO;
+		memcpy(&msg_in->process.receiver_message[sizeof(hdcp->auth.msg.hdcp2.ake_h_prime)],
+		       hdcp->auth.msg.hdcp2.ake_pairing_info, sizeof(hdcp->auth.msg.hdcp2.ake_pairing_info));
+	}
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE;
+
+	if (msg_out->process.msg1_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE;
+	else if (!hdcp->connection.is_km_stored &&
+		 msg_out->process.msg2_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE;
+
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_lc_init(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__LC_INIT;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.lc_init, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.lc_init));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_l_prime(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__LC_SEND_L_PRIME;
+	msg_in->process.msg1_desc.msg_size = TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__LC_SEND_L_PRIME;
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.lc_l_prime,
+	       sizeof(hdcp->auth.msg.hdcp2.lc_l_prime));
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE;
+
+	if (msg_out->process.msg1_status != TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE;
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_eks(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__SKE_SEND_EKS;
+
+	if (is_dp_hdcp(hdcp))
+		msg_in->prepare.msg2_id = TA_HDCP_HDCP2_MSG_ID__SIGNAL_CONTENT_STREAM_TYPE_DP;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.ske_eks, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.ske_eks));
+	msg_out->prepare.msg1_desc.msg_size = sizeof(hdcp->auth.msg.hdcp2.ske_eks);
+
+	if (is_dp_hdcp(hdcp)) {
+		memcpy(hdcp->auth.msg.hdcp2.content_stream_type_dp,
+		       &msg_out->prepare.transmitter_message[sizeof(hdcp->auth.msg.hdcp2.ske_eks)],
+		       sizeof(hdcp->auth.msg.hdcp2.content_stream_type_dp));
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_encryption(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct mod_hdcp_display *display = get_first_added_display(hdcp);
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	if (!display)
+		return MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+
+	hdcp_cmd->in_msg.hdcp1_enable_encryption.session_handle = hdcp->auth.id;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_SET_ENCRYPTION;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE;
+
+	if (!is_dp_mst_hdcp(hdcp)) {
+		display->state = MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+		HDCP_HDCP2_ENABLED_TRACE(hdcp, display->index);
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_rx_id_list(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_RECEIVERID_LIST;
+	msg_in->process.msg1_desc.msg_size = sizeof(hdcp->auth.msg.hdcp2.rx_id_list);
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.rx_id_list,
+	       sizeof(hdcp->auth.msg.hdcp2.rx_id_list));
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_ACK;
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE;
+
+	memcpy(hdcp->auth.msg.hdcp2.repeater_auth_ack, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.repeater_auth_ack));
+
+	if (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS) {
+		hdcp->connection.is_km_stored = msg_out->process.is_km_stored ? 1 : 0;
+		hdcp->connection.is_repeater = msg_out->process.is_repeater ? 1 : 0;
+		return MOD_HDCP_STATUS_SUCCESS;
+	}
+
+
+	return MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_enable_dp_stream_encryption(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	uint8_t i;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED ||
+		    hdcp->connection.displays[i].adjust.disable)
+			continue;
+		hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.display_handle = hdcp->connection.displays[i].index;
+		hdcp_cmd->in_msg.hdcp2_enable_dp_stream_encryption.session_handle = hdcp->auth.id;
+
+		hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_ENABLE_DP_STREAM_ENCRYPTION;
+		psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+		if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+			break;
+
+		hdcp->connection.displays[i].state = MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+		HDCP_HDCP2_ENABLED_TRACE(hdcp, hdcp->connection.displays[i].index);
+	}
+
+	return (hdcp_cmd->hdcp_status == TA_HDCP_STATUS__SUCCESS) ? MOD_HDCP_STATUS_SUCCESS
+								  : MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_prepare_stream_management(struct mod_hdcp *hdcp)
+{
+
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->prepare.msg1_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_MANAGE;
+
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE;
+
+	hdcp->auth.msg.hdcp2.stream_manage_size = msg_out->prepare.msg1_desc.msg_size;
+
+	memcpy(hdcp->auth.msg.hdcp2.repeater_auth_stream_manage, &msg_out->prepare.transmitter_message[0],
+	       sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_manage));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_validate_stream_ready(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 *msg_in;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 *msg_out;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	msg_in = &hdcp_cmd->in_msg.hdcp2_prepare_process_authentication_message_v2;
+	msg_out = &hdcp_cmd->out_msg.hdcp2_prepare_process_authentication_message_v2;
+
+	hdcp2_message_init(hdcp, msg_in);
+
+	msg_in->process.msg1_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_READY;
+
+	msg_in->process.msg1_desc.msg_size = sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready);
+
+	memcpy(&msg_in->process.receiver_message[0], hdcp->auth.msg.hdcp2.repeater_auth_stream_ready,
+	       sizeof(hdcp->auth.msg.hdcp2.repeater_auth_stream_ready));
+
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2;
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	return (hdcp_cmd->hdcp_status == TA_HDCP_STATUS__SUCCESS) &&
+			       (msg_out->process.msg1_status == TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS)
+		       ? MOD_HDCP_STATUS_SUCCESS
+		       : MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp2_get_link_encryption_status(struct mod_hdcp *hdcp,
+							       enum mod_hdcp_encryption_status *encryption_status)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp2_get_encryption_status.session_handle = hdcp->auth.id;
+	hdcp_cmd->out_msg.hdcp2_get_encryption_status.protection_level = 0;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP2_GET_ENCRYPTION_STATUS;
+	*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_FAILURE;
+
+	if (hdcp_cmd->out_msg.hdcp2_get_encryption_status.protection_level == 1) {
+		if (hdcp_cmd->out_msg.hdcp2_get_encryption_status.hdcp2_type == TA_HDCP2_CONTENT_TYPE__TYPE1)
+			*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON;
+		else
+			*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON;
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
index 986fc07ea9ea..82a5e997d573 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
@@ -36,6 +36,11 @@ enum bgd_security_hdcp_encryption_level {
 	HDCP_ENCRYPTION_LEVEL__ON
 };
 
+enum bgd_security_hdcp2_content_type {
+	HDCP2_CONTENT_TYPE__INVALID = 0,
+	HDCP2_CONTENT_TYPE__TYPE0,
+	HDCP2_CONTENT_TYPE__TYPE1
+};
 enum ta_dtm_command {
 	TA_DTM_COMMAND__UNUSED_1 = 1,
 	TA_DTM_COMMAND__TOPOLOGY_UPDATE_V2,
@@ -121,8 +126,64 @@ enum ta_hdcp_command {
 	TA_HDCP_COMMAND__HDCP1_ENABLE_ENCRYPTION,
 	TA_HDCP_COMMAND__HDCP1_ENABLE_DP_STREAM_ENCRYPTION,
 	TA_HDCP_COMMAND__HDCP1_GET_ENCRYPTION_STATUS,
+	TA_HDCP_COMMAND__UNUSED_1,
+	TA_HDCP_COMMAND__HDCP2_DESTROY_SESSION,
+	TA_HDCP_COMMAND__UNUSED_2,
+	TA_HDCP_COMMAND__HDCP2_SET_ENCRYPTION,
+	TA_HDCP_COMMAND__HDCP2_GET_ENCRYPTION_STATUS,
+	TA_HDCP_COMMAND__UNUSED_3,
+	TA_HDCP_COMMAND__HDCP2_CREATE_SESSION_V2,
+	TA_HDCP_COMMAND__HDCP2_PREPARE_PROCESS_AUTHENTICATION_MSG_V2,
+	TA_HDCP_COMMAND__HDCP2_ENABLE_DP_STREAM_ENCRYPTION
+};
+
+enum ta_hdcp2_msg_id {
+	TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE = 1,
+	TA_HDCP_HDCP2_MSG_ID__AKE_INIT = 2,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_CERT = 3,
+	TA_HDCP_HDCP2_MSG_ID__AKE_NO_STORED_KM = 4,
+	TA_HDCP_HDCP2_MSG_ID__AKE_STORED_KM = 5,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_RRX = 6,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_H_PRIME = 7,
+	TA_HDCP_HDCP2_MSG_ID__AKE_SEND_PAIRING_INFO = 8,
+	TA_HDCP_HDCP2_MSG_ID__LC_INIT = 9,
+	TA_HDCP_HDCP2_MSG_ID__LC_SEND_L_PRIME = 10,
+	TA_HDCP_HDCP2_MSG_ID__SKE_SEND_EKS = 11,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_RECEIVERID_LIST = 12,
+	TA_HDCP_HDCP2_MSG_ID__RTT_READY = 13,
+	TA_HDCP_HDCP2_MSG_ID__RTT_CHALLENGE = 14,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_SEND_ACK = 15,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_MANAGE = 16,
+	TA_HDCP_HDCP2_MSG_ID__REPEATERAUTH_STREAM_READY = 17,
+	TA_HDCP_HDCP2_MSG_ID__RECEIVER_AUTH_STATUS = 18,
+	TA_HDCP_HDCP2_MSG_ID__AKE_TRANSMITTER_INFO = 19,
+	TA_HDCP_HDCP2_MSG_ID__AKE_RECEIVER_INFO = 20,
+	TA_HDCP_HDCP2_MSG_ID__SIGNAL_CONTENT_STREAM_TYPE_DP = 129
 };
 
+enum ta_hdcp2_hdcp2_msg_id_max_size {
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__NULL_MESSAGE = 0,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_INIT = 12,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_CERT = 534,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_NO_STORED_KM = 129,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_STORED_KM = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_RRX = 9,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_H_PRIME = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_PAIRING_INFO = 17,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__LC_INIT = 9,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__LC_SEND_L_PRIME = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__SKE_SEND_EKS = 25,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_SEND_RECEIVERID_LIST = 181,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__RTT_READY = 1,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__RTT_CHALLENGE = 17,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_SEND_RACK = 17,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_STREAM_MANAGE = 13,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__REPEATERAUTH_STREAM_READY = 33,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__RECEIVER_AUTH_STATUS = 4,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_TRANSMITTER_INFO = 6,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_RECEIVER_INFO = 6,
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__SIGNAL_CONTENT_STREAM_TYPE_DP = 1
+};
 
 /* HDCP related enumerations */
 /**********************************************************/
@@ -131,6 +192,12 @@ enum ta_hdcp_command {
 #define TA_HDCP__HDCP1_KSV_SIZE 5
 #define TA_HDCP__HDCP1_KSV_LIST_MAX_ENTRIES 127
 #define TA_HDCP__HDCP1_V_PRIME_SIZE 20
+#define TA_HDCP__HDCP2_TX_BUF_MAX_SIZE                                                                                 \
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_NO_STORED_KM + TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_STORED_KM + 6
+
+// 64 bits boundaries
+#define TA_HDCP__HDCP2_RX_BUF_MAX_SIZE                                                                                 \
+	TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_SEND_CERT + TA_HDCP_HDCP2_MSG_ID_MAX_SIZE__AKE_RECEIVER_INFO + 4
 
 enum ta_hdcp_status {
 	TA_HDCP_STATUS__SUCCESS = 0x00,
@@ -165,9 +232,47 @@ enum ta_hdcp_authentication_status {
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_FIRST_PART_COMPLETE = 0x02,
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_SECOND_PART_FAILED = 0x03,
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_AUTHENTICATED = 0x04,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP22_AUTHENTICATION_PENDING = 0x06,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP22_AUTHENTICATION_FAILED = 0x07,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP22_AUTHENTICATED = 0x08,
 	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_KSV_VALIDATION_FAILED = 0x09
 };
 
+enum ta_hdcp2_msg_authentication_status {
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__SUCCESS = 0,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__KM_NOT_AVAILABLE,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__UNUSED,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID = 100, // everything above does not fail the request
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__NOT_ENOUGH_MEMORY,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__NOT_EXPECTED_MSG,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__SIGNATURE_CERTIFICAT_ERROR,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INCORRECT_HDCP_VERSION,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__UNKNOWN_MESSAGE,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_HMAC,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_TOPOLOGY,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_SEQ_NUM,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_SIZE,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__INVALID_LENGTH,
+	TA_HDCP2_MSG_AUTHENTICATION_STATUS__REAUTH_REQUEST
+};
+
+enum ta_hdcp_content_type {
+	TA_HDCP2_CONTENT_TYPE__TYPE0 = 1,
+	TA_HDCP2_CONTENT_TYPE__TYPE1,
+};
+
+enum ta_hdcp_content_type_negotiation_type {
+	TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE0 = 1,
+	TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__FORCE_TYPE1,
+	TA_HDCP2_CONTENT_TYPE_NEGOTIATION_TYPE__MAX_SUPPORTED
+};
+
+enum ta_hdcp2_version {
+	TA_HDCP2_VERSION_UNKNOWN = 0,
+	TA_HDCP2_VERSION_2_0 = 20,
+	TA_HDCP2_VERSION_2_1 = 21,
+	TA_HDCP2_VERSION_2_2 = 22
+};
 
 /* input/output structures for HDCP commands */
 /**********************************************************/
@@ -232,6 +337,84 @@ struct ta_hdcp_cmd_hdcp1_get_encryption_status_output {
 	uint32_t protection_level;
 };
 
+struct ta_hdcp_cmd_hdcp2_create_session_input_v2 {
+	uint32_t display_handle;
+	enum ta_hdcp_content_type_negotiation_type negotiate_content_type;
+};
+
+struct ta_hdcp_cmd_hdcp2_create_session_output_v2 {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_destroy_session_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_authentication_message_v2 {
+	enum ta_hdcp2_msg_id msg_id;
+	uint32_t msg_size;
+};
+
+struct ta_hdcp_cmd_hdcp2_process_authentication_message_input_v2 {
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg1_desc;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg2_desc;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg3_desc;
+	uint8_t receiver_message[TA_HDCP__HDCP2_RX_BUF_MAX_SIZE];
+};
+
+struct ta_hdcp_cmd_hdcp2_process_authentication_message_output_v2 {
+	uint32_t hdcp_version;
+	uint32_t is_km_stored;
+	uint32_t is_locality_precompute_support;
+	uint32_t is_repeater;
+	enum ta_hdcp2_msg_authentication_status msg1_status;
+	enum ta_hdcp2_msg_authentication_status msg2_status;
+	enum ta_hdcp2_msg_authentication_status msg3_status;
+};
+
+struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_input_v2 {
+	enum ta_hdcp2_msg_id msg1_id;
+	enum ta_hdcp2_msg_id msg2_id;
+};
+
+struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_output_v2 {
+	enum ta_hdcp2_msg_authentication_status msg1_status;
+	enum ta_hdcp2_msg_authentication_status msg2_status;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg1_desc;
+	struct ta_hdcp_cmd_hdcp2_authentication_message_v2 msg2_desc;
+	uint8_t transmitter_message[TA_HDCP__HDCP2_TX_BUF_MAX_SIZE];
+};
+
+struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2 {
+	uint32_t session_handle;
+	struct ta_hdcp_cmd_hdcp2_process_authentication_message_input_v2 process;
+	struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_input_v2 prepare;
+};
+
+struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2 {
+	uint32_t authentication_status;
+	struct ta_hdcp_cmd_hdcp2_process_authentication_message_output_v2 process;
+	struct ta_hdcp_cmd_hdcp2_prepare_authentication_message_output_v2 prepare;
+};
+
+struct ta_hdcp_cmd_hdcp2_set_encryption_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_get_encryption_status_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp2_get_encryption_status_output {
+	enum ta_hdcp_content_type hdcp2_type;
+	uint32_t protection_level;
+};
+
+struct ta_hdcp_cmd_hdcp2_enable_dp_stream_encryption_input {
+	uint32_t session_handle;
+	uint32_t display_handle;
+};
+
 /**********************************************************/
 /* Common input structure for HDCP callbacks */
 union ta_hdcp_cmd_input {
@@ -242,6 +425,13 @@ union ta_hdcp_cmd_input {
 	struct ta_hdcp_cmd_hdcp1_enable_encryption_input hdcp1_enable_encryption;
 	struct ta_hdcp_cmd_hdcp1_enable_dp_stream_encryption_input hdcp1_enable_dp_stream_encryption;
 	struct ta_hdcp_cmd_hdcp1_get_encryption_status_input hdcp1_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_destroy_session_input hdcp2_destroy_session;
+	struct ta_hdcp_cmd_hdcp2_set_encryption_input hdcp2_set_encryption;
+	struct ta_hdcp_cmd_hdcp2_get_encryption_status_input hdcp2_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_create_session_input_v2 hdcp2_create_session_v2;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_input_v2
+		hdcp2_prepare_process_authentication_message_v2;
+	struct ta_hdcp_cmd_hdcp2_enable_dp_stream_encryption_input hdcp2_enable_dp_stream_encryption;
 };
 
 /* Common output structure for HDCP callbacks */
@@ -250,6 +440,10 @@ union ta_hdcp_cmd_output {
 	struct ta_hdcp_cmd_hdcp1_first_part_authentication_output hdcp1_first_part_authentication;
 	struct ta_hdcp_cmd_hdcp1_second_part_authentication_output hdcp1_second_part_authentication;
 	struct ta_hdcp_cmd_hdcp1_get_encryption_status_output hdcp1_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_get_encryption_status_output hdcp2_get_encryption_status;
+	struct ta_hdcp_cmd_hdcp2_create_session_output_v2 hdcp2_create_session_v2;
+	struct ta_hdcp_cmd_hdcp2_process_prepare_authentication_message_output_v2
+		hdcp2_prepare_process_authentication_message_v2;
 };
 /**********************************************************/
 
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
index dc187844d10b..dbe7835aabcf 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
@@ -92,6 +92,7 @@ struct mod_vrr_params_btr {
 	uint32_t inserted_duration_in_us;
 	uint32_t frames_to_insert;
 	uint32_t frame_counter;
+	uint32_t margin_in_us;
 };
 
 struct mod_vrr_params_fixed_refresh {
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
index dea21702edff..f2a0e1a064da 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
@@ -77,6 +77,7 @@ enum mod_hdcp_status {
 	MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING,
 	MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_AKE_CERT_REVOKED,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE,
 	MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE,
@@ -86,6 +87,7 @@ enum mod_hdcp_status {
 	MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE,
 	MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_REVOKED,
 	MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION,
 	MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING,
 	MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE,
@@ -156,12 +158,18 @@ struct mod_hdcp_link_adjustment_hdcp1 {
 	uint8_t reserved		: 6;
 };
 
+enum mod_hdcp_force_hdcp_type {
+	MOD_HDCP_FORCE_TYPE_MAX = 0,
+	MOD_HDCP_FORCE_TYPE_0,
+	MOD_HDCP_FORCE_TYPE_1
+};
+
 struct mod_hdcp_link_adjustment_hdcp2 {
 	uint8_t disable			: 1;
-	uint8_t disable_type1		: 1;
+	uint8_t force_type		: 2;
 	uint8_t force_no_stored_km	: 1;
 	uint8_t increase_h_prime_timeout: 1;
-	uint8_t reserved		: 4;
+	uint8_t reserved		: 3;
 };
 
 struct mod_hdcp_link_adjustment {
@@ -184,7 +192,8 @@ enum mod_hdcp_encryption_status {
 	MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF = 0,
 	MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON,
 	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON,
-	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON,
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_ON
 };
 
 /* per link events dm has to notify to hdcp module */
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
index ca8ce3c55337..42cbeffac640 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
@@ -26,6 +26,7 @@
 #ifndef MOD_INFO_PACKET_H_
 #define MOD_INFO_PACKET_H_
 
+#include "dm_services.h"
 #include "mod_shared.h"
 //Forward Declarations
 struct dc_stream_state;
@@ -33,7 +34,8 @@ struct dc_info_packet;
 struct mod_vrr_params;
 
 void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
-		struct dc_info_packet *info_packet);
+		struct dc_info_packet *info_packet,
+		bool *use_vsc_sdp_for_colorimetry);
 
 void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
 		struct dc_info_packet *info_packet, int ALLMEnabled, int ALLMValue);
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h b/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h
index b45f7d65e76a..fe2117904329 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_shared.h
@@ -45,7 +45,6 @@ enum vrr_packet_type {
 	PACKET_TYPE_VTEM
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 union lut3d_control_flags {
 	unsigned int raw;
 	struct {
@@ -104,6 +103,5 @@ struct lut3d_settings {
 	enum lut3d_control_gamut_map map2;
 	enum lut3d_control_rotation_mode rotation2;
 };
-#endif
 
 #endif /* MOD_SHARED_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index db6b08f6d093..6a8a056424b8 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -30,6 +30,20 @@
 #include "mod_freesync.h"
 #include "dc.h"
 
+enum vsc_packet_revision {
+	vsc_packet_undefined = 0,
+	//01h = VSC SDP supports only 3D stereo.
+	vsc_packet_rev1 = 1,
+	//02h = 3D stereo + PSR.
+	vsc_packet_rev2 = 2,
+	//03h = 3D stereo + PSR2.
+	vsc_packet_rev3 = 3,
+	//04h = 3D stereo + PSR/PSR2 + Y-coordinate.
+	vsc_packet_rev4 = 4,
+	//05h = 3D stereo + PSR/PSR2 + Y-coordinate + Pixel Encoding/Colorimetry Format
+	vsc_packet_rev5 = 5,
+};
+
 #define HDMI_INFOFRAME_TYPE_VENDOR 0x81
 #define HF_VSIF_VERSION 1
 
@@ -116,35 +130,41 @@ enum ColorimetryYCCDP {
 };
 
 void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
-		struct dc_info_packet *info_packet)
+		struct dc_info_packet *info_packet,
+		bool *use_vsc_sdp_for_colorimetry)
 {
-	unsigned int vscPacketRevision = 0;
+	unsigned int vsc_packet_revision = vsc_packet_undefined;
 	unsigned int i;
 	unsigned int pixelEncoding = 0;
 	unsigned int colorimetryFormat = 0;
 	bool stereo3dSupport = false;
 
+	/* Initialize first, later if infopacket is valid determine if VSC SDP
+	 * should be used to signal colorimetry format and pixel encoding.
+	 */
+	*use_vsc_sdp_for_colorimetry = false;
+
 	if (stream->timing.timing_3d_format != TIMING_3D_FORMAT_NONE && stream->view_format != VIEW_3D_FORMAT_NONE) {
-		vscPacketRevision = 1;
+		vsc_packet_revision = vsc_packet_rev1;
 		stereo3dSupport = true;
 	}
 
 	/*VSC packet set to 2 when DP revision >= 1.2*/
 	if (stream->psr_version != 0)
-		vscPacketRevision = 2;
+		vsc_packet_revision = vsc_packet_rev2;
 
 	/* Update to revision 5 for extended colorimetry support for DPCD 1.4+ */
 	if (stream->link->dpcd_caps.dpcd_rev.raw >= 0x14 &&
 			stream->link->dpcd_caps.dprx_feature.bits.VSC_SDP_COLORIMETRY_SUPPORTED)
-		vscPacketRevision = 5;
+		vsc_packet_revision = vsc_packet_rev5;
 
 	/* VSC packet not needed based on the features
 	 * supported by this DP display
 	 */
-	if (vscPacketRevision == 0)
+	if (vsc_packet_revision == vsc_packet_undefined)
 		return;
 
-	if (vscPacketRevision == 0x2) {
+	if (vsc_packet_revision == vsc_packet_rev2) {
 		/* Secondary-data Packet ID = 0*/
 		info_packet->hb0 = 0x00;
 		/* 07h - Packet Type Value indicating Video
@@ -166,7 +186,7 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 		info_packet->valid = true;
 	}
 
-	if (vscPacketRevision == 0x1) {
+	if (vsc_packet_revision == vsc_packet_rev1) {
 
 		info_packet->hb0 = 0x00;	// Secondary-data Packet ID = 0
 		info_packet->hb1 = 0x07;	// 07h = Packet Type Value indicating Video Stream Configuration packet
@@ -237,7 +257,7 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 	 *   the Pixel Encoding/Colorimetry Format and that a Sink device must ignore MISC1, bit 7, and
 	 *   MISC0, bits 7:1 (MISC1, bit 7. and MISC0, bits 7:1 become "don't care").)
 	 */
-	if (vscPacketRevision == 0x5) {
+	if (vsc_packet_revision == vsc_packet_rev5) {
 		/* Secondary-data Packet ID = 0 */
 		info_packet->hb0 = 0x00;
 		/* 07h - Packet Type Value indicating Video Stream Configuration packet */
@@ -249,6 +269,13 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 
 		info_packet->valid = true;
 
+		/* If we are using VSC SDP revision 05h, use this to signal for
+		 * colorimetry format and pixel encoding. HW should later be
+		 * programmed to set MSA MISC1 bit 6 to indicate ignore
+		 * colorimetry format and pixel encoding in the MSA.
+		 */
+		*use_vsc_sdp_for_colorimetry = true;
+
 		/* Set VSC SDP fields for pixel encoding and colorimetry format from DP 1.3 specs
 		 * Data Bytes DB 18~16
 		 * Bits 3:0 (Colorimetry Format)        |  Bits 7:4 (Pixel Encoding)
@@ -393,7 +420,6 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 		 */
 		info_packet->sb[18] = 0;
 	}
-
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 4e2f615c3566..e75a4bb94488 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -662,7 +662,11 @@ bool dmcu_load_iram(struct dmcu *dmcu,
 
 	memset(&ram_table, 0, sizeof(ram_table));
 
-	if (dmcu->dmcu_version.abm_version == 0x23) {
+	if (dmcu->dmcu_version.abm_version == 0x24) {
+		fill_iram_v_2_3((struct iram_table_v_2_2 *)ram_table, params);
+		result = dmcu->funcs->load_iram(
+				dmcu, 0, (char *)(&ram_table), IRAM_RESERVE_AREA_START_V2_2);
+	} else if (dmcu->dmcu_version.abm_version == 0x23) {
 		fill_iram_v_2_3((struct iram_table_v_2_2 *)ram_table, params);
 
 		result = dmcu->funcs->load_iram(
@@ -687,3 +691,4 @@ bool dmcu_load_iram(struct dmcu *dmcu,
 
 	return result;
 }
+
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index dc7eb28f0296..d655a76bedc6 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -53,7 +53,8 @@ enum amd_ip_block_type {
 	AMD_IP_BLOCK_TYPE_VCE,
 	AMD_IP_BLOCK_TYPE_ACP,
 	AMD_IP_BLOCK_TYPE_VCN,
-	AMD_IP_BLOCK_TYPE_MES
+	AMD_IP_BLOCK_TYPE_MES,
+	AMD_IP_BLOCK_TYPE_JPEG
 };
 
 enum amd_clockgating_state {
@@ -99,6 +100,7 @@ enum amd_powergating_state {
 #define AMD_CG_SUPPORT_IH_CG			(1 << 27)
 #define AMD_CG_SUPPORT_ATHUB_LS			(1 << 28)
 #define AMD_CG_SUPPORT_ATHUB_MGCG		(1 << 29)
+#define AMD_CG_SUPPORT_JPEG_MGCG		(1 << 30)
 /* PG flags */
 #define AMD_PG_SUPPORT_GFX_PG			(1 << 0)
 #define AMD_PG_SUPPORT_GFX_SMG			(1 << 1)
@@ -117,6 +119,7 @@ enum amd_powergating_state {
 #define AMD_PG_SUPPORT_VCN			(1 << 14)
 #define AMD_PG_SUPPORT_VCN_DPG			(1 << 15)
 #define AMD_PG_SUPPORT_ATHUB			(1 << 16)
+#define AMD_PG_SUPPORT_JPEG			(1 << 17)
 
 enum PP_FEATURE_MASK {
 	PP_SCLK_DPM_MASK = 0x1,
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h
index cff8f91555d3..e9b2bd84cfed 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_offset.h
@@ -8134,6 +8134,10 @@
 #define mmMPC_OUT5_CSC_C33_C34_B                                                                       0x1604
 #define mmMPC_OUT5_CSC_C33_C34_B_BASE_IDX                                                              2
 
+#define mmMPC_OCSC_TEST_DEBUG_INDEX                                                                    0x163b
+#define mmMPC_OCSC_TEST_DEBUG_INDEX_BASE_IDX                                                           2
+#define mmMPC_OCSC_TEST_DEBUG_DATA_BASE_IDX                                                            2
+#define mmMPC_OCSC_TEST_DEBUG_DATA                                                                     0x163c
 
 // addressBlock: dce_dc_mpc_mpc_dcperfmon_dc_perfmon_dispdec
 // base address: 0x5964
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h
index 10c83fecd147..dc8ce7aaa0cf 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_0_0_sh_mask.h
@@ -28263,7 +28263,14 @@
 #define MPC_OUT5_CSC_C33_C34_B__MPC_OCSC_C34_B__SHIFT                                                         0x10
 #define MPC_OUT5_CSC_C33_C34_B__MPC_OCSC_C33_B_MASK                                                           0x0000FFFFL
 #define MPC_OUT5_CSC_C33_C34_B__MPC_OCSC_C34_B_MASK                                                           0xFFFF0000L
-
+//MPC_OCSC_TEST_DEBUG_INDEX
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX__SHIFT                                           0x0
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN__SHIFT                                        0x8
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX_MASK                                             0x000000FFL
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN_MASK                                          0x00000100L
+//MPC_OCSC_TEST_DEBUG_DATA
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA__SHIFT                                             0x0
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA_MASK                                               0xFFFFFFFFL
 
 // addressBlock: dce_dc_mpc_mpc_dcperfmon_dc_perfmon_dispdec
 //DC_PERFMON17_PERFCOUNTER_CNTL
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
index eddf83ec1c39..7cd0ee61c030 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
@@ -7103,7 +7103,10 @@
 #define mmMPC_OUT3_CSC_C31_C32_B_BASE_IDX                                                              2
 #define mmMPC_OUT3_CSC_C33_C34_B                                                                       0x15ea
 #define mmMPC_OUT3_CSC_C33_C34_B_BASE_IDX                                                              2
-
+#define mmMPC_OCSC_TEST_DEBUG_INDEX                                                                    0x163b
+#define mmMPC_OCSC_TEST_DEBUG_INDEX_BASE_IDX                                                           2
+#define mmMPC_OCSC_TEST_DEBUG_DATA_BASE_IDX                                                            2
+#define mmMPC_OCSC_TEST_DEBUG_DATA                                                                     0x163c
 
 // addressBlock: dce_dc_mpc_mpc_dcperfmon_dc_perfmon_dispdec
 // base address: 0x5964
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h
index faa0e76e32b4..2f780aefc722 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_sh_mask.h
@@ -56634,5 +56634,13 @@
 #define AZF0INPUTENDPOINT7_AZALIA_F0_CODEC_INPUT_PIN_CONTROL_INFOFRAME__INFOFRAME_BYTE_5_MASK                 0x00FF0000L
 #define AZF0INPUTENDPOINT7_AZALIA_F0_CODEC_INPUT_PIN_CONTROL_INFOFRAME__INFOFRAME_VALID_MASK                  0x80000000L
 
+//MPC_OCSC_TEST_DEBUG_INDEX
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX__SHIFT                                           0x0
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN__SHIFT                                        0x8
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_INDEX_MASK                                             0x000000FFL
+#define MPC_OCSC_TEST_DEBUG_INDEX__MPC_OCSC_TEST_DEBUG_WRITE_EN_MASK                                          0x00000100L
+//MPC_OCSC_TEST_DEBUG_DATA
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA__SHIFT                                             0x0
+#define MPC_OCSC_TEST_DEBUG_DATA__MPC_OCSC_TEST_DEBUG_DATA_MASK                                               0xFFFFFFFFL
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
index c2bd25589e84..87c84691b5be 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_offset.h
@@ -27,6 +27,9 @@
 #define mmDF_PIE_AON0_DfGlobalClkGater									0x00fc
 #define mmDF_PIE_AON0_DfGlobalClkGater_BASE_IDX								0
 
+#define mmDF_CS_UMC_AON0_DfGlobalCtrl									0x00fe
+#define mmDF_CS_UMC_AON0_DfGlobalCtrl_BASE_IDX								0
+
 #define mmDF_CS_UMC_AON0_DramBaseAddress0								0x0044
 #define mmDF_CS_UMC_AON0_DramBaseAddress0_BASE_IDX							0
 
@@ -38,6 +41,14 @@
 #define smnPerfMonCtlHi2					0x01d464UL
 #define smnPerfMonCtlLo3					0x01d470UL
 #define smnPerfMonCtlHi3					0x01d474UL
+#define smnPerfMonCtlLo4					0x01d880UL
+#define smnPerfMonCtlHi4					0x01d884UL
+#define smnPerfMonCtlLo5					0x01d888UL
+#define smnPerfMonCtlHi5					0x01d88cUL
+#define smnPerfMonCtlLo6					0x01d890UL
+#define smnPerfMonCtlHi6					0x01d894UL
+#define smnPerfMonCtlLo7					0x01d898UL
+#define smnPerfMonCtlHi7					0x01d89cUL
 
 #define smnPerfMonCtrLo0					0x01d448UL
 #define smnPerfMonCtrHi0					0x01d44cUL
@@ -47,6 +58,14 @@
 #define smnPerfMonCtrHi2					0x01d46cUL
 #define smnPerfMonCtrLo3					0x01d478UL
 #define smnPerfMonCtrHi3					0x01d47cUL
+#define smnPerfMonCtrLo4					0x01d790UL
+#define smnPerfMonCtrHi4					0x01d794UL
+#define smnPerfMonCtrLo5					0x01d798UL
+#define smnPerfMonCtrHi5					0x01d79cUL
+#define smnPerfMonCtrLo6					0x01d7a0UL
+#define smnPerfMonCtrHi6					0x01d7a4UL
+#define smnPerfMonCtrLo7					0x01d7a8UL
+#define smnPerfMonCtrHi7					0x01d7acUL
 
 #define smnDF_PIE_AON_FabricIndirectConfigAccessAddress3	0x1d05cUL
 #define smnDF_PIE_AON_FabricIndirectConfigAccessDataLo3		0x1d098UL
diff --git a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
index 06fac509e987..65e9f756e86e 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/df/df_3_6_sh_mask.h
@@ -33,6 +33,14 @@
 #define DF_PIE_AON0_DfGlobalClkGater__MGCGMode__SHIFT							0x0
 #define DF_PIE_AON0_DfGlobalClkGater__MGCGMode_MASK							0x0000000FL
 
+/* DF_CS_UMC_AON0_DfGlobalCtrl */
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl64K__SHIFT						0x14
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl2M__SHIFT						0x15
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl1G__SHIFT						0x16
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl64K_MASK						0x00100000L
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl2M_MASK						0x00200000L
+#define DF_CS_UMC_AON0_DfGlobalCtrl__GlbHashIntlvCtl1G_MASK						0x00400000L
+
 /* DF_CS_AON0_DramBaseAddress0 */
 #define DF_CS_UMC_AON0_DramBaseAddress0__AddrRngVal__SHIFT						0x0
 #define DF_CS_UMC_AON0_DramBaseAddress0__LgcyMmioHoleEn__SHIFT						0x1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_offset.h
new file mode 100644
index 000000000000..36ae5b7fe88e
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_offset.h
@@ -0,0 +1,647 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _dpcs_2_0_0_OFFSET_HEADER
+#define _dpcs_2_0_0_OFFSET_HEADER
+
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx0_dispdec
+// base address: 0x0
+#define mmDPCSTX0_DPCSTX_TX_CLOCK_CNTL                                                                 0x2928
+#define mmDPCSTX0_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX0_DPCSTX_TX_CNTL                                                                       0x2929
+#define mmDPCSTX0_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX0_DPCSTX_CBUS_CNTL                                                                     0x292a
+#define mmDPCSTX0_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX0_DPCSTX_INTERRUPT_CNTL                                                                0x292b
+#define mmDPCSTX0_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_ADDR                                                               0x292c
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_DATA                                                               0x292d
+#define mmDPCSTX0_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX0_DPCSTX_DEBUG_CONFIG                                                                  0x292e
+#define mmDPCSTX0_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx0_dispdec
+// base address: 0x0
+#define mmRDPCSTX0_RDPCSTX_CNTL                                                                        0x2930
+#define mmRDPCSTX0_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX0_RDPCSTX_CLOCK_CNTL                                                                  0x2931
+#define mmRDPCSTX0_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_INTERRUPT_CONTROL                                                           0x2932
+#define mmRDPCSTX0_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX0_RDPCSTX_PLL_UPDATE_DATA                                                             0x2933
+#define mmRDPCSTX0_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX0_RDPCS_TX_CR_ADDR                                                                    0x2934
+#define mmRDPCSTX0_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX0_RDPCS_TX_CR_DATA                                                                    0x2935
+#define mmRDPCSTX0_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX0_RDPCS_TX_SRAM_CNTL                                                                  0x2936
+#define mmRDPCSTX0_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL                                                              0x2937
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL2                                                             0x2938
+#define mmRDPCSTX0_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX0_RDPCSTX_SCRATCH                                                                     0x2939
+#define mmRDPCSTX0_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x293c
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX0_RDPCSTX_DEBUG_CONFIG                                                                0x293d
+#define mmRDPCSTX0_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL0                                                                   0x2940
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL1                                                                   0x2941
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL2                                                                   0x2942
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL3                                                                   0x2943
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL4                                                                   0x2944
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL5                                                                   0x2945
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL6                                                                   0x2946
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL7                                                                   0x2947
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL8                                                                   0x2948
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL9                                                                   0x2949
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL10                                                                  0x294a
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL11                                                                  0x294b
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL12                                                                  0x294c
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL13                                                                  0x294d
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL14                                                                  0x294e
+#define mmRDPCSTX0_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE0                                                                   0x294f
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE1                                                                   0x2950
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE2                                                                   0x2951
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE3                                                                   0x2952
+#define mmRDPCSTX0_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX0_RDPCSTX_PHY_RX_LD_VAL                                                               0x2953
+#define mmRDPCSTX0_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2954
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2955
+#define mmRDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX0_RDPCSTX_DPALT_CONTROL_REG                                                           0x2956
+#define mmRDPCSTX0_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr0_dispdec
+// base address: 0x0
+#define mmDPCSSYS_CR0_DPCSSYS_CR_ADDR                                                                  0x2934
+#define mmDPCSSYS_CR0_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR0_DPCSSYS_CR_DATA                                                                  0x2935
+#define mmDPCSSYS_CR0_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx1_dispdec
+// base address: 0x360
+#define mmDPCSTX1_DPCSTX_TX_CLOCK_CNTL                                                                 0x2a00
+#define mmDPCSTX1_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX1_DPCSTX_TX_CNTL                                                                       0x2a01
+#define mmDPCSTX1_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX1_DPCSTX_CBUS_CNTL                                                                     0x2a02
+#define mmDPCSTX1_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX1_DPCSTX_INTERRUPT_CNTL                                                                0x2a03
+#define mmDPCSTX1_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_ADDR                                                               0x2a04
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_DATA                                                               0x2a05
+#define mmDPCSTX1_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX1_DPCSTX_DEBUG_CONFIG                                                                  0x2a06
+#define mmDPCSTX1_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx1_dispdec
+// base address: 0x360
+#define mmRDPCSTX1_RDPCSTX_CNTL                                                                        0x2a08
+#define mmRDPCSTX1_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX1_RDPCSTX_CLOCK_CNTL                                                                  0x2a09
+#define mmRDPCSTX1_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_INTERRUPT_CONTROL                                                           0x2a0a
+#define mmRDPCSTX1_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX1_RDPCSTX_PLL_UPDATE_DATA                                                             0x2a0b
+#define mmRDPCSTX1_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX1_RDPCS_TX_CR_ADDR                                                                    0x2a0c
+#define mmRDPCSTX1_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX1_RDPCS_TX_CR_DATA                                                                    0x2a0d
+#define mmRDPCSTX1_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX1_RDPCS_TX_SRAM_CNTL                                                                  0x2a0e
+#define mmRDPCSTX1_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL                                                              0x2a0f
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL2                                                             0x2a10
+#define mmRDPCSTX1_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX1_RDPCSTX_SCRATCH                                                                     0x2a11
+#define mmRDPCSTX1_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2a14
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX1_RDPCSTX_DEBUG_CONFIG                                                                0x2a15
+#define mmRDPCSTX1_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL0                                                                   0x2a18
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL1                                                                   0x2a19
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL2                                                                   0x2a1a
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL3                                                                   0x2a1b
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL4                                                                   0x2a1c
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL5                                                                   0x2a1d
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL6                                                                   0x2a1e
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL7                                                                   0x2a1f
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL8                                                                   0x2a20
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL9                                                                   0x2a21
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL10                                                                  0x2a22
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL11                                                                  0x2a23
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL12                                                                  0x2a24
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL13                                                                  0x2a25
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL14                                                                  0x2a26
+#define mmRDPCSTX1_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE0                                                                   0x2a27
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE1                                                                   0x2a28
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE2                                                                   0x2a29
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE3                                                                   0x2a2a
+#define mmRDPCSTX1_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX1_RDPCSTX_PHY_RX_LD_VAL                                                               0x2a2b
+#define mmRDPCSTX1_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2a2c
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2a2d
+#define mmRDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX1_RDPCSTX_DPALT_CONTROL_REG                                                           0x2a2e
+#define mmRDPCSTX1_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr1_dispdec
+// base address: 0x360
+#define mmDPCSSYS_CR1_DPCSSYS_CR_ADDR                                                                  0x2a0c
+#define mmDPCSSYS_CR1_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR1_DPCSSYS_CR_DATA                                                                  0x2a0d
+#define mmDPCSSYS_CR1_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx2_dispdec
+// base address: 0x6c0
+#define mmDPCSTX2_DPCSTX_TX_CLOCK_CNTL                                                                 0x2ad8
+#define mmDPCSTX2_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX2_DPCSTX_TX_CNTL                                                                       0x2ad9
+#define mmDPCSTX2_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX2_DPCSTX_CBUS_CNTL                                                                     0x2ada
+#define mmDPCSTX2_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX2_DPCSTX_INTERRUPT_CNTL                                                                0x2adb
+#define mmDPCSTX2_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_ADDR                                                               0x2adc
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_DATA                                                               0x2add
+#define mmDPCSTX2_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX2_DPCSTX_DEBUG_CONFIG                                                                  0x2ade
+#define mmDPCSTX2_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx2_dispdec
+// base address: 0x6c0
+#define mmRDPCSTX2_RDPCSTX_CNTL                                                                        0x2ae0
+#define mmRDPCSTX2_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX2_RDPCSTX_CLOCK_CNTL                                                                  0x2ae1
+#define mmRDPCSTX2_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_INTERRUPT_CONTROL                                                           0x2ae2
+#define mmRDPCSTX2_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX2_RDPCSTX_PLL_UPDATE_DATA                                                             0x2ae3
+#define mmRDPCSTX2_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX2_RDPCS_TX_CR_ADDR                                                                    0x2ae4
+#define mmRDPCSTX2_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX2_RDPCS_TX_CR_DATA                                                                    0x2ae5
+#define mmRDPCSTX2_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX2_RDPCS_TX_SRAM_CNTL                                                                  0x2ae6
+#define mmRDPCSTX2_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL                                                              0x2ae7
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL2                                                             0x2ae8
+#define mmRDPCSTX2_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX2_RDPCSTX_SCRATCH                                                                     0x2ae9
+#define mmRDPCSTX2_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2aec
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX2_RDPCSTX_DEBUG_CONFIG                                                                0x2aed
+#define mmRDPCSTX2_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL0                                                                   0x2af0
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL1                                                                   0x2af1
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL2                                                                   0x2af2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL3                                                                   0x2af3
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL4                                                                   0x2af4
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL5                                                                   0x2af5
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL6                                                                   0x2af6
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL7                                                                   0x2af7
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL8                                                                   0x2af8
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL9                                                                   0x2af9
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL10                                                                  0x2afa
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL11                                                                  0x2afb
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL12                                                                  0x2afc
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL13                                                                  0x2afd
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL14                                                                  0x2afe
+#define mmRDPCSTX2_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE0                                                                   0x2aff
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE1                                                                   0x2b00
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE2                                                                   0x2b01
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE3                                                                   0x2b02
+#define mmRDPCSTX2_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX2_RDPCSTX_PHY_RX_LD_VAL                                                               0x2b03
+#define mmRDPCSTX2_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2b04
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2b05
+#define mmRDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX2_RDPCSTX_DPALT_CONTROL_REG                                                           0x2b06
+#define mmRDPCSTX2_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr2_dispdec
+// base address: 0x6c0
+#define mmDPCSSYS_CR2_DPCSSYS_CR_ADDR                                                                  0x2ae4
+#define mmDPCSSYS_CR2_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR2_DPCSSYS_CR_DATA                                                                  0x2ae5
+#define mmDPCSSYS_CR2_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx3_dispdec
+// base address: 0xa20
+#define mmDPCSTX3_DPCSTX_TX_CLOCK_CNTL                                                                 0x2bb0
+#define mmDPCSTX3_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX3_DPCSTX_TX_CNTL                                                                       0x2bb1
+#define mmDPCSTX3_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX3_DPCSTX_CBUS_CNTL                                                                     0x2bb2
+#define mmDPCSTX3_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX3_DPCSTX_INTERRUPT_CNTL                                                                0x2bb3
+#define mmDPCSTX3_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_ADDR                                                               0x2bb4
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_DATA                                                               0x2bb5
+#define mmDPCSTX3_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX3_DPCSTX_DEBUG_CONFIG                                                                  0x2bb6
+#define mmDPCSTX3_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx3_dispdec
+// base address: 0xa20
+#define mmRDPCSTX3_RDPCSTX_CNTL                                                                        0x2bb8
+#define mmRDPCSTX3_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX3_RDPCSTX_CLOCK_CNTL                                                                  0x2bb9
+#define mmRDPCSTX3_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_INTERRUPT_CONTROL                                                           0x2bba
+#define mmRDPCSTX3_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX3_RDPCSTX_PLL_UPDATE_DATA                                                             0x2bbb
+#define mmRDPCSTX3_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX3_RDPCS_TX_CR_ADDR                                                                    0x2bbc
+#define mmRDPCSTX3_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX3_RDPCS_TX_CR_DATA                                                                    0x2bbd
+#define mmRDPCSTX3_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX3_RDPCS_TX_SRAM_CNTL                                                                  0x2bbe
+#define mmRDPCSTX3_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL                                                              0x2bbf
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL2                                                             0x2bc0
+#define mmRDPCSTX3_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX3_RDPCSTX_SCRATCH                                                                     0x2bc1
+#define mmRDPCSTX3_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2bc4
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX3_RDPCSTX_DEBUG_CONFIG                                                                0x2bc5
+#define mmRDPCSTX3_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL0                                                                   0x2bc8
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL1                                                                   0x2bc9
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL2                                                                   0x2bca
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL3                                                                   0x2bcb
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL4                                                                   0x2bcc
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL5                                                                   0x2bcd
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL6                                                                   0x2bce
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL7                                                                   0x2bcf
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL8                                                                   0x2bd0
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL9                                                                   0x2bd1
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL10                                                                  0x2bd2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL11                                                                  0x2bd3
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL12                                                                  0x2bd4
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL13                                                                  0x2bd5
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL14                                                                  0x2bd6
+#define mmRDPCSTX3_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE0                                                                   0x2bd7
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE1                                                                   0x2bd8
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE2                                                                   0x2bd9
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE3                                                                   0x2bda
+#define mmRDPCSTX3_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX3_RDPCSTX_PHY_RX_LD_VAL                                                               0x2bdb
+#define mmRDPCSTX3_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2bdc
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2bdd
+#define mmRDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX3_RDPCSTX_DPALT_CONTROL_REG                                                           0x2bde
+#define mmRDPCSTX3_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr3_dispdec
+// base address: 0xa20
+#define mmDPCSSYS_CR3_DPCSSYS_CR_ADDR                                                                  0x2bbc
+#define mmDPCSSYS_CR3_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR3_DPCSSYS_CR_DATA                                                                  0x2bbd
+#define mmDPCSSYS_CR3_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcsrx_dispdec
+// base address: 0x0
+#define mmDPCSRX_PHY_CNTL                                                                              0x2c76
+#define mmDPCSRX_PHY_CNTL_BASE_IDX                                                                     2
+#define mmDPCSRX_RX_CLOCK_CNTL                                                                         0x2c78
+#define mmDPCSRX_RX_CLOCK_CNTL_BASE_IDX                                                                2
+#define mmDPCSRX_RX_CNTL                                                                               0x2c7a
+#define mmDPCSRX_RX_CNTL_BASE_IDX                                                                      2
+#define mmDPCSRX_CBUS_CNTL                                                                             0x2c7b
+#define mmDPCSRX_CBUS_CNTL_BASE_IDX                                                                    2
+#define mmDPCSRX_REG_ERROR_STATUS                                                                      0x2c7c
+#define mmDPCSRX_REG_ERROR_STATUS_BASE_IDX                                                             2
+#define mmDPCSRX_RX_ERROR_STATUS                                                                       0x2c7d
+#define mmDPCSRX_RX_ERROR_STATUS_BASE_IDX                                                              2
+#define mmDPCSRX_INDEX_MODE_ADDR                                                                       0x2c80
+#define mmDPCSRX_INDEX_MODE_ADDR_BASE_IDX                                                              2
+#define mmDPCSRX_INDEX_MODE_DATA                                                                       0x2c81
+#define mmDPCSRX_INDEX_MODE_DATA_BASE_IDX                                                              2
+#define mmDPCSRX_DEBUG_CONFIG                                                                          0x2c82
+#define mmDPCSRX_DEBUG_CONFIG_BASE_IDX                                                                 2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx4_dispdec
+// base address: 0xd80
+#define mmDPCSTX4_DPCSTX_TX_CLOCK_CNTL                                                                 0x2c88
+#define mmDPCSTX4_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX4_DPCSTX_TX_CNTL                                                                       0x2c89
+#define mmDPCSTX4_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX4_DPCSTX_CBUS_CNTL                                                                     0x2c8a
+#define mmDPCSTX4_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX4_DPCSTX_INTERRUPT_CNTL                                                                0x2c8b
+#define mmDPCSTX4_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_ADDR                                                               0x2c8c
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_DATA                                                               0x2c8d
+#define mmDPCSTX4_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX4_DPCSTX_DEBUG_CONFIG                                                                  0x2c8e
+#define mmDPCSTX4_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx4_dispdec
+// base address: 0xd80
+#define mmRDPCSTX4_RDPCSTX_CNTL                                                                        0x2c90
+#define mmRDPCSTX4_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX4_RDPCSTX_CLOCK_CNTL                                                                  0x2c91
+#define mmRDPCSTX4_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_INTERRUPT_CONTROL                                                           0x2c92
+#define mmRDPCSTX4_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX4_RDPCSTX_PLL_UPDATE_DATA                                                             0x2c93
+#define mmRDPCSTX4_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX4_RDPCS_TX_CR_ADDR                                                                    0x2c94
+#define mmRDPCSTX4_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX4_RDPCS_TX_CR_DATA                                                                    0x2c95
+#define mmRDPCSTX4_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX4_RDPCS_TX_SRAM_CNTL                                                                  0x2c96
+#define mmRDPCSTX4_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL                                                              0x2c97
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL2                                                             0x2c98
+#define mmRDPCSTX4_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX4_RDPCSTX_SCRATCH                                                                     0x2c99
+#define mmRDPCSTX4_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2c9c
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX4_RDPCSTX_DEBUG_CONFIG                                                                0x2c9d
+#define mmRDPCSTX4_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL0                                                                   0x2ca0
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL1                                                                   0x2ca1
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL2                                                                   0x2ca2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL3                                                                   0x2ca3
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL4                                                                   0x2ca4
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL5                                                                   0x2ca5
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL6                                                                   0x2ca6
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL7                                                                   0x2ca7
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL8                                                                   0x2ca8
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL9                                                                   0x2ca9
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL10                                                                  0x2caa
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL11                                                                  0x2cab
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL12                                                                  0x2cac
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL13                                                                  0x2cad
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL14                                                                  0x2cae
+#define mmRDPCSTX4_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE0                                                                   0x2caf
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE1                                                                   0x2cb0
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE2                                                                   0x2cb1
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE3                                                                   0x2cb2
+#define mmRDPCSTX4_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX4_RDPCSTX_PHY_RX_LD_VAL                                                               0x2cb3
+#define mmRDPCSTX4_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2cb4
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2cb5
+#define mmRDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX4_RDPCSTX_DPALT_CONTROL_REG                                                           0x2cb6
+#define mmRDPCSTX4_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr4_dispdec
+// base address: 0xd80
+#define mmDPCSSYS_CR4_DPCSSYS_CR_ADDR                                                                  0x2c94
+#define mmDPCSSYS_CR4_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR4_DPCSSYS_CR_DATA                                                                  0x2c95
+#define mmDPCSSYS_CR4_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx5_dispdec
+// base address: 0x10e0
+#define mmDPCSTX5_DPCSTX_TX_CLOCK_CNTL                                                                 0x2d60
+#define mmDPCSTX5_DPCSTX_TX_CLOCK_CNTL_BASE_IDX                                                        2
+#define mmDPCSTX5_DPCSTX_TX_CNTL                                                                       0x2d61
+#define mmDPCSTX5_DPCSTX_TX_CNTL_BASE_IDX                                                              2
+#define mmDPCSTX5_DPCSTX_CBUS_CNTL                                                                     0x2d62
+#define mmDPCSTX5_DPCSTX_CBUS_CNTL_BASE_IDX                                                            2
+#define mmDPCSTX5_DPCSTX_INTERRUPT_CNTL                                                                0x2d63
+#define mmDPCSTX5_DPCSTX_INTERRUPT_CNTL_BASE_IDX                                                       2
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_ADDR                                                               0x2d64
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_ADDR_BASE_IDX                                                      2
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_DATA                                                               0x2d65
+#define mmDPCSTX5_DPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                      2
+#define mmDPCSTX5_DPCSTX_DEBUG_CONFIG                                                                  0x2d66
+#define mmDPCSTX5_DPCSTX_DEBUG_CONFIG_BASE_IDX                                                         2
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx5_dispdec
+// base address: 0x10e0
+#define mmRDPCSTX5_RDPCSTX_CNTL                                                                        0x2d68
+#define mmRDPCSTX5_RDPCSTX_CNTL_BASE_IDX                                                               2
+#define mmRDPCSTX5_RDPCSTX_CLOCK_CNTL                                                                  0x2d69
+#define mmRDPCSTX5_RDPCSTX_CLOCK_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_INTERRUPT_CONTROL                                                           0x2d6a
+#define mmRDPCSTX5_RDPCSTX_INTERRUPT_CONTROL_BASE_IDX                                                  2
+#define mmRDPCSTX5_RDPCSTX_PLL_UPDATE_DATA                                                             0x2d6b
+#define mmRDPCSTX5_RDPCSTX_PLL_UPDATE_DATA_BASE_IDX                                                    2
+#define mmRDPCSTX5_RDPCS_TX_CR_ADDR                                                                    0x2d6c
+#define mmRDPCSTX5_RDPCS_TX_CR_ADDR_BASE_IDX                                                           2
+#define mmRDPCSTX5_RDPCS_TX_CR_DATA                                                                    0x2d6d
+#define mmRDPCSTX5_RDPCS_TX_CR_DATA_BASE_IDX                                                           2
+#define mmRDPCSTX5_RDPCS_TX_SRAM_CNTL                                                                  0x2d6e
+#define mmRDPCSTX5_RDPCS_TX_SRAM_CNTL_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL                                                              0x2d6f
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL_BASE_IDX                                                     2
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL2                                                             0x2d70
+#define mmRDPCSTX5_RDPCSTX_MEM_POWER_CTRL2_BASE_IDX                                                    2
+#define mmRDPCSTX5_RDPCSTX_SCRATCH                                                                     0x2d71
+#define mmRDPCSTX5_RDPCSTX_SCRATCH_BASE_IDX                                                            2
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG                                                    0x2d74
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG_BASE_IDX                                           2
+#define mmRDPCSTX5_RDPCSTX_DEBUG_CONFIG                                                                0x2d75
+#define mmRDPCSTX5_RDPCSTX_DEBUG_CONFIG_BASE_IDX                                                       2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL0                                                                   0x2d78
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL0_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL1                                                                   0x2d79
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL1_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL2                                                                   0x2d7a
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL2_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL3                                                                   0x2d7b
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL3_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL4                                                                   0x2d7c
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL4_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL5                                                                   0x2d7d
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL5_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL6                                                                   0x2d7e
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL6_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL7                                                                   0x2d7f
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL7_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL8                                                                   0x2d80
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL8_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL9                                                                   0x2d81
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL9_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL10                                                                  0x2d82
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL10_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL11                                                                  0x2d83
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL11_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL12                                                                  0x2d84
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL12_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL13                                                                  0x2d85
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL13_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL14                                                                  0x2d86
+#define mmRDPCSTX5_RDPCSTX_PHY_CNTL14_BASE_IDX                                                         2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE0                                                                   0x2d87
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE0_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE1                                                                   0x2d88
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE1_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE2                                                                   0x2d89
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE2_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE3                                                                   0x2d8a
+#define mmRDPCSTX5_RDPCSTX_PHY_FUSE3_BASE_IDX                                                          2
+#define mmRDPCSTX5_RDPCSTX_PHY_RX_LD_VAL                                                               0x2d8b
+#define mmRDPCSTX5_RDPCSTX_PHY_RX_LD_VAL_BASE_IDX                                                      2
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3                                                        0x2d8c
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3_BASE_IDX                                               2
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6                                                        0x2d8d
+#define mmRDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6_BASE_IDX                                               2
+#define mmRDPCSTX5_RDPCSTX_DPALT_CONTROL_REG                                                           0x2d8e
+#define mmRDPCSTX5_RDPCSTX_DPALT_CONTROL_REG_BASE_IDX                                                  2
+
+
+// addressBlock: dpcssys_dpcssys_cr5_dispdec
+// base address: 0x10e0
+#define mmDPCSSYS_CR5_DPCSSYS_CR_ADDR                                                                  0x2d6c
+#define mmDPCSSYS_CR5_DPCSSYS_CR_ADDR_BASE_IDX                                                         2
+#define mmDPCSSYS_CR5_DPCSSYS_CR_DATA                                                                  0x2d6d
+#define mmDPCSSYS_CR5_DPCSSYS_CR_DATA_BASE_IDX                                                         2
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_sh_mask.h
new file mode 100644
index 000000000000..25e0569e05c8
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_0_0_sh_mask.h
@@ -0,0 +1,3912 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _dpcs_2_0_0_SH_MASK_HEADER
+#define _dpcs_2_0_0_SH_MASK_HEADER
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx0_dispdec
+//DPCSTX0_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX0_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX0_DPCSTX_TX_CNTL
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX0_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX0_DPCSTX_CBUS_CNTL
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX0_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX0_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX0_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX0_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX0_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX0_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX0_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX0_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX0_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX0_DPCSTX_DEBUG_CONFIG
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX0_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx0_dispdec
+//RDPCSTX0_RDPCSTX_CNTL
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX0_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX0_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX0_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX0_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX0_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX0_RDPCS_TX_CR_ADDR
+#define RDPCSTX0_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX0_RDPCS_TX_CR_DATA
+#define RDPCSTX0_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX0_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX0_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX0_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX0_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX0_RDPCSTX_SCRATCH
+#define RDPCSTX0_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX0_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX0_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX0_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX0_RDPCSTX_PHY_CNTL2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX0_RDPCSTX_PHY_CNTL3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL5
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX0_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX0_RDPCSTX_PHY_CNTL9
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX0_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX0_RDPCSTX_PHY_CNTL11
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL12
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX0_RDPCSTX_PHY_CNTL13
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX0_RDPCSTX_PHY_CNTL14
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX0_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE1
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE2
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX0_RDPCSTX_PHY_FUSE3
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX0_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX0_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX0_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX0_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr0_dispdec
+//DPCSSYS_CR0_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR0_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR0_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR0_DPCSSYS_CR_DATA
+#define DPCSSYS_CR0_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR0_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx1_dispdec
+//DPCSTX1_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX1_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX1_DPCSTX_TX_CNTL
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX1_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX1_DPCSTX_CBUS_CNTL
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX1_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX1_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX1_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX1_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX1_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX1_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX1_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX1_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX1_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX1_DPCSTX_DEBUG_CONFIG
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX1_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx1_dispdec
+//RDPCSTX1_RDPCSTX_CNTL
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX1_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX1_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX1_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX1_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX1_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX1_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX1_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX1_RDPCS_TX_CR_ADDR
+#define RDPCSTX1_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX1_RDPCS_TX_CR_DATA
+#define RDPCSTX1_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX1_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX1_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX1_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX1_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX1_RDPCSTX_SCRATCH
+#define RDPCSTX1_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX1_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX1_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX1_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX1_RDPCSTX_PHY_CNTL2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX1_RDPCSTX_PHY_CNTL3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL5
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX1_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX1_RDPCSTX_PHY_CNTL9
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX1_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX1_RDPCSTX_PHY_CNTL11
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL12
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX1_RDPCSTX_PHY_CNTL13
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX1_RDPCSTX_PHY_CNTL14
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX1_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE1
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE2
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX1_RDPCSTX_PHY_FUSE3
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX1_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX1_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX1_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX1_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr1_dispdec
+//DPCSSYS_CR1_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR1_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR1_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR1_DPCSSYS_CR_DATA
+#define DPCSSYS_CR1_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR1_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx2_dispdec
+//DPCSTX2_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX2_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX2_DPCSTX_TX_CNTL
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX2_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX2_DPCSTX_CBUS_CNTL
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX2_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX2_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX2_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX2_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX2_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX2_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX2_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX2_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX2_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX2_DPCSTX_DEBUG_CONFIG
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX2_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx2_dispdec
+//RDPCSTX2_RDPCSTX_CNTL
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX2_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX2_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX2_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX2_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX2_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX2_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX2_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX2_RDPCS_TX_CR_ADDR
+#define RDPCSTX2_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX2_RDPCS_TX_CR_DATA
+#define RDPCSTX2_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX2_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX2_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX2_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX2_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX2_RDPCSTX_SCRATCH
+#define RDPCSTX2_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX2_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX2_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX2_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX2_RDPCSTX_PHY_CNTL2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX2_RDPCSTX_PHY_CNTL3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL5
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX2_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX2_RDPCSTX_PHY_CNTL9
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX2_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX2_RDPCSTX_PHY_CNTL11
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL12
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX2_RDPCSTX_PHY_CNTL13
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX2_RDPCSTX_PHY_CNTL14
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX2_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE1
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE2
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX2_RDPCSTX_PHY_FUSE3
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX2_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX2_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX2_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX2_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr2_dispdec
+//DPCSSYS_CR2_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR2_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR2_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR2_DPCSSYS_CR_DATA
+#define DPCSSYS_CR2_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR2_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx3_dispdec
+//DPCSTX3_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX3_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX3_DPCSTX_TX_CNTL
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX3_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX3_DPCSTX_CBUS_CNTL
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX3_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX3_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX3_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX3_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX3_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX3_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX3_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX3_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX3_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX3_DPCSTX_DEBUG_CONFIG
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX3_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx3_dispdec
+//RDPCSTX3_RDPCSTX_CNTL
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX3_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX3_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX3_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX3_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX3_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX3_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX3_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX3_RDPCS_TX_CR_ADDR
+#define RDPCSTX3_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX3_RDPCS_TX_CR_DATA
+#define RDPCSTX3_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX3_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX3_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX3_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX3_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX3_RDPCSTX_SCRATCH
+#define RDPCSTX3_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX3_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX3_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX3_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX3_RDPCSTX_PHY_CNTL2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX3_RDPCSTX_PHY_CNTL3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL5
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX3_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX3_RDPCSTX_PHY_CNTL9
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX3_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX3_RDPCSTX_PHY_CNTL11
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL12
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX3_RDPCSTX_PHY_CNTL13
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX3_RDPCSTX_PHY_CNTL14
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX3_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE1
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE2
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX3_RDPCSTX_PHY_FUSE3
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX3_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX3_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX3_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX3_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr3_dispdec
+//DPCSSYS_CR3_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR3_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR3_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR3_DPCSSYS_CR_DATA
+#define DPCSSYS_CR3_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR3_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcsrx_dispdec
+//DPCSRX_PHY_CNTL
+#define DPCSRX_PHY_CNTL__DPCS_PHY_RESET__SHIFT                                                                0x0
+#define DPCSRX_PHY_CNTL__DPCS_PHY_RESET_MASK                                                                  0x00000001L
+//DPCSRX_RX_CLOCK_CNTL
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_GATE_DIS__SHIFT                                                  0x0
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_EN__SHIFT                                                        0x1
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_SEL__SHIFT                                                       0x2
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_CLOCK_ON__SHIFT                                                  0x4
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_GATE_DIS__SHIFT                                                 0x10
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_EN__SHIFT                                                       0x11
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_CLOCK_ON__SHIFT                                                 0x12
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_GATE_DIS__SHIFT                                                 0x14
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_EN__SHIFT                                                       0x15
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_CLOCK_ON__SHIFT                                                 0x16
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_GATE_DIS__SHIFT                                                 0x18
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_EN__SHIFT                                                       0x19
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_CLOCK_ON__SHIFT                                                 0x1a
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_GATE_DIS__SHIFT                                                 0x1c
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_EN__SHIFT                                                       0x1d
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_CLOCK_ON__SHIFT                                                 0x1e
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_GATE_DIS_MASK                                                    0x00000001L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_EN_MASK                                                          0x00000002L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_SEL_MASK                                                         0x0000000CL
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX_CLOCK_ON_MASK                                                    0x00000010L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_GATE_DIS_MASK                                                   0x00010000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_EN_MASK                                                         0x00020000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX0_CLOCK_ON_MASK                                                   0x00040000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_GATE_DIS_MASK                                                   0x00100000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_EN_MASK                                                         0x00200000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX1_CLOCK_ON_MASK                                                   0x00400000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_GATE_DIS_MASK                                                   0x01000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_EN_MASK                                                         0x02000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX2_CLOCK_ON_MASK                                                   0x04000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_GATE_DIS_MASK                                                   0x10000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_EN_MASK                                                         0x20000000L
+#define DPCSRX_RX_CLOCK_CNTL__DPCS_SYMCLK_RX3_CLOCK_ON_MASK                                                   0x40000000L
+//DPCSRX_RX_CNTL
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE0_EN__SHIFT                                                               0x0
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE1_EN__SHIFT                                                               0x1
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE2_EN__SHIFT                                                               0x2
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE3_EN__SHIFT                                                               0x3
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_EN__SHIFT                                                                0x4
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_START__SHIFT                                                             0x5
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_RD_START_DELAY__SHIFT                                                    0x8
+#define DPCSRX_RX_CNTL__DPCS_RX_SOFT_RESET__SHIFT                                                             0x1f
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE0_EN_MASK                                                                 0x00000001L
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE1_EN_MASK                                                                 0x00000002L
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE2_EN_MASK                                                                 0x00000004L
+#define DPCSRX_RX_CNTL__DPCS_RX_LANE3_EN_MASK                                                                 0x00000008L
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_EN_MASK                                                                  0x00000010L
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_START_MASK                                                               0x00000020L
+#define DPCSRX_RX_CNTL__DPCS_RX_FIFO_RD_START_DELAY_MASK                                                      0x00000F00L
+#define DPCSRX_RX_CNTL__DPCS_RX_SOFT_RESET_MASK                                                               0x80000000L
+//DPCSRX_CBUS_CNTL
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                                       0x0
+#define DPCSRX_CBUS_CNTL__DPCS_PHY_MASTER_REQ_DELAY__SHIFT                                                    0x8
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                         0x1f
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                         0x0000000FL
+#define DPCSRX_CBUS_CNTL__DPCS_PHY_MASTER_REQ_DELAY_MASK                                                      0x0000FF00L
+#define DPCSRX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                           0x80000000L
+//DPCSRX_REG_ERROR_STATUS
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_OVERFLOW__SHIFT                                                0x0
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_ERROR_CLR__SHIFT                                                    0x1
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                              0x4
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_OVERFLOW_MASK                                                  0x00000001L
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_ERROR_CLR_MASK                                                      0x00000002L
+#define DPCSRX_REG_ERROR_STATUS__DPCS_REG_FIFO_ERROR_MASK_MASK                                                0x00000010L
+//DPCSRX_RX_ERROR_STATUS
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX0_FIFO_ERROR__SHIFT                                                    0x0
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX1_FIFO_ERROR__SHIFT                                                    0x1
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX2_FIFO_ERROR__SHIFT                                                    0x2
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX3_FIFO_ERROR__SHIFT                                                    0x3
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_ERROR_CLR__SHIFT                                                      0x8
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_FIFO_ERROR_MASK__SHIFT                                                0xc
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX0_FIFO_ERROR_MASK                                                      0x00000001L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX1_FIFO_ERROR_MASK                                                      0x00000002L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX2_FIFO_ERROR_MASK                                                      0x00000004L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX3_FIFO_ERROR_MASK                                                      0x00000008L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_ERROR_CLR_MASK                                                        0x00000100L
+#define DPCSRX_RX_ERROR_STATUS__DPCS_RX_FIFO_ERROR_MASK_MASK                                                  0x00001000L
+//DPCSRX_INDEX_MODE_ADDR
+#define DPCSRX_INDEX_MODE_ADDR__DPCS_INDEX_MODE_ADDR__SHIFT                                                   0x0
+#define DPCSRX_INDEX_MODE_ADDR__DPCS_INDEX_MODE_ADDR_MASK                                                     0x0003FFFFL
+//DPCSRX_INDEX_MODE_DATA
+#define DPCSRX_INDEX_MODE_DATA__DPCS_INDEX_MODE_DATA__SHIFT                                                   0x0
+#define DPCSRX_INDEX_MODE_DATA__DPCS_INDEX_MODE_DATA_MASK                                                     0xFFFFFFFFL
+//DPCSRX_DEBUG_CONFIG
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                               0x0
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                                       0x1
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_RX_SYMCLK_SEL__SHIFT                                                    0x6
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_BLOCK_SEL__SHIFT                                                        0xb
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                         0xe
+#define DPCSRX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                                  0x10
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                                 0x00000001L
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                         0x0000000EL
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_RX_SYMCLK_SEL_MASK                                                      0x000000C0L
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_BLOCK_SEL_MASK                                                          0x00003800L
+#define DPCSRX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                           0x00004000L
+#define DPCSRX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                                    0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx4_dispdec
+//DPCSTX4_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX4_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX4_DPCSTX_TX_CNTL
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX4_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX4_DPCSTX_CBUS_CNTL
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX4_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX4_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX4_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX4_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX4_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX4_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX4_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX4_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX4_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX4_DPCSTX_DEBUG_CONFIG
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX4_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx4_dispdec
+//RDPCSTX4_RDPCSTX_CNTL
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX4_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX4_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX4_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX4_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX4_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX4_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX4_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX4_RDPCS_TX_CR_ADDR
+#define RDPCSTX4_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX4_RDPCS_TX_CR_DATA
+#define RDPCSTX4_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX4_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX4_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX4_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX4_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX4_RDPCSTX_SCRATCH
+#define RDPCSTX4_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX4_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX4_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX4_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX4_RDPCSTX_PHY_CNTL2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX4_RDPCSTX_PHY_CNTL3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL5
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX4_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX4_RDPCSTX_PHY_CNTL9
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX4_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX4_RDPCSTX_PHY_CNTL11
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL12
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX4_RDPCSTX_PHY_CNTL13
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX4_RDPCSTX_PHY_CNTL14
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX4_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE1
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE2
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX4_RDPCSTX_PHY_FUSE3
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX4_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX4_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX4_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX4_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr4_dispdec
+//DPCSSYS_CR4_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR4_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR4_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR4_DPCSSYS_CR_DATA
+#define DPCSSYS_CR4_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR4_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+
+// addressBlock: dpcssys_dpcs0_dpcstx5_dispdec
+//DPCSTX5_DPCSTX_TX_CLOCK_CNTL
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS__SHIFT                                             0x0
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN__SHIFT                                                   0x1
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON__SHIFT                                             0x2
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0x3
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_GATE_DIS_MASK                                               0x00000001L
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_EN_MASK                                                     0x00000002L
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_CLOCK_ON_MASK                                               0x00000004L
+#define DPCSTX5_DPCSTX_TX_CLOCK_CNTL__DPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000008L
+//DPCSTX5_DPCSTX_TX_CNTL
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ__SHIFT                                                 0xc
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING__SHIFT                                             0xd
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP__SHIFT                                                      0xe
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT__SHIFT                                              0xf
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_REQ_MASK                                                   0x00001000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_PLL_UPDATE_PENDING_MASK                                               0x00002000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_SWAP_MASK                                                        0x00004000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_DATA_ORDER_INVERT_MASK                                                0x00008000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define DPCSTX5_DPCSTX_TX_CNTL__DPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//DPCSTX5_DPCSTX_CBUS_CNTL
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY__SHIFT                                               0x0
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET__SHIFT                                                 0x1f
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_WR_CMD_DELAY_MASK                                                 0x000000FFL
+#define DPCSTX5_DPCSTX_CBUS_CNTL__DPCS_CBUS_SOFT_RESET_MASK                                                   0x80000000L
+//DPCSTX5_DPCSTX_INTERRUPT_CNTL
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW__SHIFT                                          0x0
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR__SHIFT                                              0x1
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK__SHIFT                                        0x4
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR__SHIFT                                             0x8
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR__SHIFT                                             0x9
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR__SHIFT                                             0xa
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR__SHIFT                                             0xb
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR__SHIFT                                               0xc
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK__SHIFT                                         0x10
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK__SHIFT                                             0x14
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_OVERFLOW_MASK                                            0x00000001L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_ERROR_CLR_MASK                                                0x00000002L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_REG_FIFO_ERROR_MASK_MASK                                          0x00000010L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX0_FIFO_ERROR_MASK                                               0x00000100L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX1_FIFO_ERROR_MASK                                               0x00000200L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX2_FIFO_ERROR_MASK                                               0x00000400L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX3_FIFO_ERROR_MASK                                               0x00000800L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_ERROR_CLR_MASK                                                 0x00001000L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_TX_FIFO_ERROR_MASK_MASK                                           0x00010000L
+#define DPCSTX5_DPCSTX_INTERRUPT_CNTL__DPCS_INTERRUPT_MASK_MASK                                               0x00100000L
+//DPCSTX5_DPCSTX_PLL_UPDATE_ADDR
+#define DPCSTX5_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR__SHIFT                                           0x0
+#define DPCSTX5_DPCSTX_PLL_UPDATE_ADDR__DPCS_PLL_UPDATE_ADDR_MASK                                             0x0003FFFFL
+//DPCSTX5_DPCSTX_PLL_UPDATE_DATA
+#define DPCSTX5_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA__SHIFT                                           0x0
+#define DPCSTX5_DPCSTX_PLL_UPDATE_DATA__DPCS_PLL_UPDATE_DATA_MASK                                             0xFFFFFFFFL
+//DPCSTX5_DPCSTX_DEBUG_CONFIG
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN__SHIFT                                                       0x0
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL__SHIFT                                               0x1
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL__SHIFT                                            0x4
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL__SHIFT                                       0x8
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS__SHIFT                                                 0xe
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN__SHIFT                                          0x10
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_EN_MASK                                                         0x00000001L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CFGCLK_SEL_MASK                                                 0x0000000EL
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_SEL_MASK                                              0x00000070L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_TX_SYMCLK_DIV2_SEL_MASK                                         0x00000700L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_DBG_CBUS_DIS_MASK                                                   0x00004000L
+#define DPCSTX5_DPCSTX_DEBUG_CONFIG__DPCS_TEST_DEBUG_WRITE_EN_MASK                                            0x00010000L
+
+
+// addressBlock: dpcssys_dpcs0_rdpcstx5_dispdec
+//RDPCSTX5_RDPCSTX_CNTL
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET__SHIFT                                                   0x0
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET__SHIFT                                                   0x4
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN__SHIFT                                                  0xc
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN__SHIFT                                                  0xd
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN__SHIFT                                                  0xe
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN__SHIFT                                                  0xf
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN__SHIFT                                                        0x10
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_START__SHIFT                                                     0x11
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY__SHIFT                                            0x14
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN__SHIFT                                              0x18
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN__SHIFT                                       0x19
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS__SHIFT                                                0x1a
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET__SHIFT                                                     0x1f
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CBUS_SOFT_RESET_MASK                                                     0x00000001L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_SRAM_SOFT_RESET_MASK                                                     0x00000010L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE0_EN_MASK                                                    0x00001000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE1_EN_MASK                                                    0x00002000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE2_EN_MASK                                                    0x00004000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_LANE3_EN_MASK                                                    0x00008000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_EN_MASK                                                          0x00010000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_START_MASK                                                       0x00020000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_FIFO_RD_START_DELAY_MASK                                              0x00F00000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_CR_REGISTER_BLOCK_EN_MASK                                                0x01000000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_NON_DPALT_REGISTER_BLOCK_EN_MASK                                         0x02000000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_DPALT_BLOCK_STATUS_MASK                                                  0x04000000L
+#define RDPCSTX5_RDPCSTX_CNTL__RDPCS_TX_SOFT_RESET_MASK                                                       0x80000000L
+//RDPCSTX5_RDPCSTX_CLOCK_CNTL
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN__SHIFT                                               0x0
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN__SHIFT                                          0x4
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN__SHIFT                                          0x5
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN__SHIFT                                          0x6
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN__SHIFT                                          0x7
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS__SHIFT                                        0x8
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN__SHIFT                                              0x9
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON__SHIFT                                        0xa
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS__SHIFT                                            0xc
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN__SHIFT                                                  0xd
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON__SHIFT                                            0xe
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS__SHIFT                                              0x10
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_EXT_REFCLK_EN_MASK                                                 0x00000001L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX0_EN_MASK                                            0x00000010L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX1_EN_MASK                                            0x00000020L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX2_EN_MASK                                            0x00000040L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_TX3_EN_MASK                                            0x00000080L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_GATE_DIS_MASK                                          0x00000100L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_EN_MASK                                                0x00000200L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SYMCLK_DIV2_CLOCK_ON_MASK                                          0x00000400L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_GATE_DIS_MASK                                              0x00001000L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_EN_MASK                                                    0x00002000L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_CLOCK_ON_MASK                                              0x00004000L
+#define RDPCSTX5_RDPCSTX_CLOCK_CNTL__RDPCS_SRAMCLK_BYPASS_MASK                                                0x00010000L
+//RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE__SHIFT                                 0x1
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE__SHIFT                                   0x2
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR__SHIFT                                       0x4
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR__SHIFT                                       0x5
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR__SHIFT                                       0x6
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR__SHIFT                                       0x7
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR__SHIFT                                        0x8
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR__SHIFT                             0x9
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR__SHIFT                               0xa
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR__SHIFT                                         0xc
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK__SHIFT                                  0x10
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK__SHIFT                            0x11
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK__SHIFT                              0x12
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK__SHIFT                                   0x14
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_OVERFLOW_MASK                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK                                   0x00000002L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK                                     0x00000004L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX0_FIFO_ERROR_MASK                                         0x00000010L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX1_FIFO_ERROR_MASK                                         0x00000020L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX2_FIFO_ERROR_MASK                                         0x00000040L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX3_FIFO_ERROR_MASK                                         0x00000080L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_ERROR_CLR_MASK                                          0x00000100L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_CLR_MASK                               0x00000200L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_CLR_MASK                                 0x00000400L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_ERROR_CLR_MASK                                           0x00001000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_REG_FIFO_ERROR_MASK_MASK                                    0x00010000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_DISABLE_TOGGLE_MASK_MASK                              0x00020000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_DPALT_4LANE_TOGGLE_MASK_MASK                                0x00040000L
+#define RDPCSTX5_RDPCSTX_INTERRUPT_CONTROL__RDPCS_TX_FIFO_ERROR_MASK_MASK                                     0x00100000L
+//RDPCSTX5_RDPCSTX_PLL_UPDATE_DATA
+#define RDPCSTX5_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA__SHIFT                                        0x0
+#define RDPCSTX5_RDPCSTX_PLL_UPDATE_DATA__RDPCS_PLL_UPDATE_DATA_MASK                                          0x00000001L
+//RDPCSTX5_RDPCS_TX_CR_ADDR
+#define RDPCSTX5_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCS_TX_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                      0x0000FFFFL
+//RDPCSTX5_RDPCS_TX_CR_DATA
+#define RDPCSTX5_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCS_TX_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                      0x0000FFFFL
+//RDPCSTX5_RDPCS_TX_SRAM_CNTL
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS__SHIFT                                                 0x14
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE__SHIFT                                               0x18
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE__SHIFT                                           0x1c
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_DIS_MASK                                                   0x00100000L
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_FORCE_MASK                                                 0x03000000L
+#define RDPCSTX5_RDPCS_TX_SRAM_CNTL__RDPCS_MEM_PWR_PWR_STATE_MASK                                             0x30000000L
+//RDPCSTX5_RDPCSTX_MEM_POWER_CTRL
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES__SHIFT                                    0xc
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1__SHIFT                                  0x1a
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2__SHIFT                                  0x1b
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1__SHIFT                                   0x1c
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2__SHIFT                                   0x1d
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM__SHIFT                                         0x1e
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_RM_FUSES_MASK                                             0x00000FFFL
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_FUSE_CUSTOM_RM_FUSES_MASK                                      0x03FFF000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC1_MASK                                    0x04000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_PDP_BC2_MASK                                    0x08000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC1_MASK                                     0x10000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_MEM_POWER_CTRL_HD_BC2_MASK                                     0x20000000L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL__RDPCS_LIVMIN_DIS_SRAM_MASK                                           0x40000000L
+//RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO__SHIFT                                    0x2
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_POFF_MASK                                      0x00000003L
+#define RDPCSTX5_RDPCSTX_MEM_POWER_CTRL2__RDPCS_MEM_POWER_CTRL_FISO_MASK                                      0x00000004L
+//RDPCSTX5_RDPCSTX_SCRATCH
+#define RDPCSTX5_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH__SHIFT                                                      0x0
+#define RDPCSTX5_RDPCSTX_SCRATCH__RDPCSTX_SCRATCH_MASK                                                        0xFFFFFFFFL
+//RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG__SHIFT                      0x0
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS__SHIFT              0x4
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE__SHIFT                      0x8
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_DIS_BLOCK_REG_MASK                        0x00000001L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_FORCE_SYMCLK_DIV2_DIS_MASK                0x00000010L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_DIS_BLOCK_REG__RDPCS_DMCU_DPALT_CONTROL_SPARE_MASK                        0x0000FF00L
+//RDPCSTX5_RDPCSTX_DEBUG_CONFIG
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT__SHIFT                                        0x4
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP__SHIFT                                        0x7
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK__SHIFT                                          0x8
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE__SHIFT                                       0xf
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX__SHIFT                                          0x10
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT__SHIFT                                              0x18
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_EN_MASK                                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_8BIT_MASK                                          0x00000070L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_ASYNC_SWAP_MASK                                          0x00000080L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_SEL_TEST_CLK_MASK                                            0x00001F00L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_EXPIRE_MASK                                         0x00008000L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MAX_MASK                                            0x00FF0000L
+#define RDPCSTX5_RDPCSTX_DEBUG_CONFIG__RDPCS_DBG_CR_COUNT_MASK                                                0xFF000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET__SHIFT                                                    0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET__SHIFT                                            0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N__SHIFT                                          0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN__SHIFT                                           0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT__SHIFT                                                  0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE__SHIFT                                          0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE__SHIFT                                                0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL__SHIFT                                            0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ__SHIFT                                                0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK__SHIFT                                                0x12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL__SHIFT                                              0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL__SHIFT                                               0x15
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN__SHIFT                                            0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT__SHIFT                                        0x19
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE__SHIFT                                               0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE__SHIFT                                             0x1d
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS__SHIFT                                                  0x1f
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RESET_MASK                                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_PHY_RESET_MASK                                              0x00000002L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TCA_APB_RESET_N_MASK                                            0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TEST_POWERDOWN_MASK                                             0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_DTB_OUT_MASK                                                    0x00000030L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_HDMIMODE_ENABLE_MASK                                            0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_RANGE_MASK                                                  0x00003E00L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_TX_VBOOST_LVL_MASK                                              0x0001C000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_REQ_MASK                                                  0x00020000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_RTUNE_ACK_MASK                                                  0x00040000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_PARA_SEL_MASK                                                0x00100000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_CR_MUX_SEL_MASK                                                 0x00200000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_EN_MASK                                              0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_PHY_REF_CLKDET_RESULT_MASK                                          0x02000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_INIT_DONE_MASK                                                 0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_EXT_LD_DONE_MASK                                               0x20000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL0__RDPCS_SRAM_BYPASS_MASK                                                    0x80000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN__SHIFT                                               0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN__SHIFT                                               0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE__SHIFT                                           0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN__SHIFT                                               0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE__SHIFT                                           0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET__SHIFT                                              0x5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN__SHIFT                                               0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE__SHIFT                                           0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PG_MODE_EN_MASK                                                 0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_EN_MASK                                                 0x00000002L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PCS_PWR_STABLE_MASK                                             0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_EN_MASK                                                 0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_PMA_PWR_STABLE_MASK                                             0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_DP_PG_RESET_MASK                                                0x00000020L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_EN_MASK                                                 0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL1__RDPCS_PHY_ANA_PWR_STABLE_MASK                                             0x00000080L
+//RDPCSTX5_RDPCSTX_PHY_CNTL2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR__SHIFT                                                  0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN__SHIFT                                 0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN__SHIFT                                 0x5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN__SHIFT                                 0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN__SHIFT                                 0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN__SHIFT                                 0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN__SHIFT                                 0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN__SHIFT                                 0xa
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN__SHIFT                                 0xb
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP4_POR_MASK                                                    0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_RX2TX_PAR_LB_EN_MASK                                   0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_RX2TX_PAR_LB_EN_MASK                                   0x00000020L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_RX2TX_PAR_LB_EN_MASK                                   0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_RX2TX_PAR_LB_EN_MASK                                   0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE0_TX2RX_SER_LB_EN_MASK                                   0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE1_TX2RX_SER_LB_EN_MASK                                   0x00000200L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE2_TX2RX_SER_LB_EN_MASK                                   0x00000400L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL2__RDPCS_PHY_DP_LANE3_TX2RX_SER_LB_EN_MASK                                   0x00000800L
+//RDPCSTX5_RDPCSTX_PHY_CNTL3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET__SHIFT                                             0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE__SHIFT                                           0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY__SHIFT                                           0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN__SHIFT                                           0x3
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ__SHIFT                                               0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK__SHIFT                                               0x5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET__SHIFT                                             0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE__SHIFT                                           0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY__SHIFT                                           0xa
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN__SHIFT                                           0xb
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ__SHIFT                                               0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK__SHIFT                                               0xd
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET__SHIFT                                             0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE__SHIFT                                           0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY__SHIFT                                           0x12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN__SHIFT                                           0x13
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ__SHIFT                                               0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK__SHIFT                                               0x15
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET__SHIFT                                             0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE__SHIFT                                           0x19
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY__SHIFT                                           0x1a
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN__SHIFT                                           0x1b
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ__SHIFT                                               0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK__SHIFT                                               0x1d
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_MASK                                               0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_MASK                                             0x00000002L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_MASK                                             0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_MASK                                             0x00000008L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_MASK                                                 0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_MASK                                                 0x00000020L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_MASK                                               0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_MASK                                             0x00000200L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_MASK                                             0x00000400L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_MASK                                             0x00000800L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_MASK                                                 0x00001000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_MASK                                                 0x00002000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_MASK                                               0x00010000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_MASK                                             0x00020000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_MASK                                             0x00040000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_MASK                                             0x00080000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_MASK                                                 0x00100000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_MASK                                                 0x00200000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_MASK                                               0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_MASK                                             0x02000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_MASK                                             0x04000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_MASK                                             0x08000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_MASK                                                 0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_MASK                                                 0x20000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL__SHIFT                                         0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT__SHIFT                                            0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC__SHIFT                                    0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN__SHIFT                                        0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL__SHIFT                                         0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT__SHIFT                                            0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC__SHIFT                                    0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN__SHIFT                                        0xf
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL__SHIFT                                         0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT__SHIFT                                            0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC__SHIFT                                    0x16
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN__SHIFT                                        0x17
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL__SHIFT                                         0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT__SHIFT                                            0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC__SHIFT                                    0x1e
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN__SHIFT                                        0x1f
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_TERM_CTRL_MASK                                           0x00000007L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_INVERT_MASK                                              0x00000010L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_BYPASS_EQ_CALC_MASK                                      0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX0_HP_PROT_EN_MASK                                          0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_TERM_CTRL_MASK                                           0x00000700L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_INVERT_MASK                                              0x00001000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_BYPASS_EQ_CALC_MASK                                      0x00004000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX1_HP_PROT_EN_MASK                                          0x00008000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_TERM_CTRL_MASK                                           0x00070000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_INVERT_MASK                                              0x00100000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_BYPASS_EQ_CALC_MASK                                      0x00400000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX2_HP_PROT_EN_MASK                                          0x00800000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_TERM_CTRL_MASK                                           0x07000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_INVERT_MASK                                              0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_BYPASS_EQ_CALC_MASK                                      0x40000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL4__RDPCS_PHY_DP_TX3_HP_PROT_EN_MASK                                          0x80000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL5
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD__SHIFT                                               0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE__SHIFT                                              0x1
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH__SHIFT                                             0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ__SHIFT                                         0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT__SHIFT                                      0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD__SHIFT                                               0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE__SHIFT                                              0x9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH__SHIFT                                             0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ__SHIFT                                         0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT__SHIFT                                      0xf
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD__SHIFT                                               0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE__SHIFT                                              0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH__SHIFT                                             0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ__SHIFT                                         0x16
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT__SHIFT                                      0x17
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD__SHIFT                                               0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE__SHIFT                                              0x19
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH__SHIFT                                             0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ__SHIFT                                         0x1e
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT__SHIFT                                      0x1f
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_LPD_MASK                                                 0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_RATE_MASK                                                0x0000000EL
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_WIDTH_MASK                                               0x00000030L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_REQ_MASK                                           0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX0_DETRX_RESULT_MASK                                        0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_LPD_MASK                                                 0x00000100L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_RATE_MASK                                                0x00000E00L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_WIDTH_MASK                                               0x00003000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_REQ_MASK                                           0x00004000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX1_DETRX_RESULT_MASK                                        0x00008000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_LPD_MASK                                                 0x00010000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_RATE_MASK                                                0x000E0000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_WIDTH_MASK                                               0x00300000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_REQ_MASK                                           0x00400000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX2_DETRX_RESULT_MASK                                        0x00800000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_LPD_MASK                                                 0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_RATE_MASK                                                0x0E000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_WIDTH_MASK                                               0x30000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_REQ_MASK                                           0x40000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL5__RDPCS_PHY_DP_TX3_DETRX_RESULT_MASK                                        0x80000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE__SHIFT                                            0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN__SHIFT                                           0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE__SHIFT                                            0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN__SHIFT                                           0x6
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE__SHIFT                                            0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN__SHIFT                                           0xa
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE__SHIFT                                            0xc
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN__SHIFT                                           0xe
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4__SHIFT                                                0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE__SHIFT                                            0x11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK__SHIFT                                        0x12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN__SHIFT                                            0x13
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ__SHIFT                                           0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_MASK                                              0x00000003L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_MASK                                             0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_MASK                                              0x00000030L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_MASK                                             0x00000040L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_MASK                                              0x00000300L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_MASK                                             0x00000400L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_MASK                                              0x00003000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_MASK                                             0x00004000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_MASK                                                  0x00010000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_MASK                                              0x00020000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_MASK                                          0x00040000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_MASK                                              0x00080000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_MASK                                             0x00100000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN__SHIFT                                       0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT__SHIFT                                      0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_DEN_MASK                                         0x0000FFFFL
+#define RDPCSTX5_RDPCSTX_PHY_CNTL7__RDPCS_PHY_DP_MPLLB_FRACN_QUOT_MASK                                        0xFFFF0000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK__SHIFT                                        0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL8__RDPCS_PHY_DP_MPLLB_SSC_PEAK_MASK                                          0x000FFFFFL
+//RDPCSTX5_RDPCSTX_PHY_CNTL9
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD__SHIFT                                   0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_STEPSIZE_MASK                                      0x001FFFFFL
+#define RDPCSTX5_RDPCSTX_PHY_CNTL9__RDPCS_PHY_DP_MPLLB_SSC_UP_SPREAD_MASK                                     0x01000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM__SHIFT                                      0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL10__RDPCS_PHY_DP_MPLLB_FRACN_REM_MASK                                        0x0000FFFFL
+//RDPCSTX5_RDPCSTX_PHY_CNTL11
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER__SHIFT                                     0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV__SHIFT                                     0x10
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV__SHIFT                                    0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV__SHIFT                           0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_MPLLB_MULTIPLIER_MASK                                       0x0000FFF0L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_DIV_MASK                                       0x00070000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_DP_REF_CLK_MPLLB_DIV_MASK                                      0x00700000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL11__RDPCS_PHY_HDMI_MPLLB_HDMI_PIXEL_CLK_DIV_MASK                             0x03000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL12
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN__SHIFT                                    0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN__SHIFT                                   0x2
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV__SHIFT                                     0x4
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE__SHIFT                                          0x7
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN__SHIFT                                         0x8
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_DIV5_CLK_EN_MASK                                      0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_WORD_DIV2_EN_MASK                                     0x00000004L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_TX_CLK_DIV_MASK                                       0x00000070L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_STATE_MASK                                            0x00000080L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL12__RDPCS_PHY_DP_MPLLB_SSC_EN_MASK                                           0x00000100L
+//RDPCSTX5_RDPCSTX_PHY_CNTL13
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER__SHIFT                                 0x14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN__SHIFT                                     0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN__SHIFT                                       0x1d
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE__SHIFT                               0x1e
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_MULTIPLIER_MASK                                   0x0FF00000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_DIV_CLK_EN_MASK                                       0x10000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_FORCE_EN_MASK                                         0x20000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL13__RDPCS_PHY_DP_MPLLB_INIT_CAL_DISABLE_MASK                                 0x40000000L
+//RDPCSTX5_RDPCSTX_PHY_CNTL14
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE__SHIFT                                      0x0
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN__SHIFT                                       0x18
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN__SHIFT                                        0x1c
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_CAL_FORCE_MASK                                        0x00000001L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_FRACN_EN_MASK                                         0x01000000L
+#define RDPCSTX5_RDPCSTX_PHY_CNTL14__RDPCS_PHY_DP_MPLLB_PMIX_EN_MASK                                          0x10000000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I__SHIFT                                             0x12
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO__SHIFT                                        0x14
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_TX0_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_V2I_MASK                                               0x000C0000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE0__RDPCS_PHY_DP_MPLLB_FREQ_VCO_MASK                                          0x00300000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE1
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT__SHIFT                                          0x12
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP__SHIFT                                         0x19
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_TX1_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_INT_MASK                                            0x01FC0000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE1__RDPCS_PHY_DP_MPLLB_CP_PROP_MASK                                           0xFE000000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE2
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE2__RDPCS_PHY_DP_TX2_EQ_POST_MASK                                             0x0003F000L
+//RDPCSTX5_RDPCSTX_PHY_FUSE3
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN__SHIFT                                           0x0
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE__SHIFT                                            0x6
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST__SHIFT                                           0xc
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE__SHIFT                                             0x12
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE__SHIFT                                                0x18
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_MAIN_MASK                                             0x0000003FL
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_PRE_MASK                                              0x00000FC0L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DP_TX3_EQ_POST_MASK                                             0x0003F000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_FINETUNE_MASK                                               0x00FC0000L
+#define RDPCSTX5_RDPCSTX_PHY_FUSE3__RDPCS_PHY_DCO_RANGE_MASK                                                  0x03000000L
+//RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL__SHIFT                                        0x0
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL__SHIFT                                        0x8
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_REF_LD_VAL_MASK                                          0x0000007FL
+#define RDPCSTX5_RDPCSTX_PHY_RX_LD_VAL__RDPCS_PHY_RX_VCO_LD_VAL_MASK                                          0x001FFF00L
+//RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED__SHIFT                         0x0
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED__SHIFT                       0x1
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED__SHIFT                       0x2
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED__SHIFT                       0x3
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED__SHIFT                           0x4
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED__SHIFT                           0x5
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED__SHIFT                         0x8
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED__SHIFT                       0x9
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED__SHIFT                       0xa
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED__SHIFT                       0xb
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED__SHIFT                           0xc
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED__SHIFT                           0xd
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED__SHIFT                         0x10
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED__SHIFT                       0x11
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED__SHIFT                       0x12
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED__SHIFT                       0x13
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED__SHIFT                           0x14
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED__SHIFT                           0x15
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED__SHIFT                         0x18
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED__SHIFT                       0x19
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED__SHIFT                       0x1a
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED__SHIFT                       0x1b
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED__SHIFT                           0x1c
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED__SHIFT                           0x1d
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_RESET_RESERVED_MASK                           0x00000001L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DISABLE_RESERVED_MASK                         0x00000002L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_CLK_RDY_RESERVED_MASK                         0x00000004L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_DATA_EN_RESERVED_MASK                         0x00000008L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_REQ_RESERVED_MASK                             0x00000010L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX0_ACK_RESERVED_MASK                             0x00000020L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_RESET_RESERVED_MASK                           0x00000100L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DISABLE_RESERVED_MASK                         0x00000200L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_CLK_RDY_RESERVED_MASK                         0x00000400L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_DATA_EN_RESERVED_MASK                         0x00000800L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_REQ_RESERVED_MASK                             0x00001000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX1_ACK_RESERVED_MASK                             0x00002000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_RESET_RESERVED_MASK                           0x00010000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DISABLE_RESERVED_MASK                         0x00020000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_CLK_RDY_RESERVED_MASK                         0x00040000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_DATA_EN_RESERVED_MASK                         0x00080000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_REQ_RESERVED_MASK                             0x00100000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX2_ACK_RESERVED_MASK                             0x00200000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_RESET_RESERVED_MASK                           0x01000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DISABLE_RESERVED_MASK                         0x02000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_CLK_RDY_RESERVED_MASK                         0x04000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_DATA_EN_RESERVED_MASK                         0x08000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_REQ_RESERVED_MASK                             0x10000000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL3__RDPCS_PHY_DP_TX3_ACK_RESERVED_MASK                             0x20000000L
+//RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED__SHIFT                        0x0
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED__SHIFT                       0x2
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED__SHIFT                        0x4
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED__SHIFT                       0x6
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED__SHIFT                        0x8
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED__SHIFT                       0xa
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED__SHIFT                        0xc
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED__SHIFT                       0xe
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED__SHIFT                            0x10
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED__SHIFT                        0x11
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED__SHIFT                    0x12
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED__SHIFT                        0x13
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED__SHIFT                       0x14
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_PSTATE_RESERVED_MASK                          0x00000003L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX0_MPLL_EN_RESERVED_MASK                         0x00000004L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_PSTATE_RESERVED_MASK                          0x00000030L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX1_MPLL_EN_RESERVED_MASK                         0x00000040L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_PSTATE_RESERVED_MASK                          0x00000300L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX2_MPLL_EN_RESERVED_MASK                         0x00000400L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_PSTATE_RESERVED_MASK                          0x00003000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_TX3_MPLL_EN_RESERVED_MASK                         0x00004000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DP4_RESERVED_MASK                              0x00010000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_RESERVED_MASK                          0x00020000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DPALT_DISABLE_ACK_RESERVED_MASK                      0x00040000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_EN_RESERVED_MASK                          0x00080000L
+#define RDPCSTX5_RDPCSTX_DMCU_DPALT_PHY_CNTL6__RDPCS_PHY_DP_REF_CLK_REQ_RESERVED_MASK                         0x00100000L
+//RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS__SHIFT                                  0x0
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED__SHIFT                                0x4
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE__SHIFT                                  0x8
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_ALLOW_DRIVER_ACCESS_MASK                                    0x00000001L
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DRIVER_ACCESS_BLOCKED_MASK                                  0x00000010L
+#define RDPCSTX5_RDPCSTX_DPALT_CONTROL_REG__RDPCS_DPALT_CONTROL_SPARE_MASK                                    0x0000FF00L
+
+
+// addressBlock: dpcssys_dpcssys_cr5_dispdec
+//DPCSSYS_CR5_DPCSSYS_CR_ADDR
+#define DPCSSYS_CR5_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR__SHIFT                                                  0x0
+#define DPCSSYS_CR5_DPCSSYS_CR_ADDR__RDPCS_TX_CR_ADDR_MASK                                                    0x0000FFFFL
+//DPCSSYS_CR5_DPCSSYS_CR_DATA
+#define DPCSSYS_CR5_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA__SHIFT                                                  0x0
+#define DPCSSYS_CR5_DPCSSYS_CR_DATA__RDPCS_TX_CR_DATA_MASK                                                    0x0000FFFFL
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_offset.h
index 945bb6101a9d..945bb6101a9d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_offset.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_sh_mask.h
index 6e039f2208e1..6e039f2208e1 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dpcs_2_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dpcs/dpcs_2_1_0_sh_mask.h
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
index 2bfaaa8157d0..d984c916df80 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
@@ -2224,6 +2224,14 @@
 #define mmCOMPUTE_STATIC_THREAD_MGMT_SE2_BASE_IDX                                                      0
 #define mmCOMPUTE_STATIC_THREAD_MGMT_SE3                                                               0x0e1a
 #define mmCOMPUTE_STATIC_THREAD_MGMT_SE3_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE4                                                               0x0e25
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE4_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE5                                                               0x0e26
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE5_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE6                                                               0x0e27
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE6_BASE_IDX                                                      0
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE7                                                               0x0e28
+#define mmCOMPUTE_STATIC_THREAD_MGMT_SE7_BASE_IDX                                                      0
 #define mmCOMPUTE_RESTART_X                                                                            0x0e1b
 #define mmCOMPUTE_RESTART_X_BASE_IDX                                                                   0
 #define mmCOMPUTE_RESTART_Y                                                                            0x0e1c
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
index d4c613a85352..c9e3f6d849a8 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
@@ -8739,10 +8739,16 @@
 #define TCP_ADDR_CONFIG__NUM_BANKS__SHIFT                                                                     0x4
 #define TCP_ADDR_CONFIG__COLHI_WIDTH__SHIFT                                                                   0x6
 #define TCP_ADDR_CONFIG__RB_SPLIT_COLHI__SHIFT                                                                0x9
+#define TCP_ADDR_CONFIG__ENABLE64KHASH__SHIFT                                                                 0xb
+#define TCP_ADDR_CONFIG__ENABLE2MHASH__SHIFT                                                                  0xc
+#define TCP_ADDR_CONFIG__ENABLE1GHASH__SHIFT                                                                  0xd
 #define TCP_ADDR_CONFIG__NUM_TCC_BANKS_MASK                                                                   0x0000000FL
 #define TCP_ADDR_CONFIG__NUM_BANKS_MASK                                                                       0x00000030L
 #define TCP_ADDR_CONFIG__COLHI_WIDTH_MASK                                                                     0x000001C0L
 #define TCP_ADDR_CONFIG__RB_SPLIT_COLHI_MASK                                                                  0x00000200L
+#define TCP_ADDR_CONFIG__ENABLE64KHASH_MASK                                                                   0x00000800L
+#define TCP_ADDR_CONFIG__ENABLE2MHASH_MASK                                                                    0x00001000L
+#define TCP_ADDR_CONFIG__ENABLE1GHASH_MASK                                                                    0x00002000L
 //TCP_CREDIT
 #define TCP_CREDIT__LFIFO_CREDIT__SHIFT                                                                       0x0
 #define TCP_CREDIT__REQ_FIFO_CREDIT__SHIFT                                                                    0x10
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
index 352ffae7a7ca..2c3ce243861a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_offset.h
@@ -1964,4 +1964,20 @@
 #define mmATC_L2_PERFCOUNTER_RSLT_CNTL                                                                 0x084a
 #define mmATC_L2_PERFCOUNTER_RSLT_CNTL_BASE_IDX                                                        0
 
+/* MMEA */
+#define mmMMEA0_EDC_CNT_VG20                                                                           0x0206
+#define mmMMEA0_EDC_CNT_VG20_BASE_IDX                                                                  0
+#define mmMMEA0_EDC_CNT2_VG20                                                                          0x0207
+#define mmMMEA0_EDC_CNT2_VG20_BASE_IDX                                                                 0
+#define mmMMEA1_EDC_CNT_VG20                                                                           0x0346
+#define mmMMEA1_EDC_CNT_VG20_BASE_IDX                                                                  0
+#define mmMMEA1_EDC_CNT2_VG20                                                                          0x0347
+#define mmMMEA1_EDC_CNT2_VG20_BASE_IDX                                                                 0
+
+// addressBlock: mmhub_utcl2_vmsharedpfdec
+// base address: 0x6a040
+#define mmMC_VM_XGMI_LFB_CNTL                                                                          0x0823
+#define mmMC_VM_XGMI_LFB_CNTL_BASE_IDX                                                                 0
+#define mmMC_VM_XGMI_LFB_SIZE                                                                          0x0824
+#define mmMC_VM_XGMI_LFB_SIZE_BASE_IDX                                                                 0
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
index 34278ef2aa1b..198f5f93ed1a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_1_0_sh_mask.h
@@ -10124,4 +10124,126 @@
 #define ATC_L2_PERFCOUNTER_RSLT_CNTL__CLEAR_ALL_MASK                                                          0x02000000L
 #define ATC_L2_PERFCOUNTER_RSLT_CNTL__STOP_ALL_ON_SATURATE_MASK                                               0x04000000L
 
+//MMEA0_EDC_CNT
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
+#define MMEA0_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
+#define MMEA0_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
+#define MMEA0_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
+#define MMEA0_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
+#define MMEA0_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA0_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
+#define MMEA0_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
+#define MMEA0_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
+#define MMEA0_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
+#define MMEA0_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
+#define MMEA0_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
+#define MMEA0_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
+#define MMEA0_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
+//MMEA0_EDC_CNT2
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA0_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
+#define MMEA0_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
+#define MMEA0_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
+#define MMEA0_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
+#define MMEA0_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
+#define MMEA0_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA0_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA0_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
+#define MMEA0_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
+#define MMEA0_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
+//MMEA1_EDC_CNT
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
+#define MMEA1_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
+#define MMEA1_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
+#define MMEA1_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
+#define MMEA1_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
+#define MMEA1_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA1_EDC_CNT_VG20__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
+#define MMEA1_EDC_CNT_VG20__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
+#define MMEA1_EDC_CNT_VG20__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
+#define MMEA1_EDC_CNT_VG20__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
+#define MMEA1_EDC_CNT_VG20__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
+#define MMEA1_EDC_CNT_VG20__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
+#define MMEA1_EDC_CNT_VG20__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
+#define MMEA1_EDC_CNT_VG20__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
+//MMEA1_EDC_CNT2
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
+#define MMEA1_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
+#define MMEA1_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
+#define MMEA1_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
+#define MMEA1_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
+#define MMEA1_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
+#define MMEA1_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
+#define MMEA1_EDC_CNT2_VG20__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
+#define MMEA1_EDC_CNT2_VG20__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
+#define MMEA1_EDC_CNT2_VG20__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
+#define MMEA1_EDC_CNT2_VG20__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
+
+// addressBlock: mmhub_utcl2_vmsharedpfdec
+//MC_VM_XGMI_LFB_CNTL
+#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION__SHIFT                                                             0x0
+#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION__SHIFT                                                             0x4
+#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION_MASK                                                               0x00000007L
+#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION_MASK                                                               0x00000070L
+//MC_VM_XGMI_LFB_SIZE
+#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE__SHIFT                                                               0x0
+#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE_MASK                                                                 0x0000FFFFL
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_offset.h
deleted file mode 100644
index f2ae3a58949e..000000000000
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_offset.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Copyright (C) 2018  Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included
- * in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
- * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
- */
-#ifndef _mmhub_9_4_0_OFFSET_HEADER
-#define _mmhub_9_4_0_OFFSET_HEADER
-
-/* MMEA */
-#define mmMMEA0_SDP_ARB_FINAL_VG20                                                                     0x01ee
-#define mmMMEA0_SDP_ARB_FINAL_VG20_BASE_IDX                                                            0
-#define mmMMEA0_EDC_CNT_VG20                                                                           0x0206
-#define mmMMEA0_EDC_CNT_VG20_BASE_IDX                                                                  0
-#define mmMMEA0_EDC_CNT2_VG20                                                                          0x0207
-#define mmMMEA0_EDC_CNT2_VG20_BASE_IDX                                                                 0
-#define mmMMEA0_EDC_MODE_VG20                                                                          0x0210
-#define mmMMEA0_EDC_MODE_VG20_BASE_IDX                                                                 0
-#define mmMMEA0_ERR_STATUS_VG20                                                                        0x0211
-#define mmMMEA0_ERR_STATUS_VG20_BASE_IDX                                                               0
-#define mmMMEA1_SDP_ARB_FINAL_VG20                                                                     0x032e
-#define mmMMEA1_SDP_ARB_FINAL_VG20_BASE_IDX                                                            0
-#define mmMMEA1_EDC_CNT_VG20                                                                           0x0346
-#define mmMMEA1_EDC_CNT_VG20_BASE_IDX                                                                  0
-#define mmMMEA1_EDC_CNT2_VG20                                                                          0x0347
-#define mmMMEA1_EDC_CNT2_VG20_BASE_IDX                                                                 0
-#define mmMMEA1_EDC_MODE_VG20                                                                          0x0350
-#define mmMMEA1_EDC_MODE_VG20_BASE_IDX                                                                 0
-#define mmMMEA1_ERR_STATUS_VG20                                                                        0x0351
-#define mmMMEA1_ERR_STATUS_VG20_BASE_IDX                                                               0
-
-// addressBlock: mmhub_utcl2_vmsharedpfdec
-// base address: 0x6a040
-#define mmMC_VM_XGMI_LFB_CNTL                                                                          0x0823
-#define mmMC_VM_XGMI_LFB_CNTL_BASE_IDX                                                                 0
-#define mmMC_VM_XGMI_LFB_SIZE                                                                          0x0824
-#define mmMC_VM_XGMI_LFB_SIZE_BASE_IDX                                                                 0
-
-#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_sh_mask.h
deleted file mode 100644
index c24259ed12a1..000000000000
--- a/drivers/gpu/drm/amd/include/asic_reg/mmhub/mmhub_9_4_0_sh_mask.h
+++ /dev/null
@@ -1,257 +0,0 @@
-/*
- * Copyright (C) 2018  Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included
- * in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
- * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
- * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
- */
-#ifndef _mmhub_9_4_0_SH_MASK_HEADER
-#define _mmhub_9_4_0_SH_MASK_HEADER
-
-//MMEA0_SDP_ARB_FINAL
-#define MMEA0_SDP_ARB_FINAL__DRAM_BURST_LIMIT__SHIFT                                                          0x0
-#define MMEA0_SDP_ARB_FINAL__GMI_BURST_LIMIT__SHIFT                                                           0x5
-#define MMEA0_SDP_ARB_FINAL__IO_BURST_LIMIT__SHIFT                                                            0xa
-#define MMEA0_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER__SHIFT                                                    0xf
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC0__SHIFT                                                                0x11
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC1__SHIFT                                                                0x12
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC2__SHIFT                                                                0x13
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC3__SHIFT                                                                0x14
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC4__SHIFT                                                                0x15
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC5__SHIFT                                                                0x16
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC6__SHIFT                                                                0x17
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC7__SHIFT                                                                0x18
-#define MMEA0_SDP_ARB_FINAL__ERREVENT_ON_ERROR__SHIFT                                                         0x19
-#define MMEA0_SDP_ARB_FINAL__HALTREQ_ON_ERROR__SHIFT                                                          0x1a
-#define MMEA0_SDP_ARB_FINAL__DRAM_BURST_LIMIT_MASK                                                            0x0000001FL
-#define MMEA0_SDP_ARB_FINAL__GMI_BURST_LIMIT_MASK                                                             0x000003E0L
-#define MMEA0_SDP_ARB_FINAL__IO_BURST_LIMIT_MASK                                                              0x00007C00L
-#define MMEA0_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER_MASK                                                      0x00018000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC0_MASK                                                                  0x00020000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC1_MASK                                                                  0x00040000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC2_MASK                                                                  0x00080000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC3_MASK                                                                  0x00100000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC4_MASK                                                                  0x00200000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC5_MASK                                                                  0x00400000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC6_MASK                                                                  0x00800000L
-#define MMEA0_SDP_ARB_FINAL__RDONLY_VC7_MASK                                                                  0x01000000L
-#define MMEA0_SDP_ARB_FINAL__ERREVENT_ON_ERROR_MASK                                                           0x02000000L
-#define MMEA0_SDP_ARB_FINAL__HALTREQ_ON_ERROR_MASK                                                            0x04000000L
-//MMEA0_EDC_CNT
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA0_EDC_CNT__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
-#define MMEA0_EDC_CNT__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
-#define MMEA0_EDC_CNT__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
-#define MMEA0_EDC_CNT__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
-#define MMEA0_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
-#define MMEA0_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
-#define MMEA0_EDC_CNT__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
-#define MMEA0_EDC_CNT__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
-#define MMEA0_EDC_CNT__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA0_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA0_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA0_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA0_EDC_CNT__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
-#define MMEA0_EDC_CNT__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
-#define MMEA0_EDC_CNT__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
-#define MMEA0_EDC_CNT__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
-#define MMEA0_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
-#define MMEA0_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
-#define MMEA0_EDC_CNT__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
-#define MMEA0_EDC_CNT__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
-#define MMEA0_EDC_CNT__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
-//MMEA0_EDC_CNT2
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA0_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
-#define MMEA0_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
-#define MMEA0_EDC_CNT2__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
-#define MMEA0_EDC_CNT2__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
-#define MMEA0_EDC_CNT2__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
-#define MMEA0_EDC_CNT2__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA0_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA0_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA0_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA0_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
-#define MMEA0_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
-#define MMEA0_EDC_CNT2__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
-#define MMEA0_EDC_CNT2__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
-#define MMEA0_EDC_CNT2__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
-#define MMEA0_EDC_CNT2__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
-//MMEA0_EDC_MODE
-#define MMEA0_EDC_MODE__COUNT_FED_OUT__SHIFT                                                                  0x10
-#define MMEA0_EDC_MODE__GATE_FUE__SHIFT                                                                       0x11
-#define MMEA0_EDC_MODE__DED_MODE__SHIFT                                                                       0x14
-#define MMEA0_EDC_MODE__PROP_FED__SHIFT                                                                       0x1d
-#define MMEA0_EDC_MODE__BYPASS__SHIFT                                                                         0x1f
-#define MMEA0_EDC_MODE__COUNT_FED_OUT_MASK                                                                    0x00010000L
-#define MMEA0_EDC_MODE__GATE_FUE_MASK                                                                         0x00020000L
-#define MMEA0_EDC_MODE__DED_MODE_MASK                                                                         0x00300000L
-#define MMEA0_EDC_MODE__PROP_FED_MASK                                                                         0x20000000L
-#define MMEA0_EDC_MODE__BYPASS_MASK                                                                           0x80000000L
-//MMEA0_ERR_STATUS
-#define MMEA0_ERR_STATUS__SDP_RDRSP_STATUS__SHIFT                                                             0x0
-#define MMEA0_ERR_STATUS__SDP_WRRSP_STATUS__SHIFT                                                             0x4
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATASTATUS__SHIFT                                                         0x8
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR__SHIFT                                                   0xa
-#define MMEA0_ERR_STATUS__CLEAR_ERROR_STATUS__SHIFT                                                           0xb
-#define MMEA0_ERR_STATUS__BUSY_ON_ERROR__SHIFT                                                                0xc
-#define MMEA0_ERR_STATUS__FUE_FLAG__SHIFT                                                                     0xd
-#define MMEA0_ERR_STATUS__SDP_RDRSP_STATUS_MASK                                                               0x0000000FL
-#define MMEA0_ERR_STATUS__SDP_WRRSP_STATUS_MASK                                                               0x000000F0L
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATASTATUS_MASK                                                           0x00000300L
-#define MMEA0_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR_MASK                                                     0x00000400L
-#define MMEA0_ERR_STATUS__CLEAR_ERROR_STATUS_MASK                                                             0x00000800L
-#define MMEA0_ERR_STATUS__BUSY_ON_ERROR_MASK                                                                  0x00001000L
-#define MMEA0_ERR_STATUS__FUE_FLAG_MASK                                                                       0x00002000L
-//MMEA1_SDP_ARB_FINAL
-#define MMEA1_SDP_ARB_FINAL__DRAM_BURST_LIMIT__SHIFT                                                          0x0
-#define MMEA1_SDP_ARB_FINAL__GMI_BURST_LIMIT__SHIFT                                                           0x5
-#define MMEA1_SDP_ARB_FINAL__IO_BURST_LIMIT__SHIFT                                                            0xa
-#define MMEA1_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER__SHIFT                                                    0xf
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC0__SHIFT                                                                0x11
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC1__SHIFT                                                                0x12
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC2__SHIFT                                                                0x13
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC3__SHIFT                                                                0x14
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC4__SHIFT                                                                0x15
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC5__SHIFT                                                                0x16
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC6__SHIFT                                                                0x17
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC7__SHIFT                                                                0x18
-#define MMEA1_SDP_ARB_FINAL__ERREVENT_ON_ERROR__SHIFT                                                         0x19
-#define MMEA1_SDP_ARB_FINAL__HALTREQ_ON_ERROR__SHIFT                                                          0x1a
-#define MMEA1_SDP_ARB_FINAL__DRAM_BURST_LIMIT_MASK                                                            0x0000001FL
-#define MMEA1_SDP_ARB_FINAL__GMI_BURST_LIMIT_MASK                                                             0x000003E0L
-#define MMEA1_SDP_ARB_FINAL__IO_BURST_LIMIT_MASK                                                              0x00007C00L
-#define MMEA1_SDP_ARB_FINAL__BURST_LIMIT_MULTIPLIER_MASK                                                      0x00018000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC0_MASK                                                                  0x00020000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC1_MASK                                                                  0x00040000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC2_MASK                                                                  0x00080000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC3_MASK                                                                  0x00100000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC4_MASK                                                                  0x00200000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC5_MASK                                                                  0x00400000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC6_MASK                                                                  0x00800000L
-#define MMEA1_SDP_ARB_FINAL__RDONLY_VC7_MASK                                                                  0x01000000L
-#define MMEA1_SDP_ARB_FINAL__ERREVENT_ON_ERROR_MASK                                                           0x02000000L
-#define MMEA1_SDP_ARB_FINAL__HALTREQ_ON_ERROR_MASK                                                            0x04000000L
-//MMEA1_EDC_CNT
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA1_EDC_CNT__RRET_TAGMEM_SEC_COUNT__SHIFT                                                           0xc
-#define MMEA1_EDC_CNT__RRET_TAGMEM_DED_COUNT__SHIFT                                                           0xe
-#define MMEA1_EDC_CNT__WRET_TAGMEM_SEC_COUNT__SHIFT                                                           0x10
-#define MMEA1_EDC_CNT__WRET_TAGMEM_DED_COUNT__SHIFT                                                           0x12
-#define MMEA1_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT__SHIFT                                                        0x14
-#define MMEA1_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT__SHIFT                                                        0x16
-#define MMEA1_EDC_CNT__IORD_CMDMEM_SED_COUNT__SHIFT                                                           0x18
-#define MMEA1_EDC_CNT__IOWR_CMDMEM_SED_COUNT__SHIFT                                                           0x1a
-#define MMEA1_EDC_CNT__IOWR_DATAMEM_SED_COUNT__SHIFT                                                          0x1c
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA1_EDC_CNT__DRAMRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA1_EDC_CNT__DRAMWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA1_EDC_CNT__DRAMWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA1_EDC_CNT__RRET_TAGMEM_SEC_COUNT_MASK                                                             0x00003000L
-#define MMEA1_EDC_CNT__RRET_TAGMEM_DED_COUNT_MASK                                                             0x0000C000L
-#define MMEA1_EDC_CNT__WRET_TAGMEM_SEC_COUNT_MASK                                                             0x00030000L
-#define MMEA1_EDC_CNT__WRET_TAGMEM_DED_COUNT_MASK                                                             0x000C0000L
-#define MMEA1_EDC_CNT__DRAMRD_PAGEMEM_SED_COUNT_MASK                                                          0x00300000L
-#define MMEA1_EDC_CNT__DRAMWR_PAGEMEM_SED_COUNT_MASK                                                          0x00C00000L
-#define MMEA1_EDC_CNT__IORD_CMDMEM_SED_COUNT_MASK                                                             0x03000000L
-#define MMEA1_EDC_CNT__IOWR_CMDMEM_SED_COUNT_MASK                                                             0x0C000000L
-#define MMEA1_EDC_CNT__IOWR_DATAMEM_SED_COUNT_MASK                                                            0x30000000L
-//MMEA1_EDC_CNT2
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT__SHIFT                                                         0x0
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT__SHIFT                                                         0x2
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT__SHIFT                                                         0x4
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT__SHIFT                                                         0x6
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT__SHIFT                                                        0x8
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT__SHIFT                                                        0xa
-#define MMEA1_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT__SHIFT                                                        0xc
-#define MMEA1_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT__SHIFT                                                        0xe
-#define MMEA1_EDC_CNT2__MAM_D0MEM_SED_COUNT__SHIFT                                                            0x10
-#define MMEA1_EDC_CNT2__MAM_D1MEM_SED_COUNT__SHIFT                                                            0x12
-#define MMEA1_EDC_CNT2__MAM_D2MEM_SED_COUNT__SHIFT                                                            0x14
-#define MMEA1_EDC_CNT2__MAM_D3MEM_SED_COUNT__SHIFT                                                            0x16
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_SEC_COUNT_MASK                                                           0x00000003L
-#define MMEA1_EDC_CNT2__GMIRD_CMDMEM_DED_COUNT_MASK                                                           0x0000000CL
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_SEC_COUNT_MASK                                                           0x00000030L
-#define MMEA1_EDC_CNT2__GMIWR_CMDMEM_DED_COUNT_MASK                                                           0x000000C0L
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_SEC_COUNT_MASK                                                          0x00000300L
-#define MMEA1_EDC_CNT2__GMIWR_DATAMEM_DED_COUNT_MASK                                                          0x00000C00L
-#define MMEA1_EDC_CNT2__GMIRD_PAGEMEM_SED_COUNT_MASK                                                          0x00003000L
-#define MMEA1_EDC_CNT2__GMIWR_PAGEMEM_SED_COUNT_MASK                                                          0x0000C000L
-#define MMEA1_EDC_CNT2__MAM_D0MEM_SED_COUNT_MASK                                                              0x00030000L
-#define MMEA1_EDC_CNT2__MAM_D1MEM_SED_COUNT_MASK                                                              0x000C0000L
-#define MMEA1_EDC_CNT2__MAM_D2MEM_SED_COUNT_MASK                                                              0x00300000L
-#define MMEA1_EDC_CNT2__MAM_D3MEM_SED_COUNT_MASK                                                              0x00C00000L
-//MMEA1_EDC_MODE
-#define MMEA1_EDC_MODE__COUNT_FED_OUT__SHIFT                                                                  0x10
-#define MMEA1_EDC_MODE__GATE_FUE__SHIFT                                                                       0x11
-#define MMEA1_EDC_MODE__DED_MODE__SHIFT                                                                       0x14
-#define MMEA1_EDC_MODE__PROP_FED__SHIFT                                                                       0x1d
-#define MMEA1_EDC_MODE__BYPASS__SHIFT                                                                         0x1f
-#define MMEA1_EDC_MODE__COUNT_FED_OUT_MASK                                                                    0x00010000L
-#define MMEA1_EDC_MODE__GATE_FUE_MASK                                                                         0x00020000L
-#define MMEA1_EDC_MODE__DED_MODE_MASK                                                                         0x00300000L
-#define MMEA1_EDC_MODE__PROP_FED_MASK                                                                         0x20000000L
-#define MMEA1_EDC_MODE__BYPASS_MASK                                                                           0x80000000L
-//MMEA1_ERR_STATUS
-#define MMEA1_ERR_STATUS__SDP_RDRSP_STATUS__SHIFT                                                             0x0
-#define MMEA1_ERR_STATUS__SDP_WRRSP_STATUS__SHIFT                                                             0x4
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATASTATUS__SHIFT                                                         0x8
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR__SHIFT                                                   0xa
-#define MMEA1_ERR_STATUS__CLEAR_ERROR_STATUS__SHIFT                                                           0xb
-#define MMEA1_ERR_STATUS__BUSY_ON_ERROR__SHIFT                                                                0xc
-#define MMEA1_ERR_STATUS__FUE_FLAG__SHIFT                                                                     0xd
-#define MMEA1_ERR_STATUS__SDP_RDRSP_STATUS_MASK                                                               0x0000000FL
-#define MMEA1_ERR_STATUS__SDP_WRRSP_STATUS_MASK                                                               0x000000F0L
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATASTATUS_MASK                                                           0x00000300L
-#define MMEA1_ERR_STATUS__SDP_RDRSP_DATAPARITY_ERROR_MASK                                                     0x00000400L
-#define MMEA1_ERR_STATUS__CLEAR_ERROR_STATUS_MASK                                                             0x00000800L
-#define MMEA1_ERR_STATUS__BUSY_ON_ERROR_MASK                                                                  0x00001000L
-#define MMEA1_ERR_STATUS__FUE_FLAG_MASK                                                                       0x00002000L
-
-// addressBlock: mmhub_utcl2_vmsharedpfdec
-//MC_VM_XGMI_LFB_CNTL
-#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION__SHIFT                                                             0x0
-#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION__SHIFT                                                             0x4
-#define MC_VM_XGMI_LFB_CNTL__PF_LFB_REGION_MASK                                                               0x00000007L
-#define MC_VM_XGMI_LFB_CNTL__PF_MAX_REGION_MASK                                                               0x00000070L
-//MC_VM_XGMI_LFB_SIZE
-#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE__SHIFT                                                               0x0
-#define MC_VM_XGMI_LFB_SIZE__PF_LFB_SIZE_MASK                                                                 0x0000FFFFL
-
-#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h
index 043aa695d63f..0d6b594be775 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_1_offset.h
@@ -27,5 +27,7 @@
 #define mmUMCCH0_0_EccErrCnt_BASE_IDX                                                                  0
 #define mmMCA_UMC_UMC0_MCUMC_STATUST0                                                                  0x03c2
 #define mmMCA_UMC_UMC0_MCUMC_STATUST0_BASE_IDX                                                         0
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0                                                                    0x03c4
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_BASE_IDX                                                           0
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_offset.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_offset.h
new file mode 100644
index 000000000000..ce005c674a18
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_offset.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _umc_6_1_2_OFFSET_HEADER
+#define _umc_6_1_2_OFFSET_HEADER
+
+#define mmUMCCH0_0_EccErrCntSel_ARCT                                     0x0360
+#define mmUMCCH0_0_EccErrCntSel_ARCT_BASE_IDX                            1
+#define mmUMCCH0_0_EccErrCnt_ARCT                                        0x0361
+#define mmUMCCH0_0_EccErrCnt_ARCT_BASE_IDX                               1
+#define mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT                               0x03c2
+#define mmMCA_UMC_UMC0_MCUMC_STATUST0_ARCT_BASE_IDX                      1
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_ARCT                                 0x03c4
+#define mmMCA_UMC_UMC0_MCUMC_ADDRT0_ARCT_BASE_IDX                        1
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_sh_mask.h
new file mode 100644
index 000000000000..a5a8c993ec3a
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/asic_reg/umc/umc_6_1_2_sh_mask.h
@@ -0,0 +1,91 @@
+/*
+ * Copyright (C) 2020  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef _umc_6_1_2_SH_MASK_HEADER
+#define _umc_6_1_2_SH_MASK_HEADER
+
+//UMCCH0_0_EccErrCntSel_ARCT
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntCsSel__SHIFT                                                          0x0
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrInt__SHIFT                                                               0xc
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntEn__SHIFT                                                             0xf
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntCsSel_MASK                                                            0x0000000FL
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrInt_MASK                                                                 0x00003000L
+#define UMCCH0_0_EccErrCntSel_ARCT__EccErrCntEn_MASK                                                               0x00008000L
+//UMCCH0_0_EccErrCnt_ARCT
+#define UMCCH0_0_EccErrCnt_ARCT__EccErrCnt__SHIFT                                                                  0x0
+#define UMCCH0_0_EccErrCnt_ARCT__EccErrCnt_MASK                                                                    0x0000FFFFL
+//MCA_UMC_UMC0_MCUMC_STATUST0_ARCT
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCode__SHIFT                                                         0x0
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCodeExt__SHIFT                                                      0x10
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV0__SHIFT                                                           0x16
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreId__SHIFT                                                         0x20
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV1__SHIFT                                                           0x26
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Scrub__SHIFT                                                             0x28
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV2__SHIFT                                                           0x29
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Poison__SHIFT                                                            0x2b
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Deferred__SHIFT                                                          0x2c
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UECC__SHIFT                                                              0x2d
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__CECC__SHIFT                                                              0x2e
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV3__SHIFT                                                           0x2f
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Transparent__SHIFT                                                       0x34
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__SyndV__SHIFT                                                             0x35
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV4__SHIFT                                                           0x36
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__TCC__SHIFT                                                               0x37
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreIdVal__SHIFT                                                      0x38
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__PCC__SHIFT                                                               0x39
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__AddrV__SHIFT                                                             0x3a
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__MiscV__SHIFT                                                             0x3b
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__En__SHIFT                                                                0x3c
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UC__SHIFT                                                                0x3d
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Overflow__SHIFT                                                          0x3e
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Val__SHIFT                                                               0x3f
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCode_MASK                                                           0x000000000000FFFFL
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrorCodeExt_MASK                                                        0x00000000003F0000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV0_MASK                                                             0x00000000FFC00000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreId_MASK                                                           0x0000003F00000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV1_MASK                                                             0x000000C000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Scrub_MASK                                                               0x0000010000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV2_MASK                                                             0x0000060000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Poison_MASK                                                              0x0000080000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Deferred_MASK                                                            0x0000100000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UECC_MASK                                                                0x0000200000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__CECC_MASK                                                                0x0000400000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV3_MASK                                                             0x000F800000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Transparent_MASK                                                         0x0010000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__SyndV_MASK                                                               0x0020000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__RESERV4_MASK                                                             0x0040000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__TCC_MASK                                                                 0x0080000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__ErrCoreIdVal_MASK                                                        0x0100000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__PCC_MASK                                                                 0x0200000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__AddrV_MASK                                                               0x0400000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__MiscV_MASK                                                               0x0800000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__En_MASK                                                                  0x1000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__UC_MASK                                                                  0x2000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Overflow_MASK                                                            0x4000000000000000L
+#define MCA_UMC_UMC0_MCUMC_STATUST0_ARCT__Val_MASK                                                                 0x8000000000000000L
+//MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__ErrorAddr__SHIFT                                                           0x0
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__LSB__SHIFT                                                                 0x38
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__Reserved__SHIFT                                                            0x3e
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__ErrorAddr_MASK                                                             0x00FFFFFFFFFFFFFFL
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__LSB_MASK                                                                   0x3F00000000000000L
+#define MCA_UMC_UMC0_MCUMC_ADDRT0_ARCT__Reserved_MASK                                                              0xC000000000000000L
+
+#endif
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index dd7cbc00a0aa..70146518174c 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -672,20 +672,6 @@ struct vram_usagebyfirmware_v2_1
   uint16_t  used_by_driver_in_kb; 
 };
 
-/* This is part of vram_usagebyfirmware_v2_1 */
-struct vram_reserve_block
-{
-	uint32_t start_address_in_kb;
-	uint16_t used_by_firmware_in_kb;
-	uint16_t used_by_driver_in_kb;
-};
-
-/* Definitions for constance */
-enum atomfirmware_internal_constants
-{
-	ONE_KiB	= 0x400,
-	ONE_MiB	= 0x100000,
-};
 
 /* 
   ***************************************************************************
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 2cd217e60125..a607b1034962 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -256,6 +256,10 @@ struct kfd2kgd_calls {
 			uint32_t wptr_shift, uint32_t wptr_mask,
 			struct mm_struct *mm);
 
+	int (*hiq_mqd_load)(struct kgd_dev *kgd, void *mqd,
+			    uint32_t pipe_id, uint32_t queue_id,
+			    uint32_t doorbell_off);
+
 	int (*hqd_sdma_load)(struct kgd_dev *kgd, void *mqd,
 			     uint32_t __user *wptr, struct mm_struct *mm);
 
@@ -307,8 +311,6 @@ struct kfd2kgd_calls {
 
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,
 			uint32_t vmid, uint64_t page_table_base);
-	int (*invalidate_tlbs)(struct kgd_dev *kgd, uint16_t pasid);
-	int (*invalidate_tlbs_vmid)(struct kgd_dev *kgd, uint16_t vmid);
 	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
 	uint64_t (*get_hive_id)(struct kgd_dev *kgd);
 
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 7932eb163a00..c195575366a3 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -48,7 +48,6 @@ static int amd_powerplay_create(struct amdgpu_device *adev)
 
 	hwmgr->adev = adev;
 	hwmgr->not_vf = !amdgpu_sriov_vf(adev);
-	hwmgr->pm_en = (amdgpu_dpm && hwmgr->not_vf) ? true : false;
 	hwmgr->device = amdgpu_cgs_create_device(adev);
 	mutex_init(&hwmgr->smu_lock);
 	hwmgr->chip_family = adev->family;
@@ -928,9 +927,12 @@ static int pp_dpm_set_mp1_state(void *handle, enum pp_mp1_state mp1_state)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr)
 		return -EINVAL;
 
+	if (!hwmgr->pm_en)
+		return 0;
+
 	if (hwmgr->hwmgr_func->set_mp1_state)
 		return hwmgr->hwmgr_func->set_mp1_state(hwmgr, mp1_state);
 
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index a23729d3174b..99469479e277 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -356,6 +356,35 @@ int smu_get_dpm_level_count(struct smu_context *smu, enum smu_clk_type clk_type,
 	return smu_get_dpm_freq_by_index(smu, clk_type, 0xff, value);
 }
 
+int smu_get_dpm_level_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t *min_value, uint32_t *max_value)
+{
+	int ret = 0;
+	uint32_t level_count = 0;
+
+	if (!min_value && !max_value)
+		return -EINVAL;
+
+	if (min_value) {
+		/* by default, level 0 clock value as min value */
+		ret = smu_get_dpm_freq_by_index(smu, clk_type, 0, min_value);
+		if (ret)
+			return ret;
+	}
+
+	if (max_value) {
+		ret = smu_get_dpm_level_count(smu, clk_type, &level_count);
+		if (ret)
+			return ret;
+
+		ret = smu_get_dpm_freq_by_index(smu, clk_type, level_count - 1, max_value);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
 bool smu_clk_dpm_is_enabled(struct smu_context *smu, enum smu_clk_type clk_type)
 {
 	enum smu_feature_mask feature_id = 0;
@@ -404,10 +433,10 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 
 	switch (block_type) {
 	case AMD_IP_BLOCK_TYPE_UVD:
-		ret = smu_dpm_set_uvd_enable(smu, gate);
+		ret = smu_dpm_set_uvd_enable(smu, !gate);
 		break;
 	case AMD_IP_BLOCK_TYPE_VCE:
-		ret = smu_dpm_set_vce_enable(smu, gate);
+		ret = smu_dpm_set_vce_enable(smu, !gate);
 		break;
 	case AMD_IP_BLOCK_TYPE_GFX:
 		ret = smu_gfx_off_control(smu, gate);
@@ -415,6 +444,9 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 	case AMD_IP_BLOCK_TYPE_SDMA:
 		ret = smu_powergate_sdma(smu, gate);
 		break;
+	case AMD_IP_BLOCK_TYPE_JPEG:
+		ret = smu_dpm_set_jpeg_enable(smu, !gate);
+		break;
 	default:
 		break;
 	}
@@ -487,26 +519,25 @@ int smu_update_table(struct smu_context *smu, enum smu_table_id table_index, int
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct amdgpu_device *adev = smu->adev;
-	struct smu_table *table = NULL;
-	int ret = 0;
+	struct smu_table *table = &smu_table->driver_table;
 	int table_id = smu_table_get_index(smu, table_index);
+	uint32_t table_size;
+	int ret = 0;
 
 	if (!table_data || table_id >= SMU_TABLE_COUNT || table_id < 0)
 		return -EINVAL;
 
-	table = &smu_table->tables[table_index];
+	table_size = smu_table->tables[table_index].size;
 
-	if (drv2smu)
-		memcpy(table->cpu_addr, table_data, table->size);
+	if (drv2smu) {
+		memcpy(table->cpu_addr, table_data, table_size);
+		/*
+		 * Flush hdp cache: to guard the content seen by
+		 * GPU is consitent with CPU.
+		 */
+		amdgpu_asic_flush_hdp(adev, NULL);
+	}
 
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetDriverDramAddrHigh,
-					  upper_32_bits(table->mc_address));
-	if (ret)
-		return ret;
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetDriverDramAddrLow,
-					  lower_32_bits(table->mc_address));
-	if (ret)
-		return ret;
 	ret = smu_send_smc_msg_with_param(smu, drv2smu ?
 					  SMU_MSG_TransferTableDram2Smu :
 					  SMU_MSG_TransferTableSmu2Dram,
@@ -514,11 +545,10 @@ int smu_update_table(struct smu_context *smu, enum smu_table_id table_index, int
 	if (ret)
 		return ret;
 
-	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
-
-	if (!drv2smu)
-		memcpy(table_data, table->cpu_addr, table->size);
+	if (!drv2smu) {
+		amdgpu_asic_flush_hdp(adev, NULL);
+		memcpy(table_data, table->cpu_addr, table_size);
+	}
 
 	return ret;
 }
@@ -527,9 +557,12 @@ bool is_support_sw_smu(struct amdgpu_device *adev)
 {
 	if (adev->asic_type == CHIP_VEGA20)
 		return (amdgpu_dpm == 2) ? true : false;
-	else if (adev->asic_type >= CHIP_ARCTURUS)
-		return true;
-	else
+	else if (adev->asic_type >= CHIP_ARCTURUS) {
+		if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
+			return false;
+		else
+			return true;
+	} else
 		return false;
 }
 
@@ -637,12 +670,11 @@ int smu_feature_init_dpm(struct smu_context *smu)
 
 int smu_feature_is_enabled(struct smu_context *smu, enum smu_feature_mask mask)
 {
-	struct amdgpu_device *adev = smu->adev;
 	struct smu_feature *feature = &smu->smu_feature;
 	int feature_id;
 	int ret = 0;
 
-	if (adev->flags & AMD_IS_APU)
+	if (smu->is_apu)
 		return 1;
 
 	feature_id = smu_feature_get_index(smu, mask);
@@ -942,32 +974,56 @@ static int smu_init_fb_allocations(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
+	struct smu_table *driver_table = &(smu_table->driver_table);
+	uint32_t max_table_size = 0;
 	int ret, i;
 
-	for (i = 0; i < SMU_TABLE_COUNT; i++) {
-		if (tables[i].size == 0)
-			continue;
+	/* VRAM allocation for tool table */
+	if (tables[SMU_TABLE_PMSTATUSLOG].size) {
 		ret = amdgpu_bo_create_kernel(adev,
-					      tables[i].size,
-					      tables[i].align,
-					      tables[i].domain,
-					      &tables[i].bo,
-					      &tables[i].mc_address,
-					      &tables[i].cpu_addr);
-		if (ret)
-			goto failed;
+					      tables[SMU_TABLE_PMSTATUSLOG].size,
+					      tables[SMU_TABLE_PMSTATUSLOG].align,
+					      tables[SMU_TABLE_PMSTATUSLOG].domain,
+					      &tables[SMU_TABLE_PMSTATUSLOG].bo,
+					      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
+					      &tables[SMU_TABLE_PMSTATUSLOG].cpu_addr);
+		if (ret) {
+			pr_err("VRAM allocation for tool table failed!\n");
+			return ret;
+		}
 	}
 
-	return 0;
-failed:
-	while (--i >= 0) {
+	/* VRAM allocation for driver table */
+	for (i = 0; i < SMU_TABLE_COUNT; i++) {
 		if (tables[i].size == 0)
 			continue;
-		amdgpu_bo_free_kernel(&tables[i].bo,
-				      &tables[i].mc_address,
-				      &tables[i].cpu_addr);
 
+		if (i == SMU_TABLE_PMSTATUSLOG)
+			continue;
+
+		if (max_table_size < tables[i].size)
+			max_table_size = tables[i].size;
+	}
+
+	driver_table->size = max_table_size;
+	driver_table->align = PAGE_SIZE;
+	driver_table->domain = AMDGPU_GEM_DOMAIN_VRAM;
+
+	ret = amdgpu_bo_create_kernel(adev,
+				      driver_table->size,
+				      driver_table->align,
+				      driver_table->domain,
+				      &driver_table->bo,
+				      &driver_table->mc_address,
+				      &driver_table->cpu_addr);
+	if (ret) {
+		pr_err("VRAM allocation for driver table failed!\n");
+		if (tables[SMU_TABLE_PMSTATUSLOG].mc_address)
+			amdgpu_bo_free_kernel(&tables[SMU_TABLE_PMSTATUSLOG].bo,
+					      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
+					      &tables[SMU_TABLE_PMSTATUSLOG].cpu_addr);
 	}
+
 	return ret;
 }
 
@@ -975,18 +1031,19 @@ static int smu_fini_fb_allocations(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
-	uint32_t i = 0;
+	struct smu_table *driver_table = &(smu_table->driver_table);
 
 	if (!tables)
 		return 0;
 
-	for (i = 0; i < SMU_TABLE_COUNT; i++) {
-		if (tables[i].size == 0)
-			continue;
-		amdgpu_bo_free_kernel(&tables[i].bo,
-				      &tables[i].mc_address,
-				      &tables[i].cpu_addr);
-	}
+	if (tables[SMU_TABLE_PMSTATUSLOG].mc_address)
+		amdgpu_bo_free_kernel(&tables[SMU_TABLE_PMSTATUSLOG].bo,
+				      &tables[SMU_TABLE_PMSTATUSLOG].mc_address,
+				      &tables[SMU_TABLE_PMSTATUSLOG].cpu_addr);
+
+	amdgpu_bo_free_kernel(&driver_table->bo,
+			      &driver_table->mc_address,
+			      &driver_table->cpu_addr);
 
 	return 0;
 }
@@ -1056,28 +1113,31 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 	}
 
 	/* smu_dump_pptable(smu); */
+	if (!amdgpu_sriov_vf(adev)) {
+		ret = smu_set_driver_table_location(smu);
+		if (ret)
+			return ret;
 
-	/*
-	 * Copy pptable bo in the vram to smc with SMU MSGs such as
-	 * SetDriverDramAddr and TransferTableDram2Smu.
-	 */
-	ret = smu_write_pptable(smu);
-	if (ret)
-		return ret;
-
-	/* issue Run*Btc msg */
-	ret = smu_run_btc(smu);
-	if (ret)
-		return ret;
-
-	ret = smu_feature_set_allowed_mask(smu);
-	if (ret)
-		return ret;
+		/*
+		 * Copy pptable bo in the vram to smc with SMU MSGs such as
+		 * SetDriverDramAddr and TransferTableDram2Smu.
+		 */
+		ret = smu_write_pptable(smu);
+		if (ret)
+			return ret;
 
-	ret = smu_system_features_control(smu, true);
-	if (ret)
-		return ret;
+		/* issue Run*Btc msg */
+		ret = smu_run_btc(smu);
+		if (ret)
+			return ret;
+		ret = smu_feature_set_allowed_mask(smu);
+		if (ret)
+			return ret;
 
+		ret = smu_system_features_control(smu, true);
+		if (ret)
+			return ret;
+	}
 	if (adev->asic_type != CHIP_ARCTURUS) {
 		ret = smu_notify_display_change(smu);
 		if (ret)
@@ -1130,8 +1190,9 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 	/*
 	 * Set PMSTATUSLOG table bo address with SetToolsDramAddr MSG for tools.
 	 */
-	ret = smu_set_tool_table_location(smu);
-
+	if (!amdgpu_sriov_vf(adev)) {
+		ret = smu_set_tool_table_location(smu);
+	}
 	if (!smu_is_dpm_running(smu))
 		pr_info("dpm has been disabled\n");
 
@@ -1187,10 +1248,9 @@ static int smu_free_memory_pool(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *memory_pool = &smu_table->memory_pool;
-	int ret = 0;
 
 	if (memory_pool->size == SMU_MEMORY_POOL_SIZE_ZERO)
-		return ret;
+		return 0;
 
 	amdgpu_bo_free_kernel(&memory_pool->bo,
 			      &memory_pool->mc_address,
@@ -1198,7 +1258,7 @@ static int smu_free_memory_pool(struct smu_context *smu)
 
 	memset(memory_pool, 0, sizeof(struct smu_table));
 
-	return ret;
+	return 0;
 }
 
 static int smu_start_smc_engine(struct smu_context *smu)
@@ -1237,12 +1297,16 @@ static int smu_hw_init(void *handle)
 		return ret;
 	}
 
-	if (adev->flags & AMD_IS_APU) {
+	if (smu->is_apu) {
 		smu_powergate_sdma(&adev->smu, false);
 		smu_powergate_vcn(&adev->smu, false);
+		smu_powergate_jpeg(&adev->smu, false);
 		smu_set_gfx_cgpg(&adev->smu, true);
 	}
 
+	if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
 	if (!smu->pm_enabled)
 		return 0;
 
@@ -1285,7 +1349,7 @@ failed:
 
 static int smu_stop_dpms(struct smu_context *smu)
 {
-	return smu_send_smc_msg(smu, SMU_MSG_DisableAllSmuFeatures);
+	return smu_system_features_control(smu, false);
 }
 
 static int smu_hw_fini(void *handle)
@@ -1295,36 +1359,45 @@ static int smu_hw_fini(void *handle)
 	struct smu_table_context *table_context = &smu->smu_table;
 	int ret = 0;
 
-	if (adev->flags & AMD_IS_APU) {
+	if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	if (smu->is_apu) {
 		smu_powergate_sdma(&adev->smu, true);
 		smu_powergate_vcn(&adev->smu, true);
+		smu_powergate_jpeg(&adev->smu, true);
 	}
 
-	ret = smu_stop_thermal_control(smu);
-	if (ret) {
-		pr_warn("Fail to stop thermal control!\n");
-		return ret;
-	}
+	if (!smu->pm_enabled)
+		return 0;
 
-	/*
-	 * For custom pptable uploading, skip the DPM features
-	 * disable process on Navi1x ASICs.
-	 *   - As the gfx related features are under control of
-	 *     RLC on those ASICs. RLC reinitialization will be
-	 *     needed to reenable them. That will cost much more
-	 *     efforts.
-	 *
-	 *   - SMU firmware can handle the DPM reenablement
-	 *     properly.
-	 */
-	if (!smu->uploading_custom_pp_table ||
-	    !((adev->asic_type >= CHIP_NAVI10) &&
-	      (adev->asic_type <= CHIP_NAVI12))) {
-		ret = smu_stop_dpms(smu);
+	if (!amdgpu_sriov_vf(adev)){
+		ret = smu_stop_thermal_control(smu);
 		if (ret) {
-			pr_warn("Fail to stop Dpms!\n");
+			pr_warn("Fail to stop thermal control!\n");
 			return ret;
 		}
+
+		/*
+		 * For custom pptable uploading, skip the DPM features
+		 * disable process on Navi1x ASICs.
+		 *   - As the gfx related features are under control of
+		 *     RLC on those ASICs. RLC reinitialization will be
+		 *     needed to reenable them. That will cost much more
+		 *     efforts.
+		 *
+		 *   - SMU firmware can handle the DPM reenablement
+		 *     properly.
+		 */
+		if (!smu->uploading_custom_pp_table ||
+				!((adev->asic_type >= CHIP_NAVI10) &&
+					(adev->asic_type <= CHIP_NAVI12))) {
+			ret = smu_stop_dpms(smu);
+			if (ret) {
+				pr_warn("Fail to stop Dpms!\n");
+				return ret;
+			}
+		}
 	}
 
 	kfree(table_context->driver_pptable);
@@ -1370,14 +1443,17 @@ static int smu_suspend(void *handle)
 	struct smu_context *smu = &adev->smu;
 	bool baco_feature_is_enabled = false;
 
-	if(!(adev->flags & AMD_IS_APU))
+	if (!smu->pm_enabled)
+		return 0;
+
+	if(!smu->is_apu)
 		baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT);
 
 	ret = smu_system_features_control(smu, false);
 	if (ret)
 		return ret;
 
-	if (adev->in_gpu_reset && baco_feature_is_enabled) {
+	if (baco_feature_is_enabled) {
 		ret = smu_feature_set_enabled(smu, SMU_FEATURE_BACO_BIT, true);
 		if (ret) {
 			pr_warn("set BACO feature enabled failed, return %d\n", ret);
@@ -1402,6 +1478,12 @@ static int smu_resume(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = &adev->smu;
 
+	if (amdgpu_sriov_vf(adev)&& !amdgpu_sriov_is_pp_one_vf(adev))
+		return 0;
+
+	if (!smu->pm_enabled)
+		return 0;
+
 	pr_info("SMU is resuming...\n");
 
 	ret = smu_start_smc_engine(smu);
@@ -1600,43 +1682,6 @@ static int smu_enable_umd_pstate(void *handle,
 	return 0;
 }
 
-static int smu_default_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
-{
-	int ret = 0;
-	uint32_t sclk_mask, mclk_mask, soc_mask;
-
-	switch (level) {
-	case AMD_DPM_FORCED_LEVEL_HIGH:
-		ret = smu_force_dpm_limit_value(smu, true);
-		break;
-	case AMD_DPM_FORCED_LEVEL_LOW:
-		ret = smu_force_dpm_limit_value(smu, false);
-		break;
-	case AMD_DPM_FORCED_LEVEL_AUTO:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
-		ret = smu_unforce_dpm_levels(smu);
-		break;
-	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-		ret = smu_get_profiling_clk_mask(smu, level,
-						 &sclk_mask,
-						 &mclk_mask,
-						 &soc_mask);
-		if (ret)
-			return ret;
-		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
-		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
-		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
-		break;
-	case AMD_DPM_FORCED_LEVEL_MANUAL:
-	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
-	default:
-		break;
-	}
-	return ret;
-}
-
 int smu_adjust_power_state_dynamic(struct smu_context *smu,
 				   enum amd_dpm_forced_level level,
 				   bool skip_display_settings)
@@ -1664,7 +1709,7 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu,
 	}
 
 	if (!skip_display_settings) {
-		ret = smu_notify_smc_dispaly_config(smu);
+		ret = smu_notify_smc_display_config(smu);
 		if (ret) {
 			pr_err("Failed to notify smc display config!");
 			return ret;
@@ -1674,11 +1719,8 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu,
 	if (smu_dpm_ctx->dpm_level != level) {
 		ret = smu_asic_set_performance_level(smu, level);
 		if (ret) {
-			ret = smu_default_set_performance_level(smu, level);
-			if (ret) {
-				pr_err("Failed to set performance level!");
-				return ret;
-			}
+			pr_err("Failed to set performance level!");
+			return ret;
 		}
 
 		/* update the saved copy */
@@ -1920,27 +1962,25 @@ int smu_set_df_cstate(struct smu_context *smu,
 
 int smu_write_watermarks_table(struct smu_context *smu)
 {
-	int ret = 0;
-	struct smu_table_context *smu_table = &smu->smu_table;
-	struct smu_table *table = NULL;
-
-	table = &smu_table->tables[SMU_TABLE_WATERMARKS];
+	void *watermarks_table = smu->smu_table.watermarks_table;
 
-	if (!table->cpu_addr)
+	if (!watermarks_table)
 		return -EINVAL;
 
-	ret = smu_update_table(smu, SMU_TABLE_WATERMARKS, 0, table->cpu_addr,
+	return smu_update_table(smu,
+				SMU_TABLE_WATERMARKS,
+				0,
+				watermarks_table,
 				true);
-
-	return ret;
 }
 
 int smu_set_watermarks_for_clock_ranges(struct smu_context *smu,
 		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
 {
-	int ret = 0;
-	struct smu_table *watermarks = &smu->smu_table.tables[SMU_TABLE_WATERMARKS];
-	void *table = watermarks->cpu_addr;
+	void *table = smu->smu_table.watermarks_table;
+
+	if (!table)
+		return -EINVAL;
 
 	mutex_lock(&smu->mutex);
 
@@ -1954,7 +1994,7 @@ int smu_set_watermarks_for_clock_ranges(struct smu_context *smu,
 
 	mutex_unlock(&smu->mutex);
 
-	return ret;
+	return 0;
 }
 
 const struct amd_ip_funcs smu_ip_funcs = {
@@ -2279,13 +2319,9 @@ int smu_set_active_display_count(struct smu_context *smu, uint32_t count)
 {
 	int ret = 0;
 
-	mutex_lock(&smu->mutex);
-
 	if (smu->ppt_funcs->set_active_display_count)
 		ret = smu->ppt_funcs->set_active_display_count(smu, count);
 
-	mutex_unlock(&smu->mutex);
-
 	return ret;
 }
 
@@ -2432,7 +2468,7 @@ bool smu_baco_is_support(struct smu_context *smu)
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->baco_is_support)
+	if (smu->ppt_funcs && smu->ppt_funcs->baco_is_support)
 		ret = smu->ppt_funcs->baco_is_support(smu);
 
 	mutex_unlock(&smu->mutex);
@@ -2452,14 +2488,28 @@ int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state)
 	return 0;
 }
 
-int smu_baco_reset(struct smu_context *smu)
+int smu_baco_enter(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->baco_enter)
+		ret = smu->ppt_funcs->baco_enter(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_baco_exit(struct smu_context *smu)
 {
 	int ret = 0;
 
 	mutex_lock(&smu->mutex);
 
-	if (smu->ppt_funcs->baco_reset)
-		ret = smu->ppt_funcs->baco_reset(smu);
+	if (smu->ppt_funcs->baco_exit)
+		ret = smu->ppt_funcs->baco_exit(smu);
 
 	mutex_unlock(&smu->mutex);
 
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index 472e9fed411a..14ba6aa876e2 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -179,6 +179,7 @@ static struct smu_11_0_cmn2aisc_mapping arcturus_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP(DRIVER_SMU_CONFIG),
 	TAB_MAP(OVERDRIVE),
 	TAB_MAP(I2C_COMMANDS),
+	TAB_MAP(ACTIVITY_MONITOR_COEFF),
 };
 
 static struct smu_11_0_cmn2aisc_mapping arcturus_pwr_src_map[SMU_POWER_SOURCE_COUNT] = {
@@ -280,10 +281,8 @@ static int arcturus_get_workload_type(struct smu_context *smu, enum PP_SMC_POWER
 		return -EINVAL;
 
 	mapping = arcturus_workload_map[profile];
-	if (!(mapping.valid_mapping)) {
-		pr_warn("Unsupported SMU power source: %d\n", profile);
+	if (!(mapping.valid_mapping))
 		return -EINVAL;
-	}
 
 	return mapping.map_to;
 }
@@ -304,6 +303,10 @@ static int arcturus_tables_init(struct smu_context *smu, struct smu_table *table
 	SMU_TABLE_INIT(tables, SMU_TABLE_I2C_COMMANDS, sizeof(SwI2cRequest_t),
 			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 
+	SMU_TABLE_INIT(tables, SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+		       sizeof(DpmActivityMonitorCoeffInt_t), PAGE_SIZE,
+		       AMDGPU_GEM_DOMAIN_VRAM);
+
 	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
 	if (!smu_table->metrics_table)
 		return -ENOMEM;
@@ -495,6 +498,7 @@ static int arcturus_store_powerplay_table(struct smu_context *smu)
 {
 	struct smu_11_0_powerplay_table *powerplay_table = NULL;
 	struct smu_table_context *table_context = &smu->smu_table;
+	struct smu_baco_context *smu_baco = &smu->smu_baco;
 	int ret = 0;
 
 	if (!table_context->power_play_table)
@@ -507,6 +511,12 @@ static int arcturus_store_powerplay_table(struct smu_context *smu)
 
 	table_context->thermal_controller_type = powerplay_table->thermal_controller_type;
 
+	mutex_lock(&smu_baco->mutex);
+	if (powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_BACO ||
+	    powerplay_table->platform_caps & SMU_11_0_PP_PLATFORM_CAP_MACO)
+		smu_baco->platform_support = true;
+	mutex_unlock(&smu_baco->mutex);
+
 	return ret;
 }
 
@@ -1308,6 +1318,8 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 static int arcturus_get_power_profile_mode(struct smu_context *smu,
 					   char *buf)
 {
+	struct amdgpu_device *adev = smu->adev;
+	DpmActivityMonitorCoeffInt_t activity_monitor;
 	static const char *profile_name[] = {
 					"BOOTUP_DEFAULT",
 					"3D_FULL_SCREEN",
@@ -1317,14 +1329,35 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 					"COMPUTE",
 					"CUSTOM"};
 	static const char *title[] = {
-			"PROFILE_INDEX(NAME)"};
+			"PROFILE_INDEX(NAME)",
+			"CLOCK_TYPE(NAME)",
+			"FPS",
+			"UseRlcBusy",
+			"MinActiveFreqType",
+			"MinActiveFreq",
+			"BoosterFreqType",
+			"BoosterFreq",
+			"PD_Data_limit_c",
+			"PD_Data_error_coeff",
+			"PD_Data_error_rate_coeff"};
 	uint32_t i, size = 0;
 	int16_t workload_type = 0;
+	int result = 0;
+	uint32_t smu_version;
 
-	if (!smu->pm_enabled || !buf)
+	if (!buf)
 		return -EINVAL;
 
-	size += sprintf(buf + size, "%16s\n",
+	result = smu_get_smc_version(smu, NULL, &smu_version);
+	if (result)
+		return result;
+
+	if (smu_version >= 0x360d00 && !amdgpu_sriov_vf(adev))
+		size += sprintf(buf + size, "%16s %s %s %s %s %s %s %s %s %s %s\n",
+			title[0], title[1], title[2], title[3], title[4], title[5],
+			title[6], title[7], title[8], title[9], title[10]);
+	else
+		size += sprintf(buf + size, "%16s\n",
 			title[0]);
 
 	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
@@ -1336,8 +1369,50 @@ static int arcturus_get_power_profile_mode(struct smu_context *smu,
 		if (workload_type < 0)
 			continue;
 
+		if (smu_version >= 0x360d00 && !amdgpu_sriov_vf(adev)) {
+			result = smu_update_table(smu,
+						  SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+						  workload_type,
+						  (void *)(&activity_monitor),
+						  false);
+			if (result) {
+				pr_err("[%s] Failed to get activity monitor!", __func__);
+				return result;
+			}
+		}
+
 		size += sprintf(buf + size, "%2d %14s%s\n",
 			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
+
+		if (smu_version >= 0x360d00 && !amdgpu_sriov_vf(adev)) {
+			size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+				" ",
+				0,
+				"GFXCLK",
+				activity_monitor.Gfx_FPS,
+				activity_monitor.Gfx_UseRlcBusy,
+				activity_monitor.Gfx_MinActiveFreqType,
+				activity_monitor.Gfx_MinActiveFreq,
+				activity_monitor.Gfx_BoosterFreqType,
+				activity_monitor.Gfx_BoosterFreq,
+				activity_monitor.Gfx_PD_Data_limit_c,
+				activity_monitor.Gfx_PD_Data_error_coeff,
+				activity_monitor.Gfx_PD_Data_error_rate_coeff);
+
+			size += sprintf(buf + size, "%19s %d(%13s) %7d %7d %7d %7d %7d %7d %7d %7d %7d\n",
+				" ",
+				1,
+				"UCLK",
+				activity_monitor.Mem_FPS,
+				activity_monitor.Mem_UseRlcBusy,
+				activity_monitor.Mem_MinActiveFreqType,
+				activity_monitor.Mem_MinActiveFreq,
+				activity_monitor.Mem_BoosterFreqType,
+				activity_monitor.Mem_BoosterFreq,
+				activity_monitor.Mem_PD_Data_limit_c,
+				activity_monitor.Mem_PD_Data_error_coeff,
+				activity_monitor.Mem_PD_Data_error_rate_coeff);
+		}
 	}
 
 	return size;
@@ -1347,18 +1422,69 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
 					   long *input,
 					   uint32_t size)
 {
+	DpmActivityMonitorCoeffInt_t activity_monitor;
 	int workload_type = 0;
 	uint32_t profile_mode = input[size];
 	int ret = 0;
-
-	if (!smu->pm_enabled)
-		return -EINVAL;
+	uint32_t smu_version;
 
 	if (profile_mode > PP_SMC_POWER_PROFILE_CUSTOM) {
 		pr_err("Invalid power profile mode %d\n", profile_mode);
 		return -EINVAL;
 	}
 
+	ret = smu_get_smc_version(smu, NULL, &smu_version);
+	if (ret)
+		return ret;
+
+	if ((profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) &&
+	     (smu_version >=0x360d00)) {
+		ret = smu_update_table(smu,
+				       SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+				       WORKLOAD_PPLIB_CUSTOM_BIT,
+				       (void *)(&activity_monitor),
+				       false);
+		if (ret) {
+			pr_err("[%s] Failed to get activity monitor!", __func__);
+			return ret;
+		}
+
+		switch (input[0]) {
+		case 0: /* Gfxclk */
+			activity_monitor.Gfx_FPS = input[1];
+			activity_monitor.Gfx_UseRlcBusy = input[2];
+			activity_monitor.Gfx_MinActiveFreqType = input[3];
+			activity_monitor.Gfx_MinActiveFreq = input[4];
+			activity_monitor.Gfx_BoosterFreqType = input[5];
+			activity_monitor.Gfx_BoosterFreq = input[6];
+			activity_monitor.Gfx_PD_Data_limit_c = input[7];
+			activity_monitor.Gfx_PD_Data_error_coeff = input[8];
+			activity_monitor.Gfx_PD_Data_error_rate_coeff = input[9];
+			break;
+		case 1: /* Uclk */
+			activity_monitor.Mem_FPS = input[1];
+			activity_monitor.Mem_UseRlcBusy = input[2];
+			activity_monitor.Mem_MinActiveFreqType = input[3];
+			activity_monitor.Mem_MinActiveFreq = input[4];
+			activity_monitor.Mem_BoosterFreqType = input[5];
+			activity_monitor.Mem_BoosterFreq = input[6];
+			activity_monitor.Mem_PD_Data_limit_c = input[7];
+			activity_monitor.Mem_PD_Data_error_coeff = input[8];
+			activity_monitor.Mem_PD_Data_error_rate_coeff = input[9];
+			break;
+		}
+
+		ret = smu_update_table(smu,
+				       SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+				       WORKLOAD_PPLIB_CUSTOM_BIT,
+				       (void *)(&activity_monitor),
+				       true);
+		if (ret) {
+			pr_err("[%s] Failed to set activity monitor!", __func__);
+			return ret;
+		}
+	}
+
 	/*
 	 * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT
 	 * Not all profile modes are supported on arcturus.
@@ -1897,7 +2023,7 @@ static int arcturus_i2c_eeprom_read_data(struct i2c_adapter *control,
 	SwI2cRequest_t req;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 	struct smu_table_context *smu_table = &adev->smu.smu_table;
-	struct smu_table *table = &smu_table->tables[SMU_TABLE_I2C_COMMANDS];
+	struct smu_table *table = &smu_table->driver_table;
 
 	memset(&req, 0, sizeof(req));
 	arcturus_fill_eeprom_i2c_req(&req, false, address, numbytes, data);
@@ -2051,8 +2177,12 @@ static const struct i2c_algorithm arcturus_i2c_eeprom_i2c_algo = {
 static int arcturus_i2c_eeprom_control_init(struct i2c_adapter *control)
 {
 	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct smu_context *smu = &adev->smu;
 	int res;
 
+	if (!smu->pm_enabled)
+		return -EOPNOTSUPP;
+
 	control->owner = THIS_MODULE;
 	control->class = I2C_CLASS_SPD;
 	control->dev.parent = &adev->pdev->dev;
@@ -2068,6 +2198,12 @@ static int arcturus_i2c_eeprom_control_init(struct i2c_adapter *control)
 
 static void arcturus_i2c_eeprom_control_fini(struct i2c_adapter *control)
 {
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct smu_context *smu = &adev->smu;
+
+	if (!smu->pm_enabled)
+		return;
+
 	i2c_del_adapter(control);
 }
 
@@ -2112,6 +2248,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.get_profiling_clk_mask = arcturus_get_profiling_clk_mask,
 	.get_power_profile_mode = arcturus_get_power_profile_mode,
 	.set_power_profile_mode = arcturus_set_power_profile_mode,
+	.set_performance_level = smu_v11_0_set_performance_level,
 	/* debug (internal used) */
 	.dump_pptable = arcturus_dump_pptable,
 	.get_power_limit = arcturus_get_power_limit,
@@ -2135,6 +2272,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.write_pptable = smu_v11_0_write_pptable,
 	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
@@ -2163,7 +2301,8 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.baco_is_support= smu_v11_0_baco_is_support,
 	.baco_get_state = smu_v11_0_baco_get_state,
 	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
+	.baco_enter = smu_v11_0_baco_enter,
+	.baco_exit = smu_v11_0_baco_exit,
 	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index cc57fb953e62..9454ab50f9a1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -81,8 +81,8 @@ int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 	adev = hwmgr->adev;
 
 	/* Skip for suspend/resume case */
-	if (smum_is_dpm_running(hwmgr) && !amdgpu_passthrough(adev)
-		&& adev->in_suspend) {
+	if (!hwmgr->pp_one_vf && smum_is_dpm_running(hwmgr)
+	    && !amdgpu_passthrough(adev) && adev->in_suspend) {
 		pr_info("dpm has been enabled\n");
 		return 0;
 	}
@@ -99,6 +99,9 @@ int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr)
 
 	PHM_FUNC_CHECK(hwmgr);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (!smum_is_dpm_running(hwmgr)) {
 		pr_info("dpm has been disabled\n");
 		return 0;
@@ -200,6 +203,9 @@ int phm_stop_thermal_controller(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (hwmgr->hwmgr_func->stop_thermal_controller == NULL)
 		return -EINVAL;
 
@@ -237,6 +243,9 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 		TEMP_RANGE_MAX};
 	struct amdgpu_device *adev = hwmgr->adev;
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (hwmgr->hwmgr_func->get_thermal_temperature_range)
 		hwmgr->hwmgr_func->get_thermal_temperature_range(
 				hwmgr, &range);
@@ -263,6 +272,8 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 bool phm_check_smc_update_required_for_display_configuration(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
+	if (hwmgr->pp_one_vf)
+		return false;
 
 	if (hwmgr->hwmgr_func->check_smc_update_required_for_display_configuration == NULL)
 		return false;
@@ -482,6 +493,9 @@ int phm_disable_smc_firmware_ctf(struct pp_hwmgr *hwmgr)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (hwmgr->hwmgr_func->disable_smc_firmware_ctf == NULL)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index d2909c91d65b..f48fdc7f0382 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -221,6 +221,9 @@ int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
+	hwmgr->pp_one_vf = amdgpu_sriov_is_pp_one_vf((struct amdgpu_device *)hwmgr->adev);
+	hwmgr->pm_en = (amdgpu_dpm && (hwmgr->not_vf || hwmgr->pp_one_vf))
+			? true : false;
 	if (!hwmgr->pm_en)
 		return 0;
 
@@ -279,7 +282,7 @@ err:
 
 int hwmgr_hw_fini(struct pp_hwmgr *hwmgr)
 {
-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->not_vf)
 		return 0;
 
 	phm_stop_thermal_controller(hwmgr);
@@ -299,7 +302,7 @@ int hwmgr_suspend(struct pp_hwmgr *hwmgr)
 {
 	int ret = 0;
 
-	if (!hwmgr || !hwmgr->pm_en)
+	if (!hwmgr || !hwmgr->pm_en || !hwmgr->not_vf)
 		return 0;
 
 	phm_disable_smc_firmware_ctf(hwmgr);
@@ -321,7 +324,7 @@ int hwmgr_resume(struct pp_hwmgr *hwmgr)
 	if (!hwmgr)
 		return -EINVAL;
 
-	if (!hwmgr->pm_en)
+	if (!hwmgr->not_vf || !hwmgr->pm_en)
 		return 0;
 
 	ret = phm_setup_asic(hwmgr);
@@ -365,6 +368,8 @@ int hwmgr_handle_task(struct pp_hwmgr *hwmgr, enum amd_pp_task task_id,
 
 	switch (task_id) {
 	case AMD_PP_TASK_DISPLAY_CONFIG_CHANGE:
+		if (!hwmgr->not_vf)
+			return ret;
 		ret = phm_pre_display_configuration_changed(hwmgr);
 		if (ret)
 			return ret;
@@ -381,6 +386,8 @@ int hwmgr_handle_task(struct pp_hwmgr *hwmgr, enum amd_pp_task task_id,
 		enum PP_StateUILabel requested_ui_label;
 		struct pp_power_state *requested_ps = NULL;
 
+		if (!hwmgr->not_vf)
+			return ret;
 		if (user_state == NULL) {
 			ret = -EINVAL;
 			break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
index 6bf48934fdc4..31a32a79cfc2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_psm.c
@@ -262,20 +262,22 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set
 	uint32_t index;
 	long workload;
 
-	if (!skip_display_settings)
-		phm_display_configuration_changed(hwmgr);
-
-	if (hwmgr->ps)
-		power_state_management(hwmgr, new_ps);
-	else
-		/*
-		 * for vega12/vega20 which does not support power state manager
-		 * DAL clock limits should also be honoured
-		 */
-		phm_apply_clock_adjust_rules(hwmgr);
-
-	if (!skip_display_settings)
-		phm_notify_smc_display_config_after_ps_adjustment(hwmgr);
+	if (hwmgr->not_vf) {
+		if (!skip_display_settings)
+			phm_display_configuration_changed(hwmgr);
+
+		if (hwmgr->ps)
+			power_state_management(hwmgr, new_ps);
+		else
+			/*
+			 * for vega12/vega20 which does not support power state manager
+			 * DAL clock limits should also be honoured
+			 */
+			phm_apply_clock_adjust_rules(hwmgr);
+
+		if (!skip_display_settings)
+			phm_notify_smc_display_config_after_ps_adjustment(hwmgr);
+	}
 
 	if (!phm_force_dpm_levels(hwmgr, hwmgr->request_dpm_level))
 		hwmgr->dpm_level = hwmgr->request_dpm_level;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 1115761982a7..4e8ab139bb3b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1151,12 +1151,11 @@ static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct smu10_hwmgr *data = hwmgr->backend;
 	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	Watermarks_t *table = &(data->water_marks_table);
-	int result = 0;
 
 	smu_set_watermarks_for_clocks_ranges(table,wm_with_clock_ranges);
 	smum_smc_table_manager(hwmgr, (uint8_t *)table, (uint16_t)SMU10_WMTABLE, false);
 	data->water_marks_exist = true;
-	return result;
+	return 0;
 }
 
 static int smu10_smus_notify_pwe(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index f73dff68e799..d70abada66bf 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -4238,7 +4238,6 @@ static int smu7_check_mc_firmware(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
-	uint32_t vbios_version;
 	uint32_t tmp;
 
 	/* Read MC indirect register offset 0x9F bits [3:0] to see
@@ -4247,7 +4246,6 @@ static int smu7_check_mc_firmware(struct pp_hwmgr *hwmgr)
 	 */
 
 	smu7_get_mc_microcode_version(hwmgr);
-	vbios_version = hwmgr->microcode_version_info.MC & 0xf;
 
 	data->need_long_memory_training = false;
 
@@ -4945,7 +4943,7 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 			title[0], title[1], title[2], title[3],
 			title[4], title[5], title[6], title[7]);
 
-	len = sizeof(smu7_profiling) / sizeof(struct profile_mode_setting);
+	len = ARRAY_SIZE(smu7_profiling);
 
 	for (i = 0; i < len; i++) {
 		if (i == hwmgr->power_profile_mode) {
@@ -5077,13 +5075,11 @@ static int smu7_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_hw
 				PHM_PerformanceLevel *level)
 {
 	const struct smu7_power_state *ps;
-	struct smu7_hwmgr *data;
 	uint32_t i;
 
 	if (level == NULL || hwmgr == NULL || state == NULL)
 		return -EINVAL;
 
-	data = hwmgr->backend;
 	ps = cast_const_phw_smu7_power_state(state);
 
 	i = index > ps->performance_level_count - 1 ?
@@ -5189,13 +5185,11 @@ uint8_t smu7_get_sleep_divider_id_from_clock(uint32_t clock,
 
 int smu7_init_function_pointers(struct pp_hwmgr *hwmgr)
 {
-	int ret = 0;
-
 	hwmgr->hwmgr_func = &smu7_hwmgr_funcs;
 	if (hwmgr->pp_table_version == PP_TABLE_V0)
 		hwmgr->pptable_func = &pptable_funcs;
 	else if (hwmgr->pp_table_version == PP_TABLE_V1)
 		hwmgr->pptable_func = &pptable_v1_0_funcs;
 
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d71a492c87a3..92a65e3daff4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -912,6 +912,9 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 	hwmgr->platform_descriptor.clockStep.memoryClock = 500;
 
 	data->total_active_cus = adev->gfx.cu_info.number;
+	if (!hwmgr->not_vf)
+		return result;
+
 	/* Setup default Overdrive Fan control settings */
 	data->odn_fan_table.target_fan_speed =
 			hwmgr->thermal_controller.advanceFanControlParameters.usMaxFanRPM;
@@ -979,6 +982,9 @@ static int vega10_setup_dpm_led_config(struct pp_hwmgr *hwmgr)
 
 static int vega10_setup_asic_task(struct pp_hwmgr *hwmgr)
 {
+	if (!hwmgr->not_vf)
+		return 0;
+
 	PP_ASSERT_WITH_CODE(!vega10_init_sclk_threshold(hwmgr),
 			"Failed to init sclk threshold!",
 			return -EINVAL);
@@ -2503,6 +2509,9 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			"Failed to setup default DPM tables!",
 			return result);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	/* initialize ODN table */
 	if (hwmgr->od_enabled) {
 		if (odn_table->max_vddc) {
@@ -2826,6 +2835,8 @@ static int vega10_stop_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap)
 	struct vega10_hwmgr *data = hwmgr->backend;
 	uint32_t i, feature_mask = 0;
 
+	if (!hwmgr->not_vf)
+		return 0;
 
 	if(data->smu_features[GNLD_LED_DISPLAY].supported == true){
 		PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
@@ -2932,61 +2943,73 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 	struct vega10_hwmgr *data = hwmgr->backend;
 	int tmp_result, result = 0;
 
-	vega10_enable_disable_PCC_limit_feature(hwmgr, true);
-
-	smum_send_msg_to_smc_with_parameter(hwmgr,
-		PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
+	if (hwmgr->not_vf) {
+		vega10_enable_disable_PCC_limit_feature(hwmgr, true);
 
-	tmp_result = vega10_construct_voltage_tables(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to construct voltage tables!",
-			result = tmp_result);
+		smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
 
-	tmp_result = vega10_init_smc_table(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to initialize SMC table!",
-			result = tmp_result);
+		tmp_result = vega10_construct_voltage_tables(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to construct voltage tables!",
+				    result = tmp_result);
+	}
 
-	if (PP_CAP(PHM_PlatformCaps_ThermalController)) {
-		tmp_result = vega10_enable_thermal_protection(hwmgr);
+	if (hwmgr->not_vf || hwmgr->pp_one_vf) {
+		tmp_result = vega10_init_smc_table(hwmgr);
 		PP_ASSERT_WITH_CODE(!tmp_result,
-				"Failed to enable thermal protection!",
-				result = tmp_result);
+				    "Failed to initialize SMC table!",
+				    result = tmp_result);
 	}
 
-	tmp_result = vega10_enable_vrhot_feature(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable VR hot feature!",
-			result = tmp_result);
+	if (hwmgr->not_vf) {
+		if (PP_CAP(PHM_PlatformCaps_ThermalController)) {
+			tmp_result = vega10_enable_thermal_protection(hwmgr);
+			PP_ASSERT_WITH_CODE(!tmp_result,
+					    "Failed to enable thermal protection!",
+					    result = tmp_result);
+		}
 
-	tmp_result = vega10_enable_deep_sleep_master_switch(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable deep sleep master switch!",
-			result = tmp_result);
+		tmp_result = vega10_enable_vrhot_feature(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to enable VR hot feature!",
+				    result = tmp_result);
 
-	tmp_result = vega10_start_dpm(hwmgr, SMC_DPM_FEATURES);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to start DPM!", result = tmp_result);
+		tmp_result = vega10_enable_deep_sleep_master_switch(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to enable deep sleep master switch!",
+				    result = tmp_result);
+	}
 
-	/* enable didt, do not abort if failed didt */
-	tmp_result = vega10_enable_didt_config(hwmgr);
-	PP_ASSERT(!tmp_result,
-			"Failed to enable didt config!");
+	if (hwmgr->not_vf) {
+		tmp_result = vega10_start_dpm(hwmgr, SMC_DPM_FEATURES);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to start DPM!", result = tmp_result);
+	}
+
+	if (hwmgr->not_vf) {
+		/* enable didt, do not abort if failed didt */
+		tmp_result = vega10_enable_didt_config(hwmgr);
+		PP_ASSERT(!tmp_result,
+			  "Failed to enable didt config!");
+	}
 
 	tmp_result = vega10_enable_power_containment(hwmgr);
 	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable power containment!",
-			result = tmp_result);
+			    "Failed to enable power containment!",
+			    result = tmp_result);
 
-	tmp_result = vega10_power_control_set_level(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to power control set level!",
-			result = tmp_result);
+	if (hwmgr->not_vf) {
+		tmp_result = vega10_power_control_set_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to power control set level!",
+				    result = tmp_result);
 
-	tmp_result = vega10_enable_ulv(hwmgr);
-	PP_ASSERT_WITH_CODE(!tmp_result,
-			"Failed to enable ULV!",
-			result = tmp_result);
+		tmp_result = vega10_enable_ulv(hwmgr);
+		PP_ASSERT_WITH_CODE(!tmp_result,
+				    "Failed to enable ULV!",
+				    result = tmp_result);
+	}
 
 	return result;
 }
@@ -3080,11 +3103,22 @@ static int vega10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr,
 	performance_level->soc_clock = socclk_dep_table->entries
 				[state_entry->ucSocClockIndexHigh].ulClk;
 	if (gfxclk_dep_table->ucRevId == 0) {
-		performance_level->gfx_clock = gfxclk_dep_table->entries
-			[state_entry->ucGfxClockIndexHigh].ulClk;
+		/* under vega10 pp one vf mode, the gfx clk dpm need be lower
+		 * to level-4 due to the limited 110w-power
+		 */
+		if (hwmgr->pp_one_vf && (state_entry->ucGfxClockIndexHigh > 0))
+			performance_level->gfx_clock =
+				gfxclk_dep_table->entries[4].ulClk;
+		else
+			performance_level->gfx_clock = gfxclk_dep_table->entries
+				[state_entry->ucGfxClockIndexHigh].ulClk;
 	} else if (gfxclk_dep_table->ucRevId == 1) {
 		patom_record_V2 = (ATOM_Vega10_GFXCLK_Dependency_Record_V2 *)gfxclk_dep_table->entries;
-		performance_level->gfx_clock = patom_record_V2[state_entry->ucGfxClockIndexHigh].ulClk;
+		if (hwmgr->pp_one_vf && (state_entry->ucGfxClockIndexHigh > 0))
+			performance_level->gfx_clock = patom_record_V2[4].ulClk;
+		else
+			performance_level->gfx_clock =
+				patom_record_V2[state_entry->ucGfxClockIndexHigh].ulClk;
 	}
 
 	performance_level->mem_clock = mclk_dep_table->entries
@@ -3495,6 +3529,7 @@ static int vega10_upload_dpm_bootup_level(struct pp_hwmgr *hwmgr)
 			smum_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetSoftMinGfxclkByIndex,
 				data->smc_state_table.gfx_boot_level);
+
 			data->dpm_table.gfx_table.dpm_state.soft_min_level =
 					data->smc_state_table.gfx_boot_level;
 		}
@@ -3503,7 +3538,8 @@ static int vega10_upload_dpm_bootup_level(struct pp_hwmgr *hwmgr)
 	if (!data->registry_data.mclk_dpm_key_disabled) {
 		if (data->smc_state_table.mem_boot_level !=
 				data->dpm_table.mem_table.dpm_state.soft_min_level) {
-			if (data->smc_state_table.mem_boot_level == NUM_UCLK_DPM_LEVELS - 1) {
+			if ((data->smc_state_table.mem_boot_level == NUM_UCLK_DPM_LEVELS - 1)
+			    && hwmgr->not_vf) {
 				socclk_idx = vega10_get_soc_index_for_max_uclk(hwmgr);
 				smum_send_msg_to_smc_with_parameter(hwmgr,
 						PPSMC_MSG_SetSoftMinSocclkByIndex,
@@ -3518,6 +3554,9 @@ static int vega10_upload_dpm_bootup_level(struct pp_hwmgr *hwmgr)
 		}
 	}
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (!data->registry_data.socclk_dpm_key_disabled) {
 		if (data->smc_state_table.soc_boot_level !=
 				data->dpm_table.soc_table.dpm_state.soft_min_level) {
@@ -3560,6 +3599,9 @@ static int vega10_upload_dpm_max_level(struct pp_hwmgr *hwmgr)
 		}
 	}
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (!data->registry_data.socclk_dpm_key_disabled) {
 		if (data->smc_state_table.soc_max_level !=
 			data->dpm_table.soc_table.dpm_state.soft_max_level) {
@@ -4054,15 +4096,25 @@ static int vega10_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
 		*mclk_mask = 0;
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
-		*sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
+		/* under vega10  pp one vf mode, the gfx clk dpm need be lower
+		 * to level-4 due to the limited power
+		 */
+		if (hwmgr->pp_one_vf)
+			*sclk_mask = 4;
+		else
+			*sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
 		*soc_mask = table_info->vdd_dep_on_socclk->count - 1;
 		*mclk_mask = table_info->vdd_dep_on_mclk->count - 1;
 	}
+
 	return 0;
 }
 
 static void vega10_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
+	if (!hwmgr->not_vf)
+		return;
+
 	switch (mode) {
 	case AMD_FAN_CTRL_NONE:
 		vega10_fan_ctrl_set_fan_speed_percent(hwmgr, 100);
@@ -4176,6 +4228,9 @@ static int vega10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 		break;
 	}
 
+	if (!hwmgr->not_vf)
+		return ret;
+
 	if (!ret) {
 		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
 			vega10_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_NONE);
@@ -4360,14 +4415,13 @@ static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct vega10_hwmgr *data = hwmgr->backend;
 	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_range;
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
-	int result = 0;
 
 	if (!data->registry_data.disable_water_mark) {
 		smu_set_watermarks_for_clocks_ranges(table, wm_with_clock_ranges);
 		data->water_marks_bitmap = WaterMarksExist;
 	}
 
-	return result;
+	return 0;
 }
 
 static int vega10_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
@@ -4480,7 +4534,7 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 	struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table);
 	struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL;
 
-	int i, now, size = 0;
+	int i, now, size = 0, count = 0;
 
 	switch (type) {
 	case PP_SCLK:
@@ -4490,7 +4544,12 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex);
 		now = smum_get_argument(hwmgr);
 
-		for (i = 0; i < sclk_table->count; i++)
+		if (hwmgr->pp_one_vf &&
+		    (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK))
+			count = 5;
+		else
+			count = sclk_table->count;
+		for (i = 0; i < count; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 					i, sclk_table->dpm_levels[i].value / 100,
 					(i == now) ? "*" : "");
@@ -4701,6 +4760,9 @@ static int vega10_disable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (PP_CAP(PHM_PlatformCaps_ThermalController))
 		vega10_disable_thermal_protection(hwmgr);
 
@@ -5252,13 +5314,11 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_
 				PHM_PerformanceLevel *level)
 {
 	const struct vega10_power_state *ps;
-	struct vega10_hwmgr *data;
 	uint32_t i;
 
 	if (level == NULL || hwmgr == NULL || state == NULL)
 		return -EINVAL;
 
-	data = hwmgr->backend;
 	ps = cast_const_phw_vega10_power_state(state);
 
 	i = index > ps->performance_level_count - 1 ?
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
index 6f26cb241ecc..0a677d4bc87b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_powertune.c
@@ -1343,6 +1343,9 @@ int vega10_enable_power_containment(struct pp_hwmgr *hwmgr)
 	hwmgr->default_power_limit = hwmgr->power_limit =
 			(uint32_t)(tdp_table->usMaximumPowerDeliveryLimit);
 
+	if (!hwmgr->not_vf)
+		return 0;
+
 	if (PP_CAP(PHM_PlatformCaps_PowerContainment)) {
 		if (data->smu_features[GNLD_PPT].supported)
 			PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 7af9ad450ac4..aca61d1ff3c2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -499,8 +499,6 @@ static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
 static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		PPCLK_e clkID, uint32_t index, uint32_t *clock)
 {
-	int result = 0;
-
 	/*
 	 *SMU expects the Clock ID to be in the top 16 bits.
 	 *Lower 16 bits specify the level
@@ -512,7 +510,7 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 
 	*clock = smum_get_argument(hwmgr);
 
-	return result;
+	return 0;
 }
 
 static int vega12_setup_single_dpm_table(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index 5bcf0d684151..3b3ec5666051 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -872,7 +872,7 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr)
 		"[OverridePcieParameters] Attempt to override pcie params failed!",
 		return ret);
 
-	data->pcie_parameters_override = 1;
+	data->pcie_parameters_override = true;
 	data->pcie_gen_level1 = pcie_gen;
 	data->pcie_width_level1 = pcie_width;
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 41fce75b263f..b0591a8dda41 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -254,11 +254,21 @@ struct smu_table_context
 	unsigned long			metrics_time;
 	void				*metrics_table;
 	void				*clocks_table;
+	void				*watermarks_table;
 
 	void				*max_sustainable_clocks;
 	struct smu_bios_boot_up_values	boot_values;
 	void                            *driver_pptable;
 	struct smu_table		*tables;
+	/*
+	 * The driver table is just a staging buffer for
+	 * uploading/downloading content from the SMU.
+	 *
+	 * And the table_id for SMU_MSG_TransferTableSmu2Dram/
+	 * SMU_MSG_TransferTableDram2Smu instructs SMU
+	 * which content driver is interested.
+	 */
+	struct smu_table		driver_table;
 	struct smu_table		memory_pool;
 	uint8_t                         thermal_controller_type;
 
@@ -282,6 +292,7 @@ struct smu_power_gate {
 	bool uvd_gated;
 	bool vce_gated;
 	bool vcn_gated;
+	bool jpeg_gated;
 };
 
 struct smu_power_context {
@@ -437,12 +448,13 @@ struct pptable_funcs {
 	int (*set_power_profile_mode)(struct smu_context *smu, long *input, uint32_t size);
 	int (*dpm_set_uvd_enable)(struct smu_context *smu, bool enable);
 	int (*dpm_set_vce_enable)(struct smu_context *smu, bool enable);
+	int (*dpm_set_jpeg_enable)(struct smu_context *smu, bool enable);
 	int (*read_sensor)(struct smu_context *smu, enum amd_pp_sensors sensor,
 			   void *data, uint32_t *size);
 	int (*pre_display_config_changed)(struct smu_context *smu);
 	int (*display_config_changed)(struct smu_context *smu);
 	int (*apply_clocks_adjust_rules)(struct smu_context *smu);
-	int (*notify_smc_dispaly_config)(struct smu_context *smu);
+	int (*notify_smc_display_config)(struct smu_context *smu);
 	int (*force_dpm_limit_value)(struct smu_context *smu, bool highest);
 	int (*unforce_dpm_levels)(struct smu_context *smu);
 	int (*get_profiling_clk_mask)(struct smu_context *smu,
@@ -491,9 +503,11 @@ struct pptable_funcs {
 	int (*check_fw_version)(struct smu_context *smu);
 	int (*powergate_sdma)(struct smu_context *smu, bool gate);
 	int (*powergate_vcn)(struct smu_context *smu, bool gate);
+	int (*powergate_jpeg)(struct smu_context *smu, bool gate);
 	int (*set_gfx_cgpg)(struct smu_context *smu, bool enable);
 	int (*write_pptable)(struct smu_context *smu);
 	int (*set_min_dcef_deep_sleep)(struct smu_context *smu);
+	int (*set_driver_table_location)(struct smu_context *smu);
 	int (*set_tool_table_location)(struct smu_context *smu);
 	int (*notify_memory_pool_location)(struct smu_context *smu);
 	int (*set_last_dcef_min_deep_sleep_clk)(struct smu_context *smu);
@@ -544,7 +558,8 @@ struct pptable_funcs {
 	bool (*baco_is_support)(struct smu_context *smu);
 	enum smu_baco_state (*baco_get_state)(struct smu_context *smu);
 	int (*baco_set_state)(struct smu_context *smu, enum smu_baco_state state);
-	int (*baco_reset)(struct smu_context *smu);
+	int (*baco_enter)(struct smu_context *smu);
+	int (*baco_exit)(struct smu_context *smu);
 	int (*mode2_reset)(struct smu_context *smu);
 	int (*get_dpm_ultimate_freq)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max);
 	int (*set_soft_freq_limited_range)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t min, uint32_t max);
@@ -626,7 +641,8 @@ bool smu_baco_is_support(struct smu_context *smu);
 
 int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state);
 
-int smu_baco_reset(struct smu_context *smu);
+int smu_baco_enter(struct smu_context *smu);
+int smu_baco_exit(struct smu_context *smu);
 
 int smu_mode2_reset(struct smu_context *smu);
 
@@ -692,6 +708,8 @@ int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
 int smu_set_hard_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
+int smu_get_dpm_level_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t *min_value, uint32_t *max_value);
 enum amd_dpm_forced_level smu_get_performance_level(struct smu_context *smu);
 int smu_force_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level);
 int smu_set_display_count(struct smu_context *smu, uint32_t count);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index af977675fd33..2ffb666b97e6 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -741,6 +741,7 @@ struct pp_hwmgr {
 	uint32_t smu_version;
 	bool not_vf;
 	bool pm_en;
+	bool pp_one_vf;
 	struct mutex smu_lock;
 
 	uint32_t pp_table_version;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
index a886f0644d24..ce5b5011c122 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
@@ -622,8 +622,14 @@ typedef struct {
   uint16_t     PccThresholdHigh;
   uint32_t     PaddingAPCC[6];  //FIXME pending SPEC
 
+  // OOB Settings
+  uint16_t BasePerformanceCardPower;
+  uint16_t MaxPerformanceCardPower;
+  uint16_t BasePerformanceFrequencyCap;   //In Mhz
+  uint16_t MaxPerformanceFrequencyCap;    //In Mhz
+
   // SECTION: Reserved
-  uint32_t     Reserved[11];
+  uint32_t     Reserved[9];
 
   // SECTION: BOARD PARAMETERS
 
@@ -823,7 +829,6 @@ typedef struct {
   uint32_t MmHubPadding[8]; // SMU internal use
 } AvfsFuseOverride_t;
 
-/* NOT CURRENTLY USED
 typedef struct {
   uint8_t   Gfx_ActiveHystLimit;
   uint8_t   Gfx_IdleHystLimit;
@@ -866,7 +871,6 @@ typedef struct {
 
   uint32_t  MmHubPadding[8]; // SMU internal use
 } DpmActivityMonitorCoeffInt_t;
-*/
 
 // These defines are used with the following messages:
 // SMC_MSG_TransferTableDram2Smu
@@ -878,11 +882,11 @@ typedef struct {
 #define TABLE_PMSTATUSLOG             4
 #define TABLE_SMU_METRICS             5
 #define TABLE_DRIVER_SMU_CONFIG       6
-//#define TABLE_ACTIVITY_MONITOR_COEFF  7
 #define TABLE_OVERDRIVE               7
 #define TABLE_WAFL_XGMI_TOPOLOGY      8
 #define TABLE_I2C_COMMANDS            9
-#define TABLE_COUNT                   10
+#define TABLE_ACTIVITY_MONITOR_COEFF  10
+#define TABLE_COUNT                   11
 
 // These defines are used with the SMC_MSG_SetUclkFastSwitch message.
 typedef enum {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
index c27c82851468..2f85a34c0591 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu12_driver_if.h
@@ -27,7 +27,7 @@
 // *** IMPORTANT ***
 // SMU TEAM: Always increment the interface version if 
 // any structure is changed in this file
-#define SMU12_DRIVER_IF_VERSION 10
+#define SMU12_DRIVER_IF_VERSION 11
 
 typedef struct {
   int32_t value;
@@ -192,6 +192,11 @@ typedef struct {
   uint16_t SocTemperature;              //[centi-Celsius]
   uint16_t ThrottlerStatus;
   uint16_t spare;
+
+  uint16_t StapmOriginalLimit;          //[mW]
+  uint16_t StapmCurrentLimit;           //[mW]
+  uint16_t ApuPower;              //[mW]
+  uint16_t dGpuPower;               //[mW]
 } SmuMetrics_t;
 
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 719844257713..d5314d12628a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -27,7 +27,7 @@
 
 #define SMU11_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU11_DRIVER_IF_VERSION_VG20 0x13
-#define SMU11_DRIVER_IF_VERSION_ARCT 0x10
+#define SMU11_DRIVER_IF_VERSION_ARCT 0x12
 #define SMU11_DRIVER_IF_VERSION_NV10 0x33
 #define SMU11_DRIVER_IF_VERSION_NV14 0x34
 
@@ -170,6 +170,8 @@ int smu_v11_0_write_pptable(struct smu_context *smu);
 
 int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu);
 
+int smu_v11_0_set_driver_table_location(struct smu_context *smu);
+
 int smu_v11_0_set_tool_table_location(struct smu_context *smu);
 
 int smu_v11_0_notify_memory_pool_location(struct smu_context *smu);
@@ -247,7 +249,8 @@ enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu);
 
 int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state);
 
-int smu_v11_0_baco_reset(struct smu_context *smu);
+int smu_v11_0_baco_enter(struct smu_context *smu);
+int smu_v11_0_baco_exit(struct smu_context *smu);
 
 int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
 						 uint32_t *min, uint32_t *max);
@@ -261,4 +264,7 @@ int smu_v11_0_set_default_od_settings(struct smu_context *smu, bool initialize,
 
 uint32_t smu_v11_0_get_max_power_limit(struct smu_context *smu);
 
+int smu_v11_0_set_performance_level(struct smu_context *smu,
+				    enum amd_dpm_forced_level level);
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
index 9d81d789c713..d79e54b5ebf6 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
@@ -57,8 +57,14 @@ int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate);
 
 int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate);
 
+int smu_v12_0_powergate_jpeg(struct smu_context *smu, bool gate);
+
 int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable);
 
+int smu_v12_0_read_sensor(struct smu_context *smu,
+			  enum amd_pp_sensors sensor,
+			  void *data, uint32_t *size);
+
 uint32_t smu_v12_0_get_gfxoff_status(struct smu_context *smu);
 
 int smu_v12_0_gfx_off_control(struct smu_context *smu, bool enable);
@@ -69,6 +75,13 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu);
 
 int smu_v12_0_populate_smc_tables(struct smu_context *smu);
 
+int smu_v12_0_get_enabled_mask(struct smu_context *smu,
+				      uint32_t *feature_mask, uint32_t num);
+
+int smu_v12_0_get_current_clk_freq(struct smu_context *smu,
+					  enum smu_clk_type clk_id,
+					  uint32_t *value);
+
 int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
 						 uint32_t *min, uint32_t *max);
 
@@ -77,4 +90,6 @@ int smu_v12_0_mode2_reset(struct smu_context *smu);
 int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
 
+int smu_v12_0_set_driver_table_location(struct smu_context *smu);
+
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index ca62e92e5a4f..93c66c69ca28 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -384,8 +384,10 @@ navi10_get_allowed_feature_mask(struct smu_context *smu,
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_ATHUB_PG_BIT);
 
 	if (smu->adev->pg_flags & AMD_PG_SUPPORT_VCN)
-		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VCN_PG_BIT)
-				| FEATURE_MASK(FEATURE_JPEG_PG_BIT);
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_VCN_PG_BIT);
+
+	if (smu->adev->pg_flags & AMD_PG_SUPPORT_JPEG)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_JPEG_PG_BIT);
 
 	/* disable DPM UCLK and DS SOCCLK on navi10 A0 secure board */
 	if (is_asic_secure(smu)) {
@@ -553,6 +555,10 @@ static int navi10_tables_init(struct smu_context *smu, struct smu_table *tables)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
+	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
+	if (!smu_table->watermarks_table)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -668,6 +674,31 @@ static int navi10_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
 	return ret;
 }
 
+static int navi10_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (enable) {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg(smu, SMU_MSG_PowerUpJpeg);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = false;
+	} else {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownJpeg);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = true;
+	}
+
+	return ret;
+}
+
 static int navi10_get_current_clk_freq_by_table(struct smu_context *smu,
 				       enum smu_clk_type clk_type,
 				       uint32_t *value)
@@ -1350,7 +1381,7 @@ static int navi10_get_profiling_clk_mask(struct smu_context *smu,
 	return ret;
 }
 
-static int navi10_notify_smc_dispaly_config(struct smu_context *smu)
+static int navi10_notify_smc_display_config(struct smu_context *smu)
 {
 	struct smu_clocks min_clocks = {0};
 	struct pp_display_clock_request clock_req;
@@ -1555,12 +1586,44 @@ static int navi10_get_uclk_dpm_states(struct smu_context *smu, uint32_t *clocks_
 	return 0;
 }
 
-static int navi10_set_peak_clock_by_device(struct smu_context *smu)
+static int navi10_set_performance_level(struct smu_context *smu,
+					enum amd_dpm_forced_level level);
+
+static int navi10_set_standard_performance_level(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
+	uint32_t sclk_freq = 0, uclk_freq = 0;
+
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+		sclk_freq = NAVI10_UMD_PSTATE_PROFILING_GFXCLK;
+		uclk_freq = NAVI10_UMD_PSTATE_PROFILING_MEMCLK;
+		break;
+	case CHIP_NAVI14:
+		sclk_freq = NAVI14_UMD_PSTATE_PROFILING_GFXCLK;
+		uclk_freq = NAVI14_UMD_PSTATE_PROFILING_MEMCLK;
+		break;
+	default:
+		/* by default, this is same as auto performance level */
+		return navi10_set_performance_level(smu, AMD_DPM_FORCED_LEVEL_AUTO);
+	}
+
+	ret = smu_set_soft_freq_range(smu, SMU_SCLK, sclk_freq, sclk_freq);
+	if (ret)
+		return ret;
+	ret = smu_set_soft_freq_range(smu, SMU_UCLK, uclk_freq, uclk_freq);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int navi10_set_peak_performance_level(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	uint32_t sclk_freq = 0, uclk_freq = 0;
-	uint32_t uclk_level = 0;
 
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
@@ -1601,14 +1664,16 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu)
 			break;
 		}
 		break;
+	case CHIP_NAVI12:
+		sclk_freq = NAVI12_UMD_PSTATE_PEAK_GFXCLK;
+		break;
 	default:
-		return -EINVAL;
+		ret = smu_get_dpm_level_range(smu, SMU_SCLK, NULL, &sclk_freq);
+		if (ret)
+			return ret;
 	}
 
-	ret = smu_get_dpm_level_count(smu, SMU_UCLK, &uclk_level);
-	if (ret)
-		return ret;
-	ret = smu_get_dpm_freq_by_index(smu, SMU_UCLK, uclk_level - 1, &uclk_freq);
+	ret = smu_get_dpm_level_range(smu, SMU_UCLK, NULL, &uclk_freq);
 	if (ret)
 		return ret;
 
@@ -1622,19 +1687,45 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu)
 	return ret;
 }
 
-static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+static int navi10_set_performance_level(struct smu_context *smu,
+					enum amd_dpm_forced_level level)
 {
 	int ret = 0;
+	uint32_t sclk_mask, mclk_mask, soc_mask;
 
 	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_HIGH:
+		ret = smu_force_dpm_limit_value(smu, true);
+		break;
+	case AMD_DPM_FORCED_LEVEL_LOW:
+		ret = smu_force_dpm_limit_value(smu, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_AUTO:
+		ret = smu_unforce_dpm_levels(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = navi10_set_standard_performance_level(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+		ret = smu_get_profiling_clk_mask(smu, level,
+						 &sclk_mask,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			return ret;
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
+		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-		ret = navi10_set_peak_clock_by_device(smu);
+		ret = navi10_set_peak_performance_level(smu);
 		break;
+	case AMD_DPM_FORCED_LEVEL_MANUAL:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
-		ret = -EINVAL;
 		break;
 	}
-
 	return ret;
 }
 
@@ -2015,6 +2106,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_allowed_feature_mask = navi10_get_allowed_feature_mask,
 	.set_default_dpm_table = navi10_set_default_dpm_table,
 	.dpm_set_uvd_enable = navi10_dpm_set_uvd_enable,
+	.dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable,
 	.get_current_clk_freq_by_table = navi10_get_current_clk_freq_by_table,
 	.print_clk_levels = navi10_print_clk_levels,
 	.force_clk_levels = navi10_force_clk_levels,
@@ -2022,7 +2114,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_clock_by_type_with_latency = navi10_get_clock_by_type_with_latency,
 	.pre_display_config_changed = navi10_pre_display_config_changed,
 	.display_config_changed = navi10_display_config_changed,
-	.notify_smc_dispaly_config = navi10_notify_smc_dispaly_config,
+	.notify_smc_display_config = navi10_notify_smc_display_config,
 	.force_dpm_limit_value = navi10_force_dpm_limit_value,
 	.unforce_dpm_levels = navi10_unforce_dpm_levels,
 	.is_dpm_running = navi10_is_dpm_running,
@@ -2055,6 +2147,7 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.write_pptable = smu_v11_0_write_pptable,
 	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
@@ -2083,7 +2176,8 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.baco_is_support= smu_v11_0_baco_is_support,
 	.baco_get_state = smu_v11_0_baco_get_state,
 	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
+	.baco_enter = smu_v11_0_baco_enter,
+	.baco_exit = smu_v11_0_baco_exit,
 	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
index ec03c7992f6d..2abb4ba01db1 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
@@ -27,12 +27,26 @@
 #define NAVI10_PEAK_SCLK_XT  		(1755)
 #define NAVI10_PEAK_SCLK_XL  		(1625)
 
+#define NAVI10_UMD_PSTATE_PROFILING_GFXCLK    (1300)
+#define NAVI10_UMD_PSTATE_PROFILING_SOCCLK    (980)
+#define NAVI10_UMD_PSTATE_PROFILING_MEMCLK    (625)
+#define NAVI10_UMD_PSTATE_PROFILING_VCLK      (980)
+#define NAVI10_UMD_PSTATE_PROFILING_DCLK      (850)
+
 #define NAVI14_UMD_PSTATE_PEAK_XT_GFXCLK      (1670)
 #define NAVI14_UMD_PSTATE_PEAK_XTM_GFXCLK     (1448)
 #define NAVI14_UMD_PSTATE_PEAK_XLM_GFXCLK     (1181)
 #define NAVI14_UMD_PSTATE_PEAK_XTX_GFXCLK     (1717)
 #define NAVI14_UMD_PSTATE_PEAK_XL_GFXCLK      (1448)
 
+#define NAVI14_UMD_PSTATE_PROFILING_GFXCLK    (1200)
+#define NAVI14_UMD_PSTATE_PROFILING_SOCCLK    (900)
+#define NAVI14_UMD_PSTATE_PROFILING_MEMCLK    (600)
+#define NAVI14_UMD_PSTATE_PROFILING_VCLK      (900)
+#define NAVI14_UMD_PSTATE_PROFILING_DCLK      (800)
+
+#define NAVI12_UMD_PSTATE_PEAK_GFXCLK     (1100)
+
 #define NAVI10_VOLTAGE_SCALE (4)
 
 #define smnPCIE_LC_SPEED_CNTL			0x11140290
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 977bdd962e98..861e6410363b 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -31,6 +31,9 @@
 #include "renoir_ppt.h"
 
 
+#define CLK_MAP(clk, index) \
+	[SMU_##clk] = {1, (index)}
+
 #define MSG_MAP(msg, index) \
 	[SMU_MSG_##msg] = {1, (index)}
 
@@ -104,6 +107,14 @@ static struct smu_12_0_cmn2aisc_mapping renoir_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(SetHardMinFclkByFreq,           PPSMC_MSG_SetHardMinFclkByFreq),
 };
 
+static struct smu_12_0_cmn2aisc_mapping renoir_clk_map[SMU_CLK_COUNT] = {
+	CLK_MAP(GFXCLK, CLOCK_GFXCLK),
+	CLK_MAP(SCLK,	CLOCK_GFXCLK),
+	CLK_MAP(SOCCLK, CLOCK_SOCCLK),
+	CLK_MAP(UCLK, CLOCK_UMCCLK),
+	CLK_MAP(MCLK, CLOCK_UMCCLK),
+};
+
 static struct smu_12_0_cmn2aisc_mapping renoir_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP_VALID(WATERMARKS),
 	TAB_MAP_INVALID(CUSTOM_DPM),
@@ -125,6 +136,21 @@ static int renoir_get_smu_msg_index(struct smu_context *smc, uint32_t index)
 	return mapping.map_to;
 }
 
+static int renoir_get_smu_clk_index(struct smu_context *smc, uint32_t index)
+{
+	struct smu_12_0_cmn2aisc_mapping mapping;
+
+	if (index >= SMU_CLK_COUNT)
+		return -EINVAL;
+
+	mapping = renoir_clk_map[index];
+	if (!(mapping.valid_mapping)) {
+		return -EINVAL;
+	}
+
+	return mapping.map_to;
+}
+
 static int renoir_get_smu_table_index(struct smu_context *smc, uint32_t index)
 {
 	struct smu_12_0_cmn2aisc_mapping mapping;
@@ -139,6 +165,30 @@ static int renoir_get_smu_table_index(struct smu_context *smc, uint32_t index)
 	return mapping.map_to;
 }
 
+static int renoir_get_metrics_table(struct smu_context *smu,
+				    SmuMetrics_t *metrics_table)
+{
+	struct smu_table_context *smu_table= &smu->smu_table;
+	int ret = 0;
+
+	mutex_lock(&smu->metrics_lock);
+	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
+		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
+				(void *)smu_table->metrics_table, false);
+		if (ret) {
+			pr_info("Failed to export SMU metrics table!\n");
+			mutex_unlock(&smu->metrics_lock);
+			return ret;
+		}
+		smu_table->metrics_time = jiffies;
+	}
+
+	memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+	mutex_unlock(&smu->metrics_lock);
+
+	return ret;
+}
+
 static int renoir_tables_init(struct smu_context *smu, struct smu_table *tables)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
@@ -154,6 +204,15 @@ static int renoir_tables_init(struct smu_context *smu, struct smu_table *tables)
 	if (!smu_table->clocks_table)
 		return -ENOMEM;
 
+	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
+	if (!smu_table->metrics_table)
+		return -ENOMEM;
+	smu_table->metrics_time = 0;
+
+	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
+	if (!smu_table->watermarks_table)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -187,8 +246,7 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 
 	memset(&metrics, 0, sizeof(metrics));
 
-	ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
-			       (void *)&metrics, false);
+	ret = renoir_get_metrics_table(smu, &metrics);
 	if (ret)
 		return ret;
 
@@ -301,6 +359,51 @@ static int renoir_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
 	return ret;
 }
 
+static int renoir_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (enable) {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpJpeg, 0);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = false;
+	} else {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_JPEG_PG_BIT)) {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerDownJpeg, 0);
+			if (ret)
+				return ret;
+		}
+		power_gate->jpeg_gated = true;
+	}
+
+	return ret;
+}
+
+static int renoir_get_current_clk_freq_by_table(struct smu_context *smu,
+				       enum smu_clk_type clk_type,
+				       uint32_t *value)
+{
+	int ret = 0, clk_id = 0;
+	SmuMetrics_t metrics;
+
+	ret = renoir_get_metrics_table(smu, &metrics);
+	if (ret)
+		return ret;
+
+	clk_id = smu_clk_get_index(smu, clk_type);
+	if (clk_id < 0)
+		return clk_id;
+
+	*value = metrics.ClockFrequency[clk_id];
+
+	return ret;
+}
+
 static int renoir_force_dpm_limit_value(struct smu_context *smu, bool highest)
 {
 	int ret = 0, i = 0;
@@ -361,6 +464,50 @@ static int renoir_unforce_dpm_levels(struct smu_context *smu) {
 	return ret;
 }
 
+static int renoir_get_gpu_temperature(struct smu_context *smu, uint32_t *value)
+{
+	int ret = 0;
+	SmuMetrics_t metrics;
+
+	if (!value)
+		return -EINVAL;
+
+	ret = renoir_get_metrics_table(smu, &metrics);
+	if (ret)
+		return ret;
+
+	*value = (metrics.GfxTemperature / 100) *
+		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
+	return 0;
+}
+
+static int renoir_get_current_activity_percent(struct smu_context *smu,
+					       enum amd_pp_sensors sensor,
+					       uint32_t *value)
+{
+	int ret = 0;
+	SmuMetrics_t metrics;
+
+	if (!value)
+		return -EINVAL;
+
+	ret = renoir_get_metrics_table(smu, &metrics);
+	if (ret)
+		return ret;
+
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GPU_LOAD:
+		*value = metrics.AverageGfxActivity / 100;
+		break;
+	default:
+		pr_err("Invalid sensor for retrieving clock activity\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int renoir_get_workload_type(struct smu_context *smu, uint32_t profile)
 {
 
@@ -565,19 +712,43 @@ static int renoir_set_peak_clock_by_device(struct smu_context *smu)
 	return ret;
 }
 
-static int renoir_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+static int renoir_set_performance_level(struct smu_context *smu,
+					enum amd_dpm_forced_level level)
 {
 	int ret = 0;
+	uint32_t sclk_mask, mclk_mask, soc_mask;
 
 	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_HIGH:
+		ret = smu_force_dpm_limit_value(smu, true);
+		break;
+	case AMD_DPM_FORCED_LEVEL_LOW:
+		ret = smu_force_dpm_limit_value(smu, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_AUTO:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = smu_unforce_dpm_levels(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+		ret = smu_get_profiling_clk_mask(smu, level,
+						 &sclk_mask,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			return ret;
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
+		break;
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
 		ret = renoir_set_peak_clock_by_device(smu);
 		break;
+	case AMD_DPM_FORCED_LEVEL_MANUAL:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
-		ret = -EINVAL;
 		break;
 	}
-
 	return ret;
 }
 
@@ -636,9 +807,17 @@ static int renoir_set_watermarks_table(
 	}
 
 	/* pass data to smu controller */
-	ret = smu_write_watermarks_table(smu);
+	if ((smu->watermarks_bitmap & WATERMARKS_EXIST) &&
+			!(smu->watermarks_bitmap & WATERMARKS_LOADED)) {
+		ret = smu_write_watermarks_table(smu);
+		if (ret) {
+			pr_err("Failed to update WMTABLE!");
+			return ret;
+		}
+		smu->watermarks_bitmap |= WATERMARKS_LOADED;
+	}
 
-	return ret;
+	return 0;
 }
 
 static int renoir_get_power_profile_mode(struct smu_context *smu,
@@ -674,8 +853,36 @@ static int renoir_get_power_profile_mode(struct smu_context *smu,
 	return size;
 }
 
+static int renoir_read_sensor(struct smu_context *smu,
+				 enum amd_pp_sensors sensor,
+				 void *data, uint32_t *size)
+{
+	int ret = 0;
+
+	if (!data || !size)
+		return -EINVAL;
+
+	mutex_lock(&smu->sensor_lock);
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GPU_LOAD:
+		ret = renoir_get_current_activity_percent(smu, sensor, (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GPU_TEMP:
+		ret = renoir_get_gpu_temperature(smu, (uint32_t *)data);
+		*size = 4;
+		break;
+	default:
+		ret = smu_v12_0_read_sensor(smu, sensor, data, size);
+	}
+	mutex_unlock(&smu->sensor_lock);
+
+	return ret;
+}
+
 static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_smu_msg_index = renoir_get_smu_msg_index,
+	.get_smu_clk_index = renoir_get_smu_clk_index,
 	.get_smu_table_index = renoir_get_smu_table_index,
 	.tables_init = renoir_tables_init,
 	.set_power_state = NULL,
@@ -683,6 +890,8 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.print_clk_levels = renoir_print_clk_levels,
 	.get_current_power_state = renoir_get_current_power_state,
 	.dpm_set_uvd_enable = renoir_dpm_set_uvd_enable,
+	.dpm_set_jpeg_enable = renoir_dpm_set_jpeg_enable,
+	.get_current_clk_freq_by_table = renoir_get_current_clk_freq_by_table,
 	.force_dpm_limit_value = renoir_force_dpm_limit_value,
 	.unforce_dpm_levels = renoir_unforce_dpm_levels,
 	.get_workload_type = renoir_get_workload_type,
@@ -693,10 +902,12 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_dpm_clock_table = renoir_get_dpm_clock_table,
 	.set_watermarks_table = renoir_set_watermarks_table,
 	.get_power_profile_mode = renoir_get_power_profile_mode,
+	.read_sensor = renoir_read_sensor,
 	.check_fw_status = smu_v12_0_check_fw_status,
 	.check_fw_version = smu_v12_0_check_fw_version,
 	.powergate_sdma = smu_v12_0_powergate_sdma,
 	.powergate_vcn = smu_v12_0_powergate_vcn,
+	.powergate_jpeg = smu_v12_0_powergate_jpeg,
 	.send_smc_msg_with_param = smu_v12_0_send_msg_with_param,
 	.read_smc_arg = smu_v12_0_read_arg,
 	.set_gfx_cgpg = smu_v12_0_set_gfx_cgpg,
@@ -704,9 +915,12 @@ static const struct pptable_funcs renoir_ppt_funcs = {
 	.init_smc_tables = smu_v12_0_init_smc_tables,
 	.fini_smc_tables = smu_v12_0_fini_smc_tables,
 	.populate_smc_tables = smu_v12_0_populate_smc_tables,
+	.get_enabled_mask = smu_v12_0_get_enabled_mask,
+	.get_current_clk_freq = smu_v12_0_get_current_clk_freq,
 	.get_dpm_ultimate_freq = smu_v12_0_get_dpm_ultimate_freq,
 	.mode2_reset = smu_v12_0_mode2_reset,
 	.set_soft_freq_limited_range = smu_v12_0_set_soft_freq_limited_range,
+	.set_driver_table_location = smu_v12_0_set_driver_table_location,
 };
 
 void renoir_set_ppt_funcs(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h
index 8872f8b2d502..783319ec8bf9 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_internal.h
+++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h
@@ -42,6 +42,8 @@
 	((smu)->ppt_funcs->powergate_sdma ? (smu)->ppt_funcs->powergate_sdma((smu), (gate)) : 0)
 #define smu_powergate_vcn(smu, gate) \
 	((smu)->ppt_funcs->powergate_vcn ? (smu)->ppt_funcs->powergate_vcn((smu), (gate)) : 0)
+#define smu_powergate_jpeg(smu, gate) \
+	((smu)->ppt_funcs->powergate_jpeg ? (smu)->ppt_funcs->powergate_jpeg((smu), (gate)) : 0)
 
 #define smu_get_vbios_bootup_values(smu) \
 	((smu)->ppt_funcs->get_vbios_bootup_values ? (smu)->ppt_funcs->get_vbios_bootup_values((smu)) : 0)
@@ -59,6 +61,8 @@
 	((smu)->ppt_funcs->write_pptable ? (smu)->ppt_funcs->write_pptable((smu)) : 0)
 #define smu_set_min_dcef_deep_sleep(smu) \
 	((smu)->ppt_funcs->set_min_dcef_deep_sleep ? (smu)->ppt_funcs->set_min_dcef_deep_sleep((smu)) : 0)
+#define smu_set_driver_table_location(smu) \
+	((smu)->ppt_funcs->set_driver_table_location ? (smu)->ppt_funcs->set_driver_table_location((smu)) : 0)
 #define smu_set_tool_table_location(smu) \
 	((smu)->ppt_funcs->set_tool_table_location ? (smu)->ppt_funcs->set_tool_table_location((smu)) : 0)
 #define smu_notify_memory_pool_location(smu) \
@@ -127,8 +131,8 @@ int smu_send_smc_msg(struct smu_context *smu, enum smu_message_type msg);
 	((smu)->ppt_funcs->display_config_changed ? (smu)->ppt_funcs->display_config_changed((smu)) : 0)
 #define smu_apply_clocks_adjust_rules(smu) \
 	((smu)->ppt_funcs->apply_clocks_adjust_rules ? (smu)->ppt_funcs->apply_clocks_adjust_rules((smu)) : 0)
-#define smu_notify_smc_dispaly_config(smu) \
-	((smu)->ppt_funcs->notify_smc_dispaly_config ? (smu)->ppt_funcs->notify_smc_dispaly_config((smu)) : 0)
+#define smu_notify_smc_display_config(smu) \
+	((smu)->ppt_funcs->notify_smc_display_config ? (smu)->ppt_funcs->notify_smc_display_config((smu)) : 0)
 #define smu_force_dpm_limit_value(smu, highest) \
 	((smu)->ppt_funcs->force_dpm_limit_value ? (smu)->ppt_funcs->force_dpm_limit_value((smu), (highest)) : 0)
 #define smu_unforce_dpm_levels(smu) \
@@ -170,6 +174,8 @@ int smu_send_smc_msg(struct smu_context *smu, enum smu_message_type msg);
 	((smu)->ppt_funcs->dpm_set_uvd_enable ? (smu)->ppt_funcs->dpm_set_uvd_enable((smu), (enable)) : 0)
 #define smu_dpm_set_vce_enable(smu, enable) \
 	((smu)->ppt_funcs->dpm_set_vce_enable ? (smu)->ppt_funcs->dpm_set_vce_enable((smu), (enable)) : 0)
+#define smu_dpm_set_jpeg_enable(smu, enable) \
+	((smu)->ppt_funcs->dpm_set_jpeg_enable ? (smu)->ppt_funcs->dpm_set_jpeg_enable((smu), (enable)) : 0)
 
 #define smu_set_watermarks_table(smu, tab, clock_ranges) \
 	((smu)->ppt_funcs->set_watermarks_table ? (smu)->ppt_funcs->set_watermarks_table((smu), (tab), (clock_ranges)) : 0)
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index e4268a627eff..02f8c9cb89d9 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -37,6 +37,7 @@
 #include "soc15_common.h"
 #include "atom.h"
 #include "amd_pcie.h"
+#include "amdgpu_ras.h"
 
 #include "asic_reg/thm/thm_11_0_2_offset.h"
 #include "asic_reg/thm/thm_11_0_2_sh_mask.h"
@@ -79,15 +80,13 @@ static int smu_v11_0_wait_for_response(struct smu_context *smu)
 	for (i = 0; i < timeout; i++) {
 		cur_value = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 		if ((cur_value & MP1_C2PMSG_90__CONTENT_MASK) != 0)
-			break;
+			return cur_value == 0x1 ? 0 : -EIO;
+
 		udelay(1);
 	}
 
 	/* timeout means wrong logic */
-	if (i == timeout)
-		return -ETIME;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
+	return -ETIME;
 }
 
 int
@@ -103,9 +102,11 @@ smu_v11_0_send_msg_with_param(struct smu_context *smu,
 		return index;
 
 	ret = smu_v11_0_wait_for_response(smu);
-	if (ret)
-		pr_err("failed send message: %10s (%d) \tparam: 0x%08x response %#x\n",
-		       smu_get_message_name(smu, msg), index, param, ret);
+	if (ret) {
+		pr_err("Msg issuing pre-check failed and "
+		       "SMU may be not in the right state!\n");
+		return ret;
+	}
 
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
@@ -449,8 +450,10 @@ int smu_v11_0_fini_smc_tables(struct smu_context *smu)
 
 	kfree(smu_table->tables);
 	kfree(smu_table->metrics_table);
+	kfree(smu_table->watermarks_table);
 	smu_table->tables = NULL;
 	smu_table->metrics_table = NULL;
+	smu_table->watermarks_table = NULL;
 	smu_table->metrics_time = 0;
 
 	ret = smu_v11_0_fini_dpm_context(smu);
@@ -773,6 +776,24 @@ int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu)
 	return smu_v11_0_set_deep_sleep_dcefclk(smu, table_context->boot_values.dcefclk / 100);
 }
 
+int smu_v11_0_set_driver_table_location(struct smu_context *smu)
+{
+	struct smu_table *driver_table = &smu->smu_table.driver_table;
+	int ret = 0;
+
+	if (driver_table->mc_address) {
+		ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrHigh,
+				upper_32_bits(driver_table->mc_address));
+		if (!ret)
+			ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrLow,
+				lower_32_bits(driver_table->mc_address));
+	}
+
+	return ret;
+}
+
 int smu_v11_0_set_tool_table_location(struct smu_context *smu)
 {
 	int ret = 0;
@@ -834,27 +855,33 @@ int smu_v11_0_get_enabled_mask(struct smu_context *smu,
 				      uint32_t *feature_mask, uint32_t num)
 {
 	uint32_t feature_mask_high = 0, feature_mask_low = 0;
+	struct smu_feature *feature = &smu->smu_feature;
 	int ret = 0;
 
 	if (!feature_mask || num < 2)
 		return -EINVAL;
 
-	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesHigh);
-	if (ret)
-		return ret;
-	ret = smu_read_smc_arg(smu, &feature_mask_high);
-	if (ret)
-		return ret;
+	if (bitmap_empty(feature->enabled, feature->feature_num)) {
+		ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesHigh);
+		if (ret)
+			return ret;
+		ret = smu_read_smc_arg(smu, &feature_mask_high);
+		if (ret)
+			return ret;
 
-	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesLow);
-	if (ret)
-		return ret;
-	ret = smu_read_smc_arg(smu, &feature_mask_low);
-	if (ret)
-		return ret;
+		ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesLow);
+		if (ret)
+			return ret;
+		ret = smu_read_smc_arg(smu, &feature_mask_low);
+		if (ret)
+			return ret;
 
-	feature_mask[0] = feature_mask_low;
-	feature_mask[1] = feature_mask_high;
+		feature_mask[0] = feature_mask_low;
+		feature_mask[1] = feature_mask_high;
+	} else {
+		bitmap_copy((unsigned long *)feature_mask, feature->enabled,
+			     feature->feature_num);
+	}
 
 	return ret;
 }
@@ -866,21 +893,24 @@ int smu_v11_0_system_features_control(struct smu_context *smu,
 	uint32_t feature_mask[2];
 	int ret = 0;
 
-	if (smu->pm_enabled) {
-		ret = smu_send_smc_msg(smu, (en ? SMU_MSG_EnableAllSmuFeatures :
-					     SMU_MSG_DisableAllSmuFeatures));
-		if (ret)
-			return ret;
-	}
-
-	ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
+	ret = smu_send_smc_msg(smu, (en ? SMU_MSG_EnableAllSmuFeatures :
+				     SMU_MSG_DisableAllSmuFeatures));
 	if (ret)
 		return ret;
 
-	bitmap_copy(feature->enabled, (unsigned long *)&feature_mask,
-		    feature->feature_num);
-	bitmap_copy(feature->supported, (unsigned long *)&feature_mask,
-		    feature->feature_num);
+	if (en) {
+		ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
+		if (ret)
+			return ret;
+
+		bitmap_copy(feature->enabled, (unsigned long *)&feature_mask,
+			    feature->feature_num);
+		bitmap_copy(feature->supported, (unsigned long *)&feature_mask,
+			    feature->feature_num);
+	} else {
+		bitmap_zero(feature->enabled, feature->feature_num);
+		bitmap_zero(feature->supported, feature->feature_num);
+	}
 
 	return ret;
 }
@@ -1124,11 +1154,12 @@ static int smu_v11_0_set_thermal_range(struct smu_context *smu,
 	int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
 	int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
 	uint32_t val;
+	struct smu_table_context *table_context = &smu->smu_table;
+	struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table;
 
 	low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP,
 			range.min / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
-	high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP,
-			range.max / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES);
+	high = min((uint16_t)SMU_THERMAL_MAXIMUM_ALERT_TEMP, powerplay_table->software_shutdown_temp);
 
 	if (low > high)
 		return -EINVAL;
@@ -1617,7 +1648,9 @@ bool smu_v11_0_baco_is_support(struct smu_context *smu)
 	if (!baco_support)
 		return false;
 
-	if (!smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
+	/* Arcturus does not support this bit mask */
+	if (smu_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) &&
+	   !smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT))
 		return false;
 
 	val = RREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP0);
@@ -1643,6 +1676,10 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
 {
 
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
+	struct amdgpu_device *adev = smu->adev;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+	uint32_t bif_doorbell_intr_cntl;
+	uint32_t data;
 	int ret = 0;
 
 	if (smu_v11_0_baco_get_state(smu) == state)
@@ -1650,10 +1687,37 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
 
 	mutex_lock(&smu_baco->mutex);
 
-	if (state == SMU_BACO_STATE_ENTER)
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, BACO_SEQ_BACO);
-	else
+	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+
+	if (state == SMU_BACO_STATE_ENTER) {
+		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
+						BIF_DOORBELL_INT_CNTL,
+						DOORBELL_INTERRUPT_DISABLE, 1);
+		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		if (!ras || !ras->supported) {
+			data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL);
+			data |= 0x80000000;
+			WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data);
+
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, 0);
+		} else {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, 1);
+		}
+	} else {
 		ret = smu_send_smc_msg(smu, SMU_MSG_ExitBaco);
+		if (ret)
+			goto out;
+
+		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
+						BIF_DOORBELL_INT_CNTL,
+						DOORBELL_INTERRUPT_DISABLE, 0);
+		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		/* clear vbios scratch 6 and 7 for coming asic reinit */
+		WREG32(adev->bios_scratch_reg_offset + 6, 0);
+		WREG32(adev->bios_scratch_reg_offset + 7, 0);
+	}
 	if (ret)
 		goto out;
 
@@ -1663,13 +1727,17 @@ out:
 	return ret;
 }
 
-int smu_v11_0_baco_reset(struct smu_context *smu)
+int smu_v11_0_baco_enter(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
-	ret = smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
-	if (ret)
-		return ret;
+	/* Arcturus does not need this audio workaround */
+	if (adev->asic_type != CHIP_ARCTURUS) {
+		ret = smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO);
+		if (ret)
+			return ret;
+	}
 
 	ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_ENTER);
 	if (ret)
@@ -1677,6 +1745,13 @@ int smu_v11_0_baco_reset(struct smu_context *smu)
 
 	msleep(10);
 
+	return ret;
+}
+
+int smu_v11_0_baco_exit(struct smu_context *smu)
+{
+	int ret = 0;
+
 	ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_EXIT);
 	if (ret)
 		return ret;
@@ -1815,3 +1890,42 @@ int smu_v11_0_set_default_od_settings(struct smu_context *smu, bool initialize,
 	}
 	return ret;
 }
+
+int smu_v11_0_set_performance_level(struct smu_context *smu,
+				    enum amd_dpm_forced_level level)
+{
+	int ret = 0;
+	uint32_t sclk_mask, mclk_mask, soc_mask;
+
+	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_HIGH:
+		ret = smu_force_dpm_limit_value(smu, true);
+		break;
+	case AMD_DPM_FORCED_LEVEL_LOW:
+		ret = smu_force_dpm_limit_value(smu, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_AUTO:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+		ret = smu_unforce_dpm_levels(smu);
+		break;
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+		ret = smu_get_profiling_clk_mask(smu, level,
+						 &sclk_mask,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			return ret;
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
+		break;
+	case AMD_DPM_FORCED_LEVEL_MANUAL:
+	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
+	default:
+		break;
+	}
+	return ret;
+}
+
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
index 094cfc46adac..870e6db2907e 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
@@ -66,15 +66,13 @@ int smu_v12_0_wait_for_response(struct smu_context *smu)
 	for (i = 0; i < adev->usec_timeout; i++) {
 		cur_value = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
 		if ((cur_value & MP1_C2PMSG_90__CONTENT_MASK) != 0)
-			break;
+			return cur_value == 0x1 ? 0 : -EIO;
+
 		udelay(1);
 	}
 
 	/* timeout means wrong logic */
-	if (i == adev->usec_timeout)
-		return -ETIME;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
+	return -ETIME;
 }
 
 int
@@ -90,9 +88,11 @@ smu_v12_0_send_msg_with_param(struct smu_context *smu,
 		return index;
 
 	ret = smu_v12_0_wait_for_response(smu);
-	if (ret)
-		pr_err("Failed to send message 0x%x, response 0x%x, param 0x%x\n",
-		       index, ret, param);
+	if (ret) {
+		pr_err("Msg issuing pre-check failed and "
+		       "SMU may be not in the right state!\n");
+		return ret;
+	}
 
 	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
@@ -159,7 +159,7 @@ int smu_v12_0_check_fw_version(struct smu_context *smu)
 
 int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
 {
-	if (!(smu->adev->flags & AMD_IS_APU))
+	if (!smu->is_apu)
 		return 0;
 
 	if (gate)
@@ -170,7 +170,7 @@ int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
 
 int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
 {
-	if (!(smu->adev->flags & AMD_IS_APU))
+	if (!smu->is_apu)
 		return 0;
 
 	if (gate)
@@ -179,6 +179,17 @@ int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
 		return smu_send_smc_msg(smu, SMU_MSG_PowerUpVcn);
 }
 
+int smu_v12_0_powergate_jpeg(struct smu_context *smu, bool gate)
+{
+	if (!smu->is_apu)
+		return 0;
+
+	if (gate)
+		return smu_send_smc_msg_with_param(smu, SMU_MSG_PowerDownJpeg, 0);
+	else
+		return smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpJpeg, 0);
+}
+
 int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
 {
 	if (!(smu->adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
@@ -188,6 +199,39 @@ int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
 		SMU_MSG_SetGfxCGPG, enable ? 1 : 0);
 }
 
+int smu_v12_0_read_sensor(struct smu_context *smu,
+				 enum amd_pp_sensors sensor,
+				 void *data, uint32_t *size)
+{
+	int ret = 0;
+
+	if(!data || !size)
+		return -EINVAL;
+
+	switch (sensor) {
+	case AMDGPU_PP_SENSOR_GFX_MCLK:
+		ret = smu_get_current_clk_freq(smu, SMU_UCLK, (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_GFX_SCLK:
+		ret = smu_get_current_clk_freq(smu, SMU_GFXCLK, (uint32_t *)data);
+		*size = 4;
+		break;
+	case AMDGPU_PP_SENSOR_MIN_FAN_RPM:
+		*(uint32_t *)data = 0;
+		*size = 4;
+		break;
+	default:
+		ret = smu_common_read_sensor(smu, sensor, data, size);
+		break;
+	}
+
+	if (ret)
+		*size = 0;
+
+	return ret;
+}
+
 /**
  * smu_v12_0_get_gfxoff_status - get gfxoff status
  *
@@ -274,16 +318,57 @@ int smu_v12_0_fini_smc_tables(struct smu_context *smu)
 int smu_v12_0_populate_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct smu_table *table = NULL;
 
-	table = &smu_table->tables[SMU_TABLE_DPMCLOCKS];
-	if (!table)
+	return smu_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
+}
+
+int smu_v12_0_get_enabled_mask(struct smu_context *smu,
+				      uint32_t *feature_mask, uint32_t num)
+{
+	uint32_t feature_mask_high = 0, feature_mask_low = 0;
+	int ret = 0;
+
+	if (!feature_mask || num < 2)
 		return -EINVAL;
 
-	if (!table->cpu_addr)
+	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesHigh);
+	if (ret)
+		return ret;
+	ret = smu_read_smc_arg(smu, &feature_mask_high);
+	if (ret)
+		return ret;
+
+	ret = smu_send_smc_msg(smu, SMU_MSG_GetEnabledSmuFeaturesLow);
+	if (ret)
+		return ret;
+	ret = smu_read_smc_arg(smu, &feature_mask_low);
+	if (ret)
+		return ret;
+
+	feature_mask[0] = feature_mask_low;
+	feature_mask[1] = feature_mask_high;
+
+	return ret;
+}
+
+int smu_v12_0_get_current_clk_freq(struct smu_context *smu,
+					  enum smu_clk_type clk_id,
+					  uint32_t *value)
+{
+	int ret = 0;
+	uint32_t freq = 0;
+
+	if (clk_id >= SMU_CLK_COUNT || !value)
 		return -EINVAL;
 
-	return smu_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
+	ret = smu_get_current_clk_freq_by_table(smu, clk_id, &freq);
+	if (ret)
+		return ret;
+
+	freq *= 100;
+	*value = freq;
+
+	return ret;
 }
 
 int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
@@ -421,3 +506,21 @@ int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_
 
 	return ret;
 }
+
+int smu_v12_0_set_driver_table_location(struct smu_context *smu)
+{
+	struct smu_table *driver_table = &smu->smu_table.driver_table;
+	int ret = 0;
+
+	if (driver_table->mc_address) {
+		ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrHigh,
+				upper_32_bits(driver_table->mc_address));
+		if (!ret)
+			ret = smu_send_smc_msg_with_param(smu,
+				SMU_MSG_SetDriverDramAddrLow,
+				lower_32_bits(driver_table->mc_address));
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 15590fd86ef4..868e2d5f6e62 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -653,8 +653,8 @@ static int ci_min_max_v_gnbl_pm_lid_from_bapm_vddc(struct pp_hwmgr *hwmgr)
 static int ci_populate_bapm_vddc_base_leakage_sidd(struct pp_hwmgr *hwmgr)
 {
 	struct ci_smumgr *smu_data = (struct ci_smumgr *)(hwmgr->smu_backend);
-	uint16_t HiSidd = smu_data->power_tune_table.BapmVddCBaseLeakageHiSidd;
-	uint16_t LoSidd = smu_data->power_tune_table.BapmVddCBaseLeakageLoSidd;
+	uint16_t HiSidd;
+	uint16_t LoSidd;
 	struct phm_cac_tdp_table *cac_table = hwmgr->dyn_state.cac_dtp_table;
 
 	HiSidd = (uint16_t)(cac_table->usHighCACLeakage / 100 * 256);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index da025b1d302d..32ebb383c456 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -940,7 +940,7 @@ static int fiji_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 {
 	int result;
 	/* PP_Clocks minClocks; */
-	uint32_t threshold, mvdd;
+	uint32_t mvdd;
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
@@ -973,8 +973,6 @@ static int fiji_populate_single_graphic_level(struct pp_hwmgr *hwmgr,
 	level->VoltageDownHyst = 0;
 	level->PowerThrottle = 0;
 
-	threshold = clock * data->fast_watermark_threshold / 100;
-
 	data->display_timing.min_clock_in_sr = hwmgr->display_config->min_core_set_clock_in_sr;
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SclkDeepSleep))
@@ -1501,7 +1499,7 @@ static int fiji_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 	uint32_t dram_timing;
 	uint32_t dram_timing2;
 	uint32_t burstTime;
-	ULONG state, trrds, trrdl;
+	ULONG trrds, trrdl;
 	int result;
 
 	result = atomctrl_set_engine_dram_timings_rv770(hwmgr,
@@ -1513,7 +1511,6 @@ static int fiji_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 	dram_timing2 = cgs_read_register(hwmgr->device, mmMC_ARB_DRAM_TIMING2);
 	burstTime = cgs_read_register(hwmgr->device, mmMC_ARB_BURST_TIME);
 
-	state = PHM_GET_FIELD(burstTime, MC_ARB_BURST_TIME, STATE0);
 	trrds = PHM_GET_FIELD(burstTime, MC_ARB_BURST_TIME, TRRDS0);
 	trrdl = PHM_GET_FIELD(burstTime, MC_ARB_BURST_TIME, TRRDL0);
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index aa0ee2b46135..2319400a3fcb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -137,7 +137,7 @@ static int smu10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			priv->smu_tables.entry[table_id].table_id);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, (uint8_t *)priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -150,6 +150,7 @@ static int smu10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 {
 	struct smu10_smumgr *priv =
 			(struct smu10_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	PP_ASSERT_WITH_CODE(table_id < MAX_SMU_TABLE,
 			"Invalid SMU Table ID!", return -EINVAL;);
@@ -161,6 +162,8 @@ static int smu10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	smu10_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
index 742b3dc1f6cb..adfbcbe5d113 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
@@ -61,15 +61,29 @@ static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr)
 	uint32_t reg;
 	uint32_t ret;
 
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
+	/* Due to the L1 policy problem under SRIOV, we have to use
+	 * mmMP1_SMN_C2PMSG_103 as the driver response register
+	 */
+	if (hwmgr->pp_one_vf) {
+		reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_103);
 
-	ret = phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
+		ret = phm_wait_for_register_unequal(hwmgr, reg,
+				0, MP1_C2PMSG_103__CONTENT_MASK);
 
-	if (ret)
-		pr_err("No response from smu\n");
+		if (ret)
+			pr_err("No response from smu\n");
 
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103);
+	} else {
+		reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
+
+		ret = phm_wait_for_register_unequal(hwmgr, reg,
+				0, MP1_C2PMSG_90__CONTENT_MASK);
+
+		if (ret)
+			pr_err("No response from smu\n");
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+	}
 }
 
 /*
@@ -83,7 +97,11 @@ static int smu9_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+	if (hwmgr->pp_one_vf) {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_101, msg);
+	} else {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+	}
 
 	return 0;
 }
@@ -101,7 +119,10 @@ int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
 
 	smu9_wait_for_response(hwmgr);
 
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+	if (hwmgr->pp_one_vf)
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103, 0);
+	else
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
 
 	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -127,9 +148,17 @@ int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 
 	smu9_wait_for_response(hwmgr);
 
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
+	/* Due to the L1 policy problem under SRIOV, we have to use
+	 * mmMP1_SMN_C2PMSG_101 as the driver message register and
+	 * mmMP1_SMN_C2PMSG_102 as the driver parameter register.
+	 */
+	if (hwmgr->pp_one_vf) {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_103, 0);
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_102, parameter);
+	} else {
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+		WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
+	}
 
 	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
 
@@ -144,5 +173,8 @@ uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
+	if (hwmgr->pp_one_vf)
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_102);
+	else
+		return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index 0f3836fd9666..715564009089 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -58,7 +58,7 @@ static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			priv->smu_tables.entry[table_id].table_id);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -70,6 +70,13 @@ static int vega10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id)
 {
 	struct vega10_smumgr *priv = hwmgr->smu_backend;
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	/* under sriov, vbios or hypervisor driver
+	 * has already copy table to smc so here only skip it
+	 */
+	if (!hwmgr->not_vf)
+		return 0;
 
 	PP_ASSERT_WITH_CODE(table_id < MAX_SMU_TABLE,
 			"Invalid SMU Table ID!", return -EINVAL);
@@ -81,6 +88,8 @@ static int vega10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
@@ -100,6 +109,14 @@ int vega10_enable_smc_features(struct pp_hwmgr *hwmgr,
 	int msg = enable ? PPSMC_MSG_EnableSmuFeatures :
 			PPSMC_MSG_DisableSmuFeatures;
 
+	/* VF has no permission to change smu feature due
+	 * to security concern even under pp one vf mode
+	 * it still can't do it. For vega10, the smu in
+	 * vbios will enable the appropriate features.
+	 * */
+	if (!hwmgr->not_vf)
+		return 0;
+
 	return smum_send_msg_to_smc_with_parameter(hwmgr,
 			msg, feature_mask);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 90c782c132d2..a3915bfcce81 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -66,7 +66,7 @@ static int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			return -EINVAL);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -84,6 +84,7 @@ static int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 {
 	struct vega12_smumgr *priv =
 			(struct vega12_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 
 	PP_ASSERT_WITH_CODE(table_id < TABLE_COUNT,
 			"Invalid SMU Table ID!", return -EINVAL);
@@ -95,6 +96,8 @@ static int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
index f604612f411f..0db57fb83d30 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
@@ -189,7 +189,7 @@ static int vega20_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			return ret);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -207,6 +207,7 @@ static int vega20_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 {
 	struct vega20_smumgr *priv =
 			(struct vega20_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 	int ret = 0;
 
 	PP_ASSERT_WITH_CODE(table_id < TABLE_COUNT,
@@ -219,6 +220,8 @@ static int vega20_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	PP_ASSERT_WITH_CODE((ret = vega20_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr))) == 0,
@@ -242,11 +245,14 @@ int vega20_set_activity_monitor_coeff(struct pp_hwmgr *hwmgr,
 {
 	struct vega20_smumgr *priv =
 			(struct vega20_smumgr *)(hwmgr->smu_backend);
+	struct amdgpu_device *adev = hwmgr->adev;
 	int ret = 0;
 
 	memcpy(priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].table, table,
 			priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size);
 
+	amdgpu_asic_flush_hdp(adev, NULL);
+
 	PP_ASSERT_WITH_CODE((ret = vega20_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].mc_addr))) == 0,
@@ -290,7 +296,7 @@ int vega20_get_activity_monitor_coeff(struct pp_hwmgr *hwmgr,
 			return ret);
 
 	/* flush hdp cache */
-	adev->nbio.funcs->hdp_flush(adev, NULL);
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].table,
 			priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index ae18fbcb26fb..b0e0d67cd54b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -1114,7 +1114,6 @@ static int vegam_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	SMIO_Pattern vol_level;
 	uint32_t mvdd;
-	uint16_t us_mvdd;
 
 	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
 
@@ -1168,17 +1167,6 @@ static int vegam_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			"in Clock Dependency Table",
 			);
 
-	us_mvdd = 0;
-	if ((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
-			(data->mclk_dpm_key_disabled))
-		us_mvdd = data->vbios_boot_state.mvdd_bootup_value;
-	else {
-		if (!vegam_populate_mvdd_value(hwmgr,
-				data->dpm_table.mclk_table.dpm_levels[0].value,
-				&vol_level))
-			us_mvdd = vol_level.Voltage;
-	}
-
 	if (!vegam_populate_mvdd_value(hwmgr, 0, &vol_level))
 		table->MemoryACPILevel.MinMvdd = PP_HOST_TO_SMC_UL(vol_level.Voltage);
 	else
@@ -1383,11 +1371,16 @@ static int vegam_populate_smc_boot_level(struct pp_hwmgr *hwmgr,
 	result = phm_find_boot_level(&(data->dpm_table.sclk_table),
 			data->vbios_boot_state.sclk_bootup_value,
 			(uint32_t *)&(table->GraphicsBootLevel));
+	if (result)
+		return result;
 
 	result = phm_find_boot_level(&(data->dpm_table.mclk_table),
 			data->vbios_boot_state.mclk_bootup_value,
 			(uint32_t *)&(table->MemoryBootLevel));
 
+	if (result)
+		return result;
+
 	table->BootVddc  = data->vbios_boot_state.vddc_bootup_value *
 			VOLTAGE_SCALE;
 	table->BootVddci = data->vbios_boot_state.vddci_bootup_value *
@@ -1493,7 +1486,7 @@ static int vegam_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 	struct vegam_smumgr *smu_data =
 			(struct vegam_smumgr *)(hwmgr->smu_backend);
 
-	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
+	uint8_t i, stretch_amount, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1532,11 +1525,9 @@ static int vegam_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 			(table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ?
 			table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 5;
 	/* Populate CKS Lookup Table */
-	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
-		stretch_amount2 = 0;
-	else if (stretch_amount == 3 || stretch_amount == 4)
-		stretch_amount2 = 1;
-	else {
+	if (!(stretch_amount == 1 || stretch_amount == 2 ||
+	      stretch_amount == 5 || stretch_amount == 3 ||
+	      stretch_amount == 4)) {
 		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_ClockStretcher);
 		PP_ASSERT_WITH_CODE(false,
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 0d3a3b0a934e..38febd5ca4da 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -338,6 +338,10 @@ static int vega20_tables_init(struct smu_context *smu, struct smu_table *tables)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
+	smu_table->watermarks_table = kzalloc(sizeof(Watermarks_t), GFP_KERNEL);
+	if (!smu_table->watermarks_table)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -2235,7 +2239,7 @@ static int vega20_apply_clocks_adjust_rules(struct smu_context *smu)
 }
 
 static int
-vega20_notify_smc_dispaly_config(struct smu_context *smu)
+vega20_notify_smc_display_config(struct smu_context *smu)
 {
 	struct vega20_dpm_table *dpm_table = smu->smu_dpm.dpm_context;
 	struct vega20_single_dpm_table *memtable = &dpm_table->mem_table;
@@ -3194,6 +3198,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.get_od_percentage = vega20_get_od_percentage,
 	.get_power_profile_mode = vega20_get_power_profile_mode,
 	.set_power_profile_mode = vega20_set_power_profile_mode,
+	.set_performance_level = smu_v11_0_set_performance_level,
 	.set_od_percentage = vega20_set_od_percentage,
 	.set_default_od_settings = vega20_set_default_od_settings,
 	.od_edit_dpm_table = vega20_odn_edit_dpm_table,
@@ -3203,7 +3208,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.pre_display_config_changed = vega20_pre_display_config_changed,
 	.display_config_changed = vega20_display_config_changed,
 	.apply_clocks_adjust_rules = vega20_apply_clocks_adjust_rules,
-	.notify_smc_dispaly_config = vega20_notify_smc_dispaly_config,
+	.notify_smc_display_config = vega20_notify_smc_display_config,
 	.force_dpm_limit_value = vega20_force_dpm_limit_value,
 	.unforce_dpm_levels = vega20_unforce_dpm_levels,
 	.get_profiling_clk_mask = vega20_get_profiling_clk_mask,
@@ -3231,6 +3236,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.check_fw_version = smu_v11_0_check_fw_version,
 	.write_pptable = smu_v11_0_write_pptable,
 	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_driver_table_location = smu_v11_0_set_driver_table_location,
 	.set_tool_table_location = smu_v11_0_set_tool_table_location,
 	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
 	.system_features_control = smu_v11_0_system_features_control,
@@ -3259,7 +3265,8 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.baco_is_support= smu_v11_0_baco_is_support,
 	.baco_get_state = smu_v11_0_baco_get_state,
 	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
+	.baco_enter = smu_v11_0_baco_enter,
+	.baco_exit = smu_v11_0_baco_exit,
 	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
 	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
 	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c
index dfaddbb7da0d..8ae1e1f97a73 100644
--- a/drivers/gpu/drm/arc/arcpgu_crtc.c
+++ b/drivers/gpu/drm/arc/arcpgu_crtc.c
@@ -20,9 +20,10 @@
 
 #define ENCODE_PGU_XY(x, y)	((((x) - 1) << 16) | ((y) - 1))
 
-static struct simplefb_format supported_formats[] = {
-	{ "r5g6b5", 16, {11, 5}, {5, 6}, {0, 5}, {0, 0}, DRM_FORMAT_RGB565 },
-	{ "r8g8b8", 24, {16, 8}, {8, 8}, {0, 8}, {0, 0}, DRM_FORMAT_RGB888 },
+static const u32 arc_pgu_supported_formats[] = {
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
 };
 
 static void arc_pgu_set_pxl_fmt(struct drm_crtc *crtc)
@@ -30,22 +31,24 @@ static void arc_pgu_set_pxl_fmt(struct drm_crtc *crtc)
 	struct arcpgu_drm_private *arcpgu = crtc_to_arcpgu_priv(crtc);
 	const struct drm_framebuffer *fb = crtc->primary->state->fb;
 	uint32_t pixel_format = fb->format->format;
-	struct simplefb_format *format = NULL;
+	u32 format = DRM_FORMAT_INVALID;
 	int i;
+	u32 reg_ctrl;
 
-	for (i = 0; i < ARRAY_SIZE(supported_formats); i++) {
-		if (supported_formats[i].fourcc == pixel_format)
-			format = &supported_formats[i];
+	for (i = 0; i < ARRAY_SIZE(arc_pgu_supported_formats); i++) {
+		if (arc_pgu_supported_formats[i] == pixel_format)
+			format = arc_pgu_supported_formats[i];
 	}
 
-	if (WARN_ON(!format))
+	if (WARN_ON(format == DRM_FORMAT_INVALID))
 		return;
 
-	if (format->fourcc == DRM_FORMAT_RGB888)
-		arc_pgu_write(arcpgu, ARCPGU_REG_CTRL,
-			      arc_pgu_read(arcpgu, ARCPGU_REG_CTRL) |
-					   ARCPGU_MODE_RGB888_MASK);
-
+	reg_ctrl = arc_pgu_read(arcpgu, ARCPGU_REG_CTRL);
+	if (format == DRM_FORMAT_RGB565)
+		reg_ctrl &= ~ARCPGU_MODE_XRGB8888;
+	else
+		reg_ctrl |= ARCPGU_MODE_XRGB8888;
+	arc_pgu_write(arcpgu, ARCPGU_REG_CTRL, reg_ctrl);
 }
 
 static const struct drm_crtc_funcs arc_pgu_crtc_funcs = {
@@ -193,18 +196,15 @@ static struct drm_plane *arc_pgu_plane_init(struct drm_device *drm)
 {
 	struct arcpgu_drm_private *arcpgu = drm->dev_private;
 	struct drm_plane *plane = NULL;
-	u32 formats[ARRAY_SIZE(supported_formats)], i;
 	int ret;
 
 	plane = devm_kzalloc(drm->dev, sizeof(*plane), GFP_KERNEL);
 	if (!plane)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(supported_formats); i++)
-		formats[i] = supported_formats[i].fourcc;
-
 	ret = drm_universal_plane_init(drm, plane, 0xff, &arc_pgu_plane_funcs,
-				       formats, ARRAY_SIZE(formats),
+				       arc_pgu_supported_formats,
+				       ARRAY_SIZE(arc_pgu_supported_formats),
 				       NULL,
 				       DRM_PLANE_TYPE_PRIMARY, NULL);
 	if (ret)
diff --git a/drivers/gpu/drm/arc/arcpgu_regs.h b/drivers/gpu/drm/arc/arcpgu_regs.h
index dab2c380f7f3..b689a382d556 100644
--- a/drivers/gpu/drm/arc/arcpgu_regs.h
+++ b/drivers/gpu/drm/arc/arcpgu_regs.h
@@ -25,7 +25,7 @@
 #define ARCPGU_CTRL_VS_POL_OFST	0x3
 #define ARCPGU_CTRL_HS_POL_MASK	0x1
 #define ARCPGU_CTRL_HS_POL_OFST	0x4
-#define ARCPGU_MODE_RGB888_MASK	0x04
+#define ARCPGU_MODE_XRGB8888	BIT(2)
 #define ARCPGU_STAT_BUSY_MASK	0x02
 
 #endif
diff --git a/drivers/gpu/drm/arm/display/Kconfig b/drivers/gpu/drm/arm/display/Kconfig
index e87ff8623076..cec0639e3aa1 100644
--- a/drivers/gpu/drm/arm/display/Kconfig
+++ b/drivers/gpu/drm/arm/display/Kconfig
@@ -12,9 +12,3 @@ config DRM_KOMEDA
 	  Processor driver. It supports the D71 variants of the hardware.
 
 	  If compiled as a module it will be called komeda.
-
-config DRM_KOMEDA_ERROR_PRINT
-	bool "Enable komeda error print"
-	depends on DRM_KOMEDA
-	help
-	  Choose this option to enable error printing.
diff --git a/drivers/gpu/drm/arm/display/include/malidp_product.h b/drivers/gpu/drm/arm/display/include/malidp_product.h
index 1053b11352eb..16a8a2c22c42 100644
--- a/drivers/gpu/drm/arm/display/include/malidp_product.h
+++ b/drivers/gpu/drm/arm/display/include/malidp_product.h
@@ -18,7 +18,8 @@
 #define MALIDP_CORE_ID_STATUS(__core_id)     (((__u32)(__core_id)) & 0xFF)
 
 /* Mali-display product IDs */
-#define MALIDP_D71_PRODUCT_ID   0x0071
+#define MALIDP_D71_PRODUCT_ID	0x0071
+#define MALIDP_D32_PRODUCT_ID	0x0032
 
 union komeda_config_id {
 	struct {
diff --git a/drivers/gpu/drm/arm/display/komeda/Makefile b/drivers/gpu/drm/arm/display/komeda/Makefile
index f095a1c68ac7..1931a7fa1a14 100644
--- a/drivers/gpu/drm/arm/display/komeda/Makefile
+++ b/drivers/gpu/drm/arm/display/komeda/Makefile
@@ -16,12 +16,11 @@ komeda-y := \
 	komeda_crtc.o \
 	komeda_plane.o \
 	komeda_wb_connector.o \
-	komeda_private_obj.o
+	komeda_private_obj.o \
+	komeda_event.o
 
 komeda-y += \
 	d71/d71_dev.o \
 	d71/d71_component.o
 
-komeda-$(CONFIG_DRM_KOMEDA_ERROR_PRINT) += komeda_event.o
-
 obj-$(CONFIG_DRM_KOMEDA) += komeda.o
diff --git a/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c b/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c
index f0ba26e282c3..8a02ade369db 100644
--- a/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c
+++ b/drivers/gpu/drm/arm/display/komeda/d71/d71_component.c
@@ -1044,7 +1044,9 @@ static int d71_merger_init(struct d71_dev *d71,
 static void d71_improc_update(struct komeda_component *c,
 			      struct komeda_component_state *state)
 {
+	struct drm_crtc_state *crtc_st = state->crtc->state;
 	struct komeda_improc_state *st = to_improc_st(state);
+	struct d71_pipeline *pipe = to_d71_pipeline(c->pipeline);
 	u32 __iomem *reg = c->reg;
 	u32 index, mask = 0, ctrl = 0;
 
@@ -1055,6 +1057,24 @@ static void d71_improc_update(struct komeda_component *c,
 	malidp_write32(reg, BLK_SIZE, HV_SIZE(st->hsize, st->vsize));
 	malidp_write32(reg, IPS_DEPTH, st->color_depth);
 
+	if (crtc_st->color_mgmt_changed) {
+		mask |= IPS_CTRL_FT | IPS_CTRL_RGB;
+
+		if (crtc_st->gamma_lut) {
+			malidp_write_group(pipe->dou_ft_coeff_addr, FT_COEFF0,
+					   KOMEDA_N_GAMMA_COEFFS,
+					   st->fgamma_coeffs);
+			ctrl |= IPS_CTRL_FT; /* enable gamma */
+		}
+
+		if (crtc_st->ctm) {
+			malidp_write_group(reg, IPS_RGB_RGB_COEFF0,
+					   KOMEDA_N_CTM_COEFFS,
+					   st->ctm_coeffs);
+			ctrl |= IPS_CTRL_RGB; /* enable gamut */
+		}
+	}
+
 	mask |= IPS_CTRL_YUV | IPS_CTRL_CHD422 | IPS_CTRL_CHD420;
 
 	/* config color format */
@@ -1250,7 +1270,7 @@ static int d71_timing_ctrlr_init(struct d71_dev *d71,
 
 	ctrlr = to_ctrlr(c);
 
-	ctrlr->supports_dual_link = true;
+	ctrlr->supports_dual_link = d71->supports_dual_link;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c b/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c
index 822b23a1ce75..00fa56c29b3e 100644
--- a/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c
+++ b/drivers/gpu/drm/arm/display/komeda/d71/d71_dev.c
@@ -20,8 +20,10 @@ static u64 get_lpu_event(struct d71_pipeline *d71_pipeline)
 		evts |= KOMEDA_EVENT_IBSY;
 	if (raw_status & LPU_IRQ_EOW)
 		evts |= KOMEDA_EVENT_EOW;
+	if (raw_status & LPU_IRQ_OVR)
+		evts |= KOMEDA_EVENT_OVR;
 
-	if (raw_status & (LPU_IRQ_ERR | LPU_IRQ_IBSY)) {
+	if (raw_status & (LPU_IRQ_ERR | LPU_IRQ_IBSY | LPU_IRQ_OVR)) {
 		u32 restore = 0, tbu_status;
 		/* Check error of LPU status */
 		status = malidp_read32(reg, BLK_STATUS);
@@ -45,6 +47,15 @@ static u64 get_lpu_event(struct d71_pipeline *d71_pipeline)
 			restore |= LPU_STATUS_ACE3;
 			evts |= KOMEDA_ERR_ACE3;
 		}
+		if (status & LPU_STATUS_FEMPTY) {
+			restore |= LPU_STATUS_FEMPTY;
+			evts |= KOMEDA_EVENT_EMPTY;
+		}
+		if (status & LPU_STATUS_FFULL) {
+			restore |= LPU_STATUS_FFULL;
+			evts |= KOMEDA_EVENT_FULL;
+		}
+
 		if (restore != 0)
 			malidp_write32_mask(reg, BLK_STATUS, restore, 0);
 
@@ -371,23 +382,33 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 		goto err_cleanup;
 	}
 
-	/* probe PERIPH */
+	/* Only the legacy HW has the periph block, the newer merges the periph
+	 * into GCU
+	 */
 	value = malidp_read32(d71->periph_addr, BLK_BLOCK_INFO);
-	if (BLOCK_INFO_BLK_TYPE(value) != D71_BLK_TYPE_PERIPH) {
-		DRM_ERROR("access blk periph but got blk: %d.\n",
-			  BLOCK_INFO_BLK_TYPE(value));
-		err = -EINVAL;
-		goto err_cleanup;
+	if (BLOCK_INFO_BLK_TYPE(value) != D71_BLK_TYPE_PERIPH)
+		d71->periph_addr = NULL;
+
+	if (d71->periph_addr) {
+		/* probe PERIPHERAL in legacy HW */
+		value = malidp_read32(d71->periph_addr, PERIPH_CONFIGURATION_ID);
+
+		d71->max_line_size	= value & PERIPH_MAX_LINE_SIZE ? 4096 : 2048;
+		d71->max_vsize		= 4096;
+		d71->num_rich_layers	= value & PERIPH_NUM_RICH_LAYERS ? 2 : 1;
+		d71->supports_dual_link	= !!(value & PERIPH_SPLIT_EN);
+		d71->integrates_tbu	= !!(value & PERIPH_TBU_EN);
+	} else {
+		value = malidp_read32(d71->gcu_addr, GCU_CONFIGURATION_ID0);
+		d71->max_line_size	= GCU_MAX_LINE_SIZE(value);
+		d71->max_vsize		= GCU_MAX_NUM_LINES(value);
+
+		value = malidp_read32(d71->gcu_addr, GCU_CONFIGURATION_ID1);
+		d71->num_rich_layers	= GCU_NUM_RICH_LAYERS(value);
+		d71->supports_dual_link	= GCU_DISPLAY_SPLIT_EN(value);
+		d71->integrates_tbu	= GCU_DISPLAY_TBU_EN(value);
 	}
 
-	value = malidp_read32(d71->periph_addr, PERIPH_CONFIGURATION_ID);
-
-	d71->max_line_size	= value & PERIPH_MAX_LINE_SIZE ? 4096 : 2048;
-	d71->max_vsize		= 4096;
-	d71->num_rich_layers	= value & PERIPH_NUM_RICH_LAYERS ? 2 : 1;
-	d71->supports_dual_link	= value & PERIPH_SPLIT_EN ? true : false;
-	d71->integrates_tbu	= value & PERIPH_TBU_EN ? true : false;
-
 	for (i = 0; i < d71->num_pipelines; i++) {
 		pipe = komeda_pipeline_add(mdev, sizeof(struct d71_pipeline),
 					   &d71_pipeline_funcs);
@@ -414,8 +435,11 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 		d71->pipes[i] = to_d71_pipeline(pipe);
 	}
 
-	/* loop the register blks and probe */
-	i = 2; /* exclude GCU and PERIPH */
+	/* loop the register blks and probe.
+	 * NOTE: d71->num_blocks includes reserved blocks.
+	 * d71->num_blocks = GCU + valid blocks + reserved blocks
+	 */
+	i = 1; /* exclude GCU */
 	offset = D71_BLOCK_SIZE; /* skip GCU */
 	while (i < d71->num_blocks) {
 		blk_base = mdev->reg_base + (offset >> 2);
@@ -425,9 +449,9 @@ static int d71_enum_resources(struct komeda_dev *mdev)
 			err = d71_probe_block(d71, &blk, blk_base);
 			if (err)
 				goto err_cleanup;
-			i++;
 		}
 
+		i++;
 		offset += D71_BLOCK_SIZE;
 	}
 
@@ -594,10 +618,26 @@ static const struct komeda_dev_funcs d71_chip_funcs = {
 const struct komeda_dev_funcs *
 d71_identify(u32 __iomem *reg_base, struct komeda_chip_info *chip)
 {
+	const struct komeda_dev_funcs *funcs;
+	u32 product_id;
+
+	chip->core_id = malidp_read32(reg_base, GLB_CORE_ID);
+
+	product_id = MALIDP_CORE_ID_PRODUCT_ID(chip->core_id);
+
+	switch (product_id) {
+	case MALIDP_D71_PRODUCT_ID:
+	case MALIDP_D32_PRODUCT_ID:
+		funcs = &d71_chip_funcs;
+		break;
+	default:
+		DRM_ERROR("Unsupported product: 0x%x\n", product_id);
+		return NULL;
+	}
+
 	chip->arch_id	= malidp_read32(reg_base, GLB_ARCH_ID);
-	chip->core_id	= malidp_read32(reg_base, GLB_CORE_ID);
 	chip->core_info	= malidp_read32(reg_base, GLB_CORE_INFO);
 	chip->bus_width	= D71_BUS_WIDTH_16_BYTES;
 
-	return &d71_chip_funcs;
+	return funcs;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h b/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h
index 1727dc993909..e80172a0b320 100644
--- a/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h
+++ b/drivers/gpu/drm/arm/display/komeda/d71/d71_regs.h
@@ -72,6 +72,19 @@
 #define GCU_CONTROL_MODE(x)	((x) & 0x7)
 #define GCU_CONTROL_SRST	BIT(16)
 
+/* GCU_CONFIGURATION registers */
+#define GCU_CONFIGURATION_ID0	0x100
+#define GCU_CONFIGURATION_ID1	0x104
+
+/* GCU configuration */
+#define GCU_MAX_LINE_SIZE(x)	((x) & 0xFFFF)
+#define GCU_MAX_NUM_LINES(x)	((x) >> 16)
+#define GCU_NUM_RICH_LAYERS(x)	((x) & 0x7)
+#define GCU_NUM_PIPELINES(x)	(((x) >> 3) & 0x7)
+#define GCU_NUM_SCALERS(x)	(((x) >> 6) & 0x7)
+#define GCU_DISPLAY_SPLIT_EN(x)	(((x) >> 16) & 0x1)
+#define GCU_DISPLAY_TBU_EN(x)	(((x) >> 17) & 0x1)
+
 /* GCU opmode */
 #define INACTIVE_MODE		0
 #define TBU_CONNECT_MODE	1
@@ -162,6 +175,7 @@
 #define TBU_DOUTSTDCAPB_MASK	0x3F
 
 /* LPU_IRQ_BITS */
+#define LPU_IRQ_OVR		BIT(9)
 #define LPU_IRQ_IBSY		BIT(10)
 #define LPU_IRQ_ERR		BIT(11)
 #define LPU_IRQ_EOW		BIT(12)
@@ -172,6 +186,8 @@
 #define LPU_STATUS_AXIE		BIT(4)
 #define LPU_STATUS_AXIRP	BIT(5)
 #define LPU_STATUS_AXIWP	BIT(6)
+#define LPU_STATUS_FEMPTY	BIT(11)
+#define LPU_STATUS_FFULL	BIT(14)
 #define LPU_STATUS_ACE0		BIT(16)
 #define LPU_STATUS_ACE1		BIT(17)
 #define LPU_STATUS_ACE2		BIT(18)
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
index 9d14a92dbb17..d8e449e6ebda 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.c
@@ -65,3 +65,69 @@ const s32 *komeda_select_yuv2rgb_coeffs(u32 color_encoding, u32 color_range)
 
 	return coeffs;
 }
+
+struct gamma_curve_sector {
+	u32 boundary_start;
+	u32 num_of_segments;
+	u32 segment_width;
+};
+
+struct gamma_curve_segment {
+	u32 start;
+	u32 end;
+};
+
+static struct gamma_curve_sector sector_tbl[] = {
+	{ 0,    4,  4   },
+	{ 16,   4,  4   },
+	{ 32,   4,  8   },
+	{ 64,   4,  16  },
+	{ 128,  4,  32  },
+	{ 256,  4,  64  },
+	{ 512,  16, 32  },
+	{ 1024, 24, 128 },
+};
+
+static void
+drm_lut_to_coeffs(struct drm_property_blob *lut_blob, u32 *coeffs,
+		  struct gamma_curve_sector *sector_tbl, u32 num_sectors)
+{
+	struct drm_color_lut *lut;
+	u32 i, j, in, num = 0;
+
+	if (!lut_blob)
+		return;
+
+	lut = lut_blob->data;
+
+	for (i = 0; i < num_sectors; i++) {
+		for (j = 0; j < sector_tbl[i].num_of_segments; j++) {
+			in = sector_tbl[i].boundary_start +
+			     j * sector_tbl[i].segment_width;
+
+			coeffs[num++] = drm_color_lut_extract(lut[in].red,
+						KOMEDA_COLOR_PRECISION);
+		}
+	}
+
+	coeffs[num] = BIT(KOMEDA_COLOR_PRECISION);
+}
+
+void drm_lut_to_fgamma_coeffs(struct drm_property_blob *lut_blob, u32 *coeffs)
+{
+	drm_lut_to_coeffs(lut_blob, coeffs, sector_tbl, ARRAY_SIZE(sector_tbl));
+}
+
+void drm_ctm_to_coeffs(struct drm_property_blob *ctm_blob, u32 *coeffs)
+{
+	struct drm_color_ctm *ctm;
+	u32 i;
+
+	if (!ctm_blob)
+		return;
+
+	ctm = ctm_blob->data;
+
+	for (i = 0; i < KOMEDA_N_CTM_COEFFS; i++)
+		coeffs[i] = drm_color_ctm_s31_32_to_qm_n(ctm->matrix[i], 3, 12);
+}
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h
index a2df218f58e7..2f4668466112 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_color_mgmt.h
@@ -11,7 +11,15 @@
 #include <drm/drm_color_mgmt.h>
 
 #define KOMEDA_N_YUV2RGB_COEFFS		12
+#define KOMEDA_N_RGB2YUV_COEFFS		12
+#define KOMEDA_COLOR_PRECISION		12
+#define KOMEDA_N_GAMMA_COEFFS		65
+#define KOMEDA_COLOR_LUT_SIZE		BIT(KOMEDA_COLOR_PRECISION)
+#define KOMEDA_N_CTM_COEFFS		9
+
+void drm_lut_to_fgamma_coeffs(struct drm_property_blob *lut_blob, u32 *coeffs);
+void drm_ctm_to_coeffs(struct drm_property_blob *ctm_blob, u32 *coeffs);
 
 const s32 *komeda_select_yuv2rgb_coeffs(u32 color_encoding, u32 color_range);
 
-#endif
+#endif /*_KOMEDA_COLOR_MGMT_H_*/
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
index 252015210fbc..56bd938961ee 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
@@ -5,6 +5,7 @@
  *
  */
 #include <linux/clk.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock.h>
 
 #include <drm/drm_atomic.h>
@@ -274,6 +275,7 @@ static void
 komeda_crtc_atomic_enable(struct drm_crtc *crtc,
 			  struct drm_crtc_state *old)
 {
+	pm_runtime_get_sync(crtc->dev->dev);
 	komeda_crtc_prepare(to_kcrtc(crtc));
 	drm_crtc_vblank_on(crtc);
 	WARN_ON(drm_crtc_vblank_get(crtc));
@@ -372,6 +374,7 @@ komeda_crtc_atomic_disable(struct drm_crtc *crtc,
 	drm_crtc_vblank_put(crtc);
 	drm_crtc_vblank_off(crtc);
 	komeda_crtc_unprepare(kcrtc);
+	pm_runtime_put(crtc->dev->dev);
 }
 
 static void
@@ -617,6 +620,8 @@ static int komeda_crtc_add(struct komeda_kms_dev *kms,
 
 	crtc->port = kcrtc->master->of_output_port;
 
+	drm_crtc_enable_color_mgmt(crtc, 0, true, KOMEDA_COLOR_LUT_SIZE);
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
index 937a6d4c4865..1d767473ba8a 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c
@@ -10,6 +10,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/dma-mapping.h>
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
@@ -27,12 +28,16 @@ static int komeda_register_show(struct seq_file *sf, void *x)
 
 	seq_puts(sf, "\n====== Komeda register dump =========\n");
 
+	pm_runtime_get_sync(mdev->dev);
+
 	if (mdev->funcs->dump_register)
 		mdev->funcs->dump_register(mdev, sf);
 
 	for (i = 0; i < mdev->n_pipelines; i++)
 		komeda_pipeline_dump_register(mdev->pipelines[i], sf);
 
+	pm_runtime_put(mdev->dev);
+
 	return 0;
 }
 
@@ -58,6 +63,8 @@ static void komeda_debugfs_init(struct komeda_dev *mdev)
 	mdev->debugfs_root = debugfs_create_dir("komeda", NULL);
 	debugfs_create_file("register", 0444, mdev->debugfs_root,
 			    mdev, &komeda_register_fops);
+	debugfs_create_x16("err_verbosity", 0664, mdev->debugfs_root,
+			   &mdev->err_verbosity);
 }
 #endif
 
@@ -113,22 +120,14 @@ static struct attribute_group komeda_sysfs_attr_group = {
 	.attrs = komeda_sysfs_entries,
 };
 
-static int komeda_parse_pipe_dt(struct komeda_dev *mdev, struct device_node *np)
+static int komeda_parse_pipe_dt(struct komeda_pipeline *pipe)
 {
-	struct komeda_pipeline *pipe;
+	struct device_node *np = pipe->of_node;
 	struct clk *clk;
-	u32 pipe_id;
-	int ret = 0;
-
-	ret = of_property_read_u32(np, "reg", &pipe_id);
-	if (ret != 0 || pipe_id >= mdev->n_pipelines)
-		return -EINVAL;
-
-	pipe = mdev->pipelines[pipe_id];
 
 	clk = of_clk_get_by_name(np, "pxclk");
 	if (IS_ERR(clk)) {
-		DRM_ERROR("get pxclk for pipeline %d failed!\n", pipe_id);
+		DRM_ERROR("get pxclk for pipeline %d failed!\n", pipe->id);
 		return PTR_ERR(clk);
 	}
 	pipe->pxlclk = clk;
@@ -142,7 +141,6 @@ static int komeda_parse_pipe_dt(struct komeda_dev *mdev, struct device_node *np)
 		of_graph_get_port_by_id(np, KOMEDA_OF_PORT_OUTPUT);
 
 	pipe->dual_link = pipe->of_output_links[0] && pipe->of_output_links[1];
-	pipe->of_node = of_node_get(np);
 
 	return 0;
 }
@@ -151,7 +149,9 @@ static int komeda_parse_dt(struct device *dev, struct komeda_dev *mdev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct device_node *child, *np = dev->of_node;
-	int ret;
+	struct komeda_pipeline *pipe;
+	u32 pipe_id = U32_MAX;
+	int ret = -1;
 
 	mdev->irq  = platform_get_irq(pdev, 0);
 	if (mdev->irq < 0) {
@@ -166,37 +166,44 @@ static int komeda_parse_dt(struct device *dev, struct komeda_dev *mdev)
 	ret = 0;
 
 	for_each_available_child_of_node(np, child) {
-		if (of_node_cmp(child->name, "pipeline") == 0) {
-			ret = komeda_parse_pipe_dt(mdev, child);
-			if (ret) {
-				DRM_ERROR("parse pipeline dt error!\n");
-				of_node_put(child);
-				break;
+		if (of_node_name_eq(child, "pipeline")) {
+			of_property_read_u32(child, "reg", &pipe_id);
+			if (pipe_id >= mdev->n_pipelines) {
+				DRM_WARN("Skip the redundant DT node: pipeline-%u.\n",
+					 pipe_id);
+				continue;
 			}
+			mdev->pipelines[pipe_id]->of_node = of_node_get(child);
 		}
 	}
 
-	return ret;
+	for (pipe_id = 0; pipe_id < mdev->n_pipelines; pipe_id++) {
+		pipe = mdev->pipelines[pipe_id];
+
+		if (!pipe->of_node) {
+			DRM_ERROR("Pipeline-%d doesn't have a DT node.\n",
+				  pipe->id);
+			return -EINVAL;
+		}
+		ret = komeda_parse_pipe_dt(pipe);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 struct komeda_dev *komeda_dev_create(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	const struct komeda_product_data *product;
+	komeda_identify_func komeda_identify;
 	struct komeda_dev *mdev;
-	struct resource *io_res;
 	int err = 0;
 
-	product = of_device_get_match_data(dev);
-	if (!product)
+	komeda_identify = of_device_get_match_data(dev);
+	if (!komeda_identify)
 		return ERR_PTR(-ENODEV);
 
-	io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!io_res) {
-		DRM_ERROR("No registers defined.\n");
-		return ERR_PTR(-ENODEV);
-	}
-
 	mdev = devm_kzalloc(dev, sizeof(*mdev), GFP_KERNEL);
 	if (!mdev)
 		return ERR_PTR(-ENOMEM);
@@ -204,7 +211,7 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 	mutex_init(&mdev->lock);
 
 	mdev->dev = dev;
-	mdev->reg_base = devm_ioremap_resource(dev, io_res);
+	mdev->reg_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(mdev->reg_base)) {
 		DRM_ERROR("Map register space failed.\n");
 		err = PTR_ERR(mdev->reg_base);
@@ -222,11 +229,9 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 
 	clk_prepare_enable(mdev->aclk);
 
-	mdev->funcs = product->identify(mdev->reg_base, &mdev->chip);
-	if (!komeda_product_match(mdev, product->product_id)) {
-		DRM_ERROR("DT configured %x mismatch with real HW %x.\n",
-			  product->product_id,
-			  MALIDP_CORE_ID_PRODUCT_ID(mdev->chip.core_id));
+	mdev->funcs = komeda_identify(mdev->reg_base, &mdev->chip);
+	if (!mdev->funcs) {
+		DRM_ERROR("Failed to identify the HW.\n");
 		err = -ENODEV;
 		goto disable_clk;
 	}
@@ -263,15 +268,6 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 	if (!mdev->iommu)
 		DRM_INFO("continue without IOMMU support!\n");
 
-	if (mdev->iommu && mdev->funcs->connect_iommu) {
-		err = mdev->funcs->connect_iommu(mdev);
-		if (err) {
-			DRM_ERROR("connect iommu failed.\n");
-			mdev->iommu = NULL;
-			goto disable_clk;
-		}
-	}
-
 	clk_disable_unprepare(mdev->aclk);
 
 	err = sysfs_create_group(&dev->kobj, &komeda_sysfs_attr_group);
@@ -280,6 +276,8 @@ struct komeda_dev *komeda_dev_create(struct device *dev)
 		goto err_cleanup;
 	}
 
+	mdev->err_verbosity = KOMEDA_DEV_PRINT_ERR_EVENTS;
+
 #ifdef CONFIG_DEBUG_FS
 	komeda_debugfs_init(mdev);
 #endif
@@ -308,11 +306,6 @@ void komeda_dev_destroy(struct komeda_dev *mdev)
 	if (mdev->aclk)
 		clk_prepare_enable(mdev->aclk);
 
-	if (mdev->iommu && mdev->funcs->disconnect_iommu)
-		if (mdev->funcs->disconnect_iommu(mdev))
-			DRM_ERROR("disconnect iommu failed.\n");
-	mdev->iommu = NULL;
-
 	for (i = 0; i < mdev->n_pipelines; i++) {
 		komeda_pipeline_destroy(mdev, mdev->pipelines[i]);
 		mdev->pipelines[i] = NULL;
@@ -341,44 +334,26 @@ void komeda_dev_destroy(struct komeda_dev *mdev)
 
 int komeda_dev_resume(struct komeda_dev *mdev)
 {
-	int ret = 0;
-
 	clk_prepare_enable(mdev->aclk);
 
-	if (mdev->iommu && mdev->funcs->connect_iommu) {
-		ret = mdev->funcs->connect_iommu(mdev);
-		if (ret < 0) {
-			DRM_ERROR("connect iommu failed.\n");
-			goto disable_clk;
-		}
-	}
-
-	ret = mdev->funcs->enable_irq(mdev);
+	mdev->funcs->enable_irq(mdev);
 
-disable_clk:
-	clk_disable_unprepare(mdev->aclk);
+	if (mdev->iommu && mdev->funcs->connect_iommu)
+		if (mdev->funcs->connect_iommu(mdev))
+			DRM_ERROR("connect iommu failed.\n");
 
-	return ret;
+	return 0;
 }
 
 int komeda_dev_suspend(struct komeda_dev *mdev)
 {
-	int ret = 0;
-
-	clk_prepare_enable(mdev->aclk);
-
-	if (mdev->iommu && mdev->funcs->disconnect_iommu) {
-		ret = mdev->funcs->disconnect_iommu(mdev);
-		if (ret < 0) {
+	if (mdev->iommu && mdev->funcs->disconnect_iommu)
+		if (mdev->funcs->disconnect_iommu(mdev))
 			DRM_ERROR("disconnect iommu failed.\n");
-			goto disable_clk;
-		}
-	}
 
-	ret = mdev->funcs->disable_irq(mdev);
+	mdev->funcs->disable_irq(mdev);
 
-disable_clk:
 	clk_disable_unprepare(mdev->aclk);
 
-	return ret;
+	return 0;
 }
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.h b/drivers/gpu/drm/arm/display/komeda/komeda_dev.h
index 414200233b64..ce27f2f27c24 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.h
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.h
@@ -20,6 +20,8 @@
 #define KOMEDA_EVENT_OVR		BIT_ULL(4)
 #define KOMEDA_EVENT_EOW		BIT_ULL(5)
 #define KOMEDA_EVENT_MODE		BIT_ULL(6)
+#define KOMEDA_EVENT_FULL		BIT_ULL(7)
+#define KOMEDA_EVENT_EMPTY		BIT_ULL(8)
 
 #define KOMEDA_ERR_TETO			BIT_ULL(14)
 #define KOMEDA_ERR_TEMR			BIT_ULL(15)
@@ -49,12 +51,15 @@
 	KOMEDA_ERR_ZME		| KOMEDA_ERR_MERR	| KOMEDA_ERR_TCF |\
 	KOMEDA_ERR_TTNG		| KOMEDA_ERR_TTF)
 
-#define KOMEDA_WARN_EVENTS	KOMEDA_ERR_CSCE
+#define KOMEDA_WARN_EVENTS	\
+	(KOMEDA_ERR_CSCE | KOMEDA_EVENT_FULL | KOMEDA_EVENT_EMPTY)
 
-/* malidp device id */
-enum {
-	MALI_D71 = 0,
-};
+#define KOMEDA_INFO_EVENTS (0 \
+			    | KOMEDA_EVENT_VSYNC \
+			    | KOMEDA_EVENT_FLIP \
+			    | KOMEDA_EVENT_EOW \
+			    | KOMEDA_EVENT_MODE \
+			    )
 
 /* pipeline DT ports */
 enum {
@@ -69,12 +74,6 @@ struct komeda_chip_info {
 	u32 bus_width;
 };
 
-struct komeda_product_data {
-	u32 product_id;
-	const struct komeda_dev_funcs *(*identify)(u32 __iomem *reg,
-					     struct komeda_chip_info *info);
-};
-
 struct komeda_dev;
 
 struct komeda_events {
@@ -202,6 +201,23 @@ struct komeda_dev {
 
 	/** @debugfs_root: root directory of komeda debugfs */
 	struct dentry *debugfs_root;
+	/**
+	 * @err_verbosity: bitmask for how much extra info to print on error
+	 *
+	 * See KOMEDA_DEV_* macros for details. Low byte contains the debug
+	 * level categories, the high byte contains extra debug options.
+	 */
+	u16 err_verbosity;
+	/* Print a single line per error per frame with error events. */
+#define KOMEDA_DEV_PRINT_ERR_EVENTS BIT(0)
+	/* Print a single line per warning per frame with error events. */
+#define KOMEDA_DEV_PRINT_WARN_EVENTS BIT(1)
+	/* Print a single line per info event per frame with error events. */
+#define KOMEDA_DEV_PRINT_INFO_EVENTS BIT(2)
+	/* Dump DRM state on an error or warning event. */
+#define KOMEDA_DEV_PRINT_DUMP_STATE_ON_EVENT BIT(8)
+	/* Disable rate limiting of event prints (normally one per commit) */
+#define KOMEDA_DEV_PRINT_DISABLE_RATELIMIT BIT(12)
 };
 
 static inline bool
@@ -210,6 +226,9 @@ komeda_product_match(struct komeda_dev *mdev, u32 target)
 	return MALIDP_CORE_ID_PRODUCT_ID(mdev->chip.core_id) == target;
 }
 
+typedef const struct komeda_dev_funcs *
+(*komeda_identify_func)(u32 __iomem *reg, struct komeda_chip_info *chip);
+
 const struct komeda_dev_funcs *
 d71_identify(u32 __iomem *reg, struct komeda_chip_info *chip);
 
@@ -218,11 +237,7 @@ void komeda_dev_destroy(struct komeda_dev *mdev);
 
 struct komeda_dev *dev_to_mdev(struct device *dev);
 
-#ifdef CONFIG_DRM_KOMEDA_ERROR_PRINT
-void komeda_print_events(struct komeda_events *evts);
-#else
-static inline void komeda_print_events(struct komeda_events *evts) {}
-#endif
+void komeda_print_events(struct komeda_events *evts, struct drm_device *dev);
 
 int komeda_dev_resume(struct komeda_dev *mdev);
 int komeda_dev_suspend(struct komeda_dev *mdev);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c
index d6c2222c5d33..ea5cd1e17304 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_drv.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_drv.c
@@ -33,6 +33,12 @@ static void komeda_unbind(struct device *dev)
 		return;
 
 	komeda_kms_detach(mdrv->kms);
+
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	else
+		komeda_dev_suspend(mdrv->mdev);
+
 	komeda_dev_destroy(mdrv->mdev);
 
 	dev_set_drvdata(dev, NULL);
@@ -54,6 +60,10 @@ static int komeda_bind(struct device *dev)
 		goto free_mdrv;
 	}
 
+	pm_runtime_enable(dev);
+	if (!pm_runtime_enabled(dev))
+		komeda_dev_resume(mdrv->mdev);
+
 	mdrv->kms = komeda_kms_attach(mdrv->mdev);
 	if (IS_ERR(mdrv->kms)) {
 		err = PTR_ERR(mdrv->kms);
@@ -65,6 +75,11 @@ static int komeda_bind(struct device *dev)
 	return 0;
 
 destroy_mdev:
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	else
+		komeda_dev_suspend(mdrv->mdev);
+
 	komeda_dev_destroy(mdrv->mdev);
 
 free_mdrv:
@@ -123,29 +138,37 @@ static int komeda_platform_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct komeda_product_data komeda_products[] = {
-	[MALI_D71] = {
-		.product_id = MALIDP_D71_PRODUCT_ID,
-		.identify = d71_identify,
-	},
-};
-
 static const struct of_device_id komeda_of_match[] = {
-	{ .compatible = "arm,mali-d71", .data = &komeda_products[MALI_D71], },
+	{ .compatible = "arm,mali-d71", .data = d71_identify, },
+	{ .compatible = "arm,mali-d32", .data = d71_identify, },
 	{},
 };
 
 MODULE_DEVICE_TABLE(of, komeda_of_match);
 
+static int komeda_rt_pm_suspend(struct device *dev)
+{
+	struct komeda_drv *mdrv = dev_get_drvdata(dev);
+
+	return komeda_dev_suspend(mdrv->mdev);
+}
+
+static int komeda_rt_pm_resume(struct device *dev)
+{
+	struct komeda_drv *mdrv = dev_get_drvdata(dev);
+
+	return komeda_dev_resume(mdrv->mdev);
+}
+
 static int __maybe_unused komeda_pm_suspend(struct device *dev)
 {
 	struct komeda_drv *mdrv = dev_get_drvdata(dev);
-	struct drm_device *drm = &mdrv->kms->base;
 	int res;
 
-	res = drm_mode_config_helper_suspend(drm);
+	res = drm_mode_config_helper_suspend(&mdrv->kms->base);
 
-	komeda_dev_suspend(mdrv->mdev);
+	if (!pm_runtime_status_suspended(dev))
+		komeda_dev_suspend(mdrv->mdev);
 
 	return res;
 }
@@ -153,15 +176,16 @@ static int __maybe_unused komeda_pm_suspend(struct device *dev)
 static int __maybe_unused komeda_pm_resume(struct device *dev)
 {
 	struct komeda_drv *mdrv = dev_get_drvdata(dev);
-	struct drm_device *drm = &mdrv->kms->base;
 
-	komeda_dev_resume(mdrv->mdev);
+	if (!pm_runtime_status_suspended(dev))
+		komeda_dev_resume(mdrv->mdev);
 
-	return drm_mode_config_helper_resume(drm);
+	return drm_mode_config_helper_resume(&mdrv->kms->base);
 }
 
 static const struct dev_pm_ops komeda_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(komeda_pm_suspend, komeda_pm_resume)
+	SET_RUNTIME_PM_OPS(komeda_rt_pm_suspend, komeda_rt_pm_resume, NULL)
 };
 
 static struct platform_driver komeda_platform_driver = {
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_event.c b/drivers/gpu/drm/arm/display/komeda/komeda_event.c
index a36fb86cc054..53f944e66dfc 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_event.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_event.c
@@ -4,6 +4,7 @@
  * Author: James.Qian.Wang <james.qian.wang@arm.com>
  *
  */
+#include <drm/drm_atomic.h>
 #include <drm/drm_print.h>
 
 #include "komeda_dev.h"
@@ -16,6 +17,7 @@ struct komeda_str {
 
 /* return 0 on success,  < 0 on no space.
  */
+__printf(2, 3)
 static int komeda_sprintf(struct komeda_str *str, const char *fmt, ...)
 {
 	va_list args;
@@ -76,6 +78,8 @@ static void evt_str(struct komeda_str *str, u64 events)
 
 	/* LPU errors or events */
 	evt_sprintf(str, events & KOMEDA_EVENT_IBSY, "IBSY|");
+	evt_sprintf(str, events & KOMEDA_EVENT_EMPTY, "EMPTY|");
+	evt_sprintf(str, events & KOMEDA_EVENT_FULL, "FULL|");
 	evt_sprintf(str, events & KOMEDA_ERR_AXIE, "AXIE|");
 	evt_sprintf(str, events & KOMEDA_ERR_ACE0, "ACE0|");
 	evt_sprintf(str, events & KOMEDA_ERR_ACE1, "ACE1|");
@@ -107,20 +111,31 @@ static bool is_new_frame(struct komeda_events *a)
 	       (KOMEDA_EVENT_FLIP | KOMEDA_EVENT_EOW);
 }
 
-void komeda_print_events(struct komeda_events *evts)
+void komeda_print_events(struct komeda_events *evts, struct drm_device *dev)
 {
-	u64 print_evts = KOMEDA_ERR_EVENTS;
+	u64 print_evts = 0;
 	static bool en_print = true;
+	struct komeda_dev *mdev = dev->dev_private;
+	u16 const err_verbosity = mdev->err_verbosity;
+	u64 evts_mask = evts->global | evts->pipes[0] | evts->pipes[1];
 
 	/* reduce the same msg print, only print the first evt for one frame */
 	if (evts->global || is_new_frame(evts))
 		en_print = true;
-	if (!en_print)
+	if (!(err_verbosity & KOMEDA_DEV_PRINT_DISABLE_RATELIMIT) && !en_print)
 		return;
 
-	if ((evts->global | evts->pipes[0] | evts->pipes[1]) & print_evts) {
+	if (err_verbosity & KOMEDA_DEV_PRINT_ERR_EVENTS)
+		print_evts |= KOMEDA_ERR_EVENTS;
+	if (err_verbosity & KOMEDA_DEV_PRINT_WARN_EVENTS)
+		print_evts |= KOMEDA_WARN_EVENTS;
+	if (err_verbosity & KOMEDA_DEV_PRINT_INFO_EVENTS)
+		print_evts |= KOMEDA_INFO_EVENTS;
+
+	if (evts_mask & print_evts) {
 		char msg[256];
 		struct komeda_str str;
+		struct drm_printer p = drm_info_printer(dev->dev);
 
 		str.str = msg;
 		str.sz  = sizeof(msg);
@@ -134,6 +149,9 @@ void komeda_print_events(struct komeda_events *evts)
 		evt_str(&str, evts->pipes[1]);
 
 		DRM_ERROR("err detect: %s\n", msg);
+		if ((err_verbosity & KOMEDA_DEV_PRINT_DUMP_STATE_ON_EVENT) &&
+		    (evts_mask & (KOMEDA_ERR_EVENTS | KOMEDA_WARN_EVENTS)))
+			drm_state_dump(dev, &p);
 
 		en_print = false;
 	}
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index 52648b4008bc..442d4656150a 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -48,7 +48,7 @@ static irqreturn_t komeda_kms_irq_handler(int irq, void *data)
 	memset(&evts, 0, sizeof(evts));
 	status = mdev->funcs->irq_handler(mdev, &evts);
 
-	komeda_print_events(&evts);
+	komeda_print_events(&evts, drm);
 
 	/* Notify the crtc to handle the events */
 	for (i = 0; i < kms->n_crtcs; i++)
@@ -308,10 +308,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev)
 	if (err)
 		goto free_component_binding;
 
-	err = mdev->funcs->enable_irq(mdev);
-	if (err)
-		goto free_component_binding;
-
 	drm->irq_enabled = true;
 
 	drm_kms_helper_poll_init(drm);
@@ -325,7 +321,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev)
 free_interrupts:
 	drm_kms_helper_poll_fini(drm);
 	drm->irq_enabled = false;
-	mdev->funcs->disable_irq(mdev);
 free_component_binding:
 	component_unbind_all(mdev->dev, drm);
 cleanup_mode_config:
@@ -347,7 +342,6 @@ void komeda_kms_detach(struct komeda_kms_dev *kms)
 	drm_kms_helper_poll_fini(drm);
 	drm_atomic_helper_shutdown(drm);
 	drm->irq_enabled = false;
-	mdev->funcs->disable_irq(mdev);
 	component_unbind_all(mdev->dev, drm);
 	drm_mode_config_cleanup(drm);
 	komeda_kms_cleanup_private_objs(kms);
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h
index bd6ca7c87037..ac8725e24853 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline.h
@@ -11,6 +11,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include "malidp_utils.h"
+#include "komeda_color_mgmt.h"
 
 #define KOMEDA_MAX_PIPELINES		2
 #define KOMEDA_PIPELINE_MAX_LAYERS	4
@@ -327,6 +328,8 @@ struct komeda_improc_state {
 	struct komeda_component_state base;
 	u8 color_format, color_depth;
 	u16 hsize, vsize;
+	u32 fgamma_coeffs[KOMEDA_N_GAMMA_COEFFS];
+	u32 ctm_coeffs[KOMEDA_N_CTM_COEFFS];
 };
 
 /* display timing controller */
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index 52750116aa19..8f32ae7c25d0 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -802,6 +802,12 @@ komeda_improc_validate(struct komeda_improc *improc,
 		st->color_format = BIT(__ffs(avail_formats));
 	}
 
+	if (kcrtc_st->base.color_mgmt_changed) {
+		drm_lut_to_fgamma_coeffs(kcrtc_st->base.gamma_lut,
+					 st->fgamma_coeffs);
+		drm_ctm_to_coeffs(kcrtc_st->base.ctm, st->ctm_coeffs);
+	}
+
 	komeda_component_add_input(&st->base, &dflow->input, 0);
 	komeda_component_set_output(&dflow->input, &improc->base, 0);
 
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 3c70a53813bf..37715cc6064e 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -512,7 +512,7 @@ static int malidp_de_plane_check(struct drm_plane *plane,
 	int i, ret;
 	unsigned int block_w, block_h;
 
-	if (!state->crtc || !state->fb)
+	if (!state->crtc || WARN_ON(!state->fb))
 		return 0;
 
 	fb = state->fb;
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index 090cc0d699ae..ac8a78bfda03 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -16,7 +16,7 @@
 #include "armada_fb.h"
 #include "armada_gem.h"
 
-static /*const*/ struct fb_ops armada_fb_ops = {
+static const struct fb_ops armada_fb_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_fillrect	= drm_fb_helper_cfb_fillrect,
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 93cf8b8bfcff..976685f2939e 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -461,16 +461,6 @@ static void armada_gem_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
 	kfree(sgt);
 }
 
-static void *armada_gem_dmabuf_no_kmap(struct dma_buf *buf, unsigned long n)
-{
-	return NULL;
-}
-
-static void
-armada_gem_dmabuf_no_kunmap(struct dma_buf *buf, unsigned long n, void *addr)
-{
-}
-
 static int
 armada_gem_dmabuf_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
 {
@@ -481,8 +471,6 @@ static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = {
 	.map_dma_buf	= armada_gem_prime_map_dma_buf,
 	.unmap_dma_buf	= armada_gem_prime_unmap_dma_buf,
 	.release	= drm_gem_dmabuf_release,
-	.map		= armada_gem_dmabuf_no_kmap,
-	.unmap		= armada_gem_dmabuf_no_kunmap,
 	.mmap		= armada_gem_dmabuf_mmap,
 };
 
diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
index 1f17794b0890..30aa73a5d9b7 100644
--- a/drivers/gpu/drm/ast/ast_drv.c
+++ b/drivers/gpu/drm/ast/ast_drv.c
@@ -33,7 +33,6 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_vram_helper.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_probe_helper.h>
 
 #include "ast_drv.h"
@@ -86,9 +85,42 @@ static void ast_kick_out_firmware_fb(struct pci_dev *pdev)
 
 static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	struct drm_device *dev;
+	int ret;
+
 	ast_kick_out_firmware_fb(pdev);
 
-	return drm_get_pci_dev(pdev, ent, &driver);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = ast_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_ast_driver_unload;
+
+	return 0;
+
+err_ast_driver_unload:
+	ast_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+
 }
 
 static void
@@ -96,17 +128,19 @@ ast_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-	drm_put_dev(dev);
+	drm_dev_unregister(dev);
+	ast_driver_unload(dev);
+	drm_dev_put(dev);
 }
 
-
-
 static int ast_drm_freeze(struct drm_device *dev)
 {
-	drm_kms_helper_poll_disable(dev);
-	pci_save_state(dev->pdev);
-	drm_fb_helper_set_suspend_unlocked(dev->fb_helper, true);
+	int error;
 
+	error = drm_mode_config_helper_suspend(dev);
+	if (error)
+		return error;
+	pci_save_state(dev->pdev);
 	return 0;
 }
 
@@ -114,11 +148,7 @@ static int ast_drm_thaw(struct drm_device *dev)
 {
 	ast_post_gpu(dev);
 
-	drm_mode_config_reset(dev);
-	drm_helper_resume_force_mode(dev);
-	drm_fb_helper_set_suspend_unlocked(dev->fb_helper, false);
-
-	return 0;
+	return drm_mode_config_helper_resume(dev);
 }
 
 static int ast_drm_resume(struct drm_device *dev)
@@ -131,8 +161,6 @@ static int ast_drm_resume(struct drm_device *dev)
 	ret = ast_drm_thaw(dev);
 	if (ret)
 		return ret;
-
-	drm_kms_helper_poll_enable(dev);
 	return 0;
 }
 
@@ -150,6 +178,7 @@ static int ast_pm_suspend(struct device *dev)
 	pci_set_power_state(pdev, PCI_D3hot);
 	return 0;
 }
+
 static int ast_pm_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -165,7 +194,6 @@ static int ast_pm_freeze(struct device *dev)
 	if (!ddev || !ddev->dev_private)
 		return -ENODEV;
 	return ast_drm_freeze(ddev);
-
 }
 
 static int ast_pm_thaw(struct device *dev)
@@ -203,10 +231,9 @@ static struct pci_driver ast_pci_driver = {
 DEFINE_DRM_GEM_FOPS(ast_fops);
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_MODESET | DRIVER_GEM,
-
-	.load = ast_driver_load,
-	.unload = ast_driver_unload,
+	.driver_features = DRIVER_ATOMIC |
+			   DRIVER_GEM |
+			   DRIVER_MODESET,
 
 	.fops = &ast_fops,
 	.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index ff161bd622f3..f5d8780776ae 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -121,6 +121,9 @@ struct ast_private {
 		unsigned int next_index;
 	} cursor;
 
+	struct drm_plane primary_plane;
+	struct drm_plane cursor_plane;
+
 	bool support_wide_screen;
 	enum {
 		ast_use_p2a,
@@ -137,8 +140,6 @@ struct ast_private {
 int ast_driver_load(struct drm_device *dev, unsigned long flags);
 void ast_driver_unload(struct drm_device *dev);
 
-struct ast_gem_object;
-
 #define AST_IO_AR_PORT_WRITE		(0x40)
 #define AST_IO_MISC_PORT_WRITE		(0x42)
 #define AST_IO_VGA_ENABLE_PORT		(0x43)
@@ -280,6 +281,17 @@ struct ast_vbios_mode_info {
 	const struct ast_vbios_enhtable *enh_table;
 };
 
+struct ast_crtc_state {
+	struct drm_crtc_state base;
+
+	/* Last known format of primary plane */
+	const struct drm_format_info *format;
+
+	struct ast_vbios_mode_info vbios_mode_info;
+};
+
+#define to_ast_crtc_state(state) container_of(state, struct ast_crtc_state, base)
+
 extern int ast_mode_init(struct drm_device *dev);
 extern void ast_mode_fini(struct drm_device *dev);
 
@@ -289,10 +301,6 @@ extern void ast_mode_fini(struct drm_device *dev);
 int ast_mm_init(struct ast_private *ast);
 void ast_mm_fini(struct ast_private *ast);
 
-int ast_gem_create(struct drm_device *dev,
-		   u32 size, bool iskernel,
-		   struct drm_gem_object **obj);
-
 /* ast post */
 void ast_enable_vga(struct drm_device *dev);
 void ast_enable_mmio(struct drm_device *dev);
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index 21715d6a9b56..b79f484e9bd2 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -28,6 +28,7 @@
 
 #include <linux/pci.h>
 
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
@@ -387,8 +388,33 @@ static int ast_get_dram_info(struct drm_device *dev)
 	return 0;
 }
 
+enum drm_mode_status ast_mode_config_mode_valid(struct drm_device *dev,
+						const struct drm_display_mode *mode)
+{
+	static const unsigned long max_bpp = 4; /* DRM_FORMAT_XRGBA8888 */
+
+	struct ast_private *ast = dev->dev_private;
+	unsigned long fbsize, fbpages, max_fbpages;
+
+	/* To support double buffering, a framebuffer may not
+	 * consume more than half of the available VRAM.
+	 */
+	max_fbpages = (ast->vram_size / 2) >> PAGE_SHIFT;
+
+	fbsize = mode->hdisplay * mode->vdisplay * max_bpp;
+	fbpages = DIV_ROUND_UP(fbsize, PAGE_SIZE);
+
+	if (fbpages > max_fbpages)
+		return MODE_MEM;
+
+	return MODE_OK;
+}
+
 static const struct drm_mode_config_funcs ast_mode_funcs = {
-	.fb_create = drm_gem_fb_create
+	.fb_create = drm_gem_fb_create,
+	.mode_valid = ast_mode_config_mode_valid,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static u32 ast_get_vram_info(struct drm_device *dev)
@@ -506,6 +532,8 @@ int ast_driver_load(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto out_free;
 
+	drm_mode_config_reset(dev);
+
 	ret = drm_fbdev_generic_setup(dev, 32);
 	if (ret)
 		goto out_free;
@@ -535,27 +563,3 @@ void ast_driver_unload(struct drm_device *dev)
 	pci_iounmap(dev->pdev, ast->regs);
 	kfree(ast);
 }
-
-int ast_gem_create(struct drm_device *dev,
-		   u32 size, bool iskernel,
-		   struct drm_gem_object **obj)
-{
-	struct drm_gem_vram_object *gbo;
-	int ret;
-
-	*obj = NULL;
-
-	size = roundup(size, PAGE_SIZE);
-	if (size == 0)
-		return -EINVAL;
-
-	gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev, size, 0, false);
-	if (IS_ERR(gbo)) {
-		ret = PTR_ERR(gbo);
-		if (ret != -ERESTARTSYS)
-			DRM_ERROR("failed to allocate GEM object\n");
-		return ret;
-	}
-	*obj = &gbo->bo.base;
-	return 0;
-}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index b13eaa2619ab..34608f0499eb 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -31,6 +31,9 @@
 #include <linux/export.h>
 #include <linux/pci.h>
 
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_atomic_state_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fourcc.h>
@@ -43,11 +46,14 @@
 
 static struct ast_i2c_chan *ast_i2c_create(struct drm_device *dev);
 static void ast_i2c_destroy(struct ast_i2c_chan *i2c);
-static int ast_cursor_set(struct drm_crtc *crtc,
-			  struct drm_file *file_priv,
-			  uint32_t handle,
-			  uint32_t width,
-			  uint32_t height);
+static int ast_cursor_move(struct drm_crtc *crtc,
+			   int x, int y);
+
+
+static u32 copy_cursor_image(u8 *src, u8 *dst, int width, int height);
+static int ast_cursor_update(void *dst, void *src, unsigned int width,
+			     unsigned int height);
+static void ast_cursor_set_base(struct ast_private *ast, u64 address);
 static int ast_cursor_move(struct drm_crtc *crtc,
 			   int x, int y);
 
@@ -65,9 +71,8 @@ static inline void ast_load_palette_index(struct ast_private *ast,
 	ast_io_read8(ast, AST_IO_SEQ_PORT);
 }
 
-static void ast_crtc_load_lut(struct drm_crtc *crtc)
+static void ast_crtc_load_lut(struct ast_private *ast, struct drm_crtc *crtc)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	u16 *r, *g, *b;
 	int i;
 
@@ -82,36 +87,32 @@ static void ast_crtc_load_lut(struct drm_crtc *crtc)
 		ast_load_palette_index(ast, i, *r++ >> 8, *g++ >> 8, *b++ >> 8);
 }
 
-static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mode *mode,
+static bool ast_get_vbios_mode_info(const struct drm_format_info *format,
+				    const struct drm_display_mode *mode,
 				    struct drm_display_mode *adjusted_mode,
 				    struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	const struct drm_framebuffer *fb = crtc->primary->fb;
-	u32 refresh_rate_index = 0, mode_id, color_index, refresh_rate;
+	u32 refresh_rate_index = 0, refresh_rate;
 	const struct ast_vbios_enhtable *best = NULL;
 	u32 hborder, vborder;
 	bool check_sync;
 
-	switch (fb->format->cpp[0] * 8) {
+	switch (format->cpp[0] * 8) {
 	case 8:
 		vbios_mode->std_table = &vbios_stdtable[VGAModeIndex];
-		color_index = VGAModeIndex - 1;
 		break;
 	case 16:
 		vbios_mode->std_table = &vbios_stdtable[HiCModeIndex];
-		color_index = HiCModeIndex;
 		break;
 	case 24:
 	case 32:
 		vbios_mode->std_table = &vbios_stdtable[TrueCModeIndex];
-		color_index = TrueCModeIndex;
 		break;
 	default:
 		return false;
 	}
 
-	switch (crtc->mode.crtc_hdisplay) {
+	switch (mode->crtc_hdisplay) {
 	case 640:
 		vbios_mode->enh_table = &res_640x480[refresh_rate_index];
 		break;
@@ -122,7 +123,7 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		vbios_mode->enh_table = &res_1024x768[refresh_rate_index];
 		break;
 	case 1280:
-		if (crtc->mode.crtc_vdisplay == 800)
+		if (mode->crtc_vdisplay == 800)
 			vbios_mode->enh_table = &res_1280x800[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1280x1024[refresh_rate_index];
@@ -134,7 +135,7 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		vbios_mode->enh_table = &res_1440x900[refresh_rate_index];
 		break;
 	case 1600:
-		if (crtc->mode.crtc_vdisplay == 900)
+		if (mode->crtc_vdisplay == 900)
 			vbios_mode->enh_table = &res_1600x900[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1600x1200[refresh_rate_index];
@@ -143,7 +144,7 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		vbios_mode->enh_table = &res_1680x1050[refresh_rate_index];
 		break;
 	case 1920:
-		if (crtc->mode.crtc_vdisplay == 1080)
+		if (mode->crtc_vdisplay == 1080)
 			vbios_mode->enh_table = &res_1920x1080[refresh_rate_index];
 		else
 			vbios_mode->enh_table = &res_1920x1200[refresh_rate_index];
@@ -154,7 +155,8 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 
 	refresh_rate = drm_mode_vrefresh(mode);
 	check_sync = vbios_mode->enh_table->flags & WideScreenMode;
-	do {
+
+	while (1) {
 		const struct ast_vbios_enhtable *loop = vbios_mode->enh_table;
 
 		while (loop->refresh_rate != 0xff) {
@@ -178,7 +180,8 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 		if (best || !check_sync)
 			break;
 		check_sync = 0;
-	} while (1);
+	}
+
 	if (best)
 		vbios_mode->enh_table = best;
 
@@ -203,38 +206,67 @@ static bool ast_get_vbios_mode_info(struct drm_crtc *crtc, struct drm_display_mo
 					 vbios_mode->enh_table->vfp +
 					 vbios_mode->enh_table->vsync);
 
-	refresh_rate_index = vbios_mode->enh_table->refresh_rate_index;
-	mode_id = vbios_mode->enh_table->mode_id;
+	return true;
+}
 
-	if (ast->chip == AST1180) {
-		/* TODO 1180 */
-	} else {
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8c, (u8)((color_index & 0xf) << 4));
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8d, refresh_rate_index & 0xff);
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8e, mode_id & 0xff);
-
-		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
-		if (vbios_mode->enh_table->flags & NewModeInfo) {
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92,
-					  fb->format->cpp[0] * 8);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8);
-
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay);
-			ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8);
-		}
+static void ast_set_vbios_color_reg(struct ast_private *ast,
+				    const struct drm_format_info *format,
+				    const struct ast_vbios_mode_info *vbios_mode)
+{
+	u32 color_index;
+
+	switch (format->cpp[0]) {
+	case 1:
+		color_index = VGAModeIndex - 1;
+		break;
+	case 2:
+		color_index = HiCModeIndex;
+		break;
+	case 3:
+	case 4:
+		color_index = TrueCModeIndex;
+	default:
+		return;
 	}
 
-	return true;
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8c, (u8)((color_index & 0x0f) << 4));
+
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
+
+	if (vbios_mode->enh_table->flags & NewModeInfo) {
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x92, format->cpp[0] * 8);
+	}
+}
+
+static void ast_set_vbios_mode_reg(struct ast_private *ast,
+				   const struct drm_display_mode *adjusted_mode,
+				   const struct ast_vbios_mode_info *vbios_mode)
+{
+	u32 refresh_rate_index, mode_id;
+
+	refresh_rate_index = vbios_mode->enh_table->refresh_rate_index;
+	mode_id = vbios_mode->enh_table->mode_id;
 
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8d, refresh_rate_index & 0xff);
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x8e, mode_id & 0xff);
 
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0x00);
+
+	if (vbios_mode->enh_table->flags & NewModeInfo) {
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x91, 0xa8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x93, adjusted_mode->clock / 1000);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x94, adjusted_mode->crtc_hdisplay);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x95, adjusted_mode->crtc_hdisplay >> 8);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x96, adjusted_mode->crtc_vdisplay);
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0x97, adjusted_mode->crtc_vdisplay >> 8);
+	}
 }
-static void ast_set_std_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
+
+static void ast_set_std_reg(struct ast_private *ast,
+			    struct drm_display_mode *mode,
 			    struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	const struct ast_vbios_stdtable *stdtable;
 	u32 i;
 	u8 jreg;
@@ -244,18 +276,21 @@ static void ast_set_std_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	jreg = stdtable->misc;
 	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, jreg);
 
-	/* Set SEQ */
+	/* Set SEQ; except Screen Disable field */
 	ast_set_index_reg(ast, AST_IO_SEQ_PORT, 0x00, 0x03);
-	for (i = 0; i < 4; i++) {
+	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x01, 0xdf, stdtable->seq[0]);
+	for (i = 1; i < 4; i++) {
 		jreg = stdtable->seq[i];
-		if (!i)
-			jreg |= 0x20;
 		ast_set_index_reg(ast, AST_IO_SEQ_PORT, (i + 1) , jreg);
 	}
 
-	/* Set CRTC */
+	/* Set CRTC; except base address and offset */
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x11, 0x7f, 0x00);
-	for (i = 0; i < 25; i++)
+	for (i = 0; i < 12; i++)
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, stdtable->crtc[i]);
+	for (i = 14; i < 19; i++)
+		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, stdtable->crtc[i]);
+	for (i = 20; i < 25; i++)
 		ast_set_index_reg(ast, AST_IO_CRTC_PORT, i, stdtable->crtc[i]);
 
 	/* set AR */
@@ -276,10 +311,10 @@ static void ast_set_std_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 		ast_set_index_reg(ast, AST_IO_GR_PORT, i, stdtable->gr[i]);
 }
 
-static void ast_set_crtc_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
+static void ast_set_crtc_reg(struct ast_private *ast,
+			     struct drm_display_mode *mode,
 			     struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	u8 jreg05 = 0, jreg07 = 0, jreg09 = 0, jregAC = 0, jregAD = 0, jregAE = 0;
 	u16 temp, precache = 0;
 
@@ -385,11 +420,9 @@ static void ast_set_crtc_reg(struct drm_crtc *crtc, struct drm_display_mode *mod
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0x11, 0x7f, 0x80);
 }
 
-static void ast_set_offset_reg(struct drm_crtc *crtc)
+static void ast_set_offset_reg(struct ast_private *ast,
+			       struct drm_framebuffer *fb)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	const struct drm_framebuffer *fb = crtc->primary->fb;
-
 	u16 offset;
 
 	offset = fb->pitches[0] >> 3;
@@ -397,10 +430,10 @@ static void ast_set_offset_reg(struct drm_crtc *crtc)
 	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xb0, (offset >> 8) & 0x3f);
 }
 
-static void ast_set_dclk_reg(struct drm_device *dev, struct drm_display_mode *mode,
+static void ast_set_dclk_reg(struct ast_private *ast,
+			     struct drm_display_mode *mode,
 			     struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = dev->dev_private;
 	const struct ast_vbios_dclk_info *clk_info;
 
 	if (ast->chip == AST2500)
@@ -415,14 +448,12 @@ static void ast_set_dclk_reg(struct drm_device *dev, struct drm_display_mode *mo
 			       ((clk_info->param3 & 0x3) << 4));
 }
 
-static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
-			     struct ast_vbios_mode_info *vbios_mode)
+static void ast_set_color_reg(struct ast_private *ast,
+			      const struct drm_format_info *format)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	const struct drm_framebuffer *fb = crtc->primary->fb;
 	u8 jregA0 = 0, jregA3 = 0, jregA8 = 0;
 
-	switch (fb->format->cpp[0] * 8) {
+	switch (format->cpp[0] * 8) {
 	case 8:
 		jregA0 = 0x70;
 		jregA3 = 0x01;
@@ -444,7 +475,10 @@ static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa0, 0x8f, jregA0);
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xf0, jregA3);
 	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa8, 0xfd, jregA8);
+}
 
+static void ast_set_crtthd_reg(struct ast_private *ast)
+{
 	/* Set Threshold */
 	if (ast->chip == AST2300 || ast->chip == AST2400 ||
 	    ast->chip == AST2500) {
@@ -462,10 +496,10 @@ static void ast_set_ext_reg(struct drm_crtc *crtc, struct drm_display_mode *mode
 	}
 }
 
-static void ast_set_sync_reg(struct drm_device *dev, struct drm_display_mode *mode,
-		      struct ast_vbios_mode_info *vbios_mode)
+static void ast_set_sync_reg(struct ast_private *ast,
+			     struct drm_display_mode *mode,
+			     struct ast_vbios_mode_info *vbios_mode)
 {
-	struct ast_private *ast = dev->dev_private;
 	u8 jreg;
 
 	jreg  = ast_io_read8(ast, AST_IO_MISC_PORT_READ);
@@ -475,23 +509,9 @@ static void ast_set_sync_reg(struct drm_device *dev, struct drm_display_mode *mo
 	ast_io_write8(ast, AST_IO_MISC_PORT_WRITE, jreg);
 }
 
-static bool ast_set_dac_reg(struct drm_crtc *crtc, struct drm_display_mode *mode,
-		     struct ast_vbios_mode_info *vbios_mode)
-{
-	const struct drm_framebuffer *fb = crtc->primary->fb;
-
-	switch (fb->format->cpp[0] * 8) {
-	case 8:
-		break;
-	default:
-		return false;
-	}
-	return true;
-}
-
-static void ast_set_start_address_crt1(struct drm_crtc *crtc, unsigned offset)
+static void ast_set_start_address_crt1(struct ast_private *ast,
+				       unsigned offset)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
 	u32 addr;
 
 	addr = offset >> 2;
@@ -501,6 +521,247 @@ static void ast_set_start_address_crt1(struct drm_crtc *crtc, unsigned offset)
 
 }
 
+/*
+ * Primary plane
+ */
+
+static const uint32_t ast_primary_plane_formats[] = {
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_C8,
+};
+
+static int ast_primary_plane_helper_atomic_check(struct drm_plane *plane,
+						 struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct ast_crtc_state *ast_crtc_state;
+	int ret;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc);
+
+	ret = drm_atomic_helper_check_plane_state(state, crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  false, true);
+	if (ret)
+		return ret;
+
+	if (!state->visible)
+		return 0;
+
+	ast_crtc_state = to_ast_crtc_state(crtc_state);
+
+	ast_crtc_state->format = state->fb->format;
+
+	return 0;
+}
+
+void ast_primary_plane_helper_atomic_update(struct drm_plane *plane,
+					    struct drm_plane_state *old_state)
+{
+	struct ast_private *ast = plane->dev->dev_private;
+	struct drm_plane_state *state = plane->state;
+	struct drm_gem_vram_object *gbo;
+	s64 gpu_addr;
+
+	gbo = drm_gem_vram_of_gem(state->fb->obj[0]);
+	gpu_addr = drm_gem_vram_offset(gbo);
+	if (WARN_ON_ONCE(gpu_addr < 0))
+		return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
+
+	ast_set_offset_reg(ast, state->fb);
+	ast_set_start_address_crt1(ast, (u32)gpu_addr);
+
+	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x00);
+}
+
+static void
+ast_primary_plane_helper_atomic_disable(struct drm_plane *plane,
+					struct drm_plane_state *old_state)
+{
+	struct ast_private *ast = plane->dev->dev_private;
+
+	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x20);
+}
+
+static const struct drm_plane_helper_funcs ast_primary_plane_helper_funcs = {
+	.prepare_fb = drm_gem_vram_plane_helper_prepare_fb,
+	.cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb,
+	.atomic_check = ast_primary_plane_helper_atomic_check,
+	.atomic_update = ast_primary_plane_helper_atomic_update,
+	.atomic_disable = ast_primary_plane_helper_atomic_disable,
+};
+
+static const struct drm_plane_funcs ast_primary_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = drm_plane_cleanup,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+/*
+ * Cursor plane
+ */
+
+static const uint32_t ast_cursor_plane_formats[] = {
+	DRM_FORMAT_ARGB8888,
+};
+
+static int
+ast_cursor_plane_helper_prepare_fb(struct drm_plane *plane,
+				   struct drm_plane_state *new_state)
+{
+	struct drm_framebuffer *fb = new_state->fb;
+	struct drm_crtc *crtc = new_state->crtc;
+	struct drm_gem_vram_object *gbo;
+	struct ast_private *ast;
+	int ret;
+	void *src, *dst;
+
+	if (!crtc || !fb)
+		return 0;
+
+	if (WARN_ON_ONCE(fb->width > AST_MAX_HWC_WIDTH) ||
+	    WARN_ON_ONCE(fb->height > AST_MAX_HWC_HEIGHT))
+		return -EINVAL; /* BUG: didn't test in atomic_check() */
+
+	ast = crtc->dev->dev_private;
+
+	gbo = drm_gem_vram_of_gem(fb->obj[0]);
+	src = drm_gem_vram_vmap(gbo);
+	if (IS_ERR(src)) {
+		ret = PTR_ERR(src);
+		goto err_drm_gem_vram_unpin;
+	}
+
+	dst = drm_gem_vram_vmap(ast->cursor.gbo[ast->cursor.next_index]);
+	if (IS_ERR(dst)) {
+		ret = PTR_ERR(dst);
+		goto err_drm_gem_vram_vunmap_src;
+	}
+
+	ret = ast_cursor_update(dst, src, fb->width, fb->height);
+	if (ret)
+		goto err_drm_gem_vram_vunmap_dst;
+
+	/* Always unmap buffers here. Destination buffers are
+	 * perma-pinned while the driver is active. We're only
+	 * changing ref-counters here.
+	 */
+	drm_gem_vram_vunmap(ast->cursor.gbo[ast->cursor.next_index], dst);
+	drm_gem_vram_vunmap(gbo, src);
+
+	return 0;
+
+err_drm_gem_vram_vunmap_dst:
+	drm_gem_vram_vunmap(ast->cursor.gbo[ast->cursor.next_index], dst);
+err_drm_gem_vram_vunmap_src:
+	drm_gem_vram_vunmap(gbo, src);
+err_drm_gem_vram_unpin:
+	drm_gem_vram_unpin(gbo);
+	return ret;
+}
+
+static int ast_cursor_plane_helper_atomic_check(struct drm_plane *plane,
+						struct drm_plane_state *state)
+{
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_crtc_state *crtc_state;
+	int ret;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc);
+
+	ret = drm_atomic_helper_check_plane_state(state, crtc_state,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_HELPER_NO_SCALING,
+						  true, true);
+	if (ret)
+		return ret;
+
+	if (!state->visible)
+		return 0;
+
+	if (fb->width > AST_MAX_HWC_WIDTH || fb->height > AST_MAX_HWC_HEIGHT)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void
+ast_cursor_plane_helper_atomic_update(struct drm_plane *plane,
+				      struct drm_plane_state *old_state)
+{
+	struct drm_plane_state *state = plane->state;
+	struct drm_crtc *crtc = state->crtc;
+	struct drm_framebuffer *fb = state->fb;
+	struct ast_private *ast = plane->dev->dev_private;
+	struct ast_crtc *ast_crtc = to_ast_crtc(crtc);
+	struct drm_gem_vram_object *gbo;
+	s64 off;
+	u8 jreg;
+
+	ast_crtc->offset_x = AST_MAX_HWC_WIDTH - fb->width;
+	ast_crtc->offset_y = AST_MAX_HWC_WIDTH - fb->height;
+
+	if (state->fb != old_state->fb) {
+		/* A new cursor image was installed. */
+		gbo = ast->cursor.gbo[ast->cursor.next_index];
+		off = drm_gem_vram_offset(gbo);
+		if (WARN_ON_ONCE(off < 0))
+			return; /* Bug: we didn't pin cursor HW BO to VRAM. */
+		ast_cursor_set_base(ast, off);
+
+		++ast->cursor.next_index;
+		ast->cursor.next_index %= ARRAY_SIZE(ast->cursor.gbo);
+	}
+
+	ast_cursor_move(crtc, state->crtc_x, state->crtc_y);
+
+	jreg = 0x2;
+	/* enable ARGB cursor */
+	jreg |= 1;
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, jreg);
+}
+
+static void
+ast_cursor_plane_helper_atomic_disable(struct drm_plane *plane,
+				       struct drm_plane_state *old_state)
+{
+	struct ast_private *ast = plane->dev->dev_private;
+
+	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, 0x00);
+}
+
+static const struct drm_plane_helper_funcs ast_cursor_plane_helper_funcs = {
+	.prepare_fb = ast_cursor_plane_helper_prepare_fb,
+	.cleanup_fb = NULL, /* not required for cursor plane */
+	.atomic_check = ast_cursor_plane_helper_atomic_check,
+	.atomic_update = ast_cursor_plane_helper_atomic_update,
+	.atomic_disable = ast_cursor_plane_helper_atomic_disable,
+};
+
+static const struct drm_plane_funcs ast_cursor_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = drm_plane_cleanup,
+	.reset = drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+/*
+ * CRTC
+ */
+
 static void ast_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct ast_private *ast = crtc->dev->dev_private;
@@ -508,179 +769,196 @@ static void ast_crtc_dpms(struct drm_crtc *crtc, int mode)
 	if (ast->chip == AST1180)
 		return;
 
+	/* TODO: Maybe control display signal generation with
+	 *       Sync Enable (bit CR17.7).
+	 */
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
-		ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0);
 		if (ast->tx_chip_type == AST_TX_DP501)
 			ast_set_dp501_video_output(crtc->dev, 1);
-		ast_crtc_load_lut(crtc);
+		ast_crtc_load_lut(ast, crtc);
 		break;
 	case DRM_MODE_DPMS_OFF:
 		if (ast->tx_chip_type == AST_TX_DP501)
 			ast_set_dp501_video_output(crtc->dev, 0);
-		ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0x20);
 		break;
 	}
 }
 
-static int ast_crtc_do_set_base(struct drm_crtc *crtc,
-				struct drm_framebuffer *fb,
-				int x, int y, int atomic)
+static int ast_crtc_helper_atomic_check(struct drm_crtc *crtc,
+					struct drm_crtc_state *state)
 {
-	struct drm_gem_vram_object *gbo;
-	int ret;
-	s64 gpu_addr;
+	struct ast_private *ast = crtc->dev->dev_private;
+	struct ast_crtc_state *ast_state;
+	const struct drm_format_info *format;
+	bool succ;
 
-	if (!atomic && fb) {
-		gbo = drm_gem_vram_of_gem(fb->obj[0]);
-		drm_gem_vram_unpin(gbo);
+	if (ast->chip == AST1180) {
+		DRM_ERROR("AST 1180 modesetting not supported\n");
+		return -EINVAL;
 	}
 
-	gbo = drm_gem_vram_of_gem(crtc->primary->fb->obj[0]);
+	ast_state = to_ast_crtc_state(state);
 
-	ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-	if (ret)
-		return ret;
-	gpu_addr = drm_gem_vram_offset(gbo);
-	if (gpu_addr < 0) {
-		ret = (int)gpu_addr;
-		goto err_drm_gem_vram_unpin;
-	}
+	format = ast_state->format;
+	if (!format)
+		return 0;
 
-	ast_set_offset_reg(crtc);
-	ast_set_start_address_crt1(crtc, (u32)gpu_addr);
+	succ = ast_get_vbios_mode_info(format, &state->mode,
+				       &state->adjusted_mode,
+				       &ast_state->vbios_mode_info);
+	if (!succ)
+		return -EINVAL;
 
 	return 0;
-
-err_drm_gem_vram_unpin:
-	drm_gem_vram_unpin(gbo);
-	return ret;
 }
 
-static int ast_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
-			     struct drm_framebuffer *old_fb)
+static void ast_crtc_helper_atomic_begin(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
 {
-	return ast_crtc_do_set_base(crtc, old_fb, x, y, 0);
+	struct ast_private *ast = crtc->dev->dev_private;
+
+	ast_open_key(ast);
 }
 
-static int ast_crtc_mode_set(struct drm_crtc *crtc,
-			     struct drm_display_mode *mode,
-			     struct drm_display_mode *adjusted_mode,
-			     int x, int y,
-			     struct drm_framebuffer *old_fb)
+static void ast_crtc_helper_atomic_flush(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
 {
 	struct drm_device *dev = crtc->dev;
-	struct ast_private *ast = crtc->dev->dev_private;
-	struct ast_vbios_mode_info vbios_mode;
-	bool ret;
-	if (ast->chip == AST1180) {
-		DRM_ERROR("AST 1180 modesetting not supported\n");
-		return -EINVAL;
-	}
+	struct ast_private *ast = dev->dev_private;
+	struct ast_crtc_state *ast_state;
+	const struct drm_format_info *format;
+	struct ast_vbios_mode_info *vbios_mode_info;
+	struct drm_display_mode *adjusted_mode;
 
-	ret = ast_get_vbios_mode_info(crtc, mode, adjusted_mode, &vbios_mode);
-	if (ret == false)
-		return -EINVAL;
-	ast_open_key(ast);
+	crtc->state->no_vblank = true;
 
-	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06);
+	ast_state = to_ast_crtc_state(crtc->state);
 
-	ast_set_std_reg(crtc, adjusted_mode, &vbios_mode);
-	ast_set_crtc_reg(crtc, adjusted_mode, &vbios_mode);
-	ast_set_offset_reg(crtc);
-	ast_set_dclk_reg(dev, adjusted_mode, &vbios_mode);
-	ast_set_ext_reg(crtc, adjusted_mode, &vbios_mode);
-	ast_set_sync_reg(dev, adjusted_mode, &vbios_mode);
-	ast_set_dac_reg(crtc, adjusted_mode, &vbios_mode);
+	format = ast_state->format;
+	if (!format)
+		return;
 
-	ast_crtc_mode_set_base(crtc, x, y, old_fb);
+	vbios_mode_info = &ast_state->vbios_mode_info;
 
-	return 0;
-}
+	ast_set_color_reg(ast, format);
+	ast_set_vbios_color_reg(ast, format, vbios_mode_info);
 
-static void ast_crtc_disable(struct drm_crtc *crtc)
-{
-	DRM_DEBUG_KMS("\n");
-	ast_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
-	if (crtc->primary->fb) {
-		struct drm_framebuffer *fb = crtc->primary->fb;
-		struct drm_gem_vram_object *gbo =
-			drm_gem_vram_of_gem(fb->obj[0]);
+	if (!crtc->state->mode_changed)
+		return;
 
-		drm_gem_vram_unpin(gbo);
-	}
-	crtc->primary->fb = NULL;
+	adjusted_mode = &crtc->state->adjusted_mode;
+
+	ast_set_vbios_mode_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06);
+	ast_set_std_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_crtc_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_dclk_reg(ast, adjusted_mode, vbios_mode_info);
+	ast_set_crtthd_reg(ast);
+	ast_set_sync_reg(ast, adjusted_mode, vbios_mode_info);
 }
 
-static void ast_crtc_prepare(struct drm_crtc *crtc)
+static void
+ast_crtc_helper_atomic_enable(struct drm_crtc *crtc,
+			      struct drm_crtc_state *old_crtc_state)
 {
-
+	ast_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
 }
 
-static void ast_crtc_commit(struct drm_crtc *crtc)
+static void
+ast_crtc_helper_atomic_disable(struct drm_crtc *crtc,
+			       struct drm_crtc_state *old_crtc_state)
 {
-	struct ast_private *ast = crtc->dev->dev_private;
-	ast_set_index_reg_mask(ast, AST_IO_SEQ_PORT, 0x1, 0xdf, 0);
-	ast_crtc_load_lut(crtc);
+	ast_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
 }
 
-
 static const struct drm_crtc_helper_funcs ast_crtc_helper_funcs = {
-	.dpms = ast_crtc_dpms,
-	.mode_set = ast_crtc_mode_set,
-	.mode_set_base = ast_crtc_mode_set_base,
-	.disable = ast_crtc_disable,
-	.prepare = ast_crtc_prepare,
-	.commit = ast_crtc_commit,
-
+	.atomic_check = ast_crtc_helper_atomic_check,
+	.atomic_begin = ast_crtc_helper_atomic_begin,
+	.atomic_flush = ast_crtc_helper_atomic_flush,
+	.atomic_enable = ast_crtc_helper_atomic_enable,
+	.atomic_disable = ast_crtc_helper_atomic_disable,
 };
 
-static void ast_crtc_reset(struct drm_crtc *crtc)
+static void ast_crtc_destroy(struct drm_crtc *crtc)
 {
-
+	drm_crtc_cleanup(crtc);
+	kfree(crtc);
 }
 
-static int ast_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
-			      u16 *blue, uint32_t size,
-			      struct drm_modeset_acquire_ctx *ctx)
+static struct drm_crtc_state *
+ast_crtc_atomic_duplicate_state(struct drm_crtc *crtc)
 {
-	ast_crtc_load_lut(crtc);
+	struct ast_crtc_state *new_ast_state, *ast_state;
 
-	return 0;
-}
+	if (WARN_ON(!crtc->state))
+		return NULL;
 
+	new_ast_state = kmalloc(sizeof(*new_ast_state), GFP_KERNEL);
+	if (!new_ast_state)
+		return NULL;
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &new_ast_state->base);
 
-static void ast_crtc_destroy(struct drm_crtc *crtc)
+	ast_state = to_ast_crtc_state(crtc->state);
+
+	new_ast_state->format = ast_state->format;
+	memcpy(&new_ast_state->vbios_mode_info, &ast_state->vbios_mode_info,
+	       sizeof(new_ast_state->vbios_mode_info));
+
+	return &new_ast_state->base;
+}
+
+static void ast_crtc_atomic_destroy_state(struct drm_crtc *crtc,
+					  struct drm_crtc_state *state)
 {
-	drm_crtc_cleanup(crtc);
-	kfree(crtc);
+	struct ast_crtc_state *ast_state = to_ast_crtc_state(state);
+
+	__drm_atomic_helper_crtc_destroy_state(&ast_state->base);
+	kfree(ast_state);
 }
 
 static const struct drm_crtc_funcs ast_crtc_funcs = {
-	.cursor_set = ast_cursor_set,
-	.cursor_move = ast_cursor_move,
-	.reset = ast_crtc_reset,
+	.reset = drm_atomic_helper_crtc_reset,
 	.set_config = drm_crtc_helper_set_config,
-	.gamma_set = ast_crtc_gamma_set,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 	.destroy = ast_crtc_destroy,
+	.set_config = drm_atomic_helper_set_config,
+	.page_flip = drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = ast_crtc_atomic_duplicate_state,
+	.atomic_destroy_state = ast_crtc_atomic_destroy_state,
 };
 
 static int ast_crtc_init(struct drm_device *dev)
 {
+	struct ast_private *ast = dev->dev_private;
 	struct ast_crtc *crtc;
+	int ret;
 
 	crtc = kzalloc(sizeof(struct ast_crtc), GFP_KERNEL);
 	if (!crtc)
 		return -ENOMEM;
 
-	drm_crtc_init(dev, &crtc->base, &ast_crtc_funcs);
+	ret = drm_crtc_init_with_planes(dev, &crtc->base, &ast->primary_plane,
+					&ast->cursor_plane, &ast_crtc_funcs,
+					NULL);
+	if (ret)
+		goto err_kfree;
+
 	drm_mode_crtc_set_gamma_size(&crtc->base, 256);
 	drm_crtc_helper_add(&crtc->base, &ast_crtc_helper_funcs);
 	return 0;
+
+err_kfree:
+	kfree(crtc);
+	return ret;
 }
 
+/*
+ * Encoder
+ */
+
 static void ast_encoder_destroy(struct drm_encoder *encoder)
 {
 	drm_encoder_cleanup(encoder);
@@ -691,35 +969,6 @@ static const struct drm_encoder_funcs ast_enc_funcs = {
 	.destroy = ast_encoder_destroy,
 };
 
-static void ast_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-
-}
-
-static void ast_encoder_mode_set(struct drm_encoder *encoder,
-			       struct drm_display_mode *mode,
-			       struct drm_display_mode *adjusted_mode)
-{
-}
-
-static void ast_encoder_prepare(struct drm_encoder *encoder)
-{
-
-}
-
-static void ast_encoder_commit(struct drm_encoder *encoder)
-{
-
-}
-
-
-static const struct drm_encoder_helper_funcs ast_enc_helper_funcs = {
-	.dpms = ast_encoder_dpms,
-	.prepare = ast_encoder_prepare,
-	.commit = ast_encoder_commit,
-	.mode_set = ast_encoder_mode_set,
-};
-
 static int ast_encoder_init(struct drm_device *dev)
 {
 	struct ast_encoder *ast_encoder;
@@ -730,12 +979,15 @@ static int ast_encoder_init(struct drm_device *dev)
 
 	drm_encoder_init(dev, &ast_encoder->base, &ast_enc_funcs,
 			 DRM_MODE_ENCODER_DAC, NULL);
-	drm_encoder_helper_add(&ast_encoder->base, &ast_enc_helper_funcs);
 
 	ast_encoder->base.possible_crtcs = 1;
 	return 0;
 }
 
+/*
+ * Connector
+ */
+
 static int ast_get_modes(struct drm_connector *connector)
 {
 	struct ast_connector *ast_connector = to_ast_connector(connector);
@@ -834,14 +1086,16 @@ static void ast_connector_destroy(struct drm_connector *connector)
 }
 
 static const struct drm_connector_helper_funcs ast_connector_helper_funcs = {
-	.mode_valid = ast_mode_valid,
 	.get_modes = ast_get_modes,
+	.mode_valid = ast_mode_valid,
 };
 
 static const struct drm_connector_funcs ast_connector_funcs = {
-	.dpms = drm_helper_connector_dpms,
+	.reset = drm_atomic_helper_connector_reset,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = ast_connector_destroy,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
 static int ast_connector_init(struct drm_device *dev)
@@ -890,8 +1144,7 @@ static int ast_cursor_init(struct drm_device *dev)
 	size = roundup(AST_HWC_SIZE + AST_HWC_SIGNATURE_SIZE, PAGE_SIZE);
 
 	for (i = 0; i < ARRAY_SIZE(ast->cursor.gbo); ++i) {
-		gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev,
-					  size, 0, false);
+		gbo = drm_gem_vram_create(dev, size, 0);
 		if (IS_ERR(gbo)) {
 			ret = PTR_ERR(gbo);
 			goto err_drm_gem_vram_put;
@@ -934,10 +1187,39 @@ static void ast_cursor_fini(struct drm_device *dev)
 
 int ast_mode_init(struct drm_device *dev)
 {
+	struct ast_private *ast = dev->dev_private;
+	int ret;
+
+	memset(&ast->primary_plane, 0, sizeof(ast->primary_plane));
+	ret = drm_universal_plane_init(dev, &ast->primary_plane, 0x01,
+				       &ast_primary_plane_funcs,
+				       ast_primary_plane_formats,
+				       ARRAY_SIZE(ast_primary_plane_formats),
+				       NULL, DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret) {
+		DRM_ERROR("ast: drm_universal_plane_init() failed: %d\n", ret);
+		return ret;
+	}
+	drm_plane_helper_add(&ast->primary_plane,
+			     &ast_primary_plane_helper_funcs);
+
+	ret = drm_universal_plane_init(dev, &ast->cursor_plane, 0x01,
+				       &ast_cursor_plane_funcs,
+				       ast_cursor_plane_formats,
+				       ARRAY_SIZE(ast_cursor_plane_formats),
+				       NULL, DRM_PLANE_TYPE_CURSOR, NULL);
+	if (ret) {
+		DRM_ERROR("drm_universal_plane_failed(): %d\n", ret);
+		return ret;
+	}
+	drm_plane_helper_add(&ast->cursor_plane,
+			     &ast_cursor_plane_helper_funcs);
+
 	ast_cursor_init(dev);
 	ast_crtc_init(dev);
 	ast_encoder_init(dev);
 	ast_connector_init(dev);
+
 	return 0;
 }
 
@@ -1153,106 +1435,6 @@ static void ast_cursor_set_base(struct ast_private *ast, u64 address)
 	ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xca, addr2);
 }
 
-static int ast_show_cursor(struct drm_crtc *crtc, void *src,
-			   unsigned int width, unsigned int height)
-{
-	struct ast_private *ast = crtc->dev->dev_private;
-	struct ast_crtc *ast_crtc = to_ast_crtc(crtc);
-	struct drm_gem_vram_object *gbo;
-	void *dst;
-	s64 off;
-	int ret;
-	u8 jreg;
-
-	gbo = ast->cursor.gbo[ast->cursor.next_index];
-	dst = drm_gem_vram_vmap(gbo);
-	if (IS_ERR(dst))
-		return PTR_ERR(dst);
-	off = drm_gem_vram_offset(gbo);
-	if (off < 0) {
-		ret = (int)off;
-		goto err_drm_gem_vram_vunmap;
-	}
-
-	ret = ast_cursor_update(dst, src, width, height);
-	if (ret)
-		goto err_drm_gem_vram_vunmap;
-	ast_cursor_set_base(ast, off);
-
-	ast_crtc->offset_x = AST_MAX_HWC_WIDTH - width;
-	ast_crtc->offset_y = AST_MAX_HWC_WIDTH - height;
-
-	jreg = 0x2;
-	/* enable ARGB cursor */
-	jreg |= 1;
-	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, jreg);
-
-	++ast->cursor.next_index;
-	ast->cursor.next_index %= ARRAY_SIZE(ast->cursor.gbo);
-
-	drm_gem_vram_vunmap(gbo, dst);
-
-	return 0;
-
-err_drm_gem_vram_vunmap:
-	drm_gem_vram_vunmap(gbo, dst);
-	return ret;
-}
-
-static void ast_hide_cursor(struct drm_crtc *crtc)
-{
-	struct ast_private *ast = crtc->dev->dev_private;
-
-	ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xcb, 0xfc, 0x00);
-}
-
-static int ast_cursor_set(struct drm_crtc *crtc,
-			  struct drm_file *file_priv,
-			  uint32_t handle,
-			  uint32_t width,
-			  uint32_t height)
-{
-	struct drm_gem_object *obj;
-	struct drm_gem_vram_object *gbo;
-	u8 *src;
-	int ret;
-
-	if (!handle) {
-		ast_hide_cursor(crtc);
-		return 0;
-	}
-
-	if (width > AST_MAX_HWC_WIDTH || height > AST_MAX_HWC_HEIGHT)
-		return -EINVAL;
-
-	obj = drm_gem_object_lookup(file_priv, handle);
-	if (!obj) {
-		DRM_ERROR("Cannot find cursor object %x for crtc\n", handle);
-		return -ENOENT;
-	}
-	gbo = drm_gem_vram_of_gem(obj);
-	src = drm_gem_vram_vmap(gbo);
-	if (IS_ERR(src)) {
-		ret = PTR_ERR(src);
-		goto err_drm_gem_object_put_unlocked;
-	}
-
-	ret = ast_show_cursor(crtc, src, width, height);
-	if (ret)
-		goto err_drm_gem_vram_vunmap;
-
-	drm_gem_vram_vunmap(gbo, src);
-	drm_gem_object_put_unlocked(obj);
-
-	return 0;
-
-err_drm_gem_vram_vunmap:
-	drm_gem_vram_vunmap(gbo, src);
-err_drm_gem_object_put_unlocked:
-	drm_gem_object_put_unlocked(obj);
-	return ret;
-}
-
 static int ast_cursor_move(struct drm_crtc *crtc,
 			   int x, int y)
 {
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index f2e73e6d46b8..10985134ce0b 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -73,7 +73,11 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 	unsigned long prate;
 	unsigned int mask = ATMEL_HLCDC_CLKDIV_MASK | ATMEL_HLCDC_CLKPOL;
 	unsigned int cfg = 0;
-	int div;
+	int div, ret;
+
+	ret = clk_prepare_enable(crtc->dc->hlcdc->sys_clk);
+	if (ret)
+		return;
 
 	vm.vfront_porch = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	vm.vback_porch = adj->crtc_vtotal - adj->crtc_vsync_end;
@@ -95,14 +99,14 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 		     (adj->crtc_hdisplay - 1) |
 		     ((adj->crtc_vdisplay - 1) << 16));
 
+	prate = clk_get_rate(crtc->dc->hlcdc->sys_clk);
+	mode_rate = adj->crtc_clock * 1000;
 	if (!crtc->dc->desc->fixed_clksrc) {
+		prate *= 2;
 		cfg |= ATMEL_HLCDC_CLKSEL;
 		mask |= ATMEL_HLCDC_CLKSEL;
 	}
 
-	prate = 2 * clk_get_rate(crtc->dc->hlcdc->sys_clk);
-	mode_rate = adj->crtc_clock * 1000;
-
 	div = DIV_ROUND_UP(prate, mode_rate);
 	if (div < 2) {
 		div = 2;
@@ -117,8 +121,8 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 		int div_low = prate / mode_rate;
 
 		if (div_low >= 2 &&
-		    ((prate / div_low - mode_rate) <
-		     10 * (mode_rate - prate / div)))
+		    (10 * (prate / div_low - mode_rate) <
+		     (mode_rate - prate / div)))
 			/*
 			 * At least 10 times better when using a higher
 			 * frequency than requested, instead of a lower.
@@ -147,6 +151,8 @@ static void atmel_hlcdc_crtc_mode_set_nofb(struct drm_crtc *c)
 			   ATMEL_HLCDC_VSPSU | ATMEL_HLCDC_VSPHO |
 			   ATMEL_HLCDC_GUARDTIME_MASK | ATMEL_HLCDC_MODE_MASK,
 			   cfg);
+
+	clk_disable_unprepare(crtc->dc->hlcdc->sys_clk);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index 92640298ad41..112aa5066cee 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -557,12 +557,6 @@ static irqreturn_t atmel_hlcdc_dc_irq_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static struct drm_framebuffer *atmel_hlcdc_fb_create(struct drm_device *dev,
-		struct drm_file *file_priv, const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	return drm_gem_fb_create(dev, file_priv, mode_cmd);
-}
-
 struct atmel_hlcdc_dc_commit {
 	struct work_struct work;
 	struct drm_device *dev;
@@ -657,7 +651,7 @@ error:
 }
 
 static const struct drm_mode_config_funcs mode_config_funcs = {
-	.fb_create = atmel_hlcdc_fb_create,
+	.fb_create = drm_gem_fb_create,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = atmel_hlcdc_dc_atomic_commit,
 };
@@ -727,18 +721,10 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev)
 	dc->hlcdc = dev_get_drvdata(dev->dev->parent);
 	dev->dev_private = dc;
 
-	if (dc->desc->fixed_clksrc) {
-		ret = clk_prepare_enable(dc->hlcdc->sys_clk);
-		if (ret) {
-			dev_err(dev->dev, "failed to enable sys_clk\n");
-			goto err_destroy_wq;
-		}
-	}
-
 	ret = clk_prepare_enable(dc->hlcdc->periph_clk);
 	if (ret) {
 		dev_err(dev->dev, "failed to enable periph_clk\n");
-		goto err_sys_clk_disable;
+		goto err_destroy_wq;
 	}
 
 	pm_runtime_enable(dev->dev);
@@ -774,9 +760,6 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev)
 err_periph_clk_disable:
 	pm_runtime_disable(dev->dev);
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
-err_sys_clk_disable:
-	if (dc->desc->fixed_clksrc)
-		clk_disable_unprepare(dc->hlcdc->sys_clk);
 
 err_destroy_wq:
 	destroy_workqueue(dc->wq);
@@ -801,8 +784,6 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 
 	pm_runtime_disable(dev->dev);
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
-	if (dc->desc->fixed_clksrc)
-		clk_disable_unprepare(dc->hlcdc->sys_clk);
 	destroy_workqueue(dc->wq);
 }
 
@@ -916,8 +897,6 @@ static int atmel_hlcdc_dc_drm_suspend(struct device *dev)
 	regmap_read(regmap, ATMEL_HLCDC_IMR, &dc->suspend.imr);
 	regmap_write(regmap, ATMEL_HLCDC_IDR, dc->suspend.imr);
 	clk_disable_unprepare(dc->hlcdc->periph_clk);
-	if (dc->desc->fixed_clksrc)
-		clk_disable_unprepare(dc->hlcdc->sys_clk);
 
 	return 0;
 }
@@ -927,8 +906,6 @@ static int atmel_hlcdc_dc_drm_resume(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct atmel_hlcdc_dc *dc = drm_dev->dev_private;
 
-	if (dc->desc->fixed_clksrc)
-		clk_prepare_enable(dc->hlcdc->sys_clk);
 	clk_prepare_enable(dc->hlcdc->periph_clk);
 	regmap_write(dc->hlcdc->regmap, ATMEL_HLCDC_IER, dc->suspend.imr);
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 034f202dfe8f..40800ec5700a 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -604,7 +604,7 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p,
 	int ret;
 	int i;
 
-	if (!state->base.crtc || !fb)
+	if (!state->base.crtc || WARN_ON(!fb))
 		return 0;
 
 	crtc_state = drm_atomic_get_existing_crtc_state(s->state, s->crtc);
diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c
index e567bdfa2ab8..b615b7dfdd9d 100644
--- a/drivers/gpu/drm/bochs/bochs_hw.c
+++ b/drivers/gpu/drm/bochs/bochs_hw.c
@@ -255,7 +255,7 @@ void bochs_hw_setformat(struct bochs_device *bochs,
 		DRM_ERROR("%s: Huh? Got framebuffer format 0x%x",
 			  __func__, format->format);
 		break;
-	};
+	}
 }
 
 void bochs_hw_setbase(struct bochs_device *bochs,
diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 34362976cd6f..0b9ca5862455 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -16,16 +16,6 @@ config DRM_PANEL_BRIDGE
 menu "Display Interface Bridges"
 	depends on DRM && DRM_BRIDGE
 
-config DRM_ANALOGIX_ANX78XX
-	tristate "Analogix ANX78XX bridge"
-	select DRM_KMS_HELPER
-	select REGMAP_I2C
-	---help---
-	  ANX78XX is an ultra-low power Full-HD SlimPort transmitter
-	  designed for portable devices. The ANX78XX transforms
-	  the HDMI output of an application processor to MyDP
-	  or DisplayPort.
-
 config DRM_CDNS_DSI
 	tristate "Cadence DPI/DSI bridge"
 	select DRM_KMS_HELPER
@@ -45,14 +35,14 @@ config DRM_DUMB_VGA_DAC
 	  Support for non-programmable RGB to VGA DAC bridges, such as ADI
 	  ADV7123, TI THS8134 and THS8135 or passive resistor ladder DACs.
 
-config DRM_LVDS_ENCODER
-	tristate "Transparent parallel to LVDS encoder support"
+config DRM_LVDS_CODEC
+	tristate "Transparent LVDS encoders and decoders support"
 	depends on OF
 	select DRM_KMS_HELPER
 	select DRM_PANEL_BRIDGE
 	help
-	  Support for transparent parallel to LVDS encoders that don't require
-	  any configuration.
+	  Support for transparent LVDS encoders and decoders that don't
+	  require any configuration.
 
 config DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW
 	tristate "MegaChips stdp4028-ge-b850v3-fw and stdp2690-ge-b850v3-fw"
@@ -60,10 +50,10 @@ config DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW
 	select DRM_KMS_HELPER
 	select DRM_PANEL
 	---help---
-          This is a driver for the display bridges of
-          GE B850v3 that convert dual channel LVDS
-          to DP++. This is used with the i.MX6 imx-ldb
-          driver. You are likely to say N here.
+	  This is a driver for the display bridges of
+	  GE B850v3 that convert dual channel LVDS
+	  to DP++. This is used with the i.MX6 imx-ldb
+	  driver. You are likely to say N here.
 
 config DRM_NXP_PTN3460
 	tristate "NXP PTN3460 DP/LVDS bridge"
diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile
index 4934fcf5a6f8..cd16ce830270 100644
--- a/drivers/gpu/drm/bridge/Makefile
+++ b/drivers/gpu/drm/bridge/Makefile
@@ -1,8 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o
 obj-$(CONFIG_DRM_CDNS_DSI) += cdns-dsi.o
 obj-$(CONFIG_DRM_DUMB_VGA_DAC) += dumb-vga-dac.o
-obj-$(CONFIG_DRM_LVDS_ENCODER) += lvds-encoder.o
+obj-$(CONFIG_DRM_LVDS_CODEC) += lvds-codec.o
 obj-$(CONFIG_DRM_MEGACHIPS_STDPXXXX_GE_B850V3_FW) += megachips-stdpxxxx-ge-b850v3-fw.o
 obj-$(CONFIG_DRM_NXP_PTN3460) += nxp-ptn3460.o
 obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o
@@ -12,8 +11,9 @@ obj-$(CONFIG_DRM_SII9234) += sii9234.o
 obj-$(CONFIG_DRM_THINE_THC63LVD1024) += thc63lvd1024.o
 obj-$(CONFIG_DRM_TOSHIBA_TC358764) += tc358764.o
 obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o
-obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix/
 obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/
 obj-$(CONFIG_DRM_TI_SN65DSI86) += ti-sn65dsi86.o
 obj-$(CONFIG_DRM_TI_TFP410) += ti-tfp410.o
+
+obj-y += analogix/
 obj-y += synopsys/
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.h b/drivers/gpu/drm/bridge/analogix-anx78xx.h
deleted file mode 100644
index 55d6c2109740..000000000000
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.h
+++ /dev/null
@@ -1,703 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright(c) 2016, Analogix Semiconductor. All rights reserved.
- */
-
-#ifndef __ANX78xx_H
-#define __ANX78xx_H
-
-/***************************************************************/
-/* Register definitions for RX_PO                              */
-/***************************************************************/
-
-/*
- * System Control and Status
- */
-
-/* Software Reset Register 1 */
-#define SP_SOFTWARE_RESET1_REG		0x11
-#define SP_VIDEO_RST			BIT(4)
-#define SP_HDCP_MAN_RST			BIT(2)
-#define SP_TMDS_RST			BIT(1)
-#define SP_SW_MAN_RST			BIT(0)
-
-/* System Status Register */
-#define SP_SYSTEM_STATUS_REG		0x14
-#define SP_TMDS_CLOCK_DET		BIT(1)
-#define SP_TMDS_DE_DET			BIT(0)
-
-/* HDMI Status Register */
-#define SP_HDMI_STATUS_REG		0x15
-#define SP_HDMI_AUD_LAYOUT		BIT(3)
-#define SP_HDMI_DET			BIT(0)
-#  define SP_DVI_MODE			0
-#  define SP_HDMI_MODE			1
-
-/* HDMI Mute Control Register */
-#define SP_HDMI_MUTE_CTRL_REG		0x16
-#define SP_AUD_MUTE			BIT(1)
-#define SP_VID_MUTE			BIT(0)
-
-/* System Power Down Register 1 */
-#define SP_SYSTEM_POWER_DOWN1_REG	0x18
-#define SP_PWDN_CTRL			BIT(0)
-
-/*
- * Audio and Video Auto Control
- */
-
-/* Auto Audio and Video Control register */
-#define SP_AUDVID_CTRL_REG		0x20
-#define SP_AVC_OE			BIT(7)
-#define SP_AAC_OE			BIT(6)
-#define SP_AVC_EN			BIT(1)
-#define SP_AAC_EN			BIT(0)
-
-/* Audio Exception Enable Registers */
-#define SP_AUD_EXCEPTION_ENABLE_BASE	(0x24 - 1)
-/* Bits for Audio Exception Enable Register 3 */
-#define SP_AEC_EN21			BIT(5)
-
-/*
- * Interrupt
- */
-
-/* Interrupt Status Register 1 */
-#define SP_INT_STATUS1_REG		0x31
-/* Bits for Interrupt Status Register 1 */
-#define SP_HDMI_DVI			BIT(7)
-#define SP_CKDT_CHG			BIT(6)
-#define SP_SCDT_CHG			BIT(5)
-#define SP_PCLK_CHG			BIT(4)
-#define SP_PLL_UNLOCK			BIT(3)
-#define SP_CABLE_PLUG_CHG		BIT(2)
-#define SP_SET_MUTE			BIT(1)
-#define SP_SW_INTR			BIT(0)
-/* Bits for Interrupt Status Register 2 */
-#define SP_HDCP_ERR			BIT(5)
-#define SP_AUDIO_SAMPLE_CHG		BIT(0)	/* undocumented */
-/* Bits for Interrupt Status Register 3 */
-#define SP_AUD_MODE_CHG			BIT(0)
-/* Bits for Interrupt Status Register 5 */
-#define SP_AUDIO_RCV			BIT(0)
-/* Bits for Interrupt Status Register 6 */
-#define SP_INT_STATUS6_REG		0x36
-#define SP_CTS_RCV			BIT(7)
-#define SP_NEW_AUD_PKT			BIT(4)
-#define SP_NEW_AVI_PKT			BIT(1)
-#define SP_NEW_CP_PKT			BIT(0)
-/* Bits for Interrupt Status Register 7 */
-#define SP_NO_VSI			BIT(7)
-#define SP_NEW_VS			BIT(4)
-
-/* Interrupt Mask 1 Status Registers */
-#define SP_INT_MASK1_REG		0x41
-
-/* HDMI US TIMER Control Register */
-#define SP_HDMI_US_TIMER_CTRL_REG	0x49
-#define SP_MS_TIMER_MARGIN_10_8_MASK	0x07
-
-/*
- * TMDS Control
- */
-
-/* TMDS Control Registers */
-#define SP_TMDS_CTRL_BASE		(0x50 - 1)
-/* Bits for TMDS Control Register 7 */
-#define SP_PD_RT			BIT(0)
-
-/*
- * Video Control
- */
-
-/* Video Status Register */
-#define SP_VIDEO_STATUS_REG		0x70
-#define SP_COLOR_DEPTH_MASK		0xf0
-#define SP_COLOR_DEPTH_SHIFT		4
-#  define SP_COLOR_DEPTH_MODE_LEGACY	0x00
-#  define SP_COLOR_DEPTH_MODE_24BIT	0x04
-#  define SP_COLOR_DEPTH_MODE_30BIT	0x05
-#  define SP_COLOR_DEPTH_MODE_36BIT	0x06
-#  define SP_COLOR_DEPTH_MODE_48BIT	0x07
-
-/* Video Data Range Control Register */
-#define SP_VID_DATA_RANGE_CTRL_REG	0x83
-#define SP_R2Y_INPUT_LIMIT		BIT(1)
-
-/* Pixel Clock High Resolution Counter Registers */
-#define SP_PCLK_HIGHRES_CNT_BASE	(0x8c - 1)
-
-/*
- * Audio Control
- */
-
-/* Number of Audio Channels Status Registers */
-#define SP_AUD_CH_STATUS_REG_NUM	6
-
-/* Audio IN S/PDIF Channel Status Registers */
-#define SP_AUD_SPDIF_CH_STATUS_BASE	0xc7
-
-/* Audio IN S/PDIF Channel Status Register 4 */
-#define SP_FS_FREQ_MASK			0x0f
-#  define SP_FS_FREQ_44100HZ		0x00
-#  define SP_FS_FREQ_48000HZ		0x02
-#  define SP_FS_FREQ_32000HZ		0x03
-#  define SP_FS_FREQ_88200HZ		0x08
-#  define SP_FS_FREQ_96000HZ		0x0a
-#  define SP_FS_FREQ_176400HZ		0x0c
-#  define SP_FS_FREQ_192000HZ		0x0e
-
-/*
- * Micellaneous Control Block
- */
-
-/* CHIP Control Register */
-#define SP_CHIP_CTRL_REG		0xe3
-#define SP_MAN_HDMI5V_DET		BIT(3)
-#define SP_PLLLOCK_CKDT_EN		BIT(2)
-#define SP_ANALOG_CKDT_EN		BIT(1)
-#define SP_DIGITAL_CKDT_EN		BIT(0)
-
-/* Packet Receiving Status Register */
-#define SP_PACKET_RECEIVING_STATUS_REG	0xf3
-#define SP_AVI_RCVD			BIT(5)
-#define SP_VSI_RCVD			BIT(1)
-
-/***************************************************************/
-/* Register definitions for RX_P1                              */
-/***************************************************************/
-
-/* HDCP BCAPS Shadow Register */
-#define SP_HDCP_BCAPS_SHADOW_REG	0x2a
-#define SP_BCAPS_REPEATER		BIT(5)
-
-/* HDCP Status Register */
-#define SP_RX_HDCP_STATUS_REG		0x3f
-#define SP_AUTH_EN			BIT(4)
-
-/*
- * InfoFrame and Control Packet Registers
- */
-
-/* AVI InfoFrame packet checksum */
-#define SP_AVI_INFOFRAME_CHECKSUM	0xa3
-
-/* AVI InfoFrame Registers */
-#define SP_AVI_INFOFRAME_DATA_BASE	0xa4
-
-#define SP_AVI_COLOR_F_MASK		0x60
-#define SP_AVI_COLOR_F_SHIFT		5
-
-/* Audio InfoFrame Registers */
-#define SP_AUD_INFOFRAME_DATA_BASE	0xc4
-#define SP_AUD_INFOFRAME_LAYOUT_MASK	0x0f
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet type code */
-#define SP_MPEG_VS_INFOFRAME_TYPE_REG	0xe0
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet length */
-#define SP_MPEG_VS_INFOFRAME_LEN_REG	0xe2
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet version number */
-#define SP_MPEG_VS_INFOFRAME_VER_REG	0xe1
-
-/* MPEG/HDMI Vendor Specific InfoFrame Packet content */
-#define SP_MPEG_VS_INFOFRAME_DATA_BASE	0xe4
-
-/* General Control Packet Register */
-#define SP_GENERAL_CTRL_PACKET_REG	0x9f
-#define SP_CLEAR_AVMUTE			BIT(4)
-#define SP_SET_AVMUTE			BIT(0)
-
-/***************************************************************/
-/* Register definitions for TX_P0                              */
-/***************************************************************/
-
-/* HDCP Status Register */
-#define SP_TX_HDCP_STATUS_REG		0x00
-#define SP_AUTH_FAIL			BIT(5)
-#define SP_AUTHEN_PASS			BIT(1)
-
-/* HDCP Control Register 0 */
-#define SP_HDCP_CTRL0_REG		0x01
-#define SP_RX_REPEATER			BIT(6)
-#define SP_RE_AUTH			BIT(5)
-#define SP_SW_AUTH_OK			BIT(4)
-#define SP_HARD_AUTH_EN			BIT(3)
-#define SP_HDCP_ENC_EN			BIT(2)
-#define SP_BKSV_SRM_PASS		BIT(1)
-#define SP_KSVLIST_VLD			BIT(0)
-/* HDCP Function Enabled */
-#define SP_HDCP_FUNCTION_ENABLED	(BIT(0) | BIT(1) | BIT(2) | BIT(3))
-
-/* HDCP Receiver BSTATUS Register 0 */
-#define	SP_HDCP_RX_BSTATUS0_REG		0x1b
-/* HDCP Receiver BSTATUS Register 1 */
-#define	SP_HDCP_RX_BSTATUS1_REG		0x1c
-
-/* HDCP Embedded "Blue Screen" Content Registers */
-#define SP_HDCP_VID0_BLUE_SCREEN_REG	0x2c
-#define SP_HDCP_VID1_BLUE_SCREEN_REG	0x2d
-#define SP_HDCP_VID2_BLUE_SCREEN_REG	0x2e
-
-/* HDCP Wait R0 Timing Register */
-#define SP_HDCP_WAIT_R0_TIME_REG	0x40
-
-/* HDCP Link Integrity Check Timer Register */
-#define SP_HDCP_LINK_CHECK_TIMER_REG	0x41
-
-/* HDCP Repeater Ready Wait Timer Register */
-#define SP_HDCP_RPTR_RDY_WAIT_TIME_REG	0x42
-
-/* HDCP Auto Timer Register */
-#define SP_HDCP_AUTO_TIMER_REG		0x51
-
-/* HDCP Key Status Register */
-#define SP_HDCP_KEY_STATUS_REG		0x5e
-
-/* HDCP Key Command Register */
-#define SP_HDCP_KEY_COMMAND_REG		0x5f
-#define SP_DISABLE_SYNC_HDCP		BIT(2)
-
-/* OTP Memory Key Protection Registers */
-#define SP_OTP_KEY_PROTECT1_REG		0x60
-#define SP_OTP_KEY_PROTECT2_REG		0x61
-#define SP_OTP_KEY_PROTECT3_REG		0x62
-#define SP_OTP_PSW1			0xa2
-#define SP_OTP_PSW2			0x7e
-#define SP_OTP_PSW3			0xc6
-
-/* DP System Control Registers */
-#define SP_DP_SYSTEM_CTRL_BASE		(0x80 - 1)
-/* Bits for DP System Control Register 2 */
-#define SP_CHA_STA			BIT(2)
-/* Bits for DP System Control Register 3 */
-#define SP_HPD_STATUS			BIT(6)
-#define SP_STRM_VALID			BIT(2)
-/* Bits for DP System Control Register 4 */
-#define SP_ENHANCED_MODE		BIT(3)
-
-/* DP Video Control Register */
-#define SP_DP_VIDEO_CTRL_REG		0x84
-#define SP_COLOR_F_MASK			0x06
-#define SP_COLOR_F_SHIFT		1
-#define SP_BPC_MASK			0xe0
-#define SP_BPC_SHIFT			5
-#  define SP_BPC_6BITS			0x00
-#  define SP_BPC_8BITS			0x01
-#  define SP_BPC_10BITS			0x02
-#  define SP_BPC_12BITS			0x03
-
-/* DP Audio Control Register */
-#define SP_DP_AUDIO_CTRL_REG		0x87
-#define SP_AUD_EN			BIT(0)
-
-/* 10us Pulse Generate Timer Registers */
-#define SP_I2C_GEN_10US_TIMER0_REG	0x88
-#define SP_I2C_GEN_10US_TIMER1_REG	0x89
-
-/* Packet Send Control Register */
-#define SP_PACKET_SEND_CTRL_REG		0x90
-#define SP_AUD_IF_UP			BIT(7)
-#define SP_AVI_IF_UD			BIT(6)
-#define SP_MPEG_IF_UD			BIT(5)
-#define SP_SPD_IF_UD			BIT(4)
-#define SP_AUD_IF_EN			BIT(3)
-#define SP_AVI_IF_EN			BIT(2)
-#define SP_MPEG_IF_EN			BIT(1)
-#define SP_SPD_IF_EN			BIT(0)
-
-/* DP HDCP Control Register */
-#define SP_DP_HDCP_CTRL_REG		0x92
-#define SP_AUTO_EN			BIT(7)
-#define SP_AUTO_START			BIT(5)
-#define SP_LINK_POLLING			BIT(1)
-
-/* DP Main Link Bandwidth Setting Register */
-#define SP_DP_MAIN_LINK_BW_SET_REG	0xa0
-#define SP_LINK_BW_SET_MASK		0x1f
-#define SP_INITIAL_SLIM_M_AUD_SEL	BIT(5)
-
-/* DP Training Pattern Set Register */
-#define SP_DP_TRAINING_PATTERN_SET_REG	0xa2
-
-/* DP Lane 0 Link Training Control Register */
-#define SP_DP_LANE0_LT_CTRL_REG		0xa3
-#define SP_TX_SW_SET_MASK		0x1b
-#define SP_MAX_PRE_REACH		BIT(5)
-#define SP_MAX_DRIVE_REACH		BIT(4)
-#define SP_PRE_EMP_LEVEL1		BIT(3)
-#define SP_DRVIE_CURRENT_LEVEL1		BIT(0)
-
-/* DP Link Training Control Register */
-#define SP_DP_LT_CTRL_REG		0xa8
-#define SP_LT_ERROR_TYPE_MASK		0x70
-#  define SP_LT_NO_ERROR		0x00
-#  define SP_LT_AUX_WRITE_ERROR		0x01
-#  define SP_LT_MAX_DRIVE_REACHED	0x02
-#  define SP_LT_WRONG_LANE_COUNT_SET	0x03
-#  define SP_LT_LOOP_SAME_5_TIME	0x04
-#  define SP_LT_CR_FAIL_IN_EQ		0x05
-#  define SP_LT_EQ_LOOP_5_TIME		0x06
-#define SP_LT_EN			BIT(0)
-
-/* DP CEP Training Control Registers */
-#define SP_DP_CEP_TRAINING_CTRL0_REG	0xa9
-#define SP_DP_CEP_TRAINING_CTRL1_REG	0xaa
-
-/* DP Debug Register 1 */
-#define SP_DP_DEBUG1_REG		0xb0
-#define SP_DEBUG_PLL_LOCK		BIT(4)
-#define SP_POLLING_EN			BIT(1)
-
-/* DP Polling Control Register */
-#define SP_DP_POLLING_CTRL_REG		0xb4
-#define SP_AUTO_POLLING_DISABLE		BIT(0)
-
-/* DP Link Debug Control Register */
-#define SP_DP_LINK_DEBUG_CTRL_REG	0xb8
-#define SP_M_VID_DEBUG			BIT(5)
-#define SP_NEW_PRBS7			BIT(4)
-#define SP_INSERT_ER			BIT(1)
-#define SP_PRBS31_EN			BIT(0)
-
-/* AUX Misc control Register */
-#define SP_AUX_MISC_CTRL_REG		0xbf
-
-/* DP PLL control Register */
-#define SP_DP_PLL_CTRL_REG		0xc7
-#define SP_PLL_RST			BIT(6)
-
-/* DP Analog Power Down Register */
-#define SP_DP_ANALOG_POWER_DOWN_REG	0xc8
-#define SP_CH0_PD			BIT(0)
-
-/* DP Misc Control Register */
-#define SP_DP_MISC_CTRL_REG		0xcd
-#define SP_EQ_TRAINING_LOOP		BIT(6)
-
-/* DP Extra I2C Device Address Register */
-#define SP_DP_EXTRA_I2C_DEV_ADDR_REG	0xce
-#define SP_I2C_STRETCH_DISABLE		BIT(7)
-
-#define SP_I2C_EXTRA_ADDR		0x50
-
-/* DP Downspread Control Register 1 */
-#define SP_DP_DOWNSPREAD_CTRL1_REG	0xd0
-
-/* DP M Value Calculation Control Register */
-#define SP_DP_M_CALCULATION_CTRL_REG	0xd9
-#define SP_M_GEN_CLK_SEL		BIT(0)
-
-/* AUX Channel Access Status Register */
-#define SP_AUX_CH_STATUS_REG		0xe0
-#define SP_AUX_STATUS			0x0f
-
-/* AUX Channel DEFER Control Register */
-#define SP_AUX_DEFER_CTRL_REG		0xe2
-#define SP_DEFER_CTRL_EN		BIT(7)
-
-/* DP Buffer Data Count Register */
-#define SP_BUF_DATA_COUNT_REG		0xe4
-#define SP_BUF_DATA_COUNT_MASK		0x1f
-#define SP_BUF_CLR			BIT(7)
-
-/* DP AUX Channel Control Register 1 */
-#define SP_DP_AUX_CH_CTRL1_REG		0xe5
-#define SP_AUX_TX_COMM_MASK		0x0f
-#define SP_AUX_LENGTH_MASK		0xf0
-#define SP_AUX_LENGTH_SHIFT		4
-
-/* DP AUX CH Address Register 0 */
-#define SP_AUX_ADDR_7_0_REG		0xe6
-
-/* DP AUX CH Address Register 1 */
-#define SP_AUX_ADDR_15_8_REG		0xe7
-
-/* DP AUX CH Address Register 2 */
-#define SP_AUX_ADDR_19_16_REG		0xe8
-#define SP_AUX_ADDR_19_16_MASK		0x0f
-
-/* DP AUX Channel Control Register 2 */
-#define SP_DP_AUX_CH_CTRL2_REG		0xe9
-#define SP_AUX_SEL_RXCM			BIT(6)
-#define SP_AUX_CHSEL			BIT(3)
-#define SP_AUX_PN_INV			BIT(2)
-#define SP_ADDR_ONLY			BIT(1)
-#define SP_AUX_EN			BIT(0)
-
-/* DP Video Stream Control InfoFrame Register */
-#define SP_DP_3D_VSC_CTRL_REG		0xea
-#define SP_INFO_FRAME_VSC_EN		BIT(0)
-
-/* DP Video Stream Data Byte 1 Register */
-#define SP_DP_VSC_DB1_REG		0xeb
-
-/* DP AUX Channel Control Register 3 */
-#define SP_DP_AUX_CH_CTRL3_REG		0xec
-#define SP_WAIT_COUNTER_7_0_MASK	0xff
-
-/* DP AUX Channel Control Register 4 */
-#define SP_DP_AUX_CH_CTRL4_REG		0xed
-
-/* DP AUX Buffer Data Registers */
-#define SP_DP_BUF_DATA0_REG		0xf0
-
-/***************************************************************/
-/* Register definitions for TX_P2                              */
-/***************************************************************/
-
-/*
- * Core Register Definitions
- */
-
-/* Device ID Low Byte Register */
-#define SP_DEVICE_IDL_REG		0x02
-
-/* Device ID High Byte Register */
-#define SP_DEVICE_IDH_REG		0x03
-
-/* Device version register */
-#define SP_DEVICE_VERSION_REG		0x04
-
-/* Power Down Control Register */
-#define SP_POWERDOWN_CTRL_REG		0x05
-#define SP_REGISTER_PD			BIT(7)
-#define SP_HDCP_PD			BIT(5)
-#define SP_AUDIO_PD			BIT(4)
-#define SP_VIDEO_PD			BIT(3)
-#define SP_LINK_PD			BIT(2)
-#define SP_TOTAL_PD			BIT(1)
-
-/* Reset Control Register 1 */
-#define SP_RESET_CTRL1_REG		0x06
-#define SP_MISC_RST			BIT(7)
-#define SP_VIDCAP_RST			BIT(6)
-#define SP_VIDFIF_RST			BIT(5)
-#define SP_AUDFIF_RST			BIT(4)
-#define SP_AUDCAP_RST			BIT(3)
-#define SP_HDCP_RST			BIT(2)
-#define SP_SW_RST			BIT(1)
-#define SP_HW_RST			BIT(0)
-
-/* Reset Control Register 2 */
-#define SP_RESET_CTRL2_REG		0x07
-#define SP_AUX_RST			BIT(2)
-#define SP_SERDES_FIFO_RST		BIT(1)
-#define SP_I2C_REG_RST			BIT(0)
-
-/* Video Control Register 1 */
-#define SP_VID_CTRL1_REG		0x08
-#define SP_VIDEO_EN			BIT(7)
-#define SP_VIDEO_MUTE			BIT(2)
-#define SP_DE_GEN			BIT(1)
-#define SP_DEMUX			BIT(0)
-
-/* Video Control Register 2 */
-#define SP_VID_CTRL2_REG		0x09
-#define SP_IN_COLOR_F_MASK		0x03
-#define SP_IN_YC_BIT_SEL		BIT(2)
-#define SP_IN_BPC_MASK			0x70
-#define SP_IN_BPC_SHIFT			4
-#  define SP_IN_BPC_12BIT		0x03
-#  define SP_IN_BPC_10BIT		0x02
-#  define SP_IN_BPC_8BIT		0x01
-#  define SP_IN_BPC_6BIT		0x00
-#define SP_IN_D_RANGE			BIT(7)
-
-/* Video Control Register 3 */
-#define SP_VID_CTRL3_REG		0x0a
-#define SP_HPD_OUT			BIT(6)
-
-/* Video Control Register 5 */
-#define SP_VID_CTRL5_REG		0x0c
-#define SP_CSC_STD_SEL			BIT(7)
-#define SP_XVYCC_RNG_LMT		BIT(6)
-#define SP_RANGE_Y2R			BIT(5)
-#define SP_CSPACE_Y2R			BIT(4)
-#define SP_RGB_RNG_LMT			BIT(3)
-#define SP_Y_RNG_LMT			BIT(2)
-#define SP_RANGE_R2Y			BIT(1)
-#define SP_CSPACE_R2Y			BIT(0)
-
-/* Video Control Register 6 */
-#define SP_VID_CTRL6_REG		0x0d
-#define SP_TEST_PATTERN_EN		BIT(7)
-#define SP_VIDEO_PROCESS_EN		BIT(6)
-#define SP_VID_US_MODE			BIT(3)
-#define SP_VID_DS_MODE			BIT(2)
-#define SP_UP_SAMPLE			BIT(1)
-#define SP_DOWN_SAMPLE			BIT(0)
-
-/* Video Control Register 8 */
-#define SP_VID_CTRL8_REG		0x0f
-#define SP_VID_VRES_TH			BIT(0)
-
-/* Total Line Status Low Byte Register */
-#define SP_TOTAL_LINE_STAL_REG		0x24
-
-/* Total Line Status High Byte Register */
-#define SP_TOTAL_LINE_STAH_REG		0x25
-
-/* Active Line Status Low Byte Register */
-#define SP_ACT_LINE_STAL_REG		0x26
-
-/* Active Line Status High Byte Register */
-#define SP_ACT_LINE_STAH_REG		0x27
-
-/* Vertical Front Porch Status Register */
-#define SP_V_F_PORCH_STA_REG		0x28
-
-/* Vertical SYNC Width Status Register */
-#define SP_V_SYNC_STA_REG		0x29
-
-/* Vertical Back Porch Status Register */
-#define SP_V_B_PORCH_STA_REG		0x2a
-
-/* Total Pixel Status Low Byte Register */
-#define SP_TOTAL_PIXEL_STAL_REG		0x2b
-
-/* Total Pixel Status High Byte Register */
-#define SP_TOTAL_PIXEL_STAH_REG		0x2c
-
-/* Active Pixel Status Low Byte Register */
-#define SP_ACT_PIXEL_STAL_REG		0x2d
-
-/* Active Pixel Status High Byte Register */
-#define SP_ACT_PIXEL_STAH_REG		0x2e
-
-/* Horizontal Front Porch Status Low Byte Register */
-#define SP_H_F_PORCH_STAL_REG		0x2f
-
-/* Horizontal Front Porch Statys High Byte Register */
-#define SP_H_F_PORCH_STAH_REG		0x30
-
-/* Horizontal SYNC Width Status Low Byte Register */
-#define SP_H_SYNC_STAL_REG		0x31
-
-/* Horizontal SYNC Width Status High Byte Register */
-#define SP_H_SYNC_STAH_REG		0x32
-
-/* Horizontal Back Porch Status Low Byte Register */
-#define SP_H_B_PORCH_STAL_REG		0x33
-
-/* Horizontal Back Porch Status High Byte Register */
-#define SP_H_B_PORCH_STAH_REG		0x34
-
-/* InfoFrame AVI Packet DB1 Register */
-#define SP_INFOFRAME_AVI_DB1_REG	0x70
-
-/* Bit Control Specific Register */
-#define SP_BIT_CTRL_SPECIFIC_REG	0x80
-#define SP_BIT_CTRL_SELECT_SHIFT	1
-#define SP_ENABLE_BIT_CTRL		BIT(0)
-
-/* InfoFrame Audio Packet DB1 Register */
-#define SP_INFOFRAME_AUD_DB1_REG	0x83
-
-/* InfoFrame MPEG Packet DB1 Register */
-#define SP_INFOFRAME_MPEG_DB1_REG	0xb0
-
-/* Audio Channel Status Registers */
-#define SP_AUD_CH_STATUS_BASE		0xd0
-
-/* Audio Channel Num Register 5 */
-#define SP_I2S_CHANNEL_NUM_MASK		0xe0
-#  define SP_I2S_CH_NUM_1		(0x00 << 5)
-#  define SP_I2S_CH_NUM_2		(0x01 << 5)
-#  define SP_I2S_CH_NUM_3		(0x02 << 5)
-#  define SP_I2S_CH_NUM_4		(0x03 << 5)
-#  define SP_I2S_CH_NUM_5		(0x04 << 5)
-#  define SP_I2S_CH_NUM_6		(0x05 << 5)
-#  define SP_I2S_CH_NUM_7		(0x06 << 5)
-#  define SP_I2S_CH_NUM_8		(0x07 << 5)
-#define SP_EXT_VUCP			BIT(2)
-#define SP_VBIT				BIT(1)
-#define SP_AUDIO_LAYOUT			BIT(0)
-
-/* Analog Debug Register 2 */
-#define SP_ANALOG_DEBUG2_REG		0xdd
-#define SP_FORCE_SW_OFF_BYPASS		0x20
-#define SP_XTAL_FRQ			0x1c
-#  define SP_XTAL_FRQ_19M2		(0x00 << 2)
-#  define SP_XTAL_FRQ_24M		(0x01 << 2)
-#  define SP_XTAL_FRQ_25M		(0x02 << 2)
-#  define SP_XTAL_FRQ_26M		(0x03 << 2)
-#  define SP_XTAL_FRQ_27M		(0x04 << 2)
-#  define SP_XTAL_FRQ_38M4		(0x05 << 2)
-#  define SP_XTAL_FRQ_52M		(0x06 << 2)
-#define SP_POWERON_TIME_1P5MS		0x03
-
-/* Analog Control 0 Register */
-#define SP_ANALOG_CTRL0_REG		0xe1
-
-/* Common Interrupt Status Register 1 */
-#define SP_COMMON_INT_STATUS_BASE	(0xf1 - 1)
-#define SP_PLL_LOCK_CHG			0x40
-
-/* Common Interrupt Status Register 2 */
-#define SP_COMMON_INT_STATUS2		0xf2
-#define SP_HDCP_AUTH_CHG		BIT(1)
-#define SP_HDCP_AUTH_DONE		BIT(0)
-
-#define SP_HDCP_LINK_CHECK_FAIL		BIT(0)
-
-/* Common Interrupt Status Register 4 */
-#define SP_COMMON_INT_STATUS4_REG	0xf4
-#define SP_HPD_IRQ			BIT(6)
-#define SP_HPD_ESYNC_ERR		BIT(4)
-#define SP_HPD_CHG			BIT(2)
-#define SP_HPD_LOST			BIT(1)
-#define SP_HPD_PLUG			BIT(0)
-
-/* DP Interrupt Status Register */
-#define SP_DP_INT_STATUS1_REG		0xf7
-#define SP_TRAINING_FINISH		BIT(5)
-#define SP_POLLING_ERR			BIT(4)
-
-/* Common Interrupt Mask Register */
-#define SP_COMMON_INT_MASK_BASE		(0xf8 - 1)
-
-#define SP_COMMON_INT_MASK4_REG		0xfb
-
-/* DP Interrupts Mask Register */
-#define SP_DP_INT_MASK1_REG		0xfe
-
-/* Interrupt Control Register */
-#define SP_INT_CTRL_REG			0xff
-
-/***************************************************************/
-/* Register definitions for TX_P1                              */
-/***************************************************************/
-
-/* DP TX Link Training Control Register */
-#define SP_DP_TX_LT_CTRL0_REG		0x30
-
-/* PD 1.2 Lint Training 80bit Pattern Register */
-#define SP_DP_LT_80BIT_PATTERN0_REG	0x80
-#define SP_DP_LT_80BIT_PATTERN_REG_NUM	10
-
-/* Audio Interface Control Register 0 */
-#define SP_AUD_INTERFACE_CTRL0_REG	0x5f
-#define SP_AUD_INTERFACE_DISABLE	0x80
-
-/* Audio Interface Control Register 2 */
-#define SP_AUD_INTERFACE_CTRL2_REG	0x60
-#define SP_M_AUD_ADJUST_ST		0x04
-
-/* Audio Interface Control Register 3 */
-#define SP_AUD_INTERFACE_CTRL3_REG	0x62
-
-/* Audio Interface Control Register 4 */
-#define SP_AUD_INTERFACE_CTRL4_REG	0x67
-
-/* Audio Interface Control Register 5 */
-#define SP_AUD_INTERFACE_CTRL5_REG	0x68
-
-/* Audio Interface Control Register 6 */
-#define SP_AUD_INTERFACE_CTRL6_REG	0x69
-
-/* Firmware Version Register */
-#define SP_FW_VER_REG			0xb7
-
-#endif
diff --git a/drivers/gpu/drm/bridge/analogix/Kconfig b/drivers/gpu/drm/bridge/analogix/Kconfig
index e930ff9b5cd4..e1fa7d820373 100644
--- a/drivers/gpu/drm/bridge/analogix/Kconfig
+++ b/drivers/gpu/drm/bridge/analogix/Kconfig
@@ -1,4 +1,27 @@
 # SPDX-License-Identifier: GPL-2.0-only
+config DRM_ANALOGIX_ANX6345
+	tristate "Analogix ANX6345 bridge"
+	depends on OF
+	select DRM_ANALOGIX_DP
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	help
+	  ANX6345 is an ultra-low Full-HD DisplayPort/eDP
+	  transmitter designed for portable devices. The
+	  ANX6345 transforms the LVTTL RGB output of an
+	  application processor to eDP or DisplayPort.
+
+config DRM_ANALOGIX_ANX78XX
+	tristate "Analogix ANX78XX bridge"
+	select DRM_ANALOGIX_DP
+	select DRM_KMS_HELPER
+	select REGMAP_I2C
+	help
+	  ANX78XX is an ultra-low power Full-HD SlimPort transmitter
+	  designed for portable devices. The ANX78XX transforms
+	  the HDMI output of an application processor to MyDP
+	  or DisplayPort.
+
 config DRM_ANALOGIX_DP
 	tristate
 	depends on DRM
diff --git a/drivers/gpu/drm/bridge/analogix/Makefile b/drivers/gpu/drm/bridge/analogix/Makefile
index fdbf3fd2f087..97669b374098 100644
--- a/drivers/gpu/drm/bridge/analogix/Makefile
+++ b/drivers/gpu/drm/bridge/analogix/Makefile
@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-analogix_dp-objs := analogix_dp_core.o analogix_dp_reg.o
+analogix_dp-objs := analogix_dp_core.o analogix_dp_reg.o analogix-i2c-dptx.o
+obj-$(CONFIG_DRM_ANALOGIX_ANX6345) += analogix-anx6345.o
+obj-$(CONFIG_DRM_ANALOGIX_ANX78XX) += analogix-anx78xx.o
 obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix_dp.o
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
new file mode 100644
index 000000000000..56f55c53abfd
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c
@@ -0,0 +1,817 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor.
+ * Copyright(c) 2017, Icenowy Zheng <icenowy@aosc.io>
+ *
+ * Based on anx7808 driver obtained from chromeos with copyright:
+ * Copyright(c) 2013, Google Inc.
+ */
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/types.h>
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_bridge.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_of.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+#include <drm/drm_probe_helper.h>
+
+#include "analogix-i2c-dptx.h"
+#include "analogix-i2c-txcommon.h"
+
+#define POLL_DELAY		50000 /* us */
+#define POLL_TIMEOUT		5000000 /* us */
+
+#define I2C_IDX_DPTX		0
+#define I2C_IDX_TXCOM		1
+
+static const u8 anx6345_i2c_addresses[] = {
+	[I2C_IDX_DPTX]	= 0x70,
+	[I2C_IDX_TXCOM]	= 0x72,
+};
+#define I2C_NUM_ADDRESSES	ARRAY_SIZE(anx6345_i2c_addresses)
+
+struct anx6345 {
+	struct drm_dp_aux aux;
+	struct drm_bridge bridge;
+	struct i2c_client *client;
+	struct edid *edid;
+	struct drm_connector connector;
+	struct drm_panel *panel;
+	struct regulator *dvdd12;
+	struct regulator *dvdd25;
+	struct gpio_desc *gpiod_reset;
+	struct mutex lock;	/* protect EDID access */
+
+	/* I2C Slave addresses of ANX6345 are mapped as DPTX and SYS */
+	struct i2c_client *i2c_clients[I2C_NUM_ADDRESSES];
+	struct regmap *map[I2C_NUM_ADDRESSES];
+
+	u16 chipid;
+	u8 dpcd[DP_RECEIVER_CAP_SIZE];
+
+	bool powered;
+};
+
+static inline struct anx6345 *connector_to_anx6345(struct drm_connector *c)
+{
+	return container_of(c, struct anx6345, connector);
+}
+
+static inline struct anx6345 *bridge_to_anx6345(struct drm_bridge *bridge)
+{
+	return container_of(bridge, struct anx6345, bridge);
+}
+
+static int anx6345_set_bits(struct regmap *map, u8 reg, u8 mask)
+{
+	return regmap_update_bits(map, reg, mask, mask);
+}
+
+static int anx6345_clear_bits(struct regmap *map, u8 reg, u8 mask)
+{
+	return regmap_update_bits(map, reg, mask, 0);
+}
+
+static ssize_t anx6345_aux_transfer(struct drm_dp_aux *aux,
+				    struct drm_dp_aux_msg *msg)
+{
+	struct anx6345 *anx6345 = container_of(aux, struct anx6345, aux);
+
+	return anx_dp_aux_transfer(anx6345->map[I2C_IDX_DPTX], msg);
+}
+
+static int anx6345_dp_link_training(struct anx6345 *anx6345)
+{
+	unsigned int value;
+	u8 dp_bw, dpcd[2];
+	int err;
+
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				 SP_POWERDOWN_CTRL_REG,
+				 SP_TOTAL_PD);
+	if (err)
+		return err;
+
+	err = drm_dp_dpcd_readb(&anx6345->aux, DP_MAX_LINK_RATE, &dp_bw);
+	if (err < 0)
+		return err;
+
+	switch (dp_bw) {
+	case DP_LINK_BW_1_62:
+	case DP_LINK_BW_2_7:
+		break;
+
+	default:
+		DRM_DEBUG_KMS("DP bandwidth (%#02x) not supported\n", dp_bw);
+		return -EINVAL;
+	}
+
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL1_REG,
+			       SP_VIDEO_MUTE);
+	if (err)
+		return err;
+
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				 SP_VID_CTRL1_REG, SP_VIDEO_EN);
+	if (err)
+		return err;
+
+	/* Get DPCD info */
+	err = drm_dp_dpcd_read(&anx6345->aux, DP_DPCD_REV,
+			       &anx6345->dpcd, DP_RECEIVER_CAP_SIZE);
+	if (err < 0) {
+		DRM_ERROR("Failed to read DPCD: %d\n", err);
+		return err;
+	}
+
+	/* Clear channel x SERDES power down */
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_DPTX],
+				 SP_DP_ANALOG_POWER_DOWN_REG, SP_CH0_PD);
+	if (err)
+		return err;
+
+	/*
+	 * Power up the sink (DP_SET_POWER register is only available on DPCD
+	 * v1.1 and later).
+	 */
+	if (anx6345->dpcd[DP_DPCD_REV] >= 0x11) {
+		err = drm_dp_dpcd_readb(&anx6345->aux, DP_SET_POWER, &dpcd[0]);
+		if (err < 0) {
+			DRM_ERROR("Failed to read DP_SET_POWER register: %d\n",
+				  err);
+			return err;
+		}
+
+		dpcd[0] &= ~DP_SET_POWER_MASK;
+		dpcd[0] |= DP_SET_POWER_D0;
+
+		err = drm_dp_dpcd_writeb(&anx6345->aux, DP_SET_POWER, dpcd[0]);
+		if (err < 0) {
+			DRM_ERROR("Failed to power up DisplayPort link: %d\n",
+				  err);
+			return err;
+		}
+
+		/*
+		 * According to the DP 1.1 specification, a "Sink Device must
+		 * exit the power saving state within 1 ms" (Section 2.5.3.1,
+		 * Table 5-52, "Sink Control Field" (register 0x600).
+		 */
+		usleep_range(1000, 2000);
+	}
+
+	/* Possibly enable downspread on the sink */
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_DOWNSPREAD_CTRL1_REG, 0);
+	if (err)
+		return err;
+
+	if (anx6345->dpcd[DP_MAX_DOWNSPREAD] & DP_MAX_DOWNSPREAD_0_5) {
+		DRM_DEBUG("Enable downspread on the sink\n");
+		/* 4000PPM */
+		err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+				   SP_DP_DOWNSPREAD_CTRL1_REG, 8);
+		if (err)
+			return err;
+
+		err = drm_dp_dpcd_writeb(&anx6345->aux, DP_DOWNSPREAD_CTRL,
+					 DP_SPREAD_AMP_0_5);
+		if (err < 0)
+			return err;
+	} else {
+		err = drm_dp_dpcd_writeb(&anx6345->aux, DP_DOWNSPREAD_CTRL, 0);
+		if (err < 0)
+			return err;
+	}
+
+	/* Set the lane count and the link rate on the sink */
+	if (drm_dp_enhanced_frame_cap(anx6345->dpcd))
+		err = anx6345_set_bits(anx6345->map[I2C_IDX_DPTX],
+				       SP_DP_SYSTEM_CTRL_BASE + 4,
+				       SP_ENHANCED_MODE);
+	else
+		err = anx6345_clear_bits(anx6345->map[I2C_IDX_DPTX],
+					 SP_DP_SYSTEM_CTRL_BASE + 4,
+					 SP_ENHANCED_MODE);
+	if (err)
+		return err;
+
+	dpcd[0] = drm_dp_max_link_rate(anx6345->dpcd);
+	dpcd[0] = drm_dp_link_rate_to_bw_code(dpcd[0]);
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_MAIN_LINK_BW_SET_REG, dpcd[0]);
+	if (err)
+		return err;
+
+	dpcd[1] = drm_dp_max_lane_count(anx6345->dpcd);
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_LANE_COUNT_SET_REG, dpcd[1]);
+	if (err)
+		return err;
+
+	if (drm_dp_enhanced_frame_cap(anx6345->dpcd))
+		dpcd[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
+
+	err = drm_dp_dpcd_write(&anx6345->aux, DP_LINK_BW_SET, dpcd,
+				sizeof(dpcd));
+
+	if (err < 0) {
+		DRM_ERROR("Failed to configure link: %d\n", err);
+		return err;
+	}
+
+	/* Start training on the source */
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX], SP_DP_LT_CTRL_REG,
+			   SP_LT_EN);
+	if (err)
+		return err;
+
+	return regmap_read_poll_timeout(anx6345->map[I2C_IDX_DPTX],
+				       SP_DP_LT_CTRL_REG,
+				       value, !(value & SP_DP_LT_INPROGRESS),
+				       POLL_DELAY, POLL_TIMEOUT);
+}
+
+static int anx6345_tx_initialization(struct anx6345 *anx6345)
+{
+	int err, i;
+
+	/* FIXME: colordepth is hardcoded for now */
+	err = regmap_write(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL2_REG,
+			   SP_IN_BPC_6BIT << SP_IN_BPC_SHIFT);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX], SP_DP_PLL_CTRL_REG, 0);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_TXCOM],
+			   SP_ANALOG_DEBUG1_REG, 0);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_LINK_DEBUG_CTRL_REG,
+			   SP_NEW_PRBS7 | SP_M_VID_DEBUG);
+	if (err)
+		return err;
+
+	err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+			   SP_DP_ANALOG_POWER_DOWN_REG, 0);
+	if (err)
+		return err;
+
+	/* Force HPD */
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_DPTX],
+			       SP_DP_SYSTEM_CTRL_BASE + 3,
+			       SP_HPD_FORCE | SP_HPD_CTRL);
+	if (err)
+		return err;
+
+	for (i = 0; i < 4; i++) {
+		/* 4 lanes */
+		err = regmap_write(anx6345->map[I2C_IDX_DPTX],
+				   SP_DP_LANE0_LT_CTRL_REG + i, 0);
+		if (err)
+			return err;
+	}
+
+	/* Reset AUX */
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM],
+			       SP_RESET_CTRL2_REG, SP_AUX_RST);
+	if (err)
+		return err;
+
+	return anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				 SP_RESET_CTRL2_REG, SP_AUX_RST);
+}
+
+static void anx6345_poweron(struct anx6345 *anx6345)
+{
+	int err;
+
+	/* Ensure reset is asserted before starting power on sequence */
+	gpiod_set_value_cansleep(anx6345->gpiod_reset, 1);
+	usleep_range(1000, 2000);
+
+	err = regulator_enable(anx6345->dvdd12);
+	if (err) {
+		DRM_ERROR("Failed to enable dvdd12 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	/* T1 - delay between VDD12 and VDD25 should be 0-2ms */
+	usleep_range(1000, 2000);
+
+	err = regulator_enable(anx6345->dvdd25);
+	if (err) {
+		DRM_ERROR("Failed to enable dvdd25 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	/* T2 - delay between RESETN and all power rail stable,
+	 * should be 2-5ms
+	 */
+	usleep_range(2000, 5000);
+
+	gpiod_set_value_cansleep(anx6345->gpiod_reset, 0);
+
+	/* Power on registers module */
+	anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_POWERDOWN_CTRL_REG,
+			 SP_HDCP_PD | SP_AUDIO_PD | SP_VIDEO_PD | SP_LINK_PD);
+	anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM], SP_POWERDOWN_CTRL_REG,
+			   SP_REGISTER_PD | SP_TOTAL_PD);
+
+	if (anx6345->panel)
+		drm_panel_prepare(anx6345->panel);
+
+	anx6345->powered = true;
+}
+
+static void anx6345_poweroff(struct anx6345 *anx6345)
+{
+	int err;
+
+	gpiod_set_value_cansleep(anx6345->gpiod_reset, 1);
+	usleep_range(1000, 2000);
+
+	if (anx6345->panel)
+		drm_panel_unprepare(anx6345->panel);
+
+	err = regulator_disable(anx6345->dvdd25);
+	if (err) {
+		DRM_ERROR("Failed to disable dvdd25 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	usleep_range(5000, 10000);
+
+	err = regulator_disable(anx6345->dvdd12);
+	if (err) {
+		DRM_ERROR("Failed to disable dvdd12 regulator: %d\n",
+			  err);
+		return;
+	}
+
+	usleep_range(1000, 2000);
+
+	anx6345->powered = false;
+}
+
+static int anx6345_start(struct anx6345 *anx6345)
+{
+	int err;
+
+	if (!anx6345->powered)
+		anx6345_poweron(anx6345);
+
+	/* Power on needed modules */
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM],
+				SP_POWERDOWN_CTRL_REG,
+				SP_VIDEO_PD | SP_LINK_PD);
+
+	err = anx6345_tx_initialization(anx6345);
+	if (err) {
+		DRM_ERROR("Failed eDP transmitter initialization: %d\n", err);
+		anx6345_poweroff(anx6345);
+		return err;
+	}
+
+	err = anx6345_dp_link_training(anx6345);
+	if (err) {
+		DRM_ERROR("Failed link training: %d\n", err);
+		anx6345_poweroff(anx6345);
+		return err;
+	}
+
+	/*
+	 * This delay seems to help keep the hardware in a good state. Without
+	 * it, there are times where it fails silently.
+	 */
+	usleep_range(10000, 15000);
+
+	return 0;
+}
+
+static int anx6345_config_dp_output(struct anx6345 *anx6345)
+{
+	int err;
+
+	err = anx6345_clear_bits(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL1_REG,
+				 SP_VIDEO_MUTE);
+	if (err)
+		return err;
+
+	/* Enable DP output */
+	err = anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_VID_CTRL1_REG,
+			       SP_VIDEO_EN);
+	if (err)
+		return err;
+
+	/* Force stream valid */
+	return anx6345_set_bits(anx6345->map[I2C_IDX_DPTX],
+			       SP_DP_SYSTEM_CTRL_BASE + 3,
+			       SP_STRM_FORCE | SP_STRM_CTRL);
+}
+
+static int anx6345_get_downstream_info(struct anx6345 *anx6345)
+{
+	u8 value;
+	int err;
+
+	err = drm_dp_dpcd_readb(&anx6345->aux, DP_SINK_COUNT, &value);
+	if (err < 0) {
+		DRM_ERROR("Get sink count failed %d\n", err);
+		return err;
+	}
+
+	if (!DP_GET_SINK_COUNT(value)) {
+		DRM_ERROR("Downstream disconnected\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int anx6345_get_modes(struct drm_connector *connector)
+{
+	struct anx6345 *anx6345 = connector_to_anx6345(connector);
+	int err, num_modes = 0;
+	bool power_off = false;
+
+	mutex_lock(&anx6345->lock);
+
+	if (!anx6345->edid) {
+		if (!anx6345->powered) {
+			anx6345_poweron(anx6345);
+			power_off = true;
+		}
+
+		err = anx6345_get_downstream_info(anx6345);
+		if (err) {
+			DRM_ERROR("Failed to get downstream info: %d\n", err);
+			goto unlock;
+		}
+
+		anx6345->edid = drm_get_edid(connector, &anx6345->aux.ddc);
+		if (!anx6345->edid)
+			DRM_ERROR("Failed to read EDID from panel\n");
+
+		err = drm_connector_update_edid_property(connector,
+							 anx6345->edid);
+		if (err) {
+			DRM_ERROR("Failed to update EDID property: %d\n", err);
+			goto unlock;
+		}
+	}
+
+	num_modes += drm_add_edid_modes(connector, anx6345->edid);
+
+unlock:
+	if (power_off)
+		anx6345_poweroff(anx6345);
+
+	mutex_unlock(&anx6345->lock);
+
+	if (!num_modes && anx6345->panel)
+		num_modes += drm_panel_get_modes(anx6345->panel, connector);
+
+	return num_modes;
+}
+
+static const struct drm_connector_helper_funcs anx6345_connector_helper_funcs = {
+	.get_modes = anx6345_get_modes,
+};
+
+static void
+anx6345_connector_destroy(struct drm_connector *connector)
+{
+	struct anx6345 *anx6345 = connector_to_anx6345(connector);
+
+	if (anx6345->panel)
+		drm_panel_detach(anx6345->panel);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs anx6345_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = anx6345_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int anx6345_bridge_attach(struct drm_bridge *bridge)
+{
+	struct anx6345 *anx6345 = bridge_to_anx6345(bridge);
+	int err;
+
+	if (!bridge->encoder) {
+		DRM_ERROR("Parent encoder object not found");
+		return -ENODEV;
+	}
+
+	/* Register aux channel */
+	anx6345->aux.name = "DP-AUX";
+	anx6345->aux.dev = &anx6345->client->dev;
+	anx6345->aux.transfer = anx6345_aux_transfer;
+
+	err = drm_dp_aux_register(&anx6345->aux);
+	if (err < 0) {
+		DRM_ERROR("Failed to register aux channel: %d\n", err);
+		return err;
+	}
+
+	err = drm_connector_init(bridge->dev, &anx6345->connector,
+				 &anx6345_connector_funcs,
+				 DRM_MODE_CONNECTOR_eDP);
+	if (err) {
+		DRM_ERROR("Failed to initialize connector: %d\n", err);
+		return err;
+	}
+
+	drm_connector_helper_add(&anx6345->connector,
+				 &anx6345_connector_helper_funcs);
+
+	err = drm_connector_register(&anx6345->connector);
+	if (err) {
+		DRM_ERROR("Failed to register connector: %d\n", err);
+		return err;
+	}
+
+	anx6345->connector.polled = DRM_CONNECTOR_POLL_HPD;
+
+	err = drm_connector_attach_encoder(&anx6345->connector,
+					   bridge->encoder);
+	if (err) {
+		DRM_ERROR("Failed to link up connector to encoder: %d\n", err);
+		return err;
+	}
+
+	if (anx6345->panel) {
+		err = drm_panel_attach(anx6345->panel, &anx6345->connector);
+		if (err) {
+			DRM_ERROR("Failed to attach panel: %d\n", err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static enum drm_mode_status
+anx6345_bridge_mode_valid(struct drm_bridge *bridge,
+			  const struct drm_display_mode *mode)
+{
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		return MODE_NO_INTERLACE;
+
+	/* Max 1200p at 5.4 Ghz, one lane */
+	if (mode->clock > 154000)
+		return MODE_CLOCK_HIGH;
+
+	return MODE_OK;
+}
+
+static void anx6345_bridge_disable(struct drm_bridge *bridge)
+{
+	struct anx6345 *anx6345 = bridge_to_anx6345(bridge);
+
+	/* Power off all modules except configuration registers access */
+	anx6345_set_bits(anx6345->map[I2C_IDX_TXCOM], SP_POWERDOWN_CTRL_REG,
+			 SP_HDCP_PD | SP_AUDIO_PD | SP_VIDEO_PD | SP_LINK_PD);
+	if (anx6345->panel)
+		drm_panel_disable(anx6345->panel);
+
+	if (anx6345->powered)
+		anx6345_poweroff(anx6345);
+}
+
+static void anx6345_bridge_enable(struct drm_bridge *bridge)
+{
+	struct anx6345 *anx6345 = bridge_to_anx6345(bridge);
+	int err;
+
+	if (anx6345->panel)
+		drm_panel_enable(anx6345->panel);
+
+	err = anx6345_start(anx6345);
+	if (err) {
+		DRM_ERROR("Failed to initialize: %d\n", err);
+		return;
+	}
+
+	err = anx6345_config_dp_output(anx6345);
+	if (err)
+		DRM_ERROR("Failed to enable DP output: %d\n", err);
+}
+
+static const struct drm_bridge_funcs anx6345_bridge_funcs = {
+	.attach = anx6345_bridge_attach,
+	.mode_valid = anx6345_bridge_mode_valid,
+	.disable = anx6345_bridge_disable,
+	.enable = anx6345_bridge_enable,
+};
+
+static void unregister_i2c_dummy_clients(struct anx6345 *anx6345)
+{
+	unsigned int i;
+
+	for (i = 1; i < ARRAY_SIZE(anx6345->i2c_clients); i++)
+		if (anx6345->i2c_clients[i] &&
+		    anx6345->i2c_clients[i]->addr != anx6345->client->addr)
+			i2c_unregister_device(anx6345->i2c_clients[i]);
+}
+
+static const struct regmap_config anx6345_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = 0xff,
+	.cache_type = REGCACHE_NONE,
+};
+
+static const u16 anx6345_chipid_list[] = {
+	0x6345,
+};
+
+static bool anx6345_get_chip_id(struct anx6345 *anx6345)
+{
+	unsigned int i, idl, idh, version;
+
+	if (regmap_read(anx6345->map[I2C_IDX_TXCOM], SP_DEVICE_IDL_REG, &idl))
+		return false;
+
+	if (regmap_read(anx6345->map[I2C_IDX_TXCOM], SP_DEVICE_IDH_REG, &idh))
+		return false;
+
+	anx6345->chipid = (u8)idl | ((u8)idh << 8);
+
+	if (regmap_read(anx6345->map[I2C_IDX_TXCOM], SP_DEVICE_VERSION_REG,
+			&version))
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(anx6345_chipid_list); i++) {
+		if (anx6345->chipid == anx6345_chipid_list[i]) {
+			DRM_INFO("Found ANX%x (ver. %d) eDP Transmitter\n",
+				 anx6345->chipid, version);
+			return true;
+		}
+	}
+
+	DRM_ERROR("ANX%x (ver. %d) not supported by this driver\n",
+		  anx6345->chipid, version);
+
+	return false;
+}
+
+static int anx6345_i2c_probe(struct i2c_client *client,
+			     const struct i2c_device_id *id)
+{
+	struct anx6345 *anx6345;
+	struct device *dev;
+	int i, err;
+
+	anx6345 = devm_kzalloc(&client->dev, sizeof(*anx6345), GFP_KERNEL);
+	if (!anx6345)
+		return -ENOMEM;
+
+	mutex_init(&anx6345->lock);
+
+	anx6345->bridge.of_node = client->dev.of_node;
+
+	anx6345->client = client;
+	i2c_set_clientdata(client, anx6345);
+
+	dev = &anx6345->client->dev;
+
+	err = drm_of_find_panel_or_bridge(client->dev.of_node, 1, 0,
+					  &anx6345->panel, NULL);
+	if (err == -EPROBE_DEFER)
+		return err;
+
+	if (err)
+		DRM_DEBUG("No panel found\n");
+
+	/* 1.2V digital core power regulator  */
+	anx6345->dvdd12 = devm_regulator_get(dev, "dvdd12-supply");
+	if (IS_ERR(anx6345->dvdd12)) {
+		DRM_ERROR("dvdd12-supply not found\n");
+		return PTR_ERR(anx6345->dvdd12);
+	}
+
+	/* 2.5V digital core power regulator  */
+	anx6345->dvdd25 = devm_regulator_get(dev, "dvdd25-supply");
+	if (IS_ERR(anx6345->dvdd25)) {
+		DRM_ERROR("dvdd25-supply not found\n");
+		return PTR_ERR(anx6345->dvdd25);
+	}
+
+	/* GPIO for chip reset */
+	anx6345->gpiod_reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(anx6345->gpiod_reset)) {
+		DRM_ERROR("Reset gpio not found\n");
+		return PTR_ERR(anx6345->gpiod_reset);
+	}
+
+	/* Map slave addresses of ANX6345 */
+	for (i = 0; i < I2C_NUM_ADDRESSES; i++) {
+		if (anx6345_i2c_addresses[i] >> 1 != client->addr)
+			anx6345->i2c_clients[i] = i2c_new_dummy_device(client->adapter,
+						anx6345_i2c_addresses[i] >> 1);
+		else
+			anx6345->i2c_clients[i] = client;
+
+		if (IS_ERR(anx6345->i2c_clients[i])) {
+			err = PTR_ERR(anx6345->i2c_clients[i]);
+			DRM_ERROR("Failed to reserve I2C bus %02x\n",
+				  anx6345_i2c_addresses[i]);
+			goto err_unregister_i2c;
+		}
+
+		anx6345->map[i] = devm_regmap_init_i2c(anx6345->i2c_clients[i],
+						       &anx6345_regmap_config);
+		if (IS_ERR(anx6345->map[i])) {
+			err = PTR_ERR(anx6345->map[i]);
+			DRM_ERROR("Failed regmap initialization %02x\n",
+				  anx6345_i2c_addresses[i]);
+			goto err_unregister_i2c;
+		}
+	}
+
+	/* Look for supported chip ID */
+	anx6345_poweron(anx6345);
+	if (anx6345_get_chip_id(anx6345)) {
+		anx6345->bridge.funcs = &anx6345_bridge_funcs;
+		drm_bridge_add(&anx6345->bridge);
+
+		return 0;
+	} else {
+		anx6345_poweroff(anx6345);
+		err = -ENODEV;
+	}
+
+err_unregister_i2c:
+	unregister_i2c_dummy_clients(anx6345);
+	return err;
+}
+
+static int anx6345_i2c_remove(struct i2c_client *client)
+{
+	struct anx6345 *anx6345 = i2c_get_clientdata(client);
+
+	drm_bridge_remove(&anx6345->bridge);
+
+	unregister_i2c_dummy_clients(anx6345);
+
+	kfree(anx6345->edid);
+
+	mutex_destroy(&anx6345->lock);
+
+	return 0;
+}
+
+static const struct i2c_device_id anx6345_id[] = {
+	{ "anx6345", 0 },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(i2c, anx6345_id);
+
+static const struct of_device_id anx6345_match_table[] = {
+	{ .compatible = "analogix,anx6345", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, anx6345_match_table);
+
+static struct i2c_driver anx6345_driver = {
+	.driver = {
+		   .name = "anx6345",
+		   .of_match_table = of_match_ptr(anx6345_match_table),
+		  },
+	.probe = anx6345_i2c_probe,
+	.remove = anx6345_i2c_remove,
+	.id_table = anx6345_id,
+};
+module_i2c_driver(anx6345_driver);
+
+MODULE_DESCRIPTION("ANX6345 eDP Transmitter driver");
+MODULE_AUTHOR("Icenowy Zheng <icenowy@aosc.io>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
index 274989f96a91..41867be03751 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c
@@ -36,8 +36,6 @@
 #define I2C_IDX_RX_P1		4
 
 #define XTAL_CLK		270 /* 27M */
-#define AUX_CH_BUFFER_SIZE	16
-#define AUX_WAIT_TIMEOUT_MS	15
 
 static const u8 anx7808_i2c_addresses[] = {
 	[I2C_IDX_TX_P0] = 0x78,
@@ -107,153 +105,11 @@ static int anx78xx_clear_bits(struct regmap *map, u8 reg, u8 mask)
 	return regmap_update_bits(map, reg, mask, 0);
 }
 
-static bool anx78xx_aux_op_finished(struct anx78xx *anx78xx)
-{
-	unsigned int value;
-	int err;
-
-	err = regmap_read(anx78xx->map[I2C_IDX_TX_P0], SP_DP_AUX_CH_CTRL2_REG,
-			  &value);
-	if (err < 0)
-		return false;
-
-	return (value & SP_AUX_EN) == 0;
-}
-
-static int anx78xx_aux_wait(struct anx78xx *anx78xx)
-{
-	unsigned long timeout;
-	unsigned int status;
-	int err;
-
-	timeout = jiffies + msecs_to_jiffies(AUX_WAIT_TIMEOUT_MS) + 1;
-
-	while (!anx78xx_aux_op_finished(anx78xx)) {
-		if (time_after(jiffies, timeout)) {
-			if (!anx78xx_aux_op_finished(anx78xx)) {
-				DRM_ERROR("Timed out waiting AUX to finish\n");
-				return -ETIMEDOUT;
-			}
-
-			break;
-		}
-
-		usleep_range(1000, 2000);
-	}
-
-	/* Read the AUX channel access status */
-	err = regmap_read(anx78xx->map[I2C_IDX_TX_P0], SP_AUX_CH_STATUS_REG,
-			  &status);
-	if (err < 0) {
-		DRM_ERROR("Failed to read from AUX channel: %d\n", err);
-		return err;
-	}
-
-	if (status & SP_AUX_STATUS) {
-		DRM_ERROR("Failed to wait for AUX channel (status: %02x)\n",
-			  status);
-		return -ETIMEDOUT;
-	}
-
-	return 0;
-}
-
-static int anx78xx_aux_address(struct anx78xx *anx78xx, unsigned int addr)
-{
-	int err;
-
-	err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], SP_AUX_ADDR_7_0_REG,
-			   addr & 0xff);
-	if (err)
-		return err;
-
-	err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], SP_AUX_ADDR_15_8_REG,
-			   (addr & 0xff00) >> 8);
-	if (err)
-		return err;
-
-	/*
-	 * DP AUX CH Address Register #2, only update bits[3:0]
-	 * [7:4] RESERVED
-	 * [3:0] AUX_ADDR[19:16], Register control AUX CH address.
-	 */
-	err = regmap_update_bits(anx78xx->map[I2C_IDX_TX_P0],
-				 SP_AUX_ADDR_19_16_REG,
-				 SP_AUX_ADDR_19_16_MASK,
-				 (addr & 0xf0000) >> 16);
-
-	if (err)
-		return err;
-
-	return 0;
-}
-
 static ssize_t anx78xx_aux_transfer(struct drm_dp_aux *aux,
 				    struct drm_dp_aux_msg *msg)
 {
 	struct anx78xx *anx78xx = container_of(aux, struct anx78xx, aux);
-	u8 ctrl1 = msg->request;
-	u8 ctrl2 = SP_AUX_EN;
-	u8 *buffer = msg->buffer;
-	int err;
-
-	/* The DP AUX transmit and receive buffer has 16 bytes. */
-	if (WARN_ON(msg->size > AUX_CH_BUFFER_SIZE))
-		return -E2BIG;
-
-	/* Zero-sized messages specify address-only transactions. */
-	if (msg->size < 1)
-		ctrl2 |= SP_ADDR_ONLY;
-	else	/* For non-zero-sized set the length field. */
-		ctrl1 |= (msg->size - 1) << SP_AUX_LENGTH_SHIFT;
-
-	if ((msg->request & DP_AUX_I2C_READ) == 0) {
-		/* When WRITE | MOT write values to data buffer */
-		err = regmap_bulk_write(anx78xx->map[I2C_IDX_TX_P0],
-					SP_DP_BUF_DATA0_REG, buffer,
-					msg->size);
-		if (err)
-			return err;
-	}
-
-	/* Write address and request */
-	err = anx78xx_aux_address(anx78xx, msg->address);
-	if (err)
-		return err;
-
-	err = regmap_write(anx78xx->map[I2C_IDX_TX_P0], SP_DP_AUX_CH_CTRL1_REG,
-			   ctrl1);
-	if (err)
-		return err;
-
-	/* Start transaction */
-	err = regmap_update_bits(anx78xx->map[I2C_IDX_TX_P0],
-				 SP_DP_AUX_CH_CTRL2_REG, SP_ADDR_ONLY |
-				 SP_AUX_EN, ctrl2);
-	if (err)
-		return err;
-
-	err = anx78xx_aux_wait(anx78xx);
-	if (err)
-		return err;
-
-	msg->reply = DP_AUX_I2C_REPLY_ACK;
-
-	if ((msg->size > 0) && (msg->request & DP_AUX_I2C_READ)) {
-		/* Read values from data buffer */
-		err = regmap_bulk_read(anx78xx->map[I2C_IDX_TX_P0],
-				       SP_DP_BUF_DATA0_REG, buffer,
-				       msg->size);
-		if (err)
-			return err;
-	}
-
-	err = anx78xx_clear_bits(anx78xx->map[I2C_IDX_TX_P0],
-				 SP_DP_AUX_CH_CTRL2_REG, SP_ADDR_ONLY);
-	if (err)
-		return err;
-
-	return msg->size;
+	return anx_dp_aux_transfer(anx78xx->map[I2C_IDX_TX_P0], msg);
 }
 
 static int anx78xx_set_hpd(struct anx78xx *anx78xx)
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.h b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.h
new file mode 100644
index 000000000000..db2a2725acb2
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.h
@@ -0,0 +1,249 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor. All rights reserved.
+ */
+
+#ifndef __ANX78xx_H
+#define __ANX78xx_H
+
+#include "analogix-i2c-dptx.h"
+#include "analogix-i2c-txcommon.h"
+
+/***************************************************************/
+/* Register definitions for RX_PO                              */
+/***************************************************************/
+
+/*
+ * System Control and Status
+ */
+
+/* Software Reset Register 1 */
+#define SP_SOFTWARE_RESET1_REG		0x11
+#define SP_VIDEO_RST			BIT(4)
+#define SP_HDCP_MAN_RST			BIT(2)
+#define SP_TMDS_RST			BIT(1)
+#define SP_SW_MAN_RST			BIT(0)
+
+/* System Status Register */
+#define SP_SYSTEM_STATUS_REG		0x14
+#define SP_TMDS_CLOCK_DET		BIT(1)
+#define SP_TMDS_DE_DET			BIT(0)
+
+/* HDMI Status Register */
+#define SP_HDMI_STATUS_REG		0x15
+#define SP_HDMI_AUD_LAYOUT		BIT(3)
+#define SP_HDMI_DET			BIT(0)
+#  define SP_DVI_MODE			0
+#  define SP_HDMI_MODE			1
+
+/* HDMI Mute Control Register */
+#define SP_HDMI_MUTE_CTRL_REG		0x16
+#define SP_AUD_MUTE			BIT(1)
+#define SP_VID_MUTE			BIT(0)
+
+/* System Power Down Register 1 */
+#define SP_SYSTEM_POWER_DOWN1_REG	0x18
+#define SP_PWDN_CTRL			BIT(0)
+
+/*
+ * Audio and Video Auto Control
+ */
+
+/* Auto Audio and Video Control register */
+#define SP_AUDVID_CTRL_REG		0x20
+#define SP_AVC_OE			BIT(7)
+#define SP_AAC_OE			BIT(6)
+#define SP_AVC_EN			BIT(1)
+#define SP_AAC_EN			BIT(0)
+
+/* Audio Exception Enable Registers */
+#define SP_AUD_EXCEPTION_ENABLE_BASE	(0x24 - 1)
+/* Bits for Audio Exception Enable Register 3 */
+#define SP_AEC_EN21			BIT(5)
+
+/*
+ * Interrupt
+ */
+
+/* Interrupt Status Register 1 */
+#define SP_INT_STATUS1_REG		0x31
+/* Bits for Interrupt Status Register 1 */
+#define SP_HDMI_DVI			BIT(7)
+#define SP_CKDT_CHG			BIT(6)
+#define SP_SCDT_CHG			BIT(5)
+#define SP_PCLK_CHG			BIT(4)
+#define SP_PLL_UNLOCK			BIT(3)
+#define SP_CABLE_PLUG_CHG		BIT(2)
+#define SP_SET_MUTE			BIT(1)
+#define SP_SW_INTR			BIT(0)
+/* Bits for Interrupt Status Register 2 */
+#define SP_HDCP_ERR			BIT(5)
+#define SP_AUDIO_SAMPLE_CHG		BIT(0)	/* undocumented */
+/* Bits for Interrupt Status Register 3 */
+#define SP_AUD_MODE_CHG			BIT(0)
+/* Bits for Interrupt Status Register 5 */
+#define SP_AUDIO_RCV			BIT(0)
+/* Bits for Interrupt Status Register 6 */
+#define SP_INT_STATUS6_REG		0x36
+#define SP_CTS_RCV			BIT(7)
+#define SP_NEW_AUD_PKT			BIT(4)
+#define SP_NEW_AVI_PKT			BIT(1)
+#define SP_NEW_CP_PKT			BIT(0)
+/* Bits for Interrupt Status Register 7 */
+#define SP_NO_VSI			BIT(7)
+#define SP_NEW_VS			BIT(4)
+
+/* Interrupt Mask 1 Status Registers */
+#define SP_INT_MASK1_REG		0x41
+
+/* HDMI US TIMER Control Register */
+#define SP_HDMI_US_TIMER_CTRL_REG	0x49
+#define SP_MS_TIMER_MARGIN_10_8_MASK	0x07
+
+/*
+ * TMDS Control
+ */
+
+/* TMDS Control Registers */
+#define SP_TMDS_CTRL_BASE		(0x50 - 1)
+/* Bits for TMDS Control Register 7 */
+#define SP_PD_RT			BIT(0)
+
+/*
+ * Video Control
+ */
+
+/* Video Status Register */
+#define SP_VIDEO_STATUS_REG		0x70
+#define SP_COLOR_DEPTH_MASK		0xf0
+#define SP_COLOR_DEPTH_SHIFT		4
+#  define SP_COLOR_DEPTH_MODE_LEGACY	0x00
+#  define SP_COLOR_DEPTH_MODE_24BIT	0x04
+#  define SP_COLOR_DEPTH_MODE_30BIT	0x05
+#  define SP_COLOR_DEPTH_MODE_36BIT	0x06
+#  define SP_COLOR_DEPTH_MODE_48BIT	0x07
+
+/* Video Data Range Control Register */
+#define SP_VID_DATA_RANGE_CTRL_REG	0x83
+#define SP_R2Y_INPUT_LIMIT		BIT(1)
+
+/* Pixel Clock High Resolution Counter Registers */
+#define SP_PCLK_HIGHRES_CNT_BASE	(0x8c - 1)
+
+/*
+ * Audio Control
+ */
+
+/* Number of Audio Channels Status Registers */
+#define SP_AUD_CH_STATUS_REG_NUM	6
+
+/* Audio IN S/PDIF Channel Status Registers */
+#define SP_AUD_SPDIF_CH_STATUS_BASE	0xc7
+
+/* Audio IN S/PDIF Channel Status Register 4 */
+#define SP_FS_FREQ_MASK			0x0f
+#  define SP_FS_FREQ_44100HZ		0x00
+#  define SP_FS_FREQ_48000HZ		0x02
+#  define SP_FS_FREQ_32000HZ		0x03
+#  define SP_FS_FREQ_88200HZ		0x08
+#  define SP_FS_FREQ_96000HZ		0x0a
+#  define SP_FS_FREQ_176400HZ		0x0c
+#  define SP_FS_FREQ_192000HZ		0x0e
+
+/*
+ * Micellaneous Control Block
+ */
+
+/* CHIP Control Register */
+#define SP_CHIP_CTRL_REG		0xe3
+#define SP_MAN_HDMI5V_DET		BIT(3)
+#define SP_PLLLOCK_CKDT_EN		BIT(2)
+#define SP_ANALOG_CKDT_EN		BIT(1)
+#define SP_DIGITAL_CKDT_EN		BIT(0)
+
+/* Packet Receiving Status Register */
+#define SP_PACKET_RECEIVING_STATUS_REG	0xf3
+#define SP_AVI_RCVD			BIT(5)
+#define SP_VSI_RCVD			BIT(1)
+
+/***************************************************************/
+/* Register definitions for RX_P1                              */
+/***************************************************************/
+
+/* HDCP BCAPS Shadow Register */
+#define SP_HDCP_BCAPS_SHADOW_REG	0x2a
+#define SP_BCAPS_REPEATER		BIT(5)
+
+/* HDCP Status Register */
+#define SP_RX_HDCP_STATUS_REG		0x3f
+#define SP_AUTH_EN			BIT(4)
+
+/*
+ * InfoFrame and Control Packet Registers
+ */
+
+/* AVI InfoFrame packet checksum */
+#define SP_AVI_INFOFRAME_CHECKSUM	0xa3
+
+/* AVI InfoFrame Registers */
+#define SP_AVI_INFOFRAME_DATA_BASE	0xa4
+
+#define SP_AVI_COLOR_F_MASK		0x60
+#define SP_AVI_COLOR_F_SHIFT		5
+
+/* Audio InfoFrame Registers */
+#define SP_AUD_INFOFRAME_DATA_BASE	0xc4
+#define SP_AUD_INFOFRAME_LAYOUT_MASK	0x0f
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet type code */
+#define SP_MPEG_VS_INFOFRAME_TYPE_REG	0xe0
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet length */
+#define SP_MPEG_VS_INFOFRAME_LEN_REG	0xe2
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet version number */
+#define SP_MPEG_VS_INFOFRAME_VER_REG	0xe1
+
+/* MPEG/HDMI Vendor Specific InfoFrame Packet content */
+#define SP_MPEG_VS_INFOFRAME_DATA_BASE	0xe4
+
+/* General Control Packet Register */
+#define SP_GENERAL_CTRL_PACKET_REG	0x9f
+#define SP_CLEAR_AVMUTE			BIT(4)
+#define SP_SET_AVMUTE			BIT(0)
+
+/***************************************************************/
+/* Register definitions for TX_P1                              */
+/***************************************************************/
+
+/* DP TX Link Training Control Register */
+#define SP_DP_TX_LT_CTRL0_REG		0x30
+
+/* PD 1.2 Lint Training 80bit Pattern Register */
+#define SP_DP_LT_80BIT_PATTERN0_REG	0x80
+#define SP_DP_LT_80BIT_PATTERN_REG_NUM	10
+
+/* Audio Interface Control Register 0 */
+#define SP_AUD_INTERFACE_CTRL0_REG	0x5f
+#define SP_AUD_INTERFACE_DISABLE	0x80
+
+/* Audio Interface Control Register 2 */
+#define SP_AUD_INTERFACE_CTRL2_REG	0x60
+#define SP_M_AUD_ADJUST_ST		0x04
+
+/* Audio Interface Control Register 3 */
+#define SP_AUD_INTERFACE_CTRL3_REG	0x62
+
+/* Audio Interface Control Register 4 */
+#define SP_AUD_INTERFACE_CTRL4_REG	0x67
+
+/* Audio Interface Control Register 5 */
+#define SP_AUD_INTERFACE_CTRL5_REG	0x68
+
+/* Audio Interface Control Register 6 */
+#define SP_AUD_INTERFACE_CTRL6_REG	0x69
+
+/* Firmware Version Register */
+#define SP_FW_VER_REG			0xb7
+
+#endif
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.c b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.c
new file mode 100644
index 000000000000..fe40bab21530
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.c
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor.
+ *
+ * Based on anx7808 driver obtained from chromeos with copyright:
+ * Copyright(c) 2013, Google Inc.
+ */
+#include <linux/regmap.h>
+
+#include <drm/drm.h>
+#include <drm/drm_dp_helper.h>
+#include <drm/drm_print.h>
+
+#include "analogix-i2c-dptx.h"
+
+#define AUX_WAIT_TIMEOUT_MS	15
+#define AUX_CH_BUFFER_SIZE	16
+
+static int anx_i2c_dp_clear_bits(struct regmap *map, u8 reg, u8 mask)
+{
+	return regmap_update_bits(map, reg, mask, 0);
+}
+
+static bool anx_dp_aux_op_finished(struct regmap *map_dptx)
+{
+	unsigned int value;
+	int err;
+
+	err = regmap_read(map_dptx, SP_DP_AUX_CH_CTRL2_REG, &value);
+	if (err < 0)
+		return false;
+
+	return (value & SP_AUX_EN) == 0;
+}
+
+static int anx_dp_aux_wait(struct regmap *map_dptx)
+{
+	unsigned long timeout;
+	unsigned int status;
+	int err;
+
+	timeout = jiffies + msecs_to_jiffies(AUX_WAIT_TIMEOUT_MS) + 1;
+
+	while (!anx_dp_aux_op_finished(map_dptx)) {
+		if (time_after(jiffies, timeout)) {
+			if (!anx_dp_aux_op_finished(map_dptx)) {
+				DRM_ERROR("Timed out waiting AUX to finish\n");
+				return -ETIMEDOUT;
+			}
+
+			break;
+		}
+
+		usleep_range(1000, 2000);
+	}
+
+	/* Read the AUX channel access status */
+	err = regmap_read(map_dptx, SP_AUX_CH_STATUS_REG, &status);
+	if (err < 0) {
+		DRM_ERROR("Failed to read from AUX channel: %d\n", err);
+		return err;
+	}
+
+	if (status & SP_AUX_STATUS) {
+		DRM_ERROR("Failed to wait for AUX channel (status: %02x)\n",
+			  status);
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int anx_dp_aux_address(struct regmap *map_dptx, unsigned int addr)
+{
+	int err;
+
+	err = regmap_write(map_dptx, SP_AUX_ADDR_7_0_REG, addr & 0xff);
+	if (err)
+		return err;
+
+	err = regmap_write(map_dptx, SP_AUX_ADDR_15_8_REG,
+			   (addr & 0xff00) >> 8);
+	if (err)
+		return err;
+
+	/*
+	 * DP AUX CH Address Register #2, only update bits[3:0]
+	 * [7:4] RESERVED
+	 * [3:0] AUX_ADDR[19:16], Register control AUX CH address.
+	 */
+	err = regmap_update_bits(map_dptx, SP_AUX_ADDR_19_16_REG,
+				 SP_AUX_ADDR_19_16_MASK,
+				 (addr & 0xf0000) >> 16);
+
+	if (err)
+		return err;
+
+	return 0;
+}
+
+ssize_t anx_dp_aux_transfer(struct regmap *map_dptx,
+				struct drm_dp_aux_msg *msg)
+{
+	u8 ctrl1 = msg->request;
+	u8 ctrl2 = SP_AUX_EN;
+	u8 *buffer = msg->buffer;
+	int err;
+
+	/* The DP AUX transmit and receive buffer has 16 bytes. */
+	if (WARN_ON(msg->size > AUX_CH_BUFFER_SIZE))
+		return -E2BIG;
+
+	/* Zero-sized messages specify address-only transactions. */
+	if (msg->size < 1)
+		ctrl2 |= SP_ADDR_ONLY;
+	else	/* For non-zero-sized set the length field. */
+		ctrl1 |= (msg->size - 1) << SP_AUX_LENGTH_SHIFT;
+
+	if ((msg->size > 0) && ((msg->request & DP_AUX_I2C_READ) == 0)) {
+		/* When WRITE | MOT write values to data buffer */
+		err = regmap_bulk_write(map_dptx,
+					SP_DP_BUF_DATA0_REG, buffer,
+					msg->size);
+		if (err)
+			return err;
+	}
+
+	/* Write address and request */
+	err = anx_dp_aux_address(map_dptx, msg->address);
+	if (err)
+		return err;
+
+	err = regmap_write(map_dptx, SP_DP_AUX_CH_CTRL1_REG, ctrl1);
+	if (err)
+		return err;
+
+	/* Start transaction */
+	err = regmap_update_bits(map_dptx, SP_DP_AUX_CH_CTRL2_REG,
+				 SP_ADDR_ONLY | SP_AUX_EN, ctrl2);
+	if (err)
+		return err;
+
+	err = anx_dp_aux_wait(map_dptx);
+	if (err)
+		return err;
+
+	msg->reply = DP_AUX_I2C_REPLY_ACK;
+
+	if ((msg->size > 0) && (msg->request & DP_AUX_I2C_READ)) {
+		/* Read values from data buffer */
+		err = regmap_bulk_read(map_dptx,
+				       SP_DP_BUF_DATA0_REG, buffer,
+				       msg->size);
+		if (err)
+			return err;
+	}
+
+	err = anx_i2c_dp_clear_bits(map_dptx, SP_DP_AUX_CH_CTRL2_REG,
+				    SP_ADDR_ONLY);
+	if (err)
+		return err;
+
+	return msg->size;
+}
+EXPORT_SYMBOL_GPL(anx_dp_aux_transfer);
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.h b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.h
new file mode 100644
index 000000000000..663c4bea6e70
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-i2c-dptx.h
@@ -0,0 +1,256 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor.
+ *
+ * Based on anx7808 driver obtained from chromeos with copyright:
+ * Copyright(c) 2013, Google Inc.
+ */
+#ifndef _ANALOGIX_I2C_DPTX_H_
+#define _ANALOGIX_I2C_DPTX_H_
+
+/***************************************************************/
+/* Register definitions for TX_P0                              */
+/***************************************************************/
+
+/* HDCP Status Register */
+#define SP_TX_HDCP_STATUS_REG		0x00
+#define SP_AUTH_FAIL			BIT(5)
+#define SP_AUTHEN_PASS			BIT(1)
+
+/* HDCP Control Register 0 */
+#define SP_HDCP_CTRL0_REG		0x01
+#define SP_RX_REPEATER			BIT(6)
+#define SP_RE_AUTH			BIT(5)
+#define SP_SW_AUTH_OK			BIT(4)
+#define SP_HARD_AUTH_EN			BIT(3)
+#define SP_HDCP_ENC_EN			BIT(2)
+#define SP_BKSV_SRM_PASS		BIT(1)
+#define SP_KSVLIST_VLD			BIT(0)
+/* HDCP Function Enabled */
+#define SP_HDCP_FUNCTION_ENABLED	(BIT(0) | BIT(1) | BIT(2) | BIT(3))
+
+/* HDCP Receiver BSTATUS Register 0 */
+#define	SP_HDCP_RX_BSTATUS0_REG		0x1b
+/* HDCP Receiver BSTATUS Register 1 */
+#define	SP_HDCP_RX_BSTATUS1_REG		0x1c
+
+/* HDCP Embedded "Blue Screen" Content Registers */
+#define SP_HDCP_VID0_BLUE_SCREEN_REG	0x2c
+#define SP_HDCP_VID1_BLUE_SCREEN_REG	0x2d
+#define SP_HDCP_VID2_BLUE_SCREEN_REG	0x2e
+
+/* HDCP Wait R0 Timing Register */
+#define SP_HDCP_WAIT_R0_TIME_REG	0x40
+
+/* HDCP Link Integrity Check Timer Register */
+#define SP_HDCP_LINK_CHECK_TIMER_REG	0x41
+
+/* HDCP Repeater Ready Wait Timer Register */
+#define SP_HDCP_RPTR_RDY_WAIT_TIME_REG	0x42
+
+/* HDCP Auto Timer Register */
+#define SP_HDCP_AUTO_TIMER_REG		0x51
+
+/* HDCP Key Status Register */
+#define SP_HDCP_KEY_STATUS_REG		0x5e
+
+/* HDCP Key Command Register */
+#define SP_HDCP_KEY_COMMAND_REG		0x5f
+#define SP_DISABLE_SYNC_HDCP		BIT(2)
+
+/* OTP Memory Key Protection Registers */
+#define SP_OTP_KEY_PROTECT1_REG		0x60
+#define SP_OTP_KEY_PROTECT2_REG		0x61
+#define SP_OTP_KEY_PROTECT3_REG		0x62
+#define SP_OTP_PSW1			0xa2
+#define SP_OTP_PSW2			0x7e
+#define SP_OTP_PSW3			0xc6
+
+/* DP System Control Registers */
+#define SP_DP_SYSTEM_CTRL_BASE		(0x80 - 1)
+/* Bits for DP System Control Register 2 */
+#define SP_CHA_STA			BIT(2)
+/* Bits for DP System Control Register 3 */
+#define SP_HPD_STATUS			BIT(6)
+#define SP_HPD_FORCE			BIT(5)
+#define SP_HPD_CTRL			BIT(4)
+#define SP_STRM_VALID			BIT(2)
+#define SP_STRM_FORCE			BIT(1)
+#define SP_STRM_CTRL			BIT(0)
+/* Bits for DP System Control Register 4 */
+#define SP_ENHANCED_MODE		BIT(3)
+
+/* DP Video Control Register */
+#define SP_DP_VIDEO_CTRL_REG		0x84
+#define SP_COLOR_F_MASK			0x06
+#define SP_COLOR_F_SHIFT		1
+#define SP_BPC_MASK			0xe0
+#define SP_BPC_SHIFT			5
+#  define SP_BPC_6BITS			0x00
+#  define SP_BPC_8BITS			0x01
+#  define SP_BPC_10BITS			0x02
+#  define SP_BPC_12BITS			0x03
+
+/* DP Audio Control Register */
+#define SP_DP_AUDIO_CTRL_REG		0x87
+#define SP_AUD_EN			BIT(0)
+
+/* 10us Pulse Generate Timer Registers */
+#define SP_I2C_GEN_10US_TIMER0_REG	0x88
+#define SP_I2C_GEN_10US_TIMER1_REG	0x89
+
+/* Packet Send Control Register */
+#define SP_PACKET_SEND_CTRL_REG		0x90
+#define SP_AUD_IF_UP			BIT(7)
+#define SP_AVI_IF_UD			BIT(6)
+#define SP_MPEG_IF_UD			BIT(5)
+#define SP_SPD_IF_UD			BIT(4)
+#define SP_AUD_IF_EN			BIT(3)
+#define SP_AVI_IF_EN			BIT(2)
+#define SP_MPEG_IF_EN			BIT(1)
+#define SP_SPD_IF_EN			BIT(0)
+
+/* DP HDCP Control Register */
+#define SP_DP_HDCP_CTRL_REG		0x92
+#define SP_AUTO_EN			BIT(7)
+#define SP_AUTO_START			BIT(5)
+#define SP_LINK_POLLING			BIT(1)
+
+/* DP Main Link Bandwidth Setting Register */
+#define SP_DP_MAIN_LINK_BW_SET_REG	0xa0
+#define SP_LINK_BW_SET_MASK		0x1f
+#define SP_INITIAL_SLIM_M_AUD_SEL	BIT(5)
+
+/* DP Lane Count Setting Register */
+#define SP_DP_LANE_COUNT_SET_REG	0xa1
+
+/* DP Training Pattern Set Register */
+#define SP_DP_TRAINING_PATTERN_SET_REG	0xa2
+
+/* DP Lane 0 Link Training Control Register */
+#define SP_DP_LANE0_LT_CTRL_REG		0xa3
+#define SP_TX_SW_SET_MASK		0x1b
+#define SP_MAX_PRE_REACH		BIT(5)
+#define SP_MAX_DRIVE_REACH		BIT(4)
+#define SP_PRE_EMP_LEVEL1		BIT(3)
+#define SP_DRVIE_CURRENT_LEVEL1		BIT(0)
+
+/* DP Link Training Control Register */
+#define SP_DP_LT_CTRL_REG		0xa8
+#define SP_DP_LT_INPROGRESS		0x80
+#define SP_LT_ERROR_TYPE_MASK		0x70
+#  define SP_LT_NO_ERROR		0x00
+#  define SP_LT_AUX_WRITE_ERROR		0x01
+#  define SP_LT_MAX_DRIVE_REACHED	0x02
+#  define SP_LT_WRONG_LANE_COUNT_SET	0x03
+#  define SP_LT_LOOP_SAME_5_TIME	0x04
+#  define SP_LT_CR_FAIL_IN_EQ		0x05
+#  define SP_LT_EQ_LOOP_5_TIME		0x06
+#define SP_LT_EN			BIT(0)
+
+/* DP CEP Training Control Registers */
+#define SP_DP_CEP_TRAINING_CTRL0_REG	0xa9
+#define SP_DP_CEP_TRAINING_CTRL1_REG	0xaa
+
+/* DP Debug Register 1 */
+#define SP_DP_DEBUG1_REG		0xb0
+#define SP_DEBUG_PLL_LOCK		BIT(4)
+#define SP_POLLING_EN			BIT(1)
+
+/* DP Polling Control Register */
+#define SP_DP_POLLING_CTRL_REG		0xb4
+#define SP_AUTO_POLLING_DISABLE		BIT(0)
+
+/* DP Link Debug Control Register */
+#define SP_DP_LINK_DEBUG_CTRL_REG	0xb8
+#define SP_M_VID_DEBUG			BIT(5)
+#define SP_NEW_PRBS7			BIT(4)
+#define SP_INSERT_ER			BIT(1)
+#define SP_PRBS31_EN			BIT(0)
+
+/* AUX Misc control Register */
+#define SP_AUX_MISC_CTRL_REG		0xbf
+
+/* DP PLL control Register */
+#define SP_DP_PLL_CTRL_REG		0xc7
+#define SP_PLL_RST			BIT(6)
+
+/* DP Analog Power Down Register */
+#define SP_DP_ANALOG_POWER_DOWN_REG	0xc8
+#define SP_CH0_PD			BIT(0)
+
+/* DP Misc Control Register */
+#define SP_DP_MISC_CTRL_REG		0xcd
+#define SP_EQ_TRAINING_LOOP		BIT(6)
+
+/* DP Extra I2C Device Address Register */
+#define SP_DP_EXTRA_I2C_DEV_ADDR_REG	0xce
+#define SP_I2C_STRETCH_DISABLE		BIT(7)
+
+#define SP_I2C_EXTRA_ADDR		0x50
+
+/* DP Downspread Control Register 1 */
+#define SP_DP_DOWNSPREAD_CTRL1_REG	0xd0
+
+/* DP M Value Calculation Control Register */
+#define SP_DP_M_CALCULATION_CTRL_REG	0xd9
+#define SP_M_GEN_CLK_SEL		BIT(0)
+
+/* AUX Channel Access Status Register */
+#define SP_AUX_CH_STATUS_REG		0xe0
+#define SP_AUX_STATUS			0x0f
+
+/* AUX Channel DEFER Control Register */
+#define SP_AUX_DEFER_CTRL_REG		0xe2
+#define SP_DEFER_CTRL_EN		BIT(7)
+
+/* DP Buffer Data Count Register */
+#define SP_BUF_DATA_COUNT_REG		0xe4
+#define SP_BUF_DATA_COUNT_MASK		0x1f
+#define SP_BUF_CLR			BIT(7)
+
+/* DP AUX Channel Control Register 1 */
+#define SP_DP_AUX_CH_CTRL1_REG		0xe5
+#define SP_AUX_TX_COMM_MASK		0x0f
+#define SP_AUX_LENGTH_MASK		0xf0
+#define SP_AUX_LENGTH_SHIFT		4
+
+/* DP AUX CH Address Register 0 */
+#define SP_AUX_ADDR_7_0_REG		0xe6
+
+/* DP AUX CH Address Register 1 */
+#define SP_AUX_ADDR_15_8_REG		0xe7
+
+/* DP AUX CH Address Register 2 */
+#define SP_AUX_ADDR_19_16_REG		0xe8
+#define SP_AUX_ADDR_19_16_MASK		0x0f
+
+/* DP AUX Channel Control Register 2 */
+#define SP_DP_AUX_CH_CTRL2_REG		0xe9
+#define SP_AUX_SEL_RXCM			BIT(6)
+#define SP_AUX_CHSEL			BIT(3)
+#define SP_AUX_PN_INV			BIT(2)
+#define SP_ADDR_ONLY			BIT(1)
+#define SP_AUX_EN			BIT(0)
+
+/* DP Video Stream Control InfoFrame Register */
+#define SP_DP_3D_VSC_CTRL_REG		0xea
+#define SP_INFO_FRAME_VSC_EN		BIT(0)
+
+/* DP Video Stream Data Byte 1 Register */
+#define SP_DP_VSC_DB1_REG		0xeb
+
+/* DP AUX Channel Control Register 3 */
+#define SP_DP_AUX_CH_CTRL3_REG		0xec
+#define SP_WAIT_COUNTER_7_0_MASK	0xff
+
+/* DP AUX Channel Control Register 4 */
+#define SP_DP_AUX_CH_CTRL4_REG		0xed
+
+/* DP AUX Buffer Data Registers */
+#define SP_DP_BUF_DATA0_REG		0xf0
+
+ssize_t anx_dp_aux_transfer(struct regmap *map_dptx,
+				struct drm_dp_aux_msg *msg);
+
+#endif
diff --git a/drivers/gpu/drm/bridge/analogix/analogix-i2c-txcommon.h b/drivers/gpu/drm/bridge/analogix/analogix-i2c-txcommon.h
new file mode 100644
index 000000000000..3c843497d835
--- /dev/null
+++ b/drivers/gpu/drm/bridge/analogix/analogix-i2c-txcommon.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016, Analogix Semiconductor. All rights reserved.
+ */
+#ifndef _ANALOGIX_I2C_TXCOMMON_H_
+#define _ANALOGIX_I2C_TXCOMMON_H_
+
+/***************************************************************/
+/* Register definitions for TX_P2                              */
+/***************************************************************/
+
+/*
+ * Core Register Definitions
+ */
+
+/* Device ID Low Byte Register */
+#define SP_DEVICE_IDL_REG		0x02
+
+/* Device ID High Byte Register */
+#define SP_DEVICE_IDH_REG		0x03
+
+/* Device version register */
+#define SP_DEVICE_VERSION_REG		0x04
+
+/* Power Down Control Register */
+#define SP_POWERDOWN_CTRL_REG		0x05
+#define SP_REGISTER_PD			BIT(7)
+#define SP_HDCP_PD			BIT(5)
+#define SP_AUDIO_PD			BIT(4)
+#define SP_VIDEO_PD			BIT(3)
+#define SP_LINK_PD			BIT(2)
+#define SP_TOTAL_PD			BIT(1)
+
+/* Reset Control Register 1 */
+#define SP_RESET_CTRL1_REG		0x06
+#define SP_MISC_RST			BIT(7)
+#define SP_VIDCAP_RST			BIT(6)
+#define SP_VIDFIF_RST			BIT(5)
+#define SP_AUDFIF_RST			BIT(4)
+#define SP_AUDCAP_RST			BIT(3)
+#define SP_HDCP_RST			BIT(2)
+#define SP_SW_RST			BIT(1)
+#define SP_HW_RST			BIT(0)
+
+/* Reset Control Register 2 */
+#define SP_RESET_CTRL2_REG		0x07
+#define SP_AUX_RST			BIT(2)
+#define SP_SERDES_FIFO_RST		BIT(1)
+#define SP_I2C_REG_RST			BIT(0)
+
+/* Video Control Register 1 */
+#define SP_VID_CTRL1_REG		0x08
+#define SP_VIDEO_EN			BIT(7)
+#define SP_VIDEO_MUTE			BIT(2)
+#define SP_DE_GEN			BIT(1)
+#define SP_DEMUX			BIT(0)
+
+/* Video Control Register 2 */
+#define SP_VID_CTRL2_REG		0x09
+#define SP_IN_COLOR_F_MASK		0x03
+#define SP_IN_YC_BIT_SEL		BIT(2)
+#define SP_IN_BPC_MASK			0x70
+#define SP_IN_BPC_SHIFT			4
+#  define SP_IN_BPC_12BIT		0x03
+#  define SP_IN_BPC_10BIT		0x02
+#  define SP_IN_BPC_8BIT		0x01
+#  define SP_IN_BPC_6BIT		0x00
+#define SP_IN_D_RANGE			BIT(7)
+
+/* Video Control Register 3 */
+#define SP_VID_CTRL3_REG		0x0a
+#define SP_HPD_OUT			BIT(6)
+
+/* Video Control Register 5 */
+#define SP_VID_CTRL5_REG		0x0c
+#define SP_CSC_STD_SEL			BIT(7)
+#define SP_XVYCC_RNG_LMT		BIT(6)
+#define SP_RANGE_Y2R			BIT(5)
+#define SP_CSPACE_Y2R			BIT(4)
+#define SP_RGB_RNG_LMT			BIT(3)
+#define SP_Y_RNG_LMT			BIT(2)
+#define SP_RANGE_R2Y			BIT(1)
+#define SP_CSPACE_R2Y			BIT(0)
+
+/* Video Control Register 6 */
+#define SP_VID_CTRL6_REG		0x0d
+#define SP_TEST_PATTERN_EN		BIT(7)
+#define SP_VIDEO_PROCESS_EN		BIT(6)
+#define SP_VID_US_MODE			BIT(3)
+#define SP_VID_DS_MODE			BIT(2)
+#define SP_UP_SAMPLE			BIT(1)
+#define SP_DOWN_SAMPLE			BIT(0)
+
+/* Video Control Register 8 */
+#define SP_VID_CTRL8_REG		0x0f
+#define SP_VID_VRES_TH			BIT(0)
+
+/* Total Line Status Low Byte Register */
+#define SP_TOTAL_LINE_STAL_REG		0x24
+
+/* Total Line Status High Byte Register */
+#define SP_TOTAL_LINE_STAH_REG		0x25
+
+/* Active Line Status Low Byte Register */
+#define SP_ACT_LINE_STAL_REG		0x26
+
+/* Active Line Status High Byte Register */
+#define SP_ACT_LINE_STAH_REG		0x27
+
+/* Vertical Front Porch Status Register */
+#define SP_V_F_PORCH_STA_REG		0x28
+
+/* Vertical SYNC Width Status Register */
+#define SP_V_SYNC_STA_REG		0x29
+
+/* Vertical Back Porch Status Register */
+#define SP_V_B_PORCH_STA_REG		0x2a
+
+/* Total Pixel Status Low Byte Register */
+#define SP_TOTAL_PIXEL_STAL_REG		0x2b
+
+/* Total Pixel Status High Byte Register */
+#define SP_TOTAL_PIXEL_STAH_REG		0x2c
+
+/* Active Pixel Status Low Byte Register */
+#define SP_ACT_PIXEL_STAL_REG		0x2d
+
+/* Active Pixel Status High Byte Register */
+#define SP_ACT_PIXEL_STAH_REG		0x2e
+
+/* Horizontal Front Porch Status Low Byte Register */
+#define SP_H_F_PORCH_STAL_REG		0x2f
+
+/* Horizontal Front Porch Statys High Byte Register */
+#define SP_H_F_PORCH_STAH_REG		0x30
+
+/* Horizontal SYNC Width Status Low Byte Register */
+#define SP_H_SYNC_STAL_REG		0x31
+
+/* Horizontal SYNC Width Status High Byte Register */
+#define SP_H_SYNC_STAH_REG		0x32
+
+/* Horizontal Back Porch Status Low Byte Register */
+#define SP_H_B_PORCH_STAL_REG		0x33
+
+/* Horizontal Back Porch Status High Byte Register */
+#define SP_H_B_PORCH_STAH_REG		0x34
+
+/* InfoFrame AVI Packet DB1 Register */
+#define SP_INFOFRAME_AVI_DB1_REG	0x70
+
+/* Bit Control Specific Register */
+#define SP_BIT_CTRL_SPECIFIC_REG	0x80
+#define SP_BIT_CTRL_SELECT_SHIFT	1
+#define SP_ENABLE_BIT_CTRL		BIT(0)
+
+/* InfoFrame Audio Packet DB1 Register */
+#define SP_INFOFRAME_AUD_DB1_REG	0x83
+
+/* InfoFrame MPEG Packet DB1 Register */
+#define SP_INFOFRAME_MPEG_DB1_REG	0xb0
+
+/* Audio Channel Status Registers */
+#define SP_AUD_CH_STATUS_BASE		0xd0
+
+/* Audio Channel Num Register 5 */
+#define SP_I2S_CHANNEL_NUM_MASK		0xe0
+#  define SP_I2S_CH_NUM_1		(0x00 << 5)
+#  define SP_I2S_CH_NUM_2		(0x01 << 5)
+#  define SP_I2S_CH_NUM_3		(0x02 << 5)
+#  define SP_I2S_CH_NUM_4		(0x03 << 5)
+#  define SP_I2S_CH_NUM_5		(0x04 << 5)
+#  define SP_I2S_CH_NUM_6		(0x05 << 5)
+#  define SP_I2S_CH_NUM_7		(0x06 << 5)
+#  define SP_I2S_CH_NUM_8		(0x07 << 5)
+#define SP_EXT_VUCP			BIT(2)
+#define SP_VBIT				BIT(1)
+#define SP_AUDIO_LAYOUT			BIT(0)
+
+/* Analog Debug Register 1 */
+#define SP_ANALOG_DEBUG1_REG		0xdc
+
+/* Analog Debug Register 2 */
+#define SP_ANALOG_DEBUG2_REG		0xdd
+#define SP_FORCE_SW_OFF_BYPASS		0x20
+#define SP_XTAL_FRQ			0x1c
+#  define SP_XTAL_FRQ_19M2		(0x00 << 2)
+#  define SP_XTAL_FRQ_24M		(0x01 << 2)
+#  define SP_XTAL_FRQ_25M		(0x02 << 2)
+#  define SP_XTAL_FRQ_26M		(0x03 << 2)
+#  define SP_XTAL_FRQ_27M		(0x04 << 2)
+#  define SP_XTAL_FRQ_38M4		(0x05 << 2)
+#  define SP_XTAL_FRQ_52M		(0x06 << 2)
+#define SP_POWERON_TIME_1P5MS		0x03
+
+/* Analog Control 0 Register */
+#define SP_ANALOG_CTRL0_REG		0xe1
+
+/* Common Interrupt Status Register 1 */
+#define SP_COMMON_INT_STATUS_BASE	(0xf1 - 1)
+#define SP_PLL_LOCK_CHG			0x40
+
+/* Common Interrupt Status Register 2 */
+#define SP_COMMON_INT_STATUS2		0xf2
+#define SP_HDCP_AUTH_CHG		BIT(1)
+#define SP_HDCP_AUTH_DONE		BIT(0)
+
+#define SP_HDCP_LINK_CHECK_FAIL		BIT(0)
+
+/* Common Interrupt Status Register 4 */
+#define SP_COMMON_INT_STATUS4_REG	0xf4
+#define SP_HPD_IRQ			BIT(6)
+#define SP_HPD_ESYNC_ERR		BIT(4)
+#define SP_HPD_CHG			BIT(2)
+#define SP_HPD_LOST			BIT(1)
+#define SP_HPD_PLUG			BIT(0)
+
+/* DP Interrupt Status Register */
+#define SP_DP_INT_STATUS1_REG		0xf7
+#define SP_TRAINING_FINISH		BIT(5)
+#define SP_POLLING_ERR			BIT(4)
+
+/* Common Interrupt Mask Register */
+#define SP_COMMON_INT_MASK_BASE		(0xf8 - 1)
+
+#define SP_COMMON_INT_MASK4_REG		0xfb
+
+/* DP Interrupts Mask Register */
+#define SP_DP_INT_MASK1_REG		0xfe
+
+/* Interrupt Control Register */
+#define SP_INT_CTRL_REG			0xff
+
+#endif /* _ANALOGIX_I2C_TXCOMMON_H_ */
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index bb411fe52ae8..6effe532f820 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1111,7 +1111,7 @@ static int analogix_dp_get_modes(struct drm_connector *connector)
 	int ret, num_modes = 0;
 
 	if (dp->plat_data->panel) {
-		num_modes += drm_panel_get_modes(dp->plat_data->panel);
+		num_modes += drm_panel_get_modes(dp->plat_data->panel, connector);
 	} else {
 		ret = analogix_dp_prepare_panel(dp, true, false);
 		if (ret) {
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index 3a5bd4e7fd1e..b7c97f060241 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -512,7 +512,7 @@ static int cdns_dsi_mode2cfg(struct cdns_dsi *dsi,
 	struct cdns_dsi_output *output = &dsi->output;
 	unsigned int tmp;
 	bool sync_pulse = false;
-	int bpp, nlanes;
+	int bpp;
 
 	memset(dsi_cfg, 0, sizeof(*dsi_cfg));
 
@@ -520,7 +520,6 @@ static int cdns_dsi_mode2cfg(struct cdns_dsi *dsi,
 		sync_pulse = true;
 
 	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
-	nlanes = output->dev->lanes;
 
 	if (mode_valid_check)
 		tmp = mode->htotal -
@@ -785,13 +784,12 @@ static void cdns_dsi_bridge_enable(struct drm_bridge *bridge)
 	unsigned long tx_byte_period;
 	struct cdns_dsi_cfg dsi_cfg;
 	u32 tmp, reg_wakeup, div;
-	int bpp, nlanes;
+	int nlanes;
 
 	if (WARN_ON(pm_runtime_get_sync(dsi->base.dev) < 0))
 		return;
 
 	mode = &bridge->encoder->crtc->state->adjusted_mode;
-	bpp = mipi_dsi_pixel_format_to_bpp(output->dev->format);
 	nlanes = output->dev->lanes;
 
 	WARN_ON_ONCE(cdns_dsi_check_conf(dsi, mode, &dsi_cfg, false));
diff --git a/drivers/gpu/drm/bridge/lvds-codec.c b/drivers/gpu/drm/bridge/lvds-codec.c
new file mode 100644
index 000000000000..5f04cc11227e
--- /dev/null
+++ b/drivers/gpu/drm/bridge/lvds-codec.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2019 Renesas Electronics Corporation
+ * Copyright (C) 2016 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+
+#include <drm/drm_bridge.h>
+#include <drm/drm_panel.h>
+
+struct lvds_codec {
+	struct drm_bridge bridge;
+	struct drm_bridge *panel_bridge;
+	struct gpio_desc *powerdown_gpio;
+	u32 connector_type;
+};
+
+static int lvds_codec_attach(struct drm_bridge *bridge)
+{
+	struct lvds_codec *lvds_codec = container_of(bridge,
+						     struct lvds_codec, bridge);
+
+	return drm_bridge_attach(bridge->encoder, lvds_codec->panel_bridge,
+				 bridge);
+}
+
+static void lvds_codec_enable(struct drm_bridge *bridge)
+{
+	struct lvds_codec *lvds_codec = container_of(bridge,
+						     struct lvds_codec, bridge);
+
+	if (lvds_codec->powerdown_gpio)
+		gpiod_set_value_cansleep(lvds_codec->powerdown_gpio, 0);
+}
+
+static void lvds_codec_disable(struct drm_bridge *bridge)
+{
+	struct lvds_codec *lvds_codec = container_of(bridge,
+						     struct lvds_codec, bridge);
+
+	if (lvds_codec->powerdown_gpio)
+		gpiod_set_value_cansleep(lvds_codec->powerdown_gpio, 1);
+}
+
+static struct drm_bridge_funcs funcs = {
+	.attach = lvds_codec_attach,
+	.enable = lvds_codec_enable,
+	.disable = lvds_codec_disable,
+};
+
+static int lvds_codec_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *panel_node;
+	struct drm_panel *panel;
+	struct lvds_codec *lvds_codec;
+
+	lvds_codec = devm_kzalloc(dev, sizeof(*lvds_codec), GFP_KERNEL);
+	if (!lvds_codec)
+		return -ENOMEM;
+
+	lvds_codec->connector_type = (uintptr_t)of_device_get_match_data(dev);
+	lvds_codec->powerdown_gpio = devm_gpiod_get_optional(dev, "powerdown",
+							     GPIOD_OUT_HIGH);
+	if (IS_ERR(lvds_codec->powerdown_gpio)) {
+		int err = PTR_ERR(lvds_codec->powerdown_gpio);
+
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "powerdown GPIO failure: %d\n", err);
+		return err;
+	}
+
+	/* Locate the panel DT node. */
+	panel_node = of_graph_get_remote_node(dev->of_node, 1, 0);
+	if (!panel_node) {
+		dev_dbg(dev, "panel DT node not found\n");
+		return -ENXIO;
+	}
+
+	panel = of_drm_find_panel(panel_node);
+	of_node_put(panel_node);
+	if (IS_ERR(panel)) {
+		dev_dbg(dev, "panel not found, deferring probe\n");
+		return PTR_ERR(panel);
+	}
+
+	lvds_codec->panel_bridge =
+		devm_drm_panel_bridge_add_typed(dev, panel,
+						lvds_codec->connector_type);
+	if (IS_ERR(lvds_codec->panel_bridge))
+		return PTR_ERR(lvds_codec->panel_bridge);
+
+	/*
+	 * The panel_bridge bridge is attached to the panel's of_node,
+	 * but we need a bridge attached to our of_node for our user
+	 * to look up.
+	 */
+	lvds_codec->bridge.of_node = dev->of_node;
+	lvds_codec->bridge.funcs = &funcs;
+	drm_bridge_add(&lvds_codec->bridge);
+
+	platform_set_drvdata(pdev, lvds_codec);
+
+	return 0;
+}
+
+static int lvds_codec_remove(struct platform_device *pdev)
+{
+	struct lvds_codec *lvds_codec = platform_get_drvdata(pdev);
+
+	drm_bridge_remove(&lvds_codec->bridge);
+
+	return 0;
+}
+
+static const struct of_device_id lvds_codec_match[] = {
+	{
+		.compatible = "lvds-decoder",
+		.data = (void *)DRM_MODE_CONNECTOR_DPI,
+	},
+	{
+		.compatible = "lvds-encoder",
+		.data = (void *)DRM_MODE_CONNECTOR_LVDS,
+	},
+	{
+		.compatible = "thine,thc63lvdm83d",
+		.data = (void *)DRM_MODE_CONNECTOR_LVDS,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, lvds_codec_match);
+
+static struct platform_driver lvds_codec_driver = {
+	.probe	= lvds_codec_probe,
+	.remove	= lvds_codec_remove,
+	.driver		= {
+		.name		= "lvds-codec",
+		.of_match_table	= lvds_codec_match,
+	},
+};
+module_platform_driver(lvds_codec_driver);
+
+MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
+MODULE_DESCRIPTION("LVDS encoders and decoders");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/bridge/lvds-encoder.c b/drivers/gpu/drm/bridge/lvds-encoder.c
deleted file mode 100644
index e2132a8d5106..000000000000
--- a/drivers/gpu/drm/bridge/lvds-encoder.c
+++ /dev/null
@@ -1,155 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2016 Laurent Pinchart <laurent.pinchart@ideasonboard.com>
- */
-
-#include <linux/gpio/consumer.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_graph.h>
-#include <linux/platform_device.h>
-
-#include <drm/drm_bridge.h>
-#include <drm/drm_panel.h>
-
-struct lvds_encoder {
-	struct drm_bridge bridge;
-	struct drm_bridge *panel_bridge;
-	struct gpio_desc *powerdown_gpio;
-};
-
-static int lvds_encoder_attach(struct drm_bridge *bridge)
-{
-	struct lvds_encoder *lvds_encoder = container_of(bridge,
-							 struct lvds_encoder,
-							 bridge);
-
-	return drm_bridge_attach(bridge->encoder, lvds_encoder->panel_bridge,
-				 bridge);
-}
-
-static void lvds_encoder_enable(struct drm_bridge *bridge)
-{
-	struct lvds_encoder *lvds_encoder = container_of(bridge,
-							 struct lvds_encoder,
-							 bridge);
-
-	if (lvds_encoder->powerdown_gpio)
-		gpiod_set_value_cansleep(lvds_encoder->powerdown_gpio, 0);
-}
-
-static void lvds_encoder_disable(struct drm_bridge *bridge)
-{
-	struct lvds_encoder *lvds_encoder = container_of(bridge,
-							 struct lvds_encoder,
-							 bridge);
-
-	if (lvds_encoder->powerdown_gpio)
-		gpiod_set_value_cansleep(lvds_encoder->powerdown_gpio, 1);
-}
-
-static struct drm_bridge_funcs funcs = {
-	.attach = lvds_encoder_attach,
-	.enable = lvds_encoder_enable,
-	.disable = lvds_encoder_disable,
-};
-
-static int lvds_encoder_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct device_node *port;
-	struct device_node *endpoint;
-	struct device_node *panel_node;
-	struct drm_panel *panel;
-	struct lvds_encoder *lvds_encoder;
-
-	lvds_encoder = devm_kzalloc(dev, sizeof(*lvds_encoder), GFP_KERNEL);
-	if (!lvds_encoder)
-		return -ENOMEM;
-
-	lvds_encoder->powerdown_gpio = devm_gpiod_get_optional(dev, "powerdown",
-							       GPIOD_OUT_HIGH);
-	if (IS_ERR(lvds_encoder->powerdown_gpio)) {
-		int err = PTR_ERR(lvds_encoder->powerdown_gpio);
-
-		if (err != -EPROBE_DEFER)
-			dev_err(dev, "powerdown GPIO failure: %d\n", err);
-		return err;
-	}
-
-	/* Locate the panel DT node. */
-	port = of_graph_get_port_by_id(dev->of_node, 1);
-	if (!port) {
-		dev_dbg(dev, "port 1 not found\n");
-		return -ENXIO;
-	}
-
-	endpoint = of_get_child_by_name(port, "endpoint");
-	of_node_put(port);
-	if (!endpoint) {
-		dev_dbg(dev, "no endpoint for port 1\n");
-		return -ENXIO;
-	}
-
-	panel_node = of_graph_get_remote_port_parent(endpoint);
-	of_node_put(endpoint);
-	if (!panel_node) {
-		dev_dbg(dev, "no remote endpoint for port 1\n");
-		return -ENXIO;
-	}
-
-	panel = of_drm_find_panel(panel_node);
-	of_node_put(panel_node);
-	if (IS_ERR(panel)) {
-		dev_dbg(dev, "panel not found, deferring probe\n");
-		return PTR_ERR(panel);
-	}
-
-	lvds_encoder->panel_bridge =
-		devm_drm_panel_bridge_add_typed(dev, panel,
-						DRM_MODE_CONNECTOR_LVDS);
-	if (IS_ERR(lvds_encoder->panel_bridge))
-		return PTR_ERR(lvds_encoder->panel_bridge);
-
-	/* The panel_bridge bridge is attached to the panel's of_node,
-	 * but we need a bridge attached to our of_node for our user
-	 * to look up.
-	 */
-	lvds_encoder->bridge.of_node = dev->of_node;
-	lvds_encoder->bridge.funcs = &funcs;
-	drm_bridge_add(&lvds_encoder->bridge);
-
-	platform_set_drvdata(pdev, lvds_encoder);
-
-	return 0;
-}
-
-static int lvds_encoder_remove(struct platform_device *pdev)
-{
-	struct lvds_encoder *lvds_encoder = platform_get_drvdata(pdev);
-
-	drm_bridge_remove(&lvds_encoder->bridge);
-
-	return 0;
-}
-
-static const struct of_device_id lvds_encoder_match[] = {
-	{ .compatible = "lvds-encoder" },
-	{ .compatible = "thine,thc63lvdm83d" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, lvds_encoder_match);
-
-static struct platform_driver lvds_encoder_driver = {
-	.probe	= lvds_encoder_probe,
-	.remove	= lvds_encoder_remove,
-	.driver		= {
-		.name		= "lvds-encoder",
-		.of_match_table	= lvds_encoder_match,
-	},
-};
-module_platform_driver(lvds_encoder_driver);
-
-MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
-MODULE_DESCRIPTION("Transparent parallel to LVDS encoder");
-MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index f4e293e7cf64..f66777e24968 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -37,7 +37,7 @@ static int panel_bridge_connector_get_modes(struct drm_connector *connector)
 	struct panel_bridge *panel_bridge =
 		drm_connector_to_panel_bridge(connector);
 
-	return drm_panel_get_modes(panel_bridge->panel);
+	return drm_panel_get_modes(panel_bridge->panel, connector);
 }
 
 static const struct drm_connector_helper_funcs
@@ -289,3 +289,21 @@ struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev,
 	return bridge;
 }
 EXPORT_SYMBOL(devm_drm_panel_bridge_add_typed);
+
+/**
+ * drm_panel_bridge_connector - return the connector for the panel bridge
+ *
+ * drm_panel_bridge creates the connector.
+ * This function gives external access to the connector.
+ *
+ * Returns: Pointer to drm_connector
+ */
+struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge)
+{
+	struct panel_bridge *panel_bridge;
+
+	panel_bridge = drm_bridge_to_panel_bridge(bridge);
+
+	return &panel_bridge->connector;
+}
+EXPORT_SYMBOL(drm_panel_bridge_connector);
diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c
index b7a72dfdcac3..10c47c008b40 100644
--- a/drivers/gpu/drm/bridge/parade-ps8622.c
+++ b/drivers/gpu/drm/bridge/parade-ps8622.c
@@ -461,7 +461,7 @@ static int ps8622_get_modes(struct drm_connector *connector)
 
 	ps8622 = connector_to_ps8622(connector);
 
-	return drm_panel_get_modes(ps8622->panel);
+	return drm_panel_get_modes(ps8622->panel, connector);
 }
 
 static const struct drm_connector_helper_funcs ps8622_connector_helper_funcs = {
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
index 2b7539701b42..dd56996fe9c7 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-ahb-audio.c
@@ -291,7 +291,7 @@ static irqreturn_t snd_dw_hdmi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static struct snd_pcm_hardware dw_hdmi_hw = {
+static const struct snd_pcm_hardware dw_hdmi_hw = {
 	.info = SNDRV_PCM_INFO_INTERLEAVED |
 		SNDRV_PCM_INFO_BLOCK_TRANSFER |
 		SNDRV_PCM_INFO_MMAP |
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index b6e793bb653c..b18351b6760a 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -719,7 +719,15 @@ static void dw_mipi_dsi_vertical_timing_config(struct dw_mipi_dsi *dsi,
 
 static void dw_mipi_dsi_dphy_timing_config(struct dw_mipi_dsi *dsi)
 {
+	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
+	struct dw_mipi_dsi_dphy_timing timing;
 	u32 hw_version;
+	int ret;
+
+	ret = phy_ops->get_timing(dsi->plat_data->priv_data,
+				  dsi->lane_mbps, &timing);
+	if (ret)
+		DRM_DEV_ERROR(dsi->dev, "Retrieving phy timings failed\n");
 
 	/*
 	 * TODO dw drv improvements
@@ -732,16 +740,20 @@ static void dw_mipi_dsi_dphy_timing_config(struct dw_mipi_dsi *dsi)
 	hw_version = dsi_read(dsi, DSI_VERSION) & VERSION;
 
 	if (hw_version >= HWVER_131) {
-		dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME_V131(0x40) |
-			  PHY_LP2HS_TIME_V131(0x40));
+		dsi_write(dsi, DSI_PHY_TMR_CFG,
+			  PHY_HS2LP_TIME_V131(timing.data_hs2lp) |
+			  PHY_LP2HS_TIME_V131(timing.data_lp2hs));
 		dsi_write(dsi, DSI_PHY_TMR_RD_CFG, MAX_RD_TIME_V131(10000));
 	} else {
-		dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME(0x40) |
-			  PHY_LP2HS_TIME(0x40) | MAX_RD_TIME(10000));
+		dsi_write(dsi, DSI_PHY_TMR_CFG,
+			  PHY_HS2LP_TIME(timing.data_hs2lp) |
+			  PHY_LP2HS_TIME(timing.data_lp2hs) |
+			  MAX_RD_TIME(10000));
 	}
 
-	dsi_write(dsi, DSI_PHY_TMR_LPCLK_CFG, PHY_CLKHS2LP_TIME(0x40)
-		  | PHY_CLKLP2HS_TIME(0x40));
+	dsi_write(dsi, DSI_PHY_TMR_LPCLK_CFG,
+		  PHY_CLKHS2LP_TIME(timing.clk_hs2lp) |
+		  PHY_CLKLP2HS_TIME(timing.clk_lp2hs));
 }
 
 static void dw_mipi_dsi_dphy_interface_config(struct dw_mipi_dsi *dsi)
@@ -798,9 +810,6 @@ static void dw_mipi_dsi_bridge_post_disable(struct drm_bridge *bridge)
 	struct dw_mipi_dsi *dsi = bridge_to_dsi(bridge);
 	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
 
-	if (phy_ops->power_off)
-		phy_ops->power_off(dsi->plat_data->priv_data);
-
 	/*
 	 * Switch to command mode before panel-bridge post_disable &
 	 * panel unprepare.
@@ -817,6 +826,9 @@ static void dw_mipi_dsi_bridge_post_disable(struct drm_bridge *bridge)
 	 */
 	dsi->panel_bridge->funcs->post_disable(dsi->panel_bridge);
 
+	if (phy_ops->power_off)
+		phy_ops->power_off(dsi->plat_data->priv_data);
+
 	if (dsi->slave) {
 		dw_mipi_dsi_disable(dsi->slave);
 		clk_disable_unprepare(dsi->slave->pclk);
@@ -883,6 +895,9 @@ static void dw_mipi_dsi_mode_set(struct dw_mipi_dsi *dsi,
 
 	/* Switch to cmd mode for panel-bridge pre_enable & panel prepare */
 	dw_mipi_dsi_set_mode(dsi, 0);
+
+	if (phy_ops->power_on)
+		phy_ops->power_on(dsi->plat_data->priv_data);
 }
 
 static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
@@ -899,15 +914,11 @@ static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
 static void dw_mipi_dsi_bridge_enable(struct drm_bridge *bridge)
 {
 	struct dw_mipi_dsi *dsi = bridge_to_dsi(bridge);
-	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
 
 	/* Switch to video mode for panel-bridge enable & panel enable */
 	dw_mipi_dsi_set_mode(dsi, MIPI_DSI_MODE_VIDEO);
 	if (dsi->slave)
 		dw_mipi_dsi_set_mode(dsi->slave, MIPI_DSI_MODE_VIDEO);
-
-	if (phy_ops->power_on)
-		phy_ops->power_on(dsi->plat_data->priv_data);
 }
 
 static enum drm_mode_status
@@ -991,7 +1002,8 @@ __dw_mipi_dsi_probe(struct platform_device *pdev,
 	dsi->dev = dev;
 	dsi->plat_data = plat_data;
 
-	if (!plat_data->phy_ops->init || !plat_data->phy_ops->get_lane_mbps) {
+	if (!plat_data->phy_ops->init || !plat_data->phy_ops->get_lane_mbps ||
+	    !plat_data->phy_ops->get_timing) {
 		DRM_ERROR("Phy not properly configured\n");
 		return ERR_PTR(-ENODEV);
 	}
diff --git a/drivers/gpu/drm/bridge/tc358764.c b/drivers/gpu/drm/bridge/tc358764.c
index db298f550a5a..96207fcfde19 100644
--- a/drivers/gpu/drm/bridge/tc358764.c
+++ b/drivers/gpu/drm/bridge/tc358764.c
@@ -282,7 +282,7 @@ static int tc358764_get_modes(struct drm_connector *connector)
 {
 	struct tc358764 *ctx = connector_to_tc358764(connector);
 
-	return drm_panel_get_modes(ctx->panel);
+	return drm_panel_get_modes(ctx->panel, connector);
 }
 
 static const
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 8029478ffebb..3709e5ace724 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1346,7 +1346,7 @@ static int tc_connector_get_modes(struct drm_connector *connector)
 		return 0;
 	}
 
-	count = drm_panel_get_modes(tc->panel);
+	count = drm_panel_get_modes(tc->panel, connector);
 	if (count > 0)
 		return count;
 
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 43abf01ebd4c..9a2dd986afa5 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -206,7 +206,7 @@ static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector)
 {
 	struct ti_sn_bridge *pdata = connector_to_ti_sn_bridge(connector);
 
-	return drm_panel_get_modes(pdata->panel);
+	return drm_panel_get_modes(pdata->panel, connector);
 }
 
 static enum drm_mode_status
diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index 6e09f27fd9d6..4c7ad46fdd21 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -212,7 +212,7 @@ int drm_agp_alloc(struct drm_device *dev, struct drm_agp_buffer *request)
 	if (!entry)
 		return -ENOMEM;
 
-	pages = (request->size + PAGE_SIZE - 1) / PAGE_SIZE;
+	pages = DIV_ROUND_UP(request->size, PAGE_SIZE);
 	type = (u32) request->type;
 	memory = agp_allocate_memory(dev->agp->bridge, pages, type);
 	if (!memory) {
@@ -325,7 +325,7 @@ int drm_agp_bind(struct drm_device *dev, struct drm_agp_binding *request)
 	entry = drm_agp_lookup_entry(dev, request->handle);
 	if (!entry || entry->bound)
 		return -EINVAL;
-	page = (request->offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	page = DIV_ROUND_UP(request->offset, PAGE_SIZE);
 	retcode = drm_bind_agp(entry->memory, page);
 	if (retcode)
 		return retcode;
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 14aeaf736321..d33691512a8e 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -251,7 +251,7 @@ EXPORT_SYMBOL(drm_atomic_state_clear);
  * @ref: This atomic state to deallocate
  *
  * This frees all memory associated with an atomic state, including all the
- * per-object state for planes, crtcs and connectors.
+ * per-object state for planes, CRTCs and connectors.
  */
 void __drm_atomic_state_free(struct kref *ref)
 {
@@ -272,12 +272,12 @@ void __drm_atomic_state_free(struct kref *ref)
 EXPORT_SYMBOL(__drm_atomic_state_free);
 
 /**
- * drm_atomic_get_crtc_state - get crtc state
+ * drm_atomic_get_crtc_state - get CRTC state
  * @state: global atomic state object
- * @crtc: crtc to get state object for
+ * @crtc: CRTC to get state object for
  *
- * This function returns the crtc state for the given crtc, allocating it if
- * needed. It will also grab the relevant crtc lock to make sure that the state
+ * This function returns the CRTC state for the given CRTC, allocating it if
+ * needed. It will also grab the relevant CRTC lock to make sure that the state
  * is consistent.
  *
  * Returns:
@@ -688,10 +688,12 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
  * associated state struct &drm_private_state.
  *
  * Similar to userspace-exposed objects, private state structures can be
- * acquired by calling drm_atomic_get_private_obj_state(). Since this function
- * does not take care of locking, drivers should wrap it for each type of
- * private state object they have with the required call to drm_modeset_lock()
- * for the corresponding &drm_modeset_lock.
+ * acquired by calling drm_atomic_get_private_obj_state(). This also takes care
+ * of locking, hence drivers should not have a need to call drm_modeset_lock()
+ * directly. Sequence of the actual hardware state commit is not handled,
+ * drivers might need to keep track of struct drm_crtc_commit within subclassed
+ * structure of &drm_private_state as necessary, e.g. similar to
+ * &drm_plane_state.commit. See also &drm_atomic_state.fake_commit.
  *
  * All private state structures contained in a &drm_atomic_state update can be
  * iterated using for_each_oldnew_private_obj_in_state(),
@@ -1016,14 +1018,14 @@ static void drm_atomic_connector_print_state(struct drm_printer *p,
 }
 
 /**
- * drm_atomic_add_affected_connectors - add connectors for crtc
+ * drm_atomic_add_affected_connectors - add connectors for CRTC
  * @state: atomic state
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  *
  * This function walks the current configuration and adds all connectors
  * currently using @crtc to the atomic configuration @state. Note that this
  * function must acquire the connection mutex. This can potentially cause
- * unneeded seralization if the update is just for the planes on one crtc. Hence
+ * unneeded seralization if the update is just for the planes on one CRTC. Hence
  * drivers and helpers should only call this when really needed (e.g. when a
  * full modeset needs to happen due to some change).
  *
@@ -1076,9 +1078,9 @@ drm_atomic_add_affected_connectors(struct drm_atomic_state *state,
 EXPORT_SYMBOL(drm_atomic_add_affected_connectors);
 
 /**
- * drm_atomic_add_affected_planes - add planes for crtc
+ * drm_atomic_add_affected_planes - add planes for CRTC
  * @state: atomic state
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  *
  * This function walks the current configuration and adds all planes
  * currently used by @crtc to the atomic configuration @state. This is useful
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index b191d39c071d..4511c2e07bb9 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -150,8 +150,8 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 	 * is not set, an error is returned. Userspace can provide a solution
 	 * through the atomic ioctl.
 	 *
-	 * If the flag is set conflicting connectors are removed from the crtc
-	 * and the crtc is disabled if no encoder is left. This preserves
+	 * If the flag is set conflicting connectors are removed from the CRTC
+	 * and the CRTC is disabled if no encoder is left. This preserves
 	 * compatibility with the legacy set_config behavior.
 	 */
 	drm_connector_list_iter_begin(state->dev, &conn_iter);
@@ -220,7 +220,7 @@ set_best_encoder(struct drm_atomic_state *state,
 		crtc = conn_state->connector->state->crtc;
 
 		/* A NULL crtc is an error here because we should have
-		 *  duplicated a NULL best_encoder when crtc was NULL.
+		 * duplicated a NULL best_encoder when crtc was NULL.
 		 * As an exception restoring duplicated atomic state
 		 * during resume is allowed, so don't warn when
 		 * best_encoder is equal to encoder we intend to set.
@@ -419,6 +419,7 @@ mode_fixup(struct drm_atomic_state *state)
 	for_each_new_connector_in_state(state, connector, new_conn_state, i) {
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
+		struct drm_bridge *bridge;
 
 		WARN_ON(!!new_conn_state->best_encoder != !!new_conn_state->crtc);
 
@@ -435,8 +436,10 @@ mode_fixup(struct drm_atomic_state *state)
 		encoder = new_conn_state->best_encoder;
 		funcs = encoder->helper_private;
 
-		ret = drm_bridge_mode_fixup(encoder->bridge, &new_crtc_state->mode,
-				&new_crtc_state->adjusted_mode);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		ret = drm_bridge_chain_mode_fixup(bridge,
+					&new_crtc_state->mode,
+					&new_crtc_state->adjusted_mode);
 		if (!ret) {
 			DRM_DEBUG_ATOMIC("Bridge fixup failed\n");
 			return -EINVAL;
@@ -492,6 +495,7 @@ static enum drm_mode_status mode_valid_path(struct drm_connector *connector,
 					    struct drm_crtc *crtc,
 					    const struct drm_display_mode *mode)
 {
+	struct drm_bridge *bridge;
 	enum drm_mode_status ret;
 
 	ret = drm_encoder_mode_valid(encoder, mode);
@@ -501,7 +505,8 @@ static enum drm_mode_status mode_valid_path(struct drm_connector *connector,
 		return ret;
 	}
 
-	ret = drm_bridge_mode_valid(encoder->bridge, mode);
+	bridge = drm_bridge_chain_get_first_bridge(encoder);
+	ret = drm_bridge_chain_mode_valid(bridge, mode);
 	if (ret != MODE_OK) {
 		DRM_DEBUG_ATOMIC("[BRIDGE] mode_valid() failed\n");
 		return ret;
@@ -556,27 +561,27 @@ mode_valid(struct drm_atomic_state *state)
  * @state: the driver state object
  *
  * Check the state object to see if the requested state is physically possible.
- * This does all the crtc and connector related computations for an atomic
+ * This does all the CRTC and connector related computations for an atomic
  * update and adds any additional connectors needed for full modesets. It calls
  * the various per-object callbacks in the follow order:
  *
  * 1. &drm_connector_helper_funcs.atomic_best_encoder for determining the new encoder.
  * 2. &drm_connector_helper_funcs.atomic_check to validate the connector state.
- * 3. If it's determined a modeset is needed then all connectors on the affected crtc
- *    crtc are added and &drm_connector_helper_funcs.atomic_check is run on them.
+ * 3. If it's determined a modeset is needed then all connectors on the affected
+ *    CRTC are added and &drm_connector_helper_funcs.atomic_check is run on them.
  * 4. &drm_encoder_helper_funcs.mode_valid, &drm_bridge_funcs.mode_valid and
  *    &drm_crtc_helper_funcs.mode_valid are called on the affected components.
  * 5. &drm_bridge_funcs.mode_fixup is called on all encoder bridges.
  * 6. &drm_encoder_helper_funcs.atomic_check is called to validate any encoder state.
- *    This function is only called when the encoder will be part of a configured crtc,
+ *    This function is only called when the encoder will be part of a configured CRTC,
  *    it must not be used for implementing connector property validation.
  *    If this function is NULL, &drm_atomic_encoder_helper_funcs.mode_fixup is called
  *    instead.
- * 7. &drm_crtc_helper_funcs.mode_fixup is called last, to fix up the mode with crtc constraints.
+ * 7. &drm_crtc_helper_funcs.mode_fixup is called last, to fix up the mode with CRTC constraints.
  *
  * &drm_crtc_state.mode_changed is set when the input mode is changed.
  * &drm_crtc_state.connectors_changed is set when a connector is added or
- * removed from the crtc.  &drm_crtc_state.active_changed is set when
+ * removed from the CRTC.  &drm_crtc_state.active_changed is set when
  * &drm_crtc_state.active changes, which is used for DPMS.
  * See also: drm_atomic_crtc_needs_modeset()
  *
@@ -687,7 +692,7 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 
 	/*
 	 * After all the routing has been prepared we need to add in any
-	 * connector which is itself unchanged, but whose crtc changes its
+	 * connector which is itself unchanged, but whose CRTC changes its
 	 * configuration. This must be done before calling mode_fixup in case a
 	 * crtc only changed its mode but has the same set of connectors.
 	 */
@@ -736,13 +741,13 @@ EXPORT_SYMBOL(drm_atomic_helper_check_modeset);
 /**
  * drm_atomic_helper_check_plane_state() - Check plane state for validity
  * @plane_state: plane state to check
- * @crtc_state: crtc state to check
+ * @crtc_state: CRTC state to check
  * @min_scale: minimum @src:@dest scaling factor in 16.16 fixed point
  * @max_scale: maximum @src:@dest scaling factor in 16.16 fixed point
  * @can_position: is it legal to position the plane such that it
- *                doesn't cover the entire crtc?  This will generally
+ *                doesn't cover the entire CRTC?  This will generally
  *                only be false for primary planes.
- * @can_update_disabled: can the plane be updated while the crtc
+ * @can_update_disabled: can the plane be updated while the CRTC
  *                       is disabled?
  *
  * Checks that a desired plane update is valid, and updates various
@@ -839,7 +844,7 @@ EXPORT_SYMBOL(drm_atomic_helper_check_plane_state);
  * &drm_crtc_helper_funcs.atomic_check and &drm_plane_helper_funcs.atomic_check
  * hooks provided by the driver.
  *
- * It also sets &drm_crtc_state.planes_changed to indicate that a crtc has
+ * It also sets &drm_crtc_state.planes_changed to indicate that a CRTC has
  * updated planes.
  *
  * RETURNS:
@@ -903,7 +908,7 @@ EXPORT_SYMBOL(drm_atomic_helper_check_planes);
  * @state: the driver state object
  *
  * Check the state object to see if the requested state is physically possible.
- * Only crtcs and planes have check callbacks, so for any additional (global)
+ * Only CRTCs and planes have check callbacks, so for any additional (global)
  * checking that a driver needs it can simply wrap that around this function.
  * Drivers without such needs can directly use this as their
  * &drm_mode_config_funcs.atomic_check callback.
@@ -956,14 +961,14 @@ crtc_needs_disable(struct drm_crtc_state *old_state,
 		   struct drm_crtc_state *new_state)
 {
 	/*
-	 * No new_state means the crtc is off, so the only criteria is whether
+	 * No new_state means the CRTC is off, so the only criteria is whether
 	 * it's currently active or in self refresh mode.
 	 */
 	if (!new_state)
 		return drm_atomic_crtc_effectively_active(old_state);
 
 	/*
-	 * We need to run through the crtc_funcs->disable() function if the crtc
+	 * We need to run through the crtc_funcs->disable() function if the CRTC
 	 * is currently on, if it's transitioning to self refresh mode, or if
 	 * it's in self refresh mode and needs to be fully disabled.
 	 */
@@ -984,6 +989,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 	for_each_oldnew_connector_in_state(old_state, connector, old_conn_state, new_conn_state, i) {
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
+		struct drm_bridge *bridge;
 
 		/* Shut down everything that's in the changeset and currently
 		 * still on. So need to check the old, saved state. */
@@ -1020,7 +1026,8 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 		 * Each encoder has at most one connector (since we always steal
 		 * it away), so we won't call disable hooks twice.
 		 */
-		drm_atomic_bridge_disable(encoder->bridge, old_state);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		drm_atomic_bridge_chain_disable(bridge, old_state);
 
 		/* Right function depends upon target state. */
 		if (funcs) {
@@ -1034,7 +1041,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 				funcs->dpms(encoder, DRM_MODE_DPMS_OFF);
 		}
 
-		drm_atomic_bridge_post_disable(encoder->bridge, old_state);
+		drm_atomic_bridge_chain_post_disable(bridge, old_state);
 	}
 
 	for_each_oldnew_crtc_in_state(old_state, crtc, old_crtc_state, new_crtc_state, i) {
@@ -1080,7 +1087,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
  * @old_state: atomic state object with old state structures
  *
  * This function updates all the various legacy modeset state pointers in
- * connectors, encoders and crtcs. It also updates the timestamping constants
+ * connectors, encoders and CRTCs. It also updates the timestamping constants
  * used for precise vblank timestamps by calling
  * drm_calc_timestamping_constants().
  *
@@ -1188,6 +1195,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
 		struct drm_display_mode *mode, *adjusted_mode;
+		struct drm_bridge *bridge;
 
 		if (!new_conn_state->best_encoder)
 			continue;
@@ -1215,7 +1223,8 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
 			funcs->mode_set(encoder, mode, adjusted_mode);
 		}
 
-		drm_bridge_mode_set(encoder->bridge, mode, adjusted_mode);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		drm_bridge_chain_mode_set(bridge, mode, adjusted_mode);
 	}
 }
 
@@ -1227,7 +1236,7 @@ crtc_set_mode(struct drm_device *dev, struct drm_atomic_state *old_state)
  * This function shuts down all the outputs that need to be shut down and
  * prepares them (if required) with the new mode.
  *
- * For compatibility with legacy crtc helpers this should be called before
+ * For compatibility with legacy CRTC helpers this should be called before
  * drm_atomic_helper_commit_planes(), which is what the default commit function
  * does. But drivers with different needs can group the modeset commits together
  * and do the plane commits at the end. This is useful for drivers doing runtime
@@ -1273,7 +1282,7 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
  * This function enables all the outputs with the new configuration which had to
  * be turned off for the update.
  *
- * For compatibility with legacy crtc helpers this should be called after
+ * For compatibility with legacy CRTC helpers this should be called after
  * drm_atomic_helper_commit_planes(), which is what the default commit function
  * does. But drivers with different needs can group the modeset commits together
  * and do the plane commits at the end. This is useful for drivers doing runtime
@@ -1314,6 +1323,7 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 	for_each_new_connector_in_state(old_state, connector, new_conn_state, i) {
 		const struct drm_encoder_helper_funcs *funcs;
 		struct drm_encoder *encoder;
+		struct drm_bridge *bridge;
 
 		if (!new_conn_state->best_encoder)
 			continue;
@@ -1332,7 +1342,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 		 * Each encoder has at most one connector (since we always steal
 		 * it away), so we won't call enable hooks twice.
 		 */
-		drm_atomic_bridge_pre_enable(encoder->bridge, old_state);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		drm_atomic_bridge_chain_pre_enable(bridge, old_state);
 
 		if (funcs) {
 			if (funcs->atomic_enable)
@@ -1343,7 +1354,7 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 				funcs->commit(encoder);
 		}
 
-		drm_atomic_bridge_enable(encoder->bridge, old_state);
+		drm_atomic_bridge_chain_enable(bridge, old_state);
 	}
 
 	drm_atomic_helper_commit_writebacks(dev, old_state);
@@ -1403,12 +1414,12 @@ int drm_atomic_helper_wait_for_fences(struct drm_device *dev,
 EXPORT_SYMBOL(drm_atomic_helper_wait_for_fences);
 
 /**
- * drm_atomic_helper_wait_for_vblanks - wait for vblank on crtcs
+ * drm_atomic_helper_wait_for_vblanks - wait for vblank on CRTCs
  * @dev: DRM device
  * @old_state: atomic state object with old state structures
  *
- * Helper to, after atomic commit, wait for vblanks on all effected
- * crtcs (ie. before cleaning up old framebuffers using
+ * Helper to, after atomic commit, wait for vblanks on all affected
+ * CRTCs (ie. before cleaning up old framebuffers using
  * drm_atomic_helper_cleanup_planes()). It will only wait on CRTCs where the
  * framebuffers have actually changed to optimize for the legacy cursor and
  * plane update use-case.
@@ -1467,10 +1478,10 @@ EXPORT_SYMBOL(drm_atomic_helper_wait_for_vblanks);
  * @dev: DRM device
  * @old_state: atomic state object with old state structures
  *
- * Helper to, after atomic commit, wait for page flips on all effected
+ * Helper to, after atomic commit, wait for page flips on all affected
  * crtcs (ie. before cleaning up old framebuffers using
  * drm_atomic_helper_cleanup_planes()). Compared to
- * drm_atomic_helper_wait_for_vblanks() this waits for the completion of on all
+ * drm_atomic_helper_wait_for_vblanks() this waits for the completion on all
  * CRTCs, assuming that cursors-only updates are signalling their completion
  * immediately (or using a different path).
  *
@@ -1834,17 +1845,21 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
 /**
  * DOC: implementing nonblocking commit
  *
- * Nonblocking atomic commits have to be implemented in the following sequence:
+ * Nonblocking atomic commits should use struct &drm_crtc_commit to sequence
+ * different operations against each another. Locks, especially struct
+ * &drm_modeset_lock, should not be held in worker threads or any other
+ * asynchronous context used to commit the hardware state.
+ *
+ * drm_atomic_helper_commit() implements the recommended sequence for
+ * nonblocking commits, using drm_atomic_helper_setup_commit() internally:
  *
- * 1. Run drm_atomic_helper_prepare_planes() first. This is the only function
- * which commit needs to call which can fail, so we want to run it first and
+ * 1. Run drm_atomic_helper_prepare_planes(). Since this can fail and we
+ * need to propagate out of memory/VRAM errors to userspace, it must be called
  * synchronously.
  *
  * 2. Synchronize with any outstanding nonblocking commit worker threads which
- * might be affected the new state update. This can be done by either cancelling
- * or flushing the work items, depending upon whether the driver can deal with
- * cancelled updates. Note that it is important to ensure that the framebuffer
- * cleanup is still done when cancelling.
+ * might be affected by the new state update. This is handled by
+ * drm_atomic_helper_setup_commit().
  *
  * Asynchronous workers need to have sufficient parallelism to be able to run
  * different atomic commits on different CRTCs in parallel. The simplest way to
@@ -1855,21 +1870,29 @@ EXPORT_SYMBOL(drm_atomic_helper_commit);
  * must be done as one global operation, and enabling or disabling a CRTC can
  * take a long time. But even that is not required.
  *
+ * IMPORTANT: A &drm_atomic_state update for multiple CRTCs is sequenced
+ * against all CRTCs therein. Therefore for atomic state updates which only flip
+ * planes the driver must not get the struct &drm_crtc_state of unrelated CRTCs
+ * in its atomic check code: This would prevent committing of atomic updates to
+ * multiple CRTCs in parallel. In general, adding additional state structures
+ * should be avoided as much as possible, because this reduces parallelism in
+ * (nonblocking) commits, both due to locking and due to commit sequencing
+ * requirements.
+ *
  * 3. The software state is updated synchronously with
  * drm_atomic_helper_swap_state(). Doing this under the protection of all modeset
- * locks means concurrent callers never see inconsistent state. And doing this
- * while it's guaranteed that no relevant nonblocking worker runs means that
- * nonblocking workers do not need grab any locks. Actually they must not grab
- * locks, for otherwise the work flushing will deadlock.
+ * locks means concurrent callers never see inconsistent state. Note that commit
+ * workers do not hold any locks; their access is only coordinated through
+ * ordering. If workers would access state only through the pointers in the
+ * free-standing state objects (currently not the case for any driver) then even
+ * multiple pending commits could be in-flight at the same time.
  *
  * 4. Schedule a work item to do all subsequent steps, using the split-out
  * commit helpers: a) pre-plane commit b) plane commit c) post-plane commit and
  * then cleaning up the framebuffers after the old framebuffer is no longer
- * being displayed.
- *
- * The above scheme is implemented in the atomic helper libraries in
- * drm_atomic_helper_commit() using a bunch of helper functions. See
- * drm_atomic_helper_setup_commit() for a starting point.
+ * being displayed. The scheduled work should synchronize against other workers
+ * using the &drm_crtc_commit infrastructure as needed. See
+ * drm_atomic_helper_setup_commit() for more details.
  */
 
 static int stall_checks(struct drm_crtc *crtc, bool nonblock)
@@ -2098,7 +2121,7 @@ EXPORT_SYMBOL(drm_atomic_helper_setup_commit);
  *
  * This function waits for all preceeding commits that touch the same CRTC as
  * @old_state to both be committed to the hardware (as signalled by
- * drm_atomic_helper_commit_hw_done) and executed by the hardware (as signalled
+ * drm_atomic_helper_commit_hw_done()) and executed by the hardware (as signalled
  * by calling drm_crtc_send_vblank_event() on the &drm_crtc_state.event).
  *
  * This is part of the atomic helper support for nonblocking commits, see
@@ -2185,7 +2208,7 @@ EXPORT_SYMBOL(drm_atomic_helper_wait_for_dependencies);
  * drm_atomic_helper_fake_vblank - fake VBLANK events if needed
  * @old_state: atomic state object with old state structures
  *
- * This function walks all CRTCs and fake VBLANK events on those with
+ * This function walks all CRTCs and fakes VBLANK events on those with
  * &drm_crtc_state.no_vblank set to true and &drm_crtc_state.event != NULL.
  * The primary use of this function is writeback connectors working in oneshot
  * mode and faking VBLANK events. In this case they only fake the VBLANK event
@@ -2381,7 +2404,7 @@ static bool plane_crtc_active(const struct drm_plane_state *state)
  * @flags: flags for committing plane state
  *
  * This function commits the new plane state using the plane and atomic helper
- * functions for planes and crtcs. It assumes that the atomic state has already
+ * functions for planes and CRTCs. It assumes that the atomic state has already
  * been pushed into the relevant object state pointers, since this step can no
  * longer fail.
  *
@@ -2502,15 +2525,15 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev,
 EXPORT_SYMBOL(drm_atomic_helper_commit_planes);
 
 /**
- * drm_atomic_helper_commit_planes_on_crtc - commit plane state for a crtc
- * @old_crtc_state: atomic state object with the old crtc state
+ * drm_atomic_helper_commit_planes_on_crtc - commit plane state for a CRTC
+ * @old_crtc_state: atomic state object with the old CRTC state
  *
  * This function commits the new plane state using the plane and atomic helper
- * functions for planes on the specific crtc. It assumes that the atomic state
+ * functions for planes on the specific CRTC. It assumes that the atomic state
  * has already been pushed into the relevant object state pointers, since this
  * step can no longer fail.
  *
- * This function is useful when plane updates should be done crtc-by-crtc
+ * This function is useful when plane updates should be done CRTC-by-CRTC
  * instead of one global step like drm_atomic_helper_commit_planes() does.
  *
  * This function can only be savely used when planes are not allowed to move
@@ -2800,10 +2823,10 @@ EXPORT_SYMBOL(drm_atomic_helper_swap_state);
  * @plane: plane object to update
  * @crtc: owning CRTC of owning plane
  * @fb: framebuffer to flip onto plane
- * @crtc_x: x offset of primary plane on crtc
- * @crtc_y: y offset of primary plane on crtc
- * @crtc_w: width of primary plane rectangle on crtc
- * @crtc_h: height of primary plane rectangle on crtc
+ * @crtc_x: x offset of primary plane on @crtc
+ * @crtc_y: y offset of primary plane on @crtc
+ * @crtc_w: width of primary plane rectangle on @crtc
+ * @crtc_h: height of primary plane rectangle on @crtc
  * @src_x: x offset of @fb for panning
  * @src_y: y offset of @fb for panning
  * @src_w: width of source rectangle in @fb
@@ -2909,7 +2932,7 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_plane);
  * @set: mode set configuration
  * @ctx: lock acquisition context
  *
- * Provides a default crtc set_config handler using the atomic driver interface.
+ * Provides a default CRTC set_config handler using the atomic driver interface.
  *
  * NOTE: For backwards compatibility with old userspace this automatically
  * resets the "link-status" property to GOOD, to force any link
@@ -3322,7 +3345,7 @@ static int page_flip_common(struct drm_atomic_state *state,
 
 /**
  * drm_atomic_helper_page_flip - execute a legacy page flip
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  * @fb: DRM framebuffer
  * @event: optional DRM event to signal upon completion
  * @flags: flip flags for non-vblank sync'ed updates
@@ -3366,7 +3389,7 @@ EXPORT_SYMBOL(drm_atomic_helper_page_flip);
 
 /**
  * drm_atomic_helper_page_flip_target - do page flip on target vblank period.
- * @crtc: DRM crtc
+ * @crtc: DRM CRTC
  * @fb: DRM framebuffer
  * @event: optional DRM event to signal upon completion
  * @flags: flip flags for non-vblank sync'ed updates
diff --git a/drivers/gpu/drm/drm_atomic_state_helper.c b/drivers/gpu/drm/drm_atomic_state_helper.c
index d0a937fb0c56..7cf3cf936547 100644
--- a/drivers/gpu/drm/drm_atomic_state_helper.c
+++ b/drivers/gpu/drm/drm_atomic_state_helper.c
@@ -58,6 +58,22 @@
  */
 
 /**
+ * __drm_atomic_helper_crtc_state_reset - reset the CRTC state
+ * @crtc_state: atomic CRTC state, must not be NULL
+ * @crtc: CRTC object, must not be NULL
+ *
+ * Initializes the newly allocated @crtc_state with default
+ * values. This is useful for drivers that subclass the CRTC state.
+ */
+void
+__drm_atomic_helper_crtc_state_reset(struct drm_crtc_state *crtc_state,
+				     struct drm_crtc *crtc)
+{
+	crtc_state->crtc = crtc;
+}
+EXPORT_SYMBOL(__drm_atomic_helper_crtc_state_reset);
+
+/**
  * __drm_atomic_helper_crtc_reset - reset state on CRTC
  * @crtc: drm CRTC
  * @crtc_state: CRTC state to assign
@@ -74,7 +90,7 @@ __drm_atomic_helper_crtc_reset(struct drm_crtc *crtc,
 			       struct drm_crtc_state *crtc_state)
 {
 	if (crtc_state)
-		crtc_state->crtc = crtc;
+		__drm_atomic_helper_crtc_state_reset(crtc_state, crtc);
 
 	crtc->state = crtc_state;
 }
@@ -212,23 +228,43 @@ void drm_atomic_helper_crtc_destroy_state(struct drm_crtc *crtc,
 EXPORT_SYMBOL(drm_atomic_helper_crtc_destroy_state);
 
 /**
- * __drm_atomic_helper_plane_reset - resets planes state to default values
+ * __drm_atomic_helper_plane_state_reset - resets plane state to default values
+ * @plane_state: atomic plane state, must not be NULL
  * @plane: plane object, must not be NULL
- * @state: atomic plane state, must not be NULL
  *
- * Initializes plane state to default. This is useful for drivers that subclass
- * the plane state.
+ * Initializes the newly allocated @plane_state with default
+ * values. This is useful for drivers that subclass the CRTC state.
  */
-void __drm_atomic_helper_plane_reset(struct drm_plane *plane,
-				     struct drm_plane_state *state)
+void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *plane_state,
+					   struct drm_plane *plane)
 {
-	state->plane = plane;
-	state->rotation = DRM_MODE_ROTATE_0;
+	plane_state->plane = plane;
+	plane_state->rotation = DRM_MODE_ROTATE_0;
 
-	state->alpha = DRM_BLEND_ALPHA_OPAQUE;
-	state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI;
+	plane_state->alpha = DRM_BLEND_ALPHA_OPAQUE;
+	plane_state->pixel_blend_mode = DRM_MODE_BLEND_PREMULTI;
+}
+EXPORT_SYMBOL(__drm_atomic_helper_plane_state_reset);
 
-	plane->state = state;
+/**
+ * __drm_atomic_helper_plane_reset - reset state on plane
+ * @plane: drm plane
+ * @plane_state: plane state to assign
+ *
+ * Initializes the newly allocated @plane_state and assigns it to
+ * the &drm_crtc->state pointer of @plane, usually required when
+ * initializing the drivers or when called from the &drm_plane_funcs.reset
+ * hook.
+ *
+ * This is useful for drivers that subclass the plane state.
+ */
+void __drm_atomic_helper_plane_reset(struct drm_plane *plane,
+				     struct drm_plane_state *plane_state)
+{
+	if (plane_state)
+		__drm_atomic_helper_plane_state_reset(plane_state, plane);
+
+	plane->state = plane_state;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_plane_reset);
 
@@ -336,6 +372,22 @@ void drm_atomic_helper_plane_destroy_state(struct drm_plane *plane,
 EXPORT_SYMBOL(drm_atomic_helper_plane_destroy_state);
 
 /**
+ * __drm_atomic_helper_connector_state_reset - reset the connector state
+ * @conn_state: atomic connector state, must not be NULL
+ * @connector: connectotr object, must not be NULL
+ *
+ * Initializes the newly allocated @conn_state with default
+ * values. This is useful for drivers that subclass the connector state.
+ */
+void
+__drm_atomic_helper_connector_state_reset(struct drm_connector_state *conn_state,
+					  struct drm_connector *connector)
+{
+	conn_state->connector = connector;
+}
+EXPORT_SYMBOL(__drm_atomic_helper_connector_state_reset);
+
+/**
  * __drm_atomic_helper_connector_reset - reset state on connector
  * @connector: drm connector
  * @conn_state: connector state to assign
@@ -352,7 +404,7 @@ __drm_atomic_helper_connector_reset(struct drm_connector *connector,
 				    struct drm_connector_state *conn_state)
 {
 	if (conn_state)
-		conn_state->connector = connector;
+		__drm_atomic_helper_connector_state_reset(conn_state, connector);
 
 	connector->state = conn_state;
 }
diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 0d466d3b0809..a1e5e262bae2 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -160,12 +160,12 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 EXPORT_SYMBOL(drm_atomic_set_mode_prop_for_crtc);
 
 /**
- * drm_atomic_set_crtc_for_plane - set crtc for plane
+ * drm_atomic_set_crtc_for_plane - set CRTC for plane
  * @plane_state: the plane whose incoming state to update
- * @crtc: crtc to use for the plane
+ * @crtc: CRTC to use for the plane
  *
- * Changing the assigned crtc for a plane requires us to grab the lock and state
- * for the new crtc, as needed. This function takes care of all these details
+ * Changing the assigned CRTC for a plane requires us to grab the lock and state
+ * for the new CRTC, as needed. This function takes care of all these details
  * besides updating the pointer in the state object itself.
  *
  * Returns:
@@ -279,12 +279,12 @@ drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state,
 EXPORT_SYMBOL(drm_atomic_set_fence_for_plane);
 
 /**
- * drm_atomic_set_crtc_for_connector - set crtc for connector
+ * drm_atomic_set_crtc_for_connector - set CRTC for connector
  * @conn_state: atomic state object for the connector
- * @crtc: crtc to use for the connector
+ * @crtc: CRTC to use for the connector
  *
- * Changing the assigned crtc for a connector requires us to grab the lock and
- * state for the new crtc, as needed. This function takes care of all these
+ * Changing the assigned CRTC for a connector requires us to grab the lock and
+ * state for the new CRTC, as needed. This function takes care of all these
  * details besides updating the pointer in the state object itself.
  *
  * Returns:
diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index cba537c99e43..c2cf0c90fa26 100644
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -55,7 +55,7 @@
  * just provide additional hooks to get the desired output at the end of the
  * encoder chain.
  *
- * Bridges can also be chained up using the &drm_bridge.next pointer.
+ * Bridges can also be chained up using the &drm_bridge.chain_node field.
  *
  * Both legacy CRTC helpers and the new atomic modeset helpers support bridges.
  */
@@ -128,20 +128,21 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge,
 	bridge->dev = encoder->dev;
 	bridge->encoder = encoder;
 
+	if (previous)
+		list_add(&bridge->chain_node, &previous->chain_node);
+	else
+		list_add(&bridge->chain_node, &encoder->bridge_chain);
+
 	if (bridge->funcs->attach) {
 		ret = bridge->funcs->attach(bridge);
 		if (ret < 0) {
+			list_del(&bridge->chain_node);
 			bridge->dev = NULL;
 			bridge->encoder = NULL;
 			return ret;
 		}
 	}
 
-	if (previous)
-		previous->next = bridge;
-	else
-		encoder->bridge = bridge;
-
 	return 0;
 }
 EXPORT_SYMBOL(drm_bridge_attach);
@@ -157,6 +158,7 @@ void drm_bridge_detach(struct drm_bridge *bridge)
 	if (bridge->funcs->detach)
 		bridge->funcs->detach(bridge);
 
+	list_del(&bridge->chain_node);
 	bridge->dev = NULL;
 }
 
@@ -172,8 +174,8 @@ void drm_bridge_detach(struct drm_bridge *bridge)
  */
 
 /**
- * drm_bridge_mode_fixup - fixup proposed mode for all bridges in the
- *			   encoder chain
+ * drm_bridge_chain_mode_fixup - fixup proposed mode for all bridges in the
+ *				 encoder chain
  * @bridge: bridge control structure
  * @mode: desired mode to be set for the bridge
  * @adjusted_mode: updated mode that works for this bridge
@@ -186,27 +188,31 @@ void drm_bridge_detach(struct drm_bridge *bridge)
  * RETURNS:
  * true on success, false on failure
  */
-bool drm_bridge_mode_fixup(struct drm_bridge *bridge,
-			const struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode)
+bool drm_bridge_chain_mode_fixup(struct drm_bridge *bridge,
+				 const struct drm_display_mode *mode,
+				 struct drm_display_mode *adjusted_mode)
 {
-	bool ret = true;
+	struct drm_encoder *encoder;
 
 	if (!bridge)
 		return true;
 
-	if (bridge->funcs->mode_fixup)
-		ret = bridge->funcs->mode_fixup(bridge, mode, adjusted_mode);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (!bridge->funcs->mode_fixup)
+			continue;
 
-	ret = ret && drm_bridge_mode_fixup(bridge->next, mode, adjusted_mode);
+		if (!bridge->funcs->mode_fixup(bridge, mode, adjusted_mode))
+			return false;
+	}
 
-	return ret;
+	return true;
 }
-EXPORT_SYMBOL(drm_bridge_mode_fixup);
+EXPORT_SYMBOL(drm_bridge_chain_mode_fixup);
 
 /**
- * drm_bridge_mode_valid - validate the mode against all bridges in the
- * 			   encoder chain.
+ * drm_bridge_chain_mode_valid - validate the mode against all bridges in the
+ *				 encoder chain.
  * @bridge: bridge control structure
  * @mode: desired mode to be validated
  *
@@ -219,26 +225,33 @@ EXPORT_SYMBOL(drm_bridge_mode_fixup);
  * RETURNS:
  * MODE_OK on success, drm_mode_status Enum error code on failure
  */
-enum drm_mode_status drm_bridge_mode_valid(struct drm_bridge *bridge,
-					   const struct drm_display_mode *mode)
+enum drm_mode_status
+drm_bridge_chain_mode_valid(struct drm_bridge *bridge,
+			    const struct drm_display_mode *mode)
 {
-	enum drm_mode_status ret = MODE_OK;
+	struct drm_encoder *encoder;
 
 	if (!bridge)
-		return ret;
+		return MODE_OK;
 
-	if (bridge->funcs->mode_valid)
-		ret = bridge->funcs->mode_valid(bridge, mode);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		enum drm_mode_status ret;
 
-	if (ret != MODE_OK)
-		return ret;
+		if (!bridge->funcs->mode_valid)
+			continue;
 
-	return drm_bridge_mode_valid(bridge->next, mode);
+		ret = bridge->funcs->mode_valid(bridge, mode);
+		if (ret != MODE_OK)
+			return ret;
+	}
+
+	return MODE_OK;
 }
-EXPORT_SYMBOL(drm_bridge_mode_valid);
+EXPORT_SYMBOL(drm_bridge_chain_mode_valid);
 
 /**
- * drm_bridge_disable - disables all bridges in the encoder chain
+ * drm_bridge_chain_disable - disables all bridges in the encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.disable op for all the bridges in the encoder
@@ -247,20 +260,28 @@ EXPORT_SYMBOL(drm_bridge_mode_valid);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_disable(struct drm_bridge *bridge)
+void drm_bridge_chain_disable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_bridge_disable(bridge->next);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->disable)
+			iter->funcs->disable(iter);
 
-	if (bridge->funcs->disable)
-		bridge->funcs->disable(bridge);
+		if (iter == bridge)
+			break;
+	}
 }
-EXPORT_SYMBOL(drm_bridge_disable);
+EXPORT_SYMBOL(drm_bridge_chain_disable);
 
 /**
- * drm_bridge_post_disable - cleans up after disabling all bridges in the encoder chain
+ * drm_bridge_chain_post_disable - cleans up after disabling all bridges in the
+ *				   encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.post_disable op for all the bridges in the
@@ -269,47 +290,53 @@ EXPORT_SYMBOL(drm_bridge_disable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_post_disable(struct drm_bridge *bridge)
+void drm_bridge_chain_post_disable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->post_disable)
-		bridge->funcs->post_disable(bridge);
-
-	drm_bridge_post_disable(bridge->next);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->post_disable)
+			bridge->funcs->post_disable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_post_disable);
+EXPORT_SYMBOL(drm_bridge_chain_post_disable);
 
 /**
- * drm_bridge_mode_set - set proposed mode for all bridges in the
- *			 encoder chain
+ * drm_bridge_chain_mode_set - set proposed mode for all bridges in the
+ *			       encoder chain
  * @bridge: bridge control structure
- * @mode: desired mode to be set for the bridge
- * @adjusted_mode: updated mode that works for this bridge
+ * @mode: desired mode to be set for the encoder chain
+ * @adjusted_mode: updated mode that works for this encoder chain
  *
  * Calls &drm_bridge_funcs.mode_set op for all the bridges in the
  * encoder chain, starting from the first bridge to the last.
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_mode_set(struct drm_bridge *bridge,
-			 const struct drm_display_mode *mode,
-			 const struct drm_display_mode *adjusted_mode)
+void drm_bridge_chain_mode_set(struct drm_bridge *bridge,
+			       const struct drm_display_mode *mode,
+			       const struct drm_display_mode *adjusted_mode)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->mode_set)
-		bridge->funcs->mode_set(bridge, mode, adjusted_mode);
-
-	drm_bridge_mode_set(bridge->next, mode, adjusted_mode);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->mode_set)
+			bridge->funcs->mode_set(bridge, mode, adjusted_mode);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_mode_set);
+EXPORT_SYMBOL(drm_bridge_chain_mode_set);
 
 /**
- * drm_bridge_pre_enable - prepares for enabling all
- *			   bridges in the encoder chain
+ * drm_bridge_chain_pre_enable - prepares for enabling all bridges in the
+ *				 encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.pre_enable op for all the bridges in the encoder
@@ -318,20 +345,24 @@ EXPORT_SYMBOL(drm_bridge_mode_set);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_pre_enable(struct drm_bridge *bridge)
+void drm_bridge_chain_pre_enable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_bridge_pre_enable(bridge->next);
-
-	if (bridge->funcs->pre_enable)
-		bridge->funcs->pre_enable(bridge);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->pre_enable)
+			iter->funcs->pre_enable(iter);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_pre_enable);
+EXPORT_SYMBOL(drm_bridge_chain_pre_enable);
 
 /**
- * drm_bridge_enable - enables all bridges in the encoder chain
+ * drm_bridge_chain_enable - enables all bridges in the encoder chain
  * @bridge: bridge control structure
  *
  * Calls &drm_bridge_funcs.enable op for all the bridges in the encoder
@@ -340,22 +371,25 @@ EXPORT_SYMBOL(drm_bridge_pre_enable);
  *
  * Note that the bridge passed should be the one closest to the encoder
  */
-void drm_bridge_enable(struct drm_bridge *bridge)
+void drm_bridge_chain_enable(struct drm_bridge *bridge)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->enable)
-		bridge->funcs->enable(bridge);
-
-	drm_bridge_enable(bridge->next);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->enable)
+			bridge->funcs->enable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_bridge_enable);
+EXPORT_SYMBOL(drm_bridge_chain_enable);
 
 /**
- * drm_atomic_bridge_disable - disables all bridges in the encoder chain
+ * drm_atomic_bridge_chain_disable - disables all bridges in the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_disable (falls back on
  * &drm_bridge_funcs.disable) op for all the bridges in the encoder chain,
@@ -364,26 +398,33 @@ EXPORT_SYMBOL(drm_bridge_enable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_disable(struct drm_bridge *bridge,
-			       struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_disable(struct drm_bridge *bridge,
+				     struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_atomic_bridge_disable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->atomic_disable)
+			iter->funcs->atomic_disable(iter, old_state);
+		else if (iter->funcs->disable)
+			iter->funcs->disable(iter);
 
-	if (bridge->funcs->atomic_disable)
-		bridge->funcs->atomic_disable(bridge, state);
-	else if (bridge->funcs->disable)
-		bridge->funcs->disable(bridge);
+		if (iter == bridge)
+			break;
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_disable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_disable);
 
 /**
- * drm_atomic_bridge_post_disable - cleans up after disabling all bridges in the
- *				    encoder chain
+ * drm_atomic_bridge_chain_post_disable - cleans up after disabling all bridges
+ *					  in the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_post_disable (falls back on
  * &drm_bridge_funcs.post_disable) op for all the bridges in the encoder chain,
@@ -392,26 +433,29 @@ EXPORT_SYMBOL(drm_atomic_bridge_disable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_post_disable(struct drm_bridge *bridge,
-				    struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge,
+					  struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->atomic_post_disable)
-		bridge->funcs->atomic_post_disable(bridge, state);
-	else if (bridge->funcs->post_disable)
-		bridge->funcs->post_disable(bridge);
-
-	drm_atomic_bridge_post_disable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->atomic_post_disable)
+			bridge->funcs->atomic_post_disable(bridge, old_state);
+		else if (bridge->funcs->post_disable)
+			bridge->funcs->post_disable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_post_disable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_post_disable);
 
 /**
- * drm_atomic_bridge_pre_enable - prepares for enabling all bridges in the
- *				  encoder chain
+ * drm_atomic_bridge_chain_pre_enable - prepares for enabling all bridges in
+ *					the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_pre_enable (falls back on
  * &drm_bridge_funcs.pre_enable) op for all the bridges in the encoder chain,
@@ -420,25 +464,32 @@ EXPORT_SYMBOL(drm_atomic_bridge_post_disable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_pre_enable(struct drm_bridge *bridge,
-				  struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_pre_enable(struct drm_bridge *bridge,
+					struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+	struct drm_bridge *iter;
+
 	if (!bridge)
 		return;
 
-	drm_atomic_bridge_pre_enable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_reverse(iter, &encoder->bridge_chain, chain_node) {
+		if (iter->funcs->atomic_pre_enable)
+			iter->funcs->atomic_pre_enable(iter, old_state);
+		else if (iter->funcs->pre_enable)
+			iter->funcs->pre_enable(iter);
 
-	if (bridge->funcs->atomic_pre_enable)
-		bridge->funcs->atomic_pre_enable(bridge, state);
-	else if (bridge->funcs->pre_enable)
-		bridge->funcs->pre_enable(bridge);
+		if (iter == bridge)
+			break;
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_pre_enable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_pre_enable);
 
 /**
- * drm_atomic_bridge_enable - enables all bridges in the encoder chain
+ * drm_atomic_bridge_chain_enable - enables all bridges in the encoder chain
  * @bridge: bridge control structure
- * @state: atomic state being committed
+ * @old_state: old atomic state
  *
  * Calls &drm_bridge_funcs.atomic_enable (falls back on
  * &drm_bridge_funcs.enable) op for all the bridges in the encoder chain,
@@ -447,20 +498,23 @@ EXPORT_SYMBOL(drm_atomic_bridge_pre_enable);
  *
  * Note: the bridge passed should be the one closest to the encoder
  */
-void drm_atomic_bridge_enable(struct drm_bridge *bridge,
-			      struct drm_atomic_state *state)
+void drm_atomic_bridge_chain_enable(struct drm_bridge *bridge,
+				    struct drm_atomic_state *old_state)
 {
+	struct drm_encoder *encoder;
+
 	if (!bridge)
 		return;
 
-	if (bridge->funcs->atomic_enable)
-		bridge->funcs->atomic_enable(bridge, state);
-	else if (bridge->funcs->enable)
-		bridge->funcs->enable(bridge);
-
-	drm_atomic_bridge_enable(bridge->next, state);
+	encoder = bridge->encoder;
+	list_for_each_entry_from(bridge, &encoder->bridge_chain, chain_node) {
+		if (bridge->funcs->atomic_enable)
+			bridge->funcs->atomic_enable(bridge, old_state);
+		else if (bridge->funcs->enable)
+			bridge->funcs->enable(bridge);
+	}
 }
-EXPORT_SYMBOL(drm_atomic_bridge_enable);
+EXPORT_SYMBOL(drm_atomic_bridge_chain_enable);
 
 #ifdef CONFIG_OF
 /**
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index d9a2e3695525..b031b45aa8ef 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -150,7 +150,7 @@ void drm_client_release(struct drm_client_dev *client)
 {
 	struct drm_device *dev = client->dev;
 
-	DRM_DEV_DEBUG_KMS(dev->dev, "%s\n", client->name);
+	drm_dbg_kms(dev, "%s\n", client->name);
 
 	drm_client_modeset_free(client);
 	drm_client_close(client);
@@ -203,7 +203,7 @@ void drm_client_dev_hotplug(struct drm_device *dev)
 			continue;
 
 		ret = client->funcs->hotplug(client);
-		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret);
 	}
 	mutex_unlock(&dev->clientlist_mutex);
 }
@@ -223,7 +223,7 @@ void drm_client_dev_restore(struct drm_device *dev)
 			continue;
 
 		ret = client->funcs->restore(client);
-		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		drm_dbg_kms(dev, "%s: ret=%d\n", client->name, ret);
 		if (!ret) /* The first one to return zero gets the privilege to restore */
 			break;
 	}
@@ -351,8 +351,8 @@ static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer)
 
 	ret = drm_mode_rmfb(buffer->client->dev, buffer->fb->base.id, buffer->client->file);
 	if (ret)
-		DRM_DEV_ERROR(buffer->client->dev->dev,
-			      "Error removing FB:%u (%d)\n", buffer->fb->base.id, ret);
+		drm_err(buffer->client->dev,
+			"Error removing FB:%u (%d)\n", buffer->fb->base.id, ret);
 
 	buffer->fb = NULL;
 }
diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
index 895b73f23079..6d4a29e99ae2 100644
--- a/drivers/gpu/drm/drm_client_modeset.c
+++ b/drivers/gpu/drm/drm_client_modeset.c
@@ -115,6 +115,33 @@ drm_client_find_modeset(struct drm_client_dev *client, struct drm_crtc *crtc)
 }
 
 static struct drm_display_mode *
+drm_connector_get_tiled_mode(struct drm_connector *connector)
+{
+	struct drm_display_mode *mode;
+
+	list_for_each_entry(mode, &connector->modes, head) {
+		if (mode->hdisplay == connector->tile_h_size &&
+		    mode->vdisplay == connector->tile_v_size)
+			return mode;
+	}
+	return NULL;
+}
+
+static struct drm_display_mode *
+drm_connector_fallback_non_tiled_mode(struct drm_connector *connector)
+{
+	struct drm_display_mode *mode;
+
+	list_for_each_entry(mode, &connector->modes, head) {
+		if (mode->hdisplay == connector->tile_h_size &&
+		    mode->vdisplay == connector->tile_v_size)
+			continue;
+		return mode;
+	}
+	return NULL;
+}
+
+static struct drm_display_mode *
 drm_connector_has_preferred_mode(struct drm_connector *connector, int width, int height)
 {
 	struct drm_display_mode *mode;
@@ -348,8 +375,15 @@ static bool drm_client_target_preferred(struct drm_connector **connectors,
 	struct drm_connector *connector;
 	u64 conn_configured = 0;
 	int tile_pass = 0;
+	int num_tiled_conns = 0;
 	int i;
 
+	for (i = 0; i < connector_count; i++) {
+		if (connectors[i]->has_tile &&
+		    connectors[i]->status == connector_status_connected)
+			num_tiled_conns++;
+	}
+
 retry:
 	for (i = 0; i < connector_count; i++) {
 		connector = connectors[i];
@@ -399,6 +433,28 @@ retry:
 			list_for_each_entry(modes[i], &connector->modes, head)
 				break;
 		}
+		/*
+		 * In case of tiled mode if all tiles not present fallback to
+		 * first available non tiled mode.
+		 * After all tiles are present, try to find the tiled mode
+		 * for all and if tiled mode not present due to fbcon size
+		 * limitations, use first non tiled mode only for
+		 * tile 0,0 and set to no mode for all other tiles.
+		 */
+		if (connector->has_tile) {
+			if (num_tiled_conns <
+			    connector->num_h_tile * connector->num_v_tile ||
+			    (connector->tile_h_loc == 0 &&
+			     connector->tile_v_loc == 0 &&
+			     !drm_connector_get_tiled_mode(connector))) {
+				DRM_DEBUG_KMS("Falling back to non tiled mode on Connector %d\n",
+					      connector->base.id);
+				modes[i] = drm_connector_fallback_non_tiled_mode(connector);
+			} else {
+				modes[i] = drm_connector_get_tiled_mode(connector);
+			}
+		}
+
 		DRM_DEBUG_KMS("found mode %s\n", modes[i] ? modes[i]->name :
 			  "none");
 		conn_configured |= BIT_ULL(i);
@@ -515,6 +571,7 @@ static bool drm_client_firmware_config(struct drm_client_dev *client,
 	bool fallback = true, ret = true;
 	int num_connectors_enabled = 0;
 	int num_connectors_detected = 0;
+	int num_tiled_conns = 0;
 	struct drm_modeset_acquire_ctx ctx;
 
 	if (!drm_drv_uses_atomic_modeset(dev))
@@ -532,6 +589,11 @@ static bool drm_client_firmware_config(struct drm_client_dev *client,
 	memcpy(save_enabled, enabled, count);
 	mask = GENMASK(count - 1, 0);
 	conn_configured = 0;
+	for (i = 0; i < count; i++) {
+		if (connectors[i]->has_tile &&
+		    connectors[i]->status == connector_status_connected)
+			num_tiled_conns++;
+	}
 retry:
 	conn_seq = conn_configured;
 	for (i = 0; i < count; i++) {
@@ -631,6 +693,16 @@ retry:
 				      connector->name);
 			modes[i] = &connector->state->crtc->mode;
 		}
+		/*
+		 * In case of tiled modes, if all tiles are not present
+		 * then fallback to a non tiled mode.
+		 */
+		if (connector->has_tile &&
+		    num_tiled_conns < connector->num_h_tile * connector->num_v_tile) {
+			DRM_DEBUG_KMS("Falling back to non tiled mode on Connector %d\n",
+				      connector->base.id);
+			modes[i] = drm_connector_fallback_non_tiled_mode(connector);
+		}
 		crtcs[i] = new_crtc;
 
 		DRM_DEBUG_KMS("connector %s on [CRTC:%d:%s]: %dx%d%s\n",
diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c
index 4ce5c6d8de99..c93123ff7c21 100644
--- a/drivers/gpu/drm/drm_color_mgmt.c
+++ b/drivers/gpu/drm/drm_color_mgmt.c
@@ -109,28 +109,38 @@
  */
 
 /**
- * drm_color_lut_extract - clamp and round LUT entries
+ * drm_color_ctm_s31_32_to_qm_n
+ *
  * @user_input: input value
- * @bit_precision: number of bits the hw LUT supports
+ * @m: number of integer bits, only support m <= 32, include the sign-bit
+ * @n: number of fractional bits, only support n <= 32
+ *
+ * Convert and clamp S31.32 sign-magnitude to Qm.n (signed 2's complement).
+ * The sign-bit BIT(m+n-1) and above are 0 for positive value and 1 for negative
+ * the range of value is [-2^(m-1), 2^(m-1) - 2^-n]
+ *
+ * For example
+ * A Q3.12 format number:
+ * - required bit: 3 + 12 = 15bits
+ * - range: [-2^2, 2^2 - 2^−15]
  *
- * Extract a degamma/gamma LUT value provided by user (in the form of
- * &drm_color_lut entries) and round it to the precision supported by the
- * hardware.
+ * NOTE: the m can be zero if all bit_precision are used to present fractional
+ *       bits like Q0.32
  */
-uint32_t drm_color_lut_extract(uint32_t user_input, uint32_t bit_precision)
+u64 drm_color_ctm_s31_32_to_qm_n(u64 user_input, u32 m, u32 n)
 {
-	uint32_t val = user_input;
-	uint32_t max = 0xffff >> (16 - bit_precision);
+	u64 mag = (user_input & ~BIT_ULL(63)) >> (32 - n);
+	bool negative = !!(user_input & BIT_ULL(63));
+	s64 val;
 
-	/* Round only if we're not using full precision. */
-	if (bit_precision < 16) {
-		val += 1UL << (16 - bit_precision - 1);
-		val >>= 16 - bit_precision;
-	}
+	WARN_ON(m > 32 || n > 32);
+
+	val = clamp_val(mag, 0, negative ?
+				BIT_ULL(n + m - 1) : BIT_ULL(n + m - 1) - 1);
 
-	return clamp_val(val, 0, max);
+	return negative ? -val : val;
 }
-EXPORT_SYMBOL(drm_color_lut_extract);
+EXPORT_SYMBOL(drm_color_ctm_s31_32_to_qm_n);
 
 /**
  * drm_crtc_enable_color_mgmt - enable color management properties
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 499b05aaccfc..93a4eec429e8 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -48,6 +48,8 @@
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
 
+#include "drm_crtc_helper_internal.h"
+
 /**
  * DOC: overview
  *
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index ca3c55c6b815..e22b812c4b80 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -140,8 +140,8 @@ static ssize_t crc_control_write(struct file *file, const char __user *ubuf,
 	if (IS_ERR(source))
 		return PTR_ERR(source);
 
-	if (source[len] == '\n')
-		source[len] = '\0';
+	if (source[len - 1] == '\n')
+		source[len - 1] = '\0';
 
 	ret = crtc->funcs->verify_crc_source(crtc, source, &values_cnt);
 	if (ret)
@@ -258,6 +258,11 @@ static int crtc_crc_release(struct inode *inode, struct file *filep)
 	struct drm_crtc *crtc = filep->f_inode->i_private;
 	struct drm_crtc_crc *crc = &crtc->crc;
 
+	/* terminate the infinite while loop if 'drm_dp_aux_crc_work' running */
+	spin_lock_irq(&crc->lock);
+	crc->opened = false;
+	spin_unlock_irq(&crc->lock);
+
 	crtc->funcs->set_crc_source(crtc, NULL);
 
 	spin_lock_irq(&crc->lock);
diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c
index 0cfb386754c3..2510717d5a08 100644
--- a/drivers/gpu/drm/drm_dp_aux_dev.c
+++ b/drivers/gpu/drm/drm_dp_aux_dev.c
@@ -163,11 +163,7 @@ static ssize_t auxdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			break;
 		}
 
-		if (aux_dev->aux->is_remote)
-			res = drm_dp_mst_dpcd_read(aux_dev->aux, pos, buf,
-						   todo);
-		else
-			res = drm_dp_dpcd_read(aux_dev->aux, pos, buf, todo);
+		res = drm_dp_dpcd_read(aux_dev->aux, pos, buf, todo);
 
 		if (res <= 0)
 			break;
@@ -215,11 +211,7 @@ static ssize_t auxdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			break;
 		}
 
-		if (aux_dev->aux->is_remote)
-			res = drm_dp_mst_dpcd_write(aux_dev->aux, pos, buf,
-						    todo);
-		else
-			res = drm_dp_dpcd_write(aux_dev->aux, pos, buf, todo);
+		res = drm_dp_dpcd_write(aux_dev->aux, pos, buf, todo);
 
 		if (res <= 0)
 			break;
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index 2c7870aef469..a5364b5192b8 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -32,6 +32,7 @@
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_print.h>
 #include <drm/drm_vblank.h>
+#include <drm/drm_dp_mst_helper.h>
 
 #include "drm_crtc_helper_internal.h"
 
@@ -266,7 +267,7 @@ unlock:
 
 /**
  * drm_dp_dpcd_read() - read a series of bytes from the DPCD
- * @aux: DisplayPort AUX channel
+ * @aux: DisplayPort AUX channel (SST or MST)
  * @offset: address of the (first) register to read
  * @buffer: buffer to store the register values
  * @size: number of bytes in @buffer
@@ -295,13 +296,18 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	 * We just have to do it before any DPCD access and hope that the
 	 * monitor doesn't power down exactly after the throw away read.
 	 */
-	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, buffer,
-				 1);
-	if (ret != 1)
-		goto out;
+	if (!aux->is_remote) {
+		ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV,
+					 buffer, 1);
+		if (ret != 1)
+			goto out;
+	}
 
-	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
-				 size);
+	if (aux->is_remote)
+		ret = drm_dp_mst_dpcd_read(aux, offset, buffer, size);
+	else
+		ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset,
+					 buffer, size);
 
 out:
 	drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, buffer, ret);
@@ -311,7 +317,7 @@ EXPORT_SYMBOL(drm_dp_dpcd_read);
 
 /**
  * drm_dp_dpcd_write() - write a series of bytes to the DPCD
- * @aux: DisplayPort AUX channel
+ * @aux: DisplayPort AUX channel (SST or MST)
  * @offset: address of the (first) register to write
  * @buffer: buffer containing the values to write
  * @size: number of bytes in @buffer
@@ -328,8 +334,12 @@ ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset,
 {
 	int ret;
 
-	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
-				 size);
+	if (aux->is_remote)
+		ret = drm_dp_mst_dpcd_write(aux, offset, buffer, size);
+	else
+		ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset,
+					 buffer, size);
+
 	drm_dp_dump_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, ret);
 	return ret;
 }
@@ -969,6 +979,19 @@ static void drm_dp_aux_crc_work(struct work_struct *work)
 }
 
 /**
+ * drm_dp_remote_aux_init() - minimally initialise a remote aux channel
+ * @aux: DisplayPort AUX channel
+ *
+ * Used for remote aux channel in general. Merely initialize the crc work
+ * struct.
+ */
+void drm_dp_remote_aux_init(struct drm_dp_aux *aux)
+{
+	INIT_WORK(&aux->crc_work, drm_dp_aux_crc_work);
+}
+EXPORT_SYMBOL(drm_dp_remote_aux_init);
+
+/**
  * drm_dp_aux_init() - minimally initialise an aux channel
  * @aux: DisplayPort AUX channel
  *
@@ -1155,6 +1178,8 @@ static const struct dpcd_quirk dpcd_quirk_list[] = {
 	{ OUI(0x00, 0x10, 0xfa), DEVICE_ID_ANY, false, BIT(DP_DPCD_QUIRK_NO_PSR) },
 	/* CH7511 seems to leave SINK_COUNT zeroed */
 	{ OUI(0x00, 0x00, 0x00), DEVICE_ID('C', 'H', '7', '5', '1', '1'), false, BIT(DP_DPCD_QUIRK_NO_SINK_COUNT) },
+	/* Synaptics DP1.4 MST hubs can support DSC without virtual DPCD */
+	{ OUI(0x90, 0xCC, 0x24), DEVICE_ID_ANY, true, BIT(DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) },
 };
 
 #undef OUI
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index e6afe4faeca6..20cdaf3146b8 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -76,6 +76,11 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr,
 
 static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 				    struct drm_dp_mst_branch *mstb);
+
+static void
+drm_dp_send_clear_payload_id_table(struct drm_dp_mst_topology_mgr *mgr,
+				   struct drm_dp_mst_branch *mstb);
+
 static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 					   struct drm_dp_mst_branch *mstb,
 					   struct drm_dp_mst_port *port);
@@ -517,8 +522,10 @@ drm_dp_decode_sideband_req(const struct drm_dp_sideband_msg_tx *raw,
 			}
 
 			if (failed) {
-				for (i = 0; i < r->num_transactions; i++)
+				for (i = 0; i < r->num_transactions; i++) {
+					tx = &r->transactions[i];
 					kfree(tx->bytes);
+				}
 				return -ENOMEM;
 			}
 
@@ -846,6 +853,7 @@ static bool drm_dp_sideband_parse_enum_path_resources_ack(struct drm_dp_sideband
 {
 	int idx = 1;
 	repmsg->u.path_resources.port_number = (raw->msg[idx] >> 4) & 0xf;
+	repmsg->u.path_resources.fec_capable = raw->msg[idx] & 0x1;
 	idx++;
 	if (idx > raw->curlen)
 		goto fail_len;
@@ -950,6 +958,8 @@ static bool drm_dp_sideband_parse_reply(struct drm_dp_sideband_msg_rx *raw,
 	case DP_POWER_DOWN_PHY:
 	case DP_POWER_UP_PHY:
 		return drm_dp_sideband_parse_power_updown_phy_ack(raw, msg);
+	case DP_CLEAR_PAYLOAD_ID_TABLE:
+		return true; /* since there's nothing to parse */
 	default:
 		DRM_ERROR("Got unknown reply 0x%02x (%s)\n", msg->req_type,
 			  drm_dp_mst_req_type_str(msg->req_type));
@@ -1048,6 +1058,15 @@ static int build_link_address(struct drm_dp_sideband_msg_tx *msg)
 	return 0;
 }
 
+static int build_clear_payload_id_table(struct drm_dp_sideband_msg_tx *msg)
+{
+	struct drm_dp_sideband_msg_req_body req;
+
+	req.req_type = DP_CLEAR_PAYLOAD_ID_TABLE;
+	drm_dp_encode_sideband_req(&req, msg);
+	return 0;
+}
+
 static int build_enum_path_resources(struct drm_dp_sideband_msg_tx *msg, int port_num)
 {
 	struct drm_dp_sideband_msg_req_body req;
@@ -2175,6 +2194,7 @@ drm_dp_mst_topology_unlink_port(struct drm_dp_mst_topology_mgr *mgr,
 				struct drm_dp_mst_port *port)
 {
 	mutex_lock(&mgr->lock);
+	port->parent->num_ports--;
 	list_del(&port->next);
 	mutex_unlock(&mgr->lock);
 	drm_dp_mst_topology_put_port(port);
@@ -2199,6 +2219,9 @@ drm_dp_mst_add_port(struct drm_device *dev,
 	port->aux.dev = dev->dev;
 	port->aux.is_remote = true;
 
+	/* initialize the MST downstream port's AUX crc work queue */
+	drm_dp_remote_aux_init(&port->aux);
+
 	/*
 	 * Make sure the memory allocation for our parent branch stays
 	 * around until our own memory allocation is released
@@ -2275,6 +2298,7 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
 		mutex_lock(&mgr->lock);
 		drm_dp_mst_topology_get_port(port);
 		list_add(&port->next, &mstb->ports);
+		mstb->num_ports++;
 		mutex_unlock(&mgr->lock);
 	}
 
@@ -2564,10 +2588,14 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 	struct drm_device *dev = mgr->dev;
 	struct drm_dp_mst_branch *mstb;
 	int ret;
+	bool clear_payload_id_table;
 
 	mutex_lock(&mgr->probe_lock);
 
 	mutex_lock(&mgr->lock);
+	clear_payload_id_table = !mgr->payload_id_table_cleared;
+	mgr->payload_id_table_cleared = true;
+
 	mstb = mgr->mst_primary;
 	if (mstb) {
 		ret = drm_dp_mst_topology_try_get_mstb(mstb);
@@ -2580,6 +2608,19 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 		return;
 	}
 
+	/*
+	 * Certain branch devices seem to incorrectly report an available_pbn
+	 * of 0 on downstream sinks, even after clearing the
+	 * DP_PAYLOAD_ALLOCATE_* registers in
+	 * drm_dp_mst_topology_mgr_set_mst(). Namely, the CableMatters USB-C
+	 * 2x DP hub. Sending a CLEAR_PAYLOAD_ID_TABLE message seems to make
+	 * things work again.
+	 */
+	if (clear_payload_id_table) {
+		DRM_DEBUG_KMS("Clearing payload ID table\n");
+		drm_dp_send_clear_payload_id_table(mgr, mstb);
+	}
+
 	ret = drm_dp_check_and_send_link_address(mgr, mstb);
 	drm_dp_mst_topology_put_mstb(mstb);
 
@@ -2906,6 +2947,28 @@ out:
 	return ret < 0 ? ret : changed;
 }
 
+void drm_dp_send_clear_payload_id_table(struct drm_dp_mst_topology_mgr *mgr,
+					struct drm_dp_mst_branch *mstb)
+{
+	struct drm_dp_sideband_msg_tx *txmsg;
+	int len, ret;
+
+	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
+	if (!txmsg)
+		return;
+
+	txmsg->dst = mstb;
+	len = build_clear_payload_id_table(txmsg);
+
+	drm_dp_queue_down_tx(mgr, txmsg);
+
+	ret = drm_dp_mst_wait_tx_reply(mstb, txmsg);
+	if (ret > 0 && txmsg->reply.reply_type == DP_SIDEBAND_REPLY_NAK)
+		DRM_DEBUG_KMS("clear payload table id nak received\n");
+
+	kfree(txmsg);
+}
+
 static int
 drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 				struct drm_dp_mst_branch *mstb,
@@ -2941,6 +3004,7 @@ drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 				      path_res->avail_payload_bw_number);
 			port->available_pbn =
 				path_res->avail_payload_bw_number;
+			port->fec_capable = path_res->fec_capable;
 		}
 	}
 
@@ -3435,6 +3499,7 @@ static int drm_dp_get_vc_payload_bw(u8 dp_link_bw, u8  dp_link_count)
 int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool mst_state)
 {
 	int ret = 0;
+	int i = 0;
 	struct drm_dp_mst_branch *mstb = NULL;
 
 	mutex_lock(&mgr->lock);
@@ -3495,10 +3560,23 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 		/* this can fail if the device is gone */
 		drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, 0);
 		ret = 0;
+		mutex_lock(&mgr->payload_lock);
 		memset(mgr->payloads, 0, mgr->max_payloads * sizeof(struct drm_dp_payload));
 		mgr->payload_mask = 0;
 		set_bit(0, &mgr->payload_mask);
+		for (i = 0; i < mgr->max_payloads; i++) {
+			struct drm_dp_vcpi *vcpi = mgr->proposed_vcpis[i];
+
+			if (vcpi) {
+				vcpi->vcpi = 0;
+				vcpi->num_slots = 0;
+			}
+			mgr->proposed_vcpis[i] = NULL;
+		}
 		mgr->vcpi_mask = 0;
+		mutex_unlock(&mgr->payload_lock);
+
+		mgr->payload_id_table_cleared = false;
 	}
 
 out_unlock:
@@ -4071,6 +4149,7 @@ static int drm_dp_init_vcpi(struct drm_dp_mst_topology_mgr *mgr,
  * @mgr: MST topology manager for the port
  * @port: port to find vcpi slots for
  * @pbn: bandwidth required for the mode in PBN
+ * @pbn_div: divider for DSC mode that takes FEC into account
  *
  * Allocates VCPI slots to @port, replacing any previous VCPI allocations it
  * may have had. Any atomic drivers which support MST must call this function
@@ -4097,11 +4176,12 @@ static int drm_dp_init_vcpi(struct drm_dp_mst_topology_mgr *mgr,
  */
 int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 				  struct drm_dp_mst_topology_mgr *mgr,
-				  struct drm_dp_mst_port *port, int pbn)
+				  struct drm_dp_mst_port *port, int pbn,
+				  int pbn_div)
 {
 	struct drm_dp_mst_topology_state *topology_state;
 	struct drm_dp_vcpi_allocation *pos, *vcpi = NULL;
-	int prev_slots, req_slots;
+	int prev_slots, prev_bw, req_slots;
 
 	topology_state = drm_atomic_get_mst_topology_state(state, mgr);
 	if (IS_ERR(topology_state))
@@ -4112,6 +4192,7 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 		if (pos->port == port) {
 			vcpi = pos;
 			prev_slots = vcpi->vcpi;
+			prev_bw = vcpi->pbn;
 
 			/*
 			 * This should never happen, unless the driver tries
@@ -4127,14 +4208,22 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 			break;
 		}
 	}
-	if (!vcpi)
+	if (!vcpi) {
 		prev_slots = 0;
+		prev_bw = 0;
+	}
+
+	if (pbn_div <= 0)
+		pbn_div = mgr->pbn_div;
 
-	req_slots = DIV_ROUND_UP(pbn, mgr->pbn_div);
+	req_slots = DIV_ROUND_UP(pbn, pbn_div);
 
 	DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] [MST PORT:%p] VCPI %d -> %d\n",
 			 port->connector->base.id, port->connector->name,
 			 port, prev_slots, req_slots);
+	DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] [MST PORT:%p] PBN %d -> %d\n",
+			 port->connector->base.id, port->connector->name,
+			 port, prev_bw, pbn);
 
 	/* Add the new allocation to the state */
 	if (!vcpi) {
@@ -4147,6 +4236,7 @@ int drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 		list_add(&vcpi->next, &topology_state->vcpis);
 	}
 	vcpi->vcpi = req_slots;
+	vcpi->pbn = pbn;
 
 	return req_slots;
 }
@@ -4397,10 +4487,11 @@ EXPORT_SYMBOL(drm_dp_check_act_status);
  * drm_dp_calc_pbn_mode() - Calculate the PBN for a mode.
  * @clock: dot clock for the mode
  * @bpp: bpp for the mode.
+ * @dsc: DSC mode. If true, bpp has units of 1/16 of a bit per pixel
  *
  * This uses the formula in the spec to calculate the PBN value for a mode.
  */
-int drm_dp_calc_pbn_mode(int clock, int bpp)
+int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc)
 {
 	/*
 	 * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006
@@ -4411,7 +4502,16 @@ int drm_dp_calc_pbn_mode(int clock, int bpp)
 	 * peak_kbps *= (1006/1000)
 	 * peak_kbps *= (64/54)
 	 * peak_kbps *= 8    convert to bytes
+	 *
+	 * If the bpp is in units of 1/16, further divide by 16. Put this
+	 * factor in the numerator rather than the denominator to avoid
+	 * integer overflow
 	 */
+
+	if (dsc)
+		return DIV_ROUND_UP_ULL(mul_u32_u32(clock * (bpp / 16), 64 * 1006),
+					8 * 54 * 1000 * 1000);
+
 	return DIV_ROUND_UP_ULL(mul_u32_u32(clock * bpp, 64 * 1006),
 				8 * 54 * 1000 * 1000);
 }
@@ -4713,9 +4813,61 @@ static void drm_dp_mst_destroy_state(struct drm_private_obj *obj,
 	kfree(mst_state);
 }
 
+static bool drm_dp_mst_port_downstream_of_branch(struct drm_dp_mst_port *port,
+						 struct drm_dp_mst_branch *branch)
+{
+	while (port->parent) {
+		if (port->parent == branch)
+			return true;
+
+		if (port->parent->port_parent)
+			port = port->parent->port_parent;
+		else
+			break;
+	}
+	return false;
+}
+
+static inline
+int drm_dp_mst_atomic_check_bw_limit(struct drm_dp_mst_branch *branch,
+				     struct drm_dp_mst_topology_state *mst_state)
+{
+	struct drm_dp_mst_port *port;
+	struct drm_dp_vcpi_allocation *vcpi;
+	int pbn_limit = 0, pbn_used = 0;
+
+	list_for_each_entry(port, &branch->ports, next) {
+		if (port->mstb)
+			if (drm_dp_mst_atomic_check_bw_limit(port->mstb, mst_state))
+				return -ENOSPC;
+
+		if (port->available_pbn > 0)
+			pbn_limit = port->available_pbn;
+	}
+	DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch has %d PBN available\n",
+			 branch, pbn_limit);
+
+	list_for_each_entry(vcpi, &mst_state->vcpis, next) {
+		if (!vcpi->pbn)
+			continue;
+
+		if (drm_dp_mst_port_downstream_of_branch(vcpi->port, branch))
+			pbn_used += vcpi->pbn;
+	}
+	DRM_DEBUG_ATOMIC("[MST BRANCH:%p] branch used %d PBN\n",
+			 branch, pbn_used);
+
+	if (pbn_used > pbn_limit) {
+		DRM_DEBUG_ATOMIC("[MST BRANCH:%p] No available bandwidth\n",
+				 branch);
+		return -ENOSPC;
+	}
+	return 0;
+}
+
 static inline int
-drm_dp_mst_atomic_check_topology_state(struct drm_dp_mst_topology_mgr *mgr,
-				       struct drm_dp_mst_topology_state *mst_state)
+drm_dp_mst_atomic_check_vcpi_alloc_limit(struct drm_dp_mst_topology_mgr *mgr,
+					 struct drm_dp_mst_topology_state *mst_state)
 {
 	struct drm_dp_vcpi_allocation *vcpi;
 	int avail_slots = 63, payload_count = 0;
@@ -4753,6 +4905,128 @@ drm_dp_mst_atomic_check_topology_state(struct drm_dp_mst_topology_mgr *mgr,
 }
 
 /**
+ * drm_dp_mst_add_affected_dsc_crtcs
+ * @state: Pointer to the new struct drm_dp_mst_topology_state
+ * @mgr: MST topology manager
+ *
+ * Whenever there is a change in mst topology
+ * DSC configuration would have to be recalculated
+ * therefore we need to trigger modeset on all affected
+ * CRTCs in that topology
+ *
+ * See also:
+ * drm_dp_mst_atomic_enable_dsc()
+ */
+int drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state, struct drm_dp_mst_topology_mgr *mgr)
+{
+	struct drm_dp_mst_topology_state *mst_state;
+	struct drm_dp_vcpi_allocation *pos;
+	struct drm_connector *connector;
+	struct drm_connector_state *conn_state;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+
+	mst_state = drm_atomic_get_mst_topology_state(state, mgr);
+
+	if (IS_ERR(mst_state))
+		return -EINVAL;
+
+	list_for_each_entry(pos, &mst_state->vcpis, next) {
+
+		connector = pos->port->connector;
+
+		if (!connector)
+			return -EINVAL;
+
+		conn_state = drm_atomic_get_connector_state(state, connector);
+
+		if (IS_ERR(conn_state))
+			return PTR_ERR(conn_state);
+
+		crtc = conn_state->crtc;
+
+		if (WARN_ON(!crtc))
+			return -EINVAL;
+
+		if (!drm_dp_mst_dsc_aux_for_port(pos->port))
+			continue;
+
+		crtc_state = drm_atomic_get_crtc_state(mst_state->base.state, crtc);
+
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+
+		DRM_DEBUG_ATOMIC("[MST MGR:%p] Setting mode_changed flag on CRTC %p\n",
+				 mgr, crtc);
+
+		crtc_state->mode_changed = true;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(drm_dp_mst_add_affected_dsc_crtcs);
+
+/**
+ * drm_dp_mst_atomic_enable_dsc - Set DSC Enable Flag to On/Off
+ * @state: Pointer to the new drm_atomic_state
+ * @port: Pointer to the affected MST Port
+ * @pbn: Newly recalculated bw required for link with DSC enabled
+ * @pbn_div: Divider to calculate correct number of pbn per slot
+ * @enable: Boolean flag to enable or disable DSC on the port
+ *
+ * This function enables DSC on the given Port
+ * by recalculating its vcpi from pbn provided
+ * and sets dsc_enable flag to keep track of which
+ * ports have DSC enabled
+ *
+ */
+int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state,
+				 struct drm_dp_mst_port *port,
+				 int pbn, int pbn_div,
+				 bool enable)
+{
+	struct drm_dp_mst_topology_state *mst_state;
+	struct drm_dp_vcpi_allocation *pos;
+	bool found = false;
+	int vcpi = 0;
+
+	mst_state = drm_atomic_get_mst_topology_state(state, port->mgr);
+
+	if (IS_ERR(mst_state))
+		return PTR_ERR(mst_state);
+
+	list_for_each_entry(pos, &mst_state->vcpis, next) {
+		if (pos->port == port) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		DRM_DEBUG_ATOMIC("[MST PORT:%p] Couldn't find VCPI allocation in mst state %p\n",
+				 port, mst_state);
+		return -EINVAL;
+	}
+
+	if (pos->dsc_enabled == enable) {
+		DRM_DEBUG_ATOMIC("[MST PORT:%p] DSC flag is already set to %d, returning %d VCPI slots\n",
+				 port, enable, pos->vcpi);
+		vcpi = pos->vcpi;
+	}
+
+	if (enable) {
+		vcpi = drm_dp_atomic_find_vcpi_slots(state, port->mgr, port, pbn, pbn_div);
+		DRM_DEBUG_ATOMIC("[MST PORT:%p] Enabling DSC flag, reallocating %d VCPI slots on the port\n",
+				 port, vcpi);
+		if (vcpi < 0)
+			return -EINVAL;
+	}
+
+	pos->dsc_enabled = enable;
+
+	return vcpi;
+}
+EXPORT_SYMBOL(drm_dp_mst_atomic_enable_dsc);
+/**
  * drm_dp_mst_atomic_check - Check that the new state of an MST topology in an
  * atomic update is valid
  * @state: Pointer to the new &struct drm_dp_mst_topology_state
@@ -4780,7 +5054,13 @@ int drm_dp_mst_atomic_check(struct drm_atomic_state *state)
 	int i, ret = 0;
 
 	for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) {
-		ret = drm_dp_mst_atomic_check_topology_state(mgr, mst_state);
+		if (!mgr->mst_state)
+			continue;
+
+		ret = drm_dp_mst_atomic_check_vcpi_alloc_limit(mgr, mst_state);
+		if (ret)
+			break;
+		ret = drm_dp_mst_atomic_check_bw_limit(mgr->mst_primary, mst_state);
 		if (ret)
 			break;
 	}
@@ -5044,3 +5324,173 @@ static void drm_dp_mst_unregister_i2c_bus(struct drm_dp_aux *aux)
 {
 	i2c_del_adapter(&aux->ddc);
 }
+
+/**
+ * drm_dp_mst_is_virtual_dpcd() - Is the given port a virtual DP Peer Device
+ * @port: The port to check
+ *
+ * A single physical MST hub object can be represented in the topology
+ * by multiple branches, with virtual ports between those branches.
+ *
+ * As of DP1.4, An MST hub with internal (virtual) ports must expose
+ * certain DPCD registers over those ports. See sections 2.6.1.1.1
+ * and 2.6.1.1.2 of Display Port specification v1.4 for details.
+ *
+ * May acquire mgr->lock
+ *
+ * Returns:
+ * true if the port is a virtual DP peer device, false otherwise
+ */
+static bool drm_dp_mst_is_virtual_dpcd(struct drm_dp_mst_port *port)
+{
+	struct drm_dp_mst_port *downstream_port;
+
+	if (!port || port->dpcd_rev < DP_DPCD_REV_14)
+		return false;
+
+	/* Virtual DP Sink (Internal Display Panel) */
+	if (port->port_num >= 8)
+		return true;
+
+	/* DP-to-HDMI Protocol Converter */
+	if (port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV &&
+	    !port->mcs &&
+	    port->ldps)
+		return true;
+
+	/* DP-to-DP */
+	mutex_lock(&port->mgr->lock);
+	if (port->pdt == DP_PEER_DEVICE_MST_BRANCHING &&
+	    port->mstb &&
+	    port->mstb->num_ports == 2) {
+		list_for_each_entry(downstream_port, &port->mstb->ports, next) {
+			if (downstream_port->pdt == DP_PEER_DEVICE_SST_SINK &&
+			    !downstream_port->input) {
+				mutex_unlock(&port->mgr->lock);
+				return true;
+			}
+		}
+	}
+	mutex_unlock(&port->mgr->lock);
+
+	return false;
+}
+
+/**
+ * drm_dp_mst_dsc_aux_for_port() - Find the correct aux for DSC
+ * @port: The port to check. A leaf of the MST tree with an attached display.
+ *
+ * Depending on the situation, DSC may be enabled via the endpoint aux,
+ * the immediately upstream aux, or the connector's physical aux.
+ *
+ * This is both the correct aux to read DSC_CAPABILITY and the
+ * correct aux to write DSC_ENABLED.
+ *
+ * This operation can be expensive (up to four aux reads), so
+ * the caller should cache the return.
+ *
+ * Returns:
+ * NULL if DSC cannot be enabled on this port, otherwise the aux device
+ */
+struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port)
+{
+	struct drm_dp_mst_port *immediate_upstream_port;
+	struct drm_dp_mst_port *fec_port;
+	struct drm_dp_desc desc = { 0 };
+	u8 endpoint_fec;
+	u8 endpoint_dsc;
+
+	if (!port)
+		return NULL;
+
+	if (port->parent->port_parent)
+		immediate_upstream_port = port->parent->port_parent;
+	else
+		immediate_upstream_port = NULL;
+
+	fec_port = immediate_upstream_port;
+	while (fec_port) {
+		/*
+		 * Each physical link (i.e. not a virtual port) between the
+		 * output and the primary device must support FEC
+		 */
+		if (!drm_dp_mst_is_virtual_dpcd(fec_port) &&
+		    !fec_port->fec_capable)
+			return NULL;
+
+		fec_port = fec_port->parent->port_parent;
+	}
+
+	/* DP-to-DP peer device */
+	if (drm_dp_mst_is_virtual_dpcd(immediate_upstream_port)) {
+		u8 upstream_dsc;
+
+		if (drm_dp_dpcd_read(&port->aux,
+				     DP_DSC_SUPPORT, &endpoint_dsc, 1) != 1)
+			return NULL;
+		if (drm_dp_dpcd_read(&port->aux,
+				     DP_FEC_CAPABILITY, &endpoint_fec, 1) != 1)
+			return NULL;
+		if (drm_dp_dpcd_read(&immediate_upstream_port->aux,
+				     DP_DSC_SUPPORT, &upstream_dsc, 1) != 1)
+			return NULL;
+
+		/* Enpoint decompression with DP-to-DP peer device */
+		if ((endpoint_dsc & DP_DSC_DECOMPRESSION_IS_SUPPORTED) &&
+		    (endpoint_fec & DP_FEC_CAPABLE) &&
+		    (upstream_dsc & 0x2) /* DSC passthrough */)
+			return &port->aux;
+
+		/* Virtual DPCD decompression with DP-to-DP peer device */
+		return &immediate_upstream_port->aux;
+	}
+
+	/* Virtual DPCD decompression with DP-to-HDMI or Virtual DP Sink */
+	if (drm_dp_mst_is_virtual_dpcd(port))
+		return &port->aux;
+
+	/*
+	 * Synaptics quirk
+	 * Applies to ports for which:
+	 * - Physical aux has Synaptics OUI
+	 * - DPv1.4 or higher
+	 * - Port is on primary branch device
+	 * - Not a VGA adapter (DP_DWN_STRM_PORT_TYPE_ANALOG)
+	 */
+	if (drm_dp_read_desc(port->mgr->aux, &desc, true))
+		return NULL;
+
+	if (drm_dp_has_quirk(&desc, DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD) &&
+	    port->mgr->dpcd[DP_DPCD_REV] >= DP_DPCD_REV_14 &&
+	    port->parent == port->mgr->mst_primary) {
+		u8 downstreamport;
+
+		if (drm_dp_dpcd_read(&port->aux, DP_DOWNSTREAMPORT_PRESENT,
+				     &downstreamport, 1) < 0)
+			return NULL;
+
+		if ((downstreamport & DP_DWN_STRM_PORT_PRESENT) &&
+		   ((downstreamport & DP_DWN_STRM_PORT_TYPE_MASK)
+		     != DP_DWN_STRM_PORT_TYPE_ANALOG))
+			return port->mgr->aux;
+	}
+
+	/*
+	 * The check below verifies if the MST sink
+	 * connected to the GPU is capable of DSC -
+	 * therefore the endpoint needs to be
+	 * both DSC and FEC capable.
+	 */
+	if (drm_dp_dpcd_read(&port->aux,
+	   DP_DSC_SUPPORT, &endpoint_dsc, 1) != 1)
+		return NULL;
+	if (drm_dp_dpcd_read(&port->aux,
+	   DP_FEC_CAPABILITY, &endpoint_fec, 1) != 1)
+		return NULL;
+	if ((endpoint_dsc & DP_DSC_DECOMPRESSION_IS_SUPPORTED) &&
+	   (endpoint_fec & DP_FEC_CAPABLE))
+		return &port->aux;
+
+	return NULL;
+}
+EXPORT_SYMBOL(drm_dp_mst_dsc_aux_for_port);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 1b9b40a1c7c9..7c18a980cd4b 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -622,7 +622,8 @@ int drm_dev_init(struct drm_device *dev,
 		return -ENODEV;
 	}
 
-	BUG_ON(!parent);
+	if (WARN_ON(!parent))
+		return -EINVAL;
 
 	kref_init(&dev->ref);
 	dev->dev = get_device(parent);
@@ -725,7 +726,7 @@ int devm_drm_dev_init(struct device *parent,
 {
 	int ret;
 
-	if (WARN_ON(!parent || !driver->release))
+	if (WARN_ON(!driver->release))
 		return -EINVAL;
 
 	ret = drm_dev_init(dev, driver, parent);
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 474ac04d5600..99769d6c9f84 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -710,14 +710,11 @@ static const struct minimode extra_modes[] = {
 };
 
 /*
- * Probably taken from CEA-861 spec.
- * This table is converted from xorg's hw/xfree86/modes/xf86EdidModes.c.
+ * From CEA/CTA-861 spec.
  *
- * Index using the VIC.
+ * Do not access directly, instead always use cea_mode_for_vic().
  */
-static const struct drm_display_mode edid_cea_modes[] = {
-	/* 0 - dummy, VICs start at 1 */
-	{ },
+static const struct drm_display_mode edid_cea_modes_1[] = {
 	/* 1 - 640x480@60Hz 4:3 */
 	{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
 		   752, 800, 0, 480, 490, 492, 525, 0,
@@ -1381,6 +1378,149 @@ static const struct drm_display_mode edid_cea_modes[] = {
 };
 
 /*
+ * From CEA/CTA-861 spec.
+ *
+ * Do not access directly, instead always use cea_mode_for_vic().
+ */
+static const struct drm_display_mode edid_cea_modes_193[] = {
+	/* 193 - 5120x2160@120Hz 64:27 */
+	{ DRM_MODE("5120x2160", DRM_MODE_TYPE_DRIVER, 1485000, 5120, 5284,
+		   5372, 5500, 0, 2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 194 - 7680x4320@24Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 195 - 7680x4320@25Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 196 - 7680x4320@30Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 197 - 7680x4320@48Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 48, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 198 - 7680x4320@50Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 199 - 7680x4320@60Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 200 - 7680x4320@100Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 9792,
+		   9968, 10560, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 201 - 7680x4320@120Hz 16:9 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 8032,
+		   8208, 8800, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 202 - 7680x4320@24Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 203 - 7680x4320@25Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 204 - 7680x4320@30Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 1188000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 205 - 7680x4320@48Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10232,
+		   10408, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 48, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 206 - 7680x4320@50Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 10032,
+		   10208, 10800, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 207 - 7680x4320@60Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 2376000, 7680, 8232,
+		   8408, 9000, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 208 - 7680x4320@100Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 9792,
+		   9968, 10560, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 209 - 7680x4320@120Hz 64:27 */
+	{ DRM_MODE("7680x4320", DRM_MODE_TYPE_DRIVER, 4752000, 7680, 8032,
+		   8208, 8800, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 210 - 10240x4320@24Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 1485000, 10240, 11732,
+		   11908, 12500, 0, 4320, 4336, 4356, 4950, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 211 - 10240x4320@25Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 1485000, 10240, 12732,
+		   12908, 13500, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 212 - 10240x4320@30Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 1485000, 10240, 10528,
+		   10704, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 213 - 10240x4320@48Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 2970000, 10240, 11732,
+		   11908, 12500, 0, 4320, 4336, 4356, 4950, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 48, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 214 - 10240x4320@50Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 2970000, 10240, 12732,
+		   12908, 13500, 0, 4320, 4336, 4356, 4400, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 215 - 10240x4320@60Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 2970000, 10240, 10528,
+		   10704, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 216 - 10240x4320@100Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 5940000, 10240, 12432,
+		   12608, 13200, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 217 - 10240x4320@120Hz 64:27 */
+	{ DRM_MODE("10240x4320", DRM_MODE_TYPE_DRIVER, 5940000, 10240, 10528,
+		   10704, 11000, 0, 4320, 4336, 4356, 4500, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
+	/* 218 - 4096x2160@100Hz 256:135 */
+	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 1188000, 4096, 4896,
+		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
+	/* 219 - 4096x2160@120Hz 256:135 */
+	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 1188000, 4096, 4184,
+		   4272, 4400, 0, 2160, 2168, 2178, 2250, 0,
+		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
+};
+
+/*
  * HDMI 1.4 4k modes. Index using the VIC.
  */
 static const struct drm_display_mode edid_4k_modes[] = {
@@ -1391,25 +1531,25 @@ static const struct drm_display_mode edid_4k_modes[] = {
 		   3840, 4016, 4104, 4400, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 30, },
+	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 2 - 3840x2160@25Hz */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
 		   3840, 4896, 4984, 5280, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 25, },
+	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 3 - 3840x2160@24Hz */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000,
 		   3840, 5116, 5204, 5500, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 24, },
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
 	/* 4 - 4096x2160@24Hz (SMPTE) */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000,
 		   4096, 5116, 5204, 5500, 0,
 		   2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	  .vrefresh = 24, },
+	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
 };
 
 /*** DDC fetch and block validation ***/
@@ -3071,6 +3211,30 @@ static u8 *drm_find_cea_extension(const struct edid *edid)
 	return cea;
 }
 
+static const struct drm_display_mode *cea_mode_for_vic(u8 vic)
+{
+	BUILD_BUG_ON(1 + ARRAY_SIZE(edid_cea_modes_1) - 1 != 127);
+	BUILD_BUG_ON(193 + ARRAY_SIZE(edid_cea_modes_193) - 1 != 219);
+
+	if (vic >= 1 && vic < 1 + ARRAY_SIZE(edid_cea_modes_1))
+		return &edid_cea_modes_1[vic - 1];
+	if (vic >= 193 && vic < 193 + ARRAY_SIZE(edid_cea_modes_193))
+		return &edid_cea_modes_193[vic - 193];
+	return NULL;
+}
+
+static u8 cea_num_vics(void)
+{
+	return 193 + ARRAY_SIZE(edid_cea_modes_193);
+}
+
+static u8 cea_next_vic(u8 vic)
+{
+	if (++vic == 1 + ARRAY_SIZE(edid_cea_modes_1))
+		vic = 193;
+	return vic;
+}
+
 /*
  * Calculate the alternate clock for the CEA mode
  * (60Hz vs. 59.94Hz etc.)
@@ -3108,14 +3272,14 @@ cea_mode_alternate_timings(u8 vic, struct drm_display_mode *mode)
 	 * get the other variants by simply increasing the
 	 * vertical front porch length.
 	 */
-	BUILD_BUG_ON(edid_cea_modes[8].vtotal != 262 ||
-		     edid_cea_modes[9].vtotal != 262 ||
-		     edid_cea_modes[12].vtotal != 262 ||
-		     edid_cea_modes[13].vtotal != 262 ||
-		     edid_cea_modes[23].vtotal != 312 ||
-		     edid_cea_modes[24].vtotal != 312 ||
-		     edid_cea_modes[27].vtotal != 312 ||
-		     edid_cea_modes[28].vtotal != 312);
+	BUILD_BUG_ON(cea_mode_for_vic(8)->vtotal != 262 ||
+		     cea_mode_for_vic(9)->vtotal != 262 ||
+		     cea_mode_for_vic(12)->vtotal != 262 ||
+		     cea_mode_for_vic(13)->vtotal != 262 ||
+		     cea_mode_for_vic(23)->vtotal != 312 ||
+		     cea_mode_for_vic(24)->vtotal != 312 ||
+		     cea_mode_for_vic(27)->vtotal != 312 ||
+		     cea_mode_for_vic(28)->vtotal != 312);
 
 	if (((vic == 8 || vic == 9 ||
 	      vic == 12 || vic == 13) && mode->vtotal < 263) ||
@@ -3143,8 +3307,8 @@ static u8 drm_match_cea_mode_clock_tolerance(const struct drm_display_mode *to_m
 	if (to_match->picture_aspect_ratio)
 		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
 
-	for (vic = 1; vic < ARRAY_SIZE(edid_cea_modes); vic++) {
-		struct drm_display_mode cea_mode = edid_cea_modes[vic];
+	for (vic = 1; vic < cea_num_vics(); vic = cea_next_vic(vic)) {
+		struct drm_display_mode cea_mode = *cea_mode_for_vic(vic);
 		unsigned int clock1, clock2;
 
 		/* Check both 60Hz and 59.94Hz */
@@ -3182,8 +3346,8 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match)
 	if (to_match->picture_aspect_ratio)
 		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
 
-	for (vic = 1; vic < ARRAY_SIZE(edid_cea_modes); vic++) {
-		struct drm_display_mode cea_mode = edid_cea_modes[vic];
+	for (vic = 1; vic < cea_num_vics(); vic = cea_next_vic(vic)) {
+		struct drm_display_mode cea_mode = *cea_mode_for_vic(vic);
 		unsigned int clock1, clock2;
 
 		/* Check both 60Hz and 59.94Hz */
@@ -3206,28 +3370,31 @@ EXPORT_SYMBOL(drm_match_cea_mode);
 
 static bool drm_valid_cea_vic(u8 vic)
 {
-	return vic > 0 && vic < ARRAY_SIZE(edid_cea_modes);
+	return cea_mode_for_vic(vic) != NULL;
 }
 
 static enum hdmi_picture_aspect drm_get_cea_aspect_ratio(const u8 video_code)
 {
-	return edid_cea_modes[video_code].picture_aspect_ratio;
+	const struct drm_display_mode *mode = cea_mode_for_vic(video_code);
+
+	if (mode)
+		return mode->picture_aspect_ratio;
+
+	return HDMI_PICTURE_ASPECT_NONE;
+}
+
+static enum hdmi_picture_aspect drm_get_hdmi_aspect_ratio(const u8 video_code)
+{
+	return edid_4k_modes[video_code].picture_aspect_ratio;
 }
 
 /*
  * Calculate the alternate clock for HDMI modes (those from the HDMI vendor
  * specific block).
- *
- * It's almost like cea_mode_alternate_clock(), we just need to add an
- * exception for the VIC 4 mode (4096x2160@24Hz): no alternate clock for this
- * one.
  */
 static unsigned int
 hdmi_mode_alternate_clock(const struct drm_display_mode *hdmi_mode)
 {
-	if (hdmi_mode->vdisplay == 4096 && hdmi_mode->hdisplay == 2160)
-		return hdmi_mode->clock;
-
 	return cea_mode_alternate_clock(hdmi_mode);
 }
 
@@ -3240,6 +3407,9 @@ static u8 drm_match_hdmi_mode_clock_tolerance(const struct drm_display_mode *to_
 	if (!to_match->clock)
 		return 0;
 
+	if (to_match->picture_aspect_ratio)
+		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
+
 	for (vic = 1; vic < ARRAY_SIZE(edid_4k_modes); vic++) {
 		const struct drm_display_mode *hdmi_mode = &edid_4k_modes[vic];
 		unsigned int clock1, clock2;
@@ -3275,6 +3445,9 @@ static u8 drm_match_hdmi_mode(const struct drm_display_mode *to_match)
 	if (!to_match->clock)
 		return 0;
 
+	if (to_match->picture_aspect_ratio)
+		match_flags |= DRM_MODE_MATCH_ASPECT_RATIO;
+
 	for (vic = 1; vic < ARRAY_SIZE(edid_4k_modes); vic++) {
 		const struct drm_display_mode *hdmi_mode = &edid_4k_modes[vic];
 		unsigned int clock1, clock2;
@@ -3319,7 +3492,7 @@ add_alternate_cea_modes(struct drm_connector *connector, struct edid *edid)
 		unsigned int clock1, clock2;
 
 		if (drm_valid_cea_vic(vic)) {
-			cea_mode = &edid_cea_modes[vic];
+			cea_mode = cea_mode_for_vic(vic);
 			clock2 = cea_mode_alternate_clock(cea_mode);
 		} else {
 			vic = drm_match_hdmi_mode(mode);
@@ -3394,7 +3567,7 @@ drm_display_mode_from_vic_index(struct drm_connector *connector,
 	if (!drm_valid_cea_vic(vic))
 		return NULL;
 
-	newmode = drm_mode_duplicate(dev, &edid_cea_modes[vic]);
+	newmode = drm_mode_duplicate(dev, cea_mode_for_vic(vic));
 	if (!newmode)
 		return NULL;
 
@@ -3428,7 +3601,7 @@ static int do_y420vdb_modes(struct drm_connector *connector,
 		if (!drm_valid_cea_vic(vic))
 			continue;
 
-		newmode = drm_mode_duplicate(dev, &edid_cea_modes[vic]);
+		newmode = drm_mode_duplicate(dev, cea_mode_for_vic(vic));
 		if (!newmode)
 			break;
 		bitmap_set(hdmi->y420_vdb_modes, vic, 1);
@@ -3997,7 +4170,7 @@ static void fixup_detailed_cea_mode_clock(struct drm_display_mode *mode)
 	vic = drm_match_cea_mode_clock_tolerance(mode, 5);
 	if (drm_valid_cea_vic(vic)) {
 		type = "CEA";
-		cea_mode = &edid_cea_modes[vic];
+		cea_mode = cea_mode_for_vic(vic);
 		clock1 = cea_mode->clock;
 		clock2 = cea_mode_alternate_clock(cea_mode);
 	} else {
@@ -4279,12 +4452,12 @@ int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads)
 	cea = drm_find_cea_extension(edid);
 	if (!cea) {
 		DRM_DEBUG_KMS("SAD: no CEA Extension found\n");
-		return -ENOENT;
+		return 0;
 	}
 
 	if (cea_revision(cea) < 3) {
 		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
-		return -EOPNOTSUPP;
+		return 0;
 	}
 
 	if (cea_db_offsets(cea, &start, &end)) {
@@ -4340,12 +4513,12 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
 	cea = drm_find_cea_extension(edid);
 	if (!cea) {
 		DRM_DEBUG_KMS("SAD: no CEA Extension found\n");
-		return -ENOENT;
+		return 0;
 	}
 
 	if (cea_revision(cea) < 3) {
 		DRM_DEBUG_KMS("SAD: wrong CEA revision\n");
-		return -EOPNOTSUPP;
+		return 0;
 	}
 
 	if (cea_db_offsets(cea, &start, &end)) {
@@ -4573,7 +4746,7 @@ static void drm_parse_hdmi_forum_vsdb(struct drm_connector *connector,
 		if (scdc->supported) {
 			scdc->scrambling.supported = true;
 
-			/* Few sinks support scrambling for cloks < 340M */
+			/* Few sinks support scrambling for clocks < 340M */
 			if ((hf_vsdb[6] & 0x8))
 				scdc->scrambling.low_rates = true;
 		}
@@ -5222,6 +5395,7 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 					 const struct drm_display_mode *mode)
 {
 	enum hdmi_picture_aspect picture_aspect;
+	u8 vic, hdmi_vic;
 	int err;
 
 	if (!frame || !mode)
@@ -5234,7 +5408,8 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		frame->pixel_repeat = 1;
 
-	frame->video_code = drm_mode_cea_vic(connector, mode);
+	vic = drm_mode_cea_vic(connector, mode);
+	hdmi_vic = drm_mode_hdmi_vic(connector, mode);
 
 	frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 
@@ -5248,11 +5423,15 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 
 	/*
 	 * Populate picture aspect ratio from either
-	 * user input (if specified) or from the CEA mode list.
+	 * user input (if specified) or from the CEA/HDMI mode lists.
 	 */
 	picture_aspect = mode->picture_aspect_ratio;
-	if (picture_aspect == HDMI_PICTURE_ASPECT_NONE)
-		picture_aspect = drm_get_cea_aspect_ratio(frame->video_code);
+	if (picture_aspect == HDMI_PICTURE_ASPECT_NONE) {
+		if (vic)
+			picture_aspect = drm_get_cea_aspect_ratio(vic);
+		else if (hdmi_vic)
+			picture_aspect = drm_get_hdmi_aspect_ratio(hdmi_vic);
+	}
 
 	/*
 	 * The infoframe can't convey anything but none, 4:3
@@ -5260,12 +5439,20 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 	 * we can only satisfy it by specifying the right VIC.
 	 */
 	if (picture_aspect > HDMI_PICTURE_ASPECT_16_9) {
-		if (picture_aspect !=
-		    drm_get_cea_aspect_ratio(frame->video_code))
+		if (vic) {
+			if (picture_aspect != drm_get_cea_aspect_ratio(vic))
+				return -EINVAL;
+		} else if (hdmi_vic) {
+			if (picture_aspect != drm_get_hdmi_aspect_ratio(hdmi_vic))
+				return -EINVAL;
+		} else {
 			return -EINVAL;
+		}
+
 		picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 	}
 
+	frame->video_code = vic;
 	frame->picture_aspect = picture_aspect;
 	frame->active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
 	frame->scan_mode = HDMI_SCAN_MODE_UNDERSCAN;
diff --git a/drivers/gpu/drm/drm_encoder.c b/drivers/gpu/drm/drm_encoder.c
index 80d88a55302e..e555281f43d4 100644
--- a/drivers/gpu/drm/drm_encoder.c
+++ b/drivers/gpu/drm/drm_encoder.c
@@ -140,6 +140,7 @@ int drm_encoder_init(struct drm_device *dev,
 		goto out_put;
 	}
 
+	INIT_LIST_HEAD(&encoder->bridge_chain);
 	list_add_tail(&encoder->head, &dev->mode_config.encoder_list);
 	encoder->index = dev->mode_config.num_encoder++;
 
@@ -160,22 +161,16 @@ EXPORT_SYMBOL(drm_encoder_init);
 void drm_encoder_cleanup(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
+	struct drm_bridge *bridge, *next;
 
 	/* Note that the encoder_list is considered to be static; should we
 	 * remove the drm_encoder at runtime we would have to decrement all
 	 * the indices on the drm_encoder after us in the encoder_list.
 	 */
 
-	if (encoder->bridge) {
-		struct drm_bridge *bridge = encoder->bridge;
-		struct drm_bridge *next;
-
-		while (bridge) {
-			next = bridge->next;
-			drm_bridge_detach(bridge);
-			bridge = next;
-		}
-	}
+	list_for_each_entry_safe(bridge, next, &encoder->bridge_chain,
+				 chain_node)
+		drm_bridge_detach(bridge);
 
 	drm_mode_object_unregister(dev, &encoder->base);
 	kfree(encoder->name);
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index c0b0f603af63..9801c0333eca 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -9,6 +9,7 @@
  *  Copyright (C) 2012 Red Hat
  */
 
+#include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_cma_helper.h>
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d8e8f3960f4d..4c7cbce7bae7 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -95,10 +95,6 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  * It will automatically set up deferred I/O if the driver requires a shadow
  * buffer.
  *
- * For other drivers, setup fbdev emulation by calling
- * drm_fb_helper_fbdev_setup() and tear it down by calling
- * drm_fb_helper_fbdev_teardown().
- *
  * At runtime drivers should restore the fbdev console by using
  * drm_fb_helper_lastclose() as their &drm_driver.lastclose callback.
  * They should also notify the fb helper code from updates to the output
@@ -195,6 +191,7 @@ int drm_fb_helper_debug_leave(struct fb_info *info)
 {
 	struct drm_fb_helper *helper = info->par;
 	struct drm_client_dev *client = &helper->client;
+	struct drm_device *dev = helper->dev;
 	struct drm_crtc *crtc;
 	const struct drm_crtc_helper_funcs *funcs;
 	struct drm_mode_set *mode_set;
@@ -213,7 +210,7 @@ int drm_fb_helper_debug_leave(struct fb_info *info)
 			continue;
 
 		if (!fb) {
-			DRM_ERROR("no fb to restore??\n");
+			drm_err(dev, "no fb to restore?\n");
 			continue;
 		}
 
@@ -567,8 +564,7 @@ EXPORT_SYMBOL(drm_fb_helper_unregister_fbi);
  * drm_fb_helper_fini - finialize a &struct drm_fb_helper
  * @fb_helper: driver-allocated fbdev helper, can be NULL
  *
- * This cleans up all remaining resources associated with @fb_helper. Must be
- * called after drm_fb_helper_unlink_fbi() was called.
+ * This cleans up all remaining resources associated with @fb_helper.
  */
 void drm_fb_helper_fini(struct drm_fb_helper *fb_helper)
 {
@@ -608,19 +604,6 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper)
 }
 EXPORT_SYMBOL(drm_fb_helper_fini);
 
-/**
- * drm_fb_helper_unlink_fbi - wrapper around unlink_framebuffer
- * @fb_helper: driver-allocated fbdev helper, can be NULL
- *
- * A wrapper around unlink_framebuffer implemented by fbdev core
- */
-void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper)
-{
-	if (fb_helper && fb_helper->fbdev)
-		unlink_framebuffer(fb_helper->fbdev);
-}
-EXPORT_SYMBOL(drm_fb_helper_unlink_fbi);
-
 static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper)
 {
 	struct drm_device *dev = fb_helper->dev;
@@ -1266,12 +1249,13 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 {
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev = fb_helper->dev;
 
 	if (in_dbg_master())
 		return -EINVAL;
 
 	if (var->pixclock != 0) {
-		DRM_DEBUG("fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n");
+		drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n");
 		var->pixclock = 0;
 	}
 
@@ -1286,7 +1270,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	if (var->bits_per_pixel > fb->format->cpp[0] * 8 ||
 	    var->xres > fb->width || var->yres > fb->height ||
 	    var->xres_virtual > fb->width || var->yres_virtual > fb->height) {
-		DRM_DEBUG("fb requested width/height/bpp can't fit in current fb "
+		drm_dbg_kms(dev, "fb requested width/height/bpp can't fit in current fb "
 			  "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n",
 			  var->xres, var->yres, var->bits_per_pixel,
 			  var->xres_virtual, var->yres_virtual,
@@ -1318,7 +1302,7 @@ int drm_fb_helper_check_var(struct fb_var_screeninfo *var,
 	 * so reject all pixel format changing requests.
 	 */
 	if (!drm_fb_pixel_format_equal(var, &info->var)) {
-		DRM_DEBUG("fbdev emulation doesn't support changing the pixel format\n");
+		drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel format\n");
 		return -EINVAL;
 	}
 
@@ -1343,7 +1327,7 @@ int drm_fb_helper_set_par(struct fb_info *info)
 		return -EBUSY;
 
 	if (var->pixclock != 0) {
-		DRM_ERROR("PIXEL CLOCK SET\n");
+		drm_err(fb_helper->dev, "PIXEL CLOCK SET\n");
 		return -EINVAL;
 	}
 
@@ -1453,6 +1437,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 					 int preferred_bpp)
 {
 	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_device *dev = fb_helper->dev;
 	int ret = 0;
 	int crtc_count = 0;
 	struct drm_connector_list_iter conn_iter;
@@ -1516,7 +1501,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		struct drm_plane *plane = crtc->primary;
 		int j;
 
-		DRM_DEBUG("test CRTC %u primary plane\n", drm_crtc_index(crtc));
+		drm_dbg_kms(dev, "test CRTC %u primary plane\n", drm_crtc_index(crtc));
 
 		for (j = 0; j < plane->format_count; j++) {
 			const struct drm_format_info *fmt;
@@ -1549,7 +1534,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		}
 	}
 	if (sizes.surface_depth != best_depth && best_depth) {
-		DRM_INFO("requested bpp %d, scaled depth down to %d",
+		drm_info(dev, "requested bpp %d, scaled depth down to %d",
 			 sizes.surface_bpp, best_depth);
 		sizes.surface_depth = best_depth;
 	}
@@ -1581,7 +1566,9 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 		for (j = 0; j < mode_set->num_connectors; j++) {
 			struct drm_connector *connector = mode_set->connectors[j];
 
-			if (connector->has_tile) {
+			if (connector->has_tile &&
+			    desired_mode->hdisplay == connector->tile_h_size &&
+			    desired_mode->vdisplay == connector->tile_v_size) {
 				lasth = (connector->tile_h_loc == (connector->num_h_tile - 1));
 				lastv = (connector->tile_v_loc == (connector->num_v_tile - 1));
 				/* cloning to multiple tiles is just crazy-talk, so: */
@@ -1597,7 +1584,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 	mutex_unlock(&client->modeset_mutex);
 
 	if (crtc_count == 0 || sizes.fb_width == -1 || sizes.fb_height == -1) {
-		DRM_INFO("Cannot find any crtc or sizes\n");
+		drm_info(dev, "Cannot find any crtc or sizes\n");
 
 		/* First time: disable all crtc's.. */
 		if (!fb_helper->deferred_setup)
@@ -1912,7 +1899,7 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 
 	drm_master_internal_release(fb_helper->dev);
 
-	DRM_DEBUG_KMS("\n");
+	drm_dbg_kms(fb_helper->dev, "\n");
 
 	drm_client_modeset_probe(&fb_helper->client, fb_helper->fb->width, fb_helper->fb->height);
 	drm_setup_crtcs_fb(fb_helper);
@@ -1925,108 +1912,6 @@ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper)
 EXPORT_SYMBOL(drm_fb_helper_hotplug_event);
 
 /**
- * drm_fb_helper_fbdev_setup() - Setup fbdev emulation
- * @dev: DRM device
- * @fb_helper: fbdev helper structure to set up
- * @funcs: fbdev helper functions
- * @preferred_bpp: Preferred bits per pixel for the device.
- *                 @dev->mode_config.preferred_depth is used if this is zero.
- * @max_conn_count: Maximum number of connectors (not used)
- *
- * This function sets up fbdev emulation and registers fbdev for access by
- * userspace. If all connectors are disconnected, setup is deferred to the next
- * time drm_fb_helper_hotplug_event() is called.
- * The caller must to provide a &drm_fb_helper_funcs->fb_probe callback
- * function.
- *
- * Use drm_fb_helper_fbdev_teardown() to destroy the fbdev.
- *
- * See also: drm_fb_helper_initial_config(), drm_fbdev_generic_setup().
- *
- * Returns:
- * Zero on success or negative error code on failure.
- */
-int drm_fb_helper_fbdev_setup(struct drm_device *dev,
-			      struct drm_fb_helper *fb_helper,
-			      const struct drm_fb_helper_funcs *funcs,
-			      unsigned int preferred_bpp,
-			      unsigned int max_conn_count)
-{
-	int ret;
-
-	if (!preferred_bpp)
-		preferred_bpp = dev->mode_config.preferred_depth;
-	if (!preferred_bpp)
-		preferred_bpp = 32;
-
-	drm_fb_helper_prepare(dev, fb_helper, funcs);
-
-	ret = drm_fb_helper_init(dev, fb_helper, 0);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "fbdev: Failed to initialize (ret=%d)\n", ret);
-		return ret;
-	}
-
-	if (!drm_drv_uses_atomic_modeset(dev))
-		drm_helper_disable_unused_functions(dev);
-
-	ret = drm_fb_helper_initial_config(fb_helper, preferred_bpp);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "fbdev: Failed to set configuration (ret=%d)\n", ret);
-		goto err_drm_fb_helper_fini;
-	}
-
-	return 0;
-
-err_drm_fb_helper_fini:
-	drm_fb_helper_fbdev_teardown(dev);
-
-	return ret;
-}
-EXPORT_SYMBOL(drm_fb_helper_fbdev_setup);
-
-/**
- * drm_fb_helper_fbdev_teardown - Tear down fbdev emulation
- * @dev: DRM device
- *
- * This function unregisters fbdev if not already done and cleans up the
- * associated resources including the &drm_framebuffer.
- * The driver is responsible for freeing the &drm_fb_helper structure which is
- * stored in &drm_device->fb_helper. Do note that this pointer has been cleared
- * when this function returns.
- *
- * In order to support device removal/unplug while file handles are still open,
- * drm_fb_helper_unregister_fbi() should be called on device removal and
- * drm_fb_helper_fbdev_teardown() in the &drm_driver->release callback when
- * file handles are closed.
- */
-void drm_fb_helper_fbdev_teardown(struct drm_device *dev)
-{
-	struct drm_fb_helper *fb_helper = dev->fb_helper;
-	struct fb_ops *fbops = NULL;
-
-	if (!fb_helper)
-		return;
-
-	/* Unregister if it hasn't been done already */
-	if (fb_helper->fbdev && fb_helper->fbdev->dev)
-		drm_fb_helper_unregister_fbi(fb_helper);
-
-	if (fb_helper->fbdev && fb_helper->fbdev->fbdefio) {
-		fb_deferred_io_cleanup(fb_helper->fbdev);
-		kfree(fb_helper->fbdev->fbdefio);
-		fbops = fb_helper->fbdev->fbops;
-	}
-
-	drm_fb_helper_fini(fb_helper);
-	kfree(fbops);
-
-	if (fb_helper->fb)
-		drm_framebuffer_remove(fb_helper->fb);
-}
-EXPORT_SYMBOL(drm_fb_helper_fbdev_teardown);
-
-/**
  * drm_fb_helper_lastclose - DRM driver lastclose helper for fbdev emulation
  * @dev: DRM device
  *
@@ -2079,7 +1964,6 @@ static int drm_fbdev_fb_release(struct fb_info *info, int user)
 static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper)
 {
 	struct fb_info *fbi = fb_helper->fbdev;
-	struct fb_ops *fbops = NULL;
 	void *shadow = NULL;
 
 	if (!fb_helper->dev)
@@ -2088,15 +1972,11 @@ static void drm_fbdev_cleanup(struct drm_fb_helper *fb_helper)
 	if (fbi && fbi->fbdefio) {
 		fb_deferred_io_cleanup(fbi);
 		shadow = fbi->screen_buffer;
-		fbops = fbi->fbops;
 	}
 
 	drm_fb_helper_fini(fb_helper);
 
-	if (shadow) {
-		vfree(shadow);
-		kfree(fbops);
-	}
+	vfree(shadow);
 
 	drm_client_framebuffer_delete(fb_helper->buffer);
 }
@@ -2127,7 +2007,7 @@ static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 		return -ENODEV;
 }
 
-static struct fb_ops drm_fbdev_fb_ops = {
+static const struct fb_ops drm_fbdev_fb_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open	= drm_fbdev_fb_open,
@@ -2146,32 +2026,26 @@ static struct fb_deferred_io drm_fbdev_defio = {
 	.deferred_io	= drm_fb_helper_deferred_io,
 };
 
-/**
- * drm_fb_helper_generic_probe - Generic fbdev emulation probe helper
- * @fb_helper: fbdev helper structure
- * @sizes: describes fbdev size and scanout surface size
- *
+/*
  * This function uses the client API to create a framebuffer backed by a dumb buffer.
  *
  * The _sys_ versions are used for &fb_ops.fb_read, fb_write, fb_fillrect,
  * fb_copyarea, fb_imageblit.
- *
- * Returns:
- * Zero on success or negative error code on failure.
  */
-int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
-				struct drm_fb_helper_surface_size *sizes)
+static int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+				       struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_device *dev = fb_helper->dev;
 	struct drm_client_buffer *buffer;
 	struct drm_framebuffer *fb;
 	struct fb_info *fbi;
 	u32 format;
 	void *vaddr;
 
-	DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
-		      sizes->surface_width, sizes->surface_height,
-		      sizes->surface_bpp);
+	drm_dbg_kms(dev, "surface width(%d), height(%d) and bpp(%d)\n",
+		    sizes->surface_width, sizes->surface_height,
+		    sizes->surface_bpp);
 
 	format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
 	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
@@ -2194,24 +2068,10 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
 	drm_fb_helper_fill_info(fbi, fb_helper, sizes);
 
 	if (drm_fbdev_use_shadow_fb(fb_helper)) {
-		struct fb_ops *fbops;
-		void *shadow;
-
-		/*
-		 * fb_deferred_io_cleanup() clears &fbops->fb_mmap so a per
-		 * instance version is necessary.
-		 */
-		fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
-		shadow = vzalloc(fbi->screen_size);
-		if (!fbops || !shadow) {
-			kfree(fbops);
-			vfree(shadow);
+		fbi->screen_buffer = vzalloc(fbi->screen_size);
+		if (!fbi->screen_buffer)
 			return -ENOMEM;
-		}
 
-		*fbops = *fbi->fbops;
-		fbi->fbops = fbops;
-		fbi->screen_buffer = shadow;
 		fbi->fbdefio = &drm_fbdev_defio;
 
 		fb_deferred_io_init(fbi);
@@ -2232,7 +2092,6 @@ int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
 
 	return 0;
 }
-EXPORT_SYMBOL(drm_fb_helper_generic_probe);
 
 static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = {
 	.fb_probe = drm_fb_helper_generic_probe,
@@ -2270,7 +2129,7 @@ static int drm_fbdev_client_hotplug(struct drm_client_dev *client)
 		return drm_fb_helper_hotplug_event(dev->fb_helper);
 
 	if (!dev->mode_config.num_connector) {
-		DRM_DEV_DEBUG(dev->dev, "No connectors found, will not create framebuffer!\n");
+		drm_dbg_kms(dev, "No connectors found, will not create framebuffer!\n");
 		return 0;
 	}
 
@@ -2295,7 +2154,7 @@ err:
 	fb_helper->dev = NULL;
 	fb_helper->fbdev = NULL;
 
-	DRM_DEV_ERROR(dev->dev, "fbdev: Failed to setup generic emulation (ret=%d)\n", ret);
+	drm_err(dev, "fbdev: Failed to setup generic emulation (ret=%d)\n", ret);
 
 	return ret;
 }
@@ -2314,8 +2173,7 @@ static const struct drm_client_funcs drm_fbdev_client_funcs = {
  *                 @dev->mode_config.preferred_depth is used if this is zero.
  *
  * This function sets up generic fbdev emulation for drivers that supports
- * dumb buffers with a virtual address and that can be mmap'ed. If the driver
- * does not support these functions, it could use drm_fb_helper_fbdev_setup().
+ * dumb buffers with a virtual address and that can be mmap'ed.
  *
  * Restore, hotplug events and teardown are all taken care of. Drivers that do
  * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves.
@@ -2353,7 +2211,7 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
 	ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
 	if (ret) {
 		kfree(fb_helper);
-		DRM_DEV_ERROR(dev->dev, "Failed to register client: %d\n", ret);
+		drm_err(dev, "Failed to register client: %d\n", ret);
 		return ret;
 	}
 
@@ -2365,7 +2223,7 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
 
 	ret = drm_fbdev_client_hotplug(&fb_helper->client);
 	if (ret)
-		DRM_DEV_DEBUG(dev->dev, "client hotplug ret=%d\n", ret);
+		drm_dbg_kms(dev, "client hotplug ret=%d\n", ret);
 
 	drm_client_register(&fb_helper->client);
 
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index ea34bc991858..92d16724f949 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -31,7 +31,9 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/anon_inodes.h>
 #include <linux/dma-fence.h>
+#include <linux/file.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/poll.h>
@@ -285,7 +287,7 @@ static int drm_cpu_valid(void)
 }
 
 /*
- * Called whenever a process opens /dev/drm.
+ * Called whenever a process opens a drm node
  *
  * \param filp file pointer.
  * \param minor acquired minor-object.
@@ -754,3 +756,43 @@ void drm_send_event(struct drm_device *dev, struct drm_pending_event *e)
 	spin_unlock_irqrestore(&dev->event_lock, irqflags);
 }
 EXPORT_SYMBOL(drm_send_event);
+
+/**
+ * mock_drm_getfile - Create a new struct file for the drm device
+ * @minor: drm minor to wrap (e.g. #drm_device.primary)
+ * @flags: file creation mode (O_RDWR etc)
+ *
+ * This create a new struct file that wraps a DRM file context around a
+ * DRM minor. This mimicks userspace opening e.g. /dev/dri/card0, but without
+ * invoking userspace. The struct file may be operated on using its f_op
+ * (the drm_device.driver.fops) to mimick userspace operations, or be supplied
+ * to userspace facing functions as an internal/anonymous client.
+ *
+ * RETURNS:
+ * Pointer to newly created struct file, ERR_PTR on failure.
+ */
+struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags)
+{
+	struct drm_device *dev = minor->dev;
+	struct drm_file *priv;
+	struct file *file;
+
+	priv = drm_file_alloc(minor);
+	if (IS_ERR(priv))
+		return ERR_CAST(priv);
+
+	file = anon_inode_getfile("drm", dev->driver->fops, priv, flags);
+	if (IS_ERR(file)) {
+		drm_file_free(priv);
+		return file;
+	}
+
+	/* Everyone shares a single global address space */
+	file->f_mapping = dev->anon_inode->i_mapping;
+
+	drm_dev_get(dev);
+	priv->filp = file;
+
+	return file;
+}
+EXPORT_SYMBOL_FOR_TESTS_ONLY(mock_drm_getfile);
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index c630064ccf41..b234bfaeda06 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -253,17 +253,17 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		  .char_per_block = { 8, 0, 0 }, .block_w = { 2, 0, 0 }, .block_h = { 2, 0, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true },
 		{ .format = DRM_FORMAT_P010,            .depth = 0,  .num_planes = 2,
-		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 },
+		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true},
 		{ .format = DRM_FORMAT_P012,		.depth = 0,  .num_planes = 2,
-		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 },
+		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 },
 		   .hsub = 2, .vsub = 2, .is_yuv = true},
 		{ .format = DRM_FORMAT_P016,		.depth = 0,  .num_planes = 2,
-		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 },
+		  .char_per_block = { 2, 4, 0 }, .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true},
 		{ .format = DRM_FORMAT_P210,		.depth = 0,
 		  .num_planes = 2, .char_per_block = { 2, 4, 0 },
-		  .block_w = { 1, 0, 0 }, .block_h = { 1, 0, 0 }, .hsub = 2,
+		  .block_w = { 1, 1, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2,
 		  .vsub = 1, .is_yuv = true },
 		{ .format = DRM_FORMAT_VUY101010,	.depth = 0,
 		  .num_planes = 1, .cpp = { 0, 0, 0 }, .hsub = 1, .vsub = 1,
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 000fa4a1899f..a9e4a610445a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1114,9 +1114,6 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
 	drm_gem_object_get(obj);
 
 	if (obj->funcs && obj->funcs->mmap) {
-		/* Remove the fake offset */
-		vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
-
 		ret = obj->funcs->mmap(obj, vma);
 		if (ret) {
 			drm_gem_object_put_unlocked(obj);
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index b9bcd310ca2d..3a7ace19a902 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -74,8 +74,7 @@ drm_gem_fb_alloc(struct drm_device *dev,
 
 	ret = drm_framebuffer_init(dev, fb, funcs);
 	if (ret) {
-		DRM_DEV_ERROR(dev->dev, "Failed to init framebuffer: %d\n",
-			      ret);
+		drm_err(dev, "Failed to init framebuffer: %d\n", ret);
 		kfree(fb);
 		return ERR_PTR(ret);
 	}
@@ -160,7 +159,7 @@ drm_gem_fb_create_with_funcs(struct drm_device *dev, struct drm_file *file,
 
 		objs[i] = drm_gem_object_lookup(file, mode_cmd->handles[i]);
 		if (!objs[i]) {
-			DRM_DEBUG_KMS("Failed to lookup GEM object\n");
+			drm_dbg_kms(dev, "Failed to lookup GEM object\n");
 			ret = -ENOENT;
 			goto err_gem_object_put;
 		}
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 0810d3ef6961..a421a2eed48a 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -528,6 +528,9 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	struct drm_gem_shmem_object *shmem;
 	int ret;
 
+	/* Remove the fake offset */
+	vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
+
 	shmem = to_drm_gem_shmem_obj(obj);
 
 	ret = drm_gem_shmem_get_pages(shmem);
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 666cb4c22bb9..a4863326061a 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -2,6 +2,7 @@
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_ttm_helper.h>
@@ -92,14 +93,18 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo,
 }
 
 static int drm_gem_vram_init(struct drm_device *dev,
-			     struct ttm_bo_device *bdev,
 			     struct drm_gem_vram_object *gbo,
-			     size_t size, unsigned long pg_align,
-			     bool interruptible)
+			     size_t size, unsigned long pg_align)
 {
+	struct drm_vram_mm *vmm = dev->vram_mm;
+	struct ttm_bo_device *bdev;
 	int ret;
 	size_t acc_size;
 
+	if (WARN_ONCE(!vmm, "VRAM MM not initialized"))
+		return -EINVAL;
+	bdev = &vmm->bdev;
+
 	gbo->bo.base.funcs = &drm_gem_vram_object_funcs;
 
 	ret = drm_gem_object_init(dev, &gbo->bo.base, size);
@@ -112,7 +117,7 @@ static int drm_gem_vram_init(struct drm_device *dev,
 	drm_gem_vram_placement(gbo, TTM_PL_FLAG_VRAM | TTM_PL_FLAG_SYSTEM);
 
 	ret = ttm_bo_init(bdev, &gbo->bo, size, ttm_bo_type_device,
-			  &gbo->placement, pg_align, interruptible, acc_size,
+			  &gbo->placement, pg_align, false, acc_size,
 			  NULL, NULL, ttm_buffer_object_destroy);
 	if (ret)
 		goto err_drm_gem_object_release;
@@ -127,29 +132,33 @@ err_drm_gem_object_release:
 /**
  * drm_gem_vram_create() - Creates a VRAM-backed GEM object
  * @dev:		the DRM device
- * @bdev:		the TTM BO device backing the object
  * @size:		the buffer size in bytes
  * @pg_align:		the buffer's alignment in multiples of the page size
- * @interruptible:	sleep interruptible if waiting for memory
  *
  * Returns:
  * A new instance of &struct drm_gem_vram_object on success, or
  * an ERR_PTR()-encoded error code otherwise.
  */
 struct drm_gem_vram_object *drm_gem_vram_create(struct drm_device *dev,
-						struct ttm_bo_device *bdev,
 						size_t size,
-						unsigned long pg_align,
-						bool interruptible)
+						unsigned long pg_align)
 {
 	struct drm_gem_vram_object *gbo;
 	int ret;
 
-	gbo = kzalloc(sizeof(*gbo), GFP_KERNEL);
-	if (!gbo)
-		return ERR_PTR(-ENOMEM);
+	if (dev->driver->gem_create_object) {
+		struct drm_gem_object *gem =
+			dev->driver->gem_create_object(dev, size);
+		if (!gem)
+			return ERR_PTR(-ENOMEM);
+		gbo = drm_gem_vram_of_gem(gem);
+	} else {
+		gbo = kzalloc(sizeof(*gbo), GFP_KERNEL);
+		if (!gbo)
+			return ERR_PTR(-ENOMEM);
+	}
 
-	ret = drm_gem_vram_init(dev, bdev, gbo, size, pg_align, interruptible);
+	ret = drm_gem_vram_init(dev, gbo, size, pg_align);
 	if (ret < 0)
 		goto err_kfree;
 
@@ -483,9 +492,8 @@ EXPORT_SYMBOL(drm_gem_vram_vunmap);
 	Helper for implementing &struct drm_driver.dumb_create
  * @file:		the DRM file
  * @dev:		the DRM device
- * @bdev:		the TTM BO device managing the buffer object
  * @pg_align:		the buffer's alignment in multiples of the page size
- * @interruptible:	sleep interruptible if waiting for memory
+ * @pitch_align:	the scanline's alignment in powers of 2
  * @args:		the arguments as provided to \
 				&struct drm_driver.dumb_create
  *
@@ -500,9 +508,8 @@ EXPORT_SYMBOL(drm_gem_vram_vunmap);
  */
 int drm_gem_vram_fill_create_dumb(struct drm_file *file,
 				  struct drm_device *dev,
-				  struct ttm_bo_device *bdev,
 				  unsigned long pg_align,
-				  bool interruptible,
+				  unsigned long pitch_align,
 				  struct drm_mode_create_dumb *args)
 {
 	size_t pitch, size;
@@ -510,14 +517,19 @@ int drm_gem_vram_fill_create_dumb(struct drm_file *file,
 	int ret;
 	u32 handle;
 
-	pitch = args->width * ((args->bpp + 7) / 8);
+	pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
+	if (pitch_align) {
+		if (WARN_ON_ONCE(!is_power_of_2(pitch_align)))
+			return -EINVAL;
+		pitch = ALIGN(pitch, pitch_align);
+	}
 	size = pitch * args->height;
 
 	size = roundup(size, PAGE_SIZE);
 	if (!size)
 		return -EINVAL;
 
-	gbo = drm_gem_vram_create(dev, bdev, size, pg_align, interruptible);
+	gbo = drm_gem_vram_create(dev, size, pg_align);
 	if (IS_ERR(gbo))
 		return PTR_ERR(gbo);
 
@@ -612,8 +624,7 @@ int drm_gem_vram_driver_dumb_create(struct drm_file *file,
 	if (WARN_ONCE(!dev->vram_mm, "VRAM MM not initialized"))
 		return -EINVAL;
 
-	return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev, 0,
-					     false, args);
+	return drm_gem_vram_fill_create_dumb(file, dev, 0, 0, args);
 }
 EXPORT_SYMBOL(drm_gem_vram_driver_dumb_create);
 
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index 51a2055c8f18..6937bf923f05 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -45,12 +45,34 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor);
 void drm_file_free(struct drm_file *file);
 void drm_lastclose(struct drm_device *dev);
 
+#ifdef CONFIG_PCI
+
 /* drm_pci.c */
 int drm_irq_by_busid(struct drm_device *dev, void *data,
 		     struct drm_file *file_priv);
 void drm_pci_agp_destroy(struct drm_device *dev);
 int drm_pci_set_busid(struct drm_device *dev, struct drm_master *master);
 
+#else
+
+static inline int drm_irq_by_busid(struct drm_device *dev, void *data,
+				   struct drm_file *file_priv)
+{
+	return -EINVAL;
+}
+
+static inline void drm_pci_agp_destroy(struct drm_device *dev)
+{
+}
+
+static inline int drm_pci_set_busid(struct drm_device *dev,
+				    struct drm_master *master)
+{
+	return -EINVAL;
+}
+
+#endif
+
 /* drm_prime.c */
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index fcd728d7cf72..5afb39688b55 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -652,8 +652,8 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETRESOURCES, drm_mode_getresources, 0),
 
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_HANDLE_TO_FD, drm_prime_handle_to_fd_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF(DRM_IOCTL_PRIME_FD_TO_HANDLE, drm_prime_fd_to_handle_ioctl, DRM_RENDER_ALLOW),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPLANERESOURCES, drm_mode_getplane_res, 0),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETCRTC, drm_mode_getcrtc, 0),
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 2e8ce99d0baa..2c79e8199e3c 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -360,7 +360,8 @@ void drm_legacy_lock_master_cleanup(struct drm_device *dev, struct drm_master *m
 	/*
 	 * Since the master is disappearing, so is the
 	 * possibility to lock.
-	 */	mutex_lock(&dev->struct_mutex);
+	 */
+	mutex_lock(&dev->struct_mutex);
 	if (master->lock.hw_lock) {
 		if (dev->sigdata.lock == master->lock.hw_lock)
 			dev->sigdata.lock = NULL;
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index e34058c721be..16bff1be4b8a 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -367,9 +367,9 @@ static void mipi_dbi_blank(struct mipi_dbi_dev *dbidev)
 	memset(dbidev->tx_buf, 0, len);
 
 	mipi_dbi_command(dbi, MIPI_DCS_SET_COLUMN_ADDRESS, 0, 0,
-			 (width >> 8) & 0xFF, (width - 1) & 0xFF);
+			 ((width - 1) >> 8) & 0xFF, (width - 1) & 0xFF);
 	mipi_dbi_command(dbi, MIPI_DCS_SET_PAGE_ADDRESS, 0, 0,
-			 (height >> 8) & 0xFF, (height - 1) & 0xFF);
+			 ((height - 1) >> 8) & 0xFF, (height - 1) & 0xFF);
 	mipi_dbi_command_buf(dbi, MIPI_DCS_WRITE_MEMORY_START,
 			     (u8 *)dbidev->tx_buf, len);
 
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index bd2498bbd74a..55531895dde6 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -33,6 +33,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 
+#include <drm/drm_dsc.h>
 #include <video/mipi_display.h>
 
 /**
@@ -373,6 +374,7 @@ bool mipi_dsi_packet_format_is_short(u8 type)
 	case MIPI_DSI_V_SYNC_END:
 	case MIPI_DSI_H_SYNC_START:
 	case MIPI_DSI_H_SYNC_END:
+	case MIPI_DSI_COMPRESSION_MODE:
 	case MIPI_DSI_END_OF_TRANSMISSION:
 	case MIPI_DSI_COLOR_MODE_OFF:
 	case MIPI_DSI_COLOR_MODE_ON:
@@ -387,7 +389,7 @@ bool mipi_dsi_packet_format_is_short(u8 type)
 	case MIPI_DSI_DCS_SHORT_WRITE:
 	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
 	case MIPI_DSI_DCS_READ:
-	case MIPI_DSI_DCS_COMPRESSION_MODE:
+	case MIPI_DSI_EXECUTE_QUEUE:
 	case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE:
 		return true;
 	}
@@ -406,11 +408,12 @@ EXPORT_SYMBOL(mipi_dsi_packet_format_is_short);
 bool mipi_dsi_packet_format_is_long(u8 type)
 {
 	switch (type) {
-	case MIPI_DSI_PPS_LONG_WRITE:
 	case MIPI_DSI_NULL_PACKET:
 	case MIPI_DSI_BLANKING_PACKET:
 	case MIPI_DSI_GENERIC_LONG_WRITE:
 	case MIPI_DSI_DCS_LONG_WRITE:
+	case MIPI_DSI_PICTURE_PARAMETER_SET:
+	case MIPI_DSI_COMPRESSED_PIXEL_STREAM:
 	case MIPI_DSI_LOOSELY_PACKED_PIXEL_STREAM_YCBCR20:
 	case MIPI_DSI_PACKED_PIXEL_STREAM_YCBCR24:
 	case MIPI_DSI_PACKED_PIXEL_STREAM_YCBCR16:
@@ -547,6 +550,56 @@ int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi,
 EXPORT_SYMBOL(mipi_dsi_set_maximum_return_packet_size);
 
 /**
+ * mipi_dsi_compression_mode() - enable/disable DSC on the peripheral
+ * @dsi: DSI peripheral device
+ * @enable: Whether to enable or disable the DSC
+ *
+ * Enable or disable Display Stream Compression on the peripheral using the
+ * default Picture Parameter Set and VESA DSC 1.1 algorithm.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+ssize_t mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable)
+{
+	/* Note: Needs updating for non-default PPS or algorithm */
+	u8 tx[2] = { enable << 0, 0 };
+	struct mipi_dsi_msg msg = {
+		.channel = dsi->channel,
+		.type = MIPI_DSI_COMPRESSION_MODE,
+		.tx_len = sizeof(tx),
+		.tx_buf = tx,
+	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
+
+	return (ret < 0) ? ret : 0;
+}
+EXPORT_SYMBOL(mipi_dsi_compression_mode);
+
+/**
+ * mipi_dsi_picture_parameter_set() - transmit the DSC PPS to the peripheral
+ * @dsi: DSI peripheral device
+ * @pps: VESA DSC 1.1 Picture Parameter Set
+ *
+ * Transmit the VESA DSC 1.1 Picture Parameter Set to the peripheral.
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+ssize_t mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi,
+				       const struct drm_dsc_picture_parameter_set *pps)
+{
+	struct mipi_dsi_msg msg = {
+		.channel = dsi->channel,
+		.type = MIPI_DSI_PICTURE_PARAMETER_SET,
+		.tx_len = sizeof(*pps),
+		.tx_buf = pps,
+	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
+
+	return (ret < 0) ? ret : 0;
+}
+EXPORT_SYMBOL(mipi_dsi_picture_parameter_set);
+
+/**
  * mipi_dsi_generic_write() - transmit data using a generic write packet
  * @dsi: DSI peripheral device
  * @payload: buffer containing the payload
diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c
index 3b570a404933..08e6eff6a179 100644
--- a/drivers/gpu/drm/drm_mode_config.c
+++ b/drivers/gpu/drm/drm_mode_config.c
@@ -27,6 +27,7 @@
 #include <drm/drm_file.h>
 #include <drm/drm_mode_config.h>
 #include <drm/drm_print.h>
+#include <linux/dma-resv.h>
 
 #include "drm_crtc_internal.h"
 #include "drm_internal.h"
@@ -415,6 +416,33 @@ void drm_mode_config_init(struct drm_device *dev)
 	dev->mode_config.num_crtc = 0;
 	dev->mode_config.num_encoder = 0;
 	dev->mode_config.num_total_plane = 0;
+
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
+		struct drm_modeset_acquire_ctx modeset_ctx;
+		struct ww_acquire_ctx resv_ctx;
+		struct dma_resv resv;
+		int ret;
+
+		dma_resv_init(&resv);
+
+		drm_modeset_acquire_init(&modeset_ctx, 0);
+		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+				       &modeset_ctx);
+		if (ret == -EDEADLK)
+			ret = drm_modeset_backoff(&modeset_ctx);
+
+		ww_acquire_init(&resv_ctx, &reservation_ww_class);
+		ret = dma_resv_lock(&resv, &resv_ctx);
+		if (ret == -EDEADLK)
+			dma_resv_lock_slow(&resv, &resv_ctx);
+
+		dma_resv_unlock(&resv);
+		ww_acquire_fini(&resv_ctx);
+
+		drm_modeset_drop_locks(&modeset_ctx);
+		drm_modeset_acquire_fini(&modeset_ctx);
+		dma_resv_fini(&resv);
+	}
 }
 EXPORT_SYMBOL(drm_mode_config_init);
 
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index 6a23e36ed4fe..35c2719407a8 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -224,12 +224,26 @@ EXPORT_SYMBOL(drm_mode_object_get);
  * This attaches the given property to the modeset object with the given initial
  * value. Currently this function cannot fail since the properties are stored in
  * a statically sized array.
+ *
+ * Note that all properties must be attached before the object itself is
+ * registered and accessible from userspace.
  */
 void drm_object_attach_property(struct drm_mode_object *obj,
 				struct drm_property *property,
 				uint64_t init_val)
 {
 	int count = obj->properties->count;
+	struct drm_device *dev = property->dev;
+
+
+	if (obj->type == DRM_MODE_OBJECT_CONNECTOR) {
+		struct drm_connector *connector = obj_to_connector(obj);
+
+		WARN_ON(!dev->driver->load &&
+			connector->registration_state == DRM_CONNECTOR_REGISTERED);
+	} else {
+		WARN_ON(!dev->driver->load && dev->registered);
+	}
 
 	if (count == DRM_OBJECT_MAX_PROPERTY) {
 		WARN(1, "Failed to attach object property (type: 0x%x). Please "
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 88232698d7a0..10336b144c72 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -233,7 +233,7 @@ struct drm_display_mode *drm_cvt_mode(struct drm_device *dev, int hdisplay,
 		/* 3) Nominal HSync width (% of line period) - default 8 */
 #define CVT_HSYNC_PERCENTAGE	8
 		unsigned int hblank_percentage;
-		int vsyncandback_porch, vback_porch, hblank;
+		int vsyncandback_porch, __maybe_unused vback_porch, hblank;
 
 		/* estimated the horizontal period */
 		tmp1 = HV_FACTOR * 1000000  -
@@ -386,9 +386,10 @@ drm_gtf_mode_complex(struct drm_device *dev, int hdisplay, int vdisplay,
 	int top_margin, bottom_margin;
 	int interlace;
 	unsigned int hfreq_est;
-	int vsync_plus_bp, vback_porch;
-	unsigned int vtotal_lines, vfieldrate_est, hperiod;
-	unsigned int vfield_rate, vframe_rate;
+	int vsync_plus_bp, __maybe_unused vback_porch;
+	unsigned int vtotal_lines, __maybe_unused vfieldrate_est;
+	unsigned int __maybe_unused hperiod;
+	unsigned int vfield_rate, __maybe_unused vframe_rate;
 	int left_margin, right_margin;
 	unsigned int total_active_pixels, ideal_duty_cycle;
 	unsigned int hblank, total_pixels, pixel_freq;
@@ -1568,33 +1569,76 @@ static int drm_mode_parse_cmdline_res_mode(const char *str, unsigned int length,
 	return 0;
 }
 
-static int drm_mode_parse_cmdline_options(char *str, size_t len,
+static int drm_mode_parse_cmdline_int(const char *delim, unsigned int *int_ret)
+{
+	const char *value;
+	char *endp;
+
+	/*
+	 * delim must point to the '=', otherwise it is a syntax error and
+	 * if delim points to the terminating zero, then delim + 1 wil point
+	 * past the end of the string.
+	 */
+	if (*delim != '=')
+		return -EINVAL;
+
+	value = delim + 1;
+	*int_ret = simple_strtol(value, &endp, 10);
+
+	/* Make sure we have parsed something */
+	if (endp == value)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int drm_mode_parse_panel_orientation(const char *delim,
+					    struct drm_cmdline_mode *mode)
+{
+	const char *value;
+
+	if (*delim != '=')
+		return -EINVAL;
+
+	value = delim + 1;
+	delim = strchr(value, ',');
+	if (!delim)
+		delim = value + strlen(value);
+
+	if (!strncmp(value, "normal", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
+	else if (!strncmp(value, "upside_down", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
+	else if (!strncmp(value, "left_side_up", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP;
+	else if (!strncmp(value, "right_side_up", delim - value))
+		mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int drm_mode_parse_cmdline_options(const char *str,
+					  bool freestanding,
 					  const struct drm_connector *connector,
 					  struct drm_cmdline_mode *mode)
 {
-	unsigned int rotation = 0;
-	char *sep = str;
+	unsigned int deg, margin, rotation = 0;
+	const char *delim, *option, *sep;
 
-	while ((sep = strchr(sep, ','))) {
-		char *delim, *option;
-
-		option = sep + 1;
+	option = str;
+	do {
 		delim = strchr(option, '=');
 		if (!delim) {
 			delim = strchr(option, ',');
 
 			if (!delim)
-				delim = str + len;
+				delim = option + strlen(option);
 		}
 
 		if (!strncmp(option, "rotate", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int deg;
-
-			deg = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &deg))
 				return -EINVAL;
 
 			switch (deg) {
@@ -1619,58 +1663,40 @@ static int drm_mode_parse_cmdline_options(char *str, size_t len,
 			}
 		} else if (!strncmp(option, "reflect_x", delim - option)) {
 			rotation |= DRM_MODE_REFLECT_X;
-			sep = delim;
 		} else if (!strncmp(option, "reflect_y", delim - option)) {
 			rotation |= DRM_MODE_REFLECT_Y;
-			sep = delim;
 		} else if (!strncmp(option, "margin_right", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.right = margin;
 		} else if (!strncmp(option, "margin_left", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.left = margin;
 		} else if (!strncmp(option, "margin_top", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.top = margin;
 		} else if (!strncmp(option, "margin_bottom", delim - option)) {
-			const char *value = delim + 1;
-			unsigned int margin;
-
-			margin = simple_strtol(value, &sep, 10);
-
-			/* Make sure we have parsed something */
-			if (sep == value)
+			if (drm_mode_parse_cmdline_int(delim, &margin))
 				return -EINVAL;
 
 			mode->tv_margins.bottom = margin;
+		} else if (!strncmp(option, "panel_orientation", delim - option)) {
+			if (drm_mode_parse_panel_orientation(delim, mode))
+				return -EINVAL;
 		} else {
 			return -EINVAL;
 		}
-	}
+		sep = strchr(delim, ',');
+		option = sep + 1;
+	} while (sep);
+
+	if (rotation && freestanding)
+		return -EINVAL;
 
 	mode->rotation_reflection = rotation;
 
@@ -1682,17 +1708,6 @@ static const char * const drm_named_modes_whitelist[] = {
 	"PAL",
 };
 
-static bool drm_named_mode_is_in_whitelist(const char *mode, unsigned int size)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++)
-		if (!strncmp(mode, drm_named_modes_whitelist[i], size))
-			return true;
-
-	return false;
-}
-
 /**
  * drm_mode_parse_command_line_for_connector - parse command line modeline for connector
  * @mode_option: optional per connector mode option
@@ -1723,72 +1738,30 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 					       struct drm_cmdline_mode *mode)
 {
 	const char *name;
-	bool named_mode = false, parse_extras = false;
+	bool freestanding = false, parse_extras = false;
 	unsigned int bpp_off = 0, refresh_off = 0, options_off = 0;
 	unsigned int mode_end = 0;
-	char *bpp_ptr = NULL, *refresh_ptr = NULL, *extra_ptr = NULL;
-	char *options_ptr = NULL;
+	const char *bpp_ptr = NULL, *refresh_ptr = NULL, *extra_ptr = NULL;
+	const char *options_ptr = NULL;
 	char *bpp_end_ptr = NULL, *refresh_end_ptr = NULL;
-	int ret;
+	int i, len, ret;
 
-#ifdef CONFIG_FB
-	if (!mode_option)
-		mode_option = fb_mode_option;
-#endif
+	memset(mode, 0, sizeof(*mode));
+	mode->panel_orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN;
 
-	if (!mode_option) {
-		mode->specified = false;
+	if (!mode_option)
 		return false;
-	}
 
 	name = mode_option;
 
-	/*
-	 * This is a bit convoluted. To differentiate between the
-	 * named modes and poorly formatted resolutions, we need a
-	 * bunch of things:
-	 *   - We need to make sure that the first character (which
-	 *     would be our resolution in X) is a digit.
-	 *   - If not, then it's either a named mode or a force on/off.
-	 *     To distinguish between the two, we need to run the
-	 *     extra parsing function, and if not, then we consider it
-	 *     a named mode.
-	 *
-	 * If this isn't enough, we should add more heuristics here,
-	 * and matching unit-tests.
-	 */
-	if (!isdigit(name[0]) && name[0] != 'x') {
-		unsigned int namelen = strlen(name);
-
-		/*
-		 * Only the force on/off options can be in that case,
-		 * and they all take a single character.
-		 */
-		if (namelen == 1) {
-			ret = drm_mode_parse_cmdline_extra(name, namelen, true,
-							   connector, mode);
-			if (!ret)
-				return true;
-		}
-
-		named_mode = true;
-	}
-
 	/* Try to locate the bpp and refresh specifiers, if any */
 	bpp_ptr = strchr(name, '-');
-	if (bpp_ptr) {
+	if (bpp_ptr)
 		bpp_off = bpp_ptr - name;
-		mode->bpp_specified = true;
-	}
 
 	refresh_ptr = strchr(name, '@');
-	if (refresh_ptr) {
-		if (named_mode)
-			return false;
-
+	if (refresh_ptr)
 		refresh_off = refresh_ptr - name;
-		mode->refresh_specified = true;
-	}
 
 	/* Locate the start of named options */
 	options_ptr = strchr(name, ',');
@@ -1802,33 +1775,58 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 		mode_end = refresh_off;
 	} else if (options_ptr) {
 		mode_end = options_off;
+		parse_extras = true;
 	} else {
 		mode_end = strlen(name);
 		parse_extras = true;
 	}
 
-	if (named_mode) {
-		if (mode_end + 1 > DRM_DISPLAY_MODE_LEN)
-			return false;
+	/* First check for a named mode */
+	for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++) {
+		ret = str_has_prefix(name, drm_named_modes_whitelist[i]);
+		if (ret == mode_end) {
+			if (refresh_ptr)
+				return false; /* named + refresh is invalid */
 
-		if (!drm_named_mode_is_in_whitelist(name, mode_end))
-			return false;
+			strcpy(mode->name, drm_named_modes_whitelist[i]);
+			mode->specified = true;
+			break;
+		}
+	}
 
-		strscpy(mode->name, name, mode_end + 1);
-	} else {
+	/* No named mode? Check for a normal mode argument, e.g. 1024x768 */
+	if (!mode->specified && isdigit(name[0])) {
 		ret = drm_mode_parse_cmdline_res_mode(name, mode_end,
 						      parse_extras,
 						      connector,
 						      mode);
 		if (ret)
 			return false;
+
+		mode->specified = true;
+	}
+
+	/* No mode? Check for freestanding extras and/or options */
+	if (!mode->specified) {
+		unsigned int len = strlen(mode_option);
+
+		if (bpp_ptr || refresh_ptr)
+			return false; /* syntax error */
+
+		if (len == 1 || (len >= 2 && mode_option[1] == ','))
+			extra_ptr = mode_option;
+		else
+			options_ptr = mode_option - 1;
+
+		freestanding = true;
 	}
-	mode->specified = true;
 
 	if (bpp_ptr) {
 		ret = drm_mode_parse_cmdline_bpp(bpp_ptr, &bpp_end_ptr, mode);
 		if (ret)
 			return false;
+
+		mode->bpp_specified = true;
 	}
 
 	if (refresh_ptr) {
@@ -1836,6 +1834,8 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 						     &refresh_end_ptr, mode);
 		if (ret)
 			return false;
+
+		mode->refresh_specified = true;
 	}
 
 	/*
@@ -1849,20 +1849,21 @@ bool drm_mode_parse_command_line_for_connector(const char *mode_option,
 	else if (refresh_ptr)
 		extra_ptr = refresh_end_ptr;
 
-	if (extra_ptr &&
-	    extra_ptr != options_ptr) {
-		int len = strlen(name) - (extra_ptr - name);
+	if (extra_ptr) {
+		if (options_ptr)
+			len = options_ptr - extra_ptr;
+		else
+			len = strlen(extra_ptr);
 
-		ret = drm_mode_parse_cmdline_extra(extra_ptr, len, false,
+		ret = drm_mode_parse_cmdline_extra(extra_ptr, len, freestanding,
 						   connector, mode);
 		if (ret)
 			return false;
 	}
 
 	if (options_ptr) {
-		int len = strlen(name) - (options_ptr - name);
-
-		ret = drm_mode_parse_cmdline_options(options_ptr, len,
+		ret = drm_mode_parse_cmdline_options(options_ptr + 1,
+						     freestanding,
 						     connector, mode);
 		if (ret)
 			return false;
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 0ca58803ba46..b50b44e76279 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -274,3 +274,119 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge);
+
+enum drm_of_lvds_pixels {
+	DRM_OF_LVDS_EVEN = BIT(0),
+	DRM_OF_LVDS_ODD = BIT(1),
+};
+
+static int drm_of_lvds_get_port_pixels_type(struct device_node *port_node)
+{
+	bool even_pixels =
+		of_property_read_bool(port_node, "dual-lvds-even-pixels");
+	bool odd_pixels =
+		of_property_read_bool(port_node, "dual-lvds-odd-pixels");
+
+	return (even_pixels ? DRM_OF_LVDS_EVEN : 0) |
+	       (odd_pixels ? DRM_OF_LVDS_ODD : 0);
+}
+
+static int drm_of_lvds_get_remote_pixels_type(
+			const struct device_node *port_node)
+{
+	struct device_node *endpoint = NULL;
+	int pixels_type = -EPIPE;
+
+	for_each_child_of_node(port_node, endpoint) {
+		struct device_node *remote_port;
+		int current_pt;
+
+		if (!of_node_name_eq(endpoint, "endpoint"))
+			continue;
+
+		remote_port = of_graph_get_remote_port(endpoint);
+		if (!remote_port) {
+			of_node_put(remote_port);
+			return -EPIPE;
+		}
+
+		current_pt = drm_of_lvds_get_port_pixels_type(remote_port);
+		of_node_put(remote_port);
+		if (pixels_type < 0)
+			pixels_type = current_pt;
+
+		/*
+		 * Sanity check, ensure that all remote endpoints have the same
+		 * pixel type. We may lift this restriction later if we need to
+		 * support multiple sinks with different dual-link
+		 * configurations by passing the endpoints explicitly to
+		 * drm_of_lvds_get_dual_link_pixel_order().
+		 */
+		if (!current_pt || pixels_type != current_pt) {
+			of_node_put(remote_port);
+			return -EINVAL;
+		}
+	}
+
+	return pixels_type;
+}
+
+/**
+ * drm_of_lvds_get_dual_link_pixel_order - Get LVDS dual-link pixel order
+ * @port1: First DT port node of the Dual-link LVDS source
+ * @port2: Second DT port node of the Dual-link LVDS source
+ *
+ * An LVDS dual-link connection is made of two links, with even pixels
+ * transitting on one link, and odd pixels on the other link. This function
+ * returns, for two ports of an LVDS dual-link source, which port shall transmit
+ * the even and odd pixels, based on the requirements of the connected sink.
+ *
+ * The pixel order is determined from the dual-lvds-even-pixels and
+ * dual-lvds-odd-pixels properties in the sink's DT port nodes. If those
+ * properties are not present, or if their usage is not valid, this function
+ * returns -EINVAL.
+ *
+ * If either port is not connected, this function returns -EPIPE.
+ *
+ * @port1 and @port2 are typically DT sibling nodes, but may have different
+ * parents when, for instance, two separate LVDS encoders carry the even and odd
+ * pixels.
+ *
+ * Return:
+ * * DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS - @port1 carries even pixels and @port2
+ *   carries odd pixels
+ * * DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS - @port1 carries odd pixels and @port2
+ *   carries even pixels
+ * * -EINVAL - @port1 and @port2 are not connected to a dual-link LVDS sink, or
+ *   the sink configuration is invalid
+ * * -EPIPE - when @port1 or @port2 are not connected
+ */
+int drm_of_lvds_get_dual_link_pixel_order(const struct device_node *port1,
+					  const struct device_node *port2)
+{
+	int remote_p1_pt, remote_p2_pt;
+
+	if (!port1 || !port2)
+		return -EINVAL;
+
+	remote_p1_pt = drm_of_lvds_get_remote_pixels_type(port1);
+	if (remote_p1_pt < 0)
+		return remote_p1_pt;
+
+	remote_p2_pt = drm_of_lvds_get_remote_pixels_type(port2);
+	if (remote_p2_pt < 0)
+		return remote_p2_pt;
+
+	/*
+	 * A valid dual-lVDS bus is found when one remote port is marked with
+	 * "dual-lvds-even-pixels", and the other remote port is marked with
+	 * "dual-lvds-odd-pixels", bail out if the markers are not right.
+	 */
+	if (remote_p1_pt + remote_p2_pt != DRM_OF_LVDS_EVEN + DRM_OF_LVDS_ODD)
+		return -EINVAL;
+
+	return remote_p1_pt == DRM_OF_LVDS_EVEN ?
+		DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS :
+		DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS;
+}
+EXPORT_SYMBOL_GPL(drm_of_lvds_get_dual_link_pixel_order);
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index ed7985c0535a..8c7bac85a793 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -21,11 +21,13 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/backlight.h>
 #include <linux/err.h>
 #include <linux/module.h>
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_panel.h>
+#include <drm/drm_print.h>
 
 static DEFINE_MUTEX(panel_lock);
 static LIST_HEAD(panel_list);
@@ -112,12 +114,6 @@ EXPORT_SYMBOL(drm_panel_remove);
  */
 int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
 {
-	if (panel->connector)
-		return -EBUSY;
-
-	panel->connector = connector;
-	panel->drm = connector->dev;
-
 	return 0;
 }
 EXPORT_SYMBOL(drm_panel_attach);
@@ -134,8 +130,6 @@ EXPORT_SYMBOL(drm_panel_attach);
  */
 void drm_panel_detach(struct drm_panel *panel)
 {
-	panel->connector = NULL;
-	panel->drm = NULL;
 }
 EXPORT_SYMBOL(drm_panel_detach);
 
@@ -151,10 +145,13 @@ EXPORT_SYMBOL(drm_panel_detach);
  */
 int drm_panel_prepare(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->prepare)
+	if (!panel)
+		return -EINVAL;
+
+	if (panel->funcs && panel->funcs->prepare)
 		return panel->funcs->prepare(panel);
 
-	return panel ? -ENOSYS : -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_prepare);
 
@@ -171,10 +168,13 @@ EXPORT_SYMBOL(drm_panel_prepare);
  */
 int drm_panel_unprepare(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->unprepare)
+	if (!panel)
+		return -EINVAL;
+
+	if (panel->funcs && panel->funcs->unprepare)
 		return panel->funcs->unprepare(panel);
 
-	return panel ? -ENOSYS : -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_unprepare);
 
@@ -190,10 +190,23 @@ EXPORT_SYMBOL(drm_panel_unprepare);
  */
 int drm_panel_enable(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->enable)
-		return panel->funcs->enable(panel);
+	int ret;
+
+	if (!panel)
+		return -EINVAL;
+
+	if (panel->funcs && panel->funcs->enable) {
+		ret = panel->funcs->enable(panel);
+		if (ret < 0)
+			return ret;
+	}
 
-	return panel ? -ENOSYS : -EINVAL;
+	ret = backlight_enable(panel->backlight);
+	if (ret < 0)
+		DRM_DEV_INFO(panel->dev, "failed to enable backlight: %d\n",
+			     ret);
+
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_enable);
 
@@ -209,16 +222,27 @@ EXPORT_SYMBOL(drm_panel_enable);
  */
 int drm_panel_disable(struct drm_panel *panel)
 {
-	if (panel && panel->funcs && panel->funcs->disable)
+	int ret;
+
+	if (!panel)
+		return -EINVAL;
+
+	ret = backlight_disable(panel->backlight);
+	if (ret < 0)
+		DRM_DEV_INFO(panel->dev, "failed to disable backlight: %d\n",
+			     ret);
+
+	if (panel->funcs && panel->funcs->disable)
 		return panel->funcs->disable(panel);
 
-	return panel ? -ENOSYS : -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(drm_panel_disable);
 
 /**
  * drm_panel_get_modes - probe the available display modes of a panel
  * @panel: DRM panel
+ * @connector: DRM connector
  *
  * The modes probed from the panel are automatically added to the connector
  * that the panel is attached to.
@@ -226,12 +250,16 @@ EXPORT_SYMBOL(drm_panel_disable);
  * Return: The number of modes available from the panel on success or a
  * negative error code on failure.
  */
-int drm_panel_get_modes(struct drm_panel *panel)
+int drm_panel_get_modes(struct drm_panel *panel,
+			struct drm_connector *connector)
 {
-	if (panel && panel->funcs && panel->funcs->get_modes)
-		return panel->funcs->get_modes(panel);
+	if (!panel)
+		return -EINVAL;
 
-	return panel ? -ENOSYS : -EINVAL;
+	if (panel->funcs && panel->funcs->get_modes)
+		return panel->funcs->get_modes(panel, connector);
+
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(drm_panel_get_modes);
 
@@ -274,6 +302,45 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np)
 EXPORT_SYMBOL(of_drm_find_panel);
 #endif
 
+#if IS_REACHABLE(CONFIG_BACKLIGHT_CLASS_DEVICE)
+/**
+ * drm_panel_of_backlight - use backlight device node for backlight
+ * @panel: DRM panel
+ *
+ * Use this function to enable backlight handling if your panel
+ * uses device tree and has a backlight phandle.
+ *
+ * When the panel is enabled backlight will be enabled after a
+ * successful call to &drm_panel_funcs.enable()
+ *
+ * When the panel is disabled backlight will be disabled before the
+ * call to &drm_panel_funcs.disable().
+ *
+ * A typical implementation for a panel driver supporting device tree
+ * will call this function at probe time. Backlight will then be handled
+ * transparently without requiring any intervention from the driver.
+ * drm_panel_of_backlight() must be called after the call to drm_panel_init().
+ *
+ * Return: 0 on success or a negative error code on failure.
+ */
+int drm_panel_of_backlight(struct drm_panel *panel)
+{
+	struct backlight_device *backlight;
+
+	if (!panel || !panel->dev)
+		return -EINVAL;
+
+	backlight = devm_of_find_backlight(panel->dev);
+
+	if (IS_ERR(backlight))
+		return PTR_ERR(backlight);
+
+	panel->backlight = backlight;
+	return 0;
+}
+EXPORT_SYMBOL(drm_panel_of_backlight);
+#endif
+
 MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>");
 MODULE_DESCRIPTION("DRM panel infrastructure");
 MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index a86a3ab2771c..f2e43d341980 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -125,8 +125,6 @@ void drm_pci_free(struct drm_device * dev, drm_dma_handle_t * dmah)
 
 EXPORT_SYMBOL(drm_pci_free);
 
-#ifdef CONFIG_PCI
-
 static int drm_get_pci_domain(struct drm_device *dev)
 {
 #ifndef __alpha__
@@ -284,6 +282,8 @@ err_free:
 }
 EXPORT_SYMBOL(drm_get_pci_dev);
 
+#ifdef CONFIG_DRM_LEGACY
+
 /**
  * drm_legacy_pci_init - shadow-attach a legacy DRM PCI driver
  * @driver: DRM device driver
@@ -331,17 +331,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 }
 EXPORT_SYMBOL(drm_legacy_pci_init);
 
-#else
-
-void drm_pci_agp_destroy(struct drm_device *dev) {}
-
-int drm_irq_by_busid(struct drm_device *dev, void *data,
-		     struct drm_file *file_priv)
-{
-	return -EINVAL;
-}
-#endif
-
 /**
  * drm_legacy_pci_exit - unregister shadow-attach legacy DRM driver
  * @driver: DRM device driver
@@ -367,3 +356,5 @@ void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver)
 	DRM_INFO("Module unloaded\n");
 }
 EXPORT_SYMBOL(drm_legacy_pci_exit);
+
+#endif
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 0814211b0f3f..86d9b0e45c8c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -240,6 +240,7 @@ void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv)
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info)
 {
+	struct drm_gem_object *obj = exp_info->priv;
 	struct dma_buf *dma_buf;
 
 	dma_buf = dma_buf_export(exp_info);
@@ -247,7 +248,8 @@ struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 		return dma_buf;
 
 	drm_dev_get(dev);
-	drm_gem_object_get(exp_info->priv);
+	drm_gem_object_get(obj);
+	dma_buf->file->f_mapping = obj->dev->anon_inode->i_mapping;
 
 	return dma_buf;
 }
@@ -713,6 +715,9 @@ int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	struct file *fil;
 	int ret;
 
+	/* Add the fake offset */
+	vma->vm_pgoff += drm_vma_node_start(&obj->vma_node);
+
 	if (obj->funcs && obj->funcs->mmap) {
 		ret = obj->funcs->mmap(obj, vma);
 		if (ret)
@@ -737,8 +742,6 @@ int drm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	if (ret)
 		goto out;
 
-	vma->vm_pgoff += drm_vma_node_start(&obj->vma_node);
-
 	ret = obj->dev->driver->fops->mmap(fil, vma);
 
 	drm_vma_node_revoke(&obj->vma_node, priv);
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 9a25d73c155c..111b932cf2a9 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -37,11 +37,11 @@
 #include <drm/drm_print.h>
 
 /*
- * drm_debug: Enable debug output.
+ * __drm_debug: Enable debug output.
  * Bitmask of DRM_UT_x. See include/drm/drm_print.h for details.
  */
-unsigned int drm_debug;
-EXPORT_SYMBOL(drm_debug);
+unsigned int __drm_debug;
+EXPORT_SYMBOL(__drm_debug);
 
 MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug category.\n"
 "\t\tBit 0 (0x01)  will enable CORE messages (drm core code)\n"
@@ -52,7 +52,7 @@ MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug cat
 "\t\tBit 5 (0x20)  will enable VBL messages (vblank code)\n"
 "\t\tBit 7 (0x80)  will enable LEASE messages (leasing code)\n"
 "\t\tBit 8 (0x100) will enable DP messages (displayport code)");
-module_param_named(debug, drm_debug, int, 0600);
+module_param_named(debug, __drm_debug, int, 0600);
 
 void __drm_puts_coredump(struct drm_printer *p, const char *str)
 {
@@ -256,7 +256,7 @@ void drm_dev_printk(const struct device *dev, const char *level,
 }
 EXPORT_SYMBOL(drm_dev_printk);
 
-void drm_dev_dbg(const struct device *dev, unsigned int category,
+void drm_dev_dbg(const struct device *dev, enum drm_debug_category category,
 		 const char *format, ...)
 {
 	struct va_format vaf;
@@ -280,7 +280,7 @@ void drm_dev_dbg(const struct device *dev, unsigned int category,
 }
 EXPORT_SYMBOL(drm_dev_dbg);
 
-void drm_dbg(unsigned int category, const char *format, ...)
+void __drm_dbg(enum drm_debug_category category, const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -297,9 +297,9 @@ void drm_dbg(unsigned int category, const char *format, ...)
 
 	va_end(args);
 }
-EXPORT_SYMBOL(drm_dbg);
+EXPORT_SYMBOL(__drm_dbg);
 
-void drm_err(const char *format, ...)
+void __drm_err(const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -313,7 +313,7 @@ void drm_err(const char *format, ...)
 
 	va_end(args);
 }
-EXPORT_SYMBOL(drm_err);
+EXPORT_SYMBOL(__drm_err);
 
 /**
  * drm_print_regset32 - print the contents of registers to a
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index a7c87abe88d0..576b4b7dcd89 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -101,6 +101,7 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 
 	/* Step 2: Validate against encoders and crtcs */
 	drm_connector_for_each_possible_encoder(connector, encoder) {
+		struct drm_bridge *bridge;
 		struct drm_crtc *crtc;
 
 		ret = drm_encoder_mode_valid(encoder, mode);
@@ -112,7 +113,8 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 			continue;
 		}
 
-		ret = drm_bridge_mode_valid(encoder->bridge, mode);
+		bridge = drm_bridge_chain_get_first_bridge(encoder);
+		ret = drm_bridge_chain_mode_valid(bridge, mode);
 		if (ret != MODE_OK) {
 			/* There is also no point in continuing for crtc check
 			 * here. */
diff --git a/drivers/gpu/drm/drm_rect.c b/drivers/gpu/drm/drm_rect.c
index b8363aaa9032..0460e874896e 100644
--- a/drivers/gpu/drm/drm_rect.c
+++ b/drivers/gpu/drm/drm_rect.c
@@ -52,9 +52,17 @@ bool drm_rect_intersect(struct drm_rect *r1, const struct drm_rect *r2)
 }
 EXPORT_SYMBOL(drm_rect_intersect);
 
-static u32 clip_scaled(u32 src, u32 dst, u32 clip)
+static u32 clip_scaled(int src, int dst, int *clip)
 {
-	u64 tmp = mul_u32_u32(src, dst - clip);
+	u64 tmp;
+
+	if (dst == 0)
+		return 0;
+
+	/* Only clip what we have. Keeps the result bounded. */
+	*clip = min(*clip, dst);
+
+	tmp = mul_u32_u32(src, dst - *clip);
 
 	/*
 	 * Round toward 1.0 when clipping so that we don't accidentally
@@ -73,11 +81,13 @@ static u32 clip_scaled(u32 src, u32 dst, u32 clip)
  * @clip: clip rectangle
  *
  * Clip rectangle @dst by rectangle @clip. Clip rectangle @src by the
- * same amounts multiplied by @hscale and @vscale.
+ * the corresponding amounts, retaining the vertical and horizontal scaling
+ * factors from @src to @dst.
  *
  * RETURNS:
+ *
  * %true if rectangle @dst is still visible after being clipped,
- * %false otherwise
+ * %false otherwise.
  */
 bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst,
 			  const struct drm_rect *clip)
@@ -87,34 +97,34 @@ bool drm_rect_clip_scaled(struct drm_rect *src, struct drm_rect *dst,
 	diff = clip->x1 - dst->x1;
 	if (diff > 0) {
 		u32 new_src_w = clip_scaled(drm_rect_width(src),
-					    drm_rect_width(dst), diff);
+					    drm_rect_width(dst), &diff);
 
-		src->x1 = clamp_t(int64_t, src->x2 - new_src_w, INT_MIN, INT_MAX);
-		dst->x1 = clip->x1;
+		src->x1 = src->x2 - new_src_w;
+		dst->x1 += diff;
 	}
 	diff = clip->y1 - dst->y1;
 	if (diff > 0) {
 		u32 new_src_h = clip_scaled(drm_rect_height(src),
-					    drm_rect_height(dst), diff);
+					    drm_rect_height(dst), &diff);
 
-		src->y1 = clamp_t(int64_t, src->y2 - new_src_h, INT_MIN, INT_MAX);
-		dst->y1 = clip->y1;
+		src->y1 = src->y2 - new_src_h;
+		dst->y1 += diff;
 	}
 	diff = dst->x2 - clip->x2;
 	if (diff > 0) {
 		u32 new_src_w = clip_scaled(drm_rect_width(src),
-					    drm_rect_width(dst), diff);
+					    drm_rect_width(dst), &diff);
 
-		src->x2 = clamp_t(int64_t, src->x1 + new_src_w, INT_MIN, INT_MAX);
-		dst->x2 = clip->x2;
+		src->x2 = src->x1 + new_src_w;
+		dst->x2 -= diff;
 	}
 	diff = dst->y2 - clip->y2;
 	if (diff > 0) {
 		u32 new_src_h = clip_scaled(drm_rect_height(src),
-					    drm_rect_height(dst), diff);
+					    drm_rect_height(dst), &diff);
 
-		src->y2 = clamp_t(int64_t, src->y1 + new_src_h, INT_MIN, INT_MAX);
-		dst->y2 = clip->y2;
+		src->y2 = src->y1 + new_src_h;
+		dst->y2 -= diff;
 	}
 
 	return drm_rect_visible(dst);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index ac26c084f30d..6b43c1c94e8f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -65,12 +65,13 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file)
 
 	for (i = 0; i < ETNA_MAX_PIPES; i++) {
 		struct etnaviv_gpu *gpu = priv->gpu[i];
-		struct drm_sched_rq *rq;
+		struct drm_gpu_scheduler *sched;
 
 		if (gpu) {
-			rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+			sched = &gpu->sched;
 			drm_sched_entity_init(&ctx->sched_entity[i],
-					      &rq, 1, NULL);
+					      DRM_SCHED_PRIORITY_NORMAL, &sched,
+					      1, NULL);
 			}
 	}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index aa3e4c3b063a..3b0afa156d92 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -113,7 +113,7 @@ static void submit_unlock_object(struct etnaviv_gem_submit *submit, int i)
 	if (submit->bos[i].flags & BO_LOCKED) {
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
-		ww_mutex_unlock(&obj->resv->lock);
+		dma_resv_unlock(obj->resv);
 		submit->bos[i].flags &= ~BO_LOCKED;
 	}
 }
@@ -133,8 +133,7 @@ retry:
 		contended = i;
 
 		if (!(submit->bos[i].flags & BO_LOCKED)) {
-			ret = ww_mutex_lock_interruptible(&obj->resv->lock,
-							  ticket);
+			ret = dma_resv_lock_interruptible(obj->resv, ticket);
 			if (ret == -EALREADY)
 				DRM_ERROR("BO at index %u already on submit list\n",
 					  i);
@@ -161,8 +160,7 @@ fail:
 		obj = &submit->bos[contended].obj->base;
 
 		/* we lost out in a seqno race, lock and retry.. */
-		ret = ww_mutex_lock_slow_interruptible(&obj->resv->lock,
-						       ticket);
+		ret = dma_resv_lock_slow_interruptible(obj->resv, ticket);
 		if (!ret) {
 			submit->bos[contended].flags |= BO_LOCKED;
 			slow_locked = contended;
diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig
index 6f7d3b3b3628..6417f374b923 100644
--- a/drivers/gpu/drm/exynos/Kconfig
+++ b/drivers/gpu/drm/exynos/Kconfig
@@ -1,13 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_EXYNOS
-	tristate "DRM Support for Samsung SoC EXYNOS Series"
+	tristate "DRM Support for Samsung SoC Exynos Series"
 	depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST)
 	depends on MMU
 	select DRM_KMS_HELPER
 	select VIDEOMODE_HELPERS
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	help
-	  Choose this option if you have a Samsung SoC EXYNOS chipset.
+	  Choose this option if you have a Samsung SoC Exynos chipset.
 	  If M is selected the module will be called exynosdrm.
 
 if DRM_EXYNOS
@@ -62,7 +62,7 @@ config DRM_EXYNOS_DSI
 	  This enables support for Exynos MIPI-DSI device.
 
 config DRM_EXYNOS_DP
-	bool "EXYNOS specific extensions for Analogix DP driver"
+	bool "Exynos specific extensions for Analogix DP driver"
 	depends on DRM_EXYNOS_FIMD || DRM_EXYNOS7_DECON
 	select DRM_ANALOGIX_DP
 	default DRM_EXYNOS
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 2d5cbfda3ca7..8428ae12dfa5 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -510,7 +510,7 @@ static void decon_swreset(struct decon_context *ctx)
 	       ctx->addr + DECON_CRCCTRL);
 }
 
-static void decon_enable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 
@@ -523,7 +523,7 @@ static void decon_enable(struct exynos_drm_crtc *crtc)
 	decon_commit(ctx->crtc);
 }
 
-static void decon_disable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 	int i;
@@ -599,8 +599,8 @@ static enum drm_mode_status decon_mode_valid(struct exynos_drm_crtc *crtc,
 }
 
 static const struct exynos_drm_crtc_ops decon_crtc_ops = {
-	.enable			= decon_enable,
-	.disable		= decon_disable,
+	.atomic_enable		= decon_atomic_enable,
+	.atomic_disable		= decon_atomic_disable,
 	.enable_vblank		= decon_enable_vblank,
 	.disable_vblank		= decon_disable_vblank,
 	.atomic_begin		= decon_atomic_begin,
@@ -651,7 +651,7 @@ static void decon_unbind(struct device *dev, struct device *master, void *data)
 {
 	struct decon_context *ctx = dev_get_drvdata(dev);
 
-	decon_disable(ctx->crtc);
+	decon_atomic_disable(ctx->crtc);
 
 	/* detach this sub driver from iommu mapping if supported. */
 	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f0640950bd46..ff59c641fa80 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -526,7 +526,7 @@ static void decon_init(struct decon_context *ctx)
 		writel(VIDCON1_VCLK_HOLD, ctx->regs + VIDCON1(0));
 }
 
-static void decon_enable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 
@@ -546,7 +546,7 @@ static void decon_enable(struct exynos_drm_crtc *crtc)
 	ctx->suspended = false;
 }
 
-static void decon_disable(struct exynos_drm_crtc *crtc)
+static void decon_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct decon_context *ctx = crtc->ctx;
 	int i;
@@ -568,8 +568,8 @@ static void decon_disable(struct exynos_drm_crtc *crtc)
 }
 
 static const struct exynos_drm_crtc_ops decon_crtc_ops = {
-	.enable = decon_enable,
-	.disable = decon_disable,
+	.atomic_enable = decon_atomic_enable,
+	.atomic_disable = decon_atomic_disable,
 	.enable_vblank = decon_enable_vblank,
 	.disable_vblank = decon_disable_vblank,
 	.atomic_begin = decon_atomic_begin,
@@ -653,7 +653,7 @@ static void decon_unbind(struct device *dev, struct device *master,
 {
 	struct decon_context *ctx = dev_get_drvdata(dev);
 
-	decon_disable(ctx->crtc);
+	decon_atomic_disable(ctx->crtc);
 
 	if (ctx->encoder)
 		exynos_dpi_remove(ctx->encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 1e6aa24bf45e..4785885c0f4f 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -110,7 +110,6 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data,
 		if (ret) {
 			DRM_DEV_ERROR(dp->dev,
 				      "Failed to attach bridge to drm\n");
-			bridge->next = NULL;
 			return ret;
 		}
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 77ce78986408..1c03485676ef 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -23,8 +23,8 @@ static void exynos_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 {
 	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
 
-	if (exynos_crtc->ops->enable)
-		exynos_crtc->ops->enable(exynos_crtc);
+	if (exynos_crtc->ops->atomic_enable)
+		exynos_crtc->ops->atomic_enable(exynos_crtc);
 
 	drm_crtc_vblank_on(crtc);
 }
@@ -36,8 +36,8 @@ static void exynos_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	drm_crtc_vblank_off(crtc);
 
-	if (exynos_crtc->ops->disable)
-		exynos_crtc->ops->disable(exynos_crtc);
+	if (exynos_crtc->ops->atomic_disable)
+		exynos_crtc->ops->atomic_disable(exynos_crtc);
 
 	if (crtc->state->event && !crtc->state->active) {
 		spin_lock_irq(&crtc->dev->event_lock);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 3cebb19ec1c4..43fa0f26c052 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -43,7 +43,7 @@ exynos_dpi_detect(struct drm_connector *connector, bool force)
 {
 	struct exynos_dpi *ctx = connector_to_dpi(connector);
 
-	if (ctx->panel && !ctx->panel->connector)
+	if (ctx->panel)
 		drm_panel_attach(ctx->panel, &ctx->connector);
 
 	return connector_status_connected;
@@ -85,7 +85,7 @@ static int exynos_dpi_get_modes(struct drm_connector *connector)
 	}
 
 	if (ctx->panel)
-		return ctx->panel->funcs->get_modes(ctx->panel);
+		return drm_panel_get_modes(ctx->panel, connector);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index d4014ba592fd..d4d21d8cfb90 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -118,8 +118,8 @@ struct exynos_drm_plane_config {
 /*
  * Exynos drm crtc ops
  *
- * @enable: enable the device
- * @disable: disable the device
+ * @atomic_enable: enable the device
+ * @atomic_disable: disable the device
  * @enable_vblank: specific driver callback for enabling vblank interrupt.
  * @disable_vblank: specific driver callback for disabling vblank interrupt.
  * @mode_valid: specific driver callback for mode validation
@@ -133,8 +133,8 @@ struct exynos_drm_plane_config {
  */
 struct exynos_drm_crtc;
 struct exynos_drm_crtc_ops {
-	void (*enable)(struct exynos_drm_crtc *crtc);
-	void (*disable)(struct exynos_drm_crtc *crtc);
+	void (*atomic_enable)(struct exynos_drm_crtc *crtc);
+	void (*atomic_disable)(struct exynos_drm_crtc *crtc);
 	int (*enable_vblank)(struct exynos_drm_crtc *crtc);
 	void (*disable_vblank)(struct exynos_drm_crtc *crtc);
 	enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 72726f2c7a9f..33628d85edad 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -255,6 +255,7 @@ struct exynos_dsi {
 	struct mipi_dsi_host dsi_host;
 	struct drm_connector connector;
 	struct drm_panel *panel;
+	struct list_head bridge_chain;
 	struct drm_bridge *out_bridge;
 	struct device *dev;
 
@@ -1377,6 +1378,7 @@ static void exynos_dsi_unregister_te_irq(struct exynos_dsi *dsi)
 static void exynos_dsi_enable(struct drm_encoder *encoder)
 {
 	struct exynos_dsi *dsi = encoder_to_dsi(encoder);
+	struct drm_bridge *iter;
 	int ret;
 
 	if (dsi->state & DSIM_STATE_ENABLED)
@@ -1390,7 +1392,11 @@ static void exynos_dsi_enable(struct drm_encoder *encoder)
 		if (ret < 0)
 			goto err_put_sync;
 	} else {
-		drm_bridge_pre_enable(dsi->out_bridge);
+		list_for_each_entry_reverse(iter, &dsi->bridge_chain,
+					    chain_node) {
+			if (iter->funcs->pre_enable)
+				iter->funcs->pre_enable(iter);
+		}
 	}
 
 	exynos_dsi_set_display_mode(dsi);
@@ -1401,7 +1407,10 @@ static void exynos_dsi_enable(struct drm_encoder *encoder)
 		if (ret < 0)
 			goto err_display_disable;
 	} else {
-		drm_bridge_enable(dsi->out_bridge);
+		list_for_each_entry(iter, &dsi->bridge_chain, chain_node) {
+			if (iter->funcs->enable)
+				iter->funcs->enable(iter);
+		}
 	}
 
 	dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE;
@@ -1419,6 +1428,7 @@ err_put_sync:
 static void exynos_dsi_disable(struct drm_encoder *encoder)
 {
 	struct exynos_dsi *dsi = encoder_to_dsi(encoder);
+	struct drm_bridge *iter;
 
 	if (!(dsi->state & DSIM_STATE_ENABLED))
 		return;
@@ -1426,10 +1436,20 @@ static void exynos_dsi_disable(struct drm_encoder *encoder)
 	dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE;
 
 	drm_panel_disable(dsi->panel);
-	drm_bridge_disable(dsi->out_bridge);
+
+	list_for_each_entry_reverse(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->disable)
+			iter->funcs->disable(iter);
+	}
+
 	exynos_dsi_set_display_enable(dsi, false);
 	drm_panel_unprepare(dsi->panel);
-	drm_bridge_post_disable(dsi->out_bridge);
+
+	list_for_each_entry(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->post_disable)
+			iter->funcs->post_disable(iter);
+	}
+
 	dsi->state &= ~DSIM_STATE_ENABLED;
 	pm_runtime_put_sync(dsi->dev);
 }
@@ -1461,7 +1481,7 @@ static int exynos_dsi_get_modes(struct drm_connector *connector)
 	struct exynos_dsi *dsi = connector_to_dsi(connector);
 
 	if (dsi->panel)
-		return dsi->panel->funcs->get_modes(dsi->panel);
+		return drm_panel_get_modes(dsi->panel, connector);
 
 	return 0;
 }
@@ -1522,7 +1542,7 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 	if (out_bridge) {
 		drm_bridge_attach(encoder, out_bridge, NULL);
 		dsi->out_bridge = out_bridge;
-		encoder->bridge = NULL;
+		list_splice_init(&encoder->bridge_chain, &dsi->bridge_chain);
 	} else {
 		int ret = exynos_dsi_create_connector(encoder);
 
@@ -1588,6 +1608,7 @@ static int exynos_dsi_host_detach(struct mipi_dsi_host *host,
 		if (dsi->out_bridge->funcs->detach)
 			dsi->out_bridge->funcs->detach(dsi->out_bridge);
 		dsi->out_bridge = NULL;
+		INIT_LIST_HEAD(&dsi->bridge_chain);
 	}
 
 	if (drm->mode_config.poll_enabled)
@@ -1735,6 +1756,7 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 	init_completion(&dsi->completed);
 	spin_lock_init(&dsi->transfer_lock);
 	INIT_LIST_HEAD(&dsi->transfer_list);
+	INIT_LIST_HEAD(&dsi->bridge_chain);
 
 	dsi->dsi_host.ops = &exynos_dsi_ops;
 	dsi->dsi_host.dev = dev;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index b0877b97291c..647a1fd1d815 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -60,7 +60,7 @@ static int exynos_drm_fb_mmap(struct fb_info *info,
 	return 0;
 }
 
-static struct fb_ops exynos_drm_fb_ops = {
+static const struct fb_ops exynos_drm_fb_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_mmap        = exynos_drm_fb_mmap,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 8d0a929104e5..21aec38702fc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -894,7 +894,7 @@ static void fimd_disable_plane(struct exynos_drm_crtc *crtc,
 		fimd_enable_shadow_channel_path(ctx, win, false);
 }
 
-static void fimd_enable(struct exynos_drm_crtc *crtc)
+static void fimd_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct fimd_context *ctx = crtc->ctx;
 
@@ -912,7 +912,7 @@ static void fimd_enable(struct exynos_drm_crtc *crtc)
 	fimd_commit(ctx->crtc);
 }
 
-static void fimd_disable(struct exynos_drm_crtc *crtc)
+static void fimd_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct fimd_context *ctx = crtc->ctx;
 	int i;
@@ -1006,8 +1006,8 @@ static void fimd_dp_clock_enable(struct exynos_drm_clk *clk, bool enable)
 }
 
 static const struct exynos_drm_crtc_ops fimd_crtc_ops = {
-	.enable = fimd_enable,
-	.disable = fimd_disable,
+	.atomic_enable = fimd_atomic_enable,
+	.atomic_disable = fimd_atomic_disable,
 	.enable_vblank = fimd_enable_vblank,
 	.disable_vblank = fimd_disable_vblank,
 	.atomic_begin = fimd_atomic_begin,
@@ -1098,7 +1098,7 @@ static void fimd_unbind(struct device *dev, struct device *master,
 {
 	struct fimd_context *ctx = dev_get_drvdata(dev);
 
-	fimd_disable(ctx->crtc);
+	fimd_atomic_disable(ctx->crtc);
 
 	exynos_drm_unregister_dma(ctx->drm_dev, ctx->dev);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 65b891cb9c50..b320b3a21ad4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -120,7 +120,7 @@ static void vidi_update_plane(struct exynos_drm_crtc *crtc,
 	DRM_DEV_DEBUG_KMS(ctx->dev, "dma_addr = %pad\n", &addr);
 }
 
-static void vidi_enable(struct exynos_drm_crtc *crtc)
+static void vidi_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct vidi_context *ctx = crtc->ctx;
 
@@ -133,7 +133,7 @@ static void vidi_enable(struct exynos_drm_crtc *crtc)
 	drm_crtc_vblank_on(&crtc->base);
 }
 
-static void vidi_disable(struct exynos_drm_crtc *crtc)
+static void vidi_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct vidi_context *ctx = crtc->ctx;
 
@@ -147,8 +147,8 @@ static void vidi_disable(struct exynos_drm_crtc *crtc)
 }
 
 static const struct exynos_drm_crtc_ops vidi_crtc_ops = {
-	.enable = vidi_enable,
-	.disable = vidi_disable,
+	.atomic_enable = vidi_atomic_enable,
+	.atomic_disable = vidi_atomic_disable,
 	.enable_vblank = vidi_enable_vblank,
 	.disable_vblank = vidi_disable_vblank,
 	.update_plane = vidi_update_plane,
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 48159d5d2214..9ff921f43a93 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -946,8 +946,10 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	connector->interlace_allowed = true;
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 
-	ret = drm_connector_init(hdata->drm_dev, connector,
-			&hdmi_connector_funcs, DRM_MODE_CONNECTOR_HDMIA);
+	ret = drm_connector_init_with_ddc(hdata->drm_dev, connector,
+					  &hdmi_connector_funcs,
+					  DRM_MODE_CONNECTOR_HDMIA,
+					  hdata->ddc_adpt);
 	if (ret) {
 		DRM_DEV_ERROR(hdata->dev,
 			      "Failed to initialize connector with drm\n");
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 6cfdb95fef2f..38ae9c32feef 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -986,7 +986,7 @@ static void mixer_atomic_flush(struct exynos_drm_crtc *crtc)
 	exynos_crtc_handle_event(crtc);
 }
 
-static void mixer_enable(struct exynos_drm_crtc *crtc)
+static void mixer_atomic_enable(struct exynos_drm_crtc *crtc)
 {
 	struct mixer_context *ctx = crtc->ctx;
 
@@ -1015,7 +1015,7 @@ static void mixer_enable(struct exynos_drm_crtc *crtc)
 	set_bit(MXR_BIT_POWERED, &ctx->flags);
 }
 
-static void mixer_disable(struct exynos_drm_crtc *crtc)
+static void mixer_atomic_disable(struct exynos_drm_crtc *crtc)
 {
 	struct mixer_context *ctx = crtc->ctx;
 	int i;
@@ -1109,8 +1109,8 @@ static bool mixer_mode_fixup(struct exynos_drm_crtc *crtc,
 }
 
 static const struct exynos_drm_crtc_ops mixer_crtc_ops = {
-	.enable			= mixer_enable,
-	.disable		= mixer_disable,
+	.atomic_enable		= mixer_atomic_enable,
+	.atomic_disable		= mixer_atomic_disable,
 	.enable_vblank		= mixer_enable_vblank,
 	.disable_vblank		= mixer_disable_vblank,
 	.atomic_begin		= mixer_atomic_begin,
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 82c972e9c024..9598ee3cc4d2 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -68,7 +68,7 @@ static int fsl_dcu_drm_connector_get_modes(struct drm_connector *connector)
 	struct fsl_dcu_drm_connector *fsl_connector;
 
 	fsl_connector = to_fsl_dcu_connector(connector);
-	return drm_panel_get_modes(fsl_connector->panel);
+	return drm_panel_get_modes(fsl_connector->panel, connector);
 }
 
 static int fsl_dcu_drm_connector_mode_valid(struct drm_connector *connector,
diff --git a/drivers/gpu/drm/gma500/accel_2d.c b/drivers/gpu/drm/gma500/accel_2d.c
index 45ad5ffedc93..adc0507545bf 100644
--- a/drivers/gpu/drm/gma500/accel_2d.c
+++ b/drivers/gpu/drm/gma500/accel_2d.c
@@ -21,9 +21,9 @@
 
 #include <drm/drm.h>
 #include <drm/drm_crtc.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
 
-#include "framebuffer.h"
 #include "psb_drv.h"
 #include "psb_reg.h"
 
@@ -226,11 +226,10 @@ static int psb_accel_2d_copy(struct drm_psb_private *dev_priv,
 static void psbfb_copyarea_accel(struct fb_info *info,
 				 const struct fb_copyarea *a)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
-	struct drm_device *dev = psbfb->base.dev;
-	struct drm_framebuffer *fb = fbdev->psb_fb_helper.fb;
-	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev;
+	struct drm_psb_private *dev_priv;
 	uint32_t offset;
 	uint32_t stride;
 	uint32_t src_format;
@@ -239,6 +238,8 @@ static void psbfb_copyarea_accel(struct fb_info *info,
 	if (!fb)
 		return;
 
+	dev = fb->dev;
+	dev_priv = dev->dev_private;
 	offset = to_gtt_range(fb->obj[0])->offset;
 	stride = fb->pitches[0];
 
@@ -309,9 +310,9 @@ void psbfb_copyarea(struct fb_info *info,
  */
 int psbfb_sync(struct fb_info *info)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
-	struct drm_device *dev = psbfb->base.dev;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev = fb->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	unsigned long _end = jiffies + HZ;
 	int busy = 0;
diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c
index 8b784947ed3b..1ed854f498b7 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_display.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_display.c
@@ -582,8 +582,8 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 	struct gma_clock_t clock;
 	u32 dpll = 0, dspcntr, pipeconf;
 	bool ok;
-	bool is_crt = false, is_lvds = false, is_tv = false;
-	bool is_hdmi = false, is_dp = false;
+	bool is_lvds = false, is_tv = false;
+	bool is_dp = false;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
 	const struct gma_limit_t *limit;
@@ -607,10 +607,7 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc,
 			is_tv = true;
 			break;
 		case INTEL_OUTPUT_ANALOG:
-			is_crt = true;
-			break;
 		case INTEL_OUTPUT_HDMI:
-			is_hdmi = true;
 			break;
 		case INTEL_OUTPUT_DISPLAYPORT:
 			is_dp = true;
@@ -979,6 +976,7 @@ const struct drm_crtc_funcs cdv_intel_crtc_funcs = {
 	.gamma_set = gma_crtc_gamma_set,
 	.set_config = gma_crtc_set_config,
 	.destroy = gma_crtc_destroy,
+	.page_flip = gma_crtc_page_flip,
 };
 
 const struct gma_clock_funcs cdv_clock_funcs = {
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 570b59520fd1..5772b2dce0d6 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -1594,7 +1594,6 @@ cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct cdv_intel_dp *intel_dp = encoder->dev_priv;
-	bool channel_eq = false;
 	int tries, cr_tries;
 	u32 reg;
 	uint32_t DP = intel_dp->DP;
@@ -1602,7 +1601,6 @@ cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 	/* channel equalization */
 	tries = 0;
 	cr_tries = 0;
-	channel_eq = false;
 
 	DRM_DEBUG_KMS("\n");
 		reg = DP | DP_LINK_TRAIN_PAT_2;
@@ -1648,7 +1646,6 @@ cdv_intel_dp_complete_link_train(struct gma_encoder *encoder)
 
 		if (cdv_intel_channel_eq_ok(encoder)) {
 			DRM_DEBUG_KMS("PT2 train is done\n");
-			channel_eq = true;
 			break;
 		}
 
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 218f3bb15276..1459076d1980 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -40,8 +40,8 @@ static int psbfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 			   unsigned blue, unsigned transp,
 			   struct fb_info *info)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct drm_framebuffer *fb = fbdev->psb_fb_helper.fb;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
 	uint32_t v;
 
 	if (!fb)
@@ -77,10 +77,10 @@ static int psbfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static int psbfb_pan(struct fb_var_screeninfo *var, struct fb_info *info)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
-	struct drm_device *dev = psbfb->base.dev;
-	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct drm_device *dev = fb->dev;
+	struct gtt_range *gtt = to_gtt_range(fb->obj[0]);
 
 	/*
 	 *	We have to poke our nose in here. The core fb code assumes
@@ -99,10 +99,10 @@ static int psbfb_pan(struct fb_var_screeninfo *var, struct fb_info *info)
 static vm_fault_t psbfb_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct psb_framebuffer *psbfb = vma->vm_private_data;
-	struct drm_device *dev = psbfb->base.dev;
+	struct drm_framebuffer *fb = vma->vm_private_data;
+	struct drm_device *dev = fb->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
-	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
+	struct gtt_range *gtt = to_gtt_range(fb->obj[0]);
 	int page_num;
 	int i;
 	unsigned long address;
@@ -145,23 +145,21 @@ static const struct vm_operations_struct psbfb_vm_ops = {
 
 static int psbfb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 {
-	struct psb_fbdev *fbdev = info->par;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
+	struct drm_fb_helper *fb_helper = info->par;
+	struct drm_framebuffer *fb = fb_helper->fb;
 
 	if (vma->vm_pgoff != 0)
 		return -EINVAL;
 	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
 		return -EINVAL;
 
-	if (!psbfb->addr_space)
-		psbfb->addr_space = vma->vm_file->f_mapping;
 	/*
 	 * If this is a GEM object then info->screen_base is the virtual
 	 * kernel remapping of the object. FIXME: Review if this is
 	 * suitable for our mmap work
 	 */
 	vma->vm_ops = &psbfb_vm_ops;
-	vma->vm_private_data = (void *)psbfb;
+	vma->vm_private_data = (void *)fb;
 	vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 }
@@ -209,9 +207,9 @@ static struct fb_ops psbfb_unaccel_ops = {
  *	0 on success or an error code if we fail.
  */
 static int psb_framebuffer_init(struct drm_device *dev,
-					struct psb_framebuffer *fb,
+					struct drm_framebuffer *fb,
 					const struct drm_mode_fb_cmd2 *mode_cmd,
-					struct gtt_range *gt)
+					struct drm_gem_object *obj)
 {
 	const struct drm_format_info *info;
 	int ret;
@@ -227,9 +225,9 @@ static int psb_framebuffer_init(struct drm_device *dev,
 	if (mode_cmd->pitches[0] & 63)
 		return -EINVAL;
 
-	drm_helper_mode_fill_fb_struct(dev, &fb->base, mode_cmd);
-	fb->base.obj[0] = &gt->gem;
-	ret = drm_framebuffer_init(dev, &fb->base, &psb_fb_funcs);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
+	fb->obj[0] = obj;
+	ret = drm_framebuffer_init(dev, fb, &psb_fb_funcs);
 	if (ret) {
 		dev_err(dev->dev, "framebuffer init failed: %d\n", ret);
 		return ret;
@@ -252,21 +250,21 @@ static int psb_framebuffer_init(struct drm_device *dev,
 static struct drm_framebuffer *psb_framebuffer_create
 			(struct drm_device *dev,
 			 const struct drm_mode_fb_cmd2 *mode_cmd,
-			 struct gtt_range *gt)
+			 struct drm_gem_object *obj)
 {
-	struct psb_framebuffer *fb;
+	struct drm_framebuffer *fb;
 	int ret;
 
 	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
 	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	ret = psb_framebuffer_init(dev, fb, mode_cmd, gt);
+	ret = psb_framebuffer_init(dev, fb, mode_cmd, obj);
 	if (ret) {
 		kfree(fb);
 		return ERR_PTR(ret);
 	}
-	return &fb->base;
+	return fb;
 }
 
 /**
@@ -300,14 +298,13 @@ static struct gtt_range *psbfb_alloc(struct drm_device *dev, int aligned_size)
  *
  *	Create a framebuffer to the specifications provided
  */
-static int psbfb_create(struct psb_fbdev *fbdev,
+static int psbfb_create(struct drm_fb_helper *fb_helper,
 				struct drm_fb_helper_surface_size *sizes)
 {
-	struct drm_device *dev = fbdev->psb_fb_helper.dev;
+	struct drm_device *dev = fb_helper->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct fb_info *info;
 	struct drm_framebuffer *fb;
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
 	struct drm_mode_fb_cmd2 mode_cmd;
 	int size;
 	int ret;
@@ -372,7 +369,7 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 
 	memset(dev_priv->vram_addr + backing->offset, 0, size);
 
-	info = drm_fb_helper_alloc_fbi(&fbdev->psb_fb_helper);
+	info = drm_fb_helper_alloc_fbi(fb_helper);
 	if (IS_ERR(info)) {
 		ret = PTR_ERR(info);
 		goto out;
@@ -380,14 +377,13 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 
 	mode_cmd.pixel_format = drm_mode_legacy_fb_format(bpp, depth);
 
-	ret = psb_framebuffer_init(dev, psbfb, &mode_cmd, backing);
-	if (ret)
+	fb = psb_framebuffer_create(dev, &mode_cmd, &backing->gem);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto out;
+	}
 
-	fb = &psbfb->base;
-	psbfb->fbdev = info;
-
-	fbdev->psb_fb_helper.fb = fb;
+	fb_helper->fb = fb;
 
 	if (dev_priv->ops->accel_2d && pitch_lines > 8)	/* 2D engine */
 		info->fbops = &psbfb_ops;
@@ -411,15 +407,14 @@ static int psbfb_create(struct psb_fbdev *fbdev,
 		info->apertures->ranges[0].size = dev_priv->gtt.stolen_size;
 	}
 
-	drm_fb_helper_fill_info(info, &fbdev->psb_fb_helper, sizes);
+	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
 	info->fix.mmio_start = pci_resource_start(dev->pdev, 0);
 	info->fix.mmio_len = pci_resource_len(dev->pdev, 0);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	dev_dbg(dev->dev, "allocated %dx%d fb\n",
-					psbfb->base.width, psbfb->base.height);
+	dev_dbg(dev->dev, "allocated %dx%d fb\n", fb->width, fb->height);
 
 	return 0;
 out:
@@ -439,7 +434,6 @@ static struct drm_framebuffer *psb_user_framebuffer_create
 			(struct drm_device *dev, struct drm_file *filp,
 			 const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct gtt_range *r;
 	struct drm_gem_object *obj;
 
 	/*
@@ -451,17 +445,15 @@ static struct drm_framebuffer *psb_user_framebuffer_create
 		return ERR_PTR(-ENOENT);
 
 	/* Let the core code do all the work */
-	r = container_of(obj, struct gtt_range, gem);
-	return psb_framebuffer_create(dev, cmd, r);
+	return psb_framebuffer_create(dev, cmd, obj);
 }
 
-static int psbfb_probe(struct drm_fb_helper *helper,
+static int psbfb_probe(struct drm_fb_helper *fb_helper,
 				struct drm_fb_helper_surface_size *sizes)
 {
-	struct psb_fbdev *psb_fbdev =
-		container_of(helper, struct psb_fbdev, psb_fb_helper);
-	struct drm_device *dev = psb_fbdev->psb_fb_helper.dev;
+	struct drm_device *dev = fb_helper->dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	unsigned int fb_size;
 	int bytespp;
 
 	bytespp = sizes->surface_bpp / 8;
@@ -471,72 +463,77 @@ static int psbfb_probe(struct drm_fb_helper *helper,
 	/* If the mode will not fit in 32bit then switch to 16bit to get
 	   a console on full resolution. The X mode setting server will
 	   allocate its own 32bit GEM framebuffer */
-	if (ALIGN(sizes->fb_width * bytespp, 64) * sizes->fb_height >
-	                dev_priv->vram_stolen_size) {
+	fb_size = ALIGN(sizes->surface_width * bytespp, 64) *
+		  sizes->surface_height;
+	fb_size = ALIGN(fb_size, PAGE_SIZE);
+
+	if (fb_size > dev_priv->vram_stolen_size) {
                 sizes->surface_bpp = 16;
                 sizes->surface_depth = 16;
         }
 
-	return psbfb_create(psb_fbdev, sizes);
+	return psbfb_create(fb_helper, sizes);
 }
 
 static const struct drm_fb_helper_funcs psb_fb_helper_funcs = {
 	.fb_probe = psbfb_probe,
 };
 
-static int psb_fbdev_destroy(struct drm_device *dev, struct psb_fbdev *fbdev)
+static int psb_fbdev_destroy(struct drm_device *dev,
+			     struct drm_fb_helper *fb_helper)
 {
-	struct psb_framebuffer *psbfb = &fbdev->pfb;
+	struct drm_framebuffer *fb = fb_helper->fb;
+
+	drm_fb_helper_unregister_fbi(fb_helper);
 
-	drm_fb_helper_unregister_fbi(&fbdev->psb_fb_helper);
+	drm_fb_helper_fini(fb_helper);
+	drm_framebuffer_unregister_private(fb);
+	drm_framebuffer_cleanup(fb);
 
-	drm_fb_helper_fini(&fbdev->psb_fb_helper);
-	drm_framebuffer_unregister_private(&psbfb->base);
-	drm_framebuffer_cleanup(&psbfb->base);
+	if (fb->obj[0])
+		drm_gem_object_put_unlocked(fb->obj[0]);
+	kfree(fb);
 
-	if (psbfb->base.obj[0])
-		drm_gem_object_put_unlocked(psbfb->base.obj[0]);
 	return 0;
 }
 
 int psb_fbdev_init(struct drm_device *dev)
 {
-	struct psb_fbdev *fbdev;
+	struct drm_fb_helper *fb_helper;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	int ret;
 
-	fbdev = kzalloc(sizeof(struct psb_fbdev), GFP_KERNEL);
-	if (!fbdev) {
+	fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL);
+	if (!fb_helper) {
 		dev_err(dev->dev, "no memory\n");
 		return -ENOMEM;
 	}
 
-	dev_priv->fbdev = fbdev;
+	dev_priv->fb_helper = fb_helper;
 
-	drm_fb_helper_prepare(dev, &fbdev->psb_fb_helper, &psb_fb_helper_funcs);
+	drm_fb_helper_prepare(dev, fb_helper, &psb_fb_helper_funcs);
 
-	ret = drm_fb_helper_init(dev, &fbdev->psb_fb_helper,
-				 INTELFB_CONN_LIMIT);
+	ret = drm_fb_helper_init(dev, fb_helper, INTELFB_CONN_LIMIT);
 	if (ret)
 		goto free;
 
-	ret = drm_fb_helper_single_add_all_connectors(&fbdev->psb_fb_helper);
+	ret = drm_fb_helper_single_add_all_connectors(fb_helper);
 	if (ret)
 		goto fini;
 
 	/* disable all the possible outputs/crtcs before entering KMS mode */
 	drm_helper_disable_unused_functions(dev);
 
-	ret = drm_fb_helper_initial_config(&fbdev->psb_fb_helper, 32);
+	ret = drm_fb_helper_initial_config(fb_helper, 32);
 	if (ret)
 		goto fini;
 
 	return 0;
 
 fini:
-	drm_fb_helper_fini(&fbdev->psb_fb_helper);
+	drm_fb_helper_fini(fb_helper);
 free:
-	kfree(fbdev);
+	kfree(fb_helper);
 	return ret;
 }
 
@@ -544,12 +541,12 @@ static void psb_fbdev_fini(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
-	if (!dev_priv->fbdev)
+	if (!dev_priv->fb_helper)
 		return;
 
-	psb_fbdev_destroy(dev, dev_priv->fbdev);
-	kfree(dev_priv->fbdev);
-	dev_priv->fbdev = NULL;
+	psb_fbdev_destroy(dev, dev_priv->fb_helper);
+	kfree(dev_priv->fb_helper);
+	dev_priv->fb_helper = NULL;
 }
 
 static const struct drm_mode_config_funcs psb_mode_funcs = {
diff --git a/drivers/gpu/drm/gma500/framebuffer.h b/drivers/gpu/drm/gma500/framebuffer.h
index ae8a02639fd9..2fbba4b48841 100644
--- a/drivers/gpu/drm/gma500/framebuffer.h
+++ b/drivers/gpu/drm/gma500/framebuffer.h
@@ -9,23 +9,8 @@
 #ifndef _FRAMEBUFFER_H_
 #define _FRAMEBUFFER_H_
 
-#include <drm/drm_fb_helper.h>
-
 #include "psb_drv.h"
 
-struct psb_framebuffer {
-	struct drm_framebuffer base;
-	struct address_space *addr_space;
-	struct fb_info *fbdev;
-};
-
-struct psb_fbdev {
-	struct drm_fb_helper psb_fb_helper; /* must be first */
-	struct psb_framebuffer pfb;
-};
-
-#define to_psb_fb(x) container_of(x, struct psb_framebuffer, base)
-
 extern int gma_connector_clones(struct drm_device *dev, int type_mask);
 
 #endif
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index e20ccb5d10fd..17f136985d21 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -255,6 +255,8 @@ void gma_crtc_dpms(struct drm_crtc *crtc, int mode)
 		/* Give the overlay scaler a chance to enable
 		 * if it's on this pipe */
 		/* psb_intel_crtc_dpms_video(crtc, true); TODO */
+
+		drm_crtc_vblank_on(crtc);
 		break;
 	case DRM_MODE_DPMS_OFF:
 		if (!gma_crtc->active)
@@ -501,6 +503,52 @@ void gma_crtc_destroy(struct drm_crtc *crtc)
 	kfree(gma_crtc);
 }
 
+int gma_crtc_page_flip(struct drm_crtc *crtc,
+		       struct drm_framebuffer *fb,
+		       struct drm_pending_vblank_event *event,
+		       uint32_t page_flip_flags,
+		       struct drm_modeset_acquire_ctx *ctx)
+{
+	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+	struct drm_framebuffer *current_fb = crtc->primary->fb;
+	struct drm_framebuffer *old_fb = crtc->primary->old_fb;
+	const struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+	int ret;
+
+	if (!crtc_funcs->mode_set_base)
+		return -EINVAL;
+
+	/* Using mode_set_base requires the new fb to be set already. */
+	crtc->primary->fb = fb;
+
+	if (event) {
+		spin_lock_irqsave(&dev->event_lock, flags);
+
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+
+		gma_crtc->page_flip_event = event;
+
+		/* Call this locked if we want an event at vblank interrupt. */
+		ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb);
+		if (ret) {
+			gma_crtc->page_flip_event = NULL;
+			drm_crtc_vblank_put(crtc);
+		}
+
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	} else {
+		ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb);
+	}
+
+	/* Restore previous fb in case of failure. */
+	if (ret)
+		crtc->primary->fb = current_fb;
+
+	return ret;
+}
+
 int gma_crtc_set_config(struct drm_mode_set *set,
 			struct drm_modeset_acquire_ctx *ctx)
 {
diff --git a/drivers/gpu/drm/gma500/gma_display.h b/drivers/gpu/drm/gma500/gma_display.h
index fdbd7ecaa59c..7bd6c1ee8b21 100644
--- a/drivers/gpu/drm/gma500/gma_display.h
+++ b/drivers/gpu/drm/gma500/gma_display.h
@@ -11,6 +11,7 @@
 #define _GMA_DISPLAY_H_
 
 #include <linux/pm_runtime.h>
+#include <drm/drm_vblank.h>
 
 struct drm_encoder;
 struct drm_mode_set;
@@ -71,6 +72,11 @@ extern void gma_crtc_prepare(struct drm_crtc *crtc);
 extern void gma_crtc_commit(struct drm_crtc *crtc);
 extern void gma_crtc_disable(struct drm_crtc *crtc);
 extern void gma_crtc_destroy(struct drm_crtc *crtc);
+extern int gma_crtc_page_flip(struct drm_crtc *crtc,
+			      struct drm_framebuffer *fb,
+			      struct drm_pending_vblank_event *event,
+			      uint32_t page_flip_flags,
+			      struct drm_modeset_acquire_ctx *ctx);
 extern int gma_crtc_set_config(struct drm_mode_set *set,
 			       struct drm_modeset_acquire_ctx *ctx);
 
diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index b8bfb96008b8..4fff110c4921 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -113,27 +113,6 @@ static int psb_intel_panel_fitter_pipe(struct drm_device *dev)
 	return (pfit_control >> 29) & 0x3;
 }
 
-static struct drm_device globle_dev;
-
-void mdfld__intel_plane_set_alpha(int enable)
-{
-	struct drm_device *dev = &globle_dev;
-	int dspcntr_reg = DSPACNTR;
-	u32 dspcntr;
-
-	dspcntr = REG_READ(dspcntr_reg);
-
-	if (enable) {
-		dspcntr &= ~DISPPLANE_32BPP_NO_ALPHA;
-		dspcntr |= DISPPLANE_32BPP;
-	} else {
-		dspcntr &= ~DISPPLANE_32BPP;
-		dspcntr |= DISPPLANE_32BPP_NO_ALPHA;
-	}
-
-	REG_WRITE(dspcntr_reg, dspcntr);
-}
-
 static int check_fb(struct drm_framebuffer *fb)
 {
 	if (!fb)
@@ -164,8 +143,6 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	u32 dspcntr;
 	int ret;
 
-	memcpy(&globle_dev, dev, sizeof(struct drm_device));
-
 	dev_dbg(dev->dev, "pipe = 0x%x.\n", pipe);
 
 	/* no fb bound */
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index f4c520893ceb..f4370232767d 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -159,9 +159,7 @@ static void oaktrail_hdmi_audio_disable(struct drm_device *dev)
 
 static unsigned int htotal_calculate(struct drm_display_mode *mode)
 {
-	u32 htotal, new_crtc_htotal;
-
-	htotal = (mode->crtc_hdisplay - 1) | ((mode->crtc_htotal - 1) << 16);
+	u32 new_crtc_htotal;
 
 	/*
 	 * 1024 x 768  new_crtc_htotal = 0x1024;
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index 7390403ea1b7..582e09597500 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -117,6 +117,7 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder,
 
 	if (!connector) {
 		DRM_ERROR("Couldn't find connector when setting mode");
+		gma_power_end(dev);
 		return;
 	}
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 0900052fc484..6956c8e7501c 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -19,10 +19,10 @@
 
 #include <drm/drm.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/drm_vblank.h>
 
@@ -426,14 +426,48 @@ static long psb_unlocked_ioctl(struct file *filp, unsigned int cmd,
 
 static int psb_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	return drm_get_pci_dev(pdev, ent, &driver);
-}
+	struct drm_device *dev;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = psb_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
 
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_psb_driver_unload;
+
+	return 0;
+
+err_psb_driver_unload:
+	psb_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+}
 
 static void psb_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
-	drm_put_dev(dev);
+
+	drm_dev_unregister(dev);
+	psb_driver_unload(dev);
+	drm_dev_put(dev);
 }
 
 static const struct dev_pm_ops psb_pm_ops = {
@@ -466,8 +500,6 @@ static const struct file_operations psb_gem_fops = {
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM,
-	.load = psb_driver_load,
-	.unload = psb_driver_unload,
 	.lastclose = drm_fb_helper_lastclose,
 
 	.num_ioctls = ARRAY_SIZE(psb_ioctls),
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 9b3c03f4a38d..3d4ef3071d45 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -229,6 +229,8 @@ enum {
 #define KSEL_BYPASS_25 6
 #define KSEL_BYPASS_83_100 7
 
+struct drm_fb_helper;
+
 struct opregion_header;
 struct opregion_acpi;
 struct opregion_swsci;
@@ -432,7 +434,7 @@ struct drm_psb_private {
 	struct pci_dev *lpc_pdev; /* Currently only used by mrst */
 	const struct psb_ops *ops;
 	const struct psb_offset *regmap;
-	
+
 	struct child_device_config *child_dev;
 	int child_dev_num;
 
@@ -540,7 +542,7 @@ struct drm_psb_private {
 
 	/* Oaktrail HDMI state */
 	struct oaktrail_hdmi_dev *hdmi_priv;
-	
+
 	/* Register state */
 	struct psb_save_area regs;
 
@@ -572,7 +574,7 @@ struct drm_psb_private {
 	uint32_t blc_adj1;
 	uint32_t blc_adj2;
 
-	void *fbdev;
+	struct drm_fb_helper *fb_helper;
 
 	/* 2D acceleration */
 	spinlock_t lock_2d;
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c
index 4256410535f0..fed3b563e62e 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.c
+++ b/drivers/gpu/drm/gma500/psb_intel_display.c
@@ -432,6 +432,7 @@ const struct drm_crtc_funcs psb_intel_crtc_funcs = {
 	.gamma_set = gma_crtc_gamma_set,
 	.set_config = gma_crtc_set_config,
 	.destroy = gma_crtc_destroy,
+	.page_flip = gma_crtc_page_flip,
 };
 
 const struct gma_clock_funcs psb_clock_funcs = {
diff --git a/drivers/gpu/drm/gma500/psb_intel_drv.h b/drivers/gpu/drm/gma500/psb_intel_drv.h
index cdf10333d1c2..16c6136f778b 100644
--- a/drivers/gpu/drm/gma500/psb_intel_drv.h
+++ b/drivers/gpu/drm/gma500/psb_intel_drv.h
@@ -12,6 +12,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_probe_helper.h>
+#include <drm/drm_vblank.h>
 #include <linux/gpio.h>
 #include "gma_display.h"
 
@@ -182,6 +183,8 @@ struct gma_crtc {
 	struct psb_intel_crtc_state *crtc_state;
 
 	const struct gma_clock_funcs *clock_funcs;
+
+	struct drm_pending_vblank_event *page_flip_event;
 };
 
 #define to_gma_crtc(x)	\
diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c
index e6265fb85626..91f90016dba9 100644
--- a/drivers/gpu/drm/gma500/psb_irq.c
+++ b/drivers/gpu/drm/gma500/psb_irq.c
@@ -165,11 +165,23 @@ static void mid_pipe_event_handler(struct drm_device *dev, int pipe)
 		"%s, can't clear status bits for pipe %d, its value = 0x%x.\n",
 		__func__, pipe, PSB_RVDC32(pipe_stat_reg));
 
-	if (pipe_stat_val & PIPE_VBLANK_STATUS)
-		drm_handle_vblank(dev, pipe);
+	if (pipe_stat_val & PIPE_VBLANK_STATUS ||
+	    (IS_MFLD(dev) && pipe_stat_val & PIPE_TE_STATUS)) {
+		struct drm_crtc *crtc = drm_crtc_from_index(dev, pipe);
+		struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
+		unsigned long flags;
 
-	if (pipe_stat_val & PIPE_TE_STATUS)
 		drm_handle_vblank(dev, pipe);
+
+		spin_lock_irqsave(&dev->event_lock, flags);
+		if (gma_crtc->page_flip_event) {
+			drm_crtc_send_vblank_event(crtc,
+						   gma_crtc->page_flip_event);
+			gma_crtc->page_flip_event = NULL;
+			drm_crtc_vblank_put(crtc);
+		}
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
 }
 
 /*
@@ -194,7 +206,6 @@ static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	u32 val, addr;
-	int error = false;
 
 	if (stat_1 & _PSB_CE_TWOD_COMPLETE)
 		val = PSB_RSGX32(PSB_CR_2D_BLIT_STATUS);
@@ -229,7 +240,6 @@ static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2)
 
 			DRM_ERROR("\tMMU failing address is 0x%08x.\n",
 				  (unsigned int)addr);
-			error = true;
 		}
 	}
 
@@ -460,12 +470,11 @@ void psb_irq_turn_off_dpst(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv =
 	    (struct drm_psb_private *) dev->dev_private;
-	u32 hist_reg;
 	u32 pwm_reg;
 
 	if (gma_power_begin(dev, false)) {
 		PSB_WVDC32(0x00000000, HISTOGRAM_INT_CONTROL);
-		hist_reg = PSB_RVDC32(HISTOGRAM_INT_CONTROL);
+		PSB_RVDC32(HISTOGRAM_INT_CONTROL);
 
 		psb_disable_pipestat(dev_priv, 0, PIPE_DPST_EVENT_ENABLE);
 
diff --git a/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c b/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c
index 7de3ce637c7f..9e8224456ea2 100644
--- a/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c
+++ b/drivers/gpu/drm/gma500/tc35876x-dsi-lvds.c
@@ -25,7 +25,7 @@
 #include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/platform_data/tc35876x.h>
+#include <linux/gpio/consumer.h>
 
 #include <asm/intel_scu_ipc.h>
 
@@ -36,6 +36,11 @@
 
 static struct i2c_client *tc35876x_client;
 static struct i2c_client *cmi_lcd_i2c_client;
+/* Panel GPIOs */
+static struct gpio_desc *bridge_reset;
+static struct gpio_desc *bridge_bl_enable;
+static struct gpio_desc *backlight_voltage;
+
 
 #define FLD_MASK(start, end)	(((1 << ((start) - (end) + 1)) - 1) << (end))
 #define FLD_VAL(val, start, end) (((val) << (end)) & FLD_MASK(start, end))
@@ -316,27 +321,23 @@ static int tc35876x_regr(struct i2c_client *client, u16 reg, u32 *value)
 
 void tc35876x_set_bridge_reset_state(struct drm_device *dev, int state)
 {
-	struct tc35876x_platform_data *pdata;
-
 	if (WARN(!tc35876x_client, "%s called before probe", __func__))
 		return;
 
 	dev_dbg(&tc35876x_client->dev, "%s: state %d\n", __func__, state);
 
-	pdata = dev_get_platdata(&tc35876x_client->dev);
-
-	if (pdata->gpio_bridge_reset == -1)
+	if (!bridge_reset)
 		return;
 
 	if (state) {
-		gpio_set_value_cansleep(pdata->gpio_bridge_reset, 0);
+		gpiod_set_value_cansleep(bridge_reset, 0);
 		mdelay(10);
 	} else {
 		/* Pull MIPI Bridge reset pin to Low */
-		gpio_set_value_cansleep(pdata->gpio_bridge_reset, 0);
+		gpiod_set_value_cansleep(bridge_reset, 0);
 		mdelay(20);
 		/* Pull MIPI Bridge reset pin to High */
-		gpio_set_value_cansleep(pdata->gpio_bridge_reset, 1);
+		gpiod_set_value_cansleep(bridge_reset, 1);
 		mdelay(40);
 	}
 }
@@ -510,25 +511,20 @@ void tc35876x_brightness_control(struct drm_device *dev, int level)
 
 void tc35876x_toshiba_bridge_panel_off(struct drm_device *dev)
 {
-	struct tc35876x_platform_data *pdata;
-
 	if (WARN(!tc35876x_client, "%s called before probe", __func__))
 		return;
 
 	dev_dbg(&tc35876x_client->dev, "%s\n", __func__);
 
-	pdata = dev_get_platdata(&tc35876x_client->dev);
-
-	if (pdata->gpio_panel_bl_en != -1)
-		gpio_set_value_cansleep(pdata->gpio_panel_bl_en, 0);
+	if (bridge_bl_enable)
+		gpiod_set_value_cansleep(bridge_bl_enable, 0);
 
-	if (pdata->gpio_panel_vadd != -1)
-		gpio_set_value_cansleep(pdata->gpio_panel_vadd, 0);
+	if (backlight_voltage)
+		gpiod_set_value_cansleep(backlight_voltage, 0);
 }
 
 void tc35876x_toshiba_bridge_panel_on(struct drm_device *dev)
 {
-	struct tc35876x_platform_data *pdata;
 	struct drm_psb_private *dev_priv = dev->dev_private;
 
 	if (WARN(!tc35876x_client, "%s called before probe", __func__))
@@ -536,10 +532,8 @@ void tc35876x_toshiba_bridge_panel_on(struct drm_device *dev)
 
 	dev_dbg(&tc35876x_client->dev, "%s\n", __func__);
 
-	pdata = dev_get_platdata(&tc35876x_client->dev);
-
-	if (pdata->gpio_panel_vadd != -1) {
-		gpio_set_value_cansleep(pdata->gpio_panel_vadd, 1);
+	if (backlight_voltage) {
+		gpiod_set_value_cansleep(backlight_voltage, 1);
 		msleep(260);
 	}
 
@@ -571,8 +565,8 @@ void tc35876x_toshiba_bridge_panel_on(struct drm_device *dev)
 				"i2c write failed (%d)\n", ret);
 	}
 
-	if (pdata->gpio_panel_bl_en != -1)
-		gpio_set_value_cansleep(pdata->gpio_panel_bl_en, 1);
+	if (bridge_bl_enable)
+		gpiod_set_value_cansleep(bridge_bl_enable, 1);
 
 	tc35876x_brightness_control(dev, dev_priv->brightness_adjusted);
 }
@@ -635,8 +629,6 @@ static int tc35876x_get_panel_info(struct drm_device *dev, int pipe,
 static int tc35876x_bridge_probe(struct i2c_client *client,
 				const struct i2c_device_id *id)
 {
-	struct tc35876x_platform_data *pdata;
-
 	dev_info(&client->dev, "%s\n", __func__);
 
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
@@ -645,26 +637,23 @@ static int tc35876x_bridge_probe(struct i2c_client *client,
 		return -ENODEV;
 	}
 
-	pdata = dev_get_platdata(&client->dev);
-	if (!pdata) {
-		dev_err(&client->dev, "%s: no platform data\n", __func__);
-		return -ENODEV;
-	}
+	bridge_reset = devm_gpiod_get_optional(&client->dev, "bridge-reset", GPIOD_OUT_LOW);
+	if (IS_ERR(bridge_reset))
+		return PTR_ERR(bridge_reset);
+	if (bridge_reset)
+		gpiod_set_consumer_name(bridge_reset, "tc35876x bridge reset");
 
-	if (pdata->gpio_bridge_reset != -1) {
-		gpio_request(pdata->gpio_bridge_reset, "tc35876x bridge reset");
-		gpio_direction_output(pdata->gpio_bridge_reset, 0);
-	}
-
-	if (pdata->gpio_panel_bl_en != -1) {
-		gpio_request(pdata->gpio_panel_bl_en, "tc35876x panel bl en");
-		gpio_direction_output(pdata->gpio_panel_bl_en, 0);
-	}
+	bridge_bl_enable = devm_gpiod_get_optional(&client->dev, "bl-en", GPIOD_OUT_LOW);
+	if (IS_ERR(bridge_bl_enable))
+		return PTR_ERR(bridge_bl_enable);
+	if (bridge_bl_enable)
+		gpiod_set_consumer_name(bridge_bl_enable, "tc35876x panel bl en");
 
-	if (pdata->gpio_panel_vadd != -1) {
-		gpio_request(pdata->gpio_panel_vadd, "tc35876x panel vadd");
-		gpio_direction_output(pdata->gpio_panel_vadd, 0);
-	}
+	backlight_voltage = devm_gpiod_get_optional(&client->dev, "vadd", GPIOD_OUT_LOW);
+	if (IS_ERR(backlight_voltage))
+		return PTR_ERR(backlight_voltage);
+	if (backlight_voltage)
+		gpiod_set_consumer_name(backlight_voltage, "tc35876x panel vadd");
 
 	tc35876x_client = client;
 
@@ -673,19 +662,8 @@ static int tc35876x_bridge_probe(struct i2c_client *client,
 
 static int tc35876x_bridge_remove(struct i2c_client *client)
 {
-	struct tc35876x_platform_data *pdata = dev_get_platdata(&client->dev);
-
 	dev_dbg(&client->dev, "%s\n", __func__);
 
-	if (pdata->gpio_bridge_reset != -1)
-		gpio_free(pdata->gpio_bridge_reset);
-
-	if (pdata->gpio_panel_bl_en != -1)
-		gpio_free(pdata->gpio_panel_bl_en);
-
-	if (pdata->gpio_panel_vadd != -1)
-		gpio_free(pdata->gpio_panel_vadd);
-
 	tc35876x_client = NULL;
 
 	return 0;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/Makefile b/drivers/gpu/drm/hisilicon/hibmc/Makefile
index 0c2d4296bccd..f99132715597 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/Makefile
+++ b/drivers/gpu/drm/hisilicon/hibmc/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_drm_fbdev.o hibmc_ttm.o
+hibmc-drm-y := hibmc_drm_drv.o hibmc_drm_de.o hibmc_drm_vdac.o hibmc_ttm.o
 
 obj-$(CONFIG_DRM_HISI_HIBMC) += hibmc-drm.o
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index 6527a97f68a3..7fa7d4933f60 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -99,14 +99,12 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
 	s64 gpu_addr = 0;
 	unsigned int line_l;
 	struct hibmc_drm_private *priv = plane->dev->dev_private;
-	struct hibmc_framebuffer *hibmc_fb;
 	struct drm_gem_vram_object *gbo;
 
 	if (!state->fb)
 		return;
 
-	hibmc_fb = to_hibmc_framebuffer(state->fb);
-	gbo = drm_gem_vram_of_gem(hibmc_fb->obj);
+	gbo = drm_gem_vram_of_gem(state->fb->obj[0]);
 
 	gpu_addr = drm_gem_vram_offset(gbo);
 	if (WARN_ON_ONCE(gpu_addr < 0))
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index 8dd5a43e5486..4a8a4cfb4b75 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -17,6 +17,7 @@
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_vram_helper.h>
 #include <drm/drm_irq.h>
 #include <drm/drm_print.h>
@@ -54,6 +55,7 @@ static struct drm_driver hibmc_driver = {
 	.desc			= "hibmc drm driver",
 	.major			= 1,
 	.minor			= 0,
+	.debugfs_init		= drm_vram_mm_debugfs_init,
 	.dumb_create            = hibmc_dumb_create,
 	.dumb_map_offset        = drm_gem_vram_driver_dumb_mmap_offset,
 	.gem_prime_mmap		= drm_gem_prime_mmap,
@@ -247,8 +249,6 @@ static int hibmc_unload(struct drm_device *dev)
 {
 	struct hibmc_drm_private *priv = dev->dev_private;
 
-	hibmc_fbdev_fini(priv);
-
 	drm_atomic_helper_shutdown(dev);
 
 	if (dev->irq_enabled)
@@ -307,7 +307,7 @@ static int hibmc_load(struct drm_device *dev)
 	/* reset all the states of crtc/plane/encoder/connector */
 	drm_mode_config_reset(dev);
 
-	ret = hibmc_fbdev_init(priv);
+	ret = drm_fbdev_generic_setup(dev, 16);
 	if (ret) {
 		DRM_ERROR("failed to initialize fbdev: %d\n", ret);
 		goto err;
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
index e58ecd7edcf8..50a0c1f9d211 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h
@@ -18,18 +18,6 @@
 #include <drm/drm_framebuffer.h>
 
 struct drm_device;
-struct drm_gem_object;
-
-struct hibmc_framebuffer {
-	struct drm_framebuffer fb;
-	struct drm_gem_object *obj;
-};
-
-struct hibmc_fbdev {
-	struct drm_fb_helper helper; /* must be first */
-	struct hibmc_framebuffer *fb;
-	int size;
-};
 
 struct hibmc_drm_private {
 	/* hw */
@@ -42,13 +30,8 @@ struct hibmc_drm_private {
 	/* drm */
 	struct drm_device  *dev;
 	bool mode_config_initialized;
-
-	/* fbdev */
-	struct hibmc_fbdev *fbdev;
 };
 
-#define to_hibmc_framebuffer(x) container_of(x, struct hibmc_framebuffer, fb)
-
 void hibmc_set_power_mode(struct hibmc_drm_private *priv,
 			  unsigned int power_mode);
 void hibmc_set_current_gate(struct hibmc_drm_private *priv,
@@ -56,15 +39,6 @@ void hibmc_set_current_gate(struct hibmc_drm_private *priv,
 
 int hibmc_de_init(struct hibmc_drm_private *priv);
 int hibmc_vdac_init(struct hibmc_drm_private *priv);
-int hibmc_fbdev_init(struct hibmc_drm_private *priv);
-void hibmc_fbdev_fini(struct hibmc_drm_private *priv);
-
-int hibmc_gem_create(struct drm_device *dev, u32 size, bool iskernel,
-		     struct drm_gem_object **obj);
-struct hibmc_framebuffer *
-hibmc_framebuffer_init(struct drm_device *dev,
-		       const struct drm_mode_fb_cmd2 *mode_cmd,
-		       struct drm_gem_object *obj);
 
 int hibmc_mm_init(struct hibmc_drm_private *hibmc);
 void hibmc_mm_fini(struct hibmc_drm_private *hibmc);
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c
deleted file mode 100644
index b4c1cea051e8..000000000000
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_fbdev.c
+++ /dev/null
@@ -1,240 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* Hisilicon Hibmc SoC drm driver
- *
- * Based on the bochs drm driver.
- *
- * Copyright (c) 2016 Huawei Limited.
- *
- * Author:
- *	Rongrong Zou <zourongrong@huawei.com>
- *	Rongrong Zou <zourongrong@gmail.com>
- *	Jianhua Li <lijianhua@huawei.com>
- */
-
-#include <drm/drm_crtc.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_gem_vram_helper.h>
-#include <drm/drm_probe_helper.h>
-
-#include "hibmc_drm_drv.h"
-
-static int hibmcfb_create_object(
-				struct hibmc_drm_private *priv,
-				const struct drm_mode_fb_cmd2 *mode_cmd,
-				struct drm_gem_object **gobj_p)
-{
-	struct drm_gem_object *gobj;
-	struct drm_device *dev = priv->dev;
-	u32 size;
-	int ret = 0;
-
-	size = mode_cmd->pitches[0] * mode_cmd->height;
-	ret = hibmc_gem_create(dev, size, true, &gobj);
-	if (ret)
-		return ret;
-
-	*gobj_p = gobj;
-	return ret;
-}
-
-static struct fb_ops hibmc_drm_fb_ops = {
-	.owner = THIS_MODULE,
-	.fb_check_var = drm_fb_helper_check_var,
-	.fb_set_par = drm_fb_helper_set_par,
-	.fb_fillrect = drm_fb_helper_sys_fillrect,
-	.fb_copyarea = drm_fb_helper_sys_copyarea,
-	.fb_imageblit = drm_fb_helper_sys_imageblit,
-	.fb_pan_display = drm_fb_helper_pan_display,
-	.fb_blank = drm_fb_helper_blank,
-	.fb_setcmap = drm_fb_helper_setcmap,
-};
-
-static int hibmc_drm_fb_create(struct drm_fb_helper *helper,
-			       struct drm_fb_helper_surface_size *sizes)
-{
-	struct hibmc_fbdev *hi_fbdev =
-		container_of(helper, struct hibmc_fbdev, helper);
-	struct hibmc_drm_private *priv = helper->dev->dev_private;
-	struct fb_info *info;
-	struct drm_mode_fb_cmd2 mode_cmd;
-	struct drm_gem_object *gobj = NULL;
-	int ret = 0;
-	size_t size;
-	unsigned int bytes_per_pixel;
-	struct drm_gem_vram_object *gbo = NULL;
-	void *base;
-
-	DRM_DEBUG_DRIVER("surface width(%d), height(%d) and bpp(%d)\n",
-			 sizes->surface_width, sizes->surface_height,
-			 sizes->surface_bpp);
-
-	bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8);
-
-	mode_cmd.width = sizes->surface_width;
-	mode_cmd.height = sizes->surface_height;
-	mode_cmd.pitches[0] = mode_cmd.width * bytes_per_pixel;
-	mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
-							  sizes->surface_depth);
-
-	size = PAGE_ALIGN(mode_cmd.pitches[0] * mode_cmd.height);
-
-	ret = hibmcfb_create_object(priv, &mode_cmd, &gobj);
-	if (ret) {
-		DRM_ERROR("failed to create fbcon backing object: %d\n", ret);
-		return -ENOMEM;
-	}
-
-	gbo = drm_gem_vram_of_gem(gobj);
-
-	ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-	if (ret) {
-		DRM_ERROR("failed to pin fbcon: %d\n", ret);
-		goto out_unref_gem;
-	}
-
-	base = drm_gem_vram_kmap(gbo, true, NULL);
-	if (IS_ERR(base)) {
-		ret = PTR_ERR(base);
-		DRM_ERROR("failed to kmap fbcon: %d\n", ret);
-		goto out_unpin_bo;
-	}
-
-	info = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		DRM_ERROR("failed to allocate fbi: %d\n", ret);
-		goto out_release_fbi;
-	}
-
-	hi_fbdev->fb = hibmc_framebuffer_init(priv->dev, &mode_cmd, gobj);
-	if (IS_ERR(hi_fbdev->fb)) {
-		ret = PTR_ERR(hi_fbdev->fb);
-		hi_fbdev->fb = NULL;
-		DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
-		goto out_release_fbi;
-	}
-
-	priv->fbdev->size = size;
-	hi_fbdev->helper.fb = &hi_fbdev->fb->fb;
-
-	info->fbops = &hibmc_drm_fb_ops;
-
-	drm_fb_helper_fill_info(info, &priv->fbdev->helper, sizes);
-
-	info->screen_base = base;
-	info->screen_size = size;
-
-	info->fix.smem_start = gbo->bo.mem.bus.offset + gbo->bo.mem.bus.base;
-	info->fix.smem_len = size;
-	return 0;
-
-out_release_fbi:
-	drm_gem_vram_kunmap(gbo);
-out_unpin_bo:
-	drm_gem_vram_unpin(gbo);
-out_unref_gem:
-	drm_gem_object_put_unlocked(gobj);
-
-	return ret;
-}
-
-static void hibmc_fbdev_destroy(struct hibmc_fbdev *fbdev)
-{
-	struct hibmc_framebuffer *gfb = fbdev->fb;
-	struct drm_fb_helper *fbh = &fbdev->helper;
-
-	drm_fb_helper_unregister_fbi(fbh);
-
-	drm_fb_helper_fini(fbh);
-
-	if (gfb)
-		drm_framebuffer_put(&gfb->fb);
-}
-
-static const struct drm_fb_helper_funcs hibmc_fbdev_helper_funcs = {
-	.fb_probe = hibmc_drm_fb_create,
-};
-
-int hibmc_fbdev_init(struct hibmc_drm_private *priv)
-{
-	int ret;
-	struct fb_var_screeninfo *var;
-	struct fb_fix_screeninfo *fix;
-	struct hibmc_fbdev *hifbdev;
-
-	hifbdev = devm_kzalloc(priv->dev->dev, sizeof(*hifbdev), GFP_KERNEL);
-	if (!hifbdev) {
-		DRM_ERROR("failed to allocate hibmc_fbdev\n");
-		return -ENOMEM;
-	}
-
-	priv->fbdev = hifbdev;
-	drm_fb_helper_prepare(priv->dev, &hifbdev->helper,
-			      &hibmc_fbdev_helper_funcs);
-
-	/* Now just one crtc and one channel */
-	ret = drm_fb_helper_init(priv->dev, &hifbdev->helper, 1);
-	if (ret) {
-		DRM_ERROR("failed to initialize fb helper: %d\n", ret);
-		return ret;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(&hifbdev->helper);
-	if (ret) {
-		DRM_ERROR("failed to add all connectors: %d\n", ret);
-		goto fini;
-	}
-
-	ret = drm_fb_helper_initial_config(&hifbdev->helper, 16);
-	if (ret) {
-		DRM_ERROR("failed to setup initial conn config: %d\n", ret);
-		goto fini;
-	}
-
-	var = &hifbdev->helper.fbdev->var;
-	fix = &hifbdev->helper.fbdev->fix;
-
-	DRM_DEBUG_DRIVER("Member of info->var is :\n"
-			 "xres=%d\n"
-			 "yres=%d\n"
-			 "xres_virtual=%d\n"
-			 "yres_virtual=%d\n"
-			 "xoffset=%d\n"
-			 "yoffset=%d\n"
-			 "bits_per_pixel=%d\n"
-			 "...\n", var->xres, var->yres, var->xres_virtual,
-			 var->yres_virtual, var->xoffset, var->yoffset,
-			 var->bits_per_pixel);
-	DRM_DEBUG_DRIVER("Member of info->fix is :\n"
-			 "smem_start=%lx\n"
-			 "smem_len=%d\n"
-			 "type=%d\n"
-			 "type_aux=%d\n"
-			 "visual=%d\n"
-			 "xpanstep=%d\n"
-			 "ypanstep=%d\n"
-			 "ywrapstep=%d\n"
-			 "line_length=%d\n"
-			 "accel=%d\n"
-			 "capabilities=%d\n"
-			 "...\n", fix->smem_start, fix->smem_len, fix->type,
-			 fix->type_aux, fix->visual, fix->xpanstep,
-			 fix->ypanstep, fix->ywrapstep, fix->line_length,
-			 fix->accel, fix->capabilities);
-
-	return 0;
-
-fini:
-	drm_fb_helper_fini(&hifbdev->helper);
-	return ret;
-}
-
-void hibmc_fbdev_fini(struct hibmc_drm_private *priv)
-{
-	if (!priv->fbdev)
-		return;
-
-	hibmc_fbdev_destroy(priv->fbdev);
-	priv->fbdev = NULL;
-}
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
index 21b684eab5c9..50b988fdd5cc 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_ttm.c
@@ -15,6 +15,7 @@
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_gem_vram_helper.h>
 #include <drm/drm_print.h>
 
@@ -46,125 +47,14 @@ void hibmc_mm_fini(struct hibmc_drm_private *hibmc)
 	drm_vram_helper_release_mm(hibmc->dev);
 }
 
-int hibmc_gem_create(struct drm_device *dev, u32 size, bool iskernel,
-		     struct drm_gem_object **obj)
-{
-	struct drm_gem_vram_object *gbo;
-	int ret;
-
-	*obj = NULL;
-
-	size = roundup(size, PAGE_SIZE);
-	if (size == 0)
-		return -EINVAL;
-
-	gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev, size, 0, false);
-	if (IS_ERR(gbo)) {
-		ret = PTR_ERR(gbo);
-		if (ret != -ERESTARTSYS)
-			DRM_ERROR("failed to allocate GEM object: %d\n", ret);
-		return ret;
-	}
-	*obj = &gbo->bo.base;
-	return 0;
-}
-
 int hibmc_dumb_create(struct drm_file *file, struct drm_device *dev,
 		      struct drm_mode_create_dumb *args)
 {
-	struct drm_gem_object *gobj;
-	u32 handle;
-	int ret;
-
-	args->pitch = ALIGN(args->width * DIV_ROUND_UP(args->bpp, 8), 16);
-	args->size = args->pitch * args->height;
-
-	ret = hibmc_gem_create(dev, args->size, false,
-			       &gobj);
-	if (ret) {
-		DRM_ERROR("failed to create GEM object: %d\n", ret);
-		return ret;
-	}
-
-	ret = drm_gem_handle_create(file, gobj, &handle);
-	drm_gem_object_put_unlocked(gobj);
-	if (ret) {
-		DRM_ERROR("failed to unreference GEM object: %d\n", ret);
-		return ret;
-	}
-
-	args->handle = handle;
-	return 0;
-}
-
-static void hibmc_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct hibmc_framebuffer *hibmc_fb = to_hibmc_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(hibmc_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(hibmc_fb);
-}
-
-static const struct drm_framebuffer_funcs hibmc_fb_funcs = {
-	.destroy = hibmc_user_framebuffer_destroy,
-};
-
-struct hibmc_framebuffer *
-hibmc_framebuffer_init(struct drm_device *dev,
-		       const struct drm_mode_fb_cmd2 *mode_cmd,
-		       struct drm_gem_object *obj)
-{
-	struct hibmc_framebuffer *hibmc_fb;
-	int ret;
-
-	hibmc_fb = kzalloc(sizeof(*hibmc_fb), GFP_KERNEL);
-	if (!hibmc_fb) {
-		DRM_ERROR("failed to allocate hibmc_fb\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	drm_helper_mode_fill_fb_struct(dev, &hibmc_fb->fb, mode_cmd);
-	hibmc_fb->obj = obj;
-	ret = drm_framebuffer_init(dev, &hibmc_fb->fb, &hibmc_fb_funcs);
-	if (ret) {
-		DRM_ERROR("drm_framebuffer_init failed: %d\n", ret);
-		kfree(hibmc_fb);
-		return ERR_PTR(ret);
-	}
-
-	return hibmc_fb;
-}
-
-static struct drm_framebuffer *
-hibmc_user_framebuffer_create(struct drm_device *dev,
-			      struct drm_file *filp,
-			      const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	struct drm_gem_object *obj;
-	struct hibmc_framebuffer *hibmc_fb;
-
-	DRM_DEBUG_DRIVER("%dx%d, format %c%c%c%c\n",
-			 mode_cmd->width, mode_cmd->height,
-			 (mode_cmd->pixel_format) & 0xff,
-			 (mode_cmd->pixel_format >> 8)  & 0xff,
-			 (mode_cmd->pixel_format >> 16) & 0xff,
-			 (mode_cmd->pixel_format >> 24) & 0xff);
-
-	obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]);
-	if (!obj)
-		return ERR_PTR(-ENOENT);
-
-	hibmc_fb = hibmc_framebuffer_init(dev, mode_cmd, obj);
-	if (IS_ERR(hibmc_fb)) {
-		drm_gem_object_put_unlocked(obj);
-		return ERR_PTR((long)hibmc_fb);
-	}
-	return &hibmc_fb->fb;
+	return drm_gem_vram_fill_create_dumb(file, dev, 0, 16, args);
 }
 
 const struct drm_mode_config_funcs hibmc_mode_funcs = {
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
-	.fb_create = hibmc_user_framebuffer_create,
+	.fb_create = drm_gem_fb_create,
 };
diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index e66c38332df4..b88c3d5f92b4 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -32,6 +32,7 @@
 
 #include <linux/delay.h>
 #include <linux/mman.h>
+#include <linux/pci.h>
 
 #include <drm/drm_agpsupport.h>
 #include <drm/drm_device.h>
@@ -39,7 +40,6 @@
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_print.h>
 #include <drm/i810_drm.h>
 
diff --git a/drivers/gpu/drm/i810/i810_drv.c b/drivers/gpu/drm/i810/i810_drv.c
index 5dd26a06ee0e..0e53a066d4db 100644
--- a/drivers/gpu/drm/i810/i810_drv.c
+++ b/drivers/gpu/drm/i810/i810_drv.c
@@ -31,11 +31,12 @@
  */
 
 #include "i810_drv.h"
+
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/i810_drm.h>
 
diff --git a/drivers/gpu/drm/i915/.gitignore b/drivers/gpu/drm/i915/.gitignore
new file mode 100644
index 000000000000..d9a77f3b59b2
--- /dev/null
+++ b/drivers/gpu/drm/i915/.gitignore
@@ -0,0 +1 @@
+*.hdrtest
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 438040ff0179..1cb28c20807c 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -27,6 +27,7 @@ config DRM_I915_DEBUG
 	select X86_MSR # used by igt/pm_rpm
 	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
 	select DRM_DEBUG_MM if DRM=y
+	select DRM_EXPORT_FOR_TESTS if m
 	select DRM_DEBUG_SELFTEST
 	select DMABUF_SELFTESTS
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
@@ -149,6 +150,7 @@ config DRM_I915_SELFTEST
 	bool "Enable selftests upon driver load"
 	depends on DRM_I915
 	default n
+	select DRM_EXPORT_FOR_TESTS if m
 	select FAULT_INJECTION
 	select PRIME_NUMBERS
 	help
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 90dcf09f52cc..b8c5f8934dbd 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -31,9 +31,6 @@ CFLAGS_display/intel_fbdev.o = $(call cc-disable-warning, override-init)
 subdir-ccflags-y += \
 	$(call as-instr,movntdqa (%eax)$(comma)%xmm0,-DCONFIG_AS_MOVNTDQA)
 
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
-
 subdir-ccflags-y += -I$(srctree)/$(src)
 
 # Please keep these build lists sorted!
@@ -73,8 +70,12 @@ i915-$(CONFIG_DEBUG_FS) += i915_debugfs.o display/intel_pipe_crc.o
 i915-$(CONFIG_PERF_EVENTS) += i915_pmu.o
 
 # "Graphics Technology" (aka we talk to the gpu)
-obj-y += gt/
 gt-y += \
+	gt/debugfs_engines.o \
+	gt/debugfs_gt.o \
+	gt/debugfs_gt_pm.o \
+	gt/gen6_ppgtt.o \
+	gt/gen8_ppgtt.o \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
 	gt/intel_engine_cs.o \
@@ -82,14 +83,17 @@ gt-y += \
 	gt/intel_engine_pm.o \
 	gt/intel_engine_pool.o \
 	gt/intel_engine_user.o \
+	gt/intel_ggtt.o \
 	gt/intel_gt.o \
 	gt/intel_gt_irq.o \
 	gt/intel_gt_pm.o \
 	gt/intel_gt_pm_irq.o \
 	gt/intel_gt_requests.o \
+	gt/intel_gtt.o \
 	gt/intel_llc.o \
 	gt/intel_lrc.o \
 	gt/intel_mocs.o \
+	gt/intel_ppgtt.o \
 	gt/intel_rc6.o \
 	gt/intel_renderstate.o \
 	gt/intel_reset.o \
@@ -108,7 +112,6 @@ gt-y += \
 i915-y += $(gt-y)
 
 # GEM (Graphics Execution Management) code
-obj-y += gem/
 gem-y += \
 	gem/i915_gem_busy.o \
 	gem/i915_gem_clflush.o \
@@ -154,7 +157,6 @@ i915-y += \
 	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support
-obj-y += gt/uc/
 i915-y += gt/uc/intel_uc.o \
 	  gt/uc/intel_uc_fw.o \
 	  gt/uc/intel_guc.o \
@@ -167,7 +169,6 @@ i915-y += gt/uc/intel_uc.o \
 	  gt/uc/intel_huc_fw.o
 
 # modesetting core code
-obj-y += display/
 i915-y += \
 	display/intel_atomic.o \
 	display/intel_atomic_plane.o \
@@ -232,7 +233,6 @@ i915-y += \
 	display/vlv_dsi_pll.o
 
 # perf code
-obj-y += oa/
 i915-y += \
 	oa/i915_oa_hsw.o \
 	oa/i915_oa_bdw.o \
@@ -257,8 +257,10 @@ i915-$(CONFIG_DRM_I915_SELFTEST) += \
 	gem/selftests/igt_gem_utils.o \
 	selftests/i915_random.o \
 	selftests/i915_selftest.o \
+	selftests/igt_atomic.o \
 	selftests/igt_flush_test.o \
 	selftests/igt_live_test.o \
+	selftests/igt_mmap.o \
 	selftests/igt_reset.o \
 	selftests/igt_spinner.o
 
@@ -272,3 +274,27 @@ endif
 
 obj-$(CONFIG_DRM_I915) += i915.o
 obj-$(CONFIG_DRM_I915_GVT_KVMGT) += gvt/kvmgt.o
+
+# header test
+
+# exclude some broken headers from the test coverage
+no-header-test := \
+	display/intel_vbt_defs.h \
+	gvt/execlist.h \
+	gvt/fb_decoder.h \
+	gvt/gtt.h \
+	gvt/gvt.h \
+	gvt/interrupt.h \
+	gvt/mmio_context.h \
+	gvt/mpt.h \
+	gvt/scheduler.h
+
+extra-$(CONFIG_DRM_I915_WERROR) += \
+	$(patsubst %.h,%.hdrtest, $(filter-out $(no-header-test), \
+		$(shell cd $(srctree)/$(src) && find * -name '*.h')))
+
+quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
+      cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@
+
+$(obj)/%.hdrtest: $(src)/%.h FORCE
+	$(call if_changed_dep,hdrtest)
diff --git a/drivers/gpu/drm/i915/display/Makefile b/drivers/gpu/drm/i915/display/Makefile
deleted file mode 100644
index 173c305d7866..000000000000
--- a/drivers/gpu/drm/i915/display/Makefile
+++ /dev/null
@@ -1,6 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
-header-test- := intel_vbt_defs.h
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 325df29b0447..f8e882101396 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -34,6 +34,7 @@
 #include "intel_ddi.h"
 #include "intel_dsi.h"
 #include "intel_panel.h"
+#include "intel_vdsc.h"
 
 static inline int header_credits_available(struct drm_i915_private *dev_priv,
 					   enum transcoder dsi_trans)
@@ -76,7 +77,7 @@ static enum transcoder dsi_port_to_transcoder(enum port port)
 static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi;
 	enum port port;
 	enum transcoder dsi_trans;
@@ -201,7 +202,7 @@ static int dsi_send_pkt_payld(struct intel_dsi_host *host,
 static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 	u32 tmp;
 	int lane;
@@ -266,7 +267,7 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 				     const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 dss_ctl1;
 
 	dss_ctl1 = I915_READ(DSS_CTL1);
@@ -276,7 +277,7 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 
 	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
 		const struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
 		u32 dss_ctl2;
 		u16 hactive = adjusted_mode->crtc_hdisplay;
 		u16 dl_buffer_depth;
@@ -301,18 +302,31 @@ static void configure_dual_link_mode(struct intel_encoder *encoder,
 	I915_WRITE(DSS_CTL1, dss_ctl1);
 }
 
-static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
+/* aka DSI 8X clock */
+static int afe_clk(struct intel_encoder *encoder,
+		   const struct intel_crtc_state *crtc_state)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	int bpp;
+
+	if (crtc_state->dsc.compression_enable)
+		bpp = crtc_state->dsc.compressed_bpp;
+	else
+		bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+
+	return DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp, intel_dsi->lane_count);
+}
+
+static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder,
+					  const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
-	u32 bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
-	u32 afe_clk_khz; /* 8X Clock */
+	int afe_clk_khz;
 	u32 esc_clk_div_m;
 
-	afe_clk_khz = DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp,
-					intel_dsi->lane_count);
-
+	afe_clk_khz = afe_clk(encoder, crtc_state);
 	esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK);
 
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -346,7 +360,7 @@ static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
 static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 
@@ -362,7 +376,7 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 
 	for_each_dsi_phy(phy, intel_dsi->phys)
@@ -373,7 +387,7 @@ static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
 static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum phy phy;
 	u32 tmp;
 	int lane;
@@ -422,7 +436,7 @@ static void gen11_dsi_config_phy_lanes_sequence(struct intel_encoder *encoder)
 static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
@@ -474,7 +488,7 @@ static void gen11_dsi_voltage_swing_program_seq(struct intel_encoder *encoder)
 static void gen11_dsi_enable_ddi_buffer(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum port port;
 
@@ -490,10 +504,12 @@ static void gen11_dsi_enable_ddi_buffer(struct intel_encoder *encoder)
 	}
 }
 
-static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder)
+static void
+gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder,
+			     const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum port port;
 	enum phy phy;
@@ -531,7 +547,7 @@ static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder)
 	 * leave all fields at HW default values.
 	 */
 	if (IS_GEN(dev_priv, 11)) {
-		if (intel_dsi_bitrate(intel_dsi) <= 800000) {
+		if (afe_clk(encoder, crtc_state) <= 800000) {
 			for_each_dsi_port(port, intel_dsi->ports) {
 				tmp = I915_READ(DPHY_TA_TIMING_PARAM(port));
 				tmp &= ~TA_SURE_MASK;
@@ -559,7 +575,7 @@ static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder)
 static void gen11_dsi_gate_clocks(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
@@ -575,7 +591,7 @@ static void gen11_dsi_gate_clocks(struct intel_encoder *encoder)
 static void gen11_dsi_ungate_clocks(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum phy phy;
 
@@ -592,7 +608,7 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	enum phy phy;
 	u32 val;
@@ -624,8 +640,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			       const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum pipe pipe = intel_crtc->pipe;
 	u32 tmp;
 	enum port port;
@@ -641,7 +657,7 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 			tmp |= EOTP_DISABLED;
 
 		/* enable link calibration if freq > 1.5Gbps */
-		if (intel_dsi_bitrate(intel_dsi) >= 1500 * 1000) {
+		if (afe_clk(encoder, pipe_config) >= 1500 * 1000) {
 			tmp &= ~LINK_CALIBRATION_MASK;
 			tmp |= CALIBRATION_ENABLED_INITIAL_ONLY;
 		}
@@ -667,22 +683,26 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 		/* select pixel format */
 		tmp &= ~PIX_FMT_MASK;
-		switch (intel_dsi->pixel_format) {
-		default:
-			MISSING_CASE(intel_dsi->pixel_format);
-			/* fallthrough */
-		case MIPI_DSI_FMT_RGB565:
-			tmp |= PIX_FMT_RGB565;
-			break;
-		case MIPI_DSI_FMT_RGB666_PACKED:
-			tmp |= PIX_FMT_RGB666_PACKED;
-			break;
-		case MIPI_DSI_FMT_RGB666:
-			tmp |= PIX_FMT_RGB666_LOOSE;
-			break;
-		case MIPI_DSI_FMT_RGB888:
-			tmp |= PIX_FMT_RGB888;
-			break;
+		if (pipe_config->dsc.compression_enable) {
+			tmp |= PIX_FMT_COMPRESSED;
+		} else {
+			switch (intel_dsi->pixel_format) {
+			default:
+				MISSING_CASE(intel_dsi->pixel_format);
+				/* fallthrough */
+			case MIPI_DSI_FMT_RGB565:
+				tmp |= PIX_FMT_RGB565;
+				break;
+			case MIPI_DSI_FMT_RGB666_PACKED:
+				tmp |= PIX_FMT_RGB666_PACKED;
+				break;
+			case MIPI_DSI_FMT_RGB666:
+				tmp |= PIX_FMT_RGB666_LOOSE;
+				break;
+			case MIPI_DSI_FMT_RGB888:
+				tmp |= PIX_FMT_RGB888;
+				break;
+			}
 		}
 
 		if (INTEL_GEN(dev_priv) >= 12) {
@@ -745,6 +765,9 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 		case PIPE_C:
 			tmp |= TRANS_DDI_EDP_INPUT_C_ONOFF;
 			break;
+		case PIPE_D:
+			tmp |= TRANS_DDI_EDP_INPUT_D_ONOFF;
+			break;
 		}
 
 		/* enable DDI buffer */
@@ -763,12 +786,12 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 
 static void
 gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
-				 const struct intel_crtc_state *pipe_config)
+				 const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	const struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	enum port port;
 	enum transcoder dsi_trans;
 	/* horizontal timings */
@@ -776,11 +799,25 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 	u16 hback_porch;
 	/* vertical timings */
 	u16 vtotal, vactive, vsync_start, vsync_end, vsync_shift;
+	int mul = 1, div = 1;
+
+	/*
+	 * Adjust horizontal timings (htotal, hsync_start, hsync_end) to account
+	 * for slower link speed if DSC is enabled.
+	 *
+	 * The compression frequency ratio is the ratio between compressed and
+	 * non-compressed link speeds, and simplifies down to the ratio between
+	 * compressed and non-compressed bpp.
+	 */
+	if (crtc_state->dsc.compression_enable) {
+		mul = crtc_state->dsc.compressed_bpp;
+		div = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	}
 
 	hactive = adjusted_mode->crtc_hdisplay;
-	htotal = adjusted_mode->crtc_htotal;
-	hsync_start = adjusted_mode->crtc_hsync_start;
-	hsync_end = adjusted_mode->crtc_hsync_end;
+	htotal = DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div);
+	hsync_start = DIV_ROUND_UP(adjusted_mode->crtc_hsync_start * mul, div);
+	hsync_end = DIV_ROUND_UP(adjusted_mode->crtc_hsync_end * mul, div);
 	hsync_size  = hsync_end - hsync_start;
 	hback_porch = (adjusted_mode->crtc_htotal -
 		       adjusted_mode->crtc_hsync_end);
@@ -886,7 +923,7 @@ gen11_dsi_set_transcoder_timings(struct intel_encoder *encoder,
 static void gen11_dsi_enable_transcoder(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
@@ -904,10 +941,11 @@ static void gen11_dsi_enable_transcoder(struct intel_encoder *encoder)
 	}
 }
 
-static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder)
+static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder,
+				     const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp, hs_tx_timeout, lp_rx_timeout, ta_timeout, divisor, mul;
@@ -919,7 +957,7 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder)
 	 * TIME_NS = (BYTE_CLK_COUNT * 8 * 10^6)/ Bitrate
 	 * ESCAPE_CLK_COUNT  = TIME_NS/ESC_CLK_NS
 	 */
-	divisor = intel_dsi_tlpx_ns(intel_dsi) * intel_dsi_bitrate(intel_dsi) * 1000;
+	divisor = intel_dsi_tlpx_ns(intel_dsi) * afe_clk(encoder, crtc_state) * 1000;
 	mul = 8 * 1000000;
 	hs_tx_timeout = DIV_ROUND_UP(intel_dsi->hs_tx_timeout * mul,
 				     divisor);
@@ -955,7 +993,7 @@ static void gen11_dsi_setup_timeouts(struct intel_encoder *encoder)
 
 static void
 gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
-			      const struct intel_crtc_state *pipe_config)
+			      const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
@@ -972,13 +1010,13 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 	gen11_dsi_enable_ddi_buffer(encoder);
 
 	/* setup D-PHY timings */
-	gen11_dsi_setup_dphy_timings(encoder);
+	gen11_dsi_setup_dphy_timings(encoder, crtc_state);
 
 	/* step 4h: setup DSI protocol timeouts */
-	gen11_dsi_setup_timeouts(encoder);
+	gen11_dsi_setup_timeouts(encoder, crtc_state);
 
 	/* Step (4h, 4i, 4j, 4k): Configure transcoder */
-	gen11_dsi_configure_transcoder(encoder, pipe_config);
+	gen11_dsi_configure_transcoder(encoder, crtc_state);
 
 	/* Step 4l: Gate DDI clocks */
 	if (IS_GEN(dev_priv, 11))
@@ -988,7 +1026,7 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder,
 static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi;
 	enum port port;
 	enum transcoder dsi_trans;
@@ -1025,21 +1063,21 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 }
 
 static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder,
-				     const struct intel_crtc_state *pipe_config,
+				     const struct intel_crtc_state *crtc_state,
 				     const struct drm_connector_state *conn_state)
 {
 	/* step2: enable IO power */
 	gen11_dsi_enable_io_power(encoder);
 
 	/* step3: enable DSI PLL */
-	gen11_dsi_program_esc_clk_div(encoder);
+	gen11_dsi_program_esc_clk_div(encoder, crtc_state);
 }
 
 static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	/* step3b */
 	gen11_dsi_map_pll(encoder, pipe_config);
@@ -1050,6 +1088,8 @@ static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 	/* step5: program and powerup panel */
 	gen11_dsi_powerup_panel(encoder);
 
+	intel_dsc_enable(encoder, pipe_config);
+
 	/* step6c: configure transcoder timings */
 	gen11_dsi_set_transcoder_timings(encoder, pipe_config);
 
@@ -1064,7 +1104,7 @@ static void gen11_dsi_pre_enable(struct intel_encoder *encoder,
 static void gen11_dsi_disable_transcoder(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
@@ -1086,7 +1126,7 @@ static void gen11_dsi_disable_transcoder(struct intel_encoder *encoder)
 
 static void gen11_dsi_powerdown_panel(struct intel_encoder *encoder)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_OFF);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
@@ -1099,7 +1139,7 @@ static void gen11_dsi_powerdown_panel(struct intel_encoder *encoder)
 static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	enum transcoder dsi_trans;
 	u32 tmp;
@@ -1140,7 +1180,7 @@ static void gen11_dsi_deconfigure_trancoder(struct intel_encoder *encoder)
 static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u32 tmp;
 	enum port port;
 
@@ -1162,7 +1202,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 
@@ -1189,7 +1229,7 @@ static void gen11_dsi_disable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	/* step1: turn off backlight */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
@@ -1211,12 +1251,42 @@ static void gen11_dsi_disable(struct intel_encoder *encoder,
 	gen11_dsi_disable_io_power(encoder);
 }
 
+static void gen11_dsi_post_disable(struct intel_encoder *encoder,
+				   const struct intel_crtc_state *old_crtc_state,
+				   const struct drm_connector_state *old_conn_state)
+{
+	intel_crtc_vblank_off(old_crtc_state);
+
+	intel_dsc_disable(old_crtc_state);
+
+	skl_scaler_disable(old_crtc_state);
+}
+
+static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector,
+						 struct drm_display_mode *mode)
+{
+	/* FIXME: DSC? */
+	return intel_dsi_mode_valid(connector, mode);
+}
+
 static void gen11_dsi_get_timings(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
+
+	if (pipe_config->dsc.compressed_bpp) {
+		int div = pipe_config->dsc.compressed_bpp;
+		int mul = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+
+		adjusted_mode->crtc_htotal =
+			DIV_ROUND_UP(adjusted_mode->crtc_htotal * mul, div);
+		adjusted_mode->crtc_hsync_start =
+			DIV_ROUND_UP(adjusted_mode->crtc_hsync_start * mul, div);
+		adjusted_mode->crtc_hsync_end =
+			DIV_ROUND_UP(adjusted_mode->crtc_hsync_end * mul, div);
+	}
 
 	if (intel_dsi->dual_link) {
 		adjusted_mode->crtc_hdisplay *= 2;
@@ -1242,22 +1312,66 @@ static void gen11_dsi_get_config(struct intel_encoder *encoder,
 				 struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+
+	intel_dsc_get_config(encoder, pipe_config);
 
 	/* FIXME: adapt icl_ddi_clock_get() for DSI and use that? */
 	pipe_config->port_clock =
 		cnl_calc_wrpll_link(dev_priv, &pipe_config->dpll_hw_state);
 
-	pipe_config->base.adjusted_mode.crtc_clock = intel_dsi->pclk;
+	pipe_config->hw.adjusted_mode.crtc_clock = intel_dsi->pclk;
 	if (intel_dsi->dual_link)
-		pipe_config->base.adjusted_mode.crtc_clock *= 2;
+		pipe_config->hw.adjusted_mode.crtc_clock *= 2;
 
 	gen11_dsi_get_timings(encoder, pipe_config);
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
 	pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc);
 }
 
+static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder,
+					struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	int dsc_max_bpc = INTEL_GEN(dev_priv) >= 12 ? 12 : 10;
+	bool use_dsc;
+	int ret;
+
+	use_dsc = intel_bios_get_dsc_params(encoder, crtc_state, dsc_max_bpc);
+	if (!use_dsc)
+		return 0;
+
+	if (crtc_state->pipe_bpp < 8 * 3)
+		return -EINVAL;
+
+	/* FIXME: split only when necessary */
+	if (crtc_state->dsc.slice_count > 1)
+		crtc_state->dsc.dsc_split = true;
+
+	vdsc_cfg->convert_rgb = true;
+
+	ret = intel_dsc_compute_params(encoder, crtc_state);
+	if (ret)
+		return ret;
+
+	/* DSI specific sanity checks on the common code */
+	WARN_ON(vdsc_cfg->vbr_enable);
+	WARN_ON(vdsc_cfg->simple_422);
+	WARN_ON(vdsc_cfg->pic_width % vdsc_cfg->slice_width);
+	WARN_ON(vdsc_cfg->slice_height < 8);
+	WARN_ON(vdsc_cfg->pic_height % vdsc_cfg->slice_height);
+
+	ret = drm_dsc_compute_rc_parameters(vdsc_cfg);
+	if (ret)
+		return ret;
+
+	crtc_state->dsc.compression_enable = true;
+
+	return 0;
+}
+
 static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
@@ -1265,11 +1379,11 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *fixed_mode =
 					intel_connector->panel.fixed_mode;
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
 
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
 	intel_fixed_panel_mode(fixed_mode, adjusted_mode);
@@ -1283,8 +1397,17 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	else
 		pipe_config->cpu_transcoder = TRANSCODER_DSI_0;
 
+	if (intel_dsi->pixel_format == MIPI_DSI_FMT_RGB888)
+		pipe_config->pipe_bpp = 24;
+	else
+		pipe_config->pipe_bpp = 18;
+
 	pipe_config->clock_set = true;
-	pipe_config->port_clock = intel_dsi_bitrate(intel_dsi) / 5;
+
+	if (gen11_dsi_dsc_compute_config(encoder, pipe_config))
+		DRM_DEBUG_KMS("Attempting to use DSC failed\n");
+
+	pipe_config->port_clock = afe_clk(encoder, pipe_config) / 5;
 
 	return 0;
 }
@@ -1292,15 +1415,21 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
 					struct intel_crtc_state *crtc_state)
 {
-	get_dsi_io_power_domains(to_i915(encoder->base.dev),
-				 enc_to_intel_dsi(&encoder->base));
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+
+	get_dsi_io_power_domains(i915,
+				 enc_to_intel_dsi(encoder));
+
+	if (crtc_state->dsc.compression_enable)
+		intel_display_power_get(i915,
+					intel_dsc_power_domain(crtc_state));
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum transcoder dsi_trans;
 	intel_wakeref_t wakeref;
 	enum port port;
@@ -1325,6 +1454,9 @@ static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
 		case TRANS_DDI_EDP_INPUT_C_ONOFF:
 			*pipe = PIPE_C;
 			break;
+		case TRANS_DDI_EDP_INPUT_D_ONOFF:
+			*pipe = PIPE_D;
+			break;
 		default:
 			DRM_ERROR("Invalid PIPE input\n");
 			goto out;
@@ -1360,7 +1492,7 @@ static const struct drm_connector_funcs gen11_dsi_connector_funcs = {
 
 static const struct drm_connector_helper_funcs gen11_dsi_connector_helper_funcs = {
 	.get_modes = intel_dsi_get_modes,
-	.mode_valid = intel_dsi_mode_valid,
+	.mode_valid = gen11_dsi_mode_valid,
 	.atomic_check = intel_digital_connector_atomic_check,
 };
 
@@ -1577,6 +1709,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	encoder->pre_pll_enable = gen11_dsi_pre_pll_enable;
 	encoder->pre_enable = gen11_dsi_pre_enable;
 	encoder->disable = gen11_dsi_disable;
+	encoder->post_disable = gen11_dsi_post_disable;
 	encoder->port = port;
 	encoder->get_config = gen11_dsi_get_config;
 	encoder->update_pipe = intel_panel_update_backlight;
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index c2875b10adf9..c362eecdd414 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -37,6 +37,7 @@
 #include "intel_atomic.h"
 #include "intel_display_types.h"
 #include "intel_hdcp.h"
+#include "intel_psr.h"
 #include "intel_sprite.h"
 
 /**
@@ -129,6 +130,7 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 	struct drm_crtc_state *crtc_state;
 
 	intel_hdcp_atomic_check(conn, old_state, new_state);
+	intel_psr_atomic_check(conn, old_state, new_state);
 
 	if (!new_state->crtc)
 		return 0;
@@ -175,6 +177,38 @@ intel_digital_connector_duplicate_state(struct drm_connector *connector)
 }
 
 /**
+ * intel_connector_needs_modeset - check if connector needs a modeset
+ */
+bool
+intel_connector_needs_modeset(struct intel_atomic_state *state,
+			      struct drm_connector *connector)
+{
+	const struct drm_connector_state *old_conn_state, *new_conn_state;
+
+	old_conn_state = drm_atomic_get_old_connector_state(&state->base, connector);
+	new_conn_state = drm_atomic_get_new_connector_state(&state->base, connector);
+
+	return old_conn_state->crtc != new_conn_state->crtc ||
+	       (new_conn_state->crtc &&
+		drm_atomic_crtc_needs_modeset(drm_atomic_get_new_crtc_state(&state->base,
+									    new_conn_state->crtc)));
+}
+
+struct intel_digital_connector_state *
+intel_atomic_get_digital_connector_state(struct intel_atomic_state *state,
+					 struct intel_connector *connector)
+{
+	struct drm_connector_state *conn_state;
+
+	conn_state = drm_atomic_get_connector_state(&state->base,
+						    &connector->base);
+	if (IS_ERR(conn_state))
+		return ERR_CAST(conn_state);
+
+	return to_intel_digital_connector_state(conn_state);
+}
+
+/**
  * intel_crtc_duplicate_state - duplicate crtc state
  * @crtc: drm crtc
  *
@@ -186,13 +220,22 @@ intel_digital_connector_duplicate_state(struct drm_connector *connector)
 struct drm_crtc_state *
 intel_crtc_duplicate_state(struct drm_crtc *crtc)
 {
+	const struct intel_crtc_state *old_crtc_state = to_intel_crtc_state(crtc->state);
 	struct intel_crtc_state *crtc_state;
 
-	crtc_state = kmemdup(crtc->state, sizeof(*crtc_state), GFP_KERNEL);
+	crtc_state = kmemdup(old_crtc_state, sizeof(*crtc_state), GFP_KERNEL);
 	if (!crtc_state)
 		return NULL;
 
-	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->base);
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &crtc_state->uapi);
+
+	/* copy color blobs */
+	if (crtc_state->hw.degamma_lut)
+		drm_property_blob_get(crtc_state->hw.degamma_lut);
+	if (crtc_state->hw.ctm)
+		drm_property_blob_get(crtc_state->hw.ctm);
+	if (crtc_state->hw.gamma_lut)
+		drm_property_blob_get(crtc_state->hw.gamma_lut);
 
 	crtc_state->update_pipe = false;
 	crtc_state->disable_lp_wm = false;
@@ -205,7 +248,29 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	crtc_state->fb_bits = 0;
 	crtc_state->update_planes = 0;
 
-	return &crtc_state->base;
+	return &crtc_state->uapi;
+}
+
+static void intel_crtc_put_color_blobs(struct intel_crtc_state *crtc_state)
+{
+	drm_property_blob_put(crtc_state->hw.degamma_lut);
+	drm_property_blob_put(crtc_state->hw.gamma_lut);
+	drm_property_blob_put(crtc_state->hw.ctm);
+}
+
+void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state)
+{
+	intel_crtc_put_color_blobs(crtc_state);
+}
+
+void intel_crtc_copy_color_blobs(struct intel_crtc_state *crtc_state)
+{
+	drm_property_replace_blob(&crtc_state->hw.degamma_lut,
+				  crtc_state->uapi.degamma_lut);
+	drm_property_replace_blob(&crtc_state->hw.gamma_lut,
+				  crtc_state->uapi.gamma_lut);
+	drm_property_replace_blob(&crtc_state->hw.ctm,
+				  crtc_state->uapi.ctm);
 }
 
 /**
@@ -220,7 +285,11 @@ void
 intel_crtc_destroy_state(struct drm_crtc *crtc,
 			 struct drm_crtc_state *state)
 {
-	drm_atomic_helper_crtc_destroy_state(crtc, state);
+	struct intel_crtc_state *crtc_state = to_intel_crtc_state(state);
+
+	__drm_atomic_helper_crtc_destroy_state(&crtc_state->uapi);
+	intel_crtc_free_hw_state(crtc_state);
+	kfree(crtc_state);
 }
 
 static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_state,
@@ -249,10 +318,10 @@ static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_sta
 		return;
 
 	/* set scaler mode */
-	if (plane_state && plane_state->base.fb &&
-	    plane_state->base.fb->format->is_yuv &&
-	    plane_state->base.fb->format->num_planes > 1) {
-		struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	if (plane_state && plane_state->hw.fb &&
+	    plane_state->hw.fb->format->is_yuv &&
+	    plane_state->hw.fb->format->num_planes > 1) {
+		struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 		if (IS_GEN(dev_priv, 9) &&
 		    !IS_GEMINILAKE(dev_priv)) {
 			mode = SKL_PS_SCALER_MODE_NV12;
@@ -319,7 +388,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 	struct intel_plane_state *plane_state = NULL;
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
-	struct drm_atomic_state *drm_state = crtc_state->base.state;
+	struct drm_atomic_state *drm_state = crtc_state->uapi.state;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(drm_state);
 	int num_scalers_need;
 	int i;
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h
index 49d5cb1b9e0a..74c749dbfb4f 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic.h
@@ -17,6 +17,7 @@ struct drm_device;
 struct drm_i915_private;
 struct drm_property;
 struct intel_atomic_state;
+struct intel_connector;
 struct intel_crtc;
 struct intel_crtc_state;
 
@@ -32,10 +33,17 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 					 struct drm_atomic_state *state);
 struct drm_connector_state *
 intel_digital_connector_duplicate_state(struct drm_connector *connector);
+bool intel_connector_needs_modeset(struct intel_atomic_state *state,
+				   struct drm_connector *connector);
+struct intel_digital_connector_state *
+intel_atomic_get_digital_connector_state(struct intel_atomic_state *state,
+					 struct intel_connector *connector);
 
 struct drm_crtc_state *intel_crtc_duplicate_state(struct drm_crtc *crtc);
 void intel_crtc_destroy_state(struct drm_crtc *crtc,
 			       struct drm_crtc_state *state);
+void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state);
+void intel_crtc_copy_color_blobs(struct intel_crtc_state *crtc_state);
 struct drm_atomic_state *intel_atomic_state_alloc(struct drm_device *dev);
 void intel_atomic_state_clear(struct drm_atomic_state *state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 98f557a9f8ee..3e97af682b1b 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -41,6 +41,16 @@
 #include "intel_pm.h"
 #include "intel_sprite.h"
 
+static void intel_plane_state_reset(struct intel_plane_state *plane_state,
+				    struct intel_plane *plane)
+{
+	memset(plane_state, 0, sizeof(*plane_state));
+
+	__drm_atomic_helper_plane_state_reset(&plane_state->uapi, &plane->base);
+
+	plane_state->scaler_id = -1;
+}
+
 struct intel_plane *intel_plane_alloc(void)
 {
 	struct intel_plane_state *plane_state;
@@ -56,8 +66,9 @@ struct intel_plane *intel_plane_alloc(void)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	__drm_atomic_helper_plane_reset(&plane->base, &plane_state->base);
-	plane_state->scaler_id = -1;
+	intel_plane_state_reset(plane_state, plane);
+
+	plane->base.state = &plane_state->uapi;
 
 	return plane;
 }
@@ -80,22 +91,24 @@ void intel_plane_free(struct intel_plane *plane)
 struct drm_plane_state *
 intel_plane_duplicate_state(struct drm_plane *plane)
 {
-	struct drm_plane_state *state;
 	struct intel_plane_state *intel_state;
 
-	intel_state = kmemdup(plane->state, sizeof(*intel_state), GFP_KERNEL);
+	intel_state = to_intel_plane_state(plane->state);
+	intel_state = kmemdup(intel_state, sizeof(*intel_state), GFP_KERNEL);
 
 	if (!intel_state)
 		return NULL;
 
-	state = &intel_state->base;
-
-	__drm_atomic_helper_plane_duplicate_state(plane, state);
+	__drm_atomic_helper_plane_duplicate_state(plane, &intel_state->uapi);
 
 	intel_state->vma = NULL;
 	intel_state->flags = 0;
 
-	return state;
+	/* add reference to fb */
+	if (intel_state->hw.fb)
+		drm_framebuffer_get(intel_state->hw.fb);
+
+	return &intel_state->uapi;
 }
 
 /**
@@ -110,18 +123,22 @@ void
 intel_plane_destroy_state(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
-	WARN_ON(to_intel_plane_state(state)->vma);
+	struct intel_plane_state *plane_state = to_intel_plane_state(state);
+	WARN_ON(plane_state->vma);
 
-	drm_atomic_helper_plane_destroy_state(plane, state);
+	__drm_atomic_helper_plane_destroy_state(&plane_state->uapi);
+	if (plane_state->hw.fb)
+		drm_framebuffer_put(plane_state->hw.fb);
+	kfree(plane_state);
 }
 
 unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	cpp = fb->format->cpp[0];
@@ -144,10 +161,10 @@ bool intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	const struct intel_plane_state *plane_state =
 		intel_atomic_get_new_plane_state(state, plane);
-	struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc);
 	struct intel_crtc_state *crtc_state;
 
-	if (!plane_state->base.visible || !plane->min_cdclk)
+	if (!plane_state->uapi.visible || !plane->min_cdclk)
 		return false;
 
 	crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
@@ -176,23 +193,52 @@ bool intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
 	return false;
 }
 
+static void intel_plane_clear_hw_state(struct intel_plane_state *plane_state)
+{
+	if (plane_state->hw.fb)
+		drm_framebuffer_put(plane_state->hw.fb);
+
+	memset(&plane_state->hw, 0, sizeof(plane_state->hw));
+}
+
+void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state,
+				       const struct intel_plane_state *from_plane_state)
+{
+	intel_plane_clear_hw_state(plane_state);
+
+	plane_state->hw.crtc = from_plane_state->uapi.crtc;
+	plane_state->hw.fb = from_plane_state->uapi.fb;
+	if (plane_state->hw.fb)
+		drm_framebuffer_get(plane_state->hw.fb);
+
+	plane_state->hw.alpha = from_plane_state->uapi.alpha;
+	plane_state->hw.pixel_blend_mode =
+		from_plane_state->uapi.pixel_blend_mode;
+	plane_state->hw.rotation = from_plane_state->uapi.rotation;
+	plane_state->hw.color_encoding = from_plane_state->uapi.color_encoding;
+	plane_state->hw.color_range = from_plane_state->uapi.color_range;
+}
+
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *new_crtc_state,
 					const struct intel_plane_state *old_plane_state,
 					struct intel_plane_state *new_plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(new_plane_state->base.plane);
-	const struct drm_framebuffer *fb = new_plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(new_plane_state->uapi.plane);
+	const struct drm_framebuffer *fb;
 	int ret;
 
+	intel_plane_copy_uapi_to_hw_state(new_plane_state, new_plane_state);
+	fb = new_plane_state->hw.fb;
+
 	new_crtc_state->active_planes &= ~BIT(plane->id);
 	new_crtc_state->nv12_planes &= ~BIT(plane->id);
 	new_crtc_state->c8_planes &= ~BIT(plane->id);
 	new_crtc_state->data_rate[plane->id] = 0;
 	new_crtc_state->min_cdclk[plane->id] = 0;
-	new_plane_state->base.visible = false;
+	new_plane_state->uapi.visible = false;
 
-	if (!new_plane_state->base.crtc && !old_plane_state->base.crtc)
+	if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc)
 		return 0;
 
 	ret = plane->check_plane(new_crtc_state, new_plane_state);
@@ -200,18 +246,18 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 		return ret;
 
 	/* FIXME pre-g4x don't work like this */
-	if (new_plane_state->base.visible)
+	if (new_plane_state->uapi.visible)
 		new_crtc_state->active_planes |= BIT(plane->id);
 
-	if (new_plane_state->base.visible &&
-	    drm_format_info_is_yuv_semiplanar(fb->format))
+	if (new_plane_state->uapi.visible &&
+	    intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		new_crtc_state->nv12_planes |= BIT(plane->id);
 
-	if (new_plane_state->base.visible &&
+	if (new_plane_state->uapi.visible &&
 	    fb->format->format == DRM_FORMAT_C8)
 		new_crtc_state->c8_planes |= BIT(plane->id);
 
-	if (new_plane_state->base.visible || old_plane_state->base.visible)
+	if (new_plane_state->uapi.visible || old_plane_state->uapi.visible)
 		new_crtc_state->update_planes |= BIT(plane->id);
 
 	new_crtc_state->data_rate[plane->id] =
@@ -225,11 +271,11 @@ static struct intel_crtc *
 get_crtc_from_states(const struct intel_plane_state *old_plane_state,
 		     const struct intel_plane_state *new_plane_state)
 {
-	if (new_plane_state->base.crtc)
-		return to_intel_crtc(new_plane_state->base.crtc);
+	if (new_plane_state->uapi.crtc)
+		return to_intel_crtc(new_plane_state->uapi.crtc);
 
-	if (old_plane_state->base.crtc)
-		return to_intel_crtc(old_plane_state->base.crtc);
+	if (old_plane_state->uapi.crtc)
+		return to_intel_crtc(old_plane_state->uapi.crtc);
 
 	return NULL;
 }
@@ -246,7 +292,7 @@ int intel_plane_atomic_check(struct intel_atomic_state *state,
 	const struct intel_crtc_state *old_crtc_state;
 	struct intel_crtc_state *new_crtc_state;
 
-	new_plane_state->base.visible = false;
+	new_plane_state->uapi.visible = false;
 	if (!crtc)
 		return 0;
 
@@ -307,26 +353,16 @@ void intel_update_plane(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	trace_intel_update_plane(&plane->base, crtc);
 	plane->update_plane(plane, crtc_state, plane_state);
 }
 
-void intel_update_slave(struct intel_plane *plane,
-			const struct intel_crtc_state *crtc_state,
-			const struct intel_plane_state *plane_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-
-	trace_intel_update_plane(&plane->base, crtc);
-	plane->update_slave(plane, crtc_state, plane_state);
-}
-
 void intel_disable_plane(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	trace_intel_disable_plane(&plane->base, crtc);
 	plane->disable_plane(plane, crtc_state);
@@ -355,25 +391,9 @@ void skl_update_planes_on_crtc(struct intel_atomic_state *state,
 		struct intel_plane_state *new_plane_state =
 			intel_atomic_get_new_plane_state(state, plane);
 
-		if (new_plane_state->base.visible) {
+		if (new_plane_state->uapi.visible ||
+		    new_plane_state->planar_slave) {
 			intel_update_plane(plane, new_crtc_state, new_plane_state);
-		} else if (new_plane_state->planar_slave) {
-			struct intel_plane *master =
-				new_plane_state->planar_linked_plane;
-
-			/*
-			 * We update the slave plane from this function because
-			 * programming it from the master plane's update_plane
-			 * callback runs into issues when the Y plane is
-			 * reassigned, disabled or used by a different plane.
-			 *
-			 * The slave plane is updated with the master plane's
-			 * plane_state.
-			 */
-			new_plane_state =
-				intel_atomic_get_new_plane_state(state, master);
-
-			intel_update_slave(plane, new_crtc_state, new_plane_state);
 		} else {
 			intel_disable_plane(plane, new_crtc_state);
 		}
@@ -395,7 +415,7 @@ void i9xx_update_planes_on_crtc(struct intel_atomic_state *state,
 		    !(update_mask & BIT(plane->id)))
 			continue;
 
-		if (new_plane_state->base.visible)
+		if (new_plane_state->uapi.visible)
 			intel_update_plane(plane, new_crtc_state, new_plane_state);
 		else
 			intel_disable_plane(plane, new_crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index e61e9a82aadf..5cedafdddb55 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -20,12 +20,11 @@ extern const struct drm_plane_helper_funcs intel_plane_helper_funcs;
 
 unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state);
+void intel_plane_copy_uapi_to_hw_state(struct intel_plane_state *plane_state,
+				       const struct intel_plane_state *from_plane_state);
 void intel_update_plane(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
-void intel_update_slave(struct intel_plane *plane,
-			const struct intel_crtc_state *crtc_state,
-			const struct intel_plane_state *plane_state);
 void intel_disable_plane(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state);
 struct intel_plane *intel_plane_alloc(void);
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 3a5ac13d5801..b18040793d9e 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -234,7 +234,7 @@ static const struct hdmi_aud_ncts hdmi_aud_ncts_36bpp[] = {
 static u32 audio_config_hdmi_pixel_clock(const struct intel_crtc_state *crtc_state)
 {
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(hdmi_audio_clock); i++) {
@@ -555,7 +555,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
 	u32 tmp, eldv;
@@ -602,7 +602,7 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 				   const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
@@ -692,10 +692,10 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct i915_audio_component *acomp = dev_priv->audio_component;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	enum port port = encoder->port;
 	enum pipe pipe = crtc->pipe;
 
@@ -707,8 +707,8 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 	DRM_DEBUG_DRIVER("ELD on [CONNECTOR:%d:%s], [ENCODER:%d:%s]\n",
 			 connector->base.id,
 			 connector->name,
-			 connector->encoder->base.id,
-			 connector->encoder->name);
+			 encoder->base.base.id,
+			 encoder->base.name);
 
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
 
@@ -753,7 +753,7 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct i915_audio_component *acomp = dev_priv->audio_component;
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum port port = encoder->port;
 	enum pipe pipe = crtc->pipe;
 
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 63c1bd4c2954..8beac06e3f10 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -29,6 +29,7 @@
 #include <drm/i915_drm.h>
 
 #include "display/intel_display.h"
+#include "display/intel_display_types.h"
 #include "display/intel_gmbus.h"
 
 #include "i915_drv.h"
@@ -58,6 +59,13 @@
  * that.
  */
 
+/* Wrapper for VBT child device config */
+struct display_device_data {
+	struct child_device_config child;
+	struct dsc_compression_parameters_entry *dsc;
+	struct list_head node;
+};
+
 #define	SLAVE_ADDR1	0x70
 #define	SLAVE_ADDR2	0x72
 
@@ -202,17 +210,12 @@ get_lvds_fp_timing(const struct bdb_header *bdb,
 	return (const struct lvds_fp_timing *)((const u8 *)bdb + ofs);
 }
 
-/* Try to find integrated panel data */
+/* Parse general panel options */
 static void
-parse_lfp_panel_data(struct drm_i915_private *dev_priv,
-		     const struct bdb_header *bdb)
+parse_panel_options(struct drm_i915_private *dev_priv,
+		    const struct bdb_header *bdb)
 {
 	const struct bdb_lvds_options *lvds_options;
-	const struct bdb_lvds_lfp_data *lvds_lfp_data;
-	const struct bdb_lvds_lfp_data_ptrs *lvds_lfp_data_ptrs;
-	const struct lvds_dvo_timing *panel_dvo_timing;
-	const struct lvds_fp_timing *fp_timing;
-	struct drm_display_mode *panel_fixed_mode;
 	int panel_type;
 	int drrs_mode;
 	int ret;
@@ -261,6 +264,19 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("DRRS not supported (VBT input)\n");
 		break;
 	}
+}
+
+/* Try to find integrated panel timing data */
+static void
+parse_lfp_panel_dtd(struct drm_i915_private *dev_priv,
+		    const struct bdb_header *bdb)
+{
+	const struct bdb_lvds_lfp_data *lvds_lfp_data;
+	const struct bdb_lvds_lfp_data_ptrs *lvds_lfp_data_ptrs;
+	const struct lvds_dvo_timing *panel_dvo_timing;
+	const struct lvds_fp_timing *fp_timing;
+	struct drm_display_mode *panel_fixed_mode;
+	int panel_type = dev_priv->vbt.panel_type;
 
 	lvds_lfp_data = find_section(bdb, BDB_LVDS_LFP_DATA);
 	if (!lvds_lfp_data)
@@ -282,7 +298,7 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 
 	dev_priv->vbt.lfp_lvds_vbt_mode = panel_fixed_mode;
 
-	DRM_DEBUG_KMS("Found panel mode in BIOS VBT tables:\n");
+	DRM_DEBUG_KMS("Found panel mode in BIOS VBT legacy lfp table:\n");
 	drm_mode_debug_printmodeline(panel_fixed_mode);
 
 	fp_timing = get_lvds_fp_timing(bdb, lvds_lfp_data,
@@ -300,6 +316,98 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 }
 
 static void
+parse_generic_dtd(struct drm_i915_private *dev_priv,
+		  const struct bdb_header *bdb)
+{
+	const struct bdb_generic_dtd *generic_dtd;
+	const struct generic_dtd_entry *dtd;
+	struct drm_display_mode *panel_fixed_mode;
+	int num_dtd;
+
+	generic_dtd = find_section(bdb, BDB_GENERIC_DTD);
+	if (!generic_dtd)
+		return;
+
+	if (generic_dtd->gdtd_size < sizeof(struct generic_dtd_entry)) {
+		DRM_ERROR("GDTD size %u is too small.\n",
+			  generic_dtd->gdtd_size);
+		return;
+	} else if (generic_dtd->gdtd_size !=
+		   sizeof(struct generic_dtd_entry)) {
+		DRM_ERROR("Unexpected GDTD size %u\n", generic_dtd->gdtd_size);
+		/* DTD has unknown fields, but keep going */
+	}
+
+	num_dtd = (get_blocksize(generic_dtd) -
+		   sizeof(struct bdb_generic_dtd)) / generic_dtd->gdtd_size;
+	if (dev_priv->vbt.panel_type >= num_dtd) {
+		DRM_ERROR("Panel type %d not found in table of %d DTD's\n",
+			  dev_priv->vbt.panel_type, num_dtd);
+		return;
+	}
+
+	dtd = &generic_dtd->dtd[dev_priv->vbt.panel_type];
+
+	panel_fixed_mode = kzalloc(sizeof(*panel_fixed_mode), GFP_KERNEL);
+	if (!panel_fixed_mode)
+		return;
+
+	panel_fixed_mode->hdisplay = dtd->hactive;
+	panel_fixed_mode->hsync_start =
+		panel_fixed_mode->hdisplay + dtd->hfront_porch;
+	panel_fixed_mode->hsync_end =
+		panel_fixed_mode->hsync_start + dtd->hsync;
+	panel_fixed_mode->htotal = panel_fixed_mode->hsync_end;
+
+	panel_fixed_mode->vdisplay = dtd->vactive;
+	panel_fixed_mode->vsync_start =
+		panel_fixed_mode->vdisplay + dtd->vfront_porch;
+	panel_fixed_mode->vsync_end =
+		panel_fixed_mode->vsync_start + dtd->vsync;
+	panel_fixed_mode->vtotal = panel_fixed_mode->vsync_end;
+
+	panel_fixed_mode->clock = dtd->pixel_clock;
+	panel_fixed_mode->width_mm = dtd->width_mm;
+	panel_fixed_mode->height_mm = dtd->height_mm;
+
+	panel_fixed_mode->type = DRM_MODE_TYPE_PREFERRED;
+	drm_mode_set_name(panel_fixed_mode);
+
+	if (dtd->hsync_positive_polarity)
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_PHSYNC;
+	else
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_NHSYNC;
+
+	if (dtd->vsync_positive_polarity)
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_PVSYNC;
+	else
+		panel_fixed_mode->flags |= DRM_MODE_FLAG_NVSYNC;
+
+	DRM_DEBUG_KMS("Found panel mode in BIOS VBT generic dtd table:\n");
+	drm_mode_debug_printmodeline(panel_fixed_mode);
+
+	dev_priv->vbt.lfp_lvds_vbt_mode = panel_fixed_mode;
+}
+
+static void
+parse_panel_dtd(struct drm_i915_private *dev_priv,
+		const struct bdb_header *bdb)
+{
+	/*
+	 * Older VBTs provided provided DTD information for internal displays
+	 * through the "LFP panel DTD" block (42).  As of VBT revision 229,
+	 * that block is now deprecated and DTD information should be provided
+	 * via a newer "generic DTD" block (58).  Just to be safe, we'll
+	 * try the new generic DTD block first on VBT >= 229, but still fall
+	 * back to trying the old LFP block if that fails.
+	 */
+	if (bdb->version >= 229)
+		parse_generic_dtd(dev_priv, bdb);
+	if (!dev_priv->vbt.lfp_lvds_vbt_mode)
+		parse_lfp_panel_dtd(dev_priv, bdb);
+}
+
+static void
 parse_lfp_backlight(struct drm_i915_private *dev_priv,
 		    const struct bdb_header *bdb)
 {
@@ -449,8 +557,9 @@ static void
 parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, u8 bdb_version)
 {
 	struct sdvo_device_mapping *mapping;
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i, count = 0;
+	int count = 0;
 
 	/*
 	 * Only parse SDVO mappings on gens that could have SDVO. This isn't
@@ -461,8 +570,8 @@ parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, u8 bdb_version)
 		return;
 	}
 
-	for (i = 0, count = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if (child->slave_addr != SLAVE_ADDR1 &&
 		    child->slave_addr != SLAVE_ADDR2) {
@@ -552,16 +661,45 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 			dev_priv->vbt.int_lvds_support = 0;
 	}
 
-	DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
+	if (bdb->version < 228) {
+		DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
+		/*
+		 * If DRRS is not supported, drrs_type has to be set to 0.
+		 * This is because, VBT is configured in such a way that
+		 * static DRRS is 0 and DRRS not supported is represented by
+		 * driver->drrs_enabled=false
+		 */
+		if (!driver->drrs_enabled)
+			dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
+
+		dev_priv->vbt.psr.enable = driver->psr_enabled;
+	}
+}
+
+static void
+parse_power_conservation_features(struct drm_i915_private *dev_priv,
+				  const struct bdb_header *bdb)
+{
+	const struct bdb_lfp_power *power;
+	u8 panel_type = dev_priv->vbt.panel_type;
+
+	if (bdb->version < 228)
+		return;
+
+	power = find_section(bdb, BDB_LVDS_POWER);
+	if (!power)
+		return;
+
+	dev_priv->vbt.psr.enable = power->psr & BIT(panel_type);
+
 	/*
 	 * If DRRS is not supported, drrs_type has to be set to 0.
 	 * This is because, VBT is configured in such a way that
 	 * static DRRS is 0 and DRRS not supported is represented by
-	 * driver->drrs_enabled=false
+	 * power->drrs & BIT(panel_type)=false
 	 */
-	if (!driver->drrs_enabled)
+	if (!(power->drrs & BIT(panel_type)))
 		dev_priv->vbt.drrs_type = DRRS_NOT_SUPPORTED;
-	dev_priv->vbt.psr.enable = driver->psr_enabled;
 }
 
 static void
@@ -1230,6 +1368,57 @@ err:
 	memset(dev_priv->vbt.dsi.sequence, 0, sizeof(dev_priv->vbt.dsi.sequence));
 }
 
+static void
+parse_compression_parameters(struct drm_i915_private *i915,
+			     const struct bdb_header *bdb)
+{
+	const struct bdb_compression_parameters *params;
+	struct display_device_data *devdata;
+	const struct child_device_config *child;
+	u16 block_size;
+	int index;
+
+	if (bdb->version < 198)
+		return;
+
+	params = find_section(bdb, BDB_COMPRESSION_PARAMETERS);
+	if (params) {
+		/* Sanity checks */
+		if (params->entry_size != sizeof(params->data[0])) {
+			DRM_DEBUG_KMS("VBT: unsupported compression param entry size\n");
+			return;
+		}
+
+		block_size = get_blocksize(params);
+		if (block_size < sizeof(*params)) {
+			DRM_DEBUG_KMS("VBT: expected 16 compression param entries\n");
+			return;
+		}
+	}
+
+	list_for_each_entry(devdata, &i915->vbt.display_devices, node) {
+		child = &devdata->child;
+
+		if (!child->compression_enable)
+			continue;
+
+		if (!params) {
+			DRM_DEBUG_KMS("VBT: compression params not available\n");
+			continue;
+		}
+
+		if (child->compression_method_cps) {
+			DRM_DEBUG_KMS("VBT: CPS compression not supported\n");
+			continue;
+		}
+
+		index = child->compression_structure_index;
+
+		devdata->dsc = kmemdup(&params->data[index],
+				       sizeof(*devdata->dsc), GFP_KERNEL);
+	}
+}
+
 static u8 translate_iboost(u8 val)
 {
 	static const u8 mapping[] = { 1, 3, 7 }; /* See VBT spec */
@@ -1246,7 +1435,7 @@ static enum port get_port_by_ddc_pin(struct drm_i915_private *i915, u8 ddc_pin)
 	const struct ddi_vbt_port_info *info;
 	enum port port;
 
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+	for_each_port(port) {
 		info = &i915->vbt.ddi_port_info[port];
 
 		if (info->child && ddc_pin == info->alternate_ddc_pin)
@@ -1297,7 +1486,7 @@ static enum port get_port_by_aux_ch(struct drm_i915_private *i915, u8 aux_ch)
 	const struct ddi_vbt_port_info *info;
 	enum port port;
 
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+	for_each_port(port) {
 		info = &i915->vbt.ddi_port_info[port];
 
 		if (info->child && aux_ch == info->alternate_aux_channel)
@@ -1418,9 +1607,10 @@ static enum port dvo_port_to_port(u8 dvo_port)
 }
 
 static void parse_ddi_port(struct drm_i915_private *dev_priv,
-			   const struct child_device_config *child,
+			   struct display_device_data *devdata,
 			   u8 bdb_version)
 {
+	const struct child_device_config *child = &devdata->child;
 	struct ddi_vbt_port_info *info;
 	bool is_dvi, is_hdmi, is_dp, is_edp, is_crt;
 	enum port port;
@@ -1443,7 +1633,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 	is_hdmi = is_dvi && (child->device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0;
 	is_edp = is_dp && (child->device_type & DEVICE_TYPE_INTERNAL_CONNECTOR);
 
-	if (port == PORT_A && is_dvi) {
+	if (port == PORT_A && is_dvi && INTEL_GEN(dev_priv) < 12) {
 		DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n",
 			      is_hdmi ? "/HDMI" : "");
 		is_dvi = false;
@@ -1461,26 +1651,11 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 	if (bdb_version >= 209)
 		info->supports_tbt = child->tbt;
 
-	DRM_DEBUG_KMS("Port %c VBT info: CRT:%d DVI:%d HDMI:%d DP:%d eDP:%d LSPCON:%d USB-Type-C:%d TBT:%d\n",
+	DRM_DEBUG_KMS("Port %c VBT info: CRT:%d DVI:%d HDMI:%d DP:%d eDP:%d LSPCON:%d USB-Type-C:%d TBT:%d DSC:%d\n",
 		      port_name(port), is_crt, is_dvi, is_hdmi, is_dp, is_edp,
 		      HAS_LSPCON(dev_priv) && child->lspcon,
-		      info->supports_typec_usb, info->supports_tbt);
-
-	if (is_edp && is_dvi)
-		DRM_DEBUG_KMS("Internal DP port %c is TMDS compatible\n",
-			      port_name(port));
-	if (is_crt && port != PORT_E)
-		DRM_DEBUG_KMS("Port %c is analog\n", port_name(port));
-	if (is_crt && (is_dvi || is_dp))
-		DRM_DEBUG_KMS("Analog port %c is also DP or TMDS compatible\n",
-			      port_name(port));
-	if (is_dvi && (port == PORT_A || port == PORT_E))
-		DRM_DEBUG_KMS("Port %c is TMDS compatible\n", port_name(port));
-	if (!is_dvi && !is_dp && !is_crt)
-		DRM_DEBUG_KMS("Port %c is not DP/TMDS/CRT compatible\n",
-			      port_name(port));
-	if (is_edp && (port == PORT_B || port == PORT_C || port == PORT_E))
-		DRM_DEBUG_KMS("Port %c is internal DP\n", port_name(port));
+		      info->supports_typec_usb, info->supports_tbt,
+		      devdata->dsc != NULL);
 
 	if (is_dvi) {
 		u8 ddc_pin;
@@ -1509,6 +1684,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 			      port_name(port),
 			      hdmi_level_shift);
 		info->hdmi_level_shift = hdmi_level_shift;
+		info->hdmi_level_shift_set = true;
 	}
 
 	if (bdb_version >= 204) {
@@ -1571,8 +1747,7 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv,
 
 static void parse_ddi_ports(struct drm_i915_private *dev_priv, u8 bdb_version)
 {
-	const struct child_device_config *child;
-	int i;
+	struct display_device_data *devdata;
 
 	if (!HAS_DDI(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		return;
@@ -1580,11 +1755,8 @@ static void parse_ddi_ports(struct drm_i915_private *dev_priv, u8 bdb_version)
 	if (bdb_version < 155)
 		return;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
-
-		parse_ddi_port(dev_priv, child, bdb_version);
-	}
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node)
+		parse_ddi_port(dev_priv, devdata, bdb_version);
 }
 
 static void
@@ -1592,8 +1764,9 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 			  const struct bdb_header *bdb)
 {
 	const struct bdb_general_definitions *defs;
+	struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i, child_device_num, count;
+	int i, child_device_num;
 	u8 expected_size;
 	u16 block_size;
 	int bus_pin;
@@ -1649,26 +1822,7 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 
 	/* get the number of child device */
 	child_device_num = (block_size - sizeof(*defs)) / defs->child_dev_size;
-	count = 0;
-	/* get the number of child device that is present */
-	for (i = 0; i < child_device_num; i++) {
-		child = child_device_ptr(defs, i);
-		if (!child->device_type)
-			continue;
-		count++;
-	}
-	if (!count) {
-		DRM_DEBUG_KMS("no child dev is parsed from VBT\n");
-		return;
-	}
-	dev_priv->vbt.child_dev = kcalloc(count, sizeof(*child), GFP_KERNEL);
-	if (!dev_priv->vbt.child_dev) {
-		DRM_DEBUG_KMS("No memory space for child device\n");
-		return;
-	}
 
-	dev_priv->vbt.child_dev_num = count;
-	count = 0;
 	for (i = 0; i < child_device_num; i++) {
 		child = child_device_ptr(defs, i);
 		if (!child->device_type)
@@ -1677,23 +1831,29 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("Found VBT child device with type 0x%x\n",
 			      child->device_type);
 
+		devdata = kzalloc(sizeof(*devdata), GFP_KERNEL);
+		if (!devdata)
+			break;
+
 		/*
 		 * Copy as much as we know (sizeof) and is available
-		 * (child_dev_size) of the child device. Accessing the data must
-		 * depend on VBT version.
+		 * (child_dev_size) of the child device config. Accessing the
+		 * data must depend on VBT version.
 		 */
-		memcpy(dev_priv->vbt.child_dev + count, child,
+		memcpy(&devdata->child, child,
 		       min_t(size_t, defs->child_dev_size, sizeof(*child)));
-		count++;
+
+		list_add_tail(&devdata->node, &dev_priv->vbt.display_devices);
 	}
+
+	if (list_empty(&dev_priv->vbt.display_devices))
+		DRM_DEBUG_KMS("no child dev is parsed from VBT\n");
 }
 
 /* Common defaults which may be overridden by VBT. */
 static void
 init_vbt_defaults(struct drm_i915_private *dev_priv)
 {
-	enum port port;
-
 	dev_priv->vbt.crt_ddc_pin = GMBUS_PIN_VGADDC;
 
 	/* Default to having backlight */
@@ -1721,13 +1881,6 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	dev_priv->vbt.lvds_ssc_freq = intel_bios_ssc_frequency(dev_priv,
 			!HAS_PCH_SPLIT(dev_priv));
 	DRM_DEBUG_KMS("Set default to SSC at %d kHz\n", dev_priv->vbt.lvds_ssc_freq);
-
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
-		struct ddi_vbt_port_info *info =
-			&dev_priv->vbt.ddi_port_info[port];
-
-		info->hdmi_level_shift = HDMI_LEVEL_SHIFT_UNKNOWN;
-	}
 }
 
 /* Defaults to initialize only if there is no VBT. */
@@ -1736,7 +1889,7 @@ init_vbt_missing_defaults(struct drm_i915_private *dev_priv)
 {
 	enum port port;
 
-	for (port = PORT_A; port < I915_MAX_PORTS; port++) {
+	for_each_port(port) {
 		struct ddi_vbt_port_info *info =
 			&dev_priv->vbt.ddi_port_info[port];
 		enum phy phy = intel_port_to_phy(dev_priv, port);
@@ -1787,6 +1940,13 @@ bool intel_bios_is_valid_vbt(const void *buf, size_t size)
 		return false;
 	}
 
+	if (vbt->vbt_size > size) {
+		DRM_DEBUG_DRIVER("VBT incomplete (vbt_size overflows)\n");
+		return false;
+	}
+
+	size = vbt->vbt_size;
+
 	if (range_overflows_t(size_t,
 			      vbt->bdb_offset,
 			      sizeof(struct bdb_header),
@@ -1804,28 +1964,61 @@ bool intel_bios_is_valid_vbt(const void *buf, size_t size)
 	return vbt;
 }
 
-static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
+static struct vbt_header *oprom_get_vbt(struct drm_i915_private *dev_priv)
 {
-	size_t i;
+	struct pci_dev *pdev = dev_priv->drm.pdev;
+	void __iomem *p = NULL, *oprom;
+	struct vbt_header *vbt;
+	u16 vbt_size;
+	size_t i, size;
 
-	/* Scour memory looking for the VBT signature. */
-	for (i = 0; i + 4 < size; i++) {
-		void *vbt;
+	oprom = pci_map_rom(pdev, &size);
+	if (!oprom)
+		return NULL;
 
-		if (ioread32(bios + i) != *((const u32 *) "$VBT"))
+	/* Scour memory looking for the VBT signature. */
+	for (i = 0; i + 4 < size; i += 4) {
+		if (ioread32(oprom + i) != *((const u32 *)"$VBT"))
 			continue;
 
-		/*
-		 * This is the one place where we explicitly discard the address
-		 * space (__iomem) of the BIOS/VBT.
-		 */
-		vbt = (void __force *) bios + i;
-		if (intel_bios_is_valid_vbt(vbt, size - i))
-			return vbt;
-
+		p = oprom + i;
+		size -= i;
 		break;
 	}
 
+	if (!p)
+		goto err_unmap_oprom;
+
+	if (sizeof(struct vbt_header) > size) {
+		DRM_DEBUG_DRIVER("VBT header incomplete\n");
+		goto err_unmap_oprom;
+	}
+
+	vbt_size = ioread16(p + offsetof(struct vbt_header, vbt_size));
+	if (vbt_size > size) {
+		DRM_DEBUG_DRIVER("VBT incomplete (vbt_size overflows)\n");
+		goto err_unmap_oprom;
+	}
+
+	/* The rest will be validated by intel_bios_is_valid_vbt() */
+	vbt = kmalloc(vbt_size, GFP_KERNEL);
+	if (!vbt)
+		goto err_unmap_oprom;
+
+	memcpy_fromio(vbt, p, vbt_size);
+
+	if (!intel_bios_is_valid_vbt(vbt, vbt_size))
+		goto err_free_vbt;
+
+	pci_unmap_rom(pdev, oprom);
+
+	return vbt;
+
+err_free_vbt:
+	kfree(vbt);
+err_unmap_oprom:
+	pci_unmap_rom(pdev, oprom);
+
 	return NULL;
 }
 
@@ -1839,10 +2032,11 @@ static const struct vbt_header *find_vbt(void __iomem *bios, size_t size)
  */
 void intel_bios_init(struct drm_i915_private *dev_priv)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
 	const struct vbt_header *vbt = dev_priv->opregion.vbt;
+	struct vbt_header *oprom_vbt = NULL;
 	const struct bdb_header *bdb;
-	u8 __iomem *bios = NULL;
+
+	INIT_LIST_HEAD(&dev_priv->vbt.display_devices);
 
 	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) {
 		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
@@ -1853,15 +2047,11 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 
 	/* If the OpRegion does not have VBT, look in PCI ROM. */
 	if (!vbt) {
-		size_t size;
-
-		bios = pci_map_rom(pdev, &size);
-		if (!bios)
+		oprom_vbt = oprom_get_vbt(dev_priv);
+		if (!oprom_vbt)
 			goto out;
 
-		vbt = find_vbt(bios, size);
-		if (!vbt)
-			goto out;
+		vbt = oprom_vbt;
 
 		DRM_DEBUG_KMS("Found valid VBT in PCI ROM\n");
 	}
@@ -1874,15 +2064,20 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 	/* Grab useful general definitions */
 	parse_general_features(dev_priv, bdb);
 	parse_general_definitions(dev_priv, bdb);
-	parse_lfp_panel_data(dev_priv, bdb);
+	parse_panel_options(dev_priv, bdb);
+	parse_panel_dtd(dev_priv, bdb);
 	parse_lfp_backlight(dev_priv, bdb);
 	parse_sdvo_panel_data(dev_priv, bdb);
 	parse_driver_features(dev_priv, bdb);
+	parse_power_conservation_features(dev_priv, bdb);
 	parse_edp(dev_priv, bdb);
 	parse_psr(dev_priv, bdb);
 	parse_mipi_config(dev_priv, bdb);
 	parse_mipi_sequence(dev_priv, bdb);
 
+	/* Depends on child device list */
+	parse_compression_parameters(dev_priv, bdb);
+
 	/* Further processing on pre-parsed data */
 	parse_sdvo_device_mapping(dev_priv, bdb->version);
 	parse_ddi_ports(dev_priv, bdb->version);
@@ -1893,8 +2088,7 @@ out:
 		init_vbt_missing_defaults(dev_priv);
 	}
 
-	if (bios)
-		pci_unmap_rom(pdev, bios);
+	kfree(oprom_vbt);
 }
 
 /**
@@ -1903,9 +2097,14 @@ out:
  */
 void intel_bios_driver_remove(struct drm_i915_private *dev_priv)
 {
-	kfree(dev_priv->vbt.child_dev);
-	dev_priv->vbt.child_dev = NULL;
-	dev_priv->vbt.child_dev_num = 0;
+	struct display_device_data *devdata, *n;
+
+	list_for_each_entry_safe(devdata, n, &dev_priv->vbt.display_devices, node) {
+		list_del(&devdata->node);
+		kfree(devdata->dsc);
+		kfree(devdata);
+	}
+
 	kfree(dev_priv->vbt.sdvo_lvds_vbt_mode);
 	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
 	kfree(dev_priv->vbt.lfp_lvds_vbt_mode);
@@ -1929,17 +2128,18 @@ void intel_bios_driver_remove(struct drm_i915_private *dev_priv)
  */
 bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i;
 
 	if (!dev_priv->vbt.int_tv_support)
 		return false;
 
-	if (!dev_priv->vbt.child_dev_num)
+	if (list_empty(&dev_priv->vbt.display_devices))
 		return true;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
+
 		/*
 		 * If the device type is not TV, continue.
 		 */
@@ -1971,14 +2171,14 @@ bool intel_bios_is_tv_present(struct drm_i915_private *dev_priv)
  */
 bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
-	int i;
 
-	if (!dev_priv->vbt.child_dev_num)
+	if (list_empty(&dev_priv->vbt.display_devices))
 		return true;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		/* If the device type is not LFP, continue.
 		 * We have to check both the new identifiers as well as the
@@ -2020,6 +2220,7 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *dev_priv, u8 *i2c_pin)
  */
 bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port port)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
 	static const struct {
 		u16 dp, hdmi;
@@ -2030,7 +2231,6 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
 		[PORT_E] = { DVO_PORT_DPE, DVO_PORT_HDMIE, },
 		[PORT_F] = { DVO_PORT_DPF, DVO_PORT_HDMIF, },
 	};
-	int i;
 
 	if (HAS_DDI(dev_priv)) {
 		const struct ddi_vbt_port_info *port_info =
@@ -2045,11 +2245,8 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
 	if (WARN_ON(port == PORT_A) || port >= ARRAY_SIZE(port_mapping))
 		return false;
 
-	if (!dev_priv->vbt.child_dev_num)
-		return false;
-
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if ((child->dvo_port == port_mapping[port].dp ||
 		     child->dvo_port == port_mapping[port].hdmi) &&
@@ -2070,6 +2267,7 @@ bool intel_bios_is_port_present(struct drm_i915_private *dev_priv, enum port por
  */
 bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
 	static const short port_mapping[] = {
 		[PORT_B] = DVO_PORT_DPB,
@@ -2078,16 +2276,12 @@ bool intel_bios_is_port_edp(struct drm_i915_private *dev_priv, enum port port)
 		[PORT_E] = DVO_PORT_DPE,
 		[PORT_F] = DVO_PORT_DPF,
 	};
-	int i;
 
 	if (HAS_DDI(dev_priv))
 		return dev_priv->vbt.ddi_port_info[port].supports_edp;
 
-	if (!dev_priv->vbt.child_dev_num)
-		return false;
-
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if (child->dvo_port == port_mapping[port] &&
 		    (child->device_type & DEVICE_TYPE_eDP_BITS) ==
@@ -2136,13 +2330,10 @@ static bool child_dev_is_dp_dual_mode(const struct child_device_config *child,
 bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv,
 				     enum port port)
 {
-	const struct child_device_config *child;
-	int i;
-
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	const struct display_device_data *devdata;
 
-		if (child_dev_is_dp_dual_mode(child, port))
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		if (child_dev_is_dp_dual_mode(&devdata->child, port))
 			return true;
 	}
 
@@ -2159,12 +2350,12 @@ bool intel_bios_is_port_dp_dual_mode(struct drm_i915_private *dev_priv,
 bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv,
 			       enum port *port)
 {
+	const struct display_device_data *devdata;
 	const struct child_device_config *child;
 	u8 dvo_port;
-	int i;
 
-	for (i = 0; i < dev_priv->vbt.child_dev_num; i++) {
-		child = dev_priv->vbt.child_dev + i;
+	list_for_each_entry(devdata, &dev_priv->vbt.display_devices, node) {
+		child = &devdata->child;
 
 		if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT))
 			continue;
@@ -2188,6 +2379,104 @@ bool intel_bios_is_dsi_present(struct drm_i915_private *dev_priv,
 	return false;
 }
 
+static void fill_dsc(struct intel_crtc_state *crtc_state,
+		     struct dsc_compression_parameters_entry *dsc,
+		     int dsc_max_bpc)
+{
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	int bpc = 8;
+
+	vdsc_cfg->dsc_version_major = dsc->version_major;
+	vdsc_cfg->dsc_version_minor = dsc->version_minor;
+
+	if (dsc->support_12bpc && dsc_max_bpc >= 12)
+		bpc = 12;
+	else if (dsc->support_10bpc && dsc_max_bpc >= 10)
+		bpc = 10;
+	else if (dsc->support_8bpc && dsc_max_bpc >= 8)
+		bpc = 8;
+	else
+		DRM_DEBUG_KMS("VBT: Unsupported BPC %d for DCS\n",
+			      dsc_max_bpc);
+
+	crtc_state->pipe_bpp = bpc * 3;
+
+	crtc_state->dsc.compressed_bpp = min(crtc_state->pipe_bpp,
+					     VBT_DSC_MAX_BPP(dsc->max_bpp));
+
+	/*
+	 * FIXME: This is ugly, and slice count should take DSC engine
+	 * throughput etc. into account.
+	 *
+	 * Also, per spec DSI supports 1, 2, 3 or 4 horizontal slices.
+	 */
+	if (dsc->slices_per_line & BIT(2)) {
+		crtc_state->dsc.slice_count = 4;
+	} else if (dsc->slices_per_line & BIT(1)) {
+		crtc_state->dsc.slice_count = 2;
+	} else {
+		/* FIXME */
+		if (!(dsc->slices_per_line & BIT(0)))
+			DRM_DEBUG_KMS("VBT: Unsupported DSC slice count for DSI\n");
+
+		crtc_state->dsc.slice_count = 1;
+	}
+
+	if (crtc_state->hw.adjusted_mode.crtc_hdisplay %
+	    crtc_state->dsc.slice_count != 0)
+		DRM_DEBUG_KMS("VBT: DSC hdisplay %d not divisible by slice count %d\n",
+			      crtc_state->hw.adjusted_mode.crtc_hdisplay,
+			      crtc_state->dsc.slice_count);
+
+	/*
+	 * FIXME: Use VBT rc_buffer_block_size and rc_buffer_size for the
+	 * implementation specific physical rate buffer size. Currently we use
+	 * the required rate buffer model size calculated in
+	 * drm_dsc_compute_rc_parameters() according to VESA DSC Annex E.
+	 *
+	 * The VBT rc_buffer_block_size and rc_buffer_size definitions
+	 * correspond to DP 1.4 DPCD offsets 0x62 and 0x63. The DP DSC
+	 * implementation should also use the DPCD (or perhaps VBT for eDP)
+	 * provided value for the buffer size.
+	 */
+
+	/* FIXME: DSI spec says bpc + 1 for this one */
+	vdsc_cfg->line_buf_depth = VBT_DSC_LINE_BUFFER_DEPTH(dsc->line_buffer_depth);
+
+	vdsc_cfg->block_pred_enable = dsc->block_prediction_enable;
+
+	vdsc_cfg->slice_height = dsc->slice_height;
+}
+
+/* FIXME: initially DSI specific */
+bool intel_bios_get_dsc_params(struct intel_encoder *encoder,
+			       struct intel_crtc_state *crtc_state,
+			       int dsc_max_bpc)
+{
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	const struct display_device_data *devdata;
+	const struct child_device_config *child;
+
+	list_for_each_entry(devdata, &i915->vbt.display_devices, node) {
+		child = &devdata->child;
+
+		if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT))
+			continue;
+
+		if (child->dvo_port - DVO_PORT_MIPIA == encoder->port) {
+			if (!devdata->dsc)
+				return false;
+
+			if (crtc_state)
+				fill_dsc(crtc_state, devdata->dsc, dsc_max_bpc);
+
+			return true;
+		}
+	}
+
+	return false;
+}
+
 /**
  * intel_bios_is_port_hpd_inverted - is HPD inverted for %port
  * @i915:	i915 device instance
diff --git a/drivers/gpu/drm/i915/display/intel_bios.h b/drivers/gpu/drm/i915/display/intel_bios.h
index 98f064828a57..d6a0c29d37ac 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.h
+++ b/drivers/gpu/drm/i915/display/intel_bios.h
@@ -35,6 +35,8 @@
 #include <drm/i915_drm.h>
 
 struct drm_i915_private;
+struct intel_crtc_state;
+struct intel_encoder;
 enum port;
 
 enum intel_backlight_type {
@@ -242,5 +244,8 @@ bool intel_bios_is_port_hpd_inverted(const struct drm_i915_private *i915,
 bool intel_bios_is_lspcon_present(const struct drm_i915_private *i915,
 				  enum port port);
 enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *dev_priv, enum port port);
+bool intel_bios_get_dsc_params(struct intel_encoder *encoder,
+			       struct intel_crtc_state *crtc_state,
+			       int dsc_max_bpc);
 
 #endif /* _INTEL_BIOS_H_ */
diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 22e83f857de8..b228671d5a5d 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -15,7 +15,7 @@ struct intel_qgv_point {
 };
 
 struct intel_qgv_info {
-	struct intel_qgv_point points[3];
+	struct intel_qgv_point points[I915_NUM_QGV_POINTS];
 	u8 num_points;
 	u8 num_channels;
 	u8 t_bl;
@@ -264,6 +264,9 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv,
 
 void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 {
+	if (!HAS_DISPLAY(dev_priv))
+		return;
+
 	if (IS_GEN(dev_priv, 12))
 		icl_get_bw_info(dev_priv, &tgl_sa_info);
 	else if (IS_GEN(dev_priv, 11))
@@ -273,17 +276,29 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 static unsigned int intel_max_data_rate(struct drm_i915_private *dev_priv,
 					int num_planes)
 {
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 11) {
+		/*
+		 * Any bw group has same amount of QGV points
+		 */
+		const struct intel_bw_info *bi =
+			&dev_priv->max_bw[0];
+		unsigned int min_bw = UINT_MAX;
+		int i;
+
 		/*
 		 * FIXME with SAGV disabled maybe we can assume
 		 * point 1 will always be used? Seems to match
 		 * the behaviour observed in the wild.
 		 */
-		return min3(icl_max_bw(dev_priv, num_planes, 0),
-			    icl_max_bw(dev_priv, num_planes, 1),
-			    icl_max_bw(dev_priv, num_planes, 2));
-	else
+		for (i = 0; i < bi->num_qgv_points; i++) {
+			unsigned int bw = icl_max_bw(dev_priv, num_planes, i);
+
+			min_bw = min(bw, min_bw);
+		}
+		return min_bw;
+	} else {
 		return UINT_MAX;
+	}
 }
 
 static unsigned int intel_bw_crtc_num_active_planes(const struct intel_crtc_state *crtc_state)
@@ -297,7 +312,7 @@ static unsigned int intel_bw_crtc_num_active_planes(const struct intel_crtc_stat
 
 static unsigned int intel_bw_crtc_data_rate(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	unsigned int data_rate = 0;
 	enum plane_id plane_id;
 
@@ -318,7 +333,7 @@ static unsigned int intel_bw_crtc_data_rate(const struct intel_crtc_state *crtc_
 void intel_bw_crtc_update(struct intel_bw_state *bw_state,
 			  const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	bw_state->data_rate[crtc->pipe] =
 		intel_bw_crtc_data_rate(crtc_state);
@@ -471,3 +486,8 @@ int intel_bw_init(struct drm_i915_private *dev_priv)
 
 	return 0;
 }
+
+void intel_bw_cleanup(struct drm_i915_private *dev_priv)
+{
+	drm_atomic_private_obj_fini(&dev_priv->bw_obj);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h
index 9db10af012f4..20b9ad241802 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.h
+++ b/drivers/gpu/drm/i915/display/intel_bw.h
@@ -25,6 +25,7 @@ struct intel_bw_state {
 
 void intel_bw_init_hw(struct drm_i915_private *dev_priv);
 int intel_bw_init(struct drm_i915_private *dev_priv);
+void intel_bw_cleanup(struct drm_i915_private *dev_priv);
 int intel_bw_atomic_check(struct intel_atomic_state *state);
 void intel_bw_crtc_update(struct intel_bw_state *bw_state,
 			  const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ed8c7ce62119..0ce5926006ca 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1904,7 +1904,7 @@ intel_set_cdclk_post_plane_update(struct drm_i915_private *dev_priv,
 
 static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int pixel_rate = crtc_state->pixel_rate;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -1922,7 +1922,7 @@ static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
 
 static int intel_planes_min_cdclk(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_plane *plane;
 	int min_cdclk = 0;
@@ -1936,10 +1936,10 @@ static int intel_planes_min_cdclk(const struct intel_crtc_state *crtc_state)
 int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
+		to_i915(crtc_state->uapi.crtc->dev);
 	int min_cdclk;
 
-	if (!crtc_state->base.enable)
+	if (!crtc_state->hw.enable)
 		return 0;
 
 	min_cdclk = intel_pixel_rate_to_cdclk(crtc_state);
@@ -2004,6 +2004,18 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	/* Account for additional needs from the planes */
 	min_cdclk = max(intel_planes_min_cdclk(crtc_state), min_cdclk);
 
+	/*
+	 * HACK. Currently for TGL platforms we calculate
+	 * min_cdclk initially based on pixel_rate divided
+	 * by 2, accounting for also plane requirements,
+	 * however in some cases the lowest possible CDCLK
+	 * doesn't work and causing the underruns.
+	 * Explicitly stating here that this seems to be currently
+	 * rather a Hack, than final solution.
+	 */
+	if (IS_TIGERLAKE(dev_priv))
+		min_cdclk = max(min_cdclk, (int)crtc_state->pixel_rate);
+
 	if (min_cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n",
 			      min_cdclk, dev_priv->max_cdclk_freq);
@@ -2076,7 +2088,7 @@ static int bxt_compute_min_voltage_level(struct intel_atomic_state *state)
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
 		int ret;
 
-		if (crtc_state->base.enable)
+		if (crtc_state->hw.enable)
 			min_voltage_level = crtc_state->min_voltage_level;
 		else
 			min_voltage_level = 0;
@@ -2170,7 +2182,7 @@ static int skl_dpll0_vco(struct intel_atomic_state *state)
 		vco = dev_priv->skl_preferred_vco_freq;
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		if (!crtc_state->base.enable)
+		if (!crtc_state->hw.enable)
 			continue;
 
 		if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
@@ -2283,11 +2295,11 @@ static int intel_modeset_all_pipes(struct intel_atomic_state *state)
 		if (IS_ERR(crtc_state))
 			return PTR_ERR(crtc_state);
 
-		if (!crtc_state->base.active ||
-		    drm_atomic_crtc_needs_modeset(&crtc_state->base))
+		if (!crtc_state->hw.active ||
+		    drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
 			continue;
 
-		crtc_state->base.mode_changed = true;
+		crtc_state->uapi.mode_changed = true;
 
 		ret = drm_atomic_add_affected_connectors(&state->base,
 							 &crtc->base);
@@ -2368,7 +2380,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 		if (IS_ERR(crtc_state))
 			return PTR_ERR(crtc_state);
 
-		if (drm_atomic_crtc_needs_modeset(&crtc_state->base))
+		if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
 			pipe = INVALID_PIPE;
 	} else {
 		pipe = INVALID_PIPE;
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index aa3a063549c3..3980e8b50c28 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -117,10 +117,10 @@ static bool lut_is_legacy(const struct drm_property_blob *lut)
 
 static bool crtc_state_is_legacy_gamma(const struct intel_crtc_state *crtc_state)
 {
-	return !crtc_state->base.degamma_lut &&
-		!crtc_state->base.ctm &&
-		crtc_state->base.gamma_lut &&
-		lut_is_legacy(crtc_state->base.gamma_lut);
+	return !crtc_state->hw.degamma_lut &&
+		!crtc_state->hw.ctm &&
+		crtc_state->hw.gamma_lut &&
+		lut_is_legacy(crtc_state->hw.gamma_lut);
 }
 
 /*
@@ -205,7 +205,7 @@ static void icl_update_output_csc(struct intel_crtc *crtc,
 
 static bool ilk_csc_limited_range(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	/*
 	 * FIXME if there's a gamma LUT after the CSC, we should
@@ -219,7 +219,7 @@ static bool ilk_csc_limited_range(const struct intel_crtc_state *crtc_state)
 static void ilk_csc_convert_ctm(const struct intel_crtc_state *crtc_state,
 				u16 coeffs[9])
 {
-	const struct drm_color_ctm *ctm = crtc_state->base.ctm->data;
+	const struct drm_color_ctm *ctm = crtc_state->hw.ctm->data;
 	const u64 *input;
 	u64 temp[9];
 	int i;
@@ -270,11 +270,11 @@ static void ilk_csc_convert_ctm(const struct intel_crtc_state *crtc_state,
 
 static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	bool limited_color_range = ilk_csc_limited_range(crtc_state);
 
-	if (crtc_state->base.ctm) {
+	if (crtc_state->hw.ctm) {
 		u16 coeff[9];
 
 		ilk_csc_convert_ctm(crtc_state, coeff);
@@ -309,10 +309,10 @@ static void ilk_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 
 static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	if (crtc_state->base.ctm) {
+	if (crtc_state->hw.ctm) {
 		u16 coeff[9];
 
 		ilk_csc_convert_ctm(crtc_state, coeff);
@@ -338,12 +338,12 @@ static void icl_load_csc_matrix(const struct intel_crtc_state *crtc_state)
  */
 static void cherryview_load_csc_matrix(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	if (crtc_state->base.ctm) {
-		const struct drm_color_ctm *ctm = crtc_state->base.ctm->data;
+	if (crtc_state->hw.ctm) {
+		const struct drm_color_ctm *ctm = crtc_state->hw.ctm->data;
 		u16 coeffs[9] = {};
 		int i;
 
@@ -404,7 +404,7 @@ static u32 ilk_lut_10(const struct drm_color_lut *color)
 static void i9xx_load_luts_internal(const struct intel_crtc_state *crtc_state,
 				    const struct drm_property_blob *blob)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	int i;
@@ -435,12 +435,12 @@ static void i9xx_load_luts_internal(const struct intel_crtc_state *crtc_state,
 
 static void i9xx_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	i9xx_load_luts_internal(crtc_state, crtc_state->base.gamma_lut);
+	i9xx_load_luts_internal(crtc_state, crtc_state->hw.gamma_lut);
 }
 
 static void i9xx_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -453,7 +453,7 @@ static void i9xx_color_commit(const struct intel_crtc_state *crtc_state)
 
 static void ilk_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -468,7 +468,7 @@ static void ilk_color_commit(const struct intel_crtc_state *crtc_state)
 
 static void hsw_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	I915_WRITE(GAMMA_MODE(crtc->pipe), crtc_state->gamma_mode);
@@ -478,7 +478,7 @@ static void hsw_color_commit(const struct intel_crtc_state *crtc_state)
 
 static void skl_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val = 0;
@@ -524,8 +524,8 @@ static void i965_load_lut_10p6(struct intel_crtc *crtc,
 
 static void i965_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		i9xx_load_luts(crtc_state);
@@ -547,8 +547,8 @@ static void ilk_load_lut_10(struct intel_crtc *crtc,
 
 static void ilk_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		i9xx_load_luts(crtc_state);
@@ -654,9 +654,9 @@ static void ivb_load_lut_ext_max(struct intel_crtc *crtc)
 
 static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT) {
 		i9xx_load_luts(crtc_state);
@@ -677,9 +677,9 @@ static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
 
 static void bdw_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT) {
 		i9xx_load_luts(crtc_state);
@@ -700,11 +700,11 @@ static void bdw_load_luts(const struct intel_crtc_state *crtc_state)
 
 static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	const u32 lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
-	const struct drm_color_lut *lut = crtc_state->base.degamma_lut->data;
+	const struct drm_color_lut *lut = crtc_state->hw.degamma_lut->data;
 	u32 i;
 
 	/*
@@ -739,7 +739,7 @@ static void glk_load_degamma_lut(const struct intel_crtc_state *crtc_state)
 
 static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	const u32 lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size;
@@ -766,8 +766,8 @@ static void glk_load_degamma_lut_linear(const struct intel_crtc_state *crtc_stat
 
 static void glk_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	/*
 	 * On GLK+ both pipe CSC and degamma LUT are controlled
@@ -777,7 +777,7 @@ static void glk_load_luts(const struct intel_crtc_state *crtc_state)
 	 * the degama LUT so that we don't have to reload
 	 * it every time the pipe CSC is being enabled.
 	 */
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		glk_load_degamma_lut(crtc_state);
 	else
 		glk_load_degamma_lut_linear(crtc_state);
@@ -808,7 +808,7 @@ static void
 icl_load_gcmax(const struct intel_crtc_state *crtc_state,
 	       const struct drm_color_lut *color)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
 
@@ -822,8 +822,8 @@ icl_load_gcmax(const struct intel_crtc_state *crtc_state,
 static void
 icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *blob = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *blob = crtc_state->hw.gamma_lut;
 	const struct drm_color_lut *lut = blob->data;
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
@@ -854,8 +854,8 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 static void
 icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *blob = crtc_state->base.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *blob = crtc_state->hw.gamma_lut;
 	const struct drm_color_lut *lut = blob->data;
 	const struct drm_color_lut *entry;
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
@@ -910,11 +910,11 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 
 static void icl_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_dsb *dsb = intel_dsb_get(crtc);
 
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		glk_load_degamma_lut(crtc_state);
 
 	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
@@ -990,9 +990,9 @@ static void chv_load_cgm_gamma(struct intel_crtc *crtc,
 
 static void chv_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 
 	cherryview_load_csc_matrix(crtc_state);
 
@@ -1010,35 +1010,35 @@ static void chv_load_luts(const struct intel_crtc_state *crtc_state)
 
 void intel_color_load_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	dev_priv->display.load_luts(crtc_state);
 }
 
 void intel_color_commit(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	dev_priv->display.color_commit(crtc_state);
 }
 
 static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
-	return !old_crtc_state->base.gamma_lut &&
-		!old_crtc_state->base.degamma_lut;
+	return !old_crtc_state->hw.gamma_lut &&
+		!old_crtc_state->hw.degamma_lut;
 }
 
 static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
@@ -1050,14 +1050,14 @@ static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 	if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode)
 		return false;
 
-	return !old_crtc_state->base.gamma_lut;
+	return !old_crtc_state->hw.gamma_lut;
 }
 
 static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
@@ -1068,19 +1068,19 @@ static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
 	 * linear hardware degamma mid scanout.
 	 */
 	return !old_crtc_state->csc_enable &&
-		!old_crtc_state->base.gamma_lut;
+		!old_crtc_state->hw.gamma_lut;
 }
 
 int intel_color_check(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	return dev_priv->display.color_check(crtc_state);
 }
 
 void intel_color_get_config(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (dev_priv->display.read_luts)
 		dev_priv->display.read_luts(crtc_state);
@@ -1104,16 +1104,16 @@ static bool need_plane_update(struct intel_plane *plane,
 static int
 intel_color_add_affected_planes(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 	struct intel_plane *plane;
 
-	if (!new_crtc_state->base.active ||
-	    drm_atomic_crtc_needs_modeset(&new_crtc_state->base))
+	if (!new_crtc_state->hw.active ||
+	    drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi))
 		return 0;
 
 	if (new_crtc_state->gamma_enable == old_crtc_state->gamma_enable &&
@@ -1155,9 +1155,9 @@ static int check_lut_size(const struct drm_property_blob *lut, int expected)
 
 static int check_luts(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
-	const struct drm_property_blob *degamma_lut = crtc_state->base.degamma_lut;
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	const struct drm_property_blob *gamma_lut = crtc_state->hw.gamma_lut;
+	const struct drm_property_blob *degamma_lut = crtc_state->hw.degamma_lut;
 	int gamma_length, degamma_length;
 	u32 gamma_tests, degamma_tests;
 
@@ -1205,7 +1205,7 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		crtc_state->base.gamma_lut &&
+		crtc_state->hw.gamma_lut &&
 		!crtc_state->c8_planes;
 
 	crtc_state->gamma_mode = i9xx_gamma_mode(crtc_state);
@@ -1226,11 +1226,11 @@ static u32 chv_cgm_mode(const struct intel_crtc_state *crtc_state)
 	if (crtc_state_is_legacy_gamma(crtc_state))
 		return 0;
 
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		cgm_mode |= CGM_PIPE_MODE_DEGAMMA;
-	if (crtc_state->base.ctm)
+	if (crtc_state->hw.ctm)
 		cgm_mode |= CGM_PIPE_MODE_CSC;
-	if (crtc_state->base.gamma_lut)
+	if (crtc_state->hw.gamma_lut)
 		cgm_mode |= CGM_PIPE_MODE_GAMMA;
 
 	return cgm_mode;
@@ -1306,7 +1306,7 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		crtc_state->base.gamma_lut &&
+		crtc_state->hw.gamma_lut &&
 		!crtc_state->c8_planes;
 
 	/*
@@ -1334,8 +1334,8 @@ static u32 ivb_gamma_mode(const struct intel_crtc_state *crtc_state)
 	if (!crtc_state->gamma_enable ||
 	    crtc_state_is_legacy_gamma(crtc_state))
 		return GAMMA_MODE_MODE_8BIT;
-	else if (crtc_state->base.gamma_lut &&
-		 crtc_state->base.degamma_lut)
+	else if (crtc_state->hw.gamma_lut &&
+		 crtc_state->hw.degamma_lut)
 		return GAMMA_MODE_MODE_SPLIT;
 	else
 		return GAMMA_MODE_MODE_10BIT;
@@ -1349,7 +1349,7 @@ static u32 ivb_csc_mode(const struct intel_crtc_state *crtc_state)
 	 * CSC comes after the LUT in degamma, RGB->YCbCr,
 	 * and RGB full->limited range mode.
 	 */
-	if (crtc_state->base.degamma_lut ||
+	if (crtc_state->hw.degamma_lut ||
 	    crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
 	    limited_color_range)
 		return 0;
@@ -1367,13 +1367,13 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		(crtc_state->base.gamma_lut ||
-		 crtc_state->base.degamma_lut) &&
+		(crtc_state->hw.gamma_lut ||
+		 crtc_state->hw.degamma_lut) &&
 		!crtc_state->c8_planes;
 
 	crtc_state->csc_enable =
 		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
-		crtc_state->base.ctm || limited_color_range;
+		crtc_state->hw.ctm || limited_color_range;
 
 	crtc_state->gamma_mode = ivb_gamma_mode(crtc_state);
 
@@ -1406,14 +1406,14 @@ static int glk_color_check(struct intel_crtc_state *crtc_state)
 		return ret;
 
 	crtc_state->gamma_enable =
-		crtc_state->base.gamma_lut &&
+		crtc_state->hw.gamma_lut &&
 		!crtc_state->c8_planes;
 
 	/* On GLK+ degamma LUT is controlled by csc_enable */
 	crtc_state->csc_enable =
-		crtc_state->base.degamma_lut ||
+		crtc_state->hw.degamma_lut ||
 		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
-		crtc_state->base.ctm || crtc_state->limited_color_range;
+		crtc_state->hw.ctm || crtc_state->limited_color_range;
 
 	crtc_state->gamma_mode = glk_gamma_mode(crtc_state);
 
@@ -1432,14 +1432,14 @@ static u32 icl_gamma_mode(const struct intel_crtc_state *crtc_state)
 {
 	u32 gamma_mode = 0;
 
-	if (crtc_state->base.degamma_lut)
+	if (crtc_state->hw.degamma_lut)
 		gamma_mode |= PRE_CSC_GAMMA_ENABLE;
 
-	if (crtc_state->base.gamma_lut &&
+	if (crtc_state->hw.gamma_lut &&
 	    !crtc_state->c8_planes)
 		gamma_mode |= POST_CSC_GAMMA_ENABLE;
 
-	if (!crtc_state->base.gamma_lut ||
+	if (!crtc_state->hw.gamma_lut ||
 	    crtc_state_is_legacy_gamma(crtc_state))
 		gamma_mode |= GAMMA_MODE_MODE_8BIT;
 	else
@@ -1452,7 +1452,7 @@ static u32 icl_csc_mode(const struct intel_crtc_state *crtc_state)
 {
 	u32 csc_mode = 0;
 
-	if (crtc_state->base.ctm)
+	if (crtc_state->hw.ctm)
 		csc_mode |= ICL_CSC_ENABLE;
 
 	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB ||
@@ -1540,7 +1540,7 @@ static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (HAS_GMCH(dev_priv)) {
@@ -1646,7 +1646,7 @@ static u32 intel_color_lut_pack(u32 val, u32 bit_precision)
 static struct drm_property_blob *
 i9xx_read_lut_8(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	struct drm_property_blob *blob;
@@ -1683,13 +1683,13 @@ static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
 	if (!crtc_state->gamma_enable)
 		return;
 
-	crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 }
 
 static struct drm_property_blob *
 i965_read_lut_10p6(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
 	enum pipe pipe = crtc->pipe;
@@ -1733,15 +1733,15 @@ static void i965_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-		crtc_state->base.gamma_lut = i965_read_lut_10p6(crtc_state);
+		crtc_state->hw.gamma_lut = i965_read_lut_10p6(crtc_state);
 }
 
 static struct drm_property_blob *
 chv_read_cgm_lut(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
 	enum pipe pipe = crtc->pipe;
@@ -1775,7 +1775,7 @@ chv_read_cgm_lut(const struct intel_crtc_state *crtc_state)
 static void chv_read_luts(struct intel_crtc_state *crtc_state)
 {
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
-		crtc_state->base.gamma_lut = chv_read_cgm_lut(crtc_state);
+		crtc_state->hw.gamma_lut = chv_read_cgm_lut(crtc_state);
 	else
 		i965_read_luts(crtc_state);
 }
@@ -1783,7 +1783,7 @@ static void chv_read_luts(struct intel_crtc_state *crtc_state)
 static struct drm_property_blob *
 ilk_read_lut_10(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
 	enum pipe pipe = crtc->pipe;
@@ -1822,15 +1822,15 @@ static void ilk_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-		crtc_state->base.gamma_lut = ilk_read_lut_10(crtc_state);
+		crtc_state->hw.gamma_lut = ilk_read_lut_10(crtc_state);
 }
 
 static struct drm_property_blob *
 glk_read_lut_10(const struct intel_crtc_state *crtc_state, u32 prec_index)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	int hw_lut_size = ivb_lut_10_size(prec_index);
 	enum pipe pipe = crtc->pipe;
@@ -1871,9 +1871,9 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state)
 		return;
 
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+		crtc_state->hw.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
+		crtc_state->hw.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
 }
 
 void intel_color_init(struct intel_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index 39cc6d79dc85..f976b800b245 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -65,7 +65,7 @@ static struct intel_crt *intel_encoder_to_crt(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_crt, base);
 }
 
-static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
+static struct intel_crt *intel_attached_crt(struct intel_connector *connector)
 {
 	return intel_encoder_to_crt(intel_attached_encoder(connector));
 }
@@ -132,9 +132,9 @@ static void intel_crt_get_config(struct intel_encoder *encoder,
 {
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_ANALOG);
 
-	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
+	pipe_config->hw.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 
-	pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock;
+	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
 static void hsw_crt_get_config(struct intel_encoder *encoder,
@@ -144,13 +144,13 @@ static void hsw_crt_get_config(struct intel_encoder *encoder,
 
 	intel_ddi_get_config(encoder, pipe_config);
 
-	pipe_config->base.adjusted_mode.flags &= ~(DRM_MODE_FLAG_PHSYNC |
+	pipe_config->hw.adjusted_mode.flags &= ~(DRM_MODE_FLAG_PHSYNC |
 					      DRM_MODE_FLAG_NHSYNC |
 					      DRM_MODE_FLAG_PVSYNC |
 					      DRM_MODE_FLAG_NVSYNC);
-	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
+	pipe_config->hw.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 
-	pipe_config->base.adjusted_mode.crtc_clock = lpt_get_iclkip(dev_priv);
+	pipe_config->hw.adjusted_mode.crtc_clock = lpt_get_iclkip(dev_priv);
 }
 
 /* Note: The caller is required to filter out dpms modes not supported by the
@@ -161,8 +161,8 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 adpa;
 
 	if (INTEL_GEN(dev_priv) >= 5)
@@ -241,6 +241,14 @@ static void hsw_post_disable_crt(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
+	intel_crtc_vblank_off(old_crtc_state);
+
+	intel_disable_pipe(old_crtc_state);
+
+	intel_ddi_disable_transcoder_func(old_crtc_state);
+
+	ilk_pfit_disable(old_crtc_state);
+
 	intel_ddi_disable_pipe_clock(old_crtc_state);
 
 	pch_post_disable_crt(encoder, old_crtc_state, old_conn_state);
@@ -271,14 +279,14 @@ static void hsw_pre_enable_crt(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 
 	WARN_ON(!crtc_state->has_pch_encoder);
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 
-	dev_priv->display.fdi_link_train(crtc, crtc_state);
+	hsw_fdi_link_train(encoder, crtc_state);
 
 	intel_ddi_enable_pipe_clock(crtc_state);
 }
@@ -288,7 +296,7 @@ static void hsw_enable_crt(struct intel_encoder *encoder,
 			   const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 
 	WARN_ON(!crtc_state->has_pch_encoder);
@@ -343,7 +351,7 @@ intel_crt_mode_valid(struct drm_connector *connector,
 
 	/* The FDI receiver on LPT only supports 8bpc and only has 2 lanes. */
 	if (HAS_PCH_LPT(dev_priv) &&
-	    (ironlake_get_lanes_required(mode->clock, 270000, 24) > 2))
+	    ilk_get_lanes_required(mode->clock, 270000, 24) > 2)
 		return MODE_CLOCK_HIGH;
 
 	/* HSW/BDW FDI limited to 4k */
@@ -358,7 +366,7 @@ static int intel_crt_compute_config(struct intel_encoder *encoder,
 				    struct drm_connector_state *conn_state)
 {
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -373,7 +381,7 @@ static int pch_crt_compute_config(struct intel_encoder *encoder,
 				  struct drm_connector_state *conn_state)
 {
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -390,7 +398,7 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -419,10 +427,10 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder,
 	return 0;
 }
 
-static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
+static bool ilk_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 adpa;
 	bool ret;
@@ -432,7 +440,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 		bool turn_off_dac = HAS_PCH_SPLIT(dev_priv);
 		u32 save_adpa;
 
-		crt->force_hotplug_required = 0;
+		crt->force_hotplug_required = false;
 
 		save_adpa = adpa = I915_READ(crt->adpa_reg);
 		DRM_DEBUG_KMS("trigger hotplug detect cycle: adpa=0x%x\n", adpa);
@@ -469,7 +477,7 @@ static bool intel_ironlake_crt_detect_hotplug(struct drm_connector *connector)
 static bool valleyview_crt_detect_hotplug(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	bool reenable_hpd;
 	u32 adpa;
@@ -527,7 +535,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 	int i, tries = 0;
 
 	if (HAS_PCH_SPLIT(dev_priv))
-		return intel_ironlake_crt_detect_hotplug(connector);
+		return ilk_crt_detect_hotplug(connector);
 
 	if (IS_VALLEYVIEW(dev_priv))
 		return valleyview_crt_detect_hotplug(connector);
@@ -601,7 +609,7 @@ static int intel_crt_ddc_get_modes(struct drm_connector *connector,
 
 static bool intel_crt_detect_ddc(struct drm_connector *connector)
 {
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev);
 	struct edid *edid;
 	struct i2c_adapter *i2c;
@@ -787,7 +795,7 @@ intel_crt_detect(struct drm_connector *connector,
 		 bool force)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct intel_encoder *intel_encoder = &crt->base;
 	intel_wakeref_t wakeref;
 	int status, ret;
@@ -878,7 +886,7 @@ static int intel_crt_get_modes(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crt *crt = intel_attached_crt(connector);
+	struct intel_crt *crt = intel_attached_crt(to_intel_connector(connector));
 	struct intel_encoder *intel_encoder = &crt->base;
 	intel_wakeref_t wakeref;
 	struct i2c_adapter *i2c;
@@ -917,7 +925,7 @@ void intel_crt_reset(struct drm_encoder *encoder)
 		POSTING_READ(crt->adpa_reg);
 
 		DRM_DEBUG_KMS("crt adpa set to 0x%x\n", adpa);
-		crt->force_hotplug_required = 1;
+		crt->force_hotplug_required = true;
 	}
 
 }
@@ -1055,7 +1063,7 @@ void intel_crt_init(struct drm_i915_private *dev_priv)
 	/*
 	 * Configure the automatic hotplug detection stuff
 	 */
-	crt->force_hotplug_required = 0;
+	crt->force_hotplug_required = false;
 
 	/*
 	 * TODO: find a proper way to discover whether we need to set the the
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2a27fb5d7dc6..33f1dc3d7c1a 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -34,6 +34,7 @@
 #include "intel_ddi.h"
 #include "intel_display_types.h"
 #include "intel_dp.h"
+#include "intel_dp_mst.h"
 #include "intel_dp_link_training.h"
 #include "intel_dpio_phy.h"
 #include "intel_dsi.h"
@@ -902,11 +903,10 @@ icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, int type, int rate,
 
 static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port)
 {
+	struct ddi_vbt_port_info *port_info = &dev_priv->vbt.ddi_port_info[port];
 	int n_entries, level, default_entry;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
-	level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
-
 	if (INTEL_GEN(dev_priv) >= 12) {
 		if (intel_phy_is_combo(dev_priv, phy))
 			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
@@ -941,12 +941,14 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 		return 0;
 	}
 
-	/* Choose a good default if VBT is badly populated */
-	if (level == HDMI_LEVEL_SHIFT_UNKNOWN || level >= n_entries)
-		level = default_entry;
-
 	if (WARN_ON_ONCE(n_entries == 0))
 		return 0;
+
+	if (port_info->hdmi_level_shift_set)
+		level = port_info->hdmi_level_shift;
+	else
+		level = default_entry;
+
 	if (WARN_ON_ONCE(level >= n_entries))
 		level = n_entries - 1;
 
@@ -1106,18 +1108,14 @@ static u32 icl_pll_to_ddi_clk_sel(struct intel_encoder *encoder,
  * DDI A (which is used for eDP)
  */
 
-void hsw_fdi_link_train(struct intel_crtc *crtc,
+void hsw_fdi_link_train(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_encoder *encoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 temp, i, rx_ctl_val, ddi_pll_sel;
 
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
-		WARN_ON(encoder->type != INTEL_OUTPUT_ANALOG);
-		intel_prepare_dp_ddi_buffers(encoder, crtc_state);
-	}
+	intel_prepare_dp_ddi_buffers(encoder, crtc_state);
 
 	/* Set the FDI_RX_MISC pwrdn lanes and the 2 workarounds listed at the
 	 * mode set "sequence for CRT port" document:
@@ -1240,9 +1238,9 @@ void hsw_fdi_link_train(struct intel_crtc *crtc,
 
 static void intel_ddi_init_dp_buf_reg(struct intel_encoder *encoder)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *intel_dig_port =
-		enc_to_dig_port(&encoder->base);
+		enc_to_dig_port(encoder);
 
 	intel_dp->DP = intel_dig_port->saved_port_bits |
 		DDI_BUF_CTL_ENABLE | DDI_BUF_TRANS_SELECT(0);
@@ -1542,7 +1540,7 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config)
 	if (pipe_config->pixel_multiplier)
 		dotclock /= pipe_config->pixel_multiplier;
 
-	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+	pipe_config->hw.adjusted_mode.crtc_clock = dotclock;
 }
 
 static void icl_ddi_clock_get(struct intel_encoder *encoder,
@@ -1758,7 +1756,7 @@ static void intel_ddi_clock_get(struct intel_encoder *encoder,
 void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 			  const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 temp;
@@ -1815,22 +1813,6 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	I915_WRITE(TRANS_MSA_MISC(cpu_transcoder), temp);
 }
 
-void intel_ddi_set_vc_payload_alloc(const struct intel_crtc_state *crtc_state,
-				    bool state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	u32 temp;
-
-	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
-	if (state == true)
-		temp |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
-	else
-		temp &= ~TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
-	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
-}
-
 /*
  * Returns the TRANS_DDI_FUNC_CTL value based on CRTC state.
  *
@@ -1840,7 +1822,7 @@ void intel_ddi_set_vc_payload_alloc(const struct intel_crtc_state *crtc_state,
 static u32
 intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
@@ -1872,9 +1854,9 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 		BUG();
 	}
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_PVSYNC)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_PVSYNC)
 		temp |= TRANS_DDI_PVSYNC;
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_PHSYNC)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_PHSYNC)
 		temp |= TRANS_DDI_PHSYNC;
 
 	if (cpu_transcoder == TRANSCODER_EDP) {
@@ -1918,8 +1900,13 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 		temp |= TRANS_DDI_MODE_SELECT_DP_MST;
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
 
-		if (INTEL_GEN(dev_priv) >= 12)
-			temp |= TRANS_DDI_MST_TRANSPORT_SELECT(crtc_state->cpu_transcoder);
+		if (INTEL_GEN(dev_priv) >= 12) {
+			enum transcoder master;
+
+			master = crtc_state->mst_master_transcoder;
+			WARN_ON(master == INVALID_TRANSCODER);
+			temp |= TRANS_DDI_MST_TRANSPORT_SELECT(master);
+		}
 	} else {
 		temp |= TRANS_DDI_MODE_SELECT_DP_SST;
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
@@ -1930,12 +1917,14 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 
 void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 temp;
 
 	temp = intel_ddi_transcoder_func_reg_val_get(crtc_state);
+	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
+		temp |= TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
@@ -1946,7 +1935,7 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 static void
 intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 temp;
@@ -1958,20 +1947,21 @@ intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state)
 
 void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
-	u32 val = I915_READ(reg);
+	u32 val;
+
+	val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+	val &= ~TRANS_DDI_FUNC_ENABLE;
 
 	if (INTEL_GEN(dev_priv) >= 12) {
-		val &= ~(TRANS_DDI_FUNC_ENABLE | TGL_TRANS_DDI_PORT_MASK |
-			 TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
+		if (!intel_dp_mst_is_master_trans(crtc_state))
+			val &= ~TGL_TRANS_DDI_PORT_MASK;
 	} else {
-		val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK |
-			 TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
+		val &= ~TRANS_DDI_PORT_MASK;
 	}
-	I915_WRITE(reg, val);
+	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), val);
 
 	if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
 	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
@@ -2234,7 +2224,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
 		return;
 
-	dig_port = enc_to_dig_port(&encoder->base);
+	dig_port = enc_to_dig_port(encoder);
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	/*
@@ -2256,7 +2246,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
 	enum port port = encoder->port;
@@ -2274,7 +2264,7 @@ void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
 
 void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
 	if (cpu_transcoder != TRANSCODER_EDP) {
@@ -2304,7 +2294,7 @@ static void _skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
 static void skl_ddi_set_iboost(struct intel_encoder *encoder,
 			       int level, enum intel_output_type type)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	u8 iboost;
@@ -2375,7 +2365,7 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder,
 u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 	int n_entries;
@@ -2514,7 +2504,7 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder,
 		width = 4;
 		rate = 0; /* Rate is always < than 6GHz for HDMI */
 	} else {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		width = intel_dp->lane_count;
 		rate = intel_dp->link_rate;
@@ -2640,7 +2630,7 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 		width = 4;
 		/* Rate is always < than 6GHz for HDMI */
 	} else {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		width = intel_dp->lane_count;
 		rate = intel_dp->link_rate;
@@ -3016,11 +3006,38 @@ static void icl_unmap_plls_to_ports(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpll_lock);
 }
 
+static void icl_sanitize_port_clk_off(struct drm_i915_private *dev_priv,
+				      u32 port_mask, bool ddi_clk_needed)
+{
+	enum port port;
+	u32 val;
+
+	val = I915_READ(ICL_DPCLKA_CFGCR0);
+	for_each_port_masked(port, port_mask) {
+		enum phy phy = intel_port_to_phy(dev_priv, port);
+		bool ddi_clk_off = val & icl_dpclka_cfgcr0_clk_off(dev_priv,
+								   phy);
+
+		if (ddi_clk_needed == !ddi_clk_off)
+			continue;
+
+		/*
+		 * Punt on the case now where clock is gated, but it would
+		 * be needed by the port. Something else is really broken then.
+		 */
+		if (WARN_ON(ddi_clk_needed))
+			continue;
+
+		DRM_NOTE("PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n",
+			 phy_name(phy));
+		val |= icl_dpclka_cfgcr0_clk_off(dev_priv, phy);
+		I915_WRITE(ICL_DPCLKA_CFGCR0, val);
+	}
+}
+
 void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 val;
-	enum port port;
 	u32 port_mask;
 	bool ddi_clk_needed;
 
@@ -3069,29 +3086,7 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 		ddi_clk_needed = false;
 	}
 
-	val = I915_READ(ICL_DPCLKA_CFGCR0);
-	for_each_port_masked(port, port_mask) {
-		enum phy phy = intel_port_to_phy(dev_priv, port);
-
-		bool ddi_clk_ungated = !(val &
-					 icl_dpclka_cfgcr0_clk_off(dev_priv,
-								   phy));
-
-		if (ddi_clk_needed == ddi_clk_ungated)
-			continue;
-
-		/*
-		 * Punt on the case now where clock is gated, but it would
-		 * be needed by the port. Something else is really broken then.
-		 */
-		if (WARN_ON(ddi_clk_needed))
-			continue;
-
-		DRM_NOTE("PHY %c is disabled/in DSI mode with an ungated DDI clock, gate it\n",
-			 phy_name(port));
-		val |= icl_dpclka_cfgcr0_clk_off(dev_priv, phy);
-		I915_WRITE(ICL_DPCLKA_CFGCR0, val);
-	}
+	icl_sanitize_port_clk_off(dev_priv, port_mask, ddi_clk_needed);
 }
 
 static void intel_ddi_clk_select(struct intel_encoder *encoder,
@@ -3173,57 +3168,6 @@ static void intel_ddi_clk_disable(struct intel_encoder *encoder)
 }
 
 static void
-icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
-{
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(dev_priv, dig_port->base.port);
-	u32 val, bits;
-	int ln;
-
-	if (tc_port == PORT_TC_NONE)
-		return;
-
-	bits = MG_DP_MODE_CFG_TR2PWR_GATING | MG_DP_MODE_CFG_TRPWR_GATING |
-	       MG_DP_MODE_CFG_CLNPWR_GATING | MG_DP_MODE_CFG_DIGPWR_GATING |
-	       MG_DP_MODE_CFG_GAONPWR_GATING;
-
-	for (ln = 0; ln < 2; ln++) {
-		if (INTEL_GEN(dev_priv) >= 12) {
-			I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
-			val = I915_READ(DKL_DP_MODE(tc_port));
-		} else {
-			val = I915_READ(MG_DP_MODE(ln, tc_port));
-		}
-
-		if (enable)
-			val |= bits;
-		else
-			val &= ~bits;
-
-		if (INTEL_GEN(dev_priv) >= 12)
-			I915_WRITE(DKL_DP_MODE(tc_port), val);
-		else
-			I915_WRITE(MG_DP_MODE(ln, tc_port), val);
-	}
-
-	if (INTEL_GEN(dev_priv) == 11) {
-		bits = MG_MISC_SUS0_CFG_TR2PWR_GATING |
-		       MG_MISC_SUS0_CFG_CL2PWR_GATING |
-		       MG_MISC_SUS0_CFG_GAONPWR_GATING |
-		       MG_MISC_SUS0_CFG_TRPWR_GATING |
-		       MG_MISC_SUS0_CFG_CL1PWR_GATING |
-		       MG_MISC_SUS0_CFG_DGPWR_GATING;
-
-		val = I915_READ(MG_MISC_SUS0(tc_port));
-		if (enable)
-			val |= (bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(3));
-		else
-			val &= ~(bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK);
-		I915_WRITE(MG_MISC_SUS0(tc_port), val);
-	}
-}
-
-static void
 icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		       const struct intel_crtc_state *crtc_state)
 {
@@ -3329,7 +3273,7 @@ static void intel_ddi_enable_fec(struct intel_encoder *encoder,
 	if (!crtc_state->fec_enable)
 		return;
 
-	intel_dp = enc_to_intel_dp(&encoder->base);
+	intel_dp = enc_to_intel_dp(encoder);
 	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val |= DP_TP_CTL_FEC_ENABLE;
 	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
@@ -3349,7 +3293,7 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 	if (!crtc_state->fec_enable)
 		return;
 
-	intel_dp = enc_to_intel_dp(&encoder->base);
+	intel_dp = enc_to_intel_dp(encoder);
 	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val &= ~DP_TP_CTL_FEC_ENABLE;
 	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
@@ -3359,7 +3303,7 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 static void
 tgl_clear_psr2_transcoder_exitline(const struct intel_crtc_state *cstate)
 {
-	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(cstate->uapi.crtc->dev);
 	u32 val;
 
 	if (!cstate->dc3co_exitline)
@@ -3374,7 +3318,7 @@ static void
 tgl_set_psr2_transcoder_exitline(const struct intel_crtc_state *cstate)
 {
 	u32 val, exit_scanlines;
-	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(cstate->uapi.crtc->dev);
 
 	if (!cstate->dc3co_exitline)
 		return;
@@ -3392,8 +3336,8 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 					      struct intel_crtc_state *cstate)
 {
 	u32 exit_scanlines;
-	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
-	u32 crtc_vdisplay = cstate->base.adjusted_mode.crtc_vdisplay;
+	struct drm_i915_private *dev_priv = to_i915(cstate->uapi.crtc->dev);
+	u32 crtc_vdisplay = cstate->hw.adjusted_mode.crtc_vdisplay;
 
 	cstate->dc3co_exitline = 0;
 
@@ -3401,11 +3345,11 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 		return;
 
 	/* B.Specs:49196 DC3CO only works with pipeA and DDIA.*/
-	if (to_intel_crtc(cstate->base.crtc)->pipe != PIPE_A ||
+	if (to_intel_crtc(cstate->uapi.crtc)->pipe != PIPE_A ||
 	    encoder->port != PORT_A)
 		return;
 
-	if (!cstate->has_psr2 || !cstate->base.active)
+	if (!cstate->has_psr2 || !cstate->hw.active)
 		return;
 
 	/*
@@ -3413,7 +3357,7 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 	 * PSR2 transcoder Early Exit scanlines = ROUNDUP(200 / line time) + 1
 	 */
 	exit_scanlines =
-		intel_usecs_to_scanlines(&cstate->base.adjusted_mode, 200) + 1;
+		intel_usecs_to_scanlines(&cstate->hw.adjusted_mode, 200) + 1;
 
 	if (WARN_ON(exit_scanlines > crtc_vdisplay))
 		return;
@@ -3425,7 +3369,7 @@ static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
 static void tgl_dc3co_exitline_get_config(struct intel_crtc_state *crtc_state)
 {
 	u32 val;
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (INTEL_GEN(dev_priv) < 12)
 		return;
@@ -3440,10 +3384,10 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	int level = intel_ddi_dp_level(intel_dp);
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
@@ -3455,47 +3399,80 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp->regs.dp_tp_ctl = TGL_DP_TP_CTL(transcoder);
 	intel_dp->regs.dp_tp_status = TGL_DP_TP_STATUS(transcoder);
 
-	/* 1.a got on intel_atomic_commit_tail() */
+	/*
+	 * 1. Enable Power Wells
+	 *
+	 * This was handled at the beginning of intel_atomic_commit_tail(),
+	 * before we called down into this function.
+	 */
 
-	/* 2. */
+	/* 2. Enable Panel Power if PPS is required */
 	intel_edp_panel_on(intel_dp);
 
 	/*
-	 * 1.b, 3. and 4.a is done before tgl_ddi_pre_enable_dp() by:
-	 * haswell_crtc_enable()->intel_encoders_pre_pll_enable() and
-	 * haswell_crtc_enable()->intel_enable_shared_dpll()
+	 * 3. For non-TBT Type-C ports, set FIA lane count
+	 * (DFLEXDPSP.DPX4TXLATC)
+	 *
+	 * This was done before tgl_ddi_pre_enable_dp by
+	 * hsw_crtc_enable()->intel_encoders_pre_pll_enable().
 	 */
 
-	/* 4.b */
+	/*
+	 * 4. Enable the port PLL.
+	 *
+	 * The PLL enabling itself was already done before this function by
+	 * hsw_crtc_enable()->intel_enable_shared_dpll().  We need only
+	 * configure the PLL to port mapping here.
+	 */
 	intel_ddi_clk_select(encoder, crtc_state);
 
-	/* 5. */
+	/* 5. If IO power is controlled through PWR_WELL_CTL, Enable IO Power */
 	if (!intel_phy_is_tc(dev_priv, phy) ||
 	    dig_port->tc_mode != TC_PORT_TBT_ALT)
 		intel_display_power_get(dev_priv,
 					dig_port->ddi_io_power_domain);
 
-	/* 6. */
+	/* 6. Program DP_MODE */
 	icl_program_mg_dp_mode(dig_port, crtc_state);
 
 	/*
-	 * 7.a - Steps in this function should only be executed over MST
-	 * master, what will be taken in care by MST hook
-	 * intel_mst_pre_enable_dp()
+	 * 7. The rest of the below are substeps under the bspec's "Enable and
+	 * Train Display Port" step.  Note that steps that are specific to
+	 * MST will be handled by intel_mst_pre_enable_dp() before/after it
+	 * calls into this function.  Also intel_mst_pre_enable_dp() only calls
+	 * us when active_mst_links==0, so any steps designated for "single
+	 * stream or multi-stream master transcoder" can just be performed
+	 * unconditionally here.
+	 */
+
+	/*
+	 * 7.a Configure Transcoder Clock Select to direct the Port clock to the
+	 * Transcoder.
 	 */
 	intel_ddi_enable_pipe_clock(crtc_state);
 
-	/* 7.b */
+	/*
+	 * 7.b Configure TRANS_DDI_FUNC_CTL DDI Select, DDI Mode Select & MST
+	 * Transport Select
+	 */
 	intel_ddi_config_transcoder_func(crtc_state);
 
-	/* 7.d */
-	icl_phy_set_clock_gating(dig_port, false);
+	/*
+	 * 7.c Configure & enable DP_TP_CTL with link training pattern 1
+	 * selected
+	 *
+	 * This will be handled by the intel_dp_start_link_train() farther
+	 * down this function.
+	 */
 
-	/* 7.e */
+	/* 7.e Configure voltage swing and related IO settings */
 	tgl_ddi_vswing_sequence(encoder, crtc_state->port_clock, level,
 				encoder->type);
 
-	/* 7.f */
+	/*
+	 * 7.f Combo PHY: Configure PORT_CL_DW10 Static Power Down to power up
+	 * the used lanes of the DDI.
+	 */
 	if (intel_phy_is_combo(dev_priv, phy)) {
 		bool lane_reversal =
 			dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
@@ -3505,7 +3482,14 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					       lane_reversal);
 	}
 
-	/* 7.g */
+	/*
+	 * 7.g Configure and enable DDI_BUF_CTL
+	 * 7.h Wait for DDI_BUF_CTL DDI Idle Status = 0b (Not Idle), timeout
+	 *     after 500 us.
+	 *
+	 * We only configure what the register value will be here.  Actual
+	 * enabling happens during link training farther down.
+	 */
 	intel_ddi_init_dp_buf_reg(encoder);
 
 	if (!is_mst)
@@ -3518,23 +3502,21 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	 * training
 	 */
 	intel_dp_sink_set_fec_ready(intel_dp, crtc_state);
-	/* 7.c, 7.h, 7.i, 7.j */
+
+	/*
+	 * 7.i Follow DisplayPort specification training sequence (see notes for
+	 *     failure handling)
+	 * 7.j If DisplayPort multi-stream - Set DP_TP_CTL link training to Idle
+	 *     Pattern, wait for 5 idle patterns (DP_TP_STATUS Min_Idles_Sent)
+	 *     (timeout after 800 us)
+	 */
 	intel_dp_start_link_train(intel_dp);
 
-	/* 7.k */
+	/* 7.k Set DP_TP_CTL link training to Normal */
 	if (!is_trans_port_sync_mode(crtc_state))
 		intel_dp_stop_link_train(intel_dp);
 
-	/*
-	 * TODO: enable clock gating
-	 *
-	 * It is not written in DP enabling sequence but "PHY Clockgating
-	 * programming" states that clock gating should be enabled after the
-	 * link training but doing so causes all the following trainings to fail
-	 * so not enabling it for now.
-	 */
-
-	/* 7.l */
+	/* 7.l Configure and enable FEC if needed */
 	intel_ddi_enable_fec(encoder, crtc_state);
 	intel_dsc_enable(encoder, crtc_state);
 }
@@ -3543,15 +3525,18 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	int level = intel_ddi_dp_level(intel_dp);
 
-	WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
+	if (INTEL_GEN(dev_priv) < 11)
+		WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
+	else
+		WARN_ON(is_mst && port == PORT_A);
 
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
@@ -3569,7 +3554,6 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					dig_port->ddi_io_power_domain);
 
 	icl_program_mg_dp_mode(dig_port, crtc_state);
-	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
@@ -3603,8 +3587,6 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	intel_ddi_enable_fec(encoder, crtc_state);
 
-	icl_phy_set_clock_gating(dig_port, true);
-
 	if (!is_mst)
 		intel_ddi_enable_pipe_clock(crtc_state);
 
@@ -3633,12 +3615,12 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 				      const struct intel_crtc_state *crtc_state,
 				      const struct drm_connector_state *conn_state)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	int level = intel_ddi_hdmi_level(dev_priv, port);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
 	intel_ddi_clk_select(encoder, crtc_state);
@@ -3646,7 +3628,6 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	icl_program_mg_dp_mode(dig_port, crtc_state);
-	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 12)
 		tgl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
@@ -3661,8 +3642,6 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	else
 		intel_prepare_hdmi_ddi_buffers(encoder, level);
 
-	icl_phy_set_clock_gating(dig_port, true);
-
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, INTEL_OUTPUT_HDMI);
 
@@ -3677,7 +3656,7 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -3705,12 +3684,12 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder,
 		intel_ddi_pre_enable_hdmi(encoder, crtc_state, conn_state);
 	} else {
 		struct intel_lspcon *lspcon =
-				enc_to_intel_lspcon(&encoder->base);
+				enc_to_intel_lspcon(encoder);
 
 		intel_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
 		if (lspcon->active) {
 			struct intel_digital_port *dig_port =
-					enc_to_dig_port(&encoder->base);
+					enc_to_dig_port(encoder);
 
 			dig_port->set_infoframes(encoder,
 						 crtc_state->has_infoframe,
@@ -3735,7 +3714,7 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder,
 	}
 
 	if (intel_crtc_has_dp_encoder(crtc_state)) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		val = I915_READ(intel_dp->regs.dp_tp_ctl);
 		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
@@ -3755,23 +3734,42 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 				      const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_dp *intel_dp = &dig_port->dp;
 	bool is_mst = intel_crtc_has_type(old_crtc_state,
 					  INTEL_OUTPUT_DP_MST);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
-	if (!is_mst) {
-		intel_ddi_disable_pipe_clock(old_crtc_state);
-		/*
-		 * Power down sink before disabling the port, otherwise we end
-		 * up getting interrupts from the sink on detecting link loss.
-		 */
-		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+	/*
+	 * Power down sink before disabling the port, otherwise we end
+	 * up getting interrupts from the sink on detecting link loss.
+	 */
+	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (is_mst) {
+			enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
+			u32 val;
+
+			val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+			val &= ~TGL_TRANS_DDI_PORT_MASK;
+			I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), val);
+		}
+	} else {
+		if (!is_mst)
+			intel_ddi_disable_pipe_clock(old_crtc_state);
 	}
 
 	intel_disable_ddi_buf(encoder, old_crtc_state);
 
+	/*
+	 * From TGL spec: "If single stream or multi-stream master transcoder:
+	 * Configure Transcoder Clock select to direct no clock to the
+	 * transcoder"
+	 */
+	if (INTEL_GEN(dev_priv) >= 12)
+		intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	intel_edp_panel_vdd_on(intel_dp);
 	intel_edp_panel_off(intel_dp);
 
@@ -3789,7 +3787,7 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 					const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &dig_port->hdmi;
 
 	dig_port->set_infoframes(encoder, false,
@@ -3807,11 +3805,46 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, false);
 }
 
+static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
+		return;
+
+	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
+		      transcoder_name(old_crtc_state->cpu_transcoder));
+
+	I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
+}
+
 static void intel_ddi_post_disable(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *old_crtc_state,
 				   const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
+
+	if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST)) {
+		intel_crtc_vblank_off(old_crtc_state);
+
+		intel_disable_pipe(old_crtc_state);
+
+		if (INTEL_GEN(dev_priv) >= 11)
+			icl_disable_transcoder_port_sync(old_crtc_state);
+
+		intel_ddi_disable_transcoder_func(old_crtc_state);
+
+		intel_dsc_disable(old_crtc_state);
+
+		if (INTEL_GEN(dev_priv) >= 9)
+			skl_scaler_disable(old_crtc_state);
+		else
+			ilk_pfit_disable(old_crtc_state);
+	}
 
 	/*
 	 * When called from DP MST code:
@@ -3835,6 +3868,13 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder,
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_unmap_plls_to_ports(encoder);
+
+	if (intel_crtc_has_dp_encoder(old_crtc_state) || is_tc_port)
+		intel_display_power_put_unchecked(dev_priv,
+						  intel_ddi_main_link_aux_domain(dig_port));
+
+	if (is_tc_port)
+		intel_tc_port_put_link(dig_port);
 }
 
 void intel_ddi_fdi_post_disable(struct intel_encoder *encoder,
@@ -3876,7 +3916,7 @@ static void intel_enable_ddi_dp(struct intel_encoder *encoder,
 				const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 
 	if (port == PORT_A && INTEL_GEN(dev_priv) < 9)
@@ -3917,7 +3957,7 @@ static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
 				  const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct drm_connector *connector = conn_state->connector;
 	enum port port = encoder->port;
 
@@ -3994,7 +4034,7 @@ static void intel_disable_ddi_dp(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	intel_dp->link_trained = false;
 
@@ -4042,7 +4082,7 @@ static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder,
 				     const struct intel_crtc_state *crtc_state,
 				     const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	intel_ddi_set_dp_msa(crtc_state, conn_state);
 
@@ -4106,8 +4146,9 @@ intel_ddi_update_prepare(struct intel_atomic_state *state,
 
 	WARN_ON(crtc && crtc->active);
 
-	intel_tc_port_get_link(enc_to_dig_port(&encoder->base), required_lanes);
-	if (crtc_state && crtc_state->base.active)
+	intel_tc_port_get_link(enc_to_dig_port(encoder),
+		               required_lanes);
+	if (crtc_state && crtc_state->hw.active)
 		intel_update_active_dpll(state, crtc, encoder);
 }
 
@@ -4116,7 +4157,7 @@ intel_ddi_update_complete(struct intel_atomic_state *state,
 			  struct intel_encoder *encoder,
 			  struct intel_crtc *crtc)
 {
-	intel_tc_port_put_link(enc_to_dig_port(&encoder->base));
+	intel_tc_port_put_link(enc_to_dig_port(encoder));
 }
 
 static void
@@ -4125,7 +4166,7 @@ intel_ddi_pre_pll_enable(struct intel_encoder *encoder,
 			 const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
 
@@ -4147,61 +4188,44 @@ intel_ddi_pre_pll_enable(struct intel_encoder *encoder,
 						crtc_state->lane_lat_optim_mask);
 }
 
-static void
-intel_ddi_post_pll_disable(struct intel_encoder *encoder,
-			   const struct intel_crtc_state *crtc_state,
-			   const struct drm_connector_state *conn_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
-	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
-	bool is_tc_port = intel_phy_is_tc(dev_priv, phy);
-
-	if (intel_crtc_has_dp_encoder(crtc_state) || is_tc_port)
-		intel_display_power_put_unchecked(dev_priv,
-						  intel_ddi_main_link_aux_domain(dig_port));
-
-	if (is_tc_port)
-		intel_tc_port_put_link(dig_port);
-}
-
 static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv =
 		to_i915(intel_dig_port->base.base.dev);
 	enum port port = intel_dig_port->base.port;
-	u32 val;
+	u32 dp_tp_ctl, ddi_buf_ctl;
 	bool wait = false;
 
-	if (I915_READ(intel_dp->regs.dp_tp_ctl) & DP_TP_CTL_ENABLE) {
-		val = I915_READ(DDI_BUF_CTL(port));
-		if (val & DDI_BUF_CTL_ENABLE) {
-			val &= ~DDI_BUF_CTL_ENABLE;
-			I915_WRITE(DDI_BUF_CTL(port), val);
+	dp_tp_ctl = I915_READ(intel_dp->regs.dp_tp_ctl);
+
+	if (dp_tp_ctl & DP_TP_CTL_ENABLE) {
+		ddi_buf_ctl = I915_READ(DDI_BUF_CTL(port));
+		if (ddi_buf_ctl & DDI_BUF_CTL_ENABLE) {
+			I915_WRITE(DDI_BUF_CTL(port),
+				   ddi_buf_ctl & ~DDI_BUF_CTL_ENABLE);
 			wait = true;
 		}
 
-		val = I915_READ(intel_dp->regs.dp_tp_ctl);
-		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
-		val |= DP_TP_CTL_LINK_TRAIN_PAT1;
-		I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+		dp_tp_ctl &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
+		dp_tp_ctl |= DP_TP_CTL_LINK_TRAIN_PAT1;
+		I915_WRITE(intel_dp->regs.dp_tp_ctl, dp_tp_ctl);
 		POSTING_READ(intel_dp->regs.dp_tp_ctl);
 
 		if (wait)
 			intel_wait_ddi_buf_idle(dev_priv, port);
 	}
 
-	val = DP_TP_CTL_ENABLE |
-	      DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_SCRAMBLE_DISABLE;
+	dp_tp_ctl = DP_TP_CTL_ENABLE |
+		    DP_TP_CTL_LINK_TRAIN_PAT1 | DP_TP_CTL_SCRAMBLE_DISABLE;
 	if (intel_dp->link_mst)
-		val |= DP_TP_CTL_MODE_MST;
+		dp_tp_ctl |= DP_TP_CTL_MODE_MST;
 	else {
-		val |= DP_TP_CTL_MODE_SST;
+		dp_tp_ctl |= DP_TP_CTL_MODE_SST;
 		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
-			val |= DP_TP_CTL_ENHANCED_FRAME_ENABLE;
+			dp_tp_ctl |= DP_TP_CTL_ENHANCED_FRAME_ENABLE;
 	}
-	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+	I915_WRITE(intel_dp->regs.dp_tp_ctl, dp_tp_ctl);
 	POSTING_READ(intel_dp->regs.dp_tp_ctl);
 
 	intel_dp->DP |= DDI_BUF_CTL_ENABLE;
@@ -4237,7 +4261,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	u32 temp, flags = 0;
 
@@ -4245,6 +4269,8 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	if (WARN_ON(transcoder_is_dsi(cpu_transcoder)))
 		return;
 
+	intel_dsc_get_config(encoder, pipe_config);
+
 	temp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 	if (temp & TRANS_DDI_PHSYNC)
 		flags |= DRM_MODE_FLAG_PHSYNC;
@@ -4255,7 +4281,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	switch (temp & TRANS_DDI_BPC_MASK) {
 	case TRANS_DDI_BPC_6:
@@ -4326,6 +4352,11 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_DP_MST);
 		pipe_config->lane_count =
 			((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
+
+		if (INTEL_GEN(dev_priv) >= 12)
+			pipe_config->mst_master_transcoder =
+					REG_FIELD_GET(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, temp);
+
 		intel_dp_get_m_n(intel_crtc, pipe_config);
 		break;
 	default:
@@ -4404,7 +4435,7 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum port port = encoder->port;
 	int ret;
@@ -4439,7 +4470,7 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 
 static void intel_ddi_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
+	struct intel_digital_port *dig_port = enc_to_dig_port(to_intel_encoder(encoder));
 
 	intel_dp_encoder_flush_work(encoder);
 
@@ -4506,7 +4537,7 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder,
 				 struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_hdmi *hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *hdmi = enc_to_intel_hdmi(encoder);
 	struct intel_connector *connector = hdmi->attached_connector;
 	struct i2c_adapter *adapter =
 		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
@@ -4538,7 +4569,7 @@ static int intel_hdmi_reset_link(struct intel_encoder *encoder,
 
 	WARN_ON(!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI));
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 
 	if (!crtc_state->hdmi_high_tmds_clock_ratio &&
@@ -4578,7 +4609,7 @@ intel_ddi_hotplug(struct intel_encoder *encoder,
 		  struct intel_connector *connector,
 		  bool irq_received)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct drm_modeset_acquire_ctx ctx;
 	enum intel_hotplug_state state;
 	int ret;
@@ -4709,8 +4740,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	struct ddi_vbt_port_info *port_info =
 		&dev_priv->vbt.ddi_port_info[port];
 	struct intel_digital_port *intel_dig_port;
-	struct intel_encoder *intel_encoder;
-	struct drm_encoder *encoder;
+	struct intel_encoder *encoder;
 	bool init_hdmi, init_dp, init_lspcon = false;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
@@ -4739,31 +4769,30 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	if (!intel_dig_port)
 		return;
 
-	intel_encoder = &intel_dig_port->base;
-	encoder = &intel_encoder->base;
+	encoder = &intel_dig_port->base;
 
-	drm_encoder_init(&dev_priv->drm, encoder, &intel_ddi_funcs,
+	drm_encoder_init(&dev_priv->drm, &encoder->base, &intel_ddi_funcs,
 			 DRM_MODE_ENCODER_TMDS, "DDI %c", port_name(port));
 
-	intel_encoder->hotplug = intel_ddi_hotplug;
-	intel_encoder->compute_output_type = intel_ddi_compute_output_type;
-	intel_encoder->compute_config = intel_ddi_compute_config;
-	intel_encoder->enable = intel_enable_ddi;
-	intel_encoder->pre_pll_enable = intel_ddi_pre_pll_enable;
-	intel_encoder->post_pll_disable = intel_ddi_post_pll_disable;
-	intel_encoder->pre_enable = intel_ddi_pre_enable;
-	intel_encoder->disable = intel_disable_ddi;
-	intel_encoder->post_disable = intel_ddi_post_disable;
-	intel_encoder->update_pipe = intel_ddi_update_pipe;
-	intel_encoder->get_hw_state = intel_ddi_get_hw_state;
-	intel_encoder->get_config = intel_ddi_get_config;
-	intel_encoder->suspend = intel_dp_encoder_suspend;
-	intel_encoder->get_power_domains = intel_ddi_get_power_domains;
-	intel_encoder->type = INTEL_OUTPUT_DDI;
-	intel_encoder->power_domain = intel_port_to_power_domain(port);
-	intel_encoder->port = port;
-	intel_encoder->cloneable = 0;
-	intel_encoder->pipe_mask = ~0;
+	encoder->hotplug = intel_ddi_hotplug;
+	encoder->compute_output_type = intel_ddi_compute_output_type;
+	encoder->compute_config = intel_ddi_compute_config;
+	encoder->enable = intel_enable_ddi;
+	encoder->pre_pll_enable = intel_ddi_pre_pll_enable;
+	encoder->pre_enable = intel_ddi_pre_enable;
+	encoder->disable = intel_disable_ddi;
+	encoder->post_disable = intel_ddi_post_disable;
+	encoder->update_pipe = intel_ddi_update_pipe;
+	encoder->get_hw_state = intel_ddi_get_hw_state;
+	encoder->get_config = intel_ddi_get_config;
+	encoder->suspend = intel_dp_encoder_suspend;
+	encoder->get_power_domains = intel_ddi_get_power_domains;
+
+	encoder->type = INTEL_OUTPUT_DDI;
+	encoder->power_domain = intel_port_to_power_domain(port);
+	encoder->port = port;
+	encoder->cloneable = 0;
+	encoder->pipe_mask = ~0;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
@@ -4771,6 +4800,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	else
 		intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
 			(DDI_BUF_PORT_REVERSAL | DDI_A_4_LANES);
+
 	intel_dig_port->dp.output_reg = INVALID_MMIO_REG;
 	intel_dig_port->max_lanes = intel_ddi_max_lanes(intel_dig_port);
 	intel_dig_port->aux_ch = intel_bios_port_aux_ch(dev_priv, port);
@@ -4781,8 +4811,8 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 
 		intel_tc_port_init(intel_dig_port, is_legacy);
 
-		intel_encoder->update_prepare = intel_ddi_update_prepare;
-		intel_encoder->update_complete = intel_ddi_update_complete;
+		encoder->update_prepare = intel_ddi_update_prepare;
+		encoder->update_complete = intel_ddi_update_complete;
 	}
 
 	WARN_ON(port > PORT_I);
@@ -4798,7 +4828,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 
 	/* In theory we don't need the encoder->type check, but leave it just in
 	 * case we have some really bad VBTs... */
-	if (intel_encoder->type != INTEL_OUTPUT_EDP && init_hdmi) {
+	if (encoder->type != INTEL_OUTPUT_EDP && init_hdmi) {
 		if (!intel_ddi_init_hdmi_connector(intel_dig_port))
 			goto err;
 	}
@@ -4822,6 +4852,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	return;
 
 err:
-	drm_encoder_cleanup(encoder);
+	drm_encoder_cleanup(&encoder->base);
 	kfree(intel_dig_port);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h
index 19aeab1246ee..167c6579d972 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.h
+++ b/drivers/gpu/drm/i915/display/intel_ddi.h
@@ -22,7 +22,7 @@ struct intel_encoder;
 void intel_ddi_fdi_post_disable(struct intel_encoder *intel_encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state);
-void hsw_fdi_link_train(struct intel_crtc *crtc,
+void hsw_fdi_link_train(struct intel_encoder *encoder,
 			const struct intel_crtc_state *crtc_state);
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 301897791627..19ea842cfd84 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -46,6 +46,7 @@
 #include "display/intel_crt.h"
 #include "display/intel_ddi.h"
 #include "display/intel_dp.h"
+#include "display/intel_dp_mst.h"
 #include "display/intel_dsi.h"
 #include "display/intel_dvo.h"
 #include "display/intel_gmbus.h"
@@ -86,8 +87,8 @@
 /* Primary plane formats for gen <= 3 */
 static const u32 i8xx_primary_formats[] = {
 	DRM_FORMAT_C8,
-	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB8888,
 };
 
@@ -112,6 +113,21 @@ static const u32 i965_primary_formats[] = {
 	DRM_FORMAT_XBGR16161616F,
 };
 
+/* Primary plane formats for vlv/chv */
+static const u32 vlv_primary_formats[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_XBGR16161616F,
+};
+
 static const u64 i9xx_format_modifiers[] = {
 	I915_FORMAT_MOD_X_TILED,
 	DRM_FORMAT_MOD_LINEAR,
@@ -130,8 +146,8 @@ static const u64 cursor_format_modifiers[] = {
 
 static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 				struct intel_crtc_state *pipe_config);
-static void ironlake_pch_clock_get(struct intel_crtc *crtc,
-				   struct intel_crtc_state *pipe_config);
+static void ilk_pch_clock_get(struct intel_crtc *crtc,
+			      struct intel_crtc_state *pipe_config);
 
 static int intel_framebuffer_init(struct intel_framebuffer *ifb,
 				  struct drm_i915_gem_object *obj,
@@ -142,21 +158,18 @@ static void intel_cpu_transcoder_set_m_n(const struct intel_crtc_state *crtc_sta
 					 const struct intel_link_m_n *m_n,
 					 const struct intel_link_m_n *m2_n2);
 static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state);
-static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state);
-static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state);
+static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state);
+static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state);
 static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state);
 static void vlv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config);
 static void chv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config);
-static void intel_crtc_init_scalers(struct intel_crtc *crtc,
-				    struct intel_crtc_state *crtc_state);
-static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state);
-static void ironlake_pfit_disable(const struct intel_crtc_state *old_crtc_state);
-static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state);
+static void skl_pfit_enable(const struct intel_crtc_state *crtc_state);
+static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state);
 static void intel_modeset_setup_hw_state(struct drm_device *dev,
 					 struct drm_modeset_acquire_ctx *ctx);
-static void intel_pre_disable_primary_noatomic(struct drm_crtc *crtc);
+static struct intel_crtc_state *intel_crtc_state_alloc(struct intel_crtc *crtc);
 
 struct intel_limit {
 	struct {
@@ -357,7 +370,7 @@ static const struct intel_limit intel_limits_g4x_dual_channel_lvds = {
 	},
 };
 
-static const struct intel_limit intel_limits_pineview_sdvo = {
+static const struct intel_limit pnv_limits_sdvo = {
 	.dot = { .min = 20000, .max = 400000},
 	.vco = { .min = 1700000, .max = 3500000 },
 	/* Pineview's Ncounter is a ring counter */
@@ -372,7 +385,7 @@ static const struct intel_limit intel_limits_pineview_sdvo = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const struct intel_limit intel_limits_pineview_lvds = {
+static const struct intel_limit pnv_limits_lvds = {
 	.dot = { .min = 20000, .max = 400000 },
 	.vco = { .min = 1700000, .max = 3500000 },
 	.n = { .min = 3, .max = 6 },
@@ -390,7 +403,7 @@ static const struct intel_limit intel_limits_pineview_lvds = {
  * We calculate clock using (register_value + 2) for N/M1/M2, so here
  * the range value for them is (actual_value - 2).
  */
-static const struct intel_limit intel_limits_ironlake_dac = {
+static const struct intel_limit ilk_limits_dac = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 5 },
@@ -403,7 +416,7 @@ static const struct intel_limit intel_limits_ironlake_dac = {
 		.p2_slow = 10, .p2_fast = 5 },
 };
 
-static const struct intel_limit intel_limits_ironlake_single_lvds = {
+static const struct intel_limit ilk_limits_single_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -416,7 +429,7 @@ static const struct intel_limit intel_limits_ironlake_single_lvds = {
 		.p2_slow = 14, .p2_fast = 14 },
 };
 
-static const struct intel_limit intel_limits_ironlake_dual_lvds = {
+static const struct intel_limit ilk_limits_dual_lvds = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -430,7 +443,7 @@ static const struct intel_limit intel_limits_ironlake_dual_lvds = {
 };
 
 /* LVDS 100mhz refclk limits. */
-static const struct intel_limit intel_limits_ironlake_single_lvds_100m = {
+static const struct intel_limit ilk_limits_single_lvds_100m = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 2 },
@@ -443,7 +456,7 @@ static const struct intel_limit intel_limits_ironlake_single_lvds_100m = {
 		.p2_slow = 14, .p2_fast = 14 },
 };
 
-static const struct intel_limit intel_limits_ironlake_dual_lvds_100m = {
+static const struct intel_limit ilk_limits_dual_lvds_100m = {
 	.dot = { .min = 25000, .max = 350000 },
 	.vco = { .min = 1760000, .max = 3510000 },
 	.n = { .min = 1, .max = 3 },
@@ -530,7 +543,7 @@ icl_wa_scalerclkgating(struct drm_i915_private *dev_priv, enum pipe pipe,
 static bool
 needs_modeset(const struct intel_crtc_state *state)
 {
-	return drm_atomic_crtc_needs_modeset(&state->base);
+	return drm_atomic_crtc_needs_modeset(&state->uapi);
 }
 
 bool
@@ -541,10 +554,9 @@ is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state)
 }
 
 static bool
-is_trans_port_sync_master(const struct intel_crtc_state *crtc_state)
+is_trans_port_sync_slave(const struct intel_crtc_state *crtc_state)
 {
-	return (crtc_state->master_transcoder == INVALID_TRANSCODER &&
-		crtc_state->sync_mode_slaves_mask);
+	return crtc_state->master_transcoder != INVALID_TRANSCODER;
 }
 
 /*
@@ -658,7 +670,7 @@ i9xx_select_p2_div(const struct intel_limit *limit,
 		   const struct intel_crtc_state *crtc_state,
 		   int target)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) {
 		/*
@@ -694,7 +706,7 @@ i9xx_find_best_dpll(const struct intel_limit *limit,
 		    int target, int refclk, struct dpll *match_clock,
 		    struct dpll *best_clock)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	struct dpll clock;
 	int err = target;
 
@@ -752,7 +764,7 @@ pnv_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	struct dpll clock;
 	int err = target;
 
@@ -808,7 +820,7 @@ g4x_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	struct dpll clock;
 	int max_n;
 	bool found = false;
@@ -902,7 +914,7 @@ vlv_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct dpll clock;
 	unsigned int bestppm = 1000000;
@@ -962,7 +974,7 @@ chv_find_best_dpll(const struct intel_limit *limit,
 		   int target, int refclk, struct dpll *match_clock,
 		   struct dpll *best_clock)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	unsigned int best_error_ppm;
 	struct dpll clock;
@@ -1025,33 +1037,6 @@ bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state,
 				  NULL, best_clock);
 }
 
-bool intel_crtc_active(struct intel_crtc *crtc)
-{
-	/* Be paranoid as we can arrive here with only partial
-	 * state retrieved from the hardware during setup.
-	 *
-	 * We can ditch the adjusted_mode.crtc_clock check as soon
-	 * as Haswell has gained clock readout/fastboot support.
-	 *
-	 * We can ditch the crtc->primary->state->fb check as soon as we can
-	 * properly reconstruct framebuffers.
-	 *
-	 * FIXME: The intel_crtc->active here should be switched to
-	 * crtc->state->active once we have proper CRTC states wired up
-	 * for atomic.
-	 */
-	return crtc->active && crtc->base.primary->state->fb &&
-		crtc->config->base.adjusted_mode.crtc_clock;
-}
-
-enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
-					     enum pipe pipe)
-{
-	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-
-	return crtc->config->cpu_transcoder;
-}
-
 static bool pipe_scanline_is_moving(struct drm_i915_private *dev_priv,
 				    enum pipe pipe)
 {
@@ -1095,7 +1080,7 @@ static void intel_wait_for_pipe_scanline_moving(struct intel_crtc *crtc)
 static void
 intel_wait_for_pipe_off(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (INTEL_GEN(dev_priv) >= 4) {
@@ -1145,11 +1130,15 @@ static void assert_fdi_tx(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, bool state)
 {
 	bool cur_state;
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
 
 	if (HAS_DDI(dev_priv)) {
-		/* DDI does not have a specific FDI_TX register */
+		/*
+		 * DDI does not have a specific FDI_TX register.
+		 *
+		 * FDI is never fed from EDP transcoder
+		 * so pipe->transcoder cast is fine here.
+		 */
+		enum transcoder cpu_transcoder = (enum transcoder)pipe;
 		u32 val = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
 		cur_state = !!(val & TRANS_DDI_FUNC_ENABLE);
 	} else {
@@ -1266,11 +1255,9 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 }
 
 void assert_pipe(struct drm_i915_private *dev_priv,
-		 enum pipe pipe, bool state)
+		 enum transcoder cpu_transcoder, bool state)
 {
 	bool cur_state;
-	enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv,
-								      pipe);
 	enum intel_display_power_domain power_domain;
 	intel_wakeref_t wakeref;
 
@@ -1290,8 +1277,9 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 	}
 
 	I915_STATE_WARN(cur_state != state,
-	     "pipe %c assertion failure (expected %s, current %s)\n",
-			pipe_name(pipe), onoff(state), onoff(cur_state));
+			"transcoder %s assertion failure (expected %s, current %s)\n",
+			transcoder_name(cpu_transcoder),
+			onoff(state), onoff(cur_state));
 }
 
 static void assert_plane(struct intel_plane *plane, bool state)
@@ -1418,7 +1406,7 @@ static void vlv_enable_pll(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 
 	/* PLL is protected by panel, make sure we can write it */
 	assert_panel_unlocked(dev_priv, pipe);
@@ -1467,7 +1455,7 @@ static void chv_enable_pll(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 
 	/* PLL is protected by panel, make sure we can write it */
 	assert_panel_unlocked(dev_priv, pipe);
@@ -1514,7 +1502,7 @@ static void i9xx_enable_pll(struct intel_crtc *crtc,
 	u32 dpll = crtc_state->dpll_hw_state.dpll;
 	int i;
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder);
 
 	/* PLL is protected by panel, make sure we can write it */
 	if (i9xx_has_pps(dev_priv))
@@ -1554,7 +1542,7 @@ static void i9xx_enable_pll(struct intel_crtc *crtc,
 
 static void i9xx_disable_pll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -1563,7 +1551,7 @@ static void i9xx_disable_pll(const struct intel_crtc_state *crtc_state)
 		return;
 
 	/* Make sure the pipe isn't still relying on us */
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder);
 
 	I915_WRITE(DPLL(pipe), DPLL_VGA_MODE_DIS);
 	POSTING_READ(DPLL(pipe));
@@ -1574,7 +1562,7 @@ static void vlv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	u32 val;
 
 	/* Make sure the pipe isn't still relying on us */
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, (enum transcoder)pipe);
 
 	val = DPLL_INTEGRATED_REF_CLK_VLV |
 		DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
@@ -1591,7 +1579,7 @@ static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	u32 val;
 
 	/* Make sure the pipe isn't still relying on us */
-	assert_pipe_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev_priv, (enum transcoder)pipe);
 
 	val = DPLL_SSC_REF_CLK_CHV |
 		DPLL_REF_CLK_ENABLE_VLV | DPLL_VGA_MODE_DIS;
@@ -1643,9 +1631,9 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 		     I915_READ(dpll_reg) & port_mask, expected_mask);
 }
 
-static void ironlake_enable_pch_transcoder(const struct intel_crtc_state *crtc_state)
+static void ilk_enable_pch_transcoder(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
@@ -1659,11 +1647,16 @@ static void ironlake_enable_pch_transcoder(const struct intel_crtc_state *crtc_s
 	assert_fdi_rx_enabled(dev_priv, pipe);
 
 	if (HAS_PCH_CPT(dev_priv)) {
-		/* Workaround: Set the timing override bit before enabling the
-		 * pch transcoder. */
 		reg = TRANS_CHICKEN2(pipe);
 		val = I915_READ(reg);
+		/*
+		 * Workaround: Set the timing override bit
+		 * before enabling the pch transcoder.
+		 */
 		val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
+		/* Configure frame start delay to match the CPU */
+		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+		val |= TRANS_CHICKEN2_FRAME_START_DELAY(0);
 		I915_WRITE(reg, val);
 	}
 
@@ -1672,6 +1665,10 @@ static void ironlake_enable_pch_transcoder(const struct intel_crtc_state *crtc_s
 	pipeconf_val = I915_READ(PIPECONF(pipe));
 
 	if (HAS_PCH_IBX(dev_priv)) {
+		/* Configure frame start delay to match the CPU */
+		val &= ~TRANS_FRAME_START_DELAY_MASK;
+		val |= TRANS_FRAME_START_DELAY(0);
+
 		/*
 		 * Make the BPC in transcoder be consistent with
 		 * that in pipeconf reg. For HDMI we must use 8bpc
@@ -1709,9 +1706,12 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 	assert_fdi_tx_enabled(dev_priv, (enum pipe) cpu_transcoder);
 	assert_fdi_rx_enabled(dev_priv, PIPE_A);
 
-	/* Workaround: set timing override bit. */
 	val = I915_READ(TRANS_CHICKEN2(PIPE_A));
+	/* Workaround: set timing override bit. */
 	val |= TRANS_CHICKEN2_TIMING_OVERRIDE;
+	/* Configure frame start delay to match the CPU */
+	val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+	val |= TRANS_CHICKEN2_FRAME_START_DELAY(0);
 	I915_WRITE(TRANS_CHICKEN2(PIPE_A), val);
 
 	val = TRANS_ENABLE;
@@ -1729,8 +1729,8 @@ static void lpt_enable_pch_transcoder(struct drm_i915_private *dev_priv,
 		DRM_ERROR("Failed to enable PCH transcoder\n");
 }
 
-static void ironlake_disable_pch_transcoder(struct drm_i915_private *dev_priv,
-					    enum pipe pipe)
+static void ilk_disable_pch_transcoder(struct drm_i915_private *dev_priv,
+				       enum pipe pipe)
 {
 	i915_reg_t reg;
 	u32 val;
@@ -1789,7 +1789,7 @@ enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc)
 
 static u32 intel_crtc_max_vblank_count(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	/*
 	 * On i965gm the hardware frame counter reads
@@ -1809,16 +1809,25 @@ static u32 intel_crtc_max_vblank_count(const struct intel_crtc_state *crtc_state
 
 static void intel_crtc_vblank_on(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
+	assert_vblank_disabled(&crtc->base);
 	drm_crtc_set_max_vblank_count(&crtc->base,
 				      intel_crtc_max_vblank_count(crtc_state));
 	drm_crtc_vblank_on(&crtc->base);
 }
 
+void intel_crtc_vblank_off(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+
+	drm_crtc_vblank_off(&crtc->base);
+	assert_vblank_disabled(&crtc->base);
+}
+
 static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = new_crtc_state->cpu_transcoder;
 	enum pipe pipe = crtc->pipe;
@@ -1874,9 +1883,9 @@ static void intel_enable_pipe(const struct intel_crtc_state *new_crtc_state)
 		intel_wait_for_pipe_scanline_moving(crtc);
 }
 
-static void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state)
+void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
 	enum pipe pipe = crtc->pipe;
@@ -1919,6 +1928,74 @@ static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv)
 	return IS_GEN(dev_priv, 2) ? 2048 : 4096;
 }
 
+static bool is_ccs_plane(const struct drm_framebuffer *fb, int plane)
+{
+	if (!is_ccs_modifier(fb->modifier))
+		return false;
+
+	return plane >= fb->format->num_planes / 2;
+}
+
+static bool is_gen12_ccs_modifier(u64 modifier)
+{
+	return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
+
+}
+
+static bool is_gen12_ccs_plane(const struct drm_framebuffer *fb, int plane)
+{
+	return is_gen12_ccs_modifier(fb->modifier) && is_ccs_plane(fb, plane);
+}
+
+static bool is_aux_plane(const struct drm_framebuffer *fb, int plane)
+{
+	if (is_ccs_modifier(fb->modifier))
+		return is_ccs_plane(fb, plane);
+
+	return plane == 1;
+}
+
+static int main_to_ccs_plane(const struct drm_framebuffer *fb, int main_plane)
+{
+	WARN_ON(!is_ccs_modifier(fb->modifier) ||
+		(main_plane && main_plane >= fb->format->num_planes / 2));
+
+	return fb->format->num_planes / 2 + main_plane;
+}
+
+static int ccs_to_main_plane(const struct drm_framebuffer *fb, int ccs_plane)
+{
+	WARN_ON(!is_ccs_modifier(fb->modifier) ||
+		ccs_plane < fb->format->num_planes / 2);
+
+	return ccs_plane - fb->format->num_planes / 2;
+}
+
+/* Return either the main plane's CCS or - if not a CCS FB - UV plane */
+int intel_main_to_aux_plane(const struct drm_framebuffer *fb, int main_plane)
+{
+	if (is_ccs_modifier(fb->modifier))
+		return main_to_ccs_plane(fb, main_plane);
+
+	return 1;
+}
+
+bool
+intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info,
+				    uint64_t modifier)
+{
+	return info->is_yuv &&
+	       info->num_planes == (is_ccs_modifier(modifier) ? 4 : 2);
+}
+
+static bool is_semiplanar_uv_plane(const struct drm_framebuffer *fb,
+				   int color_plane)
+{
+	return intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
+	       color_plane == 1;
+}
+
 static unsigned int
 intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 {
@@ -1934,16 +2011,21 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 		else
 			return 512;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
-		if (color_plane == 1)
+		if (is_ccs_plane(fb, color_plane))
 			return 128;
 		/* fall through */
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		if (is_ccs_plane(fb, color_plane))
+			return 64;
+		/* fall through */
 	case I915_FORMAT_MOD_Y_TILED:
 		if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv))
 			return 128;
 		else
 			return 512;
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
-		if (color_plane == 1)
+		if (is_ccs_plane(fb, color_plane))
 			return 128;
 		/* fall through */
 	case I915_FORMAT_MOD_Yf_TILED:
@@ -1970,6 +2052,9 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane)
 static unsigned int
 intel_tile_height(const struct drm_framebuffer *fb, int color_plane)
 {
+	if (is_gen12_ccs_plane(fb, color_plane))
+		return 1;
+
 	return intel_tile_size(to_i915(fb->dev)) /
 		intel_tile_width_bytes(fb, color_plane);
 }
@@ -1983,7 +2068,17 @@ static void intel_tile_dims(const struct drm_framebuffer *fb, int color_plane,
 	unsigned int cpp = fb->format->cpp[color_plane];
 
 	*tile_width = tile_width_bytes / cpp;
-	*tile_height = intel_tile_size(to_i915(fb->dev)) / tile_width_bytes;
+	*tile_height = intel_tile_height(fb, color_plane);
+}
+
+static unsigned int intel_tile_row_size(const struct drm_framebuffer *fb,
+					int color_plane)
+{
+	unsigned int tile_width, tile_height;
+
+	intel_tile_dims(fb, color_plane, &tile_width, &tile_height);
+
+	return fb->pitches[color_plane] * tile_height;
 }
 
 unsigned int
@@ -2060,7 +2155,8 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
 
 	/* AUX_DIST needs only 4K alignment */
-	if (color_plane == 1)
+	if ((INTEL_GEN(dev_priv) < 12 && is_aux_plane(fb, color_plane)) ||
+	    is_ccs_plane(fb, color_plane))
 		return 4096;
 
 	switch (fb->modifier) {
@@ -2070,9 +2166,19 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 		if (INTEL_GEN(dev_priv) >= 9)
 			return 256 * 1024;
 		return 0;
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		if (is_semiplanar_uv_plane(fb, color_plane))
+			return intel_tile_row_size(fb, color_plane);
+		/* Fall-through */
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+		return 16 * 1024;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 	case I915_FORMAT_MOD_Y_TILED:
+		if (INTEL_GEN(dev_priv) >= 12 &&
+		    is_semiplanar_uv_plane(fb, color_plane))
+			return intel_tile_row_size(fb, color_plane);
+		/* Fall-through */
 	case I915_FORMAT_MOD_Yf_TILED:
 		return 1 * 1024 * 1024;
 	default:
@@ -2083,7 +2189,7 @@ static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
 
 static bool intel_plane_uses_fence(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 
 	return INTEL_GEN(dev_priv) < 4 ||
@@ -2109,6 +2215,8 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 		return ERR_PTR(-EINVAL);
 
 	alignment = intel_surf_alignment(fb, 0);
+	if (WARN_ON(alignment && !is_power_of_2(alignment)))
+		return ERR_PTR(-EINVAL);
 
 	/* Note that the w/a also requires 64 PTE of padding following the
 	 * bo. We currently fill all unused PTE with the shadow page and so
@@ -2126,19 +2234,18 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	 * pin/unpin/fence and not more.
 	 */
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-	i915_gem_object_lock(obj);
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
-	pinctl = 0;
-
-	/* Valleyview is definitely limited to scanning out the first
+	/*
+	 * Valleyview is definitely limited to scanning out the first
 	 * 512MiB. Lets presume this behaviour was inherited from the
 	 * g4x display engine and that all earlier gen are similarly
 	 * limited. Testing suggests that it is a little more
 	 * complicated than this. For example, Cherryview appears quite
 	 * happy to scanout from anywhere within its global aperture.
 	 */
+	pinctl = 0;
 	if (HAS_GMCH(dev_priv))
 		pinctl |= PIN_MAPPABLE;
 
@@ -2150,7 +2257,8 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	if (uses_fence && i915_vma_is_map_and_fenceable(vma)) {
 		int ret;
 
-		/* Install a fence for tiled scan-out. Pre-i965 always needs a
+		/*
+		 * Install a fence for tiled scan-out. Pre-i965 always needs a
 		 * fence, whereas 965+ only requires a fence if using
 		 * framebuffer compression.  For simplicity, we always, when
 		 * possible, install a fence as the cost is not that onerous.
@@ -2180,8 +2288,6 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	i915_vma_get(vma);
 err:
 	atomic_dec(&dev_priv->gpu_error.pending_fb_pin);
-
-	i915_gem_object_unlock(obj);
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 	return vma;
 }
@@ -2216,7 +2322,7 @@ u32 intel_fb_xy_to_linear(int x, int y,
 			  const struct intel_plane_state *state,
 			  int color_plane)
 {
-	const struct drm_framebuffer *fb = state->base.fb;
+	const struct drm_framebuffer *fb = state->hw.fb;
 	unsigned int cpp = fb->format->cpp[color_plane];
 	unsigned int pitch = state->color_plane[color_plane].stride;
 
@@ -2264,9 +2370,10 @@ static u32 intel_adjust_tile_offset(int *x, int *y,
 	return new_offset;
 }
 
-static bool is_surface_linear(u64 modifier, int color_plane)
+static bool is_surface_linear(const struct drm_framebuffer *fb, int color_plane)
 {
-	return modifier == DRM_FORMAT_MOD_LINEAR;
+	return fb->modifier == DRM_FORMAT_MOD_LINEAR ||
+	       is_gen12_ccs_plane(fb, color_plane);
 }
 
 static u32 intel_adjust_aligned_offset(int *x, int *y,
@@ -2281,7 +2388,7 @@ static u32 intel_adjust_aligned_offset(int *x, int *y,
 
 	WARN_ON(new_offset > old_offset);
 
-	if (!is_surface_linear(fb->modifier, color_plane)) {
+	if (!is_surface_linear(fb, color_plane)) {
 		unsigned int tile_size, tile_width, tile_height;
 		unsigned int pitch_tiles;
 
@@ -2317,8 +2424,8 @@ static u32 intel_plane_adjust_aligned_offset(int *x, int *y,
 					     int color_plane,
 					     u32 old_offset, u32 new_offset)
 {
-	return intel_adjust_aligned_offset(x, y, state->base.fb, color_plane,
-					   state->base.rotation,
+	return intel_adjust_aligned_offset(x, y, state->hw.fb, color_plane,
+					   state->hw.rotation,
 					   state->color_plane[color_plane].stride,
 					   old_offset, new_offset);
 }
@@ -2348,10 +2455,7 @@ static u32 intel_compute_aligned_offset(struct drm_i915_private *dev_priv,
 	unsigned int cpp = fb->format->cpp[color_plane];
 	u32 offset, offset_aligned;
 
-	if (alignment)
-		alignment--;
-
-	if (!is_surface_linear(fb->modifier, color_plane)) {
+	if (!is_surface_linear(fb, color_plane)) {
 		unsigned int tile_size, tile_width, tile_height;
 		unsigned int tile_rows, tiles, pitch_tiles;
 
@@ -2372,17 +2476,24 @@ static u32 intel_compute_aligned_offset(struct drm_i915_private *dev_priv,
 		*x %= tile_width;
 
 		offset = (tile_rows * pitch_tiles + tiles) * tile_size;
-		offset_aligned = offset & ~alignment;
+
+		offset_aligned = offset;
+		if (alignment)
+			offset_aligned = rounddown(offset_aligned, alignment);
 
 		intel_adjust_tile_offset(x, y, tile_width, tile_height,
 					 tile_size, pitch_tiles,
 					 offset, offset_aligned);
 	} else {
 		offset = *y * pitch + *x * cpp;
-		offset_aligned = offset & ~alignment;
-
-		*y = (offset & alignment) / pitch;
-		*x = ((offset & alignment) - *y * pitch) / cpp;
+		offset_aligned = offset;
+		if (alignment) {
+			offset_aligned = rounddown(offset_aligned, alignment);
+			*y = (offset % alignment) / pitch;
+			*x = ((offset % alignment) - *y * pitch) / cpp;
+		} else {
+			*y = *x = 0;
+		}
 	}
 
 	return offset_aligned;
@@ -2392,10 +2503,10 @@ static u32 intel_plane_compute_aligned_offset(int *x, int *y,
 					      const struct intel_plane_state *state,
 					      int color_plane)
 {
-	struct intel_plane *intel_plane = to_intel_plane(state->base.plane);
+	struct intel_plane *intel_plane = to_intel_plane(state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev);
-	const struct drm_framebuffer *fb = state->base.fb;
-	unsigned int rotation = state->base.rotation;
+	const struct drm_framebuffer *fb = state->hw.fb;
+	unsigned int rotation = state->hw.rotation;
 	int pitch = state->color_plane[color_plane].stride;
 	u32 alignment;
 
@@ -2415,9 +2526,17 @@ static int intel_fb_offset_to_xy(int *x, int *y,
 {
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
 	unsigned int height;
+	u32 alignment;
+
+	if (INTEL_GEN(dev_priv) >= 12 &&
+	    is_semiplanar_uv_plane(fb, color_plane))
+		alignment = intel_tile_row_size(fb, color_plane);
+	else if (fb->modifier != DRM_FORMAT_MOD_LINEAR)
+		alignment = intel_tile_size(dev_priv);
+	else
+		alignment = 0;
 
-	if (fb->modifier != DRM_FORMAT_MOD_LINEAR &&
-	    fb->offsets[color_plane] % intel_tile_size(dev_priv)) {
+	if (alignment != 0 && fb->offsets[color_plane] % alignment) {
 		DRM_DEBUG_KMS("Misaligned offset 0x%08x for color plane %d\n",
 			      fb->offsets[color_plane], color_plane);
 		return -EINVAL;
@@ -2453,6 +2572,8 @@ static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier)
 		return I915_TILING_X;
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		return I915_TILING_Y;
 	default:
 		return I915_TILING_NONE;
@@ -2473,7 +2594,7 @@ static unsigned int intel_fb_modifier_to_tiling(u64 fb_modifier)
  * us a ratio of one byte in the CCS for each 8x16 pixels in the
  * main surface.
  */
-static const struct drm_format_info ccs_formats[] = {
+static const struct drm_format_info skl_ccs_formats[] = {
 	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2,
 	  .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, },
 	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2,
@@ -2484,6 +2605,52 @@ static const struct drm_format_info ccs_formats[] = {
 	  .cpp = { 4, 1, }, .hsub = 8, .vsub = 16, .has_alpha = true, },
 };
 
+/*
+ * Gen-12 compression uses 4 bits of CCS data for each cache line pair in the
+ * main surface. And each 64B CCS cache line represents an area of 4x1 Y-tiles
+ * in the main surface. With 4 byte pixels and each Y-tile having dimensions of
+ * 32x32 pixels, the ratio turns out to 1B in the CCS for every 2x32 pixels in
+ * the main surface.
+ */
+static const struct drm_format_info gen12_ccs_formats[] = {
+	{ .format = DRM_FORMAT_XRGB8888, .depth = 24, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, },
+	{ .format = DRM_FORMAT_XBGR8888, .depth = 24, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, },
+	{ .format = DRM_FORMAT_ARGB8888, .depth = 32, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, .has_alpha = true },
+	{ .format = DRM_FORMAT_ABGR8888, .depth = 32, .num_planes = 2,
+	  .char_per_block = { 4, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 1, .vsub = 1, .has_alpha = true },
+	{ .format = DRM_FORMAT_YUYV, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_YVYU, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_UYVY, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_VYUY, .num_planes = 2,
+	  .char_per_block = { 2, 1 }, .block_w = { 1, 2 }, .block_h = { 1, 1 },
+	  .hsub = 2, .vsub = 1, .is_yuv = true },
+	{ .format = DRM_FORMAT_NV12, .num_planes = 4,
+	  .char_per_block = { 1, 2, 1, 1 }, .block_w = { 1, 1, 4, 4 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+	{ .format = DRM_FORMAT_P010, .num_planes = 4,
+	  .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+	{ .format = DRM_FORMAT_P012, .num_planes = 4,
+	  .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+	{ .format = DRM_FORMAT_P016, .num_planes = 4,
+	  .char_per_block = { 2, 4, 1, 1 }, .block_w = { 1, 1, 2, 2 }, .block_h = { 1, 1, 1, 1 },
+	  .hsub = 2, .vsub = 2, .is_yuv = true },
+};
+
 static const struct drm_format_info *
 lookup_format_info(const struct drm_format_info formats[],
 		   int num_formats, u32 format)
@@ -2504,8 +2671,13 @@ intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd)
 	switch (cmd->modifier[0]) {
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
-		return lookup_format_info(ccs_formats,
-					  ARRAY_SIZE(ccs_formats),
+		return lookup_format_info(skl_ccs_formats,
+					  ARRAY_SIZE(skl_ccs_formats),
+					  cmd->pixel_format);
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		return lookup_format_info(gen12_ccs_formats,
+					  ARRAY_SIZE(gen12_ccs_formats),
 					  cmd->pixel_format);
 	default:
 		return NULL;
@@ -2514,10 +2686,18 @@ intel_get_format_info(const struct drm_mode_fb_cmd2 *cmd)
 
 bool is_ccs_modifier(u64 modifier)
 {
-	return modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
+	return modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS ||
+	       modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 	       modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
 }
 
+static int gen12_ccs_aux_stride(struct drm_framebuffer *fb, int ccs_plane)
+{
+	return DIV_ROUND_UP(fb->pitches[ccs_to_main_plane(fb, ccs_plane)],
+			    512) * 64;
+}
+
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 			      u32 pixel_format, u64 modifier)
 {
@@ -2562,8 +2742,9 @@ static u32
 intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
+	u32 tile_width;
 
-	if (fb->modifier == DRM_FORMAT_MOD_LINEAR) {
+	if (is_surface_linear(fb, color_plane)) {
 		u32 max_stride = intel_plane_fb_max_stride(dev_priv,
 							   fb->format->format,
 							   fb->modifier);
@@ -2572,20 +2753,41 @@ intel_fb_stride_alignment(const struct drm_framebuffer *fb, int color_plane)
 		 * To make remapping with linear generally feasible
 		 * we need the stride to be page aligned.
 		 */
-		if (fb->pitches[color_plane] > max_stride)
+		if (fb->pitches[color_plane] > max_stride &&
+		    !is_ccs_modifier(fb->modifier))
 			return intel_tile_size(dev_priv);
 		else
 			return 64;
-	} else {
-		return intel_tile_width_bytes(fb, color_plane);
 	}
+
+	tile_width = intel_tile_width_bytes(fb, color_plane);
+	if (is_ccs_modifier(fb->modifier)) {
+		/*
+		 * Display WA #0531: skl,bxt,kbl,glk
+		 *
+		 * Render decompression and plane width > 3840
+		 * combined with horizontal panning requires the
+		 * plane stride to be a multiple of 4. We'll just
+		 * require the entire fb to accommodate that to avoid
+		 * potential runtime errors at plane configuration time.
+		 */
+		if (IS_GEN(dev_priv, 9) && color_plane == 0 && fb->width > 3840)
+			tile_width *= 4;
+		/*
+		 * The main surface pitch must be padded to a multiple of four
+		 * tile widths.
+		 */
+		else if (INTEL_GEN(dev_priv) >= 12)
+			tile_width *= 4;
+	}
+	return tile_width;
 }
 
 bool intel_plane_can_remap(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int i;
 
 	/* We don't want to deal with remapping with cursors */
@@ -2623,16 +2825,16 @@ bool intel_plane_can_remap(const struct intel_plane_state *plane_state)
 
 static bool intel_plane_needs_remap(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 stride, max_stride;
 
 	/*
 	 * No remapping for invisible planes since we don't have
 	 * an actual source viewport to remap.
 	 */
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return false;
 
 	if (!intel_plane_can_remap(plane_state))
@@ -2649,12 +2851,171 @@ static bool intel_plane_needs_remap(const struct intel_plane_state *plane_state)
 	return stride > max_stride;
 }
 
+static void
+intel_fb_plane_get_subsampling(int *hsub, int *vsub,
+			       const struct drm_framebuffer *fb,
+			       int color_plane)
+{
+	int main_plane;
+
+	if (color_plane == 0) {
+		*hsub = 1;
+		*vsub = 1;
+
+		return;
+	}
+
+	/*
+	 * TODO: Deduct the subsampling from the char block for all CCS
+	 * formats and planes.
+	 */
+	if (!is_gen12_ccs_plane(fb, color_plane)) {
+		*hsub = fb->format->hsub;
+		*vsub = fb->format->vsub;
+
+		return;
+	}
+
+	main_plane = ccs_to_main_plane(fb, color_plane);
+	*hsub = drm_format_info_block_width(fb->format, color_plane) /
+		drm_format_info_block_width(fb->format, main_plane);
+
+	/*
+	 * The min stride check in the core framebuffer_check() function
+	 * assumes that format->hsub applies to every plane except for the
+	 * first plane. That's incorrect for the CCS AUX plane of the first
+	 * plane, but for the above check to pass we must define the block
+	 * width with that subsampling applied to it. Adjust the width here
+	 * accordingly, so we can calculate the actual subsampling factor.
+	 */
+	if (main_plane == 0)
+		*hsub *= fb->format->hsub;
+
+	*vsub = 32;
+}
+static int
+intel_fb_check_ccs_xy(struct drm_framebuffer *fb, int ccs_plane, int x, int y)
+{
+	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	int main_plane;
+	int hsub, vsub;
+	int tile_width, tile_height;
+	int ccs_x, ccs_y;
+	int main_x, main_y;
+
+	if (!is_ccs_plane(fb, ccs_plane))
+		return 0;
+
+	intel_tile_dims(fb, ccs_plane, &tile_width, &tile_height);
+	intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane);
+
+	tile_width *= hsub;
+	tile_height *= vsub;
+
+	ccs_x = (x * hsub) % tile_width;
+	ccs_y = (y * vsub) % tile_height;
+
+	main_plane = ccs_to_main_plane(fb, ccs_plane);
+	main_x = intel_fb->normal[main_plane].x % tile_width;
+	main_y = intel_fb->normal[main_plane].y % tile_height;
+
+	/*
+	 * CCS doesn't have its own x/y offset register, so the intra CCS tile
+	 * x/y offsets must match between CCS and the main surface.
+	 */
+	if (main_x != ccs_x || main_y != ccs_y) {
+		DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
+			      main_x, main_y,
+			      ccs_x, ccs_y,
+			      intel_fb->normal[main_plane].x,
+			      intel_fb->normal[main_plane].y,
+			      x, y);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+intel_fb_plane_dims(int *w, int *h, struct drm_framebuffer *fb, int color_plane)
+{
+	int main_plane = is_ccs_plane(fb, color_plane) ?
+			 ccs_to_main_plane(fb, color_plane) : 0;
+	int main_hsub, main_vsub;
+	int hsub, vsub;
+
+	intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, fb, main_plane);
+	intel_fb_plane_get_subsampling(&hsub, &vsub, fb, color_plane);
+	*w = fb->width / main_hsub / hsub;
+	*h = fb->height / main_vsub / vsub;
+}
+
+/*
+ * Setup the rotated view for an FB plane and return the size the GTT mapping
+ * requires for this view.
+ */
+static u32
+setup_fb_rotation(int plane, const struct intel_remapped_plane_info *plane_info,
+		  u32 gtt_offset_rotated, int x, int y,
+		  unsigned int width, unsigned int height,
+		  unsigned int tile_size,
+		  unsigned int tile_width, unsigned int tile_height,
+		  struct drm_framebuffer *fb)
+{
+	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	struct intel_rotation_info *rot_info = &intel_fb->rot_info;
+	unsigned int pitch_tiles;
+	struct drm_rect r;
+
+	/* Y or Yf modifiers required for 90/270 rotation */
+	if (fb->modifier != I915_FORMAT_MOD_Y_TILED &&
+	    fb->modifier != I915_FORMAT_MOD_Yf_TILED)
+		return 0;
+
+	if (WARN_ON(plane >= ARRAY_SIZE(rot_info->plane)))
+		return 0;
+
+	rot_info->plane[plane] = *plane_info;
+
+	intel_fb->rotated[plane].pitch = plane_info->height * tile_height;
+
+	/* rotate the x/y offsets to match the GTT view */
+	drm_rect_init(&r, x, y, width, height);
+	drm_rect_rotate(&r,
+			plane_info->width * tile_width,
+			plane_info->height * tile_height,
+			DRM_MODE_ROTATE_270);
+	x = r.x1;
+	y = r.y1;
+
+	/* rotate the tile dimensions to match the GTT view */
+	pitch_tiles = intel_fb->rotated[plane].pitch / tile_height;
+	swap(tile_width, tile_height);
+
+	/*
+	 * We only keep the x/y offsets, so push all of the
+	 * gtt offset into the x/y offsets.
+	 */
+	intel_adjust_tile_offset(&x, &y,
+				 tile_width, tile_height,
+				 tile_size, pitch_tiles,
+				 gtt_offset_rotated * tile_size, 0);
+
+	/*
+	 * First pixel of the framebuffer from
+	 * the start of the rotated gtt mapping.
+	 */
+	intel_fb->rotated[plane].x = x;
+	intel_fb->rotated[plane].y = y;
+
+	return plane_info->width * plane_info->height;
+}
+
 static int
 intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		   struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
-	struct intel_rotation_info *rot_info = &intel_fb->rot_info;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 gtt_offset_rotated = 0;
 	unsigned int max_size = 0;
@@ -2669,8 +3030,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		int ret;
 
 		cpp = fb->format->cpp[i];
-		width = drm_framebuffer_plane_width(fb->width, fb, i);
-		height = drm_framebuffer_plane_height(fb->height, fb, i);
+		intel_fb_plane_dims(&width, &height, fb, i);
 
 		ret = intel_fb_offset_to_xy(&x, &y, fb, i);
 		if (ret) {
@@ -2679,36 +3039,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			return ret;
 		}
 
-		if (is_ccs_modifier(fb->modifier) && i == 1) {
-			int hsub = fb->format->hsub;
-			int vsub = fb->format->vsub;
-			int tile_width, tile_height;
-			int main_x, main_y;
-			int ccs_x, ccs_y;
-
-			intel_tile_dims(fb, i, &tile_width, &tile_height);
-			tile_width *= hsub;
-			tile_height *= vsub;
-
-			ccs_x = (x * hsub) % tile_width;
-			ccs_y = (y * vsub) % tile_height;
-			main_x = intel_fb->normal[0].x % tile_width;
-			main_y = intel_fb->normal[0].y % tile_height;
-
-			/*
-			 * CCS doesn't have its own x/y offset register, so the intra CCS tile
-			 * x/y offsets must match between CCS and the main surface.
-			 */
-			if (main_x != ccs_x || main_y != ccs_y) {
-				DRM_DEBUG_KMS("Bad CCS x/y (main %d,%d ccs %d,%d) full (main %d,%d ccs %d,%d)\n",
-					      main_x, main_y,
-					      ccs_x, ccs_y,
-					      intel_fb->normal[0].x,
-					      intel_fb->normal[0].y,
-					      x, y);
-				return -EINVAL;
-			}
-		}
+		ret = intel_fb_check_ccs_xy(fb, i, x, y);
+		if (ret)
+			return ret;
 
 		/*
 		 * The fence (if used) is aligned to the start of the object
@@ -2739,23 +3072,21 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 						      tile_size);
 		offset /= tile_size;
 
-		if (!is_surface_linear(fb->modifier, i)) {
+		if (!is_surface_linear(fb, i)) {
+			struct intel_remapped_plane_info plane_info;
 			unsigned int tile_width, tile_height;
-			unsigned int pitch_tiles;
-			struct drm_rect r;
 
 			intel_tile_dims(fb, i, &tile_width, &tile_height);
 
-			rot_info->plane[i].offset = offset;
-			rot_info->plane[i].stride = DIV_ROUND_UP(fb->pitches[i], tile_width * cpp);
-			rot_info->plane[i].width = DIV_ROUND_UP(x + width, tile_width);
-			rot_info->plane[i].height = DIV_ROUND_UP(y + height, tile_height);
-
-			intel_fb->rotated[i].pitch =
-				rot_info->plane[i].height * tile_height;
+			plane_info.offset = offset;
+			plane_info.stride = DIV_ROUND_UP(fb->pitches[i],
+							 tile_width * cpp);
+			plane_info.width = DIV_ROUND_UP(x + width, tile_width);
+			plane_info.height = DIV_ROUND_UP(y + height,
+							 tile_height);
 
 			/* how many tiles does this plane need */
-			size = rot_info->plane[i].stride * rot_info->plane[i].height;
+			size = plane_info.stride * plane_info.height;
 			/*
 			 * If the plane isn't horizontally tile aligned,
 			 * we need one more tile.
@@ -2763,36 +3094,13 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			if (x != 0)
 				size++;
 
-			/* rotate the x/y offsets to match the GTT view */
-			drm_rect_init(&r, x, y, width, height);
-			drm_rect_rotate(&r,
-					rot_info->plane[i].width * tile_width,
-					rot_info->plane[i].height * tile_height,
-					DRM_MODE_ROTATE_270);
-			x = r.x1;
-			y = r.y1;
-
-			/* rotate the tile dimensions to match the GTT view */
-			pitch_tiles = intel_fb->rotated[i].pitch / tile_height;
-			swap(tile_width, tile_height);
-
-			/*
-			 * We only keep the x/y offsets, so push all of the
-			 * gtt offset into the x/y offsets.
-			 */
-			intel_adjust_tile_offset(&x, &y,
-						 tile_width, tile_height,
-						 tile_size, pitch_tiles,
-						 gtt_offset_rotated * tile_size, 0);
-
-			gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height;
-
-			/*
-			 * First pixel of the framebuffer from
-			 * the start of the rotated gtt mapping.
-			 */
-			intel_fb->rotated[i].x = x;
-			intel_fb->rotated[i].y = y;
+			gtt_offset_rotated +=
+				setup_fb_rotation(i, &plane_info,
+						  gtt_offset_rotated,
+						  x, y, width, height,
+						  tile_size,
+						  tile_width, tile_height,
+						  fb);
 		} else {
 			size = DIV_ROUND_UP((y + height) * fb->pitches[i] +
 					    x * cpp, tile_size);
@@ -2815,11 +3123,11 @@ static void
 intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 	struct intel_rotation_info *info = &plane_state->view.rotated;
-	unsigned int rotation = plane_state->base.rotation;
+	unsigned int rotation = plane_state->hw.rotation;
 	int i, num_planes = fb->format->num_planes;
 	unsigned int tile_size = intel_tile_size(dev_priv);
 	unsigned int src_x, src_y;
@@ -2830,20 +3138,20 @@ intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 	plane_state->view.type = drm_rotation_90_or_270(rotation) ?
 		I915_GGTT_VIEW_ROTATED : I915_GGTT_VIEW_REMAPPED;
 
-	src_x = plane_state->base.src.x1 >> 16;
-	src_y = plane_state->base.src.y1 >> 16;
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	src_x = plane_state->uapi.src.x1 >> 16;
+	src_y = plane_state->uapi.src.y1 >> 16;
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 	WARN_ON(is_ccs_modifier(fb->modifier));
 
 	/* Make src coordinates relative to the viewport */
-	drm_rect_translate(&plane_state->base.src,
+	drm_rect_translate(&plane_state->uapi.src,
 			   -(src_x << 16), -(src_y << 16));
 
 	/* Rotate src coordinates to match rotated GTT view */
 	if (drm_rotation_90_or_270(rotation))
-		drm_rect_rotate(&plane_state->base.src,
+		drm_rect_rotate(&plane_state->uapi.src,
 				src_w << 16, src_h << 16,
 				DRM_MODE_ROTATE_270);
 
@@ -2876,6 +3184,7 @@ intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 						      DRM_MODE_ROTATE_0, tile_size);
 		offset /= tile_size;
 
+		WARN_ON(i >= ARRAY_SIZE(info->plane));
 		info->plane[i].offset = offset;
 		info->plane[i].stride = DIV_ROUND_UP(fb->pitches[i],
 						     tile_width * cpp);
@@ -2925,8 +3234,8 @@ static int
 intel_plane_compute_gtt(struct intel_plane_state *plane_state)
 {
 	const struct intel_framebuffer *fb =
-		to_intel_framebuffer(plane_state->base.fb);
-	unsigned int rotation = plane_state->base.rotation;
+		to_intel_framebuffer(plane_state->hw.fb);
+	unsigned int rotation = plane_state->hw.rotation;
 	int i, num_planes;
 
 	if (!fb)
@@ -2963,7 +3272,7 @@ intel_plane_compute_gtt(struct intel_plane_state *plane_state)
 
 	/* Rotate src coordinates to match rotated GTT view */
 	if (drm_rotation_90_or_270(rotation))
-		drm_rect_rotate(&plane_state->base.src,
+		drm_rect_rotate(&plane_state->uapi.src,
 				fb->base.width << 16, fb->base.height << 16,
 				DRM_MODE_ROTATE_270);
 
@@ -2975,6 +3284,8 @@ static int i9xx_format_to_fourcc(int format)
 	switch (format) {
 	case DISPPLANE_8BPP:
 		return DRM_FORMAT_C8;
+	case DISPPLANE_BGRA555:
+		return DRM_FORMAT_ARGB1555;
 	case DISPPLANE_BGRX555:
 		return DRM_FORMAT_XRGB1555;
 	case DISPPLANE_BGRX565:
@@ -2984,10 +3295,18 @@ static int i9xx_format_to_fourcc(int format)
 		return DRM_FORMAT_XRGB8888;
 	case DISPPLANE_RGBX888:
 		return DRM_FORMAT_XBGR8888;
+	case DISPPLANE_BGRA888:
+		return DRM_FORMAT_ARGB8888;
+	case DISPPLANE_RGBA888:
+		return DRM_FORMAT_ABGR8888;
 	case DISPPLANE_BGRX101010:
 		return DRM_FORMAT_XRGB2101010;
 	case DISPPLANE_RGBX101010:
 		return DRM_FORMAT_XBGR2101010;
+	case DISPPLANE_BGRA101010:
+		return DRM_FORMAT_ARGB2101010;
+	case DISPPLANE_RGBA101010:
+		return DRM_FORMAT_ABGR2101010;
 	case DISPPLANE_RGBX161616:
 		return DRM_FORMAT_XBGR16161616F;
 	}
@@ -3032,10 +3351,17 @@ int skl_format_to_fourcc(int format, bool rgb_order, bool alpha)
 				return DRM_FORMAT_XRGB8888;
 		}
 	case PLANE_CTL_FORMAT_XRGB_2101010:
-		if (rgb_order)
-			return DRM_FORMAT_XBGR2101010;
-		else
-			return DRM_FORMAT_XRGB2101010;
+		if (rgb_order) {
+			if (alpha)
+				return DRM_FORMAT_ABGR2101010;
+			else
+				return DRM_FORMAT_XBGR2101010;
+		} else {
+			if (alpha)
+				return DRM_FORMAT_ARGB2101010;
+			else
+				return DRM_FORMAT_XRGB2101010;
+		}
 	case PLANE_CTL_FORMAT_XRGB_16161616F:
 		if (rgb_order) {
 			if (alpha)
@@ -3131,19 +3457,19 @@ intel_set_plane_visible(struct intel_crtc_state *crtc_state,
 			struct intel_plane_state *plane_state,
 			bool visible)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
-	plane_state->base.visible = visible;
+	plane_state->uapi.visible = visible;
 
 	if (visible)
-		crtc_state->base.plane_mask |= drm_plane_mask(&plane->base);
+		crtc_state->uapi.plane_mask |= drm_plane_mask(&plane->base);
 	else
-		crtc_state->base.plane_mask &= ~drm_plane_mask(&plane->base);
+		crtc_state->uapi.plane_mask &= ~drm_plane_mask(&plane->base);
 }
 
 static void fixup_active_planes(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	struct drm_plane *plane;
 
 	/*
@@ -3154,13 +3480,14 @@ static void fixup_active_planes(struct intel_crtc_state *crtc_state)
 	crtc_state->active_planes = 0;
 
 	drm_for_each_plane_mask(plane, &dev_priv->drm,
-				crtc_state->base.plane_mask)
+				crtc_state->uapi.plane_mask)
 		crtc_state->active_planes |= BIT(to_intel_plane(plane)->id);
 }
 
 static void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 					 struct intel_plane *plane)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *crtc_state =
 		to_intel_crtc_state(crtc->base.state);
 	struct intel_plane_state *plane_state =
@@ -3176,7 +3503,27 @@ static void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 	crtc_state->min_cdclk[plane->id] = 0;
 
 	if (plane->id == PLANE_PRIMARY)
-		intel_pre_disable_primary_noatomic(&crtc->base);
+		hsw_disable_ips(crtc_state);
+
+	/*
+	 * Vblank time updates from the shadow to live plane control register
+	 * are blocked if the memory self-refresh mode is active at that
+	 * moment. So to make sure the plane gets truly disabled, disable
+	 * first the self-refresh mode. The self-refresh enable bit in turn
+	 * will be checked/applied by the HW only at the next frame start
+	 * event which is after the vblank start event, so we need to have a
+	 * wait-for-vblank between disabling the plane and the pipe.
+	 */
+	if (HAS_GMCH(dev_priv) &&
+	    intel_set_memory_cxsr(dev_priv, false))
+		intel_wait_for_vblank(dev_priv, crtc->pipe);
+
+	/*
+	 * Gen2 reports pipe underruns whenever all planes are disabled.
+	 * So disable underrun reporting before all the planes get disabled.
+	 */
+	if (IS_GEN(dev_priv, 2) && !crtc_state->active_planes)
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
 
 	intel_disable_plane(plane, crtc_state);
 }
@@ -3229,7 +3576,7 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 			continue;
 
 		if (intel_plane_ggtt_offset(state) == plane_config->base) {
-			fb = state->base.fb;
+			fb = state->hw.fb;
 			drm_framebuffer_get(fb);
 			goto valid_fb;
 		}
@@ -3247,11 +3594,11 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	return;
 
 valid_fb:
-	intel_state->base.rotation = plane_config->rotation;
+	intel_state->hw.rotation = plane_config->rotation;
 	intel_fill_fb_ggtt_view(&intel_state->view, fb,
-				intel_state->base.rotation);
+				intel_state->hw.rotation);
 	intel_state->color_plane[0].stride =
-		intel_fb_pitch(fb, 0, intel_state->base.rotation);
+		intel_fb_pitch(fb, 0, intel_state->hw.rotation);
 
 	intel_state->vma =
 		intel_pin_and_fence_fb_obj(fb,
@@ -3279,14 +3626,15 @@ valid_fb:
 	plane_state->crtc_w = fb->width;
 	plane_state->crtc_h = fb->height;
 
-	intel_state->base.src = drm_plane_state_src(plane_state);
-	intel_state->base.dst = drm_plane_state_dest(plane_state);
+	intel_state->uapi.src = drm_plane_state_src(plane_state);
+	intel_state->uapi.dst = drm_plane_state_dest(plane_state);
 
 	if (plane_config->tiling)
 		dev_priv->preserve_bios_swizzle = true;
 
 	plane_state->fb = fb;
 	plane_state->crtc = &intel_crtc->base;
+	intel_plane_copy_uapi_to_hw_state(intel_state, intel_state);
 
 	atomic_or(to_intel_plane(primary)->frontbuffer_bit,
 		  &to_intel_frontbuffer(fb)->bits);
@@ -3317,6 +3665,7 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
 			return 5120;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
 		/* FIXME AUX plane? */
 	case I915_FORMAT_MOD_Y_TILED:
 	case I915_FORMAT_MOD_Yf_TILED:
@@ -3375,17 +3724,20 @@ static int icl_max_plane_height(void)
 	return 4320;
 }
 
-static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
-					   int main_x, int main_y, u32 main_offset)
-{
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	int hsub = fb->format->hsub;
-	int vsub = fb->format->vsub;
-	int aux_x = plane_state->color_plane[1].x;
-	int aux_y = plane_state->color_plane[1].y;
-	u32 aux_offset = plane_state->color_plane[1].offset;
-	u32 alignment = intel_surf_alignment(fb, 1);
-
+static bool
+skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
+			       int main_x, int main_y, u32 main_offset,
+			       int ccs_plane)
+{
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	int aux_x = plane_state->color_plane[ccs_plane].x;
+	int aux_y = plane_state->color_plane[ccs_plane].y;
+	u32 aux_offset = plane_state->color_plane[ccs_plane].offset;
+	u32 alignment = intel_surf_alignment(fb, ccs_plane);
+	int hsub;
+	int vsub;
+
+	intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane);
 	while (aux_offset >= main_offset && aux_y <= main_y) {
 		int x, y;
 
@@ -3397,8 +3749,12 @@ static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state
 
 		x = aux_x / hsub;
 		y = aux_y / vsub;
-		aux_offset = intel_plane_adjust_aligned_offset(&x, &y, plane_state, 1,
-							       aux_offset, aux_offset - alignment);
+		aux_offset = intel_plane_adjust_aligned_offset(&x, &y,
+							       plane_state,
+							       ccs_plane,
+							       aux_offset,
+							       aux_offset -
+								alignment);
 		aux_x = x * hsub + aux_x % hsub;
 		aux_y = y * vsub + aux_y % vsub;
 	}
@@ -3406,25 +3762,28 @@ static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state
 	if (aux_x != main_x || aux_y != main_y)
 		return false;
 
-	plane_state->color_plane[1].offset = aux_offset;
-	plane_state->color_plane[1].x = aux_x;
-	plane_state->color_plane[1].y = aux_y;
+	plane_state->color_plane[ccs_plane].offset = aux_offset;
+	plane_state->color_plane[ccs_plane].x = aux_x;
+	plane_state->color_plane[ccs_plane].y = aux_y;
 
 	return true;
 }
 
 static int skl_check_main_surface(struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
-	int x = plane_state->base.src.x1 >> 16;
-	int y = plane_state->base.src.y1 >> 16;
-	int w = drm_rect_width(&plane_state->base.src) >> 16;
-	int h = drm_rect_height(&plane_state->base.src) >> 16;
+	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
+	int x = plane_state->uapi.src.x1 >> 16;
+	int y = plane_state->uapi.src.y1 >> 16;
+	int w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	int h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	int max_width;
 	int max_height;
-	u32 alignment, offset, aux_offset = plane_state->color_plane[1].offset;
+	u32 alignment;
+	u32 offset;
+	int aux_plane = intel_main_to_aux_plane(fb, 0);
+	u32 aux_offset = plane_state->color_plane[aux_plane].offset;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		max_width = icl_max_plane_width(fb, 0, rotation);
@@ -3447,6 +3806,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	intel_add_fb_offsets(&x, &y, plane_state, 0);
 	offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, 0);
 	alignment = intel_surf_alignment(fb, 0);
+	if (WARN_ON(alignment && !is_power_of_2(alignment)))
+		return -EINVAL;
 
 	/*
 	 * AUX surface offset is specified as the distance from the
@@ -3482,7 +3843,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	 * they match with the main surface x/y offsets.
 	 */
 	if (is_ccs_modifier(fb->modifier)) {
-		while (!skl_check_main_ccs_coordinates(plane_state, x, y, offset)) {
+		while (!skl_check_main_ccs_coordinates(plane_state, x, y,
+						       offset, aux_plane)) {
 			if (offset == 0)
 				break;
 
@@ -3490,7 +3852,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 								   offset, offset - alignment);
 		}
 
-		if (x != plane_state->color_plane[1].x || y != plane_state->color_plane[1].y) {
+		if (x != plane_state->color_plane[aux_plane].x ||
+		    y != plane_state->color_plane[aux_plane].y) {
 			DRM_DEBUG_KMS("Unable to find suitable display surface offset due to CCS\n");
 			return -EINVAL;
 		}
@@ -3504,7 +3867,7 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate_to(&plane_state->base.src,
+	drm_rect_translate_to(&plane_state->uapi.src,
 			      x << 16, y << 16);
 
 	return 0;
@@ -3512,18 +3875,20 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 
 static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
-	int max_width = skl_max_plane_width(fb, 1, rotation);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
+	int uv_plane = 1;
+	int max_width = skl_max_plane_width(fb, uv_plane, rotation);
 	int max_height = 4096;
-	int x = plane_state->base.src.x1 >> 17;
-	int y = plane_state->base.src.y1 >> 17;
-	int w = drm_rect_width(&plane_state->base.src) >> 17;
-	int h = drm_rect_height(&plane_state->base.src) >> 17;
+	int x = plane_state->uapi.src.x1 >> 17;
+	int y = plane_state->uapi.src.y1 >> 17;
+	int w = drm_rect_width(&plane_state->uapi.src) >> 17;
+	int h = drm_rect_height(&plane_state->uapi.src) >> 17;
 	u32 offset;
 
-	intel_add_fb_offsets(&x, &y, plane_state, 1);
-	offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, 1);
+	intel_add_fb_offsets(&x, &y, plane_state, uv_plane);
+	offset = intel_plane_compute_aligned_offset(&x, &y,
+						    plane_state, uv_plane);
 
 	/* FIXME not quite sure how/if these apply to the chroma plane */
 	if (w > max_width || h > max_height) {
@@ -3532,62 +3897,126 @@ static int skl_check_nv12_aux_surface(struct intel_plane_state *plane_state)
 		return -EINVAL;
 	}
 
-	plane_state->color_plane[1].offset = offset;
-	plane_state->color_plane[1].x = x;
-	plane_state->color_plane[1].y = y;
+	if (is_ccs_modifier(fb->modifier)) {
+		int ccs_plane = main_to_ccs_plane(fb, uv_plane);
+		int aux_offset = plane_state->color_plane[ccs_plane].offset;
+		int alignment = intel_surf_alignment(fb, uv_plane);
+
+		if (offset > aux_offset)
+			offset = intel_plane_adjust_aligned_offset(&x, &y,
+								   plane_state,
+								   uv_plane,
+								   offset,
+								   aux_offset & ~(alignment - 1));
+
+		while (!skl_check_main_ccs_coordinates(plane_state, x, y,
+						       offset, ccs_plane)) {
+			if (offset == 0)
+				break;
+
+			offset = intel_plane_adjust_aligned_offset(&x, &y,
+								   plane_state,
+								   uv_plane,
+								   offset, offset - alignment);
+		}
+
+		if (x != plane_state->color_plane[ccs_plane].x ||
+		    y != plane_state->color_plane[ccs_plane].y) {
+			DRM_DEBUG_KMS("Unable to find suitable display surface offset due to CCS\n");
+			return -EINVAL;
+		}
+	}
+
+	plane_state->color_plane[uv_plane].offset = offset;
+	plane_state->color_plane[uv_plane].x = x;
+	plane_state->color_plane[uv_plane].y = y;
 
 	return 0;
 }
 
 static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	int src_x = plane_state->base.src.x1 >> 16;
-	int src_y = plane_state->base.src.y1 >> 16;
-	int hsub = fb->format->hsub;
-	int vsub = fb->format->vsub;
-	int x = src_x / hsub;
-	int y = src_y / vsub;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	int src_x = plane_state->uapi.src.x1 >> 16;
+	int src_y = plane_state->uapi.src.y1 >> 16;
 	u32 offset;
+	int ccs_plane;
+
+	for (ccs_plane = 0; ccs_plane < fb->format->num_planes; ccs_plane++) {
+		int main_hsub, main_vsub;
+		int hsub, vsub;
+		int x, y;
+
+		if (!is_ccs_plane(fb, ccs_plane))
+			continue;
+
+		intel_fb_plane_get_subsampling(&main_hsub, &main_vsub, fb,
+					       ccs_to_main_plane(fb, ccs_plane));
+		intel_fb_plane_get_subsampling(&hsub, &vsub, fb, ccs_plane);
+
+		hsub *= main_hsub;
+		vsub *= main_vsub;
+		x = src_x / hsub;
+		y = src_y / vsub;
 
-	intel_add_fb_offsets(&x, &y, plane_state, 1);
-	offset = intel_plane_compute_aligned_offset(&x, &y, plane_state, 1);
+		intel_add_fb_offsets(&x, &y, plane_state, ccs_plane);
 
-	plane_state->color_plane[1].offset = offset;
-	plane_state->color_plane[1].x = x * hsub + src_x % hsub;
-	plane_state->color_plane[1].y = y * vsub + src_y % vsub;
+		offset = intel_plane_compute_aligned_offset(&x, &y,
+							    plane_state,
+							    ccs_plane);
+
+		plane_state->color_plane[ccs_plane].offset = offset;
+		plane_state->color_plane[ccs_plane].x = (x * hsub +
+							 src_x % hsub) /
+							main_hsub;
+		plane_state->color_plane[ccs_plane].y = (y * vsub +
+							 src_y % vsub) /
+							main_vsub;
+	}
 
 	return 0;
 }
 
 int skl_check_plane_surface(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
+	bool needs_aux = false;
 
 	ret = intel_plane_compute_gtt(plane_state);
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	/*
-	 * Handle the AUX surface first since
-	 * the main surface setup depends on it.
+	 * Handle the AUX surface first since the main surface setup depends on
+	 * it.
 	 */
-	if (drm_format_info_is_yuv_semiplanar(fb->format)) {
-		ret = skl_check_nv12_aux_surface(plane_state);
+	if (is_ccs_modifier(fb->modifier)) {
+		needs_aux = true;
+		ret = skl_check_ccs_aux_surface(plane_state);
 		if (ret)
 			return ret;
-	} else if (is_ccs_modifier(fb->modifier)) {
-		ret = skl_check_ccs_aux_surface(plane_state);
+	}
+
+	if (intel_format_info_is_yuv_semiplanar(fb->format,
+						fb->modifier)) {
+		needs_aux = true;
+		ret = skl_check_nv12_aux_surface(plane_state);
 		if (ret)
 			return ret;
-	} else {
-		plane_state->color_plane[1].offset = ~0xfff;
-		plane_state->color_plane[1].x = 0;
-		plane_state->color_plane[1].y = 0;
+	}
+
+	if (!needs_aux) {
+		int i;
+
+		for (i = 1; i < fb->format->num_planes; i++) {
+			plane_state->color_plane[i].offset = ~0xfff;
+			plane_state->color_plane[i].x = 0;
+			plane_state->color_plane[i].y = 0;
+		}
 	}
 
 	ret = skl_check_main_surface(plane_state);
@@ -3601,7 +4030,7 @@ static void i9xx_plane_ratio(const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state,
 			     unsigned int *num, unsigned int *den)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	/*
@@ -3673,7 +4102,7 @@ i9xx_plane_max_stride(struct intel_plane *plane,
 
 static u32 i9xx_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 dspcntr = 0;
 
@@ -3693,9 +4122,9 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 dspcntr;
 
 	dspcntr = DISPLAY_PLANE_ENABLE;
@@ -3711,6 +4140,9 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB1555:
 		dspcntr |= DISPPLANE_BGRX555;
 		break;
+	case DRM_FORMAT_ARGB1555:
+		dspcntr |= DISPPLANE_BGRA555;
+		break;
 	case DRM_FORMAT_RGB565:
 		dspcntr |= DISPPLANE_BGRX565;
 		break;
@@ -3720,12 +4152,24 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XBGR8888:
 		dspcntr |= DISPPLANE_RGBX888;
 		break;
+	case DRM_FORMAT_ARGB8888:
+		dspcntr |= DISPPLANE_BGRA888;
+		break;
+	case DRM_FORMAT_ABGR8888:
+		dspcntr |= DISPPLANE_RGBA888;
+		break;
 	case DRM_FORMAT_XRGB2101010:
 		dspcntr |= DISPPLANE_BGRX101010;
 		break;
 	case DRM_FORMAT_XBGR2101010:
 		dspcntr |= DISPPLANE_RGBX101010;
 		break;
+	case DRM_FORMAT_ARGB2101010:
+		dspcntr |= DISPPLANE_BGRA101010;
+		break;
+	case DRM_FORMAT_ABGR2101010:
+		dspcntr |= DISPPLANE_RGBA101010;
+		break;
 	case DRM_FORMAT_XBGR16161616F:
 		dspcntr |= DISPPLANE_RGBX161616;
 		break;
@@ -3750,8 +4194,8 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int src_x, src_y, src_w;
 	u32 offset;
 	int ret;
@@ -3760,12 +4204,12 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_x = plane_state->base.src.x1 >> 16;
-	src_y = plane_state->base.src.y1 >> 16;
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_x = plane_state->uapi.src.x1 >> 16;
+	src_y = plane_state->uapi.src.y1 >> 16;
 
 	/* Undocumented hardware limit on i965/g4x/vlv/chv */
 	if (HAS_GMCH(dev_priv) && fb->format->cpp[0] == 8 && src_w > 2048)
@@ -3783,14 +4227,14 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate_to(&plane_state->base.src,
+	drm_rect_translate_to(&plane_state->uapi.src,
 			      src_x << 16, src_y << 16);
 
 	/* HSW/BDW do this automagically in hardware */
 	if (!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv)) {
-		unsigned int rotation = plane_state->base.rotation;
-		int src_w = drm_rect_width(&plane_state->base.src) >> 16;
-		int src_h = drm_rect_height(&plane_state->base.src) >> 16;
+		unsigned int rotation = plane_state->hw.rotation;
+		int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+		int src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 		if (rotation & DRM_MODE_ROTATE_180) {
 			src_x += src_w - 1;
@@ -3827,15 +4271,15 @@ static int
 i9xx_plane_check(struct intel_crtc_state *crtc_state,
 		 struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	int ret;
 
 	ret = chv_plane_check_rotation(plane_state);
 	if (ret)
 		return ret;
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  i9xx_plane_has_windowing(plane),
@@ -3847,7 +4291,7 @@ i9xx_plane_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -3868,10 +4312,10 @@ static void i9xx_update_plane(struct intel_plane *plane,
 	u32 linear_offset;
 	int x = plane_state->color_plane[0].x;
 	int y = plane_state->color_plane[0].y;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	int crtc_w = drm_rect_width(&plane_state->base.dst);
-	int crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	int crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	int crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	unsigned long irqflags;
 	u32 dspaddr_offset;
 	u32 dspcntr;
@@ -4011,7 +4455,7 @@ static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
  */
 static void skl_detach_scalers(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	int i;
@@ -4030,7 +4474,7 @@ static unsigned int skl_plane_stride_mult(const struct drm_framebuffer *fb,
 	 * The stride is either expressed as a multiple of 64 bytes chunks for
 	 * linear buffers or in number of tiles for tiled buffers.
 	 */
-	if (fb->modifier == DRM_FORMAT_MOD_LINEAR)
+	if (is_surface_linear(fb, color_plane))
 		return 64;
 	else if (drm_rotation_90_or_270(rotation))
 		return intel_tile_height(fb, color_plane);
@@ -4041,8 +4485,8 @@ static unsigned int skl_plane_stride_mult(const struct drm_framebuffer *fb,
 u32 skl_plane_stride(const struct intel_plane_state *plane_state,
 		     int color_plane)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 stride = plane_state->color_plane[color_plane].stride;
 
 	if (color_plane >= fb->format->num_planes)
@@ -4065,8 +4509,10 @@ static u32 skl_plane_ctl_format(u32 pixel_format)
 	case DRM_FORMAT_ARGB8888:
 		return PLANE_CTL_FORMAT_XRGB_8888;
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ABGR2101010:
 		return PLANE_CTL_FORMAT_XRGB_2101010 | PLANE_CTL_ORDER_RGBX;
 	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
 		return PLANE_CTL_FORMAT_XRGB_2101010;
 	case DRM_FORMAT_XBGR16161616F:
 	case DRM_FORMAT_ABGR16161616F:
@@ -4111,10 +4557,10 @@ static u32 skl_plane_ctl_format(u32 pixel_format)
 
 static u32 skl_plane_ctl_alpha(const struct intel_plane_state *plane_state)
 {
-	if (!plane_state->base.fb->format->has_alpha)
+	if (!plane_state->hw.fb->format->has_alpha)
 		return PLANE_CTL_ALPHA_DISABLE;
 
-	switch (plane_state->base.pixel_blend_mode) {
+	switch (plane_state->hw.pixel_blend_mode) {
 	case DRM_MODE_BLEND_PIXEL_NONE:
 		return PLANE_CTL_ALPHA_DISABLE;
 	case DRM_MODE_BLEND_PREMULTI:
@@ -4122,17 +4568,17 @@ static u32 skl_plane_ctl_alpha(const struct intel_plane_state *plane_state)
 	case DRM_MODE_BLEND_COVERAGE:
 		return PLANE_CTL_ALPHA_HW_PREMULTIPLY;
 	default:
-		MISSING_CASE(plane_state->base.pixel_blend_mode);
+		MISSING_CASE(plane_state->hw.pixel_blend_mode);
 		return PLANE_CTL_ALPHA_DISABLE;
 	}
 }
 
 static u32 glk_plane_color_ctl_alpha(const struct intel_plane_state *plane_state)
 {
-	if (!plane_state->base.fb->format->has_alpha)
+	if (!plane_state->hw.fb->format->has_alpha)
 		return PLANE_COLOR_ALPHA_DISABLE;
 
-	switch (plane_state->base.pixel_blend_mode) {
+	switch (plane_state->hw.pixel_blend_mode) {
 	case DRM_MODE_BLEND_PIXEL_NONE:
 		return PLANE_COLOR_ALPHA_DISABLE;
 	case DRM_MODE_BLEND_PREMULTI:
@@ -4140,7 +4586,7 @@ static u32 glk_plane_color_ctl_alpha(const struct intel_plane_state *plane_state
 	case DRM_MODE_BLEND_COVERAGE:
 		return PLANE_COLOR_ALPHA_HW_PREMULTIPLY;
 	default:
-		MISSING_CASE(plane_state->base.pixel_blend_mode);
+		MISSING_CASE(plane_state->hw.pixel_blend_mode);
 		return PLANE_COLOR_ALPHA_DISABLE;
 	}
 }
@@ -4156,6 +4602,12 @@ static u32 skl_plane_ctl_tiling(u64 fb_modifier)
 		return PLANE_CTL_TILED_Y;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 		return PLANE_CTL_TILED_Y | PLANE_CTL_RENDER_DECOMPRESSION_ENABLE;
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
+		return PLANE_CTL_TILED_Y |
+		       PLANE_CTL_RENDER_DECOMPRESSION_ENABLE |
+		       PLANE_CTL_CLEAR_COLOR_DISABLE;
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		return PLANE_CTL_TILED_Y | PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE;
 	case I915_FORMAT_MOD_Yf_TILED:
 		return PLANE_CTL_TILED_YF;
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
@@ -4206,7 +4658,7 @@ static u32 cnl_plane_ctl_flip(unsigned int reflect)
 
 u32 skl_plane_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 plane_ctl = 0;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -4225,9 +4677,9 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 plane_ctl;
 
@@ -4237,10 +4689,10 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 		plane_ctl |= skl_plane_ctl_alpha(plane_state);
 		plane_ctl |= PLANE_CTL_PLANE_GAMMA_DISABLE;
 
-		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+		if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_ctl |= PLANE_CTL_YUV_TO_RGB_CSC_FORMAT_BT709;
 
-		if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+		if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 			plane_ctl |= PLANE_CTL_YUV_RANGE_CORRECTION_DISABLE;
 	}
 
@@ -4262,7 +4714,7 @@ u32 skl_plane_ctl(const struct intel_crtc_state *crtc_state,
 
 u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 plane_color_ctl = 0;
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -4281,21 +4733,21 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	u32 plane_color_ctl = 0;
 
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(plane_state);
 
 	if (fb->format->is_yuv && !icl_is_hdr_plane(dev_priv, plane->id)) {
-		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+		if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV601_TO_RGB709;
 
-		if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+		if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 			plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE;
 	} else if (fb->format->is_yuv) {
 		plane_color_ctl |= PLANE_COLOR_INPUT_CSC_ENABLE;
@@ -4483,7 +4935,7 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc)
 
 static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 trans_ddi_func_ctl2_val;
 	u8 master_select;
@@ -4511,20 +4963,6 @@ static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state
 		   trans_ddi_func_ctl2_val);
 }
 
-static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
-		return;
-
-	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
-		      transcoder_name(old_crtc_state->cpu_transcoder));
-
-	I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
-}
-
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -4567,8 +5005,8 @@ static void intel_fdi_normal_train(struct intel_crtc *crtc)
 }
 
 /* The FDI link training functions for ILK/Ibexpeak. */
-static void ironlake_fdi_link_train(struct intel_crtc *crtc,
-				    const struct intel_crtc_state *crtc_state)
+static void ilk_fdi_link_train(struct intel_crtc *crtc,
+			       const struct intel_crtc_state *crtc_state)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -4577,7 +5015,7 @@ static void ironlake_fdi_link_train(struct intel_crtc *crtc,
 	u32 temp, tries;
 
 	/* FDI needs bits from pipe first */
-	assert_pipe_enabled(dev_priv, pipe);
+	assert_pipe_enabled(dev_priv, crtc_state->cpu_transcoder);
 
 	/* Train 1: umask FDI RX Interrupt symbol_lock and bit_lock bit
 	   for train result */
@@ -4920,9 +5358,9 @@ train_done:
 	DRM_DEBUG_KMS("FDI train done.\n");
 }
 
-static void ironlake_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
+static void ilk_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	enum pipe pipe = intel_crtc->pipe;
 	i915_reg_t reg;
@@ -4957,7 +5395,7 @@ static void ironlake_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 	}
 }
 
-static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
+static void ilk_fdi_pll_disable(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -4987,12 +5425,10 @@ static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
 	udelay(100);
 }
 
-static void ironlake_fdi_disable(struct drm_crtc *crtc)
+static void ilk_fdi_disable(struct intel_crtc *crtc)
 {
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -5083,9 +5519,9 @@ void lpt_disable_iclkip(struct drm_i915_private *dev_priv)
 /* Program iCLKIP clock to the desired frequency */
 static void lpt_program_iclkip(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int clock = crtc_state->base.adjusted_mode.crtc_clock;
+	int clock = crtc_state->hw.adjusted_mode.crtc_clock;
 	u32 divsel, phaseinc, auxdiv, phasedir = 0;
 	u32 temp;
 
@@ -5196,10 +5632,10 @@ int lpt_get_iclkip(struct drm_i915_private *dev_priv)
 				 desired_divisor << auxdiv);
 }
 
-static void ironlake_pch_transcoder_set_timings(const struct intel_crtc_state *crtc_state,
-						enum pipe pch_transcoder)
+static void ilk_pch_transcoder_set_timings(const struct intel_crtc_state *crtc_state,
+					   enum pipe pch_transcoder)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
@@ -5240,9 +5676,9 @@ static void cpt_set_fdi_bc_bifurcation(struct drm_i915_private *dev_priv, bool e
 	POSTING_READ(SOUTH_CHICKEN1);
 }
 
-static void ivybridge_update_fdi_bc_bifurcation(const struct intel_crtc_state *crtc_state)
+static void ivb_update_fdi_bc_bifurcation(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	switch (crtc->pipe) {
@@ -5272,7 +5708,7 @@ static struct intel_encoder *
 intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
 			   const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct drm_connector_state *connector_state;
 	const struct drm_connector *connector;
 	struct intel_encoder *encoder = NULL;
@@ -5301,10 +5737,10 @@ intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
  *   - DP transcoding bits
  *   - transcoder
  */
-static void ironlake_pch_enable(const struct intel_atomic_state *state,
-				const struct intel_crtc_state *crtc_state)
+static void ilk_pch_enable(const struct intel_atomic_state *state,
+			   const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum pipe pipe = crtc->pipe;
@@ -5313,7 +5749,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 	assert_pch_transcoder_disabled(dev_priv, pipe);
 
 	if (IS_IVYBRIDGE(dev_priv))
-		ivybridge_update_fdi_bc_bifurcation(crtc_state);
+		ivb_update_fdi_bc_bifurcation(crtc_state);
 
 	/* Write the TU size bits before fdi link training, so that error
 	 * detection works. */
@@ -5350,7 +5786,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 
 	/* set transcoder timing, panel must allow it */
 	assert_panel_unlocked(dev_priv, pipe);
-	ironlake_pch_transcoder_set_timings(crtc_state, pipe);
+	ilk_pch_transcoder_set_timings(crtc_state, pipe);
 
 	intel_fdi_normal_train(crtc);
 
@@ -5358,7 +5794,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 	if (HAS_PCH_CPT(dev_priv) &&
 	    intel_crtc_has_dp_encoder(crtc_state)) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc_state->base.adjusted_mode;
+			&crtc_state->hw.adjusted_mode;
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5;
 		i915_reg_t reg = TRANS_DP_CTL(pipe);
 		enum port port;
@@ -5382,13 +5818,13 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 		I915_WRITE(reg, temp);
 	}
 
-	ironlake_enable_pch_transcoder(crtc_state);
+	ilk_enable_pch_transcoder(crtc_state);
 }
 
 static void lpt_pch_enable(const struct intel_atomic_state *state,
 			   const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
@@ -5397,14 +5833,14 @@ static void lpt_pch_enable(const struct intel_atomic_state *state,
 	lpt_program_iclkip(crtc_state);
 
 	/* Set transcoder timing. */
-	ironlake_pch_transcoder_set_timings(crtc_state, PIPE_A);
+	ilk_pch_transcoder_set_timings(crtc_state, PIPE_A);
 
 	lpt_enable_pch_transcoder(dev_priv, cpu_transcoder);
 }
 
-static void cpt_verify_modeset(struct drm_device *dev, enum pipe pipe)
+static void cpt_verify_modeset(struct drm_i915_private *dev_priv,
+			       enum pipe pipe)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t dslreg = PIPEDSL(pipe);
 	u32 temp;
 
@@ -5500,15 +5936,16 @@ static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
 		  int src_w, int src_h, int dst_w, int dst_h,
-		  const struct drm_format_info *format, bool need_scaler)
+		  const struct drm_format_info *format,
+		  u64 modifier, bool need_scaler)
 {
 	struct intel_crtc_scaler_state *scaler_state =
 		&crtc_state->scaler_state;
 	struct intel_crtc *intel_crtc =
-		to_intel_crtc(crtc_state->base.crtc);
+		to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	/*
 	 * Src coordinates are already rotated by 270 degrees for
@@ -5524,7 +5961,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	 * Once NV12 is enabled, handle it here while allocating scaler
 	 * for NV12.
 	 */
-	if (INTEL_GEN(dev_priv) >= 9 && crtc_state->base.enable &&
+	if (INTEL_GEN(dev_priv) >= 9 && crtc_state->hw.enable &&
 	    need_scaler && adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		DRM_DEBUG_KMS("Pipe/Plane scaling not supported with IF-ID mode\n");
 		return -EINVAL;
@@ -5554,7 +5991,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		return 0;
 	}
 
-	if (format && drm_format_info_is_yuv_semiplanar(format) &&
+	if (format && intel_format_info_is_yuv_semiplanar(format, modifier) &&
 	    (src_h < SKL_MIN_YUV_420_SRC_H || src_w < SKL_MIN_YUV_420_SRC_W)) {
 		DRM_DEBUG_KMS("Planar YUV: src dimensions not met\n");
 		return -EINVAL;
@@ -5596,17 +6033,18 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
  */
 int skl_update_scaler_crtc(struct intel_crtc_state *state)
 {
-	const struct drm_display_mode *adjusted_mode = &state->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &state->hw.adjusted_mode;
 	bool need_scaler = false;
 
 	if (state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
 		need_scaler = true;
 
-	return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX,
+	return skl_update_scaler(state, !state->hw.active, SKL_CRTC_INDEX,
 				 &state->scaler_state.scaler_id,
 				 state->pipe_src_w, state->pipe_src_h,
 				 adjusted_mode->crtc_hdisplay,
-				 adjusted_mode->crtc_vdisplay, NULL, need_scaler);
+				 adjusted_mode->crtc_vdisplay, NULL, 0,
+				 need_scaler);
 }
 
 /**
@@ -5622,26 +6060,28 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 				   struct intel_plane_state *plane_state)
 {
 	struct intel_plane *intel_plane =
-		to_intel_plane(plane_state->base.plane);
+		to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(intel_plane->base.dev);
-	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
-	bool force_detach = !fb || !plane_state->base.visible;
+	bool force_detach = !fb || !plane_state->uapi.visible;
 	bool need_scaler = false;
 
 	/* Pre-gen11 and SDR planes always need a scaler for planar formats. */
 	if (!icl_is_hdr_plane(dev_priv, intel_plane->id) &&
-	    fb && drm_format_info_is_yuv_semiplanar(fb->format))
+	    fb && intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		need_scaler = true;
 
 	ret = skl_update_scaler(crtc_state, force_detach,
 				drm_plane_index(&intel_plane->base),
 				&plane_state->scaler_id,
-				drm_rect_width(&plane_state->base.src) >> 16,
-				drm_rect_height(&plane_state->base.src) >> 16,
-				drm_rect_width(&plane_state->base.dst),
-				drm_rect_height(&plane_state->base.dst),
-				fb ? fb->format : NULL, need_scaler);
+				drm_rect_width(&plane_state->uapi.src) >> 16,
+				drm_rect_height(&plane_state->uapi.src) >> 16,
+				drm_rect_width(&plane_state->uapi.dst),
+				drm_rect_height(&plane_state->uapi.dst),
+				fb ? fb->format : NULL,
+				fb ? fb->modifier : 0,
+				need_scaler);
 
 	if (ret || plane_state->scaler_id < 0)
 		return ret;
@@ -5663,6 +6103,8 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -5695,17 +6137,18 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	return 0;
 }
 
-static void skylake_scaler_disable(struct intel_crtc *crtc)
+void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	int i;
 
 	for (i = 0; i < crtc->num_scalers; i++)
 		skl_detach_scaler(crtc, i);
 }
 
-static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state)
+static void skl_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	const struct intel_crtc_scaler_state *scaler_state =
@@ -5740,9 +6183,9 @@ static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state)
 	}
 }
 
-static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state)
+static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -5763,7 +6206,7 @@ static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state)
 
 void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -5799,7 +6242,7 @@ void hsw_enable_ips(const struct intel_crtc_state *crtc_state)
 
 void hsw_disable_ips(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -5834,77 +6277,10 @@ static void intel_crtc_dpms_overlay_disable(struct intel_crtc *intel_crtc)
 	 */
 }
 
-/**
- * intel_post_enable_primary - Perform operations after enabling primary plane
- * @crtc: the CRTC whose primary plane was just enabled
- * @new_crtc_state: the enabling state
- *
- * Performs potentially sleeping operations that must be done after the primary
- * plane is enabled, such as updating FBC and IPS.  Note that this may be
- * called due to an explicit primary plane update, or due to an implicit
- * re-enable that is caused when a sprite plane is updated to no longer
- * completely hide the primary plane.
- */
-static void
-intel_post_enable_primary(struct drm_crtc *crtc,
-			  const struct intel_crtc_state *new_crtc_state)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
-
-	/*
-	 * Gen2 reports pipe underruns whenever all planes are disabled.
-	 * So don't enable underrun reporting before at least some planes
-	 * are enabled.
-	 * FIXME: Need to fix the logic to work when we turn off all planes
-	 * but leave the pipe running.
-	 */
-	if (IS_GEN(dev_priv, 2))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
-
-	/* Underruns don't always raise interrupts, so check manually. */
-	intel_check_cpu_fifo_underruns(dev_priv);
-	intel_check_pch_fifo_underruns(dev_priv);
-}
-
-/* FIXME get rid of this and use pre_plane_update */
-static void
-intel_pre_disable_primary_noatomic(struct drm_crtc *crtc)
-{
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
-
-	/*
-	 * Gen2 reports pipe underruns whenever all planes are disabled.
-	 * So disable underrun reporting before all the planes get disabled.
-	 */
-	if (IS_GEN(dev_priv, 2))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-
-	hsw_disable_ips(to_intel_crtc_state(crtc->state));
-
-	/*
-	 * Vblank time updates from the shadow to live plane control register
-	 * are blocked if the memory self-refresh mode is active at that
-	 * moment. So to make sure the plane gets truly disabled, disable
-	 * first the self-refresh mode. The self-refresh enable bit in turn
-	 * will be checked/applied by the HW only at the next frame start
-	 * event which is after the vblank start event, so we need to have a
-	 * wait-for-vblank between disabling the plane and the pipe.
-	 */
-	if (HAS_GMCH(dev_priv) &&
-	    intel_set_memory_cxsr(dev_priv, false))
-		intel_wait_for_vblank(dev_priv, pipe);
-}
-
 static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_state,
 				       const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!old_crtc_state->ips_enabled)
@@ -5920,7 +6296,7 @@ static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_s
 	 * Disable IPS before we program the LUT.
 	 */
 	if (IS_HASWELL(dev_priv) &&
-	    (new_crtc_state->base.color_mgmt_changed ||
+	    (new_crtc_state->uapi.color_mgmt_changed ||
 	     new_crtc_state->update_pipe) &&
 	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
 		return true;
@@ -5931,7 +6307,7 @@ static bool hsw_pre_update_disable_ips(const struct intel_crtc_state *old_crtc_s
 static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_state,
 				       const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!new_crtc_state->ips_enabled)
@@ -5947,7 +6323,7 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s
 	 * Re-enable IPS after the LUT has been programmed.
 	 */
 	if (IS_HASWELL(dev_priv) &&
-	    (new_crtc_state->base.color_mgmt_changed ||
+	    (new_crtc_state->uapi.color_mgmt_changed ||
 	     new_crtc_state->update_pipe) &&
 	    new_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)
 		return true;
@@ -5957,15 +6333,16 @@ static bool hsw_post_update_enable_ips(const struct intel_crtc_state *old_crtc_s
 	 * forcibly enable IPS on the first fastset.
 	 */
 	if (new_crtc_state->update_pipe &&
-	    old_crtc_state->base.adjusted_mode.private_flags & I915_MODE_FLAG_INHERITED)
+	    old_crtc_state->hw.adjusted_mode.private_flags & I915_MODE_FLAG_INHERITED)
 		return true;
 
 	return !old_crtc_state->ips_enabled;
 }
 
-static bool needs_nv12_wa(struct drm_i915_private *dev_priv,
-			  const struct intel_crtc_state *crtc_state)
+static bool needs_nv12_wa(const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+
 	if (!crtc_state->nv12_planes)
 		return false;
 
@@ -5976,9 +6353,10 @@ static bool needs_nv12_wa(struct drm_i915_private *dev_priv,
 	return false;
 }
 
-static bool needs_scalerclk_wa(struct drm_i915_private *dev_priv,
-			       const struct intel_crtc_state *crtc_state)
+static bool needs_scalerclk_wa(const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+
 	/* Wa_2006604312:icl */
 	if (crtc_state->scaler_state.scaler_users > 0 && IS_ICELAKE(dev_priv))
 		return true;
@@ -5986,89 +6364,82 @@ static bool needs_scalerclk_wa(struct drm_i915_private *dev_priv,
 	return false;
 }
 
-static void intel_post_plane_update(struct intel_crtc_state *old_crtc_state)
+static bool planes_enabling(const struct intel_crtc_state *old_crtc_state,
+			    const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_atomic_state *state = old_crtc_state->base.state;
-	struct intel_crtc_state *pipe_config =
-		intel_atomic_get_new_crtc_state(to_intel_atomic_state(state),
-						crtc);
-	struct drm_plane *primary = crtc->base.primary;
-	struct drm_plane_state *old_primary_state =
-		drm_atomic_get_old_plane_state(state, primary);
+	return (!old_crtc_state->active_planes || needs_modeset(new_crtc_state)) &&
+		new_crtc_state->active_planes;
+}
 
-	intel_frontbuffer_flip(to_i915(crtc->base.dev), pipe_config->fb_bits);
+static bool planes_disabling(const struct intel_crtc_state *old_crtc_state,
+			     const struct intel_crtc_state *new_crtc_state)
+{
+	return old_crtc_state->active_planes &&
+		(!new_crtc_state->active_planes || needs_modeset(new_crtc_state));
+}
 
-	if (pipe_config->update_wm_post && pipe_config->base.active)
-		intel_update_watermarks(crtc);
+static void intel_post_plane_update(struct intel_atomic_state *state,
+				    struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_plane *primary = to_intel_plane(crtc->base.primary);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_plane_state *new_primary_state =
+		intel_atomic_get_new_plane_state(state, primary);
+	enum pipe pipe = crtc->pipe;
 
-	if (hsw_post_update_enable_ips(old_crtc_state, pipe_config))
-		hsw_enable_ips(pipe_config);
+	intel_frontbuffer_flip(dev_priv, new_crtc_state->fb_bits);
 
-	if (old_primary_state) {
-		struct drm_plane_state *new_primary_state =
-			drm_atomic_get_new_plane_state(state, primary);
+	if (new_crtc_state->update_wm_post && new_crtc_state->hw.active)
+		intel_update_watermarks(crtc);
 
-		intel_fbc_post_update(crtc);
+	if (hsw_post_update_enable_ips(old_crtc_state, new_crtc_state))
+		hsw_enable_ips(new_crtc_state);
 
-		if (new_primary_state->visible &&
-		    (needs_modeset(pipe_config) ||
-		     !old_primary_state->visible))
-			intel_post_enable_primary(&crtc->base, pipe_config);
-	}
+	if (new_primary_state)
+		intel_fbc_post_update(crtc);
 
-	if (needs_nv12_wa(dev_priv, old_crtc_state) &&
-	    !needs_nv12_wa(dev_priv, pipe_config))
-		skl_wa_827(dev_priv, crtc->pipe, false);
+	if (needs_nv12_wa(old_crtc_state) &&
+	    !needs_nv12_wa(new_crtc_state))
+		skl_wa_827(dev_priv, pipe, false);
 
-	if (needs_scalerclk_wa(dev_priv, old_crtc_state) &&
-	    !needs_scalerclk_wa(dev_priv, pipe_config))
-		icl_wa_scalerclkgating(dev_priv, crtc->pipe, false);
+	if (needs_scalerclk_wa(old_crtc_state) &&
+	    !needs_scalerclk_wa(new_crtc_state))
+		icl_wa_scalerclkgating(dev_priv, pipe, false);
 }
 
-static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
-				   struct intel_crtc_state *pipe_config)
+static void intel_pre_plane_update(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_atomic_state *state = old_crtc_state->base.state;
-	struct drm_plane *primary = crtc->base.primary;
-	struct drm_plane_state *old_primary_state =
-		drm_atomic_get_old_plane_state(state, primary);
-	bool modeset = needs_modeset(pipe_config);
-	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(state);
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_plane *primary = to_intel_plane(crtc->base.primary);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct intel_plane_state *new_primary_state =
+		intel_atomic_get_new_plane_state(state, primary);
+	enum pipe pipe = crtc->pipe;
 
-	if (hsw_pre_update_disable_ips(old_crtc_state, pipe_config))
+	if (hsw_pre_update_disable_ips(old_crtc_state, new_crtc_state))
 		hsw_disable_ips(old_crtc_state);
 
-	if (old_primary_state) {
-		struct intel_plane_state *new_primary_state =
-			intel_atomic_get_new_plane_state(intel_state,
-							 to_intel_plane(primary));
-
-		intel_fbc_pre_update(crtc, pipe_config, new_primary_state);
-		/*
-		 * Gen2 reports pipe underruns whenever all planes are disabled.
-		 * So disable underrun reporting before all the planes get disabled.
-		 */
-		if (IS_GEN(dev_priv, 2) && old_primary_state->visible &&
-		    (modeset || !new_primary_state->base.visible))
-			intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false);
-	}
+	if (new_primary_state &&
+	    intel_fbc_pre_update(crtc, new_crtc_state, new_primary_state))
+		intel_wait_for_vblank(dev_priv, pipe);
 
 	/* Display WA 827 */
-	if (!needs_nv12_wa(dev_priv, old_crtc_state) &&
-	    needs_nv12_wa(dev_priv, pipe_config))
-		skl_wa_827(dev_priv, crtc->pipe, true);
+	if (!needs_nv12_wa(old_crtc_state) &&
+	    needs_nv12_wa(new_crtc_state))
+		skl_wa_827(dev_priv, pipe, true);
 
 	/* Wa_2006604312:icl */
-	if (!needs_scalerclk_wa(dev_priv, old_crtc_state) &&
-	    needs_scalerclk_wa(dev_priv, pipe_config))
-		icl_wa_scalerclkgating(dev_priv, crtc->pipe, true);
+	if (!needs_scalerclk_wa(old_crtc_state) &&
+	    needs_scalerclk_wa(new_crtc_state))
+		icl_wa_scalerclkgating(dev_priv, pipe, true);
 
 	/*
 	 * Vblank time updates from the shadow to live plane control register
@@ -6079,9 +6450,9 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	 * event which is after the vblank start event, so we need to have a
 	 * wait-for-vblank between disabling the plane and the pipe.
 	 */
-	if (HAS_GMCH(dev_priv) && old_crtc_state->base.active &&
-	    pipe_config->disable_cxsr && intel_set_memory_cxsr(dev_priv, false))
-		intel_wait_for_vblank(dev_priv, crtc->pipe);
+	if (HAS_GMCH(dev_priv) && old_crtc_state->hw.active &&
+	    new_crtc_state->disable_cxsr && intel_set_memory_cxsr(dev_priv, false))
+		intel_wait_for_vblank(dev_priv, pipe);
 
 	/*
 	 * IVB workaround: must disable low power watermarks for at least
@@ -6090,36 +6461,45 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state,
 	 *
 	 * WaCxSRDisabledForSpriteScaling:ivb
 	 */
-	if (pipe_config->disable_lp_wm && ilk_disable_lp_wm(dev) &&
-	    old_crtc_state->base.active)
-		intel_wait_for_vblank(dev_priv, crtc->pipe);
+	if (old_crtc_state->hw.active &&
+	    new_crtc_state->disable_lp_wm && ilk_disable_lp_wm(dev_priv))
+		intel_wait_for_vblank(dev_priv, pipe);
 
 	/*
-	 * If we're doing a modeset, we're done.  No need to do any pre-vblank
-	 * watermark programming here.
+	 * If we're doing a modeset we don't need to do any
+	 * pre-vblank watermark programming here.
 	 */
-	if (needs_modeset(pipe_config))
-		return;
+	if (!needs_modeset(new_crtc_state)) {
+		/*
+		 * For platforms that support atomic watermarks, program the
+		 * 'intermediate' watermarks immediately.  On pre-gen9 platforms, these
+		 * will be the intermediate values that are safe for both pre- and
+		 * post- vblank; when vblank happens, the 'active' values will be set
+		 * to the final 'target' values and we'll do this again to get the
+		 * optimal watermarks.  For gen9+ platforms, the values we program here
+		 * will be the final target values which will get automatically latched
+		 * at vblank time; no further programming will be necessary.
+		 *
+		 * If a platform hasn't been transitioned to atomic watermarks yet,
+		 * we'll continue to update watermarks the old way, if flags tell
+		 * us to.
+		 */
+		if (dev_priv->display.initial_watermarks)
+			dev_priv->display.initial_watermarks(state, crtc);
+		else if (new_crtc_state->update_wm_pre)
+			intel_update_watermarks(crtc);
+	}
 
 	/*
-	 * For platforms that support atomic watermarks, program the
-	 * 'intermediate' watermarks immediately.  On pre-gen9 platforms, these
-	 * will be the intermediate values that are safe for both pre- and
-	 * post- vblank; when vblank happens, the 'active' values will be set
-	 * to the final 'target' values and we'll do this again to get the
-	 * optimal watermarks.  For gen9+ platforms, the values we program here
-	 * will be the final target values which will get automatically latched
-	 * at vblank time; no further programming will be necessary.
+	 * Gen2 reports pipe underruns whenever all planes are disabled.
+	 * So disable underrun reporting before all the planes get disabled.
 	 *
-	 * If a platform hasn't been transitioned to atomic watermarks yet,
-	 * we'll continue to update watermarks the old way, if flags tell
-	 * us to.
+	 * We do this after .initial_watermarks() so that we have a
+	 * chance of catching underruns with the intermediate watermarks
+	 * vs. the old plane configuration.
 	 */
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(intel_state,
-						     pipe_config);
-	else if (pipe_config->update_wm_pre)
-		intel_update_watermarks(crtc);
+	if (IS_GEN(dev_priv, 2) && planes_disabling(old_crtc_state, new_crtc_state))
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 }
 
 static void intel_crtc_disable_planes(struct intel_atomic_state *state,
@@ -6143,7 +6523,7 @@ static void intel_crtc_disable_planes(struct intel_atomic_state *state,
 
 		intel_disable_plane(plane, new_crtc_state);
 
-		if (old_plane_state->base.visible)
+		if (old_plane_state->uapi.visible)
 			fb_bits |= plane->frontbuffer_bit;
 	}
 
@@ -6167,45 +6547,29 @@ intel_connector_primary_encoder(struct intel_connector *connector)
 	if (connector->mst_port)
 		return &dp_to_dig_port(connector->mst_port)->base;
 
-	encoder = intel_attached_encoder(&connector->base);
+	encoder = intel_attached_encoder(connector);
 	WARN_ON(!encoder);
 
 	return encoder;
 }
 
-static bool
-intel_connector_needs_modeset(struct intel_atomic_state *state,
-			      const struct drm_connector_state *old_conn_state,
-			      const struct drm_connector_state *new_conn_state)
-{
-	struct intel_crtc *old_crtc = old_conn_state->crtc ?
-				      to_intel_crtc(old_conn_state->crtc) : NULL;
-	struct intel_crtc *new_crtc = new_conn_state->crtc ?
-				      to_intel_crtc(new_conn_state->crtc) : NULL;
-
-	return new_crtc != old_crtc ||
-	       (new_crtc &&
-		needs_modeset(intel_atomic_get_new_crtc_state(state, new_crtc)));
-}
-
 static void intel_encoders_update_prepare(struct intel_atomic_state *state)
 {
-	struct drm_connector_state *old_conn_state;
 	struct drm_connector_state *new_conn_state;
-	struct drm_connector *conn;
+	struct drm_connector *connector;
 	int i;
 
-	for_each_oldnew_connector_in_state(&state->base, conn,
-					   old_conn_state, new_conn_state, i) {
+	for_each_new_connector_in_state(&state->base, connector, new_conn_state,
+					i) {
+		struct intel_connector *intel_connector;
 		struct intel_encoder *encoder;
 		struct intel_crtc *crtc;
 
-		if (!intel_connector_needs_modeset(state,
-						   old_conn_state,
-						   new_conn_state))
+		if (!intel_connector_needs_modeset(state, connector))
 			continue;
 
-		encoder = intel_connector_primary_encoder(to_intel_connector(conn));
+		intel_connector = to_intel_connector(connector);
+		encoder = intel_connector_primary_encoder(intel_connector);
 		if (!encoder->update_prepare)
 			continue;
 
@@ -6217,22 +6581,21 @@ static void intel_encoders_update_prepare(struct intel_atomic_state *state)
 
 static void intel_encoders_update_complete(struct intel_atomic_state *state)
 {
-	struct drm_connector_state *old_conn_state;
 	struct drm_connector_state *new_conn_state;
-	struct drm_connector *conn;
+	struct drm_connector *connector;
 	int i;
 
-	for_each_oldnew_connector_in_state(&state->base, conn,
-					   old_conn_state, new_conn_state, i) {
+	for_each_new_connector_in_state(&state->base, connector, new_conn_state,
+					i) {
+		struct intel_connector *intel_connector;
 		struct intel_encoder *encoder;
 		struct intel_crtc *crtc;
 
-		if (!intel_connector_needs_modeset(state,
-						   old_conn_state,
-						   new_conn_state))
+		if (!intel_connector_needs_modeset(state, connector))
 			continue;
 
-		encoder = intel_connector_primary_encoder(to_intel_connector(conn));
+		intel_connector = to_intel_connector(connector);
+		encoder = intel_connector_primary_encoder(intel_connector);
 		if (!encoder->update_complete)
 			continue;
 
@@ -6242,11 +6605,12 @@ static void intel_encoders_update_complete(struct intel_atomic_state *state)
 	}
 }
 
-static void intel_encoders_pre_pll_enable(struct intel_crtc *crtc,
-					  struct intel_crtc_state *crtc_state,
-					  struct intel_atomic_state *state)
+static void intel_encoders_pre_pll_enable(struct intel_atomic_state *state,
+					  struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6262,11 +6626,12 @@ static void intel_encoders_pre_pll_enable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_pre_enable(struct intel_crtc *crtc,
-				      struct intel_crtc_state *crtc_state,
-				      struct intel_atomic_state *state)
+static void intel_encoders_pre_enable(struct intel_atomic_state *state,
+				      struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6282,11 +6647,12 @@ static void intel_encoders_pre_enable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_enable(struct intel_crtc *crtc,
-				  struct intel_crtc_state *crtc_state,
-				  struct intel_atomic_state *state)
+static void intel_encoders_enable(struct intel_atomic_state *state,
+				  struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6303,11 +6669,12 @@ static void intel_encoders_enable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_disable(struct intel_crtc *crtc,
-				   struct intel_crtc_state *old_crtc_state,
-				   struct intel_atomic_state *state)
+static void intel_encoders_disable(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct drm_connector_state *old_conn_state;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6324,11 +6691,12 @@ static void intel_encoders_disable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_post_disable(struct intel_crtc *crtc,
-					struct intel_crtc_state *old_crtc_state,
-					struct intel_atomic_state *state)
+static void intel_encoders_post_disable(struct intel_atomic_state *state,
+					struct intel_crtc *crtc)
 {
-	struct drm_connector_state *old_conn_state;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6344,11 +6712,12 @@ static void intel_encoders_post_disable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_post_pll_disable(struct intel_crtc *crtc,
-					    struct intel_crtc_state *old_crtc_state,
-					    struct intel_atomic_state *state)
+static void intel_encoders_post_pll_disable(struct intel_atomic_state *state,
+					    struct intel_crtc *crtc)
 {
-	struct drm_connector_state *old_conn_state;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	const struct drm_connector_state *old_conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6364,11 +6733,12 @@ static void intel_encoders_post_pll_disable(struct intel_crtc *crtc,
 	}
 }
 
-static void intel_encoders_update_pipe(struct intel_crtc *crtc,
-				       struct intel_crtc_state *crtc_state,
-				       struct intel_atomic_state *state)
+static void intel_encoders_update_pipe(struct intel_atomic_state *state,
+				       struct intel_crtc *crtc)
 {
-	struct drm_connector_state *conn_state;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct drm_connector_state *conn_state;
 	struct drm_connector *conn;
 	int i;
 
@@ -6386,22 +6756,21 @@ static void intel_encoders_update_pipe(struct intel_crtc *crtc,
 
 static void intel_disable_primary_plane(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 
 	plane->disable_plane(plane, crtc_state);
 }
 
-static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
-				 struct intel_atomic_state *state)
+static void ilk_crtc_enable(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
 	/*
@@ -6417,61 +6786,59 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
-	if (pipe_config->has_pch_encoder)
-		intel_prepare_shared_dpll(pipe_config);
+	if (new_crtc_state->has_pch_encoder)
+		intel_prepare_shared_dpll(new_crtc_state);
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
-	intel_set_pipe_timings(pipe_config);
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_timings(new_crtc_state);
+	intel_set_pipe_src_size(new_crtc_state);
 
-	if (pipe_config->has_pch_encoder) {
-		intel_cpu_transcoder_set_m_n(pipe_config,
-					     &pipe_config->fdi_m_n, NULL);
-	}
+	if (new_crtc_state->has_pch_encoder)
+		intel_cpu_transcoder_set_m_n(new_crtc_state,
+					     &new_crtc_state->fdi_m_n, NULL);
 
-	ironlake_set_pipeconf(pipe_config);
+	ilk_set_pipeconf(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	if (pipe_config->has_pch_encoder) {
+	if (new_crtc_state->has_pch_encoder) {
 		/* Note: FDI PLL enabling _must_ be done before we enable the
 		 * cpu pipes, hence this is separate from all the other fdi/pch
 		 * enabling. */
-		ironlake_fdi_pll_enable(pipe_config);
+		ilk_fdi_pll_enable(new_crtc_state);
 	} else {
 		assert_fdi_tx_disabled(dev_priv, pipe);
 		assert_fdi_rx_disabled(dev_priv, pipe);
 	}
 
-	ironlake_pfit_enable(pipe_config);
+	ilk_pfit_enable(new_crtc_state);
 
 	/*
 	 * On ILK+ LUT must be loaded before the pipe is running but with
 	 * clocks enabled
 	 */
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(pipe_config);
+	intel_disable_primary_plane(new_crtc_state);
 
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(state, pipe_config);
-	intel_enable_pipe(pipe_config);
+	if (dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state, crtc);
+	intel_enable_pipe(new_crtc_state);
 
-	if (pipe_config->has_pch_encoder)
-		ironlake_pch_enable(state, pipe_config);
+	if (new_crtc_state->has_pch_encoder)
+		ilk_pch_enable(state, new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 
 	if (HAS_PCH_CPT(dev_priv))
-		cpt_verify_modeset(dev, intel_crtc->pipe);
+		cpt_verify_modeset(dev_priv, pipe);
 
 	/*
 	 * Must wait for vblank to avoid spurious PCH FIFO underruns.
@@ -6479,7 +6846,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	 * some interlaced HDMI modes. Let's do the double wait always
 	 * in case there are more corner cases we don't know about.
 	 */
-	if (pipe_config->has_pch_encoder) {
+	if (new_crtc_state->has_pch_encoder) {
 		intel_wait_for_vblank(dev_priv, pipe);
 		intel_wait_for_vblank(dev_priv, pipe);
 	}
@@ -6526,103 +6893,112 @@ static void icl_pipe_mbus_enable(struct intel_crtc *crtc)
 	I915_WRITE(PIPE_MBUS_DBOX_CTL(pipe), val);
 }
 
-static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
-				struct intel_atomic_state *state)
+static void hsw_set_frame_start_delay(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe, hsw_workaround_pipe;
-	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	i915_reg_t reg = CHICKEN_TRANS(crtc_state->cpu_transcoder);
+	u32 val;
+
+	val = I915_READ(reg);
+	val &= ~HSW_FRAME_START_DELAY_MASK;
+	val |= HSW_FRAME_START_DELAY(0);
+	I915_WRITE(reg, val);
+}
+
+static void hsw_crtc_enable(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc)
+{
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe, hsw_workaround_pipe;
+	enum transcoder cpu_transcoder = new_crtc_state->cpu_transcoder;
 	bool psl_clkgate_wa;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
-	intel_encoders_pre_pll_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_pll_enable(state, crtc);
 
-	if (pipe_config->shared_dpll)
-		intel_enable_shared_dpll(pipe_config);
+	if (new_crtc_state->shared_dpll)
+		intel_enable_shared_dpll(new_crtc_state);
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_set_pipe_timings(pipe_config);
+		intel_set_pipe_timings(new_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icl_enable_trans_port_sync(pipe_config);
+		icl_enable_trans_port_sync(new_crtc_state);
 
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_src_size(new_crtc_state);
 
 	if (cpu_transcoder != TRANSCODER_EDP &&
-	    !transcoder_is_dsi(cpu_transcoder)) {
+	    !transcoder_is_dsi(cpu_transcoder))
 		I915_WRITE(PIPE_MULT(cpu_transcoder),
-			   pipe_config->pixel_multiplier - 1);
-	}
+			   new_crtc_state->pixel_multiplier - 1);
 
-	if (pipe_config->has_pch_encoder) {
-		intel_cpu_transcoder_set_m_n(pipe_config,
-					     &pipe_config->fdi_m_n, NULL);
-	}
+	if (new_crtc_state->has_pch_encoder)
+		intel_cpu_transcoder_set_m_n(new_crtc_state,
+					     &new_crtc_state->fdi_m_n, NULL);
 
-	if (!transcoder_is_dsi(cpu_transcoder))
-		haswell_set_pipeconf(pipe_config);
+	if (!transcoder_is_dsi(cpu_transcoder)) {
+		hsw_set_frame_start_delay(new_crtc_state);
+		hsw_set_pipeconf(new_crtc_state);
+	}
 
 	if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
-		bdw_set_pipemisc(pipe_config);
+		bdw_set_pipemisc(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
 	/* Display WA #1180: WaDisableScalarClockGating: glk, cnl */
 	psl_clkgate_wa = (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) &&
-			 pipe_config->pch_pfit.enabled;
+		new_crtc_state->pch_pfit.enabled;
 	if (psl_clkgate_wa)
 		glk_pipe_scaler_clock_gating_wa(dev_priv, pipe, true);
 
 	if (INTEL_GEN(dev_priv) >= 9)
-		skylake_pfit_enable(pipe_config);
+		skl_pfit_enable(new_crtc_state);
 	else
-		ironlake_pfit_enable(pipe_config);
+		ilk_pfit_enable(new_crtc_state);
 
 	/*
 	 * On ILK+ LUT must be loaded before the pipe is running but with
 	 * clocks enabled
 	 */
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma/csc for pipe bottom color */
 	if (INTEL_GEN(dev_priv) < 9)
-		intel_disable_primary_plane(pipe_config);
+		intel_disable_primary_plane(new_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icl_set_pipe_chicken(intel_crtc);
+		icl_set_pipe_chicken(crtc);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_enable_transcoder_func(pipe_config);
+		intel_ddi_enable_transcoder_func(new_crtc_state);
 
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(state, pipe_config);
+	if (dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state, crtc);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icl_pipe_mbus_enable(intel_crtc);
+		icl_pipe_mbus_enable(crtc);
 
 	/* XXX: Do the pipe assertions at the right place for BXT DSI. */
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_enable_pipe(pipe_config);
+		intel_enable_pipe(new_crtc_state);
 
-	if (pipe_config->has_pch_encoder)
-		lpt_pch_enable(state, pipe_config);
-
-	if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST))
-		intel_ddi_set_vc_payload_alloc(pipe_config, true);
+	if (new_crtc_state->has_pch_encoder)
+		lpt_pch_enable(state, new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 
 	if (psl_clkgate_wa) {
 		intel_wait_for_vblank(dev_priv, pipe);
@@ -6631,16 +7007,16 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	/* If we change the relative order between pipe/planes enabling, we need
 	 * to change the workaround. */
-	hsw_workaround_pipe = pipe_config->hsw_workaround_pipe;
+	hsw_workaround_pipe = new_crtc_state->hsw_workaround_pipe;
 	if (IS_HASWELL(dev_priv) && hsw_workaround_pipe != INVALID_PIPE) {
 		intel_wait_for_vblank(dev_priv, hsw_workaround_pipe);
 		intel_wait_for_vblank(dev_priv, hsw_workaround_pipe);
 	}
 }
 
-static void ironlake_pfit_disable(const struct intel_crtc_state *old_crtc_state)
+void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -6653,14 +7029,13 @@ static void ironlake_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 	}
 }
 
-static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
-				  struct intel_atomic_state *state)
+static void ilk_crtc_disable(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = old_crtc_state->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	/*
 	 * Sometimes spurious CPU pipe underruns happen when the
@@ -6670,22 +7045,21 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
-	intel_encoders_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_disable(state, crtc);
 
-	drm_crtc_vblank_off(crtc);
-	assert_vblank_disabled(crtc);
+	intel_crtc_vblank_off(old_crtc_state);
 
 	intel_disable_pipe(old_crtc_state);
 
-	ironlake_pfit_disable(old_crtc_state);
+	ilk_pfit_disable(old_crtc_state);
 
 	if (old_crtc_state->has_pch_encoder)
-		ironlake_fdi_disable(crtc);
+		ilk_fdi_disable(crtc);
 
-	intel_encoders_post_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_post_disable(state, crtc);
 
 	if (old_crtc_state->has_pch_encoder) {
-		ironlake_disable_pch_transcoder(dev_priv, pipe);
+		ilk_disable_pch_transcoder(dev_priv, pipe);
 
 		if (HAS_PCH_CPT(dev_priv)) {
 			i915_reg_t reg;
@@ -6705,54 +7079,27 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 			I915_WRITE(PCH_DPLL_SEL, temp);
 		}
 
-		ironlake_fdi_pll_disable(intel_crtc);
+		ilk_fdi_pll_disable(crtc);
 	}
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
 }
 
-static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
-				 struct intel_atomic_state *state)
+static void hsw_crtc_disable(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = old_crtc_state->base.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
-
-	intel_encoders_disable(intel_crtc, old_crtc_state, state);
-
-	drm_crtc_vblank_off(crtc);
-	assert_vblank_disabled(crtc);
-
-	/* XXX: Do the pipe assertions at the right place for BXT DSI. */
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_disable_pipe(old_crtc_state);
-
-	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
-		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		icl_disable_transcoder_port_sync(old_crtc_state);
-
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_transcoder_func(old_crtc_state);
-
-	intel_dsc_disable(old_crtc_state);
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		skylake_scaler_disable(intel_crtc);
-	else
-		ironlake_pfit_disable(old_crtc_state);
-
-	intel_encoders_post_disable(intel_crtc, old_crtc_state, state);
-
-	intel_encoders_post_pll_disable(intel_crtc, old_crtc_state, state);
+	/*
+	 * FIXME collapse everything to one hook.
+	 * Need care with mst->ddi interactions.
+	 */
+	intel_encoders_disable(state, crtc);
+	intel_encoders_post_disable(state, crtc);
 }
 
 static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!crtc_state->gmch_pfit.control)
@@ -6763,7 +7110,7 @@ static void i9xx_pfit_enable(const struct intel_crtc_state *crtc_state)
 	 * according to register description and PRM.
 	 */
 	WARN_ON(I915_READ(PFIT_CONTROL) & PFIT_ENABLE);
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, crtc_state->cpu_transcoder);
 
 	I915_WRITE(PFIT_PGM_RATIOS, crtc_state->gmch_pfit.pgm_ratios);
 	I915_WRITE(PFIT_CONTROL, crtc_state->gmch_pfit.control);
@@ -6888,14 +7235,14 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 
 static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct drm_encoder *encoder;
 	enum pipe pipe = crtc->pipe;
 	u64 mask;
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 
 	mask = BIT_ULL(POWER_DOMAIN_PIPE(pipe));
@@ -6905,7 +7252,7 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 		mask |= BIT_ULL(POWER_DOMAIN_PIPE_PANEL_FITTER(pipe));
 
 	drm_for_each_encoder_mask(encoder, &dev_priv->drm,
-				  crtc_state->base.encoder_mask) {
+				  crtc_state->uapi.encoder_mask) {
 		struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
 
 		mask |= BIT_ULL(intel_encoder->power_domain);
@@ -6923,7 +7270,7 @@ static u64 get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 static u64
 modeset_get_crtc_power_domains(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum intel_display_power_domain domain;
 	u64 domains, new_domains, old_domains;
@@ -6949,146 +7296,140 @@ static void modeset_put_power_domains(struct drm_i915_private *dev_priv,
 		intel_display_power_put_unchecked(dev_priv, domain);
 }
 
-static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config,
-				   struct intel_atomic_state *state)
+static void valleyview_crtc_enable(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
-	intel_set_pipe_timings(pipe_config);
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_timings(new_crtc_state);
+	intel_set_pipe_src_size(new_crtc_state);
 
 	if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) {
 		I915_WRITE(CHV_BLEND(pipe), CHV_BLEND_LEGACY);
 		I915_WRITE(CHV_CANVAS(pipe), 0);
 	}
 
-	i9xx_set_pipeconf(pipe_config);
+	i9xx_set_pipeconf(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 
-	intel_encoders_pre_pll_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_pll_enable(state, crtc);
 
 	if (IS_CHERRYVIEW(dev_priv)) {
-		chv_prepare_pll(intel_crtc, pipe_config);
-		chv_enable_pll(intel_crtc, pipe_config);
+		chv_prepare_pll(crtc, new_crtc_state);
+		chv_enable_pll(crtc, new_crtc_state);
 	} else {
-		vlv_prepare_pll(intel_crtc, pipe_config);
-		vlv_enable_pll(intel_crtc, pipe_config);
+		vlv_prepare_pll(crtc, new_crtc_state);
+		vlv_enable_pll(crtc, new_crtc_state);
 	}
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	i9xx_pfit_enable(pipe_config);
+	i9xx_pfit_enable(new_crtc_state);
 
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(pipe_config);
+	intel_disable_primary_plane(new_crtc_state);
 
-	dev_priv->display.initial_watermarks(state, pipe_config);
-	intel_enable_pipe(pipe_config);
+	dev_priv->display.initial_watermarks(state, crtc);
+	intel_enable_pipe(new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 }
 
 static void i9xx_set_pll_dividers(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	I915_WRITE(FP0(crtc->pipe), crtc_state->dpll_hw_state.fp0);
 	I915_WRITE(FP1(crtc->pipe), crtc_state->dpll_hw_state.fp1);
 }
 
-static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config,
-			     struct intel_atomic_state *state)
+static void i9xx_crtc_enable(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	const struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
-	if (WARN_ON(intel_crtc->active))
+	if (WARN_ON(crtc->active))
 		return;
 
-	i9xx_set_pll_dividers(pipe_config);
+	i9xx_set_pll_dividers(new_crtc_state);
 
-	if (intel_crtc_has_dp_encoder(pipe_config))
-		intel_dp_set_m_n(pipe_config, M1_N1);
+	if (intel_crtc_has_dp_encoder(new_crtc_state))
+		intel_dp_set_m_n(new_crtc_state, M1_N1);
 
-	intel_set_pipe_timings(pipe_config);
-	intel_set_pipe_src_size(pipe_config);
+	intel_set_pipe_timings(new_crtc_state);
+	intel_set_pipe_src_size(new_crtc_state);
 
-	i9xx_set_pipeconf(pipe_config);
+	i9xx_set_pipeconf(new_crtc_state);
 
-	intel_crtc->active = true;
+	crtc->active = true;
 
 	if (!IS_GEN(dev_priv, 2))
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 
-	intel_encoders_pre_enable(intel_crtc, pipe_config, state);
+	intel_encoders_pre_enable(state, crtc);
 
-	i9xx_enable_pll(intel_crtc, pipe_config);
+	i9xx_enable_pll(crtc, new_crtc_state);
 
-	i9xx_pfit_enable(pipe_config);
+	i9xx_pfit_enable(new_crtc_state);
 
-	intel_color_load_luts(pipe_config);
-	intel_color_commit(pipe_config);
+	intel_color_load_luts(new_crtc_state);
+	intel_color_commit(new_crtc_state);
 	/* update DSPCNTR to configure gamma for pipe bottom color */
-	intel_disable_primary_plane(pipe_config);
+	intel_disable_primary_plane(new_crtc_state);
 
-	if (dev_priv->display.initial_watermarks != NULL)
-		dev_priv->display.initial_watermarks(state,
-						     pipe_config);
+	if (dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state, crtc);
 	else
-		intel_update_watermarks(intel_crtc);
-	intel_enable_pipe(pipe_config);
+		intel_update_watermarks(crtc);
+	intel_enable_pipe(new_crtc_state);
 
-	assert_vblank_disabled(crtc);
-	intel_crtc_vblank_on(pipe_config);
+	intel_crtc_vblank_on(new_crtc_state);
 
-	intel_encoders_enable(intel_crtc, pipe_config, state);
+	intel_encoders_enable(state, crtc);
 }
 
 static void i9xx_pfit_disable(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!old_crtc_state->gmch_pfit.control)
 		return;
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, old_crtc_state->cpu_transcoder);
 
 	DRM_DEBUG_KMS("disabling pfit, current: 0x%08x\n",
 		      I915_READ(PFIT_CONTROL));
 	I915_WRITE(PFIT_CONTROL, 0);
 }
 
-static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
-			      struct intel_atomic_state *state)
+static void i9xx_crtc_disable(struct intel_atomic_state *state,
+			      struct intel_crtc *crtc)
 {
-	struct drm_crtc *crtc = old_crtc_state->base.crtc;
-	struct drm_device *dev = crtc->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum pipe pipe = intel_crtc->pipe;
+	struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	/*
 	 * On gen2 planes are double buffered but the pipe isn't, so we must
@@ -7097,16 +7438,15 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	if (IS_GEN(dev_priv, 2))
 		intel_wait_for_vblank(dev_priv, pipe);
 
-	intel_encoders_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_disable(state, crtc);
 
-	drm_crtc_vblank_off(crtc);
-	assert_vblank_disabled(crtc);
+	intel_crtc_vblank_off(old_crtc_state);
 
 	intel_disable_pipe(old_crtc_state);
 
 	i9xx_pfit_disable(old_crtc_state);
 
-	intel_encoders_post_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_post_disable(state, crtc);
 
 	if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DSI)) {
 		if (IS_CHERRYVIEW(dev_priv))
@@ -7117,92 +7457,97 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
 			i9xx_disable_pll(old_crtc_state);
 	}
 
-	intel_encoders_post_pll_disable(intel_crtc, old_crtc_state, state);
+	intel_encoders_post_pll_disable(state, crtc);
 
 	if (!IS_GEN(dev_priv, 2))
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	if (!dev_priv->display.initial_watermarks)
-		intel_update_watermarks(intel_crtc);
+		intel_update_watermarks(crtc);
 
 	/* clock the pipe down to 640x480@60 to potentially save power */
 	if (IS_I830(dev_priv))
 		i830_enable_pipe(dev_priv, pipe);
 }
 
-static void intel_crtc_disable_noatomic(struct drm_crtc *crtc,
+static void intel_crtc_disable_noatomic(struct intel_crtc *crtc,
 					struct drm_modeset_acquire_ctx *ctx)
 {
 	struct intel_encoder *encoder;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_bw_state *bw_state =
 		to_intel_bw_state(dev_priv->bw_obj.state);
+	struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
 	enum intel_display_power_domain domain;
 	struct intel_plane *plane;
-	u64 domains;
 	struct drm_atomic_state *state;
-	struct intel_crtc_state *crtc_state;
+	struct intel_crtc_state *temp_crtc_state;
+	enum pipe pipe = crtc->pipe;
+	u64 domains;
 	int ret;
 
-	if (!intel_crtc->active)
+	if (!crtc_state->hw.active)
 		return;
 
-	for_each_intel_plane_on_crtc(&dev_priv->drm, intel_crtc, plane) {
+	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 		const struct intel_plane_state *plane_state =
 			to_intel_plane_state(plane->base.state);
 
-		if (plane_state->base.visible)
-			intel_plane_disable_noatomic(intel_crtc, plane);
+		if (plane_state->uapi.visible)
+			intel_plane_disable_noatomic(crtc, plane);
 	}
 
-	state = drm_atomic_state_alloc(crtc->dev);
+	state = drm_atomic_state_alloc(&dev_priv->drm);
 	if (!state) {
 		DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory",
-			      crtc->base.id, crtc->name);
+			      crtc->base.base.id, crtc->base.name);
 		return;
 	}
 
 	state->acquire_ctx = ctx;
 
 	/* Everything's already locked, -EDEADLK can't happen. */
-	crtc_state = intel_atomic_get_crtc_state(state, intel_crtc);
-	ret = drm_atomic_add_affected_connectors(state, crtc);
+	temp_crtc_state = intel_atomic_get_crtc_state(state, crtc);
+	ret = drm_atomic_add_affected_connectors(state, &crtc->base);
 
-	WARN_ON(IS_ERR(crtc_state) || ret);
+	WARN_ON(IS_ERR(temp_crtc_state) || ret);
 
-	dev_priv->display.crtc_disable(crtc_state, to_intel_atomic_state(state));
+	dev_priv->display.crtc_disable(to_intel_atomic_state(state), crtc);
 
 	drm_atomic_state_put(state);
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s] hw state adjusted, was enabled, now disabled\n",
-		      crtc->base.id, crtc->name);
+		      crtc->base.base.id, crtc->base.name);
 
-	WARN_ON(drm_atomic_set_mode_for_crtc(crtc->state, NULL) < 0);
-	crtc->state->active = false;
-	intel_crtc->active = false;
-	crtc->enabled = false;
-	crtc->state->connector_mask = 0;
-	crtc->state->encoder_mask = 0;
+	crtc->active = false;
+	crtc->base.enabled = false;
+
+	WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->uapi, NULL) < 0);
+	crtc_state->uapi.active = false;
+	crtc_state->uapi.connector_mask = 0;
+	crtc_state->uapi.encoder_mask = 0;
+	intel_crtc_free_hw_state(crtc_state);
+	memset(&crtc_state->hw, 0, sizeof(crtc_state->hw));
 
-	for_each_encoder_on_crtc(crtc->dev, crtc, encoder)
+	for_each_encoder_on_crtc(&dev_priv->drm, &crtc->base, encoder)
 		encoder->base.crtc = NULL;
 
-	intel_fbc_disable(intel_crtc);
-	intel_update_watermarks(intel_crtc);
-	intel_disable_shared_dpll(to_intel_crtc_state(crtc->state));
+	intel_fbc_disable(crtc);
+	intel_update_watermarks(crtc);
+	intel_disable_shared_dpll(crtc_state);
 
-	domains = intel_crtc->enabled_power_domains;
+	domains = crtc->enabled_power_domains;
 	for_each_power_domain(domain, domains)
 		intel_display_power_put_unchecked(dev_priv, domain);
-	intel_crtc->enabled_power_domains = 0;
+	crtc->enabled_power_domains = 0;
 
-	dev_priv->active_pipes &= ~BIT(intel_crtc->pipe);
-	dev_priv->min_cdclk[intel_crtc->pipe] = 0;
-	dev_priv->min_voltage_level[intel_crtc->pipe] = 0;
+	dev_priv->active_pipes &= ~BIT(pipe);
+	dev_priv->min_cdclk[pipe] = 0;
+	dev_priv->min_voltage_level[pipe] = 0;
 
-	bw_state->data_rate[intel_crtc->pipe] = 0;
-	bw_state->num_active_planes[intel_crtc->pipe] = 0;
+	bw_state->data_rate[pipe] = 0;
+	bw_state->num_active_planes[pipe] = 0;
 }
 
 /*
@@ -7252,8 +7597,8 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 		if (!crtc_state)
 			return;
 
-		I915_STATE_WARN(!crtc_state->base.active,
-		      "connector is active, but attached crtc isn't\n");
+		I915_STATE_WARN(!crtc_state->hw.active,
+				"connector is active, but attached crtc isn't\n");
 
 		if (!encoder || encoder->type == INTEL_OUTPUT_DP_MST)
 			return;
@@ -7264,8 +7609,8 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 		I915_STATE_WARN(conn_state->crtc != encoder->base.crtc,
 			"attached encoder crtc differs from connector crtc\n");
 	} else {
-		I915_STATE_WARN(crtc_state && crtc_state->base.active,
-			"attached crtc is active, but connector isn't\n");
+		I915_STATE_WARN(crtc_state && crtc_state->hw.active,
+				"attached crtc is active, but connector isn't\n");
 		I915_STATE_WARN(!crtc_state && conn_state->best_encoder,
 			"best encoder set without crtc!\n");
 	}
@@ -7273,17 +7618,17 @@ static void intel_connector_verify_state(struct intel_crtc_state *crtc_state,
 
 static int pipe_required_fdi_lanes(struct intel_crtc_state *crtc_state)
 {
-	if (crtc_state->base.enable && crtc_state->has_pch_encoder)
+	if (crtc_state->hw.enable && crtc_state->has_pch_encoder)
 		return crtc_state->fdi_lanes;
 
 	return 0;
 }
 
-static int ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
-				     struct intel_crtc_state *pipe_config)
+static int ilk_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
+			       struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_atomic_state *state = pipe_config->base.state;
+	struct drm_atomic_state *state = pipe_config->uapi.state;
 	struct intel_crtc *other_crtc;
 	struct intel_crtc_state *other_crtc_state;
 
@@ -7352,11 +7697,11 @@ static int ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
 }
 
 #define RETRY 1
-static int ironlake_fdi_compute_config(struct intel_crtc *intel_crtc,
-				       struct intel_crtc_state *pipe_config)
+static int ilk_fdi_compute_config(struct intel_crtc *intel_crtc,
+				  struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int lane, link_bw, fdi_dotclock, ret;
 	bool needs_recompute = false;
 
@@ -7372,15 +7717,15 @@ retry:
 
 	fdi_dotclock = adjusted_mode->crtc_clock;
 
-	lane = ironlake_get_lanes_required(fdi_dotclock, link_bw,
-					   pipe_config->pipe_bpp);
+	lane = ilk_get_lanes_required(fdi_dotclock, link_bw,
+				      pipe_config->pipe_bpp);
 
 	pipe_config->fdi_lanes = lane;
 
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
 			       link_bw, &pipe_config->fdi_m_n, false, false);
 
-	ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
+	ret = ilk_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
 		return ret;
 
@@ -7402,7 +7747,7 @@ retry:
 
 bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	/* IPS only exists on ULT machines and is tied to pipe A. */
@@ -7432,9 +7777,9 @@ bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state)
 static bool hsw_compute_ips_config(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
+		to_i915(crtc_state->uapi.crtc->dev);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 
 	if (!hsw_crtc_state_ips_capable(crtc_state))
 		return false;
@@ -7473,7 +7818,7 @@ static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
 {
 	u32 pixel_rate;
 
-	pixel_rate = pipe_config->base.adjusted_mode.crtc_clock;
+	pixel_rate = pipe_config->hw.adjusted_mode.crtc_clock;
 
 	/*
 	 * We only use IF-ID interlacing. If we ever use
@@ -7506,12 +7851,12 @@ static u32 ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config)
 
 static void intel_crtc_compute_pixel_rate(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (HAS_GMCH(dev_priv))
 		/* FIXME calculate proper pipe pixel rate for GMCH pfit */
 		crtc_state->pixel_rate =
-			crtc_state->base.adjusted_mode.crtc_clock;
+			crtc_state->hw.adjusted_mode.crtc_clock;
 	else
 		crtc_state->pixel_rate =
 			ilk_pipe_pixel_rate(crtc_state);
@@ -7521,7 +7866,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 				     struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int clock_limit = dev_priv->max_dotclk_freq;
 
 	if (INTEL_GEN(dev_priv) < 4) {
@@ -7547,7 +7892,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 
 	if ((pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 ||
 	     pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR444) &&
-	     pipe_config->base.ctm) {
+	     pipe_config->hw.ctm) {
 		/*
 		 * There is only one pipe CSC unit per pipe, and we need that
 		 * for output conversion from RGB->YCBCR. So if CTM is already
@@ -7586,7 +7931,7 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 	intel_crtc_compute_pixel_rate(pipe_config);
 
 	if (pipe_config->has_pch_encoder)
-		return ironlake_fdi_compute_config(crtc, pipe_config);
+		return ilk_fdi_compute_config(crtc, pipe_config);
 
 	return 0;
 }
@@ -7741,7 +8086,7 @@ static void vlv_pllb_recal_opamp(struct drm_i915_private *dev_priv, enum pipe
 static void intel_pch_transcoder_set_m_n(const struct intel_crtc_state *crtc_state,
 					 const struct intel_link_m_n *m_n)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -7768,7 +8113,7 @@ static void intel_cpu_transcoder_set_m_n(const struct intel_crtc_state *crtc_sta
 					 const struct intel_link_m_n *m_n,
 					 const struct intel_link_m_n *m2_n2)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
@@ -8077,11 +8422,11 @@ int vlv_force_pll_on(struct drm_i915_private *dev_priv, enum pipe pipe,
 	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 	struct intel_crtc_state *pipe_config;
 
-	pipe_config = kzalloc(sizeof(*pipe_config), GFP_KERNEL);
+	pipe_config = intel_crtc_state_alloc(crtc);
 	if (!pipe_config)
 		return -ENOMEM;
 
-	pipe_config->base.crtc = &crtc->base;
+	pipe_config->cpu_transcoder = (enum transcoder)pipe;
 	pipe_config->pixel_multiplier = 1;
 	pipe_config->dpll = *dpll;
 
@@ -8241,11 +8586,11 @@ static void i8xx_compute_dpll(struct intel_crtc *crtc,
 
 static void intel_set_pipe_timings(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 crtc_vtotal, crtc_vblank_end;
 	int vsyncshift = 0;
 
@@ -8303,7 +8648,7 @@ static void intel_set_pipe_timings(const struct intel_crtc_state *crtc_state)
 
 static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 
@@ -8317,7 +8662,7 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
 
 static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
 	if (IS_GEN(dev_priv, 2))
@@ -8339,39 +8684,39 @@ static void intel_get_pipe_timings(struct intel_crtc *crtc,
 	u32 tmp;
 
 	tmp = I915_READ(HTOTAL(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_hdisplay = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_htotal = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_hdisplay = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_htotal = ((tmp >> 16) & 0xffff) + 1;
 
 	if (!transcoder_is_dsi(cpu_transcoder)) {
 		tmp = I915_READ(HBLANK(cpu_transcoder));
-		pipe_config->base.adjusted_mode.crtc_hblank_start =
+		pipe_config->hw.adjusted_mode.crtc_hblank_start =
 							(tmp & 0xffff) + 1;
-		pipe_config->base.adjusted_mode.crtc_hblank_end =
+		pipe_config->hw.adjusted_mode.crtc_hblank_end =
 						((tmp >> 16) & 0xffff) + 1;
 	}
 	tmp = I915_READ(HSYNC(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_hsync_start = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_hsync_end = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_hsync_start = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_hsync_end = ((tmp >> 16) & 0xffff) + 1;
 
 	tmp = I915_READ(VTOTAL(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_vdisplay = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_vtotal = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vdisplay = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vtotal = ((tmp >> 16) & 0xffff) + 1;
 
 	if (!transcoder_is_dsi(cpu_transcoder)) {
 		tmp = I915_READ(VBLANK(cpu_transcoder));
-		pipe_config->base.adjusted_mode.crtc_vblank_start =
+		pipe_config->hw.adjusted_mode.crtc_vblank_start =
 							(tmp & 0xffff) + 1;
-		pipe_config->base.adjusted_mode.crtc_vblank_end =
+		pipe_config->hw.adjusted_mode.crtc_vblank_end =
 						((tmp >> 16) & 0xffff) + 1;
 	}
 	tmp = I915_READ(VSYNC(cpu_transcoder));
-	pipe_config->base.adjusted_mode.crtc_vsync_start = (tmp & 0xffff) + 1;
-	pipe_config->base.adjusted_mode.crtc_vsync_end = ((tmp >> 16) & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vsync_start = (tmp & 0xffff) + 1;
+	pipe_config->hw.adjusted_mode.crtc_vsync_end = ((tmp >> 16) & 0xffff) + 1;
 
 	if (intel_pipe_is_interlaced(pipe_config)) {
-		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_INTERLACE;
-		pipe_config->base.adjusted_mode.crtc_vtotal += 1;
-		pipe_config->base.adjusted_mode.crtc_vblank_end += 1;
+		pipe_config->hw.adjusted_mode.flags |= DRM_MODE_FLAG_INTERLACE;
+		pipe_config->hw.adjusted_mode.crtc_vtotal += 1;
+		pipe_config->hw.adjusted_mode.crtc_vblank_end += 1;
 	}
 }
 
@@ -8386,27 +8731,27 @@ static void intel_get_pipe_src_size(struct intel_crtc *crtc,
 	pipe_config->pipe_src_h = (tmp & 0xffff) + 1;
 	pipe_config->pipe_src_w = ((tmp >> 16) & 0xffff) + 1;
 
-	pipe_config->base.mode.vdisplay = pipe_config->pipe_src_h;
-	pipe_config->base.mode.hdisplay = pipe_config->pipe_src_w;
+	pipe_config->hw.mode.vdisplay = pipe_config->pipe_src_h;
+	pipe_config->hw.mode.hdisplay = pipe_config->pipe_src_w;
 }
 
 void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 				 struct intel_crtc_state *pipe_config)
 {
-	mode->hdisplay = pipe_config->base.adjusted_mode.crtc_hdisplay;
-	mode->htotal = pipe_config->base.adjusted_mode.crtc_htotal;
-	mode->hsync_start = pipe_config->base.adjusted_mode.crtc_hsync_start;
-	mode->hsync_end = pipe_config->base.adjusted_mode.crtc_hsync_end;
+	mode->hdisplay = pipe_config->hw.adjusted_mode.crtc_hdisplay;
+	mode->htotal = pipe_config->hw.adjusted_mode.crtc_htotal;
+	mode->hsync_start = pipe_config->hw.adjusted_mode.crtc_hsync_start;
+	mode->hsync_end = pipe_config->hw.adjusted_mode.crtc_hsync_end;
 
-	mode->vdisplay = pipe_config->base.adjusted_mode.crtc_vdisplay;
-	mode->vtotal = pipe_config->base.adjusted_mode.crtc_vtotal;
-	mode->vsync_start = pipe_config->base.adjusted_mode.crtc_vsync_start;
-	mode->vsync_end = pipe_config->base.adjusted_mode.crtc_vsync_end;
+	mode->vdisplay = pipe_config->hw.adjusted_mode.crtc_vdisplay;
+	mode->vtotal = pipe_config->hw.adjusted_mode.crtc_vtotal;
+	mode->vsync_start = pipe_config->hw.adjusted_mode.crtc_vsync_start;
+	mode->vsync_end = pipe_config->hw.adjusted_mode.crtc_vsync_end;
 
-	mode->flags = pipe_config->base.adjusted_mode.flags;
+	mode->flags = pipe_config->hw.adjusted_mode.flags;
 	mode->type = DRM_MODE_TYPE_DRIVER;
 
-	mode->clock = pipe_config->base.adjusted_mode.crtc_clock;
+	mode->clock = pipe_config->hw.adjusted_mode.crtc_clock;
 
 	mode->hsync = drm_mode_hsync(mode);
 	mode->vrefresh = drm_mode_vrefresh(mode);
@@ -8415,7 +8760,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 
 static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 pipeconf;
 
@@ -8452,7 +8797,7 @@ static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 		}
 	}
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
 		if (INTEL_GEN(dev_priv) < 4 ||
 		    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_SDVO))
 			pipeconf |= PIPECONF_INTERLACE_W_FIELD_INDICATION;
@@ -8468,6 +8813,8 @@ static void i9xx_set_pipeconf(const struct intel_crtc_state *crtc_state)
 
 	pipeconf |= PIPECONF_GAMMA_MODE(crtc_state->gamma_mode);
 
+	pipeconf |= PIPECONF_FRAME_START_DELAY(0);
+
 	I915_WRITE(PIPECONF(crtc->pipe), pipeconf);
 	POSTING_READ(PIPECONF(crtc->pipe));
 }
@@ -8567,9 +8914,9 @@ static int pnv_crtc_compute_clock(struct intel_crtc *crtc,
 			DRM_DEBUG_KMS("using SSC reference clock of %d kHz\n", refclk);
 		}
 
-		limit = &intel_limits_pineview_lvds;
+		limit = &pnv_limits_lvds;
 	} else {
-		limit = &intel_limits_pineview_sdvo;
+		limit = &pnv_limits_sdvo;
 	}
 
 	if (!crtc_state->clock_set &&
@@ -8861,7 +9208,7 @@ bdw_get_pipemisc_output_format(struct intel_crtc *crtc)
 
 static void i9xx_get_pipe_color_config(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
@@ -8985,7 +9332,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	 * but in case the pipe is enabled w/o any ports we need a sane
 	 * default.
 	 */
-	pipe_config->base.adjusted_mode.crtc_clock =
+	pipe_config->hw.adjusted_mode.crtc_clock =
 		pipe_config->port_clock / pipe_config->pixel_multiplier;
 
 	ret = true;
@@ -8996,7 +9343,7 @@ out:
 	return ret;
 }
 
-static void ironlake_init_pch_refclk(struct drm_i915_private *dev_priv)
+static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_encoder *encoder;
 	int i;
@@ -9494,14 +9841,14 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 void intel_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv))
-		ironlake_init_pch_refclk(dev_priv);
+		ilk_init_pch_refclk(dev_priv);
 	else if (HAS_PCH_LPT(dev_priv))
 		lpt_init_pch_refclk(dev_priv);
 }
 
-static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
+static void ilk_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -9529,7 +9876,7 @@ static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
 	if (crtc_state->dither)
 		val |= (PIPECONF_DITHER_EN | PIPECONF_DITHER_TYPE_SP);
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		val |= PIPECONF_INTERLACED_ILK;
 	else
 		val |= PIPECONF_PROGRESSIVE;
@@ -9549,13 +9896,15 @@ static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
 
 	val |= PIPECONF_GAMMA_MODE(crtc_state->gamma_mode);
 
+	val |= PIPECONF_FRAME_START_DELAY(0);
+
 	I915_WRITE(PIPECONF(pipe), val);
 	POSTING_READ(PIPECONF(pipe));
 }
 
-static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
+static void hsw_set_pipeconf(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 val = 0;
@@ -9563,7 +9912,7 @@ static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
 	if (IS_HASWELL(dev_priv) && crtc_state->dither)
 		val |= (PIPECONF_DITHER_EN | PIPECONF_DITHER_TYPE_SP);
 
-	if (crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		val |= PIPECONF_INTERLACED_ILK;
 	else
 		val |= PIPECONF_PROGRESSIVE;
@@ -9578,7 +9927,7 @@ static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
 
 static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 val = 0;
 
@@ -9641,7 +9990,7 @@ int bdw_get_pipemisc_bpp(struct intel_crtc *crtc)
 	}
 }
 
-int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp)
+int ilk_get_lanes_required(int target_clock, int link_bw, int bpp)
 {
 	/*
 	 * Account for spread spectrum to avoid
@@ -9652,14 +10001,14 @@ int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp)
 	return DIV_ROUND_UP(bps, link_bw * 8);
 }
 
-static bool ironlake_needs_fb_cb_tune(struct dpll *dpll, int factor)
+static bool ilk_needs_fb_cb_tune(struct dpll *dpll, int factor)
 {
 	return i9xx_dpll_compute_m(dpll) < factor * dpll->n;
 }
 
-static void ironlake_compute_dpll(struct intel_crtc *crtc,
-				  struct intel_crtc_state *crtc_state,
-				  struct dpll *reduced_clock)
+static void ilk_compute_dpll(struct intel_crtc *crtc,
+			     struct intel_crtc_state *crtc_state,
+			     struct dpll *reduced_clock)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 dpll, fp, fp2;
@@ -9679,7 +10028,7 @@ static void ironlake_compute_dpll(struct intel_crtc *crtc,
 
 	fp = i9xx_dpll_compute_fp(&crtc_state->dpll);
 
-	if (ironlake_needs_fb_cb_tune(&crtc_state->dpll, factor))
+	if (ilk_needs_fb_cb_tune(&crtc_state->dpll, factor))
 		fp |= FP_CB_TUNE;
 
 	if (reduced_clock) {
@@ -9759,12 +10108,12 @@ static void ironlake_compute_dpll(struct intel_crtc *crtc,
 	crtc_state->dpll_hw_state.fp1 = fp2;
 }
 
-static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
-				       struct intel_crtc_state *crtc_state)
+static int ilk_crtc_compute_clock(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	const struct intel_limit *limit;
 	int refclk = 120000;
 
@@ -9784,17 +10133,17 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 
 		if (intel_is_dual_link_lvds(dev_priv)) {
 			if (refclk == 100000)
-				limit = &intel_limits_ironlake_dual_lvds_100m;
+				limit = &ilk_limits_dual_lvds_100m;
 			else
-				limit = &intel_limits_ironlake_dual_lvds;
+				limit = &ilk_limits_dual_lvds;
 		} else {
 			if (refclk == 100000)
-				limit = &intel_limits_ironlake_single_lvds_100m;
+				limit = &ilk_limits_single_lvds_100m;
 			else
-				limit = &intel_limits_ironlake_single_lvds;
+				limit = &ilk_limits_single_lvds;
 		}
 	} else {
-		limit = &intel_limits_ironlake_dac;
+		limit = &ilk_limits_dac;
 	}
 
 	if (!crtc_state->clock_set &&
@@ -9804,7 +10153,7 @@ static int ironlake_crtc_compute_clock(struct intel_crtc *crtc,
 		return -EINVAL;
 	}
 
-	ironlake_compute_dpll(crtc, crtc_state, NULL);
+	ilk_compute_dpll(crtc, crtc_state, NULL);
 
 	if (!intel_reserve_shared_dplls(state, crtc, NULL)) {
 		DRM_DEBUG_KMS("failed to find PLL for pipe %c\n",
@@ -9879,15 +10228,15 @@ void intel_dp_get_m_n(struct intel_crtc *crtc,
 					     &pipe_config->dp_m2_n2);
 }
 
-static void ironlake_get_fdi_m_n_config(struct intel_crtc *crtc,
-					struct intel_crtc_state *pipe_config)
+static void ilk_get_fdi_m_n_config(struct intel_crtc *crtc,
+				   struct intel_crtc_state *pipe_config)
 {
 	intel_cpu_transcoder_get_m_n(crtc, pipe_config->cpu_transcoder,
 				     &pipe_config->fdi_m_n, NULL);
 }
 
-static void skylake_get_pfit_config(struct intel_crtc *crtc,
-				    struct intel_crtc_state *pipe_config)
+static void skl_get_pfit_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -9918,8 +10267,8 @@ static void skylake_get_pfit_config(struct intel_crtc *crtc,
 }
 
 static void
-skylake_get_initial_plane_config(struct intel_crtc *crtc,
-				 struct intel_initial_plane_config *plane_config)
+skl_get_initial_plane_config(struct intel_crtc *crtc,
+			     struct intel_initial_plane_config *plane_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -9977,7 +10326,11 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	case PLANE_CTL_TILED_Y:
 		plane_config->tiling = I915_TILING_Y;
 		if (val & PLANE_CTL_RENDER_DECOMPRESSION_ENABLE)
-			fb->modifier = I915_FORMAT_MOD_Y_TILED_CCS;
+			fb->modifier = INTEL_GEN(dev_priv) >= 12 ?
+				I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS :
+				I915_FORMAT_MOD_Y_TILED_CCS;
+		else if (val & PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE)
+			fb->modifier = I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS;
 		else
 			fb->modifier = I915_FORMAT_MOD_Y_TILED;
 		break;
@@ -10044,8 +10397,8 @@ error:
 	kfree(intel_fb);
 }
 
-static void ironlake_get_pfit_config(struct intel_crtc *crtc,
-				     struct intel_crtc_state *pipe_config)
+static void ilk_get_pfit_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -10068,8 +10421,8 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc,
 	}
 }
 
-static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
-				     struct intel_crtc_state *pipe_config)
+static bool ilk_get_pipe_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -10140,7 +10493,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >>
 					  FDI_DP_PORT_WIDTH_SHIFT) + 1;
 
-		ironlake_get_fdi_m_n_config(crtc, pipe_config);
+		ilk_get_fdi_m_n_config(crtc, pipe_config);
 
 		if (HAS_PCH_IBX(dev_priv)) {
 			/*
@@ -10168,7 +10521,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 			((tmp & PLL_REF_SDVO_HDMI_MULTIPLIER_MASK)
 			 >> PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT) + 1;
 
-		ironlake_pch_clock_get(crtc, pipe_config);
+		ilk_pch_clock_get(crtc, pipe_config);
 	} else {
 		pipe_config->pixel_multiplier = 1;
 	}
@@ -10176,7 +10529,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	intel_get_pipe_timings(crtc, pipe_config);
 	intel_get_pipe_src_size(crtc, pipe_config);
 
-	ironlake_get_pfit_config(crtc, pipe_config);
+	ilk_get_pfit_config(crtc, pipe_config);
 
 	ret = true;
 
@@ -10185,12 +10538,13 @@ out:
 
 	return ret;
 }
-static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
-				      struct intel_crtc_state *crtc_state)
+
+static int hsw_crtc_compute_clock(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 
 	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) ||
 	    INTEL_GEN(dev_priv) >= 11) {
@@ -10207,9 +10561,8 @@ static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 	return 0;
 }
 
-static void cannonlake_get_ddi_pll(struct drm_i915_private *dev_priv,
-				   enum port port,
-				   struct intel_crtc_state *pipe_config)
+static void cnl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum intel_dpll_id id;
 	u32 temp;
@@ -10223,9 +10576,8 @@ static void cannonlake_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
-static void icelake_get_ddi_pll(struct drm_i915_private *dev_priv,
-				enum port port,
-				struct intel_crtc_state *pipe_config)
+static void icl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 	enum icl_port_dpll_id port_dpll_id;
@@ -10284,9 +10636,8 @@ static void bxt_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
-static void skylake_get_ddi_pll(struct drm_i915_private *dev_priv,
-				enum port port,
-				struct intel_crtc_state *pipe_config)
+static void skl_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum intel_dpll_id id;
 	u32 temp;
@@ -10300,9 +10651,8 @@ static void skylake_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
-static void haswell_get_ddi_pll(struct drm_i915_private *dev_priv,
-				enum port port,
-				struct intel_crtc_state *pipe_config)
+static void hsw_get_ddi_pll(struct drm_i915_private *dev_priv, enum port port,
+			    struct intel_crtc_state *pipe_config)
 {
 	enum intel_dpll_id id;
 	u32 ddi_pll_sel = I915_READ(PORT_CLK_SEL(port));
@@ -10403,6 +10753,9 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 		case TRANS_DDI_EDP_INPUT_C_ONOFF:
 			trans_pipe = PIPE_C;
 			break;
+		case TRANS_DDI_EDP_INPUT_D_ONOFF:
+			trans_pipe = PIPE_D;
+			break;
 		}
 
 		if (trans_pipe == crtc->pipe) {
@@ -10487,31 +10840,36 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 	return transcoder_is_dsi(pipe_config->cpu_transcoder);
 }
 
-static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
-				       struct intel_crtc_state *pipe_config)
+static void hsw_get_ddi_port_state(struct intel_crtc *crtc,
+				   struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	struct intel_shared_dpll *pll;
 	enum port port;
 	u32 tmp;
 
-	tmp = I915_READ(TRANS_DDI_FUNC_CTL(pipe_config->cpu_transcoder));
-
-	if (INTEL_GEN(dev_priv) >= 12)
-		port = TGL_TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
-	else
-		port = TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
+	if (transcoder_is_dsi(cpu_transcoder)) {
+		port = (cpu_transcoder == TRANSCODER_DSI_A) ?
+						PORT_A : PORT_B;
+	} else {
+		tmp = I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder));
+		if (INTEL_GEN(dev_priv) >= 12)
+			port = TGL_TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
+		else
+			port = TRANS_DDI_FUNC_CTL_VAL_TO_PORT(tmp);
+	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		icelake_get_ddi_pll(dev_priv, port, pipe_config);
+		icl_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_CANNONLAKE(dev_priv))
-		cannonlake_get_ddi_pll(dev_priv, port, pipe_config);
+		cnl_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_GEN9_BC(dev_priv))
-		skylake_get_ddi_pll(dev_priv, port, pipe_config);
+		skl_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_GEN9_LP(dev_priv))
 		bxt_get_ddi_pll(dev_priv, port, pipe_config);
 	else
-		haswell_get_ddi_pll(dev_priv, port, pipe_config);
+		hsw_get_ddi_pll(dev_priv, port, pipe_config);
 
 	pll = pipe_config->shared_dpll;
 	if (pll) {
@@ -10532,7 +10890,7 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 		pipe_config->fdi_lanes = ((FDI_DP_PORT_WIDTH_MASK & tmp) >>
 					  FDI_DP_PORT_WIDTH_SHIFT) + 1;
 
-		ironlake_get_fdi_m_n_config(crtc, pipe_config);
+		ilk_get_fdi_m_n_config(crtc, pipe_config);
 	}
 }
 
@@ -10554,9 +10912,9 @@ static enum transcoder transcoder_master_readout(struct drm_i915_private *dev_pr
 		return master_select - 1;
 }
 
-static void icelake_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
+static void icl_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 transcoders;
 	enum transcoder cpu_transcoder;
 
@@ -10589,8 +10947,8 @@ static void icelake_get_trans_port_sync_config(struct intel_crtc_state *crtc_sta
 		crtc_state->sync_mode_slaves_mask);
 }
 
-static bool haswell_get_pipe_config(struct intel_crtc *crtc,
-				    struct intel_crtc_state *pipe_config)
+static bool hsw_get_pipe_config(struct intel_crtc *crtc,
+				struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	intel_wakeref_t wakerefs[POWER_DOMAIN_NUM], wf;
@@ -10598,8 +10956,6 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	u64 power_domain_mask;
 	bool active;
 
-	intel_crtc_init_scalers(crtc, pipe_config);
-
 	pipe_config->master_transcoder = INVALID_TRANSCODER;
 
 	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
@@ -10627,7 +10983,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	if (!transcoder_is_dsi(pipe_config->cpu_transcoder) ||
 	    INTEL_GEN(dev_priv) >= 11) {
-		haswell_get_ddi_port_state(crtc, pipe_config);
+		hsw_get_ddi_port_state(crtc, pipe_config);
 		intel_get_pipe_timings(crtc, pipe_config);
 	}
 
@@ -10684,9 +11040,9 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		power_domain_mask |= BIT_ULL(power_domain);
 
 		if (INTEL_GEN(dev_priv) >= 9)
-			skylake_get_pfit_config(crtc, pipe_config);
+			skl_get_pfit_config(crtc, pipe_config);
 		else
-			ironlake_get_pfit_config(crtc, pipe_config);
+			ilk_get_pfit_config(crtc, pipe_config);
 	}
 
 	if (hsw_crtc_supports_ips(crtc)) {
@@ -10712,7 +11068,7 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	if (INTEL_GEN(dev_priv) >= 11 &&
 	    !transcoder_is_dsi(pipe_config->cpu_transcoder))
-		icelake_get_trans_port_sync_config(pipe_config);
+		icl_get_trans_port_sync_config(pipe_config);
 
 out:
 	for_each_power_domain(power_domain, power_domain_mask)
@@ -10725,8 +11081,8 @@ out:
 static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	const struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 base;
 
@@ -10740,8 +11096,8 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 
 static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
 {
-	int x = plane_state->base.dst.x1;
-	int y = plane_state->base.dst.y1;
+	int x = plane_state->uapi.dst.x1;
+	int y = plane_state->uapi.dst.y1;
 	u32 pos = 0;
 
 	if (x < 0) {
@@ -10762,9 +11118,9 @@ static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
 static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
 	const struct drm_mode_config *config =
-		&plane_state->base.plane->dev->mode_config;
-	int width = drm_rect_width(&plane_state->base.dst);
-	int height = drm_rect_height(&plane_state->base.dst);
+		&plane_state->uapi.plane->dev->mode_config;
+	int width = drm_rect_width(&plane_state->uapi.dst);
+	int height = drm_rect_height(&plane_state->uapi.dst);
 
 	return width > 0 && width <= config->cursor_width &&
 		height > 0 && height <= config->cursor_height;
@@ -10773,8 +11129,8 @@ static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state)
 static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	unsigned int rotation = plane_state->hw.rotation;
 	int src_x, src_y;
 	u32 offset;
 	int ret;
@@ -10783,11 +11139,11 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
-	src_x = plane_state->base.src.x1 >> 16;
-	src_y = plane_state->base.src.y1 >> 16;
+	src_x = plane_state->uapi.src.x1 >> 16;
+	src_y = plane_state->uapi.src.y1 >> 16;
 
 	intel_add_fb_offsets(&src_x, &src_y, plane_state, 0);
 	offset = intel_plane_compute_aligned_offset(&src_x, &src_y,
@@ -10802,14 +11158,14 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate_to(&plane_state->base.src,
+	drm_rect_translate_to(&plane_state->uapi.src,
 			      src_x << 16, src_y << 16);
 
 	/* ILK+ do this automagically in hardware */
 	if (HAS_GMCH(dev_priv) && rotation & DRM_MODE_ROTATE_180) {
-		const struct drm_framebuffer *fb = plane_state->base.fb;
-		int src_w = drm_rect_width(&plane_state->base.src) >> 16;
-		int src_h = drm_rect_height(&plane_state->base.src) >> 16;
+		const struct drm_framebuffer *fb = plane_state->hw.fb;
+		int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+		int src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 		offset += (src_h * src_w - 1) * fb->format->cpp[0];
 	}
@@ -10824,7 +11180,7 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 			      struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
 
 	if (fb && fb->modifier != DRM_FORMAT_MOD_LINEAR) {
@@ -10832,8 +11188,8 @@ static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  true, true);
@@ -10841,14 +11197,14 @@ static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	/* Use the unclipped src/dst rectangles, which we program to hw */
-	plane_state->base.src = drm_plane_state_src(&plane_state->base);
-	plane_state->base.dst = drm_plane_state_dest(&plane_state->base);
+	plane_state->uapi.src = drm_plane_state_src(&plane_state->uapi);
+	plane_state->uapi.dst = drm_plane_state_dest(&plane_state->uapi);
 
 	ret = intel_cursor_check_surface(plane_state);
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -10886,7 +11242,7 @@ static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state,
 
 static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
-	int width = drm_rect_width(&plane_state->base.dst);
+	int width = drm_rect_width(&plane_state->uapi.dst);
 
 	/*
 	 * 845g/865g are only limited by the width of their cursors,
@@ -10898,7 +11254,7 @@ static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state)
 static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 			     struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int ret;
 
 	ret = intel_check_cursor(crtc_state, plane_state);
@@ -10912,12 +11268,12 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 	/* Check for which cursor types we support */
 	if (!i845_cursor_size_ok(plane_state)) {
 		DRM_DEBUG("Cursor dimension %dx%d not supported\n",
-			  drm_rect_width(&plane_state->base.dst),
-			  drm_rect_height(&plane_state->base.dst));
+			  drm_rect_width(&plane_state->uapi.dst),
+			  drm_rect_height(&plane_state->uapi.dst));
 		return -EINVAL;
 	}
 
-	WARN_ON(plane_state->base.visible &&
+	WARN_ON(plane_state->uapi.visible &&
 		plane_state->color_plane[0].stride != fb->pitches[0]);
 
 	switch (fb->pitches[0]) {
@@ -10945,9 +11301,9 @@ static void i845_update_cursor(struct intel_plane *plane,
 	u32 cntl = 0, base = 0, pos = 0, size = 0;
 	unsigned long irqflags;
 
-	if (plane_state && plane_state->base.visible) {
-		unsigned int width = drm_rect_width(&plane_state->base.dst);
-		unsigned int height = drm_rect_height(&plane_state->base.dst);
+	if (plane_state && plane_state->uapi.visible) {
+		unsigned int width = drm_rect_width(&plane_state->uapi.dst);
+		unsigned int height = drm_rect_height(&plane_state->uapi.dst);
 
 		cntl = plane_state->ctl |
 			i845_cursor_ctl_crtc(crtc_state);
@@ -11020,7 +11376,7 @@ i9xx_cursor_max_stride(struct intel_plane *plane,
 
 static u32 i9xx_cursor_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 cntl = 0;
 
@@ -11043,13 +11399,13 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
+		to_i915(plane_state->uapi.plane->dev);
 	u32 cntl = 0;
 
 	if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv))
 		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
 
-	switch (drm_rect_width(&plane_state->base.dst)) {
+	switch (drm_rect_width(&plane_state->uapi.dst)) {
 	case 64:
 		cntl |= MCURSOR_MODE_64_ARGB_AX;
 		break;
@@ -11060,11 +11416,11 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 		cntl |= MCURSOR_MODE_256_ARGB_AX;
 		break;
 	default:
-		MISSING_CASE(drm_rect_width(&plane_state->base.dst));
+		MISSING_CASE(drm_rect_width(&plane_state->uapi.dst));
 		return 0;
 	}
 
-	if (plane_state->base.rotation & DRM_MODE_ROTATE_180)
+	if (plane_state->hw.rotation & DRM_MODE_ROTATE_180)
 		cntl |= MCURSOR_ROTATE_180;
 
 	return cntl;
@@ -11073,9 +11429,9 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	int width = drm_rect_width(&plane_state->base.dst);
-	int height = drm_rect_height(&plane_state->base.dst);
+		to_i915(plane_state->uapi.plane->dev);
+	int width = drm_rect_width(&plane_state->uapi.dst);
+	int height = drm_rect_height(&plane_state->uapi.dst);
 
 	if (!intel_cursor_size_ok(plane_state))
 		return false;
@@ -11097,7 +11453,7 @@ static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 	 * cursors.
 	 */
 	if (HAS_CUR_FBC(dev_priv) &&
-	    plane_state->base.rotation & DRM_MODE_ROTATE_0) {
+	    plane_state->hw.rotation & DRM_MODE_ROTATE_0) {
 		if (height < 8 || height > width)
 			return false;
 	} else {
@@ -11111,9 +11467,9 @@ static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 			     struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	int ret;
 
@@ -11128,19 +11484,19 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	/* Check for which cursor types we support */
 	if (!i9xx_cursor_size_ok(plane_state)) {
 		DRM_DEBUG("Cursor dimension %dx%d not supported\n",
-			  drm_rect_width(&plane_state->base.dst),
-			  drm_rect_height(&plane_state->base.dst));
+			  drm_rect_width(&plane_state->uapi.dst),
+			  drm_rect_height(&plane_state->uapi.dst));
 		return -EINVAL;
 	}
 
-	WARN_ON(plane_state->base.visible &&
+	WARN_ON(plane_state->uapi.visible &&
 		plane_state->color_plane[0].stride != fb->pitches[0]);
 
 	if (fb->pitches[0] !=
-	    drm_rect_width(&plane_state->base.dst) * fb->format->cpp[0]) {
+	    drm_rect_width(&plane_state->uapi.dst) * fb->format->cpp[0]) {
 		DRM_DEBUG_KMS("Invalid cursor stride (%u) (cursor width %d)\n",
 			      fb->pitches[0],
-			      drm_rect_width(&plane_state->base.dst));
+			      drm_rect_width(&plane_state->uapi.dst));
 		return -EINVAL;
 	}
 
@@ -11155,7 +11511,7 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	 * Refuse the put the cursor into that compromised position.
 	 */
 	if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_C &&
-	    plane_state->base.visible && plane_state->base.dst.x1 < 0) {
+	    plane_state->uapi.visible && plane_state->uapi.dst.x1 < 0) {
 		DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n");
 		return -EINVAL;
 	}
@@ -11174,9 +11530,9 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 	u32 cntl = 0, base = 0, pos = 0, fbc_ctl = 0;
 	unsigned long irqflags;
 
-	if (plane_state && plane_state->base.visible) {
-		unsigned width = drm_rect_width(&plane_state->base.dst);
-		unsigned height = drm_rect_height(&plane_state->base.dst);
+	if (plane_state && plane_state->uapi.visible) {
+		unsigned width = drm_rect_width(&plane_state->uapi.dst);
+		unsigned height = drm_rect_height(&plane_state->uapi.dst);
 
 		cntl = plane_state->ctl |
 			i9xx_cursor_ctl_crtc(crtc_state);
@@ -11332,7 +11688,7 @@ int intel_get_load_detect_pipe(struct drm_connector *connector,
 {
 	struct intel_crtc *intel_crtc;
 	struct intel_encoder *intel_encoder =
-		intel_attached_encoder(connector);
+		intel_attached_encoder(to_intel_connector(connector));
 	struct drm_crtc *possible_crtc;
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_crtc *crtc = NULL;
@@ -11431,9 +11787,9 @@ found:
 		goto fail;
 	}
 
-	crtc_state->base.active = crtc_state->base.enable = true;
+	crtc_state->uapi.active = true;
 
-	ret = drm_atomic_set_mode_for_crtc(&crtc_state->base,
+	ret = drm_atomic_set_mode_for_crtc(&crtc_state->uapi,
 					   &load_detect_mode);
 	if (ret)
 		goto fail;
@@ -11486,7 +11842,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct drm_modeset_acquire_ctx *ctx)
 {
 	struct intel_encoder *intel_encoder =
-		intel_attached_encoder(connector);
+		intel_attached_encoder(to_intel_connector(connector));
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_atomic_state *state = old->restore_state;
 	int ret;
@@ -11629,8 +11985,8 @@ int intel_dotclock_calculate(int link_freq,
 	return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n);
 }
 
-static void ironlake_pch_clock_get(struct intel_crtc *crtc,
-				   struct intel_crtc_state *pipe_config)
+static void ilk_pch_clock_get(struct intel_crtc *crtc,
+			      struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
@@ -11642,11 +11998,38 @@ static void ironlake_pch_clock_get(struct intel_crtc *crtc,
 	 * we may need some idea for the dotclock anyway.
 	 * Calculate one based on the FDI configuration.
 	 */
-	pipe_config->base.adjusted_mode.crtc_clock =
+	pipe_config->hw.adjusted_mode.crtc_clock =
 		intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, pipe_config),
 					 &pipe_config->fdi_m_n);
 }
 
+static void intel_crtc_state_reset(struct intel_crtc_state *crtc_state,
+				   struct intel_crtc *crtc)
+{
+	memset(crtc_state, 0, sizeof(*crtc_state));
+
+	__drm_atomic_helper_crtc_state_reset(&crtc_state->uapi, &crtc->base);
+
+	crtc_state->cpu_transcoder = INVALID_TRANSCODER;
+	crtc_state->master_transcoder = INVALID_TRANSCODER;
+	crtc_state->hsw_workaround_pipe = INVALID_PIPE;
+	crtc_state->output_format = INTEL_OUTPUT_FORMAT_INVALID;
+	crtc_state->scaler_state.scaler_id = -1;
+	crtc_state->mst_master_transcoder = INVALID_TRANSCODER;
+}
+
+static struct intel_crtc_state *intel_crtc_state_alloc(struct intel_crtc *crtc)
+{
+	struct intel_crtc_state *crtc_state;
+
+	crtc_state = kmalloc(sizeof(*crtc_state), GFP_KERNEL);
+
+	if (crtc_state)
+		intel_crtc_state_reset(crtc_state, crtc);
+
+	return crtc_state;
+}
+
 /* Returns the currently programmed mode of the given encoder. */
 struct drm_display_mode *
 intel_encoder_current_mode(struct intel_encoder *encoder)
@@ -11666,14 +12049,12 @@ intel_encoder_current_mode(struct intel_encoder *encoder)
 	if (!mode)
 		return NULL;
 
-	crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL);
+	crtc_state = intel_crtc_state_alloc(crtc);
 	if (!crtc_state) {
 		kfree(mode);
 		return NULL;
 	}
 
-	crtc_state->base.crtc = &crtc->base;
-
 	if (!dev_priv->display.get_pipe_config(crtc, crtc_state)) {
 		kfree(crtc_state);
 		kfree(mode);
@@ -11711,18 +12092,18 @@ static bool intel_wm_need_update(const struct intel_plane_state *cur,
 				 struct intel_plane_state *new)
 {
 	/* Update watermarks on tiling or size changes. */
-	if (new->base.visible != cur->base.visible)
+	if (new->uapi.visible != cur->uapi.visible)
 		return true;
 
-	if (!cur->base.fb || !new->base.fb)
+	if (!cur->hw.fb || !new->hw.fb)
 		return false;
 
-	if (cur->base.fb->modifier != new->base.fb->modifier ||
-	    cur->base.rotation != new->base.rotation ||
-	    drm_rect_width(&new->base.src) != drm_rect_width(&cur->base.src) ||
-	    drm_rect_height(&new->base.src) != drm_rect_height(&cur->base.src) ||
-	    drm_rect_width(&new->base.dst) != drm_rect_width(&cur->base.dst) ||
-	    drm_rect_height(&new->base.dst) != drm_rect_height(&cur->base.dst))
+	if (cur->hw.fb->modifier != new->hw.fb->modifier ||
+	    cur->hw.rotation != new->hw.rotation ||
+	    drm_rect_width(&new->uapi.src) != drm_rect_width(&cur->uapi.src) ||
+	    drm_rect_height(&new->uapi.src) != drm_rect_height(&cur->uapi.src) ||
+	    drm_rect_width(&new->uapi.dst) != drm_rect_width(&cur->uapi.dst) ||
+	    drm_rect_height(&new->uapi.dst) != drm_rect_height(&cur->uapi.dst))
 		return true;
 
 	return false;
@@ -11730,10 +12111,10 @@ static bool intel_wm_need_update(const struct intel_plane_state *cur,
 
 static bool needs_scaling(const struct intel_plane_state *state)
 {
-	int src_w = drm_rect_width(&state->base.src) >> 16;
-	int src_h = drm_rect_height(&state->base.src) >> 16;
-	int dst_w = drm_rect_width(&state->base.dst);
-	int dst_h = drm_rect_height(&state->base.dst);
+	int src_w = drm_rect_width(&state->uapi.src) >> 16;
+	int src_h = drm_rect_height(&state->uapi.src) >> 16;
+	int dst_w = drm_rect_width(&state->uapi.dst);
+	int dst_h = drm_rect_height(&state->uapi.dst);
 
 	return (src_w != dst_w || src_h != dst_h);
 }
@@ -11743,12 +12124,12 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 				    const struct intel_plane_state *old_plane_state,
 				    struct intel_plane_state *plane_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	bool mode_changed = needs_modeset(crtc_state);
-	bool was_crtc_enabled = old_crtc_state->base.active;
-	bool is_crtc_enabled = crtc_state->base.active;
+	bool was_crtc_enabled = old_crtc_state->hw.active;
+	bool is_crtc_enabled = crtc_state->hw.active;
 	bool turn_off, turn_on, visible, was_visible;
 	int ret;
 
@@ -11758,8 +12139,8 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 			return ret;
 	}
 
-	was_visible = old_plane_state->base.visible;
-	visible = plane_state->base.visible;
+	was_visible = old_plane_state->uapi.visible;
+	visible = plane_state->uapi.visible;
 
 	if (!was_crtc_enabled && WARN_ON(was_visible))
 		was_visible = false;
@@ -11775,7 +12156,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 	 * only combine the results from all planes in the current place?
 	 */
 	if (!is_crtc_enabled) {
-		plane_state->base.visible = visible = false;
+		plane_state->uapi.visible = visible = false;
 		crtc_state->active_planes &= ~BIT(plane->id);
 		crtc_state->data_rate[plane->id] = 0;
 		crtc_state->min_cdclk[plane->id] = 0;
@@ -11916,9 +12297,9 @@ static int icl_add_linked_planes(struct intel_atomic_state *state)
 
 static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->base.state);
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
 	struct intel_plane *plane, *linked;
 	struct intel_plane_state *plane_state;
 	int i;
@@ -11935,7 +12316,7 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 			continue;
 
 		plane_state->planar_linked_plane = NULL;
-		if (plane_state->planar_slave && !plane_state->base.visible) {
+		if (plane_state->planar_slave && !plane_state->uapi.visible) {
 			crtc_state->active_planes &= ~BIT(plane->id);
 			crtc_state->update_planes |= BIT(plane->id);
 		}
@@ -11981,6 +12362,25 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 		crtc_state->active_planes |= BIT(linked->id);
 		crtc_state->update_planes |= BIT(linked->id);
 		DRM_DEBUG_KMS("Using %s as Y plane for %s\n", linked->base.name, plane->base.name);
+
+		/* Copy parameters to slave plane */
+		linked_state->ctl = plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE;
+		linked_state->color_ctl = plane_state->color_ctl;
+		memcpy(linked_state->color_plane, plane_state->color_plane,
+		       sizeof(linked_state->color_plane));
+
+		intel_plane_copy_uapi_to_hw_state(linked_state, plane_state);
+		linked_state->uapi.src = plane_state->uapi.src;
+		linked_state->uapi.dst = plane_state->uapi.dst;
+
+		if (icl_is_hdr_plane(dev_priv, plane->id)) {
+			if (linked->id == PLANE_SPRITE5)
+				plane_state->cus_ctl |= PLANE_CUS_PLANE_7;
+			else if (linked->id == PLANE_SPRITE4)
+				plane_state->cus_ctl |= PLANE_CUS_PLANE_6;
+			else
+				MISSING_CASE(linked->id);
+		}
 	}
 
 	return 0;
@@ -11988,97 +12388,130 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 
 static bool c8_planes_changed(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(state, crtc);
 
 	return !old_crtc_state->c8_planes != !new_crtc_state->c8_planes;
 }
 
-static int icl_add_sync_mode_crtcs(struct intel_crtc_state *crtc_state)
+static bool
+intel_atomic_is_master_connector(struct intel_crtc_state *crtc_state)
 {
-	struct drm_crtc *crtc = crtc_state->base.crtc;
-	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->base.state);
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct drm_connector *master_connector, *connector;
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
+	int i;
+
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->crtc != crtc)
+			continue;
+		if (connector->has_tile &&
+		    connector->tile_h_loc == connector->num_h_tile - 1 &&
+		    connector->tile_v_loc == connector->num_v_tile - 1)
+			return true;
+	}
+
+	return false;
+}
+
+static void reset_port_sync_mode_state(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->master_transcoder = INVALID_TRANSCODER;
+	crtc_state->sync_mode_slaves_mask = 0;
+}
+
+static int icl_compute_port_sync_crtc_state(struct drm_connector *connector,
+					    struct intel_crtc_state *crtc_state,
+					    int num_tiled_conns)
+{
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->uapi.state);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	struct drm_connector *master_connector;
 	struct drm_connector_list_iter conn_iter;
 	struct drm_crtc *master_crtc = NULL;
 	struct drm_crtc_state *master_crtc_state;
 	struct intel_crtc_state *master_pipe_config;
-	int i, tile_group_id;
 
 	if (INTEL_GEN(dev_priv) < 11)
 		return 0;
 
+	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP))
+		return 0;
+
 	/*
 	 * In case of tiled displays there could be one or more slaves but there is
 	 * only one master. Lets make the CRTC used by the connector corresponding
 	 * to the last horizonal and last vertical tile a master/genlock CRTC.
 	 * All the other CRTCs corresponding to other tiles of the same Tile group
 	 * are the slave CRTCs and hold a pointer to their genlock CRTC.
+	 * If all tiles not present do not make master slave assignments.
 	 */
-	for_each_new_connector_in_state(&state->base, connector, connector_state, i) {
-		if (connector_state->crtc != crtc)
-			continue;
-		if (!connector->has_tile)
+	if (!connector->has_tile ||
+	    crtc_state->hw.mode.hdisplay != connector->tile_h_size ||
+	    crtc_state->hw.mode.vdisplay != connector->tile_v_size ||
+	    num_tiled_conns < connector->num_h_tile * connector->num_v_tile) {
+		reset_port_sync_mode_state(crtc_state);
+		return 0;
+	}
+	/* Last Horizontal and last vertical tile connector is a master
+	 * Master's crtc state is already populated in slave for port sync
+	 */
+	if (connector->tile_h_loc == connector->num_h_tile - 1 &&
+	    connector->tile_v_loc == connector->num_v_tile - 1)
+		return 0;
+
+	/* Loop through all connectors and configure the Slave crtc_state
+	 * to point to the correct master.
+	 */
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+	drm_for_each_connector_iter(master_connector, &conn_iter) {
+		struct drm_connector_state *master_conn_state = NULL;
+
+		if (!(master_connector->has_tile &&
+		      master_connector->tile_group->id == connector->tile_group->id))
 			continue;
-		if (crtc_state->base.mode.hdisplay != connector->tile_h_size ||
-		    crtc_state->base.mode.vdisplay != connector->tile_v_size)
-			return 0;
-		if (connector->tile_h_loc == connector->num_h_tile - 1 &&
-		    connector->tile_v_loc == connector->num_v_tile - 1)
+		if (master_connector->tile_h_loc != master_connector->num_h_tile - 1 ||
+		    master_connector->tile_v_loc != master_connector->num_v_tile - 1)
 			continue;
-		crtc_state->sync_mode_slaves_mask = 0;
-		tile_group_id = connector->tile_group->id;
-		drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
-		drm_for_each_connector_iter(master_connector, &conn_iter) {
-			struct drm_connector_state *master_conn_state = NULL;
-
-			if (!master_connector->has_tile)
-				continue;
-			if (master_connector->tile_h_loc != master_connector->num_h_tile - 1 ||
-			    master_connector->tile_v_loc != master_connector->num_v_tile - 1)
-				continue;
-			if (master_connector->tile_group->id != tile_group_id)
-				continue;
 
-			master_conn_state = drm_atomic_get_connector_state(&state->base,
-									   master_connector);
-			if (IS_ERR(master_conn_state)) {
-				drm_connector_list_iter_end(&conn_iter);
-				return PTR_ERR(master_conn_state);
-			}
-			if (master_conn_state->crtc) {
-				master_crtc = master_conn_state->crtc;
-				break;
-			}
+		master_conn_state = drm_atomic_get_connector_state(&state->base,
+								   master_connector);
+		if (IS_ERR(master_conn_state)) {
+			drm_connector_list_iter_end(&conn_iter);
+			return PTR_ERR(master_conn_state);
 		}
-		drm_connector_list_iter_end(&conn_iter);
-
-		if (!master_crtc) {
-			DRM_DEBUG_KMS("Could not find Master CRTC for Slave CRTC %d\n",
-				      connector_state->crtc->base.id);
-			return -EINVAL;
+		if (master_conn_state->crtc) {
+			master_crtc = master_conn_state->crtc;
+			break;
 		}
+	}
+	drm_connector_list_iter_end(&conn_iter);
 
-		master_crtc_state = drm_atomic_get_crtc_state(&state->base,
-							      master_crtc);
-		if (IS_ERR(master_crtc_state))
-			return PTR_ERR(master_crtc_state);
-
-		master_pipe_config = to_intel_crtc_state(master_crtc_state);
-		crtc_state->master_transcoder = master_pipe_config->cpu_transcoder;
-		master_pipe_config->sync_mode_slaves_mask |=
-			BIT(crtc_state->cpu_transcoder);
-		DRM_DEBUG_KMS("Master Transcoder = %s added for Slave CRTC = %d, slave transcoder bitmask = %d\n",
-			      transcoder_name(crtc_state->master_transcoder),
-			      crtc_state->base.crtc->base.id,
-			      master_pipe_config->sync_mode_slaves_mask);
+	if (!master_crtc) {
+		DRM_DEBUG_KMS("Could not find Master CRTC for Slave CRTC %d\n",
+			      crtc->base.id);
+		return -EINVAL;
 	}
 
+	master_crtc_state = drm_atomic_get_crtc_state(&state->base,
+						      master_crtc);
+	if (IS_ERR(master_crtc_state))
+		return PTR_ERR(master_crtc_state);
+
+	master_pipe_config = to_intel_crtc_state(master_crtc_state);
+	crtc_state->master_transcoder = master_pipe_config->cpu_transcoder;
+	master_pipe_config->sync_mode_slaves_mask |=
+		BIT(crtc_state->cpu_transcoder);
+	DRM_DEBUG_KMS("Master Transcoder = %s added for Slave CRTC = %d, slave transcoder bitmask = %d\n",
+		      transcoder_name(crtc_state->master_transcoder),
+		      crtc->base.id,
+		      master_pipe_config->sync_mode_slaves_mask);
+
 	return 0;
 }
 
@@ -12092,10 +12525,10 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	int ret;
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv) &&
-	    mode_changed && !crtc_state->base.active)
+	    mode_changed && !crtc_state->hw.active)
 		crtc_state->update_wm_post = true;
 
-	if (mode_changed && crtc_state->base.enable &&
+	if (mode_changed && crtc_state->hw.enable &&
 	    dev_priv->display.crtc_compute_clock &&
 	    !WARN_ON(crtc_state->shared_dpll)) {
 		ret = dev_priv->display.crtc_compute_clock(crtc, crtc_state);
@@ -12108,10 +12541,10 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	 * when C8 planes are getting enabled/disabled.
 	 */
 	if (c8_planes_changed(crtc_state))
-		crtc_state->base.color_mgmt_changed = true;
+		crtc_state->uapi.color_mgmt_changed = true;
 
 	if (mode_changed || crtc_state->update_pipe ||
-	    crtc_state->base.color_mgmt_changed) {
+	    crtc_state->uapi.color_mgmt_changed) {
 		ret = intel_color_check(crtc_state);
 		if (ret)
 			return ret;
@@ -12224,7 +12657,7 @@ compute_baseline_pipe_bpp(struct intel_crtc *crtc,
 			  struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct drm_atomic_state *state = pipe_config->base.state;
+	struct drm_atomic_state *state = pipe_config->uapi.state;
 	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
 	int bpp, i;
@@ -12281,7 +12714,7 @@ static void
 intel_dump_infoframe(struct drm_i915_private *dev_priv,
 		     const union hdmi_infoframe *frame)
 {
-	if ((drm_debug & DRM_UT_KMS) == 0)
+	if (!drm_debug_enabled(DRM_UT_KMS))
 		return;
 
 	hdmi_infoframe_log(KERN_DEBUG, dev_priv->drm.dev, frame);
@@ -12349,14 +12782,14 @@ static const char *output_formats(enum intel_output_format format)
 
 static void intel_dump_plane_state(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct drm_format_name_buf format_name;
 
 	if (!fb) {
 		DRM_DEBUG_KMS("[PLANE:%d:%s] fb: [NOFB], visible: %s\n",
 			      plane->base.base.id, plane->base.name,
-			      yesno(plane_state->base.visible));
+			      yesno(plane_state->uapi.visible));
 		return;
 	}
 
@@ -12364,20 +12797,20 @@ static void intel_dump_plane_state(const struct intel_plane_state *plane_state)
 		      plane->base.base.id, plane->base.name,
 		      fb->base.id, fb->width, fb->height,
 		      drm_get_format_name(fb->format->format, &format_name),
-		      yesno(plane_state->base.visible));
+		      yesno(plane_state->uapi.visible));
 	DRM_DEBUG_KMS("\trotation: 0x%x, scaler: %d\n",
-		      plane_state->base.rotation, plane_state->scaler_id);
-	if (plane_state->base.visible)
+		      plane_state->hw.rotation, plane_state->scaler_id);
+	if (plane_state->uapi.visible)
 		DRM_DEBUG_KMS("\tsrc: " DRM_RECT_FP_FMT " dst: " DRM_RECT_FMT "\n",
-			      DRM_RECT_FP_ARG(&plane_state->base.src),
-			      DRM_RECT_ARG(&plane_state->base.dst));
+			      DRM_RECT_FP_ARG(&plane_state->uapi.src),
+			      DRM_RECT_ARG(&plane_state->uapi.dst));
 }
 
 static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 				   struct intel_atomic_state *state,
 				   const char *context)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct intel_plane_state *plane_state;
 	struct intel_plane *plane;
@@ -12386,14 +12819,14 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s] enable: %s %s\n",
 		      crtc->base.base.id, crtc->base.name,
-		      yesno(pipe_config->base.enable), context);
+		      yesno(pipe_config->hw.enable), context);
 
-	if (!pipe_config->base.enable)
+	if (!pipe_config->hw.enable)
 		goto dump_planes;
 
 	snprintf_output_types(buf, sizeof(buf), pipe_config->output_types);
 	DRM_DEBUG_KMS("active: %s, output_types: %s (0x%x), output format: %s\n",
-		      yesno(pipe_config->base.active),
+		      yesno(pipe_config->hw.active),
 		      buf, pipe_config->output_types,
 		      output_formats(pipe_config->output_format));
 
@@ -12433,10 +12866,10 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 		intel_dump_infoframe(dev_priv, &pipe_config->infoframes.hdmi);
 
 	DRM_DEBUG_KMS("requested mode:\n");
-	drm_mode_debug_printmodeline(&pipe_config->base.mode);
+	drm_mode_debug_printmodeline(&pipe_config->hw.mode);
 	DRM_DEBUG_KMS("adjusted mode:\n");
-	drm_mode_debug_printmodeline(&pipe_config->base.adjusted_mode);
-	intel_dump_crtc_timings(&pipe_config->base.adjusted_mode);
+	drm_mode_debug_printmodeline(&pipe_config->hw.adjusted_mode);
+	intel_dump_crtc_timings(&pipe_config->hw.adjusted_mode);
 	DRM_DEBUG_KMS("port clock: %d, pipe src size: %dx%d, pixel rate %d\n",
 		      pipe_config->port_clock,
 		      pipe_config->pipe_src_w, pipe_config->pipe_src_h,
@@ -12474,6 +12907,9 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 			      pipe_config->csc_mode, pipe_config->gamma_mode,
 			      pipe_config->gamma_enable, pipe_config->csc_enable);
 
+	DRM_DEBUG_KMS("MST master transcoder: %s\n",
+		      transcoder_name(pipe_config->mst_master_transcoder));
+
 dump_planes:
 	if (!state)
 		return;
@@ -12556,22 +12992,59 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state)
 	return ret;
 }
 
+static void
+intel_crtc_copy_uapi_to_hw_state_nomodeset(struct intel_crtc_state *crtc_state)
+{
+	intel_crtc_copy_color_blobs(crtc_state);
+}
+
+static void
+intel_crtc_copy_uapi_to_hw_state(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->hw.enable = crtc_state->uapi.enable;
+	crtc_state->hw.active = crtc_state->uapi.active;
+	crtc_state->hw.mode = crtc_state->uapi.mode;
+	crtc_state->hw.adjusted_mode = crtc_state->uapi.adjusted_mode;
+	intel_crtc_copy_uapi_to_hw_state_nomodeset(crtc_state);
+}
+
+static void intel_crtc_copy_hw_to_uapi_state(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->uapi.enable = crtc_state->hw.enable;
+	crtc_state->uapi.active = crtc_state->hw.active;
+	WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->uapi, &crtc_state->hw.mode) < 0);
+
+	crtc_state->uapi.adjusted_mode = crtc_state->hw.adjusted_mode;
+
+	/* copy color blobs to uapi */
+	drm_property_replace_blob(&crtc_state->uapi.degamma_lut,
+				  crtc_state->hw.degamma_lut);
+	drm_property_replace_blob(&crtc_state->uapi.gamma_lut,
+				  crtc_state->hw.gamma_lut);
+	drm_property_replace_blob(&crtc_state->uapi.ctm,
+				  crtc_state->hw.ctm);
+}
+
 static int
-clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
+intel_crtc_prepare_cleared_state(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *saved_state;
 
-	saved_state = kzalloc(sizeof(*saved_state), GFP_KERNEL);
+	saved_state = intel_crtc_state_alloc(crtc);
 	if (!saved_state)
 		return -ENOMEM;
 
+	/* free the old crtc_state->hw members */
+	intel_crtc_free_hw_state(crtc_state);
+
 	/* FIXME: before the switch to atomic started, a new pipe_config was
 	 * kzalloc'd. Code that depends on any field being zero should be
 	 * fixed, so that the crtc_state can be safely duplicated. For now,
 	 * only fields that are know to not cause problems are preserved. */
 
+	saved_state->uapi = crtc_state->uapi;
 	saved_state->scaler_state = crtc_state->scaler_state;
 	saved_state->shared_dpll = crtc_state->shared_dpll;
 	saved_state->dpll_hw_state = crtc_state->dpll_hw_state;
@@ -12583,37 +13056,34 @@ clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
 		saved_state->wm = crtc_state->wm;
 	/*
 	 * Save the slave bitmask which gets filled for master crtc state during
-	 * slave atomic check call.
+	 * slave atomic check call. For all other CRTCs reset the port sync variables
+	 * crtc_state->master_transcoder needs to be set to INVALID
 	 */
-	if (is_trans_port_sync_master(crtc_state))
+	reset_port_sync_mode_state(saved_state);
+	if (intel_atomic_is_master_connector(crtc_state))
 		saved_state->sync_mode_slaves_mask =
 			crtc_state->sync_mode_slaves_mask;
 
-	/* Keep base drm_crtc_state intact, only clear our extended struct */
-	BUILD_BUG_ON(offsetof(struct intel_crtc_state, base));
-	memcpy(&crtc_state->base + 1, &saved_state->base + 1,
-	       sizeof(*crtc_state) - sizeof(crtc_state->base));
-
+	memcpy(crtc_state, saved_state, sizeof(*crtc_state));
 	kfree(saved_state);
+
+	intel_crtc_copy_uapi_to_hw_state(crtc_state);
+
 	return 0;
 }
 
 static int
 intel_modeset_pipe_config(struct intel_crtc_state *pipe_config)
 {
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_atomic_state *state = pipe_config->base.state;
+	struct drm_crtc *crtc = pipe_config->uapi.crtc;
+	struct drm_atomic_state *state = pipe_config->uapi.state;
 	struct intel_encoder *encoder;
 	struct drm_connector *connector;
 	struct drm_connector_state *connector_state;
 	int base_bpp, ret;
-	int i;
+	int i, tile_group_id = -1, num_tiled_conns = 0;
 	bool retry = true;
 
-	ret = clear_intel_crtc_state(pipe_config);
-	if (ret)
-		return ret;
-
 	pipe_config->cpu_transcoder =
 		(enum transcoder) to_intel_crtc(crtc)->pipe;
 
@@ -12622,13 +13092,13 @@ intel_modeset_pipe_config(struct intel_crtc_state *pipe_config)
 	 * positive or negative polarity is requested, treat this as meaning
 	 * negative polarity.
 	 */
-	if (!(pipe_config->base.adjusted_mode.flags &
+	if (!(pipe_config->hw.adjusted_mode.flags &
 	      (DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC)))
-		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_NHSYNC;
+		pipe_config->hw.adjusted_mode.flags |= DRM_MODE_FLAG_NHSYNC;
 
-	if (!(pipe_config->base.adjusted_mode.flags &
+	if (!(pipe_config->hw.adjusted_mode.flags &
 	      (DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC)))
-		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC;
+		pipe_config->hw.adjusted_mode.flags |= DRM_MODE_FLAG_NVSYNC;
 
 	ret = compute_baseline_pipe_bpp(to_intel_crtc(crtc),
 					pipe_config);
@@ -12645,7 +13115,7 @@ intel_modeset_pipe_config(struct intel_crtc_state *pipe_config)
 	 * computation to clearly distinguish it from the adjusted mode, which
 	 * can be changed by the connectors in the below retry loop.
 	 */
-	drm_mode_get_hv_timing(&pipe_config->base.mode,
+	drm_mode_get_hv_timing(&pipe_config->hw.mode,
 			       &pipe_config->pipe_src_w,
 			       &pipe_config->pipe_src_h);
 
@@ -12678,16 +13148,25 @@ encoder_retry:
 	pipe_config->pixel_multiplier = 1;
 
 	/* Fill in default crtc timings, allow encoders to overwrite them. */
-	drm_mode_set_crtcinfo(&pipe_config->base.adjusted_mode,
+	drm_mode_set_crtcinfo(&pipe_config->hw.adjusted_mode,
 			      CRTC_STEREO_DOUBLE);
 
-	/* Set the crtc_state defaults for trans_port_sync */
-	pipe_config->master_transcoder = INVALID_TRANSCODER;
-	ret = icl_add_sync_mode_crtcs(pipe_config);
-	if (ret) {
-		DRM_DEBUG_KMS("Cannot assign Sync Mode CRTCs: %d\n",
-			      ret);
-		return ret;
+	/* Get tile_group_id of tiled connector */
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->crtc == crtc &&
+		    connector->has_tile) {
+			tile_group_id = connector->tile_group->id;
+			break;
+		}
+	}
+
+	/* Get total number of tiled connectors in state that belong to
+	 * this tile group.
+	 */
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector->has_tile &&
+		    connector->tile_group->id == tile_group_id)
+			num_tiled_conns++;
 	}
 
 	/* Pass our mode to the connectors and the CRTC to give them a chance to
@@ -12698,6 +13177,14 @@ encoder_retry:
 		if (connector_state->crtc != crtc)
 			continue;
 
+		ret = icl_compute_port_sync_crtc_state(connector, pipe_config,
+						       num_tiled_conns);
+		if (ret) {
+			DRM_DEBUG_KMS("Cannot assign Sync Mode CRTCs: %d\n",
+				      ret);
+			return ret;
+		}
+
 		encoder = to_intel_encoder(connector_state->best_encoder);
 		ret = encoder->compute_config(encoder, pipe_config,
 					      connector_state);
@@ -12712,7 +13199,7 @@ encoder_retry:
 	/* Set default port clock if not overwritten by the encoder. Needs to be
 	 * done afterwards in case the encoder adjusts the mode. */
 	if (!pipe_config->port_clock)
-		pipe_config->port_clock = pipe_config->base.adjusted_mode.crtc_clock
+		pipe_config->port_clock = pipe_config->hw.adjusted_mode.crtc_clock
 			* pipe_config->pixel_multiplier;
 
 	ret = intel_crtc_compute_config(to_intel_crtc(crtc), pipe_config);
@@ -12741,6 +13228,12 @@ encoder_retry:
 	DRM_DEBUG_KMS("hw max bpp: %i, pipe bpp: %i, dithering: %i\n",
 		      base_bpp, pipe_config->pipe_bpp, pipe_config->dither);
 
+	/*
+	 * Make drm_calc_timestamping_constants in
+	 * drm_atomic_helper_update_legacy_modeset_state() happy
+	 */
+	pipe_config->uapi.adjusted_mode = pipe_config->hw.adjusted_mode;
+
 	return 0;
 }
 
@@ -12819,7 +13312,7 @@ pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 			       const union hdmi_infoframe *b)
 {
 	if (fastset) {
-		if ((drm_debug & DRM_UT_KMS) == 0)
+		if (!drm_debug_enabled(DRM_UT_KMS))
 			return;
 
 		DRM_DEBUG_KMS("fastset mismatch in %s infoframe\n", name);
@@ -12879,13 +13372,13 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 			  const struct intel_crtc_state *pipe_config,
 			  bool fastset)
 {
-	struct drm_i915_private *dev_priv = to_i915(current_config->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(current_config->uapi.crtc->dev);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	bool ret = true;
 	u32 bp_gamma = 0;
 	bool fixup_inherited = fastset &&
-		(current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
-		!(pipe_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED);
+		(current_config->hw.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
+		!(pipe_config->hw.mode.private_flags & I915_MODE_FLAG_INHERITED);
 
 	if (fixup_inherited && !fastboot_enabled(dev_priv)) {
 		DRM_DEBUG_KMS("initial modeset and fastboot not set\n");
@@ -13074,19 +13567,19 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	PIPE_CONF_CHECK_X(output_types);
 
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hdisplay);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_htotal);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hblank_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hblank_end);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hsync_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_hsync_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hdisplay);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_htotal);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hblank_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_hsync_end);
 
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vdisplay);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vtotal);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vblank_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vblank_end);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vsync_start);
-	PIPE_CONF_CHECK_I(base.adjusted_mode.crtc_vsync_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vdisplay);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vtotal);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vblank_end);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_start);
+	PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_vsync_end);
 
 	PIPE_CONF_CHECK_I(pixel_multiplier);
 	PIPE_CONF_CHECK_I(output_format);
@@ -13103,17 +13596,17 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	PIPE_CONF_CHECK_BOOL_INCOMPLETE(has_audio);
 
-	PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+	PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 			      DRM_MODE_FLAG_INTERLACE);
 
 	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS)) {
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_PHSYNC);
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_NHSYNC);
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_PVSYNC);
-		PIPE_CONF_CHECK_FLAGS(base.adjusted_mode.flags,
+		PIPE_CONF_CHECK_FLAGS(hw.adjusted_mode.flags,
 				      DRM_MODE_FLAG_NVSYNC);
 	}
 
@@ -13152,7 +13645,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 		bp_gamma = intel_color_get_gamma_bit_precision(pipe_config);
 		if (bp_gamma)
-			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, base.gamma_lut, bp_gamma);
+			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, hw.gamma_lut, bp_gamma);
 
 	}
 
@@ -13197,7 +13690,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	if (IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5)
 		PIPE_CONF_CHECK_I(pipe_bpp);
 
-	PIPE_CONF_CHECK_CLOCK_FUZZY(base.adjusted_mode.crtc_clock);
+	PIPE_CONF_CHECK_CLOCK_FUZZY(hw.adjusted_mode.crtc_clock);
 	PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock);
 
 	PIPE_CONF_CHECK_I(min_voltage_level);
@@ -13212,6 +13705,12 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_I(sync_mode_slaves_mask);
 	PIPE_CONF_CHECK_I(master_transcoder);
 
+	PIPE_CONF_CHECK_I(dsc.compression_enable);
+	PIPE_CONF_CHECK_I(dsc.dsc_split);
+	PIPE_CONF_CHECK_I(dsc.compressed_bpp);
+
+	PIPE_CONF_CHECK_I(mst_master_transcoder);
+
 #undef PIPE_CONF_CHECK_X
 #undef PIPE_CONF_CHECK_I
 #undef PIPE_CONF_CHECK_BOOL
@@ -13231,7 +13730,7 @@ static void intel_pipe_config_sanity_check(struct drm_i915_private *dev_priv,
 	if (pipe_config->has_pch_encoder) {
 		int fdi_dotclock = intel_dotclock_calculate(intel_fdi_link_freq(dev_priv, pipe_config),
 							    &pipe_config->fdi_m_n);
-		int dotclock = pipe_config->base.adjusted_mode.crtc_clock;
+		int dotclock = pipe_config->hw.adjusted_mode.crtc_clock;
 
 		/*
 		 * FDI already provided one idea for the dotclock.
@@ -13259,7 +13758,7 @@ static void verify_wm_state(struct intel_crtc *crtc,
 	const enum pipe pipe = crtc->pipe;
 	int plane, level, max_level = ilk_wm_max_level(dev_priv);
 
-	if (INTEL_GEN(dev_priv) < 9 || !new_crtc_state->base.active)
+	if (INTEL_GEN(dev_priv) < 9 || !new_crtc_state->hw.active)
 		return;
 
 	hw = kzalloc(sizeof(*hw), GFP_KERNEL);
@@ -13464,16 +13963,14 @@ verify_crtc_state(struct intel_crtc *crtc,
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_encoder *encoder;
-	struct intel_crtc_state *pipe_config;
-	struct drm_atomic_state *state;
+	struct intel_crtc_state *pipe_config = old_crtc_state;
+	struct drm_atomic_state *state = old_crtc_state->uapi.state;
 	bool active;
 
-	state = old_crtc_state->base.state;
-	__drm_atomic_helper_crtc_destroy_state(&old_crtc_state->base);
-	pipe_config = old_crtc_state;
-	memset(pipe_config, 0, sizeof(*pipe_config));
-	pipe_config->base.crtc = &crtc->base;
-	pipe_config->base.state = state;
+	__drm_atomic_helper_crtc_destroy_state(&old_crtc_state->uapi);
+	intel_crtc_free_hw_state(old_crtc_state);
+	intel_crtc_state_reset(old_crtc_state, crtc);
+	old_crtc_state->uapi.state = state;
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.base.id, crtc->base.name);
 
@@ -13481,23 +13978,26 @@ verify_crtc_state(struct intel_crtc *crtc,
 
 	/* we keep both pipes enabled on 830 */
 	if (IS_I830(dev_priv))
-		active = new_crtc_state->base.active;
+		active = new_crtc_state->hw.active;
 
-	I915_STATE_WARN(new_crtc_state->base.active != active,
-	     "crtc active state doesn't match with hw state "
-	     "(expected %i, found %i)\n", new_crtc_state->base.active, active);
+	I915_STATE_WARN(new_crtc_state->hw.active != active,
+			"crtc active state doesn't match with hw state "
+			"(expected %i, found %i)\n",
+			new_crtc_state->hw.active, active);
 
-	I915_STATE_WARN(crtc->active != new_crtc_state->base.active,
-	     "transitional active state does not match atomic hw state "
-	     "(expected %i, found %i)\n", new_crtc_state->base.active, crtc->active);
+	I915_STATE_WARN(crtc->active != new_crtc_state->hw.active,
+			"transitional active state does not match atomic hw state "
+			"(expected %i, found %i)\n",
+			new_crtc_state->hw.active, crtc->active);
 
 	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
 		enum pipe pipe;
 
 		active = encoder->get_hw_state(encoder, &pipe);
-		I915_STATE_WARN(active != new_crtc_state->base.active,
-			"[ENCODER:%i] active %i with crtc active %i\n",
-			encoder->base.base.id, active, new_crtc_state->base.active);
+		I915_STATE_WARN(active != new_crtc_state->hw.active,
+				"[ENCODER:%i] active %i with crtc active %i\n",
+				encoder->base.base.id, active,
+				new_crtc_state->hw.active);
 
 		I915_STATE_WARN(active && crtc->pipe != pipe,
 				"Encoder connected to wrong pipe %c\n",
@@ -13509,7 +14009,7 @@ verify_crtc_state(struct intel_crtc *crtc,
 
 	intel_crtc_compute_pixel_rate(pipe_config);
 
-	if (!new_crtc_state->base.active)
+	if (!new_crtc_state->hw.active)
 		return;
 
 	intel_pipe_config_sanity_check(dev_priv, pipe_config);
@@ -13532,7 +14032,7 @@ intel_verify_planes(struct intel_atomic_state *state)
 	for_each_new_intel_plane_in_state(state, plane,
 					  plane_state, i)
 		assert_plane(plane, plane_state->planar_slave ||
-			     plane_state->base.visible);
+			     plane_state->uapi.visible);
 }
 
 static void
@@ -13571,7 +14071,7 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 
 	crtc_mask = drm_crtc_mask(&crtc->base);
 
-	if (new_crtc_state->base.active)
+	if (new_crtc_state->hw.active)
 		I915_STATE_WARN(!(pll->active_mask & crtc_mask),
 				"pll active mismatch (expected pipe %c in active mask 0x%02x)\n",
 				pipe_name(drm_crtc_index(&crtc->base)), pll->active_mask);
@@ -13650,10 +14150,10 @@ intel_modeset_verify_disabled(struct drm_i915_private *dev_priv,
 static void
 intel_crtc_update_active_timings(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	drm_calc_timestamping_constants(&crtc->base, adjusted_mode);
 
@@ -13724,7 +14224,7 @@ static void intel_modeset_clear_plls(struct intel_atomic_state *state)
  * multiple pipes, and planes are enabled after the pipe, we need to wait at
  * least 2 vblanks on the first pipe before enabling planes on the second pipe.
  */
-static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
+static int hsw_mode_set_planes_workaround(struct intel_atomic_state *state)
 {
 	struct intel_crtc_state *crtc_state;
 	struct intel_crtc *crtc;
@@ -13735,7 +14235,7 @@ static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
 
 	/* look at all crtc's that are going to be enabled in during modeset */
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
-		if (!crtc_state->base.active ||
+		if (!crtc_state->hw.active ||
 		    !needs_modeset(crtc_state))
 			continue;
 
@@ -13760,7 +14260,7 @@ static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
 
 		crtc_state->hsw_workaround_pipe = INVALID_PIPE;
 
-		if (!crtc_state->base.active ||
+		if (!crtc_state->hw.active ||
 		    needs_modeset(crtc_state))
 			continue;
 
@@ -13797,12 +14297,12 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		if (new_crtc_state->base.active)
+		if (new_crtc_state->hw.active)
 			state->active_pipes |= BIT(crtc->pipe);
 		else
 			state->active_pipes &= ~BIT(crtc->pipe);
 
-		if (old_crtc_state->base.active != new_crtc_state->base.active)
+		if (old_crtc_state->hw.active != new_crtc_state->hw.active)
 			state->active_pipe_changes |= BIT(crtc->pipe);
 	}
 
@@ -13819,7 +14319,7 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 	intel_modeset_clear_plls(state);
 
 	if (IS_HASWELL(dev_priv))
-		return haswell_mode_set_planes_workaround(state);
+		return hsw_mode_set_planes_workaround(state);
 
 	return 0;
 }
@@ -13847,9 +14347,13 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta
 	if (!intel_pipe_config_compare(old_crtc_state, new_crtc_state, true))
 		return;
 
-	new_crtc_state->base.mode_changed = false;
+	new_crtc_state->uapi.mode_changed = false;
 	new_crtc_state->update_pipe = true;
+}
 
+static void intel_crtc_copy_fastset(const struct intel_crtc_state *old_crtc_state,
+				    struct intel_crtc_state *new_crtc_state)
+{
 	/*
 	 * If we're not doing the full modeset we want to
 	 * keep the current M/N values as they may be
@@ -13972,6 +14476,107 @@ static int intel_atomic_check_crtcs(struct intel_atomic_state *state)
 	return 0;
 }
 
+static bool intel_cpu_transcoder_needs_modeset(struct intel_atomic_state *state,
+					       enum transcoder transcoder)
+{
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
+		if (new_crtc_state->cpu_transcoder == transcoder)
+			return needs_modeset(new_crtc_state);
+
+	return false;
+}
+
+static void
+intel_modeset_synced_crtcs(struct intel_atomic_state *state,
+			   u8 transcoders)
+{
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc,
+					 new_crtc_state, i) {
+		if (transcoders & BIT(new_crtc_state->cpu_transcoder)) {
+			new_crtc_state->uapi.mode_changed = true;
+			new_crtc_state->update_pipe = false;
+		}
+	}
+}
+
+static int
+intel_modeset_all_tiles(struct intel_atomic_state *state, int tile_grp_id)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	int ret = 0;
+
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
+		struct drm_connector_state *conn_state;
+		struct drm_crtc_state *crtc_state;
+
+		if (!connector->has_tile ||
+		    connector->tile_group->id != tile_grp_id)
+			continue;
+		conn_state = drm_atomic_get_connector_state(&state->base,
+							    connector);
+		if (IS_ERR(conn_state)) {
+			ret =  PTR_ERR(conn_state);
+			break;
+		}
+
+		if (!conn_state->crtc)
+			continue;
+
+		crtc_state = drm_atomic_get_crtc_state(&state->base,
+						       conn_state->crtc);
+		if (IS_ERR(crtc_state)) {
+			ret = PTR_ERR(crtc_state);
+			break;
+		}
+		crtc_state->mode_changed = true;
+		ret = drm_atomic_add_affected_connectors(&state->base,
+							 conn_state->crtc);
+		if (ret)
+			break;
+	}
+	drm_connector_list_iter_end(&conn_iter);
+
+	return ret;
+}
+
+static int
+intel_atomic_check_tiled_conns(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_connector *connector;
+	struct drm_connector_state *old_conn_state, *new_conn_state;
+	int i, ret;
+
+	if (INTEL_GEN(dev_priv) < 11)
+		return 0;
+
+	/* Is tiled, mark all other tiled CRTCs as needing a modeset */
+	for_each_oldnew_connector_in_state(&state->base, connector,
+					   old_conn_state, new_conn_state, i) {
+		if (!connector->has_tile)
+			continue;
+		if (!intel_connector_needs_modeset(state, connector))
+			continue;
+
+		ret = intel_modeset_all_tiles(state, connector->tile_group->id);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /**
  * intel_atomic_check - validate state object
  * @dev: drm device
@@ -13990,33 +14595,96 @@ static int intel_atomic_check(struct drm_device *dev,
 	/* Catch I915_MODE_FLAG_INHERITED */
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		if (new_crtc_state->base.mode.private_flags !=
-		    old_crtc_state->base.mode.private_flags)
-			new_crtc_state->base.mode_changed = true;
+		if (new_crtc_state->hw.mode.private_flags !=
+		    old_crtc_state->hw.mode.private_flags)
+			new_crtc_state->uapi.mode_changed = true;
 	}
 
 	ret = drm_atomic_helper_check_modeset(dev, &state->base);
 	if (ret)
 		goto fail;
 
+	/**
+	 * This check adds all the connectors in current state that belong to
+	 * the same tile group to a full modeset.
+	 * This function directly sets the mode_changed to true and we also call
+	 * drm_atomic_add_affected_connectors(). Hence we are not explicitly
+	 * calling drm_atomic_helper_check_modeset() after this.
+	 *
+	 * Fixme: Handle some corner cases where one of the
+	 * tiled connectors gets disconnected and tile info is lost but since it
+	 * was previously synced to other conn, we need to add that to the modeset.
+	 */
+	ret = intel_atomic_check_tiled_conns(state);
+	if (ret)
+		goto fail;
+
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
-		if (!needs_modeset(new_crtc_state))
+		if (!needs_modeset(new_crtc_state)) {
+			/* Light copy */
+			intel_crtc_copy_uapi_to_hw_state_nomodeset(new_crtc_state);
+
 			continue;
+		}
 
-		if (!new_crtc_state->base.enable) {
-			any_ms = true;
+		if (!new_crtc_state->uapi.enable) {
+			intel_crtc_copy_uapi_to_hw_state(new_crtc_state);
 			continue;
 		}
 
+		ret = intel_crtc_prepare_cleared_state(new_crtc_state);
+		if (ret)
+			goto fail;
+
 		ret = intel_modeset_pipe_config(new_crtc_state);
 		if (ret)
 			goto fail;
 
 		intel_crtc_check_fastset(old_crtc_state, new_crtc_state);
+	}
+
+	/**
+	 * Check if fastset is allowed by external dependencies like other
+	 * pipes and transcoders.
+	 *
+	 * Right now it only forces a fullmodeset when the MST master
+	 * transcoder did not changed but the pipe of the master transcoder
+	 * needs a fullmodeset so all slaves also needs to do a fullmodeset or
+	 * in case of port synced crtcs, if one of the synced crtcs
+	 * needs a full modeset, all other synced crtcs should be
+	 * forced a full modeset.
+	 */
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (!new_crtc_state->hw.enable || needs_modeset(new_crtc_state))
+			continue;
+
+		if (intel_dp_mst_is_slave_trans(new_crtc_state)) {
+			enum transcoder master = new_crtc_state->mst_master_transcoder;
+
+			if (intel_cpu_transcoder_needs_modeset(state, master)) {
+				new_crtc_state->uapi.mode_changed = true;
+				new_crtc_state->update_pipe = false;
+			}
+		} else if (is_trans_port_sync_mode(new_crtc_state)) {
+			u8 trans = new_crtc_state->sync_mode_slaves_mask |
+				   BIT(new_crtc_state->master_transcoder);
 
-		if (needs_modeset(new_crtc_state))
+			intel_modeset_synced_crtcs(state, trans);
+		}
+	}
+
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		if (needs_modeset(new_crtc_state)) {
 			any_ms = true;
+			continue;
+		}
+
+		if (!new_crtc_state->update_pipe)
+			continue;
+
+		intel_crtc_copy_fastset(old_crtc_state, new_crtc_state);
 	}
 
 	if (any_ms && !check_digital_port_conflicts(state)) {
@@ -14106,7 +14774,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	if (!IS_GEN(dev_priv, 2))
+	if (!IS_GEN(dev_priv, 2) || crtc_state->active_planes)
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
 
 	if (crtc_state->has_pch_encoder) {
@@ -14120,7 +14788,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 			       const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	/*
@@ -14138,12 +14806,12 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
 		skl_detach_scalers(new_crtc_state);
 
 		if (new_crtc_state->pch_pfit.enabled)
-			skylake_pfit_enable(new_crtc_state);
+			skl_pfit_enable(new_crtc_state);
 	} else if (HAS_PCH_SPLIT(dev_priv)) {
 		if (new_crtc_state->pch_pfit.enabled)
-			ironlake_pfit_enable(new_crtc_state);
+			ilk_pfit_enable(new_crtc_state);
 		else if (old_crtc_state->pch_pfit.enabled)
-			ironlake_pfit_disable(old_crtc_state);
+			ilk_pfit_disable(old_crtc_state);
 	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -14154,6 +14822,7 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 			       struct intel_crtc_state *old_crtc_state,
 			       struct intel_crtc_state *new_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	bool modeset = needs_modeset(new_crtc_state);
 
@@ -14162,7 +14831,7 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 	 * CRTC was enabled.
 	 */
 	if (!modeset) {
-		if (new_crtc_state->base.color_mgmt_changed ||
+		if (new_crtc_state->uapi.color_mgmt_changed ||
 		    new_crtc_state->update_pipe)
 			intel_color_commit(new_crtc_state);
 
@@ -14177,8 +14846,7 @@ static void commit_pipe_config(struct intel_atomic_state *state,
 	}
 
 	if (dev_priv->display.atomic_update_watermarks)
-		dev_priv->display.atomic_update_watermarks(state,
-							   new_crtc_state);
+		dev_priv->display.atomic_update_watermarks(state, crtc);
 }
 
 static void intel_update_crtc(struct intel_crtc *crtc,
@@ -14195,20 +14863,20 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	if (modeset) {
 		intel_crtc_update_active_timings(new_crtc_state);
 
-		dev_priv->display.crtc_enable(new_crtc_state, state);
+		dev_priv->display.crtc_enable(state, crtc);
 
 		/* vblanks work again, re-enable pipe CRC. */
 		intel_crtc_enable_pipe_crc(crtc);
 	} else {
 		if (new_crtc_state->preload_luts &&
-		    (new_crtc_state->base.color_mgmt_changed ||
+		    (new_crtc_state->uapi.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
 			intel_color_load_luts(new_crtc_state);
 
-		intel_pre_plane_update(old_crtc_state, new_crtc_state);
+		intel_pre_plane_update(state, crtc);
 
 		if (new_crtc_state->update_pipe)
-			intel_encoders_update_pipe(crtc, new_crtc_state, state);
+			intel_encoders_update_pipe(state, crtc);
 	}
 
 	if (new_crtc_state->update_pipe && !new_crtc_state->enable_fbc)
@@ -14235,13 +14903,13 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	 * of enabling them on the CRTC's first fastset.
 	 */
 	if (new_crtc_state->update_pipe && !modeset &&
-	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
+	    old_crtc_state->hw.mode.private_flags & I915_MODE_FLAG_INHERITED)
 		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
 
 static struct intel_crtc *intel_get_slave_crtc(const struct intel_crtc_state *new_crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(new_crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(new_crtc_state->uapi.crtc->dev);
 	enum transcoder slave_transcoder;
 
 	WARN_ON(!is_power_of_2(new_crtc_state->sync_mode_slaves_mask));
@@ -14266,97 +14934,60 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
 	 */
 	intel_crtc_disable_pipe_crc(crtc);
 
-	dev_priv->display.crtc_disable(old_crtc_state, state);
+	dev_priv->display.crtc_disable(state, crtc);
 	crtc->active = false;
 	intel_fbc_disable(crtc);
 	intel_disable_shared_dpll(old_crtc_state);
 
-	/*
-	 * Underruns don't always raise interrupts,
-	 * so check manually.
-	 */
-	intel_check_cpu_fifo_underruns(dev_priv);
-	intel_check_pch_fifo_underruns(dev_priv);
-
 	/* FIXME unify this for all platforms */
-	if (!new_crtc_state->base.active &&
+	if (!new_crtc_state->hw.active &&
 	    !HAS_GMCH(dev_priv) &&
 	    dev_priv->display.initial_watermarks)
-		dev_priv->display.initial_watermarks(state,
-						     new_crtc_state);
-}
-
-static void intel_trans_port_sync_modeset_disables(struct intel_atomic_state *state,
-						   struct intel_crtc *crtc,
-						   struct intel_crtc_state *old_crtc_state,
-						   struct intel_crtc_state *new_crtc_state)
-{
-	struct intel_crtc *slave_crtc = intel_get_slave_crtc(new_crtc_state);
-	struct intel_crtc_state *new_slave_crtc_state =
-		intel_atomic_get_new_crtc_state(state, slave_crtc);
-	struct intel_crtc_state *old_slave_crtc_state =
-		intel_atomic_get_old_crtc_state(state, slave_crtc);
-
-	WARN_ON(!slave_crtc || !new_slave_crtc_state ||
-		!old_slave_crtc_state);
-
-	/* Disable Slave first */
-	intel_pre_plane_update(old_slave_crtc_state, new_slave_crtc_state);
-	if (old_slave_crtc_state->base.active)
-		intel_old_crtc_state_disables(state,
-					      old_slave_crtc_state,
-					      new_slave_crtc_state,
-					      slave_crtc);
-
-	/* Disable Master */
-	intel_pre_plane_update(old_crtc_state, new_crtc_state);
-	if (old_crtc_state->base.active)
-		intel_old_crtc_state_disables(state,
-					      old_crtc_state,
-					      new_crtc_state,
-					      crtc);
+		dev_priv->display.initial_watermarks(state, crtc);
 }
 
 static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 {
 	struct intel_crtc_state *new_crtc_state, *old_crtc_state;
 	struct intel_crtc *crtc;
+	u32 handled = 0;
 	int i;
 
-	/*
-	 * Disable CRTC/pipes in reverse order because some features(MST in
-	 * TGL+) requires master and slave relationship between pipes, so it
-	 * should always pick the lowest pipe as master as it will be enabled
-	 * first and disable in the reverse order so the master will be the
-	 * last one to be disabled.
-	 */
-	for_each_oldnew_intel_crtc_in_state_reverse(state, crtc, old_crtc_state,
-						    new_crtc_state, i) {
+	/* Only disable port sync and MST slaves */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
 		if (!needs_modeset(new_crtc_state))
 			continue;
 
+		if (!old_crtc_state->hw.active)
+			continue;
+
 		/* In case of Transcoder port Sync master slave CRTCs can be
 		 * assigned in any order and we need to make sure that
 		 * slave CRTCs are disabled first and then master CRTC since
 		 * Slave vblanks are masked till Master Vblanks.
 		 */
-		if (is_trans_port_sync_mode(new_crtc_state)) {
-			if (is_trans_port_sync_master(new_crtc_state))
-				intel_trans_port_sync_modeset_disables(state,
-								       crtc,
-								       old_crtc_state,
-								       new_crtc_state);
-			else
-				continue;
-		} else {
-			intel_pre_plane_update(old_crtc_state, new_crtc_state);
+		if (!is_trans_port_sync_slave(old_crtc_state) &&
+		    !intel_dp_mst_is_slave_trans(old_crtc_state))
+			continue;
 
-			if (old_crtc_state->base.active)
-				intel_old_crtc_state_disables(state,
-							      old_crtc_state,
-							      new_crtc_state,
-							      crtc);
-		}
+		intel_pre_plane_update(state, crtc);
+		intel_old_crtc_state_disables(state, old_crtc_state,
+					      new_crtc_state, crtc);
+		handled |= BIT(crtc->pipe);
+	}
+
+	/* Disable everything else left on */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		if (!needs_modeset(new_crtc_state) ||
+		    (handled & BIT(crtc->pipe)))
+			continue;
+
+		intel_pre_plane_update(state, crtc);
+		if (old_crtc_state->hw.active)
+			intel_old_crtc_state_disables(state, old_crtc_state,
+						      new_crtc_state, crtc);
 	}
 }
 
@@ -14367,7 +14998,7 @@ static void intel_commit_modeset_enables(struct intel_atomic_state *state)
 	int i;
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		if (!new_crtc_state->base.active)
+		if (!new_crtc_state->hw.active)
 			continue;
 
 		intel_update_crtc(crtc, state, old_crtc_state,
@@ -14382,7 +15013,7 @@ static void intel_crtc_enable_trans_port_sync(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 
 	intel_crtc_update_active_timings(new_crtc_state);
-	dev_priv->display.crtc_enable(new_crtc_state, state);
+	dev_priv->display.crtc_enable(state, crtc);
 	intel_crtc_enable_pipe_crc(crtc);
 }
 
@@ -14398,10 +15029,14 @@ static void intel_set_dp_tp_ctl_normal(struct intel_crtc *crtc,
 		if (conn_state->crtc == &crtc->base)
 			break;
 	}
-	intel_dp = enc_to_intel_dp(&intel_attached_encoder(conn)->base);
+	intel_dp = enc_to_intel_dp(intel_attached_encoder(to_intel_connector(conn)));
 	intel_dp_stop_link_train(intel_dp);
 }
 
+/*
+ * TODO: This is only called from port sync and it is identical to what will be
+ * executed again in intel_update_crtc() over port sync pipes
+ */
 static void intel_post_crtc_enable_updates(struct intel_crtc *crtc,
 					   struct intel_atomic_state *state)
 {
@@ -14432,7 +15067,7 @@ static void intel_post_crtc_enable_updates(struct intel_crtc *crtc,
 	 * of enabling them on the CRTC's first fastset.
 	 */
 	if (new_crtc_state->update_pipe && !modeset &&
-	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
+	    old_crtc_state->hw.mode.private_flags & I915_MODE_FLAG_INHERITED)
 		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
 
@@ -14487,17 +15122,25 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc *crtc;
 	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
-	unsigned int updated = 0;
-	bool progress;
-	int i;
 	u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
 	u8 required_slices = state->wm_results.ddb.enabled_slices;
 	struct skl_ddb_entry entries[I915_MAX_PIPES] = {};
+	const u8 num_pipes = INTEL_NUM_PIPES(dev_priv);
+	u8 update_pipes = 0, modeset_pipes = 0;
+	int i;
+
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		if (!new_crtc_state->hw.active)
+			continue;
 
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i)
 		/* ignore allocations for crtc's that have been turned off. */
-		if (new_crtc_state->base.active)
+		if (!needs_modeset(new_crtc_state)) {
 			entries[i] = old_crtc_state->wm.skl.ddb;
+			update_pipes |= BIT(crtc->pipe);
+		} else {
+			modeset_pipes |= BIT(crtc->pipe);
+		}
+	}
 
 	/* If 2nd DBuf slice required, enable it here */
 	if (INTEL_GEN(dev_priv) >= 11 && required_slices > hw_enabled_slices)
@@ -14506,27 +15149,29 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 	/*
 	 * Whenever the number of active pipes changes, we need to make sure we
 	 * update the pipes in the right order so that their ddb allocations
-	 * never overlap with eachother inbetween CRTC updates. Otherwise we'll
+	 * never overlap with each other between CRTC updates. Otherwise we'll
 	 * cause pipe underruns and other bad stuff.
+	 *
+	 * So first lets enable all pipes that do not need a fullmodeset as
+	 * those don't have any external dependency.
 	 */
-	do {
-		progress = false;
-
-		for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+	while (update_pipes) {
+		for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+						    new_crtc_state, i) {
 			enum pipe pipe = crtc->pipe;
-			bool vbl_wait = false;
-			bool modeset = needs_modeset(new_crtc_state);
 
-			if (updated & BIT(crtc->pipe) || !new_crtc_state->base.active)
+			if ((update_pipes & BIT(pipe)) == 0)
 				continue;
 
 			if (skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
-							entries,
-							INTEL_NUM_PIPES(dev_priv), i))
+							entries, num_pipes, i))
 				continue;
 
-			updated |= BIT(pipe);
 			entries[i] = new_crtc_state->wm.skl.ddb;
+			update_pipes &= ~BIT(pipe);
+
+			intel_update_crtc(crtc, state, old_crtc_state,
+					  new_crtc_state);
 
 			/*
 			 * If this is an already active pipe, it's DDB changed,
@@ -14536,29 +15181,71 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 			 */
 			if (!skl_ddb_entry_equal(&new_crtc_state->wm.skl.ddb,
 						 &old_crtc_state->wm.skl.ddb) &&
-			    !modeset &&
-			    state->wm_results.dirty_pipes != updated)
-				vbl_wait = true;
-
-			if (modeset && is_trans_port_sync_mode(new_crtc_state)) {
-				if (is_trans_port_sync_master(new_crtc_state))
-					intel_update_trans_port_sync_crtcs(crtc,
-									   state,
-									   old_crtc_state,
-									   new_crtc_state);
-				else
-					continue;
-			} else {
-				intel_update_crtc(crtc, state, old_crtc_state,
-						  new_crtc_state);
-			}
-
-			if (vbl_wait)
+			    (update_pipes | modeset_pipes))
 				intel_wait_for_vblank(dev_priv, pipe);
+		}
+	}
+
+	/*
+	 * Enable all pipes that needs a modeset and do not depends on other
+	 * pipes
+	 */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		enum pipe pipe = crtc->pipe;
 
-			progress = true;
+		if ((modeset_pipes & BIT(pipe)) == 0)
+			continue;
+
+		if (intel_dp_mst_is_slave_trans(new_crtc_state) ||
+		    is_trans_port_sync_slave(new_crtc_state))
+			continue;
+
+		WARN_ON(skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
+						    entries, num_pipes, i));
+
+		entries[i] = new_crtc_state->wm.skl.ddb;
+		modeset_pipes &= ~BIT(pipe);
+
+		if (is_trans_port_sync_mode(new_crtc_state)) {
+			struct intel_crtc *slave_crtc;
+
+			intel_update_trans_port_sync_crtcs(crtc, state,
+							   old_crtc_state,
+							   new_crtc_state);
+
+			slave_crtc = intel_get_slave_crtc(new_crtc_state);
+			/* TODO: update entries[] of slave */
+			modeset_pipes &= ~BIT(slave_crtc->pipe);
+
+		} else {
+			intel_update_crtc(crtc, state, old_crtc_state,
+					  new_crtc_state);
 		}
-	} while (progress);
+	}
+
+	/*
+	 * Finally enable all pipes that needs a modeset and depends on
+	 * other pipes, right now it is only MST slaves as both port sync slave
+	 * and master are enabled together
+	 */
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		enum pipe pipe = crtc->pipe;
+
+		if ((modeset_pipes & BIT(pipe)) == 0)
+			continue;
+
+		WARN_ON(skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
+						    entries, num_pipes, i));
+
+		entries[i] = new_crtc_state->wm.skl.ddb;
+		modeset_pipes &= ~BIT(pipe);
+
+		intel_update_crtc(crtc, state, old_crtc_state, new_crtc_state);
+	}
+
+	WARN_ON(modeset_pipes);
 
 	/* If 2nd DBuf slice is no more required disable it */
 	if (INTEL_GEN(dev_priv) >= 11 && required_slices < hw_enabled_slices)
@@ -14679,12 +15366,13 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		bool modeset = needs_modeset(new_crtc_state);
 
 		/* Complete events for now disable pipes here. */
-		if (modeset && !new_crtc_state->base.active && new_crtc_state->base.event) {
+		if (modeset && !new_crtc_state->hw.active && new_crtc_state->uapi.event) {
 			spin_lock_irq(&dev->event_lock);
-			drm_crtc_send_vblank_event(&crtc->base, new_crtc_state->base.event);
+			drm_crtc_send_vblank_event(&crtc->base,
+						   new_crtc_state->uapi.event);
 			spin_unlock_irq(&dev->event_lock);
 
-			new_crtc_state->base.event = NULL;
+			new_crtc_state->uapi.event = NULL;
 		}
 	}
 
@@ -14715,10 +15403,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	drm_atomic_helper_wait_for_flip_done(dev, &state->base);
 
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
-		if (new_crtc_state->base.active &&
+		if (new_crtc_state->hw.active &&
 		    !needs_modeset(new_crtc_state) &&
 		    !new_crtc_state->preload_luts &&
-		    (new_crtc_state->base.color_mgmt_changed ||
+		    (new_crtc_state->uapi.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
 			intel_color_load_luts(new_crtc_state);
 	}
@@ -14730,14 +15418,25 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	 *
 	 * TODO: Move this (and other cleanup) to an async worker eventually.
 	 */
-	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		/*
+		 * Gen2 reports pipe underruns whenever all planes are disabled.
+		 * So re-enable underrun reporting after some planes get enabled.
+		 *
+		 * We do this before .optimize_watermarks() so that we have a
+		 * chance of catching underruns with the intermediate watermarks
+		 * vs. the new plane configuration.
+		 */
+		if (IS_GEN(dev_priv, 2) && planes_enabling(old_crtc_state, new_crtc_state))
+			intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
+
 		if (dev_priv->display.optimize_watermarks)
-			dev_priv->display.optimize_watermarks(state,
-							      new_crtc_state);
+			dev_priv->display.optimize_watermarks(state, crtc);
 	}
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
-		intel_post_plane_update(old_crtc_state);
+		intel_post_plane_update(state, crtc);
 
 		if (put_domains[i])
 			modeset_put_power_domains(dev_priv, put_domains[i]);
@@ -14745,6 +15444,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		intel_modeset_verify_crtc(crtc, state, old_crtc_state, new_crtc_state);
 	}
 
+	/* Underruns don't always raise interrupts, so check manually */
+	intel_check_cpu_fifo_underruns(dev_priv);
+	intel_check_pch_fifo_underruns(dev_priv);
+
 	if (state->modeset)
 		intel_verify_planes(state);
 
@@ -14818,8 +15521,8 @@ static void intel_atomic_track_fbs(struct intel_atomic_state *state)
 
 	for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state,
 					     new_plane_state, i)
-		intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->base.fb),
-					to_intel_frontbuffer(new_plane_state->base.fb),
+		intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->hw.fb),
+					to_intel_frontbuffer(new_plane_state->hw.fb),
 					plane->frontbuffer_bit);
 }
 
@@ -14986,9 +15689,9 @@ static void add_rps_boost_after_vblank(struct drm_crtc *crtc,
 
 static int intel_plane_pin_fb(struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 	struct i915_vma *vma;
 
 	if (plane->id == PLANE_CURSOR &&
@@ -15051,9 +15754,9 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	struct intel_plane_state *new_plane_state =
 		to_intel_plane_state(_new_plane_state);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_plane_state->base.state);
+		to_intel_atomic_state(new_plane_state->uapi.state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-	struct drm_framebuffer *fb = new_plane_state->base.fb;
+	struct drm_framebuffer *fb = new_plane_state->hw.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->state->fb);
 	int ret;
@@ -15084,9 +15787,9 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		}
 	}
 
-	if (new_plane_state->base.fence) { /* explicit fencing */
+	if (new_plane_state->uapi.fence) { /* explicit fencing */
 		ret = i915_sw_fence_await_dma_fence(&intel_state->commit_ready,
-						    new_plane_state->base.fence,
+						    new_plane_state->uapi.fence,
 						    I915_FENCE_TIMEOUT,
 						    GFP_KERNEL);
 		if (ret < 0)
@@ -15109,7 +15812,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	fb_obj_bump_render_priority(obj);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_DIRTYFB);
 
-	if (!new_plane_state->base.fence) { /* implicit fencing */
+	if (!new_plane_state->uapi.fence) { /* implicit fencing */
 		struct dma_fence *fence;
 
 		ret = i915_sw_fence_await_reservation(&intel_state->commit_ready,
@@ -15121,13 +15824,13 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 
 		fence = dma_resv_get_excl_rcu(obj->base.resv);
 		if (fence) {
-			add_rps_boost_after_vblank(new_plane_state->base.crtc,
+			add_rps_boost_after_vblank(new_plane_state->hw.crtc,
 						   fence);
 			dma_fence_put(fence);
 		}
 	} else {
-		add_rps_boost_after_vblank(new_plane_state->base.crtc,
-					   new_plane_state->base.fence);
+		add_rps_boost_after_vblank(new_plane_state->hw.crtc,
+					   new_plane_state->uapi.fence);
 	}
 
 	/*
@@ -15160,7 +15863,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	struct intel_plane_state *old_plane_state =
 		to_intel_plane_state(_old_plane_state);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(old_plane_state->base.state);
+		to_intel_atomic_state(old_plane_state->uapi.state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
 	if (intel_state->rps_interactive) {
@@ -15224,8 +15927,12 @@ static bool i965_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_XBGR16161616F:
 		return modifier == DRM_FORMAT_MOD_LINEAR ||
 			modifier == I915_FORMAT_MOD_X_TILED;
@@ -15283,7 +15990,7 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 * When crtc is inactive or there is a modeset pending,
 	 * wait for it to complete in the slowpath
 	 */
-	if (!crtc_state->base.active || needs_modeset(crtc_state) ||
+	if (!crtc_state->hw.active || needs_modeset(crtc_state) ||
 	    crtc_state->update_pipe)
 		goto slow;
 
@@ -15292,8 +15999,8 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 * the plane.  This prevents our async update's changes from getting
 	 * overridden by a previous synchronous update's state.
 	 */
-	if (old_plane_state->base.commit &&
-	    !try_wait_for_completion(&old_plane_state->base.commit->hw_done))
+	if (old_plane_state->uapi.commit &&
+	    !try_wait_for_completion(&old_plane_state->uapi.commit->hw_done))
 		goto slow;
 
 	/*
@@ -15301,12 +16008,12 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 * take the slowpath. Only changing fb or position should be
 	 * in the fastpath.
 	 */
-	if (old_plane_state->base.crtc != &crtc->base ||
-	    old_plane_state->base.src_w != src_w ||
-	    old_plane_state->base.src_h != src_h ||
-	    old_plane_state->base.crtc_w != crtc_w ||
-	    old_plane_state->base.crtc_h != crtc_h ||
-	    !old_plane_state->base.fb != !fb)
+	if (old_plane_state->uapi.crtc != &crtc->base ||
+	    old_plane_state->uapi.src_w != src_w ||
+	    old_plane_state->uapi.src_h != src_h ||
+	    old_plane_state->uapi.crtc_w != crtc_w ||
+	    old_plane_state->uapi.crtc_h != crtc_h ||
+	    !old_plane_state->uapi.fb != !fb)
 		goto slow;
 
 	new_plane_state = to_intel_plane_state(intel_plane_duplicate_state(&plane->base));
@@ -15319,16 +16026,16 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 		goto out_free;
 	}
 
-	drm_atomic_set_fb_for_plane(&new_plane_state->base, fb);
+	drm_atomic_set_fb_for_plane(&new_plane_state->uapi, fb);
 
-	new_plane_state->base.src_x = src_x;
-	new_plane_state->base.src_y = src_y;
-	new_plane_state->base.src_w = src_w;
-	new_plane_state->base.src_h = src_h;
-	new_plane_state->base.crtc_x = crtc_x;
-	new_plane_state->base.crtc_y = crtc_y;
-	new_plane_state->base.crtc_w = crtc_w;
-	new_plane_state->base.crtc_h = crtc_h;
+	new_plane_state->uapi.src_x = src_x;
+	new_plane_state->uapi.src_y = src_y;
+	new_plane_state->uapi.src_w = src_w;
+	new_plane_state->uapi.src_h = src_h;
+	new_plane_state->uapi.crtc_x = crtc_x;
+	new_plane_state->uapi.crtc_y = crtc_y;
+	new_plane_state->uapi.crtc_w = crtc_w;
+	new_plane_state->uapi.crtc_h = crtc_h;
 
 	ret = intel_plane_atomic_check_with_state(crtc_state, new_crtc_state,
 						  old_plane_state, new_plane_state);
@@ -15339,13 +16046,14 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	if (ret)
 		goto out_free;
 
-	intel_frontbuffer_flush(to_intel_frontbuffer(new_plane_state->base.fb), ORIGIN_FLIP);
-	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->base.fb),
-				to_intel_frontbuffer(new_plane_state->base.fb),
+	intel_frontbuffer_flush(to_intel_frontbuffer(new_plane_state->hw.fb),
+				ORIGIN_FLIP);
+	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->hw.fb),
+				to_intel_frontbuffer(new_plane_state->hw.fb),
 				plane->frontbuffer_bit);
 
 	/* Swap plane state */
-	plane->base.state = &new_plane_state->base;
+	plane->base.state = &new_plane_state->uapi;
 
 	/*
 	 * We cannot swap crtc_state as it may be in use by an atomic commit or
@@ -15359,7 +16067,7 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 	 */
 	crtc_state->active_planes = new_crtc_state->active_planes;
 
-	if (new_plane_state->base.visible)
+	if (new_plane_state->uapi.visible)
 		intel_update_plane(plane, crtc_state, new_plane_state);
 	else
 		intel_disable_plane(plane, crtc_state);
@@ -15368,11 +16076,11 @@ intel_legacy_cursor_update(struct drm_plane *_plane,
 
 out_free:
 	if (new_crtc_state)
-		intel_crtc_destroy_state(&crtc->base, &new_crtc_state->base);
+		intel_crtc_destroy_state(&crtc->base, &new_crtc_state->uapi);
 	if (ret)
-		intel_plane_destroy_state(&plane->base, &new_plane_state->base);
+		intel_plane_destroy_state(&plane->base, &new_plane_state->uapi);
 	else
-		intel_plane_destroy_state(&plane->base, &old_plane_state->base);
+		intel_plane_destroy_state(&plane->base, &old_plane_state->uapi);
 	return ret;
 
 slow:
@@ -15414,7 +16122,6 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	const struct drm_plane_funcs *plane_funcs;
 	unsigned int supported_rotations;
 	unsigned int possible_crtcs;
-	const u64 *modifiers;
 	const u32 *formats;
 	int num_formats;
 	int ret, zpos;
@@ -15446,7 +16153,10 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		fbc->possible_framebuffer_bits |= plane->frontbuffer_bit;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 4) {
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		formats = vlv_primary_formats;
+		num_formats = ARRAY_SIZE(vlv_primary_formats);
+	} else if (INTEL_GEN(dev_priv) >= 4) {
 		/*
 		 * WaFP16GammaEnabling:ivb
 		 * "Workaround : When using the 64-bit format, the plane
@@ -15467,51 +16177,45 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 			formats = i965_primary_formats;
 			num_formats = ARRAY_SIZE(i965_primary_formats);
 		}
-		modifiers = i9xx_format_modifiers;
-
-		plane->max_stride = i9xx_plane_max_stride;
-		plane->update_plane = i9xx_update_plane;
-		plane->disable_plane = i9xx_disable_plane;
-		plane->get_hw_state = i9xx_plane_get_hw_state;
-		plane->check_plane = i9xx_plane_check;
-
-		if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
-			plane->min_cdclk = hsw_plane_min_cdclk;
-		else if (IS_IVYBRIDGE(dev_priv))
-			plane->min_cdclk = ivb_plane_min_cdclk;
-		else if (IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv))
-			plane->min_cdclk = vlv_plane_min_cdclk;
-		else
-			plane->min_cdclk = i9xx_plane_min_cdclk;
-
-		plane_funcs = &i965_plane_funcs;
 	} else {
 		formats = i8xx_primary_formats;
 		num_formats = ARRAY_SIZE(i8xx_primary_formats);
-		modifiers = i9xx_format_modifiers;
+	}
 
-		plane->max_stride = i9xx_plane_max_stride;
-		plane->update_plane = i9xx_update_plane;
-		plane->disable_plane = i9xx_disable_plane;
-		plane->get_hw_state = i9xx_plane_get_hw_state;
-		plane->check_plane = i9xx_plane_check;
+	if (INTEL_GEN(dev_priv) >= 4)
+		plane_funcs = &i965_plane_funcs;
+	else
+		plane_funcs = &i8xx_plane_funcs;
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		plane->min_cdclk = vlv_plane_min_cdclk;
+	else if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
+		plane->min_cdclk = hsw_plane_min_cdclk;
+	else if (IS_IVYBRIDGE(dev_priv))
+		plane->min_cdclk = ivb_plane_min_cdclk;
+	else
 		plane->min_cdclk = i9xx_plane_min_cdclk;
 
-		plane_funcs = &i8xx_plane_funcs;
-	}
+	plane->max_stride = i9xx_plane_max_stride;
+	plane->update_plane = i9xx_update_plane;
+	plane->disable_plane = i9xx_disable_plane;
+	plane->get_hw_state = i9xx_plane_get_hw_state;
+	plane->check_plane = i9xx_plane_check;
 
 	possible_crtcs = BIT(pipe);
 
 	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		ret = drm_universal_plane_init(&dev_priv->drm, &plane->base,
 					       possible_crtcs, plane_funcs,
-					       formats, num_formats, modifiers,
+					       formats, num_formats,
+					       i9xx_format_modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "primary %c", pipe_name(pipe));
 	else
 		ret = drm_universal_plane_init(&dev_priv->drm, &plane->base,
 					       possible_crtcs, plane_funcs,
-					       formats, num_formats, modifiers,
+					       formats, num_formats,
+					       i9xx_format_modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "plane %c",
 					       plane_name(plane->i9xx_plane));
@@ -15615,28 +16319,6 @@ fail:
 	return ERR_PTR(ret);
 }
 
-static void intel_crtc_init_scalers(struct intel_crtc *crtc,
-				    struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc_scaler_state *scaler_state =
-		&crtc_state->scaler_state;
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int i;
-
-	crtc->num_scalers = RUNTIME_INFO(dev_priv)->num_scalers[crtc->pipe];
-	if (!crtc->num_scalers)
-		return;
-
-	for (i = 0; i < crtc->num_scalers; i++) {
-		struct intel_scaler *scaler = &scaler_state->scalers[i];
-
-		scaler->in_use = 0;
-		scaler->mode = 0;
-	}
-
-	scaler_state->scaler_id = -1;
-}
-
 #define INTEL_CRTC_FUNCS \
 	.gamma_set = drm_atomic_helper_legacy_gamma_set, \
 	.set_config = drm_atomic_helper_set_config, \
@@ -15704,33 +16386,53 @@ static const struct drm_crtc_funcs i8xx_crtc_funcs = {
 	.disable_vblank = i8xx_disable_vblank,
 };
 
+static struct intel_crtc *intel_crtc_alloc(void)
+{
+	struct intel_crtc_state *crtc_state;
+	struct intel_crtc *crtc;
+
+	crtc = kzalloc(sizeof(*crtc), GFP_KERNEL);
+	if (!crtc)
+		return ERR_PTR(-ENOMEM);
+
+	crtc_state = intel_crtc_state_alloc(crtc);
+	if (!crtc_state) {
+		kfree(crtc);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	crtc->base.state = &crtc_state->uapi;
+	crtc->config = crtc_state;
+
+	return crtc;
+}
+
+static void intel_crtc_free(struct intel_crtc *crtc)
+{
+	intel_crtc_destroy_state(&crtc->base, crtc->base.state);
+	kfree(crtc);
+}
+
 static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
+	struct intel_plane *primary, *cursor;
 	const struct drm_crtc_funcs *funcs;
-	struct intel_crtc *intel_crtc;
-	struct intel_crtc_state *crtc_state = NULL;
-	struct intel_plane *primary = NULL;
-	struct intel_plane *cursor = NULL;
+	struct intel_crtc *crtc;
 	int sprite, ret;
 
-	intel_crtc = kzalloc(sizeof(*intel_crtc), GFP_KERNEL);
-	if (!intel_crtc)
-		return -ENOMEM;
+	crtc = intel_crtc_alloc();
+	if (IS_ERR(crtc))
+		return PTR_ERR(crtc);
 
-	crtc_state = kzalloc(sizeof(*crtc_state), GFP_KERNEL);
-	if (!crtc_state) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-	__drm_atomic_helper_crtc_reset(&intel_crtc->base, &crtc_state->base);
-	intel_crtc->config = crtc_state;
+	crtc->pipe = pipe;
+	crtc->num_scalers = RUNTIME_INFO(dev_priv)->num_scalers[pipe];
 
 	primary = intel_primary_plane_create(dev_priv, pipe);
 	if (IS_ERR(primary)) {
 		ret = PTR_ERR(primary);
 		goto fail;
 	}
-	intel_crtc->plane_ids_mask |= BIT(primary->id);
+	crtc->plane_ids_mask |= BIT(primary->id);
 
 	for_each_sprite(dev_priv, pipe, sprite) {
 		struct intel_plane *plane;
@@ -15740,7 +16442,7 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 			ret = PTR_ERR(plane);
 			goto fail;
 		}
-		intel_crtc->plane_ids_mask |= BIT(plane->id);
+		crtc->plane_ids_mask |= BIT(plane->id);
 	}
 
 	cursor = intel_cursor_plane_create(dev_priv, pipe);
@@ -15748,7 +16450,7 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 		ret = PTR_ERR(cursor);
 		goto fail;
 	}
-	intel_crtc->plane_ids_mask |= BIT(cursor->id);
+	crtc->plane_ids_mask |= BIT(cursor->id);
 
 	if (HAS_GMCH(dev_priv)) {
 		if (IS_CHERRYVIEW(dev_priv) ||
@@ -15769,42 +16471,32 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 			funcs = &ilk_crtc_funcs;
 	}
 
-	ret = drm_crtc_init_with_planes(&dev_priv->drm, &intel_crtc->base,
+	ret = drm_crtc_init_with_planes(&dev_priv->drm, &crtc->base,
 					&primary->base, &cursor->base,
 					funcs, "pipe %c", pipe_name(pipe));
 	if (ret)
 		goto fail;
 
-	intel_crtc->pipe = pipe;
-
-	/* initialize shared scalers */
-	intel_crtc_init_scalers(intel_crtc, crtc_state);
-
 	BUG_ON(pipe >= ARRAY_SIZE(dev_priv->pipe_to_crtc_mapping) ||
 	       dev_priv->pipe_to_crtc_mapping[pipe] != NULL);
-	dev_priv->pipe_to_crtc_mapping[pipe] = intel_crtc;
+	dev_priv->pipe_to_crtc_mapping[pipe] = crtc;
 
 	if (INTEL_GEN(dev_priv) < 9) {
 		enum i9xx_plane_id i9xx_plane = primary->i9xx_plane;
 
 		BUG_ON(i9xx_plane >= ARRAY_SIZE(dev_priv->plane_to_crtc_mapping) ||
 		       dev_priv->plane_to_crtc_mapping[i9xx_plane] != NULL);
-		dev_priv->plane_to_crtc_mapping[i9xx_plane] = intel_crtc;
+		dev_priv->plane_to_crtc_mapping[i9xx_plane] = crtc;
 	}
 
-	intel_color_init(intel_crtc);
+	intel_color_init(crtc);
 
-	WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe);
+	WARN_ON(drm_crtc_index(&crtc->base) != crtc->pipe);
 
 	return 0;
 
 fail:
-	/*
-	 * drm_mode_config_cleanup() will free up any
-	 * crtcs/planes already initialized.
-	 */
-	kfree(crtc_state);
-	kfree(intel_crtc);
+	intel_crtc_free(crtc);
 
 	return ret;
 }
@@ -16291,8 +16983,11 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 	}
 
 	/* FIXME need to adjust LINOFF/TILEOFF accordingly. */
-	if (mode_cmd->offsets[0] != 0)
+	if (mode_cmd->offsets[0] != 0) {
+		DRM_DEBUG_KMS("plane 0 offset (0x%08x) must be 0\n",
+			      mode_cmd->offsets[0]);
 		goto err;
+	}
 
 	drm_helper_mode_fill_fb_struct(&dev_priv->drm, fb, mode_cmd);
 
@@ -16305,26 +17000,23 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 		}
 
 		stride_alignment = intel_fb_stride_alignment(fb, i);
-
-		/*
-		 * Display WA #0531: skl,bxt,kbl,glk
-		 *
-		 * Render decompression and plane width > 3840
-		 * combined with horizontal panning requires the
-		 * plane stride to be a multiple of 4. We'll just
-		 * require the entire fb to accommodate that to avoid
-		 * potential runtime errors at plane configuration time.
-		 */
-		if (IS_GEN(dev_priv, 9) && i == 0 && fb->width > 3840 &&
-		    is_ccs_modifier(fb->modifier))
-			stride_alignment *= 4;
-
 		if (fb->pitches[i] & (stride_alignment - 1)) {
 			DRM_DEBUG_KMS("plane %d pitch (%d) must be at least %u byte aligned\n",
 				      i, fb->pitches[i], stride_alignment);
 			goto err;
 		}
 
+		if (is_gen12_ccs_plane(fb, i)) {
+			int ccs_aux_stride = gen12_ccs_aux_stride(fb, i);
+
+			if (fb->pitches[i] != ccs_aux_stride) {
+				DRM_DEBUG_KMS("ccs aux plane %d pitch (%d) must be %d\n",
+					      i,
+					      fb->pitches[i], ccs_aux_stride);
+				goto err;
+			}
+		}
+
 		fb->obj[i] = &obj->base;
 	}
 
@@ -16522,29 +17214,28 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 	intel_init_cdclk_hooks(dev_priv);
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		dev_priv->display.get_pipe_config = haswell_get_pipe_config;
+		dev_priv->display.get_pipe_config = hsw_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
-			skylake_get_initial_plane_config;
-		dev_priv->display.crtc_compute_clock =
-			haswell_crtc_compute_clock;
-		dev_priv->display.crtc_enable = haswell_crtc_enable;
-		dev_priv->display.crtc_disable = haswell_crtc_disable;
+			skl_get_initial_plane_config;
+		dev_priv->display.crtc_compute_clock = hsw_crtc_compute_clock;
+		dev_priv->display.crtc_enable = hsw_crtc_enable;
+		dev_priv->display.crtc_disable = hsw_crtc_disable;
 	} else if (HAS_DDI(dev_priv)) {
-		dev_priv->display.get_pipe_config = haswell_get_pipe_config;
+		dev_priv->display.get_pipe_config = hsw_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
 			i9xx_get_initial_plane_config;
 		dev_priv->display.crtc_compute_clock =
-			haswell_crtc_compute_clock;
-		dev_priv->display.crtc_enable = haswell_crtc_enable;
-		dev_priv->display.crtc_disable = haswell_crtc_disable;
+			hsw_crtc_compute_clock;
+		dev_priv->display.crtc_enable = hsw_crtc_enable;
+		dev_priv->display.crtc_disable = hsw_crtc_disable;
 	} else if (HAS_PCH_SPLIT(dev_priv)) {
-		dev_priv->display.get_pipe_config = ironlake_get_pipe_config;
+		dev_priv->display.get_pipe_config = ilk_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
 			i9xx_get_initial_plane_config;
 		dev_priv->display.crtc_compute_clock =
-			ironlake_crtc_compute_clock;
-		dev_priv->display.crtc_enable = ironlake_crtc_enable;
-		dev_priv->display.crtc_disable = ironlake_crtc_disable;
+			ilk_crtc_compute_clock;
+		dev_priv->display.crtc_enable = ilk_crtc_enable;
+		dev_priv->display.crtc_disable = ilk_crtc_disable;
 	} else if (IS_CHERRYVIEW(dev_priv)) {
 		dev_priv->display.get_pipe_config = i9xx_get_pipe_config;
 		dev_priv->display.get_initial_plane_config =
@@ -16590,14 +17281,12 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 	}
 
 	if (IS_GEN(dev_priv, 5)) {
-		dev_priv->display.fdi_link_train = ironlake_fdi_link_train;
+		dev_priv->display.fdi_link_train = ilk_fdi_link_train;
 	} else if (IS_GEN(dev_priv, 6)) {
 		dev_priv->display.fdi_link_train = gen6_fdi_link_train;
 	} else if (IS_IVYBRIDGE(dev_priv)) {
 		/* FIXME: detect B0+ stepping and use auto training */
 		dev_priv->display.fdi_link_train = ivb_manual_fdi_link_train;
-	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
-		dev_priv->display.fdi_link_train = hsw_fdi_link_train;
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9)
@@ -16687,7 +17376,7 @@ retry:
 	/* Write calculated watermark values back */
 	for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
 		crtc_state->wm.need_postvbl_update = true;
-		dev_priv->display.optimize_watermarks(intel_state, crtc_state);
+		dev_priv->display.optimize_watermarks(intel_state, crtc);
 
 		to_intel_crtc_state(crtc->base.state)->wm = crtc_state->wm;
 	}
@@ -16719,8 +17408,7 @@ static int intel_initial_commit(struct drm_device *dev)
 {
 	struct drm_atomic_state *state = NULL;
 	struct drm_modeset_acquire_ctx ctx;
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *crtc_state;
+	struct intel_crtc *crtc;
 	int ret = 0;
 
 	state = drm_atomic_state_alloc(dev);
@@ -16732,15 +17420,17 @@ static int intel_initial_commit(struct drm_device *dev)
 retry:
 	state->acquire_ctx = &ctx;
 
-	drm_for_each_crtc(crtc, dev) {
-		crtc_state = drm_atomic_get_crtc_state(state, crtc);
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			intel_atomic_get_crtc_state(state, crtc);
+
 		if (IS_ERR(crtc_state)) {
 			ret = PTR_ERR(crtc_state);
 			goto out;
 		}
 
-		if (crtc_state->active) {
-			ret = drm_atomic_add_affected_planes(state, crtc);
+		if (crtc_state->hw.active) {
+			ret = drm_atomic_add_affected_planes(state, &crtc->base);
 			if (ret)
 				goto out;
 
@@ -16750,7 +17440,7 @@ retry:
 			 * having a proper LUT loaded. Remove once we
 			 * have readout for pipe gamma enable.
 			 */
-			crtc_state->color_mgmt_changed = true;
+			crtc_state->uapi.color_mgmt_changed = true;
 		}
 	}
 
@@ -17073,31 +17763,76 @@ static bool has_pch_trancoder(struct drm_i915_private *dev_priv,
 		(HAS_PCH_LPT_H(dev_priv) && pch_transcoder == PIPE_A);
 }
 
-static void intel_sanitize_crtc(struct intel_crtc *crtc,
-				struct drm_modeset_acquire_ctx *ctx)
+static void intel_sanitize_frame_start_delay(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_device *dev = crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
-	/* Clear any frame start delays used for debugging left by the BIOS */
-	if (crtc->active && !transcoder_is_dsi(cpu_transcoder)) {
+	if (INTEL_GEN(dev_priv) >= 9 ||
+	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) {
+		i915_reg_t reg = CHICKEN_TRANS(cpu_transcoder);
+		u32 val;
+
+		if (transcoder_is_dsi(cpu_transcoder))
+			return;
+
+		val = I915_READ(reg);
+		val &= ~HSW_FRAME_START_DELAY_MASK;
+		val |= HSW_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
+	} else {
 		i915_reg_t reg = PIPECONF(cpu_transcoder);
+		u32 val;
 
-		I915_WRITE(reg,
-			   I915_READ(reg) & ~PIPECONF_FRAME_START_DELAY_MASK);
+		val = I915_READ(reg);
+		val &= ~PIPECONF_FRAME_START_DELAY_MASK;
+		val |= PIPECONF_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
 	}
 
-	if (crtc_state->base.active) {
+	if (!crtc_state->has_pch_encoder)
+		return;
+
+	if (HAS_PCH_IBX(dev_priv)) {
+		i915_reg_t reg = PCH_TRANSCONF(crtc->pipe);
+		u32 val;
+
+		val = I915_READ(reg);
+		val &= ~TRANS_FRAME_START_DELAY_MASK;
+		val |= TRANS_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
+	} else {
+		enum pipe pch_transcoder = intel_crtc_pch_transcoder(crtc);
+		i915_reg_t reg = TRANS_CHICKEN2(pch_transcoder);
+		u32 val;
+
+		val = I915_READ(reg);
+		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
+		val |= TRANS_CHICKEN2_FRAME_START_DELAY(0);
+		I915_WRITE(reg, val);
+	}
+}
+
+static void intel_sanitize_crtc(struct intel_crtc *crtc,
+				struct drm_modeset_acquire_ctx *ctx)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state);
+
+	if (crtc_state->hw.active) {
 		struct intel_plane *plane;
 
+		/* Clear any frame start delays used for debugging left by the BIOS */
+		intel_sanitize_frame_start_delay(crtc_state);
+
 		/* Disable everything but the primary plane */
 		for_each_intel_plane_on_crtc(dev, crtc, plane) {
 			const struct intel_plane_state *plane_state =
 				to_intel_plane_state(plane->base.state);
 
-			if (plane_state->base.visible &&
+			if (plane_state->uapi.visible &&
 			    plane->base.type != DRM_PLANE_TYPE_PRIMARY)
 				intel_plane_disable_noatomic(crtc, plane);
 		}
@@ -17114,10 +17849,10 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc,
 
 	/* Adjust the state of the output pipe according to whether we
 	 * have active connectors/encoders. */
-	if (crtc_state->base.active && !intel_crtc_has_encoders(crtc))
-		intel_crtc_disable_noatomic(&crtc->base, ctx);
+	if (crtc_state->hw.active && !intel_crtc_has_encoders(crtc))
+		intel_crtc_disable_noatomic(crtc, ctx);
 
-	if (crtc_state->base.active || HAS_GMCH(dev_priv)) {
+	if (crtc_state->hw.active || HAS_GMCH(dev_priv)) {
 		/*
 		 * We start out with underrun reporting disabled to avoid races.
 		 * For correct bookkeeping mark this on active crtcs.
@@ -17148,7 +17883,7 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc,
 
 static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	/*
 	 * Some SNB BIOSen (eg. ASUS K53SV) are known to misprogram
@@ -17161,7 +17896,7 @@ static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state)
 	 * road.
 	 */
 	return IS_GEN(dev_priv, 6) &&
-		crtc_state->base.active &&
+		crtc_state->hw.active &&
 		crtc_state->shared_dpll &&
 		crtc_state->port_clock == 0;
 }
@@ -17178,7 +17913,7 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 	 * encoder is active and trying to read from a pipe) and the
 	 * pipe itself being active. */
 	bool has_active_crtc = crtc_state &&
-		crtc_state->base.active;
+		crtc_state->hw.active;
 
 	if (crtc_state && has_bogus_dpll_config(crtc_state)) {
 		DRM_DEBUG_KMS("BIOS has misprogrammed the hardware. Disabling pipe %c\n",
@@ -17282,22 +18017,22 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		struct intel_crtc_state *crtc_state =
 			to_intel_crtc_state(crtc->base.state);
 
-		__drm_atomic_helper_crtc_destroy_state(&crtc_state->base);
-		memset(crtc_state, 0, sizeof(*crtc_state));
-		__drm_atomic_helper_crtc_reset(&crtc->base, &crtc_state->base);
+		__drm_atomic_helper_crtc_destroy_state(&crtc_state->uapi);
+		intel_crtc_free_hw_state(crtc_state);
+		intel_crtc_state_reset(crtc_state, crtc);
 
-		crtc_state->base.active = crtc_state->base.enable =
+		crtc_state->hw.active = crtc_state->hw.enable =
 			dev_priv->display.get_pipe_config(crtc, crtc_state);
 
-		crtc->base.enabled = crtc_state->base.enable;
-		crtc->active = crtc_state->base.active;
+		crtc->base.enabled = crtc_state->hw.enable;
+		crtc->active = crtc_state->hw.active;
 
-		if (crtc_state->base.active)
+		if (crtc_state->hw.active)
 			dev_priv->active_pipes |= BIT(crtc->pipe);
 
 		DRM_DEBUG_KMS("[CRTC:%d:%s] hw state readout: %s\n",
 			      crtc->base.base.id, crtc->base.name,
-			      enableddisabled(crtc_state->base.active));
+			      enableddisabled(crtc_state->hw.active));
 	}
 
 	readout_plane_state(dev_priv);
@@ -17319,7 +18054,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			struct intel_crtc_state *crtc_state =
 				to_intel_crtc_state(crtc->base.state);
 
-			if (crtc_state->base.active &&
+			if (crtc_state->hw.active &&
 			    crtc_state->shared_dpll == pll)
 				pll->state.crtc_mask |= 1 << crtc->pipe;
 		}
@@ -17364,15 +18099,15 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			crtc = to_intel_crtc(encoder->base.crtc);
 			crtc_state = crtc ? to_intel_crtc_state(crtc->base.state) : NULL;
 
-			if (crtc_state && crtc_state->base.active) {
+			if (crtc_state && crtc_state->hw.active) {
 				/*
 				 * This has to be done during hardware readout
 				 * because anything calling .crtc_disable may
 				 * rely on the connector_mask being accurate.
 				 */
-				crtc_state->base.connector_mask |=
+				crtc_state->uapi.connector_mask |=
 					drm_connector_mask(&connector->base);
-				crtc_state->base.encoder_mask |=
+				crtc_state->uapi.encoder_mask |=
 					drm_encoder_mask(&encoder->base);
 			}
 		} else {
@@ -17393,16 +18128,15 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		struct intel_plane *plane;
 		int min_cdclk = 0;
 
-		if (crtc_state->base.active) {
-			struct drm_display_mode mode;
+		if (crtc_state->hw.active) {
+			struct drm_display_mode *mode = &crtc_state->hw.mode;
 
-			intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode,
+			intel_mode_from_pipe_config(&crtc_state->hw.adjusted_mode,
 						    crtc_state);
 
-			mode = crtc_state->base.adjusted_mode;
-			mode.hdisplay = crtc_state->pipe_src_w;
-			mode.vdisplay = crtc_state->pipe_src_h;
-			WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->base, &mode));
+			*mode = crtc_state->hw.adjusted_mode;
+			mode->hdisplay = crtc_state->pipe_src_w;
+			mode->vdisplay = crtc_state->pipe_src_h;
 
 			/*
 			 * The initial mode needs to be set in order to keep
@@ -17413,11 +18147,13 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			 * set a flag to indicate that a full recalculation is
 			 * needed on the next commit.
 			 */
-			crtc_state->base.mode.private_flags = I915_MODE_FLAG_INHERITED;
+			mode->private_flags = I915_MODE_FLAG_INHERITED;
 
 			intel_crtc_compute_pixel_rate(crtc_state);
 
 			intel_crtc_update_active_timings(crtc_state);
+
+			intel_crtc_copy_hw_to_uapi_state(crtc_state);
 		}
 
 		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
@@ -17428,14 +18164,14 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			 * FIXME don't have the fb yet, so can't
 			 * use intel_plane_data_rate() :(
 			 */
-			if (plane_state->base.visible)
+			if (plane_state->uapi.visible)
 				crtc_state->data_rate[plane->id] =
 					4 * crtc_state->pixel_rate;
 			/*
 			 * FIXME don't have the fb yet, so can't
 			 * use plane->min_cdclk() :(
 			 */
-			if (plane_state->base.visible && plane->min_cdclk) {
+			if (plane_state->uapi.visible && plane->min_cdclk) {
 				if (crtc_state->double_wide ||
 				    INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 					crtc_state->min_cdclk[plane->id] =
@@ -17449,7 +18185,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 				      crtc_state->min_cdclk[plane->id]);
 		}
 
-		if (crtc_state->base.active) {
+		if (crtc_state->hw.active) {
 			min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
 			if (WARN_ON(min_cdclk < 0))
 				min_cdclk = 0;
@@ -17490,8 +18226,11 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 
 static void intel_early_display_was(struct drm_i915_private *dev_priv)
 {
-	/* Display WA #1185 WaDisableDARBFClkGating:cnl,glk */
-	if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+	/*
+	 * Display WA #1185 WaDisableDARBFClkGating:cnl,glk,icl,ehl,tgl
+	 * Also known as Wa_14010480278.
+	 */
+	if (IS_GEN_RANGE(dev_priv, 10, 12) || IS_GEMINILAKE(dev_priv))
 		I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 			   DARBF_GATING_DIS);
 
@@ -17572,7 +18311,6 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 			     struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc_state *crtc_state;
 	struct intel_encoder *encoder;
 	struct intel_crtc *crtc;
 	intel_wakeref_t wakeref;
@@ -17592,7 +18330,7 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 		/* We need to sanitize only the MST primary port. */
 		if (encoder->type != INTEL_OUTPUT_DP_MST &&
 		    intel_phy_is_tc(dev_priv, phy))
-			intel_tc_port_sanitize(enc_to_dig_port(&encoder->base));
+			intel_tc_port_sanitize(enc_to_dig_port(encoder));
 	}
 
 	get_encoder_power_domains(dev_priv);
@@ -17605,11 +18343,12 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 	 * waits, so we need vblank interrupts restored beforehand.
 	 */
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		crtc_state = to_intel_crtc_state(crtc->base.state);
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
 
 		drm_crtc_vblank_reset(&crtc->base);
 
-		if (crtc_state->base.active)
+		if (crtc_state->hw.active)
 			intel_crtc_vblank_on(crtc_state);
 	}
 
@@ -17619,7 +18358,9 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 		intel_sanitize_encoder(encoder);
 
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		crtc_state = to_intel_crtc_state(crtc->base.state);
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
+
 		intel_sanitize_crtc(crtc, ctx);
 		intel_dump_pipe_config(crtc_state, NULL, "[setup_hw_state]");
 	}
@@ -17652,17 +18393,16 @@ intel_modeset_setup_hw_state(struct drm_device *dev,
 	}
 
 	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			to_intel_crtc_state(crtc->base.state);
 		u64 put_domains;
 
-		crtc_state = to_intel_crtc_state(crtc->base.state);
 		put_domains = modeset_get_crtc_power_domains(crtc_state);
 		if (WARN_ON(put_domains))
 			modeset_put_power_domains(dev_priv, put_domains);
 	}
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref);
-
-	intel_fbc_init_pipe_state(dev_priv);
 }
 
 void intel_display_resume(struct drm_device *dev)
@@ -17738,6 +18478,13 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915)
 	 */
 	intel_hpd_poll_fini(i915);
 
+	/*
+	 * MST topology needs to be suspended so we don't have any calls to
+	 * fbdev after it's finalized. MST will be destroyed later as part of
+	 * drm_mode_config_cleanup()
+	 */
+	intel_dp_mst_suspend(i915);
+
 	/* poll work can call into fbdev, hence clean that up afterwards */
 	intel_fbdev_fini(i915);
 
@@ -17756,6 +18503,8 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915)
 
 	intel_gmbus_teardown(i915);
 
+	intel_bw_cleanup(i915);
+
 	destroy_workqueue(i915->flip_wq);
 	destroy_workqueue(i915->modeset_wq);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index f417e0948001..028aab728514 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -332,8 +332,11 @@ enum phy_fia {
 	     (__s) < RUNTIME_INFO(__dev_priv)->num_sprites[(__p)];	\
 	     (__s)++)
 
-#define for_each_port_masked(__port, __ports_mask) \
-	for ((__port) = PORT_A; (__port) < I915_MAX_PORTS; (__port)++)	\
+#define for_each_port(__port) \
+	for ((__port) = PORT_A; (__port) < I915_MAX_PORTS; (__port)++)
+
+#define for_each_port_masked(__port, __ports_mask)			\
+	for_each_port(__port)						\
 		for_each_if((__ports_mask) & BIT(__port))
 
 #define for_each_phy_masked(__phy, __phys_mask) \
@@ -377,6 +380,13 @@ enum phy_fia {
 			    &(dev)->mode_config.encoder_list,	\
 			    base.head)
 
+#define for_each_intel_encoder_mask(dev, intel_encoder, encoder_mask)	\
+	list_for_each_entry(intel_encoder,				\
+			    &(dev)->mode_config.encoder_list,		\
+			    base.head)					\
+		for_each_if((encoder_mask) &				\
+			    drm_encoder_mask(&intel_encoder->base))
+
 #define for_each_intel_dp(dev, intel_encoder)			\
 	for_each_intel_encoder(dev, intel_encoder)		\
 		for_each_if(intel_encoder_is_dp(intel_encoder))
@@ -446,16 +456,25 @@ enum phy_fia {
 #define intel_atomic_crtc_state_for_each_plane_state( \
 		  plane, plane_state, \
 		  crtc_state) \
-	for_each_intel_plane_mask(((crtc_state)->base.state->dev), (plane), \
-				((crtc_state)->base.plane_mask)) \
+	for_each_intel_plane_mask(((crtc_state)->uapi.state->dev), (plane), \
+				((crtc_state)->uapi.plane_mask)) \
 		for_each_if ((plane_state = \
-			      to_intel_plane_state(__drm_atomic_get_current_plane_state((crtc_state)->base.state, &plane->base))))
+			      to_intel_plane_state(__drm_atomic_get_current_plane_state((crtc_state)->uapi.state, &plane->base))))
+
+#define for_each_new_intel_connector_in_state(__state, connector, new_connector_state, __i) \
+	for ((__i) = 0; \
+	     (__i) < (__state)->base.num_connector; \
+	     (__i)++) \
+		for_each_if ((__state)->base.connectors[__i].ptr && \
+			     ((connector) = to_intel_connector((__state)->base.connectors[__i].ptr), \
+			     (new_connector_state) = to_intel_digital_connector_state((__state)->base.connectors[__i].new_state), 1))
 
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
 			    bool constant_n, bool fec_enable);
 bool is_ccs_modifier(u64 modifier);
+int intel_main_to_aux_plane(const struct drm_framebuffer *fb, int main_plane);
 void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 			      u32 pixel_format, u64 modifier);
@@ -467,6 +486,7 @@ enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
 bool is_trans_port_sync_mode(const struct intel_crtc_state *state);
 
 void intel_plane_destroy(struct drm_plane *plane);
+void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state);
 void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe);
 void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe);
 enum pipe intel_crtc_pch_transcoder(struct intel_crtc *crtc);
@@ -499,11 +519,10 @@ enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv,
 			      enum port port);
 int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
-enum transcoder intel_pipe_to_cpu_transcoder(struct drm_i915_private *dev_priv,
-					     enum pipe pipe);
 u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc);
+void intel_crtc_vblank_off(const struct intel_crtc_state *crtc_state);
 
-int ironlake_get_lanes_required(int target_clock, int link_bw, int bpp);
+int ilk_get_lanes_required(int target_clock, int link_bw, int bpp);
 void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 			 struct intel_digital_port *dport,
 			 unsigned int expected_mask);
@@ -547,7 +566,6 @@ bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state,
 			struct dpll *best_clock);
 int chv_calc_dpll_params(int refclk, struct dpll *pll_clock);
 
-bool intel_crtc_active(struct intel_crtc *crtc);
 bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state);
 void hsw_enable_ips(const struct intel_crtc_state *crtc_state);
 void hsw_disable_ips(const struct intel_crtc_state *crtc_state);
@@ -561,6 +579,8 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 
 u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
+void skl_scaler_disable(const struct intel_crtc_state *old_crtc_state);
+void ilk_pfit_disable(const struct intel_crtc_state *old_crtc_state);
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
 u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state);
@@ -582,6 +602,10 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv);
 void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 				     struct intel_display_error_state *error);
 
+bool
+intel_format_info_is_yuv_semiplanar(const struct drm_format_info *info,
+				    uint64_t modifier);
+
 /* modesetting */
 void intel_modeset_init_hw(struct drm_i915_private *i915);
 int intel_modeset_init(struct drm_i915_private *i915);
@@ -603,9 +627,10 @@ void assert_fdi_rx_pll(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, bool state);
 #define assert_fdi_rx_pll_enabled(d, p) assert_fdi_rx_pll(d, p, true)
 #define assert_fdi_rx_pll_disabled(d, p) assert_fdi_rx_pll(d, p, false)
-void assert_pipe(struct drm_i915_private *dev_priv, enum pipe pipe, bool state);
-#define assert_pipe_enabled(d, p) assert_pipe(d, p, true)
-#define assert_pipe_disabled(d, p) assert_pipe(d, p, false)
+void assert_pipe(struct drm_i915_private *dev_priv,
+		 enum transcoder cpu_transcoder, bool state);
+#define assert_pipe_enabled(d, t) assert_pipe(d, t, true)
+#define assert_pipe_disabled(d, t) assert_pipe(d, t, false)
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 12ba74788cce..21561acfa3ac 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -418,7 +418,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 	int pw_idx = power_well->desc->hsw.idx;
 	enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx);
 	u32 val;
-	int wa_idx_max;
+
+	WARN_ON(!IS_ICELAKE(dev_priv));
 
 	val = I915_READ(regs->driver);
 	I915_WRITE(regs->driver, val | HSW_PWR_WELL_CTL_REQ(pw_idx));
@@ -430,14 +431,8 @@ icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 
 	hsw_wait_for_power_well_enable(dev_priv, power_well);
 
-	/* Display WA #1178: icl, tgl */
-	if (IS_TIGERLAKE(dev_priv))
-		wa_idx_max = ICL_PW_CTL_IDX_AUX_C;
-	else
-		wa_idx_max = ICL_PW_CTL_IDX_AUX_B;
-
-	if (!IS_ELKHARTLAKE(dev_priv) &&
-	    pw_idx >= ICL_PW_CTL_IDX_AUX_A && pw_idx <= wa_idx_max &&
+	/* Display WA #1178: icl */
+	if (pw_idx >= ICL_PW_CTL_IDX_AUX_A && pw_idx <= ICL_PW_CTL_IDX_AUX_B &&
 	    !intel_bios_is_port_edp(dev_priv, (enum port)phy)) {
 		val = I915_READ(ICL_AUX_ANAOVRD1(pw_idx));
 		val |= ICL_AUX_ANAOVRD1_ENABLE | ICL_AUX_ANAOVRD1_LDO_BYPASS;
@@ -454,10 +449,10 @@ icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
 	enum phy phy = ICL_AUX_PW_TO_PHY(pw_idx);
 	u32 val;
 
-	if (INTEL_GEN(dev_priv) < 12) {
-		val = I915_READ(ICL_PORT_CL_DW12(phy));
-		I915_WRITE(ICL_PORT_CL_DW12(phy), val & ~ICL_LANE_ENABLE_AUX);
-	}
+	WARN_ON(!IS_ICELAKE(dev_priv));
+
+	val = I915_READ(ICL_PORT_CL_DW12(phy));
+	I915_WRITE(ICL_PORT_CL_DW12(phy), val & ~ICL_LANE_ENABLE_AUX);
 
 	val = I915_READ(regs->driver);
 	I915_WRITE(regs->driver, val & ~HSW_PWR_WELL_CTL_REQ(pw_idx));
@@ -519,7 +514,7 @@ static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv,
 		if (encoder->type == INTEL_OUTPUT_DP_MST)
 			continue;
 
-		dig_port = enc_to_dig_port(&encoder->base);
+		dig_port = enc_to_dig_port(encoder);
 		if (WARN_ON(!dig_port))
 			continue;
 
@@ -1669,8 +1664,8 @@ void chv_phy_powergate_lanes(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct i915_power_domains *power_domains = &dev_priv->power_domains;
-	enum dpio_phy phy = vlv_dport_to_phy(enc_to_dig_port(&encoder->base));
-	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
+	enum dpio_phy phy = vlv_dport_to_phy(enc_to_dig_port(encoder));
+	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(encoder));
 
 	mutex_lock(&power_domains->lock);
 
@@ -4928,6 +4923,56 @@ static void cnl_display_core_uninit(struct drm_i915_private *dev_priv)
 	intel_combo_phy_uninit(dev_priv);
 }
 
+struct buddy_page_mask {
+	u32 page_mask;
+	u8 type;
+	u8 num_channels;
+};
+
+static const struct buddy_page_mask tgl_buddy_page_masks[] = {
+	{ .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE },
+	{ .num_channels = 1, .type = INTEL_DRAM_DDR4,   .page_mask = 0xF },
+	{ .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C },
+	{ .num_channels = 2, .type = INTEL_DRAM_DDR4,   .page_mask = 0x1F },
+	{}
+};
+
+static const struct buddy_page_mask wa_1409767108_buddy_page_masks[] = {
+	{ .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1 },
+	{ .num_channels = 1, .type = INTEL_DRAM_DDR4,   .page_mask = 0x1 },
+	{ .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x3 },
+	{ .num_channels = 2, .type = INTEL_DRAM_DDR4,   .page_mask = 0x3 },
+	{}
+};
+
+static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
+{
+	enum intel_dram_type type = dev_priv->dram_info.type;
+	u8 num_channels = dev_priv->dram_info.num_channels;
+	const struct buddy_page_mask *table;
+	int i;
+
+	if (IS_TGL_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_A0))
+		/* Wa_1409767108: tgl */
+		table = wa_1409767108_buddy_page_masks;
+	else
+		table = tgl_buddy_page_masks;
+
+	for (i = 0; table[i].page_mask != 0; i++)
+		if (table[i].num_channels == num_channels &&
+		    table[i].type == type)
+			break;
+
+	if (table[i].page_mask == 0) {
+		DRM_DEBUG_DRIVER("Unknown memory configuration; disabling address buddy logic.\n");
+		I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE);
+		I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE);
+	} else {
+		I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask);
+		I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask);
+	}
+}
+
 static void icl_display_core_init(struct drm_i915_private *dev_priv,
 				  bool resume)
 {
@@ -4960,6 +5005,10 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 	/* 6. Setup MBUS. */
 	icl_mbus_init(dev_priv);
 
+	/* 7. Program arbiter BW_BUDDY registers */
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_bw_buddy_init(dev_priv);
+
 	if (resume && dev_priv->csr.dmc_payload)
 		intel_csr_load_program(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index 1da04f3e0fb3..2608a65af7fa 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -28,7 +28,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_TRANSCODER_C,
 	POWER_DOMAIN_TRANSCODER_D,
 	POWER_DOMAIN_TRANSCODER_EDP,
-	/* VDSC/joining for TRANSCODER_EDP (ICL) or TRANSCODER_A (TGL) */
+	/* VDSC/joining for eDP/DSI transcoder (ICL) or pipe A (TGL) */
 	POWER_DOMAIN_TRANSCODER_VDSC_PW2,
 	POWER_DOMAIN_TRANSCODER_DSI_A,
 	POWER_DOMAIN_TRANSCODER_DSI_C,
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 1a7334dbe802..888ea8a170d1 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -90,8 +90,8 @@ struct intel_framebuffer {
 	/* for each plane in the normal GTT view */
 	struct {
 		unsigned int x, y;
-	} normal[2];
-	/* for each plane in the rotated GTT view */
+	} normal[4];
+	/* for each plane in the rotated GTT view for no-CCS formats */
 	struct {
 		unsigned int x, y;
 		unsigned int pitch; /* pixels */
@@ -523,7 +523,24 @@ struct intel_atomic_state {
 };
 
 struct intel_plane_state {
-	struct drm_plane_state base;
+	struct drm_plane_state uapi;
+
+	/*
+	 * actual hardware state, the state we program to the hardware.
+	 * The following members are used to verify the hardware state:
+	 * During initial hw readout, they need to be copied from uapi.
+	 */
+	struct {
+		struct drm_crtc *crtc;
+		struct drm_framebuffer *fb;
+
+		u16 alpha;
+		uint16_t pixel_blend_mode;
+		unsigned int rotation;
+		enum drm_color_encoding color_encoding;
+		enum drm_color_range color_range;
+	} hw;
+
 	struct i915_ggtt_view view;
 	struct i915_vma *vma;
 	unsigned long flags;
@@ -538,7 +555,7 @@ struct intel_plane_state {
 		 */
 		u32 stride;
 		int x, y;
-	} color_plane[2];
+	} color_plane[4];
 
 	/* plane control register */
 	u32 ctl;
@@ -546,6 +563,9 @@ struct intel_plane_state {
 	/* plane color control register */
 	u32 color_ctl;
 
+	/* chroma upsampler control register */
+	u32 cus_ctl;
+
 	/*
 	 * scaler_id
 	 *    = -1 : not using a scaler
@@ -757,7 +777,33 @@ enum intel_output_format {
 };
 
 struct intel_crtc_state {
-	struct drm_crtc_state base;
+	/*
+	 * uapi (drm) state. This is the software state shown to userspace.
+	 * In particular, the following members are used for bookkeeping:
+	 * - crtc
+	 * - state
+	 * - *_changed
+	 * - event
+	 * - commit
+	 * - mode_blob
+	 */
+	struct drm_crtc_state uapi;
+
+	/*
+	 * actual hardware state, the state we program to the hardware.
+	 * The following members are used to verify the hardware state:
+	 * - enable
+	 * - active
+	 * - mode / adjusted_mode
+	 * - color property blobs.
+	 *
+	 * During initial hw readout, they need to be copied to uapi.
+	 */
+	struct {
+		bool active, enable;
+		struct drm_property_blob *degamma_lut, *gamma_lut, *ctm;
+		struct drm_display_mode mode, adjusted_mode;
+	} hw;
 
 	/**
 	 * quirks - bitfield with hw state readout quirks
@@ -1008,6 +1054,9 @@ struct intel_crtc_state {
 
 	/* Bitmask to indicate slaves attached */
 	u8 sync_mode_slaves_mask;
+
+	/* Only valid on TGL+ */
+	enum transcoder mst_master_transcoder;
 };
 
 struct intel_crtc {
@@ -1080,9 +1129,6 @@ struct intel_plane {
 	void (*update_plane)(struct intel_plane *plane,
 			     const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state);
-	void (*update_slave)(struct intel_plane *plane,
-			     const struct intel_crtc_state *crtc_state,
-			     const struct intel_plane_state *plane_state);
 	void (*disable_plane)(struct intel_plane *plane,
 			      const struct intel_crtc_state *crtc_state);
 	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
@@ -1113,12 +1159,12 @@ struct cxsr_latency {
 
 #define to_intel_atomic_state(x) container_of(x, struct intel_atomic_state, base)
 #define to_intel_crtc(x) container_of(x, struct intel_crtc, base)
-#define to_intel_crtc_state(x) container_of(x, struct intel_crtc_state, base)
+#define to_intel_crtc_state(x) container_of(x, struct intel_crtc_state, uapi)
 #define to_intel_connector(x) container_of(x, struct intel_connector, base)
 #define to_intel_encoder(x) container_of(x, struct intel_encoder, base)
 #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base)
 #define to_intel_plane(x) container_of(x, struct intel_plane, base)
-#define to_intel_plane_state(x) container_of(x, struct intel_plane_state, base)
+#define to_intel_plane_state(x) container_of(x, struct intel_plane_state, uapi)
 #define intel_fb_obj(x) ((x) ? to_intel_bo((x)->obj[0]) : NULL)
 
 struct intel_hdmi {
@@ -1392,9 +1438,9 @@ struct intel_load_detect_pipe {
 };
 
 static inline struct intel_encoder *
-intel_attached_encoder(struct drm_connector *connector)
+intel_attached_encoder(struct intel_connector *connector)
 {
-	return to_intel_connector(connector)->encoder;
+	return connector->encoder;
 }
 
 static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
@@ -1411,12 +1457,12 @@ static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
 }
 
 static inline struct intel_digital_port *
-enc_to_dig_port(struct drm_encoder *encoder)
+enc_to_dig_port(struct intel_encoder *encoder)
 {
-	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
+	struct intel_encoder *intel_encoder = encoder;
 
 	if (intel_encoder_is_dig_port(intel_encoder))
-		return container_of(encoder, struct intel_digital_port,
+		return container_of(&encoder->base, struct intel_digital_port,
 				    base.base);
 	else
 		return NULL;
@@ -1425,16 +1471,17 @@ enc_to_dig_port(struct drm_encoder *encoder)
 static inline struct intel_digital_port *
 conn_to_dig_port(struct intel_connector *connector)
 {
-	return enc_to_dig_port(&intel_attached_encoder(&connector->base)->base);
+	return enc_to_dig_port(intel_attached_encoder(connector));
 }
 
 static inline struct intel_dp_mst_encoder *
-enc_to_mst(struct drm_encoder *encoder)
+enc_to_mst(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_dp_mst_encoder, base.base);
+	return container_of(&encoder->base, struct intel_dp_mst_encoder,
+			    base.base);
 }
 
-static inline struct intel_dp *enc_to_intel_dp(struct drm_encoder *encoder)
+static inline struct intel_dp *enc_to_intel_dp(struct intel_encoder *encoder)
 {
 	return &enc_to_dig_port(encoder)->dp;
 }
@@ -1447,14 +1494,14 @@ static inline bool intel_encoder_is_dp(struct intel_encoder *encoder)
 		return true;
 	case INTEL_OUTPUT_DDI:
 		/* Skip pure HDMI/DVI DDI encoders */
-		return i915_mmio_reg_valid(enc_to_intel_dp(&encoder->base)->output_reg);
+		return i915_mmio_reg_valid(enc_to_intel_dp(encoder)->output_reg);
 	default:
 		return false;
 	}
 }
 
 static inline struct intel_lspcon *
-enc_to_intel_lspcon(struct drm_encoder *encoder)
+enc_to_intel_lspcon(struct intel_encoder *encoder)
 {
 	return &enc_to_dig_port(encoder)->lspcon;
 }
@@ -1528,6 +1575,24 @@ intel_atomic_get_new_crtc_state(struct intel_atomic_state *state,
 								 &crtc->base));
 }
 
+static inline struct intel_digital_connector_state *
+intel_atomic_get_new_connector_state(struct intel_atomic_state *state,
+				     struct intel_connector *connector)
+{
+	return to_intel_digital_connector_state(
+			drm_atomic_get_new_connector_state(&state->base,
+			&connector->base));
+}
+
+static inline struct intel_digital_connector_state *
+intel_atomic_get_old_connector_state(struct intel_atomic_state *state,
+				     struct intel_connector *connector)
+{
+	return to_intel_digital_connector_state(
+			drm_atomic_get_old_connector_state(&state->base,
+			&connector->base));
+}
+
 /* intel_display.c */
 static inline bool
 intel_crtc_has_type(const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index b05b2191b919..c7424e2a04a3 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -146,9 +146,9 @@ bool intel_dp_is_edp(struct intel_dp *intel_dp)
 	return intel_dig_port->base.type == INTEL_OUTPUT_EDP;
 }
 
-static struct intel_dp *intel_attached_dp(struct drm_connector *connector)
+static struct intel_dp *intel_attached_dp(struct intel_connector *connector)
 {
-	return enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+	return enc_to_intel_dp(intel_attached_encoder(connector));
 }
 
 static void intel_dp_link_down(struct intel_encoder *encoder,
@@ -614,7 +614,7 @@ static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
@@ -834,7 +834,7 @@ static enum pipe vlv_find_free_pps(struct drm_i915_private *dev_priv)
 	 * Pick one that's not used by other ports.
 	 */
 	for_each_intel_dp(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		if (encoder->type == INTEL_OUTPUT_EDP) {
 			WARN_ON(intel_dp->active_pipe != INVALID_PIPE &&
@@ -1031,7 +1031,7 @@ void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
 	 */
 
 	for_each_intel_dp(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		WARN_ON(intel_dp->active_pipe != INVALID_PIPE);
 
@@ -1814,7 +1814,7 @@ static void intel_dp_print_rates(struct intel_dp *intel_dp)
 {
 	char str[128]; /* FIXME: too big for stack? */
 
-	if ((drm_debug & DRM_UT_KMS) == 0)
+	if (!drm_debug_enabled(DRM_UT_KMS))
 		return;
 
 	snprintf_int_array(str, sizeof(str),
@@ -1889,32 +1889,15 @@ static bool intel_dp_supports_fec(struct intel_dp *intel_dp,
 		drm_dp_sink_supports_fec(intel_dp->fec_capable);
 }
 
-static bool intel_dp_source_supports_dsc(struct intel_dp *intel_dp,
-					 const struct intel_crtc_state *pipe_config)
-{
-	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-
-	if (!INTEL_INFO(dev_priv)->display.has_dsc)
-		return false;
-
-	/* On TGL, DSC is supported on all Pipes */
-	if (INTEL_GEN(dev_priv) >= 12)
-		return true;
-
-	if (INTEL_GEN(dev_priv) >= 10 &&
-	    pipe_config->cpu_transcoder != TRANSCODER_A)
-		return true;
-
-	return false;
-}
-
 static bool intel_dp_supports_dsc(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *pipe_config)
+				  const struct intel_crtc_state *crtc_state)
 {
-	if (!intel_dp_is_edp(intel_dp) && !pipe_config->fec_enable)
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+
+	if (!intel_dp_is_edp(intel_dp) && !crtc_state->fec_enable)
 		return false;
 
-	return intel_dp_source_supports_dsc(intel_dp, pipe_config) &&
+	return intel_dsc_source_support(encoder, crtc_state) &&
 		drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd);
 }
 
@@ -1999,7 +1982,7 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp,
 				  struct intel_crtc_state *pipe_config,
 				  const struct link_config_limits *limits)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int bpp, clock, lane_count;
 	int mode_rate, link_clock, link_avail;
 
@@ -2046,6 +2029,63 @@ static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc)
 	return 0;
 }
 
+#define DSC_SUPPORTED_VERSION_MIN		1
+
+static int intel_dp_dsc_compute_params(struct intel_encoder *encoder,
+				       struct intel_crtc_state *crtc_state)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	u8 line_buf_depth;
+	int ret;
+
+	ret = intel_dsc_compute_params(encoder, crtc_state);
+	if (ret)
+		return ret;
+
+	/*
+	 * Slice Height of 8 works for all currently available panels. So start
+	 * with that if pic_height is an integral multiple of 8. Eventually add
+	 * logic to try multiple slice heights.
+	 */
+	if (vdsc_cfg->pic_height % 8 == 0)
+		vdsc_cfg->slice_height = 8;
+	else if (vdsc_cfg->pic_height % 4 == 0)
+		vdsc_cfg->slice_height = 4;
+	else
+		vdsc_cfg->slice_height = 2;
+
+	vdsc_cfg->dsc_version_major =
+		(intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
+		 DP_DSC_MAJOR_MASK) >> DP_DSC_MAJOR_SHIFT;
+	vdsc_cfg->dsc_version_minor =
+		min(DSC_SUPPORTED_VERSION_MIN,
+		    (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
+		     DP_DSC_MINOR_MASK) >> DP_DSC_MINOR_SHIFT);
+
+	vdsc_cfg->convert_rgb = intel_dp->dsc_dpcd[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT] &
+		DP_DSC_RGB;
+
+	line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd);
+	if (!line_buf_depth) {
+		DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n");
+		return -EINVAL;
+	}
+
+	if (vdsc_cfg->dsc_version_minor == 2)
+		vdsc_cfg->line_buf_depth = (line_buf_depth == DSC_1_2_MAX_LINEBUF_DEPTH_BITS) ?
+			DSC_1_2_MAX_LINEBUF_DEPTH_VAL : line_buf_depth;
+	else
+		vdsc_cfg->line_buf_depth = (line_buf_depth > DSC_1_1_MAX_LINEBUF_DEPTH_BITS) ?
+			DSC_1_1_MAX_LINEBUF_DEPTH_BITS : line_buf_depth;
+
+	vdsc_cfg->block_pred_enable =
+		intel_dp->dsc_dpcd[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] &
+		DP_DSC_BLK_PREDICTION_IS_SUPPORTED;
+
+	return drm_dsc_compute_rc_parameters(vdsc_cfg);
+}
+
 static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 				       struct intel_crtc_state *pipe_config,
 				       struct drm_connector_state *conn_state,
@@ -2053,7 +2093,7 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	u8 dsc_max_bpc;
 	int pipe_bpp;
 	int ret;
@@ -2132,7 +2172,7 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 		}
 	}
 
-	ret = intel_dp_compute_dsc_params(intel_dp, pipe_config);
+	ret = intel_dp_dsc_compute_params(&dig_port->base, pipe_config);
 	if (ret < 0) {
 		DRM_DEBUG_KMS("Cannot compute valid DSC parameters for Input Bpp = %d "
 			      "Compressed BPP = %d\n",
@@ -2164,8 +2204,8 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config,
 			     struct drm_connector_state *conn_state)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct link_config_limits limits;
 	int common_len;
 	int ret;
@@ -2252,8 +2292,8 @@ intel_dp_ycbcr420_config(struct intel_dp *intel_dp,
 {
 	const struct drm_display_info *info = &connector->display_info;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+		&crtc_state->hw.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	int ret;
 
 	if (!drm_mode_is_420_only(info, adjusted_mode) ||
@@ -2281,7 +2321,7 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 	const struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	/*
 	 * Our YCbCr output is always limited range.
@@ -2308,17 +2348,28 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 	}
 }
 
+static bool intel_dp_port_has_audio(struct drm_i915_private *dev_priv,
+				    enum port port)
+{
+	if (IS_G4X(dev_priv))
+		return false;
+	if (INTEL_GEN(dev_priv) < 12 && port == PORT_A)
+		return false;
+
+	return true;
+}
+
 int
 intel_dp_compute_config(struct intel_encoder *encoder,
 			struct intel_crtc_state *pipe_config,
 			struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_lspcon *lspcon = enc_to_intel_lspcon(&encoder->base);
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_lspcon *lspcon = enc_to_intel_lspcon(encoder);
 	enum port port = encoder->port;
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
@@ -2341,7 +2392,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		return ret;
 
 	pipe_config->has_drrs = false;
-	if (IS_G4X(dev_priv) || port == PORT_A)
+	if (!intel_dp_port_has_audio(dev_priv, port))
 		pipe_config->has_audio = false;
 	else if (intel_conn_state->force_audio == HDMI_AUDIO_AUTO)
 		pipe_config->has_audio = intel_dp->has_audio;
@@ -2431,10 +2482,10 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 
 	intel_dp_set_link_params(intel_dp, pipe_config->port_clock,
 				 pipe_config->lane_count,
@@ -2458,7 +2509,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 	 *
 	 * CPT PCH is quite different, having many bits moved
 	 * to the TRANS_DP_CTL register instead. That
-	 * configuration happens (oddly) in ironlake_pch_enable
+	 * configuration happens (oddly) in ilk_pch_enable
 	 */
 
 	/* Preserve the BIOS-computed detected bit. This is
@@ -2602,7 +2653,7 @@ static void edp_wait_backlight_off(struct intel_dp *intel_dp)
  * is locked
  */
 
-static  u32 ironlake_get_pp_control(struct intel_dp *intel_dp)
+static  u32 ilk_get_pp_control(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	u32 control;
@@ -2652,7 +2703,7 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 	if (!edp_have_panel_power(intel_dp))
 		wait_panel_power_cycle(intel_dp);
 
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	pp |= EDP_FORCE_VDD;
 
 	pp_stat_reg = _pp_stat_reg(intel_dp);
@@ -2717,7 +2768,7 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 		      intel_dig_port->base.base.base.id,
 		      intel_dig_port->base.base.name);
 
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	pp &= ~EDP_FORCE_VDD;
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
@@ -2813,7 +2864,7 @@ static void edp_panel_on(struct intel_dp *intel_dp)
 	wait_panel_power_cycle(intel_dp);
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	if (IS_GEN(dev_priv, 5)) {
 		/* ILK workaround: disable reset around power sequence */
 		pp &= ~PANEL_POWER_RESET;
@@ -2868,7 +2919,7 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	WARN(!intel_dp->want_panel_vdd, "Need [ENCODER:%d:%s] VDD to turn off panel\n",
 	     dig_port->base.base.base.id, dig_port->base.base.name);
 
-	pp = ironlake_get_pp_control(intel_dp);
+	pp = ilk_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
 	 * panels get very unhappy and cease to work. */
 	pp &= ~(PANEL_POWER_ON | PANEL_POWER_RESET | EDP_FORCE_VDD |
@@ -2917,7 +2968,7 @@ static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 		i915_reg_t pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 		u32 pp;
 
-		pp = ironlake_get_pp_control(intel_dp);
+		pp = ilk_get_pp_control(intel_dp);
 		pp |= EDP_BLC_ENABLE;
 
 		I915_WRITE(pp_ctrl_reg, pp);
@@ -2929,7 +2980,7 @@ static void _intel_edp_backlight_on(struct intel_dp *intel_dp)
 void intel_edp_backlight_on(const struct intel_crtc_state *crtc_state,
 			    const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(conn_state->best_encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(conn_state->best_encoder));
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
@@ -2953,7 +3004,7 @@ static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 		i915_reg_t pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 		u32 pp;
 
-		pp = ironlake_get_pp_control(intel_dp);
+		pp = ilk_get_pp_control(intel_dp);
 		pp &= ~EDP_BLC_ENABLE;
 
 		I915_WRITE(pp_ctrl_reg, pp);
@@ -2967,7 +3018,7 @@ static void _intel_edp_backlight_off(struct intel_dp *intel_dp)
 /* Disable backlight PP control and backlight PWM. */
 void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(old_conn_state->best_encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder));
 
 	if (!intel_dp_is_edp(intel_dp))
 		return;
@@ -2985,13 +3036,13 @@ void intel_edp_backlight_off(const struct drm_connector_state *old_conn_state)
 static void intel_edp_backlight_power(struct intel_connector *connector,
 				      bool enable)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(&connector->base);
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	intel_wakeref_t wakeref;
 	bool is_enabled;
 
 	is_enabled = false;
 	with_pps_lock(intel_dp, wakeref)
-		is_enabled = ironlake_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
+		is_enabled = ilk_get_pp_control(intel_dp) & EDP_BLC_ENABLE;
 	if (is_enabled == enable)
 		return;
 
@@ -3028,13 +3079,13 @@ static void assert_edp_pll(struct drm_i915_private *dev_priv, bool state)
 #define assert_edp_pll_enabled(d) assert_edp_pll((d), true)
 #define assert_edp_pll_disabled(d) assert_edp_pll((d), false)
 
-static void ironlake_edp_pll_on(struct intel_dp *intel_dp,
-				const struct intel_crtc_state *pipe_config)
+static void ilk_edp_pll_on(struct intel_dp *intel_dp,
+			   const struct intel_crtc_state *pipe_config)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 	assert_dp_port_disabled(intel_dp);
 	assert_edp_pll_disabled(dev_priv);
 
@@ -3068,13 +3119,13 @@ static void ironlake_edp_pll_on(struct intel_dp *intel_dp,
 	udelay(200);
 }
 
-static void ironlake_edp_pll_off(struct intel_dp *intel_dp,
-				 const struct intel_crtc_state *old_crtc_state)
+static void ilk_edp_pll_off(struct intel_dp *intel_dp,
+			    const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	assert_pipe_disabled(dev_priv, crtc->pipe);
+	assert_pipe_disabled(dev_priv, old_crtc_state->cpu_transcoder);
 	assert_dp_port_disabled(intel_dp);
 	assert_edp_pll_enabled(dev_priv);
 
@@ -3207,7 +3258,7 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 				  enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	intel_wakeref_t wakeref;
 	bool ret;
 
@@ -3228,10 +3279,10 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 				struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	u32 tmp, flags = 0;
 	enum port port = encoder->port;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 
 	if (encoder->type == INTEL_OUTPUT_EDP)
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_EDP);
@@ -3266,7 +3317,7 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 			flags |= DRM_MODE_FLAG_NVSYNC;
 	}
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	if (IS_G4X(dev_priv) && tmp & DP_COLOR_RANGE_16_235)
 		pipe_config->limited_color_range = true;
@@ -3283,7 +3334,7 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 			pipe_config->port_clock = 270000;
 	}
 
-	pipe_config->base.adjusted_mode.crtc_clock =
+	pipe_config->hw.adjusted_mode.crtc_clock =
 		intel_dotclock_calculate(pipe_config->port_clock,
 					 &pipe_config->dp_m_n);
 
@@ -3312,7 +3363,7 @@ static void intel_disable_dp(struct intel_encoder *encoder,
 			     const struct intel_crtc_state *old_crtc_state,
 			     const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	intel_dp->link_trained = false;
 
@@ -3346,7 +3397,7 @@ static void g4x_post_disable_dp(struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 
 	/*
@@ -3359,7 +3410,7 @@ static void g4x_post_disable_dp(struct intel_encoder *encoder,
 
 	/* Only ilk+ has port A */
 	if (port == PORT_A)
-		ironlake_edp_pll_off(intel_dp, old_crtc_state);
+		ilk_edp_pll_off(intel_dp, old_crtc_state);
 }
 
 static void vlv_post_disable_dp(struct intel_encoder *encoder,
@@ -3497,8 +3548,8 @@ static void intel_enable_dp(struct intel_encoder *encoder,
 			    const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	u32 dp_reg = I915_READ(intel_dp->output_reg);
 	enum pipe pipe = crtc->pipe;
 	intel_wakeref_t wakeref;
@@ -3557,14 +3608,14 @@ static void g4x_pre_enable_dp(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config,
 			      const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	enum port port = encoder->port;
 
 	intel_dp_prepare(encoder, pipe_config);
 
 	/* Only ilk+ has port A */
 	if (port == PORT_A)
-		ironlake_edp_pll_on(intel_dp, pipe_config);
+		ilk_edp_pll_on(intel_dp, pipe_config);
 }
 
 static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
@@ -3607,7 +3658,7 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv,
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
 	for_each_intel_dp(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 		WARN(intel_dp->active_pipe == pipe,
 		     "stealing pipe %c power sequencer from active [ENCODER:%d:%s]\n",
@@ -3630,8 +3681,8 @@ static void vlv_init_panel_power_sequencer(struct intel_encoder *encoder,
 					   const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
@@ -4152,8 +4203,8 @@ intel_dp_link_down(struct intel_encoder *encoder,
 		   const struct intel_crtc_state *old_crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum port port = encoder->port;
 	u32 DP = intel_dp->DP;
 
@@ -4852,7 +4903,7 @@ static u8 intel_dp_autotest_video_pattern(struct intel_dp *intel_dp)
 	intel_dp->compliance.test_data.hdisplay = be16_to_cpu(h_width);
 	intel_dp->compliance.test_data.vdisplay = be16_to_cpu(v_height);
 	/* Set test active flag here so userspace doesn't interrupt things */
-	intel_dp->compliance.test_active = 1;
+	intel_dp->compliance.test_active = true;
 
 	return DP_TEST_ACK;
 }
@@ -4896,7 +4947,7 @@ static u8 intel_dp_autotest_edid(struct intel_dp *intel_dp)
 	}
 
 	/* Set test active flag here so userspace doesn't interrupt things */
-	intel_dp->compliance.test_active = 1;
+	intel_dp->compliance.test_active = true;
 
 	return test_result;
 }
@@ -5045,7 +5096,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 			  struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_connector *connector = intel_dp->attached_connector;
 	struct drm_connector_state *conn_state;
 	struct intel_crtc_state *crtc_state;
@@ -5076,7 +5127,7 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
 
 	WARN_ON(!intel_crtc_has_dp_encoder(crtc_state));
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 
 	if (conn_state->commit &&
@@ -5482,10 +5533,10 @@ static bool intel_combo_phy_connected(struct drm_i915_private *dev_priv,
 	return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(phy);
 }
 
-static bool icl_digital_port_connected(struct intel_encoder *encoder)
+static bool icp_digital_port_connected(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
 
 	if (intel_phy_is_combo(dev_priv, phy))
@@ -5520,9 +5571,9 @@ static bool __intel_digital_port_connected(struct intel_encoder *encoder)
 			return g4x_digital_port_connected(encoder);
 	}
 
-	if (INTEL_GEN(dev_priv) >= 11)
-		return icl_digital_port_connected(encoder);
-	else if (IS_GEN(dev_priv, 10) || IS_GEN9_BC(dev_priv))
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
+		return icp_digital_port_connected(encoder);
+	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_SPT)
 		return spt_digital_port_connected(encoder);
 	else if (IS_GEN9_LP(dev_priv))
 		return bxt_digital_port_connected(encoder);
@@ -5600,7 +5651,7 @@ intel_dp_detect(struct drm_connector *connector,
 		bool force)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *encoder = &dig_port->base;
 	enum drm_connector_status status;
@@ -5704,7 +5755,7 @@ out:
 static void
 intel_dp_force(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct intel_encoder *intel_encoder = &dig_port->base;
 	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
@@ -5739,7 +5790,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 	}
 
 	/* if eDP has no EDID, fall back to fixed mode */
-	if (intel_dp_is_edp(intel_attached_dp(connector)) &&
+	if (intel_dp_is_edp(intel_attached_dp(to_intel_connector(connector))) &&
 	    intel_connector->panel.fixed_mode) {
 		struct drm_display_mode *mode;
 
@@ -5757,7 +5808,7 @@ static int intel_dp_get_modes(struct drm_connector *connector)
 static int
 intel_dp_connector_register(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -5779,7 +5830,7 @@ intel_dp_connector_register(struct drm_connector *connector)
 static void
 intel_dp_connector_unregister(struct drm_connector *connector)
 {
-	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct intel_dp *intel_dp = intel_attached_dp(to_intel_connector(connector));
 
 	drm_dp_cec_unregister_connector(&intel_dp->aux);
 	drm_dp_aux_unregister(&intel_dp->aux);
@@ -5788,7 +5839,7 @@ intel_dp_connector_unregister(struct drm_connector *connector)
 
 void intel_dp_encoder_flush_work(struct drm_encoder *encoder)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(to_intel_encoder(encoder));
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
 	intel_dp_mst_encoder_cleanup(intel_dig_port);
@@ -5817,12 +5868,12 @@ static void intel_dp_encoder_destroy(struct drm_encoder *encoder)
 	intel_dp_encoder_flush_work(encoder);
 
 	drm_encoder_cleanup(encoder);
-	kfree(enc_to_dig_port(encoder));
+	kfree(enc_to_dig_port(to_intel_encoder(encoder)));
 }
 
 void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(intel_encoder);
 	intel_wakeref_t wakeref;
 
 	if (!intel_dp_is_edp(intel_dp))
@@ -5853,7 +5904,7 @@ static
 int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port,
 				u8 *an)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_dig_port->base.base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(&intel_dig_port->base.base));
 	static const struct drm_dp_aux_msg msg = {
 		.request = DP_AUX_NATIVE_WRITE,
 		.address = DP_AUX_HDCP_AKSV,
@@ -6463,7 +6514,7 @@ static enum pipe vlv_active_pipe(struct intel_dp *intel_dp)
 void intel_dp_encoder_reset(struct drm_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_dp *intel_dp = enc_to_intel_dp(to_intel_encoder(encoder));
 	struct intel_lspcon *lspcon = dp_to_lspcon(intel_dp);
 	intel_wakeref_t wakeref;
 
@@ -6642,7 +6693,7 @@ intel_pps_readout_hw_state(struct intel_dp *intel_dp, struct edp_power_seq *seq)
 
 	intel_pps_get_registers(intel_dp, &regs);
 
-	pp_ctl = ironlake_get_pp_control(intel_dp);
+	pp_ctl = ilk_get_pp_control(intel_dp);
 
 	/* Ensure PPS is unlocked */
 	if (!HAS_DDI(dev_priv))
@@ -6812,7 +6863,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	 * soon as the new power sequencer gets initialized.
 	 */
 	if (force_disable_vdd) {
-		u32 pp = ironlake_get_pp_control(intel_dp);
+		u32 pp = ilk_get_pp_control(intel_dp);
 
 		WARN(pp & PANEL_POWER_ON, "Panel power already on\n");
 
@@ -6909,7 +6960,7 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv,
 				    int refresh_rate)
 {
 	struct intel_dp *intel_dp = dev_priv->drrs.dp;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum drrs_refresh_rate_type index = DRRS_HIGH_RR;
 
 	if (refresh_rate <= 0) {
@@ -6942,7 +6993,7 @@ static void intel_dp_set_drrs_state(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	if (!crtc_state->base.active) {
+	if (!crtc_state->hw.active) {
 		DRM_DEBUG_KMS("eDP encoder disabled. CRTC not Active\n");
 		return;
 	}
@@ -7609,7 +7660,7 @@ void intel_dp_mst_suspend(struct drm_i915_private *dev_priv)
 		if (encoder->type != INTEL_OUTPUT_DDI)
 			continue;
 
-		intel_dp = enc_to_intel_dp(&encoder->base);
+		intel_dp = enc_to_intel_dp(encoder);
 
 		if (!intel_dp->can_mst)
 			continue;
@@ -7630,7 +7681,7 @@ void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 		if (encoder->type != INTEL_OUTPUT_DDI)
 			continue;
 
-		intel_dp = enc_to_intel_dp(&encoder->base);
+		intel_dp = enc_to_intel_dp(encoder);
 
 		if (!intel_dp->can_mst)
 			continue;
diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
index 020422da2ae2..7c653f8c307f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c
@@ -57,7 +57,7 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
  */
 static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	u8 read_val[2] = { 0x0 };
 	u16 level = 0;
 
@@ -82,7 +82,7 @@ static void
 intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	u8 vals[2] = { 0x0 };
 
 	vals[0] = level;
@@ -110,7 +110,7 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev
 static bool intel_dp_aux_set_pwm_freq(struct intel_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	int freq, fxp, fxp_min, fxp_max, fxp_actual, f = 1;
 	u8 pn, pn_min, pn_max;
 
@@ -178,7 +178,7 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 					  const struct drm_connector_state *conn_state)
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
@@ -222,13 +222,14 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 
 static void intel_dp_aux_disable_backlight(const struct drm_connector_state *old_conn_state)
 {
-	set_aux_backlight_enable(enc_to_intel_dp(old_conn_state->best_encoder), false);
+	set_aux_backlight_enable(enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder)),
+				 false);
 }
 
 static int intel_dp_aux_setup_backlight(struct intel_connector *connector,
 					enum pipe pipe)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 	struct intel_panel *panel = &connector->panel;
 
 	if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT)
@@ -247,7 +248,7 @@ static int intel_dp_aux_setup_backlight(struct intel_connector *connector,
 static bool
 intel_dp_aux_display_control_capable(struct intel_connector *connector)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder);
 
 	/* Check the eDP Display control capabilities registers to determine if
 	 * the panel can support backlight control over the aux channel
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 03d1cba0b696..cba68c5a80fa 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -42,13 +42,13 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 					    struct drm_connector_state *conn_state,
 					    struct link_config_limits *limits)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_dp *intel_dp = &intel_mst->primary->dp;
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	void *port = connector->port;
 	bool constant_n = drm_dp_has_quirk(&intel_dp->desc,
 					   DP_DPCD_QUIRK_CONSTANT_N);
@@ -61,10 +61,11 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 		crtc_state->pipe_bpp = bpp;
 
 		crtc_state->pbn = drm_dp_calc_pbn_mode(adjusted_mode->crtc_clock,
-						       crtc_state->pipe_bpp);
+						       crtc_state->pipe_bpp,
+						       false);
 
 		slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr,
-						      port, crtc_state->pbn);
+						      port, crtc_state->pbn, 0);
 		if (slots == -EDEADLK)
 			return slots;
 		if (slots >= 0)
@@ -87,19 +88,65 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 	return 0;
 }
 
+/*
+ * Iterate over all connectors and return the smallest transcoder in the MST
+ * stream
+ */
+static enum transcoder
+intel_dp_mst_master_trans_compute(struct intel_atomic_state *state,
+				  struct intel_dp *mst_port)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_digital_connector_state *conn_state;
+	struct intel_connector *connector;
+	enum pipe ret = I915_MAX_PIPES;
+	int i;
+
+	if (INTEL_GEN(dev_priv) < 12)
+		return INVALID_TRANSCODER;
+
+	for_each_new_intel_connector_in_state(state, connector, conn_state, i) {
+		struct intel_crtc_state *crtc_state;
+		struct intel_crtc *crtc;
+
+		if (connector->mst_port != mst_port || !conn_state->base.crtc)
+			continue;
+
+		crtc = to_intel_crtc(conn_state->base.crtc);
+		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+		if (!crtc_state->uapi.active)
+			continue;
+
+		/*
+		 * Using crtc->pipe because crtc_state->cpu_transcoder is
+		 * computed, so others CRTCs could have non-computed
+		 * cpu_transcoder
+		 */
+		if (crtc->pipe < ret)
+			ret = crtc->pipe;
+	}
+
+	if (ret == I915_MAX_PIPES)
+		return INVALID_TRANSCODER;
+
+	/* Simple cast works because TGL don't have a eDP transcoder */
+	return (enum transcoder)ret;
+}
+
 static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 				       struct intel_crtc_state *pipe_config,
 				       struct drm_connector_state *conn_state)
 {
+	struct intel_atomic_state *state = to_intel_atomic_state(conn_state->state);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_dp *intel_dp = &intel_mst->primary->dp;
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 	void *port = connector->port;
 	struct link_config_limits limits;
 	int ret;
@@ -154,25 +201,91 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 
 	intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
 
+	pipe_config->mst_master_transcoder = intel_dp_mst_master_trans_compute(state, intel_dp);
+
+	return 0;
+}
+
+/*
+ * If one of the connectors in a MST stream needs a modeset, mark all CRTCs
+ * that shares the same MST stream as mode changed,
+ * intel_modeset_pipe_config()+intel_crtc_check_fastset() will take care to do
+ * a fastset when possible.
+ */
+static int
+intel_dp_mst_atomic_master_trans_check(struct intel_connector *connector,
+				       struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct drm_connector_list_iter connector_list_iter;
+	struct intel_connector *connector_iter;
+
+	if (INTEL_GEN(dev_priv) < 12)
+		return  0;
+
+	if (!intel_connector_needs_modeset(state, &connector->base))
+		return 0;
+
+	drm_connector_list_iter_begin(&dev_priv->drm, &connector_list_iter);
+	for_each_intel_connector_iter(connector_iter, &connector_list_iter) {
+		struct intel_digital_connector_state *conn_iter_state;
+		struct intel_crtc_state *crtc_state;
+		struct intel_crtc *crtc;
+		int ret;
+
+		if (connector_iter->mst_port != connector->mst_port ||
+		    connector_iter == connector)
+			continue;
+
+		conn_iter_state = intel_atomic_get_digital_connector_state(state,
+									   connector_iter);
+		if (IS_ERR(conn_iter_state)) {
+			drm_connector_list_iter_end(&connector_list_iter);
+			return PTR_ERR(conn_iter_state);
+		}
+
+		if (!conn_iter_state->base.crtc)
+			continue;
+
+		crtc = to_intel_crtc(conn_iter_state->base.crtc);
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state)) {
+			drm_connector_list_iter_end(&connector_list_iter);
+			return PTR_ERR(crtc_state);
+		}
+
+		ret = drm_atomic_add_affected_planes(&state->base, &crtc->base);
+		if (ret) {
+			drm_connector_list_iter_end(&connector_list_iter);
+			return ret;
+		}
+		crtc_state->uapi.mode_changed = true;
+	}
+	drm_connector_list_iter_end(&connector_list_iter);
+
 	return 0;
 }
 
 static int
 intel_dp_mst_atomic_check(struct drm_connector *connector,
-			  struct drm_atomic_state *state)
+			  struct drm_atomic_state *_state)
 {
+	struct intel_atomic_state *state = to_intel_atomic_state(_state);
 	struct drm_connector_state *new_conn_state =
-		drm_atomic_get_new_connector_state(state, connector);
+		drm_atomic_get_new_connector_state(&state->base, connector);
 	struct drm_connector_state *old_conn_state =
-		drm_atomic_get_old_connector_state(state, connector);
+		drm_atomic_get_old_connector_state(&state->base, connector);
 	struct intel_connector *intel_connector =
 		to_intel_connector(connector);
 	struct drm_crtc *new_crtc = new_conn_state->crtc;
-	struct drm_crtc_state *crtc_state;
 	struct drm_dp_mst_topology_mgr *mgr;
 	int ret;
 
-	ret = intel_digital_connector_atomic_check(connector, state);
+	ret = intel_digital_connector_atomic_check(connector, &state->base);
+	if (ret)
+		return ret;
+
+	ret = intel_dp_mst_atomic_master_trans_check(intel_connector, state);
 	if (ret)
 		return ret;
 
@@ -183,16 +296,18 @@ intel_dp_mst_atomic_check(struct drm_connector *connector,
 	 * connector
 	 */
 	if (new_crtc) {
-		crtc_state = drm_atomic_get_new_crtc_state(state, new_crtc);
+		struct intel_crtc *intel_crtc = to_intel_crtc(new_crtc);
+		struct intel_crtc_state *crtc_state =
+			intel_atomic_get_new_crtc_state(state, intel_crtc);
 
 		if (!crtc_state ||
-		    !drm_atomic_crtc_needs_modeset(crtc_state) ||
-		    crtc_state->enable)
+		    !drm_atomic_crtc_needs_modeset(&crtc_state->uapi) ||
+		    crtc_state->uapi.enable)
 			return 0;
 	}
 
-	mgr = &enc_to_mst(old_conn_state->best_encoder)->primary->dp.mst_mgr;
-	ret = drm_dp_atomic_release_vcpi_slots(state, mgr,
+	mgr = &enc_to_mst(to_intel_encoder(old_conn_state->best_encoder))->primary->dp.mst_mgr;
+	ret = drm_dp_atomic_release_vcpi_slots(&state->base, mgr,
 					       intel_connector->port);
 
 	return ret;
@@ -202,7 +317,7 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *old_crtc_state,
 				 const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_connector *connector =
@@ -226,36 +341,65 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder,
 				      const struct intel_crtc_state *old_crtc_state,
 				      const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct intel_connector *connector =
 		to_intel_connector(old_conn_state->connector);
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	bool last_mst_stream;
+	u32 val;
+
+	intel_dp->active_mst_links--;
+	last_mst_stream = intel_dp->active_mst_links == 0;
+	WARN_ON(INTEL_GEN(dev_priv) >= 12 && last_mst_stream &&
+		!intel_dp_mst_is_master_trans(old_crtc_state));
 
-	intel_ddi_disable_pipe_clock(old_crtc_state);
+	intel_crtc_vblank_off(old_crtc_state);
+
+	intel_disable_pipe(old_crtc_state);
 
-	/* this can fail */
-	drm_dp_check_act_status(&intel_dp->mst_mgr);
-	/* and this can also fail */
 	drm_dp_update_payload_part2(&intel_dp->mst_mgr);
 
+	val = I915_READ(TRANS_DDI_FUNC_CTL(old_crtc_state->cpu_transcoder));
+	val &= ~TRANS_DDI_DP_VC_PAYLOAD_ALLOC;
+	I915_WRITE(TRANS_DDI_FUNC_CTL(old_crtc_state->cpu_transcoder), val);
+
+	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
+				  DP_TP_STATUS_ACT_SENT, 1))
+		DRM_ERROR("Timed out waiting for ACT sent when disabling\n");
+	drm_dp_check_act_status(&intel_dp->mst_mgr);
+
 	drm_dp_mst_deallocate_vcpi(&intel_dp->mst_mgr, connector->port);
 
+	intel_ddi_disable_transcoder_func(old_crtc_state);
+
+	if (INTEL_GEN(dev_priv) >= 9)
+		skl_scaler_disable(old_crtc_state);
+	else
+		ilk_pfit_disable(old_crtc_state);
+
 	/*
 	 * Power down mst path before disabling the port, otherwise we end
 	 * up getting interrupts from the sink upon detecting link loss.
 	 */
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port,
 				     false);
+	/*
+	 * From TGL spec: "If multi-stream slave transcoder: Configure
+	 * Transcoder Clock Select to direct no clock to the transcoder"
+	 *
+	 * From older GENs spec: "Configure Transcoder Clock Select to direct
+	 * no clock to the transcoder"
+	 */
+	if (INTEL_GEN(dev_priv) < 12 || !last_mst_stream)
+		intel_ddi_disable_pipe_clock(old_crtc_state);
 
-	intel_dp->active_mst_links--;
 
 	intel_mst->connector = NULL;
-	if (intel_dp->active_mst_links == 0) {
-		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+	if (last_mst_stream)
 		intel_dig_port->base.post_disable(&intel_dig_port->base,
 						  old_crtc_state, NULL);
-	}
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 }
@@ -264,7 +408,7 @@ static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder,
 					const struct intel_crtc_state *pipe_config,
 					const struct drm_connector_state *conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 
@@ -273,25 +417,11 @@ static void intel_mst_pre_pll_enable_dp(struct intel_encoder *encoder,
 						    pipe_config, NULL);
 }
 
-static void intel_mst_post_pll_disable_dp(struct intel_encoder *encoder,
-					  const struct intel_crtc_state *old_crtc_state,
-					  const struct drm_connector_state *old_conn_state)
-{
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
-	struct intel_digital_port *intel_dig_port = intel_mst->primary;
-	struct intel_dp *intel_dp = &intel_dig_port->dp;
-
-	if (intel_dp->active_mst_links == 0)
-		intel_dig_port->base.post_pll_disable(&intel_dig_port->base,
-						      old_crtc_state,
-						      old_conn_state);
-}
-
 static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -299,21 +429,25 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 		to_intel_connector(conn_state->connector);
 	int ret;
 	u32 temp;
+	bool first_mst_stream;
 
 	/* MST encoders are bound to a crtc, not to a connector,
 	 * force the mapping here for get_hw_state.
 	 */
 	connector->encoder = encoder;
 	intel_mst->connector = connector;
+	first_mst_stream = intel_dp->active_mst_links == 0;
+	WARN_ON(INTEL_GEN(dev_priv) >= 12 && first_mst_stream &&
+		!intel_dp_mst_is_master_trans(pipe_config));
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 
-	if (intel_dp->active_mst_links == 0)
+	if (first_mst_stream)
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
 
 	drm_dp_send_power_updown_phy(&intel_dp->mst_mgr, connector->port, true);
 
-	if (intel_dp->active_mst_links == 0)
+	if (first_mst_stream)
 		intel_dig_port->base.pre_enable(&intel_dig_port->base,
 						pipe_config, NULL);
 
@@ -330,7 +464,15 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 
 	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr);
 
-	intel_ddi_enable_pipe_clock(pipe_config);
+	/*
+	 * Before Gen 12 this is not done as part of
+	 * intel_dig_port->base.pre_enable() and should be done here. For
+	 * Gen 12+ the step in which this should be done is different for the
+	 * first MST stream, so it's done on the DDI for the first stream and
+	 * here for the following ones.
+	 */
+	if (INTEL_GEN(dev_priv) < 12 || !first_mst_stream)
+		intel_ddi_enable_pipe_clock(pipe_config);
 
 	intel_ddi_set_dp_msa(pipe_config, conn_state);
 }
@@ -339,7 +481,7 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -360,7 +502,7 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder,
 static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder,
 				      enum pipe *pipe)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	*pipe = intel_mst->pipe;
 	if (intel_mst->connector)
 		return true;
@@ -370,7 +512,7 @@ static bool intel_dp_mst_enc_get_hw_state(struct intel_encoder *encoder,
 static void intel_dp_mst_enc_get_config(struct intel_encoder *encoder,
 					struct intel_crtc_state *pipe_config)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(&encoder->base);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 
 	intel_ddi_get_config(&intel_dig_port->base, pipe_config);
@@ -478,7 +620,7 @@ static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_fun
 
 static void intel_dp_mst_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(encoder);
+	struct intel_dp_mst_encoder *intel_mst = enc_to_mst(to_intel_encoder(encoder));
 
 	drm_encoder_cleanup(encoder);
 	kfree(intel_mst);
@@ -633,7 +775,6 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->disable = intel_mst_disable_dp;
 	intel_encoder->post_disable = intel_mst_post_disable_dp;
 	intel_encoder->pre_pll_enable = intel_mst_pre_pll_enable_dp;
-	intel_encoder->post_pll_disable = intel_mst_post_pll_disable_dp;
 	intel_encoder->pre_enable = intel_mst_pre_enable_dp;
 	intel_encoder->enable = intel_mst_enable_dp;
 	intel_encoder->get_hw_state = intel_dp_mst_enc_get_hw_state;
@@ -703,3 +844,14 @@ intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port)
 	drm_dp_mst_topology_mgr_destroy(&intel_dp->mst_mgr);
 	/* encoders will get killed by normal cleanup */
 }
+
+bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->mst_master_transcoder == crtc_state->cpu_transcoder;
+}
+
+bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state)
+{
+	return crtc_state->mst_master_transcoder != INVALID_TRANSCODER &&
+	       crtc_state->mst_master_transcoder != crtc_state->cpu_transcoder;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.h b/drivers/gpu/drm/i915/display/intel_dp_mst.h
index f660ad80db04..854724f68f09 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.h
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.h
@@ -6,10 +6,15 @@
 #ifndef __INTEL_DP_MST_H__
 #define __INTEL_DP_MST_H__
 
+#include <linux/types.h>
+
 struct intel_digital_port;
+struct intel_crtc_state;
 
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
 int intel_dp_mst_encoder_active_links(struct intel_digital_port *intel_dig_port);
+bool intel_dp_mst_is_master_trans(const struct intel_crtc_state *crtc_state);
+bool intel_dp_mst_is_slave_trans(const struct intel_crtc_state *crtc_state);
 
 #endif /* __INTEL_DP_MST_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.c b/drivers/gpu/drm/i915/display/intel_dpio_phy.c
index 556d1b30f06a..6fb1f7a7364e 100644
--- a/drivers/gpu/drm/i915/display/intel_dpio_phy.c
+++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.c
@@ -642,7 +642,7 @@ void chv_set_phy_signal_level(struct intel_encoder *encoder,
 			      bool uniq_trans_scale)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
 	enum pipe pipe = intel_crtc->pipe;
@@ -738,8 +738,8 @@ void chv_data_lane_soft_reset(struct intel_encoder *encoder,
 			      bool reset)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(&encoder->base));
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(enc_to_dig_port(encoder));
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
 
@@ -781,9 +781,9 @@ void chv_data_lane_soft_reset(struct intel_encoder *encoder,
 void chv_phy_pre_pll_enable(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 	unsigned int lane_mask =
@@ -861,10 +861,10 @@ void chv_phy_pre_pll_enable(struct intel_encoder *encoder,
 void chv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *crtc_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel ch = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 	int data, i, stagger;
@@ -940,7 +940,7 @@ void chv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 
 void chv_phy_release_cl2_override(struct intel_encoder *encoder)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	if (dport->release_cl2_override) {
@@ -953,7 +953,7 @@ void chv_phy_post_pll_disable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(old_crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(old_crtc_state->uapi.crtc)->pipe;
 	u32 val;
 
 	vlv_dpio_get(dev_priv);
@@ -989,7 +989,7 @@ void vlv_set_phy_signal_level(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(encoder->base.crtc);
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = intel_crtc->pipe;
 
@@ -1014,9 +1014,9 @@ void vlv_set_phy_signal_level(struct intel_encoder *encoder,
 void vlv_phy_pre_pll_enable(struct intel_encoder *encoder,
 			    const struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 
@@ -1043,10 +1043,10 @@ void vlv_phy_pre_pll_enable(struct intel_encoder *encoder,
 void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *crtc_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *dport = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 	u32 val;
@@ -1073,9 +1073,9 @@ void vlv_phy_pre_encoder_enable(struct intel_encoder *encoder,
 void vlv_phy_reset_lanes(struct intel_encoder *encoder,
 			 const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	enum dpio_channel port = vlv_dport_to_channel(dport);
 	enum pipe pipe = crtc->pipe;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 3ce0a023eee0..c75e34d87111 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -136,7 +136,7 @@ void assert_shared_dpll(struct drm_i915_private *dev_priv,
  */
 void intel_prepare_shared_dpll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 
@@ -163,7 +163,7 @@ void intel_prepare_shared_dpll(const struct intel_crtc_state *crtc_state)
  */
 void intel_enable_shared_dpll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
@@ -208,7 +208,7 @@ out:
  */
 void intel_disable_shared_dpll(const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc_state->shared_dpll;
 	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
@@ -842,7 +842,7 @@ hsw_ddi_hdmi_get_dpll(struct intel_atomic_state *state,
 static struct intel_shared_dpll *
 hsw_ddi_dp_get_dpll(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	struct intel_shared_dpll *pll;
 	enum intel_dpll_id pll_id;
 	int clock = crtc_state->port_clock;
@@ -1751,7 +1751,7 @@ static bool
 bxt_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state,
 			  struct bxt_clk_div *clk_div)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct dpll best_clock;
 
 	/* Calculate HDMI div */
@@ -2274,7 +2274,7 @@ static bool
 cnl_ddi_calculate_wrpll(struct intel_crtc_state *crtc_state,
 			struct skl_wrpll_params *wrpll_params)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 afe_clock = crtc_state->port_clock * 5;
 	u32 ref_clock;
 	u32 dco_min = 7998000;
@@ -2553,7 +2553,7 @@ static const struct skl_wrpll_params tgl_tbt_pll_24MHz_values = {
 static bool icl_calc_dp_combo_pll(struct intel_crtc_state *crtc_state,
 				  struct skl_wrpll_params *pll_params)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	const struct icl_combo_pll_params *params =
 		dev_priv->cdclk.hw.ref == 24000 ?
 		icl_dp_combo_pll_24MHz_values :
@@ -2575,7 +2575,7 @@ static bool icl_calc_dp_combo_pll(struct intel_crtc_state *crtc_state,
 static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state,
 			     struct skl_wrpll_params *pll_params)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (INTEL_GEN(dev_priv) >= 12) {
 		switch (dev_priv->cdclk.hw.ref) {
@@ -2612,7 +2612,7 @@ static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state,
 				struct intel_encoder *encoder,
 				struct intel_dpll_hw_state *pll_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 cfgcr0, cfgcr1;
 	struct skl_wrpll_params pll_params = { 0 };
 	bool ret;
@@ -2744,7 +2744,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 				  struct intel_dpll_hw_state *pll_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int refclk_khz = dev_priv->cdclk.hw.ref;
 	int clock = crtc_state->port_clock;
 	u32 dco_khz, m1div, m2div_int, m2div_rem, m2div_frac;
@@ -2972,8 +2972,8 @@ static void icl_update_active_dpll(struct intel_atomic_state *state,
 	enum icl_port_dpll_id port_dpll_id = ICL_PORT_DPLL_DEFAULT;
 
 	primary_port = encoder->type == INTEL_OUTPUT_DP_MST ?
-		enc_to_mst(&encoder->base)->primary :
-		enc_to_dig_port(&encoder->base);
+		enc_to_mst(encoder)->primary :
+		enc_to_dig_port(encoder);
 
 	if (primary_port &&
 	    (primary_port->tc_mode == TC_PORT_DP_ALT ||
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index bb5a0e91b370..ada006a690df 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -102,43 +102,50 @@ intel_dsb_get(struct intel_crtc *crtc)
 	struct intel_dsb *dsb = &crtc->dsb;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
+	u32 *buf;
 	intel_wakeref_t wakeref;
 
 	if (!HAS_DSB(i915))
 		return dsb;
 
-	if (atomic_add_return(1, &dsb->refcount) != 1)
+	if (dsb->refcount++ != 0)
 		return dsb;
 
-	dsb->id = DSB1;
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	obj = i915_gem_object_create_internal(i915, DSB_BUF_SIZE);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("Gem object creation failed\n");
-		goto err;
+		goto out;
 	}
 
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
 	if (IS_ERR(vma)) {
 		DRM_ERROR("Vma creation failed\n");
 		i915_gem_object_put(obj);
-		atomic_dec(&dsb->refcount);
-		goto err;
+		goto out;
 	}
 
-	dsb->cmd_buf = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
-	if (IS_ERR(dsb->cmd_buf)) {
+	buf = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
+	if (IS_ERR(buf)) {
 		DRM_ERROR("Command buffer creation failed\n");
-		i915_vma_unpin_and_release(&vma, 0);
-		dsb->cmd_buf = NULL;
-		atomic_dec(&dsb->refcount);
-		goto err;
+		goto out;
 	}
+
+	dsb->id = DSB1;
 	dsb->vma = vma;
+	dsb->cmd_buf = buf;
+
+out:
+	/*
+	 * On error dsb->cmd_buf will continue to be NULL, making the writes
+	 * pass-through. Leave the dangling ref to be removed later by the
+	 * corresponding intel_dsb_put(): the important error message will
+	 * already be logged above.
+	 */
 
-err:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+
 	return dsb;
 }
 
@@ -158,10 +165,10 @@ void intel_dsb_put(struct intel_dsb *dsb)
 	if (!HAS_DSB(i915))
 		return;
 
-	if (WARN_ON(atomic_read(&dsb->refcount) == 0))
+	if (WARN_ON(dsb->refcount == 0))
 		return;
 
-	if (atomic_dec_and_test(&dsb->refcount)) {
+	if (--dsb->refcount == 0) {
 		i915_vma_unpin_and_release(&dsb->vma, I915_VMA_RELEASE_MAP);
 		dsb->cmd_buf = NULL;
 		dsb->free_pos = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h
index 6f95c8e909e6..395ef9ce558e 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.h
+++ b/drivers/gpu/drm/i915/display/intel_dsb.h
@@ -22,7 +22,7 @@ enum dsb_id {
 };
 
 struct intel_dsb {
-	atomic_t refcount;
+	long refcount;
 	enum dsb_id id;
 	u32 *cmd_buf;
 	struct i915_vma *vma;
diff --git a/drivers/gpu/drm/i915/display/intel_dsi.h b/drivers/gpu/drm/i915/display/intel_dsi.h
index b15be5814599..19f78a4022d3 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi.h
+++ b/drivers/gpu/drm/i915/display/intel_dsi.h
@@ -45,8 +45,9 @@ struct intel_dsi {
 	struct intel_dsi_host *dsi_hosts[I915_MAX_PORTS];
 	intel_wakeref_t io_wakeref[I915_MAX_PORTS];
 
-	/* GPIO Desc for CRC based Panel control */
+	/* GPIO Desc for panel and backlight control */
 	struct gpio_desc *gpio_panel;
+	struct gpio_desc *gpio_backlight;
 
 	struct intel_connector *attached_connector;
 
@@ -68,6 +69,9 @@ struct intel_dsi {
 	/* number of DSI lanes */
 	unsigned int lane_count;
 
+	/* i2c bus associated with the slave device */
+	int i2c_bus_num;
+
 	/*
 	 * video mode pixel format
 	 *
@@ -141,9 +145,9 @@ static inline struct intel_dsi_host *to_intel_dsi_host(struct mipi_dsi_host *h)
 #define for_each_dsi_phy(__phy, __phys_mask) \
 	for_each_phy_masked(__phy, __phys_mask)
 
-static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
+static inline struct intel_dsi *enc_to_intel_dsi(struct intel_encoder *encoder)
 {
-	return container_of(encoder, struct intel_dsi, base.base);
+	return container_of(&encoder->base, struct intel_dsi, base.base);
 }
 
 static inline bool is_vid_mode(struct intel_dsi *intel_dsi)
@@ -158,7 +162,7 @@ static inline bool is_cmd_mode(struct intel_dsi *intel_dsi)
 
 static inline u16 intel_dsi_encoder_ports(struct intel_encoder *encoder)
 {
-	return enc_to_intel_dsi(&encoder->base)->ports;
+	return enc_to_intel_dsi(encoder)->ports;
 }
 
 /* icl_dsi.c */
@@ -203,6 +207,8 @@ void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
 
 /* intel_dsi_vbt.c */
 bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id);
+void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on);
+void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi);
 void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
 				 enum mipi_seq seq_id);
 void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec);
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c
index bb3fd8b786a2..c87838843d0b 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c
@@ -46,7 +46,7 @@
 static u32 dcs_get_backlight(struct intel_connector *connector)
 {
 	struct intel_encoder *encoder = connector->encoder;
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct mipi_dsi_device *dsi_device;
 	u8 data = 0;
 	enum port port;
@@ -64,7 +64,7 @@ static u32 dcs_get_backlight(struct intel_connector *connector)
 
 static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32 level)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(conn_state->best_encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder));
 	struct mipi_dsi_device *dsi_device;
 	u8 data = level;
 	enum port port;
@@ -79,7 +79,7 @@ static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32
 
 static void dcs_disable_backlight(const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(conn_state->best_encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder));
 	struct mipi_dsi_device *dsi_device;
 	enum port port;
 
@@ -113,7 +113,7 @@ static void dcs_disable_backlight(const struct drm_connector_state *conn_state)
 static void dcs_enable_backlight(const struct intel_crtc_state *crtc_state,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(conn_state->best_encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder));
 	struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel;
 	struct mipi_dsi_device *dsi_device;
 	enum port port;
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index f90946c912ee..89fb0d90b694 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -25,7 +25,10 @@
  */
 
 #include <linux/gpio/consumer.h>
+#include <linux/gpio/machine.h>
 #include <linux/mfd/intel_soc_pmic.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/pinctrl/machine.h>
 #include <linux/slab.h>
 
 #include <asm/intel-mid.h>
@@ -83,6 +86,12 @@ static struct gpio_map vlv_gpio_table[] = {
 	{ VLV_GPIO_NC_11_PANEL1_BKLTCTL },
 };
 
+struct i2c_adapter_lookup {
+	u16 slave_addr;
+	struct intel_dsi *intel_dsi;
+	acpi_handle dev_handle;
+};
+
 #define CHV_GPIO_IDX_START_N		0
 #define CHV_GPIO_IDX_START_E		73
 #define CHV_GPIO_IDX_START_SW		100
@@ -375,11 +384,98 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 	return data;
 }
 
+static int i2c_adapter_lookup(struct acpi_resource *ares, void *data)
+{
+	struct i2c_adapter_lookup *lookup = data;
+	struct intel_dsi *intel_dsi = lookup->intel_dsi;
+	struct acpi_resource_i2c_serialbus *sb;
+	struct i2c_adapter *adapter;
+	acpi_handle adapter_handle;
+	acpi_status status;
+
+	if (intel_dsi->i2c_bus_num >= 0 ||
+	    !i2c_acpi_get_i2c_resource(ares, &sb))
+		return 1;
+
+	if (lookup->slave_addr != sb->slave_address)
+		return 1;
+
+	status = acpi_get_handle(lookup->dev_handle,
+				 sb->resource_source.string_ptr,
+				 &adapter_handle);
+	if (ACPI_FAILURE(status))
+		return 1;
+
+	adapter = i2c_acpi_find_adapter_by_handle(adapter_handle);
+	if (adapter)
+		intel_dsi->i2c_bus_num = adapter->nr;
+
+	return 1;
+}
+
 static const u8 *mipi_exec_i2c(struct intel_dsi *intel_dsi, const u8 *data)
 {
-	DRM_DEBUG_KMS("Skipping I2C element execution\n");
+	struct drm_device *drm_dev = intel_dsi->base.base.dev;
+	struct device *dev = &drm_dev->pdev->dev;
+	struct i2c_adapter *adapter;
+	struct acpi_device *acpi_dev;
+	struct list_head resource_list;
+	struct i2c_adapter_lookup lookup;
+	struct i2c_msg msg;
+	int ret;
+	u8 vbt_i2c_bus_num = *(data + 2);
+	u16 slave_addr = *(u16 *)(data + 3);
+	u8 reg_offset = *(data + 5);
+	u8 payload_size = *(data + 6);
+	u8 *payload_data;
+
+	if (intel_dsi->i2c_bus_num < 0) {
+		intel_dsi->i2c_bus_num = vbt_i2c_bus_num;
+
+		acpi_dev = ACPI_COMPANION(dev);
+		if (acpi_dev) {
+			memset(&lookup, 0, sizeof(lookup));
+			lookup.slave_addr = slave_addr;
+			lookup.intel_dsi = intel_dsi;
+			lookup.dev_handle = acpi_device_handle(acpi_dev);
+
+			INIT_LIST_HEAD(&resource_list);
+			acpi_dev_get_resources(acpi_dev, &resource_list,
+					       i2c_adapter_lookup,
+					       &lookup);
+			acpi_dev_free_resource_list(&resource_list);
+		}
+	}
 
-	return data + *(data + 6) + 7;
+	adapter = i2c_get_adapter(intel_dsi->i2c_bus_num);
+	if (!adapter) {
+		DRM_DEV_ERROR(dev, "Cannot find a valid i2c bus for xfer\n");
+		goto err_bus;
+	}
+
+	payload_data = kzalloc(payload_size + 1, GFP_KERNEL);
+	if (!payload_data)
+		goto err_alloc;
+
+	payload_data[0] = reg_offset;
+	memcpy(&payload_data[1], (data + 7), payload_size);
+
+	msg.addr = slave_addr;
+	msg.flags = 0;
+	msg.len = payload_size + 1;
+	msg.buf = payload_data;
+
+	ret = i2c_transfer(adapter, &msg, 1);
+	if (ret < 0)
+		DRM_DEV_ERROR(dev,
+			      "Failed to xfer payload of size (%u) to reg (%u)\n",
+			      payload_size, reg_offset);
+
+	kfree(payload_data);
+err_alloc:
+	i2c_put_adapter(adapter);
+err_bus:
+	return data + payload_size + 7;
 }
 
 static const u8 *mipi_exec_spi(struct intel_dsi *intel_dsi, const u8 *data)
@@ -453,8 +549,8 @@ static const char *sequence_name(enum mipi_seq seq_id)
 		return "(unknown)";
 }
 
-void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
-				 enum mipi_seq seq_id)
+static void intel_dsi_vbt_exec(struct intel_dsi *intel_dsi,
+			       enum mipi_seq seq_id)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
 	const u8 *data;
@@ -519,6 +615,22 @@ void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
 	}
 }
 
+void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
+				 enum mipi_seq seq_id)
+{
+	if (seq_id == MIPI_SEQ_POWER_ON && intel_dsi->gpio_panel)
+		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
+	if (seq_id == MIPI_SEQ_BACKLIGHT_ON && intel_dsi->gpio_backlight)
+		gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 1);
+
+	intel_dsi_vbt_exec(intel_dsi, seq_id);
+
+	if (seq_id == MIPI_SEQ_POWER_OFF && intel_dsi->gpio_panel)
+		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 0);
+	if (seq_id == MIPI_SEQ_BACKLIGHT_OFF && intel_dsi->gpio_backlight)
+		gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 0);
+}
+
 void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
@@ -664,6 +776,8 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 	intel_dsi->panel_off_delay = pps->panel_off_delay / 10;
 	intel_dsi->panel_pwr_cycle_delay = pps->panel_power_cycle_delay / 10;
 
+	intel_dsi->i2c_bus_num = -1;
+
 	/* a regular driver would get the device in probe */
 	for_each_dsi_port(port, intel_dsi->ports) {
 		mipi_dsi_attach(intel_dsi->dsi_hosts[port]->device);
@@ -671,3 +785,110 @@ bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id)
 
 	return true;
 }
+
+/*
+ * On some BYT/CHT devs some sequences are incomplete and we need to manually
+ * control some GPIOs. We need to add a GPIO lookup table before we get these.
+ * If the GOP did not initialize the panel (HDMI inserted) we may need to also
+ * change the pinmux for the SoC's PWM0 pin from GPIO to PWM.
+ */
+static struct gpiod_lookup_table pmic_panel_gpio_table = {
+	/* Intel GFX is consumer */
+	.dev_id = "0000:00:02.0",
+	.table = {
+		/* Panel EN/DISABLE */
+		GPIO_LOOKUP("gpio_crystalcove", 94, "panel", GPIO_ACTIVE_HIGH),
+		{ }
+	},
+};
+
+static struct gpiod_lookup_table soc_panel_gpio_table = {
+	.dev_id = "0000:00:02.0",
+	.table = {
+		GPIO_LOOKUP("INT33FC:01", 10, "backlight", GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("INT33FC:01", 11, "panel", GPIO_ACTIVE_HIGH),
+		{ }
+	},
+};
+
+static const struct pinctrl_map soc_pwm_pinctrl_map[] = {
+	PIN_MAP_MUX_GROUP("0000:00:02.0", "soc_pwm0", "INT33FC:00",
+			  "pwm0_grp", "pwm"),
+};
+
+void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on)
+{
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct mipi_config *mipi_config = dev_priv->vbt.dsi.config;
+	enum gpiod_flags flags = panel_is_on ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW;
+	bool want_backlight_gpio = false;
+	bool want_panel_gpio = false;
+	struct pinctrl *pinctrl;
+	int ret;
+
+	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    mipi_config->pwm_blc == PPS_BLC_PMIC) {
+		gpiod_add_lookup_table(&pmic_panel_gpio_table);
+		want_panel_gpio = true;
+	}
+
+	if (IS_VALLEYVIEW(dev_priv) && mipi_config->pwm_blc == PPS_BLC_SOC) {
+		gpiod_add_lookup_table(&soc_panel_gpio_table);
+		want_panel_gpio = true;
+		want_backlight_gpio = true;
+
+		/* Ensure PWM0 pin is muxed as PWM instead of GPIO */
+		ret = pinctrl_register_mappings(soc_pwm_pinctrl_map,
+					     ARRAY_SIZE(soc_pwm_pinctrl_map));
+		if (ret)
+			DRM_ERROR("Failed to register pwm0 pinmux mapping\n");
+
+		pinctrl = devm_pinctrl_get_select(dev->dev, "soc_pwm0");
+		if (IS_ERR(pinctrl))
+			DRM_ERROR("Failed to set pinmux to PWM\n");
+	}
+
+	if (want_panel_gpio) {
+		intel_dsi->gpio_panel = gpiod_get(dev->dev, "panel", flags);
+		if (IS_ERR(intel_dsi->gpio_panel)) {
+			DRM_ERROR("Failed to own gpio for panel control\n");
+			intel_dsi->gpio_panel = NULL;
+		}
+	}
+
+	if (want_backlight_gpio) {
+		intel_dsi->gpio_backlight =
+			gpiod_get(dev->dev, "backlight", flags);
+		if (IS_ERR(intel_dsi->gpio_backlight)) {
+			DRM_ERROR("Failed to own gpio for backlight control\n");
+			intel_dsi->gpio_backlight = NULL;
+		}
+	}
+}
+
+void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi)
+{
+	struct drm_device *dev = intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct mipi_config *mipi_config = dev_priv->vbt.dsi.config;
+
+	if (intel_dsi->gpio_panel) {
+		gpiod_put(intel_dsi->gpio_panel);
+		intel_dsi->gpio_panel = NULL;
+	}
+
+	if (intel_dsi->gpio_backlight) {
+		gpiod_put(intel_dsi->gpio_backlight);
+		intel_dsi->gpio_backlight = NULL;
+	}
+
+	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    mipi_config->pwm_blc == PPS_BLC_PMIC)
+		gpiod_remove_lookup_table(&pmic_panel_gpio_table);
+
+	if (IS_VALLEYVIEW(dev_priv) && mipi_config->pwm_blc == PPS_BLC_SOC) {
+		pinctrl_unregister_mappings(soc_pwm_pinctrl_map);
+		gpiod_remove_lookup_table(&soc_panel_gpio_table);
+	}
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index bcfbcb743e7d..86a337c9d85d 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -125,7 +125,7 @@ static struct intel_dvo *enc_to_dvo(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_dvo, base);
 }
 
-static struct intel_dvo *intel_attached_dvo(struct drm_connector *connector)
+static struct intel_dvo *intel_attached_dvo(struct intel_connector *connector)
 {
 	return enc_to_dvo(intel_attached_encoder(connector));
 }
@@ -134,7 +134,7 @@ static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 {
 	struct drm_device *dev = connector->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dvo *intel_dvo = intel_attached_dvo(&connector->base);
+	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
 	u32 tmp;
 
 	tmp = I915_READ(intel_dvo->dev.dvo_reg);
@@ -178,9 +178,9 @@ static void intel_dvo_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_NVSYNC;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
-	pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock;
+	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
 static void intel_disable_dvo(struct intel_encoder *encoder,
@@ -207,8 +207,8 @@ static void intel_enable_dvo(struct intel_encoder *encoder,
 	u32 temp = I915_READ(dvo_reg);
 
 	intel_dvo->dev.dev_ops->mode_set(&intel_dvo->dev,
-					 &pipe_config->base.mode,
-					 &pipe_config->base.adjusted_mode);
+					 &pipe_config->hw.mode,
+					 &pipe_config->hw.adjusted_mode);
 
 	I915_WRITE(dvo_reg, temp | DVO_ENABLE);
 	I915_READ(dvo_reg);
@@ -220,7 +220,7 @@ static enum drm_mode_status
 intel_dvo_mode_valid(struct drm_connector *connector,
 		     struct drm_display_mode *mode)
 {
-	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+	struct intel_dvo *intel_dvo = intel_attached_dvo(to_intel_connector(connector));
 	const struct drm_display_mode *fixed_mode =
 		to_intel_connector(connector)->panel.fixed_mode;
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
@@ -253,7 +253,7 @@ static int intel_dvo_compute_config(struct intel_encoder *encoder,
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	const struct drm_display_mode *fixed_mode =
 		intel_dvo->attached_connector->panel.fixed_mode;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 
 	/*
 	 * If we have timings from the BIOS for the panel, put them in
@@ -277,8 +277,8 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 				 const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	enum pipe pipe = crtc->pipe;
 	u32 dvo_val;
@@ -311,7 +311,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 static enum drm_connector_status
 intel_dvo_detect(struct drm_connector *connector, bool force)
 {
-	struct intel_dvo *intel_dvo = intel_attached_dvo(connector);
+	struct intel_dvo *intel_dvo = intel_attached_dvo(to_intel_connector(connector));
 	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
 		      connector->base.id, connector->name);
 	return intel_dvo->dev.dev_ops->detect(&intel_dvo->dev);
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 20616639b8ab..a1048ece541e 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -50,11 +50,6 @@ static inline bool fbc_supported(struct drm_i915_private *dev_priv)
 	return HAS_FBC(dev_priv);
 }
 
-static inline bool no_fbc_on_multiple_pipes(struct drm_i915_private *dev_priv)
-{
-	return INTEL_GEN(dev_priv) <= 3;
-}
-
 /*
  * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
  * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
@@ -73,7 +68,7 @@ static unsigned int get_crtc_fence_y_offset(struct intel_fbc *fbc)
  * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value
  * we wrote to PIPESRC.
  */
-static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
+static void intel_fbc_get_plane_source_size(const struct intel_fbc_state_cache *cache,
 					    int *width, int *height)
 {
 	if (width)
@@ -83,7 +78,7 @@ static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
 }
 
 static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
-					struct intel_fbc_state_cache *cache)
+					const struct intel_fbc_state_cache *cache)
 {
 	int lines;
 
@@ -143,8 +138,10 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 		u32 fbc_ctl2;
 
 		/* Set it up... */
-		fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM | FBC_CTL_CPU_FENCE;
+		fbc_ctl2 = FBC_CTL_FENCE_DBL | FBC_CTL_IDLE_IMM;
 		fbc_ctl2 |= FBC_CTL_PLANE(params->crtc.i9xx_plane);
+		if (params->fence_id >= 0)
+			fbc_ctl2 |= FBC_CTL_CPU_FENCE;
 		I915_WRITE(FBC_CONTROL2, fbc_ctl2);
 		I915_WRITE(FBC_FENCE_OFF, params->crtc.fence_y_offset);
 	}
@@ -156,7 +153,8 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 	if (IS_I945GM(dev_priv))
 		fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */
 	fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT;
-	fbc_ctl |= params->vma->fence->id;
+	if (params->fence_id >= 0)
+		fbc_ctl |= params->fence_id;
 	I915_WRITE(FBC_CONTROL, fbc_ctl);
 }
 
@@ -176,8 +174,8 @@ static void g4x_fbc_activate(struct drm_i915_private *dev_priv)
 	else
 		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
 
-	if (params->flags & PLANE_HAS_FENCE) {
-		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->vma->fence->id;
+	if (params->fence_id >= 0) {
+		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id;
 		I915_WRITE(DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
 	} else {
 		I915_WRITE(DPFC_FENCE_YOFF, 0);
@@ -234,14 +232,14 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	if (params->flags & PLANE_HAS_FENCE) {
+	if (params->fence_id >= 0) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN;
 		if (IS_GEN(dev_priv, 5))
-			dpfc_ctl |= params->vma->fence->id;
+			dpfc_ctl |= params->fence_id;
 		if (IS_GEN(dev_priv, 6)) {
 			I915_WRITE(SNB_DPFC_CTL_SA,
 				   SNB_CPU_FENCE_ENABLE |
-				   params->vma->fence->id);
+				   params->fence_id);
 			I915_WRITE(DPFC_CPU_FENCE_OFFSET,
 				   params->crtc.fence_y_offset);
 		}
@@ -253,8 +251,6 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 	}
 
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
-	I915_WRITE(ILK_FBC_RT_BASE,
-		   i915_ggtt_offset(params->vma) | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -285,13 +281,12 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 	int threshold = dev_priv->fbc.threshold;
 
 	/* Display WA #0529: skl, kbl, bxt. */
-	if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) {
 		u32 val = I915_READ(CHICKEN_MISC_4);
 
 		val &= ~(FBC_STRIDE_OVERRIDE | FBC_STRIDE_MASK);
 
-		if (i915_gem_object_get_tiling(params->vma->obj) !=
-		    I915_TILING_X)
+		if (params->gen9_wa_cfb_stride)
 			val |= FBC_STRIDE_OVERRIDE | params->gen9_wa_cfb_stride;
 
 		I915_WRITE(CHICKEN_MISC_4, val);
@@ -317,11 +312,11 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	if (params->flags & PLANE_HAS_FENCE) {
+	if (params->fence_id >= 0) {
 		dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
 		I915_WRITE(SNB_DPFC_CTL_SA,
 			   SNB_CPU_FENCE_ENABLE |
-			   params->vma->fence->id);
+			   params->fence_id);
 		I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset);
 	} else {
 		I915_WRITE(SNB_DPFC_CTL_SA,0);
@@ -367,6 +362,7 @@ static void intel_fbc_hw_activate(struct drm_i915_private *dev_priv)
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
 	fbc->active = true;
+	fbc->activated = true;
 
 	if (INTEL_GEN(dev_priv) >= 7)
 		gen7_fbc_activate(dev_priv);
@@ -419,29 +415,10 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 	fbc->no_fbc_reason = reason;
 }
 
-static bool multiple_pipes_ok(struct intel_crtc *crtc,
-			      struct intel_plane_state *plane_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	enum pipe pipe = crtc->pipe;
-
-	/* Don't even bother tracking anything we don't need. */
-	if (!no_fbc_on_multiple_pipes(dev_priv))
-		return true;
-
-	if (plane_state->base.visible)
-		fbc->visible_pipes_mask |= (1 << pipe);
-	else
-		fbc->visible_pipes_mask &= ~(1 << pipe);
-
-	return (fbc->visible_pipes_mask & ~(1 << pipe)) != 0;
-}
-
 static int find_compression_threshold(struct drm_i915_private *dev_priv,
 				      struct drm_mm_node *node,
-				      int size,
-				      int fb_cpp)
+				      unsigned int size,
+				      unsigned int fb_cpp)
 {
 	int compression_threshold = 1;
 	int ret;
@@ -487,18 +464,15 @@ again:
 	}
 }
 
-static int intel_fbc_alloc_cfb(struct intel_crtc *crtc)
+static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv,
+			       unsigned int size, unsigned int fb_cpp)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct drm_mm_node *uninitialized_var(compressed_llb);
-	int size, fb_cpp, ret;
+	int ret;
 
 	WARN_ON(drm_mm_node_allocated(&fbc->compressed_fb));
 
-	size = intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache);
-	fb_cpp = fbc->state_cache.fb.format->cpp[0];
-
 	ret = find_compression_threshold(dev_priv, &fbc->compressed_fb,
 					 size, fb_cpp);
 	if (!ret)
@@ -656,46 +630,55 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 }
 
 static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
-					 struct intel_crtc_state *crtc_state,
-					 struct intel_plane_state *plane_state)
+					 const struct intel_crtc_state *crtc_state,
+					 const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
-	struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_framebuffer *fb = plane_state->hw.fb;
 
-	cache->vma = NULL;
-	cache->flags = 0;
+	cache->plane.visible = plane_state->uapi.visible;
+	if (!cache->plane.visible)
+		return;
 
-	cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags;
+	cache->crtc.mode_flags = crtc_state->hw.adjusted_mode.flags;
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate;
 
-	cache->plane.rotation = plane_state->base.rotation;
+	cache->plane.rotation = plane_state->hw.rotation;
 	/*
 	 * Src coordinates are already rotated by 270 degrees for
 	 * the 90/270 degree plane rotation cases (to match the
 	 * GTT mapping), hence no need to account for rotation here.
 	 */
-	cache->plane.src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	cache->plane.src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	cache->plane.visible = plane_state->base.visible;
+	cache->plane.src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	cache->plane.src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	cache->plane.adjusted_x = plane_state->color_plane[0].x;
 	cache->plane.adjusted_y = plane_state->color_plane[0].y;
-	cache->plane.y = plane_state->base.src.y1 >> 16;
+	cache->plane.y = plane_state->uapi.src.y1 >> 16;
 
-	cache->plane.pixel_blend_mode = plane_state->base.pixel_blend_mode;
-
-	if (!cache->plane.visible)
-		return;
+	cache->plane.pixel_blend_mode = plane_state->hw.pixel_blend_mode;
 
 	cache->fb.format = fb->format;
 	cache->fb.stride = fb->pitches[0];
 
-	cache->vma = plane_state->vma;
-	cache->flags = plane_state->flags;
-	if (WARN_ON(cache->flags & PLANE_HAS_FENCE && !cache->vma->fence))
-		cache->flags &= ~PLANE_HAS_FENCE;
+	WARN_ON(plane_state->flags & PLANE_HAS_FENCE &&
+		!plane_state->vma->fence);
+
+	if (plane_state->flags & PLANE_HAS_FENCE &&
+	    plane_state->vma->fence)
+		cache->fence_id = plane_state->vma->fence->id;
+	else
+		cache->fence_id = -1;
+}
+
+static bool intel_fbc_cfb_size_changed(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	return intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) >
+		fbc->compressed_fb.size * fbc->threshold;
 }
 
 static bool intel_fbc_can_activate(struct intel_crtc *crtc)
@@ -704,6 +687,11 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
 
+	if (!cache->plane.visible) {
+		fbc->no_fbc_reason = "primary plane not visible";
+		return false;
+	}
+
 	/* We don't need to use a state cache here since this information is
 	 * global for all CRTC.
 	 */
@@ -712,11 +700,6 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 		return false;
 	}
 
-	if (!cache->vma) {
-		fbc->no_fbc_reason = "primary plane not visible";
-		return false;
-	}
-
 	if (cache->crtc.mode_flags & DRM_MODE_FLAG_INTERLACE) {
 		fbc->no_fbc_reason = "incompatible mode";
 		return false;
@@ -740,7 +723,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * For now this will effecively disable FBC with 90/270 degree
 	 * rotation.
 	 */
-	if (!(cache->flags & PLANE_HAS_FENCE)) {
+	if (cache->fence_id < 0) {
 		fbc->no_fbc_reason = "framebuffer not tiled or fenced";
 		return false;
 	}
@@ -783,8 +766,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * we didn't get any invalidate/deactivate calls, but this would require
 	 * a lot of tracking just for a specific case. If we conclude it's an
 	 * important case, we can implement it later. */
-	if (intel_fbc_calculate_cfb_size(dev_priv, &fbc->state_cache) >
-	    fbc->compressed_fb.size * fbc->threshold) {
+	if (intel_fbc_cfb_size_changed(dev_priv)) {
 		fbc->no_fbc_reason = "CFB requirements changed";
 		return false;
 	}
@@ -794,7 +776,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * having a Y offset that isn't divisible by 4 causes FIFO underrun
 	 * and screen flicker.
 	 */
-	if (IS_GEN_RANGE(dev_priv, 9, 10) &&
+	if (INTEL_GEN(dev_priv) >= 9 &&
 	    (fbc->state_cache.plane.adjusted_y & 3)) {
 		fbc->no_fbc_reason = "plane Y offset is misaligned";
 		return false;
@@ -837,8 +819,7 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 	 * zero. */
 	memset(params, 0, sizeof(*params));
 
-	params->vma = cache->vma;
-	params->flags = cache->flags;
+	params->fence_id = cache->fence_id;
 
 	params->crtc.pipe = crtc->pipe;
 	params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane;
@@ -849,39 +830,88 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 
 	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
 
-	if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv))
-		params->gen9_wa_cfb_stride = DIV_ROUND_UP(cache->plane.src_w,
-						32 * fbc->threshold) * 8;
+	params->gen9_wa_cfb_stride = cache->gen9_wa_cfb_stride;
+
+	params->plane_visible = cache->plane.visible;
+}
+
+static bool intel_fbc_can_flip_nuke(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_fbc *fbc = &dev_priv->fbc;
+	const struct intel_fbc_state_cache *cache = &fbc->state_cache;
+	const struct intel_fbc_reg_params *params = &fbc->params;
+
+	if (drm_atomic_crtc_needs_modeset(&crtc_state->uapi))
+		return false;
+
+	if (!params->plane_visible)
+		return false;
+
+	if (!intel_fbc_can_activate(crtc))
+		return false;
+
+	if (params->fb.format != cache->fb.format)
+		return false;
+
+	if (params->fb.stride != cache->fb.stride)
+		return false;
+
+	if (params->cfb_size != intel_fbc_calculate_cfb_size(dev_priv, cache))
+		return false;
+
+	if (params->gen9_wa_cfb_stride != cache->gen9_wa_cfb_stride)
+		return false;
+
+	return true;
 }
 
-void intel_fbc_pre_update(struct intel_crtc *crtc,
-			  struct intel_crtc_state *crtc_state,
-			  struct intel_plane_state *plane_state)
+bool intel_fbc_pre_update(struct intel_crtc *crtc,
+			  const struct intel_crtc_state *crtc_state,
+			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	const char *reason = "update pending";
+	bool need_vblank_wait = false;
 
 	if (!fbc_supported(dev_priv))
-		return;
+		return need_vblank_wait;
 
 	mutex_lock(&fbc->lock);
 
-	if (!multiple_pipes_ok(crtc, plane_state)) {
-		reason = "more than one pipe active";
-		goto deactivate;
-	}
-
-	if (!fbc->enabled || fbc->crtc != crtc)
+	if (fbc->crtc != crtc)
 		goto unlock;
 
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
 	fbc->flip_pending = true;
 
-deactivate:
-	intel_fbc_deactivate(dev_priv, reason);
+	if (!intel_fbc_can_flip_nuke(crtc_state)) {
+		intel_fbc_deactivate(dev_priv, reason);
+
+		/*
+		 * Display WA #1198: glk+
+		 * Need an extra vblank wait between FBC disable and most plane
+		 * updates. Bspec says this is only needed for plane disable, but
+		 * that is not true. Touching most plane registers will cause the
+		 * corruption to appear. Also SKL/derivatives do not seem to be
+		 * affected.
+		 *
+		 * TODO: could optimize this a bit by sampling the frame
+		 * counter when we disable FBC (if it was already done earlier)
+		 * and skipping the extra vblank wait before the plane update
+		 * if at least one frame has already passed.
+		 */
+		if (fbc->activated &&
+		    (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)))
+			need_vblank_wait = true;
+		fbc->activated = false;
+	}
 unlock:
 	mutex_unlock(&fbc->lock);
+
+	return need_vblank_wait;
 }
 
 /**
@@ -897,14 +927,13 @@ static void __intel_fbc_disable(struct drm_i915_private *dev_priv)
 	struct intel_crtc *crtc = fbc->crtc;
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
-	WARN_ON(!fbc->enabled);
+	WARN_ON(!fbc->crtc);
 	WARN_ON(fbc->active);
 
 	DRM_DEBUG_KMS("Disabling FBC on pipe %c\n", pipe_name(crtc->pipe));
 
 	__intel_fbc_cleanup_cfb(dev_priv);
 
-	fbc->enabled = false;
 	fbc->crtc = NULL;
 }
 
@@ -915,11 +944,10 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	if (!fbc->enabled || fbc->crtc != crtc)
+	if (fbc->crtc != crtc)
 		return;
 
 	fbc->flip_pending = false;
-	WARN_ON(fbc->active);
 
 	if (!i915_modparams.enable_fbc) {
 		intel_fbc_deactivate(dev_priv, "disabled at runtime per module param");
@@ -933,10 +961,9 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 	if (!intel_fbc_can_activate(crtc))
 		return;
 
-	if (!fbc->busy_bits) {
-		intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
+	if (!fbc->busy_bits)
 		intel_fbc_hw_activate(dev_priv);
-	} else
+	else
 		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 }
 
@@ -955,7 +982,7 @@ void intel_fbc_post_update(struct intel_crtc *crtc)
 
 static unsigned int intel_fbc_get_frontbuffer_bit(struct intel_fbc *fbc)
 {
-	if (fbc->enabled)
+	if (fbc->crtc)
 		return to_intel_plane(fbc->crtc->base.primary)->frontbuffer_bit;
 	else
 		return fbc->possible_framebuffer_bits;
@@ -977,7 +1004,7 @@ void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
 
 	fbc->busy_bits |= intel_fbc_get_frontbuffer_bit(fbc) & frontbuffer_bits;
 
-	if (fbc->enabled && fbc->busy_bits)
+	if (fbc->crtc && fbc->busy_bits)
 		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 
 	mutex_unlock(&fbc->lock);
@@ -998,7 +1025,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 	if (origin == ORIGIN_GTT || origin == ORIGIN_FLIP)
 		goto out;
 
-	if (!fbc->busy_bits && fbc->enabled &&
+	if (!fbc->busy_bits && fbc->crtc &&
 	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
 		if (fbc->active)
 			intel_fbc_recompress(dev_priv);
@@ -1047,12 +1074,12 @@ void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
 	 * to pipe or plane A. */
 	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
 		struct intel_crtc_state *crtc_state;
-		struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
+		struct intel_crtc *crtc = to_intel_crtc(plane_state->hw.crtc);
 
 		if (!plane->has_fbc)
 			continue;
 
-		if (!plane_state->base.visible)
+		if (!plane_state->uapi.visible)
 			continue;
 
 		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
@@ -1081,42 +1108,53 @@ out:
  * intel_fbc_disable in the middle, as long as it is deactivated.
  */
 void intel_fbc_enable(struct intel_crtc *crtc,
-		      struct intel_crtc_state *crtc_state,
-		      struct intel_plane_state *plane_state)
+		      const struct intel_crtc_state *crtc_state,
+		      const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 
 	if (!fbc_supported(dev_priv))
 		return;
 
 	mutex_lock(&fbc->lock);
 
-	if (fbc->enabled) {
-		WARN_ON(fbc->crtc == NULL);
-		if (fbc->crtc == crtc) {
-			WARN_ON(!crtc_state->enable_fbc);
-			WARN_ON(fbc->active);
-		}
-		goto out;
-	}
+	if (fbc->crtc) {
+		if (fbc->crtc != crtc ||
+		    !intel_fbc_cfb_size_changed(dev_priv))
+			goto out;
 
-	if (!crtc_state->enable_fbc)
-		goto out;
+		__intel_fbc_disable(dev_priv);
+	}
 
 	WARN_ON(fbc->active);
-	WARN_ON(fbc->crtc != NULL);
 
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
-	if (intel_fbc_alloc_cfb(crtc)) {
+
+	/* FIXME crtc_state->enable_fbc lies :( */
+	if (!cache->plane.visible)
+		goto out;
+
+	if (intel_fbc_alloc_cfb(dev_priv,
+				intel_fbc_calculate_cfb_size(dev_priv, cache),
+				fb->format->cpp[0])) {
+		cache->plane.visible = false;
 		fbc->no_fbc_reason = "not enough stolen memory";
 		goto out;
 	}
 
+	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
+	    fb->modifier != I915_FORMAT_MOD_X_TILED)
+		cache->gen9_wa_cfb_stride =
+			DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+	else
+		cache->gen9_wa_cfb_stride = 0;
+
 	DRM_DEBUG_KMS("Enabling FBC on pipe %c\n", pipe_name(crtc->pipe));
 	fbc->no_fbc_reason = "FBC enabled but not active yet\n";
 
-	fbc->enabled = true;
 	fbc->crtc = crtc;
 out:
 	mutex_unlock(&fbc->lock);
@@ -1156,7 +1194,7 @@ void intel_fbc_global_disable(struct drm_i915_private *dev_priv)
 		return;
 
 	mutex_lock(&fbc->lock);
-	if (fbc->enabled) {
+	if (fbc->crtc) {
 		WARN_ON(fbc->crtc->active);
 		__intel_fbc_disable(dev_priv);
 	}
@@ -1172,7 +1210,7 @@ static void intel_fbc_underrun_work_fn(struct work_struct *work)
 	mutex_lock(&fbc->lock);
 
 	/* Maybe we were scheduled twice. */
-	if (fbc->underrun_detected || !fbc->enabled)
+	if (fbc->underrun_detected || !fbc->crtc)
 		goto out;
 
 	DRM_DEBUG_KMS("Disabling FBC due to FIFO underrun.\n");
@@ -1244,28 +1282,6 @@ void intel_fbc_handle_fifo_underrun_irq(struct drm_i915_private *dev_priv)
 	schedule_work(&fbc->underrun_work);
 }
 
-/**
- * intel_fbc_init_pipe_state - initialize FBC's CRTC visibility tracking
- * @dev_priv: i915 device instance
- *
- * The FBC code needs to track CRTC visibility since the older platforms can't
- * have FBC enabled while multiple pipes are used. This function does the
- * initial setup at driver load to make sure FBC is matching the real hardware.
- */
-void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv)
-{
-	struct intel_crtc *crtc;
-
-	/* Don't even bother tracking anything if we don't need. */
-	if (!no_fbc_on_multiple_pipes(dev_priv))
-		return;
-
-	for_each_intel_crtc(&dev_priv->drm, crtc)
-		if (intel_crtc_active(crtc) &&
-		    crtc->base.primary->state->visible)
-			dev_priv->fbc.visible_pipes_mask |= (1 << crtc->pipe);
-}
-
 /*
  * The DDX driver changes its behavior depending on the value it reads from
  * i915.enable_fbc, so sanitize it by translating the default value into either
@@ -1283,10 +1299,6 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 	if (!HAS_FBC(dev_priv))
 		return 0;
 
-	/* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
-	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
-		return 0;
-
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
@@ -1317,7 +1329,6 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 
 	INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn);
 	mutex_init(&fbc->lock);
-	fbc->enabled = false;
 	fbc->active = false;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.h b/drivers/gpu/drm/i915/display/intel_fbc.h
index 50272eda8d43..c8a5e5098687 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.h
+++ b/drivers/gpu/drm/i915/display/intel_fbc.h
@@ -19,15 +19,14 @@ struct intel_plane_state;
 void intel_fbc_choose_crtc(struct drm_i915_private *dev_priv,
 			   struct intel_atomic_state *state);
 bool intel_fbc_is_active(struct drm_i915_private *dev_priv);
-void intel_fbc_pre_update(struct intel_crtc *crtc,
-			  struct intel_crtc_state *crtc_state,
-			  struct intel_plane_state *plane_state);
+bool intel_fbc_pre_update(struct intel_crtc *crtc,
+			  const struct intel_crtc_state *crtc_state,
+			  const struct intel_plane_state *plane_state);
 void intel_fbc_post_update(struct intel_crtc *crtc);
 void intel_fbc_init(struct drm_i915_private *dev_priv);
-void intel_fbc_init_pipe_state(struct drm_i915_private *dev_priv);
 void intel_fbc_enable(struct intel_crtc *crtc,
-		      struct intel_crtc_state *crtc_state,
-		      struct intel_plane_state *plane_state);
+		      const struct intel_crtc_state *crtc_state,
+		      const struct intel_plane_state *plane_state);
 void intel_fbc_disable(struct intel_crtc *crtc);
 void intel_fbc_global_disable(struct drm_i915_private *dev_priv);
 void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 48c960ca12fb..1e98e432c9fa 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -100,7 +100,7 @@ static int intel_fbdev_pan_display(struct fb_var_screeninfo *var,
 	return ret;
 }
 
-static struct fb_ops intelfb_ops = {
+static const struct fb_ops intelfb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_set_par = intel_fbdev_set_par,
diff --git a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c
index ab61f88d1d33..6c83b350525d 100644
--- a/drivers/gpu/drm/i915/display/intel_fifo_underrun.c
+++ b/drivers/gpu/drm/i915/display/intel_fifo_underrun.c
@@ -126,8 +126,8 @@ static void i9xx_set_fifo_underrun_reporting(struct drm_device *dev,
 	}
 }
 
-static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
-						 enum pipe pipe, bool enable)
+static void ilk_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 bit = (pipe == PIPE_A) ?
@@ -139,7 +139,7 @@ static void ironlake_set_fifo_underrun_reporting(struct drm_device *dev,
 		ilk_disable_display_irq(dev_priv, bit);
 }
 
-static void ivybridge_check_fifo_underruns(struct intel_crtc *crtc)
+static void ivb_check_fifo_underruns(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
@@ -157,9 +157,9 @@ static void ivybridge_check_fifo_underruns(struct intel_crtc *crtc)
 	DRM_ERROR("fifo underrun on pipe %c\n", pipe_name(pipe));
 }
 
-static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
-						  enum pipe pipe,
-						  bool enable, bool old)
+static void ivb_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum pipe pipe, bool enable,
+					    bool old)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	if (enable) {
@@ -180,8 +180,8 @@ static void ivybridge_set_fifo_underrun_reporting(struct drm_device *dev,
 	}
 }
 
-static void broadwell_set_fifo_underrun_reporting(struct drm_device *dev,
-						  enum pipe pipe, bool enable)
+static void bdw_set_fifo_underrun_reporting(struct drm_device *dev,
+					    enum pipe pipe, bool enable)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -264,11 +264,11 @@ static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev,
 	if (HAS_GMCH(dev_priv))
 		i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (IS_GEN_RANGE(dev_priv, 5, 6))
-		ironlake_set_fifo_underrun_reporting(dev, pipe, enable);
+		ilk_set_fifo_underrun_reporting(dev, pipe, enable);
 	else if (IS_GEN(dev_priv, 7))
-		ivybridge_set_fifo_underrun_reporting(dev, pipe, enable, old);
+		ivb_set_fifo_underrun_reporting(dev, pipe, enable, old);
 	else if (INTEL_GEN(dev_priv) >= 8)
-		broadwell_set_fifo_underrun_reporting(dev, pipe, enable);
+		bdw_set_fifo_underrun_reporting(dev, pipe, enable);
 
 	return old;
 }
@@ -427,7 +427,7 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv)
 		if (HAS_GMCH(dev_priv))
 			i9xx_check_fifo_underruns(crtc);
 		else if (IS_GEN(dev_priv, 7))
-			ivybridge_check_fifo_underruns(crtc);
+			ivb_check_fifo_underruns(crtc);
 	}
 
 	spin_unlock_irq(&dev_priv->irq_lock);
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index a448815d8fc2..0fdbd39f6641 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1870,7 +1870,7 @@ static bool is_hdcp2_supported(struct drm_i915_private *dev_priv)
 		return false;
 
 	return (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
-		IS_KABYLAKE(dev_priv));
+		IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv));
 }
 
 void intel_hdcp_component_init(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index f56fffc474fa..93ac0f296852 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -85,16 +85,17 @@ assert_hdmi_transcoder_func_disabled(struct drm_i915_private *dev_priv,
 	     "HDMI transcoder function enabled, expecting disabled\n");
 }
 
-struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder)
+struct intel_hdmi *enc_to_intel_hdmi(struct intel_encoder *encoder)
 {
 	struct intel_digital_port *intel_dig_port =
-		container_of(encoder, struct intel_digital_port, base.base);
+		container_of(&encoder->base, struct intel_digital_port,
+			     base.base);
 	return &intel_dig_port->hdmi;
 }
 
-static struct intel_hdmi *intel_attached_hdmi(struct drm_connector *connector)
+static struct intel_hdmi *intel_attached_hdmi(struct intel_connector *connector)
 {
-	return enc_to_intel_hdmi(&intel_attached_encoder(connector)->base);
+	return enc_to_intel_hdmi(intel_attached_encoder(connector));
 }
 
 static u32 g4x_infoframe_index(unsigned int type)
@@ -285,7 +286,7 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	int i;
@@ -321,7 +322,7 @@ static void ibx_read_infoframe(struct intel_encoder *encoder,
 			       void *frame, ssize_t len)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	u32 val, *data = frame;
 	int i;
 
@@ -340,7 +341,7 @@ static u32 ibx_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(pipe_config->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(pipe_config->uapi.crtc)->pipe;
 	i915_reg_t reg = TVIDEO_DIP_CTL(pipe);
 	u32 val = I915_READ(reg);
 
@@ -362,7 +363,7 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	int i;
@@ -401,7 +402,7 @@ static void cpt_read_infoframe(struct intel_encoder *encoder,
 			       void *frame, ssize_t len)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	u32 val, *data = frame;
 	int i;
 
@@ -420,7 +421,7 @@ static u32 cpt_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(pipe_config->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(pipe_config->uapi.crtc)->pipe;
 	u32 val = I915_READ(TVIDEO_DIP_CTL(pipe));
 
 	if ((val & VIDEO_DIP_ENABLE) == 0)
@@ -438,7 +439,7 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 {
 	const u32 *data = frame;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	int i;
@@ -474,7 +475,7 @@ static void vlv_read_infoframe(struct intel_encoder *encoder,
 			       void *frame, ssize_t len)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	u32 val, *data = frame;
 	int i;
 
@@ -493,7 +494,7 @@ static u32 vlv_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *pipe_config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum pipe pipe = to_intel_crtc(pipe_config->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(pipe_config->uapi.crtc)->pipe;
 	u32 val = I915_READ(VLV_TVIDEO_DIP_CTL(pipe));
 
 	if ((val & VIDEO_DIP_ENABLE) == 0)
@@ -602,7 +603,7 @@ u32 intel_hdmi_infoframes_enabled(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	u32 val, ret = 0;
 	int i;
 
@@ -646,7 +647,7 @@ static void intel_write_infoframe(struct intel_encoder *encoder,
 				  enum hdmi_infoframe_type type,
 				  const union hdmi_infoframe *frame)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	u8 buffer[VIDEO_DIP_DATA_SIZE];
 	ssize_t len;
 
@@ -675,7 +676,7 @@ void intel_read_infoframe(struct intel_encoder *encoder,
 			  enum hdmi_infoframe_type type,
 			  union hdmi_infoframe *frame)
 {
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	u8 buffer[VIDEO_DIP_DATA_SIZE];
 	int ret;
 
@@ -708,7 +709,7 @@ intel_hdmi_compute_avi_infoframe(struct intel_encoder *encoder,
 {
 	struct hdmi_avi_infoframe *frame = &crtc_state->infoframes.avi.avi;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	struct drm_connector *connector = conn_state->connector;
 	int ret;
 
@@ -804,7 +805,7 @@ intel_hdmi_compute_hdmi_infoframe(struct intel_encoder *encoder,
 
 	ret = drm_hdmi_vendor_infoframe_from_display_mode(frame,
 							  conn_state->connector,
-							  &crtc_state->base.adjusted_mode);
+							  &crtc_state->hw.adjusted_mode);
 	if (WARN_ON(ret))
 		return false;
 
@@ -855,7 +856,7 @@ static void g4x_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	i915_reg_t reg = VIDEO_DIP_CTL;
 	u32 val = I915_READ(reg);
@@ -965,7 +966,7 @@ static bool intel_hdmi_set_gcp_infoframe(struct intel_encoder *encoder,
 					 const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg;
 
 	if ((crtc_state->infoframes.enable &
@@ -990,7 +991,7 @@ void intel_hdmi_read_gcp_infoframe(struct intel_encoder *encoder,
 				   struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	i915_reg_t reg;
 
 	if ((crtc_state->infoframes.enable &
@@ -1027,7 +1028,7 @@ static void intel_hdmi_compute_gcp_infoframe(struct intel_encoder *encoder,
 
 	/* Enable default_phase whenever the display mode is suitably aligned */
 	if (gcp_default_phase_possible(crtc_state->pipe_bpp,
-				       &crtc_state->base.adjusted_mode))
+				       &crtc_state->hw.adjusted_mode))
 		crtc_state->infoframes.gcp |= GCP_DEFAULT_PHASE_ENABLE;
 }
 
@@ -1037,8 +1038,8 @@ static void ibx_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
 	struct intel_hdmi *intel_hdmi = &intel_dig_port->hdmi;
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
@@ -1096,8 +1097,8 @@ static void cpt_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 
@@ -1145,8 +1146,8 @@ static void vlv_set_infoframes(struct intel_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = VLV_TVIDEO_DIP_CTL(intel_crtc->pipe);
 	u32 val = I915_READ(reg);
 	u32 port = VIDEO_DIP_PORT(encoder->port);
@@ -1736,9 +1737,9 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	u32 hdmi_val;
 
 	intel_dp_dual_mode_set_tmds_output(intel_hdmi, true);
@@ -1774,7 +1775,7 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	intel_wakeref_t wakeref;
 	bool ret;
 
@@ -1793,7 +1794,7 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 static void intel_hdmi_get_config(struct intel_encoder *encoder,
 				  struct intel_crtc_state *pipe_config)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 tmp, flags = 0;
@@ -1829,7 +1830,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
 	    tmp & HDMI_COLOR_RANGE_16_235)
 		pipe_config->limited_color_range = true;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc)
 		dotclock = pipe_config->port_clock * 2 / 3;
@@ -1839,7 +1840,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder,
 	if (pipe_config->pixel_multiplier)
 		dotclock /= pipe_config->pixel_multiplier;
 
-	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+	pipe_config->hw.adjusted_mode.crtc_clock = dotclock;
 
 	pipe_config->lane_count = 4;
 
@@ -1860,7 +1861,7 @@ static void intel_enable_hdmi_audio(struct intel_encoder *encoder,
 				    const struct intel_crtc_state *pipe_config,
 				    const struct drm_connector_state *conn_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 
 	WARN_ON(!pipe_config->has_hdmi_sink);
 	DRM_DEBUG_DRIVER("Enabling HDMI audio on pipe %c\n",
@@ -1874,7 +1875,7 @@ static void g4x_enable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	u32 temp;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -1896,7 +1897,7 @@ static void ibx_enable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	u32 temp;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -1946,8 +1947,8 @@ static void cpt_enable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	enum pipe pipe = crtc->pipe;
 	u32 temp;
 
@@ -2007,10 +2008,10 @@ static void intel_disable_hdmi(struct intel_encoder *encoder,
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct intel_digital_port *intel_dig_port =
 		hdmi_to_dig_port(intel_hdmi);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	u32 temp;
 
 	temp = I915_READ(intel_hdmi->hdmi_reg);
@@ -2160,7 +2161,7 @@ static enum drm_mode_status
 intel_hdmi_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	struct intel_hdmi *hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum drm_mode_status status;
@@ -2210,12 +2211,12 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 				     int bpc)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(crtc_state->base.crtc->dev);
-	struct drm_atomic_state *state = crtc_state->base.state;
+		to_i915(crtc_state->uapi.crtc->dev);
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct drm_connector_state *connector_state;
 	struct drm_connector *connector;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int i;
 
 	if (HAS_GMCH(dev_priv))
@@ -2240,7 +2241,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 	for_each_new_connector_in_state(state, connector, connector_state, i) {
 		const struct drm_display_info *info = &connector->display_info;
 
-		if (connector_state->crtc != crtc_state->base.crtc)
+		if (connector_state->crtc != crtc_state->uapi.crtc)
 			continue;
 
 		if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420) {
@@ -2281,7 +2282,7 @@ static bool
 intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 			   struct intel_crtc_state *config)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(config->uapi.crtc);
 
 	if (!connector->ycbcr_420_allowed) {
 		DRM_ERROR("Platform doesn't support YCBCR420 output\n");
@@ -2316,7 +2317,7 @@ static int intel_hdmi_compute_bpc(struct intel_encoder *encoder,
 				  struct intel_crtc_state *crtc_state,
 				  int clock, bool force_dvi)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	int bpc;
 
 	for (bpc = 12; bpc >= 10; bpc -= 2) {
@@ -2334,9 +2335,9 @@ static int intel_hdmi_compute_clock(struct intel_encoder *encoder,
 				    struct intel_crtc_state *crtc_state,
 				    bool force_dvi)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int bpc, clock = adjusted_mode->crtc_clock;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
@@ -2378,7 +2379,7 @@ static bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_s
 	const struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	/*
 	 * Our YCbCr output is always limited range.
@@ -2404,9 +2405,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state)
 {
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	struct drm_connector *connector = conn_state->connector;
 	struct drm_scdc *scdc = &connector->display_info.hdmi.scdc;
 	struct intel_digital_connector_state *intel_conn_state =
@@ -2451,8 +2452,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (ret)
 		return ret;
 
-	/* Set user selected PAR to incoming mode's member */
-	adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio;
+	if (conn_state->picture_aspect_ratio)
+		adjusted_mode->picture_aspect_ratio =
+			conn_state->picture_aspect_ratio;
 
 	pipe_config->lane_count = 4;
 
@@ -2495,7 +2497,7 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 static void
 intel_hdmi_unset_edid(struct drm_connector *connector)
 {
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 
 	intel_hdmi->has_hdmi_sink = false;
 	intel_hdmi->has_audio = false;
@@ -2511,7 +2513,7 @@ static void
 intel_hdmi_dp_dual_mode_detect(struct drm_connector *connector, bool has_edid)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	enum port port = hdmi_to_dig_port(hdmi)->base.port;
 	struct i2c_adapter *adapter =
 		intel_gmbus_get_adapter(dev_priv, hdmi->ddc_bus);
@@ -2558,7 +2560,7 @@ static bool
 intel_hdmi_set_edid(struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	intel_wakeref_t wakeref;
 	struct edid *edid;
 	bool connected = false;
@@ -2599,7 +2601,7 @@ intel_hdmi_detect(struct drm_connector *connector, bool force)
 {
 	enum drm_connector_status status = connector_status_disconnected;
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 	struct intel_encoder *encoder = &hdmi_to_dig_port(intel_hdmi)->base;
 	intel_wakeref_t wakeref;
 
@@ -2662,7 +2664,7 @@ static void intel_hdmi_pre_enable(struct intel_encoder *encoder,
 				  const struct drm_connector_state *conn_state)
 {
 	struct intel_digital_port *intel_dig_port =
-		enc_to_dig_port(&encoder->base);
+		enc_to_dig_port(encoder);
 
 	intel_hdmi_prepare(encoder, pipe_config);
 
@@ -2675,7 +2677,7 @@ static void vlv_hdmi_pre_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	vlv_phy_pre_encoder_enable(encoder, pipe_config);
@@ -2745,7 +2747,7 @@ static void chv_hdmi_pre_enable(struct intel_encoder *encoder,
 				const struct intel_crtc_state *pipe_config,
 				const struct drm_connector_state *conn_state)
 {
-	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dport = enc_to_dig_port(encoder);
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
@@ -2771,7 +2773,7 @@ static struct i2c_adapter *
 intel_hdmi_get_i2c_adapter(struct drm_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(connector);
+	struct intel_hdmi *intel_hdmi = intel_attached_hdmi(to_intel_connector(connector));
 
 	return intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
 }
@@ -2815,7 +2817,7 @@ intel_hdmi_connector_register(struct drm_connector *connector)
 
 static void intel_hdmi_destroy(struct drm_connector *connector)
 {
-	struct cec_notifier *n = intel_attached_hdmi(connector)->cec_notifier;
+	struct cec_notifier *n = intel_attached_hdmi(to_intel_connector(connector))->cec_notifier;
 
 	cec_notifier_conn_unregister(n);
 
@@ -2872,7 +2874,6 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 		intel_attach_colorspace_property(connector);
 
 	drm_connector_attach_content_type_property(connector);
-	connector->state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		drm_object_attach_property(&connector->base,
@@ -2906,7 +2907,7 @@ bool intel_hdmi_handle_sink_scrambling(struct intel_encoder *encoder,
 				       bool scrambling)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	struct drm_scrambling *sink_scrambling =
 		&connector->display_info.hdmi.scdc.scrambling;
 	struct i2c_adapter *adapter =
@@ -3131,20 +3132,29 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	struct intel_encoder *intel_encoder = &intel_dig_port->base;
 	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i2c_adapter *ddc;
 	enum port port = intel_encoder->port;
 	struct cec_connector_info conn_info;
 
 	DRM_DEBUG_KMS("Adding HDMI connector on [ENCODER:%d:%s]\n",
 		      intel_encoder->base.base.id, intel_encoder->base.name);
 
+	if (INTEL_GEN(dev_priv) < 12 && WARN_ON(port == PORT_A))
+		return;
+
 	if (WARN(intel_dig_port->max_lanes < 4,
 		 "Not enough lanes (%d) for HDMI on [ENCODER:%d:%s]\n",
 		 intel_dig_port->max_lanes, intel_encoder->base.base.id,
 		 intel_encoder->base.name))
 		return;
 
-	drm_connector_init(dev, connector, &intel_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port);
+	ddc = intel_gmbus_get_adapter(dev_priv, intel_hdmi->ddc_bus);
+
+	drm_connector_init_with_ddc(dev, connector,
+				    &intel_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    ddc);
 	drm_connector_helper_add(connector, &intel_hdmi_connector_helper_funcs);
 
 	connector->interlace_allowed = 1;
@@ -3154,10 +3164,6 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		connector->ycbcr_420_allowed = true;
 
-	intel_hdmi->ddc_bus = intel_hdmi_ddc_pin(dev_priv, port);
-
-	if (WARN_ON(port == PORT_A))
-		return;
 	intel_encoder->hpd_pin = intel_hpd_pin_default(dev_priv, port);
 
 	if (HAS_DDI(dev_priv))
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h
index cf1ea5427639..d3659d0b408b 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.h
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.h
@@ -29,7 +29,7 @@ void intel_hdmi_init(struct drm_i915_private *dev_priv, i915_reg_t hdmi_reg,
 		     enum port port);
 void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 			       struct intel_connector *intel_connector);
-struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder);
+struct intel_hdmi *enc_to_intel_hdmi(struct intel_encoder *encoder);
 int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state);
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index fc29046d48ea..99d3a3c7989e 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -302,7 +302,7 @@ intel_encoder_hotplug(struct intel_encoder *encoder,
 static bool intel_encoder_has_hpd_pulse(struct intel_encoder *encoder)
 {
 	return intel_encoder_is_dig_port(encoder) &&
-		enc_to_dig_port(&encoder->base)->hpd_pulse != NULL;
+		enc_to_dig_port(encoder)->hpd_pulse != NULL;
 }
 
 static void i915_digport_work_func(struct work_struct *work)
@@ -335,7 +335,7 @@ static void i915_digport_work_func(struct work_struct *work)
 		if (!long_hpd && !short_hpd)
 			continue;
 
-		dig_port = enc_to_dig_port(&encoder->base);
+		dig_port = enc_to_dig_port(encoder);
 
 		ret = dig_port->hpd_pulse(dig_port, long_hpd);
 		if (ret == IRQ_NONE) {
diff --git a/drivers/gpu/drm/i915/display/intel_lspcon.c b/drivers/gpu/drm/i915/display/intel_lspcon.c
index f8f1308643a9..d807c5648c87 100644
--- a/drivers/gpu/drm/i915/display/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/display/intel_lspcon.c
@@ -189,7 +189,7 @@ void lspcon_ycbcr420_config(struct drm_connector *connector,
 {
 	const struct drm_display_info *info = &connector->display_info;
 	const struct drm_display_mode *adjusted_mode =
-					&crtc_state->base.adjusted_mode;
+					&crtc_state->hw.adjusted_mode;
 
 	if (drm_mode_is_420_only(info, adjusted_mode) &&
 	    connector->ycbcr_420_allowed) {
@@ -434,8 +434,8 @@ void lspcon_write_infoframe(struct intel_encoder *encoder,
 			    const void *frame, ssize_t len)
 {
 	bool ret;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	struct intel_lspcon *lspcon = enc_to_intel_lspcon(&encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+	struct intel_lspcon *lspcon = enc_to_intel_lspcon(encoder);
 
 	/* LSPCON only needs AVI IF */
 	if (type != HDMI_INFOFRAME_TYPE_AVI)
@@ -472,10 +472,10 @@ void lspcon_set_infoframes(struct intel_encoder *encoder,
 	ssize_t ret;
 	union hdmi_infoframe frame;
 	u8 buf[VIDEO_DIP_DATA_SIZE];
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 	struct intel_lspcon *lspcon = &dig_port->lspcon;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 
 	if (!lspcon->active) {
 		DRM_ERROR("Writing infoframes while LSPCON disabled ?\n");
@@ -522,7 +522,7 @@ u32 lspcon_infoframes_enabled(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *pipe_config)
 {
 	/* FIXME actually read this from the hw */
-	return enc_to_intel_lspcon(&encoder->base)->active;
+	return enc_to_intel_lspcon(encoder)->active;
 }
 
 void lspcon_resume(struct intel_lspcon *lspcon)
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index b1bc78623647..10696bb99dcf 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -135,7 +135,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 	else
 		flags |= DRM_MODE_FLAG_PVSYNC;
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	if (INTEL_GEN(dev_priv) < 5)
 		pipe_config->gmch_pfit.lvds_border_bits =
@@ -148,7 +148,7 @@ static void intel_lvds_get_config(struct intel_encoder *encoder,
 		pipe_config->gmch_pfit.control |= tmp & PANEL_8TO6_DITHER_ENABLE;
 	}
 
-	pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock;
+	pipe_config->hw.adjusted_mode.crtc_clock = pipe_config->port_clock;
 }
 
 static void intel_lvds_pps_get_hw_state(struct drm_i915_private *dev_priv,
@@ -230,8 +230,8 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder,
 {
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	enum pipe pipe = crtc->pipe;
 	u32 temp;
 
@@ -392,8 +392,8 @@ static int intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 		to_lvds_encoder(&intel_encoder->base);
 	struct intel_connector *intel_connector =
 		lvds_encoder->attached_connector;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	unsigned int lvds_bpp;
 
 	/* Should never happen!! */
diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c
index 969ade623691..e59b4992ba1b 100644
--- a/drivers/gpu/drm/i915/display/intel_opregion.c
+++ b/drivers/gpu/drm/i915/display/intel_opregion.c
@@ -941,6 +941,13 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv)
 	if (mboxes & MBOX_ACPI) {
 		DRM_DEBUG_DRIVER("Public ACPI methods supported\n");
 		opregion->acpi = base + OPREGION_ACPI_OFFSET;
+		/*
+		 * Indicate we handle monitor hotplug events ourselves so we do
+		 * not need ACPI notifications for them. Disabling these avoids
+		 * triggering the AML code doing the notifation, which may be
+		 * broken as Windows also seems to disable these.
+		 */
+		opregion->acpi->chpd = 1;
 	}
 
 	if (mboxes & MBOX_SWSCI) {
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 8a98a1aa7adc..e40c3a0e2cd7 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -677,8 +677,8 @@ static void update_colorkey(struct intel_overlay *overlay,
 	if (overlay->color_key_enabled)
 		flags |= DST_KEY_ENABLE;
 
-	if (state->base.visible)
-		format = state->base.fb->format->format;
+	if (state->uapi.visible)
+		format = state->hw.fb->format->format;
 
 	switch (format) {
 	case DRM_FORMAT_C8:
@@ -767,10 +767,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 
 	atomic_inc(&dev_priv->gpu_error.pending_fb_pin);
 
-	i915_gem_object_lock(new_bo);
 	vma = i915_gem_object_pin_to_display_plane(new_bo,
 						   0, NULL, PIN_MAPPABLE);
-	i915_gem_object_unlock(new_bo);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto out_pin_section;
@@ -1335,12 +1333,14 @@ err_put_bo:
 void intel_overlay_setup(struct drm_i915_private *dev_priv)
 {
 	struct intel_overlay *overlay;
+	struct intel_engine_cs *engine;
 	int ret;
 
 	if (!HAS_OVERLAY(dev_priv))
 		return;
 
-	if (!HAS_ENGINE(dev_priv, RCS0))
+	engine = dev_priv->engine[RCS0];
+	if (!engine || !engine->kernel_context)
 		return;
 
 	overlay = kzalloc(sizeof(*overlay), GFP_KERNEL);
@@ -1348,7 +1348,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 		return;
 
 	overlay->i915 = dev_priv;
-	overlay->context = dev_priv->engine[RCS0]->kernel_context;
+	overlay->context = engine->kernel_context;
 	GEM_BUG_ON(!overlay->context);
 
 	overlay->color_key = 0x0101fe;
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index bc14e9c0285a..7b3ec6eb3382 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -178,7 +178,7 @@ intel_pch_panel_fitting(struct intel_crtc *intel_crtc,
 			struct intel_crtc_state *pipe_config,
 			int fitting_mode)
 {
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int x = 0, y = 0, width = 0, height = 0;
 
 	/* Native modes don't need fitting */
@@ -300,7 +300,7 @@ static inline u32 panel_fitter_scaling(u32 source, u32 target)
 static void i965_scale_aspect(struct intel_crtc_state *pipe_config,
 			      u32 *pfit_control)
 {
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	u32 scaled_width = adjusted_mode->crtc_hdisplay *
 		pipe_config->pipe_src_h;
 	u32 scaled_height = pipe_config->pipe_src_w *
@@ -321,7 +321,7 @@ static void i9xx_scale_aspect(struct intel_crtc_state *pipe_config,
 			      u32 *pfit_control, u32 *pfit_pgm_ratios,
 			      u32 *border)
 {
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	u32 scaled_width = adjusted_mode->crtc_hdisplay *
 		pipe_config->pipe_src_h;
 	u32 scaled_height = pipe_config->pipe_src_w *
@@ -380,7 +380,7 @@ void intel_gmch_panel_fitting(struct intel_crtc *intel_crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	u32 pfit_control = 0, pfit_pgm_ratios = 0, border = 0;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 
 	/* Native modes don't need fitting */
 	if (adjusted_mode->crtc_hdisplay == pipe_config->pipe_src_w &&
@@ -1047,7 +1047,7 @@ static void vlv_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 	u32 ctl, ctl2;
 
 	ctl2 = I915_READ(VLV_BLC_PWM_CTL2(pipe));
@@ -1077,7 +1077,7 @@ static void bxt_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 	u32 pwm_ctl, val;
 
 	/* Controller 1 uses the utility pin. */
@@ -1189,7 +1189,7 @@ void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_panel *panel = &connector->panel;
-	enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 
 	if (!panel->backlight.present)
 		return;
@@ -1840,13 +1840,22 @@ static int pwm_setup_backlight(struct intel_connector *connector,
 			       enum pipe pipe)
 {
 	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_panel *panel = &connector->panel;
+	const char *desc;
 	int retval;
 
-	/* Get the PWM chip for backlight control */
-	panel->backlight.pwm = pwm_get(dev->dev, "pwm_backlight");
+	/* Get the right PWM chip for DSI backlight according to VBT */
+	if (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC) {
+		panel->backlight.pwm = pwm_get(dev->dev, "pwm_pmic_backlight");
+		desc = "PMIC";
+	} else {
+		panel->backlight.pwm = pwm_get(dev->dev, "pwm_soc_backlight");
+		desc = "SoC";
+	}
+
 	if (IS_ERR(panel->backlight.pwm)) {
-		DRM_ERROR("Failed to own the pwm chip\n");
+		DRM_ERROR("Failed to get the %s PWM chip\n", desc);
 		panel->backlight.pwm = NULL;
 		return -ENODEV;
 	}
@@ -1873,6 +1882,7 @@ static int pwm_setup_backlight(struct intel_connector *connector,
 				 CRC_PMIC_PWM_PERIOD_NS);
 	panel->backlight.enabled = panel->backlight.level != 0;
 
+	DRM_INFO("Using %s PWM for LCD backlight control\n", desc);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_pipe_crc.c b/drivers/gpu/drm/i915/display/intel_pipe_crc.c
index 6260a2082719..520408e83681 100644
--- a/drivers/gpu/drm/i915/display/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/display/intel_pipe_crc.c
@@ -98,7 +98,7 @@ static int i9xx_pipe_crc_auto_source(struct drm_i915_private *dev_priv,
 			break;
 		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_EDP:
-			dig_port = enc_to_dig_port(&encoder->base);
+			dig_port = enc_to_dig_port(encoder);
 			switch (dig_port->base.port) {
 			case PORT_B:
 				*source = INTEL_PIPE_CRC_SOURCE_DP_B;
@@ -309,13 +309,13 @@ retry:
 		goto put_state;
 	}
 
-	pipe_config->base.mode_changed = pipe_config->has_psr;
+	pipe_config->uapi.mode_changed = pipe_config->has_psr;
 	pipe_config->crc_enabled = enable;
 
 	if (IS_HASWELL(dev_priv) &&
-	    pipe_config->base.active && crtc->pipe == PIPE_A &&
+	    pipe_config->hw.active && crtc->pipe == PIPE_A &&
 	    pipe_config->cpu_transcoder == TRANSCODER_EDP)
-		pipe_config->base.mode_changed = true;
+		pipe_config->uapi.mode_changed = true;
 
 	ret = drm_atomic_commit(state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 6a9f322d3fca..89c9cf5f38d2 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -26,6 +26,7 @@
 #include "display/intel_dp.h"
 
 #include "i915_drv.h"
+#include "intel_atomic.h"
 #include "intel_display_types.h"
 #include "intel_psr.h"
 #include "intel_sprite.h"
@@ -401,7 +402,9 @@ static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 	/* Enable ALPM at sink for psr2 */
 	if (dev_priv->psr.psr2_enabled) {
 		drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG,
-				   DP_ALPM_ENABLE);
+				   DP_ALPM_ENABLE |
+				   DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE);
+
 		dpcd_val |= DP_PSR_ENABLE_PSR2 | DP_PSR_IRQ_HPD_WITH_CRC_ERRORS;
 	} else {
 		if (dev_priv->psr.link_standby)
@@ -536,11 +539,11 @@ transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans)
 
 static u32 intel_get_frame_time_us(const struct intel_crtc_state *cstate)
 {
-	if (!cstate || !cstate->base.active)
+	if (!cstate || !cstate->hw.active)
 		return 0;
 
 	return DIV_ROUND_UP(1000 * 1000,
-			    drm_mode_vrefresh(&cstate->base.adjusted_mode));
+			    drm_mode_vrefresh(&cstate->hw.adjusted_mode));
 }
 
 static void psr2_program_idle_frames(struct drm_i915_private *dev_priv,
@@ -605,9 +608,9 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
-	int crtc_hdisplay = crtc_state->base.adjusted_mode.crtc_hdisplay;
-	int crtc_vdisplay = crtc_state->base.adjusted_mode.crtc_vdisplay;
-	int psr_max_h = 0, psr_max_v = 0;
+	int crtc_hdisplay = crtc_state->hw.adjusted_mode.crtc_hdisplay;
+	int crtc_vdisplay = crtc_state->hw.adjusted_mode.crtc_vdisplay;
+	int psr_max_h = 0, psr_max_v = 0, max_bpp = 0;
 
 	if (!dev_priv->psr.sink_psr2_support)
 		return false;
@@ -631,12 +634,15 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	if (INTEL_GEN(dev_priv) >= 12) {
 		psr_max_h = 5120;
 		psr_max_v = 3200;
+		max_bpp = 30;
 	} else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
 		psr_max_h = 4096;
 		psr_max_v = 2304;
+		max_bpp = 24;
 	} else if (IS_GEN(dev_priv, 9)) {
 		psr_max_h = 3640;
 		psr_max_v = 2304;
+		max_bpp = 24;
 	}
 
 	if (crtc_hdisplay > psr_max_h || crtc_vdisplay > psr_max_v) {
@@ -646,6 +652,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
+	if (crtc_state->pipe_bpp > max_bpp) {
+		DRM_DEBUG_KMS("PSR2 not enabled, pipe bpp %d > max supported %d\n",
+			      crtc_state->pipe_bpp, max_bpp);
+		return false;
+	}
+
 	/*
 	 * HW sends SU blocks of size four scan lines, which means the starting
 	 * X coordinate and Y granularity requirements will always be met. We
@@ -672,7 +684,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int psr_setup_time;
 
 	if (!CAN_PSR(dev_priv))
@@ -792,7 +804,7 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 
 	dev_priv->psr.psr2_enabled = intel_psr2_enabled(dev_priv, crtc_state);
 	dev_priv->psr.busy_frontbuffer_bits = 0;
-	dev_priv->psr.pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	dev_priv->psr.pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
 	dev_priv->psr.dc3co_enabled = !!crtc_state->dc3co_exitline;
 	dev_priv->psr.dc3co_exit_delay = intel_get_frame_time_us(crtc_state);
 	dev_priv->psr.transcoder = crtc_state->cpu_transcoder;
@@ -924,6 +936,9 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
 
+	if (dev_priv->psr.psr2_enabled)
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG, 0);
+
 	dev_priv->psr.enabled = false;
 }
 
@@ -1039,7 +1054,7 @@ unlock:
 int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state,
 			    u32 *out_value)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
 	if (!dev_priv->psr.enabled || !new_crtc_state->has_psr)
@@ -1096,7 +1111,7 @@ static int intel_psr_fastset_force(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = &dev_priv->drm;
 	struct drm_modeset_acquire_ctx ctx;
 	struct drm_atomic_state *state;
-	struct drm_crtc *crtc;
+	struct intel_crtc *crtc;
 	int err;
 
 	state = drm_atomic_state_alloc(dev);
@@ -1107,21 +1122,18 @@ static int intel_psr_fastset_force(struct drm_i915_private *dev_priv)
 	state->acquire_ctx = &ctx;
 
 retry:
-	drm_for_each_crtc(crtc, dev) {
-		struct drm_crtc_state *crtc_state;
-		struct intel_crtc_state *intel_crtc_state;
+	for_each_intel_crtc(dev, crtc) {
+		struct intel_crtc_state *crtc_state =
+			intel_atomic_get_crtc_state(state, crtc);
 
-		crtc_state = drm_atomic_get_crtc_state(state, crtc);
 		if (IS_ERR(crtc_state)) {
 			err = PTR_ERR(crtc_state);
 			goto error;
 		}
 
-		intel_crtc_state = to_intel_crtc_state(crtc_state);
-
-		if (crtc_state->active && intel_crtc_state->has_psr) {
+		if (crtc_state->hw.active && crtc_state->has_psr) {
 			/* Mark mode as changed to trigger a pipe->update() */
-			crtc_state->mode_changed = true;
+			crtc_state->uapi.mode_changed = true;
 			break;
 		}
 	}
@@ -1379,11 +1391,80 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	mutex_init(&dev_priv->psr.lock);
 }
 
-void intel_psr_short_pulse(struct intel_dp *intel_dp)
+static int psr_get_status_and_error_status(struct intel_dp *intel_dp,
+					   u8 *status, u8 *error_status)
+{
+	struct drm_dp_aux *aux = &intel_dp->aux;
+	int ret;
+
+	ret = drm_dp_dpcd_readb(aux, DP_PSR_STATUS, status);
+	if (ret != 1)
+		return ret;
+
+	ret = drm_dp_dpcd_readb(aux, DP_PSR_ERROR_STATUS, error_status);
+	if (ret != 1)
+		return ret;
+
+	*status = *status & DP_PSR_SINK_STATE_MASK;
+
+	return 0;
+}
+
+static void psr_alpm_check(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct drm_dp_aux *aux = &intel_dp->aux;
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 val;
+	int r;
+
+	if (!psr->psr2_enabled)
+		return;
+
+	r = drm_dp_dpcd_readb(aux, DP_RECEIVER_ALPM_STATUS, &val);
+	if (r != 1) {
+		DRM_ERROR("Error reading ALPM status\n");
+		return;
+	}
+
+	if (val & DP_ALPM_LOCK_TIMEOUT_ERROR) {
+		intel_psr_disable_locked(intel_dp);
+		psr->sink_not_reliable = true;
+		DRM_DEBUG_KMS("ALPM lock timeout error, disabling PSR\n");
+
+		/* Clearing error */
+		drm_dp_dpcd_writeb(aux, DP_RECEIVER_ALPM_STATUS, val);
+	}
+}
+
+static void psr_capability_changed_check(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 	struct i915_psr *psr = &dev_priv->psr;
 	u8 val;
+	int r;
+
+	r = drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ESI, &val);
+	if (r != 1) {
+		DRM_ERROR("Error reading DP_PSR_ESI\n");
+		return;
+	}
+
+	if (val & DP_PSR_CAPS_CHANGE) {
+		intel_psr_disable_locked(intel_dp);
+		psr->sink_not_reliable = true;
+		DRM_DEBUG_KMS("Sink PSR capability changed, disabling PSR\n");
+
+		/* Clearing it */
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ESI, val);
+	}
+}
+
+void intel_psr_short_pulse(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 status, error_status;
 	const u8 errors = DP_PSR_RFB_STORAGE_ERROR |
 			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR |
 			  DP_PSR_LINK_CRC_ERROR;
@@ -1396,38 +1477,34 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 	if (!psr->enabled || psr->dp != intel_dp)
 		goto exit;
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) != 1) {
-		DRM_ERROR("PSR_STATUS dpcd read failed\n");
+	if (psr_get_status_and_error_status(intel_dp, &status, &error_status)) {
+		DRM_ERROR("Error reading PSR status or error status\n");
 		goto exit;
 	}
 
-	if ((val & DP_PSR_SINK_STATE_MASK) == DP_PSR_SINK_INTERNAL_ERROR) {
-		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+	if (status == DP_PSR_SINK_INTERNAL_ERROR || (error_status & errors)) {
 		intel_psr_disable_locked(intel_dp);
 		psr->sink_not_reliable = true;
 	}
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ERROR_STATUS, &val) != 1) {
-		DRM_ERROR("PSR_ERROR_STATUS dpcd read failed\n");
-		goto exit;
-	}
-
-	if (val & DP_PSR_RFB_STORAGE_ERROR)
+	if (status == DP_PSR_SINK_INTERNAL_ERROR && !error_status)
+		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+	if (error_status & DP_PSR_RFB_STORAGE_ERROR)
 		DRM_DEBUG_KMS("PSR RFB storage error, disabling PSR\n");
-	if (val & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
+	if (error_status & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
 		DRM_DEBUG_KMS("PSR VSC SDP uncorrectable error, disabling PSR\n");
-	if (val & DP_PSR_LINK_CRC_ERROR)
+	if (error_status & DP_PSR_LINK_CRC_ERROR)
 		DRM_DEBUG_KMS("PSR Link CRC error, disabling PSR\n");
 
-	if (val & ~errors)
+	if (error_status & ~errors)
 		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
-			  val & ~errors);
-	if (val & errors) {
-		intel_psr_disable_locked(intel_dp);
-		psr->sink_not_reliable = true;
-	}
+			  error_status & ~errors);
 	/* clear status register */
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, val);
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, error_status);
+
+	psr_alpm_check(intel_dp);
+	psr_capability_changed_check(intel_dp);
+
 exit:
 	mutex_unlock(&psr->lock);
 }
@@ -1446,3 +1523,27 @@ bool intel_psr_enabled(struct intel_dp *intel_dp)
 
 	return ret;
 }
+
+void intel_psr_atomic_check(struct drm_connector *connector,
+			    struct drm_connector_state *old_state,
+			    struct drm_connector_state *new_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
+	struct intel_connector *intel_connector;
+	struct intel_digital_port *dig_port;
+	struct drm_crtc_state *crtc_state;
+
+	if (!CAN_PSR(dev_priv) || !new_state->crtc ||
+	    dev_priv->psr.initially_probed)
+		return;
+
+	intel_connector = to_intel_connector(connector);
+	dig_port = enc_to_dig_port(intel_connector->encoder);
+	if (dev_priv->psr.dp != &dig_port->dp)
+		return;
+
+	crtc_state = drm_atomic_get_new_crtc_state(new_state->state,
+						   new_state->crtc);
+	crtc_state->mode_changed = true;
+	dev_priv->psr.initially_probed = true;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index 46e4de8b8cd5..c58a1d438808 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -8,6 +8,8 @@
 
 #include "intel_frontbuffer.h"
 
+struct drm_connector;
+struct drm_connector_state;
 struct drm_i915_private;
 struct intel_crtc_state;
 struct intel_dp;
@@ -35,5 +37,8 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp);
 int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state,
 			    u32 *out_value);
 bool intel_psr_enabled(struct intel_dp *intel_dp);
+void intel_psr_atomic_check(struct drm_connector *connector,
+			    struct drm_connector_state *old_state,
+			    struct drm_connector_state *new_state);
 
 #endif /* __INTEL_PSR_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 5b7f4baf7348..e8819fd21e03 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -180,7 +180,7 @@ static struct intel_sdvo *to_sdvo(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_sdvo, base);
 }
 
-static struct intel_sdvo *intel_attached_sdvo(struct drm_connector *connector)
+static struct intel_sdvo *intel_attached_sdvo(struct intel_connector *connector)
 {
 	return to_sdvo(intel_attached_encoder(connector));
 }
@@ -1087,7 +1087,7 @@ static bool intel_sdvo_compute_avi_infoframe(struct intel_sdvo *intel_sdvo,
 {
 	struct hdmi_avi_infoframe *frame = &crtc_state->infoframes.avi.avi;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	int ret;
 
 	if (!crtc_state->has_hdmi_sink)
@@ -1276,8 +1276,8 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 		to_intel_sdvo_connector_state(conn_state);
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(conn_state->connector);
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	struct drm_display_mode *mode = &pipe_config->base.mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
+	struct drm_display_mode *mode = &pipe_config->hw.mode;
 
 	DRM_DEBUG_KMS("forcing bpc to 8 for SDVO\n");
 	pipe_config->pipe_bpp = 8*3;
@@ -1349,9 +1349,9 @@ static int intel_sdvo_compute_config(struct intel_encoder *encoder,
 	if (IS_TV(intel_sdvo_connector))
 		i9xx_adjust_sdvo_tv_clock(pipe_config);
 
-	/* Set user selected PAR to incoming mode's member */
-	if (intel_sdvo_connector->is_hdmi)
-		adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio;
+	if (conn_state->picture_aspect_ratio)
+		adjusted_mode->picture_aspect_ratio =
+			conn_state->picture_aspect_ratio;
 
 	if (!intel_sdvo_compute_avi_infoframe(intel_sdvo,
 					      pipe_config, conn_state)) {
@@ -1429,13 +1429,13 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder,
 				  const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode;
 	const struct intel_sdvo_connector_state *sdvo_state =
 		to_intel_sdvo_connector_state(conn_state);
 	const struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(conn_state->connector);
-	const struct drm_display_mode *mode = &crtc_state->base.mode;
+	const struct drm_display_mode *mode = &crtc_state->hw.mode;
 	struct intel_sdvo *intel_sdvo = to_sdvo(intel_encoder);
 	u32 sdvox;
 	struct intel_sdvo_in_out_map in_out;
@@ -1551,7 +1551,7 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 {
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(&connector->base);
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(&connector->base);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 	u16 active_outputs = 0;
 
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
@@ -1629,7 +1629,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 			flags |= DRM_MODE_FLAG_NVSYNC;
 	}
 
-	pipe_config->base.adjusted_mode.flags |= flags;
+	pipe_config->hw.adjusted_mode.flags |= flags;
 
 	/*
 	 * pixel multiplier readout is tricky: Only on i915g/gm it is stored in
@@ -1649,7 +1649,7 @@ static void intel_sdvo_get_config(struct intel_encoder *encoder,
 	if (pipe_config->pixel_multiplier)
 		dotclock /= pipe_config->pixel_multiplier;
 
-	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
+	pipe_config->hw.adjusted_mode.crtc_clock = dotclock;
 
 	/* Cross check the port pixel multiplier with the sdvo encoder state. */
 	if (intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_CLOCK_RATE_MULT,
@@ -1701,7 +1701,7 @@ static void intel_sdvo_enable_audio(struct intel_sdvo *intel_sdvo,
 				    const struct drm_connector_state *conn_state)
 {
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	struct drm_connector *connector = conn_state->connector;
 	u8 *eld = connector->eld;
 
@@ -1723,7 +1723,7 @@ static void intel_disable_sdvo(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	u32 temp;
 
 	if (old_crtc_state->has_audio)
@@ -1785,7 +1785,7 @@ static void intel_enable_sdvo(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	u32 temp;
 	bool input1, input2;
 	int i;
@@ -1823,7 +1823,7 @@ static enum drm_mode_status
 intel_sdvo_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(connector);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
@@ -1941,7 +1941,7 @@ intel_sdvo_multifunc_encoder(struct intel_sdvo *intel_sdvo)
 static struct edid *
 intel_sdvo_get_edid(struct drm_connector *connector)
 {
-	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	return drm_get_edid(connector, &sdvo->ddc);
 }
 
@@ -1959,7 +1959,7 @@ intel_sdvo_get_analog_edid(struct drm_connector *connector)
 static enum drm_connector_status
 intel_sdvo_tmds_sink_detect(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector =
 		to_intel_sdvo_connector(connector);
 	enum drm_connector_status status;
@@ -2028,7 +2028,7 @@ static enum drm_connector_status
 intel_sdvo_detect(struct drm_connector *connector, bool force)
 {
 	u16 response;
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
 	enum drm_connector_status ret;
 
@@ -2175,7 +2175,7 @@ static const struct drm_display_mode sdvo_tv_modes[] = {
 
 static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	const struct drm_connector_state *conn_state = connector->state;
 	struct intel_sdvo_sdtv_resolution_request tv_res;
 	u32 reply = 0, format_map = 0;
@@ -2215,7 +2215,7 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 
 static void intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 {
-	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct drm_display_mode *newmode;
 
@@ -2379,7 +2379,7 @@ intel_sdvo_connector_atomic_set_property(struct drm_connector *connector,
 static int
 intel_sdvo_connector_register(struct drm_connector *connector)
 {
-	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *sdvo = intel_attached_sdvo(to_intel_connector(connector));
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -2394,7 +2394,7 @@ intel_sdvo_connector_register(struct drm_connector *connector)
 static void
 intel_sdvo_connector_unregister(struct drm_connector *connector)
 {
-	struct intel_sdvo *sdvo = intel_attached_sdvo(connector);
+	struct intel_sdvo *sdvo = intel_attached_sdvo(to_intel_connector(connector));
 
 	sysfs_remove_link(&connector->kdev->kobj,
 			  sdvo->ddc.dev.kobj.name);
@@ -2654,7 +2654,6 @@ intel_sdvo_add_hdmi_properties(struct intel_sdvo *intel_sdvo,
 		intel_attach_broadcast_rgb_property(&connector->base.base);
 	}
 	intel_attach_aspect_ratio_property(&connector->base.base);
-	connector->base.base.state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 }
 
 static struct intel_sdvo_connector *intel_sdvo_connector_alloc(void)
@@ -2933,7 +2932,7 @@ static void intel_sdvo_output_cleanup(struct intel_sdvo *intel_sdvo)
 
 	list_for_each_entry_safe(connector, tmp,
 				 &dev->mode_config.connector_list, head) {
-		if (intel_attached_encoder(connector) == &intel_sdvo->base) {
+		if (intel_attached_encoder(to_intel_connector(connector)) == &intel_sdvo->base) {
 			drm_connector_unregister(connector);
 			intel_connector_destroy(connector);
 		}
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 72fda0430062..fca77ec1e0dd 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -81,9 +81,9 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
  */
 void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	const struct drm_display_mode *adjusted_mode = &new_crtc_state->base.adjusted_mode;
+	const struct drm_display_mode *adjusted_mode = &new_crtc_state->hw.adjusted_mode;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
 	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
@@ -120,7 +120,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 
 	crtc->debug.min_vbl = min;
 	crtc->debug.max_vbl = max;
-	trace_i915_pipe_update_start(crtc);
+	trace_intel_pipe_update_start(crtc);
 
 	for (;;) {
 		/*
@@ -173,7 +173,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	crtc->debug.start_vbl_time = ktime_get();
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
 
-	trace_i915_pipe_update_vblank_evaded(crtc);
+	trace_intel_pipe_update_vblank_evaded(crtc);
 	return;
 
 irq_disable:
@@ -190,27 +190,28 @@ irq_disable:
  */
 void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	enum pipe pipe = crtc->pipe;
 	int scanline_end = intel_get_crtc_scanline(crtc);
 	u32 end_vbl_count = intel_crtc_get_vblank_counter(crtc);
 	ktime_t end_vbl_time = ktime_get();
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end);
+	trace_intel_pipe_update_end(crtc, end_vbl_count, scanline_end);
 
 	/* We're still in the vblank-evade critical section, this can't race.
 	 * Would be slightly nice to just grab the vblank count and arm the
 	 * event outside of the critical section - the spinlock might spin for a
 	 * while ... */
-	if (new_crtc_state->base.event) {
+	if (new_crtc_state->uapi.event) {
 		WARN_ON(drm_crtc_vblank_get(&crtc->base) != 0);
 
 		spin_lock(&crtc->base.dev->event_lock);
-		drm_crtc_arm_vblank_event(&crtc->base, new_crtc_state->base.event);
+		drm_crtc_arm_vblank_event(&crtc->base,
+				          new_crtc_state->uapi.event);
 		spin_unlock(&crtc->base.dev->event_lock);
 
-		new_crtc_state->base.event = NULL;
+		new_crtc_state->uapi.event = NULL;
 	}
 
 	local_irq_enable();
@@ -239,9 +240,9 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state)
 
 int intel_plane_check_stride(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	u32 stride, max_stride;
 
 	/*
@@ -251,7 +252,7 @@ int intel_plane_check_stride(const struct intel_plane_state *plane_state)
 	 * kick in due the plane being invisible.
 	 */
 	if (intel_plane_can_remap(plane_state) &&
-	    !plane_state->base.visible)
+	    !plane_state->uapi.visible)
 		return 0;
 
 	/* FIXME other color planes? */
@@ -271,10 +272,10 @@ int intel_plane_check_stride(const struct intel_plane_state *plane_state)
 
 int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	struct drm_rect *src = &plane_state->base.src;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	struct drm_rect *src = &plane_state->uapi.src;
 	u32 src_x, src_y, src_w, src_h, hsub, vsub;
-	bool rotated = drm_rotation_90_or_270(plane_state->base.rotation);
+	bool rotated = drm_rotation_90_or_270(plane_state->hw.rotation);
 
 	/*
 	 * Hardware doesn't handle subpixel coordinates.
@@ -327,8 +328,8 @@ skl_plane_ratio(const struct intel_crtc_state *crtc_state,
 		const struct intel_plane_state *plane_state,
 		unsigned int *num, unsigned int *den)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 
 	if (fb->format->cpp[0] == 8) {
 		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
@@ -347,7 +348,7 @@ skl_plane_ratio(const struct intel_crtc_state *crtc_state,
 static int skl_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
 			       const struct intel_plane_state *plane_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
+	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
 	unsigned int pixel_rate = crtc_state->pixel_rate;
 	unsigned int src_w, src_h, dst_w, dst_h;
 	unsigned int num, den;
@@ -358,10 +359,10 @@ static int skl_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		den *= 2;
 
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->base.dst);
-	dst_h = drm_rect_height(&plane_state->base.dst);
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->uapi.dst);
+	dst_h = drm_rect_height(&plane_state->uapi.dst);
 
 	/* Downscaling limits the maximum pixel rate */
 	dst_w = min(src_w, dst_w);
@@ -395,28 +396,28 @@ skl_program_scaler(struct intel_plane *plane,
 		   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	int scaler_id = plane_state->scaler_id;
 	const struct intel_scaler *scaler =
 		&crtc_state->scaler_state.scalers[scaler_id];
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u16 y_hphase, uv_rgb_hphase;
 	u16 y_vphase, uv_rgb_vphase;
 	int hscale, vscale;
 
-	hscale = drm_rect_calc_hscale(&plane_state->base.src,
-				      &plane_state->base.dst,
+	hscale = drm_rect_calc_hscale(&plane_state->uapi.src,
+				      &plane_state->uapi.dst,
 				      0, INT_MAX);
-	vscale = drm_rect_calc_vscale(&plane_state->base.src,
-				      &plane_state->base.dst,
+	vscale = drm_rect_calc_vscale(&plane_state->uapi.src,
+				      &plane_state->uapi.dst,
 				      0, INT_MAX);
 
 	/* TODO: handle sub-pixel coordinates */
-	if (drm_format_info_is_yuv_semiplanar(fb->format) &&
+	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
 	    !icl_is_hdr_plane(dev_priv, plane->id)) {
 		y_hphase = skl_scaler_calc_phase(1, hscale, false);
 		y_vphase = skl_scaler_calc_phase(1, vscale, false);
@@ -541,10 +542,10 @@ icl_program_input_csc(struct intel_plane *plane,
 	};
 	const u16 *csc;
 
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
-		csc = input_csc_matrix[plane_state->base.color_encoding];
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+		csc = input_csc_matrix[plane_state->hw.color_encoding];
 	else
-		csc = input_csc_matrix_lr[plane_state->base.color_encoding];
+		csc = input_csc_matrix_lr[plane_state->hw.color_encoding];
 
 	I915_WRITE_FW(PLANE_INPUT_CSC_COEFF(pipe, plane_id, 0), ROFF(csc[0]) |
 		      GOFF(csc[1]));
@@ -558,7 +559,7 @@ icl_program_input_csc(struct intel_plane *plane,
 
 	I915_WRITE_FW(PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 0),
 		      PREOFF_YUV_TO_RGB_HI);
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 		I915_WRITE_FW(PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1), 0);
 	else
 		I915_WRITE_FW(PLANE_INPUT_CSC_PREOFF(pipe, plane_id, 1),
@@ -574,7 +575,7 @@ static void
 skl_program_plane(struct intel_plane *plane,
 		  const struct intel_crtc_state *crtc_state,
 		  const struct intel_plane_state *plane_state,
-		  int color_plane, bool slave, u32 plane_ctl)
+		  int color_plane)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum plane_id plane_id = plane->id;
@@ -582,19 +583,21 @@ skl_program_plane(struct intel_plane *plane,
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 surf_addr = plane_state->color_plane[color_plane].offset;
 	u32 stride = skl_plane_stride(plane_state, color_plane);
-	u32 aux_stride = skl_plane_stride(plane_state, 1);
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	int aux_plane = intel_main_to_aux_plane(fb, color_plane);
+	u32 aux_dist = plane_state->color_plane[aux_plane].offset - surf_addr;
+	u32 aux_stride = skl_plane_stride(plane_state, aux_plane);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
 	u32 x = plane_state->color_plane[color_plane].x;
 	u32 y = plane_state->color_plane[color_plane].y;
-	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	struct intel_plane *linked = plane_state->planar_linked_plane;
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	u8 alpha = plane_state->base.alpha >> 8;
+	u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	u8 alpha = plane_state->hw.alpha >> 8;
 	u32 plane_color_ctl = 0;
 	unsigned long irqflags;
 	u32 keymsk, keymax;
+	u32 plane_ctl = plane_state->ctl;
 
 	plane_ctl |= skl_plane_ctl_crtc(crtc_state);
 
@@ -623,29 +626,13 @@ skl_program_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_STRIDE(pipe, plane_id), stride);
 	I915_WRITE_FW(PLANE_POS(pipe, plane_id), (crtc_y << 16) | crtc_x);
 	I915_WRITE_FW(PLANE_SIZE(pipe, plane_id), (src_h << 16) | src_w);
-	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id),
-		      (plane_state->color_plane[1].offset - surf_addr) | aux_stride);
 
-	if (icl_is_hdr_plane(dev_priv, plane_id)) {
-		u32 cus_ctl = 0;
-
-		if (linked) {
-			/* Enable and use MPEG-2 chroma siting */
-			cus_ctl = PLANE_CUS_ENABLE |
-				PLANE_CUS_HPHASE_0 |
-				PLANE_CUS_VPHASE_SIGN_NEGATIVE |
-				PLANE_CUS_VPHASE_0_25;
-
-			if (linked->id == PLANE_SPRITE5)
-				cus_ctl |= PLANE_CUS_PLANE_7;
-			else if (linked->id == PLANE_SPRITE4)
-				cus_ctl |= PLANE_CUS_PLANE_6;
-			else
-				MISSING_CASE(linked->id);
-		}
+	if (INTEL_GEN(dev_priv) < 12)
+		aux_dist |= aux_stride;
+	I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id), aux_dist);
 
-		I915_WRITE_FW(PLANE_CUS_CTL(pipe, plane_id), cus_ctl);
-	}
+	if (icl_is_hdr_plane(dev_priv, plane_id))
+		I915_WRITE_FW(PLANE_CUS_CTL(pipe, plane_id), plane_state->cus_ctl);
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		I915_WRITE_FW(PLANE_COLOR_CTL(pipe, plane_id), plane_color_ctl);
@@ -675,7 +662,7 @@ skl_program_plane(struct intel_plane *plane,
 	I915_WRITE_FW(PLANE_SURF(pipe, plane_id),
 		      intel_plane_ggtt_offset(plane_state) + surf_addr);
 
-	if (!slave && plane_state->scaler_id >= 0)
+	if (plane_state->scaler_id >= 0)
 		skl_program_scaler(plane, crtc_state, plane_state);
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
@@ -688,24 +675,12 @@ skl_update_plane(struct intel_plane *plane,
 {
 	int color_plane = 0;
 
-	if (plane_state->planar_linked_plane) {
-		/* Program the UV plane */
+	if (plane_state->planar_linked_plane && !plane_state->planar_slave)
+		/* Program the UV plane on planar master */
 		color_plane = 1;
-	}
 
-	skl_program_plane(plane, crtc_state, plane_state,
-			  color_plane, false, plane_state->ctl);
-}
-
-static void
-icl_update_slave(struct intel_plane *plane,
-		 const struct intel_crtc_state *crtc_state,
-		 const struct intel_plane_state *plane_state)
-{
-	skl_program_plane(plane, crtc_state, plane_state, 0, true,
-			  plane_state->ctl | PLANE_CTL_YUV420_Y_PLANE);
+	skl_program_plane(plane, crtc_state, plane_state, color_plane);
 }
-
 static void
 skl_disable_plane(struct intel_plane *plane,
 		  const struct intel_crtc_state *crtc_state)
@@ -765,9 +740,9 @@ static void i9xx_plane_linear_gamma(u16 gamma[8])
 static void
 chv_update_csc(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum plane_id plane_id = plane->id;
 	/*
 	 * |r|   | c0 c1 c2 |   |cr|
@@ -793,7 +768,7 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 			    0, 4096,  7601,
 		},
 	};
-	const s16 *csc = csc_matrix[plane_state->base.color_encoding];
+	const s16 *csc = csc_matrix[plane_state->hw.color_encoding];
 
 	/* Seems RGB data bypasses the CSC always */
 	if (!fb->format->is_yuv)
@@ -824,15 +799,15 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 static void
 vlv_update_clrc(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
 	int contrast, brightness, sh_scale, sh_sin, sh_cos;
 
 	if (fb->format->is_yuv &&
-	    plane_state->base.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
+	    plane_state->hw.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
 		/*
 		 * Expand limited range to full range:
 		 * Contrast is applied first and is used to expand Y range.
@@ -866,7 +841,7 @@ vlv_plane_ratio(const struct intel_crtc_state *crtc_state,
 		unsigned int *num, unsigned int *den)
 {
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	/*
@@ -952,8 +927,8 @@ static u32 vlv_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 sprctl;
 
@@ -972,6 +947,9 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_VYUY:
 		sprctl |= SP_FORMAT_YUV422 | SP_YUV_ORDER_VYUY;
 		break;
+	case DRM_FORMAT_C8:
+		sprctl |= SP_FORMAT_8BPP;
+		break;
 	case DRM_FORMAT_RGB565:
 		sprctl |= SP_FORMAT_BGR565;
 		break;
@@ -987,6 +965,12 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_ABGR2101010:
 		sprctl |= SP_FORMAT_RGBA1010102;
 		break;
+	case DRM_FORMAT_XRGB2101010:
+		sprctl |= SP_FORMAT_BGRX1010102;
+		break;
+	case DRM_FORMAT_ARGB2101010:
+		sprctl |= SP_FORMAT_BGRA1010102;
+		break;
 	case DRM_FORMAT_XBGR8888:
 		sprctl |= SP_FORMAT_RGBX8888;
 		break;
@@ -998,7 +982,7 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 		return 0;
 	}
 
-	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+	if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 		sprctl |= SP_YUV_FORMAT_BT709;
 
 	if (fb->modifier == I915_FORMAT_MOD_X_TILED)
@@ -1018,9 +1002,9 @@ static u32 vlv_sprite_ctl(const struct intel_crtc_state *crtc_state,
 
 static void vlv_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	enum plane_id plane_id = plane->id;
 	u16 gamma[8];
@@ -1052,10 +1036,10 @@ vlv_update_plane(struct intel_plane *plane,
 	u32 sprsurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
 	unsigned long irqflags;
@@ -1150,7 +1134,7 @@ static void ivb_plane_ratio(const struct intel_crtc_state *crtc_state,
 			    unsigned int *num, unsigned int *den)
 {
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	if (hweight8(active_planes) == 2) {
@@ -1186,7 +1170,7 @@ static void ivb_plane_ratio_scaling(const struct intel_crtc_state *crtc_state,
 				    const struct intel_plane_state *plane_state,
 				    unsigned int *num, unsigned int *den)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	switch (cpp) {
@@ -1244,8 +1228,8 @@ static int ivb_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
 	 */
 	pixel_rate = crtc_state->pixel_rate;
 
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->base.dst);
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->uapi.dst);
 
 	if (src_w != dst_w)
 		ivb_plane_ratio_scaling(crtc_state, plane_state, &num, &den);
@@ -1264,7 +1248,7 @@ static void hsw_plane_ratio(const struct intel_crtc_state *crtc_state,
 			    unsigned int *num, unsigned int *den)
 {
 	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int cpp = fb->format->cpp[0];
 
 	if (hweight8(active_planes) == 2) {
@@ -1319,8 +1303,8 @@ static u32 ivb_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 static bool ivb_need_sprite_gamma(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 
 	return fb->format->cpp[0] == 8 &&
 		(IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv));
@@ -1330,9 +1314,9 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 sprctl;
 
@@ -1348,6 +1332,12 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB8888:
 		sprctl |= SPRITE_FORMAT_RGBX888;
 		break;
+	case DRM_FORMAT_XBGR2101010:
+		sprctl |= SPRITE_FORMAT_RGBX101010 | SPRITE_RGB_ORDER_RGBX;
+		break;
+	case DRM_FORMAT_XRGB2101010:
+		sprctl |= SPRITE_FORMAT_RGBX101010;
+		break;
 	case DRM_FORMAT_XBGR16161616F:
 		sprctl |= SPRITE_FORMAT_RGBX161616 | SPRITE_RGB_ORDER_RGBX;
 		break;
@@ -1374,10 +1364,10 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	if (!ivb_need_sprite_gamma(plane_state))
 		sprctl |= SPRITE_INT_GAMMA_DISABLE;
 
-	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+	if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 		sprctl |= SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709;
 
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 		sprctl |= SPRITE_YUV_RANGE_CORRECTION_DISABLE;
 
 	if (fb->modifier == I915_FORMAT_MOD_X_TILED)
@@ -1421,7 +1411,7 @@ static void ivb_sprite_linear_gamma(const struct intel_plane_state *plane_state,
 
 static void ivb_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum pipe pipe = plane->pipe;
 	u16 gamma[18];
@@ -1460,14 +1450,14 @@ ivb_update_plane(struct intel_plane *plane,
 	u32 sprsurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
-	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	u32 sprctl, sprscale = 0;
 	unsigned long irqflags;
 
@@ -1566,7 +1556,7 @@ ivb_plane_get_hw_state(struct intel_plane *plane,
 static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
 				const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	unsigned int hscale, pixel_rate;
 	unsigned int limit, decimate;
 
@@ -1580,8 +1570,8 @@ static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
 	pixel_rate = crtc_state->pixel_rate;
 
 	/* Horizontal downscaling limits the maximum pixel rate */
-	hscale = drm_rect_calc_hscale(&plane_state->base.src,
-				      &plane_state->base.dst,
+	hscale = drm_rect_calc_hscale(&plane_state->uapi.src,
+				      &plane_state->uapi.dst,
 				      0, INT_MAX);
 	if (hscale < 0x10000)
 		return pixel_rate;
@@ -1635,9 +1625,9 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+		to_i915(plane_state->uapi.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 	u32 dvscntr;
 
@@ -1653,6 +1643,12 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB8888:
 		dvscntr |= DVS_FORMAT_RGBX888;
 		break;
+	case DRM_FORMAT_XBGR2101010:
+		dvscntr |= DVS_FORMAT_RGBX101010 | DVS_RGB_ORDER_XBGR;
+		break;
+	case DRM_FORMAT_XRGB2101010:
+		dvscntr |= DVS_FORMAT_RGBX101010;
+		break;
 	case DRM_FORMAT_XBGR16161616F:
 		dvscntr |= DVS_FORMAT_RGBX161616 | DVS_RGB_ORDER_XBGR;
 		break;
@@ -1676,10 +1672,10 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 		return 0;
 	}
 
-	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
+	if (plane_state->hw.color_encoding == DRM_COLOR_YCBCR_BT709)
 		dvscntr |= DVS_YUV_FORMAT_BT709;
 
-	if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
+	if (plane_state->hw.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 		dvscntr |= DVS_YUV_RANGE_CORRECTION_DISABLE;
 
 	if (fb->modifier == I915_FORMAT_MOD_X_TILED)
@@ -1698,9 +1694,9 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 
 static void g4x_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	u16 gamma[8];
 	int i;
@@ -1730,9 +1726,9 @@ static void ilk_sprite_linear_gamma(u16 gamma[17])
 
 static void ilk_update_gamma(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum pipe pipe = plane->pipe;
 	u16 gamma[17];
 	int i;
@@ -1766,14 +1762,14 @@ g4x_update_plane(struct intel_plane *plane,
 	u32 dvssurf_offset = plane_state->color_plane[0].offset;
 	u32 linear_offset;
 	const struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_y = plane_state->base.dst.y1;
-	u32 crtc_w = drm_rect_width(&plane_state->base.dst);
-	u32 crtc_h = drm_rect_height(&plane_state->base.dst);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_y = plane_state->uapi.dst.y1;
+	u32 crtc_w = drm_rect_width(&plane_state->uapi.dst);
+	u32 crtc_h = drm_rect_height(&plane_state->uapi.dst);
 	u32 x = plane_state->color_plane[0].x;
 	u32 y = plane_state->color_plane[0].y;
-	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	u32 src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	u32 src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	u32 dvscntr, dvsscale = 0;
 	unsigned long irqflags;
 
@@ -1886,12 +1882,12 @@ static int
 g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 			 struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	const struct drm_rect *src = &plane_state->base.src;
-	const struct drm_rect *dst = &plane_state->base.dst;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	const struct drm_rect *src = &plane_state->uapi.src;
+	const struct drm_rect *dst = &plane_state->uapi.dst;
 	int src_x, src_w, src_h, crtc_w, crtc_h;
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	unsigned int stride = plane_state->color_plane[0].stride;
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int width_bytes;
@@ -1947,13 +1943,13 @@ static int
 g4x_sprite_check(struct intel_crtc_state *crtc_state,
 		 struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	int min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int max_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int ret;
 
-	if (intel_fb_scalable(plane_state->base.fb)) {
+	if (intel_fb_scalable(plane_state->hw.fb)) {
 		if (INTEL_GEN(dev_priv) < 7) {
 			min_scale = 1;
 			max_scale = 16 << 16;
@@ -1963,8 +1959,8 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 		}
 	}
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  min_scale, max_scale,
 						  true, true);
 	if (ret)
@@ -1974,7 +1970,7 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -1995,9 +1991,9 @@ g4x_sprite_check(struct intel_crtc_state *crtc_state,
 
 int chv_plane_check_rotation(const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	unsigned int rotation = plane_state->base.rotation;
+	unsigned int rotation = plane_state->hw.rotation;
 
 	/* CHV ignores the mirror bit when the rotate bit is set :( */
 	if (IS_CHERRYVIEW(dev_priv) &&
@@ -2020,8 +2016,8 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  true, true);
@@ -2032,7 +2028,7 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = intel_plane_check_src_coordinates(plane_state);
@@ -2047,10 +2043,10 @@ vlv_sprite_check(struct intel_crtc_state *crtc_state,
 static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
 	struct drm_format_name_buf format_name;
 
 	if (!fb)
@@ -2105,12 +2101,14 @@ static int skl_plane_check_fb(const struct intel_crtc_state *crtc_state,
 	}
 
 	/* Y-tiling is not supported in IF-ID Interlace mode */
-	if (crtc_state->base.enable &&
-	    crtc_state->base.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE &&
+	if (crtc_state->hw.enable &&
+	    crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE &&
 	    (fb->modifier == I915_FORMAT_MOD_Y_TILED ||
 	     fb->modifier == I915_FORMAT_MOD_Yf_TILED ||
 	     fb->modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
-	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS)) {
+	     fb->modifier == I915_FORMAT_MOD_Yf_TILED_CCS ||
+	     fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS ||
+	     fb->modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS)) {
 		DRM_DEBUG_KMS("Y/Yf tiling not supported in IF-ID mode\n");
 		return -EINVAL;
 	}
@@ -2122,9 +2120,9 @@ static int skl_plane_check_dst_coordinates(const struct intel_crtc_state *crtc_s
 					   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
-		to_i915(plane_state->base.plane->dev);
-	int crtc_x = plane_state->base.dst.x1;
-	int crtc_w = drm_rect_width(&plane_state->base.dst);
+		to_i915(plane_state->uapi.plane->dev);
+	int crtc_x = plane_state->uapi.dst.x1;
+	int crtc_w = drm_rect_width(&plane_state->uapi.dst);
 	int pipe_src_w = crtc_state->pipe_src_w;
 
 	/*
@@ -2150,12 +2148,13 @@ static int skl_plane_check_dst_coordinates(const struct intel_crtc_state *crtc_s
 
 static int skl_plane_check_nv12_rotation(const struct intel_plane_state *plane_state)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
-	unsigned int rotation = plane_state->base.rotation;
-	int src_w = drm_rect_width(&plane_state->base.src) >> 16;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	unsigned int rotation = plane_state->hw.rotation;
+	int src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
 
 	/* Display WA #1106 */
-	if (drm_format_info_is_yuv_semiplanar(fb->format) && src_w & 3 &&
+	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
+	    src_w & 3 &&
 	    (rotation == DRM_MODE_ROTATE_270 ||
 	     rotation == (DRM_MODE_REFLECT_X | DRM_MODE_ROTATE_90))) {
 		DRM_DEBUG_KMS("src width must be multiple of 4 for rotated planar YUV\n");
@@ -2175,7 +2174,7 @@ static int skl_plane_max_scale(struct drm_i915_private *dev_priv,
 	 * FIXME need to properly check this later.
 	 */
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
-	    !drm_format_info_is_yuv_semiplanar(fb->format))
+	    !intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		return 0x30000 - 1;
 	else
 		return 0x20000 - 1;
@@ -2184,9 +2183,9 @@ static int skl_plane_max_scale(struct drm_i915_private *dev_priv,
 static int skl_plane_check(struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int max_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int ret;
@@ -2201,8 +2200,8 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		max_scale = skl_plane_max_scale(dev_priv, fb);
 	}
 
-	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
-						  &crtc_state->base,
+	ret = drm_atomic_helper_check_plane_state(&plane_state->uapi,
+						  &crtc_state->uapi,
 						  min_scale, max_scale,
 						  true, true);
 	if (ret)
@@ -2212,7 +2211,7 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	ret = skl_plane_check_dst_coordinates(crtc_state, plane_state);
@@ -2228,8 +2227,8 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		return ret;
 
 	/* HW only has 8 bits pixel precision, disable plane if invisible */
-	if (!(plane_state->base.alpha >> 8))
-		plane_state->base.visible = false;
+	if (!(plane_state->hw.alpha >> 8))
+		plane_state->uapi.visible = false;
 
 	plane_state->ctl = skl_plane_ctl(crtc_state, plane_state);
 
@@ -2237,6 +2236,15 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 		plane_state->color_ctl = glk_plane_color_ctl(crtc_state,
 							     plane_state);
 
+	if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier) &&
+	    icl_is_hdr_plane(dev_priv, plane->id))
+		/* Enable and use MPEG-2 chroma siting */
+		plane_state->cus_ctl = PLANE_CUS_ENABLE |
+			PLANE_CUS_HPHASE_0 |
+			PLANE_CUS_VPHASE_SIGN_NEGATIVE | PLANE_CUS_VPHASE_0_25;
+	else
+		plane_state->cus_ctl = 0;
+
 	return 0;
 }
 
@@ -2248,7 +2256,7 @@ static bool has_dst_key_in_primary_plane(struct drm_i915_private *dev_priv)
 static void intel_plane_set_ckey(struct intel_plane_state *plane_state,
 				 const struct drm_intel_sprite_colorkey *set)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
 
@@ -2375,6 +2383,8 @@ static const u64 i9xx_plane_format_modifiers[] = {
 static const u32 snb_plane_formats[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_XBGR2101010,
 	DRM_FORMAT_XRGB16161616F,
 	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_YUYV,
@@ -2384,12 +2394,30 @@ static const u32 snb_plane_formats[] = {
 };
 
 static const u32 vlv_plane_formats[] = {
+	DRM_FORMAT_C8,
 	DRM_FORMAT_RGB565,
-	DRM_FORMAT_ABGR8888,
-	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_VYUY,
+};
+
+static const u32 chv_pipe_b_sprite_formats[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
 	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
 	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
@@ -2462,6 +2490,8 @@ static const u32 icl_sdr_y_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2483,6 +2513,8 @@ static const u32 icl_sdr_uv_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2508,6 +2540,8 @@ static const u32 icl_hdr_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_ABGR2101010,
 	DRM_FORMAT_XRGB16161616F,
 	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_ARGB16161616F,
@@ -2546,7 +2580,17 @@ static const u64 skl_plane_format_modifiers_ccs[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
-static const u64 gen12_plane_format_modifiers_noccs[] = {
+static const u64 gen12_plane_format_modifiers_mc_ccs[] = {
+	I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS,
+	I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS,
+	I915_FORMAT_MOD_Y_TILED,
+	I915_FORMAT_MOD_X_TILED,
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
+static const u64 gen12_plane_format_modifiers_rc_ccs[] = {
+	I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS,
 	I915_FORMAT_MOD_Y_TILED,
 	I915_FORMAT_MOD_X_TILED,
 	DRM_FORMAT_MOD_LINEAR,
@@ -2593,6 +2637,8 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane,
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
 	case DRM_FORMAT_XRGB16161616F:
 	case DRM_FORMAT_XBGR16161616F:
 	case DRM_FORMAT_YUYV:
@@ -2620,6 +2666,7 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
 	}
 
 	switch (format) {
+	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_ARGB8888:
@@ -2627,6 +2674,8 @@ static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR2101010:
 	case DRM_FORMAT_ABGR2101010:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_ARGB2101010:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2671,6 +2720,8 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2703,13 +2754,25 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	}
 }
 
+static bool gen12_plane_supports_mc_ccs(enum plane_id plane_id)
+{
+	return plane_id < PLANE_SPRITE4;
+}
+
 static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 					     u32 format, u64 modifier)
 {
+	struct intel_plane *plane = to_intel_plane(_plane);
+
 	switch (modifier) {
+	case I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS:
+		if (!gen12_plane_supports_mc_ccs(plane->id))
+			return false;
+		/* fall through */
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
 	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS:
 		break;
 	default:
 		return false;
@@ -2720,9 +2783,9 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_ABGR8888:
-	case DRM_FORMAT_RGB565:
-	case DRM_FORMAT_XRGB2101010:
-	case DRM_FORMAT_XBGR2101010:
+		if (is_ccs_modifier(modifier))
+			return true;
+		/* fall through */
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2731,6 +2794,14 @@ static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_P010:
 	case DRM_FORMAT_P012:
 	case DRM_FORMAT_P016:
+		if (modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS)
+			return true;
+		/* fall through */
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_ARGB2101010:
+	case DRM_FORMAT_ABGR2101010:
 	case DRM_FORMAT_XVYU2101010:
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_XBGR16161616F:
@@ -2864,6 +2935,14 @@ static const u32 *icl_get_plane_formats(struct drm_i915_private *dev_priv,
 	}
 }
 
+static const u64 *gen12_get_plane_modifiers(enum plane_id plane_id)
+{
+	if (gen12_plane_supports_mc_ccs(plane_id))
+		return gen12_plane_format_modifiers_mc_ccs;
+	else
+		return gen12_plane_format_modifiers_rc_ccs;
+}
+
 static bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 			      enum pipe pipe, enum plane_id plane_id)
 {
@@ -2916,8 +2995,6 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 	plane->get_hw_state = skl_plane_get_hw_state;
 	plane->check_plane = skl_plane_check;
 	plane->min_cdclk = skl_plane_min_cdclk;
-	if (icl_is_nv12_y_plane(plane_id))
-		plane->update_slave = icl_update_slave;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		formats = icl_get_plane_formats(dev_priv, pipe,
@@ -2929,13 +3006,11 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 		formats = skl_get_plane_formats(dev_priv, pipe,
 						plane_id, &num_formats);
 
+	plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 	if (INTEL_GEN(dev_priv) >= 12) {
-		/* TODO: Implement support for gen-12 CCS modifiers */
-		plane->has_ccs = false;
-		modifiers = gen12_plane_format_modifiers_noccs;
+		modifiers = gen12_get_plane_modifiers(plane_id);
 		plane_funcs = &gen12_plane_funcs;
 	} else {
-		plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
 		if (plane->has_ccs)
 			modifiers = skl_plane_format_modifiers_ccs;
 		else
@@ -3025,8 +3100,13 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane->check_plane = vlv_sprite_check;
 		plane->min_cdclk = vlv_plane_min_cdclk;
 
-		formats = vlv_plane_formats;
-		num_formats = ARRAY_SIZE(vlv_plane_formats);
+		if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) {
+			formats = chv_pipe_b_sprite_formats;
+			num_formats = ARRAY_SIZE(chv_pipe_b_sprite_formats);
+		} else {
+			formats = vlv_plane_formats;
+			num_formats = ARRAY_SIZE(vlv_plane_formats);
+		}
 		modifiers = i9xx_plane_format_modifiers;
 
 		plane_funcs = &vlv_sprite_funcs;
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 9983fadf6c28..c75e0ceecee6 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -898,7 +898,7 @@ static struct intel_tv *enc_to_tv(struct intel_encoder *encoder)
 	return container_of(encoder, struct intel_tv, base);
 }
 
-static struct intel_tv *intel_attached_tv(struct drm_connector *connector)
+static struct intel_tv *intel_attached_tv(struct intel_connector *connector)
 {
 	return enc_to_tv(intel_attached_encoder(connector));
 }
@@ -924,7 +924,7 @@ intel_enable_tv(struct intel_encoder *encoder,
 
 	/* Prevents vblank waits from timing out in intel_tv_detect_type() */
 	intel_wait_for_vblank(dev_priv,
-			      to_intel_crtc(pipe_config->base.crtc)->pipe);
+			      to_intel_crtc(pipe_config->uapi.crtc)->pipe);
 
 	I915_WRITE(TV_CTL, I915_READ(TV_CTL) | TV_ENC_ENABLE);
 }
@@ -1085,7 +1085,7 @@ intel_tv_get_config(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 	struct drm_display_mode mode = {};
 	u32 tv_ctl, hctl1, hctl3, vctl1, vctl2, tmp;
 	struct tv_mode tv_mode = {};
@@ -1188,7 +1188,7 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 		to_intel_tv_connector_state(conn_state);
 	const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state);
 	struct drm_display_mode *adjusted_mode =
-		&pipe_config->base.adjusted_mode;
+		&pipe_config->hw.adjusted_mode;
 	int hdisplay = adjusted_mode->crtc_hdisplay;
 	int vdisplay = adjusted_mode->crtc_vdisplay;
 
@@ -1417,7 +1417,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder,
 				const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	struct intel_tv *intel_tv = enc_to_tv(encoder);
 	const struct intel_tv_connector_state *tv_conn_state =
 		to_intel_tv_connector_state(conn_state);
@@ -1527,7 +1527,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder,
 			   ((video_levels->black << TV_BLACK_LEVEL_SHIFT) |
 			    (video_levels->blank << TV_BLANK_LEVEL_SHIFT)));
 
-	assert_pipe_disabled(dev_priv, intel_crtc->pipe);
+	assert_pipe_disabled(dev_priv, pipe_config->cpu_transcoder);
 
 	/* Filter ctl must be set before TV_WIN_SIZE */
 	tv_filter_ctl = TV_AUTO_SCALE;
@@ -1662,7 +1662,7 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
  */
 static void intel_tv_find_better_format(struct drm_connector *connector)
 {
-	struct intel_tv *intel_tv = intel_attached_tv(connector);
+	struct intel_tv *intel_tv = intel_attached_tv(to_intel_connector(connector));
 	const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
 	int i;
 
@@ -1689,7 +1689,7 @@ intel_tv_detect(struct drm_connector *connector,
 		struct drm_modeset_acquire_ctx *ctx,
 		bool force)
 {
-	struct intel_tv *intel_tv = intel_attached_tv(connector);
+	struct intel_tv *intel_tv = intel_attached_tv(to_intel_connector(connector));
 	enum drm_connector_status status;
 	int type;
 
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index 69a7cb1fa121..4d0c23b29248 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -115,6 +115,7 @@ enum bdb_block_id {
 	BDB_MIPI_CONFIG			= 52,
 	BDB_MIPI_SEQUENCE		= 53,
 	BDB_COMPRESSION_PARAMETERS	= 56,
+	BDB_GENERIC_DTD			= 58,
 	BDB_SKIP			= 254, /* VBIOS private block, ignore */
 };
 
@@ -368,7 +369,7 @@ struct child_device_config {
 			u16 dtd_buf_ptr;			/* 161 */
 			u8 edidless_efp:1;			/* 161 */
 			u8 compression_enable:1;		/* 198 */
-			u8 compression_method:1;		/* 198 */
+			u8 compression_method_cps:1;		/* 198 */
 			u8 ganged_edp:1;			/* 202 */
 			u8 reserved0:4;
 			u8 compression_structure_index:4;	/* 198 */
@@ -793,6 +794,35 @@ struct bdb_lfp_backlight_data {
 } __packed;
 
 /*
+ * Block 44 - LFP Power Conservation Features Block
+ */
+
+struct als_data_entry {
+	u16 backlight_adjust;
+	u16 lux;
+} __packed;
+
+struct agressiveness_profile_entry {
+	u8 dpst_agressiveness : 4;
+	u8 lace_agressiveness : 4;
+} __packed;
+
+struct bdb_lfp_power {
+	u8 lfp_feature_bits;
+	struct als_data_entry als[5];
+	u8 lace_aggressiveness_profile;
+	u16 dpst;
+	u16 psr;
+	u16 drrs;
+	u16 lace_support;
+	u16 adt;
+	u16 dmrrs;
+	u16 adb;
+	u16 lace_enabled_status;
+	struct agressiveness_profile_entry aggressivenes[16];
+} __packed;
+
+/*
  * Block 52 - MIPI Configuration Block
  */
 
@@ -863,4 +893,34 @@ struct bdb_compression_parameters {
 	struct dsc_compression_parameters_entry data[16];
 } __packed;
 
+/*
+ * Block 58 - Generic DTD Block
+ */
+
+struct generic_dtd_entry {
+	u32 pixel_clock;
+	u16 hactive;
+	u16 hblank;
+	u16 hfront_porch;
+	u16 hsync;
+	u16 vactive;
+	u16 vblank;
+	u16 vfront_porch;
+	u16 vsync;
+	u16 width_mm;
+	u16 height_mm;
+
+	/* Flags */
+	u8 rsvd_flags:6;
+	u8 vsync_positive_polarity:1;
+	u8 hsync_positive_polarity:1;
+
+	u8 rsvd[3];
+} __packed;
+
+struct bdb_generic_dtd {
+	u16 gdtd_size;
+	struct generic_dtd_entry dtd[];	/* up to 24 DTD's */
+} __packed;
+
 #endif /* _INTEL_VBT_DEFS_H_ */
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 896b0c334f5e..9e6aaa302e40 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -10,6 +10,7 @@
 
 #include "i915_drv.h"
 #include "intel_display_types.h"
+#include "intel_dsi.h"
 #include "intel_vdsc.h"
 
 enum ROW_INDEX_BPP {
@@ -30,10 +31,8 @@ enum COLUMN_INDEX_BPC {
 	MAX_COLUMN_INDEX
 };
 
-#define DSC_SUPPORTED_VERSION_MIN		1
-
 /* From DSC_v1.11 spec, rc_parameter_Set syntax element typically constant */
-static u16 rc_buf_thresh[] = {
+static const u16 rc_buf_thresh[] = {
 	896, 1792, 2688, 3584, 4480, 5376, 6272, 6720, 7168, 7616,
 	7744, 7872, 8000, 8064
 };
@@ -53,7 +52,7 @@ struct rc_parameters {
  * Selected Rate Control Related Parameter Recommended Values
  * from DSC_v1.11 spec & C Model release: DSC_model_20161212
  */
-static struct rc_parameters rc_params[][MAX_COLUMN_INDEX] = {
+static const struct rc_parameters rc_parameters[][MAX_COLUMN_INDEX] = {
 {
 	/* 6BPP/8BPC */
 	{ 768, 15, 6144, 3, 13, 11, 11, {
@@ -319,63 +318,84 @@ static int get_column_index_for_rc_params(u8 bits_per_component)
 	}
 }
 
-int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
-				struct intel_crtc_state *pipe_config)
+static const struct rc_parameters *get_rc_params(u16 compressed_bpp,
+						 u8 bits_per_component)
+{
+	int row_index, column_index;
+
+	row_index = get_row_index_for_rc_params(compressed_bpp);
+	if (row_index < 0)
+		return NULL;
+
+	column_index = get_column_index_for_rc_params(bits_per_component);
+	if (column_index < 0)
+		return NULL;
+
+	return &rc_parameters[row_index][column_index];
+}
+
+bool intel_dsc_source_support(struct intel_encoder *encoder,
+			      const struct intel_crtc_state *crtc_state)
+{
+	const struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(encoder->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
+
+	if (!INTEL_INFO(i915)->display.has_dsc)
+		return false;
+
+	/* On TGL, DSC is supported on all Pipes */
+	if (INTEL_GEN(i915) >= 12)
+		return true;
+
+	if (INTEL_GEN(i915) >= 10 &&
+	    (pipe != PIPE_A ||
+	     (cpu_transcoder == TRANSCODER_EDP ||
+	      cpu_transcoder == TRANSCODER_DSI_0 ||
+	      cpu_transcoder == TRANSCODER_DSI_1)))
+		return true;
+
+	return false;
+}
+
+static bool is_pipe_dsc(const struct intel_crtc_state *crtc_state)
+{
+	const struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	const struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+
+	if (INTEL_GEN(i915) >= 12)
+		return true;
+
+	if (cpu_transcoder == TRANSCODER_EDP ||
+	    cpu_transcoder == TRANSCODER_DSI_0 ||
+	    cpu_transcoder == TRANSCODER_DSI_1)
+		return false;
+
+	/* There's no pipe A DSC engine on ICL */
+	WARN_ON(crtc->pipe == PIPE_A);
+
+	return true;
+}
+
+int intel_dsc_compute_params(struct intel_encoder *encoder,
+			     struct intel_crtc_state *pipe_config)
 {
 	struct drm_dsc_config *vdsc_cfg = &pipe_config->dsc.config;
 	u16 compressed_bpp = pipe_config->dsc.compressed_bpp;
+	const struct rc_parameters *rc_params;
 	u8 i = 0;
-	int row_index = 0;
-	int column_index = 0;
-	u8 line_buf_depth = 0;
 
-	vdsc_cfg->pic_width = pipe_config->base.adjusted_mode.crtc_hdisplay;
-	vdsc_cfg->pic_height = pipe_config->base.adjusted_mode.crtc_vdisplay;
+	vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay;
+	vdsc_cfg->pic_height = pipe_config->hw.adjusted_mode.crtc_vdisplay;
 	vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width,
 					     pipe_config->dsc.slice_count);
-	/*
-	 * Slice Height of 8 works for all currently available panels. So start
-	 * with that if pic_height is an integral multiple of 8.
-	 * Eventually add logic to try multiple slice heights.
-	 */
-	if (vdsc_cfg->pic_height % 8 == 0)
-		vdsc_cfg->slice_height = 8;
-	else if (vdsc_cfg->pic_height % 4 == 0)
-		vdsc_cfg->slice_height = 4;
-	else
-		vdsc_cfg->slice_height = 2;
-
-	/* Values filled from DSC Sink DPCD */
-	vdsc_cfg->dsc_version_major =
-		(intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
-		 DP_DSC_MAJOR_MASK) >> DP_DSC_MAJOR_SHIFT;
-	vdsc_cfg->dsc_version_minor =
-		min(DSC_SUPPORTED_VERSION_MIN,
-		    (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] &
-		     DP_DSC_MINOR_MASK) >> DP_DSC_MINOR_SHIFT);
-
-	vdsc_cfg->convert_rgb = intel_dp->dsc_dpcd[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT] &
-		DP_DSC_RGB;
-
-	line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd);
-	if (!line_buf_depth) {
-		DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n");
-		return -EINVAL;
-	}
-	if (vdsc_cfg->dsc_version_minor == 2)
-		vdsc_cfg->line_buf_depth = (line_buf_depth == DSC_1_2_MAX_LINEBUF_DEPTH_BITS) ?
-			DSC_1_2_MAX_LINEBUF_DEPTH_VAL : line_buf_depth;
-	else
-		vdsc_cfg->line_buf_depth = (line_buf_depth > DSC_1_1_MAX_LINEBUF_DEPTH_BITS) ?
-			DSC_1_1_MAX_LINEBUF_DEPTH_BITS : line_buf_depth;
 
 	/* Gen 11 does not support YCbCr */
 	vdsc_cfg->simple_422 = false;
 	/* Gen 11 does not support VBR */
 	vdsc_cfg->vbr_enable = false;
-	vdsc_cfg->block_pred_enable =
-			intel_dp->dsc_dpcd[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] &
-		DP_DSC_BLK_PREDICTION_IS_SUPPORTED;
 
 	/* Gen 11 only supports integral values of bpp */
 	vdsc_cfg->bits_per_pixel = compressed_bpp << 4;
@@ -399,39 +419,29 @@ int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
 		vdsc_cfg->rc_buf_thresh[13] = 0x7D;
 	}
 
-	row_index = get_row_index_for_rc_params(compressed_bpp);
-	column_index =
-		get_column_index_for_rc_params(vdsc_cfg->bits_per_component);
-
-	if (row_index < 0 || column_index < 0)
+	rc_params = get_rc_params(compressed_bpp, vdsc_cfg->bits_per_component);
+	if (!rc_params)
 		return -EINVAL;
 
-	vdsc_cfg->first_line_bpg_offset =
-		rc_params[row_index][column_index].first_line_bpg_offset;
-	vdsc_cfg->initial_xmit_delay =
-		rc_params[row_index][column_index].initial_xmit_delay;
-	vdsc_cfg->initial_offset =
-		rc_params[row_index][column_index].initial_offset;
-	vdsc_cfg->flatness_min_qp =
-		rc_params[row_index][column_index].flatness_min_qp;
-	vdsc_cfg->flatness_max_qp =
-		rc_params[row_index][column_index].flatness_max_qp;
-	vdsc_cfg->rc_quant_incr_limit0 =
-		rc_params[row_index][column_index].rc_quant_incr_limit0;
-	vdsc_cfg->rc_quant_incr_limit1 =
-		rc_params[row_index][column_index].rc_quant_incr_limit1;
+	vdsc_cfg->first_line_bpg_offset = rc_params->first_line_bpg_offset;
+	vdsc_cfg->initial_xmit_delay = rc_params->initial_xmit_delay;
+	vdsc_cfg->initial_offset = rc_params->initial_offset;
+	vdsc_cfg->flatness_min_qp = rc_params->flatness_min_qp;
+	vdsc_cfg->flatness_max_qp = rc_params->flatness_max_qp;
+	vdsc_cfg->rc_quant_incr_limit0 = rc_params->rc_quant_incr_limit0;
+	vdsc_cfg->rc_quant_incr_limit1 = rc_params->rc_quant_incr_limit1;
 
 	for (i = 0; i < DSC_NUM_BUF_RANGES; i++) {
 		vdsc_cfg->rc_range_params[i].range_min_qp =
-			rc_params[row_index][column_index].rc_range_params[i].range_min_qp;
+			rc_params->rc_range_params[i].range_min_qp;
 		vdsc_cfg->rc_range_params[i].range_max_qp =
-			rc_params[row_index][column_index].rc_range_params[i].range_max_qp;
+			rc_params->rc_range_params[i].range_max_qp;
 		/*
 		 * Range BPG Offset uses 2's complement and is only a 6 bits. So
 		 * mask it to get only 6 bits.
 		 */
 		vdsc_cfg->rc_range_params[i].range_bpg_offset =
-			rc_params[row_index][column_index].rc_range_params[i].range_bpg_offset &
+			rc_params->rc_range_params[i].range_bpg_offset &
 			DSC_RANGE_BPG_OFFSET_MASK;
 	}
 
@@ -453,41 +463,42 @@ int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
 	vdsc_cfg->initial_scale_value = (vdsc_cfg->rc_model_size << 3) /
 		(vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset);
 
-	return drm_dsc_compute_rc_parameters(vdsc_cfg);
+	return 0;
 }
 
 enum intel_display_power_domain
 intel_dsc_power_domain(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *i915 = to_i915(crtc_state->base.crtc->dev);
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
 
 	/*
-	 * On ICL VDSC/joining for eDP transcoder uses a separate power well,
-	 * PW2. This requires POWER_DOMAIN_TRANSCODER_VDSC_PW2 power domain.
-	 * For any other transcoder, VDSC/joining uses the power well associated
-	 * with the pipe/transcoder in use. Hence another reference on the
-	 * transcoder power domain will suffice.
+	 * VDSC/joining uses a separate power well, PW2, and requires
+	 * POWER_DOMAIN_TRANSCODER_VDSC_PW2 power domain in two cases:
+	 *
+	 *  - ICL eDP/DSI transcoder
+	 *  - TGL pipe A
 	 *
-	 * On TGL we have the same mapping, but for transcoder A (the special
-	 * TRANSCODER_EDP is gone).
+	 * For any other pipe, VDSC/joining uses the power well associated with
+	 * the pipe in use. Hence another reference on the pipe power domain
+	 * will suffice. (Except no VDSC/joining on ICL pipe A.)
 	 */
-	if (INTEL_GEN(i915) >= 12 && cpu_transcoder == TRANSCODER_A)
-		return POWER_DOMAIN_TRANSCODER_VDSC_PW2;
-	else if (cpu_transcoder == TRANSCODER_EDP)
+	if (INTEL_GEN(i915) >= 12 && pipe == PIPE_A)
 		return POWER_DOMAIN_TRANSCODER_VDSC_PW2;
+	else if (is_pipe_dsc(crtc_state))
+		return POWER_DOMAIN_PIPE(pipe);
 	else
-		return POWER_DOMAIN_TRANSCODER(cpu_transcoder);
+		return POWER_DOMAIN_TRANSCODER_VDSC_PW2;
 }
 
-static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
-						const struct intel_crtc_state *crtc_state)
+static void intel_dsc_pps_configure(struct intel_encoder *encoder,
+				    const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	enum pipe pipe = crtc->pipe;
-	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 pps_val = 0;
 	u32 rc_buf_thresh_dword[4];
 	u32 rc_range_params_dword[8];
@@ -508,7 +519,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	if (vdsc_cfg->vbr_enable)
 		pps_val |= DSC_VBR_ENABLE;
 	DRM_INFO("PPS0 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_0, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -527,7 +538,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val = 0;
 	pps_val |= DSC_BPP(vdsc_cfg->bits_per_pixel);
 	DRM_INFO("PPS1 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_1, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -547,7 +558,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) |
 		DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances);
 	DRM_INFO("PPS2 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_2, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -567,7 +578,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_SLICE_HEIGHT(vdsc_cfg->slice_height) |
 		DSC_SLICE_WIDTH(vdsc_cfg->slice_width);
 	DRM_INFO("PPS3 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_3, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -587,7 +598,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_INITIAL_XMIT_DELAY(vdsc_cfg->initial_xmit_delay) |
 		DSC_INITIAL_DEC_DELAY(vdsc_cfg->initial_dec_delay);
 	DRM_INFO("PPS4 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_4, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -607,7 +618,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_SCALE_INC_INT(vdsc_cfg->scale_increment_interval) |
 		DSC_SCALE_DEC_INT(vdsc_cfg->scale_decrement_interval);
 	DRM_INFO("PPS5 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_5, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -629,7 +640,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DSC_FLATNESS_MIN_QP(vdsc_cfg->flatness_min_qp) |
 		DSC_FLATNESS_MAX_QP(vdsc_cfg->flatness_max_qp);
 	DRM_INFO("PPS6 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_6, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -649,7 +660,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_SLICE_BPG_OFFSET(vdsc_cfg->slice_bpg_offset) |
 		DSC_NFL_BPG_OFFSET(vdsc_cfg->nfl_bpg_offset);
 	DRM_INFO("PPS7 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_7, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -669,7 +680,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_FINAL_OFFSET(vdsc_cfg->final_offset) |
 		DSC_INITIAL_OFFSET(vdsc_cfg->initial_offset);
 	DRM_INFO("PPS8 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_8, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -689,7 +700,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_RC_MODEL_SIZE(DSC_RC_MODEL_SIZE_CONST) |
 		DSC_RC_EDGE_FACTOR(DSC_RC_EDGE_FACTOR_CONST);
 	DRM_INFO("PPS9 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_9, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -711,7 +722,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DSC_RC_TARGET_OFF_HIGH(DSC_RC_TGT_OFFSET_HI_CONST) |
 		DSC_RC_TARGET_OFF_LOW(DSC_RC_TGT_OFFSET_LO_CONST);
 	DRM_INFO("PPS10 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_10, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -734,7 +745,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DSC_SLICE_ROW_PER_FRAME(vdsc_cfg->pic_height /
 					vdsc_cfg->slice_height);
 	DRM_INFO("PPS16 = 0x%08x\n", pps_val);
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_16, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
@@ -758,7 +769,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DRM_INFO(" RC_BUF_THRESH%d = 0x%08x\n", i,
 			 rc_buf_thresh_dword[i / 4]);
 	}
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_RC_BUF_THRESH_0, rc_buf_thresh_dword[0]);
 		I915_WRITE(DSCA_RC_BUF_THRESH_0_UDW, rc_buf_thresh_dword[1]);
 		I915_WRITE(DSCA_RC_BUF_THRESH_1, rc_buf_thresh_dword[2]);
@@ -807,7 +818,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		DRM_INFO(" RC_RANGE_PARAM_%d = 0x%08x\n", i,
 			 rc_range_params_dword[i / 2]);
 	}
-	if (cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		I915_WRITE(DSCA_RC_RANGE_PARAMETERS_0,
 			   rc_range_params_dword[0]);
 		I915_WRITE(DSCA_RC_RANGE_PARAMETERS_0_UDW,
@@ -880,10 +891,77 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	}
 }
 
-static void intel_dp_write_dsc_pps_sdp(struct intel_encoder *encoder,
-				       const struct intel_crtc_state *crtc_state)
+void intel_dsc_get_config(struct intel_encoder *encoder,
+			  struct intel_crtc_state *crtc_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	enum pipe pipe = crtc->pipe;
+	enum intel_display_power_domain power_domain;
+	intel_wakeref_t wakeref;
+	u32 dss_ctl1, dss_ctl2, val;
+
+	if (!intel_dsc_source_support(encoder, crtc_state))
+		return;
+
+	power_domain = intel_dsc_power_domain(crtc_state);
+
+	wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain);
+	if (!wakeref)
+		return;
+
+	if (!is_pipe_dsc(crtc_state)) {
+		dss_ctl1 = I915_READ(DSS_CTL1);
+		dss_ctl2 = I915_READ(DSS_CTL2);
+	} else {
+		dss_ctl1 = I915_READ(ICL_PIPE_DSS_CTL1(pipe));
+		dss_ctl2 = I915_READ(ICL_PIPE_DSS_CTL2(pipe));
+	}
+
+	crtc_state->dsc.compression_enable = dss_ctl2 & LEFT_BRANCH_VDSC_ENABLE;
+	if (!crtc_state->dsc.compression_enable)
+		goto out;
+
+	crtc_state->dsc.dsc_split = (dss_ctl2 & RIGHT_BRANCH_VDSC_ENABLE) &&
+		(dss_ctl1 & JOINER_ENABLE);
+
+	/* FIXME: add more state readout as needed */
+
+	/* PPS1 */
+	if (!is_pipe_dsc(crtc_state))
+		val = I915_READ(DSCA_PICTURE_PARAMETER_SET_1);
+	else
+		val = I915_READ(ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe));
+	vdsc_cfg->bits_per_pixel = val;
+	crtc_state->dsc.compressed_bpp = vdsc_cfg->bits_per_pixel >> 4;
+out:
+	intel_display_power_put(dev_priv, power_domain, wakeref);
+}
+
+static void intel_dsc_dsi_pps_write(struct intel_encoder *encoder,
+				    const struct intel_crtc_state *crtc_state)
+{
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct mipi_dsi_device *dsi;
+	struct drm_dsc_picture_parameter_set pps;
+	enum port port;
+
+	drm_dsc_pps_payload_pack(&pps, vdsc_cfg);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		dsi = intel_dsi->dsi_hosts[port]->device;
+
+		mipi_dsi_picture_parameter_set(dsi, &pps);
+		mipi_dsi_compression_mode(dsi, true);
+	}
+}
+
+static void intel_dsc_dp_pps_write(struct intel_encoder *encoder,
+				   const struct intel_crtc_state *crtc_state)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	struct drm_dsc_pps_infoframe dp_dsc_pps_sdp;
@@ -902,7 +980,7 @@ static void intel_dp_write_dsc_pps_sdp(struct intel_encoder *encoder,
 void intel_dsc_enable(struct intel_encoder *encoder,
 		      const struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t dss_ctl1_reg, dss_ctl2_reg;
@@ -916,11 +994,14 @@ void intel_dsc_enable(struct intel_encoder *encoder,
 	intel_display_power_get(dev_priv,
 				intel_dsc_power_domain(crtc_state));
 
-	intel_configure_pps_for_dsc_encoder(encoder, crtc_state);
+	intel_dsc_pps_configure(encoder, crtc_state);
 
-	intel_dp_write_dsc_pps_sdp(encoder, crtc_state);
+	if (encoder->type == INTEL_OUTPUT_DSI)
+		intel_dsc_dsi_pps_write(encoder, crtc_state);
+	else
+		intel_dsc_dp_pps_write(encoder, crtc_state);
 
-	if (crtc_state->cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(crtc_state)) {
 		dss_ctl1_reg = DSS_CTL1;
 		dss_ctl2_reg = DSS_CTL2;
 	} else {
@@ -938,7 +1019,7 @@ void intel_dsc_enable(struct intel_encoder *encoder,
 
 void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	i915_reg_t dss_ctl1_reg, dss_ctl2_reg;
@@ -947,7 +1028,7 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 	if (!old_crtc_state->dsc.compression_enable)
 		return;
 
-	if (old_crtc_state->cpu_transcoder == TRANSCODER_EDP) {
+	if (!is_pipe_dsc(old_crtc_state)) {
 		dss_ctl1_reg = DSS_CTL1;
 		dss_ctl2_reg = DSS_CTL2;
 	} else {
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.h b/drivers/gpu/drm/i915/display/intel_vdsc.h
index 90d3f6017fcb..e56a3254c214 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.h
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.h
@@ -6,15 +6,20 @@
 #ifndef __INTEL_VDSC_H__
 #define __INTEL_VDSC_H__
 
+#include <linux/types.h>
+
 struct intel_encoder;
 struct intel_crtc_state;
-struct intel_dp;
 
+bool intel_dsc_source_support(struct intel_encoder *encoder,
+			      const struct intel_crtc_state *crtc_state);
 void intel_dsc_enable(struct intel_encoder *encoder,
 		      const struct intel_crtc_state *crtc_state);
 void intel_dsc_disable(const struct intel_crtc_state *crtc_state);
-int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
-				struct intel_crtc_state *pipe_config);
+int intel_dsc_compute_params(struct intel_encoder *encoder,
+			     struct intel_crtc_state *pipe_config);
+void intel_dsc_get_config(struct intel_encoder *encoder,
+			  struct intel_crtc_state *crtc_state);
 enum intel_display_power_domain
 intel_dsc_power_domain(const struct intel_crtc_state *crtc_state);
 
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 0ca49b1604c6..daf4fc3dab6f 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -23,7 +23,6 @@
  * Author: Jani Nikula <jani.nikula@intel.com>
  */
 
-#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 
 #include <drm/drm_atomic_helper.h>
@@ -261,9 +260,9 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
 						   base);
 	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
 	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	int ret;
 
 	DRM_DEBUG_KMS("\n");
@@ -319,7 +318,7 @@ static int intel_dsi_compute_config(struct intel_encoder *encoder,
 static bool glk_dsi_enable_io(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 	bool cold_boot = false;
@@ -367,7 +366,7 @@ static bool glk_dsi_enable_io(struct intel_encoder *encoder)
 static void glk_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -438,7 +437,7 @@ static void glk_dsi_device_ready(struct intel_encoder *encoder)
 static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -465,7 +464,7 @@ static void bxt_dsi_device_ready(struct intel_encoder *encoder)
 static void vlv_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -516,7 +515,7 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -546,7 +545,7 @@ static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
 static void glk_dsi_disable_mipi_io(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 tmp;
 
@@ -579,7 +578,7 @@ static void glk_dsi_clear_device_ready(struct intel_encoder *encoder)
 static void vlv_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	DRM_DEBUG_KMS("\n");
@@ -624,8 +623,8 @@ static void intel_dsi_port_enable(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
@@ -681,7 +680,7 @@ static void intel_dsi_port_disable(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	for_each_dsi_port(port, intel_dsi->ports) {
@@ -745,8 +744,8 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *pipe_config,
 				 const struct drm_connector_state *conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct drm_crtc *crtc = pipe_config->base.crtc;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct drm_crtc *crtc = pipe_config->uapi.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	enum pipe pipe = intel_crtc->pipe;
@@ -793,9 +792,6 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	if (!IS_GEMINILAKE(dev_priv))
 		intel_dsi_prepare(encoder, pipe_config);
 
-	/* Power on, try both CRC pmic gpio and VBT */
-	if (intel_dsi->gpio_panel)
-		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
 	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
 
@@ -850,7 +846,7 @@ static void intel_dsi_disable(struct intel_encoder *encoder,
 			      const struct intel_crtc_state *old_crtc_state,
 			      const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 
 	DRM_DEBUG_KMS("\n");
@@ -882,16 +878,22 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 }
 
 static void intel_dsi_post_disable(struct intel_encoder *encoder,
-				   const struct intel_crtc_state *pipe_config,
-				   const struct drm_connector_state *conn_state)
+				   const struct intel_crtc_state *old_crtc_state,
+				   const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
 	DRM_DEBUG_KMS("\n");
 
+	if (IS_GEN9_LP(dev_priv)) {
+		intel_crtc_vblank_off(old_crtc_state);
+
+		skl_scaler_disable(old_crtc_state);
+	}
+
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports)
 			vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
@@ -939,11 +941,8 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 	/* Assert reset */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
 
-	/* Power off, try both CRC pmic gpio and VBT */
 	intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF);
-	if (intel_dsi->gpio_panel)
-		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 0);
 
 	/*
 	 * FIXME As we do with eDP, just make a note of the time here
@@ -956,7 +955,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	intel_wakeref_t wakeref;
 	enum port port;
 	bool active = false;
@@ -1032,10 +1031,10 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
+					&pipe_config->hw.adjusted_mode;
 	struct drm_display_mode *adjusted_mode_sw;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	unsigned int lane_count = intel_dsi->lane_count;
 	unsigned int bpp, fmt;
 	enum port port;
@@ -1045,7 +1044,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 				crtc_hblank_start_sw, crtc_hblank_end_sw;
 
 	/* FIXME: hw readout should not depend on SW state */
-	adjusted_mode_sw = &crtc->config->base.adjusted_mode;
+	adjusted_mode_sw = &crtc->config->hw.adjusted_mode;
 
 	/*
 	 * Atleast one port is active as encoder->get_config called only if
@@ -1204,7 +1203,7 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 	}
 
 	if (pclk) {
-		pipe_config->base.adjusted_mode.crtc_clock = pclk;
+		pipe_config->hw.adjusted_mode.crtc_clock = pclk;
 		pipe_config->port_clock = pclk;
 	}
 }
@@ -1228,7 +1227,7 @@ static void set_dsi_timings(struct drm_encoder *encoder,
 {
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
 	enum port port;
 	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	unsigned int lane_count = intel_dsi->lane_count;
@@ -1315,9 +1314,9 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 	struct drm_encoder *encoder = &intel_encoder->base;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->uapi.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
+	const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode;
 	enum port port;
 	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	u32 val, tmp;
@@ -1506,7 +1505,7 @@ static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
 static void intel_dsi_unprepare(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
@@ -1533,12 +1532,9 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder)
 
 static void intel_dsi_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-
-	/* dispose of the gpios */
-	if (intel_dsi->gpio_panel)
-		gpiod_put(intel_dsi->gpio_panel);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(encoder));
 
+	intel_dsi_vbt_gpio_cleanup(intel_dsi);
 	intel_encoder_destroy(encoder);
 }
 
@@ -1819,6 +1815,7 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 	struct drm_connector *connector;
 	struct drm_display_mode *current_mode, *fixed_mode;
 	enum port port;
+	enum pipe pipe;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -1917,20 +1914,8 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 
 	vlv_dphy_param_init(intel_dsi);
 
-	/*
-	 * In case of BYT with CRC PMIC, we need to use GPIO for
-	 * Panel control.
-	 */
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
-	    (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC)) {
-		intel_dsi->gpio_panel =
-			gpiod_get(dev->dev, "panel", GPIOD_OUT_HIGH);
-
-		if (IS_ERR(intel_dsi->gpio_panel)) {
-			DRM_ERROR("Failed to own gpio for panel control\n");
-			intel_dsi->gpio_panel = NULL;
-		}
-	}
+	intel_dsi_vbt_gpio_init(intel_dsi,
+				intel_dsi_get_hw_state(intel_encoder, &pipe));
 
 	drm_connector_init(dev, connector, &intel_dsi_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
index 95f39cd0ce02..6b89e67b120f 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c
@@ -117,7 +117,7 @@ int vlv_dsi_pll_compute(struct intel_encoder *encoder,
 			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	int ret;
 	u32 dsi_clk;
 
@@ -255,7 +255,7 @@ u32 vlv_dsi_get_pclk(struct intel_encoder *encoder,
 		     struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 	u32 dsi_clock, pclk;
 	u32 pll_ctl, pll_div;
@@ -321,7 +321,7 @@ u32 bxt_dsi_get_pclk(struct intel_encoder *encoder,
 	u32 pclk;
 	u32 dsi_clk;
 	u32 dsi_ratio;
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
 
@@ -341,7 +341,7 @@ void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 temp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 
 	temp = I915_READ(MIPI_CTRL(port));
 	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
@@ -455,7 +455,7 @@ int bxt_dsi_pll_compute(struct intel_encoder *encoder,
 			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	u8 dsi_ratio, dsi_ratio_min, dsi_ratio_max;
 	u32 dsi_clk;
 
@@ -503,7 +503,7 @@ void bxt_dsi_pll_enable(struct intel_encoder *encoder,
 			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	enum port port;
 	u32 val;
 
diff --git a/drivers/gpu/drm/i915/gem/Makefile b/drivers/gpu/drm/i915/gem/Makefile
deleted file mode 100644
index 7e73aa587967..000000000000
--- a/drivers/gpu/drm/i915/gem/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
index 18ee708585a9..34be4c0ee7c5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c
@@ -27,27 +27,24 @@ static void __do_clflush(struct drm_i915_gem_object *obj)
 static int clflush_work(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
-	struct drm_i915_gem_object *obj = fetch_and_zero(&clflush->obj);
+	struct drm_i915_gem_object *obj = clflush->obj;
 	int err;
 
 	err = i915_gem_object_pin_pages(obj);
 	if (err)
-		goto put;
+		return err;
 
 	__do_clflush(obj);
 	i915_gem_object_unpin_pages(obj);
 
-put:
-	i915_gem_object_put(obj);
-	return err;
+	return 0;
 }
 
 static void clflush_release(struct dma_fence_work *base)
 {
 	struct clflush *clflush = container_of(base, typeof(*clflush), base);
 
-	if (clflush->obj)
-		i915_gem_object_put(clflush->obj);
+	i915_gem_object_put(clflush->obj);
 }
 
 static const struct dma_fence_work_ops clflush_ops = {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 42385277c684..a2e57e62af30 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -69,7 +69,10 @@
 
 #include <drm/i915_drm.h>
 
+#include "gt/gen6_ppgtt.h"
+#include "gt/intel_context.h"
 #include "gt/intel_engine_heartbeat.h"
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_lrc_reg.h"
 #include "gt/intel_ring.h"
@@ -169,12 +172,80 @@ lookup_user_engine(struct i915_gem_context *ctx,
 	return i915_gem_context_get_engine(ctx, idx);
 }
 
+static struct i915_address_space *
+context_get_vm_rcu(struct i915_gem_context *ctx)
+{
+	GEM_BUG_ON(!rcu_access_pointer(ctx->vm));
+
+	do {
+		struct i915_address_space *vm;
+
+		/*
+		 * We do not allow downgrading from full-ppgtt [to a shared
+		 * global gtt], so ctx->vm cannot become NULL.
+		 */
+		vm = rcu_dereference(ctx->vm);
+		if (!kref_get_unless_zero(&vm->ref))
+			continue;
+
+		/*
+		 * This ppgtt may have be reallocated between
+		 * the read and the kref, and reassigned to a third
+		 * context. In order to avoid inadvertent sharing
+		 * of this ppgtt with that third context (and not
+		 * src), we have to confirm that we have the same
+		 * ppgtt after passing through the strong memory
+		 * barrier implied by a successful
+		 * kref_get_unless_zero().
+		 *
+		 * Once we have acquired the current ppgtt of ctx,
+		 * we no longer care if it is released from ctx, as
+		 * it cannot be reallocated elsewhere.
+		 */
+
+		if (vm == rcu_access_pointer(ctx->vm))
+			return rcu_pointer_handoff(vm);
+
+		i915_vm_put(vm);
+	} while (1);
+}
+
+static void intel_context_set_gem(struct intel_context *ce,
+				  struct i915_gem_context *ctx)
+{
+	GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
+	RCU_INIT_POINTER(ce->gem_context, ctx);
+
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
+		ce->ring = __intel_context_ring_size(SZ_16K);
+
+	if (rcu_access_pointer(ctx->vm)) {
+		struct i915_address_space *vm;
+
+		rcu_read_lock();
+		vm = context_get_vm_rcu(ctx); /* hmm */
+		rcu_read_unlock();
+
+		i915_vm_put(ce->vm);
+		ce->vm = vm;
+	}
+
+	GEM_BUG_ON(ce->timeline);
+	if (ctx->timeline)
+		ce->timeline = intel_timeline_get(ctx->timeline);
+
+	if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
+	    intel_engine_has_semaphores(ce->engine))
+		__set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
 static void __free_engines(struct i915_gem_engines *e, unsigned int count)
 {
 	while (count--) {
 		if (!e->engines[count])
 			continue;
 
+		RCU_INIT_POINTER(e->engines[count]->gem_context, NULL);
 		intel_context_put(e->engines[count]);
 	}
 	kfree(e);
@@ -211,12 +282,14 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 		GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
 		GEM_BUG_ON(e->engines[engine->legacy_idx]);
 
-		ce = intel_context_create(ctx, engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			__free_engines(e, e->num_engines + 1);
 			return ERR_CAST(ce);
 		}
 
+		intel_context_set_gem(ce, ctx);
+
 		e->engines[engine->legacy_idx] = ce;
 		e->num_engines = max(e->num_engines, engine->legacy_idx);
 	}
@@ -236,14 +309,10 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
-	kfree(ctx->jump_whitelist);
-
 	if (ctx->timeline)
 		intel_timeline_put(ctx->timeline);
 
-	kfree(ctx->name);
 	put_pid(ctx->pid);
-
 	mutex_destroy(&ctx->mutex);
 
 	kfree_rcu(ctx, rcu);
@@ -389,15 +458,6 @@ static void kill_context(struct i915_gem_context *ctx)
 	struct intel_context *ce;
 
 	/*
-	 * If we are already banned, it was due to a guilty request causing
-	 * a reset and the entire context being evicted from the GPU.
-	 */
-	if (i915_gem_context_is_banned(ctx))
-		return;
-
-	i915_gem_context_set_banned(ctx);
-
-	/*
 	 * Map the user's engine back to the actual engines; one virtual
 	 * engine will be mapped to multiple engines, and using ctx->engine[]
 	 * the same engine may be have multiple instances in the user's map.
@@ -407,6 +467,9 @@ static void kill_context(struct i915_gem_context *ctx)
 	for_each_gem_engine(ce, __context_engines_static(ctx), it) {
 		struct intel_engine_cs *engine;
 
+		if (intel_context_set_banned(ce))
+			continue;
+
 		/*
 		 * Check the current active state of this context; if we
 		 * are currently executing on the GPU we need to evict
@@ -427,11 +490,29 @@ static void kill_context(struct i915_gem_context *ctx)
 	}
 }
 
+static void set_closed_name(struct i915_gem_context *ctx)
+{
+	char *s;
+
+	/* Replace '[]' with '<>' to indicate closed in debug prints */
+
+	s = strrchr(ctx->name, '[');
+	if (!s)
+		return;
+
+	*s = '<';
+
+	s = strchr(s + 1, ']');
+	if (s)
+		*s = '>';
+}
+
 static void context_close(struct i915_gem_context *ctx)
 {
 	struct i915_address_space *vm;
 
 	i915_gem_context_set_closed(ctx);
+	set_closed_name(ctx);
 
 	mutex_lock(&ctx->mutex);
 
@@ -529,9 +610,6 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-	ctx->jump_whitelist = NULL;
-	ctx->jump_whitelist_cmds = 0;
-
 	spin_lock(&i915->gem.contexts.lock);
 	list_add_tail(&ctx->link, &i915->gem.contexts.list);
 	spin_unlock(&i915->gem.contexts.lock);
@@ -628,7 +706,7 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 	if (HAS_FULL_PPGTT(i915)) {
 		struct i915_ppgtt *ppgtt;
 
-		ppgtt = i915_ppgtt_create(i915);
+		ppgtt = i915_ppgtt_create(&i915->gt);
 		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
@@ -661,37 +739,6 @@ i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 	return ctx;
 }
 
-static void
-destroy_kernel_context(struct i915_gem_context **ctxp)
-{
-	struct i915_gem_context *ctx;
-
-	/* Keep the context ref so that we can free it immediately ourselves */
-	ctx = i915_gem_context_get(fetch_and_zero(ctxp));
-	GEM_BUG_ON(!i915_gem_context_is_kernel(ctx));
-
-	context_close(ctx);
-	i915_gem_context_free(ctx);
-}
-
-struct i915_gem_context *
-i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio)
-{
-	struct i915_gem_context *ctx;
-
-	ctx = i915_gem_create_context(i915, 0);
-	if (IS_ERR(ctx))
-		return ctx;
-
-	i915_gem_context_clear_bannable(ctx);
-	i915_gem_context_set_persistence(ctx);
-	ctx->sched.priority = I915_USER_PRIORITY(prio);
-
-	GEM_BUG_ON(!i915_gem_context_is_kernel(ctx));
-
-	return ctx;
-}
-
 static void init_contexts(struct i915_gem_contexts *gc)
 {
 	spin_lock_init(&gc->lock);
@@ -701,41 +748,19 @@ static void init_contexts(struct i915_gem_contexts *gc)
 	init_llist_head(&gc->free_list);
 }
 
-int i915_gem_init_contexts(struct drm_i915_private *i915)
+void i915_gem_init__contexts(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *ctx;
-
-	/* Reassure ourselves we are only called once */
-	GEM_BUG_ON(i915->kernel_context);
-
 	init_contexts(&i915->gem.contexts);
-
-	/* lowest priority; idle task */
-	ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MIN);
-	if (IS_ERR(ctx)) {
-		DRM_ERROR("Failed to create default global context\n");
-		return PTR_ERR(ctx);
-	}
-	i915->kernel_context = ctx;
-
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
 			 DRIVER_CAPS(i915)->has_logical_contexts ?
 			 "logical" : "fake");
-	return 0;
 }
 
 void i915_gem_driver_release__contexts(struct drm_i915_private *i915)
 {
-	destroy_kernel_context(&i915->kernel_context);
 	flush_work(&i915->gem.contexts.free_work);
 }
 
-static int context_idr_cleanup(int id, void *p, void *data)
-{
-	context_close(p);
-	return 0;
-}
-
 static int vm_idr_cleanup(int id, void *p, void *data)
 {
 	i915_vm_put(p);
@@ -743,7 +768,8 @@ static int vm_idr_cleanup(int id, void *p, void *data)
 }
 
 static int gem_context_register(struct i915_gem_context *ctx,
-				struct drm_i915_file_private *fpriv)
+				struct drm_i915_file_private *fpriv,
+				u32 *id)
 {
 	struct i915_address_space *vm;
 	int ret;
@@ -757,24 +783,14 @@ static int gem_context_register(struct i915_gem_context *ctx,
 	mutex_unlock(&ctx->mutex);
 
 	ctx->pid = get_task_pid(current, PIDTYPE_PID);
-	ctx->name = kasprintf(GFP_KERNEL, "%s[%d]",
-			      current->comm, pid_nr(ctx->pid));
-	if (!ctx->name) {
-		ret = -ENOMEM;
-		goto err_pid;
-	}
+	snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
+		 current->comm, pid_nr(ctx->pid));
 
 	/* And finally expose ourselves to userspace via the idr */
-	mutex_lock(&fpriv->context_idr_lock);
-	ret = idr_alloc(&fpriv->context_idr, ctx, 0, 0, GFP_KERNEL);
-	mutex_unlock(&fpriv->context_idr_lock);
-	if (ret >= 0)
-		goto out;
+	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
+	if (ret)
+		put_pid(fetch_and_zero(&ctx->pid));
 
-	kfree(fetch_and_zero(&ctx->name));
-err_pid:
-	put_pid(fetch_and_zero(&ctx->pid));
-out:
 	return ret;
 }
 
@@ -784,11 +800,11 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct i915_gem_context *ctx;
 	int err;
+	u32 id;
 
-	mutex_init(&file_priv->context_idr_lock);
-	mutex_init(&file_priv->vm_idr_lock);
+	xa_init_flags(&file_priv->context_xa, XA_FLAGS_ALLOC);
 
-	idr_init(&file_priv->context_idr);
+	mutex_init(&file_priv->vm_idr_lock);
 	idr_init_base(&file_priv->vm_idr, 1);
 
 	ctx = i915_gem_create_context(i915, 0);
@@ -797,22 +813,19 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 		goto err;
 	}
 
-	err = gem_context_register(ctx, file_priv);
+	err = gem_context_register(ctx, file_priv, &id);
 	if (err < 0)
 		goto err_ctx;
 
-	GEM_BUG_ON(i915_gem_context_is_kernel(ctx));
-	GEM_BUG_ON(err > 0);
-
+	GEM_BUG_ON(id);
 	return 0;
 
 err_ctx:
 	context_close(ctx);
 err:
 	idr_destroy(&file_priv->vm_idr);
-	idr_destroy(&file_priv->context_idr);
+	xa_destroy(&file_priv->context_xa);
 	mutex_destroy(&file_priv->vm_idr_lock);
-	mutex_destroy(&file_priv->context_idr_lock);
 	return err;
 }
 
@@ -820,10 +833,12 @@ void i915_gem_context_close(struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 	struct drm_i915_private *i915 = file_priv->dev_priv;
+	struct i915_gem_context *ctx;
+	unsigned long idx;
 
-	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
-	idr_destroy(&file_priv->context_idr);
-	mutex_destroy(&file_priv->context_idr_lock);
+	xa_for_each(&file_priv->context_xa, idx, ctx)
+		context_close(ctx);
+	xa_destroy(&file_priv->context_xa);
 
 	idr_for_each(&file_priv->vm_idr, vm_idr_cleanup, NULL);
 	idr_destroy(&file_priv->vm_idr);
@@ -847,7 +862,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
 	if (args->flags)
 		return -EINVAL;
 
-	ppgtt = i915_ppgtt_create(i915);
+	ppgtt = i915_ppgtt_create(&i915->gt);
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -1012,7 +1027,7 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 		return -ENODEV;
 
 	rcu_read_lock();
-	vm = i915_vm_get(ctx->vm);
+	vm = context_get_vm_rcu(ctx);
 	rcu_read_unlock();
 
 	ret = mutex_lock_interruptible(&file_priv->vm_idr_lock);
@@ -1049,7 +1064,7 @@ static void set_ppgtt_barrier(void *data)
 
 static int emit_ppgtt_update(struct i915_request *rq, void *data)
 {
-	struct i915_address_space *vm = rq->hw_context->vm;
+	struct i915_address_space *vm = rq->context->vm;
 	struct intel_engine_cs *engine = rq->engine;
 	u32 base = engine->mmio_base;
 	u32 *cs;
@@ -1096,9 +1111,6 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 		}
 		*cs++ = MI_NOOP;
 		intel_ring_advance(rq, cs);
-	} else {
-		/* ppGTT is not part of the legacy context image */
-		gen6_ppgtt_pin(i915_vm_to_ppgtt(vm));
 	}
 
 	return 0;
@@ -1106,10 +1118,20 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 
 static bool skip_ppgtt_update(struct intel_context *ce, void *data)
 {
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))
+		return true;
+
 	if (HAS_LOGICAL_RING_CONTEXTS(ce->engine->i915))
-		return !ce->state;
-	else
-		return !atomic_read(&ce->pin_count);
+		return false;
+
+	if (!atomic_read(&ce->pin_count))
+		return true;
+
+	/* ppGTT is not part of the legacy context image */
+	if (gen6_ppgtt_pin(i915_vm_to_ppgtt(ce->vm)))
+		return true;
+
+	return false;
 }
 
 static int set_ppgtt(struct drm_i915_file_private *file_priv,
@@ -1214,12 +1236,14 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 	 * image, or into the registers directory, does not stick). Pristine
 	 * and idle contexts will be configured on pinning.
 	 */
-	if (!intel_context_is_pinned(ce))
+	if (!intel_context_pin_if_active(ce))
 		return 0;
 
-	rq = i915_request_create(ce->engine->kernel_context);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
+	rq = intel_engine_create_kernel_request(ce->engine);
+	if (IS_ERR(rq)) {
+		ret = PTR_ERR(rq);
+		goto out_unpin;
+	}
 
 	/* Serialise with the remote context */
 	ret = intel_context_prepare_remote_request(ce, rq);
@@ -1227,6 +1251,8 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 		ret = gen8_emit_rpcs_config(rq, ce, sseu);
 
 	i915_request_add(rq);
+out_unpin:
+	intel_context_unpin(ce);
 	return ret;
 }
 
@@ -1485,12 +1511,14 @@ set_engines__load_balance(struct i915_user_extension __user *base, void *data)
 		}
 	}
 
-	ce = intel_execlists_create_virtual(set->ctx, siblings, n);
+	ce = intel_execlists_create_virtual(siblings, n);
 	if (IS_ERR(ce)) {
 		err = PTR_ERR(ce);
 		goto out_siblings;
 	}
 
+	intel_context_set_gem(ce, set->ctx);
+
 	if (cmpxchg(&set->engines->engines[idx], NULL, ce)) {
 		intel_context_put(ce);
 		err = -EEXIST;
@@ -1660,12 +1688,14 @@ set_engines(struct i915_gem_context *ctx,
 			return -ENOENT;
 		}
 
-		ce = intel_context_create(ctx, engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			__free_engines(set.engines, n);
 			return PTR_ERR(ce);
 		}
 
+		intel_context_set_gem(ce, ctx);
+
 		set.engines->engines[n] = ce;
 	}
 	set.engines->num_engines = num_engines;
@@ -1806,6 +1836,44 @@ set_persistence(struct i915_gem_context *ctx,
 	return __context_set_persistence(ctx, args->value);
 }
 
+static void __apply_priority(struct intel_context *ce, void *arg)
+{
+	struct i915_gem_context *ctx = arg;
+
+	if (!intel_engine_has_semaphores(ce->engine))
+		return;
+
+	if (ctx->sched.priority >= I915_PRIORITY_NORMAL)
+		intel_context_set_use_semaphores(ce);
+	else
+		intel_context_clear_use_semaphores(ce);
+}
+
+static int set_priority(struct i915_gem_context *ctx,
+			const struct drm_i915_gem_context_param *args)
+{
+	s64 priority = args->value;
+
+	if (args->size)
+		return -EINVAL;
+
+	if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
+		return -ENODEV;
+
+	if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
+	    priority < I915_CONTEXT_MIN_USER_PRIORITY)
+		return -EINVAL;
+
+	if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
+	    !capable(CAP_SYS_NICE))
+		return -EPERM;
+
+	ctx->sched.priority = I915_USER_PRIORITY(priority);
+	context_apply_all(ctx, __apply_priority, ctx);
+
+	return 0;
+}
+
 static int ctx_setparam(struct drm_i915_file_private *fpriv,
 			struct i915_gem_context *ctx,
 			struct drm_i915_gem_context_param *args)
@@ -1852,23 +1920,7 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		break;
 
 	case I915_CONTEXT_PARAM_PRIORITY:
-		{
-			s64 priority = args->value;
-
-			if (args->size)
-				ret = -EINVAL;
-			else if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
-				ret = -ENODEV;
-			else if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
-				 priority < I915_CONTEXT_MIN_USER_PRIORITY)
-				ret = -EINVAL;
-			else if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
-				 !capable(CAP_SYS_NICE))
-				ret = -EPERM;
-			else
-				ctx->sched.priority =
-					I915_USER_PRIORITY(priority);
-		}
+		ret = set_priority(ctx, args);
 		break;
 
 	case I915_CONTEXT_PARAM_SSEU:
@@ -1948,20 +2000,23 @@ static int clone_engines(struct i915_gem_context *dst,
 		 */
 		if (intel_engine_is_virtual(engine))
 			clone->engines[n] =
-				intel_execlists_clone_virtual(dst, engine);
+				intel_execlists_clone_virtual(engine);
 		else
-			clone->engines[n] = intel_context_create(dst, engine);
+			clone->engines[n] = intel_context_create(engine);
 		if (IS_ERR_OR_NULL(clone->engines[n])) {
 			__free_engines(clone, n);
 			goto err_unlock;
 		}
+
+		intel_context_set_gem(clone->engines[n], dst);
 	}
 	clone->num_engines = n;
 
 	user_engines = i915_gem_context_user_engines(src);
 	i915_gem_context_unlock_engines(src);
 
-	free_engines(dst->engines);
+	/* Serialised by constructor */
+	free_engines(__context_engines_static(dst));
 	RCU_INIT_POINTER(dst->engines, clone);
 	if (user_engines)
 		i915_gem_context_set_user_engines(dst);
@@ -1996,7 +2051,8 @@ static int clone_sseu(struct i915_gem_context *dst,
 	unsigned long n;
 	int err;
 
-	clone = dst->engines; /* no locking required; sole access */
+	/* no locking required; sole access under constructor*/
+	clone = __context_engines_static(dst);
 	if (e->num_engines != clone->num_engines) {
 		err = -EINVAL;
 		goto unlock;
@@ -2041,47 +2097,21 @@ static int clone_vm(struct i915_gem_context *dst,
 	struct i915_address_space *vm;
 	int err = 0;
 
-	rcu_read_lock();
-	do {
-		vm = rcu_dereference(src->vm);
-		if (!vm)
-			break;
-
-		if (!kref_get_unless_zero(&vm->ref))
-			continue;
-
-		/*
-		 * This ppgtt may have be reallocated between
-		 * the read and the kref, and reassigned to a third
-		 * context. In order to avoid inadvertent sharing
-		 * of this ppgtt with that third context (and not
-		 * src), we have to confirm that we have the same
-		 * ppgtt after passing through the strong memory
-		 * barrier implied by a successful
-		 * kref_get_unless_zero().
-		 *
-		 * Once we have acquired the current ppgtt of src,
-		 * we no longer care if it is released from src, as
-		 * it cannot be reallocated elsewhere.
-		 */
-
-		if (vm == rcu_access_pointer(src->vm))
-			break;
+	if (!rcu_access_pointer(src->vm))
+		return 0;
 
-		i915_vm_put(vm);
-	} while (1);
+	rcu_read_lock();
+	vm = context_get_vm_rcu(src);
 	rcu_read_unlock();
 
-	if (vm) {
-		if (!mutex_lock_interruptible(&dst->mutex)) {
-			__assign_ppgtt(dst, vm);
-			mutex_unlock(&dst->mutex);
-		} else {
-			err = -EINTR;
-		}
-		i915_vm_put(vm);
+	if (!mutex_lock_interruptible(&dst->mutex)) {
+		__assign_ppgtt(dst, vm);
+		mutex_unlock(&dst->mutex);
+	} else {
+		err = -EINTR;
 	}
 
+	i915_vm_put(vm);
 	return err;
 }
 
@@ -2153,6 +2183,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_context_create_ext *args = data;
 	struct create_ext ext_data;
 	int ret;
+	u32 id;
 
 	if (!DRIVER_CAPS(i915)->has_logical_contexts)
 		return -ENODEV;
@@ -2184,11 +2215,11 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 			goto err_ctx;
 	}
 
-	ret = gem_context_register(ext_data.ctx, ext_data.fpriv);
+	ret = gem_context_register(ext_data.ctx, ext_data.fpriv, &id);
 	if (ret < 0)
 		goto err_ctx;
 
-	args->ctx_id = ret;
+	args->ctx_id = id;
 	DRM_DEBUG("HW context %d created\n", args->ctx_id);
 
 	return 0;
@@ -2211,11 +2242,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	if (!args->ctx_id)
 		return -ENOENT;
 
-	if (mutex_lock_interruptible(&file_priv->context_idr_lock))
-		return -EINTR;
-
-	ctx = idr_remove(&file_priv->context_idr, args->ctx_id);
-	mutex_unlock(&file_priv->context_idr_lock);
+	ctx = xa_erase(&file_priv->context_xa, args->ctx_id);
 	if (!ctx)
 		return -ENOENT;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 18e50a769a6e..3ae61a355d87 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -13,7 +13,6 @@
 
 #include "i915_drv.h"
 #include "i915_gem.h"
-#include "i915_gem_gtt.h"
 #include "i915_scheduler.h"
 #include "intel_device_info.h"
 
@@ -91,26 +90,6 @@ static inline void i915_gem_context_clear_persistence(struct i915_gem_context *c
 	clear_bit(UCONTEXT_PERSISTENCE, &ctx->user_flags);
 }
 
-static inline bool i915_gem_context_is_banned(const struct i915_gem_context *ctx)
-{
-	return test_bit(CONTEXT_BANNED, &ctx->flags);
-}
-
-static inline void i915_gem_context_set_banned(struct i915_gem_context *ctx)
-{
-	set_bit(CONTEXT_BANNED, &ctx->flags);
-}
-
-static inline bool i915_gem_context_force_single_submission(const struct i915_gem_context *ctx)
-{
-	return test_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ctx->flags);
-}
-
-static inline void i915_gem_context_set_force_single_submission(struct i915_gem_context *ctx)
-{
-	__set_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ctx->flags);
-}
-
 static inline bool
 i915_gem_context_user_engines(const struct i915_gem_context *ctx)
 {
@@ -129,31 +108,8 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx)
 	clear_bit(CONTEXT_USER_ENGINES, &ctx->flags);
 }
 
-static inline bool
-i915_gem_context_nopreempt(const struct i915_gem_context *ctx)
-{
-	return test_bit(CONTEXT_NOPREEMPT, &ctx->flags);
-}
-
-static inline void
-i915_gem_context_set_nopreempt(struct i915_gem_context *ctx)
-{
-	set_bit(CONTEXT_NOPREEMPT, &ctx->flags);
-}
-
-static inline void
-i915_gem_context_clear_nopreempt(struct i915_gem_context *ctx)
-{
-	clear_bit(CONTEXT_NOPREEMPT, &ctx->flags);
-}
-
-static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
-{
-	return !ctx->file_priv;
-}
-
 /* i915_gem_context.c */
-int __must_check i915_gem_init_contexts(struct drm_i915_private *i915);
+void i915_gem_init__contexts(struct drm_i915_private *i915);
 void i915_gem_driver_release__contexts(struct drm_i915_private *i915);
 
 int i915_gem_context_open(struct drm_i915_private *i915,
@@ -178,9 +134,6 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data,
 				       struct drm_file *file);
 
-struct i915_gem_context *
-i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio);
-
 static inline struct i915_gem_context *
 i915_gem_context_get(struct i915_gem_context *ctx)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 3870dd5daaa0..017ca803ab47 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -100,15 +100,6 @@ struct i915_gem_context {
 	 */
 	struct pid *pid;
 
-	/**
-	 * @name: arbitrary name
-	 *
-	 * A name is constructed for the context from the creator's process
-	 * name, pid and user handle in order to uniquely identify the
-	 * context in messages.
-	 */
-	const char *name;
-
 	/** link: place with &drm_i915_private.context_list */
 	struct list_head link;
 	struct llist_node free_link;
@@ -143,11 +134,8 @@ struct i915_gem_context {
 	 * @flags: small set of booleans
 	 */
 	unsigned long flags;
-#define CONTEXT_BANNED			0
-#define CONTEXT_CLOSED			1
-#define CONTEXT_FORCE_SINGLE_SUBMISSION	2
-#define CONTEXT_USER_ENGINES		3
-#define CONTEXT_NOPREEMPT		4
+#define CONTEXT_CLOSED			0
+#define CONTEXT_USER_ENGINES		1
 
 	struct mutex mutex;
 
@@ -177,12 +165,14 @@ struct i915_gem_context {
 	 */
 	struct radix_tree_root handles_vma;
 
-	/** jump_whitelist: Bit array for tracking cmds during cmdparsing
-	 *  Guarded by struct_mutex
+	/**
+	 * @name: arbitrary name, used for user debug
+	 *
+	 * A name is constructed for the context from the creator's process
+	 * name, pid and user handle in order to uniquely identify the
+	 * context in messages.
 	 */
-	unsigned long *jump_whitelist;
-	/** jump_whitelist_cmds: No of cmd slots available */
-	u32 jump_whitelist_cmds;
+	char name[TASK_COMM_LEN + 8];
 };
 
 #endif /* __I915_GEM_CONTEXT_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index eaea49d08eb5..372b57ca0efc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -93,40 +93,6 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	i915_gem_object_unpin_map(obj);
 }
 
-static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
-	struct page *page;
-
-	if (page_num >= obj->base.size >> PAGE_SHIFT)
-		return NULL;
-
-	if (!i915_gem_object_has_struct_page(obj))
-		return NULL;
-
-	if (i915_gem_object_pin_pages(obj))
-		return NULL;
-
-	/* Synchronisation is left to the caller (via .begin_cpu_access()) */
-	page = i915_gem_object_get_page(obj, page_num);
-	if (IS_ERR(page))
-		goto err_unpin;
-
-	return kmap(page);
-
-err_unpin:
-	i915_gem_object_unpin_pages(obj);
-	return NULL;
-}
-
-static void i915_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
-
-	kunmap(virt_to_page(addr));
-	i915_gem_object_unpin_pages(obj);
-}
-
 static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
@@ -195,8 +161,6 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.map_dma_buf = i915_gem_map_dma_buf,
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
-	.map = i915_gem_dmabuf_kmap,
-	.unmap = i915_gem_dmabuf_kunmap,
 	.mmap = i915_gem_dmabuf_mmap,
 	.vmap = i915_gem_dmabuf_vmap,
 	.vunmap = i915_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index f86400a191b0..0cc40e77bbd2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -12,6 +12,8 @@
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
 #include "i915_vma.h"
+#include "i915_gem_lmem.h"
+#include "i915_gem_mman.h"
 
 static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
 {
@@ -148,9 +150,17 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 	GEM_BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
 	obj->read_domains |= I915_GEM_DOMAIN_GTT;
 	if (write) {
+		struct i915_vma *vma;
+
 		obj->read_domains = I915_GEM_DOMAIN_GTT;
 		obj->write_domain = I915_GEM_DOMAIN_GTT;
 		obj->mm.dirty = true;
+
+		spin_lock(&obj->vma.lock);
+		for_each_ggtt_vma(vma, obj)
+			if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+				i915_vma_set_ggtt_write(vma);
+		spin_unlock(&obj->vma.lock);
 	}
 
 	i915_gem_object_unpin_pages(obj);
@@ -175,138 +185,34 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 				    enum i915_cache_level cache_level)
 {
-	struct i915_vma *vma;
 	int ret;
 
-	assert_object_held(obj);
-
 	if (obj->cache_level == cache_level)
 		return 0;
 
-	/* Inspect the list of currently bound VMA and unbind any that would
-	 * be invalid given the new cache-level. This is principally to
-	 * catch the issue of the CS prefetch crossing page boundaries and
-	 * reading an invalid PTE on older architectures.
-	 */
-restart:
-	list_for_each_entry(vma, &obj->vma.list, obj_link) {
-		if (!drm_mm_node_allocated(&vma->node))
-			continue;
-
-		if (i915_vma_is_pinned(vma)) {
-			DRM_DEBUG("can not change the cache level of pinned objects\n");
-			return -EBUSY;
-		}
-
-		if (!i915_vma_is_closed(vma) &&
-		    i915_gem_valid_gtt_space(vma, cache_level))
-			continue;
-
-		ret = i915_vma_unbind(vma);
-		if (ret)
-			return ret;
-
-		/* As unbinding may affect other elements in the
-		 * obj->vma_list (due to side-effects from retiring
-		 * an active vma), play safe and restart the iterator.
-		 */
-		goto restart;
-	}
+	ret = i915_gem_object_wait(obj,
+				   I915_WAIT_INTERRUPTIBLE |
+				   I915_WAIT_ALL,
+				   MAX_SCHEDULE_TIMEOUT);
+	if (ret)
+		return ret;
 
-	/* We can reuse the existing drm_mm nodes but need to change the
-	 * cache-level on the PTE. We could simply unbind them all and
-	 * rebind with the correct cache-level on next use. However since
-	 * we already have a valid slot, dma mapping, pages etc, we may as
-	 * rewrite the PTE in the belief that doing so tramples upon less
-	 * state and so involves less work.
-	 */
-	if (atomic_read(&obj->bind_count)) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	ret = i915_gem_object_lock_interruptible(obj);
+	if (ret)
+		return ret;
 
-		/* Before we change the PTE, the GPU must not be accessing it.
-		 * If we wait upon the object, we know that all the bound
-		 * VMA are no longer active.
-		 */
-		ret = i915_gem_object_wait(obj,
-					   I915_WAIT_INTERRUPTIBLE |
-					   I915_WAIT_ALL,
-					   MAX_SCHEDULE_TIMEOUT);
-		if (ret)
-			return ret;
-
-		if (!HAS_LLC(i915) && cache_level != I915_CACHE_NONE) {
-			intel_wakeref_t wakeref =
-				intel_runtime_pm_get(&i915->runtime_pm);
-
-			/*
-			 * Access to snoopable pages through the GTT is
-			 * incoherent and on some machines causes a hard
-			 * lockup. Relinquish the CPU mmaping to force
-			 * userspace to refault in the pages and we can
-			 * then double check if the GTT mapping is still
-			 * valid for that pointer access.
-			 */
-			ret = mutex_lock_interruptible(&i915->ggtt.vm.mutex);
-			if (ret) {
-				intel_runtime_pm_put(&i915->runtime_pm,
-						     wakeref);
-				return ret;
-			}
-
-			if (obj->userfault_count)
-				__i915_gem_object_release_mmap(obj);
-
-			/*
-			 * As we no longer need a fence for GTT access,
-			 * we can relinquish it now (and so prevent having
-			 * to steal a fence from someone else on the next
-			 * fence request). Note GPU activity would have
-			 * dropped the fence as all snoopable access is
-			 * supposed to be linear.
-			 */
-			for_each_ggtt_vma(vma, obj) {
-				ret = i915_vma_revoke_fence(vma);
-				if (ret)
-					break;
-			}
-			mutex_unlock(&i915->ggtt.vm.mutex);
-			intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-			if (ret)
-				return ret;
-		} else {
-			/*
-			 * We either have incoherent backing store and
-			 * so no GTT access or the architecture is fully
-			 * coherent. In such cases, existing GTT mmaps
-			 * ignore the cache bit in the PTE and we can
-			 * rewrite it without confusing the GPU or having
-			 * to force userspace to fault back in its mmaps.
-			 */
-		}
-
-		list_for_each_entry(vma, &obj->vma.list, obj_link) {
-			if (!drm_mm_node_allocated(&vma->node))
-				continue;
-
-			/* Wait for an earlier async bind, need to rewrite it */
-			ret = i915_vma_sync(vma);
-			if (ret)
-				return ret;
-
-			ret = i915_vma_bind(vma, cache_level, PIN_UPDATE, NULL);
-			if (ret)
-				return ret;
-		}
+	/* Always invalidate stale cachelines */
+	if (obj->cache_level != cache_level) {
+		i915_gem_object_set_cache_coherency(obj, cache_level);
+		obj->cache_dirty = true;
 	}
 
-	list_for_each_entry(vma, &obj->vma.list, obj_link) {
-		if (i915_vm_has_cache_coloring(vma->vm))
-			vma->node.color = cache_level;
-	}
-	i915_gem_object_set_cache_coherency(obj, cache_level);
-	obj->cache_dirty = true; /* Always invalidate stale cachelines */
+	i915_gem_object_unlock(obj);
 
-	return 0;
+	/* The cache-level will be applied when each vma is rebound. */
+	return i915_gem_object_unbind(obj,
+				      I915_GEM_OBJECT_UNBIND_ACTIVE |
+				      I915_GEM_OBJECT_UNBIND_BARRIER);
 }
 
 int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
@@ -387,20 +293,7 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	if (obj->cache_level == level)
-		goto out;
-
-	ret = i915_gem_object_wait(obj,
-				   I915_WAIT_INTERRUPTIBLE,
-				   MAX_SCHEDULE_TIMEOUT);
-	if (ret)
-		goto out;
-
-	ret = i915_gem_object_lock_interruptible(obj);
-	if (ret == 0) {
-		ret = i915_gem_object_set_cache_level(obj, level);
-		i915_gem_object_unlock(obj);
-	}
+	ret = i915_gem_object_set_cache_level(obj, level);
 
 out:
 	i915_gem_object_put(obj);
@@ -419,10 +312,13 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 				     const struct i915_ggtt_view *view,
 				     unsigned int flags)
 {
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 	int ret;
 
-	assert_object_held(obj);
+	/* Frame buffer must be in LMEM (no migration yet) */
+	if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj))
+		return ERR_PTR(-EINVAL);
 
 	/*
 	 * The display engine is not coherent with the LLC cache on gen6.  As
@@ -435,7 +331,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * with that bit in the PTE to main memory with just one PIPE_CONTROL.
 	 */
 	ret = i915_gem_object_set_cache_level(obj,
-					      HAS_WT(to_i915(obj->base.dev)) ?
+					      HAS_WT(i915) ?
 					      I915_CACHE_WT : I915_CACHE_NONE);
 	if (ret)
 		return ERR_PTR(ret);
@@ -462,13 +358,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
-	__i915_gem_object_flush_for_display(obj);
-
-	/*
-	 * It should now be out of any other write domains, and we can update
-	 * the domain values for our changes.
-	 */
-	obj->read_domains |= I915_GEM_DOMAIN_GTT;
+	i915_gem_object_flush_if_display(obj);
 
 	return vma;
 }
@@ -479,8 +369,11 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 
 	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+	if (!atomic_read(&obj->bind_count))
+		return;
 
 	mutex_lock(&i915->ggtt.vm.mutex);
+	spin_lock(&obj->vma.lock);
 	for_each_ggtt_vma(vma, obj) {
 		if (!drm_mm_node_allocated(&vma->node))
 			continue;
@@ -488,6 +381,7 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 		GEM_BUG_ON(vma->vm != &i915->ggtt.vm);
 		list_move_tail(&vma->vm_link, &vma->vm->bound_list);
 	}
+	spin_unlock(&obj->vma.lock);
 	mutex_unlock(&i915->ggtt.vm.mutex);
 
 	if (i915_gem_object_is_shrinkable(obj)) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index bc3a67226163..d5a0f5ae4a8b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,6 +25,7 @@
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
+#include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 
 enum {
@@ -228,6 +229,7 @@ struct i915_execbuffer {
 
 	struct i915_request *request; /** our request to build */
 	struct i915_vma *batch; /** identity of the batch obj/vma */
+	struct i915_vma *trampoline; /** trampoline used for chaining */
 
 	/** actual size of execobj[] as we may extend it for the cmdparser */
 	unsigned int buffer_count;
@@ -253,7 +255,6 @@ struct i915_execbuffer {
 		bool has_fence : 1;
 		bool needs_unfenced : 1;
 
-		struct intel_context *ce;
 		struct i915_request *rq;
 		u32 *rq_cmd;
 		unsigned int rq_size;
@@ -277,25 +278,6 @@ struct i915_execbuffer {
 
 #define exec_entry(EB, VMA) (&(EB)->exec[(VMA)->exec_flags - (EB)->flags])
 
-/*
- * Used to convert any address to canonical form.
- * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
- * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
- * addresses to be in a canonical form:
- * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
- * canonical form [63:48] == [47]."
- */
-#define GEN8_HIGH_ADDRESS_BIT 47
-static inline u64 gen8_canonical_addr(u64 address)
-{
-	return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
-}
-
-static inline u64 gen8_noncanonical_addr(u64 address)
-{
-	return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0);
-}
-
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
 	return intel_engine_requires_cmd_parser(eb->engine) ||
@@ -748,9 +730,6 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 	unsigned int i, batch;
 	int err;
 
-	if (unlikely(i915_gem_context_is_banned(eb->gem_context)))
-		return -EIO;
-
 	INIT_LIST_HEAD(&eb->relocs);
 	INIT_LIST_HEAD(&eb->unbound);
 
@@ -886,9 +865,6 @@ static void eb_destroy(const struct i915_execbuffer *eb)
 {
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
-	if (eb->reloc_cache.ce)
-		intel_context_put(eb->reloc_cache.ce);
-
 	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
@@ -912,7 +888,6 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->has_fence = cache->gen < 4;
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.flags = 0;
-	cache->ce = NULL;
 	cache->rq = NULL;
 	cache->rq_size = 0;
 }
@@ -1182,7 +1157,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_unmap;
 
-	rq = intel_context_create_request(cache->ce);
+	rq = i915_request_create(eb->context);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_unpin;
@@ -1246,36 +1221,9 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 	if (unlikely(!cache->rq)) {
 		int err;
 
-		/* If we need to copy for the cmdparser, we will stall anyway */
-		if (eb_use_cmdparser(eb))
-			return ERR_PTR(-EWOULDBLOCK);
-
 		if (!intel_engine_can_store_dword(eb->engine))
 			return ERR_PTR(-ENODEV);
 
-		if (!cache->ce) {
-			struct intel_context *ce;
-
-			/*
-			 * The CS pre-parser can pre-fetch commands across
-			 * memory sync points and starting gen12 it is able to
-			 * pre-fetch across BB_START and BB_END boundaries
-			 * (within the same context). We therefore use a
-			 * separate context gen12+ to guarantee that the reloc
-			 * writes land before the parser gets to the target
-			 * memory location.
-			 */
-			if (cache->gen >= 12)
-				ce = intel_context_create(eb->context->gem_context,
-							  eb->engine);
-			else
-				ce = intel_context_get(eb->context);
-			if (IS_ERR(ce))
-				return ERR_CAST(ce);
-
-			cache->ce = ce;
-		}
-
 		err = __reloc_gpu_alloc(eb, vma, len);
 		if (unlikely(err))
 			return ERR_PTR(err);
@@ -1943,15 +1891,15 @@ err_skip:
 	return err;
 }
 
-static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
+static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 {
 	if (exec->flags & __I915_EXEC_ILLEGAL_FLAGS)
-		return false;
+		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
 	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
-			return false;
+			return -EINVAL;
 	}
 
 	if (exec->DR4 == 0xffffffff) {
@@ -1959,12 +1907,12 @@ static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		exec->DR4 = 0;
 	}
 	if (exec->DR1 || exec->DR4)
-		return false;
+		return -EINVAL;
 
 	if ((exec->batch_start_offset | exec->batch_len) & 0x7)
-		return false;
+		return -EINVAL;
 
-	return true;
+	return 0;
 }
 
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
@@ -1993,99 +1941,179 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 }
 
 static struct i915_vma *
-shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
+shadow_batch_pin(struct drm_i915_gem_object *obj,
+		 struct i915_address_space *vm,
+		 unsigned int flags)
 {
-	struct drm_i915_private *dev_priv = eb->i915;
-	struct i915_vma * const vma = *eb->vma;
-	struct i915_address_space *vm;
-	u64 flags;
+	struct i915_vma *vma;
+	int err;
 
-	/*
-	 * PPGTT backed shadow buffers must be mapped RO, to prevent
-	 * post-scan tampering
-	 */
-	if (CMDPARSER_USES_GGTT(dev_priv)) {
-		flags = PIN_GLOBAL;
-		vm = &dev_priv->ggtt.vm;
-	} else if (vma->vm->has_read_only) {
-		flags = PIN_USER;
-		vm = vma->vm;
-		i915_gem_object_set_readonly(obj);
-	} else {
-		DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
-		return ERR_PTR(-EINVAL);
-	}
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma))
+		return vma;
+
+	err = i915_vma_pin(vma, 0, 0, flags);
+	if (err)
+		return ERR_PTR(err);
 
-	return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
+	return vma;
 }
 
-static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
+struct eb_parse_work {
+	struct dma_fence_work base;
+	struct intel_engine_cs *engine;
+	struct i915_vma *batch;
+	struct i915_vma *shadow;
+	struct i915_vma *trampoline;
+	unsigned int batch_offset;
+	unsigned int batch_length;
+};
+
+static int __eb_parse(struct dma_fence_work *work)
 {
-	struct intel_engine_pool_node *pool;
-	struct i915_vma *vma;
-	u64 batch_start;
-	u64 shadow_batch_start;
+	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
+
+	return intel_engine_cmd_parser(pw->engine,
+				       pw->batch,
+				       pw->batch_offset,
+				       pw->batch_length,
+				       pw->shadow,
+				       pw->trampoline);
+}
+
+static const struct dma_fence_work_ops eb_parse_ops = {
+	.name = "eb_parse",
+	.work = __eb_parse,
+};
+
+static int eb_parse_pipeline(struct i915_execbuffer *eb,
+			     struct i915_vma *shadow,
+			     struct i915_vma *trampoline)
+{
+	struct eb_parse_work *pw;
 	int err;
 
-	pool = intel_engine_get_pool(eb->engine, eb->batch_len);
-	if (IS_ERR(pool))
-		return ERR_CAST(pool);
+	pw = kzalloc(sizeof(*pw), GFP_KERNEL);
+	if (!pw)
+		return -ENOMEM;
 
-	vma = shadow_batch_pin(eb, pool->obj);
-	if (IS_ERR(vma))
-		goto err;
+	dma_fence_work_init(&pw->base, &eb_parse_ops);
 
-	batch_start = gen8_canonical_addr(eb->batch->node.start) +
-		      eb->batch_start_offset;
+	pw->engine = eb->engine;
+	pw->batch = eb->batch;
+	pw->batch_offset = eb->batch_start_offset;
+	pw->batch_length = eb->batch_len;
+	pw->shadow = shadow;
+	pw->trampoline = trampoline;
 
-	shadow_batch_start = gen8_canonical_addr(vma->node.start);
+	dma_resv_lock(pw->batch->resv, NULL);
 
-	err = intel_engine_cmd_parser(eb->gem_context,
-				      eb->engine,
-				      eb->batch->obj,
-				      batch_start,
-				      eb->batch_start_offset,
-				      eb->batch_len,
-				      pool->obj,
-				      shadow_batch_start);
+	err = dma_resv_reserve_shared(pw->batch->resv, 1);
+	if (err)
+		goto err_batch_unlock;
 
-	if (err) {
-		i915_vma_unpin(vma);
+	/* Wait for all writes (and relocs) into the batch to complete */
+	err = i915_sw_fence_await_reservation(&pw->base.chain,
+					      pw->batch->resv, NULL, false,
+					      0, I915_FENCE_GFP);
+	if (err < 0)
+		goto err_batch_unlock;
+
+	/* Keep the batch alive and unwritten as we parse */
+	dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
+
+	dma_resv_unlock(pw->batch->resv);
 
+	/* Force execution to wait for completion of the parser */
+	dma_resv_lock(shadow->resv, NULL);
+	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
+	dma_resv_unlock(shadow->resv);
+
+	dma_fence_work_commit(&pw->base);
+	return 0;
+
+err_batch_unlock:
+	dma_resv_unlock(pw->batch->resv);
+	kfree(pw);
+	return err;
+}
+
+static int eb_parse(struct i915_execbuffer *eb)
+{
+	struct intel_engine_pool_node *pool;
+	struct i915_vma *shadow, *trampoline;
+	unsigned int len;
+	int err;
+
+	if (!eb_use_cmdparser(eb))
+		return 0;
+
+	len = eb->batch_len;
+	if (!CMDPARSER_USES_GGTT(eb->i915)) {
 		/*
-		 * Unsafe GGTT-backed buffers can still be submitted safely
-		 * as non-secure.
-		 * For PPGTT backing however, we have no choice but to forcibly
-		 * reject unsafe buffers
+		 * ppGTT backed shadow buffers must be mapped RO, to prevent
+		 * post-scan tampering
 		 */
-		if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
-			/* Execute original buffer non-secure */
-			vma = NULL;
-		else
-			vma = ERR_PTR(err);
+		if (!eb->context->vm->has_read_only) {
+			DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
+			return -EINVAL;
+		}
+	} else {
+		len += I915_CMD_PARSER_TRAMPOLINE_SIZE;
+	}
+
+	pool = intel_engine_get_pool(eb->engine, len);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	shadow = shadow_batch_pin(pool->obj, eb->context->vm, PIN_USER);
+	if (IS_ERR(shadow)) {
+		err = PTR_ERR(shadow);
 		goto err;
 	}
+	i915_gem_object_set_readonly(shadow->obj);
+
+	trampoline = NULL;
+	if (CMDPARSER_USES_GGTT(eb->i915)) {
+		trampoline = shadow;
+
+		shadow = shadow_batch_pin(pool->obj,
+					  &eb->engine->gt->ggtt->vm,
+					  PIN_GLOBAL);
+		if (IS_ERR(shadow)) {
+			err = PTR_ERR(shadow);
+			shadow = trampoline;
+			goto err_shadow;
+		}
+
+		eb->batch_flags |= I915_DISPATCH_SECURE;
+	}
+
+	err = eb_parse_pipeline(eb, shadow, trampoline);
+	if (err)
+		goto err_trampoline;
 
-	eb->vma[eb->buffer_count] = i915_vma_get(vma);
+	eb->vma[eb->buffer_count] = i915_vma_get(shadow);
 	eb->flags[eb->buffer_count] =
 		__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
-	vma->exec_flags = &eb->flags[eb->buffer_count];
+	shadow->exec_flags = &eb->flags[eb->buffer_count];
 	eb->buffer_count++;
 
+	eb->trampoline = trampoline;
 	eb->batch_start_offset = 0;
-	eb->batch = vma;
+	eb->batch = shadow;
 
-	if (CMDPARSER_USES_GGTT(eb->i915))
-		eb->batch_flags |= I915_DISPATCH_SECURE;
-
-	/* eb->batch_len unchanged */
-
-	vma->private = pool;
-	return vma;
+	shadow->private = pool;
+	return 0;
 
+err_trampoline:
+	if (trampoline)
+		i915_vma_unpin(trampoline);
+err_shadow:
+	i915_vma_unpin(shadow);
 err:
 	intel_engine_pool_put(pool);
-	return vma;
+	return err;
 }
 
 static void
@@ -2134,8 +2162,18 @@ static int eb_submit(struct i915_execbuffer *eb)
 	if (err)
 		return err;
 
-	if (i915_gem_context_nopreempt(eb->gem_context))
-		eb->request->flags |= I915_REQUEST_NOPREEMPT;
+	if (eb->trampoline) {
+		GEM_BUG_ON(eb->batch_start_offset);
+		err = eb->engine->emit_bb_start(eb->request,
+						eb->trampoline->node.start +
+						eb->batch_len,
+						0, 0);
+		if (err)
+			return err;
+	}
+
+	if (intel_context_nopreempt(eb->context))
+		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &eb->request->fence.flags);
 
 	return 0;
 }
@@ -2220,6 +2258,9 @@ static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
 	if (err)
 		return err;
 
+	if (unlikely(intel_context_is_banned(ce)))
+		return -EIO;
+
 	/*
 	 * Pinning the contexts may generate requests in order to acquire
 	 * GGTT space, so do this first before we reserve a seqno for
@@ -2515,6 +2556,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.buffer_count = args->buffer_count;
 	eb.batch_start_offset = args->batch_start_offset;
 	eb.batch_len = args->batch_len;
+	eb.trampoline = NULL;
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
@@ -2606,15 +2648,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (eb.batch_len == 0)
 		eb.batch_len = eb.batch->size - eb.batch_start_offset;
 
-	if (eb_use_cmdparser(&eb)) {
-		struct i915_vma *vma;
-
-		vma = eb_parse(&eb);
-		if (IS_ERR(vma)) {
-			err = PTR_ERR(vma);
-			goto err_vma;
-		}
-	}
+	err = eb_parse(&eb);
+	if (err)
+		goto err_vma;
 
 	/*
 	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
@@ -2720,6 +2756,8 @@ err_batch_unpin:
 err_vma:
 	if (eb.exec)
 		eb_release_vmas(&eb);
+	if (eb.trampoline)
+		i915_vma_unpin(eb.trampoline);
 	mutex_unlock(&dev->struct_mutex);
 err_engine:
 	eb_unpin_engine(&eb);
@@ -2789,8 +2827,9 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 	exec2.flags = I915_EXEC_RENDER;
 	i915_execbuffer2_set_context_id(exec2, 0);
 
-	if (!i915_gem_check_execbuffer(&exec2))
-		return -EINVAL;
+	err = i915_gem_check_execbuffer(&exec2);
+	if (err)
+		return err;
 
 	/* Copy in the exec list from userland */
 	exec_list = kvmalloc_array(count, sizeof(*exec_list),
@@ -2867,8 +2906,9 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	if (!i915_gem_check_execbuffer(args))
-		return -EINVAL;
+	err = i915_gem_check_execbuffer(args);
+	if (err)
+		return err;
 
 	/* Allocate an extra slot for use by the command parser */
 	exec2_list = kvmalloc_array(count + 1, eb_element_size(),
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
index ddc7f2a52b3e..87d8b27f426d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ioctls.h
@@ -28,8 +28,8 @@ int i915_gem_madvise_ioctl(struct drm_device *dev, void *data,
 			   struct drm_file *file);
 int i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file);
-int i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
-			    struct drm_file *file);
+int i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
+			       struct drm_file *file);
 int i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
 int i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index 0e2bf6b7e143..70543c83df06 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -16,46 +16,6 @@ const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
 	.release = i915_gem_object_release_memory_region,
 };
 
-/* XXX: Time to vfunc your life up? */
-void __iomem *
-i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj,
-				 unsigned long n)
-{
-	resource_size_t offset;
-
-	offset = i915_gem_object_get_dma_address(obj, n);
-	offset -= obj->mm.region->region.start;
-
-	return io_mapping_map_wc(&obj->mm.region->iomap, offset, PAGE_SIZE);
-}
-
-void __iomem *
-i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj,
-					unsigned long n)
-{
-	resource_size_t offset;
-
-	offset = i915_gem_object_get_dma_address(obj, n);
-	offset -= obj->mm.region->region.start;
-
-	return io_mapping_map_atomic_wc(&obj->mm.region->iomap, offset);
-}
-
-void __iomem *
-i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
-			    unsigned long n,
-			    unsigned long size)
-{
-	resource_size_t offset;
-
-	GEM_BUG_ON(!i915_gem_object_is_contiguous(obj));
-
-	offset = i915_gem_object_get_dma_address(obj, n);
-	offset -= obj->mm.region->region.start;
-
-	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
-}
-
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
 {
 	return obj->ops == &i915_gem_lmem_obj_ops;
@@ -79,9 +39,6 @@ __i915_gem_lmem_object_create(struct intel_memory_region *mem,
 	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 
-	if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
-		return ERR_PTR(-E2BIG);
-
 	obj = i915_gem_object_alloc();
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
index 7c176b8b7d2f..fc3f15580fe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
@@ -14,14 +14,6 @@ struct intel_memory_region;
 
 extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops;
 
-void __iomem *i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
-					  unsigned long n, unsigned long size);
-void __iomem *i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj,
-					       unsigned long n);
-void __iomem *
-i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj,
-					unsigned long n);
-
 bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index e3002849844b..b9fdac2f9003 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -4,7 +4,9 @@
  * Copyright © 2014-2016 Intel Corporation
  */
 
+#include <linux/anon_inodes.h>
 #include <linux/mman.h>
+#include <linux/pfn_t.h>
 #include <linux/sizes.h>
 
 #include "gt/intel_gt.h"
@@ -14,7 +16,9 @@
 #include "i915_gem_gtt.h"
 #include "i915_gem_ioctls.h"
 #include "i915_gem_object.h"
+#include "i915_gem_mman.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 #include "i915_vma.h"
 
 static inline bool
@@ -144,6 +148,9 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  * 3 - Remove implicit set-domain(GTT) and synchronisation on initial
  *     pagefault; swapin remains transparent.
  *
+ * 4 - Support multiple fault handlers per object depending on object's
+ *     backing storage (a.k.a. MMAP_OFFSET).
+ *
  * Restrictions:
  *
  *  * snoopable objects cannot be accessed via the GTT. It can cause machine
@@ -171,7 +178,7 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  */
 int i915_gem_mmap_gtt_version(void)
 {
-	return 3;
+	return 4;
 }
 
 static inline struct i915_ggtt_view
@@ -197,29 +204,80 @@ compute_partial_view(const struct drm_i915_gem_object *obj,
 	return view;
 }
 
-/**
- * i915_gem_fault - fault a page into the GTT
- * @vmf: fault info
- *
- * The fault handler is set up by drm_gem_mmap() when a object is GTT mapped
- * from userspace.  The fault handler takes care of binding the object to
- * the GTT (if needed), allocating and programming a fence register (again,
- * only if needed based on whether the old reg is still valid or the object
- * is tiled) and inserting a new PTE into the faulting process.
- *
- * Note that the faulting process may involve evicting existing objects
- * from the GTT and/or fence registers to make room.  So performance may
- * suffer if the GTT working set is large or there are few fence registers
- * left.
- *
- * The current feature set supported by i915_gem_fault() and thus GTT mmaps
- * is exposed via I915_PARAM_MMAP_GTT_VERSION (see i915_gem_mmap_gtt_version).
- */
-vm_fault_t i915_gem_fault(struct vm_fault *vmf)
+static vm_fault_t i915_error_to_vmf_fault(int err)
+{
+	switch (err) {
+	default:
+		WARN_ONCE(err, "unhandled error in %s: %i\n", __func__, err);
+		/* fallthrough */
+	case -EIO: /* shmemfs failure from swap device */
+	case -EFAULT: /* purged object */
+	case -ENODEV: /* bad object, how did you get here! */
+	case -ENXIO: /* unable to access backing store (on device) */
+		return VM_FAULT_SIGBUS;
+
+	case -ENOSPC: /* shmemfs allocation failure */
+	case -ENOMEM: /* our allocation failure */
+		return VM_FAULT_OOM;
+
+	case 0:
+	case -EAGAIN:
+	case -ERESTARTSYS:
+	case -EINTR:
+	case -EBUSY:
+		/*
+		 * EBUSY is ok: this just means that another thread
+		 * already did the job.
+		 */
+		return VM_FAULT_NOPAGE;
+	}
+}
+
+static vm_fault_t vm_fault_cpu(struct vm_fault *vmf)
+{
+	struct vm_area_struct *area = vmf->vma;
+	struct i915_mmap_offset *mmo = area->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
+	resource_size_t iomap;
+	int err;
+
+	/* Sanity check that we allow writing into this object */
+	if (unlikely(i915_gem_object_is_readonly(obj) &&
+		     area->vm_flags & VM_WRITE))
+		return VM_FAULT_SIGBUS;
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		goto out;
+
+	iomap = -1;
+	if (!i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_STRUCT_PAGE)) {
+		iomap = obj->mm.region->iomap.base;
+		iomap -= obj->mm.region->region.start;
+	}
+
+	/* PTEs are revoked in obj->ops->put_pages() */
+	err = remap_io_sg(area,
+			  area->vm_start, area->vm_end - area->vm_start,
+			  obj->mm.pages->sgl, iomap);
+
+	if (area->vm_flags & VM_WRITE) {
+		GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+		obj->mm.dirty = true;
+	}
+
+	i915_gem_object_unpin_pages(obj);
+
+out:
+	return i915_error_to_vmf_fault(err);
+}
+
+static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 {
 #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
 	struct vm_area_struct *area = vmf->vma;
-	struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data);
+	struct i915_mmap_offset *mmo = area->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
 	struct drm_device *dev = obj->base.dev;
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct intel_runtime_pm *rpm = &i915->runtime_pm;
@@ -312,6 +370,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		list_add(&obj->userfault_link, &i915->ggtt.userfault_list);
 	mutex_unlock(&i915->ggtt.vm.mutex);
 
+	/* Track the mmo associated with the fenced vma */
+	vma->mmo = mmo;
+
 	if (IS_ACTIVE(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND))
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
@@ -332,67 +393,36 @@ err_rpm:
 	intel_runtime_pm_put(rpm, wakeref);
 	i915_gem_object_unpin_pages(obj);
 err:
-	switch (ret) {
-	default:
-		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
-		/* fallthrough */
-	case -EIO: /* shmemfs failure from swap device */
-	case -EFAULT: /* purged object */
-	case -ENODEV: /* bad object, how did you get here! */
-		return VM_FAULT_SIGBUS;
-
-	case -ENOSPC: /* shmemfs allocation failure */
-	case -ENOMEM: /* our allocation failure */
-		return VM_FAULT_OOM;
-
-	case 0:
-	case -EAGAIN:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	}
+	return i915_error_to_vmf_fault(ret);
 }
 
-void __i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
+void __i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
 
 	GEM_BUG_ON(!obj->userfault_count);
 
-	obj->userfault_count = 0;
-	list_del(&obj->userfault_link);
-	drm_vma_node_unmap(&obj->base.vma_node,
-			   obj->base.dev->anon_inode->i_mapping);
-
 	for_each_ggtt_vma(vma, obj)
-		i915_vma_unset_userfault(vma);
+		i915_vma_revoke_mmap(vma);
+
+	GEM_BUG_ON(obj->userfault_count);
 }
 
-/**
- * i915_gem_object_release_mmap - remove physical page mappings
- * @obj: obj in question
- *
- * Preserve the reservation of the mmapping with the DRM core code, but
- * relinquish ownership of the pages back to the system.
- *
+/*
  * It is vital that we remove the page mapping if we have mapped a tiled
  * object through the GTT and then lose the fence register due to
  * resource pressure. Similarly if the object has been moved out of the
  * aperture, than pages mapped into userspace must be revoked. Removing the
  * mapping will then trigger a page fault on the next user access, allowing
- * fixup by i915_gem_fault().
+ * fixup by vm_fault_gtt().
  */
-void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
+static void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	intel_wakeref_t wakeref;
 
-	/* Serialisation between user GTT access and our code depends upon
+	/*
+	 * Serialisation between user GTT access and our code depends upon
 	 * revoking the CPU's PTE whilst the mutex is held. The next user
 	 * pagefault then has to wait until we release the mutex.
 	 *
@@ -406,9 +436,10 @@ void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
 	if (!obj->userfault_count)
 		goto out;
 
-	__i915_gem_object_release_mmap(obj);
+	__i915_gem_object_release_mmap_gtt(obj);
 
-	/* Ensure that the CPU's PTE are revoked and there are not outstanding
+	/*
+	 * Ensure that the CPU's PTE are revoked and there are not outstanding
 	 * memory transactions from userspace before we return. The TLB
 	 * flushing implied above by changing the PTE above *should* be
 	 * sufficient, an extra barrier here just provides us with a bit
@@ -422,54 +453,151 @@ out:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
-static int create_mmap_offset(struct drm_i915_gem_object *obj)
+void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
+{
+	struct i915_mmap_offset *mmo;
+
+	spin_lock(&obj->mmo.lock);
+	list_for_each_entry(mmo, &obj->mmo.offsets, offset) {
+		/*
+		 * vma_node_unmap for GTT mmaps handled already in
+		 * __i915_gem_object_release_mmap_gtt
+		 */
+		if (mmo->mmap_type == I915_MMAP_TYPE_GTT)
+			continue;
+
+		spin_unlock(&obj->mmo.lock);
+		drm_vma_node_unmap(&mmo->vma_node,
+				   obj->base.dev->anon_inode->i_mapping);
+		spin_lock(&obj->mmo.lock);
+	}
+	spin_unlock(&obj->mmo.lock);
+}
+
+/**
+ * i915_gem_object_release_mmap - remove physical page mappings
+ * @obj: obj in question
+ *
+ * Preserve the reservation of the mmapping with the DRM core code, but
+ * relinquish ownership of the pages back to the system.
+ */
+void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_release_mmap_gtt(obj);
+	i915_gem_object_release_mmap_offset(obj);
+}
+
+static struct i915_mmap_offset *
+mmap_offset_attach(struct drm_i915_gem_object *obj,
+		   enum i915_mmap_type mmap_type,
+		   struct drm_file *file)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct intel_gt *gt = &i915->gt;
+	struct i915_mmap_offset *mmo;
 	int err;
 
-	err = drm_gem_create_mmap_offset(&obj->base);
+	mmo = kmalloc(sizeof(*mmo), GFP_KERNEL);
+	if (!mmo)
+		return ERR_PTR(-ENOMEM);
+
+	mmo->obj = obj;
+	mmo->dev = obj->base.dev;
+	mmo->file = file;
+	mmo->mmap_type = mmap_type;
+	drm_vma_node_reset(&mmo->vma_node);
+
+	err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node,
+				 obj->base.size / PAGE_SIZE);
 	if (likely(!err))
-		return 0;
+		goto out;
 
 	/* Attempt to reap some mmap space from dead objects */
-	err = intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_retire_requests_timeout(&i915->gt, MAX_SCHEDULE_TIMEOUT);
 	if (err)
-		return err;
+		goto err;
 
 	i915_gem_drain_freed_objects(i915);
-	return drm_gem_create_mmap_offset(&obj->base);
+	err = drm_vma_offset_add(mmo->dev->vma_offset_manager, &mmo->vma_node,
+				 obj->base.size / PAGE_SIZE);
+	if (err)
+		goto err;
+
+out:
+	if (file)
+		drm_vma_node_allow(&mmo->vma_node, file);
+
+	spin_lock(&obj->mmo.lock);
+	list_add(&mmo->offset, &obj->mmo.offsets);
+	spin_unlock(&obj->mmo.lock);
+
+	return mmo;
+
+err:
+	kfree(mmo);
+	return ERR_PTR(err);
 }
 
-int
-i915_gem_mmap_gtt(struct drm_file *file,
-		  struct drm_device *dev,
-		  u32 handle,
-		  u64 *offset)
+static int
+__assign_mmap_offset(struct drm_file *file,
+		     u32 handle,
+		     enum i915_mmap_type mmap_type,
+		     u64 *offset)
 {
 	struct drm_i915_gem_object *obj;
-	int ret;
+	struct i915_mmap_offset *mmo;
+	int err;
 
 	obj = i915_gem_object_lookup(file, handle);
 	if (!obj)
 		return -ENOENT;
 
-	if (i915_gem_object_never_bind_ggtt(obj)) {
-		ret = -ENODEV;
+	if (mmap_type == I915_MMAP_TYPE_GTT &&
+	    i915_gem_object_never_bind_ggtt(obj)) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	if (mmap_type != I915_MMAP_TYPE_GTT &&
+	    !i915_gem_object_type_has(obj,
+				      I915_GEM_OBJECT_HAS_STRUCT_PAGE |
+				      I915_GEM_OBJECT_HAS_IOMEM)) {
+		err = -ENODEV;
 		goto out;
 	}
 
-	ret = create_mmap_offset(obj);
-	if (ret == 0)
-		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
+	mmo = mmap_offset_attach(obj, mmap_type, file);
+	if (IS_ERR(mmo)) {
+		err = PTR_ERR(mmo);
+		goto out;
+	}
 
+	*offset = drm_vma_node_offset_addr(&mmo->vma_node);
+	err = 0;
 out:
 	i915_gem_object_put(obj);
-	return ret;
+	return err;
+}
+
+int
+i915_gem_dumb_mmap_offset(struct drm_file *file,
+			  struct drm_device *dev,
+			  u32 handle,
+			  u64 *offset)
+{
+	enum i915_mmap_type mmap_type;
+
+	if (boot_cpu_has(X86_FEATURE_PAT))
+		mmap_type = I915_MMAP_TYPE_WC;
+	else if (!i915_ggtt_has_aperture(&to_i915(dev)->ggtt))
+		return -ENODEV;
+	else
+		mmap_type = I915_MMAP_TYPE_GTT;
+
+	return __assign_mmap_offset(file, handle, mmap_type, offset);
 }
 
 /**
- * i915_gem_mmap_gtt_ioctl - prepare an object for GTT mmap'ing
+ * i915_gem_mmap_offset_ioctl - prepare an object for GTT mmap'ing
  * @dev: DRM device
  * @data: GTT mapping ioctl data
  * @file: GEM object info
@@ -484,12 +612,237 @@ out:
  * userspace.
  */
 int
-i915_gem_mmap_gtt_ioctl(struct drm_device *dev, void *data,
-			struct drm_file *file)
+i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file)
+{
+	struct drm_i915_private *i915 = to_i915(dev);
+	struct drm_i915_gem_mmap_offset *args = data;
+	enum i915_mmap_type type;
+	int err;
+
+	/*
+	 * Historically we failed to check args.pad and args.offset
+	 * and so we cannot use those fields for user input and we cannot
+	 * add -EINVAL for them as the ABI is fixed, i.e. old userspace
+	 * may be feeding in garbage in those fields.
+	 *
+	 * if (args->pad) return -EINVAL; is verbotten!
+	 */
+
+	err = i915_user_extensions(u64_to_user_ptr(args->extensions),
+				   NULL, 0, NULL);
+	if (err)
+		return err;
+
+	switch (args->flags) {
+	case I915_MMAP_OFFSET_GTT:
+		if (!i915_ggtt_has_aperture(&i915->ggtt))
+			return -ENODEV;
+		type = I915_MMAP_TYPE_GTT;
+		break;
+
+	case I915_MMAP_OFFSET_WC:
+		if (!boot_cpu_has(X86_FEATURE_PAT))
+			return -ENODEV;
+		type = I915_MMAP_TYPE_WC;
+		break;
+
+	case I915_MMAP_OFFSET_WB:
+		type = I915_MMAP_TYPE_WB;
+		break;
+
+	case I915_MMAP_OFFSET_UC:
+		if (!boot_cpu_has(X86_FEATURE_PAT))
+			return -ENODEV;
+		type = I915_MMAP_TYPE_UC;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return __assign_mmap_offset(file, args->handle, type, &args->offset);
+}
+
+static void vm_open(struct vm_area_struct *vma)
 {
-	struct drm_i915_gem_mmap_gtt *args = data;
+	struct i915_mmap_offset *mmo = vma->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
 
-	return i915_gem_mmap_gtt(file, dev, args->handle, &args->offset);
+	GEM_BUG_ON(!obj);
+	i915_gem_object_get(obj);
+}
+
+static void vm_close(struct vm_area_struct *vma)
+{
+	struct i915_mmap_offset *mmo = vma->vm_private_data;
+	struct drm_i915_gem_object *obj = mmo->obj;
+
+	GEM_BUG_ON(!obj);
+	i915_gem_object_put(obj);
+}
+
+static const struct vm_operations_struct vm_ops_gtt = {
+	.fault = vm_fault_gtt,
+	.open = vm_open,
+	.close = vm_close,
+};
+
+static const struct vm_operations_struct vm_ops_cpu = {
+	.fault = vm_fault_cpu,
+	.open = vm_open,
+	.close = vm_close,
+};
+
+static int singleton_release(struct inode *inode, struct file *file)
+{
+	struct drm_i915_private *i915 = file->private_data;
+
+	cmpxchg(&i915->gem.mmap_singleton, file, NULL);
+	drm_dev_put(&i915->drm);
+
+	return 0;
+}
+
+static const struct file_operations singleton_fops = {
+	.owner = THIS_MODULE,
+	.release = singleton_release,
+};
+
+static struct file *mmap_singleton(struct drm_i915_private *i915)
+{
+	struct file *file;
+
+	rcu_read_lock();
+	file = i915->gem.mmap_singleton;
+	if (file && !get_file_rcu(file))
+		file = NULL;
+	rcu_read_unlock();
+	if (file)
+		return file;
+
+	file = anon_inode_getfile("i915.gem", &singleton_fops, i915, O_RDWR);
+	if (IS_ERR(file))
+		return file;
+
+	/* Everyone shares a single global address space */
+	file->f_mapping = i915->drm.anon_inode->i_mapping;
+
+	smp_store_mb(i915->gem.mmap_singleton, file);
+	drm_dev_get(&i915->drm);
+
+	return file;
+}
+
+/*
+ * This overcomes the limitation in drm_gem_mmap's assignment of a
+ * drm_gem_object as the vma->vm_private_data. Since we need to
+ * be able to resolve multiple mmap offsets which could be tied
+ * to a single gem object.
+ */
+int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct drm_vma_offset_node *node;
+	struct drm_file *priv = filp->private_data;
+	struct drm_device *dev = priv->minor->dev;
+	struct i915_mmap_offset *mmo = NULL;
+	struct drm_gem_object *obj = NULL;
+	struct file *anon;
+
+	if (drm_dev_is_unplugged(dev))
+		return -ENODEV;
+
+	drm_vma_offset_lock_lookup(dev->vma_offset_manager);
+	node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager,
+						  vma->vm_pgoff,
+						  vma_pages(vma));
+	if (likely(node)) {
+		mmo = container_of(node, struct i915_mmap_offset,
+				   vma_node);
+		/*
+		 * In our dependency chain, the drm_vma_offset_node
+		 * depends on the validity of the mmo, which depends on
+		 * the gem object. However the only reference we have
+		 * at this point is the mmo (as the parent of the node).
+		 * Try to check if the gem object was at least cleared.
+		 */
+		if (!mmo || !mmo->obj) {
+			drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
+			return -EINVAL;
+		}
+		/*
+		 * Skip 0-refcnted objects as it is in the process of being
+		 * destroyed and will be invalid when the vma manager lock
+		 * is released.
+		 */
+		obj = &mmo->obj->base;
+		if (!kref_get_unless_zero(&obj->refcount))
+			obj = NULL;
+	}
+	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
+	if (!obj)
+		return -EINVAL;
+
+	if (!drm_vma_node_is_allowed(node, priv)) {
+		drm_gem_object_put_unlocked(obj);
+		return -EACCES;
+	}
+
+	if (i915_gem_object_is_readonly(to_intel_bo(obj))) {
+		if (vma->vm_flags & VM_WRITE) {
+			drm_gem_object_put_unlocked(obj);
+			return -EINVAL;
+		}
+		vma->vm_flags &= ~VM_MAYWRITE;
+	}
+
+	anon = mmap_singleton(to_i915(obj->dev));
+	if (IS_ERR(anon)) {
+		drm_gem_object_put_unlocked(obj);
+		return PTR_ERR(anon);
+	}
+
+	vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_private_data = mmo;
+
+	/*
+	 * We keep the ref on mmo->obj, not vm_file, but we require
+	 * vma->vm_file->f_mapping, see vma_link(), for later revocation.
+	 * Our userspace is accustomed to having per-file resource cleanup
+	 * (i.e. contexts, objects and requests) on their close(fd), which
+	 * requires avoiding extraneous references to their filp, hence why
+	 * we prefer to use an anonymous file for their mmaps.
+	 */
+	fput(vma->vm_file);
+	vma->vm_file = anon;
+
+	switch (mmo->mmap_type) {
+	case I915_MMAP_TYPE_WC:
+		vma->vm_page_prot =
+			pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = &vm_ops_cpu;
+		break;
+
+	case I915_MMAP_TYPE_WB:
+		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+		vma->vm_ops = &vm_ops_cpu;
+		break;
+
+	case I915_MMAP_TYPE_UC:
+		vma->vm_page_prot =
+			pgprot_noncached(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = &vm_ops_cpu;
+		break;
+
+	case I915_MMAP_TYPE_GTT:
+		vma->vm_page_prot =
+			pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
+		vma->vm_ops = &vm_ops_gtt;
+		break;
+	}
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+
+	return 0;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.h b/drivers/gpu/drm/i915/gem/i915_gem_mman.h
new file mode 100644
index 000000000000..862e01b7cb69
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.h
@@ -0,0 +1,31 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __I915_GEM_MMAN_H__
+#define __I915_GEM_MMAN_H__
+
+#include <linux/mm_types.h>
+#include <linux/types.h>
+
+struct drm_device;
+struct drm_file;
+struct drm_i915_gem_object;
+struct file;
+struct i915_mmap_offset;
+struct mutex;
+
+int i915_gem_mmap_gtt_version(void);
+int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma);
+
+int i915_gem_dumb_mmap_offset(struct drm_file *file_priv,
+			      struct drm_device *dev,
+			      u32 handle, u64 *offset);
+
+void __i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj);
+void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj);
+void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index a596548c07bf..46bacc82ddc4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -22,11 +22,14 @@
  *
  */
 
+#include <linux/sched/mm.h>
+
 #include "display/intel_frontbuffer.h"
 #include "gt/intel_gt.h"
 #include "i915_drv.h"
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
+#include "i915_gem_mman.h"
 #include "i915_gem_object.h"
 #include "i915_globals.h"
 #include "i915_trace.h"
@@ -59,6 +62,9 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	INIT_LIST_HEAD(&obj->lut_list);
 
+	spin_lock_init(&obj->mmo.lock);
+	INIT_LIST_HEAD(&obj->mmo.offsets);
+
 	init_rcu_head(&obj->rcu);
 
 	obj->ops = ops;
@@ -95,6 +101,7 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
 	struct drm_i915_gem_object *obj = to_intel_bo(gem);
 	struct drm_i915_file_private *fpriv = file->driver_priv;
 	struct i915_lut_handle *lut, *ln;
+	struct i915_mmap_offset *mmo;
 	LIST_HEAD(close);
 
 	i915_gem_object_lock(obj);
@@ -109,6 +116,17 @@ void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *file)
 	}
 	i915_gem_object_unlock(obj);
 
+	spin_lock(&obj->mmo.lock);
+	list_for_each_entry(mmo, &obj->mmo.offsets, offset) {
+		if (mmo->file != file)
+			continue;
+
+		spin_unlock(&obj->mmo.lock);
+		drm_vma_node_revoke(&mmo->vma_node, file);
+		spin_lock(&obj->mmo.lock);
+	}
+	spin_unlock(&obj->mmo.lock);
+
 	list_for_each_entry_safe(lut, ln, &close, obj_link) {
 		struct i915_gem_context *ctx = lut->ctx;
 		struct i915_vma *vma;
@@ -156,6 +174,8 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	llist_for_each_entry_safe(obj, on, freed, freed) {
+		struct i915_mmap_offset *mmo, *mn;
+
 		trace_i915_gem_object_destroy(obj);
 
 		if (!list_empty(&obj->vma.list)) {
@@ -174,19 +194,28 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 				GEM_BUG_ON(vma->obj != obj);
 				spin_unlock(&obj->vma.lock);
 
-				i915_vma_destroy(vma);
+				__i915_vma_put(vma);
 
 				spin_lock(&obj->vma.lock);
 			}
 			spin_unlock(&obj->vma.lock);
 		}
 
+		i915_gem_object_release_mmap(obj);
+
+		list_for_each_entry_safe(mmo, mn, &obj->mmo.offsets, offset) {
+			drm_vma_offset_remove(obj->base.dev->vma_offset_manager,
+					      &mmo->vma_node);
+			kfree(mmo);
+		}
+		INIT_LIST_HEAD(&obj->mmo.offsets);
+
 		GEM_BUG_ON(atomic_read(&obj->bind_count));
 		GEM_BUG_ON(obj->userfault_count);
 		GEM_BUG_ON(!list_empty(&obj->lut_list));
 
 		atomic_set(&obj->mm.pages_pin_count, 0);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		GEM_BUG_ON(i915_gem_object_has_pages(obj));
 		bitmap_free(obj->bit_17);
 
@@ -277,18 +306,14 @@ i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj,
 
 	switch (obj->write_domain) {
 	case I915_GEM_DOMAIN_GTT:
-		for_each_ggtt_vma(vma, obj)
-			intel_gt_flush_ggtt_writes(vma->vm->gt);
-
-		i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
-
+		spin_lock(&obj->vma.lock);
 		for_each_ggtt_vma(vma, obj) {
-			if (vma->iomap)
-				continue;
-
-			i915_vma_unset_ggtt_write(vma);
+			if (i915_vma_unset_ggtt_write(vma))
+				intel_gt_flush_ggtt_writes(vma->vm->gt);
 		}
+		spin_unlock(&obj->vma.lock);
 
+		i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
 		break;
 
 	case I915_GEM_DOMAIN_WC:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 4b93591fd5c7..db70a3306e59 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -16,6 +16,7 @@
 #include "display/intel_frontbuffer.h"
 #include "i915_gem_object_types.h"
 #include "i915_gem_gtt.h"
+#include "i915_vma_types.h"
 
 void i915_gem_init__objects(struct drm_i915_private *i915);
 
@@ -132,13 +133,13 @@ void i915_gem_object_unlock_fence(struct drm_i915_gem_object *obj,
 static inline void
 i915_gem_object_set_readonly(struct drm_i915_gem_object *obj)
 {
-	obj->base.vma_node.readonly = true;
+	obj->flags |= I915_BO_READONLY;
 }
 
 static inline bool
 i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
 {
-	return obj->base.vma_node.readonly;
+	return obj->flags & I915_BO_READONLY;
 }
 
 static inline bool
@@ -271,10 +272,27 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 int ____i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
 int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj);
 
+enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
+	I915_MM_NORMAL = 0,
+	/*
+	 * Only used by struct_mutex, when called "recursively" from
+	 * direct-reclaim-esque. Safe because there is only every one
+	 * struct_mutex in the entire system.
+	 */
+	I915_MM_SHRINKER = 1,
+	/*
+	 * Used for obj->mm.lock when allocating pages. Safe because the object
+	 * isn't yet on any LRU, and therefore the shrinker can't deadlock on
+	 * it. As soon as the object has pages, obj->mm.lock nests within
+	 * fs_reclaim.
+	 */
+	I915_MM_GET_PAGES = 1,
+};
+
 static inline int __must_check
 i915_gem_object_pin_pages(struct drm_i915_gem_object *obj)
 {
-	might_lock(&obj->mm.lock);
+	might_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 
 	if (atomic_inc_not_zero(&obj->mm.pages_pin_count))
 		return 0;
@@ -317,13 +335,7 @@ i915_gem_object_unpin_pages(struct drm_i915_gem_object *obj)
 	__i915_gem_object_unpin_pages(obj);
 }
 
-enum i915_mm_subclass { /* lockdep subclass for obj->mm.lock/struct_mutex */
-	I915_MM_NORMAL = 0,
-	I915_MM_SHRINKER /* called "recursively" from direct-reclaim-esque */
-};
-
-int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				enum i915_mm_subclass subclass);
+int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj);
 void i915_gem_object_truncate(struct drm_i915_gem_object *obj);
 void i915_gem_object_writeback(struct drm_i915_gem_object *obj);
 
@@ -376,9 +388,6 @@ static inline void i915_gem_object_unpin_map(struct drm_i915_gem_object *obj)
 	i915_gem_object_unpin_pages(obj);
 }
 
-void __i915_gem_object_release_mmap(struct drm_i915_gem_object *obj);
-void i915_gem_object_release_mmap(struct drm_i915_gem_object *obj);
-
 void
 i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj,
 				   unsigned int flush_domains);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index e3f3944fbd90..88e268633fdc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -63,6 +63,23 @@ struct drm_i915_gem_object_ops {
 	void (*release)(struct drm_i915_gem_object *obj);
 };
 
+enum i915_mmap_type {
+	I915_MMAP_TYPE_GTT = 0,
+	I915_MMAP_TYPE_WC,
+	I915_MMAP_TYPE_WB,
+	I915_MMAP_TYPE_UC,
+};
+
+struct i915_mmap_offset {
+	struct drm_device *dev;
+	struct drm_vma_offset_node vma_node;
+	struct drm_i915_gem_object *obj;
+	struct drm_file *file;
+	enum i915_mmap_type mmap_type;
+
+	struct list_head offset;
+};
+
 struct drm_i915_gem_object {
 	struct drm_gem_object base;
 
@@ -118,12 +135,18 @@ struct drm_i915_gem_object {
 	unsigned int userfault_count;
 	struct list_head userfault_link;
 
+	struct {
+		spinlock_t lock; /* Protects access to mmo offsets */
+		struct list_head offsets;
+	} mmo;
+
 	I915_SELFTEST_DECLARE(struct list_head st_link);
 
 	unsigned long flags;
 #define I915_BO_ALLOC_CONTIGUOUS BIT(0)
 #define I915_BO_ALLOC_VOLATILE   BIT(1)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | I915_BO_ALLOC_VOLATILE)
+#define I915_BO_READONLY         BIT(2)
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
@@ -162,7 +185,11 @@ struct drm_i915_gem_object {
 	atomic_t bind_count;
 
 	struct {
-		struct mutex lock; /* protects the pages and their use */
+		/*
+		 * Protects the pages and their use. Do not use directly, but
+		 * instead go through the pin/unpin interfaces.
+		 */
+		struct mutex lock;
 		atomic_t pages_pin_count;
 		atomic_t shrink_pin;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 29f4c2850745..54aca5c9101e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -8,6 +8,7 @@
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_gem_lmem.h"
+#include "i915_gem_mman.h"
 
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
@@ -106,7 +107,7 @@ int __i915_gem_object_get_pages(struct drm_i915_gem_object *obj)
 {
 	int err;
 
-	err = mutex_lock_interruptible(&obj->mm.lock);
+	err = mutex_lock_interruptible_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 	if (err)
 		return err;
 
@@ -157,9 +158,7 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj)
 
 static void unmap_object(struct drm_i915_gem_object *obj, void *ptr)
 {
-	if (i915_gem_object_is_lmem(obj))
-		io_mapping_unmap((void __force __iomem *)ptr);
-	else if (is_vmalloc_addr(ptr))
+	if (is_vmalloc_addr(ptr))
 		vunmap(ptr);
 	else
 		kunmap(kmap_to_page(ptr));
@@ -190,8 +189,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	return pages;
 }
 
-int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				enum i915_mm_subclass subclass)
+int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
 {
 	struct sg_table *pages;
 	int err;
@@ -202,12 +200,14 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 	GEM_BUG_ON(atomic_read(&obj->bind_count));
 
 	/* May be called by shrinker from within get_pages() (on another bo) */
-	mutex_lock_nested(&obj->mm.lock, subclass);
+	mutex_lock(&obj->mm.lock);
 	if (unlikely(atomic_read(&obj->mm.pages_pin_count))) {
 		err = -EBUSY;
 		goto unlock;
 	}
 
+	i915_gem_object_release_mmap_offset(obj);
+
 	/*
 	 * ->put_pages might need to allocate memory for the bit17 swizzle
 	 * array, hence protect them from being reaped by removing them from gtt
@@ -234,46 +234,44 @@ unlock:
 	return err;
 }
 
+static inline pte_t iomap_pte(resource_size_t base,
+			      dma_addr_t offset,
+			      pgprot_t prot)
+{
+	return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
+}
+
 /* The 'mapping' part of i915_gem_object_pin_map() below */
 static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 				 enum i915_map_type type)
 {
-	unsigned long n_pages = obj->base.size >> PAGE_SHIFT;
+	unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
 	struct sg_table *sgt = obj->mm.pages;
-	struct sgt_iter sgt_iter;
-	struct page *page;
-	struct page *stack_pages[32];
-	struct page **pages = stack_pages;
-	unsigned long i = 0;
+	pte_t *stack[32], **mem;
+	struct vm_struct *area;
 	pgprot_t pgprot;
-	void *addr;
-
-	if (i915_gem_object_is_lmem(obj)) {
-		void __iomem *io;
-
-		if (type != I915_MAP_WC)
-			return NULL;
 
-		io = i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
-		return (void __force *)io;
-	}
+	if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
+		return NULL;
 
 	/* A single page can always be kmapped */
-	if (n_pages == 1 && type == I915_MAP_WB)
+	if (n_pte == 1 && type == I915_MAP_WB)
 		return kmap(sg_page(sgt->sgl));
 
-	if (n_pages > ARRAY_SIZE(stack_pages)) {
+	mem = stack;
+	if (n_pte > ARRAY_SIZE(stack)) {
 		/* Too big for stack -- allocate temporary array instead */
-		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
-		if (!pages)
+		mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
+		if (!mem)
 			return NULL;
 	}
 
-	for_each_sgt_page(page, sgt_iter, sgt)
-		pages[i++] = page;
-
-	/* Check that we have the expected number of pages */
-	GEM_BUG_ON(i != n_pages);
+	area = alloc_vm_area(obj->base.size, mem);
+	if (!area) {
+		if (mem != stack)
+			kvfree(mem);
+		return NULL;
+	}
 
 	switch (type) {
 	default:
@@ -286,12 +284,31 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 		pgprot = pgprot_writecombine(PAGE_KERNEL_IO);
 		break;
 	}
-	addr = vmap(pages, n_pages, 0, pgprot);
 
-	if (pages != stack_pages)
-		kvfree(pages);
+	if (i915_gem_object_has_struct_page(obj)) {
+		struct sgt_iter iter;
+		struct page *page;
+		pte_t **ptes = mem;
+
+		for_each_sgt_page(page, iter, sgt)
+			**ptes++ = mk_pte(page, pgprot);
+	} else {
+		resource_size_t iomap;
+		struct sgt_iter iter;
+		pte_t **ptes = mem;
+		dma_addr_t addr;
+
+		iomap = obj->mm.region->iomap.base;
+		iomap -= obj->mm.region->region.start;
+
+		for_each_sgt_daddr(addr, iter, sgt)
+			**ptes++ = iomap_pte(iomap, addr, pgprot);
+	}
+
+	if (mem != stack)
+		kvfree(mem);
 
-	return addr;
+	return area->addr;
 }
 
 /* get, pin, and map the pages of the object into kernel space */
@@ -308,7 +325,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	if (!i915_gem_object_type_has(obj, flags))
 		return ERR_PTR(-ENXIO);
 
-	err = mutex_lock_interruptible(&obj->mm.lock);
+	err = mutex_lock_interruptible_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 8043ff63d73f..b1b7c1b3038a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -164,7 +164,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 	if (err)
 		return err;
 
-	mutex_lock(&obj->mm.lock);
+	mutex_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 
 	if (obj->mm.madv != I915_MADV_WILLNEED) {
 		err = -EFAULT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index f88ee1317bb4..c8264eb036bf 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -13,7 +13,7 @@
 
 void i915_gem_suspend(struct drm_i915_private *i915)
 {
-	GEM_TRACE("\n");
+	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
 	intel_wakeref_auto(&i915->ggtt.userfault_wakeref, 0);
 	flush_workqueue(i915->wq);
@@ -99,30 +99,12 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 
 void i915_gem_resume(struct drm_i915_private *i915)
 {
-	GEM_TRACE("\n");
-
-	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
-
-	if (intel_gt_init_hw(&i915->gt))
-		goto err_wedged;
+	GEM_TRACE("%s\n", dev_name(i915->drm.dev));
 
 	/*
 	 * As we didn't flush the kernel context before suspend, we cannot
 	 * guarantee that the context image is complete. So let's just reset
 	 * it and start again.
 	 */
-	if (intel_gt_resume(&i915->gt))
-		goto err_wedged;
-
-out_unlock:
-	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
-	return;
-
-err_wedged:
-	if (!intel_gt_is_wedged(&i915->gt)) {
-		dev_err(i915->drm.dev,
-			"Failed to re-initialize GPU, declaring it wedged!\n");
-		intel_gt_set_wedged(&i915->gt);
-	}
-	goto out_unlock;
+	intel_gt_resume(&i915->gt);
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index 2f7bcfb9c964..1515384d7e0e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -85,7 +85,7 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 		}
 
 		prev_end = offset + block_size;
-	};
+	}
 
 	sg_page_sizes |= sg->length;
 	sg_mark_end(sg);
@@ -107,7 +107,10 @@ void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
 {
 	INIT_LIST_HEAD(&obj->mm.blocks);
 	obj->mm.region = intel_memory_region_get(mem);
+
 	obj->flags |= flags;
+	if (obj->base.size <= mem->min_page_size)
+		obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
 
 	mutex_lock(&mem->objects.lock);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 4d69c3fc3439..a2a980d9d241 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -594,6 +594,8 @@ static int init_shmem(struct intel_memory_region *mem)
 			 err);
 	}
 
+	intel_memory_region_set_name(mem, "system");
+
 	return 0; /* Don't error, we can simply fallback to the kernel mnt */
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index f2418a1cfe68..f7e4b39c734f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -57,7 +57,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj,
 		flags = I915_GEM_OBJECT_UNBIND_ACTIVE;
 
 	if (i915_gem_object_unbind(obj, flags) == 0)
-		__i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
+		__i915_gem_object_put_pages(obj);
 
 	return !i915_gem_object_has_pages(obj);
 }
@@ -209,8 +209,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 
 			if (unsafe_drop_pages(obj, shrink)) {
 				/* May arrive from get_pages on another bo */
-				mutex_lock_nested(&obj->mm.lock,
-						  I915_MM_SHRINKER);
+				mutex_lock(&obj->mm.lock);
 				if (!i915_gem_object_has_pages(obj)) {
 					try_to_writeback(obj, shrink);
 					count += obj->base.size >> PAGE_SHIFT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index a2d49c04e6a4..451f3078d60d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -26,48 +26,49 @@
  * for is a boon.
  */
 
-int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
+int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *i915,
 					 struct drm_mm_node *node, u64 size,
 					 unsigned alignment, u64 start, u64 end)
 {
 	int ret;
 
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return -ENODEV;
 
 	/* WaSkipStolenMemoryFirstPage:bdw+ */
-	if (INTEL_GEN(dev_priv) >= 8 && start < 4096)
+	if (INTEL_GEN(i915) >= 8 && start < 4096)
 		start = 4096;
 
-	mutex_lock(&dev_priv->mm.stolen_lock);
-	ret = drm_mm_insert_node_in_range(&dev_priv->mm.stolen, node,
+	mutex_lock(&i915->mm.stolen_lock);
+	ret = drm_mm_insert_node_in_range(&i915->mm.stolen, node,
 					  size, alignment, 0,
 					  start, end, DRM_MM_INSERT_BEST);
-	mutex_unlock(&dev_priv->mm.stolen_lock);
+	mutex_unlock(&i915->mm.stolen_lock);
 
 	return ret;
 }
 
-int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv,
+int i915_gem_stolen_insert_node(struct drm_i915_private *i915,
 				struct drm_mm_node *node, u64 size,
 				unsigned alignment)
 {
-	return i915_gem_stolen_insert_node_in_range(dev_priv, node, size,
+	return i915_gem_stolen_insert_node_in_range(i915, node, size,
 						    alignment, 0, U64_MAX);
 }
 
-void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
+void i915_gem_stolen_remove_node(struct drm_i915_private *i915,
 				 struct drm_mm_node *node)
 {
-	mutex_lock(&dev_priv->mm.stolen_lock);
+	mutex_lock(&i915->mm.stolen_lock);
 	drm_mm_remove_node(node);
-	mutex_unlock(&dev_priv->mm.stolen_lock);
+	mutex_unlock(&i915->mm.stolen_lock);
 }
 
-static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
+static int i915_adjust_stolen(struct drm_i915_private *i915,
 			      struct resource *dsm)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
 	struct resource *r;
 
 	if (dsm->start == 0 || dsm->end <= dsm->start)
@@ -79,14 +80,14 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	 */
 
 	/* Make sure we don't clobber the GTT if it's within stolen memory */
-	if (INTEL_GEN(dev_priv) <= 4 &&
-	    !IS_G33(dev_priv) && !IS_PINEVIEW(dev_priv) && !IS_G4X(dev_priv)) {
+	if (INTEL_GEN(i915) <= 4 &&
+	    !IS_G33(i915) && !IS_PINEVIEW(i915) && !IS_G4X(i915)) {
 		struct resource stolen[2] = {*dsm, *dsm};
 		struct resource ggtt_res;
 		resource_size_t ggtt_start;
 
-		ggtt_start = I915_READ(PGTBL_CTL);
-		if (IS_GEN(dev_priv, 4))
+		ggtt_start = intel_uncore_read(uncore, PGTBL_CTL);
+		if (IS_GEN(i915, 4))
 			ggtt_start = (ggtt_start & PGTBL_ADDRESS_LO_MASK) |
 				     (ggtt_start & PGTBL_ADDRESS_HI_MASK) << 28;
 		else
@@ -120,7 +121,7 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	 * kernel. So if the region is already marked as busy, something
 	 * is seriously wrong.
 	 */
-	r = devm_request_mem_region(dev_priv->drm.dev, dsm->start,
+	r = devm_request_mem_region(i915->drm.dev, dsm->start,
 				    resource_size(dsm),
 				    "Graphics Stolen Memory");
 	if (r == NULL) {
@@ -133,14 +134,14 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 		 * reservation starting from 1 instead of 0.
 		 * There's also BIOS with off-by-one on the other end.
 		 */
-		r = devm_request_mem_region(dev_priv->drm.dev, dsm->start + 1,
+		r = devm_request_mem_region(i915->drm.dev, dsm->start + 1,
 					    resource_size(dsm) - 2,
 					    "Graphics Stolen Memory");
 		/*
 		 * GEN3 firmware likes to smash pci bridges into the stolen
 		 * range. Apparently this works.
 		 */
-		if (r == NULL && !IS_GEN(dev_priv, 3)) {
+		if (!r && !IS_GEN(i915, 3)) {
 			DRM_ERROR("conflict detected with stolen region: %pR\n",
 				  dsm);
 
@@ -151,25 +152,27 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
-static void i915_gem_cleanup_stolen(struct drm_i915_private *dev_priv)
+static void i915_gem_cleanup_stolen(struct drm_i915_private *i915)
 {
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return;
 
-	drm_mm_takedown(&dev_priv->mm.stolen);
+	drm_mm_takedown(&i915->mm.stolen);
 }
 
-static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void g4x_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(IS_GM45(dev_priv) ?
-				CTG_STOLEN_RESERVED :
-				ELK_STOLEN_RESERVED);
-	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+	u32 reg_val = intel_uncore_read(uncore,
+					IS_GM45(i915) ?
+					CTG_STOLEN_RESERVED :
+					ELK_STOLEN_RESERVED);
+	resource_size_t stolen_top = i915->dsm.end + 1;
 
 	DRM_DEBUG_DRIVER("%s_STOLEN_RESERVED = %08x\n",
-			 IS_GM45(dev_priv) ? "CTG" : "ELK", reg_val);
+			 IS_GM45(i915) ? "CTG" : "ELK", reg_val);
 
 	if ((reg_val & G4X_STOLEN_RESERVED_ENABLE) == 0)
 		return;
@@ -178,7 +181,7 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	 * Whether ILK really reuses the ELK register for this is unclear.
 	 * Let's see if we catch anyone with this supposedly enabled on ILK.
 	 */
-	WARN(IS_GEN(dev_priv, 5), "ILK stolen reserved found? 0x%08x\n",
+	WARN(IS_GEN(i915, 5), "ILK stolen reserved found? 0x%08x\n",
 	     reg_val);
 
 	if (!(reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK))
@@ -190,11 +193,12 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*size = stolen_top - *base;
 }
 
-static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void gen6_get_stolen_reserved(struct drm_i915_private *i915,
+				     struct intel_uncore *uncore,
 				     resource_size_t *base,
 				     resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -222,12 +226,13 @@ static void gen6_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void vlv_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
-	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
+	resource_size_t stolen_top = i915->dsm.end + 1;
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -250,11 +255,12 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*base = stolen_top - *size;
 }
 
-static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void gen7_get_stolen_reserved(struct drm_i915_private *i915,
+				     struct intel_uncore *uncore,
 				     resource_size_t *base,
 				     resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -276,11 +282,12 @@ static void gen7_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void chv_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void chv_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -308,12 +315,13 @@ static void chv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
+static void bdw_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u32 reg_val = I915_READ(GEN6_STOLEN_RESERVED);
-	resource_size_t stolen_top = dev_priv->dsm.end + 1;
+	u32 reg_val = intel_uncore_read(uncore, GEN6_STOLEN_RESERVED);
+	resource_size_t stolen_top = i915->dsm.end + 1;
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = %08x\n", reg_val);
 
@@ -328,10 +336,11 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
 }
 
 static void icl_get_stolen_reserved(struct drm_i915_private *i915,
+				    struct intel_uncore *uncore,
 				    resource_size_t *base,
 				    resource_size_t *size)
 {
-	u64 reg_val = intel_uncore_read64(&i915->uncore, GEN6_STOLEN_RESERVED);
+	u64 reg_val = intel_uncore_read64(uncore, GEN6_STOLEN_RESERVED);
 
 	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
 
@@ -356,22 +365,23 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 	}
 }
 
-static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
+static int i915_gem_init_stolen(struct drm_i915_private *i915)
 {
+	struct intel_uncore *uncore = &i915->uncore;
 	resource_size_t reserved_base, stolen_top;
 	resource_size_t reserved_total, reserved_size;
 
-	mutex_init(&dev_priv->mm.stolen_lock);
+	mutex_init(&i915->mm.stolen_lock);
 
-	if (intel_vgpu_active(dev_priv)) {
-		dev_notice(dev_priv->drm.dev,
+	if (intel_vgpu_active(i915)) {
+		dev_notice(i915->drm.dev,
 			   "%s, disabling use of stolen memory\n",
 			   "iGVT-g active");
 		return 0;
 	}
 
-	if (intel_vtd_active() && INTEL_GEN(dev_priv) < 8) {
-		dev_notice(dev_priv->drm.dev,
+	if (intel_vtd_active() && INTEL_GEN(i915) < 8) {
+		dev_notice(i915->drm.dev,
 			   "%s, disabling use of stolen memory\n",
 			   "DMAR active");
 		return 0;
@@ -380,58 +390,59 @@ static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 	if (resource_size(&intel_graphics_stolen_res) == 0)
 		return 0;
 
-	dev_priv->dsm = intel_graphics_stolen_res;
+	i915->dsm = intel_graphics_stolen_res;
 
-	if (i915_adjust_stolen(dev_priv, &dev_priv->dsm))
+	if (i915_adjust_stolen(i915, &i915->dsm))
 		return 0;
 
-	GEM_BUG_ON(dev_priv->dsm.start == 0);
-	GEM_BUG_ON(dev_priv->dsm.end <= dev_priv->dsm.start);
+	GEM_BUG_ON(i915->dsm.start == 0);
+	GEM_BUG_ON(i915->dsm.end <= i915->dsm.start);
 
-	stolen_top = dev_priv->dsm.end + 1;
+	stolen_top = i915->dsm.end + 1;
 	reserved_base = stolen_top;
 	reserved_size = 0;
 
-	switch (INTEL_GEN(dev_priv)) {
+	switch (INTEL_GEN(i915)) {
 	case 2:
 	case 3:
 		break;
 	case 4:
-		if (!IS_G4X(dev_priv))
+		if (!IS_G4X(i915))
 			break;
 		/* fall through */
 	case 5:
-		g4x_get_stolen_reserved(dev_priv,
+		g4x_get_stolen_reserved(i915, uncore,
 					&reserved_base, &reserved_size);
 		break;
 	case 6:
-		gen6_get_stolen_reserved(dev_priv,
+		gen6_get_stolen_reserved(i915, uncore,
 					 &reserved_base, &reserved_size);
 		break;
 	case 7:
-		if (IS_VALLEYVIEW(dev_priv))
-			vlv_get_stolen_reserved(dev_priv,
+		if (IS_VALLEYVIEW(i915))
+			vlv_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
 		else
-			gen7_get_stolen_reserved(dev_priv,
+			gen7_get_stolen_reserved(i915, uncore,
 						 &reserved_base, &reserved_size);
 		break;
 	case 8:
 	case 9:
 	case 10:
-		if (IS_LP(dev_priv))
-			chv_get_stolen_reserved(dev_priv,
+		if (IS_LP(i915))
+			chv_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
 		else
-			bdw_get_stolen_reserved(dev_priv,
+			bdw_get_stolen_reserved(i915, uncore,
 						&reserved_base, &reserved_size);
 		break;
 	default:
-		MISSING_CASE(INTEL_GEN(dev_priv));
+		MISSING_CASE(INTEL_GEN(i915));
 		/* fall-through */
 	case 11:
 	case 12:
-		icl_get_stolen_reserved(dev_priv, &reserved_base,
+		icl_get_stolen_reserved(i915, uncore,
+					&reserved_base,
 					&reserved_size);
 		break;
 	}
@@ -448,12 +459,12 @@ static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 		reserved_size = 0;
 	}
 
-	dev_priv->dsm_reserved =
-		(struct resource) DEFINE_RES_MEM(reserved_base, reserved_size);
+	i915->dsm_reserved =
+		(struct resource)DEFINE_RES_MEM(reserved_base, reserved_size);
 
-	if (!resource_contains(&dev_priv->dsm, &dev_priv->dsm_reserved)) {
+	if (!resource_contains(&i915->dsm, &i915->dsm_reserved)) {
 		DRM_ERROR("Stolen reserved area %pR outside stolen memory %pR\n",
-			  &dev_priv->dsm_reserved, &dev_priv->dsm);
+			  &i915->dsm_reserved, &i915->dsm);
 		return 0;
 	}
 
@@ -462,14 +473,14 @@ static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 	reserved_total = stolen_top - reserved_base;
 
 	DRM_DEBUG_DRIVER("Memory reserved for graphics device: %lluK, usable: %lluK\n",
-			 (u64)resource_size(&dev_priv->dsm) >> 10,
-			 ((u64)resource_size(&dev_priv->dsm) - reserved_total) >> 10);
+			 (u64)resource_size(&i915->dsm) >> 10,
+			 ((u64)resource_size(&i915->dsm) - reserved_total) >> 10);
 
-	dev_priv->stolen_usable_size =
-		resource_size(&dev_priv->dsm) - reserved_total;
+	i915->stolen_usable_size =
+		resource_size(&i915->dsm) - reserved_total;
 
 	/* Basic memrange allocator for stolen space. */
-	drm_mm_init(&dev_priv->mm.stolen, 0, dev_priv->stolen_usable_size);
+	drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size);
 
 	return 0;
 }
@@ -478,11 +489,11 @@ static struct sg_table *
 i915_pages_create_for_stolen(struct drm_device *dev,
 			     resource_size_t offset, resource_size_t size)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct sg_table *st;
 	struct scatterlist *sg;
 
-	GEM_BUG_ON(range_overflows(offset, size, resource_size(&dev_priv->dsm)));
+	GEM_BUG_ON(range_overflows(offset, size, resource_size(&i915->dsm)));
 
 	/* We hide that we have no struct page backing our stolen object
 	 * by wrapping the contiguous physical allocation with a fake
@@ -502,7 +513,7 @@ i915_pages_create_for_stolen(struct drm_device *dev,
 	sg->offset = 0;
 	sg->length = size;
 
-	sg_dma_address(sg) = (dma_addr_t)dev_priv->dsm.start + offset;
+	sg_dma_address(sg) = (dma_addr_t)i915->dsm.start + offset;
 	sg_dma_len(sg) = size;
 
 	return st;
@@ -533,16 +544,15 @@ static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj,
 static void
 i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct drm_mm_node *stolen = fetch_and_zero(&obj->stolen);
 
 	GEM_BUG_ON(!stolen);
 
-	i915_gem_stolen_remove_node(dev_priv, stolen);
-	kfree(stolen);
+	i915_gem_object_release_memory_region(obj);
 
-	if (obj->mm.region)
-		i915_gem_object_release_memory_region(obj);
+	i915_gem_stolen_remove_node(i915, stolen);
+	kfree(stolen);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
@@ -552,9 +562,8 @@ static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
 };
 
 static struct drm_i915_gem_object *
-__i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
-				struct drm_mm_node *stolen,
-				struct intel_memory_region *mem)
+__i915_gem_object_create_stolen(struct intel_memory_region *mem,
+				struct drm_mm_node *stolen)
 {
 	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
@@ -565,20 +574,19 @@ __i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 	if (!obj)
 		goto err;
 
-	drm_gem_private_object_init(&dev_priv->drm, &obj->base, stolen->size);
+	drm_gem_private_object_init(&mem->i915->drm, &obj->base, stolen->size);
 	i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class);
 
 	obj->stolen = stolen;
 	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
-	cache_level = HAS_LLC(dev_priv) ? I915_CACHE_LLC : I915_CACHE_NONE;
+	cache_level = HAS_LLC(mem->i915) ? I915_CACHE_LLC : I915_CACHE_NONE;
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 
 	err = i915_gem_object_pin_pages(obj);
 	if (err)
 		goto cleanup;
 
-	if (mem)
-		i915_gem_object_init_memory_region(obj, mem, 0);
+	i915_gem_object_init_memory_region(obj, mem, 0);
 
 	return obj;
 
@@ -593,12 +601,12 @@ _i915_gem_object_create_stolen(struct intel_memory_region *mem,
 			       resource_size_t size,
 			       unsigned int flags)
 {
-	struct drm_i915_private *dev_priv = mem->i915;
+	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	int ret;
 
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return ERR_PTR(-ENODEV);
 
 	if (size == 0)
@@ -608,35 +616,37 @@ _i915_gem_object_create_stolen(struct intel_memory_region *mem,
 	if (!stolen)
 		return ERR_PTR(-ENOMEM);
 
-	ret = i915_gem_stolen_insert_node(dev_priv, stolen, size, 4096);
+	ret = i915_gem_stolen_insert_node(i915, stolen, size, 4096);
 	if (ret) {
 		obj = ERR_PTR(ret);
 		goto err_free;
 	}
 
-	obj = __i915_gem_object_create_stolen(dev_priv, stolen, mem);
+	obj = __i915_gem_object_create_stolen(mem, stolen);
 	if (IS_ERR(obj))
 		goto err_remove;
 
 	return obj;
 
 err_remove:
-	i915_gem_stolen_remove_node(dev_priv, stolen);
+	i915_gem_stolen_remove_node(i915, stolen);
 err_free:
 	kfree(stolen);
 	return obj;
 }
 
 struct drm_i915_gem_object *
-i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
+i915_gem_object_create_stolen(struct drm_i915_private *i915,
 			      resource_size_t size)
 {
-	return i915_gem_object_create_region(dev_priv->mm.regions[INTEL_REGION_STOLEN],
+	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_STOLEN],
 					     size, I915_BO_ALLOC_CONTIGUOUS);
 }
 
 static int init_stolen(struct intel_memory_region *mem)
 {
+	intel_memory_region_set_name(mem, "stolen");
+
 	/*
 	 * Initialise stolen early so that we may reserve preallocated
 	 * objects for the BIOS to KMS transition.
@@ -665,18 +675,19 @@ struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915)
 }
 
 struct drm_i915_gem_object *
-i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv,
+i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
 					       resource_size_t stolen_offset,
 					       resource_size_t gtt_offset,
 					       resource_size_t size)
 {
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
+	struct intel_memory_region *mem = i915->mm.regions[INTEL_REGION_STOLEN];
+	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	struct i915_vma *vma;
 	int ret;
 
-	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+	if (!drm_mm_initialized(&i915->mm.stolen))
 		return ERR_PTR(-ENODEV);
 
 	DRM_DEBUG_DRIVER("creating preallocated stolen object: stolen_offset=%pa, gtt_offset=%pa, size=%pa\n",
@@ -694,19 +705,19 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 
 	stolen->start = stolen_offset;
 	stolen->size = size;
-	mutex_lock(&dev_priv->mm.stolen_lock);
-	ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
-	mutex_unlock(&dev_priv->mm.stolen_lock);
+	mutex_lock(&i915->mm.stolen_lock);
+	ret = drm_mm_reserve_node(&i915->mm.stolen, stolen);
+	mutex_unlock(&i915->mm.stolen_lock);
 	if (ret) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen space\n");
 		kfree(stolen);
 		return ERR_PTR(ret);
 	}
 
-	obj = __i915_gem_object_create_stolen(dev_priv, stolen, NULL);
+	obj = __i915_gem_object_create_stolen(mem, stolen);
 	if (IS_ERR(obj)) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen object\n");
-		i915_gem_stolen_remove_node(dev_priv, stolen);
+		i915_gem_stolen_remove_node(i915, stolen);
 		kfree(stolen);
 		return obj;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index 1fa592d82af5..6c7825a2dc2a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -11,6 +11,7 @@
 #include "i915_drv.h"
 #include "i915_gem.h"
 #include "i915_gem_ioctls.h"
+#include "i915_gem_mman.h"
 #include "i915_gem_object.h"
 
 /**
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 0dbb44d30885..580319b7bf1a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -129,9 +129,10 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 		spin_unlock(&mn->lock);
 
 		ret = i915_gem_object_unbind(obj,
-					     I915_GEM_OBJECT_UNBIND_ACTIVE);
+					     I915_GEM_OBJECT_UNBIND_ACTIVE |
+					     I915_GEM_OBJECT_UNBIND_BARRIER);
 		if (ret == 0)
-			ret = __i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
+			ret = __i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
 		if (ret)
 			return ret;
@@ -460,31 +461,36 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 		unsigned int flags = 0;
+		int locked = 0;
 
 		if (!i915_gem_object_is_readonly(obj))
 			flags |= FOLL_WRITE;
 
 		ret = -EFAULT;
 		if (mmget_not_zero(mm)) {
-			down_read(&mm->mmap_sem);
 			while (pinned < npages) {
+				if (!locked) {
+					down_read(&mm->mmap_sem);
+					locked = 1;
+				}
 				ret = get_user_pages_remote
 					(work->task, mm,
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
 					 flags,
-					 pvec + pinned, NULL, NULL);
+					 pvec + pinned, NULL, &locked);
 				if (ret < 0)
 					break;
 
 				pinned += ret;
 			}
-			up_read(&mm->mmap_sem);
+			if (locked)
+				up_read(&mm->mmap_sem);
 			mmput(mm);
 		}
 	}
 
-	mutex_lock(&obj->mm.lock);
+	mutex_lock_nested(&obj->mm.lock, I915_MM_GET_PAGES);
 	if (obj->userptr.work == &work->work) {
 		struct sg_table *pages = ERR_PTR(ret);
 
@@ -774,15 +780,11 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -EFAULT;
 
 	if (args->flags & I915_USERPTR_READ_ONLY) {
-		struct i915_address_space *vm;
-
 		/*
 		 * On almost all of the older hw, we cannot tell the GPU that
 		 * a page is readonly.
 		 */
-		vm = rcu_dereference_protected(dev_priv->kernel_context->vm,
-					       true); /* static vm */
-		if (!vm || !vm->has_read_only)
+		if (!dev_priv->gt.vm->has_read_only)
 			return -ENODEV;
 	}
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
index 892d12db6c49..fa16f2c3f3ac 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
@@ -12,10 +12,14 @@ static void huge_free_pages(struct drm_i915_gem_object *obj,
 			    struct sg_table *pages)
 {
 	unsigned long nreal = obj->scratch / PAGE_SIZE;
-	struct scatterlist *sg;
+	struct sgt_iter sgt_iter;
+	struct page *page;
 
-	for (sg = pages->sgl; sg && nreal--; sg = __sg_next(sg))
-		__free_page(sg_page(sg));
+	for_each_sgt_page(page, sgt_iter, pages) {
+		__free_page(page);
+		if (!--nreal)
+			break;
+	}
 
 	sg_free_table(pages);
 	kfree(pages);
@@ -70,7 +74,6 @@ static int huge_get_pages(struct drm_i915_gem_object *obj)
 
 err:
 	huge_free_pages(obj, pages);
-
 	return -ENOMEM;
 #undef GFP
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h
index 549c1394bcdc..b8cf31b7bf14 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.h
@@ -7,6 +7,12 @@
 #ifndef __HUGE_GEM_OBJECT_H
 #define __HUGE_GEM_OBJECT_H
 
+#include <linux/types.h>
+
+#include "gem/i915_gem_object_types.h"
+
+struct drm_i915_private;
+
 struct drm_i915_gem_object *
 huge_gem_object(struct drm_i915_private *i915,
 		phys_addr_t phys_size,
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 688c49a24f32..9311250d7d6f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -517,7 +517,7 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 			i915_vma_unpin(vma);
 			i915_vma_close(vma);
 
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -650,7 +650,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		i915_vma_close(vma);
 
 		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
 	}
 
@@ -678,7 +678,7 @@ static void close_object_list(struct list_head *objects,
 
 		list_del(&obj->st_link);
 		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		i915_gem_object_put(obj);
 	}
 }
@@ -948,7 +948,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			i915_vma_close(vma);
 
 			i915_gem_object_unpin_pages(obj);
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1017,38 +1017,33 @@ __cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	return err;
 }
 
-static int __cpu_check_lmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
+static int __cpu_check_vmap(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
-	unsigned long n;
+	unsigned long n = obj->base.size >> PAGE_SHIFT;
+	u32 *ptr;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_wc_domain(obj, false);
-	i915_gem_object_unlock(obj);
+	err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
-	err = i915_gem_object_pin_pages(obj);
-	if (err)
-		return err;
+	ptr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
 
-	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
-		u32 __iomem *base;
-		u32 read_val;
-
-		base = i915_gem_object_lmem_io_map_page_atomic(obj, n);
-
-		read_val = ioread32(base + dword);
-		io_mapping_unmap_atomic(base);
-		if (read_val != val) {
-			pr_err("n=%lu base[%u]=%u, val=%u\n",
-			       n, dword, read_val, val);
+	ptr += dword;
+	while (n--) {
+		if (*ptr != val) {
+			pr_err("base[%u]=%08x, val=%08x\n",
+			       dword, *ptr, val);
 			err = -EINVAL;
 			break;
 		}
+
+		ptr += PAGE_SIZE / sizeof(*ptr);
 	}
 
-	i915_gem_object_unpin_pages(obj);
+	i915_gem_object_unpin_map(obj);
 	return err;
 }
 
@@ -1056,10 +1051,8 @@ static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
 	if (i915_gem_object_has_struct_page(obj))
 		return __cpu_check_shmem(obj, dword, val);
-	else if (i915_gem_object_is_lmem(obj))
-		return __cpu_check_lmem(obj, dword, val);
-
-	return -ENODEV;
+	else
+		return __cpu_check_vmap(obj, dword, val);
 }
 
 static int __igt_write_huge(struct intel_context *ce,
@@ -1110,8 +1103,7 @@ static int __igt_write_huge(struct intel_context *ce,
 out_vma_unpin:
 	i915_vma_unpin(vma);
 out_vma_close:
-	i915_vma_destroy(vma);
-
+	__i915_vma_put(vma);
 	return err;
 }
 
@@ -1301,7 +1293,7 @@ static int igt_ppgtt_exhaust_huge(void *arg)
 			}
 
 			i915_gem_object_unpin_pages(obj);
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1420,7 +1412,7 @@ try_again:
 
 		err = i915_gem_object_pin_pages(obj);
 		if (err) {
-			if (err == -ENXIO) {
+			if (err == -ENXIO || err == -E2BIG) {
 				i915_gem_object_put(obj);
 				size >>= 1;
 				goto try_again;
@@ -1442,7 +1434,7 @@ try_again:
 		}
 out_unpin:
 		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 out_put:
 		i915_gem_object_put(obj);
 
@@ -1530,7 +1522,7 @@ static int igt_ppgtt_sanity_check(void *arg)
 			err = igt_write_huge(ctx, obj);
 
 			i915_gem_object_unpin_pages(obj);
-			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			__i915_gem_object_put_pages(obj);
 			i915_gem_object_put(obj);
 
 			if (err) {
@@ -1873,7 +1865,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	mkwrite_device_info(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL;
 	mkwrite_device_info(dev_priv)->ppgtt_size = 48;
 
-	ppgtt = i915_ppgtt_create(dev_priv);
+	ppgtt = i915_ppgtt_create(&dev_priv->gt);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
@@ -1912,9 +1904,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_smoke_huge),
 		SUBTEST(igt_ppgtt_sanity_check),
 	};
-	struct drm_file *file;
 	struct i915_gem_context *ctx;
 	struct i915_address_space *vm;
+	struct file *file;
 	int err;
 
 	if (!HAS_PPGTT(i915)) {
@@ -1944,6 +1936,6 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 	err = i915_subtests(tests, ctx);
 
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index da8edee4fe0a..b972be165e85 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -24,6 +24,7 @@ static int __igt_client_fill(struct intel_engine_cs *engine)
 
 	prandom_seed_state(&prng, i915_selftest.random_seed);
 
+	intel_engine_pm_get(engine);
 	do {
 		const u32 max_block_size = S16_MAX * PAGE_SIZE;
 		u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
@@ -99,6 +100,7 @@ err_put:
 err_flush:
 	if (err == -ENOMEM)
 		err = 0;
+	intel_engine_pm_put(engine);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 2b29f6b4e1dd..3f6079e1dfb6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -6,6 +6,7 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_ring.h"
@@ -200,7 +201,7 @@ static int gpu_set(struct context *ctx, unsigned long offset, u32 v)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	rq = i915_request_create(ctx->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(ctx->engine);
 	if (IS_ERR(rq)) {
 		i915_vma_unpin(vma);
 		return PTR_ERR(rq);
@@ -324,8 +325,12 @@ static int igt_gem_coherency(void *arg)
 	values = offsets + ncachelines;
 
 	ctx.engine = random_engine(i915, &prng);
-	GEM_BUG_ON(!ctx.engine);
+	if (!ctx.engine) {
+		err = -ENODEV;
+		goto out_free;
+	}
 	pr_info("%s: using %s\n", __func__, ctx.engine->name);
+	intel_engine_pm_get(ctx.engine);
 
 	for (over = igt_coherency_mode; over->name; over++) {
 		if (!over->set)
@@ -352,7 +357,7 @@ static int igt_gem_coherency(void *arg)
 					ctx.obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 					if (IS_ERR(ctx.obj)) {
 						err = PTR_ERR(ctx.obj);
-						goto free;
+						goto out_pm;
 					}
 
 					i915_random_reorder(offsets, ncachelines, &prng);
@@ -403,13 +408,15 @@ static int igt_gem_coherency(void *arg)
 			}
 		}
 	}
-free:
+out_pm:
+	intel_engine_pm_put(ctx.engine);
+out_free:
 	kfree(offsets);
 	return err;
 
 put_object:
 	i915_gem_object_put(ctx.obj);
-	goto free;
+	goto out_pm;
 }
 
 int i915_gem_coherency_live_selftests(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 62fabc023a83..7fc46861a54d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 #include "gt/intel_reset.h"
@@ -26,6 +27,12 @@
 
 #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32))
 
+static inline struct i915_address_space *ctx_vm(struct i915_gem_context *ctx)
+{
+	/* single threaded, private ctx */
+	return rcu_dereference_protected(ctx->vm, true);
+}
+
 static int live_nop_switch(void *arg)
 {
 	const unsigned int nctx = 1024;
@@ -33,7 +40,7 @@ static int live_nop_switch(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_gem_context **ctx;
 	struct igt_live_test t;
-	struct drm_file *file;
+	struct file *file;
 	unsigned long n;
 	int err = -ENODEV;
 
@@ -67,25 +74,34 @@ static int live_nop_switch(void *arg)
 	}
 
 	for_each_uabi_engine(engine, i915) {
-		struct i915_request *rq;
+		struct i915_request *rq = NULL;
 		unsigned long end_time, prime;
 		ktime_t times[2] = {};
 
 		times[0] = ktime_get_raw();
 		for (n = 0; n < nctx; n++) {
-			rq = igt_request_alloc(ctx[n], engine);
-			if (IS_ERR(rq)) {
-				err = PTR_ERR(rq);
+			struct i915_request *this;
+
+			this = igt_request_alloc(ctx[n], engine);
+			if (IS_ERR(this)) {
+				err = PTR_ERR(this);
 				goto out_file;
 			}
-			i915_request_add(rq);
+			if (rq) {
+				i915_request_await_dma_fence(this, &rq->fence);
+				i915_request_put(rq);
+			}
+			rq = i915_request_get(this);
+			i915_request_add(this);
 		}
 		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 			pr_err("Failed to populated %d contexts\n", nctx);
 			intel_gt_set_wedged(&i915->gt);
+			i915_request_put(rq);
 			err = -EIO;
 			goto out_file;
 		}
+		i915_request_put(rq);
 
 		times[1] = ktime_get_raw();
 
@@ -100,13 +116,21 @@ static int live_nop_switch(void *arg)
 		for_each_prime_number_from(prime, 2, 8192) {
 			times[1] = ktime_get_raw();
 
+			rq = NULL;
 			for (n = 0; n < prime; n++) {
-				rq = igt_request_alloc(ctx[n % nctx], engine);
-				if (IS_ERR(rq)) {
-					err = PTR_ERR(rq);
+				struct i915_request *this;
+
+				this = igt_request_alloc(ctx[n % nctx], engine);
+				if (IS_ERR(this)) {
+					err = PTR_ERR(this);
 					goto out_file;
 				}
 
+				if (rq) { /* Force submission order */
+					i915_request_await_dma_fence(this, &rq->fence);
+					i915_request_put(rq);
+				}
+
 				/*
 				 * This space is left intentionally blank.
 				 *
@@ -121,14 +145,18 @@ static int live_nop_switch(void *arg)
 				 * for latency.
 				 */
 
-				i915_request_add(rq);
+				rq = i915_request_get(this);
+				i915_request_add(this);
 			}
+			GEM_BUG_ON(!rq);
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				pr_err("Switching between %ld contexts timed out\n",
 				       prime);
 				intel_gt_set_wedged(&i915->gt);
+				i915_request_put(rq);
 				break;
 			}
+			i915_request_put(rq);
 
 			times[1] = ktime_sub(ktime_get_raw(), times[1]);
 			if (prime == 2)
@@ -149,7 +177,7 @@ static int live_nop_switch(void *arg)
 	}
 
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -255,7 +283,7 @@ static int live_parallel_switch(void *arg)
 	int (* const *fn)(void *arg);
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
+	struct file *file;
 	int n, m, count;
 	int err = 0;
 
@@ -309,7 +337,7 @@ static int live_parallel_switch(void *arg)
 			if (!data[m].ce[0])
 				continue;
 
-			ce = intel_context_create(ctx, data[m].ce[0]->engine);
+			ce = intel_context_create(data[m].ce[0]->engine);
 			if (IS_ERR(ce))
 				goto out;
 
@@ -377,7 +405,7 @@ out:
 	}
 	kfree(data);
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -502,17 +530,17 @@ out_unmap:
 	return err;
 }
 
-static int file_add_object(struct drm_file *file,
-			    struct drm_i915_gem_object *obj)
+static int file_add_object(struct file *file, struct drm_i915_gem_object *obj)
 {
 	int err;
 
 	GEM_BUG_ON(obj->base.handle_count);
 
 	/* tie the object to the drm_file for easy reaping */
-	err = idr_alloc(&file->object_idr, &obj->base, 1, 0, GFP_KERNEL);
+	err = idr_alloc(&to_drm_file(file)->object_idr,
+			&obj->base, 1, 0, GFP_KERNEL);
 	if (err < 0)
-		return  err;
+		return err;
 
 	i915_gem_object_get(obj);
 	obj->base.handle_count++;
@@ -521,7 +549,7 @@ static int file_add_object(struct drm_file *file,
 
 static struct drm_i915_gem_object *
 create_test_object(struct i915_address_space *vm,
-		   struct drm_file *file,
+		   struct file *file,
 		   struct list_head *objects)
 {
 	struct drm_i915_gem_object *obj;
@@ -621,9 +649,9 @@ static int igt_ctx_exec(void *arg)
 		unsigned long ncontexts, ndwords, dw;
 		struct i915_request *tq[5] = {};
 		struct igt_live_test t;
-		struct drm_file *file;
 		IGT_TIMEOUT(end_time);
 		LIST_HEAD(objects);
+		struct file *file;
 
 		if (!intel_engine_can_store_dword(engine))
 			continue;
@@ -716,7 +744,7 @@ out_file:
 		if (igt_live_test_end(&t))
 			err = -EIO;
 
-		mock_file_free(i915, file);
+		fput(file);
 		if (err)
 			return err;
 
@@ -733,7 +761,7 @@ static int igt_shared_ctx_exec(void *arg)
 	struct i915_gem_context *parent;
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
-	struct drm_file *file;
+	struct file *file;
 	int err = 0;
 
 	/*
@@ -786,14 +814,15 @@ static int igt_shared_ctx_exec(void *arg)
 			}
 
 			mutex_lock(&ctx->mutex);
-			__assign_ppgtt(ctx, parent->vm);
+			__assign_ppgtt(ctx, ctx_vm(parent));
 			mutex_unlock(&ctx->mutex);
 
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
 			GEM_BUG_ON(IS_ERR(ce));
 
 			if (!obj) {
-				obj = create_test_object(parent->vm, file, &objects);
+				obj = create_test_object(ctx_vm(parent),
+							 file, &objects);
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
 					intel_context_put(ce);
@@ -854,7 +883,7 @@ out_test:
 	if (igt_live_test_end(&t))
 		err = -EIO;
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -1140,8 +1169,7 @@ out:
 		igt_spinner_end(spin);
 
 	if ((flags & TEST_IDLE) && ret == 0) {
-		ret = intel_gt_wait_for_idle(ce->engine->gt,
-					     MAX_SCHEDULE_TIMEOUT);
+		ret = igt_flush_test(ce->engine->i915);
 		if (ret)
 			return ret;
 
@@ -1163,9 +1191,11 @@ __sseu_test(const char *name,
 	struct igt_spinner *spin = NULL;
 	int ret;
 
+	intel_engine_pm_get(ce->engine);
+
 	ret = __sseu_prepare(name, flags, ce, &spin);
 	if (ret)
-		return ret;
+		goto out_pm;
 
 	ret = intel_context_reconfigure_sseu(ce, sseu);
 	if (ret)
@@ -1180,6 +1210,8 @@ out_spin:
 		igt_spinner_fini(spin);
 		kfree(spin);
 	}
+out_pm:
+	intel_engine_pm_put(ce->engine);
 	return ret;
 }
 
@@ -1232,8 +1264,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 			hweight32(engine->sseu.slice_mask),
 			hweight32(pg_sseu.slice_mask));
 
-		ce = intel_context_create(engine->kernel_context->gem_context,
-					  engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			ret = PTR_ERR(ce);
 			goto out_put;
@@ -1311,16 +1342,18 @@ static int igt_ctx_sseu(void *arg)
 static int igt_ctx_readonly(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
+	unsigned long idx, ndwords, dw, num_engines;
 	struct drm_i915_gem_object *obj = NULL;
 	struct i915_request *tq[5] = {};
+	struct i915_gem_engines_iter it;
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
-	unsigned long idx, ndwords, dw;
+	struct intel_context *ce;
 	struct igt_live_test t;
-	struct drm_file *file;
 	I915_RND_STATE(prng);
 	IGT_TIMEOUT(end_time);
 	LIST_HEAD(objects);
+	struct file *file;
 	int err = -ENODEV;
 
 	/*
@@ -1343,21 +1376,21 @@ static int igt_ctx_readonly(void *arg)
 		goto out_file;
 	}
 
-	rcu_read_lock();
-	vm = rcu_dereference(ctx->vm) ?: &i915->ggtt.alias->vm;
+	vm = ctx_vm(ctx) ?: &i915->ggtt.alias->vm;
 	if (!vm || !vm->has_read_only) {
-		rcu_read_unlock();
 		err = 0;
 		goto out_file;
 	}
-	rcu_read_unlock();
+
+	num_engines = 0;
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it)
+		if (intel_engine_can_store_dword(ce->engine))
+			num_engines++;
+	i915_gem_context_unlock_engines(ctx);
 
 	ndwords = 0;
 	dw = 0;
 	while (!time_after(jiffies, end_time)) {
-		struct i915_gem_engines_iter it;
-		struct intel_context *ce;
-
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
 			if (!intel_engine_can_store_dword(ce->engine))
@@ -1380,7 +1413,7 @@ static int igt_ctx_readonly(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       ce->engine->name,
-				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       yesno(!!ctx_vm(ctx)),
 				       err);
 				i915_gem_context_unlock_engines(ctx);
 				goto out_file;
@@ -1400,8 +1433,8 @@ static int igt_ctx_readonly(void *arg)
 		}
 		i915_gem_context_unlock_engines(ctx);
 	}
-	pr_info("Submitted %lu dwords (across %u engines)\n",
-		ndwords, RUNTIME_INFO(i915)->num_engines);
+	pr_info("Submitted %lu dwords (across %lu engines)\n",
+		ndwords, num_engines);
 
 	dw = 0;
 	idx = 0;
@@ -1426,7 +1459,7 @@ out_file:
 	if (igt_live_test_end(&t))
 		err = -EIO;
 
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -1466,7 +1499,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err;
+		goto out;
 	}
 
 	*cmd++ = MI_STORE_DWORD_IMM_GEN4;
@@ -1488,12 +1521,12 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto err_vm;
+		goto out_vm;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED);
 	if (err)
-		goto err_vm;
+		goto out_vm;
 
 	err = check_scratch(vm, offset);
 	if (err)
@@ -1517,22 +1550,20 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	if (err)
 		goto skip_request;
 
-	i915_vma_unpin_and_release(&vma, 0);
+	i915_vma_unpin(vma);
 
 	i915_request_add(rq);
 
-	i915_vm_put(vm);
-	return 0;
-
+	goto out_vm;
 skip_request:
 	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
-err_vm:
+out_vm:
 	i915_vm_put(vm);
-err:
+out:
 	i915_gem_object_put(obj);
 	return err;
 }
@@ -1560,7 +1591,7 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err;
+		goto out;
 	}
 
 	memset(cmd, POISON_INUSE, PAGE_SIZE);
@@ -1592,12 +1623,12 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto err_vm;
+		goto out_vm;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED);
 	if (err)
-		goto err_vm;
+		goto out_vm;
 
 	err = check_scratch(vm, offset);
 	if (err)
@@ -1630,29 +1661,27 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	err = i915_gem_object_set_to_cpu_domain(obj, false);
 	i915_gem_object_unlock(obj);
 	if (err)
-		goto err_vm;
+		goto out_vm;
 
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err_vm;
+		goto out_vm;
 	}
 
 	*value = cmd[result / sizeof(*cmd)];
 	i915_gem_object_unpin_map(obj);
-	i915_gem_object_put(obj);
-
-	return 0;
 
+	goto out_vm;
 skip_request:
 	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
-err_vm:
+out_vm:
 	i915_vm_put(vm);
-err:
+out:
 	i915_gem_object_put(obj);
 	return err;
 }
@@ -1661,11 +1690,11 @@ static int igt_vm_isolation(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx_a, *ctx_b;
+	unsigned long num_engines, count;
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
-	struct drm_file *file;
 	I915_RND_STATE(prng);
-	unsigned long count;
+	struct file *file;
 	u64 vm_total;
 	int err;
 
@@ -1698,14 +1727,15 @@ static int igt_vm_isolation(void *arg)
 	}
 
 	/* We can only test vm isolation, if the vm are distinct */
-	if (ctx_a->vm == ctx_b->vm)
+	if (ctx_vm(ctx_a) == ctx_vm(ctx_b))
 		goto out_file;
 
-	vm_total = ctx_a->vm->total;
-	GEM_BUG_ON(ctx_b->vm->total != vm_total);
+	vm_total = ctx_vm(ctx_a)->total;
+	GEM_BUG_ON(ctx_vm(ctx_b)->total != vm_total);
 	vm_total -= I915_GTT_PAGE_SIZE;
 
 	count = 0;
+	num_engines = 0;
 	for_each_uabi_engine(engine, i915) {
 		IGT_TIMEOUT(end_time);
 		unsigned long this = 0;
@@ -1743,14 +1773,15 @@ static int igt_vm_isolation(void *arg)
 			this++;
 		}
 		count += this;
+		num_engines++;
 	}
-	pr_info("Checked %lu scratch offsets across %d engines\n",
-		count, RUNTIME_INFO(i915)->num_engines);
+	pr_info("Checked %lu scratch offsets across %lu engines\n",
+		count, num_engines);
 
 out_file:
 	if (igt_live_test_end(&t))
 		err = -EIO;
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
index d85d1ce273ca..2a52b92586b9 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c
@@ -254,106 +254,6 @@ err_obj:
 	return err;
 }
 
-static int igt_dmabuf_export_kmap(void *arg)
-{
-	struct drm_i915_private *i915 = arg;
-	struct drm_i915_gem_object *obj;
-	struct dma_buf *dmabuf;
-	void *ptr;
-	int err;
-
-	obj = i915_gem_object_create_shmem(i915, 2 * PAGE_SIZE);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
-
-	dmabuf = i915_gem_prime_export(&obj->base, 0);
-	i915_gem_object_put(obj);
-	if (IS_ERR(dmabuf)) {
-		err = PTR_ERR(dmabuf);
-		pr_err("i915_gem_prime_export failed with err=%d\n", err);
-		return err;
-	}
-
-	ptr = dma_buf_kmap(dmabuf, 0);
-	if (!ptr) {
-		pr_err("dma_buf_kmap failed\n");
-		err = -ENOMEM;
-		goto err;
-	}
-
-	if (memchr_inv(ptr, 0, PAGE_SIZE)) {
-		dma_buf_kunmap(dmabuf, 0, ptr);
-		pr_err("Exported page[0] not initialiased to zero!\n");
-		err = -EINVAL;
-		goto err;
-	}
-
-	memset(ptr, 0xc5, PAGE_SIZE);
-	dma_buf_kunmap(dmabuf, 0, ptr);
-
-	ptr = i915_gem_object_pin_map(obj, I915_MAP_WB);
-	if (IS_ERR(ptr)) {
-		err = PTR_ERR(ptr);
-		pr_err("i915_gem_object_pin_map failed with err=%d\n", err);
-		goto err;
-	}
-	memset(ptr + PAGE_SIZE, 0xaa, PAGE_SIZE);
-	i915_gem_object_flush_map(obj);
-	i915_gem_object_unpin_map(obj);
-
-	ptr = dma_buf_kmap(dmabuf, 1);
-	if (!ptr) {
-		pr_err("dma_buf_kmap failed\n");
-		err = -ENOMEM;
-		goto err;
-	}
-
-	if (memchr_inv(ptr, 0xaa, PAGE_SIZE)) {
-		dma_buf_kunmap(dmabuf, 1, ptr);
-		pr_err("Exported page[1] not set to 0xaa!\n");
-		err = -EINVAL;
-		goto err;
-	}
-
-	memset(ptr, 0xc5, PAGE_SIZE);
-	dma_buf_kunmap(dmabuf, 1, ptr);
-
-	ptr = dma_buf_kmap(dmabuf, 0);
-	if (!ptr) {
-		pr_err("dma_buf_kmap failed\n");
-		err = -ENOMEM;
-		goto err;
-	}
-	if (memchr_inv(ptr, 0xc5, PAGE_SIZE)) {
-		dma_buf_kunmap(dmabuf, 0, ptr);
-		pr_err("Exported page[0] did not retain 0xc5!\n");
-		err = -EINVAL;
-		goto err;
-	}
-	dma_buf_kunmap(dmabuf, 0, ptr);
-
-	ptr = dma_buf_kmap(dmabuf, 2);
-	if (ptr) {
-		pr_err("Erroneously kmapped beyond the end of the object!\n");
-		dma_buf_kunmap(dmabuf, 2, ptr);
-		err = -EINVAL;
-		goto err;
-	}
-
-	ptr = dma_buf_kmap(dmabuf, -1);
-	if (ptr) {
-		pr_err("Erroneously kmapped before the start of the object!\n");
-		dma_buf_kunmap(dmabuf, -1, ptr);
-		err = -EINVAL;
-		goto err;
-	}
-
-	err = 0;
-err:
-	dma_buf_put(dmabuf);
-	return err;
-}
-
 int i915_gem_dmabuf_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
@@ -362,7 +262,6 @@ int i915_gem_dmabuf_mock_selftests(void)
 		SUBTEST(igt_dmabuf_import),
 		SUBTEST(igt_dmabuf_import_ownership),
 		SUBTEST(igt_dmabuf_export_vmap),
-		SUBTEST(igt_dmabuf_export_kmap),
 	};
 	struct drm_i915_private *i915;
 	int err;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 29b2077b73d2..ef7c74cff28a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -6,12 +6,15 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gem/i915_gem_region.h"
 #include "huge_gem_object.h"
 #include "i915_selftest.h"
 #include "selftests/i915_random.h"
 #include "selftests/igt_flush_test.h"
+#include "selftests/igt_mmap.h"
 
 struct tile {
 	unsigned int width;
@@ -161,7 +164,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 	kunmap(p);
 
 out:
-	i915_vma_destroy(vma);
+	__i915_vma_put(vma);
 	return err;
 }
 
@@ -255,7 +258,7 @@ static int check_partial_mappings(struct drm_i915_gem_object *obj,
 		if (err)
 			return err;
 
-		i915_vma_destroy(vma);
+		__i915_vma_put(vma);
 
 		if (igt_timeout(end_time,
 				"%s: timed out after tiling=%d stride=%d\n",
@@ -535,7 +538,7 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		if (err)
 			return err;
 
-		rq = i915_request_create(engine->kernel_context);
+		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
 			i915_vma_unpin(vma);
 			return PTR_ERR(rq);
@@ -563,16 +566,16 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 			       int expected)
 {
 	struct drm_i915_gem_object *obj;
-	int err;
+	struct i915_mmap_offset *mmo;
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	err = create_mmap_offset(obj);
+	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
 	i915_gem_object_put(obj);
 
-	return err == expected;
+	return PTR_ERR_OR_ZERO(mmo) == expected;
 }
 
 static void disable_retire_worker(struct drm_i915_private *i915)
@@ -606,28 +609,50 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct drm_mm *mm = &i915->drm.vma_offset_manager->vm_addr_space_mm;
 	struct drm_i915_gem_object *obj;
-	struct drm_mm_node resv, *hole;
-	u64 hole_start, hole_end;
-	int loop, err;
+	struct drm_mm_node *hole, *next;
+	struct i915_mmap_offset *mmo;
+	int loop, err = 0;
 
 	/* Disable background reaper */
 	disable_retire_worker(i915);
 	GEM_BUG_ON(!i915->gt.awake);
+	intel_gt_retire_requests(&i915->gt);
+	i915_gem_drain_freed_objects(i915);
 
 	/* Trim the device mmap space to only a page */
-	memset(&resv, 0, sizeof(resv));
-	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
-		resv.start = hole_start;
-		resv.size = hole_end - hole_start - 1; /* PAGE_SIZE units */
-		mmap_offset_lock(i915);
-		err = drm_mm_reserve_node(mm, &resv);
-		mmap_offset_unlock(i915);
+	mmap_offset_lock(i915);
+	loop = 1; /* PAGE_SIZE units */
+	list_for_each_entry_safe(hole, next, &mm->hole_stack, hole_stack) {
+		struct drm_mm_node *resv;
+
+		resv = kzalloc(sizeof(*resv), GFP_NOWAIT);
+		if (!resv) {
+			err = -ENOMEM;
+			goto out_park;
+		}
+
+		resv->start = drm_mm_hole_node_start(hole) + loop;
+		resv->size = hole->hole_size - loop;
+		resv->color = -1ul;
+		loop = 0;
+
+		if (!resv->size) {
+			kfree(resv);
+			continue;
+		}
+
+		pr_debug("Reserving hole [%llx + %llx]\n",
+			 resv->start, resv->size);
+
+		err = drm_mm_reserve_node(mm, resv);
 		if (err) {
 			pr_err("Failed to trim VMA manager, err=%d\n", err);
+			kfree(resv);
 			goto out_park;
 		}
-		break;
 	}
+	GEM_BUG_ON(!list_is_singular(&mm->hole_stack));
+	mmap_offset_unlock(i915);
 
 	/* Just fits! */
 	if (!assert_mmap_offset(i915, PAGE_SIZE, 0)) {
@@ -650,9 +675,10 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		goto out;
 	}
 
-	err = create_mmap_offset(obj);
-	if (err) {
+	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
+	if (IS_ERR(mmo)) {
 		pr_err("Unable to insert object into reclaimed hole\n");
+		err = PTR_ERR(mmo);
 		goto err_obj;
 	}
 
@@ -684,9 +710,15 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 out:
 	mmap_offset_lock(i915);
-	drm_mm_remove_node(&resv);
-	mmap_offset_unlock(i915);
 out_park:
+	drm_mm_for_each_node_safe(hole, next, mm) {
+		if (hole->color != -1ul)
+			continue;
+
+		drm_mm_remove_node(hole);
+		kfree(hole);
+	}
+	mmap_offset_unlock(i915);
 	restore_retire_worker(i915);
 	return err;
 err_obj:
@@ -694,12 +726,515 @@ err_obj:
 	goto out;
 }
 
+static int gtt_set(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	void __iomem *map;
+	int err = 0;
+
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	intel_gt_pm_get(vma->vm->gt);
+	map = i915_vma_pin_iomap(vma);
+	i915_vma_unpin(vma);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out;
+	}
+
+	memset_io(map, POISON_INUSE, obj->base.size);
+	i915_vma_unpin_iomap(vma);
+
+out:
+	intel_gt_pm_put(vma->vm->gt);
+	return err;
+}
+
+static int gtt_check(struct drm_i915_gem_object *obj)
+{
+	struct i915_vma *vma;
+	void __iomem *map;
+	int err = 0;
+
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	intel_gt_pm_get(vma->vm->gt);
+	map = i915_vma_pin_iomap(vma);
+	i915_vma_unpin(vma);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out;
+	}
+
+	if (memchr_inv((void __force *)map, POISON_FREE, obj->base.size)) {
+		pr_err("%s: Write via mmap did not land in backing store (GTT)\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+	}
+	i915_vma_unpin_iomap(vma);
+
+out:
+	intel_gt_pm_put(vma->vm->gt);
+	return err;
+}
+
+static int wc_set(struct drm_i915_gem_object *obj)
+{
+	void *vaddr;
+
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	memset(vaddr, POISON_INUSE, obj->base.size);
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
+
+	return 0;
+}
+
+static int wc_check(struct drm_i915_gem_object *obj)
+{
+	void *vaddr;
+	int err = 0;
+
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
+
+	if (memchr_inv(vaddr, POISON_FREE, obj->base.size)) {
+		pr_err("%s: Write via mmap did not land in backing store (WC)\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+	}
+	i915_gem_object_unpin_map(obj);
+
+	return err;
+}
+
+static bool can_mmap(struct drm_i915_gem_object *obj, enum i915_mmap_type type)
+{
+	if (type == I915_MMAP_TYPE_GTT &&
+	    !i915_ggtt_has_aperture(&to_i915(obj->base.dev)->ggtt))
+		return false;
+
+	if (type != I915_MMAP_TYPE_GTT &&
+	    !i915_gem_object_type_has(obj,
+				      I915_GEM_OBJECT_HAS_STRUCT_PAGE |
+				      I915_GEM_OBJECT_HAS_IOMEM))
+		return false;
+
+	return true;
+}
+
+#define expand32(x) (((x) << 0) | ((x) << 8) | ((x) << 16) | ((x) << 24))
+static int __igt_mmap(struct drm_i915_private *i915,
+		      struct drm_i915_gem_object *obj,
+		      enum i915_mmap_type type)
+{
+	struct i915_mmap_offset *mmo;
+	struct vm_area_struct *area;
+	unsigned long addr;
+	int err, i;
+
+	if (!can_mmap(obj, type))
+		return 0;
+
+	err = wc_set(obj);
+	if (err == -ENXIO)
+		err = gtt_set(obj);
+	if (err)
+		return err;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	pr_debug("igt_mmap(%s, %d) @ %lx\n", obj->mm.region->name, type, addr);
+
+	area = find_vma(current->mm, addr);
+	if (!area) {
+		pr_err("%s: Did not create a vm_area_struct for the mmap\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+		goto out_unmap;
+	}
+
+	if (area->vm_private_data != mmo) {
+		pr_err("%s: vm_area_struct did not point back to our mmap_offset object!\n",
+		       obj->mm.region->name);
+		err = -EINVAL;
+		goto out_unmap;
+	}
+
+	for (i = 0; i < obj->base.size / sizeof(u32); i++) {
+		u32 __user *ux = u64_to_user_ptr((u64)(addr + i * sizeof(*ux)));
+		u32 x;
+
+		if (get_user(x, ux)) {
+			pr_err("%s: Unable to read from mmap, offset:%zd\n",
+			       obj->mm.region->name, i * sizeof(x));
+			err = -EFAULT;
+			goto out_unmap;
+		}
+
+		if (x != expand32(POISON_INUSE)) {
+			pr_err("%s: Read incorrect value from mmap, offset:%zd, found:%x, expected:%x\n",
+			       obj->mm.region->name,
+			       i * sizeof(x), x, expand32(POISON_INUSE));
+			err = -EINVAL;
+			goto out_unmap;
+		}
+
+		x = expand32(POISON_FREE);
+		if (put_user(x, ux)) {
+			pr_err("%s: Unable to write to mmap, offset:%zd\n",
+			       obj->mm.region->name, i * sizeof(x));
+			err = -EFAULT;
+			goto out_unmap;
+		}
+	}
+
+	if (type == I915_MMAP_TYPE_GTT)
+		intel_gt_flush_ggtt_writes(&i915->gt);
+
+	err = wc_check(obj);
+	if (err == -ENXIO)
+		err = gtt_check(obj);
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		unsigned long sizes[] = {
+			PAGE_SIZE,
+			mr->min_page_size,
+			SZ_4M,
+		};
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+			struct drm_i915_gem_object *obj;
+			int err;
+
+			obj = i915_gem_object_create_region(mr, sizes[i], 0);
+			if (obj == ERR_PTR(-ENODEV))
+				continue;
+
+			if (IS_ERR(obj))
+				return PTR_ERR(obj);
+
+			err = __igt_mmap(i915, obj, I915_MMAP_TYPE_GTT);
+			if (err == 0)
+				err = __igt_mmap(i915, obj, I915_MMAP_TYPE_WC);
+
+			i915_gem_object_put(obj);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+static int __igt_mmap_gpu(struct drm_i915_private *i915,
+			  struct drm_i915_gem_object *obj,
+			  enum i915_mmap_type type)
+{
+	struct intel_engine_cs *engine;
+	struct i915_mmap_offset *mmo;
+	unsigned long addr;
+	u32 __user *ux;
+	u32 bbe;
+	int err;
+
+	/*
+	 * Verify that the mmap access into the backing store aligns with
+	 * that of the GPU, i.e. that mmap is indeed writing into the same
+	 * page as being read by the GPU.
+	 */
+
+	if (!can_mmap(obj, type))
+		return 0;
+
+	err = wc_set(obj);
+	if (err == -ENXIO)
+		err = gtt_set(obj);
+	if (err)
+		return err;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	ux = u64_to_user_ptr((u64)addr);
+	bbe = MI_BATCH_BUFFER_END;
+	if (put_user(bbe, ux)) {
+		pr_err("%s: Unable to write to mmap\n", obj->mm.region->name);
+		err = -EFAULT;
+		goto out_unmap;
+	}
+
+	if (type == I915_MMAP_TYPE_GTT)
+		intel_gt_flush_ggtt_writes(&i915->gt);
+
+	for_each_uabi_engine(engine, i915) {
+		struct i915_request *rq;
+		struct i915_vma *vma;
+
+		vma = i915_vma_instance(obj, engine->kernel_context->vm, NULL);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			goto out_unmap;
+		}
+
+		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		if (err)
+			goto out_unmap;
+
+		rq = i915_request_create(engine->kernel_context);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_unpin;
+		}
+
+		i915_vma_lock(vma);
+		err = i915_request_await_object(rq, vma->obj, false);
+		if (err == 0)
+			err = i915_vma_move_to_active(vma, rq, 0);
+		i915_vma_unlock(vma);
+
+		err = engine->emit_bb_start(rq, vma->node.start, 0, 0);
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+			struct drm_printer p =
+				drm_info_printer(engine->i915->drm.dev);
+
+			pr_err("%s(%s, %s): Failed to execute batch\n",
+			       __func__, engine->name, obj->mm.region->name);
+			intel_engine_dump(engine, &p,
+					  "%s\n", engine->name);
+
+			intel_gt_set_wedged(engine->gt);
+			err = -EIO;
+		}
+		i915_request_put(rq);
+
+out_unpin:
+		i915_vma_unpin(vma);
+		if (err)
+			goto out_unmap;
+	}
+
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap_gpu(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		struct drm_i915_gem_object *obj;
+		int err;
+
+		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		if (obj == ERR_PTR(-ENODEV))
+			continue;
+
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_GTT);
+		if (err == 0)
+			err = __igt_mmap_gpu(i915, obj, I915_MMAP_TYPE_WC);
+
+		i915_gem_object_put(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int check_present_pte(pte_t *pte, unsigned long addr, void *data)
+{
+	if (!pte_present(*pte) || pte_none(*pte)) {
+		pr_err("missing PTE:%lx\n",
+		       (addr - (unsigned long)data) >> PAGE_SHIFT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_absent_pte(pte_t *pte, unsigned long addr, void *data)
+{
+	if (pte_present(*pte) && !pte_none(*pte)) {
+		pr_err("present PTE:%lx; expected to be revoked\n",
+		       (addr - (unsigned long)data) >> PAGE_SHIFT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int check_present(unsigned long addr, unsigned long len)
+{
+	return apply_to_page_range(current->mm, addr, len,
+				   check_present_pte, (void *)addr);
+}
+
+static int check_absent(unsigned long addr, unsigned long len)
+{
+	return apply_to_page_range(current->mm, addr, len,
+				   check_absent_pte, (void *)addr);
+}
+
+static int prefault_range(u64 start, u64 len)
+{
+	const char __user *addr, *end;
+	char __maybe_unused c;
+	int err;
+
+	addr = u64_to_user_ptr(start);
+	end = addr + len;
+
+	for (; addr < end; addr += PAGE_SIZE) {
+		err = __get_user(c, addr);
+		if (err)
+			return err;
+	}
+
+	return __get_user(c, end - 1);
+}
+
+static int __igt_mmap_revoke(struct drm_i915_private *i915,
+			     struct drm_i915_gem_object *obj,
+			     enum i915_mmap_type type)
+{
+	struct i915_mmap_offset *mmo;
+	unsigned long addr;
+	int err;
+
+	if (!can_mmap(obj, type))
+		return 0;
+
+	mmo = mmap_offset_attach(obj, type, NULL);
+	if (IS_ERR(mmo))
+		return PTR_ERR(mmo);
+
+	addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
+	err = prefault_range(addr, obj->base.size);
+	if (err)
+		goto out_unmap;
+
+	GEM_BUG_ON(mmo->mmap_type == I915_MMAP_TYPE_GTT &&
+		   !atomic_read(&obj->bind_count));
+
+	err = check_present(addr, obj->base.size);
+	if (err) {
+		pr_err("%s: was not present\n", obj->mm.region->name);
+		goto out_unmap;
+	}
+
+	/*
+	 * After unbinding the object from the GGTT, its address may be reused
+	 * for other objects. Ergo we have to revoke the previous mmap PTE
+	 * access as it no longer points to the same object.
+	 */
+	err = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE);
+	if (err) {
+		pr_err("Failed to unbind object!\n");
+		goto out_unmap;
+	}
+	GEM_BUG_ON(atomic_read(&obj->bind_count));
+
+	if (type != I915_MMAP_TYPE_GTT) {
+		__i915_gem_object_put_pages(obj);
+		if (i915_gem_object_has_pages(obj)) {
+			pr_err("Failed to put-pages object!\n");
+			err = -EINVAL;
+			goto out_unmap;
+		}
+	}
+
+	err = check_absent(addr, obj->base.size);
+	if (err) {
+		pr_err("%s: was not absent\n", obj->mm.region->name);
+		goto out_unmap;
+	}
+
+out_unmap:
+	vm_munmap(addr, obj->base.size);
+	return err;
+}
+
+static int igt_mmap_revoke(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
+
+	for_each_memory_region(mr, i915, id) {
+		struct drm_i915_gem_object *obj;
+		int err;
+
+		obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0);
+		if (obj == ERR_PTR(-ENODEV))
+			continue;
+
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_GTT);
+		if (err == 0)
+			err = __igt_mmap_revoke(i915, obj, I915_MMAP_TYPE_WC);
+
+		i915_gem_object_put(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 int i915_gem_mman_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_partial_tiling),
 		SUBTEST(igt_smoke_tiling),
 		SUBTEST(igt_mmap_offset_exhaustion),
+		SUBTEST(igt_mmap),
+		SUBTEST(igt_mmap_revoke),
+		SUBTEST(igt_mmap_gpu),
 	};
 
 	return i915_subtests(tests, i915);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index e8132aca0bb6..62077fe46715 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -41,6 +41,7 @@ static int __perf_fill_blt(struct drm_i915_gem_object *obj)
 		if (!engine)
 			return 0;
 
+		intel_engine_pm_get(engine);
 		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
 			struct intel_context *ce = engine->kernel_context;
 			ktime_t t0, t1;
@@ -49,17 +50,20 @@ static int __perf_fill_blt(struct drm_i915_gem_object *obj)
 
 			err = i915_gem_object_fill_blt(obj, ce, 0);
 			if (err)
-				return err;
+				break;
 
 			err = i915_gem_object_wait(obj,
 						   I915_WAIT_ALL,
 						   MAX_SCHEDULE_TIMEOUT);
 			if (err)
-				return err;
+				break;
 
 			t1 = ktime_get();
 			t[pass] = ktime_sub(t1, t0);
 		}
+		intel_engine_pm_put(engine);
+		if (err)
+			return err;
 
 		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
 		pr_info("%s: blt %zd KiB fill: %lld MiB/s\n",
@@ -109,6 +113,7 @@ static int __perf_copy_blt(struct drm_i915_gem_object *src,
 		struct intel_engine_cs *engine;
 		ktime_t t[5];
 		int pass;
+		int err = 0;
 
 		engine = intel_engine_lookup_user(i915,
 						  I915_ENGINE_CLASS_COPY,
@@ -116,26 +121,29 @@ static int __perf_copy_blt(struct drm_i915_gem_object *src,
 		if (!engine)
 			return 0;
 
+		intel_engine_pm_get(engine);
 		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
 			struct intel_context *ce = engine->kernel_context;
 			ktime_t t0, t1;
-			int err;
 
 			t0 = ktime_get();
 
 			err = i915_gem_object_copy_blt(src, dst, ce);
 			if (err)
-				return err;
+				break;
 
 			err = i915_gem_object_wait(dst,
 						   I915_WAIT_ALL,
 						   MAX_SCHEDULE_TIMEOUT);
 			if (err)
-				return err;
+				break;
 
 			t1 = ktime_get();
 			t[pass] = ktime_sub(t1, t0);
 		}
+		intel_engine_pm_put(engine);
+		if (err)
+			return err;
 
 		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
 		pr_info("%s: blt %zd KiB copy: %lld MiB/s\n",
@@ -186,6 +194,8 @@ err_src:
 
 struct igt_thread_arg {
 	struct drm_i915_private *i915;
+	struct i915_gem_context *ctx;
+	struct file *file;
 	struct rnd_state prng;
 	unsigned int n_cpus;
 };
@@ -198,24 +208,20 @@ static int igt_fill_blt_thread(void *arg)
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
 	unsigned int prio;
 	IGT_TIMEOUT(end);
 	int err;
 
-	file = mock_file(i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	ctx = thread->ctx;
+	if (!ctx) {
+		ctx = live_context(i915, thread->file);
+		if (IS_ERR(ctx))
+			return PTR_ERR(ctx);
 
-	ctx = live_context(i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_file;
+		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
+		ctx->sched.priority = I915_USER_PRIORITY(prio);
 	}
 
-	prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-	ctx->sched.priority = I915_USER_PRIORITY(prio);
-
 	ce = i915_gem_context_get_engine(ctx, BCS0);
 	GEM_BUG_ON(IS_ERR(ce));
 
@@ -300,8 +306,6 @@ err_flush:
 		err = 0;
 
 	intel_context_put(ce);
-out_file:
-	mock_file_free(i915, file);
 	return err;
 }
 
@@ -313,24 +317,20 @@ static int igt_copy_blt_thread(void *arg)
 	struct drm_i915_gem_object *src, *dst;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
 	unsigned int prio;
 	IGT_TIMEOUT(end);
 	int err;
 
-	file = mock_file(i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	ctx = thread->ctx;
+	if (!ctx) {
+		ctx = live_context(i915, thread->file);
+		if (IS_ERR(ctx))
+			return PTR_ERR(ctx);
 
-	ctx = live_context(i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_file;
+		prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
+		ctx->sched.priority = I915_USER_PRIORITY(prio);
 	}
 
-	prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
-	ctx->sched.priority = I915_USER_PRIORITY(prio);
-
 	ce = i915_gem_context_get_engine(ctx, BCS0);
 	GEM_BUG_ON(IS_ERR(ce));
 
@@ -431,19 +431,18 @@ err_flush:
 		err = 0;
 
 	intel_context_put(ce);
-out_file:
-	mock_file_free(i915, file);
 	return err;
 }
 
 static int igt_threaded_blt(struct drm_i915_private *i915,
-			    int (*blt_fn)(void *arg))
+			    int (*blt_fn)(void *arg),
+			    unsigned int flags)
+#define SINGLE_CTX BIT(0)
 {
 	struct igt_thread_arg *thread;
 	struct task_struct **tsk;
+	unsigned int n_cpus, i;
 	I915_RND_STATE(prng);
-	unsigned int n_cpus;
-	unsigned int i;
 	int err = 0;
 
 	n_cpus = num_online_cpus() + 1;
@@ -453,13 +452,27 @@ static int igt_threaded_blt(struct drm_i915_private *i915,
 		return 0;
 
 	thread = kcalloc(n_cpus, sizeof(struct igt_thread_arg), GFP_KERNEL);
-	if (!thread) {
-		kfree(tsk);
-		return 0;
+	if (!thread)
+		goto out_tsk;
+
+	thread[0].file = mock_file(i915);
+	if (IS_ERR(thread[0].file)) {
+		err = PTR_ERR(thread[0].file);
+		goto out_thread;
+	}
+
+	if (flags & SINGLE_CTX) {
+		thread[0].ctx = live_context(i915, thread[0].file);
+		if (IS_ERR(thread[0].ctx)) {
+			err = PTR_ERR(thread[0].ctx);
+			goto out_file;
+		}
 	}
 
 	for (i = 0; i < n_cpus; ++i) {
 		thread[i].i915 = i915;
+		thread[i].file = thread[0].file;
+		thread[i].ctx = thread[0].ctx;
 		thread[i].n_cpus = n_cpus;
 		thread[i].prng =
 			I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
@@ -488,29 +501,42 @@ static int igt_threaded_blt(struct drm_i915_private *i915,
 		put_task_struct(tsk[i]);
 	}
 
-	kfree(tsk);
+out_file:
+	fput(thread[0].file);
+out_thread:
 	kfree(thread);
-
+out_tsk:
+	kfree(tsk);
 	return err;
 }
 
 static int igt_fill_blt(void *arg)
 {
-	return igt_threaded_blt(arg, igt_fill_blt_thread);
+	return igt_threaded_blt(arg, igt_fill_blt_thread, 0);
+}
+
+static int igt_fill_blt_ctx0(void *arg)
+{
+	return igt_threaded_blt(arg, igt_fill_blt_thread, SINGLE_CTX);
 }
 
 static int igt_copy_blt(void *arg)
 {
-	return igt_threaded_blt(arg, igt_copy_blt_thread);
+	return igt_threaded_blt(arg, igt_copy_blt_thread, 0);
+}
+
+static int igt_copy_blt_ctx0(void *arg)
+{
+	return igt_threaded_blt(arg, igt_copy_blt_thread, SINGLE_CTX);
 }
 
 int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
-		SUBTEST(perf_fill_blt),
-		SUBTEST(perf_copy_blt),
 		SUBTEST(igt_fill_blt),
+		SUBTEST(igt_fill_blt_ctx0),
 		SUBTEST(igt_copy_blt),
+		SUBTEST(igt_copy_blt_ctx0),
 	};
 
 	if (intel_gt_is_wedged(&i915->gt))
@@ -521,3 +547,16 @@ int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
 
 	return i915_live_subtests(tests, i915);
 }
+
+int i915_gem_object_blt_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_fill_blt),
+		SUBTEST(perf_copy_blt),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_live_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index 29b8984f0e47..384143aa7776 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -5,6 +5,7 @@
  */
 
 #include "mock_context.h"
+#include "selftests/mock_drm.h"
 #include "selftests/mock_gtt.h"
 
 struct i915_gem_context *
@@ -36,9 +37,7 @@ mock_context(struct drm_i915_private *i915,
 	if (name) {
 		struct i915_ppgtt *ppgtt;
 
-		ctx->name = kstrdup(name, GFP_KERNEL);
-		if (!ctx->name)
-			goto err_put;
+		strncpy(ctx->name, name, sizeof(ctx->name));
 
 		ppgtt = mock_ppgtt(i915, name);
 		if (!ppgtt)
@@ -74,16 +73,17 @@ void mock_init_contexts(struct drm_i915_private *i915)
 }
 
 struct i915_gem_context *
-live_context(struct drm_i915_private *i915, struct drm_file *file)
+live_context(struct drm_i915_private *i915, struct file *file)
 {
 	struct i915_gem_context *ctx;
 	int err;
+	u32 id;
 
 	ctx = i915_gem_create_context(i915, 0);
 	if (IS_ERR(ctx))
 		return ctx;
 
-	err = gem_context_register(ctx, file->driver_priv);
+	err = gem_context_register(ctx, to_drm_file(file)->driver_priv, &id);
 	if (err < 0)
 		goto err_ctx;
 
@@ -97,7 +97,16 @@ err_ctx:
 struct i915_gem_context *
 kernel_context(struct drm_i915_private *i915)
 {
-	return i915_gem_context_create_kernel(i915, I915_PRIORITY_NORMAL);
+	struct i915_gem_context *ctx;
+
+	ctx = i915_gem_create_context(i915, 0);
+	if (IS_ERR(ctx))
+		return ctx;
+
+	i915_gem_context_clear_bannable(ctx);
+	i915_gem_context_set_persistence(ctx);
+
+	return ctx;
 }
 
 void kernel_context_close(struct i915_gem_context *ctx)
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.h b/drivers/gpu/drm/i915/gem/selftests/mock_context.h
index 0b926653914f..fb83d2f09212 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.h
@@ -7,6 +7,9 @@
 #ifndef __MOCK_CONTEXT_H
 #define __MOCK_CONTEXT_H
 
+struct file;
+struct drm_i915_private;
+
 void mock_init_contexts(struct drm_i915_private *i915);
 
 struct i915_gem_context *
@@ -16,7 +19,7 @@ mock_context(struct drm_i915_private *i915,
 void mock_context_close(struct i915_gem_context *ctx);
 
 struct i915_gem_context *
-live_context(struct drm_i915_private *i915, struct drm_file *file);
+live_context(struct drm_i915_private *i915, struct file *file);
 
 struct i915_gem_context *kernel_context(struct drm_i915_private *i915);
 void kernel_context_close(struct i915_gem_context *ctx);
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
index b9e059d4328a..9272bef57092 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c
@@ -76,20 +76,6 @@ static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	vm_unmap_ram(vaddr, mock->npages);
 }
 
-static void *mock_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	struct mock_dmabuf *mock = to_mock(dma_buf);
-
-	return kmap(mock->pages[page_num]);
-}
-
-static void mock_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-	struct mock_dmabuf *mock = to_mock(dma_buf);
-
-	return kunmap(mock->pages[page_num]);
-}
-
 static int mock_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
 {
 	return -ENODEV;
@@ -99,8 +85,6 @@ static const struct dma_buf_ops mock_dmabuf_ops =  {
 	.map_dma_buf = mock_map_dma_buf,
 	.unmap_dma_buf = mock_unmap_dma_buf,
 	.release = mock_dmabuf_release,
-	.map = mock_dmabuf_kmap,
-	.unmap = mock_dmabuf_kunmap,
 	.mmap = mock_dmabuf_mmap,
 	.vmap = mock_dmabuf_vmap,
 	.vunmap = mock_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h
index f0f8bbd82dfc..22818bbb139d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.h
@@ -14,7 +14,7 @@ struct mock_dmabuf {
 	struct page *pages[];
 };
 
-static struct mock_dmabuf *to_mock(struct dma_buf *buf)
+static inline struct mock_dmabuf *to_mock(struct dma_buf *buf)
 {
 	return buf->priv;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h b/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h
index 370360b4a148..688511afa883 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_gem_object.h
@@ -7,6 +7,8 @@
 #ifndef __MOCK_GEM_OBJECT_H__
 #define __MOCK_GEM_OBJECT_H__
 
+#include "gem/i915_gem_object_types.h"
+
 struct mock_object {
 	struct drm_i915_gem_object base;
 };
diff --git a/drivers/gpu/drm/i915/gt/Makefile b/drivers/gpu/drm/i915/gt/Makefile
deleted file mode 100644
index 7e73aa587967..000000000000
--- a/drivers/gpu/drm/i915/gt/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.c b/drivers/gpu/drm/i915/gt/debugfs_engines.c
new file mode 100644
index 000000000000..6a5e9ab20b94
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_engines.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <drm/drm_print.h>
+
+#include "debugfs_engines.h"
+#include "debugfs_gt.h"
+#include "i915_drv.h" /* for_each_engine! */
+#include "intel_engine.h"
+
+static int engines_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct drm_printer p;
+
+	p = drm_seq_file_printer(m);
+	for_each_engine(engine, gt, id)
+		intel_engine_dump(engine, &p, "%s\n", engine->name);
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(engines);
+
+void debugfs_engines_register(struct intel_gt *gt, struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "engines", &engines_fops },
+	};
+
+	debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files));
+}
diff --git a/drivers/gpu/drm/i915/gt/debugfs_engines.h b/drivers/gpu/drm/i915/gt/debugfs_engines.h
new file mode 100644
index 000000000000..f69257eaa1cc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_engines.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef DEBUGFS_ENGINES_H
+#define DEBUGFS_ENGINES_H
+
+struct intel_gt;
+struct dentry;
+
+void debugfs_engines_register(struct intel_gt *gt, struct dentry *root);
+
+#endif /* DEBUGFS_ENGINES_H */
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.c b/drivers/gpu/drm/i915/gt/debugfs_gt.c
new file mode 100644
index 000000000000..75255aaacaed
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/debugfs.h>
+
+#include "debugfs_engines.h"
+#include "debugfs_gt.h"
+#include "debugfs_gt_pm.h"
+#include "i915_drv.h"
+
+void debugfs_gt_register(struct intel_gt *gt)
+{
+	struct dentry *root;
+
+	if (!gt->i915->drm.primary->debugfs_root)
+		return;
+
+	root = debugfs_create_dir("gt", gt->i915->drm.primary->debugfs_root);
+	if (IS_ERR(root))
+		return;
+
+	debugfs_engines_register(gt, root);
+	debugfs_gt_pm_register(gt, root);
+}
+
+void debugfs_gt_register_files(struct intel_gt *gt,
+			       struct dentry *root,
+			       const struct debugfs_gt_file *files,
+			       unsigned long count)
+{
+	while (count--) {
+		if (!files->eval || files->eval(gt))
+			debugfs_create_file(files->name,
+					    0444, root, gt,
+					    files->fops);
+
+		files++;
+	}
+}
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.h b/drivers/gpu/drm/i915/gt/debugfs_gt.h
new file mode 100644
index 000000000000..4ea0f06cda8f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef DEBUGFS_GT_H
+#define DEBUGFS_GT_H
+
+#include <linux/file.h>
+
+struct intel_gt;
+
+#define DEFINE_GT_DEBUGFS_ATTRIBUTE(__name)				\
+	static int __name ## _open(struct inode *inode, struct file *file) \
+{									\
+	return single_open(file, __name ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __name ## _fops = {			\
+	.owner = THIS_MODULE,						\
+	.open = __name ## _open,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+	.release = single_release,					\
+}
+
+void debugfs_gt_register(struct intel_gt *gt);
+
+struct debugfs_gt_file {
+	const char *name;
+	const struct file_operations *fops;
+	bool (*eval)(const struct intel_gt *gt);
+};
+
+void debugfs_gt_register_files(struct intel_gt *gt,
+			       struct dentry *root,
+			       const struct debugfs_gt_file *files,
+			       unsigned long count);
+
+#endif /* DEBUGFS_GT_H */
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
new file mode 100644
index 000000000000..059c9e5c002e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.c
@@ -0,0 +1,601 @@
+// SPDX-License-Identifier: MIT
+
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/seq_file.h>
+
+#include "debugfs_gt.h"
+#include "debugfs_gt_pm.h"
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_llc.h"
+#include "intel_rc6.h"
+#include "intel_rps.h"
+#include "intel_runtime_pm.h"
+#include "intel_sideband.h"
+#include "intel_uncore.h"
+
+static int fw_domains_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_uncore_forcewake_domain *fw_domain;
+	unsigned int tmp;
+
+	seq_printf(m, "user.bypass_count = %u\n",
+		   uncore->user_forcewake_count);
+
+	for_each_fw_domain(fw_domain, uncore, tmp)
+		seq_printf(m, "%s.wake_count = %u\n",
+			   intel_uncore_forcewake_domain_to_str(fw_domain->id),
+			   READ_ONCE(fw_domain->wake_count));
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(fw_domains);
+
+static void print_rc6_res(struct seq_file *m,
+			  const char *title,
+			  const i915_reg_t reg)
+{
+	struct intel_gt *gt = m->private;
+	intel_wakeref_t wakeref;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		seq_printf(m, "%s %u (%llu us)\n", title,
+			   intel_uncore_read(gt->uncore, reg),
+			   intel_rc6_residency_us(&gt->rc6, reg));
+}
+
+static int vlv_drpc(struct seq_file *m)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_uncore *uncore = gt->uncore;
+	u32 rcctl1, pw_status;
+
+	pw_status = intel_uncore_read(uncore, VLV_GTLC_PW_STATUS);
+	rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL);
+
+	seq_printf(m, "RC6 Enabled: %s\n",
+		   yesno(rcctl1 & (GEN7_RC_CTL_TO_MODE |
+					GEN6_RC_CTL_EI_MODE(1))));
+	seq_printf(m, "Render Power Well: %s\n",
+		   (pw_status & VLV_GTLC_PW_RENDER_STATUS_MASK) ? "Up" : "Down");
+	seq_printf(m, "Media Power Well: %s\n",
+		   (pw_status & VLV_GTLC_PW_MEDIA_STATUS_MASK) ? "Up" : "Down");
+
+	print_rc6_res(m, "Render RC6 residency since boot:", VLV_GT_RENDER_RC6);
+	print_rc6_res(m, "Media RC6 residency since boot:", VLV_GT_MEDIA_RC6);
+
+	return fw_domains_show(m, NULL);
+}
+
+static int gen6_drpc(struct seq_file *m)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	u32 gt_core_status, rcctl1, rc6vids = 0;
+	u32 gen9_powergate_enable = 0, gen9_powergate_status = 0;
+
+	gt_core_status = intel_uncore_read_fw(uncore, GEN6_GT_CORE_STATUS);
+
+	rcctl1 = intel_uncore_read(uncore, GEN6_RC_CONTROL);
+	if (INTEL_GEN(i915) >= 9) {
+		gen9_powergate_enable =
+			intel_uncore_read(uncore, GEN9_PG_ENABLE);
+		gen9_powergate_status =
+			intel_uncore_read(uncore, GEN9_PWRGT_DOMAIN_STATUS);
+	}
+
+	if (INTEL_GEN(i915) <= 7)
+		sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS,
+				       &rc6vids, NULL);
+
+	seq_printf(m, "RC1e Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC1e_ENABLE));
+	seq_printf(m, "RC6 Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC6_ENABLE));
+	if (INTEL_GEN(i915) >= 9) {
+		seq_printf(m, "Render Well Gating Enabled: %s\n",
+			   yesno(gen9_powergate_enable & GEN9_RENDER_PG_ENABLE));
+		seq_printf(m, "Media Well Gating Enabled: %s\n",
+			   yesno(gen9_powergate_enable & GEN9_MEDIA_PG_ENABLE));
+	}
+	seq_printf(m, "Deep RC6 Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC6p_ENABLE));
+	seq_printf(m, "Deepest RC6 Enabled: %s\n",
+		   yesno(rcctl1 & GEN6_RC_CTL_RC6pp_ENABLE));
+	seq_puts(m, "Current RC state: ");
+	switch (gt_core_status & GEN6_RCn_MASK) {
+	case GEN6_RC0:
+		if (gt_core_status & GEN6_CORE_CPD_STATE_MASK)
+			seq_puts(m, "Core Power Down\n");
+		else
+			seq_puts(m, "on\n");
+		break;
+	case GEN6_RC3:
+		seq_puts(m, "RC3\n");
+		break;
+	case GEN6_RC6:
+		seq_puts(m, "RC6\n");
+		break;
+	case GEN6_RC7:
+		seq_puts(m, "RC7\n");
+		break;
+	default:
+		seq_puts(m, "Unknown\n");
+		break;
+	}
+
+	seq_printf(m, "Core Power Down: %s\n",
+		   yesno(gt_core_status & GEN6_CORE_CPD_STATE_MASK));
+	if (INTEL_GEN(i915) >= 9) {
+		seq_printf(m, "Render Power Well: %s\n",
+			   (gen9_powergate_status &
+			    GEN9_PWRGT_RENDER_STATUS_MASK) ? "Up" : "Down");
+		seq_printf(m, "Media Power Well: %s\n",
+			   (gen9_powergate_status &
+			    GEN9_PWRGT_MEDIA_STATUS_MASK) ? "Up" : "Down");
+	}
+
+	/* Not exactly sure what this is */
+	print_rc6_res(m, "RC6 \"Locked to RPn\" residency since boot:",
+		      GEN6_GT_GFX_RC6_LOCKED);
+	print_rc6_res(m, "RC6 residency since boot:", GEN6_GT_GFX_RC6);
+	print_rc6_res(m, "RC6+ residency since boot:", GEN6_GT_GFX_RC6p);
+	print_rc6_res(m, "RC6++ residency since boot:", GEN6_GT_GFX_RC6pp);
+
+	if (INTEL_GEN(i915) <= 7) {
+		seq_printf(m, "RC6   voltage: %dmV\n",
+			   GEN6_DECODE_RC6_VID(((rc6vids >> 0) & 0xff)));
+		seq_printf(m, "RC6+  voltage: %dmV\n",
+			   GEN6_DECODE_RC6_VID(((rc6vids >> 8) & 0xff)));
+		seq_printf(m, "RC6++ voltage: %dmV\n",
+			   GEN6_DECODE_RC6_VID(((rc6vids >> 16) & 0xff)));
+	}
+
+	return fw_domains_show(m, NULL);
+}
+
+static int ilk_drpc(struct seq_file *m)
+{
+	struct intel_gt *gt = m->private;
+	struct intel_uncore *uncore = gt->uncore;
+	u32 rgvmodectl, rstdbyctl;
+	u16 crstandvid;
+
+	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);
+	rstdbyctl = intel_uncore_read(uncore, RSTDBYCTL);
+	crstandvid = intel_uncore_read16(uncore, CRSTANDVID);
+
+	seq_printf(m, "HD boost: %s\n", yesno(rgvmodectl & MEMMODE_BOOST_EN));
+	seq_printf(m, "Boost freq: %d\n",
+		   (rgvmodectl & MEMMODE_BOOST_FREQ_MASK) >>
+		   MEMMODE_BOOST_FREQ_SHIFT);
+	seq_printf(m, "HW control enabled: %s\n",
+		   yesno(rgvmodectl & MEMMODE_HWIDLE_EN));
+	seq_printf(m, "SW control enabled: %s\n",
+		   yesno(rgvmodectl & MEMMODE_SWMODE_EN));
+	seq_printf(m, "Gated voltage change: %s\n",
+		   yesno(rgvmodectl & MEMMODE_RCLK_GATE));
+	seq_printf(m, "Starting frequency: P%d\n",
+		   (rgvmodectl & MEMMODE_FSTART_MASK) >> MEMMODE_FSTART_SHIFT);
+	seq_printf(m, "Max P-state: P%d\n",
+		   (rgvmodectl & MEMMODE_FMAX_MASK) >> MEMMODE_FMAX_SHIFT);
+	seq_printf(m, "Min P-state: P%d\n", (rgvmodectl & MEMMODE_FMIN_MASK));
+	seq_printf(m, "RS1 VID: %d\n", (crstandvid & 0x3f));
+	seq_printf(m, "RS2 VID: %d\n", ((crstandvid >> 8) & 0x3f));
+	seq_printf(m, "Render standby enabled: %s\n",
+		   yesno(!(rstdbyctl & RCX_SW_EXIT)));
+	seq_puts(m, "Current RS state: ");
+	switch (rstdbyctl & RSX_STATUS_MASK) {
+	case RSX_STATUS_ON:
+		seq_puts(m, "on\n");
+		break;
+	case RSX_STATUS_RC1:
+		seq_puts(m, "RC1\n");
+		break;
+	case RSX_STATUS_RC1E:
+		seq_puts(m, "RC1E\n");
+		break;
+	case RSX_STATUS_RS1:
+		seq_puts(m, "RS1\n");
+		break;
+	case RSX_STATUS_RS2:
+		seq_puts(m, "RS2 (RC6)\n");
+		break;
+	case RSX_STATUS_RS3:
+		seq_puts(m, "RC3 (RC6+)\n");
+		break;
+	default:
+		seq_puts(m, "unknown\n");
+		break;
+	}
+
+	return 0;
+}
+
+static int drpc_show(struct seq_file *m, void *unused)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	intel_wakeref_t wakeref;
+	int err = -ENODEV;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref) {
+		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+			err = vlv_drpc(m);
+		else if (INTEL_GEN(i915) >= 6)
+			err = gen6_drpc(m);
+		else
+			err = ilk_drpc(m);
+	}
+
+	return err;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(drpc);
+
+static int frequency_show(struct seq_file *m, void *unused)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_rps *rps = &gt->rps;
+	intel_wakeref_t wakeref;
+
+	wakeref = intel_runtime_pm_get(uncore->rpm);
+
+	if (IS_GEN(i915, 5)) {
+		u16 rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
+		u16 rgvstat = intel_uncore_read16(uncore, MEMSTAT_ILK);
+
+		seq_printf(m, "Requested P-state: %d\n", (rgvswctl >> 8) & 0xf);
+		seq_printf(m, "Requested VID: %d\n", rgvswctl & 0x3f);
+		seq_printf(m, "Current VID: %d\n", (rgvstat & MEMSTAT_VID_MASK) >>
+			   MEMSTAT_VID_SHIFT);
+		seq_printf(m, "Current P-state: %d\n",
+			   (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT);
+	} else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		u32 rpmodectl, freq_sts;
+
+		rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL);
+		seq_printf(m, "Video Turbo Mode: %s\n",
+			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
+		seq_printf(m, "HW control enabled: %s\n",
+			   yesno(rpmodectl & GEN6_RP_ENABLE));
+		seq_printf(m, "SW control enabled: %s\n",
+			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
+				  GEN6_RP_MEDIA_SW_MODE));
+
+		vlv_punit_get(i915);
+		freq_sts = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+		vlv_punit_put(i915);
+
+		seq_printf(m, "PUNIT_REG_GPU_FREQ_STS: 0x%08x\n", freq_sts);
+		seq_printf(m, "DDR freq: %d MHz\n", i915->mem_freq);
+
+		seq_printf(m, "actual GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, (freq_sts >> 8) & 0xff));
+
+		seq_printf(m, "current GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->cur_freq));
+
+		seq_printf(m, "max GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->max_freq));
+
+		seq_printf(m, "min GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->min_freq));
+
+		seq_printf(m, "idle GPU freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->idle_freq));
+
+		seq_printf(m, "efficient (RPe) frequency: %d MHz\n",
+			   intel_gpu_freq(rps, rps->efficient_freq));
+	} else if (INTEL_GEN(i915) >= 6) {
+		u32 rp_state_limits;
+		u32 gt_perf_status;
+		u32 rp_state_cap;
+		u32 rpmodectl, rpinclimit, rpdeclimit;
+		u32 rpstat, cagf, reqf;
+		u32 rpupei, rpcurup, rpprevup;
+		u32 rpdownei, rpcurdown, rpprevdown;
+		u32 pm_ier, pm_imr, pm_isr, pm_iir, pm_mask;
+		int max_freq;
+
+		rp_state_limits = intel_uncore_read(uncore, GEN6_RP_STATE_LIMITS);
+		if (IS_GEN9_LP(i915)) {
+			rp_state_cap = intel_uncore_read(uncore, BXT_RP_STATE_CAP);
+			gt_perf_status = intel_uncore_read(uncore, BXT_GT_PERF_STATUS);
+		} else {
+			rp_state_cap = intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
+			gt_perf_status = intel_uncore_read(uncore, GEN6_GT_PERF_STATUS);
+		}
+
+		/* RPSTAT1 is in the GT power well */
+		intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+		reqf = intel_uncore_read(uncore, GEN6_RPNSWREQ);
+		if (INTEL_GEN(i915) >= 9) {
+			reqf >>= 23;
+		} else {
+			reqf &= ~GEN6_TURBO_DISABLE;
+			if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+				reqf >>= 24;
+			else
+				reqf >>= 25;
+		}
+		reqf = intel_gpu_freq(rps, reqf);
+
+		rpmodectl = intel_uncore_read(uncore, GEN6_RP_CONTROL);
+		rpinclimit = intel_uncore_read(uncore, GEN6_RP_UP_THRESHOLD);
+		rpdeclimit = intel_uncore_read(uncore, GEN6_RP_DOWN_THRESHOLD);
+
+		rpstat = intel_uncore_read(uncore, GEN6_RPSTAT1);
+		rpupei = intel_uncore_read(uncore, GEN6_RP_CUR_UP_EI) & GEN6_CURICONT_MASK;
+		rpcurup = intel_uncore_read(uncore, GEN6_RP_CUR_UP) & GEN6_CURBSYTAVG_MASK;
+		rpprevup = intel_uncore_read(uncore, GEN6_RP_PREV_UP) & GEN6_CURBSYTAVG_MASK;
+		rpdownei = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
+		rpcurdown = intel_uncore_read(uncore, GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
+		rpprevdown = intel_uncore_read(uncore, GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
+		cagf = intel_rps_read_actual_frequency(rps);
+
+		intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+
+		if (INTEL_GEN(i915) >= 11) {
+			pm_ier = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+			pm_imr = intel_uncore_read(uncore, GEN11_GPM_WGBOXPERF_INTR_MASK);
+			/*
+			 * The equivalent to the PM ISR & IIR cannot be read
+			 * without affecting the current state of the system
+			 */
+			pm_isr = 0;
+			pm_iir = 0;
+		} else if (INTEL_GEN(i915) >= 8) {
+			pm_ier = intel_uncore_read(uncore, GEN8_GT_IER(2));
+			pm_imr = intel_uncore_read(uncore, GEN8_GT_IMR(2));
+			pm_isr = intel_uncore_read(uncore, GEN8_GT_ISR(2));
+			pm_iir = intel_uncore_read(uncore, GEN8_GT_IIR(2));
+		} else {
+			pm_ier = intel_uncore_read(uncore, GEN6_PMIER);
+			pm_imr = intel_uncore_read(uncore, GEN6_PMIMR);
+			pm_isr = intel_uncore_read(uncore, GEN6_PMISR);
+			pm_iir = intel_uncore_read(uncore, GEN6_PMIIR);
+		}
+		pm_mask = intel_uncore_read(uncore, GEN6_PMINTRMSK);
+
+		seq_printf(m, "Video Turbo Mode: %s\n",
+			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
+		seq_printf(m, "HW control enabled: %s\n",
+			   yesno(rpmodectl & GEN6_RP_ENABLE));
+		seq_printf(m, "SW control enabled: %s\n",
+			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
+				  GEN6_RP_MEDIA_SW_MODE));
+
+		seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
+			   pm_ier, pm_imr, pm_mask);
+		if (INTEL_GEN(i915) <= 10)
+			seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n",
+				   pm_isr, pm_iir);
+		seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n",
+			   rps->pm_intrmsk_mbz);
+		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
+		seq_printf(m, "Render p-state ratio: %d\n",
+			   (gt_perf_status & (INTEL_GEN(i915) >= 9 ? 0x1ff00 : 0xff00)) >> 8);
+		seq_printf(m, "Render p-state VID: %d\n",
+			   gt_perf_status & 0xff);
+		seq_printf(m, "Render p-state limit: %d\n",
+			   rp_state_limits & 0xff);
+		seq_printf(m, "RPSTAT1: 0x%08x\n", rpstat);
+		seq_printf(m, "RPMODECTL: 0x%08x\n", rpmodectl);
+		seq_printf(m, "RPINCLIMIT: 0x%08x\n", rpinclimit);
+		seq_printf(m, "RPDECLIMIT: 0x%08x\n", rpdeclimit);
+		seq_printf(m, "RPNSWREQ: %dMHz\n", reqf);
+		seq_printf(m, "CAGF: %dMHz\n", cagf);
+		seq_printf(m, "RP CUR UP EI: %d (%dus)\n",
+			   rpupei, GT_PM_INTERVAL_TO_US(i915, rpupei));
+		seq_printf(m, "RP CUR UP: %d (%dus)\n",
+			   rpcurup, GT_PM_INTERVAL_TO_US(i915, rpcurup));
+		seq_printf(m, "RP PREV UP: %d (%dus)\n",
+			   rpprevup, GT_PM_INTERVAL_TO_US(i915, rpprevup));
+		seq_printf(m, "Up threshold: %d%%\n",
+			   rps->power.up_threshold);
+
+		seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n",
+			   rpdownei, GT_PM_INTERVAL_TO_US(i915, rpdownei));
+		seq_printf(m, "RP CUR DOWN: %d (%dus)\n",
+			   rpcurdown, GT_PM_INTERVAL_TO_US(i915, rpcurdown));
+		seq_printf(m, "RP PREV DOWN: %d (%dus)\n",
+			   rpprevdown, GT_PM_INTERVAL_TO_US(i915, rpprevdown));
+		seq_printf(m, "Down threshold: %d%%\n",
+			   rps->power.down_threshold);
+
+		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 0 :
+			    rp_state_cap >> 16) & 0xff;
+		max_freq *= (IS_GEN9_BC(i915) ||
+			     INTEL_GEN(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+		seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
+			   intel_gpu_freq(rps, max_freq));
+
+		max_freq = (rp_state_cap & 0xff00) >> 8;
+		max_freq *= (IS_GEN9_BC(i915) ||
+			     INTEL_GEN(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+		seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
+			   intel_gpu_freq(rps, max_freq));
+
+		max_freq = (IS_GEN9_LP(i915) ? rp_state_cap >> 16 :
+			    rp_state_cap >> 0) & 0xff;
+		max_freq *= (IS_GEN9_BC(i915) ||
+			     INTEL_GEN(i915) >= 10 ? GEN9_FREQ_SCALER : 1);
+		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
+			   intel_gpu_freq(rps, max_freq));
+		seq_printf(m, "Max overclocked frequency: %dMHz\n",
+			   intel_gpu_freq(rps, rps->max_freq));
+
+		seq_printf(m, "Current freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->cur_freq));
+		seq_printf(m, "Actual freq: %d MHz\n", cagf);
+		seq_printf(m, "Idle freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->idle_freq));
+		seq_printf(m, "Min freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->min_freq));
+		seq_printf(m, "Boost freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->boost_freq));
+		seq_printf(m, "Max freq: %d MHz\n",
+			   intel_gpu_freq(rps, rps->max_freq));
+		seq_printf(m,
+			   "efficient (RPe) frequency: %d MHz\n",
+			   intel_gpu_freq(rps, rps->efficient_freq));
+	} else {
+		seq_puts(m, "no P-state info available\n");
+	}
+
+	seq_printf(m, "Current CD clock frequency: %d kHz\n", i915->cdclk.hw.cdclk);
+	seq_printf(m, "Max CD clock frequency: %d kHz\n", i915->max_cdclk_freq);
+	seq_printf(m, "Max pixel clock frequency: %d kHz\n", i915->max_dotclk_freq);
+
+	intel_runtime_pm_put(uncore->rpm, wakeref);
+
+	return 0;
+}
+DEFINE_GT_DEBUGFS_ATTRIBUTE(frequency);
+
+static int llc_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	const bool edram = INTEL_GEN(i915) > 8;
+	struct intel_rps *rps = &gt->rps;
+	unsigned int max_gpu_freq, min_gpu_freq;
+	intel_wakeref_t wakeref;
+	int gpu_freq, ia_freq;
+
+	seq_printf(m, "LLC: %s\n", yesno(HAS_LLC(i915)));
+	seq_printf(m, "%s: %uMB\n", edram ? "eDRAM" : "eLLC",
+		   i915->edram_size_mb);
+
+	min_gpu_freq = rps->min_freq;
+	max_gpu_freq = rps->max_freq;
+	if (IS_GEN9_BC(i915) || INTEL_GEN(i915) >= 10) {
+		/* Convert GT frequency to 50 HZ units */
+		min_gpu_freq /= GEN9_FREQ_SCALER;
+		max_gpu_freq /= GEN9_FREQ_SCALER;
+	}
+
+	seq_puts(m, "GPU freq (MHz)\tEffective CPU freq (MHz)\tEffective Ring freq (MHz)\n");
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+	for (gpu_freq = min_gpu_freq; gpu_freq <= max_gpu_freq; gpu_freq++) {
+		ia_freq = gpu_freq;
+		sandybridge_pcode_read(i915,
+				       GEN6_PCODE_READ_MIN_FREQ_TABLE,
+				       &ia_freq, NULL);
+		seq_printf(m, "%d\t\t%d\t\t\t\t%d\n",
+			   intel_gpu_freq(rps,
+					  (gpu_freq *
+					   (IS_GEN9_BC(i915) ||
+					    INTEL_GEN(i915) >= 10 ?
+					    GEN9_FREQ_SCALER : 1))),
+			   ((ia_freq >> 0) & 0xff) * 100,
+			   ((ia_freq >> 8) & 0xff) * 100);
+	}
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+
+	return 0;
+}
+
+static bool llc_eval(const struct intel_gt *gt)
+{
+	return HAS_LLC(gt->i915);
+}
+
+DEFINE_GT_DEBUGFS_ATTRIBUTE(llc);
+
+static const char *rps_power_to_str(unsigned int power)
+{
+	static const char * const strings[] = {
+		[LOW_POWER] = "low power",
+		[BETWEEN] = "mixed",
+		[HIGH_POWER] = "high power",
+	};
+
+	if (power >= ARRAY_SIZE(strings) || !strings[power])
+		return "unknown";
+
+	return strings[power];
+}
+
+static int rps_boost_show(struct seq_file *m, void *data)
+{
+	struct intel_gt *gt = m->private;
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_rps *rps = &gt->rps;
+
+	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
+	seq_printf(m, "GPU busy? %s\n", yesno(gt->awake));
+	seq_printf(m, "Boosts outstanding? %d\n",
+		   atomic_read(&rps->num_waiters));
+	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
+	seq_printf(m, "Frequency requested %d, actual %d\n",
+		   intel_gpu_freq(rps, rps->cur_freq),
+		   intel_rps_read_actual_frequency(rps));
+	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
+		   intel_gpu_freq(rps, rps->min_freq),
+		   intel_gpu_freq(rps, rps->min_freq_softlimit),
+		   intel_gpu_freq(rps, rps->max_freq_softlimit),
+		   intel_gpu_freq(rps, rps->max_freq));
+	seq_printf(m, "  idle:%d, efficient:%d, boost:%d\n",
+		   intel_gpu_freq(rps, rps->idle_freq),
+		   intel_gpu_freq(rps, rps->efficient_freq),
+		   intel_gpu_freq(rps, rps->boost_freq));
+
+	seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
+
+	if (INTEL_GEN(i915) >= 6 && rps->enabled && gt->awake) {
+		struct intel_uncore *uncore = gt->uncore;
+		u32 rpup, rpupei;
+		u32 rpdown, rpdownei;
+
+		intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+		rpup = intel_uncore_read_fw(uncore, GEN6_RP_CUR_UP) & GEN6_RP_EI_MASK;
+		rpupei = intel_uncore_read_fw(uncore, GEN6_RP_CUR_UP_EI) & GEN6_RP_EI_MASK;
+		rpdown = intel_uncore_read_fw(uncore, GEN6_RP_CUR_DOWN) & GEN6_RP_EI_MASK;
+		rpdownei = intel_uncore_read_fw(uncore, GEN6_RP_CUR_DOWN_EI) & GEN6_RP_EI_MASK;
+		intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+
+		seq_printf(m, "\nRPS Autotuning (current \"%s\" window):\n",
+			   rps_power_to_str(rps->power.mode));
+		seq_printf(m, "  Avg. up: %d%% [above threshold? %d%%]\n",
+			   rpup && rpupei ? 100 * rpup / rpupei : 0,
+			   rps->power.up_threshold);
+		seq_printf(m, "  Avg. down: %d%% [below threshold? %d%%]\n",
+			   rpdown && rpdownei ? 100 * rpdown / rpdownei : 0,
+			   rps->power.down_threshold);
+	} else {
+		seq_puts(m, "\nRPS Autotuning inactive\n");
+	}
+
+	return 0;
+}
+
+static bool rps_eval(const struct intel_gt *gt)
+{
+	return HAS_RPS(gt->i915);
+}
+
+DEFINE_GT_DEBUGFS_ATTRIBUTE(rps_boost);
+
+void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root)
+{
+	static const struct debugfs_gt_file files[] = {
+		{ "drpc", &drpc_fops, NULL },
+		{ "frequency", &frequency_fops, NULL },
+		{ "forcewake", &fw_domains_fops, NULL },
+		{ "llc", &llc_fops, llc_eval },
+		{ "rps_boost", &rps_boost_fops, rps_eval },
+	};
+
+	debugfs_gt_register_files(gt, root, files, ARRAY_SIZE(files));
+}
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h
new file mode 100644
index 000000000000..4cf5f5c9da7d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/debugfs_gt_pm.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef DEBUGFS_GT_PM_H
+#define DEBUGFS_GT_PM_H
+
+struct intel_gt;
+struct dentry;
+
+void debugfs_gt_pm_register(struct intel_gt *gt, struct dentry *root);
+
+#endif /* DEBUGFS_GT_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
new file mode 100644
index 000000000000..f4fec7eb4064
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/log2.h>
+
+#include "gen6_ppgtt.h"
+#include "i915_scatterlist.h"
+#include "i915_trace.h"
+#include "i915_vgpu.h"
+#include "intel_gt.h"
+
+/* Write pde (index) from the page directory @pd to the page table @pt */
+static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt,
+				  const unsigned int pde,
+				  const struct i915_page_table *pt)
+{
+	/* Caller needs to make sure the write completes if necessary */
+	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+		  ppgtt->pd_addr + pde);
+}
+
+void gen7_ppgtt_enable(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	u32 ecochk;
+
+	intel_uncore_rmw(uncore, GAC_ECO_BITS, 0, ECOBITS_PPGTT_CACHE64B);
+
+	ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
+	if (IS_HASWELL(i915)) {
+		ecochk |= ECOCHK_PPGTT_WB_HSW;
+	} else {
+		ecochk |= ECOCHK_PPGTT_LLC_IVB;
+		ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
+	}
+	intel_uncore_write(uncore, GAM_ECOCHK, ecochk);
+
+	for_each_engine(engine, gt, id) {
+		/* GFX_MODE is per-ring on gen7+ */
+		ENGINE_WRITE(engine,
+			     RING_MODE_GEN7,
+			     _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+	}
+}
+
+void gen6_ppgtt_enable(struct intel_gt *gt)
+{
+	struct intel_uncore *uncore = gt->uncore;
+
+	intel_uncore_rmw(uncore,
+			 GAC_ECO_BITS,
+			 0,
+			 ECOBITS_SNB_BIT | ECOBITS_PPGTT_CACHE64B);
+
+	intel_uncore_rmw(uncore,
+			 GAB_CTL,
+			 0,
+			 GAB_CTL_CONT_AFTER_PAGEFAULT);
+
+	intel_uncore_rmw(uncore,
+			 GAM_ECOCHK,
+			 0,
+			 ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);
+
+	if (HAS_PPGTT(uncore->i915)) /* may be disabled for VT-d */
+		intel_uncore_write(uncore,
+				   GFX_MODE,
+				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
+}
+
+/* PPGTT support for Sandybdrige/Gen6 and later */
+static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
+				   u64 start, u64 length)
+{
+	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	const gen6_pte_t scratch_pte = vm->scratch[0].encode;
+	unsigned int pde = first_entry / GEN6_PTES;
+	unsigned int pte = first_entry % GEN6_PTES;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+
+	while (num_entries) {
+		struct i915_page_table * const pt =
+			i915_pt_entry(ppgtt->base.pd, pde++);
+		const unsigned int count = min(num_entries, GEN6_PTES - pte);
+		gen6_pte_t *vaddr;
+
+		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));
+
+		num_entries -= count;
+
+		GEM_BUG_ON(count > atomic_read(&pt->used));
+		if (!atomic_sub_return(count, &pt->used))
+			ppgtt->scan_for_unused_pt = true;
+
+		/*
+		 * Note that the hw doesn't support removing PDE on the fly
+		 * (they are cached inside the context with no means to
+		 * invalidate the cache), so we can only reset the PTE
+		 * entries back to scratch.
+		 */
+
+		vaddr = kmap_atomic_px(pt);
+		memset32(vaddr + pte, scratch_pte, count);
+		kunmap_atomic(vaddr);
+
+		pte = 0;
+	}
+}
+
+static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
+				      struct i915_vma *vma,
+				      enum i915_cache_level cache_level,
+				      u32 flags)
+{
+	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct i915_page_directory * const pd = ppgtt->pd;
+	unsigned int first_entry = vma->node.start / I915_GTT_PAGE_SIZE;
+	unsigned int act_pt = first_entry / GEN6_PTES;
+	unsigned int act_pte = first_entry % GEN6_PTES;
+	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
+	struct sgt_dma iter = sgt_dma(vma);
+	gen6_pte_t *vaddr;
+
+	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);
+
+	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
+	do {
+		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
+		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
+
+		iter.dma += I915_GTT_PAGE_SIZE;
+		if (iter.dma == iter.max) {
+			iter.sg = __sg_next(iter.sg);
+			if (!iter.sg)
+				break;
+
+			iter.dma = sg_dma_address(iter.sg);
+			iter.max = iter.dma + iter.sg->length;
+		}
+
+		if (++act_pte == GEN6_PTES) {
+			kunmap_atomic(vaddr);
+			vaddr = kmap_atomic_px(i915_pt_entry(pd, ++act_pt));
+			act_pte = 0;
+		}
+	} while (1);
+	kunmap_atomic(vaddr);
+
+	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+}
+
+static void gen6_flush_pd(struct gen6_ppgtt *ppgtt, u64 start, u64 end)
+{
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_table *pt;
+	unsigned int pde;
+
+	start = round_down(start, SZ_64K);
+	end = round_up(end, SZ_64K) - start;
+
+	mutex_lock(&ppgtt->flush);
+
+	gen6_for_each_pde(pt, pd, start, end, pde)
+		gen6_write_pde(ppgtt, pde, pt);
+
+	mb();
+	ioread32(ppgtt->pd_addr + pde - 1);
+	gen6_ggtt_invalidate(ppgtt->base.vm.gt->ggtt);
+	mb();
+
+	mutex_unlock(&ppgtt->flush);
+}
+
+static int gen6_alloc_va_range(struct i915_address_space *vm,
+			       u64 start, u64 length)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_table *pt, *alloc = NULL;
+	intel_wakeref_t wakeref;
+	u64 from = start;
+	unsigned int pde;
+	int ret = 0;
+
+	wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
+
+	spin_lock(&pd->lock);
+	gen6_for_each_pde(pt, pd, start, length, pde) {
+		const unsigned int count = gen6_pte_count(start, length);
+
+		if (px_base(pt) == px_base(&vm->scratch[1])) {
+			spin_unlock(&pd->lock);
+
+			pt = fetch_and_zero(&alloc);
+			if (!pt)
+				pt = alloc_pt(vm);
+			if (IS_ERR(pt)) {
+				ret = PTR_ERR(pt);
+				goto unwind_out;
+			}
+
+			fill32_px(pt, vm->scratch[0].encode);
+
+			spin_lock(&pd->lock);
+			if (pd->entry[pde] == &vm->scratch[1]) {
+				pd->entry[pde] = pt;
+			} else {
+				alloc = pt;
+				pt = pd->entry[pde];
+			}
+		}
+
+		atomic_add(count, &pt->used);
+	}
+	spin_unlock(&pd->lock);
+
+	if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND))
+		gen6_flush_pd(ppgtt, from, start);
+
+	goto out;
+
+unwind_out:
+	gen6_ppgtt_clear_range(vm, from, start - from);
+out:
+	if (alloc)
+		free_px(vm, alloc);
+	intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
+	return ret;
+}
+
+static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
+{
+	struct i915_address_space * const vm = &ppgtt->base.vm;
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	int ret;
+
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	if (ret)
+		return ret;
+
+	vm->scratch[0].encode =
+		vm->pte_encode(px_dma(&vm->scratch[0]),
+			       I915_CACHE_NONE, PTE_READ_ONLY);
+
+	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {
+		cleanup_scratch_page(vm);
+		return -ENOMEM;
+	}
+
+	fill32_px(&vm->scratch[1], vm->scratch[0].encode);
+	memset_p(pd->entry, &vm->scratch[1], I915_PDES);
+
+	return 0;
+}
+
+static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
+{
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_dma * const scratch =
+		px_base(&ppgtt->base.vm.scratch[1]);
+	struct i915_page_table *pt;
+	u32 pde;
+
+	gen6_for_all_pdes(pt, pd, pde)
+		if (px_base(pt) != scratch)
+			free_px(&ppgtt->base.vm, pt);
+}
+
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+
+	__i915_vma_put(ppgtt->vma);
+
+	gen6_ppgtt_free_pd(ppgtt);
+	free_scratch(vm);
+
+	mutex_destroy(&ppgtt->flush);
+	mutex_destroy(&ppgtt->pin_mutex);
+	kfree(ppgtt->base.pd);
+}
+
+static int pd_vma_set_pages(struct i915_vma *vma)
+{
+	vma->pages = ERR_PTR(-ENODEV);
+	return 0;
+}
+
+static void pd_vma_clear_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
+
+	vma->pages = NULL;
+}
+
+static int pd_vma_bind(struct i915_vma *vma,
+		       enum i915_cache_level cache_level,
+		       u32 unused)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
+	struct gen6_ppgtt *ppgtt = vma->private;
+	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
+
+	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
+	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
+
+	gen6_flush_pd(ppgtt, 0, ppgtt->base.vm.total);
+	return 0;
+}
+
+static void pd_vma_unbind(struct i915_vma *vma)
+{
+	struct gen6_ppgtt *ppgtt = vma->private;
+	struct i915_page_directory * const pd = ppgtt->base.pd;
+	struct i915_page_dma * const scratch =
+		px_base(&ppgtt->base.vm.scratch[1]);
+	struct i915_page_table *pt;
+	unsigned int pde;
+
+	if (!ppgtt->scan_for_unused_pt)
+		return;
+
+	/* Free all no longer used page tables */
+	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {
+		if (px_base(pt) == scratch || atomic_read(&pt->used))
+			continue;
+
+		free_px(&ppgtt->base.vm, pt);
+		pd->entry[pde] = scratch;
+	}
+
+	ppgtt->scan_for_unused_pt = false;
+}
+
+static const struct i915_vma_ops pd_vma_ops = {
+	.set_pages = pd_vma_set_pages,
+	.clear_pages = pd_vma_clear_pages,
+	.bind_vma = pd_vma_bind,
+	.unbind_vma = pd_vma_unbind,
+};
+
+static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
+{
+	struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt;
+	struct i915_vma *vma;
+
+	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
+	GEM_BUG_ON(size > ggtt->vm.total);
+
+	vma = i915_vma_alloc();
+	if (!vma)
+		return ERR_PTR(-ENOMEM);
+
+	i915_active_init(&vma->active, NULL, NULL);
+
+	kref_init(&vma->ref);
+	mutex_init(&vma->pages_mutex);
+	vma->vm = i915_vm_get(&ggtt->vm);
+	vma->ops = &pd_vma_ops;
+	vma->private = ppgtt;
+
+	vma->size = size;
+	vma->fence_size = size;
+	atomic_set(&vma->flags, I915_VMA_GGTT);
+	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
+
+	INIT_LIST_HEAD(&vma->obj_link);
+	INIT_LIST_HEAD(&vma->closed_link);
+
+	return vma;
+}
+
+int gen6_ppgtt_pin(struct i915_ppgtt *base)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
+	int err;
+
+	GEM_BUG_ON(!atomic_read(&ppgtt->base.vm.open));
+
+	/*
+	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
+	 * which will be pinned into every active context.
+	 * (When vma->pin_count becomes atomic, I expect we will naturally
+	 * need a larger, unpacked, type and kill this redundancy.)
+	 */
+	if (atomic_add_unless(&ppgtt->pin_count, 1, 0))
+		return 0;
+
+	if (mutex_lock_interruptible(&ppgtt->pin_mutex))
+		return -EINTR;
+
+	/*
+	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
+	 * allocator works in address space sizes, so it's multiplied by page
+	 * size. We allocate at the top of the GTT to avoid fragmentation.
+	 */
+	err = 0;
+	if (!atomic_read(&ppgtt->pin_count))
+		err = i915_ggtt_pin(ppgtt->vma, GEN6_PD_ALIGN, PIN_HIGH);
+	if (!err)
+		atomic_inc(&ppgtt->pin_count);
+	mutex_unlock(&ppgtt->pin_mutex);
+
+	return err;
+}
+
+void gen6_ppgtt_unpin(struct i915_ppgtt *base)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	GEM_BUG_ON(!atomic_read(&ppgtt->pin_count));
+	if (atomic_dec_and_test(&ppgtt->pin_count))
+		i915_vma_unpin(ppgtt->vma);
+}
+
+void gen6_ppgtt_unpin_all(struct i915_ppgtt *base)
+{
+	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	if (!atomic_read(&ppgtt->pin_count))
+		return;
+
+	i915_vma_unpin(ppgtt->vma);
+	atomic_set(&ppgtt->pin_count, 0);
+}
+
+struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
+{
+	struct i915_ggtt * const ggtt = gt->ggtt;
+	struct gen6_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&ppgtt->flush);
+	mutex_init(&ppgtt->pin_mutex);
+
+	ppgtt_init(&ppgtt->base, gt);
+	ppgtt->base.vm.top = 1;
+
+	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
+	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
+	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
+	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
+
+	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
+
+	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));
+	if (!ppgtt->base.pd) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	err = gen6_ppgtt_init_scratch(ppgtt);
+	if (err)
+		goto err_pd;
+
+	ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE);
+	if (IS_ERR(ppgtt->vma)) {
+		err = PTR_ERR(ppgtt->vma);
+		goto err_scratch;
+	}
+
+	return &ppgtt->base;
+
+err_scratch:
+	free_scratch(&ppgtt->base.vm);
+err_pd:
+	kfree(ppgtt->base.pd);
+err_free:
+	mutex_destroy(&ppgtt->pin_mutex);
+	kfree(ppgtt);
+	return ERR_PTR(err);
+}
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
new file mode 100644
index 000000000000..72e481806c96
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __GEN6_PPGTT_H__
+#define __GEN6_PPGTT_H__
+
+#include "intel_gtt.h"
+
+struct gen6_ppgtt {
+	struct i915_ppgtt base;
+
+	struct mutex flush;
+	struct i915_vma *vma;
+	gen6_pte_t __iomem *pd_addr;
+
+	atomic_t pin_count;
+	struct mutex pin_mutex;
+
+	bool scan_for_unused_pt;
+};
+
+static inline u32 gen6_pte_index(u32 addr)
+{
+	return i915_pte_index(addr, GEN6_PDE_SHIFT);
+}
+
+static inline u32 gen6_pte_count(u32 addr, u32 length)
+{
+	return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
+}
+
+static inline u32 gen6_pde_index(u32 addr)
+{
+	return i915_pde_index(addr, GEN6_PDE_SHIFT);
+}
+
+#define __to_gen6_ppgtt(base) container_of(base, struct gen6_ppgtt, base)
+
+static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
+{
+	BUILD_BUG_ON(offsetof(struct gen6_ppgtt, base));
+	return __to_gen6_ppgtt(base);
+}
+
+/*
+ * gen6_for_each_pde() iterates over every pde from start until start+length.
+ * If start and start+length are not perfectly divisible, the macro will round
+ * down and up as needed. Start=0 and length=2G effectively iterates over
+ * every PDE in the system. The macro modifies ALL its parameters except 'pd',
+ * so each of the other parameters should preferably be a simple variable, or
+ * at most an lvalue with no side-effects!
+ */
+#define gen6_for_each_pde(pt, pd, start, length, iter)			\
+	for (iter = gen6_pde_index(start);				\
+	     length > 0 && iter < I915_PDES &&				\
+		     (pt = i915_pt_entry(pd, iter), true);		\
+	     ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT);		\
+		    temp = min(temp - start, length);			\
+		    start += temp, length -= temp; }), ++iter)
+
+#define gen6_for_all_pdes(pt, pd, iter)					\
+	for (iter = 0;							\
+	     iter < I915_PDES &&					\
+		     (pt = i915_pt_entry(pd, iter), true);		\
+	     ++iter)
+
+int gen6_ppgtt_pin(struct i915_ppgtt *base);
+void gen6_ppgtt_unpin(struct i915_ppgtt *base);
+void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
+void gen6_ppgtt_enable(struct intel_gt *gt);
+void gen7_ppgtt_enable(struct intel_gt *gt);
+struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
new file mode 100644
index 000000000000..4d1de2d97d5c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -0,0 +1,724 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/log2.h>
+
+#include "gen8_ppgtt.h"
+#include "i915_scatterlist.h"
+#include "i915_trace.h"
+#include "i915_vgpu.h"
+#include "intel_gt.h"
+#include "intel_gtt.h"
+
+static u64 gen8_pde_encode(const dma_addr_t addr,
+			   const enum i915_cache_level level)
+{
+	u64 pde = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (level != I915_CACHE_NONE)
+		pde |= PPAT_CACHED_PDE;
+	else
+		pde |= PPAT_UNCACHED;
+
+	return pde;
+}
+
+static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
+{
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
+	struct intel_uncore *uncore = ppgtt->vm.gt->uncore;
+	enum vgt_g2v_type msg;
+	int i;
+
+	if (create)
+		atomic_inc(px_used(ppgtt->pd)); /* never remove */
+	else
+		atomic_dec(px_used(ppgtt->pd));
+
+	mutex_lock(&i915->vgpu.lock);
+
+	if (i915_vm_is_4lvl(&ppgtt->vm)) {
+		const u64 daddr = px_dma(ppgtt->pd);
+
+		intel_uncore_write(uncore,
+				   vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
+		intel_uncore_write(uncore,
+				   vgtif_reg(pdp[0].hi), upper_32_bits(daddr));
+
+		msg = create ?
+			VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
+			VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY;
+	} else {
+		for (i = 0; i < GEN8_3LVL_PDPES; i++) {
+			const u64 daddr = i915_page_dir_dma_addr(ppgtt, i);
+
+			intel_uncore_write(uncore,
+					   vgtif_reg(pdp[i].lo),
+					   lower_32_bits(daddr));
+			intel_uncore_write(uncore,
+					   vgtif_reg(pdp[i].hi),
+					   upper_32_bits(daddr));
+		}
+
+		msg = create ?
+			VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
+			VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY;
+	}
+
+	/* g2v_notify atomically (via hv trap) consumes the message packet. */
+	intel_uncore_write(uncore, vgtif_reg(g2v_notify), msg);
+
+	mutex_unlock(&i915->vgpu.lock);
+}
+
+/* Index shifts into the pagetable are offset by GEN8_PTE_SHIFT [12] */
+#define GEN8_PAGE_SIZE (SZ_4K) /* page and page-directory sizes are the same */
+#define GEN8_PTE_SHIFT (ilog2(GEN8_PAGE_SIZE))
+#define GEN8_PDES (GEN8_PAGE_SIZE / sizeof(u64))
+#define gen8_pd_shift(lvl) ((lvl) * ilog2(GEN8_PDES))
+#define gen8_pd_index(i, lvl) i915_pde_index((i), gen8_pd_shift(lvl))
+#define __gen8_pte_shift(lvl) (GEN8_PTE_SHIFT + gen8_pd_shift(lvl))
+#define __gen8_pte_index(a, lvl) i915_pde_index((a), __gen8_pte_shift(lvl))
+
+#define as_pd(x) container_of((x), typeof(struct i915_page_directory), pt)
+
+static inline unsigned int
+gen8_pd_range(u64 start, u64 end, int lvl, unsigned int *idx)
+{
+	const int shift = gen8_pd_shift(lvl);
+	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
+
+	GEM_BUG_ON(start >= end);
+	end += ~mask >> gen8_pd_shift(1);
+
+	*idx = i915_pde_index(start, shift);
+	if ((start ^ end) & mask)
+		return GEN8_PDES - *idx;
+	else
+		return i915_pde_index(end, shift) - *idx;
+}
+
+static inline bool gen8_pd_contains(u64 start, u64 end, int lvl)
+{
+	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
+
+	GEM_BUG_ON(start >= end);
+	return (start ^ end) & mask && (start & ~mask) == 0;
+}
+
+static inline unsigned int gen8_pt_count(u64 start, u64 end)
+{
+	GEM_BUG_ON(start >= end);
+	if ((start ^ end) >> gen8_pd_shift(1))
+		return GEN8_PDES - (start & (GEN8_PDES - 1));
+	else
+		return end - start;
+}
+
+static inline unsigned int
+gen8_pd_top_count(const struct i915_address_space *vm)
+{
+	unsigned int shift = __gen8_pte_shift(vm->top);
+	return (vm->total + (1ull << shift) - 1) >> shift;
+}
+
+static inline struct i915_page_directory *
+gen8_pdp_for_page_index(struct i915_address_space * const vm, const u64 idx)
+{
+	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
+
+	if (vm->top == 2)
+		return ppgtt->pd;
+	else
+		return i915_pd_entry(ppgtt->pd, gen8_pd_index(idx, vm->top));
+}
+
+static inline struct i915_page_directory *
+gen8_pdp_for_page_address(struct i915_address_space * const vm, const u64 addr)
+{
+	return gen8_pdp_for_page_index(vm, addr >> GEN8_PTE_SHIFT);
+}
+
+static void __gen8_ppgtt_cleanup(struct i915_address_space *vm,
+				 struct i915_page_directory *pd,
+				 int count, int lvl)
+{
+	if (lvl) {
+		void **pde = pd->entry;
+
+		do {
+			if (!*pde)
+				continue;
+
+			__gen8_ppgtt_cleanup(vm, *pde, GEN8_PDES, lvl - 1);
+		} while (pde++, --count);
+	}
+
+	free_px(vm, pd);
+}
+
+static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+
+	if (intel_vgpu_active(vm->i915))
+		gen8_ppgtt_notify_vgt(ppgtt, false);
+
+	__gen8_ppgtt_cleanup(vm, ppgtt->pd, gen8_pd_top_count(vm), vm->top);
+	free_scratch(vm);
+}
+
+static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
+			      struct i915_page_directory * const pd,
+			      u64 start, const u64 end, int lvl)
+{
+	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
+	unsigned int idx, len;
+
+	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
+
+	len = gen8_pd_range(start, end, lvl--, &idx);
+	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
+	    __func__, vm, lvl + 1, start, end,
+	    idx, len, atomic_read(px_used(pd)));
+	GEM_BUG_ON(!len || len >= atomic_read(px_used(pd)));
+
+	do {
+		struct i915_page_table *pt = pd->entry[idx];
+
+		if (atomic_fetch_inc(&pt->used) >> gen8_pd_shift(1) &&
+		    gen8_pd_contains(start, end, lvl)) {
+			DBG("%s(%p):{ lvl:%d, idx:%d, start:%llx, end:%llx } removing pd\n",
+			    __func__, vm, lvl + 1, idx, start, end);
+			clear_pd_entry(pd, idx, scratch);
+			__gen8_ppgtt_cleanup(vm, as_pd(pt), I915_PDES, lvl);
+			start += (u64)I915_PDES << gen8_pd_shift(lvl);
+			continue;
+		}
+
+		if (lvl) {
+			start = __gen8_ppgtt_clear(vm, as_pd(pt),
+						   start, end, lvl);
+		} else {
+			unsigned int count;
+			u64 *vaddr;
+
+			count = gen8_pt_count(start, end);
+			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } removing pte\n",
+			    __func__, vm, lvl, start, end,
+			    gen8_pd_index(start, 0), count,
+			    atomic_read(&pt->used));
+			GEM_BUG_ON(!count || count >= atomic_read(&pt->used));
+
+			vaddr = kmap_atomic_px(pt);
+			memset64(vaddr + gen8_pd_index(start, 0),
+				 vm->scratch[0].encode,
+				 count);
+			kunmap_atomic(vaddr);
+
+			atomic_sub(count, &pt->used);
+			start += count;
+		}
+
+		if (release_pd_entry(pd, idx, pt, scratch))
+			free_px(vm, pt);
+	} while (idx++, --len);
+
+	return start;
+}
+
+static void gen8_ppgtt_clear(struct i915_address_space *vm,
+			     u64 start, u64 length)
+{
+	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(range_overflows(start, length, vm->total));
+
+	start >>= GEN8_PTE_SHIFT;
+	length >>= GEN8_PTE_SHIFT;
+	GEM_BUG_ON(length == 0);
+
+	__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
+			   start, start + length, vm->top);
+}
+
+static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
+			      struct i915_page_directory * const pd,
+			      u64 * const start, const u64 end, int lvl)
+{
+	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
+	struct i915_page_table *alloc = NULL;
+	unsigned int idx, len;
+	int ret = 0;
+
+	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
+
+	len = gen8_pd_range(*start, end, lvl--, &idx);
+	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
+	    __func__, vm, lvl + 1, *start, end,
+	    idx, len, atomic_read(px_used(pd)));
+	GEM_BUG_ON(!len || (idx + len - 1) >> gen8_pd_shift(1));
+
+	spin_lock(&pd->lock);
+	GEM_BUG_ON(!atomic_read(px_used(pd))); /* Must be pinned! */
+	do {
+		struct i915_page_table *pt = pd->entry[idx];
+
+		if (!pt) {
+			spin_unlock(&pd->lock);
+
+			DBG("%s(%p):{ lvl:%d, idx:%d } allocating new tree\n",
+			    __func__, vm, lvl + 1, idx);
+
+			pt = fetch_and_zero(&alloc);
+			if (lvl) {
+				if (!pt) {
+					pt = &alloc_pd(vm)->pt;
+					if (IS_ERR(pt)) {
+						ret = PTR_ERR(pt);
+						goto out;
+					}
+				}
+
+				fill_px(pt, vm->scratch[lvl].encode);
+			} else {
+				if (!pt) {
+					pt = alloc_pt(vm);
+					if (IS_ERR(pt)) {
+						ret = PTR_ERR(pt);
+						goto out;
+					}
+				}
+
+				if (intel_vgpu_active(vm->i915) ||
+				    gen8_pt_count(*start, end) < I915_PDES)
+					fill_px(pt, vm->scratch[lvl].encode);
+			}
+
+			spin_lock(&pd->lock);
+			if (likely(!pd->entry[idx]))
+				set_pd_entry(pd, idx, pt);
+			else
+				alloc = pt, pt = pd->entry[idx];
+		}
+
+		if (lvl) {
+			atomic_inc(&pt->used);
+			spin_unlock(&pd->lock);
+
+			ret = __gen8_ppgtt_alloc(vm, as_pd(pt),
+						 start, end, lvl);
+			if (unlikely(ret)) {
+				if (release_pd_entry(pd, idx, pt, scratch))
+					free_px(vm, pt);
+				goto out;
+			}
+
+			spin_lock(&pd->lock);
+			atomic_dec(&pt->used);
+			GEM_BUG_ON(!atomic_read(&pt->used));
+		} else {
+			unsigned int count = gen8_pt_count(*start, end);
+
+			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } inserting pte\n",
+			    __func__, vm, lvl, *start, end,
+			    gen8_pd_index(*start, 0), count,
+			    atomic_read(&pt->used));
+
+			atomic_add(count, &pt->used);
+			/* All other pdes may be simultaneously removed */
+			GEM_BUG_ON(atomic_read(&pt->used) > NALLOC * I915_PDES);
+			*start += count;
+		}
+	} while (idx++, --len);
+	spin_unlock(&pd->lock);
+out:
+	if (alloc)
+		free_px(vm, alloc);
+	return ret;
+}
+
+static int gen8_ppgtt_alloc(struct i915_address_space *vm,
+			    u64 start, u64 length)
+{
+	u64 from;
+	int err;
+
+	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
+	GEM_BUG_ON(range_overflows(start, length, vm->total));
+
+	start >>= GEN8_PTE_SHIFT;
+	length >>= GEN8_PTE_SHIFT;
+	GEM_BUG_ON(length == 0);
+	from = start;
+
+	err = __gen8_ppgtt_alloc(vm, i915_vm_to_ppgtt(vm)->pd,
+				 &start, start + length, vm->top);
+	if (unlikely(err && from != start))
+		__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
+				   from, start, vm->top);
+
+	return err;
+}
+
+static __always_inline u64
+gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
+		      struct i915_page_directory *pdp,
+		      struct sgt_dma *iter,
+		      u64 idx,
+		      enum i915_cache_level cache_level,
+		      u32 flags)
+{
+	struct i915_page_directory *pd;
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	gen8_pte_t *vaddr;
+
+	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
+	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+	do {
+		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
+		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
+
+		iter->dma += I915_GTT_PAGE_SIZE;
+		if (iter->dma >= iter->max) {
+			iter->sg = __sg_next(iter->sg);
+			if (!iter->sg) {
+				idx = 0;
+				break;
+			}
+
+			iter->dma = sg_dma_address(iter->sg);
+			iter->max = iter->dma + iter->sg->length;
+		}
+
+		if (gen8_pd_index(++idx, 0) == 0) {
+			if (gen8_pd_index(idx, 1) == 0) {
+				/* Limited by sg length for 3lvl */
+				if (gen8_pd_index(idx, 2) == 0)
+					break;
+
+				pd = pdp->entry[gen8_pd_index(idx, 2)];
+			}
+
+			kunmap_atomic(vaddr);
+			vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+		}
+	} while (1);
+	kunmap_atomic(vaddr);
+
+	return idx;
+}
+
+static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
+				   struct sgt_dma *iter,
+				   enum i915_cache_level cache_level,
+				   u32 flags)
+{
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	u64 start = vma->node.start;
+	dma_addr_t rem = iter->sg->length;
+
+	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
+
+	do {
+		struct i915_page_directory * const pdp =
+			gen8_pdp_for_page_address(vma->vm, start);
+		struct i915_page_directory * const pd =
+			i915_pd_entry(pdp, __gen8_pte_index(start, 2));
+		gen8_pte_t encode = pte_encode;
+		unsigned int maybe_64K = -1;
+		unsigned int page_size;
+		gen8_pte_t *vaddr;
+		u16 index;
+
+		if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
+		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
+		    rem >= I915_GTT_PAGE_SIZE_2M &&
+		    !__gen8_pte_index(start, 0)) {
+			index = __gen8_pte_index(start, 1);
+			encode |= GEN8_PDE_PS_2M;
+			page_size = I915_GTT_PAGE_SIZE_2M;
+
+			vaddr = kmap_atomic_px(pd);
+		} else {
+			struct i915_page_table *pt =
+				i915_pt_entry(pd, __gen8_pte_index(start, 1));
+
+			index = __gen8_pte_index(start, 0);
+			page_size = I915_GTT_PAGE_SIZE;
+
+			if (!index &&
+			    vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
+			    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
+			    (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
+			     rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE))
+				maybe_64K = __gen8_pte_index(start, 1);
+
+			vaddr = kmap_atomic_px(pt);
+		}
+
+		do {
+			GEM_BUG_ON(iter->sg->length < page_size);
+			vaddr[index++] = encode | iter->dma;
+
+			start += page_size;
+			iter->dma += page_size;
+			rem -= page_size;
+			if (iter->dma >= iter->max) {
+				iter->sg = __sg_next(iter->sg);
+				if (!iter->sg)
+					break;
+
+				rem = iter->sg->length;
+				iter->dma = sg_dma_address(iter->sg);
+				iter->max = iter->dma + rem;
+
+				if (maybe_64K != -1 && index < I915_PDES &&
+				    !(IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
+				      (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
+				       rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE)))
+					maybe_64K = -1;
+
+				if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
+					break;
+			}
+		} while (rem >= page_size && index < I915_PDES);
+
+		kunmap_atomic(vaddr);
+
+		/*
+		 * Is it safe to mark the 2M block as 64K? -- Either we have
+		 * filled whole page-table with 64K entries, or filled part of
+		 * it and have reached the end of the sg table and we have
+		 * enough padding.
+		 */
+		if (maybe_64K != -1 &&
+		    (index == I915_PDES ||
+		     (i915_vm_has_scratch_64K(vma->vm) &&
+		      !iter->sg && IS_ALIGNED(vma->node.start +
+					      vma->node.size,
+					      I915_GTT_PAGE_SIZE_2M)))) {
+			vaddr = kmap_atomic_px(pd);
+			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
+			kunmap_atomic(vaddr);
+			page_size = I915_GTT_PAGE_SIZE_64K;
+
+			/*
+			 * We write all 4K page entries, even when using 64K
+			 * pages. In order to verify that the HW isn't cheating
+			 * by using the 4K PTE instead of the 64K PTE, we want
+			 * to remove all the surplus entries. If the HW skipped
+			 * the 64K PTE, it will read/write into the scratch page
+			 * instead - which we detect as missing results during
+			 * selftests.
+			 */
+			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
+				u16 i;
+
+				encode = vma->vm->scratch[0].encode;
+				vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K));
+
+				for (i = 1; i < index; i += 16)
+					memset64(vaddr + i, encode, 15);
+
+				kunmap_atomic(vaddr);
+			}
+		}
+
+		vma->page_sizes.gtt |= page_size;
+	} while (iter->sg);
+}
+
+static void gen8_ppgtt_insert(struct i915_address_space *vm,
+			      struct i915_vma *vma,
+			      enum i915_cache_level cache_level,
+			      u32 flags)
+{
+	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
+	struct sgt_dma iter = sgt_dma(vma);
+
+	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
+		gen8_ppgtt_insert_huge(vma, &iter, cache_level, flags);
+	} else  {
+		u64 idx = vma->node.start >> GEN8_PTE_SHIFT;
+
+		do {
+			struct i915_page_directory * const pdp =
+				gen8_pdp_for_page_index(vm, idx);
+
+			idx = gen8_ppgtt_insert_pte(ppgtt, pdp, &iter, idx,
+						    cache_level, flags);
+		} while (idx);
+
+		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+	}
+}
+
+static int gen8_init_scratch(struct i915_address_space *vm)
+{
+	int ret;
+	int i;
+
+	/*
+	 * If everybody agrees to not to write into the scratch page,
+	 * we can reuse it for all vm, keeping contexts and processes separate.
+	 */
+	if (vm->has_read_only && vm->gt->vm && !i915_is_ggtt(vm->gt->vm)) {
+		struct i915_address_space *clone = vm->gt->vm;
+
+		GEM_BUG_ON(!clone->has_read_only);
+
+		vm->scratch_order = clone->scratch_order;
+		memcpy(vm->scratch, clone->scratch, sizeof(vm->scratch));
+		px_dma(&vm->scratch[0]) = 0; /* no xfer of ownership */
+		return 0;
+	}
+
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
+	if (ret)
+		return ret;
+
+	vm->scratch[0].encode =
+		gen8_pte_encode(px_dma(&vm->scratch[0]),
+				I915_CACHE_LLC, vm->has_read_only);
+
+	for (i = 1; i <= vm->top; i++) {
+		if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[i]))))
+			goto free_scratch;
+
+		fill_px(&vm->scratch[i], vm->scratch[i - 1].encode);
+		vm->scratch[i].encode =
+			gen8_pde_encode(px_dma(&vm->scratch[i]),
+					I915_CACHE_LLC);
+	}
+
+	return 0;
+
+free_scratch:
+	free_scratch(vm);
+	return -ENOMEM;
+}
+
+static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
+{
+	struct i915_address_space *vm = &ppgtt->vm;
+	struct i915_page_directory *pd = ppgtt->pd;
+	unsigned int idx;
+
+	GEM_BUG_ON(vm->top != 2);
+	GEM_BUG_ON(gen8_pd_top_count(vm) != GEN8_3LVL_PDPES);
+
+	for (idx = 0; idx < GEN8_3LVL_PDPES; idx++) {
+		struct i915_page_directory *pde;
+
+		pde = alloc_pd(vm);
+		if (IS_ERR(pde))
+			return PTR_ERR(pde);
+
+		fill_px(pde, vm->scratch[1].encode);
+		set_pd_entry(pd, idx, pde);
+		atomic_inc(px_used(pde)); /* keep pinned */
+	}
+	wmb();
+
+	return 0;
+}
+
+static struct i915_page_directory *
+gen8_alloc_top_pd(struct i915_address_space *vm)
+{
+	const unsigned int count = gen8_pd_top_count(vm);
+	struct i915_page_directory *pd;
+
+	GEM_BUG_ON(count > ARRAY_SIZE(pd->entry));
+
+	pd = __alloc_pd(offsetof(typeof(*pd), entry[count]));
+	if (unlikely(!pd))
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
+		kfree(pd);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fill_page_dma(px_base(pd), vm->scratch[vm->top].encode, count);
+	atomic_inc(px_used(pd)); /* mark as pinned */
+	return pd;
+}
+
+/*
+ * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
+ * with a net effect resembling a 2-level page table in normal x86 terms. Each
+ * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
+ * space.
+ *
+ */
+struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt)
+{
+	struct i915_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	ppgtt_init(ppgtt, gt);
+	ppgtt->vm.top = i915_vm_is_4lvl(&ppgtt->vm) ? 3 : 2;
+
+	/*
+	 * From bdw, there is hw support for read-only pages in the PPGTT.
+	 *
+	 * Gen11 has HSDES#:1807136187 unresolved. Disable ro support
+	 * for now.
+	 *
+	 * Gen12 has inherited the same read-only fault issue from gen11.
+	 */
+	ppgtt->vm.has_read_only = !IS_GEN_RANGE(gt->i915, 11, 12);
+
+	/*
+	 * There are only few exceptions for gen >=6. chv and bxt.
+	 * And we are not sure about the latter so play safe for now.
+	 */
+	if (IS_CHERRYVIEW(gt->i915) || IS_BROXTON(gt->i915))
+		ppgtt->vm.pt_kmap_wc = true;
+
+	err = gen8_init_scratch(&ppgtt->vm);
+	if (err)
+		goto err_free;
+
+	ppgtt->pd = gen8_alloc_top_pd(&ppgtt->vm);
+	if (IS_ERR(ppgtt->pd)) {
+		err = PTR_ERR(ppgtt->pd);
+		goto err_free_scratch;
+	}
+
+	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
+		err = gen8_preallocate_top_level_pdp(ppgtt);
+		if (err)
+			goto err_free_pd;
+	}
+
+	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
+	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
+	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
+	ppgtt->vm.clear_range = gen8_ppgtt_clear;
+
+	if (intel_vgpu_active(gt->i915))
+		gen8_ppgtt_notify_vgt(ppgtt, true);
+
+	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
+
+	return ppgtt;
+
+err_free_pd:
+	__gen8_ppgtt_cleanup(&ppgtt->vm, ppgtt->pd,
+			     gen8_pd_top_count(&ppgtt->vm), ppgtt->vm.top);
+err_free_scratch:
+	free_scratch(&ppgtt->vm);
+err_free:
+	kfree(ppgtt);
+	return ERR_PTR(err);
+}
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.h b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
new file mode 100644
index 000000000000..76a08b9c1f5c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#ifndef __GEN8_PPGTT_H__
+#define __GEN8_PPGTT_H__
+
+struct intel_gt;
+
+struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 55317081d48b..0ba524a414c6 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -28,6 +28,8 @@
 
 #include "i915_drv.h"
 #include "i915_trace.h"
+#include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 
 static void irq_enable(struct intel_engine_cs *engine)
 {
@@ -53,15 +55,17 @@ static void irq_disable(struct intel_engine_cs *engine)
 
 static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b)
 {
+	struct intel_engine_cs *engine =
+		container_of(b, struct intel_engine_cs, breadcrumbs);
+
 	lockdep_assert_held(&b->irq_lock);
 
 	GEM_BUG_ON(!b->irq_enabled);
 	if (!--b->irq_enabled)
-		irq_disable(container_of(b,
-					 struct intel_engine_cs,
-					 breadcrumbs));
+		irq_disable(engine);
 
 	b->irq_armed = false;
+	intel_gt_pm_put_async(engine->gt);
 }
 
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine)
@@ -127,16 +131,23 @@ __dma_fence_signal__notify(struct dma_fence *fence,
 	}
 }
 
-void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
+static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl)
 {
-	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	struct intel_engine_cs *engine =
+		container_of(b, struct intel_engine_cs, breadcrumbs);
+
+	intel_engine_add_retire(engine, tl);
+}
+
+static void signal_irq_work(struct irq_work *work)
+{
+	struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work);
 	const ktime_t timestamp = ktime_get();
 	struct intel_context *ce, *cn;
 	struct list_head *pos, *next;
-	unsigned long flags;
 	LIST_HEAD(signal);
 
-	spin_lock_irqsave(&b->irq_lock, flags);
+	spin_lock(&b->irq_lock);
 
 	if (b->irq_armed && list_empty(&b->signalers))
 		__intel_breadcrumbs_disarm_irq(b);
@@ -177,44 +188,41 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 		if (!list_is_first(pos, &ce->signals)) {
 			/* Advance the list to the first incomplete request */
 			__list_del_many(&ce->signals, pos);
-			if (&ce->signals == pos) /* now empty */
+			if (&ce->signals == pos) { /* now empty */
 				list_del_init(&ce->signal_link);
+				add_retire(b, ce->timeline);
+			}
 		}
 	}
 
-	spin_unlock_irqrestore(&b->irq_lock, flags);
+	spin_unlock(&b->irq_lock);
 
 	list_for_each_safe(pos, next, &signal) {
 		struct i915_request *rq =
 			list_entry(pos, typeof(*rq), signal_link);
 		struct list_head cb_list;
 
-		spin_lock_irqsave(&rq->lock, flags);
+		spin_lock(&rq->lock);
 		list_replace(&rq->fence.cb_list, &cb_list);
 		__dma_fence_signal__timestamp(&rq->fence, timestamp);
 		__dma_fence_signal__notify(&rq->fence, &cb_list);
-		spin_unlock_irqrestore(&rq->lock, flags);
+		spin_unlock(&rq->lock);
 
 		i915_request_put(rq);
 	}
 }
 
-static void signal_irq_work(struct irq_work *work)
-{
-	struct intel_engine_cs *engine =
-		container_of(work, typeof(*engine), breadcrumbs.irq_work);
-
-	intel_engine_breadcrumbs_irq(engine);
-}
-
-static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
+static bool __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 {
 	struct intel_engine_cs *engine =
 		container_of(b, struct intel_engine_cs, breadcrumbs);
 
 	lockdep_assert_held(&b->irq_lock);
 	if (b->irq_armed)
-		return;
+		return true;
+
+	if (!intel_gt_pm_get_if_awake(engine->gt))
+		return false;
 
 	/*
 	 * The breadcrumb irq will be disarmed on the interrupt after the
@@ -234,6 +242,8 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b)
 
 	if (!b->irq_enabled++)
 		irq_enable(engine);
+
+	return true;
 }
 
 void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine)
@@ -271,19 +281,20 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 
 	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
 		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
-		struct intel_context *ce = rq->hw_context;
+		struct intel_context *ce = rq->context;
 		struct list_head *pos;
 
 		spin_lock(&b->irq_lock);
 		GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
 
-		__intel_breadcrumbs_arm_irq(b);
+		if (!__intel_breadcrumbs_arm_irq(b))
+			goto unlock;
 
 		/*
 		 * We keep the seqno in retirement order, so we can break
-		 * inside intel_engine_breadcrumbs_irq as soon as we've passed
-		 * the last completed request (or seen a request that hasn't
-		 * event started). We could iterate the timeline->requests list,
+		 * inside intel_engine_signal_breadcrumbs as soon as we've
+		 * passed the last completed request (or seen a request that
+		 * hasn't event started). We could walk the timeline->requests,
 		 * but keeping a separate signalers_list has the advantage of
 		 * hopefully being much smaller than the full list and so
 		 * provides faster iteration and detection when there are no
@@ -306,6 +317,7 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 		GEM_BUG_ON(!check_signal_order(ce, rq));
 
 		set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+unlock:
 		spin_unlock(&b->irq_lock);
 	}
 
@@ -326,7 +338,7 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 	 */
 	spin_lock(&b->irq_lock);
 	if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) {
-		struct intel_context *ce = rq->hw_context;
+		struct intel_context *ce = rq->context;
 
 		list_del(&rq->signal_link);
 		if (list_empty(&ce->signals))
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 5b7ff3ccfa8e..23137b2a8689 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -31,8 +31,7 @@ void intel_context_free(struct intel_context *ce)
 }
 
 struct intel_context *
-intel_context_create(struct i915_gem_context *ctx,
-		     struct intel_engine_cs *engine)
+intel_context_create(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 
@@ -40,39 +39,82 @@ intel_context_create(struct i915_gem_context *ctx,
 	if (!ce)
 		return ERR_PTR(-ENOMEM);
 
-	intel_context_init(ce, ctx, engine);
+	intel_context_init(ce, engine);
 	return ce;
 }
 
-int __intel_context_do_pin(struct intel_context *ce)
+int intel_context_alloc_state(struct intel_context *ce)
 {
-	int err;
+	int err = 0;
 
 	if (mutex_lock_interruptible(&ce->pin_mutex))
 		return -EINTR;
 
-	if (likely(!atomic_read(&ce->pin_count))) {
-		intel_wakeref_t wakeref;
+	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
+		err = ce->ops->alloc(ce);
+		if (unlikely(err))
+			goto unlock;
 
-		if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
-			err = ce->ops->alloc(ce);
-			if (unlikely(err))
-				goto err;
+		set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+	}
+
+unlock:
+	mutex_unlock(&ce->pin_mutex);
+	return err;
+}
+
+static int intel_context_active_acquire(struct intel_context *ce)
+{
+	int err;
 
-			__set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+	err = i915_active_acquire(&ce->active);
+	if (err)
+		return err;
+
+	/* Preallocate tracking nodes */
+	if (!intel_context_is_barrier(ce)) {
+		err = i915_active_acquire_preallocate_barrier(&ce->active,
+							      ce->engine);
+		if (err) {
+			i915_active_release(&ce->active);
+			return err;
 		}
+	}
+
+	return 0;
+}
 
-		err = 0;
-		with_intel_runtime_pm(ce->engine->uncore->rpm, wakeref)
-			err = ce->ops->pin(ce);
+static void intel_context_active_release(struct intel_context *ce)
+{
+	/* Nodes preallocated in intel_context_active() */
+	i915_active_acquire_barrier(&ce->active);
+	i915_active_release(&ce->active);
+}
+
+int __intel_context_do_pin(struct intel_context *ce)
+{
+	int err;
+
+	if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
+		err = intel_context_alloc_state(ce);
 		if (err)
+			return err;
+	}
+
+	if (mutex_lock_interruptible(&ce->pin_mutex))
+		return -EINTR;
+
+	if (likely(!atomic_read(&ce->pin_count))) {
+		err = intel_context_active_acquire(ce);
+		if (unlikely(err))
 			goto err;
 
-		GEM_TRACE("%s context:%llx pin ring:{head:%04x, tail:%04x}\n",
-			  ce->engine->name, ce->timeline->fence_context,
-			  ce->ring->head, ce->ring->tail);
+		err = ce->ops->pin(ce);
+		if (unlikely(err))
+			goto err_active;
 
-		i915_gem_context_get(ce->gem_context); /* for ctx->ppgtt */
+		CE_TRACE(ce, "pin ring:{head:%04x, tail:%04x}\n",
+			 ce->ring->head, ce->ring->tail);
 
 		smp_mb__before_atomic(); /* flush pin before it is visible */
 	}
@@ -83,6 +125,8 @@ int __intel_context_do_pin(struct intel_context *ce)
 	mutex_unlock(&ce->pin_mutex);
 	return 0;
 
+err_active:
+	intel_context_active_release(ce);
 err:
 	mutex_unlock(&ce->pin_mutex);
 	return err;
@@ -90,36 +134,29 @@ err:
 
 void intel_context_unpin(struct intel_context *ce)
 {
-	if (likely(atomic_add_unless(&ce->pin_count, -1, 1)))
+	if (!atomic_dec_and_test(&ce->pin_count))
 		return;
 
-	/* We may be called from inside intel_context_pin() to evict another */
-	intel_context_get(ce);
-	mutex_lock_nested(&ce->pin_mutex, SINGLE_DEPTH_NESTING);
-
-	if (likely(atomic_dec_and_test(&ce->pin_count))) {
-		GEM_TRACE("%s context:%llx retire\n",
-			  ce->engine->name, ce->timeline->fence_context);
-
-		ce->ops->unpin(ce);
-
-		i915_gem_context_put(ce->gem_context);
-		intel_context_active_release(ce);
-	}
+	CE_TRACE(ce, "unpin\n");
+	ce->ops->unpin(ce);
 
-	mutex_unlock(&ce->pin_mutex);
+	/*
+	 * Once released, we may asynchronously drop the active reference.
+	 * As that may be the only reference keeping the context alive,
+	 * take an extra now so that it is not freed before we finish
+	 * dereferencing it.
+	 */
+	intel_context_get(ce);
+	intel_context_active_release(ce);
 	intel_context_put(ce);
 }
 
 static int __context_pin_state(struct i915_vma *vma)
 {
-	u64 flags;
+	unsigned int bias = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
 	int err;
 
-	flags = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
-	flags |= PIN_HIGH | PIN_GLOBAL;
-
-	err = i915_vma_pin(vma, 0, 0, flags);
+	err = i915_ggtt_pin(vma, 0, bias | PIN_HIGH);
 	if (err)
 		return err;
 
@@ -178,9 +215,9 @@ static void __intel_context_retire(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
 
-	GEM_TRACE("%s context:%llx retire\n",
-		  ce->engine->name, ce->timeline->fence_context);
+	CE_TRACE(ce, "retire\n");
 
+	set_bit(CONTEXT_VALID_BIT, &ce->flags);
 	if (ce->state)
 		__context_unpin_state(ce->state);
 
@@ -195,6 +232,8 @@ static int __intel_context_active(struct i915_active *active)
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
 	int err;
 
+	CE_TRACE(ce, "active\n");
+
 	intel_context_get(ce);
 
 	err = __ring_active(ce->ring);
@@ -223,60 +262,21 @@ err_put:
 	return err;
 }
 
-int intel_context_active_acquire(struct intel_context *ce)
-{
-	int err;
-
-	err = i915_active_acquire(&ce->active);
-	if (err)
-		return err;
-
-	/* Preallocate tracking nodes */
-	if (!i915_gem_context_is_kernel(ce->gem_context)) {
-		err = i915_active_acquire_preallocate_barrier(&ce->active,
-							      ce->engine);
-		if (err) {
-			i915_active_release(&ce->active);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-void intel_context_active_release(struct intel_context *ce)
-{
-	/* Nodes preallocated in intel_context_active() */
-	i915_active_acquire_barrier(&ce->active);
-	i915_active_release(&ce->active);
-}
-
 void
 intel_context_init(struct intel_context *ce,
-		   struct i915_gem_context *ctx,
 		   struct intel_engine_cs *engine)
 {
-	struct i915_address_space *vm;
-
 	GEM_BUG_ON(!engine->cops);
+	GEM_BUG_ON(!engine->gt->vm);
 
 	kref_init(&ce->ref);
 
-	ce->gem_context = ctx;
-	rcu_read_lock();
-	vm = rcu_dereference(ctx->vm);
-	if (vm)
-		ce->vm = i915_vm_get(vm);
-	else
-		ce->vm = i915_vm_get(&engine->gt->ggtt->vm);
-	rcu_read_unlock();
-	if (ctx->timeline)
-		ce->timeline = intel_timeline_get(ctx->timeline);
-
 	ce->engine = engine;
 	ce->ops = engine->cops;
 	ce->sseu = engine->sseu;
-	ce->ring = __intel_context_ring_size(SZ_16K);
+	ce->ring = __intel_context_ring_size(SZ_4K);
+
+	ce->vm = i915_vm_get(engine->gt->vm);
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
@@ -341,30 +341,11 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 	int err;
 
 	/* Only suitable for use in remotely modifying this context */
-	GEM_BUG_ON(rq->hw_context == ce);
+	GEM_BUG_ON(rq->context == ce);
 
 	if (rcu_access_pointer(rq->timeline) != tl) { /* timeline sharing! */
-		/*
-		 * Ideally, we just want to insert our foreign fence as
-		 * a barrier into the remove context, such that this operation
-		 * occurs after all current operations in that context, and
-		 * all future operations must occur after this.
-		 *
-		 * Currently, the timeline->last_request tracking is guarded
-		 * by its mutex and so we must obtain that to atomically
-		 * insert our barrier. However, since we already hold our
-		 * timeline->mutex, we must be careful against potential
-		 * inversion if we are the kernel_context as the remote context
-		 * will itself poke at the kernel_context when it needs to
-		 * unpin. Ergo, if already locked, we drop both locks and
-		 * try again (through the magic of userspace repeating EAGAIN).
-		 */
-		if (!mutex_trylock(&tl->mutex))
-			return -EAGAIN;
-
 		/* Queue this switch after current activity by this context. */
 		err = i915_active_fence_set(&tl->last_request, rq);
-		mutex_unlock(&tl->mutex);
 		if (err)
 			return err;
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 68b3d317d959..30bd248827d8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -7,7 +7,9 @@
 #ifndef __INTEL_CONTEXT_H__
 #define __INTEL_CONTEXT_H__
 
+#include <linux/bitops.h>
 #include <linux/lockdep.h>
+#include <linux/types.h>
 
 #include "i915_active.h"
 #include "intel_context_types.h"
@@ -15,14 +17,21 @@
 #include "intel_ring_types.h"
 #include "intel_timeline_types.h"
 
+#define CE_TRACE(ce, fmt, ...) do {					\
+	const struct intel_context *ce__ = (ce);			\
+	ENGINE_TRACE(ce__->engine, "context:%llx " fmt,			\
+		     ce__->timeline->fence_context,			\
+		     ##__VA_ARGS__);					\
+} while (0)
+
 void intel_context_init(struct intel_context *ce,
-			struct i915_gem_context *ctx,
 			struct intel_engine_cs *engine);
 void intel_context_fini(struct intel_context *ce);
 
 struct intel_context *
-intel_context_create(struct i915_gem_context *ctx,
-		     struct intel_engine_cs *engine);
+intel_context_create(struct intel_engine_cs *engine);
+
+int intel_context_alloc_state(struct intel_context *ce);
 
 void intel_context_free(struct intel_context *ce);
 
@@ -69,9 +78,14 @@ static inline void intel_context_unlock_pinned(struct intel_context *ce)
 
 int __intel_context_do_pin(struct intel_context *ce);
 
+static inline bool intel_context_pin_if_active(struct intel_context *ce)
+{
+	return atomic_inc_not_zero(&ce->pin_count);
+}
+
 static inline int intel_context_pin(struct intel_context *ce)
 {
-	if (likely(atomic_inc_not_zero(&ce->pin_count)))
+	if (likely(intel_context_pin_if_active(ce)))
 		return 0;
 
 	return __intel_context_do_pin(ce);
@@ -109,9 +123,6 @@ static inline void intel_context_exit(struct intel_context *ce)
 		ce->ops->exit(ce);
 }
 
-int intel_context_active_acquire(struct intel_context *ce);
-void intel_context_active_release(struct intel_context *ce);
-
 static inline struct intel_context *intel_context_get(struct intel_context *ce)
 {
 	kref_get(&ce->ref);
@@ -153,4 +164,64 @@ static inline struct intel_ring *__intel_context_ring_size(u64 sz)
 	return u64_to_ptr(struct intel_ring, sz);
 }
 
+static inline bool intel_context_is_barrier(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_BARRIER_BIT, &ce->flags);
+}
+
+static inline bool intel_context_use_semaphores(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
+static inline void intel_context_set_use_semaphores(struct intel_context *ce)
+{
+	set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
+static inline void intel_context_clear_use_semaphores(struct intel_context *ce)
+{
+	clear_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
+}
+
+static inline bool intel_context_is_banned(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_BANNED, &ce->flags);
+}
+
+static inline bool intel_context_set_banned(struct intel_context *ce)
+{
+	return test_and_set_bit(CONTEXT_BANNED, &ce->flags);
+}
+
+static inline bool
+intel_context_force_single_submission(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ce->flags);
+}
+
+static inline void
+intel_context_set_single_submission(struct intel_context *ce)
+{
+	__set_bit(CONTEXT_FORCE_SINGLE_SUBMISSION, &ce->flags);
+}
+
+static inline bool
+intel_context_nopreempt(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_NOPREEMPT, &ce->flags);
+}
+
+static inline void
+intel_context_set_nopreempt(struct intel_context *ce)
+{
+	set_bit(CONTEXT_NOPREEMPT, &ce->flags);
+}
+
+static inline void
+intel_context_clear_nopreempt(struct intel_context *ce)
+{
+	clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
+}
+
 #endif /* __INTEL_CONTEXT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index 6959b05ae5f8..ca1420fb8b53 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -17,6 +17,8 @@
 #include "intel_engine_types.h"
 #include "intel_sseu.h"
 
+#define CONTEXT_REDZONE POISON_INUSE
+
 struct i915_gem_context;
 struct i915_vma;
 struct intel_context;
@@ -44,7 +46,7 @@ struct intel_context {
 #define intel_context_inflight_count(ce) ptr_unmask_bits((ce)->inflight, 2)
 
 	struct i915_address_space *vm;
-	struct i915_gem_context *gem_context;
+	struct i915_gem_context __rcu *gem_context;
 
 	struct list_head signal_link;
 	struct list_head signals;
@@ -54,7 +56,13 @@ struct intel_context {
 	struct intel_timeline *timeline;
 
 	unsigned long flags;
-#define CONTEXT_ALLOC_BIT 0
+#define CONTEXT_BARRIER_BIT		0
+#define CONTEXT_ALLOC_BIT		1
+#define CONTEXT_VALID_BIT		2
+#define CONTEXT_USE_SEMAPHORES		3
+#define CONTEXT_BANNED			4
+#define CONTEXT_FORCE_SINGLE_SUBMISSION	5
+#define CONTEXT_NOPREEMPT		6
 
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 01765a7ec18f..5df003061e44 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -29,6 +29,13 @@ struct intel_gt;
 #define CACHELINE_BYTES 64
 #define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(u32))
 
+#define ENGINE_TRACE(e, fmt, ...) do {					\
+	const struct intel_engine_cs *e__ __maybe_unused = (e);		\
+	GEM_TRACE("%s %s: " fmt,					\
+		  dev_name(e__->i915->drm.dev), e__->name,		\
+		  ##__VA_ARGS__);					\
+} while (0)
+
 /*
  * The register defines to be used with the following macros need to accept a
  * base param, e.g:
@@ -177,15 +184,15 @@ void intel_engine_stop(struct intel_engine_cs *engine);
 void intel_engine_cleanup(struct intel_engine_cs *engine);
 
 int intel_engines_init_mmio(struct intel_gt *gt);
-int intel_engines_setup(struct intel_gt *gt);
 int intel_engines_init(struct intel_gt *gt);
-void intel_engines_cleanup(struct intel_gt *gt);
+
+void intel_engines_release(struct intel_gt *gt);
+void intel_engines_free(struct intel_gt *gt);
 
 int intel_engine_init_common(struct intel_engine_cs *engine);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
 int intel_ring_submission_setup(struct intel_engine_cs *engine);
-int intel_ring_submission_init(struct intel_engine_cs *engine);
 
 int intel_engine_stop_cs(struct intel_engine_cs *engine);
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
@@ -195,7 +202,7 @@ void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
 u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
 
-void intel_engine_get_instdone(struct intel_engine_cs *engine,
+void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone);
 
 void intel_engine_init_execlists(struct intel_engine_cs *engine);
@@ -206,13 +213,11 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine);
 
 static inline void
-intel_engine_queue_breadcrumbs(struct intel_engine_cs *engine)
+intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
 {
 	irq_work_queue(&engine->breadcrumbs.irq_work);
 }
 
-void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine);
-
 void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 
@@ -270,8 +275,8 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags)
 static inline void __intel_engine_reset(struct intel_engine_cs *engine,
 					bool stalled)
 {
-	if (engine->reset.reset)
-		engine->reset.reset(engine, stalled);
+	if (engine->reset.rewind)
+		engine->reset.rewind(engine, stalled);
 	engine->serial++; /* contexts lost */
 }
 
@@ -296,7 +301,7 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 struct i915_request *
 intel_engine_find_active_request(struct intel_engine_cs *engine);
 
-u32 intel_engine_context_size(struct drm_i915_private *i915, u8 class);
+u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 813bd3a610d2..f451ef376548 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -141,7 +141,7 @@ static const struct engine_info intel_engines[] = {
 
 /**
  * intel_engine_context_size() - return the size of the context for an engine
- * @dev_priv: i915 device private
+ * @gt: the gt
  * @class: engine class
  *
  * Each engine class may require a different amount of space for a context
@@ -153,17 +153,18 @@ static const struct engine_info intel_engines[] = {
  * in LRC mode, but does not include the "shared data page" used with
  * GuC submission. The caller should account for this if using the GuC.
  */
-u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
+u32 intel_engine_context_size(struct intel_gt *gt, u8 class)
 {
+	struct intel_uncore *uncore = gt->uncore;
 	u32 cxt_size;
 
 	BUILD_BUG_ON(I915_GTT_PAGE_SIZE != PAGE_SIZE);
 
 	switch (class) {
 	case RENDER_CLASS:
-		switch (INTEL_GEN(dev_priv)) {
+		switch (INTEL_GEN(gt->i915)) {
 		default:
-			MISSING_CASE(INTEL_GEN(dev_priv));
+			MISSING_CASE(INTEL_GEN(gt->i915));
 			return DEFAULT_LR_CONTEXT_RENDER_SIZE;
 		case 12:
 		case 11:
@@ -175,14 +176,14 @@ u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		case 8:
 			return GEN8_LR_CONTEXT_RENDER_SIZE;
 		case 7:
-			if (IS_HASWELL(dev_priv))
+			if (IS_HASWELL(gt->i915))
 				return HSW_CXT_TOTAL_SIZE;
 
-			cxt_size = I915_READ(GEN7_CXT_SIZE);
+			cxt_size = intel_uncore_read(uncore, GEN7_CXT_SIZE);
 			return round_up(GEN7_CXT_TOTAL_SIZE(cxt_size) * 64,
 					PAGE_SIZE);
 		case 6:
-			cxt_size = I915_READ(CXT_SIZE);
+			cxt_size = intel_uncore_read(uncore, CXT_SIZE);
 			return round_up(GEN6_CXT_TOTAL_SIZE(cxt_size) * 64,
 					PAGE_SIZE);
 		case 5:
@@ -197,9 +198,9 @@ u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 			 * minimum allocation anyway so it should all come
 			 * out in the wash.
 			 */
-			cxt_size = I915_READ(CXT_SIZE) + 1;
+			cxt_size = intel_uncore_read(uncore, CXT_SIZE) + 1;
 			DRM_DEBUG_DRIVER("gen%d CXT_SIZE = %d bytes [0x%08x]\n",
-					 INTEL_GEN(dev_priv),
+					 INTEL_GEN(gt->i915),
 					 cxt_size * 64,
 					 cxt_size - 1);
 			return round_up(cxt_size * 64, PAGE_SIZE);
@@ -216,7 +217,7 @@ u32 intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
-		if (INTEL_GEN(dev_priv) < 8)
+		if (INTEL_GEN(gt->i915) < 8)
 			return 0;
 		return GEN8_LR_CONTEXT_OTHER_SIZE;
 	}
@@ -318,14 +319,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->props.timeslice_duration_ms =
 		CONFIG_DRM_I915_TIMESLICE_DURATION;
 
-	/*
-	 * To be overridden by the backend on setup. However to facilitate
-	 * cleanup on error during setup, we always provide the destroy vfunc.
-	 */
-	engine->destroy = (typeof(engine->destroy))kfree;
-
-	engine->context_size = intel_engine_context_size(gt->i915,
-							 engine->class);
+	engine->context_size = intel_engine_context_size(gt, engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
 	if (engine->context_size)
@@ -334,6 +328,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	ewma__engine_latency_init(&engine->latency);
 	seqlock_init(&engine->stats.lock);
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
@@ -344,7 +339,6 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	gt->engine_class[info->class][info->instance] = engine;
 	gt->engine[id] = engine;
 
-	intel_engine_add_user(engine);
 	gt->i915->engine[id] = engine;
 
 	return 0;
@@ -390,21 +384,39 @@ static void intel_setup_engine_capabilities(struct intel_gt *gt)
 }
 
 /**
- * intel_engines_cleanup() - free the resources allocated for Command Streamers
+ * intel_engines_release() - free the resources allocated for Command Streamers
  * @gt: pointer to struct intel_gt
  */
-void intel_engines_cleanup(struct intel_gt *gt)
+void intel_engines_release(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	/* Decouple the backend; but keep the layout for late GPU resets */
 	for_each_engine(engine, gt, id) {
-		engine->destroy(engine);
-		gt->engine[id] = NULL;
+		if (!engine->release)
+			continue;
+
+		engine->release(engine);
+		engine->release = NULL;
+
+		memset(&engine->reset, 0, sizeof(engine->reset));
+
 		gt->i915->engine[id] = NULL;
 	}
 }
 
+void intel_engines_free(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id) {
+		kfree(engine);
+		gt->engine[id] = NULL;
+	}
+}
+
 /**
  * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers
  * @gt: pointer to struct intel_gt
@@ -455,38 +467,7 @@ int intel_engines_init_mmio(struct intel_gt *gt)
 	return 0;
 
 cleanup:
-	intel_engines_cleanup(gt);
-	return err;
-}
-
-/**
- * intel_engines_init() - init the Engine Command Streamers
- * @gt: pointer to struct intel_gt
- *
- * Return: non-zero if the initialization failed.
- */
-int intel_engines_init(struct intel_gt *gt)
-{
-	int (*init)(struct intel_engine_cs *engine);
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err;
-
-	if (HAS_EXECLISTS(gt->i915))
-		init = intel_execlists_submission_init;
-	else
-		init = intel_ring_submission_init;
-
-	for_each_engine(engine, gt, id) {
-		err = init(engine);
-		if (err)
-			goto cleanup;
-	}
-
-	return 0;
-
-cleanup:
-	intel_engines_cleanup(gt);
+	intel_engines_free(gt);
 	return err;
 }
 
@@ -601,7 +582,7 @@ err:
 	return ret;
 }
 
-static int intel_engine_setup_common(struct intel_engine_cs *engine)
+static int engine_setup_common(struct intel_engine_cs *engine)
 {
 	int err;
 
@@ -631,49 +612,6 @@ static int intel_engine_setup_common(struct intel_engine_cs *engine)
 	return 0;
 }
 
-/**
- * intel_engines_setup- setup engine state not requiring hw access
- * @gt: pointer to struct intel_gt
- *
- * Initializes engine structure members shared between legacy and execlists
- * submission modes which do not require hardware access.
- *
- * Typically done early in the submission mode specific engine setup stage.
- */
-int intel_engines_setup(struct intel_gt *gt)
-{
-	int (*setup)(struct intel_engine_cs *engine);
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err;
-
-	if (HAS_EXECLISTS(gt->i915))
-		setup = intel_execlists_submission_setup;
-	else
-		setup = intel_ring_submission_setup;
-
-	for_each_engine(engine, gt, id) {
-		err = intel_engine_setup_common(engine);
-		if (err)
-			goto cleanup;
-
-		err = setup(engine);
-		if (err)
-			goto cleanup;
-
-		/* We expect the backend to take control over its state */
-		GEM_BUG_ON(engine->destroy == (typeof(engine->destroy))kfree);
-
-		GEM_BUG_ON(!engine->cops);
-	}
-
-	return 0;
-
-cleanup:
-	intel_engines_cleanup(gt);
-	return err;
-}
-
 struct measure_breadcrumb {
 	struct i915_request rq;
 	struct intel_timeline timeline;
@@ -757,13 +695,13 @@ create_kernel_context(struct intel_engine_cs *engine)
 	struct intel_context *ce;
 	int err;
 
-	ce = intel_context_create(engine->i915->kernel_context, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return ce;
 
-	ce->ring = __intel_context_ring_size(SZ_4K);
+	__set_bit(CONTEXT_BARRIER_BIT, &ce->flags);
 
-	err = intel_context_pin(ce);
+	err = intel_context_pin(ce); /* perma-pin so it is always available */
 	if (err) {
 		intel_context_put(ce);
 		return ERR_PTR(err);
@@ -791,13 +729,19 @@ create_kernel_context(struct intel_engine_cs *engine)
  *
  * Returns zero on success or an error code on failure.
  */
-int intel_engine_init_common(struct intel_engine_cs *engine)
+static int engine_init_common(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 	int ret;
 
 	engine->set_default_submission(engine);
 
+	ret = measure_breadcrumb_dw(engine);
+	if (ret < 0)
+		return ret;
+
+	engine->emit_fini_breadcrumb_dw = ret;
+
 	/*
 	 * We may need to do things with the shrinker which
 	 * require us to immediately switch back to the default
@@ -812,18 +756,38 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 
 	engine->kernel_context = ce;
 
-	ret = measure_breadcrumb_dw(engine);
-	if (ret < 0)
-		goto err_unpin;
+	return 0;
+}
 
-	engine->emit_fini_breadcrumb_dw = ret;
+int intel_engines_init(struct intel_gt *gt)
+{
+	int (*setup)(struct intel_engine_cs *engine);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err;
 
-	return 0;
+	if (HAS_EXECLISTS(gt->i915))
+		setup = intel_execlists_submission_setup;
+	else
+		setup = intel_ring_submission_setup;
 
-err_unpin:
-	intel_context_unpin(ce);
-	intel_context_put(ce);
-	return ret;
+	for_each_engine(engine, gt, id) {
+		err = engine_setup_common(engine);
+		if (err)
+			return err;
+
+		err = setup(engine);
+		if (err)
+			return err;
+
+		err = engine_init_common(engine);
+		if (err)
+			return err;
+
+		intel_engine_add_user(engine);
+	}
+
+	return 0;
 }
 
 /**
@@ -836,6 +800,7 @@ err_unpin:
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
 	GEM_BUG_ON(!list_empty(&engine->active.requests));
+	tasklet_kill(&engine->execlists.tasklet); /* flush the callback */
 
 	cleanup_status_page(engine);
 
@@ -911,7 +876,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 	if (INTEL_GEN(engine->i915) < 3)
 		return -ENODEV;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
 
@@ -920,7 +885,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 					 mode, MODE_IDLE, MODE_IDLE,
 					 1000, stop_timeout(engine),
 					 NULL)) {
-		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+		ENGINE_TRACE(engine, "timed out on STOP_RING -> IDLE\n");
 		err = -ETIMEDOUT;
 	}
 
@@ -932,7 +897,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 
 void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
 {
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
 }
@@ -949,8 +914,8 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 }
 
 static u32
-read_subslice_reg(struct intel_engine_cs *engine, int slice, int subslice,
-		  i915_reg_t reg)
+read_subslice_reg(const struct intel_engine_cs *engine,
+		  int slice, int subslice, i915_reg_t reg)
 {
 	struct drm_i915_private *i915 = engine->i915;
 	struct intel_uncore *uncore = engine->uncore;
@@ -994,7 +959,7 @@ read_subslice_reg(struct intel_engine_cs *engine, int slice, int subslice,
 }
 
 /* NB: please notice the memset */
-void intel_engine_get_instdone(struct intel_engine_cs *engine,
+void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone)
 {
 	struct drm_i915_private *i915 = engine->i915;
@@ -1478,6 +1443,10 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "*** WEDGED ***\n");
 
 	drm_printf(m, "\tAwake? %d\n", atomic_read(&engine->wakeref.count));
+	drm_printf(m, "\tBarriers?: %s\n",
+		   yesno(!llist_empty(&engine->barrier_tasks)));
+	drm_printf(m, "\tLatency: %luus\n",
+		   ewma__engine_latency_read(&engine->latency));
 
 	rcu_read_lock();
 	rq = READ_ONCE(engine->heartbeat.systole);
@@ -1517,9 +1486,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 
 		print_request_ring(m, rq);
 
-		if (rq->hw_context->lrc_reg_state) {
+		if (rq->context->lrc_reg_state) {
 			drm_printf(m, "Logical Ring Context:\n");
-			hexdump(m, rq->hw_context->lrc_reg_state, PAGE_SIZE);
+			hexdump(m, rq->context->lrc_reg_state, PAGE_SIZE);
 		}
 	}
 	spin_unlock_irqrestore(&engine->active.lock, flags);
@@ -1580,7 +1549,7 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 
 		for (port = execlists->pending; (rq = *port); port++) {
 			/* Exclude any contexts already counted in active */
-			if (!intel_context_inflight_count(rq->hw_context))
+			if (!intel_context_inflight_count(rq->context))
 				engine->stats.active++;
 		}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
index 06aa14c7aa8c..6c6fd185457c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -63,15 +63,15 @@ static void heartbeat(struct work_struct *wrk)
 	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
 
-	if (!intel_engine_pm_get_if_awake(engine))
-		return;
-
 	rq = engine->heartbeat.systole;
 	if (rq && i915_request_completed(rq)) {
 		i915_request_put(rq);
 		engine->heartbeat.systole = NULL;
 	}
 
+	if (!intel_engine_pm_get_if_awake(engine))
+		return;
+
 	if (intel_gt_is_wedged(engine->gt))
 		goto out;
 
@@ -199,7 +199,7 @@ int intel_engine_pulse(struct intel_engine_cs *engine)
 		goto out_unlock;
 	}
 
-	rq->flags |= I915_REQUEST_SENTINEL;
+	__set_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags);
 	idle_pulse(engine, rq);
 
 	__i915_request_commit(rq);
@@ -215,18 +215,26 @@ out_rpm:
 int intel_engine_flush_barriers(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
+	int err = 0;
 
 	if (llist_empty(&engine->barrier_tasks))
 		return 0;
 
+	if (!intel_engine_pm_get_if_awake(engine))
+		return 0;
+
 	rq = i915_request_create(engine->kernel_context);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_rpm;
+	}
 
 	idle_pulse(engine, rq);
 	i915_request_add(rq);
 
-	return 0;
+out_rpm:
+	intel_engine_pm_put(engine);
+	return err;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index c1dd0cd3efc7..ea90ab3e396e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -6,6 +6,7 @@
 
 #include "i915_drv.h"
 
+#include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
@@ -19,9 +20,10 @@ static int __engine_unpark(struct intel_wakeref *wf)
 {
 	struct intel_engine_cs *engine =
 		container_of(wf, typeof(*engine), wakeref);
+	struct intel_context *ce;
 	void *map;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	intel_gt_pm_get(engine->gt);
 
@@ -33,6 +35,27 @@ static int __engine_unpark(struct intel_wakeref *wf)
 	if (!IS_ERR_OR_NULL(map))
 		engine->pinned_default_state = map;
 
+	/* Discard stale context state from across idling */
+	ce = engine->kernel_context;
+	if (ce) {
+		GEM_BUG_ON(test_bit(CONTEXT_VALID_BIT, &ce->flags));
+
+		/* First poison the image to verify we never fully trust it */
+		if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && ce->state) {
+			struct drm_i915_gem_object *obj = ce->state->obj;
+			int type = i915_coherent_map_type(engine->i915);
+
+			map = i915_gem_object_pin_map(obj, type);
+			if (!IS_ERR(map)) {
+				memset(map, CONTEXT_REDZONE, obj->base.size);
+				i915_gem_object_flush_map(obj);
+				i915_gem_object_unpin_map(obj);
+			}
+		}
+
+		ce->ops->reset(ce);
+	}
+
 	if (engine->unpark)
 		engine->unpark(engine);
 
@@ -73,6 +96,15 @@ static inline void __timeline_mark_unlock(struct intel_context *ce,
 
 #endif /* !IS_ENABLED(CONFIG_LOCKDEP) */
 
+static void duration(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct i915_request *rq = to_request(fence);
+
+	ewma__engine_latency_add(&rq->engine->latency,
+				 ktime_us_delta(rq->fence.timestamp,
+						rq->duration.emitted));
+}
+
 static void
 __queue_and_release_pm(struct i915_request *rq,
 		       struct intel_timeline *tl,
@@ -80,7 +112,7 @@ __queue_and_release_pm(struct i915_request *rq,
 {
 	struct intel_gt_timelines *timelines = &engine->gt->timelines;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * We have to serialise all potential retirement paths with our
@@ -113,14 +145,16 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	unsigned long flags;
 	bool result = true;
 
-	/* Already inside the kernel context, safe to power down. */
-	if (engine->wakeref_serial == engine->serial)
-		return true;
-
 	/* GPU is pointing to the void, as good as in the kernel context. */
 	if (intel_gt_is_wedged(engine->gt))
 		return true;
 
+	GEM_BUG_ON(!intel_context_is_barrier(ce));
+
+	/* Already inside the kernel context, safe to power down. */
+	if (engine->wakeref_serial == engine->serial)
+		return true;
+
 	/*
 	 * Note, we do this without taking the timeline->mutex. We cannot
 	 * as we may be called while retiring the kernel context and so
@@ -163,7 +197,18 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 
 	/* Install ourselves as a preemption barrier */
 	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
-	__i915_request_commit(rq);
+	if (likely(!__i915_request_commit(rq))) { /* engine should be idle! */
+		/*
+		 * Use an interrupt for precise measurement of duration,
+		 * otherwise we rely on someone else retiring all the requests
+		 * which may delay the signaling (i.e. we will likely wait
+		 * until the background request retirement running every
+		 * second or two).
+		 */
+		BUILD_BUG_ON(sizeof(rq->duration) > sizeof(rq->submitq));
+		dma_fence_add_callback(&rq->fence, &rq->duration.cb, duration);
+		rq->duration.emitted = ktime_get();
+	}
 
 	/* Expose ourselves to the world */
 	__queue_and_release_pm(rq, ce->timeline, engine);
@@ -183,7 +228,7 @@ static void call_idle_barriers(struct intel_engine_cs *engine)
 			container_of((struct list_head *)node,
 				     typeof(*cb), node);
 
-		cb->func(NULL, cb);
+		cb->func(ERR_PTR(-EAGAIN), cb);
 	}
 }
 
@@ -204,7 +249,7 @@ static int __engine_park(struct intel_wakeref *wf)
 	if (!switch_to_kernel_context(engine))
 		return -EBUSY;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	call_idle_barriers(engine); /* cleanup after wedging */
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index 24e20344dc22..e52c2b0cb245 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -7,6 +7,7 @@
 #ifndef INTEL_ENGINE_PM_H
 #define INTEL_ENGINE_PM_H
 
+#include "i915_request.h"
 #include "intel_engine_types.h"
 #include "intel_wakeref.h"
 
@@ -41,6 +42,26 @@ static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
 	intel_wakeref_unlock_wait(&engine->wakeref);
 }
 
+static inline struct i915_request *
+intel_engine_create_kernel_request(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	/*
+	 * The engine->kernel_context is special as it is used inside
+	 * the engine-pm barrier (see __engine_park()), circumventing
+	 * the usual mutexes and relying on the engine-pm barrier
+	 * instead. So whenever we use the engine->kernel_context
+	 * outside of the barrier, we must manually handle the
+	 * engine wakeref to serialise with the use inside.
+	 */
+	intel_engine_pm_get(engine);
+	rq = i915_request_create(engine->kernel_context);
+	intel_engine_pm_put(engine);
+
+	return rq;
+}
+
 void intel_engine_init__pm(struct intel_engine_cs *engine);
 
 #endif /* INTEL_ENGINE_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 2b446474e010..350da59e605b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -7,6 +7,7 @@
 #ifndef __INTEL_ENGINE_TYPES__
 #define __INTEL_ENGINE_TYPES__
 
+#include <linux/average.h>
 #include <linux/hashtable.h>
 #include <linux/irq_work.h>
 #include <linux/kref.h>
@@ -119,6 +120,9 @@ enum intel_engine_id {
 #define INVALID_ENGINE ((enum intel_engine_id)-1)
 };
 
+/* A simple estimator for the round-trip latency of an engine */
+DECLARE_EWMA(_engine_latency, 6, 4)
+
 struct st_preempt_hang {
 	struct completion completion;
 	unsigned int count;
@@ -316,6 +320,13 @@ struct intel_engine_cs {
 		struct intel_timeline *timeline;
 	} legacy;
 
+	/*
+	 * We track the average duration of the idle pulse on parking the
+	 * engine to keep an estimate of the how the fast the engine is
+	 * under ideal conditions.
+	 */
+	struct ewma__engine_latency latency;
+
 	/* Rather than have every client wait upon all user interrupts,
 	 * with the herd waking after every interrupt and each doing the
 	 * heavyweight seqno dance, we delegate the task (of being the
@@ -389,7 +400,10 @@ struct intel_engine_cs {
 
 	struct {
 		void (*prepare)(struct intel_engine_cs *engine);
-		void (*reset)(struct intel_engine_cs *engine, bool stalled);
+
+		void (*rewind)(struct intel_engine_cs *engine, bool stalled);
+		void (*cancel)(struct intel_engine_cs *engine);
+
 		void (*finish)(struct intel_engine_cs *engine);
 	} reset;
 
@@ -439,15 +453,7 @@ struct intel_engine_cs {
 	void		(*schedule)(struct i915_request *request,
 				    const struct i915_sched_attr *attr);
 
-	/*
-	 * Cancel all requests on the hardware, or queued for execution.
-	 * This should only cancel the ready requests that have been
-	 * submitted to the engine (via the engine->submit_request callback).
-	 * This is called when marking the device as wedged.
-	 */
-	void		(*cancel_requests)(struct intel_engine_cs *engine);
-
-	void		(*destroy)(struct intel_engine_cs *engine);
+	void		(*release)(struct intel_engine_cs *engine);
 
 	struct intel_engine_execlists execlists;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 7f7150a733f4..9e7f12bef828 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -11,6 +11,7 @@
 #include "i915_drv.h"
 #include "intel_engine.h"
 #include "intel_engine_user.h"
+#include "intel_gt.h"
 
 struct intel_engine_cs *
 intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
@@ -200,6 +201,9 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
 				     uabi_node);
 		char old[sizeof(engine->name)];
 
+		if (intel_gt_has_init_error(engine->gt))
+			continue; /* ignore incomplete engines */
+
 		GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes));
 		engine->uabi_class = uabi_classes[engine->class];
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
new file mode 100644
index 000000000000..531d501be01f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -0,0 +1,1486 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/stop_machine.h>
+
+#include <asm/set_memory.h>
+#include <asm/smp.h>
+
+#include "intel_gt.h"
+#include "i915_drv.h"
+#include "i915_scatterlist.h"
+#include "i915_vgpu.h"
+
+#include "intel_gtt.h"
+
+static int
+i915_get_ggtt_vma_pages(struct i915_vma *vma);
+
+static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
+				   unsigned long color,
+				   u64 *start,
+				   u64 *end)
+{
+	if (i915_node_color_differs(node, color))
+		*start += I915_GTT_PAGE_SIZE;
+
+	/*
+	 * Also leave a space between the unallocated reserved node after the
+	 * GTT and any objects within the GTT, i.e. we use the color adjustment
+	 * to insert a guard page to prevent prefetches crossing over the
+	 * GTT boundary.
+	 */
+	node = list_next_entry(node, node_list);
+	if (node->color != color)
+		*end -= I915_GTT_PAGE_SIZE;
+}
+
+static int ggtt_init_hw(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+
+	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
+
+	ggtt->vm.is_ggtt = true;
+
+	/* Only VLV supports read-only GGTT mappings */
+	ggtt->vm.has_read_only = IS_VALLEYVIEW(i915);
+
+	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
+		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
+
+	if (ggtt->mappable_end) {
+		if (!io_mapping_init_wc(&ggtt->iomap,
+					ggtt->gmadr.start,
+					ggtt->mappable_end)) {
+			ggtt->vm.cleanup(&ggtt->vm);
+			return -EIO;
+		}
+
+		ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start,
+					      ggtt->mappable_end);
+	}
+
+	i915_ggtt_init_fences(ggtt);
+
+	return 0;
+}
+
+/**
+ * i915_ggtt_init_hw - Initialize GGTT hardware
+ * @i915: i915 device
+ */
+int i915_ggtt_init_hw(struct drm_i915_private *i915)
+{
+	int ret;
+
+	stash_init(&i915->mm.wc_stash);
+
+	/*
+	 * Note that we use page colouring to enforce a guard page at the
+	 * end of the address space. This is required as the CS may prefetch
+	 * beyond the end of the batch buffer, across the page boundary,
+	 * and beyond the end of the GTT if we do not provide a guard.
+	 */
+	ret = ggtt_init_hw(&i915->ggtt);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * Certain Gen5 chipsets require require idling the GPU before
+ * unmapping anything from the GTT when VT-d is enabled.
+ */
+static bool needs_idle_maps(struct drm_i915_private *i915)
+{
+	/*
+	 * Query intel_iommu to see if we need the workaround. Presumably that
+	 * was loaded first.
+	 */
+	return IS_GEN(i915, 5) && IS_MOBILE(i915) && intel_vtd_active();
+}
+
+static void ggtt_suspend_mappings(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+
+	/*
+	 * Don't bother messing with faults pre GEN6 as we have little
+	 * documentation supporting that it's a good idea.
+	 */
+	if (INTEL_GEN(i915) < 6)
+		return;
+
+	intel_gt_check_and_clear_faults(ggtt->vm.gt);
+
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
+
+	ggtt->invalidate(ggtt);
+}
+
+void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915)
+{
+	ggtt_suspend_mappings(&i915->ggtt);
+}
+
+void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+
+	spin_lock_irq(&uncore->lock);
+	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+	intel_uncore_read_fw(uncore, GFX_FLSH_CNTL_GEN6);
+	spin_unlock_irq(&uncore->lock);
+}
+
+static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+
+	/*
+	 * Note that as an uncached mmio write, this will flush the
+	 * WCB of the writes into the GGTT before it triggers the invalidate.
+	 */
+	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
+}
+
+static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+
+	gen8_ggtt_invalidate(ggtt);
+
+	if (INTEL_GEN(i915) >= 12)
+		intel_uncore_write_fw(uncore, GEN12_GUC_TLB_INV_CR,
+				      GEN12_GUC_TLB_INV_CR_INVALIDATE);
+	else
+		intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+}
+
+static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
+{
+	intel_gtt_chipset_flush();
+}
+
+static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
+{
+	writeq(pte, addr);
+}
+
+static void gen8_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  u64 offset,
+				  enum i915_cache_level level,
+				  u32 unused)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen8_pte_t __iomem *pte =
+		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
+
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
+
+	ggtt->invalidate(ggtt);
+}
+
+static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
+				     struct i915_vma *vma,
+				     enum i915_cache_level level,
+				     u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	struct sgt_iter sgt_iter;
+	gen8_pte_t __iomem *gtt_entries;
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
+	dma_addr_t addr;
+
+	/*
+	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
+	 * not to allow the user to override access to a read only page.
+	 */
+
+	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
+	gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE;
+	for_each_sgt_daddr(addr, sgt_iter, vma->pages)
+		gen8_set_pte(gtt_entries++, pte_encode | addr);
+
+	/*
+	 * We want to flush the TLBs only after we're certain all the PTE
+	 * updates have finished.
+	 */
+	ggtt->invalidate(ggtt);
+}
+
+static void gen6_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  u64 offset,
+				  enum i915_cache_level level,
+				  u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen6_pte_t __iomem *pte =
+		(gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
+
+	iowrite32(vm->pte_encode(addr, level, flags), pte);
+
+	ggtt->invalidate(ggtt);
+}
+
+/*
+ * Binds an object into the global gtt with the specified cache level.
+ * The object will be accessible to the GPU via commands whose operands
+ * reference offsets within the global GTT as well as accessible by the GPU
+ * through the GMADR mapped BAR (i915->mm.gtt->gtt).
+ */
+static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
+				     struct i915_vma *vma,
+				     enum i915_cache_level level,
+				     u32 flags)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm;
+	unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE;
+	struct sgt_iter iter;
+	dma_addr_t addr;
+
+	for_each_sgt_daddr(addr, iter, vma->pages)
+		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
+
+	/*
+	 * We want to flush the TLBs only after we're certain all the PTE
+	 * updates have finished.
+	 */
+	ggtt->invalidate(ggtt);
+}
+
+static void nop_clear_range(struct i915_address_space *vm,
+			    u64 start, u64 length)
+{
+}
+
+static void gen8_ggtt_clear_range(struct i915_address_space *vm,
+				  u64 start, u64 length)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+	const gen8_pte_t scratch_pte = vm->scratch[0].encode;
+	gen8_pte_t __iomem *gtt_base =
+		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
+	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+	int i;
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	for (i = 0; i < num_entries; i++)
+		gen8_set_pte(&gtt_base[i], scratch_pte);
+}
+
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+	/*
+	 * Make sure the internal GAM fifo has been cleared of all GTT
+	 * writes before exiting stop_machine(). This guarantees that
+	 * any aperture accesses waiting to start in another process
+	 * cannot back up behind the GTT writes causing a hang.
+	 * The register can be any arbitrary GAM register.
+	 */
+	intel_uncore_posting_read_fw(vm->gt->uncore, GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+	struct i915_address_space *vm;
+	dma_addr_t addr;
+	u64 offset;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+	struct insert_page *arg = _arg;
+
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+					  dma_addr_t addr,
+					  u64 offset,
+					  enum i915_cache_level level,
+					  u32 unused)
+{
+	struct insert_page arg = { vm, addr, offset, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct i915_vma *vma;
+	enum i915_cache_level level;
+	u32 flags;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+
+	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					     struct i915_vma *vma,
+					     enum i915_cache_level level,
+					     u32 flags)
+{
+	struct insert_entries arg = { vm, vma, level, flags };
+
+	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+	struct i915_address_space *vm;
+	u64 start;
+	u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+	struct clear_range *arg = _arg;
+
+	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+					  u64 start,
+					  u64 length)
+{
+	struct clear_range arg = { vm, start, length };
+
+	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
+static void gen6_ggtt_clear_range(struct i915_address_space *vm,
+				  u64 start, u64 length)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
+	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
+	gen6_pte_t scratch_pte, __iomem *gtt_base =
+		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
+	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
+	int i;
+
+	if (WARN(num_entries > max_entries,
+		 "First entry = %d; Num entries = %d (max=%d)\n",
+		 first_entry, num_entries, max_entries))
+		num_entries = max_entries;
+
+	scratch_pte = vm->scratch[0].encode;
+	for (i = 0; i < num_entries; i++)
+		iowrite32(scratch_pte, &gtt_base[i]);
+}
+
+static void i915_ggtt_insert_page(struct i915_address_space *vm,
+				  dma_addr_t addr,
+				  u64 offset,
+				  enum i915_cache_level cache_level,
+				  u32 unused)
+{
+	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
+}
+
+static void i915_ggtt_insert_entries(struct i915_address_space *vm,
+				     struct i915_vma *vma,
+				     enum i915_cache_level cache_level,
+				     u32 unused)
+{
+	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
+		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
+
+	intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT,
+				    flags);
+}
+
+static void i915_ggtt_clear_range(struct i915_address_space *vm,
+				  u64 start, u64 length)
+{
+	intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
+}
+
+static int ggtt_bind_vma(struct i915_vma *vma,
+			 enum i915_cache_level cache_level,
+			 u32 flags)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+	u32 pte_flags;
+
+	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
+	pte_flags = 0;
+	if (i915_gem_object_is_readonly(obj))
+		pte_flags |= PTE_READ_ONLY;
+
+	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+
+	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
+
+	/*
+	 * Without aliasing PPGTT there's no difference between
+	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
+	 * upgrade to both bound if we bind either to avoid double-binding.
+	 */
+	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
+
+	return 0;
+}
+
+static void ggtt_unbind_vma(struct i915_vma *vma)
+{
+	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
+}
+
+static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
+{
+	u64 size;
+	int ret;
+
+	if (!USES_GUC(ggtt->vm.i915))
+		return 0;
+
+	GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP);
+	size = ggtt->vm.total - GUC_GGTT_TOP;
+
+	ret = i915_gem_gtt_reserve(&ggtt->vm, &ggtt->uc_fw, size,
+				   GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE,
+				   PIN_NOEVICT);
+	if (ret)
+		DRM_DEBUG_DRIVER("Failed to reserve top of GGTT for GuC\n");
+
+	return ret;
+}
+
+static void ggtt_release_guc_top(struct i915_ggtt *ggtt)
+{
+	if (drm_mm_node_allocated(&ggtt->uc_fw))
+		drm_mm_remove_node(&ggtt->uc_fw);
+}
+
+static void cleanup_init_ggtt(struct i915_ggtt *ggtt)
+{
+	ggtt_release_guc_top(ggtt);
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_mm_remove_node(&ggtt->error_capture);
+	mutex_destroy(&ggtt->error_mutex);
+}
+
+static int init_ggtt(struct i915_ggtt *ggtt)
+{
+	/*
+	 * Let GEM Manage all of the aperture.
+	 *
+	 * However, leave one page at the end still bound to the scratch page.
+	 * There are a number of places where the hardware apparently prefetches
+	 * past the end of the object, and we've seen multiple hangs with the
+	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
+	 * aperture.  One page should be enough to keep any prefetching inside
+	 * of the aperture.
+	 */
+	unsigned long hole_start, hole_end;
+	struct drm_mm_node *entry;
+	int ret;
+
+	/*
+	 * GuC requires all resources that we're sharing with it to be placed in
+	 * non-WOPCM memory. If GuC is not present or not in use we still need a
+	 * small bias as ring wraparound at offset 0 sometimes hangs. No idea
+	 * why.
+	 */
+	ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE,
+			       intel_wopcm_guc_size(&ggtt->vm.i915->wopcm));
+
+	ret = intel_vgt_balloon(ggtt);
+	if (ret)
+		return ret;
+
+	mutex_init(&ggtt->error_mutex);
+	if (ggtt->mappable_end) {
+		/* Reserve a mappable slot for our lockless error capture */
+		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm,
+						  &ggtt->error_capture,
+						  PAGE_SIZE, 0,
+						  I915_COLOR_UNEVICTABLE,
+						  0, ggtt->mappable_end,
+						  DRM_MM_INSERT_LOW);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * The upper portion of the GuC address space has a sizeable hole
+	 * (several MB) that is inaccessible by GuC. Reserve this range within
+	 * GGTT as it can comfortably hold GuC/HuC firmware images.
+	 */
+	ret = ggtt_reserve_guc_top(ggtt);
+	if (ret)
+		goto err;
+
+	/* Clear any non-preallocated blocks */
+	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
+		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
+			      hole_start, hole_end);
+		ggtt->vm.clear_range(&ggtt->vm, hole_start,
+				     hole_end - hole_start);
+	}
+
+	/* And finally clear the reserved guard page */
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
+
+	return 0;
+
+err:
+	cleanup_init_ggtt(ggtt);
+	return ret;
+}
+
+static int aliasing_gtt_bind_vma(struct i915_vma *vma,
+				 enum i915_cache_level cache_level,
+				 u32 flags)
+{
+	u32 pte_flags;
+	int ret;
+
+	/* Currently applicable only to VLV */
+	pte_flags = 0;
+	if (i915_gem_object_is_readonly(vma->obj))
+		pte_flags |= PTE_READ_ONLY;
+
+	if (flags & I915_VMA_LOCAL_BIND) {
+		struct i915_ppgtt *alias = i915_vm_to_ggtt(vma->vm)->alias;
+
+		if (flags & I915_VMA_ALLOC) {
+			ret = alias->vm.allocate_va_range(&alias->vm,
+							  vma->node.start,
+							  vma->size);
+			if (ret)
+				return ret;
+
+			set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
+		}
+
+		GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT,
+				     __i915_vma_flags(vma)));
+		alias->vm.insert_entries(&alias->vm, vma,
+					 cache_level, pte_flags);
+	}
+
+	if (flags & I915_VMA_GLOBAL_BIND)
+		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+
+	return 0;
+}
+
+static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
+{
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
+		struct i915_address_space *vm = vma->vm;
+
+		vm->clear_range(vm, vma->node.start, vma->size);
+	}
+
+	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
+		struct i915_address_space *vm =
+			&i915_vm_to_ggtt(vma->vm)->alias->vm;
+
+		vm->clear_range(vm, vma->node.start, vma->size);
+	}
+}
+
+static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
+{
+	struct i915_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = i915_ppgtt_create(ggtt->vm.gt);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
+
+	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
+		err = -ENODEV;
+		goto err_ppgtt;
+	}
+
+	/*
+	 * Note we only pre-allocate as far as the end of the global
+	 * GTT. On 48b / 4-level page-tables, the difference is very,
+	 * very significant! We have to preallocate as GVT/vgpu does
+	 * not like the page directory disappearing.
+	 */
+	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
+	if (err)
+		goto err_ppgtt;
+
+	ggtt->alias = ppgtt;
+	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
+
+	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
+	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
+
+	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
+	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
+
+	return 0;
+
+err_ppgtt:
+	i915_vm_put(&ppgtt->vm);
+	return err;
+}
+
+static void fini_aliasing_ppgtt(struct i915_ggtt *ggtt)
+{
+	struct i915_ppgtt *ppgtt;
+
+	ppgtt = fetch_and_zero(&ggtt->alias);
+	if (!ppgtt)
+		return;
+
+	i915_vm_put(&ppgtt->vm);
+
+	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
+}
+
+int i915_init_ggtt(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = init_ggtt(&i915->ggtt);
+	if (ret)
+		return ret;
+
+	if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) {
+		ret = init_aliasing_ppgtt(&i915->ggtt);
+		if (ret)
+			cleanup_init_ggtt(&i915->ggtt);
+	}
+
+	return 0;
+}
+
+static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
+{
+	struct i915_vma *vma, *vn;
+
+	atomic_set(&ggtt->vm.open, 0);
+
+	rcu_barrier(); /* flush the RCU'ed__i915_vm_release */
+	flush_workqueue(ggtt->vm.i915->wq);
+
+	mutex_lock(&ggtt->vm.mutex);
+
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link)
+		WARN_ON(__i915_vma_unbind(vma));
+
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_mm_remove_node(&ggtt->error_capture);
+	mutex_destroy(&ggtt->error_mutex);
+
+	ggtt_release_guc_top(ggtt);
+	intel_vgt_deballoon(ggtt);
+
+	ggtt->vm.cleanup(&ggtt->vm);
+
+	mutex_unlock(&ggtt->vm.mutex);
+	i915_address_space_fini(&ggtt->vm);
+
+	arch_phys_wc_del(ggtt->mtrr);
+
+	if (ggtt->iomap.size)
+		io_mapping_fini(&ggtt->iomap);
+}
+
+/**
+ * i915_ggtt_driver_release - Clean up GGTT hardware initialization
+ * @i915: i915 device
+ */
+void i915_ggtt_driver_release(struct drm_i915_private *i915)
+{
+	struct pagevec *pvec;
+
+	fini_aliasing_ppgtt(&i915->ggtt);
+
+	ggtt_cleanup_hw(&i915->ggtt);
+
+	pvec = &i915->mm.wc_stash.pvec;
+	if (pvec->nr) {
+		set_pages_array_wb(pvec->pages, pvec->nr);
+		__pagevec_release(pvec);
+	}
+}
+
+static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
+{
+	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
+	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
+	return snb_gmch_ctl << 20;
+}
+
+static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
+{
+	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
+	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
+	if (bdw_gmch_ctl)
+		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
+
+#ifdef CONFIG_X86_32
+	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
+	if (bdw_gmch_ctl > 4)
+		bdw_gmch_ctl = 4;
+#endif
+
+	return bdw_gmch_ctl << 20;
+}
+
+static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
+{
+	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
+	gmch_ctrl &= SNB_GMCH_GGMS_MASK;
+
+	if (gmch_ctrl)
+		return 1 << (20 + gmch_ctrl);
+
+	return 0;
+}
+
+static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct pci_dev *pdev = i915->drm.pdev;
+	phys_addr_t phys_addr;
+	int ret;
+
+	/* For Modern GENs the PTEs and register space are split in the BAR */
+	phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2;
+
+	/*
+	 * On BXT+/CNL+ writes larger than 64 bit to the GTT pagetable range
+	 * will be dropped. For WC mappings in general we have 64 byte burst
+	 * writes when the WC buffer is flushed, so we can't use it, but have to
+	 * resort to an uncached mapping. The WC issue is easily caught by the
+	 * readback check when writing GTT PTE entries.
+	 */
+	if (IS_GEN9_LP(i915) || INTEL_GEN(i915) >= 10)
+		ggtt->gsm = ioremap(phys_addr, size);
+	else
+		ggtt->gsm = ioremap_wc(phys_addr, size);
+	if (!ggtt->gsm) {
+		DRM_ERROR("Failed to map the ggtt page table\n");
+		return -ENOMEM;
+	}
+
+	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
+	if (ret) {
+		DRM_ERROR("Scratch setup failed\n");
+		/* iounmap will also get called at remove, but meh */
+		iounmap(ggtt->gsm);
+		return ret;
+	}
+
+	ggtt->vm.scratch[0].encode =
+		ggtt->vm.pte_encode(px_dma(&ggtt->vm.scratch[0]),
+				    I915_CACHE_NONE, 0);
+
+	return 0;
+}
+
+int ggtt_set_pages(struct i915_vma *vma)
+{
+	int ret;
+
+	GEM_BUG_ON(vma->pages);
+
+	ret = i915_get_ggtt_vma_pages(vma);
+	if (ret)
+		return ret;
+
+	vma->page_sizes = vma->obj->mm.page_sizes;
+
+	return 0;
+}
+
+static void gen6_gmch_remove(struct i915_address_space *vm)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+
+	iounmap(ggtt->gsm);
+	cleanup_scratch_page(vm);
+}
+
+static struct resource pci_resource(struct pci_dev *pdev, int bar)
+{
+	return (struct resource)DEFINE_RES_MEM(pci_resource_start(pdev, bar),
+					       pci_resource_len(pdev, bar));
+}
+
+static int gen8_gmch_probe(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct pci_dev *pdev = i915->drm.pdev;
+	unsigned int size;
+	u16 snb_gmch_ctl;
+	int err;
+
+	/* TODO: We're not aware of mappable constraints on gen8 yet */
+	if (!IS_DGFX(i915)) {
+		ggtt->gmadr = pci_resource(pdev, 2);
+		ggtt->mappable_end = resource_size(&ggtt->gmadr);
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
+	if (!err)
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39));
+	if (err)
+		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
+
+	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+	if (IS_CHERRYVIEW(i915))
+		size = chv_get_total_gtt_size(snb_gmch_ctl);
+	else
+		size = gen8_get_total_gtt_size(snb_gmch_ctl);
+
+	ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
+	ggtt->vm.cleanup = gen6_gmch_remove;
+	ggtt->vm.insert_page = gen8_ggtt_insert_page;
+	ggtt->vm.clear_range = nop_clear_range;
+	if (intel_scanout_needs_vtd_wa(i915))
+		ggtt->vm.clear_range = gen8_ggtt_clear_range;
+
+	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
+
+	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+	if (intel_ggtt_update_needs_vtd_wa(i915) ||
+	    IS_CHERRYVIEW(i915) /* fails with concurrent use/update */) {
+		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->vm.clear_range != nop_clear_range)
+			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+	}
+
+	ggtt->invalidate = gen8_ggtt_invalidate;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	ggtt->vm.pte_encode = gen8_pte_encode;
+
+	setup_private_pat(ggtt->vm.gt->uncore);
+
+	return ggtt_probe_common(ggtt, size);
+}
+
+static u64 snb_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	switch (level) {
+	case I915_CACHE_L3_LLC:
+	case I915_CACHE_LLC:
+		pte |= GEN6_PTE_CACHE_LLC;
+		break;
+	case I915_CACHE_NONE:
+		pte |= GEN6_PTE_UNCACHED;
+		break;
+	default:
+		MISSING_CASE(level);
+	}
+
+	return pte;
+}
+
+static u64 ivb_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	switch (level) {
+	case I915_CACHE_L3_LLC:
+		pte |= GEN7_PTE_CACHE_L3_LLC;
+		break;
+	case I915_CACHE_LLC:
+		pte |= GEN6_PTE_CACHE_LLC;
+		break;
+	case I915_CACHE_NONE:
+		pte |= GEN6_PTE_UNCACHED;
+		break;
+	default:
+		MISSING_CASE(level);
+	}
+
+	return pte;
+}
+
+static u64 byt_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = GEN6_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	if (!(flags & PTE_READ_ONLY))
+		pte |= BYT_PTE_WRITEABLE;
+
+	if (level != I915_CACHE_NONE)
+		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
+
+	return pte;
+}
+
+static u64 hsw_pte_encode(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags)
+{
+	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	if (level != I915_CACHE_NONE)
+		pte |= HSW_WB_LLC_AGE3;
+
+	return pte;
+}
+
+static u64 iris_pte_encode(dma_addr_t addr,
+			   enum i915_cache_level level,
+			   u32 flags)
+{
+	gen6_pte_t pte = HSW_PTE_ADDR_ENCODE(addr) | GEN6_PTE_VALID;
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		break;
+	case I915_CACHE_WT:
+		pte |= HSW_WT_ELLC_LLC_AGE3;
+		break;
+	default:
+		pte |= HSW_WB_ELLC_LLC_AGE3;
+		break;
+	}
+
+	return pte;
+}
+
+static int gen6_gmch_probe(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct pci_dev *pdev = i915->drm.pdev;
+	unsigned int size;
+	u16 snb_gmch_ctl;
+	int err;
+
+	ggtt->gmadr = pci_resource(pdev, 2);
+	ggtt->mappable_end = resource_size(&ggtt->gmadr);
+
+	/*
+	 * 64/512MB is the current min/max we actually know of, but this is
+	 * just a coarse sanity check.
+	 */
+	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
+		DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end);
+		return -ENXIO;
+	}
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(40));
+	if (!err)
+		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40));
+	if (err)
+		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
+	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
+
+	size = gen6_get_total_gtt_size(snb_gmch_ctl);
+	ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
+
+	ggtt->vm.clear_range = nop_clear_range;
+	if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
+		ggtt->vm.clear_range = gen6_ggtt_clear_range;
+	ggtt->vm.insert_page = gen6_ggtt_insert_page;
+	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
+	ggtt->vm.cleanup = gen6_gmch_remove;
+
+	ggtt->invalidate = gen6_ggtt_invalidate;
+
+	if (HAS_EDRAM(i915))
+		ggtt->vm.pte_encode = iris_pte_encode;
+	else if (IS_HASWELL(i915))
+		ggtt->vm.pte_encode = hsw_pte_encode;
+	else if (IS_VALLEYVIEW(i915))
+		ggtt->vm.pte_encode = byt_pte_encode;
+	else if (INTEL_GEN(i915) >= 7)
+		ggtt->vm.pte_encode = ivb_pte_encode;
+	else
+		ggtt->vm.pte_encode = snb_pte_encode;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	return ggtt_probe_common(ggtt, size);
+}
+
+static void i915_gmch_remove(struct i915_address_space *vm)
+{
+	intel_gmch_remove();
+}
+
+static int i915_gmch_probe(struct i915_ggtt *ggtt)
+{
+	struct drm_i915_private *i915 = ggtt->vm.i915;
+	phys_addr_t gmadr_base;
+	int ret;
+
+	ret = intel_gmch_probe(i915->bridge_dev, i915->drm.pdev, NULL);
+	if (!ret) {
+		DRM_ERROR("failed to set up gmch\n");
+		return -EIO;
+	}
+
+	intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
+
+	ggtt->gmadr =
+		(struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end);
+
+	ggtt->do_idle_maps = needs_idle_maps(i915);
+	ggtt->vm.insert_page = i915_ggtt_insert_page;
+	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
+	ggtt->vm.clear_range = i915_ggtt_clear_range;
+	ggtt->vm.cleanup = i915_gmch_remove;
+
+	ggtt->invalidate = gmch_ggtt_invalidate;
+
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
+	if (unlikely(ggtt->do_idle_maps))
+		dev_notice(i915->drm.dev,
+			   "Applying Ironlake quirks for intel_iommu\n");
+
+	return 0;
+}
+
+static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	int ret;
+
+	ggtt->vm.gt = gt;
+	ggtt->vm.i915 = i915;
+	ggtt->vm.dma = &i915->drm.pdev->dev;
+
+	if (INTEL_GEN(i915) <= 5)
+		ret = i915_gmch_probe(ggtt);
+	else if (INTEL_GEN(i915) < 8)
+		ret = gen6_gmch_probe(ggtt);
+	else
+		ret = gen8_gmch_probe(ggtt);
+	if (ret)
+		return ret;
+
+	if ((ggtt->vm.total - 1) >> 32) {
+		DRM_ERROR("We never expected a Global GTT with more than 32bits"
+			  " of address space! Found %lldM!\n",
+			  ggtt->vm.total >> 20);
+		ggtt->vm.total = 1ULL << 32;
+		ggtt->mappable_end =
+			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
+	}
+
+	if (ggtt->mappable_end > ggtt->vm.total) {
+		DRM_ERROR("mappable aperture extends past end of GGTT,"
+			  " aperture=%pa, total=%llx\n",
+			  &ggtt->mappable_end, ggtt->vm.total);
+		ggtt->mappable_end = ggtt->vm.total;
+	}
+
+	/* GMADR is the PCI mmio aperture into the global GTT. */
+	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
+	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
+	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
+			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
+
+	return 0;
+}
+
+/**
+ * i915_ggtt_probe_hw - Probe GGTT hardware location
+ * @i915: i915 device
+ */
+int i915_ggtt_probe_hw(struct drm_i915_private *i915)
+{
+	int ret;
+
+	ret = ggtt_probe_hw(&i915->ggtt, &i915->gt);
+	if (ret)
+		return ret;
+
+	if (intel_vtd_active())
+		dev_info(i915->drm.dev, "VT-d active for gfx access\n");
+
+	return 0;
+}
+
+int i915_ggtt_enable_hw(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) < 6 && !intel_enable_gtt())
+		return -EIO;
+
+	return 0;
+}
+
+void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
+{
+	GEM_BUG_ON(ggtt->invalidate != gen8_ggtt_invalidate);
+
+	ggtt->invalidate = guc_ggtt_invalidate;
+
+	ggtt->invalidate(ggtt);
+}
+
+void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
+{
+	/* XXX Temporary pardon for error unload */
+	if (ggtt->invalidate == gen8_ggtt_invalidate)
+		return;
+
+	/* We should only be called after i915_ggtt_enable_guc() */
+	GEM_BUG_ON(ggtt->invalidate != guc_ggtt_invalidate);
+
+	ggtt->invalidate = gen8_ggtt_invalidate;
+
+	ggtt->invalidate(ggtt);
+}
+
+static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
+{
+	struct i915_vma *vma;
+	bool flush = false;
+	int open;
+
+	intel_gt_check_and_clear_faults(ggtt->vm.gt);
+
+	mutex_lock(&ggtt->vm.mutex);
+
+	/* First fill our portion of the GTT with scratch pages */
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
+
+	/* Skip rewriting PTE on VMA unbind. */
+	open = atomic_xchg(&ggtt->vm.open, 0);
+
+	/* clflush objects bound into the GGTT and rebind them. */
+	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+			continue;
+
+		clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
+		WARN_ON(i915_vma_bind(vma,
+				      obj ? obj->cache_level : 0,
+				      PIN_GLOBAL, NULL));
+		if (obj) { /* only used during resume => exclusive access */
+			flush |= fetch_and_zero(&obj->write_domain);
+			obj->read_domains |= I915_GEM_DOMAIN_GTT;
+		}
+	}
+
+	atomic_set(&ggtt->vm.open, open);
+	ggtt->invalidate(ggtt);
+
+	mutex_unlock(&ggtt->vm.mutex);
+
+	if (flush)
+		wbinvd_on_all_cpus();
+}
+
+void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915)
+{
+	struct i915_ggtt *ggtt = &i915->ggtt;
+
+	ggtt_restore_mappings(ggtt);
+
+	if (INTEL_GEN(i915) >= 8)
+		setup_private_pat(ggtt->vm.gt->uncore);
+}
+
+static struct scatterlist *
+rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset,
+	     unsigned int width, unsigned int height,
+	     unsigned int stride,
+	     struct sg_table *st, struct scatterlist *sg)
+{
+	unsigned int column, row;
+	unsigned int src_idx;
+
+	for (column = 0; column < width; column++) {
+		src_idx = stride * (height - 1) + column + offset;
+		for (row = 0; row < height; row++) {
+			st->nents++;
+			/*
+			 * We don't need the pages, but need to initialize
+			 * the entries so the sg list can be happily traversed.
+			 * The only thing we need are DMA addresses.
+			 */
+			sg_set_page(sg, NULL, I915_GTT_PAGE_SIZE, 0);
+			sg_dma_address(sg) =
+				i915_gem_object_get_dma_address(obj, src_idx);
+			sg_dma_len(sg) = I915_GTT_PAGE_SIZE;
+			sg = sg_next(sg);
+			src_idx -= stride;
+		}
+	}
+
+	return sg;
+}
+
+static noinline struct sg_table *
+intel_rotate_pages(struct intel_rotation_info *rot_info,
+		   struct drm_i915_gem_object *obj)
+{
+	unsigned int size = intel_rotation_info_size(rot_info);
+	struct sg_table *st;
+	struct scatterlist *sg;
+	int ret = -ENOMEM;
+	int i;
+
+	/* Allocate target SG list. */
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, size, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	st->nents = 0;
+	sg = st->sgl;
+
+	for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) {
+		sg = rotate_pages(obj, rot_info->plane[i].offset,
+				  rot_info->plane[i].width, rot_info->plane[i].height,
+				  rot_info->plane[i].stride, st, sg);
+	}
+
+	return st;
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+
+	DRM_DEBUG_DRIVER("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
+			 obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
+
+	return ERR_PTR(ret);
+}
+
+static struct scatterlist *
+remap_pages(struct drm_i915_gem_object *obj, unsigned int offset,
+	    unsigned int width, unsigned int height,
+	    unsigned int stride,
+	    struct sg_table *st, struct scatterlist *sg)
+{
+	unsigned int row;
+
+	for (row = 0; row < height; row++) {
+		unsigned int left = width * I915_GTT_PAGE_SIZE;
+
+		while (left) {
+			dma_addr_t addr;
+			unsigned int length;
+
+			/*
+			 * We don't need the pages, but need to initialize
+			 * the entries so the sg list can be happily traversed.
+			 * The only thing we need are DMA addresses.
+			 */
+
+			addr = i915_gem_object_get_dma_address_len(obj, offset, &length);
+
+			length = min(left, length);
+
+			st->nents++;
+
+			sg_set_page(sg, NULL, length, 0);
+			sg_dma_address(sg) = addr;
+			sg_dma_len(sg) = length;
+			sg = sg_next(sg);
+
+			offset += length / I915_GTT_PAGE_SIZE;
+			left -= length;
+		}
+
+		offset += stride - width;
+	}
+
+	return sg;
+}
+
+static noinline struct sg_table *
+intel_remap_pages(struct intel_remapped_info *rem_info,
+		  struct drm_i915_gem_object *obj)
+{
+	unsigned int size = intel_remapped_info_size(rem_info);
+	struct sg_table *st;
+	struct scatterlist *sg;
+	int ret = -ENOMEM;
+	int i;
+
+	/* Allocate target SG list. */
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, size, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	st->nents = 0;
+	sg = st->sgl;
+
+	for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) {
+		sg = remap_pages(obj, rem_info->plane[i].offset,
+				 rem_info->plane[i].width, rem_info->plane[i].height,
+				 rem_info->plane[i].stride, st, sg);
+	}
+
+	i915_sg_trim(st);
+
+	return st;
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+
+	DRM_DEBUG_DRIVER("Failed to create remapped mapping for object size %zu! (%ux%u tiles, %u pages)\n",
+			 obj->base.size, rem_info->plane[0].width, rem_info->plane[0].height, size);
+
+	return ERR_PTR(ret);
+}
+
+static noinline struct sg_table *
+intel_partial_pages(const struct i915_ggtt_view *view,
+		    struct drm_i915_gem_object *obj)
+{
+	struct sg_table *st;
+	struct scatterlist *sg, *iter;
+	unsigned int count = view->partial.size;
+	unsigned int offset;
+	int ret = -ENOMEM;
+
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto err_st_alloc;
+
+	ret = sg_alloc_table(st, count, GFP_KERNEL);
+	if (ret)
+		goto err_sg_alloc;
+
+	iter = i915_gem_object_get_sg(obj, view->partial.offset, &offset);
+	GEM_BUG_ON(!iter);
+
+	sg = st->sgl;
+	st->nents = 0;
+	do {
+		unsigned int len;
+
+		len = min(iter->length - (offset << PAGE_SHIFT),
+			  count << PAGE_SHIFT);
+		sg_set_page(sg, NULL, len, 0);
+		sg_dma_address(sg) =
+			sg_dma_address(iter) + (offset << PAGE_SHIFT);
+		sg_dma_len(sg) = len;
+
+		st->nents++;
+		count -= len >> PAGE_SHIFT;
+		if (count == 0) {
+			sg_mark_end(sg);
+			i915_sg_trim(st); /* Drop any unused tail entries. */
+
+			return st;
+		}
+
+		sg = __sg_next(sg);
+		iter = __sg_next(iter);
+		offset = 0;
+	} while (1);
+
+err_sg_alloc:
+	kfree(st);
+err_st_alloc:
+	return ERR_PTR(ret);
+}
+
+static int
+i915_get_ggtt_vma_pages(struct i915_vma *vma)
+{
+	int ret;
+
+	/*
+	 * The vma->pages are only valid within the lifespan of the borrowed
+	 * obj->mm.pages. When the obj->mm.pages sg_table is regenerated, so
+	 * must be the vma->pages. A simple rule is that vma->pages must only
+	 * be accessed when the obj->mm.pages are pinned.
+	 */
+	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj));
+
+	switch (vma->ggtt_view.type) {
+	default:
+		GEM_BUG_ON(vma->ggtt_view.type);
+		/* fall through */
+	case I915_GGTT_VIEW_NORMAL:
+		vma->pages = vma->obj->mm.pages;
+		return 0;
+
+	case I915_GGTT_VIEW_ROTATED:
+		vma->pages =
+			intel_rotate_pages(&vma->ggtt_view.rotated, vma->obj);
+		break;
+
+	case I915_GGTT_VIEW_REMAPPED:
+		vma->pages =
+			intel_remap_pages(&vma->ggtt_view.remapped, vma->obj);
+		break;
+
+	case I915_GGTT_VIEW_PARTIAL:
+		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
+		break;
+	}
+
+	ret = 0;
+	if (IS_ERR(vma->pages)) {
+		ret = PTR_ERR(vma->pages);
+		vma->pages = NULL;
+		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
+			  vma->ggtt_view.type, ret);
+	}
+	return ret;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 4294f146f13c..51b8718513bc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -7,6 +7,8 @@
 #ifndef _INTEL_GPU_COMMANDS_H_
 #define _INTEL_GPU_COMMANDS_H_
 
+#include <linux/bitops.h>
+
 /*
  * Target address alignments required for GPU access e.g.
  * MI_STORE_DWORD_IMM.
@@ -319,4 +321,31 @@
 #define COLOR_BLT     ((0x2<<29)|(0x40<<22))
 #define SRC_COPY_BLT  ((0x2<<29)|(0x43<<22))
 
+/*
+ * Used to convert any address to canonical form.
+ * Starting from gen8, some commands (e.g. STATE_BASE_ADDRESS,
+ * MI_LOAD_REGISTER_MEM and others, see Broadwell PRM Vol2a) require the
+ * addresses to be in a canonical form:
+ * "GraphicsAddress[63:48] are ignored by the HW and assumed to be in correct
+ * canonical form [63:48] == [47]."
+ */
+#define GEN8_HIGH_ADDRESS_BIT 47
+static inline u64 gen8_canonical_addr(u64 address)
+{
+	return sign_extend64(address, GEN8_HIGH_ADDRESS_BIT);
+}
+
+static inline u64 gen8_noncanonical_addr(u64 address)
+{
+	return address & GENMASK_ULL(GEN8_HIGH_ADDRESS_BIT, 0);
+}
+
+static inline u32 *__gen6_emit_bb_start(u32 *cs, u32 addr, unsigned int flags)
+{
+	*cs++ = MI_BATCH_BUFFER_START | flags;
+	*cs++ = addr;
+
+	return cs;
+}
+
 #endif /* _INTEL_GPU_COMMANDS_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 4c26daf7ee46..da2b6e2ae692 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -3,12 +3,15 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include "debugfs_gt.h"
 #include "i915_drv.h"
+#include "intel_context.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_mocs.h"
 #include "intel_rc6.h"
+#include "intel_renderstate.h"
 #include "intel_rps.h"
 #include "intel_uncore.h"
 #include "intel_pm.h"
@@ -25,6 +28,7 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
+	intel_gt_init_timelines(gt);
 	intel_gt_pm_init_early(gt);
 
 	intel_rps_init_early(&gt->rps);
@@ -34,8 +38,6 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt)
 {
 	gt->ggtt = ggtt;
-
-	intel_gt_sanitize(gt, false);
 }
 
 static void init_unused_ring(struct intel_gt *gt, u32 base)
@@ -73,11 +75,6 @@ int intel_gt_init_hw(struct intel_gt *gt)
 	struct intel_uncore *uncore = gt->uncore;
 	int ret;
 
-	BUG_ON(!i915->kernel_context);
-	ret = intel_gt_terminally_wedged(gt);
-	if (ret)
-		return ret;
-
 	gt->last_init_time = ktime_get();
 
 	/* Double layer security blanket, see i915_gem_init() */
@@ -303,7 +300,7 @@ void intel_gt_flush_ggtt_writes(struct intel_gt *gt)
 
 	intel_gt_chipset_flush(gt);
 
-	with_intel_runtime_pm(uncore->rpm, wakeref) {
+	with_intel_runtime_pm_if_in_use(uncore->rpm, wakeref) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&uncore->lock, flags);
@@ -323,6 +320,8 @@ void intel_gt_chipset_flush(struct intel_gt *gt)
 void intel_gt_driver_register(struct intel_gt *gt)
 {
 	intel_rps_driver_register(&gt->rps);
+
+	debugfs_gt_register(gt);
 }
 
 static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
@@ -364,22 +363,272 @@ static void intel_gt_fini_scratch(struct intel_gt *gt)
 	i915_vma_unpin_and_release(&gt->scratch, 0);
 }
 
+static struct i915_address_space *kernel_vm(struct intel_gt *gt)
+{
+	if (INTEL_PPGTT(gt->i915) > INTEL_PPGTT_ALIASING)
+		return &i915_ppgtt_create(gt)->vm;
+	else
+		return i915_vm_get(&gt->ggtt->vm);
+}
+
+static int __intel_context_flush_retire(struct intel_context *ce)
+{
+	struct intel_timeline *tl;
+
+	tl = intel_context_timeline_lock(ce);
+	if (IS_ERR(tl))
+		return PTR_ERR(tl);
+
+	intel_context_timeline_unlock(tl);
+	return 0;
+}
+
+static int __engines_record_defaults(struct intel_gt *gt)
+{
+	struct i915_request *requests[I915_NUM_ENGINES] = {};
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * As we reset the gpu during very early sanitisation, the current
+	 * register state on the GPU should reflect its defaults values.
+	 * We load a context onto the hw (with restore-inhibit), then switch
+	 * over to a second context to save that default register state. We
+	 * can then prime every new context with that state so they all start
+	 * from the same default HW values.
+	 */
+
+	for_each_engine(engine, gt, id) {
+		struct intel_renderstate so;
+		struct intel_context *ce;
+		struct i915_request *rq;
+
+		/* We must be able to switch to something! */
+		GEM_BUG_ON(!engine->kernel_context);
+
+		err = intel_renderstate_init(&so, engine);
+		if (err)
+			goto out;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			goto out;
+		}
+
+		rq = intel_context_create_request(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			intel_context_put(ce);
+			goto out;
+		}
+
+		err = intel_engine_emit_ctx_wa(rq);
+		if (err)
+			goto err_rq;
+
+		err = intel_renderstate_emit(&so, rq);
+		if (err)
+			goto err_rq;
+
+err_rq:
+		requests[id] = i915_request_get(rq);
+		i915_request_add(rq);
+		intel_renderstate_fini(&so);
+		if (err)
+			goto out;
+	}
+
+	/* Flush the default context image to memory, and enable powersaving. */
+	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+		err = -EIO;
+		goto out;
+	}
+
+	for (id = 0; id < ARRAY_SIZE(requests); id++) {
+		struct i915_request *rq;
+		struct i915_vma *state;
+		void *vaddr;
+
+		rq = requests[id];
+		if (!rq)
+			continue;
+
+		GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT, &rq->context->flags));
+		state = rq->context->state;
+		if (!state)
+			continue;
+
+		/* Serialise with retirement on another CPU */
+		GEM_BUG_ON(!i915_request_completed(rq));
+		err = __intel_context_flush_retire(rq->context);
+		if (err)
+			goto out;
+
+		/* We want to be able to unbind the state from the GGTT */
+		GEM_BUG_ON(intel_context_is_pinned(rq->context));
+
+		/*
+		 * As we will hold a reference to the logical state, it will
+		 * not be torn down with the context, and importantly the
+		 * object will hold onto its vma (making it possible for a
+		 * stray GTT write to corrupt our defaults). Unmap the vma
+		 * from the GTT to prevent such accidents and reclaim the
+		 * space.
+		 */
+		err = i915_vma_unbind(state);
+		if (err)
+			goto out;
+
+		i915_gem_object_lock(state->obj);
+		err = i915_gem_object_set_to_cpu_domain(state->obj, false);
+		i915_gem_object_unlock(state->obj);
+		if (err)
+			goto out;
+
+		i915_gem_object_set_cache_coherency(state->obj, I915_CACHE_LLC);
+
+		/* Check we can acquire the image of the context state */
+		vaddr = i915_gem_object_pin_map(state->obj, I915_MAP_FORCE_WB);
+		if (IS_ERR(vaddr)) {
+			err = PTR_ERR(vaddr);
+			goto out;
+		}
+
+		rq->engine->default_state = i915_gem_object_get(state->obj);
+		i915_gem_object_unpin_map(state->obj);
+	}
+
+out:
+	/*
+	 * If we have to abandon now, we expect the engines to be idle
+	 * and ready to be torn-down. The quickest way we can accomplish
+	 * this is by declaring ourselves wedged.
+	 */
+	if (err)
+		intel_gt_set_wedged(gt);
+
+	for (id = 0; id < ARRAY_SIZE(requests); id++) {
+		struct intel_context *ce;
+		struct i915_request *rq;
+
+		rq = requests[id];
+		if (!rq)
+			continue;
+
+		ce = rq->context;
+		i915_request_put(rq);
+		intel_context_put(ce);
+	}
+	return err;
+}
+
+static int __engines_verify_workarounds(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		return 0;
+
+	for_each_engine(engine, gt, id) {
+		if (intel_engine_verify_workarounds(engine, "load"))
+			err = -EIO;
+	}
+
+	return err;
+}
+
+static void __intel_gt_disable(struct intel_gt *gt)
+{
+	intel_gt_set_wedged_on_init(gt);
+
+	intel_gt_suspend_prepare(gt);
+	intel_gt_suspend_late(gt);
+
+	GEM_BUG_ON(intel_gt_pm_is_awake(gt));
+}
+
 int intel_gt_init(struct intel_gt *gt)
 {
 	int err;
 
-	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
+	err = i915_inject_probe_error(gt->i915, -ENODEV);
 	if (err)
 		return err;
 
+	/*
+	 * This is just a security blanket to placate dragons.
+	 * On some systems, we very sporadically observe that the first TLBs
+	 * used by the CS may be stale, despite us poking the TLB reset. If
+	 * we hold the forcewake during initialisation these problems
+	 * just magically go away.
+	 */
+	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
+
+	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
+	if (err)
+		goto out_fw;
+
 	intel_gt_pm_init(gt);
 
-	return 0;
+	gt->vm = kernel_vm(gt);
+	if (!gt->vm) {
+		err = -ENOMEM;
+		goto err_pm;
+	}
+
+	err = intel_engines_init(gt);
+	if (err)
+		goto err_engines;
+
+	intel_uc_init(&gt->uc);
+
+	err = intel_gt_resume(gt);
+	if (err)
+		goto err_uc_init;
+
+	err = __engines_record_defaults(gt);
+	if (err)
+		goto err_gt;
+
+	err = __engines_verify_workarounds(gt);
+	if (err)
+		goto err_gt;
+
+	err = i915_inject_probe_error(gt->i915, -EIO);
+	if (err)
+		goto err_gt;
+
+	goto out_fw;
+err_gt:
+	__intel_gt_disable(gt);
+	intel_uc_fini_hw(&gt->uc);
+err_uc_init:
+	intel_uc_fini(&gt->uc);
+err_engines:
+	intel_engines_release(gt);
+	i915_vm_put(fetch_and_zero(&gt->vm));
+err_pm:
+	intel_gt_pm_fini(gt);
+	intel_gt_fini_scratch(gt);
+out_fw:
+	if (err)
+		intel_gt_set_wedged_on_init(gt);
+	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
+	return err;
 }
 
 void intel_gt_driver_remove(struct intel_gt *gt)
 {
-	GEM_BUG_ON(gt->awake);
+	__intel_gt_disable(gt);
+
+	intel_uc_fini_hw(&gt->uc);
+	intel_uc_fini(&gt->uc);
+
+	intel_engines_release(gt);
 }
 
 void intel_gt_driver_unregister(struct intel_gt *gt)
@@ -389,6 +638,12 @@ void intel_gt_driver_unregister(struct intel_gt *gt)
 
 void intel_gt_driver_release(struct intel_gt *gt)
 {
+	struct i915_address_space *vm;
+
+	vm = fetch_and_zero(&gt->vm);
+	if (vm) /* FIXME being called twice on error paths :( */
+		i915_vm_put(vm);
+
 	intel_gt_pm_fini(gt);
 	intel_gt_fini_scratch(gt);
 }
@@ -396,5 +651,8 @@ void intel_gt_driver_release(struct intel_gt *gt)
 void intel_gt_driver_late_release(struct intel_gt *gt)
 {
 	intel_uc_driver_late_release(&gt->uc);
+	intel_gt_fini_requests(gt);
 	intel_gt_fini_reset(gt);
+	intel_gt_fini_timelines(gt);
+	intel_engines_free(gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 5436f8c30708..1dac441cb8f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -12,6 +12,12 @@
 
 struct drm_i915_private;
 
+#define GT_TRACE(gt, fmt, ...) do {					\
+	const struct intel_gt *gt__ __maybe_unused = (gt);		\
+	GEM_TRACE("%s  " fmt, dev_name(gt__->i915->drm.dev),		\
+		  ##__VA_ARGS__);					\
+} while (0)
+
 static inline struct intel_gt *uc_to_gt(struct intel_uc *uc)
 {
 	return container_of(uc, struct intel_gt, uc);
@@ -52,9 +58,14 @@ static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt,
 	return i915_ggtt_offset(gt->scratch) + field;
 }
 
-static inline bool intel_gt_is_wedged(struct intel_gt *gt)
+static inline bool intel_gt_is_wedged(const struct intel_gt *gt)
 {
 	return __intel_reset_failed(&gt->reset);
 }
 
+static inline bool intel_gt_has_init_error(const struct intel_gt *gt)
+{
+	return test_bit(I915_WEDGED_ON_INIT, &gt->reset.flags);
+}
+
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 973ee7eded64..f796bdf1ed30 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -28,7 +28,7 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 		tasklet = true;
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
-		intel_engine_breadcrumbs_irq(engine);
+		intel_engine_signal_breadcrumbs(engine);
 		tasklet |= intel_engine_needs_breadcrumb_tasklet(engine);
 	}
 
@@ -245,9 +245,9 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 void gen5_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[RENDER_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
 	if (gt_iir & ILK_BSD_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
 }
 
 static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
@@ -271,11 +271,11 @@ static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir)
 void gen6_gt_irq_handler(struct intel_gt *gt, u32 gt_iir)
 {
 	if (gt_iir & GT_RENDER_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[RENDER_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[RENDER_CLASS][0]);
 	if (gt_iir & GT_BSD_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[VIDEO_DECODE_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[VIDEO_DECODE_CLASS][0]);
 	if (gt_iir & GT_BLT_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine_class[COPY_ENGINE_CLASS][0]);
+		intel_engine_signal_breadcrumbs(gt->engine_class[COPY_ENGINE_CLASS][0]);
 
 	if (gt_iir & (GT_BLT_CS_ERROR_INTERRUPT |
 		      GT_BSD_CS_ERROR_INTERRUPT |
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 7e64b7d7d330..d1c2f034296a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -43,7 +43,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	struct intel_gt *gt = container_of(wf, typeof(*gt), wakeref);
 	struct drm_i915_private *i915 = gt->i915;
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 
 	i915_globals_unpark();
 
@@ -61,9 +61,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 	GEM_BUG_ON(!gt->awake);
 
-	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
-		intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
-
+	intel_rc6_unpark(&gt->rc6);
 	intel_rps_unpark(&gt->rps);
 	i915_pmu_gt_unparked(i915);
 
@@ -78,22 +76,18 @@ static int __gt_park(struct intel_wakeref *wf)
 	intel_wakeref_t wakeref = fetch_and_zero(&gt->awake);
 	struct drm_i915_private *i915 = gt->i915;
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 
 	intel_gt_park_requests(gt);
 
 	i915_vma_parked(gt);
 	i915_pmu_gt_parked(i915);
 	intel_rps_park(&gt->rps);
+	intel_rc6_park(&gt->rc6);
 
 	/* Everything switched off, flush any residual interrupt just in case */
 	intel_synchronize_irq(i915);
 
-	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
-		intel_rc6_ctx_wa_check(&i915->gt.rc6);
-		intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
-	}
-
 	/* Defer dropping the display power well for 100ms, it's slow! */
 	GEM_BUG_ON(!wakeref);
 	intel_display_power_put_async(i915, POWER_DOMAIN_GT_IRQ, wakeref);
@@ -132,23 +126,13 @@ static bool reset_engines(struct intel_gt *gt)
 	return __intel_gt_reset(gt, ALL_ENGINES) == 0;
 }
 
-/**
- * intel_gt_sanitize: called after the GPU has lost power
- * @gt: the i915 GT container
- * @force: ignore a failed reset and sanitize engine state anyway
- *
- * Anytime we reset the GPU, either with an explicit GPU reset or through a
- * PCI power cycle, the GPU loses state and we must reset our state tracking
- * to match. Note that calling intel_gt_sanitize() if the GPU has not
- * been reset results in much confusion!
- */
-void intel_gt_sanitize(struct intel_gt *gt, bool force)
+static void gt_sanitize(struct intel_gt *gt, bool force)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	intel_wakeref_t wakeref;
 
-	GEM_TRACE("force:%s\n", yesno(force));
+	GT_TRACE(gt, "force:%s", yesno(force));
 
 	/* Use a raw wakeref to avoid calling intel_display_power_get early */
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
@@ -193,9 +177,13 @@ int intel_gt_resume(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	int err = 0;
+	int err;
 
-	GEM_TRACE("\n");
+	err = intel_gt_has_init_error(gt);
+	if (err)
+		return err;
+
+	GT_TRACE(gt, "\n");
 
 	/*
 	 * After resume, we may need to poke into the pinned kernel
@@ -207,21 +195,26 @@ int intel_gt_resume(struct intel_gt *gt)
 
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
+	gt_sanitize(gt, true);
+	if (intel_gt_is_wedged(gt)) {
+		err = -EIO;
+		goto out_fw;
+	}
+
+	/* Only when the HW is re-initialised, can we replay the requests */
+	err = intel_gt_init_hw(gt);
+	if (err) {
+		dev_err(gt->i915->drm.dev,
+			"Failed to initialize GPU, declaring it wedged!\n");
+		goto err_wedged;
+	}
 
 	intel_rps_enable(&gt->rps);
 	intel_llc_enable(&gt->llc);
 
 	for_each_engine(engine, gt, id) {
-		struct intel_context *ce;
-
 		intel_engine_pm_get(engine);
 
-		ce = engine->kernel_context;
-		if (ce) {
-			GEM_BUG_ON(!intel_context_is_pinned(ce));
-			ce->ops->reset(ce);
-		}
-
 		engine->serial++; /* kernel context lost */
 		err = engine->resume(engine);
 
@@ -230,7 +223,7 @@ int intel_gt_resume(struct intel_gt *gt)
 			dev_err(gt->i915->drm.dev,
 				"Failed to restart %s (%d)\n",
 				engine->name, err);
-			break;
+			goto err_wedged;
 		}
 	}
 
@@ -240,10 +233,14 @@ int intel_gt_resume(struct intel_gt *gt)
 
 	user_forcewake(gt, false);
 
+out_fw:
 	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 	intel_gt_pm_put(gt);
-
 	return err;
+
+err_wedged:
+	intel_gt_set_wedged(gt);
+	goto out_fw;
 }
 
 static void wait_for_suspend(struct intel_gt *gt)
@@ -257,6 +254,7 @@ static void wait_for_suspend(struct intel_gt *gt)
 		 * the gpu quiet.
 		 */
 		intel_gt_set_wedged(gt);
+		intel_gt_retire_requests(gt);
 	}
 
 	intel_gt_pm_wait_for_idle(gt);
@@ -286,6 +284,11 @@ void intel_gt_suspend_late(struct intel_gt *gt)
 	/* We expect to be idle already; but also want to be independent */
 	wait_for_suspend(gt);
 
+	if (is_mock_gt(gt))
+		return;
+
+	GEM_BUG_ON(gt->awake);
+
 	/*
 	 * On disabling the device, we want to turn off HW access to memory
 	 * that we no longer own.
@@ -305,22 +308,21 @@ void intel_gt_suspend_late(struct intel_gt *gt)
 		intel_llc_disable(&gt->llc);
 	}
 
-	intel_gt_sanitize(gt, false);
+	gt_sanitize(gt, false);
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 }
 
 void intel_gt_runtime_suspend(struct intel_gt *gt)
 {
 	intel_uc_runtime_suspend(&gt->uc);
 
-	GEM_TRACE("\n");
+	GT_TRACE(gt, "\n");
 }
 
 int intel_gt_runtime_resume(struct intel_gt *gt)
 {
-	GEM_TRACE("\n");
-
+	GT_TRACE(gt, "\n");
 	intel_gt_init_swizzling(gt);
 
 	return intel_uc_runtime_resume(&gt->uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index 990efc27a4e4..60f0e2fbe55c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -22,6 +22,11 @@ static inline void intel_gt_pm_get(struct intel_gt *gt)
 	intel_wakeref_get(&gt->wakeref);
 }
 
+static inline void __intel_gt_pm_get(struct intel_gt *gt)
+{
+	__intel_wakeref_get(&gt->wakeref);
+}
+
 static inline bool intel_gt_pm_get_if_awake(struct intel_gt *gt)
 {
 	return intel_wakeref_get_if_active(&gt->wakeref);
@@ -46,8 +51,6 @@ void intel_gt_pm_init_early(struct intel_gt *gt);
 void intel_gt_pm_init(struct intel_gt *gt);
 void intel_gt_pm_fini(struct intel_gt *gt);
 
-void intel_gt_sanitize(struct intel_gt *gt, bool force);
-
 void intel_gt_suspend_prepare(struct intel_gt *gt);
 void intel_gt_suspend_late(struct intel_gt *gt);
 int intel_gt_resume(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 3dc13ecf41bf..7ef1d37970f6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -8,27 +8,40 @@
 
 #include "i915_drv.h" /* for_each_engine() */
 #include "i915_request.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
 #include "intel_timeline.h"
 
-static void retire_requests(struct intel_timeline *tl)
+static bool retire_requests(struct intel_timeline *tl)
 {
 	struct i915_request *rq, *rn;
 
 	list_for_each_entry_safe(rq, rn, &tl->requests, link)
 		if (!i915_request_retire(rq))
-			break;
+			return false;
+
+	/* And check nothing new was submitted */
+	return !i915_active_fence_isset(&tl->last_request);
 }
 
-static void flush_submission(struct intel_gt *gt)
+static bool flush_submission(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	bool active = false;
+
+	if (!intel_gt_pm_is_awake(gt))
+		return false;
 
-	for_each_engine(engine, gt, id)
+	for_each_engine(engine, gt, id) {
 		intel_engine_flush_submission(engine);
+		active |= flush_work(&engine->retire_work);
+		active |= flush_work(&engine->wakeref.work);
+	}
+
+	return active;
 }
 
 static void engine_retire(struct work_struct *work)
@@ -62,19 +75,16 @@ static void engine_retire(struct work_struct *work)
 static bool add_retire(struct intel_engine_cs *engine,
 		       struct intel_timeline *tl)
 {
+#define STUB ((struct intel_timeline *)1)
 	struct intel_timeline *first;
 
 	/*
 	 * We open-code a llist here to include the additional tag [BIT(0)]
 	 * so that we know when the timeline is already on a
 	 * retirement queue: either this engine or another.
-	 *
-	 * However, we rely on that a timeline can only be active on a single
-	 * engine at any one time and that add_retire() is called before the
-	 * engine releases the timeline and transferred to another to retire.
 	 */
 
-	if (READ_ONCE(tl->retire)) /* already queued */
+	if (cmpxchg(&tl->retire, NULL, STUB)) /* already queued */
 		return false;
 
 	intel_timeline_get(tl);
@@ -109,7 +119,6 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl, *tn;
 	unsigned long active_count = 0;
-	unsigned long flags;
 	bool interruptible;
 	LIST_HEAD(free);
 
@@ -118,8 +127,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 		timeout = -timeout, interruptible = false;
 
 	flush_submission(gt); /* kick the ksoftirqd tasklets */
-
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
 		if (!mutex_trylock(&tl->mutex)) {
 			active_count++; /* report busy to caller, try again? */
@@ -129,7 +137,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 		intel_timeline_get(tl);
 		GEM_BUG_ON(!atomic_read(&tl->active_count));
 		atomic_inc(&tl->active_count); /* pin the list element */
-		spin_unlock_irqrestore(&timelines->lock, flags);
+		spin_unlock(&timelines->lock);
 
 		if (timeout > 0) {
 			struct dma_fence *fence;
@@ -143,16 +151,15 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 			}
 		}
 
-		retire_requests(tl);
+		if (!retire_requests(tl) || flush_submission(gt))
+			active_count++;
 
-		spin_lock_irqsave(&timelines->lock, flags);
+		spin_lock(&timelines->lock);
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
-		else
-			active_count += !!rcu_access_pointer(tl->last_request.fence);
 
 		mutex_unlock(&tl->mutex);
 
@@ -162,7 +169,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 			list_add(&tl->link, &free);
 		}
 	}
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 
 	list_for_each_entry_safe(tl, tn, &free, link)
 		__intel_timeline_free(&tl->kref);
@@ -190,9 +197,9 @@ static void retire_work_handler(struct work_struct *work)
 	struct intel_gt *gt =
 		container_of(work, typeof(*gt), requests.retire_work.work);
 
-	intel_gt_retire_requests(gt);
 	schedule_delayed_work(&gt->requests.retire_work,
 			      round_jiffies_up_relative(HZ));
+	intel_gt_retire_requests(gt);
 }
 
 void intel_gt_init_requests(struct intel_gt *gt)
@@ -210,3 +217,9 @@ void intel_gt_unpark_requests(struct intel_gt *gt)
 	schedule_delayed_work(&gt->requests.retire_work,
 			      round_jiffies_up_relative(HZ));
 }
+
+void intel_gt_fini_requests(struct intel_gt *gt)
+{
+	/* Wait until the work is marked as finished before unloading! */
+	cancel_delayed_work_sync(&gt->requests.retire_work);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
index d626fb115386..dbac53baf1cb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -27,5 +27,6 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
 void intel_gt_init_requests(struct intel_gt *gt);
 void intel_gt_park_requests(struct intel_gt *gt);
 void intel_gt_unpark_requests(struct intel_gt *gt);
+void intel_gt_fini_requests(struct intel_gt *gt);
 
 #endif /* INTEL_GT_REQUESTS_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index d4e14dbd172e..96890dd12b5f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -90,6 +90,13 @@ struct intel_gt {
 	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1]
 					    [MAX_ENGINE_INSTANCE + 1];
+
+	/*
+	 * Default address space (either GGTT or ppGTT depending on arch).
+	 *
+	 * Reserved for exclusive use by the kernel.
+	 */
+	struct i915_address_space *vm;
 };
 
 enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
new file mode 100644
index 000000000000..16acdc5d6734
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -0,0 +1,598 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/slab.h> /* fault-inject.h is not standalone! */
+
+#include <linux/fault-inject.h>
+
+#include "i915_trace.h"
+#include "intel_gt.h"
+#include "intel_gtt.h"
+
+void stash_init(struct pagestash *stash)
+{
+	pagevec_init(&stash->pvec);
+	spin_lock_init(&stash->lock);
+}
+
+static struct page *stash_pop_page(struct pagestash *stash)
+{
+	struct page *page = NULL;
+
+	spin_lock(&stash->lock);
+	if (likely(stash->pvec.nr))
+		page = stash->pvec.pages[--stash->pvec.nr];
+	spin_unlock(&stash->lock);
+
+	return page;
+}
+
+static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
+{
+	unsigned int nr;
+
+	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
+
+	nr = min_t(typeof(nr), pvec->nr, pagevec_space(&stash->pvec));
+	memcpy(stash->pvec.pages + stash->pvec.nr,
+	       pvec->pages + pvec->nr - nr,
+	       sizeof(pvec->pages[0]) * nr);
+	stash->pvec.nr += nr;
+
+	spin_unlock(&stash->lock);
+
+	pvec->nr -= nr;
+}
+
+static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
+{
+	struct pagevec stack;
+	struct page *page;
+
+	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
+		i915_gem_shrink_all(vm->i915);
+
+	page = stash_pop_page(&vm->free_pages);
+	if (page)
+		return page;
+
+	if (!vm->pt_kmap_wc)
+		return alloc_page(gfp);
+
+	/* Look in our global stash of WC pages... */
+	page = stash_pop_page(&vm->i915->mm.wc_stash);
+	if (page)
+		return page;
+
+	/*
+	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
+	 *
+	 * We have to be careful as page allocation may trigger the shrinker
+	 * (via direct reclaim) which will fill up the WC stash underneath us.
+	 * So we add our WB pages into a temporary pvec on the stack and merge
+	 * them into the WC stash after all the allocations are complete.
+	 */
+	pagevec_init(&stack);
+	do {
+		struct page *page;
+
+		page = alloc_page(gfp);
+		if (unlikely(!page))
+			break;
+
+		stack.pages[stack.nr++] = page;
+	} while (pagevec_space(&stack));
+
+	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
+		page = stack.pages[--stack.nr];
+
+		/* Merge spare WC pages to the global stash */
+		if (stack.nr)
+			stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
+
+		/* Push any surplus WC pages onto the local VM stash */
+		if (stack.nr)
+			stash_push_pagevec(&vm->free_pages, &stack);
+	}
+
+	/* Return unwanted leftovers */
+	if (unlikely(stack.nr)) {
+		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
+		__pagevec_release(&stack);
+	}
+
+	return page;
+}
+
+static void vm_free_pages_release(struct i915_address_space *vm,
+				  bool immediate)
+{
+	struct pagevec *pvec = &vm->free_pages.pvec;
+	struct pagevec stack;
+
+	lockdep_assert_held(&vm->free_pages.lock);
+	GEM_BUG_ON(!pagevec_count(pvec));
+
+	if (vm->pt_kmap_wc) {
+		/*
+		 * When we use WC, first fill up the global stash and then
+		 * only if full immediately free the overflow.
+		 */
+		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
+
+		/*
+		 * As we have made some room in the VM's free_pages,
+		 * we can wait for it to fill again. Unless we are
+		 * inside i915_address_space_fini() and must
+		 * immediately release the pages!
+		 */
+		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
+			return;
+
+		/*
+		 * We have to drop the lock to allow ourselves to sleep,
+		 * so take a copy of the pvec and clear the stash for
+		 * others to use it as we sleep.
+		 */
+		stack = *pvec;
+		pagevec_reinit(pvec);
+		spin_unlock(&vm->free_pages.lock);
+
+		pvec = &stack;
+		set_pages_array_wb(pvec->pages, pvec->nr);
+
+		spin_lock(&vm->free_pages.lock);
+	}
+
+	__pagevec_release(pvec);
+}
+
+static void vm_free_page(struct i915_address_space *vm, struct page *page)
+{
+	/*
+	 * On !llc, we need to change the pages back to WB. We only do so
+	 * in bulk, so we rarely need to change the page attributes here,
+	 * but doing so requires a stop_machine() from deep inside arch/x86/mm.
+	 * To make detection of the possible sleep more likely, use an
+	 * unconditional might_sleep() for everybody.
+	 */
+	might_sleep();
+	spin_lock(&vm->free_pages.lock);
+	while (!pagevec_space(&vm->free_pages.pvec))
+		vm_free_pages_release(vm, false);
+	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec) >= PAGEVEC_SIZE);
+	pagevec_add(&vm->free_pages.pvec, page);
+	spin_unlock(&vm->free_pages.lock);
+}
+
+void __i915_vm_close(struct i915_address_space *vm)
+{
+	struct i915_vma *vma, *vn;
+
+	mutex_lock(&vm->mutex);
+	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		/* Keep the obj (and hence the vma) alive as _we_ destroy it */
+		if (!kref_get_unless_zero(&obj->base.refcount))
+			continue;
+
+		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
+		WARN_ON(__i915_vma_unbind(vma));
+		__i915_vma_put(vma);
+
+		i915_gem_object_put(obj);
+	}
+	GEM_BUG_ON(!list_empty(&vm->bound_list));
+	mutex_unlock(&vm->mutex);
+}
+
+void i915_address_space_fini(struct i915_address_space *vm)
+{
+	spin_lock(&vm->free_pages.lock);
+	if (pagevec_count(&vm->free_pages.pvec))
+		vm_free_pages_release(vm, true);
+	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
+	spin_unlock(&vm->free_pages.lock);
+
+	drm_mm_takedown(&vm->mm);
+
+	mutex_destroy(&vm->mutex);
+}
+
+static void __i915_vm_release(struct work_struct *work)
+{
+	struct i915_address_space *vm =
+		container_of(work, struct i915_address_space, rcu.work);
+
+	vm->cleanup(vm);
+	i915_address_space_fini(vm);
+
+	kfree(vm);
+}
+
+void i915_vm_release(struct kref *kref)
+{
+	struct i915_address_space *vm =
+		container_of(kref, struct i915_address_space, ref);
+
+	GEM_BUG_ON(i915_is_ggtt(vm));
+	trace_i915_ppgtt_release(vm);
+
+	queue_rcu_work(vm->i915->wq, &vm->rcu);
+}
+
+void i915_address_space_init(struct i915_address_space *vm, int subclass)
+{
+	kref_init(&vm->ref);
+	INIT_RCU_WORK(&vm->rcu, __i915_vm_release);
+	atomic_set(&vm->open, 1);
+
+	/*
+	 * The vm->mutex must be reclaim safe (for use in the shrinker).
+	 * Do a dummy acquire now under fs_reclaim so that any allocation
+	 * attempt holding the lock is immediately reported by lockdep.
+	 */
+	mutex_init(&vm->mutex);
+	lockdep_set_subclass(&vm->mutex, subclass);
+	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
+
+	GEM_BUG_ON(!vm->total);
+	drm_mm_init(&vm->mm, 0, vm->total);
+	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
+
+	stash_init(&vm->free_pages);
+
+	INIT_LIST_HEAD(&vm->bound_list);
+}
+
+void clear_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
+
+	if (vma->pages != vma->obj->mm.pages) {
+		sg_free_table(vma->pages);
+		kfree(vma->pages);
+	}
+	vma->pages = NULL;
+
+	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
+}
+
+static int __setup_page_dma(struct i915_address_space *vm,
+			    struct i915_page_dma *p,
+			    gfp_t gfp)
+{
+	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
+	if (unlikely(!p->page))
+		return -ENOMEM;
+
+	p->daddr = dma_map_page_attrs(vm->dma,
+				      p->page, 0, PAGE_SIZE,
+				      PCI_DMA_BIDIRECTIONAL,
+				      DMA_ATTR_SKIP_CPU_SYNC |
+				      DMA_ATTR_NO_WARN);
+	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
+		vm_free_page(vm, p->page);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p)
+{
+	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
+}
+
+void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p)
+{
+	dma_unmap_page(vm->dma, p->daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
+	vm_free_page(vm, p->page);
+}
+
+void
+fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count)
+{
+	kunmap_atomic(memset64(kmap_atomic(p->page), val, count));
+}
+
+int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
+{
+	unsigned long size;
+
+	/*
+	 * In order to utilize 64K pages for an object with a size < 2M, we will
+	 * need to support a 64K scratch page, given that every 16th entry for a
+	 * page-table operating in 64K mode must point to a properly aligned 64K
+	 * region, including any PTEs which happen to point to scratch.
+	 *
+	 * This is only relevant for the 48b PPGTT where we support
+	 * huge-gtt-pages, see also i915_vma_insert(). However, as we share the
+	 * scratch (read-only) between all vm, we create one 64k scratch page
+	 * for all.
+	 */
+	size = I915_GTT_PAGE_SIZE_4K;
+	if (i915_vm_is_4lvl(vm) &&
+	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
+		size = I915_GTT_PAGE_SIZE_64K;
+		gfp |= __GFP_NOWARN;
+	}
+	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
+
+	do {
+		unsigned int order = get_order(size);
+		struct page *page;
+		dma_addr_t addr;
+
+		page = alloc_pages(gfp, order);
+		if (unlikely(!page))
+			goto skip;
+
+		addr = dma_map_page_attrs(vm->dma,
+					  page, 0, size,
+					  PCI_DMA_BIDIRECTIONAL,
+					  DMA_ATTR_SKIP_CPU_SYNC |
+					  DMA_ATTR_NO_WARN);
+		if (unlikely(dma_mapping_error(vm->dma, addr)))
+			goto free_page;
+
+		if (unlikely(!IS_ALIGNED(addr, size)))
+			goto unmap_page;
+
+		vm->scratch[0].base.page = page;
+		vm->scratch[0].base.daddr = addr;
+		vm->scratch_order = order;
+		return 0;
+
+unmap_page:
+		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
+free_page:
+		__free_pages(page, order);
+skip:
+		if (size == I915_GTT_PAGE_SIZE_4K)
+			return -ENOMEM;
+
+		size = I915_GTT_PAGE_SIZE_4K;
+		gfp &= ~__GFP_NOWARN;
+	} while (1);
+}
+
+void cleanup_scratch_page(struct i915_address_space *vm)
+{
+	struct i915_page_dma *p = px_base(&vm->scratch[0]);
+	unsigned int order = vm->scratch_order;
+
+	dma_unmap_page(vm->dma, p->daddr, BIT(order) << PAGE_SHIFT,
+		       PCI_DMA_BIDIRECTIONAL);
+	__free_pages(p->page, order);
+}
+
+void free_scratch(struct i915_address_space *vm)
+{
+	int i;
+
+	if (!px_dma(&vm->scratch[0])) /* set to 0 on clones */
+		return;
+
+	for (i = 1; i <= vm->top; i++) {
+		if (!px_dma(&vm->scratch[i]))
+			break;
+		cleanup_page_dma(vm, px_base(&vm->scratch[i]));
+	}
+
+	cleanup_scratch_page(vm);
+}
+
+void gtt_write_workarounds(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+
+	/*
+	 * This function is for gtt related workarounds. This function is
+	 * called on driver load and after a GPU reset, so you can place
+	 * workarounds here even if they get overwritten by GPU reset.
+	 */
+	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl,icl */
+	if (IS_BROADWELL(i915))
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
+	else if (IS_CHERRYVIEW(i915))
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
+	else if (IS_GEN9_LP(i915))
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
+	else if (INTEL_GEN(i915) >= 9 && INTEL_GEN(i915) <= 11)
+		intel_uncore_write(uncore,
+				   GEN8_L3_LRA_1_GPGPU,
+				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
+
+	/*
+	 * To support 64K PTEs we need to first enable the use of the
+	 * Intermediate-Page-Size(IPS) bit of the PDE field via some magical
+	 * mmio, otherwise the page-walker will simply ignore the IPS bit. This
+	 * shouldn't be needed after GEN10.
+	 *
+	 * 64K pages were first introduced from BDW+, although technically they
+	 * only *work* from gen9+. For pre-BDW we instead have the option for
+	 * 32K pages, but we don't currently have any support for it in our
+	 * driver.
+	 */
+	if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_64K) &&
+	    INTEL_GEN(i915) <= 10)
+		intel_uncore_rmw(uncore,
+				 GEN8_GAMW_ECO_DEV_RW_IA,
+				 0,
+				 GAMW_ECO_ENABLE_64K_IPS_FIELD);
+
+	if (IS_GEN_RANGE(i915, 8, 11)) {
+		bool can_use_gtt_cache = true;
+
+		/*
+		 * According to the BSpec if we use 2M/1G pages then we also
+		 * need to disable the GTT cache. At least on BDW we can see
+		 * visual corruption when using 2M pages, and not disabling the
+		 * GTT cache.
+		 */
+		if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_2M))
+			can_use_gtt_cache = false;
+
+		/* WaGttCachingOffByDefault */
+		intel_uncore_write(uncore,
+				   HSW_GTT_CACHE_EN,
+				   can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0);
+		WARN_ON_ONCE(can_use_gtt_cache &&
+			     intel_uncore_read(uncore,
+					       HSW_GTT_CACHE_EN) == 0);
+	}
+}
+
+u64 gen8_pte_encode(dma_addr_t addr,
+		    enum i915_cache_level level,
+		    u32 flags)
+{
+	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~_PAGE_RW;
+
+	switch (level) {
+	case I915_CACHE_NONE:
+		pte |= PPAT_UNCACHED;
+		break;
+	case I915_CACHE_WT:
+		pte |= PPAT_DISPLAY_ELLC;
+		break;
+	default:
+		pte |= PPAT_CACHED;
+		break;
+	}
+
+	return pte;
+}
+
+static void tgl_setup_private_ppat(struct intel_uncore *uncore)
+{
+	/* TGL doesn't support LLC or AGE settings */
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(0), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(1), GEN8_PPAT_WC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(2), GEN8_PPAT_WT);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(3), GEN8_PPAT_UC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(4), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(5), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(6), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
+}
+
+static void cnl_setup_private_ppat(struct intel_uncore *uncore)
+{
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(0),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(1),
+			   GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(2),
+			   GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(3),
+			   GEN8_PPAT_UC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(4),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(5),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(6),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(7),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+}
+
+/*
+ * The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
+ * bits. When using advanced contexts each context stores its own PAT, but
+ * writing this data shouldn't be harmful even in those cases.
+ */
+static void bdw_setup_private_ppat(struct intel_uncore *uncore)
+{
+	u64 pat;
+
+	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) |	/* for normal objects, no eLLC */
+	      GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) |	/* for something pointing to ptes? */
+	      GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) |	/* for scanout with eLLC */
+	      GEN8_PPAT(3, GEN8_PPAT_UC) |			/* Uncached objects, mostly for scanout */
+	      GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
+	      GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
+	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
+	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+}
+
+static void chv_setup_private_ppat(struct intel_uncore *uncore)
+{
+	u64 pat;
+
+	/*
+	 * Map WB on BDW to snooped on CHV.
+	 *
+	 * Only the snoop bit has meaning for CHV, the rest is
+	 * ignored.
+	 *
+	 * The hardware will never snoop for certain types of accesses:
+	 * - CPU GTT (GMADR->GGTT->no snoop->memory)
+	 * - PPGTT page tables
+	 * - some other special cycles
+	 *
+	 * As with BDW, we also need to consider the following for GT accesses:
+	 * "For GGTT, there is NO pat_sel[2:0] from the entry,
+	 * so RTL will always use the value corresponding to
+	 * pat_sel = 000".
+	 * Which means we must set the snoop bit in PAT entry 0
+	 * in order to keep the global status page working.
+	 */
+
+	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(1, 0) |
+	      GEN8_PPAT(2, 0) |
+	      GEN8_PPAT(3, 0) |
+	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
+	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
+
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+}
+
+void setup_private_pat(struct intel_uncore *uncore)
+{
+	struct drm_i915_private *i915 = uncore->i915;
+
+	GEM_BUG_ON(INTEL_GEN(i915) < 8);
+
+	if (INTEL_GEN(i915) >= 12)
+		tgl_setup_private_ppat(uncore);
+	else if (INTEL_GEN(i915) >= 10)
+		cnl_setup_private_ppat(uncore);
+	else if (IS_CHERRYVIEW(i915) || IS_GEN9_LP(i915))
+		chv_setup_private_ppat(uncore);
+	else
+		bdw_setup_private_ppat(uncore);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/mock_gtt.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
new file mode 100644
index 000000000000..7da7681c20b1
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -0,0 +1,587 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2020 Intel Corporation
+ *
+ * Please try to maintain the following order within this file unless it makes
+ * sense to do otherwise. From top to bottom:
+ * 1. typedefs
+ * 2. #defines, and macros
+ * 3. structure definitions
+ * 4. function prototypes
+ *
+ * Within each section, please try to order by generation in ascending order,
+ * from top to bottom (ie. gen6 on the top, gen8 on the bottom).
+ */
+
+#ifndef __INTEL_GTT_H__
+#define __INTEL_GTT_H__
+
+#include <linux/io-mapping.h>
+#include <linux/kref.h>
+#include <linux/mm.h>
+#include <linux/pagevec.h>
+#include <linux/scatterlist.h>
+#include <linux/workqueue.h>
+
+#include <drm/drm_mm.h>
+
+#include "gt/intel_reset.h"
+#include "i915_gem_fence_reg.h"
+#include "i915_selftest.h"
+#include "i915_vma_types.h"
+
+#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
+
+#if IS_ENABLED(CONFIG_DRM_I915_TRACE_GTT)
+#define DBG(...) trace_printk(__VA_ARGS__)
+#else
+#define DBG(...)
+#endif
+
+#define NALLOC 3 /* 1 normal, 1 for concurrent threads, 1 for preallocation */
+
+#define I915_GTT_PAGE_SIZE_4K	BIT_ULL(12)
+#define I915_GTT_PAGE_SIZE_64K	BIT_ULL(16)
+#define I915_GTT_PAGE_SIZE_2M	BIT_ULL(21)
+
+#define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K
+#define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M
+
+#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE
+
+#define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE
+
+#define I915_FENCE_REG_NONE -1
+#define I915_MAX_NUM_FENCES 32
+/* 32 fences + sign bit for FENCE_REG_NONE */
+#define I915_MAX_NUM_FENCE_BITS 6
+
+typedef u32 gen6_pte_t;
+typedef u64 gen8_pte_t;
+
+#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
+
+#define I915_PTES(pte_len)		((unsigned int)(PAGE_SIZE / (pte_len)))
+#define I915_PTE_MASK(pte_len)		(I915_PTES(pte_len) - 1)
+#define I915_PDES			512
+#define I915_PDE_MASK			(I915_PDES - 1)
+
+/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
+#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
+#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
+#define GEN6_PTE_CACHE_LLC		(2 << 1)
+#define GEN6_PTE_UNCACHED		(1 << 1)
+#define GEN6_PTE_VALID			REG_BIT(0)
+
+#define GEN6_PTES			I915_PTES(sizeof(gen6_pte_t))
+#define GEN6_PD_SIZE		        (I915_PDES * PAGE_SIZE)
+#define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
+#define GEN6_PDE_SHIFT			22
+#define GEN6_PDE_VALID			REG_BIT(0)
+#define NUM_PTE(pde_shift)     (1 << (pde_shift - PAGE_SHIFT))
+
+#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
+
+#define BYT_PTE_SNOOPED_BY_CPU_CACHES	REG_BIT(2)
+#define BYT_PTE_WRITEABLE		REG_BIT(1)
+
+/*
+ * Cacheability Control is a 4-bit value. The low three bits are stored in bits
+ * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
+ */
+#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
+					 (((bits) & 0x8) << (11 - 3)))
+#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
+#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
+#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
+#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
+#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
+#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
+#define HSW_PTE_UNCACHED		(0)
+#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
+#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
+
+/*
+ * GEN8 32b style address is defined as a 3 level page table:
+ * 31:30 | 29:21 | 20:12 |  11:0
+ * PDPE  |  PDE  |  PTE  | offset
+ * The difference as compared to normal x86 3 level page table is the PDPEs are
+ * programmed via register.
+ *
+ * GEN8 48b style address is defined as a 4 level page table:
+ * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
+ * PML4E | PDPE  |  PDE  |  PTE  | offset
+ */
+#define GEN8_3LVL_PDPES			4
+
+#define PPAT_UNCACHED			(_PAGE_PWT | _PAGE_PCD)
+#define PPAT_CACHED_PDE			0 /* WB LLC */
+#define PPAT_CACHED			_PAGE_PAT /* WB LLCeLLC */
+#define PPAT_DISPLAY_ELLC		_PAGE_PCD /* WT eLLC */
+
+#define CHV_PPAT_SNOOP			REG_BIT(6)
+#define GEN8_PPAT_AGE(x)		((x)<<4)
+#define GEN8_PPAT_LLCeLLC		(3<<2)
+#define GEN8_PPAT_LLCELLC		(2<<2)
+#define GEN8_PPAT_LLC			(1<<2)
+#define GEN8_PPAT_WB			(3<<0)
+#define GEN8_PPAT_WT			(2<<0)
+#define GEN8_PPAT_WC			(1<<0)
+#define GEN8_PPAT_UC			(0<<0)
+#define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
+#define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))
+
+#define GEN8_PDE_IPS_64K BIT(11)
+#define GEN8_PDE_PS_2M   BIT(7)
+
+#define for_each_sgt_daddr(__dp, __iter, __sgt) \
+	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
+
+struct i915_page_dma {
+	struct page *page;
+	union {
+		dma_addr_t daddr;
+
+		/*
+		 * For gen6/gen7 only. This is the offset in the GGTT
+		 * where the page directory entries for PPGTT begin
+		 */
+		u32 ggtt_offset;
+	};
+};
+
+struct i915_page_scratch {
+	struct i915_page_dma base;
+	u64 encode;
+};
+
+struct i915_page_table {
+	struct i915_page_dma base;
+	atomic_t used;
+};
+
+struct i915_page_directory {
+	struct i915_page_table pt;
+	spinlock_t lock;
+	void *entry[512];
+};
+
+#define __px_choose_expr(x, type, expr, other) \
+	__builtin_choose_expr( \
+	__builtin_types_compatible_p(typeof(x), type) || \
+	__builtin_types_compatible_p(typeof(x), const type), \
+	({ type __x = (type)(x); expr; }), \
+	other)
+
+#define px_base(px) \
+	__px_choose_expr(px, struct i915_page_dma *, __x, \
+	__px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
+	__px_choose_expr(px, struct i915_page_table *, &__x->base, \
+	__px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
+	(void)0))))
+#define px_dma(px) (px_base(px)->daddr)
+
+#define px_pt(px) \
+	__px_choose_expr(px, struct i915_page_table *, __x, \
+	__px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
+	(void)0))
+#define px_used(px) (&px_pt(px)->used)
+
+enum i915_cache_level;
+
+struct drm_i915_file_private;
+struct drm_i915_gem_object;
+struct i915_vma;
+struct intel_gt;
+
+struct i915_vma_ops {
+	/* Map an object into an address space with the given cache flags. */
+	int (*bind_vma)(struct i915_vma *vma,
+			enum i915_cache_level cache_level,
+			u32 flags);
+	/*
+	 * Unmap an object from an address space. This usually consists of
+	 * setting the valid PTE entries to a reserved scratch page.
+	 */
+	void (*unbind_vma)(struct i915_vma *vma);
+
+	int (*set_pages)(struct i915_vma *vma);
+	void (*clear_pages)(struct i915_vma *vma);
+};
+
+struct pagestash {
+	spinlock_t lock;
+	struct pagevec pvec;
+};
+
+void stash_init(struct pagestash *stash);
+
+struct i915_address_space {
+	struct kref ref;
+	struct rcu_work rcu;
+
+	struct drm_mm mm;
+	struct intel_gt *gt;
+	struct drm_i915_private *i915;
+	struct device *dma;
+	/*
+	 * Every address space belongs to a struct file - except for the global
+	 * GTT that is owned by the driver (and so @file is set to NULL). In
+	 * principle, no information should leak from one context to another
+	 * (or between files/processes etc) unless explicitly shared by the
+	 * owner. Tracking the owner is important in order to free up per-file
+	 * objects along with the file, to aide resource tracking, and to
+	 * assign blame.
+	 */
+	struct drm_i915_file_private *file;
+	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
+	u64 reserved;		/* size addr space reserved */
+
+	unsigned int bind_async_flags;
+
+	/*
+	 * Each active user context has its own address space (in full-ppgtt).
+	 * Since the vm may be shared between multiple contexts, we count how
+	 * many contexts keep us "open". Once open hits zero, we are closed
+	 * and do not allow any new attachments, and proceed to shutdown our
+	 * vma and page directories.
+	 */
+	atomic_t open;
+
+	struct mutex mutex; /* protects vma and our lists */
+#define VM_CLASS_GGTT 0
+#define VM_CLASS_PPGTT 1
+
+	struct i915_page_scratch scratch[4];
+	unsigned int scratch_order;
+	unsigned int top;
+
+	/**
+	 * List of vma currently bound.
+	 */
+	struct list_head bound_list;
+
+	struct pagestash free_pages;
+
+	/* Global GTT */
+	bool is_ggtt:1;
+
+	/* Some systems require uncached updates of the page directories */
+	bool pt_kmap_wc:1;
+
+	/* Some systems support read-only mappings for GGTT and/or PPGTT */
+	bool has_read_only:1;
+
+	u64 (*pte_encode)(dma_addr_t addr,
+			  enum i915_cache_level level,
+			  u32 flags); /* Create a valid PTE */
+#define PTE_READ_ONLY	BIT(0)
+
+	int (*allocate_va_range)(struct i915_address_space *vm,
+				 u64 start, u64 length);
+	void (*clear_range)(struct i915_address_space *vm,
+			    u64 start, u64 length);
+	void (*insert_page)(struct i915_address_space *vm,
+			    dma_addr_t addr,
+			    u64 offset,
+			    enum i915_cache_level cache_level,
+			    u32 flags);
+	void (*insert_entries)(struct i915_address_space *vm,
+			       struct i915_vma *vma,
+			       enum i915_cache_level cache_level,
+			       u32 flags);
+	void (*cleanup)(struct i915_address_space *vm);
+
+	struct i915_vma_ops vma_ops;
+
+	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
+	I915_SELFTEST_DECLARE(bool scrub_64K);
+};
+
+/*
+ * The Graphics Translation Table is the way in which GEN hardware translates a
+ * Graphics Virtual Address into a Physical Address. In addition to the normal
+ * collateral associated with any va->pa translations GEN hardware also has a
+ * portion of the GTT which can be mapped by the CPU and remain both coherent
+ * and correct (in cases like swizzling). That region is referred to as GMADR in
+ * the spec.
+ */
+struct i915_ggtt {
+	struct i915_address_space vm;
+
+	struct io_mapping iomap;	/* Mapping to our CPU mappable region */
+	struct resource gmadr;          /* GMADR resource */
+	resource_size_t mappable_end;	/* End offset that we can CPU map */
+
+	/** "Graphics Stolen Memory" holds the global PTEs */
+	void __iomem *gsm;
+	void (*invalidate)(struct i915_ggtt *ggtt);
+
+	/** PPGTT used for aliasing the PPGTT with the GTT */
+	struct i915_ppgtt *alias;
+
+	bool do_idle_maps;
+
+	int mtrr;
+
+	/** Bit 6 swizzling required for X tiling */
+	u32 bit_6_swizzle_x;
+	/** Bit 6 swizzling required for Y tiling */
+	u32 bit_6_swizzle_y;
+
+	u32 pin_bias;
+
+	unsigned int num_fences;
+	struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
+	struct list_head fence_list;
+
+	/**
+	 * List of all objects in gtt_space, currently mmaped by userspace.
+	 * All objects within this list must also be on bound_list.
+	 */
+	struct list_head userfault_list;
+
+	/* Manual runtime pm autosuspend delay for user GGTT mmaps */
+	struct intel_wakeref_auto userfault_wakeref;
+
+	struct mutex error_mutex;
+	struct drm_mm_node error_capture;
+	struct drm_mm_node uc_fw;
+};
+
+struct i915_ppgtt {
+	struct i915_address_space vm;
+
+	struct i915_page_directory *pd;
+};
+
+#define i915_is_ggtt(vm) ((vm)->is_ggtt)
+
+static inline bool
+i915_vm_is_4lvl(const struct i915_address_space *vm)
+{
+	return (vm->total - 1) >> 32;
+}
+
+static inline bool
+i915_vm_has_scratch_64K(struct i915_address_space *vm)
+{
+	return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
+}
+
+static inline bool
+i915_vm_has_cache_coloring(struct i915_address_space *vm)
+{
+	return i915_is_ggtt(vm) && vm->mm.color_adjust;
+}
+
+static inline struct i915_ggtt *
+i915_vm_to_ggtt(struct i915_address_space *vm)
+{
+	BUILD_BUG_ON(offsetof(struct i915_ggtt, vm));
+	GEM_BUG_ON(!i915_is_ggtt(vm));
+	return container_of(vm, struct i915_ggtt, vm);
+}
+
+static inline struct i915_ppgtt *
+i915_vm_to_ppgtt(struct i915_address_space *vm)
+{
+	BUILD_BUG_ON(offsetof(struct i915_ppgtt, vm));
+	GEM_BUG_ON(i915_is_ggtt(vm));
+	return container_of(vm, struct i915_ppgtt, vm);
+}
+
+static inline struct i915_address_space *
+i915_vm_get(struct i915_address_space *vm)
+{
+	kref_get(&vm->ref);
+	return vm;
+}
+
+void i915_vm_release(struct kref *kref);
+
+static inline void i915_vm_put(struct i915_address_space *vm)
+{
+	kref_put(&vm->ref, i915_vm_release);
+}
+
+static inline struct i915_address_space *
+i915_vm_open(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!atomic_read(&vm->open));
+	atomic_inc(&vm->open);
+	return i915_vm_get(vm);
+}
+
+static inline bool
+i915_vm_tryopen(struct i915_address_space *vm)
+{
+	if (atomic_add_unless(&vm->open, 1, 0))
+		return i915_vm_get(vm);
+
+	return false;
+}
+
+void __i915_vm_close(struct i915_address_space *vm);
+
+static inline void
+i915_vm_close(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!atomic_read(&vm->open));
+	if (atomic_dec_and_test(&vm->open))
+		__i915_vm_close(vm);
+
+	i915_vm_put(vm);
+}
+
+void i915_address_space_init(struct i915_address_space *vm, int subclass);
+void i915_address_space_fini(struct i915_address_space *vm);
+
+static inline u32 i915_pte_index(u64 address, unsigned int pde_shift)
+{
+	const u32 mask = NUM_PTE(pde_shift) - 1;
+
+	return (address >> PAGE_SHIFT) & mask;
+}
+
+/*
+ * Helper to counts the number of PTEs within the given length. This count
+ * does not cross a page table boundary, so the max value would be
+ * GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
+ */
+static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
+{
+	const u64 mask = ~((1ULL << pde_shift) - 1);
+	u64 end;
+
+	GEM_BUG_ON(length == 0);
+	GEM_BUG_ON(offset_in_page(addr | length));
+
+	end = addr + length;
+
+	if ((addr & mask) != (end & mask))
+		return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);
+
+	return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
+}
+
+static inline u32 i915_pde_index(u64 addr, u32 shift)
+{
+	return (addr >> shift) & I915_PDE_MASK;
+}
+
+static inline struct i915_page_table *
+i915_pt_entry(const struct i915_page_directory * const pd,
+	      const unsigned short n)
+{
+	return pd->entry[n];
+}
+
+static inline struct i915_page_directory *
+i915_pd_entry(const struct i915_page_directory * const pdp,
+	      const unsigned short n)
+{
+	return pdp->entry[n];
+}
+
+static inline dma_addr_t
+i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
+{
+	struct i915_page_dma *pt = ppgtt->pd->entry[n];
+
+	return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
+}
+
+void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt);
+
+int i915_ggtt_probe_hw(struct drm_i915_private *i915);
+int i915_ggtt_init_hw(struct drm_i915_private *i915);
+int i915_ggtt_enable_hw(struct drm_i915_private *i915);
+void i915_ggtt_enable_guc(struct i915_ggtt *ggtt);
+void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
+int i915_init_ggtt(struct drm_i915_private *i915);
+void i915_ggtt_driver_release(struct drm_i915_private *i915);
+
+static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt)
+{
+	return ggtt->mappable_end > 0;
+}
+
+int i915_ppgtt_init_hw(struct intel_gt *gt);
+
+struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt);
+
+void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915);
+void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915);
+
+u64 gen8_pte_encode(dma_addr_t addr,
+		    enum i915_cache_level level,
+		    u32 flags);
+
+int setup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
+void cleanup_page_dma(struct i915_address_space *vm, struct i915_page_dma *p);
+
+#define kmap_atomic_px(px) kmap_atomic(px_base(px)->page)
+
+void
+fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count);
+
+#define fill_px(px, v) fill_page_dma(px_base(px), (v), PAGE_SIZE / sizeof(u64))
+#define fill32_px(px, v) do {						\
+	u64 v__ = lower_32_bits(v);					\
+	fill_px((px), v__ << 32 | v__);					\
+} while (0)
+
+int setup_scratch_page(struct i915_address_space *vm, gfp_t gfp);
+void cleanup_scratch_page(struct i915_address_space *vm);
+void free_scratch(struct i915_address_space *vm);
+
+struct i915_page_table *alloc_pt(struct i915_address_space *vm);
+struct i915_page_directory *alloc_pd(struct i915_address_space *vm);
+struct i915_page_directory *__alloc_pd(size_t sz);
+
+void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd);
+
+#define free_px(vm, px) free_pd(vm, px_base(px))
+
+void
+__set_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       struct i915_page_dma * const to,
+	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level));
+
+#define set_pd_entry(pd, idx, to) \
+	__set_pd_entry((pd), (idx), px_base(to), gen8_pde_encode)
+
+void
+clear_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       const struct i915_page_scratch * const scratch);
+
+bool
+release_pd_entry(struct i915_page_directory * const pd,
+		 const unsigned short idx,
+		 struct i915_page_table * const pt,
+		 const struct i915_page_scratch * const scratch);
+void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
+
+int ggtt_set_pages(struct i915_vma *vma);
+int ppgtt_set_pages(struct i915_vma *vma);
+void clear_pages(struct i915_vma *vma);
+
+void gtt_write_workarounds(struct intel_gt *gt);
+
+void setup_private_pat(struct intel_uncore *uncore);
+
+static inline struct sgt_dma {
+	struct scatterlist *sg;
+	dma_addr_t dma, max;
+} sgt_dma(struct i915_vma *vma) {
+	struct scatterlist *sg = vma->pages->sgl;
+	dma_addr_t addr = sg_dma_address(sg);
+
+	return (struct sgt_dma){ sg, addr, addr + sg->length };
+}
+
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d925a1035c9d..0cf0f6fae675 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -133,12 +133,11 @@
  */
 #include <linux/interrupt.h>
 
-#include "gem/i915_gem_context.h"
-
 #include "i915_drv.h"
 #include "i915_perf.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
+#include "intel_context.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
@@ -489,17 +488,23 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	return desc;
 }
 
-static u32 *set_offsets(u32 *regs,
+static inline unsigned int dword_in_page(void *addr)
+{
+	return offset_in_page(addr) / sizeof(u32);
+}
+
+static void set_offsets(u32 *regs,
 			const u8 *data,
-			const struct intel_engine_cs *engine)
+			const struct intel_engine_cs *engine,
+			bool clear)
 #define NOP(x) (BIT(7) | (x))
-#define LRI(count, flags) ((flags) << 6 | (count))
+#define LRI(count, flags) ((flags) << 6 | (count) | BUILD_BUG_ON_ZERO(count >= BIT(6)))
 #define POSTED BIT(0)
 #define REG(x) (((x) >> 2) | BUILD_BUG_ON_ZERO(x >= 0x200))
 #define REG16(x) \
 	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
 	(((x) >> 2) & 0x7f)
-#define END() 0
+#define END(x) 0, (x)
 {
 	const u32 base = engine->mmio_base;
 
@@ -507,7 +512,10 @@ static u32 *set_offsets(u32 *regs,
 		u8 count, flags;
 
 		if (*data & BIT(7)) { /* skip */
-			regs += *data++ & ~BIT(7);
+			count = *data++ & ~BIT(7);
+			if (clear)
+				memset32(regs, MI_NOOP, count);
+			regs += count;
 			continue;
 		}
 
@@ -533,12 +541,25 @@ static u32 *set_offsets(u32 *regs,
 				offset |= v & ~BIT(7);
 			} while (v & BIT(7));
 
-			*regs = base + (offset << 2);
+			regs[0] = base + (offset << 2);
+			if (clear)
+				regs[1] = 0;
 			regs += 2;
 		} while (--count);
 	}
 
-	return regs;
+	if (clear) {
+		u8 count = *++data;
+
+		/* Clear past the tail for HW access */
+		GEM_BUG_ON(dword_in_page(regs) > count);
+		memset32(regs, MI_NOOP, count - dword_in_page(regs));
+
+		/* Close the batch; used mainly by live_lrc_layout() */
+		*regs = MI_BATCH_BUFFER_END;
+		if (INTEL_GEN(engine->i915) >= 10)
+			*regs |= BIT(0);
+	}
 }
 
 static const u8 gen8_xcs_offsets[] = {
@@ -573,7 +594,7 @@ static const u8 gen8_xcs_offsets[] = {
 	REG16(0x200),
 	REG(0x028),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen9_xcs_offsets[] = {
@@ -657,7 +678,7 @@ static const u8 gen9_xcs_offsets[] = {
 	REG16(0x67c),
 	REG(0x068),
 
-	END(),
+	END(176)
 };
 
 static const u8 gen12_xcs_offsets[] = {
@@ -689,7 +710,7 @@ static const u8 gen12_xcs_offsets[] = {
 	REG16(0x274),
 	REG16(0x270),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen8_rcs_offsets[] = {
@@ -726,7 +747,91 @@ static const u8 gen8_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
+};
+
+static const u8 gen9_rcs_offsets[] = {
+	NOP(1),
+	LRI(14, POSTED),
+	REG16(0x244),
+	REG(0x34),
+	REG(0x30),
+	REG(0x38),
+	REG(0x3c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+
+	NOP(3),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(1, 0),
+	REG(0xc8),
+
+	NOP(13),
+	LRI(44, POSTED),
+	REG(0x28),
+	REG(0x9c),
+	REG(0xc0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x68),
+
+	END(176)
 };
 
 static const u8 gen11_rcs_offsets[] = {
@@ -767,7 +872,7 @@ static const u8 gen11_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
 };
 
 static const u8 gen12_rcs_offsets[] = {
@@ -808,7 +913,7 @@ static const u8 gen12_rcs_offsets[] = {
 	LRI(1, 0),
 	REG(0x0c8),
 
-	END(),
+	END(80)
 };
 
 #undef END
@@ -833,6 +938,8 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 			return gen12_rcs_offsets;
 		else if (INTEL_GEN(engine->i915) >= 11)
 			return gen11_rcs_offsets;
+		else if (INTEL_GEN(engine->i915) >= 9)
+			return gen9_rcs_offsets;
 		else
 			return gen8_rcs_offsets;
 	} else {
@@ -880,7 +987,7 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			active = rq;
 		} else {
-			struct intel_engine_cs *owner = rq->hw_context->engine;
+			struct intel_engine_cs *owner = rq->context->engine;
 
 			/*
 			 * Decouple the virtual breadcrumb before moving it
@@ -983,6 +1090,58 @@ static void intel_engine_context_out(struct intel_engine_cs *engine)
 	write_sequnlock_irqrestore(&engine->stats.lock, flags);
 }
 
+static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
+{
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x60;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x54;
+	else if (engine->class == RENDER_CLASS)
+		return 0x58;
+	else
+		return -1;
+}
+
+static void
+execlists_check_context(const struct intel_context *ce,
+			const struct intel_engine_cs *engine)
+{
+	const struct intel_ring *ring = ce->ring;
+	u32 *regs = ce->lrc_reg_state;
+	bool valid = true;
+	int x;
+
+	if (regs[CTX_RING_START] != i915_ggtt_offset(ring->vma)) {
+		pr_err("%s: context submitted with incorrect RING_START [%08x], expected %08x\n",
+		       engine->name,
+		       regs[CTX_RING_START],
+		       i915_ggtt_offset(ring->vma));
+		regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
+		valid = false;
+	}
+
+	if ((regs[CTX_RING_CTL] & ~(RING_WAIT | RING_WAIT_SEMAPHORE)) !=
+	    (RING_CTL_SIZE(ring->size) | RING_VALID)) {
+		pr_err("%s: context submitted with incorrect RING_CTL [%08x], expected %08x\n",
+		       engine->name,
+		       regs[CTX_RING_CTL],
+		       (u32)(RING_CTL_SIZE(ring->size) | RING_VALID));
+		regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
+		valid = false;
+	}
+
+	x = lrc_ring_mi_mode(engine);
+	if (x != -1 && regs[x + 1] & (regs[x + 1] >> 16) & STOP_RING) {
+		pr_err("%s: context submitted with STOP_RING [%08x] in RING_MI_MODE\n",
+		       engine->name, regs[x + 1]);
+		regs[x + 1] &= ~STOP_RING;
+		regs[x + 1] |= STOP_RING << 16;
+		valid = false;
+	}
+
+	WARN_ONCE(!valid, "Invalid lrc state found before submission\n");
+}
+
 static void restore_default_state(struct intel_context *ce,
 				  struct intel_engine_cs *engine)
 {
@@ -999,7 +1158,7 @@ static void restore_default_state(struct intel_context *ce,
 static void reset_active(struct i915_request *rq,
 			 struct intel_engine_cs *engine)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	u32 head;
 
 	/*
@@ -1017,8 +1176,8 @@ static void reset_active(struct i915_request *rq,
 	 * remain correctly ordered. And we defer to __i915_request_submit()
 	 * so that all asynchronous waits are correctly handled.
 	 */
-	GEM_TRACE("%s(%s): { rq=%llx:%lld }\n",
-		  __func__, engine->name, rq->fence.context, rq->fence.seqno);
+	ENGINE_TRACE(engine, "{ rq=%llx:%lld }\n",
+		     rq->fence.context, rq->fence.seqno);
 
 	/* On resubmission of the active request, payload will be scrubbed */
 	if (i915_request_completed(rq))
@@ -1040,13 +1199,16 @@ static inline struct intel_engine_cs *
 __execlists_schedule_in(struct i915_request *rq)
 {
 	struct intel_engine_cs * const engine = rq->engine;
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 
 	intel_context_get(ce);
 
-	if (unlikely(i915_gem_context_is_banned(ce->gem_context)))
+	if (unlikely(intel_context_is_banned(ce)))
 		reset_active(rq, engine);
 
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+		execlists_check_context(ce, engine);
+
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
 		ce->lrc_desc |= (u64)ce->tag << 32;
@@ -1054,12 +1216,12 @@ __execlists_schedule_in(struct i915_request *rq)
 		/* We don't need a strict matching tag, just different values */
 		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
 		ce->lrc_desc |=
-			(u64)(engine->context_tag++ % NUM_CONTEXT_TAG) <<
+			(u64)(++engine->context_tag % NUM_CONTEXT_TAG) <<
 			GEN11_SW_CTX_ID_SHIFT;
 		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
 	}
 
-	intel_gt_pm_get(engine->gt);
+	__intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
 
@@ -1069,7 +1231,7 @@ __execlists_schedule_in(struct i915_request *rq)
 static inline struct i915_request *
 execlists_schedule_in(struct i915_request *rq, int idx)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *old;
 
 	GEM_BUG_ON(!intel_engine_pm_is_awake(rq->engine));
@@ -1100,7 +1262,7 @@ static inline void
 __execlists_schedule_out(struct i915_request *rq,
 			 struct intel_engine_cs * const engine)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 
 	/*
 	 * NB process_csb() is not under the engine->active.lock and hence
@@ -1138,7 +1300,7 @@ __execlists_schedule_out(struct i915_request *rq,
 static inline void
 execlists_schedule_out(struct i915_request *rq)
 {
-	struct intel_context * const ce = rq->hw_context;
+	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
@@ -1155,7 +1317,7 @@ execlists_schedule_out(struct i915_request *rq)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce = rq->hw_context;
+	struct intel_context *ce = rq->context;
 	u64 desc = ce->lrc_desc;
 	u32 tail;
 
@@ -1186,17 +1348,8 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * may not be visible to the HW prior to the completion of the UC
 	 * register write and that we may begin execution from the context
 	 * before its image is complete leading to invalid PD chasing.
-	 *
-	 * Furthermore, Braswell, at least, wants a full mb to be sure that
-	 * the writes are coherent in memory (visible to the GPU) prior to
-	 * execution, and not just visible to other CPUs (as is the result of
-	 * wmb).
 	 */
-	mb();
-
-	/* Wa_1607138340:tgl */
-	if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0))
-		desc |= CTX_DESC_FORCE_RESTORE;
+	wmb();
 
 	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
 	return desc;
@@ -1224,15 +1377,14 @@ trace_ports(const struct intel_engine_execlists *execlists,
 	if (!ports[0])
 		return;
 
-	GEM_TRACE("%s: %s { %llx:%lld%s, %llx:%lld }\n",
-		  engine->name, msg,
-		  ports[0]->fence.context,
-		  ports[0]->fence.seqno,
-		  i915_request_completed(ports[0]) ? "!" :
-		  i915_request_started(ports[0]) ? "*" :
-		  "",
-		  ports[1] ? ports[1]->fence.context : 0,
-		  ports[1] ? ports[1]->fence.seqno : 0);
+	ENGINE_TRACE(engine, "%s { %llx:%lld%s, %llx:%lld }\n", msg,
+		     ports[0]->fence.context,
+		     ports[0]->fence.seqno,
+		     i915_request_completed(ports[0]) ? "!" :
+		     i915_request_started(ports[0]) ? "*" :
+		     "",
+		     ports[1] ? ports[1]->fence.context : 0,
+		     ports[1] ? ports[1]->fence.seqno : 0);
 }
 
 static __maybe_unused bool
@@ -1256,33 +1408,56 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 	}
 
 	for (port = execlists->pending; (rq = *port); port++) {
-		if (ce == rq->hw_context) {
-			GEM_TRACE_ERR("Duplicate context in pending[%zd]\n",
+		unsigned long flags;
+		bool ok = true;
+
+		GEM_BUG_ON(!kref_read(&rq->fence.refcount));
+		GEM_BUG_ON(!i915_request_is_active(rq));
+
+		if (ce == rq->context) {
+			GEM_TRACE_ERR("Dup context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
 			return false;
 		}
+		ce = rq->context;
 
-		ce = rq->hw_context;
-		if (i915_request_completed(rq))
+		/* Hold tightly onto the lock to prevent concurrent retires! */
+		if (!spin_trylock_irqsave(&rq->lock, flags))
 			continue;
 
-		if (i915_active_is_idle(&ce->active)) {
-			GEM_TRACE_ERR("Inactive context in pending[%zd]\n",
+		if (i915_request_completed(rq))
+			goto unlock;
+
+		if (i915_active_is_idle(&ce->active) &&
+		    !intel_context_is_barrier(ce)) {
+			GEM_TRACE_ERR("Inactive context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
 
 		if (!i915_vma_is_pinned(ce->state)) {
-			GEM_TRACE_ERR("Unpinned context in pending[%zd]\n",
+			GEM_TRACE_ERR("Unpinned context:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
 
 		if (!i915_vma_is_pinned(ce->ring->vma)) {
-			GEM_TRACE_ERR("Unpinned ringbuffer in pending[%zd]\n",
+			GEM_TRACE_ERR("Unpinned ring:%llx in pending[%zd]\n",
+				      ce->timeline->fence_context,
 				      port - execlists->pending);
-			return false;
+			ok = false;
+			goto unlock;
 		}
+
+unlock:
+		spin_unlock_irqrestore(&rq->lock, flags);
+		if (!ok)
+			return false;
 	}
 
 	return ce;
@@ -1327,7 +1502,7 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 static bool ctx_single_port_submission(const struct intel_context *ce)
 {
 	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
-		i915_gem_context_force_single_submission(ce->gem_context));
+		intel_context_force_single_submission(ce));
 }
 
 static bool can_merge_ctx(const struct intel_context *prev,
@@ -1359,11 +1534,11 @@ static bool can_merge_rq(const struct i915_request *prev,
 	if (i915_request_completed(next))
 		return true;
 
-	if (unlikely((prev->flags ^ next->flags) &
-		     (I915_REQUEST_NOPREEMPT | I915_REQUEST_SENTINEL)))
+	if (unlikely((prev->fence.flags ^ next->fence.flags) &
+		     (I915_FENCE_FLAG_NOPREEMPT | I915_FENCE_FLAG_SENTINEL)))
 		return false;
 
-	if (!can_merge_ctx(prev->hw_context, next->hw_context))
+	if (!can_merge_ctx(prev->context, next->context))
 		return false;
 
 	return true;
@@ -1372,7 +1547,7 @@ static bool can_merge_rq(const struct i915_request *prev,
 static void virtual_update_register_offsets(u32 *regs,
 					    struct intel_engine_cs *engine)
 {
-	set_offsets(regs, reg_offsets(engine), engine);
+	set_offsets(regs, reg_offsets(engine), engine, false);
 }
 
 static bool virtual_matches(const struct virtual_engine *ve,
@@ -1411,7 +1586,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 	if (!list_empty(&ve->context.signal_link)) {
 		list_move_tail(&ve->context.signal_link,
 			       &engine->breadcrumbs.signalers);
-		intel_engine_queue_breadcrumbs(engine);
+		intel_engine_signal_breadcrumbs(engine);
 	}
 	spin_unlock(&old->breadcrumbs.irq_lock);
 }
@@ -1519,7 +1694,7 @@ active_timeslice(const struct intel_engine_cs *engine)
 {
 	const struct i915_request *rq = *engine->execlists.active;
 
-	if (i915_request_completed(rq))
+	if (!rq || i915_request_completed(rq))
 		return 0;
 
 	if (engine->execlists.switch_priority_hint < effective_prio(rq))
@@ -1550,7 +1725,7 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
 		return 0;
 
 	/* Force a fast reset for terminated contexts (ignoring sysfs!) */
-	if (unlikely(i915_gem_context_is_banned(rq->gem_context)))
+	if (unlikely(intel_context_is_banned(rq->context)))
 		return 1;
 
 	return READ_ONCE(engine->props.preempt_timeout_ms);
@@ -1565,6 +1740,11 @@ static void set_preempt_timeout(struct intel_engine_cs *engine)
 		     active_preempt_timeout(engine));
 }
 
+static inline void clear_ports(struct i915_request **ports, int count)
+{
+	memset_p((void **)ports, NULL, count);
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1627,12 +1807,12 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	last = last_active(execlists);
 	if (last) {
 		if (need_preempt(engine, last, rb)) {
-			GEM_TRACE("%s: preempting last=%llx:%lld, prio=%d, hint=%d\n",
-				  engine->name,
-				  last->fence.context,
-				  last->fence.seqno,
-				  last->sched.attr.priority,
-				  execlists->queue_priority_hint);
+			ENGINE_TRACE(engine,
+				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
+				     last->fence.context,
+				     last->fence.seqno,
+				     last->sched.attr.priority,
+				     execlists->queue_priority_hint);
 			record_preemption(execlists);
 
 			/*
@@ -1658,16 +1838,16 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * tendency to ignore us rewinding the TAIL to the
 			 * end of an earlier request.
 			 */
-			last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+			last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timer_expired(&engine->execlists.timer)) {
-			GEM_TRACE("%s: expired last=%llx:%lld, prio=%d, hint=%d\n",
-				  engine->name,
-				  last->fence.context,
-				  last->fence.seqno,
-				  last->sched.attr.priority,
-				  execlists->queue_priority_hint);
+			ENGINE_TRACE(engine,
+				     "expired last=%llx:%lld, prio=%d, hint=%d\n",
+				     last->fence.context,
+				     last->fence.seqno,
+				     last->sched.attr.priority,
+				     execlists->queue_priority_hint);
 
 			ring_set_paused(engine, 1);
 			defer_active(engine);
@@ -1730,7 +1910,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 		GEM_BUG_ON(rq != ve->request);
 		GEM_BUG_ON(rq->engine != &ve->base);
-		GEM_BUG_ON(rq->hw_context != &ve->context);
+		GEM_BUG_ON(rq->context != &ve->context);
 
 		if (rq_prio(rq) >= queue_prio(execlists)) {
 			if (!virtual_matches(ve, rq, engine)) {
@@ -1744,14 +1924,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				return; /* leave this for another */
 			}
 
-			GEM_TRACE("%s: virtual rq=%llx:%lld%s, new engine? %s\n",
-				  engine->name,
-				  rq->fence.context,
-				  rq->fence.seqno,
-				  i915_request_completed(rq) ? "!" :
-				  i915_request_started(rq) ? "*" :
-				  "",
-				  yesno(engine != ve->siblings[0]));
+			ENGINE_TRACE(engine,
+				     "virtual rq=%llx:%lld%s, new engine? %s\n",
+				     rq->fence.context,
+				     rq->fence.seqno,
+				     i915_request_completed(rq) ? "!" :
+				     i915_request_started(rq) ? "*" :
+				     "",
+				     yesno(engine != ve->siblings[0]));
 
 			ve->request = NULL;
 			ve->base.execlists.queue_priority_hint = INT_MIN;
@@ -1849,7 +2029,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * same LRCA, i.e. we must submit 2 different
 				 * contexts if we submit 2 ELSP.
 				 */
-				if (last->hw_context == rq->hw_context)
+				if (last->context == rq->context)
 					goto done;
 
 				if (i915_request_has_sentinel(last))
@@ -1862,8 +2042,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->hw_context) ||
-				    ctx_single_port_submission(rq->hw_context))
+				if (ctx_single_port_submission(last->context) ||
+				    ctx_single_port_submission(rq->context))
 					goto done;
 
 				merge = false;
@@ -1877,8 +2057,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				}
 
 				GEM_BUG_ON(last &&
-					   !can_merge_ctx(last->hw_context,
-							  rq->hw_context));
+					   !can_merge_ctx(last->context,
+							  rq->context));
 
 				submit = true;
 				last = rq;
@@ -1907,9 +2087,6 @@ done:
 	 * interrupt for secondary ports).
 	 */
 	execlists->queue_priority_hint = queue_prio(execlists);
-	GEM_TRACE("%s: queue_priority_hint:%d, submit:%s\n",
-		  engine->name, execlists->queue_priority_hint,
-		  yesno(submit));
 
 	if (submit) {
 		*port = execlists_schedule_in(last, port - execlists->pending);
@@ -1928,10 +2105,9 @@ done:
 
 			goto skip_submit;
 		}
+		clear_ports(port + 1, last_port - port);
 
-		memset(port + 1, 0, (last_port - port) * sizeof(*port));
 		execlists_submit_ports(engine);
-
 		set_preempt_timeout(engine);
 	} else {
 skip_submit:
@@ -1946,13 +2122,14 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 
 	for (port = execlists->pending; *port; port++)
 		execlists_schedule_out(*port);
-	memset(execlists->pending, 0, sizeof(execlists->pending));
+	clear_ports(execlists->pending, ARRAY_SIZE(execlists->pending));
 
 	/* Mark the end of active before we overwrite *active */
 	for (port = xchg(&execlists->active, execlists->pending); *port; port++)
 		execlists_schedule_out(*port);
-	WRITE_ONCE(execlists->active,
-		   memset(execlists->inflight, 0, sizeof(execlists->inflight)));
+	clear_ports(execlists->inflight, ARRAY_SIZE(execlists->inflight));
+
+	WRITE_ONCE(execlists->active, execlists->inflight);
 }
 
 static inline void
@@ -2058,7 +2235,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	 */
 	head = execlists->csb_head;
 	tail = READ_ONCE(*execlists->csb_write);
-	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	ENGINE_TRACE(engine, "cs-irq head=%d, tail=%d\n", head, tail);
 	if (unlikely(head == tail))
 		return;
 
@@ -2096,9 +2273,8 @@ static void process_csb(struct intel_engine_cs *engine)
 		 * status notifier.
 		 */
 
-		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x\n",
-			  engine->name, head,
-			  buf[2 * head + 0], buf[2 * head + 1]);
+		ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n",
+			     head, buf[2 * head + 0], buf[2 * head + 1]);
 
 		if (INTEL_GEN(engine->i915) >= 12)
 			promote = gen12_csb_parse(execlists, buf + 2 * head);
@@ -2109,7 +2285,6 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* Point active to the new ELSP; prevent overwriting */
 			WRITE_ONCE(execlists->active, execlists->pending);
-			set_timeslice(engine);
 
 			if (!inject_preempt_hang(execlists))
 				ring_set_paused(engine, 0);
@@ -2150,6 +2325,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	} while (head != tail);
 
 	execlists->csb_head = head;
+	set_timeslice(engine);
 
 	/*
 	 * Gen11 has proven to fail wrt global observation point between
@@ -2189,10 +2365,9 @@ static noinline void preempt_reset(struct intel_engine_cs *engine)
 	/* Mark this tasklet as disabled to avoid waiting for it to complete */
 	tasklet_disable_nosync(&engine->execlists.tasklet);
 
-	GEM_TRACE("%s: preempt timeout %lu+%ums\n",
-		  engine->name,
-		  READ_ONCE(engine->props.preempt_timeout_ms),
-		  jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
+	ENGINE_TRACE(engine, "preempt timeout %lu+%ums\n",
+		     READ_ONCE(engine->props.preempt_timeout_ms),
+		     jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
 	intel_engine_reset(engine, "preemption time out");
 
 	tasklet_enable(&engine->execlists.tasklet);
@@ -2333,7 +2508,7 @@ set_redzone(void *vaddr, const struct intel_engine_cs *engine)
 
 	vaddr += engine->context_size;
 
-	memset(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE);
+	memset(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE);
 }
 
 static void
@@ -2344,7 +2519,7 @@ check_redzone(const void *vaddr, const struct intel_engine_cs *engine)
 
 	vaddr += engine->context_size;
 
-	if (memchr_inv(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE))
+	if (memchr_inv(vaddr, CONTEXT_REDZONE, I915_GTT_PAGE_SIZE))
 		dev_err_once(engine->i915->drm.dev,
 			     "%s context redzone overwritten!\n",
 			     engine->name);
@@ -2369,7 +2544,7 @@ __execlists_update_reg_state(const struct intel_context *ce,
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
 
-	regs[CTX_RING_BUFFER_START] = i915_ggtt_offset(ring->vma);
+	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
 	regs[CTX_RING_HEAD] = ring->head;
 	regs[CTX_RING_TAIL] = ring->tail;
 
@@ -2387,33 +2562,21 @@ __execlists_context_pin(struct intel_context *ce,
 			struct intel_engine_cs *engine)
 {
 	void *vaddr;
-	int ret;
 
 	GEM_BUG_ON(!ce->state);
-
-	ret = intel_context_active_acquire(ce);
-	if (ret)
-		goto err;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	vaddr = i915_gem_object_pin_map(ce->state->obj,
 					i915_coherent_map_type(engine->i915) |
 					I915_MAP_OVERRIDE);
-	if (IS_ERR(vaddr)) {
-		ret = PTR_ERR(vaddr);
-		goto unpin_active;
-	}
+	if (IS_ERR(vaddr))
+		return PTR_ERR(vaddr);
 
-	ce->lrc_desc = lrc_descriptor(ce, engine);
+	ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine);
 
 	return 0;
-
-unpin_active:
-	intel_context_active_release(ce);
-err:
-	return ret;
 }
 
 static int execlists_context_pin(struct intel_context *ce)
@@ -2428,6 +2591,9 @@ static int execlists_context_alloc(struct intel_context *ce)
 
 static void execlists_context_reset(struct intel_context *ce)
 {
+	CE_TRACE(ce, "reset\n");
+	GEM_BUG_ON(!intel_context_is_pinned(ce));
+
 	/*
 	 * Because we emit WA_TAIL_DWORDS there may be a disparity
 	 * between our bookkeeping in ce->ring->head and ce->ring->tail and
@@ -2444,8 +2610,14 @@ static void execlists_context_reset(struct intel_context *ce)
 	 * So to avoid that we reset the context images upon resume. For
 	 * simplicity, we just zero everything out.
 	 */
-	intel_ring_reset(ce->ring, 0);
+	intel_ring_reset(ce->ring, ce->ring->emit);
+
+	/* Scrub away the garbage */
+	execlists_init_reg_state(ce->lrc_reg_state,
+				 ce, ce->engine, ce->ring, true);
 	__execlists_update_reg_state(ce, ce->engine);
+
+	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 }
 
 static const struct intel_context_ops execlists_context_ops = {
@@ -2497,7 +2669,7 @@ static int execlists_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!intel_context_is_pinned(request->hw_context));
+	GEM_BUG_ON(!intel_context_is_pinned(request->context));
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
@@ -2867,6 +3039,8 @@ static void enable_execlists(struct intel_engine_cs *engine)
 			RING_HWS_PGA,
 			i915_ggtt_offset(engine->status_page.vma));
 	ENGINE_POSTING_READ(engine, RING_HWS_PGA);
+
+	engine->context_tag = 0;
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -2906,8 +3080,8 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
 
-	GEM_TRACE("%s: depth<-%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth<-%d\n",
+		     atomic_read(&execlists->tasklet.count));
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -2960,26 +3134,20 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 	WRITE_ONCE(*execlists->csb_write, reset_value);
 	wmb(); /* Make sure this is visible to HW (paranoia?) */
 
+	/*
+	 * Sometimes Icelake forgets to reset its pointers on a GPU reset.
+	 * Bludgeon them with a mmio update to be sure.
+	 */
+	ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
+		     reset_value << 8 | reset_value);
+	ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
 	invalidate_csb_entries(&execlists->csb_status[0],
 			       &execlists->csb_status[reset_value]);
 }
 
-static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
-{
-	if (INTEL_GEN(engine->i915) >= 12)
-		return 0x60;
-	else if (INTEL_GEN(engine->i915) >= 9)
-		return 0x54;
-	else if (engine->class == RENDER_CLASS)
-		return 0x58;
-	else
-		return -1;
-}
-
-static void __execlists_reset_reg_state(const struct intel_context *ce,
-					const struct intel_engine_cs *engine)
+static void __reset_stop_ring(u32 *regs, const struct intel_engine_cs *engine)
 {
-	u32 *regs = ce->lrc_reg_state;
 	int x;
 
 	x = lrc_ring_mi_mode(engine);
@@ -2989,6 +3157,14 @@ static void __execlists_reset_reg_state(const struct intel_context *ce,
 	}
 }
 
+static void __execlists_reset_reg_state(const struct intel_context *ce,
+					const struct intel_engine_cs *engine)
+{
+	u32 *regs = ce->lrc_reg_state;
+
+	__reset_stop_ring(regs, engine);
+}
+
 static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -3016,7 +3192,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	/* We still have requests in-flight; the engine should be active */
 	GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 
-	ce = rq->hw_context;
+	ce = rq->context;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	if (i915_request_completed(rq)) {
@@ -3073,8 +3249,8 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	restore_default_state(ce, engine);
 
 out_replay:
-	GEM_TRACE("%s replay {head:%04x, tail:%04x}\n",
-		  engine->name, ce->ring->head, ce->ring->tail);
+	ENGINE_TRACE(engine, "replay {head:%04x, tail:%04x}\n",
+		     ce->ring->head, ce->ring->tail);
 	intel_ring_update_space(ce->ring);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
@@ -3086,11 +3262,11 @@ unwind:
 	__unwind_incomplete_requests(engine);
 }
 
-static void execlists_reset(struct intel_engine_cs *engine, bool stalled)
+static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	spin_lock_irqsave(&engine->active.lock, flags);
 
@@ -3104,14 +3280,14 @@ static void nop_submission_tasklet(unsigned long data)
 	/* The driver is wedged; don't process any more events. */
 }
 
-static void execlists_cancel_requests(struct intel_engine_cs *engine)
+static void execlists_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -3198,13 +3374,13 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	if (__tasklet_enable(&execlists->tasklet))
 		/* And kick in case we missed a new request submission. */
 		tasklet_hi_schedule(&execlists->tasklet);
-	GEM_TRACE("%s: depth->%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth->%d\n",
+		     atomic_read(&execlists->tasklet.count));
 }
 
-static int gen8_emit_bb_start(struct i915_request *rq,
-			      u64 offset, u32 len,
-			      const unsigned int flags)
+static int gen8_emit_bb_start_noarb(struct i915_request *rq,
+				    u64 offset, u32 len,
+				    const unsigned int flags)
 {
 	u32 *cs;
 
@@ -3238,7 +3414,7 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 	return 0;
 }
 
-static int gen9_emit_bb_start(struct i915_request *rq,
+static int gen8_emit_bb_start(struct i915_request *rq,
 			      u64 offset, u32 len,
 			      const unsigned int flags)
 {
@@ -3693,12 +3869,12 @@ static void execlists_park(struct intel_engine_cs *engine)
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
-	engine->cancel_requests = execlists_cancel_requests;
 	engine->schedule = i915_schedule;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
 	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.reset = execlists_reset;
+	engine->reset.rewind = execlists_reset_rewind;
+	engine->reset.cancel = execlists_reset_cancel;
 	engine->reset.finish = execlists_reset_finish;
 
 	engine->park = execlists_park;
@@ -3713,13 +3889,27 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 
 	if (INTEL_GEN(engine->i915) >= 12)
 		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
+
+	if (intel_engine_has_preemption(engine))
+		engine->emit_bb_start = gen8_emit_bb_start;
+	else
+		engine->emit_bb_start = gen8_emit_bb_start_noarb;
 }
 
-static void execlists_destroy(struct intel_engine_cs *engine)
+static void execlists_shutdown(struct intel_engine_cs *engine)
 {
+	/* Synchronise with residual timers and any softirq they raise */
+	del_timer_sync(&engine->execlists.timer);
+	del_timer_sync(&engine->execlists.preempt);
+	tasklet_kill(&engine->execlists.tasklet);
+}
+
+static void execlists_release(struct intel_engine_cs *engine)
+{
+	execlists_shutdown(engine);
+
 	intel_engine_cleanup_common(engine);
 	lrc_destroy_wa_ctx(engine);
-	kfree(engine);
 }
 
 static void
@@ -3727,13 +3917,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overriden by each engine. */
 
-	engine->destroy = execlists_destroy;
 	engine->resume = execlists_resume;
 
-	engine->reset.prepare = execlists_reset_prepare;
-	engine->reset.reset = execlists_reset;
-	engine->reset.finish = execlists_reset_finish;
-
 	engine->cops = &execlists_context_ops;
 	engine->request_alloc = execlists_request_alloc;
 
@@ -3756,10 +3941,6 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 		 * until a more refined solution exists.
 		 */
 	}
-	if (IS_GEN(engine->i915, 8))
-		engine->emit_bb_start = gen8_emit_bb_start;
-	else
-		engine->emit_bb_start = gen9_emit_bb_start;
 }
 
 static inline void
@@ -3803,6 +3984,11 @@ static void rcs_submission_override(struct intel_engine_cs *engine)
 
 int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
+	u32 base = engine->mmio_base;
+
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 	timer_setup(&engine->execlists.timer, execlists_timeslice, 0);
@@ -3814,21 +4000,6 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	if (engine->class == RENDER_CLASS)
 		rcs_submission_override(engine);
 
-	return 0;
-}
-
-int intel_execlists_submission_init(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct drm_i915_private *i915 = engine->i915;
-	struct intel_uncore *uncore = engine->uncore;
-	u32 base = engine->mmio_base;
-	int ret;
-
-	ret = intel_engine_init_common(engine);
-	if (ret)
-		return ret;
-
 	if (intel_init_workaround_bb(engine))
 		/*
 		 * We continue even if we fail to initialize WA batch
@@ -3860,6 +4031,9 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine)
 
 	reset_csb_pointers(engine);
 
+	/* Finally, take ownership and responsibility for cleanup! */
+	engine->release = execlists_release;
+
 	return 0;
 }
 
@@ -3899,18 +4073,21 @@ static u32 intel_lr_indirect_ctx_offset(const struct intel_engine_cs *engine)
 
 static void init_common_reg_state(u32 * const regs,
 				  const struct intel_engine_cs *engine,
-				  const struct intel_ring *ring)
+				  const struct intel_ring *ring,
+				  bool inhibit)
 {
-	regs[CTX_CONTEXT_CONTROL] =
-		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
-		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	u32 ctl;
+
+	ctl = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	if (inhibit)
+		ctl |= CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT;
 	if (INTEL_GEN(engine->i915) < 11)
-		regs[CTX_CONTEXT_CONTROL] |=
-			_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
-					    CTX_CTRL_RS_CTX_ENABLE);
+		ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
+					   CTX_CTRL_RS_CTX_ENABLE);
+	regs[CTX_CONTEXT_CONTROL] = ctl;
 
-	regs[CTX_RING_BUFFER_CONTROL] = RING_CTL_SIZE(ring->size) | RING_VALID;
-	regs[CTX_BB_STATE] = RING_BB_PPGTT;
+	regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
 }
 
 static void init_wa_bb_reg_state(u32 * const regs,
@@ -3966,7 +4143,7 @@ static void execlists_init_reg_state(u32 *regs,
 				     const struct intel_context *ce,
 				     const struct intel_engine_cs *engine,
 				     const struct intel_ring *ring,
-				     bool close)
+				     bool inhibit)
 {
 	/*
 	 * A context is actually a big batch buffer with several
@@ -3978,21 +4155,17 @@ static void execlists_init_reg_state(u32 *regs,
 	 *
 	 * Must keep consistent with virtual_update_register_offsets().
 	 */
-	u32 *bbe = set_offsets(regs, reg_offsets(engine), engine);
-
-	if (close) { /* Close the batch; used mainly by live_lrc_layout() */
-		*bbe = MI_BATCH_BUFFER_END;
-		if (INTEL_GEN(engine->i915) >= 10)
-			*bbe |= BIT(0);
-	}
+	set_offsets(regs, reg_offsets(engine), engine, inhibit);
 
-	init_common_reg_state(regs, engine, ring);
+	init_common_reg_state(regs, engine, ring, inhibit);
 	init_ppgtt_reg_state(regs, vm_alias(ce->vm));
 
 	init_wa_bb_reg_state(regs, engine,
 			     INTEL_GEN(engine->i915) >= 12 ?
 			     GEN12_CTX_BB_PER_CTX_PTR :
 			     CTX_BB_PER_CTX_PTR);
+
+	__reset_stop_ring(regs, engine);
 }
 
 static int
@@ -4003,7 +4176,6 @@ populate_lr_context(struct intel_context *ce,
 {
 	bool inhibit = true;
 	void *vaddr;
-	u32 *regs;
 	int ret;
 
 	vaddr = i915_gem_object_pin_map(ctx_obj, I915_MAP_WB);
@@ -4027,16 +4199,14 @@ populate_lr_context(struct intel_context *ce,
 
 		memcpy(vaddr, defaults, engine->context_size);
 		i915_gem_object_unpin_map(engine->default_state);
+		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 		inhibit = false;
 	}
 
 	/* The second page of the context object contains some fields which must
 	 * be set up prior to the first execution. */
-	regs = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	execlists_init_reg_state(regs, ce, engine, ring, inhibit);
-	if (inhibit)
-		regs[CTX_CONTEXT_CONTROL] |=
-			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
+	execlists_init_reg_state(vaddr + LRC_STATE_PN * PAGE_SIZE,
+				 ce, engine, ring, inhibit);
 
 	ret = 0;
 err_unpin_ctx:
@@ -4174,6 +4344,13 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 						ve->siblings[0]);
 }
 
+static int virtual_context_alloc(struct intel_context *ce)
+{
+	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
+
+	return __execlists_context_alloc(ce, ve->siblings[0]);
+}
+
 static int virtual_context_pin(struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
@@ -4211,6 +4388,8 @@ static void virtual_context_exit(struct intel_context *ce)
 }
 
 static const struct intel_context_ops virtual_context_ops = {
+	.alloc = virtual_context_alloc,
+
 	.pin = virtual_context_pin,
 	.unpin = execlists_context_unpin,
 
@@ -4237,10 +4416,9 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve)
 		mask = ve->siblings[0]->mask;
 	}
 
-	GEM_TRACE("%s: rq=%llx:%lld, mask=%x, prio=%d\n",
-		  ve->base.name,
-		  rq->fence.context, rq->fence.seqno,
-		  mask, ve->base.execlists.queue_priority_hint);
+	ENGINE_TRACE(&ve->base, "rq=%llx:%lld, mask=%x, prio=%d\n",
+		     rq->fence.context, rq->fence.seqno,
+		     mask, ve->base.execlists.queue_priority_hint);
 
 	return mask;
 }
@@ -4331,10 +4509,9 @@ static void virtual_submit_request(struct i915_request *rq)
 	struct i915_request *old;
 	unsigned long flags;
 
-	GEM_TRACE("%s: rq=%llx:%lld\n",
-		  ve->base.name,
-		  rq->fence.context,
-		  rq->fence.seqno);
+	ENGINE_TRACE(&ve->base, "rq=%llx:%lld\n",
+		     rq->fence.context,
+		     rq->fence.seqno);
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
@@ -4402,8 +4579,7 @@ virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 }
 
 struct intel_context *
-intel_execlists_create_virtual(struct i915_gem_context *ctx,
-			       struct intel_engine_cs **siblings,
+intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			       unsigned int count)
 {
 	struct virtual_engine *ve;
@@ -4414,13 +4590,13 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 		return ERR_PTR(-EINVAL);
 
 	if (count == 1)
-		return intel_context_create(ctx, siblings[0]);
+		return intel_context_create(siblings[0]);
 
 	ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL);
 	if (!ve)
 		return ERR_PTR(-ENOMEM);
 
-	ve->base.i915 = ctx->i915;
+	ve->base.i915 = siblings[0]->i915;
 	ve->base.gt = siblings[0]->gt;
 	ve->base.uncore = siblings[0]->uncore;
 	ve->base.id = -1;
@@ -4449,7 +4625,6 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
-
 	intel_engine_init_execlists(&ve->base);
 
 	ve->base.cops = &virtual_context_ops;
@@ -4465,7 +4640,7 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 		     virtual_submission_tasklet,
 		     (unsigned long)ve);
 
-	intel_context_init(&ve->context, ctx, &ve->base);
+	intel_context_init(&ve->context, &ve->base);
 
 	for (n = 0; n < count; n++) {
 		struct intel_engine_cs *sibling = siblings[n];
@@ -4532,12 +4707,6 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
 
-	err = __execlists_context_alloc(&ve->context, siblings[0]);
-	if (err)
-		goto err_put;
-
-	__set_bit(CONTEXT_ALLOC_BIT, &ve->context.flags);
-
 	return &ve->context;
 
 err_put:
@@ -4546,14 +4715,12 @@ err_put:
 }
 
 struct intel_context *
-intel_execlists_clone_virtual(struct i915_gem_context *ctx,
-			      struct intel_engine_cs *src)
+intel_execlists_clone_virtual(struct intel_engine_cs *src)
 {
 	struct virtual_engine *se = to_virtual_engine(src);
 	struct intel_context *dst;
 
-	dst = intel_execlists_create_virtual(ctx,
-					     se->siblings,
+	dst = intel_execlists_create_virtual(se->siblings,
 					     se->num_siblings);
 	if (IS_ERR(dst))
 		return dst;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 04511d8ebdc1..dfbc214e14f5 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -83,7 +83,6 @@ enum {
 void intel_logical_ring_cleanup(struct intel_engine_cs *engine);
 
 int intel_execlists_submission_setup(struct intel_engine_cs *engine);
-int intel_execlists_submission_init(struct intel_engine_cs *engine);
 
 /* Logical Ring Contexts */
 /* At the start of the context image is its per-process HWS page */
@@ -111,13 +110,11 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 				   unsigned int max);
 
 struct intel_context *
-intel_execlists_create_virtual(struct i915_gem_context *ctx,
-			       struct intel_engine_cs **siblings,
+intel_execlists_create_virtual(struct intel_engine_cs **siblings,
 			       unsigned int count);
 
 struct intel_context *
-intel_execlists_clone_virtual(struct i915_gem_context *ctx,
-			      struct intel_engine_cs *src);
+intel_execlists_clone_virtual(struct intel_engine_cs *src);
 
 int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
 				     const struct intel_engine_cs *master,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 06ab0276e10e..08a3be65f700 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -13,8 +13,8 @@
 #define CTX_CONTEXT_CONTROL		(0x02 + 1)
 #define CTX_RING_HEAD			(0x04 + 1)
 #define CTX_RING_TAIL			(0x06 + 1)
-#define CTX_RING_BUFFER_START		(0x08 + 1)
-#define CTX_RING_BUFFER_CONTROL		(0x0a + 1)
+#define CTX_RING_START			(0x08 + 1)
+#define CTX_RING_CTL			(0x0a + 1)
 #define CTX_BB_STATE			(0x10 + 1)
 #define CTX_BB_PER_CTX_PTR		(0x18 + 1)
 #define CTX_PDP3_UDW			(0x24 + 1)
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 2b977991b785..eeef90b55c64 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -127,7 +127,7 @@ struct drm_i915_mocs_table {
 		   LE_0_PAGETABLE | LE_TC_2_LLC_ELLC | LE_LRUM(3), \
 		   L3_3_WB)
 
-static const struct drm_i915_mocs_entry skylake_mocs_table[] = {
+static const struct drm_i915_mocs_entry skl_mocs_table[] = {
 	GEN9_MOCS_ENTRIES,
 	MOCS_ENTRY(I915_MOCS_CACHED,
 		   LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3),
@@ -233,7 +233,7 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
 		   LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), \
 		   L3_1_UC)
 
-static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
+static const struct drm_i915_mocs_entry tgl_mocs_table[] = {
 	/* Base - Error (Reserved for Non-Use) */
 	MOCS_ENTRY(0, 0x0, 0x0),
 	/* Base - Reserved */
@@ -267,7 +267,7 @@ static const struct drm_i915_mocs_entry tigerlake_mocs_table[] = {
 		   L3_3_WB),
 };
 
-static const struct drm_i915_mocs_entry icelake_mocs_table[] = {
+static const struct drm_i915_mocs_entry icl_mocs_table[] = {
 	/* Base - Uncached (Deprecated) */
 	MOCS_ENTRY(I915_MOCS_UNCACHED,
 		   LE_1_UC | LE_TC_1_LLC,
@@ -283,65 +283,42 @@ static const struct drm_i915_mocs_entry icelake_mocs_table[] = {
 static bool get_mocs_settings(const struct drm_i915_private *i915,
 			      struct drm_i915_mocs_table *table)
 {
-	bool result = false;
-
 	if (INTEL_GEN(i915) >= 12) {
-		table->size  = ARRAY_SIZE(tigerlake_mocs_table);
-		table->table = tigerlake_mocs_table;
+		table->size  = ARRAY_SIZE(tgl_mocs_table);
+		table->table = tgl_mocs_table;
 		table->n_entries = GEN11_NUM_MOCS_ENTRIES;
-		result = true;
 	} else if (IS_GEN(i915, 11)) {
-		table->size  = ARRAY_SIZE(icelake_mocs_table);
-		table->table = icelake_mocs_table;
+		table->size  = ARRAY_SIZE(icl_mocs_table);
+		table->table = icl_mocs_table;
 		table->n_entries = GEN11_NUM_MOCS_ENTRIES;
-		result = true;
 	} else if (IS_GEN9_BC(i915) || IS_CANNONLAKE(i915)) {
-		table->size  = ARRAY_SIZE(skylake_mocs_table);
+		table->size  = ARRAY_SIZE(skl_mocs_table);
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
-		table->table = skylake_mocs_table;
-		result = true;
+		table->table = skl_mocs_table;
 	} else if (IS_GEN9_LP(i915)) {
 		table->size  = ARRAY_SIZE(broxton_mocs_table);
 		table->n_entries = GEN9_NUM_MOCS_ENTRIES;
 		table->table = broxton_mocs_table;
-		result = true;
 	} else {
 		WARN_ONCE(INTEL_GEN(i915) >= 9,
 			  "Platform that should have a MOCS table does not.\n");
+		return false;
 	}
 
+	if (GEM_DEBUG_WARN_ON(table->size > table->n_entries))
+		return false;
+
 	/* WaDisableSkipCaching:skl,bxt,kbl,glk */
 	if (IS_GEN(i915, 9)) {
 		int i;
 
 		for (i = 0; i < table->size; i++)
-			if (WARN_ON(table->table[i].l3cc_value &
-				    (L3_ESC(1) | L3_SCC(0x7))))
+			if (GEM_DEBUG_WARN_ON(table->table[i].l3cc_value &
+					      (L3_ESC(1) | L3_SCC(0x7))))
 				return false;
 	}
 
-	return result;
-}
-
-static i915_reg_t mocs_register(const struct intel_engine_cs *engine, int index)
-{
-	switch (engine->id) {
-	case RCS0:
-		return GEN9_GFX_MOCS(index);
-	case VCS0:
-		return GEN9_MFX0_MOCS(index);
-	case BCS0:
-		return GEN9_BLT_MOCS(index);
-	case VECS0:
-		return GEN9_VEBOX_MOCS(index);
-	case VCS1:
-		return GEN9_MFX1_MOCS(index);
-	case VCS2:
-		return GEN11_MFX2_MOCS(index);
-	default:
-		MISSING_CASE(engine->id);
-		return INVALID_MMIO_REG;
-	}
+	return true;
 }
 
 /*
@@ -351,29 +328,47 @@ static i915_reg_t mocs_register(const struct intel_engine_cs *engine, int index)
 static u32 get_entry_control(const struct drm_i915_mocs_table *table,
 			     unsigned int index)
 {
-	if (table->table[index].used)
+	if (index < table->size && table->table[index].used)
 		return table->table[index].control_value;
 
 	return table->table[I915_MOCS_PTE].control_value;
 }
 
-static void init_mocs_table(struct intel_engine_cs *engine,
-			    const struct drm_i915_mocs_table *table)
+#define for_each_mocs(mocs, t, i) \
+	for (i = 0; \
+	     i < (t)->n_entries ? (mocs = get_entry_control((t), i)), 1 : 0;\
+	     i++)
+
+static void __init_mocs_table(struct intel_uncore *uncore,
+			      const struct drm_i915_mocs_table *table,
+			      u32 addr)
 {
-	struct intel_uncore *uncore = engine->uncore;
-	u32 unused_value = table->table[I915_MOCS_PTE].control_value;
 	unsigned int i;
+	u32 mocs;
+
+	for_each_mocs(mocs, table, i)
+		intel_uncore_write_fw(uncore, _MMIO(addr + i * 4), mocs);
+}
 
-	for (i = 0; i < table->size; i++)
-		intel_uncore_write_fw(uncore,
-				      mocs_register(engine, i),
-				      get_entry_control(table, i));
+static u32 mocs_offset(const struct intel_engine_cs *engine)
+{
+	static const u32 offset[] = {
+		[RCS0]  =  __GEN9_RCS0_MOCS0,
+		[VCS0]  =  __GEN9_VCS0_MOCS0,
+		[VCS1]  =  __GEN9_VCS1_MOCS0,
+		[VECS0] =  __GEN9_VECS0_MOCS0,
+		[BCS0]  =  __GEN9_BCS0_MOCS0,
+		[VCS2]  = __GEN11_VCS2_MOCS0,
+	};
+
+	GEM_BUG_ON(engine->id >= ARRAY_SIZE(offset));
+	return offset[engine->id];
+}
 
-	/* All remaining entries are unused */
-	for (; i < table->n_entries; i++)
-		intel_uncore_write_fw(uncore,
-				      mocs_register(engine, i),
-				      unused_value);
+static void init_mocs_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table)
+{
+	__init_mocs_table(engine->uncore, table, mocs_offset(engine));
 }
 
 /*
@@ -383,51 +378,34 @@ static void init_mocs_table(struct intel_engine_cs *engine,
 static u16 get_entry_l3cc(const struct drm_i915_mocs_table *table,
 			  unsigned int index)
 {
-	if (table->table[index].used)
+	if (index < table->size && table->table[index].used)
 		return table->table[index].l3cc_value;
 
 	return table->table[I915_MOCS_PTE].l3cc_value;
 }
 
-static inline u32 l3cc_combine(const struct drm_i915_mocs_table *table,
-			       u16 low,
-			       u16 high)
+static inline u32 l3cc_combine(u16 low, u16 high)
 {
 	return low | (u32)high << 16;
 }
 
+#define for_each_l3cc(l3cc, t, i) \
+	for (i = 0; \
+	     i < ((t)->n_entries + 1) / 2 ? \
+	     (l3cc = l3cc_combine(get_entry_l3cc((t), 2 * i), \
+				  get_entry_l3cc((t), 2 * i + 1))), 1 : \
+	     0; \
+	     i++)
+
 static void init_l3cc_table(struct intel_engine_cs *engine,
 			    const struct drm_i915_mocs_table *table)
 {
 	struct intel_uncore *uncore = engine->uncore;
-	u16 unused_value = table->table[I915_MOCS_PTE].l3cc_value;
 	unsigned int i;
+	u32 l3cc;
 
-	for (i = 0; i < table->size / 2; i++) {
-		u16 low = get_entry_l3cc(table, 2 * i);
-		u16 high = get_entry_l3cc(table, 2 * i + 1);
-
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(table, low, high));
-	}
-
-	/* Odd table size - 1 left over */
-	if (table->size & 1) {
-		u16 low = get_entry_l3cc(table, 2 * i);
-
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(table, low, unused_value));
-		i++;
-	}
-
-	/* All remaining entries are also unused */
-	for (; i < table->n_entries / 2; i++)
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(table, unused_value,
-						unused_value));
+	for_each_l3cc(l3cc, table, i)
+		intel_uncore_write_fw(uncore, GEN9_LNCFCMOCS(i), l3cc);
 }
 
 void intel_mocs_init_engine(struct intel_engine_cs *engine)
@@ -448,11 +426,14 @@ void intel_mocs_init_engine(struct intel_engine_cs *engine)
 		init_l3cc_table(engine, &table);
 }
 
-static void intel_mocs_init_global(struct intel_gt *gt)
+static u32 global_mocs_offset(void)
+{
+	return i915_mmio_reg_offset(GEN12_GLOBAL_MOCS(0));
+}
+
+static void init_global_mocs(struct intel_gt *gt)
 {
-	struct intel_uncore *uncore = gt->uncore;
 	struct drm_i915_mocs_table table;
-	unsigned int index;
 
 	/*
 	 * LLC and eDRAM control values are not applicable to dgfx
@@ -460,32 +441,18 @@ static void intel_mocs_init_global(struct intel_gt *gt)
 	if (IS_DGFX(gt->i915))
 		return;
 
-	GEM_BUG_ON(!HAS_GLOBAL_MOCS_REGISTERS(gt->i915));
-
 	if (!get_mocs_settings(gt->i915, &table))
 		return;
 
-	if (GEM_DEBUG_WARN_ON(table.size > table.n_entries))
-		return;
-
-	for (index = 0; index < table.size; index++)
-		intel_uncore_write(uncore,
-				   GEN12_GLOBAL_MOCS(index),
-				   table.table[index].control_value);
-
-	/*
-	 * Ok, now set the unused entries to the invalid entry (index 0). These
-	 * entries are officially undefined and no contract for the contents and
-	 * settings is given for these entries.
-	 */
-	for (; index < table.n_entries; index++)
-		intel_uncore_write(uncore,
-				   GEN12_GLOBAL_MOCS(index),
-				   table.table[0].control_value);
+	__init_mocs_table(gt->uncore, &table, global_mocs_offset());
 }
 
 void intel_mocs_init(struct intel_gt *gt)
 {
 	if (HAS_GLOBAL_MOCS_REGISTERS(gt->i915))
-		intel_mocs_init_global(gt);
+		init_global_mocs(gt);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_mocs.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
new file mode 100644
index 000000000000..f86f7e68ce5e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+#include <linux/slab.h>
+
+#include "i915_trace.h"
+#include "intel_gtt.h"
+#include "gen6_ppgtt.h"
+#include "gen8_ppgtt.h"
+
+struct i915_page_table *alloc_pt(struct i915_address_space *vm)
+{
+	struct i915_page_table *pt;
+
+	pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL);
+	if (unlikely(!pt))
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(setup_page_dma(vm, &pt->base))) {
+		kfree(pt);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	atomic_set(&pt->used, 0);
+	return pt;
+}
+
+struct i915_page_directory *__alloc_pd(size_t sz)
+{
+	struct i915_page_directory *pd;
+
+	pd = kzalloc(sz, I915_GFP_ALLOW_FAIL);
+	if (unlikely(!pd))
+		return NULL;
+
+	spin_lock_init(&pd->lock);
+	return pd;
+}
+
+struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
+{
+	struct i915_page_directory *pd;
+
+	pd = __alloc_pd(sizeof(*pd));
+	if (unlikely(!pd))
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
+		kfree(pd);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return pd;
+}
+
+void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd)
+{
+	cleanup_page_dma(vm, pd);
+	kfree(pd);
+}
+
+static inline void
+write_dma_entry(struct i915_page_dma * const pdma,
+		const unsigned short idx,
+		const u64 encoded_entry)
+{
+	u64 * const vaddr = kmap_atomic(pdma->page);
+
+	vaddr[idx] = encoded_entry;
+	kunmap_atomic(vaddr);
+}
+
+void
+__set_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       struct i915_page_dma * const to,
+	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
+{
+	/* Each thread pre-pins the pd, and we may have a thread per pde. */
+	GEM_BUG_ON(atomic_read(px_used(pd)) > NALLOC * ARRAY_SIZE(pd->entry));
+
+	atomic_inc(px_used(pd));
+	pd->entry[idx] = to;
+	write_dma_entry(px_base(pd), idx, encode(to->daddr, I915_CACHE_LLC));
+}
+
+void
+clear_pd_entry(struct i915_page_directory * const pd,
+	       const unsigned short idx,
+	       const struct i915_page_scratch * const scratch)
+{
+	GEM_BUG_ON(atomic_read(px_used(pd)) == 0);
+
+	write_dma_entry(px_base(pd), idx, scratch->encode);
+	pd->entry[idx] = NULL;
+	atomic_dec(px_used(pd));
+}
+
+bool
+release_pd_entry(struct i915_page_directory * const pd,
+		 const unsigned short idx,
+		 struct i915_page_table * const pt,
+		 const struct i915_page_scratch * const scratch)
+{
+	bool free = false;
+
+	if (atomic_add_unless(&pt->used, -1, 1))
+		return false;
+
+	spin_lock(&pd->lock);
+	if (atomic_dec_and_test(&pt->used)) {
+		clear_pd_entry(pd, idx, scratch);
+		free = true;
+	}
+	spin_unlock(&pd->lock);
+
+	return free;
+}
+
+int i915_ppgtt_init_hw(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+
+	gtt_write_workarounds(gt);
+
+	if (IS_GEN(i915, 6))
+		gen6_ppgtt_enable(gt);
+	else if (IS_GEN(i915, 7))
+		gen7_ppgtt_enable(gt);
+
+	return 0;
+}
+
+static struct i915_ppgtt *
+__ppgtt_create(struct intel_gt *gt)
+{
+	if (INTEL_GEN(gt->i915) < 8)
+		return gen6_ppgtt_create(gt);
+	else
+		return gen8_ppgtt_create(gt);
+}
+
+struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt)
+{
+	struct i915_ppgtt *ppgtt;
+
+	ppgtt = __ppgtt_create(gt);
+	if (IS_ERR(ppgtt))
+		return ppgtt;
+
+	trace_i915_ppgtt_create(&ppgtt->vm);
+
+	return ppgtt;
+}
+
+static int ppgtt_bind_vma(struct i915_vma *vma,
+			  enum i915_cache_level cache_level,
+			  u32 flags)
+{
+	u32 pte_flags;
+	int err;
+
+	if (flags & I915_VMA_ALLOC) {
+		err = vma->vm->allocate_va_range(vma->vm,
+						 vma->node.start, vma->size);
+		if (err)
+			return err;
+
+		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
+	}
+
+	/* Applicable to VLV, and gen8+ */
+	pte_flags = 0;
+	if (i915_gem_object_is_readonly(vma->obj))
+		pte_flags |= PTE_READ_ONLY;
+
+	GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)));
+	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+	wmb();
+
+	return 0;
+}
+
+static void ppgtt_unbind_vma(struct i915_vma *vma)
+{
+	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)))
+		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
+}
+
+int ppgtt_set_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(vma->pages);
+
+	vma->pages = vma->obj->mm.pages;
+
+	vma->page_sizes = vma->obj->mm.page_sizes;
+
+	return 0;
+}
+
+void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+
+	ppgtt->vm.gt = gt;
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.dma = &i915->drm.pdev->dev;
+	ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size);
+
+	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
+
+	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
+	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 700104b90163..9e303c29d6e3 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -88,21 +88,18 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 	 * do not want the enable hysteresis to less than the wakeup latency.
 	 *
 	 * igt/gem_exec_nop/sequential provides a rough estimate for the
-	 * service latency, and puts it around 10us for Broadwell (and other
-	 * big core) and around 40us for Broxton (and other low power cores).
-	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
-	 * However, the wakeup latency on Broxton is closer to 100us. To be
-	 * conservative, we have to factor in a context switch on top (due
-	 * to ksoftirqd).
+	 * service latency, and puts it under 10us for Icelake, similar to
+	 * Broadwell+, To be conservative, we want to factor in a context
+	 * switch on top (due to ksoftirqd).
 	 */
-	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
-	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
+	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 60);
+	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 60);
 
 	/* 3a: Enable RC6 */
-	set(uncore, GEN6_RC_CONTROL,
-	    GEN6_RC_CTL_HW_ENABLE |
-	    GEN6_RC_CTL_RC6_ENABLE |
-	    GEN6_RC_CTL_EI_MODE(1));
+	rc6->ctl_enable =
+		GEN6_RC_CTL_HW_ENABLE |
+		GEN6_RC_CTL_RC6_ENABLE |
+		GEN6_RC_CTL_EI_MODE(1);
 
 	set(uncore, GEN9_PG_ENABLE,
 	    GEN9_RENDER_PG_ENABLE |
@@ -173,10 +170,10 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	else
 		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
 
-	set(uncore, GEN6_RC_CONTROL,
-	    GEN6_RC_CTL_HW_ENABLE |
-	    GEN6_RC_CTL_RC6_ENABLE |
-	    rc6_mode);
+	rc6->ctl_enable =
+		GEN6_RC_CTL_HW_ENABLE |
+		GEN6_RC_CTL_RC6_ENABLE |
+		rc6_mode;
 
 	/*
 	 * WaRsDisableCoarsePowerGating:skl,cnl
@@ -203,10 +200,10 @@ static void gen8_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
 
 	/* 3: Enable RC6 */
-	set(uncore, GEN6_RC_CONTROL,
+	rc6->ctl_enable =
 	    GEN6_RC_CTL_HW_ENABLE |
 	    GEN7_RC_CTL_TO_MODE |
-	    GEN6_RC_CTL_RC6_ENABLE);
+	    GEN6_RC_CTL_RC6_ENABLE;
 }
 
 static void gen6_rc6_enable(struct intel_rc6 *rc6)
@@ -242,10 +239,10 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6)
 		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
 	if (HAS_RC6pp(i915))
 		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
-	set(uncore, GEN6_RC_CONTROL,
+	rc6->ctl_enable =
 	    rc6_mask |
 	    GEN6_RC_CTL_EI_MODE(1) |
-	    GEN6_RC_CTL_HW_ENABLE);
+	    GEN6_RC_CTL_HW_ENABLE;
 
 	rc6vids = 0;
 	ret = sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS,
@@ -363,7 +360,7 @@ static void chv_rc6_enable(struct intel_rc6 *rc6)
 			       VLV_RENDER_RC6_COUNT_EN));
 
 	/* 3: Enable RC6 */
-	set(uncore, GEN6_RC_CONTROL, GEN7_RC_CTL_TO_MODE);
+	rc6->ctl_enable = GEN7_RC_CTL_TO_MODE;
 }
 
 static void vlv_rc6_enable(struct intel_rc6 *rc6)
@@ -389,8 +386,8 @@ static void vlv_rc6_enable(struct intel_rc6 *rc6)
 			       VLV_MEDIA_RC6_COUNT_EN |
 			       VLV_RENDER_RC6_COUNT_EN));
 
-	set(uncore, GEN6_RC_CONTROL,
-	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL);
+	rc6->ctl_enable =
+	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
 }
 
 static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
@@ -491,64 +488,19 @@ static void rpm_put(struct intel_rc6 *rc6)
 	rc6->wakeref = false;
 }
 
-static bool intel_rc6_ctx_corrupted(struct intel_rc6 *rc6)
-{
-	return !intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO);
-}
-
-static void intel_rc6_ctx_wa_init(struct intel_rc6 *rc6)
+static bool pctx_corrupted(struct intel_rc6 *rc6)
 {
 	struct drm_i915_private *i915 = rc6_to_i915(rc6);
 
 	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
-		return;
-
-	if (intel_rc6_ctx_corrupted(rc6)) {
-		DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
-		rc6->ctx_corrupted = true;
-	}
-}
-
-/**
- * intel_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
- * @rc6: rc6 state
- *
- * Perform any steps needed to re-init the RC6 CTX WA after system resume.
- */
-void intel_rc6_ctx_wa_resume(struct intel_rc6 *rc6)
-{
-	if (rc6->ctx_corrupted && !intel_rc6_ctx_corrupted(rc6)) {
-		DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
-		rc6->ctx_corrupted = false;
-	}
-}
-
-/**
- * intel_rc6_ctx_wa_check - check for a new RC6 CTX corruption
- * @rc6: rc6 state
- *
- * Check if an RC6 CTX corruption has happened since the last check and if so
- * disable RC6 and runtime power management.
-*/
-void intel_rc6_ctx_wa_check(struct intel_rc6 *rc6)
-{
-	struct drm_i915_private *i915 = rc6_to_i915(rc6);
-
-	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
-		return;
-
-	if (rc6->ctx_corrupted)
-		return;
-
-	if (!intel_rc6_ctx_corrupted(rc6))
-		return;
-
-	DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+		return false;
 
-	intel_rc6_disable(rc6);
-	rc6->ctx_corrupted = true;
+	if (intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO))
+		return false;
 
-	return;
+	dev_notice(i915->drm.dev,
+		   "RC6 context corruption, disabling runtime power management\n");
+	return true;
 }
 
 static void __intel_rc6_disable(struct intel_rc6 *rc6)
@@ -575,8 +527,6 @@ void intel_rc6_init(struct intel_rc6 *rc6)
 	if (!rc6_supported(rc6))
 		return;
 
-	intel_rc6_ctx_wa_init(rc6);
-
 	if (IS_CHERRYVIEW(i915))
 		err = chv_rc6_init(rc6);
 	else if (IS_VALLEYVIEW(i915))
@@ -611,9 +561,6 @@ void intel_rc6_enable(struct intel_rc6 *rc6)
 
 	GEM_BUG_ON(rc6->enabled);
 
-	if (rc6->ctx_corrupted)
-		return;
-
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	if (IS_CHERRYVIEW(i915))
@@ -629,13 +576,51 @@ void intel_rc6_enable(struct intel_rc6 *rc6)
 	else if (INTEL_GEN(i915) >= 6)
 		gen6_rc6_enable(rc6);
 
+	rc6->manual = rc6->ctl_enable & GEN6_RC_CTL_RC6_ENABLE;
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		rc6->ctl_enable = 0;
+
 	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
 
+	if (unlikely(pctx_corrupted(rc6)))
+		return;
+
 	/* rc6 is ready, runtime-pm is go! */
 	rpm_put(rc6);
 	rc6->enabled = true;
 }
 
+void intel_rc6_unpark(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+
+	if (!rc6->enabled)
+		return;
+
+	/* Restore HW timers for automatic RC6 entry while busy */
+	set(uncore, GEN6_RC_CONTROL, rc6->ctl_enable);
+}
+
+void intel_rc6_park(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+
+	if (!rc6->enabled)
+		return;
+
+	if (unlikely(pctx_corrupted(rc6))) {
+		intel_rc6_disable(rc6);
+		return;
+	}
+
+	if (!rc6->manual)
+		return;
+
+	/* Turn off the HW timers and go directly to rc6 */
+	set(uncore, GEN6_RC_CONTROL, GEN6_RC_CTL_RC6_ENABLE);
+	set(uncore, GEN6_RC_STATE, 0x4 << RC_SW_TARGET_STATE_SHIFT);
+}
+
 void intel_rc6_disable(struct intel_rc6 *rc6)
 {
 	if (!rc6->enabled)
@@ -785,3 +770,7 @@ u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg)
 {
 	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_rc6.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h
index 1370f6834a4c..9f0f23fca8af 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.h
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.h
@@ -15,6 +15,9 @@ struct intel_rc6;
 void intel_rc6_init(struct intel_rc6 *rc6);
 void intel_rc6_fini(struct intel_rc6 *rc6);
 
+void intel_rc6_unpark(struct intel_rc6 *rc6);
+void intel_rc6_park(struct intel_rc6 *rc6);
+
 void intel_rc6_sanitize(struct intel_rc6 *rc6);
 void intel_rc6_enable(struct intel_rc6 *rc6);
 void intel_rc6_disable(struct intel_rc6 *rc6);
@@ -22,7 +25,4 @@ void intel_rc6_disable(struct intel_rc6 *rc6);
 u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, i915_reg_t reg);
 u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg);
 
-void intel_rc6_ctx_wa_check(struct intel_rc6 *rc6);
-void intel_rc6_ctx_wa_resume(struct intel_rc6 *rc6);
-
 #endif /* INTEL_RC6_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
index 89ad5697a8d4..bfbb623f7a4f 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
@@ -18,12 +18,14 @@ struct intel_rc6 {
 	u64 prev_hw_residency[4];
 	u64 cur_residency[4];
 
+	u32 ctl_enable;
+
 	struct drm_i915_gem_object *pctx;
 
 	bool supported : 1;
 	bool enabled : 1;
+	bool manual : 1;
 	bool wakeref : 1;
-	bool ctx_corrupted : 1;
 };
 
 #endif /* INTEL_RC6_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index c4edc35e7d89..5954ecc3207f 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -29,16 +29,6 @@
 #include "intel_renderstate.h"
 #include "intel_ring.h"
 
-struct intel_renderstate {
-	const struct intel_renderstate_rodata *rodata;
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-	u32 batch_offset;
-	u32 batch_size;
-	u32 aux_offset;
-	u32 aux_size;
-};
-
 static const struct intel_renderstate_rodata *
 render_state_get_rodata(const struct intel_engine_cs *engine)
 {
@@ -84,11 +74,11 @@ static int render_state_setup(struct intel_renderstate *so,
 	u32 *d;
 	int ret;
 
-	ret = i915_gem_object_prepare_write(so->obj, &needs_clflush);
+	ret = i915_gem_object_prepare_write(so->vma->obj, &needs_clflush);
 	if (ret)
 		return ret;
 
-	d = kmap_atomic(i915_gem_object_get_dirty_page(so->obj, 0));
+	d = kmap_atomic(i915_gem_object_get_dirty_page(so->vma->obj, 0));
 
 	while (i < rodata->batch_items) {
 		u32 s = rodata->batch[i];
@@ -166,7 +156,7 @@ static int render_state_setup(struct intel_renderstate *so,
 
 	ret = 0;
 out:
-	i915_gem_object_finish_access(so->obj);
+	i915_gem_object_finish_access(so->vma->obj);
 	return ret;
 
 err:
@@ -177,61 +167,84 @@ err:
 
 #undef OUT_BATCH
 
-int intel_renderstate_emit(struct i915_request *rq)
+int intel_renderstate_init(struct intel_renderstate *so,
+			   struct intel_engine_cs *engine)
 {
-	struct intel_engine_cs *engine = rq->engine;
-	struct intel_renderstate so = {}; /* keep the compiler happy */
+	struct drm_i915_gem_object *obj;
 	int err;
 
-	so.rodata = render_state_get_rodata(engine);
-	if (!so.rodata)
+	memset(so, 0, sizeof(*so));
+
+	so->rodata = render_state_get_rodata(engine);
+	if (!so->rodata)
 		return 0;
 
-	if (so.rodata->batch_items * 4 > PAGE_SIZE)
+	if (so->rodata->batch_items * 4 > PAGE_SIZE)
 		return -EINVAL;
 
-	so.obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
-	if (IS_ERR(so.obj))
-		return PTR_ERR(so.obj);
+	obj = i915_gem_object_create_internal(engine->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
-	so.vma = i915_vma_instance(so.obj, &engine->gt->ggtt->vm, NULL);
-	if (IS_ERR(so.vma)) {
-		err = PTR_ERR(so.vma);
+	so->vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
+	if (IS_ERR(so->vma)) {
+		err = PTR_ERR(so->vma);
 		goto err_obj;
 	}
 
-	err = i915_vma_pin(so.vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	err = i915_vma_pin(so->vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
 		goto err_vma;
 
-	err = render_state_setup(&so, rq->i915);
+	err = render_state_setup(so, engine->i915);
 	if (err)
 		goto err_unpin;
 
+	return 0;
+
+err_unpin:
+	i915_vma_unpin(so->vma);
+err_vma:
+	i915_vma_close(so->vma);
+err_obj:
+	i915_gem_object_put(obj);
+	so->vma = NULL;
+	return err;
+}
+
+int intel_renderstate_emit(struct intel_renderstate *so,
+			   struct i915_request *rq)
+{
+	struct intel_engine_cs *engine = rq->engine;
+	int err;
+
+	if (!so->vma)
+		return 0;
+
 	err = engine->emit_bb_start(rq,
-				    so.batch_offset, so.batch_size,
+				    so->batch_offset, so->batch_size,
 				    I915_DISPATCH_SECURE);
 	if (err)
-		goto err_unpin;
+		return err;
 
-	if (so.aux_size > 8) {
+	if (so->aux_size > 8) {
 		err = engine->emit_bb_start(rq,
-					    so.aux_offset, so.aux_size,
+					    so->aux_offset, so->aux_size,
 					    I915_DISPATCH_SECURE);
 		if (err)
-			goto err_unpin;
+			return err;
 	}
 
-	i915_vma_lock(so.vma);
-	err = i915_request_await_object(rq, so.vma->obj, false);
+	i915_vma_lock(so->vma);
+	err = i915_request_await_object(rq, so->vma->obj, false);
 	if (err == 0)
-		err = i915_vma_move_to_active(so.vma, rq, 0);
-	i915_vma_unlock(so.vma);
-err_unpin:
-	i915_vma_unpin(so.vma);
-err_vma:
-	i915_vma_close(so.vma);
-err_obj:
-	i915_gem_object_put(so.obj);
+		err = i915_vma_move_to_active(so->vma, rq, 0);
+	i915_vma_unlock(so->vma);
+
 	return err;
 }
+
+void intel_renderstate_fini(struct intel_renderstate *so)
+{
+	i915_vma_unpin_and_release(&so->vma, 0);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.h b/drivers/gpu/drm/i915/gt/intel_renderstate.h
index 8d5079145054..5700be69a05a 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.h
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.h
@@ -27,6 +27,8 @@
 #include <linux/types.h>
 
 struct i915_request;
+struct intel_engine_cs;
+struct i915_vma;
 
 struct intel_renderstate_rodata {
 	const u32 *reloc;
@@ -46,6 +48,19 @@ extern const struct intel_renderstate_rodata gen7_null_state;
 extern const struct intel_renderstate_rodata gen8_null_state;
 extern const struct intel_renderstate_rodata gen9_null_state;
 
-int intel_renderstate_emit(struct i915_request *rq);
+struct intel_renderstate {
+	const struct intel_renderstate_rodata *rodata;
+	struct i915_vma *vma;
+	u32 batch_offset;
+	u32 batch_size;
+	u32 aux_offset;
+	u32 aux_size;
+};
+
+int intel_renderstate_init(struct intel_renderstate *so,
+			   struct intel_engine_cs *engine);
+int intel_renderstate_emit(struct intel_renderstate *so,
+			   struct i915_request *rq);
+void intel_renderstate_fini(struct intel_renderstate *so);
 
 #endif /* _INTEL_RENDERSTATE_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index c97423a76642..beee0cf89bce 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -21,6 +21,7 @@
 #include "intel_reset.h"
 
 #include "uc/intel_guc.h"
+#include "uc/intel_guc_submission.h"
 
 #define RESET_MAX_RETRIES 3
 
@@ -40,27 +41,29 @@ static void rmw_clear_fw(struct intel_uncore *uncore, i915_reg_t reg, u32 clr)
 static void engine_skip_context(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	struct i915_gem_context *hung_ctx = rq->gem_context;
+	struct intel_context *hung_ctx = rq->context;
 
 	if (!i915_request_is_active(rq))
 		return;
 
 	lockdep_assert_held(&engine->active.lock);
 	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
-		if (rq->gem_context == hung_ctx)
+		if (rq->context == hung_ctx)
 			i915_request_skip(rq, -EIO);
 }
 
-static void client_mark_guilty(struct drm_i915_file_private *file_priv,
-			       const struct i915_gem_context *ctx)
+static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
 {
-	unsigned int score;
+	struct drm_i915_file_private *file_priv = ctx->file_priv;
 	unsigned long prev_hang;
+	unsigned int score;
+
+	if (IS_ERR_OR_NULL(file_priv))
+		return;
 
-	if (i915_gem_context_is_banned(ctx))
+	score = 0;
+	if (banned)
 		score = I915_CLIENT_SCORE_CONTEXT_BAN;
-	else
-		score = 0;
 
 	prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
 	if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
@@ -75,17 +78,38 @@ static void client_mark_guilty(struct drm_i915_file_private *file_priv,
 	}
 }
 
-static bool context_mark_guilty(struct i915_gem_context *ctx)
+static bool mark_guilty(struct i915_request *rq)
 {
+	struct i915_gem_context *ctx;
 	unsigned long prev_hang;
 	bool banned;
 	int i;
 
+	rcu_read_lock();
+	ctx = rcu_dereference(rq->context->gem_context);
+	if (ctx && !kref_get_unless_zero(&ctx->ref))
+		ctx = NULL;
+	rcu_read_unlock();
+	if (!ctx)
+		return false;
+
+	if (i915_gem_context_is_closed(ctx)) {
+		intel_context_set_banned(rq->context);
+		banned = true;
+		goto out;
+	}
+
 	atomic_inc(&ctx->guilty_count);
 
 	/* Cool contexts are too cool to be banned! (Used for reset testing.) */
-	if (!i915_gem_context_is_bannable(ctx))
-		return false;
+	if (!i915_gem_context_is_bannable(ctx)) {
+		banned = false;
+		goto out;
+	}
+
+	dev_notice(ctx->i915->drm.dev,
+		   "%s context reset due to GPU hang\n",
+		   ctx->name);
 
 	/* Record the timestamp for the last N hangs */
 	prev_hang = ctx->hang_timestamp[0];
@@ -100,38 +124,43 @@ static bool context_mark_guilty(struct i915_gem_context *ctx)
 	if (banned) {
 		DRM_DEBUG_DRIVER("context %s: guilty %d, banned\n",
 				 ctx->name, atomic_read(&ctx->guilty_count));
-		i915_gem_context_set_banned(ctx);
+		intel_context_set_banned(rq->context);
 	}
 
-	if (!IS_ERR_OR_NULL(ctx->file_priv))
-		client_mark_guilty(ctx->file_priv, ctx);
+	client_mark_guilty(ctx, banned);
 
+out:
+	i915_gem_context_put(ctx);
 	return banned;
 }
 
-static void context_mark_innocent(struct i915_gem_context *ctx)
+static void mark_innocent(struct i915_request *rq)
 {
-	atomic_inc(&ctx->active_count);
+	struct i915_gem_context *ctx;
+
+	rcu_read_lock();
+	ctx = rcu_dereference(rq->context->gem_context);
+	if (ctx)
+		atomic_inc(&ctx->active_count);
+	rcu_read_unlock();
 }
 
 void __i915_request_reset(struct i915_request *rq, bool guilty)
 {
-	GEM_TRACE("%s rq=%llx:%lld, guilty? %s\n",
-		  rq->engine->name,
-		  rq->fence.context,
-		  rq->fence.seqno,
-		  yesno(guilty));
+	RQ_TRACE(rq, "guilty? %s\n", yesno(guilty));
 
 	GEM_BUG_ON(i915_request_completed(rq));
 
+	rcu_read_lock(); /* protect the GEM context */
 	if (guilty) {
 		i915_request_skip(rq, -EIO);
-		if (context_mark_guilty(rq->gem_context))
+		if (mark_guilty(rq))
 			engine_skip_context(rq);
 	} else {
 		dma_fence_set_error(&rq->fence, -EAGAIN);
-		context_mark_innocent(rq->gem_context);
+		mark_innocent(rq);
 	}
+	rcu_read_unlock();
 }
 
 static bool i915_in_reset(struct pci_dev *pdev)
@@ -218,9 +247,8 @@ out:
 	return ret;
 }
 
-static int ironlake_do_reset(struct intel_gt *gt,
-			     intel_engine_mask_t engine_mask,
-			     unsigned int retry)
+static int ilk_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask,
+			unsigned int retry)
 {
 	struct intel_uncore *uncore = gt->uncore;
 	int ret;
@@ -564,7 +592,7 @@ static reset_func intel_get_gpu_reset(const struct intel_gt *gt)
 	else if (INTEL_GEN(i915) >= 6)
 		return gen6_reset_engines;
 	else if (INTEL_GEN(i915) >= 5)
-		return ironlake_do_reset;
+		return ilk_do_reset;
 	else if (IS_G4X(i915))
 		return g4x_do_reset;
 	else if (IS_G33(i915) || IS_PINEVIEW(i915))
@@ -592,7 +620,7 @@ int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 	 */
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	for (retry = 0; ret == -ETIMEDOUT && retry < retries; retry++) {
-		GEM_TRACE("engine_mask=%x\n", engine_mask);
+		GT_TRACE(gt, "engine_mask=%x\n", engine_mask);
 		preempt_disable();
 		ret = reset(gt, engine_mask, retry);
 		preempt_enable();
@@ -647,7 +675,8 @@ static void reset_prepare_engine(struct intel_engine_cs *engine)
 	 * GPU state upon resume, i.e. fail to restart after a reset.
 	 */
 	intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL);
-	engine->reset.prepare(engine);
+	if (engine->reset.prepare)
+		engine->reset.prepare(engine);
 }
 
 static void revoke_mmaps(struct intel_gt *gt)
@@ -667,8 +696,13 @@ static void revoke_mmaps(struct intel_gt *gt)
 			continue;
 
 		GEM_BUG_ON(vma->fence != &gt->ggtt->fence_regs[i]);
-		node = &vma->obj->base.vma_node;
+
+		if (!vma->mmo)
+			continue;
+
+		node = &vma->mmo->vma_node;
 		vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
+
 		unmap_mapping_range(gt->i915->drm.anon_inode->i_mapping,
 				    drm_vma_node_offset_addr(node) + vma_offset,
 				    vma->size,
@@ -722,10 +756,11 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 
 static void reset_finish_engine(struct intel_engine_cs *engine)
 {
-	engine->reset.finish(engine);
+	if (engine->reset.finish)
+		engine->reset.finish(engine);
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 
-	intel_engine_breadcrumbs_irq(engine);
+	intel_engine_signal_breadcrumbs(engine);
 }
 
 static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
@@ -745,8 +780,7 @@ static void nop_submit_request(struct i915_request *request)
 	struct intel_engine_cs *engine = request->engine;
 	unsigned long flags;
 
-	GEM_TRACE("%s fence %llx:%lld -> -EIO\n",
-		  engine->name, request->fence.context, request->fence.seqno);
+	RQ_TRACE(request, "-EIO\n");
 	dma_fence_set_error(&request->fence, -EIO);
 
 	spin_lock_irqsave(&engine->active.lock, flags);
@@ -754,7 +788,7 @@ static void nop_submit_request(struct i915_request *request)
 	i915_request_mark_complete(request);
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 
-	intel_engine_queue_breadcrumbs(engine);
+	intel_engine_signal_breadcrumbs(engine);
 }
 
 static void __intel_gt_set_wedged(struct intel_gt *gt)
@@ -773,7 +807,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 	}
 
-	GEM_TRACE("start\n");
+	GT_TRACE(gt, "start\n");
 
 	/*
 	 * First, stop submission to hw, but do not yet complete requests by
@@ -799,11 +833,12 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 
 	/* Mark all executing requests as skipped */
 	for_each_engine(engine, gt, id)
-		engine->cancel_requests(engine);
+		if (engine->reset.cancel)
+			engine->reset.cancel(engine);
 
 	reset_finish(gt, awake);
 
-	GEM_TRACE("end\n");
+	GT_TRACE(gt, "end\n");
 }
 
 void intel_gt_set_wedged(struct intel_gt *gt)
@@ -820,7 +855,6 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
-	unsigned long flags;
 	bool ok;
 
 	if (!test_bit(I915_WEDGED, &gt->reset.flags))
@@ -830,7 +864,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	if (test_bit(I915_WEDGED_ON_INIT, &gt->reset.flags))
 		return false;
 
-	GEM_TRACE("start\n");
+	GT_TRACE(gt, "start\n");
 
 	/*
 	 * Before unwedging, make sure that all pending operations
@@ -842,7 +876,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 *
 	 * No more can be submitted until we reset the wedged bit.
 	 */
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	list_for_each_entry(tl, &timelines->active_list, link) {
 		struct dma_fence *fence;
 
@@ -850,7 +884,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		if (!fence)
 			continue;
 
-		spin_unlock_irqrestore(&timelines->lock, flags);
+		spin_unlock(&timelines->lock);
 
 		/*
 		 * All internal dependencies (i915_requests) will have
@@ -863,10 +897,10 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		dma_fence_put(fence);
 
 		/* Restart iteration after droping lock */
-		spin_lock_irqsave(&timelines->lock, flags);
+		spin_lock(&timelines->lock);
 		tl = list_entry(&timelines->active_list, typeof(*tl), link);
 	}
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 
 	/* We must reset pending GPU events before restoring our submission */
 	ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */
@@ -892,7 +926,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 */
 	intel_engines_reset_default_submission(gt);
 
-	GEM_TRACE("end\n");
+	GT_TRACE(gt, "end\n");
 
 	smp_mb__before_atomic(); /* complete takeover before enabling execbuf */
 	clear_bit(I915_WEDGED, &gt->reset.flags);
@@ -967,7 +1001,7 @@ void intel_gt_reset(struct intel_gt *gt,
 	intel_engine_mask_t awake;
 	int ret;
 
-	GEM_TRACE("flags=%lx\n", gt->reset.flags);
+	GT_TRACE(gt, "flags=%lx\n", gt->reset.flags);
 
 	might_sleep();
 	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
@@ -1070,9 +1104,10 @@ static inline int intel_gt_reset_engine(struct intel_engine_cs *engine)
 int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 {
 	struct intel_gt *gt = engine->gt;
+	bool uses_guc = intel_engine_in_guc_submission_mode(engine);
 	int ret;
 
-	GEM_TRACE("%s flags=%lx\n", engine->name, gt->reset.flags);
+	ENGINE_TRACE(engine, "flags=%lx\n", gt->reset.flags);
 	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &gt->reset.flags));
 
 	if (!intel_engine_pm_get_if_awake(engine))
@@ -1085,14 +1120,14 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 			   "Resetting %s for %s\n", engine->name, msg);
 	atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]);
 
-	if (!engine->gt->uc.guc.execbuf_client)
+	if (!uses_guc)
 		ret = intel_gt_reset_engine(engine);
 	else
 		ret = intel_guc_reset_engine(&engine->gt->uc.guc, engine);
 	if (ret) {
 		/* If we fail here, we expect to fallback to a global reset */
 		DRM_DEBUG_DRIVER("%sFailed to reset %s, ret=%d\n",
-				 engine->gt->uc.guc.execbuf_client ? "GuC " : "",
+				 uses_guc ? "GuC " : "",
 				 engine->name, ret);
 		goto out;
 	}
@@ -1195,7 +1230,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	engine_mask &= INTEL_INFO(gt->i915)->engine_mask;
 
 	if (flags & I915_ERROR_CAPTURE) {
-		i915_capture_error_state(gt->i915, engine_mask, msg);
+		i915_capture_error_state(gt->i915);
 		intel_gt_clear_error_registers(gt, engine_mask);
 	}
 
@@ -1288,10 +1323,10 @@ int intel_gt_terminally_wedged(struct intel_gt *gt)
 	if (!intel_gt_is_wedged(gt))
 		return 0;
 
-	/* Reset still in progress? Maybe we will recover? */
-	if (!test_bit(I915_RESET_BACKOFF, &gt->reset.flags))
+	if (intel_gt_has_init_error(gt))
 		return -EIO;
 
+	/* Reset still in progress? Maybe we will recover? */
 	if (wait_event_interruptible(gt->reset.queue,
 				     !test_bit(I915_RESET_BACKOFF,
 					       &gt->reset.flags)))
@@ -1313,6 +1348,9 @@ void intel_gt_init_reset(struct intel_gt *gt)
 	init_waitqueue_head(&gt->reset.queue);
 	mutex_init(&gt->reset.mutex);
 	init_srcu_struct(&gt->reset.backoff_srcu);
+
+	/* no GPU until we are ready! */
+	__set_bit(I915_WEDGED, &gt->reset.flags);
 }
 
 void intel_gt_fini_reset(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 93026217c121..bc44fe8e5ffa 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -33,6 +33,7 @@
 
 #include "gem/i915_gem_context.h"
 
+#include "gen6_ppgtt.h"
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_context.h"
@@ -362,6 +363,12 @@ gen7_render_ring_flush(struct i915_request *rq, u32 mode)
 	 */
 	flags |= PIPE_CONTROL_CS_STALL;
 
+	/*
+	 * CS_STALL suggests at least a post-sync write.
+	 */
+	flags |= PIPE_CONTROL_QW_WRITE;
+	flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
 	/* Just flush everything.  Experiments have shown that reducing the
 	 * number of bits based on the write domains has little performance
 	 * impact.
@@ -380,13 +387,6 @@ gen7_render_ring_flush(struct i915_request *rq, u32 mode)
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR;
-		/*
-		 * TLB invalidate requires a post-sync write.
-		 */
-		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
-
-		flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD;
 
 		/* Workaround: we must issue a pipe_control with CS-stall bit
 		 * set before a pipe_control command that has the state cache
@@ -454,7 +454,8 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
 	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
 
-	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
+	*cs++ = MI_FLUSH_DW | MI_INVALIDATE_TLB |
+		MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
 	*cs++ = rq->fence.seqno;
 
@@ -496,14 +497,13 @@ static void set_hwstam(struct intel_engine_cs *engine, u32 mask)
 
 static void set_hws_pga(struct intel_engine_cs *engine, phys_addr_t phys)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	u32 addr;
 
 	addr = lower_32_bits(phys);
-	if (INTEL_GEN(dev_priv) >= 4)
+	if (INTEL_GEN(engine->i915) >= 4)
 		addr |= (phys >> 28) & 0xf0;
 
-	I915_WRITE(HWS_PGA, addr);
+	intel_uncore_write(engine->uncore, HWS_PGA, addr);
 }
 
 static struct page *status_page(struct intel_engine_cs *engine)
@@ -522,14 +522,13 @@ static void ring_setup_phys_status_page(struct intel_engine_cs *engine)
 
 static void set_hwsp(struct intel_engine_cs *engine, u32 offset)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	i915_reg_t hwsp;
 
 	/*
 	 * The ring status page addresses are no longer next to the rest of
 	 * the ring registers as of gen7.
 	 */
-	if (IS_GEN(dev_priv, 7)) {
+	if (IS_GEN(engine->i915, 7)) {
 		switch (engine->id) {
 		/*
 		 * No more rings exist on Gen7. Default case is only to shut up
@@ -551,14 +550,14 @@ static void set_hwsp(struct intel_engine_cs *engine, u32 offset)
 			hwsp = VEBOX_HWS_PGA_GEN7;
 			break;
 		}
-	} else if (IS_GEN(dev_priv, 6)) {
+	} else if (IS_GEN(engine->i915, 6)) {
 		hwsp = RING_HWS_PGA_GEN6(engine->mmio_base);
 	} else {
 		hwsp = RING_HWS_PGA(engine->mmio_base);
 	}
 
-	I915_WRITE(hwsp, offset);
-	POSTING_READ(hwsp);
+	intel_uncore_write(engine->uncore, hwsp, offset);
+	intel_uncore_posting_read(engine->uncore, hwsp);
 }
 
 static void flush_cs_tlb(struct intel_engine_cs *engine)
@@ -633,8 +632,8 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	struct intel_ring *ring = engine->legacy.ring;
 	int ret = 0;
 
-	GEM_TRACE("%s: ring:{HEAD:%04x, TAIL:%04x}\n",
-		  engine->name, ring->head, ring->tail);
+	ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n",
+		     ring->head, ring->tail);
 
 	intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL);
 
@@ -721,7 +720,7 @@ static int xcs_resume(struct intel_engine_cs *engine)
 	}
 
 	/* Papering over lost _interrupts_ immediately following the restart */
-	intel_engine_queue_breadcrumbs(engine);
+	intel_engine_signal_breadcrumbs(engine);
 out:
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 
@@ -747,10 +746,10 @@ static void reset_prepare(struct intel_engine_cs *engine)
 	 *
 	 * FIXME: Wa for more modern gens needs to be validated
 	 */
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	if (intel_engine_stop_cs(engine))
-		GEM_TRACE("%s: timed out on STOP_RING\n", engine->name);
+		ENGINE_TRACE(engine, "timed out on STOP_RING\n");
 
 	intel_uncore_write_fw(uncore,
 			      RING_HEAD(base),
@@ -766,12 +765,11 @@ static void reset_prepare(struct intel_engine_cs *engine)
 
 	/* Check acts as a post */
 	if (intel_uncore_read_fw(uncore, RING_HEAD(base)))
-		GEM_TRACE("%s: ring head [%x] not parked\n",
-			  engine->name,
-			  intel_uncore_read_fw(uncore, RING_HEAD(base)));
+		ENGINE_TRACE(engine, "ring head [%x] not parked\n",
+			     intel_uncore_read_fw(uncore, RING_HEAD(base)));
 }
 
-static void reset_ring(struct intel_engine_cs *engine, bool stalled)
+static void reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	struct i915_request *pos, *rq;
 	unsigned long flags;
@@ -842,7 +840,8 @@ static void reset_finish(struct intel_engine_cs *engine)
 
 static int rcs_resume(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_uncore *uncore = engine->uncore;
 
 	/*
 	 * Disable CONSTANT_BUFFER before it is loaded from the context
@@ -854,13 +853,14 @@ static int rcs_resume(struct intel_engine_cs *engine)
 	 * they are already accustomed to from before contexts were
 	 * enabled.
 	 */
-	if (IS_GEN(dev_priv, 4))
-		I915_WRITE(ECOSKPD,
+	if (IS_GEN(i915, 4))
+		intel_uncore_write(uncore, ECOSKPD,
 			   _MASKED_BIT_ENABLE(ECO_CONSTANT_BUFFER_SR_DISABLE));
 
 	/* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
-	if (IS_GEN_RANGE(dev_priv, 4, 6))
-		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
+	if (IS_GEN_RANGE(i915, 4, 6))
+		intel_uncore_write(uncore, MI_MODE,
+				   _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
 
 	/* We need to disable the AsyncFlip performance optimisations in order
 	 * to use MI_WAIT_FOR_EVENT within the CS. It should already be
@@ -868,38 +868,40 @@ static int rcs_resume(struct intel_engine_cs *engine)
 	 *
 	 * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv
 	 */
-	if (IS_GEN_RANGE(dev_priv, 6, 7))
-		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
+	if (IS_GEN_RANGE(i915, 6, 7))
+		intel_uncore_write(uncore, MI_MODE,
+				   _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE));
 
 	/* Required for the hardware to program scanline values for waiting */
 	/* WaEnableFlushTlbInvalidationMode:snb */
-	if (IS_GEN(dev_priv, 6))
-		I915_WRITE(GFX_MODE,
+	if (IS_GEN(i915, 6))
+		intel_uncore_write(uncore, GFX_MODE,
 			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT));
 
 	/* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */
-	if (IS_GEN(dev_priv, 7))
-		I915_WRITE(GFX_MODE_GEN7,
+	if (IS_GEN(i915, 7))
+		intel_uncore_write(uncore, GFX_MODE_GEN7,
 			   _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) |
 			   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 
-	if (IS_GEN(dev_priv, 6)) {
+	if (IS_GEN(i915, 6)) {
 		/* From the Sandybridge PRM, volume 1 part 3, page 24:
 		 * "If this bit is set, STCunit will have LRA as replacement
 		 *  policy. [...] This bit must be reset.  LRA replacement
 		 *  policy is not supported."
 		 */
-		I915_WRITE(CACHE_MODE_0,
+		intel_uncore_write(uncore, CACHE_MODE_0,
 			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 	}
 
-	if (IS_GEN_RANGE(dev_priv, 6, 7))
-		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
+	if (IS_GEN_RANGE(i915, 6, 7))
+		intel_uncore_write(uncore, INSTPM,
+				   _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	return xcs_resume(engine);
 }
 
-static void cancel_requests(struct intel_engine_cs *engine)
+static void reset_cancel(struct intel_engine_cs *engine)
 {
 	struct i915_request *request;
 	unsigned long flags;
@@ -1318,6 +1320,8 @@ static int ring_context_alloc(struct intel_context *ce)
 			return PTR_ERR(vma);
 
 		ce->state = vma;
+		if (engine->default_state)
+			__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 	}
 
 	return 0;
@@ -1325,26 +1329,12 @@ static int ring_context_alloc(struct intel_context *ce)
 
 static int ring_context_pin(struct intel_context *ce)
 {
-	int err;
-
-	err = intel_context_active_acquire(ce);
-	if (err)
-		return err;
-
-	err = __context_pin_ppgtt(ce);
-	if (err)
-		goto err_active;
-
-	return 0;
-
-err_active:
-	intel_context_active_release(ce);
-	return err;
+	return __context_pin_ppgtt(ce);
 }
 
 static void ring_context_reset(struct intel_context *ce)
 {
-	intel_ring_reset(ce->ring, 0);
+	intel_ring_reset(ce->ring, ce->ring->emit);
 }
 
 static const struct intel_context_ops ring_context_ops = {
@@ -1360,46 +1350,38 @@ static const struct intel_context_ops ring_context_ops = {
 	.destroy = ring_context_destroy,
 };
 
-static int load_pd_dir(struct i915_request *rq, const struct i915_ppgtt *ppgtt)
+static int load_pd_dir(struct i915_request *rq,
+		       const struct i915_ppgtt *ppgtt,
+		       u32 valid)
 {
 	const struct intel_engine_cs * const engine = rq->engine;
 	u32 *cs;
 
-	cs = intel_ring_begin(rq, 6);
+	cs = intel_ring_begin(rq, 12);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine->mmio_base));
-	*cs++ = PP_DIR_DCLV_2G;
+	*cs++ = valid;
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1);
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
 	*cs++ = px_base(ppgtt->pd)->ggtt_offset << 10;
 
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int flush_pd_dir(struct i915_request *rq)
-{
-	const struct intel_engine_cs * const engine = rq->engine;
-	u32 *cs;
-
-	cs = intel_ring_begin(rq, 4);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	/* Stall until the page table load is complete */
+	/* Stall until the page table load is complete? */
 	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
 	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine->mmio_base));
-	*cs++ = intel_gt_scratch_offset(rq->engine->gt,
+	*cs++ = intel_gt_scratch_offset(engine->gt,
 					INTEL_GT_SCRATCH_FIELD_DEFAULT);
-	*cs++ = MI_NOOP;
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_INSTPM(engine->mmio_base));
+	*cs++ = _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE);
 
 	intel_ring_advance(rq, cs);
-	return 0;
+
+	return rq->engine->emit_flush(rq, EMIT_FLUSH);
 }
 
 static inline int mi_set_context(struct i915_request *rq, u32 flags)
@@ -1477,7 +1459,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(rq->hw_context->state) | flags;
+	*cs++ = i915_ggtt_offset(rq->context->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1547,10 +1529,10 @@ static int remap_l3_slice(struct i915_request *rq, int slice)
 
 static int remap_l3(struct i915_request *rq)
 {
-	struct i915_gem_context *ctx = rq->gem_context;
+	struct i915_gem_context *ctx = i915_request_gem_context(rq);
 	int i, err;
 
-	if (!ctx->remap_slice)
+	if (!ctx || !ctx->remap_slice)
 		return 0;
 
 	for (i = 0; i < MAX_L3_SLICES; i++) {
@@ -1566,19 +1548,42 @@ static int remap_l3(struct i915_request *rq)
 	return 0;
 }
 
+static int switch_mm(struct i915_request *rq, struct i915_address_space *vm)
+{
+	int ret;
+
+	if (!vm)
+		return 0;
+
+	ret = rq->engine->emit_flush(rq, EMIT_FLUSH);
+	if (ret)
+		return ret;
+
+	/*
+	 * Not only do we need a full barrier (post-sync write) after
+	 * invalidating the TLBs, but we need to wait a little bit
+	 * longer. Whether this is merely delaying us, or the
+	 * subsequent flush is a key part of serialising with the
+	 * post-sync op, this extra pass appears vital before a
+	 * mm switch!
+	 */
+	ret = load_pd_dir(rq, i915_vm_to_ppgtt(vm), PP_DIR_DCLV_2G);
+	if (ret)
+		return ret;
+
+	return rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+}
+
 static int switch_context(struct i915_request *rq)
 {
-	struct intel_context *ce = rq->hw_context;
-	struct i915_address_space *vm = vm_alias(ce);
+	struct intel_context *ce = rq->context;
 	int ret;
 
 	GEM_BUG_ON(HAS_EXECLISTS(rq->i915));
 
-	if (vm) {
-		ret = load_pd_dir(rq, i915_vm_to_ppgtt(vm));
-		if (ret)
-			return ret;
-	}
+	ret = switch_mm(rq, vm_alias(ce));
+	if (ret)
+		return ret;
 
 	if (ce->state) {
 		u32 flags;
@@ -1590,7 +1595,7 @@ static int switch_context(struct i915_request *rq)
 		BUILD_BUG_ON(HSW_MI_RS_RESTORE_STATE_EN != MI_RESTORE_EXT_STATE_EN);
 
 		flags = MI_SAVE_EXT_STATE_EN | MI_MM_SPACE_GTT;
-		if (!i915_gem_context_is_kernel(rq->gem_context))
+		if (test_bit(CONTEXT_VALID_BIT, &ce->flags))
 			flags |= MI_RESTORE_EXT_STATE_EN;
 		else
 			flags |= MI_RESTORE_INHIBIT;
@@ -1600,34 +1605,6 @@ static int switch_context(struct i915_request *rq)
 			return ret;
 	}
 
-	if (vm) {
-		struct intel_engine_cs *engine = rq->engine;
-
-		ret = engine->emit_flush(rq, EMIT_INVALIDATE);
-		if (ret)
-			return ret;
-
-		ret = flush_pd_dir(rq);
-		if (ret)
-			return ret;
-
-		/*
-		 * Not only do we need a full barrier (post-sync write) after
-		 * invalidating the TLBs, but we need to wait a little bit
-		 * longer. Whether this is merely delaying us, or the
-		 * subsequent flush is a key part of serialising with the
-		 * post-sync op, this extra pass appears vital before a
-		 * mm switch!
-		 */
-		ret = engine->emit_flush(rq, EMIT_INVALIDATE);
-		if (ret)
-			return ret;
-
-		ret = engine->emit_flush(rq, EMIT_FLUSH);
-		if (ret)
-			return ret;
-	}
-
 	ret = remap_l3(rq);
 	if (ret)
 		return ret;
@@ -1639,7 +1616,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!intel_context_is_pinned(request->hw_context));
+	GEM_BUG_ON(!intel_context_is_pinned(request->context));
 	GEM_BUG_ON(i915_request_timeline(request)->has_initial_breadcrumb);
 
 	/*
@@ -1795,7 +1772,6 @@ static int gen6_ring_flush(struct i915_request *rq, u32 mode)
 static void i9xx_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = i9xx_submit_request;
-	engine->cancel_requests = cancel_requests;
 
 	engine->park = NULL;
 	engine->unpark = NULL;
@@ -1807,7 +1783,7 @@ static void gen6_bsd_set_default_submission(struct intel_engine_cs *engine)
 	engine->submit_request = gen6_bsd_submit_request;
 }
 
-static void ring_destroy(struct intel_engine_cs *engine)
+static void ring_release(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 
@@ -1821,8 +1797,6 @@ static void ring_destroy(struct intel_engine_cs *engine)
 
 	intel_timeline_unpin(engine->legacy.timeline);
 	intel_timeline_put(engine->legacy.timeline);
-
-	kfree(engine);
 }
 
 static void setup_irq(struct intel_engine_cs *engine)
@@ -1853,11 +1827,10 @@ static void setup_common(struct intel_engine_cs *engine)
 
 	setup_irq(engine);
 
-	engine->destroy = ring_destroy;
-
 	engine->resume = xcs_resume;
 	engine->reset.prepare = reset_prepare;
-	engine->reset.reset = reset_ring;
+	engine->reset.rewind = reset_rewind;
+	engine->reset.cancel = reset_cancel;
 	engine->reset.finish = reset_finish;
 
 	engine->cops = &ring_context_ops;
@@ -1968,6 +1941,10 @@ static void setup_vecs(struct intel_engine_cs *engine)
 
 int intel_ring_submission_setup(struct intel_engine_cs *engine)
 {
+	struct intel_timeline *timeline;
+	struct intel_ring *ring;
+	int err;
+
 	setup_common(engine);
 
 	switch (engine->class) {
@@ -1988,15 +1965,6 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
 		return -ENODEV;
 	}
 
-	return 0;
-}
-
-int intel_ring_submission_init(struct intel_engine_cs *engine)
-{
-	struct intel_timeline *timeline;
-	struct intel_ring *ring;
-	int err;
-
 	timeline = intel_timeline_create(engine->gt, engine->status_page.vma);
 	if (IS_ERR(timeline)) {
 		err = PTR_ERR(timeline);
@@ -2022,16 +1990,13 @@ int intel_ring_submission_init(struct intel_engine_cs *engine)
 	engine->legacy.ring = ring;
 	engine->legacy.timeline = timeline;
 
-	err = intel_engine_init_common(engine);
-	if (err)
-		goto err_ring_unpin;
-
 	GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma);
 
+	/* Finally, take ownership and responsibility for cleanup! */
+	engine->release = ring_release;
+
 	return 0;
 
-err_ring_unpin:
-	intel_ring_unpin(ring);
 err_ring:
 	intel_ring_put(ring);
 err_timeline_unpin:
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 20d6ee148afc..d2a3d935d186 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -37,6 +37,11 @@ static u32 rps_pm_sanitize_mask(struct intel_rps *rps, u32 mask)
 	return mask & ~rps->pm_intrmsk_mbz;
 }
 
+static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
+{
+	intel_uncore_write_fw(uncore, reg, val);
+}
+
 static u32 rps_pm_mask(struct intel_rps *rps, u8 val)
 {
 	u32 mask = 0;
@@ -78,8 +83,7 @@ static void rps_enable_interrupts(struct intel_rps *rps)
 	gen6_gt_pm_enable_irq(gt, rps->pm_events);
 	spin_unlock_irq(&gt->irq_lock);
 
-	intel_uncore_write(gt->uncore, GEN6_PMINTRMSK,
-			   rps_pm_mask(rps, rps->cur_freq));
+	set(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->cur_freq));
 }
 
 static void gen6_rps_reset_interrupts(struct intel_rps *rps)
@@ -113,8 +117,7 @@ static void rps_disable_interrupts(struct intel_rps *rps)
 
 	rps->pm_events = 0;
 
-	intel_uncore_write(gt->uncore, GEN6_PMINTRMSK,
-			   rps_pm_sanitize_mask(rps, ~0u));
+	set(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
 
 	spin_lock_irq(&gt->irq_lock);
 	gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
@@ -573,25 +576,21 @@ static void rps_set_power(struct intel_rps *rps, int new_power)
 	if (IS_VALLEYVIEW(i915))
 		goto skip_hw_write;
 
-	intel_uncore_write(uncore, GEN6_RP_UP_EI,
-			   GT_INTERVAL_FROM_US(i915, ei_up));
-	intel_uncore_write(uncore, GEN6_RP_UP_THRESHOLD,
-			   GT_INTERVAL_FROM_US(i915,
-					       ei_up * threshold_up / 100));
-
-	intel_uncore_write(uncore, GEN6_RP_DOWN_EI,
-			   GT_INTERVAL_FROM_US(i915, ei_down));
-	intel_uncore_write(uncore, GEN6_RP_DOWN_THRESHOLD,
-			   GT_INTERVAL_FROM_US(i915,
-					       ei_down * threshold_down / 100));
-
-	intel_uncore_write(uncore, GEN6_RP_CONTROL,
-			   (INTEL_GEN(i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
-			   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-			   GEN6_RP_MEDIA_IS_GFX |
-			   GEN6_RP_ENABLE |
-			   GEN6_RP_UP_BUSY_AVG |
-			   GEN6_RP_DOWN_IDLE_AVG);
+	set(uncore, GEN6_RP_UP_EI, GT_INTERVAL_FROM_US(i915, ei_up));
+	set(uncore, GEN6_RP_UP_THRESHOLD,
+	    GT_INTERVAL_FROM_US(i915, ei_up * threshold_up / 100));
+
+	set(uncore, GEN6_RP_DOWN_EI, GT_INTERVAL_FROM_US(i915, ei_down));
+	set(uncore, GEN6_RP_DOWN_THRESHOLD,
+	    GT_INTERVAL_FROM_US(i915, ei_down * threshold_down / 100));
+
+	set(uncore, GEN6_RP_CONTROL,
+	    (INTEL_GEN(i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
+	    GEN6_RP_MEDIA_HW_NORMAL_MODE |
+	    GEN6_RP_MEDIA_IS_GFX |
+	    GEN6_RP_ENABLE |
+	    GEN6_RP_UP_BUSY_AVG |
+	    GEN6_RP_DOWN_IDLE_AVG);
 
 skip_hw_write:
 	rps->power.mode = new_power;
@@ -666,7 +665,7 @@ static int gen6_rps_set(struct intel_rps *rps, u8 val)
 		swreq = (GEN6_FREQUENCY(val) |
 			 GEN6_OFFSET(0) |
 			 GEN6_AGGRESSIVE_TURBO);
-	intel_uncore_write(uncore, GEN6_RPNSWREQ, swreq);
+	set(uncore, GEN6_RPNSWREQ, swreq);
 
 	return 0;
 }
@@ -683,7 +682,7 @@ static int vlv_rps_set(struct intel_rps *rps, u8 val)
 	return err;
 }
 
-static int rps_set(struct intel_rps *rps, u8 val)
+static int rps_set(struct intel_rps *rps, u8 val, bool update)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	int err;
@@ -701,7 +700,8 @@ static int rps_set(struct intel_rps *rps, u8 val)
 	if (err)
 		return err;
 
-	gen6_rps_set_thresholds(rps, val);
+	if (update)
+		gen6_rps_set_thresholds(rps, val);
 	rps->last_freq = val;
 
 	return 0;
@@ -761,7 +761,7 @@ void intel_rps_park(struct intel_rps *rps)
 	 * power than the render powerwell.
 	 */
 	intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA);
-	rps_set(rps, rps->idle_freq);
+	rps_set(rps, rps->idle_freq, false);
 	intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA);
 }
 
@@ -777,7 +777,7 @@ void intel_rps_boost(struct i915_request *rq)
 	spin_lock_irqsave(&rq->lock, flags);
 	if (!i915_request_has_waitboost(rq) &&
 	    !dma_fence_is_signaled_locked(&rq->fence)) {
-		rq->flags |= I915_REQUEST_WAITBOOST;
+		set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
 
 		if (!atomic_fetch_inc(&rps->num_waiters) &&
 		    READ_ONCE(rps->cur_freq) < rps->boost_freq)
@@ -790,14 +790,16 @@ void intel_rps_boost(struct i915_request *rq)
 
 int intel_rps_set(struct intel_rps *rps, u8 val)
 {
-	int err = 0;
+	int err;
 
 	lockdep_assert_held(&rps->lock);
 	GEM_BUG_ON(val > rps->max_freq);
 	GEM_BUG_ON(val < rps->min_freq);
 
 	if (rps->active) {
-		err = rps_set(rps, val);
+		err = rps_set(rps, val, true);
+		if (err)
+			return err;
 
 		/*
 		 * Make sure we continue to get interrupts
@@ -806,18 +808,15 @@ int intel_rps_set(struct intel_rps *rps, u8 val)
 		if (INTEL_GEN(rps_to_i915(rps)) >= 6) {
 			struct intel_uncore *uncore = rps_to_uncore(rps);
 
-			intel_uncore_write(uncore, GEN6_RP_INTERRUPT_LIMITS,
-					   rps_limits(rps, val));
+			set(uncore,
+			    GEN6_RP_INTERRUPT_LIMITS, rps_limits(rps, val));
 
-			intel_uncore_write(uncore, GEN6_PMINTRMSK,
-					   rps_pm_mask(rps, val));
+			set(uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, val));
 		}
 	}
 
-	if (err == 0)
-		rps->cur_freq = val;
-
-	return err;
+	rps->cur_freq = val;
+	return 0;
 }
 
 static void gen6_rps_init(struct intel_rps *rps)
@@ -878,7 +877,7 @@ static bool rps_reset(struct intel_rps *rps)
 	rps->power.mode = -1;
 	rps->last_freq = -1;
 
-	if (rps_set(rps, rps->min_freq)) {
+	if (rps_set(rps, rps->min_freq, true)) {
 		DRM_ERROR("Failed to reset RPS to initial values\n");
 		return false;
 	}
@@ -1201,7 +1200,7 @@ void intel_rps_enable(struct intel_rps *rps)
 
 static void gen6_rps_disable(struct intel_rps *rps)
 {
-	intel_uncore_write(rps_to_uncore(rps), GEN6_RP_CONTROL, 0);
+	set(rps_to_uncore(rps), GEN6_RP_CONTROL, 0);
 }
 
 void intel_rps_disable(struct intel_rps *rps)
@@ -1566,7 +1565,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
 		return;
 
 	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(gt->engine[VECS0]);
+		intel_engine_signal_breadcrumbs(gt->engine[VECS0]);
 
 	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
 		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
@@ -1663,23 +1662,53 @@ void intel_rps_init(struct intel_rps *rps)
 	if (INTEL_GEN(i915) <= 7)
 		rps->pm_intrmsk_mbz |= GEN6_PM_RP_UP_EI_EXPIRED;
 
-	if (INTEL_GEN(i915) >= 8)
+	if (INTEL_GEN(i915) >= 8 && INTEL_GEN(i915) < 11)
 		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
 }
 
-u32 intel_get_cagf(struct intel_rps *rps, u32 rpstat)
+u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat)
 {
 	struct drm_i915_private *i915 = rps_to_i915(rps);
 	u32 cagf;
 
-	if (INTEL_GEN(i915) >= 9)
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+		cagf = (rpstat >> 8) & 0xff;
+	else if (INTEL_GEN(i915) >= 9)
 		cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
 	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
 		cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
 	else
 		cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
 
-	return  cagf;
+	return cagf;
+}
+
+static u32 read_cagf(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 freq;
+
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		vlv_punit_get(i915);
+		freq = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+		vlv_punit_put(i915);
+	} else {
+		freq = intel_uncore_read(rps_to_gt(rps)->uncore, GEN6_RPSTAT1);
+	}
+
+	return intel_rps_get_cagf(rps, freq);
+}
+
+u32 intel_rps_read_actual_frequency(struct intel_rps *rps)
+{
+	struct intel_runtime_pm *rpm = rps_to_gt(rps)->uncore->rpm;
+	intel_wakeref_t wakeref;
+	u32 freq = 0;
+
+	with_intel_runtime_pm_if_in_use(rpm, wakeref)
+		freq = intel_gpu_freq(rps, read_cagf(rps));
+
+	return freq;
 }
 
 /* External interface for intel_ips.ko */
@@ -1715,6 +1744,7 @@ void intel_rps_driver_register(struct intel_rps *rps)
 	 * set up, to avoid intel-ips sneaking in and reading bogus values.
 	 */
 	if (IS_GEN(gt->i915, 5)) {
+		GEM_BUG_ON(ips_mchdev);
 		rcu_assign_pointer(ips_mchdev, gt->i915);
 		ips_ping_for_i915_load();
 	}
@@ -1722,7 +1752,8 @@ void intel_rps_driver_register(struct intel_rps *rps)
 
 void intel_rps_driver_unregister(struct intel_rps *rps)
 {
-	rcu_assign_pointer(ips_mchdev, NULL);
+	if (rcu_access_pointer(ips_mchdev) == rps_to_i915(rps))
+		rcu_assign_pointer(ips_mchdev, NULL);
 }
 
 static struct drm_i915_private *mchdev_get(void)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
index 9518c66c9792..dfa98194f3b2 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.h
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -29,7 +29,8 @@ void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive);
 
 int intel_gpu_freq(struct intel_rps *rps, int val);
 int intel_freq_opcode(struct intel_rps *rps, int val);
-u32 intel_get_cagf(struct intel_rps *rps, u32 rpstat1);
+u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1);
+u32 intel_rps_read_actual_frequency(struct intel_rps *rps);
 
 void gen5_rps_irq_handler(struct intel_rps *rps);
 void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 649798c184fb..87716529cd2f 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -15,6 +15,9 @@
 #define ptr_set_bit(ptr, bit) ((typeof(ptr))((unsigned long)(ptr) | BIT(bit)))
 #define ptr_test_bit(ptr, bit) ((unsigned long)(ptr) & BIT(bit))
 
+#define CACHELINE_BITS 6
+#define CACHELINE_FREE CACHELINE_BITS
+
 struct intel_timeline_hwsp {
 	struct intel_gt *gt;
 	struct intel_gt_timelines *gt_timelines;
@@ -23,14 +26,6 @@ struct intel_timeline_hwsp {
 	u64 free_bitmap;
 };
 
-struct intel_timeline_cacheline {
-	struct i915_active active;
-	struct intel_timeline_hwsp *hwsp;
-	void *vaddr;
-#define CACHELINE_BITS 6
-#define CACHELINE_FREE CACHELINE_BITS
-};
-
 static struct i915_vma *__hwsp_alloc(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -133,7 +128,7 @@ static void __idle_cacheline_free(struct intel_timeline_cacheline *cl)
 	__idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS));
 
 	i915_active_fini(&cl->active);
-	kfree(cl);
+	kfree_rcu(cl, rcu);
 }
 
 __i915_active_call
@@ -254,7 +249,7 @@ int intel_timeline_init(struct intel_timeline *timeline,
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_FENCE(&timeline->last_request, &timeline->mutex);
+	INIT_ACTIVE_FENCE(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
@@ -262,7 +257,7 @@ int intel_timeline_init(struct intel_timeline *timeline,
 	return 0;
 }
 
-static void timelines_init(struct intel_gt *gt)
+void intel_gt_init_timelines(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 
@@ -273,11 +268,6 @@ static void timelines_init(struct intel_gt *gt)
 	INIT_LIST_HEAD(&timelines->hwsp_free_list);
 }
 
-void intel_timelines_init(struct drm_i915_private *i915)
-{
-	timelines_init(&i915->gt);
-}
-
 void intel_timeline_fini(struct intel_timeline *timeline)
 {
 	GEM_BUG_ON(atomic_read(&timeline->pin_count));
@@ -338,7 +328,6 @@ int intel_timeline_pin(struct intel_timeline *tl)
 void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
-	unsigned long flags;
 
 	/*
 	 * Pretend we are serialised by the timeline->mutex.
@@ -359,21 +348,19 @@ void intel_timeline_enter(struct intel_timeline *tl)
 	 * use atomic to manipulate tl->active_count.
 	 */
 	lockdep_assert_held(&tl->mutex);
-	GEM_BUG_ON(!atomic_read(&tl->pin_count));
 
 	if (atomic_add_unless(&tl->active_count, 1, 0))
 		return;
 
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	if (!atomic_fetch_inc(&tl->active_count))
 		list_add_tail(&tl->link, &timelines->active_list);
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 }
 
 void intel_timeline_exit(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
-	unsigned long flags;
 
 	/* See intel_timeline_enter() */
 	lockdep_assert_held(&tl->mutex);
@@ -382,10 +369,10 @@ void intel_timeline_exit(struct intel_timeline *tl)
 	if (atomic_add_unless(&tl->active_count, -1, 1))
 		return;
 
-	spin_lock_irqsave(&timelines->lock, flags);
+	spin_lock(&timelines->lock);
 	if (atomic_dec_and_test(&tl->active_count))
 		list_del(&tl->link);
-	spin_unlock_irqrestore(&timelines->lock, flags);
+	spin_unlock(&timelines->lock);
 
 	/*
 	 * Since this timeline is idle, all bariers upon which we were waiting
@@ -521,46 +508,35 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 			     struct i915_request *to,
 			     u32 *hwsp)
 {
-	struct intel_timeline *tl;
+	struct intel_timeline_cacheline *cl;
 	int err;
 
+	GEM_BUG_ON(!rcu_access_pointer(from->hwsp_cacheline));
+
 	rcu_read_lock();
-	tl = rcu_dereference(from->timeline);
-	if (i915_request_completed(from) || !kref_get_unless_zero(&tl->kref))
-		tl = NULL;
+	cl = rcu_dereference(from->hwsp_cacheline);
+	if (unlikely(!i915_active_acquire_if_busy(&cl->active)))
+		goto unlock; /* seqno wrapped and completed! */
+	if (unlikely(i915_request_completed(from)))
+		goto release;
 	rcu_read_unlock();
-	if (!tl) /* already completed */
-		return 1;
-
-	GEM_BUG_ON(rcu_access_pointer(to->timeline) == tl);
-
-	err = -EBUSY;
-	if (mutex_trylock(&tl->mutex)) {
-		struct intel_timeline_cacheline *cl = from->hwsp_cacheline;
 
-		if (i915_request_completed(from)) {
-			err = 1;
-			goto unlock;
-		}
+	err = cacheline_ref(cl, to);
+	if (err)
+		goto out;
 
-		err = cacheline_ref(cl, to);
-		if (err)
-			goto unlock;
+	*hwsp = i915_ggtt_offset(cl->hwsp->vma) +
+		ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES;
 
-		if (likely(cl == tl->hwsp_cacheline)) {
-			*hwsp = tl->hwsp_offset;
-		} else { /* across a seqno wrap, recover the original offset */
-			*hwsp = i915_ggtt_offset(cl->hwsp->vma) +
-				ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) *
-				CACHELINE_BYTES;
-		}
+out:
+	i915_active_release(&cl->active);
+	return err;
 
+release:
+	i915_active_release(&cl->active);
 unlock:
-		mutex_unlock(&tl->mutex);
-	}
-	intel_timeline_put(tl);
-
-	return err;
+	rcu_read_unlock();
+	return 1;
 }
 
 void intel_timeline_unpin(struct intel_timeline *tl)
@@ -583,7 +559,7 @@ void __intel_timeline_free(struct kref *kref)
 	kfree_rcu(timeline, rcu);
 }
 
-static void timelines_fini(struct intel_gt *gt)
+void intel_gt_fini_timelines(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 
@@ -591,11 +567,6 @@ static void timelines_fini(struct intel_gt *gt)
 	GEM_BUG_ON(!list_empty(&timelines->hwsp_free_list));
 }
 
-void intel_timelines_fini(struct drm_i915_private *i915)
-{
-	timelines_fini(&i915->gt);
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "gt/selftests/mock_timeline.c"
 #include "gt/selftest_timeline.c"
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index f583af1ba18d..f5b7eade3809 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -88,7 +88,7 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 			     struct i915_request *until,
 			     u32 *hwsp_offset);
 
-void intel_timelines_init(struct drm_i915_private *i915);
-void intel_timelines_fini(struct drm_i915_private *i915);
+void intel_gt_init_timelines(struct intel_gt *gt);
+void intel_gt_fini_timelines(struct intel_gt *gt);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index aaf15cbe1ce1..02181c5020db 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -10,14 +10,15 @@
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/mutex.h>
+#include <linux/rcupdate.h>
 #include <linux/types.h>
 
 #include "i915_active_types.h"
 
-struct drm_i915_private;
 struct i915_vma;
-struct intel_timeline_cacheline;
 struct i915_syncmap;
+struct intel_gt;
+struct intel_timeline_hwsp;
 
 struct intel_timeline {
 	u64 fence_context;
@@ -87,4 +88,13 @@ struct intel_timeline {
 	struct rcu_head rcu;
 };
 
+struct intel_timeline_cacheline {
+	struct i915_active active;
+
+	struct intel_timeline_hwsp *hwsp;
+	void *vaddr;
+
+	struct rcu_head rcu;
+};
+
 #endif /* __I915_TIMELINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index e4bccc14602f..4e292d4bf7b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -6,6 +6,7 @@
 
 #include "i915_drv.h"
 #include "intel_context.h"
+#include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_ring.h"
 #include "intel_workarounds.h"
@@ -146,21 +147,27 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa)
 	}
 }
 
-static void
-wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
-		   u32 val)
+static void wa_add(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
+		   u32 val, u32 read_mask)
 {
 	struct i915_wa wa = {
 		.reg  = reg,
 		.mask = mask,
 		.val  = val,
-		.read = mask,
+		.read = read_mask,
 	};
 
 	_wa_add(wal, &wa);
 }
 
 static void
+wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask,
+		   u32 val)
+{
+	wa_add(wal, reg, mask, val, mask);
+}
+
+static void
 wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val)
 {
 	wa_write_masked_or(wal, reg, val, _MASKED_BIT_ENABLE(val));
@@ -247,7 +254,7 @@ static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine,
 
 	/* WaDisableDopClockGating:bdw
 	 *
-	 * Also see the related UCGTCL1 write in broadwell_init_clock_gating()
+	 * Also see the related UCGTCL1 write in bdw_init_clock_gating()
 	 * to disable EUTC clock gating.
 	 */
 	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
@@ -568,9 +575,24 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
+	u32 val;
+
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
+
+	/* Wa_1604555607:tgl */
+	val = intel_uncore_read(engine->uncore, FF_MODE2);
+	val &= ~FF_MODE2_TDS_TIMER_MASK;
+	val |= FF_MODE2_TDS_TIMER_128;
+	/*
+	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
+	 * enable verification of WA from the later steppings, which enables
+	 * the read of FF_MODE2.
+	 */
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
+	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
+			    FF_MODE2_TDS_TIMER_MASK);
 }
 
 static void
@@ -1315,6 +1337,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			     GEN6_RC_SLEEP_PSMI_CONTROL,
 			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
 			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
+
+		/*
+		 * Wa_1606679103:tgl
+		 * (see also Wa_1606682166:icl)
+		 */
+		wa_write_or(wal,
+			    GEN7_SARCHKMD,
+			    GEN7_DISABLE_SAMPLER_PREFETCH);
 	}
 
 	if (IS_GEN(i915, 11)) {
@@ -1574,7 +1604,9 @@ static int engine_wa_list_verify(struct intel_context *ce,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
+	intel_engine_pm_get(ce->engine);
 	rq = intel_context_create_request(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_vma;
@@ -1584,16 +1616,17 @@ static int engine_wa_list_verify(struct intel_context *ce,
 	if (err)
 		goto err_vma;
 
+	i915_request_get(rq);
 	i915_request_add(rq);
 	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 		err = -ETIME;
-		goto err_vma;
+		goto err_rq;
 	}
 
 	results = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
 	if (IS_ERR(results)) {
 		err = PTR_ERR(results);
-		goto err_vma;
+		goto err_rq;
 	}
 
 	err = 0;
@@ -1607,6 +1640,8 @@ static int engine_wa_list_verify(struct intel_context *ce,
 
 	i915_gem_object_unpin_map(vma->obj);
 
+err_rq:
+	i915_request_put(rq);
 err_vma:
 	i915_vma_unpin(vma);
 	i915_vma_put(vma);
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 83f549d203a0..a560b7eee2cd 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -77,7 +77,7 @@ static void advance(struct i915_request *request)
 	i915_request_mark_complete(request);
 	GEM_BUG_ON(!i915_request_completed(request));
 
-	intel_engine_queue_breadcrumbs(request->engine);
+	intel_engine_signal_breadcrumbs(request->engine);
 }
 
 static void hw_delay_complete(struct timer_list *t)
@@ -149,7 +149,11 @@ static int mock_context_alloc(struct intel_context *ce)
 
 static int mock_context_pin(struct intel_context *ce)
 {
-	return intel_context_active_acquire(ce);
+	return 0;
+}
+
+static void mock_context_reset(struct intel_context *ce)
+{
 }
 
 static const struct intel_context_ops mock_context_ops = {
@@ -161,6 +165,7 @@ static const struct intel_context_ops mock_context_ops = {
 	.enter = intel_context_enter_engine,
 	.exit = intel_context_exit_engine,
 
+	.reset = mock_context_reset,
 	.destroy = mock_context_destroy,
 };
 
@@ -207,16 +212,12 @@ static void mock_reset_prepare(struct intel_engine_cs *engine)
 {
 }
 
-static void mock_reset(struct intel_engine_cs *engine, bool stalled)
+static void mock_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	GEM_BUG_ON(stalled);
 }
 
-static void mock_reset_finish(struct intel_engine_cs *engine)
-{
-}
-
-static void mock_cancel_requests(struct intel_engine_cs *engine)
+static void mock_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct i915_request *request;
 	unsigned long flags;
@@ -234,6 +235,24 @@ static void mock_cancel_requests(struct intel_engine_cs *engine)
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
+static void mock_reset_finish(struct intel_engine_cs *engine)
+{
+}
+
+static void mock_engine_release(struct intel_engine_cs *engine)
+{
+	struct mock_engine *mock =
+		container_of(engine, typeof(*mock), base);
+
+	GEM_BUG_ON(timer_pending(&mock->hw_delay));
+
+	intel_context_unpin(engine->kernel_context);
+	intel_context_put(engine->kernel_context);
+
+	intel_engine_fini_retire(engine);
+	intel_engine_fini_breadcrumbs(engine);
+}
+
 struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 				    const char *name,
 				    int id)
@@ -265,9 +284,11 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.submit_request = mock_submit_request;
 
 	engine->base.reset.prepare = mock_reset_prepare;
-	engine->base.reset.reset = mock_reset;
+	engine->base.reset.rewind = mock_reset_rewind;
+	engine->base.reset.cancel = mock_reset_cancel;
 	engine->base.reset.finish = mock_reset_finish;
-	engine->base.cancel_requests = mock_cancel_requests;
+
+	engine->base.release = mock_engine_release;
 
 	i915->gt.engine[id] = &engine->base;
 	i915->gt.engine_class[0][id] = &engine->base;
@@ -290,6 +311,7 @@ int mock_engine_init(struct intel_engine_cs *engine)
 	intel_engine_init_breadcrumbs(engine);
 	intel_engine_init_execlists(engine);
 	intel_engine_init__pm(engine);
+	intel_engine_init_retire(engine);
 	intel_engine_pool_init(&engine->pool);
 
 	ce = create_kernel_context(engine);
@@ -321,18 +343,3 @@ void mock_engine_flush(struct intel_engine_cs *engine)
 void mock_engine_reset(struct intel_engine_cs *engine)
 {
 }
-
-void mock_engine_free(struct intel_engine_cs *engine)
-{
-	struct mock_engine *mock =
-		container_of(engine, typeof(*mock), base);
-
-	GEM_BUG_ON(timer_pending(&mock->hw_delay));
-
-	intel_context_unpin(engine->kernel_context);
-	intel_context_put(engine->kernel_context);
-
-	intel_engine_fini_breadcrumbs(engine);
-
-	kfree(engine);
-}
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index bc720defc6b8..e874dfaa5316 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -5,6 +5,7 @@
  */
 
 #include "i915_selftest.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 
@@ -47,35 +48,36 @@ static int context_sync(struct intel_context *ce)
 
 	mutex_lock(&tl->mutex);
 	do {
-		struct dma_fence *fence;
+		struct i915_request *rq;
 		long timeout;
 
-		fence = i915_active_fence_get(&tl->last_request);
-		if (!fence)
+		if (list_empty(&tl->requests))
 			break;
 
-		timeout = dma_fence_wait_timeout(fence, false, HZ / 10);
+		rq = list_last_entry(&tl->requests, typeof(*rq), link);
+		i915_request_get(rq);
+
+		timeout = i915_request_wait(rq, 0, HZ / 10);
 		if (timeout < 0)
 			err = timeout;
 		else
-			i915_request_retire_upto(to_request(fence));
+			i915_request_retire_upto(rq);
 
-		dma_fence_put(fence);
+		i915_request_put(rq);
 	} while (!err);
 	mutex_unlock(&tl->mutex);
 
 	return err;
 }
 
-static int __live_context_size(struct intel_engine_cs *engine,
-			       struct i915_gem_context *fixme)
+static int __live_context_size(struct intel_engine_cs *engine)
 {
 	struct intel_context *ce;
 	struct i915_request *rq;
 	void *vaddr;
 	int err;
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
@@ -118,7 +120,7 @@ static int __live_context_size(struct intel_engine_cs *engine,
 		goto err_unpin;
 
 	/* Force the context switch */
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_unpin;
@@ -143,7 +145,6 @@ static int live_context_size(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	enum intel_engine_id id;
 	int err = 0;
 
@@ -152,10 +153,6 @@ static int live_context_size(void *arg)
 	 * HW tries to write past the end of one.
 	 */
 
-	fixme = kernel_context(gt->i915);
-	if (IS_ERR(fixme))
-		return PTR_ERR(fixme);
-
 	for_each_engine(engine, gt, id) {
 		struct {
 			struct drm_i915_gem_object *state;
@@ -180,7 +177,7 @@ static int live_context_size(void *arg)
 		/* Overlaps with the execlists redzone */
 		engine->context_size += I915_GTT_PAGE_SIZE;
 
-		err = __live_context_size(engine, fixme);
+		err = __live_context_size(engine);
 
 		engine->context_size -= I915_GTT_PAGE_SIZE;
 
@@ -193,13 +190,12 @@ static int live_context_size(void *arg)
 			break;
 	}
 
-	kernel_context_close(fixme);
 	return err;
 }
 
-static int __live_active_context(struct intel_engine_cs *engine,
-				 struct i915_gem_context *fixme)
+static int __live_active_context(struct intel_engine_cs *engine)
 {
+	unsigned long saved_heartbeat;
 	struct intel_context *ce;
 	int pass;
 	int err;
@@ -223,40 +219,55 @@ static int __live_active_context(struct intel_engine_cs *engine,
 		return -EINVAL;
 	}
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
+	saved_heartbeat = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+
 	for (pass = 0; pass <= 2; pass++) {
 		struct i915_request *rq;
 
+		intel_engine_pm_get(engine);
+
 		rq = intel_context_create_request(ce);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			goto err;
+			goto out_engine;
 		}
 
 		err = request_sync(rq);
 		if (err)
-			goto err;
+			goto out_engine;
 
 		/* Context will be kept active until after an idle-barrier. */
 		if (i915_active_is_idle(&ce->active)) {
 			pr_err("context is not active; expected idle-barrier (%s pass %d)\n",
 			       engine->name, pass);
 			err = -EINVAL;
-			goto err;
+			goto out_engine;
 		}
 
 		if (!intel_engine_pm_is_awake(engine)) {
 			pr_err("%s is asleep before idle-barrier\n",
 			       engine->name);
 			err = -EINVAL;
-			goto err;
+			goto out_engine;
 		}
+
+out_engine:
+		intel_engine_pm_put(engine);
+		if (err)
+			goto err;
 	}
 
 	/* Now make sure our idle-barriers are flushed */
+	err = intel_engine_flush_barriers(engine);
+	if (err)
+		goto err;
+
+	/* Wait for the barrier and in the process wait for engine to park */
 	err = context_sync(engine->kernel_context);
 	if (err)
 		goto err;
@@ -266,12 +277,15 @@ static int __live_active_context(struct intel_engine_cs *engine,
 		err = -EINVAL;
 	}
 
+	intel_engine_pm_flush(engine);
+
 	if (intel_engine_pm_is_awake(engine)) {
 		struct drm_printer p = drm_debug_printer(__func__);
 
 		intel_engine_dump(engine, &p,
-				  "%s is still awake after idle-barriers\n",
-				  engine->name);
+				  "%s is still awake:%d after idle-barriers\n",
+				  engine->name,
+				  atomic_read(&engine->wakeref.count));
 		GEM_TRACE_DUMP();
 
 		err = -EINVAL;
@@ -279,6 +293,7 @@ static int __live_active_context(struct intel_engine_cs *engine,
 	}
 
 err:
+	engine->props.heartbeat_interval_ms = saved_heartbeat;
 	intel_context_put(ce);
 	return err;
 }
@@ -287,23 +302,11 @@ static int live_active_context(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	enum intel_engine_id id;
-	struct drm_file *file;
 	int err = 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	fixme = live_context(gt->i915, file);
-	if (IS_ERR(fixme)) {
-		err = PTR_ERR(fixme);
-		goto out_file;
-	}
-
 	for_each_engine(engine, gt, id) {
-		err = __live_active_context(engine, fixme);
+		err = __live_active_context(engine);
 		if (err)
 			break;
 
@@ -312,8 +315,6 @@ static int live_active_context(void *arg)
 			break;
 	}
 
-out_file:
-	mock_file_free(gt->i915, file);
 	return err;
 }
 
@@ -345,10 +346,10 @@ unpin:
 	return err;
 }
 
-static int __live_remote_context(struct intel_engine_cs *engine,
-				 struct i915_gem_context *fixme)
+static int __live_remote_context(struct intel_engine_cs *engine)
 {
 	struct intel_context *local, *remote;
+	unsigned long saved_heartbeat;
 	int pass;
 	int err;
 
@@ -360,16 +361,26 @@ static int __live_remote_context(struct intel_engine_cs *engine,
 	 * clobber the idle-barrier.
 	 */
 
-	remote = intel_context_create(fixme, engine);
+	if (intel_engine_pm_is_awake(engine)) {
+		pr_err("%s is awake before starting %s!\n",
+		       engine->name, __func__);
+		return -EINVAL;
+	}
+
+	remote = intel_context_create(engine);
 	if (IS_ERR(remote))
 		return PTR_ERR(remote);
 
-	local = intel_context_create(fixme, engine);
+	local = intel_context_create(engine);
 	if (IS_ERR(local)) {
 		err = PTR_ERR(local);
 		goto err_remote;
 	}
 
+	saved_heartbeat = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+	intel_engine_pm_get(engine);
+
 	for (pass = 0; pass <= 2; pass++) {
 		err = __remote_sync(local, remote);
 		if (err)
@@ -387,6 +398,9 @@ static int __live_remote_context(struct intel_engine_cs *engine,
 		}
 	}
 
+	intel_engine_pm_put(engine);
+	engine->props.heartbeat_interval_ms = saved_heartbeat;
+
 	intel_context_put(local);
 err_remote:
 	intel_context_put(remote);
@@ -397,23 +411,11 @@ static int live_remote_context(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	enum intel_engine_id id;
-	struct drm_file *file;
 	int err = 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	fixme = live_context(gt->i915, file);
-	if (IS_ERR(fixme)) {
-		err = PTR_ERR(fixme);
-		goto out_file;
-	}
-
 	for_each_engine(engine, gt, id) {
-		err = __live_remote_context(engine, fixme);
+		err = __live_remote_context(engine);
 		if (err)
 			break;
 
@@ -422,8 +424,6 @@ static int live_remote_context(void *arg)
 			break;
 	}
 
-out_file:
-	mock_file_free(gt->i915, file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
index 3880f07c29b8..f88e445a1cae 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
@@ -4,7 +4,365 @@
  * Copyright © 2018 Intel Corporation
  */
 
-#include "../i915_selftest.h"
+#include <linux/sort.h>
+
+#include "intel_gt_pm.h"
+#include "intel_rps.h"
+
+#include "i915_selftest.h"
+#include "selftests/igt_flush_test.h"
+
+#define COUNT 5
+
+static int cmp_u32(const void *A, const void *B)
+{
+	const u32 *a = A, *b = B;
+
+	return *a - *b;
+}
+
+static void perf_begin(struct intel_gt *gt)
+{
+	intel_gt_pm_get(gt);
+
+	/* Boost gpufreq to max [waitboost] and keep it fixed */
+	atomic_inc(&gt->rps.num_waiters);
+	schedule_work(&gt->rps.work);
+	flush_work(&gt->rps.work);
+}
+
+static int perf_end(struct intel_gt *gt)
+{
+	atomic_dec(&gt->rps.num_waiters);
+	intel_gt_pm_put(gt);
+
+	return igt_flush_test(gt->i915);
+}
+
+static int write_timestamp(struct i915_request *rq, int slot)
+{
+	u32 cmd;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	cmd = MI_STORE_REGISTER_MEM | MI_USE_GGTT;
+	if (INTEL_GEN(rq->i915) >= 8)
+		cmd++;
+	*cs++ = cmd;
+	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base));
+	*cs++ = i915_request_timeline(rq)->hwsp_offset + slot * sizeof(u32);
+	*cs++ = 0;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static struct i915_vma *create_empty_batch(struct intel_context *ce)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+
+	obj = i915_gem_object_create_internal(ce->engine->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_put;
+	}
+
+	cs[0] = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_unpin;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err_unpin;
+
+	i915_gem_object_unpin_map(obj);
+	return vma;
+
+err_unpin:
+	i915_gem_object_unpin_map(obj);
+err_put:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static u32 trifilter(u32 *a)
+{
+	u64 sum;
+
+	sort(a, COUNT, sizeof(*a), cmp_u32, NULL);
+
+	sum = mul_u32_u32(a[2], 2);
+	sum += a[1];
+	sum += a[3];
+
+	return sum >> 2;
+}
+
+static int perf_mi_bb_start(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	if (INTEL_GEN(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */
+		return 0;
+
+	perf_begin(gt);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce = engine->kernel_context;
+		struct i915_vma *batch;
+		u32 cycles[COUNT];
+		int i;
+
+		intel_engine_pm_get(engine);
+
+		batch = create_empty_batch(ce);
+		if (IS_ERR(batch)) {
+			err = PTR_ERR(batch);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		err = i915_vma_sync(batch);
+		if (err) {
+			intel_engine_pm_put(engine);
+			i915_vma_put(batch);
+			break;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(cycles); i++) {
+			struct i915_request *rq;
+
+			rq = i915_request_create(ce);
+			if (IS_ERR(rq)) {
+				err = PTR_ERR(rq);
+				break;
+			}
+
+			err = write_timestamp(rq, 2);
+			if (err)
+				goto out;
+
+			err = rq->engine->emit_bb_start(rq,
+							batch->node.start, 8,
+							0);
+			if (err)
+				goto out;
+
+			err = write_timestamp(rq, 3);
+			if (err)
+				goto out;
+
+out:
+			i915_request_get(rq);
+			i915_request_add(rq);
+
+			if (i915_request_wait(rq, 0, HZ / 5) < 0)
+				err = -EIO;
+			i915_request_put(rq);
+			if (err)
+				break;
+
+			cycles[i] = rq->hwsp_seqno[3] - rq->hwsp_seqno[2];
+		}
+		i915_vma_put(batch);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+
+		pr_info("%s: MI_BB_START cycles: %u\n",
+			engine->name, trifilter(cycles));
+	}
+	if (perf_end(gt))
+		err = -EIO;
+
+	return err;
+}
+
+static struct i915_vma *create_nop_batch(struct intel_context *ce)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+
+	obj = i915_gem_object_create_internal(ce->engine->i915, SZ_64K);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_put;
+	}
+
+	memset(cs, 0, SZ_64K);
+	cs[SZ_64K / sizeof(*cs) - 1] = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_unpin;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err_unpin;
+
+	i915_gem_object_unpin_map(obj);
+	return vma;
+
+err_unpin:
+	i915_gem_object_unpin_map(obj);
+err_put:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static int perf_mi_noop(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	if (INTEL_GEN(gt->i915) < 7) /* for per-engine CS_TIMESTAMP */
+		return 0;
+
+	perf_begin(gt);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce = engine->kernel_context;
+		struct i915_vma *base, *nop;
+		u32 cycles[COUNT];
+		int i;
+
+		intel_engine_pm_get(engine);
+
+		base = create_empty_batch(ce);
+		if (IS_ERR(base)) {
+			err = PTR_ERR(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		err = i915_vma_sync(base);
+		if (err) {
+			i915_vma_put(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		nop = create_nop_batch(ce);
+		if (IS_ERR(nop)) {
+			err = PTR_ERR(nop);
+			i915_vma_put(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		err = i915_vma_sync(nop);
+		if (err) {
+			i915_vma_put(nop);
+			i915_vma_put(base);
+			intel_engine_pm_put(engine);
+			break;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(cycles); i++) {
+			struct i915_request *rq;
+
+			rq = i915_request_create(ce);
+			if (IS_ERR(rq)) {
+				err = PTR_ERR(rq);
+				break;
+			}
+
+			err = write_timestamp(rq, 2);
+			if (err)
+				goto out;
+
+			err = rq->engine->emit_bb_start(rq,
+							base->node.start, 8,
+							0);
+			if (err)
+				goto out;
+
+			err = write_timestamp(rq, 3);
+			if (err)
+				goto out;
+
+			err = rq->engine->emit_bb_start(rq,
+							nop->node.start,
+							nop->node.size,
+							0);
+			if (err)
+				goto out;
+
+			err = write_timestamp(rq, 4);
+			if (err)
+				goto out;
+
+out:
+			i915_request_get(rq);
+			i915_request_add(rq);
+
+			if (i915_request_wait(rq, 0, HZ / 5) < 0)
+				err = -EIO;
+			i915_request_put(rq);
+			if (err)
+				break;
+
+			cycles[i] =
+				(rq->hwsp_seqno[4] - rq->hwsp_seqno[3]) -
+				(rq->hwsp_seqno[3] - rq->hwsp_seqno[2]);
+		}
+		i915_vma_put(nop);
+		i915_vma_put(base);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+
+		pr_info("%s: 16K MI_NOOP cycles: %u\n",
+			engine->name, trifilter(cycles));
+	}
+	if (perf_end(gt))
+		err = -EIO;
+
+	return err;
+}
+
+int intel_engine_cs_perf_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_mi_bb_start),
+		SUBTEST(perf_mi_noop),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
 
 static int intel_mmio_bases_check(void *arg)
 {
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
index e864406bd2d9..43d4d589749f 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -11,6 +11,28 @@
 #include "intel_gt_requests.h"
 #include "i915_selftest.h"
 
+static int timeline_sync(struct intel_timeline *tl)
+{
+	struct dma_fence *fence;
+	long timeout;
+
+	fence = i915_active_fence_get(&tl->last_request);
+	if (!fence)
+		return 0;
+
+	timeout = dma_fence_wait_timeout(fence, true, HZ / 2);
+	dma_fence_put(fence);
+	if (timeout < 0)
+		return timeout;
+
+	return 0;
+}
+
+static int engine_sync_barrier(struct intel_engine_cs *engine)
+{
+	return timeline_sync(engine->kernel_context->timeline);
+}
+
 struct pulse {
 	struct i915_active active;
 	struct kref kref;
@@ -53,9 +75,7 @@ static struct pulse *pulse_create(void)
 
 static void pulse_unlock_wait(struct pulse *p)
 {
-	mutex_lock(&p->active.mutex);
-	mutex_unlock(&p->active.mutex);
-	flush_work(&p->active.work);
+	i915_active_unlock_wait(&p->active);
 }
 
 static int __live_idle_pulse(struct intel_engine_cs *engine,
@@ -92,7 +112,12 @@ static int __live_idle_pulse(struct intel_engine_cs *engine,
 
 	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
 
-	if (intel_gt_retire_requests_timeout(engine->gt, HZ / 5)) {
+	if (engine_sync_barrier(engine)) {
+		struct drm_printer m = drm_err_printer("pulse");
+
+		pr_err("%s: no heartbeat pulse?\n", engine->name);
+		intel_engine_dump(engine, &m, "%s", engine->name);
+
 		err = -ETIME;
 		goto out;
 	}
@@ -175,8 +200,7 @@ static int __live_heartbeat_fast(struct intel_engine_cs *engine)
 	int err;
 	int i;
 
-	ce = intel_context_create(engine->kernel_context->gem_context,
-				  engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index d1752f15702a..09ff8e4f88af 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -6,6 +6,7 @@
  */
 
 #include "selftest_llc.h"
+#include "selftest_rc6.h"
 
 static int live_gt_resume(void *arg)
 {
@@ -50,6 +51,7 @@ static int live_gt_resume(void *arg)
 int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(live_rc6_manual),
 		SUBTEST(live_gt_resume),
 	};
 
@@ -58,3 +60,20 @@ int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
 
 	return intel_gt_live_subtests(tests, &i915->gt);
 }
+
+int intel_gt_pm_late_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		/*
+		 * These tests may leave the system in an undesirable state.
+		 * They are intended to be run last in CI and the system
+		 * rebooted afterwards.
+		 */
+		SUBTEST(live_rc6_ctx_wa),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 85e9ccf5c304..3e5e6c86e843 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -25,7 +25,9 @@
 #include <linux/kthread.h>
 
 #include "gem/i915_gem_context.h"
-#include "gt/intel_gt.h"
+
+#include "intel_gt.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 
 #include "i915_selftest.h"
@@ -308,6 +310,24 @@ static bool wait_until_running(struct hang *h, struct i915_request *rq)
 			  1000));
 }
 
+static void engine_heartbeat_disable(struct intel_engine_cs *engine,
+				     unsigned long *saved)
+{
+	*saved = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+
+	intel_engine_pm_get(engine);
+	intel_engine_park_heartbeat(engine);
+}
+
+static void engine_heartbeat_enable(struct intel_engine_cs *engine,
+				    unsigned long saved)
+{
+	intel_engine_pm_put(engine);
+
+	engine->props.heartbeat_interval_ms = saved;
+}
+
 static int igt_hang_sanitycheck(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -377,36 +397,30 @@ static int igt_reset_nop(void *arg)
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	unsigned int reset_count, count;
 	enum intel_engine_id id;
-	struct drm_file *file;
 	IGT_TIMEOUT(end_time);
 	int err = 0;
 
 	/* Check that we can reset during non-user portions of requests */
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out;
-	}
-
-	i915_gem_context_clear_bannable(ctx);
 	reset_count = i915_reset_count(global);
 	count = 0;
 	do {
 		for_each_engine(engine, gt, id) {
+			struct intel_context *ce;
 			int i;
 
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce)) {
+				err = PTR_ERR(ce);
+				break;
+			}
+
 			for (i = 0; i < 16; i++) {
 				struct i915_request *rq;
 
-				rq = igt_request_alloc(ctx, engine);
+				rq = intel_context_create_request(ce);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
 					break;
@@ -414,6 +428,8 @@ static int igt_reset_nop(void *arg)
 
 				i915_request_add(rq);
 			}
+
+			intel_context_put(ce);
 		}
 
 		igt_global_reset_lock(gt);
@@ -437,10 +453,7 @@ static int igt_reset_nop(void *arg)
 	} while (time_before(jiffies, end_time));
 	pr_info("%s: %d resets\n", __func__, count);
 
-	err = igt_flush_test(gt->i915);
-out:
-	mock_file_free(gt->i915, file);
-	if (intel_gt_is_wedged(gt))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 	return err;
 }
@@ -450,36 +463,29 @@ static int igt_reset_nop_engine(void *arg)
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
-	struct drm_file *file;
-	int err = 0;
 
 	/* Check that we can engine-reset during non-user portions */
 
 	if (!intel_has_reset_engine(gt))
 		return 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out;
-	}
-
-	i915_gem_context_clear_bannable(ctx);
 	for_each_engine(engine, gt, id) {
-		unsigned int reset_count, reset_engine_count;
-		unsigned int count;
+		unsigned int reset_count, reset_engine_count, count;
+		struct intel_context *ce;
+		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
+		int err;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			return PTR_ERR(ce);
 
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 		count = 0;
 
+		engine_heartbeat_disable(engine, &heartbeat);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			int i;
@@ -494,7 +500,7 @@ static int igt_reset_nop_engine(void *arg)
 			for (i = 0; i < 16; i++) {
 				struct i915_request *rq;
 
-				rq = igt_request_alloc(ctx, engine);
+				rq = intel_context_create_request(ce);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
 					break;
@@ -523,22 +529,18 @@ static int igt_reset_nop_engine(void *arg)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
+		engine_heartbeat_enable(engine, heartbeat);
 
-		if (err)
-			break;
+		pr_info("%s(%s): %d resets\n", __func__, engine->name, count);
 
-		err = igt_flush_test(gt->i915);
+		intel_context_put(ce);
+		if (igt_flush_test(gt->i915))
+			err = -EIO;
 		if (err)
-			break;
+			return err;
 	}
 
-	err = igt_flush_test(gt->i915);
-out:
-	mock_file_free(gt->i915, file);
-	if (intel_gt_is_wedged(gt))
-		err = -EIO;
-	return err;
+	return 0;
 }
 
 static int __igt_reset_engine(struct intel_gt *gt, bool active)
@@ -562,6 +564,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
+		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (active && !intel_engine_can_store_dword(engine))
@@ -577,7 +580,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		reset_count = i915_reset_count(global);
 		reset_engine_count = i915_reset_engine_count(global, engine);
 
-		intel_engine_pm_get(engine);
+		engine_heartbeat_disable(engine, &heartbeat);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			if (active) {
@@ -629,7 +632,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		intel_engine_pm_put(engine);
+		engine_heartbeat_enable(engine, heartbeat);
 
 		if (err)
 			break;
@@ -699,43 +702,43 @@ static int active_engine(void *data)
 	struct active_engine *arg = data;
 	struct intel_engine_cs *engine = arg->engine;
 	struct i915_request *rq[8] = {};
-	struct i915_gem_context *ctx[ARRAY_SIZE(rq)];
-	struct drm_file *file;
-	unsigned long count = 0;
+	struct intel_context *ce[ARRAY_SIZE(rq)];
+	unsigned long count;
 	int err = 0;
 
-	file = mock_file(engine->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	for (count = 0; count < ARRAY_SIZE(ctx); count++) {
-		ctx[count] = live_context(engine->i915, file);
-		if (IS_ERR(ctx[count])) {
-			err = PTR_ERR(ctx[count]);
+	for (count = 0; count < ARRAY_SIZE(ce); count++) {
+		ce[count] = intel_context_create(engine);
+		if (IS_ERR(ce[count])) {
+			err = PTR_ERR(ce[count]);
 			while (--count)
-				i915_gem_context_put(ctx[count]);
-			goto err_file;
+				intel_context_put(ce[count]);
+			return err;
 		}
 	}
 
+	count = 0;
 	while (!kthread_should_stop()) {
 		unsigned int idx = count++ & (ARRAY_SIZE(rq) - 1);
 		struct i915_request *old = rq[idx];
 		struct i915_request *new;
 
-		new = igt_request_alloc(ctx[idx], engine);
+		new = intel_context_create_request(ce[idx]);
 		if (IS_ERR(new)) {
 			err = PTR_ERR(new);
 			break;
 		}
 
-		if (arg->flags & TEST_PRIORITY)
-			ctx[idx]->sched.priority =
-				i915_prandom_u32_max_state(512, &prng);
-
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
 
+		if (engine->schedule && arg->flags & TEST_PRIORITY) {
+			struct i915_sched_attr attr = {
+				.priority =
+					i915_prandom_u32_max_state(512, &prng),
+			};
+			engine->schedule(rq[idx], &attr);
+		}
+
 		err = active_request_put(old);
 		if (err)
 			break;
@@ -749,10 +752,10 @@ static int active_engine(void *data)
 		/* Keep the first error */
 		if (!err)
 			err = err__;
+
+		intel_context_put(ce[count]);
 	}
 
-err_file:
-	mock_file_free(engine->i915, file);
 	return err;
 }
 
@@ -786,6 +789,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
+		unsigned long heartbeat;
 		IGT_TIMEOUT(end_time);
 
 		if (flags & TEST_ACTIVE &&
@@ -828,7 +832,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 
 		yield(); /* start all threads before we begin */
 
-		intel_engine_pm_get(engine);
+		engine_heartbeat_disable(engine, &heartbeat);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
 			struct i915_request *rq = NULL;
@@ -902,7 +906,8 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			}
 		} while (time_before(jiffies, end_time));
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
-		intel_engine_pm_put(engine);
+		engine_heartbeat_enable(engine, heartbeat);
+
 		pr_info("i915_reset_engine(%s:%s): %lu resets\n",
 			engine->name, test_name, count);
 
@@ -1300,32 +1305,21 @@ static int igt_reset_evict_ggtt(void *arg)
 static int igt_reset_evict_ppgtt(void *arg)
 {
 	struct intel_gt *gt = arg;
-	struct i915_gem_context *ctx;
-	struct i915_address_space *vm;
-	struct drm_file *file;
+	struct i915_ppgtt *ppgtt;
 	int err;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
+	/* aliasing == global gtt locking, covered above */
+	if (INTEL_PPGTT(gt->i915) < INTEL_PPGTT_FULL)
+		return 0;
 
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out;
-	}
+	ppgtt = i915_ppgtt_create(gt);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
-	err = 0;
-	vm = i915_gem_context_get_vm_rcu(ctx);
-	if (!i915_is_ggtt(vm)) {
-		/* aliasing == global gtt locking, covered above */
-		err = __igt_reset_evict_vma(gt, vm,
-					    evict_vma, EXEC_OBJECT_WRITE);
-	}
-	i915_vm_put(vm);
+	err = __igt_reset_evict_vma(gt, &ppgtt->vm,
+				    evict_vma, EXEC_OBJECT_WRITE);
+	i915_vm_put(&ppgtt->vm);
 
-out:
-	mock_file_free(gt->i915, file);
 	return err;
 }
 
@@ -1504,7 +1498,7 @@ static int igt_handle_error(void *arg)
 	struct intel_engine_cs *engine = gt->engine[RCS0];
 	struct hang h;
 	struct i915_request *rq;
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 	int err;
 
 	/* Check that we can issue a global GPU and engine reset */
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index eb71ac2f992c..15cda024e3e4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -50,14 +50,31 @@ static struct i915_vma *create_scratch(struct intel_gt *gt)
 	return vma;
 }
 
+static void engine_heartbeat_disable(struct intel_engine_cs *engine,
+				     unsigned long *saved)
+{
+	*saved = engine->props.heartbeat_interval_ms;
+	engine->props.heartbeat_interval_ms = 0;
+
+	intel_engine_pm_get(engine);
+	intel_engine_park_heartbeat(engine);
+}
+
+static void engine_heartbeat_enable(struct intel_engine_cs *engine,
+				    unsigned long saved)
+{
+	intel_engine_pm_put(engine);
+
+	engine->props.heartbeat_interval_ms = saved;
+}
+
 static int live_sanitycheck(void *arg)
 {
 	struct intel_gt *gt = arg;
-	struct i915_gem_engines_iter it;
-	struct i915_gem_context *ctx;
-	struct intel_context *ce;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	struct igt_spinner spin;
-	int err = -ENOMEM;
+	int err = 0;
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(gt->i915))
 		return 0;
@@ -65,17 +82,20 @@ static int live_sanitycheck(void *arg)
 	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		goto err_spin;
-
-	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
 		struct i915_request *rq;
 
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
 		rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			goto err_ctx;
+			goto out_ctx;
 		}
 
 		i915_request_add(rq);
@@ -84,21 +104,21 @@ static int live_sanitycheck(void *arg)
 			GEM_TRACE_DUMP();
 			intel_gt_set_wedged(gt);
 			err = -EIO;
-			goto err_ctx;
+			goto out_ctx;
 		}
 
 		igt_spinner_end(&spin);
 		if (igt_flush_test(gt->i915)) {
 			err = -EIO;
-			goto err_ctx;
+			goto out_ctx;
 		}
+
+out_ctx:
+		intel_context_put(ce);
+		if (err)
+			break;
 	}
 
-	err = 0;
-err_ctx:
-	i915_gem_context_unlock_engines(ctx);
-	kernel_context_close(ctx);
-err_spin:
 	igt_spinner_fini(&spin);
 	return err;
 }
@@ -106,7 +126,6 @@ err_spin:
 static int live_unlite_restore(struct intel_gt *gt, int prio)
 {
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
 	struct igt_spinner spin;
 	int err = -ENOMEM;
@@ -119,15 +138,12 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 	if (igt_spinner_init(&spin, gt))
 		return err;
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		goto err_spin;
-
 	err = 0;
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce[2] = {};
 		struct i915_request *rq[2];
 		struct igt_live_test t;
+		unsigned long saved;
 		int n;
 
 		if (prio && !intel_engine_has_preemption(engine))
@@ -140,11 +156,12 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 			err = -EIO;
 			break;
 		}
+		engine_heartbeat_disable(engine, &saved);
 
 		for (n = 0; n < ARRAY_SIZE(ce); n++) {
 			struct intel_context *tmp;
 
-			tmp = intel_context_create(ctx, engine);
+			tmp = intel_context_create(engine);
 			if (IS_ERR(tmp)) {
 				err = PTR_ERR(tmp);
 				goto err_ce;
@@ -247,14 +264,13 @@ err_ce:
 			intel_context_put(ce[n]);
 		}
 
+		engine_heartbeat_enable(engine, saved);
 		if (igt_live_test_end(&t))
 			err = -EIO;
 		if (err)
 			break;
 	}
 
-	kernel_context_close(ctx);
-err_spin:
 	igt_spinner_fini(&spin);
 	return err;
 }
@@ -309,17 +325,17 @@ emit_semaphore_chain(struct i915_request *rq, struct i915_vma *vma, int idx)
 static struct i915_request *
 semaphore_queue(struct intel_engine_cs *engine, struct i915_vma *vma, int idx)
 {
-	struct i915_gem_context *ctx;
+	struct intel_context *ce;
 	struct i915_request *rq;
 	int err;
 
-	ctx = kernel_context(engine->i915);
-	if (!ctx)
-		return ERR_PTR(-ENOMEM);
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
 
-	rq = igt_request_alloc(ctx, engine);
+	rq = intel_context_create_request(ce);
 	if (IS_ERR(rq))
-		goto out_ctx;
+		goto out_ce;
 
 	err = 0;
 	if (rq->engine->emit_init_breadcrumb)
@@ -332,8 +348,8 @@ semaphore_queue(struct intel_engine_cs *engine, struct i915_vma *vma, int idx)
 	if (err)
 		rq = ERR_PTR(err);
 
-out_ctx:
-	kernel_context_close(ctx);
+out_ce:
+	intel_context_put(ce);
 	return rq;
 }
 
@@ -348,7 +364,7 @@ release_queue(struct intel_engine_cs *engine,
 	struct i915_request *rq;
 	u32 *cs;
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -468,12 +484,16 @@ static int live_timeslice_preempt(void *arg)
 		enum intel_engine_id id;
 
 		for_each_engine(engine, gt, id) {
+			unsigned long saved;
+
 			if (!intel_engine_has_preemption(engine))
 				continue;
 
 			memset(vaddr, 0, PAGE_SIZE);
 
+			engine_heartbeat_disable(engine, &saved);
 			err = slice_semaphore_queue(engine, vma, count);
+			engine_heartbeat_enable(engine, saved);
 			if (err)
 				goto err_pin;
 
@@ -497,7 +517,7 @@ static struct i915_request *nop_request(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		return rq;
 
@@ -507,13 +527,19 @@ static struct i915_request *nop_request(struct intel_engine_cs *engine)
 	return rq;
 }
 
-static void wait_for_submit(struct intel_engine_cs *engine,
-			    struct i915_request *rq)
+static int wait_for_submit(struct intel_engine_cs *engine,
+			   struct i915_request *rq,
+			   unsigned long timeout)
 {
+	timeout += jiffies;
 	do {
 		cond_resched();
 		intel_engine_flush_submission(engine);
-	} while (!i915_request_is_active(rq));
+		if (i915_request_is_active(rq))
+			return 0;
+	} while (time_before(jiffies, timeout));
+
+	return -ETIME;
 }
 
 static long timeslice_threshold(const struct intel_engine_cs *engine)
@@ -566,40 +592,49 @@ static int live_timeslice_queue(void *arg)
 			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
 		};
 		struct i915_request *rq, *nop;
+		unsigned long saved;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
+		engine_heartbeat_disable(engine, &saved);
 		memset(vaddr, 0, PAGE_SIZE);
 
 		/* ELSP[0]: semaphore wait */
 		rq = semaphore_queue(engine, vma, 0);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
-			goto err_pin;
+			goto err_heartbeat;
 		}
 		engine->schedule(rq, &attr);
-		wait_for_submit(engine, rq);
+		err = wait_for_submit(engine, rq, HZ / 2);
+		if (err) {
+			pr_err("%s: Timed out trying to submit semaphores\n",
+			       engine->name);
+			goto err_rq;
+		}
 
 		/* ELSP[1]: nop request */
 		nop = nop_request(engine);
 		if (IS_ERR(nop)) {
 			err = PTR_ERR(nop);
-			i915_request_put(rq);
-			goto err_pin;
+			goto err_rq;
 		}
-		wait_for_submit(engine, nop);
+		err = wait_for_submit(engine, nop, HZ / 2);
 		i915_request_put(nop);
+		if (err) {
+			pr_err("%s: Timed out trying to submit nop\n",
+			       engine->name);
+			goto err_rq;
+		}
 
 		GEM_BUG_ON(i915_request_completed(rq));
 		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
 
 		/* Queue: semaphore signal, matching priority as semaphore */
 		err = release_queue(engine, vma, 1, effective_prio(rq));
-		if (err) {
-			i915_request_put(rq);
-			goto err_pin;
-		}
+		if (err)
+			goto err_rq;
 
 		intel_engine_flush_submission(engine);
 		if (!READ_ONCE(engine->execlists.timer.expires) &&
@@ -630,12 +665,14 @@ static int live_timeslice_queue(void *arg)
 			memset(vaddr, 0xff, PAGE_SIZE);
 			err = -EIO;
 		}
+err_rq:
 		i915_request_put(rq);
+err_heartbeat:
+		engine_heartbeat_enable(engine, saved);
 		if (err)
 			break;
 	}
 
-err_pin:
 	i915_vma_unpin(vma);
 err_map:
 	i915_gem_object_unpin_map(obj);
@@ -748,15 +785,19 @@ static int live_busywait_preempt(void *arg)
 		*cs++ = 0;
 
 		intel_ring_advance(lo, cs);
+
+		i915_request_get(lo);
 		i915_request_add(lo);
 
 		if (wait_for(READ_ONCE(*map), 10)) {
+			i915_request_put(lo);
 			err = -ETIMEDOUT;
 			goto err_vma;
 		}
 
 		/* Low priority request should be busywaiting now */
 		if (i915_request_wait(lo, 0, 1) != -ETIME) {
+			i915_request_put(lo);
 			pr_err("%s: Busywaiting request did not!\n",
 			       engine->name);
 			err = -EIO;
@@ -766,6 +807,7 @@ static int live_busywait_preempt(void *arg)
 		hi = igt_request_alloc(ctx_hi, engine);
 		if (IS_ERR(hi)) {
 			err = PTR_ERR(hi);
+			i915_request_put(lo);
 			goto err_vma;
 		}
 
@@ -773,6 +815,7 @@ static int live_busywait_preempt(void *arg)
 		if (IS_ERR(cs)) {
 			err = PTR_ERR(cs);
 			i915_request_add(hi);
+			i915_request_put(lo);
 			goto err_vma;
 		}
 
@@ -793,11 +836,13 @@ static int live_busywait_preempt(void *arg)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 			GEM_TRACE_DUMP();
 
+			i915_request_put(lo);
 			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_vma;
 		}
 		GEM_BUG_ON(READ_ONCE(*map));
+		i915_request_put(lo);
 
 		if (igt_live_test_end(&t)) {
 			err = -EIO;
@@ -1108,7 +1153,7 @@ static int live_nopreempt(void *arg)
 		}
 
 		/* Low priority client, but unpreemptable! */
-		rq_a->flags |= I915_REQUEST_NOPREEMPT;
+		__set_bit(I915_FENCE_FLAG_NOPREEMPT, &rq_a->fence.flags);
 
 		i915_request_add(rq_a);
 		if (!igt_wait_for_spinner(&a.spin, rq_a)) {
@@ -1187,13 +1232,13 @@ static int __cancel_active0(struct live_preempt_cancel *arg)
 				__func__, arg->engine->name))
 		return -EIO;
 
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq = spinner_create_request(&arg->a.spin,
 				    arg->a.ctx, arg->engine,
 				    MI_ARB_CHECK);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	clear_bit(CONTEXT_BANNED, &rq->context->flags);
 	i915_request_get(rq);
 	i915_request_add(rq);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
@@ -1201,7 +1246,7 @@ static int __cancel_active0(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	i915_gem_context_set_banned(arg->a.ctx);
+	intel_context_set_banned(rq->context);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -1236,13 +1281,13 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 				__func__, arg->engine->name))
 		return -EIO;
 
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq[0] = spinner_create_request(&arg->a.spin,
 				       arg->a.ctx, arg->engine,
 				       MI_NOOP); /* no preemption */
 	if (IS_ERR(rq[0]))
 		return PTR_ERR(rq[0]);
 
+	clear_bit(CONTEXT_BANNED, &rq[0]->context->flags);
 	i915_request_get(rq[0]);
 	i915_request_add(rq[0]);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
@@ -1250,7 +1295,6 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
 	rq[1] = spinner_create_request(&arg->b.spin,
 				       arg->b.ctx, arg->engine,
 				       MI_ARB_CHECK);
@@ -1259,13 +1303,14 @@ static int __cancel_active1(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
+	clear_bit(CONTEXT_BANNED, &rq[1]->context->flags);
 	i915_request_get(rq[1]);
 	err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
 	i915_request_add(rq[1]);
 	if (err)
 		goto out;
 
-	i915_gem_context_set_banned(arg->b.ctx);
+	intel_context_set_banned(rq[1]->context);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -1308,13 +1353,13 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 				__func__, arg->engine->name))
 		return -EIO;
 
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq[0] = spinner_create_request(&arg->a.spin,
 				       arg->a.ctx, arg->engine,
 				       MI_ARB_CHECK);
 	if (IS_ERR(rq[0]))
 		return PTR_ERR(rq[0]);
 
+	clear_bit(CONTEXT_BANNED, &rq[0]->context->flags);
 	i915_request_get(rq[0]);
 	i915_request_add(rq[0]);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
@@ -1322,13 +1367,13 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
 	rq[1] = igt_request_alloc(arg->b.ctx, arg->engine);
 	if (IS_ERR(rq[1])) {
 		err = PTR_ERR(rq[1]);
 		goto out;
 	}
 
+	clear_bit(CONTEXT_BANNED, &rq[1]->context->flags);
 	i915_request_get(rq[1]);
 	err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
 	i915_request_add(rq[1]);
@@ -1349,7 +1394,7 @@ static int __cancel_queued(struct live_preempt_cancel *arg)
 	if (err)
 		goto out;
 
-	i915_gem_context_set_banned(arg->a.ctx);
+	intel_context_set_banned(rq[2]->context);
 	err = intel_engine_pulse(arg->engine);
 	if (err)
 		goto out;
@@ -1396,13 +1441,13 @@ static int __cancel_hostile(struct live_preempt_cancel *arg)
 		return 0;
 
 	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
-	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
 	rq = spinner_create_request(&arg->a.spin,
 				    arg->a.ctx, arg->engine,
 				    MI_NOOP); /* preemption disabled */
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	clear_bit(CONTEXT_BANNED, &rq->context->flags);
 	i915_request_get(rq);
 	i915_request_add(rq);
 	if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
@@ -1410,7 +1455,7 @@ static int __cancel_hostile(struct live_preempt_cancel *arg)
 		goto out;
 	}
 
-	i915_gem_context_set_banned(arg->a.ctx);
+	intel_context_set_banned(rq->context);
 	err = intel_engine_pulse(arg->engine); /* force reset */
 	if (err)
 		goto out;
@@ -1665,6 +1710,7 @@ static int live_suppress_wait_preempt(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct preempt_client client[4];
+	struct i915_request *rq[ARRAY_SIZE(client)] = {};
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err = -ENOMEM;
@@ -1698,7 +1744,6 @@ static int live_suppress_wait_preempt(void *arg)
 			continue;
 
 		for (depth = 0; depth < ARRAY_SIZE(client); depth++) {
-			struct i915_request *rq[ARRAY_SIZE(client)];
 			struct i915_request *dummy;
 
 			engine->execlists.preempt_hang.count = 0;
@@ -1708,18 +1753,22 @@ static int live_suppress_wait_preempt(void *arg)
 				goto err_client_3;
 
 			for (i = 0; i < ARRAY_SIZE(client); i++) {
-				rq[i] = spinner_create_request(&client[i].spin,
-							       client[i].ctx, engine,
-							       MI_NOOP);
-				if (IS_ERR(rq[i])) {
-					err = PTR_ERR(rq[i]);
+				struct i915_request *this;
+
+				this = spinner_create_request(&client[i].spin,
+							      client[i].ctx, engine,
+							      MI_NOOP);
+				if (IS_ERR(this)) {
+					err = PTR_ERR(this);
 					goto err_wedged;
 				}
 
 				/* Disable NEWCLIENT promotion */
-				__i915_active_fence_set(&i915_request_timeline(rq[i])->last_request,
+				__i915_active_fence_set(&i915_request_timeline(this)->last_request,
 							&dummy->fence);
-				i915_request_add(rq[i]);
+
+				rq[i] = i915_request_get(this);
+				i915_request_add(this);
 			}
 
 			dummy_request_free(dummy);
@@ -1740,8 +1789,11 @@ static int live_suppress_wait_preempt(void *arg)
 				goto err_wedged;
 			}
 
-			for (i = 0; i < ARRAY_SIZE(client); i++)
+			for (i = 0; i < ARRAY_SIZE(client); i++) {
 				igt_spinner_end(&client[i].spin);
+				i915_request_put(rq[i]);
+				rq[i] = NULL;
+			}
 
 			if (igt_flush_test(gt->i915))
 				goto err_wedged;
@@ -1769,8 +1821,10 @@ err_client_0:
 	return err;
 
 err_wedged:
-	for (i = 0; i < ARRAY_SIZE(client); i++)
+	for (i = 0; i < ARRAY_SIZE(client); i++) {
 		igt_spinner_end(&client[i].spin);
+		i915_request_put(rq[i]);
+	}
 	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_client_3;
@@ -1815,6 +1869,8 @@ static int live_chain_preempt(void *arg)
 					    MI_ARB_CHECK);
 		if (IS_ERR(rq))
 			goto err_wedged;
+
+		i915_request_get(rq);
 		i915_request_add(rq);
 
 		ring_size = rq->wa_tail - rq->head;
@@ -1827,8 +1883,10 @@ static int live_chain_preempt(void *arg)
 		igt_spinner_end(&lo.spin);
 		if (i915_request_wait(rq, 0, HZ / 2) < 0) {
 			pr_err("Timed out waiting to flush %s\n", engine->name);
+			i915_request_put(rq);
 			goto err_wedged;
 		}
+		i915_request_put(rq);
 
 		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
@@ -1862,6 +1920,8 @@ static int live_chain_preempt(void *arg)
 			rq = igt_request_alloc(hi.ctx, engine);
 			if (IS_ERR(rq))
 				goto err_wedged;
+
+			i915_request_get(rq);
 			i915_request_add(rq);
 			engine->schedule(rq, &attr);
 
@@ -1874,14 +1934,19 @@ static int live_chain_preempt(void *arg)
 				       count);
 				intel_engine_dump(engine, &p,
 						  "%s\n", engine->name);
+				i915_request_put(rq);
 				goto err_wedged;
 			}
 			igt_spinner_end(&lo.spin);
+			i915_request_put(rq);
 
 			rq = igt_request_alloc(lo.ctx, engine);
 			if (IS_ERR(rq))
 				goto err_wedged;
+
+			i915_request_get(rq);
 			i915_request_add(rq);
+
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				struct drm_printer p =
 					drm_info_printer(gt->i915->drm.dev);
@@ -1890,8 +1955,11 @@ static int live_chain_preempt(void *arg)
 				       count);
 				intel_engine_dump(engine, &p,
 						  "%s\n", engine->name);
+
+				i915_request_put(rq);
 				goto err_wedged;
 			}
+			i915_request_put(rq);
 		}
 
 		if (igt_live_test_end(&t)) {
@@ -1915,6 +1983,201 @@ err_wedged:
 	goto err_client_lo;
 }
 
+static int create_gang(struct intel_engine_cs *engine,
+		       struct i915_request **prev)
+{
+	struct drm_i915_gem_object *obj;
+	struct intel_context *ce;
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	u32 *cs;
+	int err;
+
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	obj = i915_gem_object_create_internal(engine->i915, 4096);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto err_ce;
+	}
+
+	vma = i915_vma_instance(obj, ce->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto err_obj;
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(cs))
+		goto err_obj;
+
+	/* Semaphore target: spin until zero */
+	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
+
+	*cs++ = MI_SEMAPHORE_WAIT |
+		MI_SEMAPHORE_POLL |
+		MI_SEMAPHORE_SAD_EQ_SDD;
+	*cs++ = 0;
+	*cs++ = lower_32_bits(vma->node.start);
+	*cs++ = upper_32_bits(vma->node.start);
+
+	if (*prev) {
+		u64 offset = (*prev)->batch->node.start;
+
+		/* Terminate the spinner in the next lower priority batch. */
+		*cs++ = MI_STORE_DWORD_IMM_GEN4;
+		*cs++ = lower_32_bits(offset);
+		*cs++ = upper_32_bits(offset);
+		*cs++ = 0;
+	}
+
+	*cs++ = MI_BATCH_BUFFER_END;
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		goto err_obj;
+
+	rq->batch = vma;
+	i915_request_get(rq);
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, false);
+	if (!err)
+		err = i915_vma_move_to_active(vma, rq, 0);
+	if (!err)
+		err = rq->engine->emit_bb_start(rq,
+						vma->node.start,
+						PAGE_SIZE, 0);
+	i915_vma_unlock(vma);
+	i915_request_add(rq);
+	if (err)
+		goto err_rq;
+
+	i915_gem_object_put(obj);
+	intel_context_put(ce);
+
+	rq->client_link.next = &(*prev)->client_link;
+	*prev = rq;
+	return 0;
+
+err_rq:
+	i915_request_put(rq);
+err_obj:
+	i915_gem_object_put(obj);
+err_ce:
+	intel_context_put(ce);
+	return err;
+}
+
+static int live_preempt_gang(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
+		return 0;
+
+	/*
+	 * Build as long a chain of preempters as we can, with each
+	 * request higher priority than the last. Once we are ready, we release
+	 * the last batch which then precolates down the chain, each releasing
+	 * the next oldest in turn. The intent is to simply push as hard as we
+	 * can with the number of preemptions, trying to exceed narrow HW
+	 * limits. At a minimum, we insist that we can sort all the user
+	 * high priority levels into execution order.
+	 */
+
+	for_each_engine(engine, gt, id) {
+		struct i915_request *rq = NULL;
+		struct igt_live_test t;
+		IGT_TIMEOUT(end_time);
+		int prio = 0;
+		int err = 0;
+		u32 *cs;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name))
+			return -EIO;
+
+		do {
+			struct i915_sched_attr attr = {
+				.priority = I915_USER_PRIORITY(prio++),
+			};
+
+			err = create_gang(engine, &rq);
+			if (err)
+				break;
+
+			/* Submit each spinner at increasing priority */
+			engine->schedule(rq, &attr);
+
+			if (prio <= I915_PRIORITY_MAX)
+				continue;
+
+			if (prio > (INT_MAX >> I915_USER_PRIORITY_SHIFT))
+				break;
+
+			if (__igt_timeout(end_time, NULL))
+				break;
+		} while (1);
+		pr_debug("%s: Preempt chain of %d requests\n",
+			 engine->name, prio);
+
+		/*
+		 * Such that the last spinner is the highest priority and
+		 * should execute first. When that spinner completes,
+		 * it will terminate the next lowest spinner until there
+		 * are no more spinners and the gang is complete.
+		 */
+		cs = i915_gem_object_pin_map(rq->batch->obj, I915_MAP_WC);
+		if (!IS_ERR(cs)) {
+			*cs = 0;
+			i915_gem_object_unpin_map(rq->batch->obj);
+		} else {
+			err = PTR_ERR(cs);
+			intel_gt_set_wedged(gt);
+		}
+
+		while (rq) { /* wait for each rq from highest to lowest prio */
+			struct i915_request *n =
+				list_next_entry(rq, client_link);
+
+			if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0) {
+				struct drm_printer p =
+					drm_info_printer(engine->i915->drm.dev);
+
+				pr_err("Failed to flush chain of %d requests, at %d\n",
+				       prio, rq_prio(rq) >> I915_USER_PRIORITY_SHIFT);
+				intel_engine_dump(engine, &p,
+						  "%s\n", engine->name);
+
+				err = -ETIME;
+			}
+
+			i915_request_put(rq);
+			rq = n;
+		}
+
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int live_preempt_hang(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -2391,28 +2654,18 @@ static int nop_virtual_engine(struct intel_gt *gt,
 #define CHAIN BIT(0)
 {
 	IGT_TIMEOUT(end_time);
-	struct i915_request *request[16];
-	struct i915_gem_context *ctx[16];
+	struct i915_request *request[16] = {};
 	struct intel_context *ve[16];
 	unsigned long n, prime, nc;
 	struct igt_live_test t;
 	ktime_t times[2] = {};
 	int err;
 
-	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ctx));
+	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve));
 
 	for (n = 0; n < nctx; n++) {
-		ctx[n] = kernel_context(gt->i915);
-		if (!ctx[n]) {
-			err = -ENOMEM;
-			nctx = n;
-			goto out;
-		}
-
-		ve[n] = intel_execlists_create_virtual(ctx[n],
-						       siblings, nsibling);
+		ve[n] = intel_execlists_create_virtual(siblings, nsibling);
 		if (IS_ERR(ve[n])) {
-			kernel_context_close(ctx[n]);
 			err = PTR_ERR(ve[n]);
 			nctx = n;
 			goto out;
@@ -2421,7 +2674,6 @@ static int nop_virtual_engine(struct intel_gt *gt,
 		err = intel_context_pin(ve[n]);
 		if (err) {
 			intel_context_put(ve[n]);
-			kernel_context_close(ctx[n]);
 			nctx = n;
 			goto out;
 		}
@@ -2437,27 +2689,35 @@ static int nop_virtual_engine(struct intel_gt *gt,
 		if (flags & CHAIN) {
 			for (nc = 0; nc < nctx; nc++) {
 				for (n = 0; n < prime; n++) {
-					request[nc] =
-						i915_request_create(ve[nc]);
-					if (IS_ERR(request[nc])) {
-						err = PTR_ERR(request[nc]);
+					struct i915_request *rq;
+
+					rq = i915_request_create(ve[nc]);
+					if (IS_ERR(rq)) {
+						err = PTR_ERR(rq);
 						goto out;
 					}
 
-					i915_request_add(request[nc]);
+					if (request[nc])
+						i915_request_put(request[nc]);
+					request[nc] = i915_request_get(rq);
+					i915_request_add(rq);
 				}
 			}
 		} else {
 			for (n = 0; n < prime; n++) {
 				for (nc = 0; nc < nctx; nc++) {
-					request[nc] =
-						i915_request_create(ve[nc]);
-					if (IS_ERR(request[nc])) {
-						err = PTR_ERR(request[nc]);
+					struct i915_request *rq;
+
+					rq = i915_request_create(ve[nc]);
+					if (IS_ERR(rq)) {
+						err = PTR_ERR(rq);
 						goto out;
 					}
 
-					i915_request_add(request[nc]);
+					if (request[nc])
+						i915_request_put(request[nc]);
+					request[nc] = i915_request_get(rq);
+					i915_request_add(rq);
 				}
 			}
 		}
@@ -2483,6 +2743,11 @@ static int nop_virtual_engine(struct intel_gt *gt,
 		if (prime == 1)
 			times[0] = times[1];
 
+		for (nc = 0; nc < nctx; nc++) {
+			i915_request_put(request[nc]);
+			request[nc] = NULL;
+		}
+
 		if (__igt_timeout(end_time, NULL))
 			break;
 	}
@@ -2500,9 +2765,9 @@ out:
 		err = -EIO;
 
 	for (nc = 0; nc < nctx; nc++) {
+		i915_request_put(request[nc]);
 		intel_context_unpin(ve[nc]);
 		intel_context_put(ve[nc]);
-		kernel_context_close(ctx[nc]);
 	}
 	return err;
 }
@@ -2561,7 +2826,6 @@ static int mask_virtual_engine(struct intel_gt *gt,
 			       unsigned int nsibling)
 {
 	struct i915_request *request[MAX_ENGINE_INSTANCE + 1];
-	struct i915_gem_context *ctx;
 	struct intel_context *ve;
 	struct igt_live_test t;
 	unsigned int n;
@@ -2572,11 +2836,7 @@ static int mask_virtual_engine(struct intel_gt *gt,
 	 * restrict it to our desired engine within the virtual engine.
 	 */
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		return -ENOMEM;
-
-	ve = intel_execlists_create_virtual(ctx, siblings, nsibling);
+	ve = intel_execlists_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_close;
@@ -2644,7 +2904,6 @@ out_unpin:
 out_put:
 	intel_context_put(ve);
 out_close:
-	kernel_context_close(ctx);
 	return err;
 }
 
@@ -2684,7 +2943,6 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 				    unsigned int nsibling)
 {
 	struct i915_request *last = NULL;
-	struct i915_gem_context *ctx;
 	struct intel_context *ve;
 	struct i915_vma *scratch;
 	struct igt_live_test t;
@@ -2692,17 +2950,11 @@ static int preserved_virtual_engine(struct intel_gt *gt,
 	int err = 0;
 	u32 *cs;
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
-		return -ENOMEM;
-
 	scratch = create_scratch(siblings[0]->gt);
-	if (IS_ERR(scratch)) {
-		err = PTR_ERR(scratch);
-		goto out_close;
-	}
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
 
-	ve = intel_execlists_create_virtual(ctx, siblings, nsibling);
+	ve = intel_execlists_create_virtual(siblings, nsibling);
 	if (IS_ERR(ve)) {
 		err = PTR_ERR(ve);
 		goto out_scratch;
@@ -2785,8 +3037,6 @@ out_put:
 	intel_context_put(ve);
 out_scratch:
 	i915_vma_unpin_and_release(&scratch, 0);
-out_close:
-	kernel_context_close(ctx);
 	return err;
 }
 
@@ -2838,16 +3088,54 @@ static int bond_virtual_engine(struct intel_gt *gt,
 #define BOND_SCHEDULE BIT(0)
 {
 	struct intel_engine_cs *master;
-	struct i915_gem_context *ctx;
 	struct i915_request *rq[16];
 	enum intel_engine_id id;
+	struct igt_spinner spin;
 	unsigned long n;
 	int err;
 
+	/*
+	 * A set of bonded requests is intended to be run concurrently
+	 * across a number of engines. We use one request per-engine
+	 * and a magic fence to schedule each of the bonded requests
+	 * at the same time. A consequence of our current scheduler is that
+	 * we only move requests to the HW ready queue when the request
+	 * becomes ready, that is when all of its prerequisite fences have
+	 * been signaled. As one of those fences is the master submit fence,
+	 * there is a delay on all secondary fences as the HW may be
+	 * currently busy. Equally, as all the requests are independent,
+	 * they may have other fences that delay individual request
+	 * submission to HW. Ergo, we do not guarantee that all requests are
+	 * immediately submitted to HW at the same time, just that if the
+	 * rules are abided by, they are ready at the same time as the
+	 * first is submitted. Userspace can embed semaphores in its batch
+	 * to ensure parallel execution of its phases as it requires.
+	 * Though naturally it gets requested that perhaps the scheduler should
+	 * take care of parallel execution, even across preemption events on
+	 * different HW. (The proper answer is of course "lalalala".)
+	 *
+	 * With the submit-fence, we have identified three possible phases
+	 * of synchronisation depending on the master fence: queued (not
+	 * ready), executing, and signaled. The first two are quite simple
+	 * and checked below. However, the signaled master fence handling is
+	 * contentious. Currently we do not distinguish between a signaled
+	 * fence and an expired fence, as once signaled it does not convey
+	 * any information about the previous execution. It may even be freed
+	 * and hence checking later it may not exist at all. Ergo we currently
+	 * do not apply the bonding constraint for an already signaled fence,
+	 * as our expectation is that it should not constrain the secondaries
+	 * and is outside of the scope of the bonded request API (i.e. all
+	 * userspace requests are meant to be running in parallel). As
+	 * it imposes no constraint, and is effectively a no-op, we do not
+	 * check below as normal execution flows are checked extensively above.
+	 *
+	 * XXX Is the degenerate handling of signaled submit fences the
+	 * expected behaviour for userpace?
+	 */
+
 	GEM_BUG_ON(nsibling >= ARRAY_SIZE(rq) - 1);
 
-	ctx = kernel_context(gt->i915);
-	if (!ctx)
+	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
 	err = 0;
@@ -2860,7 +3148,9 @@ static int bond_virtual_engine(struct intel_gt *gt,
 
 		memset_p((void *)rq, ERR_PTR(-EINVAL), ARRAY_SIZE(rq));
 
-		rq[0] = igt_request_alloc(ctx, master);
+		rq[0] = igt_spinner_create_request(&spin,
+						   master->kernel_context,
+						   MI_NOOP);
 		if (IS_ERR(rq[0])) {
 			err = PTR_ERR(rq[0]);
 			goto out;
@@ -2873,16 +3163,21 @@ static int bond_virtual_engine(struct intel_gt *gt,
 							       &fence,
 							       GFP_KERNEL);
 		}
+
 		i915_request_add(rq[0]);
 		if (err < 0)
 			goto out;
 
+		if (!(flags & BOND_SCHEDULE) &&
+		    !igt_wait_for_spinner(&spin, rq[0])) {
+			err = -EIO;
+			goto out;
+		}
+
 		for (n = 0; n < nsibling; n++) {
 			struct intel_context *ve;
 
-			ve = intel_execlists_create_virtual(ctx,
-							    siblings,
-							    nsibling);
+			ve = intel_execlists_create_virtual(siblings, nsibling);
 			if (IS_ERR(ve)) {
 				err = PTR_ERR(ve);
 				onstack_fence_fini(&fence);
@@ -2924,6 +3219,8 @@ static int bond_virtual_engine(struct intel_gt *gt,
 			}
 		}
 		onstack_fence_fini(&fence);
+		intel_engine_flush_submission(master);
+		igt_spinner_end(&spin);
 
 		if (i915_request_wait(rq[0], 0, HZ / 10) < 0) {
 			pr_err("Master request did not execute (on %s)!\n",
@@ -2960,7 +3257,7 @@ out:
 	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
-	kernel_context_close(ctx);
+	igt_spinner_fini(&spin);
 	return err;
 }
 
@@ -3028,6 +3325,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_suppress_self_preempt),
 		SUBTEST(live_suppress_wait_preempt),
 		SUBTEST(live_chain_preempt),
+		SUBTEST(live_preempt_gang),
 		SUBTEST(live_preempt_hang),
 		SUBTEST(live_preempt_timeout),
 		SUBTEST(live_preempt_smoke),
@@ -3080,7 +3378,7 @@ static int live_lrc_layout(void *arg)
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	u32 *mem;
+	u32 *lrc;
 	int err;
 
 	/*
@@ -3088,13 +3386,13 @@ static int live_lrc_layout(void *arg)
 	 * match the layout saved by HW.
 	 */
 
-	mem = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!mem)
+	lrc = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!lrc)
 		return -ENOMEM;
 
 	err = 0;
 	for_each_engine(engine, gt, id) {
-		u32 *hw, *lrc;
+		u32 *hw;
 		int dw;
 
 		if (!engine->default_state)
@@ -3108,8 +3406,7 @@ static int live_lrc_layout(void *arg)
 		}
 		hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
 
-		lrc = memset(mem, 0, PAGE_SIZE);
-		execlists_init_reg_state(lrc,
+		execlists_init_reg_state(memset(lrc, POISON_INUSE, PAGE_SIZE),
 					 engine->kernel_context,
 					 engine,
 					 engine->kernel_context->ring,
@@ -3124,6 +3421,13 @@ static int live_lrc_layout(void *arg)
 				continue;
 			}
 
+			if (lrc[dw] == 0) {
+				pr_debug("%s: skipped instruction %x at dword %d\n",
+					 engine->name, lri, dw);
+				dw++;
+				continue;
+			}
+
 			if ((lri & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) {
 				pr_err("%s: Expected LRI command at dword %d, found %08x\n",
 				       engine->name, dw, lri);
@@ -3172,7 +3476,7 @@ static int live_lrc_layout(void *arg)
 			break;
 	}
 
-	kfree(mem);
+	kfree(lrc);
 	return err;
 }
 
@@ -3207,12 +3511,12 @@ static int live_lrc_fixed(void *arg)
 		} tbl[] = {
 			{
 				i915_mmio_reg_offset(RING_START(engine->mmio_base)),
-				CTX_RING_BUFFER_START - 1,
+				CTX_RING_START - 1,
 				"RING_START"
 			},
 			{
 				i915_mmio_reg_offset(RING_CTL(engine->mmio_base)),
-				CTX_RING_BUFFER_CONTROL - 1,
+				CTX_RING_CTL - 1,
 				"RING_CTL"
 			},
 			{
@@ -3231,7 +3535,7 @@ static int live_lrc_fixed(void *arg)
 				"RING_MI_MODE"
 			},
 			{
-				engine->mmio_base + 0x110,
+				i915_mmio_reg_offset(RING_BBSTATE(engine->mmio_base)),
 				CTX_BB_STATE - 1,
 				"BB_STATE"
 			},
@@ -3270,8 +3574,7 @@ static int live_lrc_fixed(void *arg)
 	return err;
 }
 
-static int __live_lrc_state(struct i915_gem_context *fixme,
-			    struct intel_engine_cs *engine,
+static int __live_lrc_state(struct intel_engine_cs *engine,
 			    struct i915_vma *scratch)
 {
 	struct intel_context *ce;
@@ -3286,7 +3589,7 @@ static int __live_lrc_state(struct i915_gem_context *fixme,
 	int err;
 	int n;
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
@@ -3360,7 +3663,6 @@ static int live_lrc_state(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	struct i915_vma *scratch;
 	enum intel_engine_id id;
 	int err = 0;
@@ -3370,18 +3672,12 @@ static int live_lrc_state(void *arg)
 	 * intel_context.
 	 */
 
-	fixme = kernel_context(gt->i915);
-	if (!fixme)
-		return -ENOMEM;
-
 	scratch = create_scratch(gt);
-	if (IS_ERR(scratch)) {
-		err = PTR_ERR(scratch);
-		goto out_close;
-	}
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
 
 	for_each_engine(engine, gt, id) {
-		err = __live_lrc_state(fixme, engine, scratch);
+		err = __live_lrc_state(engine, scratch);
 		if (err)
 			break;
 	}
@@ -3390,8 +3686,6 @@ static int live_lrc_state(void *arg)
 		err = -EIO;
 
 	i915_vma_unpin_and_release(&scratch, 0);
-out_close:
-	kernel_context_close(fixme);
 	return err;
 }
 
@@ -3401,7 +3695,7 @@ static int gpr_make_dirty(struct intel_engine_cs *engine)
 	u32 *cs;
 	int n;
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -3424,8 +3718,7 @@ static int gpr_make_dirty(struct intel_engine_cs *engine)
 	return 0;
 }
 
-static int __live_gpr_clear(struct i915_gem_context *fixme,
-			    struct intel_engine_cs *engine,
+static int __live_gpr_clear(struct intel_engine_cs *engine,
 			    struct i915_vma *scratch)
 {
 	struct intel_context *ce;
@@ -3441,7 +3734,7 @@ static int __live_gpr_clear(struct i915_gem_context *fixme,
 	if (err)
 		return err;
 
-	ce = intel_context_create(fixme, engine);
+	ce = intel_context_create(engine);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
@@ -3503,7 +3796,6 @@ static int live_gpr_clear(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *fixme;
 	struct i915_vma *scratch;
 	enum intel_engine_id id;
 	int err = 0;
@@ -3513,18 +3805,12 @@ static int live_gpr_clear(void *arg)
 	 * to avoid leaking any information from previous contexts.
 	 */
 
-	fixme = kernel_context(gt->i915);
-	if (!fixme)
-		return -ENOMEM;
-
 	scratch = create_scratch(gt);
-	if (IS_ERR(scratch)) {
-		err = PTR_ERR(scratch);
-		goto out_close;
-	}
+	if (IS_ERR(scratch))
+		return PTR_ERR(scratch);
 
 	for_each_engine(engine, gt, id) {
-		err = __live_gpr_clear(fixme, engine, scratch);
+		err = __live_gpr_clear(engine, scratch);
 		if (err)
 			break;
 	}
@@ -3533,8 +3819,6 @@ static int live_gpr_clear(void *arg)
 		err = -EIO;
 
 	i915_vma_unpin_and_release(&scratch, 0);
-out_close:
-	kernel_context_close(fixme);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c
new file mode 100644
index 000000000000..de1f83100fb6
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c
@@ -0,0 +1,419 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "gt/intel_engine_pm.h"
+#include "i915_selftest.h"
+
+#include "gem/selftests/mock_context.h"
+#include "selftests/igt_reset.h"
+#include "selftests/igt_spinner.h"
+
+struct live_mocs {
+	struct drm_i915_mocs_table table;
+	struct i915_vma *scratch;
+	void *vaddr;
+};
+
+static int request_add_sync(struct i915_request *rq, int err)
+{
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -ETIME;
+	i915_request_put(rq);
+
+	return err;
+}
+
+static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin)
+{
+	int err = 0;
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (spin && !igt_wait_for_spinner(spin, rq))
+		err = -ETIME;
+	i915_request_put(rq);
+
+	return err;
+}
+
+static struct i915_vma *create_scratch(struct intel_gt *gt)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err;
+
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHING_CACHED);
+
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
+	if (IS_ERR(vma)) {
+		i915_gem_object_put(obj);
+		return vma;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL);
+	if (err) {
+		i915_gem_object_put(obj);
+		return ERR_PTR(err);
+	}
+
+	return vma;
+}
+
+static int live_mocs_init(struct live_mocs *arg, struct intel_gt *gt)
+{
+	int err;
+
+	if (!get_mocs_settings(gt->i915, &arg->table))
+		return -EINVAL;
+
+	arg->scratch = create_scratch(gt);
+	if (IS_ERR(arg->scratch))
+		return PTR_ERR(arg->scratch);
+
+	arg->vaddr = i915_gem_object_pin_map(arg->scratch->obj, I915_MAP_WB);
+	if (IS_ERR(arg->vaddr)) {
+		err = PTR_ERR(arg->vaddr);
+		goto err_scratch;
+	}
+
+	return 0;
+
+err_scratch:
+	i915_vma_unpin_and_release(&arg->scratch, 0);
+	return err;
+}
+
+static void live_mocs_fini(struct live_mocs *arg)
+{
+	i915_vma_unpin_and_release(&arg->scratch, I915_VMA_RELEASE_MAP);
+}
+
+static int read_regs(struct i915_request *rq,
+		     u32 addr, unsigned int count,
+		     uint32_t *offset)
+{
+	unsigned int i;
+	u32 *cs;
+
+	GEM_BUG_ON(!IS_ALIGNED(*offset, sizeof(u32)));
+
+	cs = intel_ring_begin(rq, 4 * count);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	for (i = 0; i < count; i++) {
+		*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+		*cs++ = addr;
+		*cs++ = *offset;
+		*cs++ = 0;
+
+		addr += sizeof(u32);
+		*offset += sizeof(u32);
+	}
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static int read_mocs_table(struct i915_request *rq,
+			   const struct drm_i915_mocs_table *table,
+			   uint32_t *offset)
+{
+	u32 addr;
+
+	if (HAS_GLOBAL_MOCS_REGISTERS(rq->i915))
+		addr = global_mocs_offset();
+	else
+		addr = mocs_offset(rq->engine);
+
+	return read_regs(rq, addr, table->n_entries, offset);
+}
+
+static int read_l3cc_table(struct i915_request *rq,
+			   const struct drm_i915_mocs_table *table,
+			   uint32_t *offset)
+{
+	u32 addr = i915_mmio_reg_offset(GEN9_LNCFCMOCS(0));
+
+	return read_regs(rq, addr, (table->n_entries + 1) / 2, offset);
+}
+
+static int check_mocs_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table,
+			    uint32_t **vaddr)
+{
+	unsigned int i;
+	u32 expect;
+
+	for_each_mocs(expect, table, i) {
+		if (**vaddr != expect) {
+			pr_err("%s: Invalid MOCS[%d] entry, found %08x, expected %08x\n",
+			       engine->name, i, **vaddr, expect);
+			return -EINVAL;
+		}
+		++*vaddr;
+	}
+
+	return 0;
+}
+
+static bool mcr_range(struct drm_i915_private *i915, u32 offset)
+{
+	/*
+	 * Registers in this range are affected by the MCR selector
+	 * which only controls CPU initiated MMIO. Routing does not
+	 * work for CS access so we cannot verify them on this path.
+	 */
+	return INTEL_GEN(i915) >= 8 && offset >= 0xb000 && offset <= 0xb4ff;
+}
+
+static int check_l3cc_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table,
+			    uint32_t **vaddr)
+{
+	/* Can we read the MCR range 0xb00 directly? See intel_workarounds! */
+	u32 reg = i915_mmio_reg_offset(GEN9_LNCFCMOCS(0));
+	unsigned int i;
+	u32 expect;
+
+	for_each_l3cc(expect, table, i) {
+		if (!mcr_range(engine->i915, reg) && **vaddr != expect) {
+			pr_err("%s: Invalid L3CC[%d] entry, found %08x, expected %08x\n",
+			       engine->name, i, **vaddr, expect);
+			return -EINVAL;
+		}
+		++*vaddr;
+		reg += 4;
+	}
+
+	return 0;
+}
+
+static int check_mocs_engine(struct live_mocs *arg,
+			     struct intel_context *ce)
+{
+	struct i915_vma *vma = arg->scratch;
+	struct i915_request *rq;
+	u32 offset;
+	u32 *vaddr;
+	int err;
+
+	memset32(arg->vaddr, STACK_MAGIC, PAGE_SIZE / sizeof(u32));
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, true);
+	if (!err)
+		err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unlock(vma);
+
+	/* Read the mocs tables back using SRM */
+	offset = i915_ggtt_offset(vma);
+	if (!err)
+		err = read_mocs_table(rq, &arg->table, &offset);
+	if (!err && ce->engine->class == RENDER_CLASS)
+		err = read_l3cc_table(rq, &arg->table, &offset);
+	offset -= i915_ggtt_offset(vma);
+	GEM_BUG_ON(offset > PAGE_SIZE);
+
+	err = request_add_sync(rq, err);
+	if (err)
+		return err;
+
+	/* Compare the results against the expected tables */
+	vaddr = arg->vaddr;
+	if (!err)
+		err = check_mocs_table(ce->engine, &arg->table, &vaddr);
+	if (!err && ce->engine->class == RENDER_CLASS)
+		err = check_l3cc_table(ce->engine, &arg->table, &vaddr);
+	if (err)
+		return err;
+
+	GEM_BUG_ON(arg->vaddr + offset != vaddr);
+	return 0;
+}
+
+static int live_mocs_kernel(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct live_mocs mocs;
+	int err;
+
+	/* Basic check the system is configured with the expected mocs table */
+
+	err = live_mocs_init(&mocs, gt);
+	if (err)
+		return err;
+
+	for_each_engine(engine, gt, id) {
+		intel_engine_pm_get(engine);
+		err = check_mocs_engine(&mocs, engine->kernel_context);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+	}
+
+	live_mocs_fini(&mocs);
+	return err;
+}
+
+static int live_mocs_clean(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct live_mocs mocs;
+	int err;
+
+	/* Every new context should see the same mocs table */
+
+	err = live_mocs_init(&mocs, gt);
+	if (err)
+		return err;
+
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		err = check_mocs_engine(&mocs, ce);
+		intel_context_put(ce);
+		if (err)
+			break;
+	}
+
+	live_mocs_fini(&mocs);
+	return err;
+}
+
+static int active_engine_reset(struct intel_context *ce,
+			       const char *reason)
+{
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	int err;
+
+	err = igt_spinner_init(&spin, ce->engine->gt);
+	if (err)
+		return err;
+
+	rq = igt_spinner_create_request(&spin, ce, MI_NOOP);
+	if (IS_ERR(rq)) {
+		igt_spinner_fini(&spin);
+		return PTR_ERR(rq);
+	}
+
+	err = request_add_spin(rq, &spin);
+	if (err == 0)
+		err = intel_engine_reset(ce->engine, reason);
+
+	igt_spinner_end(&spin);
+	igt_spinner_fini(&spin);
+
+	return err;
+}
+
+static int __live_mocs_reset(struct live_mocs *mocs,
+			     struct intel_context *ce)
+{
+	int err;
+
+	err = intel_engine_reset(ce->engine, "mocs");
+	if (err)
+		return err;
+
+	err = check_mocs_engine(mocs, ce);
+	if (err)
+		return err;
+
+	err = active_engine_reset(ce, "mocs");
+	if (err)
+		return err;
+
+	err = check_mocs_engine(mocs, ce);
+	if (err)
+		return err;
+
+	intel_gt_reset(ce->engine->gt, ce->engine->mask, "mocs");
+
+	err = check_mocs_engine(mocs, ce);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int live_mocs_reset(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct live_mocs mocs;
+	int err = 0;
+
+	/* Check the mocs setup is retained over per-engine and global resets */
+
+	if (!intel_has_reset_engine(gt))
+		return 0;
+
+	err = live_mocs_init(&mocs, gt);
+	if (err)
+		return err;
+
+	igt_global_reset_lock(gt);
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			break;
+		}
+
+		intel_engine_pm_get(engine);
+		err = __live_mocs_reset(&mocs, ce);
+		intel_engine_pm_put(engine);
+
+		intel_context_put(ce);
+		if (err)
+			break;
+	}
+	igt_global_reset_unlock(gt);
+
+	live_mocs_fini(&mocs);
+	return err;
+}
+
+int intel_mocs_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_mocs_kernel),
+		SUBTEST(live_mocs_clean),
+		SUBTEST(live_mocs_reset),
+	};
+	struct drm_i915_mocs_table table;
+
+	if (!get_mocs_settings(i915, &table))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
new file mode 100644
index 000000000000..8cc55a0e9e06
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -0,0 +1,203 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_context.h"
+#include "intel_engine_pm.h"
+#include "intel_gt_requests.h"
+#include "intel_ring.h"
+#include "selftest_rc6.h"
+
+#include "selftests/i915_random.h"
+
+int live_rc6_manual(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_rc6 *rc6 = &gt->rc6;
+	intel_wakeref_t wakeref;
+	u64 res[2];
+	int err = 0;
+
+	/*
+	 * Our claim is that we can "encourage" the GPU to enter rc6 at will.
+	 * Let's try it!
+	 */
+
+	if (!rc6->enabled)
+		return 0;
+
+	/* bsw/byt use a PCU and decouple RC6 from our manual control */
+	if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915))
+		return 0;
+
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+
+	/* Force RC6 off for starters */
+	__intel_rc6_disable(rc6);
+	msleep(1); /* wakeup is not immediate, takes about 100us on icl */
+
+	res[0] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+	msleep(250);
+	res[1] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+	if ((res[1] - res[0]) >> 10) {
+		pr_err("RC6 residency increased by %lldus while disabled for 250ms!\n",
+		       (res[1] - res[0]) >> 10);
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	/* Manually enter RC6 */
+	intel_rc6_park(rc6);
+
+	res[0] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+	msleep(100);
+	res[1] = intel_rc6_residency_ns(rc6, GEN6_GT_GFX_RC6);
+
+	if (res[1] == res[0]) {
+		pr_err("Did not enter RC6! RC6_STATE=%08x, RC6_CONTROL=%08x\n",
+		       intel_uncore_read_fw(gt->uncore, GEN6_RC_STATE),
+		       intel_uncore_read_fw(gt->uncore, GEN6_RC_CONTROL));
+		err = -EINVAL;
+	}
+
+	/* Restore what should have been the original state! */
+	intel_rc6_unpark(rc6);
+
+out_unlock:
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	return err;
+}
+
+static const u32 *__live_rc6_ctx(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	const u32 *result;
+	u32 cmd;
+	u32 *cs;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return ERR_CAST(rq);
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return cs;
+	}
+
+	cmd = MI_STORE_REGISTER_MEM | MI_USE_GGTT;
+	if (INTEL_GEN(rq->i915) >= 8)
+		cmd++;
+
+	*cs++ = cmd;
+	*cs++ = i915_mmio_reg_offset(GEN8_RC6_CTX_INFO);
+	*cs++ = ce->timeline->hwsp_offset + 8;
+	*cs++ = 0;
+	intel_ring_advance(rq, cs);
+
+	result = rq->hwsp_seqno + 2;
+	i915_request_add(rq);
+
+	return result;
+}
+
+static struct intel_engine_cs **
+randomised_engines(struct intel_gt *gt,
+		   struct rnd_state *prng,
+		   unsigned int *count)
+{
+	struct intel_engine_cs *engine, **engines;
+	enum intel_engine_id id;
+	int n;
+
+	n = 0;
+	for_each_engine(engine, gt, id)
+		n++;
+	if (!n)
+		return NULL;
+
+	engines = kmalloc_array(n, sizeof(*engines), GFP_KERNEL);
+	if (!engines)
+		return NULL;
+
+	n = 0;
+	for_each_engine(engine, gt, id)
+		engines[n++] = engine;
+
+	i915_prandom_shuffle(engines, sizeof(*engines), n, prng);
+
+	*count = n;
+	return engines;
+}
+
+int live_rc6_ctx_wa(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs **engines;
+	unsigned int n, count;
+	I915_RND_STATE(prng);
+	int err = 0;
+
+	/* A read of CTX_INFO upsets rc6. Poke the bear! */
+	if (INTEL_GEN(gt->i915) < 8)
+		return 0;
+
+	engines = randomised_engines(gt, &prng, &count);
+	if (!engines)
+		return 0;
+
+	for (n = 0; n < count; n++) {
+		struct intel_engine_cs *engine = engines[n];
+		int pass;
+
+		for (pass = 0; pass < 2; pass++) {
+			struct intel_context *ce;
+			unsigned int resets =
+				i915_reset_engine_count(&gt->i915->gpu_error,
+							engine);
+			const u32 *res;
+
+			/* Use a sacrifical context */
+			ce = intel_context_create(engine);
+			if (IS_ERR(ce)) {
+				err = PTR_ERR(ce);
+				goto out;
+			}
+
+			intel_engine_pm_get(engine);
+			res = __live_rc6_ctx(ce);
+			intel_engine_pm_put(engine);
+			intel_context_put(ce);
+			if (IS_ERR(res)) {
+				err = PTR_ERR(res);
+				goto out;
+			}
+
+			if (intel_gt_wait_for_idle(gt, HZ / 5) == -ETIME) {
+				intel_gt_set_wedged(gt);
+				err = -ETIME;
+				goto out;
+			}
+
+			intel_gt_pm_wait_for_idle(gt);
+			pr_debug("%s: CTX_INFO=%0x\n",
+				 engine->name, READ_ONCE(*res));
+
+			if (resets !=
+			    i915_reset_engine_count(&gt->i915->gpu_error,
+						    engine)) {
+				pr_err("%s: GPU reset required\n",
+				       engine->name);
+				add_taint_for_CI(TAINT_WARN);
+				err = -EIO;
+				goto out;
+			}
+		}
+	}
+
+out:
+	kfree(engines);
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.h b/drivers/gpu/drm/i915/gt/selftest_rc6.h
new file mode 100644
index 000000000000..762fd442d7b2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.h
@@ -0,0 +1,13 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef SELFTEST_RC6_H
+#define SELFTEST_RC6_H
+
+int live_rc6_ctx_wa(void *arg);
+int live_rc6_manual(void *arg);
+
+#endif /* SELFTEST_RC6_H */
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index f04a59fe5d2c..e2d78cc22fb4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -458,7 +458,7 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 		goto out;
 	}
 
-	rq = i915_request_create(engine->kernel_context);
+	rq = intel_engine_create_kernel_request(engine);
 	if (IS_ERR(rq))
 		goto out_unpin;
 
@@ -675,9 +675,7 @@ static int live_hwsp_wrap(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		intel_engine_pm_get(engine);
-		rq = i915_request_create(engine->kernel_context);
-		intel_engine_pm_put(engine);
+		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			goto out;
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index abce6e4ec9c0..ac1921854cbf 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -264,22 +264,15 @@ static int
 switch_to_scratch_context(struct intel_engine_cs *engine,
 			  struct igt_spinner *spin)
 {
-	struct i915_gem_context *ctx;
 	struct intel_context *ce;
 	struct i915_request *rq;
 	int err = 0;
 
-	ctx = kernel_context(engine->i915);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	GEM_BUG_ON(i915_gem_context_is_bannable(ctx));
-
-	ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
-	GEM_BUG_ON(IS_ERR(ce));
+	ce = intel_context_create(engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
 	rq = igt_spinner_create_request(spin, ce, MI_NOOP);
-
 	intel_context_put(ce);
 
 	if (IS_ERR(rq)) {
@@ -293,7 +286,6 @@ err:
 	if (err && spin)
 		igt_spinner_end(spin);
 
-	kernel_context_close(ctx);
 	return err;
 }
 
@@ -367,20 +359,17 @@ out_ctx:
 	return err;
 }
 
-static struct i915_vma *create_batch(struct i915_gem_context *ctx)
+static struct i915_vma *create_batch(struct i915_address_space *vm)
 {
 	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	int err;
 
-	obj = i915_gem_object_create_internal(ctx->i915, 16 * PAGE_SIZE);
+	obj = i915_gem_object_create_internal(vm->i915, 16 * PAGE_SIZE);
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
 	vma = i915_vma_instance(obj, vm, NULL);
-	i915_vm_put(vm);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
@@ -452,8 +441,7 @@ static int whitelist_writable_count(struct intel_engine_cs *engine)
 	return count;
 }
 
-static int check_dirty_whitelist(struct i915_gem_context *ctx,
-				 struct intel_engine_cs *engine)
+static int check_dirty_whitelist(struct intel_context *ce)
 {
 	const u32 values[] = {
 		0x00000000,
@@ -481,19 +469,17 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 		0xffff00ff,
 		0xffffffff,
 	};
-	struct i915_address_space *vm;
+	struct intel_engine_cs *engine = ce->engine;
 	struct i915_vma *scratch;
 	struct i915_vma *batch;
 	int err = 0, i, v;
 	u32 *cs, *results;
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
-	scratch = create_scratch(vm, 2 * ARRAY_SIZE(values) + 1);
-	i915_vm_put(vm);
+	scratch = create_scratch(ce->vm, 2 * ARRAY_SIZE(values) + 1);
 	if (IS_ERR(scratch))
 		return PTR_ERR(scratch);
 
-	batch = create_batch(ctx);
+	batch = create_batch(ce->vm);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		goto out_scratch;
@@ -518,7 +504,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 
 		srm = MI_STORE_REGISTER_MEM;
 		lrm = MI_LOAD_REGISTER_MEM;
-		if (INTEL_GEN(ctx->i915) >= 8)
+		if (INTEL_GEN(engine->i915) >= 8)
 			lrm++, srm++;
 
 		pr_debug("%s: Writing garbage to %x\n",
@@ -577,7 +563,7 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 		i915_gem_object_unpin_map(batch->obj);
 		intel_gt_chipset_flush(engine->gt);
 
-		rq = igt_request_alloc(ctx, engine);
+		rq = intel_context_create_request(ce);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			goto out_batch;
@@ -696,7 +682,7 @@ out_unpin:
 			break;
 	}
 
-	if (igt_flush_test(ctx->i915))
+	if (igt_flush_test(engine->i915))
 		err = -EIO;
 out_batch:
 	i915_vma_unpin_and_release(&batch, 0);
@@ -709,38 +695,31 @@ static int live_dirty_whitelist(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
-	struct drm_file *file;
-	int err = 0;
 
 	/* Can the user write to the whitelisted registers? */
 
 	if (INTEL_GEN(gt->i915) < 7) /* minimum requirement for LRI, SRM, LRM */
 		return 0;
 
-	file = mock_file(gt->i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	ctx = live_context(gt->i915, file);
-	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_file;
-	}
-
 	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+		int err;
+
 		if (engine->whitelist.count == 0)
 			continue;
 
-		err = check_dirty_whitelist(ctx, engine);
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce))
+			return PTR_ERR(ce);
+
+		err = check_dirty_whitelist(ce);
+		intel_context_put(ce);
 		if (err)
-			goto out_file;
+			return err;
 	}
 
-out_file:
-	mock_file_free(gt->i915, file);
-	return err;
+	return 0;
 }
 
 static int live_reset_whitelist(void *arg)
@@ -830,12 +809,15 @@ err_req:
 static int scrub_whitelisted_registers(struct i915_gem_context *ctx,
 				       struct intel_engine_cs *engine)
 {
+	struct i915_address_space *vm;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	int i, err = 0;
 	u32 *cs;
 
-	batch = create_batch(ctx);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	batch = create_batch(vm);
+	i915_vm_put(vm);
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
diff --git a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
index 2a77c051f36a..aeb1d1f616e8 100644
--- a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
@@ -15,7 +15,7 @@ void mock_timeline_init(struct intel_timeline *timeline, u64 context)
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_FENCE(&timeline->last_request, &timeline->mutex);
+	INIT_ACTIVE_FENCE(&timeline->last_request);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
diff --git a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h
index 689efc66c908..d2bcc3df6183 100644
--- a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h
+++ b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.h
@@ -7,6 +7,8 @@
 #ifndef __MOCK_TIMELINE__
 #define __MOCK_TIMELINE__
 
+#include <linux/types.h>
+
 struct intel_timeline;
 
 void mock_timeline_init(struct intel_timeline *timeline, u64 context);
diff --git a/drivers/gpu/drm/i915/gt/uc/Makefile b/drivers/gpu/drm/i915/gt/uc/Makefile
deleted file mode 100644
index bec94d434cb6..000000000000
--- a/drivers/gpu/drm/i915/gt/uc/Makefile
+++ /dev/null
@@ -1,5 +0,0 @@
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/../..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 3ee4a4e7689d..5d00a3b2d914 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -32,18 +32,17 @@
  * just the HuC, but more are expected to land in the future).
  */
 
-static void gen8_guc_raise_irq(struct intel_guc *guc)
+void intel_guc_notify(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 
-	intel_uncore_write(gt->uncore, GUC_SEND_INTERRUPT, GUC_SEND_TRIGGER);
-}
-
-static void gen11_guc_raise_irq(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	intel_uncore_write(gt->uncore, GEN11_GUC_HOST_INTERRUPT, 0);
+	/*
+	 * On Gen11+, the value written to the register is passes as a payload
+	 * to the FW. However, the FW currently treats all values the same way
+	 * (H2G interrupt), so we can just write the value that the HW expects
+	 * on older gens.
+	 */
+	intel_uncore_write(gt->uncore, guc->notify_reg, GUC_SEND_TRIGGER);
 }
 
 static inline i915_reg_t guc_send_reg(struct intel_guc *guc, u32 i)
@@ -177,15 +176,13 @@ void intel_guc_init_early(struct intel_guc *guc)
 
 	mutex_init(&guc->send_mutex);
 	spin_lock_init(&guc->irq_lock);
-	guc->send = intel_guc_send_nop;
-	guc->handler = intel_guc_to_host_event_handler_nop;
 	if (INTEL_GEN(i915) >= 11) {
-		guc->notify = gen11_guc_raise_irq;
+		guc->notify_reg = GEN11_GUC_HOST_INTERRUPT;
 		guc->interrupts.reset = gen11_reset_guc_interrupts;
 		guc->interrupts.enable = gen11_enable_guc_interrupts;
 		guc->interrupts.disable = gen11_disable_guc_interrupts;
 	} else {
-		guc->notify = gen8_guc_raise_irq;
+		guc->notify_reg = GUC_SEND_INTERRUPT;
 		guc->interrupts.reset = gen9_reset_guc_interrupts;
 		guc->interrupts.enable = gen9_enable_guc_interrupts;
 		guc->interrupts.disable = gen9_disable_guc_interrupts;
@@ -401,18 +398,8 @@ void intel_guc_fini(struct intel_guc *guc)
 	intel_guc_log_destroy(&guc->log);
 	intel_uc_fw_fini(&guc->fw);
 	intel_uc_fw_cleanup_fetch(&guc->fw);
-}
 
-int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
-		       u32 *response_buf, u32 response_buf_size)
-{
-	WARN(1, "Unexpected send: action=%#x\n", *action);
-	return -ENODEV;
-}
-
-void intel_guc_to_host_event_handler_nop(struct intel_guc *guc)
-{
-	WARN(1, "Unexpected event: no suitable handler\n");
+	intel_uc_fw_change_status(&guc->fw, INTEL_UC_FIRMWARE_DISABLED);
 }
 
 /*
@@ -704,3 +691,37 @@ err:
 	i915_gem_object_put(obj);
 	return vma;
 }
+
+/**
+ * intel_guc_allocate_and_map_vma() - Allocate and map VMA for GuC usage
+ * @guc:	the guc
+ * @size:	size of area to allocate (both virtual space and memory)
+ * @out_vma:	return variable for the allocated vma pointer
+ * @out_vaddr:	return variable for the obj mapping
+ *
+ * This wrapper calls intel_guc_allocate_vma() and then maps the allocated
+ * object with I915_MAP_WB.
+ *
+ * Return:	0 if successful, a negative errno code otherwise.
+ */
+int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
+				   struct i915_vma **out_vma, void **out_vaddr)
+{
+	struct i915_vma *vma;
+	void *vaddr;
+
+	vma = intel_guc_allocate_vma(guc, size);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
+	if (IS_ERR(vaddr)) {
+		i915_vma_unpin_and_release(&vma, 0);
+		return PTR_ERR(vaddr);
+	}
+
+	*out_vma = vma;
+	*out_vaddr = vaddr;
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index e6400204a2bd..910d49590068 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -20,8 +20,8 @@ struct __guc_ads_blob;
 
 /*
  * Top level structure of GuC. It handles firmware loading and manages client
- * pool and doorbells. intel_guc owns a intel_guc_client to replace the legacy
- * ExecList submission.
+ * pool. intel_guc owns a intel_guc_client to replace the legacy ExecList
+ * submission.
  */
 struct intel_guc {
 	struct intel_uc_fw fw;
@@ -46,13 +46,13 @@ struct intel_guc {
 
 	struct i915_vma *stage_desc_pool;
 	void *stage_desc_pool_vaddr;
-	struct ida stage_ids;
 
-	struct intel_guc_client *execbuf_client;
+	struct i915_vma *workqueue;
+	void *workqueue_vaddr;
+	spinlock_t wq_lock;
 
-	DECLARE_BITMAP(doorbell_bitmap, GUC_NUM_DOORBELLS);
-	/* Cyclic counter mod pagesize	*/
-	u32 db_cacheline;
+	struct i915_vma *proc_desc;
+	void *proc_desc_vaddr;
 
 	/* Control params for fw initialization */
 	u32 params[GUC_CTL_MAX_DWORDS];
@@ -64,44 +64,33 @@ struct intel_guc {
 		enum forcewake_domains fw_domains;
 	} send_regs;
 
+	/* register used to send interrupts to the GuC FW */
+	i915_reg_t notify_reg;
+
 	/* Store msg (e.g. log flush) that we see while CTBs are disabled */
 	u32 mmio_msg;
 
 	/* To serialize the intel_guc_send actions */
 	struct mutex send_mutex;
-
-	/* GuC's FW specific send function */
-	int (*send)(struct intel_guc *guc, const u32 *data, u32 len,
-		    u32 *response_buf, u32 response_buf_size);
-
-	/* GuC's FW specific event handler function */
-	void (*handler)(struct intel_guc *guc);
-
-	/* GuC's FW specific notify function */
-	void (*notify)(struct intel_guc *guc);
 };
 
 static
 inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len)
 {
-	return guc->send(guc, action, len, NULL, 0);
+	return intel_guc_ct_send(&guc->ct, action, len, NULL, 0);
 }
 
 static inline int
 intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len,
 			   u32 *response_buf, u32 response_buf_size)
 {
-	return guc->send(guc, action, len, response_buf, response_buf_size);
-}
-
-static inline void intel_guc_notify(struct intel_guc *guc)
-{
-	guc->notify(guc);
+	return intel_guc_ct_send(&guc->ct, action, len,
+				 response_buf, response_buf_size);
 }
 
 static inline void intel_guc_to_host_event_handler(struct intel_guc *guc)
 {
-	guc->handler(guc);
+	intel_guc_ct_event_handler(&guc->ct);
 }
 
 /* GuC addresses above GUC_GGTT_TOP also don't map through the GTT */
@@ -136,12 +125,9 @@ void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_write_params(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
 void intel_guc_fini(struct intel_guc *guc);
-int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
-		       u32 *response_buf, u32 response_buf_size);
+void intel_guc_notify(struct intel_guc *guc);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
 			u32 *response_buf, u32 response_buf_size);
-void intel_guc_to_host_event_handler(struct intel_guc *guc);
-void intel_guc_to_host_event_handler_nop(struct intel_guc *guc);
 int intel_guc_to_host_process_recv_msg(struct intel_guc *guc,
 				       const u32 *payload, u32 len);
 int intel_guc_sample_forcewake(struct intel_guc *guc);
@@ -149,6 +135,8 @@ int intel_guc_auth_huc(struct intel_guc *guc, u32 rsa_offset);
 int intel_guc_suspend(struct intel_guc *guc);
 int intel_guc_resume(struct intel_guc *guc);
 struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size);
+int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size,
+				   struct i915_vma **out_vma, void **out_vaddr);
 
 static inline bool intel_guc_is_supported(struct intel_guc *guc)
 {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
index ca6674b8e00c..101728006ae9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c
@@ -93,7 +93,8 @@ static void __guc_ads_init(struct intel_guc *guc)
 		 */
 		blob->ads.golden_context_lrca[engine_class] = 0;
 		blob->ads.eng_state_size[engine_class] =
-			intel_engine_context_size(dev_priv, engine_class) -
+			intel_engine_context_size(guc_to_gt(guc),
+						  engine_class) -
 			skipped_size;
 	}
 
@@ -135,32 +136,19 @@ static void __guc_ads_init(struct intel_guc *guc)
 int intel_guc_ads_create(struct intel_guc *guc)
 {
 	const u32 size = PAGE_ALIGN(sizeof(struct __guc_ads_blob));
-	struct i915_vma *vma;
-	void *blob;
 	int ret;
 
 	GEM_BUG_ON(guc->ads_vma);
 
-	vma = intel_guc_allocate_vma(guc, size);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+	ret = intel_guc_allocate_and_map_vma(guc, size, &guc->ads_vma,
+					     (void **)&guc->ads_blob);
 
-	blob = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(blob)) {
-		ret = PTR_ERR(blob);
-		goto err_vma;
-	}
-
-	guc->ads_vma = vma;
-	guc->ads_blob = blob;
+	if (ret)
+		return ret;
 
 	__guc_ads_init(guc);
 
 	return 0;
-
-err_vma:
-	i915_vma_unpin_and_release(&guc->ads_vma, 0);
-	return ret;
 }
 
 void intel_guc_ads_destroy(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index b49115517510..c6f971a049f9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -37,13 +37,10 @@ static void ct_incoming_request_worker_func(struct work_struct *w);
  */
 void intel_guc_ct_init_early(struct intel_guc_ct *ct)
 {
-	/* we're using static channel owners */
-	ct->host_channel.owner = CTB_OWNER_HOST;
-
-	spin_lock_init(&ct->lock);
-	INIT_LIST_HEAD(&ct->pending_requests);
-	INIT_LIST_HEAD(&ct->incoming_requests);
-	INIT_WORK(&ct->worker, ct_incoming_request_worker_func);
+	spin_lock_init(&ct->requests.lock);
+	INIT_LIST_HEAD(&ct->requests.pending);
+	INIT_LIST_HEAD(&ct->requests.incoming);
+	INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
 }
 
 static inline struct intel_guc *ct_to_guc(struct intel_guc_ct *ct)
@@ -64,14 +61,13 @@ static inline const char *guc_ct_buffer_type_to_str(u32 type)
 }
 
 static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc,
-				    u32 cmds_addr, u32 size, u32 owner)
+				    u32 cmds_addr, u32 size)
 {
-	CT_DEBUG_DRIVER("CT: desc %p init addr=%#x size=%u owner=%u\n",
-			desc, cmds_addr, size, owner);
+	CT_DEBUG_DRIVER("CT: init addr=%#x size=%u\n", cmds_addr, size);
 	memset(desc, 0, sizeof(*desc));
 	desc->addr = cmds_addr;
 	desc->size = size;
-	desc->owner = owner;
+	desc->owner = CTB_OWNER_HOST;
 }
 
 static void guc_ct_buffer_desc_reset(struct guc_ct_buffer_desc *desc)
@@ -104,12 +100,11 @@ static int guc_action_register_ct_buffer(struct intel_guc *guc,
 }
 
 static int guc_action_deregister_ct_buffer(struct intel_guc *guc,
-					   u32 owner,
 					   u32 type)
 {
 	u32 action[] = {
 		INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER,
-		owner,
+		CTB_OWNER_HOST,
 		type
 	};
 	int err;
@@ -117,20 +112,27 @@ static int guc_action_deregister_ct_buffer(struct intel_guc *guc,
 	/* Can't use generic send(), CT deregistration must go over MMIO */
 	err = intel_guc_send_mmio(guc, action, ARRAY_SIZE(action), NULL, 0);
 	if (err)
-		DRM_ERROR("CT: deregister %s buffer failed; owner=%d err=%d\n",
-			  guc_ct_buffer_type_to_str(type), owner, err);
+		DRM_ERROR("CT: deregister %s buffer failed; err=%d\n",
+			  guc_ct_buffer_type_to_str(type), err);
 	return err;
 }
 
-static int ctch_init(struct intel_guc *guc,
-		     struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_init - Init buffer-based communication
+ * @ct: pointer to CT struct
+ *
+ * Allocate memory required for buffer-based communication.
+ *
+ * Return: 0 on success, a negative errno code on failure.
+ */
+int intel_guc_ct_init(struct intel_guc_ct *ct)
 {
-	struct i915_vma *vma;
+	struct intel_guc *guc = ct_to_guc(ct);
 	void *blob;
 	int err;
 	int i;
 
-	GEM_BUG_ON(ctch->vma);
+	GEM_BUG_ON(ct->vma);
 
 	/* We allocate 1 page to hold both descriptors and both buffers.
 	 *       ___________.....................
@@ -154,71 +156,65 @@ static int ctch_init(struct intel_guc *guc,
 	 * other code will need updating as well.
 	 */
 
-	/* allocate vma */
-	vma = intel_guc_allocate_vma(guc, PAGE_SIZE);
-	if (IS_ERR(vma)) {
-		err = PTR_ERR(vma);
-		goto err_out;
+	err = intel_guc_allocate_and_map_vma(guc, PAGE_SIZE, &ct->vma, &blob);
+	if (err) {
+		DRM_ERROR("CT: channel allocation failed; err=%d\n", err);
+		return err;
 	}
-	ctch->vma = vma;
 
-	/* map first page */
-	blob = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(blob)) {
-		err = PTR_ERR(blob);
-		goto err_vma;
-	}
 	CT_DEBUG_DRIVER("CT: vma base=%#x\n",
-			intel_guc_ggtt_offset(guc, ctch->vma));
+			intel_guc_ggtt_offset(guc, ct->vma));
 
 	/* store pointers to desc and cmds */
-	for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) {
-		GEM_BUG_ON((i != CTB_SEND) && (i != CTB_RECV));
-		ctch->ctbs[i].desc = blob + PAGE_SIZE/4 * i;
-		ctch->ctbs[i].cmds = blob + PAGE_SIZE/4 * i + PAGE_SIZE/2;
+	for (i = 0; i < ARRAY_SIZE(ct->ctbs); i++) {
+		GEM_BUG_ON((i !=  CTB_SEND) && (i != CTB_RECV));
+		ct->ctbs[i].desc = blob + PAGE_SIZE/4 * i;
+		ct->ctbs[i].cmds = blob + PAGE_SIZE/4 * i + PAGE_SIZE/2;
 	}
 
 	return 0;
-
-err_vma:
-	i915_vma_unpin_and_release(&ctch->vma, 0);
-err_out:
-	CT_DEBUG_DRIVER("CT: channel %d initialization failed; err=%d\n",
-			ctch->owner, err);
-	return err;
 }
 
-static void ctch_fini(struct intel_guc *guc,
-		      struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_fini - Fini buffer-based communication
+ * @ct: pointer to CT struct
+ *
+ * Deallocate memory required for buffer-based communication.
+ */
+void intel_guc_ct_fini(struct intel_guc_ct *ct)
 {
-	GEM_BUG_ON(ctch->enabled);
+	GEM_BUG_ON(ct->enabled);
 
-	i915_vma_unpin_and_release(&ctch->vma, I915_VMA_RELEASE_MAP);
+	i915_vma_unpin_and_release(&ct->vma, I915_VMA_RELEASE_MAP);
 }
 
-static int ctch_enable(struct intel_guc *guc,
-		       struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_enable - Enable buffer based command transport.
+ * @ct: pointer to CT struct
+ *
+ * Return: 0 on success, a negative errno code on failure.
+ */
+int intel_guc_ct_enable(struct intel_guc_ct *ct)
 {
+	struct intel_guc *guc = ct_to_guc(ct);
 	u32 base;
 	int err;
 	int i;
 
-	GEM_BUG_ON(!ctch->vma);
-
-	GEM_BUG_ON(ctch->enabled);
+	GEM_BUG_ON(ct->enabled);
 
 	/* vma should be already allocated and map'ed */
-	base = intel_guc_ggtt_offset(guc, ctch->vma);
+	GEM_BUG_ON(!ct->vma);
+	base = intel_guc_ggtt_offset(guc, ct->vma);
 
 	/* (re)initialize descriptors
 	 * cmds buffers are in the second half of the blob page
 	 */
-	for (i = 0; i < ARRAY_SIZE(ctch->ctbs); i++) {
+	for (i = 0; i < ARRAY_SIZE(ct->ctbs); i++) {
 		GEM_BUG_ON((i != CTB_SEND) && (i != CTB_RECV));
-		guc_ct_buffer_desc_init(ctch->ctbs[i].desc,
+		guc_ct_buffer_desc_init(ct->ctbs[i].desc,
 					base + PAGE_SIZE/4 * i + PAGE_SIZE/2,
-					PAGE_SIZE/4,
-					ctch->owner);
+					PAGE_SIZE/4);
 	}
 
 	/* register buffers, starting wirh RECV buffer
@@ -236,38 +232,42 @@ static int ctch_enable(struct intel_guc *guc,
 	if (unlikely(err))
 		goto err_deregister;
 
-	ctch->enabled = true;
+	ct->enabled = true;
 
 	return 0;
 
 err_deregister:
 	guc_action_deregister_ct_buffer(guc,
-					ctch->owner,
 					INTEL_GUC_CT_BUFFER_TYPE_RECV);
 err_out:
-	DRM_ERROR("CT: can't open channel %d; err=%d\n", ctch->owner, err);
+	DRM_ERROR("CT: can't open channel; err=%d\n", err);
 	return err;
 }
 
-static void ctch_disable(struct intel_guc *guc,
-			 struct intel_guc_ct_channel *ctch)
+/**
+ * intel_guc_ct_disable - Disable buffer based command transport.
+ * @ct: pointer to CT struct
+ */
+void intel_guc_ct_disable(struct intel_guc_ct *ct)
 {
-	GEM_BUG_ON(!ctch->enabled);
+	struct intel_guc *guc = ct_to_guc(ct);
 
-	ctch->enabled = false;
+	GEM_BUG_ON(!ct->enabled);
 
-	guc_action_deregister_ct_buffer(guc,
-					ctch->owner,
-					INTEL_GUC_CT_BUFFER_TYPE_SEND);
-	guc_action_deregister_ct_buffer(guc,
-					ctch->owner,
-					INTEL_GUC_CT_BUFFER_TYPE_RECV);
+	ct->enabled = false;
+
+	if (intel_guc_is_running(guc)) {
+		guc_action_deregister_ct_buffer(guc,
+						INTEL_GUC_CT_BUFFER_TYPE_SEND);
+		guc_action_deregister_ct_buffer(guc,
+						INTEL_GUC_CT_BUFFER_TYPE_RECV);
+	}
 }
 
-static u32 ctch_get_next_fence(struct intel_guc_ct_channel *ctch)
+static u32 ct_get_next_fence(struct intel_guc_ct *ct)
 {
 	/* For now it's trivial */
-	return ++ctch->next_fence;
+	return ++ct->requests.next_fence;
 }
 
 /**
@@ -440,35 +440,34 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
 	return err;
 }
 
-static int ctch_send(struct intel_guc_ct *ct,
-		     struct intel_guc_ct_channel *ctch,
-		     const u32 *action,
-		     u32 len,
-		     u32 *response_buf,
-		     u32 response_buf_size,
-		     u32 *status)
+static int ct_send(struct intel_guc_ct *ct,
+		   const u32 *action,
+		   u32 len,
+		   u32 *response_buf,
+		   u32 response_buf_size,
+		   u32 *status)
 {
-	struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_SEND];
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs[CTB_SEND];
 	struct guc_ct_buffer_desc *desc = ctb->desc;
 	struct ct_request request;
 	unsigned long flags;
 	u32 fence;
 	int err;
 
-	GEM_BUG_ON(!ctch->enabled);
+	GEM_BUG_ON(!ct->enabled);
 	GEM_BUG_ON(!len);
 	GEM_BUG_ON(len & ~GUC_CT_MSG_LEN_MASK);
 	GEM_BUG_ON(!response_buf && response_buf_size);
 
-	fence = ctch_get_next_fence(ctch);
+	fence = ct_get_next_fence(ct);
 	request.fence = fence;
 	request.status = 0;
 	request.response_len = response_buf_size;
 	request.response_buf = response_buf;
 
-	spin_lock_irqsave(&ct->lock, flags);
-	list_add_tail(&request.link, &ct->pending_requests);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	spin_lock_irqsave(&ct->requests.lock, flags);
+	list_add_tail(&request.link, &ct->requests.pending);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	err = ctb_write(ctb, action, len, fence, !!response_buf);
 	if (unlikely(err))
@@ -501,9 +500,9 @@ static int ctch_send(struct intel_guc_ct *ct,
 	}
 
 unlink:
-	spin_lock_irqsave(&ct->lock, flags);
+	spin_lock_irqsave(&ct->requests.lock, flags);
 	list_del(&request.link);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	return err;
 }
@@ -511,18 +510,21 @@ unlink:
 /*
  * Command Transport (CT) buffer based GuC send function.
  */
-int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len,
+int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 		      u32 *response_buf, u32 response_buf_size)
 {
-	struct intel_guc_ct *ct = &guc->ct;
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
+	struct intel_guc *guc = ct_to_guc(ct);
 	u32 status = ~0; /* undefined */
 	int ret;
 
+	if (unlikely(!ct->enabled)) {
+		WARN(1, "Unexpected send: action=%#x\n", *action);
+		return -ENODEV;
+	}
+
 	mutex_lock(&guc->send_mutex);
 
-	ret = ctch_send(ct, ctch, action, len, response_buf, response_buf_size,
-			&status);
+	ret = ct_send(ct, action, len, response_buf, response_buf_size, &status);
 	if (unlikely(ret < 0)) {
 		DRM_ERROR("CT: send action %#X failed; err=%d status=%#X\n",
 			  action[0], ret, status);
@@ -653,8 +655,8 @@ static int ct_handle_response(struct intel_guc_ct *ct, const u32 *msg)
 
 	CT_DEBUG_DRIVER("CT: response fence %u status %#x\n", fence, status);
 
-	spin_lock(&ct->lock);
-	list_for_each_entry(req, &ct->pending_requests, link) {
+	spin_lock(&ct->requests.lock);
+	list_for_each_entry(req, &ct->requests.pending, link) {
 		if (unlikely(fence != req->fence)) {
 			CT_DEBUG_DRIVER("CT: request %u awaits response\n",
 					req->fence);
@@ -672,7 +674,7 @@ static int ct_handle_response(struct intel_guc_ct *ct, const u32 *msg)
 		found = true;
 		break;
 	}
-	spin_unlock(&ct->lock);
+	spin_unlock(&ct->requests.lock);
 
 	if (!found)
 		DRM_ERROR("CT: unsolicited response %*ph\n", 4 * msglen, msg);
@@ -710,13 +712,13 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
 	u32 *payload;
 	bool done;
 
-	spin_lock_irqsave(&ct->lock, flags);
-	request = list_first_entry_or_null(&ct->incoming_requests,
+	spin_lock_irqsave(&ct->requests.lock, flags);
+	request = list_first_entry_or_null(&ct->requests.incoming,
 					   struct ct_incoming_request, link);
 	if (request)
 		list_del(&request->link);
-	done = !!list_empty(&ct->incoming_requests);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	done = !!list_empty(&ct->requests.incoming);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
 	if (!request)
 		return true;
@@ -734,12 +736,13 @@ static bool ct_process_incoming_requests(struct intel_guc_ct *ct)
 
 static void ct_incoming_request_worker_func(struct work_struct *w)
 {
-	struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct, worker);
+	struct intel_guc_ct *ct =
+		container_of(w, struct intel_guc_ct, requests.worker);
 	bool done;
 
 	done = ct_process_incoming_requests(ct);
 	if (!done)
-		queue_work(system_unbound_wq, &ct->worker);
+		queue_work(system_unbound_wq, &ct->requests.worker);
 }
 
 /**
@@ -777,23 +780,28 @@ static int ct_handle_request(struct intel_guc_ct *ct, const u32 *msg)
 	}
 	memcpy(request->msg, msg, 4 * msglen);
 
-	spin_lock_irqsave(&ct->lock, flags);
-	list_add_tail(&request->link, &ct->incoming_requests);
-	spin_unlock_irqrestore(&ct->lock, flags);
+	spin_lock_irqsave(&ct->requests.lock, flags);
+	list_add_tail(&request->link, &ct->requests.incoming);
+	spin_unlock_irqrestore(&ct->requests.lock, flags);
 
-	queue_work(system_unbound_wq, &ct->worker);
+	queue_work(system_unbound_wq, &ct->requests.worker);
 	return 0;
 }
 
-static void ct_process_host_channel(struct intel_guc_ct *ct)
+/*
+ * When we're communicating with the GuC over CT, GuC uses events
+ * to notify us about new messages being posted on the RECV buffer.
+ */
+void intel_guc_ct_event_handler(struct intel_guc_ct *ct)
 {
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-	struct intel_guc_ct_buffer *ctb = &ctch->ctbs[CTB_RECV];
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs[CTB_RECV];
 	u32 msg[GUC_CT_MSG_LEN_MASK + 1]; /* one extra dw for the header */
 	int err = 0;
 
-	if (!ctch->enabled)
+	if (unlikely(!ct->enabled)) {
+		WARN(1, "Unexpected GuC event received while CT disabled!\n");
 		return;
+	}
 
 	do {
 		err = ctb_read(ctb, msg);
@@ -812,86 +820,3 @@ static void ct_process_host_channel(struct intel_guc_ct *ct)
 	}
 }
 
-/*
- * When we're communicating with the GuC over CT, GuC uses events
- * to notify us about new messages being posted on the RECV buffer.
- */
-void intel_guc_to_host_event_handler_ct(struct intel_guc *guc)
-{
-	struct intel_guc_ct *ct = &guc->ct;
-
-	ct_process_host_channel(ct);
-}
-
-/**
- * intel_guc_ct_init - Init CT communication
- * @ct: pointer to CT struct
- *
- * Allocate memory required for communication via
- * the CT channel.
- *
- * Return: 0 on success, a negative errno code on failure.
- */
-int intel_guc_ct_init(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-	int err;
-
-	err = ctch_init(guc, ctch);
-	if (unlikely(err)) {
-		DRM_ERROR("CT: can't open channel %d; err=%d\n",
-			  ctch->owner, err);
-		return err;
-	}
-
-	GEM_BUG_ON(!ctch->vma);
-	return 0;
-}
-
-/**
- * intel_guc_ct_fini - Fini CT communication
- * @ct: pointer to CT struct
- *
- * Deallocate memory required for communication via
- * the CT channel.
- */
-void intel_guc_ct_fini(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-
-	ctch_fini(guc, ctch);
-}
-
-/**
- * intel_guc_ct_enable - Enable buffer based command transport.
- * @ct: pointer to CT struct
- *
- * Return: 0 on success, a negative errno code on failure.
- */
-int intel_guc_ct_enable(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-
-	if (ctch->enabled)
-		return 0;
-
-	return ctch_enable(guc, ctch);
-}
-
-/**
- * intel_guc_ct_disable - Disable buffer based command transport.
- * @ct: pointer to CT struct
- */
-void intel_guc_ct_disable(struct intel_guc_ct *ct)
-{
-	struct intel_guc *guc = ct_to_guc(ct);
-	struct intel_guc_ct_channel *ctch = &ct->host_channel;
-
-	if (!ctch->enabled)
-		return;
-
-	ctch_disable(guc, ctch);
-}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
index 7c24d83f5c24..3e7fe237cfa5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
@@ -35,44 +35,28 @@ struct intel_guc_ct_buffer {
 	u32 *cmds;
 };
 
-/** Represents pair of command transport buffers.
- *
- * Buffers go in pairs to allow bi-directional communication.
- * To simplify the code we place both of them in the same vma.
- * Buffers from the same pair must share unique owner id.
- *
- * @vma: pointer to the vma with pair of CT buffers
- * @ctbs: buffers for sending(0) and receiving(1) commands
- * @owner: unique identifier
- * @next_fence: fence to be used with next send command
- */
-struct intel_guc_ct_channel {
-	struct i915_vma *vma;
-	struct intel_guc_ct_buffer ctbs[2];
-	u32 owner;
-	u32 next_fence;
-	bool enabled;
-};
 
-/** Holds all command transport channels.
+/** Top-level structure for Command Transport related data
  *
- * @host_channel: main channel used by the host
+ * Includes a pair of CT buffers for bi-directional communication and tracking
+ * for the H2G and G2H requests sent and received through the buffers.
  */
 struct intel_guc_ct {
-	struct intel_guc_ct_channel host_channel;
-	/* other channels are tbd */
+	struct i915_vma *vma;
+	bool enabled;
 
-	/** @lock: protects pending requests list */
-	spinlock_t lock;
+	/* buffers for sending(0) and receiving(1) commands */
+	struct intel_guc_ct_buffer ctbs[2];
 
-	/** @pending_requests: list of requests waiting for response */
-	struct list_head pending_requests;
+	struct {
+		u32 next_fence; /* fence to be used with next request to send */
 
-	/** @incoming_requests: list of incoming requests */
-	struct list_head incoming_requests;
+		spinlock_t lock; /* protects pending requests list */
+		struct list_head pending; /* requests waiting for response */
 
-	/** @worker: worker for handling incoming requests */
-	struct work_struct worker;
+		struct list_head incoming; /* incoming requests */
+		struct work_struct worker; /* handler for incoming requests */
+	} requests;
 };
 
 void intel_guc_ct_init_early(struct intel_guc_ct *ct);
@@ -81,13 +65,13 @@ void intel_guc_ct_fini(struct intel_guc_ct *ct);
 int intel_guc_ct_enable(struct intel_guc_ct *ct);
 void intel_guc_ct_disable(struct intel_guc_ct *ct);
 
-static inline void intel_guc_ct_stop(struct intel_guc_ct *ct)
+static inline bool intel_guc_ct_enabled(struct intel_guc_ct *ct)
 {
-	ct->host_channel.enabled = false;
+	return ct->enabled;
 }
 
-int intel_guc_send_ct(struct intel_guc *guc, const u32 *action, u32 len,
+int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 		      u32 *response_buf, u32 response_buf_size);
-void intel_guc_to_host_event_handler_ct(struct intel_guc *guc);
+void intel_guc_ct_event_handler(struct intel_guc_ct *ct);
 
 #endif /* _INTEL_GUC_CT_H_ */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
index 5528224448f6..3a1c47d600ea 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
@@ -149,7 +149,7 @@ int intel_guc_fw_upload(struct intel_guc *guc)
 	 * Current uCode expects the code to be loaded at 8k; locations below
 	 * this are used for the stack.
 	 */
-	ret = intel_uc_fw_upload(&guc->fw, gt, 0x2000, UOS_MOVE);
+	ret = intel_uc_fw_upload(&guc->fw, 0x2000, UOS_MOVE);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index a26a85d50209..a6b733c146c9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -31,7 +31,6 @@
 
 #define GUC_DOORBELL_INVALID		256
 
-#define GUC_DB_SIZE			(PAGE_SIZE)
 #define GUC_WQ_SIZE			(PAGE_SIZE * 2)
 
 /* Work queue item header definitions */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 2498c55e0ea5..9e42324fdecd 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -18,15 +18,6 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-enum {
-	GUC_PREEMPT_NONE = 0,
-	GUC_PREEMPT_INPROGRESS,
-	GUC_PREEMPT_FINISHED,
-};
-#define GUC_PREEMPT_BREADCRUMB_DWORDS	0x8
-#define GUC_PREEMPT_BREADCRUMB_BYTES	\
-	(sizeof(u32) * GUC_PREEMPT_BREADCRUMB_DWORDS)
-
 /**
  * DOC: GuC-based command submission
  *
@@ -36,25 +27,14 @@ enum {
  * code) matches the old submission model and will be updated as part of the
  * upgrade to the new flow.
  *
- * GuC client:
- * A intel_guc_client refers to a submission path through GuC. Currently, there
- * is only one client, which is charged with all submissions to the GuC. This
- * struct is the owner of a doorbell, a process descriptor and a workqueue (all
- * of them inside a single gem object that contains all required pages for these
- * elements).
- *
  * GuC stage descriptor:
  * During initialization, the driver allocates a static pool of 1024 such
- * descriptors, and shares them with the GuC.
- * Currently, there exists a 1:1 mapping between a intel_guc_client and a
- * guc_stage_desc (via the client's stage_id), so effectively only one
- * gets used. This stage descriptor lets the GuC know about the doorbell,
- * workqueue and process descriptor. Theoretically, it also lets the GuC
- * know about our HW contexts (context ID, etc...), but we actually
- * employ a kind of submission where the GuC uses the LRCA sent via the work
- * item instead (the single guc_stage_desc associated to execbuf client
- * contains information about the default kernel context only, but this is
- * essentially unused). This is called a "proxy" submission.
+ * descriptors, and shares them with the GuC. Currently, we only use one
+ * descriptor. This stage descriptor lets the GuC know about the workqueue and
+ * process descriptor. Theoretically, it also lets the GuC know about our HW
+ * contexts (context ID, etc...), but we actually employ a kind of submission
+ * where the GuC uses the LRCA sent via the work item instead. This is called
+ * a "proxy" submission.
  *
  * The Scratch registers:
  * There are 16 MMIO-based registers start from 0xC180. The kernel driver writes
@@ -63,11 +43,6 @@ enum {
  * Firmware writes a success/fail code back to the action register after
  * processes the request. The kernel driver polls waiting for this update and
  * then proceeds.
- * See intel_guc_send()
- *
- * Doorbells:
- * Doorbells are interrupts to uKernel. A doorbell is a single cache line (QW)
- * mapped into process space.
  *
  * Work Items:
  * There are several types of work items that the host may place into a
@@ -84,213 +59,45 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 	return rb_entry(rb, struct i915_priolist, node);
 }
 
-static inline bool is_high_priority(struct intel_guc_client *client)
+static struct guc_stage_desc *__get_stage_desc(struct intel_guc *guc, u32 id)
 {
-	return (client->priority == GUC_CLIENT_PRIORITY_KMD_HIGH ||
-		client->priority == GUC_CLIENT_PRIORITY_HIGH);
-}
-
-static int reserve_doorbell(struct intel_guc_client *client)
-{
-	unsigned long offset;
-	unsigned long end;
-	u16 id;
-
-	GEM_BUG_ON(client->doorbell_id != GUC_DOORBELL_INVALID);
+	struct guc_stage_desc *base = guc->stage_desc_pool_vaddr;
 
-	/*
-	 * The bitmap tracks which doorbell registers are currently in use.
-	 * It is split into two halves; the first half is used for normal
-	 * priority contexts, the second half for high-priority ones.
-	 */
-	offset = 0;
-	end = GUC_NUM_DOORBELLS / 2;
-	if (is_high_priority(client)) {
-		offset = end;
-		end += offset;
-	}
-
-	id = find_next_zero_bit(client->guc->doorbell_bitmap, end, offset);
-	if (id == end)
-		return -ENOSPC;
-
-	__set_bit(id, client->guc->doorbell_bitmap);
-	client->doorbell_id = id;
-	DRM_DEBUG_DRIVER("client %u (high prio=%s) reserved doorbell: %d\n",
-			 client->stage_id, yesno(is_high_priority(client)),
-			 id);
-	return 0;
+	return &base[id];
 }
 
-static bool has_doorbell(struct intel_guc_client *client)
+static int guc_workqueue_create(struct intel_guc *guc)
 {
-	if (client->doorbell_id == GUC_DOORBELL_INVALID)
-		return false;
-
-	return test_bit(client->doorbell_id, client->guc->doorbell_bitmap);
+	return intel_guc_allocate_and_map_vma(guc, GUC_WQ_SIZE, &guc->workqueue,
+					      &guc->workqueue_vaddr);
 }
 
-static void unreserve_doorbell(struct intel_guc_client *client)
+static void guc_workqueue_destroy(struct intel_guc *guc)
 {
-	GEM_BUG_ON(!has_doorbell(client));
-
-	__clear_bit(client->doorbell_id, client->guc->doorbell_bitmap);
-	client->doorbell_id = GUC_DOORBELL_INVALID;
+	i915_vma_unpin_and_release(&guc->workqueue, I915_VMA_RELEASE_MAP);
 }
 
 /*
- * Tell the GuC to allocate or deallocate a specific doorbell
- */
-
-static int __guc_allocate_doorbell(struct intel_guc *guc, u32 stage_id)
-{
-	u32 action[] = {
-		INTEL_GUC_ACTION_ALLOCATE_DOORBELL,
-		stage_id
-	};
-
-	return intel_guc_send(guc, action, ARRAY_SIZE(action));
-}
-
-static int __guc_deallocate_doorbell(struct intel_guc *guc, u32 stage_id)
-{
-	u32 action[] = {
-		INTEL_GUC_ACTION_DEALLOCATE_DOORBELL,
-		stage_id
-	};
-
-	return intel_guc_send(guc, action, ARRAY_SIZE(action));
-}
-
-static struct guc_stage_desc *__get_stage_desc(struct intel_guc_client *client)
-{
-	struct guc_stage_desc *base = client->guc->stage_desc_pool_vaddr;
-
-	return &base[client->stage_id];
-}
-
-/*
- * Initialise, update, or clear doorbell data shared with the GuC
- *
- * These functions modify shared data and so need access to the mapped
- * client object which contains the page being used for the doorbell
+ * Initialise the process descriptor shared with the GuC firmware.
  */
-
-static void __update_doorbell_desc(struct intel_guc_client *client, u16 new_id)
-{
-	struct guc_stage_desc *desc;
-
-	/* Update the GuC's idea of the doorbell ID */
-	desc = __get_stage_desc(client);
-	desc->db_id = new_id;
-}
-
-static struct guc_doorbell_info *__get_doorbell(struct intel_guc_client *client)
-{
-	return client->vaddr + client->doorbell_offset;
-}
-
-static bool __doorbell_valid(struct intel_guc *guc, u16 db_id)
-{
-	struct intel_uncore *uncore = guc_to_gt(guc)->uncore;
-
-	GEM_BUG_ON(db_id >= GUC_NUM_DOORBELLS);
-	return intel_uncore_read(uncore, GEN8_DRBREGL(db_id)) & GEN8_DRB_VALID;
-}
-
-static void __init_doorbell(struct intel_guc_client *client)
-{
-	struct guc_doorbell_info *doorbell;
-
-	doorbell = __get_doorbell(client);
-	doorbell->db_status = GUC_DOORBELL_ENABLED;
-	doorbell->cookie = 0;
-}
-
-static void __fini_doorbell(struct intel_guc_client *client)
-{
-	struct guc_doorbell_info *doorbell;
-	u16 db_id = client->doorbell_id;
-
-	doorbell = __get_doorbell(client);
-	doorbell->db_status = GUC_DOORBELL_DISABLED;
-
-	/* Doorbell release flow requires that we wait for GEN8_DRB_VALID bit
-	 * to go to zero after updating db_status before we call the GuC to
-	 * release the doorbell
-	 */
-	if (wait_for_us(!__doorbell_valid(client->guc, db_id), 10))
-		WARN_ONCE(true, "Doorbell never became invalid after disable\n");
-}
-
-static int create_doorbell(struct intel_guc_client *client)
+static int guc_proc_desc_create(struct intel_guc *guc)
 {
-	int ret;
-
-	if (WARN_ON(!has_doorbell(client)))
-		return -ENODEV; /* internal setup error, should never happen */
-
-	__update_doorbell_desc(client, client->doorbell_id);
-	__init_doorbell(client);
-
-	ret = __guc_allocate_doorbell(client->guc, client->stage_id);
-	if (ret) {
-		__fini_doorbell(client);
-		__update_doorbell_desc(client, GUC_DOORBELL_INVALID);
-		DRM_DEBUG_DRIVER("Couldn't create client %u doorbell: %d\n",
-				 client->stage_id, ret);
-		return ret;
-	}
+	const u32 size = PAGE_ALIGN(sizeof(struct guc_process_desc));
 
-	return 0;
+	return intel_guc_allocate_and_map_vma(guc, size, &guc->proc_desc,
+					      &guc->proc_desc_vaddr);
 }
 
-static int destroy_doorbell(struct intel_guc_client *client)
+static void guc_proc_desc_destroy(struct intel_guc *guc)
 {
-	int ret;
-
-	GEM_BUG_ON(!has_doorbell(client));
-
-	__fini_doorbell(client);
-	ret = __guc_deallocate_doorbell(client->guc, client->stage_id);
-	if (ret)
-		DRM_ERROR("Couldn't destroy client %u doorbell: %d\n",
-			  client->stage_id, ret);
-
-	__update_doorbell_desc(client, GUC_DOORBELL_INVALID);
-
-	return ret;
+	i915_vma_unpin_and_release(&guc->proc_desc, I915_VMA_RELEASE_MAP);
 }
 
-static unsigned long __select_cacheline(struct intel_guc *guc)
-{
-	unsigned long offset;
-
-	/* Doorbell uses a single cache line within a page */
-	offset = offset_in_page(guc->db_cacheline);
-
-	/* Moving to next cache line to reduce contention */
-	guc->db_cacheline += cache_line_size();
-
-	DRM_DEBUG_DRIVER("reserved cacheline 0x%lx, next 0x%x, linesize %u\n",
-			 offset, guc->db_cacheline, cache_line_size());
-	return offset;
-}
-
-static inline struct guc_process_desc *
-__get_process_desc(struct intel_guc_client *client)
-{
-	return client->vaddr + client->proc_desc_offset;
-}
-
-/*
- * Initialise the process descriptor shared with the GuC firmware.
- */
-static void guc_proc_desc_init(struct intel_guc_client *client)
+static void guc_proc_desc_init(struct intel_guc *guc)
 {
 	struct guc_process_desc *desc;
 
-	desc = memset(__get_process_desc(client), 0, sizeof(*desc));
+	desc = memset(guc->proc_desc_vaddr, 0, sizeof(*desc));
 
 	/*
 	 * XXX: pDoorbell and WQVBaseAddress are pointers in process address
@@ -301,47 +108,27 @@ static void guc_proc_desc_init(struct intel_guc_client *client)
 	desc->wq_base_addr = 0;
 	desc->db_base_addr = 0;
 
-	desc->stage_id = client->stage_id;
 	desc->wq_size_bytes = GUC_WQ_SIZE;
 	desc->wq_status = WQ_STATUS_ACTIVE;
-	desc->priority = client->priority;
+	desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL;
 }
 
-static void guc_proc_desc_fini(struct intel_guc_client *client)
+static void guc_proc_desc_fini(struct intel_guc *guc)
 {
-	struct guc_process_desc *desc;
-
-	desc = __get_process_desc(client);
-	memset(desc, 0, sizeof(*desc));
+	memset(guc->proc_desc_vaddr, 0, sizeof(struct guc_process_desc));
 }
 
 static int guc_stage_desc_pool_create(struct intel_guc *guc)
 {
-	struct i915_vma *vma;
-	void *vaddr;
-
-	vma = intel_guc_allocate_vma(guc,
-				     PAGE_ALIGN(sizeof(struct guc_stage_desc) *
-				     GUC_MAX_STAGE_DESCRIPTORS));
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
-
-	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(vaddr)) {
-		i915_vma_unpin_and_release(&vma, 0);
-		return PTR_ERR(vaddr);
-	}
-
-	guc->stage_desc_pool = vma;
-	guc->stage_desc_pool_vaddr = vaddr;
-	ida_init(&guc->stage_ids);
+	u32 size = PAGE_ALIGN(sizeof(struct guc_stage_desc) *
+			      GUC_MAX_STAGE_DESCRIPTORS);
 
-	return 0;
+	return intel_guc_allocate_and_map_vma(guc, size, &guc->stage_desc_pool,
+					      &guc->stage_desc_pool_vaddr);
 }
 
 static void guc_stage_desc_pool_destroy(struct intel_guc *guc)
 {
-	ida_destroy(&guc->stage_ids);
 	i915_vma_unpin_and_release(&guc->stage_desc_pool, I915_VMA_RELEASE_MAP);
 }
 
@@ -349,63 +136,49 @@ static void guc_stage_desc_pool_destroy(struct intel_guc *guc)
  * Initialise/clear the stage descriptor shared with the GuC firmware.
  *
  * This descriptor tells the GuC where (in GGTT space) to find the important
- * data structures relating to this client (doorbell, process descriptor,
- * write queue, etc).
+ * data structures related to work submission (process descriptor, write queue,
+ * etc).
  */
-static void guc_stage_desc_init(struct intel_guc_client *client)
+static void guc_stage_desc_init(struct intel_guc *guc)
 {
-	struct intel_guc *guc = client->guc;
 	struct guc_stage_desc *desc;
-	u32 gfx_addr;
 
-	desc = __get_stage_desc(client);
+	/* we only use 1 stage desc, so hardcode it to 0 */
+	desc = __get_stage_desc(guc, 0);
 	memset(desc, 0, sizeof(*desc));
 
 	desc->attribute = GUC_STAGE_DESC_ATTR_ACTIVE |
 			  GUC_STAGE_DESC_ATTR_KERNEL;
-	if (is_high_priority(client))
-		desc->attribute |= GUC_STAGE_DESC_ATTR_PREEMPT;
-	desc->stage_id = client->stage_id;
-	desc->priority = client->priority;
-	desc->db_id = client->doorbell_id;
 
-	/*
-	 * The doorbell, process descriptor, and workqueue are all parts
-	 * of the client object, which the GuC will reference via the GGTT
-	 */
-	gfx_addr = intel_guc_ggtt_offset(guc, client->vma);
-	desc->db_trigger_phy = sg_dma_address(client->vma->pages->sgl) +
-				client->doorbell_offset;
-	desc->db_trigger_cpu = ptr_to_u64(__get_doorbell(client));
-	desc->db_trigger_uk = gfx_addr + client->doorbell_offset;
-	desc->process_desc = gfx_addr + client->proc_desc_offset;
-	desc->wq_addr = gfx_addr + GUC_DB_SIZE;
-	desc->wq_size = GUC_WQ_SIZE;
+	desc->stage_id = 0;
+	desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL;
 
-	desc->desc_private = ptr_to_u64(client);
+	desc->process_desc = intel_guc_ggtt_offset(guc, guc->proc_desc);
+	desc->wq_addr = intel_guc_ggtt_offset(guc, guc->workqueue);
+	desc->wq_size = GUC_WQ_SIZE;
 }
 
-static void guc_stage_desc_fini(struct intel_guc_client *client)
+static void guc_stage_desc_fini(struct intel_guc *guc)
 {
 	struct guc_stage_desc *desc;
 
-	desc = __get_stage_desc(client);
+	desc = __get_stage_desc(guc, 0);
 	memset(desc, 0, sizeof(*desc));
 }
 
 /* Construct a Work Item and append it to the GuC's Work Queue */
-static void guc_wq_item_append(struct intel_guc_client *client,
+static void guc_wq_item_append(struct intel_guc *guc,
 			       u32 target_engine, u32 context_desc,
 			       u32 ring_tail, u32 fence_id)
 {
 	/* wqi_len is in DWords, and does not include the one-word header */
 	const size_t wqi_size = sizeof(struct guc_wq_item);
 	const u32 wqi_len = wqi_size / sizeof(u32) - 1;
-	struct guc_process_desc *desc = __get_process_desc(client);
+	struct guc_process_desc *desc = guc->proc_desc_vaddr;
 	struct guc_wq_item *wqi;
 	u32 wq_off;
 
-	lockdep_assert_held(&client->wq_lock);
+	lockdep_assert_held(&guc->wq_lock);
 
 	/* For now workqueue item is 4 DWs; workqueue buffer is 2 pages. So we
 	 * should not have the case where structure wqi is across page, neither
@@ -425,58 +198,30 @@ static void guc_wq_item_append(struct intel_guc_client *client,
 			      GUC_WQ_SIZE) < wqi_size);
 	GEM_BUG_ON(wq_off & (wqi_size - 1));
 
-	/* WQ starts from the page after doorbell / process_desc */
-	wqi = client->vaddr + wq_off + GUC_DB_SIZE;
-
-	if (I915_SELFTEST_ONLY(client->use_nop_wqi)) {
-		wqi->header = WQ_TYPE_NOOP | (wqi_len << WQ_LEN_SHIFT);
-	} else {
-		/* Now fill in the 4-word work queue item */
-		wqi->header = WQ_TYPE_INORDER |
-			      (wqi_len << WQ_LEN_SHIFT) |
-			      (target_engine << WQ_TARGET_SHIFT) |
-			      WQ_NO_WCFLUSH_WAIT;
-		wqi->context_desc = context_desc;
-		wqi->submit_element_info = ring_tail << WQ_RING_TAIL_SHIFT;
-		GEM_BUG_ON(ring_tail > WQ_RING_TAIL_MAX);
-		wqi->fence_id = fence_id;
-	}
+	wqi = guc->workqueue_vaddr + wq_off;
+
+	/* Now fill in the 4-word work queue item */
+	wqi->header = WQ_TYPE_INORDER |
+		      (wqi_len << WQ_LEN_SHIFT) |
+		      (target_engine << WQ_TARGET_SHIFT) |
+		      WQ_NO_WCFLUSH_WAIT;
+	wqi->context_desc = context_desc;
+	wqi->submit_element_info = ring_tail << WQ_RING_TAIL_SHIFT;
+	GEM_BUG_ON(ring_tail > WQ_RING_TAIL_MAX);
+	wqi->fence_id = fence_id;
 
 	/* Make the update visible to GuC */
 	WRITE_ONCE(desc->tail, (wq_off + wqi_size) & (GUC_WQ_SIZE - 1));
 }
 
-static void guc_ring_doorbell(struct intel_guc_client *client)
-{
-	struct guc_doorbell_info *db;
-	u32 cookie;
-
-	lockdep_assert_held(&client->wq_lock);
-
-	/* pointer of current doorbell cacheline */
-	db = __get_doorbell(client);
-
-	/*
-	 * We're not expecting the doorbell cookie to change behind our back,
-	 * we also need to treat 0 as a reserved value.
-	 */
-	cookie = READ_ONCE(db->cookie);
-	WARN_ON_ONCE(xchg(&db->cookie, cookie + 1 ?: cookie + 2) != cookie);
-
-	/* XXX: doorbell was lost and need to acquire it again */
-	GEM_BUG_ON(db->db_status != GUC_DOORBELL_ENABLED);
-}
-
 static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
-	struct intel_guc_client *client = guc->execbuf_client;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc = lower_32_bits(rq->hw_context->lrc_desc);
+	u32 ctx_desc = lower_32_bits(rq->context->lrc_desc);
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
-	guc_wq_item_append(client, engine->guc_id, ctx_desc,
+	guc_wq_item_append(guc, engine->guc_id, ctx_desc,
 			   ring_tail, rq->fence.seqno);
-	guc_ring_doorbell(client);
 }
 
 /*
@@ -488,10 +233,9 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
  */
 static void flush_ggtt_writes(struct i915_vma *vma)
 {
-	struct drm_i915_private *i915 = vma->vm->i915;
-
 	if (i915_vma_is_map_and_fenceable(vma))
-		intel_uncore_posting_read_fw(&i915->uncore, GUC_STATUS);
+		intel_uncore_posting_read_fw(vma->vm->gt->uncore,
+					     GUC_STATUS);
 }
 
 static void guc_submit(struct intel_engine_cs *engine,
@@ -499,9 +243,8 @@ static void guc_submit(struct intel_engine_cs *engine,
 		       struct i915_request **end)
 {
 	struct intel_guc *guc = &engine->gt->uc.guc;
-	struct intel_guc_client *client = guc->execbuf_client;
 
-	spin_lock(&client->wq_lock);
+	spin_lock(&guc->wq_lock);
 
 	do {
 		struct i915_request *rq = *out++;
@@ -510,7 +253,7 @@ static void guc_submit(struct intel_engine_cs *engine,
 		guc_add_request(guc, rq);
 	} while (out != end);
 
-	spin_unlock(&client->wq_lock);
+	spin_unlock(&guc->wq_lock);
 }
 
 static inline int rq_prio(const struct i915_request *rq)
@@ -529,7 +272,7 @@ static struct i915_request *schedule_in(struct i915_request *rq, int idx)
 	 * required if we generalise the inflight tracking.
 	 */
 
-	intel_gt_pm_get(rq->engine->gt);
+	__intel_gt_pm_get(rq->engine->gt);
 	return i915_request_get(rq);
 }
 
@@ -537,7 +280,7 @@ static void schedule_out(struct i915_request *rq)
 {
 	trace_i915_request_out(rq);
 
-	intel_gt_pm_put(rq->engine->gt);
+	intel_gt_pm_put_async(rq->engine->gt);
 	i915_request_put(rq);
 }
 
@@ -572,7 +315,7 @@ static void __guc_dequeue(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			if (last && rq->hw_context != last->hw_context) {
+			if (last && rq->context != last->context) {
 				if (port == last_port)
 					goto done;
 
@@ -631,7 +374,7 @@ static void guc_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Prevent request submission to the hardware until we have
@@ -658,7 +401,7 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 		memset(execlists->inflight, 0, sizeof(execlists->inflight));
 }
 
-static void guc_reset(struct intel_engine_cs *engine, bool stalled)
+static void guc_reset_rewind(struct intel_engine_cs *engine, bool stalled)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq;
@@ -677,20 +420,20 @@ static void guc_reset(struct intel_engine_cs *engine, bool stalled)
 		stalled = false;
 
 	__i915_request_reset(rq, stalled);
-	intel_lr_context_reset(engine, rq->hw_context, rq->head, stalled);
+	intel_lr_context_reset(engine, rq->context, rq->head, stalled);
 
 out_unlock:
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 }
 
-static void guc_cancel_requests(struct intel_engine_cs *engine)
+static void guc_reset_cancel(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *rq, *rn;
 	struct rb_node *rb;
 	unsigned long flags;
 
-	GEM_TRACE("%s\n", engine->name);
+	ENGINE_TRACE(engine, "\n");
 
 	/*
 	 * Before we call engine->cancel_requests(), we should have exclusive
@@ -751,8 +494,8 @@ static void guc_reset_finish(struct intel_engine_cs *engine)
 		/* And kick in case we missed a new request submission. */
 		tasklet_hi_schedule(&execlists->tasklet);
 
-	GEM_TRACE("%s: depth->%d\n", engine->name,
-		  atomic_read(&execlists->tasklet.count));
+	ENGINE_TRACE(engine, "depth->%d\n",
+		     atomic_read(&execlists->tasklet.count));
 }
 
 /*
@@ -761,213 +504,6 @@ static void guc_reset_finish(struct intel_engine_cs *engine)
  * path of guc_submit() above.
  */
 
-/* Check that a doorbell register is in the expected state */
-static bool doorbell_ok(struct intel_guc *guc, u16 db_id)
-{
-	bool valid;
-
-	GEM_BUG_ON(db_id >= GUC_NUM_DOORBELLS);
-
-	valid = __doorbell_valid(guc, db_id);
-
-	if (test_bit(db_id, guc->doorbell_bitmap) == valid)
-		return true;
-
-	DRM_DEBUG_DRIVER("Doorbell %u has unexpected state: valid=%s\n",
-			 db_id, yesno(valid));
-
-	return false;
-}
-
-static bool guc_verify_doorbells(struct intel_guc *guc)
-{
-	bool doorbells_ok = true;
-	u16 db_id;
-
-	for (db_id = 0; db_id < GUC_NUM_DOORBELLS; ++db_id)
-		if (!doorbell_ok(guc, db_id))
-			doorbells_ok = false;
-
-	return doorbells_ok;
-}
-
-/**
- * guc_client_alloc() - Allocate an intel_guc_client
- * @guc:	the intel_guc structure
- * @priority:	four levels priority _CRITICAL, _HIGH, _NORMAL and _LOW
- *		The kernel client to replace ExecList submission is created with
- *		NORMAL priority. Priority of a client for scheduler can be HIGH,
- *		while a preemption context can use CRITICAL.
- *
- * Return:	An intel_guc_client object if success, else NULL.
- */
-static struct intel_guc_client *
-guc_client_alloc(struct intel_guc *guc, u32 priority)
-{
-	struct intel_guc_client *client;
-	struct i915_vma *vma;
-	void *vaddr;
-	int ret;
-
-	client = kzalloc(sizeof(*client), GFP_KERNEL);
-	if (!client)
-		return ERR_PTR(-ENOMEM);
-
-	client->guc = guc;
-	client->priority = priority;
-	client->doorbell_id = GUC_DOORBELL_INVALID;
-	spin_lock_init(&client->wq_lock);
-
-	ret = ida_simple_get(&guc->stage_ids, 0, GUC_MAX_STAGE_DESCRIPTORS,
-			     GFP_KERNEL);
-	if (ret < 0)
-		goto err_client;
-
-	client->stage_id = ret;
-
-	/* The first page is doorbell/proc_desc. Two followed pages are wq. */
-	vma = intel_guc_allocate_vma(guc, GUC_DB_SIZE + GUC_WQ_SIZE);
-	if (IS_ERR(vma)) {
-		ret = PTR_ERR(vma);
-		goto err_id;
-	}
-
-	/* We'll keep just the first (doorbell/proc) page permanently kmap'd. */
-	client->vma = vma;
-
-	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(vaddr)) {
-		ret = PTR_ERR(vaddr);
-		goto err_vma;
-	}
-	client->vaddr = vaddr;
-
-	ret = reserve_doorbell(client);
-	if (ret)
-		goto err_vaddr;
-
-	client->doorbell_offset = __select_cacheline(guc);
-
-	/*
-	 * Since the doorbell only requires a single cacheline, we can save
-	 * space by putting the application process descriptor in the same
-	 * page. Use the half of the page that doesn't include the doorbell.
-	 */
-	if (client->doorbell_offset >= (GUC_DB_SIZE / 2))
-		client->proc_desc_offset = 0;
-	else
-		client->proc_desc_offset = (GUC_DB_SIZE / 2);
-
-	DRM_DEBUG_DRIVER("new priority %u client %p: stage_id %u\n",
-			 priority, client, client->stage_id);
-	DRM_DEBUG_DRIVER("doorbell id %u, cacheline offset 0x%lx\n",
-			 client->doorbell_id, client->doorbell_offset);
-
-	return client;
-
-err_vaddr:
-	i915_gem_object_unpin_map(client->vma->obj);
-err_vma:
-	i915_vma_unpin_and_release(&client->vma, 0);
-err_id:
-	ida_simple_remove(&guc->stage_ids, client->stage_id);
-err_client:
-	kfree(client);
-	return ERR_PTR(ret);
-}
-
-static void guc_client_free(struct intel_guc_client *client)
-{
-	unreserve_doorbell(client);
-	i915_vma_unpin_and_release(&client->vma, I915_VMA_RELEASE_MAP);
-	ida_simple_remove(&client->guc->stage_ids, client->stage_id);
-	kfree(client);
-}
-
-static inline bool ctx_save_restore_disabled(struct intel_context *ce)
-{
-	u32 sr = ce->lrc_reg_state[CTX_CONTEXT_CONTROL + 1];
-
-#define SR_DISABLED \
-	_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT | \
-			   CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT)
-
-	return (sr & SR_DISABLED) == SR_DISABLED;
-
-#undef SR_DISABLED
-}
-
-static int guc_clients_create(struct intel_guc *guc)
-{
-	struct intel_guc_client *client;
-
-	GEM_BUG_ON(guc->execbuf_client);
-
-	client = guc_client_alloc(guc, GUC_CLIENT_PRIORITY_KMD_NORMAL);
-	if (IS_ERR(client)) {
-		DRM_ERROR("Failed to create GuC client for submission!\n");
-		return PTR_ERR(client);
-	}
-	guc->execbuf_client = client;
-
-	return 0;
-}
-
-static void guc_clients_destroy(struct intel_guc *guc)
-{
-	struct intel_guc_client *client;
-
-	client = fetch_and_zero(&guc->execbuf_client);
-	if (client)
-		guc_client_free(client);
-}
-
-static int __guc_client_enable(struct intel_guc_client *client)
-{
-	int ret;
-
-	guc_proc_desc_init(client);
-	guc_stage_desc_init(client);
-
-	ret = create_doorbell(client);
-	if (ret)
-		goto fail;
-
-	return 0;
-
-fail:
-	guc_stage_desc_fini(client);
-	guc_proc_desc_fini(client);
-	return ret;
-}
-
-static void __guc_client_disable(struct intel_guc_client *client)
-{
-	/*
-	 * By the time we're here, GuC may have already been reset. if that is
-	 * the case, instead of trying (in vain) to communicate with it, let's
-	 * just cleanup the doorbell HW and our internal state.
-	 */
-	if (intel_guc_is_running(client->guc))
-		destroy_doorbell(client);
-	else
-		__fini_doorbell(client);
-
-	guc_stage_desc_fini(client);
-	guc_proc_desc_fini(client);
-}
-
-static int guc_clients_enable(struct intel_guc *guc)
-{
-	return __guc_client_enable(guc->execbuf_client);
-}
-
-static void guc_clients_disable(struct intel_guc *guc)
-{
-	if (guc->execbuf_client)
-		__guc_client_disable(guc->execbuf_client);
-}
-
 /*
  * Set up the memory resources to be shared with the GuC (via the GGTT)
  * at firmware loading time.
@@ -988,13 +524,20 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	 */
 	GEM_BUG_ON(!guc->stage_desc_pool);
 
-	WARN_ON(!guc_verify_doorbells(guc));
-	ret = guc_clients_create(guc);
+	ret = guc_workqueue_create(guc);
 	if (ret)
 		goto err_pool;
 
+	ret = guc_proc_desc_create(guc);
+	if (ret)
+		goto err_workqueue;
+
+	spin_lock_init(&guc->wq_lock);
+
 	return 0;
 
+err_workqueue:
+	guc_workqueue_destroy(guc);
 err_pool:
 	guc_stage_desc_pool_destroy(guc);
 	return ret;
@@ -1002,83 +545,37 @@ err_pool:
 
 void intel_guc_submission_fini(struct intel_guc *guc)
 {
-	guc_clients_destroy(guc);
-	WARN_ON(!guc_verify_doorbells(guc));
-
-	if (guc->stage_desc_pool)
+	if (guc->stage_desc_pool) {
+		guc_proc_desc_destroy(guc);
+		guc_workqueue_destroy(guc);
 		guc_stage_desc_pool_destroy(guc);
+	}
 }
 
 static void guc_interrupts_capture(struct intel_gt *gt)
 {
-	struct intel_rps *rps = &gt->rps;
 	struct intel_uncore *uncore = gt->uncore;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int irqs;
+	u32 irqs = GT_CONTEXT_SWITCH_INTERRUPT;
+	u32 dmask = irqs << 16 | irqs;
 
-	/* tell all command streamers to forward interrupts (but not vblank)
-	 * to GuC
-	 */
-	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, gt, id)
-		ENGINE_WRITE(engine, RING_MODE_GEN7, irqs);
-
-	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
-	irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
-	       GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
-	/* These three registers have the same bit definitions */
-	intel_uncore_write(uncore, GUC_BCS_RCS_IER, ~irqs);
-	intel_uncore_write(uncore, GUC_VCS2_VCS1_IER, ~irqs);
-	intel_uncore_write(uncore, GUC_WD_VECS_IER, ~irqs);
+	GEM_BUG_ON(INTEL_GEN(gt->i915) < 11);
 
-	/*
-	 * The REDIRECT_TO_GUC bit of the PMINTRMSK register directs all
-	 * (unmasked) PM interrupts to the GuC. All other bits of this
-	 * register *disable* generation of a specific interrupt.
-	 *
-	 * 'pm_intrmsk_mbz' indicates bits that are NOT to be set when
-	 * writing to the PM interrupt mask register, i.e. interrupts
-	 * that must not be disabled.
-	 *
-	 * If the GuC is handling these interrupts, then we must not let
-	 * the PM code disable ANY interrupt that the GuC is expecting.
-	 * So for each ENABLED (0) bit in this register, we must SET the
-	 * bit in pm_intrmsk_mbz so that it's left enabled for the GuC.
-	 * GuC needs ARAT expired interrupt unmasked hence it is set in
-	 * pm_intrmsk_mbz.
-	 *
-	 * Here we CLEAR REDIRECT_TO_GUC bit in pm_intrmsk_mbz, which will
-	 * result in the register bit being left SET!
-	 */
-	rps->pm_intrmsk_mbz |= ARAT_EXPIRED_INTRMSK;
-	rps->pm_intrmsk_mbz &= ~GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
+	/* Don't handle the ctx switch interrupt in GuC submission mode */
+	intel_uncore_rmw(uncore, GEN11_RENDER_COPY_INTR_ENABLE, dmask, 0);
+	intel_uncore_rmw(uncore, GEN11_VCS_VECS_INTR_ENABLE, dmask, 0);
 }
 
 static void guc_interrupts_release(struct intel_gt *gt)
 {
-	struct intel_rps *rps = &gt->rps;
 	struct intel_uncore *uncore = gt->uncore;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int irqs;
+	u32 irqs = GT_CONTEXT_SWITCH_INTERRUPT;
+	u32 dmask = irqs << 16 | irqs;
 
-	/*
-	 * tell all command streamers NOT to forward interrupts or vblank
-	 * to GuC.
-	 */
-	irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
-	irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, gt, id)
-		ENGINE_WRITE(engine, RING_MODE_GEN7, irqs);
-
-	/* route all GT interrupts to the host */
-	intel_uncore_write(uncore, GUC_BCS_RCS_IER, 0);
-	intel_uncore_write(uncore, GUC_VCS2_VCS1_IER, 0);
-	intel_uncore_write(uncore, GUC_WD_VECS_IER, 0);
-
-	rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
-	rps->pm_intrmsk_mbz &= ~ARAT_EXPIRED_INTRMSK;
+	GEM_BUG_ON(INTEL_GEN(gt->i915) < 11);
+
+	/* Handle ctx switch interrupts again */
+	intel_uncore_rmw(uncore, GEN11_RENDER_COPY_INTR_ENABLE, 0, dmask);
+	intel_uncore_rmw(uncore, GEN11_VCS_VECS_INTR_ENABLE, 0, dmask);
 }
 
 static void guc_set_default_submission(struct intel_engine_cs *engine)
@@ -1102,11 +599,10 @@ static void guc_set_default_submission(struct intel_engine_cs *engine)
 	engine->park = engine->unpark = NULL;
 
 	engine->reset.prepare = guc_reset_prepare;
-	engine->reset.reset = guc_reset;
+	engine->reset.rewind = guc_reset_rewind;
+	engine->reset.cancel = guc_reset_cancel;
 	engine->reset.finish = guc_reset_finish;
 
-	engine->cancel_requests = guc_cancel_requests;
-
 	engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
 	engine->flags |= I915_ENGINE_NEEDS_BREADCRUMB_TASKLET;
 
@@ -1119,16 +615,11 @@ static void guc_set_default_submission(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->irq_enable || engine->irq_disable);
 }
 
-int intel_guc_submission_enable(struct intel_guc *guc)
+void intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	int err;
-
-	err = i915_inject_probe_error(gt->i915, -ENXIO);
-	if (err)
-		return err;
 
 	/*
 	 * We're using GuC work items for submitting work through GuC. Since
@@ -1143,11 +634,8 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 		     sizeof(struct guc_wq_item) *
 		     I915_NUM_ENGINES > GUC_WQ_SIZE);
 
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	err = guc_clients_enable(guc);
-	if (err)
-		return err;
+	guc_proc_desc_init(guc);
+	guc_stage_desc_init(guc);
 
 	/* Take over from manual control of ELSP (execlists) */
 	guc_interrupts_capture(gt);
@@ -1156,8 +644,6 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 		engine->set_default_submission = guc_set_default_submission;
 		engine->set_default_submission(engine);
 	}
-
-	return 0;
 }
 
 void intel_guc_submission_disable(struct intel_guc *guc)
@@ -1166,8 +652,12 @@ void intel_guc_submission_disable(struct intel_guc *guc)
 
 	GEM_BUG_ON(gt->awake); /* GT should be parked first */
 
+	/* Note: By the time we're here, GuC may have already been reset */
+
 	guc_interrupts_release(gt);
-	guc_clients_disable(guc);
+
+	guc_stage_desc_fini(guc);
+	guc_proc_desc_fini(guc);
 }
 
 static bool __guc_submission_support(struct intel_guc *guc)
@@ -1186,6 +676,7 @@ void intel_guc_submission_init_early(struct intel_guc *guc)
 	guc->submission_supported = __guc_submission_support(guc);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftest_guc.c"
-#endif
+bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine)
+{
+	return engine->set_default_submission == guc_set_default_submission;
+}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
index 54d716828352..e402a2932592 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h
@@ -6,62 +6,18 @@
 #ifndef _INTEL_GUC_SUBMISSION_H_
 #define _INTEL_GUC_SUBMISSION_H_
 
-#include <linux/spinlock.h>
+#include <linux/types.h>
 
-#include "gt/intel_engine_types.h"
-
-#include "i915_gem.h"
-#include "i915_selftest.h"
-
-struct drm_i915_private;
-
-/*
- * This structure primarily describes the GEM object shared with the GuC.
- * The specs sometimes refer to this object as a "GuC context", but we use
- * the term "client" to avoid confusion with hardware contexts. This
- * GEM object is held for the entire lifetime of our interaction with
- * the GuC, being allocated before the GuC is loaded with its firmware.
- * Because there's no way to update the address used by the GuC after
- * initialisation, the shared object must stay pinned into the GGTT as
- * long as the GuC is in use. We also keep the first page (only) mapped
- * into kernel address space, as it includes shared data that must be
- * updated on every request submission.
- *
- * The single GEM object described here is actually made up of several
- * separate areas, as far as the GuC is concerned. The first page (kept
- * kmap'd) includes the "process descriptor" which holds sequence data for
- * the doorbell, and one cacheline which actually *is* the doorbell; a
- * write to this will "ring the doorbell" (i.e. send an interrupt to the
- * GuC). The subsequent  pages of the client object constitute the work
- * queue (a circular array of work items), again described in the process
- * descriptor. Work queue pages are mapped momentarily as required.
- */
-struct intel_guc_client {
-	struct i915_vma *vma;
-	void *vaddr;
-	struct intel_guc *guc;
-
-	/* bitmap of (host) engine ids */
-	u32 priority;
-	u32 stage_id;
-	u32 proc_desc_offset;
-
-	u16 doorbell_id;
-	unsigned long doorbell_offset;
-
-	/* Protects GuC client's WQ access */
-	spinlock_t wq_lock;
-
-	/* For testing purposes, use nop WQ items instead of real ones */
-	I915_SELFTEST_DECLARE(bool use_nop_wqi);
-};
+struct intel_guc;
+struct intel_engine_cs;
 
 void intel_guc_submission_init_early(struct intel_guc *guc);
 int intel_guc_submission_init(struct intel_guc *guc);
-int intel_guc_submission_enable(struct intel_guc *guc);
+void intel_guc_submission_enable(struct intel_guc *guc);
 void intel_guc_submission_disable(struct intel_guc *guc);
 void intel_guc_submission_fini(struct intel_guc *guc);
 int intel_guc_preempt_work_create(struct intel_guc *guc);
 void intel_guc_preempt_work_destroy(struct intel_guc *guc);
+bool intel_engine_in_guc_submission_mode(const struct intel_engine_cs *engine);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
index d654340d4d03..eee193bf2cc4 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
@@ -39,5 +39,5 @@ void intel_huc_fw_init_early(struct intel_huc *huc)
 int intel_huc_fw_upload(struct intel_huc *huc)
 {
 	/* HW doesn't look at destination address for HuC, so set it to 0 */
-	return intel_uc_fw_upload(&huc->fw, huc_to_gt(huc), 0, HUC_UKERNEL);
+	return intel_uc_fw_upload(&huc->fw, 0, HUC_UKERNEL);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 629b19377a29..64934a876a50 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -12,6 +12,9 @@
 
 #include "i915_drv.h"
 
+static const struct intel_uc_ops uc_ops_off;
+static const struct intel_uc_ops uc_ops_on;
+
 /* Reset GuC providing us with fresh state for both GuC and HuC.
  */
 static int __intel_uc_reset_hw(struct intel_uc *uc)
@@ -89,6 +92,11 @@ void intel_uc_init_early(struct intel_uc *uc)
 	intel_huc_init_early(&uc->huc);
 
 	__confirm_options(uc);
+
+	if (intel_uc_uses_guc(uc))
+		uc->ops = &uc_ops_on;
+	else
+		uc->ops = &uc_ops_off;
 }
 
 void intel_uc_driver_late_release(struct intel_uc *uc)
@@ -123,6 +131,11 @@ static void __uc_free_load_err_log(struct intel_uc *uc)
 		i915_gem_object_put(log);
 }
 
+static inline bool guc_communication_enabled(struct intel_guc *guc)
+{
+	return intel_guc_ct_enabled(&guc->ct);
+}
+
 /*
  * Events triggered while CT buffers are disabled are logged in the SCRATCH_15
  * register using the same bits used in the CT message payload. Since our
@@ -158,7 +171,7 @@ static void guc_handle_mmio_msg(struct intel_guc *guc)
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 
 	/* we need communication to be enabled to reply to GuC */
-	GEM_BUG_ON(guc->handler == intel_guc_to_host_event_handler_nop);
+	GEM_BUG_ON(!guc_communication_enabled(guc));
 
 	if (!guc->mmio_msg)
 		return;
@@ -185,11 +198,6 @@ static void guc_disable_interrupts(struct intel_guc *guc)
 	guc->interrupts.disable(guc);
 }
 
-static inline bool guc_communication_enabled(struct intel_guc *guc)
-{
-	return guc->send != intel_guc_send_nop;
-}
-
 static int guc_enable_communication(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
@@ -205,9 +213,6 @@ static int guc_enable_communication(struct intel_guc *guc)
 	if (ret)
 		return ret;
 
-	guc->send = intel_guc_send_ct;
-	guc->handler = intel_guc_to_host_event_handler_ct;
-
 	/* check for mmio messages received before/during the CT enable */
 	guc_get_mmio_msg(guc);
 	guc_handle_mmio_msg(guc);
@@ -216,7 +221,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 
 	/* check for CT messages received before we enabled interrupts */
 	spin_lock_irq(&i915->irq_lock);
-	intel_guc_to_host_event_handler_ct(guc);
+	intel_guc_ct_event_handler(&guc->ct);
 	spin_unlock_irq(&i915->irq_lock);
 
 	DRM_INFO("GuC communication enabled\n");
@@ -224,7 +229,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 	return 0;
 }
 
-static void __guc_stop_communication(struct intel_guc *guc)
+static void guc_disable_communication(struct intel_guc *guc)
 {
 	/*
 	 * Events generated during or after CT disable are logged by guc in
@@ -235,23 +240,6 @@ static void __guc_stop_communication(struct intel_guc *guc)
 
 	guc_disable_interrupts(guc);
 
-	guc->send = intel_guc_send_nop;
-	guc->handler = intel_guc_to_host_event_handler_nop;
-}
-
-static void guc_stop_communication(struct intel_guc *guc)
-{
-	intel_guc_ct_stop(&guc->ct);
-
-	__guc_stop_communication(guc);
-
-	DRM_INFO("GuC communication stopped\n");
-}
-
-static void guc_disable_communication(struct intel_guc *guc)
-{
-	__guc_stop_communication(guc);
-
 	intel_guc_ct_disable(&guc->ct);
 
 	/*
@@ -265,41 +253,33 @@ static void guc_disable_communication(struct intel_guc *guc)
 	DRM_INFO("GuC communication disabled\n");
 }
 
-void intel_uc_fetch_firmwares(struct intel_uc *uc)
+static void __uc_fetch_firmwares(struct intel_uc *uc)
 {
-	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
 	int err;
 
-	if (!intel_uc_uses_guc(uc))
-		return;
+	GEM_BUG_ON(!intel_uc_uses_guc(uc));
 
-	err = intel_uc_fw_fetch(&uc->guc.fw, i915);
+	err = intel_uc_fw_fetch(&uc->guc.fw);
 	if (err)
 		return;
 
 	if (intel_uc_uses_huc(uc))
-		intel_uc_fw_fetch(&uc->huc.fw, i915);
+		intel_uc_fw_fetch(&uc->huc.fw);
 }
 
-void intel_uc_cleanup_firmwares(struct intel_uc *uc)
+static void __uc_cleanup_firmwares(struct intel_uc *uc)
 {
-	if (!intel_uc_uses_guc(uc))
-		return;
-
-	if (intel_uc_uses_huc(uc))
-		intel_uc_fw_cleanup_fetch(&uc->huc.fw);
-
+	intel_uc_fw_cleanup_fetch(&uc->huc.fw);
 	intel_uc_fw_cleanup_fetch(&uc->guc.fw);
 }
 
-void intel_uc_init(struct intel_uc *uc)
+static void __uc_init(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 	struct intel_huc *huc = &uc->huc;
 	int ret;
 
-	if (!intel_uc_uses_guc(uc))
-		return;
+	GEM_BUG_ON(!intel_uc_uses_guc(uc));
 
 	/* XXX: GuC submission is unavailable for now */
 	GEM_BUG_ON(intel_uc_supports_guc_submission(uc));
@@ -314,17 +294,10 @@ void intel_uc_init(struct intel_uc *uc)
 		intel_huc_init(huc);
 }
 
-void intel_uc_fini(struct intel_uc *uc)
+static void __uc_fini(struct intel_uc *uc)
 {
-	struct intel_guc *guc = &uc->guc;
-
-	if (!intel_uc_uses_guc(uc))
-		return;
-
-	if (intel_uc_uses_huc(uc))
-		intel_huc_fini(&uc->huc);
-
-	intel_guc_fini(guc);
+	intel_huc_fini(&uc->huc);
+	intel_guc_fini(&uc->guc);
 
 	__uc_free_load_err_log(uc);
 }
@@ -342,14 +315,6 @@ static int __uc_sanitize(struct intel_uc *uc)
 	return __intel_uc_reset_hw(uc);
 }
 
-void intel_uc_sanitize(struct intel_uc *uc)
-{
-	if (!intel_uc_supports_guc(uc))
-		return;
-
-	__uc_sanitize(uc);
-}
-
 /* Initialize and verify the uC regs related to uC positioning in WOPCM */
 static int uc_init_wopcm(struct intel_uc *uc)
 {
@@ -413,13 +378,8 @@ static bool uc_is_wopcm_locked(struct intel_uc *uc)
 	       (intel_uncore_read(uncore, DMA_GUC_WOPCM_OFFSET) & GUC_WOPCM_OFFSET_VALID);
 }
 
-int intel_uc_init_hw(struct intel_uc *uc)
+static int __uc_check_hw(struct intel_uc *uc)
 {
-	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
-	struct intel_guc *guc = &uc->guc;
-	struct intel_huc *huc = &uc->huc;
-	int ret, attempts;
-
 	if (!intel_uc_supports_guc(uc))
 		return 0;
 
@@ -428,11 +388,24 @@ int intel_uc_init_hw(struct intel_uc *uc)
 	 * before on this system after reboot, otherwise we risk GPU hangs.
 	 * To check if GuC was loaded before we look at WOPCM registers.
 	 */
-	if (!intel_uc_uses_guc(uc) && !uc_is_wopcm_locked(uc))
-		return 0;
+	if (uc_is_wopcm_locked(uc))
+		return -EIO;
+
+	return 0;
+}
+
+static int __uc_init_hw(struct intel_uc *uc)
+{
+	struct drm_i915_private *i915 = uc_to_gt(uc)->i915;
+	struct intel_guc *guc = &uc->guc;
+	struct intel_huc *huc = &uc->huc;
+	int ret, attempts;
+
+	GEM_BUG_ON(!intel_uc_supports_guc(uc));
+	GEM_BUG_ON(!intel_uc_uses_guc(uc));
 
 	if (!intel_uc_fw_is_available(&guc->fw)) {
-		ret = uc_is_wopcm_locked(uc) ||
+		ret = __uc_check_hw(uc) ||
 		      intel_uc_fw_is_overridden(&guc->fw) ||
 		      intel_uc_supports_guc_submission(uc) ?
 		      intel_uc_fw_status_to_error(guc->fw.status) : 0;
@@ -486,11 +459,8 @@ int intel_uc_init_hw(struct intel_uc *uc)
 	if (ret)
 		goto err_communication;
 
-	if (intel_uc_supports_guc_submission(uc)) {
-		ret = intel_guc_submission_enable(guc);
-		if (ret)
-			goto err_communication;
-	}
+	if (intel_uc_supports_guc_submission(uc))
+		intel_guc_submission_enable(guc);
 
 	dev_info(i915->drm.dev, "%s firmware %s version %u.%u %s:%s\n",
 		 intel_uc_fw_type_repr(INTEL_UC_FW_TYPE_GUC), guc->fw.path,
@@ -531,7 +501,7 @@ err_out:
 	return -EIO;
 }
 
-void intel_uc_fini_hw(struct intel_uc *uc)
+static void __uc_fini_hw(struct intel_uc *uc)
 {
 	struct intel_guc *guc = &uc->guc;
 
@@ -560,7 +530,7 @@ void intel_uc_reset_prepare(struct intel_uc *uc)
 	if (!intel_guc_is_running(guc))
 		return;
 
-	guc_stop_communication(guc);
+	guc_disable_communication(guc);
 	__uc_sanitize(uc);
 }
 
@@ -631,3 +601,20 @@ int intel_uc_runtime_resume(struct intel_uc *uc)
 	 */
 	return __uc_resume(uc, true);
 }
+
+static const struct intel_uc_ops uc_ops_off = {
+	.init_hw = __uc_check_hw,
+};
+
+static const struct intel_uc_ops uc_ops_on = {
+	.sanitize = __uc_sanitize,
+
+	.init_fw = __uc_fetch_firmwares,
+	.fini_fw = __uc_cleanup_firmwares,
+
+	.init = __uc_init,
+	.fini = __uc_fini,
+
+	.init_hw = __uc_init_hw,
+	.fini_hw = __uc_fini_hw,
+};
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.h b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
index 527995c21196..49c913524686 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.h
@@ -10,7 +10,20 @@
 #include "intel_huc.h"
 #include "i915_params.h"
 
+struct intel_uc;
+
+struct intel_uc_ops {
+	int (*sanitize)(struct intel_uc *uc);
+	void (*init_fw)(struct intel_uc *uc);
+	void (*fini_fw)(struct intel_uc *uc);
+	void (*init)(struct intel_uc *uc);
+	void (*fini)(struct intel_uc *uc);
+	int (*init_hw)(struct intel_uc *uc);
+	void (*fini_hw)(struct intel_uc *uc);
+};
+
 struct intel_uc {
+	struct intel_uc_ops const *ops;
 	struct intel_guc guc;
 	struct intel_huc huc;
 
@@ -21,13 +34,6 @@ struct intel_uc {
 void intel_uc_init_early(struct intel_uc *uc);
 void intel_uc_driver_late_release(struct intel_uc *uc);
 void intel_uc_init_mmio(struct intel_uc *uc);
-void intel_uc_fetch_firmwares(struct intel_uc *uc);
-void intel_uc_cleanup_firmwares(struct intel_uc *uc);
-void intel_uc_sanitize(struct intel_uc *uc);
-void intel_uc_init(struct intel_uc *uc);
-int intel_uc_init_hw(struct intel_uc *uc);
-void intel_uc_fini_hw(struct intel_uc *uc);
-void intel_uc_fini(struct intel_uc *uc);
 void intel_uc_reset_prepare(struct intel_uc *uc);
 void intel_uc_suspend(struct intel_uc *uc);
 void intel_uc_runtime_suspend(struct intel_uc *uc);
@@ -64,4 +70,20 @@ static inline bool intel_uc_uses_huc(struct intel_uc *uc)
 	return intel_huc_is_enabled(&uc->huc);
 }
 
+#define intel_uc_ops_function(_NAME, _OPS, _TYPE, _RET) \
+static inline _TYPE intel_uc_##_NAME(struct intel_uc *uc) \
+{ \
+	if (uc->ops->_OPS) \
+		return uc->ops->_OPS(uc); \
+	return _RET; \
+}
+intel_uc_ops_function(sanitize, sanitize, int, 0);
+intel_uc_ops_function(fetch_firmwares, init_fw, void, );
+intel_uc_ops_function(cleanup_firmwares, fini_fw, void, );
+intel_uc_ops_function(init, init, void, );
+intel_uc_ops_function(fini, fini, void, );
+intel_uc_ops_function(init_hw, init_hw, int, 0);
+intel_uc_ops_function(fini_hw, fini_hw, void, );
+#undef intel_uc_ops_function
+
 #endif
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 66a30ab7044a..8ee0a0c7f447 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -11,7 +11,6 @@
 #include "intel_uc_fw_abi.h"
 #include "i915_drv.h"
 
-#ifdef CONFIG_DRM_I915_DEBUG_GUC
 static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw)
 {
 	GEM_BUG_ON(uc_fw->status == INTEL_UC_FIRMWARE_UNINITIALIZED);
@@ -22,6 +21,7 @@ static inline struct intel_gt *__uc_fw_to_gt(struct intel_uc_fw *uc_fw)
 	return container_of(uc_fw, struct intel_gt, uc.huc.fw);
 }
 
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
 void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 			       enum intel_uc_fw_status status)
 {
@@ -219,10 +219,9 @@ void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
 				  INTEL_UC_FIRMWARE_NOT_SUPPORTED);
 }
 
-static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw,
-				      struct drm_i915_private *i915,
-				      int e)
+static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw, int e)
 {
+	struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915;
 	bool user = e == -EINVAL;
 
 	if (i915_inject_probe_error(i915, e)) {
@@ -260,14 +259,14 @@ static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw,
 /**
  * intel_uc_fw_fetch - fetch uC firmware
  * @uc_fw: uC firmware
- * @i915: device private
  *
  * Fetch uC firmware into GEM obj.
  *
  * Return: 0 on success, a negative errno code on failure.
  */
-int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915)
+int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 {
+	struct drm_i915_private *i915 = __uc_fw_to_gt(uc_fw)->i915;
 	struct device *dev = i915->drm.dev;
 	struct drm_i915_gem_object *obj;
 	const struct firmware *fw = NULL;
@@ -282,8 +281,8 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915)
 	if (err)
 		return err;
 
-	__force_fw_fetch_failures(uc_fw, i915, -EINVAL);
-	__force_fw_fetch_failures(uc_fw, i915, -ESTALE);
+	__force_fw_fetch_failures(uc_fw, -EINVAL);
+	__force_fw_fetch_failures(uc_fw, -ESTALE);
 
 	err = request_firmware(&fw, uc_fw->path, dev);
 	if (err)
@@ -390,8 +389,9 @@ fail:
 	return err;
 }
 
-static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw, struct i915_ggtt *ggtt)
+static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw)
 {
+	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
 	struct drm_mm_node *node = &ggtt->uc_fw;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(node));
@@ -401,13 +401,12 @@ static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw, struct i915_ggtt *ggtt)
 	return lower_32_bits(node->start);
 }
 
-static void intel_uc_fw_ggtt_bind(struct intel_uc_fw *uc_fw,
-				  struct intel_gt *gt)
+static void uc_fw_bind_ggtt(struct intel_uc_fw *uc_fw)
 {
 	struct drm_i915_gem_object *obj = uc_fw->obj;
-	struct i915_ggtt *ggtt = gt->ggtt;
+	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
 	struct i915_vma dummy = {
-		.node.start = uc_fw_ggtt_offset(uc_fw, ggtt),
+		.node.start = uc_fw_ggtt_offset(uc_fw),
 		.node.size = obj->base.size,
 		.pages = obj->mm.pages,
 		.vm = &ggtt->vm,
@@ -422,19 +421,18 @@ static void intel_uc_fw_ggtt_bind(struct intel_uc_fw *uc_fw,
 	ggtt->vm.insert_entries(&ggtt->vm, &dummy, I915_CACHE_NONE, 0);
 }
 
-static void intel_uc_fw_ggtt_unbind(struct intel_uc_fw *uc_fw,
-				    struct intel_gt *gt)
+static void uc_fw_unbind_ggtt(struct intel_uc_fw *uc_fw)
 {
 	struct drm_i915_gem_object *obj = uc_fw->obj;
-	struct i915_ggtt *ggtt = gt->ggtt;
-	u64 start = uc_fw_ggtt_offset(uc_fw, ggtt);
+	struct i915_ggtt *ggtt = __uc_fw_to_gt(uc_fw)->ggtt;
+	u64 start = uc_fw_ggtt_offset(uc_fw);
 
 	ggtt->vm.clear_range(&ggtt->vm, start, obj->base.size);
 }
 
-static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
-		      u32 wopcm_offset, u32 dma_flags)
+static int uc_fw_xfer(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags)
 {
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 	struct intel_uncore *uncore = gt->uncore;
 	u64 offset;
 	int ret;
@@ -446,13 +444,13 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	/* Set the source address for the uCode */
-	offset = uc_fw_ggtt_offset(uc_fw, gt->ggtt);
+	offset = uc_fw_ggtt_offset(uc_fw);
 	GEM_BUG_ON(upper_32_bits(offset) & 0xFFFF0000);
 	intel_uncore_write_fw(uncore, DMA_ADDR_0_LOW, lower_32_bits(offset));
 	intel_uncore_write_fw(uncore, DMA_ADDR_0_HIGH, upper_32_bits(offset));
 
 	/* Set the DMA destination */
-	intel_uncore_write_fw(uncore, DMA_ADDR_1_LOW, wopcm_offset);
+	intel_uncore_write_fw(uncore, DMA_ADDR_1_LOW, dst_offset);
 	intel_uncore_write_fw(uncore, DMA_ADDR_1_HIGH, DMA_ADDRESS_SPACE_WOPCM);
 
 	/*
@@ -484,17 +482,16 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 /**
  * intel_uc_fw_upload - load uC firmware using custom loader
  * @uc_fw: uC firmware
- * @gt: the intel_gt structure
- * @wopcm_offset: destination offset in wopcm
+ * @dst_offset: destination offset
  * @dma_flags: flags for flags for dma ctrl
  *
  * Loads uC firmware and updates internal flags.
  *
  * Return: 0 on success, non-zero on failure.
  */
-int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
-		       u32 wopcm_offset, u32 dma_flags)
+int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, u32 dst_offset, u32 dma_flags)
 {
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 	int err;
 
 	/* make sure the status was cleared the last time we reset the uc */
@@ -508,9 +505,9 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 		return -ENOEXEC;
 
 	/* Call custom loader */
-	intel_uc_fw_ggtt_bind(uc_fw, gt);
-	err = uc_fw_xfer(uc_fw, gt, wopcm_offset, dma_flags);
-	intel_uc_fw_ggtt_unbind(uc_fw, gt);
+	uc_fw_bind_ggtt(uc_fw);
+	err = uc_fw_xfer(uc_fw, dst_offset, dma_flags);
+	uc_fw_unbind_ggtt(uc_fw);
 	if (err)
 		goto fail;
 
@@ -547,10 +544,7 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw)
 
 void intel_uc_fw_fini(struct intel_uc_fw *uc_fw)
 {
-	if (!intel_uc_fw_is_available(uc_fw))
-		return;
-
-	i915_gem_object_unpin_pages(uc_fw->obj);
+	intel_uc_fw_cleanup_fetch(uc_fw);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
index 7a0a5989afc9..1f30543d0d2d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
@@ -229,10 +229,9 @@ static inline u32 intel_uc_fw_get_upload_size(struct intel_uc_fw *uc_fw)
 void intel_uc_fw_init_early(struct intel_uc_fw *uc_fw,
 			    enum intel_uc_fw_type type, bool supported,
 			    enum intel_platform platform, u8 rev);
-int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915);
+int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw);
 void intel_uc_fw_cleanup_fetch(struct intel_uc_fw *uc_fw);
-int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
-		       u32 wopcm_offset, u32 dma_flags);
+int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, u32 offset, u32 dma_flags);
 int intel_uc_fw_init(struct intel_uc_fw *uc_fw);
 void intel_uc_fw_fini(struct intel_uc_fw *uc_fw);
 size_t intel_uc_fw_copy_rsa(struct intel_uc_fw *uc_fw, void *dst, u32 max_len);
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
deleted file mode 100644
index d8a80388bd31..000000000000
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
+++ /dev/null
@@ -1,299 +0,0 @@
-// SPDX-License-Identifier: MIT
-/*
- * Copyright © 2017 Intel Corporation
- */
-
-#include "i915_selftest.h"
-#include "gem/i915_gem_pm.h"
-
-/* max doorbell number + negative test for each client type */
-#define ATTEMPTS (GUC_NUM_DOORBELLS + GUC_CLIENT_PRIORITY_NUM)
-
-static struct intel_guc_client *clients[ATTEMPTS];
-
-static bool available_dbs(struct intel_guc *guc, u32 priority)
-{
-	unsigned long offset;
-	unsigned long end;
-	u16 id;
-
-	/* first half is used for normal priority, second half for high */
-	offset = 0;
-	end = GUC_NUM_DOORBELLS / 2;
-	if (priority <= GUC_CLIENT_PRIORITY_HIGH) {
-		offset = end;
-		end += offset;
-	}
-
-	id = find_next_zero_bit(guc->doorbell_bitmap, end, offset);
-	if (id < end)
-		return true;
-
-	return false;
-}
-
-static int check_all_doorbells(struct intel_guc *guc)
-{
-	u16 db_id;
-
-	pr_info_once("Max number of doorbells: %d", GUC_NUM_DOORBELLS);
-	for (db_id = 0; db_id < GUC_NUM_DOORBELLS; ++db_id) {
-		if (!doorbell_ok(guc, db_id)) {
-			pr_err("doorbell %d, not ok\n", db_id);
-			return -EIO;
-		}
-	}
-
-	return 0;
-}
-
-static int ring_doorbell_nop(struct intel_guc_client *client)
-{
-	struct guc_process_desc *desc = __get_process_desc(client);
-	int err;
-
-	client->use_nop_wqi = true;
-
-	spin_lock_irq(&client->wq_lock);
-
-	guc_wq_item_append(client, 0, 0, 0, 0);
-	guc_ring_doorbell(client);
-
-	spin_unlock_irq(&client->wq_lock);
-
-	client->use_nop_wqi = false;
-
-	/* if there are no issues GuC will update the WQ head and keep the
-	 * WQ in active status
-	 */
-	err = wait_for(READ_ONCE(desc->head) == READ_ONCE(desc->tail), 10);
-	if (err) {
-		pr_err("doorbell %u ring failed!\n", client->doorbell_id);
-		return -EIO;
-	}
-
-	if (desc->wq_status != WQ_STATUS_ACTIVE) {
-		pr_err("doorbell %u ring put WQ in bad state (%u)!\n",
-		       client->doorbell_id, desc->wq_status);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/*
- * Basic client sanity check, handy to validate create_clients.
- */
-static int validate_client(struct intel_guc_client *client, int client_priority)
-{
-	if (client->priority != client_priority ||
-	    client->doorbell_id == GUC_DOORBELL_INVALID)
-		return -EINVAL;
-	else
-		return 0;
-}
-
-static bool client_doorbell_in_sync(struct intel_guc_client *client)
-{
-	return !client || doorbell_ok(client->guc, client->doorbell_id);
-}
-
-/*
- * Check that we're able to synchronize guc_clients with their doorbells
- *
- * We're creating clients and reserving doorbells once, at module load. During
- * module lifetime, GuC, doorbell HW, and i915 state may go out of sync due to
- * GuC being reset. In other words - GuC clients are still around, but the
- * status of their doorbells may be incorrect. This is the reason behind
- * validating that the doorbells status expected by the driver matches what the
- * GuC/HW have.
- */
-static int igt_guc_clients(void *arg)
-{
-	struct intel_gt *gt = arg;
-	struct intel_guc *guc = &gt->uc.guc;
-	intel_wakeref_t wakeref;
-	int err = 0;
-
-	GEM_BUG_ON(!HAS_GT_UC(gt->i915));
-	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
-
-	err = check_all_doorbells(guc);
-	if (err)
-		goto unlock;
-
-	/*
-	 * Get rid of clients created during driver load because the test will
-	 * recreate them.
-	 */
-	guc_clients_disable(guc);
-	guc_clients_destroy(guc);
-	if (guc->execbuf_client) {
-		pr_err("guc_clients_destroy lied!\n");
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	err = guc_clients_create(guc);
-	if (err) {
-		pr_err("Failed to create clients\n");
-		goto unlock;
-	}
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	err = validate_client(guc->execbuf_client,
-			      GUC_CLIENT_PRIORITY_KMD_NORMAL);
-	if (err) {
-		pr_err("execbug client validation failed\n");
-		goto out;
-	}
-
-	/* the client should now have reserved a doorbell */
-	if (!has_doorbell(guc->execbuf_client)) {
-		pr_err("guc_clients_create didn't reserve doorbells\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	/* Now enable the clients */
-	guc_clients_enable(guc);
-
-	/* each client should now have received a doorbell */
-	if (!client_doorbell_in_sync(guc->execbuf_client)) {
-		pr_err("failed to initialize the doorbells\n");
-		err = -EINVAL;
-		goto out;
-	}
-
-	/*
-	 * Basic test - an attempt to reallocate a valid doorbell to the
-	 * client it is currently assigned should not cause a failure.
-	 */
-	err = create_doorbell(guc->execbuf_client);
-
-out:
-	/*
-	 * Leave clean state for other test, plus the driver always destroy the
-	 * clients during unload.
-	 */
-	guc_clients_disable(guc);
-	guc_clients_destroy(guc);
-	guc_clients_create(guc);
-	guc_clients_enable(guc);
-unlock:
-	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
-	return err;
-}
-
-/*
- * Create as many clients as number of doorbells. Note that there's already
- * client(s)/doorbell(s) created during driver load, but this test creates
- * its own and do not interact with the existing ones.
- */
-static int igt_guc_doorbells(void *arg)
-{
-	struct intel_gt *gt = arg;
-	struct intel_guc *guc = &gt->uc.guc;
-	intel_wakeref_t wakeref;
-	int i, err = 0;
-	u16 db_id;
-
-	GEM_BUG_ON(!HAS_GT_UC(gt->i915));
-	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
-
-	err = check_all_doorbells(guc);
-	if (err)
-		goto unlock;
-
-	for (i = 0; i < ATTEMPTS; i++) {
-		clients[i] = guc_client_alloc(guc, i % GUC_CLIENT_PRIORITY_NUM);
-
-		if (!clients[i]) {
-			pr_err("[%d] No guc client\n", i);
-			err = -EINVAL;
-			goto out;
-		}
-
-		if (IS_ERR(clients[i])) {
-			if (PTR_ERR(clients[i]) != -ENOSPC) {
-				pr_err("[%d] unexpected error\n", i);
-				err = PTR_ERR(clients[i]);
-				goto out;
-			}
-
-			if (available_dbs(guc, i % GUC_CLIENT_PRIORITY_NUM)) {
-				pr_err("[%d] non-db related alloc fail\n", i);
-				err = -EINVAL;
-				goto out;
-			}
-
-			/* expected, ran out of dbs for this client type */
-			continue;
-		}
-
-		/*
-		 * The check below is only valid because we keep a doorbell
-		 * assigned during the whole life of the client.
-		 */
-		if (clients[i]->stage_id >= GUC_NUM_DOORBELLS) {
-			pr_err("[%d] more clients than doorbells (%d >= %d)\n",
-			       i, clients[i]->stage_id, GUC_NUM_DOORBELLS);
-			err = -EINVAL;
-			goto out;
-		}
-
-		err = validate_client(clients[i], i % GUC_CLIENT_PRIORITY_NUM);
-		if (err) {
-			pr_err("[%d] client_alloc sanity check failed!\n", i);
-			err = -EINVAL;
-			goto out;
-		}
-
-		db_id = clients[i]->doorbell_id;
-
-		err = __guc_client_enable(clients[i]);
-		if (err) {
-			pr_err("[%d] Failed to create a doorbell\n", i);
-			goto out;
-		}
-
-		/* doorbell id shouldn't change, we are holding the mutex */
-		if (db_id != clients[i]->doorbell_id) {
-			pr_err("[%d] doorbell id changed (%d != %d)\n",
-			       i, db_id, clients[i]->doorbell_id);
-			err = -EINVAL;
-			goto out;
-		}
-
-		err = check_all_doorbells(guc);
-		if (err)
-			goto out;
-
-		err = ring_doorbell_nop(clients[i]);
-		if (err)
-			goto out;
-	}
-
-out:
-	for (i = 0; i < ATTEMPTS; i++)
-		if (!IS_ERR_OR_NULL(clients[i])) {
-			__guc_client_disable(clients[i]);
-			guc_client_free(clients[i]);
-		}
-unlock:
-	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
-	return err;
-}
-
-int intel_guc_live_selftest(struct drm_i915_private *i915)
-{
-	static const struct i915_subtest tests[] = {
-		SUBTEST(igt_guc_clients),
-		SUBTEST(igt_guc_doorbells),
-	};
-
-	if (!USES_GUC_SUBMISSION(i915))
-		return 0;
-
-	return intel_gt_live_subtests(tests, &i915->gt);
-}
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.h b/drivers/gpu/drm/i915/gvt/cmd_parser.h
index 286703643002..ab25d151932a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.h
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.h
@@ -38,6 +38,10 @@
 
 #define GVT_CMD_HASH_BITS 7
 
+struct intel_gvt;
+struct intel_shadow_wa_ctx;
+struct intel_vgpu_workload;
+
 void intel_gvt_clean_cmd_parser(struct intel_gvt *gvt);
 
 int intel_gvt_init_cmd_parser(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h
index a87f33e6a23c..b59b34046e1e 100644
--- a/drivers/gpu/drm/i915/gvt/display.h
+++ b/drivers/gpu/drm/i915/gvt/display.h
@@ -35,6 +35,11 @@
 #ifndef _GVT_DISPLAY_H_
 #define _GVT_DISPLAY_H_
 
+#include <linux/types.h>
+
+struct intel_gvt;
+struct intel_vgpu;
+
 #define SBI_REG_MAX	20
 #define DPCD_SIZE	0x700
 
diff --git a/drivers/gpu/drm/i915/gvt/edid.h b/drivers/gpu/drm/i915/gvt/edid.h
index f6dfc8b795ec..dfe0cbc6aad8 100644
--- a/drivers/gpu/drm/i915/gvt/edid.h
+++ b/drivers/gpu/drm/i915/gvt/edid.h
@@ -35,6 +35,10 @@
 #ifndef _GVT_EDID_H_
 #define _GVT_EDID_H_
 
+#include <linux/types.h>
+
+struct intel_vgpu;
+
 #define EDID_SIZE		128
 #define EDID_ADDR		0x50 /* Linux hvm EDID addr */
 
diff --git a/drivers/gpu/drm/i915/gvt/execlist.h b/drivers/gpu/drm/i915/gvt/execlist.h
index 5ccc2c695848..5c0c1fd30c83 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.h
+++ b/drivers/gpu/drm/i915/gvt/execlist.h
@@ -35,6 +35,8 @@
 #ifndef _GVT_EXECLIST_H_
 #define _GVT_EXECLIST_H_
 
+#include <linux/types.h>
+
 struct execlist_ctx_descriptor_format {
 	union {
 		u32 ldw;
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.h b/drivers/gpu/drm/i915/gvt/fb_decoder.h
index 60c155085029..67b6ede9e707 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.h
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.h
@@ -36,6 +36,8 @@
 #ifndef _GVT_FB_DECODER_H_
 #define _GVT_FB_DECODER_H_
 
+#include <linux/types.h>
+
 #define _PLANE_CTL_FORMAT_SHIFT		24
 #define _PLANE_CTL_TILED_SHIFT		10
 #define _PIPE_V_SRCSZ_SHIFT		0
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4b04af569c05..34cb404ba4b7 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1282,7 +1282,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
-	};
+	}
 
 	/* direct shadow */
 	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, page_size,
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 1043e6d564df..6d28d72e6c7e 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2691,7 +2691,7 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	return 0;
 }
 
-static int init_broadwell_mmio_info(struct intel_gvt *gvt)
+static int init_bdw_mmio_info(struct intel_gvt *gvt)
 {
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
 	int ret;
@@ -3380,20 +3380,20 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 		goto err;
 
 	if (IS_BROADWELL(dev_priv)) {
-		ret = init_broadwell_mmio_info(gvt);
+		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
 	} else if (IS_SKYLAKE(dev_priv)
 		|| IS_KABYLAKE(dev_priv)
 		|| IS_COFFEELAKE(dev_priv)) {
-		ret = init_broadwell_mmio_info(gvt);
+		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
 		ret = init_skl_mmio_info(gvt);
 		if (ret)
 			goto err;
 	} else if (IS_BROXTON(dev_priv)) {
-		ret = init_broadwell_mmio_info(gvt);
+		ret = init_bdw_mmio_info(gvt);
 		if (ret)
 			goto err;
 		ret = init_skl_mmio_info(gvt);
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index b19a3b1ea4c1..b17c4a1599cd 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -33,6 +33,10 @@
 #ifndef _GVT_HYPERCALL_H_
 #define _GVT_HYPERCALL_H_
 
+#include <linux/types.h>
+
+struct device;
+
 enum hypervisor_type {
 	INTEL_GVT_HYPERVISOR_XEN = 0,
 	INTEL_GVT_HYPERVISOR_KVM,
diff --git a/drivers/gpu/drm/i915/gvt/interrupt.h b/drivers/gpu/drm/i915/gvt/interrupt.h
index 5313fb1b33e1..fcd663811d37 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.h
+++ b/drivers/gpu/drm/i915/gvt/interrupt.h
@@ -32,6 +32,8 @@
 #ifndef _GVT_INTERRUPT_H_
 #define _GVT_INTERRUPT_H_
 
+#include <linux/types.h>
+
 enum intel_gvt_event_type {
 	RCS_MI_USER_INTERRUPT = 0,
 	RCS_DEBUG,
@@ -135,6 +137,7 @@ enum intel_gvt_event_type {
 
 struct intel_gvt_irq;
 struct intel_gvt;
+struct intel_vgpu;
 
 typedef void (*gvt_event_virt_handler_t)(struct intel_gvt_irq *irq,
 	enum intel_gvt_event_type event, struct intel_vgpu *vgpu);
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 5874f1cb4306..2e68f4b02c94 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -36,6 +36,8 @@
 #ifndef _GVT_MMIO_H_
 #define _GVT_MMIO_H_
 
+#include <linux/types.h>
+
 struct intel_gvt;
 struct intel_vgpu;
 
diff --git a/drivers/gpu/drm/i915/gvt/page_track.h b/drivers/gpu/drm/i915/gvt/page_track.h
index fa607a71c3c0..f6eb7135583c 100644
--- a/drivers/gpu/drm/i915/gvt/page_track.h
+++ b/drivers/gpu/drm/i915/gvt/page_track.h
@@ -25,6 +25,9 @@
 #ifndef _GVT_PAGE_TRACK_H_
 #define _GVT_PAGE_TRACK_H_
 
+#include <linux/types.h>
+
+struct intel_vgpu;
 struct intel_vgpu_page_track;
 
 typedef int (*gvt_page_track_handler_t)(
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.h b/drivers/gpu/drm/i915/gvt/sched_policy.h
index 7b59e3e88b8b..3dacdad5f529 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.h
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.h
@@ -34,6 +34,9 @@
 #ifndef __GVT_SCHED_POLICY__
 #define __GVT_SCHED_POLICY__
 
+struct intel_gvt;
+struct intel_vgpu;
+
 struct intel_gvt_sched_policy_ops {
 	int (*init)(struct intel_gvt *gvt);
 	void (*clean)(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 5b2a7d072ec9..685d1e04a5ff 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -35,12 +35,12 @@
 
 #include <linux/kthread.h>
 
-#include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_context.h"
 #include "gt/intel_ring.h"
 
 #include "i915_drv.h"
+#include "i915_gem_gtt.h"
 #include "gvt.h"
 
 #define RING_CTX_OFF(x) \
@@ -59,7 +59,7 @@ static void set_context_pdp_root_pointer(
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 {
 	struct drm_i915_gem_object *ctx_obj =
-		workload->req->hw_context->state->obj;
+		workload->req->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -130,7 +130,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	struct intel_gvt *gvt = vgpu->gvt;
 	int ring_id = workload->ring_id;
 	struct drm_i915_gem_object *ctx_obj =
-		workload->req->hw_context->state->obj;
+		workload->req->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *dst;
@@ -205,9 +205,9 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	return 0;
 }
 
-static inline bool is_gvt_request(struct i915_request *req)
+static inline bool is_gvt_request(struct i915_request *rq)
 {
-	return i915_gem_context_force_single_submission(req->gem_context);
+	return intel_context_force_single_submission(rq->context);
 }
 
 static void save_ring_hw_state(struct intel_vgpu *vgpu, int ring_id)
@@ -307,7 +307,7 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	u32 *cs;
 	int err;
 
-	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->hw_context))
+	if (IS_GEN(req->i915, 9) && is_inhibit_context(req->context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/*
@@ -363,11 +363,10 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 }
 
 static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
-					  struct i915_gem_context *ctx)
+					  struct intel_context *ce)
 {
 	struct intel_vgpu_mm *mm = workload->shadow_mm;
-	struct i915_ppgtt *ppgtt =
-		i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx));
+	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ce->vm);
 	int i = 0;
 
 	if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
@@ -380,8 +379,6 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
 		}
 	}
-
-	i915_vm_put(&ppgtt->vm);
 }
 
 static int
@@ -529,7 +526,7 @@ static void update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 		container_of(wa_ctx, struct intel_vgpu_workload, wa_ctx);
 	struct i915_request *rq = workload->req;
 	struct execlist_ring_context *shadow_ring_context =
-		(struct execlist_ring_context *)rq->hw_context->lrc_reg_state;
+		(struct execlist_ring_context *)rq->context->lrc_reg_state;
 
 	shadow_ring_context->bb_per_ctx_ptr.val =
 		(shadow_ring_context->bb_per_ctx_ptr.val &
@@ -628,7 +625,7 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 
 	update_shadow_pdps(workload);
 
-	set_context_ppgtt_from_shadow(workload, s->shadow[ring]->gem_context);
+	set_context_ppgtt_from_shadow(workload, s->shadow[ring]);
 
 	ret = intel_vgpu_sync_oos_pages(workload->vgpu);
 	if (ret) {
@@ -787,7 +784,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 	struct i915_request *rq = workload->req;
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct drm_i915_gem_object *ctx_obj = rq->hw_context->state->obj;
+	struct drm_i915_gem_object *ctx_obj = rq->context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *src;
@@ -1223,18 +1220,14 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	struct drm_i915_private *i915 = vgpu->gvt->dev_priv;
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
 	struct i915_ppgtt *ppgtt;
 	enum intel_engine_id i;
 	int ret;
 
-	ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MAX);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
+	ppgtt = i915_ppgtt_create(&i915->gt);
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
-	i915_gem_context_set_force_single_submission(ctx);
-
-	ppgtt = i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx));
 	i915_context_ppgtt_root_save(s, ppgtt);
 
 	for_each_engine(engine, i915, i) {
@@ -1243,12 +1236,16 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 		INIT_LIST_HEAD(&s->workload_q_head[i]);
 		s->shadow[i] = ERR_PTR(-EINVAL);
 
-		ce = intel_context_create(ctx, engine);
+		ce = intel_context_create(engine);
 		if (IS_ERR(ce)) {
 			ret = PTR_ERR(ce);
 			goto out_shadow_ctx;
 		}
 
+		i915_vm_put(ce->vm);
+		ce->vm = i915_vm_get(&ppgtt->vm);
+		intel_context_set_single_submission(ce);
+
 		if (!USES_GUC_SUBMISSION(i915)) { /* Max ring buffer size */
 			const unsigned int ring_size = 512 * SZ_4K;
 
@@ -1281,7 +1278,6 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	bitmap_zero(s->tlb_handle_pending, I915_NUM_ENGINES);
 
 	i915_vm_put(&ppgtt->vm);
-	i915_gem_context_put(ctx);
 	return 0;
 
 out_shadow_ctx:
@@ -1294,7 +1290,6 @@ out_shadow_ctx:
 		intel_context_put(s->shadow[i]);
 	}
 	i915_vm_put(&ppgtt->vm);
-	i915_gem_context_put(ctx);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index a19e7d89bc8a..f3da5c06f331 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -6,6 +6,7 @@
 
 #include <linux/debugobjects.h>
 
+#include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_ring.h"
 
@@ -91,10 +92,9 @@ static void debug_active_init(struct i915_active *ref)
 
 static void debug_active_activate(struct i915_active *ref)
 {
-	spin_lock_irq(&ref->tree_lock);
+	lockdep_assert_held(&ref->tree_lock);
 	if (!atomic_read(&ref->count)) /* before the first inc */
 		debug_object_activate(ref, &active_debug_desc);
-	spin_unlock_irq(&ref->tree_lock);
 }
 
 static void debug_active_deactivate(struct i915_active *ref)
@@ -186,18 +186,33 @@ active_retire(struct i915_active *ref)
 	__active_retire(ref);
 }
 
+static inline struct dma_fence **
+__active_fence_slot(struct i915_active_fence *active)
+{
+	return (struct dma_fence ** __force)&active->fence;
+}
+
+static inline bool
+active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct i915_active_fence *active =
+		container_of(cb, typeof(*active), cb);
+
+	return cmpxchg(__active_fence_slot(active), fence, NULL) == fence;
+}
+
 static void
 node_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	i915_active_fence_cb(fence, cb);
-	active_retire(container_of(cb, struct active_node, base.cb)->ref);
+	if (active_fence_cb(fence, cb))
+		active_retire(container_of(cb, struct active_node, base.cb)->ref);
 }
 
 static void
 excl_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	i915_active_fence_cb(fence, cb);
-	active_retire(container_of(cb, struct i915_active, excl.cb));
+	if (active_fence_cb(fence, cb))
+		active_retire(container_of(cb, struct i915_active, excl.cb));
 }
 
 static struct i915_active_fence *
@@ -244,7 +259,7 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	}
 
 	node = prealloc;
-	__i915_active_fence_init(&node->base, &tl->mutex, NULL, node_retire);
+	__i915_active_fence_init(&node->base, NULL, node_retire);
 	node->ref = ref;
 	node->timeline = idx;
 
@@ -262,7 +277,8 @@ out:
 void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
-			struct lock_class_key *key)
+			struct lock_class_key *mkey,
+			struct lock_class_key *wkey)
 {
 	unsigned long bits;
 
@@ -280,9 +296,12 @@ void __i915_active_init(struct i915_active *ref,
 
 	init_llist_head(&ref->preallocated_barriers);
 	atomic_set(&ref->count, 0);
-	__mutex_init(&ref->mutex, "i915_active", key);
-	__i915_active_fence_init(&ref->excl, &ref->mutex, NULL, excl_retire);
+	__mutex_init(&ref->mutex, "i915_active", mkey);
+	__i915_active_fence_init(&ref->excl, NULL, excl_retire);
 	INIT_WORK(&ref->work, active_work);
+#if IS_ENABLED(CONFIG_LOCKDEP)
+	lockdep_init_map(&ref->work.lockdep_map, "i915_active.work", wkey, 0);
+#endif
 }
 
 static bool ____active_del_barrier(struct i915_active *ref,
@@ -376,15 +395,8 @@ void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
 	/* We expect the caller to manage the exclusive timeline ordering */
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
-	/*
-	 * As we don't know which mutex the caller is using, we told a small
-	 * lie to the debug code that it is using the i915_active.mutex;
-	 * and now we must stick to that lie.
-	 */
-	mutex_acquire(&ref->mutex.dep_map, 0, 0, _THIS_IP_);
 	if (!__i915_active_fence_set(&ref->excl, f))
 		atomic_inc(&ref->count);
-	mutex_release(&ref->mutex.dep_map, _THIS_IP_);
 }
 
 bool i915_active_acquire_if_busy(struct i915_active *ref)
@@ -407,8 +419,10 @@ int i915_active_acquire(struct i915_active *ref)
 	if (!atomic_read(&ref->count) && ref->active)
 		err = ref->active(ref);
 	if (!err) {
+		spin_lock_irq(&ref->tree_lock); /* vs __active_retire() */
 		debug_active_activate(ref);
 		atomic_inc(&ref->count);
+		spin_unlock_irq(&ref->tree_lock);
 	}
 
 	mutex_unlock(&ref->mutex);
@@ -461,6 +475,7 @@ int i915_active_wait(struct i915_active *ref)
 	if (wait_var_event_interruptible(ref, i915_active_is_idle(ref)))
 		return -EINTR;
 
+	flush_work(&ref->work);
 	return 0;
 }
 
@@ -590,12 +605,15 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine)
 {
 	intel_engine_mask_t tmp, mask = engine->mask;
+	struct llist_node *pos = NULL, *next;
 	struct intel_gt *gt = engine->gt;
-	struct llist_node *pos, *next;
 	int err;
 
 	GEM_BUG_ON(i915_active_is_idle(ref));
-	GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers));
+
+	/* Wait until the previous preallocation is completed */
+	while (!llist_empty(&ref->preallocated_barriers))
+		cond_resched();
 
 	/*
 	 * Preallocate a node for each physical engine supporting the target
@@ -615,10 +633,6 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 				goto unwind;
 			}
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-			node->base.lock =
-				&engine->kernel_context->timeline->mutex;
-#endif
 			RCU_INIT_POINTER(node->base.fence, NULL);
 			node->base.cb.func = node_retire;
 			node->timeline = idx;
@@ -639,18 +653,27 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			node->base.cb.node.prev = (void *)engine;
 			atomic_inc(&ref->count);
 		}
+		GEM_BUG_ON(rcu_access_pointer(node->base.fence) != ERR_PTR(-EAGAIN));
 
 		GEM_BUG_ON(barrier_to_engine(node) != engine);
-		llist_add(barrier_to_ll(node), &ref->preallocated_barriers);
+		next = barrier_to_ll(node);
+		next->next = pos;
+		if (!pos)
+			pos = next;
 		intel_engine_pm_get(engine);
 	}
 
+	GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers));
+	llist_add_batch(next, pos, &ref->preallocated_barriers);
+
 	return 0;
 
 unwind:
-	llist_for_each_safe(pos, next, take_preallocated_barriers(ref)) {
+	while (pos) {
 		struct active_node *node = barrier_from_ll(pos);
 
+		pos = pos->next;
+
 		atomic_dec(&ref->count);
 		intel_engine_pm_put(barrier_to_engine(node));
 
@@ -702,12 +725,18 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 	}
 }
 
+static struct dma_fence **ll_to_fence_slot(struct llist_node *node)
+{
+	return __active_fence_slot(&barrier_from_ll(node)->base);
+}
+
 void i915_request_add_active_barriers(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
 	struct llist_node *node, *next;
 	unsigned long flags;
 
+	GEM_BUG_ON(!intel_context_is_barrier(rq->context));
 	GEM_BUG_ON(intel_engine_is_virtual(engine));
 	GEM_BUG_ON(i915_request_timeline(rq) != engine->kernel_context->timeline);
 
@@ -721,19 +750,13 @@ void i915_request_add_active_barriers(struct i915_request *rq)
 	 */
 	spin_lock_irqsave(&rq->lock, flags);
 	llist_for_each_safe(node, next, node) {
-		RCU_INIT_POINTER(barrier_from_ll(node)->base.fence, &rq->fence);
-		smp_wmb(); /* serialise with reuse_idle_barrier */
+		/* serialise with reuse_idle_barrier */
+		smp_store_mb(*ll_to_fence_slot(node), &rq->fence);
 		list_add_tail((struct list_head *)node, &rq->fence.cb_list);
 	}
 	spin_unlock_irqrestore(&rq->lock, flags);
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-#define active_is_held(active) lockdep_is_held((active)->lock)
-#else
-#define active_is_held(active) true
-#endif
-
 /*
  * __i915_active_fence_set: Update the last active fence along its timeline
  * @active: the active tracker
@@ -744,7 +767,7 @@ void i915_request_add_active_barriers(struct i915_request *rq)
  * fence onto this one. Returns the previous fence (if not already completed),
  * which the caller must ensure is executed before the new fence. To ensure
  * that the order of fences within the timeline of the i915_active_fence is
- * maintained, it must be locked by the caller.
+ * understood, it should be locked by the caller.
  */
 struct dma_fence *
 __i915_active_fence_set(struct i915_active_fence *active,
@@ -753,34 +776,41 @@ __i915_active_fence_set(struct i915_active_fence *active,
 	struct dma_fence *prev;
 	unsigned long flags;
 
-	/* NB: must be serialised by an outer timeline mutex (active->lock) */
-	spin_lock_irqsave(fence->lock, flags);
+	if (fence == rcu_access_pointer(active->fence))
+		return fence;
+
 	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags));
 
-	prev = rcu_dereference_protected(active->fence, active_is_held(active));
+	/*
+	 * Consider that we have two threads arriving (A and B), with
+	 * C already resident as the active->fence.
+	 *
+	 * A does the xchg first, and so it sees C or NULL depending
+	 * on the timing of the interrupt handler. If it is NULL, the
+	 * previous fence must have been signaled and we know that
+	 * we are first on the timeline. If it is still present,
+	 * we acquire the lock on that fence and serialise with the interrupt
+	 * handler, in the process removing it from any future interrupt
+	 * callback. A will then wait on C before executing (if present).
+	 *
+	 * As B is second, it sees A as the previous fence and so waits for
+	 * it to complete its transition and takes over the occupancy for
+	 * itself -- remembering that it needs to wait on A before executing.
+	 *
+	 * Note the strong ordering of the timeline also provides consistent
+	 * nesting rules for the fence->lock; the inner lock is always the
+	 * older lock.
+	 */
+	spin_lock_irqsave(fence->lock, flags);
+	prev = xchg(__active_fence_slot(active), fence);
 	if (prev) {
 		GEM_BUG_ON(prev == fence);
 		spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
 		__list_del_entry(&active->cb.node);
 		spin_unlock(prev->lock); /* serialise with prev->cb_list */
-
-		/*
-		 * active->fence is reset by the callback from inside
-		 * interrupt context. We need to serialise our list
-		 * manipulation with the fence->lock to prevent the prev
-		 * being lost inside an interrupt (it can't be replaced as
-		 * no other caller is allowed to enter __i915_active_fence_set
-		 * as we hold the timeline lock). After serialising with
-		 * the callback, we need to double check which ran first,
-		 * our list_del() [decoupling prev from the callback] or
-		 * the callback...
-		 */
-		prev = rcu_access_pointer(active->fence);
 	}
-
-	rcu_assign_pointer(active->fence, fence);
+	GEM_BUG_ON(rcu_access_pointer(active->fence) != fence);
 	list_add_tail(&active->cb.node, &fence->cb_list);
-
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	return prev;
@@ -792,10 +822,6 @@ int i915_active_fence_set(struct i915_active_fence *active,
 	struct dma_fence *fence;
 	int err = 0;
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	lockdep_assert_held(active->lock);
-#endif
-
 	/* Must maintain timeline ordering wrt previous active requests */
 	rcu_read_lock();
 	fence = __i915_active_fence_set(active, &rq->fence);
@@ -812,7 +838,7 @@ int i915_active_fence_set(struct i915_active_fence *active,
 
 void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	i915_active_fence_cb(fence, cb);
+	active_fence_cb(fence, cb);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 44859356ce97..b571f675c795 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -61,19 +61,15 @@ void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb);
  */
 static inline void
 __i915_active_fence_init(struct i915_active_fence *active,
-			 struct mutex *lock,
 			 void *fence,
 			 dma_fence_func_t fn)
 {
 	RCU_INIT_POINTER(active->fence, fence);
 	active->cb.func = fn ?: i915_active_noop;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	active->lock = lock;
-#endif
 }
 
-#define INIT_ACTIVE_FENCE(A, LOCK) \
-	__i915_active_fence_init((A), (LOCK), NULL, NULL)
+#define INIT_ACTIVE_FENCE(A) \
+	__i915_active_fence_init((A), NULL, NULL)
 
 struct dma_fence *
 __i915_active_fence_set(struct i915_active_fence *active,
@@ -127,15 +123,6 @@ i915_active_fence_isset(const struct i915_active_fence *active)
 	return rcu_access_pointer(active->fence);
 }
 
-static inline void
-i915_active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
-{
-	struct i915_active_fence *active =
-		container_of(cb, typeof(*active), cb);
-
-	RCU_INIT_POINTER(active->fence, NULL);
-}
-
 /*
  * GPU activity tracking
  *
@@ -165,11 +152,15 @@ i915_active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
-			struct lock_class_key *key);
+			struct lock_class_key *mkey,
+			struct lock_class_key *wkey);
+
+/* Specialise each class of i915_active to avoid impossible lockdep cycles. */
 #define i915_active_init(ref, active, retire) do {		\
-	static struct lock_class_key __key;				\
+	static struct lock_class_key __mkey;				\
+	static struct lock_class_key __wkey;				\
 									\
-	__i915_active_init(ref, active, retire, &__key);		\
+	__i915_active_init(ref, active, retire, &__mkey, &__wkey);	\
 } while (0)
 
 int i915_active_ref(struct i915_active *ref,
@@ -215,5 +206,6 @@ void i915_active_acquire_barrier(struct i915_active *ref);
 void i915_request_add_active_barriers(struct i915_request *rq);
 
 void i915_active_print(struct i915_active *ref, struct drm_printer *m);
+void i915_active_unlock_wait(struct i915_active *ref);
 
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 96aed0ee700a..6360c3e4b765 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -20,21 +20,6 @@
 struct i915_active_fence {
 	struct dma_fence __rcu *fence;
 	struct dma_fence_cb cb;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	/*
-	 * Incorporeal!
-	 *
-	 * Updates to the i915_active_request must be serialised under a lock
-	 * to ensure that the timeline is ordered. Normally, this is the
-	 * timeline->mutex, but another mutex may be used so long as it is
-	 * done so consistently.
-	 *
-	 * For lockdep tracking of the above, we store the lock we intend
-	 * to always use for updates of this i915_active_request during
-	 * construction and assert that is held on every update.
-	 */
-	struct mutex *lock;
-#endif
 };
 
 struct active_node;
diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c
index e9d4200ce3bc..66883af64ca1 100644
--- a/drivers/gpu/drm/i915/i915_buddy.c
+++ b/drivers/gpu/drm/i915/i915_buddy.c
@@ -262,8 +262,10 @@ void i915_buddy_free_list(struct i915_buddy_mm *mm, struct list_head *objects)
 {
 	struct i915_buddy_block *block, *on;
 
-	list_for_each_entry_safe(block, on, objects, link)
+	list_for_each_entry_safe(block, on, objects, link) {
 		i915_buddy_free(mm, block);
+		cond_resched();
+	}
 	INIT_LIST_HEAD(objects);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index f24096e27bef..a0e437aa65b7 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -235,7 +235,7 @@ static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
 	/*
 	 * MI_BATCH_BUFFER_START requires some special handling. It's not
 	 * really a 'skip' action but it doesn't seem like it's worth adding
-	 * a new action. See i915_parse_cmds().
+	 * a new action. See intel_engine_cmd_parser().
 	 */
 	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
 };
@@ -731,7 +731,7 @@ static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
 			return 0xFF;
 	}
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal rcs cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal rcs cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -754,7 +754,7 @@ static u32 gen7_bsd_get_cmd_length_mask(u32 cmd_header)
 			return 0xFF;
 	}
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal bsd cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal bsd cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -767,7 +767,7 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	else if (client == INSTR_BC_CLIENT)
 		return 0xFF;
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -778,7 +778,7 @@ static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
 	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
 		return 0xFF;
 
-	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	DRM_DEBUG("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
 	return 0;
 }
 
@@ -1127,79 +1127,71 @@ find_reg(const struct intel_engine_cs *engine, u32 addr)
 /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
 static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		       struct drm_i915_gem_object *src_obj,
-		       u32 batch_start_offset,
-		       u32 batch_len,
-		       bool *needs_clflush_after)
+		       u32 offset, u32 length)
 {
-	unsigned int src_needs_clflush;
-	unsigned int dst_needs_clflush;
+	bool needs_clflush;
 	void *dst, *src;
 	int ret;
 
-	ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
-	if (ret)
-		return ERR_PTR(ret);
-
 	dst = i915_gem_object_pin_map(dst_obj, I915_MAP_FORCE_WB);
-	i915_gem_object_finish_access(dst_obj);
 	if (IS_ERR(dst))
 		return dst;
 
-	ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
+	ret = i915_gem_object_pin_pages(src_obj);
 	if (ret) {
 		i915_gem_object_unpin_map(dst_obj);
 		return ERR_PTR(ret);
 	}
 
+	needs_clflush =
+		!(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
+
 	src = ERR_PTR(-ENODEV);
-	if (src_needs_clflush &&
-	    i915_can_memcpy_from_wc(NULL, batch_start_offset, 0)) {
+	if (needs_clflush && i915_has_memcpy_from_wc()) {
 		src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
 		if (!IS_ERR(src)) {
-			i915_memcpy_from_wc(dst,
-					    src + batch_start_offset,
-					    ALIGN(batch_len, 16));
+			i915_unaligned_memcpy_from_wc(dst,
+						      src + offset,
+						      length);
 			i915_gem_object_unpin_map(src_obj);
 		}
 	}
 	if (IS_ERR(src)) {
 		void *ptr;
-		int offset, n;
+		int x, n;
 
-		offset = offset_in_page(batch_start_offset);
-
-		/* We can avoid clflushing partial cachelines before the write
+		/*
+		 * We can avoid clflushing partial cachelines before the write
 		 * if we only every write full cache-lines. Since we know that
 		 * both the source and destination are in multiples of
 		 * PAGE_SIZE, we can simply round up to the next cacheline.
 		 * We don't care about copying too much here as we only
 		 * validate up to the end of the batch.
 		 */
-		if (dst_needs_clflush & CLFLUSH_BEFORE)
-			batch_len = roundup(batch_len,
-					    boot_cpu_data.x86_clflush_size);
+		if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+			length = round_up(length,
+					  boot_cpu_data.x86_clflush_size);
 
 		ptr = dst;
-		for (n = batch_start_offset >> PAGE_SHIFT; batch_len; n++) {
-			int len = min_t(int, batch_len, PAGE_SIZE - offset);
+		x = offset_in_page(offset);
+		for (n = offset >> PAGE_SHIFT; length; n++) {
+			int len = min_t(int, length, PAGE_SIZE - x);
 
 			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
-			if (src_needs_clflush)
-				drm_clflush_virt_range(src + offset, len);
-			memcpy(ptr, src + offset, len);
+			if (needs_clflush)
+				drm_clflush_virt_range(src + x, len);
+			memcpy(ptr, src + x, len);
 			kunmap_atomic(src);
 
 			ptr += len;
-			batch_len -= len;
-			offset = 0;
+			length -= len;
+			x = 0;
 		}
 	}
 
-	i915_gem_object_finish_access(src_obj);
+	i915_gem_object_unpin_pages(src_obj);
 
 	/* dst_obj is returned with vmap pinned */
-	*needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER;
-
 	return dst;
 }
 
@@ -1211,7 +1203,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		return true;
 
 	if (desc->flags & CMD_DESC_REJECT) {
-		DRM_DEBUG_DRIVER("CMD: Rejected command: 0x%08X\n", *cmd);
+		DRM_DEBUG("CMD: Rejected command: 0x%08X\n", *cmd);
 		return false;
 	}
 
@@ -1231,8 +1223,8 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 				find_reg(engine, reg_addr);
 
 			if (!reg) {
-				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
-						 reg_addr, *cmd, engine->name);
+				DRM_DEBUG("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
+					  reg_addr, *cmd, engine->name);
 				return false;
 			}
 
@@ -1242,22 +1234,22 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 			 */
 			if (reg->mask) {
 				if (desc->cmd.value == MI_LOAD_REGISTER_MEM) {
-					DRM_DEBUG_DRIVER("CMD: Rejected LRM to masked register 0x%08X\n",
-							 reg_addr);
+					DRM_DEBUG("CMD: Rejected LRM to masked register 0x%08X\n",
+						  reg_addr);
 					return false;
 				}
 
 				if (desc->cmd.value == MI_LOAD_REGISTER_REG) {
-					DRM_DEBUG_DRIVER("CMD: Rejected LRR to masked register 0x%08X\n",
-							 reg_addr);
+					DRM_DEBUG("CMD: Rejected LRR to masked register 0x%08X\n",
+						  reg_addr);
 					return false;
 				}
 
 				if (desc->cmd.value == MI_LOAD_REGISTER_IMM(1) &&
 				    (offset + 2 > length ||
 				     (cmd[offset + 1] & reg->mask) != reg->value)) {
-					DRM_DEBUG_DRIVER("CMD: Rejected LRI to masked register 0x%08X\n",
-							 reg_addr);
+					DRM_DEBUG("CMD: Rejected LRI to masked register 0x%08X\n",
+						  reg_addr);
 					return false;
 				}
 			}
@@ -1284,8 +1276,8 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 			}
 
 			if (desc->bits[i].offset >= length) {
-				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
-						 *cmd, engine->name);
+				DRM_DEBUG("CMD: Rejected command 0x%08X, too short to check bitmask (%s)\n",
+					  *cmd, engine->name);
 				return false;
 			}
 
@@ -1293,11 +1285,11 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 				desc->bits[i].mask;
 
 			if (dword != desc->bits[i].expected) {
-				DRM_DEBUG_DRIVER("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (%s)\n",
-						 *cmd,
-						 desc->bits[i].mask,
-						 desc->bits[i].expected,
-						 dword, engine->name);
+				DRM_DEBUG("CMD: Rejected command 0x%08X for bitmask 0x%08X (exp=0x%08X act=0x%08X) (%s)\n",
+					  *cmd,
+					  desc->bits[i].mask,
+					  desc->bits[i].expected,
+					  dword, engine->name);
 				return false;
 			}
 		}
@@ -1306,17 +1298,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 	return true;
 }
 
-static int check_bbstart(const struct i915_gem_context *ctx,
-			 u32 *cmd, u32 offset, u32 length,
-			 u32 batch_len,
-			 u64 batch_start,
-			 u64 shadow_batch_start)
+static int check_bbstart(u32 *cmd, u32 offset, u32 length,
+			 u32 batch_length,
+			 u64 batch_addr,
+			 u64 shadow_addr,
+			 const unsigned long *jump_whitelist)
 {
 	u64 jump_offset, jump_target;
 	u32 target_cmd_offset, target_cmd_index;
 
 	/* For igt compatibility on older platforms */
-	if (CMDPARSER_USES_GGTT(ctx->i915)) {
+	if (!jump_whitelist) {
 		DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
 		return -EACCES;
 	}
@@ -1327,14 +1319,14 @@ static int check_bbstart(const struct i915_gem_context *ctx,
 		return -EINVAL;
 	}
 
-	jump_target = *(u64*)(cmd+1);
-	jump_offset = jump_target - batch_start;
+	jump_target = *(u64 *)(cmd + 1);
+	jump_offset = jump_target - batch_addr;
 
 	/*
 	 * Any underflow of jump_target is guaranteed to be outside the range
 	 * of a u32, so >= test catches both too large and too small
 	 */
-	if (jump_offset >= batch_len) {
+	if (jump_offset >= batch_length) {
 		DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
 			  jump_target);
 		return -EINVAL;
@@ -1342,20 +1334,20 @@ static int check_bbstart(const struct i915_gem_context *ctx,
 
 	/*
 	 * This cannot overflow a u32 because we already checked jump_offset
-	 * is within the BB, and the batch_len is a u32
+	 * is within the BB, and the batch_length is a u32
 	 */
 	target_cmd_offset = lower_32_bits(jump_offset);
 	target_cmd_index = target_cmd_offset / sizeof(u32);
 
-	*(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
+	*(u64 *)(cmd + 1) = shadow_addr + target_cmd_offset;
 
 	if (target_cmd_index == offset)
 		return 0;
 
-	if (ctx->jump_whitelist_cmds <= target_cmd_index) {
-		DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
-		return -EINVAL;
-	} else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+	if (IS_ERR(jump_whitelist))
+		return PTR_ERR(jump_whitelist);
+
+	if (!test_bit(target_cmd_index, jump_whitelist)) {
 		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
 			  jump_target);
 		return -EINVAL;
@@ -1364,54 +1356,40 @@ static int check_bbstart(const struct i915_gem_context *ctx,
 	return 0;
 }
 
-static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+static unsigned long *alloc_whitelist(u32 batch_length)
 {
-	const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
-	const u32 exact_size = BITS_TO_LONGS(batch_cmds);
-	u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
-	unsigned long *next_whitelist;
+	unsigned long *jmp;
 
-	if (CMDPARSER_USES_GGTT(ctx->i915))
-		return;
-
-	if (batch_cmds <= ctx->jump_whitelist_cmds) {
-		bitmap_zero(ctx->jump_whitelist, batch_cmds);
-		return;
-	}
-
-again:
-	next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
-	if (next_whitelist) {
-		kfree(ctx->jump_whitelist);
-		ctx->jump_whitelist = next_whitelist;
-		ctx->jump_whitelist_cmds =
-			next_size * BITS_PER_BYTE * sizeof(long);
-		return;
-	}
-
-	if (next_size > exact_size) {
-		next_size = exact_size;
-		goto again;
-	}
+	/*
+	 * We expect batch_length to be less than 256KiB for known users,
+	 * i.e. we need at most an 8KiB bitmap allocation which should be
+	 * reasonably cheap due to kmalloc caches.
+	 */
 
-	DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
-	bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+	/* Prefer to report transient allocation failure rather than hit oom */
+	jmp = bitmap_zalloc(DIV_ROUND_UP(batch_length, sizeof(u32)),
+			    GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+	if (!jmp)
+		return ERR_PTR(-ENOMEM);
 
-	return;
+	return jmp;
 }
 
 #define LENGTH_BIAS 2
 
+static bool shadow_needs_clflush(struct drm_i915_gem_object *obj)
+{
+	return !(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE);
+}
+
 /**
- * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
- * @ctx: the context in which the batch is to execute
+ * intel_engine_cmd_parser() - parse a batch buffer for privilege violations
  * @engine: the engine on which the batch is to execute
- * @batch_obj: the batch buffer in question
- * @batch_start: Canonical base address of batch
- * @batch_start_offset: byte offset in the batch at which execution starts
- * @batch_len: length of the commands in batch_obj
- * @shadow_batch_obj: copy of the batch buffer in question
- * @shadow_batch_start: Canonical base address of shadow_batch_obj
+ * @batch: the batch buffer in question
+ * @batch_offset: byte offset in the batch at which execution starts
+ * @batch_length: length of the commands in batch_obj
+ * @shadow: validated copy of the batch buffer in question
+ * @trampoline: whether to emit a conditional trampoline at the end of the batch
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1419,38 +1397,46 @@ again:
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
-
-int intel_engine_cmd_parser(struct i915_gem_context *ctx,
-			    struct intel_engine_cs *engine,
-			    struct drm_i915_gem_object *batch_obj,
-			    u64 batch_start,
-			    u32 batch_start_offset,
-			    u32 batch_len,
-			    struct drm_i915_gem_object *shadow_batch_obj,
-			    u64 shadow_batch_start)
+int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+			    struct i915_vma *batch,
+			    u32 batch_offset,
+			    u32 batch_length,
+			    struct i915_vma *shadow,
+			    bool trampoline)
 {
 	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
-	bool needs_clflush_after = false;
+	unsigned long *jump_whitelist;
+	u64 batch_addr, shadow_addr;
 	int ret = 0;
 
-	cmd = copy_batch(shadow_batch_obj, batch_obj,
-			 batch_start_offset, batch_len,
-			 &needs_clflush_after);
+	GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
+	GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
+	GEM_BUG_ON(range_overflows_t(u64, batch_offset, batch_length,
+				     batch->size));
+	GEM_BUG_ON(!batch_length);
+
+	cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length);
 	if (IS_ERR(cmd)) {
-		DRM_DEBUG_DRIVER("CMD: Failed to copy batch\n");
+		DRM_DEBUG("CMD: Failed to copy batch\n");
 		return PTR_ERR(cmd);
 	}
 
-	init_whitelist(ctx, batch_len);
+	jump_whitelist = NULL;
+	if (!trampoline)
+		/* Defer failure until attempted use */
+		jump_whitelist = alloc_whitelist(batch_length);
+
+	shadow_addr = gen8_canonical_addr(shadow->node.start);
+	batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
 
 	/*
 	 * We use the batch length as size because the shadow object is as
 	 * large or larger and copy_batch() will write MI_NOPs to the extra
 	 * space. Parsing should be faster in some cases this way.
 	 */
-	batch_end = cmd + (batch_len / sizeof(*batch_end));
+	batch_end = cmd + batch_length / sizeof(*batch_end);
 	do {
 		u32 length;
 
@@ -1459,61 +1445,99 @@ int intel_engine_cmd_parser(struct i915_gem_context *ctx,
 
 		desc = find_cmd(engine, *cmd, desc, &default_desc);
 		if (!desc) {
-			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
-					 *cmd);
+			DRM_DEBUG("CMD: Unrecognized command: 0x%08X\n", *cmd);
 			ret = -EINVAL;
-			goto err;
+			break;
 		}
 
 		if (desc->flags & CMD_DESC_FIXED)
 			length = desc->length.fixed;
 		else
-			length = ((*cmd & desc->length.mask) + LENGTH_BIAS);
+			length = (*cmd & desc->length.mask) + LENGTH_BIAS;
 
 		if ((batch_end - cmd) < length) {
-			DRM_DEBUG_DRIVER("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
-					 *cmd,
-					 length,
-					 batch_end - cmd);
+			DRM_DEBUG("CMD: Command length exceeds batch length: 0x%08X length=%u batchlen=%td\n",
+				  *cmd,
+				  length,
+				  batch_end - cmd);
 			ret = -EINVAL;
-			goto err;
+			break;
 		}
 
 		if (!check_cmd(engine, desc, cmd, length)) {
 			ret = -EACCES;
-			goto err;
+			break;
 		}
 
 		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
-			ret = check_bbstart(ctx, cmd, offset, length,
-					    batch_len, batch_start,
-					    shadow_batch_start);
-
-			if (ret)
-				goto err;
+			ret = check_bbstart(cmd, offset, length, batch_length,
+					    batch_addr, shadow_addr,
+					    jump_whitelist);
 			break;
 		}
 
-		if (ctx->jump_whitelist_cmds > offset)
-			set_bit(offset, ctx->jump_whitelist);
+		if (!IS_ERR_OR_NULL(jump_whitelist))
+			__set_bit(offset, jump_whitelist);
 
 		cmd += length;
 		offset += length;
 		if  (cmd >= batch_end) {
-			DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
+			DRM_DEBUG("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
 			ret = -EINVAL;
-			goto err;
+			break;
 		}
 	} while (1);
 
-	if (needs_clflush_after) {
-		void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
+	if (trampoline) {
+		/*
+		 * With the trampoline, the shadow is executed twice.
+		 *
+		 *   1 - starting at offset 0, in privileged mode
+		 *   2 - starting at offset batch_len, as non-privileged
+		 *
+		 * Only if the batch is valid and safe to execute, do we
+		 * allow the first privileged execution to proceed. If not,
+		 * we terminate the first batch and use the second batchbuffer
+		 * entry to chain to the original unsafe non-privileged batch,
+		 * leaving it to the HW to validate.
+		 */
+		*batch_end = MI_BATCH_BUFFER_END;
+
+		if (ret) {
+			/* Batch unsafe to execute with privileges, cancel! */
+			cmd = page_mask_bits(shadow->obj->mm.mapping);
+			*cmd = MI_BATCH_BUFFER_END;
+
+			/* If batch is unsafe but valid, jump to the original */
+			if (ret == -EACCES) {
+				unsigned int flags;
+
+				flags = MI_BATCH_NON_SECURE_I965;
+				if (IS_HASWELL(engine->i915))
+					flags = MI_BATCH_NON_SECURE_HSW;
+
+				GEM_BUG_ON(!IS_GEN_RANGE(engine->i915, 6, 7));
+				__gen6_emit_bb_start(batch_end,
+						     batch_addr,
+						     flags);
+
+				ret = 0; /* allow execution */
+			}
+		}
+
+		if (shadow_needs_clflush(shadow->obj))
+			drm_clflush_virt_range(batch_end, 8);
+	}
+
+	if (shadow_needs_clflush(shadow->obj)) {
+		void *ptr = page_mask_bits(shadow->obj->mm.mapping);
 
 		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
 	}
 
-err:
-	i915_gem_object_unpin_map(shadow_batch_obj);
+	if (!IS_ERR_OR_NULL(jump_whitelist))
+		kfree(jump_whitelist);
+	i915_gem_object_unpin_map(shadow->obj);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 8016484ebcd3..d5a9b8a964c2 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -61,24 +61,14 @@ static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node)
 
 static int i915_capabilities(struct seq_file *m, void *data)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	const struct intel_device_info *info = INTEL_INFO(dev_priv);
+	struct drm_i915_private *i915 = node_to_i915(m->private);
 	struct drm_printer p = drm_seq_file_printer(m);
-	const char *msg;
 
-	seq_printf(m, "gen: %d\n", INTEL_GEN(dev_priv));
-	seq_printf(m, "platform: %s\n", intel_platform_name(info->platform));
-	seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev_priv));
+	seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(i915));
 
-	msg = "n/a";
-#ifdef CONFIG_INTEL_IOMMU
-	msg = enableddisabled(intel_iommu_gfx_mapped);
-#endif
-	seq_printf(m, "iommu: %s\n", msg);
-
-	intel_device_info_dump_flags(info, &p);
-	intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p);
-	intel_driver_caps_print(&dev_priv->caps, &p);
+	intel_device_info_print_static(INTEL_INFO(i915), &p);
+	intel_device_info_print_runtime(RUNTIME_INFO(i915), &p);
+	intel_driver_caps_print(&i915->caps, &p);
 
 	kernel_param_lock(THIS_MODULE);
 	i915_params_dump(&i915_modparams, &p);
@@ -331,16 +321,15 @@ static void print_context_stats(struct seq_file *m,
 
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
-			intel_context_lock_pinned(ce);
-			if (intel_context_is_pinned(ce)) {
+			if (intel_context_pin_if_active(ce)) {
 				rcu_read_lock();
 				if (ce->state)
 					per_file_stats(0,
 						       ce->state->obj, &kstats);
 				per_file_stats(0, ce->ring->vma->obj, &kstats);
 				rcu_read_unlock();
+				intel_context_unpin(ce);
 			}
-			intel_context_unlock_pinned(ce);
 		}
 		i915_gem_context_unlock_engines(ctx);
 
@@ -377,12 +366,16 @@ static void print_context_stats(struct seq_file *m,
 static int i915_gem_object_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
+	struct intel_memory_region *mr;
+	enum intel_region_id id;
 
 	seq_printf(m, "%u shrinkable [%u free] objects, %llu bytes\n",
 		   i915->mm.shrink_count,
 		   atomic_read(&i915->mm.free_count),
 		   i915->mm.shrink_memory);
-
+	for_each_memory_region(mr, i915, id)
+		seq_printf(m, "%s: total:%pa, available:%pa bytes\n",
+			   mr->name, &mr->total, &mr->avail);
 	seq_putc(m, '\n');
 
 	print_context_stats(m, i915);
@@ -692,7 +685,7 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 static ssize_t gpu_state_read(struct file *file, char __user *ubuf,
 			      size_t count, loff_t *pos)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 	ssize_t ret;
 	void *buf;
 
@@ -705,7 +698,7 @@ static ssize_t gpu_state_read(struct file *file, char __user *ubuf,
 	if (!buf)
 		return -ENOMEM;
 
-	ret = i915_gpu_state_copy_to_buffer(error, buf, *pos, count);
+	ret = i915_gpu_coredump_copy_to_buffer(error, buf, *pos, count);
 	if (ret <= 0)
 		goto out;
 
@@ -721,19 +714,19 @@ out:
 
 static int gpu_state_release(struct inode *inode, struct file *file)
 {
-	i915_gpu_state_put(file->private_data);
+	i915_gpu_coredump_put(file->private_data);
 	return 0;
 }
 
 static int i915_gpu_info_open(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *i915 = inode->i_private;
-	struct i915_gpu_state *gpu;
+	struct i915_gpu_coredump *gpu;
 	intel_wakeref_t wakeref;
 
 	gpu = NULL;
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		gpu = i915_capture_gpu_state(i915);
+		gpu = i915_gpu_coredump(i915);
 	if (IS_ERR(gpu))
 		return PTR_ERR(gpu);
 
@@ -755,7 +748,7 @@ i915_error_state_write(struct file *filp,
 		       size_t cnt,
 		       loff_t *ppos)
 {
-	struct i915_gpu_state *error = filp->private_data;
+	struct i915_gpu_coredump *error = filp->private_data;
 
 	if (!error)
 		return 0;
@@ -768,7 +761,7 @@ i915_error_state_write(struct file *filp,
 
 static int i915_error_state_open(struct inode *inode, struct file *file)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 
 	error = i915_first_error_state(inode->i_private);
 	if (IS_ERR(error))
@@ -891,7 +884,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
-		cagf = intel_gpu_freq(rps, intel_get_cagf(rps, rpstat));
+		cagf = intel_rps_read_actual_frequency(rps);
 
 		intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 
@@ -1011,7 +1004,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 	return ret;
 }
 
-static int ironlake_drpc_info(struct seq_file *m)
+static int ilk_drpc_info(struct seq_file *m)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
 	struct intel_uncore *uncore = &i915->uncore;
@@ -1219,7 +1212,7 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 		else if (INTEL_GEN(dev_priv) >= 6)
 			err = gen6_drpc_info(m);
 		else
-			err = ironlake_drpc_info(m);
+			err = ilk_drpc_info(m);
 	}
 
 	return err;
@@ -1519,15 +1512,14 @@ static int i915_context_status(struct seq_file *m, void *unused)
 
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
-			intel_context_lock_pinned(ce);
-			if (intel_context_is_pinned(ce)) {
+			if (intel_context_pin_if_active(ce)) {
 				seq_printf(m, "%s: ", ce->engine->name);
 				if (ce->state)
 					describe_obj(m, ce->state->obj);
 				describe_ctx_ring(m, ce->ring);
 				seq_putc(m, '\n');
+				intel_context_unpin(ce);
 			}
-			intel_context_unlock_pinned(ce);
 		}
 		i915_gem_context_unlock_engines(ctx);
 
@@ -1633,21 +1625,6 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_rps *rps = &dev_priv->gt.rps;
-	u32 act_freq = rps->cur_freq;
-	intel_wakeref_t wakeref;
-
-	with_intel_runtime_pm_if_in_use(&dev_priv->runtime_pm, wakeref) {
-		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-			vlv_punit_get(dev_priv);
-			act_freq = vlv_punit_read(dev_priv,
-						  PUNIT_REG_GPU_FREQ_STS);
-			vlv_punit_put(dev_priv);
-			act_freq = (act_freq >> 8) & 0xff;
-		} else {
-			act_freq = intel_get_cagf(rps,
-						  I915_READ(GEN6_RPSTAT1));
-		}
-	}
 
 	seq_printf(m, "RPS enabled? %d\n", rps->enabled);
 	seq_printf(m, "GPU busy? %s\n", yesno(dev_priv->gt.awake));
@@ -1656,7 +1633,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
 	seq_printf(m, "Frequency requested %d, actual %d\n",
 		   intel_gpu_freq(rps, rps->cur_freq),
-		   intel_gpu_freq(rps, act_freq));
+		   intel_rps_read_actual_frequency(rps));
 	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
 		   intel_gpu_freq(rps, rps->min_freq),
 		   intel_gpu_freq(rps, rps->min_freq_softlimit),
@@ -1802,30 +1779,12 @@ static void i915_guc_log_info(struct seq_file *m,
 static int i915_guc_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	const struct intel_guc *guc = &dev_priv->gt.uc.guc;
-	struct intel_guc_client *client = guc->execbuf_client;
 
 	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
 	i915_guc_log_info(m, dev_priv);
 
-	if (!USES_GUC_SUBMISSION(dev_priv))
-		return 0;
-
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	seq_printf(m, "\nDoorbell map:\n");
-	seq_printf(m, "\t%*pb\n", GUC_NUM_DOORBELLS, guc->doorbell_bitmap);
-	seq_printf(m, "Doorbell next cacheline: 0x%x\n", guc->db_cacheline);
-
-	seq_printf(m, "\nGuC execbuf client @ %p:\n", client);
-	seq_printf(m, "\tPriority %d, GuC stage index: %u, PD offset 0x%x\n",
-		   client->priority,
-		   client->stage_id,
-		   client->proc_desc_offset);
-	seq_printf(m, "\tDoorbell id %d, offset: 0x%lx\n",
-		   client->doorbell_id, client->doorbell_offset);
 	/* Add more as required ... */
 
 	return 0;
@@ -2020,7 +1979,7 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data)
 	struct drm_connector *connector = m->private;
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_dp *intel_dp =
-		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 	int ret;
 
 	if (!CAN_PSR(dev_priv)) {
@@ -2367,7 +2326,7 @@ out:
 }
 
 static void intel_seq_print_mode(struct seq_file *m, int tabs,
-				 struct drm_display_mode *mode)
+				 const struct drm_display_mode *mode)
 {
 	int i;
 
@@ -2378,59 +2337,35 @@ static void intel_seq_print_mode(struct seq_file *m, int tabs,
 }
 
 static void intel_encoder_info(struct seq_file *m,
-			       struct intel_crtc *intel_crtc,
-			       struct intel_encoder *intel_encoder)
+			       struct intel_crtc *crtc,
+			       struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct drm_crtc *crtc = &intel_crtc->base;
-	struct intel_connector *intel_connector;
-	struct drm_encoder *encoder;
-
-	encoder = &intel_encoder->base;
-	seq_printf(m, "\tencoder %d: type: %s, connectors:\n",
-		   encoder->base.id, encoder->name);
-	for_each_connector_on_encoder(dev, encoder, intel_connector) {
-		struct drm_connector *connector = &intel_connector->base;
-		seq_printf(m, "\t\tconnector %d: type: %s, status: %s",
-			   connector->base.id,
-			   connector->name,
-			   drm_get_connector_status_name(connector->status));
-		if (connector->status == connector_status_connected) {
-			struct drm_display_mode *mode = &crtc->mode;
-			seq_printf(m, ", mode:\n");
-			intel_seq_print_mode(m, 2, mode);
-		} else {
-			seq_putc(m, '\n');
-		}
-	}
-}
+	struct drm_connector_list_iter conn_iter;
+	struct drm_connector *connector;
 
-static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct drm_crtc *crtc = &intel_crtc->base;
-	struct intel_encoder *intel_encoder;
-	struct drm_plane_state *plane_state = crtc->primary->state;
-	struct drm_framebuffer *fb = plane_state->fb;
+	seq_printf(m, "\t[ENCODER:%d:%s]: connectors:\n",
+		   encoder->base.base.id, encoder->base.name);
 
-	if (fb)
-		seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
-			   fb->base.id, plane_state->src_x >> 16,
-			   plane_state->src_y >> 16, fb->width, fb->height);
-	else
-		seq_puts(m, "\tprimary plane disabled\n");
-	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
-		intel_encoder_info(m, intel_crtc, intel_encoder);
+	drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
+		const struct drm_connector_state *conn_state =
+			connector->state;
+
+		if (conn_state->best_encoder != &encoder->base)
+			continue;
+
+		seq_printf(m, "\t\t[CONNECTOR:%d:%s]\n",
+			   connector->base.id, connector->name);
+	}
+	drm_connector_list_iter_end(&conn_iter);
 }
 
 static void intel_panel_info(struct seq_file *m, struct intel_panel *panel)
 {
-	struct drm_display_mode *mode = panel->fixed_mode;
+	const struct drm_display_mode *mode = panel->fixed_mode;
 
-	seq_printf(m, "\tfixed mode:\n");
-	intel_seq_print_mode(m, 2, mode);
+	seq_printf(m, "\tfixed mode: " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode));
 }
 
 static void intel_hdcp_info(struct seq_file *m,
@@ -2456,7 +2391,7 @@ static void intel_dp_info(struct seq_file *m,
 			  struct intel_connector *intel_connector)
 {
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base);
+	struct intel_dp *intel_dp = enc_to_intel_dp(intel_encoder);
 
 	seq_printf(m, "\tDPCD rev: %x\n", intel_dp->dpcd[DP_DPCD_REV]);
 	seq_printf(m, "\taudio support: %s\n", yesno(intel_dp->has_audio));
@@ -2476,7 +2411,7 @@ static void intel_dp_mst_info(struct seq_file *m,
 {
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
 	struct intel_dp_mst_encoder *intel_mst =
-		enc_to_mst(&intel_encoder->base);
+		enc_to_mst(intel_encoder);
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	bool has_audio = drm_dp_mst_port_has_audio(&intel_dp->mst_mgr,
@@ -2489,7 +2424,7 @@ static void intel_hdmi_info(struct seq_file *m,
 			    struct intel_connector *intel_connector)
 {
 	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&intel_encoder->base);
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(intel_encoder);
 
 	seq_printf(m, "\taudio support: %s\n", yesno(intel_hdmi->has_audio));
 	if (intel_connector->hdcp.shim) {
@@ -2508,10 +2443,12 @@ static void intel_connector_info(struct seq_file *m,
 				 struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_encoder *intel_encoder = intel_connector->encoder;
-	struct drm_display_mode *mode;
+	const struct drm_connector_state *conn_state = connector->state;
+	struct intel_encoder *encoder =
+		to_intel_encoder(conn_state->best_encoder);
+	const struct drm_display_mode *mode;
 
-	seq_printf(m, "connector %d: type %s, status: %s\n",
+	seq_printf(m, "[CONNECTOR:%d:%s]: status: %s\n",
 		   connector->base.id, connector->name,
 		   drm_get_connector_status_name(connector->status));
 
@@ -2525,24 +2462,24 @@ static void intel_connector_info(struct seq_file *m,
 		   drm_get_subpixel_order_name(connector->display_info.subpixel_order));
 	seq_printf(m, "\tCEA rev: %d\n", connector->display_info.cea_rev);
 
-	if (!intel_encoder)
+	if (!encoder)
 		return;
 
 	switch (connector->connector_type) {
 	case DRM_MODE_CONNECTOR_DisplayPort:
 	case DRM_MODE_CONNECTOR_eDP:
-		if (intel_encoder->type == INTEL_OUTPUT_DP_MST)
+		if (encoder->type == INTEL_OUTPUT_DP_MST)
 			intel_dp_mst_info(m, intel_connector);
 		else
 			intel_dp_info(m, intel_connector);
 		break;
 	case DRM_MODE_CONNECTOR_LVDS:
-		if (intel_encoder->type == INTEL_OUTPUT_LVDS)
+		if (encoder->type == INTEL_OUTPUT_LVDS)
 			intel_lvds_info(m, intel_connector);
 		break;
 	case DRM_MODE_CONNECTOR_HDMIA:
-		if (intel_encoder->type == INTEL_OUTPUT_HDMI ||
-		    intel_encoder->type == INTEL_OUTPUT_DDI)
+		if (encoder->type == INTEL_OUTPUT_HDMI ||
+		    encoder->type == INTEL_OUTPUT_DDI)
 			intel_hdmi_info(m, intel_connector);
 		break;
 	default:
@@ -2589,70 +2526,88 @@ static void plane_rotation(char *buf, size_t bufsize, unsigned int rotation)
 		 rotation);
 }
 
-static void intel_plane_info(struct seq_file *m, struct intel_crtc *intel_crtc)
+static void intel_plane_uapi_info(struct seq_file *m, struct intel_plane *plane)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_plane *intel_plane;
+	const struct intel_plane_state *plane_state =
+		to_intel_plane_state(plane->base.state);
+	const struct drm_framebuffer *fb = plane_state->uapi.fb;
+	struct drm_format_name_buf format_name;
+	struct drm_rect src, dst;
+	char rot_str[48];
 
-	for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) {
-		struct drm_plane_state *state;
-		struct drm_plane *plane = &intel_plane->base;
-		struct drm_format_name_buf format_name;
-		char rot_str[48];
+	src = drm_plane_state_src(&plane_state->uapi);
+	dst = drm_plane_state_dest(&plane_state->uapi);
 
-		if (!plane->state) {
-			seq_puts(m, "plane->state is NULL!\n");
-			continue;
-		}
+	if (fb)
+		drm_get_format_name(fb->format->format, &format_name);
 
-		state = plane->state;
+	plane_rotation(rot_str, sizeof(rot_str),
+		       plane_state->uapi.rotation);
 
-		if (state->fb) {
-			drm_get_format_name(state->fb->format->format,
-					    &format_name);
-		} else {
-			sprintf(format_name.str, "N/A");
-		}
+	seq_printf(m, "\t\tuapi: fb=%d,%s,%dx%d, src=" DRM_RECT_FP_FMT ", dst=" DRM_RECT_FMT ", rotation=%s\n",
+		   fb ? fb->base.id : 0, fb ? format_name.str : "n/a",
+		   fb ? fb->width : 0, fb ? fb->height : 0,
+		   DRM_RECT_FP_ARG(&src),
+		   DRM_RECT_ARG(&dst),
+		   rot_str);
+}
+
+static void intel_plane_hw_info(struct seq_file *m, struct intel_plane *plane)
+{
+	const struct intel_plane_state *plane_state =
+		to_intel_plane_state(plane->base.state);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
+	struct drm_format_name_buf format_name;
+	char rot_str[48];
+
+	if (!fb)
+		return;
 
-		plane_rotation(rot_str, sizeof(rot_str), state->rotation);
-
-		seq_printf(m, "\t--Plane id %d: type=%s, crtc_pos=%4dx%4d, crtc_size=%4dx%4d, src_pos=%d.%04ux%d.%04u, src_size=%d.%04ux%d.%04u, format=%s, rotation=%s\n",
-			   plane->base.id,
-			   plane_type(intel_plane->base.type),
-			   state->crtc_x, state->crtc_y,
-			   state->crtc_w, state->crtc_h,
-			   (state->src_x >> 16),
-			   ((state->src_x & 0xffff) * 15625) >> 10,
-			   (state->src_y >> 16),
-			   ((state->src_y & 0xffff) * 15625) >> 10,
-			   (state->src_w >> 16),
-			   ((state->src_w & 0xffff) * 15625) >> 10,
-			   (state->src_h >> 16),
-			   ((state->src_h & 0xffff) * 15625) >> 10,
-			   format_name.str,
-			   rot_str);
+	drm_get_format_name(fb->format->format, &format_name);
+
+	plane_rotation(rot_str, sizeof(rot_str),
+		       plane_state->hw.rotation);
+
+	seq_printf(m, "\t\thw: fb=%d,%s,%dx%d, visible=%s, src=" DRM_RECT_FP_FMT ", dst=" DRM_RECT_FMT ", rotation=%s\n",
+		   fb->base.id, format_name.str,
+		   fb->width, fb->height,
+		   yesno(plane_state->uapi.visible),
+		   DRM_RECT_FP_ARG(&plane_state->uapi.src),
+		   DRM_RECT_ARG(&plane_state->uapi.dst),
+		   rot_str);
+}
+
+static void intel_plane_info(struct seq_file *m, struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	struct intel_plane *plane;
+
+	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+		seq_printf(m, "\t[PLANE:%d:%s]: type=%s\n",
+			   plane->base.base.id, plane->base.name,
+			   plane_type(plane->base.type));
+		intel_plane_uapi_info(m, plane);
+		intel_plane_hw_info(m, plane);
 	}
 }
 
-static void intel_scaler_info(struct seq_file *m, struct intel_crtc *intel_crtc)
+static void intel_scaler_info(struct seq_file *m, struct intel_crtc *crtc)
 {
-	struct intel_crtc_state *pipe_config;
-	int num_scalers = intel_crtc->num_scalers;
+	const struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
+	int num_scalers = crtc->num_scalers;
 	int i;
 
-	pipe_config = to_intel_crtc_state(intel_crtc->base.state);
-
 	/* Not all platformas have a scaler */
 	if (num_scalers) {
 		seq_printf(m, "\tnum_scalers=%d, scaler_users=%x scaler_id=%d",
 			   num_scalers,
-			   pipe_config->scaler_state.scaler_users,
-			   pipe_config->scaler_state.scaler_id);
+			   crtc_state->scaler_state.scaler_users,
+			   crtc_state->scaler_state.scaler_id);
 
 		for (i = 0; i < num_scalers; i++) {
-			struct intel_scaler *sc =
-					&pipe_config->scaler_state.scalers[i];
+			const struct intel_scaler *sc =
+				&crtc_state->scaler_state.scalers[i];
 
 			seq_printf(m, ", scalers[%d]: use=%s, mode=%x",
 				   i, yesno(sc->in_use), sc->mode);
@@ -2663,6 +2618,44 @@ static void intel_scaler_info(struct seq_file *m, struct intel_crtc *intel_crtc)
 	}
 }
 
+static void intel_crtc_info(struct seq_file *m, struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	const struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(crtc->base.state);
+	struct intel_encoder *encoder;
+
+	seq_printf(m, "[CRTC:%d:%s]:\n",
+		   crtc->base.base.id, crtc->base.name);
+
+	seq_printf(m, "\tuapi: enable=%s, active=%s, mode=" DRM_MODE_FMT "\n",
+		   yesno(crtc_state->uapi.enable),
+		   yesno(crtc_state->uapi.active),
+		   DRM_MODE_ARG(&crtc_state->uapi.mode));
+
+	if (crtc_state->hw.enable) {
+		seq_printf(m, "\thw: active=%s, adjusted_mode=" DRM_MODE_FMT "\n",
+			   yesno(crtc_state->hw.active),
+			   DRM_MODE_ARG(&crtc_state->hw.adjusted_mode));
+
+		seq_printf(m, "\tpipe src size=%dx%d, dither=%s, bpp=%d\n",
+			   crtc_state->pipe_src_w, crtc_state->pipe_src_h,
+			   yesno(crtc_state->dither), crtc_state->pipe_bpp);
+
+		intel_scaler_info(m, crtc);
+	}
+
+	for_each_intel_encoder_mask(&dev_priv->drm, encoder,
+				    crtc_state->uapi.encoder_mask)
+		intel_encoder_info(m, crtc, encoder);
+
+	intel_plane_info(m, crtc);
+
+	seq_printf(m, "\tunderrun reporting: cpu=%s pch=%s\n",
+		   yesno(!crtc->cpu_fifo_underrun_disabled),
+		   yesno(!crtc->pch_fifo_underrun_disabled));
+}
+
 static int i915_display_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -2674,52 +2667,22 @@ static int i915_display_info(struct seq_file *m, void *unused)
 
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
+	drm_modeset_lock_all(dev);
+
 	seq_printf(m, "CRTC info\n");
 	seq_printf(m, "---------\n");
-	for_each_intel_crtc(dev, crtc) {
-		struct intel_crtc_state *pipe_config;
-
-		drm_modeset_lock(&crtc->base.mutex, NULL);
-		pipe_config = to_intel_crtc_state(crtc->base.state);
-
-		seq_printf(m, "CRTC %d: pipe: %c, active=%s, (size=%dx%d), dither=%s, bpp=%d\n",
-			   crtc->base.base.id, pipe_name(crtc->pipe),
-			   yesno(pipe_config->base.active),
-			   pipe_config->pipe_src_w, pipe_config->pipe_src_h,
-			   yesno(pipe_config->dither), pipe_config->pipe_bpp);
-
-		if (pipe_config->base.active) {
-			struct intel_plane *cursor =
-				to_intel_plane(crtc->base.cursor);
-
-			intel_crtc_info(m, crtc);
-
-			seq_printf(m, "\tcursor visible? %s, position (%d, %d), size %dx%d, addr 0x%08x\n",
-				   yesno(cursor->base.state->visible),
-				   cursor->base.state->crtc_x,
-				   cursor->base.state->crtc_y,
-				   cursor->base.state->crtc_w,
-				   cursor->base.state->crtc_h,
-				   cursor->cursor.base);
-			intel_scaler_info(m, crtc);
-			intel_plane_info(m, crtc);
-		}
-
-		seq_printf(m, "\tunderrun reporting: cpu=%s pch=%s \n",
-			   yesno(!crtc->cpu_fifo_underrun_disabled),
-			   yesno(!crtc->pch_fifo_underrun_disabled));
-		drm_modeset_unlock(&crtc->base.mutex);
-	}
+	for_each_intel_crtc(dev, crtc)
+		intel_crtc_info(m, crtc);
 
 	seq_printf(m, "\n");
 	seq_printf(m, "Connector info\n");
 	seq_printf(m, "--------------\n");
-	mutex_lock(&dev->mode_config.mutex);
 	drm_connector_list_iter_begin(dev, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter)
 		intel_connector_info(m, connector);
 	drm_connector_list_iter_end(&conn_iter);
-	mutex_unlock(&dev->mode_config.mutex);
+
+	drm_modeset_unlock_all(dev);
 
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 
@@ -2755,7 +2718,7 @@ static int i915_rcs_topology(struct seq_file *m, void *unused)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	intel_device_info_dump_topology(&RUNTIME_INFO(dev_priv)->sseu, &p);
+	intel_device_info_print_topology(&RUNTIME_INFO(dev_priv)->sseu, &p);
 
 	return 0;
 }
@@ -3051,11 +3014,11 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused)
 		if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
 			continue;
 
-		intel_encoder = intel_attached_encoder(connector);
+		intel_encoder = intel_attached_encoder(to_intel_connector(connector));
 		if (!intel_encoder || intel_encoder->type == INTEL_OUTPUT_DP_MST)
 			continue;
 
-		intel_dig_port = enc_to_dig_port(&intel_encoder->base);
+		intel_dig_port = enc_to_dig_port(intel_encoder);
 		if (!intel_dig_port->dp.can_mst)
 			continue;
 
@@ -3105,7 +3068,7 @@ static ssize_t i915_displayport_test_active_write(struct file *file,
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			status = kstrtoint(input_buffer, 10, &val);
 			if (status < 0)
 				break;
@@ -3114,9 +3077,9 @@ static ssize_t i915_displayport_test_active_write(struct file *file,
 			 * testing code, only accept an actual value of 1 here
 			 */
 			if (val == 1)
-				intel_dp->compliance.test_active = 1;
+				intel_dp->compliance.test_active = true;
 			else
-				intel_dp->compliance.test_active = 0;
+				intel_dp->compliance.test_active = false;
 		}
 	}
 	drm_connector_list_iter_end(&conn_iter);
@@ -3149,7 +3112,7 @@ static int i915_displayport_test_active_show(struct seq_file *m, void *data)
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			if (intel_dp->compliance.test_active)
 				seq_puts(m, "1");
 			else
@@ -3199,7 +3162,7 @@ static int i915_displayport_test_data_show(struct seq_file *m, void *data)
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			if (intel_dp->compliance.test_type ==
 			    DP_TEST_LINK_EDID_READ)
 				seq_printf(m, "%lx",
@@ -3243,7 +3206,7 @@ static int i915_displayport_test_type_show(struct seq_file *m, void *data)
 			continue;
 
 		if (encoder && connector->status == connector_status_connected) {
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			seq_printf(m, "%02lx", intel_dp->compliance.test_type);
 		} else
 			seq_puts(m, "0");
@@ -3854,8 +3817,8 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 #undef SS_MAX
 }
 
-static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
-					 struct sseu_dev_info *sseu)
+static void bdw_sseu_device_status(struct drm_i915_private *dev_priv,
+				   struct sseu_dev_info *sseu)
 {
 	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
 	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
@@ -3940,7 +3903,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		if (IS_CHERRYVIEW(dev_priv))
 			cherryview_sseu_device_status(dev_priv, &sseu);
 		else if (IS_BROADWELL(dev_priv))
-			broadwell_sseu_device_status(dev_priv, &sseu);
+			bdw_sseu_device_status(dev_priv, &sseu);
 		else if (IS_GEN(dev_priv, 9))
 			gen9_sseu_device_status(dev_priv, &sseu);
 		else if (INTEL_GEN(dev_priv) >= 10)
@@ -4161,11 +4124,11 @@ static int i915_drrs_ctl_set(void *data, u64 val)
 
 		crtc_state = to_intel_crtc_state(crtc->base.state);
 
-		if (!crtc_state->base.active ||
+		if (!crtc_state->hw.active ||
 		    !crtc_state->has_drrs)
 			goto out;
 
-		commit = crtc_state->base.commit;
+		commit = crtc_state->uapi.commit;
 		if (commit) {
 			ret = wait_for_completion_interruptible(&commit->hw_done);
 			if (ret)
@@ -4177,18 +4140,18 @@ static int i915_drrs_ctl_set(void *data, u64 val)
 			struct intel_encoder *encoder;
 			struct intel_dp *intel_dp;
 
-			if (!(crtc_state->base.connector_mask &
+			if (!(crtc_state->uapi.connector_mask &
 			      drm_connector_mask(connector)))
 				continue;
 
-			encoder = intel_attached_encoder(connector);
+			encoder = intel_attached_encoder(to_intel_connector(connector));
 			if (encoder->type != INTEL_OUTPUT_EDP)
 				continue;
 
 			DRM_DEBUG_DRIVER("Manually %sabling DRRS. %llu\n",
 						val ? "en" : "dis", val);
 
-			intel_dp = enc_to_intel_dp(&encoder->base);
+			intel_dp = enc_to_intel_dp(encoder);
 			if (val)
 				intel_edp_drrs_enable(intel_dp,
 						      crtc_state);
@@ -4236,14 +4199,14 @@ i915_fifo_underrun_reset_write(struct file *filp,
 			return ret;
 
 		crtc_state = to_intel_crtc_state(intel_crtc->base.state);
-		commit = crtc_state->base.commit;
+		commit = crtc_state->uapi.commit;
 		if (commit) {
 			ret = wait_for_completion_interruptible(&commit->hw_done);
 			if (!ret)
 				ret = wait_for_completion_interruptible(&commit->flip_done);
 		}
 
-		if (!ret && crtc_state->base.active) {
+		if (!ret && crtc_state->hw.active) {
 			DRM_DEBUG_KMS("Re-arming FIFO underruns on pipe %c\n",
 				      pipe_name(intel_crtc->pipe));
 
@@ -4392,7 +4355,7 @@ static int i915_dpcd_show(struct seq_file *m, void *data)
 {
 	struct drm_connector *connector = m->private;
 	struct intel_dp *intel_dp =
-		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 	u8 buf[16];
 	ssize_t err;
 	int i;
@@ -4427,7 +4390,7 @@ static int i915_panel_show(struct seq_file *m, void *data)
 {
 	struct drm_connector *connector = m->private;
 	struct intel_dp *intel_dp =
-		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
@@ -4505,7 +4468,7 @@ static int i915_dsc_fec_support_show(struct seq_file *m, void *data)
 		} else if (ret) {
 			break;
 		}
-		intel_dp = enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+		intel_dp = enc_to_intel_dp(intel_attached_encoder(to_intel_connector(connector)));
 		crtc_state = to_intel_crtc_state(crtc->state);
 		seq_printf(m, "DSC_Enabled: %s\n",
 			   yesno(crtc_state->dsc.compression_enable));
@@ -4532,8 +4495,8 @@ static ssize_t i915_dsc_fec_support_write(struct file *file,
 	int ret;
 	struct drm_connector *connector =
 		((struct seq_file *)file->private_data)->private;
-	struct intel_encoder *encoder = intel_attached_encoder(connector);
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct intel_encoder *encoder = intel_attached_encoder(to_intel_connector(connector));
+	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
 	if (len == 0)
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 3c512c571e60..f7385abdd74b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -61,6 +61,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
+#include "gem/i915_gem_mman.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_rc6.h"
@@ -468,6 +469,12 @@ static void vlv_free_s0ix_state(struct drm_i915_private *i915)
 	i915->vlv_s0ix_state = NULL;
 }
 
+static void sanitize_gpu(struct drm_i915_private *i915)
+{
+	if (!INTEL_INFO(i915)->gpu_reset_clobbers_display)
+		__intel_gt_reset(&i915->gt, ALL_ENGINES);
+}
+
 /**
  * i915_driver_early_probe - setup state not requiring device access
  * @dev_priv: device private
@@ -601,6 +608,9 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_uncore;
 
+	/* As early as possible, scrub existing GPU state before clobbering */
+	sanitize_gpu(dev_priv);
+
 	return 0;
 
 err_uncore:
@@ -618,7 +628,6 @@ err_bridge:
  */
 static void i915_driver_mmio_release(struct drm_i915_private *dev_priv)
 {
-	intel_engines_cleanup(&dev_priv->gt);
 	intel_teardown_mchbar(dev_priv);
 	intel_uncore_fini_mmio(&dev_priv->uncore);
 	pci_dev_put(dev_priv->bridge_dev);
@@ -1052,7 +1061,7 @@ intel_get_dram_info(struct drm_i915_private *dev_priv)
 	 */
 	dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv);
 
-	if (INTEL_GEN(dev_priv) < 9)
+	if (INTEL_GEN(dev_priv) < 9 || !HAS_DISPLAY(dev_priv))
 		return;
 
 	if (IS_GEN9_LP(dev_priv))
@@ -1385,7 +1394,7 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 
 static void i915_welcome_messages(struct drm_i915_private *dev_priv)
 {
-	if (drm_debug & DRM_UT_DRIVER) {
+	if (drm_debug_enabled(DRM_UT_DRIVER)) {
 		struct drm_printer p = drm_debug_printer("i915 device info:");
 
 		drm_printf(&p, "pciid=0x%04x rev=0x%02x platform=%s (subplatform=0x%x) gen=%i\n",
@@ -1396,8 +1405,8 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv)
 					     INTEL_INFO(dev_priv)->platform),
 			   INTEL_GEN(dev_priv));
 
-		intel_device_info_dump_flags(INTEL_INFO(dev_priv), &p);
-		intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p);
+		intel_device_info_print_static(INTEL_INFO(dev_priv), &p);
+		intel_device_info_print_runtime(RUNTIME_INFO(dev_priv), &p);
 	}
 
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG))
@@ -1817,9 +1826,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
-	intel_rc6_ctx_wa_resume(&dev_priv->gt.rc6);
-
-	intel_gt_sanitize(&dev_priv->gt, true);
+	sanitize_gpu(dev_priv);
 
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret)
@@ -2662,18 +2669,12 @@ const struct dev_pm_ops i915_pm_ops = {
 	.runtime_resume = intel_runtime_resume,
 };
 
-static const struct vm_operations_struct i915_gem_vm_ops = {
-	.fault = i915_gem_fault,
-	.open = drm_gem_vm_open,
-	.close = drm_gem_vm_close,
-};
-
 static const struct file_operations i915_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
 	.release = drm_release,
 	.unlocked_ioctl = drm_ioctl,
-	.mmap = drm_gem_mmap,
+	.mmap = i915_gem_mmap,
 	.poll = drm_poll,
 	.read = drm_read,
 	.compat_ioctl = i915_compat_ioctl,
@@ -2720,7 +2721,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_PREAD, i915_gem_pread_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_PWRITE, i915_gem_pwrite_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP, i915_gem_mmap_ioctl, DRM_RENDER_ALLOW),
-	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_GTT, i915_gem_mmap_gtt_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_GEM_MMAP_OFFSET, i915_gem_mmap_offset_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_SET_TILING, i915_gem_set_tiling_ioctl, DRM_RENDER_ALLOW),
@@ -2762,7 +2763,6 @@ static struct drm_driver driver = {
 
 	.gem_close_object = i915_gem_close_object,
 	.gem_free_object_unlocked = i915_gem_free_object,
-	.gem_vm_ops = &i915_gem_vm_ops,
 
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
@@ -2773,7 +2773,8 @@ static struct drm_driver driver = {
 	.get_scanout_position = i915_get_crtc_scanoutpos,
 
 	.dumb_create = i915_gem_dumb_create,
-	.dumb_map_offset = i915_gem_mmap_gtt,
+	.dumb_map_offset = i915_gem_dumb_mmap_offset,
+
 	.ioctls = i915_ioctls,
 	.num_ioctls = ARRAY_SIZE(i915_ioctls),
 	.fops = &i915_driver_fops,
@@ -2784,7 +2785,3 @@ static struct drm_driver driver = {
 	.minor = DRIVER_MINOR,
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/mock_drm.c"
-#endif
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 21aa08f55811..077af22b8340 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -46,6 +46,7 @@
 #include <linux/dma-resv.h>
 #include <linux/shmem_fs.h>
 #include <linux/stackdepot.h>
+#include <linux/xarray.h>
 
 #include <drm/intel-gtt.h>
 #include <drm/drm_legacy.h> /* for struct drm_dma_handle */
@@ -110,8 +111,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20191101"
-#define DRIVER_TIMESTAMP	1572604873
+#define DRIVER_DATE		"20200114"
+#define DRIVER_TIMESTAMP	1579001978
 
 struct drm_i915_gem_object;
 
@@ -201,8 +202,7 @@ struct drm_i915_file_private {
 		struct list_head request_list;
 	} mm;
 
-	struct idr context_idr;
-	struct mutex context_idr_lock; /* guards context_idr */
+	struct xarray context_xa;
 
 	struct idr vm_idr;
 	struct mutex vm_idr_lock; /* guards vm_idr */
@@ -273,11 +273,11 @@ struct drm_i915_display_funcs {
 	int (*compute_pipe_wm)(struct intel_crtc_state *crtc_state);
 	int (*compute_intermediate_wm)(struct intel_crtc_state *crtc_state);
 	void (*initial_watermarks)(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state);
+				   struct intel_crtc *crtc);
 	void (*atomic_update_watermarks)(struct intel_atomic_state *state,
-					 struct intel_crtc_state *crtc_state);
+					 struct intel_crtc *crtc);
 	void (*optimize_watermarks)(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state);
+				    struct intel_crtc *crtc);
 	int (*compute_global_watermarks)(struct intel_atomic_state *state);
 	void (*update_wm)(struct intel_crtc *crtc);
 	int (*modeset_calc_cdclk)(struct intel_atomic_state *state);
@@ -290,10 +290,10 @@ struct drm_i915_display_funcs {
 					 struct intel_initial_plane_config *);
 	int (*crtc_compute_clock)(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
-	void (*crtc_enable)(struct intel_crtc_state *pipe_config,
-			    struct intel_atomic_state *old_state);
-	void (*crtc_disable)(struct intel_crtc_state *old_crtc_state,
-			     struct intel_atomic_state *old_state);
+	void (*crtc_enable)(struct intel_atomic_state *state,
+			    struct intel_crtc *crtc);
+	void (*crtc_disable)(struct intel_atomic_state *state,
+			     struct intel_crtc *crtc);
 	void (*commit_modeset_enables)(struct intel_atomic_state *state);
 	void (*commit_modeset_disables)(struct intel_atomic_state *state);
 	void (*audio_codec_enable)(struct intel_encoder *encoder,
@@ -366,7 +366,6 @@ struct intel_fbc {
 	unsigned threshold;
 	unsigned int possible_framebuffer_bits;
 	unsigned int busy_bits;
-	unsigned int visible_pipes_mask;
 	struct intel_crtc *crtc;
 
 	struct drm_mm_node compressed_fb;
@@ -374,8 +373,8 @@ struct intel_fbc {
 
 	bool false_color;
 
-	bool enabled;
 	bool active;
+	bool activated;
 	bool flip_pending;
 
 	bool underrun_detected;
@@ -387,9 +386,6 @@ struct intel_fbc {
 	 * these problems.
 	 */
 	struct intel_fbc_state_cache {
-		struct i915_vma *vma;
-		unsigned long flags;
-
 		struct {
 			unsigned int mode_flags;
 			u32 hsw_bdw_pixel_rate;
@@ -418,6 +414,8 @@ struct intel_fbc {
 			const struct drm_format_info *format;
 			unsigned int stride;
 		} fb;
+		u16 gen9_wa_cfb_stride;
+		s8 fence_id;
 	} state_cache;
 
 	/*
@@ -428,9 +426,6 @@ struct intel_fbc {
 	 * are supposed to read from it in order to program the registers.
 	 */
 	struct intel_fbc_reg_params {
-		struct i915_vma *vma;
-		unsigned long flags;
-
 		struct {
 			enum pipe pipe;
 			enum i9xx_plane_id i9xx_plane;
@@ -443,7 +438,9 @@ struct intel_fbc {
 		} fb;
 
 		int cfb_size;
-		unsigned int gen9_wa_cfb_stride;
+		u16 gen9_wa_cfb_stride;
+		s8 fence_id;
+		bool plane_visible;
 	} params;
 
 	const char *no_fbc_reason;
@@ -508,6 +505,7 @@ struct i915_psr {
 	bool dc3co_enabled;
 	u32 dc3co_exit_delay;
 	struct delayed_work idle_work;
+	bool initially_probed;
 };
 
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
@@ -621,19 +619,18 @@ struct i915_gem_mm {
 
 #define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
 
+/* Amount of SAGV/QGV points, BSpec precisely defines this */
+#define I915_NUM_QGV_POINTS 8
+
 struct ddi_vbt_port_info {
 	/* Non-NULL if port present. */
 	const struct child_device_config *child;
 
 	int max_tmds_clock;
 
-	/*
-	 * This is an index in the HDMI/DVI DDI buffer translation table.
-	 * The special value HDMI_LEVEL_SHIFT_UNKNOWN means the VBT didn't
-	 * populate this field.
-	 */
-#define HDMI_LEVEL_SHIFT_UNKNOWN	0xff
+	/* This is an index in the HDMI/DVI DDI buffer translation table. */
 	u8 hdmi_level_shift;
+	u8 hdmi_level_shift_set:1;
 
 	u8 supports_dvi:1;
 	u8 supports_hdmi:1;
@@ -724,8 +721,7 @@ struct intel_vbt_data {
 
 	int crt_ddc_pin;
 
-	int child_dev_num;
-	struct child_device_config *child_dev;
+	struct list_head display_devices;
 
 	struct ddi_vbt_port_info ddi_port_info[I915_MAX_PORTS];
 	struct sdvo_device_mapping sdvo_mappings[2];
@@ -891,6 +887,10 @@ struct intel_cdclk_state {
 	u8 voltage_level;
 };
 
+struct i915_selftest_stash {
+	atomic_t counter;
+};
+
 struct drm_i915_private {
 	struct drm_device drm;
 
@@ -956,9 +956,6 @@ struct drm_i915_private {
 
 	struct pci_dev *bridge_dev;
 
-	/* Context used internally to idle the GPU and setup initial state */
-	struct i915_gem_context *kernel_context;
-
 	struct intel_engine_cs *engine[I915_NUM_ENGINES];
 	struct rb_root uabi_engines;
 
@@ -1233,7 +1230,8 @@ struct drm_i915_private {
 	} dram_info;
 
 	struct intel_bw_info {
-		unsigned int deratedbw[3]; /* for each QGV point */
+		/* for each QGV point */
+		unsigned int deratedbw[I915_NUM_QGV_POINTS];
 		u8 num_qgv_points;
 		u8 num_planes;
 	} max_bw[6];
@@ -1248,8 +1246,6 @@ struct drm_i915_private {
 	struct intel_gt gt;
 
 	struct {
-		struct notifier_block pm_notifier;
-
 		struct i915_gem_contexts {
 			spinlock_t lock; /* locks list */
 			struct list_head list;
@@ -1257,6 +1253,16 @@ struct drm_i915_private {
 			struct llist_head free_list;
 			struct work_struct free_work;
 		} contexts;
+
+		/*
+		 * We replace the local file with a global mappings as the
+		 * backing storage for the mmap is on the device and not
+		 * on the struct file, and we do not want to prolong the
+		 * lifetime of the local fd. To minimise the number of
+		 * anonymous inodes we create, we use a global singleton to
+		 * share the global mapping.
+		 */
+		struct file *mmap_singleton;
 	} gem;
 
 	u8 pch_ssc_use;
@@ -1286,6 +1292,8 @@ struct drm_i915_private {
 	/* Mutex to protect the above hdcp component related values. */
 	struct mutex hdcp_comp_mutex;
 
+	I915_SELFTEST_DECLARE(struct i915_selftest_stash selftest;)
+
 	/*
 	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
 	 * will be rejected. Instead look for a better place.
@@ -1844,14 +1852,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
-
-struct i915_vma * __must_check
-i915_gem_object_pin(struct drm_i915_gem_object *obj,
-		    struct i915_address_space *vm,
-		    const struct i915_ggtt_view *view,
-		    u64 size,
-		    u64 alignment,
-		    u64 flags);
+#define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1)
 
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
@@ -1864,9 +1865,6 @@ i915_mutex_lock_interruptible(struct drm_device *dev)
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
-int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
-		      u32 handle, u64 *offset);
-int i915_gem_mmap_gtt_version(void);
 
 int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
 
@@ -1876,7 +1874,7 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
 }
 
 static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
-					  struct intel_engine_cs *engine)
+					  const struct intel_engine_cs *engine)
 {
 	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
 }
@@ -1889,7 +1887,6 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv);
 void i915_gem_suspend(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
-vm_fault_t i915_gem_fault(struct vm_fault *vmf);
 
 int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file);
 void i915_gem_release(struct drm_device *dev, struct drm_file *file);
@@ -1905,7 +1902,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags)
 static inline struct i915_gem_context *
 __i915_gem_context_lookup_rcu(struct drm_i915_file_private *file_priv, u32 id)
 {
-	return idr_find(&file_priv->context_idr, id);
+	return xa_load(&file_priv->context_xa, id);
 }
 
 static inline struct i915_gem_context *
@@ -1958,14 +1955,13 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-int intel_engine_cmd_parser(struct i915_gem_context *cxt,
-			    struct intel_engine_cs *engine,
-			    struct drm_i915_gem_object *batch_obj,
-			    u64 user_batch_start,
-			    u32 batch_start_offset,
-			    u32 batch_len,
-			    struct drm_i915_gem_object *shadow_batch_obj,
-			    u64 shadow_batch_start);
+int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+			    struct i915_vma *batch,
+			    u32 batch_offset,
+			    u32 batch_length,
+			    struct i915_vma *shadow,
+			    bool trampoline);
+#define I915_CMD_PARSER_TRAMPOLINE_SIZE 8
 
 /* intel_device_info.c */
 static inline struct intel_device_info *
@@ -2032,6 +2028,9 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 int remap_io_mapping(struct vm_area_struct *vma,
 		     unsigned long addr, unsigned long pfn, unsigned long size,
 		     struct io_mapping *iomap);
+int remap_io_sg(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size,
+		struct scatterlist *sgl, resource_size_t iobase);
 
 static inline int intel_hws_csb_write_index(struct drm_i915_private *i915)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 905890e3ac24..94f993e4c12f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -44,20 +44,14 @@
 #include "gem/i915_gem_clflush.h"
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
-#include "gem/i915_gem_pm.h"
-#include "gt/intel_context.h"
+#include "gem/i915_gem_mman.h"
+#include "gem/i915_gem_region.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
-#include "gt/intel_gt_requests.h"
-#include "gt/intel_mocs.h"
-#include "gt/intel_reset.h"
-#include "gt/intel_renderstate.h"
-#include "gt/intel_rps.h"
 #include "gt/intel_workarounds.h"
 
 #include "i915_drv.h"
-#include "i915_scatterlist.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
 
@@ -119,33 +113,65 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags)
 {
-	struct i915_vma *vma;
+	struct intel_runtime_pm *rpm = &to_i915(obj->base.dev)->runtime_pm;
 	LIST_HEAD(still_in_list);
-	int ret = 0;
+	intel_wakeref_t wakeref;
+	struct i915_vma *vma;
+	int ret;
+
+	if (!atomic_read(&obj->bind_count))
+		return 0;
+
+	/*
+	 * As some machines use ACPI to handle runtime-resume callbacks, and
+	 * ACPI is quite kmalloc happy, we cannot resume beneath the vm->mutex
+	 * as they are required by the shrinker. Ergo, we wake the device up
+	 * first just in case.
+	 */
+	wakeref = intel_runtime_pm_get(rpm);
 
+try_again:
+	ret = 0;
 	spin_lock(&obj->vma.lock);
 	while (!ret && (vma = list_first_entry_or_null(&obj->vma.list,
 						       struct i915_vma,
 						       obj_link))) {
 		struct i915_address_space *vm = vma->vm;
 
-		ret = -EBUSY;
+		list_move_tail(&vma->obj_link, &still_in_list);
+		if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK))
+			continue;
+
+		ret = -EAGAIN;
 		if (!i915_vm_tryopen(vm))
 			break;
 
-		list_move_tail(&vma->obj_link, &still_in_list);
+		/* Prevent vma being freed by i915_vma_parked as we unbind */
+		vma = __i915_vma_get(vma);
 		spin_unlock(&obj->vma.lock);
 
-		if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
-		    !i915_vma_is_active(vma))
-			ret = i915_vma_unbind(vma);
+		if (vma) {
+			ret = -EBUSY;
+			if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
+			    !i915_vma_is_active(vma))
+				ret = i915_vma_unbind(vma);
+
+			__i915_vma_put(vma);
+		}
 
 		i915_vm_close(vm);
 		spin_lock(&obj->vma.lock);
 	}
-	list_splice(&still_in_list, &obj->vma.list);
+	list_splice_init(&still_in_list, &obj->vma.list);
 	spin_unlock(&obj->vma.lock);
 
+	if (ret == -EAGAIN && flags & I915_GEM_OBJECT_UNBIND_BARRIER) {
+		rcu_barrier(); /* flush the i915_vm_release() */
+		goto try_again;
+	}
+
+	intel_runtime_pm_put(rpm, wakeref);
+
 	return ret;
 }
 
@@ -175,7 +201,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 
 static int
 i915_gem_create(struct drm_file *file,
-		struct drm_i915_private *dev_priv,
+		struct intel_memory_region *mr,
 		u64 *size_p,
 		u32 *handle_p)
 {
@@ -184,12 +210,16 @@ i915_gem_create(struct drm_file *file,
 	u64 size;
 	int ret;
 
-	size = round_up(*size_p, PAGE_SIZE);
+	GEM_BUG_ON(!is_power_of_2(mr->min_page_size));
+	size = round_up(*size_p, mr->min_page_size);
 	if (size == 0)
 		return -EINVAL;
 
+	/* For most of the ABI (e.g. mmap) we think in system pages */
+	GEM_BUG_ON(!IS_ALIGNED(size, PAGE_SIZE));
+
 	/* Allocate the new object */
-	obj = i915_gem_object_create_shmem(dev_priv, size);
+	obj = i915_gem_object_create_region(mr, size, 0);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -209,6 +239,7 @@ i915_gem_dumb_create(struct drm_file *file,
 		     struct drm_device *dev,
 		     struct drm_mode_create_dumb *args)
 {
+	enum intel_memory_type mem_type;
 	int cpp = DIV_ROUND_UP(args->bpp, 8);
 	u32 format;
 
@@ -235,7 +266,14 @@ i915_gem_dumb_create(struct drm_file *file,
 		args->pitch = ALIGN(args->pitch, 4096);
 
 	args->size = args->pitch * args->height;
-	return i915_gem_create(file, to_i915(dev),
+
+	mem_type = INTEL_MEMORY_SYSTEM;
+	if (HAS_LMEM(to_i915(dev)))
+		mem_type = INTEL_MEMORY_LOCAL;
+
+	return i915_gem_create(file,
+			       intel_memory_region_by_type(to_i915(dev),
+							   mem_type),
 			       &args->size, &args->handle);
 }
 
@@ -249,12 +287,14 @@ int
 i915_gem_create_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_create *args = data;
 
-	i915_gem_flush_free_objects(dev_priv);
+	i915_gem_flush_free_objects(i915);
 
-	return i915_gem_create(file, dev_priv,
+	return i915_gem_create(file,
+			       intel_memory_region_by_type(i915,
+							   INTEL_MEMORY_SYSTEM),
 			       &args->size, &args->handle);
 }
 
@@ -631,11 +671,12 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		user_data += page_length;
 		offset += page_length;
 	}
+
+	intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 	i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);
 
 	i915_gem_object_unlock_fence(obj, fence);
 out_unpin:
-	intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 	if (drm_mm_node_allocated(&node)) {
 		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(ggtt, &node);
@@ -855,7 +896,7 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 
 	list_for_each_entry_safe(obj, on,
 				 &i915->ggtt.userfault_list, userfault_link)
-		__i915_gem_object_release_mmap(obj);
+		__i915_gem_object_release_mmap_gtt(obj);
 
 	/*
 	 * The fence will be lost when the device powers down. If any were
@@ -892,22 +933,8 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 u64 alignment,
 			 u64 flags)
 {
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	struct i915_address_space *vm = &dev_priv->ggtt.vm;
-
-	return i915_gem_object_pin(obj, vm, view, size, alignment,
-				   flags | PIN_GLOBAL);
-}
-
-struct i915_vma *
-i915_gem_object_pin(struct drm_i915_gem_object *obj,
-		    struct i915_address_space *vm,
-		    const struct i915_ggtt_view *view,
-		    u64 size,
-		    u64 alignment,
-		    u64 flags)
-{
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct i915_vma *vma;
 	int ret;
 
@@ -916,17 +943,19 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
-		/* If the required space is larger than the available
+		/*
+		 * If the required space is larger than the available
 		 * aperture, we will not able to find a slot for the
 		 * object and unbinding the object now will be in
 		 * vain. Worse, doing so may cause us to ping-pong
 		 * the object in and out of the Global GTT and
 		 * waste a lot of cycles under the mutex.
 		 */
-		if (obj->base.size > dev_priv->ggtt.mappable_end)
+		if (obj->base.size > ggtt->mappable_end)
 			return ERR_PTR(-E2BIG);
 
-		/* If NONBLOCK is set the caller is optimistically
+		/*
+		 * If NONBLOCK is set the caller is optimistically
 		 * trying to cache the full object within the mappable
 		 * aperture, and *must* have a fallback in place for
 		 * situations where we cannot bind the object. We
@@ -942,11 +971,11 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 		 * we could try to minimise harm to others.
 		 */
 		if (flags & PIN_NONBLOCK &&
-		    obj->base.size > dev_priv->ggtt.mappable_end / 2)
+		    obj->base.size > ggtt->mappable_end / 2)
 			return ERR_PTR(-ENOSPC);
 	}
 
-	vma = i915_vma_instance(obj, vm, view);
+	vma = i915_vma_instance(obj, &ggtt->vm, view);
 	if (IS_ERR(vma))
 		return vma;
 
@@ -956,7 +985,7 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 				return ERR_PTR(-ENOSPC);
 
 			if (flags & PIN_MAPPABLE &&
-			    vma->fence_size > dev_priv->ggtt.mappable_end / 2)
+			    vma->fence_size > ggtt->mappable_end / 2)
 				return ERR_PTR(-ENOSPC);
 		}
 
@@ -966,14 +995,14 @@ i915_gem_object_pin(struct drm_i915_gem_object *obj,
 	}
 
 	if (vma->fence && !i915_gem_object_is_tiled(obj)) {
-		mutex_lock(&vma->vm->mutex);
+		mutex_lock(&ggtt->vm.mutex);
 		ret = i915_vma_revoke_fence(vma);
-		mutex_unlock(&vma->vm->mutex);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (ret)
 			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags);
+	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -1054,172 +1083,6 @@ out:
 	return err;
 }
 
-static int __intel_context_flush_retire(struct intel_context *ce)
-{
-	struct intel_timeline *tl;
-
-	tl = intel_context_timeline_lock(ce);
-	if (IS_ERR(tl))
-		return PTR_ERR(tl);
-
-	intel_context_timeline_unlock(tl);
-	return 0;
-}
-
-static int __intel_engines_record_defaults(struct intel_gt *gt)
-{
-	struct i915_request *requests[I915_NUM_ENGINES] = {};
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err = 0;
-
-	/*
-	 * As we reset the gpu during very early sanitisation, the current
-	 * register state on the GPU should reflect its defaults values.
-	 * We load a context onto the hw (with restore-inhibit), then switch
-	 * over to a second context to save that default register state. We
-	 * can then prime every new context with that state so they all start
-	 * from the same default HW values.
-	 */
-
-	for_each_engine(engine, gt, id) {
-		struct intel_context *ce;
-		struct i915_request *rq;
-
-		/* We must be able to switch to something! */
-		GEM_BUG_ON(!engine->kernel_context);
-		engine->serial++; /* force the kernel context switch */
-
-		ce = intel_context_create(engine->kernel_context->gem_context,
-					  engine);
-		if (IS_ERR(ce)) {
-			err = PTR_ERR(ce);
-			goto out;
-		}
-
-		rq = intel_context_create_request(ce);
-		if (IS_ERR(rq)) {
-			err = PTR_ERR(rq);
-			intel_context_put(ce);
-			goto out;
-		}
-
-		err = intel_engine_emit_ctx_wa(rq);
-		if (err)
-			goto err_rq;
-
-		err = intel_renderstate_emit(rq);
-		if (err)
-			goto err_rq;
-
-err_rq:
-		requests[id] = i915_request_get(rq);
-		i915_request_add(rq);
-		if (err)
-			goto out;
-	}
-
-	/* Flush the default context image to memory, and enable powersaving. */
-	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
-		err = -EIO;
-		goto out;
-	}
-
-	for (id = 0; id < ARRAY_SIZE(requests); id++) {
-		struct i915_request *rq;
-		struct i915_vma *state;
-		void *vaddr;
-
-		rq = requests[id];
-		if (!rq)
-			continue;
-
-		GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT,
-				     &rq->hw_context->flags));
-		state = rq->hw_context->state;
-		if (!state)
-			continue;
-
-		/* Serialise with retirement on another CPU */
-		err = __intel_context_flush_retire(rq->hw_context);
-		if (err)
-			goto out;
-
-		/* We want to be able to unbind the state from the GGTT */
-		GEM_BUG_ON(intel_context_is_pinned(rq->hw_context));
-
-		/*
-		 * As we will hold a reference to the logical state, it will
-		 * not be torn down with the context, and importantly the
-		 * object will hold onto its vma (making it possible for a
-		 * stray GTT write to corrupt our defaults). Unmap the vma
-		 * from the GTT to prevent such accidents and reclaim the
-		 * space.
-		 */
-		err = i915_vma_unbind(state);
-		if (err)
-			goto out;
-
-		i915_gem_object_lock(state->obj);
-		err = i915_gem_object_set_to_cpu_domain(state->obj, false);
-		i915_gem_object_unlock(state->obj);
-		if (err)
-			goto out;
-
-		i915_gem_object_set_cache_coherency(state->obj, I915_CACHE_LLC);
-
-		/* Check we can acquire the image of the context state */
-		vaddr = i915_gem_object_pin_map(state->obj, I915_MAP_FORCE_WB);
-		if (IS_ERR(vaddr)) {
-			err = PTR_ERR(vaddr);
-			goto out;
-		}
-
-		rq->engine->default_state = i915_gem_object_get(state->obj);
-		i915_gem_object_unpin_map(state->obj);
-	}
-
-out:
-	/*
-	 * If we have to abandon now, we expect the engines to be idle
-	 * and ready to be torn-down. The quickest way we can accomplish
-	 * this is by declaring ourselves wedged.
-	 */
-	if (err)
-		intel_gt_set_wedged(gt);
-
-	for (id = 0; id < ARRAY_SIZE(requests); id++) {
-		struct intel_context *ce;
-		struct i915_request *rq;
-
-		rq = requests[id];
-		if (!rq)
-			continue;
-
-		ce = rq->hw_context;
-		i915_request_put(rq);
-		intel_context_put(ce);
-	}
-	return err;
-}
-
-static int intel_engines_verify_workarounds(struct intel_gt *gt)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	int err = 0;
-
-	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
-		return 0;
-
-	for_each_engine(engine, gt, id) {
-		if (intel_engine_verify_workarounds(engine, "load"))
-			err = -EIO;
-	}
-
-	return err;
-}
-
 int i915_gem_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
@@ -1229,8 +1092,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		mkwrite_device_info(dev_priv)->page_sizes =
 			I915_GTT_PAGE_SIZE_4K;
 
-	intel_timelines_init(dev_priv);
-
 	ret = i915_gem_init_userptr(dev_priv);
 	if (ret)
 		return ret;
@@ -1238,51 +1099,12 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	intel_uc_fetch_firmwares(&dev_priv->gt.uc);
 	intel_wopcm_init(&dev_priv->wopcm);
 
-	/* This is just a security blanket to placate dragons.
-	 * On some systems, we very sporadically observe that the first TLBs
-	 * used by the CS may be stale, despite us poking the TLB reset. If
-	 * we hold the forcewake during initialisation these problems
-	 * just magically go away.
-	 */
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
 	ret = i915_init_ggtt(dev_priv);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
 		goto err_unlock;
 	}
 
-	intel_gt_init(&dev_priv->gt);
-
-	ret = intel_engines_setup(&dev_priv->gt);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_unlock;
-	}
-
-	ret = i915_gem_init_contexts(dev_priv);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_scratch;
-	}
-
-	ret = intel_engines_init(&dev_priv->gt);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_context;
-	}
-
-	intel_uc_init(&dev_priv->gt.uc);
-
-	ret = intel_gt_init_hw(&dev_priv->gt);
-	if (ret)
-		goto err_uc_init;
-
-	/* Only when the HW is re-initialised, can we replay the requests */
-	ret = intel_gt_resume(&dev_priv->gt);
-	if (ret)
-		goto err_init_hw;
-
 	/*
 	 * Despite its name intel_init_clock_gating applies both display
 	 * clock gating workarounds; GT mmio workarounds and the occasional
@@ -1294,23 +1116,9 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 */
 	intel_init_clock_gating(dev_priv);
 
-	ret = intel_engines_verify_workarounds(&dev_priv->gt);
+	ret = intel_gt_init(&dev_priv->gt);
 	if (ret)
-		goto err_gt;
-
-	ret = __intel_engines_record_defaults(&dev_priv->gt);
-	if (ret)
-		goto err_gt;
-
-	ret = i915_inject_probe_error(dev_priv, -ENODEV);
-	if (ret)
-		goto err_gt;
-
-	ret = i915_inject_probe_error(dev_priv, -EIO);
-	if (ret)
-		goto err_gt;
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
+		goto err_unlock;
 
 	return 0;
 
@@ -1320,31 +1128,12 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 * HW as irrevisibly wedged, but keep enough state around that the
 	 * driver doesn't explode during runtime.
 	 */
-err_gt:
-	intel_gt_set_wedged_on_init(&dev_priv->gt);
-	i915_gem_suspend(dev_priv);
-	i915_gem_suspend_late(dev_priv);
-
-	i915_gem_drain_workqueue(dev_priv);
-err_init_hw:
-	intel_uc_fini_hw(&dev_priv->gt.uc);
-err_uc_init:
-	if (ret != -EIO) {
-		intel_uc_fini(&dev_priv->gt.uc);
-		intel_engines_cleanup(&dev_priv->gt);
-	}
-err_context:
-	if (ret != -EIO)
-		i915_gem_driver_release__contexts(dev_priv);
-err_scratch:
-	intel_gt_driver_release(&dev_priv->gt);
 err_unlock:
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
+	i915_gem_drain_workqueue(dev_priv);
 
 	if (ret != -EIO) {
 		intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
 		i915_gem_cleanup_userptr(dev_priv);
-		intel_timelines_fini(dev_priv);
 	}
 
 	if (ret == -EIO) {
@@ -1388,27 +1177,24 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 
 	i915_gem_suspend_late(dev_priv);
 	intel_gt_driver_remove(&dev_priv->gt);
+	dev_priv->uabi_engines = RB_ROOT;
 
 	/* Flush any outstanding unpin_work. */
 	i915_gem_drain_workqueue(dev_priv);
 
-	intel_uc_fini_hw(&dev_priv->gt.uc);
-	intel_uc_fini(&dev_priv->gt.uc);
-
 	i915_gem_drain_freed_objects(dev_priv);
 }
 
 void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 {
-	intel_engines_cleanup(&dev_priv->gt);
 	i915_gem_driver_release__contexts(dev_priv);
+
 	intel_gt_driver_release(&dev_priv->gt);
 
 	intel_wa_list_free(&dev_priv->gt_wa_list);
 
 	intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
 	i915_gem_cleanup_userptr(dev_priv);
-	intel_timelines_fini(dev_priv);
 
 	i915_gem_drain_freed_objects(dev_priv);
 
@@ -1430,6 +1216,7 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 void i915_gem_init_early(struct drm_i915_private *dev_priv)
 {
 	i915_gem_init__mm(dev_priv);
+	i915_gem_init__contexts(dev_priv);
 
 	spin_lock_init(&dev_priv->fb_tracking.lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index f6f9675848b8..1753c84d6c0d 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -30,15 +30,18 @@
 
 #include <drm/drm_drv.h>
 
+#include "i915_utils.h"
+
 struct drm_i915_private;
 
 #ifdef CONFIG_DRM_I915_DEBUG_GEM
 
-#define GEM_SHOW_DEBUG() (drm_debug & DRM_UT_DRIVER)
+#define GEM_SHOW_DEBUG() drm_debug_enabled(DRM_UT_DRIVER)
 
 #define GEM_BUG_ON(condition) do { if (unlikely((condition))) {	\
 		GEM_TRACE_ERR("%s:%d GEM_BUG_ON(%s)\n", \
 			      __func__, __LINE__, __stringify(condition)); \
+		GEM_TRACE_DUMP(); \
 		BUG(); \
 		} \
 	} while(0)
@@ -68,9 +71,10 @@ struct drm_i915_private;
 	pr_err(__VA_ARGS__);						\
 	trace_printk(__VA_ARGS__);					\
 } while (0)
-#define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL)
+#define GEM_TRACE_DUMP() \
+	do { ftrace_dump(DUMP_ALL); add_taint_for_CI(TAINT_WARN); } while (0)
 #define GEM_TRACE_DUMP_ON(expr) \
-	do { if (expr) ftrace_dump(DUMP_ALL); } while (0)
+	do { if (expr) GEM_TRACE_DUMP(); } while (0)
 #else
 #define GEM_TRACE(...) do { } while (0)
 #define GEM_TRACE_ERR(...) do { } while (0)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 7e62c310290f..0697bedebeef 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -359,9 +359,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
  */
 int i915_gem_evict_vm(struct i915_address_space *vm)
 {
-	struct list_head eviction_list;
-	struct i915_vma *vma, *next;
-	int ret;
+	int ret = 0;
 
 	lockdep_assert_held(&vm->mutex);
 	trace_i915_gem_evict_vm(vm);
@@ -377,21 +375,30 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 			return ret;
 	}
 
-	INIT_LIST_HEAD(&eviction_list);
-	list_for_each_entry(vma, &vm->bound_list, vm_link) {
-		if (i915_vma_is_pinned(vma))
-			continue;
+	do {
+		struct i915_vma *vma, *vn;
+		LIST_HEAD(eviction_list);
 
-		__i915_vma_pin(vma);
-		list_add(&vma->evict_link, &eviction_list);
-	}
+		list_for_each_entry(vma, &vm->bound_list, vm_link) {
+			if (i915_vma_is_pinned(vma))
+				continue;
+
+			__i915_vma_pin(vma);
+			list_add(&vma->evict_link, &eviction_list);
+		}
+		if (list_empty(&eviction_list))
+			break;
+
+		ret = 0;
+		list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
+			__i915_vma_unpin(vma);
+			if (ret == 0)
+				ret = __i915_vma_unbind(vma);
+			if (ret != -EINTR) /* "Get me out of here!" */
+				ret = 0;
+		}
+	} while (ret == 0);
 
-	ret = 0;
-	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
-		__i915_vma_unpin(vma);
-		if (ret == 0)
-			ret = __i915_vma_unbind(vma);
-	}
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 71efccfde122..d9c34a23cd67 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -412,6 +412,9 @@ int i915_vma_pin_fence(struct i915_vma *vma)
 {
 	int err;
 
+	if (!vma->fence && !i915_gem_object_is_tiled(vma->obj))
+		return 0;
+
 	/*
 	 * Note that we revoke fences on runtime suspend. Therefore the user
 	 * must keep the device awake whilst using the fence.
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d6ce57d30958..e039eb56900f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1,26 +1,7 @@
+// SPDX-License-Identifier: MIT
 /*
  * Copyright © 2010 Daniel Vetter
- * Copyright © 2011-2014 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
+ * Copyright © 2020 Intel Corporation
  */
 
 #include <linux/slab.h> /* fault-inject.h is not standalone! */
@@ -45,2098 +26,6 @@
 #include "i915_trace.h"
 #include "i915_vgpu.h"
 
-#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
-
-#if IS_ENABLED(CONFIG_DRM_I915_TRACE_GTT)
-#define DBG(...) trace_printk(__VA_ARGS__)
-#else
-#define DBG(...)
-#endif
-
-/**
- * DOC: Global GTT views
- *
- * Background and previous state
- *
- * Historically objects could exists (be bound) in global GTT space only as
- * singular instances with a view representing all of the object's backing pages
- * in a linear fashion. This view will be called a normal view.
- *
- * To support multiple views of the same object, where the number of mapped
- * pages is not equal to the backing store, or where the layout of the pages
- * is not linear, concept of a GGTT view was added.
- *
- * One example of an alternative view is a stereo display driven by a single
- * image. In this case we would have a framebuffer looking like this
- * (2x2 pages):
- *
- *    12
- *    34
- *
- * Above would represent a normal GGTT view as normally mapped for GPU or CPU
- * rendering. In contrast, fed to the display engine would be an alternative
- * view which could look something like this:
- *
- *   1212
- *   3434
- *
- * In this example both the size and layout of pages in the alternative view is
- * different from the normal view.
- *
- * Implementation and usage
- *
- * GGTT views are implemented using VMAs and are distinguished via enum
- * i915_ggtt_view_type and struct i915_ggtt_view.
- *
- * A new flavour of core GEM functions which work with GGTT bound objects were
- * added with the _ggtt_ infix, and sometimes with _view postfix to avoid
- * renaming  in large amounts of code. They take the struct i915_ggtt_view
- * parameter encapsulating all metadata required to implement a view.
- *
- * As a helper for callers which are only interested in the normal view,
- * globally const i915_ggtt_view_normal singleton instance exists. All old core
- * GEM API functions, the ones not taking the view parameter, are operating on,
- * or with the normal GGTT view.
- *
- * Code wanting to add or use a new GGTT view needs to:
- *
- * 1. Add a new enum with a suitable name.
- * 2. Extend the metadata in the i915_ggtt_view structure if required.
- * 3. Add support to i915_get_vma_pages().
- *
- * New views are required to build a scatter-gather table from within the
- * i915_get_vma_pages function. This table is stored in the vma.ggtt_view and
- * exists for the lifetime of an VMA.
- *
- * Core API is designed to have copy semantics which means that passed in
- * struct i915_ggtt_view does not need to be persistent (left around after
- * calling the core API functions).
- *
- */
-
-#define as_pd(x) container_of((x), typeof(struct i915_page_directory), pt)
-
-static int
-i915_get_ggtt_vma_pages(struct i915_vma *vma);
-
-static void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
-	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
-
-	/*
-	 * Note that as an uncached mmio write, this will flush the
-	 * WCB of the writes into the GGTT before it triggers the invalidate.
-	 */
-	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
-}
-
-static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
-	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
-	struct drm_i915_private *i915 = ggtt->vm.i915;
-
-	gen6_ggtt_invalidate(ggtt);
-
-	if (INTEL_GEN(i915) >= 12)
-		intel_uncore_write_fw(uncore, GEN12_GUC_TLB_INV_CR,
-				      GEN12_GUC_TLB_INV_CR_INVALIDATE);
-	else
-		intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
-}
-
-static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
-{
-	intel_gtt_chipset_flush();
-}
-
-static int ppgtt_bind_vma(struct i915_vma *vma,
-			  enum i915_cache_level cache_level,
-			  u32 flags)
-{
-	u32 pte_flags;
-	int err;
-
-	if (flags & I915_VMA_ALLOC) {
-		err = vma->vm->allocate_va_range(vma->vm,
-						 vma->node.start, vma->size);
-		if (err)
-			return err;
-
-		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
-	}
-
-	/* Applicable to VLV, and gen8+ */
-	pte_flags = 0;
-	if (i915_gem_object_is_readonly(vma->obj))
-		pte_flags |= PTE_READ_ONLY;
-
-	GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)));
-	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-	wmb();
-
-	return 0;
-}
-
-static void ppgtt_unbind_vma(struct i915_vma *vma)
-{
-	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)))
-		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-}
-
-static int ppgtt_set_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(vma->pages);
-
-	vma->pages = vma->obj->mm.pages;
-
-	vma->page_sizes = vma->obj->mm.page_sizes;
-
-	return 0;
-}
-
-static void clear_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(!vma->pages);
-
-	if (vma->pages != vma->obj->mm.pages) {
-		sg_free_table(vma->pages);
-		kfree(vma->pages);
-	}
-	vma->pages = NULL;
-
-	memset(&vma->page_sizes, 0, sizeof(vma->page_sizes));
-}
-
-static u64 gen8_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
-			   u32 flags)
-{
-	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
-
-	if (unlikely(flags & PTE_READ_ONLY))
-		pte &= ~_PAGE_RW;
-
-	switch (level) {
-	case I915_CACHE_NONE:
-		pte |= PPAT_UNCACHED;
-		break;
-	case I915_CACHE_WT:
-		pte |= PPAT_DISPLAY_ELLC;
-		break;
-	default:
-		pte |= PPAT_CACHED;
-		break;
-	}
-
-	return pte;
-}
-
-static u64 gen8_pde_encode(const dma_addr_t addr,
-			   const enum i915_cache_level level)
-{
-	u64 pde = _PAGE_PRESENT | _PAGE_RW;
-	pde |= addr;
-	if (level != I915_CACHE_NONE)
-		pde |= PPAT_CACHED_PDE;
-	else
-		pde |= PPAT_UNCACHED;
-	return pde;
-}
-
-static u64 snb_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
-
-	switch (level) {
-	case I915_CACHE_L3_LLC:
-	case I915_CACHE_LLC:
-		pte |= GEN6_PTE_CACHE_LLC;
-		break;
-	case I915_CACHE_NONE:
-		pte |= GEN6_PTE_UNCACHED;
-		break;
-	default:
-		MISSING_CASE(level);
-	}
-
-	return pte;
-}
-
-static u64 ivb_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
-
-	switch (level) {
-	case I915_CACHE_L3_LLC:
-		pte |= GEN7_PTE_CACHE_L3_LLC;
-		break;
-	case I915_CACHE_LLC:
-		pte |= GEN6_PTE_CACHE_LLC;
-		break;
-	case I915_CACHE_NONE:
-		pte |= GEN6_PTE_UNCACHED;
-		break;
-	default:
-		MISSING_CASE(level);
-	}
-
-	return pte;
-}
-
-static u64 byt_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= GEN6_PTE_ADDR_ENCODE(addr);
-
-	if (!(flags & PTE_READ_ONLY))
-		pte |= BYT_PTE_WRITEABLE;
-
-	if (level != I915_CACHE_NONE)
-		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
-
-	return pte;
-}
-
-static u64 hsw_pte_encode(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= HSW_PTE_ADDR_ENCODE(addr);
-
-	if (level != I915_CACHE_NONE)
-		pte |= HSW_WB_LLC_AGE3;
-
-	return pte;
-}
-
-static u64 iris_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
-			   u32 flags)
-{
-	gen6_pte_t pte = GEN6_PTE_VALID;
-	pte |= HSW_PTE_ADDR_ENCODE(addr);
-
-	switch (level) {
-	case I915_CACHE_NONE:
-		break;
-	case I915_CACHE_WT:
-		pte |= HSW_WT_ELLC_LLC_AGE3;
-		break;
-	default:
-		pte |= HSW_WB_ELLC_LLC_AGE3;
-		break;
-	}
-
-	return pte;
-}
-
-static void stash_init(struct pagestash *stash)
-{
-	pagevec_init(&stash->pvec);
-	spin_lock_init(&stash->lock);
-}
-
-static struct page *stash_pop_page(struct pagestash *stash)
-{
-	struct page *page = NULL;
-
-	spin_lock(&stash->lock);
-	if (likely(stash->pvec.nr))
-		page = stash->pvec.pages[--stash->pvec.nr];
-	spin_unlock(&stash->lock);
-
-	return page;
-}
-
-static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
-{
-	unsigned int nr;
-
-	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
-
-	nr = min_t(typeof(nr), pvec->nr, pagevec_space(&stash->pvec));
-	memcpy(stash->pvec.pages + stash->pvec.nr,
-	       pvec->pages + pvec->nr - nr,
-	       sizeof(pvec->pages[0]) * nr);
-	stash->pvec.nr += nr;
-
-	spin_unlock(&stash->lock);
-
-	pvec->nr -= nr;
-}
-
-static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
-{
-	struct pagevec stack;
-	struct page *page;
-
-	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
-		i915_gem_shrink_all(vm->i915);
-
-	page = stash_pop_page(&vm->free_pages);
-	if (page)
-		return page;
-
-	if (!vm->pt_kmap_wc)
-		return alloc_page(gfp);
-
-	/* Look in our global stash of WC pages... */
-	page = stash_pop_page(&vm->i915->mm.wc_stash);
-	if (page)
-		return page;
-
-	/*
-	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
-	 *
-	 * We have to be careful as page allocation may trigger the shrinker
-	 * (via direct reclaim) which will fill up the WC stash underneath us.
-	 * So we add our WB pages into a temporary pvec on the stack and merge
-	 * them into the WC stash after all the allocations are complete.
-	 */
-	pagevec_init(&stack);
-	do {
-		struct page *page;
-
-		page = alloc_page(gfp);
-		if (unlikely(!page))
-			break;
-
-		stack.pages[stack.nr++] = page;
-	} while (pagevec_space(&stack));
-
-	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
-		page = stack.pages[--stack.nr];
-
-		/* Merge spare WC pages to the global stash */
-		if (stack.nr)
-			stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
-
-		/* Push any surplus WC pages onto the local VM stash */
-		if (stack.nr)
-			stash_push_pagevec(&vm->free_pages, &stack);
-	}
-
-	/* Return unwanted leftovers */
-	if (unlikely(stack.nr)) {
-		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
-		__pagevec_release(&stack);
-	}
-
-	return page;
-}
-
-static void vm_free_pages_release(struct i915_address_space *vm,
-				  bool immediate)
-{
-	struct pagevec *pvec = &vm->free_pages.pvec;
-	struct pagevec stack;
-
-	lockdep_assert_held(&vm->free_pages.lock);
-	GEM_BUG_ON(!pagevec_count(pvec));
-
-	if (vm->pt_kmap_wc) {
-		/*
-		 * When we use WC, first fill up the global stash and then
-		 * only if full immediately free the overflow.
-		 */
-		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
-
-		/*
-		 * As we have made some room in the VM's free_pages,
-		 * we can wait for it to fill again. Unless we are
-		 * inside i915_address_space_fini() and must
-		 * immediately release the pages!
-		 */
-		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
-			return;
-
-		/*
-		 * We have to drop the lock to allow ourselves to sleep,
-		 * so take a copy of the pvec and clear the stash for
-		 * others to use it as we sleep.
-		 */
-		stack = *pvec;
-		pagevec_reinit(pvec);
-		spin_unlock(&vm->free_pages.lock);
-
-		pvec = &stack;
-		set_pages_array_wb(pvec->pages, pvec->nr);
-
-		spin_lock(&vm->free_pages.lock);
-	}
-
-	__pagevec_release(pvec);
-}
-
-static void vm_free_page(struct i915_address_space *vm, struct page *page)
-{
-	/*
-	 * On !llc, we need to change the pages back to WB. We only do so
-	 * in bulk, so we rarely need to change the page attributes here,
-	 * but doing so requires a stop_machine() from deep inside arch/x86/mm.
-	 * To make detection of the possible sleep more likely, use an
-	 * unconditional might_sleep() for everybody.
-	 */
-	might_sleep();
-	spin_lock(&vm->free_pages.lock);
-	while (!pagevec_space(&vm->free_pages.pvec))
-		vm_free_pages_release(vm, false);
-	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec) >= PAGEVEC_SIZE);
-	pagevec_add(&vm->free_pages.pvec, page);
-	spin_unlock(&vm->free_pages.lock);
-}
-
-static void i915_address_space_fini(struct i915_address_space *vm)
-{
-	spin_lock(&vm->free_pages.lock);
-	if (pagevec_count(&vm->free_pages.pvec))
-		vm_free_pages_release(vm, true);
-	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
-	spin_unlock(&vm->free_pages.lock);
-
-	drm_mm_takedown(&vm->mm);
-
-	mutex_destroy(&vm->mutex);
-}
-
-void __i915_vm_close(struct i915_address_space *vm)
-{
-	struct i915_vma *vma, *vn;
-
-	mutex_lock(&vm->mutex);
-	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		/* Keep the obj (and hence the vma) alive as _we_ destroy it */
-		if (!kref_get_unless_zero(&obj->base.refcount))
-			continue;
-
-		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
-		WARN_ON(__i915_vma_unbind(vma));
-		i915_vma_destroy(vma);
-
-		i915_gem_object_put(obj);
-	}
-	GEM_BUG_ON(!list_empty(&vm->bound_list));
-	mutex_unlock(&vm->mutex);
-}
-
-static void __i915_vm_release(struct work_struct *work)
-{
-	struct i915_address_space *vm =
-		container_of(work, struct i915_address_space, rcu.work);
-
-	vm->cleanup(vm);
-	i915_address_space_fini(vm);
-
-	kfree(vm);
-}
-
-void i915_vm_release(struct kref *kref)
-{
-	struct i915_address_space *vm =
-		container_of(kref, struct i915_address_space, ref);
-
-	GEM_BUG_ON(i915_is_ggtt(vm));
-	trace_i915_ppgtt_release(vm);
-
-	queue_rcu_work(vm->i915->wq, &vm->rcu);
-}
-
-static void i915_address_space_init(struct i915_address_space *vm, int subclass)
-{
-	kref_init(&vm->ref);
-	INIT_RCU_WORK(&vm->rcu, __i915_vm_release);
-	atomic_set(&vm->open, 1);
-
-	/*
-	 * The vm->mutex must be reclaim safe (for use in the shrinker).
-	 * Do a dummy acquire now under fs_reclaim so that any allocation
-	 * attempt holding the lock is immediately reported by lockdep.
-	 */
-	mutex_init(&vm->mutex);
-	lockdep_set_subclass(&vm->mutex, subclass);
-	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
-
-	GEM_BUG_ON(!vm->total);
-	drm_mm_init(&vm->mm, 0, vm->total);
-	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
-
-	stash_init(&vm->free_pages);
-
-	INIT_LIST_HEAD(&vm->bound_list);
-}
-
-static int __setup_page_dma(struct i915_address_space *vm,
-			    struct i915_page_dma *p,
-			    gfp_t gfp)
-{
-	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
-	if (unlikely(!p->page))
-		return -ENOMEM;
-
-	p->daddr = dma_map_page_attrs(vm->dma,
-				      p->page, 0, PAGE_SIZE,
-				      PCI_DMA_BIDIRECTIONAL,
-				      DMA_ATTR_SKIP_CPU_SYNC |
-				      DMA_ATTR_NO_WARN);
-	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
-		vm_free_page(vm, p->page);
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static int setup_page_dma(struct i915_address_space *vm,
-			  struct i915_page_dma *p)
-{
-	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
-}
-
-static void cleanup_page_dma(struct i915_address_space *vm,
-			     struct i915_page_dma *p)
-{
-	dma_unmap_page(vm->dma, p->daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	vm_free_page(vm, p->page);
-}
-
-#define kmap_atomic_px(px) kmap_atomic(px_base(px)->page)
-
-static void
-fill_page_dma(const struct i915_page_dma *p, const u64 val, unsigned int count)
-{
-	kunmap_atomic(memset64(kmap_atomic(p->page), val, count));
-}
-
-#define fill_px(px, v) fill_page_dma(px_base(px), (v), PAGE_SIZE / sizeof(u64))
-#define fill32_px(px, v) do {						\
-	u64 v__ = lower_32_bits(v);					\
-	fill_px((px), v__ << 32 | v__);					\
-} while (0)
-
-static int
-setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
-{
-	unsigned long size;
-
-	/*
-	 * In order to utilize 64K pages for an object with a size < 2M, we will
-	 * need to support a 64K scratch page, given that every 16th entry for a
-	 * page-table operating in 64K mode must point to a properly aligned 64K
-	 * region, including any PTEs which happen to point to scratch.
-	 *
-	 * This is only relevant for the 48b PPGTT where we support
-	 * huge-gtt-pages, see also i915_vma_insert(). However, as we share the
-	 * scratch (read-only) between all vm, we create one 64k scratch page
-	 * for all.
-	 */
-	size = I915_GTT_PAGE_SIZE_4K;
-	if (i915_vm_is_4lvl(vm) &&
-	    HAS_PAGE_SIZES(vm->i915, I915_GTT_PAGE_SIZE_64K)) {
-		size = I915_GTT_PAGE_SIZE_64K;
-		gfp |= __GFP_NOWARN;
-	}
-	gfp |= __GFP_ZERO | __GFP_RETRY_MAYFAIL;
-
-	do {
-		unsigned int order = get_order(size);
-		struct page *page;
-		dma_addr_t addr;
-
-		page = alloc_pages(gfp, order);
-		if (unlikely(!page))
-			goto skip;
-
-		addr = dma_map_page_attrs(vm->dma,
-					  page, 0, size,
-					  PCI_DMA_BIDIRECTIONAL,
-					  DMA_ATTR_SKIP_CPU_SYNC |
-					  DMA_ATTR_NO_WARN);
-		if (unlikely(dma_mapping_error(vm->dma, addr)))
-			goto free_page;
-
-		if (unlikely(!IS_ALIGNED(addr, size)))
-			goto unmap_page;
-
-		vm->scratch[0].base.page = page;
-		vm->scratch[0].base.daddr = addr;
-		vm->scratch_order = order;
-		return 0;
-
-unmap_page:
-		dma_unmap_page(vm->dma, addr, size, PCI_DMA_BIDIRECTIONAL);
-free_page:
-		__free_pages(page, order);
-skip:
-		if (size == I915_GTT_PAGE_SIZE_4K)
-			return -ENOMEM;
-
-		size = I915_GTT_PAGE_SIZE_4K;
-		gfp &= ~__GFP_NOWARN;
-	} while (1);
-}
-
-static void cleanup_scratch_page(struct i915_address_space *vm)
-{
-	struct i915_page_dma *p = px_base(&vm->scratch[0]);
-	unsigned int order = vm->scratch_order;
-
-	dma_unmap_page(vm->dma, p->daddr, BIT(order) << PAGE_SHIFT,
-		       PCI_DMA_BIDIRECTIONAL);
-	__free_pages(p->page, order);
-}
-
-static void free_scratch(struct i915_address_space *vm)
-{
-	int i;
-
-	if (!px_dma(&vm->scratch[0])) /* set to 0 on clones */
-		return;
-
-	for (i = 1; i <= vm->top; i++) {
-		if (!px_dma(&vm->scratch[i]))
-			break;
-		cleanup_page_dma(vm, px_base(&vm->scratch[i]));
-	}
-
-	cleanup_scratch_page(vm);
-}
-
-static struct i915_page_table *alloc_pt(struct i915_address_space *vm)
-{
-	struct i915_page_table *pt;
-
-	pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL);
-	if (unlikely(!pt))
-		return ERR_PTR(-ENOMEM);
-
-	if (unlikely(setup_page_dma(vm, &pt->base))) {
-		kfree(pt);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	atomic_set(&pt->used, 0);
-	return pt;
-}
-
-static struct i915_page_directory *__alloc_pd(size_t sz)
-{
-	struct i915_page_directory *pd;
-
-	pd = kzalloc(sz, I915_GFP_ALLOW_FAIL);
-	if (unlikely(!pd))
-		return NULL;
-
-	spin_lock_init(&pd->lock);
-	return pd;
-}
-
-static struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
-{
-	struct i915_page_directory *pd;
-
-	pd = __alloc_pd(sizeof(*pd));
-	if (unlikely(!pd))
-		return ERR_PTR(-ENOMEM);
-
-	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
-		kfree(pd);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	return pd;
-}
-
-static void free_pd(struct i915_address_space *vm, struct i915_page_dma *pd)
-{
-	cleanup_page_dma(vm, pd);
-	kfree(pd);
-}
-
-#define free_px(vm, px) free_pd(vm, px_base(px))
-
-static inline void
-write_dma_entry(struct i915_page_dma * const pdma,
-		const unsigned short idx,
-		const u64 encoded_entry)
-{
-	u64 * const vaddr = kmap_atomic(pdma->page);
-
-	vaddr[idx] = encoded_entry;
-	kunmap_atomic(vaddr);
-}
-
-static inline void
-__set_pd_entry(struct i915_page_directory * const pd,
-	       const unsigned short idx,
-	       struct i915_page_dma * const to,
-	       u64 (*encode)(const dma_addr_t, const enum i915_cache_level))
-{
-	/* Each thread pre-pins the pd, and we may have a thread per pde. */
-	GEM_BUG_ON(atomic_read(px_used(pd)) > 2 * ARRAY_SIZE(pd->entry));
-
-	atomic_inc(px_used(pd));
-	pd->entry[idx] = to;
-	write_dma_entry(px_base(pd), idx, encode(to->daddr, I915_CACHE_LLC));
-}
-
-#define set_pd_entry(pd, idx, to) \
-	__set_pd_entry((pd), (idx), px_base(to), gen8_pde_encode)
-
-static inline void
-clear_pd_entry(struct i915_page_directory * const pd,
-	       const unsigned short idx,
-	       const struct i915_page_scratch * const scratch)
-{
-	GEM_BUG_ON(atomic_read(px_used(pd)) == 0);
-
-	write_dma_entry(px_base(pd), idx, scratch->encode);
-	pd->entry[idx] = NULL;
-	atomic_dec(px_used(pd));
-}
-
-static bool
-release_pd_entry(struct i915_page_directory * const pd,
-		 const unsigned short idx,
-		 struct i915_page_table * const pt,
-		 const struct i915_page_scratch * const scratch)
-{
-	bool free = false;
-
-	if (atomic_add_unless(&pt->used, -1, 1))
-		return false;
-
-	spin_lock(&pd->lock);
-	if (atomic_dec_and_test(&pt->used)) {
-		clear_pd_entry(pd, idx, scratch);
-		free = true;
-	}
-	spin_unlock(&pd->lock);
-
-	return free;
-}
-
-static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
-{
-	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
-	enum vgt_g2v_type msg;
-	int i;
-
-	if (create)
-		atomic_inc(px_used(ppgtt->pd)); /* never remove */
-	else
-		atomic_dec(px_used(ppgtt->pd));
-
-	mutex_lock(&dev_priv->vgpu.lock);
-
-	if (i915_vm_is_4lvl(&ppgtt->vm)) {
-		const u64 daddr = px_dma(ppgtt->pd);
-
-		I915_WRITE(vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
-		I915_WRITE(vgtif_reg(pdp[0].hi), upper_32_bits(daddr));
-
-		msg = (create ? VGT_G2V_PPGTT_L4_PAGE_TABLE_CREATE :
-				VGT_G2V_PPGTT_L4_PAGE_TABLE_DESTROY);
-	} else {
-		for (i = 0; i < GEN8_3LVL_PDPES; i++) {
-			const u64 daddr = i915_page_dir_dma_addr(ppgtt, i);
-
-			I915_WRITE(vgtif_reg(pdp[i].lo), lower_32_bits(daddr));
-			I915_WRITE(vgtif_reg(pdp[i].hi), upper_32_bits(daddr));
-		}
-
-		msg = (create ? VGT_G2V_PPGTT_L3_PAGE_TABLE_CREATE :
-				VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY);
-	}
-
-	/* g2v_notify atomically (via hv trap) consumes the message packet. */
-	I915_WRITE(vgtif_reg(g2v_notify), msg);
-
-	mutex_unlock(&dev_priv->vgpu.lock);
-}
-
-/* Index shifts into the pagetable are offset by GEN8_PTE_SHIFT [12] */
-#define GEN8_PAGE_SIZE (SZ_4K) /* page and page-directory sizes are the same */
-#define GEN8_PTE_SHIFT (ilog2(GEN8_PAGE_SIZE))
-#define GEN8_PDES (GEN8_PAGE_SIZE / sizeof(u64))
-#define gen8_pd_shift(lvl) ((lvl) * ilog2(GEN8_PDES))
-#define gen8_pd_index(i, lvl) i915_pde_index((i), gen8_pd_shift(lvl))
-#define __gen8_pte_shift(lvl) (GEN8_PTE_SHIFT + gen8_pd_shift(lvl))
-#define __gen8_pte_index(a, lvl) i915_pde_index((a), __gen8_pte_shift(lvl))
-
-static inline unsigned int
-gen8_pd_range(u64 start, u64 end, int lvl, unsigned int *idx)
-{
-	const int shift = gen8_pd_shift(lvl);
-	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
-
-	GEM_BUG_ON(start >= end);
-	end += ~mask >> gen8_pd_shift(1);
-
-	*idx = i915_pde_index(start, shift);
-	if ((start ^ end) & mask)
-		return GEN8_PDES - *idx;
-	else
-		return i915_pde_index(end, shift) - *idx;
-}
-
-static inline bool gen8_pd_contains(u64 start, u64 end, int lvl)
-{
-	const u64 mask = ~0ull << gen8_pd_shift(lvl + 1);
-
-	GEM_BUG_ON(start >= end);
-	return (start ^ end) & mask && (start & ~mask) == 0;
-}
-
-static inline unsigned int gen8_pt_count(u64 start, u64 end)
-{
-	GEM_BUG_ON(start >= end);
-	if ((start ^ end) >> gen8_pd_shift(1))
-		return GEN8_PDES - (start & (GEN8_PDES - 1));
-	else
-		return end - start;
-}
-
-static inline unsigned int gen8_pd_top_count(const struct i915_address_space *vm)
-{
-	unsigned int shift = __gen8_pte_shift(vm->top);
-	return (vm->total + (1ull << shift) - 1) >> shift;
-}
-
-static inline struct i915_page_directory *
-gen8_pdp_for_page_index(struct i915_address_space * const vm, const u64 idx)
-{
-	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
-
-	if (vm->top == 2)
-		return ppgtt->pd;
-	else
-		return i915_pd_entry(ppgtt->pd, gen8_pd_index(idx, vm->top));
-}
-
-static inline struct i915_page_directory *
-gen8_pdp_for_page_address(struct i915_address_space * const vm, const u64 addr)
-{
-	return gen8_pdp_for_page_index(vm, addr >> GEN8_PTE_SHIFT);
-}
-
-static void __gen8_ppgtt_cleanup(struct i915_address_space *vm,
-				 struct i915_page_directory *pd,
-				 int count, int lvl)
-{
-	if (lvl) {
-		void **pde = pd->entry;
-
-		do {
-			if (!*pde)
-				continue;
-
-			__gen8_ppgtt_cleanup(vm, *pde, GEN8_PDES, lvl - 1);
-		} while (pde++, --count);
-	}
-
-	free_px(vm, pd);
-}
-
-static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
-{
-	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-
-	if (intel_vgpu_active(vm->i915))
-		gen8_ppgtt_notify_vgt(ppgtt, false);
-
-	__gen8_ppgtt_cleanup(vm, ppgtt->pd, gen8_pd_top_count(vm), vm->top);
-	free_scratch(vm);
-}
-
-static u64 __gen8_ppgtt_clear(struct i915_address_space * const vm,
-			      struct i915_page_directory * const pd,
-			      u64 start, const u64 end, int lvl)
-{
-	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
-	unsigned int idx, len;
-
-	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
-
-	len = gen8_pd_range(start, end, lvl--, &idx);
-	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
-	    __func__, vm, lvl + 1, start, end,
-	    idx, len, atomic_read(px_used(pd)));
-	GEM_BUG_ON(!len || len >= atomic_read(px_used(pd)));
-
-	do {
-		struct i915_page_table *pt = pd->entry[idx];
-
-		if (atomic_fetch_inc(&pt->used) >> gen8_pd_shift(1) &&
-		    gen8_pd_contains(start, end, lvl)) {
-			DBG("%s(%p):{ lvl:%d, idx:%d, start:%llx, end:%llx } removing pd\n",
-			    __func__, vm, lvl + 1, idx, start, end);
-			clear_pd_entry(pd, idx, scratch);
-			__gen8_ppgtt_cleanup(vm, as_pd(pt), I915_PDES, lvl);
-			start += (u64)I915_PDES << gen8_pd_shift(lvl);
-			continue;
-		}
-
-		if (lvl) {
-			start = __gen8_ppgtt_clear(vm, as_pd(pt),
-						   start, end, lvl);
-		} else {
-			unsigned int count;
-			u64 *vaddr;
-
-			count = gen8_pt_count(start, end);
-			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } removing pte\n",
-			    __func__, vm, lvl, start, end,
-			    gen8_pd_index(start, 0), count,
-			    atomic_read(&pt->used));
-			GEM_BUG_ON(!count || count >= atomic_read(&pt->used));
-
-			vaddr = kmap_atomic_px(pt);
-			memset64(vaddr + gen8_pd_index(start, 0),
-				 vm->scratch[0].encode,
-				 count);
-			kunmap_atomic(vaddr);
-
-			atomic_sub(count, &pt->used);
-			start += count;
-		}
-
-		if (release_pd_entry(pd, idx, pt, scratch))
-			free_px(vm, pt);
-	} while (idx++, --len);
-
-	return start;
-}
-
-static void gen8_ppgtt_clear(struct i915_address_space *vm,
-			     u64 start, u64 length)
-{
-	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(range_overflows(start, length, vm->total));
-
-	start >>= GEN8_PTE_SHIFT;
-	length >>= GEN8_PTE_SHIFT;
-	GEM_BUG_ON(length == 0);
-
-	__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
-			   start, start + length, vm->top);
-}
-
-static int __gen8_ppgtt_alloc(struct i915_address_space * const vm,
-			      struct i915_page_directory * const pd,
-			      u64 * const start, const u64 end, int lvl)
-{
-	const struct i915_page_scratch * const scratch = &vm->scratch[lvl];
-	struct i915_page_table *alloc = NULL;
-	unsigned int idx, len;
-	int ret = 0;
-
-	GEM_BUG_ON(end > vm->total >> GEN8_PTE_SHIFT);
-
-	len = gen8_pd_range(*start, end, lvl--, &idx);
-	DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d }\n",
-	    __func__, vm, lvl + 1, *start, end,
-	    idx, len, atomic_read(px_used(pd)));
-	GEM_BUG_ON(!len || (idx + len - 1) >> gen8_pd_shift(1));
-
-	spin_lock(&pd->lock);
-	GEM_BUG_ON(!atomic_read(px_used(pd))); /* Must be pinned! */
-	do {
-		struct i915_page_table *pt = pd->entry[idx];
-
-		if (!pt) {
-			spin_unlock(&pd->lock);
-
-			DBG("%s(%p):{ lvl:%d, idx:%d } allocating new tree\n",
-			    __func__, vm, lvl + 1, idx);
-
-			pt = fetch_and_zero(&alloc);
-			if (lvl) {
-				if (!pt) {
-					pt = &alloc_pd(vm)->pt;
-					if (IS_ERR(pt)) {
-						ret = PTR_ERR(pt);
-						goto out;
-					}
-				}
-
-				fill_px(pt, vm->scratch[lvl].encode);
-			} else {
-				if (!pt) {
-					pt = alloc_pt(vm);
-					if (IS_ERR(pt)) {
-						ret = PTR_ERR(pt);
-						goto out;
-					}
-				}
-
-				if (intel_vgpu_active(vm->i915) ||
-				    gen8_pt_count(*start, end) < I915_PDES)
-					fill_px(pt, vm->scratch[lvl].encode);
-			}
-
-			spin_lock(&pd->lock);
-			if (likely(!pd->entry[idx]))
-				set_pd_entry(pd, idx, pt);
-			else
-				alloc = pt, pt = pd->entry[idx];
-		}
-
-		if (lvl) {
-			atomic_inc(&pt->used);
-			spin_unlock(&pd->lock);
-
-			ret = __gen8_ppgtt_alloc(vm, as_pd(pt),
-						 start, end, lvl);
-			if (unlikely(ret)) {
-				if (release_pd_entry(pd, idx, pt, scratch))
-					free_px(vm, pt);
-				goto out;
-			}
-
-			spin_lock(&pd->lock);
-			atomic_dec(&pt->used);
-			GEM_BUG_ON(!atomic_read(&pt->used));
-		} else {
-			unsigned int count = gen8_pt_count(*start, end);
-
-			DBG("%s(%p):{ lvl:%d, start:%llx, end:%llx, idx:%d, len:%d, used:%d } inserting pte\n",
-			    __func__, vm, lvl, *start, end,
-			    gen8_pd_index(*start, 0), count,
-			    atomic_read(&pt->used));
-
-			atomic_add(count, &pt->used);
-			/* All other pdes may be simultaneously removed */
-			GEM_BUG_ON(atomic_read(&pt->used) > 2 * I915_PDES);
-			*start += count;
-		}
-	} while (idx++, --len);
-	spin_unlock(&pd->lock);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	return ret;
-}
-
-static int gen8_ppgtt_alloc(struct i915_address_space *vm,
-			    u64 start, u64 length)
-{
-	u64 from;
-	int err;
-
-	GEM_BUG_ON(!IS_ALIGNED(start, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(!IS_ALIGNED(length, BIT_ULL(GEN8_PTE_SHIFT)));
-	GEM_BUG_ON(range_overflows(start, length, vm->total));
-
-	start >>= GEN8_PTE_SHIFT;
-	length >>= GEN8_PTE_SHIFT;
-	GEM_BUG_ON(length == 0);
-	from = start;
-
-	err = __gen8_ppgtt_alloc(vm, i915_vm_to_ppgtt(vm)->pd,
-				 &start, start + length, vm->top);
-	if (unlikely(err && from != start))
-		__gen8_ppgtt_clear(vm, i915_vm_to_ppgtt(vm)->pd,
-				   from, start, vm->top);
-
-	return err;
-}
-
-static inline struct sgt_dma {
-	struct scatterlist *sg;
-	dma_addr_t dma, max;
-} sgt_dma(struct i915_vma *vma) {
-	struct scatterlist *sg = vma->pages->sgl;
-	dma_addr_t addr = sg_dma_address(sg);
-	return (struct sgt_dma) { sg, addr, addr + sg->length };
-}
-
-static __always_inline u64
-gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
-		      struct i915_page_directory *pdp,
-		      struct sgt_dma *iter,
-		      u64 idx,
-		      enum i915_cache_level cache_level,
-		      u32 flags)
-{
-	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
-	gen8_pte_t *vaddr;
-
-	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
-	vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
-	do {
-		GEM_BUG_ON(iter->sg->length < I915_GTT_PAGE_SIZE);
-		vaddr[gen8_pd_index(idx, 0)] = pte_encode | iter->dma;
-
-		iter->dma += I915_GTT_PAGE_SIZE;
-		if (iter->dma >= iter->max) {
-			iter->sg = __sg_next(iter->sg);
-			if (!iter->sg) {
-				idx = 0;
-				break;
-			}
-
-			iter->dma = sg_dma_address(iter->sg);
-			iter->max = iter->dma + iter->sg->length;
-		}
-
-		if (gen8_pd_index(++idx, 0) == 0) {
-			if (gen8_pd_index(idx, 1) == 0) {
-				/* Limited by sg length for 3lvl */
-				if (gen8_pd_index(idx, 2) == 0)
-					break;
-
-				pd = pdp->entry[gen8_pd_index(idx, 2)];
-			}
-
-			kunmap_atomic(vaddr);
-			vaddr = kmap_atomic_px(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
-		}
-	} while (1);
-	kunmap_atomic(vaddr);
-
-	return idx;
-}
-
-static void gen8_ppgtt_insert_huge(struct i915_vma *vma,
-				   struct sgt_dma *iter,
-				   enum i915_cache_level cache_level,
-				   u32 flags)
-{
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
-	u64 start = vma->node.start;
-	dma_addr_t rem = iter->sg->length;
-
-	GEM_BUG_ON(!i915_vm_is_4lvl(vma->vm));
-
-	do {
-		struct i915_page_directory * const pdp =
-			gen8_pdp_for_page_address(vma->vm, start);
-		struct i915_page_directory * const pd =
-			i915_pd_entry(pdp, __gen8_pte_index(start, 2));
-		gen8_pte_t encode = pte_encode;
-		unsigned int maybe_64K = -1;
-		unsigned int page_size;
-		gen8_pte_t *vaddr;
-		u16 index;
-
-		if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_2M &&
-		    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_2M) &&
-		    rem >= I915_GTT_PAGE_SIZE_2M &&
-		    !__gen8_pte_index(start, 0)) {
-			index = __gen8_pte_index(start, 1);
-			encode |= GEN8_PDE_PS_2M;
-			page_size = I915_GTT_PAGE_SIZE_2M;
-
-			vaddr = kmap_atomic_px(pd);
-		} else {
-			struct i915_page_table *pt =
-				i915_pt_entry(pd, __gen8_pte_index(start, 1));
-
-			index = __gen8_pte_index(start, 0);
-			page_size = I915_GTT_PAGE_SIZE;
-
-			if (!index &&
-			    vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K &&
-			    IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
-			    (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
-			     rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE))
-				maybe_64K = __gen8_pte_index(start, 1);
-
-			vaddr = kmap_atomic_px(pt);
-		}
-
-		do {
-			GEM_BUG_ON(iter->sg->length < page_size);
-			vaddr[index++] = encode | iter->dma;
-
-			start += page_size;
-			iter->dma += page_size;
-			rem -= page_size;
-			if (iter->dma >= iter->max) {
-				iter->sg = __sg_next(iter->sg);
-				if (!iter->sg)
-					break;
-
-				rem = iter->sg->length;
-				iter->dma = sg_dma_address(iter->sg);
-				iter->max = iter->dma + rem;
-
-				if (maybe_64K != -1 && index < I915_PDES &&
-				    !(IS_ALIGNED(iter->dma, I915_GTT_PAGE_SIZE_64K) &&
-				      (IS_ALIGNED(rem, I915_GTT_PAGE_SIZE_64K) ||
-				       rem >= (I915_PDES - index) * I915_GTT_PAGE_SIZE)))
-					maybe_64K = -1;
-
-				if (unlikely(!IS_ALIGNED(iter->dma, page_size)))
-					break;
-			}
-		} while (rem >= page_size && index < I915_PDES);
-
-		kunmap_atomic(vaddr);
-
-		/*
-		 * Is it safe to mark the 2M block as 64K? -- Either we have
-		 * filled whole page-table with 64K entries, or filled part of
-		 * it and have reached the end of the sg table and we have
-		 * enough padding.
-		 */
-		if (maybe_64K != -1 &&
-		    (index == I915_PDES ||
-		     (i915_vm_has_scratch_64K(vma->vm) &&
-		      !iter->sg && IS_ALIGNED(vma->node.start +
-					      vma->node.size,
-					      I915_GTT_PAGE_SIZE_2M)))) {
-			vaddr = kmap_atomic_px(pd);
-			vaddr[maybe_64K] |= GEN8_PDE_IPS_64K;
-			kunmap_atomic(vaddr);
-			page_size = I915_GTT_PAGE_SIZE_64K;
-
-			/*
-			 * We write all 4K page entries, even when using 64K
-			 * pages. In order to verify that the HW isn't cheating
-			 * by using the 4K PTE instead of the 64K PTE, we want
-			 * to remove all the surplus entries. If the HW skipped
-			 * the 64K PTE, it will read/write into the scratch page
-			 * instead - which we detect as missing results during
-			 * selftests.
-			 */
-			if (I915_SELFTEST_ONLY(vma->vm->scrub_64K)) {
-				u16 i;
-
-				encode = vma->vm->scratch[0].encode;
-				vaddr = kmap_atomic_px(i915_pt_entry(pd, maybe_64K));
-
-				for (i = 1; i < index; i += 16)
-					memset64(vaddr + i, encode, 15);
-
-				kunmap_atomic(vaddr);
-			}
-		}
-
-		vma->page_sizes.gtt |= page_size;
-	} while (iter->sg);
-}
-
-static void gen8_ppgtt_insert(struct i915_address_space *vm,
-			      struct i915_vma *vma,
-			      enum i915_cache_level cache_level,
-			      u32 flags)
-{
-	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
-	struct sgt_dma iter = sgt_dma(vma);
-
-	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		gen8_ppgtt_insert_huge(vma, &iter, cache_level, flags);
-	} else  {
-		u64 idx = vma->node.start >> GEN8_PTE_SHIFT;
-
-		do {
-			struct i915_page_directory * const pdp =
-				gen8_pdp_for_page_index(vm, idx);
-
-			idx = gen8_ppgtt_insert_pte(ppgtt, pdp, &iter, idx,
-						    cache_level, flags);
-		} while (idx);
-
-		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-	}
-}
-
-static int gen8_init_scratch(struct i915_address_space *vm)
-{
-	int ret;
-	int i;
-
-	/*
-	 * If everybody agrees to not to write into the scratch page,
-	 * we can reuse it for all vm, keeping contexts and processes separate.
-	 */
-	if (vm->has_read_only &&
-	    vm->i915->kernel_context &&
-	    vm->i915->kernel_context->vm) {
-		struct i915_address_space *clone =
-			rcu_dereference_protected(vm->i915->kernel_context->vm,
-						  true); /* static */
-
-		GEM_BUG_ON(!clone->has_read_only);
-
-		vm->scratch_order = clone->scratch_order;
-		memcpy(vm->scratch, clone->scratch, sizeof(vm->scratch));
-		px_dma(&vm->scratch[0]) = 0; /* no xfer of ownership */
-		return 0;
-	}
-
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
-	if (ret)
-		return ret;
-
-	vm->scratch[0].encode =
-		gen8_pte_encode(px_dma(&vm->scratch[0]),
-				I915_CACHE_LLC, vm->has_read_only);
-
-	for (i = 1; i <= vm->top; i++) {
-		if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[i]))))
-			goto free_scratch;
-
-		fill_px(&vm->scratch[i], vm->scratch[i - 1].encode);
-		vm->scratch[i].encode =
-			gen8_pde_encode(px_dma(&vm->scratch[i]),
-					I915_CACHE_LLC);
-	}
-
-	return 0;
-
-free_scratch:
-	free_scratch(vm);
-	return -ENOMEM;
-}
-
-static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
-{
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct i915_page_directory *pd = ppgtt->pd;
-	unsigned int idx;
-
-	GEM_BUG_ON(vm->top != 2);
-	GEM_BUG_ON(gen8_pd_top_count(vm) != GEN8_3LVL_PDPES);
-
-	for (idx = 0; idx < GEN8_3LVL_PDPES; idx++) {
-		struct i915_page_directory *pde;
-
-		pde = alloc_pd(vm);
-		if (IS_ERR(pde))
-			return PTR_ERR(pde);
-
-		fill_px(pde, vm->scratch[1].encode);
-		set_pd_entry(pd, idx, pde);
-		atomic_inc(px_used(pde)); /* keep pinned */
-	}
-	wmb();
-
-	return 0;
-}
-
-static void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-
-	ppgtt->vm.gt = gt;
-	ppgtt->vm.i915 = i915;
-	ppgtt->vm.dma = &i915->drm.pdev->dev;
-	ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size);
-
-	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
-
-	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
-	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
-	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
-	ppgtt->vm.vma_ops.clear_pages = clear_pages;
-}
-
-static struct i915_page_directory *
-gen8_alloc_top_pd(struct i915_address_space *vm)
-{
-	const unsigned int count = gen8_pd_top_count(vm);
-	struct i915_page_directory *pd;
-
-	GEM_BUG_ON(count > ARRAY_SIZE(pd->entry));
-
-	pd = __alloc_pd(offsetof(typeof(*pd), entry[count]));
-	if (unlikely(!pd))
-		return ERR_PTR(-ENOMEM);
-
-	if (unlikely(setup_page_dma(vm, px_base(pd)))) {
-		kfree(pd);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	fill_page_dma(px_base(pd), vm->scratch[vm->top].encode, count);
-	atomic_inc(px_used(pd)); /* mark as pinned */
-	return pd;
-}
-
-/*
- * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
- * with a net effect resembling a 2-level page table in normal x86 terms. Each
- * PDP represents 1GB of memory 4 * 512 * 512 * 4096 = 4GB legacy 32b address
- * space.
- *
- */
-static struct i915_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
-{
-	struct i915_ppgtt *ppgtt;
-	int err;
-
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
-
-	ppgtt_init(ppgtt, &i915->gt);
-	ppgtt->vm.top = i915_vm_is_4lvl(&ppgtt->vm) ? 3 : 2;
-
-	/*
-	 * From bdw, there is hw support for read-only pages in the PPGTT.
-	 *
-	 * Gen11 has HSDES#:1807136187 unresolved. Disable ro support
-	 * for now.
-	 *
-	 * Gen12 has inherited the same read-only fault issue from gen11.
-	 */
-	ppgtt->vm.has_read_only = !IS_GEN_RANGE(i915, 11, 12);
-
-	/* There are only few exceptions for gen >=6. chv and bxt.
-	 * And we are not sure about the latter so play safe for now.
-	 */
-	if (IS_CHERRYVIEW(i915) || IS_BROXTON(i915))
-		ppgtt->vm.pt_kmap_wc = true;
-
-	err = gen8_init_scratch(&ppgtt->vm);
-	if (err)
-		goto err_free;
-
-	ppgtt->pd = gen8_alloc_top_pd(&ppgtt->vm);
-	if (IS_ERR(ppgtt->pd)) {
-		err = PTR_ERR(ppgtt->pd);
-		goto err_free_scratch;
-	}
-
-	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
-		err = gen8_preallocate_top_level_pdp(ppgtt);
-		if (err)
-			goto err_free_pd;
-	}
-
-	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
-	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
-	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
-	ppgtt->vm.clear_range = gen8_ppgtt_clear;
-
-	if (intel_vgpu_active(i915))
-		gen8_ppgtt_notify_vgt(ppgtt, true);
-
-	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
-
-	return ppgtt;
-
-err_free_pd:
-	__gen8_ppgtt_cleanup(&ppgtt->vm, ppgtt->pd,
-			     gen8_pd_top_count(&ppgtt->vm), ppgtt->vm.top);
-err_free_scratch:
-	free_scratch(&ppgtt->vm);
-err_free:
-	kfree(ppgtt);
-	return ERR_PTR(err);
-}
-
-/* Write pde (index) from the page directory @pd to the page table @pt */
-static inline void gen6_write_pde(const struct gen6_ppgtt *ppgtt,
-				  const unsigned int pde,
-				  const struct i915_page_table *pt)
-{
-	/* Caller needs to make sure the write completes if necessary */
-	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
-		  ppgtt->pd_addr + pde);
-}
-
-static void gen7_ppgtt_enable(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	struct intel_uncore *uncore = gt->uncore;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	u32 ecochk;
-
-	intel_uncore_rmw(uncore, GAC_ECO_BITS, 0, ECOBITS_PPGTT_CACHE64B);
-
-	ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
-	if (IS_HASWELL(i915)) {
-		ecochk |= ECOCHK_PPGTT_WB_HSW;
-	} else {
-		ecochk |= ECOCHK_PPGTT_LLC_IVB;
-		ecochk &= ~ECOCHK_PPGTT_GFDT_IVB;
-	}
-	intel_uncore_write(uncore, GAM_ECOCHK, ecochk);
-
-	for_each_engine(engine, gt, id) {
-		/* GFX_MODE is per-ring on gen7+ */
-		ENGINE_WRITE(engine,
-			     RING_MODE_GEN7,
-			     _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-	}
-}
-
-static void gen6_ppgtt_enable(struct intel_gt *gt)
-{
-	struct intel_uncore *uncore = gt->uncore;
-
-	intel_uncore_rmw(uncore,
-			 GAC_ECO_BITS,
-			 0,
-			 ECOBITS_SNB_BIT | ECOBITS_PPGTT_CACHE64B);
-
-	intel_uncore_rmw(uncore,
-			 GAB_CTL,
-			 0,
-			 GAB_CTL_CONT_AFTER_PAGEFAULT);
-
-	intel_uncore_rmw(uncore,
-			 GAM_ECOCHK,
-			 0,
-			 ECOCHK_SNB_BIT | ECOCHK_PPGTT_CACHE64B);
-
-	if (HAS_PPGTT(uncore->i915)) /* may be disabled for VT-d */
-		intel_uncore_write(uncore,
-				   GFX_MODE,
-				   _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE));
-}
-
-/* PPGTT support for Sandybdrige/Gen6 and later */
-static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
-				   u64 start, u64 length)
-{
-	struct gen6_ppgtt * const ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-	const unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
-	const gen6_pte_t scratch_pte = vm->scratch[0].encode;
-	unsigned int pde = first_entry / GEN6_PTES;
-	unsigned int pte = first_entry % GEN6_PTES;
-	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
-
-	while (num_entries) {
-		struct i915_page_table * const pt =
-			i915_pt_entry(ppgtt->base.pd, pde++);
-		const unsigned int count = min(num_entries, GEN6_PTES - pte);
-		gen6_pte_t *vaddr;
-
-		GEM_BUG_ON(px_base(pt) == px_base(&vm->scratch[1]));
-
-		num_entries -= count;
-
-		GEM_BUG_ON(count > atomic_read(&pt->used));
-		if (!atomic_sub_return(count, &pt->used))
-			ppgtt->scan_for_unused_pt = true;
-
-		/*
-		 * Note that the hw doesn't support removing PDE on the fly
-		 * (they are cached inside the context with no means to
-		 * invalidate the cache), so we can only reset the PTE
-		 * entries back to scratch.
-		 */
-
-		vaddr = kmap_atomic_px(pt);
-		memset32(vaddr + pte, scratch_pte, count);
-		kunmap_atomic(vaddr);
-
-		pte = 0;
-	}
-}
-
-static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
-				      struct i915_vma *vma,
-				      enum i915_cache_level cache_level,
-				      u32 flags)
-{
-	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-	struct i915_page_directory * const pd = ppgtt->pd;
-	unsigned first_entry = vma->node.start / I915_GTT_PAGE_SIZE;
-	unsigned act_pt = first_entry / GEN6_PTES;
-	unsigned act_pte = first_entry % GEN6_PTES;
-	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
-	struct sgt_dma iter = sgt_dma(vma);
-	gen6_pte_t *vaddr;
-
-	GEM_BUG_ON(pd->entry[act_pt] == &vm->scratch[1]);
-
-	vaddr = kmap_atomic_px(i915_pt_entry(pd, act_pt));
-	do {
-		GEM_BUG_ON(iter.sg->length < I915_GTT_PAGE_SIZE);
-		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
-
-		iter.dma += I915_GTT_PAGE_SIZE;
-		if (iter.dma == iter.max) {
-			iter.sg = __sg_next(iter.sg);
-			if (!iter.sg)
-				break;
-
-			iter.dma = sg_dma_address(iter.sg);
-			iter.max = iter.dma + iter.sg->length;
-		}
-
-		if (++act_pte == GEN6_PTES) {
-			kunmap_atomic(vaddr);
-			vaddr = kmap_atomic_px(i915_pt_entry(pd, ++act_pt));
-			act_pte = 0;
-		}
-	} while (1);
-	kunmap_atomic(vaddr);
-
-	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-}
-
-static int gen6_alloc_va_range(struct i915_address_space *vm,
-			       u64 start, u64 length)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_table *pt, *alloc = NULL;
-	intel_wakeref_t wakeref;
-	u64 from = start;
-	unsigned int pde;
-	bool flush = false;
-	int ret = 0;
-
-	wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
-
-	spin_lock(&pd->lock);
-	gen6_for_each_pde(pt, pd, start, length, pde) {
-		const unsigned int count = gen6_pte_count(start, length);
-
-		if (px_base(pt) == px_base(&vm->scratch[1])) {
-			spin_unlock(&pd->lock);
-
-			pt = fetch_and_zero(&alloc);
-			if (!pt)
-				pt = alloc_pt(vm);
-			if (IS_ERR(pt)) {
-				ret = PTR_ERR(pt);
-				goto unwind_out;
-			}
-
-			fill32_px(pt, vm->scratch[0].encode);
-
-			spin_lock(&pd->lock);
-			if (pd->entry[pde] == &vm->scratch[1]) {
-				pd->entry[pde] = pt;
-				if (i915_vma_is_bound(ppgtt->vma,
-						      I915_VMA_GLOBAL_BIND)) {
-					gen6_write_pde(ppgtt, pde, pt);
-					flush = true;
-				}
-			} else {
-				alloc = pt;
-				pt = pd->entry[pde];
-			}
-		}
-
-		atomic_add(count, &pt->used);
-	}
-	spin_unlock(&pd->lock);
-
-	if (flush)
-		gen6_ggtt_invalidate(vm->gt->ggtt);
-
-	goto out;
-
-unwind_out:
-	gen6_ppgtt_clear_range(vm, from, start - from);
-out:
-	if (alloc)
-		free_px(vm, alloc);
-	intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
-	return ret;
-}
-
-static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
-{
-	struct i915_address_space * const vm = &ppgtt->base.vm;
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	int ret;
-
-	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
-	if (ret)
-		return ret;
-
-	vm->scratch[0].encode =
-		vm->pte_encode(px_dma(&vm->scratch[0]),
-			       I915_CACHE_NONE, PTE_READ_ONLY);
-
-	if (unlikely(setup_page_dma(vm, px_base(&vm->scratch[1])))) {
-		cleanup_scratch_page(vm);
-		return -ENOMEM;
-	}
-
-	fill32_px(&vm->scratch[1], vm->scratch[0].encode);
-	memset_p(pd->entry, &vm->scratch[1], I915_PDES);
-
-	return 0;
-}
-
-static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
-{
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
-	struct i915_page_table *pt;
-	u32 pde;
-
-	gen6_for_all_pdes(pt, pd, pde)
-		if (px_base(pt) != scratch)
-			free_px(&ppgtt->base.vm, pt);
-}
-
-static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-
-	i915_vma_destroy(ppgtt->vma);
-
-	gen6_ppgtt_free_pd(ppgtt);
-	free_scratch(vm);
-
-	mutex_destroy(&ppgtt->pin_mutex);
-	kfree(ppgtt->base.pd);
-}
-
-static int pd_vma_set_pages(struct i915_vma *vma)
-{
-	vma->pages = ERR_PTR(-ENODEV);
-	return 0;
-}
-
-static void pd_vma_clear_pages(struct i915_vma *vma)
-{
-	GEM_BUG_ON(!vma->pages);
-
-	vma->pages = NULL;
-}
-
-static int pd_vma_bind(struct i915_vma *vma,
-		       enum i915_cache_level cache_level,
-		       u32 unused)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
-	struct gen6_ppgtt *ppgtt = vma->private;
-	u32 ggtt_offset = i915_ggtt_offset(vma) / I915_GTT_PAGE_SIZE;
-	struct i915_page_table *pt;
-	unsigned int pde;
-
-	px_base(ppgtt->base.pd)->ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
-	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
-
-	gen6_for_all_pdes(pt, ppgtt->base.pd, pde)
-		gen6_write_pde(ppgtt, pde, pt);
-
-	gen6_ggtt_invalidate(ggtt);
-
-	return 0;
-}
-
-static void pd_vma_unbind(struct i915_vma *vma)
-{
-	struct gen6_ppgtt *ppgtt = vma->private;
-	struct i915_page_directory * const pd = ppgtt->base.pd;
-	struct i915_page_dma * const scratch =
-		px_base(&ppgtt->base.vm.scratch[1]);
-	struct i915_page_table *pt;
-	unsigned int pde;
-
-	if (!ppgtt->scan_for_unused_pt)
-		return;
-
-	/* Free all no longer used page tables */
-	gen6_for_all_pdes(pt, ppgtt->base.pd, pde) {
-		if (px_base(pt) == scratch || atomic_read(&pt->used))
-			continue;
-
-		free_px(&ppgtt->base.vm, pt);
-		pd->entry[pde] = scratch;
-	}
-
-	ppgtt->scan_for_unused_pt = false;
-}
-
-static const struct i915_vma_ops pd_vma_ops = {
-	.set_pages = pd_vma_set_pages,
-	.clear_pages = pd_vma_clear_pages,
-	.bind_vma = pd_vma_bind,
-	.unbind_vma = pd_vma_unbind,
-};
-
-static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
-{
-	struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt;
-	struct i915_vma *vma;
-
-	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
-	GEM_BUG_ON(size > ggtt->vm.total);
-
-	vma = i915_vma_alloc();
-	if (!vma)
-		return ERR_PTR(-ENOMEM);
-
-	i915_active_init(&vma->active, NULL, NULL);
-
-	mutex_init(&vma->pages_mutex);
-	vma->vm = i915_vm_get(&ggtt->vm);
-	vma->ops = &pd_vma_ops;
-	vma->private = ppgtt;
-
-	vma->size = size;
-	vma->fence_size = size;
-	atomic_set(&vma->flags, I915_VMA_GGTT);
-	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
-
-	INIT_LIST_HEAD(&vma->obj_link);
-	INIT_LIST_HEAD(&vma->closed_link);
-
-	return vma;
-}
-
-int gen6_ppgtt_pin(struct i915_ppgtt *base)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	int err = 0;
-
-	GEM_BUG_ON(!atomic_read(&ppgtt->base.vm.open));
-
-	/*
-	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
-	 * which will be pinned into every active context.
-	 * (When vma->pin_count becomes atomic, I expect we will naturally
-	 * need a larger, unpacked, type and kill this redundancy.)
-	 */
-	if (atomic_add_unless(&ppgtt->pin_count, 1, 0))
-		return 0;
-
-	if (mutex_lock_interruptible(&ppgtt->pin_mutex))
-		return -EINTR;
-
-	/*
-	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
-	 * allocator works in address space sizes, so it's multiplied by page
-	 * size. We allocate at the top of the GTT to avoid fragmentation.
-	 */
-	if (!atomic_read(&ppgtt->pin_count)) {
-		err = i915_vma_pin(ppgtt->vma,
-				   0, GEN6_PD_ALIGN,
-				   PIN_GLOBAL | PIN_HIGH);
-	}
-	if (!err)
-		atomic_inc(&ppgtt->pin_count);
-	mutex_unlock(&ppgtt->pin_mutex);
-
-	return err;
-}
-
-void gen6_ppgtt_unpin(struct i915_ppgtt *base)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-
-	GEM_BUG_ON(!atomic_read(&ppgtt->pin_count));
-	if (atomic_dec_and_test(&ppgtt->pin_count))
-		i915_vma_unpin(ppgtt->vma);
-}
-
-void gen6_ppgtt_unpin_all(struct i915_ppgtt *base)
-{
-	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-
-	if (!atomic_read(&ppgtt->pin_count))
-		return;
-
-	i915_vma_unpin(ppgtt->vma);
-	atomic_set(&ppgtt->pin_count, 0);
-}
-
-static struct i915_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
-{
-	struct i915_ggtt * const ggtt = &i915->ggtt;
-	struct gen6_ppgtt *ppgtt;
-	int err;
-
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
-
-	mutex_init(&ppgtt->pin_mutex);
-
-	ppgtt_init(&ppgtt->base, &i915->gt);
-	ppgtt->base.vm.top = 1;
-
-	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
-	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
-	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
-	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
-
-	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
-
-	ppgtt->base.pd = __alloc_pd(sizeof(*ppgtt->base.pd));
-	if (!ppgtt->base.pd) {
-		err = -ENOMEM;
-		goto err_free;
-	}
-
-	err = gen6_ppgtt_init_scratch(ppgtt);
-	if (err)
-		goto err_pd;
-
-	ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE);
-	if (IS_ERR(ppgtt->vma)) {
-		err = PTR_ERR(ppgtt->vma);
-		goto err_scratch;
-	}
-
-	return &ppgtt->base;
-
-err_scratch:
-	free_scratch(&ppgtt->base.vm);
-err_pd:
-	kfree(ppgtt->base.pd);
-err_free:
-	kfree(ppgtt);
-	return ERR_PTR(err);
-}
-
-static void gtt_write_workarounds(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	struct intel_uncore *uncore = gt->uncore;
-
-	/* This function is for gtt related workarounds. This function is
-	 * called on driver load and after a GPU reset, so you can place
-	 * workarounds here even if they get overwritten by GPU reset.
-	 */
-	/* WaIncreaseDefaultTLBEntries:chv,bdw,skl,bxt,kbl,glk,cfl,cnl,icl */
-	if (IS_BROADWELL(i915))
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_BDW);
-	else if (IS_CHERRYVIEW(i915))
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN8_L3_LRA_1_GPGPU_DEFAULT_VALUE_CHV);
-	else if (IS_GEN9_LP(i915))
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
-	else if (INTEL_GEN(i915) >= 9 && INTEL_GEN(i915) <= 11)
-		intel_uncore_write(uncore,
-				   GEN8_L3_LRA_1_GPGPU,
-				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
-
-	/*
-	 * To support 64K PTEs we need to first enable the use of the
-	 * Intermediate-Page-Size(IPS) bit of the PDE field via some magical
-	 * mmio, otherwise the page-walker will simply ignore the IPS bit. This
-	 * shouldn't be needed after GEN10.
-	 *
-	 * 64K pages were first introduced from BDW+, although technically they
-	 * only *work* from gen9+. For pre-BDW we instead have the option for
-	 * 32K pages, but we don't currently have any support for it in our
-	 * driver.
-	 */
-	if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_64K) &&
-	    INTEL_GEN(i915) <= 10)
-		intel_uncore_rmw(uncore,
-				 GEN8_GAMW_ECO_DEV_RW_IA,
-				 0,
-				 GAMW_ECO_ENABLE_64K_IPS_FIELD);
-
-	if (IS_GEN_RANGE(i915, 8, 11)) {
-		bool can_use_gtt_cache = true;
-
-		/*
-		 * According to the BSpec if we use 2M/1G pages then we also
-		 * need to disable the GTT cache. At least on BDW we can see
-		 * visual corruption when using 2M pages, and not disabling the
-		 * GTT cache.
-		 */
-		if (HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_2M))
-			can_use_gtt_cache = false;
-
-		/* WaGttCachingOffByDefault */
-		intel_uncore_write(uncore,
-				   HSW_GTT_CACHE_EN,
-				   can_use_gtt_cache ? GTT_CACHE_EN_ALL : 0);
-		WARN_ON_ONCE(can_use_gtt_cache &&
-			     intel_uncore_read(uncore,
-					       HSW_GTT_CACHE_EN) == 0);
-	}
-}
-
-int i915_ppgtt_init_hw(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-
-	gtt_write_workarounds(gt);
-
-	if (IS_GEN(i915, 6))
-		gen6_ppgtt_enable(gt);
-	else if (IS_GEN(i915, 7))
-		gen7_ppgtt_enable(gt);
-
-	return 0;
-}
-
-static struct i915_ppgtt *
-__ppgtt_create(struct drm_i915_private *i915)
-{
-	if (INTEL_GEN(i915) < 8)
-		return gen6_ppgtt_create(i915);
-	else
-		return gen8_ppgtt_create(i915);
-}
-
-struct i915_ppgtt *
-i915_ppgtt_create(struct drm_i915_private *i915)
-{
-	struct i915_ppgtt *ppgtt;
-
-	ppgtt = __ppgtt_create(i915);
-	if (IS_ERR(ppgtt))
-		return ppgtt;
-
-	trace_i915_ppgtt_create(&ppgtt->vm);
-
-	return ppgtt;
-}
-
-/* Certain Gen5 chipsets require require idling the GPU before
- * unmapping anything from the GTT when VT-d is enabled.
- */
-static bool needs_idle_maps(struct drm_i915_private *dev_priv)
-{
-	/* Query intel_iommu to see if we need the workaround. Presumably that
-	 * was loaded first.
-	 */
-	return IS_GEN(dev_priv, 5) && IS_MOBILE(dev_priv) && intel_vtd_active();
-}
-
-static void ggtt_suspend_mappings(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *i915 = ggtt->vm.i915;
-
-	/* Don't bother messing with faults pre GEN6 as we have little
-	 * documentation supporting that it's a good idea.
-	 */
-	if (INTEL_GEN(i915) < 6)
-		return;
-
-	intel_gt_check_and_clear_faults(ggtt->vm.gt);
-
-	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
-
-	ggtt->invalidate(ggtt);
-}
-
-void i915_gem_suspend_gtt_mappings(struct drm_i915_private *i915)
-{
-	ggtt_suspend_mappings(&i915->ggtt);
-}
-
 int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
@@ -2163,368 +52,6 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 	return -ENOSPC;
 }
 
-static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
-{
-	writeq(pte, addr);
-}
-
-static void gen8_ggtt_insert_page(struct i915_address_space *vm,
-				  dma_addr_t addr,
-				  u64 offset,
-				  enum i915_cache_level level,
-				  u32 unused)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen8_pte_t __iomem *pte =
-		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
-
-	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
-
-	ggtt->invalidate(ggtt);
-}
-
-static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
-				     enum i915_cache_level level,
-				     u32 flags)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	struct sgt_iter sgt_iter;
-	gen8_pte_t __iomem *gtt_entries;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
-	dma_addr_t addr;
-
-	/*
-	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
-	 * not to allow the user to override access to a read only page.
-	 */
-
-	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
-	gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE;
-	for_each_sgt_daddr(addr, sgt_iter, vma->pages)
-		gen8_set_pte(gtt_entries++, pte_encode | addr);
-
-	/*
-	 * We want to flush the TLBs only after we're certain all the PTE
-	 * updates have finished.
-	 */
-	ggtt->invalidate(ggtt);
-}
-
-static void gen6_ggtt_insert_page(struct i915_address_space *vm,
-				  dma_addr_t addr,
-				  u64 offset,
-				  enum i915_cache_level level,
-				  u32 flags)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen6_pte_t __iomem *pte =
-		(gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
-
-	iowrite32(vm->pte_encode(addr, level, flags), pte);
-
-	ggtt->invalidate(ggtt);
-}
-
-/*
- * Binds an object into the global gtt with the specified cache level. The object
- * will be accessible to the GPU via commands whose operands reference offsets
- * within the global GTT as well as accessible by the GPU through the GMADR
- * mapped BAR (dev_priv->mm.gtt->gtt).
- */
-static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
-				     enum i915_cache_level level,
-				     u32 flags)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen6_pte_t __iomem *entries = (gen6_pte_t __iomem *)ggtt->gsm;
-	unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE;
-	struct sgt_iter iter;
-	dma_addr_t addr;
-	for_each_sgt_daddr(addr, iter, vma->pages)
-		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
-
-	/*
-	 * We want to flush the TLBs only after we're certain all the PTE
-	 * updates have finished.
-	 */
-	ggtt->invalidate(ggtt);
-}
-
-static void nop_clear_range(struct i915_address_space *vm,
-			    u64 start, u64 length)
-{
-}
-
-static void gen8_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	unsigned first_entry = start / I915_GTT_PAGE_SIZE;
-	unsigned num_entries = length / I915_GTT_PAGE_SIZE;
-	const gen8_pte_t scratch_pte = vm->scratch[0].encode;
-	gen8_pte_t __iomem *gtt_base =
-		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
-	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
-	int i;
-
-	if (WARN(num_entries > max_entries,
-		 "First entry = %d; Num entries = %d (max=%d)\n",
-		 first_entry, num_entries, max_entries))
-		num_entries = max_entries;
-
-	for (i = 0; i < num_entries; i++)
-		gen8_set_pte(&gtt_base[i], scratch_pte);
-}
-
-static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
-{
-	struct drm_i915_private *dev_priv = vm->i915;
-
-	/*
-	 * Make sure the internal GAM fifo has been cleared of all GTT
-	 * writes before exiting stop_machine(). This guarantees that
-	 * any aperture accesses waiting to start in another process
-	 * cannot back up behind the GTT writes causing a hang.
-	 * The register can be any arbitrary GAM register.
-	 */
-	POSTING_READ(GFX_FLSH_CNTL_GEN6);
-}
-
-struct insert_page {
-	struct i915_address_space *vm;
-	dma_addr_t addr;
-	u64 offset;
-	enum i915_cache_level level;
-};
-
-static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
-{
-	struct insert_page *arg = _arg;
-
-	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
-	bxt_vtd_ggtt_wa(arg->vm);
-
-	return 0;
-}
-
-static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
-					  dma_addr_t addr,
-					  u64 offset,
-					  enum i915_cache_level level,
-					  u32 unused)
-{
-	struct insert_page arg = { vm, addr, offset, level };
-
-	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
-}
-
-struct insert_entries {
-	struct i915_address_space *vm;
-	struct i915_vma *vma;
-	enum i915_cache_level level;
-	u32 flags;
-};
-
-static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
-{
-	struct insert_entries *arg = _arg;
-
-	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
-	bxt_vtd_ggtt_wa(arg->vm);
-
-	return 0;
-}
-
-static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
-					     struct i915_vma *vma,
-					     enum i915_cache_level level,
-					     u32 flags)
-{
-	struct insert_entries arg = { vm, vma, level, flags };
-
-	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
-}
-
-struct clear_range {
-	struct i915_address_space *vm;
-	u64 start;
-	u64 length;
-};
-
-static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
-{
-	struct clear_range *arg = _arg;
-
-	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
-	bxt_vtd_ggtt_wa(arg->vm);
-
-	return 0;
-}
-
-static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
-					  u64 start,
-					  u64 length)
-{
-	struct clear_range arg = { vm, start, length };
-
-	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
-}
-
-static void gen6_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	unsigned first_entry = start / I915_GTT_PAGE_SIZE;
-	unsigned num_entries = length / I915_GTT_PAGE_SIZE;
-	gen6_pte_t scratch_pte, __iomem *gtt_base =
-		(gen6_pte_t __iomem *)ggtt->gsm + first_entry;
-	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
-	int i;
-
-	if (WARN(num_entries > max_entries,
-		 "First entry = %d; Num entries = %d (max=%d)\n",
-		 first_entry, num_entries, max_entries))
-		num_entries = max_entries;
-
-	scratch_pte = vm->scratch[0].encode;
-	for (i = 0; i < num_entries; i++)
-		iowrite32(scratch_pte, &gtt_base[i]);
-}
-
-static void i915_ggtt_insert_page(struct i915_address_space *vm,
-				  dma_addr_t addr,
-				  u64 offset,
-				  enum i915_cache_level cache_level,
-				  u32 unused)
-{
-	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
-		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
-
-	intel_gtt_insert_page(addr, offset >> PAGE_SHIFT, flags);
-}
-
-static void i915_ggtt_insert_entries(struct i915_address_space *vm,
-				     struct i915_vma *vma,
-				     enum i915_cache_level cache_level,
-				     u32 unused)
-{
-	unsigned int flags = (cache_level == I915_CACHE_NONE) ?
-		AGP_USER_MEMORY : AGP_USER_CACHED_MEMORY;
-
-	intel_gtt_insert_sg_entries(vma->pages, vma->node.start >> PAGE_SHIFT,
-				    flags);
-}
-
-static void i915_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	intel_gtt_clear_range(start >> PAGE_SHIFT, length >> PAGE_SHIFT);
-}
-
-static int ggtt_bind_vma(struct i915_vma *vma,
-			 enum i915_cache_level cache_level,
-			 u32 flags)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-	struct drm_i915_gem_object *obj = vma->obj;
-	intel_wakeref_t wakeref;
-	u32 pte_flags;
-
-	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
-	pte_flags = 0;
-	if (i915_gem_object_is_readonly(obj))
-		pte_flags |= PTE_READ_ONLY;
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-
-	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
-
-	/*
-	 * Without aliasing PPGTT there's no difference between
-	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
-	 * upgrade to both bound if we bind either to avoid double-binding.
-	 */
-	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
-
-	return 0;
-}
-
-static void ggtt_unbind_vma(struct i915_vma *vma)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-	intel_wakeref_t wakeref;
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-}
-
-static int aliasing_gtt_bind_vma(struct i915_vma *vma,
-				 enum i915_cache_level cache_level,
-				 u32 flags)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-	u32 pte_flags;
-	int ret;
-
-	/* Currently applicable only to VLV */
-	pte_flags = 0;
-	if (i915_gem_object_is_readonly(vma->obj))
-		pte_flags |= PTE_READ_ONLY;
-
-	if (flags & I915_VMA_LOCAL_BIND) {
-		struct i915_ppgtt *alias = i915_vm_to_ggtt(vma->vm)->alias;
-
-		if (flags & I915_VMA_ALLOC) {
-			ret = alias->vm.allocate_va_range(&alias->vm,
-							  vma->node.start,
-							  vma->size);
-			if (ret)
-				return ret;
-
-			set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
-		}
-
-		GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT,
-				     __i915_vma_flags(vma)));
-		alias->vm.insert_entries(&alias->vm, vma,
-					 cache_level, pte_flags);
-	}
-
-	if (flags & I915_VMA_GLOBAL_BIND) {
-		intel_wakeref_t wakeref;
-
-		with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-			vma->vm->insert_entries(vma->vm, vma,
-						cache_level, pte_flags);
-		}
-	}
-
-	return 0;
-}
-
-static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
-{
-	struct drm_i915_private *i915 = vma->vm->i915;
-
-	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
-		struct i915_address_space *vm = vma->vm;
-		intel_wakeref_t wakeref;
-
-		with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-			vm->clear_range(vm, vma->node.start, vma->size);
-	}
-
-	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
-		struct i915_address_space *vm =
-			&i915_vm_to_ggtt(vma->vm)->alias->vm;
-
-		vm->clear_range(vm, vma->node.start, vma->size);
-	}
-}
-
 void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 			       struct sg_table *pages)
 {
@@ -2545,1067 +72,6 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	dma_unmap_sg(kdev, pages->sgl, pages->nents, PCI_DMA_BIDIRECTIONAL);
 }
 
-static int ggtt_set_pages(struct i915_vma *vma)
-{
-	int ret;
-
-	GEM_BUG_ON(vma->pages);
-
-	ret = i915_get_ggtt_vma_pages(vma);
-	if (ret)
-		return ret;
-
-	vma->page_sizes = vma->obj->mm.page_sizes;
-
-	return 0;
-}
-
-static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
-				   unsigned long color,
-				   u64 *start,
-				   u64 *end)
-{
-	if (i915_node_color_differs(node, color))
-		*start += I915_GTT_PAGE_SIZE;
-
-	/* Also leave a space between the unallocated reserved node after the
-	 * GTT and any objects within the GTT, i.e. we use the color adjustment
-	 * to insert a guard page to prevent prefetches crossing over the
-	 * GTT boundary.
-	 */
-	node = list_next_entry(node, node_list);
-	if (node->color != color)
-		*end -= I915_GTT_PAGE_SIZE;
-}
-
-static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
-{
-	struct i915_ppgtt *ppgtt;
-	int err;
-
-	ppgtt = i915_ppgtt_create(ggtt->vm.i915);
-	if (IS_ERR(ppgtt))
-		return PTR_ERR(ppgtt);
-
-	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
-		err = -ENODEV;
-		goto err_ppgtt;
-	}
-
-	/*
-	 * Note we only pre-allocate as far as the end of the global
-	 * GTT. On 48b / 4-level page-tables, the difference is very,
-	 * very significant! We have to preallocate as GVT/vgpu does
-	 * not like the page directory disappearing.
-	 */
-	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
-	if (err)
-		goto err_ppgtt;
-
-	ggtt->alias = ppgtt;
-	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
-
-	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
-	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
-
-	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
-	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
-
-	return 0;
-
-err_ppgtt:
-	i915_vm_put(&ppgtt->vm);
-	return err;
-}
-
-static void fini_aliasing_ppgtt(struct i915_ggtt *ggtt)
-{
-	struct i915_ppgtt *ppgtt;
-
-	ppgtt = fetch_and_zero(&ggtt->alias);
-	if (!ppgtt)
-		return;
-
-	i915_vm_put(&ppgtt->vm);
-
-	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
-}
-
-static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
-{
-	u64 size;
-	int ret;
-
-	if (!USES_GUC(ggtt->vm.i915))
-		return 0;
-
-	GEM_BUG_ON(ggtt->vm.total <= GUC_GGTT_TOP);
-	size = ggtt->vm.total - GUC_GGTT_TOP;
-
-	ret = i915_gem_gtt_reserve(&ggtt->vm, &ggtt->uc_fw, size,
-				   GUC_GGTT_TOP, I915_COLOR_UNEVICTABLE,
-				   PIN_NOEVICT);
-	if (ret)
-		DRM_DEBUG_DRIVER("Failed to reserve top of GGTT for GuC\n");
-
-	return ret;
-}
-
-static void ggtt_release_guc_top(struct i915_ggtt *ggtt)
-{
-	if (drm_mm_node_allocated(&ggtt->uc_fw))
-		drm_mm_remove_node(&ggtt->uc_fw);
-}
-
-static void cleanup_init_ggtt(struct i915_ggtt *ggtt)
-{
-	ggtt_release_guc_top(ggtt);
-	if (drm_mm_node_allocated(&ggtt->error_capture))
-		drm_mm_remove_node(&ggtt->error_capture);
-}
-
-static int init_ggtt(struct i915_ggtt *ggtt)
-{
-	/* Let GEM Manage all of the aperture.
-	 *
-	 * However, leave one page at the end still bound to the scratch page.
-	 * There are a number of places where the hardware apparently prefetches
-	 * past the end of the object, and we've seen multiple hangs with the
-	 * GPU head pointer stuck in a batchbuffer bound at the last page of the
-	 * aperture.  One page should be enough to keep any prefetching inside
-	 * of the aperture.
-	 */
-	unsigned long hole_start, hole_end;
-	struct drm_mm_node *entry;
-	int ret;
-
-	/*
-	 * GuC requires all resources that we're sharing with it to be placed in
-	 * non-WOPCM memory. If GuC is not present or not in use we still need a
-	 * small bias as ring wraparound at offset 0 sometimes hangs. No idea
-	 * why.
-	 */
-	ggtt->pin_bias = max_t(u32, I915_GTT_PAGE_SIZE,
-			       intel_wopcm_guc_size(&ggtt->vm.i915->wopcm));
-
-	ret = intel_vgt_balloon(ggtt);
-	if (ret)
-		return ret;
-
-	if (ggtt->mappable_end) {
-		/* Reserve a mappable slot for our lockless error capture */
-		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture,
-						  PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
-						  0, ggtt->mappable_end,
-						  DRM_MM_INSERT_LOW);
-		if (ret)
-			return ret;
-	}
-
-	/*
-	 * The upper portion of the GuC address space has a sizeable hole
-	 * (several MB) that is inaccessible by GuC. Reserve this range within
-	 * GGTT as it can comfortably hold GuC/HuC firmware images.
-	 */
-	ret = ggtt_reserve_guc_top(ggtt);
-	if (ret)
-		goto err;
-
-	/* Clear any non-preallocated blocks */
-	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
-		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
-			      hole_start, hole_end);
-		ggtt->vm.clear_range(&ggtt->vm, hole_start,
-				     hole_end - hole_start);
-	}
-
-	/* And finally clear the reserved guard page */
-	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
-
-	return 0;
-
-err:
-	cleanup_init_ggtt(ggtt);
-	return ret;
-}
-
-int i915_init_ggtt(struct drm_i915_private *i915)
-{
-	int ret;
-
-	ret = init_ggtt(&i915->ggtt);
-	if (ret)
-		return ret;
-
-	if (INTEL_PPGTT(i915) == INTEL_PPGTT_ALIASING) {
-		ret = init_aliasing_ppgtt(&i915->ggtt);
-		if (ret)
-			cleanup_init_ggtt(&i915->ggtt);
-	}
-
-	return 0;
-}
-
-static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
-{
-	struct i915_vma *vma, *vn;
-
-	atomic_set(&ggtt->vm.open, 0);
-
-	rcu_barrier(); /* flush the RCU'ed__i915_vm_release */
-	flush_workqueue(ggtt->vm.i915->wq);
-
-	mutex_lock(&ggtt->vm.mutex);
-
-	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link)
-		WARN_ON(__i915_vma_unbind(vma));
-
-	if (drm_mm_node_allocated(&ggtt->error_capture))
-		drm_mm_remove_node(&ggtt->error_capture);
-
-	ggtt_release_guc_top(ggtt);
-	intel_vgt_deballoon(ggtt);
-
-	ggtt->vm.cleanup(&ggtt->vm);
-
-	mutex_unlock(&ggtt->vm.mutex);
-	i915_address_space_fini(&ggtt->vm);
-
-	arch_phys_wc_del(ggtt->mtrr);
-
-	if (ggtt->iomap.size)
-		io_mapping_fini(&ggtt->iomap);
-}
-
-/**
- * i915_ggtt_driver_release - Clean up GGTT hardware initialization
- * @i915: i915 device
- */
-void i915_ggtt_driver_release(struct drm_i915_private *i915)
-{
-	struct pagevec *pvec;
-
-	fini_aliasing_ppgtt(&i915->ggtt);
-
-	ggtt_cleanup_hw(&i915->ggtt);
-
-	pvec = &i915->mm.wc_stash.pvec;
-	if (pvec->nr) {
-		set_pages_array_wb(pvec->pages, pvec->nr);
-		__pagevec_release(pvec);
-	}
-}
-
-static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
-{
-	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
-	snb_gmch_ctl &= SNB_GMCH_GGMS_MASK;
-	return snb_gmch_ctl << 20;
-}
-
-static unsigned int gen8_get_total_gtt_size(u16 bdw_gmch_ctl)
-{
-	bdw_gmch_ctl >>= BDW_GMCH_GGMS_SHIFT;
-	bdw_gmch_ctl &= BDW_GMCH_GGMS_MASK;
-	if (bdw_gmch_ctl)
-		bdw_gmch_ctl = 1 << bdw_gmch_ctl;
-
-#ifdef CONFIG_X86_32
-	/* Limit 32b platforms to a 2GB GGTT: 4 << 20 / pte size * I915_GTT_PAGE_SIZE */
-	if (bdw_gmch_ctl > 4)
-		bdw_gmch_ctl = 4;
-#endif
-
-	return bdw_gmch_ctl << 20;
-}
-
-static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
-{
-	gmch_ctrl >>= SNB_GMCH_GGMS_SHIFT;
-	gmch_ctrl &= SNB_GMCH_GGMS_MASK;
-
-	if (gmch_ctrl)
-		return 1 << (20 + gmch_ctrl);
-
-	return 0;
-}
-
-static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	phys_addr_t phys_addr;
-	int ret;
-
-	/* For Modern GENs the PTEs and register space are split in the BAR */
-	phys_addr = pci_resource_start(pdev, 0) + pci_resource_len(pdev, 0) / 2;
-
-	/*
-	 * On BXT+/CNL+ writes larger than 64 bit to the GTT pagetable range
-	 * will be dropped. For WC mappings in general we have 64 byte burst
-	 * writes when the WC buffer is flushed, so we can't use it, but have to
-	 * resort to an uncached mapping. The WC issue is easily caught by the
-	 * readback check when writing GTT PTE entries.
-	 */
-	if (IS_GEN9_LP(dev_priv) || INTEL_GEN(dev_priv) >= 10)
-		ggtt->gsm = ioremap(phys_addr, size);
-	else
-		ggtt->gsm = ioremap_wc(phys_addr, size);
-	if (!ggtt->gsm) {
-		DRM_ERROR("Failed to map the ggtt page table\n");
-		return -ENOMEM;
-	}
-
-	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
-	if (ret) {
-		DRM_ERROR("Scratch setup failed\n");
-		/* iounmap will also get called at remove, but meh */
-		iounmap(ggtt->gsm);
-		return ret;
-	}
-
-	ggtt->vm.scratch[0].encode =
-		ggtt->vm.pte_encode(px_dma(&ggtt->vm.scratch[0]),
-				    I915_CACHE_NONE, 0);
-
-	return 0;
-}
-
-static void tgl_setup_private_ppat(struct intel_uncore *uncore)
-{
-	/* TGL doesn't support LLC or AGE settings */
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(0), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(1), GEN8_PPAT_WC);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(2), GEN8_PPAT_WT);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(3), GEN8_PPAT_UC);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(4), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(5), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(6), GEN8_PPAT_WB);
-	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
-}
-
-static void cnl_setup_private_ppat(struct intel_uncore *uncore)
-{
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(0),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(1),
-			   GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(2),
-			   GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(3),
-			   GEN8_PPAT_UC);
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(4),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(5),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(6),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
-	intel_uncore_write(uncore,
-			   GEN10_PAT_INDEX(7),
-			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
-}
-
-/* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
- * bits. When using advanced contexts each context stores its own PAT, but
- * writing this data shouldn't be harmful even in those cases. */
-static void bdw_setup_private_ppat(struct intel_uncore *uncore)
-{
-	u64 pat;
-
-	pat = GEN8_PPAT(0, GEN8_PPAT_WB | GEN8_PPAT_LLC) |	/* for normal objects, no eLLC */
-	      GEN8_PPAT(1, GEN8_PPAT_WC | GEN8_PPAT_LLCELLC) |	/* for something pointing to ptes? */
-	      GEN8_PPAT(2, GEN8_PPAT_WT | GEN8_PPAT_LLCELLC) |	/* for scanout with eLLC */
-	      GEN8_PPAT(3, GEN8_PPAT_UC) |			/* Uncached objects, mostly for scanout */
-	      GEN8_PPAT(4, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0)) |
-	      GEN8_PPAT(5, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1)) |
-	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
-	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
-
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
-}
-
-static void chv_setup_private_ppat(struct intel_uncore *uncore)
-{
-	u64 pat;
-
-	/*
-	 * Map WB on BDW to snooped on CHV.
-	 *
-	 * Only the snoop bit has meaning for CHV, the rest is
-	 * ignored.
-	 *
-	 * The hardware will never snoop for certain types of accesses:
-	 * - CPU GTT (GMADR->GGTT->no snoop->memory)
-	 * - PPGTT page tables
-	 * - some other special cycles
-	 *
-	 * As with BDW, we also need to consider the following for GT accesses:
-	 * "For GGTT, there is NO pat_sel[2:0] from the entry,
-	 * so RTL will always use the value corresponding to
-	 * pat_sel = 000".
-	 * Which means we must set the snoop bit in PAT entry 0
-	 * in order to keep the global status page working.
-	 */
-
-	pat = GEN8_PPAT(0, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(1, 0) |
-	      GEN8_PPAT(2, 0) |
-	      GEN8_PPAT(3, 0) |
-	      GEN8_PPAT(4, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(5, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
-	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
-
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
-	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
-}
-
-static void gen6_gmch_remove(struct i915_address_space *vm)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-
-	iounmap(ggtt->gsm);
-	cleanup_scratch_page(vm);
-}
-
-static void setup_private_pat(struct intel_uncore *uncore)
-{
-	struct drm_i915_private *i915 = uncore->i915;
-
-	GEM_BUG_ON(INTEL_GEN(i915) < 8);
-
-	if (INTEL_GEN(i915) >= 12)
-		tgl_setup_private_ppat(uncore);
-	else if (INTEL_GEN(i915) >= 10)
-		cnl_setup_private_ppat(uncore);
-	else if (IS_CHERRYVIEW(i915) || IS_GEN9_LP(i915))
-		chv_setup_private_ppat(uncore);
-	else
-		bdw_setup_private_ppat(uncore);
-}
-
-static struct resource pci_resource(struct pci_dev *pdev, int bar)
-{
-	return (struct resource)DEFINE_RES_MEM(pci_resource_start(pdev, bar),
-					       pci_resource_len(pdev, bar));
-}
-
-static int gen8_gmch_probe(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	unsigned int size;
-	u16 snb_gmch_ctl;
-	int err;
-
-	/* TODO: We're not aware of mappable constraints on gen8 yet */
-	if (!IS_DGFX(dev_priv)) {
-		ggtt->gmadr = pci_resource(pdev, 2);
-		ggtt->mappable_end = resource_size(&ggtt->gmadr);
-	}
-
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39));
-	if (err)
-		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
-
-	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-	if (IS_CHERRYVIEW(dev_priv))
-		size = chv_get_total_gtt_size(snb_gmch_ctl);
-	else
-		size = gen8_get_total_gtt_size(snb_gmch_ctl);
-
-	ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
-	ggtt->vm.cleanup = gen6_gmch_remove;
-	ggtt->vm.insert_page = gen8_ggtt_insert_page;
-	ggtt->vm.clear_range = nop_clear_range;
-	if (intel_scanout_needs_vtd_wa(dev_priv))
-		ggtt->vm.clear_range = gen8_ggtt_clear_range;
-
-	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
-
-	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
-	if (intel_ggtt_update_needs_vtd_wa(dev_priv) ||
-	    IS_CHERRYVIEW(dev_priv) /* fails with concurrent use/update */) {
-		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
-		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
-		if (ggtt->vm.clear_range != nop_clear_range)
-			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
-	}
-
-	ggtt->invalidate = gen6_ggtt_invalidate;
-
-	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
-	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
-	ggtt->vm.vma_ops.clear_pages = clear_pages;
-
-	ggtt->vm.pte_encode = gen8_pte_encode;
-
-	setup_private_pat(ggtt->vm.gt->uncore);
-
-	return ggtt_probe_common(ggtt, size);
-}
-
-static int gen6_gmch_probe(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	unsigned int size;
-	u16 snb_gmch_ctl;
-	int err;
-
-	ggtt->gmadr =
-		(struct resource) DEFINE_RES_MEM(pci_resource_start(pdev, 2),
-						 pci_resource_len(pdev, 2));
-	ggtt->mappable_end = resource_size(&ggtt->gmadr);
-
-	/* 64/512MB is the current min/max we actually know of, but this is just
-	 * a coarse sanity check.
-	 */
-	if (ggtt->mappable_end < (64<<20) || ggtt->mappable_end > (512<<20)) {
-		DRM_ERROR("Unknown GMADR size (%pa)\n", &ggtt->mappable_end);
-		return -ENXIO;
-	}
-
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(40));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(40));
-	if (err)
-		DRM_ERROR("Can't set DMA mask/consistent mask (%d)\n", err);
-	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
-
-	size = gen6_get_total_gtt_size(snb_gmch_ctl);
-	ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
-
-	ggtt->vm.clear_range = nop_clear_range;
-	if (!HAS_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
-		ggtt->vm.clear_range = gen6_ggtt_clear_range;
-	ggtt->vm.insert_page = gen6_ggtt_insert_page;
-	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
-	ggtt->vm.cleanup = gen6_gmch_remove;
-
-	ggtt->invalidate = gen6_ggtt_invalidate;
-
-	if (HAS_EDRAM(dev_priv))
-		ggtt->vm.pte_encode = iris_pte_encode;
-	else if (IS_HASWELL(dev_priv))
-		ggtt->vm.pte_encode = hsw_pte_encode;
-	else if (IS_VALLEYVIEW(dev_priv))
-		ggtt->vm.pte_encode = byt_pte_encode;
-	else if (INTEL_GEN(dev_priv) >= 7)
-		ggtt->vm.pte_encode = ivb_pte_encode;
-	else
-		ggtt->vm.pte_encode = snb_pte_encode;
-
-	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
-	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
-	ggtt->vm.vma_ops.clear_pages = clear_pages;
-
-	return ggtt_probe_common(ggtt, size);
-}
-
-static void i915_gmch_remove(struct i915_address_space *vm)
-{
-	intel_gmch_remove();
-}
-
-static int i915_gmch_probe(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *dev_priv = ggtt->vm.i915;
-	phys_addr_t gmadr_base;
-	int ret;
-
-	ret = intel_gmch_probe(dev_priv->bridge_dev, dev_priv->drm.pdev, NULL);
-	if (!ret) {
-		DRM_ERROR("failed to set up gmch\n");
-		return -EIO;
-	}
-
-	intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
-
-	ggtt->gmadr =
-		(struct resource) DEFINE_RES_MEM(gmadr_base,
-						 ggtt->mappable_end);
-
-	ggtt->do_idle_maps = needs_idle_maps(dev_priv);
-	ggtt->vm.insert_page = i915_ggtt_insert_page;
-	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
-	ggtt->vm.clear_range = i915_ggtt_clear_range;
-	ggtt->vm.cleanup = i915_gmch_remove;
-
-	ggtt->invalidate = gmch_ggtt_invalidate;
-
-	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
-	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
-	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
-	ggtt->vm.vma_ops.clear_pages = clear_pages;
-
-	if (unlikely(ggtt->do_idle_maps))
-		dev_notice(dev_priv->drm.dev,
-			   "Applying Ironlake quirks for intel_iommu\n");
-
-	return 0;
-}
-
-static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	int ret;
-
-	ggtt->vm.gt = gt;
-	ggtt->vm.i915 = i915;
-	ggtt->vm.dma = &i915->drm.pdev->dev;
-
-	if (INTEL_GEN(i915) <= 5)
-		ret = i915_gmch_probe(ggtt);
-	else if (INTEL_GEN(i915) < 8)
-		ret = gen6_gmch_probe(ggtt);
-	else
-		ret = gen8_gmch_probe(ggtt);
-	if (ret)
-		return ret;
-
-	if ((ggtt->vm.total - 1) >> 32) {
-		DRM_ERROR("We never expected a Global GTT with more than 32bits"
-			  " of address space! Found %lldM!\n",
-			  ggtt->vm.total >> 20);
-		ggtt->vm.total = 1ULL << 32;
-		ggtt->mappable_end =
-			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
-	}
-
-	if (ggtt->mappable_end > ggtt->vm.total) {
-		DRM_ERROR("mappable aperture extends past end of GGTT,"
-			  " aperture=%pa, total=%llx\n",
-			  &ggtt->mappable_end, ggtt->vm.total);
-		ggtt->mappable_end = ggtt->vm.total;
-	}
-
-	/* GMADR is the PCI mmio aperture into the global GTT. */
-	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
-	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
-	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
-			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
-
-	return 0;
-}
-
-/**
- * i915_ggtt_probe_hw - Probe GGTT hardware location
- * @i915: i915 device
- */
-int i915_ggtt_probe_hw(struct drm_i915_private *i915)
-{
-	int ret;
-
-	ret = ggtt_probe_hw(&i915->ggtt, &i915->gt);
-	if (ret)
-		return ret;
-
-	if (intel_vtd_active())
-		dev_info(i915->drm.dev, "VT-d active for gfx access\n");
-
-	return 0;
-}
-
-static int ggtt_init_hw(struct i915_ggtt *ggtt)
-{
-	struct drm_i915_private *i915 = ggtt->vm.i915;
-
-	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
-
-	ggtt->vm.is_ggtt = true;
-
-	/* Only VLV supports read-only GGTT mappings */
-	ggtt->vm.has_read_only = IS_VALLEYVIEW(i915);
-
-	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
-		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
-
-	if (ggtt->mappable_end) {
-		if (!io_mapping_init_wc(&ggtt->iomap,
-					ggtt->gmadr.start,
-					ggtt->mappable_end)) {
-			ggtt->vm.cleanup(&ggtt->vm);
-			return -EIO;
-		}
-
-		ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start,
-					      ggtt->mappable_end);
-	}
-
-	i915_ggtt_init_fences(ggtt);
-
-	return 0;
-}
-
-/**
- * i915_ggtt_init_hw - Initialize GGTT hardware
- * @dev_priv: i915 device
- */
-int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
-{
-	int ret;
-
-	stash_init(&dev_priv->mm.wc_stash);
-
-	/* Note that we use page colouring to enforce a guard page at the
-	 * end of the address space. This is required as the CS may prefetch
-	 * beyond the end of the batch buffer, across the page boundary,
-	 * and beyond the end of the GTT if we do not provide a guard.
-	 */
-	ret = ggtt_init_hw(&dev_priv->ggtt);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv)
-{
-	if (INTEL_GEN(dev_priv) < 6 && !intel_enable_gtt())
-		return -EIO;
-
-	return 0;
-}
-
-void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
-{
-	GEM_BUG_ON(ggtt->invalidate != gen6_ggtt_invalidate);
-
-	ggtt->invalidate = guc_ggtt_invalidate;
-
-	ggtt->invalidate(ggtt);
-}
-
-void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
-{
-	/* XXX Temporary pardon for error unload */
-	if (ggtt->invalidate == gen6_ggtt_invalidate)
-		return;
-
-	/* We should only be called after i915_ggtt_enable_guc() */
-	GEM_BUG_ON(ggtt->invalidate != guc_ggtt_invalidate);
-
-	ggtt->invalidate = gen6_ggtt_invalidate;
-
-	ggtt->invalidate(ggtt);
-}
-
-static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
-{
-	struct i915_vma *vma;
-	bool flush = false;
-	int open;
-
-	intel_gt_check_and_clear_faults(ggtt->vm.gt);
-
-	mutex_lock(&ggtt->vm.mutex);
-
-	/* First fill our portion of the GTT with scratch pages */
-	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
-
-	/* Skip rewriting PTE on VMA unbind. */
-	open = atomic_xchg(&ggtt->vm.open, 0);
-
-	/* clflush objects bound into the GGTT and rebind them. */
-	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
-		struct drm_i915_gem_object *obj = vma->obj;
-
-		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
-			continue;
-
-		clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
-		WARN_ON(i915_vma_bind(vma,
-				      obj ? obj->cache_level : 0,
-				      PIN_GLOBAL, NULL));
-		if (obj) { /* only used during resume => exclusive access */
-			flush |= fetch_and_zero(&obj->write_domain);
-			obj->read_domains |= I915_GEM_DOMAIN_GTT;
-		}
-	}
-
-	atomic_set(&ggtt->vm.open, open);
-	ggtt->invalidate(ggtt);
-
-	mutex_unlock(&ggtt->vm.mutex);
-
-	if (flush)
-		wbinvd_on_all_cpus();
-}
-
-void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915)
-{
-	struct i915_ggtt *ggtt = &i915->ggtt;
-
-	ggtt_restore_mappings(ggtt);
-
-	if (INTEL_GEN(i915) >= 8)
-		setup_private_pat(ggtt->vm.gt->uncore);
-}
-
-static struct scatterlist *
-rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset,
-	     unsigned int width, unsigned int height,
-	     unsigned int stride,
-	     struct sg_table *st, struct scatterlist *sg)
-{
-	unsigned int column, row;
-	unsigned int src_idx;
-
-	for (column = 0; column < width; column++) {
-		src_idx = stride * (height - 1) + column + offset;
-		for (row = 0; row < height; row++) {
-			st->nents++;
-			/* We don't need the pages, but need to initialize
-			 * the entries so the sg list can be happily traversed.
-			 * The only thing we need are DMA addresses.
-			 */
-			sg_set_page(sg, NULL, I915_GTT_PAGE_SIZE, 0);
-			sg_dma_address(sg) =
-				i915_gem_object_get_dma_address(obj, src_idx);
-			sg_dma_len(sg) = I915_GTT_PAGE_SIZE;
-			sg = sg_next(sg);
-			src_idx -= stride;
-		}
-	}
-
-	return sg;
-}
-
-static noinline struct sg_table *
-intel_rotate_pages(struct intel_rotation_info *rot_info,
-		   struct drm_i915_gem_object *obj)
-{
-	unsigned int size = intel_rotation_info_size(rot_info);
-	struct sg_table *st;
-	struct scatterlist *sg;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Allocate target SG list. */
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		goto err_st_alloc;
-
-	ret = sg_alloc_table(st, size, GFP_KERNEL);
-	if (ret)
-		goto err_sg_alloc;
-
-	st->nents = 0;
-	sg = st->sgl;
-
-	for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) {
-		sg = rotate_pages(obj, rot_info->plane[i].offset,
-				  rot_info->plane[i].width, rot_info->plane[i].height,
-				  rot_info->plane[i].stride, st, sg);
-	}
-
-	return st;
-
-err_sg_alloc:
-	kfree(st);
-err_st_alloc:
-
-	DRM_DEBUG_DRIVER("Failed to create rotated mapping for object size %zu! (%ux%u tiles, %u pages)\n",
-			 obj->base.size, rot_info->plane[0].width, rot_info->plane[0].height, size);
-
-	return ERR_PTR(ret);
-}
-
-static struct scatterlist *
-remap_pages(struct drm_i915_gem_object *obj, unsigned int offset,
-	    unsigned int width, unsigned int height,
-	    unsigned int stride,
-	    struct sg_table *st, struct scatterlist *sg)
-{
-	unsigned int row;
-
-	for (row = 0; row < height; row++) {
-		unsigned int left = width * I915_GTT_PAGE_SIZE;
-
-		while (left) {
-			dma_addr_t addr;
-			unsigned int length;
-
-			/* We don't need the pages, but need to initialize
-			 * the entries so the sg list can be happily traversed.
-			 * The only thing we need are DMA addresses.
-			 */
-
-			addr = i915_gem_object_get_dma_address_len(obj, offset, &length);
-
-			length = min(left, length);
-
-			st->nents++;
-
-			sg_set_page(sg, NULL, length, 0);
-			sg_dma_address(sg) = addr;
-			sg_dma_len(sg) = length;
-			sg = sg_next(sg);
-
-			offset += length / I915_GTT_PAGE_SIZE;
-			left -= length;
-		}
-
-		offset += stride - width;
-	}
-
-	return sg;
-}
-
-static noinline struct sg_table *
-intel_remap_pages(struct intel_remapped_info *rem_info,
-		  struct drm_i915_gem_object *obj)
-{
-	unsigned int size = intel_remapped_info_size(rem_info);
-	struct sg_table *st;
-	struct scatterlist *sg;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Allocate target SG list. */
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		goto err_st_alloc;
-
-	ret = sg_alloc_table(st, size, GFP_KERNEL);
-	if (ret)
-		goto err_sg_alloc;
-
-	st->nents = 0;
-	sg = st->sgl;
-
-	for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) {
-		sg = remap_pages(obj, rem_info->plane[i].offset,
-				 rem_info->plane[i].width, rem_info->plane[i].height,
-				 rem_info->plane[i].stride, st, sg);
-	}
-
-	i915_sg_trim(st);
-
-	return st;
-
-err_sg_alloc:
-	kfree(st);
-err_st_alloc:
-
-	DRM_DEBUG_DRIVER("Failed to create remapped mapping for object size %zu! (%ux%u tiles, %u pages)\n",
-			 obj->base.size, rem_info->plane[0].width, rem_info->plane[0].height, size);
-
-	return ERR_PTR(ret);
-}
-
-static noinline struct sg_table *
-intel_partial_pages(const struct i915_ggtt_view *view,
-		    struct drm_i915_gem_object *obj)
-{
-	struct sg_table *st;
-	struct scatterlist *sg, *iter;
-	unsigned int count = view->partial.size;
-	unsigned int offset;
-	int ret = -ENOMEM;
-
-	st = kmalloc(sizeof(*st), GFP_KERNEL);
-	if (!st)
-		goto err_st_alloc;
-
-	ret = sg_alloc_table(st, count, GFP_KERNEL);
-	if (ret)
-		goto err_sg_alloc;
-
-	iter = i915_gem_object_get_sg(obj, view->partial.offset, &offset);
-	GEM_BUG_ON(!iter);
-
-	sg = st->sgl;
-	st->nents = 0;
-	do {
-		unsigned int len;
-
-		len = min(iter->length - (offset << PAGE_SHIFT),
-			  count << PAGE_SHIFT);
-		sg_set_page(sg, NULL, len, 0);
-		sg_dma_address(sg) =
-			sg_dma_address(iter) + (offset << PAGE_SHIFT);
-		sg_dma_len(sg) = len;
-
-		st->nents++;
-		count -= len >> PAGE_SHIFT;
-		if (count == 0) {
-			sg_mark_end(sg);
-			i915_sg_trim(st); /* Drop any unused tail entries. */
-
-			return st;
-		}
-
-		sg = __sg_next(sg);
-		iter = __sg_next(iter);
-		offset = 0;
-	} while (1);
-
-err_sg_alloc:
-	kfree(st);
-err_st_alloc:
-	return ERR_PTR(ret);
-}
-
-static int
-i915_get_ggtt_vma_pages(struct i915_vma *vma)
-{
-	int ret;
-
-	/* The vma->pages are only valid within the lifespan of the borrowed
-	 * obj->mm.pages. When the obj->mm.pages sg_table is regenerated, so
-	 * must be the vma->pages. A simple rule is that vma->pages must only
-	 * be accessed when the obj->mm.pages are pinned.
-	 */
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(vma->obj));
-
-	switch (vma->ggtt_view.type) {
-	default:
-		GEM_BUG_ON(vma->ggtt_view.type);
-		/* fall through */
-	case I915_GGTT_VIEW_NORMAL:
-		vma->pages = vma->obj->mm.pages;
-		return 0;
-
-	case I915_GGTT_VIEW_ROTATED:
-		vma->pages =
-			intel_rotate_pages(&vma->ggtt_view.rotated, vma->obj);
-		break;
-
-	case I915_GGTT_VIEW_REMAPPED:
-		vma->pages =
-			intel_remap_pages(&vma->ggtt_view.remapped, vma->obj);
-		break;
-
-	case I915_GGTT_VIEW_PARTIAL:
-		vma->pages = intel_partial_pages(&vma->ggtt_view, vma->obj);
-		break;
-	}
-
-	ret = 0;
-	if (IS_ERR(vma->pages)) {
-		ret = PTR_ERR(vma->pages);
-		vma->pages = NULL;
-		DRM_ERROR("Failed to get pages for VMA view type %u (%d)!\n",
-			  vma->ggtt_view.type, ret);
-	}
-	return ret;
-}
-
 /**
  * i915_gem_gtt_reserve - reserve a node in an address_space (GTT)
  * @vm: the &struct i915_address_space
@@ -3827,6 +293,5 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftests/mock_gtt.c"
 #include "selftests/i915_gem_gtt.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 402283ce2864..f6226df9f972 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -1,638 +1,21 @@
+/* SPDX-License-Identifier: MIT */
 /*
- * Copyright © 2014 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- * Please try to maintain the following order within this file unless it makes
- * sense to do otherwise. From top to bottom:
- * 1. typedefs
- * 2. #defines, and macros
- * 3. structure definitions
- * 4. function prototypes
- *
- * Within each section, please try to order by generation in ascending order,
- * from top to bottom (ie. gen6 on the top, gen8 on the bottom).
+ * Copyright © 2020 Intel Corporation
  */
 
 #ifndef __I915_GEM_GTT_H__
 #define __I915_GEM_GTT_H__
 
 #include <linux/io-mapping.h>
-#include <linux/kref.h>
-#include <linux/mm.h>
-#include <linux/pagevec.h>
-#include <linux/workqueue.h>
+#include <linux/types.h>
 
 #include <drm/drm_mm.h>
 
-#include "gt/intel_reset.h"
-#include "i915_gem_fence_reg.h"
-#include "i915_request.h"
+#include "gt/intel_gtt.h"
 #include "i915_scatterlist.h"
-#include "i915_selftest.h"
-#include "gt/intel_timeline.h"
 
-#define I915_GTT_PAGE_SIZE_4K	BIT_ULL(12)
-#define I915_GTT_PAGE_SIZE_64K	BIT_ULL(16)
-#define I915_GTT_PAGE_SIZE_2M	BIT_ULL(21)
-
-#define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K
-#define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M
-
-#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE
-
-#define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE
-
-#define I915_FENCE_REG_NONE -1
-#define I915_MAX_NUM_FENCES 32
-/* 32 fences + sign bit for FENCE_REG_NONE */
-#define I915_MAX_NUM_FENCE_BITS 6
-
-struct drm_i915_file_private;
 struct drm_i915_gem_object;
-struct i915_vma;
-struct intel_gt;
-
-typedef u32 gen6_pte_t;
-typedef u64 gen8_pte_t;
-
-#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
-
-/* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
-#define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
-#define GEN6_PTE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-#define GEN6_PDE_ADDR_ENCODE(addr)	GEN6_GTT_ADDR_ENCODE(addr)
-#define GEN6_PTE_CACHE_LLC		(2 << 1)
-#define GEN6_PTE_UNCACHED		(1 << 1)
-#define GEN6_PTE_VALID			(1 << 0)
-
-#define I915_PTES(pte_len)		((unsigned int)(PAGE_SIZE / (pte_len)))
-#define I915_PTE_MASK(pte_len)		(I915_PTES(pte_len) - 1)
-#define I915_PDES			512
-#define I915_PDE_MASK			(I915_PDES - 1)
-#define NUM_PTE(pde_shift)     (1 << (pde_shift - PAGE_SHIFT))
-
-#define GEN6_PTES			I915_PTES(sizeof(gen6_pte_t))
-#define GEN6_PD_SIZE		        (I915_PDES * PAGE_SIZE)
-#define GEN6_PD_ALIGN			(PAGE_SIZE * 16)
-#define GEN6_PDE_SHIFT			22
-#define GEN6_PDE_VALID			(1 << 0)
-
-#define GEN7_PTE_CACHE_L3_LLC		(3 << 1)
-
-#define BYT_PTE_SNOOPED_BY_CPU_CACHES	(1 << 2)
-#define BYT_PTE_WRITEABLE		(1 << 1)
-
-/* Cacheability Control is a 4-bit value. The low three bits are stored in bits
- * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
- */
-#define HSW_CACHEABILITY_CONTROL(bits)	((((bits) & 0x7) << 1) | \
-					 (((bits) & 0x8) << (11 - 3)))
-#define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
-#define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
-#define HSW_WB_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x8)
-#define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
-#define HSW_WT_ELLC_LLC_AGE3		HSW_CACHEABILITY_CONTROL(0x7)
-#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
-#define HSW_PTE_UNCACHED		(0)
-#define HSW_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0x7f0))
-#define HSW_PTE_ADDR_ENCODE(addr)	HSW_GTT_ADDR_ENCODE(addr)
-
-/*
- * GEN8 32b style address is defined as a 3 level page table:
- * 31:30 | 29:21 | 20:12 |  11:0
- * PDPE  |  PDE  |  PTE  | offset
- * The difference as compared to normal x86 3 level page table is the PDPEs are
- * programmed via register.
- *
- * GEN8 48b style address is defined as a 4 level page table:
- * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
- * PML4E | PDPE  |  PDE  |  PTE  | offset
- */
-#define GEN8_3LVL_PDPES			4
-
-#define PPAT_UNCACHED			(_PAGE_PWT | _PAGE_PCD)
-#define PPAT_CACHED_PDE			0 /* WB LLC */
-#define PPAT_CACHED			_PAGE_PAT /* WB LLCeLLC */
-#define PPAT_DISPLAY_ELLC		_PAGE_PCD /* WT eLLC */
-
-#define CHV_PPAT_SNOOP			(1<<6)
-#define GEN8_PPAT_AGE(x)		((x)<<4)
-#define GEN8_PPAT_LLCeLLC		(3<<2)
-#define GEN8_PPAT_LLCELLC		(2<<2)
-#define GEN8_PPAT_LLC			(1<<2)
-#define GEN8_PPAT_WB			(3<<0)
-#define GEN8_PPAT_WT			(2<<0)
-#define GEN8_PPAT_WC			(1<<0)
-#define GEN8_PPAT_UC			(0<<0)
-#define GEN8_PPAT_ELLC_OVERRIDE		(0<<2)
-#define GEN8_PPAT(i, x)			((u64)(x) << ((i) * 8))
-
-#define GEN8_PDE_IPS_64K BIT(11)
-#define GEN8_PDE_PS_2M   BIT(7)
-
-#define for_each_sgt_daddr(__dp, __iter, __sgt) \
-	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
-
-struct intel_remapped_plane_info {
-	/* in gtt pages */
-	unsigned int width, height, stride, offset;
-} __packed;
-
-struct intel_remapped_info {
-	struct intel_remapped_plane_info plane[2];
-	unsigned int unused_mbz;
-} __packed;
-
-struct intel_rotation_info {
-	struct intel_remapped_plane_info plane[2];
-} __packed;
-
-struct intel_partial_info {
-	u64 offset;
-	unsigned int size;
-} __packed;
-
-enum i915_ggtt_view_type {
-	I915_GGTT_VIEW_NORMAL = 0,
-	I915_GGTT_VIEW_ROTATED = sizeof(struct intel_rotation_info),
-	I915_GGTT_VIEW_PARTIAL = sizeof(struct intel_partial_info),
-	I915_GGTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info),
-};
-
-static inline void assert_i915_gem_gtt_types(void)
-{
-	BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 8*sizeof(unsigned int));
-	BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int));
-	BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 9*sizeof(unsigned int));
-
-	/* Check that rotation/remapped shares offsets for simplicity */
-	BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) !=
-		     offsetof(struct intel_rotation_info, plane[0]));
-	BUILD_BUG_ON(offsetofend(struct intel_remapped_info, plane[1]) !=
-		     offsetofend(struct intel_rotation_info, plane[1]));
-
-	/* As we encode the size of each branch inside the union into its type,
-	 * we have to be careful that each branch has a unique size.
-	 */
-	switch ((enum i915_ggtt_view_type)0) {
-	case I915_GGTT_VIEW_NORMAL:
-	case I915_GGTT_VIEW_PARTIAL:
-	case I915_GGTT_VIEW_ROTATED:
-	case I915_GGTT_VIEW_REMAPPED:
-		/* gcc complains if these are identical cases */
-		break;
-	}
-}
-
-struct i915_ggtt_view {
-	enum i915_ggtt_view_type type;
-	union {
-		/* Members need to contain no holes/padding */
-		struct intel_partial_info partial;
-		struct intel_rotation_info rotated;
-		struct intel_remapped_info remapped;
-	};
-};
-
-enum i915_cache_level;
-
-struct i915_vma;
-
-struct i915_page_dma {
-	struct page *page;
-	union {
-		dma_addr_t daddr;
-
-		/* For gen6/gen7 only. This is the offset in the GGTT
-		 * where the page directory entries for PPGTT begin
-		 */
-		u32 ggtt_offset;
-	};
-};
-
-struct i915_page_scratch {
-	struct i915_page_dma base;
-	u64 encode;
-};
-
-struct i915_page_table {
-	struct i915_page_dma base;
-	atomic_t used;
-};
-
-struct i915_page_directory {
-	struct i915_page_table pt;
-	spinlock_t lock;
-	void *entry[512];
-};
-
-#define __px_choose_expr(x, type, expr, other) \
-	__builtin_choose_expr( \
-	__builtin_types_compatible_p(typeof(x), type) || \
-	__builtin_types_compatible_p(typeof(x), const type), \
-	({ type __x = (type)(x); expr; }), \
-	other)
-
-#define px_base(px) \
-	__px_choose_expr(px, struct i915_page_dma *, __x, \
-	__px_choose_expr(px, struct i915_page_scratch *, &__x->base, \
-	__px_choose_expr(px, struct i915_page_table *, &__x->base, \
-	__px_choose_expr(px, struct i915_page_directory *, &__x->pt.base, \
-	(void)0))))
-#define px_dma(px) (px_base(px)->daddr)
-
-#define px_pt(px) \
-	__px_choose_expr(px, struct i915_page_table *, __x, \
-	__px_choose_expr(px, struct i915_page_directory *, &__x->pt, \
-	(void)0))
-#define px_used(px) (&px_pt(px)->used)
-
-struct i915_vma_ops {
-	/* Map an object into an address space with the given cache flags. */
-	int (*bind_vma)(struct i915_vma *vma,
-			enum i915_cache_level cache_level,
-			u32 flags);
-	/*
-	 * Unmap an object from an address space. This usually consists of
-	 * setting the valid PTE entries to a reserved scratch page.
-	 */
-	void (*unbind_vma)(struct i915_vma *vma);
-
-	int (*set_pages)(struct i915_vma *vma);
-	void (*clear_pages)(struct i915_vma *vma);
-};
-
-struct pagestash {
-	spinlock_t lock;
-	struct pagevec pvec;
-};
-
-struct i915_address_space {
-	struct kref ref;
-	struct rcu_work rcu;
-
-	struct drm_mm mm;
-	struct intel_gt *gt;
-	struct drm_i915_private *i915;
-	struct device *dma;
-	/* Every address space belongs to a struct file - except for the global
-	 * GTT that is owned by the driver (and so @file is set to NULL). In
-	 * principle, no information should leak from one context to another
-	 * (or between files/processes etc) unless explicitly shared by the
-	 * owner. Tracking the owner is important in order to free up per-file
-	 * objects along with the file, to aide resource tracking, and to
-	 * assign blame.
-	 */
-	struct drm_i915_file_private *file;
-	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
-	u64 reserved;		/* size addr space reserved */
-
-	unsigned int bind_async_flags;
-
-	/*
-	 * Each active user context has its own address space (in full-ppgtt).
-	 * Since the vm may be shared between multiple contexts, we count how
-	 * many contexts keep us "open". Once open hits zero, we are closed
-	 * and do not allow any new attachments, and proceed to shutdown our
-	 * vma and page directories.
-	 */
-	atomic_t open;
-
-	struct mutex mutex; /* protects vma and our lists */
-#define VM_CLASS_GGTT 0
-#define VM_CLASS_PPGTT 1
-
-	struct i915_page_scratch scratch[4];
-	unsigned int scratch_order;
-	unsigned int top;
-
-	/**
-	 * List of vma currently bound.
-	 */
-	struct list_head bound_list;
-
-	struct pagestash free_pages;
-
-	/* Global GTT */
-	bool is_ggtt:1;
-
-	/* Some systems require uncached updates of the page directories */
-	bool pt_kmap_wc:1;
-
-	/* Some systems support read-only mappings for GGTT and/or PPGTT */
-	bool has_read_only:1;
-
-	u64 (*pte_encode)(dma_addr_t addr,
-			  enum i915_cache_level level,
-			  u32 flags); /* Create a valid PTE */
-#define PTE_READ_ONLY	(1<<0)
-
-	int (*allocate_va_range)(struct i915_address_space *vm,
-				 u64 start, u64 length);
-	void (*clear_range)(struct i915_address_space *vm,
-			    u64 start, u64 length);
-	void (*insert_page)(struct i915_address_space *vm,
-			    dma_addr_t addr,
-			    u64 offset,
-			    enum i915_cache_level cache_level,
-			    u32 flags);
-	void (*insert_entries)(struct i915_address_space *vm,
-			       struct i915_vma *vma,
-			       enum i915_cache_level cache_level,
-			       u32 flags);
-	void (*cleanup)(struct i915_address_space *vm);
-
-	struct i915_vma_ops vma_ops;
-
-	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
-	I915_SELFTEST_DECLARE(bool scrub_64K);
-};
-
-#define i915_is_ggtt(vm) ((vm)->is_ggtt)
-
-static inline bool
-i915_vm_is_4lvl(const struct i915_address_space *vm)
-{
-	return (vm->total - 1) >> 32;
-}
-
-static inline bool
-i915_vm_has_scratch_64K(struct i915_address_space *vm)
-{
-	return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
-}
-
-static inline bool
-i915_vm_has_cache_coloring(struct i915_address_space *vm)
-{
-	return i915_is_ggtt(vm) && vm->mm.color_adjust;
-}
-
-/* The Graphics Translation Table is the way in which GEN hardware translates a
- * Graphics Virtual Address into a Physical Address. In addition to the normal
- * collateral associated with any va->pa translations GEN hardware also has a
- * portion of the GTT which can be mapped by the CPU and remain both coherent
- * and correct (in cases like swizzling). That region is referred to as GMADR in
- * the spec.
- */
-struct i915_ggtt {
-	struct i915_address_space vm;
-
-	struct io_mapping iomap;	/* Mapping to our CPU mappable region */
-	struct resource gmadr;          /* GMADR resource */
-	resource_size_t mappable_end;	/* End offset that we can CPU map */
-
-	/** "Graphics Stolen Memory" holds the global PTEs */
-	void __iomem *gsm;
-	void (*invalidate)(struct i915_ggtt *ggtt);
-
-	/** PPGTT used for aliasing the PPGTT with the GTT */
-	struct i915_ppgtt *alias;
-
-	bool do_idle_maps;
-
-	int mtrr;
-
-	/** Bit 6 swizzling required for X tiling */
-	u32 bit_6_swizzle_x;
-	/** Bit 6 swizzling required for Y tiling */
-	u32 bit_6_swizzle_y;
-
-	u32 pin_bias;
-
-	unsigned int num_fences;
-	struct i915_fence_reg fence_regs[I915_MAX_NUM_FENCES];
-	struct list_head fence_list;
-
-	/** List of all objects in gtt_space, currently mmaped by userspace.
-	 * All objects within this list must also be on bound_list.
-	 */
-	struct list_head userfault_list;
-
-	/* Manual runtime pm autosuspend delay for user GGTT mmaps */
-	struct intel_wakeref_auto userfault_wakeref;
-
-	struct drm_mm_node error_capture;
-	struct drm_mm_node uc_fw;
-};
-
-struct i915_ppgtt {
-	struct i915_address_space vm;
-
-	struct i915_page_directory *pd;
-};
-
-struct gen6_ppgtt {
-	struct i915_ppgtt base;
-
-	struct i915_vma *vma;
-	gen6_pte_t __iomem *pd_addr;
-
-	atomic_t pin_count;
-	struct mutex pin_mutex;
-
-	bool scan_for_unused_pt;
-};
-
-#define __to_gen6_ppgtt(base) container_of(base, struct gen6_ppgtt, base)
-
-static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base)
-{
-	BUILD_BUG_ON(offsetof(struct gen6_ppgtt, base));
-	return __to_gen6_ppgtt(base);
-}
-
-/*
- * gen6_for_each_pde() iterates over every pde from start until start+length.
- * If start and start+length are not perfectly divisible, the macro will round
- * down and up as needed. Start=0 and length=2G effectively iterates over
- * every PDE in the system. The macro modifies ALL its parameters except 'pd',
- * so each of the other parameters should preferably be a simple variable, or
- * at most an lvalue with no side-effects!
- */
-#define gen6_for_each_pde(pt, pd, start, length, iter)			\
-	for (iter = gen6_pde_index(start);				\
-	     length > 0 && iter < I915_PDES &&				\
-		     (pt = i915_pt_entry(pd, iter), true);		\
-	     ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT);		\
-		    temp = min(temp - start, length);			\
-		    start += temp, length -= temp; }), ++iter)
-
-#define gen6_for_all_pdes(pt, pd, iter)					\
-	for (iter = 0;							\
-	     iter < I915_PDES &&					\
-		     (pt = i915_pt_entry(pd, iter), true);		\
-	     ++iter)
-
-static inline u32 i915_pte_index(u64 address, unsigned int pde_shift)
-{
-	const u32 mask = NUM_PTE(pde_shift) - 1;
-
-	return (address >> PAGE_SHIFT) & mask;
-}
-
-/* Helper to counts the number of PTEs within the given length. This count
- * does not cross a page table boundary, so the max value would be
- * GEN6_PTES for GEN6, and GEN8_PTES for GEN8.
-*/
-static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
-{
-	const u64 mask = ~((1ULL << pde_shift) - 1);
-	u64 end;
-
-	GEM_BUG_ON(length == 0);
-	GEM_BUG_ON(offset_in_page(addr | length));
-
-	end = addr + length;
-
-	if ((addr & mask) != (end & mask))
-		return NUM_PTE(pde_shift) - i915_pte_index(addr, pde_shift);
-
-	return i915_pte_index(end, pde_shift) - i915_pte_index(addr, pde_shift);
-}
-
-static inline u32 i915_pde_index(u64 addr, u32 shift)
-{
-	return (addr >> shift) & I915_PDE_MASK;
-}
-
-static inline u32 gen6_pte_index(u32 addr)
-{
-	return i915_pte_index(addr, GEN6_PDE_SHIFT);
-}
-
-static inline u32 gen6_pte_count(u32 addr, u32 length)
-{
-	return i915_pte_count(addr, length, GEN6_PDE_SHIFT);
-}
-
-static inline u32 gen6_pde_index(u32 addr)
-{
-	return i915_pde_index(addr, GEN6_PDE_SHIFT);
-}
-
-static inline struct i915_page_table *
-i915_pt_entry(const struct i915_page_directory * const pd,
-	      const unsigned short n)
-{
-	return pd->entry[n];
-}
-
-static inline struct i915_page_directory *
-i915_pd_entry(const struct i915_page_directory * const pdp,
-	      const unsigned short n)
-{
-	return pdp->entry[n];
-}
-
-static inline dma_addr_t
-i915_page_dir_dma_addr(const struct i915_ppgtt *ppgtt, const unsigned int n)
-{
-	struct i915_page_dma *pt = ppgtt->pd->entry[n];
-
-	return px_dma(pt ?: px_base(&ppgtt->vm.scratch[ppgtt->vm.top]));
-}
-
-static inline struct i915_ggtt *
-i915_vm_to_ggtt(struct i915_address_space *vm)
-{
-	BUILD_BUG_ON(offsetof(struct i915_ggtt, vm));
-	GEM_BUG_ON(!i915_is_ggtt(vm));
-	return container_of(vm, struct i915_ggtt, vm);
-}
-
-static inline struct i915_ppgtt *
-i915_vm_to_ppgtt(struct i915_address_space *vm)
-{
-	BUILD_BUG_ON(offsetof(struct i915_ppgtt, vm));
-	GEM_BUG_ON(i915_is_ggtt(vm));
-	return container_of(vm, struct i915_ppgtt, vm);
-}
-
-int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv);
-int i915_ggtt_init_hw(struct drm_i915_private *dev_priv);
-int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv);
-void i915_ggtt_enable_guc(struct i915_ggtt *ggtt);
-void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
-int i915_init_ggtt(struct drm_i915_private *dev_priv);
-void i915_ggtt_driver_release(struct drm_i915_private *dev_priv);
-
-static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt)
-{
-	return ggtt->mappable_end > 0;
-}
-
-int i915_ppgtt_init_hw(struct intel_gt *gt);
-
-struct i915_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv);
-
-static inline struct i915_address_space *
-i915_vm_get(struct i915_address_space *vm)
-{
-	kref_get(&vm->ref);
-	return vm;
-}
-
-void i915_vm_release(struct kref *kref);
-
-static inline void i915_vm_put(struct i915_address_space *vm)
-{
-	kref_put(&vm->ref, i915_vm_release);
-}
-
-static inline struct i915_address_space *
-i915_vm_open(struct i915_address_space *vm)
-{
-	GEM_BUG_ON(!atomic_read(&vm->open));
-	atomic_inc(&vm->open);
-	return i915_vm_get(vm);
-}
-
-static inline bool
-i915_vm_tryopen(struct i915_address_space *vm)
-{
-	if (atomic_add_unless(&vm->open, 1, 0))
-		return i915_vm_get(vm);
-
-	return false;
-}
-
-void __i915_vm_close(struct i915_address_space *vm);
-
-static inline void
-i915_vm_close(struct i915_address_space *vm)
-{
-	GEM_BUG_ON(!atomic_read(&vm->open));
-	if (atomic_dec_and_test(&vm->open))
-		__i915_vm_close(vm);
-
-	i915_vm_put(vm);
-}
-
-int gen6_ppgtt_pin(struct i915_ppgtt *base);
-void gen6_ppgtt_unpin(struct i915_ppgtt *base);
-void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
-
-void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
-void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);
+struct i915_address_space;
 
 int __must_check i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj,
 					    struct sg_table *pages);
@@ -663,6 +46,6 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 #define PIN_GLOBAL		BIT_ULL(10) /* I915_VMA_GLOBAL_BIND */
 #define PIN_USER		BIT_ULL(11) /* I915_VMA_LOCAL_BIND */
 
-#define PIN_OFFSET_MASK		(-I915_GTT_PAGE_SIZE)
+#define PIN_OFFSET_MASK		I915_GTT_PAGE_MASK
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index cf8a8c3ef047..54fce81d5724 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -2,6 +2,7 @@
  * SPDX-License-Identifier: MIT
  */
 
+#include "gem/i915_gem_mman.h"
 #include "gt/intel_engine_user.h"
 
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c
index be127cd28931..3aa213684293 100644
--- a/drivers/gpu/drm/i915/i915_globals.c
+++ b/drivers/gpu/drm/i915/i915_globals.c
@@ -20,7 +20,10 @@ static LIST_HEAD(globals);
 static atomic_t active;
 static atomic_t epoch;
 static struct park_work {
-	struct rcu_work work;
+	struct delayed_work work;
+	struct rcu_head rcu;
+	unsigned long flags;
+#define PENDING 0
 	int epoch;
 } park;
 
@@ -37,11 +40,33 @@ static void i915_globals_shrink(void)
 		global->shrink();
 }
 
+static void __i915_globals_grace(struct rcu_head *rcu)
+{
+	/* Ratelimit parking as shrinking is quite slow */
+	schedule_delayed_work(&park.work, round_jiffies_up_relative(2 * HZ));
+}
+
+static void __i915_globals_queue_rcu(void)
+{
+	park.epoch = atomic_inc_return(&epoch);
+	if (!atomic_read(&active)) {
+		init_rcu_head(&park.rcu);
+		call_rcu(&park.rcu, __i915_globals_grace);
+	}
+}
+
 static void __i915_globals_park(struct work_struct *work)
 {
+	destroy_rcu_head(&park.rcu);
+
 	/* Confirm nothing woke up in the last grace period */
-	if (park.epoch == atomic_read(&epoch))
-		i915_globals_shrink();
+	if (park.epoch != atomic_read(&epoch)) {
+		__i915_globals_queue_rcu();
+		return;
+	}
+
+	clear_bit(PENDING, &park.flags);
+	i915_globals_shrink();
 }
 
 void __init i915_global_register(struct i915_global *global)
@@ -85,7 +110,7 @@ int __init i915_globals_init(void)
 		}
 	}
 
-	INIT_RCU_WORK(&park.work, __i915_globals_park);
+	INIT_DELAYED_WORK(&park.work, __i915_globals_park);
 	return 0;
 }
 
@@ -103,8 +128,9 @@ void i915_globals_park(void)
 	if (!atomic_dec_and_test(&active))
 		return;
 
-	park.epoch = atomic_inc_return(&epoch);
-	queue_rcu_work(system_wq, &park.work);
+	/* Queue cleanup after the next RCU grace period has freed slabs */
+	if (!test_and_set_bit(PENDING, &park.flags))
+		__i915_globals_queue_rcu();
 }
 
 void i915_globals_unpark(void)
@@ -113,12 +139,21 @@ void i915_globals_unpark(void)
 	atomic_inc(&active);
 }
 
+static void __exit __i915_globals_flush(void)
+{
+	atomic_inc(&active); /* skip shrinking */
+
+	rcu_barrier(); /* wait for the work to be queued */
+	flush_delayed_work(&park.work);
+
+	atomic_dec(&active);
+}
+
 void __exit i915_globals_exit(void)
 {
-	/* Flush any residual park_work */
-	atomic_inc(&epoch);
-	flush_rcu_work(&park.work);
+	GEM_BUG_ON(atomic_read(&active));
 
+	__i915_globals_flush();
 	__i915_globals_cleanup();
 
 	/* And ensure that our DESTROY_BY_RCU slabs are truly destroyed */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 3c85cb0ee99f..4c1836f0a991 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -41,6 +41,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_lmem.h"
+#include "gt/intel_gt_pm.h"
 
 #include "i915_drv.h"
 #include "i915_gpu_error.h"
@@ -232,14 +233,13 @@ static void pool_free(struct pagevec *pv, void *addr)
 
 #ifdef CONFIG_DRM_I915_COMPRESS_ERROR
 
-struct compress {
+struct i915_vma_compress {
 	struct pagevec pool;
 	struct z_stream_s zstream;
 	void *tmp;
-	bool wc;
 };
 
-static bool compress_init(struct compress *c)
+static bool compress_init(struct i915_vma_compress *c)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
@@ -261,7 +261,7 @@ static bool compress_init(struct compress *c)
 	return true;
 }
 
-static bool compress_start(struct compress *c)
+static bool compress_start(struct i915_vma_compress *c)
 {
 	struct z_stream_s *zstream = &c->zstream;
 	void *workspace = zstream->workspace;
@@ -272,8 +272,8 @@ static bool compress_start(struct compress *c)
 	return zlib_deflateInit(zstream, Z_DEFAULT_COMPRESSION) == Z_OK;
 }
 
-static void *compress_next_page(struct compress *c,
-				struct drm_i915_error_object *dst)
+static void *compress_next_page(struct i915_vma_compress *c,
+				struct i915_vma_coredump *dst)
 {
 	void *page;
 
@@ -287,14 +287,15 @@ static void *compress_next_page(struct compress *c,
 	return dst->pages[dst->page_count++] = page;
 }
 
-static int compress_page(struct compress *c,
+static int compress_page(struct i915_vma_compress *c,
 			 void *src,
-			 struct drm_i915_error_object *dst)
+			 struct i915_vma_coredump *dst,
+			 bool wc)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
 	zstream->next_in = src;
-	if (c->wc && c->tmp && i915_memcpy_from_wc(c->tmp, src, PAGE_SIZE))
+	if (wc && c->tmp && i915_memcpy_from_wc(c->tmp, src, PAGE_SIZE))
 		zstream->next_in = c->tmp;
 	zstream->avail_in = PAGE_SIZE;
 
@@ -318,8 +319,8 @@ static int compress_page(struct compress *c,
 	return 0;
 }
 
-static int compress_flush(struct compress *c,
-			  struct drm_i915_error_object *dst)
+static int compress_flush(struct i915_vma_compress *c,
+			  struct i915_vma_coredump *dst)
 {
 	struct z_stream_s *zstream = &c->zstream;
 
@@ -347,12 +348,12 @@ end:
 	return 0;
 }
 
-static void compress_finish(struct compress *c)
+static void compress_finish(struct i915_vma_compress *c)
 {
 	zlib_deflateEnd(&c->zstream);
 }
 
-static void compress_fini(struct compress *c)
+static void compress_fini(struct i915_vma_compress *c)
 {
 	kfree(c->zstream.workspace);
 	if (c->tmp)
@@ -367,24 +368,24 @@ static void err_compression_marker(struct drm_i915_error_state_buf *m)
 
 #else
 
-struct compress {
+struct i915_vma_compress {
 	struct pagevec pool;
-	bool wc;
 };
 
-static bool compress_init(struct compress *c)
+static bool compress_init(struct i915_vma_compress *c)
 {
 	return pool_init(&c->pool, ALLOW_FAIL) == 0;
 }
 
-static bool compress_start(struct compress *c)
+static bool compress_start(struct i915_vma_compress *c)
 {
 	return true;
 }
 
-static int compress_page(struct compress *c,
+static int compress_page(struct i915_vma_compress *c,
 			 void *src,
-			 struct drm_i915_error_object *dst)
+			 struct i915_vma_coredump *dst,
+			 bool wc)
 {
 	void *ptr;
 
@@ -392,24 +393,24 @@ static int compress_page(struct compress *c,
 	if (!ptr)
 		return -ENOMEM;
 
-	if (!(c->wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE)))
+	if (!(wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE)))
 		memcpy(ptr, src, PAGE_SIZE);
 	dst->pages[dst->page_count++] = ptr;
 
 	return 0;
 }
 
-static int compress_flush(struct compress *c,
-			  struct drm_i915_error_object *dst)
+static int compress_flush(struct i915_vma_compress *c,
+			  struct i915_vma_coredump *dst)
 {
 	return 0;
 }
 
-static void compress_finish(struct compress *c)
+static void compress_finish(struct i915_vma_compress *c)
 {
 }
 
-static void compress_fini(struct compress *c)
+static void compress_fini(struct i915_vma_compress *c)
 {
 	pool_fini(&c->pool);
 }
@@ -422,7 +423,7 @@ static void err_compression_marker(struct drm_i915_error_state_buf *m)
 #endif
 
 static void error_print_instdone(struct drm_i915_error_state_buf *m,
-				 const struct drm_i915_error_engine *ee)
+				 const struct intel_engine_coredump *ee)
 {
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(m->i915)->sseu;
 	int slice;
@@ -453,40 +454,56 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 
 static void error_print_request(struct drm_i915_error_state_buf *m,
 				const char *prefix,
-				const struct drm_i915_error_request *erq,
-				const unsigned long epoch)
+				const struct i915_request_coredump *erq)
 {
 	if (!erq->seqno)
 		return;
 
-	err_printf(m, "%s pid %d, seqno %8x:%08x%s%s, prio %d, emitted %dms, start %08x, head %08x, tail %08x\n",
+	err_printf(m, "%s pid %d, seqno %8x:%08x%s%s, prio %d, start %08x, head %08x, tail %08x\n",
 		   prefix, erq->pid, erq->context, erq->seqno,
 		   test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 			    &erq->flags) ? "!" : "",
 		   test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 			    &erq->flags) ? "+" : "",
 		   erq->sched_attr.priority,
-		   jiffies_to_msecs(erq->jiffies - epoch),
 		   erq->start, erq->head, erq->tail);
 }
 
 static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
-				const struct drm_i915_error_context *ctx)
+				const struct i915_gem_context_coredump *ctx)
 {
 	err_printf(m, "%s%s[%d] prio %d, guilty %d active %d\n",
 		   header, ctx->comm, ctx->pid, ctx->sched_attr.priority,
 		   ctx->guilty, ctx->active);
 }
 
+static struct i915_vma_coredump *
+__find_vma(struct i915_vma_coredump *vma, const char *name)
+{
+	while (vma) {
+		if (strcmp(vma->name, name) == 0)
+			return vma;
+		vma = vma->next;
+	}
+
+	return NULL;
+}
+
+static struct i915_vma_coredump *
+find_batch(const struct intel_engine_coredump *ee)
+{
+	return __find_vma(ee->vma, "batch");
+}
+
 static void error_print_engine(struct drm_i915_error_state_buf *m,
-			       const struct drm_i915_error_engine *ee,
-			       const unsigned long epoch)
+			       const struct intel_engine_coredump *ee)
 {
+	struct i915_vma_coredump *batch;
 	int n;
 
 	err_printf(m, "%s command stream:\n", ee->engine->name);
-	err_printf(m, "  IDLE?: %s\n", yesno(ee->idle));
+	err_printf(m, "  CCID:  0x%08x\n", ee->ccid);
 	err_printf(m, "  START: 0x%08x\n", ee->start);
 	err_printf(m, "  HEAD:  0x%08x [0x%08x]\n", ee->head, ee->rq_head);
 	err_printf(m, "  TAIL:  0x%08x [0x%08x, 0x%08x]\n",
@@ -501,9 +518,10 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 
 	error_print_instdone(m, ee);
 
-	if (ee->batchbuffer) {
-		u64 start = ee->batchbuffer->gtt_offset;
-		u64 end = start + ee->batchbuffer->gtt_size;
+	batch = find_batch(ee);
+	if (batch) {
+		u64 start = batch->gtt_offset;
+		u64 end = start + batch->gtt_size;
 
 		err_printf(m, "  batch: [0x%08x_%08x, 0x%08x_%08x]\n",
 			   upper_32_bits(start), lower_32_bits(start),
@@ -535,13 +553,11 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 				   ee->vm_info.pp_dir_base);
 		}
 	}
-	err_printf(m, "  ring->head: 0x%08x\n", ee->cpu_ring_head);
-	err_printf(m, "  ring->tail: 0x%08x\n", ee->cpu_ring_tail);
 	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
 	for (n = 0; n < ee->num_ports; n++) {
 		err_printf(m, "  ELSP[%d]:", n);
-		error_print_request(m, " ", &ee->execlist[n], epoch);
+		error_print_request(m, " ", &ee->execlist[n]);
 	}
 
 	error_print_context(m, "  Active context: ", &ee->context);
@@ -556,38 +572,35 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-static void print_error_obj(struct drm_i915_error_state_buf *m,
+static void print_error_vma(struct drm_i915_error_state_buf *m,
 			    const struct intel_engine_cs *engine,
-			    const char *name,
-			    const struct drm_i915_error_object *obj)
+			    const struct i915_vma_coredump *vma)
 {
 	char out[ASCII85_BUFSZ];
 	int page;
 
-	if (!obj)
+	if (!vma)
 		return;
 
-	if (name) {
-		err_printf(m, "%s --- %s = 0x%08x %08x\n",
-			   engine ? engine->name : "global", name,
-			   upper_32_bits(obj->gtt_offset),
-			   lower_32_bits(obj->gtt_offset));
-	}
+	err_printf(m, "%s --- %s = 0x%08x %08x\n",
+		   engine ? engine->name : "global", vma->name,
+		   upper_32_bits(vma->gtt_offset),
+		   lower_32_bits(vma->gtt_offset));
 
-	if (obj->gtt_page_sizes > I915_GTT_PAGE_SIZE_4K)
-		err_printf(m, "gtt_page_sizes = 0x%08x\n", obj->gtt_page_sizes);
+	if (vma->gtt_page_sizes > I915_GTT_PAGE_SIZE_4K)
+		err_printf(m, "gtt_page_sizes = 0x%08x\n", vma->gtt_page_sizes);
 
 	err_compression_marker(m);
-	for (page = 0; page < obj->page_count; page++) {
+	for (page = 0; page < vma->page_count; page++) {
 		int i, len;
 
 		len = PAGE_SIZE;
-		if (page == obj->page_count - 1)
-			len -= obj->unused;
+		if (page == vma->page_count - 1)
+			len -= vma->unused;
 		len = ascii85_encode_len(len);
 
 		for (i = 0; i < len; i++)
-			err_puts(m, ascii85_encode(obj->pages[page][i], out));
+			err_puts(m, ascii85_encode(vma->pages[page][i], out));
 	}
 	err_puts(m, "\n");
 }
@@ -599,9 +612,10 @@ static void err_print_capabilities(struct drm_i915_error_state_buf *m,
 {
 	struct drm_printer p = i915_error_printer(m);
 
-	intel_device_info_dump_flags(info, &p);
+	intel_device_info_print_static(info, &p);
+	intel_device_info_print_runtime(runtime, &p);
+	intel_device_info_print_topology(&runtime->sseu, &p);
 	intel_driver_caps_print(caps, &p);
-	intel_device_info_dump_topology(&runtime->sseu, &p);
 }
 
 static void err_print_params(struct drm_i915_error_state_buf *m,
@@ -625,18 +639,13 @@ static void err_print_pciid(struct drm_i915_error_state_buf *m,
 }
 
 static void err_print_uc(struct drm_i915_error_state_buf *m,
-			 const struct i915_error_uc *error_uc)
+			 const struct intel_uc_coredump *error_uc)
 {
 	struct drm_printer p = i915_error_printer(m);
-	const struct i915_gpu_state *error =
-		container_of(error_uc, typeof(*error), uc);
-
-	if (!error->device_info.has_gt_uc)
-		return;
 
 	intel_uc_fw_dump(&error_uc->guc_fw, &p);
 	intel_uc_fw_dump(&error_uc->huc_fw, &p);
-	print_error_obj(m, NULL, "GuC log buffer", error_uc->guc_log);
+	print_error_vma(m, NULL, error_uc->guc_log);
 }
 
 static void err_free_sgl(struct scatterlist *sgl)
@@ -656,12 +665,69 @@ static void err_free_sgl(struct scatterlist *sgl)
 	}
 }
 
+static void err_print_gt(struct drm_i915_error_state_buf *m,
+			 struct intel_gt_coredump *gt)
+{
+	const struct intel_engine_coredump *ee;
+	int i;
+
+	err_printf(m, "GT awake: %s\n", yesno(gt->awake));
+	err_printf(m, "EIR: 0x%08x\n", gt->eir);
+	err_printf(m, "IER: 0x%08x\n", gt->ier);
+	for (i = 0; i < gt->ngtier; i++)
+		err_printf(m, "GTIER[%d]: 0x%08x\n", i, gt->gtier[i]);
+	err_printf(m, "PGTBL_ER: 0x%08x\n", gt->pgtbl_er);
+	err_printf(m, "FORCEWAKE: 0x%08x\n", gt->forcewake);
+	err_printf(m, "DERRMR: 0x%08x\n", gt->derrmr);
+
+	for (i = 0; i < gt->nfence; i++)
+		err_printf(m, "  fence[%d] = %08llx\n", i, gt->fence[i]);
+
+	if (IS_GEN_RANGE(m->i915, 6, 11)) {
+		err_printf(m, "ERROR: 0x%08x\n", gt->error);
+		err_printf(m, "DONE_REG: 0x%08x\n", gt->done_reg);
+	}
+
+	if (INTEL_GEN(m->i915) >= 8)
+		err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n",
+			   gt->fault_data1, gt->fault_data0);
+
+	if (IS_GEN(m->i915, 7))
+		err_printf(m, "ERR_INT: 0x%08x\n", gt->err_int);
+
+	if (IS_GEN_RANGE(m->i915, 8, 11))
+		err_printf(m, "GTT_CACHE_EN: 0x%08x\n", gt->gtt_cache);
+
+	if (IS_GEN(m->i915, 12))
+		err_printf(m, "AUX_ERR_DBG: 0x%08x\n", gt->aux_err);
+
+	if (INTEL_GEN(m->i915) >= 12) {
+		int i;
+
+		for (i = 0; i < GEN12_SFC_DONE_MAX; i++)
+			err_printf(m, "  SFC_DONE[%d]: 0x%08x\n", i,
+				   gt->sfc_done[i]);
+
+		err_printf(m, "  GAM_DONE: 0x%08x\n", gt->gam_done);
+	}
+
+	for (ee = gt->engine; ee; ee = ee->next) {
+		const struct i915_vma_coredump *vma;
+
+		error_print_engine(m, ee);
+		for (vma = ee->vma; vma; vma = vma->next)
+			print_error_vma(m, ee->engine, vma);
+	}
+
+	if (gt->uc)
+		err_print_uc(m, gt->uc);
+}
+
 static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
-			       struct i915_gpu_state *error)
+			       struct i915_gpu_coredump *error)
 {
-	const struct drm_i915_error_engine *ee;
+	const struct intel_engine_coredump *ee;
 	struct timespec64 ts;
-	int i, j;
 
 	if (*error->error_msg)
 		err_printf(m, "%s\n", error->error_msg);
@@ -681,7 +747,7 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	err_printf(m, "Capture: %lu jiffies; %d ms ago\n",
 		   error->capture, jiffies_to_msecs(jiffies - error->capture));
 
-	for (ee = error->engine; ee; ee = ee->next)
+	for (ee = error->gt ? error->gt->engine : NULL; ee; ee = ee->next)
 		err_printf(m, "Active process (on ring %s): %s [%d]\n",
 			   ee->engine->name,
 			   ee->context.comm,
@@ -707,90 +773,11 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 			   CSR_VERSION_MINOR(csr->version));
 	}
 
-	err_printf(m, "GT awake: %s\n", yesno(error->awake));
 	err_printf(m, "RPM wakelock: %s\n", yesno(error->wakelock));
 	err_printf(m, "PM suspended: %s\n", yesno(error->suspended));
-	err_printf(m, "EIR: 0x%08x\n", error->eir);
-	err_printf(m, "IER: 0x%08x\n", error->ier);
-	for (i = 0; i < error->ngtier; i++)
-		err_printf(m, "GTIER[%d]: 0x%08x\n", i, error->gtier[i]);
-	err_printf(m, "PGTBL_ER: 0x%08x\n", error->pgtbl_er);
-	err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake);
-	err_printf(m, "DERRMR: 0x%08x\n", error->derrmr);
-	err_printf(m, "CCID: 0x%08x\n", error->ccid);
-
-	for (i = 0; i < error->nfence; i++)
-		err_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
-
-	if (IS_GEN_RANGE(m->i915, 6, 11)) {
-		err_printf(m, "ERROR: 0x%08x\n", error->error);
-		err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg);
-	}
-
-	if (INTEL_GEN(m->i915) >= 8)
-		err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n",
-			   error->fault_data1, error->fault_data0);
-
-	if (IS_GEN(m->i915, 7))
-		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
-
-	if (IS_GEN_RANGE(m->i915, 8, 11))
-		err_printf(m, "GTT_CACHE_EN: 0x%08x\n", error->gtt_cache);
-
-	if (IS_GEN(m->i915, 12))
-		err_printf(m, "AUX_ERR_DBG: 0x%08x\n", error->aux_err);
-
-	if (INTEL_GEN(m->i915) >= 12) {
-		int i;
-
-		for (i = 0; i < GEN12_SFC_DONE_MAX; i++)
-			err_printf(m, "  SFC_DONE[%d]: 0x%08x\n", i,
-				   error->sfc_done[i]);
-
-		err_printf(m, "  GAM_DONE: 0x%08x\n", error->gam_done);
-	}
-
-	for (ee = error->engine; ee; ee = ee->next)
-		error_print_engine(m, ee, error->capture);
-
-	for (ee = error->engine; ee; ee = ee->next) {
-		const struct drm_i915_error_object *obj;
-
-		obj = ee->batchbuffer;
-		if (obj) {
-			err_puts(m, ee->engine->name);
-			if (ee->context.pid)
-				err_printf(m, " (submitted by %s [%d])",
-					   ee->context.comm,
-					   ee->context.pid);
-			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
-				   upper_32_bits(obj->gtt_offset),
-				   lower_32_bits(obj->gtt_offset));
-			print_error_obj(m, ee->engine, NULL, obj);
-		}
 
-		for (j = 0; j < ee->user_bo_count; j++)
-			print_error_obj(m, ee->engine, "user", ee->user_bo[j]);
-
-		if (ee->num_requests) {
-			err_printf(m, "%s --- %d requests\n",
-				   ee->engine->name,
-				   ee->num_requests);
-			for (j = 0; j < ee->num_requests; j++)
-				error_print_request(m, " ",
-						    &ee->requests[j],
-						    error->capture);
-		}
-
-		print_error_obj(m, ee->engine, "ringbuffer", ee->ringbuffer);
-		print_error_obj(m, ee->engine, "HW Status", ee->hws_page);
-		print_error_obj(m, ee->engine, "HW context", ee->ctx);
-		print_error_obj(m, ee->engine, "WA context", ee->wa_ctx);
-		print_error_obj(m, ee->engine,
-				"WA batchbuffer", ee->wa_batchbuffer);
-		print_error_obj(m, ee->engine,
-				"NULL context", ee->default_state);
-	}
+	if (error->gt)
+		err_print_gt(m, error->gt);
 
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
@@ -801,10 +788,9 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	err_print_capabilities(m, &error->device_info, &error->runtime_info,
 			       &error->driver_caps);
 	err_print_params(m, &error->params);
-	err_print_uc(m, &error->uc);
 }
 
-static int err_print_to_sgl(struct i915_gpu_state *error)
+static int err_print_to_sgl(struct i915_gpu_coredump *error)
 {
 	struct drm_i915_error_state_buf m;
 
@@ -841,8 +827,8 @@ static int err_print_to_sgl(struct i915_gpu_state *error)
 	return 0;
 }
 
-ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
-				      char *buf, loff_t off, size_t rem)
+ssize_t i915_gpu_coredump_copy_to_buffer(struct i915_gpu_coredump *error,
+					 char *buf, loff_t off, size_t rem)
 {
 	struct scatterlist *sg;
 	size_t count;
@@ -905,85 +891,88 @@ ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
 	return count;
 }
 
-static void i915_error_object_free(struct drm_i915_error_object *obj)
+static void i915_vma_coredump_free(struct i915_vma_coredump *vma)
 {
-	int page;
+	while (vma) {
+		struct i915_vma_coredump *next = vma->next;
+		int page;
 
-	if (obj == NULL)
-		return;
-
-	for (page = 0; page < obj->page_count; page++)
-		free_page((unsigned long)obj->pages[page]);
+		for (page = 0; page < vma->page_count; page++)
+			free_page((unsigned long)vma->pages[page]);
 
-	kfree(obj);
+		kfree(vma);
+		vma = next;
+	}
 }
 
-
-static void cleanup_params(struct i915_gpu_state *error)
+static void cleanup_params(struct i915_gpu_coredump *error)
 {
 	i915_params_free(&error->params);
 }
 
-static void cleanup_uc_state(struct i915_gpu_state *error)
+static void cleanup_uc(struct intel_uc_coredump *uc)
 {
-	struct i915_error_uc *error_uc = &error->uc;
+	kfree(uc->guc_fw.path);
+	kfree(uc->huc_fw.path);
+	i915_vma_coredump_free(uc->guc_log);
 
-	kfree(error_uc->guc_fw.path);
-	kfree(error_uc->huc_fw.path);
-	i915_error_object_free(error_uc->guc_log);
+	kfree(uc);
 }
 
-void __i915_gpu_state_free(struct kref *error_ref)
+static void cleanup_gt(struct intel_gt_coredump *gt)
 {
-	struct i915_gpu_state *error =
-		container_of(error_ref, typeof(*error), ref);
-	long i;
+	while (gt->engine) {
+		struct intel_engine_coredump *ee = gt->engine;
 
-	while (error->engine) {
-		struct drm_i915_error_engine *ee = error->engine;
+		gt->engine = ee->next;
 
-		error->engine = ee->next;
+		i915_vma_coredump_free(ee->vma);
+		kfree(ee);
+	}
 
-		for (i = 0; i < ee->user_bo_count; i++)
-			i915_error_object_free(ee->user_bo[i]);
-		kfree(ee->user_bo);
+	if (gt->uc)
+		cleanup_uc(gt->uc);
 
-		i915_error_object_free(ee->batchbuffer);
-		i915_error_object_free(ee->wa_batchbuffer);
-		i915_error_object_free(ee->ringbuffer);
-		i915_error_object_free(ee->hws_page);
-		i915_error_object_free(ee->ctx);
-		i915_error_object_free(ee->wa_ctx);
+	kfree(gt);
+}
 
-		kfree(ee->requests);
-		kfree(ee);
+void __i915_gpu_coredump_free(struct kref *error_ref)
+{
+	struct i915_gpu_coredump *error =
+		container_of(error_ref, typeof(*error), ref);
+
+	while (error->gt) {
+		struct intel_gt_coredump *gt = error->gt;
+
+		error->gt = gt->next;
+		cleanup_gt(gt);
 	}
 
 	kfree(error->overlay);
 	kfree(error->display);
 
 	cleanup_params(error);
-	cleanup_uc_state(error);
 
 	err_free_sgl(error->sgl);
 	kfree(error);
 }
 
-static struct drm_i915_error_object *
-i915_error_object_create(struct drm_i915_private *i915,
-			 struct i915_vma *vma,
-			 struct compress *compress)
+static struct i915_vma_coredump *
+i915_vma_coredump_create(const struct intel_gt *gt,
+			 const struct i915_vma *vma,
+			 const char *name,
+			 struct i915_vma_compress *compress)
 {
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	const u64 slot = ggtt->error_capture.start;
-	struct drm_i915_error_object *dst;
+	struct i915_vma_coredump *dst;
 	unsigned long num_pages;
 	struct sgt_iter iter;
 	int ret;
 
 	might_sleep();
 
-	if (!vma || !vma->pages)
+	if (!vma || !vma->pages || !compress)
 		return NULL;
 
 	num_pages = min_t(u64, vma->size, vma->obj->base.size) >> PAGE_SHIFT;
@@ -997,6 +986,9 @@ i915_error_object_create(struct drm_i915_private *i915,
 		return NULL;
 	}
 
+	strcpy(dst->name, name);
+	dst->next = NULL;
+
 	dst->gtt_offset = vma->node.start;
 	dst->gtt_size = vma->node.size;
 	dst->gtt_page_sizes = vma->page_sizes.gtt;
@@ -1004,9 +996,6 @@ i915_error_object_create(struct drm_i915_private *i915,
 	dst->page_count = 0;
 	dst->unused = 0;
 
-	compress->wc = i915_gem_object_is_lmem(vma->obj) ||
-		       drm_mm_node_allocated(&ggtt->error_capture);
-
 	ret = -EINVAL;
 	if (drm_mm_node_allocated(&ggtt->error_capture)) {
 		void __iomem *s;
@@ -1015,9 +1004,12 @@ i915_error_object_create(struct drm_i915_private *i915,
 		for_each_sgt_daddr(dma, iter, vma->pages) {
 			ggtt->vm.insert_page(&ggtt->vm, dma, slot,
 					     I915_CACHE_NONE, 0);
+			mb();
 
 			s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE);
-			ret = compress_page(compress, (void  __force *)s, dst);
+			ret = compress_page(compress,
+					    (void  __force *)s, dst,
+					    true);
 			io_mapping_unmap(s);
 			if (ret)
 				break;
@@ -1030,7 +1022,9 @@ i915_error_object_create(struct drm_i915_private *i915,
 			void __iomem *s;
 
 			s = io_mapping_map_wc(&mem->iomap, dma, PAGE_SIZE);
-			ret = compress_page(compress, (void __force *)s, dst);
+			ret = compress_page(compress,
+					    (void __force *)s, dst,
+					    true);
 			io_mapping_unmap(s);
 			if (ret)
 				break;
@@ -1044,8 +1038,8 @@ i915_error_object_create(struct drm_i915_private *i915,
 			drm_clflush_pages(&page, 1);
 
 			s = kmap(page);
-			ret = compress_page(compress, s, dst);
-			kunmap(s);
+			ret = compress_page(compress, s, dst, false);
+			kunmap(page);
 
 			drm_clflush_pages(&page, 1);
 
@@ -1065,77 +1059,56 @@ i915_error_object_create(struct drm_i915_private *i915,
 	return dst;
 }
 
-/*
- * Generate a semi-unique error code. The code is not meant to have meaning, The
- * code's only purpose is to try to prevent false duplicated bug reports by
- * grossly estimating a GPU error state.
- *
- * TODO Ideally, hashing the batchbuffer would be a very nice way to determine
- * the hang if we could strip the GTT offset information from it.
- *
- * It's only a small step better than a random number in its current form.
- */
-static u32 i915_error_generate_code(struct i915_gpu_state *error)
+static void gt_record_fences(struct intel_gt_coredump *gt)
 {
-	const struct drm_i915_error_engine *ee = error->engine;
-
-	/*
-	 * IPEHR would be an ideal way to detect errors, as it's the gross
-	 * measure of "the command that hung." However, has some very common
-	 * synchronization commands which almost always appear in the case
-	 * strictly a client bug. Use instdone to differentiate those some.
-	 */
-	return ee ? ee->ipehr ^ ee->instdone.instdone : 0;
-}
-
-static void gem_record_fences(struct i915_gpu_state *error)
-{
-	struct drm_i915_private *dev_priv = error->i915;
-	struct intel_uncore *uncore = &dev_priv->uncore;
+	struct i915_ggtt *ggtt = gt->_gt->ggtt;
+	struct intel_uncore *uncore = gt->_gt->uncore;
 	int i;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
-		for (i = 0; i < dev_priv->ggtt.num_fences; i++)
-			error->fence[i] =
+	if (INTEL_GEN(uncore->i915) >= 6) {
+		for (i = 0; i < ggtt->num_fences; i++)
+			gt->fence[i] =
 				intel_uncore_read64(uncore,
 						    FENCE_REG_GEN6_LO(i));
-	} else if (INTEL_GEN(dev_priv) >= 4) {
-		for (i = 0; i < dev_priv->ggtt.num_fences; i++)
-			error->fence[i] =
+	} else if (INTEL_GEN(uncore->i915) >= 4) {
+		for (i = 0; i < ggtt->num_fences; i++)
+			gt->fence[i] =
 				intel_uncore_read64(uncore,
 						    FENCE_REG_965_LO(i));
 	} else {
-		for (i = 0; i < dev_priv->ggtt.num_fences; i++)
-			error->fence[i] =
+		for (i = 0; i < ggtt->num_fences; i++)
+			gt->fence[i] =
 				intel_uncore_read(uncore, FENCE_REG(i));
 	}
-	error->nfence = i;
+	gt->nfence = i;
 }
 
-static void error_record_engine_registers(struct i915_gpu_state *error,
-					  struct intel_engine_cs *engine,
-					  struct drm_i915_error_engine *ee)
+static void engine_record_registers(struct intel_engine_coredump *ee)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
+	const struct intel_engine_cs *engine = ee->engine;
+	struct drm_i915_private *i915 = engine->i915;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
+	if (INTEL_GEN(i915) >= 6) {
 		ee->rc_psmi = ENGINE_READ(engine, RING_PSMI_CTL);
 
-		if (INTEL_GEN(dev_priv) >= 12)
-			ee->fault_reg = I915_READ(GEN12_RING_FAULT_REG);
-		else if (INTEL_GEN(dev_priv) >= 8)
-			ee->fault_reg = I915_READ(GEN8_RING_FAULT_REG);
+		if (INTEL_GEN(i915) >= 12)
+			ee->fault_reg = intel_uncore_read(engine->uncore,
+							  GEN12_RING_FAULT_REG);
+		else if (INTEL_GEN(i915) >= 8)
+			ee->fault_reg = intel_uncore_read(engine->uncore,
+							  GEN8_RING_FAULT_REG);
 		else
 			ee->fault_reg = GEN6_RING_FAULT_REG_READ(engine);
 	}
 
-	if (INTEL_GEN(dev_priv) >= 4) {
+	if (INTEL_GEN(i915) >= 4) {
 		ee->faddr = ENGINE_READ(engine, RING_DMA_FADD);
 		ee->ipeir = ENGINE_READ(engine, RING_IPEIR);
 		ee->ipehr = ENGINE_READ(engine, RING_IPEHR);
 		ee->instps = ENGINE_READ(engine, RING_INSTPS);
 		ee->bbaddr = ENGINE_READ(engine, RING_BBADDR);
-		if (INTEL_GEN(dev_priv) >= 8) {
+		ee->ccid = ENGINE_READ(engine, CCID);
+		if (INTEL_GEN(i915) >= 8) {
 			ee->faddr |= (u64)ENGINE_READ(engine, RING_DMA_FADD_UDW) << 32;
 			ee->bbaddr |= (u64)ENGINE_READ(engine, RING_BBADDR_UDW) << 32;
 		}
@@ -1154,13 +1127,13 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 	ee->head = ENGINE_READ(engine, RING_HEAD);
 	ee->tail = ENGINE_READ(engine, RING_TAIL);
 	ee->ctl = ENGINE_READ(engine, RING_CTL);
-	if (INTEL_GEN(dev_priv) > 2)
+	if (INTEL_GEN(i915) > 2)
 		ee->mode = ENGINE_READ(engine, RING_MI_MODE);
 
-	if (!HWS_NEEDS_PHYSICAL(dev_priv)) {
+	if (!HWS_NEEDS_PHYSICAL(i915)) {
 		i915_reg_t mmio;
 
-		if (IS_GEN(dev_priv, 7)) {
+		if (IS_GEN(i915, 7)) {
 			switch (engine->id) {
 			default:
 				MISSING_CASE(engine->id);
@@ -1185,110 +1158,63 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 			mmio = RING_HWS_PGA(engine->mmio_base);
 		}
 
-		ee->hws = I915_READ(mmio);
+		ee->hws = intel_uncore_read(engine->uncore, mmio);
 	}
 
-	ee->idle = intel_engine_is_idle(engine);
-	ee->reset_count = i915_reset_engine_count(&dev_priv->gpu_error,
-						  engine);
+	ee->reset_count = i915_reset_engine_count(&i915->gpu_error, engine);
 
-	if (HAS_PPGTT(dev_priv)) {
+	if (HAS_PPGTT(i915)) {
 		int i;
 
 		ee->vm_info.gfx_mode = ENGINE_READ(engine, RING_MODE_GEN7);
 
-		if (IS_GEN(dev_priv, 6)) {
+		if (IS_GEN(i915, 6)) {
 			ee->vm_info.pp_dir_base =
 				ENGINE_READ(engine, RING_PP_DIR_BASE_READ);
-		} else if (IS_GEN(dev_priv, 7)) {
+		} else if (IS_GEN(i915, 7)) {
 			ee->vm_info.pp_dir_base =
 				ENGINE_READ(engine, RING_PP_DIR_BASE);
-		} else if (INTEL_GEN(dev_priv) >= 8) {
+		} else if (INTEL_GEN(i915) >= 8) {
 			u32 base = engine->mmio_base;
 
 			for (i = 0; i < 4; i++) {
 				ee->vm_info.pdp[i] =
-					I915_READ(GEN8_RING_PDP_UDW(base, i));
+					intel_uncore_read(engine->uncore,
+							  GEN8_RING_PDP_UDW(base, i));
 				ee->vm_info.pdp[i] <<= 32;
 				ee->vm_info.pdp[i] |=
-					I915_READ(GEN8_RING_PDP_LDW(base, i));
+					intel_uncore_read(engine->uncore,
+							  GEN8_RING_PDP_LDW(base, i));
 			}
 		}
 	}
 }
 
 static void record_request(const struct i915_request *request,
-			   struct drm_i915_error_request *erq)
+			   struct i915_request_coredump *erq)
 {
-	const struct i915_gem_context *ctx = request->gem_context;
+	const struct i915_gem_context *ctx;
 
 	erq->flags = request->fence.flags;
 	erq->context = request->fence.context;
 	erq->seqno = request->fence.seqno;
 	erq->sched_attr = request->sched.attr;
-	erq->jiffies = request->emitted_jiffies;
 	erq->start = i915_ggtt_offset(request->ring->vma);
 	erq->head = request->head;
 	erq->tail = request->tail;
 
+	erq->pid = 0;
 	rcu_read_lock();
-	erq->pid = ctx->pid ? pid_nr(ctx->pid) : 0;
+	ctx = rcu_dereference(request->context->gem_context);
+	if (ctx)
+		erq->pid = pid_nr(ctx->pid);
 	rcu_read_unlock();
 }
 
-static void engine_record_requests(struct intel_engine_cs *engine,
-				   struct i915_request *first,
-				   struct drm_i915_error_engine *ee)
+static void engine_record_execlists(struct intel_engine_coredump *ee)
 {
-	struct i915_request *request;
-	int count;
-
-	count = 0;
-	request = first;
-	list_for_each_entry_from(request, &engine->active.requests, sched.link)
-		count++;
-	if (!count)
-		return;
-
-	ee->requests = kcalloc(count, sizeof(*ee->requests), ATOMIC_MAYFAIL);
-	if (!ee->requests)
-		return;
-
-	ee->num_requests = count;
-
-	count = 0;
-	request = first;
-	list_for_each_entry_from(request,
-				 &engine->active.requests, sched.link) {
-		if (count >= ee->num_requests) {
-			/*
-			 * If the ring request list was changed in
-			 * between the point where the error request
-			 * list was created and dimensioned and this
-			 * point then just exit early to avoid crashes.
-			 *
-			 * We don't need to communicate that the
-			 * request list changed state during error
-			 * state capture and that the error state is
-			 * slightly incorrect as a consequence since we
-			 * are typically only interested in the request
-			 * list state at the point of error state
-			 * capture, not in any changes happening during
-			 * the capture.
-			 */
-			break;
-		}
-
-		record_request(request, &ee->requests[count++]);
-	}
-	ee->num_requests = count;
-}
-
-static void error_record_engine_execlists(const struct intel_engine_cs *engine,
-					  struct drm_i915_error_engine *ee)
-{
-	const struct intel_engine_execlists * const execlists = &engine->execlists;
-	struct i915_request * const *port = execlists->active;
+	const struct intel_engine_execlists * const el = &ee->engine->execlists;
+	struct i915_request * const *port = el->active;
 	unsigned int n = 0;
 
 	while (*port)
@@ -1297,47 +1223,57 @@ static void error_record_engine_execlists(const struct intel_engine_cs *engine,
 	ee->num_ports = n;
 }
 
-static bool record_context(struct drm_i915_error_context *e,
+static bool record_context(struct i915_gem_context_coredump *e,
 			   const struct i915_request *rq)
 {
-	const struct i915_gem_context *ctx = rq->gem_context;
+	struct i915_gem_context *ctx;
+	struct task_struct *task;
+	bool capture;
 
-	if (ctx->pid) {
-		struct task_struct *task;
+	rcu_read_lock();
+	ctx = rcu_dereference(rq->context->gem_context);
+	if (ctx && !kref_get_unless_zero(&ctx->ref))
+		ctx = NULL;
+	rcu_read_unlock();
+	if (!ctx)
+		return false;
 
-		rcu_read_lock();
-		task = pid_task(ctx->pid, PIDTYPE_PID);
-		if (task) {
-			strcpy(e->comm, task->comm);
-			e->pid = task->pid;
-		}
-		rcu_read_unlock();
+	rcu_read_lock();
+	task = pid_task(ctx->pid, PIDTYPE_PID);
+	if (task) {
+		strcpy(e->comm, task->comm);
+		e->pid = task->pid;
 	}
+	rcu_read_unlock();
 
 	e->sched_attr = ctx->sched;
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
 
-	return i915_gem_context_no_error_capture(ctx);
+	capture = i915_gem_context_no_error_capture(ctx);
+
+	i915_gem_context_put(ctx);
+	return capture;
 }
 
-struct capture_vma {
-	struct capture_vma *next;
-	void **slot;
+struct intel_engine_capture_vma {
+	struct intel_engine_capture_vma *next;
+	struct i915_vma *vma;
+	char name[16];
 };
 
-static struct capture_vma *
-capture_vma(struct capture_vma *next,
+static struct intel_engine_capture_vma *
+capture_vma(struct intel_engine_capture_vma *next,
 	    struct i915_vma *vma,
-	    struct drm_i915_error_object **out)
+	    const char *name,
+	    gfp_t gfp)
 {
-	struct capture_vma *c;
+	struct intel_engine_capture_vma *c;
 
-	*out = NULL;
 	if (!vma)
 		return next;
 
-	c = kmalloc(sizeof(*c), ATOMIC_MAYFAIL);
+	c = kmalloc(sizeof(*c), gfp);
 	if (!c)
 		return next;
 
@@ -1346,54 +1282,31 @@ capture_vma(struct capture_vma *next,
 		return next;
 	}
 
-	c->slot = (void **)out;
-	*c->slot = i915_vma_get(vma);
+	strcpy(c->name, name);
+	c->vma = i915_vma_get(vma);
 
 	c->next = next;
 	return c;
 }
 
-static struct capture_vma *
-request_record_user_bo(struct i915_request *request,
-		       struct drm_i915_error_engine *ee,
-		       struct capture_vma *capture)
+static struct intel_engine_capture_vma *
+capture_user(struct intel_engine_capture_vma *capture,
+	     const struct i915_request *rq,
+	     gfp_t gfp)
 {
 	struct i915_capture_list *c;
-	struct drm_i915_error_object **bo;
-	long count, max;
-
-	max = 0;
-	for (c = request->capture_list; c; c = c->next)
-		max++;
-	if (!max)
-		return capture;
-
-	bo = kmalloc_array(max, sizeof(*bo), ATOMIC_MAYFAIL);
-	if (!bo) {
-		/* If we can't capture everything, try to capture something. */
-		max = min_t(long, max, PAGE_SIZE / sizeof(*bo));
-		bo = kmalloc_array(max, sizeof(*bo), ATOMIC_MAYFAIL);
-	}
-	if (!bo)
-		return capture;
 
-	count = 0;
-	for (c = request->capture_list; c; c = c->next) {
-		capture = capture_vma(capture, c->vma, &bo[count]);
-		if (++count == max)
-			break;
-	}
-
-	ee->user_bo = bo;
-	ee->user_bo_count = count;
+	for (c = rq->capture_list; c; c = c->next)
+		capture = capture_vma(capture, c->vma, "user", gfp);
 
 	return capture;
 }
 
-static struct drm_i915_error_object *
-capture_object(struct drm_i915_private *dev_priv,
+static struct i915_vma_coredump *
+capture_object(const struct intel_gt *gt,
 	       struct drm_i915_gem_object *obj,
-	       struct compress *compress)
+	       const char *name,
+	       struct i915_vma_compress *compress)
 {
 	if (obj && i915_gem_object_has_pages(obj)) {
 		struct i915_vma fake = {
@@ -1403,127 +1316,175 @@ capture_object(struct drm_i915_private *dev_priv,
 			.obj = obj,
 		};
 
-		return i915_error_object_create(dev_priv, &fake, compress);
+		return i915_vma_coredump_create(gt, &fake, name, compress);
 	} else {
 		return NULL;
 	}
 }
 
-static void
-gem_record_rings(struct i915_gpu_state *error, struct compress *compress)
+static void add_vma(struct intel_engine_coredump *ee,
+		    struct i915_vma_coredump *vma)
 {
-	struct drm_i915_private *i915 = error->i915;
-	struct intel_engine_cs *engine;
-	struct drm_i915_error_engine *ee;
+	if (vma) {
+		vma->next = ee->vma;
+		ee->vma = vma;
+	}
+}
+
+struct intel_engine_coredump *
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
+{
+	struct intel_engine_coredump *ee;
 
-	ee = kzalloc(sizeof(*ee), GFP_KERNEL);
+	ee = kzalloc(sizeof(*ee), gfp);
 	if (!ee)
-		return;
+		return NULL;
 
-	for_each_uabi_engine(engine, i915) {
-		struct capture_vma *capture = NULL;
-		struct i915_request *request;
-		unsigned long flags;
+	ee->engine = engine;
 
-		/* Refill our page pool before entering atomic section */
-		pool_refill(&compress->pool, ALLOW_FAIL);
+	engine_record_registers(ee);
+	engine_record_execlists(ee);
 
-		spin_lock_irqsave(&engine->active.lock, flags);
-		request = intel_engine_find_active_request(engine);
-		if (!request) {
-			spin_unlock_irqrestore(&engine->active.lock, flags);
-			continue;
-		}
+	return ee;
+}
 
-		error->simulated |= record_context(&ee->context, request);
+struct intel_engine_capture_vma *
+intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
+				  struct i915_request *rq,
+				  gfp_t gfp)
+{
+	struct intel_engine_capture_vma *vma = NULL;
 
-		/*
-		 * We need to copy these to an anonymous buffer
-		 * as the simplest method to avoid being overwritten
-		 * by userspace.
-		 */
-		capture = capture_vma(capture,
-				      request->batch,
-				      &ee->batchbuffer);
+	ee->simulated |= record_context(&ee->context, rq);
+	if (ee->simulated)
+		return NULL;
 
-		if (HAS_BROKEN_CS_TLB(i915))
-			capture = capture_vma(capture,
-					      engine->gt->scratch,
-					      &ee->wa_batchbuffer);
+	/*
+	 * We need to copy these to an anonymous buffer
+	 * as the simplest method to avoid being overwritten
+	 * by userspace.
+	 */
+	vma = capture_vma(vma, rq->batch, "batch", gfp);
+	vma = capture_user(vma, rq, gfp);
+	vma = capture_vma(vma, rq->ring->vma, "ring", gfp);
+	vma = capture_vma(vma, rq->context->state, "HW context", gfp);
+
+	ee->rq_head = rq->head;
+	ee->rq_post = rq->postfix;
+	ee->rq_tail = rq->tail;
+
+	return vma;
+}
 
-		capture = request_record_user_bo(request, ee, capture);
+void
+intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
+			      struct intel_engine_capture_vma *capture,
+			      struct i915_vma_compress *compress)
+{
+	const struct intel_engine_cs *engine = ee->engine;
 
-		capture = capture_vma(capture,
-				      request->hw_context->state,
-				      &ee->ctx);
+	while (capture) {
+		struct intel_engine_capture_vma *this = capture;
+		struct i915_vma *vma = this->vma;
 
-		capture = capture_vma(capture,
-				      request->ring->vma,
-				      &ee->ringbuffer);
+		add_vma(ee,
+			i915_vma_coredump_create(engine->gt,
+						 vma, this->name,
+						 compress));
 
-		ee->cpu_ring_head = request->ring->head;
-		ee->cpu_ring_tail = request->ring->tail;
+		i915_active_release(&vma->active);
+		i915_vma_put(vma);
 
-		ee->rq_head = request->head;
-		ee->rq_post = request->postfix;
-		ee->rq_tail = request->tail;
+		capture = this->next;
+		kfree(this);
+	}
 
-		engine_record_requests(engine, request, ee);
-		spin_unlock_irqrestore(&engine->active.lock, flags);
+	add_vma(ee,
+		i915_vma_coredump_create(engine->gt,
+					 engine->status_page.vma,
+					 "HW Status",
+					 compress));
 
-		error_record_engine_registers(error, engine, ee);
-		error_record_engine_execlists(engine, ee);
+	add_vma(ee,
+		i915_vma_coredump_create(engine->gt,
+					 engine->wa_ctx.vma,
+					 "WA context",
+					 compress));
 
-		while (capture) {
-			struct capture_vma *this = capture;
-			struct i915_vma *vma = *this->slot;
+	add_vma(ee,
+		capture_object(engine->gt,
+			       engine->default_state,
+			       "NULL context",
+			       compress));
+}
 
-			*this->slot =
-				i915_error_object_create(i915, vma, compress);
+static struct intel_engine_coredump *
+capture_engine(struct intel_engine_cs *engine,
+	       struct i915_vma_compress *compress)
+{
+	struct intel_engine_capture_vma *capture = NULL;
+	struct intel_engine_coredump *ee;
+	struct i915_request *rq;
+	unsigned long flags;
 
-			i915_active_release(&vma->active);
-			i915_vma_put(vma);
+	ee = intel_engine_coredump_alloc(engine, GFP_KERNEL);
+	if (!ee)
+		return NULL;
 
-			capture = this->next;
-			kfree(this);
-		}
+	spin_lock_irqsave(&engine->active.lock, flags);
+	rq = intel_engine_find_active_request(engine);
+	if (rq)
+		capture = intel_engine_coredump_add_request(ee, rq,
+							    ATOMIC_MAYFAIL);
+	spin_unlock_irqrestore(&engine->active.lock, flags);
+	if (!capture) {
+		kfree(ee);
+		return NULL;
+	}
 
-		ee->hws_page =
-			i915_error_object_create(i915,
-						 engine->status_page.vma,
-						 compress);
+	intel_engine_coredump_add_vma(ee, capture, compress);
 
-		ee->wa_ctx =
-			i915_error_object_create(i915,
-						 engine->wa_ctx.vma,
-						 compress);
+	return ee;
+}
 
-		ee->default_state =
-			capture_object(i915, engine->default_state, compress);
+static void
+gt_record_engines(struct intel_gt_coredump *gt,
+		  struct i915_vma_compress *compress)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 
-		ee->engine = engine;
+	for_each_engine(engine, gt->_gt, id) {
+		struct intel_engine_coredump *ee;
 
-		ee->next = error->engine;
-		error->engine = ee;
+		/* Refill our page pool before entering atomic section */
+		pool_refill(&compress->pool, ALLOW_FAIL);
 
-		ee = kzalloc(sizeof(*ee), GFP_KERNEL);
+		ee = capture_engine(engine, compress);
 		if (!ee)
-			return;
-	}
+			continue;
 
-	kfree(ee);
+		gt->simulated |= ee->simulated;
+		if (ee->simulated) {
+			kfree(ee);
+			continue;
+		}
+
+		ee->next = gt->engine;
+		gt->engine = ee;
+	}
 }
 
-static void
-capture_uc_state(struct i915_gpu_state *error, struct compress *compress)
+static struct intel_uc_coredump *
+gt_record_uc(struct intel_gt_coredump *gt,
+	     struct i915_vma_compress *compress)
 {
-	struct drm_i915_private *i915 = error->i915;
-	struct i915_error_uc *error_uc = &error->uc;
-	struct intel_uc *uc = &i915->gt.uc;
+	const struct intel_uc *uc = &gt->_gt->uc;
+	struct intel_uc_coredump *error_uc;
 
-	/* Capturing uC state won't be useful if there is no GuC */
-	if (!error->device_info.has_gt_uc)
-		return;
+	error_uc = kzalloc(sizeof(*error_uc), ALLOW_FAIL);
+	if (!error_uc)
+		return NULL;
 
 	memcpy(&error_uc->guc_fw, &uc->guc.fw, sizeof(uc->guc.fw));
 	memcpy(&error_uc->huc_fw, &uc->huc.fw, sizeof(uc->huc.fw));
@@ -1534,19 +1495,42 @@ capture_uc_state(struct i915_gpu_state *error, struct compress *compress)
 	 */
 	error_uc->guc_fw.path = kstrdup(uc->guc.fw.path, ALLOW_FAIL);
 	error_uc->huc_fw.path = kstrdup(uc->huc.fw.path, ALLOW_FAIL);
-	error_uc->guc_log = i915_error_object_create(i915,
-						     uc->guc.log.vma,
-						     compress);
+	error_uc->guc_log =
+		i915_vma_coredump_create(gt->_gt,
+					 uc->guc.log.vma, "GuC log buffer",
+					 compress);
+
+	return error_uc;
+}
+
+static void gt_capture_prepare(struct intel_gt_coredump *gt)
+{
+	struct i915_ggtt *ggtt = gt->_gt->ggtt;
+
+	mutex_lock(&ggtt->error_mutex);
+}
+
+static void gt_capture_finish(struct intel_gt_coredump *gt)
+{
+	struct i915_ggtt *ggtt = gt->_gt->ggtt;
+
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		ggtt->vm.clear_range(&ggtt->vm,
+				     ggtt->error_capture.start,
+				     PAGE_SIZE);
+
+	mutex_unlock(&ggtt->error_mutex);
 }
 
 /* Capture all registers which don't fit into another category. */
-static void capture_reg_state(struct i915_gpu_state *error)
+static void gt_record_regs(struct intel_gt_coredump *gt)
 {
-	struct drm_i915_private *i915 = error->i915;
-	struct intel_uncore *uncore = &i915->uncore;
+	struct intel_uncore *uncore = gt->_gt->uncore;
+	struct drm_i915_private *i915 = uncore->i915;
 	int i;
 
-	/* General organization
+	/*
+	 * General organization
 	 * 1. Registers specific to a single generation
 	 * 2. Registers which belong to multiple generations
 	 * 3. Feature specific registers.
@@ -1556,138 +1540,162 @@ static void capture_reg_state(struct i915_gpu_state *error)
 
 	/* 1: Registers specific to a single generation */
 	if (IS_VALLEYVIEW(i915)) {
-		error->gtier[0] = intel_uncore_read(uncore, GTIER);
-		error->ier = intel_uncore_read(uncore, VLV_IER);
-		error->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_VLV);
+		gt->gtier[0] = intel_uncore_read(uncore, GTIER);
+		gt->ier = intel_uncore_read(uncore, VLV_IER);
+		gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_VLV);
 	}
 
 	if (IS_GEN(i915, 7))
-		error->err_int = intel_uncore_read(uncore, GEN7_ERR_INT);
+		gt->err_int = intel_uncore_read(uncore, GEN7_ERR_INT);
 
 	if (INTEL_GEN(i915) >= 12) {
-		error->fault_data0 = intel_uncore_read(uncore,
-						       GEN12_FAULT_TLB_DATA0);
-		error->fault_data1 = intel_uncore_read(uncore,
-						       GEN12_FAULT_TLB_DATA1);
+		gt->fault_data0 = intel_uncore_read(uncore,
+						    GEN12_FAULT_TLB_DATA0);
+		gt->fault_data1 = intel_uncore_read(uncore,
+						    GEN12_FAULT_TLB_DATA1);
 	} else if (INTEL_GEN(i915) >= 8) {
-		error->fault_data0 = intel_uncore_read(uncore,
-						       GEN8_FAULT_TLB_DATA0);
-		error->fault_data1 = intel_uncore_read(uncore,
-						       GEN8_FAULT_TLB_DATA1);
+		gt->fault_data0 = intel_uncore_read(uncore,
+						    GEN8_FAULT_TLB_DATA0);
+		gt->fault_data1 = intel_uncore_read(uncore,
+						    GEN8_FAULT_TLB_DATA1);
 	}
 
 	if (IS_GEN(i915, 6)) {
-		error->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE);
-		error->gab_ctl = intel_uncore_read(uncore, GAB_CTL);
-		error->gfx_mode = intel_uncore_read(uncore, GFX_MODE);
+		gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE);
+		gt->gab_ctl = intel_uncore_read(uncore, GAB_CTL);
+		gt->gfx_mode = intel_uncore_read(uncore, GFX_MODE);
 	}
 
 	/* 2: Registers which belong to multiple generations */
 	if (INTEL_GEN(i915) >= 7)
-		error->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
+		gt->forcewake = intel_uncore_read_fw(uncore, FORCEWAKE_MT);
 
 	if (INTEL_GEN(i915) >= 6) {
-		error->derrmr = intel_uncore_read(uncore, DERRMR);
+		gt->derrmr = intel_uncore_read(uncore, DERRMR);
 		if (INTEL_GEN(i915) < 12) {
-			error->error = intel_uncore_read(uncore, ERROR_GEN6);
-			error->done_reg = intel_uncore_read(uncore, DONE_REG);
+			gt->error = intel_uncore_read(uncore, ERROR_GEN6);
+			gt->done_reg = intel_uncore_read(uncore, DONE_REG);
 		}
 	}
 
-	if (INTEL_GEN(i915) >= 5)
-		error->ccid = intel_uncore_read(uncore, CCID(RENDER_RING_BASE));
-
 	/* 3: Feature specific registers */
 	if (IS_GEN_RANGE(i915, 6, 7)) {
-		error->gam_ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
-		error->gac_eco = intel_uncore_read(uncore, GAC_ECO_BITS);
+		gt->gam_ecochk = intel_uncore_read(uncore, GAM_ECOCHK);
+		gt->gac_eco = intel_uncore_read(uncore, GAC_ECO_BITS);
 	}
 
 	if (IS_GEN_RANGE(i915, 8, 11))
-		error->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN);
+		gt->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN);
 
 	if (IS_GEN(i915, 12))
-		error->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG);
+		gt->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG);
 
 	if (INTEL_GEN(i915) >= 12) {
 		for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
-			error->sfc_done[i] =
+			gt->sfc_done[i] =
 				intel_uncore_read(uncore, GEN12_SFC_DONE(i));
 		}
 
-		error->gam_done = intel_uncore_read(uncore, GEN12_GAM_DONE);
+		gt->gam_done = intel_uncore_read(uncore, GEN12_GAM_DONE);
 	}
 
 	/* 4: Everything else */
 	if (INTEL_GEN(i915) >= 11) {
-		error->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
-		error->gtier[0] =
+		gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
+		gt->gtier[0] =
 			intel_uncore_read(uncore,
 					  GEN11_RENDER_COPY_INTR_ENABLE);
-		error->gtier[1] =
+		gt->gtier[1] =
 			intel_uncore_read(uncore, GEN11_VCS_VECS_INTR_ENABLE);
-		error->gtier[2] =
+		gt->gtier[2] =
 			intel_uncore_read(uncore, GEN11_GUC_SG_INTR_ENABLE);
-		error->gtier[3] =
+		gt->gtier[3] =
 			intel_uncore_read(uncore,
 					  GEN11_GPM_WGBOXPERF_INTR_ENABLE);
-		error->gtier[4] =
+		gt->gtier[4] =
 			intel_uncore_read(uncore,
 					  GEN11_CRYPTO_RSVD_INTR_ENABLE);
-		error->gtier[5] =
+		gt->gtier[5] =
 			intel_uncore_read(uncore,
 					  GEN11_GUNIT_CSME_INTR_ENABLE);
-		error->ngtier = 6;
+		gt->ngtier = 6;
 	} else if (INTEL_GEN(i915) >= 8) {
-		error->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
+		gt->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
 		for (i = 0; i < 4; i++)
-			error->gtier[i] = intel_uncore_read(uncore,
-							    GEN8_GT_IER(i));
-		error->ngtier = 4;
+			gt->gtier[i] =
+				intel_uncore_read(uncore, GEN8_GT_IER(i));
+		gt->ngtier = 4;
 	} else if (HAS_PCH_SPLIT(i915)) {
-		error->ier = intel_uncore_read(uncore, DEIER);
-		error->gtier[0] = intel_uncore_read(uncore, GTIER);
-		error->ngtier = 1;
+		gt->ier = intel_uncore_read(uncore, DEIER);
+		gt->gtier[0] = intel_uncore_read(uncore, GTIER);
+		gt->ngtier = 1;
 	} else if (IS_GEN(i915, 2)) {
-		error->ier = intel_uncore_read16(uncore, GEN2_IER);
+		gt->ier = intel_uncore_read16(uncore, GEN2_IER);
 	} else if (!IS_VALLEYVIEW(i915)) {
-		error->ier = intel_uncore_read(uncore, GEN2_IER);
+		gt->ier = intel_uncore_read(uncore, GEN2_IER);
 	}
-	error->eir = intel_uncore_read(uncore, EIR);
-	error->pgtbl_er = intel_uncore_read(uncore, PGTBL_ER);
+	gt->eir = intel_uncore_read(uncore, EIR);
+	gt->pgtbl_er = intel_uncore_read(uncore, PGTBL_ER);
+}
+
+/*
+ * Generate a semi-unique error code. The code is not meant to have meaning, The
+ * code's only purpose is to try to prevent false duplicated bug reports by
+ * grossly estimating a GPU error state.
+ *
+ * TODO Ideally, hashing the batchbuffer would be a very nice way to determine
+ * the hang if we could strip the GTT offset information from it.
+ *
+ * It's only a small step better than a random number in its current form.
+ */
+static u32 generate_ecode(const struct intel_engine_coredump *ee)
+{
+	/*
+	 * IPEHR would be an ideal way to detect errors, as it's the gross
+	 * measure of "the command that hung." However, has some very common
+	 * synchronization commands which almost always appear in the case
+	 * strictly a client bug. Use instdone to differentiate those some.
+	 */
+	return ee ? ee->ipehr ^ ee->instdone.instdone : 0;
 }
 
-static const char *
-error_msg(struct i915_gpu_state *error,
-	  intel_engine_mask_t engines, const char *msg)
+static const char *error_msg(struct i915_gpu_coredump *error)
 {
+	struct intel_engine_coredump *first = NULL;
+	struct intel_gt_coredump *gt;
+	intel_engine_mask_t engines;
 	int len;
 
+	engines = 0;
+	for (gt = error->gt; gt; gt = gt->next) {
+		struct intel_engine_coredump *cs;
+
+		if (gt->engine && !first)
+			first = gt->engine;
+
+		for (cs = gt->engine; cs; cs = cs->next)
+			engines |= cs->engine->mask;
+	}
+
 	len = scnprintf(error->error_msg, sizeof(error->error_msg),
-			"GPU HANG: ecode %d:%x:0x%08x",
+			"GPU HANG: ecode %d:%x:%08x",
 			INTEL_GEN(error->i915), engines,
-			i915_error_generate_code(error));
-	if (error->engine) {
+			generate_ecode(first));
+	if (first) {
 		/* Just show the first executing process, more is confusing */
 		len += scnprintf(error->error_msg + len,
 				 sizeof(error->error_msg) - len,
 				 ", in %s [%d]",
-				 error->engine->context.comm,
-				 error->engine->context.pid);
+				 first->context.comm, first->context.pid);
 	}
-	if (msg)
-		len += scnprintf(error->error_msg + len,
-				 sizeof(error->error_msg) - len,
-				 ", %s", msg);
 
 	return error->error_msg;
 }
 
-static void capture_gen_state(struct i915_gpu_state *error)
+static void capture_gen(struct i915_gpu_coredump *error)
 {
 	struct drm_i915_private *i915 = error->i915;
 
-	error->awake = i915->gt.awake;
 	error->wakelock = atomic_read(&i915->runtime_pm.wakeref_count);
 	error->suspended = i915->runtime_pm.suspended;
 
@@ -1698,6 +1706,7 @@ static void capture_gen_state(struct i915_gpu_state *error)
 	error->reset_count = i915_reset_count(&i915->gpu_error);
 	error->suspend_count = i915->suspend_count;
 
+	i915_params_copy(&error->params, &i915_modparams);
 	memcpy(&error->device_info,
 	       INTEL_INFO(i915),
 	       sizeof(error->device_info));
@@ -1707,115 +1716,138 @@ static void capture_gen_state(struct i915_gpu_state *error)
 	error->driver_caps = i915->caps;
 }
 
-static void capture_params(struct i915_gpu_state *error)
+struct i915_gpu_coredump *
+i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp)
 {
-	i915_params_copy(&error->params, &i915_modparams);
+	struct i915_gpu_coredump *error;
+
+	if (!i915_modparams.error_capture)
+		return NULL;
+
+	error = kzalloc(sizeof(*error), gfp);
+	if (!error)
+		return NULL;
+
+	kref_init(&error->ref);
+	error->i915 = i915;
+
+	error->time = ktime_get_real();
+	error->boottime = ktime_get_boottime();
+	error->uptime = ktime_sub(ktime_get(), i915->gt.last_init_time);
+	error->capture = jiffies;
+
+	capture_gen(error);
+
+	return error;
 }
 
-static void capture_finish(struct i915_gpu_state *error)
+#define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
+
+struct intel_gt_coredump *
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp)
 {
-	struct i915_ggtt *ggtt = &error->i915->ggtt;
+	struct intel_gt_coredump *gc;
 
-	if (drm_mm_node_allocated(&ggtt->error_capture)) {
-		const u64 slot = ggtt->error_capture.start;
+	gc = kzalloc(sizeof(*gc), gfp);
+	if (!gc)
+		return NULL;
+
+	gc->_gt = gt;
+	gc->awake = intel_gt_pm_is_awake(gt);
+
+	gt_record_regs(gc);
+	gt_record_fences(gc);
+
+	return gc;
+}
 
-		ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
+struct i915_vma_compress *
+i915_vma_capture_prepare(struct intel_gt_coredump *gt)
+{
+	struct i915_vma_compress *compress;
+
+	compress = kmalloc(sizeof(*compress), ALLOW_FAIL);
+	if (!compress)
+		return NULL;
+
+	if (!compress_init(compress)) {
+		kfree(compress);
+		return NULL;
 	}
+
+	gt_capture_prepare(gt);
+
+	return compress;
 }
 
-#define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
+void i915_vma_capture_finish(struct intel_gt_coredump *gt,
+			     struct i915_vma_compress *compress)
+{
+	if (!compress)
+		return;
 
-struct i915_gpu_state *
-i915_capture_gpu_state(struct drm_i915_private *i915)
+	gt_capture_finish(gt);
+
+	compress_fini(compress);
+	kfree(compress);
+}
+
+struct i915_gpu_coredump *i915_gpu_coredump(struct drm_i915_private *i915)
 {
-	struct i915_gpu_state *error;
-	struct compress compress;
+	struct i915_gpu_coredump *error;
 
 	/* Check if GPU capture has been disabled */
 	error = READ_ONCE(i915->gpu_error.first_error);
 	if (IS_ERR(error))
 		return error;
 
-	error = kzalloc(sizeof(*error), ALLOW_FAIL);
-	if (!error) {
-		i915_disable_error_state(i915, -ENOMEM);
+	error = i915_gpu_coredump_alloc(i915, ALLOW_FAIL);
+	if (!error)
 		return ERR_PTR(-ENOMEM);
-	}
 
-	if (!compress_init(&compress)) {
-		kfree(error);
-		i915_disable_error_state(i915, -ENOMEM);
-		return ERR_PTR(-ENOMEM);
-	}
+	error->gt = intel_gt_coredump_alloc(&i915->gt, ALLOW_FAIL);
+	if (error->gt) {
+		struct i915_vma_compress *compress;
 
-	kref_init(&error->ref);
-	error->i915 = i915;
+		compress = i915_vma_capture_prepare(error->gt);
+		if (!compress) {
+			kfree(error->gt);
+			kfree(error);
+			return ERR_PTR(-ENOMEM);
+		}
 
-	error->time = ktime_get_real();
-	error->boottime = ktime_get_boottime();
-	error->uptime = ktime_sub(ktime_get(), i915->gt.last_init_time);
-	error->capture = jiffies;
+		gt_record_engines(error->gt, compress);
+
+		if (INTEL_INFO(i915)->has_gt_uc)
+			error->gt->uc = gt_record_uc(error->gt, compress);
 
-	capture_params(error);
-	capture_gen_state(error);
-	capture_uc_state(error, &compress);
-	capture_reg_state(error);
-	gem_record_fences(error);
-	gem_record_rings(error, &compress);
+		i915_vma_capture_finish(error->gt, compress);
+
+		error->simulated |= error->gt->simulated;
+	}
 
 	error->overlay = intel_overlay_capture_error_state(i915);
 	error->display = intel_display_capture_error_state(i915);
 
-	capture_finish(error);
-	compress_fini(&compress);
-
 	return error;
 }
 
-/**
- * i915_capture_error_state - capture an error record for later analysis
- * @i915: i915 device
- * @engine_mask: the mask of engines triggering the hang
- * @msg: a message to insert into the error capture header
- *
- * Should be called when an error is detected (either a hang or an error
- * interrupt) to capture error state from the time of the error.  Fills
- * out a structure which becomes available in debugfs for user level tools
- * to pick up.
- */
-void i915_capture_error_state(struct drm_i915_private *i915,
-			      intel_engine_mask_t engine_mask,
-			      const char *msg)
+void i915_error_state_store(struct i915_gpu_coredump *error)
 {
+	struct drm_i915_private *i915;
 	static bool warned;
-	struct i915_gpu_state *error;
-	unsigned long flags;
 
-	if (!i915_modparams.error_capture)
+	if (IS_ERR_OR_NULL(error))
 		return;
 
-	if (READ_ONCE(i915->gpu_error.first_error))
-		return;
+	i915 = error->i915;
+	dev_info(i915->drm.dev, "%s\n", error_msg(error));
 
-	error = i915_capture_gpu_state(i915);
-	if (IS_ERR(error))
+	if (error->simulated ||
+	    cmpxchg(&i915->gpu_error.first_error, NULL, error))
 		return;
 
-	dev_info(i915->drm.dev, "%s\n", error_msg(error, engine_mask, msg));
-
-	if (!error->simulated) {
-		spin_lock_irqsave(&i915->gpu_error.lock, flags);
-		if (!i915->gpu_error.first_error) {
-			i915->gpu_error.first_error = error;
-			error = NULL;
-		}
-		spin_unlock_irqrestore(&i915->gpu_error.lock, flags);
-	}
-
-	if (error) {
-		__i915_gpu_state_free(&error->ref);
-		return;
-	}
+	i915_gpu_coredump_get(error);
 
 	if (!xchg(&warned, true) &&
 	    ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
@@ -1828,15 +1860,38 @@ void i915_capture_error_state(struct drm_i915_private *i915,
 	}
 }
 
-struct i915_gpu_state *
+/**
+ * i915_capture_error_state - capture an error record for later analysis
+ * @i915: i915 device
+ *
+ * Should be called when an error is detected (either a hang or an error
+ * interrupt) to capture error state from the time of the error.  Fills
+ * out a structure which becomes available in debugfs for user level tools
+ * to pick up.
+ */
+void i915_capture_error_state(struct drm_i915_private *i915)
+{
+	struct i915_gpu_coredump *error;
+
+	error = i915_gpu_coredump(i915);
+	if (IS_ERR(error)) {
+		cmpxchg(&i915->gpu_error.first_error, NULL, error);
+		return;
+	}
+
+	i915_error_state_store(error);
+	i915_gpu_coredump_put(error);
+}
+
+struct i915_gpu_coredump *
 i915_first_error_state(struct drm_i915_private *i915)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 
 	spin_lock_irq(&i915->gpu_error.lock);
 	error = i915->gpu_error.first_error;
 	if (!IS_ERR_OR_NULL(error))
-		i915_gpu_state_get(error);
+		i915_gpu_coredump_get(error);
 	spin_unlock_irq(&i915->gpu_error.lock);
 
 	return error;
@@ -1844,7 +1899,7 @@ i915_first_error_state(struct drm_i915_private *i915)
 
 void i915_reset_error_state(struct drm_i915_private *i915)
 {
-	struct i915_gpu_state *error;
+	struct i915_gpu_coredump *error;
 
 	spin_lock_irq(&i915->gpu_error.lock);
 	error = i915->gpu_error.first_error;
@@ -1853,7 +1908,7 @@ void i915_reset_error_state(struct drm_i915_private *i915)
 	spin_unlock_irq(&i915->gpu_error.lock);
 
 	if (!IS_ERR_OR_NULL(error))
-		i915_gpu_state_put(error);
+		i915_gpu_coredump_put(error);
 }
 
 void i915_disable_error_state(struct drm_i915_private *i915, int err)
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 5d2c3372ff99..9109004956bd 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -25,43 +25,100 @@
 #include "i915_scheduler.h"
 
 struct drm_i915_private;
+struct i915_vma_compress;
+struct intel_engine_capture_vma;
 struct intel_overlay_error_state;
 struct intel_display_error_state;
 
-struct i915_gpu_state {
-	struct kref ref;
-	ktime_t time;
-	ktime_t boottime;
-	ktime_t uptime;
-	unsigned long capture;
+struct i915_vma_coredump {
+	struct i915_vma_coredump *next;
 
-	struct drm_i915_private *i915;
+	char name[20];
+
+	u64 gtt_offset;
+	u64 gtt_size;
+	u32 gtt_page_sizes;
+
+	int num_pages;
+	int page_count;
+	int unused;
+	u32 *pages[0];
+};
+
+struct i915_request_coredump {
+	unsigned long flags;
+	pid_t pid;
+	u32 context;
+	u32 seqno;
+	u32 start;
+	u32 head;
+	u32 tail;
+	struct i915_sched_attr sched_attr;
+};
+
+struct intel_engine_coredump {
+	const struct intel_engine_cs *engine;
 
-	char error_msg[128];
 	bool simulated;
-	bool awake;
-	bool wakelock;
-	bool suspended;
-	int iommu;
 	u32 reset_count;
-	u32 suspend_count;
-	struct intel_device_info device_info;
-	struct intel_runtime_info runtime_info;
-	struct intel_driver_caps driver_caps;
-	struct i915_params params;
 
-	struct i915_error_uc {
-		struct intel_uc_fw guc_fw;
-		struct intel_uc_fw huc_fw;
-		struct drm_i915_error_object *guc_log;
-	} uc;
+	/* position of active request inside the ring */
+	u32 rq_head, rq_post, rq_tail;
+
+	/* Register state */
+	u32 ccid;
+	u32 start;
+	u32 tail;
+	u32 head;
+	u32 ctl;
+	u32 mode;
+	u32 hws;
+	u32 ipeir;
+	u32 ipehr;
+	u32 bbstate;
+	u32 instpm;
+	u32 instps;
+	u64 bbaddr;
+	u64 acthd;
+	u32 fault_reg;
+	u64 faddr;
+	u32 rc_psmi; /* sleep state */
+	struct intel_instdone instdone;
+
+	struct i915_gem_context_coredump {
+		char comm[TASK_COMM_LEN];
+		pid_t pid;
+		int active;
+		int guilty;
+		struct i915_sched_attr sched_attr;
+	} context;
+
+	struct i915_vma_coredump *vma;
+
+	struct i915_request_coredump execlist[EXECLIST_MAX_PORTS];
+	unsigned int num_ports;
+
+	struct {
+		u32 gfx_mode;
+		union {
+			u64 pdp[4];
+			u32 pp_dir_base;
+		};
+	} vm_info;
+
+	struct intel_engine_coredump *next;
+};
+
+struct intel_gt_coredump {
+	const struct intel_gt *_gt;
+	bool awake;
+	bool simulated;
 
 	/* Generic register state */
 	u32 eir;
 	u32 pgtbl_er;
 	u32 ier;
 	u32 gtier[6], ngtier;
-	u32 ccid;
 	u32 derrmr;
 	u32 forcewake;
 	u32 error; /* gen6+ */
@@ -80,91 +137,45 @@ struct i915_gpu_state {
 
 	u32 nfence;
 	u64 fence[I915_MAX_NUM_FENCES];
+
+	struct intel_engine_coredump *engine;
+
+	struct intel_uc_coredump {
+		struct intel_uc_fw guc_fw;
+		struct intel_uc_fw huc_fw;
+		struct i915_vma_coredump *guc_log;
+	} *uc;
+
+	struct intel_gt_coredump *next;
+};
+
+struct i915_gpu_coredump {
+	struct kref ref;
+	ktime_t time;
+	ktime_t boottime;
+	ktime_t uptime;
+	unsigned long capture;
+
+	struct drm_i915_private *i915;
+
+	struct intel_gt_coredump *gt;
+
+	char error_msg[128];
+	bool simulated;
+	bool wakelock;
+	bool suspended;
+	int iommu;
+	u32 reset_count;
+	u32 suspend_count;
+
+	struct intel_device_info device_info;
+	struct intel_runtime_info runtime_info;
+	struct intel_driver_caps driver_caps;
+	struct i915_params params;
+
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
 
-	struct drm_i915_error_engine {
-		const struct intel_engine_cs *engine;
-
-		/* Software tracked state */
-		bool idle;
-		int num_requests;
-		u32 reset_count;
-
-		/* position of active request inside the ring */
-		u32 rq_head, rq_post, rq_tail;
-
-		/* our own tracking of ring head and tail */
-		u32 cpu_ring_head;
-		u32 cpu_ring_tail;
-
-		/* Register state */
-		u32 start;
-		u32 tail;
-		u32 head;
-		u32 ctl;
-		u32 mode;
-		u32 hws;
-		u32 ipeir;
-		u32 ipehr;
-		u32 bbstate;
-		u32 instpm;
-		u32 instps;
-		u64 bbaddr;
-		u64 acthd;
-		u32 fault_reg;
-		u64 faddr;
-		u32 rc_psmi; /* sleep state */
-		struct intel_instdone instdone;
-
-		struct drm_i915_error_context {
-			char comm[TASK_COMM_LEN];
-			pid_t pid;
-			int active;
-			int guilty;
-			struct i915_sched_attr sched_attr;
-		} context;
-
-		struct drm_i915_error_object {
-			u64 gtt_offset;
-			u64 gtt_size;
-			u32 gtt_page_sizes;
-			int num_pages;
-			int page_count;
-			int unused;
-			u32 *pages[0];
-		} *ringbuffer, *batchbuffer, *wa_batchbuffer, *ctx, *hws_page;
-
-		struct drm_i915_error_object **user_bo;
-		long user_bo_count;
-
-		struct drm_i915_error_object *wa_ctx;
-		struct drm_i915_error_object *default_state;
-
-		struct drm_i915_error_request {
-			unsigned long flags;
-			long jiffies;
-			pid_t pid;
-			u32 context;
-			u32 seqno;
-			u32 start;
-			u32 head;
-			u32 tail;
-			struct i915_sched_attr sched_attr;
-		} *requests, execlist[EXECLIST_MAX_PORTS];
-		unsigned int num_ports;
-
-		struct {
-			u32 gfx_mode;
-			union {
-				u64 pdp[4];
-				u32 pp_dir_base;
-			};
-		} vm_info;
-
-		struct drm_i915_error_engine *next;
-	} *engine;
-
 	struct scatterlist *sgl, *fit;
 };
 
@@ -172,7 +183,7 @@ struct i915_gpu_error {
 	/* For reset and error_state handling. */
 	spinlock_t lock;
 	/* Protected by the above dev->gpu_error.lock. */
-	struct i915_gpu_state *first_error;
+	struct i915_gpu_coredump *first_error;
 
 	atomic_t pending_fb_pin;
 
@@ -200,41 +211,115 @@ struct drm_i915_error_state_buf {
 __printf(2, 3)
 void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...);
 
-struct i915_gpu_state *i915_capture_gpu_state(struct drm_i915_private *i915);
-void i915_capture_error_state(struct drm_i915_private *dev_priv,
-			      intel_engine_mask_t engine_mask,
-			      const char *error_msg);
+struct i915_gpu_coredump *i915_gpu_coredump(struct drm_i915_private *i915);
+void i915_capture_error_state(struct drm_i915_private *i915);
+
+struct i915_gpu_coredump *
+i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp);
+
+struct intel_gt_coredump *
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp);
+
+struct intel_engine_coredump *
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp);
+
+struct intel_engine_capture_vma *
+intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
+				  struct i915_request *rq,
+				  gfp_t gfp);
 
-static inline struct i915_gpu_state *
-i915_gpu_state_get(struct i915_gpu_state *gpu)
+void intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
+				   struct intel_engine_capture_vma *capture,
+				   struct i915_vma_compress *compress);
+
+struct i915_vma_compress *
+i915_vma_capture_prepare(struct intel_gt_coredump *gt);
+
+void i915_vma_capture_finish(struct intel_gt_coredump *gt,
+			     struct i915_vma_compress *compress);
+
+void i915_error_state_store(struct i915_gpu_coredump *error);
+
+static inline struct i915_gpu_coredump *
+i915_gpu_coredump_get(struct i915_gpu_coredump *gpu)
 {
 	kref_get(&gpu->ref);
 	return gpu;
 }
 
-ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error,
-				      char *buf, loff_t offset, size_t count);
+ssize_t
+i915_gpu_coredump_copy_to_buffer(struct i915_gpu_coredump *error,
+				 char *buf, loff_t offset, size_t count);
 
-void __i915_gpu_state_free(struct kref *kref);
-static inline void i915_gpu_state_put(struct i915_gpu_state *gpu)
+void __i915_gpu_coredump_free(struct kref *kref);
+static inline void i915_gpu_coredump_put(struct i915_gpu_coredump *gpu)
 {
 	if (gpu)
-		kref_put(&gpu->ref, __i915_gpu_state_free);
+		kref_put(&gpu->ref, __i915_gpu_coredump_free);
 }
 
-struct i915_gpu_state *i915_first_error_state(struct drm_i915_private *i915);
+struct i915_gpu_coredump *i915_first_error_state(struct drm_i915_private *i915);
 void i915_reset_error_state(struct drm_i915_private *i915);
 void i915_disable_error_state(struct drm_i915_private *i915, int err);
 
 #else
 
-static inline void i915_capture_error_state(struct drm_i915_private *dev_priv,
-					    u32 engine_mask,
-					    const char *error_msg)
+static inline void i915_capture_error_state(struct drm_i915_private *i915)
+{
+}
+
+static inline struct i915_gpu_coredump *
+i915_gpu_coredump_alloc(struct drm_i915_private *i915, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline struct intel_gt_coredump *
+intel_gt_coredump_alloc(struct intel_gt *gt, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline struct intel_engine_coredump *
+intel_engine_coredump_alloc(struct intel_engine_cs *engine, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline struct intel_engine_capture_vma *
+intel_engine_coredump_add_request(struct intel_engine_coredump *ee,
+				  struct i915_request *rq,
+				  gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline void
+intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
+			      struct intel_engine_capture_vma *capture,
+			      struct i915_vma_compress *compress)
+{
+}
+
+static inline struct i915_vma_compress *
+i915_vma_capture_prepare(struct intel_gt_coredump *gt)
+{
+	return NULL;
+}
+
+static inline void
+i915_vma_capture_finish(struct intel_gt_coredump *gt,
+			struct i915_vma_compress *compress)
+{
+}
+
+static inline void
+i915_error_state_store(struct drm_i915_private *i915,
+		       struct i915_gpu_coredump *error)
 {
 }
 
-static inline struct i915_gpu_state *
+static inline struct i915_gpu_coredump *
 i915_first_error_state(struct drm_i915_private *i915)
 {
 	return ERR_PTR(-ENODEV);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index dae00f7dd7df..afc6aad9bf8c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -893,7 +893,7 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc)
 }
 
 /**
- * ivybridge_parity_work - Workqueue called when a parity error interrupt
+ * ivb_parity_work - Workqueue called when a parity error interrupt
  * occurred.
  * @work: workqueue struct
  *
@@ -901,7 +901,7 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc)
  * this event, userspace should try to remap the bad rows since statistically
  * it is likely the same row is more likely to go bad again.
  */
-static void ivybridge_parity_work(struct work_struct *work)
+static void ivb_parity_work(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, typeof(*dev_priv), l3_parity.error_work);
@@ -2031,7 +2031,7 @@ static void ivb_display_irq_handler(struct drm_i915_private *dev_priv,
  * 4 - Process the interrupt(s) that had bits set in the IIRs.
  * 5 - Re-enable Master Interrupt Control.
  */
-static irqreturn_t ironlake_irq_handler(int irq, void *arg)
+static irqreturn_t ilk_irq_handler(int irq, void *arg)
 {
 	struct drm_i915_private *dev_priv = arg;
 	u32 de_iir, gt_iir, de_ier, sde_ier = 0;
@@ -2453,6 +2453,25 @@ static inline void gen11_master_intr_enable(void __iomem * const regs)
 	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ);
 }
 
+static void
+gen11_display_irq_handler(struct drm_i915_private *i915)
+{
+	void __iomem * const regs = i915->uncore.regs;
+	const u32 disp_ctl = raw_reg_read(regs, GEN11_DISPLAY_INT_CTL);
+
+	disable_rpm_wakeref_asserts(&i915->runtime_pm);
+	/*
+	 * GEN11_DISPLAY_INT_CTL has same format as GEN8_MASTER_IRQ
+	 * for the display related bits.
+	 */
+	raw_reg_write(regs, GEN11_DISPLAY_INT_CTL, 0x0);
+	gen8_de_irq_handler(i915, disp_ctl);
+	raw_reg_write(regs, GEN11_DISPLAY_INT_CTL,
+		      GEN11_DISPLAY_IRQ_ENABLE);
+
+	enable_rpm_wakeref_asserts(&i915->runtime_pm);
+}
+
 static __always_inline irqreturn_t
 __gen11_irq_handler(struct drm_i915_private * const i915,
 		    u32 (*intr_disable)(void __iomem * const regs),
@@ -2476,17 +2495,8 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 	gen11_gt_irq_handler(gt, master_ctl);
 
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
-	if (master_ctl & GEN11_DISPLAY_IRQ) {
-		const u32 disp_ctl = raw_reg_read(regs, GEN11_DISPLAY_INT_CTL);
-
-		disable_rpm_wakeref_asserts(&i915->runtime_pm);
-		/*
-		 * GEN11_DISPLAY_INT_CTL has same format as GEN8_MASTER_IRQ
-		 * for the display related bits.
-		 */
-		gen8_de_irq_handler(i915, disp_ctl);
-		enable_rpm_wakeref_asserts(&i915->runtime_pm);
-	}
+	if (master_ctl & GEN11_DISPLAY_IRQ)
+		gen11_display_irq_handler(i915);
 
 	gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl);
 
@@ -2732,7 +2742,7 @@ static void vlv_display_irq_postinstall(struct drm_i915_private *dev_priv)
 
 /* drm_dma.h hooks
 */
-static void ironlake_irq_reset(struct drm_i915_private *dev_priv)
+static void ilk_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 
@@ -2788,15 +2798,11 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv)
 		ibx_irq_reset(dev_priv);
 }
 
-static void gen11_irq_reset(struct drm_i915_private *dev_priv)
+static void gen11_display_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 	enum pipe pipe;
 
-	gen11_master_intr_disable(dev_priv->uncore.regs);
-
-	gen11_gt_irq_reset(&dev_priv->gt);
-
 	intel_uncore_write(uncore, GEN11_DISPLAY_INT_CTL, 0);
 
 	if (INTEL_GEN(dev_priv) >= 12) {
@@ -2825,13 +2831,24 @@ static void gen11_irq_reset(struct drm_i915_private *dev_priv)
 	GEN3_IRQ_RESET(uncore, GEN8_DE_PORT_);
 	GEN3_IRQ_RESET(uncore, GEN8_DE_MISC_);
 	GEN3_IRQ_RESET(uncore, GEN11_DE_HPD_);
-	GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_);
-	GEN3_IRQ_RESET(uncore, GEN8_PCU_);
 
 	if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		GEN3_IRQ_RESET(uncore, SDE);
 }
 
+static void gen11_irq_reset(struct drm_i915_private *dev_priv)
+{
+	struct intel_uncore *uncore = &dev_priv->uncore;
+
+	gen11_master_intr_disable(dev_priv->uncore.regs);
+
+	gen11_gt_irq_reset(&dev_priv->gt);
+	gen11_display_irq_reset(dev_priv);
+
+	GEN3_IRQ_RESET(uncore, GEN11_GU_MISC_);
+	GEN3_IRQ_RESET(uncore, GEN8_PCU_);
+}
+
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
 				     u8 pipe_mask)
 {
@@ -2976,6 +2993,8 @@ static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv,
 	hotplug_irqs = sde_ddi_mask | sde_tc_mask;
 	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, pins);
 
+	I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ);
+
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
 	icp_hpd_detection_setup(dev_priv, ddi_enable_mask, tc_enable_mask);
@@ -3081,6 +3100,9 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug_irqs, enabled_irqs;
 
+	if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP)
+		I915_WRITE(SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ);
+
 	hotplug_irqs = SDE_HOTPLUG_MASK_SPT;
 	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt);
 
@@ -3203,7 +3225,7 @@ static void ibx_irq_postinstall(struct drm_i915_private *dev_priv)
 		spt_hpd_detection_setup(dev_priv);
 }
 
-static void ironlake_irq_postinstall(struct drm_i915_private *dev_priv)
+static void ilk_irq_postinstall(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
 	u32 display_mask, extra_mask;
@@ -3597,7 +3619,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		intel_uncore_write16(&dev_priv->uncore, GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3702,7 +3724,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		I915_WRITE(GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3844,10 +3866,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		I915_WRITE(GEN2_IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[RCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[RCS0]);
 
 		if (iir & I915_BSD_USER_INTERRUPT)
-			intel_engine_breadcrumbs_irq(dev_priv->engine[VCS0]);
+			intel_engine_signal_breadcrumbs(dev_priv->engine[VCS0]);
 
 		if (iir & I915_MASTER_ERROR_INTERRUPT)
 			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
@@ -3877,7 +3899,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 
 	intel_hpd_init_work(dev_priv);
 
-	INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work);
+	INIT_WORK(&dev_priv->l3_parity.error_work, ivb_parity_work);
 	for (i = 0; i < MAX_L3_SLICES; ++i)
 		dev_priv->l3_parity.remap_info[i] = NULL;
 
@@ -3958,7 +3980,7 @@ static irq_handler_t intel_irq_handler(struct drm_i915_private *dev_priv)
 		else if (INTEL_GEN(dev_priv) >= 8)
 			return gen8_irq_handler;
 		else
-			return ironlake_irq_handler;
+			return ilk_irq_handler;
 	}
 }
 
@@ -3981,7 +4003,7 @@ static void intel_irq_reset(struct drm_i915_private *dev_priv)
 		else if (INTEL_GEN(dev_priv) >= 8)
 			gen8_irq_reset(dev_priv);
 		else
-			ironlake_irq_reset(dev_priv);
+			ilk_irq_reset(dev_priv);
 	}
 }
 
@@ -4004,7 +4026,7 @@ static void intel_irq_postinstall(struct drm_i915_private *dev_priv)
 		else if (INTEL_GEN(dev_priv) >= 8)
 			gen8_irq_postinstall(dev_priv);
 		else
-			ironlake_irq_postinstall(dev_priv);
+			ilk_irq_postinstall(dev_priv);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/i915_memcpy.c b/drivers/gpu/drm/i915/i915_memcpy.c
index 07b04b0acb77..fdd550405fd3 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.c
+++ b/drivers/gpu/drm/i915/i915_memcpy.c
@@ -27,6 +27,12 @@
 
 #include "i915_memcpy.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
+#define CI_BUG_ON(expr) BUG_ON(expr)
+#else
+#define CI_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr)
+#endif
+
 static DEFINE_STATIC_KEY_FALSE(has_movntdqa);
 
 #ifdef CONFIG_AS_MOVNTDQA
@@ -34,7 +40,6 @@ static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len)
 {
 	kernel_fpu_begin();
 
-	len >>= 4;
 	while (len >= 4) {
 		asm("movntdqa   (%0), %%xmm0\n"
 		    "movntdqa 16(%0), %%xmm1\n"
@@ -59,6 +64,38 @@ static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len)
 
 	kernel_fpu_end();
 }
+
+static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len)
+{
+	kernel_fpu_begin();
+
+	while (len >= 4) {
+		asm("movntdqa   (%0), %%xmm0\n"
+		    "movntdqa 16(%0), %%xmm1\n"
+		    "movntdqa 32(%0), %%xmm2\n"
+		    "movntdqa 48(%0), %%xmm3\n"
+		    "movups %%xmm0,   (%1)\n"
+		    "movups %%xmm1, 16(%1)\n"
+		    "movups %%xmm2, 32(%1)\n"
+		    "movups %%xmm3, 48(%1)\n"
+		    :: "r" (src), "r" (dst) : "memory");
+		src += 64;
+		dst += 64;
+		len -= 4;
+	}
+	while (len--) {
+		asm("movntdqa (%0), %%xmm0\n"
+		    "movups %%xmm0, (%1)\n"
+		    :: "r" (src), "r" (dst) : "memory");
+		src += 16;
+		dst += 16;
+	}
+
+	kernel_fpu_end();
+}
+#else
+static void __memcpy_ntdqa(void *dst, const void *src, unsigned long len) {}
+static void __memcpy_ntdqu(void *dst, const void *src, unsigned long len) {}
 #endif
 
 /**
@@ -83,17 +120,47 @@ bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len)
 	if (unlikely(((unsigned long)dst | (unsigned long)src | len) & 15))
 		return false;
 
-#ifdef CONFIG_AS_MOVNTDQA
 	if (static_branch_likely(&has_movntdqa)) {
 		if (likely(len))
-			__memcpy_ntdqa(dst, src, len);
+			__memcpy_ntdqa(dst, src, len >> 4);
 		return true;
 	}
-#endif
 
 	return false;
 }
 
+/**
+ * i915_unaligned_memcpy_from_wc: perform a mostly accelerated read from WC
+ * @dst: destination pointer
+ * @src: source pointer
+ * @len: how many bytes to copy
+ *
+ * Like i915_memcpy_from_wc(), the unaligned variant copies @len bytes from
+ * @src to @dst using * non-temporal instructions where available, but
+ * accepts that its arguments may not be aligned, but are valid for the
+ * potential 16-byte read past the end.
+ */
+void i915_unaligned_memcpy_from_wc(void *dst, void *src, unsigned long len)
+{
+	unsigned long addr;
+
+	CI_BUG_ON(!i915_has_memcpy_from_wc());
+
+	addr = (unsigned long)src;
+	if (!IS_ALIGNED(addr, 16)) {
+		unsigned long x = min(ALIGN(addr, 16) - addr, len);
+
+		memcpy(dst, src, x);
+
+		len -= x;
+		dst += x;
+		src += x;
+	}
+
+	if (likely(len))
+		__memcpy_ntdqu(dst, src, DIV_ROUND_UP(len, 16));
+}
+
 void i915_memcpy_init_early(struct drm_i915_private *dev_priv)
 {
 	/*
diff --git a/drivers/gpu/drm/i915/i915_memcpy.h b/drivers/gpu/drm/i915/i915_memcpy.h
index 970d84b16987..e36d30edd987 100644
--- a/drivers/gpu/drm/i915/i915_memcpy.h
+++ b/drivers/gpu/drm/i915/i915_memcpy.h
@@ -11,7 +11,9 @@
 struct drm_i915_private;
 
 void i915_memcpy_init_early(struct drm_i915_private *i915);
+
 bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len);
+void i915_unaligned_memcpy_from_wc(void *dst, void *src, unsigned long len);
 
 /* The movntdqa instructions used for memcpy-from-wc require 16-byte alignment,
  * as well as SSE4.1 support. i915_memcpy_from_wc() will report if it cannot
diff --git a/drivers/gpu/drm/i915/i915_mm.c b/drivers/gpu/drm/i915/i915_mm.c
index 318562ce64c0..b6376b25ef63 100644
--- a/drivers/gpu/drm/i915/i915_mm.c
+++ b/drivers/gpu/drm/i915/i915_mm.c
@@ -33,6 +33,9 @@ struct remap_pfn {
 	struct mm_struct *mm;
 	unsigned long pfn;
 	pgprot_t prot;
+
+	struct sgt_iter sgt;
+	resource_size_t iobase;
 };
 
 static int remap_pfn(pte_t *pte, unsigned long addr, void *data)
@@ -46,6 +49,35 @@ static int remap_pfn(pte_t *pte, unsigned long addr, void *data)
 	return 0;
 }
 
+#define use_dma(io) ((io) != -1)
+
+static inline unsigned long sgt_pfn(const struct remap_pfn *r)
+{
+	if (use_dma(r->iobase))
+		return (r->sgt.dma + r->sgt.curr + r->iobase) >> PAGE_SHIFT;
+	else
+		return r->sgt.pfn + (r->sgt.curr >> PAGE_SHIFT);
+}
+
+static int remap_sg(pte_t *pte, unsigned long addr, void *data)
+{
+	struct remap_pfn *r = data;
+
+	if (GEM_WARN_ON(!r->sgt.pfn))
+		return -EINVAL;
+
+	/* Special PTE are not associated with any struct page */
+	set_pte_at(r->mm, addr, pte,
+		   pte_mkspecial(pfn_pte(sgt_pfn(r), r->prot)));
+	r->pfn++; /* track insertions in case we need to unwind later */
+
+	r->sgt.curr += PAGE_SIZE;
+	if (r->sgt.curr >= r->sgt.max)
+		r->sgt = __sgt_iter(__sg_next(r->sgt.sgp), use_dma(r->iobase));
+
+	return 0;
+}
+
 /**
  * remap_io_mapping - remap an IO mapping to userspace
  * @vma: user vma to map to
@@ -80,3 +112,40 @@ int remap_io_mapping(struct vm_area_struct *vma,
 
 	return 0;
 }
+
+/**
+ * remap_io_sg - remap an IO mapping to userspace
+ * @vma: user vma to map to
+ * @addr: target user address to start at
+ * @size: size of map area
+ * @sgl: Start sg entry
+ * @iobase: Use stored dma address offset by this address or pfn if -1
+ *
+ *  Note: this is only safe if the mm semaphore is held when called.
+ */
+int remap_io_sg(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long size,
+		struct scatterlist *sgl, resource_size_t iobase)
+{
+	struct remap_pfn r = {
+		.mm = vma->vm_mm,
+		.prot = vma->vm_page_prot,
+		.sgt = __sgt_iter(sgl, use_dma(iobase)),
+		.iobase = iobase,
+	};
+	int err;
+
+	/* We rely on prevalidation of the io-mapping to skip track_pfn(). */
+	GEM_BUG_ON((vma->vm_flags & EXPECTED_FLAGS) != EXPECTED_FLAGS);
+
+	if (!use_dma(iobase))
+		flush_cache_range(vma, addr, size);
+
+	err = apply_to_page_range(r.mm, addr, size, remap_sg, &r);
+	if (unlikely(err)) {
+		zap_vma_ptes(vma, addr, r.pfn << PAGE_SHIFT);
+		return err;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 1bb701d32a5d..83f01401b8b5 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -30,6 +30,7 @@
 #include "display/intel_fbdev.h"
 
 #include "i915_drv.h"
+#include "i915_perf.h"
 #include "i915_globals.h"
 #include "i915_selftest.h"
 
@@ -192,23 +193,23 @@
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_i830_info = {
+static const struct intel_device_info i830_info = {
 	I830_FEATURES,
 	PLATFORM(INTEL_I830),
 };
 
-static const struct intel_device_info intel_i845g_info = {
+static const struct intel_device_info i845g_info = {
 	I845_FEATURES,
 	PLATFORM(INTEL_I845G),
 };
 
-static const struct intel_device_info intel_i85x_info = {
+static const struct intel_device_info i85x_info = {
 	I830_FEATURES,
 	PLATFORM(INTEL_I85X),
 	.display.has_fbc = 1,
 };
 
-static const struct intel_device_info intel_i865g_info = {
+static const struct intel_device_info i865g_info = {
 	I845_FEATURES,
 	PLATFORM(INTEL_I865G),
 };
@@ -227,7 +228,7 @@ static const struct intel_device_info intel_i865g_info = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_i915g_info = {
+static const struct intel_device_info i915g_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I915G),
 	.has_coherent_ggtt = false,
@@ -238,7 +239,7 @@ static const struct intel_device_info intel_i915g_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i915gm_info = {
+static const struct intel_device_info i915gm_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I915GM),
 	.is_mobile = 1,
@@ -251,7 +252,7 @@ static const struct intel_device_info intel_i915gm_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945g_info = {
+static const struct intel_device_info i945g_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I945G),
 	.display.has_hotplug = 1,
@@ -262,7 +263,7 @@ static const struct intel_device_info intel_i945g_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_i945gm_info = {
+static const struct intel_device_info i945gm_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_I945GM),
 	.is_mobile = 1,
@@ -276,21 +277,21 @@ static const struct intel_device_info intel_i945gm_info = {
 	.unfenced_needs_alignment = 1,
 };
 
-static const struct intel_device_info intel_g33_info = {
+static const struct intel_device_info g33_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_G33),
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
 };
 
-static const struct intel_device_info intel_pineview_g_info = {
+static const struct intel_device_info pnv_g_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_PINEVIEW),
 	.display.has_hotplug = 1,
 	.display.has_overlay = 1,
 };
 
-static const struct intel_device_info intel_pineview_m_info = {
+static const struct intel_device_info pnv_m_info = {
 	GEN3_FEATURES,
 	PLATFORM(INTEL_PINEVIEW),
 	.is_mobile = 1,
@@ -313,7 +314,7 @@ static const struct intel_device_info intel_pineview_m_info = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_i965g_info = {
+static const struct intel_device_info i965g_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_I965G),
 	.display.has_overlay = 1,
@@ -321,7 +322,7 @@ static const struct intel_device_info intel_i965g_info = {
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_i965gm_info = {
+static const struct intel_device_info i965gm_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_I965GM),
 	.is_mobile = 1,
@@ -332,14 +333,14 @@ static const struct intel_device_info intel_i965gm_info = {
 	.has_snoop = false,
 };
 
-static const struct intel_device_info intel_g45_info = {
+static const struct intel_device_info g45_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_G45),
 	.engine_mask = BIT(RCS0) | BIT(VCS0),
 	.gpu_reset_clobbers_display = false,
 };
 
-static const struct intel_device_info intel_gm45_info = {
+static const struct intel_device_info gm45_info = {
 	GEN4_FEATURES,
 	PLATFORM(INTEL_GM45),
 	.is_mobile = 1,
@@ -364,12 +365,12 @@ static const struct intel_device_info intel_gm45_info = {
 	GEN_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_ironlake_d_info = {
+static const struct intel_device_info ilk_d_info = {
 	GEN5_FEATURES,
 	PLATFORM(INTEL_IRONLAKE),
 };
 
-static const struct intel_device_info intel_ironlake_m_info = {
+static const struct intel_device_info ilk_m_info = {
 	GEN5_FEATURES,
 	PLATFORM(INTEL_IRONLAKE),
 	.is_mobile = 1,
@@ -399,12 +400,12 @@ static const struct intel_device_info intel_ironlake_m_info = {
 	GEN6_FEATURES, \
 	PLATFORM(INTEL_SANDYBRIDGE)
 
-static const struct intel_device_info intel_sandybridge_d_gt1_info = {
+static const struct intel_device_info snb_d_gt1_info = {
 	SNB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_d_gt2_info = {
+static const struct intel_device_info snb_d_gt2_info = {
 	SNB_D_PLATFORM,
 	.gt = 2,
 };
@@ -415,12 +416,12 @@ static const struct intel_device_info intel_sandybridge_d_gt2_info = {
 	.is_mobile = 1
 
 
-static const struct intel_device_info intel_sandybridge_m_gt1_info = {
+static const struct intel_device_info snb_m_gt1_info = {
 	SNB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_sandybridge_m_gt2_info = {
+static const struct intel_device_info snb_m_gt2_info = {
 	SNB_M_PLATFORM,
 	.gt = 2,
 };
@@ -436,7 +437,7 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
-	.ppgtt_type = INTEL_PPGTT_ALIASING, \
+	.ppgtt_type = INTEL_PPGTT_FULL, \
 	.ppgtt_size = 31, \
 	IVB_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
@@ -449,12 +450,12 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	PLATFORM(INTEL_IVYBRIDGE), \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_d_gt1_info = {
+static const struct intel_device_info ivb_d_gt1_info = {
 	IVB_D_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_d_gt2_info = {
+static const struct intel_device_info ivb_d_gt2_info = {
 	IVB_D_PLATFORM,
 	.gt = 2,
 };
@@ -465,17 +466,17 @@ static const struct intel_device_info intel_ivybridge_d_gt2_info = {
 	.is_mobile = 1, \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_ivybridge_m_gt1_info = {
+static const struct intel_device_info ivb_m_gt1_info = {
 	IVB_M_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_ivybridge_m_gt2_info = {
+static const struct intel_device_info ivb_m_gt2_info = {
 	IVB_M_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_ivybridge_q_info = {
+static const struct intel_device_info ivb_q_info = {
 	GEN7_FEATURES,
 	PLATFORM(INTEL_IVYBRIDGE),
 	.gt = 2,
@@ -483,7 +484,7 @@ static const struct intel_device_info intel_ivybridge_q_info = {
 	.has_l3_dpf = 1,
 };
 
-static const struct intel_device_info intel_valleyview_info = {
+static const struct intel_device_info vlv_info = {
 	PLATFORM(INTEL_VALLEYVIEW),
 	GEN(7),
 	.is_lp = 1,
@@ -493,7 +494,7 @@ static const struct intel_device_info intel_valleyview_info = {
 	.has_rps = true,
 	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
-	.ppgtt_type = INTEL_PPGTT_ALIASING,
+	.ppgtt_type = INTEL_PPGTT_FULL,
 	.ppgtt_size = 31,
 	.has_snoop = true,
 	.has_coherent_ggtt = false,
@@ -522,17 +523,17 @@ static const struct intel_device_info intel_valleyview_info = {
 	PLATFORM(INTEL_HASWELL), \
 	.has_l3_dpf = 1
 
-static const struct intel_device_info intel_haswell_gt1_info = {
+static const struct intel_device_info hsw_gt1_info = {
 	HSW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_haswell_gt2_info = {
+static const struct intel_device_info hsw_gt2_info = {
 	HSW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_haswell_gt3_info = {
+static const struct intel_device_info hsw_gt3_info = {
 	HSW_PLATFORM,
 	.gt = 3,
 };
@@ -550,17 +551,17 @@ static const struct intel_device_info intel_haswell_gt3_info = {
 	GEN8_FEATURES, \
 	PLATFORM(INTEL_BROADWELL)
 
-static const struct intel_device_info intel_broadwell_gt1_info = {
+static const struct intel_device_info bdw_gt1_info = {
 	BDW_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_broadwell_gt2_info = {
+static const struct intel_device_info bdw_gt2_info = {
 	BDW_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_broadwell_rsvd_info = {
+static const struct intel_device_info bdw_rsvd_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	/* According to the device ID those devices are GT3, they were
@@ -568,14 +569,14 @@ static const struct intel_device_info intel_broadwell_rsvd_info = {
 	 */
 };
 
-static const struct intel_device_info intel_broadwell_gt3_info = {
+static const struct intel_device_info bdw_gt3_info = {
 	BDW_PLATFORM,
 	.gt = 3,
 	.engine_mask =
 		BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1),
 };
 
-static const struct intel_device_info intel_cherryview_info = {
+static const struct intel_device_info chv_info = {
 	PLATFORM(INTEL_CHERRYVIEW),
 	GEN(8),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
@@ -620,12 +621,12 @@ static const struct intel_device_info intel_cherryview_info = {
 	GEN9_FEATURES, \
 	PLATFORM(INTEL_SKYLAKE)
 
-static const struct intel_device_info intel_skylake_gt1_info = {
+static const struct intel_device_info skl_gt1_info = {
 	SKL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_skylake_gt2_info = {
+static const struct intel_device_info skl_gt2_info = {
 	SKL_PLATFORM,
 	.gt = 2,
 };
@@ -636,12 +637,12 @@ static const struct intel_device_info intel_skylake_gt2_info = {
 		BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1)
 
 
-static const struct intel_device_info intel_skylake_gt3_info = {
+static const struct intel_device_info skl_gt3_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 3,
 };
 
-static const struct intel_device_info intel_skylake_gt4_info = {
+static const struct intel_device_info skl_gt4_info = {
 	SKL_GT3_PLUS_PLATFORM,
 	.gt = 4,
 };
@@ -678,13 +679,13 @@ static const struct intel_device_info intel_skylake_gt4_info = {
 	GEN9_DEFAULT_PAGE_SIZES, \
 	GEN_DEFAULT_REGIONS
 
-static const struct intel_device_info intel_broxton_info = {
+static const struct intel_device_info bxt_info = {
 	GEN9_LP_FEATURES,
 	PLATFORM(INTEL_BROXTON),
 	.ddb_size = 512,
 };
 
-static const struct intel_device_info intel_geminilake_info = {
+static const struct intel_device_info glk_info = {
 	GEN9_LP_FEATURES,
 	PLATFORM(INTEL_GEMINILAKE),
 	.ddb_size = 1024,
@@ -695,17 +696,17 @@ static const struct intel_device_info intel_geminilake_info = {
 	GEN9_FEATURES, \
 	PLATFORM(INTEL_KABYLAKE)
 
-static const struct intel_device_info intel_kabylake_gt1_info = {
+static const struct intel_device_info kbl_gt1_info = {
 	KBL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_kabylake_gt2_info = {
+static const struct intel_device_info kbl_gt2_info = {
 	KBL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_kabylake_gt3_info = {
+static const struct intel_device_info kbl_gt3_info = {
 	KBL_PLATFORM,
 	.gt = 3,
 	.engine_mask =
@@ -716,17 +717,17 @@ static const struct intel_device_info intel_kabylake_gt3_info = {
 	GEN9_FEATURES, \
 	PLATFORM(INTEL_COFFEELAKE)
 
-static const struct intel_device_info intel_coffeelake_gt1_info = {
+static const struct intel_device_info cfl_gt1_info = {
 	CFL_PLATFORM,
 	.gt = 1,
 };
 
-static const struct intel_device_info intel_coffeelake_gt2_info = {
+static const struct intel_device_info cfl_gt2_info = {
 	CFL_PLATFORM,
 	.gt = 2,
 };
 
-static const struct intel_device_info intel_coffeelake_gt3_info = {
+static const struct intel_device_info cfl_gt3_info = {
 	CFL_PLATFORM,
 	.gt = 3,
 	.engine_mask =
@@ -741,7 +742,7 @@ static const struct intel_device_info intel_coffeelake_gt3_info = {
 	.has_coherent_ggtt = false, \
 	GLK_COLORS
 
-static const struct intel_device_info intel_cannonlake_info = {
+static const struct intel_device_info cnl_info = {
 	GEN10_FEATURES,
 	PLATFORM(INTEL_CANNONLAKE),
 	.gt = 2,
@@ -776,14 +777,14 @@ static const struct intel_device_info intel_cannonlake_info = {
 	.has_logical_ring_elsq = 1, \
 	.color = { .degamma_lut_size = 33, .gamma_lut_size = 262145 }
 
-static const struct intel_device_info intel_icelake_11_info = {
+static const struct intel_device_info icl_info = {
 	GEN11_FEATURES,
 	PLATFORM(INTEL_ICELAKE),
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
 };
 
-static const struct intel_device_info intel_elkhartlake_info = {
+static const struct intel_device_info ehl_info = {
 	GEN11_FEATURES,
 	PLATFORM(INTEL_ELKHARTLAKE),
 	.require_force_probe = 1,
@@ -814,7 +815,7 @@ static const struct intel_device_info intel_elkhartlake_info = {
 	.has_global_mocs = 1, \
 	.display.has_dsb = 1
 
-static const struct intel_device_info intel_tigerlake_12_info = {
+static const struct intel_device_info tgl_info = {
 	GEN12_FEATURES,
 	PLATFORM(INTEL_TIGERLAKE),
 	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
@@ -839,68 +840,70 @@ static const struct intel_device_info intel_tigerlake_12_info = {
  * PCI ID matches, otherwise we'll use the wrong info struct above.
  */
 static const struct pci_device_id pciidlist[] = {
-	INTEL_I830_IDS(&intel_i830_info),
-	INTEL_I845G_IDS(&intel_i845g_info),
-	INTEL_I85X_IDS(&intel_i85x_info),
-	INTEL_I865G_IDS(&intel_i865g_info),
-	INTEL_I915G_IDS(&intel_i915g_info),
-	INTEL_I915GM_IDS(&intel_i915gm_info),
-	INTEL_I945G_IDS(&intel_i945g_info),
-	INTEL_I945GM_IDS(&intel_i945gm_info),
-	INTEL_I965G_IDS(&intel_i965g_info),
-	INTEL_G33_IDS(&intel_g33_info),
-	INTEL_I965GM_IDS(&intel_i965gm_info),
-	INTEL_GM45_IDS(&intel_gm45_info),
-	INTEL_G45_IDS(&intel_g45_info),
-	INTEL_PINEVIEW_G_IDS(&intel_pineview_g_info),
-	INTEL_PINEVIEW_M_IDS(&intel_pineview_m_info),
-	INTEL_IRONLAKE_D_IDS(&intel_ironlake_d_info),
-	INTEL_IRONLAKE_M_IDS(&intel_ironlake_m_info),
-	INTEL_SNB_D_GT1_IDS(&intel_sandybridge_d_gt1_info),
-	INTEL_SNB_D_GT2_IDS(&intel_sandybridge_d_gt2_info),
-	INTEL_SNB_M_GT1_IDS(&intel_sandybridge_m_gt1_info),
-	INTEL_SNB_M_GT2_IDS(&intel_sandybridge_m_gt2_info),
-	INTEL_IVB_Q_IDS(&intel_ivybridge_q_info), /* must be first IVB */
-	INTEL_IVB_M_GT1_IDS(&intel_ivybridge_m_gt1_info),
-	INTEL_IVB_M_GT2_IDS(&intel_ivybridge_m_gt2_info),
-	INTEL_IVB_D_GT1_IDS(&intel_ivybridge_d_gt1_info),
-	INTEL_IVB_D_GT2_IDS(&intel_ivybridge_d_gt2_info),
-	INTEL_HSW_GT1_IDS(&intel_haswell_gt1_info),
-	INTEL_HSW_GT2_IDS(&intel_haswell_gt2_info),
-	INTEL_HSW_GT3_IDS(&intel_haswell_gt3_info),
-	INTEL_VLV_IDS(&intel_valleyview_info),
-	INTEL_BDW_GT1_IDS(&intel_broadwell_gt1_info),
-	INTEL_BDW_GT2_IDS(&intel_broadwell_gt2_info),
-	INTEL_BDW_GT3_IDS(&intel_broadwell_gt3_info),
-	INTEL_BDW_RSVD_IDS(&intel_broadwell_rsvd_info),
-	INTEL_CHV_IDS(&intel_cherryview_info),
-	INTEL_SKL_GT1_IDS(&intel_skylake_gt1_info),
-	INTEL_SKL_GT2_IDS(&intel_skylake_gt2_info),
-	INTEL_SKL_GT3_IDS(&intel_skylake_gt3_info),
-	INTEL_SKL_GT4_IDS(&intel_skylake_gt4_info),
-	INTEL_BXT_IDS(&intel_broxton_info),
-	INTEL_GLK_IDS(&intel_geminilake_info),
-	INTEL_KBL_GT1_IDS(&intel_kabylake_gt1_info),
-	INTEL_KBL_GT2_IDS(&intel_kabylake_gt2_info),
-	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
-	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
-	INTEL_AML_KBL_GT2_IDS(&intel_kabylake_gt2_info),
-	INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_H_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info),
-	INTEL_WHL_U_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_WHL_U_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_AML_CFL_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_WHL_U_GT3_IDS(&intel_coffeelake_gt3_info),
-	INTEL_CML_GT1_IDS(&intel_coffeelake_gt1_info),
-	INTEL_CML_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CNL_IDS(&intel_cannonlake_info),
-	INTEL_ICL_11_IDS(&intel_icelake_11_info),
-	INTEL_EHL_IDS(&intel_elkhartlake_info),
-	INTEL_TGL_12_IDS(&intel_tigerlake_12_info),
+	INTEL_I830_IDS(&i830_info),
+	INTEL_I845G_IDS(&i845g_info),
+	INTEL_I85X_IDS(&i85x_info),
+	INTEL_I865G_IDS(&i865g_info),
+	INTEL_I915G_IDS(&i915g_info),
+	INTEL_I915GM_IDS(&i915gm_info),
+	INTEL_I945G_IDS(&i945g_info),
+	INTEL_I945GM_IDS(&i945gm_info),
+	INTEL_I965G_IDS(&i965g_info),
+	INTEL_G33_IDS(&g33_info),
+	INTEL_I965GM_IDS(&i965gm_info),
+	INTEL_GM45_IDS(&gm45_info),
+	INTEL_G45_IDS(&g45_info),
+	INTEL_PINEVIEW_G_IDS(&pnv_g_info),
+	INTEL_PINEVIEW_M_IDS(&pnv_m_info),
+	INTEL_IRONLAKE_D_IDS(&ilk_d_info),
+	INTEL_IRONLAKE_M_IDS(&ilk_m_info),
+	INTEL_SNB_D_GT1_IDS(&snb_d_gt1_info),
+	INTEL_SNB_D_GT2_IDS(&snb_d_gt2_info),
+	INTEL_SNB_M_GT1_IDS(&snb_m_gt1_info),
+	INTEL_SNB_M_GT2_IDS(&snb_m_gt2_info),
+	INTEL_IVB_Q_IDS(&ivb_q_info), /* must be first IVB */
+	INTEL_IVB_M_GT1_IDS(&ivb_m_gt1_info),
+	INTEL_IVB_M_GT2_IDS(&ivb_m_gt2_info),
+	INTEL_IVB_D_GT1_IDS(&ivb_d_gt1_info),
+	INTEL_IVB_D_GT2_IDS(&ivb_d_gt2_info),
+	INTEL_HSW_GT1_IDS(&hsw_gt1_info),
+	INTEL_HSW_GT2_IDS(&hsw_gt2_info),
+	INTEL_HSW_GT3_IDS(&hsw_gt3_info),
+	INTEL_VLV_IDS(&vlv_info),
+	INTEL_BDW_GT1_IDS(&bdw_gt1_info),
+	INTEL_BDW_GT2_IDS(&bdw_gt2_info),
+	INTEL_BDW_GT3_IDS(&bdw_gt3_info),
+	INTEL_BDW_RSVD_IDS(&bdw_rsvd_info),
+	INTEL_CHV_IDS(&chv_info),
+	INTEL_SKL_GT1_IDS(&skl_gt1_info),
+	INTEL_SKL_GT2_IDS(&skl_gt2_info),
+	INTEL_SKL_GT3_IDS(&skl_gt3_info),
+	INTEL_SKL_GT4_IDS(&skl_gt4_info),
+	INTEL_BXT_IDS(&bxt_info),
+	INTEL_GLK_IDS(&glk_info),
+	INTEL_KBL_GT1_IDS(&kbl_gt1_info),
+	INTEL_KBL_GT2_IDS(&kbl_gt2_info),
+	INTEL_KBL_GT3_IDS(&kbl_gt3_info),
+	INTEL_KBL_GT4_IDS(&kbl_gt3_info),
+	INTEL_AML_KBL_GT2_IDS(&kbl_gt2_info),
+	INTEL_CFL_S_GT1_IDS(&cfl_gt1_info),
+	INTEL_CFL_S_GT2_IDS(&cfl_gt2_info),
+	INTEL_CFL_H_GT1_IDS(&cfl_gt1_info),
+	INTEL_CFL_H_GT2_IDS(&cfl_gt2_info),
+	INTEL_CFL_U_GT2_IDS(&cfl_gt2_info),
+	INTEL_CFL_U_GT3_IDS(&cfl_gt3_info),
+	INTEL_WHL_U_GT1_IDS(&cfl_gt1_info),
+	INTEL_WHL_U_GT2_IDS(&cfl_gt2_info),
+	INTEL_AML_CFL_GT2_IDS(&cfl_gt2_info),
+	INTEL_WHL_U_GT3_IDS(&cfl_gt3_info),
+	INTEL_CML_GT1_IDS(&cfl_gt1_info),
+	INTEL_CML_GT2_IDS(&cfl_gt2_info),
+	INTEL_CML_U_GT1_IDS(&cfl_gt1_info),
+	INTEL_CML_U_GT2_IDS(&cfl_gt2_info),
+	INTEL_CNL_IDS(&cnl_info),
+	INTEL_ICL_11_IDS(&icl_info),
+	INTEL_EHL_IDS(&ehl_info),
+	INTEL_TGL_12_IDS(&tgl_info),
 	{0, 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, pciidlist);
@@ -1003,6 +1006,12 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return err > 0 ? -ENOTTY : err;
 	}
 
+	err = i915_perf_selftests(pdev);
+	if (err) {
+		i915_pci_remove(pdev);
+		return err > 0 ? -ENOTTY : err;
+	}
+
 	return 0;
 }
 
@@ -1045,7 +1054,12 @@ static int __init i915_init(void)
 		return 0;
 	}
 
-	return pci_register_driver(&i915_pci_driver);
+	err = pci_register_driver(&i915_pci_driver);
+	if (err)
+		return err;
+
+	i915_perf_sysctl_register();
+	return 0;
 }
 
 static void __exit i915_exit(void)
@@ -1053,6 +1067,7 @@ static void __exit i915_exit(void)
 	if (!i915_pci_driver.driver.owner)
 		return;
 
+	i915_perf_sysctl_unregister();
 	pci_unregister_driver(&i915_pci_driver);
 	i915_globals_exit();
 }
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2ae14bc14931..0f556d80ba36 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -387,6 +387,8 @@ struct i915_oa_config_bo {
 	struct i915_vma *vma;
 };
 
+static struct ctl_table_header *sysctl_header;
+
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
 
 void i915_oa_config_release(struct kref *ref)
@@ -1777,6 +1779,8 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	*cs++ = MI_MATH_ADD;
 	*cs++ = MI_MATH_STOREINV(MI_MATH_REG(JUMP_PREDICATE), MI_MATH_REG_CF);
 
+	*cs++ = MI_ARB_CHECK;
+
 	/*
 	 * Transfer the result into the predicate register to be used for the
 	 * predicated jump.
@@ -1966,7 +1970,9 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	if (err)
 		goto err_vma_put;
 
+	intel_engine_pm_get(ce->engine);
 	rq = i915_request_create(ce);
+	intel_engine_pm_put(ce->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_vma_unpin;
@@ -2153,9 +2159,7 @@ static int gen8_modify_context(struct intel_context *ce,
 	struct i915_request *rq;
 	int err;
 
-	lockdep_assert_held(&ce->pin_mutex);
-
-	rq = i915_request_create(ce->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(ce->engine);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
@@ -2197,17 +2201,14 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 		if (ce->engine->class != RENDER_CLASS)
 			continue;
 
-		err = intel_context_lock_pinned(ce);
-		if (err)
-			break;
+		/* Otherwise OA settings will be set upon first use */
+		if (!intel_context_pin_if_active(ce))
+			continue;
 
 		flex->value = intel_sseu_make_rpcs(ctx->i915, &ce->sseu);
+		err = gen8_modify_context(ce, flex, count);
 
-		/* Otherwise OA settings will be set upon first use */
-		if (intel_context_is_pinned(ce))
-			err = gen8_modify_context(ce, flex, count);
-
-		intel_context_unlock_pinned(ce);
+		intel_context_unpin(ce);
 		if (err)
 			break;
 	}
@@ -2317,9 +2318,6 @@ static int oa_configure_all_contexts(struct i915_perf_stream *stream,
 	 */
 	spin_lock(&i915->gem.contexts.lock);
 	list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) {
-		if (ctx == i915->kernel_context)
-			continue;
-
 		if (!kref_get_unless_zero(&ctx->ref))
 			continue;
 
@@ -2455,6 +2453,13 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
 
+static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
+{
+	return _MASKED_FIELD(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS,
+			     (stream->sample_flags & SAMPLE_OA_REPORT) ?
+			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
+}
+
 static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
@@ -2468,12 +2473,10 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
 					      GEN12_OAG_OA_DEBUG_INCLUDE_CLK_RATIO) |
 			   /*
-			    * If the user didn't require OA reports, instruct the
-			    * hardware not to emit ctx switch reports.
+			    * If the user didn't require OA reports, instruct
+			    * the hardware not to emit ctx switch reports.
 			    */
-			   !(stream->sample_flags & SAMPLE_OA_REPORT) ?
-			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS) :
-			   _MASKED_BIT_DISABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS));
+			   oag_report_ctx_switches(stream));
 
 	intel_uncore_write(uncore, GEN12_OAG_OAGLBCTXCTRL, periodic ?
 			   (GEN12_OAG_OAGLBCTXCTRL_COUNTER_RESUME |
@@ -3101,7 +3104,7 @@ static void i915_perf_enable_locked(struct i915_perf_stream *stream)
 		stream->ops->enable(stream);
 
 	if (stream->hold_preemption)
-		i915_gem_context_set_nopreempt(stream->ctx);
+		intel_context_set_nopreempt(stream->pinned_ctx);
 }
 
 /**
@@ -3127,7 +3130,7 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 	stream->enabled = false;
 
 	if (stream->hold_preemption)
-		i915_gem_context_clear_nopreempt(stream->ctx);
+		intel_context_clear_nopreempt(stream->pinned_ctx);
 
 	if (stream->ops->disable)
 		stream->ops->disable(stream);
@@ -3981,7 +3984,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_oa_config *args = data;
 	struct i915_oa_config *oa_config, *tmp;
-	static struct i915_oa_reg *regs;
+	struct i915_oa_reg *regs;
 	int err, id;
 
 	if (!perf->i915) {
@@ -4219,7 +4222,7 @@ static struct ctl_table dev_root[] = {
 };
 
 /**
- * i915_perf_init - initialize i915-perf state on module load
+ * i915_perf_init - initialize i915-perf state on module bind
  * @i915: i915 device instance
  *
  * Initializes i915-perf state without exposing anything to userspace.
@@ -4336,7 +4339,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 
 		oa_sample_rate_hard_limit = 1000 *
 			(RUNTIME_INFO(i915)->cs_timestamp_frequency_khz / 2);
-		perf->sysctl_header = register_sysctl_table(dev_root);
 
 		mutex_init(&perf->metrics_lock);
 		idr_init(&perf->metrics_idr);
@@ -4372,6 +4374,16 @@ static int destroy_config(int id, void *p, void *data)
 	return 0;
 }
 
+void i915_perf_sysctl_register(void)
+{
+	sysctl_header = register_sysctl_table(dev_root);
+}
+
+void i915_perf_sysctl_unregister(void)
+{
+	unregister_sysctl_table(sysctl_header);
+}
+
 /**
  * i915_perf_fini - Counter part to i915_perf_init()
  * @i915: i915 device instance
@@ -4386,8 +4398,6 @@ void i915_perf_fini(struct drm_i915_private *i915)
 	idr_for_each(&perf->metrics_idr, destroy_config, perf);
 	idr_destroy(&perf->metrics_idr);
 
-	unregister_sysctl_table(perf->sysctl_header);
-
 	memset(&perf->ops, 0, sizeof(perf->ops));
 	perf->i915 = NULL;
 }
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 4ceebce72060..882fdd0a7680 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -23,6 +23,8 @@ void i915_perf_fini(struct drm_i915_private *i915);
 void i915_perf_register(struct drm_i915_private *i915);
 void i915_perf_unregister(struct drm_i915_private *i915);
 int i915_perf_ioctl_version(void);
+void i915_perf_sysctl_register(void);
+void i915_perf_sysctl_unregister(void);
 
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 74ddc20a0d37..45e581455f5d 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -380,7 +380,6 @@ struct i915_perf {
 	struct drm_i915_private *i915;
 
 	struct kobject *metrics_kobj;
-	struct ctl_table_header *sysctl_header;
 
 	/*
 	 * Lock associated with adding/modifying/removing OA configs
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d6d2e6fb8674..28a82c849bac 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -259,6 +259,16 @@ add_sample(struct i915_pmu_sample *sample, u32 val)
 	sample->cur += val;
 }
 
+static bool exclusive_mmio_access(const struct drm_i915_private *i915)
+{
+	/*
+	 * We have to avoid concurrent mmio cache line access on gen7 or
+	 * risk a machine hang. For a fun history lesson dig out the old
+	 * userspace intel_gpu_top and run it on Ivybridge or Haswell!
+	 */
+	return IS_GEN(i915, 7);
+}
+
 static void
 engines_sample(struct intel_gt *gt, unsigned int period_ns)
 {
@@ -269,8 +279,12 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 	if ((i915->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
 		return;
 
+	if (!intel_gt_pm_is_awake(gt))
+		return;
+
 	for_each_engine(engine, gt, id) {
 		struct intel_engine_pmu *pmu = &engine->pmu;
+		spinlock_t *mmio_lock;
 		unsigned long flags;
 		bool busy;
 		u32 val;
@@ -278,7 +292,12 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 		if (!intel_engine_pm_get_if_awake(engine))
 			continue;
 
-		spin_lock_irqsave(&engine->uncore->lock, flags);
+		mmio_lock = NULL;
+		if (exclusive_mmio_access(i915))
+			mmio_lock = &engine->uncore->lock;
+
+		if (unlikely(mmio_lock))
+			spin_lock_irqsave(mmio_lock, flags);
 
 		val = ENGINE_READ_FW(engine, RING_CTL);
 		if (val == 0) /* powerwell off => engine idle */
@@ -309,7 +328,8 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 			add_sample(&pmu->sample[I915_SAMPLE_BUSY], period_ns);
 
 skip:
-		spin_unlock_irqrestore(&engine->uncore->lock, flags);
+		if (unlikely(mmio_lock))
+			spin_unlock_irqrestore(mmio_lock, flags);
 		intel_engine_pm_put_async(engine);
 	}
 }
@@ -320,6 +340,13 @@ add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul)
 	sample->cur += mul_u32_u32(val, mul);
 }
 
+static bool frequency_sampling_enabled(struct i915_pmu *pmu)
+{
+	return pmu->enable &
+	       (config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY) |
+		config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY));
+}
+
 static void
 frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 {
@@ -328,19 +355,33 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 	struct i915_pmu *pmu = &i915->pmu;
 	struct intel_rps *rps = &gt->rps;
 
+	if (!frequency_sampling_enabled(pmu))
+		return;
+
+	/* Report 0/0 (actual/requested) frequency while parked. */
+	if (!intel_gt_pm_get_if_awake(gt))
+		return;
+
 	if (pmu->enable & config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) {
 		u32 val;
 
-		val = rps->cur_freq;
-		if (intel_gt_pm_get_if_awake(gt)) {
-			val = intel_uncore_read_notrace(uncore, GEN6_RPSTAT1);
-			val = intel_get_cagf(rps, val);
-			intel_gt_pm_put_async(gt);
-		}
+		/*
+		 * We take a quick peek here without using forcewake
+		 * so that we don't perturb the system under observation
+		 * (forcewake => !rc6 => increased power use). We expect
+		 * that if the read fails because it is outside of the
+		 * mmio power well, then it will return 0 -- in which
+		 * case we assume the system is running at the intended
+		 * frequency. Fortunately, the read should rarely fail!
+		 */
+		val = intel_uncore_read_fw(uncore, GEN6_RPSTAT1);
+		if (val)
+			val = intel_rps_get_cagf(rps, val);
+		else
+			val = rps->cur_freq;
 
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
-				intel_gpu_freq(rps, val),
-				period_ns / 1000);
+				intel_gpu_freq(rps, val), period_ns / 1000);
 	}
 
 	if (pmu->enable & config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) {
@@ -348,6 +389,8 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 				intel_gpu_freq(rps, rps->cur_freq),
 				period_ns / 1000);
 	}
+
+	intel_gt_pm_put_async(gt);
 }
 
 static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 094011b8f64d..6cc55c103f67 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2244,26 +2244,6 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 				    MG_DP_MODE_LN1_ACU_PORT1)
 #define   MG_DP_MODE_CFG_DP_X2_MODE			(1 << 7)
 #define   MG_DP_MODE_CFG_DP_X1_MODE			(1 << 6)
-#define   MG_DP_MODE_CFG_TR2PWR_GATING			(1 << 5)
-#define   MG_DP_MODE_CFG_TRPWR_GATING			(1 << 4)
-#define   MG_DP_MODE_CFG_CLNPWR_GATING			(1 << 3)
-#define   MG_DP_MODE_CFG_DIGPWR_GATING			(1 << 2)
-#define   MG_DP_MODE_CFG_GAONPWR_GATING			(1 << 1)
-
-#define MG_MISC_SUS0_PORT1				0x168814
-#define MG_MISC_SUS0_PORT2				0x169814
-#define MG_MISC_SUS0_PORT3				0x16A814
-#define MG_MISC_SUS0_PORT4				0x16B814
-#define MG_MISC_SUS0(tc_port) \
-	_MMIO(_PORT(tc_port, MG_MISC_SUS0_PORT1, MG_MISC_SUS0_PORT2))
-#define   MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK	(3 << 14)
-#define   MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(x)	((x) << 14)
-#define   MG_MISC_SUS0_CFG_TR2PWR_GATING		(1 << 12)
-#define   MG_MISC_SUS0_CFG_CL2PWR_GATING		(1 << 11)
-#define   MG_MISC_SUS0_CFG_GAONPWR_GATING		(1 << 10)
-#define   MG_MISC_SUS0_CFG_TRPWR_GATING			(1 << 7)
-#define   MG_MISC_SUS0_CFG_CL1PWR_GATING		(1 << 6)
-#define   MG_MISC_SUS0_CFG_DGPWR_GATING			(1 << 5)
 
 /* The spec defines this only for BXT PHY0, but lets assume that this
  * would exist for PHY1 too if it had a second channel.
@@ -5048,14 +5028,20 @@ enum {
 #define   BLM_PCH_POLARITY			(1 << 29)
 #define BLC_PWM_PCH_CTL2	_MMIO(0xc8254)
 
-#define UTIL_PIN_CTL		_MMIO(0x48400)
-#define   UTIL_PIN_ENABLE	(1 << 31)
-
-#define   UTIL_PIN_PIPE(x)     ((x) << 29)
-#define   UTIL_PIN_PIPE_MASK   (3 << 29)
-#define   UTIL_PIN_MODE_PWM    (1 << 24)
-#define   UTIL_PIN_MODE_MASK   (0xf << 24)
-#define   UTIL_PIN_POLARITY    (1 << 22)
+#define UTIL_PIN_CTL			_MMIO(0x48400)
+#define   UTIL_PIN_ENABLE		(1 << 31)
+#define   UTIL_PIN_PIPE_MASK		(3 << 29)
+#define   UTIL_PIN_PIPE(x)		((x) << 29)
+#define   UTIL_PIN_MODE_MASK		(0xf << 24)
+#define   UTIL_PIN_MODE_DATA		(0 << 24)
+#define   UTIL_PIN_MODE_PWM		(1 << 24)
+#define   UTIL_PIN_MODE_VBLANK		(4 << 24)
+#define   UTIL_PIN_MODE_VSYNC		(5 << 24)
+#define   UTIL_PIN_MODE_EYE_LEVEL	(8 << 24)
+#define   UTIL_PIN_OUTPUT_DATA		(1 << 23)
+#define   UTIL_PIN_POLARITY		(1 << 22)
+#define   UTIL_PIN_DIRECTION_INPUT	(1 << 19)
+#define   UTIL_PIN_INPUT_DATA		(1 << 16)
 
 /* BXT backlight register definition. */
 #define _BXT_BLC_PWM_CTL1			0xC8250
@@ -5757,7 +5743,8 @@ enum {
 #define   PIPECONF_DOUBLE_WIDE	(1 << 30)
 #define   I965_PIPECONF_ACTIVE	(1 << 30)
 #define   PIPECONF_DSI_PLL_LOCKED	(1 << 29) /* vlv & pipe A only */
-#define   PIPECONF_FRAME_START_DELAY_MASK (3 << 27)
+#define   PIPECONF_FRAME_START_DELAY_MASK	(3 << 27) /* pre-hsw */
+#define   PIPECONF_FRAME_START_DELAY(x)		((x) << 27) /* pre-hsw: 0-3 */
 #define   PIPECONF_SINGLE_WIDE	0
 #define   PIPECONF_PIPE_UNLOCKED 0
 #define   PIPECONF_PIPE_LOCKED	(1 << 25)
@@ -6365,6 +6352,7 @@ enum {
 #define   DISPPLANE_RGBX101010			(0x8 << 26)
 #define   DISPPLANE_RGBA101010			(0x9 << 26)
 #define   DISPPLANE_BGRX101010			(0xa << 26)
+#define   DISPPLANE_BGRA101010			(0xb << 26)
 #define   DISPPLANE_RGBX161616			(0xc << 26)
 #define   DISPPLANE_RGBX888			(0xe << 26)
 #define   DISPPLANE_RGBA888			(0xf << 26)
@@ -6639,12 +6627,15 @@ enum {
 #define   SP_ENABLE			(1 << 31)
 #define   SP_GAMMA_ENABLE		(1 << 30)
 #define   SP_PIXFORMAT_MASK		(0xf << 26)
-#define   SP_FORMAT_YUV422		(0 << 26)
-#define   SP_FORMAT_BGR565		(5 << 26)
-#define   SP_FORMAT_BGRX8888		(6 << 26)
-#define   SP_FORMAT_BGRA8888		(7 << 26)
-#define   SP_FORMAT_RGBX1010102		(8 << 26)
-#define   SP_FORMAT_RGBA1010102		(9 << 26)
+#define   SP_FORMAT_YUV422		(0x0 << 26)
+#define   SP_FORMAT_8BPP		(0x2 << 26)
+#define   SP_FORMAT_BGR565		(0x5 << 26)
+#define   SP_FORMAT_BGRX8888		(0x6 << 26)
+#define   SP_FORMAT_BGRA8888		(0x7 << 26)
+#define   SP_FORMAT_RGBX1010102		(0x8 << 26)
+#define   SP_FORMAT_RGBA1010102		(0x9 << 26)
+#define   SP_FORMAT_BGRX1010102		(0xa << 26) /* CHV pipe B */
+#define   SP_FORMAT_BGRA1010102		(0xb << 26) /* CHV pipe B */
 #define   SP_FORMAT_RGBX8888		(0xe << 26)
 #define   SP_FORMAT_RGBA8888		(0xf << 26)
 #define   SP_ALPHA_PREMULTIPLY		(1 << 23) /* CHV pipe B */
@@ -6795,6 +6786,7 @@ enum {
 #define   PLANE_CTL_YUV422_VYUY			(3 << 16)
 #define   PLANE_CTL_RENDER_DECOMPRESSION_ENABLE	(1 << 15)
 #define   PLANE_CTL_TRICKLE_FEED_DISABLE	(1 << 14)
+#define   PLANE_CTL_CLEAR_COLOR_DISABLE		(1 << 13) /* TGL+ */
 #define   PLANE_CTL_PLANE_GAMMA_DISABLE		(1 << 13) /* Pre-GLK */
 #define   PLANE_CTL_TILED_MASK			(0x7 << 10)
 #define   PLANE_CTL_TILED_LINEAR		(0 << 10)
@@ -6802,6 +6794,7 @@ enum {
 #define   PLANE_CTL_TILED_Y			(4 << 10)
 #define   PLANE_CTL_TILED_YF			(5 << 10)
 #define   PLANE_CTL_FLIP_HORIZONTAL		(1 << 8)
+#define   PLANE_CTL_MEDIA_DECOMPRESSION_ENABLE	(1 << 4) /* TGL+ */
 #define   PLANE_CTL_ALPHA_MASK			(0x3 << 4) /* Pre-GLK */
 #define   PLANE_CTL_ALPHA_DISABLE		(0 << 4)
 #define   PLANE_CTL_ALPHA_SW_PREMULTIPLY	(2 << 4)
@@ -7512,11 +7505,15 @@ enum {
 #define GEN8_DE_PORT_IMR _MMIO(0x44444)
 #define GEN8_DE_PORT_IIR _MMIO(0x44448)
 #define GEN8_DE_PORT_IER _MMIO(0x4444c)
+#define  DSI1_NON_TE			(1 << 31)
+#define  DSI0_NON_TE			(1 << 30)
 #define  ICL_AUX_CHANNEL_E		(1 << 29)
 #define  CNL_AUX_CHANNEL_F		(1 << 28)
 #define  GEN9_AUX_CHANNEL_D		(1 << 27)
 #define  GEN9_AUX_CHANNEL_C		(1 << 26)
 #define  GEN9_AUX_CHANNEL_B		(1 << 25)
+#define  DSI1_TE			(1 << 24)
+#define  DSI0_TE			(1 << 23)
 #define  BXT_DE_PORT_HP_DDIC		(1 << 5)
 #define  BXT_DE_PORT_HP_DDIB		(1 << 4)
 #define  BXT_DE_PORT_HP_DDIA		(1 << 3)
@@ -7731,6 +7728,8 @@ enum {
 					    [TRANSCODER_B] = _CHICKEN_TRANS_B, \
 					    [TRANSCODER_C] = _CHICKEN_TRANS_C, \
 					    [TRANSCODER_D] = _CHICKEN_TRANS_D))
+#define  HSW_FRAME_START_DELAY_MASK	(3 << 27)
+#define  HSW_FRAME_START_DELAY(x)	((x) << 27) /* 0-3 */
 #define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1 << 25) /* GLK and CNL+ */
 #define  DDI_TRAINING_OVERRIDE_ENABLE	(1 << 19)
 #define  DDI_TRAINING_OVERRIDE_VALUE	(1 << 18)
@@ -7754,6 +7753,14 @@ enum {
 #define GEN7_MSG_CTL	_MMIO(0x45010)
 #define  WAIT_FOR_PCH_RESET_ACK		(1 << 1)
 #define  WAIT_FOR_PCH_FLR_ACK		(1 << 0)
+
+#define BW_BUDDY1_CTL			_MMIO(0x45140)
+#define BW_BUDDY2_CTL			_MMIO(0x45150)
+#define   BW_BUDDY_DISABLE		REG_BIT(31)
+
+#define BW_BUDDY1_PAGE_MASK		_MMIO(0x45144)
+#define BW_BUDDY2_PAGE_MASK		_MMIO(0x45154)
+
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
 #define  RESET_PCH_HANDSHAKE_ENABLE	(1 << 4)
 
@@ -7911,6 +7918,10 @@ enum {
 #define   PIXEL_ROUNDING_TRUNC_FB_PASSTHRU 	(1 << 15)
 #define   PER_PIXEL_ALPHA_BYPASS_EN		(1 << 7)
 
+#define FF_MODE2			_MMIO(0x6604)
+#define   FF_MODE2_TDS_TIMER_MASK	REG_GENMASK(23, 16)
+#define   FF_MODE2_TDS_TIMER_128	REG_FIELD_PREP(FF_MODE2_TDS_TIMER_MASK, 4)
+
 /* PCH */
 
 #define PCH_DISPLAY_BASE	0xc0000u
@@ -8099,6 +8110,10 @@ enum {
 
 #define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
 #define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
+
+#define SHPD_FILTER_CNT				_MMIO(0xc4038)
+#define   SHPD_FILTER_CNT_500_ADJ		0x001D9
+
 /* Icelake DSC Rate Control Range Parameter Registers */
 #define DSCA_RC_RANGE_PARAMETERS_0		_MMIO(0x6B240)
 #define DSCA_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6B240 + 4)
@@ -8449,10 +8464,8 @@ enum {
 #define  TRANS_STATE_MASK       (1 << 30)
 #define  TRANS_STATE_DISABLE    (0 << 30)
 #define  TRANS_STATE_ENABLE     (1 << 30)
-#define  TRANS_FSYNC_DELAY_HB1  (0 << 27)
-#define  TRANS_FSYNC_DELAY_HB2  (1 << 27)
-#define  TRANS_FSYNC_DELAY_HB3  (2 << 27)
-#define  TRANS_FSYNC_DELAY_HB4  (3 << 27)
+#define  TRANS_FRAME_START_DELAY_MASK	(3 << 27) /* ibx */
+#define  TRANS_FRAME_START_DELAY(x)	((x) << 27) /* ibx: 0-3 */
 #define  TRANS_INTERLACE_MASK   (7 << 21)
 #define  TRANS_PROGRESSIVE      (0 << 21)
 #define  TRANS_INTERLACED       (3 << 21)
@@ -8473,6 +8486,7 @@ enum {
 #define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1 << 31)
 #define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1 << 29)
 #define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3 << 27)
+#define  TRANS_CHICKEN2_FRAME_START_DELAY(x)		((x) << 27) /* 0-3 */
 #define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1 << 26)
 #define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1 << 25)
 
@@ -9675,6 +9689,7 @@ enum skl_power_gate {
 #define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
 #define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5 << 12)
 #define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6 << 12)
+#define  TRANS_DDI_EDP_INPUT_D_ONOFF	(7 << 12)
 #define  TRANS_DDI_MST_TRANSPORT_SELECT_MASK	REG_GENMASK(11, 10)
 #define  TRANS_DDI_MST_TRANSPORT_SELECT(trans)	\
 	REG_FIELD_PREP(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, trans)
@@ -10780,6 +10795,57 @@ enum skl_power_gate {
 #define  ICL_ESC_CLK_DIV_SHIFT			0
 #define DSI_MAX_ESC_CLK			20000		/* in KHz */
 
+#define _DSI_CMD_FRMCTL_0		0x6b034
+#define _DSI_CMD_FRMCTL_1		0x6b834
+#define DSI_CMD_FRMCTL(port)		_MMIO_PORT(port,	\
+						   _DSI_CMD_FRMCTL_0,\
+						   _DSI_CMD_FRMCTL_1)
+#define   DSI_FRAME_UPDATE_REQUEST		(1 << 31)
+#define   DSI_PERIODIC_FRAME_UPDATE_ENABLE	(1 << 29)
+#define   DSI_NULL_PACKET_ENABLE		(1 << 28)
+#define   DSI_FRAME_IN_PROGRESS			(1 << 0)
+
+#define _DSI_INTR_MASK_REG_0		0x6b070
+#define _DSI_INTR_MASK_REG_1		0x6b870
+#define DSI_INTR_MASK_REG(port)		_MMIO_PORT(port,	\
+						   _DSI_INTR_MASK_REG_0,\
+						   _DSI_INTR_MASK_REG_1)
+
+#define _DSI_INTR_IDENT_REG_0		0x6b074
+#define _DSI_INTR_IDENT_REG_1		0x6b874
+#define DSI_INTR_IDENT_REG(port)	_MMIO_PORT(port,	\
+						   _DSI_INTR_IDENT_REG_0,\
+						   _DSI_INTR_IDENT_REG_1)
+#define   DSI_TE_EVENT				(1 << 31)
+#define   DSI_RX_DATA_OR_BTA_TERMINATED		(1 << 30)
+#define   DSI_TX_DATA				(1 << 29)
+#define   DSI_ULPS_ENTRY_DONE			(1 << 28)
+#define   DSI_NON_TE_TRIGGER_RECEIVED		(1 << 27)
+#define   DSI_HOST_CHKSUM_ERROR			(1 << 26)
+#define   DSI_HOST_MULTI_ECC_ERROR		(1 << 25)
+#define   DSI_HOST_SINGL_ECC_ERROR		(1 << 24)
+#define   DSI_HOST_CONTENTION_DETECTED		(1 << 23)
+#define   DSI_HOST_FALSE_CONTROL_ERROR		(1 << 22)
+#define   DSI_HOST_TIMEOUT_ERROR		(1 << 21)
+#define   DSI_HOST_LOW_POWER_TX_SYNC_ERROR	(1 << 20)
+#define   DSI_HOST_ESCAPE_MODE_ENTRY_ERROR	(1 << 19)
+#define   DSI_FRAME_UPDATE_DONE			(1 << 16)
+#define   DSI_PROTOCOL_VIOLATION_REPORTED	(1 << 15)
+#define   DSI_INVALID_TX_LENGTH			(1 << 13)
+#define   DSI_INVALID_VC			(1 << 12)
+#define   DSI_INVALID_DATA_TYPE			(1 << 11)
+#define   DSI_PERIPHERAL_CHKSUM_ERROR		(1 << 10)
+#define   DSI_PERIPHERAL_MULTI_ECC_ERROR	(1 << 9)
+#define   DSI_PERIPHERAL_SINGLE_ECC_ERROR	(1 << 8)
+#define   DSI_PERIPHERAL_CONTENTION_DETECTED	(1 << 7)
+#define   DSI_PERIPHERAL_FALSE_CTRL_ERROR	(1 << 6)
+#define   DSI_PERIPHERAL_TIMEOUT_ERROR		(1 << 5)
+#define   DSI_PERIPHERAL_LP_TX_SYNC_ERROR	(1 << 4)
+#define   DSI_PERIPHERAL_ESC_MODE_ENTRY_CMD_ERR	(1 << 3)
+#define   DSI_EOT_SYNC_ERROR			(1 << 2)
+#define   DSI_SOT_SYNC_ERROR			(1 << 1)
+#define   DSI_SOT_ERROR				(1 << 0)
+
 /* Gen4+ Timestamp and Pipe Frame time stamp registers */
 #define GEN4_TIMESTAMP		_MMIO(0x2358)
 #define ILK_TIMESTAMP_HI	_MMIO(0x70070)
@@ -11384,6 +11450,7 @@ enum skl_power_gate {
 #define  CMD_MODE_TE_GATE		(0x1 << 28)
 #define  VIDEO_MODE_SYNC_EVENT		(0x2 << 28)
 #define  VIDEO_MODE_SYNC_PULSE		(0x3 << 28)
+#define  TE_SOURCE_GPIO			(1 << 27)
 #define  LINK_READY			(1 << 20)
 #define  PIX_FMT_MASK			(0x3 << 16)
 #define  PIX_FMT_SHIFT			16
@@ -11636,13 +11703,18 @@ enum skl_power_gate {
 /* MOCS (Memory Object Control State) registers */
 #define GEN9_LNCFCMOCS(i)	_MMIO(0xb020 + (i) * 4)	/* L3 Cache Control */
 
-#define GEN9_GFX_MOCS(i)	_MMIO(0xc800 + (i) * 4)	/* Graphics MOCS registers */
-#define GEN9_MFX0_MOCS(i)	_MMIO(0xc900 + (i) * 4)	/* Media 0 MOCS registers */
-#define GEN9_MFX1_MOCS(i)	_MMIO(0xca00 + (i) * 4)	/* Media 1 MOCS registers */
-#define GEN9_VEBOX_MOCS(i)	_MMIO(0xcb00 + (i) * 4)	/* Video MOCS registers */
-#define GEN9_BLT_MOCS(i)	_MMIO(0xcc00 + (i) * 4)	/* Blitter MOCS registers */
-/* Media decoder 2 MOCS registers */
-#define GEN11_MFX2_MOCS(i)	_MMIO(0x10000 + (i) * 4)
+#define __GEN9_RCS0_MOCS0	0xc800
+#define GEN9_GFX_MOCS(i)	_MMIO(__GEN9_RCS0_MOCS0 + (i) * 4)
+#define __GEN9_VCS0_MOCS0	0xc900
+#define GEN9_MFX0_MOCS(i)	_MMIO(__GEN9_VCS0_MOCS0 + (i) * 4)
+#define __GEN9_VCS1_MOCS0	0xca00
+#define GEN9_MFX1_MOCS(i)	_MMIO(__GEN9_VCS1_MOCS0 + (i) * 4)
+#define __GEN9_VECS0_MOCS0	0xcb00
+#define GEN9_VEBOX_MOCS(i)	_MMIO(__GEN9_VECS0_MOCS0 + (i) * 4)
+#define __GEN9_BCS0_MOCS0	0xcc00
+#define GEN9_BLT_MOCS(i)	_MMIO(__GEN9_BCS0_MOCS0 + (i) * 4)
+#define __GEN11_VCS2_MOCS0	0x10000
+#define GEN11_MFX2_MOCS(i)	_MMIO(__GEN11_VCS2_MOCS0 + (i) * 4)
 
 #define GEN10_SCRATCH_LNCF2		_MMIO(0xb0a0)
 #define   PMFLUSHDONE_LNICRSDROP	(1 << 20)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 765bec89fc0d..be185886e4fc 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -57,11 +57,13 @@ static struct i915_global_request {
 
 static const char *i915_fence_get_driver_name(struct dma_fence *fence)
 {
-	return "i915";
+	return dev_name(to_request(fence)->i915->drm.dev);
 }
 
 static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
 {
+	const struct i915_gem_context *ctx;
+
 	/*
 	 * The timeline struct (as part of the ppgtt underneath a context)
 	 * may be freed when the request is no longer in use by the GPU.
@@ -74,7 +76,11 @@ static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		return "signaled";
 
-	return to_request(fence)->gem_context->name ?: "[i915]";
+	ctx = i915_request_gem_context(to_request(fence));
+	if (!ctx)
+		return "[" DRIVER_NAME "]";
+
+	return ctx->name;
 }
 
 static bool i915_fence_signaled(struct dma_fence *fence)
@@ -188,7 +194,7 @@ static void free_capture_list(struct i915_request *request)
 {
 	struct i915_capture_list *capture;
 
-	capture = request->capture_list;
+	capture = fetch_and_zero(&request->capture_list);
 	while (capture) {
 		struct i915_capture_list *next = capture->next;
 
@@ -214,7 +220,7 @@ static void remove_from_engine(struct i915_request *rq)
 		spin_lock(&engine->active.lock);
 		locked = engine;
 	}
-	list_del(&rq->sched.link);
+	list_del_init(&rq->sched.link);
 	spin_unlock_irq(&locked->active.lock);
 }
 
@@ -223,10 +229,7 @@ bool i915_request_retire(struct i915_request *rq)
 	if (!i915_request_completed(rq))
 		return false;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  rq->engine->name,
-		  rq->fence.context, rq->fence.seqno,
-		  hwsp_seqno(rq));
+	RQ_TRACE(rq, "\n");
 
 	GEM_BUG_ON(!i915_sw_fence_signaled(&rq->submit));
 	trace_i915_request_retire(rq);
@@ -272,8 +275,8 @@ bool i915_request_retire(struct i915_request *rq)
 	remove_from_client(rq);
 	list_del(&rq->link);
 
-	intel_context_exit(rq->hw_context);
-	intel_context_unpin(rq->hw_context);
+	intel_context_exit(rq->context);
+	intel_context_unpin(rq->context);
 
 	free_capture_list(rq);
 	i915_sched_node_fini(&rq->sched);
@@ -287,10 +290,7 @@ void i915_request_retire_upto(struct i915_request *rq)
 	struct intel_timeline * const tl = i915_request_timeline(rq);
 	struct i915_request *tmp;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  rq->engine->name,
-		  rq->fence.context, rq->fence.seqno,
-		  hwsp_seqno(rq));
+	RQ_TRACE(rq, "\n");
 
 	GEM_BUG_ON(!i915_request_completed(rq));
 
@@ -351,10 +351,7 @@ bool __i915_request_submit(struct i915_request *request)
 	struct intel_engine_cs *engine = request->engine;
 	bool result = false;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  engine->name,
-		  request->fence.context, request->fence.seqno,
-		  hwsp_seqno(request));
+	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
@@ -378,7 +375,7 @@ bool __i915_request_submit(struct i915_request *request)
 	if (i915_request_completed(request))
 		goto xfer;
 
-	if (i915_gem_context_is_banned(request->gem_context))
+	if (intel_context_is_banned(request->context))
 		i915_request_skip(request, -EIO);
 
 	/*
@@ -417,7 +414,7 @@ xfer:	/* We may be recursing from the signal callback of another i915 fence */
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
 	    !i915_request_enable_breadcrumb(request))
-		intel_engine_queue_breadcrumbs(engine);
+		intel_engine_signal_breadcrumbs(engine);
 
 	__notify_execute_cb(request);
 
@@ -443,10 +440,7 @@ void __i915_request_unsubmit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 
-	GEM_TRACE("%s fence %llx:%lld, current %d\n",
-		  engine->name,
-		  request->fence.context, request->fence.seqno,
-		  hwsp_seqno(request));
+	RQ_TRACE(request, "\n");
 
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
@@ -588,6 +582,21 @@ out:
 	return kmem_cache_alloc(global.slab_requests, gfp);
 }
 
+static void __i915_request_ctor(void *arg)
+{
+	struct i915_request *rq = arg;
+
+	spin_lock_init(&rq->lock);
+	i915_sched_node_init(&rq->sched);
+	i915_sw_fence_init(&rq->submit, submit_notify);
+	i915_sw_fence_init(&rq->semaphore, semaphore_notify);
+
+	rq->file_priv = NULL;
+	rq->capture_list = NULL;
+
+	INIT_LIST_HEAD(&rq->execute_cb);
+}
+
 struct i915_request *
 __i915_request_create(struct intel_context *ce, gfp_t gfp)
 {
@@ -645,35 +654,31 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 		goto err_free;
 
 	rq->i915 = ce->engine->i915;
-	rq->hw_context = ce;
-	rq->gem_context = ce->gem_context;
+	rq->context = ce;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
 	rq->execution_mask = ce->engine->mask;
 
-	rcu_assign_pointer(rq->timeline, tl);
+	RCU_INIT_POINTER(rq->timeline, tl);
+	RCU_INIT_POINTER(rq->hwsp_cacheline, tl->hwsp_cacheline);
 	rq->hwsp_seqno = tl->hwsp_seqno;
-	rq->hwsp_cacheline = tl->hwsp_cacheline;
 
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
-	spin_lock_init(&rq->lock);
 	dma_fence_init(&rq->fence, &i915_fence_ops, &rq->lock,
 		       tl->fence_context, seqno);
 
 	/* We bump the ref for the fence chain */
-	i915_sw_fence_init(&i915_request_get(rq)->submit, submit_notify);
-	i915_sw_fence_init(&i915_request_get(rq)->semaphore, semaphore_notify);
+	i915_sw_fence_reinit(&i915_request_get(rq)->submit);
+	i915_sw_fence_reinit(&i915_request_get(rq)->semaphore);
 
-	i915_sched_node_init(&rq->sched);
+	i915_sched_node_reinit(&rq->sched);
 
-	/* No zalloc, must clear what we need by hand */
-	rq->file_priv = NULL;
+	/* No zalloc, everything must be cleared after use */
 	rq->batch = NULL;
-	rq->capture_list = NULL;
-	rq->flags = 0;
-
-	INIT_LIST_HEAD(&rq->execute_cb);
+	GEM_BUG_ON(rq->file_priv);
+	GEM_BUG_ON(rq->capture_list);
+	GEM_BUG_ON(!list_empty(&rq->execute_cb));
 
 	/*
 	 * Reserve space in the ring buffer for all the commands required to
@@ -755,34 +760,37 @@ err_unlock:
 static int
 i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 {
-	struct intel_timeline *tl;
 	struct dma_fence *fence;
 	int err;
 
 	GEM_BUG_ON(i915_request_timeline(rq) ==
 		   rcu_access_pointer(signal->timeline));
 
+	fence = NULL;
 	rcu_read_lock();
-	tl = rcu_dereference(signal->timeline);
-	if (i915_request_started(signal) || !kref_get_unless_zero(&tl->kref))
-		tl = NULL;
-	rcu_read_unlock();
-	if (!tl) /* already started or maybe even completed */
-		return 0;
+	spin_lock_irq(&signal->lock);
+	if (!i915_request_started(signal) &&
+	    !list_is_first(&signal->link,
+			   &rcu_dereference(signal->timeline)->requests)) {
+		struct i915_request *prev = list_prev_entry(signal, link);
 
-	fence = ERR_PTR(-EBUSY);
-	if (mutex_trylock(&tl->mutex)) {
-		fence = NULL;
-		if (!i915_request_started(signal) &&
-		    !list_is_first(&signal->link, &tl->requests)) {
-			signal = list_prev_entry(signal, link);
-			fence = dma_fence_get(&signal->fence);
+		/*
+		 * Peek at the request before us in the timeline. That
+		 * request will only be valid before it is retired, so
+		 * after acquiring a reference to it, confirm that it is
+		 * still part of the signaler's timeline.
+		 */
+		if (i915_request_get_rcu(prev)) {
+			if (list_next_entry(prev, link) == signal)
+				fence = &prev->fence;
+			else
+				i915_request_put(prev);
 		}
-		mutex_unlock(&tl->mutex);
 	}
-	intel_timeline_put(tl);
-	if (IS_ERR_OR_NULL(fence))
-		return PTR_ERR_OR_ZERO(fence);
+	spin_unlock_irq(&signal->lock);
+	rcu_read_unlock();
+	if (!fence)
+		return 0;
 
 	err = 0;
 	if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
@@ -908,18 +916,16 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 			return ret;
 	}
 
-	if (to->engine == from->engine) {
+	if (to->engine == from->engine)
 		ret = i915_sw_fence_await_sw_fence_gfp(&to->submit,
 						       &from->submit,
 						       I915_FENCE_GFP);
-	} else if (intel_engine_has_semaphores(to->engine) &&
-		   to->gem_context->sched.priority >= I915_PRIORITY_NORMAL) {
+	else if (intel_context_use_semaphores(to->context))
 		ret = emit_semaphore_wait(to, from, I915_FENCE_GFP);
-	} else {
+	else
 		ret = i915_sw_fence_await_dma_fence(&to->submit,
 						    &from->fence, 0,
 						    I915_FENCE_GFP);
-	}
 	if (ret < 0)
 		return ret;
 
@@ -959,8 +965,10 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			i915_sw_fence_set_error_once(&rq->submit, fence->error);
 			continue;
+		}
 
 		/*
 		 * Requests on the same timeline are explicitly ordered, along
@@ -1067,8 +1075,10 @@ i915_request_await_execution(struct i915_request *rq,
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+			i915_sw_fence_set_error_once(&rq->submit, fence->error);
 			continue;
+		}
 
 		/*
 		 * We don't squash repeated fence dependencies here as we
@@ -1244,8 +1254,7 @@ struct i915_request *__i915_request_commit(struct i915_request *rq)
 	struct intel_ring *ring = rq->ring;
 	u32 *cs;
 
-	GEM_TRACE("%s fence %llx:%lld\n",
-		  engine->name, rq->fence.context, rq->fence.seqno);
+	RQ_TRACE(rq, "\n");
 
 	/*
 	 * To ensure that this call will not fail, space for its emissions
@@ -1291,8 +1300,8 @@ void __i915_request_queue(struct i915_request *rq,
 
 void i915_request_add(struct i915_request *rq)
 {
-	struct i915_sched_attr attr = rq->gem_context->sched;
 	struct intel_timeline * const tl = i915_request_timeline(rq);
+	struct i915_sched_attr attr = {};
 	struct i915_request *prev;
 
 	lockdep_assert_held(&tl->mutex);
@@ -1302,6 +1311,9 @@ void i915_request_add(struct i915_request *rq)
 
 	prev = __i915_request_commit(rq);
 
+	if (rcu_access_pointer(rq->context->gem_context))
+		attr = i915_request_gem_context(rq)->sched;
+
 	/*
 	 * Boost actual workloads past semaphores!
 	 *
@@ -1597,10 +1609,14 @@ static struct i915_global_request global = { {
 
 int __init i915_global_request_init(void)
 {
-	global.slab_requests = KMEM_CACHE(i915_request,
-					  SLAB_HWCACHE_ALIGN |
-					  SLAB_RECLAIM_ACCOUNT |
-					  SLAB_TYPESAFE_BY_RCU);
+	global.slab_requests =
+		kmem_cache_create("i915_request",
+				  sizeof(struct i915_request),
+				  __alignof__(struct i915_request),
+				  SLAB_HWCACHE_ALIGN |
+				  SLAB_RECLAIM_ACCOUNT |
+				  SLAB_TYPESAFE_BY_RCU,
+				  __i915_request_ctor);
 	if (!global.slab_requests)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 96991d64759c..031433691a06 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -28,8 +28,10 @@
 #include <linux/dma-fence.h>
 #include <linux/lockdep.h>
 
+#include "gem/i915_gem_context_types.h"
 #include "gt/intel_context_types.h"
 #include "gt/intel_engine_types.h"
+#include "gt/intel_timeline_types.h"
 
 #include "i915_gem.h"
 #include "i915_scheduler.h"
@@ -41,14 +43,19 @@
 struct drm_file;
 struct drm_i915_gem_object;
 struct i915_request;
-struct intel_timeline;
-struct intel_timeline_cacheline;
 
 struct i915_capture_list {
 	struct i915_capture_list *next;
 	struct i915_vma *vma;
 };
 
+#define RQ_TRACE(rq, fmt, ...) do {					\
+	const struct i915_request *rq__ = (rq);				\
+	ENGINE_TRACE(rq__->engine, "fence %llx:%lld, current %d " fmt,	\
+		     rq__->fence.context, rq__->fence.seqno,		\
+		     hwsp_seqno(rq__), ##__VA_ARGS__);			\
+} while (0)
+
 enum {
 	/*
 	 * I915_FENCE_FLAG_ACTIVE - this request is currently submitted to HW.
@@ -70,6 +77,38 @@ enum {
 	 * a request is on the various signal_list.
 	 */
 	I915_FENCE_FLAG_SIGNAL,
+
+	/*
+	 * I915_FENCE_FLAG_NOPREEMPT - this request should not be preempted
+	 *
+	 * The execution of some requests should not be interrupted. This is
+	 * a sensitive operation as it makes the request super important,
+	 * blocking other higher priority work. Abuse of this flag will
+	 * lead to quality of service issues.
+	 */
+	I915_FENCE_FLAG_NOPREEMPT,
+
+	/*
+	 * I915_FENCE_FLAG_SENTINEL - this request should be last in the queue
+	 *
+	 * A high priority sentinel request may be submitted to clear the
+	 * submission queue. As it will be the only request in-flight, upon
+	 * execution all other active requests will have been preempted and
+	 * unsubmitted. This preemptive pulse is used to re-evaluate the
+	 * in-flight requests, particularly in cases where an active context
+	 * is banned and those active requests need to be cancelled.
+	 */
+	I915_FENCE_FLAG_SENTINEL,
+
+	/*
+	 * I915_FENCE_FLAG_BOOST - upclock the gpu for this request
+	 *
+	 * Some requests are more important than others! In particular, a
+	 * request that the user is waiting on is typically required for
+	 * interactive latency, for which we want to minimise by upclocking
+	 * the GPU. Here we track such boost requests on a per-request basis.
+	 */
+	I915_FENCE_FLAG_BOOST,
 };
 
 /**
@@ -109,9 +148,8 @@ struct i915_request {
 	 * i915_request_free() will then decrement the refcount on the
 	 * context.
 	 */
-	struct i915_gem_context *gem_context;
 	struct intel_engine_cs *engine;
-	struct intel_context *hw_context;
+	struct intel_context *context;
 	struct intel_ring *ring;
 	struct intel_timeline __rcu *timeline;
 	struct list_head signal_link;
@@ -144,6 +182,10 @@ struct i915_request {
 	union {
 		wait_queue_entry_t submitq;
 		struct i915_sw_dma_fence_cb dmaq;
+		struct i915_request_duration_cb {
+			struct dma_fence_cb cb;
+			ktime_t emitted;
+		} duration;
 	};
 	struct list_head execute_cb;
 	struct i915_sw_fence semaphore;
@@ -176,7 +218,7 @@ struct i915_request {
 	 * inside the timeline's HWSP vma, but it is only valid while this
 	 * request has not completed and guarded by the timeline mutex.
 	 */
-	struct intel_timeline_cacheline *hwsp_cacheline;
+	struct intel_timeline_cacheline __rcu *hwsp_cacheline;
 
 	/** Position in the ring of the start of the request */
 	u32 head;
@@ -215,11 +257,6 @@ struct i915_request {
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
 
-	unsigned long flags;
-#define I915_REQUEST_WAITBOOST	BIT(0)
-#define I915_REQUEST_NOPREEMPT	BIT(1)
-#define I915_REQUEST_SENTINEL	BIT(2)
-
 	/** timeline->request entry for this request */
 	struct list_head link;
 
@@ -432,18 +469,18 @@ static inline void i915_request_mark_complete(struct i915_request *rq)
 
 static inline bool i915_request_has_waitboost(const struct i915_request *rq)
 {
-	return rq->flags & I915_REQUEST_WAITBOOST;
+	return test_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags);
 }
 
 static inline bool i915_request_has_nopreempt(const struct i915_request *rq)
 {
 	/* Preemption should only be disabled very rarely */
-	return unlikely(rq->flags & I915_REQUEST_NOPREEMPT);
+	return unlikely(test_bit(I915_FENCE_FLAG_NOPREEMPT, &rq->fence.flags));
 }
 
 static inline bool i915_request_has_sentinel(const struct i915_request *rq)
 {
-	return unlikely(rq->flags & I915_REQUEST_SENTINEL);
+	return unlikely(test_bit(I915_FENCE_FLAG_SENTINEL, &rq->fence.flags));
 }
 
 static inline struct intel_timeline *
@@ -454,6 +491,13 @@ i915_request_timeline(struct i915_request *rq)
 					 lockdep_is_held(&rcu_access_pointer(rq->timeline)->mutex));
 }
 
+static inline struct i915_gem_context *
+i915_request_gem_context(struct i915_request *rq)
+{
+	/* Valid only while the request is being constructed (or retired). */
+	return rcu_dereference_protected(rq->context->gem_context, true);
+}
+
 static inline struct intel_timeline *
 i915_request_active_timeline(struct i915_request *rq)
 {
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 247a9671bca5..bf87c70bfdd9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -213,7 +213,7 @@ static void kick_submission(struct intel_engine_cs *engine,
 	 * If we are already the currently executing context, don't
 	 * bother evaluating if we should preempt ourselves.
 	 */
-	if (inflight->hw_context == rq->hw_context)
+	if (inflight->context == rq->context)
 		goto unlock;
 
 	engine->execlists.queue_priority_hint = prio;
@@ -387,9 +387,19 @@ void i915_sched_node_init(struct i915_sched_node *node)
 	INIT_LIST_HEAD(&node->signalers_list);
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
+
+	i915_sched_node_reinit(node);
+}
+
+void i915_sched_node_reinit(struct i915_sched_node *node)
+{
 	node->attr.priority = I915_PRIORITY_INVALID;
 	node->semaphores = 0;
 	node->flags = 0;
+
+	GEM_BUG_ON(!list_empty(&node->signalers_list));
+	GEM_BUG_ON(!list_empty(&node->waiters_list));
+	GEM_BUG_ON(!list_empty(&node->link));
 }
 
 static struct i915_dependency *
@@ -480,6 +490,7 @@ void i915_sched_node_fini(struct i915_sched_node *node)
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(dep);
 	}
+	INIT_LIST_HEAD(&node->signalers_list);
 
 	/* Remove ourselves from everyone who depends upon us */
 	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
@@ -490,6 +501,7 @@ void i915_sched_node_fini(struct i915_sched_node *node)
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(dep);
 	}
+	INIT_LIST_HEAD(&node->waiters_list);
 
 	spin_unlock_irq(&schedule_lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 07d243acf553..d1dc4efef77b 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -26,6 +26,7 @@
 					 sched.link)
 
 void i915_sched_node_init(struct i915_sched_node *node);
+void i915_sched_node_reinit(struct i915_sched_node *node);
 
 bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 				      struct i915_sched_node *signal,
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index 4d88205de51b..98bcb6fa0ab4 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -36,6 +36,7 @@ struct i915_selftest {
 	char *filter;
 	int mock;
 	int live;
+	int perf;
 };
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
@@ -45,6 +46,7 @@ extern struct i915_selftest i915_selftest;
 
 int i915_mock_selftests(void);
 int i915_live_selftests(struct pci_dev *pdev);
+int i915_perf_selftests(struct pci_dev *pdev);
 
 /* We extract the function declarations from i915_mock_selftests.h and
  * i915_live_selftests.h Add your unit test declarations there!
@@ -61,6 +63,7 @@ int i915_live_selftests(struct pci_dev *pdev);
 #undef selftest
 #define selftest(name, func) int func(struct drm_i915_private *i915);
 #include "selftests/i915_live_selftests.h"
+#include "selftests/i915_perf_selftests.h"
 #undef selftest
 
 struct i915_subtest {
@@ -109,6 +112,7 @@ int __i915_subtests(const char *caller,
 
 static inline int i915_mock_selftests(void) { return 0; }
 static inline int i915_live_selftests(struct pci_dev *pdev) { return 0; }
+static inline int i915_perf_selftests(struct pci_dev *pdev) { return 0; }
 
 #define I915_SELFTEST_DECLARE(x)
 #define I915_SELFTEST_ONLY(x) 0
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 6a88db291252..51ba97daf2a0 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -12,6 +12,12 @@
 #include "i915_sw_fence.h"
 #include "i915_selftest.h"
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
+#define I915_SW_FENCE_BUG_ON(expr) BUG_ON(expr)
+#else
+#define I915_SW_FENCE_BUG_ON(expr) BUILD_BUG_ON_INVALID(expr)
+#endif
+
 #define I915_SW_FENCE_FLAG_ALLOC BIT(3) /* after WQ_FLAG_* for safety */
 
 static DEFINE_SPINLOCK(i915_sw_fence_lock);
@@ -218,13 +224,21 @@ void __i915_sw_fence_init(struct i915_sw_fence *fence,
 {
 	BUG_ON(!fn || (unsigned long)fn & ~I915_SW_FENCE_MASK);
 
+	__init_waitqueue_head(&fence->wait, name, key);
+	fence->flags = (unsigned long)fn;
+
+	i915_sw_fence_reinit(fence);
+}
+
+void i915_sw_fence_reinit(struct i915_sw_fence *fence)
+{
 	debug_fence_init(fence);
 
-	__init_waitqueue_head(&fence->wait, name, key);
 	atomic_set(&fence->pending, 1);
 	fence->error = 0;
 
-	fence->flags = (unsigned long)fn;
+	I915_SW_FENCE_BUG_ON(!fence->flags);
+	I915_SW_FENCE_BUG_ON(!list_empty(&fence->wait.head));
 }
 
 void i915_sw_fence_commit(struct i915_sw_fence *fence)
@@ -414,8 +428,10 @@ static void dma_i915_sw_fence_wake_timer(struct dma_fence *dma,
 	struct i915_sw_fence *fence;
 
 	fence = xchg(&cb->base.fence, NULL);
-	if (fence)
+	if (fence) {
+		i915_sw_fence_set_error_once(fence, dma->error);
 		i915_sw_fence_complete(fence);
+	}
 
 	irq_work_queue(&cb->work);
 }
@@ -443,8 +459,10 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 	debug_fence_assert(fence);
 	might_sleep_if(gfpflags_allow_blocking(gfp));
 
-	if (dma_fence_is_signaled(dma))
+	if (dma_fence_is_signaled(dma)) {
+		i915_sw_fence_set_error_once(fence, dma->error);
 		return 0;
+	}
 
 	cb = kmalloc(timeout ?
 		     sizeof(struct i915_sw_dma_fence_cb_timer) :
@@ -454,7 +472,12 @@ int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 		if (!gfpflags_allow_blocking(gfp))
 			return -ENOMEM;
 
-		return dma_fence_wait(dma, false);
+		ret = dma_fence_wait(dma, false);
+		if (ret)
+			return ret;
+
+		i915_sw_fence_set_error_once(fence, dma->error);
+		return 0;
 	}
 
 	cb->fence = fence;
@@ -504,8 +527,10 @@ int __i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence,
 
 	debug_fence_assert(fence);
 
-	if (dma_fence_is_signaled(dma))
+	if (dma_fence_is_signaled(dma)) {
+		i915_sw_fence_set_error_once(fence, dma->error);
 		return 0;
+	}
 
 	cb->fence = fence;
 	i915_sw_fence_await(fence);
@@ -539,8 +564,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence,
 		struct dma_fence **shared;
 		unsigned int count, i;
 
-		ret = dma_resv_get_fences_rcu(resv,
-							&excl, &count, &shared);
+		ret = dma_resv_get_fences_rcu(resv, &excl, &count, &shared);
 		if (ret)
 			return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h
index ab7d58bd0b9d..19e806ce43bc 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.h
+++ b/drivers/gpu/drm/i915/i915_sw_fence.h
@@ -54,6 +54,8 @@ do {								\
 	__i915_sw_fence_init((fence), (fn), NULL, NULL)
 #endif
 
+void i915_sw_fence_reinit(struct i915_sw_fence *fence);
+
 #ifdef CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS
 void i915_sw_fence_fini(struct i915_sw_fence *fence);
 #else
@@ -110,7 +112,8 @@ static inline void i915_sw_fence_wait(struct i915_sw_fence *fence)
 static inline void
 i915_sw_fence_set_error_once(struct i915_sw_fence *fence, int error)
 {
-	cmpxchg(&fence->error, 0, error);
+	if (unlikely(error))
+		cmpxchg(&fence->error, 0, error);
 }
 
 #endif /* _I915_SW_FENCE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_sw_fence_work.c b/drivers/gpu/drm/i915/i915_sw_fence_work.c
index 8538ee7a521d..997b2998f1f2 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence_work.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence_work.c
@@ -6,6 +6,13 @@
 
 #include "i915_sw_fence_work.h"
 
+static void fence_complete(struct dma_fence_work *f)
+{
+	if (f->ops->release)
+		f->ops->release(f);
+	dma_fence_signal(&f->dma);
+}
+
 static void fence_work(struct work_struct *work)
 {
 	struct dma_fence_work *f = container_of(work, typeof(*f), work);
@@ -14,7 +21,8 @@ static void fence_work(struct work_struct *work)
 	err = f->ops->work(f);
 	if (err)
 		dma_fence_set_error(&f->dma, err);
-	dma_fence_signal(&f->dma);
+
+	fence_complete(f);
 	dma_fence_put(&f->dma);
 }
 
@@ -32,7 +40,7 @@ fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
 			dma_fence_get(&f->dma);
 			queue_work(system_unbound_wq, &f->work);
 		} else {
-			dma_fence_signal(&f->dma);
+			fence_complete(f);
 		}
 		break;
 
@@ -60,9 +68,6 @@ static void fence_release(struct dma_fence *fence)
 {
 	struct dma_fence_work *f = container_of(fence, typeof(*f), dma);
 
-	if (f->ops->release)
-		f->ops->release(f);
-
 	i915_sw_fence_fini(&f->chain);
 
 	BUILD_BUG_ON(offsetof(typeof(*f), dma));
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 65476909d1bf..0cef3130db05 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -259,33 +259,18 @@ static const struct bin_attribute dpf_attrs_1 = {
 static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
-	intel_wakeref_t wakeref;
-	u32 freq;
-
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		vlv_punit_get(dev_priv);
-		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-		vlv_punit_put(dev_priv);
-
-		freq = (freq >> 8) & 0xff;
-	} else {
-		freq = intel_get_cagf(rps, I915_READ(GEN6_RPSTAT1));
-	}
-
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", intel_gpu_freq(rps, freq));
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			intel_rps_read_actual_frequency(rps));
 }
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
 			intel_gpu_freq(rps, rps->cur_freq));
@@ -293,8 +278,8 @@ static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 
 static ssize_t gt_boost_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt.rps;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &i915->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
 			intel_gpu_freq(rps, rps->boost_freq));
@@ -513,15 +498,15 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 
 	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
-	struct i915_gpu_state *gpu;
+	struct i915_gpu_coredump *gpu;
 	ssize_t ret;
 
 	gpu = i915_first_error_state(i915);
 	if (IS_ERR(gpu)) {
 		ret = PTR_ERR(gpu);
 	} else if (gpu) {
-		ret = i915_gpu_state_copy_to_buffer(gpu, buf, off, count);
-		i915_gpu_state_put(gpu);
+		ret = i915_gpu_coredump_copy_to_buffer(gpu, buf, off, count);
+		i915_gpu_coredump_put(gpu);
 	} else {
 		const char *str = "No error state collected\n";
 		size_t len = strlen(str);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 7ef7a1e1664c..233a97a2c276 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -341,7 +341,7 @@ TRACE_EVENT(intel_disable_plane,
 
 /* pipe updates */
 
-TRACE_EVENT(i915_pipe_update_start,
+TRACE_EVENT(intel_pipe_update_start,
 	    TP_PROTO(struct intel_crtc *crtc),
 	    TP_ARGS(crtc),
 
@@ -366,7 +366,7 @@ TRACE_EVENT(i915_pipe_update_start,
 		       __entry->scanline, __entry->min, __entry->max)
 );
 
-TRACE_EVENT(i915_pipe_update_vblank_evaded,
+TRACE_EVENT(intel_pipe_update_vblank_evaded,
 	    TP_PROTO(struct intel_crtc *crtc),
 	    TP_ARGS(crtc),
 
@@ -391,7 +391,7 @@ TRACE_EVENT(i915_pipe_update_vblank_evaded,
 		       __entry->scanline, __entry->min, __entry->max)
 );
 
-TRACE_EVENT(i915_pipe_update_end,
+TRACE_EVENT(intel_pipe_update_end,
 	    TP_PROTO(struct intel_crtc *crtc, u32 frame, int scanline_end),
 	    TP_ARGS(crtc, frame, scanline_end),
 
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index 0348c6d0ef5f..c47261ae86ea 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -23,7 +23,7 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	struct va_format vaf;
 	va_list args;
 
-	if (is_debug && !(drm_debug & DRM_UT_DRIVER))
+	if (is_debug && !drm_debug_enabled(DRM_UT_DRIVER))
 		return;
 
 	va_start(args, fmt);
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 04139ba1191e..b0ade76bec90 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -69,7 +69,7 @@ bool i915_error_injected(void);
 
 #else
 
-#define i915_inject_probe_error(_i915, _err) 0
+#define i915_inject_probe_error(i915, e) ({ BUILD_BUG_ON_INVALID(i915); 0; })
 #define i915_error_injected() false
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 01c822256b39..17d7c525ea5c 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -28,7 +28,9 @@
 #include "display/intel_frontbuffer.h"
 
 #include "gt/intel_engine.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_globals.h"
@@ -112,6 +114,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&vma->ref);
 	mutex_init(&vma->pages_mutex);
 	vma->vm = i915_vm_get(vm);
 	vma->ops = &vm->vma_ops;
@@ -290,6 +293,7 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 struct i915_vma_work {
 	struct dma_fence_work base;
 	struct i915_vma *vma;
+	struct drm_i915_gem_object *pinned;
 	enum i915_cache_level cache_level;
 	unsigned int flags;
 };
@@ -304,15 +308,21 @@ static int __vma_bind(struct dma_fence_work *work)
 	if (err)
 		atomic_or(I915_VMA_ERROR, &vma->flags);
 
-	if (vma->obj)
-		__i915_gem_object_unpin_pages(vma->obj);
-
 	return err;
 }
 
+static void __vma_release(struct dma_fence_work *work)
+{
+	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
+
+	if (vw->pinned)
+		__i915_gem_object_unpin_pages(vw->pinned);
+}
+
 static const struct dma_fence_work_ops bind_ops = {
 	.name = "bind",
 	.work = __vma_bind,
+	.release = __vma_release,
 };
 
 struct i915_vma_work *i915_vma_work(void)
@@ -393,8 +403,10 @@ int i915_vma_bind(struct i915_vma *vma,
 		i915_active_set_exclusive(&vma->active, &work->base.dma);
 		work->base.dma.error = 0; /* enable the queue_work() */
 
-		if (vma->obj)
+		if (vma->obj) {
 			__i915_gem_object_pin_pages(vma->obj);
+			work->pinned = vma->obj;
+		}
 	} else {
 		GEM_BUG_ON((bind_flags & ~vma_flags) & vma->vm->bind_async_flags);
 		ret = vma->ops->bind_vma(vma, cache_level, bind_flags);
@@ -411,8 +423,6 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	void __iomem *ptr;
 	int err;
 
-	/* Access through the GTT requires the device to be awake. */
-	assert_rpm_wakelock_held(vma->vm->gt->uncore->rpm);
 	if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
 		err = -ENODEV;
 		goto err;
@@ -444,6 +454,8 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 		goto err_unpin;
 
 	i915_vma_set_ggtt_write(vma);
+
+	/* NB Access through the GTT requires the device to be awake. */
 	return ptr;
 
 err_unpin:
@@ -846,6 +858,7 @@ static void vma_unbind_pages(struct i915_vma *vma)
 int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 {
 	struct i915_vma_work *work = NULL;
+	intel_wakeref_t wakeref = 0;
 	unsigned int bound;
 	int err;
 
@@ -871,6 +884,9 @@ int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 	}
 
+	if (flags & PIN_GLOBAL)
+		wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm);
+
 	/* No more allocations allowed once we hold vm->mutex */
 	err = mutex_lock_interruptible(&vma->vm->mutex);
 	if (err)
@@ -934,11 +950,45 @@ err_unlock:
 err_fence:
 	if (work)
 		dma_fence_work_commit(&work->base);
+	if (wakeref)
+		intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);
 err_pages:
 	vma_put_pages(vma);
 	return err;
 }
 
+static void flush_idle_contexts(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt, id)
+		intel_engine_flush_barriers(engine);
+
+	intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
+}
+
+int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags)
+{
+	struct i915_address_space *vm = vma->vm;
+	int err;
+
+	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
+
+	do {
+		err = i915_vma_pin(vma, 0, align, flags | PIN_GLOBAL);
+		if (err != -ENOSPC)
+			return err;
+
+		/* Unlike i915_vma_pin, we don't take no for an answer! */
+		flush_idle_contexts(vm->gt);
+		if (mutex_lock_interruptible(&vm->mutex) == 0) {
+			i915_gem_evict_vm(vm);
+			mutex_unlock(&vm->mutex);
+		}
+	} while (1);
+}
+
 void i915_vma_close(struct i915_vma *vma)
 {
 	struct intel_gt *gt = vma->vm->gt;
@@ -978,8 +1028,10 @@ void i915_vma_reopen(struct i915_vma *vma)
 		__i915_vma_remove_closed(vma);
 }
 
-void i915_vma_destroy(struct i915_vma *vma)
+void i915_vma_release(struct kref *ref)
 {
+	struct i915_vma *vma = container_of(ref, typeof(*vma), ref);
+
 	if (drm_mm_node_allocated(&vma->node)) {
 		mutex_lock(&vma->vm->mutex);
 		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
@@ -1019,7 +1071,9 @@ void i915_vma_parked(struct intel_gt *gt)
 		if (!kref_get_unless_zero(&obj->base.refcount))
 			continue;
 
-		if (!i915_vm_tryopen(vm)) {
+		if (i915_vm_tryopen(vm)) {
+			list_del_init(&vma->closed_link);
+		} else {
 			i915_gem_object_put(obj);
 			obj = NULL;
 		}
@@ -1027,7 +1081,7 @@ void i915_vma_parked(struct intel_gt *gt)
 		spin_unlock_irq(&gt->closed_lock);
 
 		if (obj) {
-			i915_vma_destroy(vma);
+			__i915_vma_put(vma);
 			i915_gem_object_put(obj);
 		}
 
@@ -1054,17 +1108,16 @@ static void __i915_vma_iounmap(struct i915_vma *vma)
 
 void i915_vma_revoke_mmap(struct i915_vma *vma)
 {
-	struct drm_vma_offset_node *node = &vma->obj->base.vma_node;
+	struct drm_vma_offset_node *node;
 	u64 vma_offset;
 
-	lockdep_assert_held(&vma->vm->mutex);
-
 	if (!i915_vma_has_userfault(vma))
 		return;
 
 	GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
 	GEM_BUG_ON(!vma->obj->userfault_count);
 
+	node = &vma->mmo->vma_node;
 	vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
 	unmap_mapping_range(vma->vm->i915->drm.anon_inode->i_mapping,
 			    drm_vma_node_offset_addr(node) + vma_offset,
@@ -1152,7 +1205,7 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	GEM_BUG_ON(i915_vma_is_active(vma));
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
-		return -EBUSY;
+		return -EAGAIN;
 	}
 
 	GEM_BUG_ON(i915_vma_is_active(vma));
@@ -1192,15 +1245,23 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	i915_vma_detach(vma);
 	vma_unbind_pages(vma);
 
-	drm_mm_remove_node(&vma->node); /* pairs with i915_vma_destroy() */
+	drm_mm_remove_node(&vma->node); /* pairs with i915_vma_release() */
 	return 0;
 }
 
 int i915_vma_unbind(struct i915_vma *vma)
 {
 	struct i915_address_space *vm = vma->vm;
+	intel_wakeref_t wakeref = 0;
 	int err;
 
+	if (!drm_mm_node_allocated(&vma->node))
+		return 0;
+
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
+		/* XXX not always required: nop_clear_range */
+		wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm);
+
 	err = mutex_lock_interruptible(&vm->mutex);
 	if (err)
 		return err;
@@ -1208,6 +1269,9 @@ int i915_vma_unbind(struct i915_vma *vma)
 	err = __i915_vma_unbind(vma);
 	mutex_unlock(&vm->mutex);
 
+	if (wakeref)
+		intel_runtime_pm_put(&vm->i915->runtime_pm, wakeref);
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 465932813bc5..02b31a62951e 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -30,139 +30,14 @@
 
 #include <drm/drm_mm.h>
 
+#include "gem/i915_gem_object.h"
+
 #include "i915_gem_gtt.h"
 #include "i915_gem_fence_reg.h"
-#include "gem/i915_gem_object.h"
 
 #include "i915_active.h"
 #include "i915_request.h"
-
-enum i915_cache_level;
-
-/**
- * DOC: Virtual Memory Address
- *
- * A VMA represents a GEM BO that is bound into an address space. Therefore, a
- * VMA's presence cannot be guaranteed before binding, or after unbinding the
- * object into/from the address space.
- *
- * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
- * will always be <= an objects lifetime. So object refcounting should cover us.
- */
-struct i915_vma {
-	struct drm_mm_node node;
-	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm;
-	const struct i915_vma_ops *ops;
-	struct i915_fence_reg *fence;
-	struct dma_resv *resv; /** Alias of obj->resv */
-	struct sg_table *pages;
-	void __iomem *iomap;
-	void *private; /* owned by creator */
-	u64 size;
-	u64 display_alignment;
-	struct i915_page_sizes page_sizes;
-
-	u32 fence_size;
-	u32 fence_alignment;
-
-	/**
-	 * Count of the number of times this vma has been opened by different
-	 * handles (but same file) for execbuf, i.e. the number of aliases
-	 * that exist in the ctx->handle_vmas LUT for this vma.
-	 */
-	atomic_t open_count;
-	atomic_t flags;
-	/**
-	 * How many users have pinned this object in GTT space.
-	 *
-	 * This is a tightly bound, fairly small number of users, so we
-	 * stuff inside the flags field so that we can both check for overflow
-	 * and detect a no-op i915_vma_pin() in a single check, while also
-	 * pinning the vma.
-	 *
-	 * The worst case display setup would have the same vma pinned for
-	 * use on each plane on each crtc, while also building the next atomic
-	 * state and holding a pin for the length of the cleanup queue. In the
-	 * future, the flip queue may be increased from 1.
-	 * Estimated worst case: 3 [qlen] * 4 [max crtcs] * 7 [max planes] = 84
-	 *
-	 * For GEM, the number of concurrent users for pwrite/pread is
-	 * unbounded. For execbuffer, it is currently one but will in future
-	 * be extended to allow multiple clients to pin vma concurrently.
-	 *
-	 * We also use suballocated pages, with each suballocation claiming
-	 * its own pin on the shared vma. At present, this is limited to
-	 * exclusive cachelines of a single page, so a maximum of 64 possible
-	 * users.
-	 */
-#define I915_VMA_PIN_MASK 0x3ff
-#define I915_VMA_OVERFLOW 0x200
-
-	/** Flags and address space this VMA is bound to */
-#define I915_VMA_GLOBAL_BIND_BIT 10
-#define I915_VMA_LOCAL_BIND_BIT  11
-
-#define I915_VMA_GLOBAL_BIND	((int)BIT(I915_VMA_GLOBAL_BIND_BIT))
-#define I915_VMA_LOCAL_BIND	((int)BIT(I915_VMA_LOCAL_BIND_BIT))
-
-#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND)
-
-#define I915_VMA_ALLOC_BIT	12
-#define I915_VMA_ALLOC		((int)BIT(I915_VMA_ALLOC_BIT))
-
-#define I915_VMA_ERROR_BIT	13
-#define I915_VMA_ERROR		((int)BIT(I915_VMA_ERROR_BIT))
-
-#define I915_VMA_GGTT_BIT	14
-#define I915_VMA_CAN_FENCE_BIT	15
-#define I915_VMA_USERFAULT_BIT	16
-#define I915_VMA_GGTT_WRITE_BIT	17
-
-#define I915_VMA_GGTT		((int)BIT(I915_VMA_GGTT_BIT))
-#define I915_VMA_CAN_FENCE	((int)BIT(I915_VMA_CAN_FENCE_BIT))
-#define I915_VMA_USERFAULT	((int)BIT(I915_VMA_USERFAULT_BIT))
-#define I915_VMA_GGTT_WRITE	((int)BIT(I915_VMA_GGTT_WRITE_BIT))
-
-	struct i915_active active;
-
-#define I915_VMA_PAGES_BIAS 24
-#define I915_VMA_PAGES_ACTIVE (BIT(24) | 1)
-	atomic_t pages_count; /* number of active binds to the pages */
-	struct mutex pages_mutex; /* protect acquire/release of backing pages */
-
-	/**
-	 * Support different GGTT views into the same object.
-	 * This means there can be multiple VMA mappings per object and per VM.
-	 * i915_ggtt_view_type is used to distinguish between those entries.
-	 * The default one of zero (I915_GGTT_VIEW_NORMAL) is default and also
-	 * assumed in GEM functions which take no ggtt view parameter.
-	 */
-	struct i915_ggtt_view ggtt_view;
-
-	/** This object's place on the active/inactive lists */
-	struct list_head vm_link;
-
-	struct list_head obj_link; /* Link in the object's VMA list */
-	struct rb_node obj_node;
-	struct hlist_node obj_hash;
-
-	/** This vma's place in the execbuf reservation list */
-	struct list_head exec_link;
-	struct list_head reloc_link;
-
-	/** This vma's place in the eviction list */
-	struct list_head evict_link;
-
-	struct list_head closed_link;
-
-	/**
-	 * Used for performing relocations during execbuffer insertion.
-	 */
-	unsigned int *exec_flags;
-	struct hlist_node exec_node;
-	u32 exec_handle;
-};
+#include "i915_vma_types.h"
 
 struct i915_vma *
 i915_vma_instance(struct drm_i915_gem_object *obj,
@@ -333,7 +208,20 @@ int __must_check i915_vma_unbind(struct i915_vma *vma);
 void i915_vma_unlink_ctx(struct i915_vma *vma);
 void i915_vma_close(struct i915_vma *vma);
 void i915_vma_reopen(struct i915_vma *vma);
-void i915_vma_destroy(struct i915_vma *vma);
+
+static inline struct i915_vma *__i915_vma_get(struct i915_vma *vma)
+{
+	if (kref_get_unless_zero(&vma->ref))
+		return vma;
+
+	return NULL;
+}
+
+void i915_vma_release(struct kref *ref);
+static inline void __i915_vma_put(struct i915_vma *vma)
+{
+	kref_put(&vma->ref, i915_vma_release);
+}
 
 #define assert_vma_held(vma) dma_resv_assert_held((vma)->resv)
 
@@ -349,6 +237,7 @@ static inline void i915_vma_unlock(struct i915_vma *vma)
 
 int __must_check
 i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags);
+int i915_ggtt_pin(struct i915_vma *vma, u32 align, unsigned int flags);
 
 static inline int i915_vma_pin_count(const struct i915_vma *vma)
 {
diff --git a/drivers/gpu/drm/i915/i915_vma_types.h b/drivers/gpu/drm/i915/i915_vma_types.h
new file mode 100644
index 000000000000..e0942efd5236
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_vma_types.h
@@ -0,0 +1,294 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __I915_VMA_TYPES_H__
+#define __I915_VMA_TYPES_H__
+
+#include <linux/rbtree.h>
+
+#include <drm/drm_mm.h>
+
+#include "gem/i915_gem_object_types.h"
+
+enum i915_cache_level;
+
+/**
+ * DOC: Global GTT views
+ *
+ * Background and previous state
+ *
+ * Historically objects could exists (be bound) in global GTT space only as
+ * singular instances with a view representing all of the object's backing pages
+ * in a linear fashion. This view will be called a normal view.
+ *
+ * To support multiple views of the same object, where the number of mapped
+ * pages is not equal to the backing store, or where the layout of the pages
+ * is not linear, concept of a GGTT view was added.
+ *
+ * One example of an alternative view is a stereo display driven by a single
+ * image. In this case we would have a framebuffer looking like this
+ * (2x2 pages):
+ *
+ *    12
+ *    34
+ *
+ * Above would represent a normal GGTT view as normally mapped for GPU or CPU
+ * rendering. In contrast, fed to the display engine would be an alternative
+ * view which could look something like this:
+ *
+ *   1212
+ *   3434
+ *
+ * In this example both the size and layout of pages in the alternative view is
+ * different from the normal view.
+ *
+ * Implementation and usage
+ *
+ * GGTT views are implemented using VMAs and are distinguished via enum
+ * i915_ggtt_view_type and struct i915_ggtt_view.
+ *
+ * A new flavour of core GEM functions which work with GGTT bound objects were
+ * added with the _ggtt_ infix, and sometimes with _view postfix to avoid
+ * renaming  in large amounts of code. They take the struct i915_ggtt_view
+ * parameter encapsulating all metadata required to implement a view.
+ *
+ * As a helper for callers which are only interested in the normal view,
+ * globally const i915_ggtt_view_normal singleton instance exists. All old core
+ * GEM API functions, the ones not taking the view parameter, are operating on,
+ * or with the normal GGTT view.
+ *
+ * Code wanting to add or use a new GGTT view needs to:
+ *
+ * 1. Add a new enum with a suitable name.
+ * 2. Extend the metadata in the i915_ggtt_view structure if required.
+ * 3. Add support to i915_get_vma_pages().
+ *
+ * New views are required to build a scatter-gather table from within the
+ * i915_get_vma_pages function. This table is stored in the vma.ggtt_view and
+ * exists for the lifetime of an VMA.
+ *
+ * Core API is designed to have copy semantics which means that passed in
+ * struct i915_ggtt_view does not need to be persistent (left around after
+ * calling the core API functions).
+ *
+ */
+
+struct intel_remapped_plane_info {
+	/* in gtt pages */
+	unsigned int width, height, stride, offset;
+} __packed;
+
+struct intel_remapped_info {
+	struct intel_remapped_plane_info plane[2];
+	unsigned int unused_mbz;
+} __packed;
+
+struct intel_rotation_info {
+	struct intel_remapped_plane_info plane[2];
+} __packed;
+
+struct intel_partial_info {
+	u64 offset;
+	unsigned int size;
+} __packed;
+
+enum i915_ggtt_view_type {
+	I915_GGTT_VIEW_NORMAL = 0,
+	I915_GGTT_VIEW_ROTATED = sizeof(struct intel_rotation_info),
+	I915_GGTT_VIEW_PARTIAL = sizeof(struct intel_partial_info),
+	I915_GGTT_VIEW_REMAPPED = sizeof(struct intel_remapped_info),
+};
+
+static inline void assert_i915_gem_gtt_types(void)
+{
+	BUILD_BUG_ON(sizeof(struct intel_rotation_info) != 8*sizeof(unsigned int));
+	BUILD_BUG_ON(sizeof(struct intel_partial_info) != sizeof(u64) + sizeof(unsigned int));
+	BUILD_BUG_ON(sizeof(struct intel_remapped_info) != 9*sizeof(unsigned int));
+
+	/* Check that rotation/remapped shares offsets for simplicity */
+	BUILD_BUG_ON(offsetof(struct intel_remapped_info, plane[0]) !=
+		     offsetof(struct intel_rotation_info, plane[0]));
+	BUILD_BUG_ON(offsetofend(struct intel_remapped_info, plane[1]) !=
+		     offsetofend(struct intel_rotation_info, plane[1]));
+
+	/* As we encode the size of each branch inside the union into its type,
+	 * we have to be careful that each branch has a unique size.
+	 */
+	switch ((enum i915_ggtt_view_type)0) {
+	case I915_GGTT_VIEW_NORMAL:
+	case I915_GGTT_VIEW_PARTIAL:
+	case I915_GGTT_VIEW_ROTATED:
+	case I915_GGTT_VIEW_REMAPPED:
+		/* gcc complains if these are identical cases */
+		break;
+	}
+}
+
+struct i915_ggtt_view {
+	enum i915_ggtt_view_type type;
+	union {
+		/* Members need to contain no holes/padding */
+		struct intel_partial_info partial;
+		struct intel_rotation_info rotated;
+		struct intel_remapped_info remapped;
+	};
+};
+
+/**
+ * DOC: Virtual Memory Address
+ *
+ * A VMA represents a GEM BO that is bound into an address space. Therefore, a
+ * VMA's presence cannot be guaranteed before binding, or after unbinding the
+ * object into/from the address space.
+ *
+ * To make things as simple as possible (ie. no refcounting), a VMA's lifetime
+ * will always be <= an objects lifetime. So object refcounting should cover us.
+ */
+struct i915_vma {
+	struct drm_mm_node node;
+
+	struct i915_address_space *vm;
+	const struct i915_vma_ops *ops;
+
+	struct drm_i915_gem_object *obj;
+	struct dma_resv *resv; /** Alias of obj->resv */
+
+	struct sg_table *pages;
+	void __iomem *iomap;
+	void *private; /* owned by creator */
+
+	struct i915_fence_reg *fence;
+
+	u64 size;
+	u64 display_alignment;
+	struct i915_page_sizes page_sizes;
+
+	/* mmap-offset associated with fencing for this vma */
+	struct i915_mmap_offset	*mmo;
+
+	u32 fence_size;
+	u32 fence_alignment;
+
+	/**
+	 * Count of the number of times this vma has been opened by different
+	 * handles (but same file) for execbuf, i.e. the number of aliases
+	 * that exist in the ctx->handle_vmas LUT for this vma.
+	 */
+	struct kref ref;
+	atomic_t open_count;
+	atomic_t flags;
+	/**
+	 * How many users have pinned this object in GTT space.
+	 *
+	 * This is a tightly bound, fairly small number of users, so we
+	 * stuff inside the flags field so that we can both check for overflow
+	 * and detect a no-op i915_vma_pin() in a single check, while also
+	 * pinning the vma.
+	 *
+	 * The worst case display setup would have the same vma pinned for
+	 * use on each plane on each crtc, while also building the next atomic
+	 * state and holding a pin for the length of the cleanup queue. In the
+	 * future, the flip queue may be increased from 1.
+	 * Estimated worst case: 3 [qlen] * 4 [max crtcs] * 7 [max planes] = 84
+	 *
+	 * For GEM, the number of concurrent users for pwrite/pread is
+	 * unbounded. For execbuffer, it is currently one but will in future
+	 * be extended to allow multiple clients to pin vma concurrently.
+	 *
+	 * We also use suballocated pages, with each suballocation claiming
+	 * its own pin on the shared vma. At present, this is limited to
+	 * exclusive cachelines of a single page, so a maximum of 64 possible
+	 * users.
+	 */
+#define I915_VMA_PIN_MASK 0x3ff
+#define I915_VMA_OVERFLOW 0x200
+
+	/** Flags and address space this VMA is bound to */
+#define I915_VMA_GLOBAL_BIND_BIT 10
+#define I915_VMA_LOCAL_BIND_BIT  11
+
+#define I915_VMA_GLOBAL_BIND	((int)BIT(I915_VMA_GLOBAL_BIND_BIT))
+#define I915_VMA_LOCAL_BIND	((int)BIT(I915_VMA_LOCAL_BIND_BIT))
+
+#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND)
+
+#define I915_VMA_ALLOC_BIT	12
+#define I915_VMA_ALLOC		((int)BIT(I915_VMA_ALLOC_BIT))
+
+#define I915_VMA_ERROR_BIT	13
+#define I915_VMA_ERROR		((int)BIT(I915_VMA_ERROR_BIT))
+
+#define I915_VMA_GGTT_BIT	14
+#define I915_VMA_CAN_FENCE_BIT	15
+#define I915_VMA_USERFAULT_BIT	16
+#define I915_VMA_GGTT_WRITE_BIT	17
+
+#define I915_VMA_GGTT		((int)BIT(I915_VMA_GGTT_BIT))
+#define I915_VMA_CAN_FENCE	((int)BIT(I915_VMA_CAN_FENCE_BIT))
+#define I915_VMA_USERFAULT	((int)BIT(I915_VMA_USERFAULT_BIT))
+#define I915_VMA_GGTT_WRITE	((int)BIT(I915_VMA_GGTT_WRITE_BIT))
+
+	struct i915_active active;
+
+#define I915_VMA_PAGES_BIAS 24
+#define I915_VMA_PAGES_ACTIVE (BIT(24) | 1)
+	atomic_t pages_count; /* number of active binds to the pages */
+	struct mutex pages_mutex; /* protect acquire/release of backing pages */
+
+	/**
+	 * Support different GGTT views into the same object.
+	 * This means there can be multiple VMA mappings per object and per VM.
+	 * i915_ggtt_view_type is used to distinguish between those entries.
+	 * The default one of zero (I915_GGTT_VIEW_NORMAL) is default and also
+	 * assumed in GEM functions which take no ggtt view parameter.
+	 */
+	struct i915_ggtt_view ggtt_view;
+
+	/** This object's place on the active/inactive lists */
+	struct list_head vm_link;
+
+	struct list_head obj_link; /* Link in the object's VMA list */
+	struct rb_node obj_node;
+	struct hlist_node obj_hash;
+
+	/** This vma's place in the execbuf reservation list */
+	struct list_head exec_link;
+	struct list_head reloc_link;
+
+	/** This vma's place in the eviction list */
+	struct list_head evict_link;
+
+	struct list_head closed_link;
+
+	/**
+	 * Used for performing relocations during execbuffer insertion.
+	 */
+	unsigned int *exec_flags;
+	struct hlist_node exec_node;
+	u32 exec_handle;
+};
+
+#endif
+
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index a5b571364cf6..6670a0763be2 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -73,9 +73,30 @@ const char *intel_platform_name(enum intel_platform platform)
 	return platform_names[platform];
 }
 
-void intel_device_info_dump_flags(const struct intel_device_info *info,
-				  struct drm_printer *p)
+static const char *iommu_name(void)
 {
+	const char *msg = "n/a";
+
+#ifdef CONFIG_INTEL_IOMMU
+	msg = enableddisabled(intel_iommu_gfx_mapped);
+#endif
+
+	return msg;
+}
+
+void intel_device_info_print_static(const struct intel_device_info *info,
+				    struct drm_printer *p)
+{
+	drm_printf(p, "engines: %x\n", info->engine_mask);
+	drm_printf(p, "gen: %d\n", info->gen);
+	drm_printf(p, "gt: %d\n", info->gt);
+	drm_printf(p, "iommu: %s\n", iommu_name());
+	drm_printf(p, "memory-regions: %x\n", info->memory_regions);
+	drm_printf(p, "page-sizes: %x\n", info->page_sizes);
+	drm_printf(p, "platform: %s\n", intel_platform_name(info->platform));
+	drm_printf(p, "ppgtt-size: %d\n", info->ppgtt_size);
+	drm_printf(p, "ppgtt-type: %d\n", info->ppgtt_type);
+
 #define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, yesno(info->name));
 	DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG);
 #undef PRINT_FLAG
@@ -106,8 +127,8 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 	drm_printf(p, "has EU power gating: %s\n", yesno(sseu->has_eu_pg));
 }
 
-void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
-				    struct drm_printer *p)
+void intel_device_info_print_runtime(const struct intel_runtime_info *info,
+				     struct drm_printer *p)
 {
 	sseu_dump(&info->sseu, p);
 
@@ -148,8 +169,8 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
 	}
 }
 
-void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
-				     struct drm_printer *p)
+void intel_device_info_print_topology(const struct sseu_dev_info *sseu,
+				      struct drm_printer *p)
 {
 	int s, ss;
 
@@ -498,7 +519,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	}
 }
 
-static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
+static void bdw_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	int s, ss;
@@ -579,7 +600,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->has_eu_pg = 0;
 }
 
-static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
+static void hsw_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse1;
@@ -808,6 +829,8 @@ static const u16 subplatform_ult_ids[] = {
 	INTEL_WHL_U_GT1_IDS(0),
 	INTEL_WHL_U_GT2_IDS(0),
 	INTEL_WHL_U_GT3_IDS(0),
+	INTEL_CML_U_GT1_IDS(0),
+	INTEL_CML_U_GT2_IDS(0),
 };
 
 static const u16 subplatform_ulx_ids[] = {
@@ -998,11 +1021,11 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 
 	/* Initialize slice/subslice/EU info */
 	if (IS_HASWELL(dev_priv))
-		haswell_sseu_info_init(dev_priv);
+		hsw_sseu_info_init(dev_priv);
 	else if (IS_CHERRYVIEW(dev_priv))
 		cherryview_sseu_info_init(dev_priv);
 	else if (IS_BROADWELL(dev_priv))
-		broadwell_sseu_info_init(dev_priv);
+		bdw_sseu_info_init(dev_priv);
 	else if (IS_GEN(dev_priv, 9))
 		gen9_sseu_info_init(dev_priv);
 	else if (IS_GEN(dev_priv, 10))
@@ -1070,7 +1093,7 @@ void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
 		 * hooked up to an SFC (Scaler & Format Converter) unit.
 		 * In TGL each VDBOX has access to an SFC.
 		 */
-		if (IS_TIGERLAKE(dev_priv) || logical_vdbox++ % 2 == 0)
+		if (INTEL_GEN(dev_priv) >= 12 || logical_vdbox++ % 2 == 0)
 			RUNTIME_INFO(dev_priv)->vdbox_sfc_access |= BIT(i);
 	}
 	DRM_DEBUG_DRIVER("vdbox enable: %04x, instances: %04lx\n",
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 4bdf8a6cfb47..2725cb7fc169 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -230,12 +230,13 @@ const char *intel_platform_name(enum intel_platform platform);
 
 void intel_device_info_subplatform_init(struct drm_i915_private *dev_priv);
 void intel_device_info_runtime_init(struct drm_i915_private *dev_priv);
-void intel_device_info_dump_flags(const struct intel_device_info *info,
-				  struct drm_printer *p);
-void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
+
+void intel_device_info_print_static(const struct intel_device_info *info,
 				    struct drm_printer *p);
-void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
+void intel_device_info_print_runtime(const struct intel_runtime_info *info,
 				     struct drm_printer *p);
+void intel_device_info_print_topology(const struct sseu_dev_info *sseu,
+				      struct drm_printer *p);
 
 void intel_device_info_init_mmio(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index baaeaecc64af..d0d038b3cd79 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -16,6 +16,20 @@ const u32 intel_region_map[] = {
 	[INTEL_REGION_STOLEN] = REGION_MAP(INTEL_MEMORY_STOLEN, 0),
 };
 
+struct intel_memory_region *
+intel_memory_region_by_type(struct drm_i915_private *i915,
+			    enum intel_memory_type mem_type)
+{
+	struct intel_memory_region *mr;
+	int id;
+
+	for_each_memory_region(mr, i915, id)
+		if (mr->type == mem_type)
+			return mr;
+
+	return NULL;
+}
+
 static u64
 intel_memory_region_free_pages(struct intel_memory_region *mem,
 			       struct list_head *blocks)
@@ -37,7 +51,7 @@ __intel_memory_region_put_pages_buddy(struct intel_memory_region *mem,
 				      struct list_head *blocks)
 {
 	mutex_lock(&mem->mm_lock);
-	intel_memory_region_free_pages(mem, blocks);
+	mem->avail += intel_memory_region_free_pages(mem, blocks);
 	mutex_unlock(&mem->mm_lock);
 }
 
@@ -73,6 +87,9 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
 		min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
 	}
 
+	if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+		return -E2BIG;
+
 	n_pages = size >> ilog2(mem->mm.chunk_size);
 
 	mutex_lock(&mem->mm_lock);
@@ -103,6 +120,7 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
 			break;
 	} while (1);
 
+	mem->avail -= size;
 	mutex_unlock(&mem->mm_lock);
 	return 0;
 
@@ -161,6 +179,8 @@ intel_memory_region_create(struct drm_i915_private *i915,
 	mem->io_start = io_start;
 	mem->min_page_size = min_page_size;
 	mem->ops = ops;
+	mem->total = size;
+	mem->avail = mem->total;
 
 	mutex_init(&mem->objects.lock);
 	INIT_LIST_HEAD(&mem->objects.list);
@@ -182,6 +202,16 @@ err_free:
 	return ERR_PTR(err);
 }
 
+void intel_memory_region_set_name(struct intel_memory_region *mem,
+				  const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vsnprintf(mem->name, sizeof(mem->name), fmt, ap);
+	va_end(ap);
+}
+
 static void __intel_memory_region_destroy(struct kref *kref)
 {
 	struct intel_memory_region *mem =
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 238722009677..232490d89a83 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -47,6 +47,10 @@ enum intel_region_id {
 #define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
 #define I915_ALLOC_CONTIGUOUS     BIT(1)
 
+#define for_each_memory_region(mr, i915, id) \
+	for (id = 0; id < ARRAY_SIZE((i915)->mm.regions); id++) \
+		for_each_if((mr) = (i915)->mm.regions[id])
+
 /**
  * Memory regions encoded as type | instance
  */
@@ -82,10 +86,13 @@ struct intel_memory_region {
 
 	resource_size_t io_start;
 	resource_size_t min_page_size;
+	resource_size_t total;
+	resource_size_t avail;
 
 	unsigned int type;
 	unsigned int instance;
 	unsigned int id;
+	char name[8];
 
 	dma_addr_t remap_addr;
 
@@ -125,5 +132,12 @@ void intel_memory_region_put(struct intel_memory_region *mem);
 
 int intel_memory_regions_hw_probe(struct drm_i915_private *i915);
 void intel_memory_regions_driver_release(struct drm_i915_private *i915);
+struct intel_memory_region *
+intel_memory_region_by_type(struct drm_i915_private *i915,
+			    enum intel_memory_type mem_type);
+
+__printf(2, 3) void
+intel_memory_region_set_name(struct intel_memory_region *mem,
+			     const char *fmt, ...);
 
 #endif
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index 8fd92b9130a7..4ed60e1f01db 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -12,89 +12,91 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 {
 	switch (id) {
 	case INTEL_PCH_IBX_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Ibex Peak PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Ibex Peak PCH\n");
 		WARN_ON(!IS_GEN(dev_priv, 5));
 		return PCH_IBX;
 	case INTEL_PCH_CPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found CougarPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found CougarPoint PCH\n");
 		WARN_ON(!IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv));
 		return PCH_CPT;
 	case INTEL_PCH_PPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found PantherPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found PantherPoint PCH\n");
 		WARN_ON(!IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv));
 		/* PantherPoint is CPT compatible */
 		return PCH_CPT;
 	case INTEL_PCH_LPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found LynxPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found LynxPoint PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(IS_HSW_ULT(dev_priv) || IS_BDW_ULT(dev_priv));
 		return PCH_LPT;
 	case INTEL_PCH_LPT_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found LynxPoint LP PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found LynxPoint LP PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(!IS_HSW_ULT(dev_priv) && !IS_BDW_ULT(dev_priv));
 		return PCH_LPT;
 	case INTEL_PCH_WPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found WildcatPoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found WildcatPoint PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(IS_HSW_ULT(dev_priv) || IS_BDW_ULT(dev_priv));
 		/* WildcatPoint is LPT compatible */
 		return PCH_LPT;
 	case INTEL_PCH_WPT_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found WildcatPoint LP PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found WildcatPoint LP PCH\n");
 		WARN_ON(!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv));
 		WARN_ON(!IS_HSW_ULT(dev_priv) && !IS_BDW_ULT(dev_priv));
 		/* WildcatPoint is LPT compatible */
 		return PCH_LPT;
 	case INTEL_PCH_SPT_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found SunrisePoint PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found SunrisePoint PCH\n");
 		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv));
 		return PCH_SPT;
 	case INTEL_PCH_SPT_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found SunrisePoint LP PCH\n");
 		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv) &&
 			!IS_COFFEELAKE(dev_priv));
 		return PCH_SPT;
 	case INTEL_PCH_KBP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Kaby Lake PCH (KBP)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Kaby Lake PCH (KBP)\n");
 		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv) &&
 			!IS_COFFEELAKE(dev_priv));
 		/* KBP is SPT compatible */
 		return PCH_SPT;
 	case INTEL_PCH_CNP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Cannon Lake PCH (CNP)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Cannon Lake PCH (CNP)\n");
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CNP_LP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Cannon Lake LP PCH (CNP-LP)\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Found Cannon Lake LP PCH (CNP-LP)\n");
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
 	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
 		return PCH_CNP;
 	case INTEL_PCH_CMP_V_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Comet Lake V PCH (CMP-V)\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Comet Lake V PCH (CMP-V)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* Comet Lake V PCH is based on KBP, which is SPT compatible */
 		return PCH_SPT;
 	case INTEL_PCH_ICP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Ice Lake PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Ice Lake PCH\n");
 		WARN_ON(!IS_ICELAKE(dev_priv));
 		return PCH_ICP;
 	case INTEL_PCH_MCC_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Mule Creek Canyon PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Mule Creek Canyon PCH\n");
 		WARN_ON(!IS_ELKHARTLAKE(dev_priv));
 		return PCH_MCC;
 	case INTEL_PCH_TGP_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Tiger Lake LP PCH\n");
+	case INTEL_PCH_TGP2_DEVICE_ID_TYPE:
+		drm_dbg_kms(&dev_priv->drm, "Found Tiger Lake LP PCH\n");
 		WARN_ON(!IS_TIGERLAKE(dev_priv));
 		return PCH_TGP;
 	case INTEL_PCH_JSP_DEVICE_ID_TYPE:
 	case INTEL_PCH_JSP2_DEVICE_ID_TYPE:
-		DRM_DEBUG_KMS("Found Jasper Lake PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Found Jasper Lake PCH\n");
 		WARN_ON(!IS_ELKHARTLAKE(dev_priv));
 		return PCH_JSP;
 	default:
@@ -144,9 +146,9 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv)
 		id = INTEL_PCH_IBX_DEVICE_ID_TYPE;
 
 	if (id)
-		DRM_DEBUG_KMS("Assuming PCH ID %04x\n", id);
+		drm_dbg_kms(&dev_priv->drm, "Assuming PCH ID %04x\n", id);
 	else
-		DRM_DEBUG_KMS("Assuming no PCH\n");
+		drm_dbg_kms(&dev_priv->drm, "Assuming no PCH\n");
 
 	return id;
 }
@@ -200,13 +202,14 @@ void intel_detect_pch(struct drm_i915_private *dev_priv)
 	 * display.
 	 */
 	if (pch && !HAS_DISPLAY(dev_priv)) {
-		DRM_DEBUG_KMS("Display disabled, reverting to NOP PCH\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Display disabled, reverting to NOP PCH\n");
 		dev_priv->pch_type = PCH_NOP;
 		dev_priv->pch_id = 0;
 	}
 
 	if (!pch)
-		DRM_DEBUG_KMS("No PCH found.\n");
+		drm_dbg_kms(&dev_priv->drm, "No PCH found.\n");
 
 	pci_dev_put(pch);
 }
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index d26c25dd8d54..3053d1ce398b 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -47,6 +47,7 @@ enum intel_pch {
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_TGP_DEVICE_ID_TYPE		0xA080
+#define INTEL_PCH_TGP2_DEVICE_ID_TYPE		0x4380
 #define INTEL_PCH_JSP_DEVICE_ID_TYPE		0x4D80
 #define INTEL_PCH_JSP2_DEVICE_ID_TYPE		0x3880
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 86379eddc908..bd2d30ecc030 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -140,7 +140,7 @@ static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
 
 }
 
-static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
+static void pnv_get_mem_freq(struct drm_i915_private *dev_priv)
 {
 	u32 tmp;
 
@@ -178,7 +178,7 @@ static void i915_pineview_get_mem_freq(struct drm_i915_private *dev_priv)
 	dev_priv->is_ddr3 = (tmp & CSHRDDR3CTL_DDR3) ? 1 : 0;
 }
 
-static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
+static void ilk_get_mem_freq(struct drm_i915_private *dev_priv)
 {
 	u16 ddrpll, csipll;
 
@@ -199,8 +199,8 @@ static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
 		dev_priv->mem_freq = 1600;
 		break;
 	default:
-		DRM_DEBUG_DRIVER("unknown memory frequency 0x%02x\n",
-				 ddrpll & 0xff);
+		drm_dbg(&dev_priv->drm, "unknown memory frequency 0x%02x\n",
+			ddrpll & 0xff);
 		dev_priv->mem_freq = 0;
 		break;
 	}
@@ -228,8 +228,8 @@ static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
 		dev_priv->fsb_freq = 6400;
 		break;
 	default:
-		DRM_DEBUG_DRIVER("unknown fsb frequency 0x%04x\n",
-				 csipll & 0x3ff);
+		drm_dbg(&dev_priv->drm, "unknown fsb frequency 0x%04x\n",
+			csipll & 0x3ff);
 		dev_priv->fsb_freq = 0;
 		break;
 	}
@@ -314,7 +314,8 @@ static void chv_set_memory_dvfs(struct drm_i915_private *dev_priv, bool enable)
 
 	if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
 		      FORCE_DDR_FREQ_REQ_ACK) == 0, 3))
-		DRM_ERROR("timed out waiting for Punit DDR DVFS request\n");
+		drm_err(&dev_priv->drm,
+			"timed out waiting for Punit DDR DVFS request\n");
 
 	vlv_punit_put(dev_priv);
 }
@@ -383,9 +384,9 @@ static bool _intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enabl
 
 	trace_intel_memory_cxsr(dev_priv, was_enabled, enable);
 
-	DRM_DEBUG_KMS("memory self-refresh is %s (was %s)\n",
-		      enableddisabled(enable),
-		      enableddisabled(was_enabled));
+	drm_dbg_kms(&dev_priv->drm, "memory self-refresh is %s (was %s)\n",
+		    enableddisabled(enable),
+		    enableddisabled(was_enabled));
 
 	return was_enabled;
 }
@@ -463,7 +464,7 @@ static const int pessimal_latency_ns = 5000;
 
 static void vlv_get_fifo_size(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
 	enum pipe pipe = crtc->pipe;
@@ -510,8 +511,8 @@ static int i9xx_get_fifo_size(struct drm_i915_private *dev_priv,
 	if (i9xx_plane == PLANE_B)
 		size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - size;
 
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
-		      dsparb, plane_name(i9xx_plane), size);
+	drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+		    dsparb, plane_name(i9xx_plane), size);
 
 	return size;
 }
@@ -527,8 +528,8 @@ static int i830_get_fifo_size(struct drm_i915_private *dev_priv,
 		size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - size;
 	size >>= 1; /* Convert to cachelines */
 
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
-		      dsparb, plane_name(i9xx_plane), size);
+	drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+		    dsparb, plane_name(i9xx_plane), size);
 
 	return size;
 }
@@ -542,41 +543,45 @@ static int i845_get_fifo_size(struct drm_i915_private *dev_priv,
 	size = dsparb & 0x7f;
 	size >>= 2; /* Convert to cachelines */
 
-	DRM_DEBUG_KMS("FIFO size - (0x%08x) %c: %d\n",
-		      dsparb, plane_name(i9xx_plane), size);
+	drm_dbg_kms(&dev_priv->drm, "FIFO size - (0x%08x) %c: %d\n",
+		    dsparb, plane_name(i9xx_plane), size);
 
 	return size;
 }
 
 /* Pineview has different values for various configs */
-static const struct intel_watermark_params pineview_display_wm = {
+static const struct intel_watermark_params pnv_display_wm = {
 	.fifo_size = PINEVIEW_DISPLAY_FIFO,
 	.max_wm = PINEVIEW_MAX_WM,
 	.default_wm = PINEVIEW_DFT_WM,
 	.guard_size = PINEVIEW_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params pineview_display_hplloff_wm = {
+
+static const struct intel_watermark_params pnv_display_hplloff_wm = {
 	.fifo_size = PINEVIEW_DISPLAY_FIFO,
 	.max_wm = PINEVIEW_MAX_WM,
 	.default_wm = PINEVIEW_DFT_HPLLOFF_WM,
 	.guard_size = PINEVIEW_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params pineview_cursor_wm = {
+
+static const struct intel_watermark_params pnv_cursor_wm = {
 	.fifo_size = PINEVIEW_CURSOR_FIFO,
 	.max_wm = PINEVIEW_CURSOR_MAX_WM,
 	.default_wm = PINEVIEW_CURSOR_DFT_WM,
 	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
-static const struct intel_watermark_params pineview_cursor_hplloff_wm = {
+
+static const struct intel_watermark_params pnv_cursor_hplloff_wm = {
 	.fifo_size = PINEVIEW_CURSOR_FIFO,
 	.max_wm = PINEVIEW_CURSOR_MAX_WM,
 	.default_wm = PINEVIEW_CURSOR_DFT_WM,
 	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
 	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i965_cursor_wm_info = {
 	.fifo_size = I965_CURSOR_FIFO,
 	.max_wm = I965_CURSOR_MAX_WM,
@@ -584,6 +589,7 @@ static const struct intel_watermark_params i965_cursor_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i945_wm_info = {
 	.fifo_size = I945_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -591,6 +597,7 @@ static const struct intel_watermark_params i945_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i915_wm_info = {
 	.fifo_size = I915_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -598,6 +605,7 @@ static const struct intel_watermark_params i915_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i830_a_wm_info = {
 	.fifo_size = I855GM_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -605,6 +613,7 @@ static const struct intel_watermark_params i830_a_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i830_bc_wm_info = {
 	.fifo_size = I855GM_FIFO_SIZE,
 	.max_wm = I915_MAX_WM/2,
@@ -612,6 +621,7 @@ static const struct intel_watermark_params i830_bc_wm_info = {
 	.guard_size = 2,
 	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
+
 static const struct intel_watermark_params i845_wm_info = {
 	.fifo_size = I830_FIFO_SIZE,
 	.max_wm = I915_MAX_WM,
@@ -794,10 +804,10 @@ static int intel_wm_num_levels(struct drm_i915_private *dev_priv)
 static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state,
 				   const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 
 	/* FIXME check the 'enable' instead */
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return false;
 
 	/*
@@ -809,9 +819,28 @@ static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state,
 	 * around this problem with the watermark code.
 	 */
 	if (plane->id == PLANE_CURSOR)
-		return plane_state->base.fb != NULL;
+		return plane_state->hw.fb != NULL;
 	else
-		return plane_state->base.visible;
+		return plane_state->uapi.visible;
+}
+
+static bool intel_crtc_active(struct intel_crtc *crtc)
+{
+	/* Be paranoid as we can arrive here with only partial
+	 * state retrieved from the hardware during setup.
+	 *
+	 * We can ditch the adjusted_mode.crtc_clock check as soon
+	 * as Haswell has gained clock readout/fastboot support.
+	 *
+	 * We can ditch the crtc->primary->state->fb check as soon as we can
+	 * properly reconstruct framebuffers.
+	 *
+	 * FIXME: The intel_crtc->active here should be switched to
+	 * crtc->state->active once we have proper CRTC states wired up
+	 * for atomic.
+	 */
+	return crtc->active && crtc->base.primary->state->fb &&
+		crtc->config->hw.adjusted_mode.crtc_clock;
 }
 
 static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv)
@@ -829,7 +858,7 @@ static struct intel_crtc *single_enabled_crtc(struct drm_i915_private *dev_priv)
 	return enabled;
 }
 
-static void pineview_update_wm(struct intel_crtc *unused_crtc)
+static void pnv_update_wm(struct intel_crtc *unused_crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(unused_crtc->base.dev);
 	struct intel_crtc *crtc;
@@ -842,7 +871,8 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 					 dev_priv->fsb_freq,
 					 dev_priv->mem_freq);
 	if (!latency) {
-		DRM_DEBUG_KMS("Unknown FSB/MEM found, disable CxSR\n");
+		drm_dbg_kms(&dev_priv->drm,
+			    "Unknown FSB/MEM found, disable CxSR\n");
 		intel_set_memory_cxsr(dev_priv, false);
 		return;
 	}
@@ -850,25 +880,25 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 	crtc = single_enabled_crtc(dev_priv);
 	if (crtc) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp = fb->format->cpp[0];
 		int clock = adjusted_mode->crtc_clock;
 
 		/* Display SR */
-		wm = intel_calculate_wm(clock, &pineview_display_wm,
-					pineview_display_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_display_wm,
+					pnv_display_wm.fifo_size,
 					cpp, latency->display_sr);
 		reg = I915_READ(DSPFW1);
 		reg &= ~DSPFW_SR_MASK;
 		reg |= FW_WM(wm, SR);
 		I915_WRITE(DSPFW1, reg);
-		DRM_DEBUG_KMS("DSPFW1 register is %x\n", reg);
+		drm_dbg_kms(&dev_priv->drm, "DSPFW1 register is %x\n", reg);
 
 		/* cursor SR */
-		wm = intel_calculate_wm(clock, &pineview_cursor_wm,
-					pineview_display_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_cursor_wm,
+					pnv_display_wm.fifo_size,
 					4, latency->cursor_sr);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_CURSOR_SR_MASK;
@@ -876,8 +906,8 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 		I915_WRITE(DSPFW3, reg);
 
 		/* Display HPLL off SR */
-		wm = intel_calculate_wm(clock, &pineview_display_hplloff_wm,
-					pineview_display_hplloff_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_display_hplloff_wm,
+					pnv_display_hplloff_wm.fifo_size,
 					cpp, latency->display_hpll_disable);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_HPLL_SR_MASK;
@@ -885,14 +915,14 @@ static void pineview_update_wm(struct intel_crtc *unused_crtc)
 		I915_WRITE(DSPFW3, reg);
 
 		/* cursor HPLL off SR */
-		wm = intel_calculate_wm(clock, &pineview_cursor_hplloff_wm,
-					pineview_display_hplloff_wm.fifo_size,
+		wm = intel_calculate_wm(clock, &pnv_cursor_hplloff_wm,
+					pnv_display_hplloff_wm.fifo_size,
 					4, latency->cursor_hpll_disable);
 		reg = I915_READ(DSPFW3);
 		reg &= ~DSPFW_HPLL_CURSOR_MASK;
 		reg |= FW_WM(wm, HPLL_CURSOR);
 		I915_WRITE(DSPFW3, reg);
-		DRM_DEBUG_KMS("DSPFW3 register is %x\n", reg);
+		drm_dbg_kms(&dev_priv->drm, "DSPFW3 register is %x\n", reg);
 
 		intel_set_memory_cxsr(dev_priv, true);
 	} else {
@@ -1083,10 +1113,10 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state,
 			  int level)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	unsigned int latency = dev_priv->wm.pri_latency[level] * 10;
 	unsigned int clock, htotal, cpp, width, wm;
 
@@ -1096,7 +1126,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	/*
 	 * Not 100% sure which way ELK should go here as the
@@ -1116,7 +1146,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 
-	width = drm_rect_width(&plane_state->base.dst);
+	width = drm_rect_width(&plane_state->uapi.dst);
 
 	if (plane->id == PLANE_CURSOR) {
 		wm = intel_wm_method2(clock, htotal, width, cpp, latency);
@@ -1143,7 +1173,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 				 int level, enum plane_id plane_id, u16 value)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	bool dirty = false;
 
 	for (; level < intel_wm_num_levels(dev_priv); level++) {
@@ -1159,7 +1189,7 @@ static bool g4x_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 static bool g4x_raw_fbc_wm_set(struct intel_crtc_state *crtc_state,
 			       int level, u16 value)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	bool dirty = false;
 
 	/* NORMAL level doesn't have an FBC watermark */
@@ -1182,7 +1212,8 @@ static u32 ilk_compute_fbc_wm(const struct intel_crtc_state *crtc_state,
 static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 				     const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
 	enum plane_id plane_id = plane->id;
 	bool dirty = false;
@@ -1235,16 +1266,18 @@ static bool g4x_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 
  out:
 	if (dirty) {
-		DRM_DEBUG_KMS("%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
-			      plane->base.name,
-			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
-			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
-			      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "%s watermarks: normal=%d, SR=%d, HPLL=%d\n",
+			    plane->base.name,
+			    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_NORMAL].plane[plane_id],
+			    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].plane[plane_id],
+			    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].plane[plane_id]);
 
 		if (plane_id == PLANE_PRIMARY)
-			DRM_DEBUG_KMS("FBC watermarks: SR=%d, HPLL=%d\n",
-				      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
-				      crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
+			drm_dbg_kms(&dev_priv->drm,
+				    "FBC watermarks: SR=%d, HPLL=%d\n",
+				    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_SR].fbc,
+				    crtc_state->wm.g4x.raw[G4X_WM_LEVEL_HPLL].fbc);
 	}
 
 	return dirty;
@@ -1261,7 +1294,7 @@ static bool g4x_raw_plane_wm_is_valid(const struct intel_crtc_state *crtc_state,
 static bool g4x_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
 				     int level)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 
 	if (level > dev_priv->wm.max_level)
 		return false;
@@ -1299,9 +1332,9 @@ static void g4x_invalidate_wms(struct intel_crtc *crtc,
 
 static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
 	int num_active_planes = hweight8(crtc_state->active_planes &
 					 ~BIT(PLANE_CURSOR));
@@ -1316,8 +1349,8 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	for_each_oldnew_intel_plane_in_state(state, plane,
 					     old_plane_state,
 					     new_plane_state, i) {
-		if (new_plane_state->base.crtc != &crtc->base &&
-		    old_plane_state->base.crtc != &crtc->base)
+		if (new_plane_state->hw.crtc != &crtc->base &&
+		    old_plane_state->hw.crtc != &crtc->base)
 			continue;
 
 		if (g4x_raw_plane_wm_compute(crtc_state, new_plane_state))
@@ -1388,17 +1421,17 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 
 static int g4x_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct g4x_wm_state *intermediate = &new_crtc_state->wm.g4x.intermediate;
 	const struct g4x_wm_state *optimal = &new_crtc_state->wm.g4x.optimal;
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(intel_state, crtc);
 	const struct g4x_wm_state *active = &old_crtc_state->wm.g4x.optimal;
 	enum plane_id plane_id;
 
-	if (!new_crtc_state->base.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->base)) {
+	if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
 		*intermediate = *optimal;
 
 		intermediate->cxsr = false;
@@ -1528,10 +1561,11 @@ static void g4x_program_watermarks(struct drm_i915_private *dev_priv)
 }
 
 static void g4x_initial_watermarks(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	crtc->wm.active.g4x = crtc_state->wm.g4x.intermediate;
@@ -1540,10 +1574,11 @@ static void g4x_initial_watermarks(struct intel_atomic_state *state,
 }
 
 static void g4x_optimize_watermarks(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state)
+				    struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	if (!crtc_state->wm.need_postvbl_update)
 		return;
@@ -1589,10 +1624,10 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
 				const struct intel_plane_state *plane_state,
 				int level)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	unsigned int clock, htotal, cpp, width, wm;
 
 	if (dev_priv->wm.pri_latency[level] == 0)
@@ -1601,7 +1636,7 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 	width = crtc_state->pipe_src_w;
@@ -1630,7 +1665,7 @@ static bool vlv_need_sprite0_fifo_workaround(unsigned int active_planes)
 
 static int vlv_compute_fifo(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	const struct g4x_pipe_wm *raw =
 		&crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2];
 	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
@@ -1742,7 +1777,7 @@ static u16 vlv_invert_wm_value(u16 wm, u16 fifo_size)
 static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 				 int level, enum plane_id plane_id, u16 value)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int num_levels = intel_wm_num_levels(dev_priv);
 	bool dirty = false;
 
@@ -1759,7 +1794,8 @@ static bool vlv_raw_plane_wm_set(struct intel_crtc_state *crtc_state,
 static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 				     const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	enum plane_id plane_id = plane->id;
 	int num_levels = intel_wm_num_levels(to_i915(plane->base.dev));
 	int level;
@@ -1787,11 +1823,12 @@ static bool vlv_raw_plane_wm_compute(struct intel_crtc_state *crtc_state,
 
 out:
 	if (dirty)
-		DRM_DEBUG_KMS("%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
-			      plane->base.name,
-			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
-			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
-			      crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "%s watermarks: PM2=%d, PM5=%d, DDR DVFS=%d\n",
+			    plane->base.name,
+			    crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2].plane[plane_id],
+			    crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM5].plane[plane_id],
+			    crtc_state->wm.vlv.raw[VLV_WM_LEVEL_DDR_DVFS].plane[plane_id]);
 
 	return dirty;
 }
@@ -1817,16 +1854,16 @@ static bool vlv_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state,
 
 static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_atomic_state *state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
 	int num_active_planes = hweight8(crtc_state->active_planes &
 					 ~BIT(PLANE_CURSOR));
-	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->base);
+	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->uapi);
 	const struct intel_plane_state *old_plane_state;
 	const struct intel_plane_state *new_plane_state;
 	struct intel_plane *plane;
@@ -1837,8 +1874,8 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	for_each_oldnew_intel_plane_in_state(state, plane,
 					     old_plane_state,
 					     new_plane_state, i) {
-		if (new_plane_state->base.crtc != &crtc->base &&
-		    old_plane_state->base.crtc != &crtc->base)
+		if (new_plane_state->hw.crtc != &crtc->base &&
+		    old_plane_state->hw.crtc != &crtc->base)
 			continue;
 
 		if (vlv_raw_plane_wm_compute(crtc_state, new_plane_state))
@@ -1923,11 +1960,12 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	(((value) << DSPARB_ ## plane ## _SHIFT_VLV) & DSPARB_ ## plane ## _MASK_VLV)
 
 static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_uncore *uncore = &dev_priv->uncore;
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
 	int sprite0_start, sprite1_start, fifo_size;
@@ -2021,17 +2059,17 @@ static void vlv_atomic_update_fifo(struct intel_atomic_state *state,
 
 static int vlv_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct vlv_wm_state *intermediate = &new_crtc_state->wm.vlv.intermediate;
 	const struct vlv_wm_state *optimal = &new_crtc_state->wm.vlv.optimal;
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_crtc_state->base.state);
+		to_intel_atomic_state(new_crtc_state->uapi.state);
 	const struct intel_crtc_state *old_crtc_state =
 		intel_atomic_get_old_crtc_state(intel_state, crtc);
 	const struct vlv_wm_state *active = &old_crtc_state->wm.vlv.optimal;
 	int level;
 
-	if (!new_crtc_state->base.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->base)) {
+	if (!new_crtc_state->hw.active || drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi)) {
 		*intermediate = *optimal;
 
 		intermediate->cxsr = false;
@@ -2147,10 +2185,11 @@ static void vlv_program_watermarks(struct drm_i915_private *dev_priv)
 }
 
 static void vlv_initial_watermarks(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	crtc->wm.active.vlv = crtc_state->wm.vlv.intermediate;
@@ -2159,10 +2198,11 @@ static void vlv_initial_watermarks(struct intel_atomic_state *state,
 }
 
 static void vlv_optimize_watermarks(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state)
+				    struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	if (!crtc_state->wm.need_postvbl_update)
 		return;
@@ -2187,7 +2227,7 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		/* self-refresh has much higher latency */
 		static const int sr_latency_ns = 12000;
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int clock = adjusted_mode->crtc_clock;
@@ -2203,8 +2243,9 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		if (srwm < 0)
 			srwm = 1;
 		srwm &= 0x1ff;
-		DRM_DEBUG_KMS("self-refresh entries: %d, wm: %d\n",
-			      entries, srwm);
+		drm_dbg_kms(&dev_priv->drm,
+			    "self-refresh entries: %d, wm: %d\n",
+			    entries, srwm);
 
 		entries = intel_wm_method2(clock, htotal,
 					   crtc->base.cursor->state->crtc_w, 4,
@@ -2217,8 +2258,9 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		if (cursor_sr > i965_cursor_wm_info.max_wm)
 			cursor_sr = i965_cursor_wm_info.max_wm;
 
-		DRM_DEBUG_KMS("self-refresh watermark: display plane %d "
-			      "cursor %d\n", srwm, cursor_sr);
+		drm_dbg_kms(&dev_priv->drm,
+			    "self-refresh watermark: display plane %d "
+			    "cursor %d\n", srwm, cursor_sr);
 
 		cxsr_enabled = true;
 	} else {
@@ -2227,8 +2269,9 @@ static void i965_update_wm(struct intel_crtc *unused_crtc)
 		intel_set_memory_cxsr(dev_priv, false);
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
-		      srwm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Setting FIFO watermarks - A: 8, B: 8, C: 8, SR %d\n",
+		    srwm);
 
 	/* 965 has limitations... */
 	I915_WRITE(DSPFW1, FW_WM(srwm, SR) |
@@ -2268,7 +2311,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	crtc = intel_get_crtc_for_plane(dev_priv, PLANE_A);
 	if (intel_crtc_active(crtc)) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp;
@@ -2295,7 +2338,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 	crtc = intel_get_crtc_for_plane(dev_priv, PLANE_B);
 	if (intel_crtc_active(crtc)) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc->config->base.adjusted_mode;
+			&crtc->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			crtc->base.primary->state->fb;
 		int cpp;
@@ -2318,7 +2361,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 			planeb_wm = wm_info->max_wm;
 	}
 
-	DRM_DEBUG_KMS("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm);
 
 	if (IS_I915GM(dev_priv) && enabled) {
 		struct drm_i915_gem_object *obj;
@@ -2343,7 +2387,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 		/* self-refresh has much higher latency */
 		static const int sr_latency_ns = 6000;
 		const struct drm_display_mode *adjusted_mode =
-			&enabled->config->base.adjusted_mode;
+			&enabled->config->hw.adjusted_mode;
 		const struct drm_framebuffer *fb =
 			enabled->base.primary->state->fb;
 		int clock = adjusted_mode->crtc_clock;
@@ -2360,7 +2404,8 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 		entries = intel_wm_method2(clock, htotal, hdisplay, cpp,
 					   sr_latency_ns / 100);
 		entries = DIV_ROUND_UP(entries, wm_info->cacheline_size);
-		DRM_DEBUG_KMS("self-refresh entries: %d\n", entries);
+		drm_dbg_kms(&dev_priv->drm,
+			    "self-refresh entries: %d\n", entries);
 		srwm = wm_info->fifo_size - entries;
 		if (srwm < 0)
 			srwm = 1;
@@ -2372,8 +2417,9 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc)
 			I915_WRITE(FW_BLC_SELF, srwm & 0x3f);
 	}
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
-		      planea_wm, planeb_wm, cwm, srwm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n",
+		     planea_wm, planeb_wm, cwm, srwm);
 
 	fwater_lo = ((planeb_wm & 0x3f) << 16) | (planea_wm & 0x3f);
 	fwater_hi = (cwm & 0x1f);
@@ -2401,7 +2447,7 @@ static void i845_update_wm(struct intel_crtc *unused_crtc)
 	if (crtc == NULL)
 		return;
 
-	adjusted_mode = &crtc->config->base.adjusted_mode;
+	adjusted_mode = &crtc->config->hw.adjusted_mode;
 	planea_wm = intel_calculate_wm(adjusted_mode->crtc_clock,
 				       &i845_wm_info,
 				       dev_priv->display.get_fifo_size(dev_priv, PLANE_A),
@@ -2409,7 +2455,8 @@ static void i845_update_wm(struct intel_crtc *unused_crtc)
 	fwater_lo = I915_READ(FW_BLC) & ~0xfff;
 	fwater_lo |= (3<<8) | planea_wm;
 
-	DRM_DEBUG_KMS("Setting FIFO watermarks - A: %d\n", planea_wm);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Setting FIFO watermarks - A: %d\n", planea_wm);
 
 	I915_WRITE(FW_BLC, fwater_lo);
 }
@@ -2483,7 +2530,7 @@ static u32 ilk_compute_pri_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
 
@@ -2491,8 +2538,8 @@ static u32 ilk_compute_pri_wm(const struct intel_crtc_state *crtc_state,
 		return method1;
 
 	method2 = ilk_wm_method2(crtc_state->pixel_rate,
-				 crtc_state->base.adjusted_mode.crtc_htotal,
-				 drm_rect_width(&plane_state->base.dst),
+				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 drm_rect_width(&plane_state->uapi.dst),
 				 cpp, mem_value);
 
 	return min(method1, method2);
@@ -2515,12 +2562,12 @@ static u32 ilk_compute_spr_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	method1 = ilk_wm_method1(crtc_state->pixel_rate, cpp, mem_value);
 	method2 = ilk_wm_method2(crtc_state->pixel_rate,
-				 crtc_state->base.adjusted_mode.crtc_htotal,
-				 drm_rect_width(&plane_state->base.dst),
+				 crtc_state->hw.adjusted_mode.crtc_htotal,
+				 drm_rect_width(&plane_state->uapi.dst),
 				 cpp, mem_value);
 	return min(method1, method2);
 }
@@ -2541,11 +2588,11 @@ static u32 ilk_compute_cur_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
 	return ilk_wm_method2(crtc_state->pixel_rate,
-			      crtc_state->base.adjusted_mode.crtc_htotal,
-			      drm_rect_width(&plane_state->base.dst),
+			      crtc_state->hw.adjusted_mode.crtc_htotal,
+			      drm_rect_width(&plane_state->uapi.dst),
 			      cpp, mem_value);
 }
 
@@ -2559,9 +2606,10 @@ static u32 ilk_compute_fbc_wm(const struct intel_crtc_state *crtc_state,
 	if (!intel_wm_plane_visible(crtc_state, plane_state))
 		return 0;
 
-	cpp = plane_state->base.fb->format->cpp[0];
+	cpp = plane_state->hw.fb->format->cpp[0];
 
-	return ilk_wm_fbc(pri_val, drm_rect_width(&plane_state->base.dst), cpp);
+	return ilk_wm_fbc(pri_val, drm_rect_width(&plane_state->uapi.dst),
+			  cpp);
 }
 
 static unsigned int
@@ -2766,12 +2814,12 @@ static u32
 hsw_compute_linetime_wm(const struct intel_crtc_state *crtc_state)
 {
 	const struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(crtc_state->base.state);
+		to_intel_atomic_state(crtc_state->uapi.state);
 	const struct drm_display_mode *adjusted_mode =
-		&crtc_state->base.adjusted_mode;
+		&crtc_state->hw.adjusted_mode;
 	u32 linetime, ips_linetime;
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return 0;
 	if (WARN_ON(adjusted_mode->crtc_clock == 0))
 		return 0;
@@ -2807,7 +2855,8 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 					     &val, NULL);
 
 		if (ret) {
-			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
+			drm_err(&dev_priv->drm,
+				"SKL Mailbox read error = %d\n", ret);
 			return;
 		}
 
@@ -2825,7 +2874,8 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv,
 					     GEN9_PCODE_READ_MEM_LATENCY,
 					     &val, NULL);
 		if (ret) {
-			DRM_ERROR("SKL Mailbox read error = %d\n", ret);
+			drm_err(&dev_priv->drm,
+				"SKL Mailbox read error = %d\n", ret);
 			return;
 		}
 
@@ -2943,8 +2993,9 @@ static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
 		unsigned int latency = wm[level];
 
 		if (latency == 0) {
-			DRM_DEBUG_KMS("%s WM%d latency not provided\n",
-				      name, level);
+			drm_dbg_kms(&dev_priv->drm,
+				    "%s WM%d latency not provided\n",
+				    name, level);
 			continue;
 		}
 
@@ -2957,9 +3008,9 @@ static void intel_print_wm_latency(struct drm_i915_private *dev_priv,
 		else if (level > 0)
 			latency *= 5;
 
-		DRM_DEBUG_KMS("%s WM%d latency %u (%u.%u usec)\n",
-			      name, level, wm[level],
-			      latency / 10, latency % 10);
+		drm_dbg_kms(&dev_priv->drm,
+			    "%s WM%d latency %u (%u.%u usec)\n", name, level,
+			    wm[level], latency / 10, latency % 10);
 	}
 }
 
@@ -2993,7 +3044,8 @@ static void snb_wm_latency_quirk(struct drm_i915_private *dev_priv)
 	if (!changed)
 		return;
 
-	DRM_DEBUG_KMS("WM latency values increased to avoid potential underruns\n");
+	drm_dbg_kms(&dev_priv->drm,
+		    "WM latency values increased to avoid potential underruns\n");
 	intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
 	intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
 	intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
@@ -3021,7 +3073,8 @@ static void snb_wm_lp3_irq_quirk(struct drm_i915_private *dev_priv)
 	dev_priv->wm.spr_latency[3] = 0;
 	dev_priv->wm.cur_latency[3] = 0;
 
-	DRM_DEBUG_KMS("LP3 watermarks disabled due to potential for lost interrupts\n");
+	drm_dbg_kms(&dev_priv->drm,
+		    "LP3 watermarks disabled due to potential for lost interrupts\n");
 	intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency);
 	intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency);
 	intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency);
@@ -3071,7 +3124,7 @@ static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv,
 
 	/* At least LP0 must be valid */
 	if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) {
-		DRM_DEBUG_KMS("LP0 watermark invalid\n");
+		drm_dbg_kms(&dev_priv->drm, "LP0 watermark invalid\n");
 		return false;
 	}
 
@@ -3081,11 +3134,9 @@ static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv,
 /* Compute new watermarks for the pipe */
 static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct intel_pipe_wm *pipe_wm;
-	struct drm_device *dev = state->dev;
-	const struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
 	const struct intel_plane_state *pristate = NULL;
@@ -3105,12 +3156,12 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 			curstate = plane_state;
 	}
 
-	pipe_wm->pipe_enabled = crtc_state->base.active;
+	pipe_wm->pipe_enabled = crtc_state->hw.active;
 	if (sprstate) {
-		pipe_wm->sprites_enabled = sprstate->base.visible;
-		pipe_wm->sprites_scaled = sprstate->base.visible &&
-			(drm_rect_width(&sprstate->base.dst) != drm_rect_width(&sprstate->base.src) >> 16 ||
-			 drm_rect_height(&sprstate->base.dst) != drm_rect_height(&sprstate->base.src) >> 16);
+		pipe_wm->sprites_enabled = sprstate->uapi.visible;
+		pipe_wm->sprites_scaled = sprstate->uapi.visible &&
+			(drm_rect_width(&sprstate->uapi.dst) != drm_rect_width(&sprstate->uapi.src) >> 16 ||
+			 drm_rect_height(&sprstate->uapi.dst) != drm_rect_height(&sprstate->uapi.src) >> 16);
 	}
 
 	usable_level = max_level;
@@ -3162,11 +3213,11 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
  */
 static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(newstate->base.crtc);
+	struct intel_crtc *intel_crtc = to_intel_crtc(newstate->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate;
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(newstate->base.state);
+		to_intel_atomic_state(newstate->uapi.state);
 	const struct intel_crtc_state *oldstate =
 		intel_atomic_get_old_crtc_state(intel_state, intel_crtc);
 	const struct intel_pipe_wm *b = &oldstate->wm.ilk.optimal;
@@ -3178,7 +3229,7 @@ static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate)
 	 * and after the vblank.
 	 */
 	*a = newstate->wm.ilk.optimal;
-	if (!newstate->base.active || drm_atomic_crtc_needs_modeset(&newstate->base) ||
+	if (!newstate->hw.active || drm_atomic_crtc_needs_modeset(&newstate->uapi) ||
 	    intel_state->skip_intermediate_wm)
 		return 0;
 
@@ -3588,10 +3639,8 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv,
 	dev_priv->wm.hw = *results;
 }
 
-bool ilk_disable_lp_wm(struct drm_device *dev)
+bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
 	return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL);
 }
 
@@ -3652,7 +3701,7 @@ skl_setup_sagv_block_time(struct drm_i915_private *dev_priv)
 			return;
 		}
 
-		DRM_DEBUG_DRIVER("Couldn't read SAGV block time!\n");
+		drm_dbg(&dev_priv->drm, "Couldn't read SAGV block time!\n");
 	} else if (IS_GEN(dev_priv, 11)) {
 		dev_priv->sagv_block_time_us = 10;
 		return;
@@ -3692,7 +3741,7 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 	if (dev_priv->sagv_status == I915_SAGV_ENABLED)
 		return 0;
 
-	DRM_DEBUG_KMS("Enabling SAGV\n");
+	drm_dbg_kms(&dev_priv->drm, "Enabling SAGV\n");
 	ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				      GEN9_SAGV_ENABLE);
 
@@ -3703,11 +3752,11 @@ intel_enable_sagv(struct drm_i915_private *dev_priv)
 	 * don't actually have SAGV.
 	 */
 	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
-		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+		drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n");
 		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
 	} else if (ret < 0) {
-		DRM_ERROR("Failed to enable SAGV\n");
+		drm_err(&dev_priv->drm, "Failed to enable SAGV\n");
 		return ret;
 	}
 
@@ -3726,7 +3775,7 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	if (dev_priv->sagv_status == I915_SAGV_DISABLED)
 		return 0;
 
-	DRM_DEBUG_KMS("Disabling SAGV\n");
+	drm_dbg_kms(&dev_priv->drm, "Disabling SAGV\n");
 	/* bspec says to keep retrying for at least 1 ms */
 	ret = skl_pcode_request(dev_priv, GEN9_PCODE_SAGV_CONTROL,
 				GEN9_SAGV_DISABLE,
@@ -3737,11 +3786,11 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	 * don't actually have SAGV.
 	 */
 	if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) {
-		DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+		drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n");
 		dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED;
 		return 0;
 	} else if (ret < 0) {
-		DRM_ERROR("Failed to disable SAGV (%d)\n", ret);
+		drm_err(&dev_priv->drm, "Failed to disable SAGV (%d)\n", ret);
 		return ret;
 	}
 
@@ -3780,7 +3829,7 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 	crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 	crtc_state = to_intel_crtc_state(crtc->base.state);
 
-	if (crtc->base.state->adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
 
 	for_each_intel_plane_on_crtc(dev, crtc, plane) {
@@ -3830,7 +3879,7 @@ static u16 intel_get_ddb_size(struct drm_i915_private *dev_priv,
 	if (INTEL_GEN(dev_priv) < 11)
 		return ddb_size - 4; /* 4 blocks for bypass path allocation */
 
-	adjusted_mode = &crtc_state->base.adjusted_mode;
+	adjusted_mode = &crtc_state->hw.adjusted_mode;
 	total_data_bw = total_data_rate * drm_mode_vrefresh(adjusted_mode);
 
 	/*
@@ -3859,16 +3908,16 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 				   struct skl_ddb_entry *alloc, /* out */
 				   int *num_active /* out */)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
-	struct drm_crtc *for_crtc = crtc_state->base.crtc;
+	struct drm_crtc *for_crtc = crtc_state->uapi.crtc;
 	const struct intel_crtc *crtc;
 	u32 pipe_width = 0, total_width = 0, width_before_pipe = 0;
 	enum pipe for_pipe = to_intel_crtc(for_crtc)->pipe;
 	u16 ddb_size;
 	u32 i;
 
-	if (WARN_ON(!state) || !crtc_state->base.active) {
+	if (WARN_ON(!state) || !crtc_state->hw.active) {
 		alloc->start = 0;
 		alloc->end = 0;
 		*num_active = hweight8(dev_priv->active_pipes);
@@ -3907,11 +3956,11 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 	 */
 	for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) {
 		const struct drm_display_mode *adjusted_mode =
-			&crtc_state->base.adjusted_mode;
+			&crtc_state->hw.adjusted_mode;
 		enum pipe pipe = crtc->pipe;
 		int hdisplay, vdisplay;
 
-		if (!crtc_state->base.enable)
+		if (!crtc_state->hw.enable)
 			continue;
 
 		drm_mode_get_hv_timing(adjusted_mode, &hdisplay, &vdisplay);
@@ -3942,7 +3991,7 @@ static unsigned int
 skl_cursor_allocation(const struct intel_crtc_state *crtc_state,
 		      int num_active)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int level, max_level = ilk_wm_max_level(dev_priv);
 	struct skl_wm_level wm = {};
 	int ret, min_ddb_alloc = 0;
@@ -4082,10 +4131,10 @@ skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
 	 *
 	 * n.b., src is 16.16 fixed point, dst is whole integer.
 	 */
-	src_w = drm_rect_width(&plane_state->base.src) >> 16;
-	src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	dst_w = drm_rect_width(&plane_state->base.dst);
-	dst_h = drm_rect_height(&plane_state->base.dst);
+	src_w = drm_rect_width(&plane_state->uapi.src) >> 16;
+	src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->uapi.dst);
+	dst_h = drm_rect_height(&plane_state->uapi.dst);
 
 	fp_w_ratio = div_fixed16(src_w, dst_w);
 	fp_h_ratio = div_fixed16(src_h, dst_h);
@@ -4100,21 +4149,21 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state,
 			     int color_plane)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	u32 data_rate;
 	u32 width = 0, height = 0;
 	uint_fixed_16_16_t down_scale_amount;
 	u64 rate;
 
-	if (!plane_state->base.visible)
+	if (!plane_state->uapi.visible)
 		return 0;
 
 	if (plane->id == PLANE_CURSOR)
 		return 0;
 
 	if (color_plane == 1 &&
-	    !drm_format_info_is_yuv_semiplanar(fb->format))
+	    !intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier))
 		return 0;
 
 	/*
@@ -4122,8 +4171,8 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 	 * the 90/270 degree plane rotation cases (to match the
 	 * GTT mapping), hence no need to account for rotation here.
 	 */
-	width = drm_rect_width(&plane_state->base.src) >> 16;
-	height = drm_rect_height(&plane_state->base.src) >> 16;
+	width = drm_rect_width(&plane_state->uapi.src) >> 16;
+	height = drm_rect_height(&plane_state->uapi.src) >> 16;
 
 	/* UV plane does 1/2 pixel sub-sampling */
 	if (color_plane == 1) {
@@ -4146,7 +4195,7 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 				 u64 *plane_data_rate,
 				 u64 *uv_plane_data_rate)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
 	u64 total_data_rate = 0;
@@ -4181,7 +4230,7 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 	const struct intel_plane_state *plane_state;
 	u64 total_data_rate = 0;
 
-	if (WARN_ON(!crtc_state->base.state))
+	if (WARN_ON(!crtc_state->uapi.state))
 		return 0;
 
 	/* Calculate and cache data rate for each plane */
@@ -4225,8 +4274,8 @@ static int
 skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state,
 		      struct skl_ddb_allocation *ddb /* out */)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
-	struct drm_crtc *crtc = crtc_state->base.crtc;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct skl_ddb_entry *alloc = &crtc_state->wm.skl.ddb;
@@ -4248,7 +4297,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state,
 	if (WARN_ON(!state))
 		return 0;
 
-	if (!crtc_state->base.active) {
+	if (!crtc_state->hw.active) {
 		alloc->start = alloc->end = 0;
 		return 0;
 	}
@@ -4310,9 +4359,10 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state,
 	}
 
 	if (level < 0) {
-		DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations");
-		DRM_DEBUG_KMS("minimum required %d/%d\n", blocks,
-			      alloc_size);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Requested display configuration exceeds system DDB limitations");
+		drm_dbg_kms(&dev_priv->drm, "minimum required %d/%d\n",
+			    blocks, alloc_size);
 		return -EINVAL;
 	}
 
@@ -4490,7 +4540,7 @@ intel_get_linetime_us(const struct intel_crtc_state *crtc_state)
 	u32 crtc_htotal;
 	uint_fixed_16_16_t linetime_us;
 
-	if (!crtc_state->base.active)
+	if (!crtc_state->hw.active)
 		return u32_to_fixed16(0);
 
 	pixel_rate = crtc_state->pixel_rate;
@@ -4498,7 +4548,7 @@ intel_get_linetime_us(const struct intel_crtc_state *crtc_state)
 	if (WARN_ON(pixel_rate == 0))
 		return u32_to_fixed16(0);
 
-	crtc_htotal = crtc_state->base.adjusted_mode.crtc_htotal;
+	crtc_htotal = crtc_state->hw.adjusted_mode.crtc_htotal;
 	linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate);
 
 	return linetime_us;
@@ -4533,13 +4583,15 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 		      u32 plane_pixel_rate, struct skl_wm_params *wp,
 		      int color_plane)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	u32 interm_pbpl;
 
 	/* only planar format has two planes */
-	if (color_plane == 1 && !drm_format_info_is_yuv_semiplanar(format)) {
-		DRM_DEBUG_KMS("Non planar format have single plane\n");
+	if (color_plane == 1 &&
+	    !intel_format_info_is_yuv_semiplanar(format, modifier)) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "Non planar format have single plane\n");
 		return -EINVAL;
 	}
 
@@ -4550,7 +4602,7 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
-	wp->is_planar = drm_format_info_is_yuv_semiplanar(format);
+	wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);
 
 	wp->width = width;
 	if (color_plane == 1 && wp->is_planar)
@@ -4622,7 +4674,7 @@ skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state,
 			    struct skl_wm_params *wp, int color_plane)
 {
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	int width;
 
 	/*
@@ -4630,11 +4682,11 @@ skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
 	 * the 90/270 degree plane rotation cases (to match the
 	 * GTT mapping), hence no need to account for rotation here.
 	 */
-	width = drm_rect_width(&plane_state->base.src) >> 16;
+	width = drm_rect_width(&plane_state->uapi.src) >> 16;
 
 	return skl_compute_wm_params(crtc_state, width,
 				     fb->format, fb->modifier,
-				     plane_state->base.rotation,
+				     plane_state->hw.rotation,
 				     skl_adjusted_plane_pixel_rate(crtc_state, plane_state),
 				     wp, color_plane);
 }
@@ -4654,7 +4706,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 				 const struct skl_wm_level *result_prev,
 				 struct skl_wm_level *result /* out */)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	u32 latency = dev_priv->wm.skl_latency[level];
 	uint_fixed_16_16_t method1, method2;
 	uint_fixed_16_16_t selected_result;
@@ -4680,14 +4732,14 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 	method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate,
 				 wp->cpp, latency, wp->dbuf_block_size);
 	method2 = skl_wm_method2(wp->plane_pixel_rate,
-				 crtc_state->base.adjusted_mode.crtc_htotal,
+				 crtc_state->hw.adjusted_mode.crtc_htotal,
 				 latency,
 				 wp->plane_blocks_per_line);
 
 	if (wp->y_tiled) {
 		selected_result = max_fixed16(method2, wp->y_tile_minimum);
 	} else {
-		if ((wp->cpp * crtc_state->base.adjusted_mode.crtc_htotal /
+		if ((wp->cpp * crtc_state->hw.adjusted_mode.crtc_htotal /
 		     wp->dbuf_block_size < 1) &&
 		     (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) {
 			selected_result = method2;
@@ -4778,7 +4830,7 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 		      const struct skl_wm_params *wm_params,
 		      struct skl_wm_level *levels)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int level, max_level = ilk_wm_max_level(dev_priv);
 	struct skl_wm_level *result_prev = &levels[0];
 
@@ -4795,7 +4847,7 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 static u32
 skl_compute_linetime_wm(const struct intel_crtc_state *crtc_state)
 {
-	struct drm_atomic_state *state = crtc_state->base.state;
+	struct drm_atomic_state *state = crtc_state->uapi.state;
 	struct drm_i915_private *dev_priv = to_i915(state->dev);
 	uint_fixed_16_16_t linetime_us;
 	u32 linetime_wm;
@@ -4814,7 +4866,7 @@ static void skl_compute_transition_wm(const struct intel_crtc_state *crtc_state,
 				      const struct skl_wm_params *wp,
 				      struct skl_plane_wm *wm)
 {
-	struct drm_device *dev = crtc_state->base.crtc->dev;
+	struct drm_device *dev = crtc_state->uapi.crtc->dev;
 	const struct drm_i915_private *dev_priv = to_i915(dev);
 	u16 trans_min, trans_y_tile_min;
 	const u16 trans_amount = 10; /* This is configurable amount */
@@ -4912,8 +4964,8 @@ static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state,
 static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
-	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane);
+	const struct drm_framebuffer *fb = plane_state->hw.fb;
 	enum plane_id plane_id = plane->id;
 	int ret;
 
@@ -4938,7 +4990,7 @@ static int skl_build_plane_wm(struct intel_crtc_state *crtc_state,
 static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 			      const struct intel_plane_state *plane_state)
 {
-	enum plane_id plane_id = to_intel_plane(plane_state->base.plane)->id;
+	enum plane_id plane_id = to_intel_plane(plane_state->uapi.plane)->id;
 	int ret;
 
 	/* Watermarks calculated in master */
@@ -4946,7 +4998,7 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 		return 0;
 
 	if (plane_state->planar_linked_plane) {
-		const struct drm_framebuffer *fb = plane_state->base.fb;
+		const struct drm_framebuffer *fb = plane_state->hw.fb;
 		enum plane_id y_plane_id = plane_state->planar_linked_plane->id;
 
 		WARN_ON(!intel_wm_plane_visible(crtc_state, plane_state));
@@ -4974,7 +5026,7 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 
 static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
 	struct intel_plane *plane;
 	const struct intel_plane_state *plane_state;
@@ -5151,8 +5203,8 @@ static int
 skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state,
 			    struct intel_crtc_state *new_crtc_state)
 {
-	struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->base.state);
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->uapi.state);
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_plane *plane;
 
@@ -5218,7 +5270,7 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 	struct intel_crtc *crtc;
 	int i;
 
-	if ((drm_debug & DRM_UT_KMS) == 0)
+	if (!drm_debug_enabled(DRM_UT_KMS))
 		return;
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
@@ -5238,10 +5290,11 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 			if (skl_ddb_entry_equal(old, new))
 				continue;
 
-			DRM_DEBUG_KMS("[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n",
-				      plane->base.base.id, plane->base.name,
-				      old->start, old->end, new->start, new->end,
-				      skl_ddb_entry_size(old), skl_ddb_entry_size(new));
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n",
+				    plane->base.base.id, plane->base.name,
+				    old->start, old->end, new->start, new->end,
+				    skl_ddb_entry_size(old), skl_ddb_entry_size(new));
 		}
 
 		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
@@ -5254,70 +5307,74 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 			if (skl_plane_wm_equals(dev_priv, old_wm, new_wm))
 				continue;
 
-			DRM_DEBUG_KMS("[PLANE:%d:%s]   level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm"
-				      " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm\n",
-				      plane->base.base.id, plane->base.name,
-				      enast(old_wm->wm[0].plane_en), enast(old_wm->wm[1].plane_en),
-				      enast(old_wm->wm[2].plane_en), enast(old_wm->wm[3].plane_en),
-				      enast(old_wm->wm[4].plane_en), enast(old_wm->wm[5].plane_en),
-				      enast(old_wm->wm[6].plane_en), enast(old_wm->wm[7].plane_en),
-				      enast(old_wm->trans_wm.plane_en),
-				      enast(new_wm->wm[0].plane_en), enast(new_wm->wm[1].plane_en),
-				      enast(new_wm->wm[2].plane_en), enast(new_wm->wm[3].plane_en),
-				      enast(new_wm->wm[4].plane_en), enast(new_wm->wm[5].plane_en),
-				      enast(new_wm->wm[6].plane_en), enast(new_wm->wm[7].plane_en),
-				      enast(new_wm->trans_wm.plane_en));
-
-			DRM_DEBUG_KMS("[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s]   level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm"
+				    " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm\n",
+				    plane->base.base.id, plane->base.name,
+				    enast(old_wm->wm[0].plane_en), enast(old_wm->wm[1].plane_en),
+				    enast(old_wm->wm[2].plane_en), enast(old_wm->wm[3].plane_en),
+				    enast(old_wm->wm[4].plane_en), enast(old_wm->wm[5].plane_en),
+				    enast(old_wm->wm[6].plane_en), enast(old_wm->wm[7].plane_en),
+				    enast(old_wm->trans_wm.plane_en),
+				    enast(new_wm->wm[0].plane_en), enast(new_wm->wm[1].plane_en),
+				    enast(new_wm->wm[2].plane_en), enast(new_wm->wm[3].plane_en),
+				    enast(new_wm->wm[4].plane_en), enast(new_wm->wm[5].plane_en),
+				    enast(new_wm->wm[6].plane_en), enast(new_wm->wm[7].plane_en),
+				    enast(new_wm->trans_wm.plane_en));
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
 				      " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d\n",
-				      plane->base.base.id, plane->base.name,
-				      enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
-				      enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
-				      enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].plane_res_l,
-				      enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].plane_res_l,
-				      enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].plane_res_l,
-				      enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].plane_res_l,
-				      enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].plane_res_l,
-				      enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
-				      enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
-
-				      enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
-				      enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
-				      enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].plane_res_l,
-				      enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].plane_res_l,
-				      enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].plane_res_l,
-				      enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].plane_res_l,
-				      enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].plane_res_l,
-				      enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].plane_res_l,
-				      enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l);
-
-			DRM_DEBUG_KMS("[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
-				      " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
-				      plane->base.base.id, plane->base.name,
-				      old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
-				      old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
-				      old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
-				      old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
-				      old_wm->trans_wm.plane_res_b,
-				      new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
-				      new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
-				      new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
-				      new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
-				      new_wm->trans_wm.plane_res_b);
-
-			DRM_DEBUG_KMS("[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
-				      " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
-				      plane->base.base.id, plane->base.name,
-				      old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
-				      old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
-				      old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
-				      old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
-				      old_wm->trans_wm.min_ddb_alloc,
-				      new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
-				      new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
-				      new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
-				      new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
-				      new_wm->trans_wm.min_ddb_alloc);
+				    plane->base.base.id, plane->base.name,
+				    enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
+				    enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
+				    enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].plane_res_l,
+				    enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].plane_res_l,
+				    enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].plane_res_l,
+				    enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].plane_res_l,
+				    enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].plane_res_l,
+				    enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
+				    enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
+
+				    enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
+				    enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
+				    enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].plane_res_l,
+				    enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].plane_res_l,
+				    enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].plane_res_l,
+				    enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].plane_res_l,
+				    enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].plane_res_l,
+				    enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].plane_res_l,
+				    enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.plane_res_l);
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+				    plane->base.base.id, plane->base.name,
+				    old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
+				    old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
+				    old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
+				    old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
+				    old_wm->trans_wm.plane_res_b,
+				    new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
+				    new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
+				    new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
+				    new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
+				    new_wm->trans_wm.plane_res_b);
+
+			drm_dbg_kms(&dev_priv->drm,
+				    "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
+				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
+				    plane->base.base.id, plane->base.name,
+				    old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
+				    old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
+				    old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
+				    old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
+				    old_wm->trans_wm.min_ddb_alloc,
+				    new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
+				    new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
+				    new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
+				    new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
+				    new_wm->trans_wm.min_ddb_alloc);
 		}
 	}
 }
@@ -5356,7 +5413,7 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 		if (ret)
 			return ret;
 
-		state->active_pipe_changes = ~0;
+		state->active_pipe_changes = INTEL_INFO(dev_priv)->pipe_mask;
 
 		/*
 		 * We usually only initialize state->active_pipes if we
@@ -5382,7 +5439,7 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 	 * to grab the lock on *all* CRTC's.
 	 */
 	if (state->active_pipe_changes || state->modeset) {
-		state->wm_results.dirty_pipes = ~0;
+		state->wm_results.dirty_pipes = INTEL_INFO(dev_priv)->pipe_mask;
 
 		ret = intel_add_all_pipes(state);
 		if (ret)
@@ -5436,7 +5493,7 @@ static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
 		 * power well the hardware state will go out of sync
 		 * with the software state.
 		 */
-		if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->base) &&
+		if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) &&
 		    skl_plane_wm_equals(dev_priv,
 					&old_crtc_state->wm.skl.optimal.planes[plane_id],
 					&new_crtc_state->wm.skl.optimal.planes[plane_id]))
@@ -5500,11 +5557,12 @@ skl_compute_wm(struct intel_atomic_state *state)
 }
 
 static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
-				      struct intel_crtc_state *crtc_state)
+				      struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
 	enum pipe pipe = crtc->pipe;
 
 	if ((state->wm_results.dirty_pipes & BIT(crtc->pipe)) == 0)
@@ -5514,10 +5572,11 @@ static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
 }
 
 static void skl_initial_wm(struct intel_atomic_state *state,
-			   struct intel_crtc_state *crtc_state)
+			   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 	struct skl_ddb_values *results = &state->wm_results;
 
 	if ((results->dirty_pipes & BIT(crtc->pipe)) == 0)
@@ -5525,8 +5584,8 @@ static void skl_initial_wm(struct intel_atomic_state *state,
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 
-	if (crtc_state->base.active_changed)
-		skl_atomic_update_crtc_wm(state, crtc_state);
+	if (crtc_state->uapi.active_changed)
+		skl_atomic_update_crtc_wm(state, crtc);
 
 	mutex_unlock(&dev_priv->wm.wm_mutex);
 }
@@ -5582,10 +5641,11 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv)
 }
 
 static void ilk_initial_watermarks(struct intel_atomic_state *state,
-				   struct intel_crtc_state *crtc_state)
+				   struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
 	crtc->wm.active.ilk = crtc_state->wm.ilk.intermediate;
@@ -5594,10 +5654,11 @@ static void ilk_initial_watermarks(struct intel_atomic_state *state,
 }
 
 static void ilk_optimize_watermarks(struct intel_atomic_state *state,
-				    struct intel_crtc_state *crtc_state)
+				    struct intel_crtc *crtc)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct intel_crtc_state *crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
 
 	if (!crtc_state->wm.need_postvbl_update)
 		return;
@@ -5905,19 +5966,22 @@ void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		crtc_state->wm.g4x.optimal = *active;
 		crtc_state->wm.g4x.intermediate = *active;
 
-		DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n",
-			      pipe_name(pipe),
-			      wm->pipe[pipe].plane[PLANE_PRIMARY],
-			      wm->pipe[pipe].plane[PLANE_CURSOR],
-			      wm->pipe[pipe].plane[PLANE_SPRITE0]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite=%d\n",
+			    pipe_name(pipe),
+			    wm->pipe[pipe].plane[PLANE_PRIMARY],
+			    wm->pipe[pipe].plane[PLANE_CURSOR],
+			    wm->pipe[pipe].plane[PLANE_SPRITE0]);
 	}
 
-	DRM_DEBUG_KMS("Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n",
-		      wm->sr.plane, wm->sr.cursor, wm->sr.fbc);
-	DRM_DEBUG_KMS("Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n",
-		      wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc);
-	DRM_DEBUG_KMS("Initial SR=%s HPLL=%s FBC=%s\n",
-		      yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en));
+	drm_dbg_kms(&dev_priv->drm,
+		    "Initial SR watermarks: plane=%d, cursor=%d fbc=%d\n",
+		    wm->sr.plane, wm->sr.cursor, wm->sr.fbc);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Initial HPLL watermarks: plane=%d, SR cursor=%d fbc=%d\n",
+		    wm->hpll.plane, wm->hpll.cursor, wm->hpll.fbc);
+	drm_dbg_kms(&dev_priv->drm, "Initial SR=%s HPLL=%s FBC=%s\n",
+		    yesno(wm->cxsr), yesno(wm->hpll_en), yesno(wm->fbc_en));
 }
 
 void g4x_wm_sanitize(struct drm_i915_private *dev_priv)
@@ -5938,7 +6002,7 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv)
 		enum plane_id plane_id = plane->id;
 		int level;
 
-		if (plane_state->base.visible)
+		if (plane_state->uapi.visible)
 			continue;
 
 		for (level = 0; level < 3; level++) {
@@ -6009,8 +6073,9 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
 
 		if (wait_for((vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2) &
 			      FORCE_DDR_FREQ_REQ_ACK) == 0, 3)) {
-			DRM_DEBUG_KMS("Punit not acking DDR DVFS request, "
-				      "assuming DDR DVFS is disabled\n");
+			drm_dbg_kms(&dev_priv->drm,
+				    "Punit not acking DDR DVFS request, "
+				    "assuming DDR DVFS is disabled\n");
 			dev_priv->wm.max_level = VLV_WM_LEVEL_PM5;
 		} else {
 			val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2);
@@ -6061,16 +6126,18 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		crtc_state->wm.vlv.optimal = *active;
 		crtc_state->wm.vlv.intermediate = *active;
 
-		DRM_DEBUG_KMS("Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite0=%d, sprite1=%d\n",
-			      pipe_name(pipe),
-			      wm->pipe[pipe].plane[PLANE_PRIMARY],
-			      wm->pipe[pipe].plane[PLANE_CURSOR],
-			      wm->pipe[pipe].plane[PLANE_SPRITE0],
-			      wm->pipe[pipe].plane[PLANE_SPRITE1]);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Initial watermarks: pipe %c, plane=%d, cursor=%d, sprite0=%d, sprite1=%d\n",
+			    pipe_name(pipe),
+			    wm->pipe[pipe].plane[PLANE_PRIMARY],
+			    wm->pipe[pipe].plane[PLANE_CURSOR],
+			    wm->pipe[pipe].plane[PLANE_SPRITE0],
+			    wm->pipe[pipe].plane[PLANE_SPRITE1]);
 	}
 
-	DRM_DEBUG_KMS("Initial watermarks: SR plane=%d, SR cursor=%d level=%d cxsr=%d\n",
-		      wm->sr.plane, wm->sr.cursor, wm->level, wm->cxsr);
+	drm_dbg_kms(&dev_priv->drm,
+		    "Initial watermarks: SR plane=%d, SR cursor=%d level=%d cxsr=%d\n",
+		    wm->sr.plane, wm->sr.cursor, wm->level, wm->cxsr);
 }
 
 void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
@@ -6093,7 +6160,7 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv)
 		enum plane_id plane_id = plane->id;
 		int level;
 
-		if (plane_state->base.visible)
+		if (plane_state->uapi.visible)
 			continue;
 
 		for (level = 0; level < wm_state->num_levels; level++) {
@@ -6369,7 +6436,6 @@ static void cpt_init_clock_gating(struct drm_i915_private *dev_priv)
 		val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
 		if (dev_priv->vbt.fdi_rx_polarity_inverted)
 			val |= TRANS_CHICKEN2_FDI_POLARITY_REVERSED;
-		val &= ~TRANS_CHICKEN2_FRAME_START_DELAY_MASK;
 		val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER;
 		val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH;
 		I915_WRITE(TRANS_CHICKEN2(pipe), val);
@@ -6387,8 +6453,9 @@ static void gen6_check_mch_setup(struct drm_i915_private *dev_priv)
 
 	tmp = I915_READ(MCH_SSKPD);
 	if ((tmp & MCH_SSKPD_WM0_MASK) != MCH_SSKPD_WM0_VAL)
-		DRM_DEBUG_KMS("Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
-			      tmp);
+		drm_dbg_kms(&dev_priv->drm,
+			    "Wrong MCH_SSKPD value: 0x%08x This can cause underruns.\n",
+			    tmp);
 }
 
 static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -6583,6 +6650,10 @@ static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
 	u32 vd_pg_enable = 0;
 	unsigned int i;
 
+	/* Wa_1408615072:tgl */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+			 0, VSUNIT_CLKGATE_DIS_TGL);
+
 	/* This is not a WA. Enable VD HCP & MFX_ENC powergate */
 	for (i = 0; i < I915_MAX_VCS; i++) {
 		if (HAS_ENGINE(dev_priv, _VCS(i)))
@@ -7099,7 +7170,8 @@ void intel_suspend_hw(struct drm_i915_private *dev_priv)
 
 static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	DRM_DEBUG_KMS("No clock gating settings or workarounds applied.\n");
+	drm_dbg_kms(&dev_priv->drm,
+		    "No clock gating settings or workarounds applied.\n");
 }
 
 /**
@@ -7166,9 +7238,9 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 {
 	/* For cxsr */
 	if (IS_PINEVIEW(dev_priv))
-		i915_pineview_get_mem_freq(dev_priv);
+		pnv_get_mem_freq(dev_priv);
 	else if (IS_GEN(dev_priv, 5))
-		i915_ironlake_get_mem_freq(dev_priv);
+		ilk_get_mem_freq(dev_priv);
 
 	if (intel_has_sagv(dev_priv))
 		skl_setup_sagv_block_time(dev_priv);
@@ -7194,8 +7266,9 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 			dev_priv->display.optimize_watermarks =
 				ilk_optimize_watermarks;
 		} else {
-			DRM_DEBUG_KMS("Failed to read display plane latency. "
-				      "Disable CxSR\n");
+			drm_dbg_kms(&dev_priv->drm,
+				    "Failed to read display plane latency. "
+				    "Disable CxSR\n");
 		}
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		vlv_setup_wm_latency(dev_priv);
@@ -7215,7 +7288,8 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 					    dev_priv->is_ddr3,
 					    dev_priv->fsb_freq,
 					    dev_priv->mem_freq)) {
-			DRM_INFO("failed to find known CxSR latency "
+			drm_info(&dev_priv->drm,
+				 "failed to find known CxSR latency "
 				 "(found ddr%s fsb freq %d, mem freq %d), "
 				 "disabling CxSR\n",
 				 (dev_priv->is_ddr3 == 1) ? "3" : "2",
@@ -7224,7 +7298,7 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 			intel_set_memory_cxsr(dev_priv, false);
 			dev_priv->display.update_wm = NULL;
 		} else
-			dev_priv->display.update_wm = pineview_update_wm;
+			dev_priv->display.update_wm = pnv_update_wm;
 	} else if (IS_GEN(dev_priv, 4)) {
 		dev_priv->display.update_wm = i965_update_wm;
 	} else if (IS_GEN(dev_priv, 3)) {
@@ -7239,7 +7313,8 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 			dev_priv->display.get_fifo_size = i830_get_fifo_size;
 		}
 	} else {
-		DRM_ERROR("unexpected fall-through in intel_init_pm\n");
+		drm_err(&dev_priv->drm,
+			"unexpected fall-through in %s\n", __func__);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index b579c724b915..c06c6a846d9a 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -54,7 +54,7 @@ void skl_write_plane_wm(struct intel_plane *plane,
 			const struct intel_crtc_state *crtc_state);
 void skl_write_cursor_wm(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state);
-bool ilk_disable_lp_wm(struct drm_device *dev);
+bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv);
 void intel_init_ipc(struct drm_i915_private *dev_priv);
 void intel_enable_ipc(struct drm_i915_private *dev_priv);
 
diff --git a/drivers/gpu/drm/i915/intel_region_lmem.c b/drivers/gpu/drm/i915/intel_region_lmem.c
index 583118095635..14b59b899c9b 100644
--- a/drivers/gpu/drm/i915/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/intel_region_lmem.c
@@ -51,8 +51,10 @@ static int init_fake_lmem_bar(struct intel_memory_region *mem)
 
 static void release_fake_lmem_bar(struct intel_memory_region *mem)
 {
-	if (drm_mm_node_allocated(&mem->fake_mappable))
-		drm_mm_remove_node(&mem->fake_mappable);
+	if (!drm_mm_node_allocated(&mem->fake_mappable))
+		return;
+
+	drm_mm_remove_node(&mem->fake_mappable);
 
 	dma_unmap_resource(&mem->i915->drm.pdev->dev,
 			   mem->remap_addr,
@@ -88,6 +90,8 @@ region_lmem_init(struct intel_memory_region *mem)
 	if (ret)
 		io_mapping_fini(&mem->iomap);
 
+	intel_memory_region_set_name(mem, "local");
+
 	return ret;
 }
 
@@ -121,10 +125,12 @@ intel_setup_fake_lmem(struct drm_i915_private *i915)
 					 io_start,
 					 &intel_region_lmem_ops);
 	if (!IS_ERR(mem)) {
-		DRM_INFO("Intel graphics fake LMEM: %pR\n", &mem->region);
-		DRM_INFO("Intel graphics fake LMEM IO start: %llx\n",
-			 (u64)mem->io_start);
-		DRM_INFO("Intel graphics fake LMEM size: %llx\n",
+		drm_info(&i915->drm, "Intel graphics fake LMEM: %pR\n",
+			 &mem->region);
+		drm_info(&i915->drm,
+			 "Intel graphics fake LMEM IO start: %llx\n",
+			(u64)mem->io_start);
+		drm_info(&i915->drm, "Intel graphics fake LMEM size: %llx\n",
 			 (u64)resource_size(&mem->region));
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c
index e06b35b844a0..cbfb7171d62d 100644
--- a/drivers/gpu/drm/i915/intel_sideband.c
+++ b/drivers/gpu/drm/i915/intel_sideband.c
@@ -105,8 +105,8 @@ static int vlv_sideband_rw(struct drm_i915_private *i915,
 	if (intel_wait_for_register(uncore,
 				    VLV_IOSF_DOORBELL_REQ, IOSF_SB_BUSY, 0,
 				    5)) {
-		DRM_DEBUG_DRIVER("IOSF sideband idle wait (%s) timed out\n",
-				 is_read ? "read" : "write");
+		drm_dbg(&i915->drm, "IOSF sideband idle wait (%s) timed out\n",
+			is_read ? "read" : "write");
 		return -EAGAIN;
 	}
 
@@ -129,8 +129,8 @@ static int vlv_sideband_rw(struct drm_i915_private *i915,
 			*val = intel_uncore_read_fw(uncore, VLV_IOSF_DATA);
 		err = 0;
 	} else {
-		DRM_DEBUG_DRIVER("IOSF sideband finish wait (%s) timed out\n",
-				 is_read ? "read" : "write");
+		drm_dbg(&i915->drm, "IOSF sideband finish wait (%s) timed out\n",
+			is_read ? "read" : "write");
 		err = -ETIMEDOUT;
 	}
 
@@ -283,7 +283,8 @@ static int intel_sbi_rw(struct drm_i915_private *i915, u16 reg,
 	if (intel_wait_for_register_fw(uncore,
 				       SBI_CTL_STAT, SBI_BUSY, 0,
 				       100)) {
-		DRM_ERROR("timeout waiting for SBI to become ready\n");
+		drm_err(&i915->drm,
+			"timeout waiting for SBI to become ready\n");
 		return -EBUSY;
 	}
 
@@ -301,12 +302,13 @@ static int intel_sbi_rw(struct drm_i915_private *i915, u16 reg,
 	if (__intel_wait_for_register_fw(uncore,
 					 SBI_CTL_STAT, SBI_BUSY, 0,
 					 100, 100, &cmd)) {
-		DRM_ERROR("timeout waiting for SBI to complete read\n");
+		drm_err(&i915->drm,
+			"timeout waiting for SBI to complete read\n");
 		return -ETIMEDOUT;
 	}
 
 	if (cmd & SBI_RESPONSE_FAIL) {
-		DRM_ERROR("error during SBI read of reg %x\n", reg);
+		drm_err(&i915->drm, "error during SBI read of reg %x\n", reg);
 		return -ENXIO;
 	}
 
@@ -426,8 +428,9 @@ int sandybridge_pcode_read(struct drm_i915_private *i915, u32 mbox,
 	mutex_unlock(&i915->sb_lock);
 
 	if (err) {
-		DRM_DEBUG_DRIVER("warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
-				 mbox, __builtin_return_address(0), err);
+		drm_dbg(&i915->drm,
+			"warning: pcode (read from mbox %x) mailbox access failed for %ps: %d\n",
+			mbox, __builtin_return_address(0), err);
 	}
 
 	return err;
@@ -447,8 +450,9 @@ int sandybridge_pcode_write_timeout(struct drm_i915_private *i915,
 	mutex_unlock(&i915->sb_lock);
 
 	if (err) {
-		DRM_DEBUG_DRIVER("warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
-				 val, mbox, __builtin_return_address(0), err);
+		drm_dbg(&i915->drm,
+			"warning: pcode (write of 0x%08x to mbox %x) mailbox access failed for %ps: %d\n",
+			val, mbox, __builtin_return_address(0), err);
 	}
 
 	return err;
@@ -519,7 +523,8 @@ int skl_pcode_request(struct drm_i915_private *i915, u32 mbox, u32 request,
 	 * requests, and for any quirks of the PCODE firmware that delays
 	 * the request completion.
 	 */
-	DRM_DEBUG_KMS("PCODE timeout, retrying with preemption disabled\n");
+	drm_dbg_kms(&i915->drm,
+		    "PCODE timeout, retrying with preemption disabled\n");
 	WARN_ON_ONCE(timeout_base_ms > 3);
 	preempt_disable();
 	ret = wait_for_atomic(COND, 50);
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 94a97bf8c021..5f2cf6f43b8b 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -359,7 +359,8 @@ static void __gen6_gt_wait_for_fifo(struct intel_uncore *uncore)
 		if (wait_for_atomic((n = fifo_free_entries(uncore)) >
 				    GT_FIFO_NUM_RESERVED_ENTRIES,
 				    GT_FIFO_TIMEOUT_MS)) {
-			DRM_DEBUG("GT_FIFO timeout, entries: %u\n", n);
+			drm_dbg(&uncore->i915->drm,
+				"GT_FIFO timeout, entries: %u\n", n);
 			return;
 		}
 	}
@@ -432,7 +433,7 @@ intel_uncore_forcewake_reset(struct intel_uncore *uncore)
 			break;
 
 		if (--retry_count == 0) {
-			DRM_ERROR("Timed out waiting for forcewake timers to finish\n");
+			drm_err(&uncore->i915->drm, "Timed out waiting for forcewake timers to finish\n");
 			break;
 		}
 
@@ -490,7 +491,7 @@ gen6_check_for_fifo_debug(struct intel_uncore *uncore)
 	fifodbg = __raw_uncore_read32(uncore, GTFIFODBG);
 
 	if (unlikely(fifodbg)) {
-		DRM_DEBUG_DRIVER("GTFIFODBG = 0x08%x\n", fifodbg);
+		drm_dbg(&uncore->i915->drm, "GTFIFODBG = 0x08%x\n", fifodbg);
 		__raw_uncore_write32(uncore, GTFIFODBG, fifodbg);
 	}
 
@@ -562,7 +563,7 @@ void intel_uncore_resume_early(struct intel_uncore *uncore)
 	unsigned int restore_forcewake;
 
 	if (intel_uncore_unclaimed_mmio(uncore))
-		DRM_DEBUG("unclaimed mmio detected on resume, clearing\n");
+		drm_dbg(&uncore->i915->drm, "unclaimed mmio detected on resume, clearing\n");
 
 	if (!intel_uncore_has_forcewake(uncore))
 		return;
@@ -1595,8 +1596,8 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore)
 		spin_unlock_irq(&uncore->lock);
 
 		if (!(ecobus & FORCEWAKE_MT_ENABLE)) {
-			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
-			DRM_INFO("when using vblank-synced partial screen updates.\n");
+			drm_info(&i915->drm, "No MT forcewake available on Ivybridge, this can result in issues\n");
+			drm_info(&i915->drm, "when using vblank-synced partial screen updates.\n");
 			fw_domain_fini(uncore, FW_DOMAIN_ID_RENDER);
 			fw_domain_init(uncore, FW_DOMAIN_ID_RENDER,
 				       FORCEWAKE, FORCEWAKE_ACK);
@@ -1683,8 +1684,7 @@ static int uncore_mmio_setup(struct intel_uncore *uncore)
 		mmio_size = 2 * 1024 * 1024;
 	uncore->regs = pci_iomap(pdev, mmio_bar, mmio_size);
 	if (uncore->regs == NULL) {
-		DRM_ERROR("failed to map registers\n");
-
+		drm_err(&i915->drm, "failed to map registers\n");
 		return -EIO;
 	}
 
@@ -1807,7 +1807,7 @@ int intel_uncore_init_mmio(struct intel_uncore *uncore)
 
 	/* clear out unclaimed reg detection bit */
 	if (intel_uncore_unclaimed_mmio(uncore))
-		DRM_DEBUG("unclaimed mmio detected on uncore init, clearing\n");
+		drm_dbg(&i915->drm, "unclaimed mmio detected on uncore init, clearing\n");
 
 	return 0;
 
@@ -2072,9 +2072,10 @@ intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore)
 
 	if (unlikely(check_for_unclaimed_mmio(uncore))) {
 		if (!i915_modparams.mmio_debug) {
-			DRM_DEBUG("Unclaimed register detected, "
-				  "enabling oneshot unclaimed register reporting. "
-				  "Please use i915.mmio_debug=N for more information.\n");
+			drm_dbg(&uncore->i915->drm,
+				"Unclaimed register detected, "
+				"enabling oneshot unclaimed register reporting. "
+				"Please use i915.mmio_debug=N for more information.\n");
 			i915_modparams.mmio_debug++;
 		}
 		uncore->debug->unclaimed_mmio_check--;
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 59aa1b6f1827..8fbf6f4d3f26 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -95,16 +95,17 @@ static void __intel_wakeref_put_work(struct work_struct *wrk)
 void __intel_wakeref_init(struct intel_wakeref *wf,
 			  struct intel_runtime_pm *rpm,
 			  const struct intel_wakeref_ops *ops,
-			  struct lock_class_key *key)
+			  struct intel_wakeref_lockclass *key)
 {
 	wf->rpm = rpm;
 	wf->ops = ops;
 
-	__mutex_init(&wf->mutex, "wakeref", key);
+	__mutex_init(&wf->mutex, "wakeref.mutex", &key->mutex);
 	atomic_set(&wf->count, 0);
 	wf->wakeref = 0;
 
 	INIT_WORK(&wf->work, __intel_wakeref_put_work);
+	lockdep_init_map(&wf->work.lockdep_map, "wakeref.work", &key->work, 0);
 }
 
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index da6e8fd506e6..7d1e676b71ef 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -44,12 +44,17 @@ struct intel_wakeref {
 	struct work_struct work;
 };
 
+struct intel_wakeref_lockclass {
+	struct lock_class_key mutex;
+	struct lock_class_key work;
+};
+
 void __intel_wakeref_init(struct intel_wakeref *wf,
 			  struct intel_runtime_pm *rpm,
 			  const struct intel_wakeref_ops *ops,
-			  struct lock_class_key *key);
+			  struct intel_wakeref_lockclass *key);
 #define intel_wakeref_init(wf, rpm, ops) do {				\
-	static struct lock_class_key __key;				\
+	static struct intel_wakeref_lockclass __key;			\
 									\
 	__intel_wakeref_init((wf), (rpm), (ops), &__key);		\
 } while (0)
@@ -59,9 +64,7 @@ void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags);
 
 /**
  * intel_wakeref_get: Acquire the wakeref
- * @i915: the drm_i915_private device
  * @wf: the wakeref
- * @fn: callback for acquired the wakeref, called only on first acquire.
  *
  * Acquire a hold on the wakeref. The first user to do so, will acquire
  * the runtime pm wakeref and then call the @fn underneath the wakeref
@@ -76,6 +79,7 @@ void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags);
 static inline int
 intel_wakeref_get(struct intel_wakeref *wf)
 {
+	might_sleep();
 	if (unlikely(!atomic_inc_not_zero(&wf->count)))
 		return __intel_wakeref_get_first(wf);
 
@@ -83,6 +87,22 @@ intel_wakeref_get(struct intel_wakeref *wf)
 }
 
 /**
+ * __intel_wakeref_get: Acquire the wakeref, again
+ * @wf: the wakeref
+ *
+ * Increment the wakeref counter, only valid if it is already held by
+ * the caller.
+ *
+ * See intel_wakeref_get().
+ */
+static inline void
+__intel_wakeref_get(struct intel_wakeref *wf)
+{
+	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
+	atomic_inc(&wf->count);
+}
+
+/**
  * intel_wakeref_get_if_in_use: Acquire the wakeref
  * @wf: the wakeref
  *
diff --git a/drivers/gpu/drm/i915/oa/Makefile b/drivers/gpu/drm/i915/oa/Makefile
deleted file mode 100644
index df028e2b0d64..000000000000
--- a/drivers/gpu/drm/i915/oa/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: MIT
-
-# For building individual subdir files on the command line
-subdir-ccflags-y += -I$(srctree)/$(src)/..
-
-# Extra header tests
-header-test-pattern-$(CONFIG_DRM_I915_WERROR) := *.h
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 260b0ee5d1e3..ef572a0c2566 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -99,7 +99,7 @@ __live_active_setup(struct drm_i915_private *i915)
 	for_each_uabi_engine(engine, i915) {
 		struct i915_request *rq;
 
-		rq = i915_request_create(engine->kernel_context);
+		rq = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			break;
@@ -155,7 +155,11 @@ static int live_active_wait(void *arg)
 
 	i915_active_wait(&active->base);
 	if (!READ_ONCE(active->retired)) {
+		struct drm_printer p = drm_err_printer(__func__);
+
 		pr_err("i915_active not retired after waiting!\n");
+		i915_active_print(&active->base, &p);
+
 		err = -EINVAL;
 	}
 
@@ -184,7 +188,11 @@ static int live_active_retire(void *arg)
 		err = -EIO;
 
 	if (!READ_ONCE(active->retired)) {
+		struct drm_printer p = drm_err_printer(__func__);
+
 		pr_err("i915_active not retired after flushing!\n");
+		i915_active_print(&active->base, &p);
+
 		err = -EINVAL;
 	}
 
@@ -250,3 +258,36 @@ void i915_active_print(struct i915_active *ref, struct drm_printer *m)
 		i915_active_release(ref);
 	}
 }
+
+static void spin_unlock_wait(spinlock_t *lock)
+{
+	spin_lock_irq(lock);
+	spin_unlock_irq(lock);
+}
+
+void i915_active_unlock_wait(struct i915_active *ref)
+{
+	if (i915_active_acquire_if_busy(ref)) {
+		struct active_node *it, *n;
+
+		rcu_read_lock();
+		rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
+			struct dma_fence *f;
+
+			/* Wait for all active callbacks */
+			f = rcu_dereference(it->base.fence);
+			if (f)
+				spin_unlock_wait(f->lock);
+		}
+		rcu_read_unlock();
+
+		i915_active_release(ref);
+	}
+
+	/* And wait for the retire callback */
+	spin_lock_irq(&ref->tree_lock);
+	spin_unlock_irq(&ref->tree_lock);
+
+	/* ... which may have been on a thread instead */
+	flush_work(&ref->work);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index d83f6bf6d9d4..78f36faf2bbe 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -9,6 +9,7 @@
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
 
 #include "i915_selftest.h"
 
@@ -123,8 +124,6 @@ static void pm_resume(struct drm_i915_private *i915)
 	 * that runtime-pm just works.
 	 */
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-		intel_gt_sanitize(&i915->gt, false);
-
 		i915_gem_restore_gtt_mappings(i915);
 		i915_gem_restore_fences(&i915->ggtt);
 
@@ -136,7 +135,7 @@ static int igt_gem_suspend(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx;
-	struct drm_file *file;
+	struct file *file;
 	int err;
 
 	file = mock_file(i915);
@@ -163,7 +162,7 @@ static int igt_gem_suspend(void *arg)
 
 	err = switch_to_context(ctx);
 out:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -171,7 +170,7 @@ static int igt_gem_hibernate(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_gem_context *ctx;
-	struct drm_file *file;
+	struct file *file;
 	int err;
 
 	file = mock_file(i915);
@@ -198,7 +197,7 @@ static int igt_gem_hibernate(void *arg)
 
 	err = switch_to_context(ctx);
 out:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 42e948144f1b..06ef88510209 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -198,8 +198,8 @@ static int igt_overcommit(void *arg)
 	quirk_add(obj, &objects);
 
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
-	if (!IS_ERR(vma) || PTR_ERR(vma) != -ENOSPC) {
-		pr_err("Failed to evict+insert, i915_gem_object_ggtt_pin returned err=%d\n", (int)PTR_ERR(vma));
+	if (vma != ERR_PTR(-ENOSPC)) {
+		pr_err("Failed to evict+insert, i915_gem_object_ggtt_pin returned err=%d\n", (int)PTR_ERR_OR_ZERO(vma));
 		err = -EINVAL;
 		goto cleanup;
 	}
@@ -466,7 +466,7 @@ static int igt_evict_contexts(void *arg)
 	/* Overfill the GGTT with context objects and so try to evict one. */
 	for_each_engine(engine, gt, id) {
 		struct i915_sw_fence fence;
-		struct drm_file *file;
+		struct file *file;
 
 		file = mock_file(i915);
 		if (IS_ERR(file)) {
@@ -515,7 +515,7 @@ static int igt_evict_contexts(void *arg)
 		pr_info("Submitted %lu contexts/requests on %s\n",
 			count, engine->name);
 
-		mock_file_free(i915, file);
+		fput(file);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 3f7e80fb3bbd..b342bef5e7c9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -34,6 +34,7 @@
 
 #include "mock_drm.h"
 #include "mock_gem_device.h"
+#include "mock_gtt.h"
 #include "igt_flush_test.h"
 
 static void cleanup_freed_objects(struct drm_i915_private *i915)
@@ -151,7 +152,7 @@ static int igt_ppgtt_alloc(void *arg)
 	if (!HAS_PPGTT(dev_priv))
 		return 0;
 
-	ppgtt = __ppgtt_create(dev_priv);
+	ppgtt = i915_ppgtt_create(&dev_priv->gt);
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -206,16 +207,17 @@ err_ppgtt_cleanup:
 	return err;
 }
 
-static int lowlevel_hole(struct drm_i915_private *i915,
-			 struct i915_address_space *vm,
+static int lowlevel_hole(struct i915_address_space *vm,
 			 u64 hole_start, u64 hole_end,
 			 unsigned long end_time)
 {
 	I915_RND_STATE(seed_prng);
+	struct i915_vma *mock_vma;
 	unsigned int size;
-	struct i915_vma mock_vma;
 
-	memset(&mock_vma, 0, sizeof(struct i915_vma));
+	mock_vma = kzalloc(sizeof(*mock_vma), GFP_KERNEL);
+	if (!mock_vma)
+		return -ENOMEM;
 
 	/* Keep creating larger objects until one cannot fit into the hole */
 	for (size = 12; (hole_end - hole_start) >> size; size++) {
@@ -239,8 +241,10 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			if (order)
 				break;
 		} while (count >>= 1);
-		if (!count)
+		if (!count) {
+			kfree(mock_vma);
 			return -ENOMEM;
+		}
 		GEM_BUG_ON(!order);
 
 		GEM_BUG_ON(count * BIT_ULL(size) > vm->total);
@@ -252,7 +256,7 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 		 * memory. We expect to hit -ENOMEM.
 		 */
 
-		obj = fake_dma_object(i915, BIT_ULL(size));
+		obj = fake_dma_object(vm->i915, BIT_ULL(size));
 		if (IS_ERR(obj)) {
 			kfree(order);
 			break;
@@ -283,12 +287,12 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			    vm->allocate_va_range(vm, addr, BIT_ULL(size)))
 				break;
 
-			mock_vma.pages = obj->mm.pages;
-			mock_vma.node.size = BIT_ULL(size);
-			mock_vma.node.start = addr;
+			mock_vma->pages = obj->mm.pages;
+			mock_vma->node.size = BIT_ULL(size);
+			mock_vma->node.start = addr;
 
-			with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-				vm->insert_entries(vm, &mock_vma,
+			with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref)
+				vm->insert_entries(vm, mock_vma,
 						   I915_CACHE_NONE, 0);
 		}
 		count = n;
@@ -299,7 +303,7 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			intel_wakeref_t wakeref;
 
 			GEM_BUG_ON(addr + BIT_ULL(size) > vm->total);
-			with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+			with_intel_runtime_pm(vm->gt->uncore->rpm, wakeref)
 				vm->clear_range(vm, addr, BIT_ULL(size));
 		}
 
@@ -308,9 +312,10 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 
 		kfree(order);
 
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
+	kfree(mock_vma);
 	return 0;
 }
 
@@ -335,8 +340,7 @@ static void close_object_list(struct list_head *objects,
 	}
 }
 
-static int fill_hole(struct drm_i915_private *i915,
-		     struct i915_address_space *vm,
+static int fill_hole(struct i915_address_space *vm,
 		     u64 hole_start, u64 hole_end,
 		     unsigned long end_time)
 {
@@ -369,7 +373,7 @@ static int fill_hole(struct drm_i915_private *i915,
 				{ }
 			}, *p;
 
-			obj = fake_dma_object(i915, full_size);
+			obj = fake_dma_object(vm->i915, full_size);
 			if (IS_ERR(obj))
 				break;
 
@@ -537,7 +541,7 @@ static int fill_hole(struct drm_i915_private *i915,
 		}
 
 		close_object_list(&objects, vm);
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
@@ -547,8 +551,7 @@ err:
 	return err;
 }
 
-static int walk_hole(struct drm_i915_private *i915,
-		     struct i915_address_space *vm,
+static int walk_hole(struct i915_address_space *vm,
 		     u64 hole_start, u64 hole_end,
 		     unsigned long end_time)
 {
@@ -570,7 +573,7 @@ static int walk_hole(struct drm_i915_private *i915,
 		u64 addr;
 		int err = 0;
 
-		obj = fake_dma_object(i915, size << PAGE_SHIFT);
+		obj = fake_dma_object(vm->i915, size << PAGE_SHIFT);
 		if (IS_ERR(obj))
 			break;
 
@@ -625,14 +628,13 @@ err_put:
 		if (err)
 			return err;
 
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
 }
 
-static int pot_hole(struct drm_i915_private *i915,
-		    struct i915_address_space *vm,
+static int pot_hole(struct i915_address_space *vm,
 		    u64 hole_start, u64 hole_end,
 		    unsigned long end_time)
 {
@@ -646,7 +648,7 @@ static int pot_hole(struct drm_i915_private *i915,
 	if (i915_is_ggtt(vm))
 		flags |= PIN_GLOBAL;
 
-	obj = i915_gem_object_create_internal(i915, 2 * I915_GTT_PAGE_SIZE);
+	obj = i915_gem_object_create_internal(vm->i915, 2 * I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -707,8 +709,7 @@ err_obj:
 	return err;
 }
 
-static int drunk_hole(struct drm_i915_private *i915,
-		      struct i915_address_space *vm,
+static int drunk_hole(struct i915_address_space *vm,
 		      u64 hole_start, u64 hole_end,
 		      unsigned long end_time)
 {
@@ -753,7 +754,7 @@ static int drunk_hole(struct drm_i915_private *i915,
 		 * memory. We expect to hit -ENOMEM.
 		 */
 
-		obj = fake_dma_object(i915, BIT_ULL(size));
+		obj = fake_dma_object(vm->i915, BIT_ULL(size));
 		if (IS_ERR(obj)) {
 			kfree(order);
 			break;
@@ -811,14 +812,13 @@ err_obj:
 		if (err)
 			return err;
 
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
 }
 
-static int __shrink_hole(struct drm_i915_private *i915,
-			 struct i915_address_space *vm,
+static int __shrink_hole(struct i915_address_space *vm,
 			 u64 hole_start, u64 hole_end,
 			 unsigned long end_time)
 {
@@ -835,7 +835,7 @@ static int __shrink_hole(struct drm_i915_private *i915,
 		u64 size = BIT_ULL(order++);
 
 		size = min(size, hole_end - addr);
-		obj = fake_dma_object(i915, size);
+		obj = fake_dma_object(vm->i915, size);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
 			break;
@@ -889,12 +889,11 @@ static int __shrink_hole(struct drm_i915_private *i915,
 	}
 
 	close_object_list(&objects, vm);
-	cleanup_freed_objects(i915);
+	cleanup_freed_objects(vm->i915);
 	return err;
 }
 
-static int shrink_hole(struct drm_i915_private *i915,
-		       struct i915_address_space *vm,
+static int shrink_hole(struct i915_address_space *vm,
 		       u64 hole_start, u64 hole_end,
 		       unsigned long end_time)
 {
@@ -906,7 +905,7 @@ static int shrink_hole(struct drm_i915_private *i915,
 
 	for_each_prime_number_from(prime, 0, ULONG_MAX - 1) {
 		vm->fault_attr.interval = prime;
-		err = __shrink_hole(i915, vm, hole_start, hole_end, end_time);
+		err = __shrink_hole(vm, hole_start, hole_end, end_time);
 		if (err)
 			break;
 	}
@@ -916,8 +915,7 @@ static int shrink_hole(struct drm_i915_private *i915,
 	return err;
 }
 
-static int shrink_boom(struct drm_i915_private *i915,
-		       struct i915_address_space *vm,
+static int shrink_boom(struct i915_address_space *vm,
 		       u64 hole_start, u64 hole_end,
 		       unsigned long end_time)
 {
@@ -939,7 +937,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		unsigned int size = sizes[i];
 		struct i915_vma *vma;
 
-		purge = fake_dma_object(i915, size);
+		purge = fake_dma_object(vm->i915, size);
 		if (IS_ERR(purge))
 			return PTR_ERR(purge);
 
@@ -956,7 +954,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		/* Should now be ripe for purging */
 		i915_vma_unpin(vma);
 
-		explode = fake_dma_object(i915, size);
+		explode = fake_dma_object(vm->i915, size);
 		if (IS_ERR(explode)) {
 			err = PTR_ERR(explode);
 			goto err_purge;
@@ -982,7 +980,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		i915_gem_object_put(explode);
 
 		memset(&vm->fault_attr, 0, sizeof(vm->fault_attr));
-		cleanup_freed_objects(i915);
+		cleanup_freed_objects(vm->i915);
 	}
 
 	return 0;
@@ -996,14 +994,13 @@ err_purge:
 }
 
 static int exercise_ppgtt(struct drm_i915_private *dev_priv,
-			  int (*func)(struct drm_i915_private *i915,
-				      struct i915_address_space *vm,
+			  int (*func)(struct i915_address_space *vm,
 				      u64 hole_start, u64 hole_end,
 				      unsigned long end_time))
 {
-	struct drm_file *file;
 	struct i915_ppgtt *ppgtt;
 	IGT_TIMEOUT(end_time);
+	struct file *file;
 	int err;
 
 	if (!HAS_FULL_PPGTT(dev_priv))
@@ -1013,7 +1010,7 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ppgtt = i915_ppgtt_create(dev_priv);
+	ppgtt = i915_ppgtt_create(&dev_priv->gt);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_free;
@@ -1021,12 +1018,12 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 	GEM_BUG_ON(offset_in_page(ppgtt->vm.total));
 	GEM_BUG_ON(!atomic_read(&ppgtt->vm.open));
 
-	err = func(dev_priv, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
+	err = func(&ppgtt->vm, 0, ppgtt->vm.total, end_time);
 
 	i915_vm_put(&ppgtt->vm);
 
 out_free:
-	mock_file_free(dev_priv, file);
+	fput(file);
 	return err;
 }
 
@@ -1077,8 +1074,7 @@ static int sort_holes(void *priv, struct list_head *A, struct list_head *B)
 }
 
 static int exercise_ggtt(struct drm_i915_private *i915,
-			 int (*func)(struct drm_i915_private *i915,
-				     struct i915_address_space *vm,
+			 int (*func)(struct i915_address_space *vm,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
@@ -1100,7 +1096,7 @@ restart:
 		if (hole_start >= hole_end)
 			continue;
 
-		err = func(i915, &ggtt->vm, hole_start, hole_end, end_time);
+		err = func(&ggtt->vm, hole_start, hole_end, end_time);
 		if (err)
 			break;
 
@@ -1161,11 +1157,13 @@ static int igt_ggtt_page(void *arg)
 		goto out_free;
 
 	memset(&tmp, 0, sizeof(tmp));
+	mutex_lock(&ggtt->vm.mutex);
 	err = drm_mm_insert_node_in_range(&ggtt->vm.mm, &tmp,
 					  count * PAGE_SIZE, 0,
 					  I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
 					  DRM_MM_INSERT_LOW);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err)
 		goto out_unpin;
 
@@ -1217,7 +1215,9 @@ static int igt_ggtt_page(void *arg)
 out_remove:
 	ggtt->vm.clear_range(&ggtt->vm, tmp.start, tmp.size);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	mutex_lock(&ggtt->vm.mutex);
 	drm_mm_remove_node(&tmp);
+	mutex_unlock(&ggtt->vm.mutex);
 out_unpin:
 	i915_gem_object_unpin_pages(obj);
 out_free:
@@ -1243,8 +1243,7 @@ static void track_vma_bind(struct i915_vma *vma)
 }
 
 static int exercise_mock(struct drm_i915_private *i915,
-			 int (*func)(struct drm_i915_private *i915,
-				     struct i915_address_space *vm,
+			 int (*func)(struct i915_address_space *vm,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
@@ -1259,7 +1258,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 		return -ENOMEM;
 
 	vm = i915_gem_context_get_vm_rcu(ctx);
-	err = func(i915, vm, 0, min(vm->total, limit), end_time);
+	err = func(vm, 0, min(vm->total, limit), end_time);
 	i915_vm_put(vm);
 
 	mock_context_close(ctx);
@@ -1782,9 +1781,9 @@ static int igt_cs_tlb(void *arg)
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
-	struct drm_file *file;
 	struct i915_vma *vma;
 	I915_RND_STATE(prng);
+	struct file *file;
 	unsigned int i;
 	u32 *result;
 	u32 *batch;
@@ -2022,7 +2021,7 @@ out_put_bbe:
 out_vm:
 	i915_vm_put(vm);
 out_unlock:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 4b3cac73e291..34138c7bdd15 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -1,5 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* List each unit test as selftest(name, function)
+
+#ifndef selftest
+#define selftest(x, y)
+#endif
+
+/*
+ * List each unit test as selftest(name, function)
  *
  * The name is used as both an enum and expanded as subtest__name to create
  * a module parameter. It must be unique and legal for a C identifier.
@@ -16,6 +22,7 @@ selftest(gt_engines, intel_engine_live_selftests)
 selftest(gt_timelines, intel_timeline_live_selftests)
 selftest(gt_contexts, intel_context_live_selftests)
 selftest(gt_lrc, intel_lrc_live_selftests)
+selftest(gt_mocs, intel_mocs_live_selftests)
 selftest(gt_pm, intel_gt_pm_live_selftests)
 selftest(gt_heartbeat, intel_heartbeat_live_selftests)
 selftest(requests, i915_request_live_selftests)
@@ -36,5 +43,6 @@ selftest(reset, intel_reset_live_selftests)
 selftest(memory_region, intel_memory_region_live_selftests)
 selftest(hangcheck, intel_hangcheck_live_selftests)
 selftest(execlists, intel_execlists_live_selftests)
-selftest(guc, intel_guc_live_selftest)
 selftest(perf, i915_perf_live_selftests)
+/* Here be dragons: keep last to run last! */
+selftest(late_gt_pm, intel_gt_pm_late_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index aa5a0e7f5d9e..5b39bab4da1d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -1,5 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* List each unit test as selftest(name, function)
+
+#ifndef selftest
+#define selftest(x, y)
+#endif
+
+/*
+ * List each unit test as selftest(name, function)
  *
  * The name is used as both an enum and expanded as subtest__name to create
  * a module parameter. It must be unique and legal for a C identifier.
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index aabd07f67e49..d1a1568c47ba 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -132,7 +132,7 @@ static int live_noa_delay(void *arg)
 	for (i = 0; i < 4; i++)
 		intel_write_status_page(stream->engine, 0x100 + i, 0);
 
-	rq = i915_request_create(stream->engine->kernel_context);
+	rq = intel_engine_create_kernel_request(stream->engine);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto out;
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
new file mode 100644
index 000000000000..5a577a1332f5
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_perf_selftests.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef selftest
+#define selftest(x, y)
+#endif
+
+/*
+ * List each unit test as selftest(name, function)
+ *
+ * The name is used as both an enum and expanded as subtest__name to create
+ * a module parameter. It must be unique and legal for a C identifier.
+ *
+ * The function should be of type int function(void). It may be conditionally
+ * compiled using #if IS_ENABLED(DRM_I915_SELFTEST).
+ *
+ * Tests are executed in order by igt/i915_selftest
+ */
+selftest(engine_cs, intel_engine_cs_perf_selftests)
+selftest(blt, i915_gem_object_blt_perf_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 8618a4dc0701..f89d9c42f1fa 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -27,11 +27,13 @@
 #include "gem/i915_gem_pm.h"
 #include "gem/selftests/mock_context.h"
 
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 
 #include "i915_random.h"
 #include "i915_selftest.h"
 #include "igt_live_test.h"
+#include "igt_spinner.h"
 #include "lib_sw_fence.h"
 
 #include "mock_drm.h"
@@ -540,6 +542,7 @@ static int live_nop_request(void *arg)
 		if (err)
 			return err;
 
+		intel_engine_pm_get(engine);
 		for_each_prime_number_from(prime, 1, 8192) {
 			struct i915_request *request = NULL;
 
@@ -578,6 +581,7 @@ static int live_nop_request(void *arg)
 			if (__igt_timeout(end_time, NULL))
 				break;
 		}
+		intel_engine_pm_put(engine);
 
 		err = igt_live_test_end(&t);
 		if (err)
@@ -692,10 +696,13 @@ static int live_empty_request(void *arg)
 		if (err)
 			goto out_batch;
 
+		intel_engine_pm_get(engine);
+
 		/* Warmup / preload */
 		request = empty_request(engine, batch);
 		if (IS_ERR(request)) {
 			err = PTR_ERR(request);
+			intel_engine_pm_put(engine);
 			goto out_batch;
 		}
 		i915_request_wait(request, 0, MAX_SCHEDULE_TIMEOUT);
@@ -708,6 +715,7 @@ static int live_empty_request(void *arg)
 				request = empty_request(engine, batch);
 				if (IS_ERR(request)) {
 					err = PTR_ERR(request);
+					intel_engine_pm_put(engine);
 					goto out_batch;
 				}
 			}
@@ -721,6 +729,7 @@ static int live_empty_request(void *arg)
 				break;
 		}
 		i915_request_put(request);
+		intel_engine_pm_put(engine);
 
 		err = igt_live_test_end(&t);
 		if (err)
@@ -740,10 +749,8 @@ out_batch:
 
 static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *ctx = i915->kernel_context;
 	struct drm_i915_gem_object *obj;
 	const int gen = INTEL_GEN(i915);
-	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	u32 *cmd;
 	int err;
@@ -752,9 +759,7 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vm = i915_gem_context_get_vm_rcu(ctx);
-	vma = i915_vma_instance(obj, vm, NULL);
-	i915_vm_put(vm);
+	vma = i915_vma_instance(obj, i915->gt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -845,7 +850,7 @@ static int live_all_engines(void *arg)
 
 	idx = 0;
 	for_each_uabi_engine(engine, i915) {
-		request[idx] = i915_request_create(engine->kernel_context);
+		request[idx] = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(request[idx])) {
 			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed with err=%d\n",
@@ -962,7 +967,7 @@ static int live_sequential_engines(void *arg)
 			goto out_free;
 		}
 
-		request[idx] = i915_request_create(engine->kernel_context);
+		request[idx] = intel_engine_create_kernel_request(engine);
 		if (IS_ERR(request[idx])) {
 			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed for %s with err=%d\n",
@@ -1067,15 +1072,18 @@ static int __live_parallel_engine1(void *arg)
 	struct intel_engine_cs *engine = arg;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
+	int err = 0;
 
 	count = 0;
+	intel_engine_pm_get(engine);
 	do {
 		struct i915_request *rq;
-		int err;
 
 		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
 
 		i915_request_get(rq);
 		i915_request_add(rq);
@@ -1085,13 +1093,14 @@ static int __live_parallel_engine1(void *arg)
 			err = -ETIME;
 		i915_request_put(rq);
 		if (err)
-			return err;
+			break;
 
 		count++;
 	} while (!__igt_timeout(end_time, NULL));
+	intel_engine_pm_put(engine);
 
 	pr_info("%s: %lu request + sync\n", engine->name, count);
-	return 0;
+	return err;
 }
 
 static int __live_parallel_engineN(void *arg)
@@ -1099,21 +1108,100 @@ static int __live_parallel_engineN(void *arg)
 	struct intel_engine_cs *engine = arg;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
+	int err = 0;
 
 	count = 0;
+	intel_engine_pm_get(engine);
 	do {
 		struct i915_request *rq;
 
 		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
 
 		i915_request_add(rq);
 		count++;
 	} while (!__igt_timeout(end_time, NULL));
+	intel_engine_pm_put(engine);
 
 	pr_info("%s: %lu requests\n", engine->name, count);
-	return 0;
+	return err;
+}
+
+static bool wake_all(struct drm_i915_private *i915)
+{
+	if (atomic_dec_and_test(&i915->selftest.counter)) {
+		wake_up_var(&i915->selftest.counter);
+		return true;
+	}
+
+	return false;
+}
+
+static int wait_for_all(struct drm_i915_private *i915)
+{
+	if (wake_all(i915))
+		return 0;
+
+	if (wait_var_event_timeout(&i915->selftest.counter,
+				   !atomic_read(&i915->selftest.counter),
+				   i915_selftest.timeout_jiffies))
+		return 0;
+
+	return -ETIME;
+}
+
+static int __live_parallel_spin(void *arg)
+{
+	struct intel_engine_cs *engine = arg;
+	struct igt_spinner spin;
+	struct i915_request *rq;
+	int err = 0;
+
+	/*
+	 * Create a spinner running for eternity on each engine. If a second
+	 * spinner is incorrectly placed on the same engine, it will not be
+	 * able to start in time.
+	 */
+
+	if (igt_spinner_init(&spin, engine->gt)) {
+		wake_all(engine->i915);
+		return -ENOMEM;
+	}
+
+	intel_engine_pm_get(engine);
+	rq = igt_spinner_create_request(&spin,
+					engine->kernel_context,
+					MI_NOOP); /* no preemption */
+	intel_engine_pm_put(engine);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		if (err == -ENODEV)
+			err = 0;
+		wake_all(engine->i915);
+		goto out_spin;
+	}
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (igt_wait_for_spinner(&spin, rq)) {
+		/* Occupy this engine for the whole test */
+		err = wait_for_all(engine->i915);
+	} else {
+		pr_err("Failed to start spinner on %s\n", engine->name);
+		err = -EINVAL;
+	}
+	igt_spinner_end(&spin);
+
+	if (err == 0 && i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -EIO;
+	i915_request_put(rq);
+
+out_spin:
+	igt_spinner_fini(&spin);
+	return err;
 }
 
 static int live_parallel_engines(void *arg)
@@ -1122,6 +1210,7 @@ static int live_parallel_engines(void *arg)
 	static int (* const func[])(void *arg) = {
 		__live_parallel_engine1,
 		__live_parallel_engineN,
+		__live_parallel_spin,
 		NULL,
 	};
 	const unsigned int nengines = num_uabi_engines(i915);
@@ -1140,13 +1229,17 @@ static int live_parallel_engines(void *arg)
 		return -ENOMEM;
 
 	for (fn = func; !err && *fn; fn++) {
+		char name[KSYM_NAME_LEN];
 		struct igt_live_test t;
 		unsigned int idx;
 
-		err = igt_live_test_begin(&t, i915, __func__, "");
+		snprintf(name, sizeof(name), "%pS", fn);
+		err = igt_live_test_begin(&t, i915, __func__, name);
 		if (err)
 			break;
 
+		atomic_set(&i915->selftest.counter, nengines);
+
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
 			tsk[idx] = kthread_run(*fn, engine,
@@ -1230,9 +1323,9 @@ static int live_breadcrumbs_smoketest(void *arg)
 	struct task_struct **threads;
 	struct igt_live_test live;
 	intel_wakeref_t wakeref;
-	struct drm_file *file;
 	struct smoketest *smoke;
 	unsigned int n, idx;
+	struct file *file;
 	int ret = 0;
 
 	/*
@@ -1354,7 +1447,7 @@ out_threads:
 out_smoke:
 	kfree(smoke);
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 out_rpm:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index a6cca4ad96f6..d3bf9eefb682 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -57,6 +57,12 @@ enum {
 #undef selftest
 };
 
+enum {
+#define selftest(name, func) perf_##name,
+#include "i915_perf_selftests.h"
+#undef selftest
+};
+
 struct selftest {
 	bool enabled;
 	const char *name;
@@ -78,6 +84,12 @@ static struct selftest live_selftests[] = {
 };
 #undef selftest
 
+#define selftest(n, f) [perf_##n] = { .name = #n, { .live = f } },
+static struct selftest perf_selftests[] = {
+#include "i915_perf_selftests.h"
+};
+#undef selftest
+
 /* Embed the line number into the parameter name so that we can order tests */
 #define selftest(n, func) selftest_0(n, func, param(n))
 #define param(n) __PASTE(igt__, __PASTE(__LINE__, __mock_##n))
@@ -93,6 +105,13 @@ module_param_named(id, live_selftests[live_##n].enabled, bool, 0400);
 #include "i915_live_selftests.h"
 #undef selftest_0
 #undef param
+
+#define param(n) __PASTE(igt__, __PASTE(__LINE__, __perf_##n))
+#define selftest_0(n, func, id) \
+module_param_named(id, perf_selftests[perf_##n].enabled, bool, 0400);
+#include "i915_perf_selftests.h"
+#undef selftest_0
+#undef param
 #undef selftest
 
 static void set_default_test_all(struct selftest *st, unsigned int count)
@@ -200,6 +219,27 @@ int i915_live_selftests(struct pci_dev *pdev)
 	return 0;
 }
 
+int i915_perf_selftests(struct pci_dev *pdev)
+{
+	int err;
+
+	if (!i915_selftest.perf)
+		return 0;
+
+	err = run_selftests(perf, pdev_to_i915(pdev));
+	if (err) {
+		i915_selftest.perf = err;
+		return err;
+	}
+
+	if (i915_selftest.perf < 0) {
+		i915_selftest.perf = -ENOTTY;
+		return 1;
+	}
+
+	return 0;
+}
+
 static bool apply_subtest_filter(const char *caller, const char *name)
 {
 	char *filter, *sep, *tok;
@@ -365,3 +405,6 @@ MODULE_PARM_DESC(mock_selftests, "Run selftests before loading, using mock hardw
 
 module_param_named_unsafe(live_selftests, i915_selftest.live, int, 0400);
 MODULE_PARM_DESC(live_selftests, "Run selftests after driver initialisation on the live system (0:disabled [default], 1:run tests then continue, -1:run tests then exit module)");
+
+module_param_named_unsafe(perf_selftests, i915_selftest.perf, int, 0400);
+MODULE_PARM_DESC(perf_selftests, "Run performance orientated selftests after driver initialisation on the live system (0:disabled [default], 1:run tests then continue, -1:run tests then exit module)");
diff --git a/drivers/gpu/drm/i915/selftests/igt_atomic.c b/drivers/gpu/drm/i915/selftests/igt_atomic.c
new file mode 100644
index 000000000000..fb506b699095
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_atomic.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include <linux/preempt.h>
+#include <linux/bottom_half.h>
+#include <linux/irqflags.h>
+
+#include "igt_atomic.h"
+
+static void __preempt_begin(void)
+{
+	preempt_disable();
+}
+
+static void __preempt_end(void)
+{
+	preempt_enable();
+}
+
+static void __softirq_begin(void)
+{
+	local_bh_disable();
+}
+
+static void __softirq_end(void)
+{
+	local_bh_enable();
+}
+
+static void __hardirq_begin(void)
+{
+	local_irq_disable();
+}
+
+static void __hardirq_end(void)
+{
+	local_irq_enable();
+}
+
+const struct igt_atomic_section igt_atomic_phases[] = {
+	{ "preempt", __preempt_begin, __preempt_end },
+	{ "softirq", __softirq_begin, __softirq_end },
+	{ "hardirq", __hardirq_begin, __hardirq_end },
+	{ }
+};
diff --git a/drivers/gpu/drm/i915/selftests/igt_atomic.h b/drivers/gpu/drm/i915/selftests/igt_atomic.h
index 93ec89f487ec..1991798abf4b 100644
--- a/drivers/gpu/drm/i915/selftests/igt_atomic.h
+++ b/drivers/gpu/drm/i915/selftests/igt_atomic.h
@@ -6,51 +6,12 @@
 #ifndef IGT_ATOMIC_H
 #define IGT_ATOMIC_H
 
-#include <linux/preempt.h>
-#include <linux/bottom_half.h>
-#include <linux/irqflags.h>
-
-static void __preempt_begin(void)
-{
-	preempt_disable();
-}
-
-static void __preempt_end(void)
-{
-	preempt_enable();
-}
-
-static void __softirq_begin(void)
-{
-	local_bh_disable();
-}
-
-static void __softirq_end(void)
-{
-	local_bh_enable();
-}
-
-static void __hardirq_begin(void)
-{
-	local_irq_disable();
-}
-
-static void __hardirq_end(void)
-{
-	local_irq_enable();
-}
-
 struct igt_atomic_section {
 	const char *name;
 	void (*critical_section_begin)(void);
 	void (*critical_section_end)(void);
 };
 
-static const struct igt_atomic_section igt_atomic_phases[] = {
-	{ "preempt", __preempt_begin, __preempt_end },
-	{ "softirq", __softirq_begin, __softirq_end },
-	{ "hardirq", __hardirq_begin, __hardirq_end },
-	{ }
-};
+extern const struct igt_atomic_section igt_atomic_phases[];
 
 #endif /* IGT_ATOMIC_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h
index c0e9f99d50de..36ed42736c52 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.h
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h
@@ -7,7 +7,7 @@
 #ifndef IGT_LIVE_TEST_H
 #define IGT_LIVE_TEST_H
 
-#include "../i915_gem.h"
+#include "gt/intel_engine.h" /* for I915_NUM_ENGINES */
 
 struct drm_i915_private;
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.c b/drivers/gpu/drm/i915/selftests/igt_mmap.c
new file mode 100644
index 000000000000..583a4ff8b8c9
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_mmap.c
@@ -0,0 +1,39 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <drm/drm_file.h>
+
+#include "i915_drv.h"
+#include "igt_mmap.h"
+
+unsigned long igt_mmap_node(struct drm_i915_private *i915,
+			    struct drm_vma_offset_node *node,
+			    unsigned long addr,
+			    unsigned long prot,
+			    unsigned long flags)
+{
+	struct file *file;
+	int err;
+
+	/* Pretend to open("/dev/dri/card0") */
+	file = mock_drm_getfile(i915->drm.primary, O_RDWR);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	err = drm_vma_node_allow(node, file->private_data);
+	if (err) {
+		addr = err;
+		goto out_file;
+	}
+
+	addr = vm_mmap(file, addr, drm_vma_node_size(node) << PAGE_SHIFT,
+		       prot, flags, drm_vma_node_offset_addr(node));
+
+	drm_vma_node_revoke(node, file->private_data);
+out_file:
+	fput(file);
+	return addr;
+}
diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.h b/drivers/gpu/drm/i915/selftests/igt_mmap.h
new file mode 100644
index 000000000000..6e716cb59d7e
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_mmap.h
@@ -0,0 +1,19 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef IGT_MMAP_H
+#define IGT_MMAP_H
+
+struct drm_i915_private;
+struct drm_vma_offset_node;
+
+unsigned long igt_mmap_node(struct drm_i915_private *i915,
+			    struct drm_vma_offset_node *node,
+			    unsigned long addr,
+			    unsigned long prot,
+			    unsigned long flags);
+
+#endif /* IGT_MMAP_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index ee8450b871da..e8a58fe49c39 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -15,8 +15,6 @@ int igt_spinner_init(struct igt_spinner *spin, struct intel_gt *gt)
 	void *vaddr;
 	int err;
 
-	GEM_BUG_ON(INTEL_GEN(gt->i915) < 8);
-
 	memset(spin, 0, sizeof(*spin));
 	spin->gt = gt;
 
@@ -95,11 +93,15 @@ igt_spinner_create_request(struct igt_spinner *spin,
 	struct intel_engine_cs *engine = ce->engine;
 	struct i915_request *rq = NULL;
 	struct i915_vma *hws, *vma;
+	unsigned int flags;
 	u32 *batch;
 	int err;
 
 	GEM_BUG_ON(spin->gt != ce->vm->gt);
 
+	if (!intel_engine_can_store_dword(ce->engine))
+		return ERR_PTR(-ENODEV);
+
 	vma = i915_vma_instance(spin->obj, ce->vm, NULL);
 	if (IS_ERR(vma))
 		return ERR_CAST(vma);
@@ -132,16 +134,37 @@ igt_spinner_create_request(struct igt_spinner *spin,
 
 	batch = spin->batch;
 
-	*batch++ = MI_STORE_DWORD_IMM_GEN4;
-	*batch++ = lower_32_bits(hws_address(hws, rq));
-	*batch++ = upper_32_bits(hws_address(hws, rq));
+	if (INTEL_GEN(rq->i915) >= 8) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = lower_32_bits(hws_address(hws, rq));
+		*batch++ = upper_32_bits(hws_address(hws, rq));
+	} else if (INTEL_GEN(rq->i915) >= 6) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4;
+		*batch++ = 0;
+		*batch++ = hws_address(hws, rq);
+	} else if (INTEL_GEN(rq->i915) >= 4) {
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
+		*batch++ = 0;
+		*batch++ = hws_address(hws, rq);
+	} else {
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
+		*batch++ = hws_address(hws, rq);
+	}
 	*batch++ = rq->fence.seqno;
 
 	*batch++ = arbitration_command;
 
-	*batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1;
+	if (INTEL_GEN(rq->i915) >= 8)
+		*batch++ = MI_BATCH_BUFFER_START | BIT(8) | 1;
+	else if (IS_HASWELL(rq->i915))
+		*batch++ = MI_BATCH_BUFFER_START | MI_BATCH_PPGTT_HSW;
+	else if (INTEL_GEN(rq->i915) >= 6)
+		*batch++ = MI_BATCH_BUFFER_START;
+	else
+		*batch++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
 	*batch++ = lower_32_bits(vma->node.start);
 	*batch++ = upper_32_bits(vma->node.start);
+
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
 
 	intel_gt_chipset_flush(engine->gt);
@@ -153,7 +176,10 @@ igt_spinner_create_request(struct igt_spinner *spin,
 			goto cancel_rq;
 	}
 
-	err = engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0);
+	flags = 0;
+	if (INTEL_GEN(rq->i915) <= 5)
+		flags |= I915_DISPATCH_SECURE;
+	err = engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
 
 cancel_rq:
 	if (err) {
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 19e1cca8f143..3ef3620e0da5 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -32,7 +32,7 @@ static void close_objects(struct intel_memory_region *mem,
 		if (i915_gem_object_has_pinned_pages(obj))
 			i915_gem_object_unpin_pages(obj);
 		/* No polluting the memory region between tests */
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		__i915_gem_object_put_pages(obj);
 		list_del(&obj->st_link);
 		i915_gem_object_put(obj);
 	}
@@ -122,7 +122,7 @@ put:
 static void igt_object_release(struct drm_i915_gem_object *obj)
 {
 	i915_gem_object_unpin_pages(obj);
-	__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+	__i915_gem_object_put_pages(obj);
 	list_del(&obj->st_link);
 	i915_gem_object_put(obj);
 }
@@ -270,36 +270,31 @@ static int igt_gpu_write_dw(struct intel_context *ce,
 
 static int igt_cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
-	unsigned long n;
+	unsigned long n = obj->base.size >> PAGE_SHIFT;
+	u32 *ptr;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_wc_domain(obj, false);
-	i915_gem_object_unlock(obj);
-	if (err)
-		return err;
-
-	err = i915_gem_object_pin_pages(obj);
+	err = i915_gem_object_wait(obj, 0, MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
-	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
-		u32 __iomem *base;
-		u32 read_val;
-
-		base = i915_gem_object_lmem_io_map_page_atomic(obj, n);
+	ptr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
 
-		read_val = ioread32(base + dword);
-		io_mapping_unmap_atomic(base);
-		if (read_val != val) {
-			pr_err("n=%lu base[%u]=%u, val=%u\n",
-			       n, dword, read_val, val);
+	ptr += dword;
+	while (n--) {
+		if (*ptr != val) {
+			pr_err("base[%u]=%08x, val=%08x\n",
+			       dword, *ptr, val);
 			err = -EINVAL;
 			break;
 		}
+
+		ptr += PAGE_SIZE / sizeof(*ptr);
 	}
 
-	i915_gem_object_unpin_pages(obj);
+	i915_gem_object_unpin_map(obj);
 	return err;
 }
 
@@ -404,7 +399,7 @@ static int igt_lmem_write_gpu(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_context *ctx;
-	struct drm_file *file;
+	struct file *file;
 	I915_RND_STATE(prng);
 	u32 sz;
 	int err;
@@ -439,7 +434,7 @@ static int igt_lmem_write_gpu(void *arg)
 out_put:
 	i915_gem_object_put(obj);
 out_file:
-	mock_file_free(i915, file);
+	fput(file);
 	return err;
 }
 
@@ -506,7 +501,9 @@ static int igt_lmem_write_cpu(void *arg)
 	}
 
 	/* Put the pages into a known state -- from the gpu for added fun */
+	intel_engine_pm_get(engine);
 	err = i915_gem_object_fill_blt(obj, engine->kernel_context, 0xdeadbeaf);
+	intel_engine_pm_put(engine);
 	if (err)
 		goto out_unpin;
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_drm.c b/drivers/gpu/drm/i915/selftests/mock_drm.c
deleted file mode 100644
index 09c704153456..000000000000
--- a/drivers/gpu/drm/i915/selftests/mock_drm.c
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * Copyright © 2017 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- */
-
-#include "mock_drm.h"
-
-struct drm_file *mock_file(struct drm_i915_private *i915)
-{
-	struct file *filp;
-	struct inode *inode;
-	struct drm_file *file;
-	int err;
-
-	inode = kzalloc(sizeof(*inode), GFP_KERNEL);
-	if (!inode) {
-		err = -ENOMEM;
-		goto err;
-	}
-
-	inode->i_rdev = i915->drm.primary->index;
-
-	filp = kzalloc(sizeof(*filp), GFP_KERNEL);
-	if (!filp) {
-		err = -ENOMEM;
-		goto err_inode;
-	}
-
-	err = drm_open(inode, filp);
-	if (err)
-		goto err_filp;
-
-	file = filp->private_data;
-	memset(&file->filp, POISON_INUSE, sizeof(file->filp));
-	file->authenticated = true;
-
-	kfree(filp);
-	kfree(inode);
-	return file;
-
-err_filp:
-	kfree(filp);
-err_inode:
-	kfree(inode);
-err:
-	return ERR_PTR(err);
-}
-
-void mock_file_free(struct drm_i915_private *i915, struct drm_file *file)
-{
-	struct file filp = { .private_data = file };
-
-	drm_release(NULL, &filp);
-}
diff --git a/drivers/gpu/drm/i915/selftests/mock_drm.h b/drivers/gpu/drm/i915/selftests/mock_drm.h
index b39beee9f8f6..9916b6f95526 100644
--- a/drivers/gpu/drm/i915/selftests/mock_drm.h
+++ b/drivers/gpu/drm/i915/selftests/mock_drm.h
@@ -25,7 +25,21 @@
 #ifndef __MOCK_DRM_H
 #define __MOCK_DRM_H
 
-struct drm_file *mock_file(struct drm_i915_private *i915);
-void mock_file_free(struct drm_i915_private *i915, struct drm_file *file);
+#include <drm/drm_file.h>
+
+#include "i915_drv.h"
+
+struct drm_file;
+struct file;
+
+static inline struct file *mock_file(struct drm_i915_private *i915)
+{
+	return mock_drm_getfile(i915->drm.primary, O_RDWR);
+}
+
+static inline struct drm_file *to_drm_file(struct file *f)
+{
+	return f->private_data;
+}
 
 #endif /* !__MOCK_DRM_H */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 27ed3cee6a9b..3b8986983afc 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -54,25 +54,19 @@ void mock_device_flush(struct drm_i915_private *i915)
 static void mock_device_release(struct drm_device *dev)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 
 	mock_device_flush(i915);
+	intel_gt_driver_remove(&i915->gt);
 
-	i915_gem_drain_workqueue(i915);
-
-	for_each_engine(engine, &i915->gt, id)
-		mock_engine_free(engine);
 	i915_gem_driver_release__contexts(i915);
 
-	intel_timelines_fini(i915);
-
-	drain_workqueue(i915->wq);
+	i915_gem_drain_workqueue(i915);
 	i915_gem_drain_freed_objects(i915);
 
 	mock_fini_ggtt(&i915->ggtt);
 	destroy_workqueue(i915->wq);
 
+	intel_gt_driver_late_release(&i915->gt);
 	intel_memory_regions_driver_release(i915);
 
 	drm_mode_config_cleanup(&i915->drm);
@@ -180,9 +174,8 @@ struct drm_i915_private *mock_gem_device(void)
 
 	mock_init_contexts(i915);
 
-	intel_timelines_init(i915);
-
 	mock_init_ggtt(i915, &i915->ggtt);
+	i915->gt.vm = i915_vm_get(&i915->ggtt.vm);
 
 	mkwrite_device_info(i915)->engine_mask = BIT(0);
 
@@ -190,25 +183,20 @@ struct drm_i915_private *mock_gem_device(void)
 	if (!i915->engine[RCS0])
 		goto err_unlock;
 
-	i915->kernel_context = mock_context(i915, NULL);
-	if (!i915->kernel_context)
-		goto err_engine;
-
 	if (mock_engine_init(i915->engine[RCS0]))
 		goto err_context;
 
+	__clear_bit(I915_WEDGED, &i915->gt.reset.flags);
 	intel_engines_driver_register(i915);
 
 	return i915;
 
 err_context:
-	i915_gem_driver_release__contexts(i915);
-err_engine:
-	mock_engine_free(i915->engine[RCS0]);
+	intel_gt_driver_remove(&i915->gt);
 err_unlock:
-	intel_timelines_fini(i915);
 	destroy_workqueue(i915->wq);
 err_drv:
+	intel_gt_driver_late_release(&i915->gt);
 	intel_memory_regions_driver_release(i915);
 	drm_mode_config_cleanup(&i915->drm);
 	drm_dev_fini(&i915->drm);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 20ac3844edec..edc5e3dda8ca 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -55,6 +55,11 @@ static void mock_cleanup(struct i915_address_space *vm)
 {
 }
 
+static void mock_clear_range(struct i915_address_space *vm,
+			     u64 start, u64 length)
+{
+}
+
 struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 {
 	struct i915_ppgtt *ppgtt;
@@ -70,7 +75,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 
 	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
 
-	ppgtt->vm.clear_range = nop_clear_range;
+	ppgtt->vm.clear_range = mock_clear_range;
 	ppgtt->vm.insert_page = mock_insert_page;
 	ppgtt->vm.insert_entries = mock_insert_entries;
 	ppgtt->vm.cleanup = mock_cleanup;
@@ -107,7 +112,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt)
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
 	ggtt->vm.total = 4096 * PAGE_SIZE;
 
-	ggtt->vm.clear_range = nop_clear_range;
+	ggtt->vm.clear_range = mock_clear_range;
 	ggtt->vm.insert_page = mock_insert_page;
 	ggtt->vm.insert_entries = mock_insert_entries;
 	ggtt->vm.cleanup = mock_cleanup;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.h b/drivers/gpu/drm/i915/selftests/mock_gtt.h
index 3387393286de..e3f224f43beb 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.h
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.h
@@ -25,6 +25,9 @@
 #ifndef __MOCK_GTT_H
 #define __MOCK_GTT_H
 
+struct drm_i915_private;
+struct i915_ggtt;
+
 void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt);
 void mock_fini_ggtt(struct i915_ggtt *ggtt);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.h b/drivers/gpu/drm/i915/selftests/mock_region.h
index 24608089d833..329bf74dfaca 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.h
+++ b/drivers/gpu/drm/i915/selftests/mock_region.h
@@ -6,6 +6,11 @@
 #ifndef __MOCK_REGION_H
 #define __MOCK_REGION_H
 
+#include <linux/types.h>
+
+struct drm_i915_private;
+struct intel_memory_region;
+
 struct intel_memory_region *
 mock_region_create(struct drm_i915_private *i915,
 		   resource_size_t start,
diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.h b/drivers/gpu/drm/i915/selftests/mock_uncore.h
index 8a2cc553f466..7acf1ef4d488 100644
--- a/drivers/gpu/drm/i915/selftests/mock_uncore.h
+++ b/drivers/gpu/drm/i915/selftests/mock_uncore.h
@@ -25,6 +25,9 @@
 #ifndef __MOCK_UNCORE_H
 #define __MOCK_UNCORE_H
 
+struct drm_i915_private;
+struct intel_uncore;
+
 void mock_uncore_init(struct intel_uncore *uncore,
 		      struct drm_i915_private *i915);
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 208069faf183..8cb2665b2c74 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -127,7 +127,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 	struct imx_ldb_channel *imx_ldb_ch = con_to_imx_ldb_ch(connector);
 	int num_modes;
 
-	num_modes = drm_panel_get_modes(imx_ldb_ch->panel);
+	num_modes = drm_panel_get_modes(imx_ldb_ch->panel, connector);
 	if (num_modes > 0)
 		return num_modes;
 
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 35518e5de356..3dca424059f7 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -50,7 +50,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 	struct device_node *np = imxpd->dev->of_node;
 	int num_modes;
 
-	num_modes = drm_panel_get_modes(imxpd->panel);
+	num_modes = drm_panel_get_modes(imxpd->panel, connector);
 	if (num_modes > 0)
 		return num_modes;
 
diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c
index ec32e1c67335..6d47ef7b148c 100644
--- a/drivers/gpu/drm/ingenic/ingenic-drm.c
+++ b/drivers/gpu/drm/ingenic/ingenic-drm.c
@@ -153,6 +153,7 @@ struct ingenic_dma_hwdesc {
 
 struct jz_soc_info {
 	bool needs_dev_clk;
+	unsigned int max_width, max_height;
 };
 
 struct ingenic_drm {
@@ -164,6 +165,7 @@ struct ingenic_drm {
 	struct device *dev;
 	struct regmap *map;
 	struct clk *lcd_clk, *pix_clk;
+	const struct jz_soc_info *soc_info;
 
 	struct ingenic_dma_hwdesc *dma_hwdesc;
 	dma_addr_t dma_hwdesc_phys;
@@ -326,6 +328,10 @@ static int ingenic_drm_crtc_atomic_check(struct drm_crtc *crtc,
 	if (!drm_atomic_crtc_needs_modeset(state))
 		return 0;
 
+	if (state->mode.hdisplay > priv->soc_info->max_height ||
+	    state->mode.vdisplay > priv->soc_info->max_width)
+		return -EINVAL;
+
 	rate = clk_round_rate(priv->pix_clk,
 			      state->adjusted_mode.clock * 1000);
 	if (rate < 0)
@@ -372,14 +378,18 @@ static void ingenic_drm_plane_atomic_update(struct drm_plane *plane,
 	struct ingenic_drm *priv = drm_plane_get_priv(plane);
 	struct drm_plane_state *state = plane->state;
 	unsigned int width, height, cpp;
+	dma_addr_t addr;
 
-	width = state->crtc->state->adjusted_mode.hdisplay;
-	height = state->crtc->state->adjusted_mode.vdisplay;
-	cpp = state->fb->format->cpp[plane->index];
+	if (state && state->fb) {
+		addr = drm_fb_cma_get_gem_addr(state->fb, state, 0);
+		width = state->src_w >> 16;
+		height = state->src_h >> 16;
+		cpp = state->fb->format->cpp[plane->index];
 
-	priv->dma_hwdesc->addr = drm_fb_cma_get_gem_addr(state->fb, state, 0);
-	priv->dma_hwdesc->cmd = width * height * cpp / 4;
-	priv->dma_hwdesc->cmd |= JZ_LCD_CMD_EOF_IRQ;
+		priv->dma_hwdesc->addr = addr;
+		priv->dma_hwdesc->cmd = width * height * cpp / 4;
+		priv->dma_hwdesc->cmd |= JZ_LCD_CMD_EOF_IRQ;
+	}
 }
 
 static void ingenic_drm_encoder_atomic_mode_set(struct drm_encoder *encoder,
@@ -617,6 +627,7 @@ static int ingenic_drm_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	priv->soc_info = soc_info;
 	priv->dev = dev;
 	drm = &priv->drm;
 	drm->dev_private = priv;
@@ -632,8 +643,8 @@ static int ingenic_drm_probe(struct platform_device *pdev)
 	drm_mode_config_init(drm);
 	drm->mode_config.min_width = 0;
 	drm->mode_config.min_height = 0;
-	drm->mode_config.max_width = 800;
-	drm->mode_config.max_height = 600;
+	drm->mode_config.max_width = soc_info->max_width;
+	drm->mode_config.max_height = 4095;
 	drm->mode_config.funcs = &ingenic_drm_mode_config_funcs;
 
 	base = devm_platform_ioremap_resource(pdev, 0);
@@ -810,15 +821,26 @@ static int ingenic_drm_remove(struct platform_device *pdev)
 
 static const struct jz_soc_info jz4740_soc_info = {
 	.needs_dev_clk = true,
+	.max_width = 800,
+	.max_height = 600,
 };
 
 static const struct jz_soc_info jz4725b_soc_info = {
 	.needs_dev_clk = false,
+	.max_width = 800,
+	.max_height = 600,
+};
+
+static const struct jz_soc_info jz4770_soc_info = {
+	.needs_dev_clk = false,
+	.max_width = 1280,
+	.max_height = 720,
 };
 
 static const struct of_device_id ingenic_drm_of_match[] = {
 	{ .compatible = "ingenic,jz4740-lcd", .data = &jz4740_soc_info },
 	{ .compatible = "ingenic,jz4725b-lcd", .data = &jz4725b_soc_info },
+	{ .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info },
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/gpu/drm/lima/Kconfig b/drivers/gpu/drm/lima/Kconfig
index 571dc369a7e9..d589f09d04d9 100644
--- a/drivers/gpu/drm/lima/Kconfig
+++ b/drivers/gpu/drm/lima/Kconfig
@@ -11,4 +11,4 @@ config DRM_LIMA
        select DRM_SCHED
        select DRM_GEM_SHMEM_HELPER
        help
-         DRM driver for ARM Mali 400/450 GPUs.
+	 DRM driver for ARM Mali 400/450 GPUs.
diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c
index f522c5f99729..b561dd05bd62 100644
--- a/drivers/gpu/drm/lima/lima_sched.c
+++ b/drivers/gpu/drm/lima/lima_sched.c
@@ -159,9 +159,10 @@ int lima_sched_context_init(struct lima_sched_pipe *pipe,
 			    struct lima_sched_context *context,
 			    atomic_t *guilty)
 {
-	struct drm_sched_rq *rq = pipe->base.sched_rq + DRM_SCHED_PRIORITY_NORMAL;
+	struct drm_gpu_scheduler *sched = &pipe->base;
 
-	return drm_sched_entity_init(&context->base, &rq, 1, guilty);
+	return drm_sched_entity_init(&context->base, DRM_SCHED_PRIORITY_NORMAL,
+				     &sched, 1, guilty);
 }
 
 void lima_sched_context_fini(struct lima_sched_pipe *pipe,
@@ -255,13 +256,17 @@ static struct dma_fence *lima_sched_run_job(struct drm_sched_job *job)
 	return task->fence;
 }
 
-static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe,
-					 struct lima_sched_task *task)
+static void lima_sched_timedout_job(struct drm_sched_job *job)
 {
+	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
+	struct lima_sched_task *task = to_lima_task(job);
+
+	if (!pipe->error)
+		DRM_ERROR("lima job timeout\n");
+
 	drm_sched_stop(&pipe->base, &task->base);
 
-	if (task)
-		drm_sched_increase_karma(&task->base);
+	drm_sched_increase_karma(&task->base);
 
 	pipe->task_error(pipe);
 
@@ -284,16 +289,6 @@ static void lima_sched_handle_error_task(struct lima_sched_pipe *pipe,
 	drm_sched_start(&pipe->base, true);
 }
 
-static void lima_sched_timedout_job(struct drm_sched_job *job)
-{
-	struct lima_sched_pipe *pipe = to_lima_pipe(job->sched);
-	struct lima_sched_task *task = to_lima_task(job);
-
-	DRM_ERROR("lima job timeout\n");
-
-	lima_sched_handle_error_task(pipe, task);
-}
-
 static void lima_sched_free_job(struct drm_sched_job *job)
 {
 	struct lima_sched_task *task = to_lima_task(job);
@@ -318,15 +313,6 @@ static const struct drm_sched_backend_ops lima_sched_ops = {
 	.free_job = lima_sched_free_job,
 };
 
-static void lima_sched_error_work(struct work_struct *work)
-{
-	struct lima_sched_pipe *pipe =
-		container_of(work, struct lima_sched_pipe, error_work);
-	struct lima_sched_task *task = pipe->current_task;
-
-	lima_sched_handle_error_task(pipe, task);
-}
-
 int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
 {
 	unsigned int timeout = lima_sched_timeout_ms > 0 ?
@@ -335,8 +321,6 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name)
 	pipe->fence_context = dma_fence_context_alloc(1);
 	spin_lock_init(&pipe->fence_lock);
 
-	INIT_WORK(&pipe->error_work, lima_sched_error_work);
-
 	return drm_sched_init(&pipe->base, &lima_sched_ops, 1, 0,
 			      msecs_to_jiffies(timeout), name);
 }
@@ -349,7 +333,7 @@ void lima_sched_pipe_fini(struct lima_sched_pipe *pipe)
 void lima_sched_pipe_task_done(struct lima_sched_pipe *pipe)
 {
 	if (pipe->error)
-		schedule_work(&pipe->error_work);
+		drm_sched_fault(&pipe->base);
 	else {
 		struct lima_sched_task *task = pipe->current_task;
 
diff --git a/drivers/gpu/drm/lima/lima_sched.h b/drivers/gpu/drm/lima/lima_sched.h
index 928af91c1118..1d814fecbcc0 100644
--- a/drivers/gpu/drm/lima/lima_sched.h
+++ b/drivers/gpu/drm/lima/lima_sched.h
@@ -68,8 +68,6 @@ struct lima_sched_pipe {
 	void (*task_fini)(struct lima_sched_pipe *pipe);
 	void (*task_error)(struct lima_sched_pipe *pipe);
 	void (*task_mmu_error)(struct lima_sched_pipe *pipe);
-
-	struct work_struct error_work;
 };
 
 int lima_sched_task_init(struct lima_sched_task *task,
diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c
index 751454ae3cd1..e59907e68854 100644
--- a/drivers/gpu/drm/mcde/mcde_display.c
+++ b/drivers/gpu/drm/mcde/mcde_display.c
@@ -498,24 +498,20 @@ static void mcde_configure_channel(struct mcde *mcde, enum mcde_channel ch,
 	}
 
 	/* Set up channel 0 sync (based on chnl_update_registers()) */
-	if (mcde->te_sync) {
-		/*
-		 * Turn on hardware TE0 synchronization
-		 */
+	if (mcde->video_mode || mcde->te_sync)
 		val = MCDE_CHNLXSYNCHMOD_SRC_SYNCH_HARDWARE
 			<< MCDE_CHNLXSYNCHMOD_SRC_SYNCH_SHIFT;
-		val |= MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_TE0
-			<< MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_SHIFT;
-	} else {
-		/*
-		 * Set up sync source to software, out sync formatter
-		 * Code mostly from mcde_hw.c chnl_update_registers()
-		 */
+	else
 		val = MCDE_CHNLXSYNCHMOD_SRC_SYNCH_SOFTWARE
 			<< MCDE_CHNLXSYNCHMOD_SRC_SYNCH_SHIFT;
+
+	if (mcde->te_sync)
+		val |= MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_TE0
+			<< MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_SHIFT;
+	else
 		val |= MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_FORMATTER
 			<< MCDE_CHNLXSYNCHMOD_OUT_SYNCH_SRC_SHIFT;
-	}
+
 	writel(val, mcde->regs + sync);
 
 	/* Set up pixels per line and lines per frame */
@@ -934,10 +930,17 @@ static void mcde_display_enable(struct drm_simple_display_pipe *pipe,
 		val = readl(mcde->regs + MCDE_CRC);
 		val |= MCDE_CRC_SYCEN0;
 		writel(val, mcde->regs + MCDE_CRC);
-
-		drm_crtc_vblank_on(crtc);
 	}
 
+	drm_crtc_vblank_on(crtc);
+
+	if (mcde->video_mode)
+		/*
+		 * Keep FIFO permanently enabled in video mode,
+		 * otherwise MCDE will stop feeding data to the panel.
+		 */
+		mcde_enable_fifo(mcde, MCDE_FIFO_A);
+
 	dev_info(drm->dev, "MCDE display is enabled\n");
 }
 
@@ -946,13 +949,22 @@ static void mcde_display_disable(struct drm_simple_display_pipe *pipe)
 	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_device *drm = crtc->dev;
 	struct mcde *mcde = drm->dev_private;
+	struct drm_pending_vblank_event *event;
 
-	if (mcde->te_sync)
-		drm_crtc_vblank_off(crtc);
+	drm_crtc_vblank_off(crtc);
 
 	/* Disable FIFO A flow */
 	mcde_disable_fifo(mcde, MCDE_FIFO_A, true);
 
+	event = crtc->state->event;
+	if (event) {
+		crtc->state->event = NULL;
+
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, event);
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
+
 	dev_info(drm->dev, "MCDE display is disabled\n");
 }
 
@@ -1048,8 +1060,9 @@ static void mcde_display_update(struct drm_simple_display_pipe *pipe,
 	 */
 	if (fb) {
 		mcde_set_extsrc(mcde, drm_fb_cma_get_gem_addr(fb, pstate, 0));
-		/* Send a single frame using software sync */
-		mcde_display_send_one_frame(mcde);
+		if (!mcde->video_mode)
+			/* Send a single frame using software sync */
+			mcde_display_send_one_frame(mcde);
 		dev_info_once(mcde->dev, "sent first display update\n");
 	} else {
 		/*
@@ -1097,6 +1110,8 @@ static struct drm_simple_display_pipe_funcs mcde_display_funcs = {
 	.enable = mcde_display_enable,
 	.disable = mcde_display_disable,
 	.update = mcde_display_update,
+	.enable_vblank = mcde_display_enable_vblank,
+	.disable_vblank = mcde_display_disable_vblank,
 	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
 };
 
@@ -1123,12 +1138,6 @@ int mcde_display_init(struct drm_device *drm)
 		DRM_FORMAT_YUV422,
 	};
 
-	/* Provide vblank only when we have TE enabled */
-	if (mcde->te_sync) {
-		mcde_display_funcs.enable_vblank = mcde_display_enable_vblank;
-		mcde_display_funcs.disable_vblank = mcde_display_disable_vblank;
-	}
-
 	ret = drm_simple_display_pipe_init(drm, &mcde->pipe,
 					   &mcde_display_funcs,
 					   formats, ARRAY_SIZE(formats),
diff --git a/drivers/gpu/drm/mcde/mcde_drm.h b/drivers/gpu/drm/mcde/mcde_drm.h
index dab4db021231..80edd6628979 100644
--- a/drivers/gpu/drm/mcde/mcde_drm.h
+++ b/drivers/gpu/drm/mcde/mcde_drm.h
@@ -19,6 +19,7 @@ struct mcde {
 	struct mipi_dsi_device *mdsi;
 	s16 stride;
 	bool te_sync;
+	bool video_mode;
 	bool oneshot_mode;
 	unsigned int flow_active;
 	spinlock_t flow_lock; /* Locks the channel flow control */
diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c
index 5649887d2b90..9008ddcfc528 100644
--- a/drivers/gpu/drm/mcde/mcde_drv.c
+++ b/drivers/gpu/drm/mcde/mcde_drv.c
@@ -179,18 +179,10 @@ static int mcde_modeset_init(struct drm_device *drm)
 	mode_config->min_height = 1;
 	mode_config->max_height = 1080;
 
-	/*
-	 * Currently we only support vblank handling on the DSI bridge, using
-	 * TE synchronization. If TE sync is not set up, it is still possible
-	 * to push out a single update on demand, but this is hard for DRM to
-	 * exploit.
-	 */
-	if (mcde->te_sync) {
-		ret = drm_vblank_init(drm, 1);
-		if (ret) {
-			dev_err(drm->dev, "failed to init vblank\n");
-			goto out_config;
-		}
+	ret = drm_vblank_init(drm, 1);
+	if (ret) {
+		dev_err(drm->dev, "failed to init vblank\n");
+		goto out_config;
 	}
 
 	ret = mcde_display_init(drm);
@@ -339,8 +331,6 @@ static int mcde_probe(struct platform_device *pdev)
 	drm->dev_private = mcde;
 	platform_set_drvdata(pdev, drm);
 
-	/* Enable use of the TE signal and interrupt */
-	mcde->te_sync = true;
 	/* Enable continuous updates: this is what Linux' framebuffer expects */
 	mcde->oneshot_mode = false;
 	drm->dev_private = mcde;
diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c
index ef4c630afe3f..bb6528b01cd0 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi.c
+++ b/drivers/gpu/drm/mcde/mcde_dsi.c
@@ -39,7 +39,6 @@ struct mcde_dsi {
 	struct device *dev;
 	struct mcde *mcde;
 	struct drm_bridge bridge;
-	struct drm_connector connector;
 	struct drm_panel *panel;
 	struct drm_bridge *bridge_out;
 	struct mipi_dsi_host dsi_host;
@@ -64,11 +63,6 @@ static inline struct mcde_dsi *host_to_mcde_dsi(struct mipi_dsi_host *h)
 	return container_of(h, struct mcde_dsi, dsi_host);
 }
 
-static inline struct mcde_dsi *connector_to_mcde_dsi(struct drm_connector *c)
-{
-	return container_of(c, struct mcde_dsi, connector);
-}
-
 bool mcde_dsi_irq(struct mipi_dsi_device *mdsi)
 {
 	struct mcde_dsi *d;
@@ -124,12 +118,41 @@ bool mcde_dsi_irq(struct mipi_dsi_device *mdsi)
 
 	val = readl(d->regs + DSI_VID_MODE_STS_FLAG);
 	if (val)
-		dev_err(d->dev, "some video mode error status\n");
+		dev_dbg(d->dev, "DSI_VID_MODE_STS_FLAG = %08x\n", val);
+	if (val & DSI_VID_MODE_STS_VSG_RUNNING)
+		dev_dbg(d->dev, "VID mode VSG running\n");
+	if (val & DSI_VID_MODE_STS_ERR_MISSING_DATA)
+		dev_err(d->dev, "VID mode missing data\n");
+	if (val & DSI_VID_MODE_STS_ERR_MISSING_HSYNC)
+		dev_err(d->dev, "VID mode missing HSYNC\n");
+	if (val & DSI_VID_MODE_STS_ERR_MISSING_VSYNC)
+		dev_err(d->dev, "VID mode missing VSYNC\n");
+	if (val & DSI_VID_MODE_STS_REG_ERR_SMALL_LENGTH)
+		dev_err(d->dev, "VID mode less bytes than expected between two HSYNC\n");
+	if (val & DSI_VID_MODE_STS_REG_ERR_SMALL_HEIGHT)
+		dev_err(d->dev, "VID mode less lines than expected between two VSYNC\n");
+	if (val & (DSI_VID_MODE_STS_ERR_BURSTWRITE |
+		   DSI_VID_MODE_STS_ERR_LINEWRITE |
+		   DSI_VID_MODE_STS_ERR_LONGREAD))
+		dev_err(d->dev, "VID mode read/write error\n");
+	if (val & DSI_VID_MODE_STS_ERR_VRS_WRONG_LENGTH)
+		dev_err(d->dev, "VID mode received packets differ from expected size\n");
+	if (val & DSI_VID_MODE_STS_VSG_RECOVERY)
+		dev_err(d->dev, "VID mode VSG in recovery mode\n");
 	writel(val, d->regs + DSI_VID_MODE_STS_CLR);
 
 	return te_received;
 }
 
+static void mcde_dsi_attach_to_mcde(struct mcde_dsi *d)
+{
+	d->mcde->mdsi = d->mdsi;
+
+	d->mcde->video_mode = !!(d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO);
+	/* Enable use of the TE signal for all command mode panels */
+	d->mcde->te_sync = !d->mcde->video_mode;
+}
+
 static int mcde_dsi_host_attach(struct mipi_dsi_host *host,
 				struct mipi_dsi_device *mdsi)
 {
@@ -148,7 +171,7 @@ static int mcde_dsi_host_attach(struct mipi_dsi_host *host,
 
 	d->mdsi = mdsi;
 	if (d->mcde)
-		d->mcde->mdsi = mdsi;
+		mcde_dsi_attach_to_mcde(d);
 
 	return 0;
 }
@@ -223,25 +246,25 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 	if (txlen > 0) {
 		val = 0;
 		for (i = 0; i < 4 && i < txlen; i++)
-			val |= tx[i] << (i & 3) * 8;
+			val |= tx[i] << (i * 8);
 	}
 	writel(val, d->regs + DSI_DIRECT_CMD_WRDAT0);
 	if (txlen > 4) {
 		val = 0;
 		for (i = 0; i < 4 && (i + 4) < txlen; i++)
-			val |= tx[i + 4] << (i & 3) * 8;
+			val |= tx[i + 4] << (i * 8);
 		writel(val, d->regs + DSI_DIRECT_CMD_WRDAT1);
 	}
 	if (txlen > 8) {
 		val = 0;
 		for (i = 0; i < 4 && (i + 8) < txlen; i++)
-			val |= tx[i + 8] << (i & 3) * 8;
+			val |= tx[i + 8] << (i * 8);
 		writel(val, d->regs + DSI_DIRECT_CMD_WRDAT2);
 	}
 	if (txlen > 12) {
 		val = 0;
 		for (i = 0; i < 4 && (i + 12) < txlen; i++)
-			val |= tx[i + 12] << (i & 3) * 8;
+			val |= tx[i + 12] << (i * 8);
 		writel(val, d->regs + DSI_DIRECT_CMD_WRDAT3);
 	}
 
@@ -336,7 +359,7 @@ void mcde_dsi_te_request(struct mipi_dsi_device *mdsi)
 	val |= 0 << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_ID_SHIFT;
 	val |= 2 << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_SIZE_SHIFT;
 	val |= DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LP_EN;
-	val |= DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_SHORT_WRITE_1 <<
+	val |= MIPI_DSI_GENERIC_SHORT_WRITE_1_PARAM <<
 		DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHIFT;
 	writel(val, d->regs + DSI_DIRECT_CMD_MAIN_SETTINGS);
 
@@ -365,13 +388,14 @@ void mcde_dsi_te_request(struct mipi_dsi_device *mdsi)
 static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 				      const struct drm_display_mode *mode)
 {
-	u8 bpp = mipi_dsi_pixel_format_to_bpp(d->mdsi->format);
+	/* cpp, characters per pixel, number of bytes per pixel */
+	u8 cpp = mipi_dsi_pixel_format_to_bpp(d->mdsi->format) / 8;
+	u64 pclk;
 	u64 bpl;
-	u32 hfp;
-	u32 hbp;
-	u32 hsa;
+	int hfp;
+	int hbp;
+	int hsa;
 	u32 blkline_pck, line_duration;
-	u32 blkeol_pck, blkeol_duration;
 	u32 val;
 
 	val = 0;
@@ -408,11 +432,21 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 		return;
 	}
 
-	/* TODO: TVG could be enabled here */
+	/* TODO: TVG (test video generator) could be enabled here */
 
-	/* Send blanking packet */
+	/*
+	 * During vertical blanking: go to LP mode
+	 * Like with the EOL setting, if this is not set, the EOL area will be
+	 * filled with NULL or blanking packets in the vblank area.
+	 * FIXME: some Samsung phones and display panels such as s6e63m0 use
+	 * DSI_VID_MAIN_CTL_REG_BLKLINE_MODE_BLANKING here instead,
+	 * figure out how to properly configure that from the panel.
+	 */
 	val |= DSI_VID_MAIN_CTL_REG_BLKLINE_MODE_LP_0;
-	/* Send EOL packet */
+	/*
+	 * During EOL: go to LP mode. If this is not set, the EOL area will be
+	 * filled with NULL or blanking packets.
+	 */
 	val |= DSI_VID_MAIN_CTL_REG_BLKEOL_MODE_LP_0;
 	/* Recovery mode 1 */
 	val |= 1 << DSI_VID_MAIN_CTL_RECOVERY_MODE_SHIFT;
@@ -420,13 +454,13 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 	writel(val, d->regs + DSI_VID_MAIN_CTL);
 
 	/* Vertical frame parameters are pretty straight-forward */
-	val = mode->vdisplay << DSI_VID_VSIZE_VSA_LENGTH_SHIFT;
+	val = mode->vdisplay << DSI_VID_VSIZE_VACT_LENGTH_SHIFT;
 	/* vertical front porch */
 	val |= (mode->vsync_start - mode->vdisplay)
 		<< DSI_VID_VSIZE_VFP_LENGTH_SHIFT;
 	/* vertical sync active */
 	val |= (mode->vsync_end - mode->vsync_start)
-		<< DSI_VID_VSIZE_VACT_LENGTH_SHIFT;
+		<< DSI_VID_VSIZE_VSA_LENGTH_SHIFT;
 	/* vertical back porch */
 	val |= (mode->vtotal - mode->vsync_end)
 		<< DSI_VID_VSIZE_VBP_LENGTH_SHIFT;
@@ -434,36 +468,54 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 
 	/*
 	 * Horizontal frame parameters:
-	 * horizontal resolution is given in pixels and must be re-calculated
-	 * into bytes since this is what the hardware expects.
+	 * horizontal resolution is given in pixels but must be re-calculated
+	 * into bytes since this is what the hardware expects, these registers
+	 * define the payload size of the packet.
+	 *
+	 * hfp = horizontal front porch in bytes
+	 * hbp = horizontal back porch in bytes
+	 * hsa = horizontal sync active in bytes
 	 *
 	 * 6 + 2 is HFP header + checksum
 	 */
-	hfp = (mode->hsync_start - mode->hdisplay) * bpp - 6 - 2;
+	hfp = (mode->hsync_start - mode->hdisplay) * cpp - 6 - 2;
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) {
 		/*
+		 * Use sync pulse for sync: explicit HSA time
 		 * 6 is HBP header + checksum
 		 * 4 is RGB header + checksum
 		 */
-		hbp = (mode->htotal - mode->hsync_end) * bpp - 4 - 6;
+		hbp = (mode->htotal - mode->hsync_end) * cpp - 4 - 6;
 		/*
 		 * 6 is HBP header + checksum
 		 * 4 is HSW packet bytes
 		 * 4 is RGB header + checksum
 		 */
-		hsa = (mode->hsync_end - mode->hsync_start) * bpp - 4 - 4 - 6;
+		hsa = (mode->hsync_end - mode->hsync_start) * cpp - 4 - 4 - 6;
 	} else {
 		/*
-		 * HBP includes both back porch and sync
+		 * Use event for sync: HBP includes both back porch and sync
 		 * 6 is HBP header + checksum
 		 * 4 is HSW packet bytes
 		 * 4 is RGB header + checksum
 		 */
-		hbp = (mode->htotal - mode->hsync_start) * bpp - 4 - 4 - 6;
-		/* HSA is not considered in this mode and set to 0 */
+		hbp = (mode->htotal - mode->hsync_start) * cpp - 4 - 4 - 6;
+		/* HSA is not present in this mode and set to 0 */
 		hsa = 0;
 	}
-	dev_dbg(d->dev, "hfp: %u, hbp: %u, hsa: %u\n",
+	if (hfp < 0) {
+		dev_info(d->dev, "hfp negative, set to 0\n");
+		hfp = 0;
+	}
+	if (hbp < 0) {
+		dev_info(d->dev, "hbp negative, set to 0\n");
+		hbp = 0;
+	}
+	if (hsa < 0) {
+		dev_info(d->dev, "hsa negative, set to 0\n");
+		hsa = 0;
+	}
+	dev_dbg(d->dev, "hfp: %u, hbp: %u, hsa: %u bytes\n",
 		hfp, hbp, hsa);
 
 	/* Frame parameters: horizontal sync active */
@@ -474,91 +526,185 @@ static void mcde_dsi_setup_video_mode(struct mcde_dsi *d,
 	val |= hfp << DSI_VID_HSIZE1_HFP_LENGTH_SHIFT;
 	writel(val, d->regs + DSI_VID_HSIZE1);
 
-	/* RGB data length (bytes on one scanline) */
-	val = mode->hdisplay * (bpp / 8);
+	/* RGB data length (visible bytes on one scanline) */
+	val = mode->hdisplay * cpp;
 	writel(val, d->regs + DSI_VID_HSIZE2);
+	dev_dbg(d->dev, "RGB length, visible area on a line: %u bytes\n", val);
 
-	/* TODO: further adjustments for TVG mode here */
+	/*
+	 * Calculate the time between two pixels in picoseconds using
+	 * the supplied refresh rate and total resolution including
+	 * porches and sync.
+	 */
+	/* (ps/s) / (pixels/s) = ps/pixels */
+	pclk = DIV_ROUND_UP_ULL(1000000000000,
+				(mode->vrefresh * mode->htotal * mode->vtotal));
+	dev_dbg(d->dev, "picoseconds between two pixels: %llu\n",
+		pclk);
 
 	/*
-	 * EOL packet length from bits per line calculations: pixel clock
-	 * is given in kHz, calculate the time between two pixels in
-	 * picoseconds.
+	 * How many bytes per line will this update frequency yield?
+	 *
+	 * Calculate the number of picoseconds for one scanline (1), then
+	 * divide by 1000000000000 (2) to get in pixels per second we
+	 * want to output.
+	 *
+	 * Multiply with number of bytes per second at this video display
+	 * frequency (3) to get number of bytes transferred during this
+	 * time. Notice that we use the frequency the display wants,
+	 * not what we actually get from the DSI PLL, which is hs_freq.
+	 *
+	 * These arithmetics are done in a different order to avoid
+	 * overflow.
 	 */
-	bpl = mode->clock * mode->htotal;
-	bpl *= (d->hs_freq / 8);
-	do_div(bpl, 1000000); /* microseconds */
-	do_div(bpl, 1000000); /* seconds */
+	bpl = pclk * mode->htotal; /* (1) picoseconds per line */
+	dev_dbg(d->dev, "picoseconds per line: %llu\n", bpl);
+	/* Multiply with bytes per second (3) */
+	bpl *= (d->mdsi->hs_rate / 8);
+	/* Pixels per second (2) */
+	bpl = DIV_ROUND_DOWN_ULL(bpl, 1000000); /* microseconds */
+	bpl = DIV_ROUND_DOWN_ULL(bpl, 1000000); /* seconds */
+	/* parallel transactions in all lanes */
 	bpl *= d->mdsi->lanes;
-	dev_dbg(d->dev, "calculated bytes per line: %llu\n", bpl);
+	dev_dbg(d->dev,
+		"calculated bytes per line: %llu @ %d Hz with HS %lu Hz\n",
+		bpl, mode->vrefresh, d->mdsi->hs_rate);
+
 	/*
 	 * 6 is header + checksum, header = 4 bytes, checksum = 2 bytes
 	 * 4 is short packet for vsync/hsync
 	 */
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) {
-		/* Fixme: isn't the hsync width in pixels? */
+		/* Set the event packet size to 0 (not used) */
+		writel(0, d->regs + DSI_VID_BLKSIZE1);
+		/*
+		 * FIXME: isn't the hsync width in pixels? The porch and
+		 * sync area size is in pixels here, but this -6
+		 * seems to be for bytes. It looks like this in the vendor
+		 * code though. Is it completely untested?
+		 */
 		blkline_pck = bpl - (mode->hsync_end - mode->hsync_start) - 6;
 		val = blkline_pck << DSI_VID_BLKSIZE2_BLKLINE_PULSE_PCK_SHIFT;
 		writel(val, d->regs + DSI_VID_BLKSIZE2);
 	} else {
+		/* Set the sync pulse packet size to 0 (not used) */
+		writel(0, d->regs + DSI_VID_BLKSIZE2);
+		/* Specifying payload size in bytes (-4-6 from manual) */
 		blkline_pck = bpl - 4 - 6;
+		if (blkline_pck > 0x1FFF)
+			dev_err(d->dev, "blkline_pck too big %d bytes\n",
+				blkline_pck);
 		val = blkline_pck << DSI_VID_BLKSIZE1_BLKLINE_EVENT_PCK_SHIFT;
+		val &= DSI_VID_BLKSIZE1_BLKLINE_EVENT_PCK_MASK;
 		writel(val, d->regs + DSI_VID_BLKSIZE1);
 	}
 
-	line_duration = (blkline_pck + 6) / d->mdsi->lanes;
-	dev_dbg(d->dev, "line duration %u\n", line_duration);
+	/*
+	 * The line duration is used to scale back the frequency from
+	 * the max frequency supported by the HS clock to the desired
+	 * update frequency in vrefresh.
+	 */
+	line_duration = blkline_pck + 6;
+	/*
+	 * The datasheet contains this complex condition to decreasing
+	 * the line duration by 1 under very specific circumstances.
+	 * Here we also imply that LP is used during burst EOL.
+	 */
+	if (d->mdsi->lanes == 2 && (hsa & 0x01) && (hfp & 0x01)
+	    && (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST))
+		line_duration--;
+	line_duration = DIV_ROUND_CLOSEST(line_duration, d->mdsi->lanes);
+	dev_dbg(d->dev, "line duration %u bytes\n", line_duration);
 	val = line_duration << DSI_VID_DPHY_TIME_REG_LINE_DURATION_SHIFT;
 	/*
 	 * This is the time to perform LP->HS on D-PHY
 	 * FIXME: nowhere to get this from: DT property on the DSI?
+	 * The manual says this is "system dependent".
+	 * values like 48 and 72 seen in the vendor code.
 	 */
-	val |= 0 << DSI_VID_DPHY_TIME_REG_WAKEUP_TIME_SHIFT;
+	val |= 48 << DSI_VID_DPHY_TIME_REG_WAKEUP_TIME_SHIFT;
 	writel(val, d->regs + DSI_VID_DPHY_TIME);
 
-	/* Calculate block end of line */
-	blkeol_pck = bpl - mode->hdisplay * bpp - 6;
-	blkeol_duration = (blkeol_pck + 6) / d->mdsi->lanes;
-	dev_dbg(d->dev, "blkeol pck: %u, duration: %u\n",
-		 blkeol_pck, blkeol_duration);
-
+	/*
+	 * See the manual figure 657 page 2203 for understanding the impact
+	 * of the different burst mode settings.
+	 */
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
-		/* Set up EOL clock for burst mode */
+		int blkeol_pck, blkeol_duration;
+		/*
+		 * Packet size at EOL for burst mode, this is only used
+		 * if DSI_VID_MAIN_CTL_REG_BLKEOL_MODE_LP_0 is NOT set,
+		 * but we instead send NULL or blanking packets at EOL.
+		 * This is given in number of bytes.
+		 *
+		 * See the manual page 2198 for the 13 reg_blkeol_pck bits.
+		 */
+		blkeol_pck = bpl - (mode->htotal * cpp) - 6;
+		if (blkeol_pck < 0) {
+			dev_err(d->dev, "video block does not fit on line!\n");
+			dev_err(d->dev,
+				"calculated bytes per line: %llu @ %d Hz\n",
+				bpl, mode->vrefresh);
+			dev_err(d->dev,
+				"bytes per line (blkline_pck) %u bytes\n",
+				blkline_pck);
+			dev_err(d->dev,
+				"blkeol_pck becomes %d bytes\n", blkeol_pck);
+			return;
+		}
+		dev_dbg(d->dev, "BLKEOL packet: %d bytes\n", blkeol_pck);
+
 		val = readl(d->regs + DSI_VID_BLKSIZE1);
+		val &= ~DSI_VID_BLKSIZE1_BLKEOL_PCK_MASK;
 		val |= blkeol_pck << DSI_VID_BLKSIZE1_BLKEOL_PCK_SHIFT;
 		writel(val, d->regs + DSI_VID_BLKSIZE1);
-		writel(blkeol_pck, d->regs + DSI_VID_VCA_SETTING2);
-
-		writel(blkeol_duration, d->regs + DSI_VID_PCK_TIME);
-		writel(blkeol_duration - 6, d->regs + DSI_VID_VCA_SETTING1);
+		/* Use the same value for exact burst limit */
+		val = blkeol_pck <<
+			DSI_VID_VCA_SETTING2_EXACT_BURST_LIMIT_SHIFT;
+		val &= DSI_VID_VCA_SETTING2_EXACT_BURST_LIMIT_MASK;
+		writel(val, d->regs + DSI_VID_VCA_SETTING2);
+		/*
+		 * This BLKEOL duration is claimed to be the duration in clock
+		 * cycles of the BLLP end-of-line (EOL) period for each line if
+		 * DSI_VID_MAIN_CTL_REG_BLKEOL_MODE_LP_0 is set.
+		 *
+		 * It is hard to trust the manuals' claim that this is in clock
+		 * cycles as we mimic the behaviour of the vendor code, which
+		 * appears to write a number of bytes that would have been
+		 * transferred on a single lane.
+		 *
+		 * See the manual figure 657 page 2203 and page 2198 for the 13
+		 * reg_blkeol_duration bits.
+		 *
+		 * FIXME: should this also be set up also for non-burst mode
+		 * according to figure 565 page 2202?
+		 */
+		blkeol_duration = DIV_ROUND_CLOSEST(blkeol_pck + 6,
+						    d->mdsi->lanes);
+		dev_dbg(d->dev, "BLKEOL duration: %d clock cycles\n",
+			blkeol_duration);
+
+		val = readl(d->regs + DSI_VID_PCK_TIME);
+		val &= ~DSI_VID_PCK_TIME_BLKEOL_DURATION_MASK;
+		val |= blkeol_duration <<
+			DSI_VID_PCK_TIME_BLKEOL_DURATION_SHIFT;
+		writel(val, d->regs + DSI_VID_PCK_TIME);
+
+		/* Max burst limit, this is given in bytes */
+		val = readl(d->regs + DSI_VID_VCA_SETTING1);
+		val &= ~DSI_VID_VCA_SETTING1_MAX_BURST_LIMIT_MASK;
+		val |= (blkeol_pck - 6) <<
+			DSI_VID_VCA_SETTING1_MAX_BURST_LIMIT_SHIFT;
+		writel(val, d->regs + DSI_VID_VCA_SETTING1);
 	}
 
 	/* Maximum line limit */
 	val = readl(d->regs + DSI_VID_VCA_SETTING2);
-	val |= blkline_pck <<
-		DSI_VID_VCA_SETTING2_EXACT_BURST_LIMIT_SHIFT;
+	val &= ~DSI_VID_VCA_SETTING2_MAX_LINE_LIMIT_MASK;
+	val |= (blkline_pck - 6) <<
+		DSI_VID_VCA_SETTING2_MAX_LINE_LIMIT_SHIFT;
 	writel(val, d->regs + DSI_VID_VCA_SETTING2);
-
-	/* Put IF1 into video mode */
-	val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
-	val |= DSI_MCTL_MAIN_DATA_CTL_IF1_MODE;
-	writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
-
-	/* Disable command mode on IF1 */
-	val = readl(d->regs + DSI_CMD_MODE_CTL);
-	val &= ~DSI_CMD_MODE_CTL_IF1_LP_EN;
-	writel(val, d->regs + DSI_CMD_MODE_CTL);
-
-	/* Enable some error interrupts */
-	val = readl(d->regs + DSI_VID_MODE_STS_CTL);
-	val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_VSYNC;
-	val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_DATA;
-	writel(val, d->regs + DSI_VID_MODE_STS_CTL);
-
-	/* Enable video mode */
-	val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
-	val |= DSI_MCTL_MAIN_DATA_CTL_VID_EN;
-	writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
+	dev_dbg(d->dev, "blkline pck: %d bytes\n", blkline_pck - 6);
 }
 
 static void mcde_dsi_start(struct mcde_dsi *d)
@@ -670,30 +816,25 @@ static void mcde_dsi_start(struct mcde_dsi *d)
 static void mcde_dsi_bridge_enable(struct drm_bridge *bridge)
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
+	u32 val;
+
+	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
+		/* Enable video mode */
+		val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
+		val |= DSI_MCTL_MAIN_DATA_CTL_VID_EN;
+		writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
+	}
 
 	dev_info(d->dev, "enable DSI master\n");
 };
 
-static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
-				     const struct drm_display_mode *mode,
-				     const struct drm_display_mode *adj)
+static void mcde_dsi_bridge_pre_enable(struct drm_bridge *bridge)
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
-	unsigned long pixel_clock_hz = mode->clock * 1000;
 	unsigned long hs_freq, lp_freq;
 	u32 val;
 	int ret;
 
-	if (!d->mdsi) {
-		dev_err(d->dev, "no DSI device attached to encoder!\n");
-		return;
-	}
-
-	dev_info(d->dev, "set DSI master to %dx%d %lu Hz %s mode\n",
-		 mode->hdisplay, mode->vdisplay, pixel_clock_hz,
-		 (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) ? "VIDEO" : "CMD"
-		);
-
 	/* Copy maximum clock frequencies */
 	if (d->mdsi->lp_rate)
 		lp_freq = d->mdsi->lp_rate;
@@ -732,7 +873,21 @@ static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
 			 d->hs_freq);
 
 	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
-		mcde_dsi_setup_video_mode(d, mode);
+		/* Put IF1 into video mode */
+		val = readl(d->regs + DSI_MCTL_MAIN_DATA_CTL);
+		val |= DSI_MCTL_MAIN_DATA_CTL_IF1_MODE;
+		writel(val, d->regs + DSI_MCTL_MAIN_DATA_CTL);
+
+		/* Disable command mode on IF1 */
+		val = readl(d->regs + DSI_CMD_MODE_CTL);
+		val &= ~DSI_CMD_MODE_CTL_IF1_LP_EN;
+		writel(val, d->regs + DSI_CMD_MODE_CTL);
+
+		/* Enable some error interrupts */
+		val = readl(d->regs + DSI_VID_MODE_STS_CTL);
+		val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_VSYNC;
+		val |= DSI_VID_MODE_STS_CTL_ERR_MISSING_DATA;
+		writel(val, d->regs + DSI_VID_MODE_STS_CTL);
 	} else {
 		/* Command mode, clear IF1 ID */
 		val = readl(d->regs + DSI_CMD_MODE_CTL);
@@ -746,6 +901,26 @@ static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
 	}
 }
 
+static void mcde_dsi_bridge_mode_set(struct drm_bridge *bridge,
+				     const struct drm_display_mode *mode,
+				     const struct drm_display_mode *adj)
+{
+	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
+
+	if (!d->mdsi) {
+		dev_err(d->dev, "no DSI device attached to encoder!\n");
+		return;
+	}
+
+	dev_info(d->dev, "set DSI master to %dx%d %u Hz %s mode\n",
+		 mode->hdisplay, mode->vdisplay, mode->clock * 1000,
+		 (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO) ? "VIDEO" : "CMD"
+		);
+
+	if (d->mdsi->mode_flags & MIPI_DSI_MODE_VIDEO)
+		mcde_dsi_setup_video_mode(d, mode);
+}
+
 static void mcde_dsi_wait_for_command_mode_stop(struct mcde_dsi *d)
 {
 	u32 val;
@@ -811,67 +986,23 @@ static void mcde_dsi_bridge_disable(struct drm_bridge *bridge)
 	clk_disable_unprepare(d->lp_clk);
 }
 
-/*
- * This connector needs no special handling, just use the default
- * helpers for everything. It's pretty dummy.
- */
-static const struct drm_connector_funcs mcde_dsi_connector_funcs = {
-	.reset = drm_atomic_helper_connector_reset,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = drm_connector_cleanup,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-static int mcde_dsi_get_modes(struct drm_connector *connector)
-{
-	struct mcde_dsi *d = connector_to_mcde_dsi(connector);
-
-	/* Just pass the question to the panel */
-	if (d->panel)
-		return drm_panel_get_modes(d->panel);
-
-	/* TODO: deal with bridges */
-
-	return 0;
-}
-
-static const struct drm_connector_helper_funcs
-mcde_dsi_connector_helper_funcs = {
-	.get_modes = mcde_dsi_get_modes,
-};
-
 static int mcde_dsi_bridge_attach(struct drm_bridge *bridge)
 {
 	struct mcde_dsi *d = bridge_to_mcde_dsi(bridge);
 	struct drm_device *drm = bridge->dev;
 	int ret;
 
-	drm_connector_helper_add(&d->connector,
-				 &mcde_dsi_connector_helper_funcs);
-
 	if (!drm_core_check_feature(drm, DRIVER_ATOMIC)) {
 		dev_err(d->dev, "we need atomic updates\n");
 		return -ENOTSUPP;
 	}
 
-	ret = drm_connector_init(drm, &d->connector,
-				 &mcde_dsi_connector_funcs,
-				 DRM_MODE_CONNECTOR_DSI);
-	if (ret) {
-		dev_err(d->dev, "failed to initialize DSI bridge connector\n");
-		return ret;
-	}
-	d->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
-	/* The encoder in the bridge attached to the DSI bridge */
-	drm_connector_attach_encoder(&d->connector, bridge->encoder);
-	/* Then we attach the DSI bridge to the output (panel etc) bridge */
+	/* Attach the DSI bridge to the output (panel etc) bridge */
 	ret = drm_bridge_attach(bridge->encoder, d->bridge_out, bridge);
 	if (ret) {
 		dev_err(d->dev, "failed to attach the DSI bridge\n");
 		return ret;
 	}
-	d->connector.status = connector_status_connected;
 
 	return 0;
 }
@@ -881,6 +1012,7 @@ static const struct drm_bridge_funcs mcde_dsi_bridge_funcs = {
 	.mode_set = mcde_dsi_bridge_mode_set,
 	.disable = mcde_dsi_bridge_disable,
 	.enable = mcde_dsi_bridge_enable,
+	.pre_enable = mcde_dsi_bridge_pre_enable,
 };
 
 static int mcde_dsi_bind(struct device *dev, struct device *master,
@@ -901,7 +1033,7 @@ static int mcde_dsi_bind(struct device *dev, struct device *master,
 	d->mcde = mcde;
 	/* If the display attached before binding, set this up */
 	if (d->mdsi)
-		d->mcde->mdsi = d->mdsi;
+		mcde_dsi_attach_to_mcde(d);
 
 	/* Obtain the clocks */
 	d->hs_clk = devm_clk_get(dev, "hs");
diff --git a/drivers/gpu/drm/mcde/mcde_dsi_regs.h b/drivers/gpu/drm/mcde/mcde_dsi_regs.h
index c9253321a3be..16551af1089e 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi_regs.h
+++ b/drivers/gpu/drm/mcde/mcde_dsi_regs.h
@@ -123,17 +123,6 @@
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LONGNOTSHORT BIT(3)
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHIFT 8
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_MASK 0x00003F00
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_TURN_ON_PERIPHERAL 50
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHUT_DOWN_PERIPHERAL 34
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_SHORT_WRITE_0 3
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_SHORT_WRITE_1 19
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_SHORT_WRITE_2 35
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_GENERIC_LONG_WRITE 41
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_SHORT_WRITE_0 5
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_SHORT_WRITE_1 21
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_LONG_WRITE 57
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_DCS_READ 6
-#define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SET_MAX_PKT_SIZE 55
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_ID_SHIFT 14
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_SIZE_SHIFT 16
 #define DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LP_EN BIT(21)
@@ -239,6 +228,7 @@
 
 #define DSI_VID_PCK_TIME 0x000000A8
 #define DSI_VID_PCK_TIME_BLKEOL_DURATION_SHIFT 0
+#define DSI_VID_PCK_TIME_BLKEOL_DURATION_MASK 0x00000FFF
 
 #define DSI_VID_DPHY_TIME 0x000000AC
 #define DSI_VID_DPHY_TIME_REG_LINE_DURATION_SHIFT 0
@@ -248,6 +238,16 @@
 
 #define DSI_VID_MODE_STS 0x000000BC
 #define DSI_VID_MODE_STS_VSG_RUNNING BIT(0)
+#define DSI_VID_MODE_STS_ERR_MISSING_DATA BIT(1)
+#define DSI_VID_MODE_STS_ERR_MISSING_HSYNC BIT(2)
+#define DSI_VID_MODE_STS_ERR_MISSING_VSYNC BIT(3)
+#define DSI_VID_MODE_STS_REG_ERR_SMALL_LENGTH BIT(4)
+#define DSI_VID_MODE_STS_REG_ERR_SMALL_HEIGHT BIT(5)
+#define DSI_VID_MODE_STS_ERR_BURSTWRITE BIT(6)
+#define DSI_VID_MODE_STS_ERR_LINEWRITE BIT(7)
+#define DSI_VID_MODE_STS_ERR_LONGREAD BIT(8)
+#define DSI_VID_MODE_STS_ERR_VRS_WRONG_LENGTH BIT(9)
+#define DSI_VID_MODE_STS_VSG_RECOVERY BIT(10)
 
 #define DSI_VID_VCA_SETTING1 0x000000C0
 #define DSI_VID_VCA_SETTING1_MAX_BURST_LIMIT_SHIFT 0
diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index 8067a4be8311..b7a82ed5788f 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -7,7 +7,6 @@ mediatek-drm-y := mtk_disp_color.o \
 		  mtk_drm_ddp.o \
 		  mtk_drm_ddp_comp.o \
 		  mtk_drm_drv.o \
-		  mtk_drm_fb.o \
 		  mtk_drm_gem.o \
 		  mtk_drm_plane.o \
 		  mtk_dsi.o \
@@ -21,7 +20,7 @@ obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o
 mediatek-drm-hdmi-objs := mtk_cec.o \
 			  mtk_hdmi.o \
 			  mtk_hdmi_ddc.o \
-                          mtk_mt2701_hdmi_phy.o \
+			  mtk_mt2701_hdmi_phy.o \
 			  mtk_mt8173_hdmi_phy.o \
 			  mtk_hdmi_phy.o
 
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_color.c b/drivers/gpu/drm/mediatek/mtk_disp_color.c
index 59de2a46aa49..6fb0d6983a4a 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_color.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_color.c
@@ -9,6 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -45,12 +46,12 @@ static inline struct mtk_disp_color *comp_to_color(struct mtk_ddp_comp *comp)
 
 static void mtk_color_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_color *color = comp_to_color(comp);
 
-	writel(w, comp->regs + DISP_COLOR_WIDTH(color));
-	writel(h, comp->regs + DISP_COLOR_HEIGHT(color));
+	mtk_ddp_write(cmdq_pkt, w, comp, DISP_COLOR_WIDTH(color));
+	mtk_ddp_write(cmdq_pkt, h, comp, DISP_COLOR_HEIGHT(color));
 }
 
 static void mtk_color_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 4a55bb6e2213..891d80c73e04 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -11,6 +11,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -124,14 +125,15 @@ static void mtk_ovl_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_ovl_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc)
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	if (w != 0 && h != 0)
-		writel_relaxed(h << 16 | w, comp->regs + DISP_REG_OVL_ROI_SIZE);
-	writel_relaxed(0x0, comp->regs + DISP_REG_OVL_ROI_BGCLR);
+		mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, comp,
+				      DISP_REG_OVL_ROI_SIZE);
+	mtk_ddp_write_relaxed(cmdq_pkt, 0x0, comp, DISP_REG_OVL_ROI_BGCLR);
 
-	writel(0x1, comp->regs + DISP_REG_OVL_RST);
-	writel(0x0, comp->regs + DISP_REG_OVL_RST);
+	mtk_ddp_write(cmdq_pkt, 0x1, comp, DISP_REG_OVL_RST);
+	mtk_ddp_write(cmdq_pkt, 0x0, comp, DISP_REG_OVL_RST);
 }
 
 static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp)
@@ -175,16 +177,16 @@ static int mtk_ovl_layer_check(struct mtk_ddp_comp *comp, unsigned int idx,
 	return 0;
 }
 
-static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
+static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx,
+			     struct cmdq_pkt *cmdq_pkt)
 {
-	unsigned int reg;
 	unsigned int gmc_thrshd_l;
 	unsigned int gmc_thrshd_h;
 	unsigned int gmc_value;
 	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 
-	writel(0x1, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
-
+	mtk_ddp_write(cmdq_pkt, 0x1, comp,
+		      DISP_REG_OVL_RDMA_CTRL(idx));
 	gmc_thrshd_l = GMC_THRESHOLD_LOW >>
 		      (GMC_THRESHOLD_BITS - ovl->data->gmc_bits);
 	gmc_thrshd_h = GMC_THRESHOLD_HIGH >>
@@ -194,22 +196,19 @@ static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
 	else
 		gmc_value = gmc_thrshd_l | gmc_thrshd_l << 8 |
 			    gmc_thrshd_h << 16 | gmc_thrshd_h << 24;
-	writel(gmc_value, comp->regs + DISP_REG_OVL_RDMA_GMC(idx));
-
-	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
-	reg = reg | BIT(idx);
-	writel(reg, comp->regs + DISP_REG_OVL_SRC_CON);
+	mtk_ddp_write(cmdq_pkt, gmc_value,
+		      comp, DISP_REG_OVL_RDMA_GMC(idx));
+	mtk_ddp_write_mask(cmdq_pkt, BIT(idx), comp,
+			   DISP_REG_OVL_SRC_CON, BIT(idx));
 }
 
-static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx)
+static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx,
+			      struct cmdq_pkt *cmdq_pkt)
 {
-	unsigned int reg;
-
-	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
-	reg = reg & ~BIT(idx);
-	writel(reg, comp->regs + DISP_REG_OVL_SRC_CON);
-
-	writel(0x0, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
+	mtk_ddp_write_mask(cmdq_pkt, 0, comp,
+			   DISP_REG_OVL_SRC_CON, BIT(idx));
+	mtk_ddp_write(cmdq_pkt, 0, comp,
+		      DISP_REG_OVL_RDMA_CTRL(idx));
 }
 
 static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
@@ -249,7 +248,8 @@ static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
 }
 
 static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
-				 struct mtk_plane_state *state)
+				 struct mtk_plane_state *state,
+				 struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 	struct mtk_plane_pending_state *pending = &state->pending;
@@ -260,11 +260,13 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	unsigned int src_size = (pending->height << 16) | pending->width;
 	unsigned int con;
 
-	if (!pending->enable)
-		mtk_ovl_layer_off(comp, idx);
+	if (!pending->enable) {
+		mtk_ovl_layer_off(comp, idx, cmdq_pkt);
+		return;
+	}
 
 	con = ovl_fmt_convert(ovl, fmt);
-	if (idx != 0)
+	if (state->base.fb->format->has_alpha)
 		con |= OVL_CON_AEN | OVL_CON_ALPHA;
 
 	if (pending->rotation & DRM_MODE_REFLECT_Y) {
@@ -277,14 +279,18 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 		addr += pending->pitch - 1;
 	}
 
-	writel_relaxed(con, comp->regs + DISP_REG_OVL_CON(idx));
-	writel_relaxed(pitch, comp->regs + DISP_REG_OVL_PITCH(idx));
-	writel_relaxed(src_size, comp->regs + DISP_REG_OVL_SRC_SIZE(idx));
-	writel_relaxed(offset, comp->regs + DISP_REG_OVL_OFFSET(idx));
-	writel_relaxed(addr, comp->regs + DISP_REG_OVL_ADDR(ovl, idx));
-
-	if (pending->enable)
-		mtk_ovl_layer_on(comp, idx);
+	mtk_ddp_write_relaxed(cmdq_pkt, con, comp,
+			      DISP_REG_OVL_CON(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, pitch, comp,
+			      DISP_REG_OVL_PITCH(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, src_size, comp,
+			      DISP_REG_OVL_SRC_SIZE(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, offset, comp,
+			      DISP_REG_OVL_OFFSET(idx));
+	mtk_ddp_write_relaxed(cmdq_pkt, addr, comp,
+			      DISP_REG_OVL_ADDR(ovl, idx));
+
+	mtk_ovl_layer_on(comp, idx, cmdq_pkt);
 }
 
 static void mtk_ovl_bgclr_in_on(struct mtk_ddp_comp *comp)
@@ -313,8 +319,6 @@ static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = {
 	.disable_vblank = mtk_ovl_disable_vblank,
 	.supported_rotations = mtk_ovl_supported_rotations,
 	.layer_nr = mtk_ovl_layer_nr,
-	.layer_on = mtk_ovl_layer_on,
-	.layer_off = mtk_ovl_layer_off,
 	.layer_check = mtk_ovl_layer_check,
 	.layer_config = mtk_ovl_layer_config,
 	.bgclr_in_on = mtk_ovl_bgclr_in_on,
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
index 405afef31407..0cb848d64206 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c
@@ -9,6 +9,7 @@
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
@@ -125,14 +126,16 @@ static void mtk_rdma_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width,
 			    unsigned int height, unsigned int vrefresh,
-			    unsigned int bpc)
+			    unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
 	unsigned int threshold;
 	unsigned int reg;
 	struct mtk_disp_rdma *rdma = comp_to_rdma(comp);
 
-	rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0, 0xfff, width);
-	rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_1, 0xfffff, height);
+	mtk_ddp_write_mask(cmdq_pkt, width, comp,
+			   DISP_REG_RDMA_SIZE_CON_0, 0xfff);
+	mtk_ddp_write_mask(cmdq_pkt, height, comp,
+			   DISP_REG_RDMA_SIZE_CON_1, 0xfffff);
 
 	/*
 	 * Enable FIFO underflow since DSI and DPI can't be blocked.
@@ -144,7 +147,7 @@ static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width,
 	reg = RDMA_FIFO_UNDERFLOW_EN |
 	      RDMA_FIFO_PSEUDO_SIZE(RDMA_FIFO_SIZE(rdma)) |
 	      RDMA_OUTPUT_VALID_FIFO_THRESHOLD(threshold);
-	writel(reg, comp->regs + DISP_REG_RDMA_FIFO_CON);
+	mtk_ddp_write(cmdq_pkt, reg, comp, DISP_REG_RDMA_FIFO_CON);
 }
 
 static unsigned int rdma_fmt_convert(struct mtk_disp_rdma *rdma,
@@ -190,7 +193,8 @@ static unsigned int mtk_rdma_layer_nr(struct mtk_ddp_comp *comp)
 }
 
 static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
-				  struct mtk_plane_state *state)
+				  struct mtk_plane_state *state,
+				  struct cmdq_pkt *cmdq_pkt)
 {
 	struct mtk_disp_rdma *rdma = comp_to_rdma(comp);
 	struct mtk_plane_pending_state *pending = &state->pending;
@@ -200,24 +204,27 @@ static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	unsigned int con;
 
 	con = rdma_fmt_convert(rdma, fmt);
-	writel_relaxed(con, comp->regs + DISP_RDMA_MEM_CON);
+	mtk_ddp_write_relaxed(cmdq_pkt, con, comp, DISP_RDMA_MEM_CON);
 
 	if (fmt == DRM_FORMAT_UYVY || fmt == DRM_FORMAT_YUYV) {
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_ENABLE, RDMA_MATRIX_ENABLE);
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_INT_MTX_SEL,
-				 RDMA_MATRIX_INT_MTX_BT601_to_RGB);
+		mtk_ddp_write_mask(cmdq_pkt, RDMA_MATRIX_ENABLE, comp,
+				   DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_ENABLE);
+		mtk_ddp_write_mask(cmdq_pkt, RDMA_MATRIX_INT_MTX_BT601_to_RGB,
+				   comp, DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_INT_MTX_SEL);
 	} else {
-		rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0,
-				 RDMA_MATRIX_ENABLE, 0);
+		mtk_ddp_write_mask(cmdq_pkt, 0, comp,
+				   DISP_REG_RDMA_SIZE_CON_0,
+				   RDMA_MATRIX_ENABLE);
 	}
+	mtk_ddp_write_relaxed(cmdq_pkt, addr, comp, DISP_RDMA_MEM_START_ADDR);
+	mtk_ddp_write_relaxed(cmdq_pkt, pitch, comp, DISP_RDMA_MEM_SRC_PITCH);
+	mtk_ddp_write(cmdq_pkt, RDMA_MEM_GMC, comp,
+		      DISP_RDMA_MEM_GMC_SETTING_0);
+	mtk_ddp_write_mask(cmdq_pkt, RDMA_MODE_MEMORY, comp,
+			   DISP_REG_RDMA_GLOBAL_CON, RDMA_MODE_MEMORY);
 
-	writel_relaxed(addr, comp->regs + DISP_RDMA_MEM_START_ADDR);
-	writel_relaxed(pitch, comp->regs + DISP_RDMA_MEM_SRC_PITCH);
-	writel(RDMA_MEM_GMC, comp->regs + DISP_RDMA_MEM_GMC_SETTING_0);
-	rdma_update_bits(comp, DISP_REG_RDMA_GLOBAL_CON,
-			 RDMA_MODE_MEMORY, RDMA_MODE_MEMORY);
 }
 
 static const struct mtk_ddp_comp_funcs mtk_disp_rdma_funcs = {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 3305a94fc930..0dfcd1787e65 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -5,6 +5,7 @@
 
 #include <linux/clk.h>
 #include <linux/pm_runtime.h>
+#include <linux/soc/mediatek/mtk-cmdq.h>
 
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
@@ -42,11 +43,20 @@ struct mtk_drm_crtc {
 	struct drm_plane		*planes;
 	unsigned int			layer_nr;
 	bool				pending_planes;
+	bool				pending_async_planes;
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct cmdq_client		*cmdq_client;
+	u32				cmdq_event;
+#endif
 
 	void __iomem			*config_regs;
 	struct mtk_disp_mutex		*mutex;
 	unsigned int			ddp_comp_nr;
 	struct mtk_ddp_comp		**ddp_comp;
+
+	/* lock for display hardware access */
+	struct mutex			hw_lock;
 };
 
 struct mtk_crtc_state {
@@ -230,6 +240,13 @@ struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
 	return NULL;
 }
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+static void ddp_cmdq_cb(struct cmdq_cb_data data)
+{
+	cmdq_pkt_destroy(data.data);
+}
+#endif
+
 static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_crtc *crtc = &mtk_crtc->base;
@@ -298,7 +315,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 		if (i == 1)
 			mtk_ddp_comp_bgclr_in_on(comp);
 
-		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc);
+		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc, NULL);
 		mtk_ddp_comp_start(comp);
 	}
 
@@ -313,7 +330,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 		comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
 		if (comp)
 			mtk_ddp_comp_layer_config(comp, local_layer,
-						  plane_state);
+						  plane_state, NULL);
 	}
 
 	return 0;
@@ -328,6 +345,7 @@ err_pm_runtime_put:
 static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_device *drm = mtk_crtc->base.dev;
+	struct drm_crtc *crtc = &mtk_crtc->base;
 	int i;
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
@@ -353,9 +371,17 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 	mtk_disp_mutex_unprepare(mtk_crtc->mutex);
 
 	pm_runtime_put(drm->dev);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irq(&crtc->dev->event_lock);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irq(&crtc->dev->event_lock);
+	}
 }
 
-static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
+static void mtk_crtc_ddp_config(struct drm_crtc *crtc,
+				struct cmdq_pkt *cmdq_handle)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_crtc_state *state = to_mtk_crtc_state(mtk_crtc->base.state);
@@ -371,7 +397,8 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 	if (state->pending_config) {
 		mtk_ddp_comp_config(comp, state->pending_width,
 				    state->pending_height,
-				    state->pending_vrefresh, 0);
+				    state->pending_vrefresh, 0,
+				    cmdq_handle);
 
 		state->pending_config = false;
 	}
@@ -391,11 +418,82 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 
 			if (comp)
 				mtk_ddp_comp_layer_config(comp, local_layer,
-							  plane_state);
+							  plane_state,
+							  cmdq_handle);
 			plane_state->pending.config = false;
 		}
 		mtk_crtc->pending_planes = false;
 	}
+
+	if (mtk_crtc->pending_async_planes) {
+		for (i = 0; i < mtk_crtc->layer_nr; i++) {
+			struct drm_plane *plane = &mtk_crtc->planes[i];
+			struct mtk_plane_state *plane_state;
+
+			plane_state = to_mtk_plane_state(plane->state);
+
+			if (!plane_state->pending.async_config)
+				continue;
+
+			comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
+							  &local_layer);
+
+			if (comp)
+				mtk_ddp_comp_layer_config(comp, local_layer,
+							  plane_state,
+							  cmdq_handle);
+			plane_state->pending.async_config = false;
+		}
+		mtk_crtc->pending_async_planes = false;
+	}
+}
+
+static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct cmdq_pkt *cmdq_handle;
+#endif
+	struct drm_crtc *crtc = &mtk_crtc->base;
+	struct mtk_drm_private *priv = crtc->dev->dev_private;
+	unsigned int pending_planes = 0, pending_async_planes = 0;
+	int i;
+
+	mutex_lock(&mtk_crtc->hw_lock);
+	for (i = 0; i < mtk_crtc->layer_nr; i++) {
+		struct drm_plane *plane = &mtk_crtc->planes[i];
+		struct mtk_plane_state *plane_state;
+
+		plane_state = to_mtk_plane_state(plane->state);
+		if (plane_state->pending.dirty) {
+			plane_state->pending.config = true;
+			plane_state->pending.dirty = false;
+			pending_planes |= BIT(i);
+		} else if (plane_state->pending.async_dirty) {
+			plane_state->pending.async_config = true;
+			plane_state->pending.async_dirty = false;
+			pending_async_planes |= BIT(i);
+		}
+	}
+	if (pending_planes)
+		mtk_crtc->pending_planes = true;
+	if (pending_async_planes)
+		mtk_crtc->pending_async_planes = true;
+
+	if (priv->data->shadow_register) {
+		mtk_disp_mutex_acquire(mtk_crtc->mutex);
+		mtk_crtc_ddp_config(crtc, NULL);
+		mtk_disp_mutex_release(mtk_crtc->mutex);
+	}
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (mtk_crtc->cmdq_client) {
+		cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE);
+		cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event);
+		cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event);
+		mtk_crtc_ddp_config(crtc, cmdq_handle);
+		cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle);
+	}
+#endif
+	mutex_unlock(&mtk_crtc->hw_lock);
 }
 
 int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
@@ -410,6 +508,20 @@ int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 	return 0;
 }
 
+void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
+			       struct drm_plane_state *new_state)
+{
+	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	const struct drm_plane_helper_funcs *plane_helper_funcs =
+			plane->helper_private;
+
+	if (!mtk_crtc->enabled)
+		return;
+
+	plane_helper_funcs->atomic_update(plane, new_state);
+	mtk_drm_crtc_hw_config(mtk_crtc);
+}
+
 static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 				       struct drm_crtc_state *old_state)
 {
@@ -457,6 +569,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 	mtk_crtc->pending_planes = true;
 
+	mtk_drm_crtc_hw_config(mtk_crtc);
 	/* Wait for planes to be disabled */
 	drm_crtc_wait_one_vblank(crtc);
 
@@ -488,34 +601,16 @@ static void mtk_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 				      struct drm_crtc_state *old_crtc_state)
 {
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
-	struct mtk_drm_private *priv = crtc->dev->dev_private;
-	unsigned int pending_planes = 0;
 	int i;
 
 	if (mtk_crtc->event)
 		mtk_crtc->pending_needs_vblank = true;
-	for (i = 0; i < mtk_crtc->layer_nr; i++) {
-		struct drm_plane *plane = &mtk_crtc->planes[i];
-		struct mtk_plane_state *plane_state;
-
-		plane_state = to_mtk_plane_state(plane->state);
-		if (plane_state->pending.dirty) {
-			plane_state->pending.config = true;
-			plane_state->pending.dirty = false;
-			pending_planes |= BIT(i);
-		}
-	}
-	if (pending_planes)
-		mtk_crtc->pending_planes = true;
 	if (crtc->state->color_mgmt_changed)
-		for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
+		for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 			mtk_ddp_gamma_set(mtk_crtc->ddp_comp[i], crtc->state);
-
-	if (priv->data->shadow_register) {
-		mtk_disp_mutex_acquire(mtk_crtc->mutex);
-		mtk_crtc_ddp_config(crtc);
-		mtk_disp_mutex_release(mtk_crtc->mutex);
-	}
+			mtk_ddp_ctm_set(mtk_crtc->ddp_comp[i], crtc->state);
+		}
+	mtk_drm_crtc_hw_config(mtk_crtc);
 }
 
 static const struct drm_crtc_funcs mtk_crtc_funcs = {
@@ -565,8 +660,12 @@ void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp)
 	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
 	struct mtk_drm_private *priv = crtc->dev->dev_private;
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (!priv->data->shadow_register && !mtk_crtc->cmdq_client)
+#else
 	if (!priv->data->shadow_register)
-		mtk_crtc_ddp_config(crtc);
+#endif
+		mtk_crtc_ddp_config(crtc, NULL);
 
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
@@ -633,6 +732,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int pipe = priv->num_pipes;
 	int ret;
 	int i;
+	bool has_ctm = false;
+	uint gamma_lut_size = 0;
 
 	if (!path)
 		return 0;
@@ -683,6 +784,14 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		}
 
 		mtk_crtc->ddp_comp[i] = comp;
+
+		if (comp->funcs) {
+			if (comp->funcs->gamma_set)
+				gamma_lut_size = MTK_LUT_SIZE;
+
+			if (comp->funcs->ctm_set)
+				has_ctm = true;
+		}
 	}
 
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
@@ -703,9 +812,28 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 				NULL, pipe);
 	if (ret < 0)
 		return ret;
-	drm_mode_crtc_set_gamma_size(&mtk_crtc->base, MTK_LUT_SIZE);
-	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, false, MTK_LUT_SIZE);
-	priv->num_pipes++;
 
+	if (gamma_lut_size)
+		drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size);
+	drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, has_ctm, gamma_lut_size);
+	priv->num_pipes++;
+	mutex_init(&mtk_crtc->hw_lock);
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	mtk_crtc->cmdq_client =
+			cmdq_mbox_create(dev, drm_crtc_index(&mtk_crtc->base),
+					 2000);
+	if (IS_ERR(mtk_crtc->cmdq_client)) {
+		dev_dbg(dev, "mtk_crtc %d failed to create mailbox client, writing register by CPU now\n",
+			drm_crtc_index(&mtk_crtc->base));
+		mtk_crtc->cmdq_client = NULL;
+	}
+	ret = of_property_read_u32_index(dev->of_node, "mediatek,gce-events",
+					 drm_crtc_index(&mtk_crtc->base),
+					 &mtk_crtc->cmdq_event);
+	if (ret)
+		dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n",
+			drm_crtc_index(&mtk_crtc->base));
+#endif
 	return 0;
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
index 6afe1c19557a..a2b4677a451c 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
@@ -21,5 +21,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			unsigned int path_len);
 int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
 			     struct mtk_plane_state *state);
+void mtk_drm_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
+			       struct drm_plane_state *plane_state);
 
 #endif /* MTK_DRM_CRTC_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 7f21307cda75..1f5a112bb034 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -12,7 +12,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
-
+#include <linux/soc/mediatek/mtk-cmdq.h>
 #include "mtk_drm_drv.h"
 #include "mtk_drm_plane.h"
 #include "mtk_drm_ddp_comp.h"
@@ -37,7 +37,15 @@
 #define CCORR_EN				BIT(0)
 #define DISP_CCORR_CFG				0x0020
 #define CCORR_RELAY_MODE			BIT(0)
+#define CCORR_ENGINE_EN				BIT(1)
+#define CCORR_GAMMA_OFF				BIT(2)
+#define CCORR_WGAMUT_SRC_CLIP			BIT(3)
 #define DISP_CCORR_SIZE				0x0030
+#define DISP_CCORR_COEF_0			0x0080
+#define DISP_CCORR_COEF_1			0x0084
+#define DISP_CCORR_COEF_2			0x0088
+#define DISP_CCORR_COEF_3			0x008C
+#define DISP_CCORR_COEF_4			0x0090
 
 #define DISP_DITHER_EN				0x0000
 #define DITHER_EN				BIT(0)
@@ -76,36 +84,84 @@
 #define DITHER_ADD_LSHIFT_G(x)			(((x) & 0x7) << 4)
 #define DITHER_ADD_RSHIFT_G(x)			(((x) & 0x7) << 0)
 
+void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+		   struct mtk_ddp_comp *comp, unsigned int offset)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt)
+		cmdq_pkt_write(cmdq_pkt, comp->subsys,
+			       comp->regs_pa + offset, value);
+	else
+#endif
+		writel(value, comp->regs + offset);
+}
+
+void mtk_ddp_write_relaxed(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			   struct mtk_ddp_comp *comp,
+			   unsigned int offset)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt)
+		cmdq_pkt_write(cmdq_pkt, comp->subsys,
+			       comp->regs_pa + offset, value);
+	else
+#endif
+		writel_relaxed(value, comp->regs + offset);
+}
+
+void mtk_ddp_write_mask(struct cmdq_pkt *cmdq_pkt,
+			unsigned int value,
+			struct mtk_ddp_comp *comp,
+			unsigned int offset,
+			unsigned int mask)
+{
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (cmdq_pkt) {
+		cmdq_pkt_write_mask(cmdq_pkt, comp->subsys,
+				    comp->regs_pa + offset, value, mask);
+	} else {
+#endif
+		u32 tmp = readl(comp->regs + offset);
+
+		tmp = (tmp & ~mask) | (value & mask);
+		writel(tmp, comp->regs + offset);
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	}
+#endif
+}
+
 void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc,
-		    unsigned int CFG)
+		    unsigned int CFG, struct cmdq_pkt *cmdq_pkt)
 {
 	/* If bpc equal to 0, the dithering function didn't be enabled */
 	if (bpc == 0)
 		return;
 
 	if (bpc >= MTK_MIN_BPC) {
-		writel(0, comp->regs + DISP_DITHER_5);
-		writel(0, comp->regs + DISP_DITHER_7);
-		writel(DITHER_LSB_ERR_SHIFT_R(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_R(MTK_MAX_BPC - bpc) |
-		       DITHER_NEW_BIT_MODE,
-		       comp->regs + DISP_DITHER_15);
-		writel(DITHER_LSB_ERR_SHIFT_B(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_B(MTK_MAX_BPC - bpc) |
-		       DITHER_LSB_ERR_SHIFT_G(MTK_MAX_BPC - bpc) |
-		       DITHER_ADD_LSHIFT_G(MTK_MAX_BPC - bpc),
-		       comp->regs + DISP_DITHER_16);
-		writel(DISP_DITHERING, comp->regs + CFG);
+		mtk_ddp_write(cmdq_pkt, 0, comp, DISP_DITHER_5);
+		mtk_ddp_write(cmdq_pkt, 0, comp, DISP_DITHER_7);
+		mtk_ddp_write(cmdq_pkt,
+			      DITHER_LSB_ERR_SHIFT_R(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_R(MTK_MAX_BPC - bpc) |
+			      DITHER_NEW_BIT_MODE,
+			      comp, DISP_DITHER_15);
+		mtk_ddp_write(cmdq_pkt,
+			      DITHER_LSB_ERR_SHIFT_B(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_B(MTK_MAX_BPC - bpc) |
+			      DITHER_LSB_ERR_SHIFT_G(MTK_MAX_BPC - bpc) |
+			      DITHER_ADD_LSHIFT_G(MTK_MAX_BPC - bpc),
+			      comp, DISP_DITHER_16);
+		mtk_ddp_write(cmdq_pkt, DISP_DITHERING, comp, CFG);
 	}
 }
 
 static void mtk_od_config(struct mtk_ddp_comp *comp, unsigned int w,
 			  unsigned int h, unsigned int vrefresh,
-			  unsigned int bpc)
+			  unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(w << 16 | h, comp->regs + DISP_OD_SIZE);
-	writel(OD_RELAYMODE, comp->regs + DISP_OD_CFG);
-	mtk_dither_set(comp, bpc, DISP_OD_CFG);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, comp, DISP_OD_SIZE);
+	mtk_ddp_write(cmdq_pkt, OD_RELAYMODE, comp, DISP_OD_CFG);
+	mtk_dither_set(comp, bpc, DISP_OD_CFG, cmdq_pkt);
 }
 
 static void mtk_od_start(struct mtk_ddp_comp *comp)
@@ -120,9 +176,9 @@ static void mtk_ufoe_start(struct mtk_ddp_comp *comp)
 
 static void mtk_aal_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
-			   unsigned int bpc)
+			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_AAL_SIZE);
 }
 
 static void mtk_aal_start(struct mtk_ddp_comp *comp)
@@ -137,10 +193,10 @@ static void mtk_aal_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_ccorr_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_CCORR_SIZE);
-	writel(CCORR_RELAY_MODE, comp->regs + DISP_CCORR_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_CCORR_SIZE);
+	mtk_ddp_write(cmdq_pkt, CCORR_ENGINE_EN, comp, DISP_CCORR_CFG);
 }
 
 static void mtk_ccorr_start(struct mtk_ddp_comp *comp)
@@ -153,12 +209,63 @@ static void mtk_ccorr_stop(struct mtk_ddp_comp *comp)
 	writel_relaxed(0x0, comp->regs + DISP_CCORR_EN);
 }
 
+/* Converts a DRM S31.32 value to the HW S1.10 format. */
+static u16 mtk_ctm_s31_32_to_s1_10(u64 in)
+{
+	u16 r;
+
+	/* Sign bit. */
+	r = in & BIT_ULL(63) ? BIT(11) : 0;
+
+	if ((in & GENMASK_ULL(62, 33)) > 0) {
+		/* identity value 0x100000000 -> 0x400, */
+		/* if bigger this, set it to max 0x7ff. */
+		r |= GENMASK(10, 0);
+	} else {
+		/* take the 11 most important bits. */
+		r |= (in >> 22) & GENMASK(10, 0);
+	}
+
+	return r;
+}
+
+static void mtk_ccorr_ctm_set(struct mtk_ddp_comp *comp,
+			      struct drm_crtc_state *state)
+{
+	struct drm_property_blob *blob = state->ctm;
+	struct drm_color_ctm *ctm;
+	const u64 *input;
+	uint16_t coeffs[9] = { 0 };
+	int i;
+	struct cmdq_pkt *cmdq_pkt = NULL;
+
+	if (!blob)
+		return;
+
+	ctm = (struct drm_color_ctm *)blob->data;
+	input = ctm->matrix;
+
+	for (i = 0; i < ARRAY_SIZE(coeffs); i++)
+		coeffs[i] = mtk_ctm_s31_32_to_s1_10(input[i]);
+
+	mtk_ddp_write(cmdq_pkt, coeffs[0] << 16 | coeffs[1],
+		      comp, DISP_CCORR_COEF_0);
+	mtk_ddp_write(cmdq_pkt, coeffs[2] << 16 | coeffs[3],
+		      comp, DISP_CCORR_COEF_1);
+	mtk_ddp_write(cmdq_pkt, coeffs[4] << 16 | coeffs[5],
+		      comp, DISP_CCORR_COEF_2);
+	mtk_ddp_write(cmdq_pkt, coeffs[6] << 16 | coeffs[7],
+		      comp, DISP_CCORR_COEF_3);
+	mtk_ddp_write(cmdq_pkt, coeffs[8] << 16,
+		      comp, DISP_CCORR_COEF_4);
+}
+
 static void mtk_dither_config(struct mtk_ddp_comp *comp, unsigned int w,
 			      unsigned int h, unsigned int vrefresh,
-			      unsigned int bpc)
+			      unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_DITHER_SIZE);
-	writel(DITHER_RELAY_MODE, comp->regs + DISP_DITHER_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_DITHER_SIZE);
+	mtk_ddp_write(cmdq_pkt, DITHER_RELAY_MODE, comp, DISP_DITHER_CFG);
 }
 
 static void mtk_dither_start(struct mtk_ddp_comp *comp)
@@ -173,10 +280,10 @@ static void mtk_dither_stop(struct mtk_ddp_comp *comp)
 
 static void mtk_gamma_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
-			     unsigned int bpc)
+			     unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	writel(h << 16 | w, comp->regs + DISP_GAMMA_SIZE);
-	mtk_dither_set(comp, bpc, DISP_GAMMA_CFG);
+	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_GAMMA_SIZE);
+	mtk_dither_set(comp, bpc, DISP_GAMMA_CFG, cmdq_pkt);
 }
 
 static void mtk_gamma_start(struct mtk_ddp_comp *comp)
@@ -223,6 +330,7 @@ static const struct mtk_ddp_comp_funcs ddp_ccorr = {
 	.config = mtk_ccorr_config,
 	.start = mtk_ccorr_start,
 	.stop = mtk_ccorr_stop,
+	.ctm_set = mtk_ccorr_ctm_set,
 };
 
 static const struct mtk_ddp_comp_funcs ddp_dither = {
@@ -326,6 +434,11 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	enum mtk_ddp_comp_type type;
 	struct device_node *larb_node;
 	struct platform_device *larb_pdev;
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	struct resource res;
+	struct cmdq_client_reg cmdq_reg;
+	int ret;
+#endif
 
 	if (comp_id < 0 || comp_id >= DDP_COMPONENT_ID_MAX)
 		return -EINVAL;
@@ -379,6 +492,19 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 
 	comp->larb_dev = &larb_pdev->dev;
 
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+	if (of_address_to_resource(node, 0, &res) != 0) {
+		dev_err(dev, "Missing reg in %s node\n", node->full_name);
+		return -EINVAL;
+	}
+	comp->regs_pa = res.start;
+
+	ret = cmdq_dev_get_client_reg(dev, &cmdq_reg, 0);
+	if (ret)
+		dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
+	else
+		comp->subsys = cmdq_reg.subsys;
+#endif
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 2f1e9e75b8da..debe36395fe7 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -69,27 +69,29 @@ enum mtk_ddp_comp_id {
 };
 
 struct mtk_ddp_comp;
-
+struct cmdq_pkt;
 struct mtk_ddp_comp_funcs {
 	void (*config)(struct mtk_ddp_comp *comp, unsigned int w,
-		       unsigned int h, unsigned int vrefresh, unsigned int bpc);
+		       unsigned int h, unsigned int vrefresh,
+		       unsigned int bpc, struct cmdq_pkt *cmdq_pkt);
 	void (*start)(struct mtk_ddp_comp *comp);
 	void (*stop)(struct mtk_ddp_comp *comp);
 	void (*enable_vblank)(struct mtk_ddp_comp *comp, struct drm_crtc *crtc);
 	void (*disable_vblank)(struct mtk_ddp_comp *comp);
 	unsigned int (*supported_rotations)(struct mtk_ddp_comp *comp);
 	unsigned int (*layer_nr)(struct mtk_ddp_comp *comp);
-	void (*layer_on)(struct mtk_ddp_comp *comp, unsigned int idx);
-	void (*layer_off)(struct mtk_ddp_comp *comp, unsigned int idx);
 	int (*layer_check)(struct mtk_ddp_comp *comp,
 			   unsigned int idx,
 			   struct mtk_plane_state *state);
 	void (*layer_config)(struct mtk_ddp_comp *comp, unsigned int idx,
-			     struct mtk_plane_state *state);
+			     struct mtk_plane_state *state,
+			     struct cmdq_pkt *cmdq_pkt);
 	void (*gamma_set)(struct mtk_ddp_comp *comp,
 			  struct drm_crtc_state *state);
 	void (*bgclr_in_on)(struct mtk_ddp_comp *comp);
 	void (*bgclr_in_off)(struct mtk_ddp_comp *comp);
+	void (*ctm_set)(struct mtk_ddp_comp *comp,
+			struct drm_crtc_state *state);
 };
 
 struct mtk_ddp_comp {
@@ -99,14 +101,17 @@ struct mtk_ddp_comp {
 	struct device *larb_dev;
 	enum mtk_ddp_comp_id id;
 	const struct mtk_ddp_comp_funcs *funcs;
+	resource_size_t regs_pa;
+	u8 subsys;
 };
 
 static inline void mtk_ddp_comp_config(struct mtk_ddp_comp *comp,
 				       unsigned int w, unsigned int h,
-				       unsigned int vrefresh, unsigned int bpc)
+				       unsigned int vrefresh, unsigned int bpc,
+				       struct cmdq_pkt *cmdq_pkt)
 {
 	if (comp->funcs && comp->funcs->config)
-		comp->funcs->config(comp, w, h, vrefresh, bpc);
+		comp->funcs->config(comp, w, h, vrefresh, bpc, cmdq_pkt);
 }
 
 static inline void mtk_ddp_comp_start(struct mtk_ddp_comp *comp)
@@ -151,20 +156,6 @@ static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp)
 	return 0;
 }
 
-static inline void mtk_ddp_comp_layer_on(struct mtk_ddp_comp *comp,
-					 unsigned int idx)
-{
-	if (comp->funcs && comp->funcs->layer_on)
-		comp->funcs->layer_on(comp, idx);
-}
-
-static inline void mtk_ddp_comp_layer_off(struct mtk_ddp_comp *comp,
-					  unsigned int idx)
-{
-	if (comp->funcs && comp->funcs->layer_off)
-		comp->funcs->layer_off(comp, idx);
-}
-
 static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
 					   unsigned int idx,
 					   struct mtk_plane_state *state)
@@ -176,10 +167,11 @@ static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
 
 static inline void mtk_ddp_comp_layer_config(struct mtk_ddp_comp *comp,
 					     unsigned int idx,
-					     struct mtk_plane_state *state)
+					     struct mtk_plane_state *state,
+					     struct cmdq_pkt *cmdq_pkt)
 {
 	if (comp->funcs && comp->funcs->layer_config)
-		comp->funcs->layer_config(comp, idx, state);
+		comp->funcs->layer_config(comp, idx, state, cmdq_pkt);
 }
 
 static inline void mtk_ddp_gamma_set(struct mtk_ddp_comp *comp,
@@ -201,6 +193,13 @@ static inline void mtk_ddp_comp_bgclr_in_off(struct mtk_ddp_comp *comp)
 		comp->funcs->bgclr_in_off(comp);
 }
 
+static inline void mtk_ddp_ctm_set(struct mtk_ddp_comp *comp,
+				   struct drm_crtc_state *state)
+{
+	if (comp->funcs && comp->funcs->ctm_set)
+		comp->funcs->ctm_set(comp, state);
+}
+
 int mtk_ddp_comp_get_id(struct device_node *node,
 			enum mtk_ddp_comp_type comp_type);
 int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
@@ -209,6 +208,13 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
 int mtk_ddp_comp_register(struct drm_device *drm, struct mtk_ddp_comp *comp);
 void mtk_ddp_comp_unregister(struct drm_device *drm, struct mtk_ddp_comp *comp);
 void mtk_dither_set(struct mtk_ddp_comp *comp, unsigned int bpc,
-		    unsigned int CFG);
-
+		    unsigned int CFG, struct cmdq_pkt *cmdq_pkt);
+enum mtk_ddp_comp_type mtk_ddp_comp_get_type(enum mtk_ddp_comp_id comp_id);
+void mtk_ddp_write(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+		   struct mtk_ddp_comp *comp, unsigned int offset);
+void mtk_ddp_write_relaxed(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			   struct mtk_ddp_comp *comp, unsigned int offset);
+void mtk_ddp_write_mask(struct cmdq_pkt *cmdq_pkt, unsigned int value,
+			struct mtk_ddp_comp *comp, unsigned int offset,
+			unsigned int mask);
 #endif /* MTK_DRM_DDP_COMP_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 84d14213d992..0563c6813333 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -16,8 +16,10 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_fourcc.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_of.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -27,7 +29,6 @@
 #include "mtk_drm_ddp.h"
 #include "mtk_drm_ddp_comp.h"
 #include "mtk_drm_drv.h"
-#include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 
 #define DRIVER_NAME "mediatek"
@@ -36,89 +37,27 @@
 #define DRIVER_MAJOR 1
 #define DRIVER_MINOR 0
 
-static void mtk_atomic_schedule(struct mtk_drm_private *private,
-				struct drm_atomic_state *state)
-{
-	private->commit.state = state;
-	schedule_work(&private->commit.work);
-}
-
-static void mtk_atomic_complete(struct mtk_drm_private *private,
-				struct drm_atomic_state *state)
-{
-	struct drm_device *drm = private->drm;
-
-	drm_atomic_helper_wait_for_fences(drm, state, false);
-
-	/*
-	 * Mediatek drm supports runtime PM, so plane registers cannot be
-	 * written when their crtc is disabled.
-	 *
-	 * The comment for drm_atomic_helper_commit states:
-	 *     For drivers supporting runtime PM the recommended sequence is
-	 *
-	 *     drm_atomic_helper_commit_modeset_disables(dev, state);
-	 *     drm_atomic_helper_commit_modeset_enables(dev, state);
-	 *     drm_atomic_helper_commit_planes(dev, state,
-	 *                                     DRM_PLANE_COMMIT_ACTIVE_ONLY);
-	 *
-	 * See the kerneldoc entries for these three functions for more details.
-	 */
-	drm_atomic_helper_commit_modeset_disables(drm, state);
-	drm_atomic_helper_commit_modeset_enables(drm, state);
-	drm_atomic_helper_commit_planes(drm, state,
-					DRM_PLANE_COMMIT_ACTIVE_ONLY);
-
-	drm_atomic_helper_wait_for_vblanks(drm, state);
-
-	drm_atomic_helper_cleanup_planes(drm, state);
-	drm_atomic_state_put(state);
-}
-
-static void mtk_atomic_work(struct work_struct *work)
-{
-	struct mtk_drm_private *private = container_of(work,
-			struct mtk_drm_private, commit.work);
-
-	mtk_atomic_complete(private, private->commit.state);
-}
+static const struct drm_mode_config_helper_funcs mtk_drm_mode_config_helpers = {
+	.atomic_commit_tail = drm_atomic_helper_commit_tail_rpm,
+};
 
-static int mtk_atomic_commit(struct drm_device *drm,
-			     struct drm_atomic_state *state,
-			     bool async)
+static struct drm_framebuffer *
+mtk_drm_mode_fb_create(struct drm_device *dev,
+		       struct drm_file *file,
+		       const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct mtk_drm_private *private = drm->dev_private;
-	int ret;
-
-	ret = drm_atomic_helper_prepare_planes(drm, state);
-	if (ret)
-		return ret;
+	const struct drm_format_info *info = drm_get_format_info(dev, cmd);
 
-	mutex_lock(&private->commit.lock);
-	flush_work(&private->commit.work);
+	if (info->num_planes != 1)
+		return ERR_PTR(-EINVAL);
 
-	ret = drm_atomic_helper_swap_state(state, true);
-	if (ret) {
-		mutex_unlock(&private->commit.lock);
-		drm_atomic_helper_cleanup_planes(drm, state);
-		return ret;
-	}
-
-	drm_atomic_state_get(state);
-	if (async)
-		mtk_atomic_schedule(private, state);
-	else
-		mtk_atomic_complete(private, state);
-
-	mutex_unlock(&private->commit.lock);
-
-	return 0;
+	return drm_gem_fb_create(dev, file, cmd);
 }
 
 static const struct drm_mode_config_funcs mtk_drm_mode_config_funcs = {
 	.fb_create = mtk_drm_mode_fb_create,
 	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = mtk_atomic_commit,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 static const enum mtk_ddp_comp_id mt2701_mtk_ddp_main[] = {
@@ -236,6 +175,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	drm->mode_config.max_width = 4096;
 	drm->mode_config.max_height = 4096;
 	drm->mode_config.funcs = &mtk_drm_mode_config_funcs;
+	drm->mode_config.helper_private = &mtk_drm_mode_config_helpers;
 
 	ret = component_bind_all(drm->dev, drm);
 	if (ret)
@@ -495,8 +435,6 @@ static int mtk_drm_probe(struct platform_device *pdev)
 	if (!private)
 		return -ENOMEM;
 
-	mutex_init(&private->commit.lock);
-	INIT_WORK(&private->commit.work, mtk_atomic_work);
 	private->data = of_device_get_match_data(dev);
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
index e03fea12ff59..17bc99b9f5d4 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
@@ -43,13 +43,6 @@ struct mtk_drm_private {
 	struct device_node *comp_node[DDP_COMPONENT_ID_MAX];
 	struct mtk_ddp_comp *ddp_comp[DDP_COMPONENT_ID_MAX];
 	const struct mtk_mmsys_driver_data *data;
-
-	struct {
-		struct drm_atomic_state *state;
-		struct work_struct work;
-		struct mutex lock;
-	} commit;
-
 	struct drm_atomic_state *suspend_state;
 
 	bool dma_parms_allocated;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
deleted file mode 100644
index 3f230a28a2dc..000000000000
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ /dev/null
@@ -1,92 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (c) 2015 MediaTek Inc.
- */
-
-#include <linux/dma-buf.h>
-#include <linux/dma-resv.h>
-
-#include <drm/drm_modeset_helper.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_gem.h>
-#include <drm/drm_gem_framebuffer_helper.h>
-
-#include "mtk_drm_drv.h"
-#include "mtk_drm_fb.h"
-#include "mtk_drm_gem.h"
-
-static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
-	.create_handle = drm_gem_fb_create_handle,
-	.destroy = drm_gem_fb_destroy,
-};
-
-static struct drm_framebuffer *mtk_drm_framebuffer_init(struct drm_device *dev,
-					const struct drm_mode_fb_cmd2 *mode,
-					struct drm_gem_object *obj)
-{
-	const struct drm_format_info *info = drm_get_format_info(dev, mode);
-	struct drm_framebuffer *fb;
-	int ret;
-
-	if (info->num_planes != 1)
-		return ERR_PTR(-EINVAL);
-
-	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
-	if (!fb)
-		return ERR_PTR(-ENOMEM);
-
-	drm_helper_mode_fill_fb_struct(dev, fb, mode);
-
-	fb->obj[0] = obj;
-
-	ret = drm_framebuffer_init(dev, fb, &mtk_drm_fb_funcs);
-	if (ret) {
-		DRM_ERROR("failed to initialize framebuffer\n");
-		kfree(fb);
-		return ERR_PTR(ret);
-	}
-
-	return fb;
-}
-
-struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
-					       struct drm_file *file,
-					       const struct drm_mode_fb_cmd2 *cmd)
-{
-	const struct drm_format_info *info = drm_get_format_info(dev, cmd);
-	struct drm_framebuffer *fb;
-	struct drm_gem_object *gem;
-	unsigned int width = cmd->width;
-	unsigned int height = cmd->height;
-	unsigned int size, bpp;
-	int ret;
-
-	if (info->num_planes != 1)
-		return ERR_PTR(-EINVAL);
-
-	gem = drm_gem_object_lookup(file, cmd->handles[0]);
-	if (!gem)
-		return ERR_PTR(-ENOENT);
-
-	bpp = info->cpp[0];
-	size = (height - 1) * cmd->pitches[0] + width * bpp;
-	size += cmd->offsets[0];
-
-	if (gem->size < size) {
-		ret = -EINVAL;
-		goto unreference;
-	}
-
-	fb = mtk_drm_framebuffer_init(dev, cmd, gem);
-	if (IS_ERR(fb)) {
-		ret = PTR_ERR(fb);
-		goto unreference;
-	}
-
-	return fb;
-
-unreference:
-	drm_gem_object_put_unlocked(gem);
-	return ERR_PTR(ret);
-}
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.h b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
deleted file mode 100644
index eb64d26001c6..000000000000
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (c) 2015 MediaTek Inc.
- */
-
-#ifndef MTK_DRM_FB_H
-#define MTK_DRM_FB_H
-
-struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
-					       struct drm_file *file,
-					       const struct drm_mode_fb_cmd2 *cmd);
-
-#endif /* MTK_DRM_FB_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 3b0cc91c7023..914cc7619cd7 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -7,13 +7,13 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_atomic_uapi.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 
 #include "mtk_drm_crtc.h"
 #include "mtk_drm_ddp_comp.h"
 #include "mtk_drm_drv.h"
-#include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 #include "mtk_drm_plane.h"
 
@@ -76,6 +76,50 @@ static void mtk_drm_plane_destroy_state(struct drm_plane *plane,
 	kfree(to_mtk_plane_state(state));
 }
 
+static int mtk_plane_atomic_async_check(struct drm_plane *plane,
+					struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+
+	if (plane != state->crtc->cursor)
+		return -EINVAL;
+
+	if (!plane->state)
+		return -EINVAL;
+
+	if (!plane->state->fb)
+		return -EINVAL;
+
+	if (state->state)
+		crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+								state->crtc);
+	else /* Special case for asynchronous cursor updates. */
+		crtc_state = state->crtc->state;
+
+	return drm_atomic_helper_check_plane_state(plane->state, crtc_state,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   DRM_PLANE_HELPER_NO_SCALING,
+						   true, true);
+}
+
+static void mtk_plane_atomic_async_update(struct drm_plane *plane,
+					  struct drm_plane_state *new_state)
+{
+	struct mtk_plane_state *state = to_mtk_plane_state(plane->state);
+
+	plane->state->crtc_x = new_state->crtc_x;
+	plane->state->crtc_y = new_state->crtc_y;
+	plane->state->crtc_h = new_state->crtc_h;
+	plane->state->crtc_w = new_state->crtc_w;
+	plane->state->src_x = new_state->src_x;
+	plane->state->src_y = new_state->src_y;
+	plane->state->src_h = new_state->src_h;
+	plane->state->src_w = new_state->src_w;
+	state->pending.async_dirty = true;
+
+	mtk_drm_crtc_async_update(new_state->crtc, plane, new_state);
+}
+
 static const struct drm_plane_funcs mtk_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
@@ -95,7 +139,7 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (!fb)
 		return 0;
 
-	if (!state->crtc)
+	if (WARN_ON(!state->crtc))
 		return 0;
 
 	ret = mtk_drm_crtc_plane_check(state->crtc, plane,
@@ -164,6 +208,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 	.atomic_check = mtk_plane_atomic_check,
 	.atomic_update = mtk_plane_atomic_update,
 	.atomic_disable = mtk_plane_atomic_disable,
+	.atomic_async_update = mtk_plane_atomic_async_update,
+	.atomic_async_check = mtk_plane_atomic_async_check,
 };
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.h b/drivers/gpu/drm/mediatek/mtk_drm_plane.h
index 760885e35b27..d454bece9535 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.h
@@ -22,6 +22,8 @@ struct mtk_plane_pending_state {
 	unsigned int			height;
 	unsigned int			rotation;
 	bool				dirty;
+	bool				async_dirty;
+	bool				async_config;
 };
 
 struct mtk_plane_state {
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index d77c9f484ce3..5fa1073cf26b 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -830,7 +830,7 @@ static int mtk_dsi_connector_get_modes(struct drm_connector *connector)
 {
 	struct mtk_dsi *dsi = connector_to_dsi(connector);
 
-	return drm_panel_get_modes(dsi->panel);
+	return drm_panel_get_modes(dsi->panel, connector);
 }
 
 static const struct drm_encoder_helper_funcs mtk_dsi_encoder_helper_funcs = {
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index c79b1f855d89..5e4a4dbda443 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1238,17 +1238,19 @@ static int mtk_hdmi_conn_mode_valid(struct drm_connector *conn,
 				    struct drm_display_mode *mode)
 {
 	struct mtk_hdmi *hdmi = hdmi_ctx_from_conn(conn);
+	struct drm_bridge *next_bridge;
 
 	dev_dbg(hdmi->dev, "xres=%d, yres=%d, refresh=%d, intl=%d clock=%d\n",
 		mode->hdisplay, mode->vdisplay, mode->vrefresh,
 		!!(mode->flags & DRM_MODE_FLAG_INTERLACE), mode->clock * 1000);
 
-	if (hdmi->bridge.next) {
+	next_bridge = drm_bridge_get_next_bridge(&hdmi->bridge);
+	if (next_bridge) {
 		struct drm_display_mode adjusted_mode;
 
 		drm_mode_copy(&adjusted_mode, mode);
-		if (!drm_bridge_mode_fixup(hdmi->bridge.next, mode,
-					   &adjusted_mode))
+		if (!drm_bridge_chain_mode_fixup(next_bridge, mode,
+						 &adjusted_mode))
 			return MODE_BAD;
 	}
 
@@ -1300,9 +1302,10 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge)
 	struct mtk_hdmi *hdmi = hdmi_ctx_from_bridge(bridge);
 	int ret;
 
-	ret = drm_connector_init(bridge->encoder->dev, &hdmi->conn,
-				 &mtk_hdmi_connector_funcs,
-				 DRM_MODE_CONNECTOR_HDMIA);
+	ret = drm_connector_init_with_ddc(bridge->encoder->dev, &hdmi->conn,
+					  &mtk_hdmi_connector_funcs,
+					  DRM_MODE_CONNECTOR_HDMIA,
+					  hdmi->ddc_adpt);
 	if (ret) {
 		dev_err(hdmi->dev, "Failed to initialize connector: %d\n", ret);
 		return ret;
diff --git a/drivers/gpu/drm/meson/Makefile b/drivers/gpu/drm/meson/Makefile
index c389e2399133..28a519cdf66b 100644
--- a/drivers/gpu/drm/meson/Makefile
+++ b/drivers/gpu/drm/meson/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 meson-drm-y := meson_drv.o meson_plane.o meson_crtc.o meson_venc_cvbs.o
 meson-drm-y += meson_viu.o meson_vpp.o meson_venc.o meson_vclk.o meson_overlay.o
+meson-drm-y += meson_rdma.o meson_osd_afbcd.o
 
 obj-$(CONFIG_DRM_MESON) += meson-drm.o
 obj-$(CONFIG_DRM_MESON_DW_HDMI) += meson_dw_hdmi.o
diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c
index 57ae1c13d1e6..e66b6271ff58 100644
--- a/drivers/gpu/drm/meson/meson_crtc.c
+++ b/drivers/gpu/drm/meson/meson_crtc.c
@@ -23,7 +23,9 @@
 #include "meson_registers.h"
 #include "meson_venc.h"
 #include "meson_viu.h"
+#include "meson_rdma.h"
 #include "meson_vpp.h"
+#include "meson_osd_afbcd.h"
 
 #define MESON_G12A_VIU_OFFSET	0x5ec0
 
@@ -35,7 +37,11 @@ struct meson_crtc {
 	struct meson_drm *priv;
 	void (*enable_osd1)(struct meson_drm *priv);
 	void (*enable_vd1)(struct meson_drm *priv);
+	void (*enable_osd1_afbc)(struct meson_drm *priv);
+	void (*disable_osd1_afbc)(struct meson_drm *priv);
 	unsigned int viu_offset;
+	bool vsync_forced;
+	bool vsync_disabled;
 };
 #define to_meson_crtc(x) container_of(x, struct meson_crtc, base)
 
@@ -46,6 +52,7 @@ static int meson_crtc_enable_vblank(struct drm_crtc *crtc)
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
+	meson_crtc->vsync_disabled = false;
 	meson_venc_enable_vsync(priv);
 
 	return 0;
@@ -56,7 +63,10 @@ static void meson_crtc_disable_vblank(struct drm_crtc *crtc)
 	struct meson_crtc *meson_crtc = to_meson_crtc(crtc);
 	struct meson_drm *priv = meson_crtc->priv;
 
-	meson_venc_disable_vsync(priv);
+	if (!meson_crtc->vsync_forced) {
+		meson_crtc->vsync_disabled = true;
+		meson_venc_disable_vsync(priv);
+	}
 }
 
 static const struct drm_crtc_funcs meson_crtc_funcs = {
@@ -236,6 +246,26 @@ static void meson_crtc_enable_osd1(struct meson_drm *priv)
 			    priv->io_base + _REG(VPP_MISC));
 }
 
+static void meson_crtc_g12a_enable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_relaxed(priv->viu.osd1_blk2_cfg4,
+		       priv->io_base + _REG(VIU_OSD1_BLK2_CFG_W4));
+
+	writel_bits_relaxed(OSD_MEM_LINEAR_ADDR, OSD_MEM_LINEAR_ADDR,
+			    priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+
+	writel_relaxed(priv->viu.osd1_blk1_cfg4,
+		       priv->io_base + _REG(VIU_OSD1_BLK1_CFG_W4));
+
+	meson_viu_g12a_enable_osd1_afbc(priv);
+
+	writel_bits_relaxed(OSD_MEM_LINEAR_ADDR, OSD_MEM_LINEAR_ADDR,
+			    priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+
+	writel_bits_relaxed(OSD_MALI_SRC_EN, OSD_MALI_SRC_EN,
+			    priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W0));
+}
+
 static void meson_g12a_crtc_enable_osd1(struct meson_drm *priv)
 {
 	writel_relaxed(priv->viu.osd_blend_din0_scope_h,
@@ -281,6 +311,8 @@ void meson_crtc_irq(struct meson_drm *priv)
 	if (priv->viu.osd1_enabled && priv->viu.osd1_commit) {
 		writel_relaxed(priv->viu.osd1_ctrl_stat,
 				priv->io_base + _REG(VIU_OSD1_CTRL_STAT));
+		writel_relaxed(priv->viu.osd1_ctrl_stat2,
+				priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[0],
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W0));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[1],
@@ -291,6 +323,20 @@ void meson_crtc_irq(struct meson_drm *priv)
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W3));
 		writel_relaxed(priv->viu.osd1_blk0_cfg[4],
 				priv->io_base + _REG(VIU_OSD1_BLK0_CFG_W4));
+
+		if (priv->viu.osd1_afbcd) {
+			if (meson_crtc->enable_osd1_afbc)
+				meson_crtc->enable_osd1_afbc(priv);
+		} else {
+			if (meson_crtc->disable_osd1_afbc)
+				meson_crtc->disable_osd1_afbc(priv);
+			if (priv->afbcd.ops) {
+				priv->afbcd.ops->reset(priv);
+				priv->afbcd.ops->disable(priv);
+			}
+			meson_crtc->vsync_forced = false;
+		}
+
 		writel_relaxed(priv->viu.osd_sc_ctrl0,
 				priv->io_base + _REG(VPP_OSD_SC_CTRL0));
 		writel_relaxed(priv->viu.osd_sc_i_wh_m1,
@@ -312,15 +358,25 @@ void meson_crtc_irq(struct meson_drm *priv)
 		writel_relaxed(priv->viu.osd_sc_v_ctrl0,
 				priv->io_base + _REG(VPP_OSD_VSC_CTRL0));
 
-		meson_canvas_config(priv->canvas, priv->canvas_id_osd1,
-				priv->viu.osd1_addr, priv->viu.osd1_stride,
-				priv->viu.osd1_height, MESON_CANVAS_WRAP_NONE,
-				MESON_CANVAS_BLKMODE_LINEAR, 0);
+		if (!priv->viu.osd1_afbcd)
+			meson_canvas_config(priv->canvas, priv->canvas_id_osd1,
+					    priv->viu.osd1_addr,
+					    priv->viu.osd1_stride,
+					    priv->viu.osd1_height,
+					    MESON_CANVAS_WRAP_NONE,
+					    MESON_CANVAS_BLKMODE_LINEAR, 0);
 
 		/* Enable OSD1 */
 		if (meson_crtc->enable_osd1)
 			meson_crtc->enable_osd1(priv);
 
+		if (priv->viu.osd1_afbcd) {
+			priv->afbcd.ops->reset(priv);
+			priv->afbcd.ops->setup(priv);
+			priv->afbcd.ops->enable(priv);
+			meson_crtc->vsync_forced = true;
+		}
+
 		priv->viu.osd1_commit = false;
 	}
 
@@ -357,7 +413,7 @@ void meson_crtc_irq(struct meson_drm *priv)
 					    MESON_CANVAS_WRAP_NONE,
 					    MESON_CANVAS_BLKMODE_LINEAR,
 					    MESON_CANVAS_ENDIAN_SWAP64);
-		};
+		}
 
 		writel_relaxed(priv->viu.vd1_if0_gen_reg,
 				priv->io_base + meson_crtc->viu_offset +
@@ -543,6 +599,9 @@ void meson_crtc_irq(struct meson_drm *priv)
 		priv->viu.vd1_commit = false;
 	}
 
+	if (meson_crtc->vsync_disabled)
+		return;
+
 	drm_crtc_handle_vblank(priv->crtc);
 
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
@@ -579,10 +638,20 @@ int meson_crtc_create(struct meson_drm *priv)
 		meson_crtc->enable_osd1 = meson_g12a_crtc_enable_osd1;
 		meson_crtc->enable_vd1 = meson_g12a_crtc_enable_vd1;
 		meson_crtc->viu_offset = MESON_G12A_VIU_OFFSET;
+		meson_crtc->enable_osd1_afbc =
+					meson_crtc_g12a_enable_osd1_afbc;
+		meson_crtc->disable_osd1_afbc =
+					meson_viu_g12a_disable_osd1_afbc;
 		drm_crtc_helper_add(crtc, &meson_g12a_crtc_helper_funcs);
 	} else {
 		meson_crtc->enable_osd1 = meson_crtc_enable_osd1;
 		meson_crtc->enable_vd1 = meson_crtc_enable_vd1;
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM)) {
+			meson_crtc->enable_osd1_afbc =
+					meson_viu_gxm_enable_osd1_afbc;
+			meson_crtc->disable_osd1_afbc =
+					meson_viu_gxm_disable_osd1_afbc;
+		}
 		drm_crtc_helper_add(crtc, &meson_crtc_helper_funcs);
 	}
 
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 397c33182f4f..b5f5eb7b4bb9 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -28,10 +28,12 @@
 #include "meson_drv.h"
 #include "meson_overlay.h"
 #include "meson_plane.h"
+#include "meson_osd_afbcd.h"
 #include "meson_registers.h"
 #include "meson_venc_cvbs.h"
 #include "meson_viu.h"
 #include "meson_vpp.h"
+#include "meson_rdma.h"
 
 #define DRIVER_NAME "meson"
 #define DRIVER_DESC "Amlogic Meson DRM driver"
@@ -184,6 +186,7 @@ static void meson_remove_framebuffers(void)
 static int meson_drv_bind_master(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	const struct meson_drm_match_data *match;
 	struct meson_drm *priv;
 	struct drm_device *drm;
 	struct resource *res;
@@ -196,6 +199,10 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 		return -ENODEV;
 	}
 
+	match = of_device_get_match_data(dev);
+	if (!match)
+		return -ENODEV;
+
 	drm = drm_dev_alloc(&meson_driver, dev);
 	if (IS_ERR(drm))
 		return PTR_ERR(drm);
@@ -208,8 +215,8 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	drm->dev_private = priv;
 	priv->drm = drm;
 	priv->dev = dev;
-
-	priv->compat = (enum vpu_compatible)of_device_get_match_data(priv->dev);
+	priv->compat = match->compat;
+	priv->afbcd.ops = match->afbcd_ops;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vpu");
 	regs = devm_ioremap_resource(dev, res);
@@ -289,6 +296,11 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 	meson_venc_init(priv);
 	meson_vpp_init(priv);
 	meson_viu_init(priv);
+	if (priv->afbcd.ops) {
+		ret = priv->afbcd.ops->init(priv);
+		if (ret)
+			return ret;
+	}
 
 	/* Encoder Initialization */
 
@@ -359,12 +371,16 @@ static void meson_drv_unbind(struct device *dev)
 		meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2);
 	}
 
+	if (priv->afbcd.ops) {
+		priv->afbcd.ops->reset(priv);
+		meson_rdma_free(priv);
+	}
+
 	drm_dev_unregister(drm);
 	drm_irq_uninstall(drm);
 	drm_kms_helper_poll_fini(drm);
 	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);
-
 }
 
 static const struct component_master_ops meson_drv_master_ops = {
@@ -393,6 +409,8 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev)
 	meson_venc_init(priv);
 	meson_vpp_init(priv);
 	meson_viu_init(priv);
+	if (priv->afbcd.ops)
+		priv->afbcd.ops->init(priv);
 
 	drm_mode_config_helper_resume(priv->drm);
 
@@ -481,15 +499,33 @@ static int meson_drv_probe(struct platform_device *pdev)
 	return 0;
 };
 
+static struct meson_drm_match_data meson_drm_gxbb_data = {
+	.compat = VPU_COMPATIBLE_GXBB,
+};
+
+static struct meson_drm_match_data meson_drm_gxl_data = {
+	.compat = VPU_COMPATIBLE_GXL,
+};
+
+static struct meson_drm_match_data meson_drm_gxm_data = {
+	.compat = VPU_COMPATIBLE_GXM,
+	.afbcd_ops = &meson_afbcd_gxm_ops,
+};
+
+static struct meson_drm_match_data meson_drm_g12a_data = {
+	.compat = VPU_COMPATIBLE_G12A,
+	.afbcd_ops = &meson_afbcd_g12a_ops,
+};
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "amlogic,meson-gxbb-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXBB },
+	  .data       = (void *)&meson_drm_gxbb_data },
 	{ .compatible = "amlogic,meson-gxl-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXL },
+	  .data       = (void *)&meson_drm_gxl_data },
 	{ .compatible = "amlogic,meson-gxm-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_GXM },
+	  .data       = (void *)&meson_drm_gxm_data },
 	{ .compatible = "amlogic,meson-g12a-vpu",
-	  .data       = (void *)VPU_COMPATIBLE_G12A },
+	  .data       = (void *)&meson_drm_g12a_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
diff --git a/drivers/gpu/drm/meson/meson_drv.h b/drivers/gpu/drm/meson/meson_drv.h
index 820d07bdd42a..04fdf3826643 100644
--- a/drivers/gpu/drm/meson/meson_drv.h
+++ b/drivers/gpu/drm/meson/meson_drv.h
@@ -16,6 +16,7 @@ struct drm_crtc;
 struct drm_device;
 struct drm_plane;
 struct meson_drm;
+struct meson_afbcd_ops;
 
 enum vpu_compatible {
 	VPU_COMPATIBLE_GXBB = 0,
@@ -24,6 +25,11 @@ enum vpu_compatible {
 	VPU_COMPATIBLE_G12A = 3,
 };
 
+struct meson_drm_match_data {
+	enum vpu_compatible compat;
+	struct meson_afbcd_ops *afbcd_ops;
+};
+
 struct meson_drm {
 	struct device *dev;
 	enum vpu_compatible compat;
@@ -47,11 +53,16 @@ struct meson_drm {
 		bool osd1_enabled;
 		bool osd1_interlace;
 		bool osd1_commit;
+		bool osd1_afbcd;
 		uint32_t osd1_ctrl_stat;
+		uint32_t osd1_ctrl_stat2;
 		uint32_t osd1_blk0_cfg[5];
+		uint32_t osd1_blk1_cfg4;
+		uint32_t osd1_blk2_cfg4;
 		uint32_t osd1_addr;
 		uint32_t osd1_stride;
 		uint32_t osd1_height;
+		uint32_t osd1_width;
 		uint32_t osd_sc_ctrl0;
 		uint32_t osd_sc_i_wh_m1;
 		uint32_t osd_sc_o_h_start_end;
@@ -122,6 +133,18 @@ struct meson_drm {
 		bool venc_repeat;
 		bool hdmi_use_enci;
 	} venc;
+
+	struct {
+		dma_addr_t addr_dma;
+		uint32_t *addr;
+		unsigned int offset;
+	} rdma;
+
+	struct {
+		struct meson_afbcd_ops *ops;
+		u64 modifier;
+		u32 format;
+	} afbcd;
 };
 
 static inline int meson_vpu_is_compatible(struct meson_drm *priv,
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.c b/drivers/gpu/drm/meson/meson_osd_afbcd.c
new file mode 100644
index 000000000000..f12e0271f166
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+
+#include <drm/drm_print.h>
+#include <drm/drm_fourcc.h>
+
+#include "meson_drv.h"
+#include "meson_registers.h"
+#include "meson_viu.h"
+#include "meson_rdma.h"
+#include "meson_osd_afbcd.h"
+
+/*
+ * DOC: Driver for the ARM FrameBuffer Compression Decoders
+ *
+ * The Amlogic GXM and G12A SoC families embeds an AFBC Decoder,
+ * to decode compressed buffers generated by the ARM Mali GPU.
+ *
+ * For the GXM Family, Amlogic designed their own Decoder, named in
+ * the vendor source as "MESON_AFBC", and a single decoder is available
+ * for the 2 OSD planes.
+ * This decoder is compatible with the AFBC 1.0 specifications and the
+ * Mali T820 GPU capabilities.
+ * It supports :
+ * - basic AFBC buffer for RGB32 only, thus YTR feature is mandatory
+ * - SPARSE layout and SPLIT layout
+ * - only 16x16 superblock
+ *
+ * The decoder reads the data from the SDRAM, decodes and sends the
+ * decoded pixel stream to the OSD1 Plane pixel composer.
+ *
+ * For the G12A Family, Amlogic integrated an ARM AFBC Decoder, named
+ * in the vendor source as "MALI_AFBC", and the decoder can decode up
+ * to 4 surfaces, one for each of the 4 available OSDs.
+ * This decoder is compatible with the AFBC 1.2 specifications for the
+ * Mali G31 and G52 GPUs.
+ * Is supports :
+ * - basic AFBC buffer for multiple RGB and YUV pixel formats
+ * - SPARSE layout and SPLIT layout
+ * - 16x16 and 32x8 "wideblk" superblocks
+ * - Tiled header
+ *
+ * The ARM AFBC Decoder independent from the VPU Pixel Pipeline, so
+ * the ARM AFBC Decoder reads the data from the SDRAM then decodes
+ * into a private internal physical address where the OSD1 Plane pixel
+ * composer unpacks the decoded data.
+ */
+
+/* Amlogic AFBC Decoder for GXM Family */
+
+#define OSD1_AFBCD_RGB32	0x15
+
+static int meson_gxm_afbcd_pixel_fmt(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return OSD1_AFBCD_RGB32;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static bool meson_gxm_afbcd_supported_fmt(u64 modifier, uint32_t format)
+{
+	if (modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_32x8)
+		return false;
+
+	if (!(modifier & AFBC_FORMAT_MOD_YTR))
+		return false;
+
+	return meson_gxm_afbcd_pixel_fmt(modifier, format) >= 0;
+}
+
+static int meson_gxm_afbcd_init(struct meson_drm *priv)
+{
+	return 0;
+}
+
+static int meson_gxm_afbcd_reset(struct meson_drm *priv)
+{
+	writel_relaxed(VIU_SW_RESET_OSD1_AFBCD,
+		       priv->io_base + _REG(VIU_SW_RESET));
+	writel_relaxed(0, priv->io_base + _REG(VIU_SW_RESET));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_enable(struct meson_drm *priv)
+{
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_ID_FIFO_THRD, 0x40) |
+		       OSD1_AFBCD_DEC_ENABLE,
+		       priv->io_base + _REG(OSD1_AFBCD_ENABLE));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_disable(struct meson_drm *priv)
+{
+	writel_bits_relaxed(OSD1_AFBCD_DEC_ENABLE, 0,
+			    priv->io_base + _REG(OSD1_AFBCD_ENABLE));
+
+	return 0;
+}
+
+static int meson_gxm_afbcd_setup(struct meson_drm *priv)
+{
+	u32 conv_lbuf_len;
+	u32 mode = FIELD_PREP(OSD1_AFBCD_MIF_URGENT, 3) |
+		   FIELD_PREP(OSD1_AFBCD_HOLD_LINE_NUM, 4) |
+		   FIELD_PREP(OSD1_AFBCD_RGBA_EXCHAN_CTRL, 0x34) |
+		   meson_gxm_afbcd_pixel_fmt(priv->afbcd.modifier,
+					     priv->afbcd.format);
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPARSE)
+		mode |= OSD1_AFBCD_HREG_HALF_BLOCK;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPLIT)
+		mode |= OSD1_AFBCD_HREG_BLOCK_SPLIT;
+
+	writel_relaxed(mode, priv->io_base + _REG(OSD1_AFBCD_MODE));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_HREG_VSIZE_IN,
+				  priv->viu.osd1_width) |
+		       FIELD_PREP(OSD1_AFBCD_HREG_HSIZE_IN,
+				  priv->viu.osd1_height),
+		       priv->io_base + _REG(OSD1_AFBCD_SIZE_IN));
+
+	writel_relaxed(priv->viu.osd1_addr >> 4,
+		       priv->io_base + _REG(OSD1_AFBCD_HDR_PTR));
+	writel_relaxed(priv->viu.osd1_addr >> 4,
+		       priv->io_base + _REG(OSD1_AFBCD_FRAME_PTR));
+	/* TOFIX: bits 31:24 are not documented, nor the meaning of 0xe4 */
+	writel_relaxed((0xe4 << 24) | (priv->viu.osd1_addr & 0xffffff),
+		       priv->io_base + _REG(OSD1_AFBCD_CHROMA_PTR));
+
+	if (priv->viu.osd1_width <= 128)
+		conv_lbuf_len = 32;
+	else if (priv->viu.osd1_width <= 256)
+		conv_lbuf_len = 64;
+	else if (priv->viu.osd1_width <= 512)
+		conv_lbuf_len = 128;
+	else if (priv->viu.osd1_width <= 1024)
+		conv_lbuf_len = 256;
+	else if (priv->viu.osd1_width <= 2048)
+		conv_lbuf_len = 512;
+	else
+		conv_lbuf_len = 1024;
+
+	writel_relaxed(conv_lbuf_len,
+		       priv->io_base + _REG(OSD1_AFBCD_CONV_CTRL));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_BGN_H, 0) |
+		       FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_END_H,
+				  priv->viu.osd1_width - 1),
+		       priv->io_base + _REG(OSD1_AFBCD_PIXEL_HSCOPE));
+
+	writel_relaxed(FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_BGN_V, 0) |
+		       FIELD_PREP(OSD1_AFBCD_DEC_PIXEL_END_V,
+				  priv->viu.osd1_height - 1),
+		       priv->io_base + _REG(OSD1_AFBCD_PIXEL_VSCOPE));
+
+	return 0;
+}
+
+struct meson_afbcd_ops meson_afbcd_gxm_ops = {
+	.init = meson_gxm_afbcd_init,
+	.reset = meson_gxm_afbcd_reset,
+	.enable = meson_gxm_afbcd_enable,
+	.disable = meson_gxm_afbcd_disable,
+	.setup = meson_gxm_afbcd_setup,
+	.supported_fmt = meson_gxm_afbcd_supported_fmt,
+};
+
+/* ARM AFBC Decoder for G12A Family */
+
+/* Amlogic G12A Mali AFBC Decoder supported formats */
+enum {
+	MAFBC_FMT_RGB565 = 0,
+	MAFBC_FMT_RGBA5551,
+	MAFBC_FMT_RGBA1010102,
+	MAFBC_FMT_YUV420_10B,
+	MAFBC_FMT_RGB888,
+	MAFBC_FMT_RGBA8888,
+	MAFBC_FMT_RGBA4444,
+	MAFBC_FMT_R8,
+	MAFBC_FMT_RG88,
+	MAFBC_FMT_YUV420_8B,
+	MAFBC_FMT_YUV422_8B = 11,
+	MAFBC_FMT_YUV422_10B = 14,
+};
+
+static int meson_g12a_afbcd_pixel_fmt(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+	/* fall through */
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return MAFBC_FMT_RGBA8888;
+	case DRM_FORMAT_RGB888:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+		return MAFBC_FMT_RGB888;
+	case DRM_FORMAT_RGB565:
+		/* YTR is forbidden for non XBGR formats */
+		if (modifier & AFBC_FORMAT_MOD_YTR)
+			return -EINVAL;
+		return MAFBC_FMT_RGB565;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static int meson_g12a_afbcd_bpp(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return 32;
+	case DRM_FORMAT_RGB888:
+		return 24;
+	case DRM_FORMAT_RGB565:
+		return 16;
+	/* TOFIX support mode formats */
+	default:
+		DRM_ERROR("unsupported afbc format[%08x]\n", format);
+		return 0;
+	}
+}
+
+static int meson_g12a_afbcd_fmt_to_blk_mode(u64 modifier, uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		return OSD_MALI_COLOR_MODE_RGBA8888;
+	case DRM_FORMAT_RGB888:
+		return OSD_MALI_COLOR_MODE_RGB888;
+	case DRM_FORMAT_RGB565:
+		return OSD_MALI_COLOR_MODE_RGB565;
+	/* TOFIX support mode formats */
+	default:
+		DRM_DEBUG("unsupported afbc format[%08x]\n", format);
+		return -EINVAL;
+	}
+}
+
+static bool meson_g12a_afbcd_supported_fmt(u64 modifier, uint32_t format)
+{
+	return meson_g12a_afbcd_pixel_fmt(modifier, format) >= 0;
+}
+
+static int meson_g12a_afbcd_init(struct meson_drm *priv)
+{
+	int ret;
+
+	ret = meson_rdma_init(priv);
+	if (ret)
+		return ret;
+
+	meson_rdma_setup(priv);
+
+	/* Handle AFBC Decoder reset manually */
+	writel_bits_relaxed(MALI_AFBCD_MANUAL_RESET, MALI_AFBCD_MANUAL_RESET,
+			    priv->io_base + _REG(MALI_AFBCD_TOP_CTRL));
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_reset(struct meson_drm *priv)
+{
+	meson_rdma_reset(priv);
+
+	meson_rdma_writel_sync(priv, VIU_SW_RESET_G12A_AFBC_ARB |
+			       VIU_SW_RESET_G12A_OSD1_AFBCD,
+			       VIU_SW_RESET);
+	meson_rdma_writel_sync(priv, 0, VIU_SW_RESET);
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_enable(struct meson_drm *priv)
+{
+	meson_rdma_writel_sync(priv, VPU_MAFBC_IRQ_SURFACES_COMPLETED |
+			       VPU_MAFBC_IRQ_CONFIGURATION_SWAPPED |
+			       VPU_MAFBC_IRQ_DECODE_ERROR |
+			       VPU_MAFBC_IRQ_DETILING_ERROR,
+			       VPU_MAFBC_IRQ_MASK);
+
+	meson_rdma_writel_sync(priv, VPU_MAFBC_S0_ENABLE,
+			       VPU_MAFBC_SURFACE_CFG);
+
+	meson_rdma_writel_sync(priv, VPU_MAFBC_DIRECT_SWAP,
+			       VPU_MAFBC_COMMAND);
+
+	/* This will enable the RDMA replaying the register writes on vsync */
+	meson_rdma_flush(priv);
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_disable(struct meson_drm *priv)
+{
+	writel_bits_relaxed(VPU_MAFBC_S0_ENABLE, 0,
+			    priv->io_base + _REG(VPU_MAFBC_SURFACE_CFG));
+
+	return 0;
+}
+
+static int meson_g12a_afbcd_setup(struct meson_drm *priv)
+{
+	u32 format = meson_g12a_afbcd_pixel_fmt(priv->afbcd.modifier,
+						priv->afbcd.format);
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_YTR)
+		format |= VPU_MAFBC_YUV_TRANSFORM;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_SPLIT)
+		format |= VPU_MAFBC_BLOCK_SPLIT;
+
+	if (priv->afbcd.modifier & AFBC_FORMAT_MOD_TILED)
+		format |= VPU_MAFBC_TILED_HEADER_EN;
+
+	if ((priv->afbcd.modifier & AFBC_FORMAT_MOD_BLOCK_SIZE_MASK) ==
+		AFBC_FORMAT_MOD_BLOCK_SIZE_32x8)
+		format |= FIELD_PREP(VPU_MAFBC_SUPER_BLOCK_ASPECT, 1);
+
+	meson_rdma_writel_sync(priv, format,
+			       VPU_MAFBC_FORMAT_SPECIFIER_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_addr,
+			       VPU_MAFBC_HEADER_BUF_ADDR_LOW_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width,
+			       VPU_MAFBC_BUFFER_WIDTH_S0);
+	meson_rdma_writel_sync(priv, ALIGN(priv->viu.osd1_height, 32),
+			       VPU_MAFBC_BUFFER_HEIGHT_S0);
+
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_BOUNDING_BOX_X_START_S0);
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width - 1,
+			       VPU_MAFBC_BOUNDING_BOX_X_END_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_BOUNDING_BOX_Y_START_S0);
+	meson_rdma_writel_sync(priv, priv->viu.osd1_height - 1,
+			       VPU_MAFBC_BOUNDING_BOX_Y_END_S0);
+
+	meson_rdma_writel_sync(priv, MESON_G12A_AFBCD_OUT_ADDR,
+			       VPU_MAFBC_OUTPUT_BUF_ADDR_LOW_S0);
+	meson_rdma_writel_sync(priv, 0,
+			       VPU_MAFBC_OUTPUT_BUF_ADDR_HIGH_S0);
+
+	meson_rdma_writel_sync(priv, priv->viu.osd1_width *
+			       (meson_g12a_afbcd_bpp(priv->afbcd.format) / 8),
+			       VPU_MAFBC_OUTPUT_BUF_STRIDE_S0);
+
+	return 0;
+}
+
+struct meson_afbcd_ops meson_afbcd_g12a_ops = {
+	.init = meson_g12a_afbcd_init,
+	.reset = meson_g12a_afbcd_reset,
+	.enable = meson_g12a_afbcd_enable,
+	.disable = meson_g12a_afbcd_disable,
+	.setup = meson_g12a_afbcd_setup,
+	.fmt_to_blk_mode = meson_g12a_afbcd_fmt_to_blk_mode,
+	.supported_fmt = meson_g12a_afbcd_supported_fmt,
+};
diff --git a/drivers/gpu/drm/meson/meson_osd_afbcd.h b/drivers/gpu/drm/meson/meson_osd_afbcd.h
new file mode 100644
index 000000000000..5e5523304f42
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_osd_afbcd.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_OSD_AFBCD_H
+#define __MESON_OSD_AFBCD_H
+
+#include "meson_drv.h"
+
+/* This is an internal address used to transfer pixel from AFBC to the VIU */
+#define MESON_G12A_AFBCD_OUT_ADDR	0x1000000
+
+struct meson_afbcd_ops {
+	int (*init)(struct meson_drm *priv);
+	int (*reset)(struct meson_drm *priv);
+	int (*enable)(struct meson_drm *priv);
+	int (*disable)(struct meson_drm *priv);
+	int (*setup)(struct meson_drm *priv);
+	int (*fmt_to_blk_mode)(u64 modifier, uint32_t format);
+	bool (*supported_fmt)(u64 modifier, uint32_t format);
+};
+
+extern struct meson_afbcd_ops meson_afbcd_gxm_ops;
+extern struct meson_afbcd_ops meson_afbcd_g12a_ops;
+
+#endif /* __MESON_OSD_AFBCD_H */
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index ed543227b00d..d5cbc47835bf 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -23,6 +23,7 @@
 #include "meson_plane.h"
 #include "meson_registers.h"
 #include "meson_viu.h"
+#include "meson_osd_afbcd.h"
 
 /* OSD_SCI_WH_M1 */
 #define SCI_WH_M1_W(w)			FIELD_PREP(GENMASK(28, 16), w)
@@ -92,12 +93,38 @@ static int meson_plane_atomic_check(struct drm_plane *plane,
 						   false, true);
 }
 
+#define MESON_MOD_AFBC_VALID_BITS (AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |	\
+				   AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |	\
+				   AFBC_FORMAT_MOD_YTR |		\
+				   AFBC_FORMAT_MOD_SPARSE |		\
+				   AFBC_FORMAT_MOD_SPLIT)
+
 /* Takes a fixed 16.16 number and converts it to integer. */
 static inline int64_t fixed16_to_int(int64_t value)
 {
 	return value >> 16;
 }
 
+static u32 meson_g12a_afbcd_line_stride(struct meson_drm *priv)
+{
+	u32 line_stride = 0;
+
+	switch (priv->afbcd.format) {
+	case DRM_FORMAT_RGB565:
+		line_stride = ((priv->viu.osd1_width << 4) + 127) >> 7;
+		break;
+	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		line_stride = ((priv->viu.osd1_width << 5) + 127) >> 7;
+		break;
+	}
+
+	return ((line_stride + 1) >> 1) << 1;
+}
+
 static void meson_plane_atomic_update(struct drm_plane *plane,
 				      struct drm_plane_state *old_state)
 {
@@ -126,59 +153,91 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	 */
 	spin_lock_irqsave(&priv->drm->event_lock, flags);
 
+	/* Check if AFBC decoder is required for this buffer */
+	if ((meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) ||
+	     meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) &&
+	    fb->modifier & DRM_FORMAT_MOD_ARM_AFBC(MESON_MOD_AFBC_VALID_BITS))
+		priv->viu.osd1_afbcd = true;
+	else
+		priv->viu.osd1_afbcd = false;
+
 	/* Enable OSD and BLK0, set max global alpha */
 	priv->viu.osd1_ctrl_stat = OSD_ENABLE |
 				   (0xFF << OSD_GLOBAL_ALPHA_SHIFT) |
 				   OSD_BLK0_ENABLE;
 
+	priv->viu.osd1_ctrl_stat2 = readl(priv->io_base +
+					  _REG(VIU_OSD1_CTRL_STAT2));
+
 	canvas_id_osd1 = priv->canvas_id_osd1;
 
 	/* Set up BLK0 to point to the right canvas */
-	priv->viu.osd1_blk0_cfg[0] = ((canvas_id_osd1 << OSD_CANVAS_SEL) |
-				      OSD_ENDIANNESS_LE);
+	priv->viu.osd1_blk0_cfg[0] = canvas_id_osd1 << OSD_CANVAS_SEL;
+
+	if (priv->viu.osd1_afbcd) {
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+			/* This is the internal decoding memory address */
+			priv->viu.osd1_blk1_cfg4 = MESON_G12A_AFBCD_OUT_ADDR;
+			priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_BE;
+			priv->viu.osd1_ctrl_stat2 |= OSD_PENDING_STAT_CLEAN;
+			priv->viu.osd1_ctrl_stat |= VIU_OSD1_CFG_SYN_EN;
+		}
+
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM)) {
+			priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_LE;
+			priv->viu.osd1_ctrl_stat2 |= OSD_DPATH_MALI_AFBCD;
+		}
+	} else {
+		priv->viu.osd1_blk0_cfg[0] |= OSD_ENDIANNESS_LE;
+
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+			priv->viu.osd1_ctrl_stat2 &= ~OSD_DPATH_MALI_AFBCD;
+	}
 
 	/* On GXBB, Use the old non-HDR RGB2YUV converter */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXBB))
 		priv->viu.osd1_blk0_cfg[0] |= OSD_OUTPUT_COLOR_RGB;
 
+	if (priv->viu.osd1_afbcd &&
+	    meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) {
+		priv->viu.osd1_blk0_cfg[0] |= OSD_MALI_SRC_EN |
+			priv->afbcd.ops->fmt_to_blk_mode(fb->modifier,
+							  fb->format->format);
+	} else {
+		switch (fb->format->format) {
+		case DRM_FORMAT_XRGB8888:
+		case DRM_FORMAT_ARGB8888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
+						OSD_COLOR_MATRIX_32_ARGB;
+			break;
+		case DRM_FORMAT_XBGR8888:
+		case DRM_FORMAT_ABGR8888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
+						OSD_COLOR_MATRIX_32_ABGR;
+			break;
+		case DRM_FORMAT_RGB888:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_24 |
+						OSD_COLOR_MATRIX_24_RGB;
+			break;
+		case DRM_FORMAT_RGB565:
+			priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_16 |
+						OSD_COLOR_MATRIX_16_RGB565;
+			break;
+		};
+	}
+
 	switch (fb->format->format) {
 	case DRM_FORMAT_XRGB8888:
-		/* For XRGB, replace the pixel's alpha by 0xFF */
-		writel_bits_relaxed(OSD_REPLACE_EN, OSD_REPLACE_EN,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ARGB;
-		break;
 	case DRM_FORMAT_XBGR8888:
 		/* For XRGB, replace the pixel's alpha by 0xFF */
-		writel_bits_relaxed(OSD_REPLACE_EN, OSD_REPLACE_EN,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ABGR;
+		priv->viu.osd1_ctrl_stat2 |= OSD_REPLACE_EN;
 		break;
 	case DRM_FORMAT_ARGB8888:
-		/* For ARGB, use the pixel's alpha */
-		writel_bits_relaxed(OSD_REPLACE_EN, 0,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ARGB;
-		break;
 	case DRM_FORMAT_ABGR8888:
 		/* For ARGB, use the pixel's alpha */
-		writel_bits_relaxed(OSD_REPLACE_EN, 0,
-				    priv->io_base + _REG(VIU_OSD1_CTRL_STAT2));
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_32 |
-					      OSD_COLOR_MATRIX_32_ABGR;
+		priv->viu.osd1_ctrl_stat2 &= ~OSD_REPLACE_EN;
 		break;
-	case DRM_FORMAT_RGB888:
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_24 |
-					      OSD_COLOR_MATRIX_24_RGB;
-		break;
-	case DRM_FORMAT_RGB565:
-		priv->viu.osd1_blk0_cfg[0] |= OSD_BLK_MODE_16 |
-					      OSD_COLOR_MATRIX_16_RGB565;
-		break;
-	};
+	}
 
 	/* Default scaler parameters */
 	vsc_bot_rcv_num = 0;
@@ -305,6 +364,17 @@ static void meson_plane_atomic_update(struct drm_plane *plane,
 	priv->viu.osd1_addr = gem->paddr;
 	priv->viu.osd1_stride = fb->pitches[0];
 	priv->viu.osd1_height = fb->height;
+	priv->viu.osd1_width = fb->width;
+
+	if (priv->viu.osd1_afbcd) {
+		priv->afbcd.modifier = fb->modifier;
+		priv->afbcd.format = fb->format->format;
+
+		/* Calculate decoder write stride */
+		if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+			priv->viu.osd1_blk2_cfg4 =
+				meson_g12a_afbcd_line_stride(priv);
+	}
 
 	if (!meson_plane->enabled) {
 		/* Reset OSD1 before enabling it on GXL+ SoCs */
@@ -326,6 +396,11 @@ static void meson_plane_atomic_disable(struct drm_plane *plane,
 	struct meson_plane *meson_plane = to_meson_plane(plane);
 	struct meson_drm *priv = meson_plane->priv;
 
+	if (priv->afbcd.ops) {
+		priv->afbcd.ops->reset(priv);
+		priv->afbcd.ops->disable(priv);
+	}
+
 	/* Disable OSD1 */
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
 		writel_bits_relaxed(VIU_OSD1_POSTBLD_SRC_OSD1, 0,
@@ -345,6 +420,42 @@ static const struct drm_plane_helper_funcs meson_plane_helper_funcs = {
 	.prepare_fb	= drm_gem_fb_prepare_fb,
 };
 
+static bool meson_plane_format_mod_supported(struct drm_plane *plane,
+					     u32 format, u64 modifier)
+{
+	struct meson_plane *meson_plane = to_meson_plane(plane);
+	struct meson_drm *priv = meson_plane->priv;
+	int i;
+
+	if (modifier == DRM_FORMAT_MOD_INVALID)
+		return false;
+
+	if (modifier == DRM_FORMAT_MOD_LINEAR)
+		return true;
+
+	if (!meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM) &&
+	    !meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		return false;
+
+	if (modifier & ~DRM_FORMAT_MOD_ARM_AFBC(MESON_MOD_AFBC_VALID_BITS))
+		return false;
+
+	for (i = 0 ; i < plane->modifier_count ; ++i)
+		if (plane->modifiers[i] == modifier)
+			break;
+
+	if (i == plane->modifier_count) {
+		DRM_DEBUG_KMS("Unsupported modifier\n");
+		return false;
+	}
+
+	if (priv->afbcd.ops && priv->afbcd.ops->supported_fmt)
+		return priv->afbcd.ops->supported_fmt(modifier, format);
+
+	DRM_DEBUG_KMS("AFBC Unsupported\n");
+	return false;
+}
+
 static const struct drm_plane_funcs meson_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
@@ -352,6 +463,7 @@ static const struct drm_plane_funcs meson_plane_funcs = {
 	.reset			= drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+	.format_mod_supported   = meson_plane_format_mod_supported,
 };
 
 static const uint32_t supported_drm_formats[] = {
@@ -363,10 +475,60 @@ static const uint32_t supported_drm_formats[] = {
 	DRM_FORMAT_RGB565,
 };
 
+static const uint64_t format_modifiers_afbc_gxm[] = {
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_YTR),
+	/* SPLIT mandates SPARSE, RGB modes mandates YTR */
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
+static const uint64_t format_modifiers_afbc_g12a[] = {
+	/*
+	 * - TOFIX Support AFBC modifiers for YUV formats (16x16 + TILED)
+	 * - SPLIT is mandatory for performances reasons when in 16x16
+	 *   block size
+	 * - 32x8 block size + SPLIT is mandatory with 4K frame size
+	 *   for performances reasons
+	 */
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_SPARSE),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_ARM_AFBC(AFBC_FORMAT_MOD_BLOCK_SIZE_32x8 |
+				AFBC_FORMAT_MOD_YTR |
+				AFBC_FORMAT_MOD_SPARSE |
+				AFBC_FORMAT_MOD_SPLIT),
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
+static const uint64_t format_modifiers_default[] = {
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID,
+};
+
 int meson_plane_create(struct meson_drm *priv)
 {
 	struct meson_plane *meson_plane;
 	struct drm_plane *plane;
+	const uint64_t *format_modifiers = format_modifiers_default;
 
 	meson_plane = devm_kzalloc(priv->drm->dev, sizeof(*meson_plane),
 				   GFP_KERNEL);
@@ -376,11 +538,16 @@ int meson_plane_create(struct meson_drm *priv)
 	meson_plane->priv = priv;
 	plane = &meson_plane->base;
 
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+		format_modifiers = format_modifiers_afbc_gxm;
+	else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+		format_modifiers = format_modifiers_afbc_g12a;
+
 	drm_universal_plane_init(priv->drm, plane, 0xFF,
 				 &meson_plane_funcs,
 				 supported_drm_formats,
 				 ARRAY_SIZE(supported_drm_formats),
-				 NULL,
+				 format_modifiers,
 				 DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane");
 
 	drm_plane_helper_add(plane, &meson_plane_helper_funcs);
diff --git a/drivers/gpu/drm/meson/meson_rdma.c b/drivers/gpu/drm/meson/meson_rdma.c
new file mode 100644
index 000000000000..130382178c63
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_rdma.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/dma-mapping.h>
+
+#include "meson_drv.h"
+#include "meson_registers.h"
+#include "meson_rdma.h"
+
+/*
+ * The VPU embeds a "Register DMA" that can write a sequence of registers
+ * on the VPU AHB bus, either manually or triggered by an internal IRQ
+ * event like VSYNC or a line input counter.
+ * The initial implementation handles a single channel (over 8), triggered
+ * by the VSYNC irq and does not handle the RDMA irq.
+ */
+
+#define RDMA_DESC_SIZE	(sizeof(uint32_t) * 2)
+
+int meson_rdma_init(struct meson_drm *priv)
+{
+	if (!priv->rdma.addr) {
+		/* Allocate a PAGE buffer */
+		priv->rdma.addr =
+			dma_alloc_coherent(priv->dev, SZ_4K,
+					   &priv->rdma.addr_dma,
+					   GFP_KERNEL);
+		if (!priv->rdma.addr)
+			return -ENOMEM;
+	}
+
+	priv->rdma.offset = 0;
+
+	writel_relaxed(RDMA_CTRL_SW_RESET,
+		       priv->io_base + _REG(RDMA_CTRL));
+	writel_relaxed(RDMA_DEFAULT_CONFIG |
+		       FIELD_PREP(RDMA_CTRL_AHB_WR_BURST, 3) |
+		       FIELD_PREP(RDMA_CTRL_AHB_RD_BURST, 0),
+		       priv->io_base + _REG(RDMA_CTRL));
+
+	return 0;
+}
+
+void meson_rdma_free(struct meson_drm *priv)
+{
+	if (!priv->rdma.addr && !priv->rdma.addr_dma)
+		return;
+
+	meson_rdma_stop(priv);
+
+	dma_free_coherent(priv->dev, SZ_4K,
+			  priv->rdma.addr, priv->rdma.addr_dma);
+
+	priv->rdma.addr = NULL;
+	priv->rdma.addr_dma = (dma_addr_t)0;
+}
+
+void meson_rdma_setup(struct meson_drm *priv)
+{
+	/* Channel 1: Write Flag, No Address Increment */
+	writel_bits_relaxed(RDMA_ACCESS_RW_FLAG_CHAN1 |
+			    RDMA_ACCESS_ADDR_INC_CHAN1,
+			    RDMA_ACCESS_RW_FLAG_CHAN1,
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+}
+
+void meson_rdma_stop(struct meson_drm *priv)
+{
+	writel_bits_relaxed(RDMA_IRQ_CLEAR_CHAN1,
+			    RDMA_IRQ_CLEAR_CHAN1,
+			    priv->io_base + _REG(RDMA_CTRL));
+
+	/* Stop Channel 1 */
+	writel_bits_relaxed(RDMA_ACCESS_TRIGGER_CHAN1,
+			    FIELD_PREP(RDMA_ACCESS_ADDR_INC_CHAN1,
+				       RDMA_ACCESS_TRIGGER_STOP),
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+}
+
+void meson_rdma_reset(struct meson_drm *priv)
+{
+	meson_rdma_stop(priv);
+
+	priv->rdma.offset = 0;
+}
+
+static void meson_rdma_writel(struct meson_drm *priv, uint32_t val,
+			      uint32_t reg)
+{
+	if (priv->rdma.offset >= (SZ_4K / RDMA_DESC_SIZE)) {
+		dev_warn_once(priv->dev, "%s: overflow\n", __func__);
+		return;
+	}
+
+	priv->rdma.addr[priv->rdma.offset++] = reg;
+	priv->rdma.addr[priv->rdma.offset++] = val;
+}
+
+/*
+ * This will add the register to the RDMA buffer and write it to the
+ * hardware at the same time.
+ * When meson_rdma_flush is called, the RDMA will replay the register
+ * writes in order.
+ */
+void meson_rdma_writel_sync(struct meson_drm *priv, uint32_t val, uint32_t reg)
+{
+	meson_rdma_writel(priv, val, reg);
+
+	writel_relaxed(val, priv->io_base + _REG(reg));
+}
+
+void meson_rdma_flush(struct meson_drm *priv)
+{
+	meson_rdma_stop(priv);
+
+	/* Start of Channel 1 register writes buffer */
+	writel(priv->rdma.addr_dma,
+	       priv->io_base + _REG(RDMA_AHB_START_ADDR_1));
+
+	/* Last byte on Channel 1 register writes buffer */
+	writel(priv->rdma.addr_dma + (priv->rdma.offset * RDMA_DESC_SIZE) - 1,
+	       priv->io_base + _REG(RDMA_AHB_END_ADDR_1));
+
+	/* Trigger Channel 1 on VSYNC event */
+	writel_bits_relaxed(RDMA_ACCESS_TRIGGER_CHAN1,
+			    FIELD_PREP(RDMA_ACCESS_TRIGGER_CHAN1,
+				       RDMA_ACCESS_TRIGGER_VSYNC),
+			    priv->io_base + _REG(RDMA_ACCESS_AUTO));
+
+	priv->rdma.offset = 0;
+}
diff --git a/drivers/gpu/drm/meson/meson_rdma.h b/drivers/gpu/drm/meson/meson_rdma.h
new file mode 100644
index 000000000000..3870bff7b47f
--- /dev/null
+++ b/drivers/gpu/drm/meson/meson_rdma.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2019 BayLibre, SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#ifndef __MESON_RDMA_H
+#define __MESON_RDMA_H
+
+#include "meson_drv.h"
+
+int meson_rdma_init(struct meson_drm *priv);
+void meson_rdma_free(struct meson_drm *priv);
+void meson_rdma_setup(struct meson_drm *priv);
+void meson_rdma_reset(struct meson_drm *priv);
+void meson_rdma_stop(struct meson_drm *priv);
+
+void meson_rdma_writel_sync(struct meson_drm *priv, uint32_t val, uint32_t reg);
+void meson_rdma_flush(struct meson_drm *priv);
+
+#endif /* __MESON_RDMA_H */
diff --git a/drivers/gpu/drm/meson/meson_registers.h b/drivers/gpu/drm/meson/meson_registers.h
index 05fce48ceee0..8ea00546cd4e 100644
--- a/drivers/gpu/drm/meson/meson_registers.h
+++ b/drivers/gpu/drm/meson/meson_registers.h
@@ -138,19 +138,25 @@
 #define VIU_ADDR_START 0x1a00
 #define VIU_ADDR_END 0x1aff
 #define VIU_SW_RESET 0x1a01
+#define		VIU_SW_RESET_OSD1_AFBCD		BIT(31)
+#define		VIU_SW_RESET_G12A_OSD1_AFBCD	BIT(21)
+#define		VIU_SW_RESET_G12A_AFBC_ARB	BIT(19)
 #define		VIU_SW_RESET_OSD1               BIT(0)
 #define VIU_MISC_CTRL0 0x1a06
 #define		VIU_CTRL0_VD1_AFBC_MASK         0x170000
 #define VIU_MISC_CTRL1 0x1a07
+#define		MALI_AFBC_MISC			GENMASK(15, 8)
 #define D2D3_INTF_LENGTH 0x1a08
 #define D2D3_INTF_CTRL0 0x1a09
 #define VIU_OSD1_CTRL_STAT 0x1a10
 #define		VIU_OSD1_OSD_BLK_ENABLE         BIT(0)
+#define		VIU_OSD1_OSD_MEM_MODE_LINEAR	BIT(2)
 #define		VIU_OSD1_POSTBLD_SRC_VD1        (1 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_VD2        (2 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_OSD1       (3 << 8)
 #define		VIU_OSD1_POSTBLD_SRC_OSD2       (4 << 8)
 #define		VIU_OSD1_OSD_ENABLE             BIT(21)
+#define		VIU_OSD1_CFG_SYN_EN             BIT(31)
 #define VIU_OSD1_CTRL_STAT2 0x1a2d
 #define VIU_OSD1_COLOR_ADDR 0x1a11
 #define VIU_OSD1_COLOR 0x1a12
@@ -181,6 +187,16 @@
 #define VIU_OSD1_FIFO_CTRL_STAT 0x1a2b
 #define VIU_OSD1_TEST_RDDATA 0x1a2c
 #define VIU_OSD1_PROT_CTRL 0x1a2e
+#define VIU_OSD1_MALI_UNPACK_CTRL 0x1a2f
+#define		VIU_OSD1_MALI_UNPACK_EN		BIT(31)
+#define		VIU_OSD1_MALI_AFBCD_R_REORDER	GENMASK(15, 12)
+#define		VIU_OSD1_MALI_AFBCD_G_REORDER	GENMASK(11, 8)
+#define		VIU_OSD1_MALI_AFBCD_B_REORDER	GENMASK(7, 4)
+#define		VIU_OSD1_MALI_AFBCD_A_REORDER	GENMASK(3, 0)
+#define		VIU_OSD1_MALI_REORDER_R		1
+#define		VIU_OSD1_MALI_REORDER_G		2
+#define		VIU_OSD1_MALI_REORDER_B		3
+#define		VIU_OSD1_MALI_REORDER_A		4
 #define VIU_OSD2_CTRL_STAT 0x1a30
 #define VIU_OSD2_CTRL_STAT2 0x1a4d
 #define VIU_OSD2_COLOR_ADDR 0x1a31
@@ -1195,11 +1211,59 @@
 #define RDMA_AHB_START_ADDR_7 0x110e
 #define RDMA_AHB_END_ADDR_7 0x110f
 #define RDMA_ACCESS_AUTO 0x1110
+#define		RDMA_ACCESS_TRIGGER_CHAN3	GENMASK(31, 24)
+#define		RDMA_ACCESS_TRIGGER_CHAN2	GENMASK(23, 16)
+#define		RDMA_ACCESS_TRIGGER_CHAN1	GENMASK(15, 8)
+#define		RDMA_ACCESS_TRIGGER_STOP	0
+#define		RDMA_ACCESS_TRIGGER_VSYNC	1
+#define		RDMA_ACCESS_TRIGGER_LINE	32
+#define		RDMA_ACCESS_RW_FLAG_CHAN3	BIT(7)
+#define		RDMA_ACCESS_RW_FLAG_CHAN2	BIT(6)
+#define		RDMA_ACCESS_RW_FLAG_CHAN1	BIT(5)
+#define		RDMA_ACCESS_ADDR_INC_CHAN3	BIT(3)
+#define		RDMA_ACCESS_ADDR_INC_CHAN2	BIT(2)
+#define		RDMA_ACCESS_ADDR_INC_CHAN1	BIT(1)
 #define RDMA_ACCESS_AUTO2 0x1111
+#define		RDMA_ACCESS_RW_FLAG_CHAN7	BIT(7)
+#define		RDMA_ACCESS_RW_FLAG_CHAN6	BIT(6)
+#define		RDMA_ACCESS_RW_FLAG_CHAN5	BIT(5)
+#define		RDMA_ACCESS_RW_FLAG_CHAN4	BIT(4)
+#define		RDMA_ACCESS_ADDR_INC_CHAN7	BIT(3)
+#define		RDMA_ACCESS_ADDR_INC_CHAN6	BIT(2)
+#define		RDMA_ACCESS_ADDR_INC_CHAN5	BIT(1)
+#define		RDMA_ACCESS_ADDR_INC_CHAN4	BIT(0)
 #define RDMA_ACCESS_AUTO3 0x1112
+#define		RDMA_ACCESS_TRIGGER_CHAN7	GENMASK(31, 24)
+#define		RDMA_ACCESS_TRIGGER_CHAN6	GENMASK(23, 16)
+#define		RDMA_ACCESS_TRIGGER_CHAN5	GENMASK(15, 8)
+#define		RDMA_ACCESS_TRIGGER_CHAN4	GENMASK(7, 0)
 #define RDMA_ACCESS_MAN 0x1113
+#define		RDMA_ACCESS_MAN_RW_FLAG		BIT(2)
+#define		RDMA_ACCESS_MAN_ADDR_INC	BIT(1)
+#define		RDMA_ACCESS_MAN_START		BIT(0)
 #define RDMA_CTRL 0x1114
+#define		RDMA_IRQ_CLEAR_CHAN7	BIT(31)
+#define		RDMA_IRQ_CLEAR_CHAN6	BIT(30)
+#define		RDMA_IRQ_CLEAR_CHAN5	BIT(29)
+#define		RDMA_IRQ_CLEAR_CHAN4	BIT(28)
+#define		RDMA_IRQ_CLEAR_CHAN3	BIT(27)
+#define		RDMA_IRQ_CLEAR_CHAN2	BIT(26)
+#define		RDMA_IRQ_CLEAR_CHAN1	BIT(25)
+#define		RDMA_IRQ_CLEAR_CHAN_MAN	BIT(24)
+#define		RDMA_DEFAULT_CONFIG	(BIT(7) | BIT(6))
+#define		RDMA_CTRL_AHB_WR_BURST	GENMASK(5, 4)
+#define		RDMA_CTRL_AHB_RD_BURST	GENMASK(3, 2)
+#define		RDMA_CTRL_SW_RESET	BIT(1)
+#define		RDMA_CTRL_FREE_CLK_EN	BIT(0)
 #define RDMA_STATUS 0x1115
+#define		RDMA_IRQ_STAT_CHAN7	BIT(31)
+#define		RDMA_IRQ_STAT_CHAN6	BIT(30)
+#define		RDMA_IRQ_STAT_CHAN5	BIT(29)
+#define		RDMA_IRQ_STAT_CHAN4	BIT(28)
+#define		RDMA_IRQ_STAT_CHAN3	BIT(27)
+#define		RDMA_IRQ_STAT_CHAN2	BIT(26)
+#define		RDMA_IRQ_STAT_CHAN1	BIT(25)
+#define		RDMA_IRQ_STAT_CHAN_MAN	BIT(24)
 #define RDMA_STATUS2 0x1116
 #define RDMA_STATUS3 0x1117
 #define L_GAMMA_CNTL_PORT 0x1400
@@ -1595,15 +1659,33 @@
 
 /* osd afbcd on gxtvbb */
 #define OSD1_AFBCD_ENABLE 0x31a0
+#define		OSD1_AFBCD_ID_FIFO_THRD			GENMASK(15, 9)
+#define		OSD1_AFBCD_DEC_ENABLE			BIT(8)
+#define		OSD1_AFBCD_FRM_START			BIT(0)
 #define OSD1_AFBCD_MODE 0x31a1
+#define		OSD1_AFBCD_SOFT_RESET			BIT(31)
+#define		OSD1_AFBCD_AXI_REORDER_MODE		BIT(28)
+#define		OSD1_AFBCD_MIF_URGENT			GENMASK(25, 24)
+#define		OSD1_AFBCD_HOLD_LINE_NUM		GENMASK(22, 16)
+#define		OSD1_AFBCD_RGBA_EXCHAN_CTRL		GENMASK(15, 8)
+#define		OSD1_AFBCD_HREG_BLOCK_SPLIT		BIT(6)
+#define		OSD1_AFBCD_HREG_HALF_BLOCK		BIT(5)
+#define		OSD1_AFBCD_HREG_PIXEL_PACKING_FMT	GENMASK(4, 0)
 #define OSD1_AFBCD_SIZE_IN 0x31a2
+#define		OSD1_AFBCD_HREG_VSIZE_IN		GENMASK(31, 16)
+#define		OSD1_AFBCD_HREG_HSIZE_IN		GENMASK(15, 0)
 #define OSD1_AFBCD_HDR_PTR 0x31a3
 #define OSD1_AFBCD_FRAME_PTR 0x31a4
 #define OSD1_AFBCD_CHROMA_PTR 0x31a5
 #define OSD1_AFBCD_CONV_CTRL 0x31a6
+#define		OSD1_AFBCD_CONV_LBUF_LEN		GENMASK(15, 0)
 #define OSD1_AFBCD_STATUS 0x31a8
 #define OSD1_AFBCD_PIXEL_HSCOPE 0x31a9
+#define		OSD1_AFBCD_DEC_PIXEL_BGN_H		GENMASK(31, 16)
+#define		OSD1_AFBCD_DEC_PIXEL_END_H		GENMASK(15, 0)
 #define OSD1_AFBCD_PIXEL_VSCOPE 0x31aa
+#define		OSD1_AFBCD_DEC_PIXEL_BGN_V		GENMASK(31, 16)
+#define		OSD1_AFBCD_DEC_PIXEL_END_V		GENMASK(15, 0)
 
 /* add for gxm and 962e dv core2 */
 #define DOLBY_CORE2A_SWAP_CTRL1	0x3434
@@ -1615,12 +1697,34 @@
 #define VPU_MAFBC_IRQ_CLEAR 0x3a02
 #define VPU_MAFBC_IRQ_MASK 0x3a03
 #define VPU_MAFBC_IRQ_STATUS 0x3a04
+#define		VPU_MAFBC_IRQ_SECURE_ID_ERROR		BIT(5)
+#define		VPU_MAFBC_IRQ_AXI_ERROR			BIT(4)
+#define		VPU_MAFBC_IRQ_DETILING_ERROR		BIT(3)
+#define		VPU_MAFBC_IRQ_DECODE_ERROR		BIT(2)
+#define		VPU_MAFBC_IRQ_CONFIGURATION_SWAPPED	BIT(1)
+#define		VPU_MAFBC_IRQ_SURFACES_COMPLETED	BIT(0)
 #define VPU_MAFBC_COMMAND 0x3a05
+#define		VPU_MAFBC_PENDING_SWAP	BIT(1)
+#define		VPU_MAFBC_DIRECT_SWAP	BIT(0)
 #define VPU_MAFBC_STATUS 0x3a06
+#define		VPU_MAFBC_ERROR		BIT(2)
+#define		VPU_MAFBC_SWAPPING	BIT(1)
+#define		VPU_MAFBC_ACTIVE	BIT(0)
 #define VPU_MAFBC_SURFACE_CFG 0x3a07
+#define		VPU_MAFBC_CONTINUOUS_DECODING_ENABLE	BIT(16)
+#define		VPU_MAFBC_S3_ENABLE			BIT(3)
+#define		VPU_MAFBC_S2_ENABLE			BIT(2)
+#define		VPU_MAFBC_S1_ENABLE			BIT(1)
+#define		VPU_MAFBC_S0_ENABLE			BIT(0)
 #define VPU_MAFBC_HEADER_BUF_ADDR_LOW_S0 0x3a10
 #define VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S0 0x3a11
 #define VPU_MAFBC_FORMAT_SPECIFIER_S0 0x3a12
+#define		VPU_MAFBC_PAYLOAD_LIMIT_EN	BIT(19)
+#define		VPU_MAFBC_TILED_HEADER_EN	BIT(18)
+#define		VPU_MAFBC_SUPER_BLOCK_ASPECT	GENMASK(17, 16)
+#define		VPU_MAFBC_BLOCK_SPLIT		BIT(9)
+#define		VPU_MAFBC_YUV_TRANSFORM		BIT(8)
+#define		VPU_MAFBC_PIXEL_FORMAT		GENMASK(3, 0)
 #define VPU_MAFBC_BUFFER_WIDTH_S0 0x3a13
 #define VPU_MAFBC_BUFFER_HEIGHT_S0 0x3a14
 #define VPU_MAFBC_BOUNDING_BOX_X_START_S0 0x3a15
@@ -1631,6 +1735,8 @@
 #define VPU_MAFBC_OUTPUT_BUF_ADDR_HIGH_S0 0x3a1a
 #define VPU_MAFBC_OUTPUT_BUF_STRIDE_S0 0x3a1b
 #define VPU_MAFBC_PREFETCH_CFG_S0 0x3a1c
+#define		VPU_MAFBC_PREFETCH_READ_DIRECTION_Y	BIT(1)
+#define		VPU_MAFBC_PREFETCH_READ_DIRECTION_X	BIT(0)
 
 #define VPU_MAFBC_HEADER_BUF_ADDR_LOW_S1 0x3a30
 #define VPU_MAFBC_HEADER_BUF_ADDR_HIGH_S1 0x3a31
@@ -1677,7 +1783,11 @@
 #define DOLBY_PATH_CTRL 0x1a0c
 #define		DOLBY_BYPASS_EN(val)            (val & 0xf)
 #define OSD_PATH_MISC_CTRL 0x1a0e
+#define		OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD	BIT(4)
+#define		OSD_PATH_OSD_AXI_SEL_OSD2_AFBCD	BIT(5)
+#define		OSD_PATH_OSD_AXI_SEL_OSD3_AFBCD	BIT(6)
 #define MALI_AFBCD_TOP_CTRL 0x1a0f
+#define		MALI_AFBCD_MANUAL_RESET		BIT(23)
 
 #define VIU_OSD_BLEND_CTRL 0x39b0
 #define		VIU_OSD_BLEND_REORDER(dest, src)      ((src) << (dest * 4))
diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c
index 68cf2c2eca5f..304f8ff1339c 100644
--- a/drivers/gpu/drm/meson/meson_viu.c
+++ b/drivers/gpu/drm/meson/meson_viu.c
@@ -7,6 +7,9 @@
  */
 
 #include <linux/export.h>
+#include <linux/bitfield.h>
+
+#include <drm/drm_fourcc.h>
 
 #include "meson_drv.h"
 #include "meson_viu.h"
@@ -335,6 +338,79 @@ void meson_viu_osd1_reset(struct meson_drm *priv)
 	meson_viu_load_matrix(priv);
 }
 
+#define OSD1_MALI_ORDER_ABGR				\
+	(FIELD_PREP(VIU_OSD1_MALI_AFBCD_A_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_A) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_B_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_B) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_G_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_G) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_R_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_R))
+
+#define OSD1_MALI_ORDER_ARGB				\
+	(FIELD_PREP(VIU_OSD1_MALI_AFBCD_A_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_A) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_B_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_R) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_G_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_G) |		\
+	 FIELD_PREP(VIU_OSD1_MALI_AFBCD_R_REORDER,	\
+		    VIU_OSD1_MALI_REORDER_B))
+
+void meson_viu_g12a_enable_osd1_afbc(struct meson_drm *priv)
+{
+	u32 afbc_order = OSD1_MALI_ORDER_ARGB;
+
+	/* Enable Mali AFBC Unpack */
+	writel_bits_relaxed(VIU_OSD1_MALI_UNPACK_EN,
+			    VIU_OSD1_MALI_UNPACK_EN,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+
+	switch (priv->afbcd.format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+		afbc_order = OSD1_MALI_ORDER_ABGR;
+		break;
+	}
+
+	/* Setup RGBA Reordering */
+	writel_bits_relaxed(VIU_OSD1_MALI_AFBCD_A_REORDER |
+			    VIU_OSD1_MALI_AFBCD_B_REORDER |
+			    VIU_OSD1_MALI_AFBCD_G_REORDER |
+			    VIU_OSD1_MALI_AFBCD_R_REORDER,
+			    afbc_order,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+
+	/* Select AFBCD path for OSD1 */
+	writel_bits_relaxed(OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD,
+			    OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD,
+			    priv->io_base + _REG(OSD_PATH_MISC_CTRL));
+}
+
+void meson_viu_g12a_disable_osd1_afbc(struct meson_drm *priv)
+{
+	/* Disable AFBCD path for OSD1 */
+	writel_bits_relaxed(OSD_PATH_OSD_AXI_SEL_OSD1_AFBCD, 0,
+			    priv->io_base + _REG(OSD_PATH_MISC_CTRL));
+
+	/* Disable AFBCD unpack */
+	writel_bits_relaxed(VIU_OSD1_MALI_UNPACK_EN, 0,
+			    priv->io_base + _REG(VIU_OSD1_MALI_UNPACK_CTRL));
+}
+
+void meson_viu_gxm_enable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_bits_relaxed(MALI_AFBC_MISC, FIELD_PREP(MALI_AFBC_MISC, 0x90),
+			    priv->io_base + _REG(VIU_MISC_CTRL1));
+}
+
+void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv)
+{
+	writel_bits_relaxed(MALI_AFBC_MISC, FIELD_PREP(MALI_AFBC_MISC, 0x00),
+			    priv->io_base + _REG(VIU_MISC_CTRL1));
+}
+
 static inline uint32_t meson_viu_osd_burst_length_reg(uint32_t length)
 {
 	uint32_t val = (((length & 0x80) % 24) / 12);
@@ -362,7 +438,7 @@ void meson_viu_init(struct meson_drm *priv)
 
 	/* Initialize OSD1 fifo control register */
 	reg = VIU_OSD_DDR_PRIORITY_URGENT |
-		VIU_OSD_HOLD_FIFO_LINES(4) |
+		VIU_OSD_HOLD_FIFO_LINES(31) |
 		VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
 		VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
 		VIU_OSD_FIFO_LIMITS(2);      /* fifo_lim: 2*16=32 */
@@ -420,8 +496,13 @@ void meson_viu_init(struct meson_drm *priv)
 
 		writel_bits_relaxed(DOLBY_BYPASS_EN(0xc), DOLBY_BYPASS_EN(0xc),
 				    priv->io_base + _REG(DOLBY_PATH_CTRL));
+
+		meson_viu_g12a_disable_osd1_afbc(priv);
 	}
 
+	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_GXM))
+		meson_viu_gxm_disable_osd1_afbc(priv);
+
 	priv->viu.osd1_enabled = false;
 	priv->viu.osd1_commit = false;
 	priv->viu.osd1_interlace = false;
diff --git a/drivers/gpu/drm/meson/meson_viu.h b/drivers/gpu/drm/meson/meson_viu.h
index a112e8d18850..e4a2f24d7c38 100644
--- a/drivers/gpu/drm/meson/meson_viu.h
+++ b/drivers/gpu/drm/meson/meson_viu.h
@@ -10,6 +10,8 @@
 #define __MESON_VIU_H
 
 /* OSDx_BLKx_CFG */
+#define OSD_MALI_SRC_EN		BIT(30)
+
 #define OSD_CANVAS_SEL		16
 
 #define OSD_ENDIANNESS_LE	BIT(15)
@@ -33,21 +35,38 @@
 #define OSD_COLOR_MATRIX_16_RGB655	(0x00 << 2)
 #define OSD_COLOR_MATRIX_16_RGB565	(0x04 << 2)
 
+#define OSD_MALI_COLOR_MODE_R8		(0 << 8)
+#define OSD_MALI_COLOR_MODE_YUV422	(1 << 8)
+#define OSD_MALI_COLOR_MODE_RGB565	(2 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA5551	(3 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA4444	(4 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA8888	(5 << 8)
+#define OSD_MALI_COLOR_MODE_RGB888	(7 << 8)
+#define OSD_MALI_COLOR_MODE_YUV422_10B	(8 << 8)
+#define OSD_MALI_COLOR_MODE_RGBA1010102	(9 << 8)
+
 #define OSD_INTERLACE_ENABLED	BIT(1)
 #define OSD_INTERLACE_ODD	BIT(0)
 #define OSD_INTERLACE_EVEN	(0)
 
 /* OSDx_CTRL_STAT */
 #define OSD_ENABLE		BIT(21)
+#define OSD_MEM_LINEAR_ADDR	BIT(2)
 #define OSD_BLK0_ENABLE		BIT(0)
 
 #define OSD_GLOBAL_ALPHA_SHIFT	12
 
 /* OSDx_CTRL_STAT2 */
+#define OSD_DPATH_MALI_AFBCD	BIT(15)
 #define OSD_REPLACE_EN		BIT(14)
 #define OSD_REPLACE_SHIFT	6
+#define OSD_PENDING_STAT_CLEAN	BIT(1)
 
 void meson_viu_osd1_reset(struct meson_drm *priv);
+void meson_viu_g12a_enable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_g12a_disable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_gxm_enable_osd1_afbc(struct meson_drm *priv);
+void meson_viu_gxm_disable_osd1_afbc(struct meson_drm *priv);
 void meson_viu_init(struct meson_drm *priv);
 
 #endif /* __MESON_VIU_H */
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index d5deecb93975..66df51607896 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -32,6 +32,7 @@
 #define __MGA_DRV_H__
 
 #include <linux/irqreturn.h>
+#include <linux/pci.h>
 #include <linux/slab.h>
 
 #include <drm/drm_agpsupport.h>
@@ -40,7 +41,6 @@
 #include <drm/drm_ioctl.h>
 #include <drm/drm_irq.h>
 #include <drm/drm_legacy.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_print.h>
 #include <drm/drm_sarea.h>
 #include <drm/drm_vblank.h>
diff --git a/drivers/gpu/drm/mgag200/Kconfig b/drivers/gpu/drm/mgag200/Kconfig
index aed11f4f4c55..d60aa4b9ccd4 100644
--- a/drivers/gpu/drm/mgag200/Kconfig
+++ b/drivers/gpu/drm/mgag200/Kconfig
@@ -8,8 +8,8 @@ config DRM_MGAG200
 	select DRM_TTM_HELPER
 	help
 	 This is a KMS driver for the MGA G200 server chips, it
-         does not support the original MGA G200 or any of the desktop
-         chips. It requires 0.3.0 of the modesetting userspace driver,
-         and a version of mga driver that will fail on KMS enabled
-         devices.
+	 does not support the original MGA G200 or any of the desktop
+	 chips. It requires 0.3.0 of the modesetting userspace driver,
+	 and a version of mga driver that will fail on KMS enabled
+	 devices.
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_cursor.c b/drivers/gpu/drm/mgag200/mgag200_cursor.c
index 79711dbb5b03..d491edd317ff 100644
--- a/drivers/gpu/drm/mgag200/mgag200_cursor.c
+++ b/drivers/gpu/drm/mgag200/mgag200_cursor.c
@@ -5,7 +5,7 @@
  * Author: Christopher Harvey <charvey@matrox.com>
  */
 
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "mgag200_drv.h"
 
@@ -208,8 +208,7 @@ int mgag200_cursor_init(struct mga_device *mdev)
 		return -ENOMEM;
 
 	for (i = 0; i < ncursors; ++i) {
-		gbo = drm_gem_vram_create(dev, &dev->vram_mm->bdev,
-					  size, 0, false);
+		gbo = drm_gem_vram_create(dev, size, 0);
 		if (IS_ERR(gbo)) {
 			ret = PTR_ERR(gbo);
 			goto err_drm_gem_vram_put;
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c
index b113876c2428..7a5bad2f57d7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.c
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.c
@@ -6,13 +6,13 @@
  *          Dave Airlie
  */
 
-#include <linux/module.h>
 #include <linux/console.h>
+#include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 
 #include "mgag200_drv.h"
@@ -27,6 +27,10 @@ int mgag200_modeset = -1;
 MODULE_PARM_DESC(modeset, "Disable/Enable modesetting");
 module_param_named(modeset, mgag200_modeset, int, 0400);
 
+int mgag200_hw_bug_no_startadd = -1;
+MODULE_PARM_DESC(modeset, "HW does not interpret scanout-buffer start address correctly");
+module_param_named(hw_bug_no_startadd, mgag200_hw_bug_no_startadd, int, 0400);
+
 static struct drm_driver driver;
 
 static const struct pci_device_id pciidlist[] = {
@@ -47,22 +51,66 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static int mga_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
+	struct drm_device *dev;
+	int ret;
+
 	drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, "mgag200drmfb");
 
-	return drm_get_pci_dev(pdev, ent, &driver);
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = mgag200_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_mgag200_driver_unload;
+
+	return 0;
+
+err_mgag200_driver_unload:
+	mgag200_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
 }
 
 static void mga_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-	drm_put_dev(dev);
+	drm_dev_unregister(dev);
+	mgag200_driver_unload(dev);
+	drm_dev_put(dev);
 }
 
 DEFINE_DRM_GEM_FOPS(mgag200_driver_fops);
 
 static bool mgag200_pin_bo_at_0(const struct mga_device *mdev)
 {
+	if (mgag200_hw_bug_no_startadd > 0) {
+		DRM_WARN_ONCE("Option hw_bug_no_startradd is enabled. Please "
+			      "report the output of 'lspci -vvnn' to "
+			      "<dri-devel@lists.freedesktop.org> if this "
+			      "option is required to make mgag200 work "
+			      "correctly on your system.\n");
+		return true;
+	} else if (!mgag200_hw_bug_no_startadd) {
+		return false;
+	}
 	return mdev->flags & MGAG200_FLAG_HW_BUG_NO_STARTADD;
 }
 
@@ -86,14 +134,11 @@ int mgag200_driver_dumb_create(struct drm_file *file,
 	if (mgag200_pin_bo_at_0(mdev))
 		pg_align = PFN_UP(mdev->mc.vram_size);
 
-	return drm_gem_vram_fill_create_dumb(file, dev, &dev->vram_mm->bdev,
-					     pg_align, false, args);
+	return drm_gem_vram_fill_create_dumb(file, dev, pg_align, 0, args);
 }
 
 static struct drm_driver driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET,
-	.load = mgag200_driver_load,
-	.unload = mgag200_driver_unload,
 	.fops = &mgag200_driver_fops,
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c
index 51d4037f00d4..9f4635916d32 100644
--- a/drivers/gpu/drm/mgag200/mgag200_i2c.c
+++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c
@@ -29,8 +29,7 @@
 #include <linux/export.h>
 #include <linux/i2c-algo-bit.h>
 #include <linux/i2c.h>
-
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "mgag200_drv.h"
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_main.c b/drivers/gpu/drm/mgag200/mgag200_main.c
index e1bc5b0aa774..e278b6a547bd 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -8,9 +8,10 @@
  *          Dave Airlie
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_pci.h>
 
 #include "mgag200_drv.h"
 
@@ -118,8 +119,11 @@ static int mgag200_device_init(struct drm_device *dev,
 		return -ENOMEM;
 
 	/* stash G200 SE model number for later use */
-	if (IS_G200_SE(mdev))
+	if (IS_G200_SE(mdev)) {
 		mdev->unique_rev_id = RREG32(0x1e24);
+		DRM_DEBUG("G200 SE unique revision id is 0x%x\n",
+			  mdev->unique_rev_id);
+	}
 
 	ret = mga_vram_init(mdev);
 	if (ret)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 5ec697148fc1..62a8e9ccb16d 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -9,10 +9,10 @@
  */
 
 #include <linux/delay.h>
+#include <linux/pci.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fourcc.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_ttm.c b/drivers/gpu/drm/mgag200/mgag200_ttm.c
index 99997d737362..e89657630ea7 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ttm.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ttm.c
@@ -26,7 +26,7 @@
  * Authors: Dave Airlie <airlied@redhat.com>
  */
 
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "mgag200_drv.h"
 
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 7ad14937fcdf..b67f88872726 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -506,6 +506,14 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	/*
+	 * Set the ICC path to maximum speed for now by multiplying the fastest
+	 * frequency by the bus width (8). We'll want to scale this later on to
+	 * improve battery life.
+	 */
+	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+
 	return gpu;
 
 fail:
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index b01388a9e89e..253d8d85daad 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -591,6 +591,14 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	/*
+	 * Set the ICC path to maximum speed for now by multiplying the fastest
+	 * frequency by the bus width (8). We'll want to scale this later on to
+	 * improve battery life.
+	 */
+	icc_set_bw(gpu->icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+	icc_set_bw(gpu->ocmem_icc_path, 0, Bps_to_icc(gpu->fast_rate) * 8);
+
 	return gpu;
 
 fail:
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index b02e2042547f..7d9e63e20ded 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -753,11 +753,18 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		gpu->funcs->flush(gpu, gpu->rb[0]);
 		if (!a5xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A5XX_RBBM_SECVID_TRUST_CNTL, 0x0);
+	} else {
+		return ret;
 	}
 
 	/* Last step - yield the ringbuffer */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
index f44553ec3193..ed78fee2a262 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h
@@ -16,11 +16,11 @@ The rules-ng-ng source files this header was generated from are:
 - /home/robclark/src/envytools/rnndb/adreno/a3xx.xml          (  83840 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a4xx.xml          ( 112086 bytes, from 2018-07-03 19:37:13)
 - /home/robclark/src/envytools/rnndb/adreno/a5xx.xml          ( 147240 bytes, from 2018-12-02 17:29:54)
-- /home/robclark/src/envytools/rnndb/adreno/a6xx.xml          ( 140790 bytes, from 2018-12-02 17:29:54)
+- /home/smasetty/playarea/envytools/rnndb/adreno/a6xx.xml     ( 161969 bytes, from 2019-11-29 07:18:16)
 - /home/robclark/src/envytools/rnndb/adreno/a6xx_gmu.xml      (  10431 bytes, from 2018-09-14 13:03:07)
 - /home/robclark/src/envytools/rnndb/adreno/ocmem.xml         (   1773 bytes, from 2018-07-03 19:37:13)
 
-Copyright (C) 2013-2018 by the following authors:
+Copyright (C) 2013-2019 by the following authors:
 - Rob Clark <robdclark@gmail.com> (robclark)
 - Ilia Mirkin <imirkin@alum.mit.edu> (imirkin)
 
@@ -2519,6 +2519,54 @@ static inline uint32_t A6XX_VBIF_TEST_BUS2_CTRL1_DATA_SEL(uint32_t val)
 
 #define REG_A6XX_VBIF_PERF_PWR_CNT_HIGH2			0x0000311a
 
+#define REG_A6XX_GBIF_SCACHE_CNTL1				0x00003c02
+
+#define REG_A6XX_GBIF_QSB_SIDE0					0x00003c03
+
+#define REG_A6XX_GBIF_QSB_SIDE1					0x00003c04
+
+#define REG_A6XX_GBIF_QSB_SIDE2					0x00003c05
+
+#define REG_A6XX_GBIF_QSB_SIDE3					0x00003c06
+
+#define REG_A6XX_GBIF_HALT					0x00003c45
+
+#define REG_A6XX_GBIF_HALT_ACK					0x00003c46
+
+#define REG_A6XX_GBIF_PERF_PWR_CNT_EN				0x00003cc0
+
+#define REG_A6XX_GBIF_PERF_CNT_SEL				0x00003cc2
+
+#define REG_A6XX_GBIF_PERF_PWR_CNT_SEL				0x00003cc3
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW0				0x00003cc4
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW1				0x00003cc5
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW2				0x00003cc6
+
+#define REG_A6XX_GBIF_PERF_CNT_LOW3				0x00003cc7
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH0				0x00003cc8
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH1				0x00003cc9
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH2				0x00003cca
+
+#define REG_A6XX_GBIF_PERF_CNT_HIGH3				0x00003ccb
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW0				0x00003ccc
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW1				0x00003ccd
+
+#define REG_A6XX_GBIF_PWR_CNT_LOW2				0x00003cce
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH0				0x00003ccf
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH1				0x00003cd0
+
+#define REG_A6XX_GBIF_PWR_CNT_HIGH2				0x00003cd1
+
 #define REG_A6XX_RB_WINDOW_OFFSET2				0x000088d4
 #define A6XX_RB_WINDOW_OFFSET2_WINDOW_OFFSET_DISABLE		0x80000000
 #define A6XX_RB_WINDOW_OFFSET2_X__MASK				0x00007fff
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 85f14feafdec..983afeaee737 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 #include <linux/clk.h>
 #include <linux/interconnect.h>
@@ -149,6 +149,8 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, unsigned long freq)
 		if (freq == gmu->gpu_freqs[perf_index])
 			break;
 
+	gmu->current_perf_index = perf_index;
+
 	__a6xx_gmu_set_freq(gmu, perf_index);
 }
 
@@ -433,6 +435,8 @@ static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev,
 
 static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 {
+	struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu);
+	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct platform_device *pdev = to_platform_device(gmu->dev);
 	void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc");
 	void __iomem *seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq");
@@ -480,20 +484,34 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu)
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 4, 0x30000);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 4, 0x0);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_MSGID + 8, 0x10108);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30090);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_ADDR + 8, 0x30080);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS1_CMD0_DATA + 8, 0x0);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_ENABLE_BANK, 7);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD_WAIT_FOR_CMPL_BANK, 0);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CONTROL, 0);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR, 0x30010);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA, 2);
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 4, 0x10108);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 4, 0x30000);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x2);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 4, 0x3);
+
+
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_MSGID + 8, 0x10108);
-	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080);
+	if (adreno_is_a618(adreno_gpu))
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30090);
+	else
+		pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_ADDR + 8, 0x30080);
 	pdc_write(pdcptr, REG_A6XX_PDC_GPU_TCS3_CMD0_DATA + 8, 0x3);
 
 	/* Setup GPU PDC */
@@ -741,8 +759,8 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_MASK, ~A6XX_HFI_IRQ_MASK);
 	enable_irq(gmu->hfi_irq);
 
-	/* Set the GPU to the highest power frequency */
-	__a6xx_gmu_set_freq(gmu, gmu->nr_gpu_freqs - 1);
+	/* Set the GPU to the current freq */
+	__a6xx_gmu_set_freq(gmu, gmu->current_perf_index);
 
 	/*
 	 * "enable" the GX power domain which won't actually do anything but it
@@ -1166,6 +1184,8 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu)
 	gmu->nr_gpu_freqs = a6xx_gmu_build_freq_table(&gpu->pdev->dev,
 		gmu->gpu_freqs, ARRAY_SIZE(gmu->gpu_freqs));
 
+	gmu->current_perf_index = gmu->nr_gpu_freqs - 1;
+
 	/* Build the list of RPMh votes that we'll send to the GMU */
 	return a6xx_gmu_rpmh_votes_init(gmu);
 }
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 39a26dd63674..2af91ed7ed0c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -63,6 +63,9 @@ struct a6xx_gmu {
 	struct clk_bulk_data *clocks;
 	struct clk *core_clk;
 
+	/* current performance index set externally */
+	int current_perf_index;
+
 	int nr_gpu_freqs;
 	unsigned long gpu_freqs[16];
 	u32 gx_arc_votes[16];
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index dc8ec2c94301..daf07800cde0 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2017-2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017-2019 The Linux Foundation. All rights reserved. */
 
 
 #include "msm_gem.h"
@@ -378,6 +378,18 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	int ret;
 
+	/*
+	 * During a previous slumber, GBIF halt is asserted to ensure
+	 * no further transaction can go through GPU before GPU
+	 * headswitch is turned off.
+	 *
+	 * This halt is deasserted once headswitch goes off but
+	 * incase headswitch doesn't goes off clear GBIF halt
+	 * here to ensure GPU wake-up doesn't fail because of
+	 * halted GPU transactions.
+	 */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+
 	/* Make sure the GMU keeps the GPU on while we set it up */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 
@@ -406,12 +418,17 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
 
-	/* enable hardware clockgating */
-	a6xx_set_hwcg(gpu, true);
+	/*
+	 * enable hardware clockgating
+	 * For now enable clock gating only for a630
+	 */
+	if (adreno_is_a630(adreno_gpu))
+		a6xx_set_hwcg(gpu, true);
 
-	/* VBIF start */
-	gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
+	/* VBIF/GBIF start*/
 	gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3);
+	if (adreno_is_a630(adreno_gpu))
+		gpu_write(gpu, REG_A6XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
 
 	/* Make all blocks contribute to the GPU BUSY perf counter */
 	gpu_write(gpu, REG_A6XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff);
@@ -537,12 +554,19 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		a6xx_flush(gpu, gpu->rb[0]);
 		if (!a6xx_idle(gpu, gpu->rb[0]))
 			return -EINVAL;
-	} else {
-		/* Print a warning so if we die, we know why */
+	} else if (ret == -ENODEV) {
+		/*
+		 * This device does not use zap shader (but print a warning
+		 * just in case someone got their dt wrong.. hopefully they
+		 * have a debug UART to realize the error of their ways...
+		 * if you mess this up you are about to crash horribly)
+		 */
 		dev_warn_once(gpu->dev->dev,
 			"Zap shader not enabled - using SECVID_TRUST_CNTL instead\n");
 		gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0);
 		ret = 0;
+	} else {
+		return ret;
 	}
 
 out:
@@ -724,6 +748,39 @@ static const u32 a6xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_CNTL, REG_A6XX_CP_RB_CNTL),
 };
 
+#define GBIF_CLIENT_HALT_MASK             BIT(0)
+#define GBIF_ARB_HALT_MASK                BIT(1)
+
+static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+
+	if(!a6xx_has_gbif(adreno_gpu)){
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf);
+		spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) &
+								0xf) == 0xf);
+		gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0);
+
+		return;
+	}
+
+	/* Halt new client requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK);
+	spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK);
+
+	/* Halt all AXI requests on GBIF */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK);
+	spin_until((gpu_read(gpu,  REG_A6XX_GBIF_HALT_ACK) &
+			(GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK);
+
+	/*
+	 * GMU needs DDR access in slumber path. Deassert GBIF halt now
+	 * to allow for GMU to access system memory.
+	 */
+	gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0);
+}
+
 static int a6xx_pm_resume(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -748,6 +805,16 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	devfreq_suspend_device(gpu->devfreq.devfreq);
 
+	/*
+	 * Make sure the GMU is idle before continuing (because some transitions
+	 * may use VBIF
+	 */
+	a6xx_gmu_wait_for_idle(&a6xx_gpu->gmu);
+
+	/* Clear the VBIF pipe before shutting down */
+	/* FIXME: This accesses the GPU - do we need to make sure it is on? */
+	a6xx_bus_clear_pending_transactions(adreno_gpu);
+
 	return a6xx_gmu_stop(a6xx_gpu);
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 64399554f2dd..7239b8b60939 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2017 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2017, 2019 The Linux Foundation. All rights reserved. */
 
 #ifndef __A6XX_GPU_H__
 #define __A6XX_GPU_H__
@@ -42,6 +42,13 @@ struct a6xx_gpu {
 #define A6XX_PROTECT_RDONLY(_reg, _len) \
 	((((_len) & 0x3FFF) << 18) | ((_reg) & 0x3FFFF))
 
+static inline bool a6xx_has_gbif(struct adreno_gpu *gpu)
+{
+	if(adreno_is_a630(gpu))
+		return false;
+
+	return true;
+}
 
 int a6xx_gmu_resume(struct a6xx_gpu *gpu);
 int a6xx_gmu_stop(struct a6xx_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 691c1a277d91..d6023ba8033c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. */
 
 #include <linux/ascii85.h>
 #include "msm_gem.h"
@@ -320,6 +320,7 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 {
 	struct resource *res;
 	void __iomem *cxdbg = NULL;
+	int nr_debugbus_blocks;
 
 	/* Set up the GX debug bus */
 
@@ -374,9 +375,11 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_3, 0);
 	}
 
-	a6xx_state->debugbus = state_kcalloc(a6xx_state,
-		ARRAY_SIZE(a6xx_debugbus_blocks),
-		sizeof(*a6xx_state->debugbus));
+	nr_debugbus_blocks = ARRAY_SIZE(a6xx_debugbus_blocks) +
+		(a6xx_has_gbif(to_adreno_gpu(gpu)) ? 1 : 0);
+
+	a6xx_state->debugbus = state_kcalloc(a6xx_state, nr_debugbus_blocks,
+			sizeof(*a6xx_state->debugbus));
 
 	if (a6xx_state->debugbus) {
 		int i;
@@ -388,15 +391,31 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 				&a6xx_state->debugbus[i]);
 
 		a6xx_state->nr_debugbus = ARRAY_SIZE(a6xx_debugbus_blocks);
+
+		/*
+		 * GBIF has same debugbus as of other GPU blocks, fall back to
+		 * default path if GPU uses GBIF, also GBIF uses exactly same
+		 * ID as of VBIF.
+		 */
+		if (a6xx_has_gbif(to_adreno_gpu(gpu))) {
+			a6xx_get_debugbus_block(gpu, a6xx_state,
+				&a6xx_gbif_debugbus_block,
+				&a6xx_state->debugbus[i]);
+
+			a6xx_state->nr_debugbus += 1;
+		}
 	}
 
-	a6xx_state->vbif_debugbus =
-		state_kcalloc(a6xx_state, 1,
-			sizeof(*a6xx_state->vbif_debugbus));
+	/*  Dump the VBIF debugbus on applicable targets */
+	if (!a6xx_has_gbif(to_adreno_gpu(gpu))) {
+		a6xx_state->vbif_debugbus =
+			state_kcalloc(a6xx_state, 1,
+					sizeof(*a6xx_state->vbif_debugbus));
 
-	if (a6xx_state->vbif_debugbus)
-		a6xx_get_vbif_debugbus_block(gpu, a6xx_state,
-			a6xx_state->vbif_debugbus);
+		if (a6xx_state->vbif_debugbus)
+			a6xx_get_vbif_debugbus_block(gpu, a6xx_state,
+					a6xx_state->vbif_debugbus);
+	}
 
 	if (cxdbg) {
 		a6xx_state->cx_debugbus =
@@ -770,14 +789,16 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 		&a6xx_state->gmu_registers[1]);
 }
 
+#define A6XX_GBIF_REGLIST_SIZE   1
 static void a6xx_get_registers(struct msm_gpu *gpu,
 		struct a6xx_gpu_state *a6xx_state,
 		struct a6xx_crashdumper *dumper)
 {
 	int i, count = ARRAY_SIZE(a6xx_ahb_reglist) +
 		ARRAY_SIZE(a6xx_reglist) +
-		ARRAY_SIZE(a6xx_hlsq_reglist);
+		ARRAY_SIZE(a6xx_hlsq_reglist) + A6XX_GBIF_REGLIST_SIZE;
 	int index = 0;
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 
 	a6xx_state->registers = state_kcalloc(a6xx_state,
 		count, sizeof(*a6xx_state->registers));
@@ -792,6 +813,15 @@ static void a6xx_get_registers(struct msm_gpu *gpu,
 			a6xx_state, &a6xx_ahb_reglist[i],
 			&a6xx_state->registers[index++]);
 
+	if (a6xx_has_gbif(adreno_gpu))
+		a6xx_get_ahb_gpu_registers(gpu,
+				a6xx_state, &a6xx_gbif_reglist,
+				&a6xx_state->registers[index++]);
+	else
+		a6xx_get_ahb_gpu_registers(gpu,
+				a6xx_state, &a6xx_vbif_reglist,
+				&a6xx_state->registers[index++]);
+
 	for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++)
 		a6xx_get_crashdumper_registers(gpu,
 			a6xx_state, &a6xx_reglist[i],
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index 68cccfa2870a..e67c20c415af 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018 The Linux Foundation. All rights reserved. */
+/* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. */
 
 #ifndef _A6XX_CRASH_DUMP_H_
 #define _A6XX_CRASH_DUMP_H_
@@ -307,11 +307,20 @@ static const u32 a6xx_vbif_registers[] = {
 	0x3410, 0x3410, 0x3800, 0x3801,
 };
 
+static const u32 a6xx_gbif_registers[] = {
+	0x3C00, 0X3C0B, 0X3C40, 0X3C47, 0X3CC0, 0X3CD1, 0xE3A, 0xE3A,
+};
+
 static const struct a6xx_registers a6xx_ahb_reglist[] = {
 	REGS(a6xx_ahb_registers, 0, 0),
-	REGS(a6xx_vbif_registers, 0, 0),
 };
 
+static const struct a6xx_registers a6xx_vbif_reglist =
+			REGS(a6xx_vbif_registers, 0, 0);
+
+static const struct a6xx_registers a6xx_gbif_reglist =
+			REGS(a6xx_gbif_registers, 0, 0);
+
 static const u32 a6xx_gmu_gx_registers[] = {
 	/* GMU GX */
 	0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b,
@@ -422,6 +431,9 @@ static const struct a6xx_debugbus_block {
 	DEBUGBUS(A6XX_DBGBUS_TPL1_3, 0x100),
 };
 
+static const struct a6xx_debugbus_block a6xx_gbif_debugbus_block =
+			DEBUGBUS(A6XX_DBGBUS_VBIF, 0x100);
+
 static const struct a6xx_debugbus_block a6xx_cx_debugbus_blocks[] = {
 	DEBUGBUS(A6XX_DBGBUS_GMU_CX, 0x100),
 	DEBUGBUS(A6XX_DBGBUS_CX, 0x100),
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index fbbdf86504f5..cb3a6e597d76 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -167,6 +167,17 @@ static const struct adreno_info gpulist[] = {
 		.init = a5xx_gpu_init,
 		.zapfw = "a540_zap.mdt",
 	}, {
+		.rev = ADRENO_REV(6, 1, 8, ANY_ID),
+		.revn = 618,
+		.name = "A618",
+		.fw = {
+			[ADRENO_FW_SQE] = "a630_sqe.fw",
+			[ADRENO_FW_GMU] = "a630_gmu.bin",
+		},
+		.gmem = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
+		.init = a6xx_gpu_init,
+	}, {
 		.rev = ADRENO_REV(6, 3, 0, ANY_ID),
 		.revn = 630,
 		.name = "A630",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 0783e4b5486a..7fd29829b2fa 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -26,6 +26,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 {
 	struct device *dev = &gpu->pdev->dev;
 	const struct firmware *fw;
+	const char *signed_fwname = NULL;
 	struct device_node *np, *mem_np;
 	struct resource r;
 	phys_addr_t mem_phys;
@@ -58,8 +59,43 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 
 	mem_phys = r.start;
 
-	/* Request the MDT file for the firmware */
-	fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
+	/*
+	 * Check for a firmware-name property.  This is the new scheme
+	 * to handle firmware that may be signed with device specific
+	 * keys, allowing us to have a different zap fw path for different
+	 * devices.
+	 *
+	 * If the firmware-name property is found, we bypass the
+	 * adreno_request_fw() mechanism, because we don't need to handle
+	 * the /lib/firmware/qcom/... vs /lib/firmware/... case.
+	 *
+	 * If the firmware-name property is not found, for backwards
+	 * compatibility we fall back to the fwname from the gpulist
+	 * table.
+	 */
+	of_property_read_string_index(np, "firmware-name", 0, &signed_fwname);
+	if (signed_fwname) {
+		fwname = signed_fwname;
+		ret = request_firmware_direct(&fw, fwname, gpu->dev->dev);
+		if (ret)
+			fw = ERR_PTR(ret);
+	} else if (fwname) {
+		/* Request the MDT file from the default location: */
+		fw = adreno_request_fw(to_adreno_gpu(gpu), fwname);
+	} else {
+		/*
+		 * For new targets, we require the firmware-name property,
+		 * if a zap-shader is required, rather than falling back
+		 * to a firmware name specified in gpulist.
+		 *
+		 * Because the firmware is signed with a (potentially)
+		 * device specific key, having the name come from gpulist
+		 * was a bad idea, and is only provided for backwards
+		 * compatibility for older targets.
+		 */
+		return -ENODEV;
+	}
+
 	if (IS_ERR(fw)) {
 		DRM_DEV_ERROR(dev, "Unable to load %s\n", fwname);
 		return PTR_ERR(fw);
@@ -95,7 +131,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 	 * not.  But since we've already gotten through adreno_request_fw()
 	 * we know which of the two cases it is:
 	 */
-	if (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY) {
+	if (signed_fwname || (to_adreno_gpu(gpu)->fwloc == FW_LOCATION_LEGACY)) {
 		ret = qcom_mdt_load(dev, fw, fwname, pasid,
 				mem_region, mem_phys, mem_size, NULL);
 	} else {
@@ -146,14 +182,6 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
 		return -EPROBE_DEFER;
 	}
 
-	/* Each GPU has a target specific zap shader firmware name to use */
-	if (!adreno_gpu->info->zapfw) {
-		zap_available = false;
-		DRM_DEV_ERROR(&pdev->dev,
-			"Zap shader firmware file not specified for this target\n");
-		return -ENODEV;
-	}
-
 	return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
 }
 
@@ -826,7 +854,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev)
 
 	node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels");
 	if (!node) {
-		DRM_DEV_ERROR(dev, "Could not find the GPU powerlevels\n");
+		DRM_DEV_DEBUG(dev, "Could not find the GPU powerlevels\n");
 		return -ENXIO;
 	}
 
@@ -887,10 +915,21 @@ static int adreno_get_pwrlevels(struct device *dev,
 	DBG("fast_rate=%u, slow_rate=27000000", gpu->fast_rate);
 
 	/* Check for an interconnect path for the bus */
-	gpu->icc_path = of_icc_get(dev, NULL);
+	gpu->icc_path = of_icc_get(dev, "gfx-mem");
+	if (!gpu->icc_path) {
+		/*
+		 * Keep compatbility with device trees that don't have an
+		 * interconnect-names property.
+		 */
+		gpu->icc_path = of_icc_get(dev, NULL);
+	}
 	if (IS_ERR(gpu->icc_path))
 		gpu->icc_path = NULL;
 
+	gpu->ocmem_icc_path = of_icc_get(dev, "ocmem");
+	if (IS_ERR(gpu->ocmem_icc_path))
+		gpu->ocmem_icc_path = NULL;
+
 	return 0;
 }
 
@@ -977,6 +1016,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 		release_firmware(adreno_gpu->fw[i]);
 
 	icc_put(gpu->icc_path);
+	icc_put(gpu->ocmem_icc_path);
 
 	msm_gpu_cleanup(&adreno_gpu->base);
 }
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index e71a7570ef72..9ff4e550e7bd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -3,7 +3,7 @@
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
- * Copyright (c) 2014,2017 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2014,2017, 2019 The Linux Foundation. All rights reserved.
  */
 
 #ifndef __ADRENO_GPU_H__
@@ -227,6 +227,16 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu)
 	return gpu->revn == 540;
 }
 
+static inline int adreno_is_a618(struct adreno_gpu *gpu)
+{
+       return gpu->revn == 618;
+}
+
+static inline int adreno_is_a630(struct adreno_gpu *gpu)
+{
+       return gpu->revn == 630;
+}
+
 int adreno_get_param(struct msm_gpu *gpu, uint32_t param, uint64_t *value);
 const struct firmware *adreno_request_fw(struct adreno_gpu *adreno_gpu,
 		const char *fwname);
@@ -330,10 +340,7 @@ OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt)
 static inline bool adreno_reg_check(struct adreno_gpu *gpu,
 		enum adreno_regs offset_name)
 {
-	if (offset_name >= REG_ADRENO_REGISTER_MAX ||
-			!gpu->reg_offsets[offset_name]) {
-		BUG();
-	}
+	BUG_ON(offset_name >= REG_ADRENO_REGISTER_MAX || !gpu->reg_offsets[offset_name]);
 
 	/*
 	 * REG_SKIP is a special value that tell us that the register in
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index f197dce54576..bf513411b243 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -197,10 +197,6 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc)
 	DPU_DEBUG("%s\n", dpu_crtc->name);
 
 	for (i = 0; i < cstate->num_mixers; i++) {
-		if (!mixer[i].hw_lm || !mixer[i].lm_ctl) {
-			DPU_ERROR("invalid lm or ctl assigned to mixer\n");
-			return;
-		}
 		mixer[i].mixer_op_mode = 0;
 		mixer[i].flush_mask = 0;
 		if (mixer[i].lm_ctl->ops.clear_all_blendstages)
@@ -1113,14 +1109,9 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
 
 	for (i = 0; i < cstate->num_mixers; ++i) {
 		m = &cstate->mixers[i];
-		if (!m->hw_lm)
-			seq_printf(s, "\tmixer[%d] has no lm\n", i);
-		else if (!m->lm_ctl)
-			seq_printf(s, "\tmixer[%d] has no ctl\n", i);
-		else
-			seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
-				m->hw_lm->idx - LM_0, m->lm_ctl->idx - CTL_0,
-				out_width, mode->vdisplay);
+		seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
+			m->hw_lm->idx - LM_0, m->lm_ctl->idx - CTL_0,
+			out_width, mode->vdisplay);
 	}
 
 	seq_puts(s, "\n");
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index f96e142c4361..f8ac3bf60fd6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -58,7 +58,7 @@
 
 #define IDLE_SHORT_TIMEOUT	1
 
-#define MAX_VDISPLAY_SPLIT 1080
+#define MAX_HDISPLAY_SPLIT 1080
 
 /* timeout in frames waiting for frame done */
 #define DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES 5
@@ -233,7 +233,7 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 	u32 irq_status;
 	int ret;
 
-	if (!phys_enc || !wait_info || intr_idx >= INTR_IDX_MAX) {
+	if (!wait_info || intr_idx >= INTR_IDX_MAX) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -308,7 +308,7 @@ int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
 	struct dpu_encoder_irq *irq;
 	int ret = 0;
 
-	if (!phys_enc || intr_idx >= INTR_IDX_MAX) {
+	if (intr_idx >= INTR_IDX_MAX) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -363,10 +363,6 @@ int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
 	struct dpu_encoder_irq *irq;
 	int ret;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
 	irq = &phys_enc->irq[intr_idx];
 
 	/* silently skip irqs that weren't registered */
@@ -415,7 +411,7 @@ void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.get_hw_resources)
+		if (phys->ops.get_hw_resources)
 			phys->ops.get_hw_resources(phys, hw_res);
 	}
 }
@@ -438,7 +434,7 @@ static void dpu_encoder_destroy(struct drm_encoder *drm_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.destroy) {
+		if (phys->ops.destroy) {
 			phys->ops.destroy(phys);
 			--dpu_enc->num_phys_encs;
 			dpu_enc->phys_encs[i] = NULL;
@@ -464,7 +460,7 @@ void dpu_encoder_helper_split_config(
 	struct dpu_hw_mdp *hw_mdptop;
 	struct msm_display_info *disp_info;
 
-	if (!phys_enc || !phys_enc->hw_mdptop || !phys_enc->parent) {
+	if (!phys_enc->hw_mdptop || !phys_enc->parent) {
 		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
 		return;
 	}
@@ -534,8 +530,23 @@ static struct msm_display_topology dpu_encoder_get_topology(
 		if (dpu_enc->phys_encs[i])
 			intf_count++;
 
-	/* User split topology for width > 1080 */
-	topology.num_lm = (mode->vdisplay > MAX_VDISPLAY_SPLIT) ? 2 : 1;
+	/* Datapath topology selection
+	 *
+	 * Dual display
+	 * 2 LM, 2 INTF ( Split display using 2 interfaces)
+	 *
+	 * Single display
+	 * 1 LM, 1 INTF
+	 * 2 LM, 1 INTF (stream merge to support high resolution interfaces)
+	 *
+	 */
+	if (intf_count == 2)
+		topology.num_lm = 2;
+	else if (!dpu_kms->catalog->caps->has_3d_merge)
+		topology.num_lm = 1;
+	else
+		topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1;
+
 	topology.num_enc = 0;
 	topology.num_intf = intf_count;
 
@@ -583,10 +594,10 @@ static int dpu_encoder_virt_atomic_check(
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.atomic_check)
+		if (phys->ops.atomic_check)
 			ret = phys->ops.atomic_check(phys, crtc_state,
 					conn_state);
-		else if (phys && phys->ops.mode_fixup)
+		else if (phys->ops.mode_fixup)
 			if (!phys->ops.mode_fixup(phys, mode, adj_mode))
 				ret = -EINVAL;
 
@@ -682,7 +693,7 @@ static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.irq_control)
+		if (phys->ops.irq_control)
 			phys->ops.irq_control(phys, enable);
 	}
 
@@ -1032,46 +1043,43 @@ static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys) {
-			if (!dpu_enc->hw_pp[i]) {
-				DPU_ERROR_ENC(dpu_enc, "no pp block assigned"
-					     "at idx: %d\n", i);
-				goto error;
-			}
+		if (!dpu_enc->hw_pp[i]) {
+			DPU_ERROR_ENC(dpu_enc,
+				"no pp block assigned at idx: %d\n", i);
+			goto error;
+		}
 
-			if (!hw_ctl[i]) {
-				DPU_ERROR_ENC(dpu_enc, "no ctl block assigned"
-					     "at idx: %d\n", i);
-				goto error;
-			}
+		if (!hw_ctl[i]) {
+			DPU_ERROR_ENC(dpu_enc,
+				"no ctl block assigned at idx: %d\n", i);
+			goto error;
+		}
 
-			phys->hw_pp = dpu_enc->hw_pp[i];
-			phys->hw_ctl = hw_ctl[i];
+		phys->hw_pp = dpu_enc->hw_pp[i];
+		phys->hw_ctl = hw_ctl[i];
 
-			dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id,
-					    DPU_HW_BLK_INTF);
-			for (j = 0; j < MAX_CHANNELS_PER_ENC; j++) {
-				struct dpu_hw_intf *hw_intf;
+		dpu_rm_init_hw_iter(&hw_iter, drm_enc->base.id,
+				    DPU_HW_BLK_INTF);
+		for (j = 0; j < MAX_CHANNELS_PER_ENC; j++) {
+			struct dpu_hw_intf *hw_intf;
 
-				if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
-					break;
+			if (!dpu_rm_get_hw(&dpu_kms->rm, &hw_iter))
+				break;
 
-				hw_intf = (struct dpu_hw_intf *)hw_iter.hw;
-				if (hw_intf->idx == phys->intf_idx)
-					phys->hw_intf = hw_intf;
-			}
+			hw_intf = (struct dpu_hw_intf *)hw_iter.hw;
+			if (hw_intf->idx == phys->intf_idx)
+				phys->hw_intf = hw_intf;
+		}
 
-			if (!phys->hw_intf) {
-				DPU_ERROR_ENC(dpu_enc,
-					      "no intf block assigned at idx: %d\n",
-					      i);
+		if (!phys->hw_intf) {
+			DPU_ERROR_ENC(dpu_enc,
+				      "no intf block assigned at idx: %d\n", i);
 				goto error;
-			}
-
-			phys->connector = conn->state->connector;
-			if (phys->ops.mode_set)
-				phys->ops.mode_set(phys, mode, adj_mode);
 		}
+
+		phys->connector = conn->state->connector;
+		if (phys->ops.mode_set)
+			phys->ops.mode_set(phys, mode, adj_mode);
 	}
 
 	dpu_enc->mode_set_complete = true;
@@ -1203,7 +1211,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.disable)
+		if (phys->ops.disable)
 			phys->ops.disable(phys);
 	}
 
@@ -1216,8 +1224,7 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP);
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
-		if (dpu_enc->phys_encs[i])
-			dpu_enc->phys_encs[i]->connector = NULL;
+		dpu_enc->phys_encs[i]->connector = NULL;
 	}
 
 	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
@@ -1307,7 +1314,7 @@ void dpu_encoder_toggle_vblank_for_crtc(struct drm_encoder *drm_enc,
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->ops.control_vblank_irq)
+		if (phys->ops.control_vblank_irq)
 			phys->ops.control_vblank_irq(phys, enable);
 	}
 }
@@ -1419,7 +1426,7 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
 	}
 
 	ctl = phys->hw_ctl;
-	if (!ctl || !ctl->ops.trigger_flush) {
+	if (!ctl->ops.trigger_flush) {
 		DPU_ERROR("missing trigger cb\n");
 		return;
 	}
@@ -1463,13 +1470,8 @@ void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
 {
 	struct dpu_hw_ctl *ctl;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
-
 	ctl = phys_enc->hw_ctl;
-	if (ctl && ctl->ops.trigger_start) {
+	if (ctl->ops.trigger_start) {
 		ctl->ops.trigger_start(ctl);
 		trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx);
 	}
@@ -1506,14 +1508,10 @@ static void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
 	struct dpu_hw_ctl *ctl;
 	int rc;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
 	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
 	ctl = phys_enc->hw_ctl;
 
-	if (!ctl || !ctl->ops.reset)
+	if (!ctl->ops.reset)
 		return;
 
 	DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(phys_enc->parent),
@@ -1550,12 +1548,10 @@ static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (!phys || phys->enable_state == DPU_ENC_DISABLED)
+		if (phys->enable_state == DPU_ENC_DISABLED)
 			continue;
 
 		ctl = phys->hw_ctl;
-		if (!ctl)
-			continue;
 
 		/*
 		 * This is cleared in frame_done worker, which isn't invoked
@@ -1603,17 +1599,15 @@ void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
 
-		if (phys && phys->hw_ctl) {
-			ctl = phys->hw_ctl;
-			if (ctl->ops.clear_pending_flush)
-				ctl->ops.clear_pending_flush(ctl);
+		ctl = phys->hw_ctl;
+		if (ctl->ops.clear_pending_flush)
+			ctl->ops.clear_pending_flush(ctl);
 
-			/* update only for command mode primary ctl */
-			if ((phys == dpu_enc->cur_master) &&
-			   (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE)
-			    && ctl->ops.trigger_pending)
-				ctl->ops.trigger_pending(ctl);
-		}
+		/* update only for command mode primary ctl */
+		if ((phys == dpu_enc->cur_master) &&
+		   (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE)
+		    && ctl->ops.trigger_pending)
+			ctl->ops.trigger_pending(ctl);
 	}
 }
 
@@ -1773,12 +1767,10 @@ void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc)
 	DPU_ATRACE_BEGIN("enc_prepare_for_kickoff");
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
-		if (phys) {
-			if (phys->ops.prepare_for_kickoff)
-				phys->ops.prepare_for_kickoff(phys);
-			if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
-				needs_hw_reset = true;
-		}
+		if (phys->ops.prepare_for_kickoff)
+			phys->ops.prepare_for_kickoff(phys);
+		if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
+			needs_hw_reset = true;
 	}
 	DPU_ATRACE_END("enc_prepare_for_kickoff");
 
@@ -1819,7 +1811,7 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
 	/* allow phys encs to handle any post-kickoff business */
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
-		if (phys && phys->ops.handle_post_kickoff)
+		if (phys->ops.handle_post_kickoff)
 			phys->ops.handle_post_kickoff(phys);
 	}
 
@@ -1848,7 +1840,7 @@ void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		phys = dpu_enc->phys_encs[i];
-		if (phys && phys->ops.prepare_commit)
+		if (phys->ops.prepare_commit)
 			phys->ops.prepare_commit(phys);
 	}
 }
@@ -1863,9 +1855,6 @@ static int _dpu_encoder_status_show(struct seq_file *s, void *data)
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (!phys)
-			continue;
-
 		seq_printf(s, "intf:%d    vsync:%8d     underrun:%8d    ",
 				phys->intf_idx - INTF_0,
 				atomic_read(&phys->vsync_cnt),
@@ -1924,8 +1913,7 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 		dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops);
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++)
-		if (dpu_enc->phys_encs[i] &&
-				dpu_enc->phys_encs[i]->ops.late_register)
+		if (dpu_enc->phys_encs[i]->ops.late_register)
 			dpu_enc->phys_encs[i]->ops.late_register(
 					dpu_enc->phys_encs[i],
 					dpu_enc->debugfs_root);
@@ -2094,11 +2082,8 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
-
-		if (phys) {
-			atomic_set(&phys->vsync_cnt, 0);
-			atomic_set(&phys->underrun_cnt, 0);
-		}
+		atomic_set(&phys->vsync_cnt, 0);
+		atomic_set(&phys->underrun_cnt, 0);
 	}
 	mutex_unlock(&dpu_enc->enc_lock);
 
@@ -2240,8 +2225,6 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
 
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
-		if (!phys)
-			continue;
 
 		switch (event) {
 		case MSM_ENC_COMMIT_DONE:
@@ -2257,7 +2240,7 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
 			DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n",
 					event);
 			return -EINVAL;
-		};
+		}
 
 		if (fn_wait) {
 			DPU_ATRACE_BEGIN("wait_for_completion_event");
@@ -2274,7 +2257,6 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
 enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
 {
 	struct dpu_encoder_virt *dpu_enc = NULL;
-	int i;
 
 	if (!encoder) {
 		DPU_ERROR("invalid encoder\n");
@@ -2285,12 +2267,8 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
 	if (dpu_enc->cur_master)
 		return dpu_enc->cur_master->intf_mode;
 
-	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
-		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
-
-		if (phys)
-			return phys->intf_mode;
-	}
+	if (dpu_enc->num_phys_encs)
+		return dpu_enc->phys_encs[0]->intf_mode;
 
 	return INTF_MODE_NONE;
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 047960949fbb..39e1e280ba44 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -45,8 +45,7 @@ static bool dpu_encoder_phys_cmd_mode_fixup(
 		const struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (phys_enc)
-		DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n");
+	DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n");
 	return true;
 }
 
@@ -58,11 +57,8 @@ static void _dpu_encoder_phys_cmd_update_intf_cfg(
 	struct dpu_hw_ctl *ctl;
 	struct dpu_hw_intf_cfg intf_cfg = { 0 };
 
-	if (!phys_enc)
-		return;
-
 	ctl = phys_enc->hw_ctl;
-	if (!ctl || !ctl->ops.setup_intf_cfg)
+	if (!ctl->ops.setup_intf_cfg)
 		return;
 
 	intf_cfg.intf = phys_enc->intf_idx;
@@ -79,7 +75,7 @@ static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
 	int new_cnt;
 	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
 
-	if (!phys_enc || !phys_enc->hw_pp)
+	if (!phys_enc->hw_pp)
 		return;
 
 	DPU_ATRACE_BEGIN("pp_done_irq");
@@ -106,7 +102,7 @@ static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
 	struct dpu_encoder_phys *phys_enc = arg;
 	struct dpu_encoder_phys_cmd *cmd_enc;
 
-	if (!phys_enc || !phys_enc->hw_pp)
+	if (!phys_enc->hw_pp)
 		return;
 
 	DPU_ATRACE_BEGIN("rd_ptr_irq");
@@ -125,9 +121,6 @@ static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
-	if (!phys_enc || !phys_enc->hw_ctl)
-		return;
-
 	DPU_ATRACE_BEGIN("ctl_start_irq");
 
 	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
@@ -141,9 +134,6 @@ static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
-	if (!phys_enc)
-		return;
-
 	if (phys_enc->parent_ops->handle_underrun_virt)
 		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
 			phys_enc);
@@ -179,7 +169,7 @@ static void dpu_encoder_phys_cmd_mode_set(
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !mode || !adj_mode) {
+	if (!mode || !adj_mode) {
 		DPU_ERROR("invalid args\n");
 		return;
 	}
@@ -198,7 +188,7 @@ static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
 	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
 	bool do_log = false;
 
-	if (!phys_enc || !phys_enc->hw_pp || !phys_enc->hw_ctl)
+	if (!phys_enc->hw_pp)
 		return -EINVAL;
 
 	cmd_enc->pp_timeout_report_cnt++;
@@ -247,11 +237,6 @@ static int _dpu_encoder_phys_cmd_wait_for_idle(
 	struct dpu_encoder_wait_info wait_info;
 	int ret;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
-
 	wait_info.wq = &phys_enc->pending_kickoff_wq;
 	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
 	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
@@ -273,7 +258,7 @@ static int dpu_encoder_phys_cmd_control_vblank_irq(
 	int ret = 0;
 	int refcount;
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return -EINVAL;
 	}
@@ -314,9 +299,6 @@ end:
 static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
 		bool enable)
 {
-	if (!phys_enc)
-		return;
-
 	trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent),
 			phys_enc->hw_pp->idx - PINGPONG_0,
 			enable, atomic_read(&phys_enc->vblank_refcount));
@@ -351,7 +333,7 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	u32 vsync_hz;
 	struct dpu_kms *dpu_kms;
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return;
 	}
@@ -428,8 +410,7 @@ static void _dpu_encoder_phys_cmd_pingpong_config(
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp
-			|| !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+	if (!phys_enc->hw_pp || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
 		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0);
 		return;
 	}
@@ -458,7 +439,7 @@ static void dpu_encoder_phys_cmd_enable_helper(
 	struct dpu_hw_ctl *ctl;
 	u32 flush_mask = 0;
 
-	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
 		return;
 	}
@@ -480,7 +461,7 @@ static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid phys encoder\n");
 		return;
 	}
@@ -499,8 +480,7 @@ static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
 static void _dpu_encoder_phys_cmd_connect_te(
 		struct dpu_encoder_phys *phys_enc, bool enable)
 {
-	if (!phys_enc || !phys_enc->hw_pp ||
-			!phys_enc->hw_pp->ops.connect_external_te)
+	if (!phys_enc->hw_pp || !phys_enc->hw_pp->ops.connect_external_te)
 		return;
 
 	trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable);
@@ -518,7 +498,7 @@ static int dpu_encoder_phys_cmd_get_line_count(
 {
 	struct dpu_hw_pingpong *hw_pp;
 
-	if (!phys_enc || !phys_enc->hw_pp)
+	if (!phys_enc->hw_pp)
 		return -EINVAL;
 
 	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
@@ -536,7 +516,7 @@ static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc)
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return;
 	}
@@ -559,10 +539,6 @@ static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc)
 	struct dpu_encoder_phys_cmd *cmd_enc =
 		to_dpu_encoder_phys_cmd(phys_enc);
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
 	kfree(cmd_enc);
 }
 
@@ -580,7 +556,7 @@ static void dpu_encoder_phys_cmd_prepare_for_kickoff(
 			to_dpu_encoder_phys_cmd(phys_enc);
 	int ret;
 
-	if (!phys_enc || !phys_enc->hw_pp) {
+	if (!phys_enc->hw_pp) {
 		DPU_ERROR("invalid encoder\n");
 		return;
 	}
@@ -614,11 +590,6 @@ static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
 	struct dpu_encoder_wait_info wait_info;
 	int ret;
 
-	if (!phys_enc || !phys_enc->hw_ctl) {
-		DPU_ERROR("invalid argument(s)\n");
-		return -EINVAL;
-	}
-
 	wait_info.wq = &phys_enc->pending_kickoff_wq;
 	wait_info.atomic_cnt = &phys_enc->pending_ctlstart_cnt;
 	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
@@ -639,9 +610,6 @@ static int dpu_encoder_phys_cmd_wait_for_tx_complete(
 {
 	int rc;
 
-	if (!phys_enc)
-		return -EINVAL;
-
 	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
 	if (rc) {
 		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
@@ -658,9 +626,6 @@ static int dpu_encoder_phys_cmd_wait_for_commit_done(
 	int rc = 0;
 	struct dpu_encoder_phys_cmd *cmd_enc;
 
-	if (!phys_enc)
-		return -EINVAL;
-
 	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	/* only required for master controller */
@@ -681,9 +646,6 @@ static int dpu_encoder_phys_cmd_wait_for_vblank(
 	struct dpu_encoder_phys_cmd *cmd_enc;
 	struct dpu_encoder_wait_info wait_info;
 
-	if (!phys_enc)
-		return -EINVAL;
-
 	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	/* only required for master controller */
@@ -715,9 +677,6 @@ static void dpu_encoder_phys_cmd_handle_post_kickoff(
 static void dpu_encoder_phys_cmd_trigger_start(
 		struct dpu_encoder_phys *phys_enc)
 {
-	if (!phys_enc)
-		return;
-
 	dpu_encoder_helper_trigger_start(phys_enc);
 }
 
@@ -816,6 +775,4 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
 	DPU_DEBUG_CMDENC(cmd_enc, "created\n");
 
 	return phys_enc;
-
-	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index 3123ef873cdf..c71c18de5966 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -220,8 +220,7 @@ static bool dpu_encoder_phys_vid_mode_fixup(
 		const struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (phys_enc)
-		DPU_DEBUG_VIDENC(phys_enc, "\n");
+	DPU_DEBUG_VIDENC(phys_enc, "\n");
 
 	/*
 	 * Modifying mode has consequences when the mode comes back to us
@@ -239,7 +238,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	unsigned long lock_flags;
 	struct dpu_hw_intf_cfg intf_cfg = { 0 };
 
-	if (!phys_enc || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+	if (!phys_enc->hw_ctl->ops.setup_intf_cfg) {
 		DPU_ERROR("invalid encoder %d\n", phys_enc != 0);
 		return;
 	}
@@ -280,6 +279,14 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	phys_enc->hw_intf->ops.setup_timing_gen(phys_enc->hw_intf,
 			&timing_params, fmt);
 	phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+
+	/* setup which pp blk will connect to this intf */
+	if (phys_enc->hw_intf->ops.bind_pingpong_blk)
+		phys_enc->hw_intf->ops.bind_pingpong_blk(
+				phys_enc->hw_intf,
+				true,
+				phys_enc->hw_pp->idx);
+
 	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
 
 	programmable_fetch_config(phys_enc, &timing_params);
@@ -293,12 +300,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
 	u32 flush_register = 0;
 	int new_cnt = -1, old_cnt = -1;
 
-	if (!phys_enc)
-		return;
-
 	hw_ctl = phys_enc->hw_ctl;
-	if (!hw_ctl)
-		return;
 
 	DPU_ATRACE_BEGIN("vblank_irq");
 
@@ -314,7 +316,7 @@ static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
 	 * so we need to double-check with hw that it accepted the flush bits
 	 */
 	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
-	if (hw_ctl && hw_ctl->ops.get_flush_register)
+	if (hw_ctl->ops.get_flush_register)
 		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
 
 	if (!(flush_register & hw_ctl->ops.get_pending_flush(hw_ctl)))
@@ -335,9 +337,6 @@ static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx)
 {
 	struct dpu_encoder_phys *phys_enc = arg;
 
-	if (!phys_enc)
-		return;
-
 	if (phys_enc->parent_ops->handle_underrun_virt)
 		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
 			phys_enc);
@@ -374,11 +373,6 @@ static void dpu_encoder_phys_vid_mode_set(
 		struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder/kms\n");
-		return;
-	}
-
 	if (adj_mode) {
 		phys_enc->cached_mode = *adj_mode;
 		drm_mode_debug_printmodeline(adj_mode);
@@ -395,11 +389,6 @@ static int dpu_encoder_phys_vid_control_vblank_irq(
 	int ret = 0;
 	int refcount;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
-
 	refcount = atomic_read(&phys_enc->vblank_refcount);
 
 	/* Slave encoders don't report vblank */
@@ -435,6 +424,7 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 {
 	struct dpu_hw_ctl *ctl;
 	u32 flush_mask = 0;
+	u32 intf_flush_mask = 0;
 
 	ctl = phys_enc->hw_ctl;
 
@@ -459,10 +449,18 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 	ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->hw_intf->idx);
 	ctl->ops.update_pending_flush(ctl, flush_mask);
 
+	if (ctl->ops.get_bitmask_active_intf)
+		ctl->ops.get_bitmask_active_intf(ctl, &intf_flush_mask,
+			phys_enc->hw_intf->idx);
+
+	if (ctl->ops.update_pending_intf_flush)
+		ctl->ops.update_pending_intf_flush(ctl, intf_flush_mask);
+
 skip_flush:
 	DPU_DEBUG_VIDENC(phys_enc,
-			 "update pending flush ctl %d flush_mask %x\n",
-			 ctl->idx - CTL_0, flush_mask);
+		"update pending flush ctl %d flush_mask 0%x intf_mask 0x%x\n",
+		ctl->idx - CTL_0, flush_mask, intf_flush_mask);
+
 
 	/* ctl_flush & timing engine enable will be triggered by framework */
 	if (phys_enc->enable_state == DPU_ENC_DISABLED)
@@ -471,11 +469,6 @@ skip_flush:
 
 static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc)
 {
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return;
-	}
-
 	DPU_DEBUG_VIDENC(phys_enc, "\n");
 	kfree(phys_enc);
 }
@@ -493,11 +486,6 @@ static int dpu_encoder_phys_vid_wait_for_vblank(
 	struct dpu_encoder_wait_info wait_info;
 	int ret;
 
-	if (!phys_enc) {
-		pr_err("invalid encoder\n");
-		return -EINVAL;
-	}
-
 	wait_info.wq = &phys_enc->pending_kickoff_wq;
 	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
 	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
@@ -543,13 +531,8 @@ static void dpu_encoder_phys_vid_prepare_for_kickoff(
 	struct dpu_hw_ctl *ctl;
 	int rc;
 
-	if (!phys_enc) {
-		DPU_ERROR("invalid encoder/parameters\n");
-		return;
-	}
-
 	ctl = phys_enc->hw_ctl;
-	if (!ctl || !ctl->ops.wait_reset_status)
+	if (!ctl->ops.wait_reset_status)
 		return;
 
 	/*
@@ -569,12 +552,12 @@ static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
 	unsigned long lock_flags;
 	int ret;
 
-	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev) {
+	if (!phys_enc->parent || !phys_enc->parent->dev) {
 		DPU_ERROR("invalid encoder/device\n");
 		return;
 	}
 
-	if (!phys_enc->hw_intf || !phys_enc->hw_ctl) {
+	if (!phys_enc->hw_intf) {
 		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
 				phys_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
 		return;
@@ -639,9 +622,6 @@ static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
 {
 	int ret;
 
-	if (!phys_enc)
-		return;
-
 	trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent),
 			    phys_enc->hw_intf->idx - INTF_0,
 			    enable,
@@ -662,9 +642,6 @@ static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
 static int dpu_encoder_phys_vid_get_line_count(
 		struct dpu_encoder_phys *phys_enc)
 {
-	if (!phys_enc)
-		return -EINVAL;
-
 	if (!dpu_encoder_phys_vid_is_master(phys_enc))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 24ab6249083a..528632690f1e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -489,12 +489,28 @@ static const struct dpu_format dpu_format_map_ubwc[] = {
 		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
 		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
 
+	/* ARGB8888 and ABGR8888 purposely have the same color
+	 * ordering.  The hardware only supports ABGR8888 UBWC
+	 * natively.
+	 */
+	INTERLEAVED_RGB_FMT_TILED(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
 	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
 		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
 		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
 		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
 		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
 
+	INTERLEAVED_RGB_FMT_TILED(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
 	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
 		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
 		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
@@ -550,7 +566,9 @@ static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt)
 {
 	static const struct dpu_media_color_map dpu_media_ubwc_map[] = {
 		{DRM_FORMAT_ABGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_ARGB8888, COLOR_FMT_RGBA8888_UBWC},
 		{DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_XRGB8888, COLOR_FMT_RGBA8888_UBWC},
 		{DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC},
 		{DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC},
 		{DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC},
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 04c8c44f5b9c..c567917541e8 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -11,11 +11,17 @@
 #include "dpu_hw_catalog_format.h"
 #include "dpu_kms.h"
 
-#define VIG_SDM845_MASK \
-	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_SCALER_QSEED3) | BIT(DPU_SSPP_QOS) |\
+#define VIG_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\
 	BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\
 	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT))
 
+#define VIG_SDM845_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3))
+
+#define VIG_SC7180_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED4))
+
 #define DMA_SDM845_MASK \
 	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\
 	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\
@@ -27,6 +33,9 @@
 #define MIXER_SDM845_MASK \
 	(BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER))
 
+#define MIXER_SC7180_MASK \
+	(BIT(DPU_DIM_LAYER))
+
 #define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER)
 
 #define PINGPONG_SDM845_SPLIT_MASK \
@@ -58,9 +67,20 @@ static const struct dpu_caps sdm845_dpu_caps = {
 	.has_src_split = true,
 	.has_dim_layer = true,
 	.has_idle_pc = true,
+	.has_3d_merge = true,
+};
+
+static const struct dpu_caps sc7180_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0x9,
+	.qseed_type = DPU_SSPP_SCALER_QSEED4,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
 };
 
-static struct dpu_mdp_cfg sdm845_mdp[] = {
+static const struct dpu_mdp_cfg sdm845_mdp[] = {
 	{
 	.name = "top_0", .id = MDP_TOP,
 	.base = 0x0, .len = 0x45C,
@@ -85,10 +105,27 @@ static struct dpu_mdp_cfg sdm845_mdp[] = {
 	},
 };
 
+static const struct dpu_mdp_cfg sc7180_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x494,
+	.features = 0,
+	.highest_bank_bit = 0x3,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+		.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+		.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+		.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+		.reg_off = 0x2BC, .bit_off = 8},
+	},
+};
+
 /*************************************************************
  * CTL sub blocks config
  *************************************************************/
-static struct dpu_ctl_cfg sdm845_ctl[] = {
+static const struct dpu_ctl_cfg sdm845_ctl[] = {
 	{
 	.name = "ctl_0", .id = CTL_0,
 	.base = 0x1000, .len = 0xE4,
@@ -116,6 +153,24 @@ static struct dpu_ctl_cfg sdm845_ctl[] = {
 	},
 };
 
+static const struct dpu_ctl_cfg sc7180_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0xE4,
+	.features = BIT(DPU_CTL_ACTIVE_CFG)
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0xE4,
+	.features = BIT(DPU_CTL_ACTIVE_CFG)
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0xE4,
+	.features = BIT(DPU_CTL_ACTIVE_CFG)
+	},
+};
+
 /*************************************************************
  * SSPP sub blocks config
  *************************************************************/
@@ -128,7 +183,7 @@ static const struct dpu_sspp_blks_common sdm845_sspp_common = {
 	.maxvdeciexp = MAX_VERT_DECIMATION,
 };
 
-#define _VIG_SBLK(num, sdma_pri) \
+#define _VIG_SBLK(num, sdma_pri, qseed_ver) \
 	{ \
 	.common = &sdm845_sspp_common, \
 	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
@@ -137,7 +192,7 @@ static const struct dpu_sspp_blks_common sdm845_sspp_common = {
 	.src_blk = {.name = STRCAT("sspp_src_", num), \
 		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
 	.scaler_blk = {.name = STRCAT("sspp_scaler", num), \
-		.id = DPU_SSPP_SCALER_QSEED3, \
+		.id = qseed_ver, \
 		.base = 0xa00, .len = 0xa0,}, \
 	.csc_blk = {.name = STRCAT("sspp_csc", num), \
 		.id = DPU_SSPP_CSC_10BIT, \
@@ -162,10 +217,14 @@ static const struct dpu_sspp_blks_common sdm845_sspp_common = {
 	.virt_num_formats = ARRAY_SIZE(plane_formats), \
 	}
 
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = _VIG_SBLK("0", 5);
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = _VIG_SBLK("1", 6);
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 = _VIG_SBLK("2", 7);
-static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 = _VIG_SBLK("3", 8);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 =
+				_VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 =
+				_VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 =
+				_VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 =
+				_VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3);
 
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK("8", 1);
 static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2);
@@ -184,7 +243,7 @@ static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4);
 	.clk_ctrl = _clkctrl \
 	}
 
-static struct dpu_sspp_cfg sdm845_sspp[] = {
+static const struct dpu_sspp_cfg sdm845_sspp[] = {
 	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SDM845_MASK,
 		sdm845_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
 	SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SDM845_MASK,
@@ -203,9 +262,26 @@ static struct dpu_sspp_cfg sdm845_sspp[] = {
 		sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
 };
 
+static const struct dpu_sspp_sub_blks sc7180_vig_sblk_0 =
+				_VIG_SBLK("0", 4, DPU_SSPP_SCALER_QSEED4);
+
+static const struct dpu_sspp_cfg sc7180_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SC7180_MASK,
+		sc7180_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+};
+
 /*************************************************************
  * MIXER sub blocks config
  *************************************************************/
+
+/* SDM845 */
+
 static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
 	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
 	.maxblendstages = 11, /* excluding base layer */
@@ -215,23 +291,46 @@ static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
 	},
 };
 
-#define LM_BLK(_name, _id, _base, _pp, _lmpair) \
+#define LM_BLK(_name, _id, _base, _fmask, _sblk, _pp, _lmpair) \
 	{ \
 	.name = _name, .id = _id, \
 	.base = _base, .len = 0x320, \
-	.features = MIXER_SDM845_MASK, \
-	.sblk = &sdm845_lm_sblk, \
+	.features = _fmask, \
+	.sblk = _sblk, \
 	.pingpong = _pp, \
 	.lm_pair_mask = (1 << _lmpair) \
 	}
 
-static struct dpu_lm_cfg sdm845_lm[] = {
-	LM_BLK("lm_0", LM_0, 0x44000, PINGPONG_0, LM_1),
-	LM_BLK("lm_1", LM_1, 0x45000, PINGPONG_1, LM_0),
-	LM_BLK("lm_2", LM_2, 0x46000, PINGPONG_2, LM_5),
-	LM_BLK("lm_3", LM_3, 0x0, PINGPONG_MAX, 0),
-	LM_BLK("lm_4", LM_4, 0x0, PINGPONG_MAX, 0),
-	LM_BLK("lm_5", LM_5, 0x49000, PINGPONG_3, LM_2),
+static const struct dpu_lm_cfg sdm845_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_1, LM_0),
+	LM_BLK("lm_2", LM_2, 0x46000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_2, LM_5),
+	LM_BLK("lm_3", LM_3, 0x0, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_MAX, 0),
+	LM_BLK("lm_4", LM_4, 0x0, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_MAX, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, MIXER_SDM845_MASK,
+		&sdm845_lm_sblk, PINGPONG_3, LM_2),
+};
+
+/* SC7180 */
+
+static const struct dpu_lm_sub_blks sc7180_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 7, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98, 0xb0
+	},
+};
+
+static const struct dpu_lm_cfg sc7180_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, MIXER_SC7180_MASK,
+		&sc7180_lm_sblk, PINGPONG_1, LM_0),
 };
 
 /*************************************************************
@@ -264,13 +363,18 @@ static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = {
 	.sblk = &sdm845_pp_sblk \
 	}
 
-static struct dpu_pingpong_cfg sdm845_pp[] = {
+static const struct dpu_pingpong_cfg sdm845_pp[] = {
 	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000),
 	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800),
 	PP_BLK("pingpong_2", PINGPONG_2, 0x71000),
 	PP_BLK("pingpong_3", PINGPONG_3, 0x71800),
 };
 
+static struct dpu_pingpong_cfg sc7180_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800),
+};
+
 /*************************************************************
  * INTF sub blocks config
  *************************************************************/
@@ -278,26 +382,32 @@ static struct dpu_pingpong_cfg sdm845_pp[] = {
 	{\
 	.name = _name, .id = _id, \
 	.base = _base, .len = 0x280, \
+	.features = BIT(DPU_CTL_ACTIVE_CFG), \
 	.type = _type, \
 	.controller_id = _ctrl_id, \
 	.prog_fetch_lines_worst_case = 24 \
 	}
 
-static struct dpu_intf_cfg sdm845_intf[] = {
+static const struct dpu_intf_cfg sdm845_intf[] = {
 	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0),
 	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0),
 	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1),
 	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1),
 };
 
+static const struct dpu_intf_cfg sc7180_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0),
+};
+
 /*************************************************************
  * VBIF sub blocks config
  *************************************************************/
 /* VBIF QOS remap */
-static u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
-static u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
+static const u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
+static const u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
 
-static struct dpu_vbif_cfg sdm845_vbif[] = {
+static const struct dpu_vbif_cfg sdm845_vbif[] = {
 	{
 	.name = "vbif_0", .id = VBIF_0,
 	.base = 0, .len = 0x1040,
@@ -316,7 +426,7 @@ static struct dpu_vbif_cfg sdm845_vbif[] = {
 	},
 };
 
-static struct dpu_reg_dma_cfg sdm845_regdma = {
+static const struct dpu_reg_dma_cfg sdm845_regdma = {
 	.base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c
 };
 
@@ -325,7 +435,7 @@ static struct dpu_reg_dma_cfg sdm845_regdma = {
  *************************************************************/
 
 /* SSPP QOS LUTs */
-static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
+static const struct dpu_qos_lut_entry sdm845_qos_linear[] = {
 	{.fl = 4, .lut = 0x357},
 	{.fl = 5, .lut = 0x3357},
 	{.fl = 6, .lut = 0x23357},
@@ -340,7 +450,11 @@ static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
 	{.fl = 0, .lut = 0x11222222223357}
 };
 
-static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
+static const struct dpu_qos_lut_entry sc7180_qos_linear[] = {
+	{.fl = 0, .lut = 0x0011222222335777},
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
 	{.fl = 10, .lut = 0x344556677},
 	{.fl = 11, .lut = 0x3344556677},
 	{.fl = 12, .lut = 0x23344556677},
@@ -349,11 +463,19 @@ static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
 	{.fl = 0, .lut = 0x112233344556677},
 };
 
-static struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+static const struct dpu_qos_lut_entry sc7180_qos_macrotile[] = {
+	{.fl = 0, .lut = 0x0011223344556677},
+};
+
+static const struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = {
 	{.fl = 0, .lut = 0x0},
 };
 
-static struct dpu_perf_cfg sdm845_perf_data = {
+static const struct dpu_perf_cfg sdm845_perf_data = {
 	.max_bw_low = 6800000,
 	.max_bw_high = 6800000,
 	.min_core_ib = 2400000,
@@ -392,6 +514,30 @@ static struct dpu_perf_cfg sdm845_perf_data = {
 	},
 };
 
+static const struct dpu_perf_cfg sc7180_perf_data = {
+	.max_bw_low = 3900000,
+	.max_bw_high = 5500000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.danger_lut_tbl = {0xff, 0xffff, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sc7180_qos_linear),
+		.entries = sc7180_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_macrotile),
+		.entries = sc7180_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sc7180_qos_nrt),
+		.entries = sc7180_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+};
+
 /*************************************************************
  * Hardware catalog init
  *************************************************************/
@@ -421,12 +567,43 @@ static void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
 		.reg_dma_count = 1,
 		.dma_cfg = sdm845_regdma,
 		.perf = sdm845_perf_data,
+		.mdss_irqs = 0x3ff,
+	};
+}
+
+/*
+ * sc7180_cfg_init(): populate sc7180 dpu sub-blocks reg offsets
+ * and instance counts.
+ */
+static void sc7180_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
+{
+	*dpu_cfg = (struct dpu_mdss_cfg){
+		.caps = &sc7180_dpu_caps,
+		.mdp_count = ARRAY_SIZE(sc7180_mdp),
+		.mdp = sc7180_mdp,
+		.ctl_count = ARRAY_SIZE(sc7180_ctl),
+		.ctl = sc7180_ctl,
+		.sspp_count = ARRAY_SIZE(sc7180_sspp),
+		.sspp = sc7180_sspp,
+		.mixer_count = ARRAY_SIZE(sc7180_lm),
+		.mixer = sc7180_lm,
+		.pingpong_count = ARRAY_SIZE(sc7180_pp),
+		.pingpong = sc7180_pp,
+		.intf_count = ARRAY_SIZE(sc7180_intf),
+		.intf = sc7180_intf,
+		.vbif_count = ARRAY_SIZE(sdm845_vbif),
+		.vbif = sdm845_vbif,
+		.reg_dma_count = 1,
+		.dma_cfg = sdm845_regdma,
+		.perf = sc7180_perf_data,
+		.mdss_irqs = 0x3f,
 	};
 }
 
-static struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
+static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
 	{ .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init},
 	{ .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init},
+	{ .hw_rev = DPU_HW_VER_620, .cfg_init = sc7180_cfg_init},
 };
 
 void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
index ec76b8687a98..09df7d87dd43 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -38,6 +38,7 @@
 #define DPU_HW_VER_401	DPU_HW_VER(4, 0, 1) /* sdm845 v2.0 */
 #define DPU_HW_VER_410	DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */
 #define DPU_HW_VER_500	DPU_HW_VER(5, 0, 0) /* sdm855 v1.0 */
+#define DPU_HW_VER_620	DPU_HW_VER(6, 2, 0) /* sc7180 v1.0 */
 
 
 #define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170)
@@ -45,6 +46,7 @@
 #define IS_SDM845_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_400)
 #define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410)
 #define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500)
+#define IS_SC7180_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_620)
 
 
 #define DPU_HW_BLK_NAME_LEN	16
@@ -92,6 +94,7 @@ enum {
  * @DPU_SSPP_SRC             Src and fetch part of the pipes,
  * @DPU_SSPP_SCALER_QSEED2,  QSEED2 algorithm support
  * @DPU_SSPP_SCALER_QSEED3,  QSEED3 alogorithm support
+ * @DPU_SSPP_SCALER_QSEED4,  QSEED4 algorithm support
  * @DPU_SSPP_SCALER_RGB,     RGB Scaler, supported by RGB pipes
  * @DPU_SSPP_CSC,            Support of Color space converion
  * @DPU_SSPP_CSC_10BIT,      Support of 10-bit Color space conversion
@@ -110,6 +113,7 @@ enum {
 	DPU_SSPP_SRC = 0x1,
 	DPU_SSPP_SCALER_QSEED2,
 	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_QSEED4,
 	DPU_SSPP_SCALER_RGB,
 	DPU_SSPP_CSC,
 	DPU_SSPP_CSC_10BIT,
@@ -166,6 +170,7 @@ enum {
  */
 enum {
 	DPU_CTL_SPLIT_DISPLAY = 0x1,
+	DPU_CTL_ACTIVE_CFG,
 	DPU_CTL_MAX
 };
 
@@ -269,7 +274,7 @@ struct dpu_qos_lut_entry {
  */
 struct dpu_qos_lut_tbl {
 	u32 nentry;
-	struct dpu_qos_lut_entry *entries;
+	const struct dpu_qos_lut_entry *entries;
 };
 
 /**
@@ -283,6 +288,7 @@ struct dpu_qos_lut_tbl {
  * @has_src_split      source split feature status
  * @has_dim_layer      dim layer feature status
  * @has_idle_pc        indicate if idle power collapse feature is supported
+ * @has_3d_merge       indicate if 3D merge is supported
  */
 struct dpu_caps {
 	u32 max_mixer_width;
@@ -293,6 +299,7 @@ struct dpu_caps {
 	bool has_src_split;
 	bool has_dim_layer;
 	bool has_idle_pc;
+	bool has_3d_merge;
 };
 
 /**
@@ -320,6 +327,7 @@ struct dpu_sspp_blks_common {
  * @maxupscale:  maxupscale ratio supported
  * @smart_dma_priority: hw priority of rect1 of multirect pipe
  * @max_per_pipe_bw: maximum allowable bandwidth of this pipe in kBps
+ * @qseed_ver: qseed version
  * @src_blk:
  * @scaler_blk:
  * @csc_blk:
@@ -340,6 +348,7 @@ struct dpu_sspp_sub_blks {
 	u32 maxupscale;
 	u32 smart_dma_priority;
 	u32 max_per_pipe_bw;
+	u32 qseed_ver;
 	struct dpu_src_blk src_blk;
 	struct dpu_scaler_blk scaler_blk;
 	struct dpu_pp_blk csc_blk;
@@ -511,7 +520,7 @@ struct dpu_vbif_dynamic_ot_cfg {
  */
 struct dpu_vbif_dynamic_ot_tbl {
 	u32 count;
-	struct dpu_vbif_dynamic_ot_cfg *cfg;
+	const struct dpu_vbif_dynamic_ot_cfg *cfg;
 };
 
 /**
@@ -521,7 +530,7 @@ struct dpu_vbif_dynamic_ot_tbl {
  */
 struct dpu_vbif_qos_tbl {
 	u32 npriority_lvl;
-	u32 *priority_lvl;
+	const u32 *priority_lvl;
 };
 
 /**
@@ -646,6 +655,7 @@ struct dpu_perf_cfg {
  * @dma_formats        Supported formats for dma pipe
  * @cursor_formats     Supported formats for cursor pipe
  * @vig_formats        Supported formats for vig pipe
+ * @mdss_irqs:         Bitmap with the irqs supported by the target
  */
 struct dpu_mdss_cfg {
 	u32 hwversion;
@@ -653,25 +663,25 @@ struct dpu_mdss_cfg {
 	const struct dpu_caps *caps;
 
 	u32 mdp_count;
-	struct dpu_mdp_cfg *mdp;
+	const struct dpu_mdp_cfg *mdp;
 
 	u32 ctl_count;
-	struct dpu_ctl_cfg *ctl;
+	const struct dpu_ctl_cfg *ctl;
 
 	u32 sspp_count;
-	struct dpu_sspp_cfg *sspp;
+	const struct dpu_sspp_cfg *sspp;
 
 	u32 mixer_count;
-	struct dpu_lm_cfg *mixer;
+	const struct dpu_lm_cfg *mixer;
 
 	u32 pingpong_count;
-	struct dpu_pingpong_cfg *pingpong;
+	const struct dpu_pingpong_cfg *pingpong;
 
 	u32 intf_count;
-	struct dpu_intf_cfg *intf;
+	const struct dpu_intf_cfg *intf;
 
 	u32 vbif_count;
-	struct dpu_vbif_cfg *vbif;
+	const struct dpu_vbif_cfg *vbif;
 
 	u32 reg_dma_count;
 	struct dpu_reg_dma_cfg dma_cfg;
@@ -681,9 +691,11 @@ struct dpu_mdss_cfg {
 	/* Add additional block data structures here */
 
 	struct dpu_perf_cfg perf;
-	struct dpu_format_extended *dma_formats;
-	struct dpu_format_extended *cursor_formats;
-	struct dpu_format_extended *vig_formats;
+	const struct dpu_format_extended *dma_formats;
+	const struct dpu_format_extended *cursor_formats;
+	const struct dpu_format_extended *vig_formats;
+
+	unsigned long mdss_irqs;
 };
 
 struct dpu_mdss_hw_cfg_handler {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
index bb6112c949ae..3766f0fd0bf0 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
@@ -6,8 +6,12 @@
 
 static const uint32_t qcom_compressed_supported_formats[] = {
 	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_BGR565,
+
+	DRM_FORMAT_NV12,
 };
 
 static const uint32_t plane_formats[] = {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index 179e8d52cadb..831e5f7a9b7f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -22,14 +22,18 @@
 #define   CTL_PREPARE                   0x0d0
 #define   CTL_SW_RESET                  0x030
 #define   CTL_LAYER_EXTN_OFFSET         0x40
+#define   CTL_INTF_ACTIVE               0x0F4
+#define   CTL_INTF_FLUSH                0x110
+#define   CTL_INTF_MASTER               0x134
 
 #define CTL_MIXER_BORDER_OUT            BIT(24)
 #define CTL_FLUSH_MASK_CTL              BIT(17)
 
 #define DPU_REG_RESET_TIMEOUT_US        2000
+#define  INTF_IDX       31
 
-static struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
-		struct dpu_mdss_cfg *m,
+static const struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -100,11 +104,27 @@ static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
 	ctx->pending_flush_mask |= flushbits;
 }
 
+static inline void dpu_hw_ctl_update_pending_intf_flush(struct dpu_hw_ctl *ctx,
+		u32 flushbits)
+{
+	ctx->pending_intf_flush_mask |= flushbits;
+}
+
 static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
 {
 	return ctx->pending_flush_mask;
 }
 
+static inline void dpu_hw_ctl_trigger_flush_v1(struct dpu_hw_ctl *ctx)
+{
+
+	if (ctx->pending_flush_mask & BIT(INTF_IDX))
+		DPU_REG_WRITE(&ctx->hw, CTL_INTF_FLUSH,
+				ctx->pending_intf_flush_mask);
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
 static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
 {
 	trace_dpu_hw_ctl_trigger_pending_flush(ctx->pending_flush_mask,
@@ -222,6 +242,36 @@ static int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
 	return 0;
 }
 
+static int dpu_hw_ctl_get_bitmask_intf_v1(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+	case INTF_1:
+		*flushbits |= BIT(31);
+		break;
+	default:
+		return 0;
+	}
+	return 0;
+}
+
+static int dpu_hw_ctl_active_get_bitmask_intf(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+		*flushbits |= BIT(0);
+		break;
+	case INTF_1:
+		*flushbits |= BIT(1);
+		break;
+	default:
+		return 0;
+	}
+	return 0;
+}
+
 static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us)
 {
 	struct dpu_hw_blk_reg_map *c = &ctx->hw;
@@ -422,6 +472,24 @@ exit:
 	DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3);
 }
 
+
+static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_active = 0;
+	u32 mode_sel = 0;
+
+	if (cfg->intf_mode_sel == DPU_CTL_MODE_SEL_CMD)
+		mode_sel |= BIT(17);
+
+	intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE);
+	intf_active |= BIT(cfg->intf - INTF_0);
+
+	DPU_REG_WRITE(c, CTL_TOP, mode_sel);
+	DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active);
+}
+
 static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
 		struct dpu_hw_intf_cfg *cfg)
 {
@@ -455,31 +523,41 @@ static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
 static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
 		unsigned long cap)
 {
+	if (cap & BIT(DPU_CTL_ACTIVE_CFG)) {
+		ops->trigger_flush = dpu_hw_ctl_trigger_flush_v1;
+		ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg_v1;
+		ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf_v1;
+		ops->get_bitmask_active_intf =
+			dpu_hw_ctl_active_get_bitmask_intf;
+		ops->update_pending_intf_flush =
+			dpu_hw_ctl_update_pending_intf_flush;
+	} else {
+		ops->trigger_flush = dpu_hw_ctl_trigger_flush;
+		ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
+		ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
+	}
 	ops->clear_pending_flush = dpu_hw_ctl_clear_pending_flush;
 	ops->update_pending_flush = dpu_hw_ctl_update_pending_flush;
 	ops->get_pending_flush = dpu_hw_ctl_get_pending_flush;
-	ops->trigger_flush = dpu_hw_ctl_trigger_flush;
 	ops->get_flush_register = dpu_hw_ctl_get_flush_register;
 	ops->trigger_start = dpu_hw_ctl_trigger_start;
 	ops->trigger_pending = dpu_hw_ctl_trigger_pending;
-	ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
 	ops->reset = dpu_hw_ctl_reset_control;
 	ops->wait_reset_status = dpu_hw_ctl_wait_reset_status;
 	ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages;
 	ops->setup_blendstage = dpu_hw_ctl_setup_blendstage;
 	ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp;
 	ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer;
-	ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
 };
 
 static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_ctl *c;
-	struct dpu_ctl_cfg *cfg;
+	const struct dpu_ctl_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
index d3ae939ef9f8..09e1263c72e2 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
@@ -91,6 +91,15 @@ struct dpu_hw_ctl_ops {
 		u32 flushbits);
 
 	/**
+	 * OR in the given flushbits to the cached pending_intf_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @flushbits : module flushmask
+	 */
+	void (*update_pending_intf_flush)(struct dpu_hw_ctl *ctx,
+		u32 flushbits);
+
+	/**
 	 * Write the value of the pending_flush_mask to hardware
 	 * @ctx       : ctl path ctx pointer
 	 */
@@ -130,11 +139,24 @@ struct dpu_hw_ctl_ops {
 	uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx,
 		enum dpu_lm blk);
 
+	/**
+	 * Query the value of the intf flush mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
 	int (*get_bitmask_intf)(struct dpu_hw_ctl *ctx,
 		u32 *flushbits,
 		enum dpu_intf blk);
 
 	/**
+	 * Query the value of the intf active flush mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	int (*get_bitmask_active_intf)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf blk);
+
+	/**
 	 * Set all blend stages to disabled
 	 * @ctx       : ctl path ctx pointer
 	 */
@@ -159,6 +181,7 @@ struct dpu_hw_ctl_ops {
  * @mixer_count: number of mixers
  * @mixer_hw_caps: mixer hardware capabilities
  * @pending_flush_mask: storage for pending ctl_flush managed via ops
+ * @pending_intf_flush_mask: pending INTF flush
  * @ops: operation list
  */
 struct dpu_hw_ctl {
@@ -171,6 +194,7 @@ struct dpu_hw_ctl {
 	int mixer_count;
 	const struct dpu_lm_cfg *mixer_hw_caps;
 	u32 pending_flush_mask;
+	u32 pending_intf_flush_mask;
 
 	/* ops */
 	struct dpu_hw_ctl_ops ops;
@@ -195,7 +219,7 @@ static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw)
  */
 struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_ctl_destroy(): Destroys ctl driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
index 8bfa7d0eede6..d84a84f7fe1a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -800,8 +800,8 @@ static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr,
 		start_idx = reg_idx * 32;
 		end_idx = start_idx + 32;
 
-		if (start_idx >= ARRAY_SIZE(dpu_irq_map) ||
-				end_idx > ARRAY_SIZE(dpu_irq_map))
+		if (!test_bit(reg_idx, &intr->irq_mask) ||
+			start_idx >= ARRAY_SIZE(dpu_irq_map))
 			continue;
 
 		/*
@@ -955,8 +955,11 @@ static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr)
 	if (!intr)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
-		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off, 0xffffffff);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (test_bit(i, &intr->irq_mask))
+			DPU_REG_WRITE(&intr->hw,
+					dpu_intr_set[i].clr_off, 0xffffffff);
+	}
 
 	/* ensure register writes go through */
 	wmb();
@@ -971,8 +974,11 @@ static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr)
 	if (!intr)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
-		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].en_off, 0x00000000);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (test_bit(i, &intr->irq_mask))
+			DPU_REG_WRITE(&intr->hw,
+					dpu_intr_set[i].en_off, 0x00000000);
+	}
 
 	/* ensure register writes go through */
 	wmb();
@@ -991,6 +997,9 @@ static void dpu_hw_intr_get_interrupt_statuses(struct dpu_hw_intr *intr)
 
 	spin_lock_irqsave(&intr->irq_lock, irq_flags);
 	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		if (!test_bit(i, &intr->irq_mask))
+			continue;
+
 		/* Read interrupt status */
 		intr->save_irq_status[i] = DPU_REG_READ(&intr->hw,
 				dpu_intr_set[i].status_off);
@@ -1115,6 +1124,7 @@ struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	intr->irq_mask = m->mdss_irqs;
 	spin_lock_init(&intr->irq_lock);
 
 	return intr;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
index 4edcf402dc46..fc9c98617281 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -187,6 +187,7 @@ struct dpu_hw_intr {
 	u32 *save_irq_status;
 	u32 irq_idx_tbl_size;
 	spinlock_t irq_lock;
+	unsigned long irq_mask;
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
index dcd87cda13fe..efe9a5719c6b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -56,8 +56,10 @@
 #define   INTF_FRAME_COUNT              0x0AC
 #define   INTF_LINE_COUNT               0x0B0
 
-static struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
-		struct dpu_mdss_cfg *m,
+#define   INTF_MUX                      0x25C
+
+static const struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -218,6 +220,30 @@ static void dpu_hw_intf_setup_prg_fetch(
 	DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable);
 }
 
+static void dpu_hw_intf_bind_pingpong_blk(
+		struct dpu_hw_intf *intf,
+		bool enable,
+		const enum dpu_pingpong pp)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 mux_cfg;
+
+	if (!intf)
+		return;
+
+	c = &intf->hw;
+
+	mux_cfg = DPU_REG_READ(c, INTF_MUX);
+	mux_cfg &= ~0xf;
+
+	if (enable)
+		mux_cfg |= (pp - PINGPONG_0) & 0x7;
+	else
+		mux_cfg |= 0xf;
+
+	DPU_REG_WRITE(c, INTF_MUX, mux_cfg);
+}
+
 static void dpu_hw_intf_get_status(
 		struct dpu_hw_intf *intf,
 		struct intf_status *s)
@@ -254,16 +280,18 @@ static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
 	ops->get_status = dpu_hw_intf_get_status;
 	ops->enable_timing = dpu_hw_intf_enable_timing_engine;
 	ops->get_line_count = dpu_hw_intf_get_line_count;
+	if (cap & BIT(DPU_CTL_ACTIVE_CFG))
+		ops->bind_pingpong_blk = dpu_hw_intf_bind_pingpong_blk;
 }
 
 static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_intf *c;
-	struct dpu_intf_cfg *cfg;
+	const struct dpu_intf_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
index b03acc225c9b..85468981632d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -52,6 +52,8 @@ struct intf_status {
  * @ enable_timing: enable/disable timing engine
  * @ get_status: returns if timing engine is enabled or not
  * @ get_line_count: reads current vertical line counter
+ * @bind_pingpong_blk: enable/disable the connection with pingpong which will
+ *                     feed pixels to this interface
  */
 struct dpu_hw_intf_ops {
 	void (*setup_timing_gen)(struct dpu_hw_intf *intf,
@@ -68,6 +70,10 @@ struct dpu_hw_intf_ops {
 			struct intf_status *status);
 
 	u32 (*get_line_count)(struct dpu_hw_intf *intf);
+
+	void (*bind_pingpong_blk)(struct dpu_hw_intf *intf,
+			bool enable,
+			const enum dpu_pingpong pp);
 };
 
 struct dpu_hw_intf {
@@ -92,7 +98,7 @@ struct dpu_hw_intf {
  */
 struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_intf_destroy(): Destroys INTF driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
index 5bc39baa746a..37becd43bd54 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -24,8 +24,8 @@
 #define LM_BLEND0_FG_ALPHA               0x04
 #define LM_BLEND0_BG_ALPHA               0x08
 
-static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
-		struct dpu_mdss_cfg *m,
+static const struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -147,12 +147,13 @@ static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
 	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
 }
 
-static void _setup_mixer_ops(struct dpu_mdss_cfg *m,
+static void _setup_mixer_ops(const struct dpu_mdss_cfg *m,
 		struct dpu_hw_lm_ops *ops,
 		unsigned long features)
 {
 	ops->setup_mixer_out = dpu_hw_lm_setup_out;
-	if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion))
+	if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion)
+	    || IS_SC7180_TARGET(m->hwversion))
 		ops->setup_blend_config = dpu_hw_lm_setup_blend_config_sdm845;
 	else
 		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
@@ -164,10 +165,10 @@ static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_mixer *c;
-	struct dpu_lm_cfg *cfg;
+	const struct dpu_lm_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
index 147ace31cfc2..4a6b2de19ef6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -91,7 +91,7 @@ static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw)
  */
 struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_lm_destroy(): Destroys layer mixer driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
index 5dbaba9fd180..d110a40f0e73 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -28,8 +28,8 @@
 #define PP_FBC_BUDGET_CTL               0x038
 #define PP_FBC_LOSSY_MODE               0x03C
 
-static struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
-		struct dpu_mdss_cfg *m,
+static const struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
+		const struct dpu_mdss_cfg *m,
 		void __iomem *addr,
 		struct dpu_hw_blk_reg_map *b)
 {
@@ -195,10 +195,10 @@ static struct dpu_hw_blk_ops dpu_hw_ops;
 
 struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m)
+		const struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_pingpong *c;
-	struct dpu_pingpong_cfg *cfg;
+	const struct dpu_pingpong_cfg *cfg;
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
index 58bdb9279aa8..3d6f46b1db30 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -106,7 +106,7 @@ struct dpu_hw_pingpong {
  */
 struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
 		void __iomem *addr,
-		struct dpu_mdss_cfg *m);
+		const struct dpu_mdss_cfg *m);
 
 /**
  * dpu_hw_pingpong_destroy - destroys pingpong driver context
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
index 4f8b813aab81..82c5dbfdabc7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -132,6 +132,7 @@
 /* traffic shaper clock in Hz */
 #define TS_CLK			19200000
 
+
 static int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
 		int s_id,
 		u32 *idx)
@@ -657,7 +658,8 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c,
 		test_bit(DPU_SSPP_SMART_DMA_V2, &c->cap->features))
 		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
 
-	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) {
+	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features) ||
+			test_bit(DPU_SSPP_SCALER_QSEED4, &features)) {
 		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
 		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
 	}
@@ -666,7 +668,7 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c,
 		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
 }
 
-static struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
+static const struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
 		void __iomem *addr,
 		struct dpu_mdss_cfg *catalog,
 		struct dpu_hw_blk_reg_map *b)
@@ -696,7 +698,7 @@ struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
 		bool is_virtual_pipe)
 {
 	struct dpu_hw_pipe *hw_pipe;
-	struct dpu_sspp_cfg *cfg;
+	const struct dpu_sspp_cfg *cfg;
 
 	if (!addr || !catalog)
 		return ERR_PTR(-EINVAL);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
index a3680b482b41..85b018a9b03c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -27,7 +27,8 @@ struct dpu_hw_pipe;
  */
 #define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \
 	(1UL << DPU_SSPP_SCALER_QSEED2) | \
-	(1UL << DPU_SSPP_SCALER_QSEED3))
+	 (1UL << DPU_SSPP_SCALER_QSEED3) | \
+	  (1UL << DPU_SSPP_SCALER_QSEED4))
 
 /**
  * Component indices
@@ -373,7 +374,7 @@ struct dpu_hw_pipe {
 	struct dpu_hw_blk base;
 	struct dpu_hw_blk_reg_map hw;
 	struct dpu_mdss_cfg *catalog;
-	struct dpu_mdp_cfg *mdp;
+	const struct dpu_mdp_cfg *mdp;
 
 	/* Pipe */
 	enum dpu_sspp idx;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
index 27fbeb504362..078afc5f5882 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -93,19 +93,12 @@ int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
 			DEV_DBG("%pS->%s: enable '%s'\n",
 				__builtin_return_address(0), __func__,
 				clk_arry[i].clk_name);
-			if (clk_arry[i].clk) {
-				rc = clk_prepare_enable(clk_arry[i].clk);
-				if (rc)
-					DEV_ERR("%pS->%s: %s en fail. rc=%d\n",
-						__builtin_return_address(0),
-						__func__,
-						clk_arry[i].clk_name, rc);
-			} else {
-				DEV_ERR("%pS->%s: '%s' is not available\n",
-					__builtin_return_address(0), __func__,
-					clk_arry[i].clk_name);
-				rc = -EPERM;
-			}
+			rc = clk_prepare_enable(clk_arry[i].clk);
+			if (rc)
+				DEV_ERR("%pS->%s: %s en fail. rc=%d\n",
+					__builtin_return_address(0),
+					__func__,
+					clk_arry[i].clk_name, rc);
 
 			if (rc && i) {
 				msm_dss_enable_clk(&clk_arry[i - 1],
@@ -119,12 +112,7 @@ int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
 				__builtin_return_address(0), __func__,
 				clk_arry[i].clk_name);
 
-			if (clk_arry[i].clk)
-				clk_disable_unprepare(clk_arry[i].clk);
-			else
-				DEV_ERR("%pS->%s: '%s' is not available\n",
-					__builtin_return_address(0), __func__,
-					clk_arry[i].clk_name);
+			clk_disable_unprepare(clk_arry[i].clk);
 		}
 	}
 
@@ -187,6 +175,7 @@ int msm_dss_parse_clock(struct platform_device *pdev,
 			continue;
 		mp->clk_config[i].rate = rate;
 		mp->clk_config[i].type = DSS_CLK_PCLK;
+		mp->clk_config[i].max_rate = rate;
 	}
 
 	mp->num_clk = num_clk;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 6c92f0fbeac9..cb08fafb1dc1 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1059,6 +1059,7 @@ static const struct dev_pm_ops dpu_pm_ops = {
 
 static const struct of_device_id dpu_dt_match[] = {
 	{ .compatible = "qcom,sdm845-dpu", },
+	{ .compatible = "qcom,sc7180-dpu", },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dpu_dt_match);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 58d5acbcfc5c..3b9c33e694bf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -53,8 +53,13 @@ enum {
 	R_MAX
 };
 
+/*
+ * Default Preload Values
+ */
 #define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4
 #define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3
+#define DPU_QSEED4_DEFAULT_PRELOAD_V 0x2
+#define DPU_QSEED4_DEFAULT_PRELOAD_H 0x4
 
 #define DEFAULT_REFRESH_RATE	60
 
@@ -477,8 +482,16 @@ static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
 			scale_cfg->src_width[i] /= chroma_subsmpl_h;
 			scale_cfg->src_height[i] /= chroma_subsmpl_v;
 		}
-		scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
-		scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+
+		if (pdpu->pipe_hw->cap->features &
+			BIT(DPU_SSPP_SCALER_QSEED4)) {
+			scale_cfg->preload_x[i] = DPU_QSEED4_DEFAULT_PRELOAD_H;
+			scale_cfg->preload_y[i] = DPU_QSEED4_DEFAULT_PRELOAD_V;
+		} else {
+			scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
+			scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+		}
+
 		pstate->pixel_ext.num_ext_pxls_top[i] =
 			scale_cfg->src_height[i];
 		pstate->pixel_ext.num_ext_pxls_left[i] =
@@ -738,7 +751,7 @@ done:
 	} else {
 		pstate[R0]->multirect_index = DPU_SSPP_RECT_0;
 		pstate[R1]->multirect_index = DPU_SSPP_RECT_1;
-	};
+	}
 
 	DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n",
 		pstate[R0]->multirect_mode, pstate[R0]->multirect_index);
@@ -858,7 +871,7 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 					  pdpu->pipe_sblk->maxupscale << 16,
 					  true, true);
 	if (ret) {
-		DPU_ERROR_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
+		DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret);
 		return ret;
 	}
 	if (!state->visible)
@@ -884,13 +897,13 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		(!(pdpu->features & DPU_SSPP_SCALER) ||
 		 !(pdpu->features & (BIT(DPU_SSPP_CSC)
 		 | BIT(DPU_SSPP_CSC_10BIT))))) {
-		DPU_ERROR_PLANE(pdpu,
+		DPU_DEBUG_PLANE(pdpu,
 				"plane doesn't have scaler/csc for yuv\n");
 		return -EINVAL;
 
 	/* check src bounds */
 	} else if (!dpu_plane_validate_src(&src, &fb_rect, min_src_size)) {
-		DPU_ERROR_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
 				DRM_RECT_ARG(&src));
 		return -E2BIG;
 
@@ -899,19 +912,19 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		   (src.x1 & 0x1 || src.y1 & 0x1 ||
 		    drm_rect_width(&src) & 0x1 ||
 		    drm_rect_height(&src) & 0x1)) {
-		DPU_ERROR_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
 				DRM_RECT_ARG(&src));
 		return -EINVAL;
 
 	/* min dst support */
 	} else if (drm_rect_width(&dst) < 0x1 || drm_rect_height(&dst) < 0x1) {
-		DPU_ERROR_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
 				DRM_RECT_ARG(&dst));
 		return -EINVAL;
 
 	/* check decimated source width */
 	} else if (drm_rect_width(&src) > max_linewidth) {
-		DPU_ERROR_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
+		DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
 				DRM_RECT_ARG(&src), max_linewidth);
 		return -E2BIG;
 	}
@@ -1337,7 +1350,8 @@ static int _dpu_plane_init_debugfs(struct drm_plane *plane)
 			pdpu->debugfs_root, &pdpu->debugfs_src);
 
 	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
-			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2)) {
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED4)) {
 		dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler,
 				sblk->scaler_blk.base + cfg->base,
 				sblk->scaler_blk.len,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index ddc8412731af..23f5b1433b35 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -141,11 +141,11 @@ int dpu_rm_destroy(struct dpu_rm *rm)
 
 static int _dpu_rm_hw_blk_create(
 		struct dpu_rm *rm,
-		struct dpu_mdss_cfg *cat,
+		const struct dpu_mdss_cfg *cat,
 		void __iomem *mmio,
 		enum dpu_hw_blk_type type,
 		uint32_t id,
-		void *hw_catalog_info)
+		const void *hw_catalog_info)
 {
 	struct dpu_rm_hw_blk *blk;
 	void *hw;
@@ -215,7 +215,7 @@ int dpu_rm_init(struct dpu_rm *rm,
 
 	/* Interrogate HW catalog and create tracking items for hw blocks */
 	for (i = 0; i < cat->mixer_count; i++) {
-		struct dpu_lm_cfg *lm = &cat->mixer[i];
+		const struct dpu_lm_cfg *lm = &cat->mixer[i];
 
 		if (lm->pingpong == PINGPONG_MAX) {
 			DPU_DEBUG("skip mixer %d without pingpong\n", lm->id);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 991f4c8f8a12..93ab36bd8df3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -299,7 +299,7 @@ void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 	entry = debugfs_create_dir("vbif", debugfs_root);
 
 	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
-		struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
+		const struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
 
 		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
 
@@ -318,7 +318,7 @@ void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 			(u32 *)&vbif->default_ot_wr_limit);
 
 		for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) {
-			struct dpu_vbif_dynamic_ot_cfg *cfg =
+			const struct dpu_vbif_dynamic_ot_cfg *cfg =
 					&vbif->dynamic_ot_rd_tbl.cfg[j];
 
 			snprintf(vbif_name, sizeof(vbif_name),
@@ -332,7 +332,7 @@ void dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
 		}
 
 		for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) {
-			struct dpu_vbif_dynamic_ot_cfg *cfg =
+			const struct dpu_vbif_dynamic_ot_cfg *cfg =
 					&vbif->dynamic_ot_wr_tbl.cfg[j];
 
 			snprintf(vbif_name, sizeof(vbif_name),
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
index 772f0753ed38..aaf2f26f8505 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_dsi_encoder.c
@@ -121,7 +121,7 @@ static void mdp4_dsi_encoder_enable(struct drm_encoder *encoder)
 	if (mdp4_dsi_encoder->enabled)
 		return;
 
-	 mdp4_crtc_set_config(encoder->crtc,
+	mdp4_crtc_set_config(encoder->crtc,
 			MDP4_DMA_CONFIG_PACK_ALIGN_MSB |
 			MDP4_DMA_CONFIG_DEFLKR_EN |
 			MDP4_DMA_CONFIG_DITHER_EN |
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index 9262ed2dc8c3..c7df71e2fafc 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -53,7 +53,7 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector)
 	if (panel) {
 		drm_panel_attach(panel, connector);
 
-		ret = panel->funcs->get_modes(panel);
+		ret = drm_panel_get_modes(panel, connector);
 
 		drm_panel_detach(panel);
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index 1f48f64539a2..e3c4c250238b 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -902,7 +902,7 @@ struct mdp5_cfg_handler *mdp5_cfg_init(struct mdp5_kms *mdp5_kms,
 				major, minor);
 		ret = -ENXIO;
 		goto fail;
-	};
+	}
 
 	/* only after mdp5_cfg global pointer's init can we access the hw */
 	for (i = 0; i < num_handlers; i++) {
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index eff1a4c61258..4de771d6f0be 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -178,6 +178,8 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 int msm_dsi_host_init(struct msm_dsi *msm_dsi);
 int msm_dsi_runtime_suspend(struct device *dev);
 int msm_dsi_runtime_resume(struct device *dev);
+int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host);
+int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host);
 int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host);
 int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host);
 void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 86ad3fdf207d..813d69deb5e8 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -153,6 +153,10 @@ static const char * const dsi_sdm845_bus_clk_names[] = {
 	"iface", "bus",
 };
 
+static const char * const dsi_sc7180_bus_clk_names[] = {
+	"iface", "bus",
+};
+
 static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
@@ -167,7 +171,22 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
+static const struct msm_dsi_config sc7180_dsi_cfg = {
+	.io_offset = DSI_6G_REG_SHIFT,
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vdda", 21800, 4 },	/* 1.2 V */
+		},
+	},
+	.bus_clk_names = dsi_sc7180_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_sc7180_bus_clk_names),
+	.io_start = { 0xae94000 },
+	.num_dsi = 1,
+};
+
 static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+	.link_clk_set_rate = dsi_link_clk_set_rate_v2,
 	.link_clk_enable = dsi_link_clk_enable_v2,
 	.link_clk_disable = dsi_link_clk_disable_v2,
 	.clk_init_ver = dsi_clk_init_v2,
@@ -179,6 +198,7 @@ static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 };
 
 static const struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+	.link_clk_set_rate = dsi_link_clk_set_rate_6g,
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = NULL,
@@ -190,6 +210,7 @@ static const struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 };
 
 static const struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+	.link_clk_set_rate = dsi_link_clk_set_rate_6g,
 	.link_clk_enable = dsi_link_clk_enable_6g,
 	.link_clk_disable = dsi_link_clk_disable_6g,
 	.clk_init_ver = dsi_clk_init_6g_v2,
@@ -223,6 +244,9 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
 		&msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
 		&sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_1,
+		&sc7180_dsi_cfg, &msm_dsi_6g_v2_host_ops},
+
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index 50a37ceb6a25..217e24a65178 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -20,6 +20,7 @@
 #define MSM_DSI_6G_VER_MINOR_V1_4_2	0x10040002
 #define MSM_DSI_6G_VER_MINOR_V2_2_0	0x20000000
 #define MSM_DSI_6G_VER_MINOR_V2_2_1	0x20020001
+#define MSM_DSI_6G_VER_MINOR_V2_4_1	0x20040001
 
 #define MSM_DSI_V2_VER_MINOR_8064	0x0
 
@@ -35,6 +36,7 @@ struct msm_dsi_config {
 };
 
 struct msm_dsi_host_cfg_ops {
+	int (*link_clk_set_rate)(struct msm_dsi_host *msm_host);
 	int (*link_clk_enable)(struct msm_dsi_host *msm_host);
 	void (*link_clk_disable)(struct msm_dsi_host *msm_host);
 	int (*clk_init_ver)(struct msm_dsi_host *msm_host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 458cec82ae13..11ae5b8444c3 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -505,7 +505,7 @@ int msm_dsi_runtime_resume(struct device *dev)
 	return dsi_bus_clk_enable(msm_host);
 }
 
-int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -515,13 +515,13 @@ int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 	ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate byte clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	if (msm_host->byte_intf_clk) {
@@ -530,10 +530,18 @@ int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 		if (ret) {
 			pr_err("%s: Failed to set rate byte intf clk, %d\n",
 			       __func__, ret);
-			goto error;
+			return ret;
 		}
 	}
 
+	return 0;
+}
+
+
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+{
+	int ret;
+
 	ret = clk_prepare_enable(msm_host->esc_clk);
 	if (ret) {
 		pr_err("%s: Failed to enable dsi esc clk\n", __func__);
@@ -573,7 +581,7 @@ error:
 	return ret;
 }
 
-int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+int dsi_link_clk_set_rate_v2(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -584,27 +592,34 @@ int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 	ret = clk_set_rate(msm_host->byte_clk, msm_host->byte_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate byte clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->esc_clk, msm_host->esc_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate esc clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->src_clk, msm_host->src_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate src clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
 	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
-		goto error;
+		return ret;
 	}
 
+	return 0;
+}
+
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+{
+	int ret;
+
 	ret = clk_prepare_enable(msm_host->byte_clk);
 	if (ret) {
 		pr_err("%s: Failed to enable dsi byte clk\n", __func__);
@@ -818,7 +833,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	u32 flags = msm_host->mode_flags;
 	enum mipi_dsi_pixel_format mipi_fmt = msm_host->format;
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	u32 data = 0;
+	u32 data = 0, lane_ctrl = 0;
 
 	if (!enable) {
 		dsi_write(msm_host, REG_DSI_CTRL, 0);
@@ -906,9 +921,11 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	dsi_write(msm_host, REG_DSI_LANE_SWAP_CTRL,
 		  DSI_LANE_SWAP_CTRL_DLN_SWAP_SEL(msm_host->dlane_swap));
 
-	if (!(flags & MIPI_DSI_CLOCK_NON_CONTINUOUS))
+	if (!(flags & MIPI_DSI_CLOCK_NON_CONTINUOUS)) {
+		lane_ctrl = dsi_read(msm_host, REG_DSI_LANE_CTRL);
 		dsi_write(msm_host, REG_DSI_LANE_CTRL,
-			DSI_LANE_CTRL_CLKLN_HS_FORCE_REQUEST);
+			lane_ctrl | DSI_LANE_CTRL_CLKLN_HS_FORCE_REQUEST);
+	}
 
 	data |= DSI_CTRL_ENABLE;
 
@@ -1996,6 +2013,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 	 * mdp clock need to be enabled to receive dsi interrupt
 	 */
 	pm_runtime_get_sync(&msm_host->pdev->dev);
+	cfg_hnd->ops->link_clk_set_rate(msm_host);
 	cfg_hnd->ops->link_clk_enable(msm_host);
 
 	/* TODO: vote for bus bandwidth */
@@ -2344,7 +2362,9 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	}
 
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	ret = cfg_hnd->ops->link_clk_enable(msm_host);
+	ret = cfg_hnd->ops->link_clk_set_rate(msm_host);
+	if (!ret)
+		ret = cfg_hnd->ops->link_clk_enable(msm_host);
 	if (ret) {
 		pr_err("%s: failed to enable link clocks. ret=%d\n",
 		       __func__, ret);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 271aa7bbca92..104115d112eb 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -329,7 +329,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 	 * attached to the drm_panel.
 	 */
 	drm_panel_attach(panel, connector);
-	num = drm_panel_get_modes(panel);
+	num = drm_panel_get_modes(panel, connector);
 	if (!num)
 		return 0;
 
@@ -432,20 +432,8 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 		}
 	}
 
-	if (panel) {
-		ret = drm_panel_enable(panel);
-		if (ret) {
-			pr_err("%s: enable panel %d failed, %d\n", __func__, id,
-									ret);
-			goto panel_en_fail;
-		}
-	}
-
 	return;
 
-panel_en_fail:
-	if (is_dual_dsi && msm_dsi1)
-		msm_dsi_host_disable(msm_dsi1->host);
 host1_en_fail:
 	msm_dsi_host_disable(host);
 host_en_fail:
@@ -464,12 +452,51 @@ phy_en_fail:
 
 static void dsi_mgr_bridge_enable(struct drm_bridge *bridge)
 {
-	DBG("");
+	int id = dsi_mgr_bridge_get_id(bridge);
+	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
+	struct drm_panel *panel = msm_dsi->panel;
+	bool is_dual_dsi = IS_DUAL_DSI();
+	int ret;
+
+	DBG("id=%d", id);
+	if (!msm_dsi_device_connected(msm_dsi))
+		return;
+
+	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+		return;
+
+	if (panel) {
+		ret = drm_panel_enable(panel);
+		if (ret) {
+			pr_err("%s: enable panel %d failed, %d\n", __func__, id,
+									ret);
+		}
+	}
 }
 
 static void dsi_mgr_bridge_disable(struct drm_bridge *bridge)
 {
-	DBG("");
+	int id = dsi_mgr_bridge_get_id(bridge);
+	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
+	struct drm_panel *panel = msm_dsi->panel;
+	bool is_dual_dsi = IS_DUAL_DSI();
+	int ret;
+
+	DBG("id=%d", id);
+	if (!msm_dsi_device_connected(msm_dsi))
+		return;
+
+	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
+		return;
+
+	if (panel) {
+		ret = drm_panel_disable(panel);
+		if (ret)
+			pr_err("%s: Panel %d OFF failed, %d\n", __func__, id,
+									ret);
+	}
 }
 
 static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
@@ -495,13 +522,6 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		goto disable_phy;
 
-	if (panel) {
-		ret = drm_panel_disable(panel);
-		if (ret)
-			pr_err("%s: Panel %d OFF failed, %d\n", __func__, id,
-									ret);
-	}
-
 	ret = msm_dsi_host_disable(host);
 	if (ret)
 		pr_err("%s: host %d disable failed, %d\n", __func__, id, ret);
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index 8f6100db90ed..1c894548dd72 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -751,9 +751,9 @@ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm)
 	snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->id);
 
 	hw = clk_hw_register_mux(dev, clk_name,
-				 (const char *[]){
+				 ((const char *[]){
 				 parent, parent2, parent3, parent4
-				 }, 4, 0, pll_10nm->phy_cmn_mmio +
+				 }), 4, 0, pll_10nm->phy_cmn_mmio +
 				 REG_DSI_10nm_PHY_CMN_CLK_CFG1,
 				 0, 2, 0, NULL);
 	if (IS_ERR(hw)) {
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
index 8c99e01ae332..6dffd7f4a99b 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_28nm.c
@@ -554,9 +554,9 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm)
 	snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->id);
 	snprintf(parent2, 32, "dsi%dindirect_path_div2_clk", pll_28nm->id);
 	clks[num++] = clk_register_mux(dev, clk_name,
-			(const char *[]){
+			((const char *[]){
 				parent1, parent2
-			}, 2, CLK_SET_RATE_PARENT, pll_28nm->mmio +
+			}), 2, CLK_SET_RATE_PARENT, pll_28nm->mmio +
 			REG_DSI_28nm_PHY_PLL_VREG_CFG, 1, 1, 0, NULL);
 
 	snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->id);
diff --git a/drivers/gpu/drm/msm/edp/edp_bridge.c b/drivers/gpu/drm/msm/edp/edp_bridge.c
index 2950bba4aca9..b65b5cc2dba2 100644
--- a/drivers/gpu/drm/msm/edp/edp_bridge.c
+++ b/drivers/gpu/drm/msm/edp/edp_bridge.c
@@ -55,8 +55,14 @@ static void edp_bridge_mode_set(struct drm_bridge *bridge,
 	DBG("set mode: " DRM_MODE_FMT, DRM_MODE_ARG(mode));
 
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if ((connector->encoder != NULL) &&
-			(connector->encoder->bridge == bridge)) {
+		struct drm_encoder *encoder = connector->encoder;
+		struct drm_bridge *first_bridge;
+
+		if (!connector->encoder)
+			continue;
+
+		first_bridge = drm_bridge_chain_get_first_bridge(encoder);
+		if (bridge == first_bridge) {
 			msm_edp_ctrl_timing_cfg(edp->ctrl,
 				adjusted_mode, &connector->display_info);
 			break;
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index 839822d894d0..58707a1f3878 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -101,7 +101,7 @@ static int gpio_config(struct hdmi *hdmi, bool on)
 
 				gpiod_set_value_cansleep(gpio.gpiod, value);
 			}
-		};
+		}
 
 		DBG("gpio off");
 	}
@@ -433,8 +433,10 @@ struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi)
 
 	connector = &hdmi_connector->base;
 
-	drm_connector_init(hdmi->dev, connector, &hdmi_connector_funcs,
-			DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(hdmi->dev, connector,
+				    &hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    hdmi->i2c);
 	drm_connector_helper_add(connector, &msm_hdmi_connector_helper_funcs);
 
 	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index ac678ace09a3..c26219c7a49f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1192,7 +1192,8 @@ static int add_display_components(struct device *dev,
 	 * the interfaces to our components list.
 	 */
 	if (of_device_is_compatible(dev->of_node, "qcom,mdss") ||
-	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) {
+	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss") ||
+	    of_device_is_compatible(dev->of_node, "qcom,sc7180-mdss")) {
 		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
 		if (ret) {
 			DRM_DEV_ERROR(dev, "failed to populate children devices\n");
@@ -1317,6 +1318,7 @@ static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
 	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
 	{ .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU },
+	{ .compatible = "qcom,sc7180-mdss", .data = (void *)KMS_DPU },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index cff198b2f470..db48867df47d 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -26,7 +26,7 @@ struct msm_fbdev {
 	struct drm_framebuffer *fb;
 };
 
-static struct fb_ops msm_fb_ops = {
+static const struct fb_ops msm_fb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index be5327af16fa..385d4965a8d0 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -54,7 +54,6 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 
 	INIT_LIST_HEAD(&submit->node);
 	INIT_LIST_HEAD(&submit->bo_list);
-	ww_acquire_init(&submit->ticket, &reservation_ww_class);
 
 	return submit;
 }
@@ -158,7 +157,7 @@ static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
 		msm_gem_unpin_iova(&msm_obj->base, submit->aspace);
 
 	if (submit->bos[i].flags & BO_LOCKED)
-		ww_mutex_unlock(&msm_obj->base.resv->lock);
+		dma_resv_unlock(msm_obj->base.resv);
 
 	if (backoff && !(submit->bos[i].flags & BO_VALID))
 		submit->bos[i].iova = 0;
@@ -181,8 +180,8 @@ retry:
 		contended = i;
 
 		if (!(submit->bos[i].flags & BO_LOCKED)) {
-			ret = ww_mutex_lock_interruptible(&msm_obj->base.resv->lock,
-					&submit->ticket);
+			ret = dma_resv_lock_interruptible(msm_obj->base.resv,
+							  &submit->ticket);
 			if (ret)
 				goto fail;
 			submit->bos[i].flags |= BO_LOCKED;
@@ -203,8 +202,8 @@ fail:
 	if (ret == -EDEADLK) {
 		struct msm_gem_object *msm_obj = submit->bos[contended].obj;
 		/* we lost out in a seqno race, lock and retry.. */
-		ret = ww_mutex_lock_slow_interruptible(&msm_obj->base.resv->lock,
-				&submit->ticket);
+		ret = dma_resv_lock_slow_interruptible(msm_obj->base.resv,
+						       &submit->ticket);
 		if (!ret) {
 			submit->bos[contended].flags |= BO_LOCKED;
 			slow_locked = contended;
@@ -390,8 +389,6 @@ static void submit_cleanup(struct msm_gem_submit *submit)
 		list_del_init(&msm_obj->submit_entry);
 		drm_gem_object_put(&msm_obj->base);
 	}
-
-	ww_acquire_fini(&submit->ticket);
 }
 
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
@@ -408,6 +405,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_ringbuffer *ring;
 	int out_fence_fd = -1;
 	struct pid *pid = get_pid(task_pid(current));
+	bool has_ww_ticket = false;
 	unsigned i;
 	int ret, submitid;
 	if (!gpu)
@@ -489,6 +487,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (ret)
 		goto out;
 
+	/* copy_*_user while holding a ww ticket upsets lockdep */
+	ww_acquire_init(&submit->ticket, &reservation_ww_class);
+	has_ww_ticket = true;
 	ret = submit_lock_objects(submit);
 	if (ret)
 		goto out;
@@ -588,6 +589,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 out:
 	submit_cleanup(submit);
+	if (has_ww_ticket)
+		ww_acquire_fini(&submit->ticket);
 	if (ret)
 		msm_gem_submit_free(submit);
 out_unlock:
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index ab8f0f9c9dc8..be5bc2e8425c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -111,8 +111,15 @@ struct msm_gpu {
 	struct clk *ebi1_clk, *core_clk, *rbbmtimer_clk;
 	uint32_t fast_rate;
 
+	/* The gfx-mem interconnect path that's used by all GPU types. */
 	struct icc_path *icc_path;
 
+	/*
+	 * Second interconnect path for some A3xx and all A4xx GPUs to the
+	 * On Chip MEMory (OCMEM).
+	 */
+	struct icc_path *ocmem_icc_path;
+
 	/* Hang and Inactivity Detection:
 	 */
 #define DRM_MSM_INACTIVE_PERIOD   66 /* in ms (roughly four frames) */
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_out.c b/drivers/gpu/drm/mxsfb/mxsfb_out.c
index 4eb94744c526..9eca1605d11d 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_out.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_out.c
@@ -31,7 +31,7 @@ static int mxsfb_panel_get_modes(struct drm_connector *connector)
 			drm_connector_to_mxsfb_drm_private(connector);
 
 	if (mxsfb->panel)
-		return drm_panel_get_modes(mxsfb->panel);
+		return drm_panel_get_modes(mxsfb->panel, connector);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index 3558df043592..d6e4ae1ef705 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -2,7 +2,8 @@
 config DRM_NOUVEAU
 	tristate "Nouveau (NVIDIA) cards"
 	depends on DRM && PCI && MMU
-        select FW_LOADER
+	select IOMMU_API
+	select FW_LOADER
 	select DRM_KMS_HELPER
 	select DRM_TTM
 	select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT
@@ -16,6 +17,7 @@ config DRM_NOUVEAU
 	select INPUT if ACPI && X86
 	select THERMAL if ACPI && X86
 	select ACPI_VIDEO if ACPI && X86
+	select SND_HDA_COMPONENT if SND_HDA_CORE
 	help
 	  Choose this option for open-source NVIDIA support.
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/arb.c b/drivers/gpu/drm/nouveau/dispnv04/arb.c
index 362495535e69..9d4a2d97507e 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/arb.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/arb.c
@@ -53,8 +53,8 @@ struct nv_sim_state {
 static void
 nv04_calc_arb(struct nv_fifo_info *fifo, struct nv_sim_state *arb)
 {
-	int pagemiss, cas, width, bpp;
-	int nvclks, mclks, pclks, crtpagemiss;
+	int pagemiss, cas, bpp;
+	int nvclks, mclks, crtpagemiss;
 	int found, mclk_extra, mclk_loop, cbs, m1, p1;
 	int mclk_freq, pclk_freq, nvclk_freq;
 	int us_m, us_n, us_p, crtc_drain_rate;
@@ -65,11 +65,9 @@ nv04_calc_arb(struct nv_fifo_info *fifo, struct nv_sim_state *arb)
 	nvclk_freq = arb->nvclk_khz;
 	pagemiss = arb->mem_page_miss;
 	cas = arb->mem_latency;
-	width = arb->memory_width >> 6;
 	bpp = arb->bpp;
 	cbs = 128;
 
-	pclks = 2;
 	nvclks = 10;
 	mclks = 13 + cas;
 	mclk_extra = 3;
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 03466f04c741..3a9489ed6544 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -644,16 +644,13 @@ static int nv17_tv_create_resources(struct drm_encoder *encoder,
 	int i;
 
 	if (nouveau_tv_norm) {
-		for (i = 0; i < num_tv_norms; i++) {
-			if (!strcmp(nv17_tv_norm_names[i], nouveau_tv_norm)) {
-				tv_enc->tv_norm = i;
-				break;
-			}
-		}
-
-		if (i == num_tv_norms)
+		i = match_string(nv17_tv_norm_names, num_tv_norms,
+				 nouveau_tv_norm);
+		if (i < 0)
 			NV_WARN(drm, "Invalid TV norm setting \"%s\"\n",
 				nouveau_tv_norm);
+		else
+			tv_enc->tv_norm = i;
 	}
 
 	drm_mode_create_tv_properties(dev, num_tv_norms, nv17_tv_norm_names);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/base907c.c b/drivers/gpu/drm/nouveau/dispnv50/base907c.c
index 5f2de77e0f32..224a34c340fe 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/base907c.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/base907c.c
@@ -75,12 +75,16 @@ base907c_xlut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	}
 }
 
-static void
-base907c_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+static bool
+base907c_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
-	asyw->xlut.i.mode = 7;
+	if (size != 256 && size != 1024)
+		return false;
+
+	asyw->xlut.i.mode = size == 1024 ? 4 : 7;
 	asyw->xlut.i.enable = 2;
 	asyw->xlut.i.load = head907d_olut_load;
+	return true;
 }
 
 static inline u32
@@ -160,6 +164,7 @@ base907c = {
 	.csc_set = base907c_csc_set,
 	.csc_clr = base907c_csc_clr,
 	.olut_core = true,
+	.ilut_size = 1024,
 	.xlut_set = base907c_xlut_set,
 	.xlut_clr = base907c_xlut_clr,
 	.image_set = base907c_image_set,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 63425e246018..2f123082c85d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -29,6 +29,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/hdmi.h>
+#include <linux/component.h>
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_dp_helper.h>
@@ -476,12 +477,113 @@ nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
 	return 0;
 }
 
+/*
+ * audio component binding for ELD notification
+ */
+static void
+nv50_audio_component_eld_notify(struct drm_audio_component *acomp, int port)
+{
+	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify)
+		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+						 port, -1);
+}
+
+static int
+nv50_audio_component_get_eld(struct device *kdev, int port, int pipe,
+			     bool *enabled, unsigned char *buf, int max_bytes)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(kdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_encoder *encoder;
+	struct nouveau_encoder *nv_encoder;
+	struct nouveau_connector *nv_connector;
+	struct nouveau_crtc *nv_crtc;
+	int ret = 0;
+
+	*enabled = false;
+	drm_for_each_encoder(encoder, drm->dev) {
+		nv_encoder = nouveau_encoder(encoder);
+		nv_connector = nouveau_encoder_connector_get(nv_encoder);
+		nv_crtc = nouveau_crtc(encoder->crtc);
+		if (!nv_connector || !nv_crtc || nv_crtc->index != port)
+			continue;
+		*enabled = drm_detect_monitor_audio(nv_connector->edid);
+		if (*enabled) {
+			ret = drm_eld_size(nv_connector->base.eld);
+			memcpy(buf, nv_connector->base.eld,
+			       min(max_bytes, ret));
+		}
+		break;
+	}
+	return ret;
+}
+
+static const struct drm_audio_component_ops nv50_audio_component_ops = {
+	.get_eld = nv50_audio_component_get_eld,
+};
+
+static int
+nv50_audio_component_bind(struct device *kdev, struct device *hda_kdev,
+			  void *data)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(kdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_audio_component *acomp = data;
+
+	if (WARN_ON(!device_link_add(hda_kdev, kdev, DL_FLAG_STATELESS)))
+		return -ENOMEM;
+
+	drm_modeset_lock_all(drm_dev);
+	acomp->ops = &nv50_audio_component_ops;
+	acomp->dev = kdev;
+	drm->audio.component = acomp;
+	drm_modeset_unlock_all(drm_dev);
+	return 0;
+}
+
+static void
+nv50_audio_component_unbind(struct device *kdev, struct device *hda_kdev,
+			    void *data)
+{
+	struct drm_device *drm_dev = dev_get_drvdata(kdev);
+	struct nouveau_drm *drm = nouveau_drm(drm_dev);
+	struct drm_audio_component *acomp = data;
+
+	drm_modeset_lock_all(drm_dev);
+	drm->audio.component = NULL;
+	acomp->ops = NULL;
+	acomp->dev = NULL;
+	drm_modeset_unlock_all(drm_dev);
+}
+
+static const struct component_ops nv50_audio_component_bind_ops = {
+	.bind   = nv50_audio_component_bind,
+	.unbind = nv50_audio_component_unbind,
+};
+
+static void
+nv50_audio_component_init(struct nouveau_drm *drm)
+{
+	if (!component_add(drm->dev->dev, &nv50_audio_component_bind_ops))
+		drm->audio.component_registered = true;
+}
+
+static void
+nv50_audio_component_fini(struct nouveau_drm *drm)
+{
+	if (drm->audio.component_registered) {
+		component_del(drm->dev->dev, &nv50_audio_component_bind_ops);
+		drm->audio.component_registered = false;
+	}
+}
+
 /******************************************************************************
  * Audio
  *****************************************************************************/
 static void
 nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 {
+	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nv50_disp *disp = nv50_disp(encoder->dev);
 	struct {
@@ -496,11 +598,14 @@ nv50_audio_disable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc)
 	};
 
 	nvif_mthd(&disp->disp->object, 0, &args, sizeof(args));
+
+	nv50_audio_component_eld_notify(drm->audio.component, nv_crtc->index);
 }
 
 static void
 nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 {
+	struct nouveau_drm *drm = nouveau_drm(encoder->dev);
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
 	struct nouveau_connector *nv_connector;
@@ -527,6 +632,8 @@ nv50_audio_enable(struct drm_encoder *encoder, struct drm_display_mode *mode)
 
 	nvif_mthd(&disp->disp->object, 0, &args,
 		  sizeof(args.base) + drm_eld_size(args.data));
+
+	nv50_audio_component_eld_notify(drm->audio.component, nv_crtc->index);
 }
 
 /******************************************************************************
@@ -660,7 +767,6 @@ struct nv50_mstm {
 	struct nouveau_encoder *outp;
 
 	struct drm_dp_mst_topology_mgr mgr;
-	struct nv50_msto *msto[4];
 
 	bool modified;
 	bool disabled;
@@ -726,7 +832,6 @@ nv50_msto_cleanup(struct nv50_msto *msto)
 	drm_dp_mst_deallocate_vcpi(&mstm->mgr, mstc->port);
 
 	msto->mstc = NULL;
-	msto->head = NULL;
 	msto->disabled = false;
 }
 
@@ -806,11 +911,11 @@ nv50_msto_atomic_check(struct drm_encoder *encoder,
 		 * topology
 		 */
 		asyh->or.bpc = min(connector->display_info.bpc, 8U);
-		asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3);
+		asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, asyh->or.bpc * 3, false);
 	}
 
 	slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr, mstc->port,
-					      asyh->dp.pbn);
+					      asyh->dp.pbn, 0);
 	if (slots < 0)
 		return slots;
 
@@ -872,7 +977,6 @@ nv50_msto_enable(struct drm_encoder *encoder)
 	mstm->outp->update(mstm->outp, head->base.index, armh, proto,
 			   nv50_dp_bpc_to_depth(armh->or.bpc));
 
-	msto->head = head;
 	msto->mstc = mstc;
 	mstm->modified = true;
 }
@@ -913,45 +1017,40 @@ nv50_msto = {
 	.destroy = nv50_msto_destroy,
 };
 
-static int
-nv50_msto_new(struct drm_device *dev, u32 heads, const char *name, int id,
-	      struct nv50_msto **pmsto)
+static struct nv50_msto *
+nv50_msto_new(struct drm_device *dev, struct nv50_head *head, int id)
 {
 	struct nv50_msto *msto;
 	int ret;
 
-	if (!(msto = *pmsto = kzalloc(sizeof(*msto), GFP_KERNEL)))
-		return -ENOMEM;
+	msto = kzalloc(sizeof(*msto), GFP_KERNEL);
+	if (!msto)
+		return ERR_PTR(-ENOMEM);
 
 	ret = drm_encoder_init(dev, &msto->encoder, &nv50_msto,
-			       DRM_MODE_ENCODER_DPMST, "%s-mst-%d", name, id);
+			       DRM_MODE_ENCODER_DPMST, "mst-%d", id);
 	if (ret) {
-		kfree(*pmsto);
-		*pmsto = NULL;
-		return ret;
+		kfree(msto);
+		return ERR_PTR(ret);
 	}
 
 	drm_encoder_helper_add(&msto->encoder, &nv50_msto_help);
-	msto->encoder.possible_crtcs = heads;
-	return 0;
+	msto->encoder.possible_crtcs = drm_crtc_mask(&head->base.base);
+	msto->head = head;
+	return msto;
 }
 
 static struct drm_encoder *
 nv50_mstc_atomic_best_encoder(struct drm_connector *connector,
 			      struct drm_connector_state *connector_state)
 {
-	struct nv50_head *head = nv50_head(connector_state->crtc);
 	struct nv50_mstc *mstc = nv50_mstc(connector);
+	struct drm_crtc *crtc = connector_state->crtc;
 
-	return &mstc->mstm->msto[head->base.index]->encoder;
-}
-
-static struct drm_encoder *
-nv50_mstc_best_encoder(struct drm_connector *connector)
-{
-	struct nv50_mstc *mstc = nv50_mstc(connector);
+	if (!(mstc->mstm->outp->dcb->heads & drm_crtc_mask(crtc)))
+		return NULL;
 
-	return &mstc->mstm->msto[0]->encoder;
+	return &nv50_head(crtc)->msto->encoder;
 }
 
 static enum drm_mode_status
@@ -1038,7 +1137,6 @@ static const struct drm_connector_helper_funcs
 nv50_mstc_help = {
 	.get_modes = nv50_mstc_get_modes,
 	.mode_valid = nv50_mstc_mode_valid,
-	.best_encoder = nv50_mstc_best_encoder,
 	.atomic_best_encoder = nv50_mstc_atomic_best_encoder,
 	.atomic_check = nv50_mstc_atomic_check,
 	.detect_ctx = nv50_mstc_detect,
@@ -1071,8 +1169,9 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	      const char *path, struct nv50_mstc **pmstc)
 {
 	struct drm_device *dev = mstm->outp->base.base.dev;
+	struct drm_crtc *crtc;
 	struct nv50_mstc *mstc;
-	int ret, i;
+	int ret;
 
 	if (!(mstc = *pmstc = kzalloc(sizeof(*mstc), GFP_KERNEL)))
 		return -ENOMEM;
@@ -1092,8 +1191,13 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	mstc->connector.funcs->reset(&mstc->connector);
 	nouveau_conn_attach_properties(&mstc->connector);
 
-	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
-		drm_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
+	drm_for_each_crtc(crtc, dev) {
+		if (!(mstm->outp->dcb->heads & drm_crtc_mask(crtc)))
+			continue;
+
+		drm_connector_attach_encoder(&mstc->connector,
+					     &nv50_head(crtc)->msto->encoder);
+	}
 
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
@@ -1367,7 +1471,7 @@ nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
 	const int max_payloads = hweight8(outp->dcb->heads);
 	struct drm_device *dev = outp->base.base.dev;
 	struct nv50_mstm *mstm;
-	int ret, i;
+	int ret;
 	u8 dpcd;
 
 	/* This is a workaround for some monitors not functioning
@@ -1390,13 +1494,6 @@ nv50_mstm_new(struct nouveau_encoder *outp, struct drm_dp_aux *aux, int aux_max,
 	if (ret)
 		return ret;
 
-	for (i = 0; i < max_payloads; i++) {
-		ret = nv50_msto_new(dev, outp->dcb->heads, outp->base.base.name,
-				    i, &mstm->msto[i]);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -1569,17 +1666,24 @@ nv50_sor_func = {
 	.destroy = nv50_sor_destroy,
 };
 
+static bool nv50_has_mst(struct nouveau_drm *drm)
+{
+	struct nvkm_bios *bios = nvxx_bios(&drm->client.device);
+	u32 data;
+	u8 ver, hdr, cnt, len;
+
+	data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len);
+	return data && ver >= 0x40 && (nvbios_rd08(bios, data + 0x08) & 0x04);
+}
+
 static int
 nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 {
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_drm *drm = nouveau_drm(connector->dev);
-	struct nvkm_bios *bios = nvxx_bios(&drm->client.device);
 	struct nvkm_i2c *i2c = nvxx_i2c(&drm->client.device);
 	struct nouveau_encoder *nv_encoder;
 	struct drm_encoder *encoder;
-	u8 ver, hdr, cnt, len;
-	u32 data;
 	int type, ret;
 
 	switch (dcbe->type) {
@@ -1624,10 +1728,9 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 		}
 
 		if (nv_connector->type != DCB_CONNECTOR_eDP &&
-		    (data = nvbios_dp_table(bios, &ver, &hdr, &cnt, &len)) &&
-		    ver >= 0x40 && (nvbios_rd08(bios, data + 0x08) & 0x04)) {
-			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux, 16,
-					    nv_connector->base.base.id,
+		    nv50_has_mst(drm)) {
+			ret = nv50_mstm_new(nv_encoder, &nv_connector->aux,
+					    16, nv_connector->base.base.id,
 					    &nv_encoder->dp.mstm);
 			if (ret)
 				return ret;
@@ -1673,7 +1776,6 @@ nv50_pior_enable(struct drm_encoder *encoder)
 {
 	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
 	struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc);
-	struct nouveau_connector *nv_connector;
 	struct nv50_head_atom *asyh = nv50_head_atom(nv_crtc->base.state);
 	struct nv50_core *core = nv50_disp(encoder->dev)->core;
 	u8 owner = 1 << nv_crtc->index;
@@ -1681,7 +1783,6 @@ nv50_pior_enable(struct drm_encoder *encoder)
 
 	nv50_outp_acquire(nv_encoder);
 
-	nv_connector = nouveau_encoder_connector_get(nv_encoder);
 	switch (asyh->or.bpc) {
 	case 10: asyh->or.depth = 0x6; break;
 	case  8: asyh->or.depth = 0x5; break;
@@ -2302,6 +2403,8 @@ nv50_display_destroy(struct drm_device *dev)
 {
 	struct nv50_disp *disp = nv50_disp(dev);
 
+	nv50_audio_component_fini(nouveau_drm(dev));
+
 	nv50_core_del(&disp->core);
 
 	nouveau_bo_unmap(disp->sync);
@@ -2323,6 +2426,7 @@ nv50_display_create(struct drm_device *dev)
 	struct nv50_disp *disp;
 	struct dcb_output *dcbe;
 	int crtcs, ret, i;
+	bool has_mst = nv50_has_mst(drm);
 
 	disp = kzalloc(sizeof(*disp), GFP_KERNEL);
 	if (!disp)
@@ -2371,11 +2475,37 @@ nv50_display_create(struct drm_device *dev)
 		crtcs = 0x3;
 
 	for (i = 0; i < fls(crtcs); i++) {
+		struct nv50_head *head;
+
 		if (!(crtcs & (1 << i)))
 			continue;
-		ret = nv50_head_create(dev, i);
-		if (ret)
+
+		head = nv50_head_create(dev, i);
+		if (IS_ERR(head)) {
+			ret = PTR_ERR(head);
 			goto out;
+		}
+
+		if (has_mst) {
+			head->msto = nv50_msto_new(dev, head, i);
+			if (IS_ERR(head->msto)) {
+				ret = PTR_ERR(head->msto);
+				head->msto = NULL;
+				goto out;
+			}
+
+			/*
+			 * FIXME: This is a hack to workaround the following
+			 * issues:
+			 *
+			 * https://gitlab.gnome.org/GNOME/mutter/issues/759
+			 * https://gitlab.freedesktop.org/xorg/xserver/merge_requests/277
+			 *
+			 * Once these issues are closed, this should be
+			 * removed
+			 */
+			head->msto->encoder.possible_crtcs = crtcs;
+		}
 	}
 
 	/* create encoder/connector objects based on VBIOS DCB table */
@@ -2423,6 +2553,8 @@ nv50_display_create(struct drm_device *dev)
 	/* Disable vblank irqs aggressively for power-saving, safe on nv50+ */
 	dev->vblank_disable_immediate = true;
 
+	nv50_audio_component_init(drm);
+
 out:
 	if (ret)
 		nv50_display_destroy(dev);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 7c41b0599d1a..d54fe00ac3a3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -4,6 +4,8 @@
 
 #include "nouveau_display.h"
 
+struct nv50_msto;
+
 struct nv50_disp {
 	struct nvif_disp *disp;
 	struct nv50_core *core;
@@ -78,14 +80,14 @@ void evo_kick(u32 *, struct nv50_dmac *);
 
 #define evo_mthd(p, m, s) do {						\
 	const u32 _m = (m), _s = (s);					\
-	if (drm_debug & DRM_UT_KMS)					\
+	if (drm_debug_enabled(DRM_UT_KMS))				\
 		pr_err("%04x %d %s\n", _m, _s, __func__);		\
 	*((p)++) = ((_s << 18) | _m);					\
 } while(0)
 
 #define evo_data(p, d) do {						\
 	const u32 _d = (d);						\
-	if (drm_debug & DRM_UT_KMS)					\
+	if (drm_debug_enabled(DRM_UT_KMS))				\
 		pr_err("\t%08x\n", _d);					\
 	*((p)++) = _d;							\
 } while(0)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index c9692df2b76c..d9d64602947d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -213,6 +213,7 @@ nv50_head_atomic_check_lut(struct nv50_head *head,
 {
 	struct nv50_disp *disp = nv50_disp(head->base.base.dev);
 	struct drm_property_blob *olut = asyh->state.gamma_lut;
+	int size;
 
 	/* Determine whether core output LUT should be enabled. */
 	if (olut) {
@@ -229,14 +230,23 @@ nv50_head_atomic_check_lut(struct nv50_head *head,
 		}
 	}
 
-	if (!olut && !head->func->olut_identity) {
-		asyh->olut.handle = 0;
-		return 0;
+	if (!olut) {
+		if (!head->func->olut_identity) {
+			asyh->olut.handle = 0;
+			return 0;
+		}
+		size = 0;
+	} else {
+		size = drm_color_lut_size(olut);
 	}
 
+	if (!head->func->olut(head, asyh, size)) {
+		DRM_DEBUG_KMS("Invalid olut\n");
+		return -EINVAL;
+	}
 	asyh->olut.handle = disp->core->chan.vram.handle;
 	asyh->olut.buffer = !asyh->olut.buffer;
-	head->func->olut(head, asyh);
+
 	return 0;
 }
 
@@ -473,7 +483,7 @@ nv50_head_func = {
 	.atomic_destroy_state = nv50_head_atomic_destroy_state,
 };
 
-int
+struct nv50_head *
 nv50_head_create(struct drm_device *dev, int index)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
@@ -485,7 +495,7 @@ nv50_head_create(struct drm_device *dev, int index)
 
 	head = kzalloc(sizeof(*head), GFP_KERNEL);
 	if (!head)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	head->func = disp->core->func->head;
 	head->base.index = index;
@@ -503,27 +513,26 @@ nv50_head_create(struct drm_device *dev, int index)
 		ret = nv50_curs_new(drm, head->base.index, &curs);
 	if (ret) {
 		kfree(head);
-		return ret;
+		return ERR_PTR(ret);
 	}
 
 	crtc = &head->base.base;
 	drm_crtc_init_with_planes(dev, crtc, &base->plane, &curs->plane,
 				  &nv50_head_func, "head-%d", head->base.index);
 	drm_crtc_helper_add(crtc, &nv50_head_help);
+	/* Keep the legacy gamma size at 256 to avoid compatibility issues */
 	drm_mode_crtc_set_gamma_size(crtc, 256);
-	if (disp->disp->object.oclass >= GF110_DISP)
-		drm_crtc_enable_color_mgmt(crtc, 256, true, 256);
-	else
-		drm_crtc_enable_color_mgmt(crtc, 0, false, 256);
+	drm_crtc_enable_color_mgmt(crtc, base->func->ilut_size,
+				   disp->disp->object.oclass >= GF110_DISP,
+				   head->func->olut_size);
 
 	if (head->func->olut_set) {
 		ret = nv50_lut_init(disp, &drm->client.mmu, &head->olut);
-		if (ret)
-			goto out;
+		if (ret) {
+			nv50_head_destroy(crtc);
+			return ERR_PTR(ret);
+		}
 	}
 
-out:
-	if (ret)
-		nv50_head_destroy(crtc);
-	return ret;
+	return head;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.h b/drivers/gpu/drm/nouveau/dispnv50/head.h
index d1c002f534d4..c32b27cdaefc 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.h
@@ -11,17 +11,19 @@ struct nv50_head {
 	const struct nv50_head_func *func;
 	struct nouveau_crtc base;
 	struct nv50_lut olut;
+	struct nv50_msto *msto;
 };
 
-int nv50_head_create(struct drm_device *, int index);
+struct nv50_head *nv50_head_create(struct drm_device *, int index);
 void nv50_head_flush_set(struct nv50_head *, struct nv50_head_atom *);
 void nv50_head_flush_clr(struct nv50_head *, struct nv50_head_atom *, bool y);
 
 struct nv50_head_func {
 	void (*view)(struct nv50_head *, struct nv50_head_atom *);
 	void (*mode)(struct nv50_head *, struct nv50_head_atom *);
-	void (*olut)(struct nv50_head *, struct nv50_head_atom *);
+	bool (*olut)(struct nv50_head *, struct nv50_head_atom *, int);
 	bool olut_identity;
+	int  olut_size;
 	void (*olut_set)(struct nv50_head *, struct nv50_head_atom *);
 	void (*olut_clr)(struct nv50_head *);
 	void (*core_calc)(struct nv50_head *, struct nv50_head_atom *);
@@ -43,7 +45,7 @@ struct nv50_head_func {
 extern const struct nv50_head_func head507d;
 void head507d_view(struct nv50_head *, struct nv50_head_atom *);
 void head507d_mode(struct nv50_head *, struct nv50_head_atom *);
-void head507d_olut(struct nv50_head *, struct nv50_head_atom *);
+bool head507d_olut(struct nv50_head *, struct nv50_head_atom *, int);
 void head507d_core_calc(struct nv50_head *, struct nv50_head_atom *);
 void head507d_core_clr(struct nv50_head *);
 int head507d_curs_layout(struct nv50_head *, struct nv50_wndw_atom *,
@@ -60,7 +62,7 @@ extern const struct nv50_head_func head827d;
 extern const struct nv50_head_func head907d;
 void head907d_view(struct nv50_head *, struct nv50_head_atom *);
 void head907d_mode(struct nv50_head *, struct nv50_head_atom *);
-void head907d_olut(struct nv50_head *, struct nv50_head_atom *);
+bool head907d_olut(struct nv50_head *, struct nv50_head_atom *, int);
 void head907d_olut_set(struct nv50_head *, struct nv50_head_atom *);
 void head907d_olut_clr(struct nv50_head *);
 void head907d_core_set(struct nv50_head *, struct nv50_head_atom *);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head507d.c b/drivers/gpu/drm/nouveau/dispnv50/head507d.c
index 7561be5ca707..66ccf36b56a2 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head507d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head507d.c
@@ -271,15 +271,19 @@ head507d_olut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-void
-head507d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+bool
+head507d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
+	if (size != 256)
+		return false;
+
 	if (asyh->base.cpp == 1)
 		asyh->olut.mode = 0;
 	else
 		asyh->olut.mode = 1;
 
 	asyh->olut.load = head507d_olut_load;
+	return true;
 }
 
 void
@@ -328,6 +332,7 @@ head507d = {
 	.view = head507d_view,
 	.mode = head507d_mode,
 	.olut = head507d_olut,
+	.olut_size = 256,
 	.olut_set = head507d_olut_set,
 	.olut_clr = head507d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head827d.c b/drivers/gpu/drm/nouveau/dispnv50/head827d.c
index af5e7bd5978b..11877119eea4 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head827d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head827d.c
@@ -108,6 +108,7 @@ head827d = {
 	.view = head507d_view,
 	.mode = head507d_mode,
 	.olut = head507d_olut,
+	.olut_size = 256,
 	.olut_set = head827d_olut_set,
 	.olut_clr = head827d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head907d.c b/drivers/gpu/drm/nouveau/dispnv50/head907d.c
index c2d09dd97b1f..3002ec23d7a6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head907d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head907d.c
@@ -230,11 +230,15 @@ head907d_olut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-void
-head907d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+bool
+head907d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
-	asyh->olut.mode = 7;
+	if (size != 256 && size != 1024)
+		return false;
+
+	asyh->olut.mode = size == 1024 ? 4 : 7;
 	asyh->olut.load = head907d_olut_load;
+	return true;
 }
 
 void
@@ -285,6 +289,7 @@ head907d = {
 	.view = head907d_view,
 	.mode = head907d_mode,
 	.olut = head907d_olut,
+	.olut_size = 1024,
 	.olut_set = head907d_olut_set,
 	.olut_clr = head907d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head917d.c b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
index 303df8459ca8..76958cedd51f 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head917d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head917d.c
@@ -83,6 +83,7 @@ head917d = {
 	.view = head907d_view,
 	.mode = head907d_mode,
 	.olut = head907d_olut,
+	.olut_size = 1024,
 	.olut_set = head907d_olut_set,
 	.olut_clr = head907d_olut_clr,
 	.core_calc = head507d_core_calc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/headc37d.c b/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
index ef6a99d95a9c..00011ce109a6 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/headc37d.c
@@ -148,14 +148,18 @@ headc37d_olut_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 	}
 }
 
-static void
-headc37d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+static bool
+headc37d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
+	if (size != 256 && size != 1024)
+		return false;
+
 	asyh->olut.mode = 2;
-	asyh->olut.size = 0;
+	asyh->olut.size = size == 1024 ? 2 : 0;
 	asyh->olut.range = 0;
 	asyh->olut.output_mode = 1;
 	asyh->olut.load = head907d_olut_load;
+	return true;
 }
 
 static void
@@ -201,6 +205,7 @@ headc37d = {
 	.view = headc37d_view,
 	.mode = headc37d_mode,
 	.olut = headc37d_olut,
+	.olut_size = 1024,
 	.olut_set = headc37d_olut_set,
 	.olut_clr = headc37d_olut_clr,
 	.curs_layout = head917d_curs_layout,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/headc57d.c b/drivers/gpu/drm/nouveau/dispnv50/headc57d.c
index 32a7f9e85fb0..938d910a1b1e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/headc57d.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/headc57d.c
@@ -151,17 +151,20 @@ headc57d_olut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-void
-headc57d_olut(struct nv50_head *head, struct nv50_head_atom *asyh)
+bool
+headc57d_olut(struct nv50_head *head, struct nv50_head_atom *asyh, int size)
 {
+	if (size != 0 && size != 256 && size != 1024)
+		return false;
+
 	asyh->olut.mode = 2; /* DIRECT10 */
 	asyh->olut.size = 4 /* VSS header. */ + 1024 + 1 /* Entries. */;
 	asyh->olut.output_mode = 1; /* INTERPOLATE_ENABLE. */
-	if (asyh->state.gamma_lut &&
-	    asyh->state.gamma_lut->length / sizeof(struct drm_color_lut) == 256)
+	if (size == 256)
 		asyh->olut.load = headc57d_olut_load_8;
 	else
 		asyh->olut.load = headc57d_olut_load;
+	return true;
 }
 
 static void
@@ -194,6 +197,7 @@ headc57d = {
 	.mode = headc57d_mode,
 	.olut = headc57d_olut,
 	.olut_identity = true,
+	.olut_size = 1024,
 	.olut_set = headc57d_olut_set,
 	.olut_clr = headc57d_olut_clr,
 	.curs_layout = head917d_curs_layout,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/lut.c b/drivers/gpu/drm/nouveau/dispnv50/lut.c
index 994def4fd51a..4e95ca5604ab 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/lut.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/lut.c
@@ -49,7 +49,7 @@ nv50_lut_load(struct nv50_lut *lut, int buffer, struct drm_property_blob *blob,
 			kvfree(in);
 		}
 	} else {
-		load(in, blob->length / sizeof(*in), mem);
+		load(in, drm_color_lut_size(blob), mem);
 	}
 
 	return addr;
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 5193b6257061..890315291b01 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -318,7 +318,7 @@ nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw, bool modeset,
 	return wndw->func->acquire(wndw, asyw, asyh);
 }
 
-static void
+static int
 nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 			   struct nv50_wndw_atom *armw,
 			   struct nv50_wndw_atom *asyw,
@@ -340,7 +340,7 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 		 */
 		if (!(ilut = asyh->state.gamma_lut)) {
 			asyw->visible = false;
-			return;
+			return 0;
 		}
 
 		if (wndw->func->ilut)
@@ -359,7 +359,10 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 	/* Recalculate LUT state. */
 	memset(&asyw->xlut, 0x00, sizeof(asyw->xlut));
 	if ((asyw->ilut = wndw->func->ilut ? ilut : NULL)) {
-		wndw->func->ilut(wndw, asyw);
+		if (!wndw->func->ilut(wndw, asyw, drm_color_lut_size(ilut))) {
+			DRM_DEBUG_KMS("Invalid ilut\n");
+			return -EINVAL;
+		}
 		asyw->xlut.handle = wndw->wndw.vram.handle;
 		asyw->xlut.i.buffer = !asyw->xlut.i.buffer;
 		asyw->set.xlut = true;
@@ -384,6 +387,7 @@ nv50_wndw_atomic_check_lut(struct nv50_wndw *wndw,
 
 	/* Can't do an immediate flip while changing the LUT. */
 	asyh->state.async_flip = false;
+	return 0;
 }
 
 static int
@@ -424,8 +428,11 @@ nv50_wndw_atomic_check(struct drm_plane *plane, struct drm_plane_state *state)
 	    (!armw->visible ||
 	     asyh->state.color_mgmt_changed ||
 	     asyw->state.fb->format->format !=
-	     armw->state.fb->format->format))
-		nv50_wndw_atomic_check_lut(wndw, armw, asyw, asyh);
+	     armw->state.fb->format->format)) {
+		ret = nv50_wndw_atomic_check_lut(wndw, armw, asyw, asyh);
+		if (ret)
+			return ret;
+	}
 
 	/* Calculate new window state. */
 	if (asyw->visible) {
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
index c63bd3bdaf06..caf397475918 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
@@ -64,12 +64,13 @@ struct nv50_wndw_func {
 	void (*ntfy_clr)(struct nv50_wndw *);
 	int (*ntfy_wait_begun)(struct nouveau_bo *, u32 offset,
 			       struct nvif_device *);
-	void (*ilut)(struct nv50_wndw *, struct nv50_wndw_atom *);
+	bool (*ilut)(struct nv50_wndw *, struct nv50_wndw_atom *, int);
 	void (*csc)(struct nv50_wndw *, struct nv50_wndw_atom *,
 		    const struct drm_color_ctm *);
 	void (*csc_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
 	void (*csc_clr)(struct nv50_wndw *);
 	bool ilut_identity;
+	int  ilut_size;
 	bool olut_core;
 	void (*xlut_set)(struct nv50_wndw *, struct nv50_wndw_atom *);
 	void (*xlut_clr)(struct nv50_wndw *);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
index 0f9402162bde..b92dc3461bbd 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc37e.c
@@ -71,14 +71,18 @@ wndwc37e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
 	}
 }
 
-static void
-wndwc37e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+static bool
+wndwc37e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
+	if (size != 256 && size != 1024)
+		return false;
+
 	asyw->xlut.i.mode = 2;
-	asyw->xlut.i.size = 0;
+	asyw->xlut.i.size = size == 1024 ? 2 : 0;
 	asyw->xlut.i.range = 0;
 	asyw->xlut.i.output_mode = 1;
 	asyw->xlut.i.load = head907d_olut_load;
+	return true;
 }
 
 void
@@ -261,6 +265,7 @@ wndwc37e = {
 	.ntfy_reset = corec37d_ntfy_init,
 	.ntfy_wait_begun = base507c_ntfy_wait_begun,
 	.ilut = wndwc37e_ilut,
+	.ilut_size = 1024,
 	.xlut_set = wndwc37e_ilut_set,
 	.xlut_clr = wndwc37e_ilut_clr,
 	.csc = base907c_csc,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
index a311c79e5295..35c9c52fab26 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
@@ -156,19 +156,21 @@ wndwc57e_ilut_load(struct drm_color_lut *in, int size, void __iomem *mem)
 	writew(readw(mem - 4), mem + 4);
 }
 
-static void
-wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+static bool
+wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
 {
-	u16 size = asyw->ilut->length / sizeof(struct drm_color_lut);
+	if (size = size ? size : 1024, size != 256 && size != 1024)
+		return false;
+
 	if (size == 256) {
 		asyw->xlut.i.mode = 1; /* DIRECT8. */
 	} else {
 		asyw->xlut.i.mode = 2; /* DIRECT10. */
-		size = 1024;
 	}
 	asyw->xlut.i.size = 4 /* VSS header. */ + size + 1 /* Entries. */;
 	asyw->xlut.i.output_mode = 0; /* INTERPOLATE_DISABLE. */
 	asyw->xlut.i.load = wndwc57e_ilut_load;
+	return true;
 }
 
 static const struct nv50_wndw_func
@@ -183,6 +185,7 @@ wndwc57e = {
 	.ntfy_wait_begun = base507c_ntfy_wait_begun,
 	.ilut = wndwc57e_ilut,
 	.ilut_identity = true,
+	.ilut_size = 1024,
 	.xlut_set = wndwc57e_ilut_set,
 	.xlut_clr = wndwc57e_ilut_clr,
 	.csc = base907c_csc,
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/acr.h b/drivers/gpu/drm/nouveau/include/nvfw/acr.h
new file mode 100644
index 000000000000..e65d6a8db104
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/acr.h
@@ -0,0 +1,152 @@
+#ifndef __NVFW_ACR_H__
+#define __NVFW_ACR_H__
+
+struct wpr_header {
+#define WPR_HEADER_V0_FALCON_ID_INVALID                              0xffffffff
+	u32 falcon_id;
+	u32 lsb_offset;
+	u32 bootstrap_owner;
+	u32 lazy_bootstrap;
+#define WPR_HEADER_V0_STATUS_NONE                                             0
+#define WPR_HEADER_V0_STATUS_COPY                                             1
+#define WPR_HEADER_V0_STATUS_VALIDATION_CODE_FAILED                           2
+#define WPR_HEADER_V0_STATUS_VALIDATION_DATA_FAILED                           3
+#define WPR_HEADER_V0_STATUS_VALIDATION_DONE                                  4
+#define WPR_HEADER_V0_STATUS_VALIDATION_SKIPPED                               5
+#define WPR_HEADER_V0_STATUS_BOOTSTRAP_READY                                  6
+	u32 status;
+};
+
+void wpr_header_dump(struct nvkm_subdev *, const struct wpr_header *);
+
+struct wpr_header_v1 {
+#define WPR_HEADER_V1_FALCON_ID_INVALID                              0xffffffff
+	u32 falcon_id;
+	u32 lsb_offset;
+	u32 bootstrap_owner;
+	u32 lazy_bootstrap;
+	u32 bin_version;
+#define WPR_HEADER_V1_STATUS_NONE                                             0
+#define WPR_HEADER_V1_STATUS_COPY                                             1
+#define WPR_HEADER_V1_STATUS_VALIDATION_CODE_FAILED                           2
+#define WPR_HEADER_V1_STATUS_VALIDATION_DATA_FAILED                           3
+#define WPR_HEADER_V1_STATUS_VALIDATION_DONE                                  4
+#define WPR_HEADER_V1_STATUS_VALIDATION_SKIPPED                               5
+#define WPR_HEADER_V1_STATUS_BOOTSTRAP_READY                                  6
+#define WPR_HEADER_V1_STATUS_REVOCATION_CHECK_FAILED                          7
+	u32 status;
+};
+
+void wpr_header_v1_dump(struct nvkm_subdev *, const struct wpr_header_v1 *);
+
+struct lsf_signature {
+	u8 prd_keys[2][16];
+	u8 dbg_keys[2][16];
+	u32 b_prd_present;
+	u32 b_dbg_present;
+	u32 falcon_id;
+};
+
+struct lsf_signature_v1 {
+	u8 prd_keys[2][16];
+	u8 dbg_keys[2][16];
+	u32 b_prd_present;
+	u32 b_dbg_present;
+	u32 falcon_id;
+	u32 supports_versioning;
+	u32 version;
+	u32 depmap_count;
+	u8 depmap[11/*LSF_LSB_DEPMAP_SIZE*/ * 2 * 4];
+	u8 kdf[16];
+};
+
+struct lsb_header_tail {
+	u32 ucode_off;
+	u32 ucode_size;
+	u32 data_size;
+	u32 bl_code_size;
+	u32 bl_imem_off;
+	u32 bl_data_off;
+	u32 bl_data_size;
+	u32 app_code_off;
+	u32 app_code_size;
+	u32 app_data_off;
+	u32 app_data_size;
+	u32 flags;
+};
+
+struct lsb_header {
+	struct lsf_signature signature;
+	struct lsb_header_tail tail;
+};
+
+void lsb_header_dump(struct nvkm_subdev *, struct lsb_header *);
+
+struct lsb_header_v1 {
+	struct lsf_signature_v1 signature;
+	struct lsb_header_tail tail;
+};
+
+void lsb_header_v1_dump(struct nvkm_subdev *, struct lsb_header_v1 *);
+
+struct flcn_acr_desc {
+	union {
+		u8 reserved_dmem[0x200];
+		u32 signatures[4];
+	} ucode_reserved_space;
+	u32 wpr_region_id;
+	u32 wpr_offset;
+	u32 mmu_mem_range;
+	struct {
+		u32 no_regions;
+		struct {
+			u32 start_addr;
+			u32 end_addr;
+			u32 region_id;
+			u32 read_mask;
+			u32 write_mask;
+			u32 client_mask;
+		} region_props[2];
+	} regions;
+	u32 ucode_blob_size;
+	u64 ucode_blob_base __aligned(8);
+	struct {
+		u32 vpr_enabled;
+		u32 vpr_start;
+		u32 vpr_end;
+		u32 hdcp_policies;
+	} vpr_desc;
+};
+
+void flcn_acr_desc_dump(struct nvkm_subdev *, struct flcn_acr_desc *);
+
+struct flcn_acr_desc_v1 {
+	u8 reserved_dmem[0x200];
+	u32 signatures[4];
+	u32 wpr_region_id;
+	u32 wpr_offset;
+	u32 mmu_memory_range;
+	struct {
+		u32 no_regions;
+		struct {
+			u32 start_addr;
+			u32 end_addr;
+			u32 region_id;
+			u32 read_mask;
+			u32 write_mask;
+			u32 client_mask;
+			u32 shadow_mem_start_addr;
+		} region_props[2];
+	} regions;
+	u32 ucode_blob_size;
+	u64 ucode_blob_base __aligned(8);
+	struct {
+		u32 vpr_enabled;
+		u32 vpr_start;
+		u32 vpr_end;
+		u32 hdcp_policies;
+	} vpr_desc;
+};
+
+void flcn_acr_desc_v1_dump(struct nvkm_subdev *, struct flcn_acr_desc_v1 *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/flcn.h b/drivers/gpu/drm/nouveau/include/nvfw/flcn.h
new file mode 100644
index 000000000000..e090f347d220
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/flcn.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_FLCN_H__
+#define __NVFW_FLCN_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct loader_config {
+	u32 dma_idx;
+	u32 code_dma_base;
+	u32 code_size_total;
+	u32 code_size_to_load;
+	u32 code_entry_point;
+	u32 data_dma_base;
+	u32 data_size;
+	u32 overlay_dma_base;
+	u32 argc;
+	u32 argv;
+	u32 code_dma_base1;
+	u32 data_dma_base1;
+	u32 overlay_dma_base1;
+};
+
+void
+loader_config_dump(struct nvkm_subdev *, const struct loader_config *);
+
+struct loader_config_v1 {
+	u32 reserved;
+	u32 dma_idx;
+	u64 code_dma_base;
+	u32 code_size_total;
+	u32 code_size_to_load;
+	u32 code_entry_point;
+	u64 data_dma_base;
+	u32 data_size;
+	u64 overlay_dma_base;
+	u32 argc;
+	u32 argv;
+} __packed;
+
+void
+loader_config_v1_dump(struct nvkm_subdev *, const struct loader_config_v1 *);
+
+struct flcn_bl_dmem_desc {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	u32 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	u32 data_dma_base;
+	u32 data_size;
+	u32 code_dma_base1;
+	u32 data_dma_base1;
+};
+
+void
+flcn_bl_dmem_desc_dump(struct nvkm_subdev *, const struct flcn_bl_dmem_desc *);
+
+struct flcn_bl_dmem_desc_v1 {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	u64 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	u64 data_dma_base;
+	u32 data_size;
+} __packed;
+
+void flcn_bl_dmem_desc_v1_dump(struct nvkm_subdev *,
+			       const struct flcn_bl_dmem_desc_v1 *);
+
+struct flcn_bl_dmem_desc_v2 {
+	u32 reserved[4];
+	u32 signature[4];
+	u32 ctx_dma;
+	u64 code_dma_base;
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 sec_code_off;
+	u32 sec_code_size;
+	u32 code_entry_point;
+	u64 data_dma_base;
+	u32 data_size;
+	u32 argc;
+	u32 argv;
+} __packed;
+
+void flcn_bl_dmem_desc_v2_dump(struct nvkm_subdev *,
+			       const struct flcn_bl_dmem_desc_v2 *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/fw.h b/drivers/gpu/drm/nouveau/include/nvfw/fw.h
new file mode 100644
index 000000000000..a7cf1188c9d6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/fw.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_FW_H__
+#define __NVFW_FW_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct nvfw_bin_hdr {
+	u32 bin_magic;
+	u32 bin_ver;
+	u32 bin_size;
+	u32 header_offset;
+	u32 data_offset;
+	u32 data_size;
+};
+
+const struct nvfw_bin_hdr *nvfw_bin_hdr(struct nvkm_subdev *, const void *);
+
+struct nvfw_bl_desc {
+	u32 start_tag;
+	u32 dmem_load_off;
+	u32 code_off;
+	u32 code_size;
+	u32 data_off;
+	u32 data_size;
+};
+
+const struct nvfw_bl_desc *nvfw_bl_desc(struct nvkm_subdev *, const void *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/hs.h b/drivers/gpu/drm/nouveau/include/nvfw/hs.h
new file mode 100644
index 000000000000..64d0d32200c2
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/hs.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_HS_H__
+#define __NVFW_HS_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct nvfw_hs_header {
+	u32 sig_dbg_offset;
+	u32 sig_dbg_size;
+	u32 sig_prod_offset;
+	u32 sig_prod_size;
+	u32 patch_loc;
+	u32 patch_sig;
+	u32 hdr_offset;
+	u32 hdr_size;
+};
+
+const struct nvfw_hs_header *nvfw_hs_header(struct nvkm_subdev *, const void *);
+
+struct nvfw_hs_load_header {
+	u32 non_sec_code_off;
+	u32 non_sec_code_size;
+	u32 data_dma_base;
+	u32 data_size;
+	u32 num_apps;
+	u32 apps[0];
+};
+
+const struct nvfw_hs_load_header *
+nvfw_hs_load_header(struct nvkm_subdev *, const void *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/ls.h b/drivers/gpu/drm/nouveau/include/nvfw/ls.h
new file mode 100644
index 000000000000..f63692a2a16c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/ls.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVFW_LS_H__
+#define __NVFW_LS_H__
+#include <core/os.h>
+struct nvkm_subdev;
+
+struct nvfw_ls_desc_head {
+	u32 descriptor_size;
+	u32 image_size;
+	u32 tools_version;
+	u32 app_version;
+	char date[64];
+	u32 bootloader_start_offset;
+	u32 bootloader_size;
+	u32 bootloader_imem_offset;
+	u32 bootloader_entry_point;
+	u32 app_start_offset;
+	u32 app_size;
+	u32 app_imem_offset;
+	u32 app_imem_entry;
+	u32 app_dmem_offset;
+	u32 app_resident_code_offset;
+	u32 app_resident_code_size;
+	u32 app_resident_data_offset;
+	u32 app_resident_data_size;
+};
+
+struct nvfw_ls_desc {
+	struct nvfw_ls_desc_head head;
+	u32 nb_overlays;
+	struct {
+		u32 start;
+		u32 size;
+	} load_ovl[64];
+	u32 compressed;
+};
+
+const struct nvfw_ls_desc *nvfw_ls_desc(struct nvkm_subdev *, const void *);
+
+struct nvfw_ls_desc_v1 {
+	struct nvfw_ls_desc_head head;
+	u32 nb_imem_overlays;
+	u32 nb_dmem_overlays;
+	struct {
+		u32 start;
+		u32 size;
+	} load_ovl[64];
+	u32 compressed;
+};
+
+const struct nvfw_ls_desc_v1 *
+nvfw_ls_desc_v1(struct nvkm_subdev *, const void *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/pmu.h b/drivers/gpu/drm/nouveau/include/nvfw/pmu.h
new file mode 100644
index 000000000000..452ed7d03827
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/pmu.h
@@ -0,0 +1,98 @@
+#ifndef __NVFW_PMU_H__
+#define __NVFW_PMU_H__
+
+struct nv_pmu_args {
+	u32 reserved;
+	u32 freq_hz;
+	u32 trace_size;
+	u32 trace_dma_base;
+	u16 trace_dma_base1;
+	u8 trace_dma_offset;
+	u32 trace_dma_idx;
+	bool secure_mode;
+	bool raise_priv_sec;
+	struct {
+		u32 dma_base;
+		u16 dma_base1;
+		u8 dma_offset;
+		u16 fb_size;
+		u8 dma_idx;
+	} gc6_ctx;
+	u8 pad;
+};
+
+#define NV_PMU_UNIT_INIT                                                   0x07
+#define NV_PMU_UNIT_ACR                                                    0x0a
+
+struct nv_pmu_init_msg {
+	struct nv_falcon_msg hdr;
+#define NV_PMU_INIT_MSG_INIT                                               0x00
+	u8 msg_type;
+
+	u8 pad;
+	u16 os_debug_entry_point;
+
+	struct {
+		u16 size;
+		u16 offset;
+		u8 index;
+		u8 pad;
+	} queue_info[5];
+
+	u16 sw_managed_area_offset;
+	u16 sw_managed_area_size;
+};
+
+struct nv_pmu_acr_cmd {
+	struct nv_falcon_cmd hdr;
+#define NV_PMU_ACR_CMD_INIT_WPR_REGION                                     0x00
+#define NV_PMU_ACR_CMD_BOOTSTRAP_FALCON                                    0x01
+#define NV_PMU_ACR_CMD_BOOTSTRAP_MULTIPLE_FALCONS                          0x03
+	u8 cmd_type;
+};
+
+struct nv_pmu_acr_msg {
+	struct nv_falcon_cmd hdr;
+	u8 msg_type;
+};
+
+struct nv_pmu_acr_init_wpr_region_cmd {
+	struct nv_pmu_acr_cmd cmd;
+	u32 region_id;
+	u32 wpr_offset;
+};
+
+struct nv_pmu_acr_init_wpr_region_msg {
+	struct nv_pmu_acr_msg msg;
+	u32 error_code;
+};
+
+struct nv_pmu_acr_bootstrap_falcon_cmd {
+	struct nv_pmu_acr_cmd cmd;
+#define NV_PMU_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_YES                  0x00000000
+#define NV_PMU_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_NO                   0x00000001
+	u32 flags;
+	u32 falcon_id;
+};
+
+struct nv_pmu_acr_bootstrap_falcon_msg {
+	struct nv_pmu_acr_msg msg;
+	u32 falcon_id;
+};
+
+struct nv_pmu_acr_bootstrap_multiple_falcons_cmd {
+	struct nv_pmu_acr_cmd cmd;
+#define NV_PMU_ACR_BOOTSTRAP_MULTIPLE_FALCONS_FLAGS_RESET_YES        0x00000000
+#define NV_PMU_ACR_BOOTSTRAP_MULTIPLE_FALCONS_FLAGS_RESET_NO         0x00000001
+	u32 flags;
+	u32 falcon_mask;
+	u32 use_va_mask;
+	u32 wpr_lo;
+	u32 wpr_hi;
+};
+
+struct nv_pmu_acr_bootstrap_multiple_falcons_msg {
+	struct nv_pmu_acr_msg msg;
+	u32 falcon_mask;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvfw/sec2.h b/drivers/gpu/drm/nouveau/include/nvfw/sec2.h
new file mode 100644
index 000000000000..03496558b775
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvfw/sec2.h
@@ -0,0 +1,60 @@
+#ifndef __NVFW_SEC2_H__
+#define __NVFW_SEC2_H__
+
+struct nv_sec2_args {
+	u32 freq_hz;
+	u32 falc_trace_size;
+	u32 falc_trace_dma_base;
+	u32 falc_trace_dma_idx;
+	bool secure_mode;
+};
+
+#define NV_SEC2_UNIT_INIT                                                  0x01
+#define NV_SEC2_UNIT_ACR                                                   0x08
+
+struct nv_sec2_init_msg {
+	struct nv_falcon_msg hdr;
+#define NV_SEC2_INIT_MSG_INIT                                              0x00
+	u8 msg_type;
+
+	u8 num_queues;
+	u16 os_debug_entry_point;
+
+	struct {
+		u32 offset;
+		u16 size;
+		u8 index;
+#define NV_SEC2_INIT_MSG_QUEUE_ID_CMDQ                                     0x00
+#define NV_SEC2_INIT_MSG_QUEUE_ID_MSGQ                                     0x01
+		u8 id;
+	} queue_info[2];
+
+	u32 sw_managed_area_offset;
+	u16 sw_managed_area_size;
+};
+
+struct nv_sec2_acr_cmd {
+	struct nv_falcon_cmd hdr;
+#define NV_SEC2_ACR_CMD_BOOTSTRAP_FALCON                                   0x00
+	u8 cmd_type;
+};
+
+struct nv_sec2_acr_msg {
+	struct nv_falcon_cmd hdr;
+	u8 msg_type;
+};
+
+struct nv_sec2_acr_bootstrap_falcon_cmd {
+	struct nv_sec2_acr_cmd cmd;
+#define NV_SEC2_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_YES                 0x00000000
+#define NV_SEC2_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_NO                  0x00000001
+	u32 flags;
+	u32 falcon_id;
+};
+
+struct nv_sec2_acr_bootstrap_falcon_msg {
+	struct nv_sec2_acr_msg msg;
+	u32 error_code;
+	u32 falcon_id;
+};
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index f704ae600e94..30659747ffe8 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -166,6 +166,8 @@
 
 #define VOLTA_A                                       /* cl9097.h */ 0x0000c397
 
+#define TURING_A                                      /* cl9097.h */ 0x0000c597
+
 #define NV74_BSP                                                     0x000074b0
 
 #define GT212_MSVLD                                                  0x000085b1
@@ -207,6 +209,7 @@
 #define PASCAL_COMPUTE_A                                             0x0000c0c0
 #define PASCAL_COMPUTE_B                                             0x0000c1c0
 #define VOLTA_COMPUTE_A                                              0x0000c3c0
+#define TURING_COMPUTE_A                                             0x0000c5c0
 
 #define NV74_CIPHER                                                  0x000074c1
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvif/if0008.h b/drivers/gpu/drm/nouveau/include/nvif/if0008.h
index 8450127420f5..c21d09f04f1d 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/if0008.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/if0008.h
@@ -35,7 +35,7 @@ struct nvif_mmu_type_v0 {
 
 struct nvif_mmu_kind_v0 {
 	__u8  version;
-	__u8  pad01[1];
+	__u8  kind_inv;
 	__u16 count;
 	__u8  data[];
 };
diff --git a/drivers/gpu/drm/nouveau/include/nvif/mmu.h b/drivers/gpu/drm/nouveau/include/nvif/mmu.h
index 747ecf67e403..cec1e88a0a05 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/mmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/mmu.h
@@ -7,6 +7,7 @@ struct nvif_mmu {
 	u8  dmabits;
 	u8  heap_nr;
 	u8  type_nr;
+	u8  kind_inv;
 	u16 kind_nr;
 	s32 mem;
 
@@ -36,9 +37,8 @@ void nvif_mmu_fini(struct nvif_mmu *);
 static inline bool
 nvif_mmu_kind_valid(struct nvif_mmu *mmu, u8 kind)
 {
-	const u8 invalid = mmu->kind_nr - 1;
 	if (kind) {
-		if (kind >= mmu->kind_nr || mmu->kind[kind] == invalid)
+		if (kind >= mmu->kind_nr || mmu->kind[kind] == mmu->kind_inv)
 			return false;
 	}
 	return true;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 6d55cd0476aa..5c007ce62fc3 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -23,13 +23,13 @@ enum nvkm_devidx {
 	NVKM_SUBDEV_MMU,
 	NVKM_SUBDEV_BAR,
 	NVKM_SUBDEV_FAULT,
+	NVKM_SUBDEV_ACR,
 	NVKM_SUBDEV_PMU,
 	NVKM_SUBDEV_VOLT,
 	NVKM_SUBDEV_ICCSENSE,
 	NVKM_SUBDEV_THERM,
 	NVKM_SUBDEV_CLK,
 	NVKM_SUBDEV_GSP,
-	NVKM_SUBDEV_SECBOOT,
 
 	NVKM_ENGINE_BSP,
 
@@ -129,6 +129,7 @@ struct nvkm_device {
 		struct notifier_block nb;
 	} acpi;
 
+	struct nvkm_acr *acr;
 	struct nvkm_bar *bar;
 	struct nvkm_bios *bios;
 	struct nvkm_bus *bus;
@@ -149,7 +150,6 @@ struct nvkm_device {
 	struct nvkm_subdev *mxm;
 	struct nvkm_pci *pci;
 	struct nvkm_pmu *pmu;
-	struct nvkm_secboot *secboot;
 	struct nvkm_therm *therm;
 	struct nvkm_timer *timer;
 	struct nvkm_top *top;
@@ -169,7 +169,7 @@ struct nvkm_device {
 	struct nvkm_engine *mspdec;
 	struct nvkm_engine *msppp;
 	struct nvkm_engine *msvld;
-	struct nvkm_engine *nvenc[3];
+	struct nvkm_nvenc *nvenc[3];
 	struct nvkm_nvdec *nvdec[3];
 	struct nvkm_pm *pm;
 	struct nvkm_engine *sec;
@@ -202,6 +202,7 @@ struct nvkm_device_quirk {
 struct nvkm_device_chip {
 	const char *name;
 
+	int (*acr     )(struct nvkm_device *, int idx, struct nvkm_acr **);
 	int (*bar     )(struct nvkm_device *, int idx, struct nvkm_bar **);
 	int (*bios    )(struct nvkm_device *, int idx, struct nvkm_bios **);
 	int (*bus     )(struct nvkm_device *, int idx, struct nvkm_bus **);
@@ -222,7 +223,6 @@ struct nvkm_device_chip {
 	int (*mxm     )(struct nvkm_device *, int idx, struct nvkm_subdev **);
 	int (*pci     )(struct nvkm_device *, int idx, struct nvkm_pci **);
 	int (*pmu     )(struct nvkm_device *, int idx, struct nvkm_pmu **);
-	int (*secboot )(struct nvkm_device *, int idx, struct nvkm_secboot **);
 	int (*therm   )(struct nvkm_device *, int idx, struct nvkm_therm **);
 	int (*timer   )(struct nvkm_device *, int idx, struct nvkm_timer **);
 	int (*top     )(struct nvkm_device *, int idx, struct nvkm_top **);
@@ -242,7 +242,7 @@ struct nvkm_device_chip {
 	int (*mspdec  )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*msppp   )(struct nvkm_device *, int idx, struct nvkm_engine **);
 	int (*msvld   )(struct nvkm_device *, int idx, struct nvkm_engine **);
-	int (*nvenc[3])(struct nvkm_device *, int idx, struct nvkm_engine **);
+	int (*nvenc[3])(struct nvkm_device *, int idx, struct nvkm_nvenc **);
 	int (*nvdec[3])(struct nvkm_device *, int idx, struct nvkm_nvdec **);
 	int (*pm      )(struct nvkm_device *, int idx, struct nvkm_pm **);
 	int (*sec     )(struct nvkm_device *, int idx, struct nvkm_engine **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/falcon.h b/drivers/gpu/drm/nouveau/include/nvkm/core/falcon.h
new file mode 100644
index 000000000000..daa8e4bfb6bf
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/falcon.h
@@ -0,0 +1,77 @@
+#ifndef __NVKM_FALCON_H__
+#define __NVKM_FALCON_H__
+#include <engine/falcon.h>
+
+int nvkm_falcon_ctor(const struct nvkm_falcon_func *, struct nvkm_subdev *owner,
+		     const char *name, u32 addr, struct nvkm_falcon *);
+void nvkm_falcon_dtor(struct nvkm_falcon *);
+
+void nvkm_falcon_v1_load_imem(struct nvkm_falcon *,
+			      void *, u32, u32, u16, u8, bool);
+void nvkm_falcon_v1_load_dmem(struct nvkm_falcon *, void *, u32, u32, u8);
+void nvkm_falcon_v1_read_dmem(struct nvkm_falcon *, u32, u32, u8, void *);
+void nvkm_falcon_v1_bind_context(struct nvkm_falcon *, struct nvkm_memory *);
+int nvkm_falcon_v1_wait_for_halt(struct nvkm_falcon *, u32);
+int nvkm_falcon_v1_clear_interrupt(struct nvkm_falcon *, u32);
+void nvkm_falcon_v1_set_start_addr(struct nvkm_falcon *, u32 start_addr);
+void nvkm_falcon_v1_start(struct nvkm_falcon *);
+int nvkm_falcon_v1_enable(struct nvkm_falcon *);
+void nvkm_falcon_v1_disable(struct nvkm_falcon *);
+
+void gp102_sec2_flcn_bind_context(struct nvkm_falcon *, struct nvkm_memory *);
+int gp102_sec2_flcn_enable(struct nvkm_falcon *);
+
+#define FLCN_PRINTK(t,f,fmt,a...) do {                                         \
+	if (nvkm_subdev_name[(f)->owner->index] != (f)->name)                  \
+		nvkm_##t((f)->owner, "%s: "fmt"\n", (f)->name, ##a);           \
+	else                                                                   \
+		nvkm_##t((f)->owner, fmt"\n", ##a);                            \
+} while(0)
+#define FLCN_DBG(f,fmt,a...) FLCN_PRINTK(debug, (f), fmt, ##a)
+#define FLCN_ERR(f,fmt,a...) FLCN_PRINTK(error, (f), fmt, ##a)
+
+/**
+ * struct nv_falcon_msg - header for all messages
+ *
+ * @unit_id:	id of firmware process that sent the message
+ * @size:	total size of message
+ * @ctrl_flags:	control flags
+ * @seq_id:	used to match a message from its corresponding command
+ */
+struct nv_falcon_msg {
+	u8 unit_id;
+	u8 size;
+	u8 ctrl_flags;
+	u8 seq_id;
+};
+
+#define nv_falcon_cmd nv_falcon_msg
+#define NV_FALCON_CMD_UNIT_ID_REWIND                                       0x00
+
+struct nvkm_falcon_qmgr;
+int nvkm_falcon_qmgr_new(struct nvkm_falcon *, struct nvkm_falcon_qmgr **);
+void nvkm_falcon_qmgr_del(struct nvkm_falcon_qmgr **);
+
+typedef int
+(*nvkm_falcon_qmgr_callback)(void *priv, struct nv_falcon_msg *);
+
+struct nvkm_falcon_cmdq;
+int nvkm_falcon_cmdq_new(struct nvkm_falcon_qmgr *, const char *name,
+			 struct nvkm_falcon_cmdq **);
+void nvkm_falcon_cmdq_del(struct nvkm_falcon_cmdq **);
+void nvkm_falcon_cmdq_init(struct nvkm_falcon_cmdq *,
+			   u32 index, u32 offset, u32 size);
+void nvkm_falcon_cmdq_fini(struct nvkm_falcon_cmdq *);
+int nvkm_falcon_cmdq_send(struct nvkm_falcon_cmdq *, struct nv_falcon_cmd *,
+			  nvkm_falcon_qmgr_callback, void *priv,
+			  unsigned long timeout_jiffies);
+
+struct nvkm_falcon_msgq;
+int nvkm_falcon_msgq_new(struct nvkm_falcon_qmgr *, const char *name,
+			 struct nvkm_falcon_msgq **);
+void nvkm_falcon_msgq_del(struct nvkm_falcon_msgq **);
+void nvkm_falcon_msgq_init(struct nvkm_falcon_msgq *,
+			   u32 index, u32 offset, u32 size);
+int nvkm_falcon_msgq_recv_initmsg(struct nvkm_falcon_msgq *, void *, u32 size);
+void nvkm_falcon_msgq_recv(struct nvkm_falcon_msgq *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h b/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h
index 383370c32428..d14b7fb07368 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/firmware.h
@@ -1,12 +1,55 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_FIRMWARE_H__
 #define __NVKM_FIRMWARE_H__
+#include <core/option.h>
 #include <core/subdev.h>
 
-int nvkm_firmware_get_version(const struct nvkm_subdev *, const char *fwname,
-			      int min_version, int max_version,
-			      const struct firmware **);
-int nvkm_firmware_get(const struct nvkm_subdev *, const char *fwname,
+int nvkm_firmware_get(const struct nvkm_subdev *, const char *fwname, int ver,
 		      const struct firmware **);
 void nvkm_firmware_put(const struct firmware *);
+
+int nvkm_firmware_load_blob(const struct nvkm_subdev *subdev, const char *path,
+			    const char *name, int ver, struct nvkm_blob *);
+int nvkm_firmware_load_name(const struct nvkm_subdev *subdev, const char *path,
+			    const char *name, int ver,
+			    const struct firmware **);
+
+#define nvkm_firmware_load(s,l,o,p...) ({                                      \
+	struct nvkm_subdev *_s = (s);                                          \
+	const char *_opts = (o);                                               \
+	char _option[32];                                                      \
+	typeof(l[0]) *_list = (l), *_next, *_fwif = NULL;                      \
+	int _ver, _fwv, _ret = 0;                                              \
+                                                                               \
+	snprintf(_option, sizeof(_option), "Nv%sFw", _opts);                   \
+	_ver = nvkm_longopt(_s->device->cfgopt, _option, -2);                  \
+	if (_ver >= -1) {                                                      \
+		for (_next = _list; !_fwif && _next->load; _next++) {          \
+			if (_next->version == _ver)                            \
+				_fwif = _next;                                 \
+		}                                                              \
+		_ret = _fwif ? 0 : -EINVAL;                                    \
+	}                                                                      \
+                                                                               \
+	if (_ret == 0) {                                                       \
+		snprintf(_option, sizeof(_option), "Nv%sFwVer", _opts);        \
+		_fwv = _fwif ? _fwif->version : -1;                            \
+		_ver = nvkm_longopt(_s->device->cfgopt, _option, _fwv);        \
+		for (_next = _fwif ? _fwif : _list; _next->load; _next++) {    \
+			_fwv = (_ver >= 0) ? _ver : _next->version;            \
+			_ret = _next->load(p, _fwv, _next);                    \
+			if (_ret == 0 || _ver >= 0) {                          \
+				_fwif = _next;                                 \
+				break;                                         \
+			}                                                      \
+		}                                                              \
+	}                                                                      \
+                                                                               \
+	if (_ret) {                                                            \
+		nvkm_error(_s, "failed to load firmware\n");                   \
+		_fwif = ERR_PTR(_ret);                                         \
+	}                                                                      \
+	                                                                       \
+	_fwif;                                                                 \
+})
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h b/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h
index b23bf6109f2d..74d3f1a809d7 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/memory.h
@@ -84,6 +84,22 @@ void nvkm_memory_tags_put(struct nvkm_memory *, struct nvkm_device *,
 	nvkm_wo32((o), __a + 4, upper_32_bits(__d));                           \
 } while(0)
 
+#define nvkm_robj(o,a,p,s) do {                                                \
+	u32 _addr = (a), _size = (s) >> 2, *_data = (void *)(p);               \
+	while (_size--) {                                                      \
+		*(_data++) = nvkm_ro32((o), _addr);                            \
+		_addr += 4;                                                    \
+	}                                                                      \
+} while(0)
+
+#define nvkm_wobj(o,a,p,s) do {                                                \
+	u32 _addr = (a), _size = (s) >> 2, *_data = (void *)(p);               \
+	while (_size--) {                                                      \
+		nvkm_wo32((o), _addr, *(_data++));                             \
+		_addr += 4;                                                    \
+	}                                                                      \
+} while(0)
+
 #define nvkm_fill(t,s,o,a,d,c) do {                                            \
 	u64 _a = (a), _c = (c), _d = (d), _o = _a >> s, _s = _c << s;          \
 	u##t __iomem *_m = nvkm_kmap(o);                                       \
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/os.h b/drivers/gpu/drm/nouveau/include/nvkm/core/os.h
index 029a416197db..d7ba3205207f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/os.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/os.h
@@ -21,4 +21,17 @@
 	iowrite32_native(lower_32_bits(_v), &_p[0]);			       \
 	iowrite32_native(upper_32_bits(_v), &_p[1]);			       \
 } while(0)
+
+struct nvkm_blob {
+	void *data;
+	u32 size;
+};
+
+static inline void
+nvkm_blob_dtor(struct nvkm_blob *blob)
+{
+	kfree(blob->data);
+	blob->data = NULL;
+	blob->size = 0;
+}
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h
index 23b582d696c6..27c1f868552c 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/falcon.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: MIT */
-#ifndef __NVKM_FALCON_H__
-#define __NVKM_FALCON_H__
+#ifndef __NVKM_FLCNEN_H__
+#define __NVKM_FLCNEN_H__
 #define nvkm_falcon(p) container_of((p), struct nvkm_falcon, engine)
 #include <core/engine.h>
 struct nvkm_fifo_chan;
@@ -23,12 +23,13 @@ struct nvkm_falcon {
 
 	struct mutex mutex;
 	struct mutex dmem_mutex;
+	bool oneinit;
+
 	const struct nvkm_subdev *user;
 
 	u8 version;
 	u8 secret;
 	bool debug;
-	bool has_emem;
 
 	struct nvkm_memory *core;
 	bool external;
@@ -76,9 +77,14 @@ struct nvkm_falcon_func {
 	} data;
 	void (*init)(struct nvkm_falcon *);
 	void (*intr)(struct nvkm_falcon *, struct nvkm_fifo_chan *);
+
+	u32 debug;
+	u32 fbif;
+
 	void (*load_imem)(struct nvkm_falcon *, void *, u32, u32, u16, u8, bool);
 	void (*load_dmem)(struct nvkm_falcon *, void *, u32, u32, u8);
 	void (*read_dmem)(struct nvkm_falcon *, u32, u32, u8, void *);
+	u32 emem_addr;
 	void (*bind_context)(struct nvkm_falcon *, struct nvkm_memory *);
 	int (*wait_for_halt)(struct nvkm_falcon *, u32);
 	int (*clear_interrupt)(struct nvkm_falcon *, u32);
@@ -86,6 +92,13 @@ struct nvkm_falcon_func {
 	void (*start)(struct nvkm_falcon *);
 	int (*enable)(struct nvkm_falcon *falcon);
 	void (*disable)(struct nvkm_falcon *falcon);
+	int (*reset)(struct nvkm_falcon *);
+
+	struct {
+		u32 head;
+		u32 tail;
+		u32 stride;
+	} cmdq, msgq;
 
 	struct nvkm_sclass sclass[];
 };
@@ -122,5 +135,4 @@ int nvkm_falcon_clear_interrupt(struct nvkm_falcon *, u32);
 int nvkm_falcon_enable(struct nvkm_falcon *);
 void nvkm_falcon_disable(struct nvkm_falcon *);
 int nvkm_falcon_reset(struct nvkm_falcon *);
-
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
index 2cde36f3c064..1530c81f86a2 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/gr.h
@@ -50,6 +50,8 @@ int gp100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp102_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp104_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp107_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int gp108_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gp10b_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 int gv100_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
+int tu102_gr_new(struct nvkm_device *, int, struct nvkm_gr **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h
index 7c7d7f0abfcc..1b3183e31606 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvdec.h
@@ -3,13 +3,13 @@
 #define __NVKM_NVDEC_H__
 #define nvkm_nvdec(p) container_of((p), struct nvkm_nvdec, engine)
 #include <core/engine.h>
+#include <core/falcon.h>
 
 struct nvkm_nvdec {
+	const struct nvkm_nvdec_func *func;
 	struct nvkm_engine engine;
-	u32 addr;
-
-	struct nvkm_falcon *falcon;
+	struct nvkm_falcon falcon;
 };
 
-int gp102_nvdec_new(struct nvkm_device *, int, struct nvkm_nvdec **);
+int gm107_nvdec_new(struct nvkm_device *, int, struct nvkm_nvdec **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h
index 21624046d0a1..33e6ba8adc8d 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/nvenc.h
@@ -1,5 +1,15 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_NVENC_H__
 #define __NVKM_NVENC_H__
+#define nvkm_nvenc(p) container_of((p), struct nvkm_nvenc, engine)
 #include <core/engine.h>
+#include <core/falcon.h>
+
+struct nvkm_nvenc {
+	const struct nvkm_nvenc_func *func;
+	struct nvkm_engine engine;
+	struct nvkm_falcon falcon;
+};
+
+int gm107_nvenc_new(struct nvkm_device *, int, struct nvkm_nvenc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h
index 33078f86c779..34dc765648d5 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/sec2.h
@@ -1,17 +1,24 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_SEC2_H__
 #define __NVKM_SEC2_H__
+#define nvkm_sec2(p) container_of((p), struct nvkm_sec2, engine)
 #include <core/engine.h>
+#include <core/falcon.h>
 
 struct nvkm_sec2 {
+	const struct nvkm_sec2_func *func;
 	struct nvkm_engine engine;
-	u32 addr;
+	struct nvkm_falcon falcon;
+
+	struct nvkm_falcon_qmgr *qmgr;
+	struct nvkm_falcon_cmdq *cmdq;
+	struct nvkm_falcon_msgq *msgq;
 
-	struct nvkm_falcon *falcon;
-	struct nvkm_msgqueue *queue;
 	struct work_struct work;
+	bool initmsg_received;
 };
 
 int gp102_sec2_new(struct nvkm_device *, int, struct nvkm_sec2 **);
+int gp108_sec2_new(struct nvkm_device *, int, struct nvkm_sec2 **);
 int tu102_sec2_new(struct nvkm_device *, int, struct nvkm_sec2 **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/acr.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/acr.h
new file mode 100644
index 000000000000..5d9c3a966de6
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/acr.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVKM_ACR_H__
+#define __NVKM_ACR_H__
+#define nvkm_acr(p) container_of((p), struct nvkm_acr, subdev)
+#include <core/subdev.h>
+#include <core/falcon.h>
+
+enum nvkm_acr_lsf_id {
+	NVKM_ACR_LSF_PMU = 0,
+	NVKM_ACR_LSF_GSPLITE = 1,
+	NVKM_ACR_LSF_FECS = 2,
+	NVKM_ACR_LSF_GPCCS = 3,
+	NVKM_ACR_LSF_NVDEC = 4,
+	NVKM_ACR_LSF_SEC2 = 7,
+	NVKM_ACR_LSF_MINION = 10,
+	NVKM_ACR_LSF_NUM
+};
+
+static inline const char *
+nvkm_acr_lsf_id(enum nvkm_acr_lsf_id id)
+{
+	switch (id) {
+	case NVKM_ACR_LSF_PMU    : return "pmu";
+	case NVKM_ACR_LSF_GSPLITE: return "gsplite";
+	case NVKM_ACR_LSF_FECS   : return "fecs";
+	case NVKM_ACR_LSF_GPCCS  : return "gpccs";
+	case NVKM_ACR_LSF_NVDEC  : return "nvdec";
+	case NVKM_ACR_LSF_SEC2   : return "sec2";
+	case NVKM_ACR_LSF_MINION : return "minion";
+	default:
+		return "unknown";
+	}
+}
+
+struct nvkm_acr {
+	const struct nvkm_acr_func *func;
+	struct nvkm_subdev subdev;
+
+	struct list_head hsfw, hsf;
+	struct list_head lsfw, lsf;
+
+	struct nvkm_memory *wpr;
+	u64 wpr_start;
+	u64 wpr_end;
+	u64 shadow_start;
+
+	struct nvkm_memory *inst;
+	struct nvkm_vmm *vmm;
+
+	bool done;
+
+	const struct firmware *wpr_fw;
+	bool wpr_comp;
+	u64 wpr_prev;
+};
+
+bool nvkm_acr_managed_falcon(struct nvkm_device *, enum nvkm_acr_lsf_id);
+int nvkm_acr_bootstrap_falcons(struct nvkm_device *, unsigned long mask);
+
+int gm200_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gm20b_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gp102_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gp108_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int gp10b_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+int tu102_acr_new(struct nvkm_device *, int, struct nvkm_acr **);
+
+struct nvkm_acr_lsfw {
+	const struct nvkm_acr_lsf_func *func;
+	struct nvkm_falcon *falcon;
+	enum nvkm_acr_lsf_id id;
+
+	struct list_head head;
+
+	struct nvkm_blob img;
+
+	const struct firmware *sig;
+
+	u32 bootloader_size;
+	u32 bootloader_imem_offset;
+
+	u32 app_size;
+	u32 app_start_offset;
+	u32 app_imem_entry;
+	u32 app_resident_code_offset;
+	u32 app_resident_code_size;
+	u32 app_resident_data_offset;
+	u32 app_resident_data_size;
+
+	u32 ucode_size;
+	u32 data_size;
+
+	struct {
+		u32 lsb;
+		u32 img;
+		u32 bld;
+	} offset;
+	u32 bl_data_size;
+};
+
+struct nvkm_acr_lsf_func {
+/* The (currently) map directly to LSB header flags. */
+#define NVKM_ACR_LSF_LOAD_CODE_AT_0                                  0x00000001
+#define NVKM_ACR_LSF_DMACTL_REQ_CTX                                  0x00000004
+#define NVKM_ACR_LSF_FORCE_PRIV_LOAD                                 0x00000008
+	u32 flags;
+	u32 bld_size;
+	void (*bld_write)(struct nvkm_acr *, u32 bld, struct nvkm_acr_lsfw *);
+	void (*bld_patch)(struct nvkm_acr *, u32 bld, s64 adjust);
+	int (*boot)(struct nvkm_falcon *);
+	int (*bootstrap_falcon)(struct nvkm_falcon *, enum nvkm_acr_lsf_id);
+	int (*bootstrap_multiple_falcons)(struct nvkm_falcon *, u32 mask);
+};
+
+int
+nvkm_acr_lsfw_load_sig_image_desc(struct nvkm_subdev *, struct nvkm_falcon *,
+				  enum nvkm_acr_lsf_id, const char *path,
+				  int ver, const struct nvkm_acr_lsf_func *);
+int
+nvkm_acr_lsfw_load_sig_image_desc_v1(struct nvkm_subdev *, struct nvkm_falcon *,
+				     enum nvkm_acr_lsf_id, const char *path,
+				     int ver, const struct nvkm_acr_lsf_func *);
+int
+nvkm_acr_lsfw_load_bl_inst_data_sig(struct nvkm_subdev *, struct nvkm_falcon *,
+				    enum nvkm_acr_lsf_id, const char *path,
+				    int ver, const struct nvkm_acr_lsf_func *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
index 97322f95b3ee..a513c16ab105 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fault.h
@@ -31,6 +31,7 @@ struct nvkm_fault_data {
 };
 
 int gp100_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
+int gp10b_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
 int gv100_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
 int tu102_fault_new(struct nvkm_device *, int, struct nvkm_fault **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 239ad222b95a..34b56b10218a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -33,6 +33,8 @@ struct nvkm_fb {
 	const struct nvkm_fb_func *func;
 	struct nvkm_subdev subdev;
 
+	struct nvkm_blob vpr_scrubber;
+
 	struct nvkm_ram *ram;
 	struct nvkm_mm tags;
 
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 4c672a5c4cd5..06db67610a50 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -2,12 +2,11 @@
 #define __NVKM_GSP_H__
 #define nvkm_gsp(p) container_of((p), struct nvkm_gsp, subdev)
 #include <core/subdev.h>
+#include <core/falcon.h>
 
 struct nvkm_gsp {
 	struct nvkm_subdev subdev;
-	u32 addr;
-
-	struct nvkm_falcon *falcon;
+	struct nvkm_falcon falcon;
 };
 
 int gv100_gsp_new(struct nvkm_device *, int, struct nvkm_gsp **);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
index 644d527c3b96..d76f60d7d29a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/ltc.h
@@ -40,4 +40,5 @@ int gm107_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gm200_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gp100_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 int gp102_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
+int gp10b_ltc_new(struct nvkm_device *, int, struct nvkm_ltc **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h
index 4752006880f3..da553089d2d8 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/pmu.h
@@ -2,13 +2,20 @@
 #ifndef __NVKM_PMU_H__
 #define __NVKM_PMU_H__
 #include <core/subdev.h>
-#include <engine/falcon.h>
+#include <core/falcon.h>
 
 struct nvkm_pmu {
 	const struct nvkm_pmu_func *func;
 	struct nvkm_subdev subdev;
-	struct nvkm_falcon *falcon;
-	struct nvkm_msgqueue *queue;
+	struct nvkm_falcon falcon;
+
+	struct nvkm_falcon_qmgr *qmgr;
+	struct nvkm_falcon_cmdq *hpq;
+	struct nvkm_falcon_cmdq *lpq;
+	struct nvkm_falcon_msgq *msgq;
+	bool initmsg_received;
+
+	struct completion wpr_ready;
 
 	struct {
 		u32 base;
@@ -43,6 +50,7 @@ int gm107_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 int gm20b_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 int gp100_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 int gp102_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
+int gp10b_pmu_new(struct nvkm_device *, int, struct nvkm_pmu **);
 
 /* interface to MEMX process running on PMU */
 struct nvkm_memx;
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index f8015e0318d7..1b62ccc57aef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -1162,7 +1162,7 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, bool intr,
 void
 nouveau_bo_move_init(struct nouveau_drm *drm)
 {
-	static const struct {
+	static const struct _method_table {
 		const char *name;
 		int engine;
 		s32 oclass;
@@ -1192,7 +1192,8 @@ nouveau_bo_move_init(struct nouveau_drm *drm)
 		{  "M2MF", 0, 0x0039, nv04_bo_move_m2mf, nv04_bo_move_init },
 		{},
 		{ "CRYPT", 0, 0x88b4, nv98_bo_move_exec, nv50_bo_move_init },
-	}, *mthd = _methods;
+	};
+	const struct _method_table *mthd = _methods;
 	const char *name = "CPU";
 	int ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 282fd90b65e1..d9381a053169 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -55,6 +55,8 @@ nouveau_channel_killed(struct nvif_notify *ntfy)
 	struct nouveau_cli *cli = (void *)chan->user.client;
 	NV_PRINTK(warn, cli, "channel %d killed!\n", chan->chid);
 	atomic_set(&chan->killed, 1);
+	if (chan->fence)
+		nouveau_fence_context_kill(chan->fence, -ENODEV);
 	return NVIF_NOTIFY_DROP;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index fa1439941596..0ad5d87b5a8e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -635,10 +635,10 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
 	unsigned long c, i;
 	int ret = -ENOMEM;
 
-	args.src = kcalloc(max, sizeof(args.src), GFP_KERNEL);
+	args.src = kcalloc(max, sizeof(*args.src), GFP_KERNEL);
 	if (!args.src)
 		goto out;
-	args.dst = kcalloc(max, sizeof(args.dst), GFP_KERNEL);
+	args.dst = kcalloc(max, sizeof(*args.dst), GFP_KERNEL);
 	if (!args.dst)
 		goto out_free_src;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 2cd83849600f..b65ae817eabf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -715,7 +715,6 @@ fail_nvkm:
 void
 nouveau_drm_device_remove(struct drm_device *dev)
 {
-	struct pci_dev *pdev = dev->pdev;
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvkm_client *client;
 	struct nvkm_device *device;
@@ -727,7 +726,6 @@ nouveau_drm_device_remove(struct drm_device *dev)
 	device = nvkm_device_find(client->device);
 
 	nouveau_drm_device_fini(dev);
-	pci_disable_device(pdev);
 	drm_dev_put(dev);
 	nvkm_device_del(&device);
 }
@@ -738,6 +736,7 @@ nouveau_drm_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
 	nouveau_drm_device_remove(dev);
+	pci_disable_device(pdev);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 70f34cacc552..c2c332fbde97 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -58,6 +58,8 @@
 #include <drm/ttm/ttm_module.h>
 #include <drm/ttm/ttm_page_alloc.h>
 
+#include <drm/drm_audio_component.h>
+
 #include "uapi/drm/nouveau_drm.h"
 
 struct nouveau_channel;
@@ -211,6 +213,11 @@ struct nouveau_drm {
 	struct nouveau_svm *svm;
 
 	struct nouveau_dmem *dmem;
+
+	struct {
+		struct drm_audio_component *component;
+		bool component_registered;
+	} audio;
 };
 
 static inline struct nouveau_drm *
@@ -248,11 +255,11 @@ void nouveau_drm_device_remove(struct drm_device *dev);
 #define NV_INFO(drm,f,a...) NV_PRINTK(info, &(drm)->client, f, ##a)
 
 #define NV_DEBUG(drm,f,a...) do {                                              \
-	if (unlikely(drm_debug & DRM_UT_DRIVER))                               \
+	if (drm_debug_enabled(DRM_UT_DRIVER))                                  \
 		NV_PRINTK(info, &(drm)->client, f, ##a);                       \
 } while(0)
 #define NV_ATOMIC(drm,f,a...) do {                                             \
-	if (unlikely(drm_debug & DRM_UT_ATOMIC))                               \
+	if (drm_debug_enabled(DRM_UT_ATOMIC))                                  \
 		NV_PRINTK(info, &(drm)->client, f, ##a);                       \
 } while(0)
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index f439f0a5b43a..0c5cdda3c336 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -203,7 +203,7 @@ nouveau_fbcon_release(struct fb_info *info, int user)
 	return 0;
 }
 
-static struct fb_ops nouveau_fbcon_ops = {
+static const struct fb_ops nouveau_fbcon_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = nouveau_fbcon_open,
@@ -214,7 +214,7 @@ static struct fb_ops nouveau_fbcon_ops = {
 	.fb_sync = nouveau_fbcon_sync,
 };
 
-static struct fb_ops nouveau_fbcon_sw_ops = {
+static const struct fb_ops nouveau_fbcon_sw_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = nouveau_fbcon_open,
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index 9118df035b28..666f2090d92b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -87,7 +87,7 @@ nouveau_local_fence(struct dma_fence *fence, struct nouveau_drm *drm)
 }
 
 void
-nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
+nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error)
 {
 	struct nouveau_fence *fence;
 
@@ -95,11 +95,19 @@ nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
 	while (!list_empty(&fctx->pending)) {
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 
+		if (error)
+			dma_fence_set_error(&fence->base, error);
+
 		if (nouveau_fence_signal(fence))
 			nvif_notify_put(&fctx->notify);
 	}
 	spin_unlock_irq(&fctx->lock);
+}
 
+void
+nouveau_fence_context_del(struct nouveau_fence_chan *fctx)
+{
+	nouveau_fence_context_kill(fctx, 0);
 	nvif_notify_fini(&fctx->notify);
 	fctx->dead = 1;
 
@@ -156,7 +164,7 @@ nouveau_fence_wait_uevent_handler(struct nvif_notify *notify)
 
 		fence = list_entry(fctx->pending.next, typeof(*fence), head);
 		chan = rcu_dereference_protected(fence->channel, lockdep_is_held(&fctx->lock));
-		if (nouveau_fence_update(fence->channel, fctx))
+		if (nouveau_fence_update(chan, fctx))
 			ret = NVIF_NOTIFY_DROP;
 	}
 	spin_unlock_irqrestore(&fctx->lock, flags);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index c9e24baaaa4f..4887caa69c65 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -63,6 +63,7 @@ struct nouveau_fence_priv {
 void nouveau_fence_context_new(struct nouveau_channel *, struct nouveau_fence_chan *);
 void nouveau_fence_context_del(struct nouveau_fence_chan *);
 void nouveau_fence_context_free(struct nouveau_fence_chan *);
+void nouveau_fence_context_kill(struct nouveau_fence_chan *, int error);
 
 int nv04_fence_create(struct nouveau_drm *);
 int nv04_fence_mthd(struct nouveau_channel *, u32, u32, u32);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 1324c19f4e5c..f5ece1f94973 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -484,12 +484,9 @@ retry:
 
 static int
 validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli,
-	      struct list_head *list, struct drm_nouveau_gem_pushbuf_bo *pbbo,
-	      uint64_t user_pbbo_ptr)
+	      struct list_head *list, struct drm_nouveau_gem_pushbuf_bo *pbbo)
 {
 	struct nouveau_drm *drm = chan->drm;
-	struct drm_nouveau_gem_pushbuf_bo __user *upbbo =
-				(void __force __user *)(uintptr_t)user_pbbo_ptr;
 	struct nouveau_bo *nvbo;
 	int ret, relocs = 0;
 
@@ -533,10 +530,6 @@ validate_list(struct nouveau_channel *chan, struct nouveau_cli *cli,
 			b->presumed.offset = nvbo->bo.offset;
 			b->presumed.valid = 0;
 			relocs++;
-
-			if (copy_to_user(&upbbo[nvbo->pbbo_index].presumed,
-					     &b->presumed, sizeof(b->presumed)))
-				return -EFAULT;
 		}
 	}
 
@@ -547,8 +540,8 @@ static int
 nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 			     struct drm_file *file_priv,
 			     struct drm_nouveau_gem_pushbuf_bo *pbbo,
-			     uint64_t user_buffers, int nr_buffers,
-			     struct validate_op *op, int *apply_relocs)
+			     int nr_buffers,
+			     struct validate_op *op, bool *apply_relocs)
 {
 	struct nouveau_cli *cli = nouveau_cli(file_priv);
 	int ret;
@@ -565,7 +558,7 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan,
 		return ret;
 	}
 
-	ret = validate_list(chan, cli, &op->list, pbbo, user_buffers);
+	ret = validate_list(chan, cli, &op->list, pbbo);
 	if (unlikely(ret < 0)) {
 		if (ret != -ERESTARTSYS)
 			NV_PRINTK(err, cli, "validating bo list\n");
@@ -605,16 +598,12 @@ u_memcpya(uint64_t user, unsigned nmemb, unsigned size)
 static int
 nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				struct drm_nouveau_gem_pushbuf *req,
+				struct drm_nouveau_gem_pushbuf_reloc *reloc,
 				struct drm_nouveau_gem_pushbuf_bo *bo)
 {
-	struct drm_nouveau_gem_pushbuf_reloc *reloc = NULL;
 	int ret = 0;
 	unsigned i;
 
-	reloc = u_memcpya(req->relocs, req->nr_relocs, sizeof(*reloc));
-	if (IS_ERR(reloc))
-		return PTR_ERR(reloc);
-
 	for (i = 0; i < req->nr_relocs; i++) {
 		struct drm_nouveau_gem_pushbuf_reloc *r = &reloc[i];
 		struct drm_nouveau_gem_pushbuf_bo *b;
@@ -693,11 +682,13 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_nouveau_gem_pushbuf *req = data;
 	struct drm_nouveau_gem_pushbuf_push *push;
+	struct drm_nouveau_gem_pushbuf_reloc *reloc = NULL;
 	struct drm_nouveau_gem_pushbuf_bo *bo;
 	struct nouveau_channel *chan = NULL;
 	struct validate_op op;
 	struct nouveau_fence *fence = NULL;
-	int i, j, ret = 0, do_reloc = 0;
+	int i, j, ret = 0;
+	bool do_reloc = false, sync = false;
 
 	if (unlikely(!abi16))
 		return -ENOMEM;
@@ -711,6 +702,10 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 
 	if (!chan)
 		return nouveau_abi16_put(abi16, -ENOENT);
+	if (unlikely(atomic_read(&chan->killed)))
+		return nouveau_abi16_put(abi16, -ENODEV);
+
+	sync = req->vram_available & NOUVEAU_GEM_PUSHBUF_SYNC;
 
 	req->vram_available = drm->gem.vram_available;
 	req->gart_available = drm->gem.gart_available;
@@ -755,7 +750,8 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 	}
 
 	/* Validate buffer list */
-	ret = nouveau_gem_pushbuf_validate(chan, file_priv, bo, req->buffers,
+revalidate:
+	ret = nouveau_gem_pushbuf_validate(chan, file_priv, bo,
 					   req->nr_buffers, &op, &do_reloc);
 	if (ret) {
 		if (ret != -ERESTARTSYS)
@@ -765,7 +761,18 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 
 	/* Apply any relocations that are required */
 	if (do_reloc) {
-		ret = nouveau_gem_pushbuf_reloc_apply(cli, req, bo);
+		if (!reloc) {
+			validate_fini(&op, chan, NULL, bo);
+			reloc = u_memcpya(req->relocs, req->nr_relocs, sizeof(*reloc));
+			if (IS_ERR(reloc)) {
+				ret = PTR_ERR(reloc);
+				goto out_prevalid;
+			}
+
+			goto revalidate;
+		}
+
+		ret = nouveau_gem_pushbuf_reloc_apply(cli, req, reloc, bo);
 		if (ret) {
 			NV_PRINTK(err, cli, "reloc apply: %d\n", ret);
 			goto out;
@@ -847,10 +854,33 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
 		goto out;
 	}
 
+	if (sync) {
+		if (!(ret = nouveau_fence_wait(fence, false, false))) {
+			if ((ret = dma_fence_get_status(&fence->base)) == 1)
+				ret = 0;
+		}
+	}
+
 out:
 	validate_fini(&op, chan, fence, bo);
 	nouveau_fence_unref(&fence);
 
+	if (do_reloc) {
+		struct drm_nouveau_gem_pushbuf_bo __user *upbbo =
+			u64_to_user_ptr(req->buffers);
+
+		for (i = 0; i < req->nr_buffers; i++) {
+			if (bo[i].presumed.valid)
+				continue;
+
+			if (copy_to_user(&upbbo[i].presumed, &bo[i].presumed,
+					 sizeof(bo[i].presumed))) {
+				ret = -EFAULT;
+				break;
+			}
+		}
+		u_free(reloc);
+	}
 out_prevalid:
 	u_free(bo);
 	u_free(push);
diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index d445c6f3fece..1c3104d20571 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -741,7 +741,7 @@ nouveau_hwmon_init(struct drm_device *dev)
 			special_groups[i++] = &pwm_fan_sensor_group;
 	}
 
-	special_groups[i] = 0;
+	special_groups[i] = NULL;
 	hwmon_dev = hwmon_device_register_with_info(dev->dev, "nouveau", dev,
 							&nouveau_chip_info,
 							special_groups);
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 77a0c6ad3cef..7ca0a2498532 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -63,14 +63,12 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man,
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	if (drm->client.device.info.ram_size == 0)
 		return -ENOMEM;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
@@ -103,11 +101,9 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man,
 {
 	struct nouveau_bo *nvbo = nouveau_bo(bo);
 	struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
-	struct nouveau_mem *mem;
 	int ret;
 
 	ret = nouveau_mem_new(&drm->master, nvbo->kind, nvbo->comp, reg);
-	mem = nouveau_mem(reg);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c
index 77061182a1cf..b28c7dc13ad6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c
@@ -69,8 +69,8 @@ nouveau_vma_del(struct nouveau_vma **pvma)
 		}
 		list_del(&vma->head);
 		kfree(*pvma);
-		*pvma = NULL;
 	}
+	*pvma = NULL;
 }
 
 int
diff --git a/drivers/gpu/drm/nouveau/nvif/mmu.c b/drivers/gpu/drm/nouveau/nvif/mmu.c
index 5641bda2046d..47efc408efa6 100644
--- a/drivers/gpu/drm/nouveau/nvif/mmu.c
+++ b/drivers/gpu/drm/nouveau/nvif/mmu.c
@@ -121,6 +121,7 @@ nvif_mmu_init(struct nvif_object *parent, s32 oclass, struct nvif_mmu *mmu)
 				       kind, argc);
 		if (ret == 0)
 			memcpy(mmu->kind, kind->data, kind->count);
+		mmu->kind_inv = kind->kind_inv;
 		kfree(kind);
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/Kbuild b/drivers/gpu/drm/nouveau/nvkm/Kbuild
index b53de9ba8c73..db3ade125fa9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/Kbuild
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: MIT
 include $(src)/nvkm/core/Kbuild
+include $(src)/nvkm/nvfw/Kbuild
 include $(src)/nvkm/falcon/Kbuild
 include $(src)/nvkm/subdev/Kbuild
 include $(src)/nvkm/engine/Kbuild
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
index 092acdec2c39..8b25367917ca 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@@ -22,6 +22,40 @@
 #include <core/device.h>
 #include <core/firmware.h>
 
+int
+nvkm_firmware_load_name(const struct nvkm_subdev *subdev, const char *base,
+			const char *name, int ver, const struct firmware **pfw)
+{
+	char path[64];
+	int ret;
+
+	snprintf(path, sizeof(path), "%s%s", base, name);
+	ret = nvkm_firmware_get(subdev, path, ver, pfw);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+int
+nvkm_firmware_load_blob(const struct nvkm_subdev *subdev, const char *base,
+			const char *name, int ver, struct nvkm_blob *blob)
+{
+	const struct firmware *fw;
+	int ret;
+
+	ret = nvkm_firmware_load_name(subdev, base, name, ver, &fw);
+	if (ret == 0) {
+		blob->data = kmemdup(fw->data, fw->size, GFP_KERNEL);
+		blob->size = fw->size;
+		nvkm_firmware_put(fw);
+		if (!blob->data)
+			return -ENOMEM;
+	}
+
+	return ret;
+}
+
 /**
  * nvkm_firmware_get - load firmware from the official nvidia/chip/ directory
  * @subdev	subdevice that will use that firmware
@@ -32,9 +66,8 @@
  * Firmware files released by NVIDIA will always follow this format.
  */
 int
-nvkm_firmware_get_version(const struct nvkm_subdev *subdev, const char *fwname,
-			  int min_version, int max_version,
-			  const struct firmware **fw)
+nvkm_firmware_get(const struct nvkm_subdev *subdev, const char *fwname, int ver,
+		  const struct firmware **fw)
 {
 	struct nvkm_device *device = subdev->device;
 	char f[64];
@@ -50,31 +83,21 @@ nvkm_firmware_get_version(const struct nvkm_subdev *subdev, const char *fwname,
 		cname[i] = tolower(cname[i]);
 	}
 
-	for (i = max_version; i >= min_version; i--) {
-		if (i != 0)
-			snprintf(f, sizeof(f), "nvidia/%s/%s-%d.bin", cname, fwname, i);
-		else
-			snprintf(f, sizeof(f), "nvidia/%s/%s.bin", cname, fwname);
-
-		if (!firmware_request_nowarn(fw, f, device->dev)) {
-			nvkm_debug(subdev, "firmware \"%s\" loaded\n", f);
-			return i;
-		}
+	if (ver != 0)
+		snprintf(f, sizeof(f), "nvidia/%s/%s-%d.bin", cname, fwname, ver);
+	else
+		snprintf(f, sizeof(f), "nvidia/%s/%s.bin", cname, fwname);
 
-		nvkm_debug(subdev, "firmware \"%s\" unavailable\n", f);
+	if (!firmware_request_nowarn(fw, f, device->dev)) {
+		nvkm_debug(subdev, "firmware \"%s\" loaded - %zu byte(s)\n",
+			   f, (*fw)->size);
+		return 0;
 	}
 
-	nvkm_error(subdev, "failed to load firmware \"%s\"", fwname);
+	nvkm_debug(subdev, "firmware \"%s\" unavailable\n", f);
 	return -ENOENT;
 }
 
-int
-nvkm_firmware_get(const struct nvkm_subdev *subdev, const char *fwname,
-		  const struct firmware **fw)
-{
-	return nvkm_firmware_get_version(subdev, fwname, 0, 0, fw);
-}
-
 /**
  * nvkm_firmware_put - release firmware loaded with nvkm_firmware_get
  */
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/memory.c b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
index e85a08ecd9da..4cc186262d34 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/memory.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/memory.c
@@ -91,8 +91,8 @@ nvkm_memory_tags_get(struct nvkm_memory *memory, struct nvkm_device *device,
 	}
 
 	refcount_set(&tags->refcount, 1);
+	*ptags = memory->tags = tags;
 	mutex_unlock(&fb->subdev.mutex);
-	*ptags = tags;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
index 245990de1e90..79a8f9d305c5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/subdev.c
@@ -30,6 +30,7 @@ static struct lock_class_key nvkm_subdev_lock_class[NVKM_SUBDEV_NR];
 
 const char *
 nvkm_subdev_name[NVKM_SUBDEV_NR] = {
+	[NVKM_SUBDEV_ACR     ] = "acr",
 	[NVKM_SUBDEV_BAR     ] = "bar",
 	[NVKM_SUBDEV_VBIOS   ] = "bios",
 	[NVKM_SUBDEV_BUS     ] = "bus",
@@ -50,7 +51,6 @@ nvkm_subdev_name[NVKM_SUBDEV_NR] = {
 	[NVKM_SUBDEV_MXM     ] = "mxm",
 	[NVKM_SUBDEV_PCI     ] = "pci",
 	[NVKM_SUBDEV_PMU     ] = "pmu",
-	[NVKM_SUBDEV_SECBOOT ] = "secboot",
 	[NVKM_SUBDEV_THERM   ] = "therm",
 	[NVKM_SUBDEV_TIMER   ] = "tmr",
 	[NVKM_SUBDEV_TOP     ] = "top",
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index c3c7159f3411..c7d700916eae 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -1987,6 +1987,8 @@ nv117_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm107_fifo_new,
 	.gr = gm107_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
@@ -2027,6 +2029,7 @@ nv118_chipset = {
 static const struct nvkm_device_chip
 nv120_chipset = {
 	.name = "GM200",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2045,7 +2048,6 @@ nv120_chipset = {
 	.pci = gk104_pci_new,
 	.pmu = gm107_pmu_new,
 	.therm = gm200_therm_new,
-	.secboot = gm200_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2056,12 +2058,16 @@ nv120_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm200_fifo_new,
 	.gr = gm200_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv124_chipset = {
 	.name = "GM204",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2080,7 +2086,6 @@ nv124_chipset = {
 	.pci = gk104_pci_new,
 	.pmu = gm107_pmu_new,
 	.therm = gm200_therm_new,
-	.secboot = gm200_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2091,12 +2096,16 @@ nv124_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm200_fifo_new,
 	.gr = gm200_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv126_chipset = {
 	.name = "GM206",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2115,7 +2124,6 @@ nv126_chipset = {
 	.pci = gk104_pci_new,
 	.pmu = gm107_pmu_new,
 	.therm = gm200_therm_new,
-	.secboot = gm200_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.volt = gk104_volt_new,
@@ -2126,12 +2134,15 @@ nv126_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gm200_fifo_new,
 	.gr = gm200_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv12b_chipset = {
 	.name = "GM20B",
+	.acr = gm20b_acr_new,
 	.bar = gm20b_bar_new,
 	.bus = gf100_bus_new,
 	.clk = gm20b_clk_new,
@@ -2143,7 +2154,6 @@ nv12b_chipset = {
 	.mc = gk20a_mc_new,
 	.mmu = gm20b_mmu_new,
 	.pmu = gm20b_pmu_new,
-	.secboot = gm20b_secboot_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
 	.ce[2] = gm200_ce_new,
@@ -2157,6 +2167,7 @@ nv12b_chipset = {
 static const struct nvkm_device_chip
 nv130_chipset = {
 	.name = "GP100",
+	.acr = gm200_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2172,7 +2183,6 @@ nv130_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gm200_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp100_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2187,12 +2197,17 @@ nv130_chipset = {
 	.disp = gp100_disp_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp100_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
+	.nvenc[2] = gm107_nvenc_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv132_chipset = {
 	.name = "GP102",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2208,7 +2223,6 @@ nv132_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2221,7 +2235,9 @@ nv132_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp102_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2229,6 +2245,7 @@ nv132_chipset = {
 static const struct nvkm_device_chip
 nv134_chipset = {
 	.name = "GP104",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2244,7 +2261,6 @@ nv134_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2257,7 +2273,9 @@ nv134_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp104_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2265,6 +2283,7 @@ nv134_chipset = {
 static const struct nvkm_device_chip
 nv136_chipset = {
 	.name = "GP106",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2280,7 +2299,6 @@ nv136_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2293,7 +2311,8 @@ nv136_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp104_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2301,6 +2320,7 @@ nv136_chipset = {
 static const struct nvkm_device_chip
 nv137_chipset = {
 	.name = "GP107",
+	.acr = gp102_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2316,7 +2336,6 @@ nv137_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp102_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2329,7 +2348,9 @@ nv137_chipset = {
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
 	.gr = gp107_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
 	.sec2 = gp102_sec2_new,
 	.sw = gf100_sw_new,
 };
@@ -2337,6 +2358,7 @@ nv137_chipset = {
 static const struct nvkm_device_chip
 nv138_chipset = {
 	.name = "GP108",
+	.acr = gp108_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2352,7 +2374,6 @@ nv138_chipset = {
 	.mc = gp100_mc_new,
 	.mmu = gp100_mmu_new,
 	.therm = gp100_therm_new,
-	.secboot = gp108_secboot_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
 	.timer = gk20a_timer_new,
@@ -2364,30 +2385,30 @@ nv138_chipset = {
 	.disp = gp102_disp_new,
 	.dma = gf119_dma_new,
 	.fifo = gp100_fifo_new,
-	.gr = gp107_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
-	.sec2 = gp102_sec2_new,
+	.gr = gp108_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.sec2 = gp108_sec2_new,
 	.sw = gf100_sw_new,
 };
 
 static const struct nvkm_device_chip
 nv13b_chipset = {
 	.name = "GP10B",
+	.acr = gp10b_acr_new,
 	.bar = gm20b_bar_new,
 	.bus = gf100_bus_new,
-	.fault = gp100_fault_new,
+	.fault = gp10b_fault_new,
 	.fb = gp10b_fb_new,
 	.fuse = gm107_fuse_new,
 	.ibus = gp10b_ibus_new,
 	.imem = gk20a_instmem_new,
-	.ltc = gp102_ltc_new,
+	.ltc = gp10b_ltc_new,
 	.mc = gp10b_mc_new,
 	.mmu = gp10b_mmu_new,
-	.secboot = gp10b_secboot_new,
-	.pmu = gm20b_pmu_new,
+	.pmu = gp10b_pmu_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
-	.ce[2] = gp102_ce_new,
+	.ce[0] = gp100_ce_new,
 	.dma = gf119_dma_new,
 	.fifo = gp10b_fifo_new,
 	.gr = gp10b_gr_new,
@@ -2397,6 +2418,7 @@ nv13b_chipset = {
 static const struct nvkm_device_chip
 nv140_chipset = {
 	.name = "GV100",
+	.acr = gp108_acr_new,
 	.bar = gm107_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2414,7 +2436,6 @@ nv140_chipset = {
 	.mmu = gv100_mmu_new,
 	.pci = gp100_pci_new,
 	.pmu = gp102_pmu_new,
-	.secboot = gp108_secboot_new,
 	.therm = gp100_therm_new,
 	.timer = gk20a_timer_new,
 	.top = gk104_top_new,
@@ -2431,13 +2452,17 @@ nv140_chipset = {
 	.dma = gv100_dma_new,
 	.fifo = gv100_fifo_new,
 	.gr = gv100_gr_new,
-	.nvdec[0] = gp102_nvdec_new,
-	.sec2 = gp102_sec2_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
+	.nvenc[1] = gm107_nvenc_new,
+	.nvenc[2] = gm107_nvenc_new,
+	.sec2 = gp108_sec2_new,
 };
 
 static const struct nvkm_device_chip
 nv162_chipset = {
 	.name = "TU102",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2466,13 +2491,16 @@ nv162_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.gr = tu102_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
 static const struct nvkm_device_chip
 nv164_chipset = {
 	.name = "TU104",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2501,13 +2529,17 @@ nv164_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.gr = tu102_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvdec[1] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
 static const struct nvkm_device_chip
 nv166_chipset = {
 	.name = "TU106",
+	.acr = tu102_acr_new,
 	.bar = tu102_bar_new,
 	.bios = nvkm_bios_new,
 	.bus = gf100_bus_new,
@@ -2536,7 +2568,11 @@ nv166_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.gr = tu102_gr_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvdec[1] = gm107_nvdec_new,
+	.nvdec[2] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
@@ -2571,7 +2607,8 @@ nv167_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
@@ -2606,7 +2643,8 @@ nv168_chipset = {
 	.disp = tu102_disp_new,
 	.dma = gv100_dma_new,
 	.fifo = tu102_fifo_new,
-	.nvdec[0] = gp102_nvdec_new,
+	.nvdec[0] = gm107_nvdec_new,
+	.nvenc[0] = gm107_nvenc_new,
 	.sec2 = tu102_sec2_new,
 };
 
@@ -2638,6 +2676,7 @@ nvkm_device_subdev(struct nvkm_device *device, int index)
 
 	switch (index) {
 #define _(n,p,m) case NVKM_SUBDEV_##n: if (p) return (m); break
+	_(ACR     , device->acr     , &device->acr->subdev);
 	_(BAR     , device->bar     , &device->bar->subdev);
 	_(VBIOS   , device->bios    , &device->bios->subdev);
 	_(BUS     , device->bus     , &device->bus->subdev);
@@ -2658,7 +2697,6 @@ nvkm_device_subdev(struct nvkm_device *device, int index)
 	_(MXM     , device->mxm     ,  device->mxm);
 	_(PCI     , device->pci     , &device->pci->subdev);
 	_(PMU     , device->pmu     , &device->pmu->subdev);
-	_(SECBOOT , device->secboot , &device->secboot->subdev);
 	_(THERM   , device->therm   , &device->therm->subdev);
 	_(TIMER   , device->timer   , &device->timer->subdev);
 	_(TOP     , device->top     , &device->top->subdev);
@@ -2703,9 +2741,9 @@ nvkm_device_engine(struct nvkm_device *device, int index)
 	_(MSPDEC , device->mspdec  ,  device->mspdec);
 	_(MSPPP  , device->msppp   ,  device->msppp);
 	_(MSVLD  , device->msvld   ,  device->msvld);
-	_(NVENC0 , device->nvenc[0],  device->nvenc[0]);
-	_(NVENC1 , device->nvenc[1],  device->nvenc[1]);
-	_(NVENC2 , device->nvenc[2],  device->nvenc[2]);
+	_(NVENC0 , device->nvenc[0], &device->nvenc[0]->engine);
+	_(NVENC1 , device->nvenc[1], &device->nvenc[1]->engine);
+	_(NVENC2 , device->nvenc[2], &device->nvenc[2]->engine);
 	_(NVDEC0 , device->nvdec[0], &device->nvdec[0]->engine);
 	_(NVDEC1 , device->nvdec[1], &device->nvdec[1]->engine);
 	_(NVDEC2 , device->nvdec[2], &device->nvdec[2]->engine);
@@ -3144,6 +3182,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	}                                                                      \
 	break
 		switch (i) {
+		_(NVKM_SUBDEV_ACR     ,      acr);
 		_(NVKM_SUBDEV_BAR     ,      bar);
 		_(NVKM_SUBDEV_VBIOS   ,     bios);
 		_(NVKM_SUBDEV_BUS     ,      bus);
@@ -3164,7 +3203,6 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 		_(NVKM_SUBDEV_MXM     ,      mxm);
 		_(NVKM_SUBDEV_PCI     ,      pci);
 		_(NVKM_SUBDEV_PMU     ,      pmu);
-		_(NVKM_SUBDEV_SECBOOT ,  secboot);
 		_(NVKM_SUBDEV_THERM   ,    therm);
 		_(NVKM_SUBDEV_TIMER   ,    timer);
 		_(NVKM_SUBDEV_TOP     ,      top);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
index d8be2f77ac66..54eab5e04230 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/priv.h
@@ -3,6 +3,7 @@
 #define __NVKM_DEVICE_PRIV_H__
 #include <core/device.h>
 
+#include <subdev/acr.h>
 #include <subdev/bar.h>
 #include <subdev/bios.h>
 #include <subdev/bus.h>
@@ -27,7 +28,6 @@
 #include <subdev/timer.h>
 #include <subdev/top.h>
 #include <subdev/volt.h>
-#include <subdev/secboot.h>
 
 #include <engine/bsp.h>
 #include <engine/ce.h>
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 0e372a190d3f..d0d52c1d4aee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -52,18 +52,18 @@ nvkm_device_tegra_power_up(struct nvkm_device_tegra *tdev)
 	clk_set_rate(tdev->clk_pwr, 204000000);
 	udelay(10);
 
-	reset_control_assert(tdev->rst);
-	udelay(10);
-
 	if (!tdev->pdev->dev.pm_domain) {
+		reset_control_assert(tdev->rst);
+		udelay(10);
+
 		ret = tegra_powergate_remove_clamping(TEGRA_POWERGATE_3D);
 		if (ret)
 			goto err_clamp;
 		udelay(10);
-	}
 
-	reset_control_deassert(tdev->rst);
-	udelay(10);
+		reset_control_deassert(tdev->rst);
+		udelay(10);
+	}
 
 	return 0;
 
@@ -279,6 +279,7 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 		      struct nvkm_device **pdevice)
 {
 	struct nvkm_device_tegra *tdev;
+	unsigned long rate;
 	int ret;
 
 	if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL)))
@@ -307,6 +308,17 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func,
 		goto free;
 	}
 
+	rate = clk_get_rate(tdev->clk);
+	if (rate == 0) {
+		ret = clk_set_rate(tdev->clk, ULONG_MAX);
+		if (ret < 0)
+			goto free;
+
+		rate = clk_get_rate(tdev->clk);
+
+		dev_dbg(&pdev->dev, "GPU clock set to %lu\n", rate);
+	}
+
 	if (func->require_ref_clk)
 		tdev->clk_ref = devm_clk_get(&pdev->dev, "ref");
 	if (IS_ERR(tdev->clk_ref)) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index bcf32d92ee5a..50e3539f33d2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -74,6 +74,8 @@ nv50_disp_chan_mthd(struct nv50_disp_chan *chan, int debug)
 
 	if (debug > subdev->debug)
 		return;
+	if (!mthd)
+		return;
 
 	for (i = 0; (list = mthd->data[i].mthd) != NULL; i++) {
 		u32 base = chan->head * mthd->addr;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 818d21bd28d3..3800aeb507d0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -365,7 +365,7 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps)
 	 * and it's better to have a failed modeset than that.
 	 */
 	for (cfg = nvkm_dp_rates; cfg->rate; cfg++) {
-		if (cfg->nr <= outp_nr && cfg->nr <= outp_bw) {
+		if (cfg->nr <= outp_nr && cfg->bw <= outp_bw) {
 			/* Try to respect sink limits too when selecting
 			 * lowest link configuration.
 			 */
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
index 892be6c9b76c..3aa2cc3af1e2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gv100.c
@@ -101,15 +101,26 @@ gv100_disp_exception(struct nv50_disp *disp, int chid)
 	u32 stat = nvkm_rd32(device, 0x611020 + (chid * 12));
 	u32 type = (stat & 0x00007000) >> 12;
 	u32 mthd = (stat & 0x00000fff) << 2;
-	u32 data = nvkm_rd32(device, 0x611024 + (chid * 12));
-	u32 code = nvkm_rd32(device, 0x611028 + (chid * 12));
 	const struct nvkm_enum *reason =
 		nvkm_enum_find(nv50_disp_intr_error_type, type);
 
-	nvkm_error(subdev, "chid %d stat %08x reason %d [%s] mthd %04x "
-			   "data %08x code %08x\n",
-		   chid, stat, type, reason ? reason->name : "",
-		   mthd, data, code);
+	/*TODO: Suspect 33->41 are for WRBK channel exceptions, but we
+	 *      don't support those currently.
+	 *
+	 *      CORE+WIN CHIDs map directly to the FE_EXCEPT() slots.
+	 */
+	if (chid <= 32) {
+		u32 data = nvkm_rd32(device, 0x611024 + (chid * 12));
+		u32 code = nvkm_rd32(device, 0x611028 + (chid * 12));
+		nvkm_error(subdev, "chid %d stat %08x reason %d [%s] "
+				   "mthd %04x data %08x code %08x\n",
+			   chid, stat, type, reason ? reason->name : "",
+			   mthd, data, code);
+	} else {
+		nvkm_error(subdev, "chid %d stat %08x reason %d [%s] "
+				   "mthd %04x\n",
+			   chid, stat, type, reason ? reason->name : "", mthd);
+	}
 
 	if (chid < ARRAY_SIZE(disp->chan) && disp->chan[chid]) {
 		switch (mthd) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
index 73724a8cb861..558c86fd8e82 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/Kbuild
@@ -36,8 +36,10 @@ nvkm-y += nvkm/engine/gr/gp100.o
 nvkm-y += nvkm/engine/gr/gp102.o
 nvkm-y += nvkm/engine/gr/gp104.o
 nvkm-y += nvkm/engine/gr/gp107.o
+nvkm-y += nvkm/engine/gr/gp108.o
 nvkm-y += nvkm/engine/gr/gp10b.o
 nvkm-y += nvkm/engine/gr/gv100.o
+nvkm-y += nvkm/engine/gr/tu102.o
 
 nvkm-y += nvkm/engine/gr/ctxnv40.o
 nvkm-y += nvkm/engine/gr/ctxnv50.o
@@ -60,3 +62,4 @@ nvkm-y += nvkm/engine/gr/ctxgp102.o
 nvkm-y += nvkm/engine/gr/ctxgp104.o
 nvkm-y += nvkm/engine/gr/ctxgp107.o
 nvkm-y += nvkm/engine/gr/ctxgv100.o
+nvkm-y += nvkm/engine/gr/ctxtu102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
index 85f2d1e950e8..297915719bf2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.c
@@ -1324,10 +1324,8 @@ gf100_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
 void
 gf100_grctx_generate_floorsweep(struct gf100_gr *gr)
 {
-	struct nvkm_device *device = gr->base.engine.subdev.device;
 	const struct gf100_grctx_func *func = gr->func->grctx;
-	int gpc, sm, i, j;
-	u32 data;
+	int sm;
 
 	for (sm = 0; sm < gr->sm_nr; sm++) {
 		func->sm_id(gr, gr->sm[sm].gpc, gr->sm[sm].tpc, sm);
@@ -1335,12 +1333,9 @@ gf100_grctx_generate_floorsweep(struct gf100_gr *gr)
 			func->tpc_nr(gr, gr->sm[sm].gpc);
 	}
 
-	for (gpc = 0, i = 0; i < 4; i++) {
-		for (data = 0, j = 0; j < 8 && gpc < gr->gpc_nr; j++, gpc++)
-			data |= gr->tpc_nr[gpc] << (j * 4);
-		nvkm_wr32(device, 0x406028 + (i * 4), data);
-		nvkm_wr32(device, 0x405870 + (i * 4), data);
-	}
+	gf100_gr_init_num_tpc_per_gpc(gr, false, true);
+	if (!func->skip_pd_num_tpc_per_gpc)
+		gf100_gr_init_num_tpc_per_gpc(gr, true, false);
 
 	if (func->r4060a8)
 		func->r4060a8(gr);
@@ -1374,7 +1369,7 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	nvkm_mc_unk260(device, 0);
 
-	if (!gr->fuc_sw_ctx) {
+	if (!gr->sw_ctx) {
 		gf100_gr_mmio(gr, grctx->hub);
 		gf100_gr_mmio(gr, grctx->gpc_0);
 		gf100_gr_mmio(gr, grctx->zcull);
@@ -1382,7 +1377,7 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 		gf100_gr_mmio(gr, grctx->tpc);
 		gf100_gr_mmio(gr, grctx->ppc);
 	} else {
-		gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+		gf100_gr_mmio(gr, gr->sw_ctx);
 	}
 
 	gf100_gr_wait_idle(gr);
@@ -1401,8 +1396,8 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	gf100_gr_wait_idle(gr);
 
 	if (grctx->r400088) grctx->r400088(gr, false);
-	if (gr->fuc_bundle)
-		gf100_gr_icmd(gr, gr->fuc_bundle);
+	if (gr->bundle)
+		gf100_gr_icmd(gr, gr->bundle);
 	else
 		gf100_gr_icmd(gr, grctx->icmd);
 	if (grctx->sw_veid_bundle_init)
@@ -1411,8 +1406,8 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 
 	nvkm_wr32(device, 0x404154, idle_timeout);
 
-	if (gr->fuc_method)
-		gf100_gr_mthd(gr, gr->fuc_method);
+	if (gr->method)
+		gf100_gr_mthd(gr, gr->method);
 	else
 		gf100_gr_mthd(gr, grctx->mthd);
 	nvkm_mc_unk260(device, 1);
@@ -1431,6 +1426,8 @@ gf100_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 		grctx->r419a3c(gr);
 	if (grctx->r408840)
 		grctx->r408840(gr);
+	if (grctx->r419c0c)
+		grctx->r419c0c(gr);
 }
 
 #define CB_RESERVED 0x80000
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
index 478b4723d0f9..32bbddc0993e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgf100.h
@@ -57,6 +57,7 @@ struct gf100_grctx_func {
 	/* floorsweeping */
 	void (*sm_id)(struct gf100_gr *, int gpc, int tpc, int sm);
 	void (*tpc_nr)(struct gf100_gr *, int gpc);
+	bool skip_pd_num_tpc_per_gpc;
 	void (*r4060a8)(struct gf100_gr *);
 	void (*rop_mapping)(struct gf100_gr *);
 	void (*alpha_beta_tables)(struct gf100_gr *);
@@ -76,6 +77,7 @@ struct gf100_grctx_func {
 	void (*r418e94)(struct gf100_gr *);
 	void (*r419a3c)(struct gf100_gr *);
 	void (*r408840)(struct gf100_gr *);
+	void (*r419c0c)(struct gf100_gr *);
 };
 
 extern const struct gf100_grctx_func gf100_grctx;
@@ -153,6 +155,14 @@ extern const struct gf100_grctx_func gp107_grctx;
 
 extern const struct gf100_grctx_func gv100_grctx;
 
+extern const struct gf100_grctx_func tu102_grctx;
+void gv100_grctx_unkn88c(struct gf100_gr *, bool);
+void gv100_grctx_generate_unkn(struct gf100_gr *);
+extern const struct gf100_gr_init gv100_grctx_init_sw_veid_bundle_init_0[];
+void gv100_grctx_generate_attrib(struct gf100_grctx *);
+void gv100_grctx_generate_rop_mapping(struct gf100_gr *);
+void gv100_grctx_generate_r400088(struct gf100_gr *, bool);
+
 /* context init value lists */
 
 extern const struct gf100_gr_pack gf100_grctx_pack_icmd[];
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
index 896d473dcc0f..c0d36bc601f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgk20a.c
@@ -32,7 +32,7 @@ gk20a_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	u32 idle_timeout;
 	int i;
 
-	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+	gf100_gr_mmio(gr, gr->sw_ctx);
 
 	gf100_gr_wait_idle(gr);
 
@@ -56,10 +56,10 @@ gk20a_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_mthd(gr, gr->fuc_method);
+	gf100_gr_mthd(gr, gr->method);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_icmd(gr, gr->fuc_bundle);
+	gf100_gr_icmd(gr, gr->bundle);
 	grctx->pagepool(info);
 	grctx->bundle(info);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
index a1d9e114ebeb..6b92f8aa18a3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgm20b.c
@@ -29,7 +29,7 @@ gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	u32 idle_timeout;
 	int i, tmp;
 
-	gf100_gr_mmio(gr, gr->fuc_sw_ctx);
+	gf100_gr_mmio(gr, gr->sw_ctx);
 
 	gf100_gr_wait_idle(gr);
 
@@ -59,10 +59,10 @@ gm20b_grctx_generate_main(struct gf100_gr *gr, struct gf100_grctx *info)
 	nvkm_wr32(device, 0x404154, idle_timeout);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_mthd(gr, gr->fuc_method);
+	gf100_gr_mthd(gr, gr->method);
 	gf100_gr_wait_idle(gr);
 
-	gf100_gr_icmd(gr, gr->fuc_bundle);
+	gf100_gr_icmd(gr, gr->bundle);
 	grctx->pagepool(info);
 	grctx->bundle(info);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
index 0990765ef191..39553d55d3f3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxgv100.c
@@ -25,7 +25,7 @@
  * PGRAPH context implementation
  ******************************************************************************/
 
-static const struct gf100_gr_init
+const struct gf100_gr_init
 gv100_grctx_init_sw_veid_bundle_init_0[] = {
 	{ 0x00001000, 64, 0x00100000, 0x00000008 },
 	{ 0x00000941, 64, 0x00100000, 0x00000000 },
@@ -58,7 +58,7 @@ gv100_grctx_pack_sw_veid_bundle_init[] = {
 	{}
 };
 
-static void
+void
 gv100_grctx_generate_attrib(struct gf100_grctx *info)
 {
 	struct gf100_gr *gr = info->gr;
@@ -67,14 +67,14 @@ gv100_grctx_generate_attrib(struct gf100_grctx *info)
 	const u32 attrib = grctx->attrib_nr;
 	const u32   gfxp = grctx->gfxp_nr;
 	const int s = 12;
-	const int max_batches = 0xffff;
 	u32 size = grctx->alpha_nr_max * gr->tpc_total;
 	u32 ao = 0;
 	u32 bo = ao + size;
 	int gpc, ppc, b, n = 0;
 
-	size += grctx->gfxp_nr * gr->tpc_total;
-	size = ((size * 0x20) + 128) & ~127;
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++)
+		size += grctx->gfxp_nr * gr->ppc_nr[gpc] * gr->ppc_tpc_max;
+	size = ((size * 0x20) + 127) & ~127;
 	b = mmio_vram(info, size, (1 << s), false);
 
 	mmio_refn(info, 0x418810, 0x80000000, s, b);
@@ -84,13 +84,12 @@ gv100_grctx_generate_attrib(struct gf100_grctx *info)
 	mmio_wr32(info, 0x419e04, 0x80000000 | size >> 7);
 	mmio_wr32(info, 0x405830, attrib);
 	mmio_wr32(info, 0x40585c, alpha);
-	mmio_wr32(info, 0x4064c4, ((alpha / 4) << 16) | max_batches);
 
 	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
 		for (ppc = 0; ppc < gr->ppc_nr[gpc]; ppc++, n++) {
 			const u32 as =  alpha * gr->ppc_tpc_nr[gpc][ppc];
-			const u32 bs = attrib * gr->ppc_tpc_nr[gpc][ppc];
-			const u32 gs =   gfxp * gr->ppc_tpc_nr[gpc][ppc];
+			const u32 bs = attrib * gr->ppc_tpc_max;
+			const u32 gs =   gfxp * gr->ppc_tpc_max;
 			const u32 u = 0x418ea0 + (n * 0x04);
 			const u32 o = PPC_UNIT(gpc, ppc, 0);
 			if (!(gr->ppc_mask[gpc] & (1 << ppc)))
@@ -110,7 +109,7 @@ gv100_grctx_generate_attrib(struct gf100_grctx *info)
 	mmio_wr32(info, 0x41befc, 0x00000100);
 }
 
-static void
+void
 gv100_grctx_generate_rop_mapping(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -147,7 +146,7 @@ gv100_grctx_generate_rop_mapping(struct gf100_gr *gr)
 				     gr->screen_tile_row_offset);
 }
 
-static void
+void
 gv100_grctx_generate_r400088(struct gf100_gr *gr, bool on)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -163,7 +162,7 @@ gv100_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
 	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
 }
 
-static void
+void
 gv100_grctx_generate_unkn(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -174,7 +173,7 @@ gv100_grctx_generate_unkn(struct gf100_gr *gr)
 	nvkm_mask(device, 0x419c00, 0x00000008, 0x00000008);
 }
 
-static void
+void
 gv100_grctx_unkn88c(struct gf100_gr *gr, bool on)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxtu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxtu102.c
new file mode 100644
index 000000000000..2299ca07d04a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/ctxtu102.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ctxgf100.h"
+
+static void
+tu102_grctx_generate_r419c0c(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_mask(device, 0x419c0c, 0x80000000, 0x80000000);
+	nvkm_mask(device, 0x40584c, 0x00000008, 0x00000000);
+	nvkm_mask(device, 0x400080, 0x00000000, 0x00000000);
+}
+
+static void
+tu102_grctx_generate_sm_id(struct gf100_gr *gr, int gpc, int tpc, int sm)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x608), sm);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x088), sm);
+}
+
+static const struct gf100_gr_init
+tu102_grctx_init_unknown_bundle_init_0[] = {
+	{ 0x00001000,  1, 0x00000001, 0x00000004 },
+	{ 0x00002020, 64, 0x00000001, 0x00000000 },
+	{ 0x0001e100,  1, 0x00000001, 0x00000001 },
+	{}
+};
+
+static const struct gf100_gr_pack
+tu102_grctx_pack_sw_veid_bundle_init[] = {
+	{ gv100_grctx_init_sw_veid_bundle_init_0 },
+	{ tu102_grctx_init_unknown_bundle_init_0 },
+	{}
+};
+
+static void
+tu102_grctx_generate_attrib(struct gf100_grctx *info)
+{
+	const u64 size = 0x80000; /*XXX: educated guess */
+	const int s = 8;
+	const int b = mmio_vram(info, size, (1 << s), true);
+
+	gv100_grctx_generate_attrib(info);
+
+	mmio_refn(info, 0x408070, 0x00000000, s, b);
+	mmio_wr32(info, 0x408074, size >> s); /*XXX: guess */
+	mmio_refn(info, 0x419034, 0x00000000, s, b);
+	mmio_wr32(info, 0x408078, 0x00000000);
+}
+
+const struct gf100_grctx_func
+tu102_grctx = {
+	.unkn88c = gv100_grctx_unkn88c,
+	.main = gf100_grctx_generate_main,
+	.unkn = gv100_grctx_generate_unkn,
+	.sw_veid_bundle_init = tu102_grctx_pack_sw_veid_bundle_init,
+	.bundle = gm107_grctx_generate_bundle,
+	.bundle_size = 0x3000,
+	.bundle_min_gpm_fifo_depth = 0x180,
+	.bundle_token_limit = 0xa80,
+	.pagepool = gp100_grctx_generate_pagepool,
+	.pagepool_size = 0x20000,
+	.attrib = tu102_grctx_generate_attrib,
+	.attrib_nr_max = 0x800,
+	.attrib_nr = 0x700,
+	.alpha_nr_max = 0xc00,
+	.alpha_nr = 0x800,
+	.gfxp_nr = 0xfa8,
+	.sm_id = tu102_grctx_generate_sm_id,
+	.skip_pd_num_tpc_per_gpc = true,
+	.rop_mapping = gv100_grctx_generate_rop_mapping,
+	.r406500 = gm200_grctx_generate_r406500,
+	.r400088 = gv100_grctx_generate_r400088,
+	.r419c0c = tu102_grctx_generate_r419c0c,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h
index c24f35ad56a6..ae2d5b6891cb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgk208.fuc5.h
@@ -441,7 +441,7 @@ static uint32_t gk208_grhub_code[] = {
 	0x020014fe,
 	0x12004002,
 	0xbd0002f6,
-	0x05c94104,
+	0x05ca4104,
 	0xbd0010fe,
 	0x07004024,
 	0xbd0002f6,
@@ -460,423 +460,423 @@ static uint32_t gk208_grhub_code[] = {
 	0x01039204,
 	0x03090080,
 	0xbd0003f6,
-	0x87044204,
-	0xf6040040,
-	0x04bd0002,
-	0x00400402,
-	0x0002f603,
-	0x31f404bd,
-	0x96048e10,
-	0x00657e40,
-	0xc7feb200,
-	0x01b590f1,
-	0x1ff4f003,
-	0x01020fb5,
-	0x041fbb01,
-	0x800112b6,
-	0xf6010300,
-	0x04bd0001,
-	0x01040080,
+	0x87048204,
+	0x04004000,
+	0xbd0002f6,
+	0x40040204,
+	0x02f60300,
+	0xf404bd00,
+	0x048e1031,
+	0x657e4096,
+	0xfeb20000,
+	0xb590f1c7,
+	0xf4f00301,
+	0x020fb51f,
+	0x1fbb0101,
+	0x0112b604,
+	0x01030080,
 	0xbd0001f6,
-	0x01004104,
-	0xac7e020f,
-	0xbb7e0006,
-	0x100f0006,
-	0x0006fd7e,
-	0x98000e98,
-	0x207e010f,
-	0x14950001,
-	0xc0008008,
-	0x0004f601,
-	0x008004bd,
-	0x04f601c1,
-	0xb704bd00,
-	0xbb130030,
-	0xf5b6001f,
-	0xd3008002,
-	0x000ff601,
-	0x15b604bd,
-	0x0110b608,
-	0xb20814b6,
-	0x02687e1f,
-	0x001fbb00,
-	0x84020398,
-/* 0x041f: init_gpc */
-	0xb8502000,
-	0x0008044e,
-	0x8f7e1fb2,
+	0x04008004,
+	0x0001f601,
+	0x004104bd,
+	0x7e020f01,
+	0x7e0006ad,
+	0x0f0006bc,
+	0x06fe7e10,
+	0x000e9800,
+	0x7e010f98,
+	0x95000120,
+	0x00800814,
+	0x04f601c0,
+	0x8004bd00,
+	0xf601c100,
+	0x04bd0004,
+	0x130030b7,
+	0xb6001fbb,
+	0x008002f5,
+	0x0ff601d3,
+	0xb604bd00,
+	0x10b60815,
+	0x0814b601,
+	0x687e1fb2,
+	0x1fbb0002,
+	0x02039800,
+	0x50200084,
+/* 0x0420: init_gpc */
+	0x08044eb8,
+	0x7e1fb200,
+	0xb800008f,
+	0x00010c4e,
+	0x8f7ef4bd,
 	0x4eb80000,
-	0xbd00010c,
-	0x008f7ef4,
-	0x044eb800,
-	0x8f7e0001,
+	0x7e000104,
+	0xb800008f,
+	0x0001004e,
+	0x8f7e020f,
 	0x4eb80000,
-	0x0f000100,
-	0x008f7e02,
-	0x004eb800,
-/* 0x044e: init_gpc_wait */
+/* 0x044f: init_gpc_wait */
+	0x7e000800,
+	0xc8000065,
+	0x0bf41fff,
+	0x044eb8f9,
 	0x657e0008,
-	0xffc80000,
-	0xf90bf41f,
-	0x08044eb8,
-	0x00657e00,
-	0x001fbb00,
-	0x800040b7,
-	0xf40132b6,
-	0x000fb41b,
-	0x0006fd7e,
-	0xac7e000f,
-	0x00800006,
-	0x01f60201,
-	0xbd04bd00,
-	0x1f19f014,
-	0x02300080,
-	0xbd0001f6,
-/* 0x0491: wait */
-	0x0028f404,
-/* 0x0497: main */
-	0x0d0031f4,
-	0x00377e10,
-	0xf401f400,
-	0x4001e4b1,
-	0x00c71bf5,
-	0x99f094bd,
-	0x37008004,
-	0x0009f602,
-	0x008104bd,
-	0x11cf02c0,
-	0xc1008200,
-	0x0022cf02,
-	0xf41f13c8,
-	0x23c8770b,
-	0x550bf41f,
-	0x12b220f9,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0231f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x20fc04bd,
-	0x99f094bd,
-	0x37008006,
-	0x0009f602,
-	0x31f404bd,
-	0x08807e01,
+	0x1fbb0000,
+	0x0040b700,
+	0x0132b680,
+	0x0fb41bf4,
+	0x06fe7e00,
+	0x7e000f00,
+	0x800006ad,
+	0xf6020100,
+	0x04bd0001,
+	0x19f014bd,
+	0x3000801f,
+	0x0001f602,
+/* 0x0492: wait */
+	0x28f404bd,
+	0x0031f400,
+/* 0x0498: main */
+	0x377e100d,
+	0x01f40000,
+	0x01e4b1f4,
+	0xc71bf540,
 	0xf094bd00,
-	0x00800699,
+	0x00800499,
+	0x09f60237,
+	0x8104bd00,
+	0xcf02c000,
+	0x00820011,
+	0x22cf02c1,
+	0x1f13c800,
+	0xc8770bf4,
+	0x0bf41f23,
+	0xb220f955,
+	0xf094bd12,
+	0x00800799,
+	0x09f60237,
+	0xf404bd00,
+	0x31f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
+	0xfc04bd00,
+	0xf094bd20,
+	0x00800699,
+	0x09f60237,
 	0xf404bd00,
-/* 0x0522: chsw_prev_no_next */
-	0x20f92f0e,
-	0x32f412b2,
-	0x0232f401,
-	0x0008807e,
-	0x008020fc,
-	0x02f602c0,
+	0x817e0131,
+	0x94bd0008,
+	0x800699f0,
+	0xf6021700,
+	0x04bd0009,
+/* 0x0523: chsw_prev_no_next */
+	0xf92f0ef4,
+	0xf412b220,
+	0x32f40132,
+	0x08817e02,
+	0x8020fc00,
+	0xf602c000,
+	0x04bd0002,
+/* 0x053f: chsw_no_prev */
+	0xc8130ef4,
+	0x0bf41f23,
+	0x0131f40d,
+	0x7e0232f4,
+/* 0x054f: chsw_done */
+	0x02000881,
+	0xc3008001,
+	0x0002f602,
+	0x94bd04bd,
+	0x800499f0,
+	0xf6021700,
+	0x04bd0009,
+	0xff300ef5,
+/* 0x056c: main_not_ctx_switch */
+	0xf401e4b0,
+	0xf2b20c1b,
+	0x0008217e,
+/* 0x057b: main_not_ctx_chan */
+	0xb0400ef4,
+	0x1bf402e4,
+	0xf094bd2c,
+	0x00800799,
+	0x09f60237,
 	0xf404bd00,
-/* 0x053e: chsw_no_prev */
-	0x23c8130e,
-	0x0d0bf41f,
-	0xf40131f4,
-	0x807e0232,
-/* 0x054e: chsw_done */
-	0x01020008,
-	0x02c30080,
-	0xbd0002f6,
-	0xf094bd04,
-	0x00800499,
+	0x32f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
-	0xf504bd00,
-/* 0x056b: main_not_ctx_switch */
-	0xb0ff300e,
-	0x1bf401e4,
-	0x7ef2b20c,
-	0xf4000820,
-/* 0x057a: main_not_ctx_chan */
-	0xe4b0400e,
-	0x2c1bf402,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0232f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x0ef404bd,
-/* 0x05a9: main_not_ctx_save */
-	0x10ef9411,
-	0x7e01f5f0,
-	0xf50002f8,
-/* 0x05b7: main_done */
-	0xbdfee40e,
-	0x1f29f024,
-	0x02300080,
-	0xbd0002f6,
-	0xd20ef504,
-/* 0x05c9: ih */
-	0xf900f9fe,
-	0x0188fe80,
-	0x90f980f9,
-	0xb0f9a0f9,
-	0xe0f9d0f9,
-	0x04bdf0f9,
-	0xcf02004a,
-	0xabc400aa,
-	0x230bf404,
-	0x004e100d,
-	0x00eecf1a,
-	0xcf19004f,
-	0x047e00ff,
-	0xb0b70000,
-	0x010e0400,
-	0xf61d0040,
-	0x04bd000e,
-/* 0x060c: ih_no_fifo */
-	0x0100abe4,
-	0x0d0c0bf4,
-	0x40014e10,
-	0x0000047e,
-/* 0x061c: ih_no_ctxsw */
-	0x0400abe4,
-	0x8e560bf4,
-	0x7e400708,
+	0xf404bd00,
+/* 0x05aa: main_not_ctx_save */
+	0xef94110e,
+	0x01f5f010,
+	0x0002f87e,
+	0xfee40ef5,
+/* 0x05b8: main_done */
+	0x29f024bd,
+	0x3000801f,
+	0x0002f602,
+	0x0ef504bd,
+/* 0x05ca: ih */
+	0x00f9fed2,
+	0x88fe80f9,
+	0xf980f901,
+	0xf9a0f990,
+	0xf9d0f9b0,
+	0xbdf0f9e0,
+	0x02004a04,
+	0xc400aacf,
+	0x0bf404ab,
+	0x4e100d23,
+	0xeecf1a00,
+	0x19004f00,
+	0x7e00ffcf,
+	0xb7000004,
+	0x0e0400b0,
+	0x1d004001,
+	0xbd000ef6,
+/* 0x060d: ih_no_fifo */
+	0x00abe404,
+	0x0c0bf401,
+	0x014e100d,
+	0x00047e40,
+/* 0x061d: ih_no_ctxsw */
+	0x00abe400,
+	0x560bf404,
+	0x4007088e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60204,
+	0x8e04bd00,
+	0x7e400704,
 	0xb2000065,
-	0x040080ff,
+	0x030080ff,
 	0x000ff602,
-	0x048e04bd,
-	0x657e4007,
-	0xffb20000,
-	0x02030080,
-	0xbd000ff6,
-	0x50fec704,
-	0x8f02ee94,
-	0xbb400700,
-	0x657e00ef,
-	0x00800000,
-	0x0ff60202,
+	0xfec704bd,
+	0x02ee9450,
+	0x4007008f,
+	0x7e00efbb,
+	0x80000065,
+	0xf6020200,
+	0x04bd000f,
+	0xf87e030f,
+	0x004b0002,
+	0x8ebfb201,
+	0x7e400144,
+/* 0x0677: ih_no_fwmthd */
+	0x4b00008f,
+	0xb0bd0504,
+	0xf4b4abff,
+	0x00800c0b,
+	0x0bf60307,
+/* 0x068b: ih_no_other */
+	0x4004bd00,
+	0x0af60100,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x00fc80fc,
+	0xf80032f4,
+/* 0x06ad: ctx_4170s */
+	0x10f5f001,
+	0x708effb2,
+	0x8f7e4041,
+	0x00f80000,
+/* 0x06bc: ctx_4170w */
+	0x4041708e,
+	0x0000657e,
+	0xf4f0ffb2,
+	0xf31bf410,
+/* 0x06ce: ctx_redswitch */
+	0x004e00f8,
+	0x40e5f002,
+	0xf020e5f0,
+	0x008010e5,
+	0x0ef60185,
 	0x0f04bd00,
-	0x02f87e03,
-	0x01004b00,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x0676: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd05,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x068a: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0xf400fc80,
-	0x01f80032,
-/* 0x06ac: ctx_4170s */
-	0xb210f5f0,
-	0x41708eff,
+/* 0x06e5: ctx_redswitch_delay */
+	0x01f2b608,
+	0xf1fd1bf4,
+	0xf10400e5,
+	0x800100e5,
+	0xf6018500,
+	0x04bd000e,
+/* 0x06fe: ctx_86c */
+	0x008000f8,
+	0x0ff60223,
+	0xb204bd00,
+	0x8a148eff,
 	0x008f7e40,
-/* 0x06bb: ctx_4170w */
-	0x8e00f800,
-	0x7e404170,
-	0xb2000065,
-	0x10f4f0ff,
-	0xf8f31bf4,
-/* 0x06cd: ctx_redswitch */
-	0x02004e00,
-	0xf040e5f0,
-	0xe5f020e5,
-	0x85008010,
-	0x000ef601,
-	0x080f04bd,
-/* 0x06e4: ctx_redswitch_delay */
-	0xf401f2b6,
-	0xe5f1fd1b,
-	0xe5f10400,
-	0x00800100,
-	0x0ef60185,
-	0xf804bd00,
-/* 0x06fd: ctx_86c */
-	0x23008000,
+	0x8effb200,
+	0x7e41a88c,
+	0xf800008f,
+/* 0x071d: ctx_mem */
+	0x84008000,
 	0x000ff602,
-	0xffb204bd,
-	0x408a148e,
-	0x00008f7e,
-	0x8c8effb2,
-	0x8f7e41a8,
-	0x00f80000,
-/* 0x071c: ctx_mem */
-	0x02840080,
-	0xbd000ff6,
-/* 0x0725: ctx_mem_wait */
-	0x84008f04,
-	0x00ffcf02,
-	0xf405fffd,
-	0x00f8f61b,
-/* 0x0734: ctx_load */
-	0x99f094bd,
-	0x37008005,
-	0x0009f602,
-	0x0c0a04bd,
-	0x0000b87e,
-	0x0080f4bd,
-	0x0ff60289,
-	0x8004bd00,
-	0xf602c100,
-	0x04bd0002,
-	0x02830080,
+/* 0x0726: ctx_mem_wait */
+	0x008f04bd,
+	0xffcf0284,
+	0x05fffd00,
+	0xf8f61bf4,
+/* 0x0735: ctx_load */
+	0xf094bd00,
+	0x00800599,
+	0x09f60237,
+	0x0a04bd00,
+	0x00b87e0c,
+	0x80f4bd00,
+	0xf6028900,
+	0x04bd000f,
+	0x02c10080,
 	0xbd0002f6,
-	0x7e070f04,
-	0x8000071c,
-	0xf602c000,
-	0x04bd0002,
-	0xf0000bfe,
-	0x24b61f2a,
-	0x0220b604,
-	0x99f094bd,
-	0x37008008,
-	0x0009f602,
-	0x008004bd,
-	0x02f60281,
-	0xd204bd00,
-	0x80000000,
-	0x800225f0,
-	0xf6028800,
-	0x04bd0002,
-	0x00421001,
-	0x0223f002,
-	0xf80512fa,
-	0xf094bd03,
+	0x83008004,
+	0x0002f602,
+	0x070f04bd,
+	0x00071d7e,
+	0x02c00080,
+	0xbd0002f6,
+	0x000bfe04,
+	0xb61f2af0,
+	0x20b60424,
+	0xf094bd02,
 	0x00800899,
-	0x09f60217,
-	0x9804bd00,
-	0x14b68101,
-	0x80029818,
-	0xfd0825b6,
-	0x01b50512,
-	0xf094bd16,
-	0x00800999,
 	0x09f60237,
 	0x8004bd00,
 	0xf6028100,
-	0x04bd0001,
-	0x00800102,
-	0x02f60288,
-	0x4104bd00,
-	0x13f00100,
-	0x0501fa06,
+	0x04bd0002,
+	0x000000d2,
+	0x0225f080,
+	0x02880080,
+	0xbd0002f6,
+	0x42100104,
+	0x23f00200,
+	0x0512fa02,
 	0x94bd03f8,
-	0x800999f0,
+	0x800899f0,
 	0xf6021700,
 	0x04bd0009,
-	0x99f094bd,
-	0x17008005,
-	0x0009f602,
-	0x00f804bd,
-/* 0x0820: ctx_chan */
-	0x0007347e,
-	0xb87e0c0a,
-	0x050f0000,
-	0x00071c7e,
-/* 0x0832: ctx_mmio_exec */
-	0x039800f8,
-	0x81008041,
-	0x0003f602,
-	0x34bd04bd,
-/* 0x0840: ctx_mmio_loop */
-	0xf4ff34c4,
-	0x00450e1b,
-	0x0653f002,
-	0xf80535fa,
-/* 0x0851: ctx_mmio_pull */
-	0x804e9803,
-	0x7e814f98,
-	0xb600008f,
-	0x12b60830,
-	0xdf1bf401,
-/* 0x0864: ctx_mmio_done */
-	0x80160398,
-	0xf6028100,
-	0x04bd0003,
-	0x414000b5,
-	0x13f00100,
-	0x0601fa06,
-	0x00f803f8,
-/* 0x0880: ctx_xfer */
-	0x0080040e,
-	0x0ef60302,
-/* 0x088b: ctx_xfer_idle */
-	0x8e04bd00,
-	0xcf030000,
-	0xe4f100ee,
-	0x1bf42000,
-	0x0611f4f5,
-/* 0x089f: ctx_xfer_pre */
-	0x0f0c02f4,
-	0x06fd7e10,
-	0x1b11f400,
-/* 0x08a8: ctx_xfer_pre_load */
-	0xac7e020f,
-	0xbb7e0006,
-	0xcd7e0006,
-	0xf4bd0006,
-	0x0006ac7e,
-	0x0007347e,
-/* 0x08c0: ctx_xfer_exec */
-	0xbd160198,
-	0x05008024,
-	0x0002f601,
-	0x1fb204bd,
-	0x41a5008e,
-	0x00008f7e,
-	0xf001fcf0,
-	0x24b6022c,
-	0x05f2fd01,
-	0x048effb2,
-	0x8f7e41a5,
-	0x167e0000,
-	0x24bd0002,
-	0x0247fc80,
-	0xbd0002f6,
-	0x012cf004,
-	0x800320b6,
-	0xf6024afc,
+	0xb6810198,
+	0x02981814,
+	0x0825b680,
+	0xb50512fd,
+	0x94bd1601,
+	0x800999f0,
+	0xf6023700,
+	0x04bd0009,
+	0x02810080,
+	0xbd0001f6,
+	0x80010204,
+	0xf6028800,
 	0x04bd0002,
-	0xf001acf0,
-	0x000b06a5,
-	0x98000c98,
-	0x000e010d,
-	0x00013d7e,
-	0xec7e080a,
-	0x0a7e0000,
-	0x01f40002,
-	0x7e0c0a12,
+	0xf0010041,
+	0x01fa0613,
+	0xbd03f805,
+	0x0999f094,
+	0x02170080,
+	0xbd0009f6,
+	0xf094bd04,
+	0x00800599,
+	0x09f60217,
+	0xf804bd00,
+/* 0x0821: ctx_chan */
+	0x07357e00,
+	0x7e0c0a00,
 	0x0f0000b8,
-	0x071c7e05,
-	0x2d02f400,
-/* 0x093c: ctx_xfer_post */
-	0xac7e020f,
-	0xf4bd0006,
-	0x0006fd7e,
-	0x0002277e,
-	0x0006bb7e,
-	0xac7ef4bd,
+	0x071d7e05,
+/* 0x0833: ctx_mmio_exec */
+	0x9800f800,
+	0x00804103,
+	0x03f60281,
+	0xbd04bd00,
+/* 0x0841: ctx_mmio_loop */
+	0xff34c434,
+	0x450e1bf4,
+	0x53f00200,
+	0x0535fa06,
+/* 0x0852: ctx_mmio_pull */
+	0x4e9803f8,
+	0x814f9880,
+	0x00008f7e,
+	0xb60830b6,
+	0x1bf40112,
+/* 0x0865: ctx_mmio_done */
+	0x160398df,
+	0x02810080,
+	0xbd0003f6,
+	0x4000b504,
+	0xf0010041,
+	0x01fa0613,
+	0xf803f806,
+/* 0x0881: ctx_xfer */
+	0x80040e00,
+	0xf6030200,
+	0x04bd000e,
+/* 0x088c: ctx_xfer_idle */
+	0x0300008e,
+	0xf100eecf,
+	0xf42000e4,
+	0x11f4f51b,
+	0x0c02f406,
+/* 0x08a0: ctx_xfer_pre */
+	0xfe7e100f,
 	0x11f40006,
-	0x40019810,
-	0xf40511fd,
-	0x327e070b,
-/* 0x0966: ctx_xfer_no_post_mmio */
-/* 0x0966: ctx_xfer_done */
-	0x00f80008,
+/* 0x08a9: ctx_xfer_pre_load */
+	0x7e020f1b,
+	0x7e0006ad,
+	0x7e0006bc,
+	0xbd0006ce,
+	0x06ad7ef4,
+	0x07357e00,
+/* 0x08c1: ctx_xfer_exec */
+	0x16019800,
+	0x008024bd,
+	0x02f60105,
+	0xb204bd00,
+	0xa5008e1f,
+	0x008f7e41,
+	0x01fcf000,
+	0xb6022cf0,
+	0xf2fd0124,
+	0x8effb205,
+	0x7e41a504,
+	0x7e00008f,
+	0xbd000216,
+	0x47fc8024,
+	0x0002f602,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x01acf004,
+	0x0b06a5f0,
+	0x000c9800,
+	0x0e010d98,
+	0x013d7e00,
+	0x7e080a00,
+	0x7e0000ec,
+	0xf400020a,
+	0x0c0a1201,
+	0x0000b87e,
+	0x1d7e050f,
+	0x02f40007,
+/* 0x093d: ctx_xfer_post */
+	0x7e020f2d,
+	0xbd0006ad,
+	0x06fe7ef4,
+	0x02277e00,
+	0x06bc7e00,
+	0x7ef4bd00,
+	0xf40006ad,
+	0x01981011,
+	0x0511fd40,
+	0x7e070bf4,
+/* 0x0967: ctx_xfer_no_post_mmio */
+/* 0x0967: ctx_xfer_done */
+	0xf8000833,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h
index 649a442b4390..449dae753203 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/fuc/hubgm107.fuc5.h
@@ -441,7 +441,7 @@ static uint32_t gm107_grhub_code[] = {
 	0x020014fe,
 	0x12004002,
 	0xbd0002f6,
-	0x05c94104,
+	0x05ca4104,
 	0xbd0010fe,
 	0x07004024,
 	0xbd0002f6,
@@ -460,423 +460,423 @@ static uint32_t gm107_grhub_code[] = {
 	0x01039204,
 	0x03090080,
 	0xbd0003f6,
-	0x87044204,
-	0xf6040040,
-	0x04bd0002,
-	0x00400402,
-	0x0002f603,
-	0x31f404bd,
-	0x96048e10,
-	0x00657e40,
-	0xc7feb200,
-	0x01b590f1,
-	0x1ff4f003,
-	0x01020fb5,
-	0x041fbb01,
-	0x800112b6,
-	0xf6010300,
-	0x04bd0001,
-	0x01040080,
+	0x87048204,
+	0x04004000,
+	0xbd0002f6,
+	0x40040204,
+	0x02f60300,
+	0xf404bd00,
+	0x048e1031,
+	0x657e4096,
+	0xfeb20000,
+	0xb590f1c7,
+	0xf4f00301,
+	0x020fb51f,
+	0x1fbb0101,
+	0x0112b604,
+	0x01030080,
 	0xbd0001f6,
-	0x01004104,
-	0xac7e020f,
-	0xbb7e0006,
-	0x100f0006,
-	0x0006fd7e,
-	0x98000e98,
-	0x207e010f,
-	0x14950001,
-	0xc0008008,
-	0x0004f601,
-	0x008004bd,
-	0x04f601c1,
-	0xb704bd00,
-	0xbb130030,
-	0xf5b6001f,
-	0xd3008002,
-	0x000ff601,
-	0x15b604bd,
-	0x0110b608,
-	0xb20814b6,
-	0x02687e1f,
-	0x001fbb00,
-	0x84020398,
-/* 0x041f: init_gpc */
-	0xb8502000,
-	0x0008044e,
-	0x8f7e1fb2,
+	0x04008004,
+	0x0001f601,
+	0x004104bd,
+	0x7e020f01,
+	0x7e0006ad,
+	0x0f0006bc,
+	0x06fe7e10,
+	0x000e9800,
+	0x7e010f98,
+	0x95000120,
+	0x00800814,
+	0x04f601c0,
+	0x8004bd00,
+	0xf601c100,
+	0x04bd0004,
+	0x130030b7,
+	0xb6001fbb,
+	0x008002f5,
+	0x0ff601d3,
+	0xb604bd00,
+	0x10b60815,
+	0x0814b601,
+	0x687e1fb2,
+	0x1fbb0002,
+	0x02039800,
+	0x50200084,
+/* 0x0420: init_gpc */
+	0x08044eb8,
+	0x7e1fb200,
+	0xb800008f,
+	0x00010c4e,
+	0x8f7ef4bd,
 	0x4eb80000,
-	0xbd00010c,
-	0x008f7ef4,
-	0x044eb800,
-	0x8f7e0001,
+	0x7e000104,
+	0xb800008f,
+	0x0001004e,
+	0x8f7e020f,
 	0x4eb80000,
-	0x0f000100,
-	0x008f7e02,
-	0x004eb800,
-/* 0x044e: init_gpc_wait */
+/* 0x044f: init_gpc_wait */
+	0x7e000800,
+	0xc8000065,
+	0x0bf41fff,
+	0x044eb8f9,
 	0x657e0008,
-	0xffc80000,
-	0xf90bf41f,
-	0x08044eb8,
-	0x00657e00,
-	0x001fbb00,
-	0x800040b7,
-	0xf40132b6,
-	0x000fb41b,
-	0x0006fd7e,
-	0xac7e000f,
-	0x00800006,
-	0x01f60201,
-	0xbd04bd00,
-	0x1f19f014,
-	0x02300080,
-	0xbd0001f6,
-/* 0x0491: wait */
-	0x0028f404,
-/* 0x0497: main */
-	0x0d0031f4,
-	0x00377e10,
-	0xf401f400,
-	0x4001e4b1,
-	0x00c71bf5,
-	0x99f094bd,
-	0x37008004,
-	0x0009f602,
-	0x008104bd,
-	0x11cf02c0,
-	0xc1008200,
-	0x0022cf02,
-	0xf41f13c8,
-	0x23c8770b,
-	0x550bf41f,
-	0x12b220f9,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0231f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x20fc04bd,
-	0x99f094bd,
-	0x37008006,
-	0x0009f602,
-	0x31f404bd,
-	0x08807e01,
+	0x1fbb0000,
+	0x0040b700,
+	0x0132b680,
+	0x0fb41bf4,
+	0x06fe7e00,
+	0x7e000f00,
+	0x800006ad,
+	0xf6020100,
+	0x04bd0001,
+	0x19f014bd,
+	0x3000801f,
+	0x0001f602,
+/* 0x0492: wait */
+	0x28f404bd,
+	0x0031f400,
+/* 0x0498: main */
+	0x377e100d,
+	0x01f40000,
+	0x01e4b1f4,
+	0xc71bf540,
 	0xf094bd00,
-	0x00800699,
+	0x00800499,
+	0x09f60237,
+	0x8104bd00,
+	0xcf02c000,
+	0x00820011,
+	0x22cf02c1,
+	0x1f13c800,
+	0xc8770bf4,
+	0x0bf41f23,
+	0xb220f955,
+	0xf094bd12,
+	0x00800799,
+	0x09f60237,
+	0xf404bd00,
+	0x31f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
+	0xfc04bd00,
+	0xf094bd20,
+	0x00800699,
+	0x09f60237,
 	0xf404bd00,
-/* 0x0522: chsw_prev_no_next */
-	0x20f92f0e,
-	0x32f412b2,
-	0x0232f401,
-	0x0008807e,
-	0x008020fc,
-	0x02f602c0,
+	0x817e0131,
+	0x94bd0008,
+	0x800699f0,
+	0xf6021700,
+	0x04bd0009,
+/* 0x0523: chsw_prev_no_next */
+	0xf92f0ef4,
+	0xf412b220,
+	0x32f40132,
+	0x08817e02,
+	0x8020fc00,
+	0xf602c000,
+	0x04bd0002,
+/* 0x053f: chsw_no_prev */
+	0xc8130ef4,
+	0x0bf41f23,
+	0x0131f40d,
+	0x7e0232f4,
+/* 0x054f: chsw_done */
+	0x02000881,
+	0xc3008001,
+	0x0002f602,
+	0x94bd04bd,
+	0x800499f0,
+	0xf6021700,
+	0x04bd0009,
+	0xff300ef5,
+/* 0x056c: main_not_ctx_switch */
+	0xf401e4b0,
+	0xf2b20c1b,
+	0x0008217e,
+/* 0x057b: main_not_ctx_chan */
+	0xb0400ef4,
+	0x1bf402e4,
+	0xf094bd2c,
+	0x00800799,
+	0x09f60237,
 	0xf404bd00,
-/* 0x053e: chsw_no_prev */
-	0x23c8130e,
-	0x0d0bf41f,
-	0xf40131f4,
-	0x807e0232,
-/* 0x054e: chsw_done */
-	0x01020008,
-	0x02c30080,
-	0xbd0002f6,
-	0xf094bd04,
-	0x00800499,
+	0x32f40132,
+	0x08817e02,
+	0xf094bd00,
+	0x00800799,
 	0x09f60217,
-	0xf504bd00,
-/* 0x056b: main_not_ctx_switch */
-	0xb0ff300e,
-	0x1bf401e4,
-	0x7ef2b20c,
-	0xf4000820,
-/* 0x057a: main_not_ctx_chan */
-	0xe4b0400e,
-	0x2c1bf402,
-	0x99f094bd,
-	0x37008007,
-	0x0009f602,
-	0x32f404bd,
-	0x0232f401,
-	0x0008807e,
-	0x99f094bd,
-	0x17008007,
-	0x0009f602,
-	0x0ef404bd,
-/* 0x05a9: main_not_ctx_save */
-	0x10ef9411,
-	0x7e01f5f0,
-	0xf50002f8,
-/* 0x05b7: main_done */
-	0xbdfee40e,
-	0x1f29f024,
-	0x02300080,
-	0xbd0002f6,
-	0xd20ef504,
-/* 0x05c9: ih */
-	0xf900f9fe,
-	0x0188fe80,
-	0x90f980f9,
-	0xb0f9a0f9,
-	0xe0f9d0f9,
-	0x04bdf0f9,
-	0xcf02004a,
-	0xabc400aa,
-	0x230bf404,
-	0x004e100d,
-	0x00eecf1a,
-	0xcf19004f,
-	0x047e00ff,
-	0xb0b70000,
-	0x010e0400,
-	0xf61d0040,
-	0x04bd000e,
-/* 0x060c: ih_no_fifo */
-	0x0100abe4,
-	0x0d0c0bf4,
-	0x40014e10,
-	0x0000047e,
-/* 0x061c: ih_no_ctxsw */
-	0x0400abe4,
-	0x8e560bf4,
-	0x7e400708,
+	0xf404bd00,
+/* 0x05aa: main_not_ctx_save */
+	0xef94110e,
+	0x01f5f010,
+	0x0002f87e,
+	0xfee40ef5,
+/* 0x05b8: main_done */
+	0x29f024bd,
+	0x3000801f,
+	0x0002f602,
+	0x0ef504bd,
+/* 0x05ca: ih */
+	0x00f9fed2,
+	0x88fe80f9,
+	0xf980f901,
+	0xf9a0f990,
+	0xf9d0f9b0,
+	0xbdf0f9e0,
+	0x02004a04,
+	0xc400aacf,
+	0x0bf404ab,
+	0x4e100d23,
+	0xeecf1a00,
+	0x19004f00,
+	0x7e00ffcf,
+	0xb7000004,
+	0x0e0400b0,
+	0x1d004001,
+	0xbd000ef6,
+/* 0x060d: ih_no_fifo */
+	0x00abe404,
+	0x0c0bf401,
+	0x014e100d,
+	0x00047e40,
+/* 0x061d: ih_no_ctxsw */
+	0x00abe400,
+	0x560bf404,
+	0x4007088e,
+	0x0000657e,
+	0x0080ffb2,
+	0x0ff60204,
+	0x8e04bd00,
+	0x7e400704,
 	0xb2000065,
-	0x040080ff,
+	0x030080ff,
 	0x000ff602,
-	0x048e04bd,
-	0x657e4007,
-	0xffb20000,
-	0x02030080,
-	0xbd000ff6,
-	0x50fec704,
-	0x8f02ee94,
-	0xbb400700,
-	0x657e00ef,
-	0x00800000,
-	0x0ff60202,
+	0xfec704bd,
+	0x02ee9450,
+	0x4007008f,
+	0x7e00efbb,
+	0x80000065,
+	0xf6020200,
+	0x04bd000f,
+	0xf87e030f,
+	0x004b0002,
+	0x8ebfb201,
+	0x7e400144,
+/* 0x0677: ih_no_fwmthd */
+	0x4b00008f,
+	0xb0bd0504,
+	0xf4b4abff,
+	0x00800c0b,
+	0x0bf60307,
+/* 0x068b: ih_no_other */
+	0x4004bd00,
+	0x0af60100,
+	0xfc04bd00,
+	0xfce0fcf0,
+	0xfcb0fcd0,
+	0xfc90fca0,
+	0x0088fe80,
+	0x00fc80fc,
+	0xf80032f4,
+/* 0x06ad: ctx_4170s */
+	0x10f5f001,
+	0x708effb2,
+	0x8f7e4041,
+	0x00f80000,
+/* 0x06bc: ctx_4170w */
+	0x4041708e,
+	0x0000657e,
+	0xf4f0ffb2,
+	0xf31bf410,
+/* 0x06ce: ctx_redswitch */
+	0x004e00f8,
+	0x40e5f002,
+	0xf020e5f0,
+	0x008010e5,
+	0x0ef60185,
 	0x0f04bd00,
-	0x02f87e03,
-	0x01004b00,
-	0x448ebfb2,
-	0x8f7e4001,
-/* 0x0676: ih_no_fwmthd */
-	0x044b0000,
-	0xffb0bd05,
-	0x0bf4b4ab,
-	0x0700800c,
-	0x000bf603,
-/* 0x068a: ih_no_other */
-	0x004004bd,
-	0x000af601,
-	0xf0fc04bd,
-	0xd0fce0fc,
-	0xa0fcb0fc,
-	0x80fc90fc,
-	0xfc0088fe,
-	0xf400fc80,
-	0x01f80032,
-/* 0x06ac: ctx_4170s */
-	0xb210f5f0,
-	0x41708eff,
+/* 0x06e5: ctx_redswitch_delay */
+	0x01f2b608,
+	0xf1fd1bf4,
+	0xf10400e5,
+	0x800100e5,
+	0xf6018500,
+	0x04bd000e,
+/* 0x06fe: ctx_86c */
+	0x008000f8,
+	0x0ff60223,
+	0xb204bd00,
+	0x8a148eff,
 	0x008f7e40,
-/* 0x06bb: ctx_4170w */
-	0x8e00f800,
-	0x7e404170,
-	0xb2000065,
-	0x10f4f0ff,
-	0xf8f31bf4,
-/* 0x06cd: ctx_redswitch */
-	0x02004e00,
-	0xf040e5f0,
-	0xe5f020e5,
-	0x85008010,
-	0x000ef601,
-	0x080f04bd,
-/* 0x06e4: ctx_redswitch_delay */
-	0xf401f2b6,
-	0xe5f1fd1b,
-	0xe5f10400,
-	0x00800100,
-	0x0ef60185,
-	0xf804bd00,
-/* 0x06fd: ctx_86c */
-	0x23008000,
+	0x8effb200,
+	0x7e41a88c,
+	0xf800008f,
+/* 0x071d: ctx_mem */
+	0x84008000,
 	0x000ff602,
-	0xffb204bd,
-	0x408a148e,
-	0x00008f7e,
-	0x8c8effb2,
-	0x8f7e41a8,
-	0x00f80000,
-/* 0x071c: ctx_mem */
-	0x02840080,
-	0xbd000ff6,
-/* 0x0725: ctx_mem_wait */
-	0x84008f04,
-	0x00ffcf02,
-	0xf405fffd,
-	0x00f8f61b,
-/* 0x0734: ctx_load */
-	0x99f094bd,
-	0x37008005,
-	0x0009f602,
-	0x0c0a04bd,
-	0x0000b87e,
-	0x0080f4bd,
-	0x0ff60289,
-	0x8004bd00,
-	0xf602c100,
-	0x04bd0002,
-	0x02830080,
+/* 0x0726: ctx_mem_wait */
+	0x008f04bd,
+	0xffcf0284,
+	0x05fffd00,
+	0xf8f61bf4,
+/* 0x0735: ctx_load */
+	0xf094bd00,
+	0x00800599,
+	0x09f60237,
+	0x0a04bd00,
+	0x00b87e0c,
+	0x80f4bd00,
+	0xf6028900,
+	0x04bd000f,
+	0x02c10080,
 	0xbd0002f6,
-	0x7e070f04,
-	0x8000071c,
-	0xf602c000,
-	0x04bd0002,
-	0xf0000bfe,
-	0x24b61f2a,
-	0x0220b604,
-	0x99f094bd,
-	0x37008008,
-	0x0009f602,
-	0x008004bd,
-	0x02f60281,
-	0xd204bd00,
-	0x80000000,
-	0x800225f0,
-	0xf6028800,
-	0x04bd0002,
-	0x00421001,
-	0x0223f002,
-	0xf80512fa,
-	0xf094bd03,
+	0x83008004,
+	0x0002f602,
+	0x070f04bd,
+	0x00071d7e,
+	0x02c00080,
+	0xbd0002f6,
+	0x000bfe04,
+	0xb61f2af0,
+	0x20b60424,
+	0xf094bd02,
 	0x00800899,
-	0x09f60217,
-	0x9804bd00,
-	0x14b68101,
-	0x80029818,
-	0xfd0825b6,
-	0x01b50512,
-	0xf094bd16,
-	0x00800999,
 	0x09f60237,
 	0x8004bd00,
 	0xf6028100,
-	0x04bd0001,
-	0x00800102,
-	0x02f60288,
-	0x4104bd00,
-	0x13f00100,
-	0x0501fa06,
+	0x04bd0002,
+	0x000000d2,
+	0x0225f080,
+	0x02880080,
+	0xbd0002f6,
+	0x42100104,
+	0x23f00200,
+	0x0512fa02,
 	0x94bd03f8,
-	0x800999f0,
+	0x800899f0,
 	0xf6021700,
 	0x04bd0009,
-	0x99f094bd,
-	0x17008005,
-	0x0009f602,
-	0x00f804bd,
-/* 0x0820: ctx_chan */
-	0x0007347e,
-	0xb87e0c0a,
-	0x050f0000,
-	0x00071c7e,
-/* 0x0832: ctx_mmio_exec */
-	0x039800f8,
-	0x81008041,
-	0x0003f602,
-	0x34bd04bd,
-/* 0x0840: ctx_mmio_loop */
-	0xf4ff34c4,
-	0x00450e1b,
-	0x0653f002,
-	0xf80535fa,
-/* 0x0851: ctx_mmio_pull */
-	0x804e9803,
-	0x7e814f98,
-	0xb600008f,
-	0x12b60830,
-	0xdf1bf401,
-/* 0x0864: ctx_mmio_done */
-	0x80160398,
-	0xf6028100,
-	0x04bd0003,
-	0x414000b5,
-	0x13f00100,
-	0x0601fa06,
-	0x00f803f8,
-/* 0x0880: ctx_xfer */
-	0x0080040e,
-	0x0ef60302,
-/* 0x088b: ctx_xfer_idle */
-	0x8e04bd00,
-	0xcf030000,
-	0xe4f100ee,
-	0x1bf42000,
-	0x0611f4f5,
-/* 0x089f: ctx_xfer_pre */
-	0x0f0c02f4,
-	0x06fd7e10,
-	0x1b11f400,
-/* 0x08a8: ctx_xfer_pre_load */
-	0xac7e020f,
-	0xbb7e0006,
-	0xcd7e0006,
-	0xf4bd0006,
-	0x0006ac7e,
-	0x0007347e,
-/* 0x08c0: ctx_xfer_exec */
-	0xbd160198,
-	0x05008024,
-	0x0002f601,
-	0x1fb204bd,
-	0x41a5008e,
-	0x00008f7e,
-	0xf001fcf0,
-	0x24b6022c,
-	0x05f2fd01,
-	0x048effb2,
-	0x8f7e41a5,
-	0x167e0000,
-	0x24bd0002,
-	0x0247fc80,
-	0xbd0002f6,
-	0x012cf004,
-	0x800320b6,
-	0xf6024afc,
+	0xb6810198,
+	0x02981814,
+	0x0825b680,
+	0xb50512fd,
+	0x94bd1601,
+	0x800999f0,
+	0xf6023700,
+	0x04bd0009,
+	0x02810080,
+	0xbd0001f6,
+	0x80010204,
+	0xf6028800,
 	0x04bd0002,
-	0xf001acf0,
-	0x000b06a5,
-	0x98000c98,
-	0x000e010d,
-	0x00013d7e,
-	0xec7e080a,
-	0x0a7e0000,
-	0x01f40002,
-	0x7e0c0a12,
+	0xf0010041,
+	0x01fa0613,
+	0xbd03f805,
+	0x0999f094,
+	0x02170080,
+	0xbd0009f6,
+	0xf094bd04,
+	0x00800599,
+	0x09f60217,
+	0xf804bd00,
+/* 0x0821: ctx_chan */
+	0x07357e00,
+	0x7e0c0a00,
 	0x0f0000b8,
-	0x071c7e05,
-	0x2d02f400,
-/* 0x093c: ctx_xfer_post */
-	0xac7e020f,
-	0xf4bd0006,
-	0x0006fd7e,
-	0x0002277e,
-	0x0006bb7e,
-	0xac7ef4bd,
+	0x071d7e05,
+/* 0x0833: ctx_mmio_exec */
+	0x9800f800,
+	0x00804103,
+	0x03f60281,
+	0xbd04bd00,
+/* 0x0841: ctx_mmio_loop */
+	0xff34c434,
+	0x450e1bf4,
+	0x53f00200,
+	0x0535fa06,
+/* 0x0852: ctx_mmio_pull */
+	0x4e9803f8,
+	0x814f9880,
+	0x00008f7e,
+	0xb60830b6,
+	0x1bf40112,
+/* 0x0865: ctx_mmio_done */
+	0x160398df,
+	0x02810080,
+	0xbd0003f6,
+	0x4000b504,
+	0xf0010041,
+	0x01fa0613,
+	0xf803f806,
+/* 0x0881: ctx_xfer */
+	0x80040e00,
+	0xf6030200,
+	0x04bd000e,
+/* 0x088c: ctx_xfer_idle */
+	0x0300008e,
+	0xf100eecf,
+	0xf42000e4,
+	0x11f4f51b,
+	0x0c02f406,
+/* 0x08a0: ctx_xfer_pre */
+	0xfe7e100f,
 	0x11f40006,
-	0x40019810,
-	0xf40511fd,
-	0x327e070b,
-/* 0x0966: ctx_xfer_no_post_mmio */
-/* 0x0966: ctx_xfer_done */
-	0x00f80008,
+/* 0x08a9: ctx_xfer_pre_load */
+	0x7e020f1b,
+	0x7e0006ad,
+	0x7e0006bc,
+	0xbd0006ce,
+	0x06ad7ef4,
+	0x07357e00,
+/* 0x08c1: ctx_xfer_exec */
+	0x16019800,
+	0x008024bd,
+	0x02f60105,
+	0xb204bd00,
+	0xa5008e1f,
+	0x008f7e41,
+	0x01fcf000,
+	0xb6022cf0,
+	0xf2fd0124,
+	0x8effb205,
+	0x7e41a504,
+	0x7e00008f,
+	0xbd000216,
+	0x47fc8024,
+	0x0002f602,
+	0x2cf004bd,
+	0x0320b601,
+	0x024afc80,
+	0xbd0002f6,
+	0x01acf004,
+	0x0b06a5f0,
+	0x000c9800,
+	0x0e010d98,
+	0x013d7e00,
+	0x7e080a00,
+	0x7e0000ec,
+	0xf400020a,
+	0x0c0a1201,
+	0x0000b87e,
+	0x1d7e050f,
+	0x02f40007,
+/* 0x093d: ctx_xfer_post */
+	0x7e020f2d,
+	0xbd0006ad,
+	0x06fe7ef4,
+	0x02277e00,
+	0x06bc7e00,
+	0x7ef4bd00,
+	0xf40006ad,
+	0x01981011,
+	0x0511fd40,
+	0x7e070bf4,
+/* 0x0967: ctx_xfer_no_post_mmio */
+/* 0x0967: ctx_xfer_done */
+	0xf8000833,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index c578deb5867a..dd8f85b8b3a7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -26,9 +26,9 @@
 #include "fuc/os.h"
 
 #include <core/client.h>
-#include <core/option.h>
 #include <core/firmware.h>
-#include <subdev/secboot.h>
+#include <core/option.h>
+#include <subdev/acr.h>
 #include <subdev/fb.h>
 #include <subdev/mc.h>
 #include <subdev/pmu.h>
@@ -1636,7 +1636,7 @@ gf100_gr_intr(struct nvkm_gr *base)
 
 static void
 gf100_gr_init_fw(struct nvkm_falcon *falcon,
-		 struct gf100_gr_fuc *code, struct gf100_gr_fuc *data)
+		 struct nvkm_blob *code, struct nvkm_blob *data)
 {
 	nvkm_falcon_load_dmem(falcon, data->data, 0x0, data->size, 0);
 	nvkm_falcon_load_imem(falcon, code->data, 0x0, code->size, 0, 0, false);
@@ -1690,26 +1690,30 @@ gf100_gr_init_ctxctl_ext(struct gf100_gr *gr)
 {
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	struct nvkm_secboot *sb = device->secboot;
-	u32 secboot_mask = 0;
+	u32 lsf_mask = 0;
 	int ret;
 
 	/* load fuc microcode */
 	nvkm_mc_unk260(device, 0);
 
 	/* securely-managed falcons must be reset using secure boot */
-	if (nvkm_secboot_is_managed(sb, NVKM_SECBOOT_FALCON_FECS))
-		secboot_mask |= BIT(NVKM_SECBOOT_FALCON_FECS);
-	else
-		gf100_gr_init_fw(gr->fecs.falcon, &gr->fuc409c, &gr->fuc409d);
 
-	if (nvkm_secboot_is_managed(sb, NVKM_SECBOOT_FALCON_GPCCS))
-		secboot_mask |= BIT(NVKM_SECBOOT_FALCON_GPCCS);
-	else
-		gf100_gr_init_fw(gr->gpccs.falcon, &gr->fuc41ac, &gr->fuc41ad);
+	if (!nvkm_acr_managed_falcon(device, NVKM_ACR_LSF_FECS)) {
+		gf100_gr_init_fw(&gr->fecs.falcon, &gr->fecs.inst,
+						   &gr->fecs.data);
+	} else {
+		lsf_mask |= BIT(NVKM_ACR_LSF_FECS);
+	}
 
-	if (secboot_mask != 0) {
-		int ret = nvkm_secboot_reset(sb, secboot_mask);
+	if (!nvkm_acr_managed_falcon(device, NVKM_ACR_LSF_GPCCS)) {
+		gf100_gr_init_fw(&gr->gpccs.falcon, &gr->gpccs.inst,
+						    &gr->gpccs.data);
+	} else {
+		lsf_mask |= BIT(NVKM_ACR_LSF_GPCCS);
+	}
+
+	if (lsf_mask) {
+		ret = nvkm_acr_bootstrap_falcons(device, lsf_mask);
 		if (ret)
 			return ret;
 	}
@@ -1721,8 +1725,8 @@ gf100_gr_init_ctxctl_ext(struct gf100_gr *gr)
 	nvkm_wr32(device, 0x41a10c, 0x00000000);
 	nvkm_wr32(device, 0x40910c, 0x00000000);
 
-	nvkm_falcon_start(gr->gpccs.falcon);
-	nvkm_falcon_start(gr->fecs.falcon);
+	nvkm_falcon_start(&gr->gpccs.falcon);
+	nvkm_falcon_start(&gr->fecs.falcon);
 
 	if (nvkm_msec(device, 2000,
 		if (nvkm_rd32(device, 0x409800) & 0x00000001)
@@ -1784,18 +1788,18 @@ gf100_gr_init_ctxctl_int(struct gf100_gr *gr)
 
 	/* load HUB microcode */
 	nvkm_mc_unk260(device, 0);
-	nvkm_falcon_load_dmem(gr->fecs.falcon,
+	nvkm_falcon_load_dmem(&gr->fecs.falcon,
 			      gr->func->fecs.ucode->data.data, 0x0,
 			      gr->func->fecs.ucode->data.size, 0);
-	nvkm_falcon_load_imem(gr->fecs.falcon,
+	nvkm_falcon_load_imem(&gr->fecs.falcon,
 			      gr->func->fecs.ucode->code.data, 0x0,
 			      gr->func->fecs.ucode->code.size, 0, 0, false);
 
 	/* load GPC microcode */
-	nvkm_falcon_load_dmem(gr->gpccs.falcon,
+	nvkm_falcon_load_dmem(&gr->gpccs.falcon,
 			      gr->func->gpccs.ucode->data.data, 0x0,
 			      gr->func->gpccs.ucode->data.size, 0);
-	nvkm_falcon_load_imem(gr->gpccs.falcon,
+	nvkm_falcon_load_imem(&gr->gpccs.falcon,
 			      gr->func->gpccs.ucode->code.data, 0x0,
 			      gr->func->gpccs.ucode->code.size, 0, 0, false);
 	nvkm_mc_unk260(device, 1);
@@ -1941,17 +1945,6 @@ gf100_gr_oneinit(struct nvkm_gr *base)
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
 	int i, j;
-	int ret;
-
-	ret = nvkm_falcon_v1_new(subdev, "FECS", 0x409000, &gr->fecs.falcon);
-	if (ret)
-		return ret;
-
-	mutex_init(&gr->fecs.mutex);
-
-	ret = nvkm_falcon_v1_new(subdev, "GPCCS", 0x41a000, &gr->gpccs.falcon);
-	if (ret)
-		return ret;
 
 	nvkm_pmu_pgob(device->pmu, false);
 
@@ -1992,11 +1985,11 @@ gf100_gr_init_(struct nvkm_gr *base)
 
 	nvkm_pmu_pgob(gr->base.engine.subdev.device->pmu, false);
 
-	ret = nvkm_falcon_get(gr->fecs.falcon, subdev);
+	ret = nvkm_falcon_get(&gr->fecs.falcon, subdev);
 	if (ret)
 		return ret;
 
-	ret = nvkm_falcon_get(gr->gpccs.falcon, subdev);
+	ret = nvkm_falcon_get(&gr->gpccs.falcon, subdev);
 	if (ret)
 		return ret;
 
@@ -2004,49 +1997,34 @@ gf100_gr_init_(struct nvkm_gr *base)
 }
 
 static int
-gf100_gr_fini_(struct nvkm_gr *base, bool suspend)
+gf100_gr_fini(struct nvkm_gr *base, bool suspend)
 {
 	struct gf100_gr *gr = gf100_gr(base);
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
-	nvkm_falcon_put(gr->gpccs.falcon, subdev);
-	nvkm_falcon_put(gr->fecs.falcon, subdev);
+	nvkm_falcon_put(&gr->gpccs.falcon, subdev);
+	nvkm_falcon_put(&gr->fecs.falcon, subdev);
 	return 0;
 }
 
-void
-gf100_gr_dtor_fw(struct gf100_gr_fuc *fuc)
-{
-	kfree(fuc->data);
-	fuc->data = NULL;
-}
-
-static void
-gf100_gr_dtor_init(struct gf100_gr_pack *pack)
-{
-	vfree(pack);
-}
-
 void *
 gf100_gr_dtor(struct nvkm_gr *base)
 {
 	struct gf100_gr *gr = gf100_gr(base);
 
-	if (gr->func->dtor)
-		gr->func->dtor(gr);
 	kfree(gr->data);
 
-	nvkm_falcon_del(&gr->gpccs.falcon);
-	nvkm_falcon_del(&gr->fecs.falcon);
+	nvkm_falcon_dtor(&gr->gpccs.falcon);
+	nvkm_falcon_dtor(&gr->fecs.falcon);
 
-	gf100_gr_dtor_fw(&gr->fuc409c);
-	gf100_gr_dtor_fw(&gr->fuc409d);
-	gf100_gr_dtor_fw(&gr->fuc41ac);
-	gf100_gr_dtor_fw(&gr->fuc41ad);
+	nvkm_blob_dtor(&gr->fecs.inst);
+	nvkm_blob_dtor(&gr->fecs.data);
+	nvkm_blob_dtor(&gr->gpccs.inst);
+	nvkm_blob_dtor(&gr->gpccs.data);
 
-	gf100_gr_dtor_init(gr->fuc_bundle);
-	gf100_gr_dtor_init(gr->fuc_method);
-	gf100_gr_dtor_init(gr->fuc_sw_ctx);
-	gf100_gr_dtor_init(gr->fuc_sw_nonctx);
+	vfree(gr->bundle);
+	vfree(gr->method);
+	vfree(gr->sw_ctx);
+	vfree(gr->sw_nonctx);
 
 	return gr;
 }
@@ -2056,7 +2034,7 @@ gf100_gr_ = {
 	.dtor = gf100_gr_dtor,
 	.oneinit = gf100_gr_oneinit,
 	.init = gf100_gr_init_,
-	.fini = gf100_gr_fini_,
+	.fini = gf100_gr_fini,
 	.intr = gf100_gr_intr,
 	.units = gf100_gr_units,
 	.chan_new = gf100_gr_chan_new,
@@ -2067,87 +2045,24 @@ gf100_gr_ = {
 	.ctxsw.inst = gf100_gr_ctxsw_inst,
 };
 
-int
-gf100_gr_ctor_fw_legacy(struct gf100_gr *gr, const char *fwname,
-			struct gf100_gr_fuc *fuc, int ret)
-{
-	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
-	struct nvkm_device *device = subdev->device;
-	const struct firmware *fw;
-	char f[32];
-
-	/* see if this firmware has a legacy path */
-	if (!strcmp(fwname, "fecs_inst"))
-		fwname = "fuc409c";
-	else if (!strcmp(fwname, "fecs_data"))
-		fwname = "fuc409d";
-	else if (!strcmp(fwname, "gpccs_inst"))
-		fwname = "fuc41ac";
-	else if (!strcmp(fwname, "gpccs_data"))
-		fwname = "fuc41ad";
-	else {
-		/* nope, let's just return the error we got */
-		nvkm_error(subdev, "failed to load %s\n", fwname);
-		return ret;
-	}
-
-	/* yes, try to load from the legacy path */
-	nvkm_debug(subdev, "%s: falling back to legacy path\n", fwname);
-
-	snprintf(f, sizeof(f), "nouveau/nv%02x_%s", device->chipset, fwname);
-	ret = request_firmware(&fw, f, device->dev);
-	if (ret) {
-		snprintf(f, sizeof(f), "nouveau/%s", fwname);
-		ret = request_firmware(&fw, f, device->dev);
-		if (ret) {
-			nvkm_error(subdev, "failed to load %s\n", fwname);
-			return ret;
-		}
-	}
-
-	fuc->size = fw->size;
-	fuc->data = kmemdup(fw->data, fuc->size, GFP_KERNEL);
-	release_firmware(fw);
-	return (fuc->data != NULL) ? 0 : -ENOMEM;
-}
-
-int
-gf100_gr_ctor_fw(struct gf100_gr *gr, const char *fwname,
-		 struct gf100_gr_fuc *fuc)
-{
-	const struct firmware *fw;
-	int ret;
-
-	ret = nvkm_firmware_get(&gr->base.engine.subdev, fwname, &fw);
-	if (ret) {
-		ret = gf100_gr_ctor_fw_legacy(gr, fwname, fuc, ret);
-		if (ret)
-			return -ENODEV;
-		return 0;
-	}
-
-	fuc->size = fw->size;
-	fuc->data = kmemdup(fw->data, fuc->size, GFP_KERNEL);
-	nvkm_firmware_put(fw);
-	return (fuc->data != NULL) ? 0 : -ENOMEM;
-}
-
-int
-gf100_gr_ctor(const struct gf100_gr_func *func, struct nvkm_device *device,
-	      int index, struct gf100_gr *gr)
-{
-	gr->func = func;
-	gr->firmware = nvkm_boolopt(device->cfgopt, "NvGrUseFW",
-				    func->fecs.ucode == NULL);
-
-	return nvkm_gr_ctor(&gf100_gr_, device, index,
-			    gr->firmware || func->fecs.ucode != NULL,
-			    &gr->base);
-}
+static const struct nvkm_falcon_func
+gf100_gr_flcn = {
+	.fbif = 0x600,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.bind_context = nvkm_falcon_v1_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = nvkm_falcon_v1_enable,
+	.disable = nvkm_falcon_v1_disable,
+};
 
 int
-gf100_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
-	      int index, struct nvkm_gr **pgr)
+gf100_gr_new_(const struct gf100_gr_fwif *fwif,
+	      struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
 	struct gf100_gr *gr;
 	int ret;
@@ -2156,22 +2071,49 @@ gf100_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
 		return -ENOMEM;
 	*pgr = &gr->base;
 
-	ret = gf100_gr_ctor(func, device, index, gr);
+	ret = nvkm_gr_ctor(&gf100_gr_, device, index, true, &gr->base);
 	if (ret)
 		return ret;
 
-	if (gr->firmware) {
-		if (gf100_gr_ctor_fw(gr, "fecs_inst", &gr->fuc409c) ||
-		    gf100_gr_ctor_fw(gr, "fecs_data", &gr->fuc409d) ||
-		    gf100_gr_ctor_fw(gr, "gpccs_inst", &gr->fuc41ac) ||
-		    gf100_gr_ctor_fw(gr, "gpccs_data", &gr->fuc41ad))
-			return -ENODEV;
-	}
+	fwif = nvkm_firmware_load(&gr->base.engine.subdev, fwif, "Gr", gr);
+	if (IS_ERR(fwif))
+		return -ENODEV;
+
+	gr->func = fwif->func;
+
+	ret = nvkm_falcon_ctor(&gf100_gr_flcn, &gr->base.engine.subdev,
+			       "fecs", 0x409000, &gr->fecs.falcon);
+	if (ret)
+		return ret;
+
+	mutex_init(&gr->fecs.mutex);
+
+	ret = nvkm_falcon_ctor(&gf100_gr_flcn, &gr->base.engine.subdev,
+			       "gpccs", 0x41a000, &gr->gpccs.falcon);
+	if (ret)
+		return ret;
 
 	return 0;
 }
 
 void
+gf100_gr_init_num_tpc_per_gpc(struct gf100_gr *gr, bool pd, bool ds)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int gpc, i, j;
+	u32 data;
+
+	for (gpc = 0, i = 0; i < 4; i++) {
+		for (data = 0, j = 0; j < 8 && gpc < gr->gpc_nr; j++, gpc++)
+			data |= gr->tpc_nr[gpc] << (j * 4);
+		if (pd)
+			nvkm_wr32(device, 0x406028 + (i * 4), data);
+		if (ds)
+			nvkm_wr32(device, 0x405870 + (i * 4), data);
+	}
+}
+
+void
 gf100_gr_init_400054(struct gf100_gr *gr)
 {
 	nvkm_wr32(gr->base.engine.subdev.device, 0x400054, 0x34ce3464);
@@ -2295,8 +2237,8 @@ gf100_gr_init(struct gf100_gr *gr)
 
 	gr->func->init_gpc_mmu(gr);
 
-	if (gr->fuc_sw_nonctx)
-		gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
+	if (gr->sw_nonctx)
+		gf100_gr_mmio(gr, gr->sw_nonctx);
 	else
 		gf100_gr_mmio(gr, gr->func->mmio);
 
@@ -2320,6 +2262,8 @@ gf100_gr_init(struct gf100_gr *gr)
 		gr->func->init_bios_2(gr);
 	if (gr->func->init_swdx_pes_mask)
 		gr->func->init_swdx_pes_mask(gr);
+	if (gr->func->init_fs)
+		gr->func->init_fs(gr);
 
 	nvkm_wr32(device, 0x400500, 0x00010001);
 
@@ -2338,8 +2282,8 @@ gf100_gr_init(struct gf100_gr *gr)
 	if (gr->func->init_40601c)
 		gr->func->init_40601c(gr);
 
-	nvkm_wr32(device, 0x404490, 0xc0000000);
 	nvkm_wr32(device, 0x406018, 0xc0000000);
+	nvkm_wr32(device, 0x404490, 0xc0000000);
 
 	if (gr->func->init_sked_hww_esr)
 		gr->func->init_sked_hww_esr(gr);
@@ -2454,7 +2398,66 @@ gf100_gr = {
 };
 
 int
+gf100_gr_nofw(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	gr->firmware = false;
+	return 0;
+}
+
+static int
+gf100_gr_load_fw(struct gf100_gr *gr, const char *name,
+		 struct nvkm_blob *blob)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_device *device = subdev->device;
+	const struct firmware *fw;
+	char f[32];
+	int ret;
+
+	snprintf(f, sizeof(f), "nouveau/nv%02x_%s", device->chipset, name);
+	ret = request_firmware(&fw, f, device->dev);
+	if (ret) {
+		snprintf(f, sizeof(f), "nouveau/%s", name);
+		ret = request_firmware(&fw, f, device->dev);
+		if (ret) {
+			nvkm_error(subdev, "failed to load %s\n", name);
+			return ret;
+		}
+	}
+
+	blob->size = fw->size;
+	blob->data = kmemdup(fw->data, blob->size, GFP_KERNEL);
+	release_firmware(fw);
+	return (blob->data != NULL) ? 0 : -ENOMEM;
+}
+
+int
+gf100_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+
+	if (!nvkm_boolopt(device->cfgopt, "NvGrUseFW", false))
+		return -EINVAL;
+
+	if (gf100_gr_load_fw(gr, "fuc409c", &gr->fecs.inst) ||
+	    gf100_gr_load_fw(gr, "fuc409d", &gr->fecs.data) ||
+	    gf100_gr_load_fw(gr, "fuc41ac", &gr->gpccs.inst) ||
+	    gf100_gr_load_fw(gr, "fuc41ad", &gr->gpccs.data))
+		return -ENOENT;
+
+	gr->firmware = true;
+	return 0;
+}
+
+static const struct gf100_gr_fwif
+gf100_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf100_gr },
+	{ -1, gf100_gr_nofw, &gf100_gr },
+	{}
+};
+
+int
 gf100_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf100_gr, device, index, pgr);
+	return gf100_gr_new_(gf100_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index fafdd0bbea9b..88bcb57c2e07 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -31,6 +31,8 @@
 #include <subdev/mmu.h>
 #include <engine/falcon.h>
 
+struct nvkm_acr_lsfw;
+
 #define GPC_MAX 32
 #define TPC_MAX_PER_GPC 8
 #define TPC_MAX (GPC_MAX * TPC_MAX_PER_GPC)
@@ -55,11 +57,6 @@ struct gf100_gr_mmio {
 	int buffer;
 };
 
-struct gf100_gr_fuc {
-	u32 *data;
-	u32  size;
-};
-
 struct gf100_gr_zbc_color {
 	u32 format;
 	u32 ds[4];
@@ -83,29 +80,30 @@ struct gf100_gr {
 	struct nvkm_gr base;
 
 	struct {
-		struct nvkm_falcon *falcon;
+		struct nvkm_falcon falcon;
+		struct nvkm_blob inst;
+		struct nvkm_blob data;
+
 		struct mutex mutex;
 		u32 disable;
 	} fecs;
 
 	struct {
-		struct nvkm_falcon *falcon;
+		struct nvkm_falcon falcon;
+		struct nvkm_blob inst;
+		struct nvkm_blob data;
 	} gpccs;
 
-	struct gf100_gr_fuc fuc409c;
-	struct gf100_gr_fuc fuc409d;
-	struct gf100_gr_fuc fuc41ac;
-	struct gf100_gr_fuc fuc41ad;
 	bool firmware;
 
 	/*
 	 * Used if the register packs are loaded from NVIDIA fw instead of
 	 * using hardcoded arrays. To be allocated with vzalloc().
 	 */
-	struct gf100_gr_pack *fuc_sw_nonctx;
-	struct gf100_gr_pack *fuc_sw_ctx;
-	struct gf100_gr_pack *fuc_bundle;
-	struct gf100_gr_pack *fuc_method;
+	struct gf100_gr_pack *sw_nonctx;
+	struct gf100_gr_pack *sw_ctx;
+	struct gf100_gr_pack *bundle;
+	struct gf100_gr_pack *method;
 
 	struct gf100_gr_zbc_color zbc_color[NVKM_LTC_MAX_ZBC_CNT];
 	struct gf100_gr_zbc_depth zbc_depth[NVKM_LTC_MAX_ZBC_CNT];
@@ -140,12 +138,6 @@ struct gf100_gr {
 	u32 size_pm;
 };
 
-int gf100_gr_ctor(const struct gf100_gr_func *, struct nvkm_device *,
-		  int, struct gf100_gr *);
-int gf100_gr_new_(const struct gf100_gr_func *, struct nvkm_device *,
-		  int, struct nvkm_gr **);
-void *gf100_gr_dtor(struct nvkm_gr *);
-
 int gf100_gr_fecs_bind_pointer(struct gf100_gr *, u32 inst);
 
 struct gf100_gr_func_zbc {
@@ -157,7 +149,6 @@ struct gf100_gr_func_zbc {
 };
 
 struct gf100_gr_func {
-	void (*dtor)(struct gf100_gr *);
 	void (*oneinit_tiles)(struct gf100_gr *);
 	void (*oneinit_sm_id)(struct gf100_gr *);
 	int (*init)(struct gf100_gr *);
@@ -171,6 +162,7 @@ struct gf100_gr_func {
 	void (*init_rop_active_fbps)(struct gf100_gr *);
 	void (*init_bios_2)(struct gf100_gr *);
 	void (*init_swdx_pes_mask)(struct gf100_gr *);
+	void (*init_fs)(struct gf100_gr *);
 	void (*init_fecs_exceptions)(struct gf100_gr *);
 	void (*init_ds_hww_esr_2)(struct gf100_gr *);
 	void (*init_40601c)(struct gf100_gr *);
@@ -217,6 +209,7 @@ void gf100_gr_init_419eb4(struct gf100_gr *);
 void gf100_gr_init_tex_hww_esr(struct gf100_gr *, int, int);
 void gf100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
 void gf100_gr_init_400054(struct gf100_gr *);
+void gf100_gr_init_num_tpc_per_gpc(struct gf100_gr *, bool, bool);
 extern const struct gf100_gr_func_zbc gf100_gr_zbc;
 
 void gf117_gr_init_zcull(struct gf100_gr *);
@@ -245,10 +238,18 @@ void gp100_gr_init_fecs_exceptions(struct gf100_gr *);
 void gp100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
 void gp100_gr_zbc_clear_color(struct gf100_gr *, int);
 void gp100_gr_zbc_clear_depth(struct gf100_gr *, int);
+extern const struct gf100_gr_func_zbc gp100_gr_zbc;
 
 void gp102_gr_init_swdx_pes_mask(struct gf100_gr *);
 extern const struct gf100_gr_func_zbc gp102_gr_zbc;
 
+extern const struct gf100_gr_func gp107_gr;
+
+void gv100_gr_init_419bd8(struct gf100_gr *);
+void gv100_gr_init_504430(struct gf100_gr *, int, int);
+void gv100_gr_init_shader_exceptions(struct gf100_gr *, int, int);
+void gv100_gr_trap_mp(struct gf100_gr *, int, int);
+
 #define gf100_gr_chan(p) container_of((p), struct gf100_gr_chan, object)
 #include <core/object.h>
 
@@ -269,9 +270,6 @@ struct gf100_gr_chan {
 
 void gf100_gr_ctxctl_debug(struct gf100_gr *);
 
-void gf100_gr_dtor_fw(struct gf100_gr_fuc *);
-int  gf100_gr_ctor_fw(struct gf100_gr *, const char *,
-		      struct gf100_gr_fuc *);
 u64  gf100_gr_units(struct nvkm_gr *);
 void gf100_gr_zbc_init(struct gf100_gr *);
 
@@ -294,8 +292,8 @@ struct gf100_gr_pack {
 		  for (init = pack->init; init && init->count; init++)
 
 struct gf100_gr_ucode {
-	struct gf100_gr_fuc code;
-	struct gf100_gr_fuc data;
+	struct nvkm_blob code;
+	struct nvkm_blob data;
 };
 
 extern struct gf100_gr_ucode gf100_gr_fecs_ucode;
@@ -310,17 +308,6 @@ void gf100_gr_icmd(struct gf100_gr *, const struct gf100_gr_pack *);
 void gf100_gr_mthd(struct gf100_gr *, const struct gf100_gr_pack *);
 int  gf100_gr_init_ctxctl(struct gf100_gr *);
 
-/* external bundles loading functions */
-int gk20a_gr_av_to_init(struct gf100_gr *, const char *,
-			struct gf100_gr_pack **);
-int gk20a_gr_aiv_to_init(struct gf100_gr *, const char *,
-			 struct gf100_gr_pack **);
-int gk20a_gr_av_to_method(struct gf100_gr *, const char *,
-			  struct gf100_gr_pack **);
-
-int gm200_gr_new_(const struct gf100_gr_func *, struct nvkm_device *, int,
-		  struct nvkm_gr **);
-
 /* register init value lists */
 
 extern const struct gf100_gr_init gf100_gr_init_main_0[];
@@ -403,4 +390,31 @@ extern const struct gf100_gr_init gm107_gr_init_cbm_0[];
 void gm107_gr_init_bios(struct gf100_gr *);
 
 void gm200_gr_init_gpc_mmu(struct gf100_gr *);
+
+struct gf100_gr_fwif {
+	int version;
+	int (*load)(struct gf100_gr *, int ver, const struct gf100_gr_fwif *);
+	const struct gf100_gr_func *func;
+	const struct nvkm_acr_lsf_func *fecs;
+	const struct nvkm_acr_lsf_func *gpccs;
+};
+
+int gf100_gr_load(struct gf100_gr *, int, const struct gf100_gr_fwif *);
+int gf100_gr_nofw(struct gf100_gr *, int, const struct gf100_gr_fwif *);
+
+int gk20a_gr_load_sw(struct gf100_gr *, const char *path, int ver);
+
+int gm200_gr_load(struct gf100_gr *, int, const struct gf100_gr_fwif *);
+extern const struct nvkm_acr_lsf_func gm200_gr_gpccs_acr;
+extern const struct nvkm_acr_lsf_func gm200_gr_fecs_acr;
+
+extern const struct nvkm_acr_lsf_func gm20b_gr_fecs_acr;
+void gm20b_gr_acr_bld_write(struct nvkm_acr *, u32, struct nvkm_acr_lsfw *);
+void gm20b_gr_acr_bld_patch(struct nvkm_acr *, u32, s64);
+
+extern const struct nvkm_acr_lsf_func gp108_gr_gpccs_acr;
+extern const struct nvkm_acr_lsf_func gp108_gr_fecs_acr;
+
+int gf100_gr_new_(const struct gf100_gr_fwif *, struct nvkm_device *, int,
+		  struct nvkm_gr **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c
index 42c2fd9fc04e..0536fe8b2b92 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf104.c
@@ -144,8 +144,15 @@ gf104_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gf104_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf104_gr },
+	{ -1, gf100_gr_nofw, &gf104_gr },
+	{}
+};
+
 int
 gf104_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf104_gr, device, index, pgr);
+	return gf100_gr_new_(gf104_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c
index 4731a460adc7..14284b06112f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c
@@ -143,8 +143,15 @@ gf108_gr = {
 	}
 };
 
+const struct gf100_gr_fwif
+gf108_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf108_gr },
+	{ -1, gf100_gr_nofw, &gf108_gr },
+	{}
+};
+
 int
 gf108_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf108_gr, device, index, pgr);
+	return gf100_gr_new_(gf108_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c
index cdf759c8cd7f..280752551a3a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf110.c
@@ -119,8 +119,15 @@ gf110_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gf110_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf110_gr },
+	{ -1, gf100_gr_nofw, &gf110_gr },
+	{}
+};
+
 int
 gf110_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf110_gr, device, index, pgr);
+	return gf100_gr_new_(gf110_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c
index a4158f84c649..235c3fbe4b95 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf117.c
@@ -184,8 +184,15 @@ gf117_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gf117_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf117_gr },
+	{ -1, gf100_gr_nofw, &gf117_gr },
+	{}
+};
+
 int
 gf117_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf117_gr, device, index, pgr);
+	return gf100_gr_new_(gf117_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c
index 4197844870b3..7eac385ece97 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf119.c
@@ -210,8 +210,15 @@ gf119_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gf119_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gf119_gr },
+	{ -1, gf100_gr_nofw, &gf119_gr },
+	{}
+};
+
 int
 gf119_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gf119_gr, device, index, pgr);
+	return gf100_gr_new_(gf119_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
index 477fee3e3715..89f51d76082b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk104.c
@@ -489,8 +489,15 @@ gk104_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gk104_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gk104_gr },
+	{ -1, gf100_gr_nofw, &gk104_gr },
+	{}
+};
+
 int
 gk104_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gk104_gr, device, index, pgr);
+	return gf100_gr_new_(gk104_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
index 7cd628c84e07..735f05e54d62 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110.c
@@ -385,8 +385,15 @@ gk110_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gk110_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gk110_gr },
+	{ -1, gf100_gr_nofw, &gk110_gr },
+	{}
+};
+
 int
 gk110_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gk110_gr, device, index, pgr);
+	return gf100_gr_new_(gk110_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c
index a38faa215635..adc971be8f3b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk110b.c
@@ -136,8 +136,15 @@ gk110b_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gk110b_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gk110b_gr },
+	{ -1, gf100_gr_nofw, &gk110b_gr },
+	{}
+};
+
 int
 gk110b_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gk110b_gr, device, index, pgr);
+	return gf100_gr_new_(gk110b_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c
index 58456660e603..aa0eff6795ac 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk208.c
@@ -194,8 +194,15 @@ gk208_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gk208_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gk208_gr },
+	{ -1, gf100_gr_nofw, &gk208_gr },
+	{}
+};
+
 int
 gk208_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gk208_gr, device, index, pgr);
+	return gf100_gr_new_(gk208_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
index 500cb08dd608..4209b24a46d7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gk20a.c
@@ -22,6 +22,7 @@
 #include "gf100.h"
 #include "ctxgf100.h"
 
+#include <core/firmware.h>
 #include <subdev/timer.h>
 
 #include <nvif/class.h>
@@ -33,21 +34,22 @@ struct gk20a_fw_av
 };
 
 int
-gk20a_gr_av_to_init(struct gf100_gr *gr, const char *fw_name,
-		    struct gf100_gr_pack **ppack)
+gk20a_gr_av_to_init(struct gf100_gr *gr, const char *path, const char *name,
+		    int ver, struct gf100_gr_pack **ppack)
 {
-	struct gf100_gr_fuc fuc;
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_blob blob;
 	struct gf100_gr_init *init;
 	struct gf100_gr_pack *pack;
 	int nent;
 	int ret;
 	int i;
 
-	ret = gf100_gr_ctor_fw(gr, fw_name, &fuc);
+	ret = nvkm_firmware_load_blob(subdev, path, name, ver, &blob);
 	if (ret)
 		return ret;
 
-	nent = (fuc.size / sizeof(struct gk20a_fw_av));
+	nent = (blob.size / sizeof(struct gk20a_fw_av));
 	pack = vzalloc((sizeof(*pack) * 2) + (sizeof(*init) * (nent + 1)));
 	if (!pack) {
 		ret = -ENOMEM;
@@ -59,7 +61,7 @@ gk20a_gr_av_to_init(struct gf100_gr *gr, const char *fw_name,
 
 	for (i = 0; i < nent; i++) {
 		struct gf100_gr_init *ent = &init[i];
-		struct gk20a_fw_av *av = &((struct gk20a_fw_av *)fuc.data)[i];
+		struct gk20a_fw_av *av = &((struct gk20a_fw_av *)blob.data)[i];
 
 		ent->addr = av->addr;
 		ent->data = av->data;
@@ -70,7 +72,7 @@ gk20a_gr_av_to_init(struct gf100_gr *gr, const char *fw_name,
 	*ppack = pack;
 
 end:
-	gf100_gr_dtor_fw(&fuc);
+	nvkm_blob_dtor(&blob);
 	return ret;
 }
 
@@ -82,21 +84,22 @@ struct gk20a_fw_aiv
 };
 
 int
-gk20a_gr_aiv_to_init(struct gf100_gr *gr, const char *fw_name,
-		     struct gf100_gr_pack **ppack)
+gk20a_gr_aiv_to_init(struct gf100_gr *gr, const char *path, const char *name,
+		     int ver, struct gf100_gr_pack **ppack)
 {
-	struct gf100_gr_fuc fuc;
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_blob blob;
 	struct gf100_gr_init *init;
 	struct gf100_gr_pack *pack;
 	int nent;
 	int ret;
 	int i;
 
-	ret = gf100_gr_ctor_fw(gr, fw_name, &fuc);
+	ret = nvkm_firmware_load_blob(subdev, path, name, ver, &blob);
 	if (ret)
 		return ret;
 
-	nent = (fuc.size / sizeof(struct gk20a_fw_aiv));
+	nent = (blob.size / sizeof(struct gk20a_fw_aiv));
 	pack = vzalloc((sizeof(*pack) * 2) + (sizeof(*init) * (nent + 1)));
 	if (!pack) {
 		ret = -ENOMEM;
@@ -108,7 +111,7 @@ gk20a_gr_aiv_to_init(struct gf100_gr *gr, const char *fw_name,
 
 	for (i = 0; i < nent; i++) {
 		struct gf100_gr_init *ent = &init[i];
-		struct gk20a_fw_aiv *av = &((struct gk20a_fw_aiv *)fuc.data)[i];
+		struct gk20a_fw_aiv *av = &((struct gk20a_fw_aiv *)blob.data)[i];
 
 		ent->addr = av->addr;
 		ent->data = av->data;
@@ -119,15 +122,16 @@ gk20a_gr_aiv_to_init(struct gf100_gr *gr, const char *fw_name,
 	*ppack = pack;
 
 end:
-	gf100_gr_dtor_fw(&fuc);
+	nvkm_blob_dtor(&blob);
 	return ret;
 }
 
 int
-gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name,
-		      struct gf100_gr_pack **ppack)
+gk20a_gr_av_to_method(struct gf100_gr *gr, const char *path, const char *name,
+		      int ver, struct gf100_gr_pack **ppack)
 {
-	struct gf100_gr_fuc fuc;
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	struct nvkm_blob blob;
 	struct gf100_gr_init *init;
 	struct gf100_gr_pack *pack;
 	/* We don't suppose we will initialize more than 16 classes here... */
@@ -137,29 +141,30 @@ gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name,
 	int ret;
 	int i;
 
-	ret = gf100_gr_ctor_fw(gr, fw_name, &fuc);
+	ret = nvkm_firmware_load_blob(subdev, path, name, ver, &blob);
 	if (ret)
 		return ret;
 
-	nent = (fuc.size / sizeof(struct gk20a_fw_av));
+	nent = (blob.size / sizeof(struct gk20a_fw_av));
 
-	pack = vzalloc((sizeof(*pack) * max_classes) +
-		       (sizeof(*init) * (nent + 1)));
+	pack = vzalloc((sizeof(*pack) * (max_classes + 1)) +
+		       (sizeof(*init) * (nent + max_classes + 1)));
 	if (!pack) {
 		ret = -ENOMEM;
 		goto end;
 	}
 
-	init = (void *)(pack + max_classes);
+	init = (void *)(pack + max_classes + 1);
 
-	for (i = 0; i < nent; i++) {
-		struct gf100_gr_init *ent = &init[i];
-		struct gk20a_fw_av *av = &((struct gk20a_fw_av *)fuc.data)[i];
+	for (i = 0; i < nent; i++, init++) {
+		struct gk20a_fw_av *av = &((struct gk20a_fw_av *)blob.data)[i];
 		u32 class = av->addr & 0xffff;
 		u32 addr = (av->addr & 0xffff0000) >> 14;
 
 		if (prevclass != class) {
-			pack[classidx].init = ent;
+			if (prevclass) /* Add terminator to the method list. */
+				init++;
+			pack[classidx].init = init;
 			pack[classidx].type = class;
 			prevclass = class;
 			if (++classidx >= max_classes) {
@@ -169,16 +174,16 @@ gk20a_gr_av_to_method(struct gf100_gr *gr, const char *fw_name,
 			}
 		}
 
-		ent->addr = addr;
-		ent->data = av->data;
-		ent->count = 1;
-		ent->pitch = 1;
+		init->addr = addr;
+		init->data = av->data;
+		init->count = 1;
+		init->pitch = 1;
 	}
 
 	*ppack = pack;
 
 end:
-	gf100_gr_dtor_fw(&fuc);
+	nvkm_blob_dtor(&blob);
 	return ret;
 }
 
@@ -224,7 +229,7 @@ gk20a_gr_init(struct gf100_gr *gr)
 	/* Clear SCC RAM */
 	nvkm_wr32(device, 0x40802c, 0x1);
 
-	gf100_gr_mmio(gr, gr->fuc_sw_nonctx);
+	gf100_gr_mmio(gr, gr->sw_nonctx);
 
 	ret = gk20a_gr_wait_mem_scrubbing(gr);
 	if (ret)
@@ -303,40 +308,45 @@ gk20a_gr = {
 };
 
 int
-gk20a_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+gk20a_gr_load_sw(struct gf100_gr *gr, const char *path, int ver)
 {
-	struct gf100_gr *gr;
-	int ret;
+	if (gk20a_gr_av_to_init(gr, path, "sw_nonctx", ver, &gr->sw_nonctx) ||
+	    gk20a_gr_aiv_to_init(gr, path, "sw_ctx", ver, &gr->sw_ctx) ||
+	    gk20a_gr_av_to_init(gr, path, "sw_bundle_init", ver, &gr->bundle) ||
+	    gk20a_gr_av_to_method(gr, path, "sw_method_init", ver, &gr->method))
+		return -ENOENT;
 
-	if (!(gr = kzalloc(sizeof(*gr), GFP_KERNEL)))
-		return -ENOMEM;
-	*pgr = &gr->base;
-
-	ret = gf100_gr_ctor(&gk20a_gr, device, index, gr);
-	if (ret)
-		return ret;
+	return 0;
+}
 
-	if (gf100_gr_ctor_fw(gr, "fecs_inst", &gr->fuc409c) ||
-	    gf100_gr_ctor_fw(gr, "fecs_data", &gr->fuc409d) ||
-	    gf100_gr_ctor_fw(gr, "gpccs_inst", &gr->fuc41ac) ||
-	    gf100_gr_ctor_fw(gr, "gpccs_data", &gr->fuc41ad))
-		return -ENODEV;
+static int
+gk20a_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 
-	ret = gk20a_gr_av_to_init(gr, "sw_nonctx", &gr->fuc_sw_nonctx);
-	if (ret)
-		return ret;
+	if (nvkm_firmware_load_blob(subdev, "", "fecs_inst", ver,
+				    &gr->fecs.inst) ||
+	    nvkm_firmware_load_blob(subdev, "", "fecs_data", ver,
+				    &gr->fecs.data) ||
+	    nvkm_firmware_load_blob(subdev, "", "gpccs_inst", ver,
+				    &gr->gpccs.inst) ||
+	    nvkm_firmware_load_blob(subdev, "", "gpccs_data", ver,
+				    &gr->gpccs.data))
+		return -ENOENT;
 
-	ret = gk20a_gr_aiv_to_init(gr, "sw_ctx", &gr->fuc_sw_ctx);
-	if (ret)
-		return ret;
+	gr->firmware = true;
 
-	ret = gk20a_gr_av_to_init(gr, "sw_bundle_init", &gr->fuc_bundle);
-	if (ret)
-		return ret;
+	return gk20a_gr_load_sw(gr, "", ver);
+}
 
-	ret = gk20a_gr_av_to_method(gr, "sw_method_init", &gr->fuc_method);
-	if (ret)
-		return ret;
+static const struct gf100_gr_fwif
+gk20a_gr_fwif[] = {
+	{ -1, gk20a_gr_load, &gk20a_gr },
+	{}
+};
 
-	return 0;
+int
+gk20a_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+{
+	return gf100_gr_new_(gk20a_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c
index 92e31d397207..09bb78ba9d00 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm107.c
@@ -429,8 +429,15 @@ gm107_gr = {
 	}
 };
 
+static const struct gf100_gr_fwif
+gm107_gr_fwif[] = {
+	{ -1, gf100_gr_load, &gm107_gr },
+	{ -1, gf100_gr_nofw, &gm107_gr },
+	{}
+};
+
 int
 gm107_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gf100_gr_new_(&gm107_gr, device, index, pgr);
+	return gf100_gr_new_(gm107_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
index eff30662b984..3d67cfb08395 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm200.c
@@ -24,14 +24,64 @@
 #include "gf100.h"
 #include "ctxgf100.h"
 
+#include <core/firmware.h>
+#include <subdev/acr.h>
 #include <subdev/secboot.h>
 
+#include <nvfw/flcn.h>
+
 #include <nvif/class.h>
 
 /*******************************************************************************
  * PGRAPH engine/subdev functions
  ******************************************************************************/
 
+static void
+gm200_gr_acr_bld_patch(struct nvkm_acr *acr, u32 bld, s64 adjust)
+{
+	struct flcn_bl_dmem_desc_v1 hdr;
+	nvkm_robj(acr->wpr, bld, &hdr, sizeof(hdr));
+	hdr.code_dma_base = hdr.code_dma_base + adjust;
+	hdr.data_dma_base = hdr.data_dma_base + adjust;
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+	flcn_bl_dmem_desc_v1_dump(&acr->subdev, &hdr);
+}
+
+static void
+gm200_gr_acr_bld_write(struct nvkm_acr *acr, u32 bld,
+		       struct nvkm_acr_lsfw *lsfw)
+{
+	const u64 base = lsfw->offset.img + lsfw->app_start_offset;
+	const u64 code = base + lsfw->app_resident_code_offset;
+	const u64 data = base + lsfw->app_resident_data_offset;
+	const struct flcn_bl_dmem_desc_v1 hdr = {
+		.ctx_dma = FALCON_DMAIDX_UCODE,
+		.code_dma_base = code,
+		.non_sec_code_off = lsfw->app_resident_code_offset,
+		.non_sec_code_size = lsfw->app_resident_code_size,
+		.code_entry_point = lsfw->app_imem_entry,
+		.data_dma_base = data,
+		.data_size = lsfw->app_resident_data_size,
+	};
+
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+}
+
+const struct nvkm_acr_lsf_func
+gm200_gr_gpccs_acr = {
+	.flags = NVKM_ACR_LSF_FORCE_PRIV_LOAD,
+	.bld_size = sizeof(struct flcn_bl_dmem_desc_v1),
+	.bld_write = gm200_gr_acr_bld_write,
+	.bld_patch = gm200_gr_acr_bld_patch,
+};
+
+const struct nvkm_acr_lsf_func
+gm200_gr_fecs_acr = {
+	.bld_size = sizeof(struct flcn_bl_dmem_desc_v1),
+	.bld_write = gm200_gr_acr_bld_write,
+	.bld_patch = gm200_gr_acr_bld_patch,
+};
+
 int
 gm200_gr_rops(struct gf100_gr *gr)
 {
@@ -124,44 +174,6 @@ gm200_gr_oneinit_tiles(struct gf100_gr *gr)
 	}
 }
 
-int
-gm200_gr_new_(const struct gf100_gr_func *func, struct nvkm_device *device,
-	      int index, struct nvkm_gr **pgr)
-{
-	struct gf100_gr *gr;
-	int ret;
-
-	if (!(gr = kzalloc(sizeof(*gr), GFP_KERNEL)))
-		return -ENOMEM;
-	*pgr = &gr->base;
-
-	ret = gf100_gr_ctor(func, device, index, gr);
-	if (ret)
-		return ret;
-
-	/* Load firmwares for non-secure falcons */
-	if (!nvkm_secboot_is_managed(device->secboot,
-				     NVKM_SECBOOT_FALCON_FECS)) {
-		if ((ret = gf100_gr_ctor_fw(gr, "gr/fecs_inst", &gr->fuc409c)) ||
-		    (ret = gf100_gr_ctor_fw(gr, "gr/fecs_data", &gr->fuc409d)))
-			return ret;
-	}
-	if (!nvkm_secboot_is_managed(device->secboot,
-				     NVKM_SECBOOT_FALCON_GPCCS)) {
-		if ((ret = gf100_gr_ctor_fw(gr, "gr/gpccs_inst", &gr->fuc41ac)) ||
-		    (ret = gf100_gr_ctor_fw(gr, "gr/gpccs_data", &gr->fuc41ad)))
-			return ret;
-	}
-
-	if ((ret = gk20a_gr_av_to_init(gr, "gr/sw_nonctx", &gr->fuc_sw_nonctx)) ||
-	    (ret = gk20a_gr_aiv_to_init(gr, "gr/sw_ctx", &gr->fuc_sw_ctx)) ||
-	    (ret = gk20a_gr_av_to_init(gr, "gr/sw_bundle_init", &gr->fuc_bundle)) ||
-	    (ret = gk20a_gr_av_to_method(gr, "gr/sw_method_init", &gr->fuc_method)))
-		return ret;
-
-	return 0;
-}
-
 static const struct gf100_gr_func
 gm200_gr = {
 	.oneinit_tiles = gm200_gr_oneinit_tiles,
@@ -198,7 +210,77 @@ gm200_gr = {
 };
 
 int
+gm200_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	int ret;
+
+	ret = nvkm_acr_lsfw_load_bl_inst_data_sig(&gr->base.engine.subdev,
+						  &gr->fecs.falcon,
+						  NVKM_ACR_LSF_FECS,
+						  "gr/fecs_", ver, fwif->fecs);
+	if (ret)
+		return ret;
+
+	ret = nvkm_acr_lsfw_load_bl_inst_data_sig(&gr->base.engine.subdev,
+						  &gr->gpccs.falcon,
+						  NVKM_ACR_LSF_GPCCS,
+						  "gr/gpccs_", ver,
+						  fwif->gpccs);
+	if (ret)
+		return ret;
+
+	gr->firmware = true;
+
+	return gk20a_gr_load_sw(gr, "gr/", ver);
+}
+
+MODULE_FIRMWARE("nvidia/gm200/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gm200/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/gm204/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gm204/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/gm206/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gm206/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gm200_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gm200_gr, &gm200_gr_fecs_acr, &gm200_gr_gpccs_acr },
+	{}
+};
+
+int
 gm200_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gm200_gr, device, index, pgr);
+	return gf100_gr_new_(gm200_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c
index a667770ce3cb..09d8c5d5b000 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gm20b.c
@@ -22,10 +22,61 @@
 #include "gf100.h"
 #include "ctxgf100.h"
 
+#include <core/firmware.h>
+#include <subdev/acr.h>
 #include <subdev/timer.h>
 
+#include <nvfw/flcn.h>
+
 #include <nvif/class.h>
 
+void
+gm20b_gr_acr_bld_patch(struct nvkm_acr *acr, u32 bld, s64 adjust)
+{
+	struct flcn_bl_dmem_desc hdr;
+	u64 addr;
+
+	nvkm_robj(acr->wpr, bld, &hdr, sizeof(hdr));
+	addr = ((u64)hdr.code_dma_base1 << 40 | hdr.code_dma_base << 8);
+	hdr.code_dma_base  = lower_32_bits((addr + adjust) >> 8);
+	hdr.code_dma_base1 = upper_32_bits((addr + adjust) >> 8);
+	addr = ((u64)hdr.data_dma_base1 << 40 | hdr.data_dma_base << 8);
+	hdr.data_dma_base  = lower_32_bits((addr + adjust) >> 8);
+	hdr.data_dma_base1 = upper_32_bits((addr + adjust) >> 8);
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+
+	flcn_bl_dmem_desc_dump(&acr->subdev, &hdr);
+}
+
+void
+gm20b_gr_acr_bld_write(struct nvkm_acr *acr, u32 bld,
+		       struct nvkm_acr_lsfw *lsfw)
+{
+	const u64 base = lsfw->offset.img + lsfw->app_start_offset;
+	const u64 code = (base + lsfw->app_resident_code_offset) >> 8;
+	const u64 data = (base + lsfw->app_resident_data_offset) >> 8;
+	const struct flcn_bl_dmem_desc hdr = {
+		.ctx_dma = FALCON_DMAIDX_UCODE,
+		.code_dma_base = lower_32_bits(code),
+		.non_sec_code_off = lsfw->app_resident_code_offset,
+		.non_sec_code_size = lsfw->app_resident_code_size,
+		.code_entry_point = lsfw->app_imem_entry,
+		.data_dma_base = lower_32_bits(data),
+		.data_size = lsfw->app_resident_data_size,
+		.code_dma_base1 = upper_32_bits(code),
+		.data_dma_base1 = upper_32_bits(data),
+	};
+
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+}
+
+const struct nvkm_acr_lsf_func
+gm20b_gr_fecs_acr = {
+	.bld_size = sizeof(struct flcn_bl_dmem_desc),
+	.bld_write = gm20b_gr_acr_bld_write,
+	.bld_patch = gm20b_gr_acr_bld_patch,
+};
+
 static void
 gm20b_gr_init_gpc_mmu(struct gf100_gr *gr)
 {
@@ -33,7 +84,7 @@ gm20b_gr_init_gpc_mmu(struct gf100_gr *gr)
 	u32 val;
 
 	/* Bypass MMU check for non-secure boot */
-	if (!device->secboot) {
+	if (!device->acr) {
 		nvkm_wr32(device, 0x100ce4, 0xffffffff);
 
 		if (nvkm_rd32(device, 0x100ce4) != 0xffffffff)
@@ -85,8 +136,51 @@ gm20b_gr = {
 	}
 };
 
+static int
+gm20b_gr_load(struct gf100_gr *gr, int ver, const struct gf100_gr_fwif *fwif)
+{
+	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
+	int ret;
+
+	ret = nvkm_acr_lsfw_load_bl_inst_data_sig(subdev, &gr->fecs.falcon,
+						  NVKM_ACR_LSF_FECS,
+						  "gr/fecs_", ver, fwif->fecs);
+	if (ret)
+		return ret;
+
+
+	if (nvkm_firmware_load_blob(subdev, "gr/", "gpccs_inst", ver,
+				    &gr->gpccs.inst) ||
+	    nvkm_firmware_load_blob(subdev, "gr/", "gpccs_data", ver,
+				    &gr->gpccs.data))
+		return -ENOENT;
+
+	gr->firmware = true;
+
+	return gk20a_gr_load_sw(gr, "gr/", ver);
+}
+
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gm20b/gr/sw_method_init.bin");
+#endif
+
+static const struct gf100_gr_fwif
+gm20b_gr_fwif[] = {
+	{ 0, gm20b_gr_load, &gm20b_gr, &gm20b_gr_fecs_acr },
+	{}
+};
+
 int
 gm20b_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gm20b_gr, device, index, pgr);
+	return gf100_gr_new_(gm20b_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
index 9d0521ce309a..33c8634ae567 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp100.c
@@ -62,7 +62,7 @@ gp100_gr_zbc_clear_depth(struct gf100_gr *gr, int zbc)
 			  gr->zbc_depth[zbc].format << ((znum % 4) * 7));
 }
 
-static const struct gf100_gr_func_zbc
+const struct gf100_gr_func_zbc
 gp100_gr_zbc = {
 	.clear_color = gp100_gr_zbc_clear_color,
 	.clear_depth = gp100_gr_zbc_clear_depth,
@@ -135,8 +135,27 @@ gp100_gr = {
 	}
 };
 
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp100/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gp100_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gp100_gr, &gm200_gr_fecs_acr, &gm200_gr_gpccs_acr },
+	{}
+};
+
 int
 gp100_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gp100_gr, device, index, pgr);
+	return gf100_gr_new_(gp100_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c
index 37f7d739bf80..7baf67f743f4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp102.c
@@ -131,8 +131,27 @@ gp102_gr = {
 	}
 };
 
+MODULE_FIRMWARE("nvidia/gp102/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp102/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gp102_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gp102_gr, &gm200_gr_fecs_acr, &gm200_gr_gpccs_acr },
+	{}
+};
+
 int
 gp102_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gp102_gr, device, index, pgr);
+	return gf100_gr_new_(gp102_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c
index 4573c914c021..d9b8ef875f8d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp104.c
@@ -59,8 +59,40 @@ gp104_gr = {
 	}
 };
 
+MODULE_FIRMWARE("nvidia/gp104/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp104/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/gp106/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp106/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gp104_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gp104_gr, &gm200_gr_fecs_acr, &gm200_gr_gpccs_acr },
+	{}
+};
+
 int
 gp104_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gp104_gr, device, index, pgr);
+	return gf100_gr_new_(gp104_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c
index 812aba91653f..2b1ad5522184 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp107.c
@@ -26,7 +26,7 @@
 
 #include <nvif/class.h>
 
-static const struct gf100_gr_func
+const struct gf100_gr_func
 gp107_gr = {
 	.oneinit_tiles = gm200_gr_oneinit_tiles,
 	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
@@ -61,8 +61,27 @@ gp107_gr = {
 	}
 };
 
+MODULE_FIRMWARE("nvidia/gp107/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp107/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gp107_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gp107_gr, &gm200_gr_fecs_acr, &gm200_gr_gpccs_acr },
+	{}
+};
+
 int
 gp107_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gp107_gr, device, index, pgr);
+	return gf100_gr_new_(gp107_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp108.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp108.c
new file mode 100644
index 000000000000..113e4c1ba9e8
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp108.c
@@ -0,0 +1,97 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+
+#include <subdev/acr.h>
+
+#include <nvfw/flcn.h>
+
+static void
+gp108_gr_acr_bld_patch(struct nvkm_acr *acr, u32 bld, s64 adjust)
+{
+	struct flcn_bl_dmem_desc_v2 hdr;
+	nvkm_robj(acr->wpr, bld, &hdr, sizeof(hdr));
+	hdr.code_dma_base = hdr.code_dma_base + adjust;
+	hdr.data_dma_base = hdr.data_dma_base + adjust;
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+	flcn_bl_dmem_desc_v2_dump(&acr->subdev, &hdr);
+}
+
+static void
+gp108_gr_acr_bld_write(struct nvkm_acr *acr, u32 bld,
+		       struct nvkm_acr_lsfw *lsfw)
+{
+	const u64 base = lsfw->offset.img + lsfw->app_start_offset;
+	const u64 code = base + lsfw->app_resident_code_offset;
+	const u64 data = base + lsfw->app_resident_data_offset;
+	const struct flcn_bl_dmem_desc_v2 hdr = {
+		.ctx_dma = FALCON_DMAIDX_UCODE,
+		.code_dma_base = code,
+		.non_sec_code_off = lsfw->app_resident_code_offset,
+		.non_sec_code_size = lsfw->app_resident_code_size,
+		.code_entry_point = lsfw->app_imem_entry,
+		.data_dma_base = data,
+		.data_size = lsfw->app_resident_data_size,
+	};
+
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+}
+
+const struct nvkm_acr_lsf_func
+gp108_gr_gpccs_acr = {
+	.flags = NVKM_ACR_LSF_FORCE_PRIV_LOAD,
+	.bld_size = sizeof(struct flcn_bl_dmem_desc_v2),
+	.bld_write = gp108_gr_acr_bld_write,
+	.bld_patch = gp108_gr_acr_bld_patch,
+};
+
+const struct nvkm_acr_lsf_func
+gp108_gr_fecs_acr = {
+	.bld_size = sizeof(struct flcn_bl_dmem_desc_v2),
+	.bld_write = gp108_gr_acr_bld_write,
+	.bld_patch = gp108_gr_acr_bld_patch,
+};
+
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp108/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gp108_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gp107_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
+	{}
+};
+
+int
+gp108_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+{
+	return gf100_gr_new_(gp108_gr_fwif, device, index, pgr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c
index 303dceddd4a8..eaf913eb5aa3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gp10b.c
@@ -23,8 +23,20 @@
 #include "gf100.h"
 #include "ctxgf100.h"
 
+#include <subdev/acr.h>
+
 #include <nvif/class.h>
 
+#include <nvfw/flcn.h>
+
+static const struct nvkm_acr_lsf_func
+gp10b_gr_gpccs_acr = {
+	.flags = NVKM_ACR_LSF_FORCE_PRIV_LOAD,
+	.bld_size = sizeof(struct flcn_bl_dmem_desc),
+	.bld_write = gm20b_gr_acr_bld_write,
+	.bld_patch = gm20b_gr_acr_bld_patch,
+};
+
 static const struct gf100_gr_func
 gp10b_gr = {
 	.oneinit_tiles = gm200_gr_oneinit_tiles,
@@ -48,8 +60,8 @@ gp10b_gr = {
 	.gpc_nr = 1,
 	.tpc_nr = 2,
 	.ppc_nr = 1,
-	.grctx = &gp102_grctx,
-	.zbc = &gp102_gr_zbc,
+	.grctx = &gp100_grctx,
+	.zbc = &gp100_gr_zbc,
 	.sclass = {
 		{ -1, -1, FERMI_TWOD_A },
 		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
@@ -59,8 +71,29 @@ gp10b_gr = {
 	}
 };
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
+MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gp10b/gr/sw_method_init.bin");
+#endif
+
+static const struct gf100_gr_fwif
+gp10b_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gp10b_gr, &gm20b_gr_fecs_acr, &gp10b_gr_gpccs_acr },
+	{}
+};
+
 int
 gp10b_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gp10b_gr, device, index, pgr);
+	return gf100_gr_new_(gp10b_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
index 3b3327789ae7..70639d88b8e6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
@@ -45,7 +45,7 @@ gv100_gr_trap_sm(struct gf100_gr *gr, int gpc, int tpc, int sm)
 	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734 + sm * 0x80), gerr);
 }
 
-static void
+void
 gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
 {
 	gv100_gr_trap_sm(gr, gpc, tpc, 0);
@@ -59,7 +59,7 @@ gv100_gr_init_4188a4(struct gf100_gr *gr)
 	nvkm_mask(device, 0x4188a4, 0x03000000, 0x03000000);
 }
 
-static void
+void
 gv100_gr_init_shader_exceptions(struct gf100_gr *gr, int gpc, int tpc)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -71,14 +71,14 @@ gv100_gr_init_shader_exceptions(struct gf100_gr *gr, int gpc, int tpc)
 	}
 }
 
-static void
+void
 gv100_gr_init_504430(struct gf100_gr *gr, int gpc, int tpc)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
 	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x430), 0x403f0000);
 }
 
-static void
+void
 gv100_gr_init_419bd8(struct gf100_gr *gr)
 {
 	struct nvkm_device *device = gr->base.engine.subdev.device;
@@ -120,8 +120,27 @@ gv100_gr = {
 	}
 };
 
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/gv100/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+gv100_gr_fwif[] = {
+	{ 0, gm200_gr_load, &gv100_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
+	{}
+};
+
 int
 gv100_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
 {
-	return gm200_gr_new_(&gv100_gr, device, index, pgr);
+	return gf100_gr_new_(gv100_gr_fwif, device, index, pgr);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
new file mode 100644
index 000000000000..454668b1cf54
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/tu102.c
@@ -0,0 +1,177 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ctxgf100.h"
+
+#include <nvif/class.h>
+
+static void
+tu102_gr_init_fecs_exceptions(struct gf100_gr *gr)
+{
+	nvkm_wr32(gr->base.engine.subdev.device, 0x409c24, 0x006f0002);
+}
+
+static void
+tu102_gr_init_fs(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	int sm;
+
+	gp100_grctx_generate_smid_config(gr);
+	gk104_grctx_generate_gpc_tpc_nr(gr);
+
+	for (sm = 0; sm < gr->sm_nr; sm++) {
+		nvkm_wr32(device, GPC_UNIT(gr->sm[sm].gpc, 0x0c10 +
+					   gr->sm[sm].tpc * 4), sm);
+	}
+
+	gm200_grctx_generate_dist_skip_table(gr);
+	gf100_gr_init_num_tpc_per_gpc(gr, true, true);
+}
+
+static void
+tu102_gr_init_zcull(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+	const u32 magicgpc918 = DIV_ROUND_UP(0x00800000, gr->tpc_total);
+	const u8 tile_nr = ALIGN(gr->tpc_total, 64);
+	u8 bank[GPC_MAX] = {}, gpc, i, j;
+	u32 data;
+
+	for (i = 0; i < tile_nr; i += 8) {
+		for (data = 0, j = 0; j < 8 && i + j < gr->tpc_total; j++) {
+			data |= bank[gr->tile[i + j]] << (j * 4);
+			bank[gr->tile[i + j]]++;
+		}
+		nvkm_wr32(device, GPC_BCAST(0x0980 + ((i / 8) * 4)), data);
+	}
+
+	for (gpc = 0; gpc < gr->gpc_nr; gpc++) {
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0914),
+			  gr->screen_tile_row_offset << 8 | gr->tpc_nr[gpc]);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0910), 0x00040000 |
+							 gr->tpc_total);
+		nvkm_wr32(device, GPC_UNIT(gpc, 0x0918), magicgpc918);
+	}
+
+	nvkm_wr32(device, GPC_BCAST(0x3fd4), magicgpc918);
+}
+
+static void
+tu102_gr_init_gpc_mmu(struct gf100_gr *gr)
+{
+	struct nvkm_device *device = gr->base.engine.subdev.device;
+
+	nvkm_wr32(device, 0x418880, nvkm_rd32(device, 0x100c80) & 0xf8001fff);
+	nvkm_wr32(device, 0x418890, 0x00000000);
+	nvkm_wr32(device, 0x418894, 0x00000000);
+
+	nvkm_wr32(device, 0x4188b4, nvkm_rd32(device, 0x100cc8));
+	nvkm_wr32(device, 0x4188b8, nvkm_rd32(device, 0x100ccc));
+	nvkm_wr32(device, 0x4188b0, nvkm_rd32(device, 0x100cc4));
+}
+
+static const struct gf100_gr_func
+tu102_gr = {
+	.oneinit_tiles = gm200_gr_oneinit_tiles,
+	.oneinit_sm_id = gm200_gr_oneinit_sm_id,
+	.init = gf100_gr_init,
+	.init_419bd8 = gv100_gr_init_419bd8,
+	.init_gpc_mmu = tu102_gr_init_gpc_mmu,
+	.init_vsc_stream_master = gk104_gr_init_vsc_stream_master,
+	.init_zcull = tu102_gr_init_zcull,
+	.init_num_active_ltcs = gf100_gr_init_num_active_ltcs,
+	.init_rop_active_fbps = gp100_gr_init_rop_active_fbps,
+	.init_swdx_pes_mask = gp102_gr_init_swdx_pes_mask,
+	.init_fs = tu102_gr_init_fs,
+	.init_fecs_exceptions = tu102_gr_init_fecs_exceptions,
+	.init_ds_hww_esr_2 = gm200_gr_init_ds_hww_esr_2,
+	.init_sked_hww_esr = gk104_gr_init_sked_hww_esr,
+	.init_ppc_exceptions = gk104_gr_init_ppc_exceptions,
+	.init_504430 = gv100_gr_init_504430,
+	.init_shader_exceptions = gv100_gr_init_shader_exceptions,
+	.trap_mp = gv100_gr_trap_mp,
+	.rops = gm200_gr_rops,
+	.gpc_nr = 6,
+	.tpc_nr = 5,
+	.ppc_nr = 3,
+	.grctx = &tu102_grctx,
+	.zbc = &gp102_gr_zbc,
+	.sclass = {
+		{ -1, -1, FERMI_TWOD_A },
+		{ -1, -1, KEPLER_INLINE_TO_MEMORY_B },
+		{ -1, -1, TURING_A, &gf100_fermi },
+		{ -1, -1, TURING_COMPUTE_A },
+		{}
+	}
+};
+
+MODULE_FIRMWARE("nvidia/tu102/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu102/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/tu104/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu104/gr/sw_method_init.bin");
+
+MODULE_FIRMWARE("nvidia/tu106/gr/fecs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/fecs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/fecs_data.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/fecs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/gpccs_bl.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/gpccs_inst.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/gpccs_data.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/gpccs_sig.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/sw_ctx.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/sw_nonctx.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/sw_bundle_init.bin");
+MODULE_FIRMWARE("nvidia/tu106/gr/sw_method_init.bin");
+
+static const struct gf100_gr_fwif
+tu102_gr_fwif[] = {
+	{ 0, gm200_gr_load, &tu102_gr, &gp108_gr_fecs_acr, &gp108_gr_gpccs_acr },
+	{}
+};
+
+int
+tu102_gr_new(struct nvkm_device *device, int index, struct nvkm_gr **pgr)
+{
+	return gf100_gr_new_(tu102_gr_fwif, device, index, pgr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild
index cdf631822282..9a0fd9812750 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/Kbuild
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/nvdec/base.o
-nvkm-y += nvkm/engine/nvdec/gp102.o
+nvkm-y += nvkm/engine/nvdec/gm107.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/base.c
index 4a63581bdd5e..9b23c1b70ebf 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/base.c
@@ -20,48 +20,42 @@
  * DEALINGS IN THE SOFTWARE.
  */
 #include "priv.h"
-
-#include <subdev/top.h>
-#include <engine/falcon.h>
-
-static int
-nvkm_nvdec_oneinit(struct nvkm_engine *engine)
-{
-	struct nvkm_nvdec *nvdec = nvkm_nvdec(engine);
-	struct nvkm_subdev *subdev = &nvdec->engine.subdev;
-
-	nvdec->addr = nvkm_top_addr(subdev->device, subdev->index);
-	if (!nvdec->addr)
-		return -EINVAL;
-
-	/*XXX: fix naming of this when adding support for multiple-NVDEC */
-	return nvkm_falcon_v1_new(subdev, "NVDEC", nvdec->addr,
-				  &nvdec->falcon);
-}
+#include <core/firmware.h>
 
 static void *
 nvkm_nvdec_dtor(struct nvkm_engine *engine)
 {
 	struct nvkm_nvdec *nvdec = nvkm_nvdec(engine);
-	nvkm_falcon_del(&nvdec->falcon);
+	nvkm_falcon_dtor(&nvdec->falcon);
 	return nvdec;
 }
 
 static const struct nvkm_engine_func
 nvkm_nvdec = {
 	.dtor = nvkm_nvdec_dtor,
-	.oneinit = nvkm_nvdec_oneinit,
 };
 
 int
-nvkm_nvdec_new_(struct nvkm_device *device, int index,
-		struct nvkm_nvdec **pnvdec)
+nvkm_nvdec_new_(const struct nvkm_nvdec_fwif *fwif, struct nvkm_device *device,
+		int index, struct nvkm_nvdec **pnvdec)
 {
 	struct nvkm_nvdec *nvdec;
+	int ret;
 
 	if (!(nvdec = *pnvdec = kzalloc(sizeof(*nvdec), GFP_KERNEL)))
 		return -ENOMEM;
 
-	return nvkm_engine_ctor(&nvkm_nvdec, device, index, true,
-				&nvdec->engine);
+	ret = nvkm_engine_ctor(&nvkm_nvdec, device, index, true,
+			       &nvdec->engine);
+	if (ret)
+		return ret;
+
+	fwif = nvkm_firmware_load(&nvdec->engine.subdev, fwif, "Nvdec", nvdec);
+	if (IS_ERR(fwif))
+		return -ENODEV;
+
+	nvdec->func = fwif->func;
+
+	return nvkm_falcon_ctor(nvdec->func->flcn, &nvdec->engine.subdev,
+				nvkm_subdev_name[index], 0, &nvdec->falcon);
 };
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/msgqueue.h b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/gm107.c
index bf3e532665fb..0ab27ab4d8ee 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/msgqueue.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/gm107.c
@@ -19,25 +19,45 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  * DEALINGS IN THE SOFTWARE.
  */
+#include "priv.h"
 
-#ifndef __NVKM_CORE_MSGQUEUE_H
-#define __NVKM_CORE_MSGQUEUE_H
-#include <subdev/secboot.h>
-struct nvkm_msgqueue;
+static const struct nvkm_falcon_func
+gm107_nvdec_flcn = {
+	.debug = 0xd00,
+	.fbif = 0x600,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.bind_context = nvkm_falcon_v1_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = nvkm_falcon_v1_enable,
+	.disable = nvkm_falcon_v1_disable,
+};
 
-/* Hopefully we will never have firmware arguments larger than that... */
-#define NVKM_MSGQUEUE_CMDLINE_SIZE 0x100
+static const struct nvkm_nvdec_func
+gm107_nvdec = {
+	.flcn = &gm107_nvdec_flcn,
+};
 
-int nvkm_msgqueue_new(u32, struct nvkm_falcon *, const struct nvkm_secboot *,
-		      struct nvkm_msgqueue **);
-void nvkm_msgqueue_del(struct nvkm_msgqueue **);
-void nvkm_msgqueue_recv(struct nvkm_msgqueue *);
-int nvkm_msgqueue_reinit(struct nvkm_msgqueue *);
+static int
+gm107_nvdec_nofw(struct nvkm_nvdec *nvdec, int ver,
+		 const struct nvkm_nvdec_fwif *fwif)
+{
+	return 0;
+}
 
-/* useful if we run a NVIDIA-signed firmware */
-void nvkm_msgqueue_write_cmdline(struct nvkm_msgqueue *, void *);
+static const struct nvkm_nvdec_fwif
+gm107_nvdec_fwif[] = {
+	{ -1, gm107_nvdec_nofw, &gm107_nvdec },
+	{}
+};
 
-/* interface to ACR unit running on falcon (NVIDIA signed firmware) */
-int nvkm_msgqueue_acr_boot_falcons(struct nvkm_msgqueue *, unsigned long);
-
-#endif
+int
+gm107_nvdec_new(struct nvkm_device *device, int index,
+		struct nvkm_nvdec **pnvdec)
+{
+	return nvkm_nvdec_new_(gm107_nvdec_fwif, device, index, pnvdec);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/priv.h
index 57bfa3aa1835..e14da8b000d0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvdec/priv.h
@@ -3,5 +3,17 @@
 #define __NVKM_NVDEC_PRIV_H__
 #include <engine/nvdec.h>
 
-int nvkm_nvdec_new_(struct nvkm_device *, int, struct nvkm_nvdec **);
+struct nvkm_nvdec_func {
+	const struct nvkm_falcon_func *flcn;
+};
+
+struct nvkm_nvdec_fwif {
+	int version;
+	int (*load)(struct nvkm_nvdec *, int ver,
+		    const struct nvkm_nvdec_fwif *);
+	const struct nvkm_nvdec_func *func;
+};
+
+int nvkm_nvdec_new_(const struct nvkm_nvdec_fwif *fwif,
+		    struct nvkm_device *, int, struct nvkm_nvdec **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild
index f316de8d45a8..75bf4436bf3f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/Kbuild
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: MIT
-#nvkm-y += nvkm/engine/nvenc/base.o
+nvkm-y += nvkm/engine/nvenc/base.o
+nvkm-y += nvkm/engine/nvenc/gm107.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c
new file mode 100644
index 000000000000..484100e15668
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/base.c
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include "priv.h"
+#include <core/firmware.h>
+
+static void *
+nvkm_nvenc_dtor(struct nvkm_engine *engine)
+{
+	struct nvkm_nvenc *nvenc = nvkm_nvenc(engine);
+	nvkm_falcon_dtor(&nvenc->falcon);
+	return nvenc;
+}
+
+static const struct nvkm_engine_func
+nvkm_nvenc = {
+	.dtor = nvkm_nvenc_dtor,
+};
+
+int
+nvkm_nvenc_new_(const struct nvkm_nvenc_fwif *fwif, struct nvkm_device *device,
+		int index, struct nvkm_nvenc **pnvenc)
+{
+	struct nvkm_nvenc *nvenc;
+	int ret;
+
+	if (!(nvenc = *pnvenc = kzalloc(sizeof(*nvenc), GFP_KERNEL)))
+		return -ENOMEM;
+
+	ret = nvkm_engine_ctor(&nvkm_nvenc, device, index, true,
+			       &nvenc->engine);
+	if (ret)
+		return ret;
+
+	fwif = nvkm_firmware_load(&nvenc->engine.subdev, fwif, "Nvenc", nvenc);
+	if (IS_ERR(fwif))
+		return -ENODEV;
+
+	nvenc->func = fwif->func;
+
+	return nvkm_falcon_ctor(nvenc->func->flcn, &nvenc->engine.subdev,
+				nvkm_subdev_name[index], 0, &nvenc->falcon);
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/gm107.c b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/gm107.c
new file mode 100644
index 000000000000..d249c8ffb2d5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/gm107.c
@@ -0,0 +1,63 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "priv.h"
+
+static const struct nvkm_falcon_func
+gm107_nvenc_flcn = {
+	.fbif = 0x800,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.bind_context = nvkm_falcon_v1_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = nvkm_falcon_v1_enable,
+	.disable = nvkm_falcon_v1_disable,
+};
+
+static const struct nvkm_nvenc_func
+gm107_nvenc = {
+	.flcn = &gm107_nvenc_flcn,
+};
+
+static int
+gm107_nvenc_nofw(struct nvkm_nvenc *nvenc, int ver,
+		 const struct nvkm_nvenc_fwif *fwif)
+{
+	return 0;
+}
+
+static const struct nvkm_nvenc_fwif
+gm107_nvenc_fwif[] = {
+	{ -1, gm107_nvenc_nofw, &gm107_nvenc },
+	{}
+};
+
+int
+gm107_nvenc_new(struct nvkm_device *device, int index,
+		struct nvkm_nvenc **pnvenc)
+{
+	return nvkm_nvenc_new_(gm107_nvenc_fwif, device, index, pnvenc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/priv.h
new file mode 100644
index 000000000000..100fa5ebbeef
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/nvenc/priv.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVKM_NVENC_PRIV_H__
+#define __NVKM_NVENC_PRIV_H__
+#include <engine/nvenc.h>
+
+struct nvkm_nvenc_func {
+	const struct nvkm_falcon_func *flcn;
+};
+
+struct nvkm_nvenc_fwif {
+	int version;
+	int (*load)(struct nvkm_nvenc *, int ver,
+		    const struct nvkm_nvenc_fwif *);
+	const struct nvkm_nvenc_func *func;
+};
+
+int nvkm_nvenc_new_(const struct nvkm_nvenc_fwif *, struct nvkm_device *,
+		    int, struct nvkm_nvenc **pnvenc);
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild
index 97c4696171f0..63cd2be3de08 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/Kbuild
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: MIT
 nvkm-y += nvkm/engine/sec2/base.o
 nvkm-y += nvkm/engine/sec2/gp102.o
+nvkm-y += nvkm/engine/sec2/gp108.o
 nvkm-y += nvkm/engine/sec2/tu102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c
index 1b49e5b6717f..41318aa0d481 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/base.c
@@ -21,97 +21,98 @@
  */
 #include "priv.h"
 
-#include <core/msgqueue.h>
+#include <core/firmware.h>
 #include <subdev/top.h>
-#include <engine/falcon.h>
-
-static void *
-nvkm_sec2_dtor(struct nvkm_engine *engine)
-{
-	struct nvkm_sec2 *sec2 = nvkm_sec2(engine);
-	nvkm_msgqueue_del(&sec2->queue);
-	nvkm_falcon_del(&sec2->falcon);
-	return sec2;
-}
 
 static void
-nvkm_sec2_intr(struct nvkm_engine *engine)
+nvkm_sec2_recv(struct work_struct *work)
 {
-	struct nvkm_sec2 *sec2 = nvkm_sec2(engine);
-	struct nvkm_subdev *subdev = &engine->subdev;
-	struct nvkm_device *device = subdev->device;
-	u32 disp = nvkm_rd32(device, sec2->addr + 0x01c);
-	u32 intr = nvkm_rd32(device, sec2->addr + 0x008) & disp & ~(disp >> 16);
-
-	if (intr & 0x00000040) {
-		schedule_work(&sec2->work);
-		nvkm_wr32(device, sec2->addr + 0x004, 0x00000040);
-		intr &= ~0x00000040;
-	}
+	struct nvkm_sec2 *sec2 = container_of(work, typeof(*sec2), work);
 
-	if (intr) {
-		nvkm_error(subdev, "unhandled intr %08x\n", intr);
-		nvkm_wr32(device, sec2->addr + 0x004, intr);
+	if (!sec2->initmsg_received) {
+		int ret = sec2->func->initmsg(sec2);
+		if (ret) {
+			nvkm_error(&sec2->engine.subdev,
+				   "error parsing init message: %d\n", ret);
+			return;
+		}
 
+		sec2->initmsg_received = true;
 	}
+
+	nvkm_falcon_msgq_recv(sec2->msgq);
 }
 
 static void
-nvkm_sec2_recv(struct work_struct *work)
+nvkm_sec2_intr(struct nvkm_engine *engine)
 {
-	struct nvkm_sec2 *sec2 = container_of(work, typeof(*sec2), work);
-
-	if (!sec2->queue) {
-		nvkm_warn(&sec2->engine.subdev,
-			  "recv function called while no firmware set!\n");
-		return;
-	}
-
-	nvkm_msgqueue_recv(sec2->queue);
+	struct nvkm_sec2 *sec2 = nvkm_sec2(engine);
+	sec2->func->intr(sec2);
 }
 
-
 static int
-nvkm_sec2_oneinit(struct nvkm_engine *engine)
+nvkm_sec2_fini(struct nvkm_engine *engine, bool suspend)
 {
 	struct nvkm_sec2 *sec2 = nvkm_sec2(engine);
-	struct nvkm_subdev *subdev = &sec2->engine.subdev;
 
-	if (!sec2->addr) {
-		sec2->addr = nvkm_top_addr(subdev->device, subdev->index);
-		if (WARN_ON(!sec2->addr))
-			return -EINVAL;
+	flush_work(&sec2->work);
+
+	if (suspend) {
+		nvkm_falcon_cmdq_fini(sec2->cmdq);
+		sec2->initmsg_received = false;
 	}
 
-	return nvkm_falcon_v1_new(subdev, "SEC2", sec2->addr, &sec2->falcon);
+	return 0;
 }
 
-static int
-nvkm_sec2_fini(struct nvkm_engine *engine, bool suspend)
+static void *
+nvkm_sec2_dtor(struct nvkm_engine *engine)
 {
 	struct nvkm_sec2 *sec2 = nvkm_sec2(engine);
-	flush_work(&sec2->work);
-	return 0;
+	nvkm_falcon_msgq_del(&sec2->msgq);
+	nvkm_falcon_cmdq_del(&sec2->cmdq);
+	nvkm_falcon_qmgr_del(&sec2->qmgr);
+	nvkm_falcon_dtor(&sec2->falcon);
+	return sec2;
 }
 
 static const struct nvkm_engine_func
 nvkm_sec2 = {
 	.dtor = nvkm_sec2_dtor,
-	.oneinit = nvkm_sec2_oneinit,
 	.fini = nvkm_sec2_fini,
 	.intr = nvkm_sec2_intr,
 };
 
 int
-nvkm_sec2_new_(struct nvkm_device *device, int index, u32 addr,
-	       struct nvkm_sec2 **psec2)
+nvkm_sec2_new_(const struct nvkm_sec2_fwif *fwif, struct nvkm_device *device,
+	       int index, u32 addr, struct nvkm_sec2 **psec2)
 {
 	struct nvkm_sec2 *sec2;
+	int ret;
 
 	if (!(sec2 = *psec2 = kzalloc(sizeof(*sec2), GFP_KERNEL)))
 		return -ENOMEM;
-	sec2->addr = addr;
-	INIT_WORK(&sec2->work, nvkm_sec2_recv);
 
-	return nvkm_engine_ctor(&nvkm_sec2, device, index, true, &sec2->engine);
+	ret = nvkm_engine_ctor(&nvkm_sec2, device, index, true, &sec2->engine);
+	if (ret)
+		return ret;
+
+	fwif = nvkm_firmware_load(&sec2->engine.subdev, fwif, "Sec2", sec2);
+	if (IS_ERR(fwif))
+		return PTR_ERR(fwif);
+
+	sec2->func = fwif->func;
+
+	ret = nvkm_falcon_ctor(sec2->func->flcn, &sec2->engine.subdev,
+			       nvkm_subdev_name[index], addr, &sec2->falcon);
+	if (ret)
+		return ret;
+
+	if ((ret = nvkm_falcon_qmgr_new(&sec2->falcon, &sec2->qmgr)) ||
+	    (ret = nvkm_falcon_cmdq_new(sec2->qmgr, "cmdq", &sec2->cmdq)) ||
+	    (ret = nvkm_falcon_msgq_new(sec2->qmgr, "msgq", &sec2->msgq)))
+		return ret;
+
+	INIT_WORK(&sec2->work, nvkm_sec2_recv);
+	return 0;
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp102.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp102.c
index 858cf27fa010..368f2a0042ff 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp102.c
@@ -19,12 +19,316 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  * DEALINGS IN THE SOFTWARE.
  */
-
 #include "priv.h"
 
+#include <core/memory.h>
+#include <subdev/acr.h>
+#include <subdev/timer.h>
+
+#include <nvfw/flcn.h>
+#include <nvfw/sec2.h>
+
+static int
+gp102_sec2_acr_bootstrap_falcon_callback(void *priv, struct nv_falcon_msg *hdr)
+{
+	struct nv_sec2_acr_bootstrap_falcon_msg *msg =
+		container_of(hdr, typeof(*msg), msg.hdr);
+	struct nvkm_subdev *subdev = priv;
+	const char *name = nvkm_acr_lsf_id(msg->falcon_id);
+
+	if (msg->error_code) {
+		nvkm_error(subdev, "ACR_BOOTSTRAP_FALCON failed for "
+				   "falcon %d [%s]: %08x\n",
+			   msg->falcon_id, name, msg->error_code);
+		return -EINVAL;
+	}
+
+	nvkm_debug(subdev, "%s booted\n", name);
+	return 0;
+}
+
+static int
+gp102_sec2_acr_bootstrap_falcon(struct nvkm_falcon *falcon,
+			        enum nvkm_acr_lsf_id id)
+{
+	struct nvkm_sec2 *sec2 = container_of(falcon, typeof(*sec2), falcon);
+	struct nv_sec2_acr_bootstrap_falcon_cmd cmd = {
+		.cmd.hdr.unit_id = sec2->func->unit_acr,
+		.cmd.hdr.size = sizeof(cmd),
+		.cmd.cmd_type = NV_SEC2_ACR_CMD_BOOTSTRAP_FALCON,
+		.flags = NV_SEC2_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_YES,
+		.falcon_id = id,
+	};
+
+	return nvkm_falcon_cmdq_send(sec2->cmdq, &cmd.cmd.hdr,
+				     gp102_sec2_acr_bootstrap_falcon_callback,
+				     &sec2->engine.subdev,
+				     msecs_to_jiffies(1000));
+}
+
+static int
+gp102_sec2_acr_boot(struct nvkm_falcon *falcon)
+{
+	struct nv_sec2_args args = {};
+	nvkm_falcon_load_dmem(falcon, &args,
+			      falcon->func->emem_addr, sizeof(args), 0);
+	nvkm_falcon_start(falcon);
+	return 0;
+}
+
+static void
+gp102_sec2_acr_bld_patch(struct nvkm_acr *acr, u32 bld, s64 adjust)
+{
+	struct loader_config_v1 hdr;
+	nvkm_robj(acr->wpr, bld, &hdr, sizeof(hdr));
+	hdr.code_dma_base = hdr.code_dma_base + adjust;
+	hdr.data_dma_base = hdr.data_dma_base + adjust;
+	hdr.overlay_dma_base = hdr.overlay_dma_base + adjust;
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+	loader_config_v1_dump(&acr->subdev, &hdr);
+}
+
+static void
+gp102_sec2_acr_bld_write(struct nvkm_acr *acr, u32 bld,
+			 struct nvkm_acr_lsfw *lsfw)
+{
+	const struct loader_config_v1 hdr = {
+		.dma_idx = FALCON_SEC2_DMAIDX_UCODE,
+		.code_dma_base = lsfw->offset.img + lsfw->app_start_offset,
+		.code_size_total = lsfw->app_size,
+		.code_size_to_load = lsfw->app_resident_code_size,
+		.code_entry_point = lsfw->app_imem_entry,
+		.data_dma_base = lsfw->offset.img + lsfw->app_start_offset +
+				 lsfw->app_resident_data_offset,
+		.data_size = lsfw->app_resident_data_size,
+		.overlay_dma_base = lsfw->offset.img + lsfw->app_start_offset,
+		.argc = 1,
+		.argv = lsfw->falcon->func->emem_addr,
+	};
+
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+}
+
+static const struct nvkm_acr_lsf_func
+gp102_sec2_acr_0 = {
+	.bld_size = sizeof(struct loader_config_v1),
+	.bld_write = gp102_sec2_acr_bld_write,
+	.bld_patch = gp102_sec2_acr_bld_patch,
+	.boot = gp102_sec2_acr_boot,
+	.bootstrap_falcon = gp102_sec2_acr_bootstrap_falcon,
+};
+
+int
+gp102_sec2_initmsg(struct nvkm_sec2 *sec2)
+{
+	struct nv_sec2_init_msg msg;
+	int ret, i;
+
+	ret = nvkm_falcon_msgq_recv_initmsg(sec2->msgq, &msg, sizeof(msg));
+	if (ret)
+		return ret;
+
+	if (msg.hdr.unit_id != NV_SEC2_UNIT_INIT ||
+	    msg.msg_type != NV_SEC2_INIT_MSG_INIT)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(msg.queue_info); i++) {
+		if (msg.queue_info[i].id == NV_SEC2_INIT_MSG_QUEUE_ID_MSGQ) {
+			nvkm_falcon_msgq_init(sec2->msgq,
+					      msg.queue_info[i].index,
+					      msg.queue_info[i].offset,
+					      msg.queue_info[i].size);
+		} else {
+			nvkm_falcon_cmdq_init(sec2->cmdq,
+					      msg.queue_info[i].index,
+					      msg.queue_info[i].offset,
+					      msg.queue_info[i].size);
+		}
+	}
+
+	return 0;
+}
+
+void
+gp102_sec2_intr(struct nvkm_sec2 *sec2)
+{
+	struct nvkm_subdev *subdev = &sec2->engine.subdev;
+	struct nvkm_falcon *falcon = &sec2->falcon;
+	u32 disp = nvkm_falcon_rd32(falcon, 0x01c);
+	u32 intr = nvkm_falcon_rd32(falcon, 0x008) & disp & ~(disp >> 16);
+
+	if (intr & 0x00000040) {
+		schedule_work(&sec2->work);
+		nvkm_falcon_wr32(falcon, 0x004, 0x00000040);
+		intr &= ~0x00000040;
+	}
+
+	if (intr) {
+		nvkm_error(subdev, "unhandled intr %08x\n", intr);
+		nvkm_falcon_wr32(falcon, 0x004, intr);
+	}
+}
+
+int
+gp102_sec2_flcn_enable(struct nvkm_falcon *falcon)
+{
+	nvkm_falcon_mask(falcon, 0x3c0, 0x00000001, 0x00000001);
+	udelay(10);
+	nvkm_falcon_mask(falcon, 0x3c0, 0x00000001, 0x00000000);
+	return nvkm_falcon_v1_enable(falcon);
+}
+
+void
+gp102_sec2_flcn_bind_context(struct nvkm_falcon *falcon,
+			     struct nvkm_memory *ctx)
+{
+	struct nvkm_device *device = falcon->owner->device;
+
+	nvkm_falcon_v1_bind_context(falcon, ctx);
+	if (!ctx)
+		return;
+
+	/* Not sure if this is a WAR for a HW issue, or some additional
+	 * programming sequence that's needed to properly complete the
+	 * context switch we trigger above.
+	 *
+	 * Fixes unreliability of booting the SEC2 RTOS on Quadro P620,
+	 * particularly when resuming from suspend.
+	 *
+	 * Also removes the need for an odd workaround where we needed
+	 * to program SEC2's FALCON_CPUCTL_ALIAS_STARTCPU twice before
+	 * the SEC2 RTOS would begin executing.
+	 */
+	nvkm_msec(device, 10,
+		u32 irqstat = nvkm_falcon_rd32(falcon, 0x008);
+		u32 flcn0dc = nvkm_falcon_rd32(falcon, 0x0dc);
+		if ((irqstat & 0x00000008) &&
+		    (flcn0dc & 0x00007000) == 0x00005000)
+			break;
+	);
+
+	nvkm_falcon_mask(falcon, 0x004, 0x00000008, 0x00000008);
+	nvkm_falcon_mask(falcon, 0x058, 0x00000002, 0x00000002);
+
+	nvkm_msec(device, 10,
+		u32 flcn0dc = nvkm_falcon_rd32(falcon, 0x0dc);
+		if ((flcn0dc & 0x00007000) == 0x00000000)
+			break;
+	);
+}
+
+static const struct nvkm_falcon_func
+gp102_sec2_flcn = {
+	.debug = 0x408,
+	.fbif = 0x600,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.emem_addr = 0x01000000,
+	.bind_context = gp102_sec2_flcn_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = gp102_sec2_flcn_enable,
+	.disable = nvkm_falcon_v1_disable,
+	.cmdq = { 0xa00, 0xa04, 8 },
+	.msgq = { 0xa30, 0xa34, 8 },
+};
+
+const struct nvkm_sec2_func
+gp102_sec2 = {
+	.flcn = &gp102_sec2_flcn,
+	.unit_acr = NV_SEC2_UNIT_ACR,
+	.intr = gp102_sec2_intr,
+	.initmsg = gp102_sec2_initmsg,
+};
+
+MODULE_FIRMWARE("nvidia/gp102/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/sig.bin");
+
+static void
+gp102_sec2_acr_bld_patch_1(struct nvkm_acr *acr, u32 bld, s64 adjust)
+{
+	struct flcn_bl_dmem_desc_v2 hdr;
+	nvkm_robj(acr->wpr, bld, &hdr, sizeof(hdr));
+	hdr.code_dma_base = hdr.code_dma_base + adjust;
+	hdr.data_dma_base = hdr.data_dma_base + adjust;
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+	flcn_bl_dmem_desc_v2_dump(&acr->subdev, &hdr);
+}
+
+static void
+gp102_sec2_acr_bld_write_1(struct nvkm_acr *acr, u32 bld,
+			   struct nvkm_acr_lsfw *lsfw)
+{
+	const struct flcn_bl_dmem_desc_v2 hdr = {
+		.ctx_dma = FALCON_SEC2_DMAIDX_UCODE,
+		.code_dma_base = lsfw->offset.img + lsfw->app_start_offset,
+		.non_sec_code_off = lsfw->app_resident_code_offset,
+		.non_sec_code_size = lsfw->app_resident_code_size,
+		.code_entry_point = lsfw->app_imem_entry,
+		.data_dma_base = lsfw->offset.img + lsfw->app_start_offset +
+				 lsfw->app_resident_data_offset,
+		.data_size = lsfw->app_resident_data_size,
+		.argc = 1,
+		.argv = lsfw->falcon->func->emem_addr,
+	};
+
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+}
+
+const struct nvkm_acr_lsf_func
+gp102_sec2_acr_1 = {
+	.bld_size = sizeof(struct flcn_bl_dmem_desc_v2),
+	.bld_write = gp102_sec2_acr_bld_write_1,
+	.bld_patch = gp102_sec2_acr_bld_patch_1,
+	.boot = gp102_sec2_acr_boot,
+	.bootstrap_falcon = gp102_sec2_acr_bootstrap_falcon,
+};
+
+int
+gp102_sec2_load(struct nvkm_sec2 *sec2, int ver,
+		const struct nvkm_sec2_fwif *fwif)
+{
+	return nvkm_acr_lsfw_load_sig_image_desc_v1(&sec2->engine.subdev,
+						    &sec2->falcon,
+						    NVKM_ACR_LSF_SEC2, "sec2/",
+						    ver, fwif->acr);
+}
+
+MODULE_FIRMWARE("nvidia/gp102/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/sig-1.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/sig-1.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/sig-1.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/sig-1.bin");
+
+static const struct nvkm_sec2_fwif
+gp102_sec2_fwif[] = {
+	{ 1, gp102_sec2_load, &gp102_sec2, &gp102_sec2_acr_1 },
+	{ 0, gp102_sec2_load, &gp102_sec2, &gp102_sec2_acr_0 },
+	{}
+};
+
 int
-gp102_sec2_new(struct nvkm_device *device, int index,
-	       struct nvkm_sec2 **psec2)
+gp102_sec2_new(struct nvkm_device *device, int index, struct nvkm_sec2 **psec2)
 {
-	return nvkm_sec2_new_(device, index, 0, psec2);
+	return nvkm_sec2_new_(gp102_sec2_fwif, device, index, 0, psec2);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c
new file mode 100644
index 000000000000..232a9d7c51e5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/gp108.c
@@ -0,0 +1,39 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+#include <subdev/acr.h>
+
+MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin");
+MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin");
+
+static const struct nvkm_sec2_fwif
+gp108_sec2_fwif[] = {
+	{ 0, gp102_sec2_load, &gp102_sec2, &gp102_sec2_acr_1 },
+	{}
+};
+
+int
+gp108_sec2_new(struct nvkm_device *device, int index, struct nvkm_sec2 **psec2)
+{
+	return nvkm_sec2_new_(gp108_sec2_fwif, device, index, 0, psec2);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/priv.h
index b331b00517e6..bb88117e018a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/priv.h
@@ -3,7 +3,27 @@
 #define __NVKM_SEC2_PRIV_H__
 #include <engine/sec2.h>
 
-#define nvkm_sec2(p) container_of((p), struct nvkm_sec2, engine)
+struct nvkm_sec2_func {
+	const struct nvkm_falcon_func *flcn;
+	u8 unit_acr;
+	void (*intr)(struct nvkm_sec2 *);
+	int (*initmsg)(struct nvkm_sec2 *);
+};
 
-int nvkm_sec2_new_(struct nvkm_device *, int, u32 addr, struct nvkm_sec2 **);
+void gp102_sec2_intr(struct nvkm_sec2 *);
+int gp102_sec2_initmsg(struct nvkm_sec2 *);
+
+struct nvkm_sec2_fwif {
+	int version;
+	int (*load)(struct nvkm_sec2 *, int ver, const struct nvkm_sec2_fwif *);
+	const struct nvkm_sec2_func *func;
+	const struct nvkm_acr_lsf_func *acr;
+};
+
+int gp102_sec2_load(struct nvkm_sec2 *, int, const struct nvkm_sec2_fwif *);
+extern const struct nvkm_sec2_func gp102_sec2;
+extern const struct nvkm_acr_lsf_func gp102_sec2_acr_1;
+
+int nvkm_sec2_new_(const struct nvkm_sec2_fwif *, struct nvkm_device *,
+		   int, u32 addr, struct nvkm_sec2 **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c
index d655576164b1..b6ebd95c9ba1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/sec2/tu102.c
@@ -19,15 +19,54 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
 #include "priv.h"
+#include <subdev/acr.h>
+
+static const struct nvkm_falcon_func
+tu102_sec2_flcn = {
+	.debug = 0x408,
+	.fbif = 0x600,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.emem_addr = 0x01000000,
+	.bind_context = gp102_sec2_flcn_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = nvkm_falcon_v1_enable,
+	.disable = nvkm_falcon_v1_disable,
+	.cmdq = { 0xc00, 0xc04, 8 },
+	.msgq = { 0xc80, 0xc84, 8 },
+};
+
+static const struct nvkm_sec2_func
+tu102_sec2 = {
+	.flcn = &tu102_sec2_flcn,
+	.unit_acr = 0x07,
+	.intr = gp102_sec2_intr,
+	.initmsg = gp102_sec2_initmsg,
+};
+
+static int
+tu102_sec2_nofw(struct nvkm_sec2 *sec2, int ver,
+		const struct nvkm_sec2_fwif *fwif)
+{
+	return 0;
+}
+
+static const struct nvkm_sec2_fwif
+tu102_sec2_fwif[] = {
+	{  0, gp102_sec2_load, &tu102_sec2, &gp102_sec2_acr_1 },
+	{ -1, tu102_sec2_nofw, &tu102_sec2 }
+};
 
 int
-tu102_sec2_new(struct nvkm_device *device, int index,
-	       struct nvkm_sec2 **psec2)
+tu102_sec2_new(struct nvkm_device *device, int index, struct nvkm_sec2 **psec2)
 {
 	/* TOP info wasn't updated on Turing to reflect the PRI
 	 * address change for some reason.  We override it here.
 	 */
-	return nvkm_sec2_new_(device, index, 0x840000, psec2);
+	return nvkm_sec2_new_(tu102_sec2_fwif, device, index, 0x840000, psec2);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild b/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild
index b5665ada850a..d79d783904ee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/Kbuild
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: MIT
 nvkm-y += nvkm/falcon/base.o
+nvkm-y += nvkm/falcon/cmdq.o
+nvkm-y += nvkm/falcon/msgq.o
+nvkm-y += nvkm/falcon/qmgr.o
 nvkm-y += nvkm/falcon/v1.o
-nvkm-y += nvkm/falcon/msgqueue.o
-nvkm-y += nvkm/falcon/msgqueue_0137c63d.o
-nvkm-y += nvkm/falcon/msgqueue_0148cdec.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/base.c b/drivers/gpu/drm/nouveau/nvkm/falcon/base.c
index 366c87de6e72..c6a3448180d6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/base.c
@@ -22,6 +22,7 @@
 #include "priv.h"
 
 #include <subdev/mc.h>
+#include <subdev/top.h>
 
 void
 nvkm_falcon_load_imem(struct nvkm_falcon *falcon, void *data, u32 start,
@@ -134,6 +135,37 @@ nvkm_falcon_clear_interrupt(struct nvkm_falcon *falcon, u32 mask)
 	return falcon->func->clear_interrupt(falcon, mask);
 }
 
+static int
+nvkm_falcon_oneinit(struct nvkm_falcon *falcon)
+{
+	const struct nvkm_falcon_func *func = falcon->func;
+	const struct nvkm_subdev *subdev = falcon->owner;
+	u32 reg;
+
+	if (!falcon->addr) {
+		falcon->addr = nvkm_top_addr(subdev->device, subdev->index);
+		if (WARN_ON(!falcon->addr))
+			return -ENODEV;
+	}
+
+	reg = nvkm_falcon_rd32(falcon, 0x12c);
+	falcon->version = reg & 0xf;
+	falcon->secret = (reg >> 4) & 0x3;
+	falcon->code.ports = (reg >> 8) & 0xf;
+	falcon->data.ports = (reg >> 12) & 0xf;
+
+	reg = nvkm_falcon_rd32(falcon, 0x108);
+	falcon->code.limit = (reg & 0x1ff) << 8;
+	falcon->data.limit = (reg & 0x3fe00) >> 1;
+
+	if (func->debug) {
+		u32 val = nvkm_falcon_rd32(falcon, func->debug);
+		falcon->debug = (val >> 20) & 0x1;
+	}
+
+	return 0;
+}
+
 void
 nvkm_falcon_put(struct nvkm_falcon *falcon, const struct nvkm_subdev *user)
 {
@@ -151,6 +183,8 @@ nvkm_falcon_put(struct nvkm_falcon *falcon, const struct nvkm_subdev *user)
 int
 nvkm_falcon_get(struct nvkm_falcon *falcon, const struct nvkm_subdev *user)
 {
+	int ret = 0;
+
 	mutex_lock(&falcon->mutex);
 	if (falcon->user) {
 		nvkm_error(user, "%s falcon already acquired by %s!\n",
@@ -160,70 +194,37 @@ nvkm_falcon_get(struct nvkm_falcon *falcon, const struct nvkm_subdev *user)
 	}
 
 	nvkm_debug(user, "acquired %s falcon\n", falcon->name);
+	if (!falcon->oneinit)
+		ret = nvkm_falcon_oneinit(falcon);
 	falcon->user = user;
 	mutex_unlock(&falcon->mutex);
-	return 0;
+	return ret;
 }
 
 void
+nvkm_falcon_dtor(struct nvkm_falcon *falcon)
+{
+}
+
+int
 nvkm_falcon_ctor(const struct nvkm_falcon_func *func,
 		 struct nvkm_subdev *subdev, const char *name, u32 addr,
 		 struct nvkm_falcon *falcon)
 {
-	u32 debug_reg;
-	u32 reg;
-
 	falcon->func = func;
 	falcon->owner = subdev;
 	falcon->name = name;
 	falcon->addr = addr;
 	mutex_init(&falcon->mutex);
 	mutex_init(&falcon->dmem_mutex);
-
-	reg = nvkm_falcon_rd32(falcon, 0x12c);
-	falcon->version = reg & 0xf;
-	falcon->secret = (reg >> 4) & 0x3;
-	falcon->code.ports = (reg >> 8) & 0xf;
-	falcon->data.ports = (reg >> 12) & 0xf;
-
-	reg = nvkm_falcon_rd32(falcon, 0x108);
-	falcon->code.limit = (reg & 0x1ff) << 8;
-	falcon->data.limit = (reg & 0x3fe00) >> 1;
-
-	switch (subdev->index) {
-	case NVKM_ENGINE_GR:
-		debug_reg = 0x0;
-		break;
-	case NVKM_SUBDEV_PMU:
-		debug_reg = 0xc08;
-		break;
-	case NVKM_ENGINE_NVDEC0:
-		debug_reg = 0xd00;
-		break;
-	case NVKM_ENGINE_SEC2:
-		debug_reg = 0x408;
-		falcon->has_emem = true;
-		break;
-	case NVKM_SUBDEV_GSP:
-		debug_reg = 0x0; /*XXX*/
-		break;
-	default:
-		nvkm_warn(subdev, "unsupported falcon %s!\n",
-			  nvkm_subdev_name[subdev->index]);
-		debug_reg = 0;
-		break;
-	}
-
-	if (debug_reg) {
-		u32 val = nvkm_falcon_rd32(falcon, debug_reg);
-		falcon->debug = (val >> 20) & 0x1;
-	}
+	return 0;
 }
 
 void
 nvkm_falcon_del(struct nvkm_falcon **pfalcon)
 {
 	if (*pfalcon) {
+		nvkm_falcon_dtor(*pfalcon);
 		kfree(*pfalcon);
 		*pfalcon = NULL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/cmdq.c b/drivers/gpu/drm/nouveau/nvkm/falcon/cmdq.c
new file mode 100644
index 000000000000..40e3f3fc83ef
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/cmdq.c
@@ -0,0 +1,214 @@
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "qmgr.h"
+
+static bool
+nvkm_falcon_cmdq_has_room(struct nvkm_falcon_cmdq *cmdq, u32 size, bool *rewind)
+{
+	u32 head = nvkm_falcon_rd32(cmdq->qmgr->falcon, cmdq->head_reg);
+	u32 tail = nvkm_falcon_rd32(cmdq->qmgr->falcon, cmdq->tail_reg);
+	u32 free;
+
+	size = ALIGN(size, QUEUE_ALIGNMENT);
+
+	if (head >= tail) {
+		free = cmdq->offset + cmdq->size - head;
+		free -= HDR_SIZE;
+
+		if (size > free) {
+			*rewind = true;
+			head = cmdq->offset;
+		}
+	}
+
+	if (head < tail)
+		free = tail - head - 1;
+
+	return size <= free;
+}
+
+static void
+nvkm_falcon_cmdq_push(struct nvkm_falcon_cmdq *cmdq, void *data, u32 size)
+{
+	struct nvkm_falcon *falcon = cmdq->qmgr->falcon;
+	nvkm_falcon_load_dmem(falcon, data, cmdq->position, size, 0);
+	cmdq->position += ALIGN(size, QUEUE_ALIGNMENT);
+}
+
+static void
+nvkm_falcon_cmdq_rewind(struct nvkm_falcon_cmdq *cmdq)
+{
+	struct nv_falcon_cmd cmd;
+
+	cmd.unit_id = NV_FALCON_CMD_UNIT_ID_REWIND;
+	cmd.size = sizeof(cmd);
+	nvkm_falcon_cmdq_push(cmdq, &cmd, cmd.size);
+
+	cmdq->position = cmdq->offset;
+}
+
+static int
+nvkm_falcon_cmdq_open(struct nvkm_falcon_cmdq *cmdq, u32 size)
+{
+	struct nvkm_falcon *falcon = cmdq->qmgr->falcon;
+	bool rewind = false;
+
+	mutex_lock(&cmdq->mutex);
+
+	if (!nvkm_falcon_cmdq_has_room(cmdq, size, &rewind)) {
+		FLCNQ_DBG(cmdq, "queue full");
+		mutex_unlock(&cmdq->mutex);
+		return -EAGAIN;
+	}
+
+	cmdq->position = nvkm_falcon_rd32(falcon, cmdq->head_reg);
+
+	if (rewind)
+		nvkm_falcon_cmdq_rewind(cmdq);
+
+	return 0;
+}
+
+static void
+nvkm_falcon_cmdq_close(struct nvkm_falcon_cmdq *cmdq)
+{
+	nvkm_falcon_wr32(cmdq->qmgr->falcon, cmdq->head_reg, cmdq->position);
+	mutex_unlock(&cmdq->mutex);
+}
+
+static int
+nvkm_falcon_cmdq_write(struct nvkm_falcon_cmdq *cmdq, struct nv_falcon_cmd *cmd)
+{
+	static unsigned timeout = 2000;
+	unsigned long end_jiffies = jiffies + msecs_to_jiffies(timeout);
+	int ret = -EAGAIN;
+
+	while (ret == -EAGAIN && time_before(jiffies, end_jiffies))
+		ret = nvkm_falcon_cmdq_open(cmdq, cmd->size);
+	if (ret) {
+		FLCNQ_ERR(cmdq, "timeout waiting for queue space");
+		return ret;
+	}
+
+	nvkm_falcon_cmdq_push(cmdq, cmd, cmd->size);
+	nvkm_falcon_cmdq_close(cmdq);
+	return ret;
+}
+
+/* specifies that we want to know the command status in the answer message */
+#define CMD_FLAGS_STATUS BIT(0)
+/* specifies that we want an interrupt when the answer message is queued */
+#define CMD_FLAGS_INTR BIT(1)
+
+int
+nvkm_falcon_cmdq_send(struct nvkm_falcon_cmdq *cmdq, struct nv_falcon_cmd *cmd,
+		      nvkm_falcon_qmgr_callback cb, void *priv,
+		      unsigned long timeout)
+{
+	struct nvkm_falcon_qmgr_seq *seq;
+	int ret;
+
+	if (!wait_for_completion_timeout(&cmdq->ready,
+					 msecs_to_jiffies(1000))) {
+		FLCNQ_ERR(cmdq, "timeout waiting for queue ready");
+		return -ETIMEDOUT;
+	}
+
+	seq = nvkm_falcon_qmgr_seq_acquire(cmdq->qmgr);
+	if (IS_ERR(seq))
+		return PTR_ERR(seq);
+
+	cmd->seq_id = seq->id;
+	cmd->ctrl_flags = CMD_FLAGS_STATUS | CMD_FLAGS_INTR;
+
+	seq->state = SEQ_STATE_USED;
+	seq->async = !timeout;
+	seq->callback = cb;
+	seq->priv = priv;
+
+	ret = nvkm_falcon_cmdq_write(cmdq, cmd);
+	if (ret) {
+		seq->state = SEQ_STATE_PENDING;
+		nvkm_falcon_qmgr_seq_release(cmdq->qmgr, seq);
+		return ret;
+	}
+
+	if (!seq->async) {
+		if (!wait_for_completion_timeout(&seq->done, timeout)) {
+			FLCNQ_ERR(cmdq, "timeout waiting for reply");
+			return -ETIMEDOUT;
+		}
+		ret = seq->result;
+		nvkm_falcon_qmgr_seq_release(cmdq->qmgr, seq);
+	}
+
+	return ret;
+}
+
+void
+nvkm_falcon_cmdq_fini(struct nvkm_falcon_cmdq *cmdq)
+{
+	reinit_completion(&cmdq->ready);
+}
+
+void
+nvkm_falcon_cmdq_init(struct nvkm_falcon_cmdq *cmdq,
+		      u32 index, u32 offset, u32 size)
+{
+	const struct nvkm_falcon_func *func = cmdq->qmgr->falcon->func;
+
+	cmdq->head_reg = func->cmdq.head + index * func->cmdq.stride;
+	cmdq->tail_reg = func->cmdq.tail + index * func->cmdq.stride;
+	cmdq->offset = offset;
+	cmdq->size = size;
+	complete_all(&cmdq->ready);
+
+	FLCNQ_DBG(cmdq, "initialised @ index %d offset 0x%08x size 0x%08x",
+		  index, cmdq->offset, cmdq->size);
+}
+
+void
+nvkm_falcon_cmdq_del(struct nvkm_falcon_cmdq **pcmdq)
+{
+	struct nvkm_falcon_cmdq *cmdq = *pcmdq;
+	if (cmdq) {
+		kfree(*pcmdq);
+		*pcmdq = NULL;
+	}
+}
+
+int
+nvkm_falcon_cmdq_new(struct nvkm_falcon_qmgr *qmgr, const char *name,
+		     struct nvkm_falcon_cmdq **pcmdq)
+{
+	struct nvkm_falcon_cmdq *cmdq = *pcmdq;
+
+	if (!(cmdq = *pcmdq = kzalloc(sizeof(*cmdq), GFP_KERNEL)))
+		return -ENOMEM;
+
+	cmdq->qmgr = qmgr;
+	cmdq->name = name;
+	mutex_init(&cmdq->mutex);
+	init_completion(&cmdq->ready);
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgq.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgq.c
new file mode 100644
index 000000000000..cbfe09a561a1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/msgq.c
@@ -0,0 +1,213 @@
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "qmgr.h"
+
+static void
+nvkm_falcon_msgq_open(struct nvkm_falcon_msgq *msgq)
+{
+	mutex_lock(&msgq->mutex);
+	msgq->position = nvkm_falcon_rd32(msgq->qmgr->falcon, msgq->tail_reg);
+}
+
+static void
+nvkm_falcon_msgq_close(struct nvkm_falcon_msgq *msgq, bool commit)
+{
+	struct nvkm_falcon *falcon = msgq->qmgr->falcon;
+
+	if (commit)
+		nvkm_falcon_wr32(falcon, msgq->tail_reg, msgq->position);
+
+	mutex_unlock(&msgq->mutex);
+}
+
+static bool
+nvkm_falcon_msgq_empty(struct nvkm_falcon_msgq *msgq)
+{
+	u32 head = nvkm_falcon_rd32(msgq->qmgr->falcon, msgq->head_reg);
+	u32 tail = nvkm_falcon_rd32(msgq->qmgr->falcon, msgq->tail_reg);
+	return head == tail;
+}
+
+static int
+nvkm_falcon_msgq_pop(struct nvkm_falcon_msgq *msgq, void *data, u32 size)
+{
+	struct nvkm_falcon *falcon = msgq->qmgr->falcon;
+	u32 head, tail, available;
+
+	head = nvkm_falcon_rd32(falcon, msgq->head_reg);
+	/* has the buffer looped? */
+	if (head < msgq->position)
+		msgq->position = msgq->offset;
+
+	tail = msgq->position;
+
+	available = head - tail;
+	if (size > available) {
+		FLCNQ_ERR(msgq, "requested %d bytes, but only %d available",
+			  size, available);
+		return -EINVAL;
+	}
+
+	nvkm_falcon_read_dmem(falcon, tail, size, 0, data);
+	msgq->position += ALIGN(size, QUEUE_ALIGNMENT);
+	return 0;
+}
+
+static int
+nvkm_falcon_msgq_read(struct nvkm_falcon_msgq *msgq, struct nv_falcon_msg *hdr)
+{
+	int ret = 0;
+
+	nvkm_falcon_msgq_open(msgq);
+
+	if (nvkm_falcon_msgq_empty(msgq))
+		goto close;
+
+	ret = nvkm_falcon_msgq_pop(msgq, hdr, HDR_SIZE);
+	if (ret) {
+		FLCNQ_ERR(msgq, "failed to read message header");
+		goto close;
+	}
+
+	if (hdr->size > MSG_BUF_SIZE) {
+		FLCNQ_ERR(msgq, "message too big, %d bytes", hdr->size);
+		ret = -ENOSPC;
+		goto close;
+	}
+
+	if (hdr->size > HDR_SIZE) {
+		u32 read_size = hdr->size - HDR_SIZE;
+
+		ret = nvkm_falcon_msgq_pop(msgq, (hdr + 1), read_size);
+		if (ret) {
+			FLCNQ_ERR(msgq, "failed to read message data");
+			goto close;
+		}
+	}
+
+	ret = 1;
+close:
+	nvkm_falcon_msgq_close(msgq, (ret >= 0));
+	return ret;
+}
+
+static int
+nvkm_falcon_msgq_exec(struct nvkm_falcon_msgq *msgq, struct nv_falcon_msg *hdr)
+{
+	struct nvkm_falcon_qmgr_seq *seq;
+
+	seq = &msgq->qmgr->seq.id[hdr->seq_id];
+	if (seq->state != SEQ_STATE_USED && seq->state != SEQ_STATE_CANCELLED) {
+		FLCNQ_ERR(msgq, "message for unknown sequence %08x", seq->id);
+		return -EINVAL;
+	}
+
+	if (seq->state == SEQ_STATE_USED) {
+		if (seq->callback)
+			seq->result = seq->callback(seq->priv, hdr);
+	}
+
+	if (seq->async) {
+		nvkm_falcon_qmgr_seq_release(msgq->qmgr, seq);
+		return 0;
+	}
+
+	complete_all(&seq->done);
+	return 0;
+}
+
+void
+nvkm_falcon_msgq_recv(struct nvkm_falcon_msgq *msgq)
+{
+	/*
+	 * We are invoked from a worker thread, so normally we have plenty of
+	 * stack space to work with.
+	 */
+	u8 msg_buffer[MSG_BUF_SIZE];
+	struct nv_falcon_msg *hdr = (void *)msg_buffer;
+
+	while (nvkm_falcon_msgq_read(msgq, hdr) > 0)
+		nvkm_falcon_msgq_exec(msgq, hdr);
+}
+
+int
+nvkm_falcon_msgq_recv_initmsg(struct nvkm_falcon_msgq *msgq,
+			      void *data, u32 size)
+{
+	struct nvkm_falcon *falcon = msgq->qmgr->falcon;
+	struct nv_falcon_msg *hdr = data;
+	int ret;
+
+	msgq->head_reg = falcon->func->msgq.head;
+	msgq->tail_reg = falcon->func->msgq.tail;
+	msgq->offset = nvkm_falcon_rd32(falcon, falcon->func->msgq.tail);
+
+	nvkm_falcon_msgq_open(msgq);
+	ret = nvkm_falcon_msgq_pop(msgq, data, size);
+	if (ret == 0 && hdr->size != size) {
+		FLCN_ERR(falcon, "unexpected init message size %d vs %d",
+			 hdr->size, size);
+		ret = -EINVAL;
+	}
+	nvkm_falcon_msgq_close(msgq, ret == 0);
+	return ret;
+}
+
+void
+nvkm_falcon_msgq_init(struct nvkm_falcon_msgq *msgq,
+		      u32 index, u32 offset, u32 size)
+{
+	const struct nvkm_falcon_func *func = msgq->qmgr->falcon->func;
+
+	msgq->head_reg = func->msgq.head + index * func->msgq.stride;
+	msgq->tail_reg = func->msgq.tail + index * func->msgq.stride;
+	msgq->offset = offset;
+
+	FLCNQ_DBG(msgq, "initialised @ index %d offset 0x%08x size 0x%08x",
+		  index, msgq->offset, size);
+}
+
+void
+nvkm_falcon_msgq_del(struct nvkm_falcon_msgq **pmsgq)
+{
+	struct nvkm_falcon_msgq *msgq = *pmsgq;
+	if (msgq) {
+		kfree(*pmsgq);
+		*pmsgq = NULL;
+	}
+}
+
+int
+nvkm_falcon_msgq_new(struct nvkm_falcon_qmgr *qmgr, const char *name,
+		     struct nvkm_falcon_msgq **pmsgq)
+{
+	struct nvkm_falcon_msgq *msgq = *pmsgq;
+
+	if (!(msgq = *pmsgq = kzalloc(sizeof(*msgq), GFP_KERNEL)))
+		return -ENOMEM;
+
+	msgq->qmgr = qmgr;
+	msgq->name = name;
+	mutex_init(&msgq->mutex);
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
deleted file mode 100644
index a8bee1e046aa..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.c
+++ /dev/null
@@ -1,577 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include "msgqueue.h"
-#include <engine/falcon.h>
-
-#include <subdev/secboot.h>
-
-
-#define HDR_SIZE sizeof(struct nvkm_msgqueue_hdr)
-#define QUEUE_ALIGNMENT 4
-/* max size of the messages we can receive */
-#define MSG_BUF_SIZE 128
-
-static int
-msg_queue_open(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-
-	mutex_lock(&queue->mutex);
-
-	queue->position = nvkm_falcon_rd32(falcon, queue->tail_reg);
-
-	return 0;
-}
-
-static void
-msg_queue_close(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-		bool commit)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-
-	if (commit)
-		nvkm_falcon_wr32(falcon, queue->tail_reg, queue->position);
-
-	mutex_unlock(&queue->mutex);
-}
-
-static bool
-msg_queue_empty(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-	u32 head, tail;
-
-	head = nvkm_falcon_rd32(falcon, queue->head_reg);
-	tail = nvkm_falcon_rd32(falcon, queue->tail_reg);
-
-	return head == tail;
-}
-
-static int
-msg_queue_pop(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-	      void *data, u32 size)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	u32 head, tail, available;
-
-	head = nvkm_falcon_rd32(falcon, queue->head_reg);
-	/* has the buffer looped? */
-	if (head < queue->position)
-		queue->position = queue->offset;
-
-	tail = queue->position;
-
-	available = head - tail;
-
-	if (available == 0) {
-		nvkm_warn(subdev, "no message data available\n");
-		return 0;
-	}
-
-	if (size > available) {
-		nvkm_warn(subdev, "message data smaller than read request\n");
-		size = available;
-	}
-
-	nvkm_falcon_read_dmem(priv->falcon, tail, size, 0, data);
-	queue->position += ALIGN(size, QUEUE_ALIGNMENT);
-
-	return size;
-}
-
-static int
-msg_queue_read(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-	       struct nvkm_msgqueue_hdr *hdr)
-{
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	int err;
-
-	err = msg_queue_open(priv, queue);
-	if (err) {
-		nvkm_error(subdev, "fail to open queue %d\n", queue->index);
-		return err;
-	}
-
-	if (msg_queue_empty(priv, queue)) {
-		err = 0;
-		goto close;
-	}
-
-	err = msg_queue_pop(priv, queue, hdr, HDR_SIZE);
-	if (err >= 0 && err != HDR_SIZE)
-		err = -EINVAL;
-	if (err < 0) {
-		nvkm_error(subdev, "failed to read message header: %d\n", err);
-		goto close;
-	}
-
-	if (hdr->size > MSG_BUF_SIZE) {
-		nvkm_error(subdev, "message too big (%d bytes)\n", hdr->size);
-		err = -ENOSPC;
-		goto close;
-	}
-
-	if (hdr->size > HDR_SIZE) {
-		u32 read_size = hdr->size - HDR_SIZE;
-
-		err = msg_queue_pop(priv, queue, (hdr + 1), read_size);
-		if (err >= 0 && err != read_size)
-			err = -EINVAL;
-		if (err < 0) {
-			nvkm_error(subdev, "failed to read message: %d\n", err);
-			goto close;
-		}
-	}
-
-close:
-	msg_queue_close(priv, queue, (err >= 0));
-
-	return err;
-}
-
-static bool
-cmd_queue_has_room(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-		   u32 size, bool *rewind)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-	u32 head, tail, free;
-
-	size = ALIGN(size, QUEUE_ALIGNMENT);
-
-	head = nvkm_falcon_rd32(falcon, queue->head_reg);
-	tail = nvkm_falcon_rd32(falcon, queue->tail_reg);
-
-	if (head >= tail) {
-		free = queue->offset + queue->size - head;
-		free -= HDR_SIZE;
-
-		if (size > free) {
-			*rewind = true;
-			head = queue->offset;
-		}
-	}
-
-	if (head < tail)
-		free = tail - head - 1;
-
-	return size <= free;
-}
-
-static int
-cmd_queue_push(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-	       void *data, u32 size)
-{
-	nvkm_falcon_load_dmem(priv->falcon, data, queue->position, size, 0);
-	queue->position += ALIGN(size, QUEUE_ALIGNMENT);
-
-	return 0;
-}
-
-/* REWIND unit is always 0x00 */
-#define MSGQUEUE_UNIT_REWIND 0x00
-
-static void
-cmd_queue_rewind(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue)
-{
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	struct nvkm_msgqueue_hdr cmd;
-	int err;
-
-	cmd.unit_id = MSGQUEUE_UNIT_REWIND;
-	cmd.size = sizeof(cmd);
-	err = cmd_queue_push(priv, queue, &cmd, cmd.size);
-	if (err)
-		nvkm_error(subdev, "queue %d rewind failed\n", queue->index);
-	else
-		nvkm_error(subdev, "queue %d rewinded\n", queue->index);
-
-	queue->position = queue->offset;
-}
-
-static int
-cmd_queue_open(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-	       u32 size)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	bool rewind = false;
-
-	mutex_lock(&queue->mutex);
-
-	if (!cmd_queue_has_room(priv, queue, size, &rewind)) {
-		nvkm_error(subdev, "queue full\n");
-		mutex_unlock(&queue->mutex);
-		return -EAGAIN;
-	}
-
-	queue->position = nvkm_falcon_rd32(falcon, queue->head_reg);
-
-	if (rewind)
-		cmd_queue_rewind(priv, queue);
-
-	return 0;
-}
-
-static void
-cmd_queue_close(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_queue *queue,
-		bool commit)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-
-	if (commit)
-		nvkm_falcon_wr32(falcon, queue->head_reg, queue->position);
-
-	mutex_unlock(&queue->mutex);
-}
-
-static int
-cmd_write(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_hdr *cmd,
-	  struct nvkm_msgqueue_queue *queue)
-{
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	static unsigned timeout = 2000;
-	unsigned long end_jiffies = jiffies + msecs_to_jiffies(timeout);
-	int ret = -EAGAIN;
-	bool commit = true;
-
-	while (ret == -EAGAIN && time_before(jiffies, end_jiffies))
-		ret = cmd_queue_open(priv, queue, cmd->size);
-	if (ret) {
-		nvkm_error(subdev, "pmu_queue_open_write failed\n");
-		return ret;
-	}
-
-	ret = cmd_queue_push(priv, queue, cmd, cmd->size);
-	if (ret) {
-		nvkm_error(subdev, "pmu_queue_push failed\n");
-		commit = false;
-	}
-
-	cmd_queue_close(priv, queue, commit);
-
-	return ret;
-}
-
-static struct nvkm_msgqueue_seq *
-msgqueue_seq_acquire(struct nvkm_msgqueue *priv)
-{
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	struct nvkm_msgqueue_seq *seq;
-	u32 index;
-
-	mutex_lock(&priv->seq_lock);
-
-	index = find_first_zero_bit(priv->seq_tbl, NVKM_MSGQUEUE_NUM_SEQUENCES);
-
-	if (index >= NVKM_MSGQUEUE_NUM_SEQUENCES) {
-		nvkm_error(subdev, "no free sequence available\n");
-		mutex_unlock(&priv->seq_lock);
-		return ERR_PTR(-EAGAIN);
-	}
-
-	set_bit(index, priv->seq_tbl);
-
-	mutex_unlock(&priv->seq_lock);
-
-	seq = &priv->seq[index];
-	seq->state = SEQ_STATE_PENDING;
-
-	return seq;
-}
-
-static void
-msgqueue_seq_release(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_seq *seq)
-{
-	/* no need to acquire seq_lock since clear_bit is atomic */
-	seq->state = SEQ_STATE_FREE;
-	seq->callback = NULL;
-	seq->completion = NULL;
-	clear_bit(seq->id, priv->seq_tbl);
-}
-
-/* specifies that we want to know the command status in the answer message */
-#define CMD_FLAGS_STATUS BIT(0)
-/* specifies that we want an interrupt when the answer message is queued */
-#define CMD_FLAGS_INTR BIT(1)
-
-int
-nvkm_msgqueue_post(struct nvkm_msgqueue *priv, enum msgqueue_msg_priority prio,
-		   struct nvkm_msgqueue_hdr *cmd, nvkm_msgqueue_callback cb,
-		   struct completion *completion, bool wait_init)
-{
-	struct nvkm_msgqueue_seq *seq;
-	struct nvkm_msgqueue_queue *queue;
-	int ret;
-
-	if (wait_init && !wait_for_completion_timeout(&priv->init_done,
-					 msecs_to_jiffies(1000)))
-		return -ETIMEDOUT;
-
-	queue = priv->func->cmd_queue(priv, prio);
-	if (IS_ERR(queue))
-		return PTR_ERR(queue);
-
-	seq = msgqueue_seq_acquire(priv);
-	if (IS_ERR(seq))
-		return PTR_ERR(seq);
-
-	cmd->seq_id = seq->id;
-	cmd->ctrl_flags = CMD_FLAGS_STATUS | CMD_FLAGS_INTR;
-
-	seq->callback = cb;
-	seq->state = SEQ_STATE_USED;
-	seq->completion = completion;
-
-	ret = cmd_write(priv, cmd, queue);
-	if (ret) {
-		seq->state = SEQ_STATE_PENDING;
-		msgqueue_seq_release(priv, seq);
-	}
-
-	return ret;
-}
-
-static int
-msgqueue_msg_handle(struct nvkm_msgqueue *priv, struct nvkm_msgqueue_hdr *hdr)
-{
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	struct nvkm_msgqueue_seq *seq;
-
-	seq = &priv->seq[hdr->seq_id];
-	if (seq->state != SEQ_STATE_USED && seq->state != SEQ_STATE_CANCELLED) {
-		nvkm_error(subdev, "msg for unknown sequence %d", seq->id);
-		return -EINVAL;
-	}
-
-	if (seq->state == SEQ_STATE_USED) {
-		if (seq->callback)
-			seq->callback(priv, hdr);
-	}
-
-	if (seq->completion)
-		complete(seq->completion);
-
-	msgqueue_seq_release(priv, seq);
-
-	return 0;
-}
-
-static int
-msgqueue_handle_init_msg(struct nvkm_msgqueue *priv,
-			 struct nvkm_msgqueue_hdr *hdr)
-{
-	struct nvkm_falcon *falcon = priv->falcon;
-	const struct nvkm_subdev *subdev = falcon->owner;
-	u32 tail;
-	u32 tail_reg;
-	int ret;
-
-	/*
-	 * Of course the message queue registers vary depending on the falcon
-	 * used...
-	 */
-	switch (falcon->owner->index) {
-	case NVKM_SUBDEV_PMU:
-		tail_reg = 0x4cc;
-		break;
-	case NVKM_ENGINE_SEC2:
-		tail_reg = 0xa34;
-		break;
-	default:
-		nvkm_error(subdev, "falcon %s unsupported for msgqueue!\n",
-			   nvkm_subdev_name[falcon->owner->index]);
-		return -EINVAL;
-	}
-
-	/*
-	 * Read the message - queues are not initialized yet so we cannot rely
-	 * on msg_queue_read()
-	 */
-	tail = nvkm_falcon_rd32(falcon, tail_reg);
-	nvkm_falcon_read_dmem(falcon, tail, HDR_SIZE, 0, hdr);
-
-	if (hdr->size > MSG_BUF_SIZE) {
-		nvkm_error(subdev, "message too big (%d bytes)\n", hdr->size);
-		return -ENOSPC;
-	}
-
-	nvkm_falcon_read_dmem(falcon, tail + HDR_SIZE, hdr->size - HDR_SIZE, 0,
-			      (hdr + 1));
-
-	tail += ALIGN(hdr->size, QUEUE_ALIGNMENT);
-	nvkm_falcon_wr32(falcon, tail_reg, tail);
-
-	ret = priv->func->init_func->init_callback(priv, hdr);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-void
-nvkm_msgqueue_process_msgs(struct nvkm_msgqueue *priv,
-			   struct nvkm_msgqueue_queue *queue)
-{
-	/*
-	 * We are invoked from a worker thread, so normally we have plenty of
-	 * stack space to work with.
-	 */
-	u8 msg_buffer[MSG_BUF_SIZE];
-	struct nvkm_msgqueue_hdr *hdr = (void *)msg_buffer;
-	int ret;
-
-	/* the first message we receive must be the init message */
-	if ((!priv->init_msg_received)) {
-		ret = msgqueue_handle_init_msg(priv, hdr);
-		if (!ret)
-			priv->init_msg_received = true;
-	} else {
-		while (msg_queue_read(priv, queue, hdr) > 0)
-			msgqueue_msg_handle(priv, hdr);
-	}
-}
-
-void
-nvkm_msgqueue_write_cmdline(struct nvkm_msgqueue *queue, void *buf)
-{
-	if (!queue || !queue->func || !queue->func->init_func)
-		return;
-
-	queue->func->init_func->gen_cmdline(queue, buf);
-}
-
-int
-nvkm_msgqueue_acr_boot_falcons(struct nvkm_msgqueue *queue,
-			       unsigned long falcon_mask)
-{
-	unsigned long falcon;
-
-	if (!queue || !queue->func->acr_func)
-		return -ENODEV;
-
-	/* Does the firmware support booting multiple falcons? */
-	if (queue->func->acr_func->boot_multiple_falcons)
-		return queue->func->acr_func->boot_multiple_falcons(queue,
-								   falcon_mask);
-
-	/* Else boot all requested falcons individually */
-	if (!queue->func->acr_func->boot_falcon)
-		return -ENODEV;
-
-	for_each_set_bit(falcon, &falcon_mask, NVKM_SECBOOT_FALCON_END) {
-		int ret = queue->func->acr_func->boot_falcon(queue, falcon);
-
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-int
-nvkm_msgqueue_new(u32 version, struct nvkm_falcon *falcon,
-		  const struct nvkm_secboot *sb, struct nvkm_msgqueue **queue)
-{
-	const struct nvkm_subdev *subdev = falcon->owner;
-	int ret = -EINVAL;
-
-	switch (version) {
-	case 0x0137c63d:
-		ret = msgqueue_0137c63d_new(falcon, sb, queue);
-		break;
-	case 0x0137bca5:
-		ret = msgqueue_0137bca5_new(falcon, sb, queue);
-		break;
-	case 0x0148cdec:
-	case 0x015ccf3e:
-	case 0x0167d263:
-		ret = msgqueue_0148cdec_new(falcon, sb, queue);
-		break;
-	default:
-		nvkm_error(subdev, "unhandled firmware version 0x%08x\n",
-			   version);
-		break;
-	}
-
-	if (ret == 0) {
-		nvkm_debug(subdev, "firmware version: 0x%08x\n", version);
-		(*queue)->fw_version = version;
-	}
-
-	return ret;
-}
-
-void
-nvkm_msgqueue_del(struct nvkm_msgqueue **queue)
-{
-	if (*queue) {
-		(*queue)->func->dtor(*queue);
-		*queue = NULL;
-	}
-}
-
-void
-nvkm_msgqueue_recv(struct nvkm_msgqueue *queue)
-{
-	if (!queue->func || !queue->func->recv) {
-		const struct nvkm_subdev *subdev = queue->falcon->owner;
-
-		nvkm_warn(subdev, "missing msgqueue recv function\n");
-		return;
-	}
-
-	queue->func->recv(queue);
-}
-
-int
-nvkm_msgqueue_reinit(struct nvkm_msgqueue *queue)
-{
-	/* firmware not set yet... */
-	if (!queue)
-		return 0;
-
-	queue->init_msg_received = false;
-	reinit_completion(&queue->init_done);
-
-	return 0;
-}
-
-void
-nvkm_msgqueue_ctor(const struct nvkm_msgqueue_func *func,
-		   struct nvkm_falcon *falcon,
-		   struct nvkm_msgqueue *queue)
-{
-	int i;
-
-	queue->func = func;
-	queue->falcon = falcon;
-	mutex_init(&queue->seq_lock);
-	for (i = 0; i < NVKM_MSGQUEUE_NUM_SEQUENCES; i++)
-		queue->seq[i].id = i;
-
-	init_completion(&queue->init_done);
-
-
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.h b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.h
deleted file mode 100644
index 13b54f8d8e04..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue.h
+++ /dev/null
@@ -1,213 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#ifndef __NVKM_CORE_FALCON_MSGQUEUE_H
-#define __NVKM_CORE_FALCON_MSGQUEUE_H
-
-#include <core/msgqueue.h>
-
-/*
- * The struct nvkm_msgqueue (named so for lack of better candidate) manages
- * a firmware (typically, NVIDIA signed firmware) running under a given falcon.
- *
- * Such firmwares expect to receive commands (through one or several command
- * queues) and will reply to such command by sending messages (using one
- * message queue).
- *
- * Each firmware can support one or several units - ACR for managing secure
- * falcons, PMU for power management, etc. A unit can be seen as a class to
- * which command can be sent.
- *
- * One usage example would be to send a command to the SEC falcon to ask it to
- * reset a secure falcon. The SEC falcon will receive the command, process it,
- * and send a message to signal success or failure. Only when the corresponding
- * message is received can the requester assume the request has been processed.
- *
- * Since we expect many variations between the firmwares NVIDIA will release
- * across GPU generations, this library is built in a very modular way. Message
- * formats and queues details (such as number of usage) are left to
- * specializations of struct nvkm_msgqueue, while the functions in msgqueue.c
- * take care of posting commands and processing messages in a fashion that is
- * universal.
- *
- */
-
-enum msgqueue_msg_priority {
-	MSGQUEUE_MSG_PRIORITY_HIGH,
-	MSGQUEUE_MSG_PRIORITY_LOW,
-};
-
-/**
- * struct nvkm_msgqueue_hdr - header for all commands/messages
- * @unit_id:	id of firmware using receiving the command/sending the message
- * @size:	total size of command/message
- * @ctrl_flags:	type of command/message
- * @seq_id:	used to match a message from its corresponding command
- */
-struct nvkm_msgqueue_hdr {
-	u8 unit_id;
-	u8 size;
-	u8 ctrl_flags;
-	u8 seq_id;
-};
-
-/**
- * struct nvkm_msgqueue_msg - base message.
- *
- * This is just a header and a message (or command) type. Useful when
- * building command-specific structures.
- */
-struct nvkm_msgqueue_msg {
-	struct nvkm_msgqueue_hdr hdr;
-	u8 msg_type;
-};
-
-struct nvkm_msgqueue;
-typedef void
-(*nvkm_msgqueue_callback)(struct nvkm_msgqueue *, struct nvkm_msgqueue_hdr *);
-
-/**
- * struct nvkm_msgqueue_init_func - msgqueue functions related to initialization
- *
- * @gen_cmdline:	build the commandline into a pre-allocated buffer
- * @init_callback:	called to process the init message
- */
-struct nvkm_msgqueue_init_func {
-	void (*gen_cmdline)(struct nvkm_msgqueue *, void *);
-	int (*init_callback)(struct nvkm_msgqueue *, struct nvkm_msgqueue_hdr *);
-};
-
-/**
- * struct nvkm_msgqueue_acr_func - msgqueue functions related to ACR
- *
- * @boot_falcon:	build and send the command to reset a given falcon
- * @boot_multiple_falcons: build and send the command to reset several falcons
- */
-struct nvkm_msgqueue_acr_func {
-	int (*boot_falcon)(struct nvkm_msgqueue *, enum nvkm_secboot_falcon);
-	int (*boot_multiple_falcons)(struct nvkm_msgqueue *, unsigned long);
-};
-
-struct nvkm_msgqueue_func {
-	const struct nvkm_msgqueue_init_func *init_func;
-	const struct nvkm_msgqueue_acr_func *acr_func;
-	void (*dtor)(struct nvkm_msgqueue *);
-	struct nvkm_msgqueue_queue *(*cmd_queue)(struct nvkm_msgqueue *,
-						 enum msgqueue_msg_priority);
-	void (*recv)(struct nvkm_msgqueue *queue);
-};
-
-/**
- * struct nvkm_msgqueue_queue - information about a command or message queue
- *
- * The number of queues is firmware-dependent. All queues must have their
- * information filled by the init message handler.
- *
- * @mutex_lock:	to be acquired when the queue is being used
- * @index:	physical queue index
- * @offset:	DMEM offset where this queue begins
- * @size:	size allocated to this queue in DMEM (in bytes)
- * @position:	current write position
- * @head_reg:	address of the HEAD register for this queue
- * @tail_reg:	address of the TAIL register for this queue
- */
-struct nvkm_msgqueue_queue {
-	struct mutex mutex;
-	u32 index;
-	u32 offset;
-	u32 size;
-	u32 position;
-
-	u32 head_reg;
-	u32 tail_reg;
-};
-
-/**
- * struct nvkm_msgqueue_seq - keep track of ongoing commands
- *
- * Every time a command is sent, a sequence is assigned to it so the
- * corresponding message can be matched. Upon receiving the message, a callback
- * can be called and/or a completion signaled.
- *
- * @id:		sequence ID
- * @state:	current state
- * @callback:	callback to call upon receiving matching message
- * @completion:	completion to signal after callback is called
- */
-struct nvkm_msgqueue_seq {
-	u16 id;
-	enum {
-		SEQ_STATE_FREE = 0,
-		SEQ_STATE_PENDING,
-		SEQ_STATE_USED,
-		SEQ_STATE_CANCELLED
-	} state;
-	nvkm_msgqueue_callback callback;
-	struct completion *completion;
-};
-
-/*
- * We can have an arbitrary number of sequences, but realistically we will
- * probably not use that much simultaneously.
- */
-#define NVKM_MSGQUEUE_NUM_SEQUENCES 16
-
-/**
- * struct nvkm_msgqueue - manage a command/message based FW on a falcon
- *
- * @falcon:	falcon to be managed
- * @func:	implementation of the firmware to use
- * @init_msg_received:	whether the init message has already been received
- * @init_done:	whether all init is complete and commands can be processed
- * @seq_lock:	protects seq and seq_tbl
- * @seq:	sequences to match commands and messages
- * @seq_tbl:	bitmap of sequences currently in use
- */
-struct nvkm_msgqueue {
-	struct nvkm_falcon *falcon;
-	const struct nvkm_msgqueue_func *func;
-	u32 fw_version;
-	bool init_msg_received;
-	struct completion init_done;
-
-	struct mutex seq_lock;
-	struct nvkm_msgqueue_seq seq[NVKM_MSGQUEUE_NUM_SEQUENCES];
-	unsigned long seq_tbl[BITS_TO_LONGS(NVKM_MSGQUEUE_NUM_SEQUENCES)];
-};
-
-void nvkm_msgqueue_ctor(const struct nvkm_msgqueue_func *, struct nvkm_falcon *,
-			struct nvkm_msgqueue *);
-int nvkm_msgqueue_post(struct nvkm_msgqueue *, enum msgqueue_msg_priority,
-		       struct nvkm_msgqueue_hdr *, nvkm_msgqueue_callback,
-		       struct completion *, bool);
-void nvkm_msgqueue_process_msgs(struct nvkm_msgqueue *,
-				struct nvkm_msgqueue_queue *);
-
-int msgqueue_0137c63d_new(struct nvkm_falcon *, const struct nvkm_secboot *,
-			  struct nvkm_msgqueue **);
-int msgqueue_0137bca5_new(struct nvkm_falcon *, const struct nvkm_secboot *,
-			  struct nvkm_msgqueue **);
-int msgqueue_0148cdec_new(struct nvkm_falcon *, const struct nvkm_secboot *,
-			  struct nvkm_msgqueue **);
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue_0137c63d.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue_0137c63d.c
deleted file mode 100644
index fec0273158f6..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue_0137c63d.c
+++ /dev/null
@@ -1,436 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-#include "msgqueue.h"
-#include <engine/falcon.h>
-#include <subdev/secboot.h>
-
-/* Queues identifiers */
-enum {
-	/* High Priority Command Queue for Host -> PMU communication */
-	MSGQUEUE_0137C63D_COMMAND_QUEUE_HPQ = 0,
-	/* Low Priority Command Queue for Host -> PMU communication */
-	MSGQUEUE_0137C63D_COMMAND_QUEUE_LPQ = 1,
-	/* Message queue for PMU -> Host communication */
-	MSGQUEUE_0137C63D_MESSAGE_QUEUE = 4,
-	MSGQUEUE_0137C63D_NUM_QUEUES = 5,
-};
-
-struct msgqueue_0137c63d {
-	struct nvkm_msgqueue base;
-
-	struct nvkm_msgqueue_queue queue[MSGQUEUE_0137C63D_NUM_QUEUES];
-};
-#define msgqueue_0137c63d(q) \
-	container_of(q, struct msgqueue_0137c63d, base)
-
-struct msgqueue_0137bca5 {
-	struct msgqueue_0137c63d base;
-
-	u64 wpr_addr;
-};
-#define msgqueue_0137bca5(q) \
-	container_of(container_of(q, struct msgqueue_0137c63d, base), \
-		     struct msgqueue_0137bca5, base);
-
-static struct nvkm_msgqueue_queue *
-msgqueue_0137c63d_cmd_queue(struct nvkm_msgqueue *queue,
-			    enum msgqueue_msg_priority priority)
-{
-	struct msgqueue_0137c63d *priv = msgqueue_0137c63d(queue);
-	const struct nvkm_subdev *subdev = priv->base.falcon->owner;
-
-	switch (priority) {
-	case MSGQUEUE_MSG_PRIORITY_HIGH:
-		return &priv->queue[MSGQUEUE_0137C63D_COMMAND_QUEUE_HPQ];
-	case MSGQUEUE_MSG_PRIORITY_LOW:
-		return &priv->queue[MSGQUEUE_0137C63D_COMMAND_QUEUE_LPQ];
-	default:
-		nvkm_error(subdev, "invalid command queue!\n");
-		return ERR_PTR(-EINVAL);
-	}
-}
-
-static void
-msgqueue_0137c63d_process_msgs(struct nvkm_msgqueue *queue)
-{
-	struct msgqueue_0137c63d *priv = msgqueue_0137c63d(queue);
-	struct nvkm_msgqueue_queue *q_queue =
-		&priv->queue[MSGQUEUE_0137C63D_MESSAGE_QUEUE];
-
-	nvkm_msgqueue_process_msgs(&priv->base, q_queue);
-}
-
-/* Init unit */
-#define MSGQUEUE_0137C63D_UNIT_INIT 0x07
-
-enum {
-	INIT_MSG_INIT = 0x0,
-};
-
-static void
-init_gen_cmdline(struct nvkm_msgqueue *queue, void *buf)
-{
-	struct {
-		u32 reserved;
-		u32 freq_hz;
-		u32 trace_size;
-		u32 trace_dma_base;
-		u16 trace_dma_base1;
-		u8 trace_dma_offset;
-		u32 trace_dma_idx;
-		bool secure_mode;
-		bool raise_priv_sec;
-		struct {
-			u32 dma_base;
-			u16 dma_base1;
-			u8 dma_offset;
-			u16 fb_size;
-			u8 dma_idx;
-		} gc6_ctx;
-		u8 pad;
-	} *args = buf;
-
-	args->secure_mode = 1;
-}
-
-/* forward declaration */
-static int acr_init_wpr(struct nvkm_msgqueue *queue);
-
-static int
-init_callback(struct nvkm_msgqueue *_queue, struct nvkm_msgqueue_hdr *hdr)
-{
-	struct msgqueue_0137c63d *priv = msgqueue_0137c63d(_queue);
-	struct {
-		struct nvkm_msgqueue_msg base;
-
-		u8 pad;
-		u16 os_debug_entry_point;
-
-		struct {
-			u16 size;
-			u16 offset;
-			u8 index;
-			u8 pad;
-		} queue_info[MSGQUEUE_0137C63D_NUM_QUEUES];
-
-		u16 sw_managed_area_offset;
-		u16 sw_managed_area_size;
-	} *init = (void *)hdr;
-	const struct nvkm_subdev *subdev = _queue->falcon->owner;
-	int i;
-
-	if (init->base.hdr.unit_id != MSGQUEUE_0137C63D_UNIT_INIT) {
-		nvkm_error(subdev, "expected message from init unit\n");
-		return -EINVAL;
-	}
-
-	if (init->base.msg_type != INIT_MSG_INIT) {
-		nvkm_error(subdev, "expected PMU init msg\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < MSGQUEUE_0137C63D_NUM_QUEUES; i++) {
-		struct nvkm_msgqueue_queue *queue = &priv->queue[i];
-
-		mutex_init(&queue->mutex);
-
-		queue->index = init->queue_info[i].index;
-		queue->offset = init->queue_info[i].offset;
-		queue->size = init->queue_info[i].size;
-
-		if (i != MSGQUEUE_0137C63D_MESSAGE_QUEUE) {
-			queue->head_reg = 0x4a0 + (queue->index * 4);
-			queue->tail_reg = 0x4b0 + (queue->index * 4);
-		} else {
-			queue->head_reg = 0x4c8;
-			queue->tail_reg = 0x4cc;
-		}
-
-		nvkm_debug(subdev,
-			   "queue %d: index %d, offset 0x%08x, size 0x%08x\n",
-			   i, queue->index, queue->offset, queue->size);
-	}
-
-	/* Complete initialization by initializing WPR region */
-	return acr_init_wpr(&priv->base);
-}
-
-static const struct nvkm_msgqueue_init_func
-msgqueue_0137c63d_init_func = {
-	.gen_cmdline = init_gen_cmdline,
-	.init_callback = init_callback,
-};
-
-
-
-/* ACR unit */
-#define MSGQUEUE_0137C63D_UNIT_ACR 0x0a
-
-enum {
-	ACR_CMD_INIT_WPR_REGION = 0x00,
-	ACR_CMD_BOOTSTRAP_FALCON = 0x01,
-	ACR_CMD_BOOTSTRAP_MULTIPLE_FALCONS = 0x03,
-};
-
-static void
-acr_init_wpr_callback(struct nvkm_msgqueue *queue,
-		      struct nvkm_msgqueue_hdr *hdr)
-{
-	struct {
-		struct nvkm_msgqueue_msg base;
-		u32 error_code;
-	} *msg = (void *)hdr;
-	const struct nvkm_subdev *subdev = queue->falcon->owner;
-
-	if (msg->error_code) {
-		nvkm_error(subdev, "ACR WPR init failure: %d\n",
-			   msg->error_code);
-		return;
-	}
-
-	nvkm_debug(subdev, "ACR WPR init complete\n");
-	complete_all(&queue->init_done);
-}
-
-static int
-acr_init_wpr(struct nvkm_msgqueue *queue)
-{
-	/*
-	 * region_id:	region ID in WPR region
-	 * wpr_offset:	offset in WPR region
-	 */
-	struct {
-		struct nvkm_msgqueue_hdr hdr;
-		u8 cmd_type;
-		u32 region_id;
-		u32 wpr_offset;
-	} cmd;
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.hdr.unit_id = MSGQUEUE_0137C63D_UNIT_ACR;
-	cmd.hdr.size = sizeof(cmd);
-	cmd.cmd_type = ACR_CMD_INIT_WPR_REGION;
-	cmd.region_id = 0x01;
-	cmd.wpr_offset = 0x00;
-
-	nvkm_msgqueue_post(queue, MSGQUEUE_MSG_PRIORITY_HIGH, &cmd.hdr,
-			   acr_init_wpr_callback, NULL, false);
-
-	return 0;
-}
-
-
-static void
-acr_boot_falcon_callback(struct nvkm_msgqueue *priv,
-			 struct nvkm_msgqueue_hdr *hdr)
-{
-	struct acr_bootstrap_falcon_msg {
-		struct nvkm_msgqueue_msg base;
-
-		u32 falcon_id;
-	} *msg = (void *)hdr;
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	u32 falcon_id = msg->falcon_id;
-
-	if (falcon_id >= NVKM_SECBOOT_FALCON_END) {
-		nvkm_error(subdev, "in bootstrap falcon callback:\n");
-		nvkm_error(subdev, "invalid falcon ID 0x%x\n", falcon_id);
-		return;
-	}
-	nvkm_debug(subdev, "%s booted\n", nvkm_secboot_falcon_name[falcon_id]);
-}
-
-enum {
-	ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_YES = 0,
-	ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_NO = 1,
-};
-
-static int
-acr_boot_falcon(struct nvkm_msgqueue *priv, enum nvkm_secboot_falcon falcon)
-{
-	DECLARE_COMPLETION_ONSTACK(completed);
-	/*
-	 * flags      - Flag specifying RESET or no RESET.
-	 * falcon id  - Falcon id specifying falcon to bootstrap.
-	 */
-	struct {
-		struct nvkm_msgqueue_hdr hdr;
-		u8 cmd_type;
-		u32 flags;
-		u32 falcon_id;
-	} cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.hdr.unit_id = MSGQUEUE_0137C63D_UNIT_ACR;
-	cmd.hdr.size = sizeof(cmd);
-	cmd.cmd_type = ACR_CMD_BOOTSTRAP_FALCON;
-	cmd.flags = ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_YES;
-	cmd.falcon_id = falcon;
-	nvkm_msgqueue_post(priv, MSGQUEUE_MSG_PRIORITY_HIGH, &cmd.hdr,
-			acr_boot_falcon_callback, &completed, true);
-
-	if (!wait_for_completion_timeout(&completed, msecs_to_jiffies(1000)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static void
-acr_boot_multiple_falcons_callback(struct nvkm_msgqueue *priv,
-				   struct nvkm_msgqueue_hdr *hdr)
-{
-	struct acr_bootstrap_falcon_msg {
-		struct nvkm_msgqueue_msg base;
-
-		u32 falcon_mask;
-	} *msg = (void *)hdr;
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	unsigned long falcon_mask = msg->falcon_mask;
-	u32 falcon_id, falcon_treated = 0;
-
-	for_each_set_bit(falcon_id, &falcon_mask, NVKM_SECBOOT_FALCON_END) {
-		nvkm_debug(subdev, "%s booted\n",
-			   nvkm_secboot_falcon_name[falcon_id]);
-		falcon_treated |= BIT(falcon_id);
-	}
-
-	if (falcon_treated != msg->falcon_mask) {
-		nvkm_error(subdev, "in bootstrap falcon callback:\n");
-		nvkm_error(subdev, "invalid falcon mask 0x%x\n",
-			   msg->falcon_mask);
-		return;
-	}
-}
-
-static int
-acr_boot_multiple_falcons(struct nvkm_msgqueue *priv, unsigned long falcon_mask)
-{
-	DECLARE_COMPLETION_ONSTACK(completed);
-	/*
-	 * flags      - Flag specifying RESET or no RESET.
-	 * falcon id  - Falcon id specifying falcon to bootstrap.
-	 */
-	struct {
-		struct nvkm_msgqueue_hdr hdr;
-		u8 cmd_type;
-		u32 flags;
-		u32 falcon_mask;
-		u32 use_va_mask;
-		u32 wpr_lo;
-		u32 wpr_hi;
-	} cmd;
-	struct msgqueue_0137bca5 *queue = msgqueue_0137bca5(priv);
-
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.hdr.unit_id = MSGQUEUE_0137C63D_UNIT_ACR;
-	cmd.hdr.size = sizeof(cmd);
-	cmd.cmd_type = ACR_CMD_BOOTSTRAP_MULTIPLE_FALCONS;
-	cmd.flags = ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_YES;
-	cmd.falcon_mask = falcon_mask;
-	cmd.wpr_lo = lower_32_bits(queue->wpr_addr);
-	cmd.wpr_hi = upper_32_bits(queue->wpr_addr);
-	nvkm_msgqueue_post(priv, MSGQUEUE_MSG_PRIORITY_HIGH, &cmd.hdr,
-			acr_boot_multiple_falcons_callback, &completed, true);
-
-	if (!wait_for_completion_timeout(&completed, msecs_to_jiffies(1000)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static const struct nvkm_msgqueue_acr_func
-msgqueue_0137c63d_acr_func = {
-	.boot_falcon = acr_boot_falcon,
-};
-
-static const struct nvkm_msgqueue_acr_func
-msgqueue_0137bca5_acr_func = {
-	.boot_falcon = acr_boot_falcon,
-	.boot_multiple_falcons = acr_boot_multiple_falcons,
-};
-
-static void
-msgqueue_0137c63d_dtor(struct nvkm_msgqueue *queue)
-{
-	kfree(msgqueue_0137c63d(queue));
-}
-
-static const struct nvkm_msgqueue_func
-msgqueue_0137c63d_func = {
-	.init_func = &msgqueue_0137c63d_init_func,
-	.acr_func = &msgqueue_0137c63d_acr_func,
-	.cmd_queue = msgqueue_0137c63d_cmd_queue,
-	.recv = msgqueue_0137c63d_process_msgs,
-	.dtor = msgqueue_0137c63d_dtor,
-};
-
-int
-msgqueue_0137c63d_new(struct nvkm_falcon *falcon, const struct nvkm_secboot *sb,
-		      struct nvkm_msgqueue **queue)
-{
-	struct msgqueue_0137c63d *ret;
-
-	ret = kzalloc(sizeof(*ret), GFP_KERNEL);
-	if (!ret)
-		return -ENOMEM;
-
-	*queue = &ret->base;
-
-	nvkm_msgqueue_ctor(&msgqueue_0137c63d_func, falcon, &ret->base);
-
-	return 0;
-}
-
-static const struct nvkm_msgqueue_func
-msgqueue_0137bca5_func = {
-	.init_func = &msgqueue_0137c63d_init_func,
-	.acr_func = &msgqueue_0137bca5_acr_func,
-	.cmd_queue = msgqueue_0137c63d_cmd_queue,
-	.recv = msgqueue_0137c63d_process_msgs,
-	.dtor = msgqueue_0137c63d_dtor,
-};
-
-int
-msgqueue_0137bca5_new(struct nvkm_falcon *falcon, const struct nvkm_secboot *sb,
-		      struct nvkm_msgqueue **queue)
-{
-	struct msgqueue_0137bca5 *ret;
-
-	ret = kzalloc(sizeof(*ret), GFP_KERNEL);
-	if (!ret)
-		return -ENOMEM;
-
-	*queue = &ret->base.base;
-
-	/*
-	 * FIXME this must be set to the address of a *GPU* mapping within the
-	 * ACR address space!
-	 */
-	/* ret->wpr_addr = sb->wpr_addr; */
-
-	nvkm_msgqueue_ctor(&msgqueue_0137bca5_func, falcon, &ret->base.base);
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue_0148cdec.c b/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue_0148cdec.c
deleted file mode 100644
index 9424803b9ef4..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/msgqueue_0148cdec.c
+++ /dev/null
@@ -1,264 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#include "msgqueue.h"
-#include <engine/falcon.h>
-#include <subdev/secboot.h>
-
-/*
- * This firmware runs on the SEC falcon. It only has one command and one
- * message queue, and uses a different command line and init message.
- */
-
-enum {
-	MSGQUEUE_0148CDEC_COMMAND_QUEUE = 0,
-	MSGQUEUE_0148CDEC_MESSAGE_QUEUE = 1,
-	MSGQUEUE_0148CDEC_NUM_QUEUES,
-};
-
-struct msgqueue_0148cdec {
-	struct nvkm_msgqueue base;
-
-	struct nvkm_msgqueue_queue queue[MSGQUEUE_0148CDEC_NUM_QUEUES];
-};
-#define msgqueue_0148cdec(q) \
-	container_of(q, struct msgqueue_0148cdec, base)
-
-static struct nvkm_msgqueue_queue *
-msgqueue_0148cdec_cmd_queue(struct nvkm_msgqueue *queue,
-			    enum msgqueue_msg_priority priority)
-{
-	struct msgqueue_0148cdec *priv = msgqueue_0148cdec(queue);
-
-	return &priv->queue[MSGQUEUE_0148CDEC_COMMAND_QUEUE];
-}
-
-static void
-msgqueue_0148cdec_process_msgs(struct nvkm_msgqueue *queue)
-{
-	struct msgqueue_0148cdec *priv = msgqueue_0148cdec(queue);
-	struct nvkm_msgqueue_queue *q_queue =
-		&priv->queue[MSGQUEUE_0148CDEC_MESSAGE_QUEUE];
-
-	nvkm_msgqueue_process_msgs(&priv->base, q_queue);
-}
-
-
-/* Init unit */
-#define MSGQUEUE_0148CDEC_UNIT_INIT 0x01
-
-enum {
-	INIT_MSG_INIT = 0x0,
-};
-
-static void
-init_gen_cmdline(struct nvkm_msgqueue *queue, void *buf)
-{
-	struct {
-		u32 freq_hz;
-		u32 falc_trace_size;
-		u32 falc_trace_dma_base;
-		u32 falc_trace_dma_idx;
-		bool secure_mode;
-	} *args = buf;
-
-	args->secure_mode = false;
-}
-
-static int
-init_callback(struct nvkm_msgqueue *_queue, struct nvkm_msgqueue_hdr *hdr)
-{
-	struct msgqueue_0148cdec *priv = msgqueue_0148cdec(_queue);
-	struct {
-		struct nvkm_msgqueue_msg base;
-
-		u8 num_queues;
-		u16 os_debug_entry_point;
-
-		struct {
-			u32 offset;
-			u16 size;
-			u8 index;
-			u8 id;
-		} queue_info[MSGQUEUE_0148CDEC_NUM_QUEUES];
-
-		u16 sw_managed_area_offset;
-		u16 sw_managed_area_size;
-	} *init = (void *)hdr;
-	const struct nvkm_subdev *subdev = _queue->falcon->owner;
-	int i;
-
-	if (init->base.hdr.unit_id != MSGQUEUE_0148CDEC_UNIT_INIT) {
-		nvkm_error(subdev, "expected message from init unit\n");
-		return -EINVAL;
-	}
-
-	if (init->base.msg_type != INIT_MSG_INIT) {
-		nvkm_error(subdev, "expected SEC init msg\n");
-		return -EINVAL;
-	}
-
-	for (i = 0; i < MSGQUEUE_0148CDEC_NUM_QUEUES; i++) {
-		u8 id = init->queue_info[i].id;
-		struct nvkm_msgqueue_queue *queue = &priv->queue[id];
-
-		mutex_init(&queue->mutex);
-
-		queue->index = init->queue_info[i].index;
-		queue->offset = init->queue_info[i].offset;
-		queue->size = init->queue_info[i].size;
-
-		if (id == MSGQUEUE_0148CDEC_MESSAGE_QUEUE) {
-			queue->head_reg = 0xa30 + (queue->index * 8);
-			queue->tail_reg = 0xa34 + (queue->index * 8);
-		} else {
-			queue->head_reg = 0xa00 + (queue->index * 8);
-			queue->tail_reg = 0xa04 + (queue->index * 8);
-		}
-
-		nvkm_debug(subdev,
-			   "queue %d: index %d, offset 0x%08x, size 0x%08x\n",
-			   id, queue->index, queue->offset, queue->size);
-	}
-
-	complete_all(&_queue->init_done);
-
-	return 0;
-}
-
-static const struct nvkm_msgqueue_init_func
-msgqueue_0148cdec_init_func = {
-	.gen_cmdline = init_gen_cmdline,
-	.init_callback = init_callback,
-};
-
-
-
-/* ACR unit */
-#define MSGQUEUE_0148CDEC_UNIT_ACR 0x08
-
-enum {
-	ACR_CMD_BOOTSTRAP_FALCON = 0x00,
-};
-
-static void
-acr_boot_falcon_callback(struct nvkm_msgqueue *priv,
-			 struct nvkm_msgqueue_hdr *hdr)
-{
-	struct acr_bootstrap_falcon_msg {
-		struct nvkm_msgqueue_msg base;
-
-		u32 error_code;
-		u32 falcon_id;
-	} *msg = (void *)hdr;
-	const struct nvkm_subdev *subdev = priv->falcon->owner;
-	u32 falcon_id = msg->falcon_id;
-
-	if (msg->error_code) {
-		nvkm_error(subdev, "in bootstrap falcon callback:\n");
-		nvkm_error(subdev, "expected error code 0x%x\n",
-			   msg->error_code);
-		return;
-	}
-
-	if (falcon_id >= NVKM_SECBOOT_FALCON_END) {
-		nvkm_error(subdev, "in bootstrap falcon callback:\n");
-		nvkm_error(subdev, "invalid falcon ID 0x%x\n", falcon_id);
-		return;
-	}
-
-	nvkm_debug(subdev, "%s booted\n", nvkm_secboot_falcon_name[falcon_id]);
-}
-
-enum {
-	ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_YES = 0,
-	ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_NO = 1,
-};
-
-static int
-acr_boot_falcon(struct nvkm_msgqueue *priv, enum nvkm_secboot_falcon falcon)
-{
-	DECLARE_COMPLETION_ONSTACK(completed);
-	/*
-	 * flags      - Flag specifying RESET or no RESET.
-	 * falcon id  - Falcon id specifying falcon to bootstrap.
-	 */
-	struct {
-		struct nvkm_msgqueue_hdr hdr;
-		u8 cmd_type;
-		u32 flags;
-		u32 falcon_id;
-	} cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-
-	cmd.hdr.unit_id = MSGQUEUE_0148CDEC_UNIT_ACR;
-	cmd.hdr.size = sizeof(cmd);
-	cmd.cmd_type = ACR_CMD_BOOTSTRAP_FALCON;
-	cmd.flags = ACR_CMD_BOOTSTRAP_FALCON_FLAGS_RESET_YES;
-	cmd.falcon_id = falcon;
-	nvkm_msgqueue_post(priv, MSGQUEUE_MSG_PRIORITY_HIGH, &cmd.hdr,
-			   acr_boot_falcon_callback, &completed, true);
-
-	if (!wait_for_completion_timeout(&completed, msecs_to_jiffies(1000)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-const struct nvkm_msgqueue_acr_func
-msgqueue_0148cdec_acr_func = {
-	.boot_falcon = acr_boot_falcon,
-};
-
-static void
-msgqueue_0148cdec_dtor(struct nvkm_msgqueue *queue)
-{
-	kfree(msgqueue_0148cdec(queue));
-}
-
-const struct nvkm_msgqueue_func
-msgqueue_0148cdec_func = {
-	.init_func = &msgqueue_0148cdec_init_func,
-	.acr_func = &msgqueue_0148cdec_acr_func,
-	.cmd_queue = msgqueue_0148cdec_cmd_queue,
-	.recv = msgqueue_0148cdec_process_msgs,
-	.dtor = msgqueue_0148cdec_dtor,
-};
-
-int
-msgqueue_0148cdec_new(struct nvkm_falcon *falcon, const struct nvkm_secboot *sb,
-		      struct nvkm_msgqueue **queue)
-{
-	struct msgqueue_0148cdec *ret;
-
-	ret = kzalloc(sizeof(*ret), GFP_KERNEL);
-	if (!ret)
-		return -ENOMEM;
-
-	*queue = &ret->base;
-
-	nvkm_msgqueue_ctor(&msgqueue_0148cdec_func, falcon, &ret->base);
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/priv.h b/drivers/gpu/drm/nouveau/nvkm/falcon/priv.h
index 900fe1d37b4d..466188752eb0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/priv.h
@@ -1,9 +1,5 @@
 /* SPDX-License-Identifier: MIT */
 #ifndef __NVKM_FALCON_PRIV_H__
 #define __NVKM_FALCON_PRIV_H__
-#include <engine/falcon.h>
-
-void
-nvkm_falcon_ctor(const struct nvkm_falcon_func *, struct nvkm_subdev *,
-		 const char *, u32, struct nvkm_falcon *);
+#include <core/falcon.h>
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/qmgr.c b/drivers/gpu/drm/nouveau/nvkm/falcon/qmgr.c
new file mode 100644
index 000000000000..a453de341a75
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/qmgr.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "qmgr.h"
+
+struct nvkm_falcon_qmgr_seq *
+nvkm_falcon_qmgr_seq_acquire(struct nvkm_falcon_qmgr *qmgr)
+{
+	const struct nvkm_subdev *subdev = qmgr->falcon->owner;
+	struct nvkm_falcon_qmgr_seq *seq;
+	u32 index;
+
+	mutex_lock(&qmgr->seq.mutex);
+	index = find_first_zero_bit(qmgr->seq.tbl, NVKM_FALCON_QMGR_SEQ_NUM);
+	if (index >= NVKM_FALCON_QMGR_SEQ_NUM) {
+		nvkm_error(subdev, "no free sequence available\n");
+		mutex_unlock(&qmgr->seq.mutex);
+		return ERR_PTR(-EAGAIN);
+	}
+
+	set_bit(index, qmgr->seq.tbl);
+	mutex_unlock(&qmgr->seq.mutex);
+
+	seq = &qmgr->seq.id[index];
+	seq->state = SEQ_STATE_PENDING;
+	return seq;
+}
+
+void
+nvkm_falcon_qmgr_seq_release(struct nvkm_falcon_qmgr *qmgr,
+			     struct nvkm_falcon_qmgr_seq *seq)
+{
+	/* no need to acquire seq.mutex since clear_bit is atomic */
+	seq->state = SEQ_STATE_FREE;
+	seq->callback = NULL;
+	reinit_completion(&seq->done);
+	clear_bit(seq->id, qmgr->seq.tbl);
+}
+
+void
+nvkm_falcon_qmgr_del(struct nvkm_falcon_qmgr **pqmgr)
+{
+	struct nvkm_falcon_qmgr *qmgr = *pqmgr;
+	if (qmgr) {
+		kfree(*pqmgr);
+		*pqmgr = NULL;
+	}
+}
+
+int
+nvkm_falcon_qmgr_new(struct nvkm_falcon *falcon,
+		     struct nvkm_falcon_qmgr **pqmgr)
+{
+	struct nvkm_falcon_qmgr *qmgr;
+	int i;
+
+	if (!(qmgr = *pqmgr = kzalloc(sizeof(*qmgr), GFP_KERNEL)))
+		return -ENOMEM;
+
+	qmgr->falcon = falcon;
+	mutex_init(&qmgr->seq.mutex);
+	for (i = 0; i < NVKM_FALCON_QMGR_SEQ_NUM; i++) {
+		qmgr->seq.id[i].id = i;
+		init_completion(&qmgr->seq.id[i].done);
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/qmgr.h b/drivers/gpu/drm/nouveau/nvkm/falcon/qmgr.h
new file mode 100644
index 000000000000..a45cd705e4f7
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/qmgr.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVKM_FALCON_QMGR_H__
+#define __NVKM_FALCON_QMGR_H__
+#include <core/falcon.h>
+
+#define HDR_SIZE sizeof(struct nv_falcon_msg)
+#define QUEUE_ALIGNMENT 4
+/* max size of the messages we can receive */
+#define MSG_BUF_SIZE 128
+
+/**
+ * struct nvkm_falcon_qmgr_seq - keep track of ongoing commands
+ *
+ * Every time a command is sent, a sequence is assigned to it so the
+ * corresponding message can be matched. Upon receiving the message, a callback
+ * can be called and/or a completion signaled.
+ *
+ * @id:		sequence ID
+ * @state:	current state
+ * @callback:	callback to call upon receiving matching message
+ * @completion:	completion to signal after callback is called
+ */
+struct nvkm_falcon_qmgr_seq {
+	u16 id;
+	enum {
+		SEQ_STATE_FREE = 0,
+		SEQ_STATE_PENDING,
+		SEQ_STATE_USED,
+		SEQ_STATE_CANCELLED
+	} state;
+	bool async;
+	nvkm_falcon_qmgr_callback callback;
+	void *priv;
+	struct completion done;
+	int result;
+};
+
+/*
+ * We can have an arbitrary number of sequences, but realistically we will
+ * probably not use that much simultaneously.
+ */
+#define NVKM_FALCON_QMGR_SEQ_NUM 16
+
+struct nvkm_falcon_qmgr {
+	struct nvkm_falcon *falcon;
+
+	struct {
+		struct mutex mutex;
+		struct nvkm_falcon_qmgr_seq id[NVKM_FALCON_QMGR_SEQ_NUM];
+		unsigned long tbl[BITS_TO_LONGS(NVKM_FALCON_QMGR_SEQ_NUM)];
+	} seq;
+};
+
+struct nvkm_falcon_qmgr_seq *
+nvkm_falcon_qmgr_seq_acquire(struct nvkm_falcon_qmgr *);
+void nvkm_falcon_qmgr_seq_release(struct nvkm_falcon_qmgr *,
+				  struct nvkm_falcon_qmgr_seq *);
+
+struct nvkm_falcon_cmdq {
+	struct nvkm_falcon_qmgr *qmgr;
+	const char *name;
+	struct mutex mutex;
+	struct completion ready;
+
+	u32 head_reg;
+	u32 tail_reg;
+	u32 offset;
+	u32 size;
+
+	u32 position;
+};
+
+struct nvkm_falcon_msgq {
+	struct nvkm_falcon_qmgr *qmgr;
+	const char *name;
+	struct mutex mutex;
+
+	u32 head_reg;
+	u32 tail_reg;
+	u32 offset;
+
+	u32 position;
+};
+
+#define FLCNQ_PRINTK(t,q,f,a...)                                               \
+       FLCN_PRINTK(t, (q)->qmgr->falcon, "%s: "f, (q)->name, ##a)
+#define FLCNQ_DBG(q,f,a...) FLCNQ_PRINTK(debug, (q), f, ##a)
+#define FLCNQ_ERR(q,f,a...) FLCNQ_PRINTK(error, (q), f, ##a)
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/v1.c b/drivers/gpu/drm/nouveau/nvkm/falcon/v1.c
index 6d978feebbd7..1ff9b9c2e651 100644
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/v1.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/v1.c
@@ -25,7 +25,7 @@
 #include <core/memory.h>
 #include <subdev/timer.h>
 
-static void
+void
 nvkm_falcon_v1_load_imem(struct nvkm_falcon *falcon, void *data, u32 start,
 			 u32 size, u16 tag, u8 port, bool secure)
 {
@@ -89,18 +89,17 @@ nvkm_falcon_v1_load_emem(struct nvkm_falcon *falcon, void *data, u32 start,
 	}
 }
 
-static const u32 EMEM_START_ADDR = 0x1000000;
-
-static void
+void
 nvkm_falcon_v1_load_dmem(struct nvkm_falcon *falcon, void *data, u32 start,
-		      u32 size, u8 port)
+			 u32 size, u8 port)
 {
+	const struct nvkm_falcon_func *func = falcon->func;
 	u8 rem = size % 4;
 	int i;
 
-	if (start >= EMEM_START_ADDR && falcon->has_emem)
+	if (func->emem_addr && start >= func->emem_addr)
 		return nvkm_falcon_v1_load_emem(falcon, data,
-						start - EMEM_START_ADDR, size,
+						start - func->emem_addr, size,
 						port);
 
 	size -= rem;
@@ -148,15 +147,16 @@ nvkm_falcon_v1_read_emem(struct nvkm_falcon *falcon, u32 start, u32 size,
 	}
 }
 
-static void
+void
 nvkm_falcon_v1_read_dmem(struct nvkm_falcon *falcon, u32 start, u32 size,
 			 u8 port, void *data)
 {
+	const struct nvkm_falcon_func *func = falcon->func;
 	u8 rem = size % 4;
 	int i;
 
-	if (start >= EMEM_START_ADDR && falcon->has_emem)
-		return nvkm_falcon_v1_read_emem(falcon, start - EMEM_START_ADDR,
+	if (func->emem_addr && start >= func->emem_addr)
+		return nvkm_falcon_v1_read_emem(falcon, start - func->emem_addr,
 						size, port, data);
 
 	size -= rem;
@@ -179,12 +179,11 @@ nvkm_falcon_v1_read_dmem(struct nvkm_falcon *falcon, u32 start, u32 size,
 	}
 }
 
-static void
+void
 nvkm_falcon_v1_bind_context(struct nvkm_falcon *falcon, struct nvkm_memory *ctx)
 {
-	struct nvkm_device *device = falcon->owner->device;
+	const u32 fbif = falcon->func->fbif;
 	u32 inst_loc;
-	u32 fbif;
 
 	/* disable instance block binding */
 	if (ctx == NULL) {
@@ -192,20 +191,6 @@ nvkm_falcon_v1_bind_context(struct nvkm_falcon *falcon, struct nvkm_memory *ctx)
 		return;
 	}
 
-	switch (falcon->owner->index) {
-	case NVKM_ENGINE_NVENC0:
-	case NVKM_ENGINE_NVENC1:
-	case NVKM_ENGINE_NVENC2:
-		fbif = 0x800;
-		break;
-	case NVKM_SUBDEV_PMU:
-		fbif = 0xe00;
-		break;
-	default:
-		fbif = 0x600;
-		break;
-	}
-
 	nvkm_falcon_wr32(falcon, 0x10c, 0x1);
 
 	/* setup apertures - virtual */
@@ -234,50 +219,15 @@ nvkm_falcon_v1_bind_context(struct nvkm_falcon *falcon, struct nvkm_memory *ctx)
 
 	nvkm_falcon_mask(falcon, 0x090, 0x10000, 0x10000);
 	nvkm_falcon_mask(falcon, 0x0a4, 0x8, 0x8);
-
-	/* Not sure if this is a WAR for a HW issue, or some additional
-	 * programming sequence that's needed to properly complete the
-	 * context switch we trigger above.
-	 *
-	 * Fixes unreliability of booting the SEC2 RTOS on Quadro P620,
-	 * particularly when resuming from suspend.
-	 *
-	 * Also removes the need for an odd workaround where we needed
-	 * to program SEC2's FALCON_CPUCTL_ALIAS_STARTCPU twice before
-	 * the SEC2 RTOS would begin executing.
-	 */
-	switch (falcon->owner->index) {
-	case NVKM_SUBDEV_GSP:
-	case NVKM_ENGINE_SEC2:
-		nvkm_msec(device, 10,
-			u32 irqstat = nvkm_falcon_rd32(falcon, 0x008);
-			u32 flcn0dc = nvkm_falcon_rd32(falcon, 0x0dc);
-			if ((irqstat & 0x00000008) &&
-			    (flcn0dc & 0x00007000) == 0x00005000)
-				break;
-		);
-
-		nvkm_falcon_mask(falcon, 0x004, 0x00000008, 0x00000008);
-		nvkm_falcon_mask(falcon, 0x058, 0x00000002, 0x00000002);
-
-		nvkm_msec(device, 10,
-			u32 flcn0dc = nvkm_falcon_rd32(falcon, 0x0dc);
-			if ((flcn0dc & 0x00007000) == 0x00000000)
-				break;
-		);
-		break;
-	default:
-		break;
-	}
 }
 
-static void
+void
 nvkm_falcon_v1_set_start_addr(struct nvkm_falcon *falcon, u32 start_addr)
 {
 	nvkm_falcon_wr32(falcon, 0x104, start_addr);
 }
 
-static void
+void
 nvkm_falcon_v1_start(struct nvkm_falcon *falcon)
 {
 	u32 reg = nvkm_falcon_rd32(falcon, 0x100);
@@ -288,7 +238,7 @@ nvkm_falcon_v1_start(struct nvkm_falcon *falcon)
 		nvkm_falcon_wr32(falcon, 0x100, 0x2);
 }
 
-static int
+int
 nvkm_falcon_v1_wait_for_halt(struct nvkm_falcon *falcon, u32 ms)
 {
 	struct nvkm_device *device = falcon->owner->device;
@@ -301,7 +251,7 @@ nvkm_falcon_v1_wait_for_halt(struct nvkm_falcon *falcon, u32 ms)
 	return 0;
 }
 
-static int
+int
 nvkm_falcon_v1_clear_interrupt(struct nvkm_falcon *falcon, u32 mask)
 {
 	struct nvkm_device *device = falcon->owner->device;
@@ -330,7 +280,7 @@ falcon_v1_wait_idle(struct nvkm_falcon *falcon)
 	return 0;
 }
 
-static int
+int
 nvkm_falcon_v1_enable(struct nvkm_falcon *falcon)
 {
 	struct nvkm_device *device = falcon->owner->device;
@@ -352,7 +302,7 @@ nvkm_falcon_v1_enable(struct nvkm_falcon *falcon)
 	return 0;
 }
 
-static void
+void
 nvkm_falcon_v1_disable(struct nvkm_falcon *falcon)
 {
 	/* disable IRQs and wait for any previous code to complete */
diff --git a/drivers/gpu/drm/nouveau/nvkm/nvfw/Kbuild b/drivers/gpu/drm/nouveau/nvkm/nvfw/Kbuild
new file mode 100644
index 000000000000..41d75f98e603
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/nvfw/Kbuild
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: MIT
+nvkm-y += nvkm/nvfw/fw.o
+nvkm-y += nvkm/nvfw/hs.o
+nvkm-y += nvkm/nvfw/ls.o
+
+nvkm-y += nvkm/nvfw/acr.o
+nvkm-y += nvkm/nvfw/flcn.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/nvfw/acr.c b/drivers/gpu/drm/nouveau/nvkm/nvfw/acr.c
new file mode 100644
index 000000000000..0d063b8317f7
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/nvfw/acr.c
@@ -0,0 +1,165 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <core/subdev.h>
+#include <nvfw/acr.h>
+
+void
+wpr_header_dump(struct nvkm_subdev *subdev, const struct wpr_header *hdr)
+{
+	nvkm_debug(subdev, "wprHeader\n");
+	nvkm_debug(subdev, "\tfalconID      : %d\n", hdr->falcon_id);
+	nvkm_debug(subdev, "\tlsbOffset     : 0x%x\n", hdr->lsb_offset);
+	nvkm_debug(subdev, "\tbootstrapOwner: %d\n", hdr->bootstrap_owner);
+	nvkm_debug(subdev, "\tlazyBootstrap : %d\n", hdr->lazy_bootstrap);
+	nvkm_debug(subdev, "\tstatus        : %d\n", hdr->status);
+}
+
+void
+wpr_header_v1_dump(struct nvkm_subdev *subdev, const struct wpr_header_v1 *hdr)
+{
+	nvkm_debug(subdev, "wprHeader\n");
+	nvkm_debug(subdev, "\tfalconID      : %d\n", hdr->falcon_id);
+	nvkm_debug(subdev, "\tlsbOffset     : 0x%x\n", hdr->lsb_offset);
+	nvkm_debug(subdev, "\tbootstrapOwner: %d\n", hdr->bootstrap_owner);
+	nvkm_debug(subdev, "\tlazyBootstrap : %d\n", hdr->lazy_bootstrap);
+	nvkm_debug(subdev, "\tbinVersion    : %d\n", hdr->bin_version);
+	nvkm_debug(subdev, "\tstatus        : %d\n", hdr->status);
+}
+
+void
+lsb_header_tail_dump(struct nvkm_subdev *subdev,
+			struct lsb_header_tail *hdr)
+{
+	nvkm_debug(subdev, "lsbHeader\n");
+	nvkm_debug(subdev, "\tucodeOff      : 0x%x\n", hdr->ucode_off);
+	nvkm_debug(subdev, "\tucodeSize     : 0x%x\n", hdr->ucode_size);
+	nvkm_debug(subdev, "\tdataSize      : 0x%x\n", hdr->data_size);
+	nvkm_debug(subdev, "\tblCodeSize    : 0x%x\n", hdr->bl_code_size);
+	nvkm_debug(subdev, "\tblImemOff     : 0x%x\n", hdr->bl_imem_off);
+	nvkm_debug(subdev, "\tblDataOff     : 0x%x\n", hdr->bl_data_off);
+	nvkm_debug(subdev, "\tblDataSize    : 0x%x\n", hdr->bl_data_size);
+	nvkm_debug(subdev, "\tappCodeOff    : 0x%x\n", hdr->app_code_off);
+	nvkm_debug(subdev, "\tappCodeSize   : 0x%x\n", hdr->app_code_size);
+	nvkm_debug(subdev, "\tappDataOff    : 0x%x\n", hdr->app_data_off);
+	nvkm_debug(subdev, "\tappDataSize   : 0x%x\n", hdr->app_data_size);
+	nvkm_debug(subdev, "\tflags         : 0x%x\n", hdr->flags);
+}
+
+void
+lsb_header_dump(struct nvkm_subdev *subdev, struct lsb_header *hdr)
+{
+	lsb_header_tail_dump(subdev, &hdr->tail);
+}
+
+void
+lsb_header_v1_dump(struct nvkm_subdev *subdev, struct lsb_header_v1 *hdr)
+{
+	lsb_header_tail_dump(subdev, &hdr->tail);
+}
+
+void
+flcn_acr_desc_dump(struct nvkm_subdev *subdev, struct flcn_acr_desc *hdr)
+{
+	int i;
+
+	nvkm_debug(subdev, "acrDesc\n");
+	nvkm_debug(subdev, "\twprRegionId  : %d\n", hdr->wpr_region_id);
+	nvkm_debug(subdev, "\twprOffset    : 0x%x\n", hdr->wpr_offset);
+	nvkm_debug(subdev, "\tmmuMemRange  : 0x%x\n",
+		   hdr->mmu_mem_range);
+	nvkm_debug(subdev, "\tnoRegions    : %d\n",
+		   hdr->regions.no_regions);
+
+	for (i = 0; i < ARRAY_SIZE(hdr->regions.region_props); i++) {
+		nvkm_debug(subdev, "\tregion[%d]    :\n", i);
+		nvkm_debug(subdev, "\t  startAddr  : 0x%x\n",
+			   hdr->regions.region_props[i].start_addr);
+		nvkm_debug(subdev, "\t  endAddr    : 0x%x\n",
+			   hdr->regions.region_props[i].end_addr);
+		nvkm_debug(subdev, "\t  regionId   : %d\n",
+			   hdr->regions.region_props[i].region_id);
+		nvkm_debug(subdev, "\t  readMask   : 0x%x\n",
+			   hdr->regions.region_props[i].read_mask);
+		nvkm_debug(subdev, "\t  writeMask  : 0x%x\n",
+			   hdr->regions.region_props[i].write_mask);
+		nvkm_debug(subdev, "\t  clientMask : 0x%x\n",
+			   hdr->regions.region_props[i].client_mask);
+	}
+
+	nvkm_debug(subdev, "\tucodeBlobSize: %d\n",
+		   hdr->ucode_blob_size);
+	nvkm_debug(subdev, "\tucodeBlobBase: 0x%llx\n",
+		   hdr->ucode_blob_base);
+	nvkm_debug(subdev, "\tvprEnabled   : %d\n",
+		   hdr->vpr_desc.vpr_enabled);
+	nvkm_debug(subdev, "\tvprStart     : 0x%x\n",
+		   hdr->vpr_desc.vpr_start);
+	nvkm_debug(subdev, "\tvprEnd       : 0x%x\n",
+		   hdr->vpr_desc.vpr_end);
+	nvkm_debug(subdev, "\thdcpPolicies : 0x%x\n",
+		   hdr->vpr_desc.hdcp_policies);
+}
+
+void
+flcn_acr_desc_v1_dump(struct nvkm_subdev *subdev, struct flcn_acr_desc_v1 *hdr)
+{
+	int i;
+
+	nvkm_debug(subdev, "acrDesc\n");
+	nvkm_debug(subdev, "\twprRegionId         : %d\n", hdr->wpr_region_id);
+	nvkm_debug(subdev, "\twprOffset           : 0x%x\n", hdr->wpr_offset);
+	nvkm_debug(subdev, "\tmmuMemoryRange      : 0x%x\n",
+		   hdr->mmu_memory_range);
+	nvkm_debug(subdev, "\tnoRegions           : %d\n",
+		   hdr->regions.no_regions);
+
+	for (i = 0; i < ARRAY_SIZE(hdr->regions.region_props); i++) {
+		nvkm_debug(subdev, "\tregion[%d]           :\n", i);
+		nvkm_debug(subdev, "\t  startAddr         : 0x%x\n",
+			   hdr->regions.region_props[i].start_addr);
+		nvkm_debug(subdev, "\t  endAddr           : 0x%x\n",
+			   hdr->regions.region_props[i].end_addr);
+		nvkm_debug(subdev, "\t  regionId          : %d\n",
+			   hdr->regions.region_props[i].region_id);
+		nvkm_debug(subdev, "\t  readMask          : 0x%x\n",
+			   hdr->regions.region_props[i].read_mask);
+		nvkm_debug(subdev, "\t  writeMask         : 0x%x\n",
+			   hdr->regions.region_props[i].write_mask);
+		nvkm_debug(subdev, "\t  clientMask        : 0x%x\n",
+			   hdr->regions.region_props[i].client_mask);
+		nvkm_debug(subdev, "\t  shadowMemStartAddr: 0x%x\n",
+			   hdr->regions.region_props[i].shadow_mem_start_addr);
+	}
+
+	nvkm_debug(subdev, "\tucodeBlobSize       : %d\n",
+		   hdr->ucode_blob_size);
+	nvkm_debug(subdev, "\tucodeBlobBase       : 0x%llx\n",
+		   hdr->ucode_blob_base);
+	nvkm_debug(subdev, "\tvprEnabled          : %d\n",
+		   hdr->vpr_desc.vpr_enabled);
+	nvkm_debug(subdev, "\tvprStart            : 0x%x\n",
+		   hdr->vpr_desc.vpr_start);
+	nvkm_debug(subdev, "\tvprEnd              : 0x%x\n",
+		   hdr->vpr_desc.vpr_end);
+	nvkm_debug(subdev, "\thdcpPolicies        : 0x%x\n",
+		   hdr->vpr_desc.hdcp_policies);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/nvfw/flcn.c b/drivers/gpu/drm/nouveau/nvkm/nvfw/flcn.c
new file mode 100644
index 000000000000..00ec764e1aab
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/nvfw/flcn.c
@@ -0,0 +1,115 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <core/subdev.h>
+#include <nvfw/flcn.h>
+
+void
+loader_config_dump(struct nvkm_subdev *subdev, const struct loader_config *hdr)
+{
+	nvkm_debug(subdev, "loaderConfig\n");
+	nvkm_debug(subdev, "\tdmaIdx        : %d\n", hdr->dma_idx);
+	nvkm_debug(subdev, "\tcodeDmaBase   : 0x%xx\n", hdr->code_dma_base);
+	nvkm_debug(subdev, "\tcodeSizeTotal : 0x%x\n", hdr->code_size_total);
+	nvkm_debug(subdev, "\tcodeSizeToLoad: 0x%x\n", hdr->code_size_to_load);
+	nvkm_debug(subdev, "\tcodeEntryPoint: 0x%x\n", hdr->code_entry_point);
+	nvkm_debug(subdev, "\tdataDmaBase   : 0x%x\n", hdr->data_dma_base);
+	nvkm_debug(subdev, "\tdataSize      : 0x%x\n", hdr->data_size);
+	nvkm_debug(subdev, "\toverlayDmaBase: 0x%x\n", hdr->overlay_dma_base);
+	nvkm_debug(subdev, "\targc          : 0x%08x\n", hdr->argc);
+	nvkm_debug(subdev, "\targv          : 0x%08x\n", hdr->argv);
+	nvkm_debug(subdev, "\tcodeDmaBase1  : 0x%x\n", hdr->code_dma_base1);
+	nvkm_debug(subdev, "\tdataDmaBase1  : 0x%x\n", hdr->data_dma_base1);
+	nvkm_debug(subdev, "\tovlyDmaBase1  : 0x%x\n", hdr->overlay_dma_base1);
+}
+
+void
+loader_config_v1_dump(struct nvkm_subdev *subdev,
+		      const struct loader_config_v1 *hdr)
+{
+	nvkm_debug(subdev, "loaderConfig\n");
+	nvkm_debug(subdev, "\treserved      : 0x%08x\n", hdr->reserved);
+	nvkm_debug(subdev, "\tdmaIdx        : %d\n", hdr->dma_idx);
+	nvkm_debug(subdev, "\tcodeDmaBase   : 0x%llxx\n", hdr->code_dma_base);
+	nvkm_debug(subdev, "\tcodeSizeTotal : 0x%x\n", hdr->code_size_total);
+	nvkm_debug(subdev, "\tcodeSizeToLoad: 0x%x\n", hdr->code_size_to_load);
+	nvkm_debug(subdev, "\tcodeEntryPoint: 0x%x\n", hdr->code_entry_point);
+	nvkm_debug(subdev, "\tdataDmaBase   : 0x%llx\n", hdr->data_dma_base);
+	nvkm_debug(subdev, "\tdataSize      : 0x%x\n", hdr->data_size);
+	nvkm_debug(subdev, "\toverlayDmaBase: 0x%llx\n", hdr->overlay_dma_base);
+	nvkm_debug(subdev, "\targc          : 0x%08x\n", hdr->argc);
+	nvkm_debug(subdev, "\targv          : 0x%08x\n", hdr->argv);
+}
+
+void
+flcn_bl_dmem_desc_dump(struct nvkm_subdev *subdev,
+		       const struct flcn_bl_dmem_desc *hdr)
+{
+	nvkm_debug(subdev, "flcnBlDmemDesc\n");
+	nvkm_debug(subdev, "\treserved      : 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   hdr->reserved[0], hdr->reserved[1], hdr->reserved[2],
+		   hdr->reserved[3]);
+	nvkm_debug(subdev, "\tsignature     : 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   hdr->signature[0], hdr->signature[1], hdr->signature[2],
+		   hdr->signature[3]);
+	nvkm_debug(subdev, "\tctxDma        : %d\n", hdr->ctx_dma);
+	nvkm_debug(subdev, "\tcodeDmaBase   : 0x%x\n", hdr->code_dma_base);
+	nvkm_debug(subdev, "\tnonSecCodeOff : 0x%x\n", hdr->non_sec_code_off);
+	nvkm_debug(subdev, "\tnonSecCodeSize: 0x%x\n", hdr->non_sec_code_size);
+	nvkm_debug(subdev, "\tsecCodeOff    : 0x%x\n", hdr->sec_code_off);
+	nvkm_debug(subdev, "\tsecCodeSize   : 0x%x\n", hdr->sec_code_size);
+	nvkm_debug(subdev, "\tcodeEntryPoint: 0x%x\n", hdr->code_entry_point);
+	nvkm_debug(subdev, "\tdataDmaBase   : 0x%x\n", hdr->data_dma_base);
+	nvkm_debug(subdev, "\tdataSize      : 0x%x\n", hdr->data_size);
+	nvkm_debug(subdev, "\tcodeDmaBase1  : 0x%x\n", hdr->code_dma_base1);
+	nvkm_debug(subdev, "\tdataDmaBase1  : 0x%x\n", hdr->data_dma_base1);
+}
+
+void
+flcn_bl_dmem_desc_v1_dump(struct nvkm_subdev *subdev,
+			  const struct flcn_bl_dmem_desc_v1 *hdr)
+{
+	nvkm_debug(subdev, "flcnBlDmemDesc\n");
+	nvkm_debug(subdev, "\treserved      : 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   hdr->reserved[0], hdr->reserved[1], hdr->reserved[2],
+		   hdr->reserved[3]);
+	nvkm_debug(subdev, "\tsignature     : 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   hdr->signature[0], hdr->signature[1], hdr->signature[2],
+		   hdr->signature[3]);
+	nvkm_debug(subdev, "\tctxDma        : %d\n", hdr->ctx_dma);
+	nvkm_debug(subdev, "\tcodeDmaBase   : 0x%llx\n", hdr->code_dma_base);
+	nvkm_debug(subdev, "\tnonSecCodeOff : 0x%x\n", hdr->non_sec_code_off);
+	nvkm_debug(subdev, "\tnonSecCodeSize: 0x%x\n", hdr->non_sec_code_size);
+	nvkm_debug(subdev, "\tsecCodeOff    : 0x%x\n", hdr->sec_code_off);
+	nvkm_debug(subdev, "\tsecCodeSize   : 0x%x\n", hdr->sec_code_size);
+	nvkm_debug(subdev, "\tcodeEntryPoint: 0x%x\n", hdr->code_entry_point);
+	nvkm_debug(subdev, "\tdataDmaBase   : 0x%llx\n", hdr->data_dma_base);
+	nvkm_debug(subdev, "\tdataSize      : 0x%x\n", hdr->data_size);
+}
+
+void
+flcn_bl_dmem_desc_v2_dump(struct nvkm_subdev *subdev,
+			  const struct flcn_bl_dmem_desc_v2 *hdr)
+{
+	flcn_bl_dmem_desc_v1_dump(subdev, (void *)hdr);
+	nvkm_debug(subdev, "\targc          : 0x%08x\n", hdr->argc);
+	nvkm_debug(subdev, "\targv          : 0x%08x\n", hdr->argv);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/nvfw/fw.c b/drivers/gpu/drm/nouveau/nvkm/nvfw/fw.c
new file mode 100644
index 000000000000..746803bd5318
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/nvfw/fw.c
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <core/subdev.h>
+#include <nvfw/fw.h>
+
+const struct nvfw_bin_hdr *
+nvfw_bin_hdr(struct nvkm_subdev *subdev, const void *data)
+{
+	const struct nvfw_bin_hdr *hdr = data;
+	nvkm_debug(subdev, "binHdr:\n");
+	nvkm_debug(subdev, "\tbinMagic         : 0x%08x\n", hdr->bin_magic);
+	nvkm_debug(subdev, "\tbinVer           : %d\n", hdr->bin_ver);
+	nvkm_debug(subdev, "\tbinSize          : %d\n", hdr->bin_size);
+	nvkm_debug(subdev, "\theaderOffset     : 0x%x\n", hdr->header_offset);
+	nvkm_debug(subdev, "\tdataOffset       : 0x%x\n", hdr->data_offset);
+	nvkm_debug(subdev, "\tdataSize         : 0x%x\n", hdr->data_size);
+	return hdr;
+}
+
+const struct nvfw_bl_desc *
+nvfw_bl_desc(struct nvkm_subdev *subdev, const void *data)
+{
+	const struct nvfw_bl_desc *hdr = data;
+	nvkm_debug(subdev, "blDesc\n");
+	nvkm_debug(subdev, "\tstartTag         : 0x%x\n", hdr->start_tag);
+	nvkm_debug(subdev, "\tdmemLoadOff      : 0x%x\n", hdr->dmem_load_off);
+	nvkm_debug(subdev, "\tcodeOff          : 0x%x\n", hdr->code_off);
+	nvkm_debug(subdev, "\tcodeSize         : 0x%x\n", hdr->code_size);
+	nvkm_debug(subdev, "\tdataOff          : 0x%x\n", hdr->data_off);
+	nvkm_debug(subdev, "\tdataSize         : 0x%x\n", hdr->data_size);
+	return hdr;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/nvfw/hs.c b/drivers/gpu/drm/nouveau/nvkm/nvfw/hs.c
new file mode 100644
index 000000000000..04ed77cb2eba
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/nvfw/hs.c
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <core/subdev.h>
+#include <nvfw/hs.h>
+
+const struct nvfw_hs_header *
+nvfw_hs_header(struct nvkm_subdev *subdev, const void *data)
+{
+	const struct nvfw_hs_header *hdr = data;
+	nvkm_debug(subdev, "hsHeader:\n");
+	nvkm_debug(subdev, "\tsigDbgOffset     : 0x%x\n", hdr->sig_dbg_offset);
+	nvkm_debug(subdev, "\tsigDbgSize       : 0x%x\n", hdr->sig_dbg_size);
+	nvkm_debug(subdev, "\tsigProdOffset    : 0x%x\n", hdr->sig_prod_offset);
+	nvkm_debug(subdev, "\tsigProdSize      : 0x%x\n", hdr->sig_prod_size);
+	nvkm_debug(subdev, "\tpatchLoc         : 0x%x\n", hdr->patch_loc);
+	nvkm_debug(subdev, "\tpatchSig         : 0x%x\n", hdr->patch_sig);
+	nvkm_debug(subdev, "\thdrOffset        : 0x%x\n", hdr->hdr_offset);
+	nvkm_debug(subdev, "\thdrSize          : 0x%x\n", hdr->hdr_size);
+	return hdr;
+}
+
+const struct nvfw_hs_load_header *
+nvfw_hs_load_header(struct nvkm_subdev *subdev, const void *data)
+{
+	const struct nvfw_hs_load_header *hdr = data;
+	int i;
+
+	nvkm_debug(subdev, "hsLoadHeader:\n");
+	nvkm_debug(subdev, "\tnonSecCodeOff    : 0x%x\n",
+			   hdr->non_sec_code_off);
+	nvkm_debug(subdev, "\tnonSecCodeSize   : 0x%x\n",
+			   hdr->non_sec_code_size);
+	nvkm_debug(subdev, "\tdataDmaBase      : 0x%x\n", hdr->data_dma_base);
+	nvkm_debug(subdev, "\tdataSize         : 0x%x\n", hdr->data_size);
+	nvkm_debug(subdev, "\tnumApps          : 0x%x\n", hdr->num_apps);
+	for (i = 0; i < hdr->num_apps; i++) {
+		nvkm_debug(subdev,
+			   "\tApp[%d]           : offset 0x%x size 0x%x\n", i,
+			   hdr->apps[(i * 2) + 0], hdr->apps[(i * 2) + 1]);
+	}
+
+	return hdr;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/nvfw/ls.c b/drivers/gpu/drm/nouveau/nvkm/nvfw/ls.c
new file mode 100644
index 000000000000..b847f281ce97
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/nvfw/ls.c
@@ -0,0 +1,108 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include <core/subdev.h>
+#include <nvfw/ls.h>
+
+static void
+nvfw_ls_desc_head(struct nvkm_subdev *subdev,
+		  const struct nvfw_ls_desc_head *hdr)
+{
+	char *date;
+
+	nvkm_debug(subdev, "lsUcodeImgDesc:\n");
+	nvkm_debug(subdev, "\tdescriptorSize       : %d\n",
+			   hdr->descriptor_size);
+	nvkm_debug(subdev, "\timageSize            : %d\n", hdr->image_size);
+	nvkm_debug(subdev, "\ttoolsVersion         : 0x%x\n",
+			   hdr->tools_version);
+	nvkm_debug(subdev, "\tappVersion           : 0x%x\n", hdr->app_version);
+
+	date = kstrndup(hdr->date, sizeof(hdr->date), GFP_KERNEL);
+	nvkm_debug(subdev, "\tdate                 : %s\n", date);
+	kfree(date);
+
+	nvkm_debug(subdev, "\tbootloaderStartOffset: 0x%x\n",
+			   hdr->bootloader_start_offset);
+	nvkm_debug(subdev, "\tbootloaderSize       : 0x%x\n",
+			   hdr->bootloader_size);
+	nvkm_debug(subdev, "\tbootloaderImemOffset : 0x%x\n",
+			   hdr->bootloader_imem_offset);
+	nvkm_debug(subdev, "\tbootloaderEntryPoint : 0x%x\n",
+			   hdr->bootloader_entry_point);
+
+	nvkm_debug(subdev, "\tappStartOffset       : 0x%x\n",
+			   hdr->app_start_offset);
+	nvkm_debug(subdev, "\tappSize              : 0x%x\n", hdr->app_size);
+	nvkm_debug(subdev, "\tappImemOffset        : 0x%x\n",
+			   hdr->app_imem_offset);
+	nvkm_debug(subdev, "\tappImemEntry         : 0x%x\n",
+			   hdr->app_imem_entry);
+	nvkm_debug(subdev, "\tappDmemOffset        : 0x%x\n",
+			   hdr->app_dmem_offset);
+	nvkm_debug(subdev, "\tappResidentCodeOffset: 0x%x\n",
+			   hdr->app_resident_code_offset);
+	nvkm_debug(subdev, "\tappResidentCodeSize  : 0x%x\n",
+			   hdr->app_resident_code_size);
+	nvkm_debug(subdev, "\tappResidentDataOffset: 0x%x\n",
+			   hdr->app_resident_data_offset);
+	nvkm_debug(subdev, "\tappResidentDataSize  : 0x%x\n",
+			   hdr->app_resident_data_size);
+}
+
+const struct nvfw_ls_desc *
+nvfw_ls_desc(struct nvkm_subdev *subdev, const void *data)
+{
+	const struct nvfw_ls_desc *hdr = data;
+	int i;
+
+	nvfw_ls_desc_head(subdev, &hdr->head);
+
+	nvkm_debug(subdev, "\tnbOverlays           : %d\n", hdr->nb_overlays);
+	for (i = 0; i < ARRAY_SIZE(hdr->load_ovl); i++) {
+		nvkm_debug(subdev, "\tloadOvl[%d]          : 0x%x %d\n", i,
+			   hdr->load_ovl[i].start, hdr->load_ovl[i].size);
+	}
+	nvkm_debug(subdev, "\tcompressed           : %d\n", hdr->compressed);
+
+	return hdr;
+}
+
+const struct nvfw_ls_desc_v1 *
+nvfw_ls_desc_v1(struct nvkm_subdev *subdev, const void *data)
+{
+	const struct nvfw_ls_desc_v1 *hdr = data;
+	int i;
+
+	nvfw_ls_desc_head(subdev, &hdr->head);
+
+	nvkm_debug(subdev, "\tnbImemOverlays       : %d\n",
+			   hdr->nb_imem_overlays);
+	nvkm_debug(subdev, "\tnbDmemOverlays       : %d\n",
+			   hdr->nb_imem_overlays);
+	for (i = 0; i < ARRAY_SIZE(hdr->load_ovl); i++) {
+		nvkm_debug(subdev, "\tloadOvl[%2d]          : 0x%x %d\n", i,
+			   hdr->load_ovl[i].start, hdr->load_ovl[i].size);
+	}
+	nvkm_debug(subdev, "\tcompressed           : %d\n", hdr->compressed);
+
+	return hdr;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
index 4e136f3d7c28..fb4fff1222af 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/Kbuild
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: MIT
+include $(src)/nvkm/subdev/acr/Kbuild
 include $(src)/nvkm/subdev/bar/Kbuild
 include $(src)/nvkm/subdev/bios/Kbuild
 include $(src)/nvkm/subdev/bus/Kbuild
@@ -19,7 +20,6 @@ include $(src)/nvkm/subdev/mmu/Kbuild
 include $(src)/nvkm/subdev/mxm/Kbuild
 include $(src)/nvkm/subdev/pci/Kbuild
 include $(src)/nvkm/subdev/pmu/Kbuild
-include $(src)/nvkm/subdev/secboot/Kbuild
 include $(src)/nvkm/subdev/therm/Kbuild
 include $(src)/nvkm/subdev/timer/Kbuild
 include $(src)/nvkm/subdev/top/Kbuild
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/Kbuild
new file mode 100644
index 000000000000..5b9f64a8957f
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/Kbuild
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: MIT
+nvkm-y += nvkm/subdev/acr/base.o
+nvkm-y += nvkm/subdev/acr/hsfw.o
+nvkm-y += nvkm/subdev/acr/lsfw.o
+nvkm-y += nvkm/subdev/acr/gm200.o
+nvkm-y += nvkm/subdev/acr/gm20b.o
+nvkm-y += nvkm/subdev/acr/gp102.o
+nvkm-y += nvkm/subdev/acr/gp108.o
+nvkm-y += nvkm/subdev/acr/gp10b.o
+nvkm-y += nvkm/subdev/acr/tu102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c
new file mode 100644
index 000000000000..8eb2a930a9b5
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c
@@ -0,0 +1,411 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/firmware.h>
+#include <core/memory.h>
+#include <subdev/mmu.h>
+
+static struct nvkm_acr_hsf *
+nvkm_acr_hsf_find(struct nvkm_acr *acr, const char *name)
+{
+	struct nvkm_acr_hsf *hsf;
+	list_for_each_entry(hsf, &acr->hsf, head) {
+		if (!strcmp(hsf->name, name))
+			return hsf;
+	}
+	return NULL;
+}
+
+int
+nvkm_acr_hsf_boot(struct nvkm_acr *acr, const char *name)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	struct nvkm_acr_hsf *hsf;
+	int ret;
+
+	hsf = nvkm_acr_hsf_find(acr, name);
+	if (!hsf)
+		return -EINVAL;
+
+	nvkm_debug(subdev, "executing %s binary\n", hsf->name);
+	ret = nvkm_falcon_get(hsf->falcon, subdev);
+	if (ret)
+		return ret;
+
+	ret = hsf->func->boot(acr, hsf);
+	nvkm_falcon_put(hsf->falcon, subdev);
+	if (ret) {
+		nvkm_error(subdev, "%s binary failed\n", hsf->name);
+		return ret;
+	}
+
+	nvkm_debug(subdev, "%s binary completed successfully\n", hsf->name);
+	return 0;
+}
+
+static void
+nvkm_acr_unload(struct nvkm_acr *acr)
+{
+	if (acr->done) {
+		nvkm_acr_hsf_boot(acr, "unload");
+		acr->done = false;
+	}
+}
+
+static int
+nvkm_acr_load(struct nvkm_acr *acr)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	struct nvkm_acr_lsf *lsf;
+	u64 start, limit;
+	int ret;
+
+	if (list_empty(&acr->lsf)) {
+		nvkm_debug(subdev, "No LSF(s) present.\n");
+		return 0;
+	}
+
+	ret = acr->func->init(acr);
+	if (ret)
+		return ret;
+
+	acr->func->wpr_check(acr, &start, &limit);
+
+	if (start != acr->wpr_start || limit != acr->wpr_end) {
+		nvkm_error(subdev, "WPR not configured as expected: "
+				   "%016llx-%016llx vs %016llx-%016llx\n",
+			   acr->wpr_start, acr->wpr_end, start, limit);
+		return -EIO;
+	}
+
+	acr->done = true;
+
+	list_for_each_entry(lsf, &acr->lsf, head) {
+		if (lsf->func->boot) {
+			ret = lsf->func->boot(lsf->falcon);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+static int
+nvkm_acr_reload(struct nvkm_acr *acr)
+{
+	nvkm_acr_unload(acr);
+	return nvkm_acr_load(acr);
+}
+
+static struct nvkm_acr_lsf *
+nvkm_acr_falcon(struct nvkm_device *device)
+{
+	struct nvkm_acr *acr = device->acr;
+	struct nvkm_acr_lsf *lsf;
+
+	if (acr) {
+		list_for_each_entry(lsf, &acr->lsf, head) {
+			if (lsf->func->bootstrap_falcon)
+				return lsf;
+		}
+	}
+
+	return NULL;
+}
+
+int
+nvkm_acr_bootstrap_falcons(struct nvkm_device *device, unsigned long mask)
+{
+	struct nvkm_acr_lsf *acrflcn = nvkm_acr_falcon(device);
+	struct nvkm_acr *acr = device->acr;
+	unsigned long id;
+
+	if (!acrflcn) {
+		int ret = nvkm_acr_reload(acr);
+		if (ret)
+			return ret;
+
+		return acr->done ? 0 : -EINVAL;
+	}
+
+	if (acrflcn->func->bootstrap_multiple_falcons) {
+		return acrflcn->func->
+			bootstrap_multiple_falcons(acrflcn->falcon, mask);
+	}
+
+	for_each_set_bit(id, &mask, NVKM_ACR_LSF_NUM) {
+		int ret = acrflcn->func->bootstrap_falcon(acrflcn->falcon, id);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+bool
+nvkm_acr_managed_falcon(struct nvkm_device *device, enum nvkm_acr_lsf_id id)
+{
+	struct nvkm_acr *acr = device->acr;
+	struct nvkm_acr_lsf *lsf;
+
+	if (acr) {
+		list_for_each_entry(lsf, &acr->lsf, head) {
+			if (lsf->id == id)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static int
+nvkm_acr_fini(struct nvkm_subdev *subdev, bool suspend)
+{
+	nvkm_acr_unload(nvkm_acr(subdev));
+	return 0;
+}
+
+static int
+nvkm_acr_init(struct nvkm_subdev *subdev)
+{
+	if (!nvkm_acr_falcon(subdev->device))
+		return 0;
+
+	return nvkm_acr_load(nvkm_acr(subdev));
+}
+
+static void
+nvkm_acr_cleanup(struct nvkm_acr *acr)
+{
+	nvkm_acr_lsfw_del_all(acr);
+	nvkm_acr_hsfw_del_all(acr);
+	nvkm_firmware_put(acr->wpr_fw);
+	acr->wpr_fw = NULL;
+}
+
+static int
+nvkm_acr_oneinit(struct nvkm_subdev *subdev)
+{
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_acr *acr = nvkm_acr(subdev);
+	struct nvkm_acr_hsfw *hsfw;
+	struct nvkm_acr_lsfw *lsfw, *lsft;
+	struct nvkm_acr_lsf *lsf;
+	u32 wpr_size = 0;
+	int ret, i;
+
+	if (list_empty(&acr->hsfw)) {
+		nvkm_debug(subdev, "No HSFW(s)\n");
+		nvkm_acr_cleanup(acr);
+		return 0;
+	}
+
+	/* Determine layout/size of WPR image up-front, as we need to know
+	 * it to allocate memory before we begin constructing it.
+	 */
+	list_for_each_entry_safe(lsfw, lsft, &acr->lsfw, head) {
+		/* Cull unknown falcons that are present in WPR image. */
+		if (acr->wpr_fw) {
+			if (!lsfw->func) {
+				nvkm_acr_lsfw_del(lsfw);
+				continue;
+			}
+
+			wpr_size = acr->wpr_fw->size;
+		}
+
+		/* Ensure we've fetched falcon configuration. */
+		ret = nvkm_falcon_get(lsfw->falcon, subdev);
+		if (ret)
+			return ret;
+
+		nvkm_falcon_put(lsfw->falcon, subdev);
+
+		if (!(lsf = kmalloc(sizeof(*lsf), GFP_KERNEL)))
+			return -ENOMEM;
+		lsf->func = lsfw->func;
+		lsf->falcon = lsfw->falcon;
+		lsf->id = lsfw->id;
+		list_add_tail(&lsf->head, &acr->lsf);
+	}
+
+	if (!acr->wpr_fw || acr->wpr_comp)
+		wpr_size = acr->func->wpr_layout(acr);
+
+	/* Allocate/Locate WPR + fill ucode blob pointer.
+	 *
+	 *  dGPU: allocate WPR + shadow blob
+	 * Tegra: locate WPR with regs, ensure size is sufficient,
+	 *        allocate ucode blob.
+	 */
+	ret = acr->func->wpr_alloc(acr, wpr_size);
+	if (ret)
+		return ret;
+
+	nvkm_debug(subdev, "WPR region is from 0x%llx-0x%llx (shadow 0x%llx)\n",
+		   acr->wpr_start, acr->wpr_end, acr->shadow_start);
+
+	/* Write WPR to ucode blob. */
+	nvkm_kmap(acr->wpr);
+	if (acr->wpr_fw && !acr->wpr_comp)
+		nvkm_wobj(acr->wpr, 0, acr->wpr_fw->data, acr->wpr_fw->size);
+
+	if (!acr->wpr_fw || acr->wpr_comp)
+		acr->func->wpr_build(acr, nvkm_acr_falcon(device));
+	acr->func->wpr_patch(acr, (s64)acr->wpr_start - acr->wpr_prev);
+
+	if (acr->wpr_fw && acr->wpr_comp) {
+		nvkm_kmap(acr->wpr);
+		for (i = 0; i < acr->wpr_fw->size; i += 4) {
+			u32 us = nvkm_ro32(acr->wpr, i);
+			u32 fw = ((u32 *)acr->wpr_fw->data)[i/4];
+			if (fw != us) {
+				nvkm_warn(subdev, "%08x: %08x %08x\n",
+					  i, us, fw);
+			}
+		}
+		return -EINVAL;
+	}
+	nvkm_done(acr->wpr);
+
+	/* Allocate instance block for ACR-related stuff. */
+	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0, true,
+			      &acr->inst);
+	if (ret)
+		return ret;
+
+	ret = nvkm_vmm_new(device, 0, 0, NULL, 0, NULL, "acr", &acr->vmm);
+	if (ret)
+		return ret;
+
+	acr->vmm->debug = acr->subdev.debug;
+
+	ret = nvkm_vmm_join(acr->vmm, acr->inst);
+	if (ret)
+		return ret;
+
+	/* Load HS firmware blobs into ACR VMM. */
+	list_for_each_entry(hsfw, &acr->hsfw, head) {
+		nvkm_debug(subdev, "loading %s fw\n", hsfw->name);
+		ret = hsfw->func->load(acr, hsfw);
+		if (ret)
+			return ret;
+	}
+
+	/* Kill temporary data. */
+	nvkm_acr_cleanup(acr);
+	return 0;
+}
+
+static void *
+nvkm_acr_dtor(struct nvkm_subdev *subdev)
+{
+	struct nvkm_acr *acr = nvkm_acr(subdev);
+	struct nvkm_acr_hsf *hsf, *hst;
+	struct nvkm_acr_lsf *lsf, *lst;
+
+	list_for_each_entry_safe(hsf, hst, &acr->hsf, head) {
+		nvkm_vmm_put(acr->vmm, &hsf->vma);
+		nvkm_memory_unref(&hsf->ucode);
+		kfree(hsf->imem);
+		list_del(&hsf->head);
+		kfree(hsf);
+	}
+
+	nvkm_vmm_part(acr->vmm, acr->inst);
+	nvkm_vmm_unref(&acr->vmm);
+	nvkm_memory_unref(&acr->inst);
+
+	nvkm_memory_unref(&acr->wpr);
+
+	list_for_each_entry_safe(lsf, lst, &acr->lsf, head) {
+		list_del(&lsf->head);
+		kfree(lsf);
+	}
+
+	nvkm_acr_cleanup(acr);
+	return acr;
+}
+
+static const struct nvkm_subdev_func
+nvkm_acr = {
+	.dtor = nvkm_acr_dtor,
+	.oneinit = nvkm_acr_oneinit,
+	.init = nvkm_acr_init,
+	.fini = nvkm_acr_fini,
+};
+
+static int
+nvkm_acr_ctor_wpr(struct nvkm_acr *acr, int ver)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	struct nvkm_device *device = subdev->device;
+	int ret;
+
+	ret = nvkm_firmware_get(subdev, "acr/wpr", ver, &acr->wpr_fw);
+	if (ret < 0)
+		return ret;
+
+	/* Pre-add LSFs in the order they appear in the FW WPR image so that
+	 * we're able to do a binary comparison with our own generator.
+	 */
+	ret = acr->func->wpr_parse(acr);
+	if (ret)
+		return ret;
+
+	acr->wpr_comp = nvkm_boolopt(device->cfgopt, "NvAcrWprCompare", false);
+	acr->wpr_prev = nvkm_longopt(device->cfgopt, "NvAcrWprPrevAddr", 0);
+	return 0;
+}
+
+int
+nvkm_acr_new_(const struct nvkm_acr_fwif *fwif, struct nvkm_device *device,
+	      int index, struct nvkm_acr **pacr)
+{
+	struct nvkm_acr *acr;
+	long wprfw;
+
+	if (!(acr = *pacr = kzalloc(sizeof(*acr), GFP_KERNEL)))
+		return -ENOMEM;
+	nvkm_subdev_ctor(&nvkm_acr, device, index, &acr->subdev);
+	INIT_LIST_HEAD(&acr->hsfw);
+	INIT_LIST_HEAD(&acr->lsfw);
+	INIT_LIST_HEAD(&acr->hsf);
+	INIT_LIST_HEAD(&acr->lsf);
+
+	fwif = nvkm_firmware_load(&acr->subdev, fwif, "Acr", acr);
+	if (IS_ERR(fwif))
+		return PTR_ERR(fwif);
+
+	acr->func = fwif->func;
+
+	wprfw = nvkm_longopt(device->cfgopt, "NvAcrWpr", -1);
+	if (wprfw >= 0) {
+		int ret = nvkm_acr_ctor_wpr(acr, wprfw);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c
new file mode 100644
index 000000000000..9a6394085cf0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm200.c
@@ -0,0 +1,470 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/falcon.h>
+#include <core/firmware.h>
+#include <core/memory.h>
+#include <subdev/mc.h>
+#include <subdev/mmu.h>
+#include <subdev/pmu.h>
+#include <subdev/timer.h>
+
+#include <nvfw/acr.h>
+#include <nvfw/flcn.h>
+
+int
+gm200_acr_init(struct nvkm_acr *acr)
+{
+	return nvkm_acr_hsf_boot(acr, "load");
+}
+
+void
+gm200_acr_wpr_check(struct nvkm_acr *acr, u64 *start, u64 *limit)
+{
+	struct nvkm_device *device = acr->subdev.device;
+
+	nvkm_wr32(device, 0x100cd4, 2);
+	*start = (u64)(nvkm_rd32(device, 0x100cd4) & 0xffffff00) << 8;
+	nvkm_wr32(device, 0x100cd4, 3);
+	*limit = (u64)(nvkm_rd32(device, 0x100cd4) & 0xffffff00) << 8;
+	*limit = *limit + 0x20000;
+}
+
+void
+gm200_acr_wpr_patch(struct nvkm_acr *acr, s64 adjust)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	struct wpr_header hdr;
+	struct lsb_header lsb;
+	struct nvkm_acr_lsf *lsfw;
+	u32 offset = 0;
+
+	do {
+		nvkm_robj(acr->wpr, offset, &hdr, sizeof(hdr));
+		wpr_header_dump(subdev, &hdr);
+
+		list_for_each_entry(lsfw, &acr->lsfw, head) {
+			if (lsfw->id != hdr.falcon_id)
+				continue;
+
+			nvkm_robj(acr->wpr, hdr.lsb_offset, &lsb, sizeof(lsb));
+			lsb_header_dump(subdev, &lsb);
+
+			lsfw->func->bld_patch(acr, lsb.tail.bl_data_off, adjust);
+			break;
+		}
+		offset += sizeof(hdr);
+	} while (hdr.falcon_id != WPR_HEADER_V0_FALCON_ID_INVALID);
+}
+
+void
+gm200_acr_wpr_build_lsb_tail(struct nvkm_acr_lsfw *lsfw,
+			     struct lsb_header_tail *hdr)
+{
+	hdr->ucode_off = lsfw->offset.img;
+	hdr->ucode_size = lsfw->ucode_size;
+	hdr->data_size = lsfw->data_size;
+	hdr->bl_code_size = lsfw->bootloader_size;
+	hdr->bl_imem_off = lsfw->bootloader_imem_offset;
+	hdr->bl_data_off = lsfw->offset.bld;
+	hdr->bl_data_size = lsfw->bl_data_size;
+	hdr->app_code_off = lsfw->app_start_offset +
+			   lsfw->app_resident_code_offset;
+	hdr->app_code_size = lsfw->app_resident_code_size;
+	hdr->app_data_off = lsfw->app_start_offset +
+			   lsfw->app_resident_data_offset;
+	hdr->app_data_size = lsfw->app_resident_data_size;
+	hdr->flags = lsfw->func->flags;
+}
+
+static int
+gm200_acr_wpr_build_lsb(struct nvkm_acr *acr, struct nvkm_acr_lsfw *lsfw)
+{
+	struct lsb_header hdr;
+
+	if (WARN_ON(lsfw->sig->size != sizeof(hdr.signature)))
+		return -EINVAL;
+
+	memcpy(&hdr.signature, lsfw->sig->data, lsfw->sig->size);
+	gm200_acr_wpr_build_lsb_tail(lsfw, &hdr.tail);
+
+	nvkm_wobj(acr->wpr, lsfw->offset.lsb, &hdr, sizeof(hdr));
+	return 0;
+}
+
+int
+gm200_acr_wpr_build(struct nvkm_acr *acr, struct nvkm_acr_lsf *rtos)
+{
+	struct nvkm_acr_lsfw *lsfw;
+	u32 offset = 0;
+	int ret;
+
+	/* Fill per-LSF structures. */
+	list_for_each_entry(lsfw, &acr->lsfw, head) {
+		struct wpr_header hdr = {
+			.falcon_id = lsfw->id,
+			.lsb_offset = lsfw->offset.lsb,
+			.bootstrap_owner = NVKM_ACR_LSF_PMU,
+			.lazy_bootstrap = rtos && lsfw->id != rtos->id,
+			.status = WPR_HEADER_V0_STATUS_COPY,
+		};
+
+		/* Write WPR header. */
+		nvkm_wobj(acr->wpr, offset, &hdr, sizeof(hdr));
+		offset += sizeof(hdr);
+
+		/* Write LSB header. */
+		ret = gm200_acr_wpr_build_lsb(acr, lsfw);
+		if (ret)
+			return ret;
+
+		/* Write ucode image. */
+		nvkm_wobj(acr->wpr, lsfw->offset.img,
+				    lsfw->img.data,
+				    lsfw->img.size);
+
+		/* Write bootloader data. */
+		lsfw->func->bld_write(acr, lsfw->offset.bld, lsfw);
+	}
+
+	/* Finalise WPR. */
+	nvkm_wo32(acr->wpr, offset, WPR_HEADER_V0_FALCON_ID_INVALID);
+	return 0;
+}
+
+static int
+gm200_acr_wpr_alloc(struct nvkm_acr *acr, u32 wpr_size)
+{
+	int ret = nvkm_memory_new(acr->subdev.device, NVKM_MEM_TARGET_INST,
+				  ALIGN(wpr_size, 0x40000), 0x40000, true,
+				  &acr->wpr);
+	if (ret)
+		return ret;
+
+	acr->wpr_start = nvkm_memory_addr(acr->wpr);
+	acr->wpr_end = acr->wpr_start + nvkm_memory_size(acr->wpr);
+	return 0;
+}
+
+u32
+gm200_acr_wpr_layout(struct nvkm_acr *acr)
+{
+	struct nvkm_acr_lsfw *lsfw;
+	u32 wpr = 0;
+
+	wpr += 11 /* MAX_LSF */ * sizeof(struct wpr_header);
+
+	list_for_each_entry(lsfw, &acr->lsfw, head) {
+		wpr  = ALIGN(wpr, 256);
+		lsfw->offset.lsb = wpr;
+		wpr += sizeof(struct lsb_header);
+
+		wpr  = ALIGN(wpr, 4096);
+		lsfw->offset.img = wpr;
+		wpr += lsfw->img.size;
+
+		wpr  = ALIGN(wpr, 256);
+		lsfw->offset.bld = wpr;
+		lsfw->bl_data_size = ALIGN(lsfw->func->bld_size, 256);
+		wpr += lsfw->bl_data_size;
+	}
+
+	return wpr;
+}
+
+int
+gm200_acr_wpr_parse(struct nvkm_acr *acr)
+{
+	const struct wpr_header *hdr = (void *)acr->wpr_fw->data;
+
+	while (hdr->falcon_id != WPR_HEADER_V0_FALCON_ID_INVALID) {
+		wpr_header_dump(&acr->subdev, hdr);
+		if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void
+gm200_acr_hsfw_bld(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf)
+{
+	struct flcn_bl_dmem_desc_v1 hsdesc = {
+		.ctx_dma = FALCON_DMAIDX_VIRT,
+		.code_dma_base = hsf->vma->addr,
+		.non_sec_code_off = hsf->non_sec_addr,
+		.non_sec_code_size = hsf->non_sec_size,
+		.sec_code_off = hsf->sec_addr,
+		.sec_code_size = hsf->sec_size,
+		.code_entry_point = 0,
+		.data_dma_base = hsf->vma->addr + hsf->data_addr,
+		.data_size = hsf->data_size,
+	};
+
+	flcn_bl_dmem_desc_v1_dump(&acr->subdev, &hsdesc);
+
+	nvkm_falcon_load_dmem(hsf->falcon, &hsdesc, 0, sizeof(hsdesc), 0);
+}
+
+int
+gm200_acr_hsfw_boot(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf,
+		    u32 intr_clear, u32 mbox0_ok)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_falcon *falcon = hsf->falcon;
+	u32 mbox0, mbox1;
+	int ret;
+
+	/* Reset falcon. */
+	nvkm_falcon_reset(falcon);
+	nvkm_falcon_bind_context(falcon, acr->inst);
+
+	/* Load bootloader into IMEM. */
+	nvkm_falcon_load_imem(falcon, hsf->imem,
+				      falcon->code.limit - hsf->imem_size,
+				      hsf->imem_size,
+				      hsf->imem_tag,
+				      0, false);
+
+	/* Load bootloader data into DMEM. */
+	hsf->func->bld(acr, hsf);
+
+	/* Boot the falcon. */
+	nvkm_mc_intr_mask(device, falcon->owner->index, false);
+
+	nvkm_falcon_wr32(falcon, 0x040, 0xdeada5a5);
+	nvkm_falcon_set_start_addr(falcon, hsf->imem_tag << 8);
+	nvkm_falcon_start(falcon);
+	ret = nvkm_falcon_wait_for_halt(falcon, 100);
+	if (ret)
+		return ret;
+
+	/* Check for successful completion. */
+	mbox0 = nvkm_falcon_rd32(falcon, 0x040);
+	mbox1 = nvkm_falcon_rd32(falcon, 0x044);
+	nvkm_debug(subdev, "mailbox %08x %08x\n", mbox0, mbox1);
+	if (mbox0 && mbox0 != mbox0_ok)
+		return -EIO;
+
+	nvkm_falcon_clear_interrupt(falcon, intr_clear);
+	nvkm_mc_intr_mask(device, falcon->owner->index, true);
+	return ret;
+}
+
+int
+gm200_acr_hsfw_load(struct nvkm_acr *acr, struct nvkm_acr_hsfw *hsfw,
+		    struct nvkm_falcon *falcon)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	struct nvkm_acr_hsf *hsf;
+	int ret;
+
+	/* Patch the appropriate signature (production/debug) into the FW
+	 * image, as determined by the mode the falcon is in.
+	 */
+	ret = nvkm_falcon_get(falcon, subdev);
+	if (ret)
+		return ret;
+
+	if (hsfw->sig.patch_loc) {
+		if (!falcon->debug) {
+			nvkm_debug(subdev, "patching production signature\n");
+			memcpy(hsfw->image + hsfw->sig.patch_loc,
+			       hsfw->sig.prod.data,
+			       hsfw->sig.prod.size);
+		} else {
+			nvkm_debug(subdev, "patching debug signature\n");
+			memcpy(hsfw->image + hsfw->sig.patch_loc,
+			       hsfw->sig.dbg.data,
+			       hsfw->sig.dbg.size);
+		}
+	}
+
+	nvkm_falcon_put(falcon, subdev);
+
+	if (!(hsf = kzalloc(sizeof(*hsf), GFP_KERNEL)))
+		return -ENOMEM;
+	hsf->func = hsfw->func;
+	hsf->name = hsfw->name;
+	list_add_tail(&hsf->head, &acr->hsf);
+
+	hsf->imem_size = hsfw->imem_size;
+	hsf->imem_tag = hsfw->imem_tag;
+	hsf->imem = kmemdup(hsfw->imem, hsfw->imem_size, GFP_KERNEL);
+	if (!hsf->imem)
+		return -ENOMEM;
+
+	hsf->non_sec_addr = hsfw->non_sec_addr;
+	hsf->non_sec_size = hsfw->non_sec_size;
+	hsf->sec_addr = hsfw->sec_addr;
+	hsf->sec_size = hsfw->sec_size;
+	hsf->data_addr = hsfw->data_addr;
+	hsf->data_size = hsfw->data_size;
+
+	/* Make the FW image accessible to the HS bootloader. */
+	ret = nvkm_memory_new(subdev->device, NVKM_MEM_TARGET_INST,
+			      hsfw->image_size, 0x1000, false, &hsf->ucode);
+	if (ret)
+		return ret;
+
+	nvkm_kmap(hsf->ucode);
+	nvkm_wobj(hsf->ucode, 0, hsfw->image, hsfw->image_size);
+	nvkm_done(hsf->ucode);
+
+	ret = nvkm_vmm_get(acr->vmm, 12, nvkm_memory_size(hsf->ucode),
+			   &hsf->vma);
+	if (ret)
+		return ret;
+
+	ret = nvkm_memory_map(hsf->ucode, 0, acr->vmm, hsf->vma, NULL, 0);
+	if (ret)
+		return ret;
+
+	hsf->falcon = falcon;
+	return 0;
+}
+
+int
+gm200_acr_unload_boot(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf)
+{
+	return gm200_acr_hsfw_boot(acr, hsf, 0, 0x1d);
+}
+
+int
+gm200_acr_unload_load(struct nvkm_acr *acr, struct nvkm_acr_hsfw *hsfw)
+{
+	return gm200_acr_hsfw_load(acr, hsfw, &acr->subdev.device->pmu->falcon);
+}
+
+const struct nvkm_acr_hsf_func
+gm200_acr_unload_0 = {
+	.load = gm200_acr_unload_load,
+	.boot = gm200_acr_unload_boot,
+	.bld = gm200_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/gm200/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gm204/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gm206/acr/ucode_unload.bin");
+MODULE_FIRMWARE("nvidia/gp100/acr/ucode_unload.bin");
+
+static const struct nvkm_acr_hsf_fwif
+gm200_acr_unload_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gm200_acr_unload_0 },
+	{}
+};
+
+int
+gm200_acr_load_boot(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf)
+{
+	return gm200_acr_hsfw_boot(acr, hsf, 0x10, 0);
+}
+
+static int
+gm200_acr_load_load(struct nvkm_acr *acr, struct nvkm_acr_hsfw *hsfw)
+{
+	struct flcn_acr_desc *desc = (void *)&hsfw->image[hsfw->data_addr];
+
+	desc->wpr_region_id = 1;
+	desc->regions.no_regions = 2;
+	desc->regions.region_props[0].start_addr = acr->wpr_start >> 8;
+	desc->regions.region_props[0].end_addr = acr->wpr_end >> 8;
+	desc->regions.region_props[0].region_id = 1;
+	desc->regions.region_props[0].read_mask = 0xf;
+	desc->regions.region_props[0].write_mask = 0xc;
+	desc->regions.region_props[0].client_mask = 0x2;
+	flcn_acr_desc_dump(&acr->subdev, desc);
+
+	return gm200_acr_hsfw_load(acr, hsfw, &acr->subdev.device->pmu->falcon);
+}
+
+static const struct nvkm_acr_hsf_func
+gm200_acr_load_0 = {
+	.load = gm200_acr_load_load,
+	.boot = gm200_acr_load_boot,
+	.bld = gm200_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/gm200/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gm200/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gm204/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gm204/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gm206/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gm206/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gp100/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp100/acr/ucode_load.bin");
+
+static const struct nvkm_acr_hsf_fwif
+gm200_acr_load_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gm200_acr_load_0 },
+	{}
+};
+
+static const struct nvkm_acr_func
+gm200_acr = {
+	.load = gm200_acr_load_fwif,
+	.unload = gm200_acr_unload_fwif,
+	.wpr_parse = gm200_acr_wpr_parse,
+	.wpr_layout = gm200_acr_wpr_layout,
+	.wpr_alloc = gm200_acr_wpr_alloc,
+	.wpr_build = gm200_acr_wpr_build,
+	.wpr_patch = gm200_acr_wpr_patch,
+	.wpr_check = gm200_acr_wpr_check,
+	.init = gm200_acr_init,
+};
+
+static int
+gm200_acr_load(struct nvkm_acr *acr, int ver, const struct nvkm_acr_fwif *fwif)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	const struct nvkm_acr_hsf_fwif *hsfwif;
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->load, "AcrLoad",
+				    acr, "acr/bl", "acr/ucode_load", "load");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->unload, "AcrUnload",
+				    acr, "acr/bl", "acr/ucode_unload",
+				    "unload");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	return 0;
+}
+
+static const struct nvkm_acr_fwif
+gm200_acr_fwif[] = {
+	{ 0, gm200_acr_load, &gm200_acr },
+	{}
+};
+
+int
+gm200_acr_new(struct nvkm_device *device, int index, struct nvkm_acr **pacr)
+{
+	return nvkm_acr_new_(gm200_acr_fwif, device, index, pacr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm20b.c
new file mode 100644
index 000000000000..034a6ede70c7
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gm20b.c
@@ -0,0 +1,134 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/firmware.h>
+#include <core/memory.h>
+#include <subdev/mmu.h>
+#include <subdev/pmu.h>
+
+#include <nvfw/acr.h>
+#include <nvfw/flcn.h>
+
+int
+gm20b_acr_wpr_alloc(struct nvkm_acr *acr, u32 wpr_size)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+
+	acr->func->wpr_check(acr, &acr->wpr_start, &acr->wpr_end);
+
+	if ((acr->wpr_end - acr->wpr_start) < wpr_size) {
+		nvkm_error(subdev, "WPR image too big for WPR!\n");
+		return -ENOSPC;
+	}
+
+	return nvkm_memory_new(subdev->device, NVKM_MEM_TARGET_INST,
+			       wpr_size, 0, true, &acr->wpr);
+}
+
+static void
+gm20b_acr_load_bld(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf)
+{
+	struct flcn_bl_dmem_desc hsdesc = {
+		.ctx_dma = FALCON_DMAIDX_VIRT,
+		.code_dma_base = hsf->vma->addr >> 8,
+		.non_sec_code_off = hsf->non_sec_addr,
+		.non_sec_code_size = hsf->non_sec_size,
+		.sec_code_off = hsf->sec_addr,
+		.sec_code_size = hsf->sec_size,
+		.code_entry_point = 0,
+		.data_dma_base = (hsf->vma->addr + hsf->data_addr) >> 8,
+		.data_size = hsf->data_size,
+	};
+
+	flcn_bl_dmem_desc_dump(&acr->subdev, &hsdesc);
+
+	nvkm_falcon_load_dmem(hsf->falcon, &hsdesc, 0, sizeof(hsdesc), 0);
+}
+
+static int
+gm20b_acr_load_load(struct nvkm_acr *acr, struct nvkm_acr_hsfw *hsfw)
+{
+	struct flcn_acr_desc *desc = (void *)&hsfw->image[hsfw->data_addr];
+
+	desc->ucode_blob_base = nvkm_memory_addr(acr->wpr);
+	desc->ucode_blob_size = nvkm_memory_size(acr->wpr);
+	flcn_acr_desc_dump(&acr->subdev, desc);
+
+	return gm200_acr_hsfw_load(acr, hsfw, &acr->subdev.device->pmu->falcon);
+}
+
+const struct nvkm_acr_hsf_func
+gm20b_acr_load_0 = {
+	.load = gm20b_acr_load_load,
+	.boot = gm200_acr_load_boot,
+	.bld = gm20b_acr_load_bld,
+};
+
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+MODULE_FIRMWARE("nvidia/gm20b/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gm20b/acr/ucode_load.bin");
+#endif
+
+static const struct nvkm_acr_hsf_fwif
+gm20b_acr_load_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gm20b_acr_load_0 },
+	{}
+};
+
+static const struct nvkm_acr_func
+gm20b_acr = {
+	.load = gm20b_acr_load_fwif,
+	.wpr_parse = gm200_acr_wpr_parse,
+	.wpr_layout = gm200_acr_wpr_layout,
+	.wpr_alloc = gm20b_acr_wpr_alloc,
+	.wpr_build = gm200_acr_wpr_build,
+	.wpr_patch = gm200_acr_wpr_patch,
+	.wpr_check = gm200_acr_wpr_check,
+	.init = gm200_acr_init,
+};
+
+int
+gm20b_acr_load(struct nvkm_acr *acr, int ver, const struct nvkm_acr_fwif *fwif)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	const struct nvkm_acr_hsf_fwif *hsfwif;
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->load, "AcrLoad",
+				    acr, "acr/bl", "acr/ucode_load", "load");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	return 0;
+}
+
+static const struct nvkm_acr_fwif
+gm20b_acr_fwif[] = {
+	{ 0, gm20b_acr_load, &gm20b_acr },
+	{}
+};
+
+int
+gm20b_acr_new(struct nvkm_device *device, int index, struct nvkm_acr **pacr)
+{
+	return nvkm_acr_new_(gm20b_acr_fwif, device, index, pacr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c
new file mode 100644
index 000000000000..49e11c46d525
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp102.c
@@ -0,0 +1,281 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/firmware.h>
+#include <core/memory.h>
+#include <subdev/mmu.h>
+#include <engine/sec2.h>
+
+#include <nvfw/acr.h>
+#include <nvfw/flcn.h>
+
+void
+gp102_acr_wpr_patch(struct nvkm_acr *acr, s64 adjust)
+{
+	struct wpr_header_v1 hdr;
+	struct lsb_header_v1 lsb;
+	struct nvkm_acr_lsfw *lsfw;
+	u32 offset = 0;
+
+	do {
+		nvkm_robj(acr->wpr, offset, &hdr, sizeof(hdr));
+		wpr_header_v1_dump(&acr->subdev, &hdr);
+
+		list_for_each_entry(lsfw, &acr->lsfw, head) {
+			if (lsfw->id != hdr.falcon_id)
+				continue;
+
+			nvkm_robj(acr->wpr, hdr.lsb_offset, &lsb, sizeof(lsb));
+			lsb_header_v1_dump(&acr->subdev, &lsb);
+
+			lsfw->func->bld_patch(acr, lsb.tail.bl_data_off, adjust);
+			break;
+		}
+
+		offset += sizeof(hdr);
+	} while (hdr.falcon_id != WPR_HEADER_V1_FALCON_ID_INVALID);
+}
+
+int
+gp102_acr_wpr_build_lsb(struct nvkm_acr *acr, struct nvkm_acr_lsfw *lsfw)
+{
+	struct lsb_header_v1 hdr;
+
+	if (WARN_ON(lsfw->sig->size != sizeof(hdr.signature)))
+		return -EINVAL;
+
+	memcpy(&hdr.signature, lsfw->sig->data, lsfw->sig->size);
+	gm200_acr_wpr_build_lsb_tail(lsfw, &hdr.tail);
+
+	nvkm_wobj(acr->wpr, lsfw->offset.lsb, &hdr, sizeof(hdr));
+	return 0;
+}
+
+int
+gp102_acr_wpr_build(struct nvkm_acr *acr, struct nvkm_acr_lsf *rtos)
+{
+	struct nvkm_acr_lsfw *lsfw;
+	u32 offset = 0;
+	int ret;
+
+	/* Fill per-LSF structures. */
+	list_for_each_entry(lsfw, &acr->lsfw, head) {
+		struct lsf_signature_v1 *sig = (void *)lsfw->sig->data;
+		struct wpr_header_v1 hdr = {
+			.falcon_id = lsfw->id,
+			.lsb_offset = lsfw->offset.lsb,
+			.bootstrap_owner = NVKM_ACR_LSF_SEC2,
+			.lazy_bootstrap = rtos && lsfw->id != rtos->id,
+			.bin_version = sig->version,
+			.status = WPR_HEADER_V1_STATUS_COPY,
+		};
+
+		/* Write WPR header. */
+		nvkm_wobj(acr->wpr, offset, &hdr, sizeof(hdr));
+		offset += sizeof(hdr);
+
+		/* Write LSB header. */
+		ret = gp102_acr_wpr_build_lsb(acr, lsfw);
+		if (ret)
+			return ret;
+
+		/* Write ucode image. */
+		nvkm_wobj(acr->wpr, lsfw->offset.img,
+				    lsfw->img.data,
+				    lsfw->img.size);
+
+		/* Write bootloader data. */
+		lsfw->func->bld_write(acr, lsfw->offset.bld, lsfw);
+	}
+
+	/* Finalise WPR. */
+	nvkm_wo32(acr->wpr, offset, WPR_HEADER_V1_FALCON_ID_INVALID);
+	return 0;
+}
+
+int
+gp102_acr_wpr_alloc(struct nvkm_acr *acr, u32 wpr_size)
+{
+	int ret = nvkm_memory_new(acr->subdev.device, NVKM_MEM_TARGET_INST,
+				  ALIGN(wpr_size, 0x40000) << 1, 0x40000, true,
+				  &acr->wpr);
+	if (ret)
+		return ret;
+
+	acr->shadow_start = nvkm_memory_addr(acr->wpr);
+	acr->wpr_start = acr->shadow_start + (nvkm_memory_size(acr->wpr) >> 1);
+	acr->wpr_end = acr->wpr_start + (nvkm_memory_size(acr->wpr) >> 1);
+	return 0;
+}
+
+u32
+gp102_acr_wpr_layout(struct nvkm_acr *acr)
+{
+	struct nvkm_acr_lsfw *lsfw;
+	u32 wpr = 0;
+
+	wpr += 11 /* MAX_LSF */ * sizeof(struct wpr_header_v1);
+	wpr  = ALIGN(wpr, 256);
+
+	wpr += 0x100; /* Shared sub-WPR headers. */
+
+	list_for_each_entry(lsfw, &acr->lsfw, head) {
+		wpr  = ALIGN(wpr, 256);
+		lsfw->offset.lsb = wpr;
+		wpr += sizeof(struct lsb_header_v1);
+
+		wpr  = ALIGN(wpr, 4096);
+		lsfw->offset.img = wpr;
+		wpr += lsfw->img.size;
+
+		wpr  = ALIGN(wpr, 256);
+		lsfw->offset.bld = wpr;
+		lsfw->bl_data_size = ALIGN(lsfw->func->bld_size, 256);
+		wpr += lsfw->bl_data_size;
+	}
+
+	return wpr;
+}
+
+int
+gp102_acr_wpr_parse(struct nvkm_acr *acr)
+{
+	const struct wpr_header_v1 *hdr = (void *)acr->wpr_fw->data;
+
+	while (hdr->falcon_id != WPR_HEADER_V1_FALCON_ID_INVALID) {
+		wpr_header_v1_dump(&acr->subdev, hdr);
+		if (!nvkm_acr_lsfw_add(NULL, acr, NULL, (hdr++)->falcon_id))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+MODULE_FIRMWARE("nvidia/gp102/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp102/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/gp104/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp104/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/gp106/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp106/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/gp107/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp107/acr/ucode_unload.bin");
+
+static const struct nvkm_acr_hsf_fwif
+gp102_acr_unload_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gm200_acr_unload_0 },
+	{}
+};
+
+int
+gp102_acr_load_load(struct nvkm_acr *acr, struct nvkm_acr_hsfw *hsfw)
+{
+	struct flcn_acr_desc_v1 *desc = (void *)&hsfw->image[hsfw->data_addr];
+
+	desc->wpr_region_id = 1;
+	desc->regions.no_regions = 2;
+	desc->regions.region_props[0].start_addr = acr->wpr_start >> 8;
+	desc->regions.region_props[0].end_addr = acr->wpr_end >> 8;
+	desc->regions.region_props[0].region_id = 1;
+	desc->regions.region_props[0].read_mask = 0xf;
+	desc->regions.region_props[0].write_mask = 0xc;
+	desc->regions.region_props[0].client_mask = 0x2;
+	desc->regions.region_props[0].shadow_mem_start_addr =
+		acr->shadow_start >> 8;
+	flcn_acr_desc_v1_dump(&acr->subdev, desc);
+
+	return gm200_acr_hsfw_load(acr, hsfw,
+				  &acr->subdev.device->sec2->falcon);
+}
+
+static const struct nvkm_acr_hsf_func
+gp102_acr_load_0 = {
+	.load = gp102_acr_load_load,
+	.boot = gm200_acr_load_boot,
+	.bld = gm200_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/gp102/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp102/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gp104/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp104/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gp106/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp106/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gp107/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp107/acr/ucode_load.bin");
+
+static const struct nvkm_acr_hsf_fwif
+gp102_acr_load_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gp102_acr_load_0 },
+	{}
+};
+
+static const struct nvkm_acr_func
+gp102_acr = {
+	.load = gp102_acr_load_fwif,
+	.unload = gp102_acr_unload_fwif,
+	.wpr_parse = gp102_acr_wpr_parse,
+	.wpr_layout = gp102_acr_wpr_layout,
+	.wpr_alloc = gp102_acr_wpr_alloc,
+	.wpr_build = gp102_acr_wpr_build,
+	.wpr_patch = gp102_acr_wpr_patch,
+	.wpr_check = gm200_acr_wpr_check,
+	.init = gm200_acr_init,
+};
+
+int
+gp102_acr_load(struct nvkm_acr *acr, int ver, const struct nvkm_acr_fwif *fwif)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	const struct nvkm_acr_hsf_fwif *hsfwif;
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->load, "AcrLoad",
+				    acr, "acr/bl", "acr/ucode_load", "load");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->unload, "AcrUnload",
+				    acr, "acr/unload_bl", "acr/ucode_unload",
+				    "unload");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	return 0;
+}
+
+static const struct nvkm_acr_fwif
+gp102_acr_fwif[] = {
+	{ 0, gp102_acr_load, &gp102_acr },
+	{}
+};
+
+int
+gp102_acr_new(struct nvkm_device *device, int index, struct nvkm_acr **pacr)
+{
+	return nvkm_acr_new_(gp102_acr_fwif, device, index, pacr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp108.c
new file mode 100644
index 000000000000..f10dc9112678
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp108.c
@@ -0,0 +1,111 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <subdev/mmu.h>
+
+#include <nvfw/flcn.h>
+
+void
+gp108_acr_hsfw_bld(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf)
+{
+	struct flcn_bl_dmem_desc_v2 hsdesc = {
+		.ctx_dma = FALCON_DMAIDX_VIRT,
+		.code_dma_base = hsf->vma->addr,
+		.non_sec_code_off = hsf->non_sec_addr,
+		.non_sec_code_size = hsf->non_sec_size,
+		.sec_code_off = hsf->sec_addr,
+		.sec_code_size = hsf->sec_size,
+		.code_entry_point = 0,
+		.data_dma_base = hsf->vma->addr + hsf->data_addr,
+		.data_size = hsf->data_size,
+		.argc = 0,
+		.argv = 0,
+	};
+
+	flcn_bl_dmem_desc_v2_dump(&acr->subdev, &hsdesc);
+
+	nvkm_falcon_load_dmem(hsf->falcon, &hsdesc, 0, sizeof(hsdesc), 0);
+}
+
+const struct nvkm_acr_hsf_func
+gp108_acr_unload_0 = {
+	.load = gm200_acr_unload_load,
+	.boot = gm200_acr_unload_boot,
+	.bld = gp108_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/gp108/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/gv100/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/acr/ucode_unload.bin");
+
+static const struct nvkm_acr_hsf_fwif
+gp108_acr_unload_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 },
+	{}
+};
+
+static const struct nvkm_acr_hsf_func
+gp108_acr_load_0 = {
+	.load = gp102_acr_load_load,
+	.boot = gm200_acr_load_boot,
+	.bld = gp108_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/gp108/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp108/acr/ucode_load.bin");
+
+MODULE_FIRMWARE("nvidia/gv100/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gv100/acr/ucode_load.bin");
+
+static const struct nvkm_acr_hsf_fwif
+gp108_acr_load_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gp108_acr_load_0 },
+	{}
+};
+
+static const struct nvkm_acr_func
+gp108_acr = {
+	.load = gp108_acr_load_fwif,
+	.unload = gp108_acr_unload_fwif,
+	.wpr_parse = gp102_acr_wpr_parse,
+	.wpr_layout = gp102_acr_wpr_layout,
+	.wpr_alloc = gp102_acr_wpr_alloc,
+	.wpr_build = gp102_acr_wpr_build,
+	.wpr_patch = gp102_acr_wpr_patch,
+	.wpr_check = gm200_acr_wpr_check,
+	.init = gm200_acr_init,
+};
+
+static const struct nvkm_acr_fwif
+gp108_acr_fwif[] = {
+	{ 0, gp102_acr_load, &gp108_acr },
+	{}
+};
+
+int
+gp108_acr_new(struct nvkm_device *device, int index, struct nvkm_acr **pacr)
+{
+	return nvkm_acr_new_(gp108_acr_fwif, device, index, pacr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp10b.c
new file mode 100644
index 000000000000..39de64292a41
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/gp10b.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
+MODULE_FIRMWARE("nvidia/gp10b/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/gp10b/acr/ucode_load.bin");
+#endif
+
+static const struct nvkm_acr_hsf_fwif
+gp10b_acr_load_fwif[] = {
+	{ 0, nvkm_acr_hsfw_load, &gm20b_acr_load_0 },
+	{}
+};
+
+static const struct nvkm_acr_func
+gp10b_acr = {
+	.load = gp10b_acr_load_fwif,
+	.wpr_parse = gm200_acr_wpr_parse,
+	.wpr_layout = gm200_acr_wpr_layout,
+	.wpr_alloc = gm20b_acr_wpr_alloc,
+	.wpr_build = gm200_acr_wpr_build,
+	.wpr_patch = gm200_acr_wpr_patch,
+	.wpr_check = gm200_acr_wpr_check,
+	.init = gm200_acr_init,
+};
+
+static const struct nvkm_acr_fwif
+gp10b_acr_fwif[] = {
+	{ 0, gm20b_acr_load, &gp10b_acr },
+	{}
+};
+
+int
+gp10b_acr_new(struct nvkm_device *device, int index, struct nvkm_acr **pacr)
+{
+	return nvkm_acr_new_(gp10b_acr_fwif, device, index, pacr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/hsfw.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/hsfw.c
new file mode 100644
index 000000000000..aecce2dac558
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/hsfw.c
@@ -0,0 +1,180 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/firmware.h>
+
+#include <nvfw/fw.h>
+#include <nvfw/hs.h>
+
+static void
+nvkm_acr_hsfw_del(struct nvkm_acr_hsfw *hsfw)
+{
+	list_del(&hsfw->head);
+	kfree(hsfw->imem);
+	kfree(hsfw->image);
+	kfree(hsfw->sig.prod.data);
+	kfree(hsfw->sig.dbg.data);
+	kfree(hsfw);
+}
+
+void
+nvkm_acr_hsfw_del_all(struct nvkm_acr *acr)
+{
+	struct nvkm_acr_hsfw *hsfw, *hsft;
+	list_for_each_entry_safe(hsfw, hsft, &acr->hsfw, head) {
+		nvkm_acr_hsfw_del(hsfw);
+	}
+}
+
+static int
+nvkm_acr_hsfw_load_image(struct nvkm_acr *acr, const char *name, int ver,
+			 struct nvkm_acr_hsfw *hsfw)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	const struct firmware *fw;
+	const struct nvfw_bin_hdr *hdr;
+	const struct nvfw_hs_header *fwhdr;
+	const struct nvfw_hs_load_header *lhdr;
+	u32 loc, sig;
+	int ret;
+
+	ret = nvkm_firmware_get(subdev, name, ver, &fw);
+	if (ret < 0)
+		return ret;
+
+	hdr = nvfw_bin_hdr(subdev, fw->data);
+	fwhdr = nvfw_hs_header(subdev, fw->data + hdr->header_offset);
+
+	/* Earlier FW releases by NVIDIA for Nouveau's use aren't in NVIDIA's
+	 * standard format, and don't have the indirection seen in the 0x10de
+	 * case.
+	 */
+	switch (hdr->bin_magic) {
+	case 0x000010de:
+		loc = *(u32 *)(fw->data + fwhdr->patch_loc);
+		sig = *(u32 *)(fw->data + fwhdr->patch_sig);
+		break;
+	case 0x3b1d14f0:
+		loc = fwhdr->patch_loc;
+		sig = fwhdr->patch_sig;
+		break;
+	default:
+		ret = -EINVAL;
+		goto done;
+	}
+
+	lhdr = nvfw_hs_load_header(subdev, fw->data + fwhdr->hdr_offset);
+
+	if (!(hsfw->image = kmalloc(hdr->data_size, GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	memcpy(hsfw->image, fw->data + hdr->data_offset, hdr->data_size);
+	hsfw->image_size = hdr->data_size;
+	hsfw->non_sec_addr = lhdr->non_sec_code_off;
+	hsfw->non_sec_size = lhdr->non_sec_code_size;
+	hsfw->sec_addr = lhdr->apps[0];
+	hsfw->sec_size = lhdr->apps[lhdr->num_apps];
+	hsfw->data_addr = lhdr->data_dma_base;
+	hsfw->data_size = lhdr->data_size;
+
+	hsfw->sig.prod.size = fwhdr->sig_prod_size;
+	hsfw->sig.prod.data = kmalloc(hsfw->sig.prod.size, GFP_KERNEL);
+	if (!hsfw->sig.prod.data) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	memcpy(hsfw->sig.prod.data, fw->data + fwhdr->sig_prod_offset + sig,
+	       hsfw->sig.prod.size);
+
+	hsfw->sig.dbg.size = fwhdr->sig_dbg_size;
+	hsfw->sig.dbg.data = kmalloc(hsfw->sig.dbg.size, GFP_KERNEL);
+	if (!hsfw->sig.dbg.data) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	memcpy(hsfw->sig.dbg.data, fw->data + fwhdr->sig_dbg_offset + sig,
+	       hsfw->sig.dbg.size);
+
+	hsfw->sig.patch_loc = loc;
+done:
+	nvkm_firmware_put(fw);
+	return ret;
+}
+
+static int
+nvkm_acr_hsfw_load_bl(struct nvkm_acr *acr, const char *name, int ver,
+		      struct nvkm_acr_hsfw *hsfw)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	const struct nvfw_bin_hdr *hdr;
+	const struct nvfw_bl_desc *desc;
+	const struct firmware *fw;
+	u8 *data;
+	int ret;
+
+	ret = nvkm_firmware_get(subdev, name, ver, &fw);
+	if (ret)
+		return ret;
+
+	hdr = nvfw_bin_hdr(subdev, fw->data);
+	desc = nvfw_bl_desc(subdev, fw->data + hdr->header_offset);
+	data = (void *)fw->data + hdr->data_offset;
+
+	hsfw->imem_size = desc->code_size;
+	hsfw->imem_tag = desc->start_tag;
+	hsfw->imem = kmalloc(desc->code_size, GFP_KERNEL);
+	memcpy(hsfw->imem, data + desc->code_off, desc->code_size);
+
+	nvkm_firmware_put(fw);
+	return 0;
+}
+
+int
+nvkm_acr_hsfw_load(struct nvkm_acr *acr, const char *bl, const char *fw,
+		   const char *name, int version,
+		   const struct nvkm_acr_hsf_fwif *fwif)
+{
+	struct nvkm_acr_hsfw *hsfw;
+	int ret;
+
+	if (!(hsfw = kzalloc(sizeof(*hsfw), GFP_KERNEL)))
+		return -ENOMEM;
+
+	hsfw->func = fwif->func;
+	hsfw->name = name;
+	list_add_tail(&hsfw->head, &acr->hsfw);
+
+	ret = nvkm_acr_hsfw_load_bl(acr, bl, version, hsfw);
+	if (ret)
+		goto done;
+
+	ret = nvkm_acr_hsfw_load_image(acr, fw, version, hsfw);
+done:
+	if (ret)
+		nvkm_acr_hsfw_del(hsfw);
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/lsfw.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/lsfw.c
new file mode 100644
index 000000000000..07d1830126ab
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/lsfw.c
@@ -0,0 +1,253 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+#include <core/falcon.h>
+#include <core/firmware.h>
+#include <nvfw/fw.h>
+#include <nvfw/ls.h>
+
+void
+nvkm_acr_lsfw_del(struct nvkm_acr_lsfw *lsfw)
+{
+	nvkm_blob_dtor(&lsfw->img);
+	nvkm_firmware_put(lsfw->sig);
+	list_del(&lsfw->head);
+	kfree(lsfw);
+}
+
+void
+nvkm_acr_lsfw_del_all(struct nvkm_acr *acr)
+{
+	struct nvkm_acr_lsfw *lsfw, *lsft;
+	list_for_each_entry_safe(lsfw, lsft, &acr->lsfw, head) {
+		nvkm_acr_lsfw_del(lsfw);
+	}
+}
+
+static struct nvkm_acr_lsfw *
+nvkm_acr_lsfw_get(struct nvkm_acr *acr, enum nvkm_acr_lsf_id id)
+{
+	struct nvkm_acr_lsfw *lsfw;
+	list_for_each_entry(lsfw, &acr->lsfw, head) {
+		if (lsfw->id == id)
+			return lsfw;
+	}
+	return NULL;
+}
+
+struct nvkm_acr_lsfw *
+nvkm_acr_lsfw_add(const struct nvkm_acr_lsf_func *func, struct nvkm_acr *acr,
+		 struct nvkm_falcon *falcon, enum nvkm_acr_lsf_id id)
+{
+	struct nvkm_acr_lsfw *lsfw;
+
+	if (!acr)
+		return ERR_PTR(-ENOSYS);
+
+	lsfw = nvkm_acr_lsfw_get(acr, id);
+	if (lsfw && lsfw->func) {
+		nvkm_error(&acr->subdev, "LSFW %d redefined\n", id);
+		return ERR_PTR(-EEXIST);
+	}
+
+	if (!lsfw) {
+		if (!(lsfw = kzalloc(sizeof(*lsfw), GFP_KERNEL)))
+			return ERR_PTR(-ENOMEM);
+
+		lsfw->id = id;
+		list_add_tail(&lsfw->head, &acr->lsfw);
+	}
+
+	lsfw->func = func;
+	lsfw->falcon = falcon;
+	return lsfw;
+}
+
+static struct nvkm_acr_lsfw *
+nvkm_acr_lsfw_load_sig_image_desc_(struct nvkm_subdev *subdev,
+				   struct nvkm_falcon *falcon,
+				   enum nvkm_acr_lsf_id id,
+				   const char *path, int ver,
+				   const struct nvkm_acr_lsf_func *func,
+				   const struct firmware **pdesc)
+{
+	struct nvkm_acr *acr = subdev->device->acr;
+	struct nvkm_acr_lsfw *lsfw;
+	int ret;
+
+	if (IS_ERR((lsfw = nvkm_acr_lsfw_add(func, acr, falcon, id))))
+		return lsfw;
+
+	ret = nvkm_firmware_load_name(subdev, path, "sig", ver, &lsfw->sig);
+	if (ret)
+		goto done;
+
+	ret = nvkm_firmware_load_blob(subdev, path, "image", ver, &lsfw->img);
+	if (ret)
+		goto done;
+
+	ret = nvkm_firmware_load_name(subdev, path, "desc", ver, pdesc);
+done:
+	if (ret) {
+		nvkm_acr_lsfw_del(lsfw);
+		return ERR_PTR(ret);
+	}
+
+	return lsfw;
+}
+
+static void
+nvkm_acr_lsfw_from_desc(const struct nvfw_ls_desc_head *desc,
+			struct nvkm_acr_lsfw *lsfw)
+{
+	lsfw->bootloader_size = ALIGN(desc->bootloader_size, 256);
+	lsfw->bootloader_imem_offset = desc->bootloader_imem_offset;
+
+	lsfw->app_size = ALIGN(desc->app_size, 256);
+	lsfw->app_start_offset = desc->app_start_offset;
+	lsfw->app_imem_entry = desc->app_imem_entry;
+	lsfw->app_resident_code_offset = desc->app_resident_code_offset;
+	lsfw->app_resident_code_size = desc->app_resident_code_size;
+	lsfw->app_resident_data_offset = desc->app_resident_data_offset;
+	lsfw->app_resident_data_size = desc->app_resident_data_size;
+
+	lsfw->ucode_size = ALIGN(lsfw->app_resident_data_offset, 256) +
+			   lsfw->bootloader_size;
+	lsfw->data_size = lsfw->app_size + lsfw->bootloader_size -
+			  lsfw->ucode_size;
+}
+
+int
+nvkm_acr_lsfw_load_sig_image_desc(struct nvkm_subdev *subdev,
+				  struct nvkm_falcon *falcon,
+				  enum nvkm_acr_lsf_id id,
+				  const char *path, int ver,
+				  const struct nvkm_acr_lsf_func *func)
+{
+	const struct firmware *fw;
+	struct nvkm_acr_lsfw *lsfw;
+
+	lsfw = nvkm_acr_lsfw_load_sig_image_desc_(subdev, falcon, id, path, ver,
+						  func, &fw);
+	if (IS_ERR(lsfw))
+		return PTR_ERR(lsfw);
+
+	nvkm_acr_lsfw_from_desc(&nvfw_ls_desc(subdev, fw->data)->head, lsfw);
+	nvkm_firmware_put(fw);
+	return 0;
+}
+
+int
+nvkm_acr_lsfw_load_sig_image_desc_v1(struct nvkm_subdev *subdev,
+				     struct nvkm_falcon *falcon,
+				     enum nvkm_acr_lsf_id id,
+				     const char *path, int ver,
+				     const struct nvkm_acr_lsf_func *func)
+{
+	const struct firmware *fw;
+	struct nvkm_acr_lsfw *lsfw;
+
+	lsfw = nvkm_acr_lsfw_load_sig_image_desc_(subdev, falcon, id, path, ver,
+						  func, &fw);
+	if (IS_ERR(lsfw))
+		return PTR_ERR(lsfw);
+
+	nvkm_acr_lsfw_from_desc(&nvfw_ls_desc_v1(subdev, fw->data)->head, lsfw);
+	nvkm_firmware_put(fw);
+	return 0;
+}
+
+int
+nvkm_acr_lsfw_load_bl_inst_data_sig(struct nvkm_subdev *subdev,
+				    struct nvkm_falcon *falcon,
+				    enum nvkm_acr_lsf_id id,
+				    const char *path, int ver,
+				    const struct nvkm_acr_lsf_func *func)
+{
+	struct nvkm_acr *acr = subdev->device->acr;
+	struct nvkm_acr_lsfw *lsfw;
+	const struct firmware *bl = NULL, *inst = NULL, *data = NULL;
+	const struct nvfw_bin_hdr *hdr;
+	const struct nvfw_bl_desc *desc;
+	u32 *bldata;
+	int ret;
+
+	if (IS_ERR((lsfw = nvkm_acr_lsfw_add(func, acr, falcon, id))))
+		return PTR_ERR(lsfw);
+
+	ret = nvkm_firmware_load_name(subdev, path, "bl", ver, &bl);
+	if (ret)
+		goto done;
+
+	hdr = nvfw_bin_hdr(subdev, bl->data);
+	desc = nvfw_bl_desc(subdev, bl->data + hdr->header_offset);
+	bldata = (void *)(bl->data + hdr->data_offset);
+
+	ret = nvkm_firmware_load_name(subdev, path, "inst", ver, &inst);
+	if (ret)
+		goto done;
+
+	ret = nvkm_firmware_load_name(subdev, path, "data", ver, &data);
+	if (ret)
+		goto done;
+
+	ret = nvkm_firmware_load_name(subdev, path, "sig", ver, &lsfw->sig);
+	if (ret)
+		goto done;
+
+	lsfw->bootloader_size = ALIGN(desc->code_size, 256);
+	lsfw->bootloader_imem_offset = desc->start_tag << 8;
+
+	lsfw->app_start_offset = lsfw->bootloader_size;
+	lsfw->app_imem_entry = 0;
+	lsfw->app_resident_code_offset = 0;
+	lsfw->app_resident_code_size = ALIGN(inst->size, 256);
+	lsfw->app_resident_data_offset = lsfw->app_resident_code_size;
+	lsfw->app_resident_data_size = ALIGN(data->size, 256);
+	lsfw->app_size = lsfw->app_resident_code_size +
+			 lsfw->app_resident_data_size;
+
+	lsfw->img.size = lsfw->bootloader_size + lsfw->app_size;
+	if (!(lsfw->img.data = kzalloc(lsfw->img.size, GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto done;
+	}
+
+	memcpy(lsfw->img.data, bldata, lsfw->bootloader_size);
+	memcpy(lsfw->img.data + lsfw->app_start_offset +
+	       lsfw->app_resident_code_offset, inst->data, inst->size);
+	memcpy(lsfw->img.data + lsfw->app_start_offset +
+	       lsfw->app_resident_data_offset, data->data, data->size);
+
+	lsfw->ucode_size = ALIGN(lsfw->app_resident_data_offset, 256) +
+			   lsfw->bootloader_size;
+	lsfw->data_size = lsfw->app_size + lsfw->bootloader_size -
+			  lsfw->ucode_size;
+
+done:
+	if (ret)
+		nvkm_acr_lsfw_del(lsfw);
+	nvkm_firmware_put(data);
+	nvkm_firmware_put(inst);
+	nvkm_firmware_put(bl);
+	return ret;
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/priv.h
new file mode 100644
index 000000000000..d8ba72806d39
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/priv.h
@@ -0,0 +1,151 @@
+#ifndef __NVKM_ACR_PRIV_H__
+#define __NVKM_ACR_PRIV_H__
+#include <subdev/acr.h>
+struct lsb_header_tail;
+
+struct nvkm_acr_fwif {
+	int version;
+	int (*load)(struct nvkm_acr *, int version,
+		    const struct nvkm_acr_fwif *);
+	const struct nvkm_acr_func *func;
+};
+
+int gm20b_acr_load(struct nvkm_acr *, int, const struct nvkm_acr_fwif *);
+int gp102_acr_load(struct nvkm_acr *, int, const struct nvkm_acr_fwif *);
+
+struct nvkm_acr_lsf;
+struct nvkm_acr_func {
+	const struct nvkm_acr_hsf_fwif *load;
+	const struct nvkm_acr_hsf_fwif *ahesasc;
+	const struct nvkm_acr_hsf_fwif *asb;
+	const struct nvkm_acr_hsf_fwif *unload;
+	int (*wpr_parse)(struct nvkm_acr *);
+	u32 (*wpr_layout)(struct nvkm_acr *);
+	int (*wpr_alloc)(struct nvkm_acr *, u32 wpr_size);
+	int (*wpr_build)(struct nvkm_acr *, struct nvkm_acr_lsf *rtos);
+	void (*wpr_patch)(struct nvkm_acr *, s64 adjust);
+	void (*wpr_check)(struct nvkm_acr *, u64 *start, u64 *limit);
+	int (*init)(struct nvkm_acr *);
+	void (*fini)(struct nvkm_acr *);
+};
+
+int gm200_acr_wpr_parse(struct nvkm_acr *);
+u32 gm200_acr_wpr_layout(struct nvkm_acr *);
+int gm200_acr_wpr_build(struct nvkm_acr *, struct nvkm_acr_lsf *);
+void gm200_acr_wpr_patch(struct nvkm_acr *, s64);
+void gm200_acr_wpr_check(struct nvkm_acr *, u64 *, u64 *);
+void gm200_acr_wpr_build_lsb_tail(struct nvkm_acr_lsfw *,
+				  struct lsb_header_tail *);
+int gm200_acr_init(struct nvkm_acr *);
+
+int gm20b_acr_wpr_alloc(struct nvkm_acr *, u32 wpr_size);
+
+int gp102_acr_wpr_parse(struct nvkm_acr *);
+u32 gp102_acr_wpr_layout(struct nvkm_acr *);
+int gp102_acr_wpr_alloc(struct nvkm_acr *, u32 wpr_size);
+int gp102_acr_wpr_build(struct nvkm_acr *, struct nvkm_acr_lsf *);
+int gp102_acr_wpr_build_lsb(struct nvkm_acr *, struct nvkm_acr_lsfw *);
+void gp102_acr_wpr_patch(struct nvkm_acr *, s64);
+
+struct nvkm_acr_hsfw {
+	const struct nvkm_acr_hsf_func *func;
+	const char *name;
+	struct list_head head;
+
+	u32 imem_size;
+	u32 imem_tag;
+	u32 *imem;
+
+	u8 *image;
+	u32 image_size;
+	u32 non_sec_addr;
+	u32 non_sec_size;
+	u32 sec_addr;
+	u32 sec_size;
+	u32 data_addr;
+	u32 data_size;
+
+	struct {
+		struct {
+			void *data;
+			u32 size;
+		} prod, dbg;
+		u32 patch_loc;
+	} sig;
+};
+
+struct nvkm_acr_hsf_fwif {
+	int version;
+	int (*load)(struct nvkm_acr *, const char *bl, const char *fw,
+		    const char *name, int version,
+		    const struct nvkm_acr_hsf_fwif *);
+	const struct nvkm_acr_hsf_func *func;
+};
+
+int nvkm_acr_hsfw_load(struct nvkm_acr *, const char *, const char *,
+		       const char *, int, const struct nvkm_acr_hsf_fwif *);
+void nvkm_acr_hsfw_del_all(struct nvkm_acr *);
+
+struct nvkm_acr_hsf {
+	const struct nvkm_acr_hsf_func *func;
+	const char *name;
+	struct list_head head;
+
+	u32 imem_size;
+	u32 imem_tag;
+	u32 *imem;
+
+	u32 non_sec_addr;
+	u32 non_sec_size;
+	u32 sec_addr;
+	u32 sec_size;
+	u32 data_addr;
+	u32 data_size;
+
+	struct nvkm_memory *ucode;
+	struct nvkm_vma *vma;
+	struct nvkm_falcon *falcon;
+};
+
+struct nvkm_acr_hsf_func {
+	int (*load)(struct nvkm_acr *, struct nvkm_acr_hsfw *);
+	int (*boot)(struct nvkm_acr *, struct nvkm_acr_hsf *);
+	void (*bld)(struct nvkm_acr *, struct nvkm_acr_hsf *);
+};
+
+int gm200_acr_hsfw_load(struct nvkm_acr *, struct nvkm_acr_hsfw *,
+			struct nvkm_falcon *);
+int gm200_acr_hsfw_boot(struct nvkm_acr *, struct nvkm_acr_hsf *,
+			u32 clear_intr, u32 mbox0_ok);
+
+int gm200_acr_load_boot(struct nvkm_acr *, struct nvkm_acr_hsf *);
+
+extern const struct nvkm_acr_hsf_func gm200_acr_unload_0;
+int gm200_acr_unload_load(struct nvkm_acr *, struct nvkm_acr_hsfw *);
+int gm200_acr_unload_boot(struct nvkm_acr *, struct nvkm_acr_hsf *);
+void gm200_acr_hsfw_bld(struct nvkm_acr *, struct nvkm_acr_hsf *);
+
+extern const struct nvkm_acr_hsf_func gm20b_acr_load_0;
+
+int gp102_acr_load_load(struct nvkm_acr *, struct nvkm_acr_hsfw *);
+
+extern const struct nvkm_acr_hsf_func gp108_acr_unload_0;
+void gp108_acr_hsfw_bld(struct nvkm_acr *, struct nvkm_acr_hsf *);
+
+int nvkm_acr_new_(const struct nvkm_acr_fwif *, struct nvkm_device *, int,
+		  struct nvkm_acr **);
+int nvkm_acr_hsf_boot(struct nvkm_acr *, const char *name);
+
+struct nvkm_acr_lsf {
+	const struct nvkm_acr_lsf_func *func;
+	struct nvkm_falcon *falcon;
+	enum nvkm_acr_lsf_id id;
+	struct list_head head;
+};
+
+struct nvkm_acr_lsfw *nvkm_acr_lsfw_add(const struct nvkm_acr_lsf_func *,
+					struct nvkm_acr *, struct nvkm_falcon *,
+					enum nvkm_acr_lsf_id);
+void nvkm_acr_lsfw_del(struct nvkm_acr_lsfw *);
+void nvkm_acr_lsfw_del_all(struct nvkm_acr *);
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
new file mode 100644
index 000000000000..7f4b89d82d32
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/tu102.c
@@ -0,0 +1,215 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <core/firmware.h>
+#include <core/memory.h>
+#include <subdev/gsp.h>
+#include <subdev/pmu.h>
+#include <engine/sec2.h>
+
+#include <nvfw/acr.h>
+
+static int
+tu102_acr_init(struct nvkm_acr *acr)
+{
+	int ret = nvkm_acr_hsf_boot(acr, "AHESASC");
+	if (ret)
+		return ret;
+
+	return nvkm_acr_hsf_boot(acr, "ASB");
+}
+
+static int
+tu102_acr_wpr_build(struct nvkm_acr *acr, struct nvkm_acr_lsf *rtos)
+{
+	struct nvkm_acr_lsfw *lsfw;
+	u32 offset = 0;
+	int ret;
+
+	/*XXX: shared sub-WPR headers, fill terminator for now. */
+	nvkm_wo32(acr->wpr, 0x200, 0xffffffff);
+
+	/* Fill per-LSF structures. */
+	list_for_each_entry(lsfw, &acr->lsfw, head) {
+		struct lsf_signature_v1 *sig = (void *)lsfw->sig->data;
+		struct wpr_header_v1 hdr = {
+			.falcon_id = lsfw->id,
+			.lsb_offset = lsfw->offset.lsb,
+			.bootstrap_owner = NVKM_ACR_LSF_GSPLITE,
+			.lazy_bootstrap = 1,
+			.bin_version = sig->version,
+			.status = WPR_HEADER_V1_STATUS_COPY,
+		};
+
+		/* Write WPR header. */
+		nvkm_wobj(acr->wpr, offset, &hdr, sizeof(hdr));
+		offset += sizeof(hdr);
+
+		/* Write LSB header. */
+		ret = gp102_acr_wpr_build_lsb(acr, lsfw);
+		if (ret)
+			return ret;
+
+		/* Write ucode image. */
+		nvkm_wobj(acr->wpr, lsfw->offset.img,
+				    lsfw->img.data,
+				    lsfw->img.size);
+
+		/* Write bootloader data. */
+		lsfw->func->bld_write(acr, lsfw->offset.bld, lsfw);
+	}
+
+	/* Finalise WPR. */
+	nvkm_wo32(acr->wpr, offset, WPR_HEADER_V1_FALCON_ID_INVALID);
+	return 0;
+}
+
+static int
+tu102_acr_hsfw_boot(struct nvkm_acr *acr, struct nvkm_acr_hsf *hsf)
+{
+	return gm200_acr_hsfw_boot(acr, hsf, 0, 0);
+}
+
+static int
+tu102_acr_hsfw_nofw(struct nvkm_acr *acr, const char *bl, const char *fw,
+		    const char *name, int version,
+		    const struct nvkm_acr_hsf_fwif *fwif)
+{
+	return 0;
+}
+
+MODULE_FIRMWARE("nvidia/tu102/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu102/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/tu104/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu104/acr/ucode_unload.bin");
+
+MODULE_FIRMWARE("nvidia/tu106/acr/unload_bl.bin");
+MODULE_FIRMWARE("nvidia/tu106/acr/ucode_unload.bin");
+
+static const struct nvkm_acr_hsf_fwif
+tu102_acr_unload_fwif[] = {
+	{  0, nvkm_acr_hsfw_load, &gp108_acr_unload_0 },
+	{ -1, tu102_acr_hsfw_nofw },
+	{}
+};
+
+static int
+tu102_acr_asb_load(struct nvkm_acr *acr, struct nvkm_acr_hsfw *hsfw)
+{
+	return gm200_acr_hsfw_load(acr, hsfw, &acr->subdev.device->gsp->falcon);
+}
+
+static const struct nvkm_acr_hsf_func
+tu102_acr_asb_0 = {
+	.load = tu102_acr_asb_load,
+	.boot = tu102_acr_hsfw_boot,
+	.bld = gp108_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/tu102/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu104/acr/ucode_asb.bin");
+MODULE_FIRMWARE("nvidia/tu106/acr/ucode_asb.bin");
+
+static const struct nvkm_acr_hsf_fwif
+tu102_acr_asb_fwif[] = {
+	{  0, nvkm_acr_hsfw_load, &tu102_acr_asb_0 },
+	{ -1, tu102_acr_hsfw_nofw },
+	{}
+};
+
+static const struct nvkm_acr_hsf_func
+tu102_acr_ahesasc_0 = {
+	.load = gp102_acr_load_load,
+	.boot = tu102_acr_hsfw_boot,
+	.bld = gp108_acr_hsfw_bld,
+};
+
+MODULE_FIRMWARE("nvidia/tu102/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu102/acr/ucode_ahesasc.bin");
+
+MODULE_FIRMWARE("nvidia/tu104/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu104/acr/ucode_ahesasc.bin");
+
+MODULE_FIRMWARE("nvidia/tu106/acr/bl.bin");
+MODULE_FIRMWARE("nvidia/tu106/acr/ucode_ahesasc.bin");
+
+static const struct nvkm_acr_hsf_fwif
+tu102_acr_ahesasc_fwif[] = {
+	{  0, nvkm_acr_hsfw_load, &tu102_acr_ahesasc_0 },
+	{ -1, tu102_acr_hsfw_nofw },
+	{}
+};
+
+static const struct nvkm_acr_func
+tu102_acr = {
+	.ahesasc = tu102_acr_ahesasc_fwif,
+	.asb = tu102_acr_asb_fwif,
+	.unload = tu102_acr_unload_fwif,
+	.wpr_parse = gp102_acr_wpr_parse,
+	.wpr_layout = gp102_acr_wpr_layout,
+	.wpr_alloc = gp102_acr_wpr_alloc,
+	.wpr_patch = gp102_acr_wpr_patch,
+	.wpr_build = tu102_acr_wpr_build,
+	.wpr_check = gm200_acr_wpr_check,
+	.init = tu102_acr_init,
+};
+
+static int
+tu102_acr_load(struct nvkm_acr *acr, int version,
+	       const struct nvkm_acr_fwif *fwif)
+{
+	struct nvkm_subdev *subdev = &acr->subdev;
+	const struct nvkm_acr_hsf_fwif *hsfwif;
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->ahesasc, "AcrAHESASC",
+				    acr, "acr/bl", "acr/ucode_ahesasc",
+				    "AHESASC");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->asb, "AcrASB",
+				    acr, "acr/bl", "acr/ucode_asb", "ASB");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	hsfwif = nvkm_firmware_load(subdev, fwif->func->unload, "AcrUnload",
+				    acr, "acr/unload_bl", "acr/ucode_unload",
+				    "unload");
+	if (IS_ERR(hsfwif))
+		return PTR_ERR(hsfwif);
+
+	return 0;
+}
+
+static const struct nvkm_acr_fwif
+tu102_acr_fwif[] = {
+	{  0, tu102_acr_load, &tu102_acr },
+	{}
+};
+
+int
+tu102_acr_new(struct nvkm_device *device, int index, struct nvkm_acr **pacr)
+{
+	return nvkm_acr_new_(tu102_acr_fwif, device, index, pacr);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
index 53b9d638f2c8..d65ec719f153 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/Kbuild
@@ -2,5 +2,6 @@
 nvkm-y += nvkm/subdev/fault/base.o
 nvkm-y += nvkm/subdev/fault/user.o
 nvkm-y += nvkm/subdev/fault/gp100.o
+nvkm-y += nvkm/subdev/fault/gp10b.o
 nvkm-y += nvkm/subdev/fault/gv100.o
 nvkm-y += nvkm/subdev/fault/tu102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
index ca251560d3e0..f6dca97140d6 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -108,7 +108,7 @@ nvkm_fault_oneinit_buffer(struct nvkm_fault *fault, int id)
 		return ret;
 
 	/* Pin fault buffer in BAR2. */
-	buffer->addr = nvkm_memory_bar2(buffer->mem);
+	buffer->addr = fault->func->buffer.pin(buffer);
 	if (buffer->addr == ~0ULL)
 		return -EFAULT;
 
@@ -146,6 +146,7 @@ nvkm_fault_dtor(struct nvkm_subdev *subdev)
 	struct nvkm_fault *fault = nvkm_fault(subdev);
 	int i;
 
+	nvkm_notify_fini(&fault->nrpfb);
 	nvkm_event_fini(&fault->event);
 
 	for (i = 0; i < fault->buffer_nr; i++) {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c
index 4f3c4e091117..f6b189cc4330 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp100.c
@@ -21,25 +21,26 @@
  */
 #include "priv.h"
 
+#include <core/memory.h>
 #include <subdev/mc.h>
 
 #include <nvif/class.h>
 
-static void
+void
 gp100_fault_buffer_intr(struct nvkm_fault_buffer *buffer, bool enable)
 {
 	struct nvkm_device *device = buffer->fault->subdev.device;
 	nvkm_mc_intr_mask(device, NVKM_SUBDEV_FAULT, enable);
 }
 
-static void
+void
 gp100_fault_buffer_fini(struct nvkm_fault_buffer *buffer)
 {
 	struct nvkm_device *device = buffer->fault->subdev.device;
 	nvkm_mask(device, 0x002a70, 0x00000001, 0x00000000);
 }
 
-static void
+void
 gp100_fault_buffer_init(struct nvkm_fault_buffer *buffer)
 {
 	struct nvkm_device *device = buffer->fault->subdev.device;
@@ -48,7 +49,12 @@ gp100_fault_buffer_init(struct nvkm_fault_buffer *buffer)
 	nvkm_mask(device, 0x002a70, 0x00000001, 0x00000001);
 }
 
-static void
+u64 gp100_fault_buffer_pin(struct nvkm_fault_buffer *buffer)
+{
+	return nvkm_memory_bar2(buffer->mem);
+}
+
+void
 gp100_fault_buffer_info(struct nvkm_fault_buffer *buffer)
 {
 	buffer->entries = nvkm_rd32(buffer->fault->subdev.device, 0x002a78);
@@ -56,7 +62,7 @@ gp100_fault_buffer_info(struct nvkm_fault_buffer *buffer)
 	buffer->put = 0x002a80;
 }
 
-static void
+void
 gp100_fault_intr(struct nvkm_fault *fault)
 {
 	nvkm_event_send(&fault->event, 1, 0, NULL, 0);
@@ -68,6 +74,7 @@ gp100_fault = {
 	.buffer.nr = 1,
 	.buffer.entry_size = 32,
 	.buffer.info = gp100_fault_buffer_info,
+	.buffer.pin = gp100_fault_buffer_pin,
 	.buffer.init = gp100_fault_buffer_init,
 	.buffer.fini = gp100_fault_buffer_fini,
 	.buffer.intr = gp100_fault_buffer_intr,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_cik.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp10b.c
index 19e54acb4125..9e66d1f7654d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue_cik.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gp10b.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2014 Advanced Micro Devices, Inc.
+ * Copyright (c) 2019 NVIDIA Corporation.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -18,36 +18,36 @@
  * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
- *
  */
 
-#include "kfd_kernel_queue.h"
+#include "priv.h"
 
-static bool initialize_cik(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size);
-static void uninitialize_cik(struct kernel_queue *kq);
-static void submit_packet_cik(struct kernel_queue *kq);
+#include <core/memory.h>
 
-void kernel_queue_init_cik(struct kernel_queue_ops *ops)
-{
-	ops->initialize = initialize_cik;
-	ops->uninitialize = uninitialize_cik;
-	ops->submit_packet = submit_packet_cik;
-}
+#include <nvif/class.h>
 
-static bool initialize_cik(struct kernel_queue *kq, struct kfd_dev *dev,
-			enum kfd_queue_type type, unsigned int queue_size)
+u64
+gp10b_fault_buffer_pin(struct nvkm_fault_buffer *buffer)
 {
-	return true;
+	return nvkm_memory_addr(buffer->mem);
 }
 
-static void uninitialize_cik(struct kernel_queue *kq)
-{
-}
+static const struct nvkm_fault_func
+gp10b_fault = {
+	.intr = gp100_fault_intr,
+	.buffer.nr = 1,
+	.buffer.entry_size = 32,
+	.buffer.info = gp100_fault_buffer_info,
+	.buffer.pin = gp10b_fault_buffer_pin,
+	.buffer.init = gp100_fault_buffer_init,
+	.buffer.fini = gp100_fault_buffer_fini,
+	.buffer.intr = gp100_fault_buffer_intr,
+	.user = { { 0, 0, MAXWELL_FAULT_BUFFER_A }, 0 },
+};
 
-static void submit_packet_cik(struct kernel_queue *kq)
+int
+gp10b_fault_new(struct nvkm_device *device, int index,
+		struct nvkm_fault **pfault)
 {
-	*kq->wptr_kernel = kq->pending_wptr;
-	write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
-				kq->pending_wptr);
+	return nvkm_fault_new_(&gp10b_fault, device, index, pfault);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
index 6747f09c2dc3..2707be4ffabc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
@@ -214,6 +214,7 @@ gv100_fault = {
 	.buffer.nr = 2,
 	.buffer.entry_size = 32,
 	.buffer.info = gv100_fault_buffer_info,
+	.buffer.pin = gp100_fault_buffer_pin,
 	.buffer.init = gv100_fault_buffer_init,
 	.buffer.fini = gv100_fault_buffer_fini,
 	.buffer.intr = gv100_fault_buffer_intr,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
index 975e66ac6344..f6f1dd7eee1f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
@@ -30,6 +30,7 @@ struct nvkm_fault_func {
 		int nr;
 		u32 entry_size;
 		void (*info)(struct nvkm_fault_buffer *);
+		u64 (*pin)(struct nvkm_fault_buffer *);
 		void (*init)(struct nvkm_fault_buffer *);
 		void (*fini)(struct nvkm_fault_buffer *);
 		void (*intr)(struct nvkm_fault_buffer *, bool enable);
@@ -40,6 +41,15 @@ struct nvkm_fault_func {
 	} user;
 };
 
+void gp100_fault_buffer_intr(struct nvkm_fault_buffer *, bool enable);
+void gp100_fault_buffer_fini(struct nvkm_fault_buffer *);
+void gp100_fault_buffer_init(struct nvkm_fault_buffer *);
+u64 gp100_fault_buffer_pin(struct nvkm_fault_buffer *);
+void gp100_fault_buffer_info(struct nvkm_fault_buffer *);
+void gp100_fault_intr(struct nvkm_fault *);
+
+u64 gp10b_fault_buffer_pin(struct nvkm_fault_buffer *);
+
 int gv100_fault_oneinit(struct nvkm_fault *);
 
 int nvkm_ufault_new(struct nvkm_device *, const struct nvkm_oclass *,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/tu102.c
index fa1dfe5692b0..45a6a68b9f48 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/tu102.c
@@ -154,6 +154,7 @@ tu102_fault = {
 	.buffer.nr = 2,
 	.buffer.entry_size = 32,
 	.buffer.info = tu102_fault_buffer_info,
+	.buffer.pin = gp100_fault_buffer_pin,
 	.buffer.init = tu102_fault_buffer_init,
 	.buffer.fini = tu102_fault_buffer_fini,
 	.buffer.intr = tu102_fault_buffer_intr,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
index b2bb5a3ccb02..5940e0dea2f8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
@@ -126,6 +126,34 @@ nvkm_fb_oneinit(struct nvkm_subdev *subdev)
 }
 
 static int
+nvkm_fb_init_scrub_vpr(struct nvkm_fb *fb)
+{
+	struct nvkm_subdev *subdev = &fb->subdev;
+	int ret;
+
+	nvkm_debug(subdev, "VPR locked, running scrubber binary\n");
+
+	if (!fb->vpr_scrubber.size) {
+		nvkm_warn(subdev, "VPR locked, but no scrubber binary!\n");
+		return 0;
+	}
+
+	ret = fb->func->vpr.scrub(fb);
+	if (ret) {
+		nvkm_error(subdev, "VPR scrubber binary failed\n");
+		return ret;
+	}
+
+	if (fb->func->vpr.scrub_required(fb)) {
+		nvkm_error(subdev, "VPR still locked after scrub!\n");
+		return -EIO;
+	}
+
+	nvkm_debug(subdev, "VPR scrubber binary successful\n");
+	return 0;
+}
+
+static int
 nvkm_fb_init(struct nvkm_subdev *subdev)
 {
 	struct nvkm_fb *fb = nvkm_fb(subdev);
@@ -154,6 +182,14 @@ nvkm_fb_init(struct nvkm_subdev *subdev)
 
 	if (fb->func->init_unkn)
 		fb->func->init_unkn(fb);
+
+	if (fb->func->vpr.scrub_required &&
+	    fb->func->vpr.scrub_required(fb)) {
+		ret = nvkm_fb_init_scrub_vpr(fb);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -172,6 +208,8 @@ nvkm_fb_dtor(struct nvkm_subdev *subdev)
 	nvkm_mm_fini(&fb->tags);
 	nvkm_ram_del(&fb->ram);
 
+	nvkm_blob_dtor(&fb->vpr_scrubber);
+
 	if (fb->func->dtor)
 		return fb->func->dtor(fb);
 	return fb;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
index b4d74e815674..fc8c93aa3da5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
@@ -24,7 +24,81 @@
 #include "gf100.h"
 #include "ram.h"
 
+#include <core/firmware.h>
 #include <core/memory.h>
+#include <nvfw/fw.h>
+#include <nvfw/hs.h>
+#include <engine/nvdec.h>
+
+int
+gp102_fb_vpr_scrub(struct nvkm_fb *fb)
+{
+	struct nvkm_subdev *subdev = &fb->subdev;
+	struct nvkm_device *device = subdev->device;
+	struct nvkm_falcon *falcon = &device->nvdec[0]->falcon;
+	struct nvkm_blob *blob = &fb->vpr_scrubber;
+	const struct nvfw_bin_hdr *hsbin_hdr;
+	const struct nvfw_hs_header *fw_hdr;
+	const struct nvfw_hs_load_header *lhdr;
+	void *scrub_data;
+	u32 patch_loc, patch_sig;
+	int ret;
+
+	nvkm_falcon_get(falcon, subdev);
+
+	hsbin_hdr = nvfw_bin_hdr(subdev, blob->data);
+	fw_hdr = nvfw_hs_header(subdev, blob->data + hsbin_hdr->header_offset);
+	lhdr = nvfw_hs_load_header(subdev, blob->data + fw_hdr->hdr_offset);
+	scrub_data = blob->data + hsbin_hdr->data_offset;
+
+	patch_loc = *(u32 *)(blob->data + fw_hdr->patch_loc);
+	patch_sig = *(u32 *)(blob->data + fw_hdr->patch_sig);
+	if (falcon->debug) {
+		memcpy(scrub_data + patch_loc,
+		       blob->data + fw_hdr->sig_dbg_offset + patch_sig,
+		       fw_hdr->sig_dbg_size);
+	} else {
+		memcpy(scrub_data + patch_loc,
+		       blob->data + fw_hdr->sig_prod_offset + patch_sig,
+		       fw_hdr->sig_prod_size);
+	}
+
+	nvkm_falcon_reset(falcon);
+	nvkm_falcon_bind_context(falcon, NULL);
+
+	nvkm_falcon_load_imem(falcon, scrub_data, lhdr->non_sec_code_off,
+			      lhdr->non_sec_code_size,
+			      lhdr->non_sec_code_off >> 8, 0, false);
+	nvkm_falcon_load_imem(falcon, scrub_data + lhdr->apps[0],
+			      ALIGN(lhdr->apps[0], 0x100),
+			      lhdr->apps[1],
+			      lhdr->apps[0] >> 8, 0, true);
+	nvkm_falcon_load_dmem(falcon, scrub_data + lhdr->data_dma_base, 0,
+			      lhdr->data_size, 0);
+
+	nvkm_falcon_set_start_addr(falcon, 0x0);
+	nvkm_falcon_start(falcon);
+
+	ret = nvkm_falcon_wait_for_halt(falcon, 500);
+	if (ret < 0) {
+		ret = -ETIMEDOUT;
+		goto end;
+	}
+
+	/* put nvdec in clean state - without reset it will remain in HS mode */
+	nvkm_falcon_reset(falcon);
+end:
+	nvkm_falcon_put(falcon, subdev);
+	return ret;
+}
+
+bool
+gp102_fb_vpr_scrub_required(struct nvkm_fb *fb)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	nvkm_wr32(device, 0x100cd0, 0x2);
+	return (nvkm_rd32(device, 0x100cd0) & 0x00000010) != 0;
+}
 
 static const struct nvkm_fb_func
 gp102_fb = {
@@ -33,11 +107,32 @@ gp102_fb = {
 	.init = gp100_fb_init,
 	.init_remapper = gp100_fb_init_remapper,
 	.init_page = gm200_fb_init_page,
+	.vpr.scrub_required = gp102_fb_vpr_scrub_required,
+	.vpr.scrub = gp102_fb_vpr_scrub,
 	.ram_new = gp100_ram_new,
 };
 
 int
+gp102_fb_new_(const struct nvkm_fb_func *func, struct nvkm_device *device,
+	      int index, struct nvkm_fb **pfb)
+{
+	int ret = gf100_fb_new_(func, device, index, pfb);
+	if (ret)
+		return ret;
+
+	nvkm_firmware_load_blob(&(*pfb)->subdev, "nvdec/scrubber", "", 0,
+				&(*pfb)->vpr_scrubber);
+	return 0;
+}
+
+int
 gp102_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
 {
-	return gf100_fb_new_(&gp102_fb, device, index, pfb);
+	return gp102_fb_new_(&gp102_fb, device, index, pfb);
 }
+
+MODULE_FIRMWARE("nvidia/gp102/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gp104/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gp106/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gp107/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/gp108/nvdec/scrubber.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
index 3c5e02e9794a..389bad312bf2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -35,6 +35,8 @@ gv100_fb = {
 	.init = gp100_fb_init,
 	.init_page = gv100_fb_init_page,
 	.init_unkn = gp100_fb_init_unkn,
+	.vpr.scrub_required = gp102_fb_vpr_scrub_required,
+	.vpr.scrub = gp102_fb_vpr_scrub,
 	.ram_new = gp100_ram_new,
 	.default_bigpage = 16,
 };
@@ -42,5 +44,10 @@ gv100_fb = {
 int
 gv100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
 {
-	return gf100_fb_new_(&gv100_fb, device, index, pfb);
+	return gp102_fb_new_(&gv100_fb, device, index, pfb);
 }
+
+MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin");
+MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index c4e9f55af283..5be9c563350d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -17,6 +17,11 @@ struct nvkm_fb_func {
 	void (*intr)(struct nvkm_fb *);
 
 	struct {
+		bool (*scrub_required)(struct nvkm_fb *);
+		int (*scrub)(struct nvkm_fb *);
+	} vpr;
+
+	struct {
 		int regions;
 		void (*init)(struct nvkm_fb *, int i, u32 addr, u32 size,
 			     u32 pitch, u32 flags, struct nvkm_fb_tile *);
@@ -72,4 +77,9 @@ int gm200_fb_init_page(struct nvkm_fb *);
 
 void gp100_fb_init_remapper(struct nvkm_fb *);
 void gp100_fb_init_unkn(struct nvkm_fb *);
+
+int gp102_fb_new_(const struct nvkm_fb_func *, struct nvkm_device *, int,
+		  struct nvkm_fb **);
+bool gp102_fb_vpr_scrub_required(struct nvkm_fb *);
+int gp102_fb_vpr_scrub(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c
index ac87a3b6b7c9..ba43fe158b22 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf100.c
@@ -655,7 +655,7 @@ gf100_ram_new_(const struct nvkm_ram_func *func,
 
 static const struct nvkm_ram_func
 gf100_ram = {
-	.upper = 0x0200000000,
+	.upper = 0x0200000000ULL,
 	.probe_fbp = gf100_ram_probe_fbp,
 	.probe_fbp_amount = gf100_ram_probe_fbp_amount,
 	.probe_fbpa_amount = gf100_ram_probe_fbpa_amount,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf108.c
index 70a06e3cd55a..d97fa43efb91 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgf108.c
@@ -43,7 +43,7 @@ gf108_ram_probe_fbp_amount(const struct nvkm_ram_func *func, u32 fbpao,
 
 static const struct nvkm_ram_func
 gf108_ram = {
-	.upper = 0x0200000000,
+	.upper = 0x0200000000ULL,
 	.probe_fbp = gf100_ram_probe_fbp,
 	.probe_fbp_amount = gf108_ram_probe_fbp_amount,
 	.probe_fbpa_amount = gf100_ram_probe_fbpa_amount,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgk104.c
index 456aed1f2a02..d350d92852d2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgk104.c
@@ -1698,7 +1698,7 @@ gk104_ram_new_(const struct nvkm_ram_func *func, struct nvkm_fb *fb,
 
 static const struct nvkm_ram_func
 gk104_ram = {
-	.upper = 0x0200000000,
+	.upper = 0x0200000000ULL,
 	.probe_fbp = gf100_ram_probe_fbp,
 	.probe_fbp_amount = gf108_ram_probe_fbp_amount,
 	.probe_fbpa_amount = gf100_ram_probe_fbpa_amount,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm107.c
index 27c68e3f9772..be91da854dca 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm107.c
@@ -33,7 +33,7 @@ gm107_ram_probe_fbp(const struct nvkm_ram_func *func,
 
 static const struct nvkm_ram_func
 gm107_ram = {
-	.upper = 0x1000000000,
+	.upper = 0x1000000000ULL,
 	.probe_fbp = gm107_ram_probe_fbp,
 	.probe_fbp_amount = gf108_ram_probe_fbp_amount,
 	.probe_fbpa_amount = gf100_ram_probe_fbpa_amount,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm200.c
index 6b0cac1fe7b4..8f91ea91ee25 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgm200.c
@@ -48,7 +48,7 @@ gm200_ram_probe_fbp_amount(const struct nvkm_ram_func *func, u32 fbpao,
 
 static const struct nvkm_ram_func
 gm200_ram = {
-	.upper = 0x1000000000,
+	.upper = 0x1000000000ULL,
 	.probe_fbp = gm107_ram_probe_fbp,
 	.probe_fbp_amount = gm200_ram_probe_fbp_amount,
 	.probe_fbpa_amount = gf100_ram_probe_fbpa_amount,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
index adb62a6beb63..378f6fb70990 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
@@ -79,7 +79,7 @@ gp100_ram_probe_fbpa(struct nvkm_device *device, int fbpa)
 
 static const struct nvkm_ram_func
 gp100_ram = {
-	.upper = 0x1000000000,
+	.upper = 0x1000000000ULL,
 	.probe_fbp = gm107_ram_probe_fbp,
 	.probe_fbp_amount = gm200_ram_probe_fbp_amount,
 	.probe_fbpa_amount = gp100_ram_probe_fbpa,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild
index e7c4f068936e..67cc3b320169 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/Kbuild
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: MIT
+nvkm-y += nvkm/subdev/gsp/base.o
 nvkm-y += nvkm/subdev/gsp/gv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
new file mode 100644
index 000000000000..5a32df0f9992
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/base.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright 2019 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+#include <core/falcon.h>
+#include <core/firmware.h>
+#include <subdev/acr.h>
+#include <subdev/top.h>
+
+static void *
+nvkm_gsp_dtor(struct nvkm_subdev *subdev)
+{
+	struct nvkm_gsp *gsp = nvkm_gsp(subdev);
+	nvkm_falcon_dtor(&gsp->falcon);
+	return gsp;
+}
+
+static const struct nvkm_subdev_func
+nvkm_gsp = {
+	.dtor = nvkm_gsp_dtor,
+};
+
+int
+nvkm_gsp_new_(const struct nvkm_gsp_fwif *fwif, struct nvkm_device *device,
+	      int index, struct nvkm_gsp **pgsp)
+{
+	struct nvkm_gsp *gsp;
+
+	if (!(gsp = *pgsp = kzalloc(sizeof(*gsp), GFP_KERNEL)))
+		return -ENOMEM;
+
+	nvkm_subdev_ctor(&nvkm_gsp, device, index, &gsp->subdev);
+
+	fwif = nvkm_firmware_load(&gsp->subdev, fwif, "Gsp", gsp);
+	if (IS_ERR(fwif))
+		return PTR_ERR(fwif);
+
+	return nvkm_falcon_ctor(fwif->flcn, &gsp->subdev,
+				nvkm_subdev_name[gsp->subdev.index], 0,
+				&gsp->falcon);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gv100.c
index dccfaf1162e2..2114f9b00a28 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/gv100.c
@@ -19,44 +19,37 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-#include <subdev/gsp.h>
-#include <subdev/top.h>
-#include <engine/falcon.h>
+#include "priv.h"
+
+static const struct nvkm_falcon_func
+gv100_gsp_flcn = {
+	.fbif = 0x600,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.bind_context = gp102_sec2_flcn_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = gp102_sec2_flcn_enable,
+	.disable = nvkm_falcon_v1_disable,
+};
 
 static int
-gv100_gsp_oneinit(struct nvkm_subdev *subdev)
-{
-	struct nvkm_gsp *gsp = nvkm_gsp(subdev);
-
-	gsp->addr = nvkm_top_addr(subdev->device, subdev->index);
-	if (!gsp->addr)
-		return -EINVAL;
-
-	return nvkm_falcon_v1_new(subdev, "GSP", gsp->addr, &gsp->falcon);
-}
-
-static void *
-gv100_gsp_dtor(struct nvkm_subdev *subdev)
+gv100_gsp_nofw(struct nvkm_gsp *gsp, int ver, const struct nvkm_gsp_fwif *fwif)
 {
-	struct nvkm_gsp *gsp = nvkm_gsp(subdev);
-	nvkm_falcon_del(&gsp->falcon);
-	return gsp;
+	return 0;
 }
 
-static const struct nvkm_subdev_func
-gv100_gsp = {
-	.dtor = gv100_gsp_dtor,
-	.oneinit = gv100_gsp_oneinit,
+struct nvkm_gsp_fwif
+gv100_gsp[] = {
+	{ -1, gv100_gsp_nofw, &gv100_gsp_flcn },
+	{}
 };
 
 int
 gv100_gsp_new(struct nvkm_device *device, int index, struct nvkm_gsp **pgsp)
 {
-	struct nvkm_gsp *gsp;
-
-	if (!(gsp = *pgsp = kzalloc(sizeof(*gsp), GFP_KERNEL)))
-		return -ENOMEM;
-
-	nvkm_subdev_ctor(&gv100_gsp, device, index, &gsp->subdev);
-	return 0;
+	return nvkm_gsp_new_(gv100_gsp, device, index, pgsp);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h
new file mode 100644
index 000000000000..92820fb997c1
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+#ifndef __NVKM_GSP_PRIV_H__
+#define __NVKM_GSP_PRIV_H__
+#include <subdev/gsp.h>
+enum nvkm_acr_lsf_id;
+
+struct nvkm_gsp_fwif {
+	int version;
+	int (*load)(struct nvkm_gsp *, int ver, const struct nvkm_gsp_fwif *);
+	const struct nvkm_falcon_func *flcn;
+};
+
+int nvkm_gsp_new_(const struct nvkm_gsp_fwif *, struct nvkm_device *, int,
+		  struct nvkm_gsp **);
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
index 2b6d36ea7067..728d75010847 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/Kbuild
@@ -6,3 +6,4 @@ nvkm-y += nvkm/subdev/ltc/gm107.o
 nvkm-y += nvkm/subdev/ltc/gm200.o
 nvkm-y += nvkm/subdev/ltc/gp100.o
 nvkm-y += nvkm/subdev/ltc/gp102.o
+nvkm-y += nvkm/subdev/ltc/gp10b.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
new file mode 100644
index 000000000000..c0063c7caa50
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/gp10b.c
@@ -0,0 +1,65 @@
+/*
+ * Copyright (c) 2019 NVIDIA Corporation.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: Thierry Reding
+ */
+
+#include "priv.h"
+
+static void
+gp10b_ltc_init(struct nvkm_ltc *ltc)
+{
+	struct nvkm_device *device = ltc->subdev.device;
+	struct iommu_fwspec *spec;
+
+	nvkm_wr32(device, 0x17e27c, ltc->ltc_nr);
+	nvkm_wr32(device, 0x17e000, ltc->ltc_nr);
+	nvkm_wr32(device, 0x100800, ltc->ltc_nr);
+
+	spec = dev_iommu_fwspec_get(device->dev);
+	if (spec) {
+		u32 sid = spec->ids[0] & 0xffff;
+
+		/* stream ID */
+		nvkm_wr32(device, 0x160000, sid << 2);
+	}
+}
+
+static const struct nvkm_ltc_func
+gp10b_ltc = {
+	.oneinit = gp100_ltc_oneinit,
+	.init = gp10b_ltc_init,
+	.intr = gp100_ltc_intr,
+	.cbc_clear = gm107_ltc_cbc_clear,
+	.cbc_wait = gm107_ltc_cbc_wait,
+	.zbc = 16,
+	.zbc_clear_color = gm107_ltc_zbc_clear_color,
+	.zbc_clear_depth = gm107_ltc_zbc_clear_depth,
+	.zbc_clear_stencil = gp102_ltc_zbc_clear_stencil,
+	.invalidate = gf100_ltc_invalidate,
+	.flush = gf100_ltc_flush,
+};
+
+int
+gp10b_ltc_new(struct nvkm_device *device, int index, struct nvkm_ltc **pltc)
+{
+	return nvkm_ltc_new_(&gp10b_ltc, device, index, pltc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
index 2fcf18e46ce3..eca5a711b1b8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ltc/priv.h
@@ -46,4 +46,6 @@ void gm107_ltc_zbc_clear_depth(struct nvkm_ltc *, int, const u32);
 int gp100_ltc_oneinit(struct nvkm_ltc *);
 void gp100_ltc_init(struct nvkm_ltc *);
 void gp100_ltc_intr(struct nvkm_ltc *);
+
+void gp102_ltc_zbc_clear_stencil(struct nvkm_ltc *, int, const u32);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gf100.c
index 2d075246dc46..2cd5ec81c0d0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gf100.c
@@ -30,7 +30,7 @@
  * The value 0xff represents an invalid storage type.
  */
 const u8 *
-gf100_mmu_kind(struct nvkm_mmu *mmu, int *count)
+gf100_mmu_kind(struct nvkm_mmu *mmu, int *count, u8 *invalid)
 {
 	static const u8
 	kind[256] = {
@@ -69,6 +69,7 @@ gf100_mmu_kind(struct nvkm_mmu *mmu, int *count)
 	};
 
 	*count = ARRAY_SIZE(kind);
+	*invalid = 0xff;
 	return kind;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gm200.c
index dbf644ebac97..83990c83f9f8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gm200.c
@@ -27,7 +27,7 @@
 #include <nvif/class.h>
 
 const u8 *
-gm200_mmu_kind(struct nvkm_mmu *mmu, int *count)
+gm200_mmu_kind(struct nvkm_mmu *mmu, int *count, u8 *invalid)
 {
 	static const u8
 	kind[256] = {
@@ -65,6 +65,7 @@ gm200_mmu_kind(struct nvkm_mmu *mmu, int *count)
 		0xfe, 0xfe, 0xfe, 0xfe, 0xff, 0xfd, 0xfe, 0xff
 	};
 	*count = ARRAY_SIZE(kind);
+	*invalid = 0xff;
 	return kind;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv50.c
index db3dfbbb2aa0..c0083ddda65a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/nv50.c
@@ -27,7 +27,7 @@
 #include <nvif/class.h>
 
 const u8 *
-nv50_mmu_kind(struct nvkm_mmu *base, int *count)
+nv50_mmu_kind(struct nvkm_mmu *base, int *count, u8 *invalid)
 {
 	/* 0x01: no bank swizzle
 	 * 0x02: bank swizzled
@@ -57,6 +57,7 @@ nv50_mmu_kind(struct nvkm_mmu *base, int *count)
 		0x01, 0x01, 0x02, 0x02, 0x01, 0x01, 0x7f, 0x7f
 	};
 	*count = ARRAY_SIZE(kind);
+	*invalid = 0x7f;
 	return kind;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h
index 07f2fcd18f3d..479b02344271 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/priv.h
@@ -35,17 +35,17 @@ struct nvkm_mmu_func {
 		u32 pd_offset;
 	} vmm;
 
-	const u8 *(*kind)(struct nvkm_mmu *, int *count);
+	const u8 *(*kind)(struct nvkm_mmu *, int *count, u8 *invalid);
 	bool kind_sys;
 };
 
 extern const struct nvkm_mmu_func nv04_mmu;
 
-const u8 *nv50_mmu_kind(struct nvkm_mmu *, int *count);
+const u8 *nv50_mmu_kind(struct nvkm_mmu *, int *count, u8 *invalid);
 
-const u8 *gf100_mmu_kind(struct nvkm_mmu *, int *count);
+const u8 *gf100_mmu_kind(struct nvkm_mmu *, int *count, u8 *invalid);
 
-const u8 *gm200_mmu_kind(struct nvkm_mmu *, int *);
+const u8 *gm200_mmu_kind(struct nvkm_mmu *, int *, u8 *);
 
 struct nvkm_mmu_pt {
 	union {
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/tu102.c
index c0db0ce10cba..b21e82eb0916 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/tu102.c
@@ -1,5 +1,6 @@
 /*
  * Copyright 2018 Red Hat Inc.
+ * Copyright 2019 NVIDIA Corporation.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -26,13 +27,26 @@
 
 #include <nvif/class.h>
 
+const u8 *
+tu102_mmu_kind(struct nvkm_mmu *mmu, int *count, u8 *invalid)
+{
+	static const u8
+	kind[16] = {
+		0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00 */
+		0x06, 0x06, 0x02, 0x01, 0x03, 0x04, 0x05, 0x07,
+	};
+	*count = ARRAY_SIZE(kind);
+	*invalid = 0x07;
+	return kind;
+}
+
 static const struct nvkm_mmu_func
 tu102_mmu = {
 	.dma_bits = 47,
 	.mmu = {{ -1, -1, NVIF_CLASS_MMU_GF100}},
 	.mem = {{ -1,  0, NVIF_CLASS_MEM_GF100}, gf100_mem_new, gf100_mem_map },
 	.vmm = {{ -1,  0, NVIF_CLASS_VMM_GP100}, tu102_vmm_new },
-	.kind = gm200_mmu_kind,
+	.kind = tu102_mmu_kind,
 	.kind_sys = true,
 };
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/ummu.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/ummu.c
index 353f10f92b77..0e4b8941da37 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/ummu.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/ummu.c
@@ -111,15 +111,17 @@ nvkm_ummu_kind(struct nvkm_ummu *ummu, void *argv, u32 argc)
 	} *args = argv;
 	const u8 *kind = NULL;
 	int ret = -ENOSYS, count = 0;
+	u8 kind_inv = 0;
 
 	if (mmu->func->kind)
-		kind = mmu->func->kind(mmu, &count);
+		kind = mmu->func->kind(mmu, &count, &kind_inv);
 
 	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, true))) {
 		if (argc != args->v0.count * sizeof(*args->v0.data))
 			return -EINVAL;
 		if (args->v0.count > count)
 			return -EINVAL;
+		args->v0.kind_inv = kind_inv;
 		memcpy(args->v0.data, kind, args->v0.count);
 	} else
 		return ret;
@@ -157,9 +159,10 @@ nvkm_ummu_new(struct nvkm_device *device, const struct nvkm_oclass *oclass,
 	struct nvkm_mmu *mmu = device->mmu;
 	struct nvkm_ummu *ummu;
 	int ret = -ENOSYS, kinds = 0;
+	u8 unused = 0;
 
 	if (mmu->func->kind)
-		mmu->func->kind(mmu, &kinds);
+		mmu->func->kind(mmu, &kinds, &unused);
 
 	if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, false))) {
 		args->v0.dmabits = mmu->dma_bits;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c
index ab6424faf84c..6a2d9eb8e1ea 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c
@@ -247,7 +247,7 @@ gf100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	} *args = argv;
 	struct nvkm_device *device = vmm->mmu->subdev.device;
 	struct nvkm_memory *memory = map->memory;
-	u8  kind, priv, ro, vol;
+	u8  kind, kind_inv, priv, ro, vol;
 	int kindn, aper, ret = -ENOSYS;
 	const u8 *kindm;
 
@@ -274,8 +274,8 @@ gf100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	if (WARN_ON(aper < 0))
 		return aper;
 
-	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn);
-	if (kind >= kindn || kindm[kind] == 0xff) {
+	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn, &kind_inv);
+	if (kind >= kindn || kindm[kind] == kind_inv) {
 		VMM_DEBUG(vmm, "kind %02x", kind);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
index b4f519768d5e..d86287565542 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c
@@ -320,7 +320,7 @@ gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	} *args = argv;
 	struct nvkm_device *device = vmm->mmu->subdev.device;
 	struct nvkm_memory *memory = map->memory;
-	u8  kind, priv, ro, vol;
+	u8  kind, kind_inv, priv, ro, vol;
 	int kindn, aper, ret = -ENOSYS;
 	const u8 *kindm;
 
@@ -347,8 +347,8 @@ gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	if (WARN_ON(aper < 0))
 		return aper;
 
-	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn);
-	if (kind >= kindn || kindm[kind] == 0xff) {
+	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn, &kind_inv);
+	if (kind >= kindn || kindm[kind] == kind_inv) {
 		VMM_DEBUG(vmm, "kind %02x", kind);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c
index c98afe3134ee..2d89e27e8e9e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c
@@ -235,7 +235,7 @@ nv50_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 	struct nvkm_device *device = vmm->mmu->subdev.device;
 	struct nvkm_ram *ram = device->fb->ram;
 	struct nvkm_memory *memory = map->memory;
-	u8  aper, kind, comp, priv, ro;
+	u8  aper, kind, kind_inv, comp, priv, ro;
 	int kindn, ret = -ENOSYS;
 	const u8 *kindm;
 
@@ -278,8 +278,8 @@ nv50_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc,
 		return -EINVAL;
 	}
 
-	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn);
-	if (kind >= kindn || kindm[kind] == 0x7f) {
+	kindm = vmm->mmu->func->kind(vmm->mmu, &kindn, &kind_inv);
+	if (kind >= kindn || kindm[kind] == kind_inv) {
 		VMM_DEBUG(vmm, "kind %02x", kind);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild
index e37b6e45eaa2..a76c2a7bd696 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/Kbuild
@@ -12,3 +12,4 @@ nvkm-y += nvkm/subdev/pmu/gm107.o
 nvkm-y += nvkm/subdev/pmu/gm20b.o
 nvkm-y += nvkm/subdev/pmu/gp100.o
 nvkm-y += nvkm/subdev/pmu/gp102.o
+nvkm-y += nvkm/subdev/pmu/gp10b.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c
index ea2e11771bca..a0fe607c9c07 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/base.c
@@ -23,7 +23,7 @@
  */
 #include "priv.h"
 
-#include <core/msgqueue.h>
+#include <core/firmware.h>
 #include <subdev/timer.h>
 
 bool
@@ -85,6 +85,12 @@ nvkm_pmu_fini(struct nvkm_subdev *subdev, bool suspend)
 		pmu->func->fini(pmu);
 
 	flush_work(&pmu->recv.work);
+
+	reinit_completion(&pmu->wpr_ready);
+
+	nvkm_falcon_cmdq_fini(pmu->lpq);
+	nvkm_falcon_cmdq_fini(pmu->hpq);
+	pmu->initmsg_received = false;
 	return 0;
 }
 
@@ -133,19 +139,15 @@ nvkm_pmu_init(struct nvkm_subdev *subdev)
 	return ret;
 }
 
-static int
-nvkm_pmu_oneinit(struct nvkm_subdev *subdev)
-{
-	struct nvkm_pmu *pmu = nvkm_pmu(subdev);
-	return nvkm_falcon_v1_new(&pmu->subdev, "PMU", 0x10a000, &pmu->falcon);
-}
-
 static void *
 nvkm_pmu_dtor(struct nvkm_subdev *subdev)
 {
 	struct nvkm_pmu *pmu = nvkm_pmu(subdev);
-	nvkm_msgqueue_del(&pmu->queue);
-	nvkm_falcon_del(&pmu->falcon);
+	nvkm_falcon_msgq_del(&pmu->msgq);
+	nvkm_falcon_cmdq_del(&pmu->lpq);
+	nvkm_falcon_cmdq_del(&pmu->hpq);
+	nvkm_falcon_qmgr_del(&pmu->qmgr);
+	nvkm_falcon_dtor(&pmu->falcon);
 	return nvkm_pmu(subdev);
 }
 
@@ -153,29 +155,50 @@ static const struct nvkm_subdev_func
 nvkm_pmu = {
 	.dtor = nvkm_pmu_dtor,
 	.preinit = nvkm_pmu_preinit,
-	.oneinit = nvkm_pmu_oneinit,
 	.init = nvkm_pmu_init,
 	.fini = nvkm_pmu_fini,
 	.intr = nvkm_pmu_intr,
 };
 
 int
-nvkm_pmu_ctor(const struct nvkm_pmu_func *func, struct nvkm_device *device,
+nvkm_pmu_ctor(const struct nvkm_pmu_fwif *fwif, struct nvkm_device *device,
 	      int index, struct nvkm_pmu *pmu)
 {
+	int ret;
+
 	nvkm_subdev_ctor(&nvkm_pmu, device, index, &pmu->subdev);
-	pmu->func = func;
+
 	INIT_WORK(&pmu->recv.work, nvkm_pmu_recv);
 	init_waitqueue_head(&pmu->recv.wait);
+
+	fwif = nvkm_firmware_load(&pmu->subdev, fwif, "Pmu", pmu);
+	if (IS_ERR(fwif))
+		return PTR_ERR(fwif);
+
+	pmu->func = fwif->func;
+
+	ret = nvkm_falcon_ctor(pmu->func->flcn, &pmu->subdev,
+			       nvkm_subdev_name[pmu->subdev.index], 0x10a000,
+			       &pmu->falcon);
+	if (ret)
+		return ret;
+
+	if ((ret = nvkm_falcon_qmgr_new(&pmu->falcon, &pmu->qmgr)) ||
+	    (ret = nvkm_falcon_cmdq_new(pmu->qmgr, "hpq", &pmu->hpq)) ||
+	    (ret = nvkm_falcon_cmdq_new(pmu->qmgr, "lpq", &pmu->lpq)) ||
+	    (ret = nvkm_falcon_msgq_new(pmu->qmgr, "msgq", &pmu->msgq)))
+		return ret;
+
+	init_completion(&pmu->wpr_ready);
 	return 0;
 }
 
 int
-nvkm_pmu_new_(const struct nvkm_pmu_func *func, struct nvkm_device *device,
+nvkm_pmu_new_(const struct nvkm_pmu_fwif *fwif, struct nvkm_device *device,
 	      int index, struct nvkm_pmu **ppmu)
 {
 	struct nvkm_pmu *pmu;
 	if (!(pmu = *ppmu = kzalloc(sizeof(*pmu), GFP_KERNEL)))
 		return -ENOMEM;
-	return nvkm_pmu_ctor(func, device, index, *ppmu);
+	return nvkm_pmu_ctor(fwif, device, index, *ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf100.c
index 0b458656e870..3ecb3d9cbcf2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf100.c
@@ -42,6 +42,7 @@ gf100_pmu_enabled(struct nvkm_pmu *pmu)
 
 static const struct nvkm_pmu_func
 gf100_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gf100_pmu_code,
 	.code.size = sizeof(gf100_pmu_code),
 	.data.data = gf100_pmu_data,
@@ -56,7 +57,19 @@ gf100_pmu = {
 };
 
 int
+gf100_pmu_nofw(struct nvkm_pmu *pmu, int ver, const struct nvkm_pmu_fwif *fwif)
+{
+	return 0;
+}
+
+static const struct nvkm_pmu_fwif
+gf100_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gf100_pmu },
+	{}
+};
+
+int
 gf100_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gf100_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gf100_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf119.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf119.c
index 3dfa79d4fb13..8dd0271aaaee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gf119.c
@@ -26,6 +26,7 @@
 
 static const struct nvkm_pmu_func
 gf119_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gf119_pmu_code,
 	.code.size = sizeof(gf119_pmu_code),
 	.data.data = gf119_pmu_data,
@@ -39,8 +40,14 @@ gf119_pmu = {
 	.recv = gt215_pmu_recv,
 };
 
+static const struct nvkm_pmu_fwif
+gf119_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gf119_pmu },
+	{}
+};
+
 int
 gf119_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gf119_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gf119_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c
index 8f7ec10fd2a4..8b70cc17a634 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk104.c
@@ -105,6 +105,7 @@ gk104_pmu_pgob(struct nvkm_pmu *pmu, bool enable)
 
 static const struct nvkm_pmu_func
 gk104_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gk104_pmu_code,
 	.code.size = sizeof(gk104_pmu_code),
 	.data.data = gk104_pmu_data,
@@ -119,8 +120,14 @@ gk104_pmu = {
 	.pgob = gk104_pmu_pgob,
 };
 
+static const struct nvkm_pmu_fwif
+gk104_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gk104_pmu },
+	{}
+};
+
 int
 gk104_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gk104_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gk104_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk110.c
index 345741d55a56..0081f2141b10 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk110.c
@@ -84,6 +84,7 @@ gk110_pmu_pgob(struct nvkm_pmu *pmu, bool enable)
 
 static const struct nvkm_pmu_func
 gk110_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gk110_pmu_code,
 	.code.size = sizeof(gk110_pmu_code),
 	.data.data = gk110_pmu_data,
@@ -98,8 +99,14 @@ gk110_pmu = {
 	.pgob = gk110_pmu_pgob,
 };
 
+static const struct nvkm_pmu_fwif
+gk110_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gk110_pmu },
+	{}
+};
+
 int
 gk110_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gk110_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gk110_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk208.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk208.c
index e4acf7876ea1..b227c701a5e7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk208.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk208.c
@@ -26,6 +26,7 @@
 
 static const struct nvkm_pmu_func
 gk208_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gk208_pmu_code,
 	.code.size = sizeof(gk208_pmu_code),
 	.data.data = gk208_pmu_data,
@@ -40,8 +41,14 @@ gk208_pmu = {
 	.pgob = gk110_pmu_pgob,
 };
 
+static const struct nvkm_pmu_fwif
+gk208_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gk208_pmu },
+	{}
+};
+
 int
 gk208_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gk208_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gk208_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk20a.c
index 05e81855c367..26c1adf8f44c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gk20a.c
@@ -95,7 +95,7 @@ static void
 gk20a_pmu_dvfs_get_dev_status(struct gk20a_pmu *pmu,
 			      struct gk20a_pmu_dvfs_dev_status *status)
 {
-	struct nvkm_falcon *falcon = pmu->base.falcon;
+	struct nvkm_falcon *falcon = &pmu->base.falcon;
 
 	status->busy = nvkm_falcon_rd32(falcon, 0x508 + (BUSY_SLOT * 0x10));
 	status->total= nvkm_falcon_rd32(falcon, 0x508 + (CLK_SLOT * 0x10));
@@ -104,7 +104,7 @@ gk20a_pmu_dvfs_get_dev_status(struct gk20a_pmu *pmu,
 static void
 gk20a_pmu_dvfs_reset_dev_status(struct gk20a_pmu *pmu)
 {
-	struct nvkm_falcon *falcon = pmu->base.falcon;
+	struct nvkm_falcon *falcon = &pmu->base.falcon;
 
 	nvkm_falcon_wr32(falcon, 0x508 + (BUSY_SLOT * 0x10), 0x80000000);
 	nvkm_falcon_wr32(falcon, 0x508 + (CLK_SLOT * 0x10), 0x80000000);
@@ -160,7 +160,7 @@ gk20a_pmu_fini(struct nvkm_pmu *pmu)
 	struct gk20a_pmu *gpmu = gk20a_pmu(pmu);
 	nvkm_timer_alarm(pmu->subdev.device->timer, 0, &gpmu->alarm);
 
-	nvkm_falcon_put(pmu->falcon, &pmu->subdev);
+	nvkm_falcon_put(&pmu->falcon, &pmu->subdev);
 }
 
 static int
@@ -169,7 +169,7 @@ gk20a_pmu_init(struct nvkm_pmu *pmu)
 	struct gk20a_pmu *gpmu = gk20a_pmu(pmu);
 	struct nvkm_subdev *subdev = &pmu->subdev;
 	struct nvkm_device *device = pmu->subdev.device;
-	struct nvkm_falcon *falcon = pmu->falcon;
+	struct nvkm_falcon *falcon = &pmu->falcon;
 	int ret;
 
 	ret = nvkm_falcon_get(falcon, subdev);
@@ -196,25 +196,34 @@ gk20a_dvfs_data= {
 
 static const struct nvkm_pmu_func
 gk20a_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.enabled = gf100_pmu_enabled,
 	.init = gk20a_pmu_init,
 	.fini = gk20a_pmu_fini,
 	.reset = gf100_pmu_reset,
 };
 
+static const struct nvkm_pmu_fwif
+gk20a_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gk20a_pmu },
+	{}
+};
+
 int
 gk20a_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
 	struct gk20a_pmu *pmu;
+	int ret;
 
 	if (!(pmu = kzalloc(sizeof(*pmu), GFP_KERNEL)))
 		return -ENOMEM;
 	*ppmu = &pmu->base;
 
-	nvkm_pmu_ctor(&gk20a_pmu, device, index, &pmu->base);
+	ret = nvkm_pmu_ctor(gk20a_pmu_fwif, device, index, &pmu->base);
+	if (ret)
+		return ret;
 
 	pmu->data = &gk20a_dvfs_data;
 	nvkm_alarm_init(&pmu->alarm, gk20a_pmu_dvfs_work);
-
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm107.c
index 459df1ef9e70..5afb55e58b51 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm107.c
@@ -28,6 +28,7 @@
 
 static const struct nvkm_pmu_func
 gm107_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gm107_pmu_code,
 	.code.size = sizeof(gm107_pmu_code),
 	.data.data = gm107_pmu_data,
@@ -41,8 +42,14 @@ gm107_pmu = {
 	.recv = gt215_pmu_recv,
 };
 
+static const struct nvkm_pmu_fwif
+gm107_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gm107_pmu },
+	{}
+};
+
 int
 gm107_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gm107_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gm107_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
index 31c843145c7a..82571032a07d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c
@@ -19,38 +19,224 @@
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
  * DEALINGS IN THE SOFTWARE.
  */
-
-#include <engine/falcon.h>
-#include <core/msgqueue.h>
 #include "priv.h"
 
-static void
+#include <core/memory.h>
+#include <subdev/acr.h>
+
+#include <nvfw/flcn.h>
+#include <nvfw/pmu.h>
+
+static int
+gm20b_pmu_acr_bootstrap_falcon_cb(void *priv, struct nv_falcon_msg *hdr)
+{
+	struct nv_pmu_acr_bootstrap_falcon_msg *msg =
+		container_of(hdr, typeof(*msg), msg.hdr);
+	return msg->falcon_id;
+}
+
+int
+gm20b_pmu_acr_bootstrap_falcon(struct nvkm_falcon *falcon,
+			       enum nvkm_acr_lsf_id id)
+{
+	struct nvkm_pmu *pmu = container_of(falcon, typeof(*pmu), falcon);
+	struct nv_pmu_acr_bootstrap_falcon_cmd cmd = {
+		.cmd.hdr.unit_id = NV_PMU_UNIT_ACR,
+		.cmd.hdr.size = sizeof(cmd),
+		.cmd.cmd_type = NV_PMU_ACR_CMD_BOOTSTRAP_FALCON,
+		.flags = NV_PMU_ACR_BOOTSTRAP_FALCON_FLAGS_RESET_YES,
+		.falcon_id = id,
+	};
+	int ret;
+
+	ret = nvkm_falcon_cmdq_send(pmu->hpq, &cmd.cmd.hdr,
+				    gm20b_pmu_acr_bootstrap_falcon_cb,
+				    &pmu->subdev, msecs_to_jiffies(1000));
+	if (ret >= 0) {
+		if (ret != cmd.falcon_id)
+			ret = -EIO;
+		else
+			ret = 0;
+	}
+
+	return ret;
+}
+
+int
+gm20b_pmu_acr_boot(struct nvkm_falcon *falcon)
+{
+	struct nv_pmu_args args = { .secure_mode = true };
+	const u32 addr_args = falcon->data.limit - sizeof(struct nv_pmu_args);
+	nvkm_falcon_load_dmem(falcon, &args, addr_args, sizeof(args), 0);
+	nvkm_falcon_start(falcon);
+	return 0;
+}
+
+void
+gm20b_pmu_acr_bld_patch(struct nvkm_acr *acr, u32 bld, s64 adjust)
+{
+	struct loader_config hdr;
+	u64 addr;
+
+	nvkm_robj(acr->wpr, bld, &hdr, sizeof(hdr));
+	addr = ((u64)hdr.code_dma_base1 << 40 | hdr.code_dma_base << 8);
+	hdr.code_dma_base  = lower_32_bits((addr + adjust) >> 8);
+	hdr.code_dma_base1 = upper_32_bits((addr + adjust) >> 8);
+	addr = ((u64)hdr.data_dma_base1 << 40 | hdr.data_dma_base << 8);
+	hdr.data_dma_base  = lower_32_bits((addr + adjust) >> 8);
+	hdr.data_dma_base1 = upper_32_bits((addr + adjust) >> 8);
+	addr = ((u64)hdr.overlay_dma_base1 << 40 | hdr.overlay_dma_base << 8);
+	hdr.overlay_dma_base  = lower_32_bits((addr + adjust) << 8);
+	hdr.overlay_dma_base1 = upper_32_bits((addr + adjust) << 8);
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+
+	loader_config_dump(&acr->subdev, &hdr);
+}
+
+void
+gm20b_pmu_acr_bld_write(struct nvkm_acr *acr, u32 bld,
+			struct nvkm_acr_lsfw *lsfw)
+{
+	const u64 base = lsfw->offset.img + lsfw->app_start_offset;
+	const u64 code = (base + lsfw->app_resident_code_offset) >> 8;
+	const u64 data = (base + lsfw->app_resident_data_offset) >> 8;
+	const struct loader_config hdr = {
+		.dma_idx = FALCON_DMAIDX_UCODE,
+		.code_dma_base = lower_32_bits(code),
+		.code_size_total = lsfw->app_size,
+		.code_size_to_load = lsfw->app_resident_code_size,
+		.code_entry_point = lsfw->app_imem_entry,
+		.data_dma_base = lower_32_bits(data),
+		.data_size = lsfw->app_resident_data_size,
+		.overlay_dma_base = lower_32_bits(code),
+		.argc = 1,
+		.argv = lsfw->falcon->data.limit - sizeof(struct nv_pmu_args),
+		.code_dma_base1 = upper_32_bits(code),
+		.data_dma_base1 = upper_32_bits(data),
+		.overlay_dma_base1 = upper_32_bits(code),
+	};
+
+	nvkm_wobj(acr->wpr, bld, &hdr, sizeof(hdr));
+}
+
+static const struct nvkm_acr_lsf_func
+gm20b_pmu_acr = {
+	.flags = NVKM_ACR_LSF_DMACTL_REQ_CTX,
+	.bld_size = sizeof(struct loader_config),
+	.bld_write = gm20b_pmu_acr_bld_write,
+	.bld_patch = gm20b_pmu_acr_bld_patch,
+	.boot = gm20b_pmu_acr_boot,
+	.bootstrap_falcon = gm20b_pmu_acr_bootstrap_falcon,
+};
+
+static int
+gm20b_pmu_acr_init_wpr_callback(void *priv, struct nv_falcon_msg *hdr)
+{
+	struct nv_pmu_acr_init_wpr_region_msg *msg =
+		container_of(hdr, typeof(*msg), msg.hdr);
+	struct nvkm_pmu *pmu = priv;
+	struct nvkm_subdev *subdev = &pmu->subdev;
+
+	if (msg->error_code) {
+		nvkm_error(subdev, "ACR WPR init failure: %d\n",
+			   msg->error_code);
+		return -EINVAL;
+	}
+
+	nvkm_debug(subdev, "ACR WPR init complete\n");
+	complete_all(&pmu->wpr_ready);
+	return 0;
+}
+
+static int
+gm20b_pmu_acr_init_wpr(struct nvkm_pmu *pmu)
+{
+	struct nv_pmu_acr_init_wpr_region_cmd cmd = {
+		.cmd.hdr.unit_id = NV_PMU_UNIT_ACR,
+		.cmd.hdr.size = sizeof(cmd),
+		.cmd.cmd_type = NV_PMU_ACR_CMD_INIT_WPR_REGION,
+		.region_id = 1,
+		.wpr_offset = 0,
+	};
+
+	return nvkm_falcon_cmdq_send(pmu->hpq, &cmd.cmd.hdr,
+				     gm20b_pmu_acr_init_wpr_callback, pmu, 0);
+}
+
+int
+gm20b_pmu_initmsg(struct nvkm_pmu *pmu)
+{
+	struct nv_pmu_init_msg msg;
+	int ret;
+
+	ret = nvkm_falcon_msgq_recv_initmsg(pmu->msgq, &msg, sizeof(msg));
+	if (ret)
+		return ret;
+
+	if (msg.hdr.unit_id != NV_PMU_UNIT_INIT ||
+	    msg.msg_type != NV_PMU_INIT_MSG_INIT)
+		return -EINVAL;
+
+	nvkm_falcon_cmdq_init(pmu->hpq, msg.queue_info[0].index,
+					msg.queue_info[0].offset,
+					msg.queue_info[0].size);
+	nvkm_falcon_cmdq_init(pmu->lpq, msg.queue_info[1].index,
+					msg.queue_info[1].offset,
+					msg.queue_info[1].size);
+	nvkm_falcon_msgq_init(pmu->msgq, msg.queue_info[4].index,
+					 msg.queue_info[4].offset,
+					 msg.queue_info[4].size);
+	return gm20b_pmu_acr_init_wpr(pmu);
+}
+
+void
 gm20b_pmu_recv(struct nvkm_pmu *pmu)
 {
-	if (!pmu->queue) {
-		nvkm_warn(&pmu->subdev,
-			  "recv function called while no firmware set!\n");
-		return;
+	if (!pmu->initmsg_received) {
+		int ret = pmu->func->initmsg(pmu);
+		if (ret) {
+			nvkm_error(&pmu->subdev,
+				   "error parsing init message: %d\n", ret);
+			return;
+		}
+
+		pmu->initmsg_received = true;
 	}
 
-	nvkm_msgqueue_recv(pmu->queue);
+	nvkm_falcon_msgq_recv(pmu->msgq);
 }
 
 static const struct nvkm_pmu_func
 gm20b_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.enabled = gf100_pmu_enabled,
 	.intr = gt215_pmu_intr,
 	.recv = gm20b_pmu_recv,
+	.initmsg = gm20b_pmu_initmsg,
 };
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+MODULE_FIRMWARE("nvidia/gm20b/pmu/desc.bin");
+MODULE_FIRMWARE("nvidia/gm20b/pmu/image.bin");
+MODULE_FIRMWARE("nvidia/gm20b/pmu/sig.bin");
+#endif
+
 int
-gm20b_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
+gm20b_pmu_load(struct nvkm_pmu *pmu, int ver, const struct nvkm_pmu_fwif *fwif)
 {
-	int ret;
+	return nvkm_acr_lsfw_load_sig_image_desc(&pmu->subdev, &pmu->falcon,
+						 NVKM_ACR_LSF_PMU, "pmu/",
+						 ver, fwif->acr);
+}
 
-	ret = nvkm_pmu_new_(&gm20b_pmu, device, index, ppmu);
-	if (ret)
-		return ret;
+static const struct nvkm_pmu_fwif
+gm20b_pmu_fwif[] = {
+	{ 0, gm20b_pmu_load, &gm20b_pmu, &gm20b_pmu_acr },
+	{}
+};
 
-	return 0;
+int
+gm20b_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
+{
+	return nvkm_pmu_new_(gm20b_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp100.c
index e210cd6af816..09e05db21ff5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp100.c
@@ -25,12 +25,19 @@
 
 static const struct nvkm_pmu_func
 gp100_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.enabled = gf100_pmu_enabled,
 	.reset = gf100_pmu_reset,
 };
 
+static const struct nvkm_pmu_fwif
+gp100_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gp100_pmu },
+	{}
+};
+
 int
 gp100_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gp100_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gp100_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
index 98c7a2a8afc4..262b8a3dd507 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c
@@ -39,12 +39,19 @@ gp102_pmu_enabled(struct nvkm_pmu *pmu)
 
 static const struct nvkm_pmu_func
 gp102_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.enabled = gp102_pmu_enabled,
 	.reset = gp102_pmu_reset,
 };
 
+static const struct nvkm_pmu_fwif
+gp102_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gp102_pmu },
+	{}
+};
+
 int
 gp102_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gp102_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gp102_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
new file mode 100644
index 000000000000..5b81c7320479
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
@@ -0,0 +1,101 @@
+/*
+ * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+#include <subdev/acr.h>
+
+#include <nvfw/flcn.h>
+#include <nvfw/pmu.h>
+
+static int
+gp10b_pmu_acr_bootstrap_multiple_falcons_cb(void *priv,
+					    struct nv_falcon_msg *hdr)
+{
+	struct nv_pmu_acr_bootstrap_multiple_falcons_msg *msg =
+		container_of(hdr, typeof(*msg), msg.hdr);
+	return msg->falcon_mask;
+}
+static int
+gp10b_pmu_acr_bootstrap_multiple_falcons(struct nvkm_falcon *falcon, u32 mask)
+{
+	struct nvkm_pmu *pmu = container_of(falcon, typeof(*pmu), falcon);
+	struct nv_pmu_acr_bootstrap_multiple_falcons_cmd cmd = {
+		.cmd.hdr.unit_id = NV_PMU_UNIT_ACR,
+		.cmd.hdr.size = sizeof(cmd),
+		.cmd.cmd_type = NV_PMU_ACR_CMD_BOOTSTRAP_MULTIPLE_FALCONS,
+		.flags = NV_PMU_ACR_BOOTSTRAP_MULTIPLE_FALCONS_FLAGS_RESET_YES,
+		.falcon_mask = mask,
+		.wpr_lo = 0, /*XXX*/
+		.wpr_hi = 0, /*XXX*/
+	};
+	int ret;
+
+	ret = nvkm_falcon_cmdq_send(pmu->hpq, &cmd.cmd.hdr,
+				    gp10b_pmu_acr_bootstrap_multiple_falcons_cb,
+				    &pmu->subdev, msecs_to_jiffies(1000));
+	if (ret >= 0) {
+		if (ret != cmd.falcon_mask)
+			ret = -EIO;
+		else
+			ret = 0;
+	}
+
+	return ret;
+}
+
+static const struct nvkm_acr_lsf_func
+gp10b_pmu_acr = {
+	.flags = NVKM_ACR_LSF_DMACTL_REQ_CTX,
+	.bld_size = sizeof(struct loader_config),
+	.bld_write = gm20b_pmu_acr_bld_write,
+	.bld_patch = gm20b_pmu_acr_bld_patch,
+	.boot = gm20b_pmu_acr_boot,
+	.bootstrap_falcon = gm20b_pmu_acr_bootstrap_falcon,
+	.bootstrap_multiple_falcons = gp10b_pmu_acr_bootstrap_multiple_falcons,
+};
+
+static const struct nvkm_pmu_func
+gp10b_pmu = {
+	.flcn = &gt215_pmu_flcn,
+	.enabled = gf100_pmu_enabled,
+	.intr = gt215_pmu_intr,
+	.recv = gm20b_pmu_recv,
+	.initmsg = gm20b_pmu_initmsg,
+};
+
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
+MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
+MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");
+#endif
+
+static const struct nvkm_pmu_fwif
+gp10b_pmu_fwif[] = {
+	{ 0, gm20b_pmu_load, &gp10b_pmu, &gp10b_pmu_acr },
+	{}
+};
+
+int
+gp10b_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
+{
+	return nvkm_pmu_new_(gp10b_pmu_fwif, device, index, ppmu);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gt215.c
index e04216daea58..88b909913ff9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gt215.c
@@ -241,8 +241,27 @@ gt215_pmu_init(struct nvkm_pmu *pmu)
 	return 0;
 }
 
+const struct nvkm_falcon_func
+gt215_pmu_flcn = {
+	.debug = 0xc08,
+	.fbif = 0xe00,
+	.load_imem = nvkm_falcon_v1_load_imem,
+	.load_dmem = nvkm_falcon_v1_load_dmem,
+	.read_dmem = nvkm_falcon_v1_read_dmem,
+	.bind_context = nvkm_falcon_v1_bind_context,
+	.wait_for_halt = nvkm_falcon_v1_wait_for_halt,
+	.clear_interrupt = nvkm_falcon_v1_clear_interrupt,
+	.set_start_addr = nvkm_falcon_v1_set_start_addr,
+	.start = nvkm_falcon_v1_start,
+	.enable = nvkm_falcon_v1_enable,
+	.disable = nvkm_falcon_v1_disable,
+	.cmdq = { 0x4a0, 0x4b0, 4 },
+	.msgq = { 0x4c8, 0x4cc, 0 },
+};
+
 static const struct nvkm_pmu_func
 gt215_pmu = {
+	.flcn = &gt215_pmu_flcn,
 	.code.data = gt215_pmu_code,
 	.code.size = sizeof(gt215_pmu_code),
 	.data.data = gt215_pmu_data,
@@ -256,8 +275,14 @@ gt215_pmu = {
 	.recv = gt215_pmu_recv,
 };
 
+static const struct nvkm_pmu_fwif
+gt215_pmu_fwif[] = {
+	{ -1, gf100_pmu_nofw, &gt215_pmu },
+	{}
+};
+
 int
 gt215_pmu_new(struct nvkm_device *device, int index, struct nvkm_pmu **ppmu)
 {
-	return nvkm_pmu_new_(&gt215_pmu, device, index, ppmu);
+	return nvkm_pmu_new_(gt215_pmu_fwif, device, index, ppmu);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
index 26d73f9cd6d3..f470859244de 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h
@@ -4,13 +4,12 @@
 #define nvkm_pmu(p) container_of((p), struct nvkm_pmu, subdev)
 #include <subdev/pmu.h>
 #include <subdev/pmu/fuc/os.h>
-
-int nvkm_pmu_ctor(const struct nvkm_pmu_func *, struct nvkm_device *,
-		  int index, struct nvkm_pmu *);
-int nvkm_pmu_new_(const struct nvkm_pmu_func *, struct nvkm_device *,
-		  int index, struct nvkm_pmu **);
+enum nvkm_acr_lsf_id;
+struct nvkm_acr_lsfw;
 
 struct nvkm_pmu_func {
+	const struct nvkm_falcon_func *flcn;
+
 	struct {
 		u32 *data;
 		u32  size;
@@ -29,9 +28,11 @@ struct nvkm_pmu_func {
 	int (*send)(struct nvkm_pmu *, u32 reply[2], u32 process,
 		    u32 message, u32 data0, u32 data1);
 	void (*recv)(struct nvkm_pmu *);
+	int (*initmsg)(struct nvkm_pmu *);
 	void (*pgob)(struct nvkm_pmu *, bool);
 };
 
+extern const struct nvkm_falcon_func gt215_pmu_flcn;
 int gt215_pmu_init(struct nvkm_pmu *);
 void gt215_pmu_fini(struct nvkm_pmu *);
 void gt215_pmu_intr(struct nvkm_pmu *);
@@ -42,4 +43,26 @@ bool gf100_pmu_enabled(struct nvkm_pmu *);
 void gf100_pmu_reset(struct nvkm_pmu *);
 
 void gk110_pmu_pgob(struct nvkm_pmu *, bool);
+
+void gm20b_pmu_acr_bld_patch(struct nvkm_acr *, u32, s64);
+void gm20b_pmu_acr_bld_write(struct nvkm_acr *, u32, struct nvkm_acr_lsfw *);
+int gm20b_pmu_acr_boot(struct nvkm_falcon *);
+int gm20b_pmu_acr_bootstrap_falcon(struct nvkm_falcon *, enum nvkm_acr_lsf_id);
+void gm20b_pmu_recv(struct nvkm_pmu *);
+int gm20b_pmu_initmsg(struct nvkm_pmu *);
+
+struct nvkm_pmu_fwif {
+	int version;
+	int (*load)(struct nvkm_pmu *, int ver, const struct nvkm_pmu_fwif *);
+	const struct nvkm_pmu_func *func;
+	const struct nvkm_acr_lsf_func *acr;
+};
+
+int gf100_pmu_nofw(struct nvkm_pmu *, int, const struct nvkm_pmu_fwif *);
+int gm20b_pmu_load(struct nvkm_pmu *, int, const struct nvkm_pmu_fwif *);
+
+int nvkm_pmu_ctor(const struct nvkm_pmu_fwif *, struct nvkm_device *,
+		  int index, struct nvkm_pmu *);
+int nvkm_pmu_new_(const struct nvkm_pmu_fwif *, struct nvkm_device *,
+		  int index, struct nvkm_pmu **);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
deleted file mode 100644
index f3dee2693c79..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/Kbuild
+++ /dev/null
@@ -1,17 +0,0 @@
-# SPDX-License-Identifier: MIT
-nvkm-y += nvkm/subdev/secboot/base.o
-nvkm-y += nvkm/subdev/secboot/hs_ucode.o
-nvkm-y += nvkm/subdev/secboot/ls_ucode_gr.o
-nvkm-y += nvkm/subdev/secboot/ls_ucode_msgqueue.o
-nvkm-y += nvkm/subdev/secboot/acr.o
-nvkm-y += nvkm/subdev/secboot/acr_r352.o
-nvkm-y += nvkm/subdev/secboot/acr_r361.o
-nvkm-y += nvkm/subdev/secboot/acr_r364.o
-nvkm-y += nvkm/subdev/secboot/acr_r367.o
-nvkm-y += nvkm/subdev/secboot/acr_r370.o
-nvkm-y += nvkm/subdev/secboot/acr_r375.o
-nvkm-y += nvkm/subdev/secboot/gm200.o
-nvkm-y += nvkm/subdev/secboot/gm20b.o
-nvkm-y += nvkm/subdev/secboot/gp102.o
-nvkm-y += nvkm/subdev/secboot/gp108.o
-nvkm-y += nvkm/subdev/secboot/gp10b.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.c
deleted file mode 100644
index dc80985cf093..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr.h"
-
-#include <core/firmware.h>
-
-/**
- * Convenience function to duplicate a firmware file in memory and check that
- * it has the required minimum size.
- */
-void *
-nvkm_acr_load_firmware(const struct nvkm_subdev *subdev, const char *name,
-		       size_t min_size)
-{
-	const struct firmware *fw;
-	void *blob;
-	int ret;
-
-	ret = nvkm_firmware_get(subdev, name, &fw);
-	if (ret)
-		return ERR_PTR(ret);
-	if (fw->size < min_size) {
-		nvkm_error(subdev, "%s is smaller than expected size %zu\n",
-			   name, min_size);
-		nvkm_firmware_put(fw);
-		return ERR_PTR(-EINVAL);
-	}
-	blob = kmemdup(fw->data, fw->size, GFP_KERNEL);
-	nvkm_firmware_put(fw);
-	if (!blob)
-		return ERR_PTR(-ENOMEM);
-
-	return blob;
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h
deleted file mode 100644
index 73a2ac81ac69..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-#ifndef __NVKM_SECBOOT_ACR_H__
-#define __NVKM_SECBOOT_ACR_H__
-
-#include "priv.h"
-
-struct nvkm_acr;
-
-/**
- * struct nvkm_acr_func - properties and functions specific to an ACR
- *
- * @load: make the ACR ready to run on the given secboot device
- * @reset: reset the specified falcon
- * @start: start the specified falcon (assumed to have been reset)
- */
-struct nvkm_acr_func {
-	void (*dtor)(struct nvkm_acr *);
-	int (*oneinit)(struct nvkm_acr *, struct nvkm_secboot *);
-	int (*fini)(struct nvkm_acr *, struct nvkm_secboot *, bool);
-	int (*load)(struct nvkm_acr *, struct nvkm_falcon *,
-		    struct nvkm_gpuobj *, u64);
-	int (*reset)(struct nvkm_acr *, struct nvkm_secboot *, unsigned long);
-};
-
-/**
- * struct nvkm_acr - instance of an ACR
- *
- * @boot_falcon: ID of the falcon that will perform secure boot
- * @managed_falcons: bitfield of falcons managed by this ACR
- * @optional_falcons: bitfield of falcons we can live without
- */
-struct nvkm_acr {
-	const struct nvkm_acr_func *func;
-	const struct nvkm_subdev *subdev;
-
-	enum nvkm_secboot_falcon boot_falcon;
-	unsigned long managed_falcons;
-	unsigned long optional_falcons;
-};
-
-void *nvkm_acr_load_firmware(const struct nvkm_subdev *, const char *, size_t);
-
-struct nvkm_acr *acr_r352_new(unsigned long);
-struct nvkm_acr *acr_r361_new(unsigned long);
-struct nvkm_acr *acr_r364_new(unsigned long);
-struct nvkm_acr *acr_r367_new(enum nvkm_secboot_falcon, unsigned long);
-struct nvkm_acr *acr_r370_new(enum nvkm_secboot_falcon, unsigned long);
-struct nvkm_acr *acr_r375_new(enum nvkm_secboot_falcon, unsigned long);
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
deleted file mode 100644
index 7af971db91bc..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
+++ /dev/null
@@ -1,1241 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr_r352.h"
-#include "hs_ucode.h"
-
-#include <core/gpuobj.h>
-#include <core/firmware.h>
-#include <engine/falcon.h>
-#include <subdev/pmu.h>
-#include <core/msgqueue.h>
-#include <engine/sec2.h>
-
-/**
- * struct acr_r352_flcn_bl_desc - DMEM bootloader descriptor
- * @signature:		16B signature for secure code. 0s if no secure code
- * @ctx_dma:		DMA context to be used by BL while loading code/data
- * @code_dma_base:	256B-aligned Physical FB Address where code is located
- *			(falcon's $xcbase register)
- * @non_sec_code_off:	offset from code_dma_base where the non-secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @non_sec_code_size:	the size of the nonSecure code part.
- * @sec_code_off:	offset from code_dma_base where the secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @sec_code_size:	offset from code_dma_base where the secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @code_entry_point:	code entry point which will be invoked by BL after
- *                      code is loaded.
- * @data_dma_base:	256B aligned Physical FB Address where data is located.
- *			(falcon's $xdbase register)
- * @data_size:		size of data block. Should be multiple of 256B
- *
- * Structure used by the bootloader to load the rest of the code. This has
- * to be filled by host and copied into DMEM at offset provided in the
- * hsflcn_bl_desc.bl_desc_dmem_load_off.
- */
-struct acr_r352_flcn_bl_desc {
-	u32 reserved[4];
-	u32 signature[4];
-	u32 ctx_dma;
-	u32 code_dma_base;
-	u32 non_sec_code_off;
-	u32 non_sec_code_size;
-	u32 sec_code_off;
-	u32 sec_code_size;
-	u32 code_entry_point;
-	u32 data_dma_base;
-	u32 data_size;
-	u32 code_dma_base1;
-	u32 data_dma_base1;
-};
-
-/**
- * acr_r352_generate_flcn_bl_desc - generate generic BL descriptor for LS image
- */
-static void
-acr_r352_generate_flcn_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *img, u64 wpr_addr,
-			       void *_desc)
-{
-	struct acr_r352_flcn_bl_desc *desc = _desc;
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	u64 base, addr_code, addr_data;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = (base + pdesc->app_resident_code_offset) >> 8;
-	addr_data = (base + pdesc->app_resident_data_offset) >> 8;
-
-	desc->ctx_dma = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = lower_32_bits(addr_code);
-	desc->code_dma_base1 = upper_32_bits(addr_code);
-	desc->non_sec_code_off = pdesc->app_resident_code_offset;
-	desc->non_sec_code_size = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = lower_32_bits(addr_data);
-	desc->data_dma_base1 = upper_32_bits(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-}
-
-
-/**
- * struct hsflcn_acr_desc - data section of the HS firmware
- *
- * This header is to be copied at the beginning of DMEM by the HS bootloader.
- *
- * @signature:		signature of ACR ucode
- * @wpr_region_id:	region ID holding the WPR header and its details
- * @wpr_offset:		offset from the WPR region holding the wpr header
- * @regions:		region descriptors
- * @nonwpr_ucode_blob_size:	size of LS blob
- * @nonwpr_ucode_blob_start:	FB location of LS blob is
- */
-struct hsflcn_acr_desc {
-	union {
-		u8 reserved_dmem[0x200];
-		u32 signatures[4];
-	} ucode_reserved_space;
-	u32 wpr_region_id;
-	u32 wpr_offset;
-	u32 mmu_mem_range;
-#define FLCN_ACR_MAX_REGIONS 2
-	struct {
-		u32 no_regions;
-		struct {
-			u32 start_addr;
-			u32 end_addr;
-			u32 region_id;
-			u32 read_mask;
-			u32 write_mask;
-			u32 client_mask;
-		} region_props[FLCN_ACR_MAX_REGIONS];
-	} regions;
-	u32 ucode_blob_size;
-	u64 ucode_blob_base __aligned(8);
-	struct {
-		u32 vpr_enabled;
-		u32 vpr_start;
-		u32 vpr_end;
-		u32 hdcp_policies;
-	} vpr_desc;
-};
-
-
-/*
- * Low-secure blob creation
- */
-
-/**
- * struct acr_r352_lsf_lsb_header - LS firmware header
- * @signature:		signature to verify the firmware against
- * @ucode_off:		offset of the ucode blob in the WPR region. The ucode
- *                      blob contains the bootloader, code and data of the
- *                      LS falcon
- * @ucode_size:		size of the ucode blob, including bootloader
- * @data_size:		size of the ucode blob data
- * @bl_code_size:	size of the bootloader code
- * @bl_imem_off:	offset in imem of the bootloader
- * @bl_data_off:	offset of the bootloader data in WPR region
- * @bl_data_size:	size of the bootloader data
- * @app_code_off:	offset of the app code relative to ucode_off
- * @app_code_size:	size of the app code
- * @app_data_off:	offset of the app data relative to ucode_off
- * @app_data_size:	size of the app data
- * @flags:		flags for the secure bootloader
- *
- * This structure is written into the WPR region for each managed falcon. Each
- * instance is referenced by the lsb_offset member of the corresponding
- * lsf_wpr_header.
- */
-struct acr_r352_lsf_lsb_header {
-	/**
-	 * LS falcon signatures
-	 * @prd_keys:		signature to use in production mode
-	 * @dgb_keys:		signature to use in debug mode
-	 * @b_prd_present:	whether the production key is present
-	 * @b_dgb_present:	whether the debug key is present
-	 * @falcon_id:		ID of the falcon the ucode applies to
-	 */
-	struct {
-		u8 prd_keys[2][16];
-		u8 dbg_keys[2][16];
-		u32 b_prd_present;
-		u32 b_dbg_present;
-		u32 falcon_id;
-	} signature;
-	u32 ucode_off;
-	u32 ucode_size;
-	u32 data_size;
-	u32 bl_code_size;
-	u32 bl_imem_off;
-	u32 bl_data_off;
-	u32 bl_data_size;
-	u32 app_code_off;
-	u32 app_code_size;
-	u32 app_data_off;
-	u32 app_data_size;
-	u32 flags;
-};
-
-/**
- * struct acr_r352_lsf_wpr_header - LS blob WPR Header
- * @falcon_id:		LS falcon ID
- * @lsb_offset:		offset of the lsb_lsf_header in the WPR region
- * @bootstrap_owner:	secure falcon reponsible for bootstrapping the LS falcon
- * @lazy_bootstrap:	skip bootstrapping by ACR
- * @status:		bootstrapping status
- *
- * An array of these is written at the beginning of the WPR region, one for
- * each managed falcon. The array is terminated by an instance which falcon_id
- * is LSF_FALCON_ID_INVALID.
- */
-struct acr_r352_lsf_wpr_header {
-	u32 falcon_id;
-	u32 lsb_offset;
-	u32 bootstrap_owner;
-	u32 lazy_bootstrap;
-	u32 status;
-#define LSF_IMAGE_STATUS_NONE				0
-#define LSF_IMAGE_STATUS_COPY				1
-#define LSF_IMAGE_STATUS_VALIDATION_CODE_FAILED		2
-#define LSF_IMAGE_STATUS_VALIDATION_DATA_FAILED		3
-#define LSF_IMAGE_STATUS_VALIDATION_DONE		4
-#define LSF_IMAGE_STATUS_VALIDATION_SKIPPED		5
-#define LSF_IMAGE_STATUS_BOOTSTRAP_READY		6
-};
-
-/**
- * struct ls_ucode_img_r352 - ucode image augmented with r352 headers
- */
-struct ls_ucode_img_r352 {
-	struct ls_ucode_img base;
-
-	const struct acr_r352_lsf_func *func;
-
-	struct acr_r352_lsf_wpr_header wpr_header;
-	struct acr_r352_lsf_lsb_header lsb_header;
-};
-#define ls_ucode_img_r352(i) container_of(i, struct ls_ucode_img_r352, base)
-
-/**
- * ls_ucode_img_load() - create a lsf_ucode_img and load it
- */
-struct ls_ucode_img *
-acr_r352_ls_ucode_img_load(const struct acr_r352 *acr,
-			   const struct nvkm_secboot *sb,
-			   enum nvkm_secboot_falcon falcon_id)
-{
-	const struct nvkm_subdev *subdev = acr->base.subdev;
-	const struct acr_r352_ls_func *func = acr->func->ls_func[falcon_id];
-	struct ls_ucode_img_r352 *img;
-	int ret;
-
-	img = kzalloc(sizeof(*img), GFP_KERNEL);
-	if (!img)
-		return ERR_PTR(-ENOMEM);
-
-	img->base.falcon_id = falcon_id;
-
-	ret = func->load(sb, func->version_max, &img->base);
-	if (ret < 0) {
-		kfree(img->base.ucode_data);
-		kfree(img->base.sig);
-		kfree(img);
-		return ERR_PTR(ret);
-	}
-
-	img->func = func->version[ret];
-
-	/* Check that the signature size matches our expectations... */
-	if (img->base.sig_size != sizeof(img->lsb_header.signature)) {
-		nvkm_error(subdev, "invalid signature size for %s falcon!\n",
-			   nvkm_secboot_falcon_name[falcon_id]);
-		return ERR_PTR(-EINVAL);
-	}
-
-	/* Copy signature to the right place */
-	memcpy(&img->lsb_header.signature, img->base.sig, img->base.sig_size);
-
-	/* not needed? the signature should already have the right value */
-	img->lsb_header.signature.falcon_id = falcon_id;
-
-	return &img->base;
-}
-
-#define LSF_LSB_HEADER_ALIGN 256
-#define LSF_BL_DATA_ALIGN 256
-#define LSF_BL_DATA_SIZE_ALIGN 256
-#define LSF_BL_CODE_SIZE_ALIGN 256
-#define LSF_UCODE_DATA_ALIGN 4096
-
-/**
- * acr_r352_ls_img_fill_headers - fill the WPR and LSB headers of an image
- * @acr:	ACR to use
- * @img:	image to generate for
- * @offset:	offset in the WPR region where this image starts
- *
- * Allocate space in the WPR area from offset and write the WPR and LSB headers
- * accordingly.
- *
- * Return: offset at the end of this image.
- */
-static u32
-acr_r352_ls_img_fill_headers(struct acr_r352 *acr,
-			     struct ls_ucode_img_r352 *img, u32 offset)
-{
-	struct ls_ucode_img *_img = &img->base;
-	struct acr_r352_lsf_wpr_header *whdr = &img->wpr_header;
-	struct acr_r352_lsf_lsb_header *lhdr = &img->lsb_header;
-	struct ls_ucode_img_desc *desc = &_img->ucode_desc;
-	const struct acr_r352_lsf_func *func = img->func;
-
-	/* Fill WPR header */
-	whdr->falcon_id = _img->falcon_id;
-	whdr->bootstrap_owner = acr->base.boot_falcon;
-	whdr->status = LSF_IMAGE_STATUS_COPY;
-
-	/* Skip bootstrapping falcons started by someone else than ACR */
-	if (acr->lazy_bootstrap & BIT(_img->falcon_id))
-		whdr->lazy_bootstrap = 1;
-
-	/* Align, save off, and include an LSB header size */
-	offset = ALIGN(offset, LSF_LSB_HEADER_ALIGN);
-	whdr->lsb_offset = offset;
-	offset += sizeof(*lhdr);
-
-	/*
-	 * Align, save off, and include the original (static) ucode
-	 * image size
-	 */
-	offset = ALIGN(offset, LSF_UCODE_DATA_ALIGN);
-	_img->ucode_off = lhdr->ucode_off = offset;
-	offset += _img->ucode_size;
-
-	/*
-	 * For falcons that use a boot loader (BL), we append a loader
-	 * desc structure on the end of the ucode image and consider
-	 * this the boot loader data. The host will then copy the loader
-	 * desc args to this space within the WPR region (before locking
-	 * down) and the HS bin will then copy them to DMEM 0 for the
-	 * loader.
-	 */
-	lhdr->bl_code_size = ALIGN(desc->bootloader_size,
-				   LSF_BL_CODE_SIZE_ALIGN);
-	lhdr->ucode_size = ALIGN(desc->app_resident_data_offset,
-				 LSF_BL_CODE_SIZE_ALIGN) + lhdr->bl_code_size;
-	lhdr->data_size = ALIGN(desc->app_size, LSF_BL_CODE_SIZE_ALIGN) +
-				lhdr->bl_code_size - lhdr->ucode_size;
-	/*
-	 * Though the BL is located at 0th offset of the image, the VA
-	 * is different to make sure that it doesn't collide the actual
-	 * OS VA range
-	 */
-	lhdr->bl_imem_off = desc->bootloader_imem_offset;
-	lhdr->app_code_off = desc->app_start_offset +
-			     desc->app_resident_code_offset;
-	lhdr->app_code_size = desc->app_resident_code_size;
-	lhdr->app_data_off = desc->app_start_offset +
-			     desc->app_resident_data_offset;
-	lhdr->app_data_size = desc->app_resident_data_size;
-
-	lhdr->flags = func->lhdr_flags;
-	if (_img->falcon_id == acr->base.boot_falcon)
-		lhdr->flags |= LSF_FLAG_DMACTL_REQ_CTX;
-
-	/* Align and save off BL descriptor size */
-	lhdr->bl_data_size = ALIGN(func->bl_desc_size, LSF_BL_DATA_SIZE_ALIGN);
-
-	/*
-	 * Align, save off, and include the additional BL data
-	 */
-	offset = ALIGN(offset, LSF_BL_DATA_ALIGN);
-	lhdr->bl_data_off = offset;
-	offset += lhdr->bl_data_size;
-
-	return offset;
-}
-
-/**
- * acr_r352_ls_fill_headers - fill WPR and LSB headers of all managed images
- */
-int
-acr_r352_ls_fill_headers(struct acr_r352 *acr, struct list_head *imgs)
-{
-	struct ls_ucode_img_r352 *img;
-	struct list_head *l;
-	u32 count = 0;
-	u32 offset;
-
-	/* Count the number of images to manage */
-	list_for_each(l, imgs)
-		count++;
-
-	/*
-	 * Start with an array of WPR headers at the base of the WPR.
-	 * The expectation here is that the secure falcon will do a single DMA
-	 * read of this array and cache it internally so it's ok to pack these.
-	 * Also, we add 1 to the falcon count to indicate the end of the array.
-	 */
-	offset = sizeof(img->wpr_header) * (count + 1);
-
-	/*
-	 * Walk the managed falcons, accounting for the LSB structs
-	 * as well as the ucode images.
-	 */
-	list_for_each_entry(img, imgs, base.node) {
-		offset = acr_r352_ls_img_fill_headers(acr, img, offset);
-	}
-
-	return offset;
-}
-
-/**
- * acr_r352_ls_write_wpr - write the WPR blob contents
- */
-int
-acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
-		      struct nvkm_gpuobj *wpr_blob, u64 wpr_addr)
-{
-	struct ls_ucode_img *_img;
-	u32 pos = 0;
-	u32 max_desc_size = 0;
-	u8 *gdesc;
-
-	/* Figure out how large we need gdesc to be. */
-	list_for_each_entry(_img, imgs, node) {
-		struct ls_ucode_img_r352 *img = ls_ucode_img_r352(_img);
-		const struct acr_r352_lsf_func *ls_func = img->func;
-
-		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
-	}
-
-	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
-	if (!gdesc)
-		return -ENOMEM;
-
-	nvkm_kmap(wpr_blob);
-
-	list_for_each_entry(_img, imgs, node) {
-		struct ls_ucode_img_r352 *img = ls_ucode_img_r352(_img);
-		const struct acr_r352_lsf_func *ls_func = img->func;
-
-		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
-				      sizeof(img->wpr_header));
-
-		nvkm_gpuobj_memcpy_to(wpr_blob, img->wpr_header.lsb_offset,
-				     &img->lsb_header, sizeof(img->lsb_header));
-
-		/* Generate and write BL descriptor */
-		memset(gdesc, 0, ls_func->bl_desc_size);
-		ls_func->generate_bl_desc(&acr->base, _img, wpr_addr, gdesc);
-
-		nvkm_gpuobj_memcpy_to(wpr_blob, img->lsb_header.bl_data_off,
-				      gdesc, ls_func->bl_desc_size);
-
-		/* Copy ucode */
-		nvkm_gpuobj_memcpy_to(wpr_blob, img->lsb_header.ucode_off,
-				      _img->ucode_data, _img->ucode_size);
-
-		pos += sizeof(img->wpr_header);
-	}
-
-	nvkm_wo32(wpr_blob, pos, NVKM_SECBOOT_FALCON_INVALID);
-
-	nvkm_done(wpr_blob);
-
-	kfree(gdesc);
-
-	return 0;
-}
-
-/* Both size and address of WPR need to be 256K-aligned */
-#define WPR_ALIGNMENT	0x40000
-/**
- * acr_r352_prepare_ls_blob() - prepare the LS blob
- *
- * For each securely managed falcon, load the FW, signatures and bootloaders and
- * prepare a ucode blob. Then, compute the offsets in the WPR region for each
- * blob, and finally write the headers and ucode blobs into a GPU object that
- * will be copied into the WPR region by the HS firmware.
- */
-static int
-acr_r352_prepare_ls_blob(struct acr_r352 *acr, struct nvkm_secboot *sb)
-{
-	const struct nvkm_subdev *subdev = acr->base.subdev;
-	struct list_head imgs;
-	struct ls_ucode_img *img, *t;
-	unsigned long managed_falcons = acr->base.managed_falcons;
-	u64 wpr_addr = sb->wpr_addr;
-	u32 wpr_size = sb->wpr_size;
-	int managed_count = 0;
-	u32 image_wpr_size, ls_blob_size;
-	int falcon_id;
-	int ret;
-
-	INIT_LIST_HEAD(&imgs);
-
-	/* Load all LS blobs */
-	for_each_set_bit(falcon_id, &managed_falcons, NVKM_SECBOOT_FALCON_END) {
-		struct ls_ucode_img *img;
-
-		img = acr->func->ls_ucode_img_load(acr, sb, falcon_id);
-		if (IS_ERR(img)) {
-			if (acr->base.optional_falcons & BIT(falcon_id)) {
-				managed_falcons &= ~BIT(falcon_id);
-				nvkm_info(subdev, "skipping %s falcon...\n",
-					  nvkm_secboot_falcon_name[falcon_id]);
-				continue;
-			}
-			ret = PTR_ERR(img);
-			goto cleanup;
-		}
-
-		list_add_tail(&img->node, &imgs);
-		managed_count++;
-	}
-
-	/* Commit the actual list of falcons we will manage from now on */
-	acr->base.managed_falcons = managed_falcons;
-
-	/*
-	 * If the boot falcon has a firmare, let it manage the bootstrap of other
-	 * falcons.
-	 */
-	if (acr->func->ls_func[acr->base.boot_falcon] &&
-	    (managed_falcons & BIT(acr->base.boot_falcon))) {
-		for_each_set_bit(falcon_id, &managed_falcons,
-				 NVKM_SECBOOT_FALCON_END) {
-			if (falcon_id == acr->base.boot_falcon)
-				continue;
-
-			acr->lazy_bootstrap |= BIT(falcon_id);
-		}
-	}
-
-	/*
-	 * Fill the WPR and LSF headers with the right offsets and compute
-	 * required WPR size
-	 */
-	image_wpr_size = acr->func->ls_fill_headers(acr, &imgs);
-	image_wpr_size = ALIGN(image_wpr_size, WPR_ALIGNMENT);
-
-	ls_blob_size = image_wpr_size;
-
-	/*
-	 * If we need a shadow area, allocate twice the size and use the
-	 * upper half as WPR
-	 */
-	if (wpr_size == 0 && acr->func->shadow_blob)
-		ls_blob_size *= 2;
-
-	/* Allocate GPU object that will contain the WPR region */
-	ret = nvkm_gpuobj_new(subdev->device, ls_blob_size, WPR_ALIGNMENT,
-			      false, NULL, &acr->ls_blob);
-	if (ret)
-		goto cleanup;
-
-	nvkm_debug(subdev, "%d managed LS falcons, WPR size is %d bytes\n",
-		    managed_count, image_wpr_size);
-
-	/* If WPR address and size are not fixed, set them to fit the LS blob */
-	if (wpr_size == 0) {
-		wpr_addr = acr->ls_blob->addr;
-		if (acr->func->shadow_blob)
-			wpr_addr += acr->ls_blob->size / 2;
-
-		wpr_size = image_wpr_size;
-	/*
-	 * But if the WPR region is set by the bootloader, it is illegal for
-	 * the HS blob to be larger than this region.
-	 */
-	} else if (image_wpr_size > wpr_size) {
-		nvkm_error(subdev, "WPR region too small for FW blob!\n");
-		nvkm_error(subdev, "required: %dB\n", image_wpr_size);
-		nvkm_error(subdev, "available: %dB\n", wpr_size);
-		ret = -ENOSPC;
-		goto cleanup;
-	}
-
-	/* Write LS blob */
-	ret = acr->func->ls_write_wpr(acr, &imgs, acr->ls_blob, wpr_addr);
-	if (ret)
-		nvkm_gpuobj_del(&acr->ls_blob);
-
-cleanup:
-	list_for_each_entry_safe(img, t, &imgs, node) {
-		kfree(img->ucode_data);
-		kfree(img->sig);
-		kfree(img);
-	}
-
-	return ret;
-}
-
-
-
-
-void
-acr_r352_fixup_hs_desc(struct acr_r352 *acr, struct nvkm_secboot *sb,
-		       void *_desc)
-{
-	struct hsflcn_acr_desc *desc = _desc;
-	struct nvkm_gpuobj *ls_blob = acr->ls_blob;
-
-	/* WPR region information if WPR is not fixed */
-	if (sb->wpr_size == 0) {
-		u64 wpr_start = ls_blob->addr;
-		u64 wpr_end = wpr_start + ls_blob->size;
-
-		desc->wpr_region_id = 1;
-		desc->regions.no_regions = 2;
-		desc->regions.region_props[0].start_addr = wpr_start >> 8;
-		desc->regions.region_props[0].end_addr = wpr_end >> 8;
-		desc->regions.region_props[0].region_id = 1;
-		desc->regions.region_props[0].read_mask = 0xf;
-		desc->regions.region_props[0].write_mask = 0xc;
-		desc->regions.region_props[0].client_mask = 0x2;
-	} else {
-		desc->ucode_blob_base = ls_blob->addr;
-		desc->ucode_blob_size = ls_blob->size;
-	}
-}
-
-static void
-acr_r352_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
-			     u64 offset)
-{
-	struct acr_r352_flcn_bl_desc *bl_desc = _bl_desc;
-	u64 addr_code, addr_data;
-
-	addr_code = offset >> 8;
-	addr_data = (offset + hdr->data_dma_base) >> 8;
-
-	bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
-	bl_desc->code_dma_base = lower_32_bits(addr_code);
-	bl_desc->non_sec_code_off = hdr->non_sec_code_off;
-	bl_desc->non_sec_code_size = hdr->non_sec_code_size;
-	bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
-	bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
-	bl_desc->code_entry_point = 0;
-	bl_desc->data_dma_base = lower_32_bits(addr_data);
-	bl_desc->data_size = hdr->data_size;
-}
-
-/**
- * acr_r352_prepare_hs_blob - load and prepare a HS blob and BL descriptor
- *
- * @sb secure boot instance to prepare for
- * @fw name of the HS firmware to load
- * @blob pointer to gpuobj that will be allocated to receive the HS FW payload
- * @bl_desc pointer to the BL descriptor to write for this firmware
- * @patch whether we should patch the HS descriptor (only for HS loaders)
- */
-static int
-acr_r352_prepare_hs_blob(struct acr_r352 *acr, struct nvkm_secboot *sb,
-			 const char *fw, struct nvkm_gpuobj **blob,
-			 struct hsf_load_header *load_header, bool patch)
-{
-	struct nvkm_subdev *subdev = &sb->subdev;
-	void *acr_image;
-	struct fw_bin_header *hsbin_hdr;
-	struct hsf_fw_header *fw_hdr;
-	struct hsf_load_header *load_hdr;
-	void *acr_data;
-	int ret;
-
-	acr_image = hs_ucode_load_blob(subdev, sb->boot_falcon, fw);
-	if (IS_ERR(acr_image))
-		return PTR_ERR(acr_image);
-
-	hsbin_hdr = acr_image;
-	fw_hdr = acr_image + hsbin_hdr->header_offset;
-	load_hdr = acr_image + fw_hdr->hdr_offset;
-	acr_data = acr_image + hsbin_hdr->data_offset;
-
-	/* Patch descriptor with WPR information? */
-	if (patch) {
-		struct hsflcn_acr_desc *desc;
-
-		desc = acr_data + load_hdr->data_dma_base;
-		acr->func->fixup_hs_desc(acr, sb, desc);
-	}
-
-	if (load_hdr->num_apps > ACR_R352_MAX_APPS) {
-		nvkm_error(subdev, "more apps (%d) than supported (%d)!",
-			   load_hdr->num_apps, ACR_R352_MAX_APPS);
-		ret = -EINVAL;
-		goto cleanup;
-	}
-	memcpy(load_header, load_hdr, sizeof(*load_header) +
-			  (sizeof(load_hdr->apps[0]) * 2 * load_hdr->num_apps));
-
-	/* Create ACR blob and copy HS data to it */
-	ret = nvkm_gpuobj_new(subdev->device, ALIGN(hsbin_hdr->data_size, 256),
-			      0x1000, false, NULL, blob);
-	if (ret)
-		goto cleanup;
-
-	nvkm_kmap(*blob);
-	nvkm_gpuobj_memcpy_to(*blob, 0, acr_data, hsbin_hdr->data_size);
-	nvkm_done(*blob);
-
-cleanup:
-	kfree(acr_image);
-
-	return ret;
-}
-
-/**
- * acr_r352_load_blobs - load blobs common to all ACR V1 versions.
- *
- * This includes the LS blob, HS ucode loading blob, and HS bootloader.
- *
- * The HS ucode unload blob is only used on dGPU if the WPR region is variable.
- */
-int
-acr_r352_load_blobs(struct acr_r352 *acr, struct nvkm_secboot *sb)
-{
-	struct nvkm_subdev *subdev = &sb->subdev;
-	int ret;
-
-	/* Firmware already loaded? */
-	if (acr->firmware_ok)
-		return 0;
-
-	/* Load and prepare the managed falcon's firmwares */
-	ret = acr_r352_prepare_ls_blob(acr, sb);
-	if (ret)
-		return ret;
-
-	/* Load the HS firmware that will load the LS firmwares */
-	if (!acr->load_blob) {
-		ret = acr_r352_prepare_hs_blob(acr, sb, "acr/ucode_load",
-					       &acr->load_blob,
-					       &acr->load_bl_header, true);
-		if (ret)
-			return ret;
-	}
-
-	/* If the ACR region is dynamically programmed, we need an unload FW */
-	if (sb->wpr_size == 0) {
-		ret = acr_r352_prepare_hs_blob(acr, sb, "acr/ucode_unload",
-					       &acr->unload_blob,
-					       &acr->unload_bl_header, false);
-		if (ret)
-			return ret;
-	}
-
-	/* Load the HS firmware bootloader */
-	if (!acr->hsbl_blob) {
-		acr->hsbl_blob = nvkm_acr_load_firmware(subdev, "acr/bl", 0);
-		if (IS_ERR(acr->hsbl_blob)) {
-			ret = PTR_ERR(acr->hsbl_blob);
-			acr->hsbl_blob = NULL;
-			return ret;
-		}
-
-		if (acr->base.boot_falcon != NVKM_SECBOOT_FALCON_PMU) {
-			acr->hsbl_unload_blob = nvkm_acr_load_firmware(subdev,
-							    "acr/unload_bl", 0);
-			if (IS_ERR(acr->hsbl_unload_blob)) {
-				ret = PTR_ERR(acr->hsbl_unload_blob);
-				acr->hsbl_unload_blob = NULL;
-				return ret;
-			}
-		} else {
-			acr->hsbl_unload_blob = acr->hsbl_blob;
-		}
-	}
-
-	acr->firmware_ok = true;
-	nvkm_debug(&sb->subdev, "LS blob successfully created\n");
-
-	return 0;
-}
-
-/**
- * acr_r352_load() - prepare HS falcon to run the specified blob, mapped.
- *
- * Returns the start address to use, or a negative error value.
- */
-static int
-acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
-	      struct nvkm_gpuobj *blob, u64 offset)
-{
-	struct acr_r352 *acr = acr_r352(_acr);
-	const u32 bl_desc_size = acr->func->hs_bl_desc_size;
-	const struct hsf_load_header *load_hdr;
-	struct fw_bin_header *bl_hdr;
-	struct fw_bl_desc *hsbl_desc;
-	void *bl, *blob_data, *hsbl_code, *hsbl_data;
-	u32 code_size;
-	u8 *bl_desc;
-
-	bl_desc = kzalloc(bl_desc_size, GFP_KERNEL);
-	if (!bl_desc)
-		return -ENOMEM;
-
-	/* Find the bootloader descriptor for our blob and copy it */
-	if (blob == acr->load_blob) {
-		load_hdr = &acr->load_bl_header;
-		bl = acr->hsbl_blob;
-	} else if (blob == acr->unload_blob) {
-		load_hdr = &acr->unload_bl_header;
-		bl = acr->hsbl_unload_blob;
-	} else {
-		nvkm_error(_acr->subdev, "invalid secure boot blob!\n");
-		kfree(bl_desc);
-		return -EINVAL;
-	}
-
-	bl_hdr = bl;
-	hsbl_desc = bl + bl_hdr->header_offset;
-	blob_data = bl + bl_hdr->data_offset;
-	hsbl_code = blob_data + hsbl_desc->code_off;
-	hsbl_data = blob_data + hsbl_desc->data_off;
-	code_size = ALIGN(hsbl_desc->code_size, 256);
-
-	/*
-	 * Copy HS bootloader data
-	 */
-	nvkm_falcon_load_dmem(falcon, hsbl_data, 0x0, hsbl_desc->data_size, 0);
-
-	/* Copy HS bootloader code to end of IMEM */
-	nvkm_falcon_load_imem(falcon, hsbl_code, falcon->code.limit - code_size,
-			      code_size, hsbl_desc->start_tag, 0, false);
-
-	/* Generate the BL header */
-	acr->func->generate_hs_bl_desc(load_hdr, bl_desc, offset);
-
-	/*
-	 * Copy HS BL header where the HS descriptor expects it to be
-	 */
-	nvkm_falcon_load_dmem(falcon, bl_desc, hsbl_desc->dmem_load_off,
-			      bl_desc_size, 0);
-
-	kfree(bl_desc);
-	return hsbl_desc->start_tag << 8;
-}
-
-static int
-acr_r352_shutdown(struct acr_r352 *acr, struct nvkm_secboot *sb)
-{
-	struct nvkm_subdev *subdev = &sb->subdev;
-	int i;
-
-	/* Run the unload blob to unprotect the WPR region */
-	if (acr->unload_blob && sb->wpr_set) {
-		int ret;
-
-		nvkm_debug(subdev, "running HS unload blob\n");
-		ret = sb->func->run_blob(sb, acr->unload_blob, sb->halt_falcon);
-		if (ret < 0)
-			return ret;
-		/*
-		 * Unload blob will return this error code - it is not an error
-		 * and the expected behavior on RM as well
-		 */
-		if (ret && ret != 0x1d) {
-			nvkm_error(subdev, "HS unload failed, ret 0x%08x\n", ret);
-			return -EINVAL;
-		}
-		nvkm_debug(subdev, "HS unload blob completed\n");
-	}
-
-	for (i = 0; i < NVKM_SECBOOT_FALCON_END; i++)
-		acr->falcon_state[i] = NON_SECURE;
-
-	sb->wpr_set = false;
-
-	return 0;
-}
-
-/**
- * Check if the WPR region has been indeed set by the ACR firmware, and
- * matches where it should be.
- */
-static bool
-acr_r352_wpr_is_set(const struct acr_r352 *acr, const struct nvkm_secboot *sb)
-{
-	const struct nvkm_subdev *subdev = &sb->subdev;
-	const struct nvkm_device *device = subdev->device;
-	u64 wpr_lo, wpr_hi;
-	u64 wpr_range_lo, wpr_range_hi;
-
-	nvkm_wr32(device, 0x100cd4, 0x2);
-	wpr_lo = (nvkm_rd32(device, 0x100cd4) & ~0xff);
-	wpr_lo <<= 8;
-	nvkm_wr32(device, 0x100cd4, 0x3);
-	wpr_hi = (nvkm_rd32(device, 0x100cd4) & ~0xff);
-	wpr_hi <<= 8;
-
-	if (sb->wpr_size != 0) {
-		wpr_range_lo = sb->wpr_addr;
-		wpr_range_hi = wpr_range_lo + sb->wpr_size;
-	} else {
-		wpr_range_lo = acr->ls_blob->addr;
-		wpr_range_hi = wpr_range_lo + acr->ls_blob->size;
-	}
-
-	return (wpr_lo >= wpr_range_lo && wpr_lo < wpr_range_hi &&
-		wpr_hi > wpr_range_lo && wpr_hi <= wpr_range_hi);
-}
-
-static int
-acr_r352_bootstrap(struct acr_r352 *acr, struct nvkm_secboot *sb)
-{
-	const struct nvkm_subdev *subdev = &sb->subdev;
-	unsigned long managed_falcons = acr->base.managed_falcons;
-	int falcon_id;
-	int ret;
-
-	if (sb->wpr_set)
-		return 0;
-
-	/* Make sure all blobs are ready */
-	ret = acr_r352_load_blobs(acr, sb);
-	if (ret)
-		return ret;
-
-	nvkm_debug(subdev, "running HS load blob\n");
-	ret = sb->func->run_blob(sb, acr->load_blob, sb->boot_falcon);
-	/* clear halt interrupt */
-	nvkm_falcon_clear_interrupt(sb->boot_falcon, 0x10);
-	sb->wpr_set = acr_r352_wpr_is_set(acr, sb);
-	if (ret < 0) {
-		return ret;
-	} else if (ret > 0) {
-		nvkm_error(subdev, "HS load failed, ret 0x%08x\n", ret);
-		return -EINVAL;
-	}
-	nvkm_debug(subdev, "HS load blob completed\n");
-	/* WPR must be set at this point */
-	if (!sb->wpr_set) {
-		nvkm_error(subdev, "ACR blob completed but WPR not set!\n");
-		return -EINVAL;
-	}
-
-	/* Run LS firmwares post_run hooks */
-	for_each_set_bit(falcon_id, &managed_falcons, NVKM_SECBOOT_FALCON_END) {
-		const struct acr_r352_ls_func *func =
-						  acr->func->ls_func[falcon_id];
-
-		if (func->post_run) {
-			ret = func->post_run(&acr->base, sb);
-			if (ret)
-				return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * acr_r352_reset_nopmu - dummy reset method when no PMU firmware is loaded
- *
- * Reset is done by re-executing secure boot from scratch, with lazy bootstrap
- * disabled. This has the effect of making all managed falcons ready-to-run.
- */
-static int
-acr_r352_reset_nopmu(struct acr_r352 *acr, struct nvkm_secboot *sb,
-		     unsigned long falcon_mask)
-{
-	int falcon;
-	int ret;
-
-	/*
-	 * Perform secure boot each time we are called on FECS. Since only FECS
-	 * and GPCCS are managed and started together, this ought to be safe.
-	 */
-	if (!(falcon_mask & BIT(NVKM_SECBOOT_FALCON_FECS)))
-		goto end;
-
-	ret = acr_r352_shutdown(acr, sb);
-	if (ret)
-		return ret;
-
-	ret = acr_r352_bootstrap(acr, sb);
-	if (ret)
-		return ret;
-
-end:
-	for_each_set_bit(falcon, &falcon_mask, NVKM_SECBOOT_FALCON_END) {
-		acr->falcon_state[falcon] = RESET;
-	}
-	return 0;
-}
-
-/*
- * acr_r352_reset() - execute secure boot from the prepared state
- *
- * Load the HS bootloader and ask the falcon to run it. This will in turn
- * load the HS firmware and run it, so once the falcon stops all the managed
- * falcons should have their LS firmware loaded and be ready to run.
- */
-static int
-acr_r352_reset(struct nvkm_acr *_acr, struct nvkm_secboot *sb,
-	       unsigned long falcon_mask)
-{
-	struct acr_r352 *acr = acr_r352(_acr);
-	struct nvkm_msgqueue *queue;
-	int falcon;
-	bool wpr_already_set = sb->wpr_set;
-	int ret;
-
-	/* Make sure secure boot is performed */
-	ret = acr_r352_bootstrap(acr, sb);
-	if (ret)
-		return ret;
-
-	/* No PMU interface? */
-	if (!nvkm_secboot_is_managed(sb, _acr->boot_falcon)) {
-		/* Redo secure boot entirely if it was already done */
-		if (wpr_already_set)
-			return acr_r352_reset_nopmu(acr, sb, falcon_mask);
-		/* Else return the result of the initial invokation */
-		else
-			return ret;
-	}
-
-	switch (_acr->boot_falcon) {
-	case NVKM_SECBOOT_FALCON_PMU:
-		queue = sb->subdev.device->pmu->queue;
-		break;
-	case NVKM_SECBOOT_FALCON_SEC2:
-		queue = sb->subdev.device->sec2->queue;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Otherwise just ask the LS firmware to reset the falcon */
-	for_each_set_bit(falcon, &falcon_mask, NVKM_SECBOOT_FALCON_END)
-		nvkm_debug(&sb->subdev, "resetting %s falcon\n",
-			   nvkm_secboot_falcon_name[falcon]);
-	ret = nvkm_msgqueue_acr_boot_falcons(queue, falcon_mask);
-	if (ret) {
-		nvkm_error(&sb->subdev, "error during falcon reset: %d\n", ret);
-		return ret;
-	}
-	nvkm_debug(&sb->subdev, "falcon reset done\n");
-
-	return 0;
-}
-
-static int
-acr_r352_fini(struct nvkm_acr *_acr, struct nvkm_secboot *sb, bool suspend)
-{
-	struct acr_r352 *acr = acr_r352(_acr);
-
-	return acr_r352_shutdown(acr, sb);
-}
-
-static void
-acr_r352_dtor(struct nvkm_acr *_acr)
-{
-	struct acr_r352 *acr = acr_r352(_acr);
-
-	nvkm_gpuobj_del(&acr->unload_blob);
-
-	if (_acr->boot_falcon != NVKM_SECBOOT_FALCON_PMU)
-		kfree(acr->hsbl_unload_blob);
-	kfree(acr->hsbl_blob);
-	nvkm_gpuobj_del(&acr->load_blob);
-	nvkm_gpuobj_del(&acr->ls_blob);
-
-	kfree(acr);
-}
-
-static const struct acr_r352_lsf_func
-acr_r352_ls_fecs_func_0 = {
-	.generate_bl_desc = acr_r352_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r352_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r352_ls_fecs_func = {
-	.load = acr_ls_ucode_load_fecs,
-	.version_max = 0,
-	.version = {
-		&acr_r352_ls_fecs_func_0,
-	}
-};
-
-static const struct acr_r352_lsf_func
-acr_r352_ls_gpccs_func_0 = {
-	.generate_bl_desc = acr_r352_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r352_flcn_bl_desc),
-	/* GPCCS will be loaded using PRI */
-	.lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
-};
-
-static const struct acr_r352_ls_func
-acr_r352_ls_gpccs_func = {
-	.load = acr_ls_ucode_load_gpccs,
-	.version_max = 0,
-	.version = {
-		&acr_r352_ls_gpccs_func_0,
-	}
-};
-
-
-
-/**
- * struct acr_r352_pmu_bl_desc - PMU DMEM bootloader descriptor
- * @dma_idx:		DMA context to be used by BL while loading code/data
- * @code_dma_base:	256B-aligned Physical FB Address where code is located
- * @total_code_size:	total size of the code part in the ucode
- * @code_size_to_load:	size of the code part to load in PMU IMEM.
- * @code_entry_point:	entry point in the code.
- * @data_dma_base:	Physical FB address where data part of ucode is located
- * @data_size:		Total size of the data portion.
- * @overlay_dma_base:	Physical Fb address for resident code present in ucode
- * @argc:		Total number of args
- * @argv:		offset where args are copied into PMU's DMEM.
- *
- * Structure used by the PMU bootloader to load the rest of the code
- */
-struct acr_r352_pmu_bl_desc {
-	u32 dma_idx;
-	u32 code_dma_base;
-	u32 code_size_total;
-	u32 code_size_to_load;
-	u32 code_entry_point;
-	u32 data_dma_base;
-	u32 data_size;
-	u32 overlay_dma_base;
-	u32 argc;
-	u32 argv;
-	u16 code_dma_base1;
-	u16 data_dma_base1;
-	u16 overlay_dma_base1;
-};
-
-/**
- * acr_r352_generate_pmu_bl_desc() - populate a DMEM BL descriptor for PMU LS image
- *
- */
-static void
-acr_r352_generate_pmu_bl_desc(const struct nvkm_acr *acr,
-			      const struct ls_ucode_img *img, u64 wpr_addr,
-			      void *_desc)
-{
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	const struct nvkm_pmu *pmu = acr->subdev->device->pmu;
-	struct acr_r352_pmu_bl_desc *desc = _desc;
-	u64 base;
-	u64 addr_code;
-	u64 addr_data;
-	u32 addr_args;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = (base + pdesc->app_resident_code_offset) >> 8;
-	addr_data = (base + pdesc->app_resident_data_offset) >> 8;
-	addr_args = pmu->falcon->data.limit;
-	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
-
-	desc->dma_idx = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = lower_32_bits(addr_code);
-	desc->code_dma_base1 = upper_32_bits(addr_code);
-	desc->code_size_total = pdesc->app_size;
-	desc->code_size_to_load = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = lower_32_bits(addr_data);
-	desc->data_dma_base1 = upper_32_bits(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-	desc->overlay_dma_base = lower_32_bits(addr_code);
-	desc->overlay_dma_base1 = upper_32_bits(addr_code);
-	desc->argc = 1;
-	desc->argv = addr_args;
-}
-
-static const struct acr_r352_lsf_func
-acr_r352_ls_pmu_func_0 = {
-	.generate_bl_desc = acr_r352_generate_pmu_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r352_pmu_bl_desc),
-};
-
-static const struct acr_r352_ls_func
-acr_r352_ls_pmu_func = {
-	.load = acr_ls_ucode_load_pmu,
-	.post_run = acr_ls_pmu_post_run,
-	.version_max = 0,
-	.version = {
-		&acr_r352_ls_pmu_func_0,
-	}
-};
-
-const struct acr_r352_func
-acr_r352_func = {
-	.fixup_hs_desc = acr_r352_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r352_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r352_flcn_bl_desc),
-	.ls_ucode_img_load = acr_r352_ls_ucode_img_load,
-	.ls_fill_headers = acr_r352_ls_fill_headers,
-	.ls_write_wpr = acr_r352_ls_write_wpr,
-	.ls_func = {
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r352_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r352_ls_gpccs_func,
-		[NVKM_SECBOOT_FALCON_PMU] = &acr_r352_ls_pmu_func,
-	},
-};
-
-static const struct nvkm_acr_func
-acr_r352_base_func = {
-	.dtor = acr_r352_dtor,
-	.fini = acr_r352_fini,
-	.load = acr_r352_load,
-	.reset = acr_r352_reset,
-};
-
-struct nvkm_acr *
-acr_r352_new_(const struct acr_r352_func *func,
-	      enum nvkm_secboot_falcon boot_falcon,
-	      unsigned long managed_falcons)
-{
-	struct acr_r352 *acr;
-	int i;
-
-	/* Check that all requested falcons are supported */
-	for_each_set_bit(i, &managed_falcons, NVKM_SECBOOT_FALCON_END) {
-		if (!func->ls_func[i])
-			return ERR_PTR(-ENOTSUPP);
-	}
-
-	acr = kzalloc(sizeof(*acr), GFP_KERNEL);
-	if (!acr)
-		return ERR_PTR(-ENOMEM);
-
-	acr->base.boot_falcon = boot_falcon;
-	acr->base.managed_falcons = managed_falcons;
-	acr->base.func = &acr_r352_base_func;
-	acr->func = func;
-
-	return &acr->base;
-}
-
-struct nvkm_acr *
-acr_r352_new(unsigned long managed_falcons)
-{
-	return acr_r352_new_(&acr_r352_func, NVKM_SECBOOT_FALCON_PMU,
-			     managed_falcons);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.h
deleted file mode 100644
index e516cab849dd..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.h
+++ /dev/null
@@ -1,167 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-#ifndef __NVKM_SECBOOT_ACR_R352_H__
-#define __NVKM_SECBOOT_ACR_R352_H__
-
-#include "acr.h"
-#include "ls_ucode.h"
-#include "hs_ucode.h"
-
-struct ls_ucode_img;
-
-#define ACR_R352_MAX_APPS 8
-
-#define LSF_FLAG_LOAD_CODE_AT_0		1
-#define LSF_FLAG_DMACTL_REQ_CTX		4
-#define LSF_FLAG_FORCE_PRIV_LOAD	8
-
-static inline u32
-hsf_load_header_app_off(const struct hsf_load_header *hdr, u32 app)
-{
-	return hdr->apps[app];
-}
-
-static inline u32
-hsf_load_header_app_size(const struct hsf_load_header *hdr, u32 app)
-{
-	return hdr->apps[hdr->num_apps + app];
-}
-
-/**
- * struct acr_r352_lsf_func - manages a specific LS firmware version
- *
- * @generate_bl_desc: function called on a block of bl_desc_size to generate the
- *		      proper bootloader descriptor for this LS firmware
- * @bl_desc_size: size of the bootloader descriptor
- * @lhdr_flags: LS flags
- */
-struct acr_r352_lsf_func {
-	void (*generate_bl_desc)(const struct nvkm_acr *,
-				 const struct ls_ucode_img *, u64, void *);
-	u32 bl_desc_size;
-	u32 lhdr_flags;
-};
-
-/**
- * struct acr_r352_ls_func - manages a single LS falcon
- *
- * @load: load the external firmware into a ls_ucode_img
- * @post_run: hook called right after the ACR is executed
- */
-struct acr_r352_ls_func {
-	int (*load)(const struct nvkm_secboot *, int maxver,
-		    struct ls_ucode_img *);
-	int (*post_run)(const struct nvkm_acr *, const struct nvkm_secboot *);
-	int version_max;
-	const struct acr_r352_lsf_func *version[];
-};
-
-struct acr_r352;
-
-/**
- * struct acr_r352_func - manages nuances between ACR versions
- *
- * @generate_hs_bl_desc: function called on a block of bl_desc_size to generate
- *			 the proper HS bootloader descriptor
- * @hs_bl_desc_size: size of the HS bootloader descriptor
- */
-struct acr_r352_func {
-	void (*generate_hs_bl_desc)(const struct hsf_load_header *, void *,
-				    u64);
-	void (*fixup_hs_desc)(struct acr_r352 *, struct nvkm_secboot *, void *);
-	u32 hs_bl_desc_size;
-	bool shadow_blob;
-
-	struct ls_ucode_img *(*ls_ucode_img_load)(const struct acr_r352 *,
-						  const struct nvkm_secboot *,
-						  enum nvkm_secboot_falcon);
-	int (*ls_fill_headers)(struct acr_r352 *, struct list_head *);
-	int (*ls_write_wpr)(struct acr_r352 *, struct list_head *,
-			    struct nvkm_gpuobj *, u64);
-
-	const struct acr_r352_ls_func *ls_func[NVKM_SECBOOT_FALCON_END];
-};
-
-/**
- * struct acr_r352 - ACR data for driver release 352 (and beyond)
- */
-struct acr_r352 {
-	struct nvkm_acr base;
-	const struct acr_r352_func *func;
-
-	/*
-	 * HS FW - lock WPR region (dGPU only) and load LS FWs
-	 * on Tegra the HS FW copies the LS blob into the fixed WPR instead
-	 */
-	struct nvkm_gpuobj *load_blob;
-	struct {
-		struct hsf_load_header load_bl_header;
-		u32 __load_apps[ACR_R352_MAX_APPS * 2];
-	};
-
-	/* HS FW - unlock WPR region (dGPU only) */
-	struct nvkm_gpuobj *unload_blob;
-	struct {
-		struct hsf_load_header unload_bl_header;
-		u32 __unload_apps[ACR_R352_MAX_APPS * 2];
-	};
-
-	/* HS bootloader */
-	void *hsbl_blob;
-
-	/* HS bootloader for unload blob, if using a different falcon */
-	void *hsbl_unload_blob;
-
-	/* LS FWs, to be loaded by the HS ACR */
-	struct nvkm_gpuobj *ls_blob;
-
-	/* Firmware already loaded? */
-	bool firmware_ok;
-
-	/* Falcons to lazy-bootstrap */
-	u32 lazy_bootstrap;
-
-	/* To keep track of the state of all managed falcons */
-	enum {
-		/* In non-secure state, no firmware loaded, no privileges*/
-		NON_SECURE = 0,
-		/* In low-secure mode and ready to be started */
-		RESET,
-		/* In low-secure mode and running */
-		RUNNING,
-	} falcon_state[NVKM_SECBOOT_FALCON_END];
-};
-#define acr_r352(acr) container_of(acr, struct acr_r352, base)
-
-struct nvkm_acr *acr_r352_new_(const struct acr_r352_func *,
-			       enum nvkm_secboot_falcon, unsigned long);
-
-struct ls_ucode_img *acr_r352_ls_ucode_img_load(const struct acr_r352 *,
-						const struct nvkm_secboot *,
-						enum nvkm_secboot_falcon);
-int acr_r352_ls_fill_headers(struct acr_r352 *, struct list_head *);
-int acr_r352_ls_write_wpr(struct acr_r352 *, struct list_head *,
-			  struct nvkm_gpuobj *, u64);
-
-void acr_r352_fixup_hs_desc(struct acr_r352 *, struct nvkm_secboot *, void *);
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c
deleted file mode 100644
index f6b2d20d7fc3..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.c
+++ /dev/null
@@ -1,229 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr_r361.h"
-
-#include <engine/falcon.h>
-#include <core/msgqueue.h>
-#include <subdev/pmu.h>
-#include <engine/sec2.h>
-
-static void
-acr_r361_generate_flcn_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *img, u64 wpr_addr,
-			       void *_desc)
-{
-	struct acr_r361_flcn_bl_desc *desc = _desc;
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	u64 base, addr_code, addr_data;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = base + pdesc->app_resident_code_offset;
-	addr_data = base + pdesc->app_resident_data_offset;
-
-	desc->ctx_dma = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->non_sec_code_off = pdesc->app_resident_code_offset;
-	desc->non_sec_code_size = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-}
-
-void
-acr_r361_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
-			    u64 offset)
-{
-	struct acr_r361_flcn_bl_desc *bl_desc = _bl_desc;
-
-	bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
-	bl_desc->code_dma_base = u64_to_flcn64(offset);
-	bl_desc->non_sec_code_off = hdr->non_sec_code_off;
-	bl_desc->non_sec_code_size = hdr->non_sec_code_size;
-	bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
-	bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
-	bl_desc->code_entry_point = 0;
-	bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
-	bl_desc->data_size = hdr->data_size;
-}
-
-static const struct acr_r352_lsf_func
-acr_r361_ls_fecs_func_0 = {
-	.generate_bl_desc = acr_r361_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r361_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r361_ls_fecs_func = {
-	.load = acr_ls_ucode_load_fecs,
-	.version_max = 0,
-	.version = {
-		&acr_r361_ls_fecs_func_0,
-	}
-};
-
-static const struct acr_r352_lsf_func
-acr_r361_ls_gpccs_func_0 = {
-	.generate_bl_desc = acr_r361_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r361_flcn_bl_desc),
-	/* GPCCS will be loaded using PRI */
-	.lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
-};
-
-const struct acr_r352_ls_func
-acr_r361_ls_gpccs_func = {
-	.load = acr_ls_ucode_load_gpccs,
-	.version_max = 0,
-	.version = {
-		&acr_r361_ls_gpccs_func_0,
-	}
-};
-
-struct acr_r361_pmu_bl_desc {
-	u32 reserved;
-	u32 dma_idx;
-	struct flcn_u64 code_dma_base;
-	u32 total_code_size;
-	u32 code_size_to_load;
-	u32 code_entry_point;
-	struct flcn_u64 data_dma_base;
-	u32 data_size;
-	struct flcn_u64 overlay_dma_base;
-	u32 argc;
-	u32 argv;
-};
-
-static void
-acr_r361_generate_pmu_bl_desc(const struct nvkm_acr *acr,
-			      const struct ls_ucode_img *img, u64 wpr_addr,
-			      void *_desc)
-{
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	const struct nvkm_pmu *pmu = acr->subdev->device->pmu;
-	struct acr_r361_pmu_bl_desc *desc = _desc;
-	u64 base, addr_code, addr_data;
-	u32 addr_args;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = base + pdesc->app_resident_code_offset;
-	addr_data = base + pdesc->app_resident_data_offset;
-	addr_args = pmu->falcon->data.limit;
-	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
-
-	desc->dma_idx = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->total_code_size = pdesc->app_size;
-	desc->code_size_to_load = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-	desc->overlay_dma_base = u64_to_flcn64(addr_code);
-	desc->argc = 1;
-	desc->argv = addr_args;
-}
-
-static const struct acr_r352_lsf_func
-acr_r361_ls_pmu_func_0 = {
-	.generate_bl_desc = acr_r361_generate_pmu_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r361_pmu_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r361_ls_pmu_func = {
-	.load = acr_ls_ucode_load_pmu,
-	.post_run = acr_ls_pmu_post_run,
-	.version_max = 0,
-	.version = {
-		&acr_r361_ls_pmu_func_0,
-	}
-};
-
-static void
-acr_r361_generate_sec2_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *img, u64 wpr_addr,
-			       void *_desc)
-{
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	const struct nvkm_sec2 *sec = acr->subdev->device->sec2;
-	struct acr_r361_pmu_bl_desc *desc = _desc;
-	u64 base, addr_code, addr_data;
-	u32 addr_args;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	/* For some reason we should not add app_resident_code_offset here */
-	addr_code = base;
-	addr_data = base + pdesc->app_resident_data_offset;
-	addr_args = sec->falcon->data.limit;
-	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
-
-	desc->dma_idx = FALCON_SEC2_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->total_code_size = pdesc->app_size;
-	desc->code_size_to_load = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-	desc->overlay_dma_base = u64_to_flcn64(addr_code);
-	desc->argc = 1;
-	/* args are stored at the beginning of EMEM */
-	desc->argv = 0x01000000;
-}
-
-const struct acr_r352_lsf_func
-acr_r361_ls_sec2_func_0 = {
-	.generate_bl_desc = acr_r361_generate_sec2_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r361_pmu_bl_desc),
-};
-
-static const struct acr_r352_ls_func
-acr_r361_ls_sec2_func = {
-	.load = acr_ls_ucode_load_sec2,
-	.post_run = acr_ls_sec2_post_run,
-	.version_max = 0,
-	.version = {
-		&acr_r361_ls_sec2_func_0,
-	}
-};
-
-
-const struct acr_r352_func
-acr_r361_func = {
-	.fixup_hs_desc = acr_r352_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r361_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r361_flcn_bl_desc),
-	.ls_ucode_img_load = acr_r352_ls_ucode_img_load,
-	.ls_fill_headers = acr_r352_ls_fill_headers,
-	.ls_write_wpr = acr_r352_ls_write_wpr,
-	.ls_func = {
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r361_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r361_ls_gpccs_func,
-		[NVKM_SECBOOT_FALCON_PMU] = &acr_r361_ls_pmu_func,
-		[NVKM_SECBOOT_FALCON_SEC2] = &acr_r361_ls_sec2_func,
-	},
-};
-
-struct nvkm_acr *
-acr_r361_new(unsigned long managed_falcons)
-{
-	return acr_r352_new_(&acr_r361_func, NVKM_SECBOOT_FALCON_PMU,
-			     managed_falcons);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.h
deleted file mode 100644
index 38dec93779c8..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r361.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef __NVKM_SECBOOT_ACR_R361_H__
-#define __NVKM_SECBOOT_ACR_R361_H__
-
-#include "acr_r352.h"
-
-/**
- * struct acr_r361_flcn_bl_desc - DMEM bootloader descriptor
- * @signature:		16B signature for secure code. 0s if no secure code
- * @ctx_dma:		DMA context to be used by BL while loading code/data
- * @code_dma_base:	256B-aligned Physical FB Address where code is located
- *			(falcon's $xcbase register)
- * @non_sec_code_off:	offset from code_dma_base where the non-secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @non_sec_code_size:	the size of the nonSecure code part.
- * @sec_code_off:	offset from code_dma_base where the secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @sec_code_size:	offset from code_dma_base where the secure code is
- *                      located. The offset must be multiple of 256 to help perf
- * @code_entry_point:	code entry point which will be invoked by BL after
- *                      code is loaded.
- * @data_dma_base:	256B aligned Physical FB Address where data is located.
- *			(falcon's $xdbase register)
- * @data_size:		size of data block. Should be multiple of 256B
- *
- * Structure used by the bootloader to load the rest of the code. This has
- * to be filled by host and copied into DMEM at offset provided in the
- * hsflcn_bl_desc.bl_desc_dmem_load_off.
- */
-struct acr_r361_flcn_bl_desc {
-	u32 reserved[4];
-	u32 signature[4];
-	u32 ctx_dma;
-	struct flcn_u64 code_dma_base;
-	u32 non_sec_code_off;
-	u32 non_sec_code_size;
-	u32 sec_code_off;
-	u32 sec_code_size;
-	u32 code_entry_point;
-	struct flcn_u64 data_dma_base;
-	u32 data_size;
-};
-
-void acr_r361_generate_hs_bl_desc(const struct hsf_load_header *, void *, u64);
-
-extern const struct acr_r352_ls_func acr_r361_ls_fecs_func;
-extern const struct acr_r352_ls_func acr_r361_ls_gpccs_func;
-extern const struct acr_r352_ls_func acr_r361_ls_pmu_func;
-extern const struct acr_r352_lsf_func acr_r361_ls_sec2_func_0;
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r364.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r364.c
deleted file mode 100644
index 30cf04109991..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r364.c
+++ /dev/null
@@ -1,117 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr_r361.h"
-
-#include <core/gpuobj.h>
-
-/*
- * r364 ACR: hsflcn_desc structure has changed to introduce the shadow_mem
- * parameter.
- */
-
-struct acr_r364_hsflcn_desc {
-	union {
-		u8 reserved_dmem[0x200];
-		u32 signatures[4];
-	} ucode_reserved_space;
-	u32 wpr_region_id;
-	u32 wpr_offset;
-	u32 mmu_memory_range;
-	struct {
-		u32 no_regions;
-		struct {
-			u32 start_addr;
-			u32 end_addr;
-			u32 region_id;
-			u32 read_mask;
-			u32 write_mask;
-			u32 client_mask;
-			u32 shadow_mem_start_addr;
-		} region_props[2];
-	} regions;
-	u32 ucode_blob_size;
-	u64 ucode_blob_base __aligned(8);
-	struct {
-		u32 vpr_enabled;
-		u32 vpr_start;
-		u32 vpr_end;
-		u32 hdcp_policies;
-	} vpr_desc;
-};
-
-static void
-acr_r364_fixup_hs_desc(struct acr_r352 *acr, struct nvkm_secboot *sb,
-		       void *_desc)
-{
-	struct acr_r364_hsflcn_desc *desc = _desc;
-	struct nvkm_gpuobj *ls_blob = acr->ls_blob;
-
-	/* WPR region information if WPR is not fixed */
-	if (sb->wpr_size == 0) {
-		u64 wpr_start = ls_blob->addr;
-		u64 wpr_end = ls_blob->addr + ls_blob->size;
-
-		if (acr->func->shadow_blob)
-			wpr_start += ls_blob->size / 2;
-
-		desc->wpr_region_id = 1;
-		desc->regions.no_regions = 2;
-		desc->regions.region_props[0].start_addr = wpr_start >> 8;
-		desc->regions.region_props[0].end_addr = wpr_end >> 8;
-		desc->regions.region_props[0].region_id = 1;
-		desc->regions.region_props[0].read_mask = 0xf;
-		desc->regions.region_props[0].write_mask = 0xc;
-		desc->regions.region_props[0].client_mask = 0x2;
-		if (acr->func->shadow_blob)
-			desc->regions.region_props[0].shadow_mem_start_addr =
-							     ls_blob->addr >> 8;
-		else
-			desc->regions.region_props[0].shadow_mem_start_addr = 0;
-	} else {
-		desc->ucode_blob_base = ls_blob->addr;
-		desc->ucode_blob_size = ls_blob->size;
-	}
-}
-
-const struct acr_r352_func
-acr_r364_func = {
-	.fixup_hs_desc = acr_r364_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r361_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r361_flcn_bl_desc),
-	.ls_ucode_img_load = acr_r352_ls_ucode_img_load,
-	.ls_fill_headers = acr_r352_ls_fill_headers,
-	.ls_write_wpr = acr_r352_ls_write_wpr,
-	.ls_func = {
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r361_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r361_ls_gpccs_func,
-		[NVKM_SECBOOT_FALCON_PMU] = &acr_r361_ls_pmu_func,
-	},
-};
-
-
-struct nvkm_acr *
-acr_r364_new(unsigned long managed_falcons)
-{
-	return acr_r352_new_(&acr_r364_func, NVKM_SECBOOT_FALCON_PMU,
-			     managed_falcons);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
deleted file mode 100644
index 472ced29da7e..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
+++ /dev/null
@@ -1,418 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr_r367.h"
-#include "acr_r361.h"
-#include "acr_r370.h"
-
-#include <core/gpuobj.h>
-
-/*
- * r367 ACR: new LS signature format requires a rewrite of LS firmware and
- * blob creation functions. Also the hsflcn_desc layout has changed slightly.
- */
-
-#define LSF_LSB_DEPMAP_SIZE 11
-
-/**
- * struct acr_r367_lsf_lsb_header - LS firmware header
- *
- * See also struct acr_r352_lsf_lsb_header for documentation.
- */
-struct acr_r367_lsf_lsb_header {
-	/**
-	 * LS falcon signatures
-	 * @prd_keys:		signature to use in production mode
-	 * @dgb_keys:		signature to use in debug mode
-	 * @b_prd_present:	whether the production key is present
-	 * @b_dgb_present:	whether the debug key is present
-	 * @falcon_id:		ID of the falcon the ucode applies to
-	 */
-	struct {
-		u8 prd_keys[2][16];
-		u8 dbg_keys[2][16];
-		u32 b_prd_present;
-		u32 b_dbg_present;
-		u32 falcon_id;
-		u32 supports_versioning;
-		u32 version;
-		u32 depmap_count;
-		u8 depmap[LSF_LSB_DEPMAP_SIZE * 2 * 4];
-		u8 kdf[16];
-	} signature;
-	u32 ucode_off;
-	u32 ucode_size;
-	u32 data_size;
-	u32 bl_code_size;
-	u32 bl_imem_off;
-	u32 bl_data_off;
-	u32 bl_data_size;
-	u32 app_code_off;
-	u32 app_code_size;
-	u32 app_data_off;
-	u32 app_data_size;
-	u32 flags;
-};
-
-/**
- * struct acr_r367_lsf_wpr_header - LS blob WPR Header
- *
- * See also struct acr_r352_lsf_wpr_header for documentation.
- */
-struct acr_r367_lsf_wpr_header {
-	u32 falcon_id;
-	u32 lsb_offset;
-	u32 bootstrap_owner;
-	u32 lazy_bootstrap;
-	u32 bin_version;
-	u32 status;
-#define LSF_IMAGE_STATUS_NONE				0
-#define LSF_IMAGE_STATUS_COPY				1
-#define LSF_IMAGE_STATUS_VALIDATION_CODE_FAILED		2
-#define LSF_IMAGE_STATUS_VALIDATION_DATA_FAILED		3
-#define LSF_IMAGE_STATUS_VALIDATION_DONE		4
-#define LSF_IMAGE_STATUS_VALIDATION_SKIPPED		5
-#define LSF_IMAGE_STATUS_BOOTSTRAP_READY		6
-#define LSF_IMAGE_STATUS_REVOCATION_CHECK_FAILED		7
-};
-
-/**
- * struct ls_ucode_img_r367 - ucode image augmented with r367 headers
- */
-struct ls_ucode_img_r367 {
-	struct ls_ucode_img base;
-
-	const struct acr_r352_lsf_func *func;
-
-	struct acr_r367_lsf_wpr_header wpr_header;
-	struct acr_r367_lsf_lsb_header lsb_header;
-};
-#define ls_ucode_img_r367(i) container_of(i, struct ls_ucode_img_r367, base)
-
-struct ls_ucode_img *
-acr_r367_ls_ucode_img_load(const struct acr_r352 *acr,
-			   const struct nvkm_secboot *sb,
-			   enum nvkm_secboot_falcon falcon_id)
-{
-	const struct nvkm_subdev *subdev = acr->base.subdev;
-	const struct acr_r352_ls_func *func = acr->func->ls_func[falcon_id];
-	struct ls_ucode_img_r367 *img;
-	int ret;
-
-	img = kzalloc(sizeof(*img), GFP_KERNEL);
-	if (!img)
-		return ERR_PTR(-ENOMEM);
-
-	img->base.falcon_id = falcon_id;
-
-	ret = func->load(sb, func->version_max, &img->base);
-	if (ret < 0) {
-		kfree(img->base.ucode_data);
-		kfree(img->base.sig);
-		kfree(img);
-		return ERR_PTR(ret);
-	}
-
-	img->func = func->version[ret];
-
-	/* Check that the signature size matches our expectations... */
-	if (img->base.sig_size != sizeof(img->lsb_header.signature)) {
-		nvkm_error(subdev, "invalid signature size for %s falcon!\n",
-			   nvkm_secboot_falcon_name[falcon_id]);
-		return ERR_PTR(-EINVAL);
-	}
-
-	/* Copy signature to the right place */
-	memcpy(&img->lsb_header.signature, img->base.sig, img->base.sig_size);
-
-	/* not needed? the signature should already have the right value */
-	img->lsb_header.signature.falcon_id = falcon_id;
-
-	return &img->base;
-}
-
-#define LSF_LSB_HEADER_ALIGN 256
-#define LSF_BL_DATA_ALIGN 256
-#define LSF_BL_DATA_SIZE_ALIGN 256
-#define LSF_BL_CODE_SIZE_ALIGN 256
-#define LSF_UCODE_DATA_ALIGN 4096
-
-static u32
-acr_r367_ls_img_fill_headers(struct acr_r352 *acr,
-			     struct ls_ucode_img_r367 *img, u32 offset)
-{
-	struct ls_ucode_img *_img = &img->base;
-	struct acr_r367_lsf_wpr_header *whdr = &img->wpr_header;
-	struct acr_r367_lsf_lsb_header *lhdr = &img->lsb_header;
-	struct ls_ucode_img_desc *desc = &_img->ucode_desc;
-	const struct acr_r352_lsf_func *func = img->func;
-
-	/* Fill WPR header */
-	whdr->falcon_id = _img->falcon_id;
-	whdr->bootstrap_owner = acr->base.boot_falcon;
-	whdr->bin_version = lhdr->signature.version;
-	whdr->status = LSF_IMAGE_STATUS_COPY;
-
-	/* Skip bootstrapping falcons started by someone else than ACR */
-	if (acr->lazy_bootstrap & BIT(_img->falcon_id))
-		whdr->lazy_bootstrap = 1;
-
-	/* Align, save off, and include an LSB header size */
-	offset = ALIGN(offset, LSF_LSB_HEADER_ALIGN);
-	whdr->lsb_offset = offset;
-	offset += sizeof(*lhdr);
-
-	/*
-	 * Align, save off, and include the original (static) ucode
-	 * image size
-	 */
-	offset = ALIGN(offset, LSF_UCODE_DATA_ALIGN);
-	_img->ucode_off = lhdr->ucode_off = offset;
-	offset += _img->ucode_size;
-
-	/*
-	 * For falcons that use a boot loader (BL), we append a loader
-	 * desc structure on the end of the ucode image and consider
-	 * this the boot loader data. The host will then copy the loader
-	 * desc args to this space within the WPR region (before locking
-	 * down) and the HS bin will then copy them to DMEM 0 for the
-	 * loader.
-	 */
-	lhdr->bl_code_size = ALIGN(desc->bootloader_size,
-				   LSF_BL_CODE_SIZE_ALIGN);
-	lhdr->ucode_size = ALIGN(desc->app_resident_data_offset,
-				 LSF_BL_CODE_SIZE_ALIGN) + lhdr->bl_code_size;
-	lhdr->data_size = ALIGN(desc->app_size, LSF_BL_CODE_SIZE_ALIGN) +
-				lhdr->bl_code_size - lhdr->ucode_size;
-	/*
-	 * Though the BL is located at 0th offset of the image, the VA
-	 * is different to make sure that it doesn't collide the actual
-	 * OS VA range
-	 */
-	lhdr->bl_imem_off = desc->bootloader_imem_offset;
-	lhdr->app_code_off = desc->app_start_offset +
-			     desc->app_resident_code_offset;
-	lhdr->app_code_size = desc->app_resident_code_size;
-	lhdr->app_data_off = desc->app_start_offset +
-			     desc->app_resident_data_offset;
-	lhdr->app_data_size = desc->app_resident_data_size;
-
-	lhdr->flags = func->lhdr_flags;
-	if (_img->falcon_id == acr->base.boot_falcon)
-		lhdr->flags |= LSF_FLAG_DMACTL_REQ_CTX;
-
-	/* Align and save off BL descriptor size */
-	lhdr->bl_data_size = ALIGN(func->bl_desc_size, LSF_BL_DATA_SIZE_ALIGN);
-
-	/*
-	 * Align, save off, and include the additional BL data
-	 */
-	offset = ALIGN(offset, LSF_BL_DATA_ALIGN);
-	lhdr->bl_data_off = offset;
-	offset += lhdr->bl_data_size;
-
-	return offset;
-}
-
-int
-acr_r367_ls_fill_headers(struct acr_r352 *acr, struct list_head *imgs)
-{
-	struct ls_ucode_img_r367 *img;
-	struct list_head *l;
-	u32 count = 0;
-	u32 offset;
-
-	/* Count the number of images to manage */
-	list_for_each(l, imgs)
-		count++;
-
-	/*
-	 * Start with an array of WPR headers at the base of the WPR.
-	 * The expectation here is that the secure falcon will do a single DMA
-	 * read of this array and cache it internally so it's ok to pack these.
-	 * Also, we add 1 to the falcon count to indicate the end of the array.
-	 */
-	offset = sizeof(img->wpr_header) * (count + 1);
-
-	/*
-	 * Walk the managed falcons, accounting for the LSB structs
-	 * as well as the ucode images.
-	 */
-	list_for_each_entry(img, imgs, base.node) {
-		offset = acr_r367_ls_img_fill_headers(acr, img, offset);
-	}
-
-	return offset;
-}
-
-int
-acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
-		      struct nvkm_gpuobj *wpr_blob, u64 wpr_addr)
-{
-	struct ls_ucode_img *_img;
-	u32 pos = 0;
-	u32 max_desc_size = 0;
-	u8 *gdesc;
-
-	list_for_each_entry(_img, imgs, node) {
-		struct ls_ucode_img_r367 *img = ls_ucode_img_r367(_img);
-		const struct acr_r352_lsf_func *ls_func = img->func;
-
-		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
-	}
-
-	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
-	if (!gdesc)
-		return -ENOMEM;
-
-	nvkm_kmap(wpr_blob);
-
-	list_for_each_entry(_img, imgs, node) {
-		struct ls_ucode_img_r367 *img = ls_ucode_img_r367(_img);
-		const struct acr_r352_lsf_func *ls_func = img->func;
-
-		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
-				      sizeof(img->wpr_header));
-
-		nvkm_gpuobj_memcpy_to(wpr_blob, img->wpr_header.lsb_offset,
-				     &img->lsb_header, sizeof(img->lsb_header));
-
-		/* Generate and write BL descriptor */
-		memset(gdesc, 0, ls_func->bl_desc_size);
-		ls_func->generate_bl_desc(&acr->base, _img, wpr_addr, gdesc);
-
-		nvkm_gpuobj_memcpy_to(wpr_blob, img->lsb_header.bl_data_off,
-				      gdesc, ls_func->bl_desc_size);
-
-		/* Copy ucode */
-		nvkm_gpuobj_memcpy_to(wpr_blob, img->lsb_header.ucode_off,
-				      _img->ucode_data, _img->ucode_size);
-
-		pos += sizeof(img->wpr_header);
-	}
-
-	nvkm_wo32(wpr_blob, pos, NVKM_SECBOOT_FALCON_INVALID);
-
-	nvkm_done(wpr_blob);
-
-	kfree(gdesc);
-
-	return 0;
-}
-
-struct acr_r367_hsflcn_desc {
-	u8 reserved_dmem[0x200];
-	u32 signatures[4];
-	u32 wpr_region_id;
-	u32 wpr_offset;
-	u32 mmu_memory_range;
-#define FLCN_ACR_MAX_REGIONS 2
-	struct {
-		u32 no_regions;
-		struct {
-			u32 start_addr;
-			u32 end_addr;
-			u32 region_id;
-			u32 read_mask;
-			u32 write_mask;
-			u32 client_mask;
-			u32 shadow_mem_start_addr;
-		} region_props[FLCN_ACR_MAX_REGIONS];
-	} regions;
-	u32 ucode_blob_size;
-	u64 ucode_blob_base __aligned(8);
-	struct {
-		u32 vpr_enabled;
-		u32 vpr_start;
-		u32 vpr_end;
-		u32 hdcp_policies;
-	} vpr_desc;
-};
-
-void
-acr_r367_fixup_hs_desc(struct acr_r352 *acr, struct nvkm_secboot *sb,
-		       void *_desc)
-{
-	struct acr_r367_hsflcn_desc *desc = _desc;
-	struct nvkm_gpuobj *ls_blob = acr->ls_blob;
-
-	/* WPR region information if WPR is not fixed */
-	if (sb->wpr_size == 0) {
-		u64 wpr_start = ls_blob->addr;
-		u64 wpr_end = ls_blob->addr + ls_blob->size;
-
-		if (acr->func->shadow_blob)
-			wpr_start += ls_blob->size / 2;
-
-		desc->wpr_region_id = 1;
-		desc->regions.no_regions = 2;
-		desc->regions.region_props[0].start_addr = wpr_start >> 8;
-		desc->regions.region_props[0].end_addr = wpr_end >> 8;
-		desc->regions.region_props[0].region_id = 1;
-		desc->regions.region_props[0].read_mask = 0xf;
-		desc->regions.region_props[0].write_mask = 0xc;
-		desc->regions.region_props[0].client_mask = 0x2;
-		if (acr->func->shadow_blob)
-			desc->regions.region_props[0].shadow_mem_start_addr =
-							     ls_blob->addr >> 8;
-		else
-			desc->regions.region_props[0].shadow_mem_start_addr = 0;
-	} else {
-		desc->ucode_blob_base = ls_blob->addr;
-		desc->ucode_blob_size = ls_blob->size;
-	}
-}
-
-static const struct acr_r352_ls_func
-acr_r367_ls_sec2_func = {
-	.load = acr_ls_ucode_load_sec2,
-	.post_run = acr_ls_sec2_post_run,
-	.version_max = 1,
-	.version = {
-		&acr_r361_ls_sec2_func_0,
-		&acr_r370_ls_sec2_func_0,
-	}
-};
-
-const struct acr_r352_func
-acr_r367_func = {
-	.fixup_hs_desc = acr_r367_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r361_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r361_flcn_bl_desc),
-	.shadow_blob = true,
-	.ls_ucode_img_load = acr_r367_ls_ucode_img_load,
-	.ls_fill_headers = acr_r367_ls_fill_headers,
-	.ls_write_wpr = acr_r367_ls_write_wpr,
-	.ls_func = {
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r361_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r361_ls_gpccs_func,
-		[NVKM_SECBOOT_FALCON_PMU] = &acr_r361_ls_pmu_func,
-		[NVKM_SECBOOT_FALCON_SEC2] = &acr_r367_ls_sec2_func,
-	},
-};
-
-struct nvkm_acr *
-acr_r367_new(enum nvkm_secboot_falcon boot_falcon,
-	     unsigned long managed_falcons)
-{
-	return acr_r352_new_(&acr_r367_func, boot_falcon, managed_falcons);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c
deleted file mode 100644
index e821d0fd6217..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.c
+++ /dev/null
@@ -1,168 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr_r370.h"
-#include "acr_r367.h"
-
-#include <core/msgqueue.h>
-#include <engine/falcon.h>
-#include <engine/sec2.h>
-
-static void
-acr_r370_generate_flcn_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *img, u64 wpr_addr,
-			       void *_desc)
-{
-	struct acr_r370_flcn_bl_desc *desc = _desc;
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	u64 base, addr_code, addr_data;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = base + pdesc->app_resident_code_offset;
-	addr_data = base + pdesc->app_resident_data_offset;
-
-	desc->ctx_dma = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->non_sec_code_off = pdesc->app_resident_code_offset;
-	desc->non_sec_code_size = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-}
-
-static const struct acr_r352_lsf_func
-acr_r370_ls_fecs_func_0 = {
-	.generate_bl_desc = acr_r370_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r370_ls_fecs_func = {
-	.load = acr_ls_ucode_load_fecs,
-	.version_max = 0,
-	.version = {
-		&acr_r370_ls_fecs_func_0,
-	}
-};
-
-static const struct acr_r352_lsf_func
-acr_r370_ls_gpccs_func_0 = {
-	.generate_bl_desc = acr_r370_generate_flcn_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
-	/* GPCCS will be loaded using PRI */
-	.lhdr_flags = LSF_FLAG_FORCE_PRIV_LOAD,
-};
-
-const struct acr_r352_ls_func
-acr_r370_ls_gpccs_func = {
-	.load = acr_ls_ucode_load_gpccs,
-	.version_max = 0,
-	.version = {
-		&acr_r370_ls_gpccs_func_0,
-	}
-};
-
-static void
-acr_r370_generate_sec2_bl_desc(const struct nvkm_acr *acr,
-			       const struct ls_ucode_img *img, u64 wpr_addr,
-			       void *_desc)
-{
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	const struct nvkm_sec2 *sec = acr->subdev->device->sec2;
-	struct acr_r370_flcn_bl_desc *desc = _desc;
-	u64 base, addr_code, addr_data;
-	u32 addr_args;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	/* For some reason we should not add app_resident_code_offset here */
-	addr_code = base;
-	addr_data = base + pdesc->app_resident_data_offset;
-	addr_args = sec->falcon->data.limit;
-	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
-
-	desc->ctx_dma = FALCON_SEC2_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->non_sec_code_off = pdesc->app_resident_code_offset;
-	desc->non_sec_code_size = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-	desc->argc = 1;
-	/* args are stored at the beginning of EMEM */
-	desc->argv = 0x01000000;
-}
-
-const struct acr_r352_lsf_func
-acr_r370_ls_sec2_func_0 = {
-	.generate_bl_desc = acr_r370_generate_sec2_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r370_ls_sec2_func = {
-	.load = acr_ls_ucode_load_sec2,
-	.post_run = acr_ls_sec2_post_run,
-	.version_max = 0,
-	.version = {
-		&acr_r370_ls_sec2_func_0,
-	}
-};
-
-void
-acr_r370_generate_hs_bl_desc(const struct hsf_load_header *hdr, void *_bl_desc,
-			     u64 offset)
-{
-	struct acr_r370_flcn_bl_desc *bl_desc = _bl_desc;
-
-	bl_desc->ctx_dma = FALCON_DMAIDX_VIRT;
-	bl_desc->non_sec_code_off = hdr->non_sec_code_off;
-	bl_desc->non_sec_code_size = hdr->non_sec_code_size;
-	bl_desc->sec_code_off = hsf_load_header_app_off(hdr, 0);
-	bl_desc->sec_code_size = hsf_load_header_app_size(hdr, 0);
-	bl_desc->code_entry_point = 0;
-	bl_desc->code_dma_base = u64_to_flcn64(offset);
-	bl_desc->data_dma_base = u64_to_flcn64(offset + hdr->data_dma_base);
-	bl_desc->data_size = hdr->data_size;
-}
-
-const struct acr_r352_func
-acr_r370_func = {
-	.fixup_hs_desc = acr_r367_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r370_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
-	.shadow_blob = true,
-	.ls_ucode_img_load = acr_r367_ls_ucode_img_load,
-	.ls_fill_headers = acr_r367_ls_fill_headers,
-	.ls_write_wpr = acr_r367_ls_write_wpr,
-	.ls_func = {
-		[NVKM_SECBOOT_FALCON_SEC2] = &acr_r370_ls_sec2_func,
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func,
-	},
-};
-
-struct nvkm_acr *
-acr_r370_new(enum nvkm_secboot_falcon boot_falcon,
-	     unsigned long managed_falcons)
-{
-	return acr_r352_new_(&acr_r370_func, boot_falcon, managed_falcons);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h
deleted file mode 100644
index 2efed6f995ad..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r370.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef __NVKM_SECBOOT_ACR_R370_H__
-#define __NVKM_SECBOOT_ACR_R370_H__
-
-#include "priv.h"
-struct hsf_load_header;
-
-/* Same as acr_r361_flcn_bl_desc, plus argc/argv */
-struct acr_r370_flcn_bl_desc {
-	u32 reserved[4];
-	u32 signature[4];
-	u32 ctx_dma;
-	struct flcn_u64 code_dma_base;
-	u32 non_sec_code_off;
-	u32 non_sec_code_size;
-	u32 sec_code_off;
-	u32 sec_code_size;
-	u32 code_entry_point;
-	struct flcn_u64 data_dma_base;
-	u32 data_size;
-	u32 argc;
-	u32 argv;
-};
-
-void acr_r370_generate_hs_bl_desc(const struct hsf_load_header *, void *, u64);
-extern const struct acr_r352_ls_func acr_r370_ls_fecs_func;
-extern const struct acr_r352_ls_func acr_r370_ls_gpccs_func;
-extern const struct acr_r352_lsf_func acr_r370_ls_sec2_func_0;
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c
deleted file mode 100644
index 8f0647766038..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r375.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr_r370.h"
-#include "acr_r367.h"
-
-#include <core/msgqueue.h>
-#include <subdev/pmu.h>
-
-static void
-acr_r375_generate_pmu_bl_desc(const struct nvkm_acr *acr,
-			      const struct ls_ucode_img *img, u64 wpr_addr,
-			      void *_desc)
-{
-	const struct ls_ucode_img_desc *pdesc = &img->ucode_desc;
-	const struct nvkm_pmu *pmu = acr->subdev->device->pmu;
-	struct acr_r370_flcn_bl_desc *desc = _desc;
-	u64 base, addr_code, addr_data;
-	u32 addr_args;
-
-	base = wpr_addr + img->ucode_off + pdesc->app_start_offset;
-	addr_code = base + pdesc->app_resident_code_offset;
-	addr_data = base + pdesc->app_resident_data_offset;
-	addr_args = pmu->falcon->data.limit;
-	addr_args -= NVKM_MSGQUEUE_CMDLINE_SIZE;
-
-	desc->ctx_dma = FALCON_DMAIDX_UCODE;
-	desc->code_dma_base = u64_to_flcn64(addr_code);
-	desc->non_sec_code_off = pdesc->app_resident_code_offset;
-	desc->non_sec_code_size = pdesc->app_resident_code_size;
-	desc->code_entry_point = pdesc->app_imem_entry;
-	desc->data_dma_base = u64_to_flcn64(addr_data);
-	desc->data_size = pdesc->app_resident_data_size;
-	desc->argc = 1;
-	desc->argv = addr_args;
-}
-
-static const struct acr_r352_lsf_func
-acr_r375_ls_pmu_func_0 = {
-	.generate_bl_desc = acr_r375_generate_pmu_bl_desc,
-	.bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
-};
-
-const struct acr_r352_ls_func
-acr_r375_ls_pmu_func = {
-	.load = acr_ls_ucode_load_pmu,
-	.post_run = acr_ls_pmu_post_run,
-	.version_max = 0,
-	.version = {
-		&acr_r375_ls_pmu_func_0,
-	}
-};
-
-const struct acr_r352_func
-acr_r375_func = {
-	.fixup_hs_desc = acr_r367_fixup_hs_desc,
-	.generate_hs_bl_desc = acr_r370_generate_hs_bl_desc,
-	.hs_bl_desc_size = sizeof(struct acr_r370_flcn_bl_desc),
-	.shadow_blob = true,
-	.ls_ucode_img_load = acr_r367_ls_ucode_img_load,
-	.ls_fill_headers = acr_r367_ls_fill_headers,
-	.ls_write_wpr = acr_r367_ls_write_wpr,
-	.ls_func = {
-		[NVKM_SECBOOT_FALCON_FECS] = &acr_r370_ls_fecs_func,
-		[NVKM_SECBOOT_FALCON_GPCCS] = &acr_r370_ls_gpccs_func,
-		[NVKM_SECBOOT_FALCON_PMU] = &acr_r375_ls_pmu_func,
-	},
-};
-
-struct nvkm_acr *
-acr_r375_new(enum nvkm_secboot_falcon boot_falcon,
-	     unsigned long managed_falcons)
-{
-	return acr_r352_new_(&acr_r375_func, boot_falcon, managed_falcons);
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c
deleted file mode 100644
index ee29c6c11afd..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/base.c
+++ /dev/null
@@ -1,213 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-/*
- * Secure boot is the process by which NVIDIA-signed firmware is loaded into
- * some of the falcons of a GPU. For production devices this is the only way
- * for the firmware to access useful (but sensitive) registers.
- *
- * A Falcon microprocessor supporting advanced security modes can run in one of
- * three modes:
- *
- * - Non-secure (NS). In this mode, functionality is similar to Falcon
- *   architectures before security modes were introduced (pre-Maxwell), but
- *   capability is restricted. In particular, certain registers may be
- *   inaccessible for reads and/or writes, and physical memory access may be
- *   disabled (on certain Falcon instances). This is the only possible mode that
- *   can be used if you don't have microcode cryptographically signed by NVIDIA.
- *
- * - Heavy Secure (HS). In this mode, the microprocessor is a black box - it's
- *   not possible to read or write any Falcon internal state or Falcon registers
- *   from outside the Falcon (for example, from the host system). The only way
- *   to enable this mode is by loading microcode that has been signed by NVIDIA.
- *   (The loading process involves tagging the IMEM block as secure, writing the
- *   signature into a Falcon register, and starting execution. The hardware will
- *   validate the signature, and if valid, grant HS privileges.)
- *
- * - Light Secure (LS). In this mode, the microprocessor has more privileges
- *   than NS but fewer than HS. Some of the microprocessor state is visible to
- *   host software to ease debugging. The only way to enable this mode is by HS
- *   microcode enabling LS mode. Some privileges available to HS mode are not
- *   available here. LS mode is introduced in GM20x.
- *
- * Secure boot consists in temporarily switching a HS-capable falcon (typically
- * PMU) into HS mode in order to validate the LS firmwares of managed falcons,
- * load them, and switch managed falcons into LS mode. Once secure boot
- * completes, no falcon remains in HS mode.
- *
- * Secure boot requires a write-protected memory region (WPR) which can only be
- * written by the secure falcon. On dGPU, the driver sets up the WPR region in
- * video memory. On Tegra, it is set up by the bootloader and its location and
- * size written into memory controller registers.
- *
- * The secure boot process takes place as follows:
- *
- * 1) A LS blob is constructed that contains all the LS firmwares we want to
- *    load, along with their signatures and bootloaders.
- *
- * 2) A HS blob (also called ACR) is created that contains the signed HS
- *    firmware in charge of loading the LS firmwares into their respective
- *    falcons.
- *
- * 3) The HS blob is loaded (via its own bootloader) and executed on the
- *    HS-capable falcon. It authenticates itself, switches the secure falcon to
- *    HS mode and setup the WPR region around the LS blob (dGPU) or copies the
- *    LS blob into the WPR region (Tegra).
- *
- * 4) The LS blob is now secure from all external tampering. The HS falcon
- *    checks the signatures of the LS firmwares and, if valid, switches the
- *    managed falcons to LS mode and makes them ready to run the LS firmware.
- *
- * 5) The managed falcons remain in LS mode and can be started.
- *
- */
-
-#include "priv.h"
-#include "acr.h"
-
-#include <subdev/mc.h>
-#include <subdev/timer.h>
-#include <subdev/pmu.h>
-#include <engine/sec2.h>
-
-const char *
-nvkm_secboot_falcon_name[] = {
-	[NVKM_SECBOOT_FALCON_PMU] = "PMU",
-	[NVKM_SECBOOT_FALCON_RESERVED] = "<reserved>",
-	[NVKM_SECBOOT_FALCON_FECS] = "FECS",
-	[NVKM_SECBOOT_FALCON_GPCCS] = "GPCCS",
-	[NVKM_SECBOOT_FALCON_SEC2] = "SEC2",
-	[NVKM_SECBOOT_FALCON_END] = "<invalid>",
-};
-/**
- * nvkm_secboot_reset() - reset specified falcon
- */
-int
-nvkm_secboot_reset(struct nvkm_secboot *sb, unsigned long falcon_mask)
-{
-	/* Unmanaged falcon? */
-	if ((falcon_mask | sb->acr->managed_falcons) != sb->acr->managed_falcons) {
-		nvkm_error(&sb->subdev, "cannot reset unmanaged falcon!\n");
-		return -EINVAL;
-	}
-
-	return sb->acr->func->reset(sb->acr, sb, falcon_mask);
-}
-
-/**
- * nvkm_secboot_is_managed() - check whether a given falcon is securely-managed
- */
-bool
-nvkm_secboot_is_managed(struct nvkm_secboot *sb, enum nvkm_secboot_falcon fid)
-{
-	if (!sb)
-		return false;
-
-	return sb->acr->managed_falcons & BIT(fid);
-}
-
-static int
-nvkm_secboot_oneinit(struct nvkm_subdev *subdev)
-{
-	struct nvkm_secboot *sb = nvkm_secboot(subdev);
-	int ret = 0;
-
-	switch (sb->acr->boot_falcon) {
-	case NVKM_SECBOOT_FALCON_PMU:
-		sb->halt_falcon = sb->boot_falcon = subdev->device->pmu->falcon;
-		break;
-	case NVKM_SECBOOT_FALCON_SEC2:
-		/* we must keep SEC2 alive forever since ACR will run on it */
-		nvkm_engine_ref(&subdev->device->sec2->engine);
-		sb->boot_falcon = subdev->device->sec2->falcon;
-		sb->halt_falcon = subdev->device->pmu->falcon;
-		break;
-	default:
-		nvkm_error(subdev, "Unmanaged boot falcon %s!\n",
-			                nvkm_secboot_falcon_name[sb->acr->boot_falcon]);
-		return -EINVAL;
-	}
-	nvkm_debug(subdev, "using %s falcon for ACR\n", sb->boot_falcon->name);
-
-	/* Call chip-specific init function */
-	if (sb->func->oneinit)
-		ret = sb->func->oneinit(sb);
-	if (ret) {
-		nvkm_error(subdev, "Secure Boot initialization failed: %d\n",
-			   ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int
-nvkm_secboot_fini(struct nvkm_subdev *subdev, bool suspend)
-{
-	struct nvkm_secboot *sb = nvkm_secboot(subdev);
-	int ret = 0;
-
-	if (sb->func->fini)
-		ret = sb->func->fini(sb, suspend);
-
-	return ret;
-}
-
-static void *
-nvkm_secboot_dtor(struct nvkm_subdev *subdev)
-{
-	struct nvkm_secboot *sb = nvkm_secboot(subdev);
-	void *ret = NULL;
-
-	if (sb->func->dtor)
-		ret = sb->func->dtor(sb);
-
-	return ret;
-}
-
-static const struct nvkm_subdev_func
-nvkm_secboot = {
-	.oneinit = nvkm_secboot_oneinit,
-	.fini = nvkm_secboot_fini,
-	.dtor = nvkm_secboot_dtor,
-};
-
-int
-nvkm_secboot_ctor(const struct nvkm_secboot_func *func, struct nvkm_acr *acr,
-		  struct nvkm_device *device, int index,
-		  struct nvkm_secboot *sb)
-{
-	unsigned long fid;
-
-	nvkm_subdev_ctor(&nvkm_secboot, device, index, &sb->subdev);
-	sb->func = func;
-	sb->acr = acr;
-	acr->subdev = &sb->subdev;
-
-	nvkm_debug(&sb->subdev, "securely managed falcons:\n");
-	for_each_set_bit(fid, &sb->acr->managed_falcons,
-			 NVKM_SECBOOT_FALCON_END)
-		nvkm_debug(&sb->subdev, "- %s\n",
-			   nvkm_secboot_falcon_name[fid]);
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c
deleted file mode 100644
index 5e91b3f90065..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.c
+++ /dev/null
@@ -1,262 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-
-#include "acr.h"
-#include "gm200.h"
-
-#include <core/gpuobj.h>
-#include <subdev/fb.h>
-#include <engine/falcon.h>
-#include <subdev/mc.h>
-
-/**
- * gm200_secboot_run_blob() - run the given high-secure blob
- *
- */
-int
-gm200_secboot_run_blob(struct nvkm_secboot *sb, struct nvkm_gpuobj *blob,
-		       struct nvkm_falcon *falcon)
-{
-	struct gm200_secboot *gsb = gm200_secboot(sb);
-	struct nvkm_subdev *subdev = &gsb->base.subdev;
-	struct nvkm_vma *vma = NULL;
-	u32 start_address;
-	int ret;
-
-	ret = nvkm_falcon_get(falcon, subdev);
-	if (ret)
-		return ret;
-
-	/* Map the HS firmware so the HS bootloader can see it */
-	ret = nvkm_vmm_get(gsb->vmm, 12, blob->size, &vma);
-	if (ret) {
-		nvkm_falcon_put(falcon, subdev);
-		return ret;
-	}
-
-	ret = nvkm_memory_map(blob, 0, gsb->vmm, vma, NULL, 0);
-	if (ret)
-		goto end;
-
-	/* Reset and set the falcon up */
-	ret = nvkm_falcon_reset(falcon);
-	if (ret)
-		goto end;
-	nvkm_falcon_bind_context(falcon, gsb->inst);
-
-	/* Load the HS bootloader into the falcon's IMEM/DMEM */
-	ret = sb->acr->func->load(sb->acr, falcon, blob, vma->addr);
-	if (ret < 0)
-		goto end;
-
-	start_address = ret;
-
-	/* Disable interrupts as we will poll for the HALT bit */
-	nvkm_mc_intr_mask(sb->subdev.device, falcon->owner->index, false);
-
-	/* Set default error value in mailbox register */
-	nvkm_falcon_wr32(falcon, 0x040, 0xdeada5a5);
-
-	/* Start the HS bootloader */
-	nvkm_falcon_set_start_addr(falcon, start_address);
-	nvkm_falcon_start(falcon);
-	ret = nvkm_falcon_wait_for_halt(falcon, 100);
-	if (ret)
-		goto end;
-
-	/*
-	 * The mailbox register contains the (positive) error code - return this
-	 * to the caller
-	 */
-	ret = nvkm_falcon_rd32(falcon, 0x040);
-
-end:
-	/* Reenable interrupts */
-	nvkm_mc_intr_mask(sb->subdev.device, falcon->owner->index, true);
-
-	/* We don't need the ACR firmware anymore */
-	nvkm_vmm_put(gsb->vmm, &vma);
-	nvkm_falcon_put(falcon, subdev);
-
-	return ret;
-}
-
-int
-gm200_secboot_oneinit(struct nvkm_secboot *sb)
-{
-	struct gm200_secboot *gsb = gm200_secboot(sb);
-	struct nvkm_device *device = sb->subdev.device;
-	int ret;
-
-	/* Allocate instance block and VM */
-	ret = nvkm_memory_new(device, NVKM_MEM_TARGET_INST, 0x1000, 0, true,
-			      &gsb->inst);
-	if (ret)
-		return ret;
-
-	ret = nvkm_vmm_new(device, 0, 600 * 1024, NULL, 0, NULL, "acr",
-			   &gsb->vmm);
-	if (ret)
-		return ret;
-
-	atomic_inc(&gsb->vmm->engref[NVKM_SUBDEV_PMU]);
-	gsb->vmm->debug = gsb->base.subdev.debug;
-
-	ret = nvkm_vmm_join(gsb->vmm, gsb->inst);
-	if (ret)
-		return ret;
-
-	if (sb->acr->func->oneinit) {
-		ret = sb->acr->func->oneinit(sb->acr, sb);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-int
-gm200_secboot_fini(struct nvkm_secboot *sb, bool suspend)
-{
-	int ret = 0;
-
-	if (sb->acr->func->fini)
-		ret = sb->acr->func->fini(sb->acr, sb, suspend);
-
-	return ret;
-}
-
-void *
-gm200_secboot_dtor(struct nvkm_secboot *sb)
-{
-	struct gm200_secboot *gsb = gm200_secboot(sb);
-
-	sb->acr->func->dtor(sb->acr);
-
-	nvkm_vmm_part(gsb->vmm, gsb->inst);
-	nvkm_vmm_unref(&gsb->vmm);
-	nvkm_memory_unref(&gsb->inst);
-
-	return gsb;
-}
-
-
-static const struct nvkm_secboot_func
-gm200_secboot = {
-	.dtor = gm200_secboot_dtor,
-	.oneinit = gm200_secboot_oneinit,
-	.fini = gm200_secboot_fini,
-	.run_blob = gm200_secboot_run_blob,
-};
-
-int
-gm200_secboot_new(struct nvkm_device *device, int index,
-		  struct nvkm_secboot **psb)
-{
-	int ret;
-	struct gm200_secboot *gsb;
-	struct nvkm_acr *acr;
-
-	acr = acr_r361_new(BIT(NVKM_SECBOOT_FALCON_FECS) |
-			   BIT(NVKM_SECBOOT_FALCON_GPCCS));
-	if (IS_ERR(acr))
-		return PTR_ERR(acr);
-
-	gsb = kzalloc(sizeof(*gsb), GFP_KERNEL);
-	if (!gsb) {
-		psb = NULL;
-		return -ENOMEM;
-	}
-	*psb = &gsb->base;
-
-	ret = nvkm_secboot_ctor(&gm200_secboot, acr, device, index, &gsb->base);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-
-MODULE_FIRMWARE("nvidia/gm200/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gm200/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gm200/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gm200/gr/sw_method_init.bin");
-
-MODULE_FIRMWARE("nvidia/gm204/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gm204/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gm204/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gm204/gr/sw_method_init.bin");
-
-MODULE_FIRMWARE("nvidia/gm206/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gm206/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gm206/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gm206/gr/sw_method_init.bin");
-
-MODULE_FIRMWARE("nvidia/gp100/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp100/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp100/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp100/gr/sw_method_init.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.h
deleted file mode 100644
index 62c5e162099a..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm200.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef __NVKM_SECBOOT_GM200_H__
-#define __NVKM_SECBOOT_GM200_H__
-
-#include "priv.h"
-
-struct gm200_secboot {
-	struct nvkm_secboot base;
-
-	/* Instance block & address space used for HS FW execution */
-	struct nvkm_memory *inst;
-	struct nvkm_vmm *vmm;
-};
-#define gm200_secboot(sb) container_of(sb, struct gm200_secboot, base)
-
-int gm200_secboot_oneinit(struct nvkm_secboot *);
-int gm200_secboot_fini(struct nvkm_secboot *, bool);
-void *gm200_secboot_dtor(struct nvkm_secboot *);
-int gm200_secboot_run_blob(struct nvkm_secboot *, struct nvkm_gpuobj *,
-			   struct nvkm_falcon *);
-
-/* Tegra-only */
-int gm20b_secboot_tegra_read_wpr(struct gm200_secboot *, u32);
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
deleted file mode 100644
index df8b919dcf09..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ /dev/null
@@ -1,148 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr.h"
-#include "gm200.h"
-
-#define TEGRA210_MC_BASE			0x70019000
-
-#ifdef CONFIG_ARCH_TEGRA
-#define MC_SECURITY_CARVEOUT2_CFG0		0xc58
-#define MC_SECURITY_CARVEOUT2_BOM_0		0xc5c
-#define MC_SECURITY_CARVEOUT2_BOM_HI_0		0xc60
-#define MC_SECURITY_CARVEOUT2_SIZE_128K		0xc64
-#define TEGRA_MC_SECURITY_CARVEOUT_CFG_LOCKED	(1 << 1)
-/**
- * gm20b_secboot_tegra_read_wpr() - read the WPR registers on Tegra
- *
- * On dGPU, we can manage the WPR region ourselves, but on Tegra the WPR region
- * is reserved from system memory by the bootloader and irreversibly locked.
- * This function reads the address and size of the pre-configured WPR region.
- */
-int
-gm20b_secboot_tegra_read_wpr(struct gm200_secboot *gsb, u32 mc_base)
-{
-	struct nvkm_secboot *sb = &gsb->base;
-	void __iomem *mc;
-	u32 cfg;
-
-	mc = ioremap(mc_base, 0xd00);
-	if (!mc) {
-		nvkm_error(&sb->subdev, "Cannot map Tegra MC registers\n");
-		return -ENOMEM;
-	}
-	sb->wpr_addr = ioread32_native(mc + MC_SECURITY_CARVEOUT2_BOM_0) |
-	      ((u64)ioread32_native(mc + MC_SECURITY_CARVEOUT2_BOM_HI_0) << 32);
-	sb->wpr_size = ioread32_native(mc + MC_SECURITY_CARVEOUT2_SIZE_128K)
-		<< 17;
-	cfg = ioread32_native(mc + MC_SECURITY_CARVEOUT2_CFG0);
-	iounmap(mc);
-
-	/* Check that WPR settings are valid */
-	if (sb->wpr_size == 0) {
-		nvkm_error(&sb->subdev, "WPR region is empty\n");
-		return -EINVAL;
-	}
-
-	if (!(cfg & TEGRA_MC_SECURITY_CARVEOUT_CFG_LOCKED)) {
-		nvkm_error(&sb->subdev, "WPR region not locked\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-#else
-int
-gm20b_secboot_tegra_read_wpr(struct gm200_secboot *gsb, u32 mc_base)
-{
-	nvkm_error(&gsb->base.subdev, "Tegra support not compiled in\n");
-	return -EINVAL;
-}
-#endif
-
-static int
-gm20b_secboot_oneinit(struct nvkm_secboot *sb)
-{
-	struct gm200_secboot *gsb = gm200_secboot(sb);
-	int ret;
-
-	ret = gm20b_secboot_tegra_read_wpr(gsb, TEGRA210_MC_BASE);
-	if (ret)
-		return ret;
-
-	return gm200_secboot_oneinit(sb);
-}
-
-static const struct nvkm_secboot_func
-gm20b_secboot = {
-	.dtor = gm200_secboot_dtor,
-	.oneinit = gm20b_secboot_oneinit,
-	.fini = gm200_secboot_fini,
-	.run_blob = gm200_secboot_run_blob,
-};
-
-int
-gm20b_secboot_new(struct nvkm_device *device, int index,
-		  struct nvkm_secboot **psb)
-{
-	int ret;
-	struct gm200_secboot *gsb;
-	struct nvkm_acr *acr;
-
-	acr = acr_r352_new(BIT(NVKM_SECBOOT_FALCON_FECS) |
-			   BIT(NVKM_SECBOOT_FALCON_PMU));
-	if (IS_ERR(acr))
-		return PTR_ERR(acr);
-	/* Support the initial GM20B firmware release without PMU */
-	acr->optional_falcons = BIT(NVKM_SECBOOT_FALCON_PMU);
-
-	gsb = kzalloc(sizeof(*gsb), GFP_KERNEL);
-	if (!gsb) {
-		psb = NULL;
-		return -ENOMEM;
-	}
-	*psb = &gsb->base;
-
-	ret = nvkm_secboot_ctor(&gm20b_secboot, acr, device, index, &gsb->base);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
-MODULE_FIRMWARE("nvidia/gm20b/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gm20b/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gm20b/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gm20b/pmu/desc.bin");
-MODULE_FIRMWARE("nvidia/gm20b/pmu/image.bin");
-MODULE_FIRMWARE("nvidia/gm20b/pmu/sig.bin");
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c
deleted file mode 100644
index 4695f1c8e33f..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp102.c
+++ /dev/null
@@ -1,264 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr.h"
-#include "gm200.h"
-
-#include "ls_ucode.h"
-#include "hs_ucode.h"
-#include <subdev/mc.h>
-#include <subdev/timer.h>
-#include <engine/falcon.h>
-#include <engine/nvdec.h>
-
-static bool
-gp102_secboot_scrub_required(struct nvkm_secboot *sb)
-{
-	struct nvkm_subdev *subdev = &sb->subdev;
-	struct nvkm_device *device = subdev->device;
-	u32 reg;
-
-	nvkm_wr32(device, 0x100cd0, 0x2);
-	reg = nvkm_rd32(device, 0x100cd0);
-
-	return (reg & BIT(4));
-}
-
-static int
-gp102_run_secure_scrub(struct nvkm_secboot *sb)
-{
-	struct nvkm_subdev *subdev = &sb->subdev;
-	struct nvkm_device *device = subdev->device;
-	struct nvkm_engine *engine;
-	struct nvkm_falcon *falcon;
-	void *scrub_image;
-	struct fw_bin_header *hsbin_hdr;
-	struct hsf_fw_header *fw_hdr;
-	struct hsf_load_header *lhdr;
-	void *scrub_data;
-	int ret;
-
-	nvkm_debug(subdev, "running VPR scrubber binary on NVDEC...\n");
-
-	engine = nvkm_engine_ref(&device->nvdec[0]->engine);
-	if (IS_ERR(engine))
-		return PTR_ERR(engine);
-	falcon = device->nvdec[0]->falcon;
-
-	nvkm_falcon_get(falcon, &sb->subdev);
-
-	scrub_image = hs_ucode_load_blob(subdev, falcon, "nvdec/scrubber");
-	if (IS_ERR(scrub_image))
-		return PTR_ERR(scrub_image);
-
-	nvkm_falcon_reset(falcon);
-	nvkm_falcon_bind_context(falcon, NULL);
-
-	hsbin_hdr = scrub_image;
-	fw_hdr = scrub_image + hsbin_hdr->header_offset;
-	lhdr = scrub_image + fw_hdr->hdr_offset;
-	scrub_data = scrub_image + hsbin_hdr->data_offset;
-
-	nvkm_falcon_load_imem(falcon, scrub_data, lhdr->non_sec_code_off,
-			      lhdr->non_sec_code_size,
-			      lhdr->non_sec_code_off >> 8, 0, false);
-	nvkm_falcon_load_imem(falcon, scrub_data + lhdr->apps[0],
-			      ALIGN(lhdr->apps[0], 0x100),
-			      lhdr->apps[1],
-			      lhdr->apps[0] >> 8, 0, true);
-	nvkm_falcon_load_dmem(falcon, scrub_data + lhdr->data_dma_base, 0,
-			      lhdr->data_size, 0);
-
-	kfree(scrub_image);
-
-	nvkm_falcon_set_start_addr(falcon, 0x0);
-	nvkm_falcon_start(falcon);
-
-	ret = nvkm_falcon_wait_for_halt(falcon, 500);
-	if (ret < 0) {
-		nvkm_error(subdev, "failed to run VPR scrubber binary!\n");
-		ret = -ETIMEDOUT;
-		goto end;
-	}
-
-	/* put nvdec in clean state - without reset it will remain in HS mode */
-	nvkm_falcon_reset(falcon);
-
-	if (gp102_secboot_scrub_required(sb)) {
-		nvkm_error(subdev, "VPR scrubber binary failed!\n");
-		ret = -EINVAL;
-		goto end;
-	}
-
-	nvkm_debug(subdev, "VPR scrub successfully completed\n");
-
-end:
-	nvkm_falcon_put(falcon, &sb->subdev);
-	nvkm_engine_unref(&engine);
-	return ret;
-}
-
-static int
-gp102_secboot_run_blob(struct nvkm_secboot *sb, struct nvkm_gpuobj *blob,
-		       struct nvkm_falcon *falcon)
-{
-	int ret;
-
-	/* make sure the VPR region is unlocked */
-	if (gp102_secboot_scrub_required(sb)) {
-		ret = gp102_run_secure_scrub(sb);
-		if (ret)
-			return ret;
-	}
-
-	return gm200_secboot_run_blob(sb, blob, falcon);
-}
-
-const struct nvkm_secboot_func
-gp102_secboot = {
-	.dtor = gm200_secboot_dtor,
-	.oneinit = gm200_secboot_oneinit,
-	.fini = gm200_secboot_fini,
-	.run_blob = gp102_secboot_run_blob,
-};
-
-int
-gp102_secboot_new(struct nvkm_device *device, int index,
-		  struct nvkm_secboot **psb)
-{
-	int ret;
-	struct gm200_secboot *gsb;
-	struct nvkm_acr *acr;
-
-	acr = acr_r367_new(NVKM_SECBOOT_FALCON_SEC2,
-			   BIT(NVKM_SECBOOT_FALCON_FECS) |
-			   BIT(NVKM_SECBOOT_FALCON_GPCCS) |
-			   BIT(NVKM_SECBOOT_FALCON_SEC2));
-	if (IS_ERR(acr))
-		return PTR_ERR(acr);
-
-	gsb = kzalloc(sizeof(*gsb), GFP_KERNEL);
-	if (!gsb) {
-		psb = NULL;
-		return -ENOMEM;
-	}
-	*psb = &gsb->base;
-
-	ret = nvkm_secboot_ctor(&gp102_secboot, acr, device, index, &gsb->base);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-MODULE_FIRMWARE("nvidia/gp102/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp102/acr/unload_bl.bin");
-MODULE_FIRMWARE("nvidia/gp102/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp102/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp102/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gp102/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/gp102/sec2/desc.bin");
-MODULE_FIRMWARE("nvidia/gp102/sec2/image.bin");
-MODULE_FIRMWARE("nvidia/gp102/sec2/sig.bin");
-MODULE_FIRMWARE("nvidia/gp102/sec2/desc-1.bin");
-MODULE_FIRMWARE("nvidia/gp102/sec2/image-1.bin");
-MODULE_FIRMWARE("nvidia/gp102/sec2/sig-1.bin");
-MODULE_FIRMWARE("nvidia/gp104/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp104/acr/unload_bl.bin");
-MODULE_FIRMWARE("nvidia/gp104/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp104/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp104/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gp104/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/gp104/sec2/desc.bin");
-MODULE_FIRMWARE("nvidia/gp104/sec2/image.bin");
-MODULE_FIRMWARE("nvidia/gp104/sec2/sig.bin");
-MODULE_FIRMWARE("nvidia/gp104/sec2/desc-1.bin");
-MODULE_FIRMWARE("nvidia/gp104/sec2/image-1.bin");
-MODULE_FIRMWARE("nvidia/gp104/sec2/sig-1.bin");
-MODULE_FIRMWARE("nvidia/gp106/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp106/acr/unload_bl.bin");
-MODULE_FIRMWARE("nvidia/gp106/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp106/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp106/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gp106/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/gp106/sec2/desc.bin");
-MODULE_FIRMWARE("nvidia/gp106/sec2/image.bin");
-MODULE_FIRMWARE("nvidia/gp106/sec2/sig.bin");
-MODULE_FIRMWARE("nvidia/gp106/sec2/desc-1.bin");
-MODULE_FIRMWARE("nvidia/gp106/sec2/image-1.bin");
-MODULE_FIRMWARE("nvidia/gp106/sec2/sig-1.bin");
-MODULE_FIRMWARE("nvidia/gp107/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp107/acr/unload_bl.bin");
-MODULE_FIRMWARE("nvidia/gp107/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp107/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp107/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gp107/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/gp107/sec2/desc.bin");
-MODULE_FIRMWARE("nvidia/gp107/sec2/image.bin");
-MODULE_FIRMWARE("nvidia/gp107/sec2/sig.bin");
-MODULE_FIRMWARE("nvidia/gp107/sec2/desc-1.bin");
-MODULE_FIRMWARE("nvidia/gp107/sec2/image-1.bin");
-MODULE_FIRMWARE("nvidia/gp107/sec2/sig-1.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
deleted file mode 100644
index 737a8d50a1f2..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp108.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * Copyright 2017 Red Hat Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
-#include "gm200.h"
-#include "acr.h"
-
-int
-gp108_secboot_new(struct nvkm_device *device, int index,
-		  struct nvkm_secboot **psb)
-{
-	struct gm200_secboot *gsb;
-	struct nvkm_acr *acr;
-
-	acr = acr_r370_new(NVKM_SECBOOT_FALCON_SEC2,
-			   BIT(NVKM_SECBOOT_FALCON_FECS) |
-			   BIT(NVKM_SECBOOT_FALCON_GPCCS) |
-			   BIT(NVKM_SECBOOT_FALCON_SEC2));
-	if (IS_ERR(acr))
-		return PTR_ERR(acr);
-
-	if (!(gsb = kzalloc(sizeof(*gsb), GFP_KERNEL))) {
-		acr->func->dtor(acr);
-		return -ENOMEM;
-	}
-	*psb = &gsb->base;
-
-	return nvkm_secboot_ctor(&gp102_secboot, acr, device, index, &gsb->base);
-}
-
-MODULE_FIRMWARE("nvidia/gp108/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp108/acr/unload_bl.bin");
-MODULE_FIRMWARE("nvidia/gp108/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp108/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp108/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gp108/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/gp108/sec2/desc.bin");
-MODULE_FIRMWARE("nvidia/gp108/sec2/image.bin");
-MODULE_FIRMWARE("nvidia/gp108/sec2/sig.bin");
-
-MODULE_FIRMWARE("nvidia/gv100/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gv100/acr/unload_bl.bin");
-MODULE_FIRMWARE("nvidia/gv100/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gv100/acr/ucode_unload.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gv100/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin");
-MODULE_FIRMWARE("nvidia/gv100/sec2/desc.bin");
-MODULE_FIRMWARE("nvidia/gv100/sec2/image.bin");
-MODULE_FIRMWARE("nvidia/gv100/sec2/sig.bin");
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
deleted file mode 100644
index 28ca29d0eeee..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
+++ /dev/null
@@ -1,95 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "acr.h"
-#include "gm200.h"
-
-#define TEGRA186_MC_BASE			0x02c10000
-
-static int
-gp10b_secboot_oneinit(struct nvkm_secboot *sb)
-{
-	struct gm200_secboot *gsb = gm200_secboot(sb);
-	int ret;
-
-	ret = gm20b_secboot_tegra_read_wpr(gsb, TEGRA186_MC_BASE);
-	if (ret)
-		return ret;
-
-	return gm200_secboot_oneinit(sb);
-}
-
-static const struct nvkm_secboot_func
-gp10b_secboot = {
-	.dtor = gm200_secboot_dtor,
-	.oneinit = gp10b_secboot_oneinit,
-	.fini = gm200_secboot_fini,
-	.run_blob = gm200_secboot_run_blob,
-};
-
-int
-gp10b_secboot_new(struct nvkm_device *device, int index,
-		  struct nvkm_secboot **psb)
-{
-	int ret;
-	struct gm200_secboot *gsb;
-	struct nvkm_acr *acr;
-
-	acr = acr_r352_new(BIT(NVKM_SECBOOT_FALCON_FECS) |
-			   BIT(NVKM_SECBOOT_FALCON_GPCCS) |
-			   BIT(NVKM_SECBOOT_FALCON_PMU));
-	if (IS_ERR(acr))
-		return PTR_ERR(acr);
-
-	gsb = kzalloc(sizeof(*gsb), GFP_KERNEL);
-	if (!gsb) {
-		psb = NULL;
-		return -ENOMEM;
-	}
-	*psb = &gsb->base;
-
-	ret = nvkm_secboot_ctor(&gp10b_secboot, acr, device, index, &gsb->base);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
-MODULE_FIRMWARE("nvidia/gp10b/acr/bl.bin");
-MODULE_FIRMWARE("nvidia/gp10b/acr/ucode_load.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_data.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_bl.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_inst.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_data.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/gpccs_sig.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/sw_ctx.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/sw_nonctx.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/sw_bundle_init.bin");
-MODULE_FIRMWARE("nvidia/gp10b/gr/sw_method_init.bin");
-MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
-MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
-MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/hs_ucode.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/hs_ucode.c
deleted file mode 100644
index 6b33182ddc2f..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/hs_ucode.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#include "hs_ucode.h"
-#include "ls_ucode.h"
-#include "acr.h"
-
-#include <engine/falcon.h>
-
-/**
- * hs_ucode_patch_signature() - patch HS blob with correct signature for
- * specified falcon.
- */
-static void
-hs_ucode_patch_signature(const struct nvkm_falcon *falcon, void *acr_image,
-			 bool new_format)
-{
-	struct fw_bin_header *hsbin_hdr = acr_image;
-	struct hsf_fw_header *fw_hdr = acr_image + hsbin_hdr->header_offset;
-	void *hs_data = acr_image + hsbin_hdr->data_offset;
-	void *sig;
-	u32 sig_size;
-	u32 patch_loc, patch_sig;
-
-	/*
-	 * I had the brilliant idea to "improve" the binary format by
-	 * removing this useless indirection. However to make NVIDIA files
-	 * directly compatible, let's support both format.
-	 */
-	if (new_format) {
-		patch_loc = fw_hdr->patch_loc;
-		patch_sig = fw_hdr->patch_sig;
-	} else {
-		patch_loc = *(u32 *)(acr_image + fw_hdr->patch_loc);
-		patch_sig = *(u32 *)(acr_image + fw_hdr->patch_sig);
-	}
-
-	/* Falcon in debug or production mode? */
-	if (falcon->debug) {
-		sig = acr_image + fw_hdr->sig_dbg_offset;
-		sig_size = fw_hdr->sig_dbg_size;
-	} else {
-		sig = acr_image + fw_hdr->sig_prod_offset;
-		sig_size = fw_hdr->sig_prod_size;
-	}
-
-	/* Patch signature */
-	memcpy(hs_data + patch_loc, sig + patch_sig, sig_size);
-}
-
-void *
-hs_ucode_load_blob(struct nvkm_subdev *subdev, const struct nvkm_falcon *falcon,
-		   const char *fw)
-{
-	void *acr_image;
-	bool new_format;
-
-	acr_image = nvkm_acr_load_firmware(subdev, fw, 0);
-	if (IS_ERR(acr_image))
-		return acr_image;
-
-	/* detect the format to define how signature should be patched */
-	switch (((u32 *)acr_image)[0]) {
-	case 0x3b1d14f0:
-		new_format = true;
-		break;
-	case 0x000010de:
-		new_format = false;
-		break;
-	default:
-		nvkm_error(subdev, "unknown header for HS blob %s\n", fw);
-		return ERR_PTR(-EINVAL);
-	}
-
-	hs_ucode_patch_signature(falcon, acr_image, new_format);
-
-	return acr_image;
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/hs_ucode.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/hs_ucode.h
deleted file mode 100644
index d8cfc6f7752a..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/hs_ucode.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef __NVKM_SECBOOT_HS_UCODE_H__
-#define __NVKM_SECBOOT_HS_UCODE_H__
-
-#include <core/os.h>
-#include <core/subdev.h>
-
-struct nvkm_falcon;
-
-/**
- * struct hsf_fw_header - HS firmware descriptor
- * @sig_dbg_offset:	offset of the debug signature
- * @sig_dbg_size:	size of the debug signature
- * @sig_prod_offset:	offset of the production signature
- * @sig_prod_size:	size of the production signature
- * @patch_loc:		offset of the offset (sic) of where the signature is
- * @patch_sig:		offset of the offset (sic) to add to sig_*_offset
- * @hdr_offset:		offset of the load header (see struct hs_load_header)
- * @hdr_size:		size of above header
- *
- * This structure is embedded in the HS firmware image at
- * hs_bin_hdr.header_offset.
- */
-struct hsf_fw_header {
-	u32 sig_dbg_offset;
-	u32 sig_dbg_size;
-	u32 sig_prod_offset;
-	u32 sig_prod_size;
-	u32 patch_loc;
-	u32 patch_sig;
-	u32 hdr_offset;
-	u32 hdr_size;
-};
-
-/**
- * struct hsf_load_header - HS firmware load header
- */
-struct hsf_load_header {
-	u32 non_sec_code_off;
-	u32 non_sec_code_size;
-	u32 data_dma_base;
-	u32 data_size;
-	u32 num_apps;
-	/*
-	 * Organized as follows:
-	 * - app0_code_off
-	 * - app1_code_off
-	 * - ...
-	 * - appn_code_off
-	 * - app0_code_size
-	 * - app1_code_size
-	 * - ...
-	 */
-	u32 apps[0];
-};
-
-void *hs_ucode_load_blob(struct nvkm_subdev *, const struct nvkm_falcon *,
-			 const char *);
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode.h
deleted file mode 100644
index d43f906da3a7..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode.h
+++ /dev/null
@@ -1,161 +0,0 @@
-/*
- * Copyright (c) 2014, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef __NVKM_SECBOOT_LS_UCODE_H__
-#define __NVKM_SECBOOT_LS_UCODE_H__
-
-#include <core/os.h>
-#include <core/subdev.h>
-#include <subdev/secboot.h>
-
-struct nvkm_acr;
-
-/**
- * struct ls_ucode_img_desc - descriptor of firmware image
- * @descriptor_size:		size of this descriptor
- * @image_size:			size of the whole image
- * @bootloader_start_offset:	start offset of the bootloader in ucode image
- * @bootloader_size:		size of the bootloader
- * @bootloader_imem_offset:	start off set of the bootloader in IMEM
- * @bootloader_entry_point:	entry point of the bootloader in IMEM
- * @app_start_offset:		start offset of the LS firmware
- * @app_size:			size of the LS firmware's code and data
- * @app_imem_offset:		offset of the app in IMEM
- * @app_imem_entry:		entry point of the app in IMEM
- * @app_dmem_offset:		offset of the data in DMEM
- * @app_resident_code_offset:	offset of app code from app_start_offset
- * @app_resident_code_size:	size of the code
- * @app_resident_data_offset:	offset of data from app_start_offset
- * @app_resident_data_size:	size of data
- *
- * A firmware image contains the code, data, and bootloader of a given LS
- * falcon in a single blob. This structure describes where everything is.
- *
- * This can be generated from a (bootloader, code, data) set if they have
- * been loaded separately, or come directly from a file.
- */
-struct ls_ucode_img_desc {
-	u32 descriptor_size;
-	u32 image_size;
-	u32 tools_version;
-	u32 app_version;
-	char date[64];
-	u32 bootloader_start_offset;
-	u32 bootloader_size;
-	u32 bootloader_imem_offset;
-	u32 bootloader_entry_point;
-	u32 app_start_offset;
-	u32 app_size;
-	u32 app_imem_offset;
-	u32 app_imem_entry;
-	u32 app_dmem_offset;
-	u32 app_resident_code_offset;
-	u32 app_resident_code_size;
-	u32 app_resident_data_offset;
-	u32 app_resident_data_size;
-	u32 nb_overlays;
-	struct {u32 start; u32 size; } load_ovl[64];
-	u32 compressed;
-};
-
-/**
- * struct ls_ucode_img - temporary storage for loaded LS firmwares
- * @node:		to link within lsf_ucode_mgr
- * @falcon_id:		ID of the falcon this LS firmware is for
- * @ucode_desc:		loaded or generated map of ucode_data
- * @ucode_data:		firmware payload (code and data)
- * @ucode_size:		size in bytes of data in ucode_data
- * @ucode_off:		offset of the ucode in ucode_data
- * @sig:		signature for this firmware
- * @sig:size:		size of the signature in bytes
- *
- * Preparing the WPR LS blob requires information about all the LS firmwares
- * (size, etc) to be known. This structure contains all the data of one LS
- * firmware.
- */
-struct ls_ucode_img {
-	struct list_head node;
-	enum nvkm_secboot_falcon falcon_id;
-
-	struct ls_ucode_img_desc ucode_desc;
-	u8 *ucode_data;
-	u32 ucode_size;
-	u32 ucode_off;
-
-	u8 *sig;
-	u32 sig_size;
-};
-
-/**
- * struct fw_bin_header - header of firmware files
- * @bin_magic:		always 0x3b1d14f0
- * @bin_ver:		version of the bin format
- * @bin_size:		entire image size including this header
- * @header_offset:	offset of the firmware/bootloader header in the file
- * @data_offset:	offset of the firmware/bootloader payload in the file
- * @data_size:		size of the payload
- *
- * This header is located at the beginning of the HS firmware and HS bootloader
- * files, to describe where the headers and data can be found.
- */
-struct fw_bin_header {
-	u32 bin_magic;
-	u32 bin_ver;
-	u32 bin_size;
-	u32 header_offset;
-	u32 data_offset;
-	u32 data_size;
-};
-
-/**
- * struct fw_bl_desc - firmware bootloader descriptor
- * @start_tag:		starting tag of bootloader
- * @desc_dmem_load_off:	DMEM offset of flcn_bl_dmem_desc
- * @code_off:		offset of code section
- * @code_size:		size of code section
- * @data_off:		offset of data section
- * @data_size:		size of data section
- *
- * This structure is embedded in bootloader firmware files at to describe the
- * IMEM and DMEM layout expected by the bootloader.
- */
-struct fw_bl_desc {
-	u32 start_tag;
-	u32 dmem_load_off;
-	u32 code_off;
-	u32 code_size;
-	u32 data_off;
-	u32 data_size;
-};
-
-int acr_ls_ucode_load_fecs(const struct nvkm_secboot *, int,
-			   struct ls_ucode_img *);
-int acr_ls_ucode_load_gpccs(const struct nvkm_secboot *, int,
-			    struct ls_ucode_img *);
-int acr_ls_ucode_load_pmu(const struct nvkm_secboot *, int,
-			  struct ls_ucode_img *);
-int acr_ls_pmu_post_run(const struct nvkm_acr *, const struct nvkm_secboot *);
-int acr_ls_ucode_load_sec2(const struct nvkm_secboot *, int,
-			   struct ls_ucode_img *);
-int acr_ls_sec2_post_run(const struct nvkm_acr *, const struct nvkm_secboot *);
-
-#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c
deleted file mode 100644
index 821d3b2bdb1f..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_gr.c
+++ /dev/null
@@ -1,160 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-
-#include "ls_ucode.h"
-#include "acr.h"
-
-#include <core/firmware.h>
-
-#define BL_DESC_BLK_SIZE 256
-/**
- * Build a ucode image and descriptor from provided bootloader, code and data.
- *
- * @bl:		bootloader image, including 16-bytes descriptor
- * @code:	LS firmware code segment
- * @data:	LS firmware data segment
- * @desc:	ucode descriptor to be written
- *
- * Return: allocated ucode image with corresponding descriptor information. desc
- *         is also updated to contain the right offsets within returned image.
- */
-static void *
-ls_ucode_img_build(const struct firmware *bl, const struct firmware *code,
-		   const struct firmware *data, struct ls_ucode_img_desc *desc)
-{
-	struct fw_bin_header *bin_hdr = (void *)bl->data;
-	struct fw_bl_desc *bl_desc = (void *)bl->data + bin_hdr->header_offset;
-	void *bl_data = (void *)bl->data + bin_hdr->data_offset;
-	u32 pos = 0;
-	void *image;
-
-	desc->bootloader_start_offset = pos;
-	desc->bootloader_size = ALIGN(bl_desc->code_size, sizeof(u32));
-	desc->bootloader_imem_offset = bl_desc->start_tag * 256;
-	desc->bootloader_entry_point = bl_desc->start_tag * 256;
-
-	pos = ALIGN(pos + desc->bootloader_size, BL_DESC_BLK_SIZE);
-	desc->app_start_offset = pos;
-	desc->app_size = ALIGN(code->size, BL_DESC_BLK_SIZE) +
-			 ALIGN(data->size, BL_DESC_BLK_SIZE);
-	desc->app_imem_offset = 0;
-	desc->app_imem_entry = 0;
-	desc->app_dmem_offset = 0;
-	desc->app_resident_code_offset = 0;
-	desc->app_resident_code_size = ALIGN(code->size, BL_DESC_BLK_SIZE);
-
-	pos = ALIGN(pos + desc->app_resident_code_size, BL_DESC_BLK_SIZE);
-	desc->app_resident_data_offset = pos - desc->app_start_offset;
-	desc->app_resident_data_size = ALIGN(data->size, BL_DESC_BLK_SIZE);
-
-	desc->image_size = ALIGN(bl_desc->code_size, BL_DESC_BLK_SIZE) +
-			   desc->app_size;
-
-	image = kzalloc(desc->image_size, GFP_KERNEL);
-	if (!image)
-		return ERR_PTR(-ENOMEM);
-
-	memcpy(image + desc->bootloader_start_offset, bl_data,
-	       bl_desc->code_size);
-	memcpy(image + desc->app_start_offset, code->data, code->size);
-	memcpy(image + desc->app_start_offset + desc->app_resident_data_offset,
-	       data->data, data->size);
-
-	return image;
-}
-
-/**
- * ls_ucode_img_load_gr() - load and prepare a LS GR ucode image
- *
- * Load the LS microcode, bootloader and signature and pack them into a single
- * blob. Also generate the corresponding ucode descriptor.
- */
-static int
-ls_ucode_img_load_gr(const struct nvkm_subdev *subdev, int maxver,
-		     struct ls_ucode_img *img, const char *falcon_name)
-{
-	const struct firmware *bl, *code, *data, *sig;
-	char f[64];
-	int ret;
-
-	snprintf(f, sizeof(f), "gr/%s_bl", falcon_name);
-	ret = nvkm_firmware_get(subdev, f, &bl);
-	if (ret)
-		goto error;
-
-	snprintf(f, sizeof(f), "gr/%s_inst", falcon_name);
-	ret = nvkm_firmware_get(subdev, f, &code);
-	if (ret)
-		goto free_bl;
-
-	snprintf(f, sizeof(f), "gr/%s_data", falcon_name);
-	ret = nvkm_firmware_get(subdev, f, &data);
-	if (ret)
-		goto free_inst;
-
-	snprintf(f, sizeof(f), "gr/%s_sig", falcon_name);
-	ret = nvkm_firmware_get(subdev, f, &sig);
-	if (ret)
-		goto free_data;
-
-	img->sig = kmemdup(sig->data, sig->size, GFP_KERNEL);
-	if (!img->sig) {
-		ret = -ENOMEM;
-		goto free_sig;
-	}
-	img->sig_size = sig->size;
-
-	img->ucode_data = ls_ucode_img_build(bl, code, data,
-					     &img->ucode_desc);
-	if (IS_ERR(img->ucode_data)) {
-		kfree(img->sig);
-		ret = PTR_ERR(img->ucode_data);
-		goto free_sig;
-	}
-	img->ucode_size = img->ucode_desc.image_size;
-
-free_sig:
-	nvkm_firmware_put(sig);
-free_data:
-	nvkm_firmware_put(data);
-free_inst:
-	nvkm_firmware_put(code);
-free_bl:
-	nvkm_firmware_put(bl);
-error:
-	return ret;
-}
-
-int
-acr_ls_ucode_load_fecs(const struct nvkm_secboot *sb, int maxver,
-		       struct ls_ucode_img *img)
-{
-	return ls_ucode_img_load_gr(&sb->subdev, maxver, img, "fecs");
-}
-
-int
-acr_ls_ucode_load_gpccs(const struct nvkm_secboot *sb, int maxver,
-			struct ls_ucode_img *img)
-{
-	return ls_ucode_img_load_gr(&sb->subdev, maxver, img, "gpccs");
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c
deleted file mode 100644
index a84a999445bb..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/ls_ucode_msgqueue.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-
-#include "ls_ucode.h"
-#include "acr.h"
-
-#include <core/firmware.h>
-#include <core/msgqueue.h>
-#include <subdev/pmu.h>
-#include <engine/sec2.h>
-#include <subdev/mc.h>
-#include <subdev/timer.h>
-
-/**
- * acr_ls_ucode_load_msgqueue - load and prepare a ucode img for a msgqueue fw
- *
- * Load the LS microcode, desc and signature and pack them into a single
- * blob.
- */
-static int
-acr_ls_ucode_load_msgqueue(const struct nvkm_subdev *subdev, const char *name,
-			   int maxver, struct ls_ucode_img *img)
-{
-	const struct firmware *image, *desc, *sig;
-	char f[64];
-	int ver, ret;
-
-	snprintf(f, sizeof(f), "%s/image", name);
-	ver = nvkm_firmware_get_version(subdev, f, 0, maxver, &image);
-	if (ver < 0)
-		return ver;
-	img->ucode_data = kmemdup(image->data, image->size, GFP_KERNEL);
-	nvkm_firmware_put(image);
-	if (!img->ucode_data)
-		return -ENOMEM;
-
-	snprintf(f, sizeof(f), "%s/desc", name);
-	ret = nvkm_firmware_get_version(subdev, f, ver, ver, &desc);
-	if (ret < 0)
-		return ret;
-	memcpy(&img->ucode_desc, desc->data, sizeof(img->ucode_desc));
-	img->ucode_size = ALIGN(img->ucode_desc.app_start_offset + img->ucode_desc.app_size, 256);
-	nvkm_firmware_put(desc);
-
-	snprintf(f, sizeof(f), "%s/sig", name);
-	ret = nvkm_firmware_get_version(subdev, f, ver, ver, &sig);
-	if (ret < 0)
-		return ret;
-	img->sig_size = sig->size;
-	img->sig = kmemdup(sig->data, sig->size, GFP_KERNEL);
-	nvkm_firmware_put(sig);
-	if (!img->sig)
-		return -ENOMEM;
-
-	return ver;
-}
-
-static int
-acr_ls_msgqueue_post_run(struct nvkm_msgqueue *queue,
-			 struct nvkm_falcon *falcon, u32 addr_args)
-{
-	struct nvkm_device *device = falcon->owner->device;
-	u8 buf[NVKM_MSGQUEUE_CMDLINE_SIZE];
-
-	memset(buf, 0, sizeof(buf));
-	nvkm_msgqueue_write_cmdline(queue, buf);
-	nvkm_falcon_load_dmem(falcon, buf, addr_args, sizeof(buf), 0);
-	/* rearm the queue so it will wait for the init message */
-	nvkm_msgqueue_reinit(queue);
-
-	/* Enable interrupts */
-	nvkm_falcon_wr32(falcon, 0x10, 0xff);
-	nvkm_mc_intr_mask(device, falcon->owner->index, true);
-
-	/* Start LS firmware on boot falcon */
-	nvkm_falcon_start(falcon);
-
-	return 0;
-}
-
-int
-acr_ls_ucode_load_pmu(const struct nvkm_secboot *sb, int maxver,
-		      struct ls_ucode_img *img)
-{
-	struct nvkm_pmu *pmu = sb->subdev.device->pmu;
-	int ret;
-
-	ret = acr_ls_ucode_load_msgqueue(&sb->subdev, "pmu", maxver, img);
-	if (ret)
-		return ret;
-
-	/* Allocate the PMU queue corresponding to the FW version */
-	ret = nvkm_msgqueue_new(img->ucode_desc.app_version, pmu->falcon,
-				sb, &pmu->queue);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
-int
-acr_ls_pmu_post_run(const struct nvkm_acr *acr, const struct nvkm_secboot *sb)
-{
-	struct nvkm_device *device = sb->subdev.device;
-	struct nvkm_pmu *pmu = device->pmu;
-	u32 addr_args = pmu->falcon->data.limit - NVKM_MSGQUEUE_CMDLINE_SIZE;
-	int ret;
-
-	ret = acr_ls_msgqueue_post_run(pmu->queue, pmu->falcon, addr_args);
-	if (ret)
-		return ret;
-
-	nvkm_debug(&sb->subdev, "%s started\n",
-		   nvkm_secboot_falcon_name[acr->boot_falcon]);
-
-	return 0;
-}
-
-int
-acr_ls_ucode_load_sec2(const struct nvkm_secboot *sb, int maxver,
-		       struct ls_ucode_img *img)
-{
-	struct nvkm_sec2 *sec = sb->subdev.device->sec2;
-	int ver, ret;
-
-	ver = acr_ls_ucode_load_msgqueue(&sb->subdev, "sec2", maxver, img);
-	if (ver < 0)
-		return ver;
-
-	/* Allocate the PMU queue corresponding to the FW version */
-	ret = nvkm_msgqueue_new(img->ucode_desc.app_version, sec->falcon,
-				sb, &sec->queue);
-	if (ret)
-		return ret;
-
-	return ver;
-}
-
-int
-acr_ls_sec2_post_run(const struct nvkm_acr *acr, const struct nvkm_secboot *sb)
-{
-	const struct nvkm_subdev *subdev = &sb->subdev;
-	struct nvkm_device *device = subdev->device;
-	struct nvkm_sec2 *sec = device->sec2;
-	/* on SEC arguments are always at the beginning of EMEM */
-	const u32 addr_args = 0x01000000;
-	int ret;
-
-	ret = acr_ls_msgqueue_post_run(sec->queue, sec->falcon, addr_args);
-	if (ret)
-		return ret;
-
-	nvkm_debug(&sb->subdev, "%s started\n",
-		   nvkm_secboot_falcon_name[acr->boot_falcon]);
-
-	return 0;
-}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
deleted file mode 100644
index 959a7b2dbdc9..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/priv.h
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- * Copyright (c) 2015, NVIDIA CORPORATION. All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-#ifndef __NVKM_SECBOOT_PRIV_H__
-#define __NVKM_SECBOOT_PRIV_H__
-
-#include <subdev/secboot.h>
-#include <subdev/mmu.h>
-struct nvkm_gpuobj;
-
-struct nvkm_secboot_func {
-	int (*oneinit)(struct nvkm_secboot *);
-	int (*fini)(struct nvkm_secboot *, bool suspend);
-	void *(*dtor)(struct nvkm_secboot *);
-	int (*run_blob)(struct nvkm_secboot *, struct nvkm_gpuobj *,
-			struct nvkm_falcon *);
-};
-
-int nvkm_secboot_ctor(const struct nvkm_secboot_func *, struct nvkm_acr *,
-		      struct nvkm_device *, int, struct nvkm_secboot *);
-int nvkm_secboot_falcon_reset(struct nvkm_secboot *);
-int nvkm_secboot_falcon_run(struct nvkm_secboot *);
-
-extern const struct nvkm_secboot_func gp102_secboot;
-
-struct flcn_u64 {
-	u32 lo;
-	u32 hi;
-};
-
-static inline u64 flcn64_to_u64(const struct flcn_u64 f)
-{
-	return ((u64)f.hi) << 32 | f.lo;
-}
-
-static inline struct flcn_u64 u64_to_flcn64(u64 u)
-{
-	struct flcn_u64 ret;
-
-	ret.hi = upper_32_bits(u);
-	ret.lo = lower_32_bits(u);
-
-	return ret;
-}
-
-#endif
diff --git a/drivers/gpu/drm/omapdrm/displays/Kconfig b/drivers/gpu/drm/omapdrm/displays/Kconfig
index 240dda102845..b562a8cd61bf 100644
--- a/drivers/gpu/drm/omapdrm/displays/Kconfig
+++ b/drivers/gpu/drm/omapdrm/displays/Kconfig
@@ -8,18 +8,18 @@ config DRM_OMAP_ENCODER_OPA362
 	  through a GPIO.
 
 config DRM_OMAP_ENCODER_TPD12S015
-        tristate "TPD12S015 HDMI ESD protection and level shifter"
+	tristate "TPD12S015 HDMI ESD protection and level shifter"
 	help
 	  Driver for TPD12S015, which offers HDMI ESD protection and level
 	  shifting.
 
 config DRM_OMAP_CONNECTOR_HDMI
-        tristate "HDMI Connector"
+	tristate "HDMI Connector"
 	help
 	  Driver for a generic HDMI connector.
 
 config DRM_OMAP_CONNECTOR_ANALOG_TV
-        tristate "Analog TV Connector"
+	tristate "Analog TV Connector"
 	help
 	  Driver for a generic analog TV connector.
 
diff --git a/drivers/gpu/drm/omapdrm/dss/Kconfig b/drivers/gpu/drm/omapdrm/dss/Kconfig
index 956f23e1452d..72ae79c0c9b4 100644
--- a/drivers/gpu/drm/omapdrm/dss/Kconfig
+++ b/drivers/gpu/drm/omapdrm/dss/Kconfig
@@ -6,12 +6,12 @@ config OMAP_DSS_BASE
 	tristate
 
 menuconfig OMAP2_DSS
-        tristate "OMAP2+ Display Subsystem support"
+	tristate "OMAP2+ Display Subsystem support"
 	select OMAP_DSS_BASE
 	select VIDEOMODE_HELPERS
 	select OMAP2_DSS_INIT
 	select HDMI
-        help
+	help
 	  OMAP2+ Display Subsystem support.
 
 if OMAP2_DSS
@@ -52,7 +52,7 @@ config OMAP2_DSS_DPI
 
 config OMAP2_DSS_VENC
 	bool "VENC support"
-        default y
+	default y
 	help
 	  OMAP Video Encoder support for S-Video and composite TV-out.
 
@@ -61,7 +61,7 @@ config OMAP2_DSS_HDMI_COMMON
 
 config OMAP4_DSS_HDMI
 	bool "HDMI support for OMAP4"
-        default y
+	default y
 	select OMAP2_DSS_HDMI_COMMON
 	help
 	  HDMI support for OMAP4 based SoCs.
@@ -85,7 +85,7 @@ config OMAP5_DSS_HDMI
 
 config OMAP2_DSS_SDI
 	bool "SDI support"
-        default n
+	default n
 	help
 	  SDI (Serial Display Interface) support.
 
@@ -94,7 +94,7 @@ config OMAP2_DSS_SDI
 
 config OMAP2_DSS_DSI
 	bool "DSI support"
-        default n
+	default n
 	help
 	  MIPI DSI (Display Serial Interface) support.
 
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index 413dbdd1771e..dbb90f2d2ccd 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -393,8 +393,7 @@ static void dispc_get_reg_field(struct dispc_device *dispc,
 				enum dispc_feat_reg_field id,
 				u8 *start, u8 *end)
 {
-	if (id >= dispc->feat->num_reg_fields)
-		BUG();
+	BUG_ON(id >= dispc->feat->num_reg_fields);
 
 	*start = dispc->feat->reg_fields[id].start;
 	*end = dispc->feat->reg_fields[id].end;
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index 5b8799c69f68..94cded387174 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -229,7 +229,8 @@ static int omap_connector_get_modes(struct drm_connector *connector)
 	 * operation to the panel API.
 	 */
 	if (omap_connector->output->panel)
-		return drm_panel_get_modes(omap_connector->output->panel);
+		return drm_panel_get_modes(omap_connector->output->panel,
+					   connector);
 
 	/*
 	 * We can't retrieve modes, which can happen for instance for a DVI or
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index b3e22c890c51..d2750f60f519 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -217,8 +217,8 @@ static int omap_display_id(struct omap_dss_device *output)
 	} else if (output->bridge) {
 		struct drm_bridge *bridge = output->bridge;
 
-		while (bridge->next)
-			bridge = bridge->next;
+		while (drm_bridge_get_next_bridge(bridge))
+			bridge = drm_bridge_get_next_bridge(bridge);
 
 		node = bridge->of_node;
 	} else if (output->panel) {
diff --git a/drivers/gpu/drm/omapdrm/omap_encoder.c b/drivers/gpu/drm/omapdrm/omap_encoder.c
index 24bbe9f2a32e..4f2165a37795 100644
--- a/drivers/gpu/drm/omapdrm/omap_encoder.c
+++ b/drivers/gpu/drm/omapdrm/omap_encoder.c
@@ -126,7 +126,8 @@ static void omap_encoder_mode_set(struct drm_encoder *encoder,
 	for (dssdev = output; dssdev; dssdev = dssdev->next)
 		omap_encoder_update_videomode_flags(&vm, dssdev->bus_flags);
 
-	for (bridge = output->bridge; bridge; bridge = bridge->next) {
+	for (bridge = output->bridge; bridge;
+	     bridge = drm_bridge_get_next_bridge(bridge)) {
 		if (!bridge->timings)
 			continue;
 
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index 58f53946ee4d..b06e5cbfd03a 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -70,7 +70,7 @@ fallback:
 	return drm_fb_helper_pan_display(var, fbi);
 }
 
-static struct fb_ops omap_fb_ops = {
+static const struct fb_ops omap_fb_ops = {
 	.owner = THIS_MODULE,
 
 	.fb_check_var	= drm_fb_helper_check_var,
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index 7344bb61936c..b319fe7f2371 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -85,25 +85,6 @@ static int omap_gem_dmabuf_end_cpu_access(struct dma_buf *buffer,
 	return 0;
 }
 
-static void *omap_gem_dmabuf_kmap(struct dma_buf *buffer,
-		unsigned long page_num)
-{
-	struct drm_gem_object *obj = buffer->priv;
-	struct page **pages;
-	omap_gem_get_pages(obj, &pages, false);
-	omap_gem_cpu_sync_page(obj, page_num);
-	return kmap(pages[page_num]);
-}
-
-static void omap_gem_dmabuf_kunmap(struct dma_buf *buffer,
-		unsigned long page_num, void *addr)
-{
-	struct drm_gem_object *obj = buffer->priv;
-	struct page **pages;
-	omap_gem_get_pages(obj, &pages, false);
-	kunmap(pages[page_num]);
-}
-
 static int omap_gem_dmabuf_mmap(struct dma_buf *buffer,
 		struct vm_area_struct *vma)
 {
@@ -123,8 +104,6 @@ static const struct dma_buf_ops omap_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = omap_gem_dmabuf_begin_cpu_access,
 	.end_cpu_access = omap_gem_dmabuf_end_cpu_access,
-	.map = omap_gem_dmabuf_kmap,
-	.unmap = omap_gem_dmabuf_kunmap,
 	.mmap = omap_gem_dmabuf_mmap,
 };
 
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index f152bc4eeb53..ae44ac2ec106 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -18,6 +18,17 @@ config DRM_PANEL_ARM_VERSATILE
 	  reference designs. The panel is detected using special registers
 	  in the Versatile family syscon registers.
 
+config DRM_PANEL_BOE_HIMAX8279D
+	tristate "Boe Himax8279d panel"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	help
+	  Say Y here if you want to enable support for Boe Himax8279d
+	  TFT-LCD modules. The panel has a 1200x1920 resolution and uses
+	  24 bit RGB per pixel. It provides a MIPI DSI interface to
+	  the host and has a built-in LED backlight.
+
 config DRM_PANEL_LVDS
 	tristate "Generic LVDS panel driver"
 	depends on OF
@@ -98,6 +109,17 @@ config DRM_PANEL_KINGDISPLAY_KD097D04
 	  24 bit RGB per pixel. It provides a MIPI DSI interface to
 	  the host and has a built-in LED backlight.
 
+config DRM_PANEL_LEADTEK_LTK500HD1829
+	tristate "Leadtek LTK500HD1829 panel"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	help
+	  Say Y here if you want to enable support for Kingdisplay kd097d04
+	  TFT-LCD modules. The panel has a 1536x2048 resolution and uses
+	  24 bit RGB per pixel. It provides a MIPI DSI interface to
+	  the host and has a built-in LED backlight.
+
 config DRM_PANEL_SAMSUNG_LD9040
 	tristate "Samsung LD9040 RGB/SPI panel"
 	depends on OF && SPI
@@ -316,6 +338,17 @@ config DRM_PANEL_SITRONIX_ST7789V
 	  Say Y here if you want to enable support for the Sitronix
 	  ST7789V controller for 240x320 LCD panels
 
+config DRM_PANEL_SONY_ACX424AKP
+	tristate "Sony ACX424AKP DSI command mode panel"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	select VIDEOMODE_HELPERS
+	help
+	  Say Y here if you want to enable the Sony ACX424 display
+	  panel. This panel supports DSI in both command and video
+	  mode.
+
 config DRM_PANEL_SONY_ACX565AKM
 	tristate "Sony ACX565AKM panel"
 	depends on GPIOLIB && OF && SPI
@@ -355,4 +388,14 @@ config DRM_PANEL_TRULY_NT35597_WQXGA
 	help
 	  Say Y here if you want to enable support for Truly NT35597 WQXGA Dual DSI
 	  Video Mode panel
+
+config DRM_PANEL_XINPENG_XPP055C272
+	tristate "Xinpeng XPP055C272 panel driver"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	help
+	  Say Y here if you want to enable support for the Xinpeng
+	  XPP055C272 controller for 720x1280 LCD panels with MIPI/RGB/SPI
+	  system interfaces.
 endmenu
diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile
index b6cd39fe0f20..7c4d3c581fd4 100644
--- a/drivers/gpu/drm/panel/Makefile
+++ b/drivers/gpu/drm/panel/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DRM_PANEL_ARM_VERSATILE) += panel-arm-versatile.o
+obj-$(CONFIG_DRM_PANEL_BOE_HIMAX8279D) += panel-boe-himax8279d.o
 obj-$(CONFIG_DRM_PANEL_LVDS) += panel-lvds.o
 obj-$(CONFIG_DRM_PANEL_SIMPLE) += panel-simple.o
 obj-$(CONFIG_DRM_PANEL_FEIYANG_FY07024DI26A30D) += panel-feiyang-fy07024di26a30d.o
@@ -8,6 +9,7 @@ obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o
 obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o
 obj-$(CONFIG_DRM_PANEL_JDI_LT070ME05000) += panel-jdi-lt070me05000.o
 obj-$(CONFIG_DRM_PANEL_KINGDISPLAY_KD097D04) += panel-kingdisplay-kd097d04.o
+obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK500HD1829) += panel-leadtek-ltk500hd1829.o
 obj-$(CONFIG_DRM_PANEL_LG_LB035Q02) += panel-lg-lb035q02.o
 obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o
 obj-$(CONFIG_DRM_PANEL_NEC_NL8048HL11) += panel-nec-nl8048hl11.o
@@ -33,8 +35,10 @@ obj-$(CONFIG_DRM_PANEL_SHARP_LS037V7DW01) += panel-sharp-ls037v7dw01.o
 obj-$(CONFIG_DRM_PANEL_SHARP_LS043T1LE01) += panel-sharp-ls043t1le01.o
 obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7701) += panel-sitronix-st7701.o
 obj-$(CONFIG_DRM_PANEL_SITRONIX_ST7789V) += panel-sitronix-st7789v.o
+obj-$(CONFIG_DRM_PANEL_SONY_ACX424AKP) += panel-sony-acx424akp.o
 obj-$(CONFIG_DRM_PANEL_SONY_ACX565AKM) += panel-sony-acx565akm.o
 obj-$(CONFIG_DRM_PANEL_TPO_TD028TTEC1) += panel-tpo-td028ttec1.o
 obj-$(CONFIG_DRM_PANEL_TPO_TD043MTEA1) += panel-tpo-td043mtea1.o
 obj-$(CONFIG_DRM_PANEL_TPO_TPG110) += panel-tpo-tpg110.o
 obj-$(CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA) += panel-truly-nt35597.o
+obj-$(CONFIG_DRM_PANEL_XINPENG_XPP055C272) += panel-xinpeng-xpp055c272.o
diff --git a/drivers/gpu/drm/panel/panel-arm-versatile.c b/drivers/gpu/drm/panel/panel-arm-versatile.c
index a0574dc03e16..41444a73c980 100644
--- a/drivers/gpu/drm/panel/panel-arm-versatile.c
+++ b/drivers/gpu/drm/panel/panel-arm-versatile.c
@@ -260,9 +260,9 @@ static int versatile_panel_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int versatile_panel_get_modes(struct drm_panel *panel)
+static int versatile_panel_get_modes(struct drm_panel *panel,
+				     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct versatile_panel *vpanel = to_versatile_panel(panel);
 	struct drm_display_mode *mode;
 
@@ -270,7 +270,7 @@ static int versatile_panel_get_modes(struct drm_panel *panel)
 	connector->display_info.height_mm = vpanel->panel_type->height_mm;
 	connector->display_info.bus_flags = vpanel->panel_type->bus_flags;
 
-	mode = drm_mode_duplicate(panel->drm, &vpanel->panel_type->mode);
+	mode = drm_mode_duplicate(connector->dev, &vpanel->panel_type->mode);
 	drm_mode_set_name(mode);
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
 
diff --git a/drivers/gpu/drm/panel/panel-boe-himax8279d.c b/drivers/gpu/drm/panel/panel-boe-himax8279d.c
new file mode 100644
index 000000000000..74d58ee7d04c
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-boe-himax8279d.c
@@ -0,0 +1,978 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019, Huaqin Telecom Technology Co., Ltd
+ *
+ * Author: Jerry Han <jerry.han.hq@gmail.com>
+ *
+ */
+
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+
+#include <drm/drm_device.h>
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+
+#include <video/mipi_display.h>
+
+struct panel_cmd {
+	char cmd;
+	char data;
+};
+
+struct panel_desc {
+	const struct drm_display_mode *display_mode;
+	unsigned int bpc;
+	unsigned int width_mm;
+	unsigned int height_mm;
+
+	unsigned long mode_flags;
+	enum mipi_dsi_pixel_format format;
+	unsigned int lanes;
+	const struct panel_cmd *on_cmds;
+	unsigned int on_cmds_num;
+};
+
+struct panel_info {
+	struct drm_panel base;
+	struct mipi_dsi_device *link;
+	const struct panel_desc *desc;
+
+	struct gpio_desc *enable_gpio;
+	struct gpio_desc *pp33_gpio;
+	struct gpio_desc *pp18_gpio;
+
+	bool prepared;
+	bool enabled;
+};
+
+static inline struct panel_info *to_panel_info(struct drm_panel *panel)
+{
+	return container_of(panel, struct panel_info, base);
+}
+
+static void disable_gpios(struct panel_info *pinfo)
+{
+	gpiod_set_value(pinfo->enable_gpio, 0);
+	gpiod_set_value(pinfo->pp33_gpio, 0);
+	gpiod_set_value(pinfo->pp18_gpio, 0);
+}
+
+static int send_mipi_cmds(struct drm_panel *panel, const struct panel_cmd *cmds)
+{
+	struct panel_info *pinfo = to_panel_info(panel);
+	unsigned int i = 0;
+	int err;
+
+	for (i = 0; i < pinfo->desc->on_cmds_num; i++) {
+		err = mipi_dsi_dcs_write_buffer(pinfo->link, &cmds[i],
+						sizeof(struct panel_cmd));
+
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int boe_panel_disable(struct drm_panel *panel)
+{
+	struct panel_info *pinfo = to_panel_info(panel);
+	int err;
+
+	if (!pinfo->enabled)
+		return 0;
+
+	err = mipi_dsi_dcs_set_display_off(pinfo->link);
+	if (err < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to set display off: %d\n",
+			      err);
+		return err;
+	}
+
+	pinfo->enabled = false;
+
+	return 0;
+}
+
+static int boe_panel_unprepare(struct drm_panel *panel)
+{
+	struct panel_info *pinfo = to_panel_info(panel);
+	int err;
+
+	if (!pinfo->prepared)
+		return 0;
+
+	err = mipi_dsi_dcs_set_display_off(pinfo->link);
+	if (err < 0)
+		DRM_DEV_ERROR(panel->dev, "failed to set display off: %d\n",
+			      err);
+
+	err = mipi_dsi_dcs_enter_sleep_mode(pinfo->link);
+	if (err < 0)
+		DRM_DEV_ERROR(panel->dev, "failed to enter sleep mode: %d\n",
+			      err);
+
+	/* sleep_mode_delay: 1ms - 2ms */
+	usleep_range(1000, 2000);
+
+	disable_gpios(pinfo);
+
+	pinfo->prepared = false;
+
+	return 0;
+}
+
+static int boe_panel_prepare(struct drm_panel *panel)
+{
+	struct panel_info *pinfo = to_panel_info(panel);
+	int err;
+
+	if (pinfo->prepared)
+		return 0;
+
+	gpiod_set_value(pinfo->pp18_gpio, 1);
+	/* T1: 5ms - 6ms */
+	usleep_range(5000, 6000);
+	gpiod_set_value(pinfo->pp33_gpio, 1);
+
+	/* reset sequence */
+	/* T2: 14ms - 15ms */
+	usleep_range(14000, 15000);
+	gpiod_set_value(pinfo->enable_gpio, 1);
+
+	/* T3: 1ms - 2ms */
+	usleep_range(1000, 2000);
+	gpiod_set_value(pinfo->enable_gpio, 0);
+
+	/* T4: 1ms - 2ms */
+	usleep_range(1000, 2000);
+	gpiod_set_value(pinfo->enable_gpio, 1);
+
+	/* T5: 5ms - 6ms */
+	usleep_range(5000, 6000);
+
+	/* send init code */
+	err = send_mipi_cmds(panel, pinfo->desc->on_cmds);
+	if (err < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to send DCS Init Code: %d\n",
+			      err);
+		goto poweroff;
+	}
+
+	err = mipi_dsi_dcs_exit_sleep_mode(pinfo->link);
+	if (err < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to exit sleep mode: %d\n",
+			      err);
+		goto poweroff;
+	}
+
+	/* T6: 120ms - 121ms */
+	usleep_range(120000, 121000);
+
+	err = mipi_dsi_dcs_set_display_on(pinfo->link);
+	if (err < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to set display on: %d\n",
+			      err);
+		goto poweroff;
+	}
+
+	/* T7: 20ms - 21ms */
+	usleep_range(20000, 21000);
+
+	pinfo->prepared = true;
+
+	return 0;
+
+poweroff:
+	disable_gpios(pinfo);
+	return err;
+}
+
+static int boe_panel_enable(struct drm_panel *panel)
+{
+	struct panel_info *pinfo = to_panel_info(panel);
+	int ret;
+
+	if (pinfo->enabled)
+		return 0;
+
+	usleep_range(120000, 121000);
+
+	ret = mipi_dsi_dcs_set_display_on(pinfo->link);
+	if (ret < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to set display on: %d\n",
+			      ret);
+		return ret;
+	}
+
+	pinfo->enabled = true;
+
+	return 0;
+}
+
+static int boe_panel_get_modes(struct drm_panel *panel,
+			       struct drm_connector *connector)
+{
+	struct panel_info *pinfo = to_panel_info(panel);
+	const struct drm_display_mode *m = pinfo->desc->display_mode;
+	struct drm_display_mode *mode;
+
+	mode = drm_mode_duplicate(connector->dev, m);
+	if (!mode) {
+		DRM_DEV_ERROR(pinfo->base.dev, "failed to add mode %ux%u@%u\n",
+			      m->hdisplay, m->vdisplay, m->vrefresh);
+		return -ENOMEM;
+	}
+
+	drm_mode_set_name(mode);
+
+	drm_mode_probed_add(connector, mode);
+
+	connector->display_info.width_mm = pinfo->desc->width_mm;
+	connector->display_info.height_mm = pinfo->desc->height_mm;
+	connector->display_info.bpc = pinfo->desc->bpc;
+
+	return 1;
+}
+
+static const struct drm_panel_funcs panel_funcs = {
+	.disable = boe_panel_disable,
+	.unprepare = boe_panel_unprepare,
+	.prepare = boe_panel_prepare,
+	.enable = boe_panel_enable,
+	.get_modes = boe_panel_get_modes,
+};
+
+static const struct drm_display_mode default_display_mode = {
+	.clock = 159420,
+	.hdisplay = 1200,
+	.hsync_start = 1200 + 80,
+	.hsync_end = 1200 + 80 + 60,
+	.htotal = 1200 + 80 + 60 + 24,
+	.vdisplay = 1920,
+	.vsync_start = 1920 + 10,
+	.vsync_end = 1920 + 10 + 14,
+	.vtotal = 1920 + 10 + 14 + 4,
+	.vrefresh = 60,
+};
+
+/* 8 inch */
+static const struct panel_cmd boe_himax8279d8p_on_cmds[] = {
+	{ 0xB0, 0x05 },
+	{ 0xB1, 0xE5 },
+	{ 0xB3, 0x52 },
+	{ 0xC0, 0x00 },
+	{ 0xC2, 0x57 },
+	{ 0xD9, 0x85 },
+	{ 0xB0, 0x01 },
+	{ 0xC8, 0x00 },
+	{ 0xC9, 0x00 },
+	{ 0xCC, 0x26 },
+	{ 0xCD, 0x26 },
+	{ 0xDC, 0x00 },
+	{ 0xDD, 0x00 },
+	{ 0xE0, 0x26 },
+	{ 0xE1, 0x26 },
+	{ 0xB0, 0x03 },
+	{ 0xC3, 0x2A },
+	{ 0xE7, 0x2A },
+	{ 0xC5, 0x2A },
+	{ 0xDE, 0x2A },
+	{ 0xBC, 0x02 },
+	{ 0xCB, 0x02 },
+	{ 0xB0, 0x00 },
+	{ 0xB6, 0x03 },
+	{ 0xBA, 0x8B },
+	{ 0xBF, 0x15 },
+	{ 0xC0, 0x18 },
+	{ 0xC2, 0x14 },
+	{ 0xC3, 0x02 },
+	{ 0xC4, 0x14 },
+	{ 0xC5, 0x02 },
+	{ 0xCC, 0x0A },
+	{ 0xB0, 0x06 },
+	{ 0xC0, 0xA5 },
+	{ 0xD5, 0x20 },
+	{ 0xC0, 0x00 },
+	{ 0xB0, 0x02 },
+	{ 0xC0, 0x00 },
+	{ 0xC1, 0x02 },
+	{ 0xC2, 0x06 },
+	{ 0xC3, 0x16 },
+	{ 0xC4, 0x0E },
+	{ 0xC5, 0x18 },
+	{ 0xC6, 0x26 },
+	{ 0xC7, 0x32 },
+	{ 0xC8, 0x3F },
+	{ 0xC9, 0x3F },
+	{ 0xCA, 0x3F },
+	{ 0xCB, 0x3F },
+	{ 0xCC, 0x3D },
+	{ 0xCD, 0x2F },
+	{ 0xCE, 0x2F },
+	{ 0xCF, 0x2F },
+	{ 0xD0, 0x07 },
+	{ 0xD2, 0x00 },
+	{ 0xD3, 0x02 },
+	{ 0xD4, 0x06 },
+	{ 0xD5, 0x12 },
+	{ 0xD6, 0x0A },
+	{ 0xD7, 0x14 },
+	{ 0xD8, 0x22 },
+	{ 0xD9, 0x2E },
+	{ 0xDA, 0x3D },
+	{ 0xDB, 0x3F },
+	{ 0xDC, 0x3F },
+	{ 0xDD, 0x3F },
+	{ 0xDE, 0x3D },
+	{ 0xDF, 0x2F },
+	{ 0xE0, 0x2F },
+	{ 0xE1, 0x2F },
+	{ 0xE2, 0x07 },
+	{ 0xB0, 0x07 },
+	{ 0xB1, 0x18 },
+	{ 0xB2, 0x19 },
+	{ 0xB3, 0x2E },
+	{ 0xB4, 0x52 },
+	{ 0xB5, 0x72 },
+	{ 0xB6, 0x8C },
+	{ 0xB7, 0xBD },
+	{ 0xB8, 0xEB },
+	{ 0xB9, 0x47 },
+	{ 0xBA, 0x96 },
+	{ 0xBB, 0x1E },
+	{ 0xBC, 0x90 },
+	{ 0xBD, 0x93 },
+	{ 0xBE, 0xFA },
+	{ 0xBF, 0x56 },
+	{ 0xC0, 0x8C },
+	{ 0xC1, 0xB7 },
+	{ 0xC2, 0xCC },
+	{ 0xC3, 0xDF },
+	{ 0xC4, 0xE8 },
+	{ 0xC5, 0xF0 },
+	{ 0xC6, 0xF8 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x5A },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x08 },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x15 },
+	{ 0xB3, 0x2D },
+	{ 0xB4, 0x51 },
+	{ 0xB5, 0x72 },
+	{ 0xB6, 0x8D },
+	{ 0xB7, 0xBE },
+	{ 0xB8, 0xED },
+	{ 0xB9, 0x4A },
+	{ 0xBA, 0x9A },
+	{ 0xBB, 0x23 },
+	{ 0xBC, 0x95 },
+	{ 0xBD, 0x98 },
+	{ 0xBE, 0xFF },
+	{ 0xBF, 0x59 },
+	{ 0xC0, 0x8E },
+	{ 0xC1, 0xB9 },
+	{ 0xC2, 0xCD },
+	{ 0xC3, 0xDF },
+	{ 0xC4, 0xE8 },
+	{ 0xC5, 0xF0 },
+	{ 0xC6, 0xF8 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x5A },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x09 },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x2C },
+	{ 0xB3, 0x36 },
+	{ 0xB4, 0x53 },
+	{ 0xB5, 0x73 },
+	{ 0xB6, 0x8E },
+	{ 0xB7, 0xC0 },
+	{ 0xB8, 0xEF },
+	{ 0xB9, 0x4C },
+	{ 0xBA, 0x9D },
+	{ 0xBB, 0x25 },
+	{ 0xBC, 0x96 },
+	{ 0xBD, 0x9A },
+	{ 0xBE, 0x01 },
+	{ 0xBF, 0x59 },
+	{ 0xC0, 0x8E },
+	{ 0xC1, 0xB9 },
+	{ 0xC2, 0xCD },
+	{ 0xC3, 0xDF },
+	{ 0xC4, 0xE8 },
+	{ 0xC5, 0xF0 },
+	{ 0xC6, 0xF8 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x5A },
+	{ 0xCC, 0xBF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x0A },
+	{ 0xB1, 0x18 },
+	{ 0xB2, 0x19 },
+	{ 0xB3, 0x2E },
+	{ 0xB4, 0x52 },
+	{ 0xB5, 0x72 },
+	{ 0xB6, 0x8C },
+	{ 0xB7, 0xBD },
+	{ 0xB8, 0xEB },
+	{ 0xB9, 0x47 },
+	{ 0xBA, 0x96 },
+	{ 0xBB, 0x1E },
+	{ 0xBC, 0x90 },
+	{ 0xBD, 0x93 },
+	{ 0xBE, 0xFA },
+	{ 0xBF, 0x56 },
+	{ 0xC0, 0x8C },
+	{ 0xC1, 0xB7 },
+	{ 0xC2, 0xCC },
+	{ 0xC3, 0xDF },
+	{ 0xC4, 0xE8 },
+	{ 0xC5, 0xF0 },
+	{ 0xC6, 0xF8 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x5A },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x0B },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x15 },
+	{ 0xB3, 0x2D },
+	{ 0xB4, 0x51 },
+	{ 0xB5, 0x72 },
+	{ 0xB6, 0x8D },
+	{ 0xB7, 0xBE },
+	{ 0xB8, 0xED },
+	{ 0xB9, 0x4A },
+	{ 0xBA, 0x9A },
+	{ 0xBB, 0x23 },
+	{ 0xBC, 0x95 },
+	{ 0xBD, 0x98 },
+	{ 0xBE, 0xFF },
+	{ 0xBF, 0x59 },
+	{ 0xC0, 0x8E },
+	{ 0xC1, 0xB9 },
+	{ 0xC2, 0xCD },
+	{ 0xC3, 0xDF },
+	{ 0xC4, 0xE8 },
+	{ 0xC5, 0xF0 },
+	{ 0xC6, 0xF8 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x5A },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x0C },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x2C },
+	{ 0xB3, 0x36 },
+	{ 0xB4, 0x53 },
+	{ 0xB5, 0x73 },
+	{ 0xB6, 0x8E },
+	{ 0xB7, 0xC0 },
+	{ 0xB8, 0xEF },
+	{ 0xB9, 0x4C },
+	{ 0xBA, 0x9D },
+	{ 0xBB, 0x25 },
+	{ 0xBC, 0x96 },
+	{ 0xBD, 0x9A },
+	{ 0xBE, 0x01 },
+	{ 0xBF, 0x59 },
+	{ 0xC0, 0x8E },
+	{ 0xC1, 0xB9 },
+	{ 0xC2, 0xCD },
+	{ 0xC3, 0xDF },
+	{ 0xC4, 0xE8 },
+	{ 0xC5, 0xF0 },
+	{ 0xC6, 0xF8 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x5A },
+	{ 0xCC, 0xBF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x04 },
+	{ 0xB5, 0x02 },
+	{ 0xB6, 0x01 },
+};
+
+static const struct panel_desc boe_himax8279d8p_panel_desc = {
+	.display_mode = &default_display_mode,
+	.bpc = 8,
+	.width_mm = 107,
+	.height_mm = 172,
+	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+			MIPI_DSI_CLOCK_NON_CONTINUOUS | MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.lanes = 4,
+	.on_cmds = boe_himax8279d8p_on_cmds,
+	.on_cmds_num = 260,
+};
+
+/* 10 inch */
+static const struct panel_cmd boe_himax8279d10p_on_cmds[] = {
+	{ 0xB0, 0x05 },
+	{ 0xB1, 0xE5 },
+	{ 0xB3, 0x52 },
+	{ 0xB0, 0x00 },
+	{ 0xB6, 0x03 },
+	{ 0xBA, 0x8B },
+	{ 0xBF, 0x1A },
+	{ 0xC0, 0x0F },
+	{ 0xC2, 0x0C },
+	{ 0xC3, 0x02 },
+	{ 0xC4, 0x0C },
+	{ 0xC5, 0x02 },
+	{ 0xB0, 0x01 },
+	{ 0xE0, 0x26 },
+	{ 0xE1, 0x26 },
+	{ 0xDC, 0x00 },
+	{ 0xDD, 0x00 },
+	{ 0xCC, 0x26 },
+	{ 0xCD, 0x26 },
+	{ 0xC8, 0x00 },
+	{ 0xC9, 0x00 },
+	{ 0xD2, 0x03 },
+	{ 0xD3, 0x03 },
+	{ 0xE6, 0x04 },
+	{ 0xE7, 0x04 },
+	{ 0xC4, 0x09 },
+	{ 0xC5, 0x09 },
+	{ 0xD8, 0x0A },
+	{ 0xD9, 0x0A },
+	{ 0xC2, 0x0B },
+	{ 0xC3, 0x0B },
+	{ 0xD6, 0x0C },
+	{ 0xD7, 0x0C },
+	{ 0xC0, 0x05 },
+	{ 0xC1, 0x05 },
+	{ 0xD4, 0x06 },
+	{ 0xD5, 0x06 },
+	{ 0xCA, 0x07 },
+	{ 0xCB, 0x07 },
+	{ 0xDE, 0x08 },
+	{ 0xDF, 0x08 },
+	{ 0xB0, 0x02 },
+	{ 0xC0, 0x00 },
+	{ 0xC1, 0x0D },
+	{ 0xC2, 0x17 },
+	{ 0xC3, 0x26 },
+	{ 0xC4, 0x31 },
+	{ 0xC5, 0x1C },
+	{ 0xC6, 0x2C },
+	{ 0xC7, 0x33 },
+	{ 0xC8, 0x31 },
+	{ 0xC9, 0x37 },
+	{ 0xCA, 0x37 },
+	{ 0xCB, 0x37 },
+	{ 0xCC, 0x39 },
+	{ 0xCD, 0x2E },
+	{ 0xCE, 0x2F },
+	{ 0xCF, 0x2F },
+	{ 0xD0, 0x07 },
+	{ 0xD2, 0x00 },
+	{ 0xD3, 0x0D },
+	{ 0xD4, 0x17 },
+	{ 0xD5, 0x26 },
+	{ 0xD6, 0x31 },
+	{ 0xD7, 0x3F },
+	{ 0xD8, 0x3F },
+	{ 0xD9, 0x3F },
+	{ 0xDA, 0x3F },
+	{ 0xDB, 0x37 },
+	{ 0xDC, 0x37 },
+	{ 0xDD, 0x37 },
+	{ 0xDE, 0x39 },
+	{ 0xDF, 0x2E },
+	{ 0xE0, 0x2F },
+	{ 0xE1, 0x2F },
+	{ 0xE2, 0x07 },
+	{ 0xB0, 0x03 },
+	{ 0xC8, 0x0B },
+	{ 0xC9, 0x07 },
+	{ 0xC3, 0x00 },
+	{ 0xE7, 0x00 },
+	{ 0xC5, 0x2A },
+	{ 0xDE, 0x2A },
+	{ 0xCA, 0x43 },
+	{ 0xC9, 0x07 },
+	{ 0xE4, 0xC0 },
+	{ 0xE5, 0x0D },
+	{ 0xCB, 0x01 },
+	{ 0xBC, 0x01 },
+	{ 0xB0, 0x06 },
+	{ 0xB8, 0xA5 },
+	{ 0xC0, 0xA5 },
+	{ 0xC7, 0x0F },
+	{ 0xD5, 0x32 },
+	{ 0xB8, 0x00 },
+	{ 0xC0, 0x00 },
+	{ 0xBC, 0x00 },
+	{ 0xB0, 0x07 },
+	{ 0xB1, 0x00 },
+	{ 0xB2, 0x05 },
+	{ 0xB3, 0x10 },
+	{ 0xB4, 0x22 },
+	{ 0xB5, 0x36 },
+	{ 0xB6, 0x4A },
+	{ 0xB7, 0x6C },
+	{ 0xB8, 0x9A },
+	{ 0xB9, 0xD7 },
+	{ 0xBA, 0x17 },
+	{ 0xBB, 0x92 },
+	{ 0xBC, 0x15 },
+	{ 0xBD, 0x18 },
+	{ 0xBE, 0x8C },
+	{ 0xBF, 0x00 },
+	{ 0xC0, 0x3A },
+	{ 0xC1, 0x72 },
+	{ 0xC2, 0x8C },
+	{ 0xC3, 0xA5 },
+	{ 0xC4, 0xB1 },
+	{ 0xC5, 0xBE },
+	{ 0xC6, 0xCA },
+	{ 0xC7, 0xD1 },
+	{ 0xC8, 0xD4 },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x16 },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x08 },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x05 },
+	{ 0xB3, 0x11 },
+	{ 0xB4, 0x24 },
+	{ 0xB5, 0x39 },
+	{ 0xB6, 0x4E },
+	{ 0xB7, 0x72 },
+	{ 0xB8, 0xA3 },
+	{ 0xB9, 0xE1 },
+	{ 0xBA, 0x25 },
+	{ 0xBB, 0xA8 },
+	{ 0xBC, 0x2E },
+	{ 0xBD, 0x32 },
+	{ 0xBE, 0xAD },
+	{ 0xBF, 0x28 },
+	{ 0xC0, 0x63 },
+	{ 0xC1, 0x9B },
+	{ 0xC2, 0xB5 },
+	{ 0xC3, 0xCF },
+	{ 0xC4, 0xDB },
+	{ 0xC5, 0xE8 },
+	{ 0xC6, 0xF5 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x16 },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x09 },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x04 },
+	{ 0xB3, 0x0F },
+	{ 0xB4, 0x22 },
+	{ 0xB5, 0x37 },
+	{ 0xB6, 0x4D },
+	{ 0xB7, 0x71 },
+	{ 0xB8, 0xA2 },
+	{ 0xB9, 0xE1 },
+	{ 0xBA, 0x26 },
+	{ 0xBB, 0xA9 },
+	{ 0xBC, 0x2F },
+	{ 0xBD, 0x33 },
+	{ 0xBE, 0xAC },
+	{ 0xBF, 0x24 },
+	{ 0xC0, 0x5D },
+	{ 0xC1, 0x94 },
+	{ 0xC2, 0xAC },
+	{ 0xC3, 0xC5 },
+	{ 0xC4, 0xD1 },
+	{ 0xC5, 0xDC },
+	{ 0xC6, 0xE8 },
+	{ 0xC7, 0xED },
+	{ 0xC8, 0xF0 },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x16 },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x0A },
+	{ 0xB1, 0x00 },
+	{ 0xB2, 0x05 },
+	{ 0xB3, 0x10 },
+	{ 0xB4, 0x22 },
+	{ 0xB5, 0x36 },
+	{ 0xB6, 0x4A },
+	{ 0xB7, 0x6C },
+	{ 0xB8, 0x9A },
+	{ 0xB9, 0xD7 },
+	{ 0xBA, 0x17 },
+	{ 0xBB, 0x92 },
+	{ 0xBC, 0x15 },
+	{ 0xBD, 0x18 },
+	{ 0xBE, 0x8C },
+	{ 0xBF, 0x00 },
+	{ 0xC0, 0x3A },
+	{ 0xC1, 0x72 },
+	{ 0xC2, 0x8C },
+	{ 0xC3, 0xA5 },
+	{ 0xC4, 0xB1 },
+	{ 0xC5, 0xBE },
+	{ 0xC6, 0xCA },
+	{ 0xC7, 0xD1 },
+	{ 0xC8, 0xD4 },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x16 },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x0B },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x05 },
+	{ 0xB3, 0x11 },
+	{ 0xB4, 0x24 },
+	{ 0xB5, 0x39 },
+	{ 0xB6, 0x4E },
+	{ 0xB7, 0x72 },
+	{ 0xB8, 0xA3 },
+	{ 0xB9, 0xE1 },
+	{ 0xBA, 0x25 },
+	{ 0xBB, 0xA8 },
+	{ 0xBC, 0x2E },
+	{ 0xBD, 0x32 },
+	{ 0xBE, 0xAD },
+	{ 0xBF, 0x28 },
+	{ 0xC0, 0x63 },
+	{ 0xC1, 0x9B },
+	{ 0xC2, 0xB5 },
+	{ 0xC3, 0xCF },
+	{ 0xC4, 0xDB },
+	{ 0xC5, 0xE8 },
+	{ 0xC6, 0xF5 },
+	{ 0xC7, 0xFA },
+	{ 0xC8, 0xFC },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x16 },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+	{ 0xB0, 0x0C },
+	{ 0xB1, 0x04 },
+	{ 0xB2, 0x04 },
+	{ 0xB3, 0x0F },
+	{ 0xB4, 0x22 },
+	{ 0xB5, 0x37 },
+	{ 0xB6, 0x4D },
+	{ 0xB7, 0x71 },
+	{ 0xB8, 0xA2 },
+	{ 0xB9, 0xE1 },
+	{ 0xBA, 0x26 },
+	{ 0xBB, 0xA9 },
+	{ 0xBC, 0x2F },
+	{ 0xBD, 0x33 },
+	{ 0xBE, 0xAC },
+	{ 0xBF, 0x24 },
+	{ 0xC0, 0x5D },
+	{ 0xC1, 0x94 },
+	{ 0xC2, 0xAC },
+	{ 0xC3, 0xC5 },
+	{ 0xC4, 0xD1 },
+	{ 0xC5, 0xDC },
+	{ 0xC6, 0xE8 },
+	{ 0xC7, 0xED },
+	{ 0xC8, 0xF0 },
+	{ 0xC9, 0x00 },
+	{ 0xCA, 0x00 },
+	{ 0xCB, 0x16 },
+	{ 0xCC, 0xAF },
+	{ 0xCD, 0xFF },
+	{ 0xCE, 0xFF },
+};
+
+static const struct panel_desc boe_himax8279d10p_panel_desc = {
+	.display_mode = &default_display_mode,
+	.bpc = 8,
+	.width_mm = 135,
+	.height_mm = 216,
+	.mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+			MIPI_DSI_CLOCK_NON_CONTINUOUS | MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.lanes = 4,
+	.on_cmds = boe_himax8279d10p_on_cmds,
+	.on_cmds_num = 283,
+};
+
+static const struct of_device_id panel_of_match[] = {
+	{
+		.compatible = "boe,himax8279d8p",
+		.data = &boe_himax8279d8p_panel_desc,
+	},
+	{
+		.compatible = "boe,himax8279d10p",
+		.data = &boe_himax8279d10p_panel_desc,
+	},
+	{
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(of, panel_of_match);
+
+static int panel_add(struct panel_info *pinfo)
+{
+	struct device *dev = &pinfo->link->dev;
+	int ret;
+
+	pinfo->pp18_gpio = devm_gpiod_get(dev, "pp18", GPIOD_OUT_HIGH);
+	if (IS_ERR(pinfo->pp18_gpio)) {
+		ret = PTR_ERR(pinfo->pp18_gpio);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev, "failed to get pp18 gpio: %d\n",
+				      ret);
+		return ret;
+	}
+
+	pinfo->pp33_gpio = devm_gpiod_get(dev, "pp33", GPIOD_OUT_HIGH);
+	if (IS_ERR(pinfo->pp33_gpio)) {
+		ret = PTR_ERR(pinfo->pp33_gpio);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev, "failed to get pp33 gpio: %d\n",
+				      ret);
+		return ret;
+	}
+
+	pinfo->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_HIGH);
+	if (IS_ERR(pinfo->enable_gpio)) {
+		ret = PTR_ERR(pinfo->enable_gpio);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev, "failed to get enable gpio: %d\n",
+				      ret);
+		return ret;
+	}
+
+	drm_panel_init(&pinfo->base, dev, &panel_funcs,
+		       DRM_MODE_CONNECTOR_DSI);
+
+	ret = drm_panel_of_backlight(&pinfo->base);
+	if (ret)
+		return ret;
+
+	return drm_panel_add(&pinfo->base);
+}
+
+static int panel_probe(struct mipi_dsi_device *dsi)
+{
+	struct panel_info *pinfo;
+	const struct panel_desc *desc;
+	int err;
+
+	pinfo = devm_kzalloc(&dsi->dev, sizeof(*pinfo), GFP_KERNEL);
+	if (!pinfo)
+		return -ENOMEM;
+
+	desc = of_device_get_match_data(&dsi->dev);
+	dsi->mode_flags = desc->mode_flags;
+	dsi->format = desc->format;
+	dsi->lanes = desc->lanes;
+	pinfo->desc = desc;
+
+	pinfo->link = dsi;
+	mipi_dsi_set_drvdata(dsi, pinfo);
+
+	err = panel_add(pinfo);
+	if (err < 0)
+		return err;
+
+	err = mipi_dsi_attach(dsi);
+	if (err < 0)
+		drm_panel_remove(&pinfo->base);
+
+	return err;
+}
+
+static int panel_remove(struct mipi_dsi_device *dsi)
+{
+	struct panel_info *pinfo = mipi_dsi_get_drvdata(dsi);
+	int err;
+
+	err = boe_panel_disable(&pinfo->base);
+	if (err < 0)
+		DRM_DEV_ERROR(&dsi->dev, "failed to disable panel: %d\n",
+			      err);
+
+	err = boe_panel_unprepare(&pinfo->base);
+	if (err < 0)
+		DRM_DEV_ERROR(&dsi->dev, "failed to unprepare panel: %d\n",
+			      err);
+
+	err = mipi_dsi_detach(dsi);
+	if (err < 0)
+		DRM_DEV_ERROR(&dsi->dev, "failed to detach from DSI host: %d\n",
+			      err);
+
+	drm_panel_remove(&pinfo->base);
+
+	return 0;
+}
+
+static void panel_shutdown(struct mipi_dsi_device *dsi)
+{
+	struct panel_info *pinfo = mipi_dsi_get_drvdata(dsi);
+
+	boe_panel_disable(&pinfo->base);
+	boe_panel_unprepare(&pinfo->base);
+}
+
+static struct mipi_dsi_driver panel_driver = {
+	.driver = {
+		.name = "panel-boe-himax8279d",
+		.of_match_table = panel_of_match,
+	},
+	.probe = panel_probe,
+	.remove = panel_remove,
+	.shutdown = panel_shutdown,
+};
+module_mipi_dsi_driver(panel_driver);
+
+MODULE_AUTHOR("Jerry Han <jerry.han.hq@gmail.com>");
+MODULE_DESCRIPTION("Boe Himax8279d driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
index 98f184b81187..95b789ab9d29 100644
--- a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
+++ b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
@@ -9,7 +9,6 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_print.h>
 
-#include <linux/backlight.h>
 #include <linux/gpio/consumer.h>
 #include <linux/delay.h>
 #include <linux/module.h>
@@ -22,7 +21,6 @@ struct feiyang {
 	struct drm_panel	panel;
 	struct mipi_dsi_device	*dsi;
 
-	struct backlight_device	*backlight;
 	struct regulator	*dvdd;
 	struct regulator	*avdd;
 	struct gpio_desc	*reset;
@@ -102,7 +100,6 @@ static int feiyang_enable(struct drm_panel *panel)
 	msleep(200);
 
 	mipi_dsi_dcs_set_display_on(ctx->dsi);
-	backlight_enable(ctx->backlight);
 
 	return 0;
 }
@@ -111,7 +108,6 @@ static int feiyang_disable(struct drm_panel *panel)
 {
 	struct feiyang *ctx = panel_to_feiyang(panel);
 
-	backlight_disable(ctx->backlight);
 	return mipi_dsi_dcs_set_display_off(ctx->dsi);
 }
 
@@ -162,13 +158,13 @@ static const struct drm_display_mode feiyang_default_mode = {
 	.type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED,
 };
 
-static int feiyang_get_modes(struct drm_panel *panel)
+static int feiyang_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct feiyang *ctx = panel_to_feiyang(panel);
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &feiyang_default_mode);
+	mode = drm_mode_duplicate(connector->dev, &feiyang_default_mode);
 	if (!mode) {
 		DRM_DEV_ERROR(&ctx->dsi->dev, "failed to add mode %ux%ux@%u\n",
 			      feiyang_default_mode.hdisplay,
@@ -225,9 +221,9 @@ static int feiyang_dsi_probe(struct mipi_dsi_device *dsi)
 		return PTR_ERR(ctx->reset);
 	}
 
-	ctx->backlight = devm_of_find_backlight(&dsi->dev);
-	if (IS_ERR(ctx->backlight))
-		return PTR_ERR(ctx->backlight);
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
 
 	ret = drm_panel_add(&ctx->panel);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9322.c b/drivers/gpu/drm/panel/panel-ilitek-ili9322.c
index 24955bec1958..f394d53a7da4 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9322.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9322.c
@@ -641,10 +641,11 @@ static const struct drm_display_mode itu_r_bt_656_720_mode = {
 	.flags = 0,
 };
 
-static int ili9322_get_modes(struct drm_panel *panel)
+static int ili9322_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct ili9322 *ili = panel_to_ili9322(panel);
+	struct drm_device *drm = connector->dev;
 	struct drm_display_mode *mode;
 	struct drm_display_info *info;
 
@@ -663,26 +664,26 @@ static int ili9322_get_modes(struct drm_panel *panel)
 
 	switch (ili->input) {
 	case ILI9322_INPUT_SRGB_DUMMY_320X240:
-		mode = drm_mode_duplicate(panel->drm, &srgb_320x240_mode);
+		mode = drm_mode_duplicate(drm, &srgb_320x240_mode);
 		break;
 	case ILI9322_INPUT_SRGB_DUMMY_360X240:
-		mode = drm_mode_duplicate(panel->drm, &srgb_360x240_mode);
+		mode = drm_mode_duplicate(drm, &srgb_360x240_mode);
 		break;
 	case ILI9322_INPUT_PRGB_THROUGH:
 	case ILI9322_INPUT_PRGB_ALIGNED:
-		mode = drm_mode_duplicate(panel->drm, &prgb_320x240_mode);
+		mode = drm_mode_duplicate(drm, &prgb_320x240_mode);
 		break;
 	case ILI9322_INPUT_YUV_640X320_YCBCR:
-		mode = drm_mode_duplicate(panel->drm, &yuv_640x320_mode);
+		mode = drm_mode_duplicate(drm, &yuv_640x320_mode);
 		break;
 	case ILI9322_INPUT_YUV_720X360_YCBCR:
-		mode = drm_mode_duplicate(panel->drm, &yuv_720x360_mode);
+		mode = drm_mode_duplicate(drm, &yuv_720x360_mode);
 		break;
 	case ILI9322_INPUT_ITU_R_BT656_720X360_YCBCR:
-		mode = drm_mode_duplicate(panel->drm, &itu_r_bt_656_720_mode);
+		mode = drm_mode_duplicate(drm, &itu_r_bt_656_720_mode);
 		break;
 	case ILI9322_INPUT_ITU_R_BT656_640X320_YCBCR:
-		mode = drm_mode_duplicate(panel->drm, &itu_r_bt_656_640_mode);
+		mode = drm_mode_duplicate(drm, &itu_r_bt_656_640_mode);
 		break;
 	default:
 		mode = NULL;
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
index e8789e460a16..f54077c216a3 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2017-2018, Bootlin
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -25,7 +24,6 @@ struct ili9881c {
 	struct drm_panel	panel;
 	struct mipi_dsi_device	*dsi;
 
-	struct backlight_device *backlight;
 	struct regulator	*power;
 	struct gpio_desc	*reset;
 };
@@ -348,7 +346,6 @@ static int ili9881c_enable(struct drm_panel *panel)
 	msleep(120);
 
 	mipi_dsi_dcs_set_display_on(ctx->dsi);
-	backlight_enable(ctx->backlight);
 
 	return 0;
 }
@@ -357,7 +354,6 @@ static int ili9881c_disable(struct drm_panel *panel)
 {
 	struct ili9881c *ctx = panel_to_ili9881c(panel);
 
-	backlight_disable(ctx->backlight);
 	return mipi_dsi_dcs_set_display_off(ctx->dsi);
 }
 
@@ -387,13 +383,13 @@ static const struct drm_display_mode bananapi_default_mode = {
 	.vtotal		= 1280 + 10 + 10 + 20,
 };
 
-static int ili9881c_get_modes(struct drm_panel *panel)
+static int ili9881c_get_modes(struct drm_panel *panel,
+			      struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct ili9881c *ctx = panel_to_ili9881c(panel);
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &bananapi_default_mode);
+	mode = drm_mode_duplicate(connector->dev, &bananapi_default_mode);
 	if (!mode) {
 		dev_err(&ctx->dsi->dev, "failed to add mode %ux%ux@%u\n",
 			bananapi_default_mode.hdisplay,
@@ -407,8 +403,8 @@ static int ili9881c_get_modes(struct drm_panel *panel)
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
 	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 62;
-	panel->connector->display_info.height_mm = 110;
+	connector->display_info.width_mm = 62;
+	connector->display_info.height_mm = 110;
 
 	return 1;
 }
@@ -423,7 +419,6 @@ static const struct drm_panel_funcs ili9881c_funcs = {
 
 static int ili9881c_dsi_probe(struct mipi_dsi_device *dsi)
 {
-	struct device_node *np;
 	struct ili9881c *ctx;
 	int ret;
 
@@ -448,14 +443,9 @@ static int ili9881c_dsi_probe(struct mipi_dsi_device *dsi)
 		return PTR_ERR(ctx->reset);
 	}
 
-	np = of_parse_phandle(dsi->dev.of_node, "backlight", 0);
-	if (np) {
-		ctx->backlight = of_find_backlight_by_node(np);
-		of_node_put(np);
-
-		if (!ctx->backlight)
-			return -EPROBE_DEFER;
-	}
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
 
 	ret = drm_panel_add(&ctx->panel);
 	if (ret < 0)
@@ -475,9 +465,6 @@ static int ili9881c_dsi_remove(struct mipi_dsi_device *dsi)
 	mipi_dsi_detach(dsi);
 	drm_panel_remove(&ctx->panel);
 
-	if (ctx->backlight)
-		put_device(&ctx->backlight->dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index 83df1ac4211f..7419f1f0acee 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -3,7 +3,6 @@
  * Copyright (c) 2017, Fuzhou Rockchip Electronics Co., Ltd
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
@@ -52,7 +51,6 @@ struct innolux_panel {
 	struct mipi_dsi_device *link;
 	const struct panel_desc *desc;
 
-	struct backlight_device *backlight;
 	struct regulator_bulk_data *supplies;
 	struct gpio_desc *enable_gpio;
 
@@ -72,8 +70,6 @@ static int innolux_panel_disable(struct drm_panel *panel)
 	if (!innolux->enabled)
 		return 0;
 
-	backlight_disable(innolux->backlight);
-
 	innolux->enabled = false;
 
 	return 0;
@@ -204,18 +200,10 @@ poweroff:
 static int innolux_panel_enable(struct drm_panel *panel)
 {
 	struct innolux_panel *innolux = to_innolux_panel(panel);
-	int ret;
 
 	if (innolux->enabled)
 		return 0;
 
-	ret = backlight_enable(innolux->backlight);
-	if (ret) {
-		DRM_DEV_ERROR(panel->drm->dev,
-			      "Failed to enable backlight %d\n", ret);
-		return ret;
-	}
-
 	innolux->enabled = true;
 
 	return 0;
@@ -403,28 +391,27 @@ static const struct panel_desc innolux_p097pfg_panel_desc = {
 	.sleep_mode_delay = 100, /* T15 */
 };
 
-static int innolux_panel_get_modes(struct drm_panel *panel)
+static int innolux_panel_get_modes(struct drm_panel *panel,
+				   struct drm_connector *connector)
 {
 	struct innolux_panel *innolux = to_innolux_panel(panel);
 	const struct drm_display_mode *m = innolux->desc->mode;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, m);
+	mode = drm_mode_duplicate(connector->dev, m);
 	if (!mode) {
-		DRM_DEV_ERROR(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
+		DRM_DEV_ERROR(panel->dev, "failed to add mode %ux%ux@%u\n",
 			      m->hdisplay, m->vdisplay, m->vrefresh);
 		return -ENOMEM;
 	}
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm =
-			innolux->desc->size.width;
-	panel->connector->display_info.height_mm =
-			innolux->desc->size.height;
-	panel->connector->display_info.bpc = innolux->desc->bpc;
+	connector->display_info.width_mm = innolux->desc->size.width;
+	connector->display_info.height_mm = innolux->desc->size.height;
+	connector->display_info.bpc = innolux->desc->bpc;
 
 	return 1;
 }
@@ -483,13 +470,13 @@ static int innolux_panel_add(struct mipi_dsi_device *dsi,
 		innolux->enable_gpio = NULL;
 	}
 
-	innolux->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(innolux->backlight))
-		return PTR_ERR(innolux->backlight);
-
 	drm_panel_init(&innolux->base, dev, &innolux_panel_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
+	err = drm_panel_of_backlight(&innolux->base);
+	if (err)
+		return err;
+
 	err = drm_panel_add(&innolux->base);
 	if (err < 0)
 		return err;
@@ -527,12 +514,12 @@ static int innolux_panel_remove(struct mipi_dsi_device *dsi)
 	struct innolux_panel *innolux = mipi_dsi_get_drvdata(dsi);
 	int err;
 
-	err = innolux_panel_unprepare(&innolux->base);
+	err = drm_panel_unprepare(&innolux->base);
 	if (err < 0)
 		DRM_DEV_ERROR(&dsi->dev, "failed to unprepare panel: %d\n",
 			      err);
 
-	err = innolux_panel_disable(&innolux->base);
+	err = drm_panel_disable(&innolux->base);
 	if (err < 0)
 		DRM_DEV_ERROR(&dsi->dev, "failed to disable panel: %d\n", err);
 
@@ -550,8 +537,8 @@ static void innolux_panel_shutdown(struct mipi_dsi_device *dsi)
 {
 	struct innolux_panel *innolux = mipi_dsi_get_drvdata(dsi);
 
-	innolux_panel_unprepare(&innolux->base);
-	innolux_panel_disable(&innolux->base);
+	drm_panel_unprepare(&innolux->base);
+	drm_panel_disable(&innolux->base);
 }
 
 static struct mipi_dsi_driver innolux_panel_driver = {
diff --git a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
index 56364a93f0b8..4bfd8c877c8e 100644
--- a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
+++ b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
@@ -300,13 +300,14 @@ static const struct drm_display_mode default_mode = {
 		.flags = 0,
 };
 
-static int jdi_panel_get_modes(struct drm_panel *panel)
+static int jdi_panel_get_modes(struct drm_panel *panel,
+			       struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 	struct jdi_panel *jdi = to_jdi_panel(panel);
 	struct device *dev = &jdi->dsi->dev;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		dev_err(dev, "failed to add mode %ux%ux@%u\n",
 			default_mode.hdisplay, default_mode.vdisplay,
@@ -316,10 +317,10 @@ static int jdi_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 95;
-	panel->connector->display_info.height_mm = 151;
+	connector->display_info.width_mm = 95;
+	connector->display_info.height_mm = 151;
 
 	return 1;
 }
diff --git a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
index 45f96556ec8c..bac1a2a06c92 100644
--- a/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
+++ b/drivers/gpu/drm/panel/panel-kingdisplay-kd097d04.c
@@ -3,7 +3,6 @@
  * Copyright (c) 2017, Fuzhou Rockchip Electronics Co., Ltd
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
@@ -23,7 +22,6 @@ struct kingdisplay_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *link;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 	struct gpio_desc *enable_gpio;
 
@@ -191,8 +189,6 @@ static int kingdisplay_panel_disable(struct drm_panel *panel)
 	if (!kingdisplay->enabled)
 		return 0;
 
-	backlight_disable(kingdisplay->backlight);
-
 	err = mipi_dsi_dcs_set_display_off(kingdisplay->link);
 	if (err < 0)
 		DRM_DEV_ERROR(panel->dev, "failed to set display off: %d\n",
@@ -303,18 +299,10 @@ poweroff:
 static int kingdisplay_panel_enable(struct drm_panel *panel)
 {
 	struct kingdisplay_panel *kingdisplay = to_kingdisplay_panel(panel);
-	int ret;
 
 	if (kingdisplay->enabled)
 		return 0;
 
-	ret = backlight_enable(kingdisplay->backlight);
-	if (ret) {
-		DRM_DEV_ERROR(panel->drm->dev,
-			      "Failed to enable backlight %d\n", ret);
-		return ret;
-	}
-
 	kingdisplay->enabled = true;
 
 	return 0;
@@ -333,13 +321,14 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
-static int kingdisplay_panel_get_modes(struct drm_panel *panel)
+static int kingdisplay_panel_get_modes(struct drm_panel *panel,
+				       struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
-		DRM_DEV_ERROR(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
+		DRM_DEV_ERROR(panel->dev, "failed to add mode %ux%ux@%u\n",
 			      default_mode.hdisplay, default_mode.vdisplay,
 			      default_mode.vrefresh);
 		return -ENOMEM;
@@ -347,11 +336,11 @@ static int kingdisplay_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 147;
-	panel->connector->display_info.height_mm = 196;
-	panel->connector->display_info.bpc = 8;
+	connector->display_info.width_mm = 147;
+	connector->display_info.height_mm = 196;
+	connector->display_info.bpc = 8;
 
 	return 1;
 }
@@ -387,13 +376,13 @@ static int kingdisplay_panel_add(struct kingdisplay_panel *kingdisplay)
 		kingdisplay->enable_gpio = NULL;
 	}
 
-	kingdisplay->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(kingdisplay->backlight))
-		return PTR_ERR(kingdisplay->backlight);
-
 	drm_panel_init(&kingdisplay->base, &kingdisplay->link->dev,
 		       &kingdisplay_panel_funcs, DRM_MODE_CONNECTOR_DSI);
 
+	err = drm_panel_of_backlight(&kingdisplay->base);
+	if (err)
+		return err;
+
 	return drm_panel_add(&kingdisplay->base);
 }
 
@@ -431,12 +420,12 @@ static int kingdisplay_panel_remove(struct mipi_dsi_device *dsi)
 	struct kingdisplay_panel *kingdisplay = mipi_dsi_get_drvdata(dsi);
 	int err;
 
-	err = kingdisplay_panel_unprepare(&kingdisplay->base);
+	err = drm_panel_unprepare(&kingdisplay->base);
 	if (err < 0)
 		DRM_DEV_ERROR(&dsi->dev, "failed to unprepare panel: %d\n",
 			      err);
 
-	err = kingdisplay_panel_disable(&kingdisplay->base);
+	err = drm_panel_disable(&kingdisplay->base);
 	if (err < 0)
 		DRM_DEV_ERROR(&dsi->dev, "failed to disable panel: %d\n", err);
 
@@ -454,8 +443,8 @@ static void kingdisplay_panel_shutdown(struct mipi_dsi_device *dsi)
 {
 	struct kingdisplay_panel *kingdisplay = mipi_dsi_get_drvdata(dsi);
 
-	kingdisplay_panel_unprepare(&kingdisplay->base);
-	kingdisplay_panel_disable(&kingdisplay->base);
+	drm_panel_unprepare(&kingdisplay->base);
+	drm_panel_disable(&kingdisplay->base);
 }
 
 static struct mipi_dsi_driver kingdisplay_panel_driver = {
diff --git a/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c b/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c
new file mode 100644
index 000000000000..76ecf2de9c44
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-leadtek-ltk500hd1829.c
@@ -0,0 +1,531 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2019 Theobroma Systems Design und Consulting GmbH
+ *
+ * base on panel-kingdisplay-kd097d04.c
+ * Copyright (c) 2017, Fuzhou Rockchip Electronics Co., Ltd
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regulator/consumer.h>
+
+#include <video/mipi_display.h>
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_device.h>
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+
+struct ltk500hd1829 {
+	struct device *dev;
+	struct drm_panel panel;
+	struct gpio_desc *reset_gpio;
+	struct regulator *vcc;
+	struct regulator *iovcc;
+	bool prepared;
+};
+
+struct ltk500hd1829_cmd {
+	char cmd;
+	char data;
+};
+
+/*
+ * There is no description in the Reference Manual about these commands.
+ * We received them from the vendor, so just use them as is.
+ */
+static const struct ltk500hd1829_cmd init_code[] = {
+	{ 0xE0, 0x00 },
+	{ 0xE1, 0x93 },
+	{ 0xE2, 0x65 },
+	{ 0xE3, 0xF8 },
+	{ 0x80, 0x03 },
+	{ 0xE0, 0x04 },
+	{ 0x2D, 0x03 },
+	{ 0xE0, 0x01 },
+	{ 0x00, 0x00 },
+	{ 0x01, 0xB6 },
+	{ 0x03, 0x00 },
+	{ 0x04, 0xC5 },
+	{ 0x17, 0x00 },
+	{ 0x18, 0xBF },
+	{ 0x19, 0x01 },
+	{ 0x1A, 0x00 },
+	{ 0x1B, 0xBF },
+	{ 0x1C, 0x01 },
+	{ 0x1F, 0x7C },
+	{ 0x20, 0x26 },
+	{ 0x21, 0x26 },
+	{ 0x22, 0x4E },
+	{ 0x37, 0x09 },
+	{ 0x38, 0x04 },
+	{ 0x39, 0x08 },
+	{ 0x3A, 0x1F },
+	{ 0x3B, 0x1F },
+	{ 0x3C, 0x78 },
+	{ 0x3D, 0xFF },
+	{ 0x3E, 0xFF },
+	{ 0x3F, 0x00 },
+	{ 0x40, 0x04 },
+	{ 0x41, 0xA0 },
+	{ 0x43, 0x0F },
+	{ 0x44, 0x0A },
+	{ 0x45, 0x24 },
+	{ 0x55, 0x01 },
+	{ 0x56, 0x01 },
+	{ 0x57, 0xA5 },
+	{ 0x58, 0x0A },
+	{ 0x59, 0x4A },
+	{ 0x5A, 0x38 },
+	{ 0x5B, 0x10 },
+	{ 0x5C, 0x19 },
+	{ 0x5D, 0x7C },
+	{ 0x5E, 0x64 },
+	{ 0x5F, 0x54 },
+	{ 0x60, 0x48 },
+	{ 0x61, 0x44 },
+	{ 0x62, 0x35 },
+	{ 0x63, 0x3A },
+	{ 0x64, 0x24 },
+	{ 0x65, 0x3B },
+	{ 0x66, 0x39 },
+	{ 0x67, 0x37 },
+	{ 0x68, 0x56 },
+	{ 0x69, 0x41 },
+	{ 0x6A, 0x47 },
+	{ 0x6B, 0x2F },
+	{ 0x6C, 0x23 },
+	{ 0x6D, 0x13 },
+	{ 0x6E, 0x02 },
+	{ 0x6F, 0x08 },
+	{ 0x70, 0x7C },
+	{ 0x71, 0x64 },
+	{ 0x72, 0x54 },
+	{ 0x73, 0x48 },
+	{ 0x74, 0x44 },
+	{ 0x75, 0x35 },
+	{ 0x76, 0x3A },
+	{ 0x77, 0x22 },
+	{ 0x78, 0x3B },
+	{ 0x79, 0x39 },
+	{ 0x7A, 0x38 },
+	{ 0x7B, 0x52 },
+	{ 0x7C, 0x41 },
+	{ 0x7D, 0x47 },
+	{ 0x7E, 0x2F },
+	{ 0x7F, 0x23 },
+	{ 0x80, 0x13 },
+	{ 0x81, 0x02 },
+	{ 0x82, 0x08 },
+	{ 0xE0, 0x02 },
+	{ 0x00, 0x57 },
+	{ 0x01, 0x77 },
+	{ 0x02, 0x44 },
+	{ 0x03, 0x46 },
+	{ 0x04, 0x48 },
+	{ 0x05, 0x4A },
+	{ 0x06, 0x4C },
+	{ 0x07, 0x4E },
+	{ 0x08, 0x50 },
+	{ 0x09, 0x55 },
+	{ 0x0A, 0x52 },
+	{ 0x0B, 0x55 },
+	{ 0x0C, 0x55 },
+	{ 0x0D, 0x55 },
+	{ 0x0E, 0x55 },
+	{ 0x0F, 0x55 },
+	{ 0x10, 0x55 },
+	{ 0x11, 0x55 },
+	{ 0x12, 0x55 },
+	{ 0x13, 0x40 },
+	{ 0x14, 0x55 },
+	{ 0x15, 0x55 },
+	{ 0x16, 0x57 },
+	{ 0x17, 0x77 },
+	{ 0x18, 0x45 },
+	{ 0x19, 0x47 },
+	{ 0x1A, 0x49 },
+	{ 0x1B, 0x4B },
+	{ 0x1C, 0x4D },
+	{ 0x1D, 0x4F },
+	{ 0x1E, 0x51 },
+	{ 0x1F, 0x55 },
+	{ 0x20, 0x53 },
+	{ 0x21, 0x55 },
+	{ 0x22, 0x55 },
+	{ 0x23, 0x55 },
+	{ 0x24, 0x55 },
+	{ 0x25, 0x55 },
+	{ 0x26, 0x55 },
+	{ 0x27, 0x55 },
+	{ 0x28, 0x55 },
+	{ 0x29, 0x41 },
+	{ 0x2A, 0x55 },
+	{ 0x2B, 0x55 },
+	{ 0x2C, 0x57 },
+	{ 0x2D, 0x77 },
+	{ 0x2E, 0x4F },
+	{ 0x2F, 0x4D },
+	{ 0x30, 0x4B },
+	{ 0x31, 0x49 },
+	{ 0x32, 0x47 },
+	{ 0x33, 0x45 },
+	{ 0x34, 0x41 },
+	{ 0x35, 0x55 },
+	{ 0x36, 0x53 },
+	{ 0x37, 0x55 },
+	{ 0x38, 0x55 },
+	{ 0x39, 0x55 },
+	{ 0x3A, 0x55 },
+	{ 0x3B, 0x55 },
+	{ 0x3C, 0x55 },
+	{ 0x3D, 0x55 },
+	{ 0x3E, 0x55 },
+	{ 0x3F, 0x51 },
+	{ 0x40, 0x55 },
+	{ 0x41, 0x55 },
+	{ 0x42, 0x57 },
+	{ 0x43, 0x77 },
+	{ 0x44, 0x4E },
+	{ 0x45, 0x4C },
+	{ 0x46, 0x4A },
+	{ 0x47, 0x48 },
+	{ 0x48, 0x46 },
+	{ 0x49, 0x44 },
+	{ 0x4A, 0x40 },
+	{ 0x4B, 0x55 },
+	{ 0x4C, 0x52 },
+	{ 0x4D, 0x55 },
+	{ 0x4E, 0x55 },
+	{ 0x4F, 0x55 },
+	{ 0x50, 0x55 },
+	{ 0x51, 0x55 },
+	{ 0x52, 0x55 },
+	{ 0x53, 0x55 },
+	{ 0x54, 0x55 },
+	{ 0x55, 0x50 },
+	{ 0x56, 0x55 },
+	{ 0x57, 0x55 },
+	{ 0x58, 0x40 },
+	{ 0x59, 0x00 },
+	{ 0x5A, 0x00 },
+	{ 0x5B, 0x10 },
+	{ 0x5C, 0x09 },
+	{ 0x5D, 0x30 },
+	{ 0x5E, 0x01 },
+	{ 0x5F, 0x02 },
+	{ 0x60, 0x30 },
+	{ 0x61, 0x03 },
+	{ 0x62, 0x04 },
+	{ 0x63, 0x06 },
+	{ 0x64, 0x6A },
+	{ 0x65, 0x75 },
+	{ 0x66, 0x0F },
+	{ 0x67, 0xB3 },
+	{ 0x68, 0x0B },
+	{ 0x69, 0x06 },
+	{ 0x6A, 0x6A },
+	{ 0x6B, 0x10 },
+	{ 0x6C, 0x00 },
+	{ 0x6D, 0x04 },
+	{ 0x6E, 0x04 },
+	{ 0x6F, 0x88 },
+	{ 0x70, 0x00 },
+	{ 0x71, 0x00 },
+	{ 0x72, 0x06 },
+	{ 0x73, 0x7B },
+	{ 0x74, 0x00 },
+	{ 0x75, 0xBC },
+	{ 0x76, 0x00 },
+	{ 0x77, 0x05 },
+	{ 0x78, 0x2E },
+	{ 0x79, 0x00 },
+	{ 0x7A, 0x00 },
+	{ 0x7B, 0x00 },
+	{ 0x7C, 0x00 },
+	{ 0x7D, 0x03 },
+	{ 0x7E, 0x7B },
+	{ 0xE0, 0x04 },
+	{ 0x09, 0x10 },
+	{ 0x2B, 0x2B },
+	{ 0x2E, 0x44 },
+	{ 0xE0, 0x00 },
+	{ 0xE6, 0x02 },
+	{ 0xE7, 0x02 },
+	{ 0x35, 0x00 },
+};
+
+static inline
+struct ltk500hd1829 *panel_to_ltk500hd1829(struct drm_panel *panel)
+{
+	return container_of(panel, struct ltk500hd1829, panel);
+}
+
+static int ltk500hd1829_unprepare(struct drm_panel *panel)
+{
+	struct ltk500hd1829 *ctx = panel_to_ltk500hd1829(panel);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+	int ret;
+
+	if (!ctx->prepared)
+		return 0;
+
+	ret = mipi_dsi_dcs_set_display_off(dsi);
+	if (ret < 0)
+		DRM_DEV_ERROR(panel->dev, "failed to set display off: %d\n",
+			      ret);
+
+	ret = mipi_dsi_dcs_enter_sleep_mode(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to enter sleep mode: %d\n",
+			      ret);
+	}
+
+	/* 120ms to enter sleep mode */
+	msleep(120);
+
+	regulator_disable(ctx->iovcc);
+	regulator_disable(ctx->vcc);
+
+	ctx->prepared = false;
+
+	return 0;
+}
+
+static int ltk500hd1829_prepare(struct drm_panel *panel)
+{
+	struct ltk500hd1829 *ctx = panel_to_ltk500hd1829(panel);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+	unsigned int i;
+	int ret;
+
+	if (ctx->prepared)
+		return 0;
+
+	ret = regulator_enable(ctx->vcc);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev,
+			      "Failed to enable vci supply: %d\n", ret);
+		return ret;
+	}
+	ret = regulator_enable(ctx->iovcc);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev,
+			      "Failed to enable iovcc supply: %d\n", ret);
+		goto disable_vcc;
+	}
+
+	gpiod_set_value_cansleep(ctx->reset_gpio, 1);
+	/* tRW: 10us */
+	usleep_range(10, 20);
+	gpiod_set_value_cansleep(ctx->reset_gpio, 0);
+
+	/* tRT: >= 5ms */
+	usleep_range(5000, 6000);
+
+	for (i = 0; i < ARRAY_SIZE(init_code); i++) {
+		ret = mipi_dsi_generic_write(dsi, &init_code[i],
+					     sizeof(struct ltk500hd1829_cmd));
+		if (ret < 0) {
+			DRM_DEV_ERROR(panel->dev,
+				      "failed to write init cmds: %d\n", ret);
+			goto disable_iovcc;
+		}
+	}
+
+	ret = mipi_dsi_dcs_exit_sleep_mode(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to exit sleep mode: %d\n",
+			      ret);
+		goto disable_iovcc;
+	}
+
+	/* 120ms to exit sleep mode */
+	msleep(120);
+
+	ret = mipi_dsi_dcs_set_display_on(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(panel->dev, "failed to set display on: %d\n",
+			      ret);
+		goto disable_iovcc;
+	}
+
+	ctx->prepared = true;
+
+	return 0;
+
+disable_iovcc:
+	regulator_disable(ctx->iovcc);
+disable_vcc:
+	regulator_disable(ctx->vcc);
+	return ret;
+}
+
+static const struct drm_display_mode default_mode = {
+	.hdisplay	= 720,
+	.hsync_start	= 720 + 50,
+	.hsync_end	= 720 + 50 + 50,
+	.htotal		= 720 + 50 + 50 + 50,
+	.vdisplay	= 1280,
+	.vsync_start	= 1280 + 30,
+	.vsync_end	= 1280 + 30 + 4,
+	.vtotal		= 1280 + 30 + 4 + 12,
+	.vrefresh	= 60,
+	.clock		= 41600,
+	.width_mm	= 62,
+	.height_mm	= 110,
+};
+
+static int ltk500hd1829_get_modes(struct drm_panel *panel,
+				  struct drm_connector *connector)
+{
+	struct ltk500hd1829 *ctx = panel_to_ltk500hd1829(panel);
+	struct drm_display_mode *mode;
+
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
+	if (!mode) {
+		DRM_DEV_ERROR(ctx->dev, "failed to add mode %ux%ux@%u\n",
+			      default_mode.hdisplay, default_mode.vdisplay,
+			      default_mode.vrefresh);
+		return -ENOMEM;
+	}
+
+	drm_mode_set_name(mode);
+
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
+	drm_mode_probed_add(connector, mode);
+
+	return 1;
+}
+
+static const struct drm_panel_funcs ltk500hd1829_funcs = {
+	.unprepare = ltk500hd1829_unprepare,
+	.prepare = ltk500hd1829_prepare,
+	.get_modes = ltk500hd1829_get_modes,
+};
+
+static int ltk500hd1829_probe(struct mipi_dsi_device *dsi)
+{
+	struct ltk500hd1829 *ctx;
+	struct device *dev = &dsi->dev;
+	int ret;
+
+	ctx = devm_kzalloc(&dsi->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(ctx->reset_gpio)) {
+		DRM_DEV_ERROR(dev, "cannot get reset gpio\n");
+		return PTR_ERR(ctx->reset_gpio);
+	}
+
+	ctx->vcc = devm_regulator_get(dev, "vcc");
+	if (IS_ERR(ctx->vcc)) {
+		ret = PTR_ERR(ctx->vcc);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev,
+				      "Failed to request vcc regulator: %d\n",
+				      ret);
+		return ret;
+	}
+
+	ctx->iovcc = devm_regulator_get(dev, "iovcc");
+	if (IS_ERR(ctx->iovcc)) {
+		ret = PTR_ERR(ctx->iovcc);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev,
+				      "Failed to request iovcc regulator: %d\n",
+				      ret);
+		return ret;
+	}
+
+	mipi_dsi_set_drvdata(dsi, ctx);
+
+	ctx->dev = dev;
+
+	dsi->lanes = 4;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+
+	drm_panel_init(&ctx->panel, &dsi->dev, &ltk500hd1829_funcs,
+		       DRM_MODE_CONNECTOR_DSI);
+
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
+
+	drm_panel_add(&ctx->panel);
+
+	ret = mipi_dsi_attach(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(dev, "mipi_dsi_attach failed: %d\n", ret);
+		drm_panel_remove(&ctx->panel);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ltk500hd1829_shutdown(struct mipi_dsi_device *dsi)
+{
+	struct ltk500hd1829 *ctx = mipi_dsi_get_drvdata(dsi);
+	int ret;
+
+	ret = drm_panel_unprepare(&ctx->panel);
+	if (ret < 0)
+		DRM_DEV_ERROR(&dsi->dev, "Failed to unprepare panel: %d\n",
+			      ret);
+
+	ret = drm_panel_disable(&ctx->panel);
+	if (ret < 0)
+		DRM_DEV_ERROR(&dsi->dev, "Failed to disable panel: %d\n",
+			      ret);
+}
+
+static int ltk500hd1829_remove(struct mipi_dsi_device *dsi)
+{
+	struct ltk500hd1829 *ctx = mipi_dsi_get_drvdata(dsi);
+	int ret;
+
+	ltk500hd1829_shutdown(dsi);
+
+	ret = mipi_dsi_detach(dsi);
+	if (ret < 0)
+		DRM_DEV_ERROR(&dsi->dev, "failed to detach from DSI host: %d\n",
+			      ret);
+
+	drm_panel_remove(&ctx->panel);
+
+	return 0;
+}
+
+static const struct of_device_id ltk500hd1829_of_match[] = {
+	{ .compatible = "leadtek,ltk500hd1829", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ltk500hd1829_of_match);
+
+static struct mipi_dsi_driver ltk500hd1829_driver = {
+	.driver = {
+		.name = "panel-leadtek-ltk500hd1829",
+		.of_match_table = ltk500hd1829_of_match,
+	},
+	.probe = ltk500hd1829_probe,
+	.remove = ltk500hd1829_remove,
+	.shutdown = ltk500hd1829_shutdown,
+};
+module_mipi_dsi_driver(ltk500hd1829_driver);
+
+MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@theobroma-systems.com>");
+MODULE_DESCRIPTION("Leadtek LTK500HD1829 panel driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
index 7a1385e834f0..e90efeaba4ad 100644
--- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c
+++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
@@ -141,12 +141,12 @@ static const struct drm_display_mode lb035q02_mode = {
 	.height_mm = 53,
 };
 
-static int lb035q02_get_modes(struct drm_panel *panel)
+static int lb035q02_get_modes(struct drm_panel *panel,
+			      struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &lb035q02_mode);
+	mode = drm_mode_duplicate(connector->dev, &lb035q02_mode);
 	if (!mode)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/panel/panel-lg-lg4573.c b/drivers/gpu/drm/panel/panel-lg-lg4573.c
index db4865a4c2b9..b262b53dbd85 100644
--- a/drivers/gpu/drm/panel/panel-lg-lg4573.c
+++ b/drivers/gpu/drm/panel/panel-lg-lg4573.c
@@ -42,7 +42,7 @@ static int lg4573_spi_write_u16(struct lg4573 *ctx, u16 data)
 	struct spi_transfer xfer = {
 		.len = 2,
 	};
-	u16 temp = cpu_to_be16(data);
+	__be16 temp = cpu_to_be16(data);
 	struct spi_message msg;
 
 	dev_dbg(ctx->panel.dev, "writing data: %x\n", data);
@@ -209,14 +209,14 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
-static int lg4573_get_modes(struct drm_panel *panel)
+static int lg4573_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
-		dev_err(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
+		dev_err(panel->dev, "failed to add mode %ux%ux@%u\n",
 			default_mode.hdisplay, default_mode.vdisplay,
 			default_mode.vrefresh);
 		return -ENOMEM;
@@ -227,8 +227,8 @@ static int lg4573_get_modes(struct drm_panel *panel)
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
 	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 61;
-	panel->connector->display_info.height_mm = 103;
+	connector->display_info.width_mm = 61;
+	connector->display_info.height_mm = 103;
 
 	return 1;
 }
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index 2405f26e5d31..5ce3f4a2b7a1 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -8,7 +8,6 @@
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  */
 
-#include <linux/backlight.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of_platform.h>
@@ -34,7 +33,6 @@ struct panel_lvds {
 	unsigned int bus_format;
 	bool data_mirror;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 
 	struct gpio_desc *enable_gpio;
@@ -46,19 +44,6 @@ static inline struct panel_lvds *to_panel_lvds(struct drm_panel *panel)
 	return container_of(panel, struct panel_lvds, panel);
 }
 
-static int panel_lvds_disable(struct drm_panel *panel)
-{
-	struct panel_lvds *lvds = to_panel_lvds(panel);
-
-	if (lvds->backlight) {
-		lvds->backlight->props.power = FB_BLANK_POWERDOWN;
-		lvds->backlight->props.state |= BL_CORE_FBBLANK;
-		backlight_update_status(lvds->backlight);
-	}
-
-	return 0;
-}
-
 static int panel_lvds_unprepare(struct drm_panel *panel)
 {
 	struct panel_lvds *lvds = to_panel_lvds(panel);
@@ -93,26 +78,13 @@ static int panel_lvds_prepare(struct drm_panel *panel)
 	return 0;
 }
 
-static int panel_lvds_enable(struct drm_panel *panel)
+static int panel_lvds_get_modes(struct drm_panel *panel,
+				struct drm_connector *connector)
 {
 	struct panel_lvds *lvds = to_panel_lvds(panel);
-
-	if (lvds->backlight) {
-		lvds->backlight->props.state &= ~BL_CORE_FBBLANK;
-		lvds->backlight->props.power = FB_BLANK_UNBLANK;
-		backlight_update_status(lvds->backlight);
-	}
-
-	return 0;
-}
-
-static int panel_lvds_get_modes(struct drm_panel *panel)
-{
-	struct panel_lvds *lvds = to_panel_lvds(panel);
-	struct drm_connector *connector = lvds->panel.connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_create(lvds->panel.drm);
+	mode = drm_mode_create(connector->dev);
 	if (!mode)
 		return 0;
 
@@ -132,10 +104,8 @@ static int panel_lvds_get_modes(struct drm_panel *panel)
 }
 
 static const struct drm_panel_funcs panel_lvds_funcs = {
-	.disable = panel_lvds_disable,
 	.unprepare = panel_lvds_unprepare,
 	.prepare = panel_lvds_prepare,
-	.enable = panel_lvds_enable,
 	.get_modes = panel_lvds_get_modes,
 };
 
@@ -242,10 +212,6 @@ static int panel_lvds_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	lvds->backlight = devm_of_find_backlight(lvds->dev);
-	if (IS_ERR(lvds->backlight))
-		return PTR_ERR(lvds->backlight);
-
 	/*
 	 * TODO: Handle all power supplies specified in the DT node in a generic
 	 * way for panels that don't care about power supply ordering. LVDS
@@ -257,6 +223,10 @@ static int panel_lvds_probe(struct platform_device *pdev)
 	drm_panel_init(&lvds->panel, lvds->dev, &panel_lvds_funcs,
 		       DRM_MODE_CONNECTOR_LVDS);
 
+	ret = drm_panel_of_backlight(&lvds->panel);
+	if (ret)
+		return ret;
+
 	ret = drm_panel_add(&lvds->panel);
 	if (ret < 0)
 		return ret;
@@ -271,7 +241,7 @@ static int panel_lvds_remove(struct platform_device *pdev)
 
 	drm_panel_remove(&lvds->panel);
 
-	panel_lvds_disable(&lvds->panel);
+	drm_panel_disable(&lvds->panel);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
index fd593532ab23..c4f83f6384e1 100644
--- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
@@ -123,12 +123,12 @@ static const struct drm_display_mode nl8048_mode = {
 	.height_mm = 53,
 };
 
-static int nl8048_get_modes(struct drm_panel *panel)
+static int nl8048_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &nl8048_mode);
+	mode = drm_mode_duplicate(connector->dev, &nl8048_mode);
 	if (!mode)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt39016.c b/drivers/gpu/drm/panel/panel-novatek-nt39016.c
index 60ccedce530c..a470810f7dbe 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt39016.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt39016.c
@@ -206,14 +206,14 @@ static int nt39016_disable(struct drm_panel *drm_panel)
 	return 0;
 }
 
-static int nt39016_get_modes(struct drm_panel *drm_panel)
+static int nt39016_get_modes(struct drm_panel *drm_panel,
+			     struct drm_connector *connector)
 {
 	struct nt39016 *panel = to_nt39016(drm_panel);
 	const struct nt39016_panel_info *panel_info = panel->panel_info;
-	struct drm_connector *connector = drm_panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(drm_panel->drm, &panel_info->display_mode);
+	mode = drm_mode_duplicate(connector->dev, &panel_info->display_mode);
 	if (!mode)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c b/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c
index f2a72ee6ee07..09deb99981a4 100644
--- a/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c
+++ b/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c
@@ -6,7 +6,6 @@
  *   Author: Stefan Mavrodiev <stefan@olimex.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/crc32.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -68,7 +67,6 @@ struct lcd_olinuxino {
 	bool prepared;
 	bool enabled;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 	struct gpio_desc *enable_gpio;
 
@@ -87,8 +85,6 @@ static int lcd_olinuxino_disable(struct drm_panel *panel)
 	if (!lcd->enabled)
 		return 0;
 
-	backlight_disable(lcd->backlight);
-
 	lcd->enabled = false;
 
 	return 0;
@@ -134,19 +130,16 @@ static int lcd_olinuxino_enable(struct drm_panel *panel)
 	if (lcd->enabled)
 		return 0;
 
-	backlight_enable(lcd->backlight);
-
 	lcd->enabled = true;
 
 	return 0;
 }
 
-static int lcd_olinuxino_get_modes(struct drm_panel *panel)
+static int lcd_olinuxino_get_modes(struct drm_panel *panel,
+				   struct drm_connector *connector)
 {
 	struct lcd_olinuxino *lcd = to_lcd_olinuxino(panel);
-	struct drm_connector *connector = lcd->panel.connector;
 	struct lcd_olinuxino_info *lcd_info = &lcd->eeprom.info;
-	struct drm_device *drm = lcd->panel.drm;
 	struct lcd_olinuxino_mode *lcd_mode;
 	struct drm_display_mode *mode;
 	u32 i, num = 0;
@@ -155,13 +148,13 @@ static int lcd_olinuxino_get_modes(struct drm_panel *panel)
 		lcd_mode = (struct lcd_olinuxino_mode *)
 			   &lcd->eeprom.reserved[i * sizeof(*lcd_mode)];
 
-		mode = drm_mode_create(drm);
+		mode = drm_mode_create(connector->dev);
 		if (!mode) {
-			dev_err(drm->dev, "failed to add mode %ux%u@%u\n",
+			dev_err(panel->dev, "failed to add mode %ux%u@%u\n",
 				lcd_mode->hactive,
 				lcd_mode->vactive,
 				lcd_mode->refresh);
-				continue;
+			continue;
 		}
 
 		mode->clock = lcd_mode->pixelclock;
@@ -284,13 +277,13 @@ static int lcd_olinuxino_probe(struct i2c_client *client,
 	if (IS_ERR(lcd->enable_gpio))
 		return PTR_ERR(lcd->enable_gpio);
 
-	lcd->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(lcd->backlight))
-		return PTR_ERR(lcd->backlight);
-
 	drm_panel_init(&lcd->panel, dev, &lcd_olinuxino_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
+	ret = drm_panel_of_backlight(&lcd->panel);
+	if (ret)
+		return ret;
+
 	return drm_panel_add(&lcd->panel);
 }
 
@@ -300,8 +293,8 @@ static int lcd_olinuxino_remove(struct i2c_client *client)
 
 	drm_panel_remove(&panel->panel);
 
-	lcd_olinuxino_disable(&panel->panel);
-	lcd_olinuxino_unprepare(&panel->panel);
+	drm_panel_disable(&panel->panel);
+	drm_panel_unprepare(&panel->panel);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index bf1f928b215f..bb0c992171e8 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -349,11 +349,12 @@ static int otm8009a_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int otm8009a_get_modes(struct drm_panel *panel)
+static int otm8009a_get_modes(struct drm_panel *panel,
+			      struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_ERROR("failed to add mode %ux%ux@%u\n",
 			  default_mode.hdisplay, default_mode.vdisplay,
@@ -364,10 +365,10 @@ static int otm8009a_get_modes(struct drm_panel *panel)
 	drm_mode_set_name(mode);
 
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = mode->width_mm;
-	panel->connector->display_info.height_mm = mode->height_mm;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
 
 	return 1;
 }
diff --git a/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c b/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
index 2b40913899d8..3a0229d60095 100644
--- a/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
+++ b/drivers/gpu/drm/panel/panel-osd-osd101t2587-53ts.c
@@ -4,7 +4,6 @@
  *  Author: Peter Ujfalusi <peter.ujfalusi@ti.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/regulator/consumer.h>
@@ -20,7 +19,6 @@ struct osd101t2587_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *dsi;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 
 	bool prepared;
@@ -42,8 +40,6 @@ static int osd101t2587_panel_disable(struct drm_panel *panel)
 	if (!osd101t2587->enabled)
 		return 0;
 
-	backlight_disable(osd101t2587->backlight);
-
 	ret = mipi_dsi_shutdown_peripheral(osd101t2587->dsi);
 
 	osd101t2587->enabled = false;
@@ -91,8 +87,6 @@ static int osd101t2587_panel_enable(struct drm_panel *panel)
 	if (ret)
 		return ret;
 
-	backlight_enable(osd101t2587->backlight);
-
 	osd101t2587->enabled = true;
 
 	return ret;
@@ -112,14 +106,15 @@ static const struct drm_display_mode default_mode_osd101t2587 = {
 	.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
 };
 
-static int osd101t2587_panel_get_modes(struct drm_panel *panel)
+static int osd101t2587_panel_get_modes(struct drm_panel *panel,
+				       struct drm_connector *connector)
 {
 	struct osd101t2587_panel *osd101t2587 = ti_osd_panel(panel);
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, osd101t2587->default_mode);
+	mode = drm_mode_duplicate(connector->dev, osd101t2587->default_mode);
 	if (!mode) {
-		dev_err(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
+		dev_err(panel->dev, "failed to add mode %ux%ux@%u\n",
 			osd101t2587->default_mode->hdisplay,
 			osd101t2587->default_mode->vdisplay,
 			osd101t2587->default_mode->vrefresh);
@@ -128,10 +123,10 @@ static int osd101t2587_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 217;
-	panel->connector->display_info.height_mm = 136;
+	connector->display_info.width_mm = 217;
+	connector->display_info.height_mm = 136;
 
 	return 1;
 }
@@ -157,18 +152,19 @@ MODULE_DEVICE_TABLE(of, osd101t2587_of_match);
 static int osd101t2587_panel_add(struct osd101t2587_panel *osd101t2587)
 {
 	struct device *dev = &osd101t2587->dsi->dev;
+	int ret;
 
 	osd101t2587->supply = devm_regulator_get(dev, "power");
 	if (IS_ERR(osd101t2587->supply))
 		return PTR_ERR(osd101t2587->supply);
 
-	osd101t2587->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(osd101t2587->backlight))
-		return PTR_ERR(osd101t2587->backlight);
-
 	drm_panel_init(&osd101t2587->base, &osd101t2587->dsi->dev,
 		       &osd101t2587_panel_funcs, DRM_MODE_CONNECTOR_DSI);
 
+	ret = drm_panel_of_backlight(&osd101t2587->base);
+	if (ret)
+		return ret;
+
 	return drm_panel_add(&osd101t2587->base);
 }
 
@@ -214,12 +210,11 @@ static int osd101t2587_panel_remove(struct mipi_dsi_device *dsi)
 	struct osd101t2587_panel *osd101t2587 = mipi_dsi_get_drvdata(dsi);
 	int ret;
 
-	ret = osd101t2587_panel_disable(&osd101t2587->base);
+	ret = drm_panel_disable(&osd101t2587->base);
 	if (ret < 0)
 		dev_warn(&dsi->dev, "failed to disable panel: %d\n", ret);
 
-	osd101t2587_panel_unprepare(&osd101t2587->base);
-
+	drm_panel_unprepare(&osd101t2587->base);
 	drm_panel_remove(&osd101t2587->base);
 
 	ret = mipi_dsi_detach(dsi);
@@ -233,8 +228,8 @@ static void osd101t2587_panel_shutdown(struct mipi_dsi_device *dsi)
 {
 	struct osd101t2587_panel *osd101t2587 = mipi_dsi_get_drvdata(dsi);
 
-	osd101t2587_panel_disable(&osd101t2587->base);
-	osd101t2587_panel_unprepare(&osd101t2587->base);
+	drm_panel_disable(&osd101t2587->base);
+	drm_panel_unprepare(&osd101t2587->base);
 }
 
 static struct mipi_dsi_driver osd101t2587_panel_driver = {
diff --git a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
index 664605071d34..69693451462e 100644
--- a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
+++ b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
@@ -7,7 +7,6 @@
  * Based on AUO panel driver by Rob Clark <robdclark@gmail.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -31,7 +30,6 @@ struct wuxga_nt_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *dsi;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 
 	bool prepared;
@@ -62,12 +60,6 @@ static int wuxga_nt_panel_disable(struct drm_panel *panel)
 
 	mipi_ret = mipi_dsi_shutdown_peripheral(wuxga_nt->dsi);
 
-	if (wuxga_nt->backlight) {
-		wuxga_nt->backlight->props.power = FB_BLANK_POWERDOWN;
-		wuxga_nt->backlight->props.state |= BL_CORE_FBBLANK;
-		bl_ret = backlight_update_status(wuxga_nt->backlight);
-	}
-
 	wuxga_nt->enabled = false;
 
 	return mipi_ret ? mipi_ret : bl_ret;
@@ -142,12 +134,6 @@ static int wuxga_nt_panel_enable(struct drm_panel *panel)
 	if (wuxga_nt->enabled)
 		return 0;
 
-	if (wuxga_nt->backlight) {
-		wuxga_nt->backlight->props.power = FB_BLANK_UNBLANK;
-		wuxga_nt->backlight->props.state &= ~BL_CORE_FBBLANK;
-		backlight_update_status(wuxga_nt->backlight);
-	}
-
 	wuxga_nt->enabled = true;
 
 	return 0;
@@ -166,24 +152,25 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
-static int wuxga_nt_panel_get_modes(struct drm_panel *panel)
+static int wuxga_nt_panel_get_modes(struct drm_panel *panel,
+				    struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
-		dev_err(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
-				default_mode.hdisplay, default_mode.vdisplay,
-				default_mode.vrefresh);
+		dev_err(panel->dev, "failed to add mode %ux%u@%u\n",
+			default_mode.hdisplay, default_mode.vdisplay,
+			default_mode.vrefresh);
 		return -ENOMEM;
 	}
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 217;
-	panel->connector->display_info.height_mm = 136;
+	connector->display_info.width_mm = 217;
+	connector->display_info.height_mm = 136;
 
 	return 1;
 }
@@ -205,7 +192,6 @@ MODULE_DEVICE_TABLE(of, wuxga_nt_of_match);
 static int wuxga_nt_panel_add(struct wuxga_nt_panel *wuxga_nt)
 {
 	struct device *dev = &wuxga_nt->dsi->dev;
-	struct device_node *np;
 	int ret;
 
 	wuxga_nt->mode = &default_mode;
@@ -214,38 +200,20 @@ static int wuxga_nt_panel_add(struct wuxga_nt_panel *wuxga_nt)
 	if (IS_ERR(wuxga_nt->supply))
 		return PTR_ERR(wuxga_nt->supply);
 
-	np = of_parse_phandle(dev->of_node, "backlight", 0);
-	if (np) {
-		wuxga_nt->backlight = of_find_backlight_by_node(np);
-		of_node_put(np);
-
-		if (!wuxga_nt->backlight)
-			return -EPROBE_DEFER;
-	}
-
 	drm_panel_init(&wuxga_nt->base, &wuxga_nt->dsi->dev,
 		       &wuxga_nt_panel_funcs, DRM_MODE_CONNECTOR_DSI);
 
-	ret = drm_panel_add(&wuxga_nt->base);
-	if (ret < 0)
-		goto put_backlight;
-
-	return 0;
-
-put_backlight:
-	if (wuxga_nt->backlight)
-		put_device(&wuxga_nt->backlight->dev);
+	ret = drm_panel_of_backlight(&wuxga_nt->base);
+	if (ret)
+		return ret;
 
-	return ret;
+	return drm_panel_add(&wuxga_nt->base);
 }
 
 static void wuxga_nt_panel_del(struct wuxga_nt_panel *wuxga_nt)
 {
 	if (wuxga_nt->base.dev)
 		drm_panel_remove(&wuxga_nt->base);
-
-	if (wuxga_nt->backlight)
-		put_device(&wuxga_nt->backlight->dev);
 }
 
 static int wuxga_nt_panel_probe(struct mipi_dsi_device *dsi)
@@ -280,7 +248,7 @@ static int wuxga_nt_panel_remove(struct mipi_dsi_device *dsi)
 	struct wuxga_nt_panel *wuxga_nt = mipi_dsi_get_drvdata(dsi);
 	int ret;
 
-	ret = wuxga_nt_panel_disable(&wuxga_nt->base);
+	ret = drm_panel_disable(&wuxga_nt->base);
 	if (ret < 0)
 		dev_err(&dsi->dev, "failed to disable panel: %d\n", ret);
 
@@ -297,7 +265,7 @@ static void wuxga_nt_panel_shutdown(struct mipi_dsi_device *dsi)
 {
 	struct wuxga_nt_panel *wuxga_nt = mipi_dsi_get_drvdata(dsi);
 
-	wuxga_nt_panel_disable(&wuxga_nt->base);
+	drm_panel_disable(&wuxga_nt->base);
 }
 
 static struct mipi_dsi_driver wuxga_nt_panel_driver = {
diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
index 09824e92fc78..8f078b7dd89e 100644
--- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
+++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
@@ -44,8 +44,6 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -311,10 +309,9 @@ static int rpi_touchscreen_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int rpi_touchscreen_get_modes(struct drm_panel *panel)
+static int rpi_touchscreen_get_modes(struct drm_panel *panel,
+				     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
-	struct drm_device *drm = panel->drm;
 	unsigned int i, num = 0;
 	static const u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
 
@@ -322,9 +319,9 @@ static int rpi_touchscreen_get_modes(struct drm_panel *panel)
 		const struct drm_display_mode *m = &rpi_touchscreen_modes[i];
 		struct drm_display_mode *mode;
 
-		mode = drm_mode_duplicate(drm, m);
+		mode = drm_mode_duplicate(connector->dev, m);
 		if (!mode) {
-			dev_err(drm->dev, "failed to add mode %ux%u@%u\n",
+			dev_err(panel->dev, "failed to add mode %ux%u@%u\n",
 				m->hdisplay, m->vdisplay, m->vrefresh);
 			continue;
 		}
diff --git a/drivers/gpu/drm/panel/panel-raydium-rm67191.c b/drivers/gpu/drm/panel/panel-raydium-rm67191.c
index fd67fc6185c4..313637d53d28 100644
--- a/drivers/gpu/drm/panel/panel-raydium-rm67191.c
+++ b/drivers/gpu/drm/panel/panel-raydium-rm67191.c
@@ -436,12 +436,12 @@ static int rad_panel_disable(struct drm_panel *panel)
 	return 0;
 }
 
-static int rad_panel_get_modes(struct drm_panel *panel)
+static int rad_panel_get_modes(struct drm_panel *panel,
+			       struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_DEV_ERROR(panel->dev, "failed to add mode %ux%ux@%u\n",
 			      default_mode.hdisplay, default_mode.vdisplay,
@@ -451,7 +451,7 @@ static int rad_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_set_name(mode);
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
 	connector->display_info.width_mm = mode->width_mm;
 	connector->display_info.height_mm = mode->height_mm;
diff --git a/drivers/gpu/drm/panel/panel-raydium-rm68200.c b/drivers/gpu/drm/panel/panel-raydium-rm68200.c
index 994e855721f4..e8982948e0ea 100644
--- a/drivers/gpu/drm/panel/panel-raydium-rm68200.c
+++ b/drivers/gpu/drm/panel/panel-raydium-rm68200.c
@@ -6,9 +6,9 @@
  *          Yannick Fertre <yannick.fertre@st.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
 
@@ -78,7 +78,6 @@ struct rm68200 {
 	struct drm_panel panel;
 	struct gpio_desc *reset_gpio;
 	struct regulator *supply;
-	struct backlight_device *backlight;
 	bool prepared;
 	bool enabled;
 };
@@ -242,8 +241,6 @@ static int rm68200_disable(struct drm_panel *panel)
 	if (!ctx->enabled)
 		return 0;
 
-	backlight_disable(ctx->backlight);
-
 	ctx->enabled = false;
 
 	return 0;
@@ -328,18 +325,17 @@ static int rm68200_enable(struct drm_panel *panel)
 	if (ctx->enabled)
 		return 0;
 
-	backlight_enable(ctx->backlight);
-
 	ctx->enabled = true;
 
 	return 0;
 }
 
-static int rm68200_get_modes(struct drm_panel *panel)
+static int rm68200_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_ERROR("failed to add mode %ux%ux@%u\n",
 			  default_mode.hdisplay, default_mode.vdisplay,
@@ -350,10 +346,10 @@ static int rm68200_get_modes(struct drm_panel *panel)
 	drm_mode_set_name(mode);
 
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = mode->width_mm;
-	panel->connector->display_info.height_mm = mode->height_mm;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
 
 	return 1;
 }
@@ -391,10 +387,6 @@ static int rm68200_probe(struct mipi_dsi_device *dsi)
 		return ret;
 	}
 
-	ctx->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(ctx->backlight))
-		return PTR_ERR(ctx->backlight);
-
 	mipi_dsi_set_drvdata(dsi, ctx);
 
 	ctx->dev = dev;
@@ -407,6 +399,10 @@ static int rm68200_probe(struct mipi_dsi_device *dsi)
 	drm_panel_init(&ctx->panel, dev, &rm68200_drm_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
+
 	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
diff --git a/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c b/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c
index 31234b79d3b1..38ff742bc120 100644
--- a/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c
+++ b/drivers/gpu/drm/panel/panel-rocktech-jh057n00900.c
@@ -5,20 +5,22 @@
  * Copyright (C) Purism SPC 2019
  */
 
-#include <drm/drm_mipi_dsi.h>
-#include <drm/drm_modes.h>
-#include <drm/drm_panel.h>
-#include <drm/drm_print.h>
-#include <linux/backlight.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/media-bus-format.h>
+#include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/regulator/consumer.h>
+
 #include <video/display_timing.h>
 #include <video/mipi_display.h>
 
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+
 #define DRV_NAME "panel-rocktech-jh057n00900"
 
 /* Manufacturer specific Commands send via DSI */
@@ -47,7 +49,6 @@ struct jh057n {
 	struct device *dev;
 	struct drm_panel panel;
 	struct gpio_desc *reset_gpio;
-	struct backlight_device *backlight;
 	struct regulator *vcc;
 	struct regulator *iovcc;
 	bool prepared;
@@ -152,7 +153,7 @@ static int jh057n_enable(struct drm_panel *panel)
 		return ret;
 	}
 
-	return backlight_enable(ctx->backlight);
+	return 0;
 }
 
 static int jh057n_disable(struct drm_panel *panel)
@@ -160,7 +161,6 @@ static int jh057n_disable(struct drm_panel *panel)
 	struct jh057n *ctx = panel_to_jh057n(panel);
 	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
 
-	backlight_disable(ctx->backlight);
 	return mipi_dsi_dcs_set_display_off(dsi);
 }
 
@@ -230,12 +230,13 @@ static const struct drm_display_mode default_mode = {
 	.height_mm   = 130,
 };
 
-static int jh057n_get_modes(struct drm_panel *panel)
+static int jh057n_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
 {
 	struct jh057n *ctx = panel_to_jh057n(panel);
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_DEV_ERROR(ctx->dev, "Failed to add mode %ux%u@%u\n",
 			      default_mode.hdisplay, default_mode.vdisplay,
@@ -246,9 +247,9 @@ static int jh057n_get_modes(struct drm_panel *panel)
 	drm_mode_set_name(mode);
 
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
-	panel->connector->display_info.width_mm = mode->width_mm;
-	panel->connector->display_info.height_mm = mode->height_mm;
-	drm_mode_probed_add(panel->connector, mode);
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
+	drm_mode_probed_add(connector, mode);
 
 	return 1;
 }
@@ -320,10 +321,6 @@ static int jh057n_probe(struct mipi_dsi_device *dsi)
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO |
 		MIPI_DSI_MODE_VIDEO_BURST | MIPI_DSI_MODE_VIDEO_SYNC_PULSE;
 
-	ctx->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(ctx->backlight))
-		return PTR_ERR(ctx->backlight);
-
 	ctx->vcc = devm_regulator_get(dev, "vcc");
 	if (IS_ERR(ctx->vcc)) {
 		ret = PTR_ERR(ctx->vcc);
@@ -346,6 +343,10 @@ static int jh057n_probe(struct mipi_dsi_device *dsi)
 	drm_panel_init(&ctx->panel, dev, &jh057n_drm_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
+
 	drm_panel_add(&ctx->panel);
 
 	ret = mipi_dsi_attach(dsi);
diff --git a/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c b/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
index 170a5cda21b9..ef18559e237e 100644
--- a/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
+++ b/drivers/gpu/drm/panel/panel-ronbo-rb070d30.c
@@ -7,7 +7,6 @@
  * This file based on panel-ilitek-ili9881c.c
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -29,7 +28,6 @@
 struct rb070d30_panel {
 	struct drm_panel panel;
 	struct mipi_dsi_device *dsi;
-	struct backlight_device *backlight;
 	struct regulator *supply;
 
 	struct {
@@ -84,22 +82,13 @@ static int rb070d30_panel_enable(struct drm_panel *panel)
 	if (ret)
 		return ret;
 
-	ret = backlight_enable(ctx->backlight);
-	if (ret)
-		goto out;
-
 	return 0;
-
-out:
-	mipi_dsi_dcs_enter_sleep_mode(ctx->dsi);
-	return ret;
 }
 
 static int rb070d30_panel_disable(struct drm_panel *panel)
 {
 	struct rb070d30_panel *ctx = panel_to_rb070d30_panel(panel);
 
-	backlight_disable(ctx->backlight);
 	return mipi_dsi_dcs_enter_sleep_mode(ctx->dsi);
 }
 
@@ -120,14 +109,14 @@ static const struct drm_display_mode default_mode = {
 	.height_mm	= 85,
 };
 
-static int rb070d30_panel_get_modes(struct drm_panel *panel)
+static int rb070d30_panel_get_modes(struct drm_panel *panel,
+				    struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct rb070d30_panel *ctx = panel_to_rb070d30_panel(panel);
 	struct drm_display_mode *mode;
 	static const u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_DEV_ERROR(&ctx->dsi->dev,
 			      "Failed to add mode " DRM_MODE_FMT "\n",
@@ -140,9 +129,9 @@ static int rb070d30_panel_get_modes(struct drm_panel *panel)
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
 	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.bpc = 8;
-	panel->connector->display_info.width_mm = mode->width_mm;
-	panel->connector->display_info.height_mm = mode->height_mm;
+	connector->display_info.bpc = 8;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
 	drm_display_info_set_bus_formats(&connector->display_info,
 					 &bus_format, 1);
 
@@ -208,11 +197,9 @@ static int rb070d30_panel_dsi_probe(struct mipi_dsi_device *dsi)
 		return PTR_ERR(ctx->gpios.shlr);
 	}
 
-	ctx->backlight = devm_of_find_backlight(&dsi->dev);
-	if (IS_ERR(ctx->backlight)) {
-		DRM_DEV_ERROR(&dsi->dev, "Couldn't get our backlight\n");
-		return PTR_ERR(ctx->backlight);
-	}
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
 
 	ret = drm_panel_add(&ctx->panel);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/panel/panel-samsung-ld9040.c b/drivers/gpu/drm/panel/panel-samsung-ld9040.c
index 250809ba37c7..3c52f15f7a1c 100644
--- a/drivers/gpu/drm/panel/panel-samsung-ld9040.c
+++ b/drivers/gpu/drm/panel/panel-samsung-ld9040.c
@@ -261,9 +261,9 @@ static int ld9040_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int ld9040_get_modes(struct drm_panel *panel)
+static int ld9040_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct ld9040 *ctx = panel_to_ld9040(panel);
 	struct drm_display_mode *mode;
 
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c b/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c
index e3a0397e953e..2150043dcf6b 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6d16d0.c
@@ -143,12 +143,12 @@ static int s6d16d0_disable(struct drm_panel *panel)
 	return 0;
 }
 
-static int s6d16d0_get_modes(struct drm_panel *panel)
+static int s6d16d0_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &samsung_s6d16d0_mode);
+	mode = drm_mode_duplicate(connector->dev, &samsung_s6d16d0_mode);
 	if (!mode) {
 		DRM_ERROR("bad mode or failed to add mode\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c b/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c
index 938ab72c5540..36ebd5a4ac7b 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e3ha2.c
@@ -645,13 +645,13 @@ static const struct s6e3ha2_panel_desc samsung_s6e3hf2 = {
 	.type = HF2_TYPE,
 };
 
-static int s6e3ha2_get_modes(struct drm_panel *panel)
+static int s6e3ha2_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct s6e3ha2 *ctx = container_of(panel, struct s6e3ha2, panel);
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, ctx->desc->mode);
+	mode = drm_mode_duplicate(connector->dev, ctx->desc->mode);
 	if (!mode) {
 		DRM_ERROR("failed to add mode %ux%ux@%u\n",
 			ctx->desc->mode->hdisplay, ctx->desc->mode->vdisplay,
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c b/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
index a60635e9226d..a3570e0a90a8 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63j0x03.c
@@ -400,12 +400,12 @@ static int s6e63j0x03_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int s6e63j0x03_get_modes(struct drm_panel *panel)
+static int s6e63j0x03_get_modes(struct drm_panel *panel,
+				struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_ERROR("failed to add mode %ux%ux@%u\n",
 			default_mode.hdisplay, default_mode.vdisplay,
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
index ba01af0b14fd..a5f76eb4fa25 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c
@@ -362,12 +362,12 @@ static int s6e63m0_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int s6e63m0_get_modes(struct drm_panel *panel)
+static int s6e63m0_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
 		DRM_ERROR("failed to add mode %ux%ux@%u\n",
 			  default_mode.hdisplay, default_mode.vdisplay,
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
index dbced6501204..8a028d2bd0d6 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
@@ -920,9 +920,9 @@ static int s6e8aa0_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int s6e8aa0_get_modes(struct drm_panel *panel)
+static int s6e8aa0_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct s6e8aa0 *ctx = panel_to_s6e8aa0(panel);
 	struct drm_display_mode *mode;
 
diff --git a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
index b3619ba443bd..40fcbbbacb2c 100644
--- a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
+++ b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
@@ -6,7 +6,6 @@
  * Based on Panel Simple driver by Thierry Reding <treding@nvidia.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -46,7 +45,6 @@ struct seiko_panel {
 	bool prepared;
 	bool enabled;
 	const struct seiko_panel_desc *desc;
-	struct backlight_device *backlight;
 	struct regulator *dvdd;
 	struct regulator *avdd;
 };
@@ -56,10 +54,9 @@ static inline struct seiko_panel *to_seiko_panel(struct drm_panel *panel)
 	return container_of(panel, struct seiko_panel, base);
 }
 
-static int seiko_panel_get_fixed_modes(struct seiko_panel *panel)
+static int seiko_panel_get_fixed_modes(struct seiko_panel *panel,
+				       struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->base.connector;
-	struct drm_device *drm = panel->base.drm;
 	struct drm_display_mode *mode;
 	unsigned int i, num = 0;
 
@@ -71,9 +68,9 @@ static int seiko_panel_get_fixed_modes(struct seiko_panel *panel)
 		struct videomode vm;
 
 		videomode_from_timing(dt, &vm);
-		mode = drm_mode_create(drm);
+		mode = drm_mode_create(connector->dev);
 		if (!mode) {
-			dev_err(drm->dev, "failed to add mode %ux%u\n",
+			dev_err(panel->base.dev, "failed to add mode %ux%u\n",
 				dt->hactive.typ, dt->vactive.typ);
 			continue;
 		}
@@ -92,9 +89,9 @@ static int seiko_panel_get_fixed_modes(struct seiko_panel *panel)
 	for (i = 0; i < panel->desc->num_modes; i++) {
 		const struct drm_display_mode *m = &panel->desc->modes[i];
 
-		mode = drm_mode_duplicate(drm, m);
+		mode = drm_mode_duplicate(connector->dev, m);
 		if (!mode) {
-			dev_err(drm->dev, "failed to add mode %ux%u@%u\n",
+			dev_err(panel->base.dev, "failed to add mode %ux%u@%u\n",
 				m->hdisplay, m->vdisplay, m->vrefresh);
 			continue;
 		}
@@ -128,12 +125,6 @@ static int seiko_panel_disable(struct drm_panel *panel)
 	if (!p->enabled)
 		return 0;
 
-	if (p->backlight) {
-		p->backlight->props.power = FB_BLANK_POWERDOWN;
-		p->backlight->props.state |= BL_CORE_FBBLANK;
-		backlight_update_status(p->backlight);
-	}
-
 	p->enabled = false;
 
 	return 0;
@@ -197,23 +188,18 @@ static int seiko_panel_enable(struct drm_panel *panel)
 	if (p->enabled)
 		return 0;
 
-	if (p->backlight) {
-		p->backlight->props.state &= ~BL_CORE_FBBLANK;
-		p->backlight->props.power = FB_BLANK_UNBLANK;
-		backlight_update_status(p->backlight);
-	}
-
 	p->enabled = true;
 
 	return 0;
 }
 
-static int seiko_panel_get_modes(struct drm_panel *panel)
+static int seiko_panel_get_modes(struct drm_panel *panel,
+				 struct drm_connector *connector)
 {
 	struct seiko_panel *p = to_seiko_panel(panel);
 
 	/* add hard-coded panel modes */
-	return seiko_panel_get_fixed_modes(p);
+	return seiko_panel_get_fixed_modes(p, connector);
 }
 
 static int seiko_panel_get_timings(struct drm_panel *panel,
@@ -245,7 +231,6 @@ static const struct drm_panel_funcs seiko_panel_funcs = {
 static int seiko_panel_probe(struct device *dev,
 					const struct seiko_panel_desc *desc)
 {
-	struct device_node *backlight;
 	struct seiko_panel *panel;
 	int err;
 
@@ -265,18 +250,13 @@ static int seiko_panel_probe(struct device *dev,
 	if (IS_ERR(panel->avdd))
 		return PTR_ERR(panel->avdd);
 
-	backlight = of_parse_phandle(dev->of_node, "backlight", 0);
-	if (backlight) {
-		panel->backlight = of_find_backlight_by_node(backlight);
-		of_node_put(backlight);
-
-		if (!panel->backlight)
-			return -EPROBE_DEFER;
-	}
-
 	drm_panel_init(&panel->base, dev, &seiko_panel_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
+	err = drm_panel_of_backlight(&panel->base);
+	if (err)
+		return err;
+
 	err = drm_panel_add(&panel->base);
 	if (err < 0)
 		return err;
@@ -291,11 +271,7 @@ static int seiko_panel_remove(struct platform_device *pdev)
 	struct seiko_panel *panel = dev_get_drvdata(&pdev->dev);
 
 	drm_panel_remove(&panel->base);
-
-	seiko_panel_disable(&panel->base);
-
-	if (panel->backlight)
-		put_device(&panel->backlight->dev);
+	drm_panel_disable(&panel->base);
 
 	return 0;
 }
@@ -304,7 +280,7 @@ static void seiko_panel_shutdown(struct platform_device *pdev)
 {
 	struct seiko_panel *panel = dev_get_drvdata(&pdev->dev);
 
-	seiko_panel_disable(&panel->base);
+	drm_panel_disable(&panel->base);
 }
 
 static const struct display_timing seiko_43wvf1g_timing = {
diff --git a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
index 5e136c3ba185..b5d1977221a7 100644
--- a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2014 NVIDIA Corporation
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
@@ -23,7 +22,6 @@ struct sharp_panel {
 	struct mipi_dsi_device *link1;
 	struct mipi_dsi_device *link2;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 
 	bool prepared;
@@ -94,8 +92,6 @@ static int sharp_panel_disable(struct drm_panel *panel)
 	if (!sharp->enabled)
 		return 0;
 
-	backlight_disable(sharp->backlight);
-
 	sharp->enabled = false;
 
 	return 0;
@@ -258,8 +254,6 @@ static int sharp_panel_enable(struct drm_panel *panel)
 	if (sharp->enabled)
 		return 0;
 
-	backlight_enable(sharp->backlight);
-
 	sharp->enabled = true;
 
 	return 0;
@@ -278,13 +272,14 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
-static int sharp_panel_get_modes(struct drm_panel *panel)
+static int sharp_panel_get_modes(struct drm_panel *panel,
+				 struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
-		dev_err(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
+		dev_err(panel->dev, "failed to add mode %ux%ux@%u\n",
 			default_mode.hdisplay, default_mode.vdisplay,
 			default_mode.vrefresh);
 		return -ENOMEM;
@@ -292,10 +287,10 @@ static int sharp_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 217;
-	panel->connector->display_info.height_mm = 136;
+	connector->display_info.width_mm = 217;
+	connector->display_info.height_mm = 136;
 
 	return 1;
 }
@@ -316,7 +311,7 @@ MODULE_DEVICE_TABLE(of, sharp_of_match);
 
 static int sharp_panel_add(struct sharp_panel *sharp)
 {
-	struct device *dev = &sharp->link1->dev;
+	int ret;
 
 	sharp->mode = &default_mode;
 
@@ -324,14 +319,13 @@ static int sharp_panel_add(struct sharp_panel *sharp)
 	if (IS_ERR(sharp->supply))
 		return PTR_ERR(sharp->supply);
 
-	sharp->backlight = devm_of_find_backlight(dev);
-
-	if (IS_ERR(sharp->backlight))
-		return PTR_ERR(sharp->backlight);
-
 	drm_panel_init(&sharp->base, &sharp->link1->dev, &sharp_panel_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
+	ret = drm_panel_of_backlight(&sharp->base);
+	if (ret)
+		return ret;
+
 	return drm_panel_add(&sharp->base);
 }
 
@@ -407,7 +401,7 @@ static int sharp_panel_remove(struct mipi_dsi_device *dsi)
 		return 0;
 	}
 
-	err = sharp_panel_disable(&sharp->base);
+	err = drm_panel_disable(&sharp->base);
 	if (err < 0)
 		dev_err(&dsi->dev, "failed to disable panel: %d\n", err);
 
@@ -428,7 +422,7 @@ static void sharp_panel_shutdown(struct mipi_dsi_device *dsi)
 	if (!sharp)
 		return;
 
-	sharp_panel_disable(&sharp->base);
+	drm_panel_disable(&sharp->base);
 }
 
 static struct mipi_dsi_driver sharp_panel_driver = {
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c b/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c
index eeab7998c7de..1cf3f02435c1 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls037v7dw01.c
@@ -100,12 +100,12 @@ static const struct drm_display_mode ls037v7dw01_mode = {
 	.height_mm = 75,
 };
 
-static int ls037v7dw01_get_modes(struct drm_panel *panel)
+static int ls037v7dw01_get_modes(struct drm_panel *panel,
+				 struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &ls037v7dw01_mode);
+	mode = drm_mode_duplicate(connector->dev, &ls037v7dw01_mode);
 	if (!mode)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
index b963ba4ab589..ce586c6d70c7 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
@@ -7,7 +7,6 @@
  * Based on AUO panel driver by Rob Clark <robdclark@gmail.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
@@ -25,7 +24,6 @@ struct sharp_nt_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *dsi;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 	struct gpio_desc *reset_gpio;
 
@@ -107,8 +105,6 @@ static int sharp_nt_panel_disable(struct drm_panel *panel)
 	if (!sharp_nt->enabled)
 		return 0;
 
-	backlight_disable(sharp_nt->backlight);
-
 	sharp_nt->enabled = false;
 
 	return 0;
@@ -190,8 +186,6 @@ static int sharp_nt_panel_enable(struct drm_panel *panel)
 	if (sharp_nt->enabled)
 		return 0;
 
-	backlight_enable(sharp_nt->backlight);
-
 	sharp_nt->enabled = true;
 
 	return 0;
@@ -210,24 +204,25 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
-static int sharp_nt_panel_get_modes(struct drm_panel *panel)
+static int sharp_nt_panel_get_modes(struct drm_panel *panel,
+				    struct drm_connector *connector)
 {
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
-		dev_err(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
-				default_mode.hdisplay, default_mode.vdisplay,
-				default_mode.vrefresh);
+		dev_err(panel->dev, "failed to add mode %ux%u@%u\n",
+			default_mode.hdisplay, default_mode.vdisplay,
+			default_mode.vrefresh);
 		return -ENOMEM;
 	}
 
 	drm_mode_set_name(mode);
 
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 54;
-	panel->connector->display_info.height_mm = 95;
+	connector->display_info.width_mm = 54;
+	connector->display_info.height_mm = 95;
 
 	return 1;
 }
@@ -243,6 +238,7 @@ static const struct drm_panel_funcs sharp_nt_panel_funcs = {
 static int sharp_nt_panel_add(struct sharp_nt_panel *sharp_nt)
 {
 	struct device *dev = &sharp_nt->dsi->dev;
+	int ret;
 
 	sharp_nt->mode = &default_mode;
 
@@ -259,14 +255,13 @@ static int sharp_nt_panel_add(struct sharp_nt_panel *sharp_nt)
 		gpiod_set_value(sharp_nt->reset_gpio, 0);
 	}
 
-	sharp_nt->backlight = devm_of_find_backlight(dev);
-
-	if (IS_ERR(sharp_nt->backlight))
-		return PTR_ERR(sharp_nt->backlight);
-
 	drm_panel_init(&sharp_nt->base, &sharp_nt->dsi->dev,
 		       &sharp_nt_panel_funcs, DRM_MODE_CONNECTOR_DSI);
 
+	ret = drm_panel_of_backlight(&sharp_nt->base);
+	if (ret)
+		return ret;
+
 	return drm_panel_add(&sharp_nt->base);
 }
 
@@ -308,7 +303,7 @@ static int sharp_nt_panel_remove(struct mipi_dsi_device *dsi)
 	struct sharp_nt_panel *sharp_nt = mipi_dsi_get_drvdata(dsi);
 	int ret;
 
-	ret = sharp_nt_panel_disable(&sharp_nt->base);
+	ret = drm_panel_disable(&sharp_nt->base);
 	if (ret < 0)
 		dev_err(&dsi->dev, "failed to disable panel: %d\n", ret);
 
@@ -325,7 +320,7 @@ static void sharp_nt_panel_shutdown(struct mipi_dsi_device *dsi)
 {
 	struct sharp_nt_panel *sharp_nt = mipi_dsi_get_drvdata(dsi);
 
-	sharp_nt_panel_disable(&sharp_nt->base);
+	drm_panel_disable(&sharp_nt->base);
 }
 
 static const struct of_device_id sharp_nt_of_match[] = {
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 5d487686d25c..e14c14ac62b5 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -21,7 +21,6 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
@@ -105,7 +104,6 @@ struct panel_simple {
 
 	const struct panel_desc *desc;
 
-	struct backlight_device *backlight;
 	struct regulator *supply;
 	struct i2c_adapter *ddc;
 
@@ -119,10 +117,9 @@ static inline struct panel_simple *to_panel_simple(struct drm_panel *panel)
 	return container_of(panel, struct panel_simple, base);
 }
 
-static unsigned int panel_simple_get_timings_modes(struct panel_simple *panel)
+static unsigned int panel_simple_get_timings_modes(struct panel_simple *panel,
+						   struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->base.connector;
-	struct drm_device *drm = panel->base.drm;
 	struct drm_display_mode *mode;
 	unsigned int i, num = 0;
 
@@ -131,9 +128,9 @@ static unsigned int panel_simple_get_timings_modes(struct panel_simple *panel)
 		struct videomode vm;
 
 		videomode_from_timing(dt, &vm);
-		mode = drm_mode_create(drm);
+		mode = drm_mode_create(connector->dev);
 		if (!mode) {
-			dev_err(drm->dev, "failed to add mode %ux%u\n",
+			dev_err(panel->base.dev, "failed to add mode %ux%u\n",
 				dt->hactive.typ, dt->vactive.typ);
 			continue;
 		}
@@ -152,19 +149,18 @@ static unsigned int panel_simple_get_timings_modes(struct panel_simple *panel)
 	return num;
 }
 
-static unsigned int panel_simple_get_display_modes(struct panel_simple *panel)
+static unsigned int panel_simple_get_display_modes(struct panel_simple *panel,
+						   struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->base.connector;
-	struct drm_device *drm = panel->base.drm;
 	struct drm_display_mode *mode;
 	unsigned int i, num = 0;
 
 	for (i = 0; i < panel->desc->num_modes; i++) {
 		const struct drm_display_mode *m = &panel->desc->modes[i];
 
-		mode = drm_mode_duplicate(drm, m);
+		mode = drm_mode_duplicate(connector->dev, m);
 		if (!mode) {
-			dev_err(drm->dev, "failed to add mode %ux%u@%u\n",
+			dev_err(panel->base.dev, "failed to add mode %ux%u@%u\n",
 				m->hdisplay, m->vdisplay, m->vrefresh);
 			continue;
 		}
@@ -183,10 +179,9 @@ static unsigned int panel_simple_get_display_modes(struct panel_simple *panel)
 	return num;
 }
 
-static int panel_simple_get_non_edid_modes(struct panel_simple *panel)
+static int panel_simple_get_non_edid_modes(struct panel_simple *panel,
+					   struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->base.connector;
-	struct drm_device *drm = panel->base.drm;
 	struct drm_display_mode *mode;
 	bool has_override = panel->override_mode.type;
 	unsigned int num = 0;
@@ -195,18 +190,19 @@ static int panel_simple_get_non_edid_modes(struct panel_simple *panel)
 		return 0;
 
 	if (has_override) {
-		mode = drm_mode_duplicate(drm, &panel->override_mode);
+		mode = drm_mode_duplicate(connector->dev,
+					  &panel->override_mode);
 		if (mode) {
 			drm_mode_probed_add(connector, mode);
 			num = 1;
 		} else {
-			dev_err(drm->dev, "failed to add override mode\n");
+			dev_err(panel->base.dev, "failed to add override mode\n");
 		}
 	}
 
 	/* Only add timings if override was not there or failed to validate */
 	if (num == 0 && panel->desc->num_timings)
-		num = panel_simple_get_timings_modes(panel);
+		num = panel_simple_get_timings_modes(panel, connector);
 
 	/*
 	 * Only add fixed modes if timings/override added no mode.
@@ -216,7 +212,7 @@ static int panel_simple_get_non_edid_modes(struct panel_simple *panel)
 	 */
 	WARN_ON(panel->desc->num_timings && panel->desc->num_modes);
 	if (num == 0)
-		num = panel_simple_get_display_modes(panel);
+		num = panel_simple_get_display_modes(panel, connector);
 
 	connector->display_info.bpc = panel->desc->bpc;
 	connector->display_info.width_mm = panel->desc->size.width;
@@ -236,12 +232,6 @@ static int panel_simple_disable(struct drm_panel *panel)
 	if (!p->enabled)
 		return 0;
 
-	if (p->backlight) {
-		p->backlight->props.power = FB_BLANK_POWERDOWN;
-		p->backlight->props.state |= BL_CORE_FBBLANK;
-		backlight_update_status(p->backlight);
-	}
-
 	if (p->desc->delay.disable)
 		msleep(p->desc->delay.disable);
 
@@ -307,34 +297,30 @@ static int panel_simple_enable(struct drm_panel *panel)
 	if (p->desc->delay.enable)
 		msleep(p->desc->delay.enable);
 
-	if (p->backlight) {
-		p->backlight->props.state &= ~BL_CORE_FBBLANK;
-		p->backlight->props.power = FB_BLANK_UNBLANK;
-		backlight_update_status(p->backlight);
-	}
-
 	p->enabled = true;
 
 	return 0;
 }
 
-static int panel_simple_get_modes(struct drm_panel *panel)
+static int panel_simple_get_modes(struct drm_panel *panel,
+				  struct drm_connector *connector)
 {
 	struct panel_simple *p = to_panel_simple(panel);
 	int num = 0;
 
 	/* probe EDID if a DDC bus is available */
 	if (p->ddc) {
-		struct edid *edid = drm_get_edid(panel->connector, p->ddc);
-		drm_connector_update_edid_property(panel->connector, edid);
+		struct edid *edid = drm_get_edid(connector, p->ddc);
+
+		drm_connector_update_edid_property(connector, edid);
 		if (edid) {
-			num += drm_add_edid_modes(panel->connector, edid);
+			num += drm_add_edid_modes(connector, edid);
 			kfree(edid);
 		}
 	}
 
 	/* add hard-coded panel modes */
-	num += panel_simple_get_non_edid_modes(p);
+	num += panel_simple_get_non_edid_modes(p, connector);
 
 	return num;
 }
@@ -414,9 +400,9 @@ static void panel_simple_parse_panel_timing_node(struct device *dev,
 
 static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 {
-	struct device_node *backlight, *ddc;
 	struct panel_simple *panel;
 	struct display_timing dt;
+	struct device_node *ddc;
 	int err;
 
 	panel = devm_kzalloc(dev, sizeof(*panel), GFP_KERNEL);
@@ -442,24 +428,13 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 		return err;
 	}
 
-	backlight = of_parse_phandle(dev->of_node, "backlight", 0);
-	if (backlight) {
-		panel->backlight = of_find_backlight_by_node(backlight);
-		of_node_put(backlight);
-
-		if (!panel->backlight)
-			return -EPROBE_DEFER;
-	}
-
 	ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0);
 	if (ddc) {
 		panel->ddc = of_find_i2c_adapter_by_node(ddc);
 		of_node_put(ddc);
 
-		if (!panel->ddc) {
-			err = -EPROBE_DEFER;
-			goto free_backlight;
-		}
+		if (!panel->ddc)
+			return -EPROBE_DEFER;
 	}
 
 	if (!of_get_display_timing(dev->of_node, "panel-timing", &dt))
@@ -468,6 +443,10 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 	drm_panel_init(&panel->base, dev, &panel_simple_funcs,
 		       desc->connector_type);
 
+	err = drm_panel_of_backlight(&panel->base);
+	if (err)
+		goto free_ddc;
+
 	err = drm_panel_add(&panel->base);
 	if (err < 0)
 		goto free_ddc;
@@ -479,9 +458,6 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 free_ddc:
 	if (panel->ddc)
 		put_device(&panel->ddc->dev);
-free_backlight:
-	if (panel->backlight)
-		put_device(&panel->backlight->dev);
 
 	return err;
 }
@@ -491,16 +467,12 @@ static int panel_simple_remove(struct device *dev)
 	struct panel_simple *panel = dev_get_drvdata(dev);
 
 	drm_panel_remove(&panel->base);
-
-	panel_simple_disable(&panel->base);
-	panel_simple_unprepare(&panel->base);
+	drm_panel_disable(&panel->base);
+	drm_panel_unprepare(&panel->base);
 
 	if (panel->ddc)
 		put_device(&panel->ddc->dev);
 
-	if (panel->backlight)
-		put_device(&panel->backlight->dev);
-
 	return 0;
 }
 
@@ -508,8 +480,8 @@ static void panel_simple_shutdown(struct device *dev)
 {
 	struct panel_simple *panel = dev_get_drvdata(dev);
 
-	panel_simple_disable(&panel->base);
-	panel_simple_unprepare(&panel->base);
+	drm_panel_disable(&panel->base);
+	drm_panel_unprepare(&panel->base);
 }
 
 static const struct drm_display_mode ampire_am_480272h3tmqw_t01h_mode = {
@@ -657,6 +629,35 @@ static const struct panel_desc auo_b101xtn01 = {
 	},
 };
 
+static const struct drm_display_mode auo_b116xak01_mode = {
+	.clock = 69300,
+	.hdisplay = 1366,
+	.hsync_start = 1366 + 48,
+	.hsync_end = 1366 + 48 + 32,
+	.htotal = 1366 + 48 + 32 + 10,
+	.vdisplay = 768,
+	.vsync_start = 768 + 4,
+	.vsync_end = 768 + 4 + 6,
+	.vtotal = 768 + 4 + 6 + 15,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc auo_b116xak01 = {
+	.modes = &auo_b116xak01_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 256,
+		.height = 144,
+	},
+	.delay = {
+		.hpd_absent_delay = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+	.connector_type = DRM_MODE_CONNECTOR_eDP,
+};
+
 static const struct drm_display_mode auo_b116xw03_mode = {
 	.clock = 70589,
 	.hdisplay = 1366,
@@ -1036,6 +1037,38 @@ static const struct panel_desc boe_nv101wxmn51 = {
 	},
 };
 
+static const struct drm_display_mode boe_nv140fhmn49_modes[] = {
+	{
+		.clock = 148500,
+		.hdisplay = 1920,
+		.hsync_start = 1920 + 48,
+		.hsync_end = 1920 + 48 + 32,
+		.htotal = 2200,
+		.vdisplay = 1080,
+		.vsync_start = 1080 + 3,
+		.vsync_end = 1080 + 3 + 5,
+		.vtotal = 1125,
+		.vrefresh = 60,
+	},
+};
+
+static const struct panel_desc boe_nv140fhmn49 = {
+	.modes = boe_nv140fhmn49_modes,
+	.num_modes = ARRAY_SIZE(boe_nv140fhmn49_modes),
+	.bpc = 6,
+	.size = {
+		.width = 309,
+		.height = 174,
+	},
+	.delay = {
+		.prepare = 210,
+		.enable = 50,
+		.unprepare = 160,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+	.connector_type = DRM_MODE_CONNECTOR_eDP,
+};
+
 static const struct drm_display_mode cdtech_s043wq26h_ct7_mode = {
 	.clock = 9000,
 	.hdisplay = 480,
@@ -2061,6 +2094,40 @@ static const struct drm_display_mode mitsubishi_aa070mc01_mode = {
 	.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
 };
 
+static const struct drm_display_mode logicpd_type_28_mode = {
+	.clock = 9000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 3,
+	.hsync_end = 480 + 3 + 42,
+	.htotal = 480 + 3 + 42 + 2,
+
+	.vdisplay = 272,
+	.vsync_start = 272 + 2,
+	.vsync_end = 272 + 2 + 11,
+	.vtotal = 272 + 2 + 11 + 3,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+};
+
+static const struct panel_desc logicpd_type_28 = {
+	.modes = &logicpd_type_28_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 105,
+		.height = 67,
+	},
+	.delay = {
+		.prepare = 200,
+		.enable = 200,
+		.unprepare = 200,
+		.disable = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE |
+		     DRM_BUS_FLAG_SYNC_DRIVE_NEGEDGE,
+};
+
 static const struct panel_desc mitsubishi_aa070mc01 = {
 	.modes = &mitsubishi_aa070mc01_mode,
 	.num_modes = 1,
@@ -2547,6 +2614,30 @@ static const struct panel_desc samsung_ltn140at29_301 = {
 	},
 };
 
+static const struct display_timing satoz_sat050at40h12r2_timing = {
+	.pixelclock = {33300000, 33300000, 50000000},
+	.hactive = {800, 800, 800},
+	.hfront_porch = {16, 210, 354},
+	.hback_porch = {46, 46, 46},
+	.hsync_len = {1, 1, 40},
+	.vactive = {480, 480, 480},
+	.vfront_porch = {7, 22, 147},
+	.vback_porch = {23, 23, 23},
+	.vsync_len = {1, 1, 20},
+};
+
+static const struct panel_desc satoz_sat050at40h12r2 = {
+	.timings = &satoz_sat050at40h12r2_timing,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 108,
+		.height = 65,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.connector_type = DRM_MODE_CONNECTOR_LVDS,
+};
+
 static const struct drm_display_mode sharp_ld_d5116z01b_mode = {
 	.clock = 168480,
 	.hdisplay = 1920,
@@ -3120,6 +3211,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "auo,b101xtn01",
 		.data = &auo_b101xtn01,
 	}, {
+		.compatible = "auo,b116xa01",
+		.data = &auo_b116xak01,
+	}, {
 		.compatible = "auo,b116xw03",
 		.data = &auo_b116xw03,
 	}, {
@@ -3162,6 +3256,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "boe,nv101wxmn51",
 		.data = &boe_nv101wxmn51,
 	}, {
+		.compatible = "boe,nv140fhmn49",
+		.data = &boe_nv140fhmn49,
+	}, {
 		.compatible = "cdtech,s043wq26h-ct7",
 		.data = &cdtech_s043wq26h_ct7,
 	}, {
@@ -3288,6 +3385,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "lg,lp129qe",
 		.data = &lg_lp129qe,
 	}, {
+		.compatible = "logicpd,type28",
+		.data = &logicpd_type_28,
+	}, {
 		.compatible = "mitsubishi,aa070mc01-ca1",
 		.data = &mitsubishi_aa070mc01,
 	}, {
@@ -3348,6 +3448,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "samsung,ltn140at29-301",
 		.data = &samsung_ltn140at29_301,
 	}, {
+		.compatible = "satoz,sat050at40h12r2",
+		.data = &satoz_sat050at40h12r2,
+	}, {
 		.compatible = "sharp,ld-d5116z01b",
 		.data = &sharp_ld_d5116z01b,
 	}, {
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c
index ee3f23f45755..4b4f2558e3b4 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c
@@ -9,7 +9,6 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_print.h>
 
-#include <linux/backlight.h>
 #include <linux/gpio/consumer.h>
 #include <linux/delay.h>
 #include <linux/module.h>
@@ -103,7 +102,6 @@ struct st7701 {
 	struct mipi_dsi_device *dsi;
 	const struct st7701_panel_desc *desc;
 
-	struct backlight_device *backlight;
 	struct regulator_bulk_data *supplies;
 	struct gpio_desc *reset;
 	unsigned int sleep_delay;
@@ -223,7 +221,6 @@ static int st7701_enable(struct drm_panel *panel)
 	struct st7701 *st7701 = panel_to_st7701(panel);
 
 	ST7701_DSI(st7701, MIPI_DCS_SET_DISPLAY_ON, 0x00);
-	backlight_enable(st7701->backlight);
 
 	return 0;
 }
@@ -232,7 +229,6 @@ static int st7701_disable(struct drm_panel *panel)
 {
 	struct st7701 *st7701 = panel_to_st7701(panel);
 
-	backlight_disable(st7701->backlight);
 	ST7701_DSI(st7701, MIPI_DCS_SET_DISPLAY_OFF, 0x00);
 
 	return 0;
@@ -264,13 +260,14 @@ static int st7701_unprepare(struct drm_panel *panel)
 	return 0;
 }
 
-static int st7701_get_modes(struct drm_panel *panel)
+static int st7701_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
 {
 	struct st7701 *st7701 = panel_to_st7701(panel);
 	const struct drm_display_mode *desc_mode = st7701->desc->mode;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, desc_mode);
+	mode = drm_mode_duplicate(connector->dev, desc_mode);
 	if (!mode) {
 		DRM_DEV_ERROR(&st7701->dsi->dev,
 			      "failed to add mode %ux%ux@%u\n",
@@ -280,10 +277,10 @@ static int st7701_get_modes(struct drm_panel *panel)
 	}
 
 	drm_mode_set_name(mode);
-	drm_mode_probed_add(panel->connector, mode);
+	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = desc_mode->width_mm;
-	panel->connector->display_info.height_mm = desc_mode->height_mm;
+	connector->display_info.width_mm = desc_mode->width_mm;
+	connector->display_info.height_mm = desc_mode->height_mm;
 
 	return 1;
 }
@@ -365,10 +362,6 @@ static int st7701_dsi_probe(struct mipi_dsi_device *dsi)
 		return PTR_ERR(st7701->reset);
 	}
 
-	st7701->backlight = devm_of_find_backlight(&dsi->dev);
-	if (IS_ERR(st7701->backlight))
-		return PTR_ERR(st7701->backlight);
-
 	drm_panel_init(&st7701->panel, &dsi->dev, &st7701_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
 
@@ -383,6 +376,10 @@ static int st7701_dsi_probe(struct mipi_dsi_device *dsi)
 	 */
 	st7701->sleep_delay = 120 + desc->panel_sleep_delay;
 
+	ret = drm_panel_of_backlight(&st7701->panel);
+	if (ret)
+		return ret;
+
 	ret = drm_panel_add(&st7701->panel);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 108a85bb6667..cc02c54c1b2e 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2017 Free Electrons
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
@@ -116,7 +115,6 @@ struct st7789v {
 	struct drm_panel panel;
 	struct spi_device *spi;
 	struct gpio_desc *reset;
-	struct backlight_device *backlight;
 	struct regulator *power;
 };
 
@@ -170,14 +168,14 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
-static int st7789v_get_modes(struct drm_panel *panel)
+static int st7789v_get_modes(struct drm_panel *panel,
+			     struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
 	if (!mode) {
-		dev_err(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
+		dev_err(panel->dev, "failed to add mode %ux%ux@%u\n",
 			default_mode.hdisplay, default_mode.vdisplay,
 			default_mode.vrefresh);
 		return -ENOMEM;
@@ -188,8 +186,8 @@ static int st7789v_get_modes(struct drm_panel *panel)
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
 	drm_mode_probed_add(connector, mode);
 
-	panel->connector->display_info.width_mm = 61;
-	panel->connector->display_info.height_mm = 103;
+	connector->display_info.width_mm = 61;
+	connector->display_info.height_mm = 103;
 
 	return 1;
 }
@@ -323,12 +321,6 @@ static int st7789v_enable(struct drm_panel *panel)
 {
 	struct st7789v *ctx = panel_to_st7789v(panel);
 
-	if (ctx->backlight) {
-		ctx->backlight->props.state &= ~BL_CORE_FBBLANK;
-		ctx->backlight->props.power = FB_BLANK_UNBLANK;
-		backlight_update_status(ctx->backlight);
-	}
-
 	return st7789v_write_command(ctx, MIPI_DCS_SET_DISPLAY_ON);
 }
 
@@ -339,12 +331,6 @@ static int st7789v_disable(struct drm_panel *panel)
 
 	ST7789V_TEST(ret, st7789v_write_command(ctx, MIPI_DCS_SET_DISPLAY_OFF));
 
-	if (ctx->backlight) {
-		ctx->backlight->props.power = FB_BLANK_POWERDOWN;
-		ctx->backlight->props.state |= BL_CORE_FBBLANK;
-		backlight_update_status(ctx->backlight);
-	}
-
 	return 0;
 }
 
@@ -370,7 +356,6 @@ static const struct drm_panel_funcs st7789v_drm_funcs = {
 
 static int st7789v_probe(struct spi_device *spi)
 {
-	struct device_node *backlight;
 	struct st7789v *ctx;
 	int ret;
 
@@ -394,26 +379,15 @@ static int st7789v_probe(struct spi_device *spi)
 		return PTR_ERR(ctx->reset);
 	}
 
-	backlight = of_parse_phandle(spi->dev.of_node, "backlight", 0);
-	if (backlight) {
-		ctx->backlight = of_find_backlight_by_node(backlight);
-		of_node_put(backlight);
-
-		if (!ctx->backlight)
-			return -EPROBE_DEFER;
-	}
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
 
 	ret = drm_panel_add(&ctx->panel);
 	if (ret < 0)
-		goto err_free_backlight;
+		return ret;
 
 	return 0;
-
-err_free_backlight:
-	if (ctx->backlight)
-		put_device(&ctx->backlight->dev);
-
-	return ret;
 }
 
 static int st7789v_remove(struct spi_device *spi)
@@ -422,9 +396,6 @@ static int st7789v_remove(struct spi_device *spi)
 
 	drm_panel_remove(&ctx->panel);
 
-	if (ctx->backlight)
-		put_device(&ctx->backlight->dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/panel/panel-sony-acx424akp.c b/drivers/gpu/drm/panel/panel-sony-acx424akp.c
new file mode 100644
index 000000000000..de0abf76ae6f
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-sony-acx424akp.c
@@ -0,0 +1,550 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * MIPI-DSI Sony ACX424AKP panel driver. This is a 480x864
+ * AMOLED panel with a command-only DSI interface.
+ *
+ * Copyright (C) Linaro Ltd. 2019
+ * Author: Linus Walleij
+ * Based on code and know-how from Marcus Lorentzon
+ * Copyright (C) ST-Ericsson SA 2010
+ */
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regulator/consumer.h>
+
+#include <video/mipi_display.h>
+
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+
+#define ACX424_DCS_READ_ID1		0xDA
+#define ACX424_DCS_READ_ID2		0xDB
+#define ACX424_DCS_READ_ID3		0xDC
+#define ACX424_DCS_SET_MDDI		0xAE
+
+/*
+ * Sony seems to use vendor ID 0x81
+ */
+#define DISPLAY_SONY_ACX424AKP_ID1	0x811b
+#define DISPLAY_SONY_ACX424AKP_ID2	0x811a
+/*
+ * The third ID looks like a bug, vendor IDs begin at 0x80
+ * and panel 00 ... seems like default values.
+ */
+#define DISPLAY_SONY_ACX424AKP_ID3	0x8000
+
+struct acx424akp {
+	struct drm_panel panel;
+	struct device *dev;
+	struct backlight_device *bl;
+	struct regulator *supply;
+	struct gpio_desc *reset_gpio;
+	bool video_mode;
+};
+
+static const struct drm_display_mode sony_acx424akp_vid_mode = {
+	.clock = 330000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 15,
+	.hsync_end = 480 + 15 + 0,
+	.htotal = 480 + 15 + 0 + 15,
+	.vdisplay = 864,
+	.vsync_start = 864 + 14,
+	.vsync_end = 864 + 14 + 1,
+	.vtotal = 864 + 14 + 1 + 11,
+	.vrefresh = 60,
+	.width_mm = 48,
+	.height_mm = 84,
+	.flags = DRM_MODE_FLAG_PVSYNC,
+};
+
+/*
+ * The timings are not very helpful as the display is used in
+ * command mode using the maximum HS frequency.
+ */
+static const struct drm_display_mode sony_acx424akp_cmd_mode = {
+	.clock = 420160,
+	.hdisplay = 480,
+	.hsync_start = 480 + 154,
+	.hsync_end = 480 + 154 + 16,
+	.htotal = 480 + 154 + 16 + 32,
+	.vdisplay = 864,
+	.vsync_start = 864 + 1,
+	.vsync_end = 864 + 1 + 1,
+	.vtotal = 864 + 1 + 1 + 1,
+	/*
+	 * Some desired refresh rate, experiments at the maximum "pixel"
+	 * clock speed (HS clock 420 MHz) yields around 117Hz.
+	 */
+	.vrefresh = 60,
+	.width_mm = 48,
+	.height_mm = 84,
+};
+
+static inline struct acx424akp *panel_to_acx424akp(struct drm_panel *panel)
+{
+	return container_of(panel, struct acx424akp, panel);
+}
+
+#define FOSC			20 /* 20Mhz */
+#define SCALE_FACTOR_NS_DIV_MHZ	1000
+
+static int acx424akp_set_brightness(struct backlight_device *bl)
+{
+	struct acx424akp *acx = bl_get_data(bl);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(acx->dev);
+	int period_ns = 1023;
+	int duty_ns = bl->props.brightness;
+	u8 pwm_ratio;
+	u8 pwm_div;
+	u8 par;
+	int ret;
+
+	/* Calculate the PWM duty cycle in n/256's */
+	pwm_ratio = max(((duty_ns * 256) / period_ns) - 1, 1);
+	pwm_div = max(1,
+		      ((FOSC * period_ns) / 256) /
+		      SCALE_FACTOR_NS_DIV_MHZ);
+
+	/* Set up PWM dutycycle ONE byte (differs from the standard) */
+	DRM_DEV_DEBUG(acx->dev, "calculated duty cycle %02x\n", pwm_ratio);
+	ret = mipi_dsi_dcs_write(dsi, MIPI_DCS_SET_DISPLAY_BRIGHTNESS,
+				 &pwm_ratio, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to set display PWM ratio (%d)\n",
+			      ret);
+		return ret;
+	}
+
+	/*
+	 * Sequence to write PWMDIV:
+	 *	address		data
+	 *	0xF3		0xAA   CMD2 Unlock
+	 *	0x00		0x01   Enter CMD2 page 0
+	 *	0X7D		0x01   No reload MTP of CMD2 P1
+	 *	0x22		PWMDIV
+	 *	0x7F		0xAA   CMD2 page 1 lock
+	 */
+	par = 0xaa;
+	ret = mipi_dsi_dcs_write(dsi, 0xf3, &par, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to unlock CMD 2 (%d)\n",
+			      ret);
+		return ret;
+	}
+	par = 0x01;
+	ret = mipi_dsi_dcs_write(dsi, 0x00, &par, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to enter page 1 (%d)\n",
+			      ret);
+		return ret;
+	}
+	par = 0x01;
+	ret = mipi_dsi_dcs_write(dsi, 0x7d, &par, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to disable MTP reload (%d)\n",
+			      ret);
+		return ret;
+	}
+	ret = mipi_dsi_dcs_write(dsi, 0x22, &pwm_div, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to set PWM divisor (%d)\n",
+			      ret);
+		return ret;
+	}
+	par = 0xaa;
+	ret = mipi_dsi_dcs_write(dsi, 0x7f, &par, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to lock CMD 2 (%d)\n",
+			      ret);
+		return ret;
+	}
+
+	/* Enable backlight */
+	par = 0x24;
+	ret = mipi_dsi_dcs_write(dsi, MIPI_DCS_WRITE_CONTROL_DISPLAY,
+				 &par, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to enable display backlight (%d)\n",
+			      ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct backlight_ops acx424akp_bl_ops = {
+	.update_status = acx424akp_set_brightness,
+};
+
+static int acx424akp_read_id(struct acx424akp *acx)
+{
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(acx->dev);
+	u8 vendor, version, panel;
+	u16 val;
+	int ret;
+
+	ret = mipi_dsi_dcs_read(dsi, ACX424_DCS_READ_ID1, &vendor, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev, "could not vendor ID byte\n");
+		return ret;
+	}
+	ret = mipi_dsi_dcs_read(dsi, ACX424_DCS_READ_ID2, &version, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev, "could not read device version byte\n");
+		return ret;
+	}
+	ret = mipi_dsi_dcs_read(dsi, ACX424_DCS_READ_ID3, &panel, 1);
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev, "could not read panel ID byte\n");
+		return ret;
+	}
+
+	if (vendor == 0x00) {
+		DRM_DEV_ERROR(acx->dev, "device vendor ID is zero\n");
+		return -ENODEV;
+	}
+
+	val = (vendor << 8) | panel;
+	switch (val) {
+	case DISPLAY_SONY_ACX424AKP_ID1:
+	case DISPLAY_SONY_ACX424AKP_ID2:
+	case DISPLAY_SONY_ACX424AKP_ID3:
+		DRM_DEV_INFO(acx->dev,
+			     "MTP vendor: %02x, version: %02x, panel: %02x\n",
+			     vendor, version, panel);
+		break;
+	default:
+		DRM_DEV_INFO(acx->dev,
+			     "unknown vendor: %02x, version: %02x, panel: %02x\n",
+			     vendor, version, panel);
+		break;
+	}
+
+	return 0;
+}
+
+static int acx424akp_power_on(struct acx424akp *acx)
+{
+	int ret;
+
+	ret = regulator_enable(acx->supply);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to enable supply (%d)\n", ret);
+		return ret;
+	}
+
+	/* Assert RESET */
+	gpiod_set_value_cansleep(acx->reset_gpio, 1);
+	udelay(20);
+	/* De-assert RESET */
+	gpiod_set_value_cansleep(acx->reset_gpio, 0);
+	usleep_range(11000, 20000);
+
+	return 0;
+}
+
+static void acx424akp_power_off(struct acx424akp *acx)
+{
+	/* Assert RESET */
+	gpiod_set_value_cansleep(acx->reset_gpio, 1);
+	usleep_range(11000, 20000);
+
+	regulator_disable(acx->supply);
+}
+
+static int acx424akp_prepare(struct drm_panel *panel)
+{
+	struct acx424akp *acx = panel_to_acx424akp(panel);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(acx->dev);
+	const u8 mddi = 3;
+	int ret;
+
+	ret = acx424akp_power_on(acx);
+	if (ret)
+		return ret;
+
+	ret = acx424akp_read_id(acx);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to read panel ID (%d)\n", ret);
+		goto err_power_off;
+	}
+
+	/* Enabe tearing mode: send TE (tearing effect) at VBLANK */
+	ret = mipi_dsi_dcs_set_tear_on(dsi,
+				       MIPI_DSI_DCS_TEAR_MODE_VBLANK);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to enable vblank TE (%d)\n",
+			      ret);
+		goto err_power_off;
+	}
+
+	/*
+	 * Set MDDI
+	 *
+	 * This presumably deactivates the Qualcomm MDDI interface and
+	 * selects DSI, similar code is found in other drivers such as the
+	 * Sharp LS043T1LE01 which makes us suspect that this panel may be
+	 * using a Novatek NT35565 or similar display driver chip that shares
+	 * this command. Due to the lack of documentation we cannot know for
+	 * sure.
+	 */
+	ret = mipi_dsi_dcs_write(dsi, ACX424_DCS_SET_MDDI,
+				 &mddi, sizeof(mddi));
+	if (ret < 0) {
+		DRM_DEV_ERROR(acx->dev, "failed to set MDDI (%d)\n", ret);
+		goto err_power_off;
+	}
+
+	/* Exit sleep mode */
+	ret = mipi_dsi_dcs_exit_sleep_mode(dsi);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to exit sleep mode (%d)\n",
+			      ret);
+		goto err_power_off;
+	}
+	msleep(140);
+
+	ret = mipi_dsi_dcs_set_display_on(dsi);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to turn display on (%d)\n",
+			      ret);
+		goto err_power_off;
+	}
+	if (acx->video_mode) {
+		/* In video mode turn peripheral on */
+		ret = mipi_dsi_turn_on_peripheral(dsi);
+		if (ret) {
+			dev_err(acx->dev, "failed to turn on peripheral\n");
+			goto err_power_off;
+		}
+	}
+
+	acx->bl->props.power = FB_BLANK_NORMAL;
+
+	return 0;
+
+err_power_off:
+	acx424akp_power_off(acx);
+	return ret;
+}
+
+static int acx424akp_unprepare(struct drm_panel *panel)
+{
+	struct acx424akp *acx = panel_to_acx424akp(panel);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(acx->dev);
+	u8 par;
+	int ret;
+
+	/* Disable backlight */
+	par = 0x00;
+	ret = mipi_dsi_dcs_write(dsi, MIPI_DCS_WRITE_CONTROL_DISPLAY,
+				 &par, 1);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev,
+			      "failed to disable display backlight (%d)\n",
+			      ret);
+		return ret;
+	}
+
+	ret = mipi_dsi_dcs_set_display_off(dsi);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to turn display off (%d)\n",
+			      ret);
+		return ret;
+	}
+
+	/* Enter sleep mode */
+	ret = mipi_dsi_dcs_enter_sleep_mode(dsi);
+	if (ret) {
+		DRM_DEV_ERROR(acx->dev, "failed to enter sleep mode (%d)\n",
+			      ret);
+		return ret;
+	}
+	msleep(85);
+
+	acx424akp_power_off(acx);
+	acx->bl->props.power = FB_BLANK_POWERDOWN;
+
+	return 0;
+}
+
+static int acx424akp_enable(struct drm_panel *panel)
+{
+	struct acx424akp *acx = panel_to_acx424akp(panel);
+
+	/*
+	 * The backlight is on as long as the display is on
+	 * so no use to call backlight_enable() here.
+	 */
+	acx->bl->props.power = FB_BLANK_UNBLANK;
+
+	return 0;
+}
+
+static int acx424akp_disable(struct drm_panel *panel)
+{
+	struct acx424akp *acx = panel_to_acx424akp(panel);
+
+	/*
+	 * The backlight is on as long as the display is on
+	 * so no use to call backlight_disable() here.
+	 */
+	acx->bl->props.power = FB_BLANK_NORMAL;
+
+	return 0;
+}
+
+static int acx424akp_get_modes(struct drm_panel *panel,
+			       struct drm_connector *connector)
+{
+	struct acx424akp *acx = panel_to_acx424akp(panel);
+	struct drm_display_mode *mode;
+
+	if (acx->video_mode)
+		mode = drm_mode_duplicate(connector->dev,
+					  &sony_acx424akp_vid_mode);
+	else
+		mode = drm_mode_duplicate(connector->dev,
+					  &sony_acx424akp_cmd_mode);
+	if (!mode) {
+		DRM_ERROR("bad mode or failed to add mode\n");
+		return -EINVAL;
+	}
+	drm_mode_set_name(mode);
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
+
+	drm_mode_probed_add(connector, mode);
+
+	return 1; /* Number of modes */
+}
+
+static const struct drm_panel_funcs acx424akp_drm_funcs = {
+	.disable = acx424akp_disable,
+	.unprepare = acx424akp_unprepare,
+	.prepare = acx424akp_prepare,
+	.enable = acx424akp_enable,
+	.get_modes = acx424akp_get_modes,
+};
+
+static int acx424akp_probe(struct mipi_dsi_device *dsi)
+{
+	struct device *dev = &dsi->dev;
+	struct acx424akp *acx;
+	int ret;
+
+	acx = devm_kzalloc(dev, sizeof(struct acx424akp), GFP_KERNEL);
+	if (!acx)
+		return -ENOMEM;
+	acx->video_mode = of_property_read_bool(dev->of_node,
+						"enforce-video-mode");
+
+	mipi_dsi_set_drvdata(dsi, acx);
+	acx->dev = dev;
+
+	dsi->lanes = 2;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	/*
+	 * FIXME: these come from the ST-Ericsson vendor driver for the
+	 * HREF520 and seems to reflect limitations in the PLLs on that
+	 * platform, if you have the datasheet, please cross-check the
+	 * actual max rates.
+	 */
+	dsi->lp_rate = 19200000;
+	dsi->hs_rate = 420160000;
+
+	if (acx->video_mode)
+		/* Burst mode using event for sync */
+		dsi->mode_flags =
+			MIPI_DSI_MODE_VIDEO |
+			MIPI_DSI_MODE_VIDEO_BURST;
+	else
+		dsi->mode_flags =
+			MIPI_DSI_CLOCK_NON_CONTINUOUS |
+			MIPI_DSI_MODE_EOT_PACKET;
+
+	acx->supply = devm_regulator_get(dev, "vddi");
+	if (IS_ERR(acx->supply))
+		return PTR_ERR(acx->supply);
+
+	/* This asserts RESET by default */
+	acx->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						  GPIOD_OUT_HIGH);
+	if (IS_ERR(acx->reset_gpio)) {
+		ret = PTR_ERR(acx->reset_gpio);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev, "failed to request GPIO (%d)\n",
+				      ret);
+		return ret;
+	}
+
+	drm_panel_init(&acx->panel, dev, &acx424akp_drm_funcs,
+		       DRM_MODE_CONNECTOR_DSI);
+
+	acx->bl = devm_backlight_device_register(dev, "acx424akp", dev, acx,
+						 &acx424akp_bl_ops, NULL);
+	if (IS_ERR(acx->bl)) {
+		DRM_DEV_ERROR(dev, "failed to register backlight device\n");
+		return PTR_ERR(acx->bl);
+	}
+	acx->bl->props.max_brightness = 1023;
+	acx->bl->props.brightness = 512;
+	acx->bl->props.power = FB_BLANK_POWERDOWN;
+
+	ret = drm_panel_add(&acx->panel);
+	if (ret < 0)
+		return ret;
+
+	ret = mipi_dsi_attach(dsi);
+	if (ret < 0) {
+		drm_panel_remove(&acx->panel);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int acx424akp_remove(struct mipi_dsi_device *dsi)
+{
+	struct acx424akp *acx = mipi_dsi_get_drvdata(dsi);
+
+	mipi_dsi_detach(dsi);
+	drm_panel_remove(&acx->panel);
+
+	return 0;
+}
+
+static const struct of_device_id acx424akp_of_match[] = {
+	{ .compatible = "sony,acx424akp" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, acx424akp_of_match);
+
+static struct mipi_dsi_driver acx424akp_driver = {
+	.probe = acx424akp_probe,
+	.remove = acx424akp_remove,
+	.driver = {
+		.name = "panel-sony-acx424akp",
+		.of_match_table = acx424akp_of_match,
+	},
+};
+module_mipi_dsi_driver(acx424akp_driver);
+
+MODULE_AUTHOR("Linus Wallei <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("MIPI-DSI Sony acx424akp Panel Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
index d6387d8f88a3..5c4b6f6e5c2d 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
@@ -521,12 +521,12 @@ static const struct drm_display_mode acx565akm_mode = {
 	.height_mm = 46,
 };
 
-static int acx565akm_get_modes(struct drm_panel *panel)
+static int acx565akm_get_modes(struct drm_panel *panel,
+			       struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &acx565akm_mode);
+	mode = drm_mode_duplicate(connector->dev, &acx565akm_mode);
 	if (!mode)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
index c44d6a65c0aa..cf29405a2dbe 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
@@ -17,7 +17,6 @@
  * H. Nikolaus Schaller <hns@goldelico.com>
  */
 
-#include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/spi/spi.h>
@@ -83,7 +82,6 @@ struct td028ttec1_panel {
 	struct drm_panel panel;
 
 	struct spi_device *spi;
-	struct backlight_device *backlight;
 };
 
 #define to_td028ttec1_device(p) container_of(p, struct td028ttec1_panel, panel)
@@ -243,8 +241,6 @@ static int td028ttec1_enable(struct drm_panel *panel)
 	if (ret)
 		return ret;
 
-	backlight_enable(lcd->backlight);
-
 	return 0;
 }
 
@@ -252,8 +248,6 @@ static int td028ttec1_disable(struct drm_panel *panel)
 {
 	struct td028ttec1_panel *lcd = to_td028ttec1_device(panel);
 
-	backlight_disable(lcd->backlight);
-
 	jbt_ret_write_0(lcd, JBT_REG_DISPLAY_OFF, NULL);
 
 	return 0;
@@ -287,12 +281,12 @@ static const struct drm_display_mode td028ttec1_mode = {
 	.height_mm = 58,
 };
 
-static int td028ttec1_get_modes(struct drm_panel *panel)
+static int td028ttec1_get_modes(struct drm_panel *panel,
+				struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &td028ttec1_mode);
+	mode = drm_mode_duplicate(connector->dev, &td028ttec1_mode);
 	if (!mode)
 		return -ENOMEM;
 
@@ -334,10 +328,6 @@ static int td028ttec1_probe(struct spi_device *spi)
 	spi_set_drvdata(spi, lcd);
 	lcd->spi = spi;
 
-	lcd->backlight = devm_of_find_backlight(&spi->dev);
-	if (IS_ERR(lcd->backlight))
-		return PTR_ERR(lcd->backlight);
-
 	spi->mode = SPI_MODE_3;
 	spi->bits_per_word = 9;
 
@@ -350,6 +340,10 @@ static int td028ttec1_probe(struct spi_device *spi)
 	drm_panel_init(&lcd->panel, &lcd->spi->dev, &td028ttec1_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
 
+	ret = drm_panel_of_backlight(&lcd->panel);
+	if (ret)
+		return ret;
+
 	return drm_panel_add(&lcd->panel);
 }
 
diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
index 621b65feec07..75f1f1f1b6de 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
@@ -346,12 +346,12 @@ static const struct drm_display_mode td043mtea1_mode = {
 	.height_mm = 56,
 };
 
-static int td043mtea1_get_modes(struct drm_panel *panel)
+static int td043mtea1_get_modes(struct drm_panel *panel,
+				struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &td043mtea1_mode);
+	mode = drm_mode_duplicate(connector->dev, &td043mtea1_mode);
 	if (!mode)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/panel/panel-tpo-tpg110.c b/drivers/gpu/drm/panel/panel-tpo-tpg110.c
index 1a5418ae2ccf..8472d018c16f 100644
--- a/drivers/gpu/drm/panel/panel-tpo-tpg110.c
+++ b/drivers/gpu/drm/panel/panel-tpo-tpg110.c
@@ -14,13 +14,13 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_print.h>
 
-#include <linux/backlight.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 
@@ -77,10 +77,6 @@ struct tpg110 {
 	 */
 	struct drm_panel panel;
 	/**
-	 * @backlight: backlight for this panel
-	 */
-	struct backlight_device *backlight;
-	/**
 	 * @panel_type: the panel mode as detected
 	 */
 	const struct tpg110_panel_mode *panel_mode;
@@ -356,8 +352,6 @@ static int tpg110_disable(struct drm_panel *panel)
 	val &= ~TPG110_CTRL2_PM;
 	tpg110_write_reg(tpg, TPG110_CTRL2_PM, val);
 
-	backlight_disable(tpg->backlight);
-
 	return 0;
 }
 
@@ -366,8 +360,6 @@ static int tpg110_enable(struct drm_panel *panel)
 	struct tpg110 *tpg = to_tpg110(panel);
 	u8 val;
 
-	backlight_enable(tpg->backlight);
-
 	/* Take chip out of standby */
 	val = tpg110_read_reg(tpg, TPG110_CTRL2_PM);
 	val |= TPG110_CTRL2_PM;
@@ -384,9 +376,9 @@ static int tpg110_enable(struct drm_panel *panel)
  * presents the mode that is configured for the system under use,
  * and which is detected by reading the registers of the display.
  */
-static int tpg110_get_modes(struct drm_panel *panel)
+static int tpg110_get_modes(struct drm_panel *panel,
+			    struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct tpg110 *tpg = to_tpg110(panel);
 	struct drm_display_mode *mode;
 
@@ -394,7 +386,7 @@ static int tpg110_get_modes(struct drm_panel *panel)
 	connector->display_info.height_mm = tpg->height;
 	connector->display_info.bus_flags = tpg->panel_mode->bus_flags;
 
-	mode = drm_mode_duplicate(panel->drm, &tpg->panel_mode->mode);
+	mode = drm_mode_duplicate(connector->dev, &tpg->panel_mode->mode);
 	drm_mode_set_name(mode);
 	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
 
@@ -432,11 +424,6 @@ static int tpg110_probe(struct spi_device *spi)
 	if (ret)
 		DRM_DEV_ERROR(dev, "no panel height specified\n");
 
-	/* Look for some optional backlight */
-	tpg->backlight = devm_of_find_backlight(dev);
-	if (IS_ERR(tpg->backlight))
-		return PTR_ERR(tpg->backlight);
-
 	/* This asserts the GRESTB signal, putting the display into reset */
 	tpg->grestb = devm_gpiod_get(dev, "grestb", GPIOD_OUT_HIGH);
 	if (IS_ERR(tpg->grestb)) {
@@ -459,6 +446,11 @@ static int tpg110_probe(struct spi_device *spi)
 
 	drm_panel_init(&tpg->panel, dev, &tpg110_drm_funcs,
 		       DRM_MODE_CONNECTOR_DPI);
+
+	ret = drm_panel_of_backlight(&tpg->panel);
+	if (ret)
+		return ret;
+
 	spi_set_drvdata(spi, tpg);
 
 	return drm_panel_add(&tpg->panel);
diff --git a/drivers/gpu/drm/panel/panel-truly-nt35597.c b/drivers/gpu/drm/panel/panel-truly-nt35597.c
index 0feea2456e14..012ca62bf30e 100644
--- a/drivers/gpu/drm/panel/panel-truly-nt35597.c
+++ b/drivers/gpu/drm/panel/panel-truly-nt35597.c
@@ -454,9 +454,9 @@ static int truly_nt35597_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static int truly_nt35597_get_modes(struct drm_panel *panel)
+static int truly_nt35597_get_modes(struct drm_panel *panel,
+				   struct drm_connector *connector)
 {
-	struct drm_connector *connector = panel->connector;
 	struct truly_nt35597 *ctx = panel_to_ctx(panel);
 	struct drm_display_mode *mode;
 	const struct nt35597_config *config;
diff --git a/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c b/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c
new file mode 100644
index 000000000000..1645aceab597
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-xinpeng-xpp055c272.c
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Xinpeng xpp055c272 5.5" MIPI-DSI panel driver
+ * Copyright (C) 2019 Theobroma Systems Design und Consulting GmbH
+ *
+ * based on
+ *
+ * Rockteck jh057n00900 5.5" MIPI-DSI panel driver
+ * Copyright (C) Purism SPC 2019
+ */
+
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_print.h>
+
+#include <video/display_timing.h>
+#include <video/mipi_display.h>
+
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/media-bus-format.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regulator/consumer.h>
+
+/* Manufacturer specific Commands send via DSI */
+#define XPP055C272_CMD_ALL_PIXEL_OFF	0x22
+#define XPP055C272_CMD_ALL_PIXEL_ON	0x23
+#define XPP055C272_CMD_SETDISP		0xb2
+#define XPP055C272_CMD_SETRGBIF		0xb3
+#define XPP055C272_CMD_SETCYC		0xb4
+#define XPP055C272_CMD_SETBGP		0xb5
+#define XPP055C272_CMD_SETVCOM		0xb6
+#define XPP055C272_CMD_SETOTP		0xb7
+#define XPP055C272_CMD_SETPOWER_EXT	0xb8
+#define XPP055C272_CMD_SETEXTC		0xb9
+#define XPP055C272_CMD_SETMIPI		0xbA
+#define XPP055C272_CMD_SETVDC		0xbc
+#define XPP055C272_CMD_SETPCR		0xbf
+#define XPP055C272_CMD_SETSCR		0xc0
+#define XPP055C272_CMD_SETPOWER		0xc1
+#define XPP055C272_CMD_SETECO		0xc6
+#define XPP055C272_CMD_SETPANEL		0xcc
+#define XPP055C272_CMD_SETGAMMA		0xe0
+#define XPP055C272_CMD_SETEQ		0xe3
+#define XPP055C272_CMD_SETGIP1		0xe9
+#define XPP055C272_CMD_SETGIP2		0xea
+
+struct xpp055c272 {
+	struct device *dev;
+	struct drm_panel panel;
+	struct gpio_desc *reset_gpio;
+	struct regulator *vci;
+	struct regulator *iovcc;
+	bool prepared;
+};
+
+static inline struct xpp055c272 *panel_to_xpp055c272(struct drm_panel *panel)
+{
+	return container_of(panel, struct xpp055c272, panel);
+}
+
+#define dsi_generic_write_seq(dsi, cmd, seq...) do {			\
+		static const u8 d[] = { seq };				\
+		int ret;						\
+		ret = mipi_dsi_dcs_write(dsi, cmd, d, ARRAY_SIZE(d));	\
+		if (ret < 0)						\
+			return ret;					\
+	} while (0)
+
+static int xpp055c272_init_sequence(struct xpp055c272 *ctx)
+{
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+	struct device *dev = ctx->dev;
+
+	/*
+	 * Init sequence was supplied by the panel vendor without much
+	 * documentation.
+	 */
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETEXTC, 0xf1, 0x12, 0x83);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETMIPI,
+			      0x33, 0x81, 0x05, 0xf9, 0x0e, 0x0e, 0x00, 0x00,
+			      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x44, 0x25,
+			      0x00, 0x91, 0x0a, 0x00, 0x00, 0x02, 0x4f, 0x01,
+			      0x00, 0x00, 0x37);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETPOWER_EXT, 0x25);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETPCR, 0x02, 0x11, 0x00);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETRGBIF,
+			      0x0c, 0x10, 0x0a, 0x50, 0x03, 0xff, 0x00, 0x00,
+			      0x00, 0x00);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETSCR,
+			      0x73, 0x73, 0x50, 0x50, 0x00, 0x00, 0x08, 0x70,
+			      0x00);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETVDC, 0x46);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETPANEL, 0x0b);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETCYC, 0x80);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETDISP, 0xc8, 0x12, 0x30);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETEQ,
+			      0x07, 0x07, 0x0B, 0x0B, 0x03, 0x0B, 0x00, 0x00,
+			      0x00, 0x00, 0xFF, 0x00, 0xC0, 0x10);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETPOWER,
+			      0x53, 0x00, 0x1e, 0x1e, 0x77, 0xe1, 0xcc, 0xdd,
+			      0x67, 0x77, 0x33, 0x33);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETECO, 0x00, 0x00, 0xff,
+			      0xff, 0x01, 0xff);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETBGP, 0x09, 0x09);
+	msleep(20);
+
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETVCOM, 0x87, 0x95);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETGIP1,
+			      0xc2, 0x10, 0x05, 0x05, 0x10, 0x05, 0xa0, 0x12,
+			      0x31, 0x23, 0x3f, 0x81, 0x0a, 0xa0, 0x37, 0x18,
+			      0x00, 0x80, 0x01, 0x00, 0x00, 0x00, 0x00, 0x80,
+			      0x01, 0x00, 0x00, 0x00, 0x48, 0xf8, 0x86, 0x42,
+			      0x08, 0x88, 0x88, 0x80, 0x88, 0x88, 0x88, 0x58,
+			      0xf8, 0x87, 0x53, 0x18, 0x88, 0x88, 0x81, 0x88,
+			      0x88, 0x88, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00,
+			      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETGIP2,
+			      0x00, 0x1a, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00,
+			      0x00, 0x00, 0x00, 0x00, 0x1f, 0x88, 0x81, 0x35,
+			      0x78, 0x88, 0x88, 0x85, 0x88, 0x88, 0x88, 0x0f,
+			      0x88, 0x80, 0x24, 0x68, 0x88, 0x88, 0x84, 0x88,
+			      0x88, 0x88, 0x23, 0x10, 0x00, 0x00, 0x1c, 0x00,
+			      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+			      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x30, 0x05,
+			      0xa0, 0x00, 0x00, 0x00, 0x00);
+	dsi_generic_write_seq(dsi, XPP055C272_CMD_SETGAMMA,
+			      0x00, 0x06, 0x08, 0x2a, 0x31, 0x3f, 0x38, 0x36,
+			      0x07, 0x0c, 0x0d, 0x11, 0x13, 0x12, 0x13, 0x11,
+			      0x18, 0x00, 0x06, 0x08, 0x2a, 0x31, 0x3f, 0x38,
+			      0x36, 0x07, 0x0c, 0x0d, 0x11, 0x13, 0x12, 0x13,
+			      0x11, 0x18);
+
+	msleep(60);
+
+	DRM_DEV_DEBUG_DRIVER(dev, "Panel init sequence done\n");
+	return 0;
+}
+
+static int xpp055c272_unprepare(struct drm_panel *panel)
+{
+	struct xpp055c272 *ctx = panel_to_xpp055c272(panel);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+	int ret;
+
+	if (!ctx->prepared)
+		return 0;
+
+	ret = mipi_dsi_dcs_set_display_off(dsi);
+	if (ret < 0)
+		DRM_DEV_ERROR(ctx->dev, "failed to set display off: %d\n",
+			      ret);
+
+	mipi_dsi_dcs_enter_sleep_mode(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev, "failed to enter sleep mode: %d\n",
+			      ret);
+		return ret;
+	}
+
+	regulator_disable(ctx->iovcc);
+	regulator_disable(ctx->vci);
+
+	ctx->prepared = false;
+
+	return 0;
+}
+
+static int xpp055c272_prepare(struct drm_panel *panel)
+{
+	struct xpp055c272 *ctx = panel_to_xpp055c272(panel);
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+	int ret;
+
+	if (ctx->prepared)
+		return 0;
+
+	DRM_DEV_DEBUG_DRIVER(ctx->dev, "Resetting the panel\n");
+	ret = regulator_enable(ctx->vci);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev,
+			      "Failed to enable vci supply: %d\n", ret);
+		return ret;
+	}
+	ret = regulator_enable(ctx->iovcc);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev,
+			      "Failed to enable iovcc supply: %d\n", ret);
+		goto disable_vci;
+	}
+
+	gpiod_set_value_cansleep(ctx->reset_gpio, 1);
+	/* T6: 10us */
+	usleep_range(10, 20);
+	gpiod_set_value_cansleep(ctx->reset_gpio, 0);
+
+	/* T8: 20ms */
+	msleep(20);
+
+	ret = xpp055c272_init_sequence(ctx);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev, "Panel init sequence failed: %d\n",
+			      ret);
+		goto disable_iovcc;
+	}
+
+	ret = mipi_dsi_dcs_exit_sleep_mode(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev, "Failed to exit sleep mode: %d\n", ret);
+		goto disable_iovcc;
+	}
+
+	/* T9: 120ms */
+	msleep(120);
+
+	ret = mipi_dsi_dcs_set_display_on(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(ctx->dev, "Failed to set display on: %d\n", ret);
+		goto disable_iovcc;
+	}
+
+	msleep(50);
+
+	ctx->prepared = true;
+
+	return 0;
+
+disable_iovcc:
+	regulator_disable(ctx->iovcc);
+disable_vci:
+	regulator_disable(ctx->vci);
+	return ret;
+}
+
+static const struct drm_display_mode default_mode = {
+	.hdisplay	= 720,
+	.hsync_start	= 720 + 40,
+	.hsync_end	= 720 + 40 + 10,
+	.htotal		= 720 + 40 + 10 + 40,
+	.vdisplay	= 1280,
+	.vsync_start	= 1280 + 22,
+	.vsync_end	= 1280 + 22 + 4,
+	.vtotal		= 1280 + 22 + 4 + 11,
+	.vrefresh	= 60,
+	.clock		= 64000,
+	.width_mm	= 68,
+	.height_mm	= 121,
+};
+
+static int xpp055c272_get_modes(struct drm_panel *panel,
+				struct drm_connector *connector)
+{
+	struct xpp055c272 *ctx = panel_to_xpp055c272(panel);
+	struct drm_display_mode *mode;
+
+	mode = drm_mode_duplicate(connector->dev, &default_mode);
+	if (!mode) {
+		DRM_DEV_ERROR(ctx->dev, "Failed to add mode %ux%u@%u\n",
+			      default_mode.hdisplay, default_mode.vdisplay,
+			      default_mode.vrefresh);
+		return -ENOMEM;
+	}
+
+	drm_mode_set_name(mode);
+
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+	connector->display_info.width_mm = mode->width_mm;
+	connector->display_info.height_mm = mode->height_mm;
+	drm_mode_probed_add(connector, mode);
+
+	return 1;
+}
+
+static const struct drm_panel_funcs xpp055c272_funcs = {
+	.unprepare	= xpp055c272_unprepare,
+	.prepare	= xpp055c272_prepare,
+	.get_modes	= xpp055c272_get_modes,
+};
+
+static int xpp055c272_probe(struct mipi_dsi_device *dsi)
+{
+	struct device *dev = &dsi->dev;
+	struct xpp055c272 *ctx;
+	int ret;
+
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(ctx->reset_gpio)) {
+		DRM_DEV_ERROR(dev, "cannot get reset gpio\n");
+		return PTR_ERR(ctx->reset_gpio);
+	}
+
+	ctx->vci = devm_regulator_get(dev, "vci");
+	if (IS_ERR(ctx->vci)) {
+		ret = PTR_ERR(ctx->vci);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev,
+				      "Failed to request vci regulator: %d\n",
+				      ret);
+		return ret;
+	}
+
+	ctx->iovcc = devm_regulator_get(dev, "iovcc");
+	if (IS_ERR(ctx->iovcc)) {
+		ret = PTR_ERR(ctx->iovcc);
+		if (ret != -EPROBE_DEFER)
+			DRM_DEV_ERROR(dev,
+				      "Failed to request iovcc regulator: %d\n",
+				      ret);
+		return ret;
+	}
+
+	mipi_dsi_set_drvdata(dsi, ctx);
+
+	ctx->dev = dev;
+
+	dsi->lanes = 4;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+
+	drm_panel_init(&ctx->panel, &dsi->dev, &xpp055c272_funcs,
+		       DRM_MODE_CONNECTOR_DSI);
+
+	ret = drm_panel_of_backlight(&ctx->panel);
+	if (ret)
+		return ret;
+
+	drm_panel_add(&ctx->panel);
+
+	ret = mipi_dsi_attach(dsi);
+	if (ret < 0) {
+		DRM_DEV_ERROR(dev, "mipi_dsi_attach failed: %d\n", ret);
+		drm_panel_remove(&ctx->panel);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void xpp055c272_shutdown(struct mipi_dsi_device *dsi)
+{
+	struct xpp055c272 *ctx = mipi_dsi_get_drvdata(dsi);
+	int ret;
+
+	ret = drm_panel_unprepare(&ctx->panel);
+	if (ret < 0)
+		DRM_DEV_ERROR(&dsi->dev, "Failed to unprepare panel: %d\n",
+			      ret);
+
+	ret = drm_panel_disable(&ctx->panel);
+	if (ret < 0)
+		DRM_DEV_ERROR(&dsi->dev, "Failed to disable panel: %d\n",
+			      ret);
+}
+
+static int xpp055c272_remove(struct mipi_dsi_device *dsi)
+{
+	struct xpp055c272 *ctx = mipi_dsi_get_drvdata(dsi);
+	int ret;
+
+	xpp055c272_shutdown(dsi);
+
+	ret = mipi_dsi_detach(dsi);
+	if (ret < 0)
+		DRM_DEV_ERROR(&dsi->dev, "Failed to detach from DSI host: %d\n",
+			      ret);
+
+	drm_panel_remove(&ctx->panel);
+
+	return 0;
+}
+
+static const struct of_device_id xpp055c272_of_match[] = {
+	{ .compatible = "xinpeng,xpp055c272" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, xpp055c272_of_match);
+
+static struct mipi_dsi_driver xpp055c272_driver = {
+	.driver = {
+		.name = "panel-xinpeng-xpp055c272",
+		.of_match_table = xpp055c272_of_match,
+	},
+	.probe	= xpp055c272_probe,
+	.remove = xpp055c272_remove,
+	.shutdown = xpp055c272_shutdown,
+};
+module_mipi_dsi_driver(xpp055c272_driver);
+
+MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@theobroma-systems.com>");
+MODULE_DESCRIPTION("DRM driver for Xinpeng xpp055c272 MIPI DSI panel");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 536ba93b0f46..413987038fbf 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright 2019 Collabora ltd. */
 #include <linux/devfreq.h>
+#include <linux/devfreq_cooling.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
 #include <linux/clk.h>
@@ -74,8 +75,11 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 	int ret;
 	struct dev_pm_opp *opp;
 	unsigned long cur_freq;
+	struct device *dev = &pfdev->pdev->dev;
+	struct devfreq *devfreq;
+	struct thermal_cooling_device *cooling;
 
-	ret = dev_pm_opp_of_add_table(&pfdev->pdev->dev);
+	ret = dev_pm_opp_of_add_table(dev);
 	if (ret == -ENODEV) /* Optional, continue without devfreq */
 		return 0;
 	else if (ret)
@@ -85,29 +89,35 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 
 	cur_freq = clk_get_rate(pfdev->clock);
 
-	opp = devfreq_recommended_opp(&pfdev->pdev->dev, &cur_freq, 0);
+	opp = devfreq_recommended_opp(dev, &cur_freq, 0);
 	if (IS_ERR(opp))
 		return PTR_ERR(opp);
 
 	panfrost_devfreq_profile.initial_freq = cur_freq;
 	dev_pm_opp_put(opp);
 
-	pfdev->devfreq.devfreq = devm_devfreq_add_device(&pfdev->pdev->dev,
-			&panfrost_devfreq_profile, DEVFREQ_GOV_SIMPLE_ONDEMAND,
-			NULL);
-	if (IS_ERR(pfdev->devfreq.devfreq)) {
-		DRM_DEV_ERROR(&pfdev->pdev->dev, "Couldn't initialize GPU devfreq\n");
-		ret = PTR_ERR(pfdev->devfreq.devfreq);
-		pfdev->devfreq.devfreq = NULL;
-		dev_pm_opp_of_remove_table(&pfdev->pdev->dev);
-		return ret;
+	devfreq = devm_devfreq_add_device(dev, &panfrost_devfreq_profile,
+					  DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
+	if (IS_ERR(devfreq)) {
+		DRM_DEV_ERROR(dev, "Couldn't initialize GPU devfreq\n");
+		dev_pm_opp_of_remove_table(dev);
+		return PTR_ERR(devfreq);
 	}
+	pfdev->devfreq.devfreq = devfreq;
+
+	cooling = of_devfreq_cooling_register(dev->of_node, devfreq);
+	if (IS_ERR(cooling))
+		DRM_DEV_INFO(dev, "Failed to register cooling device\n");
+	else
+		pfdev->devfreq.cooling = cooling;
 
 	return 0;
 }
 
 void panfrost_devfreq_fini(struct panfrost_device *pfdev)
 {
+	if (pfdev->devfreq.cooling)
+		devfreq_cooling_unregister(pfdev->devfreq.cooling);
 	dev_pm_opp_of_remove_table(&pfdev->pdev->dev);
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 88b431a267af..6da59f476aba 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -526,15 +526,11 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file)
 	kfree(panfrost_priv);
 }
 
-/* DRM_AUTH is required on SUBMIT for now, while all clients share a single
- * address space.  Note that render nodes would be able to submit jobs that
- * could access BOs from clients authenticated with the master node.
- */
 static const struct drm_ioctl_desc panfrost_drm_driver_ioctls[] = {
 #define PANFROST_IOCTL(n, func, flags) \
 	DRM_IOCTL_DEF_DRV(PANFROST_##n, panfrost_ioctl_##func, flags)
 
-	PANFROST_IOCTL(SUBMIT,		submit,		DRM_RENDER_ALLOW | DRM_AUTH),
+	PANFROST_IOCTL(SUBMIT,		submit,		DRM_RENDER_ALLOW),
 	PANFROST_IOCTL(WAIT_BO,		wait_bo,	DRM_RENDER_ALLOW),
 	PANFROST_IOCTL(CREATE_BO,	create_bo,	DRM_RENDER_ALLOW),
 	PANFROST_IOCTL(MMAP_BO,		mmap_bo,	DRM_RENDER_ALLOW),
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index e364ee00f3d0..7c36ec675b73 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -553,12 +553,14 @@ int panfrost_job_open(struct panfrost_file_priv *panfrost_priv)
 {
 	struct panfrost_device *pfdev = panfrost_priv->pfdev;
 	struct panfrost_job_slot *js = pfdev->js;
-	struct drm_sched_rq *rq;
+	struct drm_gpu_scheduler *sched;
 	int ret, i;
 
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-		rq = &js->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		ret = drm_sched_entity_init(&panfrost_priv->sched_entity[i], &rq, 1, NULL);
+		sched = &js->queue[i].sched;
+		ret = drm_sched_entity_init(&panfrost_priv->sched_entity[i],
+					    DRM_SCHED_PRIORITY_NORMAL, &sched,
+					    1, NULL);
 		if (WARN_ON(ret))
 			return ret;
 	}
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 63dfcda04147..aa8aa8d9e405 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -166,7 +166,7 @@ static int pl111_modeset_init(struct drm_device *dev)
 	priv->bridge = bridge;
 	if (panel) {
 		priv->panel = panel;
-		priv->connector = panel->connector;
+		priv->connector = drm_panel_bridge_connector(bridge);
 	}
 
 	ret = pl111_display_init(dev);
diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c
index 611cbe7aee69..bfc1631093e9 100644
--- a/drivers/gpu/drm/qxl/qxl_kms.c
+++ b/drivers/gpu/drm/qxl/qxl_kms.c
@@ -184,7 +184,7 @@ int qxl_device_init(struct qxl_device *qdev,
 
 	if (!qxl_check_device(qdev)) {
 		r = -ENODEV;
-		goto surface_mapping_free;
+		goto rom_unmap;
 	}
 
 	r = qxl_bo_init(qdev);
diff --git a/drivers/gpu/drm/r128/Makefile b/drivers/gpu/drm/r128/Makefile
index ae8a1860c6b8..c07a069533ef 100644
--- a/drivers/gpu/drm/r128/Makefile
+++ b/drivers/gpu/drm/r128/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the drm device driver.  This driver provides support for the
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
-r128-y   := r128_drv.o r128_cce.o r128_state.o r128_irq.o
+r128-y   := r128_drv.o r128_cce.o r128_state.o r128_irq.o ati_pcigart.o
 
 r128-$(CONFIG_COMPAT)   += r128_ioc32.o
 
diff --git a/drivers/gpu/drm/ati_pcigart.c b/drivers/gpu/drm/r128/ati_pcigart.c
index 580aa2676358..9b4072f97215 100644
--- a/drivers/gpu/drm/ati_pcigart.c
+++ b/drivers/gpu/drm/r128/ati_pcigart.c
@@ -33,11 +33,12 @@
 
 #include <linux/export.h>
 
-#include <drm/ati_pcigart.h>
 #include <drm/drm_device.h>
 #include <drm/drm_pci.h>
 #include <drm/drm_print.h>
 
+#include "ati_pcigart.h"
+
 # define ATI_PCIGART_PAGE_SIZE		4096	/**< PCI GART page size */
 
 static int drm_ati_alloc_pcigart_table(struct drm_device *dev,
@@ -95,7 +96,6 @@ int drm_ati_pcigart_cleanup(struct drm_device *dev, struct drm_ati_pcigart_info
 
 	return 1;
 }
-EXPORT_SYMBOL(drm_ati_pcigart_cleanup);
 
 int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *gart_info)
 {
@@ -207,4 +207,3 @@ int drm_ati_pcigart_init(struct drm_device *dev, struct drm_ati_pcigart_info *ga
 	gart_info->bus_addr = bus_address;
 	return ret;
 }
-EXPORT_SYMBOL(drm_ati_pcigart_init);
diff --git a/include/drm/ati_pcigart.h b/drivers/gpu/drm/r128/ati_pcigart.h
index a728a1364e66..a728a1364e66 100644
--- a/include/drm/ati_pcigart.h
+++ b/drivers/gpu/drm/r128/ati_pcigart.h
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index fd74f744604f..b7a5f162ebae 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -30,10 +30,10 @@
  */
 
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/drm_vblank.h>
 #include <drm/r128_drm.h>
diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h
index ba8c30ed91d1..8b256123cf2b 100644
--- a/drivers/gpu/drm/r128/r128_drv.h
+++ b/drivers/gpu/drm/r128/r128_drv.h
@@ -39,11 +39,12 @@
 #include <linux/io.h>
 #include <linux/irqreturn.h>
 
-#include <drm/ati_pcigart.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_legacy.h>
 #include <drm/r128_drm.h>
 
+#include "ati_pcigart.h"
+
 /* General customization:
  */
 #define DRIVER_AUTHOR		"Gareth Hughes, VA Linux Systems Inc."
diff --git a/drivers/gpu/drm/radeon/atom.h b/drivers/gpu/drm/radeon/atom.h
index 364b895e7ebb..1bf06c91cd95 100644
--- a/drivers/gpu/drm/radeon/atom.h
+++ b/drivers/gpu/drm/radeon/atom.h
@@ -25,6 +25,7 @@
 #ifndef ATOM_H
 #define ATOM_H
 
+#include <linux/mutex.h>
 #include <linux/types.h>
 
 #define ATOM_BIOS_MAGIC		0xAA55
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index da2c9e295408..be583695427a 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -244,9 +244,8 @@ static void atombios_blank_crtc(struct drm_crtc *crtc, int state)
 
 	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 
-	if (ASIC_IS_DCE8(rdev)) {
+	if (ASIC_IS_DCE8(rdev))
 		WREG32(vga_control_regs[radeon_crtc->crtc_id], vga_control);
-	}
 }
 
 static void atombios_powergate_crtc(struct drm_crtc *crtc, int state)
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 6f38375c77c8..15b00a347560 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -412,7 +412,6 @@ int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
-	struct radeon_connector_atom_dig *dig_connector;
 	int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
 	u16 dp_bridge = radeon_connector_encoder_get_dp_bridge_encoder_id(connector);
 	u8 tmp;
@@ -423,8 +422,6 @@ int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 	if (!radeon_connector->con_priv)
 		return panel_mode;
 
-	dig_connector = radeon_connector->con_priv;
-
 	if (dp_bridge != ENCODER_OBJECT_ID_NONE) {
 		/* DP bridge chips */
 		if (drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux,
@@ -816,9 +813,8 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
 	dp_info.use_dpencoder = true;
 	index = GetIndexIntoMasterTable(COMMAND, DPEncoderService);
 	if (atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) {
-		if (crev > 1) {
+		if (crev > 1)
 			dp_info.use_dpencoder = false;
-		}
 	}
 
 	dp_info.enc_id = 0;
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index cc8f32a1b03c..cc5ee1b3af84 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -26,10 +26,10 @@
 
 #include <linux/backlight.h>
 #include <linux/dmi.h>
+#include <linux/pci.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "atom.h"
@@ -1885,11 +1885,10 @@ atombios_set_encoder_crtc_source(struct drm_encoder *encoder)
 			if (ASIC_IS_AVIVO(rdev))
 				args.v1.ucCRTC = radeon_crtc->crtc_id;
 			else {
-				if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_DAC1) {
+				if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_DAC1)
 					args.v1.ucCRTC = radeon_crtc->crtc_id;
-				} else {
+				else
 					args.v1.ucCRTC = radeon_crtc->crtc_id << 2;
-				}
 			}
 			switch (radeon_encoder->encoder_id) {
 			case ENCODER_OBJECT_ID_INTERNAL_TMDS1:
@@ -2234,9 +2233,9 @@ assigned:
 		DRM_ERROR("Got encoder index incorrect - returning 0\n");
 		return 0;
 	}
-	if (rdev->mode_info.active_encoders & (1 << enc_idx)) {
+	if (rdev->mode_info.active_encoders & (1 << enc_idx))
 		DRM_ERROR("chosen encoder in use %d\n", enc_idx);
-	}
+
 	rdev->mode_info.active_encoders |= (1 << enc_idx);
 	return enc_idx;
 }
diff --git a/drivers/gpu/drm/radeon/atombios_i2c.c b/drivers/gpu/drm/radeon/atombios_i2c.c
index a570ce40af19..ab4d21072191 100644
--- a/drivers/gpu/drm/radeon/atombios_i2c.c
+++ b/drivers/gpu/drm/radeon/atombios_i2c.c
@@ -68,11 +68,6 @@ static int radeon_process_i2c_ch(struct radeon_i2c_chan *chan,
 			memcpy(&out, &buf[1], num);
 		args.lpI2CDataOut = cpu_to_le16(out);
 	} else {
-		if (num > ATOM_MAX_HW_I2C_READ) {
-			DRM_ERROR("hw i2c: tried to read too many bytes (%d vs 255)\n", num);
-			r = -EINVAL;
-			goto done;
-		}
 		args.ucRegIndex = 0;
 		args.lpI2CDataOut = 0;
 	}
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index ce37de020b91..d1d8aaf8323c 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -22,10 +22,9 @@
  * Authors: Alex Deucher
  */
 
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "atom.h"
 #include "btc_dpm.h"
 #include "btcd.h"
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index c6fd123f60b5..a9257bed3484 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -22,10 +22,9 @@
  */
 
 #include <linux/firmware.h>
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "atom.h"
 #include "ci_dpm.h"
 #include "cikd.h"
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 40a7e702c2a9..5c42877fd6fb 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -23,10 +23,10 @@
  */
 
 #include <linux/firmware.h>
-#include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
 
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 
 #include "atom.h"
@@ -8137,7 +8137,7 @@ static void cik_uvd_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable uvd here.
 		 */
-		rdev->has_uvd = 0;
+		rdev->has_uvd = false;
 		return;
 	}
 	rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
@@ -8209,7 +8209,7 @@ static void cik_vce_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable vce here.
 		 */
-		rdev->has_vce = 0;
+		rdev->has_vce = false;
 		return;
 	}
 	rdev->ring[TN_RING_TYPE_VCE1_INDEX].ring_obj = NULL;
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index 35b9dc6ce46a..68403e77756d 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -333,7 +333,7 @@ void cik_sdma_enable(struct radeon_device *rdev, bool enable)
 	u32 me_cntl, reg_offset;
 	int i;
 
-	if (enable == false) {
+	if (!enable) {
 		cik_sdma_gfx_stop(rdev);
 		cik_sdma_rlc_stop(rdev);
 	}
diff --git a/drivers/gpu/drm/radeon/cypress_dpm.c b/drivers/gpu/drm/radeon/cypress_dpm.c
index 32ed60f1048b..35b177d77791 100644
--- a/drivers/gpu/drm/radeon/cypress_dpm.c
+++ b/drivers/gpu/drm/radeon/cypress_dpm.c
@@ -22,7 +22,7 @@
  * Authors: Alex Deucher
  */
 
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "atom.h"
 #include "cypress_dpm.h"
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 1d978a3d9c82..14d90dc376e7 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -23,9 +23,9 @@
  */
 
 #include <linux/firmware.h>
+#include <linux/pci.h>
 #include <linux/slab.h>
 
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
 
@@ -4945,7 +4945,7 @@ static void evergreen_uvd_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable uvd here.
 		 */
-		rdev->has_uvd = 0;
+		rdev->has_uvd = false;
 		return;
 	}
 	rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 0d8d30b78f95..5e6086eb1807 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -21,10 +21,9 @@
  *
  */
 
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "cikd.h"
 #include "kv_dpm.h"
 #include "r600_dpm.h"
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 410f626a39d4..02feb0801fd3 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -23,10 +23,10 @@
  */
 
 #include <linux/firmware.h>
-#include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
 
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "atom.h"
@@ -2017,7 +2017,7 @@ static void cayman_uvd_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable uvd here.
 		 */
-		rdev->has_uvd = 0;
+		rdev->has_uvd = false;
 		return;
 	}
 	rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
@@ -2085,7 +2085,7 @@ static void cayman_vce_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable vce here.
 		 */
-		rdev->has_vce = 0;
+		rdev->has_vce = false;
 		return;
 	}
 	rdev->ring[TN_RING_TYPE_VCE1_INDEX].ring_obj = NULL;
diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index d9e62ca65ab8..b57c37ddd164 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -22,10 +22,9 @@
  */
 
 #include <linux/math64.h>
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "atom.h"
 #include "ni_dpm.h"
 #include "nid.h"
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 110fb38004b1..24c8db673931 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -26,16 +26,16 @@
  *          Jerome Glisse
  */
 
-#include <linux/seq_file.h>
-#include <linux/slab.h>
 #include <linux/firmware.h>
 #include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
 #include <drm/drm_fourcc.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
 
@@ -1823,9 +1823,9 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 	case RADEON_PP_TXFORMAT_2:
 		i = (reg - RADEON_PP_TXFORMAT_0) / 24;
 		if (idx_value & RADEON_TXFORMAT_NON_POWER2) {
-			track->textures[i].use_pitch = 1;
+			track->textures[i].use_pitch = true;
 		} else {
-			track->textures[i].use_pitch = 0;
+			track->textures[i].use_pitch = false;
 			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
 			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
@@ -2387,12 +2387,12 @@ void r100_cs_track_clear(struct radeon_device *rdev, struct r100_cs_track *track
 		else
 			track->num_texture = 6;
 		track->maxy = 2048;
-		track->separate_cube = 1;
+		track->separate_cube = true;
 	} else {
 		track->num_cb = 4;
 		track->num_texture = 16;
 		track->maxy = 4096;
-		track->separate_cube = 0;
+		track->separate_cube = false;
 		track->aaresolve = false;
 		track->aa.robj = NULL;
 	}
@@ -2815,7 +2815,7 @@ void r100_vga_set_state(struct radeon_device *rdev, bool state)
 	uint32_t temp;
 
 	temp = RREG32(RADEON_CONFIG_CNTL);
-	if (state == false) {
+	if (!state) {
 		temp &= ~RADEON_CFG_VGA_RAM_EN;
 		temp |= RADEON_CFG_VGA_IO_DIS;
 	} else {
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 44856e3a7108..3b7ead5be5bf 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -26,6 +26,7 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 
@@ -34,7 +35,6 @@
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "r100_track.h"
diff --git a/drivers/gpu/drm/radeon/r420.c b/drivers/gpu/drm/radeon/r420.c
index 83282ee2bde0..1d4c04e0a449 100644
--- a/drivers/gpu/drm/radeon/r420.c
+++ b/drivers/gpu/drm/radeon/r420.c
@@ -26,13 +26,13 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 
 #include "atom.h"
 #include "r100d.h"
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 033bc466a862..d9a33ca768f3 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -26,14 +26,14 @@
  *          Jerome Glisse
  */
 
-#include <linux/slab.h>
-#include <linux/seq_file.h>
 #include <linux/firmware.h>
 #include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
 
@@ -3053,7 +3053,7 @@ static void r600_uvd_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable uvd here.
 		 */
-		rdev->has_uvd = 0;
+		rdev->has_uvd = false;
 		return;
 	}
 	rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
@@ -3191,7 +3191,7 @@ void r600_vga_set_state(struct radeon_device *rdev, bool state)
 	uint32_t temp;
 
 	temp = RREG32(CONFIG_CNTL);
-	if (state == false) {
+	if (!state) {
 		temp &= ~(1<<0);
 		temp |= (1<<1);
 	} else {
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index d6c28a5d77ab..49e8266461f8 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -350,7 +350,7 @@ static void r600_cs_track_init(struct r600_cs_track *track)
 static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 {
 	struct r600_cs_track *track = p->track;
-	u32 slice_tile_max, size, tmp;
+	u32 slice_tile_max, tmp;
 	u32 height, height_align, pitch, pitch_align, depth_align;
 	u64 base_offset, base_align;
 	struct array_mode_checker array_check;
@@ -360,7 +360,6 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 	/* When resolve is used, the second colorbuffer has always 1 sample. */
 	unsigned nsamples = track->is_resolve && i == 1 ? 1 : track->nsamples;
 
-	size = radeon_bo_size(track->cb_color_bo[i]) - track->cb_color_bo_offset[i];
 	format = G_0280A0_FORMAT(track->cb_color_info[i]);
 	if (!r600_fmt_is_valid_color(format)) {
 		dev_warn(p->dev, "%s:%d cb invalid format %d for %d (0x%08X)\n",
@@ -517,7 +516,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i)
 static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 {
 	struct r600_cs_track *track = p->track;
-	u32 nviews, bpe, ntiles, size, slice_tile_max, tmp;
+	u32 nviews, bpe, ntiles, slice_tile_max, tmp;
 	u32 height_align, pitch_align, depth_align;
 	u32 pitch = 8192;
 	u32 height = 8192;
@@ -564,7 +563,6 @@ static int r600_cs_track_validate_db(struct radeon_cs_parser *p)
 		}
 		ib[track->db_depth_size_idx] = S_028000_SLICE_TILE_MAX(tmp - 1) | (track->db_depth_size & 0x3FF);
 	} else {
-		size = radeon_bo_size(track->db_bo);
 		/* pitch in pixels */
 		pitch = (G_028000_PITCH_TILE_MAX(track->db_depth_size) + 1) * 8;
 		slice_tile_max = G_028000_SLICE_TILE_MAX(track->db_depth_size) + 1;
@@ -2342,7 +2340,6 @@ int r600_cs_parse(struct radeon_cs_parser *p)
 int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
 			   struct radeon_bo_list **cs_reloc)
 {
-	struct radeon_cs_chunk *relocs_chunk;
 	unsigned idx;
 
 	*cs_reloc = NULL;
@@ -2350,7 +2347,6 @@ int r600_dma_cs_next_reloc(struct radeon_cs_parser *p,
 		DRM_ERROR("No relocation chunk !\n");
 		return -EINVAL;
 	}
-	relocs_chunk = p->chunk_relocs;
 	idx = p->dma_reloc_idx;
 	if (idx >= p->nrelocs) {
 		DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
diff --git a/drivers/gpu/drm/radeon/radeon_agp.c b/drivers/gpu/drm/radeon/radeon_agp.c
index 4de16f3badb4..0aca7bdf54c7 100644
--- a/drivers/gpu/drm/radeon/radeon_agp.c
+++ b/drivers/gpu/drm/radeon/radeon_agp.c
@@ -25,9 +25,10 @@
  *    Jerome Glisse <glisse@freedesktop.org>
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_agpsupport.h>
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index dc3c2227e06a..495700d16fc9 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -27,10 +27,10 @@
  */
 
 #include <linux/console.h>
+#include <linux/pci.h>
 #include <linux/vgaarb.h>
 
 #include <drm/drm_crtc_helper.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "atom.h"
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 226a7bf0eb7a..848ef68d9086 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -24,8 +24,9 @@
  *          Alex Deucher
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
@@ -569,7 +570,7 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev)
 		path_size += le16_to_cpu(path->usSize);
 
 		if (device_support & le16_to_cpu(path->usDeviceTag)) {
-			uint8_t con_obj_id, con_obj_num, con_obj_type;
+			uint8_t con_obj_id, con_obj_num;
 
 			con_obj_id =
 			    (le16_to_cpu(path->usConnObjectId) & OBJECT_ID_MASK)
@@ -577,9 +578,6 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev)
 			con_obj_num =
 			    (le16_to_cpu(path->usConnObjectId) & ENUM_ID_MASK)
 			    >> ENUM_ID_SHIFT;
-			con_obj_type =
-			    (le16_to_cpu(path->usConnObjectId) &
-			     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
 			/* TODO CV support */
 			if (le16_to_cpu(path->usDeviceTag) ==
@@ -647,15 +645,7 @@ bool radeon_get_atom_connector_info_from_object_table(struct drm_device *dev)
 			router.ddc_valid = false;
 			router.cd_valid = false;
 			for (j = 0; j < ((le16_to_cpu(path->usSize) - 8) / 2); j++) {
-				uint8_t grph_obj_id, grph_obj_num, grph_obj_type;
-
-				grph_obj_id =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     OBJECT_ID_MASK) >> OBJECT_ID_SHIFT;
-				grph_obj_num =
-				    (le16_to_cpu(path->usGraphicObjIds[j]) &
-				     ENUM_ID_MASK) >> ENUM_ID_SHIFT;
-				grph_obj_type =
+				uint8_t grph_obj_type =
 				    (le16_to_cpu(path->usGraphicObjIds[j]) &
 				     OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
 
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index 72db2b41e96d..8c63ccb8b623 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -288,7 +288,7 @@ static void radeon_audio_interface_init(struct radeon_device *rdev)
 	} else {
 		rdev->audio.funcs = &r600_funcs;
 		rdev->audio.hdmi_funcs = &r600_hdmi_funcs;
-		rdev->audio.dp_funcs = 0;
+		rdev->audio.dp_funcs = NULL;
 	}
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index 4d1490fbb075..c42f73fad3e3 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -26,11 +26,11 @@
  *          Jerome Glisse
  */
 
-#include <linux/slab.h>
 #include <linux/acpi.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
 
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 
 #include "atom.h"
 #include "radeon.h"
@@ -664,17 +664,17 @@ bool radeon_get_bios(struct radeon_device *rdev)
 	uint16_t tmp;
 
 	r = radeon_atrm_get_bios(rdev);
-	if (r == false)
+	if (!r)
 		r = radeon_acpi_vfct_bios(rdev);
-	if (r == false)
+	if (!r)
 		r = igp_read_bios_from_vram(rdev);
-	if (r == false)
+	if (!r)
 		r = radeon_read_bios(rdev);
-	if (r == false)
+	if (!r)
 		r = radeon_read_disabled_bios(rdev);
-	if (r == false)
+	if (!r)
 		r = radeon_read_platform_bios(rdev);
-	if (r == false || rdev->bios == NULL) {
+	if (!r || rdev->bios == NULL) {
 		DRM_ERROR("Unable to locate a BIOS ROM\n");
 		rdev->bios = NULL;
 		return false;
diff --git a/drivers/gpu/drm/radeon/radeon_clocks.c b/drivers/gpu/drm/radeon/radeon_clocks.c
index 9057b32f4498..c594ca68e3a7 100644
--- a/drivers/gpu/drm/radeon/radeon_clocks.c
+++ b/drivers/gpu/drm/radeon/radeon_clocks.c
@@ -26,8 +26,9 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "atom.h"
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index c18ae15189f3..c3e49c973812 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -25,8 +25,9 @@
  *          Alex Deucher
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
@@ -2638,7 +2639,7 @@ void radeon_combios_get_power_modes(struct radeon_device *rdev)
 {
 	struct drm_device *dev = rdev->ddev;
 	u16 offset, misc, misc2 = 0;
-	u8 rev, blocks, tmp;
+	u8 rev, tmp;
 	int state_index = 0;
 	struct radeon_i2c_bus_rec i2c_bus;
 
@@ -2731,7 +2732,6 @@ void radeon_combios_get_power_modes(struct radeon_device *rdev)
 		offset = combios_get_table_offset(dev, COMBIOS_POWERPLAY_INFO_TABLE);
 		if (offset) {
 			rev = RBIOS8(offset);
-			blocks = RBIOS8(offset + 0x2);
 			/* power mode 0 tends to be the only valid one */
 			rdev->pm.power_state[state_index].num_clock_modes = 1;
 			rdev->pm.power_state[state_index].clock_info[0].mclk = RBIOS32(offset + 0x5 + 0x2);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index c07427d3c199..fe12d9d91d7a 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -440,7 +440,7 @@ radeon_connector_analog_encoder_conflict_solve(struct drm_connector *connector,
 				if (radeon_conflict->use_digital)
 					continue;
 
-				if (priority == true) {
+				if (priority) {
 					DRM_DEBUG_KMS("1: conflicting encoders switching off %s\n",
 						      conflict->name);
 					DRM_DEBUG_KMS("in favor of %s\n",
@@ -700,9 +700,9 @@ static int radeon_connector_set_property(struct drm_connector *connector, struct
 			else
 				ret = radeon_legacy_get_tmds_info_from_combios(radeon_encoder, tmds);
 		}
-		if (val == 1 || ret == false) {
+		if (val == 1 || !ret)
 			radeon_legacy_get_tmds_info_from_table(radeon_encoder, tmds);
-		}
+
 		radeon_property_change_mode(&radeon_encoder->base);
 	}
 
@@ -1861,6 +1861,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 	struct radeon_connector_atom_dig *radeon_dig_connector;
 	struct drm_encoder *encoder;
 	struct radeon_encoder *radeon_encoder;
+	struct i2c_adapter *ddc = NULL;
 	uint32_t subpixel_order = SubPixelNone;
 	bool shared_ddc = false;
 	bool is_dp_bridge = false;
@@ -1938,17 +1939,21 @@ radeon_add_atom_connector(struct drm_device *dev,
 		radeon_connector->con_priv = radeon_dig_connector;
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
-			if (radeon_connector->ddc_bus)
+			if (radeon_connector->ddc_bus) {
 				has_aux = true;
-			else
+				ddc = &radeon_connector->ddc_bus->adapter;
+			} else {
 				DRM_ERROR("DP: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+			}
 		}
 		switch (connector_type) {
 		case DRM_MODE_CONNECTOR_VGA:
 		case DRM_MODE_CONNECTOR_DVIA:
 		default:
-			drm_connector_init(dev, &radeon_connector->base,
-					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_dp_connector_funcs,
+						    connector_type,
+						    ddc);
 			drm_connector_helper_add(&radeon_connector->base,
 						 &radeon_dp_connector_helper_funcs);
 			connector->interlace_allowed = true;
@@ -1970,8 +1975,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_HDMIA:
 		case DRM_MODE_CONNECTOR_HDMIB:
 		case DRM_MODE_CONNECTOR_DisplayPort:
-			drm_connector_init(dev, &radeon_connector->base,
-					   &radeon_dp_connector_funcs, connector_type);
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_dp_connector_funcs,
+						    connector_type,
+						    ddc);
 			drm_connector_helper_add(&radeon_connector->base,
 						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
@@ -2018,8 +2025,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 			break;
 		case DRM_MODE_CONNECTOR_LVDS:
 		case DRM_MODE_CONNECTOR_eDP:
-			drm_connector_init(dev, &radeon_connector->base,
-					   &radeon_lvds_bridge_connector_funcs, connector_type);
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_lvds_bridge_connector_funcs,
+						    connector_type,
+						    ddc);
 			drm_connector_helper_add(&radeon_connector->base,
 						 &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
@@ -2033,13 +2042,18 @@ radeon_add_atom_connector(struct drm_device *dev,
 	} else {
 		switch (connector_type) {
 		case DRM_MODE_CONNECTOR_VGA:
-			drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 				if (!radeon_connector->ddc_bus)
 					DRM_ERROR("VGA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				else
+					ddc = &radeon_connector->ddc_bus->adapter;
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_vga_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 			radeon_connector->dac_load_detect = true;
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.load_detect_property,
@@ -2058,13 +2072,18 @@ radeon_add_atom_connector(struct drm_device *dev,
 			connector->doublescan_allowed = true;
 			break;
 		case DRM_MODE_CONNECTOR_DVIA:
-			drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 				if (!radeon_connector->ddc_bus)
 					DRM_ERROR("DVIA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				else
+					ddc = &radeon_connector->ddc_bus->adapter;
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_vga_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 			radeon_connector->dac_load_detect = true;
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.load_detect_property,
@@ -2089,13 +2108,18 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 				if (!radeon_connector->ddc_bus)
 					DRM_ERROR("DVI: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				else
+					ddc = &radeon_connector->ddc_bus->adapter;
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_dvi_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs);
 			subpixel_order = SubPixelHorizontalRGB;
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.coherent_mode_property,
@@ -2146,13 +2170,18 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 				if (!radeon_connector->ddc_bus)
 					DRM_ERROR("HDMI: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				else
+					ddc = &radeon_connector->ddc_bus->adapter;
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_dvi_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.coherent_mode_property,
 						      1);
@@ -2196,15 +2225,20 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_dp_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
-				if (radeon_connector->ddc_bus)
+				if (radeon_connector->ddc_bus) {
 					has_aux = true;
-				else
+					ddc = &radeon_connector->ddc_bus->adapter;
+				} else {
 					DRM_ERROR("DP: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				}
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_dp_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			subpixel_order = SubPixelHorizontalRGB;
 			drm_object_attach_property(&radeon_connector->base.base,
 						      rdev->mode_info.coherent_mode_property,
@@ -2246,15 +2280,20 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_edp_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
-				if (radeon_connector->ddc_bus)
+				if (radeon_connector->ddc_bus) {
 					has_aux = true;
-				else
+					ddc = &radeon_connector->ddc_bus->adapter;
+				} else {
 					DRM_ERROR("DP: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				}
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_edp_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_dp_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      dev->mode_config.scaling_mode_property,
 						      DRM_MODE_SCALE_FULLSCREEN);
@@ -2265,7 +2304,10 @@ radeon_add_atom_connector(struct drm_device *dev,
 		case DRM_MODE_CONNECTOR_SVIDEO:
 		case DRM_MODE_CONNECTOR_Composite:
 		case DRM_MODE_CONNECTOR_9PinDIN:
-			drm_connector_init(dev, &radeon_connector->base, &radeon_tv_connector_funcs, connector_type);
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_tv_connector_funcs,
+						    connector_type,
+						    ddc);
 			drm_connector_helper_add(&radeon_connector->base, &radeon_tv_connector_helper_funcs);
 			radeon_connector->dac_load_detect = true;
 			drm_object_attach_property(&radeon_connector->base.base,
@@ -2285,13 +2327,18 @@ radeon_add_atom_connector(struct drm_device *dev,
 				goto failed;
 			radeon_dig_connector->igp_lane_info = igp_lane_info;
 			radeon_connector->con_priv = radeon_dig_connector;
-			drm_connector_init(dev, &radeon_connector->base, &radeon_lvds_connector_funcs, connector_type);
-			drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs);
 			if (i2c_bus->valid) {
 				radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 				if (!radeon_connector->ddc_bus)
 					DRM_ERROR("LVDS: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+				else
+					ddc = &radeon_connector->ddc_bus->adapter;
 			}
+			drm_connector_init_with_ddc(dev, &radeon_connector->base,
+						    &radeon_lvds_connector_funcs,
+						    connector_type,
+						    ddc);
+			drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs);
 			drm_object_attach_property(&radeon_connector->base.base,
 						      dev->mode_config.scaling_mode_property,
 						      DRM_MODE_SCALE_FULLSCREEN);
@@ -2335,6 +2382,7 @@ radeon_add_legacy_connector(struct drm_device *dev,
 	struct radeon_device *rdev = dev->dev_private;
 	struct drm_connector *connector;
 	struct radeon_connector *radeon_connector;
+	struct i2c_adapter *ddc = NULL;
 	uint32_t subpixel_order = SubPixelNone;
 
 	if (connector_type == DRM_MODE_CONNECTOR_Unknown)
@@ -2369,13 +2417,18 @@ radeon_add_legacy_connector(struct drm_device *dev,
 
 	switch (connector_type) {
 	case DRM_MODE_CONNECTOR_VGA:
-		drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
 				DRM_ERROR("VGA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+			else
+				ddc = &radeon_connector->ddc_bus->adapter;
 		}
+		drm_connector_init_with_ddc(dev, &radeon_connector->base,
+					    &radeon_vga_connector_funcs,
+					    connector_type,
+					    ddc);
+		drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 		radeon_connector->dac_load_detect = true;
 		drm_object_attach_property(&radeon_connector->base.base,
 					      rdev->mode_info.load_detect_property,
@@ -2386,13 +2439,18 @@ radeon_add_legacy_connector(struct drm_device *dev,
 		connector->doublescan_allowed = true;
 		break;
 	case DRM_MODE_CONNECTOR_DVIA:
-		drm_connector_init(dev, &radeon_connector->base, &radeon_vga_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
 				DRM_ERROR("DVIA: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+			else
+				ddc = &radeon_connector->ddc_bus->adapter;
 		}
+		drm_connector_init_with_ddc(dev, &radeon_connector->base,
+					    &radeon_vga_connector_funcs,
+					    connector_type,
+					    ddc);
+		drm_connector_helper_add(&radeon_connector->base, &radeon_vga_connector_helper_funcs);
 		radeon_connector->dac_load_detect = true;
 		drm_object_attach_property(&radeon_connector->base.base,
 					      rdev->mode_info.load_detect_property,
@@ -2404,13 +2462,18 @@ radeon_add_legacy_connector(struct drm_device *dev,
 		break;
 	case DRM_MODE_CONNECTOR_DVII:
 	case DRM_MODE_CONNECTOR_DVID:
-		drm_connector_init(dev, &radeon_connector->base, &radeon_dvi_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
 				DRM_ERROR("DVI: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+			else
+				ddc = &radeon_connector->ddc_bus->adapter;
 		}
+		drm_connector_init_with_ddc(dev, &radeon_connector->base,
+					    &radeon_dvi_connector_funcs,
+					    connector_type,
+					    ddc);
+		drm_connector_helper_add(&radeon_connector->base, &radeon_dvi_connector_helper_funcs);
 		if (connector_type == DRM_MODE_CONNECTOR_DVII) {
 			radeon_connector->dac_load_detect = true;
 			drm_object_attach_property(&radeon_connector->base.base,
@@ -2427,7 +2490,10 @@ radeon_add_legacy_connector(struct drm_device *dev,
 	case DRM_MODE_CONNECTOR_SVIDEO:
 	case DRM_MODE_CONNECTOR_Composite:
 	case DRM_MODE_CONNECTOR_9PinDIN:
-		drm_connector_init(dev, &radeon_connector->base, &radeon_tv_connector_funcs, connector_type);
+		drm_connector_init_with_ddc(dev, &radeon_connector->base,
+					    &radeon_tv_connector_funcs,
+					    connector_type,
+					    ddc);
 		drm_connector_helper_add(&radeon_connector->base, &radeon_tv_connector_helper_funcs);
 		radeon_connector->dac_load_detect = true;
 		/* RS400,RC410,RS480 chipset seems to report a lot
@@ -2449,13 +2515,18 @@ radeon_add_legacy_connector(struct drm_device *dev,
 		connector->doublescan_allowed = false;
 		break;
 	case DRM_MODE_CONNECTOR_LVDS:
-		drm_connector_init(dev, &radeon_connector->base, &radeon_lvds_connector_funcs, connector_type);
-		drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs);
 		if (i2c_bus->valid) {
 			radeon_connector->ddc_bus = radeon_i2c_lookup(rdev, i2c_bus);
 			if (!radeon_connector->ddc_bus)
 				DRM_ERROR("LVDS: Failed to assign ddc bus! Check dmesg for i2c errors.\n");
+			else
+				ddc = &radeon_connector->ddc_bus->adapter;
 		}
+		drm_connector_init_with_ddc(dev, &radeon_connector->base,
+					    &radeon_lvds_connector_funcs,
+					    connector_type,
+					    ddc);
+		drm_connector_helper_add(&radeon_connector->base, &radeon_lvds_connector_helper_funcs);
 		drm_object_attach_property(&radeon_connector->base.base,
 					      dev->mode_config.scaling_mode_property,
 					      DRM_MODE_SCALE_FULLSCREEN);
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 7b5460678382..0d0ab8e0ff3b 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -26,11 +26,11 @@
  */
 
 #include <linux/list_sort.h>
+#include <linux/pci.h>
 #include <linux/uaccess.h>
 
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 5d017f0aec66..a522e092038b 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -28,6 +28,7 @@
 
 #include <linux/console.h>
 #include <linux/efi.h>
+#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/vga_switcheroo.h>
@@ -38,7 +39,6 @@
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/radeon_drm.h>
 
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index e81b01f8db90..856526cb2caf 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -24,6 +24,7 @@
  *          Alex Deucher
  */
 
+#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/gcd.h>
 
@@ -36,7 +37,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
@@ -847,11 +847,11 @@ static bool radeon_setup_enc_conn(struct drm_device *dev)
 	if (rdev->bios) {
 		if (rdev->is_atom_bios) {
 			ret = radeon_get_atom_connector_info_from_supported_devices_table(dev);
-			if (ret == false)
+			if (!ret)
 				ret = radeon_get_atom_connector_info_from_object_table(dev);
 		} else {
 			ret = radeon_get_legacy_connector_info_from_bios(dev);
-			if (ret == false)
+			if (!ret)
 				ret = radeon_get_legacy_connector_info_from_table(dev);
 		}
 	} else {
@@ -1687,7 +1687,6 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 	struct radeon_encoder *radeon_encoder;
 	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector;
 	bool first = true;
 	u32 src_v = 1, dst_v = 1;
 	u32 src_h = 1, dst_h = 1;
@@ -1700,7 +1699,6 @@ bool radeon_crtc_scaling_mode_fixup(struct drm_crtc *crtc,
 			continue;
 		radeon_encoder = to_radeon_encoder(encoder);
 		connector = radeon_get_connector_for_encoder(encoder);
-		radeon_connector = to_radeon_connector(connector);
 
 		if (first) {
 			/* set scaling */
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index ee28f5b3785e..28eef9282874 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -518,7 +518,7 @@ static bool radeon_mst_mode_fixup(struct drm_encoder *encoder,
 
 	mst_enc = radeon_encoder->enc_priv;
 
-	mst_enc->pbn = drm_dp_calc_pbn_mode(adjusted_mode->clock, bpp);
+	mst_enc->pbn = drm_dp_calc_pbn_mode(adjusted_mode->clock, bpp, false);
 
 	mst_enc->primary->active_device = mst_enc->primary->devices & mst_enc->connector->devices;
 	DRM_DEBUG_KMS("setting active device to %08x from %08x %08x for encoder %d\n",
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index a0c99087034a..ced022fae19d 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -24,9 +24,10 @@
  *          Alex Deucher
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 2c564f4f3468..ec0b7d6c994d 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -25,6 +25,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/vga_switcheroo.h>
@@ -33,7 +34,6 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
@@ -73,7 +73,7 @@ radeonfb_release(struct fb_info *info, int user)
 	return 0;
 }
 
-static struct fb_ops radeonfb_ops = {
+static const struct fb_ops radeonfb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_open = radeonfb_open,
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index d4d3778d0a98..f178ba321715 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -26,9 +26,9 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
 #include <linux/vmalloc.h>
 
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 67298a0739cb..068c3e5da173 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -26,10 +26,11 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/radeon_i2c.c b/drivers/gpu/drm/radeon/radeon_i2c.c
index d465a3de7732..545e31e6cc3a 100644
--- a/drivers/gpu/drm/radeon/radeon_i2c.c
+++ b/drivers/gpu/drm/radeon/radeon_i2c.c
@@ -25,10 +25,10 @@
  */
 
 #include <linux/export.h>
+#include <linux/pci.h>
 
 #include <drm/drm_device.h>
 #include <drm/drm_edid.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index d9613638f9cc..b86bc88ad430 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -26,12 +26,12 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_device.h>
 #include <drm/drm_irq.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index e85c554eeaa9..d24f23a81656 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -26,6 +26,7 @@
  *          Jerome Glisse
  */
 
+#include <linux/pci.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
@@ -34,7 +35,6 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index ef100b790463..44d060f75318 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -25,11 +25,11 @@
  */
 
 #include <linux/backlight.h>
+#include <linux/pci.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_util.h>
 #include <drm/radeon_drm.h>
 
@@ -1712,7 +1712,7 @@ static struct radeon_encoder_int_tmds *radeon_legacy_get_tmds_info(struct radeon
 	else
 		ret = radeon_legacy_get_tmds_info_from_combios(encoder, tmds);
 
-	if (ret == false)
+	if (!ret)
 		radeon_legacy_get_tmds_info_from_table(encoder, tmds);
 
 	return tmds;
@@ -1735,7 +1735,7 @@ static struct radeon_encoder_ext_tmds *radeon_legacy_get_ext_tmds_info(struct ra
 
 	ret = radeon_legacy_get_ext_tmds_info_from_combios(encoder, tmds);
 
-	if (ret == false)
+	if (!ret)
 		radeon_legacy_get_ext_tmds_info_from_table(encoder, tmds);
 
 	return tmds;
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_tv.c b/drivers/gpu/drm/radeon/radeon_legacy_tv.c
index f132eec737ad..d9df7f311e76 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_tv.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_tv.c
@@ -537,7 +537,7 @@ void radeon_legacy_tv_mode_set(struct drm_encoder *encoder,
 	uint32_t tv_master_cntl, tv_rgb_cntl, tv_dac_cntl;
 	uint32_t tv_modulator_cntl1, tv_modulator_cntl2;
 	uint32_t tv_vscaler_cntl1, tv_vscaler_cntl2;
-	uint32_t tv_pll_cntl, tv_pll_cntl1, tv_ftotal;
+	uint32_t tv_pll_cntl, tv_ftotal;
 	uint32_t tv_y_fall_cntl, tv_y_rise_cntl, tv_y_saw_tooth_cntl;
 	uint32_t m, n, p;
 	const uint16_t *hor_timing;
@@ -709,12 +709,6 @@ void radeon_legacy_tv_mode_set(struct drm_encoder *encoder,
 		(((n >> 9) & RADEON_TV_N0HI_MASK) << RADEON_TV_N0HI_SHIFT) |
 		((p & RADEON_TV_P_MASK) << RADEON_TV_P_SHIFT);
 
-	tv_pll_cntl1 = (((4 & RADEON_TVPCP_MASK) << RADEON_TVPCP_SHIFT) |
-			((4 & RADEON_TVPVG_MASK) << RADEON_TVPVG_SHIFT) |
-			((1 & RADEON_TVPDC_MASK) << RADEON_TVPDC_SHIFT) |
-			RADEON_TVCLK_SRC_SEL_TVPLL |
-			RADEON_TVPLL_TEST_DIS);
-
 	tv_dac->tv.tv_uv_adr = 0xc8;
 
 	if (tv_dac->tv_std == TV_STD_NTSC ||
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 5d10e11a9225..8c5d6fda0d75 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -23,10 +23,10 @@
 
 #include <linux/hwmon-sysfs.h>
 #include <linux/hwmon.h>
+#include <linux/pci.h>
 #include <linux/power_supply.h>
 
 #include <drm/drm_debugfs.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 
 #include "atom.h"
@@ -1789,7 +1789,7 @@ static bool radeon_pm_debug_check_in_vbl(struct radeon_device *rdev, bool finish
 	u32 stat_crtc = 0;
 	bool in_vbl = radeon_pm_in_vbl(rdev);
 
-	if (in_vbl == false)
+	if (!in_vbl)
 		DRM_DEBUG_DRIVER("not in vbl for pm change %08x at %s\n", stat_crtc,
 			 finish ? "exit" : "entry");
 	return in_vbl;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 15bf8a207cb0..3b92311d30b9 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -32,6 +32,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -41,7 +42,6 @@
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_prime.h>
 #include <drm/radeon_drm.h>
 #include <drm/ttm/ttm_bo_api.h>
@@ -881,9 +881,6 @@ void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
 	man->size = size >> PAGE_SHIFT;
 }
 
-static struct vm_operations_struct radeon_ttm_vm_ops;
-static const struct vm_operations_struct *ttm_vm_ops = NULL;
-
 static vm_fault_t radeon_ttm_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo;
@@ -891,34 +888,36 @@ static vm_fault_t radeon_ttm_fault(struct vm_fault *vmf)
 	vm_fault_t ret;
 
 	bo = (struct ttm_buffer_object *)vmf->vma->vm_private_data;
-	if (bo == NULL) {
+	if (bo == NULL)
 		return VM_FAULT_NOPAGE;
-	}
+
 	rdev = radeon_get_rdev(bo->bdev);
 	down_read(&rdev->pm.mclk_lock);
-	ret = ttm_vm_ops->fault(vmf);
+	ret = ttm_bo_vm_fault(vmf);
 	up_read(&rdev->pm.mclk_lock);
 	return ret;
 }
 
+static struct vm_operations_struct radeon_ttm_vm_ops = {
+	.fault = radeon_ttm_fault,
+	.open = ttm_bo_vm_open,
+	.close = ttm_bo_vm_close,
+	.access = ttm_bo_vm_access
+};
+
 int radeon_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	int r;
 	struct drm_file *file_priv = filp->private_data;
 	struct radeon_device *rdev = file_priv->minor->dev->dev_private;
 
-	if (rdev == NULL) {
+	if (rdev == NULL)
 		return -EINVAL;
-	}
+
 	r = ttm_bo_mmap(filp, vma, &rdev->mman.bdev);
-	if (unlikely(r != 0)) {
+	if (unlikely(r != 0))
 		return r;
-	}
-	if (unlikely(ttm_vm_ops == NULL)) {
-		ttm_vm_ops = vma->vm_ops;
-		radeon_ttm_vm_ops = *ttm_vm_ops;
-		radeon_ttm_vm_ops.fault = &radeon_ttm_fault;
-	}
+
 	vma->vm_ops = &radeon_ttm_vm_ops;
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index 59db54ace428..5e8006444704 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -388,9 +388,9 @@ int radeon_vce_get_create_msg(struct radeon_device *rdev, int ring,
 		ib.ptr[i] = cpu_to_le32(0x0);
 
 	r = radeon_ib_schedule(rdev, &ib, NULL, false);
-	if (r) {
+	if (r)
 		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
-	}
+
 
 	if (fence)
 		*fence = radeon_fence_ref(ib.fence);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index e0ad547786e8..f60fae0aed11 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -296,9 +296,9 @@ struct radeon_bo_va *radeon_vm_bo_find(struct radeon_vm *vm,
 	struct radeon_bo_va *bo_va;
 
 	list_for_each_entry(bo_va, &bo->va, bo_list) {
-		if (bo_va->vm == vm) {
+		if (bo_va->vm == vm)
 			return bo_va;
-		}
+
 	}
 	return NULL;
 }
@@ -323,9 +323,9 @@ struct radeon_bo_va *radeon_vm_bo_add(struct radeon_device *rdev,
 	struct radeon_bo_va *bo_va;
 
 	bo_va = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
-	if (bo_va == NULL) {
+	if (bo_va == NULL)
 		return NULL;
-	}
+
 	bo_va->vm = vm;
 	bo_va->bo = bo;
 	bo_va->it.start = 0;
@@ -947,9 +947,9 @@ int radeon_vm_bo_update(struct radeon_device *rdev,
 
 	if (mem) {
 		addr = (u64)mem->start << PAGE_SHIFT;
-		if (mem->mem_type != TTM_PL_SYSTEM) {
+		if (mem->mem_type != TTM_PL_SYSTEM)
 			bo_va->flags |= RADEON_VM_PAGE_VALID;
-		}
+
 		if (mem->mem_type == TTM_PL_TT) {
 			bo_va->flags |= RADEON_VM_PAGE_SYSTEM;
 			if (!(bo_va->bo->flags & (RADEON_GEM_GTT_WC | RADEON_GEM_GTT_UC)))
@@ -1233,9 +1233,9 @@ void radeon_vm_fini(struct radeon_device *rdev, struct radeon_vm *vm)
 	struct radeon_bo_va *bo_va, *tmp;
 	int i, r;
 
-	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
+	if (!RB_EMPTY_ROOT(&vm->va.rb_root))
 		dev_err(rdev->dev, "still active bo inside vm\n");
-	}
+
 	rbtree_postorder_for_each_entry_safe(bo_va, tmp,
 					     &vm->va.rb_root, it.rb) {
 		interval_tree_remove(&bo_va->it, &vm->va);
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 2f8ff089f7b1..c88b4906f7bc 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -37,9 +37,9 @@
  */
 
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/pci.h>
 
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 
 #include "atom.h"
diff --git a/drivers/gpu/drm/radeon/rs690.c b/drivers/gpu/drm/radeon/rs690.c
index 267d8a9134c8..c296f94f9700 100644
--- a/drivers/gpu/drm/radeon/rs690.c
+++ b/drivers/gpu/drm/radeon/rs690.c
@@ -26,7 +26,7 @@
  *          Jerome Glisse
  */
 
-#include <drm/drm_pci.h>
+#include <linux/pci.h>
 
 #include "atom.h"
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/rs780_dpm.c b/drivers/gpu/drm/radeon/rs780_dpm.c
index 72dbf3251c53..17390074277a 100644
--- a/drivers/gpu/drm/radeon/rs780_dpm.c
+++ b/drivers/gpu/drm/radeon/rs780_dpm.c
@@ -22,10 +22,9 @@
  * Authors: Alex Deucher
  */
 
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "atom.h"
 #include "r600_dpm.h"
 #include "radeon.h"
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 7a6fc66d6a40..21f653ae1e1b 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -27,10 +27,10 @@
  */
 
 #include <linux/firmware.h>
+#include <linux/pci.h>
 #include <linux/slab.h>
 
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/radeon_drm.h>
 
 #include "atom.h"
@@ -1703,7 +1703,7 @@ static void rv770_uvd_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable uvd here.
 		 */
-		rdev->has_uvd = 0;
+		rdev->has_uvd = false;
 		return;
 	}
 	rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index d7eea75b2c27..93dcab548a83 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -23,10 +23,10 @@
  */
 
 #include <linux/firmware.h>
-#include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
 
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 #include <drm/radeon_drm.h>
 
@@ -6472,7 +6472,7 @@ static void si_uvd_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable uvd here.
 		 */
-		rdev->has_uvd = 0;
+		rdev->has_uvd = false;
 		return;
 	}
 	rdev->ring[R600_RING_TYPE_UVD_INDEX].ring_obj = NULL;
@@ -6539,7 +6539,7 @@ static void si_vce_init(struct radeon_device *rdev)
 		 * there. So it is pointless to try to go through that code
 		 * hence why we disable vce here.
 		 */
-		rdev->has_vce = 0;
+		rdev->has_vce = false;
 		return;
 	}
 	rdev->ring[TN_RING_TYPE_VCE1_INDEX].ring_obj = NULL;
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index a0b382a637a6..05e8b4d0af3f 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -22,10 +22,9 @@
  */
 
 #include <linux/math64.h>
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "atom.h"
 #include "r600_dpm.h"
 #include "radeon.h"
@@ -3640,14 +3639,13 @@ static int si_notify_smc_display_change(struct radeon_device *rdev,
 
 static void si_program_response_times(struct radeon_device *rdev)
 {
-	u32 voltage_response_time, backbias_response_time, acpi_delay_time, vbi_time_out;
+	u32 voltage_response_time, acpi_delay_time, vbi_time_out;
 	u32 vddc_dly, acpi_dly, vbi_dly;
 	u32 reference_clock;
 
 	si_write_smc_soft_register(rdev, SI_SMC_SOFT_REGISTER_mvdd_chg_time, 1);
 
 	voltage_response_time = (u32)rdev->pm.dpm.voltage_response_time;
-	backbias_response_time = (u32)rdev->pm.dpm.backbias_response_time;
 
 	if (voltage_response_time == 0)
 		voltage_response_time = 1000;
@@ -5900,7 +5898,7 @@ static int si_patch_single_dependency_table_based_on_leakage(struct radeon_devic
 
 static int si_patch_dependency_tables_based_on_leakage(struct radeon_device *rdev)
 {
-	int ret = 0;
+	int ret;
 
 	ret = si_patch_single_dependency_table_based_on_leakage(rdev,
 								&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk);
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 65302f9d025e..4d93b84aa739 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -21,10 +21,9 @@
  *
  */
 
+#include <linux/pci.h>
 #include <linux/seq_file.h>
 
-#include <drm/drm_pci.h>
-
 #include "r600_dpm.h"
 #include "radeon.h"
 #include "radeon_asic.h"
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index 1529849e217e..0919f1f159a4 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -4,6 +4,7 @@ config DRM_RCAR_DU
 	depends on DRM && OF
 	depends on ARM || ARM64
 	depends on ARCH_RENESAS || COMPILE_TEST
+	imply DRM_RCAR_CMM
 	imply DRM_RCAR_LVDS
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
@@ -13,6 +14,13 @@ config DRM_RCAR_DU
 	  Choose this option if you have an R-Car chipset.
 	  If M is selected the module will be called rcar-du-drm.
 
+config DRM_RCAR_CMM
+	tristate "R-Car DU Color Management Module (CMM) Support"
+	depends on DRM && OF
+	depends on DRM_RCAR_DU
+	help
+	  Enable support for R-Car Color Management Module (CMM).
+
 config DRM_RCAR_DW_HDMI
 	tristate "R-Car DU Gen3 HDMI Encoder Support"
 	depends on DRM && OF
diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile
index 6c2ed9c46467..4d1187ccc3e5 100644
--- a/drivers/gpu/drm/rcar-du/Makefile
+++ b/drivers/gpu/drm/rcar-du/Makefile
@@ -15,6 +15,7 @@ rcar-du-drm-$(CONFIG_DRM_RCAR_LVDS)	+= rcar_du_of.o \
 rcar-du-drm-$(CONFIG_DRM_RCAR_VSP)	+= rcar_du_vsp.o
 rcar-du-drm-$(CONFIG_DRM_RCAR_WRITEBACK) += rcar_du_writeback.o
 
+obj-$(CONFIG_DRM_RCAR_CMM)		+= rcar_cmm.o
 obj-$(CONFIG_DRM_RCAR_DU)		+= rcar-du-drm.o
 obj-$(CONFIG_DRM_RCAR_DW_HDMI)		+= rcar_dw_hdmi.o
 obj-$(CONFIG_DRM_RCAR_LVDS)		+= rcar_lvds.o
diff --git a/drivers/gpu/drm/rcar-du/rcar_cmm.c b/drivers/gpu/drm/rcar-du/rcar_cmm.c
new file mode 100644
index 000000000000..c578095b09a5
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_cmm.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * rcar_cmm.c -- R-Car Display Unit Color Management Module
+ *
+ * Copyright (C) 2019 Jacopo Mondi <jacopo+renesas@jmondi.org>
+ */
+
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+#include <drm/drm_color_mgmt.h>
+
+#include "rcar_cmm.h"
+
+#define CM2_LUT_CTRL		0x0000
+#define CM2_LUT_CTRL_LUT_EN	BIT(0)
+#define CM2_LUT_TBL_BASE	0x0600
+#define CM2_LUT_TBL(__i)	(CM2_LUT_TBL_BASE + (__i) * 4)
+
+struct rcar_cmm {
+	void __iomem *base;
+
+	/*
+	 * @lut:		1D-LUT state
+	 * @lut.enabled:	1D-LUT enabled flag
+	 */
+	struct {
+		bool enabled;
+	} lut;
+};
+
+static inline int rcar_cmm_read(struct rcar_cmm *rcmm, u32 reg)
+{
+	return ioread32(rcmm->base + reg);
+}
+
+static inline void rcar_cmm_write(struct rcar_cmm *rcmm, u32 reg, u32 data)
+{
+	iowrite32(data, rcmm->base + reg);
+}
+
+/*
+ * rcar_cmm_lut_write() - Scale the DRM LUT table entries to hardware precision
+ *			  and write to the CMM registers
+ * @rcmm: Pointer to the CMM device
+ * @drm_lut: Pointer to the DRM LUT table
+ */
+static void rcar_cmm_lut_write(struct rcar_cmm *rcmm,
+			       const struct drm_color_lut *drm_lut)
+{
+	unsigned int i;
+
+	for (i = 0; i < CM2_LUT_SIZE; ++i) {
+		u32 entry = drm_color_lut_extract(drm_lut[i].red, 8) << 16
+			  | drm_color_lut_extract(drm_lut[i].green, 8) << 8
+			  | drm_color_lut_extract(drm_lut[i].blue, 8);
+
+		rcar_cmm_write(rcmm, CM2_LUT_TBL(i), entry);
+	}
+}
+
+/*
+ * rcar_cmm_setup() - Configure the CMM unit
+ * @pdev: The platform device associated with the CMM instance
+ * @config: The CMM unit configuration
+ *
+ * Configure the CMM unit with the given configuration. Currently enabling,
+ * disabling and programming of the 1-D LUT unit is supported.
+ *
+ * As rcar_cmm_setup() accesses the CMM registers the unit should be powered
+ * and its functional clock enabled. To guarantee this, before any call to
+ * this function is made, the CMM unit has to be enabled by calling
+ * rcar_cmm_enable() first.
+ *
+ * TODO: Add support for LUT double buffer operations to avoid updating the
+ * LUT table entries while a frame is being displayed.
+ */
+int rcar_cmm_setup(struct platform_device *pdev,
+		   const struct rcar_cmm_config *config)
+{
+	struct rcar_cmm *rcmm = platform_get_drvdata(pdev);
+
+	/* Disable LUT if no table is provided. */
+	if (!config->lut.table) {
+		if (rcmm->lut.enabled) {
+			rcar_cmm_write(rcmm, CM2_LUT_CTRL, 0);
+			rcmm->lut.enabled = false;
+		}
+
+		return 0;
+	}
+
+	/* Enable LUT and program the new gamma table values. */
+	if (!rcmm->lut.enabled) {
+		rcar_cmm_write(rcmm, CM2_LUT_CTRL, CM2_LUT_CTRL_LUT_EN);
+		rcmm->lut.enabled = true;
+	}
+
+	rcar_cmm_lut_write(rcmm, config->lut.table);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rcar_cmm_setup);
+
+/*
+ * rcar_cmm_enable() - Enable the CMM unit
+ * @pdev: The platform device associated with the CMM instance
+ *
+ * When the output of the corresponding DU channel is routed to the CMM unit,
+ * the unit shall be enabled before the DU channel is started, and remain
+ * enabled until the channel is stopped. The CMM unit shall be disabled with
+ * rcar_cmm_disable().
+ *
+ * Calls to rcar_cmm_enable() and rcar_cmm_disable() are not reference-counted.
+ * It is an error to attempt to enable an already enabled CMM unit, or to
+ * attempt to disable a disabled unit.
+ */
+int rcar_cmm_enable(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rcar_cmm_enable);
+
+/*
+ * rcar_cmm_disable() - Disable the CMM unit
+ * @pdev: The platform device associated with the CMM instance
+ *
+ * See rcar_cmm_enable() for usage information.
+ *
+ * Disabling the CMM unit disable all the internal processing blocks. The CMM
+ * state shall thus be restored with rcar_cmm_setup() when re-enabling the CMM
+ * unit after the next rcar_cmm_enable() call.
+ */
+void rcar_cmm_disable(struct platform_device *pdev)
+{
+	struct rcar_cmm *rcmm = platform_get_drvdata(pdev);
+
+	rcar_cmm_write(rcmm, CM2_LUT_CTRL, 0);
+	rcmm->lut.enabled = false;
+
+	pm_runtime_put(&pdev->dev);
+}
+EXPORT_SYMBOL_GPL(rcar_cmm_disable);
+
+/*
+ * rcar_cmm_init() - Initialize the CMM unit
+ * @pdev: The platform device associated with the CMM instance
+ *
+ * Return: 0 on success, -EPROBE_DEFER if the CMM is not available yet,
+ *         -ENODEV if the DRM_RCAR_CMM config option is disabled
+ */
+int rcar_cmm_init(struct platform_device *pdev)
+{
+	struct rcar_cmm *rcmm = platform_get_drvdata(pdev);
+
+	if (!rcmm)
+		return -EPROBE_DEFER;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rcar_cmm_init);
+
+static int rcar_cmm_probe(struct platform_device *pdev)
+{
+	struct rcar_cmm *rcmm;
+
+	rcmm = devm_kzalloc(&pdev->dev, sizeof(*rcmm), GFP_KERNEL);
+	if (!rcmm)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, rcmm);
+
+	rcmm->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(rcmm->base))
+		return PTR_ERR(rcmm->base);
+
+	pm_runtime_enable(&pdev->dev);
+
+	return 0;
+}
+
+static int rcar_cmm_remove(struct platform_device *pdev)
+{
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+static const struct of_device_id rcar_cmm_of_table[] = {
+	{ .compatible = "renesas,rcar-gen3-cmm", },
+	{ .compatible = "renesas,rcar-gen2-cmm", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rcar_cmm_of_table);
+
+static struct platform_driver rcar_cmm_platform_driver = {
+	.probe		= rcar_cmm_probe,
+	.remove		= rcar_cmm_remove,
+	.driver		= {
+		.name	= "rcar-cmm",
+		.of_match_table = rcar_cmm_of_table,
+	},
+};
+
+module_platform_driver(rcar_cmm_platform_driver);
+
+MODULE_AUTHOR("Jacopo Mondi <jacopo+renesas@jmondi.org>");
+MODULE_DESCRIPTION("Renesas R-Car CMM Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/rcar-du/rcar_cmm.h b/drivers/gpu/drm/rcar-du/rcar_cmm.h
new file mode 100644
index 000000000000..b5f7ec6db04a
--- /dev/null
+++ b/drivers/gpu/drm/rcar-du/rcar_cmm.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * rcar_cmm.h -- R-Car Display Unit Color Management Module
+ *
+ * Copyright (C) 2019 Jacopo Mondi <jacopo+renesas@jmondi.org>
+ */
+
+#ifndef __RCAR_CMM_H__
+#define __RCAR_CMM_H__
+
+#define CM2_LUT_SIZE		256
+
+struct drm_color_lut;
+struct platform_device;
+
+/**
+ * struct rcar_cmm_config - CMM configuration
+ *
+ * @lut:	1D-LUT configuration
+ * @lut.table:	1D-LUT table entries. Disable LUT operations when NULL
+ */
+struct rcar_cmm_config {
+	struct {
+		struct drm_color_lut *table;
+	} lut;
+};
+
+#if IS_ENABLED(CONFIG_DRM_RCAR_CMM)
+int rcar_cmm_init(struct platform_device *pdev);
+
+int rcar_cmm_enable(struct platform_device *pdev);
+void rcar_cmm_disable(struct platform_device *pdev);
+
+int rcar_cmm_setup(struct platform_device *pdev,
+		   const struct rcar_cmm_config *config);
+#else
+static inline int rcar_cmm_init(struct platform_device *pdev)
+{
+	return -ENODEV;
+}
+
+static inline int rcar_cmm_enable(struct platform_device *pdev)
+{
+	return 0;
+}
+
+static inline void rcar_cmm_disable(struct platform_device *pdev)
+{
+}
+
+static inline int rcar_cmm_setup(struct platform_device *pdev,
+				 const struct rcar_cmm_config *config)
+{
+	return 0;
+}
+#endif /* IS_ENABLED(CONFIG_DRM_RCAR_CMM) */
+
+#endif /* __RCAR_CMM_H__ */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index 2da46e3dc4ae..d73e88ddecd0 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -14,6 +14,7 @@
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_bridge.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_device.h>
 #include <drm/drm_fb_cma_helper.h>
@@ -21,6 +22,7 @@
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_vblank.h>
 
+#include "rcar_cmm.h"
 #include "rcar_du_crtc.h"
 #include "rcar_du_drv.h"
 #include "rcar_du_encoder.h"
@@ -475,6 +477,45 @@ static void rcar_du_crtc_wait_page_flip(struct rcar_du_crtc *rcrtc)
 }
 
 /* -----------------------------------------------------------------------------
+ * Color Management Module (CMM)
+ */
+
+static int rcar_du_cmm_check(struct drm_crtc *crtc,
+			     struct drm_crtc_state *state)
+{
+	struct drm_property_blob *drm_lut = state->gamma_lut;
+	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
+	struct device *dev = rcrtc->dev->dev;
+
+	if (!drm_lut)
+		return 0;
+
+	/* We only accept fully populated LUT tables. */
+	if (drm_color_lut_size(drm_lut) != CM2_LUT_SIZE) {
+		dev_err(dev, "invalid gamma lut size: %zu bytes\n",
+			drm_lut->length);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void rcar_du_cmm_setup(struct drm_crtc *crtc)
+{
+	struct drm_property_blob *drm_lut = crtc->state->gamma_lut;
+	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
+	struct rcar_cmm_config cmm_config = {};
+
+	if (!rcrtc->cmm)
+		return;
+
+	if (drm_lut)
+		cmm_config.lut.table = (struct drm_color_lut *)drm_lut->data;
+
+	rcar_cmm_setup(rcrtc->cmm, &cmm_config);
+}
+
+/* -----------------------------------------------------------------------------
  * Start/Stop and Suspend/Resume
  */
 
@@ -619,6 +660,9 @@ static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc)
 	if (rcar_du_has(rcrtc->dev, RCAR_DU_FEATURE_VSP1_SOURCE))
 		rcar_du_vsp_disable(rcrtc);
 
+	if (rcrtc->cmm)
+		rcar_cmm_disable(rcrtc->cmm);
+
 	/*
 	 * Select switch sync mode. This stops display operation and configures
 	 * the HSYNC and VSYNC signals as inputs.
@@ -642,6 +686,11 @@ static int rcar_du_crtc_atomic_check(struct drm_crtc *crtc,
 {
 	struct rcar_du_crtc_state *rstate = to_rcar_crtc_state(state);
 	struct drm_encoder *encoder;
+	int ret;
+
+	ret = rcar_du_cmm_check(crtc, state);
+	if (ret)
+		return ret;
 
 	/* Store the routes from the CRTC output to the DU outputs. */
 	rstate->outputs = 0;
@@ -667,6 +716,8 @@ static void rcar_du_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct rcar_du_crtc_state *rstate = to_rcar_crtc_state(crtc->state);
 	struct rcar_du_device *rcdu = rcrtc->dev;
 
+	if (rcrtc->cmm)
+		rcar_cmm_enable(rcrtc->cmm);
 	rcar_du_crtc_get(rcrtc);
 
 	/*
@@ -680,12 +731,20 @@ static void rcar_du_crtc_atomic_enable(struct drm_crtc *crtc,
 			rcdu->encoders[RCAR_DU_OUTPUT_LVDS0 + rcrtc->index];
 		const struct drm_display_mode *mode =
 			&crtc->state->adjusted_mode;
+		struct drm_bridge *bridge;
 
-		rcar_lvds_clk_enable(encoder->base.bridge,
-				     mode->clock * 1000);
+		bridge = drm_bridge_chain_get_first_bridge(&encoder->base);
+		rcar_lvds_clk_enable(bridge, mode->clock * 1000);
 	}
 
 	rcar_du_crtc_start(rcrtc);
+
+	/*
+	 * TODO: The chip manual indicates that CMM tables should be written
+	 * after the DU channel has been activated. Investigate the impact
+	 * of this restriction on the first displayed frame.
+	 */
+	rcar_du_cmm_setup(crtc);
 }
 
 static void rcar_du_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -702,12 +761,14 @@ static void rcar_du_crtc_atomic_disable(struct drm_crtc *crtc,
 	    rstate->outputs == BIT(RCAR_DU_OUTPUT_DPAD0)) {
 		struct rcar_du_encoder *encoder =
 			rcdu->encoders[RCAR_DU_OUTPUT_LVDS0 + rcrtc->index];
+		struct drm_bridge *bridge;
 
 		/*
 		 * Disable the LVDS clock output, see
 		 * rcar_du_crtc_atomic_enable().
 		 */
-		rcar_lvds_clk_disable(encoder->base.bridge);
+		bridge = drm_bridge_chain_get_first_bridge(&encoder->base);
+		rcar_lvds_clk_disable(bridge);
 	}
 
 	spin_lock_irq(&crtc->dev->event_lock);
@@ -739,6 +800,10 @@ static void rcar_du_crtc_atomic_begin(struct drm_crtc *crtc,
 	 */
 	rcar_du_crtc_get(rcrtc);
 
+	/* If the active state changed, we let .atomic_enable handle CMM. */
+	if (crtc->state->color_mgmt_changed && !crtc->state->active_changed)
+		rcar_du_cmm_setup(crtc);
+
 	if (rcar_du_has(rcrtc->dev, RCAR_DU_FEATURE_VSP1_SOURCE))
 		rcar_du_vsp_atomic_begin(rcrtc);
 }
@@ -1075,6 +1140,7 @@ static const struct drm_crtc_funcs crtc_funcs_gen3 = {
 	.set_crc_source = rcar_du_crtc_set_crc_source,
 	.verify_crc_source = rcar_du_crtc_verify_crc_source,
 	.get_crc_sources = rcar_du_crtc_get_crc_sources,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 };
 
 /* -----------------------------------------------------------------------------
@@ -1194,6 +1260,15 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int swindex,
 	if (ret < 0)
 		return ret;
 
+	/* CMM might be disabled for this CRTC. */
+	if (rcdu->cmms[swindex]) {
+		rcrtc->cmm = rcdu->cmms[swindex];
+		rgrp->cmms_mask |= BIT(hwindex % 2);
+
+		drm_mode_crtc_set_gamma_size(crtc, CM2_LUT_SIZE);
+		drm_crtc_enable_color_mgmt(crtc, 0, false, CM2_LUT_SIZE);
+	}
+
 	drm_crtc_helper_add(crtc, &crtc_helper_funcs);
 
 	/* Start with vertical blanking interrupt reporting disabled. */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index 3b7fc668996f..5f2940c42225 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
@@ -39,6 +39,7 @@ struct rcar_du_vsp;
  * @vblank_wait: wait queue used to signal vertical blanking
  * @vblank_count: number of vertical blanking interrupts to wait for
  * @group: CRTC group this CRTC belongs to
+ * @cmm: CMM associated with this CRTC
  * @vsp: VSP feeding video to this CRTC
  * @vsp_pipe: index of the VSP pipeline feeding video to this CRTC
  * @writeback: the writeback connector
@@ -64,6 +65,7 @@ struct rcar_du_crtc {
 	unsigned int vblank_count;
 
 	struct rcar_du_group *group;
+	struct platform_device *cmm;
 	struct rcar_du_vsp *vsp;
 	unsigned int vsp_pipe;
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index f266c17b907a..654e2dd08146 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -399,7 +399,10 @@ static const struct rcar_du_device_info rcar_du_r8a77970_info = {
 		  | RCAR_DU_FEATURE_TVM_SYNC,
 	.channels_mask = BIT(0),
 	.routes = {
-		/* R8A77970 has one RGB output and one LVDS output. */
+		/*
+		 * R8A77970 and R8A77980 have one RGB output and one LVDS
+		 * output.
+		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
 			.possible_crtcs = BIT(0),
 			.port = 0,
@@ -457,6 +460,7 @@ static const struct of_device_id rcar_du_of_table[] = {
 	{ .compatible = "renesas,du-r8a7796", .data = &rcar_du_r8a7796_info },
 	{ .compatible = "renesas,du-r8a77965", .data = &rcar_du_r8a77965_info },
 	{ .compatible = "renesas,du-r8a77970", .data = &rcar_du_r8a77970_info },
+	{ .compatible = "renesas,du-r8a77980", .data = &rcar_du_r8a77970_info },
 	{ .compatible = "renesas,du-r8a77990", .data = &rcar_du_r8a7799x_info },
 	{ .compatible = "renesas,du-r8a77995", .data = &rcar_du_r8a7799x_info },
 	{ }
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
index 1327cd0df90a..61504c54e2ec 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/wait.h>
 
+#include "rcar_cmm.h"
 #include "rcar_du_crtc.h"
 #include "rcar_du_group.h"
 #include "rcar_du_vsp.h"
@@ -85,6 +86,7 @@ struct rcar_du_device {
 	struct rcar_du_encoder *encoders[RCAR_DU_OUTPUT_MAX];
 
 	struct rcar_du_group groups[RCAR_DU_MAX_GROUPS];
+	struct platform_device *cmms[RCAR_DU_MAX_CRTCS];
 	struct rcar_du_vsp vsps[RCAR_DU_MAX_VSPS];
 
 	struct {
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.c b/drivers/gpu/drm/rcar-du/rcar_du_group.c
index 9eee47969e77..88a783ceb3e9 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.c
@@ -135,6 +135,7 @@ static void rcar_du_group_setup_didsr(struct rcar_du_group *rgrp)
 static void rcar_du_group_setup(struct rcar_du_group *rgrp)
 {
 	struct rcar_du_device *rcdu = rgrp->dev;
+	u32 defr7 = DEFR7_CODE;
 
 	/* Enable extended features */
 	rcar_du_group_write(rgrp, DEFR, DEFR_CODE | DEFR_DEFE);
@@ -147,6 +148,15 @@ static void rcar_du_group_setup(struct rcar_du_group *rgrp)
 
 	rcar_du_group_setup_pins(rgrp);
 
+	/*
+	 * TODO: Handle routing of the DU output to CMM dynamically, as we
+	 * should bypass CMM completely when no color management feature is
+	 * used.
+	 */
+	defr7 |= (rgrp->cmms_mask & BIT(1) ? DEFR7_CMME1 : 0) |
+		 (rgrp->cmms_mask & BIT(0) ? DEFR7_CMME0 : 0);
+	rcar_du_group_write(rgrp, DEFR7, defr7);
+
 	if (rcdu->info->gen >= 2) {
 		rcar_du_group_setup_defr8(rgrp);
 		rcar_du_group_setup_didsr(rgrp);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.h b/drivers/gpu/drm/rcar-du/rcar_du_group.h
index 87950c1f6a52..e9906609c635 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.h
@@ -22,6 +22,7 @@ struct rcar_du_device;
  * @mmio_offset: registers offset in the device memory map
  * @index: group index
  * @channels_mask: bitmask of populated DU channels in this group
+ * @cmms_mask: bitmask of available CMMs in this group
  * @num_crtcs: number of CRTCs in this group (1 or 2)
  * @use_count: number of users of the group (rcar_du_group_(get|put))
  * @used_crtcs: number of CRTCs currently in use
@@ -37,6 +38,7 @@ struct rcar_du_group {
 	unsigned int index;
 
 	unsigned int channels_mask;
+	unsigned int cmms_mask;
 	unsigned int num_crtcs;
 	unsigned int use_count;
 	unsigned int used_crtcs;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 0d59f390de19..fcfd916227d1 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -17,7 +17,9 @@
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_vblank.h>
 
+#include <linux/device.h>
 #include <linux/of_graph.h>
+#include <linux/of_platform.h>
 #include <linux/wait.h>
 
 #include "rcar_du_crtc.h"
@@ -542,6 +544,7 @@ static int rcar_du_properties_init(struct rcar_du_device *rcdu)
 static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 {
 	const struct device_node *np = rcdu->dev->of_node;
+	const char *vsps_prop_name = "renesas,vsps";
 	struct of_phandle_args args;
 	struct {
 		struct device_node *np;
@@ -557,15 +560,21 @@ static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 	 * entry contains a pointer to the VSP DT node and a bitmask of the
 	 * connected DU CRTCs.
 	 */
-	cells = of_property_count_u32_elems(np, "vsps") / rcdu->num_crtcs - 1;
+	ret = of_property_count_u32_elems(np, vsps_prop_name);
+	if (ret < 0) {
+		/* Backward compatibility with old DTBs. */
+		vsps_prop_name = "vsps";
+		ret = of_property_count_u32_elems(np, vsps_prop_name);
+	}
+	cells = ret / rcdu->num_crtcs - 1;
 	if (cells > 1)
 		return -EINVAL;
 
 	for (i = 0; i < rcdu->num_crtcs; ++i) {
 		unsigned int j;
 
-		ret = of_parse_phandle_with_fixed_args(np, "vsps", cells, i,
-						       &args);
+		ret = of_parse_phandle_with_fixed_args(np, vsps_prop_name,
+						       cells, i, &args);
 		if (ret < 0)
 			goto error;
 
@@ -587,8 +596,8 @@ static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 
 		/*
 		 * Store the VSP pointer and pipe index in the CRTC. If the
-		 * second cell of the 'vsps' specifier isn't present, default
-		 * to 0 to remain compatible with older DT bindings.
+		 * second cell of the 'renesas,vsps' specifier isn't present,
+		 * default to 0 to remain compatible with older DT bindings.
 		 */
 		rcdu->crtcs[i].vsp = &rcdu->vsps[j];
 		rcdu->crtcs[i].vsp_pipe = cells >= 1 ? args.args[0] : 0;
@@ -618,6 +627,75 @@ error:
 	return ret;
 }
 
+static int rcar_du_cmm_init(struct rcar_du_device *rcdu)
+{
+	const struct device_node *np = rcdu->dev->of_node;
+	unsigned int i;
+	int cells;
+
+	cells = of_property_count_u32_elems(np, "renesas,cmms");
+	if (cells == -EINVAL)
+		return 0;
+
+	if (cells > rcdu->num_crtcs) {
+		dev_err(rcdu->dev,
+			"Invalid number of entries in 'renesas,cmms'\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < cells; ++i) {
+		struct platform_device *pdev;
+		struct device_link *link;
+		struct device_node *cmm;
+		int ret;
+
+		cmm = of_parse_phandle(np, "renesas,cmms", i);
+		if (IS_ERR(cmm)) {
+			dev_err(rcdu->dev,
+				"Failed to parse 'renesas,cmms' property\n");
+			return PTR_ERR(cmm);
+		}
+
+		if (!of_device_is_available(cmm)) {
+			/* It's fine to have a phandle to a non-enabled CMM. */
+			of_node_put(cmm);
+			continue;
+		}
+
+		pdev = of_find_device_by_node(cmm);
+		if (IS_ERR(pdev)) {
+			dev_err(rcdu->dev, "No device found for CMM%u\n", i);
+			of_node_put(cmm);
+			return PTR_ERR(pdev);
+		}
+
+		of_node_put(cmm);
+
+		/*
+		 * -ENODEV is used to report that the CMM config option is
+		 * disabled: return 0 and let the DU continue probing.
+		 */
+		ret = rcar_cmm_init(pdev);
+		if (ret)
+			return ret == -ENODEV ? 0 : ret;
+
+		/*
+		 * Enforce suspend/resume ordering by making the CMM a provider
+		 * of the DU: CMM is suspended after and resumed before the DU.
+		 */
+		link = device_link_add(rcdu->dev, &pdev->dev, DL_FLAG_STATELESS);
+		if (!link) {
+			dev_err(rcdu->dev,
+				"Failed to create device link to CMM%u\n", i);
+			return -EINVAL;
+		}
+
+		rcdu->cmms[i] = pdev;
+	}
+
+	return 0;
+}
+
 int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 {
 	static const unsigned int mmio_offsets[] = {
@@ -708,6 +786,11 @@ int rcar_du_modeset_init(struct rcar_du_device *rcdu)
 			return ret;
 	}
 
+	/* Initialize the Color Management Modules. */
+	ret = rcar_du_cmm_init(rcdu);
+	if (ret)
+		return ret;
+
 	/* Create the CRTCs. */
 	for (swindex = 0, hwindex = 0; swindex < rcdu->num_crtcs; ++hwindex) {
 		struct rcar_du_group *rgrp;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_regs.h b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
index bc87f080b170..fb9964949368 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_regs.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_regs.h
@@ -197,6 +197,11 @@
 #define DEFR6_MLOS1		(1 << 2)
 #define DEFR6_DEFAULT		(DEFR6_CODE | DEFR6_TCNE1)
 
+#define DEFR7			0x000ec
+#define DEFR7_CODE		(0x7779 << 16)
+#define DEFR7_CMME1		BIT(6)
+#define DEFR7_CMME0		BIT(4)
+
 /* -----------------------------------------------------------------------------
  * R8A7790-only Control Registers
  */
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 8c6c172bbf2e..8ffa4fbbdeb3 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -21,6 +21,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
+#include <drm/drm_of.h>
 #include <drm/drm_panel.h>
 #include <drm/drm_probe_helper.h>
 
@@ -36,6 +37,12 @@ enum rcar_lvds_mode {
 	RCAR_LVDS_MODE_VESA = 4,
 };
 
+enum rcar_lvds_link_type {
+	RCAR_LVDS_SINGLE_LINK = 0,
+	RCAR_LVDS_DUAL_LINK_EVEN_ODD_PIXELS = 1,
+	RCAR_LVDS_DUAL_LINK_ODD_EVEN_PIXELS = 2,
+};
+
 #define RCAR_LVDS_QUIRK_LANES		BIT(0)	/* LVDS lanes 1 and 3 inverted */
 #define RCAR_LVDS_QUIRK_GEN3_LVEN	BIT(1)	/* LVEN bit needs to be set on R8A77970/R8A7799x */
 #define RCAR_LVDS_QUIRK_PWD		BIT(2)	/* PWD bit available (all of Gen3 but E3) */
@@ -65,11 +72,8 @@ struct rcar_lvds {
 		struct clk *dotclkin[2];	/* External DU clocks */
 	} clocks;
 
-	struct drm_display_mode display_mode;
-	enum rcar_lvds_mode mode;
-
 	struct drm_bridge *companion;
-	bool dual_link;
+	enum rcar_lvds_link_type link_type;
 };
 
 #define bridge_to_rcar_lvds(b) \
@@ -91,7 +95,7 @@ static int rcar_lvds_connector_get_modes(struct drm_connector *connector)
 {
 	struct rcar_lvds *lvds = connector_to_rcar_lvds(connector);
 
-	return drm_panel_get_modes(lvds->panel);
+	return drm_panel_get_modes(lvds->panel, connector);
 }
 
 static int rcar_lvds_connector_atomic_check(struct drm_connector *connector,
@@ -402,10 +406,53 @@ EXPORT_SYMBOL_GPL(rcar_lvds_clk_disable);
  * Bridge
  */
 
-static void rcar_lvds_enable(struct drm_bridge *bridge)
+static enum rcar_lvds_mode rcar_lvds_get_lvds_mode(struct rcar_lvds *lvds,
+					const struct drm_connector *connector)
+{
+	const struct drm_display_info *info;
+	enum rcar_lvds_mode mode;
+
+	/*
+	 * There is no API yet to retrieve LVDS mode from a bridge, only panels
+	 * are supported.
+	 */
+	if (!lvds->panel)
+		return RCAR_LVDS_MODE_JEIDA;
+
+	info = &connector->display_info;
+	if (!info->num_bus_formats || !info->bus_formats) {
+		dev_warn(lvds->dev,
+			 "no LVDS bus format reported, using JEIDA\n");
+		return RCAR_LVDS_MODE_JEIDA;
+	}
+
+	switch (info->bus_formats[0]) {
+	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
+	case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
+		mode = RCAR_LVDS_MODE_JEIDA;
+		break;
+	case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
+		mode = RCAR_LVDS_MODE_VESA;
+		break;
+	default:
+		dev_warn(lvds->dev,
+			 "unsupported LVDS bus format 0x%04x, using JEIDA\n",
+			 info->bus_formats[0]);
+		return RCAR_LVDS_MODE_JEIDA;
+	}
+
+	if (info->bus_flags & DRM_BUS_FLAG_DATA_LSB_TO_MSB)
+		mode |= RCAR_LVDS_MODE_MIRROR;
+
+	return mode;
+}
+
+static void __rcar_lvds_atomic_enable(struct drm_bridge *bridge,
+				      struct drm_atomic_state *state,
+				      struct drm_crtc *crtc,
+				      struct drm_connector *connector)
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
-	const struct drm_display_mode *mode = &lvds->display_mode;
 	u32 lvdhcr;
 	u32 lvdcr0;
 	int ret;
@@ -415,8 +462,9 @@ static void rcar_lvds_enable(struct drm_bridge *bridge)
 		return;
 
 	/* Enable the companion LVDS encoder in dual-link mode. */
-	if (lvds->dual_link && lvds->companion)
-		lvds->companion->funcs->enable(lvds->companion);
+	if (lvds->link_type != RCAR_LVDS_SINGLE_LINK && lvds->companion)
+		__rcar_lvds_atomic_enable(lvds->companion, state, crtc,
+					  connector);
 
 	/*
 	 * Hardcode the channels and control signals routing for now.
@@ -440,30 +488,51 @@ static void rcar_lvds_enable(struct drm_bridge *bridge)
 	rcar_lvds_write(lvds, LVDCHCR, lvdhcr);
 
 	if (lvds->info->quirks & RCAR_LVDS_QUIRK_DUAL_LINK) {
-		/*
-		 * Configure vertical stripe based on the mode of operation of
-		 * the connected device.
-		 */
-		rcar_lvds_write(lvds, LVDSTRIPE,
-				lvds->dual_link ? LVDSTRIPE_ST_ON : 0);
+		u32 lvdstripe = 0;
+
+		if (lvds->link_type != RCAR_LVDS_SINGLE_LINK) {
+			/*
+			 * By default we generate even pixels from the primary
+			 * encoder and odd pixels from the companion encoder.
+			 * Swap pixels around if the sink requires odd pixels
+			 * from the primary encoder and even pixels from the
+			 * companion encoder.
+			 */
+			bool swap_pixels = lvds->link_type ==
+				RCAR_LVDS_DUAL_LINK_ODD_EVEN_PIXELS;
+
+			/*
+			 * Configure vertical stripe since we are dealing with
+			 * an LVDS dual-link connection.
+			 *
+			 * ST_SWAP is reserved for the companion encoder, only
+			 * set it in the primary encoder.
+			 */
+			lvdstripe = LVDSTRIPE_ST_ON
+				  | (lvds->companion && swap_pixels ?
+				     LVDSTRIPE_ST_SWAP : 0);
+		}
+		rcar_lvds_write(lvds, LVDSTRIPE, lvdstripe);
 	}
 
 	/*
 	 * PLL clock configuration on all instances but the companion in
 	 * dual-link mode.
 	 */
-	if (!lvds->dual_link || lvds->companion)
+	if (lvds->link_type == RCAR_LVDS_SINGLE_LINK || lvds->companion) {
+		const struct drm_crtc_state *crtc_state =
+			drm_atomic_get_new_crtc_state(state, crtc);
+		const struct drm_display_mode *mode =
+			&crtc_state->adjusted_mode;
+
 		lvds->info->pll_setup(lvds, mode->clock * 1000);
+	}
 
 	/* Set the LVDS mode and select the input. */
-	lvdcr0 = lvds->mode << LVDCR0_LVMD_SHIFT;
+	lvdcr0 = rcar_lvds_get_lvds_mode(lvds, connector) << LVDCR0_LVMD_SHIFT;
 
 	if (lvds->bridge.encoder) {
-		/*
-		 * FIXME: We should really retrieve the CRTC through the state,
-		 * but how do we get a state pointer?
-		 */
-		if (drm_crtc_index(lvds->bridge.encoder->crtc) == 2)
+		if (drm_crtc_index(crtc) == 2)
 			lvdcr0 |= LVDCR0_DUSEL;
 	}
 
@@ -520,7 +589,21 @@ static void rcar_lvds_enable(struct drm_bridge *bridge)
 	}
 }
 
-static void rcar_lvds_disable(struct drm_bridge *bridge)
+static void rcar_lvds_atomic_enable(struct drm_bridge *bridge,
+				    struct drm_atomic_state *state)
+{
+	struct drm_connector *connector;
+	struct drm_crtc *crtc;
+
+	connector = drm_atomic_get_new_connector_for_encoder(state,
+							     bridge->encoder);
+	crtc = drm_atomic_get_new_connector_state(state, connector)->crtc;
+
+	__rcar_lvds_atomic_enable(bridge, state, crtc, connector);
+}
+
+static void rcar_lvds_atomic_disable(struct drm_bridge *bridge,
+				     struct drm_atomic_state *state)
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
 
@@ -534,8 +617,8 @@ static void rcar_lvds_disable(struct drm_bridge *bridge)
 	rcar_lvds_write(lvds, LVDPLLCR, 0);
 
 	/* Disable the companion LVDS encoder in dual-link mode. */
-	if (lvds->dual_link && lvds->companion)
-		lvds->companion->funcs->disable(lvds->companion);
+	if (lvds->link_type != RCAR_LVDS_SINGLE_LINK && lvds->companion)
+		lvds->companion->funcs->atomic_disable(lvds->companion, state);
 
 	clk_disable_unprepare(lvds->clocks.mod);
 }
@@ -558,54 +641,6 @@ static bool rcar_lvds_mode_fixup(struct drm_bridge *bridge,
 	return true;
 }
 
-static void rcar_lvds_get_lvds_mode(struct rcar_lvds *lvds)
-{
-	struct drm_display_info *info = &lvds->connector.display_info;
-	enum rcar_lvds_mode mode;
-
-	/*
-	 * There is no API yet to retrieve LVDS mode from a bridge, only panels
-	 * are supported.
-	 */
-	if (!lvds->panel)
-		return;
-
-	if (!info->num_bus_formats || !info->bus_formats) {
-		dev_err(lvds->dev, "no LVDS bus format reported\n");
-		return;
-	}
-
-	switch (info->bus_formats[0]) {
-	case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
-	case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA:
-		mode = RCAR_LVDS_MODE_JEIDA;
-		break;
-	case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG:
-		mode = RCAR_LVDS_MODE_VESA;
-		break;
-	default:
-		dev_err(lvds->dev, "unsupported LVDS bus format 0x%04x\n",
-			info->bus_formats[0]);
-		return;
-	}
-
-	if (info->bus_flags & DRM_BUS_FLAG_DATA_LSB_TO_MSB)
-		mode |= RCAR_LVDS_MODE_MIRROR;
-
-	lvds->mode = mode;
-}
-
-static void rcar_lvds_mode_set(struct drm_bridge *bridge,
-			       const struct drm_display_mode *mode,
-			       const struct drm_display_mode *adjusted_mode)
-{
-	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
-
-	lvds->display_mode = *adjusted_mode;
-
-	rcar_lvds_get_lvds_mode(lvds);
-}
-
 static int rcar_lvds_attach(struct drm_bridge *bridge)
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
@@ -647,17 +682,16 @@ static void rcar_lvds_detach(struct drm_bridge *bridge)
 static const struct drm_bridge_funcs rcar_lvds_bridge_ops = {
 	.attach = rcar_lvds_attach,
 	.detach = rcar_lvds_detach,
-	.enable = rcar_lvds_enable,
-	.disable = rcar_lvds_disable,
+	.atomic_enable = rcar_lvds_atomic_enable,
+	.atomic_disable = rcar_lvds_atomic_disable,
 	.mode_fixup = rcar_lvds_mode_fixup,
-	.mode_set = rcar_lvds_mode_set,
 };
 
 bool rcar_lvds_dual_link(struct drm_bridge *bridge)
 {
 	struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge);
 
-	return lvds->dual_link;
+	return lvds->link_type != RCAR_LVDS_SINGLE_LINK;
 }
 EXPORT_SYMBOL_GPL(rcar_lvds_dual_link);
 
@@ -669,7 +703,10 @@ static int rcar_lvds_parse_dt_companion(struct rcar_lvds *lvds)
 {
 	const struct of_device_id *match;
 	struct device_node *companion;
+	struct device_node *port0, *port1;
+	struct rcar_lvds *companion_lvds;
 	struct device *dev = lvds->dev;
+	int dual_link;
 	int ret = 0;
 
 	/* Locate the companion LVDS encoder for dual-link operation, if any. */
@@ -688,13 +725,68 @@ static int rcar_lvds_parse_dt_companion(struct rcar_lvds *lvds)
 		goto done;
 	}
 
+	/*
+	 * We need to work out if the sink is expecting us to function in
+	 * dual-link mode. We do this by looking at the DT port nodes we are
+	 * connected to, if they are marked as expecting even pixels and
+	 * odd pixels than we need to enable vertical stripe output.
+	 */
+	port0 = of_graph_get_port_by_id(dev->of_node, 1);
+	port1 = of_graph_get_port_by_id(companion, 1);
+	dual_link = drm_of_lvds_get_dual_link_pixel_order(port0, port1);
+	of_node_put(port0);
+	of_node_put(port1);
+
+	switch (dual_link) {
+	case DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS:
+		lvds->link_type = RCAR_LVDS_DUAL_LINK_ODD_EVEN_PIXELS;
+		break;
+	case DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS:
+		lvds->link_type = RCAR_LVDS_DUAL_LINK_EVEN_ODD_PIXELS;
+		break;
+	default:
+		/*
+		 * Early dual-link bridge specific implementations populate the
+		 * timings field of drm_bridge. If the flag is set, we assume
+		 * that we are expected to generate even pixels from the primary
+		 * encoder, and odd pixels from the companion encoder.
+		 */
+		if (lvds->next_bridge && lvds->next_bridge->timings &&
+		    lvds->next_bridge->timings->dual_link)
+			lvds->link_type = RCAR_LVDS_DUAL_LINK_EVEN_ODD_PIXELS;
+		else
+			lvds->link_type = RCAR_LVDS_SINGLE_LINK;
+	}
+
+	if (lvds->link_type == RCAR_LVDS_SINGLE_LINK) {
+		dev_dbg(dev, "Single-link configuration detected\n");
+		goto done;
+	}
+
 	lvds->companion = of_drm_find_bridge(companion);
 	if (!lvds->companion) {
 		ret = -EPROBE_DEFER;
 		goto done;
 	}
 
-	dev_dbg(dev, "Found companion encoder %pOF\n", companion);
+	dev_dbg(dev,
+		"Dual-link configuration detected (companion encoder %pOF)\n",
+		companion);
+
+	if (lvds->link_type == RCAR_LVDS_DUAL_LINK_ODD_EVEN_PIXELS)
+		dev_dbg(dev, "Data swapping required\n");
+
+	/*
+	 * FIXME: We should not be messing with the companion encoder private
+	 * data from the primary encoder, we should rather let the companion
+	 * encoder work things out on its own. However, the companion encoder
+	 * doesn't hold a reference to the primary encoder, and
+	 * drm_of_lvds_get_dual_link_pixel_order needs to be given references
+	 * to the output ports of both encoders, therefore leave it like this
+	 * for the time being.
+	 */
+	companion_lvds = bridge_to_rcar_lvds(lvds->companion);
+	companion_lvds->link_type = lvds->link_type;
 
 done:
 	of_node_put(companion);
@@ -704,79 +796,17 @@ done:
 
 static int rcar_lvds_parse_dt(struct rcar_lvds *lvds)
 {
-	struct device_node *local_output = NULL;
-	struct device_node *remote_input = NULL;
-	struct device_node *remote = NULL;
-	struct device_node *node;
-	bool is_bridge = false;
-	int ret = 0;
-
-	local_output = of_graph_get_endpoint_by_regs(lvds->dev->of_node, 1, 0);
-	if (!local_output) {
-		dev_dbg(lvds->dev, "unconnected port@1\n");
-		ret = -ENODEV;
-		goto done;
-	}
-
-	/*
-	 * Locate the connected entity and infer its type from the number of
-	 * endpoints.
-	 */
-	remote = of_graph_get_remote_port_parent(local_output);
-	if (!remote) {
-		dev_dbg(lvds->dev, "unconnected endpoint %pOF\n", local_output);
-		ret = -ENODEV;
-		goto done;
-	}
+	int ret;
 
-	if (!of_device_is_available(remote)) {
-		dev_dbg(lvds->dev, "connected entity %pOF is disabled\n",
-			remote);
-		ret = -ENODEV;
+	ret = drm_of_find_panel_or_bridge(lvds->dev->of_node, 1, 0,
+					  &lvds->panel, &lvds->next_bridge);
+	if (ret)
 		goto done;
-	}
-
-	remote_input = of_graph_get_remote_endpoint(local_output);
 
-	for_each_endpoint_of_node(remote, node) {
-		if (node != remote_input) {
-			/*
-			 * We've found one endpoint other than the input, this
-			 * must be a bridge.
-			 */
-			is_bridge = true;
-			of_node_put(node);
-			break;
-		}
-	}
-
-	if (is_bridge) {
-		lvds->next_bridge = of_drm_find_bridge(remote);
-		if (!lvds->next_bridge) {
-			ret = -EPROBE_DEFER;
-			goto done;
-		}
-
-		if (lvds->info->quirks & RCAR_LVDS_QUIRK_DUAL_LINK)
-			lvds->dual_link = lvds->next_bridge->timings
-					? lvds->next_bridge->timings->dual_link
-					: false;
-	} else {
-		lvds->panel = of_drm_find_panel(remote);
-		if (IS_ERR(lvds->panel)) {
-			ret = PTR_ERR(lvds->panel);
-			goto done;
-		}
-	}
-
-	if (lvds->dual_link)
+	if (lvds->info->quirks & RCAR_LVDS_QUIRK_DUAL_LINK)
 		ret = rcar_lvds_parse_dt_companion(lvds);
 
 done:
-	of_node_put(local_output);
-	of_node_put(remote_input);
-	of_node_put(remote);
-
 	/*
 	 * On D3/E3 the LVDS encoder provides a clock to the DU, which can be
 	 * used for the DPAD output even when the LVDS output is not connected.
diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig
index 6f4222f8beeb..310aa1546893 100644
--- a/drivers/gpu/drm/rockchip/Kconfig
+++ b/drivers/gpu/drm/rockchip/Kconfig
@@ -28,17 +28,17 @@ config ROCKCHIP_ANALOGIX_DP
 	  on RK3288 or RK3399 based SoC, you should select this option.
 
 config ROCKCHIP_CDN_DP
-        bool "Rockchip cdn DP"
+	bool "Rockchip cdn DP"
 	depends on EXTCON=y || (EXTCON=m && DRM_ROCKCHIP=m)
-        help
+	help
 	  This selects support for Rockchip SoC specific extensions
 	  for the cdn DP driver. If you want to enable Dp on
 	  RK3399 based SoC, you should select this
 	  option.
 
 config ROCKCHIP_DW_HDMI
-        bool "Rockchip specific extensions for Synopsys DW HDMI"
-        help
+	bool "Rockchip specific extensions for Synopsys DW HDMI"
+	help
 	  This selects support for Rockchip SoC specific extensions
 	  for the Synopsys DesignWare HDMI driver. If you want to
 	  enable HDMI on RK3288 or RK3399 based SoC, you should select
@@ -46,6 +46,7 @@ config ROCKCHIP_DW_HDMI
 
 config ROCKCHIP_DW_MIPI_DSI
 	bool "Rockchip specific extensions for Synopsys DW MIPI DSI"
+	select GENERIC_PHY_MIPI_DPHY
 	help
 	  This selects support for Rockchip SoC specific extensions
 	  for the Synopsys DesignWare HDMI driver. If you want to
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
index bc073ec5c183..6e1270e45f97 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
@@ -12,6 +12,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 
@@ -139,6 +140,12 @@
 #define DW_MIPI_NEEDS_PHY_CFG_CLK	BIT(0)
 #define DW_MIPI_NEEDS_GRF_CLK		BIT(1)
 
+#define PX30_GRF_PD_VO_CON1		0x0438
+#define PX30_DSI_FORCETXSTOPMODE	(0xf << 7)
+#define PX30_DSI_FORCERXMODE		BIT(6)
+#define PX30_DSI_TURNDISABLE		BIT(5)
+#define PX30_DSI_LCDC_SEL		BIT(0)
+
 #define RK3288_GRF_SOC_CON6		0x025c
 #define RK3288_DSI0_LCDC_SEL		BIT(6)
 #define RK3288_DSI1_LCDC_SEL		BIT(9)
@@ -223,6 +230,10 @@ struct dw_mipi_dsi_rockchip {
 	bool is_slave;
 	struct dw_mipi_dsi_rockchip *slave;
 
+	/* optional external dphy */
+	struct phy *phy;
+	union phy_configure_opts phy_opts;
+
 	unsigned int lane_mbps; /* per lane */
 	u16 input_div;
 	u16 feedback_div;
@@ -359,6 +370,9 @@ static int dw_mipi_dsi_phy_init(void *priv_data)
 	struct dw_mipi_dsi_rockchip *dsi = priv_data;
 	int ret, i, vco;
 
+	if (dsi->phy)
+		return 0;
+
 	/*
 	 * Get vco from frequency(lane_mbps)
 	 * vco	frequency table
@@ -467,6 +481,28 @@ static int dw_mipi_dsi_phy_init(void *priv_data)
 	return ret;
 }
 
+static void dw_mipi_dsi_phy_power_on(void *priv_data)
+{
+	struct dw_mipi_dsi_rockchip *dsi = priv_data;
+	int ret;
+
+	ret = phy_set_mode(dsi->phy, PHY_MODE_MIPI_DPHY);
+	if (ret) {
+		DRM_DEV_ERROR(dsi->dev, "failed to set phy mode: %d\n", ret);
+		return;
+	}
+
+	phy_configure(dsi->phy, &dsi->phy_opts);
+	phy_power_on(dsi->phy);
+}
+
+static void dw_mipi_dsi_phy_power_off(void *priv_data)
+{
+	struct dw_mipi_dsi_rockchip *dsi = priv_data;
+
+	phy_power_off(dsi->phy);
+}
+
 static int
 dw_mipi_dsi_get_lane_mbps(void *priv_data, const struct drm_display_mode *mode,
 			  unsigned long mode_flags, u32 lanes, u32 format,
@@ -504,6 +540,17 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, const struct drm_display_mode *mode,
 				      "DPHY clock frequency is out of range\n");
 	}
 
+	/* for external phy only a the mipi_dphy_config is necessary */
+	if (dsi->phy) {
+		phy_mipi_dphy_get_default_config(mode->clock * 1000 * 10 / 8,
+						 bpp, lanes,
+						 &dsi->phy_opts.mipi_dphy);
+		dsi->lane_mbps = target_mbps;
+		*lane_mbps = dsi->lane_mbps;
+
+		return 0;
+	}
+
 	fin = clk_get_rate(dsi->pllref_clk);
 	fout = target_mbps * USEC_PER_SEC;
 
@@ -559,9 +606,89 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, const struct drm_display_mode *mode,
 	return 0;
 }
 
+struct hstt {
+	unsigned int maxfreq;
+	struct dw_mipi_dsi_dphy_timing timing;
+};
+
+#define HSTT(_maxfreq, _c_lp2hs, _c_hs2lp, _d_lp2hs, _d_hs2lp)	\
+{					\
+	.maxfreq = _maxfreq,		\
+	.timing = {			\
+		.clk_lp2hs = _c_lp2hs,	\
+		.clk_hs2lp = _c_hs2lp,	\
+		.data_lp2hs = _d_lp2hs,	\
+		.data_hs2lp = _d_hs2lp,	\
+	}				\
+}
+
+/* Table A-3 High-Speed Transition Times */
+struct hstt hstt_table[] = {
+	HSTT(  90,  32, 20,  26, 13),
+	HSTT( 100,  35, 23,  28, 14),
+	HSTT( 110,  32, 22,  26, 13),
+	HSTT( 130,  31, 20,  27, 13),
+	HSTT( 140,  33, 22,  26, 14),
+	HSTT( 150,  33, 21,  26, 14),
+	HSTT( 170,  32, 20,  27, 13),
+	HSTT( 180,  36, 23,  30, 15),
+	HSTT( 200,  40, 22,  33, 15),
+	HSTT( 220,  40, 22,  33, 15),
+	HSTT( 240,  44, 24,  36, 16),
+	HSTT( 250,  48, 24,  38, 17),
+	HSTT( 270,  48, 24,  38, 17),
+	HSTT( 300,  50, 27,  41, 18),
+	HSTT( 330,  56, 28,  45, 18),
+	HSTT( 360,  59, 28,  48, 19),
+	HSTT( 400,  61, 30,  50, 20),
+	HSTT( 450,  67, 31,  55, 21),
+	HSTT( 500,  73, 31,  59, 22),
+	HSTT( 550,  79, 36,  63, 24),
+	HSTT( 600,  83, 37,  68, 25),
+	HSTT( 650,  90, 38,  73, 27),
+	HSTT( 700,  95, 40,  77, 28),
+	HSTT( 750, 102, 40,  84, 28),
+	HSTT( 800, 106, 42,  87, 30),
+	HSTT( 850, 113, 44,  93, 31),
+	HSTT( 900, 118, 47,  98, 32),
+	HSTT( 950, 124, 47, 102, 34),
+	HSTT(1000, 130, 49, 107, 35),
+	HSTT(1050, 135, 51, 111, 37),
+	HSTT(1100, 139, 51, 114, 38),
+	HSTT(1150, 146, 54, 120, 40),
+	HSTT(1200, 153, 57, 125, 41),
+	HSTT(1250, 158, 58, 130, 42),
+	HSTT(1300, 163, 58, 135, 44),
+	HSTT(1350, 168, 60, 140, 45),
+	HSTT(1400, 172, 64, 144, 47),
+	HSTT(1450, 176, 65, 148, 48),
+	HSTT(1500, 181, 66, 153, 50)
+};
+
+static int
+dw_mipi_dsi_phy_get_timing(void *priv_data, unsigned int lane_mbps,
+			   struct dw_mipi_dsi_dphy_timing *timing)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hstt_table); i++)
+		if (lane_mbps < hstt_table[i].maxfreq)
+			break;
+
+	if (i == ARRAY_SIZE(hstt_table))
+		i--;
+
+	*timing = hstt_table[i].timing;
+
+	return 0;
+}
+
 static const struct dw_mipi_dsi_phy_ops dw_mipi_dsi_rockchip_phy_ops = {
 	.init = dw_mipi_dsi_phy_init,
+	.power_on = dw_mipi_dsi_phy_power_on,
+	.power_off = dw_mipi_dsi_phy_power_off,
 	.get_lane_mbps = dw_mipi_dsi_get_lane_mbps,
+	.get_timing = dw_mipi_dsi_phy_get_timing,
 };
 
 static void dw_mipi_dsi_rockchip_config(struct dw_mipi_dsi_rockchip *dsi,
@@ -916,16 +1043,33 @@ static int dw_mipi_dsi_rockchip_probe(struct platform_device *pdev)
 	}
 
 	if (!dsi->cdata) {
-		dev_err(dev, "no dsi-config for %s node\n", np->name);
+		DRM_DEV_ERROR(dev, "no dsi-config for %s node\n", np->name);
 		return -EINVAL;
 	}
 
+	/* try to get a possible external dphy */
+	dsi->phy = devm_phy_optional_get(dev, "dphy");
+	if (IS_ERR(dsi->phy)) {
+		ret = PTR_ERR(dsi->phy);
+		DRM_DEV_ERROR(dev, "failed to get mipi dphy: %d\n", ret);
+		return ret;
+	}
+
 	dsi->pllref_clk = devm_clk_get(dev, "ref");
 	if (IS_ERR(dsi->pllref_clk)) {
-		ret = PTR_ERR(dsi->pllref_clk);
-		DRM_DEV_ERROR(dev,
-			      "Unable to get pll reference clock: %d\n", ret);
-		return ret;
+		if (dsi->phy) {
+			/*
+			 * if external phy is present, pll will be
+			 * generated there.
+			 */
+			dsi->pllref_clk = NULL;
+		} else {
+			ret = PTR_ERR(dsi->pllref_clk);
+			DRM_DEV_ERROR(dev,
+				      "Unable to get pll reference clock: %d\n",
+				      ret);
+			return ret;
+		}
 	}
 
 	if (dsi->cdata->flags & DW_MIPI_NEEDS_PHY_CFG_CLK) {
@@ -989,6 +1133,24 @@ static int dw_mipi_dsi_rockchip_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct rockchip_dw_dsi_chip_data px30_chip_data[] = {
+	{
+		.reg = 0xff450000,
+		.lcdsel_grf_reg = PX30_GRF_PD_VO_CON1,
+		.lcdsel_big = HIWORD_UPDATE(0, PX30_DSI_LCDC_SEL),
+		.lcdsel_lit = HIWORD_UPDATE(PX30_DSI_LCDC_SEL,
+					    PX30_DSI_LCDC_SEL),
+
+		.lanecfg1_grf_reg = PX30_GRF_PD_VO_CON1,
+		.lanecfg1 = HIWORD_UPDATE(0, PX30_DSI_TURNDISABLE |
+					     PX30_DSI_FORCERXMODE |
+					     PX30_DSI_FORCETXSTOPMODE),
+
+		.max_data_lanes = 4,
+	},
+	{ /* sentinel */ }
+};
+
 static const struct rockchip_dw_dsi_chip_data rk3288_chip_data[] = {
 	{
 		.reg = 0xff960000,
@@ -1057,6 +1219,9 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = {
 
 static const struct of_device_id dw_mipi_dsi_rockchip_dt_ids[] = {
 	{
+	 .compatible = "rockchip,px30-mipi-dsi",
+	 .data = &px30_chip_data,
+	}, {
 	 .compatible = "rockchip,rk3288-mipi-dsi",
 	 .data = &rk3288_chip_data,
 	}, {
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index ed344a795b4d..e5864e823020 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -624,8 +624,10 @@ static int inno_hdmi_register(struct drm_device *drm, struct inno_hdmi *hdmi)
 
 	drm_connector_helper_add(&hdmi->connector,
 				 &inno_hdmi_connector_helper_funcs);
-	drm_connector_init(drm, &hdmi->connector, &inno_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(drm, &hdmi->connector,
+				    &inno_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    hdmi->ddc);
 
 	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
diff --git a/drivers/gpu/drm/rockchip/rk3066_hdmi.c b/drivers/gpu/drm/rockchip/rk3066_hdmi.c
index cdb401f4283d..fe203d38664e 100644
--- a/drivers/gpu/drm/rockchip/rk3066_hdmi.c
+++ b/drivers/gpu/drm/rockchip/rk3066_hdmi.c
@@ -564,9 +564,10 @@ rk3066_hdmi_register(struct drm_device *drm, struct rk3066_hdmi *hdmi)
 
 	drm_connector_helper_add(&hdmi->connector,
 				 &rk3066_hdmi_connector_helper_funcs);
-	drm_connector_init(drm, &hdmi->connector,
-			   &rk3066_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(drm, &hdmi->connector,
+				    &rk3066_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    hdmi->ddc);
 
 	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
@@ -640,6 +641,9 @@ static int rk3066_hdmi_i2c_write(struct rk3066_hdmi *hdmi, struct i2c_msg *msgs)
 	if (msgs->addr == DDC_ADDR)
 		hdmi->i2c->ddc_addr = msgs->buf[0];
 
+	/* Set edid fifo first address. */
+	hdmi_writeb(hdmi, HDMI_EDID_FIFO_ADDR, 0x00);
+
 	/* Set edid word address 0x00/0x80. */
 	hdmi_writeb(hdmi, HDMI_EDID_WORD_ADDR, hdmi->i2c->ddc_addr);
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index ca01234c037c..221e72e71432 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -53,64 +53,12 @@ rockchip_fb_alloc(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cm
 	return fb;
 }
 
-static struct drm_framebuffer *
-rockchip_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
-			const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	const struct drm_format_info *info = drm_get_format_info(dev,
-								 mode_cmd);
-	struct drm_framebuffer *fb;
-	struct drm_gem_object *objs[ROCKCHIP_MAX_FB_BUFFER];
-	struct drm_gem_object *obj;
-	int num_planes = min_t(int, info->num_planes, ROCKCHIP_MAX_FB_BUFFER);
-	int ret;
-	int i;
-
-	for (i = 0; i < num_planes; i++) {
-		unsigned int width = mode_cmd->width / (i ? info->hsub : 1);
-		unsigned int height = mode_cmd->height / (i ? info->vsub : 1);
-		unsigned int min_size;
-
-		obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]);
-		if (!obj) {
-			DRM_DEV_ERROR(dev->dev,
-				      "Failed to lookup GEM object\n");
-			ret = -ENXIO;
-			goto err_gem_object_unreference;
-		}
-
-		min_size = (height - 1) * mode_cmd->pitches[i] +
-			mode_cmd->offsets[i] +
-			width * info->cpp[i];
-
-		if (obj->size < min_size) {
-			drm_gem_object_put_unlocked(obj);
-			ret = -EINVAL;
-			goto err_gem_object_unreference;
-		}
-		objs[i] = obj;
-	}
-
-	fb = rockchip_fb_alloc(dev, mode_cmd, objs, i);
-	if (IS_ERR(fb)) {
-		ret = PTR_ERR(fb);
-		goto err_gem_object_unreference;
-	}
-
-	return fb;
-
-err_gem_object_unreference:
-	for (i--; i >= 0; i--)
-		drm_gem_object_put_unlocked(objs[i]);
-	return ERR_PTR(ret);
-}
-
 static const struct drm_mode_config_helper_funcs rockchip_mode_config_helpers = {
 	.atomic_commit_tail = drm_atomic_helper_commit_tail_rpm,
 };
 
 static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = {
-	.fb_create = rockchip_user_fb_create,
+	.fb_create = drm_gem_fb_create_with_dirty,
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c
index 02be6c5ff857..521fe42ac5e2 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fbdev.c
@@ -27,7 +27,7 @@ static int rockchip_fbdev_mmap(struct fb_info *info,
 	return rockchip_gem_mmap_buf(private->fbdev_bo, vma);
 }
 
-static struct fb_ops rockchip_drm_fbdev_ops = {
+static const struct fb_ops rockchip_drm_fbdev_ops = {
 	.owner		= THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_mmap	= rockchip_fbdev_mmap,
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index 8a4c9af0ba73..f25a36743cbd 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -10,6 +10,7 @@
 #include <linux/component.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_graph.h>
+#include <linux/phy/phy.h>
 #include <linux/pinctrl/devinfo.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -31,6 +32,8 @@
 #define DISPLAY_OUTPUT_LVDS		1
 #define DISPLAY_OUTPUT_DUAL_LVDS	2
 
+struct rockchip_lvds;
+
 #define connector_to_lvds(c) \
 		container_of(c, struct rockchip_lvds, connector)
 
@@ -39,16 +42,12 @@
 
 /**
  * rockchip_lvds_soc_data - rockchip lvds Soc private data
- * @ch1_offset: lvds channel 1 registe offset
- * grf_soc_con6: general registe offset for LVDS contrl
- * grf_soc_con7: general registe offset for LVDS contrl
- * has_vop_sel: to indicate whether need to choose from different VOP.
+ * @probe: LVDS platform probe function
+ * @helper_funcs: LVDS connector helper functions
  */
 struct rockchip_lvds_soc_data {
-	u32 ch1_offset;
-	int grf_soc_con6;
-	int grf_soc_con7;
-	bool has_vop_sel;
+	int (*probe)(struct platform_device *pdev, struct rockchip_lvds *lvds);
+	const struct drm_encoder_helper_funcs *helper_funcs;
 };
 
 struct rockchip_lvds {
@@ -56,6 +55,7 @@ struct rockchip_lvds {
 	void __iomem *regs;
 	struct regmap *grf;
 	struct clk *pclk;
+	struct phy *dphy;
 	const struct rockchip_lvds_soc_data *soc_data;
 	int output; /* rgb lvds or dual lvds output */
 	int format; /* vesa or jeida format */
@@ -67,15 +67,16 @@ struct rockchip_lvds {
 	struct dev_pin_info *pins;
 };
 
-static inline void lvds_writel(struct rockchip_lvds *lvds, u32 offset, u32 val)
+static inline void rk3288_writel(struct rockchip_lvds *lvds, u32 offset,
+				 u32 val)
 {
 	writel_relaxed(val, lvds->regs + offset);
 	if (lvds->output == DISPLAY_OUTPUT_LVDS)
 		return;
-	writel_relaxed(val, lvds->regs + offset + lvds->soc_data->ch1_offset);
+	writel_relaxed(val, lvds->regs + offset + RK3288_LVDS_CH1_OFFSET);
 }
 
-static inline int lvds_name_to_format(const char *s)
+static inline int rockchip_lvds_name_to_format(const char *s)
 {
 	if (strncmp(s, "jeida-18", 8) == 0)
 		return LVDS_JEIDA_18;
@@ -87,7 +88,7 @@ static inline int lvds_name_to_format(const char *s)
 	return -EINVAL;
 }
 
-static inline int lvds_name_to_output(const char *s)
+static inline int rockchip_lvds_name_to_output(const char *s)
 {
 	if (strncmp(s, "rgb", 3) == 0)
 		return DISPLAY_OUTPUT_RGB;
@@ -99,7 +100,41 @@ static inline int lvds_name_to_output(const char *s)
 	return -EINVAL;
 }
 
-static int rockchip_lvds_poweron(struct rockchip_lvds *lvds)
+static const struct drm_connector_funcs rockchip_lvds_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = drm_connector_cleanup,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int rockchip_lvds_connector_get_modes(struct drm_connector *connector)
+{
+	struct rockchip_lvds *lvds = connector_to_lvds(connector);
+	struct drm_panel *panel = lvds->panel;
+
+	return drm_panel_get_modes(panel, connector);
+}
+
+static const
+struct drm_connector_helper_funcs rockchip_lvds_connector_helper_funcs = {
+	.get_modes = rockchip_lvds_connector_get_modes,
+};
+
+static int
+rockchip_lvds_encoder_atomic_check(struct drm_encoder *encoder,
+				   struct drm_crtc_state *crtc_state,
+				   struct drm_connector_state *conn_state)
+{
+	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
+
+	s->output_mode = ROCKCHIP_OUT_MODE_P888;
+	s->output_type = DRM_MODE_CONNECTOR_LVDS;
+
+	return 0;
+}
+
+static int rk3288_lvds_poweron(struct rockchip_lvds *lvds)
 {
 	int ret;
 	u32 val;
@@ -121,66 +156,73 @@ static int rockchip_lvds_poweron(struct rockchip_lvds *lvds)
 	if (lvds->output == DISPLAY_OUTPUT_RGB) {
 		val |= RK3288_LVDS_CH0_REG0_TTL_EN |
 			RK3288_LVDS_CH0_REG0_LANECK_EN;
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG0, val);
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG2,
-			    RK3288_LVDS_PLL_FBDIV_REG2(0x46));
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG4,
-			    RK3288_LVDS_CH0_REG4_LANECK_TTL_MODE |
-			    RK3288_LVDS_CH0_REG4_LANE4_TTL_MODE |
-			    RK3288_LVDS_CH0_REG4_LANE3_TTL_MODE |
-			    RK3288_LVDS_CH0_REG4_LANE2_TTL_MODE |
-			    RK3288_LVDS_CH0_REG4_LANE1_TTL_MODE |
-			    RK3288_LVDS_CH0_REG4_LANE0_TTL_MODE);
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG5,
-			    RK3288_LVDS_CH0_REG5_LANECK_TTL_DATA |
-			    RK3288_LVDS_CH0_REG5_LANE4_TTL_DATA |
-			    RK3288_LVDS_CH0_REG5_LANE3_TTL_DATA |
-			    RK3288_LVDS_CH0_REG5_LANE2_TTL_DATA |
-			    RK3288_LVDS_CH0_REG5_LANE1_TTL_DATA |
-			    RK3288_LVDS_CH0_REG5_LANE0_TTL_DATA);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG0, val);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG2,
+			      RK3288_LVDS_PLL_FBDIV_REG2(0x46));
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG4,
+			      RK3288_LVDS_CH0_REG4_LANECK_TTL_MODE |
+			      RK3288_LVDS_CH0_REG4_LANE4_TTL_MODE |
+			      RK3288_LVDS_CH0_REG4_LANE3_TTL_MODE |
+			      RK3288_LVDS_CH0_REG4_LANE2_TTL_MODE |
+			      RK3288_LVDS_CH0_REG4_LANE1_TTL_MODE |
+			      RK3288_LVDS_CH0_REG4_LANE0_TTL_MODE);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG5,
+			      RK3288_LVDS_CH0_REG5_LANECK_TTL_DATA |
+			      RK3288_LVDS_CH0_REG5_LANE4_TTL_DATA |
+			      RK3288_LVDS_CH0_REG5_LANE3_TTL_DATA |
+			      RK3288_LVDS_CH0_REG5_LANE2_TTL_DATA |
+			      RK3288_LVDS_CH0_REG5_LANE1_TTL_DATA |
+			      RK3288_LVDS_CH0_REG5_LANE0_TTL_DATA);
 	} else {
 		val |= RK3288_LVDS_CH0_REG0_LVDS_EN |
 			    RK3288_LVDS_CH0_REG0_LANECK_EN;
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG0, val);
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG1,
-			    RK3288_LVDS_CH0_REG1_LANECK_BIAS |
-			    RK3288_LVDS_CH0_REG1_LANE4_BIAS |
-			    RK3288_LVDS_CH0_REG1_LANE3_BIAS |
-			    RK3288_LVDS_CH0_REG1_LANE2_BIAS |
-			    RK3288_LVDS_CH0_REG1_LANE1_BIAS |
-			    RK3288_LVDS_CH0_REG1_LANE0_BIAS);
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG2,
-			    RK3288_LVDS_CH0_REG2_RESERVE_ON |
-			    RK3288_LVDS_CH0_REG2_LANECK_LVDS_MODE |
-			    RK3288_LVDS_CH0_REG2_LANE4_LVDS_MODE |
-			    RK3288_LVDS_CH0_REG2_LANE3_LVDS_MODE |
-			    RK3288_LVDS_CH0_REG2_LANE2_LVDS_MODE |
-			    RK3288_LVDS_CH0_REG2_LANE1_LVDS_MODE |
-			    RK3288_LVDS_CH0_REG2_LANE0_LVDS_MODE |
-			    RK3288_LVDS_PLL_FBDIV_REG2(0x46));
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG4, 0x00);
-		lvds_writel(lvds, RK3288_LVDS_CH0_REG5, 0x00);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG0, val);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG1,
+			      RK3288_LVDS_CH0_REG1_LANECK_BIAS |
+			      RK3288_LVDS_CH0_REG1_LANE4_BIAS |
+			      RK3288_LVDS_CH0_REG1_LANE3_BIAS |
+			      RK3288_LVDS_CH0_REG1_LANE2_BIAS |
+			      RK3288_LVDS_CH0_REG1_LANE1_BIAS |
+			      RK3288_LVDS_CH0_REG1_LANE0_BIAS);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG2,
+			      RK3288_LVDS_CH0_REG2_RESERVE_ON |
+			      RK3288_LVDS_CH0_REG2_LANECK_LVDS_MODE |
+			      RK3288_LVDS_CH0_REG2_LANE4_LVDS_MODE |
+			      RK3288_LVDS_CH0_REG2_LANE3_LVDS_MODE |
+			      RK3288_LVDS_CH0_REG2_LANE2_LVDS_MODE |
+			      RK3288_LVDS_CH0_REG2_LANE1_LVDS_MODE |
+			      RK3288_LVDS_CH0_REG2_LANE0_LVDS_MODE |
+			      RK3288_LVDS_PLL_FBDIV_REG2(0x46));
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG4, 0x00);
+		rk3288_writel(lvds, RK3288_LVDS_CH0_REG5, 0x00);
 	}
-	lvds_writel(lvds, RK3288_LVDS_CH0_REG3, RK3288_LVDS_PLL_FBDIV_REG3(0x46));
-	lvds_writel(lvds, RK3288_LVDS_CH0_REGD, RK3288_LVDS_PLL_PREDIV_REGD(0x0a));
-	lvds_writel(lvds, RK3288_LVDS_CH0_REG20, RK3288_LVDS_CH0_REG20_LSB);
-
-	lvds_writel(lvds, RK3288_LVDS_CFG_REGC, RK3288_LVDS_CFG_REGC_PLL_ENABLE);
-	lvds_writel(lvds, RK3288_LVDS_CFG_REG21, RK3288_LVDS_CFG_REG21_TX_ENABLE);
+	rk3288_writel(lvds, RK3288_LVDS_CH0_REG3,
+		      RK3288_LVDS_PLL_FBDIV_REG3(0x46));
+	rk3288_writel(lvds, RK3288_LVDS_CH0_REGD,
+		      RK3288_LVDS_PLL_PREDIV_REGD(0x0a));
+	rk3288_writel(lvds, RK3288_LVDS_CH0_REG20,
+		      RK3288_LVDS_CH0_REG20_LSB);
+
+	rk3288_writel(lvds, RK3288_LVDS_CFG_REGC,
+		      RK3288_LVDS_CFG_REGC_PLL_ENABLE);
+	rk3288_writel(lvds, RK3288_LVDS_CFG_REG21,
+		      RK3288_LVDS_CFG_REG21_TX_ENABLE);
 
 	return 0;
 }
 
-static void rockchip_lvds_poweroff(struct rockchip_lvds *lvds)
+static void rk3288_lvds_poweroff(struct rockchip_lvds *lvds)
 {
 	int ret;
 	u32 val;
 
-	lvds_writel(lvds, RK3288_LVDS_CFG_REG21, RK3288_LVDS_CFG_REG21_TX_ENABLE);
-	lvds_writel(lvds, RK3288_LVDS_CFG_REGC, RK3288_LVDS_CFG_REGC_PLL_ENABLE);
+	rk3288_writel(lvds, RK3288_LVDS_CFG_REG21,
+		      RK3288_LVDS_CFG_REG21_TX_ENABLE);
+	rk3288_writel(lvds, RK3288_LVDS_CFG_REGC,
+		      RK3288_LVDS_CFG_REGC_PLL_ENABLE);
 	val = LVDS_DUAL | LVDS_TTL_EN | LVDS_CH0_EN | LVDS_CH1_EN | LVDS_PWRDN;
 	val |= val << 16;
-	ret = regmap_write(lvds->grf, lvds->soc_data->grf_soc_con7, val);
+	ret = regmap_write(lvds->grf, RK3288_LVDS_GRF_SOC_CON7, val);
 	if (ret != 0)
 		DRM_DEV_ERROR(lvds->dev, "Could not write to GRF: %d\n", ret);
 
@@ -188,29 +230,8 @@ static void rockchip_lvds_poweroff(struct rockchip_lvds *lvds)
 	clk_disable(lvds->pclk);
 }
 
-static const struct drm_connector_funcs rockchip_lvds_connector_funcs = {
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = drm_connector_cleanup,
-	.reset = drm_atomic_helper_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-static int rockchip_lvds_connector_get_modes(struct drm_connector *connector)
-{
-	struct rockchip_lvds *lvds = connector_to_lvds(connector);
-	struct drm_panel *panel = lvds->panel;
-
-	return drm_panel_get_modes(panel);
-}
-
-static const
-struct drm_connector_helper_funcs rockchip_lvds_connector_helper_funcs = {
-	.get_modes = rockchip_lvds_connector_get_modes,
-};
-
-static void rockchip_lvds_grf_config(struct drm_encoder *encoder,
-				     struct drm_display_mode *mode)
+static int rk3288_lvds_grf_config(struct drm_encoder *encoder,
+				  struct drm_display_mode *mode)
 {
 	struct rockchip_lvds *lvds = encoder_to_lvds(encoder);
 	u8 pin_hsync = (mode->flags & DRM_MODE_FLAG_PHSYNC) ? 1 : 0;
@@ -234,22 +255,19 @@ static void rockchip_lvds_grf_config(struct drm_encoder *encoder,
 
 	val |= (pin_dclk << 8) | (pin_hsync << 9);
 	val |= (0xffff << 16);
-	ret = regmap_write(lvds->grf, lvds->soc_data->grf_soc_con7, val);
-	if (ret != 0) {
+	ret = regmap_write(lvds->grf, RK3288_LVDS_GRF_SOC_CON7, val);
+	if (ret)
 		DRM_DEV_ERROR(lvds->dev, "Could not write to GRF: %d\n", ret);
-		return;
-	}
+
+	return ret;
 }
 
-static int rockchip_lvds_set_vop_source(struct rockchip_lvds *lvds,
-					struct drm_encoder *encoder)
+static int rk3288_lvds_set_vop_source(struct rockchip_lvds *lvds,
+				      struct drm_encoder *encoder)
 {
 	u32 val;
 	int ret;
 
-	if (!lvds->soc_data->has_vop_sel)
-		return 0;
-
 	ret = drm_of_encoder_active_endpoint_id(lvds->dev->of_node, encoder);
 	if (ret < 0)
 		return ret;
@@ -258,56 +276,162 @@ static int rockchip_lvds_set_vop_source(struct rockchip_lvds *lvds,
 	if (ret)
 		val |= RK3288_LVDS_SOC_CON6_SEL_VOP_LIT;
 
-	ret = regmap_write(lvds->grf, lvds->soc_data->grf_soc_con6, val);
+	ret = regmap_write(lvds->grf, RK3288_LVDS_GRF_SOC_CON6, val);
 	if (ret < 0)
 		return ret;
 
 	return 0;
 }
 
-static int
-rockchip_lvds_encoder_atomic_check(struct drm_encoder *encoder,
-				   struct drm_crtc_state *crtc_state,
-				   struct drm_connector_state *conn_state)
+static void rk3288_lvds_encoder_enable(struct drm_encoder *encoder)
 {
-	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
+	struct rockchip_lvds *lvds = encoder_to_lvds(encoder);
+	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
+	int ret;
 
-	s->output_mode = ROCKCHIP_OUT_MODE_P888;
-	s->output_type = DRM_MODE_CONNECTOR_LVDS;
+	drm_panel_prepare(lvds->panel);
 
-	return 0;
+	ret = rk3288_lvds_poweron(lvds);
+	if (ret < 0) {
+		DRM_DEV_ERROR(lvds->dev, "failed to power on LVDS: %d\n", ret);
+		drm_panel_unprepare(lvds->panel);
+		return;
+	}
+
+	ret = rk3288_lvds_grf_config(encoder, mode);
+	if (ret) {
+		DRM_DEV_ERROR(lvds->dev, "failed to configure LVDS: %d\n", ret);
+		drm_panel_unprepare(lvds->panel);
+		return;
+	}
+
+	ret = rk3288_lvds_set_vop_source(lvds, encoder);
+	if (ret) {
+		DRM_DEV_ERROR(lvds->dev, "failed to set VOP source: %d\n", ret);
+		drm_panel_unprepare(lvds->panel);
+		return;
+	}
+
+	drm_panel_enable(lvds->panel);
+}
+
+static void rk3288_lvds_encoder_disable(struct drm_encoder *encoder)
+{
+	struct rockchip_lvds *lvds = encoder_to_lvds(encoder);
+
+	drm_panel_disable(lvds->panel);
+	rk3288_lvds_poweroff(lvds);
+	drm_panel_unprepare(lvds->panel);
+}
+
+static int px30_lvds_poweron(struct rockchip_lvds *lvds)
+{
+	int ret;
+
+	ret = pm_runtime_get_sync(lvds->dev);
+	if (ret < 0) {
+		DRM_DEV_ERROR(lvds->dev, "failed to get pm runtime: %d\n", ret);
+		return ret;
+	}
+
+	/* Enable LVDS mode */
+	return regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1,
+				  PX30_LVDS_MODE_EN(1) | PX30_LVDS_P2S_EN(1),
+				  PX30_LVDS_MODE_EN(1) | PX30_LVDS_P2S_EN(1));
+}
+
+static void px30_lvds_poweroff(struct rockchip_lvds *lvds)
+{
+	regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1,
+			   PX30_LVDS_MODE_EN(1) | PX30_LVDS_P2S_EN(1),
+			   PX30_LVDS_MODE_EN(0) | PX30_LVDS_P2S_EN(0));
+
+	pm_runtime_put(lvds->dev);
+}
+
+static int px30_lvds_grf_config(struct drm_encoder *encoder,
+				struct drm_display_mode *mode)
+{
+	struct rockchip_lvds *lvds = encoder_to_lvds(encoder);
+
+	if (lvds->output != DISPLAY_OUTPUT_LVDS) {
+		DRM_DEV_ERROR(lvds->dev, "Unsupported display output %d\n",
+			      lvds->output);
+		return -EINVAL;
+	}
+
+	/* Set format */
+	return regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1,
+				  PX30_LVDS_FORMAT(lvds->format),
+				  PX30_LVDS_FORMAT(lvds->format));
+}
+
+static int px30_lvds_set_vop_source(struct rockchip_lvds *lvds,
+				    struct drm_encoder *encoder)
+{
+	int vop;
+
+	vop = drm_of_encoder_active_endpoint_id(lvds->dev->of_node, encoder);
+	if (vop < 0)
+		return vop;
+
+	return regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1,
+				  PX30_LVDS_VOP_SEL(1),
+				  PX30_LVDS_VOP_SEL(vop));
 }
 
-static void rockchip_lvds_encoder_enable(struct drm_encoder *encoder)
+static void px30_lvds_encoder_enable(struct drm_encoder *encoder)
 {
 	struct rockchip_lvds *lvds = encoder_to_lvds(encoder);
 	struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode;
 	int ret;
 
 	drm_panel_prepare(lvds->panel);
-	ret = rockchip_lvds_poweron(lvds);
-	if (ret < 0) {
-		DRM_DEV_ERROR(lvds->dev, "failed to power on lvds: %d\n", ret);
+
+	ret = px30_lvds_poweron(lvds);
+	if (ret) {
+		DRM_DEV_ERROR(lvds->dev, "failed to power on LVDS: %d\n", ret);
 		drm_panel_unprepare(lvds->panel);
+		return;
+	}
+
+	ret = px30_lvds_grf_config(encoder, mode);
+	if (ret) {
+		DRM_DEV_ERROR(lvds->dev, "failed to configure LVDS: %d\n", ret);
+		drm_panel_unprepare(lvds->panel);
+		return;
 	}
-	rockchip_lvds_grf_config(encoder, mode);
-	rockchip_lvds_set_vop_source(lvds, encoder);
+
+	ret = px30_lvds_set_vop_source(lvds, encoder);
+	if (ret) {
+		DRM_DEV_ERROR(lvds->dev, "failed to set VOP source: %d\n", ret);
+		drm_panel_unprepare(lvds->panel);
+		return;
+	}
+
 	drm_panel_enable(lvds->panel);
 }
 
-static void rockchip_lvds_encoder_disable(struct drm_encoder *encoder)
+static void px30_lvds_encoder_disable(struct drm_encoder *encoder)
 {
 	struct rockchip_lvds *lvds = encoder_to_lvds(encoder);
 
 	drm_panel_disable(lvds->panel);
-	rockchip_lvds_poweroff(lvds);
+	px30_lvds_poweroff(lvds);
 	drm_panel_unprepare(lvds->panel);
 }
 
 static const
-struct drm_encoder_helper_funcs rockchip_lvds_encoder_helper_funcs = {
-	.enable = rockchip_lvds_encoder_enable,
-	.disable = rockchip_lvds_encoder_disable,
+struct drm_encoder_helper_funcs rk3288_lvds_encoder_helper_funcs = {
+	.enable = rk3288_lvds_encoder_enable,
+	.disable = rk3288_lvds_encoder_disable,
+	.atomic_check = rockchip_lvds_encoder_atomic_check,
+};
+
+static const
+struct drm_encoder_helper_funcs px30_lvds_encoder_helper_funcs = {
+	.enable = px30_lvds_encoder_enable,
+	.disable = px30_lvds_encoder_disable,
 	.atomic_check = rockchip_lvds_encoder_atomic_check,
 };
 
@@ -315,11 +439,88 @@ static const struct drm_encoder_funcs rockchip_lvds_encoder_funcs = {
 	.destroy = drm_encoder_cleanup,
 };
 
+static int rk3288_lvds_probe(struct platform_device *pdev,
+			     struct rockchip_lvds *lvds)
+{
+	struct resource *res;
+	int ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	lvds->regs = devm_ioremap_resource(lvds->dev, res);
+	if (IS_ERR(lvds->regs))
+		return PTR_ERR(lvds->regs);
+
+	lvds->pclk = devm_clk_get(lvds->dev, "pclk_lvds");
+	if (IS_ERR(lvds->pclk)) {
+		DRM_DEV_ERROR(lvds->dev, "could not get pclk_lvds\n");
+		return PTR_ERR(lvds->pclk);
+	}
+
+	lvds->pins = devm_kzalloc(lvds->dev, sizeof(*lvds->pins),
+				  GFP_KERNEL);
+	if (!lvds->pins)
+		return -ENOMEM;
+
+	lvds->pins->p = devm_pinctrl_get(lvds->dev);
+	if (IS_ERR(lvds->pins->p)) {
+		DRM_DEV_ERROR(lvds->dev, "no pinctrl handle\n");
+		devm_kfree(lvds->dev, lvds->pins);
+		lvds->pins = NULL;
+	} else {
+		lvds->pins->default_state =
+			pinctrl_lookup_state(lvds->pins->p, "lcdc");
+		if (IS_ERR(lvds->pins->default_state)) {
+			DRM_DEV_ERROR(lvds->dev, "no default pinctrl state\n");
+			devm_kfree(lvds->dev, lvds->pins);
+			lvds->pins = NULL;
+		}
+	}
+
+	ret = clk_prepare(lvds->pclk);
+	if (ret < 0) {
+		DRM_DEV_ERROR(lvds->dev, "failed to prepare pclk_lvds\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int px30_lvds_probe(struct platform_device *pdev,
+			   struct rockchip_lvds *lvds)
+{
+	int ret;
+
+	/* MSB */
+	ret =  regmap_update_bits(lvds->grf, PX30_LVDS_GRF_PD_VO_CON1,
+				  PX30_LVDS_MSBSEL(1),
+				  PX30_LVDS_MSBSEL(1));
+	if (ret)
+		return ret;
+
+	/* PHY */
+	lvds->dphy = devm_phy_get(&pdev->dev, "dphy");
+	if (IS_ERR(lvds->dphy))
+		return PTR_ERR(lvds->dphy);
+
+	phy_init(lvds->dphy);
+	if (ret)
+		return ret;
+
+	phy_set_mode(lvds->dphy, PHY_MODE_LVDS);
+	if (ret)
+		return ret;
+
+	return phy_power_on(lvds->dphy);
+}
+
 static const struct rockchip_lvds_soc_data rk3288_lvds_data = {
-	.ch1_offset = 0x100,
-	.grf_soc_con6 = 0x025c,
-	.grf_soc_con7 = 0x0260,
-	.has_vop_sel = true,
+	.probe = rk3288_lvds_probe,
+	.helper_funcs = &rk3288_lvds_encoder_helper_funcs,
+};
+
+static const struct rockchip_lvds_soc_data px30_lvds_data = {
+	.probe = px30_lvds_probe,
+	.helper_funcs = &px30_lvds_encoder_helper_funcs,
 };
 
 static const struct of_device_id rockchip_lvds_dt_ids[] = {
@@ -327,6 +528,10 @@ static const struct of_device_id rockchip_lvds_dt_ids[] = {
 		.compatible = "rockchip,rk3288-lvds",
 		.data = &rk3288_lvds_data
 	},
+	{
+		.compatible = "rockchip,px30-lvds",
+		.data = &px30_lvds_data
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, rockchip_lvds_dt_ids);
@@ -378,7 +583,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		/* default set it as output rgb */
 		lvds->output = DISPLAY_OUTPUT_RGB;
 	else
-		lvds->output = lvds_name_to_output(name);
+		lvds->output = rockchip_lvds_name_to_output(name);
 
 	if (lvds->output < 0) {
 		DRM_DEV_ERROR(dev, "invalid output type [%s]\n", name);
@@ -390,7 +595,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		/* default set it as format vesa 18 */
 		lvds->format = LVDS_VESA_18;
 	else
-		lvds->format = lvds_name_to_format(name);
+		lvds->format = rockchip_lvds_name_to_format(name);
 
 	if (lvds->format < 0) {
 		DRM_DEV_ERROR(dev, "invalid data-mapping format [%s]\n", name);
@@ -410,7 +615,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		goto err_put_remote;
 	}
 
-	drm_encoder_helper_add(encoder, &rockchip_lvds_encoder_helper_funcs);
+	drm_encoder_helper_add(encoder, lvds->soc_data->helper_funcs);
 
 	if (lvds->panel) {
 		connector = &lvds->connector;
@@ -471,8 +676,10 @@ static void rockchip_lvds_unbind(struct device *dev, struct device *master,
 				void *data)
 {
 	struct rockchip_lvds *lvds = dev_get_drvdata(dev);
+	const struct drm_encoder_helper_funcs *encoder_funcs;
 
-	rockchip_lvds_encoder_disable(&lvds->encoder);
+	encoder_funcs = lvds->soc_data->helper_funcs;
+	encoder_funcs->disable(&lvds->encoder);
 	if (lvds->panel)
 		drm_panel_detach(lvds->panel);
 	pm_runtime_disable(dev);
@@ -490,7 +697,6 @@ static int rockchip_lvds_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct rockchip_lvds *lvds;
 	const struct of_device_id *match;
-	struct resource *res;
 	int ret;
 
 	if (!dev->of_node)
@@ -506,37 +712,6 @@ static int rockchip_lvds_probe(struct platform_device *pdev)
 		return -ENODEV;
 	lvds->soc_data = match->data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	lvds->regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(lvds->regs))
-		return PTR_ERR(lvds->regs);
-
-	lvds->pclk = devm_clk_get(&pdev->dev, "pclk_lvds");
-	if (IS_ERR(lvds->pclk)) {
-		DRM_DEV_ERROR(dev, "could not get pclk_lvds\n");
-		return PTR_ERR(lvds->pclk);
-	}
-
-	lvds->pins = devm_kzalloc(lvds->dev, sizeof(*lvds->pins),
-				  GFP_KERNEL);
-	if (!lvds->pins)
-		return -ENOMEM;
-
-	lvds->pins->p = devm_pinctrl_get(lvds->dev);
-	if (IS_ERR(lvds->pins->p)) {
-		DRM_DEV_ERROR(dev, "no pinctrl handle\n");
-		devm_kfree(lvds->dev, lvds->pins);
-		lvds->pins = NULL;
-	} else {
-		lvds->pins->default_state =
-			pinctrl_lookup_state(lvds->pins->p, "lcdc");
-		if (IS_ERR(lvds->pins->default_state)) {
-			DRM_DEV_ERROR(dev, "no default pinctrl state\n");
-			devm_kfree(lvds->dev, lvds->pins);
-			lvds->pins = NULL;
-		}
-	}
-
 	lvds->grf = syscon_regmap_lookup_by_phandle(dev->of_node,
 						    "rockchip,grf");
 	if (IS_ERR(lvds->grf)) {
@@ -544,13 +719,14 @@ static int rockchip_lvds_probe(struct platform_device *pdev)
 		return PTR_ERR(lvds->grf);
 	}
 
-	dev_set_drvdata(dev, lvds);
-
-	ret = clk_prepare(lvds->pclk);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev, "failed to prepare pclk_lvds\n");
+	ret = lvds->soc_data->probe(pdev, lvds);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "Platform initialization failed\n");
 		return ret;
 	}
+
+	dev_set_drvdata(dev, lvds);
+
 	ret = component_add(&pdev->dev, &rockchip_lvds_component_ops);
 	if (ret < 0) {
 		DRM_DEV_ERROR(dev, "failed to add component\n");
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.h b/drivers/gpu/drm/rockchip/rockchip_lvds.h
index 029bad8e1a14..4ce967d23813 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.h
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.h
@@ -70,7 +70,10 @@
 #define RK3288_LVDS_CFG_REG21			0x84
 #define RK3288_LVDS_CFG_REG21_TX_ENABLE		0x92
 #define RK3288_LVDS_CFG_REG21_TX_DISABLE	0x00
-#define RK3288_LVDS_CH1_OFFSET                 0x100
+#define RK3288_LVDS_CH1_OFFSET			0x100
+
+#define RK3288_LVDS_GRF_SOC_CON6		0x025C
+#define RK3288_LVDS_GRF_SOC_CON7		0x0260
 
 /* fbdiv value is split over 2 registers, with bit8 in reg2 */
 #define RK3288_LVDS_PLL_FBDIV_REG2(_fbd) \
@@ -103,4 +106,18 @@
 #define LVDS_VESA_18				2
 #define LVDS_JEIDA_18				3
 
+#define HIWORD_UPDATE(v, h, l)  ((GENMASK(h, l) << 16) | ((v) << (l)))
+
+#define PX30_LVDS_GRF_PD_VO_CON0		0x434
+#define   PX30_LVDS_TIE_CLKS(val)		HIWORD_UPDATE(val,  8,  8)
+#define   PX30_LVDS_INVERT_CLKS(val)		HIWORD_UPDATE(val,  9,  9)
+#define   PX30_LVDS_INVERT_DCLK(val)		HIWORD_UPDATE(val,  5,  5)
+
+#define PX30_LVDS_GRF_PD_VO_CON1		0x438
+#define   PX30_LVDS_FORMAT(val)			HIWORD_UPDATE(val, 14, 13)
+#define   PX30_LVDS_MODE_EN(val)		HIWORD_UPDATE(val, 12, 12)
+#define   PX30_LVDS_MSBSEL(val)			HIWORD_UPDATE(val, 11, 11)
+#define   PX30_LVDS_P2S_EN(val)			HIWORD_UPDATE(val,  6,  6)
+#define   PX30_LVDS_VOP_SEL(val)		HIWORD_UPDATE(val,  1,  1)
+
 #endif /* _ROCKCHIP_LVDS_ */
diff --git a/drivers/gpu/drm/savage/savage_drv.c b/drivers/gpu/drm/savage/savage_drv.c
index 2966fcfd9548..799bd11adb9c 100644
--- a/drivers/gpu/drm/savage/savage_drv.c
+++ b/drivers/gpu/drm/savage/savage_drv.c
@@ -24,10 +24,10 @@
  */
 
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 
 #include "savage_drv.h"
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 461a7a8129f4..ec79e8e5ad3c 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -38,46 +38,40 @@
  * submit to HW ring.
  *
  * @entity: scheduler entity to init
- * @rq_list: the list of run queue on which jobs from this
+ * @priority: priority of the entity
+ * @sched_list: the list of drm scheds on which jobs from this
  *           entity can be submitted
- * @num_rq_list: number of run queue in rq_list
+ * @num_sched_list: number of drm sched in sched_list
  * @guilty: atomic_t set to 1 when a job on this queue
  *          is found to be guilty causing a timeout
  *
- * Note: the rq_list should have atleast one element to schedule
+ * Note: the sched_list should have atleast one element to schedule
  *       the entity
  *
  * Returns 0 on success or a negative error code on failure.
  */
 int drm_sched_entity_init(struct drm_sched_entity *entity,
-			  struct drm_sched_rq **rq_list,
-			  unsigned int num_rq_list,
+			  enum drm_sched_priority priority,
+			  struct drm_gpu_scheduler **sched_list,
+			  unsigned int num_sched_list,
 			  atomic_t *guilty)
 {
-	int i;
-
-	if (!(entity && rq_list && (num_rq_list == 0 || rq_list[0])))
+	if (!(entity && sched_list && (num_sched_list == 0 || sched_list[0])))
 		return -EINVAL;
 
 	memset(entity, 0, sizeof(struct drm_sched_entity));
 	INIT_LIST_HEAD(&entity->list);
 	entity->rq = NULL;
 	entity->guilty = guilty;
-	entity->num_rq_list = num_rq_list;
-	entity->rq_list = kcalloc(num_rq_list, sizeof(struct drm_sched_rq *),
-				GFP_KERNEL);
-	if (!entity->rq_list)
-		return -ENOMEM;
-
-	init_completion(&entity->entity_idle);
-
-	for (i = 0; i < num_rq_list; ++i)
-		entity->rq_list[i] = rq_list[i];
+	entity->num_sched_list = num_sched_list;
+	entity->priority = priority;
+	entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
+	entity->last_scheduled = NULL;
 
-	if (num_rq_list)
-		entity->rq = rq_list[0];
+	if(num_sched_list)
+		entity->rq = &sched_list[0]->sched_rq[entity->priority];
 
-	entity->last_scheduled = NULL;
+	init_completion(&entity->entity_idle);
 
 	spin_lock_init(&entity->rq_lock);
 	spsc_queue_init(&entity->job_queue);
@@ -136,21 +130,21 @@ static struct drm_sched_rq *
 drm_sched_entity_get_free_sched(struct drm_sched_entity *entity)
 {
 	struct drm_sched_rq *rq = NULL;
-	unsigned int min_jobs = UINT_MAX, num_jobs;
+	unsigned int min_score = UINT_MAX, num_score;
 	int i;
 
-	for (i = 0; i < entity->num_rq_list; ++i) {
-		struct drm_gpu_scheduler *sched = entity->rq_list[i]->sched;
+	for (i = 0; i < entity->num_sched_list; ++i) {
+		struct drm_gpu_scheduler *sched = entity->sched_list[i];
 
-		if (!entity->rq_list[i]->sched->ready) {
+		if (!entity->sched_list[i]->ready) {
 			DRM_WARN("sched%s is not ready, skipping", sched->name);
 			continue;
 		}
 
-		num_jobs = atomic_read(&sched->num_jobs);
-		if (num_jobs < min_jobs) {
-			min_jobs = num_jobs;
-			rq = entity->rq_list[i];
+		num_score = atomic_read(&sched->score);
+		if (num_score < min_score) {
+			min_score = num_score;
+			rq = &entity->sched_list[i]->sched_rq[entity->priority];
 		}
 	}
 
@@ -308,7 +302,6 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
 
 	dma_fence_put(entity->last_scheduled);
 	entity->last_scheduled = NULL;
-	kfree(entity->rq_list);
 }
 EXPORT_SYMBOL(drm_sched_entity_fini);
 
@@ -354,15 +347,6 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
 }
 
 /**
- * drm_sched_entity_set_rq_priority - helper for drm_sched_entity_set_priority
- */
-static void drm_sched_entity_set_rq_priority(struct drm_sched_rq **rq,
-					     enum drm_sched_priority priority)
-{
-	*rq = &(*rq)->sched->sched_rq[priority];
-}
-
-/**
  * drm_sched_entity_set_priority - Sets priority of the entity
  *
  * @entity: scheduler entity
@@ -373,19 +357,8 @@ static void drm_sched_entity_set_rq_priority(struct drm_sched_rq **rq,
 void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
 				   enum drm_sched_priority priority)
 {
-	unsigned int i;
-
 	spin_lock(&entity->rq_lock);
-
-	for (i = 0; i < entity->num_rq_list; ++i)
-		drm_sched_entity_set_rq_priority(&entity->rq_list[i], priority);
-
-	if (entity->rq) {
-		drm_sched_rq_remove_entity(entity->rq, entity);
-		drm_sched_entity_set_rq_priority(&entity->rq, priority);
-		drm_sched_rq_add_entity(entity->rq, entity);
-	}
-
+	entity->priority = priority;
 	spin_unlock(&entity->rq_lock);
 }
 EXPORT_SYMBOL(drm_sched_entity_set_priority);
@@ -490,20 +463,20 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 	struct dma_fence *fence;
 	struct drm_sched_rq *rq;
 
-	if (spsc_queue_count(&entity->job_queue) || entity->num_rq_list <= 1)
+	if (spsc_queue_count(&entity->job_queue) || entity->num_sched_list <= 1)
 		return;
 
 	fence = READ_ONCE(entity->last_scheduled);
 	if (fence && !dma_fence_is_signaled(fence))
 		return;
 
+	spin_lock(&entity->rq_lock);
 	rq = drm_sched_entity_get_free_sched(entity);
-	if (rq == entity->rq)
-		return;
+	if (rq != entity->rq) {
+		drm_sched_rq_remove_entity(entity->rq, entity);
+		entity->rq = rq;
+	}
 
-	spin_lock(&entity->rq_lock);
-	drm_sched_rq_remove_entity(entity->rq, entity);
-	entity->rq = rq;
 	spin_unlock(&entity->rq_lock);
 }
 
@@ -525,7 +498,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 	bool first;
 
 	trace_drm_sched_job(sched_job, entity);
-	atomic_inc(&entity->rq->sched->num_jobs);
+	atomic_inc(&entity->rq->sched->score);
 	WRITE_ONCE(entity->last_user, current->group_leader);
 	first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
 
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 3c57e84222ca..71ce6215956f 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -92,6 +92,7 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 	if (!list_empty(&entity->list))
 		return;
 	spin_lock(&rq->lock);
+	atomic_inc(&rq->sched->score);
 	list_add_tail(&entity->list, &rq->entities);
 	spin_unlock(&rq->lock);
 }
@@ -110,6 +111,7 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 	if (list_empty(&entity->list))
 		return;
 	spin_lock(&rq->lock);
+	atomic_dec(&rq->sched->score);
 	list_del_init(&entity->list);
 	if (rq->current_entity == entity)
 		rq->current_entity = NULL;
@@ -287,10 +289,21 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	unsigned long flags;
 
 	sched = container_of(work, struct drm_gpu_scheduler, work_tdr.work);
+
+	/* Protects against concurrent deletion in drm_sched_get_cleanup_job */
+	spin_lock_irqsave(&sched->job_list_lock, flags);
 	job = list_first_entry_or_null(&sched->ring_mirror_list,
 				       struct drm_sched_job, node);
 
 	if (job) {
+		/*
+		 * Remove the bad job so it cannot be freed by concurrent
+		 * drm_sched_cleanup_jobs. It will be reinserted back after sched->thread
+		 * is parked at which point it's safe.
+		 */
+		list_del_init(&job->node);
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
 		job->sched->ops->timedout_job(job);
 
 		/*
@@ -301,6 +314,8 @@ static void drm_sched_job_timedout(struct work_struct *work)
 			job->sched->ops->free_job(job);
 			sched->free_guilty = false;
 		}
+	} else {
+		spin_unlock_irqrestore(&sched->job_list_lock, flags);
 	}
 
 	spin_lock_irqsave(&sched->job_list_lock, flags);
@@ -373,6 +388,20 @@ void drm_sched_stop(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 	kthread_park(sched->thread);
 
 	/*
+	 * Reinsert back the bad job here - now it's safe as
+	 * drm_sched_get_cleanup_job cannot race against us and release the
+	 * bad job at this point - we parked (waited for) any in progress
+	 * (earlier) cleanups and drm_sched_get_cleanup_job will not be called
+	 * now until the scheduler thread is unparked.
+	 */
+	if (bad && bad->sched == sched)
+		/*
+		 * Add at the head of the queue to reflect it was the earliest
+		 * job extracted.
+		 */
+		list_add(&bad->node, &sched->ring_mirror_list);
+
+	/*
 	 * Iterate the job list from later to  earlier one and either deactive
 	 * their HW callbacks or remove them from mirror list if they already
 	 * signaled.
@@ -628,7 +657,7 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 	struct drm_gpu_scheduler *sched = s_fence->sched;
 
 	atomic_dec(&sched->hw_rq_count);
-	atomic_dec(&sched->num_jobs);
+	atomic_dec(&sched->score);
 
 	trace_drm_sched_process_job(s_fence);
 
@@ -803,7 +832,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	spin_lock_init(&sched->job_list_lock);
 	atomic_set(&sched->hw_rq_count, 0);
 	INIT_DELAYED_WORK(&sched->work_tdr, drm_sched_job_timedout);
-	atomic_set(&sched->num_jobs, 0);
+	atomic_set(&sched->score, 0);
 	atomic64_set(&sched->job_id_count, 0);
 
 	/* Each scheduler will run on a seperate kernel thread */
diff --git a/drivers/gpu/drm/selftests/Makefile b/drivers/gpu/drm/selftests/Makefile
index d2137342b371..0856e4b12f70 100644
--- a/drivers/gpu/drm/selftests/Makefile
+++ b/drivers/gpu/drm/selftests/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 test-drm_modeset-y := test-drm_modeset_common.o test-drm_plane_helper.o \
                       test-drm_format.o test-drm_framebuffer.o \
-		      test-drm_damage_helper.o test-drm_dp_mst_helper.o
+		      test-drm_damage_helper.o test-drm_dp_mst_helper.o \
+		      test-drm_rect.o
 
 obj-$(CONFIG_DRM_DEBUG_SELFTEST) += test-drm_mm.o test-drm_modeset.o test-drm_cmdline_parser.o
diff --git a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
index 6d61a0eb5d64..ceac7af9a172 100644
--- a/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_cmdline_selftests.h
@@ -60,3 +60,8 @@ cmdline_test(drm_cmdline_test_vmirror)
 cmdline_test(drm_cmdline_test_margin_options)
 cmdline_test(drm_cmdline_test_multiple_options)
 cmdline_test(drm_cmdline_test_invalid_option)
+cmdline_test(drm_cmdline_test_bpp_extra_and_option)
+cmdline_test(drm_cmdline_test_extra_and_option)
+cmdline_test(drm_cmdline_test_freestanding_options)
+cmdline_test(drm_cmdline_test_freestanding_force_e_and_options)
+cmdline_test(drm_cmdline_test_panel_orientation)
diff --git a/drivers/gpu/drm/selftests/drm_modeset_selftests.h b/drivers/gpu/drm/selftests/drm_modeset_selftests.h
index 1898de0b4a4d..782e285ca383 100644
--- a/drivers/gpu/drm/selftests/drm_modeset_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_modeset_selftests.h
@@ -6,6 +6,10 @@
  *
  * Tests are executed in order by igt/drm_selftests_helper
  */
+selftest(drm_rect_clip_scaled_div_by_zero, igt_drm_rect_clip_scaled_div_by_zero)
+selftest(drm_rect_clip_scaled_not_clipped, igt_drm_rect_clip_scaled_not_clipped)
+selftest(drm_rect_clip_scaled_clipped, igt_drm_rect_clip_scaled_clipped)
+selftest(drm_rect_clip_scaled_signed_vs_unsigned, igt_drm_rect_clip_scaled_signed_vs_unsigned)
 selftest(check_plane_state, igt_check_plane_state)
 selftest(check_drm_format_block_width, igt_check_drm_format_block_width)
 selftest(check_drm_format_block_height, igt_check_drm_format_block_height)
diff --git a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
index 013de9d27c35..520f3e66a384 100644
--- a/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
+++ b/drivers/gpu/drm/selftests/test-drm_cmdline_parser.c
@@ -992,6 +992,128 @@ static int drm_cmdline_test_invalid_option(void *ignored)
 	return 0;
 }
 
+static int drm_cmdline_test_bpp_extra_and_option(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(!drm_mode_parse_command_line_for_connector("720x480-24e,rotate=180",
+							   &no_connector,
+							   &mode));
+	FAIL_ON(!mode.specified);
+	FAIL_ON(mode.xres != 720);
+	FAIL_ON(mode.yres != 480);
+	FAIL_ON(mode.rotation_reflection != DRM_MODE_ROTATE_180);
+
+	FAIL_ON(mode.refresh_specified);
+
+	FAIL_ON(!mode.bpp_specified);
+	FAIL_ON(mode.bpp != 24);
+
+	FAIL_ON(mode.rb);
+	FAIL_ON(mode.cvt);
+	FAIL_ON(mode.interlace);
+	FAIL_ON(mode.margins);
+	FAIL_ON(mode.force != DRM_FORCE_ON);
+
+	return 0;
+}
+
+static int drm_cmdline_test_extra_and_option(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(!drm_mode_parse_command_line_for_connector("720x480e,rotate=180",
+							   &no_connector,
+							   &mode));
+	FAIL_ON(!mode.specified);
+	FAIL_ON(mode.xres != 720);
+	FAIL_ON(mode.yres != 480);
+	FAIL_ON(mode.rotation_reflection != DRM_MODE_ROTATE_180);
+
+	FAIL_ON(mode.refresh_specified);
+	FAIL_ON(mode.bpp_specified);
+
+	FAIL_ON(mode.rb);
+	FAIL_ON(mode.cvt);
+	FAIL_ON(mode.interlace);
+	FAIL_ON(mode.margins);
+	FAIL_ON(mode.force != DRM_FORCE_ON);
+
+	return 0;
+}
+
+static int drm_cmdline_test_freestanding_options(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(!drm_mode_parse_command_line_for_connector("margin_right=14,margin_left=24,margin_bottom=36,margin_top=42",
+							   &no_connector,
+							   &mode));
+	FAIL_ON(mode.specified);
+	FAIL_ON(mode.refresh_specified);
+	FAIL_ON(mode.bpp_specified);
+
+	FAIL_ON(mode.tv_margins.right != 14);
+	FAIL_ON(mode.tv_margins.left != 24);
+	FAIL_ON(mode.tv_margins.bottom != 36);
+	FAIL_ON(mode.tv_margins.top != 42);
+
+	FAIL_ON(mode.rb);
+	FAIL_ON(mode.cvt);
+	FAIL_ON(mode.interlace);
+	FAIL_ON(mode.margins);
+	FAIL_ON(mode.force != DRM_FORCE_UNSPECIFIED);
+
+	return 0;
+}
+
+static int drm_cmdline_test_freestanding_force_e_and_options(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(!drm_mode_parse_command_line_for_connector("e,margin_right=14,margin_left=24,margin_bottom=36,margin_top=42",
+							   &no_connector,
+							   &mode));
+	FAIL_ON(mode.specified);
+	FAIL_ON(mode.refresh_specified);
+	FAIL_ON(mode.bpp_specified);
+
+	FAIL_ON(mode.tv_margins.right != 14);
+	FAIL_ON(mode.tv_margins.left != 24);
+	FAIL_ON(mode.tv_margins.bottom != 36);
+	FAIL_ON(mode.tv_margins.top != 42);
+
+	FAIL_ON(mode.rb);
+	FAIL_ON(mode.cvt);
+	FAIL_ON(mode.interlace);
+	FAIL_ON(mode.margins);
+	FAIL_ON(mode.force != DRM_FORCE_ON);
+
+	return 0;
+}
+
+static int drm_cmdline_test_panel_orientation(void *ignored)
+{
+	struct drm_cmdline_mode mode = { };
+
+	FAIL_ON(!drm_mode_parse_command_line_for_connector("panel_orientation=upside_down",
+							   &no_connector,
+							   &mode));
+	FAIL_ON(mode.specified);
+	FAIL_ON(mode.refresh_specified);
+	FAIL_ON(mode.bpp_specified);
+
+	FAIL_ON(mode.panel_orientation != DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP);
+
+	FAIL_ON(mode.rb);
+	FAIL_ON(mode.cvt);
+	FAIL_ON(mode.interlace);
+	FAIL_ON(mode.margins);
+	FAIL_ON(mode.force != DRM_FORCE_UNSPECIFIED);
+
+	return 0;
+}
+
 #include "drm_selftest.c"
 
 static int __init test_drm_cmdline_init(void)
diff --git a/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c b/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c
index af2b2de65316..bd990d178765 100644
--- a/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c
+++ b/drivers/gpu/drm/selftests/test-drm_dp_mst_helper.c
@@ -18,15 +18,19 @@ int igt_dp_mst_calc_pbn_mode(void *ignored)
 		int rate;
 		int bpp;
 		int expected;
+		bool dsc;
 	} test_params[] = {
-		{ 154000, 30, 689 },
-		{ 234000, 30, 1047 },
-		{ 297000, 24, 1063 },
+		{ 154000, 30, 689, false },
+		{ 234000, 30, 1047, false },
+		{ 297000, 24, 1063, false },
+		{ 332880, 24, 50, true },
+		{ 324540, 24, 49, true },
 	};
 
 	for (i = 0; i < ARRAY_SIZE(test_params); i++) {
 		pbn = drm_dp_calc_pbn_mode(test_params[i].rate,
-					   test_params[i].bpp);
+					   test_params[i].bpp,
+					   test_params[i].dsc);
 		FAIL(pbn != test_params[i].expected,
 		     "Expected PBN %d for clock %d bpp %d, got %d\n",
 		     test_params[i].expected, test_params[i].rate,
diff --git a/drivers/gpu/drm/selftests/test-drm_modeset_common.h b/drivers/gpu/drm/selftests/test-drm_modeset_common.h
index 0fcb8bbc6a1b..cfb51d8da2bc 100644
--- a/drivers/gpu/drm/selftests/test-drm_modeset_common.h
+++ b/drivers/gpu/drm/selftests/test-drm_modeset_common.h
@@ -3,6 +3,9 @@
 #ifndef __TEST_DRM_MODESET_COMMON_H__
 #define __TEST_DRM_MODESET_COMMON_H__
 
+#include <linux/errno.h>
+#include <linux/printk.h>
+
 #define FAIL(test, msg, ...) \
 	do { \
 		if (test) { \
@@ -13,6 +16,10 @@
 
 #define FAIL_ON(x) FAIL((x), "%s", "FAIL_ON(" __stringify(x) ")\n")
 
+int igt_drm_rect_clip_scaled_div_by_zero(void *ignored);
+int igt_drm_rect_clip_scaled_not_clipped(void *ignored);
+int igt_drm_rect_clip_scaled_clipped(void *ignored);
+int igt_drm_rect_clip_scaled_signed_vs_unsigned(void *ignored);
 int igt_check_plane_state(void *ignored);
 int igt_check_drm_format_block_width(void *ignored);
 int igt_check_drm_format_block_height(void *ignored);
diff --git a/drivers/gpu/drm/selftests/test-drm_rect.c b/drivers/gpu/drm/selftests/test-drm_rect.c
new file mode 100644
index 000000000000..3a5ff38321f4
--- /dev/null
+++ b/drivers/gpu/drm/selftests/test-drm_rect.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test cases for the drm_rect functions
+ */
+
+#define pr_fmt(fmt) "drm_rect: " fmt
+
+#include <linux/limits.h>
+
+#include <drm/drm_rect.h>
+
+#include "test-drm_modeset_common.h"
+
+int igt_drm_rect_clip_scaled_div_by_zero(void *ignored)
+{
+	struct drm_rect src, dst, clip;
+	bool visible;
+
+	/*
+	 * Make sure we don't divide by zero when dst
+	 * width/height is zero and dst and clip do not intersect.
+	 */
+	drm_rect_init(&src, 0, 0, 0, 0);
+	drm_rect_init(&dst, 0, 0, 0, 0);
+	drm_rect_init(&clip, 1, 1, 1, 1);
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+	FAIL(visible, "Destination not be visible\n");
+	FAIL(drm_rect_visible(&src), "Source should not be visible\n");
+
+	drm_rect_init(&src, 0, 0, 0, 0);
+	drm_rect_init(&dst, 3, 3, 0, 0);
+	drm_rect_init(&clip, 1, 1, 1, 1);
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+	FAIL(visible, "Destination not be visible\n");
+	FAIL(drm_rect_visible(&src), "Source should not be visible\n");
+
+	return 0;
+}
+
+int igt_drm_rect_clip_scaled_not_clipped(void *ignored)
+{
+	struct drm_rect src, dst, clip;
+	bool visible;
+
+	/* 1:1 scaling */
+	drm_rect_init(&src, 0, 0, 1 << 16, 1 << 16);
+	drm_rect_init(&dst, 0, 0, 1, 1);
+	drm_rect_init(&clip, 0, 0, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 0 || src.x2 != 1 << 16 ||
+	     src.y1 != 0 || src.y2 != 1 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 0 || dst.x2 != 1 ||
+	     dst.y1 != 0 || dst.y2 != 1,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 2:1 scaling */
+	drm_rect_init(&src, 0, 0, 2 << 16, 2 << 16);
+	drm_rect_init(&dst, 0, 0, 1, 1);
+	drm_rect_init(&clip, 0, 0, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 0 || src.x2 != 2 << 16 ||
+	     src.y1 != 0 || src.y2 != 2 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 0 || dst.x2 != 1 ||
+	     dst.y1 != 0 || dst.y2 != 1,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 1:2 scaling */
+	drm_rect_init(&src, 0, 0, 1 << 16, 1 << 16);
+	drm_rect_init(&dst, 0, 0, 2, 2);
+	drm_rect_init(&clip, 0, 0, 2, 2);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 0 || src.x2 != 1 << 16 ||
+	     src.y1 != 0 || src.y2 != 1 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 0 || dst.x2 != 2 ||
+	     dst.y1 != 0 || dst.y2 != 2,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	return 0;
+}
+
+int igt_drm_rect_clip_scaled_clipped(void *ignored)
+{
+	struct drm_rect src, dst, clip;
+	bool visible;
+
+	/* 1:1 scaling top/left clip */
+	drm_rect_init(&src, 0, 0, 2 << 16, 2 << 16);
+	drm_rect_init(&dst, 0, 0, 2, 2);
+	drm_rect_init(&clip, 0, 0, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 0 || src.x2 != 1 << 16 ||
+	     src.y1 != 0 || src.y2 != 1 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 0 || dst.x2 != 1 ||
+	     dst.y1 != 0 || dst.y2 != 1,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 1:1 scaling bottom/right clip */
+	drm_rect_init(&src, 0, 0, 2 << 16, 2 << 16);
+	drm_rect_init(&dst, 0, 0, 2, 2);
+	drm_rect_init(&clip, 1, 1, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 1 << 16 || src.x2 != 2 << 16 ||
+	     src.y1 != 1 << 16 || src.y2 != 2 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 1 || dst.x2 != 2 ||
+	     dst.y1 != 1 || dst.y2 != 2,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 2:1 scaling top/left clip */
+	drm_rect_init(&src, 0, 0, 4 << 16, 4 << 16);
+	drm_rect_init(&dst, 0, 0, 2, 2);
+	drm_rect_init(&clip, 0, 0, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 0 || src.x2 != 2 << 16 ||
+	     src.y1 != 0 || src.y2 != 2 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 0 || dst.x2 != 1 ||
+	     dst.y1 != 0 || dst.y2 != 1,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 2:1 scaling bottom/right clip */
+	drm_rect_init(&src, 0, 0, 4 << 16, 4 << 16);
+	drm_rect_init(&dst, 0, 0, 2, 2);
+	drm_rect_init(&clip, 1, 1, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 2 << 16 || src.x2 != 4 << 16 ||
+	     src.y1 != 2 << 16 || src.y2 != 4 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 1 || dst.x2 != 2 ||
+	     dst.y1 != 1 || dst.y2 != 2,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 1:2 scaling top/left clip */
+	drm_rect_init(&src, 0, 0, 2 << 16, 2 << 16);
+	drm_rect_init(&dst, 0, 0, 4, 4);
+	drm_rect_init(&clip, 0, 0, 2, 2);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 0 || src.x2 != 1 << 16 ||
+	     src.y1 != 0 || src.y2 != 1 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 0 || dst.x2 != 2 ||
+	     dst.y1 != 0 || dst.y2 != 2,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	/* 1:2 scaling bottom/right clip */
+	drm_rect_init(&src, 0, 0, 2 << 16, 2 << 16);
+	drm_rect_init(&dst, 0, 0, 4, 4);
+	drm_rect_init(&clip, 2, 2, 2, 2);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(src.x1 != 1 << 16 || src.x2 != 2 << 16 ||
+	     src.y1 != 1 << 16 || src.y2 != 2 << 16,
+	     "Source badly clipped\n");
+	FAIL(dst.x1 != 2 || dst.x2 != 4 ||
+	     dst.y1 != 2 || dst.y2 != 4,
+	     "Destination badly clipped\n");
+	FAIL(!visible, "Destination should be visible\n");
+	FAIL(!drm_rect_visible(&src), "Source should be visible\n");
+
+	return 0;
+}
+
+int igt_drm_rect_clip_scaled_signed_vs_unsigned(void *ignored)
+{
+	struct drm_rect src, dst, clip;
+	bool visible;
+
+	/*
+	 * 'clip.x2 - dst.x1 >= dst width' could result a negative
+	 * src rectangle width which is no longer expected by the
+	 * code as it's using unsigned types. This could lead to
+	 * the clipped source rectangle appering visible when it
+	 * should have been fully clipped. Make sure both rectangles
+	 * end up invisible.
+	 */
+	drm_rect_init(&src, 0, 0, INT_MAX, INT_MAX);
+	drm_rect_init(&dst, 0, 0, 2, 2);
+	drm_rect_init(&clip, 3, 3, 1, 1);
+
+	visible = drm_rect_clip_scaled(&src, &dst, &clip);
+
+	FAIL(visible, "Destination should not be visible\n");
+	FAIL(drm_rect_visible(&src), "Source should not be visible\n");
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/sis/sis_drv.c b/drivers/gpu/drm/sis/sis_drv.c
index ee3801201ecc..2c54b33abb54 100644
--- a/drivers/gpu/drm/sis/sis_drv.c
+++ b/drivers/gpu/drm/sis/sis_drv.c
@@ -26,10 +26,10 @@
  */
 
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/sis_drm.h>
 
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index 68261c7f8c5f..b2778ec1cdd7 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -339,7 +339,7 @@ static int sti_dvo_connector_get_modes(struct drm_connector *connector)
 	struct sti_dvo *dvo = dvo_connector->dvo;
 
 	if (dvo->panel)
-		return drm_panel_get_modes(dvo->panel);
+		return drm_panel_get_modes(dvo->panel, connector);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
index 514efefb0016..4b165635b2d4 100644
--- a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
+++ b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
@@ -309,11 +309,24 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, const struct drm_display_mode *mode,
 	return 0;
 }
 
+static int
+dw_mipi_dsi_phy_get_timing(void *priv_data, unsigned int lane_mbps,
+			   struct dw_mipi_dsi_dphy_timing *timing)
+{
+	timing->clk_hs2lp = 0x40;
+	timing->clk_lp2hs = 0x40;
+	timing->data_hs2lp = 0x40;
+	timing->data_lp2hs = 0x40;
+
+	return 0;
+}
+
 static const struct dw_mipi_dsi_phy_ops dw_mipi_dsi_stm_phy_ops = {
 	.init = dw_mipi_dsi_phy_init,
 	.power_on = dw_mipi_dsi_phy_power_on,
 	.power_off = dw_mipi_dsi_phy_power_off,
 	.get_lane_mbps = dw_mipi_dsi_get_lane_mbps,
+	.get_timing = dw_mipi_dsi_phy_get_timing,
 };
 
 static struct dw_mipi_dsi_plat_data dw_mipi_dsi_stm_plat_data = {
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index 5b51298921cf..c2815e8ae1da 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -437,9 +437,6 @@ static void ltdc_crtc_atomic_enable(struct drm_crtc *crtc,
 	/* Commit shadow registers = update planes at next vblank */
 	reg_set(ldev->regs, LTDC_SRCR, SRCR_VBR);
 
-	/* Enable LTDC */
-	reg_set(ldev->regs, LTDC_GCR, GCR_LTDCEN);
-
 	drm_crtc_vblank_on(crtc);
 }
 
@@ -453,9 +450,6 @@ static void ltdc_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	drm_crtc_vblank_off(crtc);
 
-	/* disable LTDC */
-	reg_clear(ldev->regs, LTDC_GCR, GCR_LTDCEN);
-
 	/* disable IRQ */
 	reg_clear(ldev->regs, LTDC_IER, IER_RRIE | IER_FUIE | IER_TERRIE);
 
@@ -1044,9 +1038,13 @@ static const struct drm_encoder_funcs ltdc_encoder_funcs = {
 static void ltdc_encoder_disable(struct drm_encoder *encoder)
 {
 	struct drm_device *ddev = encoder->dev;
+	struct ltdc_device *ldev = ddev->dev_private;
 
 	DRM_DEBUG_DRIVER("\n");
 
+	/* Disable LTDC */
+	reg_clear(ldev->regs, LTDC_GCR, GCR_LTDCEN);
+
 	/* Set to sleep state the pinctrl whatever type of encoder */
 	pinctrl_pm_select_sleep_state(ddev->dev);
 }
@@ -1054,6 +1052,19 @@ static void ltdc_encoder_disable(struct drm_encoder *encoder)
 static void ltdc_encoder_enable(struct drm_encoder *encoder)
 {
 	struct drm_device *ddev = encoder->dev;
+	struct ltdc_device *ldev = ddev->dev_private;
+
+	DRM_DEBUG_DRIVER("\n");
+
+	/* Enable LTDC */
+	reg_set(ldev->regs, LTDC_GCR, GCR_LTDCEN);
+}
+
+static void ltdc_encoder_mode_set(struct drm_encoder *encoder,
+				  struct drm_display_mode *mode,
+				  struct drm_display_mode *adjusted_mode)
+{
+	struct drm_device *ddev = encoder->dev;
 
 	DRM_DEBUG_DRIVER("\n");
 
@@ -1069,6 +1080,7 @@ static void ltdc_encoder_enable(struct drm_encoder *encoder)
 static const struct drm_encoder_helper_funcs ltdc_encoder_helper_funcs = {
 	.disable = ltdc_encoder_disable,
 	.enable = ltdc_encoder_enable,
+	.mode_set = ltdc_encoder_mode_set,
 };
 
 static int ltdc_encoder_init(struct drm_device *ddev, struct drm_bridge *bridge)
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 37e90e42943f..5755f0432e77 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -17,18 +17,18 @@ config DRM_SUN4I
 if DRM_SUN4I
 
 config DRM_SUN4I_HDMI
-       tristate "Allwinner A10 HDMI Controller Support"
-       default DRM_SUN4I
-       help
+	tristate "Allwinner A10 HDMI Controller Support"
+	default DRM_SUN4I
+	help
 	  Choose this option if you have an Allwinner SoC with an HDMI
 	  controller.
 
 config DRM_SUN4I_HDMI_CEC
-       bool "Allwinner A10 HDMI CEC Support"
-       depends on DRM_SUN4I_HDMI
-       select CEC_CORE
-       select CEC_PIN
-       help
+	bool "Allwinner A10 HDMI CEC Support"
+	depends on DRM_SUN4I_HDMI
+	select CEC_CORE
+	select CEC_PIN
+	help
 	  Choose this option if you have an Allwinner SoC with an HDMI
 	  controller and want to use CEC.
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 4e29f4fe4a05..072ea113e6be 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -856,6 +856,13 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 		ret = PTR_ERR(backend->mod_clk);
 		goto err_disable_bus_clk;
 	}
+
+	ret = clk_set_rate_exclusive(backend->mod_clk, 300000000);
+	if (ret) {
+		dev_err(dev, "Couldn't set the module clock frequency\n");
+		goto err_disable_bus_clk;
+	}
+
 	clk_prepare_enable(backend->mod_clk);
 
 	backend->ram_clk = devm_clk_get(dev, "ram");
@@ -932,6 +939,7 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 err_disable_ram_clk:
 	clk_disable_unprepare(backend->ram_clk);
 err_disable_mod_clk:
+	clk_rate_exclusive_put(backend->mod_clk);
 	clk_disable_unprepare(backend->mod_clk);
 err_disable_bus_clk:
 	clk_disable_unprepare(backend->bus_clk);
@@ -952,6 +960,7 @@ static void sun4i_backend_unbind(struct device *dev, struct device *master,
 		sun4i_backend_free_sat(dev);
 
 	clk_disable_unprepare(backend->ram_clk);
+	clk_rate_exclusive_put(backend->mod_clk);
 	clk_disable_unprepare(backend->mod_clk);
 	clk_disable_unprepare(backend->bus_clk);
 	reset_control_assert(backend->reset);
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index a5757b11b730..5ae67d526b1d 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -346,6 +346,27 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 	return count;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int sun4i_drv_drm_sys_suspend(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+
+	return drm_mode_config_helper_suspend(drm);
+}
+
+static int sun4i_drv_drm_sys_resume(struct device *dev)
+{
+	struct drm_device *drm = dev_get_drvdata(dev);
+
+	return drm_mode_config_helper_resume(drm);
+}
+#endif
+
+static const struct dev_pm_ops sun4i_drv_drm_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(sun4i_drv_drm_sys_suspend,
+				sun4i_drv_drm_sys_resume)
+};
+
 static int sun4i_drv_probe(struct platform_device *pdev)
 {
 	struct component_match *match = NULL;
@@ -418,6 +439,7 @@ static struct platform_driver sun4i_drv_platform_driver = {
 	.driver		= {
 		.name		= "sun4i-drm",
 		.of_match_table	= sun4i_drv_of_table,
+		.pm = &sun4i_drv_drm_pm_ops,
 	},
 };
 module_platform_driver(sun4i_drv_platform_driver);
diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c
index c04f4ba0d69d..acfbfd4463a1 100644
--- a/drivers/gpu/drm/sun4i/sun4i_layer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_layer.c
@@ -250,11 +250,11 @@ struct drm_plane **sun4i_layers_init(struct drm_device *drm,
 			dev_err(drm->dev, "Couldn't initialize %s plane\n",
 				i ? "overlay" : "primary");
 			return ERR_CAST(layer);
-		};
+		}
 
 		layer->id = i;
 		planes[i] = &layer->plane;
-	};
+	}
 
 	return planes;
 }
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index 25ab2ef6d545..65b7a8739666 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -43,7 +43,7 @@ static int sun4i_lvds_get_modes(struct drm_connector *connector)
 	struct sun4i_lvds *lvds =
 		drm_connector_to_sun4i_lvds(connector);
 
-	return drm_panel_get_modes(lvds->panel);
+	return drm_panel_get_modes(lvds->panel, connector);
 }
 
 static struct drm_connector_helper_funcs sun4i_lvds_con_helper_funcs = {
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index e74b9eddca01..b27f16af50f5 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -47,7 +47,7 @@ static int sun4i_rgb_get_modes(struct drm_connector *connector)
 	struct sun4i_rgb *rgb =
 		drm_connector_to_sun4i_rgb(connector);
 
-	return drm_panel_get_modes(rgb->panel);
+	return drm_panel_get_modes(rgb->panel, connector);
 }
 
 /*
diff --git a/drivers/gpu/drm/sun4i/sun6i_drc.c b/drivers/gpu/drm/sun4i/sun6i_drc.c
index f7ab72244796..4fbe9a6b5182 100644
--- a/drivers/gpu/drm/sun4i/sun6i_drc.c
+++ b/drivers/gpu/drm/sun4i/sun6i_drc.c
@@ -56,6 +56,13 @@ static int sun6i_drc_bind(struct device *dev, struct device *master,
 		ret = PTR_ERR(drc->mod_clk);
 		goto err_disable_bus_clk;
 	}
+
+	ret = clk_set_rate_exclusive(drc->mod_clk, 300000000);
+	if (ret) {
+		dev_err(dev, "Couldn't set the module clock frequency\n");
+		goto err_disable_bus_clk;
+	}
+
 	clk_prepare_enable(drc->mod_clk);
 
 	return 0;
@@ -72,6 +79,7 @@ static void sun6i_drc_unbind(struct device *dev, struct device *master,
 {
 	struct sun6i_drc *drc = dev_get_drvdata(dev);
 
+	clk_rate_exclusive_put(drc->mod_clk);
 	clk_disable_unprepare(drc->mod_clk);
 	clk_disable_unprepare(drc->bus_clk);
 	reset_control_assert(drc->reset);
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index c958ca9bae63..a75fcb113172 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -795,7 +795,7 @@ static int sun6i_dsi_get_modes(struct drm_connector *connector)
 {
 	struct sun6i_dsi *dsi = connector_to_sun6i_dsi(connector);
 
-	return drm_panel_get_modes(dsi->panel);
+	return drm_panel_get_modes(dsi->panel, connector);
 }
 
 static struct drm_connector_helper_funcs sun6i_dsi_connector_helper_funcs = {
@@ -1081,6 +1081,7 @@ static const struct component_ops sun6i_dsi_ops = {
 static int sun6i_dsi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	const char *bus_clk_name = NULL;
 	struct sun6i_dsi *dsi;
 	struct resource *res;
 	void __iomem *base;
@@ -1094,6 +1095,10 @@ static int sun6i_dsi_probe(struct platform_device *pdev)
 	dsi->host.ops = &sun6i_dsi_host_ops;
 	dsi->host.dev = dev;
 
+	if (of_device_is_compatible(dev->of_node,
+				    "allwinner,sun6i-a31-mipi-dsi"))
+		bus_clk_name = "bus";
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base)) {
@@ -1107,23 +1112,36 @@ static int sun6i_dsi_probe(struct platform_device *pdev)
 		return PTR_ERR(dsi->regulator);
 	}
 
-	dsi->regs = devm_regmap_init_mmio_clk(dev, "bus", base,
-					      &sun6i_dsi_regmap_config);
-	if (IS_ERR(dsi->regs)) {
-		dev_err(dev, "Couldn't create the DSI encoder regmap\n");
-		return PTR_ERR(dsi->regs);
-	}
-
 	dsi->reset = devm_reset_control_get_shared(dev, NULL);
 	if (IS_ERR(dsi->reset)) {
 		dev_err(dev, "Couldn't get our reset line\n");
 		return PTR_ERR(dsi->reset);
 	}
 
-	dsi->mod_clk = devm_clk_get(dev, "mod");
-	if (IS_ERR(dsi->mod_clk)) {
-		dev_err(dev, "Couldn't get the DSI mod clock\n");
-		return PTR_ERR(dsi->mod_clk);
+	dsi->regs = devm_regmap_init_mmio(dev, base, &sun6i_dsi_regmap_config);
+	if (IS_ERR(dsi->regs)) {
+		dev_err(dev, "Couldn't init regmap\n");
+		return PTR_ERR(dsi->regs);
+	}
+
+	dsi->bus_clk = devm_clk_get(dev, bus_clk_name);
+	if (IS_ERR(dsi->bus_clk)) {
+		dev_err(dev, "Couldn't get the DSI bus clock\n");
+		return PTR_ERR(dsi->bus_clk);
+	}
+
+	ret = regmap_mmio_attach_clk(dsi->regs, dsi->bus_clk);
+	if (ret)
+		return ret;
+
+	if (of_device_is_compatible(dev->of_node,
+				    "allwinner,sun6i-a31-mipi-dsi")) {
+		dsi->mod_clk = devm_clk_get(dev, "mod");
+		if (IS_ERR(dsi->mod_clk)) {
+			dev_err(dev, "Couldn't get the DSI mod clock\n");
+			ret = PTR_ERR(dsi->mod_clk);
+			goto err_attach_clk;
+		}
 	}
 
 	/*
@@ -1161,6 +1179,9 @@ err_pm_disable:
 	pm_runtime_disable(dev);
 err_unprotect_clk:
 	clk_rate_exclusive_put(dsi->mod_clk);
+err_attach_clk:
+	if (!IS_ERR(dsi->bus_clk))
+		regmap_mmio_detach_clk(dsi->regs);
 	return ret;
 }
 
@@ -1174,6 +1195,9 @@ static int sun6i_dsi_remove(struct platform_device *pdev)
 	pm_runtime_disable(dev);
 	clk_rate_exclusive_put(dsi->mod_clk);
 
+	if (!IS_ERR(dsi->bus_clk))
+		regmap_mmio_detach_clk(dsi->regs);
+
 	return 0;
 }
 
@@ -1232,6 +1256,7 @@ static const struct dev_pm_ops sun6i_dsi_pm_ops = {
 
 static const struct of_device_id sun6i_dsi_of_table[] = {
 	{ .compatible = "allwinner,sun6i-a31-mipi-dsi" },
+	{ .compatible = "allwinner,sun50i-a64-mipi-dsi" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, sun6i_dsi_of_table);
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 8b803eb903b8..7c24f8f832a5 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -286,10 +286,10 @@ static struct drm_plane **sun8i_layers_init(struct drm_device *drm,
 			dev_err(drm->dev,
 				"Couldn't initialize overlay plane\n");
 			return ERR_CAST(layer);
-		};
+		}
 
 		planes[i] = &layer->plane;
-	};
+	}
 
 	for (i = 0; i < mixer->cfg->ui_num; i++) {
 		struct sun8i_ui_layer *layer;
@@ -299,10 +299,10 @@ static struct drm_plane **sun8i_layers_init(struct drm_device *drm,
 			dev_err(drm->dev, "Couldn't initialize %s plane\n",
 				i ? "overlay" : "primary");
 			return ERR_CAST(layer);
-		};
+		}
 
 		planes[mixer->cfg->vi_num + i] = &layer->plane;
-	};
+	}
 
 	return planes;
 }
diff --git a/drivers/gpu/drm/tdfx/tdfx_drv.c b/drivers/gpu/drm/tdfx/tdfx_drv.c
index c243af156ee7..ab699bf0ac5c 100644
--- a/drivers/gpu/drm/tdfx/tdfx_drv.c
+++ b/drivers/gpu/drm/tdfx/tdfx_drv.c
@@ -31,12 +31,12 @@
  */
 
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_legacy.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 
 #include "tdfx_drv.h"
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 714af052fbef..7c70fd31a4c2 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -1727,6 +1727,7 @@ static void tegra_crtc_atomic_disable(struct drm_crtc *crtc,
 {
 	struct tegra_dc *dc = to_tegra_dc(crtc);
 	u32 value;
+	int err;
 
 	if (!tegra_dc_idle(dc)) {
 		tegra_dc_stop(dc);
@@ -1773,7 +1774,9 @@ static void tegra_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	spin_unlock_irq(&crtc->dev->event_lock);
 
-	pm_runtime_put_sync(dc->dev);
+	err = host1x_client_suspend(&dc->client);
+	if (err < 0)
+		dev_err(dc->dev, "failed to suspend: %d\n", err);
 }
 
 static void tegra_crtc_atomic_enable(struct drm_crtc *crtc,
@@ -1783,8 +1786,13 @@ static void tegra_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct tegra_dc_state *state = to_dc_state(crtc->state);
 	struct tegra_dc *dc = to_tegra_dc(crtc);
 	u32 value;
+	int err;
 
-	pm_runtime_get_sync(dc->dev);
+	err = host1x_client_resume(&dc->client);
+	if (err < 0) {
+		dev_err(dc->dev, "failed to resume: %d\n", err);
+		return;
+	}
 
 	/* initialize display controller */
 	if (dc->syncpt) {
@@ -1996,7 +2004,7 @@ static bool tegra_dc_has_window_groups(struct tegra_dc *dc)
 
 static int tegra_dc_init(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	unsigned long flags = HOST1X_SYNCPT_CLIENT_MANAGED;
 	struct tegra_dc *dc = host1x_client_to_dc(client);
 	struct tegra_drm *tegra = drm->dev_private;
@@ -2012,6 +2020,15 @@ static int tegra_dc_init(struct host1x_client *client)
 	if (!tegra_dc_has_window_groups(dc))
 		return 0;
 
+	/*
+	 * Set the display hub as the host1x client parent for the display
+	 * controller. This is needed for the runtime reference counting that
+	 * ensures the display hub is always powered when any of the display
+	 * controllers are.
+	 */
+	if (dc->soc->has_nvdisplay)
+		client->parent = &tegra->hub->client;
+
 	dc->syncpt = host1x_syncpt_request(client, flags);
 	if (!dc->syncpt)
 		dev_warn(dc->dev, "failed to allocate syncpoint\n");
@@ -2077,9 +2094,9 @@ static int tegra_dc_init(struct host1x_client *client)
 
 	/*
 	 * Inherit the DMA parameters (such as maximum segment size) from the
-	 * parent device.
+	 * parent host1x device.
 	 */
-	client->dev->dma_parms = client->parent->dma_parms;
+	client->dev->dma_parms = client->host->dma_parms;
 
 	return 0;
 
@@ -2121,9 +2138,74 @@ static int tegra_dc_exit(struct host1x_client *client)
 	return 0;
 }
 
+static int tegra_dc_runtime_suspend(struct host1x_client *client)
+{
+	struct tegra_dc *dc = host1x_client_to_dc(client);
+	struct device *dev = client->dev;
+	int err;
+
+	err = reset_control_assert(dc->rst);
+	if (err < 0) {
+		dev_err(dev, "failed to assert reset: %d\n", err);
+		return err;
+	}
+
+	if (dc->soc->has_powergate)
+		tegra_powergate_power_off(dc->powergate);
+
+	clk_disable_unprepare(dc->clk);
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int tegra_dc_runtime_resume(struct host1x_client *client)
+{
+	struct tegra_dc *dc = host1x_client_to_dc(client);
+	struct device *dev = client->dev;
+	int err;
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get runtime PM: %d\n", err);
+		return err;
+	}
+
+	if (dc->soc->has_powergate) {
+		err = tegra_powergate_sequence_power_up(dc->powergate, dc->clk,
+							dc->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to power partition: %d\n", err);
+			goto put_rpm;
+		}
+	} else {
+		err = clk_prepare_enable(dc->clk);
+		if (err < 0) {
+			dev_err(dev, "failed to enable clock: %d\n", err);
+			goto put_rpm;
+		}
+
+		err = reset_control_deassert(dc->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to deassert reset: %d\n", err);
+			goto disable_clk;
+		}
+	}
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(dc->clk);
+put_rpm:
+	pm_runtime_put_sync(dev);
+	return err;
+}
+
 static const struct host1x_client_ops dc_client_ops = {
 	.init = tegra_dc_init,
 	.exit = tegra_dc_exit,
+	.suspend = tegra_dc_runtime_suspend,
+	.resume = tegra_dc_runtime_resume,
 };
 
 static const struct tegra_dc_soc_info tegra20_dc_soc_info = {
@@ -2535,65 +2617,10 @@ static int tegra_dc_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int tegra_dc_suspend(struct device *dev)
-{
-	struct tegra_dc *dc = dev_get_drvdata(dev);
-	int err;
-
-	err = reset_control_assert(dc->rst);
-	if (err < 0) {
-		dev_err(dev, "failed to assert reset: %d\n", err);
-		return err;
-	}
-
-	if (dc->soc->has_powergate)
-		tegra_powergate_power_off(dc->powergate);
-
-	clk_disable_unprepare(dc->clk);
-
-	return 0;
-}
-
-static int tegra_dc_resume(struct device *dev)
-{
-	struct tegra_dc *dc = dev_get_drvdata(dev);
-	int err;
-
-	if (dc->soc->has_powergate) {
-		err = tegra_powergate_sequence_power_up(dc->powergate, dc->clk,
-							dc->rst);
-		if (err < 0) {
-			dev_err(dev, "failed to power partition: %d\n", err);
-			return err;
-		}
-	} else {
-		err = clk_prepare_enable(dc->clk);
-		if (err < 0) {
-			dev_err(dev, "failed to enable clock: %d\n", err);
-			return err;
-		}
-
-		err = reset_control_deassert(dc->rst);
-		if (err < 0) {
-			dev_err(dev, "failed to deassert reset: %d\n", err);
-			return err;
-		}
-	}
-
-	return 0;
-}
-#endif
-
-static const struct dev_pm_ops tegra_dc_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_dc_suspend, tegra_dc_resume, NULL)
-};
-
 struct platform_driver tegra_dc_driver = {
 	.driver = {
 		.name = "tegra-dc",
 		.of_match_table = tegra_dc_of_match,
-		.pm = &tegra_dc_pm_ops,
 	},
 	.probe = tegra_dc_probe,
 	.remove = tegra_dc_remove,
diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c
index 622cdf1ad246..7dfb50f65067 100644
--- a/drivers/gpu/drm/tegra/dpaux.c
+++ b/drivers/gpu/drm/tegra/dpaux.c
@@ -588,7 +588,7 @@ static int tegra_dpaux_remove(struct platform_device *pdev)
 	/* make sure pads are powered down when not in use */
 	tegra_dpaux_pad_power_down(dpaux);
 
-	pm_runtime_put(&pdev->dev);
+	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 	drm_dp_aux_unregister(&dpaux->aux);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index f455ce71e85d..aa9e49f04988 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -905,7 +905,7 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra,
 int host1x_client_iommu_attach(struct host1x_client *client)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(client->dev);
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = drm->dev_private;
 	struct iommu_group *group = NULL;
 	int err;
@@ -941,7 +941,7 @@ int host1x_client_iommu_attach(struct host1x_client *client)
 
 void host1x_client_iommu_detach(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = drm->dev_private;
 	struct iommu_domain *domain;
 
diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h
index d941553f7a3d..ed99b67deb29 100644
--- a/drivers/gpu/drm/tegra/drm.h
+++ b/drivers/gpu/drm/tegra/drm.h
@@ -144,6 +144,8 @@ int tegra_output_init(struct drm_device *drm, struct tegra_output *output);
 void tegra_output_exit(struct tegra_output *output);
 void tegra_output_find_possible_crtcs(struct tegra_output *output,
 				      struct drm_device *drm);
+int tegra_output_suspend(struct tegra_output *output);
+int tegra_output_resume(struct tegra_output *output);
 
 int tegra_output_connector_get_modes(struct drm_connector *connector);
 enum drm_connector_status
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index a5d47e301c5f..88b9d64c77bf 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -840,7 +840,9 @@ static void tegra_dsi_unprepare(struct tegra_dsi *dsi)
 		dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n",
 			err);
 
-	pm_runtime_put(dsi->dev);
+	err = host1x_client_suspend(&dsi->client);
+	if (err < 0)
+		dev_err(dsi->dev, "failed to suspend: %d\n", err);
 }
 
 static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
@@ -882,11 +884,15 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
 	tegra_dsi_unprepare(dsi);
 }
 
-static void tegra_dsi_prepare(struct tegra_dsi *dsi)
+static int tegra_dsi_prepare(struct tegra_dsi *dsi)
 {
 	int err;
 
-	pm_runtime_get_sync(dsi->dev);
+	err = host1x_client_resume(&dsi->client);
+	if (err < 0) {
+		dev_err(dsi->dev, "failed to resume: %d\n", err);
+		return err;
+	}
 
 	err = tegra_mipi_enable(dsi->mipi);
 	if (err < 0)
@@ -899,6 +905,8 @@ static void tegra_dsi_prepare(struct tegra_dsi *dsi)
 
 	if (dsi->slave)
 		tegra_dsi_prepare(dsi->slave);
+
+	return 0;
 }
 
 static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
@@ -909,8 +917,13 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
 	struct tegra_dsi *dsi = to_dsi(output);
 	struct tegra_dsi_state *state;
 	u32 value;
+	int err;
 
-	tegra_dsi_prepare(dsi);
+	err = tegra_dsi_prepare(dsi);
+	if (err < 0) {
+		dev_err(dsi->dev, "failed to prepare: %d\n", err);
+		return;
+	}
 
 	state = tegra_dsi_get_state(dsi);
 
@@ -1030,7 +1043,7 @@ static const struct drm_encoder_helper_funcs tegra_dsi_encoder_helper_funcs = {
 
 static int tegra_dsi_init(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	struct tegra_dsi *dsi = host1x_client_to_dsi(client);
 	int err;
 
@@ -1075,9 +1088,89 @@ static int tegra_dsi_exit(struct host1x_client *client)
 	return 0;
 }
 
+static int tegra_dsi_runtime_suspend(struct host1x_client *client)
+{
+	struct tegra_dsi *dsi = host1x_client_to_dsi(client);
+	struct device *dev = client->dev;
+	int err;
+
+	if (dsi->rst) {
+		err = reset_control_assert(dsi->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to assert reset: %d\n", err);
+			return err;
+		}
+	}
+
+	usleep_range(1000, 2000);
+
+	clk_disable_unprepare(dsi->clk_lp);
+	clk_disable_unprepare(dsi->clk);
+
+	regulator_disable(dsi->vdd);
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int tegra_dsi_runtime_resume(struct host1x_client *client)
+{
+	struct tegra_dsi *dsi = host1x_client_to_dsi(client);
+	struct device *dev = client->dev;
+	int err;
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get runtime PM: %d\n", err);
+		return err;
+	}
+
+	err = regulator_enable(dsi->vdd);
+	if (err < 0) {
+		dev_err(dev, "failed to enable VDD supply: %d\n", err);
+		goto put_rpm;
+	}
+
+	err = clk_prepare_enable(dsi->clk);
+	if (err < 0) {
+		dev_err(dev, "cannot enable DSI clock: %d\n", err);
+		goto disable_vdd;
+	}
+
+	err = clk_prepare_enable(dsi->clk_lp);
+	if (err < 0) {
+		dev_err(dev, "cannot enable low-power clock: %d\n", err);
+		goto disable_clk;
+	}
+
+	usleep_range(1000, 2000);
+
+	if (dsi->rst) {
+		err = reset_control_deassert(dsi->rst);
+		if (err < 0) {
+			dev_err(dev, "cannot assert reset: %d\n", err);
+			goto disable_clk_lp;
+		}
+	}
+
+	return 0;
+
+disable_clk_lp:
+	clk_disable_unprepare(dsi->clk_lp);
+disable_clk:
+	clk_disable_unprepare(dsi->clk);
+disable_vdd:
+	regulator_disable(dsi->vdd);
+put_rpm:
+	pm_runtime_put_sync(dev);
+	return err;
+}
+
 static const struct host1x_client_ops dsi_client_ops = {
 	.init = tegra_dsi_init,
 	.exit = tegra_dsi_exit,
+	.suspend = tegra_dsi_runtime_suspend,
+	.resume = tegra_dsi_runtime_resume,
 };
 
 static int tegra_dsi_setup_clocks(struct tegra_dsi *dsi)
@@ -1596,79 +1689,6 @@ static int tegra_dsi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int tegra_dsi_suspend(struct device *dev)
-{
-	struct tegra_dsi *dsi = dev_get_drvdata(dev);
-	int err;
-
-	if (dsi->rst) {
-		err = reset_control_assert(dsi->rst);
-		if (err < 0) {
-			dev_err(dev, "failed to assert reset: %d\n", err);
-			return err;
-		}
-	}
-
-	usleep_range(1000, 2000);
-
-	clk_disable_unprepare(dsi->clk_lp);
-	clk_disable_unprepare(dsi->clk);
-
-	regulator_disable(dsi->vdd);
-
-	return 0;
-}
-
-static int tegra_dsi_resume(struct device *dev)
-{
-	struct tegra_dsi *dsi = dev_get_drvdata(dev);
-	int err;
-
-	err = regulator_enable(dsi->vdd);
-	if (err < 0) {
-		dev_err(dsi->dev, "failed to enable VDD supply: %d\n", err);
-		return err;
-	}
-
-	err = clk_prepare_enable(dsi->clk);
-	if (err < 0) {
-		dev_err(dev, "cannot enable DSI clock: %d\n", err);
-		goto disable_vdd;
-	}
-
-	err = clk_prepare_enable(dsi->clk_lp);
-	if (err < 0) {
-		dev_err(dev, "cannot enable low-power clock: %d\n", err);
-		goto disable_clk;
-	}
-
-	usleep_range(1000, 2000);
-
-	if (dsi->rst) {
-		err = reset_control_deassert(dsi->rst);
-		if (err < 0) {
-			dev_err(dev, "cannot assert reset: %d\n", err);
-			goto disable_clk_lp;
-		}
-	}
-
-	return 0;
-
-disable_clk_lp:
-	clk_disable_unprepare(dsi->clk_lp);
-disable_clk:
-	clk_disable_unprepare(dsi->clk);
-disable_vdd:
-	regulator_disable(dsi->vdd);
-	return err;
-}
-#endif
-
-static const struct dev_pm_ops tegra_dsi_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_dsi_suspend, tegra_dsi_resume, NULL)
-};
-
 static const struct of_device_id tegra_dsi_of_match[] = {
 	{ .compatible = "nvidia,tegra210-dsi", },
 	{ .compatible = "nvidia,tegra132-dsi", },
@@ -1682,7 +1702,6 @@ struct platform_driver tegra_dsi_driver = {
 	.driver = {
 		.name = "tegra-dsi",
 		.of_match_table = tegra_dsi_of_match,
-		.pm = &tegra_dsi_pm_ops,
 	},
 	.probe = tegra_dsi_probe,
 	.remove = tegra_dsi_remove,
diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c
index 7cea89f29a5c..84f0e01e3428 100644
--- a/drivers/gpu/drm/tegra/fb.c
+++ b/drivers/gpu/drm/tegra/fb.c
@@ -192,7 +192,7 @@ static int tegra_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	return __tegra_gem_mmap(&bo->gem, vma);
 }
 
-static struct fb_ops tegra_fb_ops = {
+static const struct fb_ops tegra_fb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
 	.fb_fillrect = drm_fb_helper_sys_fillrect,
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index bc15b430156d..1237df157e05 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -146,32 +146,6 @@ static void tegra_bo_munmap(struct host1x_bo *bo, void *addr)
 		vunmap(addr);
 }
 
-static void *tegra_bo_kmap(struct host1x_bo *bo, unsigned int page)
-{
-	struct tegra_bo *obj = host1x_to_tegra_bo(bo);
-
-	if (obj->vaddr)
-		return obj->vaddr + page * PAGE_SIZE;
-	else if (obj->gem.import_attach)
-		return dma_buf_kmap(obj->gem.import_attach->dmabuf, page);
-	else
-		return vmap(obj->pages + page, 1, VM_MAP,
-			    pgprot_writecombine(PAGE_KERNEL));
-}
-
-static void tegra_bo_kunmap(struct host1x_bo *bo, unsigned int page,
-			    void *addr)
-{
-	struct tegra_bo *obj = host1x_to_tegra_bo(bo);
-
-	if (obj->vaddr)
-		return;
-	else if (obj->gem.import_attach)
-		dma_buf_kunmap(obj->gem.import_attach->dmabuf, page, addr);
-	else
-		vunmap(addr);
-}
-
 static struct host1x_bo *tegra_bo_get(struct host1x_bo *bo)
 {
 	struct tegra_bo *obj = host1x_to_tegra_bo(bo);
@@ -188,8 +162,6 @@ static const struct host1x_bo_ops tegra_bo_ops = {
 	.unpin = tegra_bo_unpin,
 	.mmap = tegra_bo_mmap,
 	.munmap = tegra_bo_munmap,
-	.kmap = tegra_bo_kmap,
-	.kunmap = tegra_bo_kunmap,
 };
 
 static int tegra_bo_iommu_map(struct tegra_drm *tegra, struct tegra_bo *bo)
@@ -649,16 +621,6 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf,
 	return 0;
 }
 
-static void *tegra_gem_prime_kmap(struct dma_buf *buf, unsigned long page)
-{
-	return NULL;
-}
-
-static void tegra_gem_prime_kunmap(struct dma_buf *buf, unsigned long page,
-				   void *addr)
-{
-}
-
 static int tegra_gem_prime_mmap(struct dma_buf *buf, struct vm_area_struct *vma)
 {
 	struct drm_gem_object *gem = buf->priv;
@@ -689,8 +651,6 @@ static const struct dma_buf_ops tegra_gem_prime_dmabuf_ops = {
 	.release = tegra_gem_prime_release,
 	.begin_cpu_access = tegra_gem_prime_begin_cpu_access,
 	.end_cpu_access = tegra_gem_prime_end_cpu_access,
-	.map = tegra_gem_prime_kmap,
-	.unmap = tegra_gem_prime_kunmap,
 	.mmap = tegra_gem_prime_mmap,
 	.vmap = tegra_gem_prime_vmap,
 	.vunmap = tegra_gem_prime_vunmap,
diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c
index 1fc4e56c7cc5..48363f744bb9 100644
--- a/drivers/gpu/drm/tegra/gr2d.c
+++ b/drivers/gpu/drm/tegra/gr2d.c
@@ -34,7 +34,7 @@ static inline struct gr2d *to_gr2d(struct tegra_drm_client *client)
 static int gr2d_init(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->host);
 	unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
 	struct gr2d *gr2d = to_gr2d(drm);
 	int err;
@@ -76,7 +76,7 @@ put:
 static int gr2d_exit(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = dev->dev_private;
 	struct gr2d *gr2d = to_gr2d(drm);
 	int err;
diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c
index 24fae0f64032..c0a528be0369 100644
--- a/drivers/gpu/drm/tegra/gr3d.c
+++ b/drivers/gpu/drm/tegra/gr3d.c
@@ -43,7 +43,7 @@ static inline struct gr3d *to_gr3d(struct tegra_drm_client *client)
 static int gr3d_init(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->host);
 	unsigned long flags = HOST1X_SYNCPT_HAS_BASE;
 	struct gr3d *gr3d = to_gr3d(drm);
 	int err;
@@ -85,7 +85,7 @@ put:
 static int gr3d_exit(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->host);
 	struct gr3d *gr3d = to_gr3d(drm);
 	int err;
 
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 50269ffbcb6b..6f117628f257 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1146,6 +1146,7 @@ static void tegra_hdmi_encoder_disable(struct drm_encoder *encoder)
 	struct tegra_dc *dc = to_tegra_dc(encoder->crtc);
 	struct tegra_hdmi *hdmi = to_hdmi(output);
 	u32 value;
+	int err;
 
 	/*
 	 * The following accesses registers of the display controller, so make
@@ -1171,7 +1172,9 @@ static void tegra_hdmi_encoder_disable(struct drm_encoder *encoder)
 	tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_INT_ENABLE);
 	tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_INT_MASK);
 
-	pm_runtime_put(hdmi->dev);
+	err = host1x_client_suspend(&hdmi->client);
+	if (err < 0)
+		dev_err(hdmi->dev, "failed to suspend: %d\n", err);
 }
 
 static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
@@ -1186,7 +1189,11 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 	u32 value;
 	int err;
 
-	pm_runtime_get_sync(hdmi->dev);
+	err = host1x_client_resume(&hdmi->client);
+	if (err < 0) {
+		dev_err(hdmi->dev, "failed to resume: %d\n", err);
+		return;
+	}
 
 	/*
 	 * Enable and unmask the HDA codec SCRATCH0 register interrupt. This
@@ -1424,15 +1431,16 @@ static const struct drm_encoder_helper_funcs tegra_hdmi_encoder_helper_funcs = {
 
 static int tegra_hdmi_init(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
 	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	int err;
 
 	hdmi->output.dev = client->dev;
 
-	drm_connector_init(drm, &hdmi->output.connector,
-			   &tegra_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(drm, &hdmi->output.connector,
+				    &tegra_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    hdmi->output.ddc);
 	drm_connector_helper_add(&hdmi->output.connector,
 				 &tegra_hdmi_connector_helper_funcs);
 	hdmi->output.connector.dpms = DRM_MODE_DPMS_OFF;
@@ -1489,9 +1497,66 @@ static int tegra_hdmi_exit(struct host1x_client *client)
 	return 0;
 }
 
+static int tegra_hdmi_runtime_suspend(struct host1x_client *client)
+{
+	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
+	struct device *dev = client->dev;
+	int err;
+
+	err = reset_control_assert(hdmi->rst);
+	if (err < 0) {
+		dev_err(dev, "failed to assert reset: %d\n", err);
+		return err;
+	}
+
+	usleep_range(1000, 2000);
+
+	clk_disable_unprepare(hdmi->clk);
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int tegra_hdmi_runtime_resume(struct host1x_client *client)
+{
+	struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client);
+	struct device *dev = client->dev;
+	int err;
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get runtime PM: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(hdmi->clk);
+	if (err < 0) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		goto put_rpm;
+	}
+
+	usleep_range(1000, 2000);
+
+	err = reset_control_deassert(hdmi->rst);
+	if (err < 0) {
+		dev_err(dev, "failed to deassert reset: %d\n", err);
+		goto disable_clk;
+	}
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(hdmi->clk);
+put_rpm:
+	pm_runtime_put_sync(dev);
+	return err;
+}
+
 static const struct host1x_client_ops hdmi_client_ops = {
 	.init = tegra_hdmi_init,
 	.exit = tegra_hdmi_exit,
+	.suspend = tegra_hdmi_runtime_suspend,
+	.resume = tegra_hdmi_runtime_resume,
 };
 
 static const struct tegra_hdmi_config tegra20_hdmi_config = {
@@ -1699,58 +1764,10 @@ static int tegra_hdmi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int tegra_hdmi_suspend(struct device *dev)
-{
-	struct tegra_hdmi *hdmi = dev_get_drvdata(dev);
-	int err;
-
-	err = reset_control_assert(hdmi->rst);
-	if (err < 0) {
-		dev_err(dev, "failed to assert reset: %d\n", err);
-		return err;
-	}
-
-	usleep_range(1000, 2000);
-
-	clk_disable_unprepare(hdmi->clk);
-
-	return 0;
-}
-
-static int tegra_hdmi_resume(struct device *dev)
-{
-	struct tegra_hdmi *hdmi = dev_get_drvdata(dev);
-	int err;
-
-	err = clk_prepare_enable(hdmi->clk);
-	if (err < 0) {
-		dev_err(dev, "failed to enable clock: %d\n", err);
-		return err;
-	}
-
-	usleep_range(1000, 2000);
-
-	err = reset_control_deassert(hdmi->rst);
-	if (err < 0) {
-		dev_err(dev, "failed to deassert reset: %d\n", err);
-		clk_disable_unprepare(hdmi->clk);
-		return err;
-	}
-
-	return 0;
-}
-#endif
-
-static const struct dev_pm_ops tegra_hdmi_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_hdmi_suspend, tegra_hdmi_resume, NULL)
-};
-
 struct platform_driver tegra_hdmi_driver = {
 	.driver = {
 		.name = "tegra-hdmi",
 		.of_match_table = tegra_hdmi_of_match,
-		.pm = &tegra_hdmi_pm_ops,
 	},
 	.probe = tegra_hdmi_probe,
 	.remove = tegra_hdmi_remove,
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index 47d985ac7cd7..8183e617bf6b 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -95,17 +95,25 @@ static inline void tegra_plane_writel(struct tegra_plane *plane, u32 value,
 
 static int tegra_windowgroup_enable(struct tegra_windowgroup *wgrp)
 {
+	int err = 0;
+
 	mutex_lock(&wgrp->lock);
 
 	if (wgrp->usecount == 0) {
-		pm_runtime_get_sync(wgrp->parent);
+		err = host1x_client_resume(wgrp->parent);
+		if (err < 0) {
+			dev_err(wgrp->parent->dev, "failed to resume: %d\n", err);
+			goto unlock;
+		}
+
 		reset_control_deassert(wgrp->rst);
 	}
 
 	wgrp->usecount++;
-	mutex_unlock(&wgrp->lock);
 
-	return 0;
+unlock:
+	mutex_unlock(&wgrp->lock);
+	return err;
 }
 
 static void tegra_windowgroup_disable(struct tegra_windowgroup *wgrp)
@@ -121,7 +129,7 @@ static void tegra_windowgroup_disable(struct tegra_windowgroup *wgrp)
 			       wgrp->index);
 		}
 
-		pm_runtime_put(wgrp->parent);
+		host1x_client_suspend(wgrp->parent);
 	}
 
 	wgrp->usecount--;
@@ -379,6 +387,7 @@ static void tegra_shared_plane_atomic_disable(struct drm_plane *plane,
 	struct tegra_plane *p = to_tegra_plane(plane);
 	struct tegra_dc *dc;
 	u32 value;
+	int err;
 
 	/* rien ne va plus */
 	if (!old_state || !old_state->crtc)
@@ -386,6 +395,12 @@ static void tegra_shared_plane_atomic_disable(struct drm_plane *plane,
 
 	dc = to_tegra_dc(old_state->crtc);
 
+	err = host1x_client_resume(&dc->client);
+	if (err < 0) {
+		dev_err(dc->dev, "failed to resume: %d\n", err);
+		return;
+	}
+
 	/*
 	 * XXX Legacy helpers seem to sometimes call ->atomic_disable() even
 	 * on planes that are already disabled. Make sure we fallback to the
@@ -394,15 +409,13 @@ static void tegra_shared_plane_atomic_disable(struct drm_plane *plane,
 	if (WARN_ON(p->dc == NULL))
 		p->dc = dc;
 
-	pm_runtime_get_sync(dc->dev);
-
 	value = tegra_plane_readl(p, DC_WIN_WIN_OPTIONS);
 	value &= ~WIN_ENABLE;
 	tegra_plane_writel(p, value, DC_WIN_WIN_OPTIONS);
 
 	tegra_dc_remove_shared_plane(dc, p);
 
-	pm_runtime_put(dc->dev);
+	host1x_client_suspend(&dc->client);
 }
 
 static void tegra_shared_plane_atomic_update(struct drm_plane *plane,
@@ -415,6 +428,7 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane,
 	struct tegra_plane *p = to_tegra_plane(plane);
 	dma_addr_t base;
 	u32 value;
+	int err;
 
 	/* rien ne va plus */
 	if (!plane->state->crtc || !plane->state->fb)
@@ -425,7 +439,11 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane,
 		return;
 	}
 
-	pm_runtime_get_sync(dc->dev);
+	err = host1x_client_resume(&dc->client);
+	if (err < 0) {
+		dev_err(dc->dev, "failed to resume: %d\n", err);
+		return;
+	}
 
 	tegra_dc_assign_shared_plane(dc, p);
 
@@ -515,7 +533,7 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane,
 	value &= ~CONTROL_CSC_ENABLE;
 	tegra_plane_writel(p, value, DC_WIN_WINDOW_SET_CONTROL);
 
-	pm_runtime_put(dc->dev);
+	host1x_client_suspend(&dc->client);
 }
 
 static const struct drm_plane_helper_funcs tegra_shared_plane_helper_funcs = {
@@ -551,7 +569,7 @@ struct drm_plane *tegra_shared_plane_create(struct drm_device *drm,
 	plane->base.index = index;
 
 	plane->wgrp = &hub->wgrps[wgrp];
-	plane->wgrp->parent = dc->dev;
+	plane->wgrp->parent = &dc->client;
 
 	p = &plane->base.base;
 
@@ -656,8 +674,13 @@ int tegra_display_hub_atomic_check(struct drm_device *drm,
 static void tegra_display_hub_update(struct tegra_dc *dc)
 {
 	u32 value;
+	int err;
 
-	pm_runtime_get_sync(dc->dev);
+	err = host1x_client_resume(&dc->client);
+	if (err < 0) {
+		dev_err(dc->dev, "failed to resume: %d\n", err);
+		return;
+	}
 
 	value = tegra_dc_readl(dc, DC_CMD_IHUB_COMMON_MISC_CTL);
 	value &= ~LATENCY_EVENT;
@@ -672,7 +695,7 @@ static void tegra_display_hub_update(struct tegra_dc *dc)
 	tegra_dc_writel(dc, COMMON_ACTREQ, DC_CMD_STATE_CONTROL);
 	tegra_dc_readl(dc, DC_CMD_STATE_CONTROL);
 
-	pm_runtime_put(dc->dev);
+	host1x_client_suspend(&dc->client);
 }
 
 void tegra_display_hub_atomic_commit(struct drm_device *drm,
@@ -705,7 +728,7 @@ void tegra_display_hub_atomic_commit(struct drm_device *drm,
 static int tegra_display_hub_init(struct host1x_client *client)
 {
 	struct tegra_display_hub *hub = to_tegra_display_hub(client);
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = drm->dev_private;
 	struct tegra_display_hub_state *state;
 
@@ -723,7 +746,7 @@ static int tegra_display_hub_init(struct host1x_client *client)
 
 static int tegra_display_hub_exit(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = drm->dev_private;
 
 	drm_atomic_private_obj_fini(&tegra->hub->base);
@@ -732,9 +755,85 @@ static int tegra_display_hub_exit(struct host1x_client *client)
 	return 0;
 }
 
+static int tegra_display_hub_runtime_suspend(struct host1x_client *client)
+{
+	struct tegra_display_hub *hub = to_tegra_display_hub(client);
+	struct device *dev = client->dev;
+	unsigned int i = hub->num_heads;
+	int err;
+
+	err = reset_control_assert(hub->rst);
+	if (err < 0)
+		return err;
+
+	while (i--)
+		clk_disable_unprepare(hub->clk_heads[i]);
+
+	clk_disable_unprepare(hub->clk_hub);
+	clk_disable_unprepare(hub->clk_dsc);
+	clk_disable_unprepare(hub->clk_disp);
+
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int tegra_display_hub_runtime_resume(struct host1x_client *client)
+{
+	struct tegra_display_hub *hub = to_tegra_display_hub(client);
+	struct device *dev = client->dev;
+	unsigned int i;
+	int err;
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get runtime PM: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(hub->clk_disp);
+	if (err < 0)
+		goto put_rpm;
+
+	err = clk_prepare_enable(hub->clk_dsc);
+	if (err < 0)
+		goto disable_disp;
+
+	err = clk_prepare_enable(hub->clk_hub);
+	if (err < 0)
+		goto disable_dsc;
+
+	for (i = 0; i < hub->num_heads; i++) {
+		err = clk_prepare_enable(hub->clk_heads[i]);
+		if (err < 0)
+			goto disable_heads;
+	}
+
+	err = reset_control_deassert(hub->rst);
+	if (err < 0)
+		goto disable_heads;
+
+	return 0;
+
+disable_heads:
+	while (i--)
+		clk_disable_unprepare(hub->clk_heads[i]);
+
+	clk_disable_unprepare(hub->clk_hub);
+disable_dsc:
+	clk_disable_unprepare(hub->clk_dsc);
+disable_disp:
+	clk_disable_unprepare(hub->clk_disp);
+put_rpm:
+	pm_runtime_put_sync(dev);
+	return err;
+}
+
 static const struct host1x_client_ops tegra_display_hub_ops = {
 	.init = tegra_display_hub_init,
 	.exit = tegra_display_hub_exit,
+	.suspend = tegra_display_hub_runtime_suspend,
+	.resume = tegra_display_hub_runtime_resume,
 };
 
 static int tegra_display_hub_probe(struct platform_device *pdev)
@@ -851,6 +950,7 @@ static int tegra_display_hub_probe(struct platform_device *pdev)
 static int tegra_display_hub_remove(struct platform_device *pdev)
 {
 	struct tegra_display_hub *hub = platform_get_drvdata(pdev);
+	unsigned int i;
 	int err;
 
 	err = host1x_client_unregister(&hub->client);
@@ -859,78 +959,17 @@ static int tegra_display_hub_remove(struct platform_device *pdev)
 			err);
 	}
 
-	pm_runtime_disable(&pdev->dev);
-
-	return err;
-}
-
-static int __maybe_unused tegra_display_hub_suspend(struct device *dev)
-{
-	struct tegra_display_hub *hub = dev_get_drvdata(dev);
-	unsigned int i = hub->num_heads;
-	int err;
-
-	err = reset_control_assert(hub->rst);
-	if (err < 0)
-		return err;
-
-	while (i--)
-		clk_disable_unprepare(hub->clk_heads[i]);
-
-	clk_disable_unprepare(hub->clk_hub);
-	clk_disable_unprepare(hub->clk_dsc);
-	clk_disable_unprepare(hub->clk_disp);
-
-	return 0;
-}
-
-static int __maybe_unused tegra_display_hub_resume(struct device *dev)
-{
-	struct tegra_display_hub *hub = dev_get_drvdata(dev);
-	unsigned int i;
-	int err;
-
-	err = clk_prepare_enable(hub->clk_disp);
-	if (err < 0)
-		return err;
-
-	err = clk_prepare_enable(hub->clk_dsc);
-	if (err < 0)
-		goto disable_disp;
-
-	err = clk_prepare_enable(hub->clk_hub);
-	if (err < 0)
-		goto disable_dsc;
+	for (i = 0; i < hub->soc->num_wgrps; i++) {
+		struct tegra_windowgroup *wgrp = &hub->wgrps[i];
 
-	for (i = 0; i < hub->num_heads; i++) {
-		err = clk_prepare_enable(hub->clk_heads[i]);
-		if (err < 0)
-			goto disable_heads;
+		mutex_destroy(&wgrp->lock);
 	}
 
-	err = reset_control_deassert(hub->rst);
-	if (err < 0)
-		goto disable_heads;
-
-	return 0;
-
-disable_heads:
-	while (i--)
-		clk_disable_unprepare(hub->clk_heads[i]);
+	pm_runtime_disable(&pdev->dev);
 
-	clk_disable_unprepare(hub->clk_hub);
-disable_dsc:
-	clk_disable_unprepare(hub->clk_dsc);
-disable_disp:
-	clk_disable_unprepare(hub->clk_disp);
 	return err;
 }
 
-static const struct dev_pm_ops tegra_display_hub_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_display_hub_suspend,
-			   tegra_display_hub_resume, NULL)
-};
-
 static const struct tegra_display_hub_soc tegra186_display_hub = {
 	.num_wgrps = 6,
 	.supports_dsc = true,
@@ -958,7 +997,6 @@ struct platform_driver tegra_display_hub_driver = {
 	.driver = {
 		.name = "tegra-display-hub",
 		.of_match_table = tegra_display_hub_of_match,
-		.pm = &tegra_display_hub_pm_ops,
 	},
 	.probe = tegra_display_hub_probe,
 	.remove = tegra_display_hub_remove,
diff --git a/drivers/gpu/drm/tegra/hub.h b/drivers/gpu/drm/tegra/hub.h
index 767a60d9313c..3efa1be07ff8 100644
--- a/drivers/gpu/drm/tegra/hub.h
+++ b/drivers/gpu/drm/tegra/hub.h
@@ -17,7 +17,7 @@ struct tegra_windowgroup {
 	struct mutex lock;
 
 	unsigned int index;
-	struct device *parent;
+	struct host1x_client *parent;
 	struct reset_control *rst;
 };
 
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index 34373734ff68..a264259b97a2 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -23,7 +23,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector)
 	 * ignore any other means of obtaining a mode.
 	 */
 	if (output->panel) {
-		err = output->panel->funcs->get_modes(output->panel);
+		err = drm_panel_get_modes(output->panel, connector);
 		if (err > 0)
 			return err;
 	}
@@ -250,3 +250,19 @@ void tegra_output_find_possible_crtcs(struct tegra_output *output,
 
 	output->encoder.possible_crtcs = mask;
 }
+
+int tegra_output_suspend(struct tegra_output *output)
+{
+	if (output->hpd_irq)
+		disable_irq(output->hpd_irq);
+
+	return 0;
+}
+
+int tegra_output_resume(struct tegra_output *output)
+{
+	if (output->hpd_irq)
+		enable_irq(output->hpd_irq);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index a68d3b36b972..41d24949478e 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -2255,7 +2255,7 @@ static void tegra_sor_hdmi_disable(struct drm_encoder *encoder)
 	if (err < 0)
 		dev_err(sor->dev, "failed to power off I/O pad: %d\n", err);
 
-	pm_runtime_put(sor->dev);
+	host1x_client_suspend(&sor->client);
 }
 
 static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
@@ -2276,7 +2276,11 @@ static void tegra_sor_hdmi_enable(struct drm_encoder *encoder)
 	mode = &encoder->crtc->state->adjusted_mode;
 	pclk = mode->clock * 1000;
 
-	pm_runtime_get_sync(sor->dev);
+	err = host1x_client_resume(&sor->client);
+	if (err < 0) {
+		dev_err(sor->dev, "failed to resume: %d\n", err);
+		return;
+	}
 
 	/* switch to safe parent clock */
 	err = tegra_sor_set_parent_clock(sor, sor->clk_safe);
@@ -2722,7 +2726,7 @@ static void tegra_sor_dp_disable(struct drm_encoder *encoder)
 	if (output->panel)
 		drm_panel_unprepare(output->panel);
 
-	pm_runtime_put(sor->dev);
+	host1x_client_suspend(&sor->client);
 }
 
 static void tegra_sor_dp_enable(struct drm_encoder *encoder)
@@ -2742,7 +2746,11 @@ static void tegra_sor_dp_enable(struct drm_encoder *encoder)
 	mode = &encoder->crtc->state->adjusted_mode;
 	info = &output->connector.display_info;
 
-	pm_runtime_get_sync(sor->dev);
+	err = host1x_client_resume(&sor->client);
+	if (err < 0) {
+		dev_err(sor->dev, "failed to resume: %d\n", err);
+		return;
+	}
 
 	/* switch to safe parent clock */
 	err = tegra_sor_set_parent_clock(sor, sor->clk_safe);
@@ -3053,7 +3061,7 @@ static const struct tegra_sor_ops tegra_sor_dp_ops = {
 
 static int tegra_sor_init(struct host1x_client *client)
 {
-	struct drm_device *drm = dev_get_drvdata(client->parent);
+	struct drm_device *drm = dev_get_drvdata(client->host);
 	const struct drm_encoder_helper_funcs *helpers = NULL;
 	struct tegra_sor *sor = host1x_client_to_sor(client);
 	int connector = DRM_MODE_CONNECTOR_Unknown;
@@ -3086,9 +3094,10 @@ static int tegra_sor_init(struct host1x_client *client)
 
 	sor->output.dev = sor->dev;
 
-	drm_connector_init(drm, &sor->output.connector,
-			   &tegra_sor_connector_funcs,
-			   connector);
+	drm_connector_init_with_ddc(drm, &sor->output.connector,
+				    &tegra_sor_connector_funcs,
+				    connector,
+				    sor->output.ddc);
 	drm_connector_helper_add(&sor->output.connector,
 				 &tegra_sor_connector_helper_funcs);
 	sor->output.connector.dpms = DRM_MODE_DPMS_OFF;
@@ -3189,9 +3198,80 @@ static int tegra_sor_exit(struct host1x_client *client)
 	return 0;
 }
 
+static int tegra_sor_runtime_suspend(struct host1x_client *client)
+{
+	struct tegra_sor *sor = host1x_client_to_sor(client);
+	struct device *dev = client->dev;
+	int err;
+
+	if (sor->rst) {
+		err = reset_control_assert(sor->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to assert reset: %d\n", err);
+			return err;
+		}
+
+		reset_control_release(sor->rst);
+	}
+
+	usleep_range(1000, 2000);
+
+	clk_disable_unprepare(sor->clk);
+	pm_runtime_put_sync(dev);
+
+	return 0;
+}
+
+static int tegra_sor_runtime_resume(struct host1x_client *client)
+{
+	struct tegra_sor *sor = host1x_client_to_sor(client);
+	struct device *dev = client->dev;
+	int err;
+
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to get runtime PM: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(sor->clk);
+	if (err < 0) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		goto put_rpm;
+	}
+
+	usleep_range(1000, 2000);
+
+	if (sor->rst) {
+		err = reset_control_acquire(sor->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to acquire reset: %d\n", err);
+			goto disable_clk;
+		}
+
+		err = reset_control_deassert(sor->rst);
+		if (err < 0) {
+			dev_err(dev, "failed to deassert reset: %d\n", err);
+			goto release_reset;
+		}
+	}
+
+	return 0;
+
+release_reset:
+	reset_control_release(sor->rst);
+disable_clk:
+	clk_disable_unprepare(sor->clk);
+put_rpm:
+	pm_runtime_put_sync(dev);
+	return err;
+}
+
 static const struct host1x_client_ops sor_client_ops = {
 	.init = tegra_sor_init,
 	.exit = tegra_sor_exit,
+	.suspend = tegra_sor_runtime_suspend,
+	.resume = tegra_sor_runtime_resume,
 };
 
 static const u8 tegra124_sor_xbar_cfg[5] = {
@@ -3842,10 +3922,9 @@ static int tegra_sor_probe(struct platform_device *pdev)
 	if (!sor->clk_pad) {
 		char *name;
 
-		err = pm_runtime_get_sync(&pdev->dev);
+		err = host1x_client_resume(&sor->client);
 		if (err < 0) {
-			dev_err(&pdev->dev, "failed to get runtime PM: %d\n",
-				err);
+			dev_err(sor->dev, "failed to resume: %d\n", err);
 			goto remove;
 		}
 
@@ -3856,7 +3935,7 @@ static int tegra_sor_probe(struct platform_device *pdev)
 		}
 
 		sor->clk_pad = tegra_clk_sor_pad_register(sor, name);
-		pm_runtime_put(&pdev->dev);
+		host1x_client_suspend(&sor->client);
 	}
 
 	if (IS_ERR(sor->clk_pad)) {
@@ -3912,54 +3991,21 @@ static int tegra_sor_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int tegra_sor_runtime_suspend(struct device *dev)
-{
-	struct tegra_sor *sor = dev_get_drvdata(dev);
-	int err;
-
-	if (sor->rst) {
-		err = reset_control_assert(sor->rst);
-		if (err < 0) {
-			dev_err(dev, "failed to assert reset: %d\n", err);
-			return err;
-		}
-
-		reset_control_release(sor->rst);
-	}
-
-	usleep_range(1000, 2000);
-
-	clk_disable_unprepare(sor->clk);
-
-	return 0;
-}
-
-static int tegra_sor_runtime_resume(struct device *dev)
+static int __maybe_unused tegra_sor_suspend(struct device *dev)
 {
 	struct tegra_sor *sor = dev_get_drvdata(dev);
 	int err;
 
-	err = clk_prepare_enable(sor->clk);
+	err = tegra_output_suspend(&sor->output);
 	if (err < 0) {
-		dev_err(dev, "failed to enable clock: %d\n", err);
+		dev_err(dev, "failed to suspend output: %d\n", err);
 		return err;
 	}
 
-	usleep_range(1000, 2000);
-
-	if (sor->rst) {
-		err = reset_control_acquire(sor->rst);
-		if (err < 0) {
-			dev_err(dev, "failed to acquire reset: %d\n", err);
-			clk_disable_unprepare(sor->clk);
-			return err;
-		}
-
-		err = reset_control_deassert(sor->rst);
+	if (sor->hdmi_supply) {
+		err = regulator_disable(sor->hdmi_supply);
 		if (err < 0) {
-			dev_err(dev, "failed to deassert reset: %d\n", err);
-			reset_control_release(sor->rst);
-			clk_disable_unprepare(sor->clk);
+			tegra_output_resume(&sor->output);
 			return err;
 		}
 	}
@@ -3967,37 +4013,31 @@ static int tegra_sor_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static int tegra_sor_suspend(struct device *dev)
+static int __maybe_unused tegra_sor_resume(struct device *dev)
 {
 	struct tegra_sor *sor = dev_get_drvdata(dev);
 	int err;
 
 	if (sor->hdmi_supply) {
-		err = regulator_disable(sor->hdmi_supply);
+		err = regulator_enable(sor->hdmi_supply);
 		if (err < 0)
 			return err;
 	}
 
-	return 0;
-}
+	err = tegra_output_resume(&sor->output);
+	if (err < 0) {
+		dev_err(dev, "failed to resume output: %d\n", err);
 
-static int tegra_sor_resume(struct device *dev)
-{
-	struct tegra_sor *sor = dev_get_drvdata(dev);
-	int err;
+		if (sor->hdmi_supply)
+			regulator_disable(sor->hdmi_supply);
 
-	if (sor->hdmi_supply) {
-		err = regulator_enable(sor->hdmi_supply);
-		if (err < 0)
-			return err;
+		return err;
 	}
 
 	return 0;
 }
 
 static const struct dev_pm_ops tegra_sor_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_sor_runtime_suspend, tegra_sor_runtime_resume,
-			   NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_sor_suspend, tegra_sor_resume)
 };
 
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index 3526c2892ddb..ade56b860cf9 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/drivers/gpu/drm/tegra/vic.c
@@ -161,7 +161,7 @@ static int vic_boot(struct vic *vic)
 static int vic_init(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = dev->dev_private;
 	struct vic *vic = to_vic(drm);
 	int err;
@@ -190,9 +190,9 @@ static int vic_init(struct host1x_client *client)
 
 	/*
 	 * Inherit the DMA parameters (such as maximum segment size) from the
-	 * parent device.
+	 * parent host1x device.
 	 */
-	client->dev->dma_parms = client->parent->dma_parms;
+	client->dev->dma_parms = client->host->dma_parms;
 
 	return 0;
 
@@ -209,7 +209,7 @@ detach:
 static int vic_exit(struct host1x_client *client)
 {
 	struct tegra_drm_client *drm = host1x_to_drm_client(client);
-	struct drm_device *dev = dev_get_drvdata(client->parent);
+	struct drm_device *dev = dev_get_drvdata(client->host);
 	struct tegra_drm *tegra = dev->dev_private;
 	struct vic *vic = to_vic(drm);
 	int err;
diff --git a/drivers/gpu/drm/tilcdc/Makefile b/drivers/gpu/drm/tilcdc/Makefile
index 87f9480e43b0..662bf3a348c9 100644
--- a/drivers/gpu/drm/tilcdc/Makefile
+++ b/drivers/gpu/drm/tilcdc/Makefile
@@ -6,7 +6,6 @@ endif
 tilcdc-y := \
 	tilcdc_plane.o \
 	tilcdc_crtc.o \
-	tilcdc_tfp410.o \
 	tilcdc_panel.o \
 	tilcdc_external.o \
 	tilcdc_drv.o
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index a3612369750f..0791a0200cc3 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -30,7 +30,6 @@
 #include "tilcdc_external.h"
 #include "tilcdc_panel.h"
 #include "tilcdc_regs.h"
-#include "tilcdc_tfp410.h"
 
 static LIST_HEAD(module_list);
 
@@ -64,12 +63,6 @@ void tilcdc_module_cleanup(struct tilcdc_module *mod)
 
 static struct of_device_id tilcdc_of_match[];
 
-static struct drm_framebuffer *tilcdc_fb_create(struct drm_device *dev,
-		struct drm_file *file_priv, const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	return drm_gem_fb_create(dev, file_priv, mode_cmd);
-}
-
 static int tilcdc_atomic_check(struct drm_device *dev,
 			       struct drm_atomic_state *state)
 {
@@ -140,7 +133,7 @@ static int tilcdc_commit(struct drm_device *dev,
 }
 
 static const struct drm_mode_config_funcs mode_config_funcs = {
-	.fb_create = tilcdc_fb_create,
+	.fb_create = drm_gem_fb_create,
 	.atomic_check = tilcdc_atomic_check,
 	.atomic_commit = tilcdc_commit,
 };
@@ -649,7 +642,6 @@ static struct platform_driver tilcdc_platform_driver = {
 static int __init tilcdc_drm_init(void)
 {
 	DBG("init");
-	tilcdc_tfp410_init();
 	tilcdc_panel_init();
 	return platform_driver_register(&tilcdc_platform_driver);
 }
@@ -659,7 +651,6 @@ static void __exit tilcdc_drm_fini(void)
 	DBG("fini");
 	platform_driver_unregister(&tilcdc_platform_driver);
 	tilcdc_panel_fini();
-	tilcdc_tfp410_fini();
 }
 
 module_init(tilcdc_drm_init);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
deleted file mode 100644
index 530edb3b51cc..000000000000
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ /dev/null
@@ -1,379 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012 Texas Instruments
- * Author: Rob Clark <robdclark@gmail.com>
- */
-
-#include <linux/gpio.h>
-#include <linux/mod_devicetable.h>
-#include <linux/of_gpio.h>
-#include <linux/pinctrl/consumer.h>
-#include <linux/platform_device.h>
-
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_encoder.h>
-#include <drm/drm_modeset_helper_vtables.h>
-#include <drm/drm_probe_helper.h>
-
-#include "tilcdc_drv.h"
-#include "tilcdc_tfp410.h"
-
-struct tfp410_module {
-	struct tilcdc_module base;
-	struct i2c_adapter *i2c;
-	int gpio;
-};
-#define to_tfp410_module(x) container_of(x, struct tfp410_module, base)
-
-
-static const struct tilcdc_panel_info dvi_info = {
-		.ac_bias                = 255,
-		.ac_bias_intrpt         = 0,
-		.dma_burst_sz           = 16,
-		.bpp                    = 16,
-		.fdd                    = 0x80,
-		.tft_alt_mode           = 0,
-		.sync_edge              = 0,
-		.sync_ctrl              = 1,
-		.raster_order           = 0,
-};
-
-/*
- * Encoder:
- */
-
-struct tfp410_encoder {
-	struct drm_encoder base;
-	struct tfp410_module *mod;
-	int dpms;
-};
-#define to_tfp410_encoder(x) container_of(x, struct tfp410_encoder, base)
-
-static void tfp410_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	struct tfp410_encoder *tfp410_encoder = to_tfp410_encoder(encoder);
-
-	if (tfp410_encoder->dpms == mode)
-		return;
-
-	if (mode == DRM_MODE_DPMS_ON) {
-		DBG("Power on");
-		gpio_direction_output(tfp410_encoder->mod->gpio, 1);
-	} else {
-		DBG("Power off");
-		gpio_direction_output(tfp410_encoder->mod->gpio, 0);
-	}
-
-	tfp410_encoder->dpms = mode;
-}
-
-static void tfp410_encoder_prepare(struct drm_encoder *encoder)
-{
-	tfp410_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
-}
-
-static void tfp410_encoder_commit(struct drm_encoder *encoder)
-{
-	tfp410_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
-}
-
-static void tfp410_encoder_mode_set(struct drm_encoder *encoder,
-		struct drm_display_mode *mode,
-		struct drm_display_mode *adjusted_mode)
-{
-	/* nothing needed */
-}
-
-static const struct drm_encoder_funcs tfp410_encoder_funcs = {
-		.destroy        = drm_encoder_cleanup,
-};
-
-static const struct drm_encoder_helper_funcs tfp410_encoder_helper_funcs = {
-		.dpms           = tfp410_encoder_dpms,
-		.prepare        = tfp410_encoder_prepare,
-		.commit         = tfp410_encoder_commit,
-		.mode_set       = tfp410_encoder_mode_set,
-};
-
-static struct drm_encoder *tfp410_encoder_create(struct drm_device *dev,
-		struct tfp410_module *mod)
-{
-	struct tfp410_encoder *tfp410_encoder;
-	struct drm_encoder *encoder;
-	int ret;
-
-	tfp410_encoder = devm_kzalloc(dev->dev, sizeof(*tfp410_encoder),
-				      GFP_KERNEL);
-	if (!tfp410_encoder)
-		return NULL;
-
-	tfp410_encoder->dpms = DRM_MODE_DPMS_OFF;
-	tfp410_encoder->mod = mod;
-
-	encoder = &tfp410_encoder->base;
-	encoder->possible_crtcs = 1;
-
-	ret = drm_encoder_init(dev, encoder, &tfp410_encoder_funcs,
-			DRM_MODE_ENCODER_TMDS, NULL);
-	if (ret < 0)
-		goto fail;
-
-	drm_encoder_helper_add(encoder, &tfp410_encoder_helper_funcs);
-
-	return encoder;
-
-fail:
-	drm_encoder_cleanup(encoder);
-	return NULL;
-}
-
-/*
- * Connector:
- */
-
-struct tfp410_connector {
-	struct drm_connector base;
-
-	struct drm_encoder *encoder;  /* our connected encoder */
-	struct tfp410_module *mod;
-};
-#define to_tfp410_connector(x) container_of(x, struct tfp410_connector, base)
-
-
-static void tfp410_connector_destroy(struct drm_connector *connector)
-{
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
-
-static enum drm_connector_status tfp410_connector_detect(
-		struct drm_connector *connector,
-		bool force)
-{
-	struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
-
-	if (drm_probe_ddc(tfp410_connector->mod->i2c))
-		return connector_status_connected;
-
-	return connector_status_unknown;
-}
-
-static int tfp410_connector_get_modes(struct drm_connector *connector)
-{
-	struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
-	struct edid *edid;
-	int ret = 0;
-
-	edid = drm_get_edid(connector, tfp410_connector->mod->i2c);
-
-	drm_connector_update_edid_property(connector, edid);
-
-	if (edid) {
-		ret = drm_add_edid_modes(connector, edid);
-		kfree(edid);
-	}
-
-	return ret;
-}
-
-static struct drm_encoder *tfp410_connector_best_encoder(
-		struct drm_connector *connector)
-{
-	struct tfp410_connector *tfp410_connector = to_tfp410_connector(connector);
-	return tfp410_connector->encoder;
-}
-
-static const struct drm_connector_funcs tfp410_connector_funcs = {
-	.destroy            = tfp410_connector_destroy,
-	.detect             = tfp410_connector_detect,
-	.fill_modes         = drm_helper_probe_single_connector_modes,
-	.reset              = drm_atomic_helper_connector_reset,
-	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-};
-
-static const struct drm_connector_helper_funcs tfp410_connector_helper_funcs = {
-	.get_modes          = tfp410_connector_get_modes,
-	.best_encoder       = tfp410_connector_best_encoder,
-};
-
-static struct drm_connector *tfp410_connector_create(struct drm_device *dev,
-		struct tfp410_module *mod, struct drm_encoder *encoder)
-{
-	struct tfp410_connector *tfp410_connector;
-	struct drm_connector *connector;
-	int ret;
-
-	tfp410_connector = devm_kzalloc(dev->dev, sizeof(*tfp410_connector),
-					GFP_KERNEL);
-	if (!tfp410_connector)
-		return NULL;
-
-	tfp410_connector->encoder = encoder;
-	tfp410_connector->mod = mod;
-
-	connector = &tfp410_connector->base;
-
-	drm_connector_init(dev, connector, &tfp410_connector_funcs,
-			DRM_MODE_CONNECTOR_DVID);
-	drm_connector_helper_add(connector, &tfp410_connector_helper_funcs);
-
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT |
-			DRM_CONNECTOR_POLL_DISCONNECT;
-
-	connector->interlace_allowed = 0;
-	connector->doublescan_allowed = 0;
-
-	ret = drm_connector_attach_encoder(connector, encoder);
-	if (ret)
-		goto fail;
-
-	return connector;
-
-fail:
-	tfp410_connector_destroy(connector);
-	return NULL;
-}
-
-/*
- * Module:
- */
-
-static int tfp410_modeset_init(struct tilcdc_module *mod, struct drm_device *dev)
-{
-	struct tfp410_module *tfp410_mod = to_tfp410_module(mod);
-	struct tilcdc_drm_private *priv = dev->dev_private;
-	struct drm_encoder *encoder;
-	struct drm_connector *connector;
-
-	encoder = tfp410_encoder_create(dev, tfp410_mod);
-	if (!encoder)
-		return -ENOMEM;
-
-	connector = tfp410_connector_create(dev, tfp410_mod, encoder);
-	if (!connector)
-		return -ENOMEM;
-
-	priv->encoders[priv->num_encoders++] = encoder;
-	priv->connectors[priv->num_connectors++] = connector;
-
-	tilcdc_crtc_set_panel_info(priv->crtc, &dvi_info);
-	return 0;
-}
-
-static const struct tilcdc_module_ops tfp410_module_ops = {
-		.modeset_init = tfp410_modeset_init,
-};
-
-/*
- * Device:
- */
-
-static int tfp410_probe(struct platform_device *pdev)
-{
-	struct device_node *node = pdev->dev.of_node;
-	struct device_node *i2c_node;
-	struct tfp410_module *tfp410_mod;
-	struct tilcdc_module *mod;
-	struct pinctrl *pinctrl;
-	uint32_t i2c_phandle;
-	int ret = -EINVAL;
-
-	/* bail out early if no DT data: */
-	if (!node) {
-		dev_err(&pdev->dev, "device-tree data is missing\n");
-		return -ENXIO;
-	}
-
-	tfp410_mod = devm_kzalloc(&pdev->dev, sizeof(*tfp410_mod), GFP_KERNEL);
-	if (!tfp410_mod)
-		return -ENOMEM;
-
-	mod = &tfp410_mod->base;
-	pdev->dev.platform_data = mod;
-
-	tilcdc_module_init(mod, "tfp410", &tfp410_module_ops);
-
-	pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
-	if (IS_ERR(pinctrl))
-		dev_warn(&pdev->dev, "pins are not configured\n");
-
-	if (of_property_read_u32(node, "i2c", &i2c_phandle)) {
-		dev_err(&pdev->dev, "could not get i2c bus phandle\n");
-		goto fail;
-	}
-
-	i2c_node = of_find_node_by_phandle(i2c_phandle);
-	if (!i2c_node) {
-		dev_err(&pdev->dev, "could not get i2c bus node\n");
-		goto fail;
-	}
-
-	tfp410_mod->i2c = of_find_i2c_adapter_by_node(i2c_node);
-	if (!tfp410_mod->i2c) {
-		dev_err(&pdev->dev, "could not get i2c\n");
-		of_node_put(i2c_node);
-		goto fail;
-	}
-
-	of_node_put(i2c_node);
-
-	tfp410_mod->gpio = of_get_named_gpio_flags(node, "powerdn-gpio",
-			0, NULL);
-	if (tfp410_mod->gpio < 0) {
-		dev_warn(&pdev->dev, "No power down GPIO\n");
-	} else {
-		ret = gpio_request(tfp410_mod->gpio, "DVI_PDn");
-		if (ret) {
-			dev_err(&pdev->dev, "could not get DVI_PDn gpio\n");
-			goto fail_adapter;
-		}
-	}
-
-	return 0;
-
-fail_adapter:
-	i2c_put_adapter(tfp410_mod->i2c);
-
-fail:
-	tilcdc_module_cleanup(mod);
-	return ret;
-}
-
-static int tfp410_remove(struct platform_device *pdev)
-{
-	struct tilcdc_module *mod = dev_get_platdata(&pdev->dev);
-	struct tfp410_module *tfp410_mod = to_tfp410_module(mod);
-
-	i2c_put_adapter(tfp410_mod->i2c);
-	gpio_free(tfp410_mod->gpio);
-
-	tilcdc_module_cleanup(mod);
-
-	return 0;
-}
-
-static const struct of_device_id tfp410_of_match[] = {
-		{ .compatible = "ti,tilcdc,tfp410", },
-		{ },
-};
-
-struct platform_driver tfp410_driver = {
-	.probe = tfp410_probe,
-	.remove = tfp410_remove,
-	.driver = {
-		.owner = THIS_MODULE,
-		.name = "tfp410",
-		.of_match_table = tfp410_of_match,
-	},
-};
-
-int __init tilcdc_tfp410_init(void)
-{
-	return platform_driver_register(&tfp410_driver);
-}
-
-void __exit tilcdc_tfp410_fini(void)
-{
-	platform_driver_unregister(&tfp410_driver);
-}
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.h b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.h
deleted file mode 100644
index f9aaf6911ffc..000000000000
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012 Texas Instruments
- * Author: Rob Clark <robdclark@gmail.com>
- */
-
-#ifndef __TILCDC_TFP410_H__
-#define __TILCDC_TFP410_H__
-
-/* sub-module for tfp410 dvi adaptor */
-
-int tilcdc_tfp410_init(void);
-void tilcdc_tfp410_fini(void);
-
-#endif /* __TILCDC_TFP410_H__ */
diff --git a/drivers/gpu/drm/tiny/st7586.c b/drivers/gpu/drm/tiny/st7586.c
index 3cc21a1b30c8..060cc756194f 100644
--- a/drivers/gpu/drm/tiny/st7586.c
+++ b/drivers/gpu/drm/tiny/st7586.c
@@ -240,7 +240,7 @@ static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	mipi_dbi_command(dbi, ST7586_SET_DISP_DUTY, 0x7f);
 	mipi_dbi_command(dbi, ST7586_SET_PART_DISP, 0xa0);
-	mipi_dbi_command(dbi, MIPI_DCS_SET_PARTIAL_AREA, 0x00, 0x00, 0x00, 0x77);
+	mipi_dbi_command(dbi, MIPI_DCS_SET_PARTIAL_ROWS, 0x00, 0x00, 0x00, 0x77);
 	mipi_dbi_command(dbi, MIPI_DCS_EXIT_INVERT_MODE);
 
 	msleep(100);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 8d91b0428af1..5df596fb0280 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -161,7 +161,6 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	dma_fence_put(bo->moving);
 	if (!ttm_bo_uses_embedded_gem_object(bo))
 		dma_resv_fini(&bo->base._resv);
-	mutex_destroy(&bo->wu_mutex);
 	bo->destroy(bo);
 	ttm_mem_global_free(&ttm_mem_glob, acc_size);
 }
@@ -1299,7 +1298,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
 	INIT_LIST_HEAD(&bo->io_reserve_lru);
-	mutex_init(&bo->wu_mutex);
 	bo->bdev = bdev;
 	bo->type = type;
 	bo->num_pages = num_pages;
@@ -1903,37 +1901,3 @@ void ttm_bo_swapout_all(struct ttm_bo_device *bdev)
 	while (ttm_bo_swapout(&ttm_bo_glob, &ctx) == 0);
 }
 EXPORT_SYMBOL(ttm_bo_swapout_all);
-
-/**
- * ttm_bo_wait_unreserved - interruptible wait for a buffer object to become
- * unreserved
- *
- * @bo: Pointer to buffer
- */
-int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo)
-{
-	int ret;
-
-	/*
-	 * In the absense of a wait_unlocked API,
-	 * Use the bo::wu_mutex to avoid triggering livelocks due to
-	 * concurrent use of this function. Note that this use of
-	 * bo::wu_mutex can go away if we change locking order to
-	 * mmap_sem -> bo::reserve.
-	 */
-	ret = mutex_lock_interruptible(&bo->wu_mutex);
-	if (unlikely(ret != 0))
-		return -ERESTARTSYS;
-	if (!dma_resv_is_locked(bo->base.resv))
-		goto out_unlock;
-	ret = dma_resv_lock_interruptible(bo->base.resv, NULL);
-	if (ret == -EINTR)
-		ret = -ERESTARTSYS;
-	if (unlikely(ret != 0))
-		goto out_unlock;
-	dma_resv_unlock(bo->base.resv);
-
-out_unlock:
-	mutex_unlock(&bo->wu_mutex);
-	return ret;
-}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 97fd1dafc3e8..49ed55779128 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -504,7 +504,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	INIT_LIST_HEAD(&fbo->base.lru);
 	INIT_LIST_HEAD(&fbo->base.swap);
 	INIT_LIST_HEAD(&fbo->base.io_reserve_lru);
-	mutex_init(&fbo->base.wu_mutex);
 	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 11863fbdd5d6..389128b8c4dd 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -139,19 +139,17 @@ vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
 				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
-				(void) ttm_bo_wait_unreserved(bo);
+				if (!dma_resv_lock_interruptible(bo->base.resv,
+								 NULL))
+					dma_resv_unlock(bo->base.resv);
 				ttm_bo_put(bo);
 			}
 
 			return VM_FAULT_RETRY;
 		}
 
-		/*
-		 * If we'd want to change locking order to
-		 * mmap_sem -> bo::reserve, we'd use a blocking reserve here
-		 * instead of retrying the fault...
-		 */
-		return VM_FAULT_NOPAGE;
+		if (dma_resv_lock_interruptible(bo->base.resv, NULL))
+			return VM_FAULT_NOPAGE;
 	}
 
 	return 0;
@@ -181,7 +179,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 				    pgoff_t num_prefault)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct vm_area_struct cvma = *vma;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
 	struct ttm_bo_device *bdev = bo->bdev;
 	unsigned long page_offset;
@@ -252,7 +249,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		goto out_io_unlock;
 	}
 
-	cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, prot);
+	prot = ttm_io_prot(bo->mem.placement, prot);
 	if (!bo->mem.bus.is_iomem) {
 		struct ttm_operation_ctx ctx = {
 			.interruptible = false,
@@ -268,7 +265,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		}
 	} else {
 		/* Iomem should not be marked encrypted */
-		cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot);
+		prot = pgprot_decrypted(prot);
 	}
 
 	/*
@@ -291,11 +288,20 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 			pfn = page_to_pfn(page);
 		}
 
+		/*
+		 * Note that the value of @prot at this point may differ from
+		 * the value of @vma->vm_page_prot in the caching- and
+		 * encryption bits. This is because the exact location of the
+		 * data may not be known at mmap() time and may also change
+		 * at arbitrary times while the data is mmap'ed.
+		 * See vmf_insert_mixed_prot() for a discussion.
+		 */
 		if (vma->vm_flags & VM_MIXEDMAP)
-			ret = vmf_insert_mixed(&cvma, address,
-					__pfn_to_pfn_t(pfn, PFN_DEV));
+			ret = vmf_insert_mixed_prot(vma, address,
+						    __pfn_to_pfn_t(pfn, PFN_DEV),
+						    prot);
 		else
-			ret = vmf_insert_pfn(&cvma, address, pfn);
+			ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
 
 		/* Never error on prefaulted PTEs */
 		if (unlikely((ret & VM_FAULT_ERROR))) {
@@ -316,7 +322,7 @@ out_io_unlock:
 }
 EXPORT_SYMBOL(ttm_bo_vm_fault_reserved);
 
-static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
+vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t prot;
@@ -327,7 +333,7 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 	if (ret)
 		return ret;
 
-	prot = vm_get_page_prot(vma->vm_flags);
+	prot = vma->vm_page_prot;
 	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
@@ -336,6 +342,7 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 
 	return ret;
 }
+EXPORT_SYMBOL(ttm_bo_vm_fault);
 
 void ttm_bo_vm_open(struct vm_area_struct *vma)
 {
@@ -395,8 +402,8 @@ static int ttm_bo_vm_access_kmap(struct ttm_buffer_object *bo,
 	return len;
 }
 
-static int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
-			    void *buf, int len, int write)
+int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
+		     void *buf, int len, int write)
 {
 	unsigned long offset = (addr) - vma->vm_start;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
@@ -432,6 +439,7 @@ static int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
 
 	return ret;
 }
+EXPORT_SYMBOL(ttm_bo_vm_access);
 
 static const struct vm_operations_struct ttm_bo_vm_ops = {
 	.fault = ttm_bo_vm_fault,
@@ -520,13 +528,6 @@ EXPORT_SYMBOL(ttm_bo_mmap);
 int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 {
 	ttm_bo_get(bo);
-
-	/*
-	 * FIXME: &drm_gem_object_funcs.mmap is called with the fake offset
-	 * removed. Add it back here until the rest of TTM works without it.
-	 */
-	vma->vm_pgoff += drm_vma_node_start(&bo->base.vma_node);
-
 	ttm_bo_mmap_vma_setup(bo, vma);
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index e0e9b4f69db6..2ec448e1d663 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -223,8 +223,9 @@ void ttm_tt_destroy(struct ttm_tt *ttm)
 	ttm->func->destroy(ttm);
 }
 
-void ttm_tt_init_fields(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
-			uint32_t page_flags)
+static void ttm_tt_init_fields(struct ttm_tt *ttm,
+			       struct ttm_buffer_object *bo,
+			       uint32_t page_flags)
 {
 	ttm->bdev = bo->bdev;
 	ttm->num_pages = bo->num_pages;
diff --git a/drivers/gpu/drm/tve200/tve200_drv.c b/drivers/gpu/drm/tve200/tve200_drv.c
index 954b09c948eb..00ba9e5ce130 100644
--- a/drivers/gpu/drm/tve200/tve200_drv.c
+++ b/drivers/gpu/drm/tve200/tve200_drv.c
@@ -110,7 +110,7 @@ static int tve200_modeset_init(struct drm_device *dev)
 	}
 
 	priv->panel = panel;
-	priv->connector = panel->connector;
+	priv->connector = drm_panel_bridge_connector(bridge);
 	priv->bridge = bridge;
 
 	dev_info(dev->dev, "attached to panel %s\n",
diff --git a/drivers/gpu/drm/udl/Kconfig b/drivers/gpu/drm/udl/Kconfig
index b4d179b87f01..1f497d8f1ae5 100644
--- a/drivers/gpu/drm/udl/Kconfig
+++ b/drivers/gpu/drm/udl/Kconfig
@@ -2,10 +2,10 @@
 config DRM_UDL
 	tristate "DisplayLink"
 	depends on DRM
-	depends on USB_SUPPORT
+	depends on USB
 	depends on USB_ARCH_HAS_HCD
-	select USB
+	select DRM_GEM_SHMEM_HELPER
 	select DRM_KMS_HELPER
 	help
 	  This is a KMS driver for the USB displaylink video adapters.
-          Say M/Y to add support for these devices via drm/kms interfaces.
+	  Say M/Y to add support for these devices via drm/kms interfaces.
diff --git a/drivers/gpu/drm/udl/Makefile b/drivers/gpu/drm/udl/Makefile
index e5bb6f757e11..b50179bb4de0 100644
--- a/drivers/gpu/drm/udl/Makefile
+++ b/drivers/gpu/drm/udl/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-udl-y := udl_drv.o udl_modeset.o udl_connector.o udl_encoder.o udl_main.o udl_fb.o udl_transfer.o udl_gem.o udl_dmabuf.o
+udl-y := udl_drv.o udl_modeset.o udl_connector.o udl_main.o udl_transfer.o udl_gem.o
 
 obj-$(CONFIG_DRM_UDL) := udl.o
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index b4ae3e89a7b4..e9671d38b4a0 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2009 Bernie Thompson <bernie@plugable.com>
  */
 
+#include <drm/drm_atomic_state_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_probe_helper.h>
 
@@ -90,13 +91,6 @@ udl_detect(struct drm_connector *connector, bool force)
 	return connector_status_connected;
 }
 
-static int udl_connector_set_property(struct drm_connector *connector,
-				      struct drm_property *property,
-				      uint64_t val)
-{
-	return 0;
-}
-
 static void udl_connector_destroy(struct drm_connector *connector)
 {
 	struct udl_drm_connector *udl_connector =
@@ -104,7 +98,6 @@ static void udl_connector_destroy(struct drm_connector *connector)
 					struct udl_drm_connector,
 					connector);
 
-	drm_connector_unregister(connector);
 	drm_connector_cleanup(connector);
 	kfree(udl_connector->edid);
 	kfree(connector);
@@ -117,30 +110,30 @@ static const struct drm_connector_helper_funcs udl_connector_helper_funcs = {
 
 static const struct drm_connector_funcs udl_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
+	.reset = drm_atomic_helper_connector_reset,
 	.detect = udl_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = udl_connector_destroy,
-	.set_property = udl_connector_set_property,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state   = drm_atomic_helper_connector_destroy_state,
 };
 
-int udl_connector_init(struct drm_device *dev, struct drm_encoder *encoder)
+struct drm_connector *udl_connector_init(struct drm_device *dev)
 {
 	struct udl_drm_connector *udl_connector;
 	struct drm_connector *connector;
 
 	udl_connector = kzalloc(sizeof(struct udl_drm_connector), GFP_KERNEL);
 	if (!udl_connector)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	connector = &udl_connector->connector;
 	drm_connector_init(dev, connector, &udl_connector_funcs,
 			   DRM_MODE_CONNECTOR_DVII);
 	drm_connector_helper_add(connector, &udl_connector_helper_funcs);
 
-	drm_connector_register(connector);
-	drm_connector_attach_encoder(connector, encoder);
 	connector->polled = DRM_CONNECTOR_POLL_HPD |
 		DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 
-	return 0;
+	return connector;
 }
diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c
deleted file mode 100644
index 3108e9a9234b..000000000000
--- a/drivers/gpu/drm/udl/udl_dmabuf.c
+++ /dev/null
@@ -1,255 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * udl_dmabuf.c
- *
- * Copyright (c) 2014 The Chromium OS Authors
- */
-
-#include <linux/shmem_fs.h>
-#include <linux/dma-buf.h>
-
-#include <drm/drm_prime.h>
-
-#include "udl_drv.h"
-
-struct udl_drm_dmabuf_attachment {
-	struct sg_table sgt;
-	enum dma_data_direction dir;
-	bool is_mapped;
-};
-
-static int udl_attach_dma_buf(struct dma_buf *dmabuf,
-			      struct dma_buf_attachment *attach)
-{
-	struct udl_drm_dmabuf_attachment *udl_attach;
-
-	DRM_DEBUG_PRIME("[DEV:%s] size:%zd\n", dev_name(attach->dev),
-			attach->dmabuf->size);
-
-	udl_attach = kzalloc(sizeof(*udl_attach), GFP_KERNEL);
-	if (!udl_attach)
-		return -ENOMEM;
-
-	udl_attach->dir = DMA_NONE;
-	attach->priv = udl_attach;
-
-	return 0;
-}
-
-static void udl_detach_dma_buf(struct dma_buf *dmabuf,
-			       struct dma_buf_attachment *attach)
-{
-	struct udl_drm_dmabuf_attachment *udl_attach = attach->priv;
-	struct sg_table *sgt;
-
-	if (!udl_attach)
-		return;
-
-	DRM_DEBUG_PRIME("[DEV:%s] size:%zd\n", dev_name(attach->dev),
-			attach->dmabuf->size);
-
-	sgt = &udl_attach->sgt;
-
-	if (udl_attach->dir != DMA_NONE)
-		dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents,
-				udl_attach->dir);
-
-	sg_free_table(sgt);
-	kfree(udl_attach);
-	attach->priv = NULL;
-}
-
-static struct sg_table *udl_map_dma_buf(struct dma_buf_attachment *attach,
-					enum dma_data_direction dir)
-{
-	struct udl_drm_dmabuf_attachment *udl_attach = attach->priv;
-	struct udl_gem_object *obj = to_udl_bo(attach->dmabuf->priv);
-	struct drm_device *dev = obj->base.dev;
-	struct udl_device *udl = dev->dev_private;
-	struct scatterlist *rd, *wr;
-	struct sg_table *sgt = NULL;
-	unsigned int i;
-	int page_count;
-	int nents, ret;
-
-	DRM_DEBUG_PRIME("[DEV:%s] size:%zd dir=%d\n", dev_name(attach->dev),
-			attach->dmabuf->size, dir);
-
-	/* just return current sgt if already requested. */
-	if (udl_attach->dir == dir && udl_attach->is_mapped)
-		return &udl_attach->sgt;
-
-	if (!obj->pages) {
-		ret = udl_gem_get_pages(obj);
-		if (ret) {
-			DRM_ERROR("failed to map pages.\n");
-			return ERR_PTR(ret);
-		}
-	}
-
-	page_count = obj->base.size / PAGE_SIZE;
-	obj->sg = drm_prime_pages_to_sg(obj->pages, page_count);
-	if (IS_ERR(obj->sg)) {
-		DRM_ERROR("failed to allocate sgt.\n");
-		return ERR_CAST(obj->sg);
-	}
-
-	sgt = &udl_attach->sgt;
-
-	ret = sg_alloc_table(sgt, obj->sg->orig_nents, GFP_KERNEL);
-	if (ret) {
-		DRM_ERROR("failed to alloc sgt.\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
-	mutex_lock(&udl->gem_lock);
-
-	rd = obj->sg->sgl;
-	wr = sgt->sgl;
-	for (i = 0; i < sgt->orig_nents; ++i) {
-		sg_set_page(wr, sg_page(rd), rd->length, rd->offset);
-		rd = sg_next(rd);
-		wr = sg_next(wr);
-	}
-
-	if (dir != DMA_NONE) {
-		nents = dma_map_sg(attach->dev, sgt->sgl, sgt->orig_nents, dir);
-		if (!nents) {
-			DRM_ERROR("failed to map sgl with iommu.\n");
-			sg_free_table(sgt);
-			sgt = ERR_PTR(-EIO);
-			goto err_unlock;
-		}
-	}
-
-	udl_attach->is_mapped = true;
-	udl_attach->dir = dir;
-	attach->priv = udl_attach;
-
-err_unlock:
-	mutex_unlock(&udl->gem_lock);
-	return sgt;
-}
-
-static void udl_unmap_dma_buf(struct dma_buf_attachment *attach,
-			      struct sg_table *sgt,
-			      enum dma_data_direction dir)
-{
-	/* Nothing to do. */
-	DRM_DEBUG_PRIME("[DEV:%s] size:%zd dir:%d\n", dev_name(attach->dev),
-			attach->dmabuf->size, dir);
-}
-
-static void *udl_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	/* TODO */
-
-	return NULL;
-}
-
-static void udl_dmabuf_kunmap(struct dma_buf *dma_buf,
-			      unsigned long page_num, void *addr)
-{
-	/* TODO */
-}
-
-static int udl_dmabuf_mmap(struct dma_buf *dma_buf,
-			   struct vm_area_struct *vma)
-{
-	/* TODO */
-
-	return -EINVAL;
-}
-
-static const struct dma_buf_ops udl_dmabuf_ops = {
-	.attach			= udl_attach_dma_buf,
-	.detach			= udl_detach_dma_buf,
-	.map_dma_buf		= udl_map_dma_buf,
-	.unmap_dma_buf		= udl_unmap_dma_buf,
-	.map			= udl_dmabuf_kmap,
-	.unmap			= udl_dmabuf_kunmap,
-	.mmap			= udl_dmabuf_mmap,
-	.release		= drm_gem_dmabuf_release,
-};
-
-struct dma_buf *udl_gem_prime_export(struct drm_gem_object *obj, int flags)
-{
-	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
-
-	exp_info.ops = &udl_dmabuf_ops;
-	exp_info.size = obj->size;
-	exp_info.flags = flags;
-	exp_info.priv = obj;
-
-	return drm_gem_dmabuf_export(obj->dev, &exp_info);
-}
-
-static int udl_prime_create(struct drm_device *dev,
-			    size_t size,
-			    struct sg_table *sg,
-			    struct udl_gem_object **obj_p)
-{
-	struct udl_gem_object *obj;
-	int npages;
-
-	npages = size / PAGE_SIZE;
-
-	*obj_p = NULL;
-	obj = udl_gem_alloc_object(dev, npages * PAGE_SIZE);
-	if (!obj)
-		return -ENOMEM;
-
-	obj->sg = sg;
-	obj->pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
-	if (obj->pages == NULL) {
-		DRM_ERROR("obj pages is NULL %d\n", npages);
-		return -ENOMEM;
-	}
-
-	drm_prime_sg_to_page_addr_arrays(sg, obj->pages, NULL, npages);
-
-	*obj_p = obj;
-	return 0;
-}
-
-struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev,
-				struct dma_buf *dma_buf)
-{
-	struct dma_buf_attachment *attach;
-	struct sg_table *sg;
-	struct udl_gem_object *uobj;
-	int ret;
-
-	/* need to attach */
-	get_device(dev->dev);
-	attach = dma_buf_attach(dma_buf, dev->dev);
-	if (IS_ERR(attach)) {
-		put_device(dev->dev);
-		return ERR_CAST(attach);
-	}
-
-	get_dma_buf(dma_buf);
-
-	sg = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
-	if (IS_ERR(sg)) {
-		ret = PTR_ERR(sg);
-		goto fail_detach;
-	}
-
-	ret = udl_prime_create(dev, dma_buf->size, sg, &uobj);
-	if (ret)
-		goto fail_unmap;
-
-	uobj->base.import_attach = attach;
-	uobj->flags = UDL_BO_WC;
-
-	return &uobj->base;
-
-fail_unmap:
-	dma_buf_unmap_attachment(attach, sg, DMA_BIDIRECTIONAL);
-fail_detach:
-	dma_buf_detach(dma_buf, attach);
-	dma_buf_put(dma_buf);
-	put_device(dev->dev);
-	return ERR_PTR(ret);
-}
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 8426669433e4..e6c1cd77d4d4 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -7,7 +7,9 @@
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_file.h>
+#include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_probe_helper.h>
 #include <drm/drm_print.h>
@@ -19,36 +21,17 @@ static int udl_usb_suspend(struct usb_interface *interface,
 {
 	struct drm_device *dev = usb_get_intfdata(interface);
 
-	drm_kms_helper_poll_disable(dev);
-	return 0;
+	return drm_mode_config_helper_suspend(dev);
 }
 
 static int udl_usb_resume(struct usb_interface *interface)
 {
 	struct drm_device *dev = usb_get_intfdata(interface);
 
-	drm_kms_helper_poll_enable(dev);
-	udl_modeset_restore(dev);
-	return 0;
+	return drm_mode_config_helper_resume(dev);
 }
 
-static const struct vm_operations_struct udl_gem_vm_ops = {
-	.fault = udl_gem_fault,
-	.open = drm_gem_vm_open,
-	.close = drm_gem_vm_close,
-};
-
-static const struct file_operations udl_driver_fops = {
-	.owner = THIS_MODULE,
-	.open = drm_open,
-	.mmap = udl_drm_gem_mmap,
-	.poll = drm_poll,
-	.read = drm_read,
-	.unlocked_ioctl	= drm_ioctl,
-	.release = drm_release,
-	.compat_ioctl = drm_compat_ioctl,
-	.llseek = noop_llseek,
-};
+DEFINE_DRM_GEM_FOPS(udl_driver_fops);
 
 static void udl_driver_release(struct drm_device *dev)
 {
@@ -59,21 +42,14 @@ static void udl_driver_release(struct drm_device *dev)
 }
 
 static struct drm_driver driver = {
-	.driver_features = DRIVER_MODESET | DRIVER_GEM,
+	.driver_features = DRIVER_ATOMIC | DRIVER_GEM | DRIVER_MODESET,
 	.release = udl_driver_release,
 
 	/* gem hooks */
-	.gem_free_object_unlocked = udl_gem_free_object,
-	.gem_vm_ops = &udl_gem_vm_ops,
+	.gem_create_object = udl_driver_gem_create_object,
 
-	.dumb_create = udl_dumb_create,
-	.dumb_map_offset = udl_gem_mmap,
 	.fops = &udl_driver_fops,
-
-	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
-	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
-	.gem_prime_export = udl_gem_prime_export,
-	.gem_prime_import = udl_gem_prime_import,
+	DRM_GEM_SHMEM_DRIVER_OPS,
 
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
@@ -129,8 +105,14 @@ static int udl_usb_probe(struct usb_interface *interface,
 
 	DRM_INFO("Initialized udl on minor %d\n", udl->drm.primary->index);
 
+	r = drm_fbdev_generic_setup(&udl->drm, 0);
+	if (r)
+		goto err_drm_dev_unregister;
+
 	return 0;
 
+err_drm_dev_unregister:
+	drm_dev_unregister(&udl->drm);
 err_free:
 	drm_dev_put(&udl->drm);
 	return r;
@@ -141,7 +123,6 @@ static void udl_usb_disconnect(struct usb_interface *interface)
 	struct drm_device *dev = usb_get_intfdata(interface);
 
 	drm_kms_helper_poll_disable(dev);
-	udl_fbdev_unplug(dev);
 	udl_drop_usb(dev);
 	drm_dev_unplug(dev);
 	drm_dev_put(dev);
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 12a970fd9a87..e67227c44cc4 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -17,8 +17,8 @@
 #include <drm/drm_device.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_simple_kms_helper.h>
 
-struct drm_encoder;
 struct drm_mode_create_dumb;
 
 #define DRIVER_NAME		"udl"
@@ -29,9 +29,6 @@ struct drm_mode_create_dumb;
 #define DRIVER_MINOR		0
 #define DRIVER_PATCHLEVEL	1
 
-#define UDL_BO_CACHEABLE		(1 << 0)
-#define UDL_BO_WC		(1 << 1)
-
 struct udl_device;
 
 struct urb_node {
@@ -50,57 +47,29 @@ struct urb_list {
 	size_t size;
 };
 
-struct udl_fbdev;
-
 struct udl_device {
 	struct drm_device drm;
 	struct device *dev;
 	struct usb_device *udev;
-	struct drm_crtc *crtc;
+
+	struct drm_simple_display_pipe display_pipe;
 
 	struct mutex gem_lock;
 
 	int sku_pixel_limit;
 
 	struct urb_list urbs;
-	atomic_t lost_pixels; /* 1 = a render op failed. Need screen refresh */
 
-	struct udl_fbdev *fbdev;
 	char mode_buf[1024];
 	uint32_t mode_buf_len;
-	atomic_t bytes_rendered; /* raw pixel-bytes driver asked to render */
-	atomic_t bytes_identical; /* saved effort with backbuffer comparison */
-	atomic_t bytes_sent; /* to usb, after compression including overhead */
-	atomic_t cpu_kcycles_used; /* transpired during pixel processing */
 };
 
 #define to_udl(x) container_of(x, struct udl_device, drm)
 
-struct udl_gem_object {
-	struct drm_gem_object base;
-	struct page **pages;
-	void *vmapping;
-	struct sg_table *sg;
-	unsigned int flags;
-};
-
-#define to_udl_bo(x) container_of(x, struct udl_gem_object, base)
-
-struct udl_framebuffer {
-	struct drm_framebuffer base;
-	struct udl_gem_object *obj;
-	bool active_16; /* active on the 16-bit channel */
-};
-
-#define to_udl_fb(x) container_of(x, struct udl_framebuffer, base)
-
 /* modeset */
 int udl_modeset_init(struct drm_device *dev);
-void udl_modeset_restore(struct drm_device *dev);
 void udl_modeset_cleanup(struct drm_device *dev);
-int udl_connector_init(struct drm_device *dev, struct drm_encoder *encoder);
-
-struct drm_encoder *udl_encoder_init(struct drm_device *dev);
+struct drm_connector *udl_connector_init(struct drm_device *dev);
 
 struct urb *udl_get_urb(struct drm_device *dev);
 
@@ -110,41 +79,12 @@ void udl_urb_completion(struct urb *urb);
 int udl_init(struct udl_device *udl);
 void udl_fini(struct drm_device *dev);
 
-int udl_fbdev_init(struct drm_device *dev);
-void udl_fbdev_cleanup(struct drm_device *dev);
-void udl_fbdev_unplug(struct drm_device *dev);
-struct drm_framebuffer *
-udl_fb_user_fb_create(struct drm_device *dev,
-		      struct drm_file *file,
-		      const struct drm_mode_fb_cmd2 *mode_cmd);
-
 int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
-		     u32 byte_offset, u32 device_byte_offset, u32 byte_width,
-		     int *ident_ptr, int *sent_ptr);
-
-int udl_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args);
-int udl_gem_mmap(struct drm_file *file_priv, struct drm_device *dev,
-		 uint32_t handle, uint64_t *offset);
-
-void udl_gem_free_object(struct drm_gem_object *gem_obj);
-struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev,
-					    size_t size);
-struct dma_buf *udl_gem_prime_export(struct drm_gem_object *obj, int flags);
-struct drm_gem_object *udl_gem_prime_import(struct drm_device *dev,
-				struct dma_buf *dma_buf);
-
-int udl_gem_get_pages(struct udl_gem_object *obj);
-void udl_gem_put_pages(struct udl_gem_object *obj);
-int udl_gem_vmap(struct udl_gem_object *obj);
-void udl_gem_vunmap(struct udl_gem_object *obj);
-int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-vm_fault_t udl_gem_fault(struct vm_fault *vmf);
-
-int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
-		      int width, int height);
+		     u32 byte_offset, u32 device_byte_offset, u32 byte_width);
+
+struct drm_gem_object *udl_driver_gem_create_object(struct drm_device *dev,
+						    size_t size);
 
 int udl_drop_usb(struct drm_device *dev);
 
@@ -158,4 +98,13 @@ int udl_drop_usb(struct drm_device *dev);
 #define CMD_WRITE_COPY16 "\xAF\x6A" /**< 16 bit copy command. */
 #define CMD_WRITE_RLX16  "\xAF\x6B" /**< 16 bit extended run length command. */
 
+/* On/Off for driving the DisplayLink framebuffer to the display */
+#define UDL_REG_BLANK_MODE		0x1f
+
+#define UDL_BLANK_MODE_ON		0x00 /* hsync and vsync on, visible */
+#define UDL_BLANK_MODE_BLANKED		0x01 /* hsync and vsync on, blanked */
+#define UDL_BLANK_MODE_VSYNC_OFF	0x03 /* vsync off, blanked */
+#define UDL_BLANK_MODE_HSYNC_OFF	0x05 /* hsync off, blanked */
+#define UDL_BLANK_MODE_POWERDOWN	0x07 /* powered off; requires modeset */
+
 #endif
diff --git a/drivers/gpu/drm/udl/udl_encoder.c b/drivers/gpu/drm/udl/udl_encoder.c
deleted file mode 100644
index 203f041e737c..000000000000
--- a/drivers/gpu/drm/udl/udl_encoder.c
+++ /dev/null
@@ -1,70 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012 Red Hat
- * based in parts on udlfb.c:
- * Copyright (C) 2009 Roberto De Ioris <roberto@unbit.it>
- * Copyright (C) 2009 Jaya Kumar <jayakumar.lkml@gmail.com>
- * Copyright (C) 2009 Bernie Thompson <bernie@plugable.com>
- */
-
-#include <drm/drm_encoder.h>
-#include <drm/drm_modeset_helper_vtables.h>
-
-#include "udl_drv.h"
-
-/* dummy encoder */
-static void udl_enc_destroy(struct drm_encoder *encoder)
-{
-	drm_encoder_cleanup(encoder);
-	kfree(encoder);
-}
-
-static void udl_encoder_disable(struct drm_encoder *encoder)
-{
-}
-
-static void udl_encoder_prepare(struct drm_encoder *encoder)
-{
-}
-
-static void udl_encoder_commit(struct drm_encoder *encoder)
-{
-}
-
-static void udl_encoder_mode_set(struct drm_encoder *encoder,
-				 struct drm_display_mode *mode,
-				 struct drm_display_mode *adjusted_mode)
-{
-}
-
-static void
-udl_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-}
-
-static const struct drm_encoder_helper_funcs udl_helper_funcs = {
-	.dpms = udl_encoder_dpms,
-	.prepare = udl_encoder_prepare,
-	.mode_set = udl_encoder_mode_set,
-	.commit = udl_encoder_commit,
-	.disable = udl_encoder_disable,
-};
-
-static const struct drm_encoder_funcs udl_enc_funcs = {
-	.destroy = udl_enc_destroy,
-};
-
-struct drm_encoder *udl_encoder_init(struct drm_device *dev)
-{
-	struct drm_encoder *encoder;
-
-	encoder = kzalloc(sizeof(struct drm_encoder), GFP_KERNEL);
-	if (!encoder)
-		return NULL;
-
-	drm_encoder_init(dev, encoder, &udl_enc_funcs, DRM_MODE_ENCODER_TMDS,
-			 NULL);
-	drm_encoder_helper_add(encoder, &udl_helper_funcs);
-	encoder->possible_crtcs = 1;
-	return encoder;
-}
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
deleted file mode 100644
index ef3504d06343..000000000000
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ /dev/null
@@ -1,527 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012 Red Hat
- *
- * based in parts on udlfb.c:
- * Copyright (C) 2009 Roberto De Ioris <roberto@unbit.it>
- * Copyright (C) 2009 Jaya Kumar <jayakumar.lkml@gmail.com>
- * Copyright (C) 2009 Bernie Thompson <bernie@plugable.com>
- */
-
-#include <linux/moduleparam.h>
-#include <linux/dma-buf.h>
-
-#include <drm/drm_crtc_helper.h>
-#include <drm/drm_drv.h>
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_fourcc.h>
-#include <drm/drm_modeset_helper.h>
-
-#include "udl_drv.h"
-
-#define DL_DEFIO_WRITE_DELAY    (HZ/20) /* fb_deferred_io.delay in jiffies */
-
-static int fb_defio = 0;  /* Optionally enable experimental fb_defio mmap support */
-static int fb_bpp = 16;
-
-module_param(fb_bpp, int, S_IWUSR | S_IRUSR | S_IWGRP | S_IRGRP);
-module_param(fb_defio, int, S_IWUSR | S_IRUSR | S_IWGRP | S_IRGRP);
-
-struct udl_fbdev {
-	struct drm_fb_helper helper; /* must be first */
-	struct udl_framebuffer ufb;
-	int fb_count;
-};
-
-#define DL_ALIGN_UP(x, a) ALIGN(x, a)
-#define DL_ALIGN_DOWN(x, a) ALIGN_DOWN(x, a)
-
-/** Read the red component (0..255) of a 32 bpp colour. */
-#define DLO_RGB_GETRED(col) (uint8_t)((col) & 0xFF)
-
-/** Read the green component (0..255) of a 32 bpp colour. */
-#define DLO_RGB_GETGRN(col) (uint8_t)(((col) >> 8) & 0xFF)
-
-/** Read the blue component (0..255) of a 32 bpp colour. */
-#define DLO_RGB_GETBLU(col) (uint8_t)(((col) >> 16) & 0xFF)
-
-/** Return red/green component of a 16 bpp colour number. */
-#define DLO_RG16(red, grn) (uint8_t)((((red) & 0xF8) | ((grn) >> 5)) & 0xFF)
-
-/** Return green/blue component of a 16 bpp colour number. */
-#define DLO_GB16(grn, blu) (uint8_t)(((((grn) & 0x1C) << 3) | ((blu) >> 3)) & 0xFF)
-
-/** Return 8 bpp colour number from red, green and blue components. */
-#define DLO_RGB8(red, grn, blu) ((((red) << 5) | (((grn) & 3) << 3) | ((blu) & 7)) & 0xFF)
-
-#if 0
-static uint8_t rgb8(uint32_t col)
-{
-	uint8_t red = DLO_RGB_GETRED(col);
-	uint8_t grn = DLO_RGB_GETGRN(col);
-	uint8_t blu = DLO_RGB_GETBLU(col);
-
-	return DLO_RGB8(red, grn, blu);
-}
-
-static uint16_t rgb16(uint32_t col)
-{
-	uint8_t red = DLO_RGB_GETRED(col);
-	uint8_t grn = DLO_RGB_GETGRN(col);
-	uint8_t blu = DLO_RGB_GETBLU(col);
-
-	return (DLO_RG16(red, grn) << 8) + DLO_GB16(grn, blu);
-}
-#endif
-
-int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
-		      int width, int height)
-{
-	struct drm_device *dev = fb->base.dev;
-	struct udl_device *udl = to_udl(dev);
-	int i, ret;
-	char *cmd;
-	cycles_t start_cycles, end_cycles;
-	int bytes_sent = 0;
-	int bytes_identical = 0;
-	struct urb *urb;
-	int aligned_x;
-	int log_bpp;
-
-	BUG_ON(!is_power_of_2(fb->base.format->cpp[0]));
-	log_bpp = __ffs(fb->base.format->cpp[0]);
-
-	if (!fb->active_16)
-		return 0;
-
-	if (!fb->obj->vmapping) {
-		ret = udl_gem_vmap(fb->obj);
-		if (ret == -ENOMEM) {
-			DRM_ERROR("failed to vmap fb\n");
-			return 0;
-		}
-		if (!fb->obj->vmapping) {
-			DRM_ERROR("failed to vmapping\n");
-			return 0;
-		}
-	}
-
-	aligned_x = DL_ALIGN_DOWN(x, sizeof(unsigned long));
-	width = DL_ALIGN_UP(width + (x-aligned_x), sizeof(unsigned long));
-	x = aligned_x;
-
-	if ((width <= 0) ||
-	    (x + width > fb->base.width) ||
-	    (y + height > fb->base.height))
-		return -EINVAL;
-
-	start_cycles = get_cycles();
-
-	urb = udl_get_urb(dev);
-	if (!urb)
-		return 0;
-	cmd = urb->transfer_buffer;
-
-	for (i = y; i < y + height ; i++) {
-		const int line_offset = fb->base.pitches[0] * i;
-		const int byte_offset = line_offset + (x << log_bpp);
-		const int dev_byte_offset = (fb->base.width * i + x) << log_bpp;
-		if (udl_render_hline(dev, log_bpp, &urb,
-				     (char *) fb->obj->vmapping,
-				     &cmd, byte_offset, dev_byte_offset,
-				     width << log_bpp,
-				     &bytes_identical, &bytes_sent))
-			goto error;
-	}
-
-	if (cmd > (char *) urb->transfer_buffer) {
-		/* Send partial buffer remaining before exiting */
-		int len;
-		if (cmd < (char *) urb->transfer_buffer + urb->transfer_buffer_length)
-			*cmd++ = 0xAF;
-		len = cmd - (char *) urb->transfer_buffer;
-		ret = udl_submit_urb(dev, urb, len);
-		bytes_sent += len;
-	} else
-		udl_urb_completion(urb);
-
-error:
-	atomic_add(bytes_sent, &udl->bytes_sent);
-	atomic_add(bytes_identical, &udl->bytes_identical);
-	atomic_add((width * height) << log_bpp, &udl->bytes_rendered);
-	end_cycles = get_cycles();
-	atomic_add(((unsigned int) ((end_cycles - start_cycles)
-		    >> 10)), /* Kcycles */
-		   &udl->cpu_kcycles_used);
-
-	return 0;
-}
-
-static int udl_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
-{
-	unsigned long start = vma->vm_start;
-	unsigned long size = vma->vm_end - vma->vm_start;
-	unsigned long offset;
-	unsigned long page, pos;
-
-	if (vma->vm_pgoff > (~0UL >> PAGE_SHIFT))
-		return -EINVAL;
-
-	offset = vma->vm_pgoff << PAGE_SHIFT;
-
-	if (offset > info->fix.smem_len || size > info->fix.smem_len - offset)
-		return -EINVAL;
-
-	pos = (unsigned long)info->fix.smem_start + offset;
-
-	pr_debug("mmap() framebuffer addr:%lu size:%lu\n",
-		  pos, size);
-
-	/* We don't want the framebuffer to be mapped encrypted */
-	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
-
-	while (size > 0) {
-		page = vmalloc_to_pfn((void *)pos);
-		if (remap_pfn_range(vma, start, page, PAGE_SIZE, PAGE_SHARED))
-			return -EAGAIN;
-
-		start += PAGE_SIZE;
-		pos += PAGE_SIZE;
-		if (size > PAGE_SIZE)
-			size -= PAGE_SIZE;
-		else
-			size = 0;
-	}
-
-	/* VM_IO | VM_DONTEXPAND | VM_DONTDUMP are set by remap_pfn_range() */
-	return 0;
-}
-
-/*
- * It's common for several clients to have framebuffer open simultaneously.
- * e.g. both fbcon and X. Makes things interesting.
- * Assumes caller is holding info->lock (for open and release at least)
- */
-static int udl_fb_open(struct fb_info *info, int user)
-{
-	struct udl_fbdev *ufbdev = info->par;
-	struct drm_device *dev = ufbdev->ufb.base.dev;
-	struct udl_device *udl = to_udl(dev);
-
-	/* If the USB device is gone, we don't accept new opens */
-	if (drm_dev_is_unplugged(&udl->drm))
-		return -ENODEV;
-
-	ufbdev->fb_count++;
-
-#ifdef CONFIG_DRM_FBDEV_EMULATION
-	if (fb_defio && (info->fbdefio == NULL)) {
-		/* enable defio at last moment if not disabled by client */
-
-		struct fb_deferred_io *fbdefio;
-
-		fbdefio = kzalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
-
-		if (fbdefio) {
-			fbdefio->delay = DL_DEFIO_WRITE_DELAY;
-			fbdefio->deferred_io = drm_fb_helper_deferred_io;
-		}
-
-		info->fbdefio = fbdefio;
-		fb_deferred_io_init(info);
-	}
-#endif
-
-	pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d\n",
-		  info->node, user, info, ufbdev->fb_count);
-
-	return 0;
-}
-
-
-/*
- * Assumes caller is holding info->lock mutex (for open and release at least)
- */
-static int udl_fb_release(struct fb_info *info, int user)
-{
-	struct udl_fbdev *ufbdev = info->par;
-
-	ufbdev->fb_count--;
-
-#ifdef CONFIG_DRM_FBDEV_EMULATION
-	if ((ufbdev->fb_count == 0) && (info->fbdefio)) {
-		fb_deferred_io_cleanup(info);
-		kfree(info->fbdefio);
-		info->fbdefio = NULL;
-		info->fbops->fb_mmap = udl_fb_mmap;
-	}
-#endif
-
-	pr_debug("released /dev/fb%d user=%d count=%d\n",
-		info->node, user, ufbdev->fb_count);
-
-	return 0;
-}
-
-static struct fb_ops udlfb_ops = {
-	.owner = THIS_MODULE,
-	DRM_FB_HELPER_DEFAULT_OPS,
-	.fb_fillrect = drm_fb_helper_sys_fillrect,
-	.fb_copyarea = drm_fb_helper_sys_copyarea,
-	.fb_imageblit = drm_fb_helper_sys_imageblit,
-	.fb_mmap = udl_fb_mmap,
-	.fb_open = udl_fb_open,
-	.fb_release = udl_fb_release,
-};
-
-static int udl_user_framebuffer_dirty(struct drm_framebuffer *fb,
-				      struct drm_file *file,
-				      unsigned flags, unsigned color,
-				      struct drm_clip_rect *clips,
-				      unsigned num_clips)
-{
-	struct udl_framebuffer *ufb = to_udl_fb(fb);
-	int i;
-	int ret = 0;
-
-	drm_modeset_lock_all(fb->dev);
-
-	if (!ufb->active_16)
-		goto unlock;
-
-	if (ufb->obj->base.import_attach) {
-		ret = dma_buf_begin_cpu_access(ufb->obj->base.import_attach->dmabuf,
-					       DMA_FROM_DEVICE);
-		if (ret)
-			goto unlock;
-	}
-
-	for (i = 0; i < num_clips; i++) {
-		ret = udl_handle_damage(ufb, clips[i].x1, clips[i].y1,
-				  clips[i].x2 - clips[i].x1,
-				  clips[i].y2 - clips[i].y1);
-		if (ret)
-			break;
-	}
-
-	if (ufb->obj->base.import_attach) {
-		ret = dma_buf_end_cpu_access(ufb->obj->base.import_attach->dmabuf,
-					     DMA_FROM_DEVICE);
-	}
-
- unlock:
-	drm_modeset_unlock_all(fb->dev);
-
-	return ret;
-}
-
-static void udl_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct udl_framebuffer *ufb = to_udl_fb(fb);
-
-	if (ufb->obj)
-		drm_gem_object_put_unlocked(&ufb->obj->base);
-
-	drm_framebuffer_cleanup(fb);
-	kfree(ufb);
-}
-
-static const struct drm_framebuffer_funcs udlfb_funcs = {
-	.destroy = udl_user_framebuffer_destroy,
-	.dirty = udl_user_framebuffer_dirty,
-};
-
-
-static int
-udl_framebuffer_init(struct drm_device *dev,
-		     struct udl_framebuffer *ufb,
-		     const struct drm_mode_fb_cmd2 *mode_cmd,
-		     struct udl_gem_object *obj)
-{
-	int ret;
-
-	ufb->obj = obj;
-	drm_helper_mode_fill_fb_struct(dev, &ufb->base, mode_cmd);
-	ret = drm_framebuffer_init(dev, &ufb->base, &udlfb_funcs);
-	return ret;
-}
-
-
-static int udlfb_create(struct drm_fb_helper *helper,
-			struct drm_fb_helper_surface_size *sizes)
-{
-	struct udl_fbdev *ufbdev =
-		container_of(helper, struct udl_fbdev, helper);
-	struct drm_device *dev = ufbdev->helper.dev;
-	struct fb_info *info;
-	struct drm_framebuffer *fb;
-	struct drm_mode_fb_cmd2 mode_cmd;
-	struct udl_gem_object *obj;
-	uint32_t size;
-	int ret = 0;
-
-	if (sizes->surface_bpp == 24)
-		sizes->surface_bpp = 32;
-
-	mode_cmd.width = sizes->surface_width;
-	mode_cmd.height = sizes->surface_height;
-	mode_cmd.pitches[0] = mode_cmd.width * ((sizes->surface_bpp + 7) / 8);
-
-	mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp,
-							  sizes->surface_depth);
-
-	size = mode_cmd.pitches[0] * mode_cmd.height;
-	size = ALIGN(size, PAGE_SIZE);
-
-	obj = udl_gem_alloc_object(dev, size);
-	if (!obj)
-		goto out;
-
-	ret = udl_gem_vmap(obj);
-	if (ret) {
-		DRM_ERROR("failed to vmap fb\n");
-		goto out_gfree;
-	}
-
-	info = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(info)) {
-		ret = PTR_ERR(info);
-		goto out_gfree;
-	}
-
-	ret = udl_framebuffer_init(dev, &ufbdev->ufb, &mode_cmd, obj);
-	if (ret)
-		goto out_gfree;
-
-	fb = &ufbdev->ufb.base;
-
-	ufbdev->helper.fb = fb;
-
-	info->screen_base = ufbdev->ufb.obj->vmapping;
-	info->fix.smem_len = size;
-	info->fix.smem_start = (unsigned long)ufbdev->ufb.obj->vmapping;
-
-	info->fbops = &udlfb_ops;
-	drm_fb_helper_fill_info(info, &ufbdev->helper, sizes);
-
-	DRM_DEBUG_KMS("allocated %dx%d vmal %p\n",
-		      fb->width, fb->height,
-		      ufbdev->ufb.obj->vmapping);
-
-	return ret;
-out_gfree:
-	drm_gem_object_put_unlocked(&ufbdev->ufb.obj->base);
-out:
-	return ret;
-}
-
-static const struct drm_fb_helper_funcs udl_fb_helper_funcs = {
-	.fb_probe = udlfb_create,
-};
-
-static void udl_fbdev_destroy(struct drm_device *dev,
-			      struct udl_fbdev *ufbdev)
-{
-	drm_fb_helper_unregister_fbi(&ufbdev->helper);
-	drm_fb_helper_fini(&ufbdev->helper);
-	if (ufbdev->ufb.obj) {
-		drm_framebuffer_unregister_private(&ufbdev->ufb.base);
-		drm_framebuffer_cleanup(&ufbdev->ufb.base);
-		drm_gem_object_put_unlocked(&ufbdev->ufb.obj->base);
-	}
-}
-
-int udl_fbdev_init(struct drm_device *dev)
-{
-	struct udl_device *udl = to_udl(dev);
-	int bpp_sel = fb_bpp;
-	struct udl_fbdev *ufbdev;
-	int ret;
-
-	ufbdev = kzalloc(sizeof(struct udl_fbdev), GFP_KERNEL);
-	if (!ufbdev)
-		return -ENOMEM;
-
-	udl->fbdev = ufbdev;
-
-	drm_fb_helper_prepare(dev, &ufbdev->helper, &udl_fb_helper_funcs);
-
-	ret = drm_fb_helper_init(dev, &ufbdev->helper, 1);
-	if (ret)
-		goto free;
-
-	ret = drm_fb_helper_single_add_all_connectors(&ufbdev->helper);
-	if (ret)
-		goto fini;
-
-	/* disable all the possible outputs/crtcs before entering KMS mode */
-	drm_helper_disable_unused_functions(dev);
-
-	ret = drm_fb_helper_initial_config(&ufbdev->helper, bpp_sel);
-	if (ret)
-		goto fini;
-
-	return 0;
-
-fini:
-	drm_fb_helper_fini(&ufbdev->helper);
-free:
-	kfree(ufbdev);
-	return ret;
-}
-
-void udl_fbdev_cleanup(struct drm_device *dev)
-{
-	struct udl_device *udl = to_udl(dev);
-	if (!udl->fbdev)
-		return;
-
-	udl_fbdev_destroy(dev, udl->fbdev);
-	kfree(udl->fbdev);
-	udl->fbdev = NULL;
-}
-
-void udl_fbdev_unplug(struct drm_device *dev)
-{
-	struct udl_device *udl = to_udl(dev);
-	struct udl_fbdev *ufbdev;
-	if (!udl->fbdev)
-		return;
-
-	ufbdev = udl->fbdev;
-	drm_fb_helper_unlink_fbi(&ufbdev->helper);
-}
-
-struct drm_framebuffer *
-udl_fb_user_fb_create(struct drm_device *dev,
-		   struct drm_file *file,
-		   const struct drm_mode_fb_cmd2 *mode_cmd)
-{
-	struct drm_gem_object *obj;
-	struct udl_framebuffer *ufb;
-	int ret;
-	uint32_t size;
-
-	obj = drm_gem_object_lookup(file, mode_cmd->handles[0]);
-	if (obj == NULL)
-		return ERR_PTR(-ENOENT);
-
-	size = mode_cmd->pitches[0] * mode_cmd->height;
-	size = ALIGN(size, PAGE_SIZE);
-
-	if (size > obj->size) {
-		DRM_ERROR("object size not sufficient for fb %d %zu %d %d\n", size, obj->size, mode_cmd->pitches[0], mode_cmd->height);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	ufb = kzalloc(sizeof(*ufb), GFP_KERNEL);
-	if (ufb == NULL)
-		return ERR_PTR(-ENOMEM);
-
-	ret = udl_framebuffer_init(dev, ufb, mode_cmd, to_udl_bo(obj));
-	if (ret) {
-		kfree(ufb);
-		return ERR_PTR(-EINVAL);
-	}
-	return &ufb->base;
-}
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index b23a5c2fcd80..b6e26f98aa0a 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -6,226 +6,101 @@
 #include <linux/dma-buf.h>
 #include <linux/vmalloc.h>
 
+#include <drm/drm_drv.h>
+#include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_mode.h>
 #include <drm/drm_prime.h>
 
 #include "udl_drv.h"
 
-struct udl_gem_object *udl_gem_alloc_object(struct drm_device *dev,
-					    size_t size)
-{
-	struct udl_gem_object *obj;
-
-	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
-	if (obj == NULL)
-		return NULL;
-
-	if (drm_gem_object_init(dev, &obj->base, size) != 0) {
-		kfree(obj);
-		return NULL;
-	}
-
-	obj->flags = UDL_BO_CACHEABLE;
-	return obj;
-}
-
-static int
-udl_gem_create(struct drm_file *file,
-	       struct drm_device *dev,
-	       uint64_t size,
-	       uint32_t *handle_p)
-{
-	struct udl_gem_object *obj;
-	int ret;
-	u32 handle;
-
-	size = roundup(size, PAGE_SIZE);
-
-	obj = udl_gem_alloc_object(dev, size);
-	if (obj == NULL)
-		return -ENOMEM;
-
-	ret = drm_gem_handle_create(file, &obj->base, &handle);
-	if (ret) {
-		drm_gem_object_release(&obj->base);
-		kfree(obj);
-		return ret;
-	}
-
-	drm_gem_object_put_unlocked(&obj->base);
-	*handle_p = handle;
-	return 0;
-}
-
-static void update_vm_cache_attr(struct udl_gem_object *obj,
-				 struct vm_area_struct *vma)
-{
-	DRM_DEBUG_KMS("flags = 0x%x\n", obj->flags);
-
-	/* non-cacheable as default. */
-	if (obj->flags & UDL_BO_CACHEABLE) {
-		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
-	} else if (obj->flags & UDL_BO_WC) {
-		vma->vm_page_prot =
-			pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
-	} else {
-		vma->vm_page_prot =
-			pgprot_noncached(vm_get_page_prot(vma->vm_flags));
-	}
-}
-
-int udl_dumb_create(struct drm_file *file,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args)
-{
-	args->pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
-	args->size = args->pitch * args->height;
-	return udl_gem_create(file, dev,
-			      args->size, &args->handle);
-}
+/*
+ * GEM object funcs
+ */
 
-int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+static int udl_gem_object_mmap(struct drm_gem_object *obj,
+			       struct vm_area_struct *vma)
 {
 	int ret;
 
-	ret = drm_gem_mmap(filp, vma);
+	ret = drm_gem_shmem_mmap(obj, vma);
 	if (ret)
 		return ret;
 
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP;
-
-	update_vm_cache_attr(to_udl_bo(vma->vm_private_data), vma);
-
-	return ret;
-}
-
-vm_fault_t udl_gem_fault(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-	struct udl_gem_object *obj = to_udl_bo(vma->vm_private_data);
-	struct page *page;
-	unsigned int page_offset;
-
-	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
-
-	if (!obj->pages)
-		return VM_FAULT_SIGBUS;
-
-	page = obj->pages[page_offset];
-	return vmf_insert_page(vma, vmf->address, page);
-}
-
-int udl_gem_get_pages(struct udl_gem_object *obj)
-{
-	struct page **pages;
-
-	if (obj->pages)
-		return 0;
-
-	pages = drm_gem_get_pages(&obj->base);
-	if (IS_ERR(pages))
-		return PTR_ERR(pages);
-
-	obj->pages = pages;
+	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
+	if (obj->import_attach)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
 
 	return 0;
 }
 
-void udl_gem_put_pages(struct udl_gem_object *obj)
-{
-	if (obj->base.import_attach) {
-		kvfree(obj->pages);
-		obj->pages = NULL;
-		return;
-	}
-
-	drm_gem_put_pages(&obj->base, obj->pages, false, false);
-	obj->pages = NULL;
-}
-
-int udl_gem_vmap(struct udl_gem_object *obj)
+static void *udl_gem_object_vmap(struct drm_gem_object *obj)
 {
-	int page_count = obj->base.size / PAGE_SIZE;
+	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 	int ret;
 
-	if (obj->base.import_attach) {
-		obj->vmapping = dma_buf_vmap(obj->base.import_attach->dmabuf);
-		if (!obj->vmapping)
-			return -ENOMEM;
-		return 0;
-	}
-		
-	ret = udl_gem_get_pages(obj);
+	ret = mutex_lock_interruptible(&shmem->vmap_lock);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
-	obj->vmapping = vmap(obj->pages, page_count, 0, PAGE_KERNEL);
-	if (!obj->vmapping)
-		return -ENOMEM;
-	return 0;
-}
+	if (shmem->vmap_use_count++ > 0)
+		goto out;
 
-void udl_gem_vunmap(struct udl_gem_object *obj)
-{
-	if (obj->base.import_attach) {
-		dma_buf_vunmap(obj->base.import_attach->dmabuf, obj->vmapping);
-		return;
+	ret = drm_gem_shmem_get_pages(shmem);
+	if (ret)
+		goto err_zero_use;
+
+	if (obj->import_attach)
+		shmem->vaddr = dma_buf_vmap(obj->import_attach->dmabuf);
+	else
+		shmem->vaddr = vmap(shmem->pages, obj->size >> PAGE_SHIFT,
+				    VM_MAP, PAGE_KERNEL);
+
+	if (!shmem->vaddr) {
+		DRM_DEBUG_KMS("Failed to vmap pages\n");
+		ret = -ENOMEM;
+		goto err_put_pages;
 	}
 
-	vunmap(obj->vmapping);
-
-	udl_gem_put_pages(obj);
+out:
+	mutex_unlock(&shmem->vmap_lock);
+	return shmem->vaddr;
+
+err_put_pages:
+	drm_gem_shmem_put_pages(shmem);
+err_zero_use:
+	shmem->vmap_use_count = 0;
+	mutex_unlock(&shmem->vmap_lock);
+	return ERR_PTR(ret);
 }
 
-void udl_gem_free_object(struct drm_gem_object *gem_obj)
-{
-	struct udl_gem_object *obj = to_udl_bo(gem_obj);
+static const struct drm_gem_object_funcs udl_gem_object_funcs = {
+	.free = drm_gem_shmem_free_object,
+	.print_info = drm_gem_shmem_print_info,
+	.pin = drm_gem_shmem_pin,
+	.unpin = drm_gem_shmem_unpin,
+	.get_sg_table = drm_gem_shmem_get_sg_table,
+	.vmap = udl_gem_object_vmap,
+	.vunmap = drm_gem_shmem_vunmap,
+	.mmap = udl_gem_object_mmap,
+};
 
-	if (obj->vmapping)
-		udl_gem_vunmap(obj);
-
-	if (gem_obj->import_attach) {
-		drm_prime_gem_destroy(gem_obj, obj->sg);
-		put_device(gem_obj->dev->dev);
-	}
-
-	if (obj->pages)
-		udl_gem_put_pages(obj);
-
-	drm_gem_free_mmap_offset(gem_obj);
-}
+/*
+ * Helpers for struct drm_driver
+ */
 
-/* the dumb interface doesn't work with the GEM straight MMAP
-   interface, it expects to do MMAP on the drm fd, like normal */
-int udl_gem_mmap(struct drm_file *file, struct drm_device *dev,
-		 uint32_t handle, uint64_t *offset)
+struct drm_gem_object *udl_driver_gem_create_object(struct drm_device *dev,
+						    size_t size)
 {
-	struct udl_gem_object *gobj;
+	struct drm_gem_shmem_object *shmem;
 	struct drm_gem_object *obj;
-	struct udl_device *udl = to_udl(dev);
-	int ret = 0;
-
-	mutex_lock(&udl->gem_lock);
-	obj = drm_gem_object_lookup(file, handle);
-	if (obj == NULL) {
-		ret = -ENOENT;
-		goto unlock;
-	}
-	gobj = to_udl_bo(obj);
 
-	ret = udl_gem_get_pages(gobj);
-	if (ret)
-		goto out;
-	ret = drm_gem_create_mmap_offset(obj);
-	if (ret)
-		goto out;
+	shmem = kzalloc(sizeof(*shmem), GFP_KERNEL);
+	if (!shmem)
+		return NULL;
 
-	*offset = drm_vma_node_offset_addr(&gobj->base.vma_node);
+	obj = &shmem->base;
+	obj->funcs = &udl_gem_object_funcs;
 
-out:
-	drm_gem_object_put_unlocked(&gobj->base);
-unlock:
-	mutex_unlock(&udl->gem_lock);
-	return ret;
+	return obj;
 }
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 4e854e017390..538718919916 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -140,7 +140,6 @@ void udl_urb_completion(struct urb *urb)
 		    urb->status == -ESHUTDOWN)) {
 			DRM_ERROR("%s - nonzero write bulk status received: %d\n",
 				__func__, urb->status);
-			atomic_set(&udl->lost_pixels, 1);
 		}
 	}
 
@@ -271,7 +270,6 @@ struct urb *udl_get_urb(struct drm_device *dev)
 	/* Wait for an in-flight buffer to complete and get re-queued */
 	ret = down_timeout(&udl->urbs.limit_sem, GET_URB_TIMEOUT);
 	if (ret) {
-		atomic_set(&udl->lost_pixels, 1);
 		DRM_INFO("wait for urb interrupted: %x available: %d\n",
 		       ret, udl->urbs.available);
 		goto error;
@@ -304,7 +302,6 @@ int udl_submit_urb(struct drm_device *dev, struct urb *urb, size_t len)
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
 	if (ret) {
 		udl_urb_completion(urb); /* because no one else will */
-		atomic_set(&udl->lost_pixels, 1);
 		DRM_ERROR("usb_submit_urb error %x\n", ret);
 	}
 	return ret;
@@ -338,10 +335,6 @@ int udl_init(struct udl_device *udl)
 	if (ret)
 		goto err;
 
-	ret = udl_fbdev_init(dev);
-	if (ret)
-		goto err;
-
 	drm_kms_helper_poll_init(dev);
 
 	return 0;
@@ -367,6 +360,4 @@ void udl_fini(struct drm_device *dev)
 
 	if (udl->urbs.count)
 		udl_free_urb_list(dev);
-
-	udl_fbdev_cleanup(dev);
 }
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index bc1ab6060dc6..22af17959053 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -9,12 +9,21 @@
 
  */
 
+#include <linux/dma-buf.h>
+
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_modeset_helper_vtables.h>
 #include <drm/drm_vblank.h>
 
 #include "udl_drv.h"
 
+#define UDL_COLOR_DEPTH_16BPP	0
+
 /*
  * All DisplayLink bulk operations start with 0xAF, followed by specific code
  * All operations are written to buffers which then later get sent to device
@@ -38,31 +47,9 @@ static char *udl_vidreg_unlock(char *buf)
 	return udl_set_register(buf, 0xFF, 0xFF);
 }
 
-/*
- * On/Off for driving the DisplayLink framebuffer to the display
- *  0x00 H and V sync on
- *  0x01 H and V sync off (screen blank but powered)
- *  0x07 DPMS powerdown (requires modeset to come back)
- */
-static char *udl_set_blank(char *buf, int dpms_mode)
+static char *udl_set_blank_mode(char *buf, u8 mode)
 {
-	u8 reg;
-	switch (dpms_mode) {
-	case DRM_MODE_DPMS_OFF:
-		reg = 0x07;
-		break;
-	case DRM_MODE_DPMS_STANDBY:
-		reg = 0x05;
-		break;
-	case DRM_MODE_DPMS_SUSPEND:
-		reg = 0x01;
-		break;
-	case DRM_MODE_DPMS_ON:
-		reg = 0x00;
-		break;
-	}
-
-	return udl_set_register(buf, 0x1f, reg);
+	return udl_set_register(buf, UDL_REG_BLANK_MODE, mode);
 }
 
 static char *udl_set_color_depth(char *buf, u8 selection)
@@ -233,6 +220,11 @@ static int udl_crtc_write_mode_to_hw(struct drm_crtc *crtc)
 	char *buf;
 	int retval;
 
+	if (udl->mode_buf_len == 0) {
+		DRM_ERROR("No mode set\n");
+		return -EINVAL;
+	}
+
 	urb = udl_get_urb(dev);
 	if (!urb)
 		return -ENOMEM;
@@ -245,80 +237,152 @@ static int udl_crtc_write_mode_to_hw(struct drm_crtc *crtc)
 	return retval;
 }
 
+static long udl_log_cpp(unsigned int cpp)
+{
+	if (WARN_ON(!is_power_of_2(cpp)))
+		return -EINVAL;
+	return __ffs(cpp);
+}
 
-static void udl_crtc_dpms(struct drm_crtc *crtc, int mode)
+static int udl_aligned_damage_clip(struct drm_rect *clip, int x, int y,
+				   int width, int height)
 {
-	struct drm_device *dev = crtc->dev;
-	struct udl_device *udl = dev->dev_private;
-	int retval;
+	int x1, x2;
 
-	if (mode == DRM_MODE_DPMS_OFF) {
-		char *buf;
-		struct urb *urb;
-		urb = udl_get_urb(dev);
-		if (!urb)
-			return;
-
-		buf = (char *)urb->transfer_buffer;
-		buf = udl_vidreg_lock(buf);
-		buf = udl_set_blank(buf, mode);
-		buf = udl_vidreg_unlock(buf);
-
-		buf = udl_dummy_render(buf);
-		retval = udl_submit_urb(dev, urb, buf - (char *)
-					urb->transfer_buffer);
-	} else {
-		if (udl->mode_buf_len == 0) {
-			DRM_ERROR("Trying to enable DPMS with no mode\n");
-			return;
-		}
-		udl_crtc_write_mode_to_hw(crtc);
-	}
+	if (WARN_ON_ONCE(x < 0) ||
+	    WARN_ON_ONCE(y < 0) ||
+	    WARN_ON_ONCE(width < 0) ||
+	    WARN_ON_ONCE(height < 0))
+		return -EINVAL;
 
-}
+	x1 = ALIGN_DOWN(x, sizeof(unsigned long));
+	x2 = ALIGN(width + (x - x1), sizeof(unsigned long)) + x1;
+
+	clip->x1 = x1;
+	clip->y1 = y;
+	clip->x2 = x2;
+	clip->y2 = y + height;
 
-#if 0
-static int
-udl_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
-			   int x, int y, enum mode_set_atomic state)
-{
 	return 0;
 }
 
-static int
-udl_pipe_set_base(struct drm_crtc *crtc, int x, int y,
-		    struct drm_framebuffer *old_fb)
+int udl_handle_damage(struct drm_framebuffer *fb, int x, int y,
+		      int width, int height)
 {
-	return 0;
+	struct drm_device *dev = fb->dev;
+	struct dma_buf_attachment *import_attach = fb->obj[0]->import_attach;
+	int i, ret, tmp_ret;
+	char *cmd;
+	struct urb *urb;
+	struct drm_rect clip;
+	int log_bpp;
+	void *vaddr;
+
+	ret = udl_log_cpp(fb->format->cpp[0]);
+	if (ret < 0)
+		return ret;
+	log_bpp = ret;
+
+	ret = udl_aligned_damage_clip(&clip, x, y, width, height);
+	if (ret)
+		return ret;
+	else if ((clip.x2 > fb->width) || (clip.y2 > fb->height))
+		return -EINVAL;
+
+	if (import_attach) {
+		ret = dma_buf_begin_cpu_access(import_attach->dmabuf,
+					       DMA_FROM_DEVICE);
+		if (ret)
+			return ret;
+	}
+
+	vaddr = drm_gem_shmem_vmap(fb->obj[0]);
+	if (IS_ERR(vaddr)) {
+		DRM_ERROR("failed to vmap fb\n");
+		goto out_dma_buf_end_cpu_access;
+	}
+
+	urb = udl_get_urb(dev);
+	if (!urb)
+		goto out_drm_gem_shmem_vunmap;
+	cmd = urb->transfer_buffer;
+
+	for (i = clip.y1; i < clip.y2; i++) {
+		const int line_offset = fb->pitches[0] * i;
+		const int byte_offset = line_offset + (clip.x1 << log_bpp);
+		const int dev_byte_offset = (fb->width * i + clip.x1) << log_bpp;
+		const int byte_width = (clip.x2 - clip.x1) << log_bpp;
+		ret = udl_render_hline(dev, log_bpp, &urb, (char *)vaddr,
+				       &cmd, byte_offset, dev_byte_offset,
+				       byte_width);
+		if (ret)
+			goto out_drm_gem_shmem_vunmap;
+	}
+
+	if (cmd > (char *)urb->transfer_buffer) {
+		/* Send partial buffer remaining before exiting */
+		int len;
+		if (cmd < (char *)urb->transfer_buffer + urb->transfer_buffer_length)
+			*cmd++ = 0xAF;
+		len = cmd - (char *)urb->transfer_buffer;
+		ret = udl_submit_urb(dev, urb, len);
+	} else {
+		udl_urb_completion(urb);
+	}
+
+	ret = 0;
+
+out_drm_gem_shmem_vunmap:
+	drm_gem_shmem_vunmap(fb->obj[0], vaddr);
+out_dma_buf_end_cpu_access:
+	if (import_attach) {
+		tmp_ret = dma_buf_end_cpu_access(import_attach->dmabuf,
+						 DMA_FROM_DEVICE);
+		if (tmp_ret && !ret)
+			ret = tmp_ret; /* only update ret if not set yet */
+	}
+
+	return ret;
 }
-#endif
 
-static int udl_crtc_mode_set(struct drm_crtc *crtc,
-			       struct drm_display_mode *mode,
-			       struct drm_display_mode *adjusted_mode,
-			       int x, int y,
-			       struct drm_framebuffer *old_fb)
+/*
+ * Simple display pipeline
+ */
 
+static const uint32_t udl_simple_display_pipe_formats[] = {
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+};
+
+static enum drm_mode_status
+udl_simple_display_pipe_mode_valid(struct drm_simple_display_pipe *pipe,
+				   const struct drm_display_mode *mode)
 {
+	return MODE_OK;
+}
+
+static void
+udl_simple_display_pipe_enable(struct drm_simple_display_pipe *pipe,
+			       struct drm_crtc_state *crtc_state,
+			       struct drm_plane_state *plane_state)
+{
+	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_device *dev = crtc->dev;
-	struct udl_framebuffer *ufb = to_udl_fb(crtc->primary->fb);
+	struct drm_framebuffer *fb = plane_state->fb;
 	struct udl_device *udl = dev->dev_private;
+	struct drm_display_mode *mode = &crtc_state->mode;
 	char *buf;
 	char *wrptr;
-	int color_depth = 0;
+	int color_depth = UDL_COLOR_DEPTH_16BPP;
 
-	udl->crtc = crtc;
+	crtc_state->no_vblank = true;
 
 	buf = (char *)udl->mode_buf;
 
-	/* for now we just clip 24 -> 16 - if we fix that fix this */
-	/*if  (crtc->fb->bits_per_pixel != 16)
-	  color_depth = 1; */
-
 	/* This first section has to do with setting the base address on the
-	* controller * associated with the display. There are 2 base
-	* pointers, currently, we only * use the 16 bpp segment.
-	*/
+	 * controller associated with the display. There are 2 base
+	 * pointers, currently, we only use the 16 bpp segment.
+	 */
 	wrptr = udl_vidreg_lock(buf);
 	wrptr = udl_set_color_depth(wrptr, color_depth);
 	/* set base for 16bpp segment to 0 */
@@ -326,108 +390,95 @@ static int udl_crtc_mode_set(struct drm_crtc *crtc,
 	/* set base for 8bpp segment to end of fb */
 	wrptr = udl_set_base8bpp(wrptr, 2 * mode->vdisplay * mode->hdisplay);
 
-	wrptr = udl_set_vid_cmds(wrptr, adjusted_mode);
-	wrptr = udl_set_blank(wrptr, DRM_MODE_DPMS_ON);
+	wrptr = udl_set_vid_cmds(wrptr, mode);
+	wrptr = udl_set_blank_mode(wrptr, UDL_BLANK_MODE_ON);
 	wrptr = udl_vidreg_unlock(wrptr);
 
 	wrptr = udl_dummy_render(wrptr);
 
-	if (old_fb) {
-		struct udl_framebuffer *uold_fb = to_udl_fb(old_fb);
-		uold_fb->active_16 = false;
-	}
-	ufb->active_16 = true;
 	udl->mode_buf_len = wrptr - buf;
 
-	/* damage all of it */
-	udl_handle_damage(ufb, 0, 0, ufb->base.width, ufb->base.height);
-	return 0;
-}
-
+	udl_handle_damage(fb, 0, 0, fb->width, fb->height);
 
-static void udl_crtc_disable(struct drm_crtc *crtc)
-{
-	udl_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
-}
+	if (!crtc_state->mode_changed)
+		return;
 
-static void udl_crtc_destroy(struct drm_crtc *crtc)
-{
-	drm_crtc_cleanup(crtc);
-	kfree(crtc);
+	/* enable display */
+	udl_crtc_write_mode_to_hw(crtc);
 }
 
-static int udl_crtc_page_flip(struct drm_crtc *crtc,
-			      struct drm_framebuffer *fb,
-			      struct drm_pending_vblank_event *event,
-			      uint32_t page_flip_flags,
-			      struct drm_modeset_acquire_ctx *ctx)
+static void
+udl_simple_display_pipe_disable(struct drm_simple_display_pipe *pipe)
 {
-	struct udl_framebuffer *ufb = to_udl_fb(fb);
+	struct drm_crtc *crtc = &pipe->crtc;
 	struct drm_device *dev = crtc->dev;
+	struct urb *urb;
+	char *buf;
 
-	struct drm_framebuffer *old_fb = crtc->primary->fb;
-	if (old_fb) {
-		struct udl_framebuffer *uold_fb = to_udl_fb(old_fb);
-		uold_fb->active_16 = false;
-	}
-	ufb->active_16 = true;
-
-	udl_handle_damage(ufb, 0, 0, fb->width, fb->height);
+	urb = udl_get_urb(dev);
+	if (!urb)
+		return;
 
-	spin_lock_irq(&dev->event_lock);
-	if (event)
-		drm_crtc_send_vblank_event(crtc, event);
-	spin_unlock_irq(&dev->event_lock);
-	crtc->primary->fb = fb;
+	buf = (char *)urb->transfer_buffer;
+	buf = udl_vidreg_lock(buf);
+	buf = udl_set_blank_mode(buf, UDL_BLANK_MODE_POWERDOWN);
+	buf = udl_vidreg_unlock(buf);
+	buf = udl_dummy_render(buf);
 
-	return 0;
+	udl_submit_urb(dev, urb, buf - (char *)urb->transfer_buffer);
 }
 
-static void udl_crtc_prepare(struct drm_crtc *crtc)
+static int
+udl_simple_display_pipe_check(struct drm_simple_display_pipe *pipe,
+			      struct drm_plane_state *plane_state,
+			      struct drm_crtc_state *crtc_state)
 {
+	return 0;
 }
 
-static void udl_crtc_commit(struct drm_crtc *crtc)
+static void
+udl_simple_display_pipe_update(struct drm_simple_display_pipe *pipe,
+			       struct drm_plane_state *old_plane_state)
 {
-	udl_crtc_dpms(crtc, DRM_MODE_DPMS_ON);
-}
-
-static const struct drm_crtc_helper_funcs udl_helper_funcs = {
-	.dpms = udl_crtc_dpms,
-	.mode_set = udl_crtc_mode_set,
-	.prepare = udl_crtc_prepare,
-	.commit = udl_crtc_commit,
-	.disable = udl_crtc_disable,
-};
+	struct drm_plane_state *state = pipe->plane.state;
+	struct drm_framebuffer *fb = state->fb;
+	struct drm_rect rect;
 
-static const struct drm_crtc_funcs udl_crtc_funcs = {
-	.set_config = drm_crtc_helper_set_config,
-	.destroy = udl_crtc_destroy,
-	.page_flip = udl_crtc_page_flip,
-};
-
-static int udl_crtc_init(struct drm_device *dev)
-{
-	struct drm_crtc *crtc;
+	if (!fb)
+		return;
 
-	crtc = kzalloc(sizeof(struct drm_crtc) + sizeof(struct drm_connector *), GFP_KERNEL);
-	if (crtc == NULL)
-		return -ENOMEM;
+	if (drm_atomic_helper_damage_merged(old_plane_state, state, &rect))
+		udl_handle_damage(fb, rect.x1, rect.y1, rect.x2 - rect.x1,
+				  rect.y2 - rect.y1);
+}
 
-	drm_crtc_init(dev, crtc, &udl_crtc_funcs);
-	drm_crtc_helper_add(crtc, &udl_helper_funcs);
+static const
+struct drm_simple_display_pipe_funcs udl_simple_display_pipe_funcs = {
+	.mode_valid = udl_simple_display_pipe_mode_valid,
+	.enable = udl_simple_display_pipe_enable,
+	.disable = udl_simple_display_pipe_disable,
+	.check = udl_simple_display_pipe_check,
+	.update = udl_simple_display_pipe_update,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
+};
 
-	return 0;
-}
+/*
+ * Modesetting
+ */
 
 static const struct drm_mode_config_funcs udl_mode_funcs = {
-	.fb_create = udl_fb_user_fb_create,
-	.output_poll_changed = NULL,
+	.fb_create = drm_gem_fb_create_with_dirty,
+	.atomic_check  = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
 int udl_modeset_init(struct drm_device *dev)
 {
-	struct drm_encoder *encoder;
+	size_t format_count = ARRAY_SIZE(udl_simple_display_pipe_formats);
+	struct udl_device *udl = dev->dev_private;
+	struct drm_connector *connector;
+	int ret;
+
 	drm_mode_config_init(dev);
 
 	dev->mode_config.min_width = 640;
@@ -437,29 +488,32 @@ int udl_modeset_init(struct drm_device *dev)
 	dev->mode_config.max_height = 2048;
 
 	dev->mode_config.prefer_shadow = 0;
-	dev->mode_config.preferred_depth = 24;
+	dev->mode_config.preferred_depth = 16;
 
 	dev->mode_config.funcs = &udl_mode_funcs;
 
-	udl_crtc_init(dev);
+	connector = udl_connector_init(dev);
+	if (IS_ERR(connector)) {
+		ret = PTR_ERR(connector);
+		goto err_drm_mode_config_cleanup;
+	}
 
-	encoder = udl_encoder_init(dev);
+	format_count = ARRAY_SIZE(udl_simple_display_pipe_formats);
 
-	udl_connector_init(dev, encoder);
+	ret = drm_simple_display_pipe_init(dev, &udl->display_pipe,
+					   &udl_simple_display_pipe_funcs,
+					   udl_simple_display_pipe_formats,
+					   format_count, NULL, connector);
+	if (ret)
+		goto err_drm_mode_config_cleanup;
 
-	return 0;
-}
+	drm_mode_config_reset(dev);
 
-void udl_modeset_restore(struct drm_device *dev)
-{
-	struct udl_device *udl = dev->dev_private;
-	struct udl_framebuffer *ufb;
+	return 0;
 
-	if (!udl->crtc || !udl->crtc->primary->fb)
-		return;
-	udl_crtc_commit(udl->crtc);
-	ufb = to_udl_fb(udl->crtc->primary->fb);
-	udl_handle_damage(ufb, 0, 0, ufb->base.width, ufb->base.height);
+err_drm_mode_config_cleanup:
+	drm_mode_config_cleanup(dev);
+	return ret;
 }
 
 void udl_modeset_cleanup(struct drm_device *dev)
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index 1973a4c1e358..971927669d6b 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -212,8 +212,7 @@ static void udl_compress_hline16(
 int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset,
-		     u32 byte_width,
-		     int *ident_ptr, int *sent_ptr)
+		     u32 byte_width)
 {
 	const u8 *line_start, *line_end, *next_pixel;
 	u32 base16 = 0 + (device_byte_offset >> log_bpp) * 2;
@@ -235,12 +234,12 @@ int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 
 		if (cmd >= cmd_end) {
 			int len = cmd - (u8 *) urb->transfer_buffer;
-			if (udl_submit_urb(dev, urb, len))
-				return 1; /* lost pixels is set */
-			*sent_ptr += len;
+			int ret = udl_submit_urb(dev, urb, len);
+			if (ret)
+				return ret;
 			urb = udl_get_urb(dev);
 			if (!urb)
-				return 1; /* lost_pixels is set */
+				return -EAGAIN;
 			*urb_ptr = urb;
 			cmd = urb->transfer_buffer;
 			cmd_end = &cmd[urb->transfer_buffer_length];
@@ -251,4 +250,3 @@ int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 
 	return 0;
 }
-
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 1a07462b4528..eaa8e9682373 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -140,7 +140,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv;
-	struct drm_sched_rq *rq;
+	struct drm_gpu_scheduler *sched;
 	int i;
 
 	v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL);
@@ -150,8 +150,10 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 	v3d_priv->v3d = v3d;
 
 	for (i = 0; i < V3D_MAX_QUEUES; i++) {
-		rq = &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		drm_sched_entity_init(&v3d_priv->sched_entity[i], &rq, 1, NULL);
+		sched = &v3d->queue[i].sched;
+		drm_sched_entity_init(&v3d_priv->sched_entity[i],
+				      DRM_SCHED_PRIORITY_NORMAL, &sched,
+				      1, NULL);
 	}
 
 	file->driver_priv = v3d_priv;
diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 7c2317efd5b7..118e8a426b1a 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -22,9 +22,9 @@ config DRM_VC4
 	  our display setup.
 
 config DRM_VC4_HDMI_CEC
-       bool "Broadcom VC4 HDMI CEC Support"
-       depends on DRM_VC4
-       select CEC_CORE
-       help
+	bool "Broadcom VC4 HDMI CEC Support"
+	depends on DRM_VC4
+	select CEC_CORE
+	help
 	  Choose this option if you have a Broadcom VC4 GPU
 	  and want to use CEC.
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index c9ba83ed49b9..fd8a2eb60505 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -499,6 +499,7 @@ struct vc4_dsi {
 	struct mipi_dsi_host dsi_host;
 	struct drm_encoder *encoder;
 	struct drm_bridge *bridge;
+	struct list_head bridge_chain;
 
 	void __iomem *regs;
 
@@ -752,10 +753,19 @@ static void vc4_dsi_encoder_disable(struct drm_encoder *encoder)
 	struct vc4_dsi_encoder *vc4_encoder = to_vc4_dsi_encoder(encoder);
 	struct vc4_dsi *dsi = vc4_encoder->dsi;
 	struct device *dev = &dsi->pdev->dev;
+	struct drm_bridge *iter;
+
+	list_for_each_entry_reverse(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->disable)
+			iter->funcs->disable(iter);
+	}
 
-	drm_bridge_disable(dsi->bridge);
 	vc4_dsi_ulps(dsi, true);
-	drm_bridge_post_disable(dsi->bridge);
+
+	list_for_each_entry_from(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->post_disable)
+			iter->funcs->post_disable(iter);
+	}
 
 	clk_disable_unprepare(dsi->pll_phy_clock);
 	clk_disable_unprepare(dsi->escape_clock);
@@ -823,6 +833,7 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 	struct vc4_dsi *dsi = vc4_encoder->dsi;
 	struct device *dev = &dsi->pdev->dev;
 	bool debug_dump_regs = false;
+	struct drm_bridge *iter;
 	unsigned long hs_clock;
 	u32 ui_ns;
 	/* Minimum LP state duration in escape clock cycles. */
@@ -1055,7 +1066,10 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 
 	vc4_dsi_ulps(dsi, false);
 
-	drm_bridge_pre_enable(dsi->bridge);
+	list_for_each_entry_reverse(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->pre_enable)
+			iter->funcs->pre_enable(iter);
+	}
 
 	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
 		DSI_PORT_WRITE(DISP0_CTRL,
@@ -1072,7 +1086,10 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 			       DSI_DISP0_ENABLE);
 	}
 
-	drm_bridge_enable(dsi->bridge);
+	list_for_each_entry(iter, &dsi->bridge_chain, chain_node) {
+		if (iter->funcs->enable)
+			iter->funcs->enable(iter);
+	}
 
 	if (debug_dump_regs) {
 		struct drm_printer p = drm_info_printer(&dsi->pdev->dev);
@@ -1460,6 +1477,8 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 				       GFP_KERNEL);
 	if (!vc4_dsi_encoder)
 		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dsi->bridge_chain);
 	vc4_dsi_encoder->base.type = VC4_ENCODER_TYPE_DSI1;
 	vc4_dsi_encoder->dsi = dsi;
 	dsi->encoder = &vc4_dsi_encoder->base.base;
@@ -1610,7 +1629,7 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 	 * from our driver, since we need to sequence them within the
 	 * encoder's enable/disable paths.
 	 */
-	dsi->encoder->bridge = NULL;
+	list_splice_init(&dsi->encoder->bridge_chain, &dsi->bridge_chain);
 
 	if (dsi->port == 0)
 		vc4_debugfs_add_regset32(drm, "dsi0_regs", &dsi->regset);
@@ -1632,6 +1651,11 @@ static void vc4_dsi_unbind(struct device *dev, struct device *master,
 	if (dsi->bridge)
 		pm_runtime_disable(dev);
 
+	/*
+	 * Restore the bridge_chain so the bridge detach procedure can happen
+	 * normally.
+	 */
+	list_splice_init(&dsi->bridge_chain, &dsi->encoder->bridge_chain);
 	vc4_dsi_encoder_destroy(dsi->encoder);
 
 	if (dsi->port == 1)
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 7a06cb6e31c5..e1cfc3ccd05a 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -568,7 +568,7 @@ vc4_unlock_bo_reservations(struct drm_device *dev,
 	for (i = 0; i < exec->bo_count; i++) {
 		struct drm_gem_object *bo = &exec->bo[i]->base;
 
-		ww_mutex_unlock(&bo->resv->lock);
+		dma_resv_unlock(bo->resv);
 	}
 
 	ww_acquire_fini(acquire_ctx);
@@ -595,8 +595,7 @@ vc4_lock_bo_reservations(struct drm_device *dev,
 retry:
 	if (contended_lock != -1) {
 		bo = &exec->bo[contended_lock]->base;
-		ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
-						       acquire_ctx);
+		ret = dma_resv_lock_slow_interruptible(bo->resv, acquire_ctx);
 		if (ret) {
 			ww_acquire_done(acquire_ctx);
 			return ret;
@@ -609,19 +608,19 @@ retry:
 
 		bo = &exec->bo[i]->base;
 
-		ret = ww_mutex_lock_interruptible(&bo->resv->lock, acquire_ctx);
+		ret = dma_resv_lock_interruptible(bo->resv, acquire_ctx);
 		if (ret) {
 			int j;
 
 			for (j = 0; j < i; j++) {
 				bo = &exec->bo[j]->base;
-				ww_mutex_unlock(&bo->resv->lock);
+				dma_resv_unlock(bo->resv);
 			}
 
 			if (contended_lock != -1 && contended_lock >= i) {
 				bo = &exec->bo[contended_lock]->base;
 
-				ww_mutex_unlock(&bo->resv->lock);
+				dma_resv_unlock(bo->resv);
 			}
 
 			if (ret == -EDEADLK) {
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 1c62c6c9244b..cea18dc15f77 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -267,7 +267,8 @@ static const struct drm_connector_helper_funcs vc4_hdmi_connector_helper_funcs =
 };
 
 static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev,
-						     struct drm_encoder *encoder)
+						     struct drm_encoder *encoder,
+						     struct i2c_adapter *ddc)
 {
 	struct drm_connector *connector;
 	struct vc4_hdmi_connector *hdmi_connector;
@@ -281,8 +282,10 @@ static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev,
 
 	hdmi_connector->encoder = encoder;
 
-	drm_connector_init(dev, connector, &vc4_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(dev, connector,
+				    &vc4_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    ddc);
 	drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs);
 
 	/* Create and attach TV margin props to this connector. */
@@ -1395,7 +1398,8 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data)
 			 DRM_MODE_ENCODER_TMDS, NULL);
 	drm_encoder_helper_add(hdmi->encoder, &vc4_hdmi_encoder_helper_funcs);
 
-	hdmi->connector = vc4_hdmi_connector_init(drm, hdmi->encoder);
+	hdmi->connector =
+		vc4_hdmi_connector_init(drm, hdmi->encoder, hdmi->ddc);
 	if (IS_ERR(hdmi->connector)) {
 		ret = PTR_ERR(hdmi->connector);
 		goto err_destroy_encoder;
diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
index 3db000aacd26..551fa31629af 100644
--- a/drivers/gpu/drm/via/via_dmablit.c
+++ b/drivers/gpu/drm/via/via_dmablit.c
@@ -35,11 +35,11 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/via_drm.h>
 
 #include "via_dmablit.h"
@@ -188,8 +188,8 @@ via_free_sg_info(struct pci_dev *pdev, drm_via_sg_info_t *vsg)
 		kfree(vsg->desc_pages);
 		/* fall through */
 	case dr_via_pages_locked:
-		put_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
-					  (vsg->direction == DMA_FROM_DEVICE));
+		unpin_user_pages_dirty_lock(vsg->pages, vsg->num_pages,
+					   (vsg->direction == DMA_FROM_DEVICE));
 		/* fall through */
 	case dr_via_pages_alloc:
 		vfree(vsg->pages);
@@ -239,7 +239,7 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg,  drm_via_dmablit_t *xfer)
 	vsg->pages = vzalloc(array_size(sizeof(struct page *), vsg->num_pages));
 	if (NULL == vsg->pages)
 		return -ENOMEM;
-	ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
+	ret = pin_user_pages_fast((unsigned long)xfer->mem_addr,
 			vsg->num_pages,
 			vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
 			vsg->pages);
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index 666a16de84f9..5da38082821f 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -23,10 +23,10 @@
  */
 
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_pciids.h>
 #include <drm/via_drm.h>
 
diff --git a/drivers/gpu/drm/via/via_map.c b/drivers/gpu/drm/via/via_map.c
index 431c150df014..255c5066a939 100644
--- a/drivers/gpu/drm/via/via_map.c
+++ b/drivers/gpu/drm/via/via_map.c
@@ -22,8 +22,9 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+#include <linux/pci.h>
+
 #include <drm/drm_device.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_vblank.h>
 #include <drm/via_drm.h>
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index e622485ae826..0966208ec30d 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -43,6 +43,9 @@
 #define XRES_MAX  8192
 #define YRES_MAX  8192
 
+#define drm_connector_to_virtio_gpu_output(x) \
+	container_of(x, struct virtio_gpu_output, conn)
+
 static const struct drm_crtc_funcs virtio_gpu_crtc_funcs = {
 	.set_config             = drm_atomic_helper_set_config,
 	.destroy                = drm_crtc_cleanup,
@@ -59,7 +62,7 @@ static const struct drm_framebuffer_funcs virtio_gpu_fb_funcs = {
 	.dirty = drm_atomic_helper_dirtyfb,
 };
 
-int
+static int
 virtio_gpu_framebuffer_init(struct drm_device *dev,
 			    struct virtio_gpu_framebuffer *vgfb,
 			    const struct drm_mode_fb_cmd2 *mode_cmd,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index 8dee698c90ff..8cf27af3ad53 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -137,7 +137,7 @@ static void virtio_gpu_remove(struct virtio_device *vdev)
 
 	drm_dev_unregister(dev);
 	virtio_gpu_deinit(dev);
-	drm_put_dev(dev);
+	drm_dev_put(dev);
 }
 
 static void virtio_gpu_config_changed(struct virtio_device *vdev)
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 0b56ba005e25..7e69c06e168e 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -38,6 +38,7 @@
 #include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_ioctl.h>
 #include <drm/drm_probe_helper.h>
+#include <drm/virtgpu_drm.h>
 
 #define DRIVER_NAME "virtio_gpu"
 #define DRIVER_DESC "virtio GPU"
@@ -102,8 +103,6 @@ struct virtio_gpu_fence {
 	struct virtio_gpu_fence_driver *drv;
 	struct list_head node;
 };
-#define to_virtio_fence(x) \
-	container_of(x, struct virtio_gpu_fence, f)
 
 struct virtio_gpu_vbuffer {
 	char *buf;
@@ -134,10 +133,6 @@ struct virtio_gpu_output {
 };
 #define drm_crtc_to_virtio_gpu_output(x) \
 	container_of(x, struct virtio_gpu_output, crtc)
-#define drm_connector_to_virtio_gpu_output(x) \
-	container_of(x, struct virtio_gpu_output, conn)
-#define drm_encoder_to_virtio_gpu_output(x) \
-	container_of(x, struct virtio_gpu_output, enc)
 
 struct virtio_gpu_framebuffer {
 	struct drm_framebuffer base;
@@ -182,6 +177,9 @@ struct virtio_gpu_device {
 	struct kmem_cache *vbufs;
 	bool vqs_ready;
 
+	bool disable_notify;
+	bool pending_notify;
+
 	struct ida	resource_ida;
 
 	wait_queue_head_t resp_wq;
@@ -312,13 +310,13 @@ void virtio_gpu_cmd_submit(struct virtio_gpu_device *vgdev,
 void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev,
 					  uint32_t ctx_id,
 					  uint64_t offset, uint32_t level,
-					  struct virtio_gpu_box *box,
+					  struct drm_virtgpu_3d_box *box,
 					  struct virtio_gpu_object_array *objs,
 					  struct virtio_gpu_fence *fence);
 void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 					uint32_t ctx_id,
 					uint64_t offset, uint32_t level,
-					struct virtio_gpu_box *box,
+					struct drm_virtgpu_3d_box *box,
 					struct virtio_gpu_object_array *objs,
 					struct virtio_gpu_fence *fence);
 void
@@ -334,11 +332,10 @@ void virtio_gpu_dequeue_ctrl_func(struct work_struct *work);
 void virtio_gpu_dequeue_cursor_func(struct work_struct *work);
 void virtio_gpu_dequeue_fence_func(struct work_struct *work);
 
+void virtio_gpu_disable_notify(struct virtio_gpu_device *vgdev);
+void virtio_gpu_enable_notify(struct virtio_gpu_device *vgdev);
+
 /* virtio_gpu_display.c */
-int virtio_gpu_framebuffer_init(struct drm_device *dev,
-				struct virtio_gpu_framebuffer *vgfb,
-				const struct drm_mode_fb_cmd2 *mode_cmd,
-				struct drm_gem_object *obj);
 void virtio_gpu_modeset_init(struct virtio_gpu_device *vgdev);
 void virtio_gpu_modeset_fini(struct virtio_gpu_device *vgdev);
 
@@ -349,7 +346,6 @@ struct drm_plane *virtio_gpu_plane_init(struct virtio_gpu_device *vgdev,
 					int index);
 
 /* virtio_gpu_fence.c */
-bool virtio_fence_signaled(struct dma_fence *f);
 struct virtio_gpu_fence *virtio_gpu_fence_alloc(
 	struct virtio_gpu_device *vgdev);
 void virtio_gpu_fence_emit(struct virtio_gpu_device *vgdev,
@@ -365,18 +361,12 @@ int virtio_gpu_object_create(struct virtio_gpu_device *vgdev,
 			     struct virtio_gpu_object_params *params,
 			     struct virtio_gpu_object **bo_ptr,
 			     struct virtio_gpu_fence *fence);
-
 /* virtgpu_prime.c */
 struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
 	struct drm_device *dev, struct dma_buf_attachment *attach,
 	struct sg_table *sgt);
 
-static inline u64 virtio_gpu_object_mmap_offset(struct virtio_gpu_object *bo)
-{
-	return drm_vma_node_offset_addr(&bo->base.base.vma_node);
-}
-
-/* virgl debufs */
+/* virgl debugfs */
 int virtio_gpu_debugfs_init(struct drm_minor *minor);
 
 #endif
diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c
index a4b9881ca1d3..5b2a4146c5bd 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fence.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fence.c
@@ -27,6 +27,9 @@
 
 #include "virtgpu_drv.h"
 
+#define to_virtio_fence(x) \
+	container_of(x, struct virtio_gpu_fence, f)
+
 static const char *virtio_get_driver_name(struct dma_fence *f)
 {
 	return "virtio_gpu";
@@ -37,7 +40,7 @@ static const char *virtio_get_timeline_name(struct dma_fence *f)
 	return "controlq";
 }
 
-bool virtio_fence_signaled(struct dma_fence *f)
+static bool virtio_fence_signaled(struct dma_fence *f)
 {
 	struct virtio_gpu_fence *fence = to_virtio_fence(f);
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c
index 4c1f579edfb3..0a2b62279647 100644
--- a/drivers/gpu/drm/virtio/virtgpu_gem.c
+++ b/drivers/gpu/drm/virtio/virtgpu_gem.c
@@ -96,14 +96,12 @@ int virtio_gpu_mode_dumb_mmap(struct drm_file *file_priv,
 			      uint32_t handle, uint64_t *offset_p)
 {
 	struct drm_gem_object *gobj;
-	struct virtio_gpu_object *obj;
 
 	BUG_ON(!offset_p);
 	gobj = drm_gem_object_lookup(file_priv, handle);
 	if (gobj == NULL)
 		return -ENOENT;
-	obj = gem_to_virtio_gpu_obj(gobj);
-	*offset_p = virtio_gpu_object_mmap_offset(obj);
+	*offset_p = drm_vma_node_offset_addr(&gobj->vma_node);
 	drm_gem_object_put_unlocked(gobj);
 	return 0;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 9af1ec62434f..205ec4abae2b 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -33,17 +33,6 @@
 
 #include "virtgpu_drv.h"
 
-static void convert_to_hw_box(struct virtio_gpu_box *dst,
-			      const struct drm_virtgpu_3d_box *src)
-{
-	dst->x = cpu_to_le32(src->x);
-	dst->y = cpu_to_le32(src->y);
-	dst->z = cpu_to_le32(src->z);
-	dst->w = cpu_to_le32(src->w);
-	dst->h = cpu_to_le32(src->h);
-	dst->d = cpu_to_le32(src->d);
-}
-
 static int virtio_gpu_map_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
@@ -304,7 +293,6 @@ static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev,
 	struct virtio_gpu_fence *fence;
 	int ret;
 	u32 offset = args->offset;
-	struct virtio_gpu_box box;
 
 	if (vgdev->has_virgl_3d == false)
 		return -ENOSYS;
@@ -317,8 +305,6 @@ static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev,
 	if (ret != 0)
 		goto err_put_free;
 
-	convert_to_hw_box(&box, &args->box);
-
 	fence = virtio_gpu_fence_alloc(vgdev);
 	if (!fence) {
 		ret = -ENOMEM;
@@ -326,7 +312,7 @@ static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev,
 	}
 	virtio_gpu_cmd_transfer_from_host_3d
 		(vgdev, vfpriv->ctx_id, offset, args->level,
-		 &box, objs, fence);
+		 &args->box, objs, fence);
 	dma_fence_put(&fence->f);
 	return 0;
 
@@ -345,7 +331,6 @@ static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data,
 	struct drm_virtgpu_3d_transfer_to_host *args = data;
 	struct virtio_gpu_object_array *objs;
 	struct virtio_gpu_fence *fence;
-	struct virtio_gpu_box box;
 	int ret;
 	u32 offset = args->offset;
 
@@ -353,11 +338,10 @@ static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data,
 	if (objs == NULL)
 		return -ENOENT;
 
-	convert_to_hw_box(&box, &args->box);
 	if (!vgdev->has_virgl_3d) {
 		virtio_gpu_cmd_transfer_to_host_2d
 			(vgdev, offset,
-			 box.w, box.h, box.x, box.y,
+			 args->box.w, args->box.h, args->box.x, args->box.y,
 			 objs, NULL);
 	} else {
 		ret = virtio_gpu_array_lock_resv(objs);
@@ -372,7 +356,7 @@ static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data,
 		virtio_gpu_cmd_transfer_to_host_3d
 			(vgdev,
 			 vfpriv ? vfpriv->ctx_id : 0, offset,
-			 args->level, &box, objs, fence);
+			 args->level, &args->box, objs, fence);
 		dma_fence_put(&fence->f);
 	}
 	return 0;
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 1635a9ff4794..d1c3f5fbfee4 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -24,6 +24,7 @@
  */
 
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_damage_helper.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_plane_helper.h>
 
@@ -88,7 +89,7 @@ static int virtio_gpu_plane_atomic_check(struct drm_plane *plane,
 	struct drm_crtc_state *crtc_state;
 	int ret;
 
-	if (!state->fb || !state->crtc)
+	if (!state->fb || WARN_ON(!state->crtc))
 		return 0;
 
 	crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc);
@@ -102,15 +103,37 @@ static int virtio_gpu_plane_atomic_check(struct drm_plane *plane,
 	return ret;
 }
 
+static void virtio_gpu_update_dumb_bo(struct virtio_gpu_device *vgdev,
+				      struct drm_plane_state *state,
+				      struct drm_rect *rect)
+{
+	struct virtio_gpu_object *bo =
+		gem_to_virtio_gpu_obj(state->fb->obj[0]);
+	struct virtio_gpu_object_array *objs;
+	uint32_t w = rect->x2 - rect->x1;
+	uint32_t h = rect->y2 - rect->y1;
+	uint32_t x = rect->x1;
+	uint32_t y = rect->y1;
+	uint32_t off = x * state->fb->format->cpp[0] +
+		y * state->fb->pitches[0];
+
+	objs = virtio_gpu_array_alloc(1);
+	if (!objs)
+		return;
+	virtio_gpu_array_add_obj(objs, &bo->base.base);
+
+	virtio_gpu_cmd_transfer_to_host_2d(vgdev, off, w, h, x, y,
+					   objs, NULL);
+}
+
 static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 					    struct drm_plane_state *old_state)
 {
 	struct drm_device *dev = plane->dev;
 	struct virtio_gpu_device *vgdev = dev->dev_private;
 	struct virtio_gpu_output *output = NULL;
-	struct virtio_gpu_framebuffer *vgfb;
 	struct virtio_gpu_object *bo;
-	uint32_t handle;
+	struct drm_rect rect;
 
 	if (plane->state->crtc)
 		output = drm_crtc_to_virtio_gpu_output(plane->state->crtc);
@@ -119,47 +142,52 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 	if (WARN_ON(!output))
 		return;
 
-	if (plane->state->fb && output->enabled) {
-		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
-		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
-		handle = bo->hw_res_handle;
-		if (bo->dumb) {
-			struct virtio_gpu_object_array *objs;
-
-			objs = virtio_gpu_array_alloc(1);
-			if (!objs)
-				return;
-			virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]);
-			virtio_gpu_cmd_transfer_to_host_2d
-				(vgdev, 0,
-				 plane->state->src_w >> 16,
-				 plane->state->src_h >> 16,
-				 plane->state->src_x >> 16,
-				 plane->state->src_y >> 16,
-				 objs, NULL);
-		}
-	} else {
-		handle = 0;
+	if (!plane->state->fb || !output->enabled) {
+		DRM_DEBUG("nofb\n");
+		virtio_gpu_cmd_set_scanout(vgdev, output->index, 0,
+					   plane->state->src_w >> 16,
+					   plane->state->src_h >> 16,
+					   0, 0);
+		return;
 	}
 
-	DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n", handle,
-		  plane->state->crtc_w, plane->state->crtc_h,
-		  plane->state->crtc_x, plane->state->crtc_y,
-		  plane->state->src_w >> 16,
-		  plane->state->src_h >> 16,
-		  plane->state->src_x >> 16,
-		  plane->state->src_y >> 16);
-	virtio_gpu_cmd_set_scanout(vgdev, output->index, handle,
-				   plane->state->src_w >> 16,
-				   plane->state->src_h >> 16,
-				   plane->state->src_x >> 16,
-				   plane->state->src_y >> 16);
-	if (handle)
-		virtio_gpu_cmd_resource_flush(vgdev, handle,
-					      plane->state->src_x >> 16,
-					      plane->state->src_y >> 16,
-					      plane->state->src_w >> 16,
-					      plane->state->src_h >> 16);
+	if (!drm_atomic_helper_damage_merged(old_state, plane->state, &rect))
+		return;
+
+	virtio_gpu_disable_notify(vgdev);
+
+	bo = gem_to_virtio_gpu_obj(plane->state->fb->obj[0]);
+	if (bo->dumb)
+		virtio_gpu_update_dumb_bo(vgdev, plane->state, &rect);
+
+	if (plane->state->fb != old_state->fb ||
+	    plane->state->src_w != old_state->src_w ||
+	    plane->state->src_h != old_state->src_h ||
+	    plane->state->src_x != old_state->src_x ||
+	    plane->state->src_y != old_state->src_y) {
+		DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n",
+			  bo->hw_res_handle,
+			  plane->state->crtc_w, plane->state->crtc_h,
+			  plane->state->crtc_x, plane->state->crtc_y,
+			  plane->state->src_w >> 16,
+			  plane->state->src_h >> 16,
+			  plane->state->src_x >> 16,
+			  plane->state->src_y >> 16);
+		virtio_gpu_cmd_set_scanout(vgdev, output->index,
+					   bo->hw_res_handle,
+					   plane->state->src_w >> 16,
+					   plane->state->src_h >> 16,
+					   plane->state->src_x >> 16,
+					   plane->state->src_y >> 16);
+	}
+
+	virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle,
+				      rect.x1,
+				      rect.y1,
+				      rect.x2 - rect.x1,
+				      rect.y2 - rect.y1);
+
+	virtio_gpu_enable_notify(vgdev);
 }
 
 static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c
index 74ad3bc3ebe8..5914e79d3429 100644
--- a/drivers/gpu/drm/virtio/virtgpu_vq.c
+++ b/drivers/gpu/drm/virtio/virtgpu_vq.c
@@ -40,6 +40,17 @@
 			       + MAX_INLINE_CMD_SIZE		 \
 			       + MAX_INLINE_RESP_SIZE)
 
+static void convert_to_hw_box(struct virtio_gpu_box *dst,
+			      const struct drm_virtgpu_3d_box *src)
+{
+	dst->x = cpu_to_le32(src->x);
+	dst->y = cpu_to_le32(src->y);
+	dst->z = cpu_to_le32(src->z);
+	dst->w = cpu_to_le32(src->w);
+	dst->h = cpu_to_le32(src->h);
+	dst->d = cpu_to_le32(src->d);
+}
+
 void virtio_gpu_ctrl_ack(struct virtqueue *vq)
 {
 	struct drm_device *dev = vq->vdev->priv;
@@ -393,8 +404,12 @@ again:
 	}
 	notify = virtio_gpu_queue_ctrl_buffer_locked(vgdev, vbuf, vout);
 	spin_unlock(&vgdev->ctrlq.qlock);
-	if (notify)
-		virtqueue_notify(vgdev->ctrlq.vq);
+	if (notify) {
+		if (vgdev->disable_notify)
+			vgdev->pending_notify = true;
+		else
+			virtqueue_notify(vgdev->ctrlq.vq);
+	}
 
 	if (sgt) {
 		sg_free_table(sgt);
@@ -402,6 +417,21 @@ again:
 	}
 }
 
+void virtio_gpu_disable_notify(struct virtio_gpu_device *vgdev)
+{
+	vgdev->disable_notify = true;
+}
+
+void virtio_gpu_enable_notify(struct virtio_gpu_device *vgdev)
+{
+	vgdev->disable_notify = false;
+
+	if (!vgdev->pending_notify)
+		return;
+	vgdev->pending_notify = false;
+	virtqueue_notify(vgdev->ctrlq.vq);
+}
+
 static void virtio_gpu_queue_ctrl_buffer(struct virtio_gpu_device *vgdev,
 					 struct virtio_gpu_vbuffer *vbuf)
 {
@@ -965,7 +995,7 @@ virtio_gpu_cmd_resource_create_3d(struct virtio_gpu_device *vgdev,
 void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 					uint32_t ctx_id,
 					uint64_t offset, uint32_t level,
-					struct virtio_gpu_box *box,
+					struct drm_virtgpu_3d_box *box,
 					struct virtio_gpu_object_array *objs,
 					struct virtio_gpu_fence *fence)
 {
@@ -987,7 +1017,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 	cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D);
 	cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id);
 	cmd_p->resource_id = cpu_to_le32(bo->hw_res_handle);
-	cmd_p->box = *box;
+	convert_to_hw_box(&cmd_p->box, box);
 	cmd_p->offset = cpu_to_le64(offset);
 	cmd_p->level = cpu_to_le32(level);
 
@@ -997,7 +1027,7 @@ void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev,
 void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev,
 					  uint32_t ctx_id,
 					  uint64_t offset, uint32_t level,
-					  struct virtio_gpu_box *box,
+					  struct drm_virtgpu_3d_box *box,
 					  struct virtio_gpu_object_array *objs,
 					  struct virtio_gpu_fence *fence)
 {
@@ -1013,7 +1043,7 @@ void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev,
 	cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_FROM_HOST_3D);
 	cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id);
 	cmd_p->resource_id = cpu_to_le32(bo->hw_res_handle);
-	cmd_p->box = *box;
+	convert_to_hw_box(&cmd_p->box, box);
 	cmd_p->offset = cpu_to_le64(offset);
 	cmd_p->level = cpu_to_le32(level);
 
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index d5585695c64d..4af2f19480f4 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -43,18 +43,18 @@ static uint32_t compute_crc(void *vaddr_out, struct vkms_composer *composer)
 }
 
 /**
- * blend - belnd value at vaddr_src with value at vaddr_dst
+ * blend - blend value at vaddr_src with value at vaddr_dst
  * @vaddr_dst: destination address
  * @vaddr_src: source address
  * @dest_composer: destination framebuffer's metadata
  * @src_composer: source framebuffer's metadata
  *
  * Blend value at vaddr_src with value at vaddr_dst.
- * Currently, this function write value at vaddr_src on value
+ * Currently, this function write value of vaddr_src on value
  * at vaddr_dst using buffer's metadata to locate the new values
- * from vaddr_src and their distenation at vaddr_dst.
+ * from vaddr_src and their destination at vaddr_dst.
  *
- * Todo: Use the alpha value to blend vaddr_src with vaddr_dst
+ * TODO: Use the alpha value to blend vaddr_src with vaddr_dst
  *	 instead of overwriting it.
  */
 static void blend(void *vaddr_dst, void *vaddr_src,
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index d1fe144aa289..25bd7519295f 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -3,10 +3,10 @@
 /**
  * DOC: vkms (Virtual Kernel Modesetting)
  *
- * vkms is a software-only model of a kms driver that is useful for testing,
- * or for running X (or similar) on headless machines and be able to still
- * use the GPU. vkms aims to enable a virtual display without the need for
- * a hardware display capability.
+ * VKMS is a software-only model of a KMS driver that is useful for testing
+ * and for running X (or similar) on headless machines. VKMS aims to enable
+ * a virtual display with no need of a hardware display capability, releasing
+ * the GPU in DRM API tests.
  */
 
 #include <linux/module.h>
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index 4ac55fc2bf97..44d858ce4ce7 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -209,8 +209,10 @@ int vmw_cmdbuf_res_add(struct vmw_cmdbuf_res_manager *man,
 
 	cres->hash.key = user_key | (res_type << 24);
 	ret = drm_ht_insert_item(&man->resources, &cres->hash);
-	if (unlikely(ret != 0))
+	if (unlikely(ret != 0)) {
+		kfree(cres);
 		goto out_invalid_key;
+	}
 
 	cres->state = VMW_CMDBUF_RES_ADD;
 	cres->res = vmw_resource_reference(res);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index e962048f65d2..827458f49112 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -28,10 +28,10 @@
 #include <linux/console.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_ioctl.h>
-#include <drm/drm_pci.h>
 #include <drm/drm_sysfs.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_module.h>
@@ -150,6 +150,9 @@
 #define DRM_IOCTL_VMW_GB_SURFACE_REF_EXT				\
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_REF_EXT,		\
 		union drm_vmw_gb_surface_reference_ext_arg)
+#define DRM_IOCTL_VMW_MSG						\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_MSG,			\
+		struct drm_vmw_msg_arg)
 
 /**
  * The core DRM version of this macro doesn't account for
@@ -165,9 +168,9 @@
 
 static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CURSOR_BYPASS,
@@ -182,16 +185,16 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 		      DRM_MASTER),
 
 	VMW_IOCTL_DEF(VMW_CREATE_CONTEXT, vmw_context_define_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_UNREF_CONTEXT, vmw_context_destroy_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CREATE_SURFACE, vmw_surface_define_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_UNREF_SURFACE, vmw_surface_destroy_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_REF_SURFACE, vmw_surface_reference_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_EXECBUF, vmw_execbuf_ioctl, DRM_AUTH |
+		      DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_EXECBUF, vmw_execbuf_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_FENCE_WAIT, vmw_fence_obj_wait_ioctl,
 		      DRM_RENDER_ALLOW),
@@ -201,9 +204,9 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_FENCE_UNREF, vmw_fence_obj_unref_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_FENCE_EVENT, vmw_fence_event_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_GET_3D_CAP, vmw_get_cap_3d_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 
 	/* these allow direct access to the framebuffers mark as master only */
 	VMW_IOCTL_DEF(VMW_PRESENT, vmw_present_ioctl,
@@ -221,28 +224,31 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CREATE_SHADER,
 		      vmw_shader_define_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_UNREF_SHADER,
 		      vmw_shader_destroy_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE,
 		      vmw_gb_surface_define_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF,
 		      vmw_gb_surface_reference_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_SYNCCPU,
 		      vmw_user_bo_synccpu_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT,
 		      vmw_extended_context_define_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE_EXT,
 		      vmw_gb_surface_define_ext_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF_EXT,
 		      vmw_gb_surface_reference_ext_ioctl,
-		      DRM_AUTH | DRM_RENDER_ALLOW),
+		      DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_MSG,
+		      vmw_msg_ioctl,
+		      DRM_RENDER_ALLOW),
 };
 
 static const struct pci_device_id vmw_pci_id_list[] = {
@@ -1211,8 +1217,10 @@ static void vmw_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
+	drm_dev_unregister(dev);
+	vmw_driver_unload(dev);
+	drm_dev_put(dev);
 	pci_disable_device(pdev);
-	drm_put_dev(dev);
 }
 
 static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val,
@@ -1391,8 +1399,6 @@ static const struct file_operations vmwgfx_driver_fops = {
 static struct drm_driver driver = {
 	.driver_features =
 	DRIVER_MODESET | DRIVER_RENDER | DRIVER_ATOMIC,
-	.load = vmw_driver_load,
-	.unload = vmw_driver_unload,
 	.get_vblank_counter = vmw_get_vblank_counter,
 	.enable_vblank = vmw_enable_vblank,
 	.disable_vblank = vmw_disable_vblank,
@@ -1431,7 +1437,39 @@ static struct pci_driver vmw_pci_driver = {
 
 static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
-	return drm_get_pci_dev(pdev, ent, &driver);
+	struct drm_device *dev;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	dev = drm_dev_alloc(&driver, &pdev->dev);
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_pci_disable_device;
+	}
+
+	dev->pdev = pdev;
+	pci_set_drvdata(pdev, dev);
+
+	ret = vmw_driver_load(dev, ent->driver_data);
+	if (ret)
+		goto err_drm_dev_put;
+
+	ret = drm_dev_register(dev, ent->driver_data);
+	if (ret)
+		goto err_vmw_driver_unload;
+
+	return 0;
+
+err_vmw_driver_unload:
+	vmw_driver_unload(dev);
+err_drm_dev_put:
+	drm_dev_put(dev);
+err_pci_disable_device:
+	pci_disable_device(pdev);
+	return ret;
 }
 
 static int __init vmwgfx_init(void)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a31e726d6d71..86b69397d166 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -56,9 +56,9 @@
 
 
 #define VMWGFX_DRIVER_NAME "vmwgfx"
-#define VMWGFX_DRIVER_DATE "20190328"
+#define VMWGFX_DRIVER_DATE "20200114"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 16
+#define VMWGFX_DRIVER_MINOR 17
 #define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
 #define VMWGFX_MAX_RELOCATIONS 2048
@@ -1403,6 +1403,8 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 int vmw_host_get_guestinfo(const char *guest_info_param,
 			   char *buffer, size_t *length);
 int vmw_host_log(const char *log);
+int vmw_msg_ioctl(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv);
 
 /* VMW logging */
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 934ad7c0c342..73489a45decb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2377,9 +2377,12 @@ static int vmw_cmd_dx_clear_rendertarget_view(struct vmw_private *dev_priv,
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXClearRenderTargetView) =
 		container_of(header, typeof(*cmd), header);
+	struct vmw_resource *ret;
 
-	return PTR_RET(vmw_view_id_val_add(sw_context, vmw_view_rt,
-					   cmd->body.renderTargetViewId));
+	ret = vmw_view_id_val_add(sw_context, vmw_view_rt,
+				  cmd->body.renderTargetViewId);
+
+	return PTR_ERR_OR_ZERO(ret);
 }
 
 /**
@@ -2396,9 +2399,12 @@ static int vmw_cmd_dx_clear_depthstencil_view(struct vmw_private *dev_priv,
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXClearDepthStencilView) =
 		container_of(header, typeof(*cmd), header);
+	struct vmw_resource *ret;
+
+	ret = vmw_view_id_val_add(sw_context, vmw_view_ds,
+				  cmd->body.depthStencilViewId);
 
-	return PTR_RET(vmw_view_id_val_add(sw_context, vmw_view_ds,
-					   cmd->body.depthStencilViewId));
+	return PTR_ERR_OR_ZERO(ret);
 }
 
 static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv,
@@ -2741,9 +2747,12 @@ static int vmw_cmd_dx_genmips(struct vmw_private *dev_priv,
 {
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdDXGenMips) =
 		container_of(header, typeof(*cmd), header);
+	struct vmw_resource *ret;
+
+	ret = vmw_view_id_val_add(sw_context, vmw_view_sr,
+				  cmd->body.shaderResourceViewId);
 
-	return PTR_RET(vmw_view_id_val_add(sw_context, vmw_view_sr,
-					   cmd->body.shaderResourceViewId));
+	return PTR_ERR_OR_ZERO(ret);
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index ea29953e0b08..c59806d40e15 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -624,7 +624,7 @@ out_unlock:
 }
 
 
-static struct fb_ops vmw_fb_ops = {
+static const struct fb_ops vmw_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = vmw_fb_check_var,
 	.fb_set_par = vmw_fb_set_par,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index b6c5e4c2ac3c..e9f448a5ebb3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -28,6 +28,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/hypervisor.h>
 
@@ -56,6 +57,8 @@
 
 #define HIGH_WORD(X) ((X & 0xFFFF0000) >> 16)
 
+#define MAX_USER_MSG_LENGTH	PAGE_SIZE
+
 static u32 vmw_msg_enabled = 1;
 
 enum rpc_msg_type {
@@ -148,7 +151,8 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel,
 	unsigned long si, di, eax, ebx, ecx, edx;
 	unsigned long msg_len = strlen(msg);
 
-	if (hb) {
+	/* HB port can't access encrypted memory. */
+	if (hb && !mem_encrypt_active()) {
 		unsigned long bp = channel->cookie_high;
 
 		si = (uintptr_t) msg;
@@ -202,7 +206,8 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply,
 {
 	unsigned long si, di, eax, ebx, ecx, edx;
 
-	if (hb) {
+	/* HB port can't access encrypted memory */
+	if (hb && !mem_encrypt_active()) {
 		unsigned long bp = channel->cookie_low;
 
 		si = channel->cookie_high;
@@ -514,3 +519,84 @@ out_open:
 
 	return -EINVAL;
 }
+
+
+/**
+ * vmw_msg_ioctl: Sends and receveives a message to/from host from/to user-space
+ *
+ * Sends a message from user-space to host.
+ * Can also receive a result from host and return that to user-space.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ */
+
+int vmw_msg_ioctl(struct drm_device *dev, void *data,
+		  struct drm_file *file_priv)
+{
+	struct drm_vmw_msg_arg *arg =
+		(struct drm_vmw_msg_arg *) data;
+	struct rpc_channel channel;
+	char *msg;
+	int length;
+
+	msg = kmalloc(MAX_USER_MSG_LENGTH, GFP_KERNEL);
+	if (!msg) {
+		DRM_ERROR("Cannot allocate memory for log message.\n");
+		return -ENOMEM;
+	}
+
+	length = strncpy_from_user(msg, (void __user *)((unsigned long)arg->send),
+				   MAX_USER_MSG_LENGTH);
+	if (length < 0 || length >= MAX_USER_MSG_LENGTH) {
+		DRM_ERROR("Userspace message access failure.\n");
+		kfree(msg);
+		return -EINVAL;
+	}
+
+
+	if (vmw_open_channel(&channel, RPCI_PROTOCOL_NUM)) {
+		DRM_ERROR("Failed to open channel.\n");
+		goto out_open;
+	}
+
+	if (vmw_send_msg(&channel, msg)) {
+		DRM_ERROR("Failed to send message to host.\n");
+		goto out_msg;
+	}
+
+	if (!arg->send_only) {
+		char *reply = NULL;
+		size_t reply_len = 0;
+
+		if (vmw_recv_msg(&channel, (void *) &reply, &reply_len)) {
+			DRM_ERROR("Failed to receive message from host.\n");
+			goto out_msg;
+		}
+		if (reply && reply_len > 0) {
+			if (copy_to_user((void __user *)((unsigned long)arg->receive),
+							 reply, reply_len)) {
+				DRM_ERROR("Failed to copy message to userspace.\n");
+				kfree(reply);
+				goto out_msg;
+			}
+			arg->receive_len = (__u32)reply_len;
+		}
+		kfree(reply);
+	}
+
+	vmw_close_channel(&channel);
+	kfree(msg);
+
+	return 0;
+
+out_msg:
+	vmw_close_channel(&channel);
+out_open:
+	kfree(msg);
+
+	return -EINVAL;
+}
+
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index e420675e8db3..d9552a1efd13 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -62,45 +62,12 @@ static void vmw_prime_unmap_dma_buf(struct dma_buf_attachment *attach,
 {
 }
 
-static void *vmw_prime_dmabuf_vmap(struct dma_buf *dma_buf)
-{
-	return NULL;
-}
-
-static void vmw_prime_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
-{
-}
-
-static void *vmw_prime_dmabuf_kmap(struct dma_buf *dma_buf,
-		unsigned long page_num)
-{
-	return NULL;
-}
-
-static void vmw_prime_dmabuf_kunmap(struct dma_buf *dma_buf,
-		unsigned long page_num, void *addr)
-{
-
-}
-
-static int vmw_prime_dmabuf_mmap(struct dma_buf *dma_buf,
-				 struct vm_area_struct *vma)
-{
-	WARN_ONCE(true, "Attempted use of dmabuf mmap. Bad.\n");
-	return -ENOSYS;
-}
-
 const struct dma_buf_ops vmw_prime_dmabuf_ops =  {
 	.attach = vmw_prime_map_attach,
 	.detach = vmw_prime_map_detach,
 	.map_dma_buf = vmw_prime_map_dma_buf,
 	.unmap_dma_buf = vmw_prime_unmap_dma_buf,
 	.release = NULL,
-	.map = vmw_prime_dmabuf_kmap,
-	.unmap = vmw_prime_dmabuf_kunmap,
-	.mmap = vmw_prime_dmabuf_mmap,
-	.vmap = vmw_prime_dmabuf_vmap,
-	.vunmap = vmw_prime_dmabuf_vunmap,
 };
 
 int vmw_prime_fd_to_handle(struct drm_device *dev,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 32b9131b2bae..3ce630aa4fde 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -934,16 +934,12 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 	uint32_t handle;
 	struct ttm_base_object *base;
 	int ret;
-	bool require_exist = false;
 
 	if (handle_type == DRM_VMW_HANDLE_PRIME) {
 		ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle);
 		if (unlikely(ret != 0))
 			return ret;
 	} else {
-		if (unlikely(drm_is_render_client(file_priv)))
-			require_exist = true;
-
 		handle = u_handle;
 	}
 
@@ -960,9 +956,18 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 	}
 
 	if (handle_type != DRM_VMW_HANDLE_PRIME) {
+		bool require_exist = false;
+
 		user_srf = container_of(base, struct vmw_user_surface,
 					prime.base);
 
+		/* Error out if we are unauthenticated primary */
+		if (drm_is_primary_client(file_priv) &&
+		    !file_priv->authenticated) {
+			ret = -EACCES;
+			goto out_bad_resource;
+		}
+
 		/*
 		 * Make sure the surface creator has the same
 		 * authenticating master, or is already registered with us.
@@ -971,6 +976,9 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
 		    user_srf->master != file_priv->master)
 			require_exist = true;
 
+		if (unlikely(drm_is_render_client(file_priv)))
+			require_exist = true;
+
 		ret = ttm_ref_object_add(tfile, base, TTM_REF_USAGE, NULL,
 					 require_exist);
 		if (unlikely(ret != 0)) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
index ce288756531b..aa7e50f63b94 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
@@ -45,6 +45,10 @@ int vmw_mmap(struct file *filp, struct vm_area_struct *vma)
 
 	vma->vm_ops = &vmw_vm_ops;
 
+	/* Use VM_PFNMAP rather than VM_MIXEDMAP if not a COW mapping */
+	if ((vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) != VM_MAYWRITE)
+		vma->vm_flags = (vma->vm_flags & ~VM_MIXEDMAP) | VM_PFNMAP;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c
index ff506bc99414..4f34c5208180 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_kms.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c
@@ -63,14 +63,7 @@ fb_create(struct drm_device *dev, struct drm_file *filp,
 	if (IS_ERR_OR_NULL(fb))
 		return fb;
 
-	gem_obj = drm_gem_object_lookup(filp, mode_cmd->handles[0]);
-	if (!gem_obj) {
-		DRM_ERROR("Failed to lookup GEM object\n");
-		ret = -ENOENT;
-		goto fail;
-	}
-
-	drm_gem_object_put_unlocked(gem_obj);
+	gem_obj = fb->obj[0];
 
 	ret = xen_drm_front_fb_attach(drm_info->front_info,
 				      xen_drm_front_dbuf_to_cookie(gem_obj),
diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c
index a50f5a1f09b8..b98a1420dcd3 100644
--- a/drivers/gpu/drm/zte/zx_hdmi.c
+++ b/drivers/gpu/drm/zte/zx_hdmi.c
@@ -319,8 +319,10 @@ static int zx_hdmi_register(struct drm_device *drm, struct zx_hdmi *hdmi)
 
 	hdmi->connector.polled = DRM_CONNECTOR_POLL_HPD;
 
-	drm_connector_init(drm, &hdmi->connector, &zx_hdmi_connector_funcs,
-			   DRM_MODE_CONNECTOR_HDMIA);
+	drm_connector_init_with_ddc(drm, &hdmi->connector,
+				    &zx_hdmi_connector_funcs,
+				    DRM_MODE_CONNECTOR_HDMIA,
+				    &hdmi->ddc->adap);
 	drm_connector_helper_add(&hdmi->connector,
 				 &zx_hdmi_connector_helper_funcs);
 
diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c
index 9b67e419280c..c4fa3bbaba78 100644
--- a/drivers/gpu/drm/zte/zx_vga.c
+++ b/drivers/gpu/drm/zte/zx_vga.c
@@ -165,8 +165,10 @@ static int zx_vga_register(struct drm_device *drm, struct zx_vga *vga)
 
 	vga->connector.polled = DRM_CONNECTOR_POLL_HPD;
 
-	ret = drm_connector_init(drm, connector, &zx_vga_connector_funcs,
-				 DRM_MODE_CONNECTOR_VGA);
+	ret = drm_connector_init_with_ddc(drm, connector,
+					  &zx_vga_connector_funcs,
+					  DRM_MODE_CONNECTOR_VGA,
+					  &vga->ddc->adap);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to init connector: %d\n", ret);
 		goto clean_encoder;
diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c
index 2c8559ff3481..6a995db51d6d 100644
--- a/drivers/gpu/host1x/bus.c
+++ b/drivers/gpu/host1x/bus.c
@@ -120,7 +120,7 @@ static void host1x_subdev_register(struct host1x_device *device,
 	mutex_lock(&device->clients_lock);
 	list_move_tail(&client->list, &device->clients);
 	list_move_tail(&subdev->list, &device->active);
-	client->parent = &device->dev;
+	client->host = &device->dev;
 	subdev->client = client;
 	mutex_unlock(&device->clients_lock);
 	mutex_unlock(&device->subdevs_lock);
@@ -156,7 +156,7 @@ static void __host1x_subdev_unregister(struct host1x_device *device,
 	 */
 	mutex_lock(&device->clients_lock);
 	subdev->client = NULL;
-	client->parent = NULL;
+	client->host = NULL;
 	list_move_tail(&subdev->list, &device->subdevs);
 	/*
 	 * XXX: Perhaps don't do this here, but rather explicitly remove it
@@ -710,6 +710,10 @@ int host1x_client_register(struct host1x_client *client)
 	struct host1x *host1x;
 	int err;
 
+	INIT_LIST_HEAD(&client->list);
+	mutex_init(&client->lock);
+	client->usecount = 0;
+
 	mutex_lock(&devices_lock);
 
 	list_for_each_entry(host1x, &devices, list) {
@@ -768,3 +772,74 @@ int host1x_client_unregister(struct host1x_client *client)
 	return 0;
 }
 EXPORT_SYMBOL(host1x_client_unregister);
+
+int host1x_client_suspend(struct host1x_client *client)
+{
+	int err = 0;
+
+	mutex_lock(&client->lock);
+
+	if (client->usecount == 1) {
+		if (client->ops && client->ops->suspend) {
+			err = client->ops->suspend(client);
+			if (err < 0)
+				goto unlock;
+		}
+	}
+
+	client->usecount--;
+	dev_dbg(client->dev, "use count: %u\n", client->usecount);
+
+	if (client->parent) {
+		err = host1x_client_suspend(client->parent);
+		if (err < 0)
+			goto resume;
+	}
+
+	goto unlock;
+
+resume:
+	if (client->usecount == 0)
+		if (client->ops && client->ops->resume)
+			client->ops->resume(client);
+
+	client->usecount++;
+unlock:
+	mutex_unlock(&client->lock);
+	return err;
+}
+EXPORT_SYMBOL(host1x_client_suspend);
+
+int host1x_client_resume(struct host1x_client *client)
+{
+	int err = 0;
+
+	mutex_lock(&client->lock);
+
+	if (client->parent) {
+		err = host1x_client_resume(client->parent);
+		if (err < 0)
+			goto unlock;
+	}
+
+	if (client->usecount == 0) {
+		if (client->ops && client->ops->resume) {
+			err = client->ops->resume(client);
+			if (err < 0)
+				goto suspend;
+		}
+	}
+
+	client->usecount++;
+	dev_dbg(client->dev, "use count: %u\n", client->usecount);
+
+	goto unlock;
+
+suspend:
+	if (client->parent)
+		host1x_client_suspend(client->parent);
+unlock:
+	mutex_unlock(&client->lock);
+	return err;
+}
+EXPORT_SYMBOL(host1x_client_resume);
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index a738ea55e407..388bcc2889aa 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -339,10 +339,8 @@ static int host1x_probe(struct platform_device *pdev)
 	}
 
 	syncpt_irq = platform_get_irq(pdev, 0);
-	if (syncpt_irq < 0) {
-		dev_err(&pdev->dev, "failed to get IRQ: %d\n", syncpt_irq);
+	if (syncpt_irq < 0)
 		return syncpt_irq;
-	}
 
 	mutex_init(&host->devices_lock);
 	INIT_LIST_HEAD(&host->devices);
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index 25ca54de8fc5..60b2fedd0061 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -244,8 +244,7 @@ unpin:
 
 static int do_relocs(struct host1x_job *job, struct host1x_job_gather *g)
 {
-	u32 last_page = ~0;
-	void *cmdbuf_page_addr = NULL;
+	void *cmdbuf_addr = NULL;
 	struct host1x_bo *cmdbuf = g->bo;
 	unsigned int i;
 
@@ -267,28 +266,22 @@ static int do_relocs(struct host1x_job *job, struct host1x_job_gather *g)
 			goto patch_reloc;
 		}
 
-		if (last_page != reloc->cmdbuf.offset >> PAGE_SHIFT) {
-			if (cmdbuf_page_addr)
-				host1x_bo_kunmap(cmdbuf, last_page,
-						 cmdbuf_page_addr);
+		if (!cmdbuf_addr) {
+			cmdbuf_addr = host1x_bo_mmap(cmdbuf);
 
-			cmdbuf_page_addr = host1x_bo_kmap(cmdbuf,
-					reloc->cmdbuf.offset >> PAGE_SHIFT);
-			last_page = reloc->cmdbuf.offset >> PAGE_SHIFT;
-
-			if (unlikely(!cmdbuf_page_addr)) {
+			if (unlikely(!cmdbuf_addr)) {
 				pr_err("Could not map cmdbuf for relocation\n");
 				return -ENOMEM;
 			}
 		}
 
-		target = cmdbuf_page_addr + (reloc->cmdbuf.offset & ~PAGE_MASK);
+		target = cmdbuf_addr + reloc->cmdbuf.offset;
 patch_reloc:
 		*target = reloc_addr;
 	}
 
-	if (cmdbuf_page_addr)
-		host1x_bo_kunmap(cmdbuf, last_page, cmdbuf_page_addr);
+	if (cmdbuf_addr)
+		host1x_bo_munmap(cmdbuf, cmdbuf_addr);
 
 	return 0;
 }
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index dd1cd0142941..fce7892d5137 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -421,7 +421,7 @@ int host1x_syncpt_init(struct host1x *host)
 struct host1x_syncpt *host1x_syncpt_request(struct host1x_client *client,
 					    unsigned long flags)
 {
-	struct host1x *host = dev_get_drvdata(client->parent->parent);
+	struct host1x *host = dev_get_drvdata(client->host->parent);
 
 	return host1x_syncpt_alloc(host, client, flags);
 }
diff --git a/drivers/gpu/vga/Kconfig b/drivers/gpu/vga/Kconfig
index c8c770b05ed9..1ad4c4ef0b5e 100644
--- a/drivers/gpu/vga/Kconfig
+++ b/drivers/gpu/vga/Kconfig
@@ -28,6 +28,6 @@ config VGA_SWITCHEROO
 	help
 	  Many laptops released in 2008/9/10 have two GPUs with a multiplexer
 	  to switch between them. This adds support for dynamic switching when
-          X isn't running and delayed switching until the next logoff. This
+	  X isn't running and delayed switching until the next logoff. This
 	  feature is called hybrid graphics, ATI PowerXpress, and Nvidia
 	  HybridPower.
diff --git a/drivers/hid/hid-picolcd_fb.c b/drivers/hid/hid-picolcd_fb.c
index e162a668fb7e..a549c42e8c90 100644
--- a/drivers/hid/hid-picolcd_fb.c
+++ b/drivers/hid/hid-picolcd_fb.c
@@ -417,8 +417,7 @@ static int picolcd_set_par(struct fb_info *info)
 	return 0;
 }
 
-/* Note this can't be const because of struct fb_info definition */
-static struct fb_ops picolcdfb_ops = {
+static const struct fb_ops picolcdfb_ops = {
 	.owner        = THIS_MODULE,
 	.fb_destroy   = picolcd_fb_destroy,
 	.fb_read      = fb_sys_read,
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 8eb167540b4f..0370364169c4 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -1351,6 +1351,8 @@ channel_message_table[CHANNELMSG_COUNT] = {
 	{ CHANNELMSG_19,			0, NULL },
 	{ CHANNELMSG_20,			0, NULL },
 	{ CHANNELMSG_TL_CONNECT_REQUEST,	0, NULL },
+	{ CHANNELMSG_22,			0, NULL },
+	{ CHANNELMSG_TL_CONNECT_RESULT,		0, NULL },
 };
 
 /*
@@ -1362,25 +1364,16 @@ void vmbus_onmessage(void *context)
 {
 	struct hv_message *msg = context;
 	struct vmbus_channel_message_header *hdr;
-	int size;
 
 	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
-	size = msg->header.payload_size;
 
 	trace_vmbus_on_message(hdr);
 
-	if (hdr->msgtype >= CHANNELMSG_COUNT) {
-		pr_err("Received invalid channel message type %d size %d\n",
-			   hdr->msgtype, size);
-		print_hex_dump_bytes("", DUMP_PREFIX_NONE,
-				     (unsigned char *)msg->u.payload, size);
-		return;
-	}
-
-	if (channel_message_table[hdr->msgtype].message_handler)
-		channel_message_table[hdr->msgtype].message_handler(hdr);
-	else
-		pr_err("Unhandled channel message type %d\n", hdr->msgtype);
+	/*
+	 * vmbus_on_msg_dpc() makes sure the hdr->msgtype here can not go
+	 * out of bound and the message_handler pointer can not be NULL.
+	 */
+	channel_message_table[hdr->msgtype].message_handler(hdr);
 }
 
 /*
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b155d0052981..a02ce43d778d 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -1217,10 +1217,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
 	unsigned int i, j;
 	struct page *pg;
 
-	if (num_pages < alloc_unit)
-		return 0;
-
-	for (i = 0; (i * alloc_unit) < num_pages; i++) {
+	for (i = 0; i < num_pages / alloc_unit; i++) {
 		if (bl_resp->hdr.size + sizeof(union dm_mem_page_range) >
 			HV_HYP_PAGE_SIZE)
 			return i * alloc_unit;
@@ -1258,7 +1255,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
 
 	}
 
-	return num_pages;
+	return i * alloc_unit;
 }
 
 static void balloon_up(struct work_struct *dummy)
@@ -1273,9 +1270,6 @@ static void balloon_up(struct work_struct *dummy)
 	long avail_pages;
 	unsigned long floor;
 
-	/* The host balloons pages in 2M granularity. */
-	WARN_ON_ONCE(num_pages % PAGES_IN_2M != 0);
-
 	/*
 	 * We will attempt 2M allocations. However, if we fail to
 	 * allocate 2M chunks, we will go back to PAGE_SIZE allocations.
@@ -1285,14 +1279,13 @@ static void balloon_up(struct work_struct *dummy)
 	avail_pages = si_mem_available();
 	floor = compute_balloon_floor();
 
-	/* Refuse to balloon below the floor, keep the 2M granularity. */
+	/* Refuse to balloon below the floor. */
 	if (avail_pages < num_pages || avail_pages - num_pages < floor) {
 		pr_warn("Balloon request will be partially fulfilled. %s\n",
 			avail_pages < num_pages ? "Not enough memory." :
 			"Balloon floor reached.");
 
 		num_pages = avail_pages > floor ? (avail_pages - floor) : 0;
-		num_pages -= num_pages % PAGES_IN_2M;
 	}
 
 	while (!done) {
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 08fa4a5de644..bb9ba3f7c794 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -346,9 +346,61 @@ int hv_fcopy_init(struct hv_util_service *srv)
 	return 0;
 }
 
+static void hv_fcopy_cancel_work(void)
+{
+	cancel_delayed_work_sync(&fcopy_timeout_work);
+	cancel_work_sync(&fcopy_send_work);
+}
+
+int hv_fcopy_pre_suspend(void)
+{
+	struct vmbus_channel *channel = fcopy_transaction.recv_channel;
+	struct hv_fcopy_hdr *fcopy_msg;
+
+	/*
+	 * Fake a CANCEL_FCOPY message for the user space daemon in case the
+	 * daemon is in the middle of copying some file. It doesn't matter if
+	 * there is already a message pending to be delivered to the user
+	 * space since we force fcopy_transaction.state to be HVUTIL_READY, so
+	 * the user space daemon's write() will fail with EINVAL (see
+	 * fcopy_on_msg()), and the daemon will reset the device by closing
+	 * and re-opening it.
+	 */
+	fcopy_msg = kzalloc(sizeof(*fcopy_msg), GFP_KERNEL);
+	if (!fcopy_msg)
+		return -ENOMEM;
+
+	tasklet_disable(&channel->callback_event);
+
+	fcopy_msg->operation = CANCEL_FCOPY;
+
+	hv_fcopy_cancel_work();
+
+	/* We don't care about the return value. */
+	hvutil_transport_send(hvt, fcopy_msg, sizeof(*fcopy_msg), NULL);
+
+	kfree(fcopy_msg);
+
+	fcopy_transaction.state = HVUTIL_READY;
+
+	/* tasklet_enable() will be called in hv_fcopy_pre_resume(). */
+	return 0;
+}
+
+int hv_fcopy_pre_resume(void)
+{
+	struct vmbus_channel *channel = fcopy_transaction.recv_channel;
+
+	tasklet_enable(&channel->callback_event);
+
+	return 0;
+}
+
 void hv_fcopy_deinit(void)
 {
 	fcopy_transaction.state = HVUTIL_DEVICE_DYING;
-	cancel_delayed_work_sync(&fcopy_timeout_work);
+
+	hv_fcopy_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index ae7c028dc5a8..e74b144b8f3d 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -758,11 +758,50 @@ hv_kvp_init(struct hv_util_service *srv)
 	return 0;
 }
 
-void hv_kvp_deinit(void)
+static void hv_kvp_cancel_work(void)
 {
-	kvp_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&kvp_host_handshake_work);
 	cancel_delayed_work_sync(&kvp_timeout_work);
 	cancel_work_sync(&kvp_sendkey_work);
+}
+
+int hv_kvp_pre_suspend(void)
+{
+	struct vmbus_channel *channel = kvp_transaction.recv_channel;
+
+	tasklet_disable(&channel->callback_event);
+
+	/*
+	 * If there is a pending transtion, it's unnecessary to tell the host
+	 * that the transaction will fail, because that is implied when
+	 * util_suspend() calls vmbus_close() later.
+	 */
+	hv_kvp_cancel_work();
+
+	/*
+	 * Forece the state to READY to handle the ICMSGTYPE_NEGOTIATE message
+	 * later. The user space daemon may go out of order and its write()
+	 * may fail with EINVAL: this doesn't matter since the daemon will
+	 * reset the device by closing and re-opening it.
+	 */
+	kvp_transaction.state = HVUTIL_READY;
+	return 0;
+}
+
+int hv_kvp_pre_resume(void)
+{
+	struct vmbus_channel *channel = kvp_transaction.recv_channel;
+
+	tasklet_enable(&channel->callback_event);
+
+	return 0;
+}
+
+void hv_kvp_deinit(void)
+{
+	kvp_transaction.state = HVUTIL_DEVICE_DYING;
+
+	hv_kvp_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 03b6454268b3..1c75b38f0d6d 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -379,10 +379,61 @@ hv_vss_init(struct hv_util_service *srv)
 	return 0;
 }
 
-void hv_vss_deinit(void)
+static void hv_vss_cancel_work(void)
 {
-	vss_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&vss_timeout_work);
 	cancel_work_sync(&vss_handle_request_work);
+}
+
+int hv_vss_pre_suspend(void)
+{
+	struct vmbus_channel *channel = vss_transaction.recv_channel;
+	struct hv_vss_msg *vss_msg;
+
+	/*
+	 * Fake a THAW message for the user space daemon in case the daemon
+	 * has frozen the file systems. It doesn't matter if there is already
+	 * a message pending to be delivered to the user space since we force
+	 * vss_transaction.state to be HVUTIL_READY, so the user space daemon's
+	 * write() will fail with EINVAL (see vss_on_msg()), and the daemon
+	 * will reset the device by closing and re-opening it.
+	 */
+	vss_msg = kzalloc(sizeof(*vss_msg), GFP_KERNEL);
+	if (!vss_msg)
+		return -ENOMEM;
+
+	tasklet_disable(&channel->callback_event);
+
+	vss_msg->vss_hdr.operation = VSS_OP_THAW;
+
+	/* Cancel any possible pending work. */
+	hv_vss_cancel_work();
+
+	/* We don't care about the return value. */
+	hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL);
+
+	kfree(vss_msg);
+
+	vss_transaction.state = HVUTIL_READY;
+
+	/* tasklet_enable() will be called in hv_vss_pre_resume(). */
+	return 0;
+}
+
+int hv_vss_pre_resume(void)
+{
+	struct vmbus_channel *channel = vss_transaction.recv_channel;
+
+	tasklet_enable(&channel->callback_event);
+
+	return 0;
+}
+
+void hv_vss_deinit(void)
+{
+	vss_transaction.state = HVUTIL_DEVICE_DYING;
+
+	hv_vss_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 296f9098c9e4..92ee0fe4c919 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -24,6 +24,10 @@
 
 #define SD_MAJOR	3
 #define SD_MINOR	0
+#define SD_MINOR_1	1
+#define SD_MINOR_2	2
+#define SD_VERSION_3_1	(SD_MAJOR << 16 | SD_MINOR_1)
+#define SD_VERSION_3_2	(SD_MAJOR << 16 | SD_MINOR_2)
 #define SD_VERSION	(SD_MAJOR << 16 | SD_MINOR)
 
 #define SD_MAJOR_1	1
@@ -50,8 +54,10 @@ static int sd_srv_version;
 static int ts_srv_version;
 static int hb_srv_version;
 
-#define SD_VER_COUNT 2
+#define SD_VER_COUNT 4
 static const int sd_versions[] = {
+	SD_VERSION_3_2,
+	SD_VERSION_3_1,
 	SD_VERSION,
 	SD_VERSION_1
 };
@@ -75,18 +81,56 @@ static const int fw_versions[] = {
 	UTIL_WS2K8_FW_VERSION
 };
 
+/*
+ * Send the "hibernate" udev event in a thread context.
+ */
+struct hibernate_work_context {
+	struct work_struct work;
+	struct hv_device *dev;
+};
+
+static struct hibernate_work_context hibernate_context;
+static bool hibernation_supported;
+
+static void send_hibernate_uevent(struct work_struct *work)
+{
+	char *uevent_env[2] = { "EVENT=hibernate", NULL };
+	struct hibernate_work_context *ctx;
+
+	ctx = container_of(work, struct hibernate_work_context, work);
+
+	kobject_uevent_env(&ctx->dev->device.kobj, KOBJ_CHANGE, uevent_env);
+
+	pr_info("Sent hibernation uevent\n");
+}
+
+static int hv_shutdown_init(struct hv_util_service *srv)
+{
+	struct vmbus_channel *channel = srv->channel;
+
+	INIT_WORK(&hibernate_context.work, send_hibernate_uevent);
+	hibernate_context.dev = channel->device_obj;
+
+	hibernation_supported = hv_is_hibernation_supported();
+
+	return 0;
+}
+
 static void shutdown_onchannelcallback(void *context);
 static struct hv_util_service util_shutdown = {
 	.util_cb = shutdown_onchannelcallback,
+	.util_init = hv_shutdown_init,
 };
 
 static int hv_timesync_init(struct hv_util_service *srv);
+static int hv_timesync_pre_suspend(void);
 static void hv_timesync_deinit(void);
 
 static void timesync_onchannelcallback(void *context);
 static struct hv_util_service util_timesynch = {
 	.util_cb = timesync_onchannelcallback,
 	.util_init = hv_timesync_init,
+	.util_pre_suspend = hv_timesync_pre_suspend,
 	.util_deinit = hv_timesync_deinit,
 };
 
@@ -98,18 +142,24 @@ static struct hv_util_service util_heartbeat = {
 static struct hv_util_service util_kvp = {
 	.util_cb = hv_kvp_onchannelcallback,
 	.util_init = hv_kvp_init,
+	.util_pre_suspend = hv_kvp_pre_suspend,
+	.util_pre_resume = hv_kvp_pre_resume,
 	.util_deinit = hv_kvp_deinit,
 };
 
 static struct hv_util_service util_vss = {
 	.util_cb = hv_vss_onchannelcallback,
 	.util_init = hv_vss_init,
+	.util_pre_suspend = hv_vss_pre_suspend,
+	.util_pre_resume = hv_vss_pre_resume,
 	.util_deinit = hv_vss_deinit,
 };
 
 static struct hv_util_service util_fcopy = {
 	.util_cb = hv_fcopy_onchannelcallback,
 	.util_init = hv_fcopy_init,
+	.util_pre_suspend = hv_fcopy_pre_suspend,
+	.util_pre_resume = hv_fcopy_pre_resume,
 	.util_deinit = hv_fcopy_deinit,
 };
 
@@ -118,17 +168,27 @@ static void perform_shutdown(struct work_struct *dummy)
 	orderly_poweroff(true);
 }
 
+static void perform_restart(struct work_struct *dummy)
+{
+	orderly_reboot();
+}
+
 /*
  * Perform the shutdown operation in a thread context.
  */
 static DECLARE_WORK(shutdown_work, perform_shutdown);
 
+/*
+ * Perform the restart operation in a thread context.
+ */
+static DECLARE_WORK(restart_work, perform_restart);
+
 static void shutdown_onchannelcallback(void *context)
 {
 	struct vmbus_channel *channel = context;
+	struct work_struct *work = NULL;
 	u32 recvlen;
 	u64 requestid;
-	bool execute_shutdown = false;
 	u8  *shut_txf_buf = util_shutdown.recv_buffer;
 
 	struct shutdown_msg_data *shutdown_msg;
@@ -157,19 +217,37 @@ static void shutdown_onchannelcallback(void *context)
 					sizeof(struct vmbuspipe_hdr) +
 					sizeof(struct icmsg_hdr)];
 
+			/*
+			 * shutdown_msg->flags can be 0(shut down), 2(reboot),
+			 * or 4(hibernate). It may bitwise-OR 1, which means
+			 * performing the request by force. Linux always tries
+			 * to perform the request by force.
+			 */
 			switch (shutdown_msg->flags) {
 			case 0:
 			case 1:
 				icmsghdrp->status = HV_S_OK;
-				execute_shutdown = true;
-
+				work = &shutdown_work;
 				pr_info("Shutdown request received -"
 					    " graceful shutdown initiated\n");
 				break;
+			case 2:
+			case 3:
+				icmsghdrp->status = HV_S_OK;
+				work = &restart_work;
+				pr_info("Restart request received -"
+					    " graceful restart initiated\n");
+				break;
+			case 4:
+			case 5:
+				pr_info("Hibernation request received\n");
+				icmsghdrp->status = hibernation_supported ?
+					HV_S_OK : HV_E_FAIL;
+				if (hibernation_supported)
+					work = &hibernate_context.work;
+				break;
 			default:
 				icmsghdrp->status = HV_E_FAIL;
-				execute_shutdown = false;
-
 				pr_info("Shutdown request received -"
 					    " Invalid request\n");
 				break;
@@ -184,8 +262,8 @@ static void shutdown_onchannelcallback(void *context)
 				       VM_PKT_DATA_INBAND, 0);
 	}
 
-	if (execute_shutdown == true)
-		schedule_work(&shutdown_work);
+	if (work)
+		schedule_work(work);
 }
 
 /*
@@ -441,6 +519,44 @@ static int util_remove(struct hv_device *dev)
 	return 0;
 }
 
+/*
+ * When we're in util_suspend(), all the userspace processes have been frozen
+ * (refer to hibernate() -> freeze_processes()). The userspace is thawed only
+ * after the whole resume procedure, including util_resume(), finishes.
+ */
+static int util_suspend(struct hv_device *dev)
+{
+	struct hv_util_service *srv = hv_get_drvdata(dev);
+	int ret = 0;
+
+	if (srv->util_pre_suspend) {
+		ret = srv->util_pre_suspend();
+		if (ret)
+			return ret;
+	}
+
+	vmbus_close(dev->channel);
+
+	return 0;
+}
+
+static int util_resume(struct hv_device *dev)
+{
+	struct hv_util_service *srv = hv_get_drvdata(dev);
+	int ret = 0;
+
+	if (srv->util_pre_resume) {
+		ret = srv->util_pre_resume();
+		if (ret)
+			return ret;
+	}
+
+	ret = vmbus_open(dev->channel, 4 * HV_HYP_PAGE_SIZE,
+			 4 * HV_HYP_PAGE_SIZE, NULL, 0, srv->util_cb,
+			 dev->channel);
+	return ret;
+}
+
 static const struct hv_vmbus_device_id id_table[] = {
 	/* Shutdown guid */
 	{ HV_SHUTDOWN_GUID,
@@ -477,6 +593,8 @@ static  struct hv_driver util_drv = {
 	.id_table = id_table,
 	.probe =  util_probe,
 	.remove =  util_remove,
+	.suspend = util_suspend,
+	.resume =  util_resume,
 	.driver = {
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
@@ -546,11 +664,23 @@ static int hv_timesync_init(struct hv_util_service *srv)
 	return 0;
 }
 
+static void hv_timesync_cancel_work(void)
+{
+	cancel_work_sync(&adj_time_work);
+}
+
+static int hv_timesync_pre_suspend(void)
+{
+	hv_timesync_cancel_work();
+	return 0;
+}
+
 static void hv_timesync_deinit(void)
 {
 	if (hv_ptp_clock)
 		ptp_clock_unregister(hv_ptp_clock);
-	cancel_work_sync(&adj_time_work);
+
+	hv_timesync_cancel_work();
 }
 
 static int __init init_hyperv_utils(void)
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 20edcfd3b96c..f5fa3b3c9baf 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -352,14 +352,20 @@ void vmbus_on_msg_dpc(unsigned long data);
 
 int hv_kvp_init(struct hv_util_service *srv);
 void hv_kvp_deinit(void);
+int hv_kvp_pre_suspend(void);
+int hv_kvp_pre_resume(void);
 void hv_kvp_onchannelcallback(void *context);
 
 int hv_vss_init(struct hv_util_service *srv);
 void hv_vss_deinit(void);
+int hv_vss_pre_suspend(void);
+int hv_vss_pre_resume(void);
 void hv_vss_onchannelcallback(void *context);
 
 int hv_fcopy_init(struct hv_util_service *srv);
 void hv_fcopy_deinit(void);
+int hv_fcopy_pre_suspend(void);
+int hv_fcopy_pre_resume(void);
 void hv_fcopy_onchannelcallback(void *context);
 void vmbus_initiate_unload(bool crash);
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 4ef5a66df680..029378c27421 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1033,6 +1033,10 @@ void vmbus_on_msg_dpc(unsigned long data)
 	}
 
 	entry = &channel_message_table[hdr->msgtype];
+
+	if (!entry->message_handler)
+		goto msg_handled;
+
 	if (entry->handler_type	== VMHT_BLOCKING) {
 		ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
 		if (ctx == NULL)
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 17583bf8c2dc..d4c83009d625 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -595,19 +595,18 @@ static int i8k_open_fs(struct inode *inode, struct file *file)
 	return single_open(file, i8k_proc_show, NULL);
 }
 
-static const struct file_operations i8k_fops = {
-	.owner		= THIS_MODULE,
-	.open		= i8k_open_fs,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.unlocked_ioctl	= i8k_ioctl,
+static const struct proc_ops i8k_proc_ops = {
+	.proc_open	= i8k_open_fs,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_ioctl	= i8k_ioctl,
 };
 
 static void __init i8k_init_procfs(void)
 {
 	/* Register the proc entry */
-	proc_create("i8k", 0, NULL, &i8k_fops);
+	proc_create("i8k", 0, NULL, &i8k_proc_ops);
 }
 
 static void __exit i8k_exit_procfs(void)
diff --git a/drivers/hwspinlock/omap_hwspinlock.c b/drivers/hwspinlock/omap_hwspinlock.c
index 14e1a532ebb5..3b05560456ea 100644
--- a/drivers/hwspinlock/omap_hwspinlock.c
+++ b/drivers/hwspinlock/omap_hwspinlock.c
@@ -76,7 +76,6 @@ static int omap_hwspinlock_probe(struct platform_device *pdev)
 	struct device_node *node = pdev->dev.of_node;
 	struct hwspinlock_device *bank;
 	struct hwspinlock *hwlock;
-	struct resource *res;
 	void __iomem *io_base;
 	int num_locks, i, ret;
 	/* Only a single hwspinlock block device is supported */
@@ -85,13 +84,9 @@ static int omap_hwspinlock_probe(struct platform_device *pdev)
 	if (!node)
 		return -ENODEV;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -ENODEV;
-
-	io_base = ioremap(res->start, resource_size(res));
-	if (!io_base)
-		return -ENOMEM;
+	io_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(io_base))
+		return PTR_ERR(io_base);
 
 	/*
 	 * make sure the module is enabled and clocked before reading
@@ -101,7 +96,7 @@ static int omap_hwspinlock_probe(struct platform_device *pdev)
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		pm_runtime_put_noidle(&pdev->dev);
-		goto iounmap_base;
+		goto runtime_err;
 	}
 
 	/* Determine number of locks */
@@ -114,20 +109,21 @@ static int omap_hwspinlock_probe(struct platform_device *pdev)
 	 */
 	ret = pm_runtime_put(&pdev->dev);
 	if (ret < 0)
-		goto iounmap_base;
+		goto runtime_err;
 
 	/* one of the four lsb's must be set, and nothing else */
 	if (hweight_long(i & 0xf) != 1 || i > 8) {
 		ret = -EINVAL;
-		goto iounmap_base;
+		goto runtime_err;
 	}
 
 	num_locks = i * 32; /* actual number of locks in this device */
 
-	bank = kzalloc(struct_size(bank, lock, num_locks), GFP_KERNEL);
+	bank = devm_kzalloc(&pdev->dev, struct_size(bank, lock, num_locks),
+			    GFP_KERNEL);
 	if (!bank) {
 		ret = -ENOMEM;
-		goto iounmap_base;
+		goto runtime_err;
 	}
 
 	platform_set_drvdata(pdev, bank);
@@ -138,25 +134,21 @@ static int omap_hwspinlock_probe(struct platform_device *pdev)
 	ret = hwspin_lock_register(bank, &pdev->dev, &omap_hwspinlock_ops,
 						base_id, num_locks);
 	if (ret)
-		goto reg_fail;
+		goto runtime_err;
 
 	dev_dbg(&pdev->dev, "Registered %d locks with HwSpinlock core\n",
 		num_locks);
 
 	return 0;
 
-reg_fail:
-	kfree(bank);
-iounmap_base:
+runtime_err:
 	pm_runtime_disable(&pdev->dev);
-	iounmap(io_base);
 	return ret;
 }
 
 static int omap_hwspinlock_remove(struct platform_device *pdev)
 {
 	struct hwspinlock_device *bank = platform_get_drvdata(pdev);
-	void __iomem *io_base = bank->lock[0].priv - LOCK_BASE_OFFSET;
 	int ret;
 
 	ret = hwspin_lock_unregister(bank);
@@ -166,8 +158,6 @@ static int omap_hwspinlock_remove(struct platform_device *pdev)
 	}
 
 	pm_runtime_disable(&pdev->dev);
-	iounmap(io_base);
-	kfree(bank);
 
 	return 0;
 }
diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c
index 6da7447d277d..f0da544b14d2 100644
--- a/drivers/hwspinlock/qcom_hwspinlock.c
+++ b/drivers/hwspinlock/qcom_hwspinlock.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 
 #include "hwspinlock_internal.h"
@@ -122,35 +121,12 @@ static int qcom_hwspinlock_probe(struct platform_device *pdev)
 							     regmap, field);
 	}
 
-	pm_runtime_enable(&pdev->dev);
-
-	ret = hwspin_lock_register(bank, &pdev->dev, &qcom_hwspinlock_ops,
-				   0, QCOM_MUTEX_NUM_LOCKS);
-	if (ret)
-		pm_runtime_disable(&pdev->dev);
-
-	return ret;
-}
-
-static int qcom_hwspinlock_remove(struct platform_device *pdev)
-{
-	struct hwspinlock_device *bank = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = hwspin_lock_unregister(bank);
-	if (ret) {
-		dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
-		return ret;
-	}
-
-	pm_runtime_disable(&pdev->dev);
-
-	return 0;
+	return devm_hwspin_lock_register(&pdev->dev, bank, &qcom_hwspinlock_ops,
+					 0, QCOM_MUTEX_NUM_LOCKS);
 }
 
 static struct platform_driver qcom_hwspinlock_driver = {
 	.probe		= qcom_hwspinlock_probe,
-	.remove		= qcom_hwspinlock_remove,
 	.driver		= {
 		.name	= "qcom_hwspinlock",
 		.of_match_table = qcom_hwspinlock_of_match,
diff --git a/drivers/hwspinlock/sirf_hwspinlock.c b/drivers/hwspinlock/sirf_hwspinlock.c
index 1f625cd68c50..823d3c4f621e 100644
--- a/drivers/hwspinlock/sirf_hwspinlock.c
+++ b/drivers/hwspinlock/sirf_hwspinlock.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/io.h>
-#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/hwspinlock.h>
@@ -56,7 +55,7 @@ static int sirf_hwspinlock_probe(struct platform_device *pdev)
 {
 	struct sirf_hwspinlock *hwspin;
 	struct hwspinlock *hwlock;
-	int idx, ret;
+	int idx;
 
 	if (!pdev->dev.of_node)
 		return -ENODEV;
@@ -69,9 +68,9 @@ static int sirf_hwspinlock_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	/* retrieve io base */
-	hwspin->io_base = of_iomap(pdev->dev.of_node, 0);
-	if (!hwspin->io_base)
-		return -ENOMEM;
+	hwspin->io_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(hwspin->io_base))
+		return PTR_ERR(hwspin->io_base);
 
 	for (idx = 0; idx < HW_SPINLOCK_NUMBER; idx++) {
 		hwlock = &hwspin->bank.lock[idx];
@@ -80,39 +79,9 @@ static int sirf_hwspinlock_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, hwspin);
 
-	pm_runtime_enable(&pdev->dev);
-
-	ret = hwspin_lock_register(&hwspin->bank, &pdev->dev,
-				   &sirf_hwspinlock_ops, 0,
-				   HW_SPINLOCK_NUMBER);
-	if (ret)
-		goto reg_failed;
-
-	return 0;
-
-reg_failed:
-	pm_runtime_disable(&pdev->dev);
-	iounmap(hwspin->io_base);
-
-	return ret;
-}
-
-static int sirf_hwspinlock_remove(struct platform_device *pdev)
-{
-	struct sirf_hwspinlock *hwspin = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = hwspin_lock_unregister(&hwspin->bank);
-	if (ret) {
-		dev_err(&pdev->dev, "%s failed: %d\n", __func__, ret);
-		return ret;
-	}
-
-	pm_runtime_disable(&pdev->dev);
-
-	iounmap(hwspin->io_base);
-
-	return 0;
+	return devm_hwspin_lock_register(&pdev->dev, &hwspin->bank,
+					 &sirf_hwspinlock_ops, 0,
+					 HW_SPINLOCK_NUMBER);
 }
 
 static const struct of_device_id sirf_hwpinlock_ids[] = {
@@ -123,7 +92,6 @@ MODULE_DEVICE_TABLE(of, sirf_hwpinlock_ids);
 
 static struct platform_driver sirf_hwspinlock_driver = {
 	.probe = sirf_hwspinlock_probe,
-	.remove = sirf_hwspinlock_remove,
 	.driver = {
 		.name = "atlas7_hwspinlock",
 		.of_match_table = of_match_ptr(sirf_hwpinlock_ids),
diff --git a/drivers/hwspinlock/stm32_hwspinlock.c b/drivers/hwspinlock/stm32_hwspinlock.c
index c8eacf4f9692..3ad0ce0da4d9 100644
--- a/drivers/hwspinlock/stm32_hwspinlock.c
+++ b/drivers/hwspinlock/stm32_hwspinlock.c
@@ -58,12 +58,10 @@ static int stm32_hwspinlock_probe(struct platform_device *pdev)
 {
 	struct stm32_hwspinlock *hw;
 	void __iomem *io_base;
-	struct resource *res;
 	size_t array_size;
 	int i, ret;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	io_base = devm_ioremap_resource(&pdev->dev, res);
+	io_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(io_base))
 		return PTR_ERR(io_base);
 
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index a5a95ea5b81a..febb7c7ea72b 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -901,14 +901,13 @@ mv64xxx_i2c_probe(struct platform_device *pd)
 
 	/* Not all platforms have clocks */
 	drv_data->clk = devm_clk_get(&pd->dev, NULL);
-	if (IS_ERR(drv_data->clk) && PTR_ERR(drv_data->clk) == -EPROBE_DEFER)
+	if (PTR_ERR(drv_data->clk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 	if (!IS_ERR(drv_data->clk))
 		clk_prepare_enable(drv_data->clk);
 
 	drv_data->reg_clk = devm_clk_get(&pd->dev, "reg");
-	if (IS_ERR(drv_data->reg_clk) &&
-	    PTR_ERR(drv_data->reg_clk) == -EPROBE_DEFER)
+	if (PTR_ERR(drv_data->reg_clk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 	if (!IS_ERR(drv_data->reg_clk))
 		clk_prepare_enable(drv_data->reg_clk);
diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c
index 39762f0611b1..86026798b4f7 100644
--- a/drivers/i2c/busses/i2c-synquacer.c
+++ b/drivers/i2c/busses/i2c-synquacer.c
@@ -553,7 +553,7 @@ static int synquacer_i2c_probe(struct platform_device *pdev)
 				 &i2c->pclkrate);
 
 	i2c->pclk = devm_clk_get(&pdev->dev, "pclk");
-	if (IS_ERR(i2c->pclk) && PTR_ERR(i2c->pclk) == -EPROBE_DEFER)
+	if (PTR_ERR(i2c->pclk) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 	if (!IS_ERR_OR_NULL(i2c->pclk)) {
 		dev_dbg(&pdev->dev, "clock source %p\n", i2c->pclk);
diff --git a/drivers/ide/Makefile b/drivers/ide/Makefile
index cac02db4098d..d4f4409cfb8b 100644
--- a/drivers/ide/Makefile
+++ b/drivers/ide/Makefile
@@ -3,8 +3,6 @@
 # link order is important here
 #
 
-ccflags-y				:= -Idrivers/ide
-
 ide-core-y += ide.o ide-ioctls.o ide-io.o ide-iops.o ide-lib.o ide-probe.o \
 	      ide-taskfile.o ide-pm.o ide-park.o ide-sysfs.o ide-devsets.o \
 	      ide-io-std.o ide-eh.o
diff --git a/drivers/ide/cmd64x.c b/drivers/ide/cmd64x.c
index a1898e11b04e..943bf944bf72 100644
--- a/drivers/ide/cmd64x.c
+++ b/drivers/ide/cmd64x.c
@@ -66,6 +66,9 @@ static void cmd64x_program_timings(ide_drive_t *drive, u8 mode)
 	struct ide_timing t;
 	u8 arttim = 0;
 
+	if (drive->dn >= ARRAY_SIZE(drwtim_regs))
+		return;
+
 	ide_timing_compute(drive, mode, &t, T, 0);
 
 	/*
diff --git a/drivers/ide/ht6560b.c b/drivers/ide/ht6560b.c
index 0dae65ac7d6d..743bc3693ac8 100644
--- a/drivers/ide/ht6560b.c
+++ b/drivers/ide/ht6560b.c
@@ -310,7 +310,7 @@ static void __init ht6560b_init_dev(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
 	/* Setting default configurations for drives. */
-	int t = (HT_CONFIG_DEFAULT << 8) | HT_TIMING_DEFAULT;
+	unsigned long t = (HT_CONFIG_DEFAULT << 8) | HT_TIMING_DEFAULT;
 
 	if (hwif->channel)
 		t |= (HT_SECONDARY_IF << 8);
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 9d117936bee1..dcf8b51b47fd 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -25,6 +25,7 @@
 
 #define IDECD_VERSION "5.00"
 
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
@@ -1710,6 +1711,41 @@ static int idecd_ioctl(struct block_device *bdev, fmode_t mode,
 	return ret;
 }
 
+static int idecd_locked_compat_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned int cmd, unsigned long arg)
+{
+	struct cdrom_info *info = ide_drv_g(bdev->bd_disk, cdrom_info);
+	void __user *argp = compat_ptr(arg);
+	int err;
+
+	switch (cmd) {
+	case CDROMSETSPINDOWN:
+		return idecd_set_spindown(&info->devinfo, (unsigned long)argp);
+	case CDROMGETSPINDOWN:
+		return idecd_get_spindown(&info->devinfo, (unsigned long)argp);
+	default:
+		break;
+	}
+
+	err = generic_ide_ioctl(info->drive, bdev, cmd, arg);
+	if (err == -EINVAL)
+		err = cdrom_ioctl(&info->devinfo, bdev, mode, cmd,
+				  (unsigned long)argp);
+
+	return err;
+}
+
+static int idecd_compat_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long arg)
+{
+	int ret;
+
+	mutex_lock(&ide_cd_mutex);
+	ret = idecd_locked_compat_ioctl(bdev, mode, cmd, arg);
+	mutex_unlock(&ide_cd_mutex);
+
+	return ret;
+}
 
 static unsigned int idecd_check_events(struct gendisk *disk,
 				       unsigned int clearing)
@@ -1732,6 +1768,8 @@ static const struct block_device_operations idecd_ops = {
 	.open			= idecd_open,
 	.release		= idecd_release,
 	.ioctl			= idecd_ioctl,
+	.compat_ioctl		= IS_ENABLED(CONFIG_COMPAT) ?
+				  idecd_compat_ioctl : NULL,
 	.check_events		= idecd_check_events,
 	.revalidate_disk	= idecd_revalidate_disk
 };
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 197912af5c2f..1d3407d7e095 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -794,4 +794,5 @@ const struct ide_disk_ops ide_ata_disk_ops = {
 	.set_doorlock		= ide_disk_set_doorlock,
 	.do_request		= ide_do_rw_disk,
 	.ioctl			= ide_disk_ioctl,
+	.compat_ioctl		= ide_disk_ioctl,
 };
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 1ea2f9e82bf8..1fe1f9d37a51 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/compat.h>
 #include <linux/delay.h>
 #include <linux/timer.h>
 #include <linux/mm.h>
@@ -546,4 +547,7 @@ const struct ide_disk_ops ide_atapi_disk_ops = {
 	.set_doorlock	= ide_set_media_lock,
 	.do_request	= ide_floppy_do_request,
 	.ioctl		= ide_floppy_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ide_floppy_compat_ioctl,
+#endif
 };
diff --git a/drivers/ide/ide-floppy.h b/drivers/ide/ide-floppy.h
index 13c9b4b6d75e..8505a5f58f4e 100644
--- a/drivers/ide/ide-floppy.h
+++ b/drivers/ide/ide-floppy.h
@@ -26,6 +26,8 @@ void ide_floppy_create_read_capacity_cmd(struct ide_atapi_pc *);
 /* ide-floppy_ioctl.c */
 int ide_floppy_ioctl(ide_drive_t *, struct block_device *, fmode_t,
 		     unsigned int, unsigned long);
+int ide_floppy_compat_ioctl(ide_drive_t *, struct block_device *, fmode_t,
+			    unsigned int, unsigned long);
 
 #ifdef CONFIG_IDE_PROC_FS
 /* ide-floppy_proc.c */
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index 40a2ebe34e1d..39a790ac6cc3 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -5,6 +5,7 @@
 
 #include <linux/kernel.h>
 #include <linux/ide.h>
+#include <linux/compat.h>
 #include <linux/cdrom.h>
 #include <linux/mutex.h>
 
@@ -302,3 +303,37 @@ out:
 	mutex_unlock(&ide_floppy_ioctl_mutex);
 	return err;
 }
+
+#ifdef CONFIG_COMPAT
+int ide_floppy_compat_ioctl(ide_drive_t *drive, struct block_device *bdev,
+			    fmode_t mode, unsigned int cmd, unsigned long arg)
+{
+	struct ide_atapi_pc pc;
+	void __user *argp = compat_ptr(arg);
+	int err;
+
+	mutex_lock(&ide_floppy_ioctl_mutex);
+	if (cmd == CDROMEJECT || cmd == CDROM_LOCKDOOR) {
+		err = ide_floppy_lockdoor(drive, &pc, arg, cmd);
+		goto out;
+	}
+
+	err = ide_floppy_format_ioctl(drive, &pc, mode, cmd, argp);
+	if (err != -ENOTTY)
+		goto out;
+
+	/*
+	 * skip SCSI_IOCTL_SEND_COMMAND (deprecated)
+	 * and CDROM_SEND_PACKET (legacy) ioctls
+	 */
+	if (cmd != CDROM_SEND_PACKET && cmd != SCSI_IOCTL_SEND_COMMAND)
+		err = scsi_cmd_blk_ioctl(bdev, mode, cmd, argp);
+
+	if (err == -ENOTTY)
+		err = generic_ide_ioctl(drive, bdev, cmd, arg);
+
+out:
+	mutex_unlock(&ide_floppy_ioctl_mutex);
+	return err;
+}
+#endif
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index dba9ad5c97b3..1bb99b556393 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -341,11 +341,28 @@ static int ide_gd_ioctl(struct block_device *bdev, fmode_t mode,
 	return drive->disk_ops->ioctl(drive, bdev, mode, cmd, arg);
 }
 
+#ifdef CONFIG_COMPAT
+static int ide_gd_compat_ioctl(struct block_device *bdev, fmode_t mode,
+			       unsigned int cmd, unsigned long arg)
+{
+	struct ide_disk_obj *idkp = ide_drv_g(bdev->bd_disk, ide_disk_obj);
+	ide_drive_t *drive = idkp->drive;
+
+	if (!drive->disk_ops->compat_ioctl)
+		return -ENOIOCTLCMD;
+
+	return drive->disk_ops->compat_ioctl(drive, bdev, mode, cmd, arg);
+}
+#endif
+
 static const struct block_device_operations ide_gd_ops = {
 	.owner			= THIS_MODULE,
 	.open			= ide_gd_unlocked_open,
 	.release		= ide_gd_release,
 	.ioctl			= ide_gd_ioctl,
+#ifdef CONFIG_COMPAT
+	.ioctl			= ide_gd_compat_ioctl,
+#endif
 	.getgeo			= ide_gd_getgeo,
 	.check_events		= ide_gd_check_events,
 	.unlock_native_capacity	= ide_gd_unlock_native_capacity,
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index d48c17003874..09491098047b 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -3,11 +3,20 @@
  * IDE ioctls handling.
  */
 
+#include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/hdreg.h>
 #include <linux/ide.h>
 #include <linux/slab.h>
 
+static int put_user_long(long val, unsigned long arg)
+{
+	if (in_compat_syscall())
+		return put_user(val, (compat_long_t __user *)compat_ptr(arg));
+
+	return put_user(val, (long __user *)arg);
+}
+
 static const struct ide_ioctl_devset ide_ioctl_settings[] = {
 { HDIO_GET_32BIT,	 HDIO_SET_32BIT,	&ide_devset_io_32bit  },
 { HDIO_GET_KEEPSETTINGS, HDIO_SET_KEEPSETTINGS,	&ide_devset_keepsettings },
@@ -37,7 +46,7 @@ read_val:
 	mutex_lock(&ide_setting_mtx);
 	err = ds->get(drive);
 	mutex_unlock(&ide_setting_mtx);
-	return err >= 0 ? put_user(err, (long __user *)arg) : err;
+	return err >= 0 ? put_user_long(err, arg) : err;
 
 set_val:
 	if (bdev != bdev->bd_contains)
@@ -56,7 +65,7 @@ set_val:
 EXPORT_SYMBOL_GPL(ide_setting_ioctl);
 
 static int ide_get_identity_ioctl(ide_drive_t *drive, unsigned int cmd,
-				  unsigned long arg)
+				  void __user *argp)
 {
 	u16 *id = NULL;
 	int size = (cmd == HDIO_GET_IDENTITY) ? (ATA_ID_WORDS * 2) : 142;
@@ -77,7 +86,7 @@ static int ide_get_identity_ioctl(ide_drive_t *drive, unsigned int cmd,
 	memcpy(id, drive->id, size);
 	ata_id_to_hd_driveid(id);
 
-	if (copy_to_user((void __user *)arg, id, size))
+	if (copy_to_user(argp, id, size))
 		rc = -EFAULT;
 
 	kfree(id);
@@ -87,10 +96,10 @@ out:
 
 static int ide_get_nice_ioctl(ide_drive_t *drive, unsigned long arg)
 {
-	return put_user((!!(drive->dev_flags & IDE_DFLAG_DSC_OVERLAP)
+	return put_user_long((!!(drive->dev_flags & IDE_DFLAG_DSC_OVERLAP)
 			 << IDE_NICE_DSC_OVERLAP) |
 			(!!(drive->dev_flags & IDE_DFLAG_NICE1)
-			 << IDE_NICE_1), (long __user *)arg);
+			 << IDE_NICE_1), arg);
 }
 
 static int ide_set_nice_ioctl(ide_drive_t *drive, unsigned long arg)
@@ -115,7 +124,7 @@ static int ide_set_nice_ioctl(ide_drive_t *drive, unsigned long arg)
 	return 0;
 }
 
-static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
+static int ide_cmd_ioctl(ide_drive_t *drive, void __user *argp)
 {
 	u8 *buf = NULL;
 	int bufsize = 0, err = 0;
@@ -123,7 +132,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 	struct ide_cmd cmd;
 	struct ide_taskfile *tf = &cmd.tf;
 
-	if (NULL == (void *) arg) {
+	if (NULL == argp) {
 		struct request *rq;
 
 		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
@@ -135,7 +144,7 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 		return err;
 	}
 
-	if (copy_from_user(args, (void __user *)arg, 4))
+	if (copy_from_user(args, argp, 4))
 		return -EFAULT;
 
 	memset(&cmd, 0, sizeof(cmd));
@@ -181,19 +190,18 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 	args[1] = tf->error;
 	args[2] = tf->nsect;
 abort:
-	if (copy_to_user((void __user *)arg, &args, 4))
+	if (copy_to_user(argp, &args, 4))
 		err = -EFAULT;
 	if (buf) {
-		if (copy_to_user((void __user *)(arg + 4), buf, bufsize))
+		if (copy_to_user((argp + 4), buf, bufsize))
 			err = -EFAULT;
 		kfree(buf);
 	}
 	return err;
 }
 
-static int ide_task_ioctl(ide_drive_t *drive, unsigned long arg)
+static int ide_task_ioctl(ide_drive_t *drive, void __user *p)
 {
-	void __user *p = (void __user *)arg;
 	int err = 0;
 	u8 args[7];
 	struct ide_cmd cmd;
@@ -237,6 +245,10 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 		      unsigned int cmd, unsigned long arg)
 {
 	int err;
+	void __user *argp = (void __user *)arg;
+
+	if (in_compat_syscall())
+		argp = compat_ptr(arg);
 
 	err = ide_setting_ioctl(drive, bdev, cmd, arg, ide_ioctl_settings);
 	if (err != -EOPNOTSUPP)
@@ -247,7 +259,7 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	case HDIO_GET_IDENTITY:
 		if (bdev != bdev->bd_contains)
 			return -EINVAL;
-		return ide_get_identity_ioctl(drive, cmd, arg);
+		return ide_get_identity_ioctl(drive, cmd, argp);
 	case HDIO_GET_NICE:
 		return ide_get_nice_ioctl(drive, arg);
 	case HDIO_SET_NICE:
@@ -258,6 +270,9 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	case HDIO_DRIVE_TASKFILE:
 		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
 			return -EACCES;
+		/* missing compat handler for HDIO_DRIVE_TASKFILE */
+		if (in_compat_syscall())
+			return -ENOTTY;
 		if (drive->media == ide_disk)
 			return ide_taskfile_ioctl(drive, arg);
 		return -ENOMSG;
@@ -265,11 +280,11 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	case HDIO_DRIVE_CMD:
 		if (!capable(CAP_SYS_RAWIO))
 			return -EACCES;
-		return ide_cmd_ioctl(drive, arg);
+		return ide_cmd_ioctl(drive, argp);
 	case HDIO_DRIVE_TASK:
 		if (!capable(CAP_SYS_RAWIO))
 			return -EACCES;
-		return ide_task_ioctl(drive, arg);
+		return ide_task_ioctl(drive, argp);
 	case HDIO_DRIVE_RESET:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
@@ -277,7 +292,7 @@ int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 	case HDIO_GET_BUSSTATE:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		if (put_user(BUSSTATE_ON, (long __user *)arg))
+		if (put_user_long(BUSSTATE_ON, arg))
 			return -EFAULT;
 		return 0;
 	case HDIO_SET_BUSSTATE:
diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
index d1445d74e9c3..f2be127ee96e 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -530,7 +530,6 @@ int ide_wait_not_busy(ide_hwif_t *hwif, unsigned long timeout)
 		 */
 		if (stat == 0xff)
 			return -ENODEV;
-		touch_softlockup_watchdog();
 		touch_nmi_watchdog();
 	}
 	return -EBUSY;
diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c
index 0363d73b0be0..15c17f3781ee 100644
--- a/drivers/ide/ide-proc.c
+++ b/drivers/ide/ide-proc.c
@@ -206,7 +206,7 @@ static int set_xfer_rate (ide_drive_t *drive, int arg)
 ide_devset_rw(current_speed, xfer_rate);
 ide_devset_rw_field(init_speed, init_speed);
 ide_devset_rw_flag(nice1, IDE_DFLAG_NICE1);
-ide_devset_rw_field(number, dn);
+ide_devset_ro_field(number, dn);
 
 static const struct ide_proc_devset ide_generic_settings[] = {
 	IDE_PROC_DEVSET(current_speed, 0, 70),
@@ -381,13 +381,12 @@ parse_error:
 	return -EINVAL;
 }
 
-static const struct file_operations ide_settings_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= ide_settings_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= ide_settings_proc_write,
+static const struct proc_ops ide_settings_proc_ops = {
+	.proc_open	= ide_settings_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= ide_settings_proc_write,
 };
 
 int ide_capacity_proc_show(struct seq_file *m, void *v)
@@ -546,7 +545,7 @@ void ide_proc_port_register_devices(ide_hwif_t *hwif)
 		if (drive->proc) {
 			ide_add_proc_entries(drive->proc, generic_drive_entries, drive);
 			proc_create_data("settings", S_IFREG|S_IRUSR|S_IWUSR,
-					drive->proc, &ide_settings_proc_fops,
+					drive->proc, &ide_settings_proc_ops,
 					drive);
 		}
 		sprintf(name, "ide%d/%s", (drive->name[2]-'a')/2, drive->name);
@@ -615,7 +614,7 @@ static int ide_drivers_show(struct seq_file *s, void *p)
 	return 0;
 }
 
-DEFINE_SHOW_ATTRIBUTE(ide_drivers);
+DEFINE_PROC_SHOW_ATTRIBUTE(ide_drivers);
 
 void proc_ide_create(void)
 {
@@ -624,7 +623,7 @@ void proc_ide_create(void)
 	if (!proc_ide_root)
 		return;
 
-	proc_create("drivers", 0, proc_ide_root, &ide_drivers_fops);
+	proc_create("drivers", 0, proc_ide_root, &ide_drivers_proc_ops);
 }
 
 void proc_ide_destroy(void)
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 3e7482695f77..6f26634b22bb 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -1945,11 +1945,22 @@ static int idetape_ioctl(struct block_device *bdev, fmode_t mode,
 	return err;
 }
 
+static int idetape_compat_ioctl(struct block_device *bdev, fmode_t mode,
+				unsigned int cmd, unsigned long arg)
+{
+        if (cmd == 0x0340 || cmd == 0x350)
+		arg = (unsigned long)compat_ptr(arg);
+
+	return idetape_ioctl(bdev, mode, cmd, arg);
+}
+
 static const struct block_device_operations idetape_block_ops = {
 	.owner		= THIS_MODULE,
 	.open		= idetape_open,
 	.release	= idetape_release,
 	.ioctl		= idetape_ioctl,
+	.compat_ioctl	= IS_ENABLED(CONFIG_COMPAT) ?
+				idetape_compat_ioctl : NULL,
 };
 
 static int ide_tape_probe(ide_drive_t *drive)
diff --git a/drivers/ide/pmac.c b/drivers/ide/pmac.c
index b5647e34e74e..ea0b064b5f56 100644
--- a/drivers/ide/pmac.c
+++ b/drivers/ide/pmac.c
@@ -1019,7 +1019,6 @@ static int pmac_ide_setup_device(pmac_ide_hwif_t *pmif, struct ide_hw *hw)
 	struct device_node *np = pmif->node;
 	const int *bidp;
 	struct ide_host *host;
-	ide_hwif_t *hwif;
 	struct ide_hw *hws[] = { hw };
 	struct ide_port_info d = pmac_port_info;
 	int rc;
@@ -1075,7 +1074,7 @@ static int pmac_ide_setup_device(pmac_ide_hwif_t *pmif, struct ide_hw *hw)
 		rc = -ENOMEM;
 		goto bail;
 	}
-	hwif = pmif->hwif = host->ports[0];
+	pmif->hwif = host->ports[0];
 
 	if (on_media_bay(pmif)) {
 		/* Fixup bus ID for media bay */
diff --git a/drivers/ide/qd65xx.c b/drivers/ide/qd65xx.c
index 6ce318ebd0cc..ab79b6289464 100644
--- a/drivers/ide/qd65xx.c
+++ b/drivers/ide/qd65xx.c
@@ -299,7 +299,7 @@ static void __init qd6500_init_dev(ide_drive_t *drive)
 static void __init qd6580_init_dev(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
-	u16 t1, t2;
+	unsigned long t1, t2;
 	u8 base = (hwif->config_data & 0xff00) >> 8;
 	u8 config = QD_CONFIG(hwif);
 
diff --git a/drivers/ide/serverworks.c b/drivers/ide/serverworks.c
index ac6fc3fffa0d..458e72e034b0 100644
--- a/drivers/ide/serverworks.c
+++ b/drivers/ide/serverworks.c
@@ -115,6 +115,9 @@ static void svwks_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
 	struct pci_dev *dev = to_pci_dev(hwif->dev);
 	const u8 pio = drive->pio_mode - XFER_PIO_0;
 
+	if (drive->dn >= ARRAY_SIZE(drive_pci))
+		return;
+
 	pci_write_config_byte(dev, drive_pci[drive->dn], pio_modes[pio]);
 
 	if (svwks_csb_check(dev)) {
@@ -141,6 +144,9 @@ static void svwks_set_dma_mode(ide_hwif_t *hwif, ide_drive_t *drive)
 
 	u8 ultra_enable	 = 0, ultra_timing = 0, dma_timing = 0;
 
+	if (drive->dn >= ARRAY_SIZE(drive_pci2))
+		return;
+
 	pci_read_config_byte(dev, (0x56|hwif->channel), &ultra_timing);
 	pci_read_config_byte(dev, 0x54, &ultra_enable);
 
diff --git a/drivers/ide/siimage.c b/drivers/ide/siimage.c
index 57eea5a9047f..c4b20f350b84 100644
--- a/drivers/ide/siimage.c
+++ b/drivers/ide/siimage.c
@@ -648,8 +648,7 @@ static void sil_quirkproc(ide_drive_t *drive)
 
 static void init_iops_siimage(ide_hwif_t *hwif)
 {
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
-	struct ide_host *host = pci_get_drvdata(dev);
+	struct ide_host *host = dev_get_drvdata(hwif->dev);
 
 	hwif->hwif_data = NULL;
 
diff --git a/drivers/ide/tx4939ide.c b/drivers/ide/tx4939ide.c
index d5e871fe840d..b1bbf807bb3d 100644
--- a/drivers/ide/tx4939ide.c
+++ b/drivers/ide/tx4939ide.c
@@ -549,7 +549,7 @@ static int __init tx4939ide_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	if (!devm_request_mem_region(&pdev->dev, res->start,
-				     resource_size(res), "tx4938ide"))
+				     resource_size(res), MODNAME))
 		return -EBUSY;
 	mapbase = (unsigned long)devm_ioremap(&pdev->dev, res->start,
 					      resource_size(res));
diff --git a/drivers/ide/via82cxxx.c b/drivers/ide/via82cxxx.c
index 977cb00398b0..63a3aca506fc 100644
--- a/drivers/ide/via82cxxx.c
+++ b/drivers/ide/via82cxxx.c
@@ -175,8 +175,7 @@ static void via_set_speed(ide_hwif_t *hwif, u8 dn, struct ide_timing *timing)
 static void via_set_drive(ide_hwif_t *hwif, ide_drive_t *drive)
 {
 	ide_drive_t *peer = ide_get_pair_dev(drive);
-	struct pci_dev *dev = to_pci_dev(hwif->dev);
-	struct ide_host *host = pci_get_drvdata(dev);
+	struct ide_host *host = dev_get_drvdata(hwif->dev);
 	struct via82cxxx_dev *vdev = host->host_priv;
 	struct ide_timing t, p;
 	unsigned int T, UT;
diff --git a/drivers/iio/accel/cros_ec_accel_legacy.c b/drivers/iio/accel/cros_ec_accel_legacy.c
index 65f85faf6f31..68e847c6255e 100644
--- a/drivers/iio/accel/cros_ec_accel_legacy.c
+++ b/drivers/iio/accel/cros_ec_accel_legacy.c
@@ -18,7 +18,6 @@
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/triggered_buffer.h>
 #include <linux/kernel.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/platform_data/cros_ec_commands.h>
diff --git a/drivers/iio/adc/qcom-vadc-common.c b/drivers/iio/adc/qcom-vadc-common.c
index dcd7fb5b9fb2..2bb78d1c4daa 100644
--- a/drivers/iio/adc/qcom-vadc-common.c
+++ b/drivers/iio/adc/qcom-vadc-common.c
@@ -6,6 +6,7 @@
 #include <linux/log2.h>
 #include <linux/err.h>
 #include <linux/module.h>
+#include <linux/units.h>
 
 #include "qcom-vadc-common.h"
 
@@ -236,8 +237,7 @@ static int qcom_vadc_scale_die_temp(const struct vadc_linear_graph *calib_graph,
 		voltage = 0;
 	}
 
-	voltage -= KELVINMIL_CELSIUSMIL;
-	*result_mdec = voltage;
+	*result_mdec = milli_kelvin_to_millicelsius(voltage);
 
 	return 0;
 }
@@ -325,7 +325,7 @@ static int qcom_vadc_scale_hw_calib_die_temp(
 {
 	*result_mdec = qcom_vadc_scale_code_voltage_factor(adc_code,
 				prescale, data, 2);
-	*result_mdec -= KELVINMIL_CELSIUSMIL;
+	*result_mdec = milli_kelvin_to_millicelsius(*result_mdec);
 
 	return 0;
 }
diff --git a/drivers/iio/adc/qcom-vadc-common.h b/drivers/iio/adc/qcom-vadc-common.h
index bbb1fa02b382..e074902a24cc 100644
--- a/drivers/iio/adc/qcom-vadc-common.h
+++ b/drivers/iio/adc/qcom-vadc-common.h
@@ -38,7 +38,6 @@
 #define VADC_AVG_SAMPLES_MAX			512
 #define ADC5_AVG_SAMPLES_MAX			16
 
-#define KELVINMIL_CELSIUSMIL			273150
 #define PMIC5_CHG_TEMP_SCALE_FACTOR		377500
 #define PMIC5_SMB_TEMP_CONSTANT			419400
 #define PMIC5_SMB_TEMP_SCALE_FACTOR		356
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index 7dce04473467..576e45faafaf 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -16,7 +16,6 @@
 #include <linux/iio/trigger_consumer.h>
 #include <linux/iio/triggered_buffer.h>
 #include <linux/kernel.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index 81a7f692de2f..d3a3626c7cd8 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -13,7 +13,6 @@
 #include <linux/iio/kfifo_buf.h>
 #include <linux/iio/trigger_consumer.h>
 #include <linux/kernel.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/platform_data/cros_ec_commands.h>
diff --git a/drivers/iio/light/cros_ec_light_prox.c b/drivers/iio/light/cros_ec_light_prox.c
index d85a391e50c5..7a838e2956f4 100644
--- a/drivers/iio/light/cros_ec_light_prox.c
+++ b/drivers/iio/light/cros_ec_light_prox.c
@@ -14,7 +14,6 @@
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 #include <linux/kernel.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
diff --git a/drivers/iio/pressure/cros_ec_baro.c b/drivers/iio/pressure/cros_ec_baro.c
index 52f53f3123b1..b521bebd551c 100644
--- a/drivers/iio/pressure/cros_ec_baro.c
+++ b/drivers/iio/pressure/cros_ec_baro.c
@@ -14,7 +14,6 @@
 #include <linux/iio/triggered_buffer.h>
 #include <linux/iio/trigger_consumer.h>
 #include <linux/kernel.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/platform_data/cros_ec_commands.h>
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 9a8871e21545..d1b14887960e 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,7 +11,8 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o \
-				nldev.o restrack.o counters.o ib_core_uverbs.o
+				nldev.o restrack.o counters.o ib_core_uverbs.o \
+				trace.o
 
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
@@ -20,7 +21,8 @@ ib_cm-y :=			cm.o
 
 iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
 
-rdma_cm-y :=			cma.o
+CFLAGS_cma_trace.o +=		-I$(src)
+rdma_cm-y :=			cma.o cma_trace.o
 
 rdma_cm-$(CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS) += cma_configfs.o
 
@@ -33,6 +35,7 @@ ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
 				uverbs_std_types_cq.o \
 				uverbs_std_types_flow_action.o uverbs_std_types_dm.o \
 				uverbs_std_types_mr.o uverbs_std_types_counters.o \
-				uverbs_uapi.o uverbs_std_types_device.o
+				uverbs_uapi.o uverbs_std_types_device.o \
+				uverbs_std_types_async_fd.o
 ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_uverbs-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 606fa6d86685..1753a9801b70 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -139,7 +139,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 	if (ib_nl_is_good_ip_resp(nlh))
 		ib_nl_process_good_ip_rsep(nlh);
 
-	return skb->len;
+	return 0;
 }
 
 static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index d535995711c3..17bfedd24cc3 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -51,9 +51,8 @@ struct ib_pkey_cache {
 
 struct ib_update_work {
 	struct work_struct work;
-	struct ib_device  *device;
-	u8                 port_num;
-	bool		   enforce_security;
+	struct ib_event event;
+	bool enforce_security;
 };
 
 union ib_gid zgid;
@@ -130,7 +129,7 @@ static void dispatch_gid_change_event(struct ib_device *ib_dev, u8 port)
 	event.element.port_num	= port;
 	event.event		= IB_EVENT_GID_CHANGE;
 
-	ib_dispatch_event(&event);
+	ib_dispatch_event_clients(&event);
 }
 
 static const char * const gid_type_str[] = {
@@ -1034,7 +1033,7 @@ int ib_get_cached_pkey(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 
 	cache = device->port_data[port_num].cache.pkey;
 
@@ -1043,7 +1042,7 @@ int ib_get_cached_pkey(struct ib_device *device,
 	else
 		*pkey = cache->table[index];
 
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1058,9 +1057,9 @@ int ib_get_cached_subnet_prefix(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 	*sn_pfx = device->port_data[port_num].cache.subnet_prefix;
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return 0;
 }
@@ -1080,7 +1079,7 @@ int ib_find_cached_pkey(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 
 	cache = device->port_data[port_num].cache.pkey;
 
@@ -1101,7 +1100,7 @@ int ib_find_cached_pkey(struct ib_device *device,
 		ret = 0;
 	}
 
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1120,7 +1119,7 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 
 	cache = device->port_data[port_num].cache.pkey;
 
@@ -1133,7 +1132,7 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 			break;
 		}
 
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1149,9 +1148,9 @@ int ib_get_cached_lmc(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 	*lmc = device->port_data[port_num].cache.lmc;
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1167,9 +1166,9 @@ int ib_get_cached_port_state(struct ib_device   *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 	*port_state = device->port_data[port_num].cache.port_state;
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1381,9 +1380,8 @@ err:
 	return ret;
 }
 
-static void ib_cache_update(struct ib_device *device,
-			    u8                port,
-			    bool	      enforce_security)
+static int
+ib_cache_update(struct ib_device *device, u8 port, bool enforce_security)
 {
 	struct ib_port_attr       *tprops = NULL;
 	struct ib_pkey_cache      *pkey_cache = NULL, *old_pkey_cache;
@@ -1391,11 +1389,11 @@ static void ib_cache_update(struct ib_device *device,
 	int                        ret;
 
 	if (!rdma_is_port_valid(device, port))
-		return;
+		return -EINVAL;
 
 	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
 	if (!tprops)
-		return;
+		return -ENOMEM;
 
 	ret = ib_query_port(device, port, tprops);
 	if (ret) {
@@ -1413,8 +1411,10 @@ static void ib_cache_update(struct ib_device *device,
 	pkey_cache = kmalloc(struct_size(pkey_cache, table,
 					 tprops->pkey_tbl_len),
 			     GFP_KERNEL);
-	if (!pkey_cache)
+	if (!pkey_cache) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	pkey_cache->table_len = tprops->pkey_tbl_len;
 
@@ -1428,7 +1428,7 @@ static void ib_cache_update(struct ib_device *device,
 		}
 	}
 
-	write_lock_irq(&device->cache.lock);
+	write_lock_irq(&device->cache_lock);
 
 	old_pkey_cache = device->port_data[port].cache.pkey;
 
@@ -1437,7 +1437,7 @@ static void ib_cache_update(struct ib_device *device,
 	device->port_data[port].cache.port_state = tprops->state;
 
 	device->port_data[port].cache.subnet_prefix = tprops->subnet_prefix;
-	write_unlock_irq(&device->cache.lock);
+	write_unlock_irq(&device->cache_lock);
 
 	if (enforce_security)
 		ib_security_cache_change(device,
@@ -1446,57 +1446,91 @@ static void ib_cache_update(struct ib_device *device,
 
 	kfree(old_pkey_cache);
 	kfree(tprops);
-	return;
+	return 0;
 
 err:
 	kfree(pkey_cache);
 	kfree(tprops);
+	return ret;
+}
+
+static void ib_cache_event_task(struct work_struct *_work)
+{
+	struct ib_update_work *work =
+		container_of(_work, struct ib_update_work, work);
+	int ret;
+
+	/* Before distributing the cache update event, first sync
+	 * the cache.
+	 */
+	ret = ib_cache_update(work->event.device, work->event.element.port_num,
+			      work->enforce_security);
+
+	/* GID event is notified already for individual GID entries by
+	 * dispatch_gid_change_event(). Hence, notifiy for rest of the
+	 * events.
+	 */
+	if (!ret && work->event.event != IB_EVENT_GID_CHANGE)
+		ib_dispatch_event_clients(&work->event);
+
+	kfree(work);
 }
 
-static void ib_cache_task(struct work_struct *_work)
+static void ib_generic_event_task(struct work_struct *_work)
 {
 	struct ib_update_work *work =
 		container_of(_work, struct ib_update_work, work);
 
-	ib_cache_update(work->device,
-			work->port_num,
-			work->enforce_security);
+	ib_dispatch_event_clients(&work->event);
 	kfree(work);
 }
 
-static void ib_cache_event(struct ib_event_handler *handler,
-			   struct ib_event *event)
+static bool is_cache_update_event(const struct ib_event *event)
+{
+	return (event->event == IB_EVENT_PORT_ERR    ||
+		event->event == IB_EVENT_PORT_ACTIVE ||
+		event->event == IB_EVENT_LID_CHANGE  ||
+		event->event == IB_EVENT_PKEY_CHANGE ||
+		event->event == IB_EVENT_CLIENT_REREGISTER ||
+		event->event == IB_EVENT_GID_CHANGE);
+}
+
+/**
+ * ib_dispatch_event - Dispatch an asynchronous event
+ * @event:Event to dispatch
+ *
+ * Low-level drivers must call ib_dispatch_event() to dispatch the
+ * event to all registered event handlers when an asynchronous event
+ * occurs.
+ */
+void ib_dispatch_event(const struct ib_event *event)
 {
 	struct ib_update_work *work;
 
-	if (event->event == IB_EVENT_PORT_ERR    ||
-	    event->event == IB_EVENT_PORT_ACTIVE ||
-	    event->event == IB_EVENT_LID_CHANGE  ||
-	    event->event == IB_EVENT_PKEY_CHANGE ||
-	    event->event == IB_EVENT_CLIENT_REREGISTER ||
-	    event->event == IB_EVENT_GID_CHANGE) {
-		work = kmalloc(sizeof *work, GFP_ATOMIC);
-		if (work) {
-			INIT_WORK(&work->work, ib_cache_task);
-			work->device   = event->device;
-			work->port_num = event->element.port_num;
-			if (event->event == IB_EVENT_PKEY_CHANGE ||
-			    event->event == IB_EVENT_GID_CHANGE)
-				work->enforce_security = true;
-			else
-				work->enforce_security = false;
-
-			queue_work(ib_wq, &work->work);
-		}
-	}
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return;
+
+	if (is_cache_update_event(event))
+		INIT_WORK(&work->work, ib_cache_event_task);
+	else
+		INIT_WORK(&work->work, ib_generic_event_task);
+
+	work->event = *event;
+	if (event->event == IB_EVENT_PKEY_CHANGE ||
+	    event->event == IB_EVENT_GID_CHANGE)
+		work->enforce_security = true;
+
+	queue_work(ib_wq, &work->work);
 }
+EXPORT_SYMBOL(ib_dispatch_event);
 
 int ib_cache_setup_one(struct ib_device *device)
 {
 	unsigned int p;
 	int err;
 
-	rwlock_init(&device->cache.lock);
+	rwlock_init(&device->cache_lock);
 
 	err = gid_table_setup_one(device);
 	if (err)
@@ -1505,9 +1539,6 @@ int ib_cache_setup_one(struct ib_device *device)
 	rdma_for_each_port (device, p)
 		ib_cache_update(device, p, true);
 
-	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
-			      device, ib_cache_event);
-	ib_register_event_handler(&device->cache.event_handler);
 	return 0;
 }
 
@@ -1529,14 +1560,12 @@ void ib_cache_release_one(struct ib_device *device)
 
 void ib_cache_cleanup_one(struct ib_device *device)
 {
-	/* The cleanup function unregisters the event handler,
-	 * waits for all in-progress workqueue elements and cleans
-	 * up the GID cache. This function should be called after
-	 * the device was removed from the devices list and all
-	 * clients were removed, so the cache exists but is
+	/* The cleanup function waits for all in-progress workqueue
+	 * elements and cleans up the GID cache. This function should be
+	 * called after the device was removed from the devices list and
+	 * all clients were removed, so the cache exists but is
 	 * non-functional and shouldn't be updated anymore.
 	 */
-	ib_unregister_event_handler(&device->cache.event_handler);
 	flush_workqueue(ib_wq);
 	gid_table_cleanup_one(device);
 
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 455b3659d84b..68cc1b2d6824 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -241,6 +241,7 @@ struct cm_id_private {
 	/* Number of clients sharing this ib_cm_id. Only valid for listeners.
 	 * Protected by the cm.lock spinlock. */
 	int listen_sharecount;
+	struct rcu_head rcu;
 
 	struct ib_mad_send_buf *msg;
 	struct cm_timewait_info *timewait_info;
@@ -593,28 +594,16 @@ static void cm_free_id(__be32 local_id)
 	xa_erase_irq(&cm.local_id_table, cm_local_id(local_id));
 }
 
-static struct cm_id_private * cm_get_id(__be32 local_id, __be32 remote_id)
+static struct cm_id_private *cm_acquire_id(__be32 local_id, __be32 remote_id)
 {
 	struct cm_id_private *cm_id_priv;
 
+	rcu_read_lock();
 	cm_id_priv = xa_load(&cm.local_id_table, cm_local_id(local_id));
-	if (cm_id_priv) {
-		if (cm_id_priv->id.remote_id == remote_id)
-			refcount_inc(&cm_id_priv->refcount);
-		else
-			cm_id_priv = NULL;
-	}
-
-	return cm_id_priv;
-}
-
-static struct cm_id_private * cm_acquire_id(__be32 local_id, __be32 remote_id)
-{
-	struct cm_id_private *cm_id_priv;
-
-	spin_lock_irq(&cm.lock);
-	cm_id_priv = cm_get_id(local_id, remote_id);
-	spin_unlock_irq(&cm.lock);
+	if (!cm_id_priv || cm_id_priv->id.remote_id != remote_id ||
+	    !refcount_inc_not_zero(&cm_id_priv->refcount))
+		cm_id_priv = NULL;
+	rcu_read_unlock();
 
 	return cm_id_priv;
 }
@@ -1089,7 +1078,7 @@ retest:
 	rdma_destroy_ah_attr(&cm_id_priv->av.ah_attr);
 	rdma_destroy_ah_attr(&cm_id_priv->alt_av.ah_attr);
 	kfree(cm_id_priv->private_data);
-	kfree(cm_id_priv);
+	kfree_rcu(cm_id_priv, rcu);
 }
 
 void ib_destroy_cm_id(struct ib_cm_id *cm_id)
@@ -1262,54 +1251,72 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 	cm_format_mad_hdr(&req_msg->hdr, CM_REQ_ATTR_ID,
 			  cm_form_tid(cm_id_priv));
 
-	req_msg->local_comm_id = cm_id_priv->id.local_id;
-	req_msg->service_id = param->service_id;
-	req_msg->local_ca_guid = cm_id_priv->id.device->node_guid;
-	cm_req_set_local_qpn(req_msg, cpu_to_be32(param->qp_num));
-	cm_req_set_init_depth(req_msg, param->initiator_depth);
-	cm_req_set_remote_resp_timeout(req_msg,
-				       param->remote_cm_response_timeout);
+	IBA_SET(CM_REQ_LOCAL_COMM_ID, req_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_REQ_SERVICE_ID, req_msg, be64_to_cpu(param->service_id));
+	IBA_SET(CM_REQ_LOCAL_CA_GUID, req_msg,
+		be64_to_cpu(cm_id_priv->id.device->node_guid));
+	IBA_SET(CM_REQ_LOCAL_QPN, req_msg, param->qp_num);
+	IBA_SET(CM_REQ_INITIATOR_DEPTH, req_msg, param->initiator_depth);
+	IBA_SET(CM_REQ_REMOTE_CM_RESPONSE_TIMEOUT, req_msg,
+		param->remote_cm_response_timeout);
 	cm_req_set_qp_type(req_msg, param->qp_type);
-	cm_req_set_flow_ctrl(req_msg, param->flow_control);
-	cm_req_set_starting_psn(req_msg, cpu_to_be32(param->starting_psn));
-	cm_req_set_local_resp_timeout(req_msg,
-				      param->local_cm_response_timeout);
-	req_msg->pkey = param->primary_path->pkey;
-	cm_req_set_path_mtu(req_msg, param->primary_path->mtu);
-	cm_req_set_max_cm_retries(req_msg, param->max_cm_retries);
+	IBA_SET(CM_REQ_END_TO_END_FLOW_CONTROL, req_msg, param->flow_control);
+	IBA_SET(CM_REQ_STARTING_PSN, req_msg, param->starting_psn);
+	IBA_SET(CM_REQ_LOCAL_CM_RESPONSE_TIMEOUT, req_msg,
+		param->local_cm_response_timeout);
+	IBA_SET(CM_REQ_PARTITION_KEY, req_msg,
+		be16_to_cpu(param->primary_path->pkey));
+	IBA_SET(CM_REQ_PATH_PACKET_PAYLOAD_MTU, req_msg,
+		param->primary_path->mtu);
+	IBA_SET(CM_REQ_MAX_CM_RETRIES, req_msg, param->max_cm_retries);
 
 	if (param->qp_type != IB_QPT_XRC_INI) {
-		cm_req_set_resp_res(req_msg, param->responder_resources);
-		cm_req_set_retry_count(req_msg, param->retry_count);
-		cm_req_set_rnr_retry_count(req_msg, param->rnr_retry_count);
-		cm_req_set_srq(req_msg, param->srq);
+		IBA_SET(CM_REQ_RESPONDER_RESOURCES, req_msg,
+			param->responder_resources);
+		IBA_SET(CM_REQ_RETRY_COUNT, req_msg, param->retry_count);
+		IBA_SET(CM_REQ_RNR_RETRY_COUNT, req_msg,
+			param->rnr_retry_count);
+		IBA_SET(CM_REQ_SRQ, req_msg, param->srq);
 	}
 
-	req_msg->primary_local_gid = pri_path->sgid;
-	req_msg->primary_remote_gid = pri_path->dgid;
+	*IBA_GET_MEM_PTR(CM_REQ_PRIMARY_LOCAL_PORT_GID, req_msg) =
+		pri_path->sgid;
+	*IBA_GET_MEM_PTR(CM_REQ_PRIMARY_REMOTE_PORT_GID, req_msg) =
+		pri_path->dgid;
 	if (pri_ext) {
-		req_msg->primary_local_gid.global.interface_id
-			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.slid));
-		req_msg->primary_remote_gid.global.interface_id
-			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.dlid));
+		IBA_GET_MEM_PTR(CM_REQ_PRIMARY_LOCAL_PORT_GID, req_msg)
+			->global.interface_id =
+			OPA_MAKE_ID(be32_to_cpu(pri_path->opa.slid));
+		IBA_GET_MEM_PTR(CM_REQ_PRIMARY_REMOTE_PORT_GID, req_msg)
+			->global.interface_id =
+			OPA_MAKE_ID(be32_to_cpu(pri_path->opa.dlid));
 	}
 	if (pri_path->hop_limit <= 1) {
-		req_msg->primary_local_lid = pri_ext ? 0 :
-			htons(ntohl(sa_path_get_slid(pri_path)));
-		req_msg->primary_remote_lid = pri_ext ? 0 :
-			htons(ntohl(sa_path_get_dlid(pri_path)));
+		IBA_SET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg,
+			be16_to_cpu(pri_ext ? 0 :
+					      htons(ntohl(sa_path_get_slid(
+						      pri_path)))));
+		IBA_SET(CM_REQ_PRIMARY_REMOTE_PORT_LID, req_msg,
+			be16_to_cpu(pri_ext ? 0 :
+					      htons(ntohl(sa_path_get_dlid(
+						      pri_path)))));
 	} else {
 		/* Work-around until there's a way to obtain remote LID info */
-		req_msg->primary_local_lid = IB_LID_PERMISSIVE;
-		req_msg->primary_remote_lid = IB_LID_PERMISSIVE;
+		IBA_SET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg,
+			be16_to_cpu(IB_LID_PERMISSIVE));
+		IBA_SET(CM_REQ_PRIMARY_REMOTE_PORT_LID, req_msg,
+			be16_to_cpu(IB_LID_PERMISSIVE));
 	}
-	cm_req_set_primary_flow_label(req_msg, pri_path->flow_label);
-	cm_req_set_primary_packet_rate(req_msg, pri_path->rate);
-	req_msg->primary_traffic_class = pri_path->traffic_class;
-	req_msg->primary_hop_limit = pri_path->hop_limit;
-	cm_req_set_primary_sl(req_msg, pri_path->sl);
-	cm_req_set_primary_subnet_local(req_msg, (pri_path->hop_limit <= 1));
-	cm_req_set_primary_local_ack_timeout(req_msg,
+	IBA_SET(CM_REQ_PRIMARY_FLOW_LABEL, req_msg,
+		be32_to_cpu(pri_path->flow_label));
+	IBA_SET(CM_REQ_PRIMARY_PACKET_RATE, req_msg, pri_path->rate);
+	IBA_SET(CM_REQ_PRIMARY_TRAFFIC_CLASS, req_msg, pri_path->traffic_class);
+	IBA_SET(CM_REQ_PRIMARY_HOP_LIMIT, req_msg, pri_path->hop_limit);
+	IBA_SET(CM_REQ_PRIMARY_SL, req_msg, pri_path->sl);
+	IBA_SET(CM_REQ_PRIMARY_SUBNET_LOCAL, req_msg,
+		(pri_path->hop_limit <= 1));
+	IBA_SET(CM_REQ_PRIMARY_LOCAL_ACK_TIMEOUT, req_msg,
 		cm_ack_timeout(cm_id_priv->av.port->cm_dev->ack_delay,
 			       pri_path->packet_life_time));
 
@@ -1320,38 +1327,55 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 			alt_ext = opa_is_extended_lid(alt_path->opa.dlid,
 						      alt_path->opa.slid);
 
-		req_msg->alt_local_gid = alt_path->sgid;
-		req_msg->alt_remote_gid = alt_path->dgid;
+		*IBA_GET_MEM_PTR(CM_REQ_ALTERNATE_LOCAL_PORT_GID, req_msg) =
+			alt_path->sgid;
+		*IBA_GET_MEM_PTR(CM_REQ_ALTERNATE_REMOTE_PORT_GID, req_msg) =
+			alt_path->dgid;
 		if (alt_ext) {
-			req_msg->alt_local_gid.global.interface_id
-				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.slid));
-			req_msg->alt_remote_gid.global.interface_id
-				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.dlid));
+			IBA_GET_MEM_PTR(CM_REQ_ALTERNATE_LOCAL_PORT_GID,
+					req_msg)
+				->global.interface_id =
+				OPA_MAKE_ID(be32_to_cpu(alt_path->opa.slid));
+			IBA_GET_MEM_PTR(CM_REQ_ALTERNATE_REMOTE_PORT_GID,
+					req_msg)
+				->global.interface_id =
+				OPA_MAKE_ID(be32_to_cpu(alt_path->opa.dlid));
 		}
 		if (alt_path->hop_limit <= 1) {
-			req_msg->alt_local_lid = alt_ext ? 0 :
-				htons(ntohl(sa_path_get_slid(alt_path)));
-			req_msg->alt_remote_lid = alt_ext ? 0 :
-				htons(ntohl(sa_path_get_dlid(alt_path)));
+			IBA_SET(CM_REQ_ALTERNATE_LOCAL_PORT_LID, req_msg,
+				be16_to_cpu(
+					alt_ext ? 0 :
+						  htons(ntohl(sa_path_get_slid(
+							  alt_path)))));
+			IBA_SET(CM_REQ_ALTERNATE_REMOTE_PORT_LID, req_msg,
+				be16_to_cpu(
+					alt_ext ? 0 :
+						  htons(ntohl(sa_path_get_dlid(
+							  alt_path)))));
 		} else {
-			req_msg->alt_local_lid = IB_LID_PERMISSIVE;
-			req_msg->alt_remote_lid = IB_LID_PERMISSIVE;
+			IBA_SET(CM_REQ_ALTERNATE_LOCAL_PORT_LID, req_msg,
+				be16_to_cpu(IB_LID_PERMISSIVE));
+			IBA_SET(CM_REQ_ALTERNATE_REMOTE_PORT_LID, req_msg,
+				be16_to_cpu(IB_LID_PERMISSIVE));
 		}
-		cm_req_set_alt_flow_label(req_msg,
-					  alt_path->flow_label);
-		cm_req_set_alt_packet_rate(req_msg, alt_path->rate);
-		req_msg->alt_traffic_class = alt_path->traffic_class;
-		req_msg->alt_hop_limit = alt_path->hop_limit;
-		cm_req_set_alt_sl(req_msg, alt_path->sl);
-		cm_req_set_alt_subnet_local(req_msg, (alt_path->hop_limit <= 1));
-		cm_req_set_alt_local_ack_timeout(req_msg,
+		IBA_SET(CM_REQ_ALTERNATE_FLOW_LABEL, req_msg,
+			be32_to_cpu(alt_path->flow_label));
+		IBA_SET(CM_REQ_ALTERNATE_PACKET_RATE, req_msg, alt_path->rate);
+		IBA_SET(CM_REQ_ALTERNATE_TRAFFIC_CLASS, req_msg,
+			alt_path->traffic_class);
+		IBA_SET(CM_REQ_ALTERNATE_HOP_LIMIT, req_msg,
+			alt_path->hop_limit);
+		IBA_SET(CM_REQ_ALTERNATE_SL, req_msg, alt_path->sl);
+		IBA_SET(CM_REQ_ALTERNATE_SUBNET_LOCAL, req_msg,
+			(alt_path->hop_limit <= 1));
+		IBA_SET(CM_REQ_ALTERNATE_LOCAL_ACK_TIMEOUT, req_msg,
 			cm_ack_timeout(cm_id_priv->av.port->cm_dev->ack_delay,
 				       alt_path->packet_life_time));
 	}
 
 	if (param->private_data && param->private_data_len)
-		memcpy(req_msg->private_data, param->private_data,
-		       param->private_data_len);
+		IBA_SET_MEM(CM_REQ_PRIVATE_DATA, req_msg, param->private_data,
+			    param->private_data_len);
 }
 
 static int cm_validate_req_param(struct ib_cm_req_param *param)
@@ -1443,8 +1467,8 @@ int ib_send_cm_req(struct ib_cm_id *cm_id,
 	cm_id_priv->msg->timeout_ms = cm_id_priv->timeout_ms;
 	cm_id_priv->msg->context[1] = (void *) (unsigned long) IB_CM_REQ_SENT;
 
-	cm_id_priv->local_qpn = cm_req_get_local_qpn(req_msg);
-	cm_id_priv->rq_psn = cm_req_get_starting_psn(req_msg);
+	cm_id_priv->local_qpn = cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
+	cm_id_priv->rq_psn = cpu_to_be32(IBA_GET(CM_REQ_STARTING_PSN, req_msg));
 
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
 	ret = ib_post_send_mad(cm_id_priv->msg, NULL);
@@ -1482,14 +1506,16 @@ static int cm_issue_rej(struct cm_port *port,
 	rej_msg = (struct cm_rej_msg *) msg->mad;
 
 	cm_format_mad_hdr(&rej_msg->hdr, CM_REJ_ATTR_ID, rcv_msg->hdr.tid);
-	rej_msg->remote_comm_id = rcv_msg->local_comm_id;
-	rej_msg->local_comm_id = rcv_msg->remote_comm_id;
-	cm_rej_set_msg_rejected(rej_msg, msg_rejected);
-	rej_msg->reason = cpu_to_be16(reason);
+	IBA_SET(CM_REJ_REMOTE_COMM_ID, rej_msg,
+		IBA_GET(CM_REJ_LOCAL_COMM_ID, rcv_msg));
+	IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg,
+		IBA_GET(CM_REJ_REMOTE_COMM_ID, rcv_msg));
+	IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, msg_rejected);
+	IBA_SET(CM_REJ_REASON, rej_msg, reason);
 
 	if (ari && ari_length) {
-		cm_rej_set_reject_info_len(rej_msg, ari_length);
-		memcpy(rej_msg->ari, ari, ari_length);
+		IBA_SET(CM_REJ_REJECTED_INFO_LENGTH, rej_msg, ari_length);
+		IBA_SET_MEM(CM_REJ_ARI, rej_msg, ari, ari_length);
 	}
 
 	ret = ib_post_send_mad(msg, NULL);
@@ -1501,8 +1527,10 @@ static int cm_issue_rej(struct cm_port *port,
 
 static bool cm_req_has_alt_path(struct cm_req_msg *req_msg)
 {
-	return ((req_msg->alt_local_lid) ||
-		(ib_is_opa_gid(&req_msg->alt_local_gid)));
+	return ((cpu_to_be16(
+			IBA_GET(CM_REQ_ALTERNATE_LOCAL_PORT_LID, req_msg))) ||
+		(ib_is_opa_gid(IBA_GET_MEM_PTR(CM_REQ_ALTERNATE_LOCAL_PORT_GID,
+					       req_msg))));
 }
 
 static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
@@ -1522,14 +1550,18 @@ static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
 
 	if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) {
 		sa_path_set_dlid(primary_path,
-				 ntohs(req_msg->primary_local_lid));
+				 IBA_GET(CM_REQ_PRIMARY_LOCAL_PORT_LID,
+					 req_msg));
 		sa_path_set_slid(primary_path,
-				 ntohs(req_msg->primary_remote_lid));
+				 IBA_GET(CM_REQ_PRIMARY_REMOTE_PORT_LID,
+					 req_msg));
 	} else {
-		lid = opa_get_lid_from_gid(&req_msg->primary_local_gid);
+		lid = opa_get_lid_from_gid(IBA_GET_MEM_PTR(
+			CM_REQ_PRIMARY_LOCAL_PORT_GID, req_msg));
 		sa_path_set_dlid(primary_path, lid);
 
-		lid = opa_get_lid_from_gid(&req_msg->primary_remote_gid);
+		lid = opa_get_lid_from_gid(IBA_GET_MEM_PTR(
+			CM_REQ_PRIMARY_REMOTE_PORT_GID, req_msg));
 		sa_path_set_slid(primary_path, lid);
 	}
 
@@ -1537,13 +1569,19 @@ static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
 		return;
 
 	if (alt_path->rec_type != SA_PATH_REC_TYPE_OPA) {
-		sa_path_set_dlid(alt_path, ntohs(req_msg->alt_local_lid));
-		sa_path_set_slid(alt_path, ntohs(req_msg->alt_remote_lid));
+		sa_path_set_dlid(alt_path,
+				 IBA_GET(CM_REQ_ALTERNATE_LOCAL_PORT_LID,
+					 req_msg));
+		sa_path_set_slid(alt_path,
+				 IBA_GET(CM_REQ_ALTERNATE_REMOTE_PORT_LID,
+					 req_msg));
 	} else {
-		lid = opa_get_lid_from_gid(&req_msg->alt_local_gid);
+		lid = opa_get_lid_from_gid(IBA_GET_MEM_PTR(
+			CM_REQ_ALTERNATE_LOCAL_PORT_GID, req_msg));
 		sa_path_set_dlid(alt_path, lid);
 
-		lid = opa_get_lid_from_gid(&req_msg->alt_remote_gid);
+		lid = opa_get_lid_from_gid(IBA_GET_MEM_PTR(
+			CM_REQ_ALTERNATE_REMOTE_PORT_GID, req_msg));
 		sa_path_set_slid(alt_path, lid);
 	}
 }
@@ -1552,44 +1590,58 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 				     struct sa_path_rec *primary_path,
 				     struct sa_path_rec *alt_path)
 {
-	primary_path->dgid = req_msg->primary_local_gid;
-	primary_path->sgid = req_msg->primary_remote_gid;
-	primary_path->flow_label = cm_req_get_primary_flow_label(req_msg);
-	primary_path->hop_limit = req_msg->primary_hop_limit;
-	primary_path->traffic_class = req_msg->primary_traffic_class;
+	primary_path->dgid =
+		*IBA_GET_MEM_PTR(CM_REQ_PRIMARY_LOCAL_PORT_GID, req_msg);
+	primary_path->sgid =
+		*IBA_GET_MEM_PTR(CM_REQ_PRIMARY_REMOTE_PORT_GID, req_msg);
+	primary_path->flow_label =
+		cpu_to_be32(IBA_GET(CM_REQ_PRIMARY_FLOW_LABEL, req_msg));
+	primary_path->hop_limit = IBA_GET(CM_REQ_PRIMARY_HOP_LIMIT, req_msg);
+	primary_path->traffic_class =
+		IBA_GET(CM_REQ_PRIMARY_TRAFFIC_CLASS, req_msg);
 	primary_path->reversible = 1;
-	primary_path->pkey = req_msg->pkey;
-	primary_path->sl = cm_req_get_primary_sl(req_msg);
+	primary_path->pkey =
+		cpu_to_be16(IBA_GET(CM_REQ_PARTITION_KEY, req_msg));
+	primary_path->sl = IBA_GET(CM_REQ_PRIMARY_SL, req_msg);
 	primary_path->mtu_selector = IB_SA_EQ;
-	primary_path->mtu = cm_req_get_path_mtu(req_msg);
+	primary_path->mtu = IBA_GET(CM_REQ_PATH_PACKET_PAYLOAD_MTU, req_msg);
 	primary_path->rate_selector = IB_SA_EQ;
-	primary_path->rate = cm_req_get_primary_packet_rate(req_msg);
+	primary_path->rate = IBA_GET(CM_REQ_PRIMARY_PACKET_RATE, req_msg);
 	primary_path->packet_life_time_selector = IB_SA_EQ;
 	primary_path->packet_life_time =
-		cm_req_get_primary_local_ack_timeout(req_msg);
+		IBA_GET(CM_REQ_PRIMARY_LOCAL_ACK_TIMEOUT, req_msg);
 	primary_path->packet_life_time -= (primary_path->packet_life_time > 0);
-	primary_path->service_id = req_msg->service_id;
+	primary_path->service_id =
+		cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg));
 	if (sa_path_is_roce(primary_path))
 		primary_path->roce.route_resolved = false;
 
 	if (cm_req_has_alt_path(req_msg)) {
-		alt_path->dgid = req_msg->alt_local_gid;
-		alt_path->sgid = req_msg->alt_remote_gid;
-		alt_path->flow_label = cm_req_get_alt_flow_label(req_msg);
-		alt_path->hop_limit = req_msg->alt_hop_limit;
-		alt_path->traffic_class = req_msg->alt_traffic_class;
+		alt_path->dgid = *IBA_GET_MEM_PTR(
+			CM_REQ_ALTERNATE_LOCAL_PORT_GID, req_msg);
+		alt_path->sgid = *IBA_GET_MEM_PTR(
+			CM_REQ_ALTERNATE_REMOTE_PORT_GID, req_msg);
+		alt_path->flow_label = cpu_to_be32(
+			IBA_GET(CM_REQ_ALTERNATE_FLOW_LABEL, req_msg));
+		alt_path->hop_limit =
+			IBA_GET(CM_REQ_ALTERNATE_HOP_LIMIT, req_msg);
+		alt_path->traffic_class =
+			IBA_GET(CM_REQ_ALTERNATE_TRAFFIC_CLASS, req_msg);
 		alt_path->reversible = 1;
-		alt_path->pkey = req_msg->pkey;
-		alt_path->sl = cm_req_get_alt_sl(req_msg);
+		alt_path->pkey =
+			cpu_to_be16(IBA_GET(CM_REQ_PARTITION_KEY, req_msg));
+		alt_path->sl = IBA_GET(CM_REQ_ALTERNATE_SL, req_msg);
 		alt_path->mtu_selector = IB_SA_EQ;
-		alt_path->mtu = cm_req_get_path_mtu(req_msg);
+		alt_path->mtu =
+			IBA_GET(CM_REQ_PATH_PACKET_PAYLOAD_MTU, req_msg);
 		alt_path->rate_selector = IB_SA_EQ;
-		alt_path->rate = cm_req_get_alt_packet_rate(req_msg);
+		alt_path->rate = IBA_GET(CM_REQ_ALTERNATE_PACKET_RATE, req_msg);
 		alt_path->packet_life_time_selector = IB_SA_EQ;
 		alt_path->packet_life_time =
-			cm_req_get_alt_local_ack_timeout(req_msg);
+			IBA_GET(CM_REQ_ALTERNATE_LOCAL_ACK_TIMEOUT, req_msg);
 		alt_path->packet_life_time -= (alt_path->packet_life_time > 0);
-		alt_path->service_id = req_msg->service_id;
+		alt_path->service_id =
+			cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg));
 
 		if (sa_path_is_roce(alt_path))
 			alt_path->roce.route_resolved = false;
@@ -1664,23 +1716,25 @@ static void cm_format_req_event(struct cm_work *work,
 	} else {
 		param->alternate_path = NULL;
 	}
-	param->remote_ca_guid = req_msg->local_ca_guid;
-	param->remote_qkey = be32_to_cpu(req_msg->local_qkey);
-	param->remote_qpn = be32_to_cpu(cm_req_get_local_qpn(req_msg));
+	param->remote_ca_guid =
+		cpu_to_be64(IBA_GET(CM_REQ_LOCAL_CA_GUID, req_msg));
+	param->remote_qkey = IBA_GET(CM_REQ_LOCAL_Q_KEY, req_msg);
+	param->remote_qpn = IBA_GET(CM_REQ_LOCAL_QPN, req_msg);
 	param->qp_type = cm_req_get_qp_type(req_msg);
-	param->starting_psn = be32_to_cpu(cm_req_get_starting_psn(req_msg));
-	param->responder_resources = cm_req_get_init_depth(req_msg);
-	param->initiator_depth = cm_req_get_resp_res(req_msg);
+	param->starting_psn = IBA_GET(CM_REQ_STARTING_PSN, req_msg);
+	param->responder_resources = IBA_GET(CM_REQ_INITIATOR_DEPTH, req_msg);
+	param->initiator_depth = IBA_GET(CM_REQ_RESPONDER_RESOURCES, req_msg);
 	param->local_cm_response_timeout =
-					cm_req_get_remote_resp_timeout(req_msg);
-	param->flow_control = cm_req_get_flow_ctrl(req_msg);
+		IBA_GET(CM_REQ_REMOTE_CM_RESPONSE_TIMEOUT, req_msg);
+	param->flow_control = IBA_GET(CM_REQ_END_TO_END_FLOW_CONTROL, req_msg);
 	param->remote_cm_response_timeout =
-					cm_req_get_local_resp_timeout(req_msg);
-	param->retry_count = cm_req_get_retry_count(req_msg);
-	param->rnr_retry_count = cm_req_get_rnr_retry_count(req_msg);
-	param->srq = cm_req_get_srq(req_msg);
+		IBA_GET(CM_REQ_LOCAL_CM_RESPONSE_TIMEOUT, req_msg);
+	param->retry_count = IBA_GET(CM_REQ_RETRY_COUNT, req_msg);
+	param->rnr_retry_count = IBA_GET(CM_REQ_RNR_RETRY_COUNT, req_msg);
+	param->srq = IBA_GET(CM_REQ_SRQ, req_msg);
 	param->ppath_sgid_attr = cm_id_priv->av.ah_attr.grh.sgid_attr;
-	work->cm_event.private_data = &req_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_REQ_PRIVATE_DATA, req_msg);
 }
 
 static void cm_process_work(struct cm_id_private *cm_id_priv,
@@ -1714,13 +1768,16 @@ static void cm_format_mra(struct cm_mra_msg *mra_msg,
 			  const void *private_data, u8 private_data_len)
 {
 	cm_format_mad_hdr(&mra_msg->hdr, CM_MRA_ATTR_ID, cm_id_priv->tid);
-	cm_mra_set_msg_mraed(mra_msg, msg_mraed);
-	mra_msg->local_comm_id = cm_id_priv->id.local_id;
-	mra_msg->remote_comm_id = cm_id_priv->id.remote_id;
-	cm_mra_set_service_timeout(mra_msg, service_timeout);
+	IBA_SET(CM_MRA_MESSAGE_MRAED, mra_msg, msg_mraed);
+	IBA_SET(CM_MRA_LOCAL_COMM_ID, mra_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_MRA_REMOTE_COMM_ID, mra_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
+	IBA_SET(CM_MRA_SERVICE_TIMEOUT, mra_msg, service_timeout);
 
 	if (private_data && private_data_len)
-		memcpy(mra_msg->private_data, private_data, private_data_len);
+		IBA_SET_MEM(CM_MRA_PRIVATE_DATA, mra_msg, private_data,
+			    private_data_len);
 }
 
 static void cm_format_rej(struct cm_rej_msg *rej_msg,
@@ -1732,36 +1789,42 @@ static void cm_format_rej(struct cm_rej_msg *rej_msg,
 			  u8 private_data_len)
 {
 	cm_format_mad_hdr(&rej_msg->hdr, CM_REJ_ATTR_ID, cm_id_priv->tid);
-	rej_msg->remote_comm_id = cm_id_priv->id.remote_id;
+	IBA_SET(CM_REJ_REMOTE_COMM_ID, rej_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
 
 	switch(cm_id_priv->id.state) {
 	case IB_CM_REQ_RCVD:
-		rej_msg->local_comm_id = 0;
-		cm_rej_set_msg_rejected(rej_msg, CM_MSG_RESPONSE_REQ);
+		IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg, be32_to_cpu(0));
+		IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, CM_MSG_RESPONSE_REQ);
 		break;
 	case IB_CM_MRA_REQ_SENT:
-		rej_msg->local_comm_id = cm_id_priv->id.local_id;
-		cm_rej_set_msg_rejected(rej_msg, CM_MSG_RESPONSE_REQ);
+		IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg,
+			be32_to_cpu(cm_id_priv->id.local_id));
+		IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, CM_MSG_RESPONSE_REQ);
 		break;
 	case IB_CM_REP_RCVD:
 	case IB_CM_MRA_REP_SENT:
-		rej_msg->local_comm_id = cm_id_priv->id.local_id;
-		cm_rej_set_msg_rejected(rej_msg, CM_MSG_RESPONSE_REP);
+		IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg,
+			be32_to_cpu(cm_id_priv->id.local_id));
+		IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg, CM_MSG_RESPONSE_REP);
 		break;
 	default:
-		rej_msg->local_comm_id = cm_id_priv->id.local_id;
-		cm_rej_set_msg_rejected(rej_msg, CM_MSG_RESPONSE_OTHER);
+		IBA_SET(CM_REJ_LOCAL_COMM_ID, rej_msg,
+			be32_to_cpu(cm_id_priv->id.local_id));
+		IBA_SET(CM_REJ_MESSAGE_REJECTED, rej_msg,
+			CM_MSG_RESPONSE_OTHER);
 		break;
 	}
 
-	rej_msg->reason = cpu_to_be16(reason);
+	IBA_SET(CM_REJ_REASON, rej_msg, reason);
 	if (ari && ari_length) {
-		cm_rej_set_reject_info_len(rej_msg, ari_length);
-		memcpy(rej_msg->ari, ari, ari_length);
+		IBA_SET(CM_REJ_REJECTED_INFO_LENGTH, rej_msg, ari_length);
+		IBA_SET_MEM(CM_REJ_ARI, rej_msg, ari, ari_length);
 	}
 
 	if (private_data && private_data_len)
-		memcpy(rej_msg->private_data, private_data, private_data_len);
+		IBA_SET_MEM(CM_REJ_PRIVATE_DATA, rej_msg, private_data,
+			    private_data_len);
 }
 
 static void cm_dup_req_handler(struct cm_work *work,
@@ -1821,7 +1884,7 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
 	spin_lock_irq(&cm.lock);
 	timewait_info = cm_insert_remote_id(cm_id_priv->timewait_info);
 	if (timewait_info) {
-		cur_cm_id_priv = cm_get_id(timewait_info->work.local_id,
+		cur_cm_id_priv = cm_acquire_id(timewait_info->work.local_id,
 					   timewait_info->work.remote_id);
 		spin_unlock_irq(&cm.lock);
 		if (cur_cm_id_priv) {
@@ -1835,7 +1898,7 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
 	timewait_info = cm_insert_remote_qpn(cm_id_priv->timewait_info);
 	if (timewait_info) {
 		cm_cleanup_timewait(cm_id_priv->timewait_info);
-		cur_cm_id_priv = cm_get_id(timewait_info->work.local_id,
+		cur_cm_id_priv = cm_acquire_id(timewait_info->work.local_id,
 					   timewait_info->work.remote_id);
 
 		spin_unlock_irq(&cm.lock);
@@ -1851,8 +1914,9 @@ static struct cm_id_private * cm_match_req(struct cm_work *work,
 	}
 
 	/* Find matching listen request. */
-	listen_cm_id_priv = cm_find_listen(cm_id_priv->id.device,
-					   req_msg->service_id);
+	listen_cm_id_priv = cm_find_listen(
+		cm_id_priv->id.device,
+		cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg)));
 	if (!listen_cm_id_priv) {
 		cm_cleanup_timewait(cm_id_priv->timewait_info);
 		spin_unlock_irq(&cm.lock);
@@ -1877,24 +1941,32 @@ out:
  */
 static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 {
-	if (!cm_req_get_primary_subnet_local(req_msg)) {
-		if (req_msg->primary_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->primary_local_lid = ib_lid_be16(wc->slid);
-			cm_req_set_primary_sl(req_msg, wc->sl);
+	if (!IBA_GET(CM_REQ_PRIMARY_SUBNET_LOCAL, req_msg)) {
+		if (cpu_to_be16(IBA_GET(CM_REQ_PRIMARY_LOCAL_PORT_LID,
+					req_msg)) == IB_LID_PERMISSIVE) {
+			IBA_SET(CM_REQ_PRIMARY_LOCAL_PORT_LID, req_msg,
+				be16_to_cpu(ib_lid_be16(wc->slid)));
+			IBA_SET(CM_REQ_PRIMARY_SL, req_msg, wc->sl);
 		}
 
-		if (req_msg->primary_remote_lid == IB_LID_PERMISSIVE)
-			req_msg->primary_remote_lid = cpu_to_be16(wc->dlid_path_bits);
+		if (cpu_to_be16(IBA_GET(CM_REQ_PRIMARY_REMOTE_PORT_LID,
+					req_msg)) == IB_LID_PERMISSIVE)
+			IBA_SET(CM_REQ_PRIMARY_REMOTE_PORT_LID, req_msg,
+				wc->dlid_path_bits);
 	}
 
-	if (!cm_req_get_alt_subnet_local(req_msg)) {
-		if (req_msg->alt_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->alt_local_lid = ib_lid_be16(wc->slid);
-			cm_req_set_alt_sl(req_msg, wc->sl);
+	if (!IBA_GET(CM_REQ_ALTERNATE_SUBNET_LOCAL, req_msg)) {
+		if (cpu_to_be16(IBA_GET(CM_REQ_ALTERNATE_LOCAL_PORT_LID,
+					req_msg)) == IB_LID_PERMISSIVE) {
+			IBA_SET(CM_REQ_ALTERNATE_LOCAL_PORT_LID, req_msg,
+				be16_to_cpu(ib_lid_be16(wc->slid)));
+			IBA_SET(CM_REQ_ALTERNATE_SL, req_msg, wc->sl);
 		}
 
-		if (req_msg->alt_remote_lid == IB_LID_PERMISSIVE)
-			req_msg->alt_remote_lid = cpu_to_be16(wc->dlid_path_bits);
+		if (cpu_to_be16(IBA_GET(CM_REQ_ALTERNATE_REMOTE_PORT_LID,
+					req_msg)) == IB_LID_PERMISSIVE)
+			IBA_SET(CM_REQ_ALTERNATE_REMOTE_PORT_LID, req_msg,
+				wc->dlid_path_bits);
 	}
 }
 
@@ -1914,7 +1986,8 @@ static int cm_req_handler(struct cm_work *work)
 		return PTR_ERR(cm_id);
 
 	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-	cm_id_priv->id.remote_id = req_msg->local_comm_id;
+	cm_id_priv->id.remote_id =
+		cpu_to_be32(IBA_GET(CM_REQ_LOCAL_COMM_ID, req_msg));
 	ret = cm_init_av_for_response(work->port, work->mad_recv_wc->wc,
 				      work->mad_recv_wc->recv_buf.grh,
 				      &cm_id_priv->av);
@@ -1926,9 +1999,12 @@ static int cm_req_handler(struct cm_work *work)
 		ret = PTR_ERR(cm_id_priv->timewait_info);
 		goto destroy;
 	}
-	cm_id_priv->timewait_info->work.remote_id = req_msg->local_comm_id;
-	cm_id_priv->timewait_info->remote_ca_guid = req_msg->local_ca_guid;
-	cm_id_priv->timewait_info->remote_qpn = cm_req_get_local_qpn(req_msg);
+	cm_id_priv->timewait_info->work.remote_id =
+		cpu_to_be32(IBA_GET(CM_REQ_LOCAL_COMM_ID, req_msg));
+	cm_id_priv->timewait_info->remote_ca_guid =
+		cpu_to_be64(IBA_GET(CM_REQ_LOCAL_CA_GUID, req_msg));
+	cm_id_priv->timewait_info->remote_qpn =
+		cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
 
 	listen_cm_id_priv = cm_match_req(work, cm_id_priv);
 	if (!listen_cm_id_priv) {
@@ -1940,7 +2016,8 @@ static int cm_req_handler(struct cm_work *work)
 
 	cm_id_priv->id.cm_handler = listen_cm_id_priv->id.cm_handler;
 	cm_id_priv->id.context = listen_cm_id_priv->id.context;
-	cm_id_priv->id.service_id = req_msg->service_id;
+	cm_id_priv->id.service_id =
+		cpu_to_be64(IBA_GET(CM_REQ_SERVICE_ID, req_msg));
 	cm_id_priv->id.service_mask = ~cpu_to_be64(0);
 
 	cm_process_routed_req(req_msg, work->mad_recv_wc->wc);
@@ -1957,10 +2034,11 @@ static int cm_req_handler(struct cm_work *work)
 		work->path[0].rec_type =
 			sa_conv_gid_to_pathrec_type(gid_attr->gid_type);
 	} else {
-		cm_path_set_rec_type(work->port->cm_dev->ib_device,
-				     work->port->port_num,
-				     &work->path[0],
-				     &req_msg->primary_local_gid);
+		cm_path_set_rec_type(
+			work->port->cm_dev->ib_device, work->port->port_num,
+			&work->path[0],
+			IBA_GET_MEM_PTR(CM_REQ_PRIMARY_LOCAL_PORT_GID,
+					req_msg));
 	}
 	if (cm_req_has_alt_path(req_msg))
 		work->path[1].rec_type = work->path[0].rec_type;
@@ -2000,16 +2078,19 @@ static int cm_req_handler(struct cm_work *work)
 	}
 	cm_id_priv->tid = req_msg->hdr.tid;
 	cm_id_priv->timeout_ms = cm_convert_to_ms(
-					cm_req_get_local_resp_timeout(req_msg));
-	cm_id_priv->max_cm_retries = cm_req_get_max_cm_retries(req_msg);
-	cm_id_priv->remote_qpn = cm_req_get_local_qpn(req_msg);
-	cm_id_priv->initiator_depth = cm_req_get_resp_res(req_msg);
-	cm_id_priv->responder_resources = cm_req_get_init_depth(req_msg);
-	cm_id_priv->path_mtu = cm_req_get_path_mtu(req_msg);
-	cm_id_priv->pkey = req_msg->pkey;
-	cm_id_priv->sq_psn = cm_req_get_starting_psn(req_msg);
-	cm_id_priv->retry_count = cm_req_get_retry_count(req_msg);
-	cm_id_priv->rnr_retry_count = cm_req_get_rnr_retry_count(req_msg);
+		IBA_GET(CM_REQ_LOCAL_CM_RESPONSE_TIMEOUT, req_msg));
+	cm_id_priv->max_cm_retries = IBA_GET(CM_REQ_MAX_CM_RETRIES, req_msg);
+	cm_id_priv->remote_qpn =
+		cpu_to_be32(IBA_GET(CM_REQ_LOCAL_QPN, req_msg));
+	cm_id_priv->initiator_depth =
+		IBA_GET(CM_REQ_RESPONDER_RESOURCES, req_msg);
+	cm_id_priv->responder_resources =
+		IBA_GET(CM_REQ_INITIATOR_DEPTH, req_msg);
+	cm_id_priv->path_mtu = IBA_GET(CM_REQ_PATH_PACKET_PAYLOAD_MTU, req_msg);
+	cm_id_priv->pkey = cpu_to_be16(IBA_GET(CM_REQ_PARTITION_KEY, req_msg));
+	cm_id_priv->sq_psn = cpu_to_be32(IBA_GET(CM_REQ_STARTING_PSN, req_msg));
+	cm_id_priv->retry_count = IBA_GET(CM_REQ_RETRY_COUNT, req_msg);
+	cm_id_priv->rnr_retry_count = IBA_GET(CM_REQ_RNR_RETRY_COUNT, req_msg);
 	cm_id_priv->qp_type = cm_req_get_qp_type(req_msg);
 
 	cm_format_req_event(work, cm_id_priv, &listen_cm_id_priv->id);
@@ -2032,29 +2113,35 @@ static void cm_format_rep(struct cm_rep_msg *rep_msg,
 			  struct ib_cm_rep_param *param)
 {
 	cm_format_mad_hdr(&rep_msg->hdr, CM_REP_ATTR_ID, cm_id_priv->tid);
-	rep_msg->local_comm_id = cm_id_priv->id.local_id;
-	rep_msg->remote_comm_id = cm_id_priv->id.remote_id;
-	cm_rep_set_starting_psn(rep_msg, cpu_to_be32(param->starting_psn));
-	rep_msg->resp_resources = param->responder_resources;
-	cm_rep_set_target_ack_delay(rep_msg,
-				    cm_id_priv->av.port->cm_dev->ack_delay);
-	cm_rep_set_failover(rep_msg, param->failover_accepted);
-	cm_rep_set_rnr_retry_count(rep_msg, param->rnr_retry_count);
-	rep_msg->local_ca_guid = cm_id_priv->id.device->node_guid;
+	IBA_SET(CM_REP_LOCAL_COMM_ID, rep_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_REP_REMOTE_COMM_ID, rep_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
+	IBA_SET(CM_REP_STARTING_PSN, rep_msg, param->starting_psn);
+	IBA_SET(CM_REP_RESPONDER_RESOURCES, rep_msg,
+		param->responder_resources);
+	IBA_SET(CM_REP_TARGET_ACK_DELAY, rep_msg,
+		cm_id_priv->av.port->cm_dev->ack_delay);
+	IBA_SET(CM_REP_FAILOVER_ACCEPTED, rep_msg, param->failover_accepted);
+	IBA_SET(CM_REP_RNR_RETRY_COUNT, rep_msg, param->rnr_retry_count);
+	IBA_SET(CM_REP_LOCAL_CA_GUID, rep_msg,
+		be64_to_cpu(cm_id_priv->id.device->node_guid));
 
 	if (cm_id_priv->qp_type != IB_QPT_XRC_TGT) {
-		rep_msg->initiator_depth = param->initiator_depth;
-		cm_rep_set_flow_ctrl(rep_msg, param->flow_control);
-		cm_rep_set_srq(rep_msg, param->srq);
-		cm_rep_set_local_qpn(rep_msg, cpu_to_be32(param->qp_num));
+		IBA_SET(CM_REP_INITIATOR_DEPTH, rep_msg,
+			param->initiator_depth);
+		IBA_SET(CM_REP_END_TO_END_FLOW_CONTROL, rep_msg,
+			param->flow_control);
+		IBA_SET(CM_REP_SRQ, rep_msg, param->srq);
+		IBA_SET(CM_REP_LOCAL_QPN, rep_msg, param->qp_num);
 	} else {
-		cm_rep_set_srq(rep_msg, 1);
-		cm_rep_set_local_eecn(rep_msg, cpu_to_be32(param->qp_num));
+		IBA_SET(CM_REP_SRQ, rep_msg, 1);
+		IBA_SET(CM_REP_LOCAL_EE_CONTEXT_NUMBER, rep_msg, param->qp_num);
 	}
 
 	if (param->private_data && param->private_data_len)
-		memcpy(rep_msg->private_data, param->private_data,
-		       param->private_data_len);
+		IBA_SET_MEM(CM_REP_PRIVATE_DATA, rep_msg, param->private_data,
+			    param->private_data_len);
 }
 
 int ib_send_cm_rep(struct ib_cm_id *cm_id,
@@ -2100,7 +2187,7 @@ int ib_send_cm_rep(struct ib_cm_id *cm_id,
 	cm_id_priv->msg = msg;
 	cm_id_priv->initiator_depth = param->initiator_depth;
 	cm_id_priv->responder_resources = param->responder_resources;
-	cm_id_priv->rq_psn = cm_rep_get_starting_psn(rep_msg);
+	cm_id_priv->rq_psn = cpu_to_be32(IBA_GET(CM_REP_STARTING_PSN, rep_msg));
 	cm_id_priv->local_qpn = cpu_to_be32(param->qp_num & 0xFFFFFF);
 
 out:	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
@@ -2114,11 +2201,14 @@ static void cm_format_rtu(struct cm_rtu_msg *rtu_msg,
 			  u8 private_data_len)
 {
 	cm_format_mad_hdr(&rtu_msg->hdr, CM_RTU_ATTR_ID, cm_id_priv->tid);
-	rtu_msg->local_comm_id = cm_id_priv->id.local_id;
-	rtu_msg->remote_comm_id = cm_id_priv->id.remote_id;
+	IBA_SET(CM_RTU_LOCAL_COMM_ID, rtu_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_RTU_REMOTE_COMM_ID, rtu_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
 
 	if (private_data && private_data_len)
-		memcpy(rtu_msg->private_data, private_data, private_data_len);
+		IBA_SET_MEM(CM_RTU_PRIVATE_DATA, rtu_msg, private_data,
+			    private_data_len);
 }
 
 int ib_send_cm_rtu(struct ib_cm_id *cm_id,
@@ -2181,18 +2271,20 @@ static void cm_format_rep_event(struct cm_work *work, enum ib_qp_type qp_type)
 
 	rep_msg = (struct cm_rep_msg *)work->mad_recv_wc->recv_buf.mad;
 	param = &work->cm_event.param.rep_rcvd;
-	param->remote_ca_guid = rep_msg->local_ca_guid;
-	param->remote_qkey = be32_to_cpu(rep_msg->local_qkey);
+	param->remote_ca_guid =
+		cpu_to_be64(IBA_GET(CM_REP_LOCAL_CA_GUID, rep_msg));
+	param->remote_qkey = IBA_GET(CM_REP_LOCAL_Q_KEY, rep_msg);
 	param->remote_qpn = be32_to_cpu(cm_rep_get_qpn(rep_msg, qp_type));
-	param->starting_psn = be32_to_cpu(cm_rep_get_starting_psn(rep_msg));
-	param->responder_resources = rep_msg->initiator_depth;
-	param->initiator_depth = rep_msg->resp_resources;
-	param->target_ack_delay = cm_rep_get_target_ack_delay(rep_msg);
-	param->failover_accepted = cm_rep_get_failover(rep_msg);
-	param->flow_control = cm_rep_get_flow_ctrl(rep_msg);
-	param->rnr_retry_count = cm_rep_get_rnr_retry_count(rep_msg);
-	param->srq = cm_rep_get_srq(rep_msg);
-	work->cm_event.private_data = &rep_msg->private_data;
+	param->starting_psn = IBA_GET(CM_REP_STARTING_PSN, rep_msg);
+	param->responder_resources = IBA_GET(CM_REP_INITIATOR_DEPTH, rep_msg);
+	param->initiator_depth = IBA_GET(CM_REP_RESPONDER_RESOURCES, rep_msg);
+	param->target_ack_delay = IBA_GET(CM_REP_TARGET_ACK_DELAY, rep_msg);
+	param->failover_accepted = IBA_GET(CM_REP_FAILOVER_ACCEPTED, rep_msg);
+	param->flow_control = IBA_GET(CM_REP_END_TO_END_FLOW_CONTROL, rep_msg);
+	param->rnr_retry_count = IBA_GET(CM_REP_RNR_RETRY_COUNT, rep_msg);
+	param->srq = IBA_GET(CM_REP_SRQ, rep_msg);
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_REP_PRIVATE_DATA, rep_msg);
 }
 
 static void cm_dup_rep_handler(struct cm_work *work)
@@ -2203,8 +2295,9 @@ static void cm_dup_rep_handler(struct cm_work *work)
 	int ret;
 
 	rep_msg = (struct cm_rep_msg *) work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(rep_msg->remote_comm_id,
-				   rep_msg->local_comm_id);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg)),
+		cpu_to_be32(IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg)));
 	if (!cm_id_priv)
 		return;
 
@@ -2248,11 +2341,12 @@ static int cm_rep_handler(struct cm_work *work)
 	struct cm_timewait_info *timewait_info;
 
 	rep_msg = (struct cm_rep_msg *)work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(rep_msg->remote_comm_id, 0);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg)), 0);
 	if (!cm_id_priv) {
 		cm_dup_rep_handler(work);
 		pr_debug("%s: remote_comm_id %d, no cm_id_priv\n", __func__,
-			 be32_to_cpu(rep_msg->remote_comm_id));
+			 IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 		return -EINVAL;
 	}
 
@@ -2266,15 +2360,18 @@ static int cm_rep_handler(struct cm_work *work)
 	default:
 		spin_unlock_irq(&cm_id_priv->lock);
 		ret = -EINVAL;
-		pr_debug("%s: cm_id_priv->id.state: %d, local_comm_id %d, remote_comm_id %d\n",
-			 __func__, cm_id_priv->id.state,
-			 be32_to_cpu(rep_msg->local_comm_id),
-			 be32_to_cpu(rep_msg->remote_comm_id));
+		pr_debug(
+			"%s: cm_id_priv->id.state: %d, local_comm_id %d, remote_comm_id %d\n",
+			__func__, cm_id_priv->id.state,
+			IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
+			IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 		goto error;
 	}
 
-	cm_id_priv->timewait_info->work.remote_id = rep_msg->local_comm_id;
-	cm_id_priv->timewait_info->remote_ca_guid = rep_msg->local_ca_guid;
+	cm_id_priv->timewait_info->work.remote_id =
+		cpu_to_be32(IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg));
+	cm_id_priv->timewait_info->remote_ca_guid =
+		cpu_to_be64(IBA_GET(CM_REP_LOCAL_CA_GUID, rep_msg));
 	cm_id_priv->timewait_info->remote_qpn = cm_rep_get_qpn(rep_msg, cm_id_priv->qp_type);
 
 	spin_lock(&cm.lock);
@@ -2284,7 +2381,7 @@ static int cm_rep_handler(struct cm_work *work)
 		spin_unlock_irq(&cm_id_priv->lock);
 		ret = -EINVAL;
 		pr_debug("%s: Failed to insert remote id %d\n", __func__,
-			 be32_to_cpu(rep_msg->remote_comm_id));
+			 IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 		goto error;
 	}
 	/* Check for a stale connection. */
@@ -2293,7 +2390,7 @@ static int cm_rep_handler(struct cm_work *work)
 		rb_erase(&cm_id_priv->timewait_info->remote_id_node,
 			 &cm.remote_id_table);
 		cm_id_priv->timewait_info->inserted_remote_id = 0;
-		cur_cm_id_priv = cm_get_id(timewait_info->work.local_id,
+		cur_cm_id_priv = cm_acquire_id(timewait_info->work.local_id,
 					   timewait_info->work.remote_id);
 
 		spin_unlock(&cm.lock);
@@ -2302,9 +2399,10 @@ static int cm_rep_handler(struct cm_work *work)
 			     IB_CM_REJ_STALE_CONN, CM_MSG_RESPONSE_REP,
 			     NULL, 0);
 		ret = -EINVAL;
-		pr_debug("%s: Stale connection. local_comm_id %d, remote_comm_id %d\n",
-			 __func__, be32_to_cpu(rep_msg->local_comm_id),
-			 be32_to_cpu(rep_msg->remote_comm_id));
+		pr_debug(
+			"%s: Stale connection. local_comm_id %d, remote_comm_id %d\n",
+			__func__, IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg),
+			IBA_GET(CM_REP_REMOTE_COMM_ID, rep_msg));
 
 		if (cur_cm_id_priv) {
 			cm_id = &cur_cm_id_priv->id;
@@ -2317,13 +2415,17 @@ static int cm_rep_handler(struct cm_work *work)
 	spin_unlock(&cm.lock);
 
 	cm_id_priv->id.state = IB_CM_REP_RCVD;
-	cm_id_priv->id.remote_id = rep_msg->local_comm_id;
+	cm_id_priv->id.remote_id =
+		cpu_to_be32(IBA_GET(CM_REP_LOCAL_COMM_ID, rep_msg));
 	cm_id_priv->remote_qpn = cm_rep_get_qpn(rep_msg, cm_id_priv->qp_type);
-	cm_id_priv->initiator_depth = rep_msg->resp_resources;
-	cm_id_priv->responder_resources = rep_msg->initiator_depth;
-	cm_id_priv->sq_psn = cm_rep_get_starting_psn(rep_msg);
-	cm_id_priv->rnr_retry_count = cm_rep_get_rnr_retry_count(rep_msg);
-	cm_id_priv->target_ack_delay = cm_rep_get_target_ack_delay(rep_msg);
+	cm_id_priv->initiator_depth =
+		IBA_GET(CM_REP_RESPONDER_RESOURCES, rep_msg);
+	cm_id_priv->responder_resources =
+		IBA_GET(CM_REP_INITIATOR_DEPTH, rep_msg);
+	cm_id_priv->sq_psn = cpu_to_be32(IBA_GET(CM_REP_STARTING_PSN, rep_msg));
+	cm_id_priv->rnr_retry_count = IBA_GET(CM_REP_RNR_RETRY_COUNT, rep_msg);
+	cm_id_priv->target_ack_delay =
+		IBA_GET(CM_REP_TARGET_ACK_DELAY, rep_msg);
 	cm_id_priv->av.timeout =
 			cm_ack_timeout(cm_id_priv->target_ack_delay,
 				       cm_id_priv->av.timeout - 1);
@@ -2389,12 +2491,14 @@ static int cm_rtu_handler(struct cm_work *work)
 	int ret;
 
 	rtu_msg = (struct cm_rtu_msg *)work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(rtu_msg->remote_comm_id,
-				   rtu_msg->local_comm_id);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_RTU_REMOTE_COMM_ID, rtu_msg)),
+		cpu_to_be32(IBA_GET(CM_RTU_LOCAL_COMM_ID, rtu_msg)));
 	if (!cm_id_priv)
 		return -EINVAL;
 
-	work->cm_event.private_data = &rtu_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_RTU_PRIVATE_DATA, rtu_msg);
 
 	spin_lock_irq(&cm_id_priv->lock);
 	if (cm_id_priv->id.state != IB_CM_REP_SENT &&
@@ -2429,12 +2533,16 @@ static void cm_format_dreq(struct cm_dreq_msg *dreq_msg,
 {
 	cm_format_mad_hdr(&dreq_msg->hdr, CM_DREQ_ATTR_ID,
 			  cm_form_tid(cm_id_priv));
-	dreq_msg->local_comm_id = cm_id_priv->id.local_id;
-	dreq_msg->remote_comm_id = cm_id_priv->id.remote_id;
-	cm_dreq_set_remote_qpn(dreq_msg, cm_id_priv->remote_qpn);
+	IBA_SET(CM_DREQ_LOCAL_COMM_ID, dreq_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_DREQ_REMOTE_COMM_ID, dreq_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
+	IBA_SET(CM_DREQ_REMOTE_QPN_EECN, dreq_msg,
+		be32_to_cpu(cm_id_priv->remote_qpn));
 
 	if (private_data && private_data_len)
-		memcpy(dreq_msg->private_data, private_data, private_data_len);
+		IBA_SET_MEM(CM_DREQ_PRIVATE_DATA, dreq_msg, private_data,
+			    private_data_len);
 }
 
 int ib_send_cm_dreq(struct ib_cm_id *cm_id,
@@ -2494,11 +2602,14 @@ static void cm_format_drep(struct cm_drep_msg *drep_msg,
 			  u8 private_data_len)
 {
 	cm_format_mad_hdr(&drep_msg->hdr, CM_DREP_ATTR_ID, cm_id_priv->tid);
-	drep_msg->local_comm_id = cm_id_priv->id.local_id;
-	drep_msg->remote_comm_id = cm_id_priv->id.remote_id;
+	IBA_SET(CM_DREP_LOCAL_COMM_ID, drep_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_DREP_REMOTE_COMM_ID, drep_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
 
 	if (private_data && private_data_len)
-		memcpy(drep_msg->private_data, private_data, private_data_len);
+		IBA_SET_MEM(CM_DREP_PRIVATE_DATA, drep_msg, private_data,
+			    private_data_len);
 }
 
 int ib_send_cm_drep(struct ib_cm_id *cm_id,
@@ -2566,8 +2677,10 @@ static int cm_issue_drep(struct cm_port *port,
 	drep_msg = (struct cm_drep_msg *) msg->mad;
 
 	cm_format_mad_hdr(&drep_msg->hdr, CM_DREP_ATTR_ID, dreq_msg->hdr.tid);
-	drep_msg->remote_comm_id = dreq_msg->local_comm_id;
-	drep_msg->local_comm_id = dreq_msg->remote_comm_id;
+	IBA_SET(CM_DREP_REMOTE_COMM_ID, drep_msg,
+		IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg));
+	IBA_SET(CM_DREP_LOCAL_COMM_ID, drep_msg,
+		IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
 
 	ret = ib_post_send_mad(msg, NULL);
 	if (ret)
@@ -2584,22 +2697,26 @@ static int cm_dreq_handler(struct cm_work *work)
 	int ret;
 
 	dreq_msg = (struct cm_dreq_msg *)work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(dreq_msg->remote_comm_id,
-				   dreq_msg->local_comm_id);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg)),
+		cpu_to_be32(IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg)));
 	if (!cm_id_priv) {
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_DREQ_COUNTER]);
 		cm_issue_drep(work->port, work->mad_recv_wc);
-		pr_debug("%s: no cm_id_priv, local_comm_id %d, remote_comm_id %d\n",
-			 __func__, be32_to_cpu(dreq_msg->local_comm_id),
-			 be32_to_cpu(dreq_msg->remote_comm_id));
+		pr_debug(
+			"%s: no cm_id_priv, local_comm_id %d, remote_comm_id %d\n",
+			__func__, IBA_GET(CM_DREQ_LOCAL_COMM_ID, dreq_msg),
+			IBA_GET(CM_DREQ_REMOTE_COMM_ID, dreq_msg));
 		return -EINVAL;
 	}
 
-	work->cm_event.private_data = &dreq_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_DREQ_PRIVATE_DATA, dreq_msg);
 
 	spin_lock_irq(&cm_id_priv->lock);
-	if (cm_id_priv->local_qpn != cm_dreq_get_remote_qpn(dreq_msg))
+	if (cm_id_priv->local_qpn !=
+	    cpu_to_be32(IBA_GET(CM_DREQ_REMOTE_QPN_EECN, dreq_msg)))
 		goto unlock;
 
 	switch (cm_id_priv->id.state) {
@@ -2665,12 +2782,14 @@ static int cm_drep_handler(struct cm_work *work)
 	int ret;
 
 	drep_msg = (struct cm_drep_msg *)work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(drep_msg->remote_comm_id,
-				   drep_msg->local_comm_id);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_DREP_REMOTE_COMM_ID, drep_msg)),
+		cpu_to_be32(IBA_GET(CM_DREP_LOCAL_COMM_ID, drep_msg)));
 	if (!cm_id_priv)
 		return -EINVAL;
 
-	work->cm_event.private_data = &drep_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_DREP_PRIVATE_DATA, drep_msg);
 
 	spin_lock_irq(&cm_id_priv->lock);
 	if (cm_id_priv->id.state != IB_CM_DREQ_SENT &&
@@ -2766,10 +2885,11 @@ static void cm_format_rej_event(struct cm_work *work)
 
 	rej_msg = (struct cm_rej_msg *)work->mad_recv_wc->recv_buf.mad;
 	param = &work->cm_event.param.rej_rcvd;
-	param->ari = rej_msg->ari;
-	param->ari_length = cm_rej_get_reject_info_len(rej_msg);
-	param->reason = __be16_to_cpu(rej_msg->reason);
-	work->cm_event.private_data = &rej_msg->private_data;
+	param->ari = IBA_GET_MEM_PTR(CM_REJ_ARI, rej_msg);
+	param->ari_length = IBA_GET(CM_REJ_REJECTED_INFO_LENGTH, rej_msg);
+	param->reason = IBA_GET(CM_REJ_REASON, rej_msg);
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_REJ_PRIVATE_DATA, rej_msg);
 }
 
 static struct cm_id_private * cm_acquire_rejected_id(struct cm_rej_msg *rej_msg)
@@ -2778,29 +2898,29 @@ static struct cm_id_private * cm_acquire_rejected_id(struct cm_rej_msg *rej_msg)
 	struct cm_id_private *cm_id_priv;
 	__be32 remote_id;
 
-	remote_id = rej_msg->local_comm_id;
+	remote_id = cpu_to_be32(IBA_GET(CM_REJ_LOCAL_COMM_ID, rej_msg));
 
-	if (__be16_to_cpu(rej_msg->reason) == IB_CM_REJ_TIMEOUT) {
+	if (IBA_GET(CM_REJ_REASON, rej_msg) == IB_CM_REJ_TIMEOUT) {
 		spin_lock_irq(&cm.lock);
-		timewait_info = cm_find_remote_id( *((__be64 *) rej_msg->ari),
-						  remote_id);
+		timewait_info = cm_find_remote_id(
+			*((__be64 *)IBA_GET_MEM_PTR(CM_REJ_ARI, rej_msg)),
+			remote_id);
 		if (!timewait_info) {
 			spin_unlock_irq(&cm.lock);
 			return NULL;
 		}
-		cm_id_priv = xa_load(&cm.local_id_table,
-				cm_local_id(timewait_info->work.local_id));
-		if (cm_id_priv) {
-			if (cm_id_priv->id.remote_id == remote_id)
-				refcount_inc(&cm_id_priv->refcount);
-			else
-				cm_id_priv = NULL;
-		}
+		cm_id_priv =
+			cm_acquire_id(timewait_info->work.local_id, remote_id);
 		spin_unlock_irq(&cm.lock);
-	} else if (cm_rej_get_msg_rejected(rej_msg) == CM_MSG_RESPONSE_REQ)
-		cm_id_priv = cm_acquire_id(rej_msg->remote_comm_id, 0);
+	} else if (IBA_GET(CM_REJ_MESSAGE_REJECTED, rej_msg) ==
+		   CM_MSG_RESPONSE_REQ)
+		cm_id_priv = cm_acquire_id(
+			cpu_to_be32(IBA_GET(CM_REJ_REMOTE_COMM_ID, rej_msg)),
+			0);
 	else
-		cm_id_priv = cm_acquire_id(rej_msg->remote_comm_id, remote_id);
+		cm_id_priv = cm_acquire_id(
+			cpu_to_be32(IBA_GET(CM_REJ_REMOTE_COMM_ID, rej_msg)),
+			remote_id);
 
 	return cm_id_priv;
 }
@@ -2828,7 +2948,7 @@ static int cm_rej_handler(struct cm_work *work)
 		/* fall through */
 	case IB_CM_REQ_RCVD:
 	case IB_CM_MRA_REQ_SENT:
-		if (__be16_to_cpu(rej_msg->reason) == IB_CM_REJ_STALE_CONN)
+		if (IBA_GET(CM_REJ_REASON, rej_msg) == IB_CM_REJ_STALE_CONN)
 			cm_enter_timewait(cm_id_priv);
 		else
 			cm_reset_to_idle(cm_id_priv);
@@ -2958,13 +3078,16 @@ EXPORT_SYMBOL(ib_send_cm_mra);
 
 static struct cm_id_private * cm_acquire_mraed_id(struct cm_mra_msg *mra_msg)
 {
-	switch (cm_mra_get_msg_mraed(mra_msg)) {
+	switch (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg)) {
 	case CM_MSG_RESPONSE_REQ:
-		return cm_acquire_id(mra_msg->remote_comm_id, 0);
+		return cm_acquire_id(
+			cpu_to_be32(IBA_GET(CM_MRA_REMOTE_COMM_ID, mra_msg)),
+			0);
 	case CM_MSG_RESPONSE_REP:
 	case CM_MSG_RESPONSE_OTHER:
-		return cm_acquire_id(mra_msg->remote_comm_id,
-				     mra_msg->local_comm_id);
+		return cm_acquire_id(
+			cpu_to_be32(IBA_GET(CM_MRA_REMOTE_COMM_ID, mra_msg)),
+			cpu_to_be32(IBA_GET(CM_MRA_LOCAL_COMM_ID, mra_msg)));
 	default:
 		return NULL;
 	}
@@ -2981,30 +3104,34 @@ static int cm_mra_handler(struct cm_work *work)
 	if (!cm_id_priv)
 		return -EINVAL;
 
-	work->cm_event.private_data = &mra_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_MRA_PRIVATE_DATA, mra_msg);
 	work->cm_event.param.mra_rcvd.service_timeout =
-					cm_mra_get_service_timeout(mra_msg);
-	timeout = cm_convert_to_ms(cm_mra_get_service_timeout(mra_msg)) +
+		IBA_GET(CM_MRA_SERVICE_TIMEOUT, mra_msg);
+	timeout = cm_convert_to_ms(IBA_GET(CM_MRA_SERVICE_TIMEOUT, mra_msg)) +
 		  cm_convert_to_ms(cm_id_priv->av.timeout);
 
 	spin_lock_irq(&cm_id_priv->lock);
 	switch (cm_id_priv->id.state) {
 	case IB_CM_REQ_SENT:
-		if (cm_mra_get_msg_mraed(mra_msg) != CM_MSG_RESPONSE_REQ ||
+		if (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg) !=
+			    CM_MSG_RESPONSE_REQ ||
 		    ib_modify_mad(cm_id_priv->av.port->mad_agent,
 				  cm_id_priv->msg, timeout))
 			goto out;
 		cm_id_priv->id.state = IB_CM_MRA_REQ_RCVD;
 		break;
 	case IB_CM_REP_SENT:
-		if (cm_mra_get_msg_mraed(mra_msg) != CM_MSG_RESPONSE_REP ||
+		if (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg) !=
+			    CM_MSG_RESPONSE_REP ||
 		    ib_modify_mad(cm_id_priv->av.port->mad_agent,
 				  cm_id_priv->msg, timeout))
 			goto out;
 		cm_id_priv->id.state = IB_CM_MRA_REP_RCVD;
 		break;
 	case IB_CM_ESTABLISHED:
-		if (cm_mra_get_msg_mraed(mra_msg) != CM_MSG_RESPONSE_OTHER ||
+		if (IBA_GET(CM_MRA_MESSAGE_MRAED, mra_msg) !=
+			    CM_MSG_RESPONSE_OTHER ||
 		    cm_id_priv->id.lap_state != IB_CM_LAP_SENT ||
 		    ib_modify_mad(cm_id_priv->av.port->mad_agent,
 				  cm_id_priv->msg, timeout)) {
@@ -3046,117 +3173,23 @@ out:
 	return -EINVAL;
 }
 
-static void cm_format_lap(struct cm_lap_msg *lap_msg,
-			  struct cm_id_private *cm_id_priv,
-			  struct sa_path_rec *alternate_path,
-			  const void *private_data,
-			  u8 private_data_len)
-{
-	bool alt_ext = false;
-
-	if (alternate_path->rec_type == SA_PATH_REC_TYPE_OPA)
-		alt_ext = opa_is_extended_lid(alternate_path->opa.dlid,
-					      alternate_path->opa.slid);
-	cm_format_mad_hdr(&lap_msg->hdr, CM_LAP_ATTR_ID,
-			  cm_form_tid(cm_id_priv));
-	lap_msg->local_comm_id = cm_id_priv->id.local_id;
-	lap_msg->remote_comm_id = cm_id_priv->id.remote_id;
-	cm_lap_set_remote_qpn(lap_msg, cm_id_priv->remote_qpn);
-	/* todo: need remote CM response timeout */
-	cm_lap_set_remote_resp_timeout(lap_msg, 0x1F);
-	lap_msg->alt_local_lid =
-		htons(ntohl(sa_path_get_slid(alternate_path)));
-	lap_msg->alt_remote_lid =
-		htons(ntohl(sa_path_get_dlid(alternate_path)));
-	lap_msg->alt_local_gid = alternate_path->sgid;
-	lap_msg->alt_remote_gid = alternate_path->dgid;
-	if (alt_ext) {
-		lap_msg->alt_local_gid.global.interface_id
-			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.slid));
-		lap_msg->alt_remote_gid.global.interface_id
-			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.dlid));
-	}
-	cm_lap_set_flow_label(lap_msg, alternate_path->flow_label);
-	cm_lap_set_traffic_class(lap_msg, alternate_path->traffic_class);
-	lap_msg->alt_hop_limit = alternate_path->hop_limit;
-	cm_lap_set_packet_rate(lap_msg, alternate_path->rate);
-	cm_lap_set_sl(lap_msg, alternate_path->sl);
-	cm_lap_set_subnet_local(lap_msg, 1); /* local only... */
-	cm_lap_set_local_ack_timeout(lap_msg,
-		cm_ack_timeout(cm_id_priv->av.port->cm_dev->ack_delay,
-			       alternate_path->packet_life_time));
-
-	if (private_data && private_data_len)
-		memcpy(lap_msg->private_data, private_data, private_data_len);
-}
-
-int ib_send_cm_lap(struct ib_cm_id *cm_id,
-		   struct sa_path_rec *alternate_path,
-		   const void *private_data,
-		   u8 private_data_len)
-{
-	struct cm_id_private *cm_id_priv;
-	struct ib_mad_send_buf *msg;
-	unsigned long flags;
-	int ret;
-
-	if (private_data && private_data_len > IB_CM_LAP_PRIVATE_DATA_SIZE)
-		return -EINVAL;
-
-	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-	spin_lock_irqsave(&cm_id_priv->lock, flags);
-	if (cm_id->state != IB_CM_ESTABLISHED ||
-	    (cm_id->lap_state != IB_CM_LAP_UNINIT &&
-	     cm_id->lap_state != IB_CM_LAP_IDLE)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = cm_init_av_by_path(alternate_path, NULL, &cm_id_priv->alt_av,
-				 cm_id_priv);
-	if (ret)
-		goto out;
-	cm_id_priv->alt_av.timeout =
-			cm_ack_timeout(cm_id_priv->target_ack_delay,
-				       cm_id_priv->alt_av.timeout - 1);
-
-	ret = cm_alloc_msg(cm_id_priv, &msg);
-	if (ret)
-		goto out;
-
-	cm_format_lap((struct cm_lap_msg *) msg->mad, cm_id_priv,
-		      alternate_path, private_data, private_data_len);
-	msg->timeout_ms = cm_id_priv->timeout_ms;
-	msg->context[1] = (void *) (unsigned long) IB_CM_ESTABLISHED;
-
-	ret = ib_post_send_mad(msg, NULL);
-	if (ret) {
-		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-		cm_free_msg(msg);
-		return ret;
-	}
-
-	cm_id->lap_state = IB_CM_LAP_SENT;
-	cm_id_priv->msg = msg;
-
-out:	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(ib_send_cm_lap);
-
 static void cm_format_path_lid_from_lap(struct cm_lap_msg *lap_msg,
 					struct sa_path_rec *path)
 {
 	u32 lid;
 
 	if (path->rec_type != SA_PATH_REC_TYPE_OPA) {
-		sa_path_set_dlid(path, ntohs(lap_msg->alt_local_lid));
-		sa_path_set_slid(path, ntohs(lap_msg->alt_remote_lid));
+		sa_path_set_dlid(path, IBA_GET(CM_LAP_ALTERNATE_LOCAL_PORT_LID,
+					       lap_msg));
+		sa_path_set_slid(path, IBA_GET(CM_LAP_ALTERNATE_REMOTE_PORT_LID,
+					       lap_msg));
 	} else {
-		lid = opa_get_lid_from_gid(&lap_msg->alt_local_gid);
+		lid = opa_get_lid_from_gid(IBA_GET_MEM_PTR(
+			CM_LAP_ALTERNATE_LOCAL_PORT_GID, lap_msg));
 		sa_path_set_dlid(path, lid);
 
-		lid = opa_get_lid_from_gid(&lap_msg->alt_remote_gid);
+		lid = opa_get_lid_from_gid(IBA_GET_MEM_PTR(
+			CM_LAP_ALTERNATE_REMOTE_PORT_GID, lap_msg));
 		sa_path_set_slid(path, lid);
 	}
 }
@@ -3165,20 +3198,23 @@ static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 				    struct sa_path_rec *path,
 				    struct cm_lap_msg *lap_msg)
 {
-	path->dgid = lap_msg->alt_local_gid;
-	path->sgid = lap_msg->alt_remote_gid;
-	path->flow_label = cm_lap_get_flow_label(lap_msg);
-	path->hop_limit = lap_msg->alt_hop_limit;
-	path->traffic_class = cm_lap_get_traffic_class(lap_msg);
+	path->dgid = *IBA_GET_MEM_PTR(CM_LAP_ALTERNATE_LOCAL_PORT_GID, lap_msg);
+	path->sgid =
+		*IBA_GET_MEM_PTR(CM_LAP_ALTERNATE_REMOTE_PORT_GID, lap_msg);
+	path->flow_label =
+		cpu_to_be32(IBA_GET(CM_LAP_ALTERNATE_FLOW_LABEL, lap_msg));
+	path->hop_limit = IBA_GET(CM_LAP_ALTERNATE_HOP_LIMIT, lap_msg);
+	path->traffic_class = IBA_GET(CM_LAP_ALTERNATE_TRAFFIC_CLASS, lap_msg);
 	path->reversible = 1;
 	path->pkey = cm_id_priv->pkey;
-	path->sl = cm_lap_get_sl(lap_msg);
+	path->sl = IBA_GET(CM_LAP_ALTERNATE_SL, lap_msg);
 	path->mtu_selector = IB_SA_EQ;
 	path->mtu = cm_id_priv->path_mtu;
 	path->rate_selector = IB_SA_EQ;
-	path->rate = cm_lap_get_packet_rate(lap_msg);
+	path->rate = IBA_GET(CM_LAP_ALTERNATE_PACKET_RATE, lap_msg);
 	path->packet_life_time_selector = IB_SA_EQ;
-	path->packet_life_time = cm_lap_get_local_ack_timeout(lap_msg);
+	path->packet_life_time =
+		IBA_GET(CM_LAP_ALTERNATE_LOCAL_ACK_TIMEOUT, lap_msg);
 	path->packet_life_time -= (path->packet_life_time > 0);
 	cm_format_path_lid_from_lap(lap_msg, path);
 }
@@ -3200,20 +3236,22 @@ static int cm_lap_handler(struct cm_work *work)
 
 	/* todo: verify LAP request and send reject APR if invalid. */
 	lap_msg = (struct cm_lap_msg *)work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(lap_msg->remote_comm_id,
-				   lap_msg->local_comm_id);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_LAP_REMOTE_COMM_ID, lap_msg)),
+		cpu_to_be32(IBA_GET(CM_LAP_LOCAL_COMM_ID, lap_msg)));
 	if (!cm_id_priv)
 		return -EINVAL;
 
 	param = &work->cm_event.param.lap_rcvd;
 	memset(&work->path[0], 0, sizeof(work->path[1]));
 	cm_path_set_rec_type(work->port->cm_dev->ib_device,
-			     work->port->port_num,
-			     &work->path[0],
-			     &lap_msg->alt_local_gid);
+			     work->port->port_num, &work->path[0],
+			     IBA_GET_MEM_PTR(CM_LAP_ALTERNATE_LOCAL_PORT_GID,
+					     lap_msg));
 	param->alternate_path = &work->path[0];
 	cm_format_path_from_lap(cm_id_priv, param->alternate_path, lap_msg);
-	work->cm_event.private_data = &lap_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_LAP_PRIVATE_DATA, lap_msg);
 
 	spin_lock_irq(&cm_id_priv->lock);
 	if (cm_id_priv->id.state != IB_CM_ESTABLISHED)
@@ -3278,72 +3316,6 @@ deref:	cm_deref_id(cm_id_priv);
 	return -EINVAL;
 }
 
-static void cm_format_apr(struct cm_apr_msg *apr_msg,
-			  struct cm_id_private *cm_id_priv,
-			  enum ib_cm_apr_status status,
-			  void *info,
-			  u8 info_length,
-			  const void *private_data,
-			  u8 private_data_len)
-{
-	cm_format_mad_hdr(&apr_msg->hdr, CM_APR_ATTR_ID, cm_id_priv->tid);
-	apr_msg->local_comm_id = cm_id_priv->id.local_id;
-	apr_msg->remote_comm_id = cm_id_priv->id.remote_id;
-	apr_msg->ap_status = (u8) status;
-
-	if (info && info_length) {
-		apr_msg->info_length = info_length;
-		memcpy(apr_msg->info, info, info_length);
-	}
-
-	if (private_data && private_data_len)
-		memcpy(apr_msg->private_data, private_data, private_data_len);
-}
-
-int ib_send_cm_apr(struct ib_cm_id *cm_id,
-		   enum ib_cm_apr_status status,
-		   void *info,
-		   u8 info_length,
-		   const void *private_data,
-		   u8 private_data_len)
-{
-	struct cm_id_private *cm_id_priv;
-	struct ib_mad_send_buf *msg;
-	unsigned long flags;
-	int ret;
-
-	if ((private_data && private_data_len > IB_CM_APR_PRIVATE_DATA_SIZE) ||
-	    (info && info_length > IB_CM_APR_INFO_LENGTH))
-		return -EINVAL;
-
-	cm_id_priv = container_of(cm_id, struct cm_id_private, id);
-	spin_lock_irqsave(&cm_id_priv->lock, flags);
-	if (cm_id->state != IB_CM_ESTABLISHED ||
-	    (cm_id->lap_state != IB_CM_LAP_RCVD &&
-	     cm_id->lap_state != IB_CM_MRA_LAP_SENT)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	ret = cm_alloc_msg(cm_id_priv, &msg);
-	if (ret)
-		goto out;
-
-	cm_format_apr((struct cm_apr_msg *) msg->mad, cm_id_priv, status,
-		      info, info_length, private_data, private_data_len);
-	ret = ib_post_send_mad(msg, NULL);
-	if (ret) {
-		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-		cm_free_msg(msg);
-		return ret;
-	}
-
-	cm_id->lap_state = IB_CM_LAP_IDLE;
-out:	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-	return ret;
-}
-EXPORT_SYMBOL(ib_send_cm_apr);
-
 static int cm_apr_handler(struct cm_work *work)
 {
 	struct cm_id_private *cm_id_priv;
@@ -3358,15 +3330,20 @@ static int cm_apr_handler(struct cm_work *work)
 		return -EINVAL;
 
 	apr_msg = (struct cm_apr_msg *)work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(apr_msg->remote_comm_id,
-				   apr_msg->local_comm_id);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_APR_REMOTE_COMM_ID, apr_msg)),
+		cpu_to_be32(IBA_GET(CM_APR_LOCAL_COMM_ID, apr_msg)));
 	if (!cm_id_priv)
 		return -EINVAL; /* Unmatched reply. */
 
-	work->cm_event.param.apr_rcvd.ap_status = apr_msg->ap_status;
-	work->cm_event.param.apr_rcvd.apr_info = &apr_msg->info;
-	work->cm_event.param.apr_rcvd.info_len = apr_msg->info_length;
-	work->cm_event.private_data = &apr_msg->private_data;
+	work->cm_event.param.apr_rcvd.ap_status =
+		IBA_GET(CM_APR_AR_STATUS, apr_msg);
+	work->cm_event.param.apr_rcvd.apr_info =
+		IBA_GET_MEM_PTR(CM_APR_ADDITIONAL_INFORMATION, apr_msg);
+	work->cm_event.param.apr_rcvd.info_len =
+		IBA_GET(CM_APR_ADDITIONAL_INFORMATION_LENGTH, apr_msg);
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_APR_PRIVATE_DATA, apr_msg);
 
 	spin_lock_irq(&cm_id_priv->lock);
 	if (cm_id_priv->id.state != IB_CM_ESTABLISHED ||
@@ -3438,13 +3415,16 @@ static void cm_format_sidr_req(struct cm_sidr_req_msg *sidr_req_msg,
 {
 	cm_format_mad_hdr(&sidr_req_msg->hdr, CM_SIDR_REQ_ATTR_ID,
 			  cm_form_tid(cm_id_priv));
-	sidr_req_msg->request_id = cm_id_priv->id.local_id;
-	sidr_req_msg->pkey = param->path->pkey;
-	sidr_req_msg->service_id = param->service_id;
+	IBA_SET(CM_SIDR_REQ_REQUESTID, sidr_req_msg,
+		be32_to_cpu(cm_id_priv->id.local_id));
+	IBA_SET(CM_SIDR_REQ_PARTITION_KEY, sidr_req_msg,
+		be16_to_cpu(param->path->pkey));
+	IBA_SET(CM_SIDR_REQ_SERVICEID, sidr_req_msg,
+		be64_to_cpu(param->service_id));
 
 	if (param->private_data && param->private_data_len)
-		memcpy(sidr_req_msg->private_data, param->private_data,
-		       param->private_data_len);
+		IBA_SET_MEM(CM_SIDR_REQ_PRIVATE_DATA, sidr_req_msg,
+			    param->private_data, param->private_data_len);
 }
 
 int ib_send_cm_sidr_req(struct ib_cm_id *cm_id,
@@ -3508,13 +3488,15 @@ static void cm_format_sidr_req_event(struct cm_work *work,
 	sidr_req_msg = (struct cm_sidr_req_msg *)
 				work->mad_recv_wc->recv_buf.mad;
 	param = &work->cm_event.param.sidr_req_rcvd;
-	param->pkey = __be16_to_cpu(sidr_req_msg->pkey);
+	param->pkey = IBA_GET(CM_SIDR_REQ_PARTITION_KEY, sidr_req_msg);
 	param->listen_id = listen_id;
-	param->service_id = sidr_req_msg->service_id;
+	param->service_id =
+		cpu_to_be64(IBA_GET(CM_SIDR_REQ_SERVICEID, sidr_req_msg));
 	param->bth_pkey = cm_get_bth_pkey(work);
 	param->port = work->port->port_num;
 	param->sgid_attr = rx_cm_id->av.ah_attr.grh.sgid_attr;
-	work->cm_event.private_data = &sidr_req_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_SIDR_REQ_PRIVATE_DATA, sidr_req_msg);
 }
 
 static int cm_sidr_req_handler(struct cm_work *work)
@@ -3542,7 +3524,8 @@ static int cm_sidr_req_handler(struct cm_work *work)
 	if (ret)
 		goto out;
 
-	cm_id_priv->id.remote_id = sidr_req_msg->request_id;
+	cm_id_priv->id.remote_id =
+		cpu_to_be32(IBA_GET(CM_SIDR_REQ_REQUESTID, sidr_req_msg));
 	cm_id_priv->tid = sidr_req_msg->hdr.tid;
 	atomic_inc(&cm_id_priv->work_count);
 
@@ -3555,8 +3538,9 @@ static int cm_sidr_req_handler(struct cm_work *work)
 		goto out; /* Duplicate message. */
 	}
 	cm_id_priv->id.state = IB_CM_SIDR_REQ_RCVD;
-	cur_cm_id_priv = cm_find_listen(cm_id->device,
-					sidr_req_msg->service_id);
+	cur_cm_id_priv = cm_find_listen(
+		cm_id->device,
+		cpu_to_be64(IBA_GET(CM_SIDR_REQ_SERVICEID, sidr_req_msg)));
 	if (!cur_cm_id_priv) {
 		spin_unlock_irq(&cm.lock);
 		cm_reject_sidr_req(cm_id_priv, IB_SIDR_UNSUPPORTED);
@@ -3568,7 +3552,8 @@ static int cm_sidr_req_handler(struct cm_work *work)
 
 	cm_id_priv->id.cm_handler = cur_cm_id_priv->id.cm_handler;
 	cm_id_priv->id.context = cur_cm_id_priv->id.context;
-	cm_id_priv->id.service_id = sidr_req_msg->service_id;
+	cm_id_priv->id.service_id =
+		cpu_to_be64(IBA_GET(CM_SIDR_REQ_SERVICEID, sidr_req_msg));
 	cm_id_priv->id.service_mask = ~cpu_to_be64(0);
 
 	cm_format_sidr_req_event(work, cm_id_priv, &cur_cm_id_priv->id);
@@ -3586,18 +3571,21 @@ static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,
 {
 	cm_format_mad_hdr(&sidr_rep_msg->hdr, CM_SIDR_REP_ATTR_ID,
 			  cm_id_priv->tid);
-	sidr_rep_msg->request_id = cm_id_priv->id.remote_id;
-	sidr_rep_msg->status = param->status;
-	cm_sidr_rep_set_qpn(sidr_rep_msg, cpu_to_be32(param->qp_num));
-	sidr_rep_msg->service_id = cm_id_priv->id.service_id;
-	sidr_rep_msg->qkey = cpu_to_be32(param->qkey);
+	IBA_SET(CM_SIDR_REP_REQUESTID, sidr_rep_msg,
+		be32_to_cpu(cm_id_priv->id.remote_id));
+	IBA_SET(CM_SIDR_REP_STATUS, sidr_rep_msg, param->status);
+	IBA_SET(CM_SIDR_REP_QPN, sidr_rep_msg, param->qp_num);
+	IBA_SET(CM_SIDR_REP_SERVICEID, sidr_rep_msg,
+		be64_to_cpu(cm_id_priv->id.service_id));
+	IBA_SET(CM_SIDR_REP_Q_KEY, sidr_rep_msg, param->qkey);
 
 	if (param->info && param->info_length)
-		memcpy(sidr_rep_msg->info, param->info, param->info_length);
+		IBA_SET_MEM(CM_SIDR_REP_ADDITIONAL_INFORMATION, sidr_rep_msg,
+			    param->info, param->info_length);
 
 	if (param->private_data && param->private_data_len)
-		memcpy(sidr_rep_msg->private_data, param->private_data,
-		       param->private_data_len);
+		IBA_SET_MEM(CM_SIDR_REP_PRIVATE_DATA, sidr_rep_msg,
+			    param->private_data, param->private_data_len);
 }
 
 int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
@@ -3657,13 +3645,16 @@ static void cm_format_sidr_rep_event(struct cm_work *work,
 	sidr_rep_msg = (struct cm_sidr_rep_msg *)
 				work->mad_recv_wc->recv_buf.mad;
 	param = &work->cm_event.param.sidr_rep_rcvd;
-	param->status = sidr_rep_msg->status;
-	param->qkey = be32_to_cpu(sidr_rep_msg->qkey);
-	param->qpn = be32_to_cpu(cm_sidr_rep_get_qpn(sidr_rep_msg));
-	param->info = &sidr_rep_msg->info;
-	param->info_len = sidr_rep_msg->info_length;
+	param->status = IBA_GET(CM_SIDR_REP_STATUS, sidr_rep_msg);
+	param->qkey = IBA_GET(CM_SIDR_REP_Q_KEY, sidr_rep_msg);
+	param->qpn = IBA_GET(CM_SIDR_REP_QPN, sidr_rep_msg);
+	param->info = IBA_GET_MEM_PTR(CM_SIDR_REP_ADDITIONAL_INFORMATION,
+				      sidr_rep_msg);
+	param->info_len = IBA_GET(CM_SIDR_REP_ADDITIONAL_INFORMATION_LENGTH,
+				  sidr_rep_msg);
 	param->sgid_attr = cm_id_priv->av.ah_attr.grh.sgid_attr;
-	work->cm_event.private_data = &sidr_rep_msg->private_data;
+	work->cm_event.private_data =
+		IBA_GET_MEM_PTR(CM_SIDR_REP_PRIVATE_DATA, sidr_rep_msg);
 }
 
 static int cm_sidr_rep_handler(struct cm_work *work)
@@ -3673,7 +3664,8 @@ static int cm_sidr_rep_handler(struct cm_work *work)
 
 	sidr_rep_msg = (struct cm_sidr_rep_msg *)
 				work->mad_recv_wc->recv_buf.mad;
-	cm_id_priv = cm_acquire_id(sidr_rep_msg->request_id, 0);
+	cm_id_priv = cm_acquire_id(
+		cpu_to_be32(IBA_GET(CM_SIDR_REP_REQUESTID, sidr_rep_msg)), 0);
 	if (!cm_id_priv)
 		return -EINVAL; /* Unmatched reply. */
 
diff --git a/drivers/infiniband/core/cm_msgs.h b/drivers/infiniband/core/cm_msgs.h
index 92d7260ac913..0cc40656b5c5 100644
--- a/drivers/infiniband/core/cm_msgs.h
+++ b/drivers/infiniband/core/cm_msgs.h
@@ -8,6 +8,7 @@
 #ifndef CM_MSGS_H
 #define CM_MSGS_H
 
+#include <rdma/ibta_vol1_c12.h>
 #include <rdma/ib_mad.h>
 #include <rdma/ib_cm.h>
 
@@ -18,120 +19,14 @@
 
 #define IB_CM_CLASS_VERSION	2 /* IB specification 1.2 */
 
-struct cm_req_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 rsvd4;
-	__be64 service_id;
-	__be64 local_ca_guid;
-	__be32 rsvd24;
-	__be32 local_qkey;
-	/* local QPN:24, responder resources:8 */
-	__be32 offset32;
-	/* local EECN:24, initiator depth:8 */
-	__be32 offset36;
-	/*
-	 * remote EECN:24, remote CM response timeout:5,
-	 * transport service type:2, end-to-end flow control:1
-	 */
-	__be32 offset40;
-	/* starting PSN:24, local CM response timeout:5, retry count:3 */
-	__be32 offset44;
-	__be16 pkey;
-	/* path MTU:4, RDC exists:1, RNR retry count:3. */
-	u8 offset50;
-	/* max CM Retries:4, SRQ:1, extended transport type:3 */
-	u8 offset51;
-
-	__be16 primary_local_lid;
-	__be16 primary_remote_lid;
-	union ib_gid primary_local_gid;
-	union ib_gid primary_remote_gid;
-	/* flow label:20, rsvd:6, packet rate:6 */
-	__be32 primary_offset88;
-	u8 primary_traffic_class;
-	u8 primary_hop_limit;
-	/* SL:4, subnet local:1, rsvd:3 */
-	u8 primary_offset94;
-	/* local ACK timeout:5, rsvd:3 */
-	u8 primary_offset95;
-
-	__be16 alt_local_lid;
-	__be16 alt_remote_lid;
-	union ib_gid alt_local_gid;
-	union ib_gid alt_remote_gid;
-	/* flow label:20, rsvd:6, packet rate:6 */
-	__be32 alt_offset132;
-	u8 alt_traffic_class;
-	u8 alt_hop_limit;
-	/* SL:4, subnet local:1, rsvd:3 */
-	u8 alt_offset138;
-	/* local ACK timeout:5, rsvd:3 */
-	u8 alt_offset139;
-
-	u32 private_data[IB_CM_REQ_PRIVATE_DATA_SIZE / sizeof(u32)];
-
-} __packed;
-
-static inline __be32 cm_req_get_local_qpn(struct cm_req_msg *req_msg)
-{
-	return cpu_to_be32(be32_to_cpu(req_msg->offset32) >> 8);
-}
-
-static inline void cm_req_set_local_qpn(struct cm_req_msg *req_msg, __be32 qpn)
-{
-	req_msg->offset32 = cpu_to_be32((be32_to_cpu(qpn) << 8) |
-					 (be32_to_cpu(req_msg->offset32) &
-					  0x000000FF));
-}
-
-static inline u8 cm_req_get_resp_res(struct cm_req_msg *req_msg)
-{
-	return (u8) be32_to_cpu(req_msg->offset32);
-}
-
-static inline void cm_req_set_resp_res(struct cm_req_msg *req_msg, u8 resp_res)
-{
-	req_msg->offset32 = cpu_to_be32(resp_res |
-					(be32_to_cpu(req_msg->offset32) &
-					 0xFFFFFF00));
-}
-
-static inline u8 cm_req_get_init_depth(struct cm_req_msg *req_msg)
-{
-	return (u8) be32_to_cpu(req_msg->offset36);
-}
-
-static inline void cm_req_set_init_depth(struct cm_req_msg *req_msg,
-					 u8 init_depth)
-{
-	req_msg->offset36 = cpu_to_be32(init_depth |
-					(be32_to_cpu(req_msg->offset36) &
-					 0xFFFFFF00));
-}
-
-static inline u8 cm_req_get_remote_resp_timeout(struct cm_req_msg *req_msg)
-{
-	return (u8) ((be32_to_cpu(req_msg->offset40) & 0xF8) >> 3);
-}
-
-static inline void cm_req_set_remote_resp_timeout(struct cm_req_msg *req_msg,
-						  u8 resp_timeout)
-{
-	req_msg->offset40 = cpu_to_be32((resp_timeout << 3) |
-					 (be32_to_cpu(req_msg->offset40) &
-					  0xFFFFFF07));
-}
-
 static inline enum ib_qp_type cm_req_get_qp_type(struct cm_req_msg *req_msg)
 {
-	u8 transport_type = (u8) (be32_to_cpu(req_msg->offset40) & 0x06) >> 1;
+	u8 transport_type = IBA_GET(CM_REQ_TRANSPORT_SERVICE_TYPE, req_msg);
 	switch(transport_type) {
 	case 0: return IB_QPT_RC;
 	case 1: return IB_QPT_UC;
 	case 3:
-		switch (req_msg->offset51 & 0x7) {
+		switch (IBA_GET(CM_REQ_EXTENDED_TRANSPORT_TYPE, req_msg)) {
 		case 1: return IB_QPT_XRC_TGT;
 		default: return 0;
 		}
@@ -144,240 +39,17 @@ static inline void cm_req_set_qp_type(struct cm_req_msg *req_msg,
 {
 	switch(qp_type) {
 	case IB_QPT_UC:
-		req_msg->offset40 = cpu_to_be32((be32_to_cpu(
-						  req_msg->offset40) &
-						   0xFFFFFFF9) | 0x2);
+		IBA_SET(CM_REQ_TRANSPORT_SERVICE_TYPE, req_msg, 1);
 		break;
 	case IB_QPT_XRC_INI:
-		req_msg->offset40 = cpu_to_be32((be32_to_cpu(
-						 req_msg->offset40) &
-						   0xFFFFFFF9) | 0x6);
-		req_msg->offset51 = (req_msg->offset51 & 0xF8) | 1;
+		IBA_SET(CM_REQ_TRANSPORT_SERVICE_TYPE, req_msg, 3);
+		IBA_SET(CM_REQ_EXTENDED_TRANSPORT_TYPE, req_msg, 1);
 		break;
 	default:
-		req_msg->offset40 = cpu_to_be32(be32_to_cpu(
-						 req_msg->offset40) &
-						  0xFFFFFFF9);
+		IBA_SET(CM_REQ_TRANSPORT_SERVICE_TYPE, req_msg, 0);
 	}
 }
 
-static inline u8 cm_req_get_flow_ctrl(struct cm_req_msg *req_msg)
-{
-	return be32_to_cpu(req_msg->offset40) & 0x1;
-}
-
-static inline void cm_req_set_flow_ctrl(struct cm_req_msg *req_msg,
-					u8 flow_ctrl)
-{
-	req_msg->offset40 = cpu_to_be32((flow_ctrl & 0x1) |
-					 (be32_to_cpu(req_msg->offset40) &
-					  0xFFFFFFFE));
-}
-
-static inline __be32 cm_req_get_starting_psn(struct cm_req_msg *req_msg)
-{
-	return cpu_to_be32(be32_to_cpu(req_msg->offset44) >> 8);
-}
-
-static inline void cm_req_set_starting_psn(struct cm_req_msg *req_msg,
-					   __be32 starting_psn)
-{
-	req_msg->offset44 = cpu_to_be32((be32_to_cpu(starting_psn) << 8) |
-			    (be32_to_cpu(req_msg->offset44) & 0x000000FF));
-}
-
-static inline u8 cm_req_get_local_resp_timeout(struct cm_req_msg *req_msg)
-{
-	return (u8) ((be32_to_cpu(req_msg->offset44) & 0xF8) >> 3);
-}
-
-static inline void cm_req_set_local_resp_timeout(struct cm_req_msg *req_msg,
-						 u8 resp_timeout)
-{
-	req_msg->offset44 = cpu_to_be32((resp_timeout << 3) |
-			    (be32_to_cpu(req_msg->offset44) & 0xFFFFFF07));
-}
-
-static inline u8 cm_req_get_retry_count(struct cm_req_msg *req_msg)
-{
-	return (u8) (be32_to_cpu(req_msg->offset44) & 0x7);
-}
-
-static inline void cm_req_set_retry_count(struct cm_req_msg *req_msg,
-					  u8 retry_count)
-{
-	req_msg->offset44 = cpu_to_be32((retry_count & 0x7) |
-			    (be32_to_cpu(req_msg->offset44) & 0xFFFFFFF8));
-}
-
-static inline u8 cm_req_get_path_mtu(struct cm_req_msg *req_msg)
-{
-	return req_msg->offset50 >> 4;
-}
-
-static inline void cm_req_set_path_mtu(struct cm_req_msg *req_msg, u8 path_mtu)
-{
-	req_msg->offset50 = (u8) ((req_msg->offset50 & 0xF) | (path_mtu << 4));
-}
-
-static inline u8 cm_req_get_rnr_retry_count(struct cm_req_msg *req_msg)
-{
-	return req_msg->offset50 & 0x7;
-}
-
-static inline void cm_req_set_rnr_retry_count(struct cm_req_msg *req_msg,
-					      u8 rnr_retry_count)
-{
-	req_msg->offset50 = (u8) ((req_msg->offset50 & 0xF8) |
-				  (rnr_retry_count & 0x7));
-}
-
-static inline u8 cm_req_get_max_cm_retries(struct cm_req_msg *req_msg)
-{
-	return req_msg->offset51 >> 4;
-}
-
-static inline void cm_req_set_max_cm_retries(struct cm_req_msg *req_msg,
-					     u8 retries)
-{
-	req_msg->offset51 = (u8) ((req_msg->offset51 & 0xF) | (retries << 4));
-}
-
-static inline u8 cm_req_get_srq(struct cm_req_msg *req_msg)
-{
-	return (req_msg->offset51 & 0x8) >> 3;
-}
-
-static inline void cm_req_set_srq(struct cm_req_msg *req_msg, u8 srq)
-{
-	req_msg->offset51 = (u8) ((req_msg->offset51 & 0xF7) |
-				  ((srq & 0x1) << 3));
-}
-
-static inline __be32 cm_req_get_primary_flow_label(struct cm_req_msg *req_msg)
-{
-	return cpu_to_be32(be32_to_cpu(req_msg->primary_offset88) >> 12);
-}
-
-static inline void cm_req_set_primary_flow_label(struct cm_req_msg *req_msg,
-						 __be32 flow_label)
-{
-	req_msg->primary_offset88 = cpu_to_be32(
-				    (be32_to_cpu(req_msg->primary_offset88) &
-				     0x00000FFF) |
-				     (be32_to_cpu(flow_label) << 12));
-}
-
-static inline u8 cm_req_get_primary_packet_rate(struct cm_req_msg *req_msg)
-{
-	return (u8) (be32_to_cpu(req_msg->primary_offset88) & 0x3F);
-}
-
-static inline void cm_req_set_primary_packet_rate(struct cm_req_msg *req_msg,
-						  u8 rate)
-{
-	req_msg->primary_offset88 = cpu_to_be32(
-				    (be32_to_cpu(req_msg->primary_offset88) &
-				     0xFFFFFFC0) | (rate & 0x3F));
-}
-
-static inline u8 cm_req_get_primary_sl(struct cm_req_msg *req_msg)
-{
-	return (u8) (req_msg->primary_offset94 >> 4);
-}
-
-static inline void cm_req_set_primary_sl(struct cm_req_msg *req_msg, u8 sl)
-{
-	req_msg->primary_offset94 = (u8) ((req_msg->primary_offset94 & 0x0F) |
-					  (sl << 4));
-}
-
-static inline u8 cm_req_get_primary_subnet_local(struct cm_req_msg *req_msg)
-{
-	return (u8) ((req_msg->primary_offset94 & 0x08) >> 3);
-}
-
-static inline void cm_req_set_primary_subnet_local(struct cm_req_msg *req_msg,
-						   u8 subnet_local)
-{
-	req_msg->primary_offset94 = (u8) ((req_msg->primary_offset94 & 0xF7) |
-					  ((subnet_local & 0x1) << 3));
-}
-
-static inline u8 cm_req_get_primary_local_ack_timeout(struct cm_req_msg *req_msg)
-{
-	return (u8) (req_msg->primary_offset95 >> 3);
-}
-
-static inline void cm_req_set_primary_local_ack_timeout(struct cm_req_msg *req_msg,
-							u8 local_ack_timeout)
-{
-	req_msg->primary_offset95 = (u8) ((req_msg->primary_offset95 & 0x07) |
-					  (local_ack_timeout << 3));
-}
-
-static inline __be32 cm_req_get_alt_flow_label(struct cm_req_msg *req_msg)
-{
-	return cpu_to_be32(be32_to_cpu(req_msg->alt_offset132) >> 12);
-}
-
-static inline void cm_req_set_alt_flow_label(struct cm_req_msg *req_msg,
-					     __be32 flow_label)
-{
-	req_msg->alt_offset132 = cpu_to_be32(
-				 (be32_to_cpu(req_msg->alt_offset132) &
-				  0x00000FFF) |
-				  (be32_to_cpu(flow_label) << 12));
-}
-
-static inline u8 cm_req_get_alt_packet_rate(struct cm_req_msg *req_msg)
-{
-	return (u8) (be32_to_cpu(req_msg->alt_offset132) & 0x3F);
-}
-
-static inline void cm_req_set_alt_packet_rate(struct cm_req_msg *req_msg,
-					      u8 rate)
-{
-	req_msg->alt_offset132 = cpu_to_be32(
-				 (be32_to_cpu(req_msg->alt_offset132) &
-				  0xFFFFFFC0) | (rate & 0x3F));
-}
-
-static inline u8 cm_req_get_alt_sl(struct cm_req_msg *req_msg)
-{
-	return (u8) (req_msg->alt_offset138 >> 4);
-}
-
-static inline void cm_req_set_alt_sl(struct cm_req_msg *req_msg, u8 sl)
-{
-	req_msg->alt_offset138 = (u8) ((req_msg->alt_offset138 & 0x0F) |
-				       (sl << 4));
-}
-
-static inline u8 cm_req_get_alt_subnet_local(struct cm_req_msg *req_msg)
-{
-	return (u8) ((req_msg->alt_offset138 & 0x08) >> 3);
-}
-
-static inline void cm_req_set_alt_subnet_local(struct cm_req_msg *req_msg,
-					       u8 subnet_local)
-{
-	req_msg->alt_offset138 = (u8) ((req_msg->alt_offset138 & 0xF7) |
-				       ((subnet_local & 0x1) << 3));
-}
-
-static inline u8 cm_req_get_alt_local_ack_timeout(struct cm_req_msg *req_msg)
-{
-	return (u8) (req_msg->alt_offset139 >> 3);
-}
-
-static inline void cm_req_set_alt_local_ack_timeout(struct cm_req_msg *req_msg,
-						    u8 local_ack_timeout)
-{
-	req_msg->alt_offset139 = (u8) ((req_msg->alt_offset139 & 0x07) |
-				       (local_ack_timeout << 3));
-}
-
 /* Message REJected or MRAed */
 enum cm_msg_response {
 	CM_MSG_RESPONSE_REQ = 0x0,
@@ -385,419 +57,12 @@ enum cm_msg_response {
 	CM_MSG_RESPONSE_OTHER = 0x2
 };
 
- struct cm_mra_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-	/* message MRAed:2, rsvd:6 */
-	u8 offset8;
-	/* service timeout:5, rsvd:3 */
-	u8 offset9;
-
-	u8 private_data[IB_CM_MRA_PRIVATE_DATA_SIZE];
-
-} __packed;
-
-static inline u8 cm_mra_get_msg_mraed(struct cm_mra_msg *mra_msg)
-{
-	return (u8) (mra_msg->offset8 >> 6);
-}
-
-static inline void cm_mra_set_msg_mraed(struct cm_mra_msg *mra_msg, u8 msg)
-{
-	mra_msg->offset8 = (u8) ((mra_msg->offset8 & 0x3F) | (msg << 6));
-}
-
-static inline u8 cm_mra_get_service_timeout(struct cm_mra_msg *mra_msg)
-{
-	return (u8) (mra_msg->offset9 >> 3);
-}
-
-static inline void cm_mra_set_service_timeout(struct cm_mra_msg *mra_msg,
-					      u8 service_timeout)
-{
-	mra_msg->offset9 = (u8) ((mra_msg->offset9 & 0x07) |
-				 (service_timeout << 3));
-}
-
-struct cm_rej_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-	/* message REJected:2, rsvd:6 */
-	u8 offset8;
-	/* reject info length:7, rsvd:1. */
-	u8 offset9;
-	__be16 reason;
-	u8 ari[IB_CM_REJ_ARI_LENGTH];
-
-	u8 private_data[IB_CM_REJ_PRIVATE_DATA_SIZE];
-
-} __packed;
-
-static inline u8 cm_rej_get_msg_rejected(struct cm_rej_msg *rej_msg)
-{
-	return (u8) (rej_msg->offset8 >> 6);
-}
-
-static inline void cm_rej_set_msg_rejected(struct cm_rej_msg *rej_msg, u8 msg)
-{
-	rej_msg->offset8 = (u8) ((rej_msg->offset8 & 0x3F) | (msg << 6));
-}
-
-static inline u8 cm_rej_get_reject_info_len(struct cm_rej_msg *rej_msg)
-{
-	return (u8) (rej_msg->offset9 >> 1);
-}
-
-static inline void cm_rej_set_reject_info_len(struct cm_rej_msg *rej_msg,
-					      u8 len)
-{
-	rej_msg->offset9 = (u8) ((rej_msg->offset9 & 0x1) | (len << 1));
-}
-
-struct cm_rep_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-	__be32 local_qkey;
-	/* local QPN:24, rsvd:8 */
-	__be32 offset12;
-	/* local EECN:24, rsvd:8 */
-	__be32 offset16;
-	/* starting PSN:24 rsvd:8 */
-	__be32 offset20;
-	u8 resp_resources;
-	u8 initiator_depth;
-	/* target ACK delay:5, failover accepted:2, end-to-end flow control:1 */
-	u8 offset26;
-	/* RNR retry count:3, SRQ:1, rsvd:5 */
-	u8 offset27;
-	__be64 local_ca_guid;
-
-	u8 private_data[IB_CM_REP_PRIVATE_DATA_SIZE];
-
-} __packed;
-
-static inline __be32 cm_rep_get_local_qpn(struct cm_rep_msg *rep_msg)
-{
-	return cpu_to_be32(be32_to_cpu(rep_msg->offset12) >> 8);
-}
-
-static inline void cm_rep_set_local_qpn(struct cm_rep_msg *rep_msg, __be32 qpn)
-{
-	rep_msg->offset12 = cpu_to_be32((be32_to_cpu(qpn) << 8) |
-			    (be32_to_cpu(rep_msg->offset12) & 0x000000FF));
-}
-
-static inline __be32 cm_rep_get_local_eecn(struct cm_rep_msg *rep_msg)
-{
-	return cpu_to_be32(be32_to_cpu(rep_msg->offset16) >> 8);
-}
-
-static inline void cm_rep_set_local_eecn(struct cm_rep_msg *rep_msg, __be32 eecn)
-{
-	rep_msg->offset16 = cpu_to_be32((be32_to_cpu(eecn) << 8) |
-			    (be32_to_cpu(rep_msg->offset16) & 0x000000FF));
-}
-
 static inline __be32 cm_rep_get_qpn(struct cm_rep_msg *rep_msg, enum ib_qp_type qp_type)
 {
 	return (qp_type == IB_QPT_XRC_INI) ?
-		cm_rep_get_local_eecn(rep_msg) : cm_rep_get_local_qpn(rep_msg);
-}
-
-static inline __be32 cm_rep_get_starting_psn(struct cm_rep_msg *rep_msg)
-{
-	return cpu_to_be32(be32_to_cpu(rep_msg->offset20) >> 8);
-}
-
-static inline void cm_rep_set_starting_psn(struct cm_rep_msg *rep_msg,
-					   __be32 starting_psn)
-{
-	rep_msg->offset20 = cpu_to_be32((be32_to_cpu(starting_psn) << 8) |
-			    (be32_to_cpu(rep_msg->offset20) & 0x000000FF));
-}
-
-static inline u8 cm_rep_get_target_ack_delay(struct cm_rep_msg *rep_msg)
-{
-	return (u8) (rep_msg->offset26 >> 3);
-}
-
-static inline void cm_rep_set_target_ack_delay(struct cm_rep_msg *rep_msg,
-					       u8 target_ack_delay)
-{
-	rep_msg->offset26 = (u8) ((rep_msg->offset26 & 0x07) |
-				  (target_ack_delay << 3));
-}
-
-static inline u8 cm_rep_get_failover(struct cm_rep_msg *rep_msg)
-{
-	return (u8) ((rep_msg->offset26 & 0x06) >> 1);
-}
-
-static inline void cm_rep_set_failover(struct cm_rep_msg *rep_msg, u8 failover)
-{
-	rep_msg->offset26 = (u8) ((rep_msg->offset26 & 0xF9) |
-				  ((failover & 0x3) << 1));
-}
-
-static inline u8 cm_rep_get_flow_ctrl(struct cm_rep_msg *rep_msg)
-{
-	return (u8) (rep_msg->offset26 & 0x01);
-}
-
-static inline void cm_rep_set_flow_ctrl(struct cm_rep_msg *rep_msg,
-					    u8 flow_ctrl)
-{
-	rep_msg->offset26 = (u8) ((rep_msg->offset26 & 0xFE) |
-				  (flow_ctrl & 0x1));
-}
-
-static inline u8 cm_rep_get_rnr_retry_count(struct cm_rep_msg *rep_msg)
-{
-	return (u8) (rep_msg->offset27 >> 5);
-}
-
-static inline void cm_rep_set_rnr_retry_count(struct cm_rep_msg *rep_msg,
-					      u8 rnr_retry_count)
-{
-	rep_msg->offset27 = (u8) ((rep_msg->offset27 & 0x1F) |
-				  (rnr_retry_count << 5));
-}
-
-static inline u8 cm_rep_get_srq(struct cm_rep_msg *rep_msg)
-{
-	return (u8) ((rep_msg->offset27 >> 4) & 0x1);
-}
-
-static inline void cm_rep_set_srq(struct cm_rep_msg *rep_msg, u8 srq)
-{
-	rep_msg->offset27 = (u8) ((rep_msg->offset27 & 0xEF) |
-				  ((srq & 0x1) << 4));
-}
-
-struct cm_rtu_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-
-	u8 private_data[IB_CM_RTU_PRIVATE_DATA_SIZE];
-
-} __packed;
-
-struct cm_dreq_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-	/* remote QPN/EECN:24, rsvd:8 */
-	__be32 offset8;
-
-	u8 private_data[IB_CM_DREQ_PRIVATE_DATA_SIZE];
-
-} __packed;
-
-static inline __be32 cm_dreq_get_remote_qpn(struct cm_dreq_msg *dreq_msg)
-{
-	return cpu_to_be32(be32_to_cpu(dreq_msg->offset8) >> 8);
-}
-
-static inline void cm_dreq_set_remote_qpn(struct cm_dreq_msg *dreq_msg, __be32 qpn)
-{
-	dreq_msg->offset8 = cpu_to_be32((be32_to_cpu(qpn) << 8) |
-			    (be32_to_cpu(dreq_msg->offset8) & 0x000000FF));
-}
-
-struct cm_drep_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-
-	u8 private_data[IB_CM_DREP_PRIVATE_DATA_SIZE];
-
-} __packed;
-
-struct cm_lap_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-
-	__be32 rsvd8;
-	/* remote QPN/EECN:24, remote CM response timeout:5, rsvd:3 */
-	__be32 offset12;
-	__be32 rsvd16;
-
-	__be16 alt_local_lid;
-	__be16 alt_remote_lid;
-	union ib_gid alt_local_gid;
-	union ib_gid alt_remote_gid;
-	/* flow label:20, rsvd:4, traffic class:8 */
-	__be32 offset56;
-	u8 alt_hop_limit;
-	/* rsvd:2, packet rate:6 */
-	u8 offset61;
-	/* SL:4, subnet local:1, rsvd:3 */
-	u8 offset62;
-	/* local ACK timeout:5, rsvd:3 */
-	u8 offset63;
-
-	u8 private_data[IB_CM_LAP_PRIVATE_DATA_SIZE];
-} __packed;
-
-static inline __be32 cm_lap_get_remote_qpn(struct cm_lap_msg *lap_msg)
-{
-	return cpu_to_be32(be32_to_cpu(lap_msg->offset12) >> 8);
-}
-
-static inline void cm_lap_set_remote_qpn(struct cm_lap_msg *lap_msg, __be32 qpn)
-{
-	lap_msg->offset12 = cpu_to_be32((be32_to_cpu(qpn) << 8) |
-					 (be32_to_cpu(lap_msg->offset12) &
-					  0x000000FF));
-}
-
-static inline u8 cm_lap_get_remote_resp_timeout(struct cm_lap_msg *lap_msg)
-{
-	return (u8) ((be32_to_cpu(lap_msg->offset12) & 0xF8) >> 3);
-}
-
-static inline void cm_lap_set_remote_resp_timeout(struct cm_lap_msg *lap_msg,
-						  u8 resp_timeout)
-{
-	lap_msg->offset12 = cpu_to_be32((resp_timeout << 3) |
-					 (be32_to_cpu(lap_msg->offset12) &
-					  0xFFFFFF07));
-}
-
-static inline __be32 cm_lap_get_flow_label(struct cm_lap_msg *lap_msg)
-{
-	return cpu_to_be32(be32_to_cpu(lap_msg->offset56) >> 12);
-}
-
-static inline void cm_lap_set_flow_label(struct cm_lap_msg *lap_msg,
-					 __be32 flow_label)
-{
-	lap_msg->offset56 = cpu_to_be32(
-				 (be32_to_cpu(lap_msg->offset56) & 0x00000FFF) |
-				 (be32_to_cpu(flow_label) << 12));
-}
-
-static inline u8 cm_lap_get_traffic_class(struct cm_lap_msg *lap_msg)
-{
-	return (u8) be32_to_cpu(lap_msg->offset56);
-}
-
-static inline void cm_lap_set_traffic_class(struct cm_lap_msg *lap_msg,
-					    u8 traffic_class)
-{
-	lap_msg->offset56 = cpu_to_be32(traffic_class |
-					 (be32_to_cpu(lap_msg->offset56) &
-					  0xFFFFFF00));
-}
-
-static inline u8 cm_lap_get_packet_rate(struct cm_lap_msg *lap_msg)
-{
-	return lap_msg->offset61 & 0x3F;
-}
-
-static inline void cm_lap_set_packet_rate(struct cm_lap_msg *lap_msg,
-					  u8 packet_rate)
-{
-	lap_msg->offset61 = (packet_rate & 0x3F) | (lap_msg->offset61 & 0xC0);
-}
-
-static inline u8 cm_lap_get_sl(struct cm_lap_msg *lap_msg)
-{
-	return lap_msg->offset62 >> 4;
-}
-
-static inline void cm_lap_set_sl(struct cm_lap_msg *lap_msg, u8 sl)
-{
-	lap_msg->offset62 = (sl << 4) | (lap_msg->offset62 & 0x0F);
-}
-
-static inline u8 cm_lap_get_subnet_local(struct cm_lap_msg *lap_msg)
-{
-	return (lap_msg->offset62 >> 3) & 0x1;
-}
-
-static inline void cm_lap_set_subnet_local(struct cm_lap_msg *lap_msg,
-					   u8 subnet_local)
-{
-	lap_msg->offset62 = ((subnet_local & 0x1) << 3) |
-			     (lap_msg->offset61 & 0xF7);
-}
-static inline u8 cm_lap_get_local_ack_timeout(struct cm_lap_msg *lap_msg)
-{
-	return lap_msg->offset63 >> 3;
-}
-
-static inline void cm_lap_set_local_ack_timeout(struct cm_lap_msg *lap_msg,
-						u8 local_ack_timeout)
-{
-	lap_msg->offset63 = (local_ack_timeout << 3) |
-			    (lap_msg->offset63 & 0x07);
-}
-
-struct cm_apr_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 local_comm_id;
-	__be32 remote_comm_id;
-
-	u8 info_length;
-	u8 ap_status;
-	__be16 rsvd;
-	u8 info[IB_CM_APR_INFO_LENGTH];
-
-	u8 private_data[IB_CM_APR_PRIVATE_DATA_SIZE];
-} __packed;
-
-struct cm_sidr_req_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 request_id;
-	__be16 pkey;
-	__be16 rsvd;
-	__be64 service_id;
-
-	u32 private_data[IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE / sizeof(u32)];
-} __packed;
-
-struct cm_sidr_rep_msg {
-	struct ib_mad_hdr hdr;
-
-	__be32 request_id;
-	u8 status;
-	u8 info_length;
-	__be16 rsvd;
-	/* QPN:24, rsvd:8 */
-	__be32 offset8;
-	__be64 service_id;
-	__be32 qkey;
-	u8 info[IB_CM_SIDR_REP_INFO_LENGTH];
-
-	u8 private_data[IB_CM_SIDR_REP_PRIVATE_DATA_SIZE];
-} __packed;
-
-static inline __be32 cm_sidr_rep_get_qpn(struct cm_sidr_rep_msg *sidr_rep_msg)
-{
-	return cpu_to_be32(be32_to_cpu(sidr_rep_msg->offset8) >> 8);
-}
-
-static inline void cm_sidr_rep_set_qpn(struct cm_sidr_rep_msg *sidr_rep_msg,
-				       __be32 qpn)
-{
-	sidr_rep_msg->offset8 = cpu_to_be32((be32_to_cpu(qpn) << 8) |
-					(be32_to_cpu(sidr_rep_msg->offset8) &
-					 0x000000FF));
+		       cpu_to_be32(IBA_GET(CM_REP_LOCAL_EE_CONTEXT_NUMBER,
+					   rep_msg)) :
+		       cpu_to_be32(IBA_GET(CM_REP_LOCAL_QPN, rep_msg));
 }
 
 #endif /* CM_MSGS_H */
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 43a6f07e0afe..72f032160c4b 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -36,6 +36,7 @@
 
 #include "core_priv.h"
 #include "cma_priv.h"
+#include "cma_trace.h"
 
 MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("Generic RDMA CM Agent");
@@ -877,6 +878,7 @@ struct rdma_cm_id *__rdma_create_id(struct net *net,
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
 	id_priv->seq_num &= 0x00ffffff;
 
+	trace_cm_id_create(id_priv);
 	return &id_priv->id;
 }
 EXPORT_SYMBOL(__rdma_create_id);
@@ -928,27 +930,34 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
 	int ret;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
-	if (id->device != pd->device)
-		return -EINVAL;
+	if (id->device != pd->device) {
+		ret = -EINVAL;
+		goto out_err;
+	}
 
 	qp_init_attr->port_num = id->port_num;
 	qp = ib_create_qp(pd, qp_init_attr);
-	if (IS_ERR(qp))
-		return PTR_ERR(qp);
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
+		goto out_err;
+	}
 
 	if (id->qp_type == IB_QPT_UD)
 		ret = cma_init_ud_qp(id_priv, qp);
 	else
 		ret = cma_init_conn_qp(id_priv, qp);
 	if (ret)
-		goto err;
+		goto out_destroy;
 
 	id->qp = qp;
 	id_priv->qp_num = qp->qp_num;
 	id_priv->srq = (qp->srq != NULL);
+	trace_cm_qp_create(id_priv, pd, qp_init_attr, 0);
 	return 0;
-err:
+out_destroy:
 	ib_destroy_qp(qp);
+out_err:
+	trace_cm_qp_create(id_priv, pd, qp_init_attr, ret);
 	return ret;
 }
 EXPORT_SYMBOL(rdma_create_qp);
@@ -958,6 +967,7 @@ void rdma_destroy_qp(struct rdma_cm_id *id)
 	struct rdma_id_private *id_priv;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
+	trace_cm_qp_destroy(id_priv);
 	mutex_lock(&id_priv->qp_mutex);
 	ib_destroy_qp(id_priv->id.qp);
 	id_priv->id.qp = NULL;
@@ -1811,6 +1821,7 @@ void rdma_destroy_id(struct rdma_cm_id *id)
 	enum rdma_cm_state state;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
+	trace_cm_id_destroy(id_priv);
 	state = cma_exch(id_priv, RDMA_CM_DESTROYING);
 	cma_cancel_operation(id_priv, state);
 
@@ -1863,6 +1874,7 @@ static int cma_rep_recv(struct rdma_id_private *id_priv)
 	if (ret)
 		goto reject;
 
+	trace_cm_send_rtu(id_priv);
 	ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0);
 	if (ret)
 		goto reject;
@@ -1871,6 +1883,7 @@ static int cma_rep_recv(struct rdma_id_private *id_priv)
 reject:
 	pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret);
 	cma_modify_qp_err(id_priv);
+	trace_cm_send_rej(id_priv);
 	ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED,
 		       NULL, 0, NULL, 0);
 	return ret;
@@ -1890,6 +1903,17 @@ static void cma_set_rep_event_data(struct rdma_cm_event *event,
 	event->param.conn.qp_num = rep_data->remote_qpn;
 }
 
+static int cma_cm_event_handler(struct rdma_id_private *id_priv,
+				struct rdma_cm_event *event)
+{
+	int ret;
+
+	trace_cm_event_handler(id_priv, event);
+	ret = id_priv->id.event_handler(&id_priv->id, event);
+	trace_cm_event_done(id_priv, event, ret);
+	return ret;
+}
+
 static int cma_ib_handler(struct ib_cm_id *cm_id,
 			  const struct ib_cm_event *ib_event)
 {
@@ -1912,8 +1936,10 @@ static int cma_ib_handler(struct ib_cm_id *cm_id,
 		break;
 	case IB_CM_REP_RECEIVED:
 		if (cma_comp(id_priv, RDMA_CM_CONNECT) &&
-		    (id_priv->id.qp_type != IB_QPT_UD))
+		    (id_priv->id.qp_type != IB_QPT_UD)) {
+			trace_cm_send_mra(id_priv);
 			ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
+		}
 		if (id_priv->id.qp) {
 			event.status = cma_rep_recv(id_priv);
 			event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR :
@@ -1958,7 +1984,7 @@ static int cma_ib_handler(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 	if (ret) {
 		/* Destroy the CM ID by returning a non-zero value. */
 		id_priv->cm_id.ib = NULL;
@@ -2119,6 +2145,7 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id,
 	if (IS_ERR(listen_id))
 		return PTR_ERR(listen_id);
 
+	trace_cm_req_handler(listen_id, ib_event->event);
 	if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) {
 		ret = -EINVAL;
 		goto net_dev_put;
@@ -2161,7 +2188,7 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id,
 	 * until we're done accessing it.
 	 */
 	atomic_inc(&conn_id->refcount);
-	ret = conn_id->id.event_handler(&conn_id->id, &event);
+	ret = cma_cm_event_handler(conn_id, &event);
 	if (ret)
 		goto err3;
 	/*
@@ -2170,8 +2197,10 @@ static int cma_ib_req_handler(struct ib_cm_id *cm_id,
 	 */
 	mutex_lock(&lock);
 	if (cma_comp(conn_id, RDMA_CM_CONNECT) &&
-	    (conn_id->id.qp_type != IB_QPT_UD))
+	    (conn_id->id.qp_type != IB_QPT_UD)) {
+		trace_cm_send_mra(cm_id->context);
 		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
+	}
 	mutex_unlock(&lock);
 	mutex_unlock(&conn_id->handler_mutex);
 	mutex_unlock(&listen_id->handler_mutex);
@@ -2286,7 +2315,7 @@ static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event)
 	event.status = iw_event->status;
 	event.param.conn.private_data = iw_event->private_data;
 	event.param.conn.private_data_len = iw_event->private_data_len;
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 	if (ret) {
 		/* Destroy the CM ID by returning a non-zero value. */
 		id_priv->cm_id.iw = NULL;
@@ -2363,7 +2392,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 	 * until we're done accessing it.
 	 */
 	atomic_inc(&conn_id->refcount);
-	ret = conn_id->id.event_handler(&conn_id->id, &event);
+	ret = cma_cm_event_handler(conn_id, &event);
 	if (ret) {
 		/* User wants to destroy the CM ID */
 		conn_id->cm_id.iw = NULL;
@@ -2435,6 +2464,7 @@ static int cma_listen_handler(struct rdma_cm_id *id,
 
 	id->context = id_priv->id.context;
 	id->event_handler = id_priv->id.event_handler;
+	trace_cm_event_handler(id_priv, event);
 	return id_priv->id.event_handler(id, event);
 }
 
@@ -2611,7 +2641,7 @@ static void cma_work_handler(struct work_struct *_work)
 	if (!cma_comp_exch(id_priv, work->old_state, work->new_state))
 		goto out;
 
-	if (id_priv->id.event_handler(&id_priv->id, &work->event)) {
+	if (cma_cm_event_handler(id_priv, &work->event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
 		destroy = 1;
 	}
@@ -2634,7 +2664,7 @@ static void cma_ndev_work_handler(struct work_struct *_work)
 	    id_priv->state == RDMA_CM_DEVICE_REMOVAL)
 		goto out;
 
-	if (id_priv->id.event_handler(&id_priv->id, &work->event)) {
+	if (cma_cm_event_handler(id_priv, &work->event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
 		destroy = 1;
 	}
@@ -3089,7 +3119,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 	} else
 		event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
 
-	if (id_priv->id.event_handler(&id_priv->id, &event)) {
+	if (cma_cm_event_handler(id_priv, &event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
 		mutex_unlock(&id_priv->handler_mutex);
 		rdma_destroy_id(&id_priv->id);
@@ -3118,6 +3148,7 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv)
 	rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid);
 	rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid);
 
+	atomic_inc(&id_priv->refcount);
 	cma_init_resolve_addr_work(work, id_priv);
 	queue_work(cma_wq, &work->work);
 	return 0;
@@ -3144,6 +3175,7 @@ static int cma_resolve_ib_addr(struct rdma_id_private *id_priv)
 	rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)
 		&(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr));
 
+	atomic_inc(&id_priv->refcount);
 	cma_init_resolve_addr_work(work, id_priv);
 	queue_work(cma_wq, &work->work);
 	return 0;
@@ -3736,7 +3768,7 @@ static int cma_sidr_rep_handler(struct ib_cm_id *cm_id,
 		goto out;
 	}
 
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 
 	rdma_destroy_ah_attr(&event.param.ud.ah_attr);
 	if (ret) {
@@ -3800,6 +3832,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 	req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8);
 	req.max_cm_retries = CMA_MAX_CM_RETRIES;
 
+	trace_cm_send_sidr_req(id_priv);
 	ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req);
 	if (ret) {
 		ib_destroy_cm_id(id_priv->cm_id.ib);
@@ -3873,6 +3906,7 @@ static int cma_connect_ib(struct rdma_id_private *id_priv,
 	req.max_cm_retries = CMA_MAX_CM_RETRIES;
 	req.srq = id_priv->srq ? 1 : 0;
 
+	trace_cm_send_req(id_priv);
 	ret = ib_send_cm_req(id_priv->cm_id.ib, &req);
 out:
 	if (ret && !IS_ERR(id)) {
@@ -3986,6 +4020,7 @@ static int cma_accept_ib(struct rdma_id_private *id_priv,
 	rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count);
 	rep.srq = id_priv->srq ? 1 : 0;
 
+	trace_cm_send_rep(id_priv);
 	ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep);
 out:
 	return ret;
@@ -4035,6 +4070,7 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv,
 	rep.private_data = private_data;
 	rep.private_data_len = private_data_len;
 
+	trace_cm_send_sidr_rep(id_priv);
 	return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep);
 }
 
@@ -4120,13 +4156,15 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 		return -EINVAL;
 
 	if (rdma_cap_ib_cm(id->device, id->port_num)) {
-		if (id->qp_type == IB_QPT_UD)
+		if (id->qp_type == IB_QPT_UD) {
 			ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0,
 						private_data, private_data_len);
-		else
+		} else {
+			trace_cm_send_rej(id_priv);
 			ret = ib_send_cm_rej(id_priv->cm_id.ib,
 					     IB_CM_REJ_CONSUMER_DEFINED, NULL,
 					     0, private_data, private_data_len);
+		}
 	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_reject(id_priv->cm_id.iw,
 				   private_data, private_data_len);
@@ -4151,8 +4189,13 @@ int rdma_disconnect(struct rdma_cm_id *id)
 		if (ret)
 			goto out;
 		/* Initiate or respond to a disconnect. */
-		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0))
-			ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0);
+		trace_cm_disconnect(id_priv);
+		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) {
+			if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0))
+				trace_cm_sent_drep(id_priv);
+		} else {
+			trace_cm_sent_dreq(id_priv);
+		}
 	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_disconnect(id_priv->cm_id.iw, 0);
 	} else
@@ -4218,7 +4261,7 @@ static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast)
 	} else
 		event.event = RDMA_CM_EVENT_MULTICAST_ERROR;
 
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 
 	rdma_destroy_ah_attr(&event.param.ud.ah_attr);
 	if (ret) {
@@ -4623,6 +4666,7 @@ static void cma_add_one(struct ib_device *device)
 		cma_listen_on_dev(id_priv, cma_dev);
 	mutex_unlock(&lock);
 
+	trace_cm_add_one(device);
 	return;
 
 free_gid_type:
@@ -4653,7 +4697,7 @@ static int cma_remove_id_dev(struct rdma_id_private *id_priv)
 		goto out;
 
 	event.event = RDMA_CM_EVENT_DEVICE_REMOVAL;
-	ret = id_priv->id.event_handler(&id_priv->id, &event);
+	ret = cma_cm_event_handler(id_priv, &event);
 out:
 	mutex_unlock(&id_priv->handler_mutex);
 	return ret;
@@ -4691,6 +4735,8 @@ static void cma_remove_one(struct ib_device *device, void *client_data)
 {
 	struct cma_device *cma_dev = client_data;
 
+	trace_cm_remove_one(device);
+
 	if (!cma_dev)
 		return;
 
diff --git a/drivers/infiniband/core/cma_trace.c b/drivers/infiniband/core/cma_trace.c
new file mode 100644
index 000000000000..b314a281e10e
--- /dev/null
+++ b/drivers/infiniband/core/cma_trace.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Trace points for the RDMA Connection Manager.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ */
+
+#define CREATE_TRACE_POINTS
+
+#include <rdma/rdma_cm.h>
+#include <rdma/ib_cm.h>
+#include "cma_priv.h"
+
+#include "cma_trace.h"
diff --git a/drivers/infiniband/core/cma_trace.h b/drivers/infiniband/core/cma_trace.h
new file mode 100644
index 000000000000..81e36bf13159
--- /dev/null
+++ b/drivers/infiniband/core/cma_trace.h
@@ -0,0 +1,391 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Trace point definitions for the RDMA Connect Manager.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rdma_cma
+
+#if !defined(_TRACE_RDMA_CMA_H) || defined(TRACE_HEADER_MULTI_READ)
+
+#define _TRACE_RDMA_CMA_H
+
+#include <linux/tracepoint.h>
+#include <trace/events/rdma.h>
+
+/*
+ * enum ib_cm_event_type, from include/rdma/ib_cm.h
+ */
+#define IB_CM_EVENT_LIST			\
+	ib_cm_event(REQ_ERROR)			\
+	ib_cm_event(REQ_RECEIVED)		\
+	ib_cm_event(REP_ERROR)			\
+	ib_cm_event(REP_RECEIVED)		\
+	ib_cm_event(RTU_RECEIVED)		\
+	ib_cm_event(USER_ESTABLISHED)		\
+	ib_cm_event(DREQ_ERROR)			\
+	ib_cm_event(DREQ_RECEIVED)		\
+	ib_cm_event(DREP_RECEIVED)		\
+	ib_cm_event(TIMEWAIT_EXIT)		\
+	ib_cm_event(MRA_RECEIVED)		\
+	ib_cm_event(REJ_RECEIVED)		\
+	ib_cm_event(LAP_ERROR)			\
+	ib_cm_event(LAP_RECEIVED)		\
+	ib_cm_event(APR_RECEIVED)		\
+	ib_cm_event(SIDR_REQ_ERROR)		\
+	ib_cm_event(SIDR_REQ_RECEIVED)		\
+	ib_cm_event_end(SIDR_REP_RECEIVED)
+
+#undef ib_cm_event
+#undef ib_cm_event_end
+
+#define ib_cm_event(x)		TRACE_DEFINE_ENUM(IB_CM_##x);
+#define ib_cm_event_end(x)	TRACE_DEFINE_ENUM(IB_CM_##x);
+
+IB_CM_EVENT_LIST
+
+#undef ib_cm_event
+#undef ib_cm_event_end
+
+#define ib_cm_event(x)		{ IB_CM_##x, #x },
+#define ib_cm_event_end(x)	{ IB_CM_##x, #x }
+
+#define rdma_show_ib_cm_event(x) \
+		__print_symbolic(x, IB_CM_EVENT_LIST)
+
+
+DECLARE_EVENT_CLASS(cma_fsm_class,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv
+	),
+
+	TP_ARGS(id_priv),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+		__field(u32, tos)
+		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
+		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+		__entry->tos = id_priv->tos;
+		memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr,
+		       sizeof(struct sockaddr_in6));
+		memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u",
+		__entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos
+	)
+);
+
+#define DEFINE_CMA_FSM_EVENT(name)						\
+		DEFINE_EVENT(cma_fsm_class, cm_##name,				\
+				TP_PROTO(					\
+					const struct rdma_id_private *id_priv	\
+				),						\
+				TP_ARGS(id_priv))
+
+DEFINE_CMA_FSM_EVENT(send_rtu);
+DEFINE_CMA_FSM_EVENT(send_rej);
+DEFINE_CMA_FSM_EVENT(send_mra);
+DEFINE_CMA_FSM_EVENT(send_sidr_req);
+DEFINE_CMA_FSM_EVENT(send_sidr_rep);
+DEFINE_CMA_FSM_EVENT(disconnect);
+DEFINE_CMA_FSM_EVENT(sent_drep);
+DEFINE_CMA_FSM_EVENT(sent_dreq);
+DEFINE_CMA_FSM_EVENT(id_destroy);
+
+TRACE_EVENT(cm_id_create,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv
+	),
+
+	TP_ARGS(id_priv),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+	),
+
+	TP_printk("cm.id=%u",
+		__entry->cm_id
+	)
+);
+
+DECLARE_EVENT_CLASS(cma_qp_class,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv
+	),
+
+	TP_ARGS(id_priv),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+		__field(u32, tos)
+		__field(u32, qp_num)
+		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
+		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+		__entry->tos = id_priv->tos;
+		__entry->qp_num = id_priv->qp_num;
+		memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr,
+		       sizeof(struct sockaddr_in6));
+		memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u qp_num=%u",
+		__entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos,
+		__entry->qp_num
+	)
+);
+
+#define DEFINE_CMA_QP_EVENT(name)						\
+		DEFINE_EVENT(cma_qp_class, cm_##name,				\
+				TP_PROTO(					\
+					const struct rdma_id_private *id_priv	\
+				),						\
+				TP_ARGS(id_priv))
+
+DEFINE_CMA_QP_EVENT(send_req);
+DEFINE_CMA_QP_EVENT(send_rep);
+DEFINE_CMA_QP_EVENT(qp_destroy);
+
+/*
+ * enum ib_wp_type, from include/rdma/ib_verbs.h
+ */
+#define IB_QP_TYPE_LIST				\
+	ib_qp_type(SMI)				\
+	ib_qp_type(GSI)				\
+	ib_qp_type(RC)				\
+	ib_qp_type(UC)				\
+	ib_qp_type(UD)				\
+	ib_qp_type(RAW_IPV6)			\
+	ib_qp_type(RAW_ETHERTYPE)		\
+	ib_qp_type(RAW_PACKET)			\
+	ib_qp_type(XRC_INI)			\
+	ib_qp_type_end(XRC_TGT)
+
+#undef ib_qp_type
+#undef ib_qp_type_end
+
+#define ib_qp_type(x)		TRACE_DEFINE_ENUM(IB_QPT_##x);
+#define ib_qp_type_end(x)	TRACE_DEFINE_ENUM(IB_QPT_##x);
+
+IB_QP_TYPE_LIST
+
+#undef ib_qp_type
+#undef ib_qp_type_end
+
+#define ib_qp_type(x)		{ IB_QPT_##x, #x },
+#define ib_qp_type_end(x)	{ IB_QPT_##x, #x }
+
+#define rdma_show_qp_type(x) \
+		__print_symbolic(x, IB_QP_TYPE_LIST)
+
+
+TRACE_EVENT(cm_qp_create,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv,
+		const struct ib_pd *pd,
+		const struct ib_qp_init_attr *qp_init_attr,
+		int rc
+	),
+
+	TP_ARGS(id_priv, pd, qp_init_attr, rc),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+		__field(u32, pd_id)
+		__field(u32, tos)
+		__field(u32, qp_num)
+		__field(u32, send_wr)
+		__field(u32, recv_wr)
+		__field(int, rc)
+		__field(unsigned long, qp_type)
+		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
+		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+		__entry->pd_id = pd->res.id;
+		__entry->tos = id_priv->tos;
+		__entry->send_wr = qp_init_attr->cap.max_send_wr;
+		__entry->recv_wr = qp_init_attr->cap.max_recv_wr;
+		__entry->rc = rc;
+		if (!rc) {
+			__entry->qp_num = id_priv->qp_num;
+			__entry->qp_type = id_priv->id.qp_type;
+		} else {
+			__entry->qp_num = 0;
+			__entry->qp_type = 0;
+		}
+		memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr,
+		       sizeof(struct sockaddr_in6));
+		memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u pd.id=%u qp_type=%s"
+		" send_wr=%u recv_wr=%u qp_num=%u rc=%d",
+		__entry->cm_id, __entry->srcaddr, __entry->dstaddr,
+		__entry->tos, __entry->pd_id,
+		rdma_show_qp_type(__entry->qp_type), __entry->send_wr,
+		__entry->recv_wr, __entry->qp_num, __entry->rc
+	)
+);
+
+TRACE_EVENT(cm_req_handler,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv,
+		int event
+	),
+
+	TP_ARGS(id_priv, event),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+		__field(u32, tos)
+		__field(unsigned long, event)
+		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
+		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+		__entry->tos = id_priv->tos;
+		__entry->event = event;
+		memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr,
+		       sizeof(struct sockaddr_in6));
+		memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s (%lu)",
+		__entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos,
+		rdma_show_ib_cm_event(__entry->event), __entry->event
+	)
+);
+
+TRACE_EVENT(cm_event_handler,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv,
+		const struct rdma_cm_event *event
+	),
+
+	TP_ARGS(id_priv, event),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+		__field(u32, tos)
+		__field(unsigned long, event)
+		__field(int, status)
+		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
+		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+		__entry->tos = id_priv->tos;
+		__entry->event = event->event;
+		__entry->status = event->status;
+		memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr,
+		       sizeof(struct sockaddr_in6));
+		memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s (%lu/%d)",
+		__entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos,
+		rdma_show_cm_event(__entry->event), __entry->event,
+		__entry->status
+	)
+);
+
+TRACE_EVENT(cm_event_done,
+	TP_PROTO(
+		const struct rdma_id_private *id_priv,
+		const struct rdma_cm_event *event,
+		int result
+	),
+
+	TP_ARGS(id_priv, event, result),
+
+	TP_STRUCT__entry(
+		__field(u32, cm_id)
+		__field(u32, tos)
+		__field(unsigned long, event)
+		__field(int, result)
+		__array(unsigned char, srcaddr, sizeof(struct sockaddr_in6))
+		__array(unsigned char, dstaddr, sizeof(struct sockaddr_in6))
+	),
+
+	TP_fast_assign(
+		__entry->cm_id = id_priv->res.id;
+		__entry->tos = id_priv->tos;
+		__entry->event = event->event;
+		__entry->result = result;
+		memcpy(__entry->srcaddr, &id_priv->id.route.addr.src_addr,
+		       sizeof(struct sockaddr_in6));
+		memcpy(__entry->dstaddr, &id_priv->id.route.addr.dst_addr,
+		       sizeof(struct sockaddr_in6));
+	),
+
+	TP_printk("cm.id=%u src=%pISpc dst=%pISpc tos=%u %s consumer returns %d",
+		__entry->cm_id, __entry->srcaddr, __entry->dstaddr, __entry->tos,
+		rdma_show_cm_event(__entry->event), __entry->result
+	)
+);
+
+DECLARE_EVENT_CLASS(cma_client_class,
+	TP_PROTO(
+		const struct ib_device *device
+	),
+
+	TP_ARGS(device),
+
+	TP_STRUCT__entry(
+		__string(name, device->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, device->name);
+	),
+
+	TP_printk("device name=%s",
+		__get_str(name)
+	)
+);
+
+#define DEFINE_CMA_CLIENT_EVENT(name)						\
+		DEFINE_EVENT(cma_client_class, cm_##name,			\
+				TP_PROTO(					\
+					const struct ib_device *device		\
+				),						\
+				TP_ARGS(device))
+
+DEFINE_CMA_CLIENT_EVENT(add_one);
+DEFINE_CMA_CLIENT_EVENT(remove_one);
+
+#endif /* _TRACE_RDMA_CMA_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE cma_trace
+
+#include <trace/define_trace.h>
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 3645e092e1c7..b1457b3464d3 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -149,6 +149,7 @@ unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u8 port);
 int ib_cache_setup_one(struct ib_device *device);
 void ib_cache_cleanup_one(struct ib_device *device);
 void ib_cache_release_one(struct ib_device *device);
+void ib_dispatch_event_clients(struct ib_event *event);
 
 #ifdef CONFIG_CGROUP_RDMA
 void ib_device_register_rdmacg(struct ib_device *device);
@@ -320,7 +321,7 @@ static inline struct ib_qp *_ib_create_qp(struct ib_device *dev,
 					  struct ib_pd *pd,
 					  struct ib_qp_init_attr *attr,
 					  struct ib_udata *udata,
-					  struct ib_uobject *uobj)
+					  struct ib_uqp_object *uobj)
 {
 	enum ib_qp_type qp_type = attr->qp_type;
 	struct ib_qp *qp;
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index bbfded6d5d3d..4f25b2400694 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -7,6 +7,8 @@
 #include <linux/slab.h>
 #include <rdma/ib_verbs.h>
 
+#include <trace/events/rdma_core.h>
+
 /* # of WCs to poll for with a single call to ib_poll_cq */
 #define IB_POLL_BATCH			16
 #define IB_POLL_BATCH_DIRECT		8
@@ -41,6 +43,7 @@ static void ib_cq_rdma_dim_work(struct work_struct *w)
 
 	dim->state = DIM_START_MEASURE;
 
+	trace_cq_modify(cq, comps, usec);
 	cq->device->ops.modify_cq(cq, comps, usec);
 }
 
@@ -65,18 +68,29 @@ static void rdma_dim_init(struct ib_cq *cq)
 	INIT_WORK(&dim->work, ib_cq_rdma_dim_work);
 }
 
+static int __poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc)
+{
+	int rc;
+
+	rc = ib_poll_cq(cq, num_entries, wc);
+	trace_cq_poll(cq, num_entries, rc);
+	return rc;
+}
+
 static int __ib_process_cq(struct ib_cq *cq, int budget, struct ib_wc *wcs,
 			   int batch)
 {
 	int i, n, completed = 0;
 
+	trace_cq_process(cq);
+
 	/*
 	 * budget might be (-1) if the caller does not
 	 * want to bound this call, thus we need unsigned
 	 * minimum here.
 	 */
-	while ((n = ib_poll_cq(cq, min_t(u32, batch,
-					 budget - completed), wcs)) > 0) {
+	while ((n = __poll_cq(cq, min_t(u32, batch,
+					budget - completed), wcs)) > 0) {
 		for (i = 0; i < n; i++) {
 			struct ib_wc *wc = &wcs[i];
 
@@ -131,8 +145,10 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 	completed = __ib_process_cq(cq, budget, cq->wc, IB_POLL_BATCH);
 	if (completed < budget) {
 		irq_poll_complete(&cq->iop);
-		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
+		if (ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0) {
+			trace_cq_reschedule(cq);
 			irq_poll_sched(&cq->iop);
+		}
 	}
 
 	if (dim)
@@ -143,6 +159,7 @@ static int ib_poll_handler(struct irq_poll *iop, int budget)
 
 static void ib_cq_completion_softirq(struct ib_cq *cq, void *private)
 {
+	trace_cq_schedule(cq);
 	irq_poll_sched(&cq->iop);
 }
 
@@ -162,6 +179,7 @@ static void ib_cq_poll_work(struct work_struct *work)
 
 static void ib_cq_completion_workqueue(struct ib_cq *cq, void *private)
 {
+	trace_cq_schedule(cq);
 	queue_work(cq->comp_wq, &cq->work);
 }
 
@@ -239,6 +257,7 @@ struct ib_cq *__ib_alloc_cq_user(struct ib_device *dev, void *private,
 		goto out_destroy_cq;
 	}
 
+	trace_cq_alloc(cq, nr_cqe, comp_vector, poll_ctx);
 	return cq;
 
 out_destroy_cq:
@@ -248,6 +267,7 @@ out_free_wc:
 	kfree(cq->wc);
 out_free_cq:
 	kfree(cq);
+	trace_cq_alloc_error(nr_cqe, comp_vector, poll_ctx, ret);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL(__ib_alloc_cq_user);
@@ -304,6 +324,7 @@ void ib_free_cq_user(struct ib_cq *cq, struct ib_udata *udata)
 		WARN_ON_ONCE(1);
 	}
 
+	trace_cq_free(cq);
 	rdma_restrack_del(&cq->res);
 	cq->device->ops.destroy_cq(cq, udata);
 	if (cq->dim)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 84dd74fe13b8..f6c255202d7f 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -587,7 +587,8 @@ struct ib_device *_ib_alloc_device(size_t size)
 	rdma_init_coredev(&device->coredev, device, &init_net);
 
 	INIT_LIST_HEAD(&device->event_handler_list);
-	spin_lock_init(&device->event_handler_lock);
+	spin_lock_init(&device->qp_open_list_lock);
+	init_rwsem(&device->event_handler_rwsem);
 	mutex_init(&device->unregistration_lock);
 	/*
 	 * client_data needs to be alloc because we don't want our mark to be
@@ -1931,17 +1932,15 @@ EXPORT_SYMBOL(ib_set_client_data);
  *
  * ib_register_event_handler() registers an event handler that will be
  * called back when asynchronous IB events occur (as defined in
- * chapter 11 of the InfiniBand Architecture Specification).  This
- * callback may occur in interrupt context.
+ * chapter 11 of the InfiniBand Architecture Specification). This
+ * callback occurs in workqueue context.
  */
 void ib_register_event_handler(struct ib_event_handler *event_handler)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
+	down_write(&event_handler->device->event_handler_rwsem);
 	list_add_tail(&event_handler->list,
 		      &event_handler->device->event_handler_list);
-	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
+	up_write(&event_handler->device->event_handler_rwsem);
 }
 EXPORT_SYMBOL(ib_register_event_handler);
 
@@ -1954,35 +1953,23 @@ EXPORT_SYMBOL(ib_register_event_handler);
  */
 void ib_unregister_event_handler(struct ib_event_handler *event_handler)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
+	down_write(&event_handler->device->event_handler_rwsem);
 	list_del(&event_handler->list);
-	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
+	up_write(&event_handler->device->event_handler_rwsem);
 }
 EXPORT_SYMBOL(ib_unregister_event_handler);
 
-/**
- * ib_dispatch_event - Dispatch an asynchronous event
- * @event:Event to dispatch
- *
- * Low-level drivers must call ib_dispatch_event() to dispatch the
- * event to all registered event handlers when an asynchronous event
- * occurs.
- */
-void ib_dispatch_event(struct ib_event *event)
+void ib_dispatch_event_clients(struct ib_event *event)
 {
-	unsigned long flags;
 	struct ib_event_handler *handler;
 
-	spin_lock_irqsave(&event->device->event_handler_lock, flags);
+	down_read(&event->device->event_handler_rwsem);
 
 	list_for_each_entry(handler, &event->device->event_handler_list, list)
 		handler->handler(handler, event);
 
-	spin_unlock_irqrestore(&event->device->event_handler_lock, flags);
+	up_read(&event->device->event_handler_rwsem);
 }
-EXPORT_SYMBOL(ib_dispatch_event);
 
 static int iw_query_port(struct ib_device *device,
 			   u8 port_num,
@@ -1990,7 +1977,6 @@ static int iw_query_port(struct ib_device *device,
 {
 	struct in_device *inetdev;
 	struct net_device *netdev;
-	int err;
 
 	memset(port_attr, 0, sizeof(*port_attr));
 
@@ -2021,11 +2007,7 @@ static int iw_query_port(struct ib_device *device,
 	}
 
 	dev_put(netdev);
-	err = device->ops.query_port(device, port_num, port_attr);
-	if (err)
-		return err;
-
-	return 0;
+	return device->ops.query_port(device, port_num, port_attr);
 }
 
 static int __ib_query_port(struct ib_device *device,
diff --git a/drivers/infiniband/core/ib_core_uverbs.c b/drivers/infiniband/core/ib_core_uverbs.c
index b7cb59844ece..b51bd7087a88 100644
--- a/drivers/infiniband/core/ib_core_uverbs.c
+++ b/drivers/infiniband/core/ib_core_uverbs.c
@@ -232,7 +232,9 @@ void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry)
 	if (!entry)
 		return;
 
+	xa_lock(&entry->ucontext->mmap_xa);
 	entry->driver_removed = true;
+	xa_unlock(&entry->ucontext->mmap_xa);
 	kref_put(&entry->ref, rdma_user_mmap_entry_free);
 }
 EXPORT_SYMBOL(rdma_user_mmap_entry_remove);
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index cbf6041a5d4a..37b433aa7306 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -41,6 +41,7 @@
 #include "core_priv.h"
 #include "cma_priv.h"
 #include "restrack.h"
+#include "uverbs.h"
 
 typedef int (*res_fill_func_t)(struct sk_buff*, bool,
 			       struct rdma_restrack_entry*, uint32_t);
@@ -599,7 +600,7 @@ static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin,
 		goto err;
 	if (!rdma_is_kernel_res(res) &&
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CTXN,
-			cq->uobject->context->res.id))
+			cq->uobject->uevent.uobject.context->res.id))
 		goto err;
 
 	if (fill_res_name_pid(msg, res))
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 6c72773faf29..5128cb16bb48 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -42,26 +42,21 @@
 #include "core_priv.h"
 #include "rdma_core.h"
 
-void uverbs_uobject_get(struct ib_uobject *uobject)
-{
-	kref_get(&uobject->ref);
-}
-
 static void uverbs_uobject_free(struct kref *ref)
 {
-	struct ib_uobject *uobj =
-		container_of(ref, struct ib_uobject, ref);
-
-	if (uobj->uapi_object->type_class->needs_kfree_rcu)
-		kfree_rcu(uobj, rcu);
-	else
-		kfree(uobj);
+	kfree_rcu(container_of(ref, struct ib_uobject, ref), rcu);
 }
 
+/*
+ * In order to indicate we no longer needs this uobject, uverbs_uobject_put
+ * is called. When the reference count is decreased, the uobject is freed.
+ * For example, this is used when attaching a completion channel to a CQ.
+ */
 void uverbs_uobject_put(struct ib_uobject *uobject)
 {
 	kref_put(&uobject->ref, uverbs_uobject_free);
 }
+EXPORT_SYMBOL(uverbs_uobject_put);
 
 static int uverbs_try_lock_object(struct ib_uobject *uobj,
 				  enum rdma_lookup_mode mode)
@@ -135,7 +130,11 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 	lockdep_assert_held(&ufile->hw_destroy_rwsem);
 	assert_uverbs_usecnt(uobj, UVERBS_LOOKUP_WRITE);
 
-	if (uobj->object) {
+	if (reason == RDMA_REMOVE_ABORT) {
+		WARN_ON(!list_empty(&uobj->list));
+		WARN_ON(!uobj->context);
+		uobj->uapi_object->type_class->alloc_abort(uobj);
+	} else if (uobj->object) {
 		ret = uobj->uapi_object->type_class->destroy_hw(uobj, reason,
 								attrs);
 		if (ret) {
@@ -151,12 +150,6 @@ static int uverbs_destroy_uobject(struct ib_uobject *uobj,
 		uobj->object = NULL;
 	}
 
-	if (reason == RDMA_REMOVE_ABORT) {
-		WARN_ON(!list_empty(&uobj->list));
-		WARN_ON(!uobj->context);
-		uobj->uapi_object->type_class->alloc_abort(uobj);
-	}
-
 	uobj->context = NULL;
 
 	/*
@@ -263,15 +256,20 @@ int __uobj_perform_destroy(const struct uverbs_api_object *obj, u32 id,
 }
 
 /* alloc_uobj must be undone by uverbs_destroy_uobject() */
-static struct ib_uobject *alloc_uobj(struct ib_uverbs_file *ufile,
+static struct ib_uobject *alloc_uobj(struct uverbs_attr_bundle *attrs,
 				     const struct uverbs_api_object *obj)
 {
+	struct ib_uverbs_file *ufile = attrs->ufile;
 	struct ib_uobject *uobj;
-	struct ib_ucontext *ucontext;
 
-	ucontext = ib_uverbs_get_ucontext_file(ufile);
-	if (IS_ERR(ucontext))
-		return ERR_CAST(ucontext);
+	if (!attrs->context) {
+		struct ib_ucontext *ucontext =
+			ib_uverbs_get_ucontext_file(ufile);
+
+		if (IS_ERR(ucontext))
+			return ERR_CAST(ucontext);
+		attrs->context = ucontext;
+	}
 
 	uobj = kzalloc(obj->type_attrs->obj_size, GFP_KERNEL);
 	if (!uobj)
@@ -281,7 +279,7 @@ static struct ib_uobject *alloc_uobj(struct ib_uverbs_file *ufile,
 	 * The object is added to the list in the commit stage.
 	 */
 	uobj->ufile = ufile;
-	uobj->context = ucontext;
+	uobj->context = attrs->context;
 	INIT_LIST_HEAD(&uobj->list);
 	uobj->uapi_object = obj;
 	/*
@@ -358,9 +356,9 @@ lookup_get_fd_uobject(const struct uverbs_api_object *obj,
 
 	uobject = f->private_data;
 	/*
-	 * fget(id) ensures we are not currently running uverbs_close_fd,
-	 * and the caller is expected to ensure that uverbs_close_fd is never
-	 * done while a call top lookup is possible.
+	 * fget(id) ensures we are not currently running
+	 * uverbs_uobject_fd_release(), and the caller is expected to ensure
+	 * that release is never done while a call to lookup is possible.
 	 */
 	if (f->f_op != fd_type->fops) {
 		fput(f);
@@ -424,12 +422,12 @@ free:
 
 static struct ib_uobject *
 alloc_begin_idr_uobject(const struct uverbs_api_object *obj,
-			struct ib_uverbs_file *ufile)
+			struct uverbs_attr_bundle *attrs)
 {
 	int ret;
 	struct ib_uobject *uobj;
 
-	uobj = alloc_uobj(ufile, obj);
+	uobj = alloc_uobj(attrs, obj);
 	if (IS_ERR(uobj))
 		return uobj;
 
@@ -445,7 +443,7 @@ alloc_begin_idr_uobject(const struct uverbs_api_object *obj,
 	return uobj;
 
 remove:
-	xa_erase(&ufile->idr, uobj->id);
+	xa_erase(&attrs->ufile->idr, uobj->id);
 uobj_put:
 	uverbs_uobject_put(uobj);
 	return ERR_PTR(ret);
@@ -453,31 +451,48 @@ uobj_put:
 
 static struct ib_uobject *
 alloc_begin_fd_uobject(const struct uverbs_api_object *obj,
-		       struct ib_uverbs_file *ufile)
+		       struct uverbs_attr_bundle *attrs)
 {
+	const struct uverbs_obj_fd_type *fd_type =
+		container_of(obj->type_attrs, struct uverbs_obj_fd_type, type);
 	int new_fd;
 	struct ib_uobject *uobj;
+	struct file *filp;
+
+	if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release))
+		return ERR_PTR(-EINVAL);
 
 	new_fd = get_unused_fd_flags(O_CLOEXEC);
 	if (new_fd < 0)
 		return ERR_PTR(new_fd);
 
-	uobj = alloc_uobj(ufile, obj);
-	if (IS_ERR(uobj)) {
-		put_unused_fd(new_fd);
-		return uobj;
+	uobj = alloc_uobj(attrs, obj);
+	if (IS_ERR(uobj))
+		goto err_fd;
+
+	/* Note that uverbs_uobject_fd_release() is called during abort */
+	filp = anon_inode_getfile(fd_type->name, fd_type->fops, NULL,
+				  fd_type->flags);
+	if (IS_ERR(filp)) {
+		uobj = ERR_CAST(filp);
+		goto err_uobj;
 	}
+	uobj->object = filp;
 
 	uobj->id = new_fd;
-	uobj->ufile = ufile;
+	return uobj;
 
+err_uobj:
+	uverbs_uobject_put(uobj);
+err_fd:
+	put_unused_fd(new_fd);
 	return uobj;
 }
 
 struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_api_object *obj,
-					    struct ib_uverbs_file *ufile,
 					    struct uverbs_attr_bundle *attrs)
 {
+	struct ib_uverbs_file *ufile = attrs->ufile;
 	struct ib_uobject *ret;
 
 	if (IS_ERR(obj))
@@ -491,13 +506,11 @@ struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_api_object *obj,
 	if (!down_read_trylock(&ufile->hw_destroy_rwsem))
 		return ERR_PTR(-EIO);
 
-	ret = obj->type_class->alloc_begin(obj, ufile);
+	ret = obj->type_class->alloc_begin(obj, attrs);
 	if (IS_ERR(ret)) {
 		up_read(&ufile->hw_destroy_rwsem);
 		return ret;
 	}
-	if (attrs)
-		attrs->context = ret->context;
 	return ret;
 }
 
@@ -544,6 +557,9 @@ static void remove_handle_idr_uobject(struct ib_uobject *uobj)
 
 static void alloc_abort_fd_uobject(struct ib_uobject *uobj)
 {
+	struct file *filp = uobj->object;
+
+	fput(filp);
 	put_unused_fd(uobj->id);
 }
 
@@ -553,7 +569,7 @@ static int __must_check destroy_hw_fd_uobject(struct ib_uobject *uobj,
 {
 	const struct uverbs_obj_fd_type *fd_type = container_of(
 		uobj->uapi_object->type_attrs, struct uverbs_obj_fd_type, type);
-	int ret = fd_type->context_closed(uobj, why);
+	int ret = fd_type->destroy_object(uobj, why);
 
 	if (ib_is_destroy_retryable(ret, why, uobj))
 		return ret;
@@ -565,7 +581,7 @@ static void remove_handle_fd_uobject(struct ib_uobject *uobj)
 {
 }
 
-static int alloc_commit_idr_uobject(struct ib_uobject *uobj)
+static void alloc_commit_idr_uobject(struct ib_uobject *uobj)
 {
 	struct ib_uverbs_file *ufile = uobj->ufile;
 	void *old;
@@ -579,33 +595,14 @@ static int alloc_commit_idr_uobject(struct ib_uobject *uobj)
 	 */
 	old = xa_store(&ufile->idr, uobj->id, uobj, GFP_KERNEL);
 	WARN_ON(old != NULL);
-
-	return 0;
 }
 
-static int alloc_commit_fd_uobject(struct ib_uobject *uobj)
+static void alloc_commit_fd_uobject(struct ib_uobject *uobj)
 {
-	const struct uverbs_obj_fd_type *fd_type = container_of(
-		uobj->uapi_object->type_attrs, struct uverbs_obj_fd_type, type);
 	int fd = uobj->id;
-	struct file *filp;
-
-	/*
-	 * The kref for uobj is moved into filp->private data and put in
-	 * uverbs_close_fd(). Once alloc_commit() succeeds uverbs_close_fd()
-	 * must be guaranteed to be called from the provided fops release
-	 * callback.
-	 */
-	filp = anon_inode_getfile(fd_type->name,
-				  fd_type->fops,
-				  uobj,
-				  fd_type->flags);
-	if (IS_ERR(filp))
-		return PTR_ERR(filp);
-
-	uobj->object = filp;
+	struct file *filp = uobj->object;
 
-	/* Matching put will be done in uverbs_close_fd() */
+	/* Matching put will be done in uverbs_uobject_fd_release() */
 	kref_get(&uobj->ufile->ref);
 
 	/* This shouldn't be used anymore. Use the file object instead */
@@ -613,11 +610,10 @@ static int alloc_commit_fd_uobject(struct ib_uobject *uobj)
 
 	/*
 	 * NOTE: Once we install the file we loose ownership of our kref on
-	 * uobj. It will be put by uverbs_close_fd()
+	 * uobj. It will be put by uverbs_uobject_fd_release()
 	 */
+	filp->private_data = uobj;
 	fd_install(fd, filp);
-
-	return 0;
 }
 
 /*
@@ -625,19 +621,13 @@ static int alloc_commit_fd_uobject(struct ib_uobject *uobj)
  * caller can no longer assume uobj is valid. If this function fails it
  * destroys the uboject, including the attached HW object.
  */
-int __must_check rdma_alloc_commit_uobject(struct ib_uobject *uobj,
-					   struct uverbs_attr_bundle *attrs)
+void rdma_alloc_commit_uobject(struct ib_uobject *uobj,
+			       struct uverbs_attr_bundle *attrs)
 {
 	struct ib_uverbs_file *ufile = attrs->ufile;
-	int ret;
 
 	/* alloc_commit consumes the uobj kref */
-	ret = uobj->uapi_object->type_class->alloc_commit(uobj);
-	if (ret) {
-		uverbs_destroy_uobject(uobj, RDMA_REMOVE_ABORT, attrs);
-		up_read(&ufile->hw_destroy_rwsem);
-		return ret;
-	}
+	uobj->uapi_object->type_class->alloc_commit(uobj);
 
 	/* kref is held so long as the uobj is on the uobj list. */
 	uverbs_uobject_get(uobj);
@@ -650,8 +640,6 @@ int __must_check rdma_alloc_commit_uobject(struct ib_uobject *uobj,
 
 	/* Matches the down_read in rdma_alloc_begin_uobject */
 	up_read(&ufile->hw_destroy_rwsem);
-
-	return 0;
 }
 
 /*
@@ -663,7 +651,6 @@ void rdma_alloc_abort_uobject(struct ib_uobject *uobj,
 {
 	struct ib_uverbs_file *ufile = uobj->ufile;
 
-	uobj->object = NULL;
 	uverbs_destroy_uobject(uobj, RDMA_REMOVE_ABORT, attrs);
 
 	/* Matches the down_read in rdma_alloc_begin_uobject */
@@ -681,7 +668,10 @@ static void lookup_put_fd_uobject(struct ib_uobject *uobj,
 	struct file *filp = uobj->object;
 
 	WARN_ON(mode != UVERBS_LOOKUP_READ);
-	/* This indirectly calls uverbs_close_fd and free the object */
+	/*
+	 * This indirectly calls uverbs_uobject_fd_release() and free the
+	 * object
+	 */
 	fput(filp);
 }
 
@@ -744,33 +734,32 @@ const struct uverbs_obj_type_class uverbs_idr_class = {
 	.lookup_put = lookup_put_idr_uobject,
 	.destroy_hw = destroy_hw_idr_uobject,
 	.remove_handle = remove_handle_idr_uobject,
-	/*
-	 * When we destroy an object, we first just lock it for WRITE and
-	 * actually DESTROY it in the finalize stage. So, the problematic
-	 * scenario is when we just started the finalize stage of the
-	 * destruction (nothing was executed yet). Now, the other thread
-	 * fetched the object for READ access, but it didn't lock it yet.
-	 * The DESTROY thread continues and starts destroying the object.
-	 * When the other thread continue - without the RCU, it would
-	 * access freed memory. However, the rcu_read_lock delays the free
-	 * until the rcu_read_lock of the READ operation quits. Since the
-	 * exclusive lock of the object is still taken by the DESTROY flow, the
-	 * READ operation will get -EBUSY and it'll just bail out.
-	 */
-	.needs_kfree_rcu = true,
 };
 EXPORT_SYMBOL(uverbs_idr_class);
 
-void uverbs_close_fd(struct file *f)
+/*
+ * Users of UVERBS_TYPE_ALLOC_FD should set this function as the struct
+ * file_operations release method.
+ */
+int uverbs_uobject_fd_release(struct inode *inode, struct file *filp)
 {
-	struct ib_uobject *uobj = f->private_data;
-	struct ib_uverbs_file *ufile = uobj->ufile;
-	struct uverbs_attr_bundle attrs = {
-		.context = uobj->context,
-		.ufile = ufile,
-	};
+	struct ib_uverbs_file *ufile;
+	struct ib_uobject *uobj;
+
+	/*
+	 * This can only happen if the fput came from alloc_abort_fd_uobject()
+	 */
+	if (!filp->private_data)
+		return 0;
+	uobj = filp->private_data;
+	ufile = uobj->ufile;
 
 	if (down_read_trylock(&ufile->hw_destroy_rwsem)) {
+		struct uverbs_attr_bundle attrs = {
+			.context = uobj->context,
+			.ufile = ufile,
+		};
+
 		/*
 		 * lookup_get_fd_uobject holds the kref on the struct file any
 		 * time a FD uobj is locked, which prevents this release
@@ -782,13 +771,14 @@ void uverbs_close_fd(struct file *f)
 		up_read(&ufile->hw_destroy_rwsem);
 	}
 
-	/* Matches the get in alloc_begin_fd_uobject */
+	/* Matches the get in alloc_commit_fd_uobject() */
 	kref_put(&ufile->ref, ib_uverbs_release_file);
 
 	/* Pairs with filp->private_data in alloc_begin_fd_uobject */
 	uverbs_uobject_put(uobj);
+	return 0;
 }
-EXPORT_SYMBOL(uverbs_close_fd);
+EXPORT_SYMBOL(uverbs_uobject_fd_release);
 
 /*
  * Drop the ucontext off the ufile and completely disconnect it from the
@@ -855,9 +845,7 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile,
 }
 
 /*
- * Destroy the uncontext and every uobject associated with it. If called with
- * reason != RDMA_REMOVE_CLOSE this will not return until the destruction has
- * been completed and ufile->ucontext is NULL.
+ * Destroy the uncontext and every uobject associated with it.
  *
  * This is internally locked and can be called in parallel from multiple
  * contexts.
@@ -865,22 +853,6 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile,
 void uverbs_destroy_ufile_hw(struct ib_uverbs_file *ufile,
 			     enum rdma_remove_reason reason)
 {
-	if (reason == RDMA_REMOVE_CLOSE) {
-		/*
-		 * During destruction we might trigger something that
-		 * synchronously calls release on any file descriptor. For
-		 * this reason all paths that come from file_operations
-		 * release must use try_lock. They can progress knowing that
-		 * there is an ongoing uverbs_destroy_ufile_hw that will clean
-		 * up the driver resources.
-		 */
-		if (!mutex_trylock(&ufile->ucontext_lock))
-			return;
-
-	} else {
-		mutex_lock(&ufile->ucontext_lock);
-	}
-
 	down_write(&ufile->hw_destroy_rwsem);
 
 	/*
@@ -909,7 +881,6 @@ void uverbs_destroy_ufile_hw(struct ib_uverbs_file *ufile,
 
 done:
 	up_write(&ufile->hw_destroy_rwsem);
-	mutex_unlock(&ufile->ucontext_lock);
 }
 
 const struct uverbs_obj_type_class uverbs_fd_class = {
@@ -920,7 +891,6 @@ const struct uverbs_obj_type_class uverbs_fd_class = {
 	.lookup_put = lookup_put_fd_uobject,
 	.destroy_hw = destroy_hw_fd_uobject,
 	.remove_handle = remove_handle_fd_uobject,
-	.needs_kfree_rcu = false,
 };
 EXPORT_SYMBOL(uverbs_fd_class);
 
@@ -943,19 +913,17 @@ uverbs_get_uobject_from_file(u16 object_id, enum uverbs_obj_access access,
 		return rdma_lookup_get_uobject(obj, attrs->ufile, id,
 					       UVERBS_LOOKUP_WRITE, attrs);
 	case UVERBS_ACCESS_NEW:
-		return rdma_alloc_begin_uobject(obj, attrs->ufile, attrs);
+		return rdma_alloc_begin_uobject(obj, attrs);
 	default:
 		WARN_ON(true);
 		return ERR_PTR(-EOPNOTSUPP);
 	}
 }
 
-int uverbs_finalize_object(struct ib_uobject *uobj,
-			   enum uverbs_obj_access access, bool commit,
-			   struct uverbs_attr_bundle *attrs)
+void uverbs_finalize_object(struct ib_uobject *uobj,
+			    enum uverbs_obj_access access, bool commit,
+			    struct uverbs_attr_bundle *attrs)
 {
-	int ret = 0;
-
 	/*
 	 * refcounts should be handled at the object level and not at the
 	 * uobject level. Refcounts of the objects themselves are done in
@@ -975,14 +943,11 @@ int uverbs_finalize_object(struct ib_uobject *uobj,
 		break;
 	case UVERBS_ACCESS_NEW:
 		if (commit)
-			ret = rdma_alloc_commit_uobject(uobj, attrs);
+			rdma_alloc_commit_uobject(uobj, attrs);
 		else
 			rdma_alloc_abort_uobject(uobj, attrs);
 		break;
 	default:
 		WARN_ON(true);
-		ret = -EOPNOTSUPP;
 	}
-
-	return ret;
 }
diff --git a/drivers/infiniband/core/rdma_core.h b/drivers/infiniband/core/rdma_core.h
index e63fbda25e1d..33978e0f1262 100644
--- a/drivers/infiniband/core/rdma_core.h
+++ b/drivers/infiniband/core/rdma_core.h
@@ -51,29 +51,6 @@ void uverbs_destroy_ufile_hw(struct ib_uverbs_file *ufile,
 int uobj_destroy(struct ib_uobject *uobj, struct uverbs_attr_bundle *attrs);
 
 /*
- * uverbs_uobject_get is called in order to increase the reference count on
- * an uobject. This is useful when a handler wants to keep the uobject's memory
- * alive, regardless if this uobject is still alive in the context's objects
- * repository. Objects are put via uverbs_uobject_put.
- */
-void uverbs_uobject_get(struct ib_uobject *uobject);
-
-/*
- * In order to indicate we no longer needs this uobject, uverbs_uobject_put
- * is called. When the reference count is decreased, the uobject is freed.
- * For example, this is used when attaching a completion channel to a CQ.
- */
-void uverbs_uobject_put(struct ib_uobject *uobject);
-
-/* Indicate this fd is no longer used by this consumer, but its memory isn't
- * necessarily released yet. When the last reference is put, we release the
- * memory. After this call is executed, calling uverbs_uobject_get isn't
- * allowed.
- * This must be called from the release file_operations of the file!
- */
-void uverbs_close_fd(struct file *f);
-
-/*
  * Get an ib_uobject that corresponds to the given id from ufile, assuming
  * the object is from the given type. Lock it to the required access when
  * applicable.
@@ -86,24 +63,9 @@ struct ib_uobject *
 uverbs_get_uobject_from_file(u16 object_id, enum uverbs_obj_access access,
 			     s64 id, struct uverbs_attr_bundle *attrs);
 
-/*
- * Note that certain finalize stages could return a status:
- *   (a) alloc_commit could return a failure if the object is committed at the
- *       same time when the context is destroyed.
- *   (b) remove_commit could fail if the object wasn't destroyed successfully.
- * Since multiple objects could be finalized in one transaction, it is very NOT
- * recommended to have several finalize actions which have side effects.
- * For example, it's NOT recommended to have a certain action which has both
- * a commit action and a destroy action or two destroy objects in the same
- * action. The rule of thumb is to have one destroy or commit action with
- * multiple lookups.
- * The first non zero return value of finalize_object is returned from this
- * function. For example, this could happen when we couldn't destroy an
- * object.
- */
-int uverbs_finalize_object(struct ib_uobject *uobj,
-			   enum uverbs_obj_access access, bool commit,
-			   struct uverbs_attr_bundle *attrs);
+void uverbs_finalize_object(struct ib_uobject *uobj,
+			    enum uverbs_obj_access access, bool commit,
+			    struct uverbs_attr_bundle *attrs);
 
 int uverbs_output_written(const struct uverbs_attr_bundle *bundle, size_t idx);
 
@@ -189,6 +151,7 @@ void uapi_compute_bundle_size(struct uverbs_api_ioctl_method *method_elm,
 			      unsigned int num_attrs);
 void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile);
 
+extern const struct uapi_definition uverbs_def_obj_async_fd[];
 extern const struct uapi_definition uverbs_def_obj_counters[];
 extern const struct uapi_definition uverbs_def_obj_cq[];
 extern const struct uapi_definition uverbs_def_obj_device[];
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 8917125ea16d..30d4c126a2db 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1068,7 +1068,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	}
 
 settimeout_out:
-	return skb->len;
+	return 0;
 }
 
 static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
@@ -1139,7 +1139,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 	}
 
 resp_out:
-	return skb->len;
+	return 0;
 }
 
 static void free_sm_ah(struct kref *kref)
diff --git a/drivers/infiniband/core/trace.c b/drivers/infiniband/core/trace.c
new file mode 100644
index 000000000000..6c3514beac4d
--- /dev/null
+++ b/drivers/infiniband/core/trace.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Trace points for core RDMA functions.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ */
+
+#define CREATE_TRACE_POINTS
+
+#include <rdma/ib_verbs.h>
+
+#include <trace/events/rdma_core.h>
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 146f98fbf22b..06b6125b5ae1 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -54,7 +54,7 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		put_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
+		unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
 	}
 
 	sg_free_table(&umem->sg_head);
@@ -166,10 +166,13 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 		 * for any address.
 		 */
 		mask |= (sg_dma_address(sg) + pgoff) ^ va;
-		if (i && i != (umem->nmap - 1))
-			/* restrict by length as well for interior SGEs */
-			mask |= sg_dma_len(sg);
 		va += sg_dma_len(sg) - pgoff;
+		/* Except for the last entry, the ending iova alignment sets
+		 * the maximum possible page size as the low bits of the iova
+		 * must be zero when starting the next chunk.
+		 */
+		if (i != (umem->nmap - 1))
+			mask |= va;
 		pgoff = 0;
 	}
 	best_pg_bit = rdma_find_pg_bit(mask, pgsz_bitmap);
@@ -257,16 +260,13 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 	sg = umem->sg_head.sgl;
 
 	while (npages) {
-		down_read(&mm->mmap_sem);
-		ret = get_user_pages(cur_base,
-				     min_t(unsigned long, npages,
-					   PAGE_SIZE / sizeof (struct page *)),
-				     gup_flags | FOLL_LONGTERM,
-				     page_list, NULL);
-		if (ret < 0) {
-			up_read(&mm->mmap_sem);
+		ret = pin_user_pages_fast(cur_base,
+					  min_t(unsigned long, npages,
+						PAGE_SIZE /
+						sizeof(struct page *)),
+					  gup_flags | FOLL_LONGTERM, page_list);
+		if (ret < 0)
 			goto umem_release;
-		}
 
 		cur_base += ret * PAGE_SIZE;
 		npages   -= ret;
@@ -274,8 +274,6 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 		sg = ib_umem_add_sg_table(sg, page_list, ret,
 			dma_get_max_seg_size(device->dma_device),
 			&umem->sg_nents);
-
-		up_read(&mm->mmap_sem);
 	}
 
 	sg_mark_end(sg);
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index dac3fd2ebc26..b8c657b28380 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -227,21 +227,10 @@ struct ib_umem_odp *ib_umem_odp_get(struct ib_device *device,
 	umem_odp->notifier.ops = ops;
 
 	umem_odp->page_shift = PAGE_SHIFT;
-	if (access & IB_ACCESS_HUGETLB) {
-		struct vm_area_struct *vma;
-		struct hstate *h;
-
-		down_read(&mm->mmap_sem);
-		vma = find_vma(mm, ib_umem_start(umem_odp));
-		if (!vma || !is_vm_hugetlb_page(vma)) {
-			up_read(&mm->mmap_sem);
-			ret = -EINVAL;
-			goto err_free;
-		}
-		h = hstate_vma(vma);
-		umem_odp->page_shift = huge_page_shift(h);
-		up_read(&mm->mmap_sem);
-	}
+#ifdef CONFIG_HUGETLB_PAGE
+	if (access & IB_ACCESS_HUGETLB)
+		umem_odp->page_shift = HPAGE_SHIFT;
+#endif
 
 	umem_odp->tgid = get_task_pid(current->group_leader, PIDTYPE_PID);
 	ret = ib_init_umem_odp(umem_odp, ops);
@@ -251,7 +240,6 @@ struct ib_umem_odp *ib_umem_odp_get(struct ib_device *device,
 
 err_put_pid:
 	put_pid(umem_odp->tgid);
-err_free:
 	kfree(umem_odp);
 	return ERR_PTR(ret);
 }
@@ -293,9 +281,8 @@ EXPORT_SYMBOL(ib_umem_odp_release);
  * The function returns -EFAULT if the DMA mapping operation fails. It returns
  * -EAGAIN if a concurrent invalidation prevents us from updating the page.
  *
- * The page is released via put_user_page even if the operation failed. For
- * on-demand pinning, the page is released whenever it isn't stored in the
- * umem.
+ * The page is released via put_page even if the operation failed. For on-demand
+ * pinning, the page is released whenever it isn't stored in the umem.
  */
 static int ib_umem_odp_map_dma_single_page(
 		struct ib_umem_odp *umem_odp,
@@ -348,7 +335,7 @@ static int ib_umem_odp_map_dma_single_page(
 	}
 
 out:
-	put_user_page(page);
+	put_page(page);
 	return ret;
 }
 
@@ -425,7 +412,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 
 	while (bcnt > 0) {
 		const size_t gup_num_pages = min_t(size_t,
-				(bcnt + BIT(page_shift) - 1) >> page_shift,
+				ALIGN(bcnt, PAGE_SIZE) / PAGE_SIZE,
 				PAGE_SIZE / sizeof(struct page *));
 
 		down_read(&owning_mm->mmap_sem);
@@ -458,7 +445,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 					ret = -EFAULT;
 					break;
 				}
-				put_user_page(local_page_list[j]);
+				put_page(local_page_list[j]);
 				continue;
 			}
 
@@ -485,8 +472,8 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt,
 			 * ib_umem_odp_map_dma_single_page().
 			 */
 			if (npages - (j + 1) > 0)
-				put_user_pages(&local_page_list[j+1],
-					       npages - (j + 1));
+				release_pages(&local_page_list[j+1],
+					      npages - (j + 1));
 			break;
 		}
 	}
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 63f7f7db5902..7df71983212d 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -111,7 +111,6 @@ struct ib_uverbs_device {
 	struct srcu_struct			disassociate_srcu;
 	struct mutex				lists_mutex; /* protect lists */
 	struct list_head			uverbs_file_list;
-	struct list_head			uverbs_events_file_list;
 	struct uverbs_api			*uapi;
 };
 
@@ -124,10 +123,9 @@ struct ib_uverbs_event_queue {
 };
 
 struct ib_uverbs_async_event_file {
+	struct ib_uobject			uobj;
 	struct ib_uverbs_event_queue		ev_queue;
-	struct ib_uverbs_file		       *uverbs_file;
-	struct kref				ref;
-	struct list_head			list;
+	struct ib_event_handler			event_handler;
 };
 
 struct ib_uverbs_completion_event_file {
@@ -144,8 +142,7 @@ struct ib_uverbs_file {
 	 * ucontext_lock held
 	 */
 	struct ib_ucontext		       *ucontext;
-	struct ib_event_handler			event_handler;
-	struct ib_uverbs_async_event_file       *async_file;
+	struct ib_uverbs_async_event_file      *async_file;
 	struct list_head			list;
 
 	/*
@@ -183,6 +180,7 @@ struct ib_uverbs_mcast_entry {
 
 struct ib_uevent_object {
 	struct ib_uobject	uobject;
+	/* List member for ib_uverbs_async_event_file list */
 	struct list_head	event_list;
 	u32			events_reported;
 };
@@ -210,25 +208,24 @@ struct ib_uwq_object {
 };
 
 struct ib_ucq_object {
-	struct ib_uobject	uobject;
+	struct ib_uevent_object uevent;
 	struct list_head	comp_list;
-	struct list_head	async_list;
 	u32			comp_events_reported;
-	u32			async_events_reported;
 };
 
 extern const struct file_operations uverbs_event_fops;
+extern const struct file_operations uverbs_async_event_fops;
 void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue);
-struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file,
-					      struct ib_device *ib_dev);
-void ib_uverbs_free_async_event_file(struct ib_uverbs_file *uverbs_file);
+void ib_uverbs_init_async_event_file(struct ib_uverbs_async_event_file *ev_file);
+void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue);
 void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res);
 
-void ib_uverbs_release_ucq(struct ib_uverbs_file *file,
-			   struct ib_uverbs_completion_event_file *ev_file,
+int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs);
+int ib_init_ucontext(struct uverbs_attr_bundle *attrs);
+
+void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file,
 			   struct ib_ucq_object *uobj);
-void ib_uverbs_release_uevent(struct ib_uverbs_file *file,
-			      struct ib_uevent_object *uobj);
+void ib_uverbs_release_uevent(struct ib_uevent_object *uobj);
 void ib_uverbs_release_file(struct kref *ref);
 
 void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context);
@@ -236,8 +233,6 @@ void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr);
 void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr);
 void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr);
 void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr);
-void ib_uverbs_event_handler(struct ib_event_handler *handler,
-			     struct ib_event *event);
 int ib_uverbs_dealloc_xrcd(struct ib_uobject *uobject, struct ib_xrcd *xrcd,
 			   enum rdma_remove_reason why,
 			   struct uverbs_attr_bundle *attrs);
@@ -276,23 +271,6 @@ int ib_uverbs_kern_spec_to_ib_spec_filter(enum ib_flow_spec_type type,
 					  size_t kern_filter_sz,
 					  union ib_flow_spec *ib_spec);
 
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_DEVICE);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_PD);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_MR);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_COMP_CHANNEL);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_CQ);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_QP);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_AH);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_MW);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_SRQ);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_FLOW);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_WQ);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_RWQ_IND_TBL);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_XRCD);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_FLOW_ACTION);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_DM);
-extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_COUNTERS);
-
 /*
  * ib_uverbs_query_port_resp.port_cap_flags started out as just a copy of the
  * PortInfo CapabilityMask, but was extended with unique bits.
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 06ed32c8662f..c8693f5231dd 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -203,82 +203,55 @@ _ib_uverbs_lookup_comp_file(s32 fd, struct uverbs_attr_bundle *attrs)
 #define ib_uverbs_lookup_comp_file(_fd, _ufile)                                \
 	_ib_uverbs_lookup_comp_file((_fd)*typecheck(s32, _fd), _ufile)
 
-static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs)
+int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs)
 {
-	struct ib_uverbs_file *file = attrs->ufile;
-	struct ib_uverbs_get_context      cmd;
-	struct ib_uverbs_get_context_resp resp;
-	struct ib_ucontext		 *ucontext;
-	struct file			 *filp;
-	struct ib_rdmacg_object		 cg_obj;
+	struct ib_uverbs_file *ufile = attrs->ufile;
+	struct ib_ucontext *ucontext;
 	struct ib_device *ib_dev;
-	int ret;
 
-	ret = uverbs_request(attrs, &cmd, sizeof(cmd));
-	if (ret)
-		return ret;
-
-	mutex_lock(&file->ucontext_lock);
-	ib_dev = srcu_dereference(file->device->ib_dev,
-				  &file->device->disassociate_srcu);
-	if (!ib_dev) {
-		ret = -EIO;
-		goto err;
-	}
-
-	if (file->ucontext) {
-		ret = -EINVAL;
-		goto err;
-	}
-
-	ret = ib_rdmacg_try_charge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
-	if (ret)
-		goto err;
+	ib_dev = srcu_dereference(ufile->device->ib_dev,
+				  &ufile->device->disassociate_srcu);
+	if (!ib_dev)
+		return -EIO;
 
 	ucontext = rdma_zalloc_drv_obj(ib_dev, ib_ucontext);
-	if (!ucontext) {
-		ret = -ENOMEM;
-		goto err_alloc;
-	}
-
-	attrs->context = ucontext;
+	if (!ucontext)
+		return -ENOMEM;
 
 	ucontext->res.type = RDMA_RESTRACK_CTX;
 	ucontext->device = ib_dev;
-	ucontext->cg_obj = cg_obj;
-	/* ufile is required when some objects are released */
-	ucontext->ufile = file;
-
-	ucontext->closing = false;
-	ucontext->cleanup_retryable = false;
-
+	ucontext->ufile = ufile;
 	xa_init_flags(&ucontext->mmap_xa, XA_FLAGS_ALLOC);
+	attrs->context = ucontext;
+	return 0;
+}
 
-	ret = get_unused_fd_flags(O_CLOEXEC);
-	if (ret < 0)
-		goto err_free;
-	resp.async_fd = ret;
+int ib_init_ucontext(struct uverbs_attr_bundle *attrs)
+{
+	struct ib_ucontext *ucontext = attrs->context;
+	struct ib_uverbs_file *file = attrs->ufile;
+	int ret;
 
-	filp = ib_uverbs_alloc_async_event_file(file, ib_dev);
-	if (IS_ERR(filp)) {
-		ret = PTR_ERR(filp);
-		goto err_fd;
+	if (!down_read_trylock(&file->hw_destroy_rwsem))
+		return -EIO;
+	mutex_lock(&file->ucontext_lock);
+	if (file->ucontext) {
+		ret = -EINVAL;
+		goto err;
 	}
 
-	resp.num_comp_vectors = file->device->num_comp_vectors;
-
-	ret = uverbs_response(attrs, &resp, sizeof(resp));
+	ret = ib_rdmacg_try_charge(&ucontext->cg_obj, ucontext->device,
+				   RDMACG_RESOURCE_HCA_HANDLE);
 	if (ret)
-		goto err_file;
+		goto err;
 
-	ret = ib_dev->ops.alloc_ucontext(ucontext, &attrs->driver_udata);
+	ret = ucontext->device->ops.alloc_ucontext(ucontext,
+						   &attrs->driver_udata);
 	if (ret)
-		goto err_file;
+		goto err_uncharge;
 
 	rdma_restrack_uadd(&ucontext->res);
 
-	fd_install(resp.async_fd, filp);
-
 	/*
 	 * Make sure that ib_uverbs_get_ucontext() sees the pointer update
 	 * only after all writes to setup the ucontext have completed
@@ -286,24 +259,62 @@ static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs)
 	smp_store_release(&file->ucontext, ucontext);
 
 	mutex_unlock(&file->ucontext_lock);
-
+	up_read(&file->hw_destroy_rwsem);
 	return 0;
 
-err_file:
-	ib_uverbs_free_async_event_file(file);
-	fput(filp);
+err_uncharge:
+	ib_rdmacg_uncharge(&ucontext->cg_obj, ucontext->device,
+			   RDMACG_RESOURCE_HCA_HANDLE);
+err:
+	mutex_unlock(&file->ucontext_lock);
+	up_read(&file->hw_destroy_rwsem);
+	return ret;
+}
 
-err_fd:
-	put_unused_fd(resp.async_fd);
+static int ib_uverbs_get_context(struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uverbs_get_context_resp resp;
+	struct ib_uverbs_get_context cmd;
+	struct ib_device *ib_dev;
+	struct ib_uobject *uobj;
+	int ret;
 
-err_free:
-	kfree(ucontext);
+	ret = uverbs_request(attrs, &cmd, sizeof(cmd));
+	if (ret)
+		return ret;
 
-err_alloc:
-	ib_rdmacg_uncharge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
+	ret = ib_alloc_ucontext(attrs);
+	if (ret)
+		return ret;
 
-err:
-	mutex_unlock(&file->ucontext_lock);
+	uobj = uobj_alloc(UVERBS_OBJECT_ASYNC_EVENT, attrs, &ib_dev);
+	if (IS_ERR(uobj)) {
+		ret = PTR_ERR(uobj);
+		goto err_ucontext;
+	}
+
+	resp = (struct ib_uverbs_get_context_resp){
+		.num_comp_vectors = attrs->ufile->device->num_comp_vectors,
+		.async_fd = uobj->id,
+	};
+	ret = uverbs_response(attrs, &resp, sizeof(resp));
+	if (ret)
+		goto err_uobj;
+
+	ret = ib_init_ucontext(attrs);
+	if (ret)
+		goto err_uobj;
+
+	ib_uverbs_init_async_event_file(
+		container_of(uobj, struct ib_uverbs_async_event_file, uobj));
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
+
+err_uobj:
+	rdma_alloc_abort_uobject(uobj, attrs);
+err_ucontext:
+	kfree(attrs->context);
+	attrs->context = NULL;
 	return ret;
 }
 
@@ -446,7 +457,8 @@ static int ib_uverbs_alloc_pd(struct uverbs_attr_bundle *attrs)
 	if (ret)
 		goto err_copy;
 
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 
 err_copy:
 	ib_dealloc_pd_user(pd, uverbs_get_cleared_udata(attrs));
@@ -642,7 +654,8 @@ static int ib_uverbs_open_xrcd(struct uverbs_attr_bundle *attrs)
 
 	mutex_unlock(&ibudev->xrcd_tree_mutex);
 
-	return uobj_alloc_commit(&obj->uobject, attrs);
+	rdma_alloc_commit_uobject(&obj->uobject, attrs);
+	return 0;
 
 err_copy:
 	if (inode) {
@@ -774,7 +787,8 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 
 	uobj_put_obj_read(pd);
 
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 
 err_copy:
 	ib_dereg_mr_user(mr, uverbs_get_cleared_udata(attrs));
@@ -928,7 +942,8 @@ static int ib_uverbs_alloc_mw(struct uverbs_attr_bundle *attrs)
 		goto err_copy;
 
 	uobj_put_obj_read(pd);
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 
 err_copy:
 	uverbs_dealloc_mw(mw);
@@ -980,7 +995,8 @@ static int ib_uverbs_create_comp_channel(struct uverbs_attr_bundle *attrs)
 		return ret;
 	}
 
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 }
 
 static struct ib_ucq_object *create_cq(struct uverbs_attr_bundle *attrs,
@@ -1010,11 +1026,9 @@ static struct ib_ucq_object *create_cq(struct uverbs_attr_bundle *attrs,
 		}
 	}
 
-	obj->uobject.user_handle = cmd->user_handle;
-	obj->comp_events_reported  = 0;
-	obj->async_events_reported = 0;
+	obj->uevent.uobject.user_handle = cmd->user_handle;
 	INIT_LIST_HEAD(&obj->comp_list);
-	INIT_LIST_HEAD(&obj->async_list);
+	INIT_LIST_HEAD(&obj->uevent.event_list);
 
 	attr.cqe = cmd->cqe;
 	attr.comp_vector = cmd->comp_vector;
@@ -1026,7 +1040,7 @@ static struct ib_ucq_object *create_cq(struct uverbs_attr_bundle *attrs,
 		goto err_file;
 	}
 	cq->device        = ib_dev;
-	cq->uobject       = &obj->uobject;
+	cq->uobject       = obj;
 	cq->comp_handler  = ib_uverbs_comp_handler;
 	cq->event_handler = ib_uverbs_cq_event_handler;
 	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
@@ -1036,9 +1050,9 @@ static struct ib_ucq_object *create_cq(struct uverbs_attr_bundle *attrs,
 	if (ret)
 		goto err_free;
 
-	obj->uobject.object = cq;
+	obj->uevent.uobject.object = cq;
 	memset(&resp, 0, sizeof resp);
-	resp.base.cq_handle = obj->uobject.id;
+	resp.base.cq_handle = obj->uevent.uobject.id;
 	resp.base.cqe       = cq->cqe;
 	resp.response_length = uverbs_response_length(attrs, sizeof(resp));
 
@@ -1049,9 +1063,7 @@ static struct ib_ucq_object *create_cq(struct uverbs_attr_bundle *attrs,
 	if (ret)
 		goto err_cb;
 
-	ret = uobj_alloc_commit(&obj->uobject, attrs);
-	if (ret)
-		return ERR_PTR(ret);
+	rdma_alloc_commit_uobject(&obj->uevent.uobject, attrs);
 	return obj;
 
 err_cb:
@@ -1061,10 +1073,10 @@ err_free:
 	kfree(cq);
 err_file:
 	if (ev_file)
-		ib_uverbs_release_ucq(attrs->ufile, ev_file, obj);
+		ib_uverbs_release_ucq(ev_file, obj);
 
 err:
-	uobj_alloc_abort(&obj->uobject, attrs);
+	uobj_alloc_abort(&obj->uevent.uobject, attrs);
 
 	return ERR_PTR(ret);
 }
@@ -1133,7 +1145,8 @@ static int ib_uverbs_resize_cq(struct uverbs_attr_bundle *attrs)
 
 	ret = uverbs_response(attrs, &resp, sizeof(resp));
 out:
-	uobj_put_obj_read(cq);
+	rdma_lookup_put_uobject(&cq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	return ret;
 }
@@ -1216,7 +1229,8 @@ static int ib_uverbs_poll_cq(struct uverbs_attr_bundle *attrs)
 		ret = uverbs_output_written(attrs, UVERBS_ATTR_CORE_OUT);
 
 out_put:
-	uobj_put_obj_read(cq);
+	rdma_lookup_put_uobject(&cq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	return ret;
 }
 
@@ -1237,8 +1251,8 @@ static int ib_uverbs_req_notify_cq(struct uverbs_attr_bundle *attrs)
 	ib_req_notify_cq(cq, cmd.solicited_only ?
 			 IB_CQ_SOLICITED : IB_CQ_NEXT_COMP);
 
-	uobj_put_obj_read(cq);
-
+	rdma_lookup_put_uobject(&cq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	return 0;
 }
 
@@ -1258,10 +1272,10 @@ static int ib_uverbs_destroy_cq(struct uverbs_attr_bundle *attrs)
 	if (IS_ERR(uobj))
 		return PTR_ERR(uobj);
 
-	obj = container_of(uobj, struct ib_ucq_object, uobject);
+	obj = container_of(uobj, struct ib_ucq_object, uevent.uobject);
 	memset(&resp, 0, sizeof(resp));
 	resp.comp_events_reported  = obj->comp_events_reported;
-	resp.async_events_reported = obj->async_events_reported;
+	resp.async_events_reported = obj->uevent.events_reported;
 
 	uobj_put_destroy(uobj);
 
@@ -1375,7 +1389,6 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 	}
 
 	attr.event_handler = ib_uverbs_qp_event_handler;
-	attr.qp_context    = attrs->ufile;
 	attr.send_cq       = scq;
 	attr.recv_cq       = rcq;
 	attr.srq           = srq;
@@ -1391,7 +1404,6 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 	attr.cap.max_recv_sge    = cmd->max_recv_sge;
 	attr.cap.max_inline_data = cmd->max_inline_data;
 
-	obj->uevent.events_reported     = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 	INIT_LIST_HEAD(&obj->mcast_list);
 
@@ -1421,7 +1433,7 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 		qp = ib_create_qp(pd, &attr);
 	else
 		qp = _ib_create_qp(device, pd, &attr, &attrs->driver_udata,
-				   &obj->uevent.uobject);
+				   obj);
 
 	if (IS_ERR(qp)) {
 		ret = PTR_ERR(qp);
@@ -1439,7 +1451,6 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 		qp->srq		  = attr.srq;
 		qp->rwq_ind_tbl	  = ind_tbl;
 		qp->event_handler = attr.event_handler;
-		qp->qp_context	  = attr.qp_context;
 		qp->qp_type	  = attr.qp_type;
 		atomic_set(&qp->usecnt, 0);
 		atomic_inc(&pd->usecnt);
@@ -1454,7 +1465,7 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 			atomic_inc(&ind_tbl->usecnt);
 	} else {
 		/* It is done in _ib_create_qp for other QP types */
-		qp->uobject = &obj->uevent.uobject;
+		qp->uobject = obj;
 	}
 
 	obj->uevent.uobject.object = qp;
@@ -1483,15 +1494,19 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 	if (pd)
 		uobj_put_obj_read(pd);
 	if (scq)
-		uobj_put_obj_read(scq);
+		rdma_lookup_put_uobject(&scq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 	if (rcq && rcq != scq)
-		uobj_put_obj_read(rcq);
+		rdma_lookup_put_uobject(&rcq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 	if (srq)
-		uobj_put_obj_read(srq);
+		rdma_lookup_put_uobject(&srq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 	if (ind_tbl)
 		uobj_put_obj_read(ind_tbl);
 
-	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
+	rdma_alloc_commit_uobject(&obj->uevent.uobject, attrs);
+	return 0;
 err_cb:
 	ib_destroy_qp_user(qp, uverbs_get_cleared_udata(attrs));
 
@@ -1501,11 +1516,14 @@ err_put:
 	if (pd)
 		uobj_put_obj_read(pd);
 	if (scq)
-		uobj_put_obj_read(scq);
+		rdma_lookup_put_uobject(&scq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 	if (rcq && rcq != scq)
-		uobj_put_obj_read(rcq);
+		rdma_lookup_put_uobject(&rcq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 	if (srq)
-		uobj_put_obj_read(srq);
+		rdma_lookup_put_uobject(&srq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 	if (ind_tbl)
 		uobj_put_obj_read(ind_tbl);
 
@@ -1567,7 +1585,7 @@ static int ib_uverbs_open_qp(struct uverbs_attr_bundle *attrs)
 	struct ib_xrcd		       *xrcd;
 	struct ib_uobject	       *uninitialized_var(xrcd_uobj);
 	struct ib_qp                   *qp;
-	struct ib_qp_open_attr          attr;
+	struct ib_qp_open_attr          attr = {};
 	int ret;
 	struct ib_device *ib_dev;
 
@@ -1593,11 +1611,9 @@ static int ib_uverbs_open_qp(struct uverbs_attr_bundle *attrs)
 	}
 
 	attr.event_handler = ib_uverbs_qp_event_handler;
-	attr.qp_context    = attrs->ufile;
 	attr.qp_num        = cmd.qpn;
 	attr.qp_type       = cmd.qp_type;
 
-	obj->uevent.events_reported = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 	INIT_LIST_HEAD(&obj->mcast_list);
 
@@ -1620,10 +1636,11 @@ static int ib_uverbs_open_qp(struct uverbs_attr_bundle *attrs)
 
 	obj->uxrcd = container_of(xrcd_uobj, struct ib_uxrcd_object, uobject);
 	atomic_inc(&obj->uxrcd->refcnt);
-	qp->uobject = &obj->uevent.uobject;
+	qp->uobject = obj;
 	uobj_put_read(xrcd_uobj);
 
-	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
+	rdma_alloc_commit_uobject(&obj->uevent.uobject, attrs);
+	return 0;
 
 err_destroy:
 	ib_destroy_qp_user(qp, uverbs_get_cleared_udata(attrs));
@@ -1684,7 +1701,8 @@ static int ib_uverbs_query_qp(struct uverbs_attr_bundle *attrs)
 
 	ret = ib_query_qp(qp, attr, cmd.attr_mask, init_attr);
 
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	if (ret)
 		goto out;
@@ -1921,7 +1939,8 @@ static int modify_qp(struct uverbs_attr_bundle *attrs,
 				      &attrs->driver_udata);
 
 release_qp:
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 out:
 	kfree(attr);
 
@@ -2185,7 +2204,8 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs)
 		ret = ret2;
 
 out_put:
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	while (wr) {
 		if (is_ud && ud_wr(wr)->ah)
@@ -2327,7 +2347,8 @@ static int ib_uverbs_post_recv(struct uverbs_attr_bundle *attrs)
 	resp.bad_wr = 0;
 	ret = qp->device->ops.post_recv(qp->real_qp, wr, &bad_wr);
 
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	if (ret) {
 		for (next = wr; next; next = next->next) {
 			++resp.bad_wr;
@@ -2377,7 +2398,8 @@ static int ib_uverbs_post_srq_recv(struct uverbs_attr_bundle *attrs)
 	resp.bad_wr = 0;
 	ret = srq->device->ops.post_srq_recv(srq, wr, &bad_wr);
 
-	uobj_put_obj_read(srq);
+	rdma_lookup_put_uobject(&srq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	if (ret)
 		for (next = wr; next; next = next->next) {
@@ -2465,7 +2487,8 @@ static int ib_uverbs_create_ah(struct uverbs_attr_bundle *attrs)
 		goto err_copy;
 
 	uobj_put_obj_read(pd);
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 
 err_copy:
 	rdma_destroy_ah_user(ah, RDMA_DESTROY_AH_SLEEPABLE,
@@ -2507,7 +2530,7 @@ static int ib_uverbs_attach_mcast(struct uverbs_attr_bundle *attrs)
 	if (!qp)
 		return -EINVAL;
 
-	obj = container_of(qp->uobject, struct ib_uqp_object, uevent.uobject);
+	obj = qp->uobject;
 
 	mutex_lock(&obj->mcast_lock);
 	list_for_each_entry(mcast, &obj->mcast_list, list)
@@ -2534,7 +2557,8 @@ static int ib_uverbs_attach_mcast(struct uverbs_attr_bundle *attrs)
 
 out_put:
 	mutex_unlock(&obj->mcast_lock);
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	return ret;
 }
@@ -2556,7 +2580,7 @@ static int ib_uverbs_detach_mcast(struct uverbs_attr_bundle *attrs)
 	if (!qp)
 		return -EINVAL;
 
-	obj = container_of(qp->uobject, struct ib_uqp_object, uevent.uobject);
+	obj = qp->uobject;
 	mutex_lock(&obj->mcast_lock);
 
 	list_for_each_entry(mcast, &obj->mcast_list, list)
@@ -2577,7 +2601,8 @@ static int ib_uverbs_detach_mcast(struct uverbs_attr_bundle *attrs)
 
 out_put:
 	mutex_unlock(&obj->mcast_lock);
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	return ret;
 }
 
@@ -2943,7 +2968,6 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs)
 	wq_init_attr.wq_type = cmd.wq_type;
 	wq_init_attr.event_handler = ib_uverbs_wq_event_handler;
 	wq_init_attr.create_flags = cmd.create_flags;
-	obj->uevent.events_reported = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 
 	wq = pd->device->ops.create_wq(pd, &wq_init_attr, &attrs->driver_udata);
@@ -2952,7 +2976,7 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs)
 		goto err_put_cq;
 	}
 
-	wq->uobject = &obj->uevent.uobject;
+	wq->uobject = obj;
 	obj->uevent.uobject.object = wq;
 	wq->wq_type = wq_init_attr.wq_type;
 	wq->cq = cq;
@@ -2962,7 +2986,7 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs)
 	atomic_set(&wq->usecnt, 0);
 	atomic_inc(&pd->usecnt);
 	atomic_inc(&cq->usecnt);
-	wq->uobject = &obj->uevent.uobject;
+	wq->uobject = obj;
 	obj->uevent.uobject.object = wq;
 
 	memset(&resp, 0, sizeof(resp));
@@ -2976,13 +3000,16 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs)
 		goto err_copy;
 
 	uobj_put_obj_read(pd);
-	uobj_put_obj_read(cq);
-	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
+	rdma_lookup_put_uobject(&cq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
+	rdma_alloc_commit_uobject(&obj->uevent.uobject, attrs);
+	return 0;
 
 err_copy:
 	ib_destroy_wq(wq, uverbs_get_cleared_udata(attrs));
 err_put_cq:
-	uobj_put_obj_read(cq);
+	rdma_lookup_put_uobject(&cq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 err_put_pd:
 	uobj_put_obj_read(pd);
 err_uobj:
@@ -3048,7 +3075,8 @@ static int ib_uverbs_ex_modify_wq(struct uverbs_attr_bundle *attrs)
 	}
 	ret = wq->device->ops.modify_wq(wq, &wq_attr, cmd.attr_mask,
 					&attrs->driver_udata);
-	uobj_put_obj_read(wq);
+	rdma_lookup_put_uobject(&wq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	return ret;
 }
 
@@ -3149,9 +3177,11 @@ static int ib_uverbs_ex_create_rwq_ind_table(struct uverbs_attr_bundle *attrs)
 	kfree(wqs_handles);
 
 	for (j = 0; j < num_read_wqs; j++)
-		uobj_put_obj_read(wqs[j]);
+		rdma_lookup_put_uobject(&wqs[j]->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 
 err_copy:
 	ib_destroy_rwq_ind_table(rwq_ind_tbl);
@@ -3159,7 +3189,8 @@ err_uobj:
 	uobj_alloc_abort(uobj, attrs);
 put_wqs:
 	for (j = 0; j < num_read_wqs; j++)
-		uobj_put_obj_read(wqs[j]);
+		rdma_lookup_put_uobject(&wqs[j]->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 err_free:
 	kfree(wqs_handles);
 	kfree(wqs);
@@ -3325,11 +3356,13 @@ static int ib_uverbs_ex_create_flow(struct uverbs_attr_bundle *attrs)
 	if (err)
 		goto err_copy;
 
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	kfree(flow_attr);
 	if (cmd.flow_attr.num_of_specs)
 		kfree(kern_flow_attr);
-	return uobj_alloc_commit(uobj, attrs);
+	rdma_alloc_commit_uobject(uobj, attrs);
+	return 0;
 err_copy:
 	if (!qp->device->ops.destroy_flow(flow_id))
 		atomic_dec(&qp->usecnt);
@@ -3338,7 +3371,8 @@ err_free:
 err_free_flow_attr:
 	kfree(flow_attr);
 err_put:
-	uobj_put_obj_read(qp);
+	rdma_lookup_put_uobject(&qp->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 err_uobj:
 	uobj_alloc_abort(uobj, attrs);
 err_free_attr:
@@ -3423,7 +3457,6 @@ static int __uverbs_create_xsrq(struct uverbs_attr_bundle *attrs,
 	attr.attr.max_sge   = cmd->max_sge;
 	attr.attr.srq_limit = cmd->srq_limit;
 
-	obj->uevent.events_reported = 0;
 	INIT_LIST_HEAD(&obj->uevent.event_list);
 
 	srq = rdma_zalloc_drv_obj(ib_dev, ib_srq);
@@ -3435,7 +3468,7 @@ static int __uverbs_create_xsrq(struct uverbs_attr_bundle *attrs,
 	srq->device        = pd->device;
 	srq->pd            = pd;
 	srq->srq_type	   = cmd->srq_type;
-	srq->uobject       = &obj->uevent.uobject;
+	srq->uobject       = obj;
 	srq->event_handler = attr.event_handler;
 	srq->srq_context   = attr.srq_context;
 
@@ -3474,10 +3507,12 @@ static int __uverbs_create_xsrq(struct uverbs_attr_bundle *attrs,
 		uobj_put_read(xrcd_uobj);
 
 	if (ib_srq_has_cq(cmd->srq_type))
-		uobj_put_obj_read(attr.ext.cq);
+		rdma_lookup_put_uobject(&attr.ext.cq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 
 	uobj_put_obj_read(pd);
-	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
+	rdma_alloc_commit_uobject(&obj->uevent.uobject, attrs);
+	return 0;
 
 err_copy:
 	ib_destroy_srq_user(srq, uverbs_get_cleared_udata(attrs));
@@ -3490,7 +3525,8 @@ err_put:
 
 err_put_cq:
 	if (ib_srq_has_cq(cmd->srq_type))
-		uobj_put_obj_read(attr.ext.cq);
+		rdma_lookup_put_uobject(&attr.ext.cq->uobject->uevent.uobject,
+					UVERBS_LOOKUP_READ);
 
 err_put_xrcd:
 	if (cmd->srq_type == IB_SRQT_XRC) {
@@ -3558,7 +3594,8 @@ static int ib_uverbs_modify_srq(struct uverbs_attr_bundle *attrs)
 	ret = srq->device->ops.modify_srq(srq, &attr, cmd.attr_mask,
 					  &attrs->driver_udata);
 
-	uobj_put_obj_read(srq);
+	rdma_lookup_put_uobject(&srq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	return ret;
 }
@@ -3581,7 +3618,8 @@ static int ib_uverbs_query_srq(struct uverbs_attr_bundle *attrs)
 
 	ret = ib_query_srq(srq, &attr);
 
-	uobj_put_obj_read(srq);
+	rdma_lookup_put_uobject(&srq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 
 	if (ret)
 		return ret;
@@ -3706,8 +3744,8 @@ static int ib_uverbs_ex_modify_cq(struct uverbs_attr_bundle *attrs)
 
 	ret = rdma_set_cq_moderation(cq, cmd.attr.cq_count, cmd.attr.cq_period);
 
-	uobj_put_obj_read(cq);
-
+	rdma_lookup_put_uobject(&cq->uobject->uevent.uobject,
+				UVERBS_LOOKUP_READ);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
index 269938f59d3f..538affbc517e 100644
--- a/drivers/infiniband/core/uverbs_ioctl.c
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -220,24 +220,17 @@ static int uverbs_process_idrs_array(struct bundle_priv *pbundle,
 	return ret;
 }
 
-static int uverbs_free_idrs_array(const struct uverbs_api_attr *attr_uapi,
-				  struct uverbs_objs_arr_attr *attr,
-				  bool commit, struct uverbs_attr_bundle *attrs)
+static void uverbs_free_idrs_array(const struct uverbs_api_attr *attr_uapi,
+				   struct uverbs_objs_arr_attr *attr,
+				   bool commit,
+				   struct uverbs_attr_bundle *attrs)
 {
 	const struct uverbs_attr_spec *spec = &attr_uapi->spec;
-	int current_ret;
-	int ret = 0;
 	size_t i;
 
-	for (i = 0; i != attr->len; i++) {
-		current_ret = uverbs_finalize_object(attr->uobjects[i],
-						     spec->u2.objs_arr.access,
-						     commit, attrs);
-		if (!ret)
-			ret = current_ret;
-	}
-
-	return ret;
+	for (i = 0; i != attr->len; i++)
+		uverbs_finalize_object(attr->uobjects[i],
+				       spec->u2.objs_arr.access, commit, attrs);
 }
 
 static int uverbs_process_attr(struct bundle_priv *pbundle,
@@ -495,26 +488,22 @@ static int ib_uverbs_run_method(struct bundle_priv *pbundle,
 	return ret;
 }
 
-static int bundle_destroy(struct bundle_priv *pbundle, bool commit)
+static void bundle_destroy(struct bundle_priv *pbundle, bool commit)
 {
 	unsigned int key_bitmap_len = pbundle->method_elm->key_bitmap_len;
 	struct bundle_alloc_head *memblock;
 	unsigned int i;
-	int ret = 0;
 
 	/* fast path for simple uobjects */
 	i = -1;
 	while ((i = find_next_bit(pbundle->uobj_finalize, key_bitmap_len,
 				  i + 1)) < key_bitmap_len) {
 		struct uverbs_attr *attr = &pbundle->bundle.attrs[i];
-		int current_ret;
 
-		current_ret = uverbs_finalize_object(
+		uverbs_finalize_object(
 			attr->obj_attr.uobject,
 			attr->obj_attr.attr_elm->spec.u.obj.access, commit,
 			&pbundle->bundle);
-		if (!ret)
-			ret = current_ret;
 	}
 
 	i = -1;
@@ -523,7 +512,6 @@ static int bundle_destroy(struct bundle_priv *pbundle, bool commit)
 		struct uverbs_attr *attr = &pbundle->bundle.attrs[i];
 		const struct uverbs_api_attr *attr_uapi;
 		void __rcu **slot;
-		int current_ret;
 
 		slot = uapi_get_attr_for_method(
 			pbundle,
@@ -534,11 +522,8 @@ static int bundle_destroy(struct bundle_priv *pbundle, bool commit)
 		attr_uapi = rcu_dereference_protected(*slot, true);
 
 		if (attr_uapi->spec.type == UVERBS_ATTR_TYPE_IDRS_ARRAY) {
-			current_ret = uverbs_free_idrs_array(
-				attr_uapi, &attr->objs_arr_attr, commit,
-				&pbundle->bundle);
-			if (!ret)
-				ret = current_ret;
+			uverbs_free_idrs_array(attr_uapi, &attr->objs_arr_attr,
+					       commit, &pbundle->bundle);
 		}
 	}
 
@@ -548,8 +533,6 @@ static int bundle_destroy(struct bundle_priv *pbundle, bool commit)
 		memblock = memblock->next;
 		kvfree(tmp);
 	}
-
-	return ret;
 }
 
 static int ib_uverbs_cmd_verbs(struct ib_uverbs_file *ufile,
@@ -562,7 +545,6 @@ static int ib_uverbs_cmd_verbs(struct ib_uverbs_file *ufile,
 	struct bundle_priv *pbundle;
 	struct bundle_priv onstack;
 	void __rcu **slot;
-	int destroy_ret;
 	int ret;
 
 	if (unlikely(hdr->driver_id != uapi->driver_id))
@@ -610,10 +592,7 @@ static int ib_uverbs_cmd_verbs(struct ib_uverbs_file *ufile,
 	memset(pbundle->spec_finalize, 0, sizeof(pbundle->spec_finalize));
 
 	ret = ib_uverbs_run_method(pbundle, hdr->num_attrs);
-	destroy_ret = bundle_destroy(pbundle, ret == 0);
-	if (unlikely(destroy_ret && !ret))
-		return destroy_ret;
-
+	bundle_destroy(pbundle, ret == 0);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 970d8e31dd65..2d4083bf4a04 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -125,17 +125,8 @@ static void ib_uverbs_release_dev(struct device *device)
 	kfree(dev);
 }
 
-static void ib_uverbs_release_async_event_file(struct kref *ref)
-{
-	struct ib_uverbs_async_event_file *file =
-		container_of(ref, struct ib_uverbs_async_event_file, ref);
-
-	kfree(file);
-}
-
-void ib_uverbs_release_ucq(struct ib_uverbs_file *file,
-			  struct ib_uverbs_completion_event_file *ev_file,
-			  struct ib_ucq_object *uobj)
+void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file,
+			   struct ib_ucq_object *uobj)
 {
 	struct ib_uverbs_event *evt, *tmp;
 
@@ -150,25 +141,24 @@ void ib_uverbs_release_ucq(struct ib_uverbs_file *file,
 		uverbs_uobject_put(&ev_file->uobj);
 	}
 
-	spin_lock_irq(&file->async_file->ev_queue.lock);
-	list_for_each_entry_safe(evt, tmp, &uobj->async_list, obj_list) {
-		list_del(&evt->list);
-		kfree(evt);
-	}
-	spin_unlock_irq(&file->async_file->ev_queue.lock);
+	ib_uverbs_release_uevent(&uobj->uevent);
 }
 
-void ib_uverbs_release_uevent(struct ib_uverbs_file *file,
-			      struct ib_uevent_object *uobj)
+void ib_uverbs_release_uevent(struct ib_uevent_object *uobj)
 {
+	struct ib_uverbs_async_event_file *async_file =
+		READ_ONCE(uobj->uobject.ufile->async_file);
 	struct ib_uverbs_event *evt, *tmp;
 
-	spin_lock_irq(&file->async_file->ev_queue.lock);
+	if (!async_file)
+		return;
+
+	spin_lock_irq(&async_file->ev_queue.lock);
 	list_for_each_entry_safe(evt, tmp, &uobj->event_list, obj_list) {
 		list_del(&evt->list);
 		kfree(evt);
 	}
-	spin_unlock_irq(&file->async_file->ev_queue.lock);
+	spin_unlock_irq(&async_file->ev_queue.lock);
 }
 
 void ib_uverbs_detach_umcast(struct ib_qp *qp,
@@ -208,8 +198,7 @@ void ib_uverbs_release_file(struct kref *ref)
 		ib_uverbs_comp_dev(file->device);
 
 	if (file->async_file)
-		kref_put(&file->async_file->ref,
-			 ib_uverbs_release_async_event_file);
+		uverbs_uobject_put(&file->async_file->uobj);
 	put_device(&file->device->dev);
 
 	if (file->disassociate_page)
@@ -220,7 +209,6 @@ void ib_uverbs_release_file(struct kref *ref)
 }
 
 static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue,
-				    struct ib_uverbs_file *uverbs_file,
 				    struct file *filp, char __user *buf,
 				    size_t count, loff_t *pos,
 				    size_t eventsz)
@@ -238,19 +226,16 @@ static ssize_t ib_uverbs_event_read(struct ib_uverbs_event_queue *ev_queue,
 
 		if (wait_event_interruptible(ev_queue->poll_wait,
 					     (!list_empty(&ev_queue->event_list) ||
-			/* The barriers built into wait_event_interruptible()
-			 * and wake_up() guarentee this will see the null set
-			 * without using RCU
-			 */
-					     !uverbs_file->device->ib_dev)))
+					      ev_queue->is_closed)))
 			return -ERESTARTSYS;
 
+		spin_lock_irq(&ev_queue->lock);
+
 		/* If device was disassociated and no event exists set an error */
-		if (list_empty(&ev_queue->event_list) &&
-		    !uverbs_file->device->ib_dev)
+		if (list_empty(&ev_queue->event_list) && ev_queue->is_closed) {
+			spin_unlock_irq(&ev_queue->lock);
 			return -EIO;
-
-		spin_lock_irq(&ev_queue->lock);
+		}
 	}
 
 	event = list_entry(ev_queue->event_list.next, struct ib_uverbs_event, list);
@@ -285,8 +270,7 @@ static ssize_t ib_uverbs_async_event_read(struct file *filp, char __user *buf,
 {
 	struct ib_uverbs_async_event_file *file = filp->private_data;
 
-	return ib_uverbs_event_read(&file->ev_queue, file->uverbs_file, filp,
-				    buf, count, pos,
+	return ib_uverbs_event_read(&file->ev_queue, filp, buf, count, pos,
 				    sizeof(struct ib_uverbs_async_event_desc));
 }
 
@@ -296,9 +280,8 @@ static ssize_t ib_uverbs_comp_event_read(struct file *filp, char __user *buf,
 	struct ib_uverbs_completion_event_file *comp_ev_file =
 		filp->private_data;
 
-	return ib_uverbs_event_read(&comp_ev_file->ev_queue,
-				    comp_ev_file->uobj.ufile, filp,
-				    buf, count, pos,
+	return ib_uverbs_event_read(&comp_ev_file->ev_queue, filp, buf, count,
+				    pos,
 				    sizeof(struct ib_uverbs_comp_event_desc));
 }
 
@@ -321,7 +304,9 @@ static __poll_t ib_uverbs_event_poll(struct ib_uverbs_event_queue *ev_queue,
 static __poll_t ib_uverbs_async_event_poll(struct file *filp,
 					       struct poll_table_struct *wait)
 {
-	return ib_uverbs_event_poll(filp->private_data, filp, wait);
+	struct ib_uverbs_async_event_file *file = filp->private_data;
+
+	return ib_uverbs_event_poll(&file->ev_queue, filp, wait);
 }
 
 static __poll_t ib_uverbs_comp_event_poll(struct file *filp,
@@ -335,9 +320,9 @@ static __poll_t ib_uverbs_comp_event_poll(struct file *filp,
 
 static int ib_uverbs_async_event_fasync(int fd, struct file *filp, int on)
 {
-	struct ib_uverbs_event_queue *ev_queue = filp->private_data;
+	struct ib_uverbs_async_event_file *file = filp->private_data;
 
-	return fasync_helper(fd, filp, on, &ev_queue->async_queue);
+	return fasync_helper(fd, filp, on, &file->ev_queue.async_queue);
 }
 
 static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on)
@@ -348,70 +333,20 @@ static int ib_uverbs_comp_event_fasync(int fd, struct file *filp, int on)
 	return fasync_helper(fd, filp, on, &comp_ev_file->ev_queue.async_queue);
 }
 
-static int ib_uverbs_async_event_close(struct inode *inode, struct file *filp)
-{
-	struct ib_uverbs_async_event_file *file = filp->private_data;
-	struct ib_uverbs_file *uverbs_file = file->uverbs_file;
-	struct ib_uverbs_event *entry, *tmp;
-	int closed_already = 0;
-
-	mutex_lock(&uverbs_file->device->lists_mutex);
-	spin_lock_irq(&file->ev_queue.lock);
-	closed_already = file->ev_queue.is_closed;
-	file->ev_queue.is_closed = 1;
-	list_for_each_entry_safe(entry, tmp, &file->ev_queue.event_list, list) {
-		if (entry->counter)
-			list_del(&entry->obj_list);
-		kfree(entry);
-	}
-	spin_unlock_irq(&file->ev_queue.lock);
-	if (!closed_already) {
-		list_del(&file->list);
-		ib_unregister_event_handler(&uverbs_file->event_handler);
-	}
-	mutex_unlock(&uverbs_file->device->lists_mutex);
-
-	kref_put(&uverbs_file->ref, ib_uverbs_release_file);
-	kref_put(&file->ref, ib_uverbs_release_async_event_file);
-
-	return 0;
-}
-
-static int ib_uverbs_comp_event_close(struct inode *inode, struct file *filp)
-{
-	struct ib_uobject *uobj = filp->private_data;
-	struct ib_uverbs_completion_event_file *file = container_of(
-		uobj, struct ib_uverbs_completion_event_file, uobj);
-	struct ib_uverbs_event *entry, *tmp;
-
-	spin_lock_irq(&file->ev_queue.lock);
-	list_for_each_entry_safe(entry, tmp, &file->ev_queue.event_list, list) {
-		if (entry->counter)
-			list_del(&entry->obj_list);
-		kfree(entry);
-	}
-	file->ev_queue.is_closed = 1;
-	spin_unlock_irq(&file->ev_queue.lock);
-
-	uverbs_close_fd(filp);
-
-	return 0;
-}
-
 const struct file_operations uverbs_event_fops = {
 	.owner	 = THIS_MODULE,
 	.read	 = ib_uverbs_comp_event_read,
 	.poll    = ib_uverbs_comp_event_poll,
-	.release = ib_uverbs_comp_event_close,
+	.release = uverbs_uobject_fd_release,
 	.fasync  = ib_uverbs_comp_event_fasync,
 	.llseek	 = no_llseek,
 };
 
-static const struct file_operations uverbs_async_event_fops = {
+const struct file_operations uverbs_async_event_fops = {
 	.owner	 = THIS_MODULE,
 	.read	 = ib_uverbs_async_event_read,
 	.poll    = ib_uverbs_async_event_poll,
-	.release = ib_uverbs_async_event_close,
+	.release = uverbs_uobject_fd_release,
 	.fasync  = ib_uverbs_async_event_fasync,
 	.llseek	 = no_llseek,
 };
@@ -438,9 +373,9 @@ void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context)
 		return;
 	}
 
-	uobj = container_of(cq->uobject, struct ib_ucq_object, uobject);
+	uobj = cq->uobject;
 
-	entry->desc.comp.cq_handle = cq->uobject->user_handle;
+	entry->desc.comp.cq_handle = cq->uobject->uevent.uobject.user_handle;
 	entry->counter		   = &uobj->comp_events_reported;
 
 	list_add_tail(&entry->list, &ev_queue->event_list);
@@ -451,102 +386,82 @@ void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context)
 	kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN);
 }
 
-static void ib_uverbs_async_handler(struct ib_uverbs_file *file,
-				    __u64 element, __u64 event,
-				    struct list_head *obj_list,
-				    u32 *counter)
+static void
+ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file,
+			__u64 element, __u64 event, struct list_head *obj_list,
+			u32 *counter)
 {
 	struct ib_uverbs_event *entry;
 	unsigned long flags;
 
-	spin_lock_irqsave(&file->async_file->ev_queue.lock, flags);
-	if (file->async_file->ev_queue.is_closed) {
-		spin_unlock_irqrestore(&file->async_file->ev_queue.lock, flags);
+	if (!async_file)
+		return;
+
+	spin_lock_irqsave(&async_file->ev_queue.lock, flags);
+	if (async_file->ev_queue.is_closed) {
+		spin_unlock_irqrestore(&async_file->ev_queue.lock, flags);
 		return;
 	}
 
 	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry) {
-		spin_unlock_irqrestore(&file->async_file->ev_queue.lock, flags);
+		spin_unlock_irqrestore(&async_file->ev_queue.lock, flags);
 		return;
 	}
 
-	entry->desc.async.element    = element;
+	entry->desc.async.element = element;
 	entry->desc.async.event_type = event;
-	entry->desc.async.reserved   = 0;
-	entry->counter               = counter;
+	entry->desc.async.reserved = 0;
+	entry->counter = counter;
 
-	list_add_tail(&entry->list, &file->async_file->ev_queue.event_list);
+	list_add_tail(&entry->list, &async_file->ev_queue.event_list);
 	if (obj_list)
 		list_add_tail(&entry->obj_list, obj_list);
-	spin_unlock_irqrestore(&file->async_file->ev_queue.lock, flags);
+	spin_unlock_irqrestore(&async_file->ev_queue.lock, flags);
 
-	wake_up_interruptible(&file->async_file->ev_queue.poll_wait);
-	kill_fasync(&file->async_file->ev_queue.async_queue, SIGIO, POLL_IN);
+	wake_up_interruptible(&async_file->ev_queue.poll_wait);
+	kill_fasync(&async_file->ev_queue.async_queue, SIGIO, POLL_IN);
 }
 
-void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr)
+static void uverbs_uobj_event(struct ib_uevent_object *eobj,
+			      struct ib_event *event)
 {
-	struct ib_ucq_object *uobj = container_of(event->element.cq->uobject,
-						  struct ib_ucq_object, uobject);
+	ib_uverbs_async_handler(READ_ONCE(eobj->uobject.ufile->async_file),
+				eobj->uobject.user_handle, event->event,
+				&eobj->event_list, &eobj->events_reported);
+}
 
-	ib_uverbs_async_handler(uobj->uobject.ufile, uobj->uobject.user_handle,
-				event->event, &uobj->async_list,
-				&uobj->async_events_reported);
+void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr)
+{
+	uverbs_uobj_event(&event->element.cq->uobject->uevent, event);
 }
 
 void ib_uverbs_qp_event_handler(struct ib_event *event, void *context_ptr)
 {
-	struct ib_uevent_object *uobj;
-
 	/* for XRC target qp's, check that qp is live */
 	if (!event->element.qp->uobject)
 		return;
 
-	uobj = container_of(event->element.qp->uobject,
-			    struct ib_uevent_object, uobject);
-
-	ib_uverbs_async_handler(context_ptr, uobj->uobject.user_handle,
-				event->event, &uobj->event_list,
-				&uobj->events_reported);
+	uverbs_uobj_event(&event->element.qp->uobject->uevent, event);
 }
 
 void ib_uverbs_wq_event_handler(struct ib_event *event, void *context_ptr)
 {
-	struct ib_uevent_object *uobj = container_of(event->element.wq->uobject,
-						  struct ib_uevent_object, uobject);
-
-	ib_uverbs_async_handler(context_ptr, uobj->uobject.user_handle,
-				event->event, &uobj->event_list,
-				&uobj->events_reported);
+	uverbs_uobj_event(&event->element.wq->uobject->uevent, event);
 }
 
 void ib_uverbs_srq_event_handler(struct ib_event *event, void *context_ptr)
 {
-	struct ib_uevent_object *uobj;
-
-	uobj = container_of(event->element.srq->uobject,
-			    struct ib_uevent_object, uobject);
-
-	ib_uverbs_async_handler(context_ptr, uobj->uobject.user_handle,
-				event->event, &uobj->event_list,
-				&uobj->events_reported);
-}
-
-void ib_uverbs_event_handler(struct ib_event_handler *handler,
-			     struct ib_event *event)
-{
-	struct ib_uverbs_file *file =
-		container_of(handler, struct ib_uverbs_file, event_handler);
-
-	ib_uverbs_async_handler(file, event->element.port_num, event->event,
-				NULL, NULL);
+	uverbs_uobj_event(&event->element.srq->uobject->uevent, event);
 }
 
-void ib_uverbs_free_async_event_file(struct ib_uverbs_file *file)
+static void ib_uverbs_event_handler(struct ib_event_handler *handler,
+				    struct ib_event *event)
 {
-	kref_put(&file->async_file->ref, ib_uverbs_release_async_event_file);
-	file->async_file = NULL;
+	ib_uverbs_async_handler(
+		container_of(handler, struct ib_uverbs_async_event_file,
+			     event_handler),
+		event->element.port_num, event->event, NULL, NULL);
 }
 
 void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue)
@@ -558,45 +473,26 @@ void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue)
 	ev_queue->async_queue = NULL;
 }
 
-struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file,
-					      struct ib_device	*ib_dev)
+void ib_uverbs_init_async_event_file(
+	struct ib_uverbs_async_event_file *async_file)
 {
-	struct ib_uverbs_async_event_file *ev_file;
-	struct file *filp;
-
-	ev_file = kzalloc(sizeof(*ev_file), GFP_KERNEL);
-	if (!ev_file)
-		return ERR_PTR(-ENOMEM);
-
-	ib_uverbs_init_event_queue(&ev_file->ev_queue);
-	ev_file->uverbs_file = uverbs_file;
-	kref_get(&ev_file->uverbs_file->ref);
-	kref_init(&ev_file->ref);
-	filp = anon_inode_getfile("[infinibandevent]", &uverbs_async_event_fops,
-				  ev_file, O_RDONLY);
-	if (IS_ERR(filp))
-		goto err_put_refs;
-
-	mutex_lock(&uverbs_file->device->lists_mutex);
-	list_add_tail(&ev_file->list,
-		      &uverbs_file->device->uverbs_events_file_list);
-	mutex_unlock(&uverbs_file->device->lists_mutex);
-
-	WARN_ON(uverbs_file->async_file);
-	uverbs_file->async_file = ev_file;
-	kref_get(&uverbs_file->async_file->ref);
-	INIT_IB_EVENT_HANDLER(&uverbs_file->event_handler,
-			      ib_dev,
-			      ib_uverbs_event_handler);
-	ib_register_event_handler(&uverbs_file->event_handler);
-	/* At that point async file stuff was fully set */
+	struct ib_uverbs_file *uverbs_file = async_file->uobj.ufile;
+	struct ib_device *ib_dev = async_file->uobj.context->device;
+
+	ib_uverbs_init_event_queue(&async_file->ev_queue);
 
-	return filp;
+	/* The first async_event_file becomes the default one for the file. */
+	mutex_lock(&uverbs_file->ucontext_lock);
+	if (!uverbs_file->async_file) {
+		/* Pairs with the put in ib_uverbs_release_file */
+		uverbs_uobject_get(&async_file->uobj);
+		smp_store_release(&uverbs_file->async_file, async_file);
+	}
+	mutex_unlock(&uverbs_file->ucontext_lock);
 
-err_put_refs:
-	kref_put(&ev_file->uverbs_file->ref, ib_uverbs_release_file);
-	kref_put(&ev_file->ref, ib_uverbs_release_async_event_file);
-	return filp;
+	INIT_IB_EVENT_HANDLER(&async_file->event_handler, ib_dev,
+			      ib_uverbs_event_handler);
+	ib_register_event_handler(&async_file->event_handler);
 }
 
 static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr,
@@ -1225,7 +1121,6 @@ static void ib_uverbs_add_one(struct ib_device *device)
 	mutex_init(&uverbs_dev->xrcd_tree_mutex);
 	mutex_init(&uverbs_dev->lists_mutex);
 	INIT_LIST_HEAD(&uverbs_dev->uverbs_file_list);
-	INIT_LIST_HEAD(&uverbs_dev->uverbs_events_file_list);
 	rcu_assign_pointer(uverbs_dev->ib_dev, device);
 	uverbs_dev->num_comp_vectors = device->num_comp_vectors;
 
@@ -1270,14 +1165,9 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 					struct ib_device *ib_dev)
 {
 	struct ib_uverbs_file *file;
-	struct ib_uverbs_async_event_file *event_file;
-	struct ib_event event;
 
 	/* Pending running commands to terminate */
 	uverbs_disassociate_api_pre(uverbs_dev);
-	event.event = IB_EVENT_DEVICE_FATAL;
-	event.element.port_num = 0;
-	event.device = ib_dev;
 
 	mutex_lock(&uverbs_dev->lists_mutex);
 	while (!list_empty(&uverbs_dev->uverbs_file_list)) {
@@ -1293,31 +1183,14 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 		 */
 		mutex_unlock(&uverbs_dev->lists_mutex);
 
-		ib_uverbs_event_handler(&file->event_handler, &event);
+		ib_uverbs_async_handler(READ_ONCE(file->async_file), 0,
+					IB_EVENT_DEVICE_FATAL, NULL, NULL);
+
 		uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE);
 		kref_put(&file->ref, ib_uverbs_release_file);
 
 		mutex_lock(&uverbs_dev->lists_mutex);
 	}
-
-	while (!list_empty(&uverbs_dev->uverbs_events_file_list)) {
-		event_file = list_first_entry(&uverbs_dev->
-					      uverbs_events_file_list,
-					      struct ib_uverbs_async_event_file,
-					      list);
-		spin_lock_irq(&event_file->ev_queue.lock);
-		event_file->ev_queue.is_closed = 1;
-		spin_unlock_irq(&event_file->ev_queue.lock);
-
-		list_del(&event_file->list);
-		ib_unregister_event_handler(
-			&event_file->uverbs_file->event_handler);
-		event_file->uverbs_file->event_handler.device =
-			NULL;
-
-		wake_up_interruptible(&event_file->ev_queue.poll_wait);
-		kill_fasync(&event_file->ev_queue.async_queue, SIGIO, POLL_IN);
-	}
 	mutex_unlock(&uverbs_dev->lists_mutex);
 
 	uverbs_disassociate_api(uverbs_dev->uapi);
diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index 35b2e2c640cc..994d8744b246 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -105,7 +105,7 @@ static int uverbs_free_qp(struct ib_uobject *uobject,
 	if (uqp->uxrcd)
 		atomic_dec(&uqp->uxrcd->refcnt);
 
-	ib_uverbs_release_uevent(attrs->ufile, &uqp->uevent);
+	ib_uverbs_release_uevent(&uqp->uevent);
 	return ret;
 }
 
@@ -138,7 +138,7 @@ static int uverbs_free_wq(struct ib_uobject *uobject,
 	if (ib_is_destroy_retryable(ret, why, uobject))
 		return ret;
 
-	ib_uverbs_release_uevent(attrs->ufile, &uwq->uevent);
+	ib_uverbs_release_uevent(&uwq->uevent);
 	return ret;
 }
 
@@ -163,7 +163,7 @@ static int uverbs_free_srq(struct ib_uobject *uobject,
 		atomic_dec(&us->uxrcd->refcnt);
 	}
 
-	ib_uverbs_release_uevent(attrs->ufile, uevent);
+	ib_uverbs_release_uevent(uevent);
 	return ret;
 }
 
@@ -202,24 +202,40 @@ static int uverbs_free_pd(struct ib_uobject *uobject,
 	return 0;
 }
 
-static int uverbs_hot_unplug_completion_event_file(struct ib_uobject *uobj,
-						   enum rdma_remove_reason why)
+void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue)
 {
-	struct ib_uverbs_completion_event_file *comp_event_file =
-		container_of(uobj, struct ib_uverbs_completion_event_file,
-			     uobj);
-	struct ib_uverbs_event_queue *event_queue = &comp_event_file->ev_queue;
+	struct ib_uverbs_event *entry, *tmp;
 
 	spin_lock_irq(&event_queue->lock);
+	/*
+	 * The user must ensure that no new items are added to the event_list
+	 * once is_closed is set.
+	 */
 	event_queue->is_closed = 1;
 	spin_unlock_irq(&event_queue->lock);
+	wake_up_interruptible(&event_queue->poll_wait);
+	kill_fasync(&event_queue->async_queue, SIGIO, POLL_IN);
 
-	if (why == RDMA_REMOVE_DRIVER_REMOVE) {
-		wake_up_interruptible(&event_queue->poll_wait);
-		kill_fasync(&event_queue->async_queue, SIGIO, POLL_IN);
+	spin_lock_irq(&event_queue->lock);
+	list_for_each_entry_safe(entry, tmp, &event_queue->event_list, list) {
+		if (entry->counter)
+			list_del(&entry->obj_list);
+		kfree(entry);
 	}
+	spin_unlock_irq(&event_queue->lock);
+}
+
+static int
+uverbs_completion_event_file_destroy_uobj(struct ib_uobject *uobj,
+					  enum rdma_remove_reason why)
+{
+	struct ib_uverbs_completion_event_file *file =
+		container_of(uobj, struct ib_uverbs_completion_event_file,
+			     uobj);
+
+	ib_uverbs_free_event_queue(&file->ev_queue);
 	return 0;
-};
+}
 
 int uverbs_destroy_def_handler(struct uverbs_attr_bundle *attrs)
 {
@@ -230,7 +246,7 @@ EXPORT_SYMBOL(uverbs_destroy_def_handler);
 DECLARE_UVERBS_NAMED_OBJECT(
 	UVERBS_OBJECT_COMP_CHANNEL,
 	UVERBS_TYPE_ALLOC_FD(sizeof(struct ib_uverbs_completion_event_file),
-			     uverbs_hot_unplug_completion_event_file,
+			     uverbs_completion_event_file_destroy_uobj,
 			     &uverbs_event_fops,
 			     "[infinibandevent]",
 			     O_RDONLY));
diff --git a/drivers/infiniband/core/uverbs_std_types_async_fd.c b/drivers/infiniband/core/uverbs_std_types_async_fd.c
new file mode 100644
index 000000000000..82ec0806b34b
--- /dev/null
+++ b/drivers/infiniband/core/uverbs_std_types_async_fd.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2019, Mellanox Technologies inc.  All rights reserved.
+ */
+
+#include <rdma/uverbs_std_types.h>
+#include <rdma/uverbs_ioctl.h>
+#include "rdma_core.h"
+#include "uverbs.h"
+
+static int UVERBS_HANDLER(UVERBS_METHOD_ASYNC_EVENT_ALLOC)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj =
+		uverbs_attr_get_uobject(attrs, UVERBS_METHOD_ASYNC_EVENT_ALLOC);
+
+	ib_uverbs_init_async_event_file(
+		container_of(uobj, struct ib_uverbs_async_event_file, uobj));
+	return 0;
+}
+
+static int uverbs_async_event_destroy_uobj(struct ib_uobject *uobj,
+					   enum rdma_remove_reason why)
+{
+	struct ib_uverbs_async_event_file *event_file =
+		container_of(uobj, struct ib_uverbs_async_event_file, uobj);
+
+	ib_unregister_event_handler(&event_file->event_handler);
+	ib_uverbs_free_event_queue(&event_file->ev_queue);
+	return 0;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_ASYNC_EVENT_ALLOC,
+	UVERBS_ATTR_FD(UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE,
+		       UVERBS_OBJECT_ASYNC_EVENT,
+		       UVERBS_ACCESS_NEW,
+		       UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_OBJECT(
+	UVERBS_OBJECT_ASYNC_EVENT,
+	UVERBS_TYPE_ALLOC_FD(sizeof(struct ib_uverbs_async_event_file),
+			     uverbs_async_event_destroy_uobj,
+			     &uverbs_async_event_fops,
+			     "[infinibandevent]",
+			     O_RDONLY),
+	&UVERBS_METHOD(UVERBS_METHOD_ASYNC_EVENT_ALLOC));
+
+const struct uapi_definition uverbs_def_obj_async_fd[] = {
+	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(UVERBS_OBJECT_ASYNC_EVENT),
+	{}
+};
diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c
index e39fe6a8aac4..da4110a0eea2 100644
--- a/drivers/infiniband/core/uverbs_std_types_cq.c
+++ b/drivers/infiniband/core/uverbs_std_types_cq.c
@@ -41,7 +41,7 @@ static int uverbs_free_cq(struct ib_uobject *uobject,
 	struct ib_cq *cq = uobject->object;
 	struct ib_uverbs_event_queue *ev_queue = cq->cq_context;
 	struct ib_ucq_object *ucq =
-		container_of(uobject, struct ib_ucq_object, uobject);
+		container_of(uobject, struct ib_ucq_object, uevent.uobject);
 	int ret;
 
 	ret = ib_destroy_cq_user(cq, &attrs->driver_udata);
@@ -49,7 +49,6 @@ static int uverbs_free_cq(struct ib_uobject *uobject,
 		return ret;
 
 	ib_uverbs_release_ucq(
-		attrs->ufile,
 		ev_queue ? container_of(ev_queue,
 					struct ib_uverbs_completion_event_file,
 					ev_queue) :
@@ -63,7 +62,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 {
 	struct ib_ucq_object *obj = container_of(
 		uverbs_attr_get_uobject(attrs, UVERBS_ATTR_CREATE_CQ_HANDLE),
-		typeof(*obj), uobject);
+		typeof(*obj), uevent.uobject);
 	struct ib_device *ib_dev = attrs->context->device;
 	int ret;
 	u64 user_handle;
@@ -106,10 +105,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 		goto err_event_file;
 	}
 
-	obj->comp_events_reported  = 0;
-	obj->async_events_reported = 0;
 	INIT_LIST_HEAD(&obj->comp_list);
-	INIT_LIST_HEAD(&obj->async_list);
+	INIT_LIST_HEAD(&obj->uevent.event_list);
 
 	cq = rdma_zalloc_drv_obj(ib_dev, ib_cq);
 	if (!cq) {
@@ -118,7 +115,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	}
 
 	cq->device        = ib_dev;
-	cq->uobject       = &obj->uobject;
+	cq->uobject       = obj;
 	cq->comp_handler  = ib_uverbs_comp_handler;
 	cq->event_handler = ib_uverbs_cq_event_handler;
 	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
@@ -129,8 +126,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 	if (ret)
 		goto err_free;
 
-	obj->uobject.object = cq;
-	obj->uobject.user_handle = user_handle;
+	obj->uevent.uobject.object = cq;
+	obj->uevent.uobject.user_handle = user_handle;
 	rdma_restrack_uadd(&cq->res);
 
 	ret = uverbs_copy_to(attrs, UVERBS_ATTR_CREATE_CQ_RESP_CQE, &cq->cqe,
@@ -182,10 +179,10 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_DESTROY)(
 	struct ib_uobject *uobj =
 		uverbs_attr_get_uobject(attrs, UVERBS_ATTR_DESTROY_CQ_HANDLE);
 	struct ib_ucq_object *obj =
-		container_of(uobj, struct ib_ucq_object, uobject);
+		container_of(uobj, struct ib_ucq_object, uevent.uobject);
 	struct ib_uverbs_destroy_cq_resp resp = {
 		.comp_events_reported = obj->comp_events_reported,
-		.async_events_reported = obj->async_events_reported
+		.async_events_reported = obj->uevent.events_reported
 	};
 
 	return uverbs_copy_to(attrs, UVERBS_ATTR_DESTROY_CQ_RESP, &resp,
diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
index 2a3f2f01028d..ae4a59d6f9b1 100644
--- a/drivers/infiniband/core/uverbs_std_types_device.c
+++ b/drivers/infiniband/core/uverbs_std_types_device.c
@@ -200,6 +200,43 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_PORT)(
 					     &resp, sizeof(resp));
 }
 
+static int UVERBS_HANDLER(UVERBS_METHOD_GET_CONTEXT)(
+	struct uverbs_attr_bundle *attrs)
+{
+	u32 num_comp = attrs->ufile->device->num_comp_vectors;
+	u64 core_support = IB_UVERBS_CORE_SUPPORT_OPTIONAL_MR_ACCESS;
+	int ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
+			     &num_comp, sizeof(num_comp));
+	if (IS_UVERBS_COPY_ERR(ret))
+		return ret;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
+			     &core_support, sizeof(core_support));
+	if (IS_UVERBS_COPY_ERR(ret))
+		return ret;
+
+	ret = ib_alloc_ucontext(attrs);
+	if (ret)
+		return ret;
+	ret = ib_init_ucontext(attrs);
+	if (ret) {
+		kfree(attrs->context);
+		attrs->context = NULL;
+		return ret;
+	}
+	return 0;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(
+	UVERBS_METHOD_GET_CONTEXT,
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
+			    UVERBS_ATTR_TYPE(u32), UA_OPTIONAL),
+	UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
+			    UVERBS_ATTR_TYPE(u64), UA_OPTIONAL),
+	UVERBS_ATTR_UHW());
+
 DECLARE_UVERBS_NAMED_METHOD(
 	UVERBS_METHOD_INFO_HANDLES,
 	/* Also includes any device specific object ids */
@@ -220,6 +257,7 @@ DECLARE_UVERBS_NAMED_METHOD(
 		UA_MANDATORY));
 
 DECLARE_UVERBS_GLOBAL_METHODS(UVERBS_OBJECT_DEVICE,
+			      &UVERBS_METHOD(UVERBS_METHOD_GET_CONTEXT),
 			      &UVERBS_METHOD(UVERBS_METHOD_INVOKE_WRITE),
 			      &UVERBS_METHOD(UVERBS_METHOD_INFO_HANDLES),
 			      &UVERBS_METHOD(UVERBS_METHOD_QUERY_PORT));
diff --git a/drivers/infiniband/core/uverbs_uapi.c b/drivers/infiniband/core/uverbs_uapi.c
index 00c547887132..3f121ac31e0a 100644
--- a/drivers/infiniband/core/uverbs_uapi.c
+++ b/drivers/infiniband/core/uverbs_uapi.c
@@ -195,9 +195,9 @@ static int uapi_merge_obj_tree(struct uverbs_api *uapi,
 		 * disassociation, and the FD types require the driver to use
 		 * struct file_operations.owner to prevent the driver module
 		 * code from unloading while the file is open. This provides
-		 * enough safety that uverbs_close_fd() will continue to work.
-		 * Drivers using FD are responsible to handle disassociation of
-		 * the device on their own.
+		 * enough safety that uverbs_uobject_fd_release() will
+		 * continue to work.  Drivers using FD are responsible to
+		 * handle disassociation of the device on their own.
 		 */
 		if (WARN_ON(is_driver &&
 			    obj->type_attrs->type_class != &uverbs_idr_class &&
@@ -626,6 +626,7 @@ void uverbs_destroy_api(struct uverbs_api *uapi)
 }
 
 static const struct uapi_definition uverbs_core_api[] = {
+	UAPI_DEF_CHAIN(uverbs_def_obj_async_fd),
 	UAPI_DEF_CHAIN(uverbs_def_obj_counters),
 	UAPI_DEF_CHAIN(uverbs_def_obj_cq),
 	UAPI_DEF_CHAIN(uverbs_def_obj_device),
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index d33bdc9b01cd..3ebae3b65c28 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -52,6 +52,9 @@
 #include <rdma/rw.h>
 
 #include "core_priv.h"
+#include <trace/events/rdma_core.h>
+
+#include <trace/events/rdma_core.h>
 
 static int ib_resolve_eth_dmac(struct ib_device *device,
 			       struct rdma_ah_attr *ah_attr);
@@ -1053,11 +1056,11 @@ static void __ib_shared_qp_event_handler(struct ib_event *event, void *context)
 	struct ib_qp *qp = context;
 	unsigned long flags;
 
-	spin_lock_irqsave(&qp->device->event_handler_lock, flags);
+	spin_lock_irqsave(&qp->device->qp_open_list_lock, flags);
 	list_for_each_entry(event->element.qp, &qp->open_list, open_list)
 		if (event->element.qp->event_handler)
 			event->element.qp->event_handler(event, event->element.qp->qp_context);
-	spin_unlock_irqrestore(&qp->device->event_handler_lock, flags);
+	spin_unlock_irqrestore(&qp->device->qp_open_list_lock, flags);
 }
 
 static void __ib_insert_xrcd_qp(struct ib_xrcd *xrcd, struct ib_qp *qp)
@@ -1094,9 +1097,9 @@ static struct ib_qp *__ib_open_qp(struct ib_qp *real_qp,
 	qp->qp_num = real_qp->qp_num;
 	qp->qp_type = real_qp->qp_type;
 
-	spin_lock_irqsave(&real_qp->device->event_handler_lock, flags);
+	spin_lock_irqsave(&real_qp->device->qp_open_list_lock, flags);
 	list_add(&qp->open_list, &real_qp->open_list);
-	spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);
+	spin_unlock_irqrestore(&real_qp->device->qp_open_list_lock, flags);
 
 	return qp;
 }
@@ -1824,9 +1827,9 @@ int ib_close_qp(struct ib_qp *qp)
 	if (real_qp == qp)
 		return -EINVAL;
 
-	spin_lock_irqsave(&real_qp->device->event_handler_lock, flags);
+	spin_lock_irqsave(&real_qp->device->qp_open_list_lock, flags);
 	list_del(&qp->open_list);
-	spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);
+	spin_unlock_irqrestore(&real_qp->device->qp_open_list_lock, flags);
 
 	atomic_dec(&real_qp->usecnt);
 	if (qp->qp_sec)
@@ -2038,6 +2041,7 @@ int ib_dereg_mr_user(struct ib_mr *mr, struct ib_udata *udata)
 	struct ib_sig_attrs *sig_attrs = mr->sig_attrs;
 	int ret;
 
+	trace_mr_dereg(mr);
 	rdma_restrack_del(&mr->res);
 	ret = mr->device->ops.dereg_mr(mr, udata);
 	if (!ret) {
@@ -2069,11 +2073,16 @@ struct ib_mr *ib_alloc_mr_user(struct ib_pd *pd, enum ib_mr_type mr_type,
 {
 	struct ib_mr *mr;
 
-	if (!pd->device->ops.alloc_mr)
-		return ERR_PTR(-EOPNOTSUPP);
+	if (!pd->device->ops.alloc_mr) {
+		mr = ERR_PTR(-EOPNOTSUPP);
+		goto out;
+	}
 
-	if (WARN_ON_ONCE(mr_type == IB_MR_TYPE_INTEGRITY))
-		return ERR_PTR(-EINVAL);
+	if (mr_type == IB_MR_TYPE_INTEGRITY) {
+		WARN_ON_ONCE(1);
+		mr = ERR_PTR(-EINVAL);
+		goto out;
+	}
 
 	mr = pd->device->ops.alloc_mr(pd, mr_type, max_num_sg, udata);
 	if (!IS_ERR(mr)) {
@@ -2089,6 +2098,8 @@ struct ib_mr *ib_alloc_mr_user(struct ib_pd *pd, enum ib_mr_type mr_type,
 		mr->sig_attrs = NULL;
 	}
 
+out:
+	trace_mr_alloc(pd, mr_type, max_num_sg, mr);
 	return mr;
 }
 EXPORT_SYMBOL(ib_alloc_mr_user);
@@ -2113,21 +2124,27 @@ struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
 	struct ib_sig_attrs *sig_attrs;
 
 	if (!pd->device->ops.alloc_mr_integrity ||
-	    !pd->device->ops.map_mr_sg_pi)
-		return ERR_PTR(-EOPNOTSUPP);
+	    !pd->device->ops.map_mr_sg_pi) {
+		mr = ERR_PTR(-EOPNOTSUPP);
+		goto out;
+	}
 
-	if (!max_num_meta_sg)
-		return ERR_PTR(-EINVAL);
+	if (!max_num_meta_sg) {
+		mr = ERR_PTR(-EINVAL);
+		goto out;
+	}
 
 	sig_attrs = kzalloc(sizeof(struct ib_sig_attrs), GFP_KERNEL);
-	if (!sig_attrs)
-		return ERR_PTR(-ENOMEM);
+	if (!sig_attrs) {
+		mr = ERR_PTR(-ENOMEM);
+		goto out;
+	}
 
 	mr = pd->device->ops.alloc_mr_integrity(pd, max_num_data_sg,
 						max_num_meta_sg);
 	if (IS_ERR(mr)) {
 		kfree(sig_attrs);
-		return mr;
+		goto out;
 	}
 
 	mr->device = pd->device;
@@ -2141,6 +2158,8 @@ struct ib_mr *ib_alloc_mr_integrity(struct ib_pd *pd,
 	mr->type = IB_MR_TYPE_INTEGRITY;
 	mr->sig_attrs = sig_attrs;
 
+out:
+	trace_mr_integ_alloc(pd, max_num_data_sg, max_num_meta_sg, mr);
 	return mr;
 }
 EXPORT_SYMBOL(ib_alloc_mr_integrity);
@@ -2785,6 +2804,7 @@ void ib_drain_sq(struct ib_qp *qp)
 		qp->device->ops.drain_sq(qp);
 	else
 		__ib_drain_sq(qp);
+	trace_cq_drain_complete(qp->send_cq);
 }
 EXPORT_SYMBOL(ib_drain_sq);
 
@@ -2813,6 +2833,7 @@ void ib_drain_rq(struct ib_qp *qp)
 		qp->device->ops.drain_rq(qp);
 	else
 		__ib_drain_rq(qp);
+	trace_cq_drain_complete(qp->recv_cq);
 }
 EXPORT_SYMBOL(ib_drain_rq);
 
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index e7e8a0f49464..793c97251588 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -677,7 +677,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev)
 
 	bnxt_qplib_get_guid(rdev->netdev->dev_addr, (u8 *)&ibdev->node_guid);
 
-	ibdev->num_comp_vectors	= 1;
+	ibdev->num_comp_vectors	= rdev->num_msix - 1;
 	ibdev->dev.parent = &rdev->en_dev->pdev->dev;
 	ibdev->local_dma_lkey = BNXT_QPLIB_RSVD_LKEY;
 
diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index e96bcb16bd2b..74b787a90660 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -160,10 +160,16 @@ struct efa_admin_create_qp_resp {
 	/* Common Admin Queue completion descriptor */
 	struct efa_admin_acq_common_desc acq_common_desc;
 
-	/* Opaque handle to be used for consequent operations on the QP */
+	/*
+	 * Opaque handle to be used for consequent admin operations on the
+	 * QP
+	 */
 	u32 qp_handle;
 
-	/* QP number in the given EFA virtual device */
+	/*
+	 * QP number in the given EFA virtual device. Least-significant bits
+	 *    (as needed according to max_qp) carry unique QP ID
+	 */
 	u16 qp_num;
 
 	/* MBZ */
@@ -286,6 +292,7 @@ struct efa_admin_create_ah_cmd {
 	/* PD number */
 	u16 pd;
 
+	/* MBZ */
 	u16 reserved;
 };
 
@@ -296,6 +303,7 @@ struct efa_admin_create_ah_resp {
 	/* Target interface address handle (opaque) */
 	u16 ah;
 
+	/* MBZ */
 	u16 reserved;
 };
 
@@ -372,6 +380,7 @@ struct efa_admin_reg_mr_cmd {
 	 */
 	u8 permissions;
 
+	/* MBZ */
 	u16 reserved16_w5;
 
 	/* number of pages in PBL (redundant, could be calculated) */
@@ -419,20 +428,20 @@ struct efa_admin_create_cq_cmd {
 	struct efa_admin_aq_common_desc aq_common_desc;
 
 	/*
-	 * 4:0 : reserved5
+	 * 4:0 : reserved5 - MBZ
 	 * 5 : interrupt_mode_enabled - if set, cq operates
 	 *    in interrupt mode (i.e. CQ events and MSI-X are
 	 *    generated), otherwise - polling
 	 * 6 : virt - If set, ring base address is virtual
 	 *    (IOVA returned by MR registration)
-	 * 7 : reserved6
+	 * 7 : reserved6 - MBZ
 	 */
 	u8 cq_caps_1;
 
 	/*
 	 * 4:0 : cq_entry_size_words - size of CQ entry in
 	 *    32-bit words, valid values: 4, 8.
-	 * 7:5 : reserved7
+	 * 7:5 : reserved7 - MBZ
 	 */
 	u8 cq_caps_2;
 
@@ -478,6 +487,7 @@ struct efa_admin_destroy_cq_cmd {
 
 	u16 cq_idx;
 
+	/* MBZ */
 	u16 reserved1;
 };
 
@@ -530,7 +540,7 @@ struct efa_admin_get_set_feature_common_desc {
 	/*
 	 * 1:0 : select - 0x1 - current value; 0x3 - default
 	 *    value
-	 * 7:3 : reserved3
+	 * 7:3 : reserved3 - MBZ
 	 */
 	u8 flags;
 
@@ -557,10 +567,10 @@ struct efa_admin_feature_device_attr_desc {
 	/* Bar used for SQ and RQ doorbells */
 	u16 db_bar;
 
-	/* Indicates how many bits are used physical address access */
+	/* Indicates how many bits are used on physical address access */
 	u8 phys_addr_width;
 
-	/* Indicates how many bits are used virtual address access */
+	/* Indicates how many bits are used on virtual address access */
 	u8 virt_addr_width;
 
 	/*
@@ -578,27 +588,28 @@ struct efa_admin_feature_queue_attr_desc {
 	/* The maximum number of queue pairs supported */
 	u32 max_qp;
 
+	/* Maximum number of WQEs per Send Queue */
 	u32 max_sq_depth;
 
-	/* max send wr used in inline-buf */
+	/* Maximum size of data that can be sent inline in a Send WQE */
 	u32 inline_buf_size;
 
+	/* Maximum number of buffer descriptors per Recv Queue */
 	u32 max_rq_depth;
 
 	/* The maximum number of completion queues supported per VF */
 	u32 max_cq;
 
+	/* Maximum number of CQEs per Completion Queue */
 	u32 max_cq_depth;
 
 	/* Number of sub-CQs to be created for each CQ */
 	u16 sub_cqs_per_cq;
 
+	/* MBZ */
 	u16 reserved;
 
-	/*
-	 * Maximum number of SGEs (buffs) allowed for a single send work
-	 *    queue element (WQE)
-	 */
+	/* Maximum number of SGEs (buffers) allowed for a single send WQE */
 	u16 max_wr_send_sges;
 
 	/* Maximum number of SGEs allowed for a single recv WQE */
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 4822f5fa12be..ec5545870554 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -387,8 +387,7 @@ static int efa_destroy_qp_handle(struct efa_dev *dev, u32 qp_handle)
 	return efa_com_destroy_qp(&dev->edev, &params);
 }
 
-static void efa_qp_user_mmap_entries_remove(struct efa_ucontext *uctx,
-					    struct efa_qp *qp)
+static void efa_qp_user_mmap_entries_remove(struct efa_qp *qp)
 {
 	rdma_user_mmap_entry_remove(qp->rq_mmap_entry);
 	rdma_user_mmap_entry_remove(qp->rq_db_mmap_entry);
@@ -398,8 +397,6 @@ static void efa_qp_user_mmap_entries_remove(struct efa_ucontext *uctx,
 
 int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 {
-	struct efa_ucontext *ucontext = rdma_udata_to_drv_context(udata,
-		struct efa_ucontext, ibucontext);
 	struct efa_dev *dev = to_edev(ibqp->pd->device);
 	struct efa_qp *qp = to_eqp(ibqp);
 	int err;
@@ -418,7 +415,7 @@ int efa_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 				 DMA_TO_DEVICE);
 	}
 
-	efa_qp_user_mmap_entries_remove(ucontext, qp);
+	efa_qp_user_mmap_entries_remove(qp);
 	kfree(qp);
 	return 0;
 }
@@ -510,7 +507,7 @@ static int qp_mmap_entries_setup(struct efa_qp *qp,
 	return 0;
 
 err_remove_mmap:
-	efa_qp_user_mmap_entries_remove(ucontext, qp);
+	efa_qp_user_mmap_entries_remove(qp);
 
 	return -ENOMEM;
 }
@@ -719,7 +716,7 @@ struct ib_qp *efa_create_qp(struct ib_pd *ibpd,
 	return &qp->ibqp;
 
 err_remove_mmap_entries:
-	efa_qp_user_mmap_entries_remove(ucontext, qp);
+	efa_qp_user_mmap_entries_remove(qp);
 err_destroy_qp:
 	efa_destroy_qp_handle(dev, create_qp_resp.qp_handle);
 err_free_mapped:
@@ -1370,6 +1367,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 		IB_ACCESS_LOCAL_WRITE |
 		(is_rdma_read_cap(dev) ? IB_ACCESS_REMOTE_READ : 0);
 
+	access_flags &= ~IB_ACCESS_OPTIONAL;
 	if (access_flags & ~supp_access_flags) {
 		ibdev_dbg(&dev->ibdev,
 			  "Unsupported access flags[%#x], supported[%#x]\n",
@@ -1608,13 +1606,12 @@ static int __efa_mmap(struct efa_dev *dev, struct efa_ucontext *ucontext,
 		err = -EINVAL;
 	}
 
-	if (err) {
+	if (err)
 		ibdev_dbg(
 			&dev->ibdev,
 			"Couldn't mmap address[%#llx] length[%#zx] mmap_flag[%d] err[%d]\n",
 			entry->address, rdma_entry->npages * PAGE_SIZE,
 			entry->mmap_flag, err);
-	}
 
 	rdma_user_mmap_entry_put(rdma_entry);
 	return err;
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9b1fb84a3d45..e0b1238d31df 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1685,6 +1685,14 @@ static u64 access_sw_pio_drain(const struct cntr_entry *entry,
 	return dd->verbs_dev.n_piodrain;
 }
 
+static u64 access_sw_ctx0_seq_drop(const struct cntr_entry *entry,
+				   void *context, int vl, int mode, u64 data)
+{
+	struct hfi1_devdata *dd = context;
+
+	return dd->ctx0_seq_drop;
+}
+
 static u64 access_sw_vtx_wait(const struct cntr_entry *entry,
 			      void *context, int vl, int mode, u64 data)
 {
@@ -4106,6 +4114,7 @@ def_access_ibp_counter(rc_crwaits);
 static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 [C_RCV_OVF] = RXE32_DEV_CNTR_ELEM(RcvOverflow, RCV_BUF_OVFL_CNT, CNTR_SYNTH),
 [C_RX_LEN_ERR] = RXE32_DEV_CNTR_ELEM(RxLenErr, RCV_LENGTH_ERR_CNT, CNTR_SYNTH),
+[C_RX_SHORT_ERR] = RXE32_DEV_CNTR_ELEM(RxShrErr, RCV_SHORT_ERR_CNT, CNTR_SYNTH),
 [C_RX_ICRC_ERR] = RXE32_DEV_CNTR_ELEM(RxICrcErr, RCV_ICRC_ERR_CNT, CNTR_SYNTH),
 [C_RX_EBP] = RXE32_DEV_CNTR_ELEM(RxEbpCnt, RCV_EBP_CNT, CNTR_SYNTH),
 [C_RX_TID_FULL] = RXE32_DEV_CNTR_ELEM(RxTIDFullEr, RCV_TID_FULL_ERR_CNT,
@@ -4249,6 +4258,8 @@ static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
 			    access_sw_cpu_intr),
 [C_SW_CPU_RCV_LIM] = CNTR_ELEM("RcvLimit", 0, 0, CNTR_NORMAL,
 			    access_sw_cpu_rcv_limit),
+[C_SW_CTX0_SEQ_DROP] = CNTR_ELEM("SeqDrop0", 0, 0, CNTR_NORMAL,
+			    access_sw_ctx0_seq_drop),
 [C_SW_VTX_WAIT] = CNTR_ELEM("vTxWait", 0, 0, CNTR_NORMAL,
 			    access_sw_vtx_wait),
 [C_SW_PIO_WAIT] = CNTR_ELEM("PioWait", 0, 0, CNTR_NORMAL,
@@ -6862,7 +6873,7 @@ static void rxe_kernel_unfreeze(struct hfi1_devdata *dd)
 		}
 		rcvmask = HFI1_RCVCTRL_CTXT_ENB;
 		/* HFI1_RCVCTRL_TAILUPD_[ENB|DIS] needs to be set explicitly */
-		rcvmask |= rcd->rcvhdrtail_kvaddr ?
+		rcvmask |= hfi1_rcvhdrtail_kvaddr(rcd) ?
 			HFI1_RCVCTRL_TAILUPD_ENB : HFI1_RCVCTRL_TAILUPD_DIS;
 		hfi1_rcvctrl(dd, rcvmask, rcd);
 		hfi1_rcd_put(rcd);
@@ -8394,20 +8405,62 @@ void force_recv_intr(struct hfi1_ctxtdata *rcd)
 static inline int check_packet_present(struct hfi1_ctxtdata *rcd)
 {
 	u32 tail;
-	int present;
 
-	if (!rcd->rcvhdrtail_kvaddr)
-		present = (rcd->seq_cnt ==
-				rhf_rcv_seq(rhf_to_cpu(get_rhf_addr(rcd))));
-	else /* is RDMA rtail */
-		present = (rcd->head != get_rcvhdrtail(rcd));
-
-	if (present)
+	if (hfi1_packet_present(rcd))
 		return 1;
 
 	/* fall back to a CSR read, correct indpendent of DMA_RTAIL */
 	tail = (u32)read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL);
-	return rcd->head != tail;
+	return hfi1_rcd_head(rcd) != tail;
+}
+
+/**
+ * Common code for receive contexts interrupt handlers.
+ * Update traces, increment kernel IRQ counter and
+ * setup ASPM when needed.
+ */
+static void receive_interrupt_common(struct hfi1_ctxtdata *rcd)
+{
+	struct hfi1_devdata *dd = rcd->dd;
+
+	trace_hfi1_receive_interrupt(dd, rcd);
+	this_cpu_inc(*dd->int_counter);
+	aspm_ctx_disable(rcd);
+}
+
+/**
+ * __hfi1_rcd_eoi_intr() - Make HW issue receive interrupt
+ * when there are packets present in the queue. When calling
+ * with interrupts enabled please use hfi1_rcd_eoi_intr.
+ *
+ * @rcd: valid receive context
+ */
+static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
+{
+	clear_recv_intr(rcd);
+	if (check_packet_present(rcd))
+		force_recv_intr(rcd);
+}
+
+/**
+ * hfi1_rcd_eoi_intr() - End of Interrupt processing action
+ *
+ * @rcd: Ptr to hfi1_ctxtdata of receive context
+ *
+ *  Hold IRQs so we can safely clear the interrupt and
+ *  recheck for a packet that may have arrived after the previous
+ *  check and the interrupt clear.  If a packet arrived, force another
+ *  interrupt. This routine can be called at the end of receive packet
+ *  processing in interrupt service routines, interrupt service thread
+ *  and softirqs
+ */
+static void hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__hfi1_rcd_eoi_intr(rcd);
+	local_irq_restore(flags);
 }
 
 /*
@@ -8421,13 +8474,9 @@ static inline int check_packet_present(struct hfi1_ctxtdata *rcd)
 irqreturn_t receive_context_interrupt(int irq, void *data)
 {
 	struct hfi1_ctxtdata *rcd = data;
-	struct hfi1_devdata *dd = rcd->dd;
 	int disposition;
-	int present;
 
-	trace_hfi1_receive_interrupt(dd, rcd);
-	this_cpu_inc(*dd->int_counter);
-	aspm_ctx_disable(rcd);
+	receive_interrupt_common(rcd);
 
 	/* receive interrupt remains blocked while processing packets */
 	disposition = rcd->do_interrupt(rcd, 0);
@@ -8440,17 +8489,7 @@ irqreturn_t receive_context_interrupt(int irq, void *data)
 	if (disposition == RCV_PKT_LIMIT)
 		return IRQ_WAKE_THREAD;
 
-	/*
-	 * The packet processor detected no more packets.  Clear the receive
-	 * interrupt and recheck for a packet packet that may have arrived
-	 * after the previous check and interrupt clear.  If a packet arrived,
-	 * force another interrupt.
-	 */
-	clear_recv_intr(rcd);
-	present = check_packet_present(rcd);
-	if (present)
-		force_recv_intr(rcd);
-
+	__hfi1_rcd_eoi_intr(rcd);
 	return IRQ_HANDLED;
 }
 
@@ -8461,24 +8500,11 @@ irqreturn_t receive_context_interrupt(int irq, void *data)
 irqreturn_t receive_context_thread(int irq, void *data)
 {
 	struct hfi1_ctxtdata *rcd = data;
-	int present;
 
 	/* receive interrupt is still blocked from the IRQ handler */
 	(void)rcd->do_interrupt(rcd, 1);
 
-	/*
-	 * The packet processor will only return if it detected no more
-	 * packets.  Hold IRQs here so we can safely clear the interrupt and
-	 * recheck for a packet that may have arrived after the previous
-	 * check and the interrupt clear.  If a packet arrived, force another
-	 * interrupt.
-	 */
-	local_irq_disable();
-	clear_recv_intr(rcd);
-	present = check_packet_present(rcd);
-	if (present)
-		force_recv_intr(rcd);
-	local_irq_enable();
+	hfi1_rcd_eoi_intr(rcd);
 
 	return IRQ_HANDLED;
 }
@@ -10049,7 +10075,7 @@ u32 lrh_max_header_bytes(struct hfi1_devdata *dd)
 	 * the first kernel context would have been allocated by now so
 	 * we are guaranteed a valid value.
 	 */
-	return (dd->rcd[0]->rcvhdrqentsize - 2/*PBC/RHF*/ + 1/*ICRC*/) << 2;
+	return (get_hdrqentsize(dd->rcd[0]) - 2/*PBC/RHF*/ + 1/*ICRC*/) << 2;
 }
 
 /*
@@ -10094,7 +10120,7 @@ static void set_send_length(struct hfi1_pportdata *ppd)
 		thres = min(sc_percent_to_threshold(dd->vld[i].sc, 50),
 			    sc_mtu_to_threshold(dd->vld[i].sc,
 						dd->vld[i].mtu,
-						dd->rcd[0]->rcvhdrqentsize));
+						get_hdrqentsize(dd->rcd[0])));
 		for (j = 0; j < INIT_SC_PER_VL; j++)
 			sc_set_cr_threshold(
 					pio_select_send_context_vl(dd, j, i),
@@ -11821,7 +11847,7 @@ u32 hdrqempty(struct hfi1_ctxtdata *rcd)
 	head = (read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_HEAD)
 		& RCV_HDR_HEAD_HEAD_SMASK) >> RCV_HDR_HEAD_HEAD_SHIFT;
 
-	if (rcd->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(rcd))
 		tail = get_rcvhdrtail(rcd);
 	else
 		tail = read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL);
@@ -11865,6 +11891,84 @@ static u32 encoded_size(u32 size)
 	return 0x1;	/* if invalid, go with the minimum size */
 }
 
+/**
+ * encode_rcv_header_entry_size - return chip specific encoding for size
+ * @size: size in dwords
+ *
+ * Convert a receive header entry size that to the encoding used in the CSR.
+ *
+ * Return a zero if the given size is invalid, otherwise the encoding.
+ */
+u8 encode_rcv_header_entry_size(u8 size)
+{
+	/* there are only 3 valid receive header entry sizes */
+	if (size == 2)
+		return 1;
+	if (size == 16)
+		return 2;
+	if (size == 32)
+		return 4;
+	return 0; /* invalid */
+}
+
+/**
+ * hfi1_validate_rcvhdrcnt - validate hdrcnt
+ * @dd: the device data
+ * @thecnt: the header count
+ */
+int hfi1_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt)
+{
+	if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
+		dd_dev_err(dd, "Receive header queue count too small\n");
+		return -EINVAL;
+	}
+
+	if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
+		dd_dev_err(dd,
+			   "Receive header queue count cannot be greater than %u\n",
+			   HFI1_MAX_HDRQ_EGRBUF_CNT);
+		return -EINVAL;
+	}
+
+	if (thecnt % HDRQ_INCREMENT) {
+		dd_dev_err(dd, "Receive header queue count %d must be divisible by %lu\n",
+			   thecnt, HDRQ_INCREMENT);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * set_hdrq_regs - set header queue registers for context
+ * @dd: the device data
+ * @ctxt: the context
+ * @entsize: the dword entry size
+ * @hdrcnt: the number of header entries
+ */
+void set_hdrq_regs(struct hfi1_devdata *dd, u8 ctxt, u8 entsize, u16 hdrcnt)
+{
+	u64 reg;
+
+	reg = (((u64)hdrcnt >> HDRQ_SIZE_SHIFT) & RCV_HDR_CNT_CNT_MASK) <<
+	      RCV_HDR_CNT_CNT_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_CNT, reg);
+	reg = ((u64)encode_rcv_header_entry_size(entsize) &
+	       RCV_HDR_ENT_SIZE_ENT_SIZE_MASK) <<
+	      RCV_HDR_ENT_SIZE_ENT_SIZE_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_ENT_SIZE, reg);
+	reg = ((u64)DEFAULT_RCVHDRSIZE & RCV_HDR_SIZE_HDR_SIZE_MASK) <<
+	      RCV_HDR_SIZE_HDR_SIZE_SHIFT;
+	write_kctxt_csr(dd, ctxt, RCV_HDR_SIZE, reg);
+
+	/*
+	 * Program dummy tail address for every receive context
+	 * before enabling any receive context
+	 */
+	write_kctxt_csr(dd, ctxt, RCV_HDR_TAIL_ADDR,
+			dd->rcvhdrtail_dummy_dma);
+}
+
 void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 		  struct hfi1_ctxtdata *rcd)
 {
@@ -11886,13 +11990,13 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 		/* reset the tail and hdr addresses, and sequence count */
 		write_kctxt_csr(dd, ctxt, RCV_HDR_ADDR,
 				rcd->rcvhdrq_dma);
-		if (rcd->rcvhdrtail_kvaddr)
+		if (hfi1_rcvhdrtail_kvaddr(rcd))
 			write_kctxt_csr(dd, ctxt, RCV_HDR_TAIL_ADDR,
 					rcd->rcvhdrqtailaddr_dma);
-		rcd->seq_cnt = 1;
+		hfi1_set_seq_cnt(rcd, 1);
 
 		/* reset the cached receive header queue head value */
-		rcd->head = 0;
+		hfi1_set_rcd_head(rcd, 0);
 
 		/*
 		 * Zero the receive header queue so we don't get false
@@ -11972,7 +12076,7 @@ void hfi1_rcvctrl(struct hfi1_devdata *dd, unsigned int op,
 			      IS_RCVAVAIL_START + rcd->ctxt, false);
 		rcvctrl &= ~RCV_CTXT_CTRL_INTR_AVAIL_SMASK;
 	}
-	if ((op & HFI1_RCVCTRL_TAILUPD_ENB) && rcd->rcvhdrtail_kvaddr)
+	if ((op & HFI1_RCVCTRL_TAILUPD_ENB) && hfi1_rcvhdrtail_kvaddr(rcd))
 		rcvctrl |= RCV_CTXT_CTRL_TAIL_UPD_SMASK;
 	if (op & HFI1_RCVCTRL_TAILUPD_DIS) {
 		/* See comment on RcvCtxtCtrl.TailUpd above */
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 4ca5ac8d7e9e..725509261016 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -358,6 +358,8 @@
 #define MAX_EAGER_BUFFER       (256 * 1024)
 #define MAX_EAGER_BUFFER_TOTAL (64 * (1 << 20)) /* max per ctxt 64MB */
 #define MAX_EXPECTED_BUFFER    (2048 * 1024)
+#define HFI1_MIN_HDRQ_EGRBUF_CNT 32
+#define HFI1_MAX_HDRQ_EGRBUF_CNT 16352
 
 /*
  * Receive expected base and count and eager base and count increment -
@@ -699,6 +701,10 @@ static inline u32 chip_rcv_array_count(struct hfi1_devdata *dd)
 	return read_csr(dd, RCV_ARRAY_CNT);
 }
 
+u8 encode_rcv_header_entry_size(u8 size);
+int hfi1_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt);
+void set_hdrq_regs(struct hfi1_devdata *dd, u8 ctxt, u8 entsize, u16 hdrcnt);
+
 u64 create_pbc(struct hfi1_pportdata *ppd, u64 flags, int srate_mbs, u32 vl,
 	       u32 dw_len);
 
@@ -859,6 +865,7 @@ static inline int idx_from_vl(int vl)
 enum {
 	C_RCV_OVF = 0,
 	C_RX_LEN_ERR,
+	C_RX_SHORT_ERR,
 	C_RX_ICRC_ERR,
 	C_RX_EBP,
 	C_RX_TID_FULL,
@@ -926,6 +933,7 @@ enum {
 	C_DC_PG_STS_TX_MBE_CNT,
 	C_SW_CPU_INTR,
 	C_SW_CPU_RCV_LIM,
+	C_SW_CTX0_SEQ_DROP,
 	C_SW_VTX_WAIT,
 	C_SW_PIO_WAIT,
 	C_SW_PIO_DRAIN,
diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index ab3589d17aee..fb3ec9bff7a2 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -381,6 +381,7 @@
 #define DC_LCB_STS_LINK_TRANSFER_ACTIVE (DC_LCB_CSRS + 0x000000000468)
 #define DC_LCB_STS_ROUND_TRIP_LTP_CNT (DC_LCB_CSRS + 0x0000000004B0)
 #define RCV_LENGTH_ERR_CNT 0
+#define RCV_SHORT_ERR_CNT 2
 #define RCV_ICRC_ERR_CNT 6
 #define RCV_EBP_CNT 9
 #define RCV_BUF_OVFL_CNT 10
diff --git a/drivers/infiniband/hw/hfi1/common.h b/drivers/infiniband/hw/hfi1/common.h
index d47da7b0438f..40a1ff0c8a8e 100644
--- a/drivers/infiniband/hw/hfi1/common.h
+++ b/drivers/infiniband/hw/hfi1/common.h
@@ -323,6 +323,9 @@ struct diag_pkt {
 /* RHF receive type error - bypass packet errors */
 #define RHF_RTE_BYPASS_NO_ERR		0x0
 
+/* MAX RcvSEQ */
+#define RHF_MAX_SEQ 13
+
 /* IB - LRH header constants */
 #define HFI1_LRH_GRH 0x0003      /* 1. word of IB LRH - next header: GRH */
 #define HFI1_LRH_BTH 0x0002      /* 1. word of IB LRH - next header: BTH */
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index d268bf9c42ee..4633a0ce1a8c 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -379,7 +379,7 @@ static void *_rcds_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	struct hfi1_devdata *dd = dd_from_dev(ibd);
 
 	++*pos;
-	if (!dd->rcd || *pos >= dd->n_krcv_queues)
+	if (!dd->rcd || *pos >= dd->num_rcv_contexts)
 		return NULL;
 	return pos;
 }
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 01aa1f132f55..049d15befe58 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -411,14 +411,14 @@ drop:
 static inline void init_packet(struct hfi1_ctxtdata *rcd,
 			       struct hfi1_packet *packet)
 {
-	packet->rsize = rcd->rcvhdrqentsize; /* words */
-	packet->maxcnt = rcd->rcvhdrq_cnt * packet->rsize; /* words */
+	packet->rsize = get_hdrqentsize(rcd); /* words */
+	packet->maxcnt = get_hdrq_cnt(rcd) * packet->rsize; /* words */
 	packet->rcd = rcd;
 	packet->updegr = 0;
 	packet->etail = -1;
 	packet->rhf_addr = get_rhf_addr(rcd);
 	packet->rhf = rhf_to_cpu(packet->rhf_addr);
-	packet->rhqoff = rcd->head;
+	packet->rhqoff = hfi1_rcd_head(rcd);
 	packet->numpkt = 0;
 }
 
@@ -551,22 +551,22 @@ static inline void init_ps_mdata(struct ps_mdata *mdata,
 	mdata->maxcnt = packet->maxcnt;
 	mdata->ps_head = packet->rhqoff;
 
-	if (HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
+	if (get_dma_rtail_setting(rcd)) {
 		mdata->ps_tail = get_rcvhdrtail(rcd);
 		if (rcd->ctxt == HFI1_CTRL_CTXT)
-			mdata->ps_seq = rcd->seq_cnt;
+			mdata->ps_seq = hfi1_seq_cnt(rcd);
 		else
 			mdata->ps_seq = 0; /* not used with DMA_RTAIL */
 	} else {
 		mdata->ps_tail = 0; /* used only with DMA_RTAIL*/
-		mdata->ps_seq = rcd->seq_cnt;
+		mdata->ps_seq = hfi1_seq_cnt(rcd);
 	}
 }
 
 static inline int ps_done(struct ps_mdata *mdata, u64 rhf,
 			  struct hfi1_ctxtdata *rcd)
 {
-	if (HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL))
+	if (get_dma_rtail_setting(rcd))
 		return mdata->ps_head == mdata->ps_tail;
 	return mdata->ps_seq != rhf_rcv_seq(rhf);
 }
@@ -592,11 +592,9 @@ static inline void update_ps_mdata(struct ps_mdata *mdata,
 		mdata->ps_head = 0;
 
 	/* Control context must do seq counting */
-	if (!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ||
-	    (rcd->ctxt == HFI1_CTRL_CTXT)) {
-		if (++mdata->ps_seq > 13)
-			mdata->ps_seq = 1;
-	}
+	if (!get_dma_rtail_setting(rcd) ||
+	    rcd->ctxt == HFI1_CTRL_CTXT)
+		mdata->ps_seq = hfi1_seq_incr_wrap(mdata->ps_seq);
 }
 
 /*
@@ -734,6 +732,7 @@ static noinline int skip_rcv_packet(struct hfi1_packet *packet, int thread)
 {
 	int ret;
 
+	packet->rcd->dd->ctx0_seq_drop++;
 	/* Set up for the next packet */
 	packet->rhqoff += packet->rsize;
 	if (packet->rhqoff >= packet->maxcnt)
@@ -769,7 +768,7 @@ static inline int process_rcv_packet(struct hfi1_packet *packet, int thread)
 		 * The +2 is the size of the RHF.
 		 */
 		prefetch_range(packet->ebuf,
-			       packet->tlen - ((packet->rcd->rcvhdrqentsize -
+			       packet->tlen - ((get_hdrqentsize(packet->rcd) -
 					       (rhf_hdrq_offset(packet->rhf)
 						+ 2)) * 4));
 	}
@@ -823,7 +822,7 @@ static inline void finish_packet(struct hfi1_packet *packet)
 	 * The only thing we need to do is a final update and call for an
 	 * interrupt
 	 */
-	update_usrhead(packet->rcd, packet->rcd->head, packet->updegr,
+	update_usrhead(packet->rcd, hfi1_rcd_head(packet->rcd), packet->updegr,
 		       packet->etail, rcv_intr_dynamic, packet->numpkt);
 }
 
@@ -832,13 +831,11 @@ static inline void finish_packet(struct hfi1_packet *packet)
  */
 int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 {
-	u32 seq;
 	int last = RCV_PKT_OK;
 	struct hfi1_packet packet;
 
 	init_packet(rcd, &packet);
-	seq = rhf_rcv_seq(packet.rhf);
-	if (seq != rcd->seq_cnt) {
+	if (last_rcv_seq(rcd, rhf_rcv_seq(packet.rhf))) {
 		last = RCV_PKT_DONE;
 		goto bail;
 	}
@@ -847,15 +844,12 @@ int handle_receive_interrupt_nodma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 
 	while (last == RCV_PKT_OK) {
 		last = process_rcv_packet(&packet, thread);
-		seq = rhf_rcv_seq(packet.rhf);
-		if (++rcd->seq_cnt > 13)
-			rcd->seq_cnt = 1;
-		if (seq != rcd->seq_cnt)
+		if (hfi1_seq_incr(rcd, rhf_rcv_seq(packet.rhf)))
 			last = RCV_PKT_DONE;
 		process_rcv_update(last, &packet);
 	}
 	process_rcv_qp_work(&packet);
-	rcd->head = packet.rhqoff;
+	hfi1_set_rcd_head(rcd, packet.rhqoff);
 bail:
 	finish_packet(&packet);
 	return last;
@@ -884,15 +878,14 @@ int handle_receive_interrupt_dma_rtail(struct hfi1_ctxtdata *rcd, int thread)
 		process_rcv_update(last, &packet);
 	}
 	process_rcv_qp_work(&packet);
-	rcd->head = packet.rhqoff;
+	hfi1_set_rcd_head(rcd, packet.rhqoff);
 bail:
 	finish_packet(&packet);
 	return last;
 }
 
-static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt)
+static void set_all_fastpath(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 {
-	struct hfi1_ctxtdata *rcd;
 	u16 i;
 
 	/*
@@ -900,50 +893,17 @@ static inline void set_nodma_rtail(struct hfi1_devdata *dd, u16 ctxt)
 	 * interrupt handler only for that context. Otherwise, switch
 	 * interrupt handler for all statically allocated kernel contexts.
 	 */
-	if (ctxt >= dd->first_dyn_alloc_ctxt) {
-		rcd = hfi1_rcd_get_by_index_safe(dd, ctxt);
-		if (rcd) {
-			rcd->do_interrupt =
-				&handle_receive_interrupt_nodma_rtail;
-			hfi1_rcd_put(rcd);
-		}
-		return;
-	}
-
-	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++) {
-		rcd = hfi1_rcd_get_by_index(dd, i);
-		if (rcd)
-			rcd->do_interrupt =
-				&handle_receive_interrupt_nodma_rtail;
+	if (rcd->ctxt >= dd->first_dyn_alloc_ctxt && !rcd->is_vnic) {
+		hfi1_rcd_get(rcd);
+		hfi1_set_fast(rcd);
 		hfi1_rcd_put(rcd);
-	}
-}
-
-static inline void set_dma_rtail(struct hfi1_devdata *dd, u16 ctxt)
-{
-	struct hfi1_ctxtdata *rcd;
-	u16 i;
-
-	/*
-	 * For dynamically allocated kernel contexts (like vnic) switch
-	 * interrupt handler only for that context. Otherwise, switch
-	 * interrupt handler for all statically allocated kernel contexts.
-	 */
-	if (ctxt >= dd->first_dyn_alloc_ctxt) {
-		rcd = hfi1_rcd_get_by_index_safe(dd, ctxt);
-		if (rcd) {
-			rcd->do_interrupt =
-				&handle_receive_interrupt_dma_rtail;
-			hfi1_rcd_put(rcd);
-		}
 		return;
 	}
 
-	for (i = HFI1_CTRL_CTXT + 1; i < dd->first_dyn_alloc_ctxt; i++) {
+	for (i = HFI1_CTRL_CTXT + 1; i < dd->num_rcv_contexts; i++) {
 		rcd = hfi1_rcd_get_by_index(dd, i);
-		if (rcd)
-			rcd->do_interrupt =
-				&handle_receive_interrupt_dma_rtail;
+		if (rcd && (i < dd->first_dyn_alloc_ctxt || rcd->is_vnic))
+			hfi1_set_fast(rcd);
 		hfi1_rcd_put(rcd);
 	}
 }
@@ -959,17 +919,14 @@ void set_all_slowpath(struct hfi1_devdata *dd)
 		if (!rcd)
 			continue;
 		if (i < dd->first_dyn_alloc_ctxt || rcd->is_vnic)
-			rcd->do_interrupt = &handle_receive_interrupt;
+			rcd->do_interrupt = rcd->slow_handler;
 
 		hfi1_rcd_put(rcd);
 	}
 }
 
-static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
-				      struct hfi1_packet *packet,
-				      struct hfi1_devdata *dd)
+static bool __set_armed_to_active(struct hfi1_packet *packet)
 {
-	struct work_struct *lsaw = &rcd->ppd->linkstate_active_work;
 	u8 etype = rhf_rcv_type(packet->rhf);
 	u8 sc = SC15_PACKET;
 
@@ -984,19 +941,34 @@ static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
 		sc = hfi1_16B_get_sc(hdr);
 	}
 	if (sc != SC15_PACKET) {
-		int hwstate = driver_lstate(rcd->ppd);
+		int hwstate = driver_lstate(packet->rcd->ppd);
+		struct work_struct *lsaw =
+				&packet->rcd->ppd->linkstate_active_work;
 
 		if (hwstate != IB_PORT_ACTIVE) {
-			dd_dev_info(dd,
+			dd_dev_info(packet->rcd->dd,
 				    "Unexpected link state %s\n",
 				    opa_lstate_name(hwstate));
-			return 0;
+			return false;
 		}
 
-		queue_work(rcd->ppd->link_wq, lsaw);
-		return 1;
+		queue_work(packet->rcd->ppd->link_wq, lsaw);
+		return true;
 	}
-	return 0;
+	return false;
+}
+
+/**
+ * armed to active - the fast path for armed to active
+ * @packet: the packet structure
+ *
+ * Return true if packet processing needs to bail.
+ */
+static bool set_armed_to_active(struct hfi1_packet *packet)
+{
+	if (likely(packet->rcd->ppd->host_link_state != HLS_UP_ARMED))
+		return false;
+	return __set_armed_to_active(packet);
 }
 
 /*
@@ -1019,10 +991,8 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 
 	init_packet(rcd, &packet);
 
-	if (!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
-		u32 seq = rhf_rcv_seq(packet.rhf);
-
-		if (seq != rcd->seq_cnt) {
+	if (!get_dma_rtail_setting(rcd)) {
+		if (last_rcv_seq(rcd, rhf_rcv_seq(packet.rhf))) {
 			last = RCV_PKT_DONE;
 			goto bail;
 		}
@@ -1039,22 +1009,15 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 		 * Control context can potentially receive an invalid
 		 * rhf. Drop such packets.
 		 */
-		if (rcd->ctxt == HFI1_CTRL_CTXT) {
-			u32 seq = rhf_rcv_seq(packet.rhf);
-
-			if (seq != rcd->seq_cnt)
+		if (rcd->ctxt == HFI1_CTRL_CTXT)
+			if (last_rcv_seq(rcd, rhf_rcv_seq(packet.rhf)))
 				skip_pkt = 1;
-		}
 	}
 
 	prescan_rxq(rcd, &packet);
 
 	while (last == RCV_PKT_OK) {
-		if (unlikely(dd->do_drop &&
-			     atomic_xchg(&dd->drop_packet, DROP_PACKET_OFF) ==
-			     DROP_PACKET_ON)) {
-			dd->do_drop = 0;
-
+		if (hfi1_need_drop(dd)) {
 			/* On to the next packet */
 			packet.rhqoff += packet.rsize;
 			packet.rhf_addr = (__le32 *)rcd->rcvhdrq +
@@ -1066,26 +1029,14 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 			last = skip_rcv_packet(&packet, thread);
 			skip_pkt = 0;
 		} else {
-			/* Auto activate link on non-SC15 packet receive */
-			if (unlikely(rcd->ppd->host_link_state ==
-				     HLS_UP_ARMED) &&
-			    set_armed_to_active(rcd, &packet, dd))
+			if (set_armed_to_active(&packet))
 				goto bail;
 			last = process_rcv_packet(&packet, thread);
 		}
 
-		if (!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL)) {
-			u32 seq = rhf_rcv_seq(packet.rhf);
-
-			if (++rcd->seq_cnt > 13)
-				rcd->seq_cnt = 1;
-			if (seq != rcd->seq_cnt)
+		if (!get_dma_rtail_setting(rcd)) {
+			if (hfi1_seq_incr(rcd, rhf_rcv_seq(packet.rhf)))
 				last = RCV_PKT_DONE;
-			if (needset) {
-				dd_dev_info(dd, "Switching to NO_DMA_RTAIL\n");
-				set_nodma_rtail(dd, rcd->ctxt);
-				needset = 0;
-			}
 		} else {
 			if (packet.rhqoff == hdrqtail)
 				last = RCV_PKT_DONE;
@@ -1094,27 +1045,24 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread)
 			 * rhf. Drop such packets.
 			 */
 			if (rcd->ctxt == HFI1_CTRL_CTXT) {
-				u32 seq = rhf_rcv_seq(packet.rhf);
+				bool lseq;
 
-				if (++rcd->seq_cnt > 13)
-					rcd->seq_cnt = 1;
-				if (!last && (seq != rcd->seq_cnt))
+				lseq = hfi1_seq_incr(rcd,
+						     rhf_rcv_seq(packet.rhf));
+				if (!last && lseq)
 					skip_pkt = 1;
 			}
-
-			if (needset) {
-				dd_dev_info(dd,
-					    "Switching to DMA_RTAIL\n");
-				set_dma_rtail(dd, rcd->ctxt);
-				needset = 0;
-			}
 		}
 
+		if (needset) {
+			needset = false;
+			set_all_fastpath(dd, rcd);
+		}
 		process_rcv_update(last, &packet);
 	}
 
 	process_rcv_qp_work(&packet);
-	rcd->head = packet.rhqoff;
+	hfi1_set_rcd_head(rcd, packet.rhqoff);
 
 bail:
 	/*
@@ -1606,23 +1554,22 @@ void handle_eflags(struct hfi1_packet *packet)
  * The following functions are called by the interrupt handler. They are type
  * specific handlers for each packet type.
  */
-static int process_receive_ib(struct hfi1_packet *packet)
+static void process_receive_ib(struct hfi1_packet *packet)
 {
 	if (hfi1_setup_9B_packet(packet))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	if (unlikely(hfi1_dbg_should_fault_rx(packet)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	trace_hfi1_rcvhdr(packet);
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
-		return RHF_RCV_CONTINUE;
+		return;
 	}
 
 	hfi1_ib_rcv(packet);
-	return RHF_RCV_CONTINUE;
 }
 
 static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
@@ -1638,23 +1585,23 @@ static inline bool hfi1_is_vnic_packet(struct hfi1_packet *packet)
 	return false;
 }
 
-static int process_receive_bypass(struct hfi1_packet *packet)
+static void process_receive_bypass(struct hfi1_packet *packet)
 {
 	struct hfi1_devdata *dd = packet->rcd->dd;
 
 	if (hfi1_is_vnic_packet(packet)) {
 		hfi1_vnic_bypass_rcv(packet);
-		return RHF_RCV_CONTINUE;
+		return;
 	}
 
 	if (hfi1_setup_bypass_packet(packet))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	trace_hfi1_rcvhdr(packet);
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		handle_eflags(packet);
-		return RHF_RCV_CONTINUE;
+		return;
 	}
 
 	if (hfi1_16B_get_l2(packet->hdr) == 0x2) {
@@ -1677,17 +1624,16 @@ static int process_receive_bypass(struct hfi1_packet *packet)
 				(OPA_EI_STATUS_SMASK | BAD_L2_ERR);
 		}
 	}
-	return RHF_RCV_CONTINUE;
 }
 
-static int process_receive_error(struct hfi1_packet *packet)
+static void process_receive_error(struct hfi1_packet *packet)
 {
 	/* KHdrHCRCErr -- KDETH packet with a bad HCRC */
 	if (unlikely(
 		 hfi1_dbg_fault_suppress_err(&packet->rcd->dd->verbs_dev) &&
 		 (rhf_rcv_type_err(packet->rhf) == RHF_RCV_TYPE_ERROR ||
 		  packet->rhf & RHF_DC_ERR)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	hfi1_setup_ib_header(packet);
 	handle_eflags(packet);
@@ -1695,32 +1641,29 @@ static int process_receive_error(struct hfi1_packet *packet)
 	if (unlikely(rhf_err_flags(packet->rhf)))
 		dd_dev_err(packet->rcd->dd,
 			   "Unhandled error packet received. Dropping.\n");
-
-	return RHF_RCV_CONTINUE;
 }
 
-static int kdeth_process_expected(struct hfi1_packet *packet)
+static void kdeth_process_expected(struct hfi1_packet *packet)
 {
 	hfi1_setup_9B_packet(packet);
 	if (unlikely(hfi1_dbg_should_fault_rx(packet)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	if (unlikely(rhf_err_flags(packet->rhf))) {
 		struct hfi1_ctxtdata *rcd = packet->rcd;
 
 		if (hfi1_handle_kdeth_eflags(rcd, rcd->ppd, packet))
-			return RHF_RCV_CONTINUE;
+			return;
 	}
 
 	hfi1_kdeth_expected_rcv(packet);
-	return RHF_RCV_CONTINUE;
 }
 
-static int kdeth_process_eager(struct hfi1_packet *packet)
+static void kdeth_process_eager(struct hfi1_packet *packet)
 {
 	hfi1_setup_9B_packet(packet);
 	if (unlikely(hfi1_dbg_should_fault_rx(packet)))
-		return RHF_RCV_CONTINUE;
+		return;
 
 	trace_hfi1_rcvhdr(packet);
 	if (unlikely(rhf_err_flags(packet->rhf))) {
@@ -1728,37 +1671,41 @@ static int kdeth_process_eager(struct hfi1_packet *packet)
 
 		show_eflags_errs(packet);
 		if (hfi1_handle_kdeth_eflags(rcd, rcd->ppd, packet))
-			return RHF_RCV_CONTINUE;
+			return;
 	}
 
 	hfi1_kdeth_eager_rcv(packet);
-	return RHF_RCV_CONTINUE;
 }
 
-static int process_receive_invalid(struct hfi1_packet *packet)
+static void process_receive_invalid(struct hfi1_packet *packet)
 {
 	dd_dev_err(packet->rcd->dd, "Invalid packet type %d. Dropping\n",
 		   rhf_rcv_type(packet->rhf));
-	return RHF_RCV_CONTINUE;
 }
 
+#define HFI1_RCVHDR_DUMP_MAX	5
+
 void seqfile_dump_rcd(struct seq_file *s, struct hfi1_ctxtdata *rcd)
 {
 	struct hfi1_packet packet;
 	struct ps_mdata mdata;
+	int i;
 
-	seq_printf(s, "Rcd %u: RcvHdr cnt %u entsize %u %s head %llu tail %llu\n",
-		   rcd->ctxt, rcd->rcvhdrq_cnt, rcd->rcvhdrqentsize,
-		   HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL) ?
+	seq_printf(s, "Rcd %u: RcvHdr cnt %u entsize %u %s ctrl 0x%08llx status 0x%08llx, head %llu tail %llu  sw head %u\n",
+		   rcd->ctxt, get_hdrq_cnt(rcd), get_hdrqentsize(rcd),
+		   get_dma_rtail_setting(rcd) ?
 		   "dma_rtail" : "nodma_rtail",
+		   read_kctxt_csr(rcd->dd, rcd->ctxt, RCV_CTXT_CTRL),
+		   read_kctxt_csr(rcd->dd, rcd->ctxt, RCV_CTXT_STATUS),
 		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_HEAD) &
 		   RCV_HDR_HEAD_HEAD_MASK,
-		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL));
+		   read_uctxt_csr(rcd->dd, rcd->ctxt, RCV_HDR_TAIL),
+		   rcd->head);
 
 	init_packet(rcd, &packet);
 	init_ps_mdata(&mdata, &packet);
 
-	while (1) {
+	for (i = 0; i < HFI1_RCVHDR_DUMP_MAX; i++) {
 		__le32 *rhf_addr = (__le32 *)rcd->rcvhdrq + mdata.ps_head +
 					 rcd->rhf_offset;
 		struct ib_header *hdr;
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index 7c5e3fb22413..bef6946861b2 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -505,12 +505,12 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma)
 			ret = -EINVAL;
 			goto done;
 		}
-		if ((flags & VM_WRITE) || !uctxt->rcvhdrtail_kvaddr) {
+		if ((flags & VM_WRITE) || !hfi1_rcvhdrtail_kvaddr(uctxt)) {
 			ret = -EPERM;
 			goto done;
 		}
 		memlen = PAGE_SIZE;
-		memvirt = (void *)uctxt->rcvhdrtail_kvaddr;
+		memvirt = (void *)hfi1_rcvhdrtail_kvaddr(uctxt);
 		flags &= ~VM_MAYWRITE;
 		break;
 	case SUBCTXT_UREGS:
@@ -1090,7 +1090,7 @@ static void user_init(struct hfi1_ctxtdata *uctxt)
 	 * don't have to wait to be sure the DMA update has happened
 	 * (chip resets head/tail to 0 on transition to enable).
 	 */
-	if (uctxt->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(uctxt))
 		clear_rcvhdrtail(uctxt);
 
 	/* Setup J_KEY before enabling the context */
@@ -1154,8 +1154,8 @@ static int get_ctxt_info(struct hfi1_filedata *fd, unsigned long arg, u32 len)
 	cinfo.send_ctxt = uctxt->sc->hw_context;
 
 	cinfo.egrtids = uctxt->egrbufs.alloced;
-	cinfo.rcvhdrq_cnt = uctxt->rcvhdrq_cnt;
-	cinfo.rcvhdrq_entsize = uctxt->rcvhdrqentsize << 2;
+	cinfo.rcvhdrq_cnt = get_hdrq_cnt(uctxt);
+	cinfo.rcvhdrq_entsize = get_hdrqentsize(uctxt) << 2;
 	cinfo.sdma_ring_size = fd->cq->nentries;
 	cinfo.rcvegr_size = uctxt->egrbufs.rcvtid_size;
 
@@ -1543,7 +1543,7 @@ static int manage_rcvq(struct hfi1_ctxtdata *uctxt, u16 subctxt,
 		 * always resets it's tail register back to 0 on a
 		 * transition from disabled to enabled.
 		 */
-		if (uctxt->rcvhdrtail_kvaddr)
+		if (hfi1_rcvhdrtail_kvaddr(uctxt))
 			clear_rcvhdrtail(uctxt);
 		rcvctrl_op = HFI1_RCVCTRL_CTXT_ENB;
 	} else {
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index fc10d65fc3e1..6365e8ffed9d 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -197,7 +197,9 @@ struct exp_tid_set {
 	u32 count;
 };
 
-typedef int (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
+struct hfi1_ctxtdata;
+typedef int (*intr_handler)(struct hfi1_ctxtdata *rcd, int data);
+typedef void (*rhf_rcv_function_ptr)(struct hfi1_packet *packet);
 
 struct tid_queue {
 	struct list_head queue_head;
@@ -226,7 +228,11 @@ struct hfi1_ctxtdata {
 	 * be valid. Worst case is we process an extra interrupt and up to 64
 	 * packets with the wrong interrupt handler.
 	 */
-	int (*do_interrupt)(struct hfi1_ctxtdata *rcd, int threaded);
+	intr_handler do_interrupt;
+	/** fast handler after autoactive */
+	intr_handler fast_handler;
+	/** slow handler */
+	intr_handler slow_handler;
 	/* verbs rx_stats per rcd */
 	struct hfi1_opcode_stats_perctx *opstats;
 	/* clear interrupt mask */
@@ -1153,6 +1159,8 @@ struct hfi1_devdata {
 
 	char *boardname; /* human readable board info */
 
+	u64 ctx0_seq_drop;
+
 	/* reset value */
 	u64 z_int_counter;
 	u64 z_rcv_limit;
@@ -1310,7 +1318,7 @@ struct hfi1_devdata {
 	struct err_info_constraint err_info_xmit_constraint;
 
 	atomic_t drop_packet;
-	u8 do_drop;
+	bool do_drop;
 	u8 err_info_uncorrectable;
 	u8 err_info_fmconfig;
 
@@ -1507,12 +1515,148 @@ void hfi1_make_ud_req_16B(struct rvt_qp *qp,
 #define RCV_PKT_LIMIT   0x1 /* stop, hit limit, start thread */
 #define RCV_PKT_DONE    0x2 /* stop, no more packets detected */
 
+/**
+ * hfi1_rcd_head - add accessor for rcd head
+ * @rcd: the context
+ */
+static inline u32 hfi1_rcd_head(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->head;
+}
+
+/**
+ * hfi1_set_rcd_head - add accessor for rcd head
+ * @rcd: the context
+ * @head: the new head
+ */
+static inline void hfi1_set_rcd_head(struct hfi1_ctxtdata *rcd, u32 head)
+{
+	rcd->head = head;
+}
+
 /* calculate the current RHF address */
 static inline __le32 *get_rhf_addr(struct hfi1_ctxtdata *rcd)
 {
 	return (__le32 *)rcd->rcvhdrq + rcd->head + rcd->rhf_offset;
 }
 
+/* return DMA_RTAIL configuration */
+static inline bool get_dma_rtail_setting(struct hfi1_ctxtdata *rcd)
+{
+	return !!HFI1_CAP_KGET_MASK(rcd->flags, DMA_RTAIL);
+}
+
+/**
+ * hfi1_seq_incr_wrap - wrapping increment for sequence
+ * @seq: the current sequence number
+ *
+ * Returns: the incremented seq
+ */
+static inline u8 hfi1_seq_incr_wrap(u8 seq)
+{
+	if (++seq > RHF_MAX_SEQ)
+		seq = 1;
+	return seq;
+}
+
+/**
+ * hfi1_seq_cnt - return seq_cnt member
+ * @rcd: the receive context
+ *
+ * Return seq_cnt member
+ */
+static inline u8 hfi1_seq_cnt(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->seq_cnt;
+}
+
+/**
+ * hfi1_set_seq_cnt - return seq_cnt member
+ * @rcd: the receive context
+ *
+ * Return seq_cnt member
+ */
+static inline void hfi1_set_seq_cnt(struct hfi1_ctxtdata *rcd, u8 cnt)
+{
+	rcd->seq_cnt = cnt;
+}
+
+/**
+ * last_rcv_seq - is last
+ * @rcd: the receive context
+ * @seq: sequence
+ *
+ * return true if last packet
+ */
+static inline bool last_rcv_seq(struct hfi1_ctxtdata *rcd, u32 seq)
+{
+	return seq != rcd->seq_cnt;
+}
+
+/**
+ * rcd_seq_incr - increment context sequence number
+ * @rcd: the receive context
+ * @seq: the current sequence number
+ *
+ * Returns: true if the this was the last packet
+ */
+static inline bool hfi1_seq_incr(struct hfi1_ctxtdata *rcd, u32 seq)
+{
+	rcd->seq_cnt = hfi1_seq_incr_wrap(rcd->seq_cnt);
+	return last_rcv_seq(rcd, seq);
+}
+
+/**
+ * get_hdrqentsize - return hdrq entry size
+ * @rcd: the receive context
+ */
+static inline u8 get_hdrqentsize(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->rcvhdrqentsize;
+}
+
+/**
+ * get_hdrq_cnt - return hdrq count
+ * @rcd: the receive context
+ */
+static inline u16 get_hdrq_cnt(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->rcvhdrq_cnt;
+}
+
+/**
+ * hfi1_is_slowpath - check if this context is slow path
+ * @rcd: the receive context
+ */
+static inline bool hfi1_is_slowpath(struct hfi1_ctxtdata *rcd)
+{
+	return rcd->do_interrupt == rcd->slow_handler;
+}
+
+/**
+ * hfi1_is_fastpath - check if this context is fast path
+ * @rcd: the receive context
+ */
+static inline bool hfi1_is_fastpath(struct hfi1_ctxtdata *rcd)
+{
+	if (rcd->ctxt == HFI1_CTRL_CTXT)
+		return false;
+
+	return rcd->do_interrupt == rcd->fast_handler;
+}
+
+/**
+ * hfi1_set_fast - change to the fast handler
+ * @rcd: the receive context
+ */
+static inline void hfi1_set_fast(struct hfi1_ctxtdata *rcd)
+{
+	if (unlikely(!rcd))
+		return;
+	if (unlikely(!hfi1_is_fastpath(rcd)))
+		rcd->do_interrupt = rcd->fast_handler;
+}
+
 int hfi1_reset_device(int);
 
 void receive_interrupt_work(struct work_struct *work);
@@ -2015,9 +2159,21 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr,
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty);
 
+/**
+ * hfi1_rcvhdrtail_kvaddr - return tail kvaddr
+ * @rcd - the receive context
+ */
+static inline __le64 *hfi1_rcvhdrtail_kvaddr(const struct hfi1_ctxtdata *rcd)
+{
+	return (__le64 *)rcd->rcvhdrtail_kvaddr;
+}
+
 static inline void clear_rcvhdrtail(const struct hfi1_ctxtdata *rcd)
 {
-	*((u64 *)rcd->rcvhdrtail_kvaddr) = 0ULL;
+	u64 *kv = (u64 *)hfi1_rcvhdrtail_kvaddr(rcd);
+
+	if (kv)
+		*kv = 0ULL;
 }
 
 static inline u32 get_rcvhdrtail(const struct hfi1_ctxtdata *rcd)
@@ -2026,7 +2182,17 @@ static inline u32 get_rcvhdrtail(const struct hfi1_ctxtdata *rcd)
 	 * volatile because it's a DMA target from the chip, routine is
 	 * inlined, and don't want register caching or reordering.
 	 */
-	return (u32)le64_to_cpu(*rcd->rcvhdrtail_kvaddr);
+	return (u32)le64_to_cpu(*hfi1_rcvhdrtail_kvaddr(rcd));
+}
+
+static inline bool hfi1_packet_present(struct hfi1_ctxtdata *rcd)
+{
+	if (likely(!rcd->rcvhdrtail_kvaddr)) {
+		u32 seq = rhf_rcv_seq(rhf_to_cpu(get_rhf_addr(rcd)));
+
+		return !last_rcv_seq(rcd, seq);
+	}
+	return hfi1_rcd_head(rcd) != get_rcvhdrtail(rcd);
 }
 
 /*
@@ -2298,6 +2464,25 @@ static inline bool is_integrated(struct hfi1_devdata *dd)
 	return dd->pcidev->device == PCI_DEVICE_ID_INTEL1;
 }
 
+/**
+ * hfi1_need_drop - detect need for drop
+ * @dd: - the device
+ *
+ * In some cases, the first packet needs to be dropped.
+ *
+ * Return true is the current packet needs to be dropped and false otherwise.
+ */
+static inline bool hfi1_need_drop(struct hfi1_devdata *dd)
+{
+	if (unlikely(dd->do_drop &&
+		     atomic_xchg(&dd->drop_packet, DROP_PACKET_OFF) ==
+		     DROP_PACKET_ON)) {
+		dd->do_drop = false;
+		return true;
+	}
+	return false;
+}
+
 int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 
 #define DD_DEV_ENTRY(dd)       __string(dev, dev_name(&(dd)->pcidev->dev))
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 26b792bb1027..e3acda7a0800 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -78,8 +78,6 @@
  */
 #define HFI1_MIN_USER_CTXT_BUFCNT 7
 
-#define HFI1_MIN_HDRQ_EGRBUF_CNT 2
-#define HFI1_MAX_HDRQ_EGRBUF_CNT 16352
 #define HFI1_MIN_EAGER_BUFFER_SIZE (4 * 1024) /* 4KB */
 #define HFI1_MAX_EAGER_BUFFER_SIZE (256 * 1024) /* 256KB */
 
@@ -122,8 +120,6 @@ unsigned int user_credit_return_threshold = 33;	/* default is 33% */
 module_param(user_credit_return_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(user_credit_return_threshold, "Credit return threshold for user send contexts, return when unreturned credits passes this many blocks (in percent of allocated blocks, 0 is off)");
 
-static inline u64 encode_rcv_header_entry_size(u16 size);
-
 DEFINE_XARRAY_FLAGS(hfi1_dev_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 
 static int hfi1_create_kctxt(struct hfi1_devdata *dd,
@@ -154,7 +150,12 @@ static int hfi1_create_kctxt(struct hfi1_devdata *dd,
 	/* Control context must use DMA_RTAIL */
 	if (rcd->ctxt == HFI1_CTRL_CTXT)
 		rcd->flags |= HFI1_CAP_DMA_RTAIL;
-	rcd->seq_cnt = 1;
+	rcd->fast_handler = get_dma_rtail_setting(rcd) ?
+				handle_receive_interrupt_dma_rtail :
+				handle_receive_interrupt_nodma_rtail;
+	rcd->slow_handler = handle_receive_interrupt;
+
+	hfi1_set_seq_cnt(rcd, 1);
 
 	rcd->sc = sc_alloc(dd, SC_ACK, rcd->rcvhdrqentsize, dd->node);
 	if (!rcd->sc) {
@@ -511,23 +512,6 @@ void hfi1_free_ctxt(struct hfi1_ctxtdata *rcd)
 }
 
 /*
- * Convert a receive header entry size that to the encoding used in the CSR.
- *
- * Return a zero if the given size is invalid.
- */
-static inline u64 encode_rcv_header_entry_size(u16 size)
-{
-	/* there are only 3 valid receive header entry sizes */
-	if (size == 2)
-		return 1;
-	if (size == 16)
-		return 2;
-	else if (size == 32)
-		return 4;
-	return 0; /* invalid */
-}
-
-/*
  * Select the largest ccti value over all SLs to determine the intra-
  * packet gap for the link.
  *
@@ -892,10 +876,10 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit)
 
 	if (is_ax(dd)) {
 		atomic_set(&dd->drop_packet, DROP_PACKET_ON);
-		dd->do_drop = 1;
+		dd->do_drop = true;
 	} else {
 		atomic_set(&dd->drop_packet, DROP_PACKET_OFF);
-		dd->do_drop = 0;
+		dd->do_drop = false;
 	}
 
 	/* make sure the link is not "up" */
@@ -1149,9 +1133,9 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 		dma_free_coherent(&dd->pcidev->dev, rcvhdrq_size(rcd),
 				  rcd->rcvhdrq, rcd->rcvhdrq_dma);
 		rcd->rcvhdrq = NULL;
-		if (rcd->rcvhdrtail_kvaddr) {
+		if (hfi1_rcvhdrtail_kvaddr(rcd)) {
 			dma_free_coherent(&dd->pcidev->dev, PAGE_SIZE,
-					  (void *)rcd->rcvhdrtail_kvaddr,
+					  (void *)hfi1_rcvhdrtail_kvaddr(rcd),
 					  rcd->rcvhdrqtailaddr_dma);
 			rcd->rcvhdrtail_kvaddr = NULL;
 		}
@@ -1611,29 +1595,6 @@ static void postinit_cleanup(struct hfi1_devdata *dd)
 	hfi1_free_devdata(dd);
 }
 
-static int init_validate_rcvhdrcnt(struct hfi1_devdata *dd, uint thecnt)
-{
-	if (thecnt <= HFI1_MIN_HDRQ_EGRBUF_CNT) {
-		dd_dev_err(dd, "Receive header queue count too small\n");
-		return -EINVAL;
-	}
-
-	if (thecnt > HFI1_MAX_HDRQ_EGRBUF_CNT) {
-		dd_dev_err(dd,
-			   "Receive header queue count cannot be greater than %u\n",
-			   HFI1_MAX_HDRQ_EGRBUF_CNT);
-		return -EINVAL;
-	}
-
-	if (thecnt % HDRQ_INCREMENT) {
-		dd_dev_err(dd, "Receive header queue count %d must be divisible by %lu\n",
-			   thecnt, HDRQ_INCREMENT);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int ret = 0, j, pidx, initfail;
@@ -1661,7 +1622,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* Validate some global module parameters */
-	ret = init_validate_rcvhdrcnt(dd, rcvhdrcnt);
+	ret = hfi1_validate_rcvhdrcnt(dd, rcvhdrcnt);
 	if (ret)
 		goto bail;
 
@@ -1842,7 +1803,6 @@ static void shutdown_one(struct pci_dev *pdev)
 int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 {
 	unsigned amt;
-	u64 reg;
 
 	if (!rcd->rcvhdrq) {
 		gfp_t gfp_flags;
@@ -1874,30 +1834,9 @@ int hfi1_create_rcvhdrq(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 				goto bail_free;
 		}
 	}
-	/*
-	 * These values are per-context:
-	 *	RcvHdrCnt
-	 *	RcvHdrEntSize
-	 *	RcvHdrSize
-	 */
-	reg = ((u64)(rcd->rcvhdrq_cnt >> HDRQ_SIZE_SHIFT)
-			& RCV_HDR_CNT_CNT_MASK)
-		<< RCV_HDR_CNT_CNT_SHIFT;
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_CNT, reg);
-	reg = (encode_rcv_header_entry_size(rcd->rcvhdrqentsize)
-			& RCV_HDR_ENT_SIZE_ENT_SIZE_MASK)
-		<< RCV_HDR_ENT_SIZE_ENT_SIZE_SHIFT;
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_ENT_SIZE, reg);
-	reg = ((u64)DEFAULT_RCVHDRSIZE & RCV_HDR_SIZE_HDR_SIZE_MASK)
-		<< RCV_HDR_SIZE_HDR_SIZE_SHIFT;
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_SIZE, reg);
 
-	/*
-	 * Program dummy tail address for every receive context
-	 * before enabling any receive context
-	 */
-	write_kctxt_csr(dd, rcd->ctxt, RCV_HDR_TAIL_ADDR,
-			dd->rcvhdrtail_dummy_dma);
+	set_hdrq_regs(rcd->dd, rcd->ctxt, rcd->rcvhdrqentsize,
+		      rcd->rcvhdrq_cnt);
 
 	return 0;
 
diff --git a/drivers/infiniband/hw/hfi1/msix.c b/drivers/infiniband/hw/hfi1/msix.c
index d920b165d696..db82db497b2c 100644
--- a/drivers/infiniband/hw/hfi1/msix.c
+++ b/drivers/infiniband/hw/hfi1/msix.c
@@ -115,13 +115,11 @@ int msix_initialize(struct hfi1_devdata *dd)
  */
 static int msix_request_irq(struct hfi1_devdata *dd, void *arg,
 			    irq_handler_t handler, irq_handler_t thread,
-			    u32 idx, enum irq_type type)
+			    enum irq_type type, const char *name)
 {
 	unsigned long nr;
 	int irq;
 	int ret;
-	const char *err_info;
-	char name[MAX_NAME_SIZE];
 	struct hfi1_msix_entry *me;
 
 	/* Allocate an MSIx vector */
@@ -135,43 +133,15 @@ static int msix_request_irq(struct hfi1_devdata *dd, void *arg,
 	if (nr == dd->msix_info.max_requested)
 		return -ENOSPC;
 
-	/* Specific verification and determine the name */
-	switch (type) {
-	case IRQ_GENERAL:
-		/* general interrupt must be MSIx vector 0 */
-		if (nr) {
-			spin_lock(&dd->msix_info.msix_lock);
-			__clear_bit(nr, dd->msix_info.in_use_msix);
-			spin_unlock(&dd->msix_info.msix_lock);
-			dd_dev_err(dd, "Invalid index %lu for GENERAL IRQ\n",
-				   nr);
-			return -EINVAL;
-		}
-		snprintf(name, sizeof(name), DRIVER_NAME "_%d", dd->unit);
-		err_info = "general";
-		break;
-	case IRQ_SDMA:
-		snprintf(name, sizeof(name), DRIVER_NAME "_%d sdma%d",
-			 dd->unit, idx);
-		err_info = "sdma";
-		break;
-	case IRQ_RCVCTXT:
-		snprintf(name, sizeof(name), DRIVER_NAME "_%d kctxt%d",
-			 dd->unit, idx);
-		err_info = "receive context";
-		break;
-	case IRQ_OTHER:
-	default:
+	if (type < IRQ_SDMA || type >= IRQ_OTHER)
 		return -EINVAL;
-	}
-	name[sizeof(name) - 1] = 0;
 
 	irq = pci_irq_vector(dd->pcidev, nr);
 	ret = pci_request_irq(dd->pcidev, nr, handler, thread, arg, name);
 	if (ret) {
 		dd_dev_err(dd,
-			   "%s: request for IRQ %d failed, MSIx %d, err %d\n",
-			   err_info, irq, idx, ret);
+			   "%s: request for IRQ %d failed, MSIx %lu, err %d\n",
+			   name, irq, nr, ret);
 		spin_lock(&dd->msix_info.msix_lock);
 		__clear_bit(nr, dd->msix_info.in_use_msix);
 		spin_unlock(&dd->msix_info.msix_lock);
@@ -195,17 +165,13 @@ static int msix_request_irq(struct hfi1_devdata *dd, void *arg,
 	return nr;
 }
 
-/**
- * msix_request_rcd_irq() - Helper function for RCVAVAIL IRQs
- * @rcd: valid rcd context
- *
- */
-int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
+static int msix_request_rcd_irq_common(struct hfi1_ctxtdata *rcd,
+				       irq_handler_t handler,
+				       irq_handler_t thread,
+				       const char *name)
 {
-	int nr;
-
-	nr = msix_request_irq(rcd->dd, rcd, receive_context_interrupt,
-			      receive_context_thread, rcd->ctxt, IRQ_RCVCTXT);
+	int nr = msix_request_irq(rcd->dd, rcd, handler, thread,
+				  IRQ_RCVCTXT, name);
 	if (nr < 0)
 		return nr;
 
@@ -222,6 +188,22 @@ int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
 }
 
 /**
+ * msix_request_rcd_irq() - Helper function for RCVAVAIL IRQs
+ * @rcd: valid rcd context
+ *
+ */
+int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
+{
+	char name[MAX_NAME_SIZE];
+
+	snprintf(name, sizeof(name), DRIVER_NAME "_%d kctxt%d",
+		 rcd->dd->unit, rcd->ctxt);
+
+	return msix_request_rcd_irq_common(rcd, receive_context_interrupt,
+					   receive_context_thread, name);
+}
+
+/**
  * msix_request_smda_ira() - Helper for getting SDMA IRQ resources
  * @sde: valid sdma engine
  *
@@ -229,9 +211,12 @@ int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd)
 int msix_request_sdma_irq(struct sdma_engine *sde)
 {
 	int nr;
+	char name[MAX_NAME_SIZE];
 
+	snprintf(name, sizeof(name), DRIVER_NAME "_%d sdma%d",
+		 sde->dd->unit, sde->this_idx);
 	nr = msix_request_irq(sde->dd, sde, sdma_interrupt, NULL,
-			      sde->this_idx, IRQ_SDMA);
+			      IRQ_SDMA, name);
 	if (nr < 0)
 		return nr;
 	sde->msix_intr = nr;
@@ -241,6 +226,32 @@ int msix_request_sdma_irq(struct sdma_engine *sde)
 }
 
 /**
+ * msix_request_general_irq(void) - Helper for getting general IRQ
+ * resources
+ * @dd: valid device data
+ */
+int msix_request_general_irq(struct hfi1_devdata *dd)
+{
+	int nr;
+	char name[MAX_NAME_SIZE];
+
+	snprintf(name, sizeof(name), DRIVER_NAME "_%d", dd->unit);
+	nr = msix_request_irq(dd, dd, general_interrupt, NULL, IRQ_GENERAL,
+			      name);
+	if (nr < 0)
+		return nr;
+
+	/* general interrupt must be MSIx vector 0 */
+	if (nr) {
+		msix_free_irq(dd, (u8)nr);
+		dd_dev_err(dd, "Invalid index %d for GENERAL IRQ\n", nr);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
  * enable_sdma_src() - Helper to enable SDMA IRQ srcs
  * @dd: valid devdata structure
  * @i: index of SDMA engine
@@ -265,10 +276,9 @@ static void enable_sdma_srcs(struct hfi1_devdata *dd, int i)
 int msix_request_irqs(struct hfi1_devdata *dd)
 {
 	int i;
-	int ret;
+	int ret = msix_request_general_irq(dd);
 
-	ret = msix_request_irq(dd, dd, general_interrupt, NULL, 0, IRQ_GENERAL);
-	if (ret < 0)
+	if (ret)
 		return ret;
 
 	for (i = 0; i < dd->num_sdma; i++) {
diff --git a/drivers/infiniband/hw/hfi1/msix.h b/drivers/infiniband/hw/hfi1/msix.h
index a514881632a4..1a02ab7971c8 100644
--- a/drivers/infiniband/hw/hfi1/msix.h
+++ b/drivers/infiniband/hw/hfi1/msix.h
@@ -54,6 +54,7 @@
 int msix_initialize(struct hfi1_devdata *dd);
 int msix_request_irqs(struct hfi1_devdata *dd);
 void msix_clean_up_interrupts(struct hfi1_devdata *dd);
+int msix_request_general_irq(struct hfi1_devdata *dd);
 int msix_request_rcd_irq(struct hfi1_ctxtdata *rcd);
 int msix_request_sdma_irq(struct sdma_engine *sde);
 void msix_free_irq(struct hfi1_devdata *dd, u8 msix_intr);
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 1a3c647675a7..f1734e5e9ac4 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -2599,7 +2599,7 @@ static noinline int rc_rcv_error(struct ib_other_headers *ohdr, void *data,
 	 * to be sent before sending this one.
 	 */
 	e = NULL;
-	old_req = 1;
+	old_req = true;
 	ibp->rvp.n_rc_dupreq++;
 
 	spin_lock_irqsave(&qp->s_lock, flags);
diff --git a/drivers/infiniband/hw/hfi1/trace_ctxts.h b/drivers/infiniband/hw/hfi1/trace_ctxts.h
index e00c8a7d559c..b5fc5c6cd52f 100644
--- a/drivers/infiniband/hw/hfi1/trace_ctxts.h
+++ b/drivers/infiniband/hw/hfi1/trace_ctxts.h
@@ -80,7 +80,7 @@ TRACE_EVENT(hfi1_uctxtdata,
 			   __entry->credits = uctxt->sc->credits;
 			   __entry->hw_free = le64_to_cpu(*uctxt->sc->hw_free);
 			   __entry->piobase = uctxt->sc->base_addr;
-			   __entry->rcvhdrq_cnt = uctxt->rcvhdrq_cnt;
+			   __entry->rcvhdrq_cnt = get_hdrq_cnt(uctxt);
 			   __entry->rcvhdrq_dma = uctxt->rcvhdrq_dma;
 			   __entry->eager_cnt = uctxt->egrbufs.alloced;
 			   __entry->rcvegr_dma = uctxt->egrbufs.rcvtids[0].dma;
diff --git a/drivers/infiniband/hw/hfi1/trace_rx.h b/drivers/infiniband/hw/hfi1/trace_rx.h
index 3cec960e9674..168079ed122c 100644
--- a/drivers/infiniband/hw/hfi1/trace_rx.h
+++ b/drivers/infiniband/hw/hfi1/trace_rx.h
@@ -106,19 +106,8 @@ TRACE_EVENT(hfi1_receive_interrupt,
 			     ),
 	    TP_fast_assign(DD_DEV_ASSIGN(dd);
 			__entry->ctxt = rcd->ctxt;
-			if (rcd->do_interrupt ==
-			    &handle_receive_interrupt) {
-				__entry->slow_path = 1;
-				__entry->dma_rtail = 0xFF;
-			} else if (rcd->do_interrupt ==
-					&handle_receive_interrupt_dma_rtail){
-				__entry->dma_rtail = 1;
-				__entry->slow_path = 0;
-			} else if (rcd->do_interrupt ==
-					&handle_receive_interrupt_nodma_rtail) {
-				__entry->dma_rtail = 0;
-				__entry->slow_path = 0;
-			}
+			__entry->slow_path = hfi1_is_slowpath(rcd);
+			__entry->dma_rtail = get_dma_rtail_setting(rcd);
 			),
 	    TP_printk("[%s] ctxt %d SlowPath: %d DmaRtail: %d",
 		      __get_str(dev),
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index 469acb961fbd..3b505006c0a6 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -106,7 +106,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 	int ret;
 	unsigned int gup_flags = FOLL_LONGTERM | (writable ? FOLL_WRITE : 0);
 
-	ret = get_user_pages_fast(vaddr, npages, gup_flags, pages);
+	ret = pin_user_pages_fast(vaddr, npages, gup_flags, pages);
 	if (ret < 0)
 		return ret;
 
@@ -118,7 +118,7 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
 void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
 			     size_t npages, bool dirty)
 {
-	put_user_pages_dirty_lock(p, npages, dirty);
+	unpin_user_pages_dirty_lock(p, npages, dirty);
 
 	if (mm) { /* during close after signal, mm can be NULL */
 		atomic64_sub(npages, &mm->pinned_vm);
diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index b49e60e8397d..6b14581b9965 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -78,7 +78,7 @@ static int setup_vnic_ctxt(struct hfi1_devdata *dd, struct hfi1_ctxtdata *uctxt)
 	if (ret)
 		goto done;
 
-	if (uctxt->rcvhdrtail_kvaddr)
+	if (hfi1_rcvhdrtail_kvaddr(uctxt))
 		clear_rcvhdrtail(uctxt);
 
 	rcvctrl_ops = HFI1_RCVCTRL_CTXT_ENB;
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index a2d1e5331bf1..5ffe4c996ed3 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -370,6 +370,8 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr,
 	hr_cq->buf.size = hr_cq->cq_depth * hr_dev->caps.cq_entry_sz;
 	hr_cq->buf.page_shift = PAGE_SHIFT + hr_dev->caps.cqe_buf_pg_sz;
 	spin_lock_init(&hr_cq->lock);
+	INIT_LIST_HEAD(&hr_cq->sq_list);
+	INIT_LIST_HEAD(&hr_cq->rq_list);
 
 	if (udata) {
 		ret = create_user_cq(hr_dev, hr_cq, udata, &resp);
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 5617434cbfb4..a7c4ff975c28 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -45,8 +45,6 @@
 
 #define HNS_ROCE_MAX_MSG_LEN			0x80000000
 
-#define HNS_ROCE_ALIGN_UP(a, b) ((((a) + (b) - 1) / (b)) * (b))
-
 #define HNS_ROCE_IB_MIN_SQ_STRIDE		6
 
 #define HNS_ROCE_BA_SIZE			(32 * 4096)
@@ -107,11 +105,6 @@
 #define NODE_DESC_SIZE				64
 #define DB_REG_OFFSET				0x1000
 
-#define SERV_TYPE_RC				0
-#define SERV_TYPE_RD				1
-#define SERV_TYPE_UC				2
-#define SERV_TYPE_UD				3
-
 /* Configure to HW for PAGE_SIZE larger than 4KB */
 #define PG_SHIFT_OFFSET				(PAGE_SHIFT - 12)
 
@@ -131,6 +124,13 @@
 #define EQ_DEPTH_COEFF				2
 
 enum {
+	SERV_TYPE_RC,
+	SERV_TYPE_UC,
+	SERV_TYPE_RD,
+	SERV_TYPE_UD,
+};
+
+enum {
 	HNS_ROCE_SUPPORT_RQ_RECORD_DB = 1 << 0,
 	HNS_ROCE_SUPPORT_SQ_RECORD_DB = 1 << 1,
 };
@@ -423,7 +423,7 @@ struct hns_roce_mr_table {
 struct hns_roce_wq {
 	u64		*wrid;     /* Work request ID */
 	spinlock_t	lock;
-	int		wqe_cnt;  /* WQE num */
+	u32		wqe_cnt;  /* WQE num */
 	int		max_gs;
 	int		offset;
 	int		wqe_shift;	/* WQE size */
@@ -498,6 +498,10 @@ struct hns_roce_cq {
 	u32				vector;
 	atomic_t			refcount;
 	struct completion		free;
+	struct list_head		sq_list; /* all qps on this send cq */
+	struct list_head		rq_list; /* all qps on this recv cq */
+	int				is_armed; /* cq is armed */
+	struct list_head		node; /* all armed cqs are on a list */
 };
 
 struct hns_roce_idx_que {
@@ -647,7 +651,6 @@ struct hns_roce_qp {
 	u8			sdb_en;
 	u32			doorbell_qpn;
 	u32			sq_signal_bits;
-	u32			sq_next_wqe;
 	struct hns_roce_wq	sq;
 
 	struct ib_umem		*umem;
@@ -682,6 +685,9 @@ struct hns_roce_qp {
 	u32			next_sge;
 
 	struct hns_roce_rinl_buf rq_inl_buf;
+	struct list_head	node;		/* all qps are on a list */
+	struct list_head	rq_node;	/* all recv qps are on a list */
+	struct list_head	sq_node;	/* all send qps are on a list */
 };
 
 struct hns_roce_ib_iboe {
@@ -794,10 +800,8 @@ struct hns_roce_caps {
 	int             reserved_qps;
 	int		num_qpc_timer;
 	int		num_cqc_timer;
-	u32		max_srq_sg;
 	int		num_srqs;
 	u32		max_wqes;
-	u32		max_srqs;
 	u32		max_srq_wrs;
 	u32		max_srq_sges;
 	u32		max_sq_desc_sz;
@@ -811,7 +815,6 @@ struct hns_roce_caps {
 	u32		min_wqes;
 	int		reserved_cqs;
 	int		reserved_srqs;
-	u32		max_srqwqes;
 	int		num_aeq_vectors;
 	int		num_comp_vectors;
 	int		num_other_vectors;
@@ -895,6 +898,12 @@ struct hns_roce_caps {
 	u32		tpq_buf_pg_sz;
 	u32		chunk_sz;	/* chunk size in non multihop mode */
 	u64		flags;
+	u16		default_ceq_max_cnt;
+	u16		default_ceq_period;
+	u16		default_aeq_max_cnt;
+	u16		default_aeq_period;
+	u16		default_aeq_arm_st;
+	u16		default_ceq_arm_st;
 };
 
 struct hns_roce_work {
@@ -911,6 +920,12 @@ struct hns_roce_dfx_hw {
 			      int *buffer);
 };
 
+enum hns_roce_device_state {
+	HNS_ROCE_DEVICE_STATE_INITED,
+	HNS_ROCE_DEVICE_STATE_RST_DOWN,
+	HNS_ROCE_DEVICE_STATE_UNINIT,
+};
+
 struct hns_roce_hw {
 	int (*reset)(struct hns_roce_dev *hr_dev, bool enable);
 	int (*cmq_init)(struct hns_roce_dev *hr_dev);
@@ -993,6 +1008,9 @@ struct hns_roce_dev {
 	bool			dis_db;
 	unsigned long		reset_cnt;
 	struct hns_roce_ib_iboe iboe;
+	enum hns_roce_device_state state;
+	struct list_head	qp_list; /* list of all qps on this dev */
+	spinlock_t		qp_list_lock; /* protect qp_list */
 
 	struct list_head        pgdir_list;
 	struct mutex            pgdir_mutex;
@@ -1133,7 +1151,6 @@ int hns_roce_mtr_find(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr,
 
 int hns_roce_init_pd_table(struct hns_roce_dev *hr_dev);
 int hns_roce_init_mr_table(struct hns_roce_dev *hr_dev);
-int hns_roce_init_eq_table(struct hns_roce_dev *hr_dev);
 int hns_roce_init_cq_table(struct hns_roce_dev *hr_dev);
 int hns_roce_init_qp_table(struct hns_roce_dev *hr_dev);
 int hns_roce_init_srq_table(struct hns_roce_dev *hr_dev);
@@ -1257,6 +1274,7 @@ void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type);
 void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type);
 void hns_roce_srq_event(struct hns_roce_dev *hr_dev, u32 srqn, int event_type);
 int hns_get_gid_index(struct hns_roce_dev *hr_dev, u8 port, int gid_index);
+void hns_roce_handle_device_err(struct hns_roce_dev *hr_dev);
 int hns_roce_init(struct hns_roce_dev *hr_dev);
 void hns_roce_exit(struct hns_roce_dev *hr_dev);
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 2a2b2112f886..c6e66586e533 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -74,8 +74,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 	unsigned long flags = 0;
 	void *wqe = NULL;
 	__le32 doorbell[2];
+	u32 wqe_idx = 0;
 	int nreq = 0;
-	u32 ind = 0;
 	int ret = 0;
 	u8 *smac;
 	int loopback;
@@ -88,7 +88,7 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 	}
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
-	ind = qp->sq_next_wqe;
+
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) {
 			ret = -ENOMEM;
@@ -96,6 +96,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > qp->sq.max_gs)) {
 			dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, qp->sq.max_gs);
@@ -104,9 +106,8 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1));
-		qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
-								      wr->wr_id;
+		wqe = get_send_wqe(qp, wqe_idx);
+		qp->sq.wrid[wqe_idx] = wr->wr_id;
 
 		/* Corresponding to the RC and RD type wqe process separately */
 		if (ibqp->qp_type == IB_QPT_GSI) {
@@ -210,7 +211,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 				       cpu_to_le32((wr->sg_list[1].addr) >> 32);
 			ud_sq_wqe->l_key1 =
 				       cpu_to_le32(wr->sg_list[1].lkey);
-			ind++;
 		} else if (ibqp->qp_type == IB_QPT_RC) {
 			u32 tmp_len = 0;
 
@@ -308,7 +308,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 				ctrl->flag |= cpu_to_le32(wr->num_sge <<
 					      HNS_ROCE_WQE_SGE_NUM_BIT);
 			}
-			ind++;
 		}
 	}
 
@@ -336,7 +335,6 @@ out:
 		doorbell[1] = sq_db.u32_8;
 
 		hns_roce_write64_k(doorbell, qp->sq.db_reg_l);
-		qp->sq_next_wqe = ind;
 	}
 
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
@@ -348,12 +346,6 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 				 const struct ib_recv_wr *wr,
 				 const struct ib_recv_wr **bad_wr)
 {
-	int ret = 0;
-	int nreq = 0;
-	int ind = 0;
-	int i = 0;
-	u32 reg_val;
-	unsigned long flags = 0;
 	struct hns_roce_rq_wqe_ctrl *ctrl = NULL;
 	struct hns_roce_wqe_data_seg *scat = NULL;
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
@@ -361,9 +353,14 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 	struct device *dev = &hr_dev->pdev->dev;
 	struct hns_roce_rq_db rq_db;
 	__le32 doorbell[2] = {0};
+	unsigned long flags = 0;
+	unsigned int wqe_idx;
+	int ret = 0;
+	int nreq = 0;
+	int i = 0;
+	u32 reg_val;
 
 	spin_lock_irqsave(&hr_qp->rq.lock, flags);
-	ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1);
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (hns_roce_wq_overflow(&hr_qp->rq, nreq,
@@ -373,6 +370,8 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) {
 			dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, hr_qp->rq.max_gs);
@@ -381,7 +380,7 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		ctrl = get_recv_wqe(hr_qp, ind);
+		ctrl = get_recv_wqe(hr_qp, wqe_idx);
 
 		roce_set_field(ctrl->rwqe_byte_12,
 			       RQ_WQE_CTRL_RWQE_BYTE_12_RWQE_SGE_NUM_M,
@@ -393,9 +392,7 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 		for (i = 0; i < wr->num_sge; i++)
 			set_data_seg(scat + i, wr->sg_list + i);
 
-		hr_qp->rq.wrid[ind] = wr->wr_id;
-
-		ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1);
+		hr_qp->rq.wrid[wqe_idx] = wr->wr_id;
 	}
 
 out:
@@ -2701,7 +2698,6 @@ static int hns_roce_v1_m_sqp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 		hr_qp->rq.tail = 0;
 		hr_qp->sq.head = 0;
 		hr_qp->sq.tail = 0;
-		hr_qp->sq_next_wqe = 0;
 	}
 
 	kfree(context);
@@ -3315,7 +3311,6 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 		hr_qp->rq.tail = 0;
 		hr_qp->sq.head = 0;
 		hr_qp->sq.tail = 0;
-		hr_qp->sq_next_wqe = 0;
 	}
 out:
 	kfree(context);
@@ -3614,14 +3609,18 @@ int hns_roce_v1_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 	if (ret)
 		return ret;
 
-	send_cq = to_hr_cq(hr_qp->ibqp.send_cq);
-	recv_cq = to_hr_cq(hr_qp->ibqp.recv_cq);
+	send_cq = hr_qp->ibqp.send_cq ? to_hr_cq(hr_qp->ibqp.send_cq) : NULL;
+	recv_cq = hr_qp->ibqp.recv_cq ? to_hr_cq(hr_qp->ibqp.recv_cq) : NULL;
 
 	hns_roce_lock_cqs(send_cq, recv_cq);
 	if (!udata) {
-		__hns_roce_v1_cq_clean(recv_cq, hr_qp->qpn, hr_qp->ibqp.srq ?
-				       to_hr_srq(hr_qp->ibqp.srq) : NULL);
-		if (send_cq != recv_cq)
+		if (recv_cq)
+			__hns_roce_v1_cq_clean(recv_cq, hr_qp->qpn,
+					       (hr_qp->ibqp.srq ?
+						to_hr_srq(hr_qp->ibqp.srq) :
+						NULL));
+
+		if (send_cq && send_cq != recv_cq)
 			__hns_roce_v1_cq_clean(send_cq, hr_qp->qpn, NULL);
 	}
 	hns_roce_unlock_cqs(send_cq, recv_cq);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index cb8071a3e0d5..12c4cd8e9378 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -63,20 +63,15 @@ static void set_frmr_seg(struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
 	struct hns_roce_mr *mr = to_hr_mr(wr->mr);
 
 	/* use ib_access_flags */
-	roce_set_bit(rc_sq_wqe->byte_4,
-		     V2_RC_FRMR_WQE_BYTE_4_BIND_EN_S,
+	roce_set_bit(rc_sq_wqe->byte_4, V2_RC_FRMR_WQE_BYTE_4_BIND_EN_S,
 		     wr->access & IB_ACCESS_MW_BIND ? 1 : 0);
-	roce_set_bit(rc_sq_wqe->byte_4,
-		     V2_RC_FRMR_WQE_BYTE_4_ATOMIC_S,
+	roce_set_bit(rc_sq_wqe->byte_4, V2_RC_FRMR_WQE_BYTE_4_ATOMIC_S,
 		     wr->access & IB_ACCESS_REMOTE_ATOMIC ? 1 : 0);
-	roce_set_bit(rc_sq_wqe->byte_4,
-		     V2_RC_FRMR_WQE_BYTE_4_RR_S,
+	roce_set_bit(rc_sq_wqe->byte_4, V2_RC_FRMR_WQE_BYTE_4_RR_S,
 		     wr->access & IB_ACCESS_REMOTE_READ ? 1 : 0);
-	roce_set_bit(rc_sq_wqe->byte_4,
-		     V2_RC_FRMR_WQE_BYTE_4_RW_S,
+	roce_set_bit(rc_sq_wqe->byte_4, V2_RC_FRMR_WQE_BYTE_4_RW_S,
 		     wr->access & IB_ACCESS_REMOTE_WRITE ? 1 : 0);
-	roce_set_bit(rc_sq_wqe->byte_4,
-		     V2_RC_FRMR_WQE_BYTE_4_LW_S,
+	roce_set_bit(rc_sq_wqe->byte_4, V2_RC_FRMR_WQE_BYTE_4_LW_S,
 		     wr->access & IB_ACCESS_LOCAL_WRITE ? 1 : 0);
 
 	/* Data structure reuse may lead to confusion */
@@ -110,7 +105,7 @@ static void set_atomic_seg(struct hns_roce_wqe_atomic_seg *aseg,
 }
 
 static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
-			   unsigned int *sge_ind)
+			   unsigned int *sge_ind, int valid_num_sge)
 {
 	struct hns_roce_v2_wqe_data_seg *dseg;
 	struct ib_sge *sg;
@@ -123,7 +118,7 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
 
 	if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC)
 		num_in_wqe = HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE;
-	extend_sge_num = wr->num_sge - num_in_wqe;
+	extend_sge_num = valid_num_sge - num_in_wqe;
 	sg = wr->sg_list + num_in_wqe;
 	shift = qp->hr_buf.page_shift;
 
@@ -159,14 +154,16 @@ static void set_extend_sge(struct hns_roce_qp *qp, const struct ib_send_wr *wr,
 static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 			     struct hns_roce_v2_rc_send_wqe *rc_sq_wqe,
 			     void *wqe, unsigned int *sge_ind,
+			     int valid_num_sge,
 			     const struct ib_send_wr **bad_wr)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_v2_wqe_data_seg *dseg = wqe;
 	struct hns_roce_qp *qp = to_hr_qp(ibqp);
+	int j = 0;
 	int i;
 
-	if (wr->send_flags & IB_SEND_INLINE && wr->num_sge) {
+	if (wr->send_flags & IB_SEND_INLINE && valid_num_sge) {
 		if (le32_to_cpu(rc_sq_wqe->msg_len) >
 		    hr_dev->caps.max_sq_inline) {
 			*bad_wr = wr;
@@ -190,7 +187,7 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 		roce_set_bit(rc_sq_wqe->byte_4, V2_RC_SEND_WQE_BYTE_4_INLINE_S,
 			     1);
 	} else {
-		if (wr->num_sge <= HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE) {
+		if (valid_num_sge <= HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE) {
 			for (i = 0; i < wr->num_sge; i++) {
 				if (likely(wr->sg_list[i].length)) {
 					set_data_seg_v2(dseg, wr->sg_list + i);
@@ -203,19 +200,21 @@ static int set_rwqe_data_seg(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 				     V2_RC_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S,
 				     (*sge_ind) & (qp->sge.sge_cnt - 1));
 
-			for (i = 0; i < HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; i++) {
+			for (i = 0; i < wr->num_sge &&
+			     j < HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE; i++) {
 				if (likely(wr->sg_list[i].length)) {
 					set_data_seg_v2(dseg, wr->sg_list + i);
 					dseg++;
+					j++;
 				}
 			}
 
-			set_extend_sge(qp, wr, sge_ind);
+			set_extend_sge(qp, wr, sge_ind, valid_num_sge);
 		}
 
 		roce_set_field(rc_sq_wqe->byte_16,
 			       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
-			       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, wr->num_sge);
+			       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S, valid_num_sge);
 	}
 
 	return 0;
@@ -226,6 +225,30 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 				 int attr_mask, enum ib_qp_state cur_state,
 				 enum ib_qp_state new_state);
 
+static int check_send_valid(struct hns_roce_dev *hr_dev,
+			    struct hns_roce_qp *hr_qp)
+{
+	struct ib_qp *ibqp = &hr_qp->ibqp;
+	struct device *dev = hr_dev->dev;
+
+	if (unlikely(ibqp->qp_type != IB_QPT_RC &&
+		     ibqp->qp_type != IB_QPT_GSI &&
+		     ibqp->qp_type != IB_QPT_UD)) {
+		dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type);
+		return -EOPNOTSUPP;
+	} else if (unlikely(hr_qp->state == IB_QPS_RESET ||
+		   hr_qp->state == IB_QPS_INIT ||
+		   hr_qp->state == IB_QPS_RTR)) {
+		dev_err(dev, "Post WQE fail, QP state %d!\n", hr_qp->state);
+		return -EINVAL;
+	} else if (unlikely(hr_dev->state >= HNS_ROCE_DEVICE_STATE_RST_DOWN)) {
+		dev_err(dev, "Post WQE fail, dev state %d!\n", hr_dev->state);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 				 const struct ib_send_wr *wr,
 				 const struct ib_send_wr **bad_wr)
@@ -239,38 +262,31 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 	struct device *dev = hr_dev->dev;
 	struct hns_roce_v2_db sq_db;
 	struct ib_qp_attr attr;
-	unsigned int sge_ind;
 	unsigned int owner_bit;
+	unsigned int sge_idx;
+	unsigned int wqe_idx;
 	unsigned long flags;
-	unsigned int ind;
+	int valid_num_sge;
 	void *wqe = NULL;
 	bool loopback;
 	int attr_mask;
 	u32 tmp_len;
-	int ret = 0;
 	u32 hr_op;
 	u8 *smac;
 	int nreq;
+	int ret;
 	int i;
 
-	if (unlikely(ibqp->qp_type != IB_QPT_RC &&
-		     ibqp->qp_type != IB_QPT_GSI &&
-		     ibqp->qp_type != IB_QPT_UD)) {
-		dev_err(dev, "Not supported QP(0x%x)type!\n", ibqp->qp_type);
-		*bad_wr = wr;
-		return -EOPNOTSUPP;
-	}
+	spin_lock_irqsave(&qp->sq.lock, flags);
 
-	if (unlikely(qp->state == IB_QPS_RESET || qp->state == IB_QPS_INIT ||
-		     qp->state == IB_QPS_RTR)) {
-		dev_err(dev, "Post WQE fail, QP state %d err!\n", qp->state);
+	ret = check_send_valid(hr_dev, qp);
+	if (ret) {
 		*bad_wr = wr;
-		return -EINVAL;
+		nreq = 0;
+		goto out;
 	}
 
-	spin_lock_irqsave(&qp->sq.lock, flags);
-	ind = qp->sq_next_wqe;
-	sge_ind = qp->next_sge;
+	sge_idx = qp->next_sge;
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
 		if (hns_roce_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)) {
@@ -279,6 +295,8 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > qp->sq.max_gs)) {
 			dev_err(dev, "num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, qp->sq.max_gs);
@@ -287,14 +305,20 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1));
-		qp->sq.wrid[(qp->sq.head + nreq) & (qp->sq.wqe_cnt - 1)] =
-								      wr->wr_id;
-
+		wqe = get_send_wqe(qp, wqe_idx);
+		qp->sq.wrid[wqe_idx] = wr->wr_id;
 		owner_bit =
 		       ~(((qp->sq.head + nreq) >> ilog2(qp->sq.wqe_cnt)) & 0x1);
+		valid_num_sge = 0;
 		tmp_len = 0;
 
+		for (i = 0; i < wr->num_sge; i++) {
+			if (likely(wr->sg_list[i].length)) {
+				tmp_len += wr->sg_list[i].length;
+				valid_num_sge++;
+			}
+		}
+
 		/* Corresponding to the QP type, wqe process separately */
 		if (ibqp->qp_type == IB_QPT_GSI) {
 			ud_sq_wqe = wqe;
@@ -330,9 +354,6 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 				       V2_UD_SEND_WQE_BYTE_4_OPCODE_S,
 				       HNS_ROCE_V2_WQE_OP_SEND);
 
-			for (i = 0; i < wr->num_sge; i++)
-				tmp_len += wr->sg_list[i].length;
-
 			ud_sq_wqe->msg_len =
 			 cpu_to_le32(le32_to_cpu(ud_sq_wqe->msg_len) + tmp_len);
 
@@ -368,12 +389,12 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			roce_set_field(ud_sq_wqe->byte_16,
 				       V2_UD_SEND_WQE_BYTE_16_SGE_NUM_M,
 				       V2_UD_SEND_WQE_BYTE_16_SGE_NUM_S,
-				       wr->num_sge);
+				       valid_num_sge);
 
 			roce_set_field(ud_sq_wqe->byte_20,
 				     V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_M,
 				     V2_UD_SEND_WQE_BYTE_20_MSG_START_SGE_IDX_S,
-				     sge_ind & (qp->sge.sge_cnt - 1));
+				     sge_idx & (qp->sge.sge_cnt - 1));
 
 			roce_set_field(ud_sq_wqe->byte_24,
 				       V2_UD_SEND_WQE_BYTE_24_UDPSPN_M,
@@ -423,13 +444,10 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 			memcpy(&ud_sq_wqe->dgid[0], &ah->av.dgid[0],
 			       GID_LEN_V2);
 
-			set_extend_sge(qp, wr, &sge_ind);
-			ind++;
+			set_extend_sge(qp, wr, &sge_idx, valid_num_sge);
 		} else if (ibqp->qp_type == IB_QPT_RC) {
 			rc_sq_wqe = wqe;
 			memset(rc_sq_wqe, 0, sizeof(*rc_sq_wqe));
-			for (i = 0; i < wr->num_sge; i++)
-				tmp_len += wr->sg_list[i].length;
 
 			rc_sq_wqe->msg_len =
 			 cpu_to_le32(le32_to_cpu(rc_sq_wqe->msg_len) + tmp_len);
@@ -550,15 +568,14 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 				roce_set_field(rc_sq_wqe->byte_16,
 					       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_M,
 					       V2_RC_SEND_WQE_BYTE_16_SGE_NUM_S,
-					       wr->num_sge);
+					       valid_num_sge);
 			} else if (wr->opcode != IB_WR_REG_MR) {
 				ret = set_rwqe_data_seg(ibqp, wr, rc_sq_wqe,
-							wqe, &sge_ind, bad_wr);
+							wqe, &sge_idx,
+							valid_num_sge, bad_wr);
 				if (ret)
 					goto out;
 			}
-
-			ind++;
 		} else {
 			dev_err(dev, "Illegal qp_type(0x%x)\n", ibqp->qp_type);
 			spin_unlock_irqrestore(&qp->sq.lock, flags);
@@ -588,8 +605,7 @@ out:
 
 		hns_roce_write64(hr_dev, (__le32 *)&sq_db, qp->sq.db_reg_l);
 
-		qp->sq_next_wqe = ind;
-		qp->next_sge = sge_ind;
+		qp->next_sge = sge_idx;
 
 		if (qp->state == IB_QPS_ERR) {
 			attr_mask = IB_QP_STATE;
@@ -610,6 +626,17 @@ out:
 	return ret;
 }
 
+static int check_recv_valid(struct hns_roce_dev *hr_dev,
+			    struct hns_roce_qp *hr_qp)
+{
+	if (unlikely(hr_dev->state >= HNS_ROCE_DEVICE_STATE_RST_DOWN))
+		return -EIO;
+	else if (hr_qp->state == IB_QPS_RESET)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 				 const struct ib_recv_wr *wr,
 				 const struct ib_recv_wr **bad_wr)
@@ -623,18 +650,18 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 	unsigned long flags;
 	void *wqe = NULL;
 	int attr_mask;
-	int ret = 0;
+	u32 wqe_idx;
 	int nreq;
-	int ind;
+	int ret;
 	int i;
 
 	spin_lock_irqsave(&hr_qp->rq.lock, flags);
-	ind = hr_qp->rq.head & (hr_qp->rq.wqe_cnt - 1);
 
-	if (hr_qp->state == IB_QPS_RESET) {
-		spin_unlock_irqrestore(&hr_qp->rq.lock, flags);
+	ret = check_recv_valid(hr_dev, hr_qp);
+	if (ret) {
 		*bad_wr = wr;
-		return -EINVAL;
+		nreq = 0;
+		goto out;
 	}
 
 	for (nreq = 0; wr; ++nreq, wr = wr->next) {
@@ -645,6 +672,8 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
+		wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1);
+
 		if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) {
 			dev_err(dev, "rq:num_sge=%d > qp->sq.max_gs=%d\n",
 				wr->num_sge, hr_qp->rq.max_gs);
@@ -653,7 +682,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 			goto out;
 		}
 
-		wqe = get_recv_wqe(hr_qp, ind);
+		wqe = get_recv_wqe(hr_qp, wqe_idx);
 		dseg = (struct hns_roce_v2_wqe_data_seg *)wqe;
 		for (i = 0; i < wr->num_sge; i++) {
 			if (!wr->sg_list[i].length)
@@ -669,8 +698,8 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 
 		/* rq support inline data */
 		if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_RQ_INLINE) {
-			sge_list = hr_qp->rq_inl_buf.wqe_list[ind].sg_list;
-			hr_qp->rq_inl_buf.wqe_list[ind].sge_cnt =
+			sge_list = hr_qp->rq_inl_buf.wqe_list[wqe_idx].sg_list;
+			hr_qp->rq_inl_buf.wqe_list[wqe_idx].sge_cnt =
 							       (u32)wr->num_sge;
 			for (i = 0; i < wr->num_sge; i++) {
 				sge_list[i].addr =
@@ -679,9 +708,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 			}
 		}
 
-		hr_qp->rq.wrid[ind] = wr->wr_id;
-
-		ind = (ind + 1) & (hr_qp->rq.wqe_cnt - 1);
+		hr_qp->rq.wrid[wqe_idx] = wr->wr_id;
 	}
 
 out:
@@ -1254,7 +1281,6 @@ static void hns_roce_function_clear(struct hns_roce_dev *hr_dev)
 	}
 
 out:
-	dev_err(hr_dev->dev, "Func clear fail.\n");
 	hns_roce_func_clr_rst_prc(hr_dev, ret, fclr_write_fail_flag);
 }
 
@@ -1378,8 +1404,7 @@ static int hns_roce_query_pf_timer_resource(struct hns_roce_dev *hr_dev)
 	return 0;
 }
 
-static int hns_roce_set_vf_switch_param(struct hns_roce_dev *hr_dev,
-						  int vf_id)
+static int hns_roce_set_vf_switch_param(struct hns_roce_dev *hr_dev, int vf_id)
 {
 	struct hns_roce_cmq_desc desc;
 	struct hns_roce_vf_switch *swt;
@@ -1388,13 +1413,12 @@ static int hns_roce_set_vf_switch_param(struct hns_roce_dev *hr_dev,
 	swt = (struct hns_roce_vf_switch *)desc.data;
 	hns_roce_cmq_setup_basic_desc(&desc, HNS_SWITCH_PARAMETER_CFG, true);
 	swt->rocee_sel |= cpu_to_le32(HNS_ICL_SWITCH_CMD_ROCEE_SEL);
-	roce_set_field(swt->fun_id,
-			VF_SWITCH_DATA_FUN_ID_VF_ID_M,
-			VF_SWITCH_DATA_FUN_ID_VF_ID_S,
-			vf_id);
+	roce_set_field(swt->fun_id, VF_SWITCH_DATA_FUN_ID_VF_ID_M,
+		       VF_SWITCH_DATA_FUN_ID_VF_ID_S, vf_id);
 	ret = hns_roce_cmq_send(hr_dev, &desc, 1);
 	if (ret)
 		return ret;
+
 	desc.flag =
 		cpu_to_le16(HNS_ROCE_CMD_FLAG_NO_INTR | HNS_ROCE_CMD_FLAG_IN);
 	desc.flag &= cpu_to_le16(~HNS_ROCE_CMD_FLAG_WR);
@@ -1574,69 +1598,9 @@ static int hns_roce_v2_set_bt(struct hns_roce_dev *hr_dev)
 	return hns_roce_cmq_send(hr_dev, &desc, 1);
 }
 
-static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
+static void set_default_caps(struct hns_roce_dev *hr_dev)
 {
 	struct hns_roce_caps *caps = &hr_dev->caps;
-	int ret;
-
-	ret = hns_roce_cmq_query_hw_info(hr_dev);
-	if (ret) {
-		dev_err(hr_dev->dev, "Query hardware version fail, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	ret = hns_roce_query_fw_ver(hr_dev);
-	if (ret) {
-		dev_err(hr_dev->dev, "Query firmware version fail, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	ret = hns_roce_config_global_param(hr_dev);
-	if (ret) {
-		dev_err(hr_dev->dev, "Configure global param fail, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	/* Get pf resource owned by every pf */
-	ret = hns_roce_query_pf_resource(hr_dev);
-	if (ret) {
-		dev_err(hr_dev->dev, "Query pf resource fail, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	if (hr_dev->pci_dev->revision == 0x21) {
-		ret = hns_roce_query_pf_timer_resource(hr_dev);
-		if (ret) {
-			dev_err(hr_dev->dev,
-				"Query pf timer resource fail, ret = %d.\n",
-				ret);
-			return ret;
-		}
-	}
-
-	ret = hns_roce_alloc_vf_resource(hr_dev);
-	if (ret) {
-		dev_err(hr_dev->dev, "Allocate vf resource fail, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	if (hr_dev->pci_dev->revision == 0x21) {
-		ret = hns_roce_set_vf_switch_param(hr_dev, 0);
-		if (ret) {
-			dev_err(hr_dev->dev,
-				"Set function switch param fail, ret = %d.\n",
-				ret);
-			return ret;
-		}
-	}
-
-	hr_dev->vendor_part_id = hr_dev->pci_dev->device;
-	hr_dev->sys_image_guid = be64_to_cpu(hr_dev->ib_dev.node_guid);
 
 	caps->num_qps		= HNS_ROCE_V2_MAX_QP_NUM;
 	caps->max_wqes		= HNS_ROCE_V2_MAX_WQE_NUM;
@@ -1644,17 +1608,15 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 	caps->num_srqs		= HNS_ROCE_V2_MAX_SRQ_NUM;
 	caps->min_cqes		= HNS_ROCE_MIN_CQE_NUM;
 	caps->max_cqes		= HNS_ROCE_V2_MAX_CQE_NUM;
-	caps->max_srqwqes	= HNS_ROCE_V2_MAX_SRQWQE_NUM;
 	caps->max_sq_sg		= HNS_ROCE_V2_MAX_SQ_SGE_NUM;
 	caps->max_extend_sg	= HNS_ROCE_V2_MAX_EXTEND_SGE_NUM;
 	caps->max_rq_sg		= HNS_ROCE_V2_MAX_RQ_SGE_NUM;
 	caps->max_sq_inline	= HNS_ROCE_V2_MAX_SQ_INLINE;
-	caps->max_srq_sg	= HNS_ROCE_V2_MAX_SRQ_SGE_NUM;
 	caps->num_uars		= HNS_ROCE_V2_UAR_NUM;
 	caps->phy_num_uars	= HNS_ROCE_V2_PHY_UAR_NUM;
 	caps->num_aeq_vectors	= HNS_ROCE_V2_AEQE_VEC_NUM;
 	caps->num_comp_vectors	= HNS_ROCE_V2_COMP_VEC_NUM;
-	caps->num_other_vectors	= HNS_ROCE_V2_ABNORMAL_VEC_NUM;
+	caps->num_other_vectors = HNS_ROCE_V2_ABNORMAL_VEC_NUM;
 	caps->num_mtpts		= HNS_ROCE_V2_MAX_MTPT_NUM;
 	caps->num_mtt_segs	= HNS_ROCE_V2_MAX_MTT_SEGS;
 	caps->num_cqe_segs	= HNS_ROCE_V2_MAX_CQE_SEGS;
@@ -1668,12 +1630,12 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 	caps->max_srq_desc_sz	= HNS_ROCE_V2_MAX_SRQ_DESC_SZ;
 	caps->qpc_entry_sz	= HNS_ROCE_V2_QPC_ENTRY_SZ;
 	caps->irrl_entry_sz	= HNS_ROCE_V2_IRRL_ENTRY_SZ;
-	caps->trrl_entry_sz	= HNS_ROCE_V2_TRRL_ENTRY_SZ;
+	caps->trrl_entry_sz	= HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ;
 	caps->cqc_entry_sz	= HNS_ROCE_V2_CQC_ENTRY_SZ;
 	caps->srqc_entry_sz	= HNS_ROCE_V2_SRQC_ENTRY_SZ;
 	caps->mtpt_entry_sz	= HNS_ROCE_V2_MTPT_ENTRY_SZ;
 	caps->mtt_entry_sz	= HNS_ROCE_V2_MTT_ENTRY_SZ;
-	caps->idx_entry_sz	= 4;
+	caps->idx_entry_sz	= HNS_ROCE_V2_IDX_ENTRY_SZ;
 	caps->cq_entry_sz	= HNS_ROCE_V2_CQE_ENTRY_SIZE;
 	caps->page_size_cap	= HNS_ROCE_V2_PAGE_SIZE_SUPPORTED;
 	caps->reserved_lkey	= 0;
@@ -1696,16 +1658,13 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 	caps->mpt_ba_pg_sz	= 0;
 	caps->mpt_buf_pg_sz	= 0;
 	caps->mpt_hop_num	= HNS_ROCE_CONTEXT_HOP_NUM;
-	caps->pbl_ba_pg_sz	= 2;
-	caps->pbl_buf_pg_sz	= 0;
-	caps->pbl_hop_num	= HNS_ROCE_PBL_HOP_NUM;
 	caps->mtt_ba_pg_sz	= 0;
 	caps->mtt_buf_pg_sz	= 0;
 	caps->mtt_hop_num	= HNS_ROCE_MTT_HOP_NUM;
-	caps->wqe_sq_hop_num	= 2;
-	caps->wqe_sge_hop_num	= 1;
-	caps->wqe_rq_hop_num	= 2;
-	caps->cqe_ba_pg_sz	= 6;
+	caps->wqe_sq_hop_num	= HNS_ROCE_SQWQE_HOP_NUM;
+	caps->wqe_sge_hop_num	= HNS_ROCE_EXT_SGE_HOP_NUM;
+	caps->wqe_rq_hop_num	= HNS_ROCE_RQWQE_HOP_NUM;
+	caps->cqe_ba_pg_sz	= HNS_ROCE_BA_PG_SZ_SUPPORTED_256K;
 	caps->cqe_buf_pg_sz	= 0;
 	caps->cqe_hop_num	= HNS_ROCE_CQE_HOP_NUM;
 	caps->srqwqe_ba_pg_sz	= 0;
@@ -1714,10 +1673,6 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 	caps->idx_ba_pg_sz	= 0;
 	caps->idx_buf_pg_sz	= 0;
 	caps->idx_hop_num	= HNS_ROCE_IDX_HOP_NUM;
-	caps->eqe_ba_pg_sz	= 0;
-	caps->eqe_buf_pg_sz	= 0;
-	caps->eqe_hop_num	= HNS_ROCE_EQE_HOP_NUM;
-	caps->tsq_buf_pg_sz	= 0;
 	caps->chunk_sz		= HNS_ROCE_V2_TABLE_CHUNK_SIZE;
 
 	caps->flags		= HNS_ROCE_CAP_FLAG_REREG_MR |
@@ -1726,24 +1681,19 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 				  HNS_ROCE_CAP_FLAG_RECORD_DB |
 				  HNS_ROCE_CAP_FLAG_SQ_RECORD_DB;
 
-	if (hr_dev->pci_dev->revision == 0x21)
-		caps->flags |= HNS_ROCE_CAP_FLAG_MW |
-			       HNS_ROCE_CAP_FLAG_FRMR;
-
 	caps->pkey_table_len[0] = 1;
-	caps->gid_table_len[0] = HNS_ROCE_V2_GID_INDEX_NUM;
+	caps->gid_table_len[0]	= HNS_ROCE_V2_GID_INDEX_NUM;
 	caps->ceqe_depth	= HNS_ROCE_V2_COMP_EQE_NUM;
 	caps->aeqe_depth	= HNS_ROCE_V2_ASYNC_EQE_NUM;
 	caps->local_ca_ack_delay = 0;
 	caps->max_mtu = IB_MTU_4096;
 
-	caps->max_srqs		= HNS_ROCE_V2_MAX_SRQ;
 	caps->max_srq_wrs	= HNS_ROCE_V2_MAX_SRQ_WR;
 	caps->max_srq_sges	= HNS_ROCE_V2_MAX_SRQ_SGE;
 
-	if (hr_dev->pci_dev->revision == 0x21) {
-		caps->flags |= HNS_ROCE_CAP_FLAG_ATOMIC |
-			       HNS_ROCE_CAP_FLAG_SRQ |
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08_B) {
+		caps->flags |= HNS_ROCE_CAP_FLAG_ATOMIC | HNS_ROCE_CAP_FLAG_MW |
+			       HNS_ROCE_CAP_FLAG_SRQ | HNS_ROCE_CAP_FLAG_FRMR |
 			       HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL;
 
 		caps->num_qpc_timer	  = HNS_ROCE_V2_MAX_QPC_TIMER_NUM;
@@ -1757,12 +1707,345 @@ static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
 		caps->cqc_timer_buf_pg_sz = 0;
 		caps->cqc_timer_hop_num   = HNS_ROCE_HOP_NUM_0;
 
-		caps->sccc_entry_sz	= HNS_ROCE_V2_SCCC_ENTRY_SZ;
-		caps->sccc_ba_pg_sz	= 0;
-		caps->sccc_buf_pg_sz    = 0;
-		caps->sccc_hop_num	= HNS_ROCE_SCCC_HOP_NUM;
+		caps->sccc_entry_sz	  = HNS_ROCE_V2_SCCC_ENTRY_SZ;
+		caps->sccc_ba_pg_sz	  = 0;
+		caps->sccc_buf_pg_sz	  = 0;
+		caps->sccc_hop_num	  = HNS_ROCE_SCCC_HOP_NUM;
+	}
+}
+
+static void calc_pg_sz(int obj_num, int obj_size, int hop_num, int ctx_bt_num,
+		       int *buf_page_size, int *bt_page_size, u32 hem_type)
+{
+	u64 obj_per_chunk;
+	int bt_chunk_size = 1 << PAGE_SHIFT;
+	int buf_chunk_size = 1 << PAGE_SHIFT;
+	int obj_per_chunk_default = buf_chunk_size / obj_size;
+
+	*buf_page_size = 0;
+	*bt_page_size = 0;
+
+	switch (hop_num) {
+	case 3:
+		obj_per_chunk = ctx_bt_num * (bt_chunk_size / BA_BYTE_LEN) *
+				(bt_chunk_size / BA_BYTE_LEN) *
+				(bt_chunk_size / BA_BYTE_LEN) *
+				 obj_per_chunk_default;
+		break;
+	case 2:
+		obj_per_chunk = ctx_bt_num * (bt_chunk_size / BA_BYTE_LEN) *
+				(bt_chunk_size / BA_BYTE_LEN) *
+				 obj_per_chunk_default;
+		break;
+	case 1:
+		obj_per_chunk = ctx_bt_num * (bt_chunk_size / BA_BYTE_LEN) *
+				obj_per_chunk_default;
+		break;
+	case HNS_ROCE_HOP_NUM_0:
+		obj_per_chunk = ctx_bt_num * obj_per_chunk_default;
+		break;
+	default:
+		pr_err("Table %d not support hop_num = %d!\n", hem_type,
+			hop_num);
+		return;
+	}
+
+	if (hem_type >= HEM_TYPE_MTT)
+		*bt_page_size = ilog2(DIV_ROUND_UP(obj_num, obj_per_chunk));
+	else
+		*buf_page_size = ilog2(DIV_ROUND_UP(obj_num, obj_per_chunk));
+}
+
+static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_cmq_desc desc[HNS_ROCE_QUERY_PF_CAPS_CMD_NUM];
+	struct hns_roce_caps *caps = &hr_dev->caps;
+	struct hns_roce_query_pf_caps_a *resp_a;
+	struct hns_roce_query_pf_caps_b *resp_b;
+	struct hns_roce_query_pf_caps_c *resp_c;
+	struct hns_roce_query_pf_caps_d *resp_d;
+	struct hns_roce_query_pf_caps_e *resp_e;
+	int ctx_hop_num;
+	int pbl_hop_num;
+	int ret;
+	int i;
+
+	for (i = 0; i < HNS_ROCE_QUERY_PF_CAPS_CMD_NUM; i++) {
+		hns_roce_cmq_setup_basic_desc(&desc[i],
+					      HNS_ROCE_OPC_QUERY_PF_CAPS_NUM,
+					      true);
+		if (i < (HNS_ROCE_QUERY_PF_CAPS_CMD_NUM - 1))
+			desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
+		else
+			desc[i].flag &= ~cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);
+	}
+
+	ret = hns_roce_cmq_send(hr_dev, desc, HNS_ROCE_QUERY_PF_CAPS_CMD_NUM);
+	if (ret)
+		return ret;
+
+	resp_a = (struct hns_roce_query_pf_caps_a *)desc[0].data;
+	resp_b = (struct hns_roce_query_pf_caps_b *)desc[1].data;
+	resp_c = (struct hns_roce_query_pf_caps_c *)desc[2].data;
+	resp_d = (struct hns_roce_query_pf_caps_d *)desc[3].data;
+	resp_e = (struct hns_roce_query_pf_caps_e *)desc[4].data;
+
+	caps->local_ca_ack_delay     = resp_a->local_ca_ack_delay;
+	caps->max_sq_sg		     = le16_to_cpu(resp_a->max_sq_sg);
+	caps->max_sq_inline	     = le16_to_cpu(resp_a->max_sq_inline);
+	caps->max_rq_sg		     = le16_to_cpu(resp_a->max_rq_sg);
+	caps->max_extend_sg	     = le32_to_cpu(resp_a->max_extend_sg);
+	caps->num_qpc_timer	     = le16_to_cpu(resp_a->num_qpc_timer);
+	caps->num_cqc_timer	     = le16_to_cpu(resp_a->num_cqc_timer);
+	caps->max_srq_sges	     = le16_to_cpu(resp_a->max_srq_sges);
+	caps->num_aeq_vectors	     = resp_a->num_aeq_vectors;
+	caps->num_other_vectors	     = resp_a->num_other_vectors;
+	caps->max_sq_desc_sz	     = resp_a->max_sq_desc_sz;
+	caps->max_rq_desc_sz	     = resp_a->max_rq_desc_sz;
+	caps->max_srq_desc_sz	     = resp_a->max_srq_desc_sz;
+	caps->cq_entry_sz	     = resp_a->cq_entry_sz;
+
+	caps->mtpt_entry_sz	     = resp_b->mtpt_entry_sz;
+	caps->irrl_entry_sz	     = resp_b->irrl_entry_sz;
+	caps->trrl_entry_sz	     = resp_b->trrl_entry_sz;
+	caps->cqc_entry_sz	     = resp_b->cqc_entry_sz;
+	caps->srqc_entry_sz	     = resp_b->srqc_entry_sz;
+	caps->idx_entry_sz	     = resp_b->idx_entry_sz;
+	caps->sccc_entry_sz	     = resp_b->scc_ctx_entry_sz;
+	caps->max_mtu		     = resp_b->max_mtu;
+	caps->qpc_entry_sz	     = le16_to_cpu(resp_b->qpc_entry_sz);
+	caps->min_cqes		     = resp_b->min_cqes;
+	caps->min_wqes		     = resp_b->min_wqes;
+	caps->page_size_cap	     = le32_to_cpu(resp_b->page_size_cap);
+	caps->pkey_table_len[0]	     = resp_b->pkey_table_len;
+	caps->phy_num_uars	     = resp_b->phy_num_uars;
+	ctx_hop_num		     = resp_b->ctx_hop_num;
+	pbl_hop_num		     = resp_b->pbl_hop_num;
+
+	caps->num_pds = 1 << roce_get_field(resp_c->cap_flags_num_pds,
+					    V2_QUERY_PF_CAPS_C_NUM_PDS_M,
+					    V2_QUERY_PF_CAPS_C_NUM_PDS_S);
+	caps->flags = roce_get_field(resp_c->cap_flags_num_pds,
+				     V2_QUERY_PF_CAPS_C_CAP_FLAGS_M,
+				     V2_QUERY_PF_CAPS_C_CAP_FLAGS_S);
+	caps->num_cqs = 1 << roce_get_field(resp_c->max_gid_num_cqs,
+					    V2_QUERY_PF_CAPS_C_NUM_CQS_M,
+					    V2_QUERY_PF_CAPS_C_NUM_CQS_S);
+	caps->gid_table_len[0] = roce_get_field(resp_c->max_gid_num_cqs,
+						V2_QUERY_PF_CAPS_C_MAX_GID_M,
+						V2_QUERY_PF_CAPS_C_MAX_GID_S);
+	caps->max_cqes = 1 << roce_get_field(resp_c->cq_depth,
+					     V2_QUERY_PF_CAPS_C_CQ_DEPTH_M,
+					     V2_QUERY_PF_CAPS_C_CQ_DEPTH_S);
+	caps->num_mtpts = 1 << roce_get_field(resp_c->num_mrws,
+					      V2_QUERY_PF_CAPS_C_NUM_MRWS_M,
+					      V2_QUERY_PF_CAPS_C_NUM_MRWS_S);
+	caps->num_qps = 1 << roce_get_field(resp_c->ord_num_qps,
+					    V2_QUERY_PF_CAPS_C_NUM_QPS_M,
+					    V2_QUERY_PF_CAPS_C_NUM_QPS_S);
+	caps->max_qp_init_rdma = roce_get_field(resp_c->ord_num_qps,
+						V2_QUERY_PF_CAPS_C_MAX_ORD_M,
+						V2_QUERY_PF_CAPS_C_MAX_ORD_S);
+	caps->max_qp_dest_rdma = caps->max_qp_init_rdma;
+	caps->max_wqes = 1 << le16_to_cpu(resp_c->sq_depth);
+	caps->num_srqs = 1 << roce_get_field(resp_d->wq_hop_num_max_srqs,
+					     V2_QUERY_PF_CAPS_D_NUM_SRQS_M,
+					     V2_QUERY_PF_CAPS_D_NUM_SRQS_S);
+	caps->max_srq_wrs = 1 << le16_to_cpu(resp_d->srq_depth);
+	caps->ceqe_depth = 1 << roce_get_field(resp_d->num_ceqs_ceq_depth,
+					       V2_QUERY_PF_CAPS_D_CEQ_DEPTH_M,
+					       V2_QUERY_PF_CAPS_D_CEQ_DEPTH_S);
+	caps->num_comp_vectors = roce_get_field(resp_d->num_ceqs_ceq_depth,
+						V2_QUERY_PF_CAPS_D_NUM_CEQS_M,
+						V2_QUERY_PF_CAPS_D_NUM_CEQS_S);
+	caps->aeqe_depth = 1 << roce_get_field(resp_d->arm_st_aeq_depth,
+					       V2_QUERY_PF_CAPS_D_AEQ_DEPTH_M,
+					       V2_QUERY_PF_CAPS_D_AEQ_DEPTH_S);
+	caps->default_aeq_arm_st = roce_get_field(resp_d->arm_st_aeq_depth,
+					    V2_QUERY_PF_CAPS_D_AEQ_ARM_ST_M,
+					    V2_QUERY_PF_CAPS_D_AEQ_ARM_ST_S);
+	caps->default_ceq_arm_st = roce_get_field(resp_d->arm_st_aeq_depth,
+					    V2_QUERY_PF_CAPS_D_CEQ_ARM_ST_M,
+					    V2_QUERY_PF_CAPS_D_CEQ_ARM_ST_S);
+	caps->reserved_pds = roce_get_field(resp_d->num_uars_rsv_pds,
+					    V2_QUERY_PF_CAPS_D_RSV_PDS_M,
+					    V2_QUERY_PF_CAPS_D_RSV_PDS_S);
+	caps->num_uars = 1 << roce_get_field(resp_d->num_uars_rsv_pds,
+					     V2_QUERY_PF_CAPS_D_NUM_UARS_M,
+					     V2_QUERY_PF_CAPS_D_NUM_UARS_S);
+	caps->reserved_qps = roce_get_field(resp_d->rsv_uars_rsv_qps,
+					    V2_QUERY_PF_CAPS_D_RSV_QPS_M,
+					    V2_QUERY_PF_CAPS_D_RSV_QPS_S);
+	caps->reserved_uars = roce_get_field(resp_d->rsv_uars_rsv_qps,
+					     V2_QUERY_PF_CAPS_D_RSV_UARS_M,
+					     V2_QUERY_PF_CAPS_D_RSV_UARS_S);
+	caps->reserved_mrws = roce_get_field(resp_e->chunk_size_shift_rsv_mrws,
+					     V2_QUERY_PF_CAPS_E_RSV_MRWS_M,
+					     V2_QUERY_PF_CAPS_E_RSV_MRWS_S);
+	caps->chunk_sz = 1 << roce_get_field(resp_e->chunk_size_shift_rsv_mrws,
+					 V2_QUERY_PF_CAPS_E_CHUNK_SIZE_SHIFT_M,
+					 V2_QUERY_PF_CAPS_E_CHUNK_SIZE_SHIFT_S);
+	caps->reserved_cqs = roce_get_field(resp_e->rsv_cqs,
+					    V2_QUERY_PF_CAPS_E_RSV_CQS_M,
+					    V2_QUERY_PF_CAPS_E_RSV_CQS_S);
+	caps->reserved_srqs = roce_get_field(resp_e->rsv_srqs,
+					     V2_QUERY_PF_CAPS_E_RSV_SRQS_M,
+					     V2_QUERY_PF_CAPS_E_RSV_SRQS_S);
+	caps->reserved_lkey = roce_get_field(resp_e->rsv_lkey,
+					     V2_QUERY_PF_CAPS_E_RSV_LKEYS_M,
+					     V2_QUERY_PF_CAPS_E_RSV_LKEYS_S);
+	caps->default_ceq_max_cnt = le16_to_cpu(resp_e->ceq_max_cnt);
+	caps->default_ceq_period = le16_to_cpu(resp_e->ceq_period);
+	caps->default_aeq_max_cnt = le16_to_cpu(resp_e->aeq_max_cnt);
+	caps->default_aeq_period = le16_to_cpu(resp_e->aeq_period);
+
+	caps->qpc_timer_entry_sz = HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ;
+	caps->cqc_timer_entry_sz = HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ;
+	caps->mtt_entry_sz = HNS_ROCE_V2_MTT_ENTRY_SZ;
+	caps->num_mtt_segs = HNS_ROCE_V2_MAX_MTT_SEGS;
+	caps->mtt_ba_pg_sz = 0;
+	caps->num_cqe_segs = HNS_ROCE_V2_MAX_CQE_SEGS;
+	caps->num_srqwqe_segs = HNS_ROCE_V2_MAX_SRQWQE_SEGS;
+	caps->num_idx_segs = HNS_ROCE_V2_MAX_IDX_SEGS;
+
+	caps->qpc_hop_num = ctx_hop_num;
+	caps->srqc_hop_num = ctx_hop_num;
+	caps->cqc_hop_num = ctx_hop_num;
+	caps->mpt_hop_num = ctx_hop_num;
+	caps->mtt_hop_num = pbl_hop_num;
+	caps->cqe_hop_num = pbl_hop_num;
+	caps->srqwqe_hop_num = pbl_hop_num;
+	caps->idx_hop_num = pbl_hop_num;
+	caps->wqe_sq_hop_num = roce_get_field(resp_d->wq_hop_num_max_srqs,
+					  V2_QUERY_PF_CAPS_D_SQWQE_HOP_NUM_M,
+					  V2_QUERY_PF_CAPS_D_SQWQE_HOP_NUM_S);
+	caps->wqe_sge_hop_num = roce_get_field(resp_d->wq_hop_num_max_srqs,
+					  V2_QUERY_PF_CAPS_D_EX_SGE_HOP_NUM_M,
+					  V2_QUERY_PF_CAPS_D_EX_SGE_HOP_NUM_S);
+	caps->wqe_rq_hop_num = roce_get_field(resp_d->wq_hop_num_max_srqs,
+					  V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_M,
+					  V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_S);
+
+	calc_pg_sz(caps->num_qps, caps->qpc_entry_sz, caps->qpc_hop_num,
+		   caps->qpc_bt_num, &caps->qpc_buf_pg_sz, &caps->qpc_ba_pg_sz,
+		   HEM_TYPE_QPC);
+	calc_pg_sz(caps->num_mtpts, caps->mtpt_entry_sz, caps->mpt_hop_num,
+		   caps->mpt_bt_num, &caps->mpt_buf_pg_sz, &caps->mpt_ba_pg_sz,
+		   HEM_TYPE_MTPT);
+	calc_pg_sz(caps->num_cqs, caps->cqc_entry_sz, caps->cqc_hop_num,
+		   caps->cqc_bt_num, &caps->cqc_buf_pg_sz, &caps->cqc_ba_pg_sz,
+		   HEM_TYPE_CQC);
+	calc_pg_sz(caps->num_srqs, caps->srqc_entry_sz, caps->srqc_hop_num,
+		   caps->srqc_bt_num, &caps->srqc_buf_pg_sz,
+		   &caps->srqc_ba_pg_sz, HEM_TYPE_SRQC);
+
+	if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08_B) {
+		caps->sccc_hop_num = ctx_hop_num;
+		caps->qpc_timer_hop_num = HNS_ROCE_HOP_NUM_0;
+		caps->cqc_timer_hop_num = HNS_ROCE_HOP_NUM_0;
+
+		calc_pg_sz(caps->num_qps, caps->sccc_entry_sz,
+			   caps->sccc_hop_num, caps->sccc_bt_num,
+			   &caps->sccc_buf_pg_sz, &caps->sccc_ba_pg_sz,
+			   HEM_TYPE_SCCC);
+		calc_pg_sz(caps->num_cqc_timer, caps->cqc_timer_entry_sz,
+			   caps->cqc_timer_hop_num, caps->cqc_timer_bt_num,
+			   &caps->cqc_timer_buf_pg_sz,
+			   &caps->cqc_timer_ba_pg_sz, HEM_TYPE_CQC_TIMER);
+	}
+
+	calc_pg_sz(caps->num_cqe_segs, caps->mtt_entry_sz, caps->cqe_hop_num,
+		   1, &caps->cqe_buf_pg_sz, &caps->cqe_ba_pg_sz, HEM_TYPE_CQE);
+	calc_pg_sz(caps->num_srqwqe_segs, caps->mtt_entry_sz,
+		   caps->srqwqe_hop_num, 1, &caps->srqwqe_buf_pg_sz,
+		   &caps->srqwqe_ba_pg_sz, HEM_TYPE_SRQWQE);
+	calc_pg_sz(caps->num_idx_segs, caps->idx_entry_sz, caps->idx_hop_num,
+		   1, &caps->idx_buf_pg_sz, &caps->idx_ba_pg_sz, HEM_TYPE_IDX);
+
+	return 0;
+}
+
+static int hns_roce_v2_profile(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_caps *caps = &hr_dev->caps;
+	int ret;
+
+	ret = hns_roce_cmq_query_hw_info(hr_dev);
+	if (ret) {
+		dev_err(hr_dev->dev, "Query hardware version fail, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
+	ret = hns_roce_query_fw_ver(hr_dev);
+	if (ret) {
+		dev_err(hr_dev->dev, "Query firmware version fail, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
+	ret = hns_roce_config_global_param(hr_dev);
+	if (ret) {
+		dev_err(hr_dev->dev, "Configure global param fail, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
+	/* Get pf resource owned by every pf */
+	ret = hns_roce_query_pf_resource(hr_dev);
+	if (ret) {
+		dev_err(hr_dev->dev, "Query pf resource fail, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
+	if (hr_dev->pci_dev->revision == 0x21) {
+		ret = hns_roce_query_pf_timer_resource(hr_dev);
+		if (ret) {
+			dev_err(hr_dev->dev,
+				"Query pf timer resource fail, ret = %d.\n",
+				ret);
+			return ret;
+		}
+	}
+
+	ret = hns_roce_alloc_vf_resource(hr_dev);
+	if (ret) {
+		dev_err(hr_dev->dev, "Allocate vf resource fail, ret = %d.\n",
+			ret);
+		return ret;
+	}
+
+	if (hr_dev->pci_dev->revision == 0x21) {
+		ret = hns_roce_set_vf_switch_param(hr_dev, 0);
+		if (ret) {
+			dev_err(hr_dev->dev,
+				"Set function switch param fail, ret = %d.\n",
+				ret);
+			return ret;
+		}
 	}
 
+	hr_dev->vendor_part_id = hr_dev->pci_dev->device;
+	hr_dev->sys_image_guid = be64_to_cpu(hr_dev->ib_dev.node_guid);
+
+	caps->num_mtt_segs	= HNS_ROCE_V2_MAX_MTT_SEGS;
+	caps->num_cqe_segs	= HNS_ROCE_V2_MAX_CQE_SEGS;
+	caps->num_srqwqe_segs	= HNS_ROCE_V2_MAX_SRQWQE_SEGS;
+	caps->num_idx_segs	= HNS_ROCE_V2_MAX_IDX_SEGS;
+
+	caps->pbl_ba_pg_sz	= HNS_ROCE_BA_PG_SZ_SUPPORTED_16K;
+	caps->pbl_buf_pg_sz	= 0;
+	caps->pbl_hop_num	= HNS_ROCE_PBL_HOP_NUM;
+	caps->eqe_ba_pg_sz	= 0;
+	caps->eqe_buf_pg_sz	= 0;
+	caps->eqe_hop_num	= HNS_ROCE_EQE_HOP_NUM;
+	caps->tsq_buf_pg_sz	= 0;
+
+	ret = hns_roce_query_pf_caps(hr_dev);
+	if (ret)
+		set_default_caps(hr_dev);
+
 	ret = hns_roce_v2_set_bt(hr_dev);
 	if (ret)
 		dev_err(hr_dev->dev, "Configure bt attribute fail, ret = %d.\n",
@@ -1818,37 +2101,32 @@ static int hns_roce_config_link_table(struct hns_roce_dev *hr_dev,
 			req_a->base_addr_h =
 				cpu_to_le32(link_tbl->table.map >> 32);
 			roce_set_field(req_a->depth_pgsz_init_en,
-				       CFG_LLM_QUE_DEPTH_M,
-				       CFG_LLM_QUE_DEPTH_S,
+				       CFG_LLM_QUE_DEPTH_M, CFG_LLM_QUE_DEPTH_S,
 				       link_tbl->npages);
 			roce_set_field(req_a->depth_pgsz_init_en,
-				       CFG_LLM_QUE_PGSZ_M,
-				       CFG_LLM_QUE_PGSZ_S,
+				       CFG_LLM_QUE_PGSZ_M, CFG_LLM_QUE_PGSZ_S,
 				       link_tbl->pg_sz);
 			req_a->head_ba_l = cpu_to_le32(entry[0].blk_ba0);
 			req_a->head_ba_h_nxtptr =
 				cpu_to_le32(entry[0].blk_ba1_nxt_ptr);
-			roce_set_field(req_a->head_ptr,
-				       CFG_LLM_HEAD_PTR_M,
+			roce_set_field(req_a->head_ptr, CFG_LLM_HEAD_PTR_M,
 				       CFG_LLM_HEAD_PTR_S, 0);
 		} else {
 			req_b->tail_ba_l =
 				cpu_to_le32(entry[page_num - 1].blk_ba0);
-			roce_set_field(req_b->tail_ba_h,
-				       CFG_LLM_TAIL_BA_H_M,
+			roce_set_field(req_b->tail_ba_h, CFG_LLM_TAIL_BA_H_M,
 				       CFG_LLM_TAIL_BA_H_S,
 				       entry[page_num - 1].blk_ba1_nxt_ptr &
-				       HNS_ROCE_LINK_TABLE_BA1_M);
-			roce_set_field(req_b->tail_ptr,
-				       CFG_LLM_TAIL_PTR_M,
+					       HNS_ROCE_LINK_TABLE_BA1_M);
+			roce_set_field(req_b->tail_ptr, CFG_LLM_TAIL_PTR_M,
 				       CFG_LLM_TAIL_PTR_S,
 				       (entry[page_num - 2].blk_ba1_nxt_ptr &
-				       HNS_ROCE_LINK_TABLE_NXT_PTR_M) >>
-				       HNS_ROCE_LINK_TABLE_NXT_PTR_S);
+					HNS_ROCE_LINK_TABLE_NXT_PTR_M) >>
+					       HNS_ROCE_LINK_TABLE_NXT_PTR_S);
 		}
 	}
-	roce_set_field(req_a->depth_pgsz_init_en,
-		       CFG_LLM_INIT_EN_M, CFG_LLM_INIT_EN_S, 1);
+	roce_set_field(req_a->depth_pgsz_init_en, CFG_LLM_INIT_EN_M,
+		       CFG_LLM_INIT_EN_S, 1);
 
 	return hns_roce_cmq_send(hr_dev, desc, 2);
 }
@@ -2141,11 +2419,9 @@ static int hns_roce_config_sgid_table(struct hns_roce_dev *hr_dev,
 
 	hns_roce_cmq_setup_basic_desc(&desc, HNS_ROCE_OPC_CFG_SGID_TB, false);
 
-	roce_set_field(sgid_tb->table_idx_rsv,
-		       CFG_SGID_TB_TABLE_IDX_M,
+	roce_set_field(sgid_tb->table_idx_rsv, CFG_SGID_TB_TABLE_IDX_M,
 		       CFG_SGID_TB_TABLE_IDX_S, gid_index);
-	roce_set_field(sgid_tb->vf_sgid_type_rsv,
-		       CFG_SGID_TB_VF_SGID_TYPE_M,
+	roce_set_field(sgid_tb->vf_sgid_type_rsv, CFG_SGID_TB_VF_SGID_TYPE_M,
 		       CFG_SGID_TB_VF_SGID_TYPE_S, sgid_type);
 
 	p = (u32 *)&gid->raw[0];
@@ -2416,11 +2692,10 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw)
 		       V2_MPT_BYTE_4_MPT_ST_S, V2_MPT_ST_FREE);
 	roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M,
 		       V2_MPT_BYTE_4_PD_S, mw->pdn);
-	roce_set_field(mpt_entry->byte_4_pd_hop_st,
-		       V2_MPT_BYTE_4_PBL_HOP_NUM_M,
+	roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PBL_HOP_NUM_M,
 		       V2_MPT_BYTE_4_PBL_HOP_NUM_S,
-		       mw->pbl_hop_num == HNS_ROCE_HOP_NUM_0 ?
-		       0 : mw->pbl_hop_num);
+		       mw->pbl_hop_num == HNS_ROCE_HOP_NUM_0 ? 0 :
+							       mw->pbl_hop_num);
 	roce_set_field(mpt_entry->byte_4_pd_hop_st,
 		       V2_MPT_BYTE_4_PBL_BA_PG_SZ_M,
 		       V2_MPT_BYTE_4_PBL_BA_PG_SZ_S,
@@ -2561,8 +2836,7 @@ static void hns_roce_v2_write_cqc(struct hns_roce_dev *hr_dev,
 	roce_set_field(cq_context->byte_4_pg_ceqn, V2_CQC_BYTE_4_ARM_ST_M,
 		       V2_CQC_BYTE_4_ARM_ST_S, REG_NXT_CEQE);
 	roce_set_field(cq_context->byte_4_pg_ceqn, V2_CQC_BYTE_4_SHIFT_M,
-		       V2_CQC_BYTE_4_SHIFT_S,
-		       ilog2(hr_cq->cq_depth));
+		       V2_CQC_BYTE_4_SHIFT_S, ilog2(hr_cq->cq_depth));
 	roce_set_field(cq_context->byte_4_pg_ceqn, V2_CQC_BYTE_4_CEQN_M,
 		       V2_CQC_BYTE_4_CEQN_S, hr_cq->vector);
 
@@ -2687,6 +2961,55 @@ static int hns_roce_handle_recv_inl_wqe(struct hns_roce_v2_cqe *cqe,
 	return 0;
 }
 
+static int sw_comp(struct hns_roce_qp *hr_qp, struct hns_roce_wq *wq,
+		   int num_entries, struct ib_wc *wc)
+{
+	unsigned int left;
+	int npolled = 0;
+
+	left = wq->head - wq->tail;
+	if (left == 0)
+		return 0;
+
+	left = min_t(unsigned int, (unsigned int)num_entries, left);
+	while (npolled < left) {
+		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
+		wc->status = IB_WC_WR_FLUSH_ERR;
+		wc->vendor_err = 0;
+		wc->qp = &hr_qp->ibqp;
+
+		wq->tail++;
+		wc++;
+		npolled++;
+	}
+
+	return npolled;
+}
+
+static int hns_roce_v2_sw_poll_cq(struct hns_roce_cq *hr_cq, int num_entries,
+				  struct ib_wc *wc)
+{
+	struct hns_roce_qp *hr_qp;
+	int npolled = 0;
+
+	list_for_each_entry(hr_qp, &hr_cq->sq_list, sq_node) {
+		npolled += sw_comp(hr_qp, &hr_qp->sq,
+				   num_entries - npolled, wc + npolled);
+		if (npolled >= num_entries)
+			goto out;
+	}
+
+	list_for_each_entry(hr_qp, &hr_cq->rq_list, rq_node) {
+		npolled += sw_comp(hr_qp, &hr_qp->rq,
+				   num_entries - npolled, wc + npolled);
+		if (npolled >= num_entries)
+			goto out;
+	}
+
+out:
+	return npolled;
+}
+
 static int hns_roce_v2_poll_one(struct hns_roce_cq *hr_cq,
 				struct hns_roce_qp **cur_qp, struct ib_wc *wc)
 {
@@ -2967,6 +3290,7 @@ static int hns_roce_v2_poll_one(struct hns_roce_cq *hr_cq,
 static int hns_roce_v2_poll_cq(struct ib_cq *ibcq, int num_entries,
 			       struct ib_wc *wc)
 {
+	struct hns_roce_dev *hr_dev = to_hr_dev(ibcq->device);
 	struct hns_roce_cq *hr_cq = to_hr_cq(ibcq);
 	struct hns_roce_qp *cur_qp = NULL;
 	unsigned long flags;
@@ -2974,6 +3298,18 @@ static int hns_roce_v2_poll_cq(struct ib_cq *ibcq, int num_entries,
 
 	spin_lock_irqsave(&hr_cq->lock, flags);
 
+	/*
+	 * When the device starts to reset, the state is RST_DOWN. At this time,
+	 * there may still be some valid CQEs in the hardware that are not
+	 * polled. Therefore, it is not allowed to switch to the software mode
+	 * immediately. When the state changes to UNINIT, CQE no longer exists
+	 * in the hardware, and then switch to software mode.
+	 */
+	if (hr_dev->state == HNS_ROCE_DEVICE_STATE_UNINIT) {
+		npolled = hns_roce_v2_sw_poll_cq(hr_cq, num_entries, wc);
+		goto out;
+	}
+
 	for (npolled = 0; npolled < num_entries; ++npolled) {
 		if (hns_roce_v2_poll_one(hr_cq, &cur_qp, wc + npolled))
 			break;
@@ -2985,6 +3321,7 @@ static int hns_roce_v2_poll_cq(struct ib_cq *ibcq, int num_entries,
 		hns_roce_v2_cq_set_ci(hr_cq, hr_cq->cons_index);
 	}
 
+out:
 	spin_unlock_irqrestore(&hr_cq->lock, flags);
 
 	return npolled;
@@ -3159,8 +3496,6 @@ static int hns_roce_v2_clear_hem(struct hns_roce_dev *hr_dev,
 }
 
 static int hns_roce_v2_qp_modify(struct hns_roce_dev *hr_dev,
-				 enum ib_qp_state cur_state,
-				 enum ib_qp_state new_state,
 				 struct hns_roce_v2_qp_context *context,
 				 struct hns_roce_qp *hr_qp)
 {
@@ -3210,6 +3545,9 @@ static void set_access_flags(struct hns_roce_qp *hr_qp,
 	roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S,
 		     !!(access_flags & IB_ACCESS_REMOTE_ATOMIC));
 	roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S, 0);
+	roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_EXT_ATE_S,
+		     !!(access_flags & IB_ACCESS_REMOTE_ATOMIC));
+	roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_EXT_ATE_S, 0);
 }
 
 static void set_qpc_wqe_cnt(struct hns_roce_qp *hr_qp,
@@ -3577,6 +3915,12 @@ static void modify_qp_init_to_init(struct ib_qp *ibqp,
 			     IB_ACCESS_REMOTE_ATOMIC));
 		roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S,
 			     0);
+		roce_set_bit(context->byte_76_srqn_op_en,
+			     V2_QPC_BYTE_76_EXT_ATE_S,
+			     !!(attr->qp_access_flags &
+				IB_ACCESS_REMOTE_ATOMIC));
+		roce_set_bit(qpc_mask->byte_76_srqn_op_en,
+			     V2_QPC_BYTE_76_EXT_ATE_S, 0);
 	} else {
 		roce_set_bit(context->byte_76_srqn_op_en, V2_QPC_BYTE_76_RRE_S,
 			     !!(hr_qp->access_flags & IB_ACCESS_REMOTE_READ));
@@ -3592,6 +3936,11 @@ static void modify_qp_init_to_init(struct ib_qp *ibqp,
 			     !!(hr_qp->access_flags & IB_ACCESS_REMOTE_ATOMIC));
 		roce_set_bit(qpc_mask->byte_76_srqn_op_en, V2_QPC_BYTE_76_ATE_S,
 			     0);
+		roce_set_bit(context->byte_76_srqn_op_en,
+			     V2_QPC_BYTE_76_EXT_ATE_S,
+			     !!(hr_qp->access_flags & IB_ACCESS_REMOTE_ATOMIC));
+		roce_set_bit(qpc_mask->byte_76_srqn_op_en,
+			     V2_QPC_BYTE_76_EXT_ATE_S, 0);
 	}
 
 	roce_set_field(context->byte_16_buf_ba_pg_sz, V2_QPC_BYTE_16_PD_M,
@@ -3838,13 +4187,11 @@ static int modify_qp_init_to_rtr(struct ib_qp *ibqp,
 	/* Configure GID index */
 	port_num = rdma_ah_get_port_num(&attr->ah_attr);
 	roce_set_field(context->byte_20_smac_sgid_idx,
-		       V2_QPC_BYTE_20_SGID_IDX_M,
-		       V2_QPC_BYTE_20_SGID_IDX_S,
+		       V2_QPC_BYTE_20_SGID_IDX_M, V2_QPC_BYTE_20_SGID_IDX_S,
 		       hns_get_gid_index(hr_dev, port_num - 1,
 					 grh->sgid_index));
 	roce_set_field(qpc_mask->byte_20_smac_sgid_idx,
-		       V2_QPC_BYTE_20_SGID_IDX_M,
-		       V2_QPC_BYTE_20_SGID_IDX_S, 0);
+		       V2_QPC_BYTE_20_SGID_IDX_M, V2_QPC_BYTE_20_SGID_IDX_S, 0);
 	memcpy(&(context->dmac), dmac, sizeof(u32));
 	roce_set_field(context->byte_52_udpspn_dmac, V2_QPC_BYTE_52_DMAC_M,
 		       V2_QPC_BYTE_52_DMAC_S, *((u16 *)(&dmac[4])));
@@ -4234,8 +4581,7 @@ static int hns_roce_v2_set_opt_fields(struct ib_qp *ibqp,
 
 		roce_set_field(context->byte_212_lsn,
 			       V2_QPC_BYTE_212_RETRY_CNT_M,
-			       V2_QPC_BYTE_212_RETRY_CNT_S,
-			       attr->retry_cnt);
+			       V2_QPC_BYTE_212_RETRY_CNT_S, attr->retry_cnt);
 		roce_set_field(qpc_mask->byte_212_lsn,
 			       V2_QPC_BYTE_212_RETRY_CNT_M,
 			       V2_QPC_BYTE_212_RETRY_CNT_S, 0);
@@ -4443,7 +4789,7 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 		       V2_QPC_BYTE_60_QP_ST_S, 0);
 
 	/* SW pass context to HW */
-	ret = hns_roce_v2_qp_modify(hr_dev, cur_state, new_state, ctx, hr_qp);
+	ret = hns_roce_v2_qp_modify(hr_dev, ctx, hr_qp);
 	if (ret) {
 		dev_err(dev, "hns_roce_qp_modify failed(%d)\n", ret);
 		goto out;
@@ -4464,7 +4810,6 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 		hr_qp->rq.tail = 0;
 		hr_qp->sq.head = 0;
 		hr_qp->sq.tail = 0;
-		hr_qp->sq_next_wqe = 0;
 		hr_qp->next_sge = 0;
 		if (hr_qp->rq.wqe_cnt)
 			*hr_qp->rdb.db_record = 0;
@@ -4649,6 +4994,7 @@ static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev,
 {
 	struct hns_roce_cq *send_cq, *recv_cq;
 	struct ib_device *ibdev = &hr_dev->ib_dev;
+	unsigned long flags;
 	int ret = 0;
 
 	if (hr_qp->ibqp.qp_type == IB_QPT_RC && hr_qp->state != IB_QPS_RESET) {
@@ -4659,21 +5005,32 @@ static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev,
 			ibdev_err(ibdev, "modify QP to Reset failed.\n");
 	}
 
-	send_cq = to_hr_cq(hr_qp->ibqp.send_cq);
-	recv_cq = to_hr_cq(hr_qp->ibqp.recv_cq);
+	send_cq = hr_qp->ibqp.send_cq ? to_hr_cq(hr_qp->ibqp.send_cq) : NULL;
+	recv_cq = hr_qp->ibqp.recv_cq ? to_hr_cq(hr_qp->ibqp.recv_cq) : NULL;
 
+	spin_lock_irqsave(&hr_dev->qp_list_lock, flags);
 	hns_roce_lock_cqs(send_cq, recv_cq);
 
+	list_del(&hr_qp->node);
+	list_del(&hr_qp->sq_node);
+	list_del(&hr_qp->rq_node);
+
 	if (!udata) {
-		__hns_roce_v2_cq_clean(recv_cq, hr_qp->qpn, hr_qp->ibqp.srq ?
-				       to_hr_srq(hr_qp->ibqp.srq) : NULL);
-		if (send_cq != recv_cq)
+		if (recv_cq)
+			__hns_roce_v2_cq_clean(recv_cq, hr_qp->qpn,
+					       (hr_qp->ibqp.srq ?
+						to_hr_srq(hr_qp->ibqp.srq) :
+						NULL));
+
+		if (send_cq && send_cq != recv_cq)
 			__hns_roce_v2_cq_clean(send_cq, hr_qp->qpn, NULL);
+
 	}
 
 	hns_roce_qp_remove(hr_dev, hr_qp);
 
 	hns_roce_unlock_cqs(send_cq, recv_cq);
+	spin_unlock_irqrestore(&hr_dev->qp_list_lock, flags);
 
 	hns_roce_qp_free(hr_dev, hr_qp);
 
@@ -5155,8 +5512,7 @@ static int hns_roce_v2_ceq_int(struct hns_roce_dev *hr_dev,
 		 */
 		dma_rmb();
 
-		cqn = roce_get_field(ceqe->comp,
-				     HNS_ROCE_V2_CEQE_COMP_CQN_M,
+		cqn = roce_get_field(ceqe->comp, HNS_ROCE_V2_CEQE_COMP_CQN_M,
 				     HNS_ROCE_V2_CEQE_COMP_CQN_S);
 
 		hns_roce_cq_completion(hr_dev, cqn);
@@ -5409,126 +5765,98 @@ static void hns_roce_config_eqc(struct hns_roce_dev *hr_dev,
 		eq->eqe_ba = eq->l0_dma;
 
 	/* set eqc state */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_EQ_ST_M,
-		       HNS_ROCE_EQC_EQ_ST_S,
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_EQ_ST_M, HNS_ROCE_EQC_EQ_ST_S,
 		       HNS_ROCE_V2_EQ_STATE_VALID);
 
 	/* set eqe hop num */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_HOP_NUM_M,
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_HOP_NUM_M,
 		       HNS_ROCE_EQC_HOP_NUM_S, eq->hop_num);
 
 	/* set eqc over_ignore */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_OVER_IGNORE_M,
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_OVER_IGNORE_M,
 		       HNS_ROCE_EQC_OVER_IGNORE_S, eq->over_ignore);
 
 	/* set eqc coalesce */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_COALESCE_M,
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_COALESCE_M,
 		       HNS_ROCE_EQC_COALESCE_S, eq->coalesce);
 
 	/* set eqc arm_state */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_ARM_ST_M,
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_ARM_ST_M,
 		       HNS_ROCE_EQC_ARM_ST_S, eq->arm_st);
 
 	/* set eqn */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_EQN_M,
-		       HNS_ROCE_EQC_EQN_S, eq->eqn);
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_EQN_M, HNS_ROCE_EQC_EQN_S,
+		       eq->eqn);
 
 	/* set eqe_cnt */
-	roce_set_field(eqc->byte_4,
-		       HNS_ROCE_EQC_EQE_CNT_M,
-		       HNS_ROCE_EQC_EQE_CNT_S,
-		       HNS_ROCE_EQ_INIT_EQE_CNT);
+	roce_set_field(eqc->byte_4, HNS_ROCE_EQC_EQE_CNT_M,
+		       HNS_ROCE_EQC_EQE_CNT_S, HNS_ROCE_EQ_INIT_EQE_CNT);
 
 	/* set eqe_ba_pg_sz */
-	roce_set_field(eqc->byte_8,
-		       HNS_ROCE_EQC_BA_PG_SZ_M,
+	roce_set_field(eqc->byte_8, HNS_ROCE_EQC_BA_PG_SZ_M,
 		       HNS_ROCE_EQC_BA_PG_SZ_S,
 		       eq->eqe_ba_pg_sz + PG_SHIFT_OFFSET);
 
 	/* set eqe_buf_pg_sz */
-	roce_set_field(eqc->byte_8,
-		       HNS_ROCE_EQC_BUF_PG_SZ_M,
+	roce_set_field(eqc->byte_8, HNS_ROCE_EQC_BUF_PG_SZ_M,
 		       HNS_ROCE_EQC_BUF_PG_SZ_S,
 		       eq->eqe_buf_pg_sz + PG_SHIFT_OFFSET);
 
 	/* set eq_producer_idx */
-	roce_set_field(eqc->byte_8,
-		       HNS_ROCE_EQC_PROD_INDX_M,
-		       HNS_ROCE_EQC_PROD_INDX_S,
-		       HNS_ROCE_EQ_INIT_PROD_IDX);
+	roce_set_field(eqc->byte_8, HNS_ROCE_EQC_PROD_INDX_M,
+		       HNS_ROCE_EQC_PROD_INDX_S, HNS_ROCE_EQ_INIT_PROD_IDX);
 
 	/* set eq_max_cnt */
-	roce_set_field(eqc->byte_12,
-		       HNS_ROCE_EQC_MAX_CNT_M,
+	roce_set_field(eqc->byte_12, HNS_ROCE_EQC_MAX_CNT_M,
 		       HNS_ROCE_EQC_MAX_CNT_S, eq->eq_max_cnt);
 
 	/* set eq_period */
-	roce_set_field(eqc->byte_12,
-		       HNS_ROCE_EQC_PERIOD_M,
+	roce_set_field(eqc->byte_12, HNS_ROCE_EQC_PERIOD_M,
 		       HNS_ROCE_EQC_PERIOD_S, eq->eq_period);
 
 	/* set eqe_report_timer */
-	roce_set_field(eqc->eqe_report_timer,
-		       HNS_ROCE_EQC_REPORT_TIMER_M,
+	roce_set_field(eqc->eqe_report_timer, HNS_ROCE_EQC_REPORT_TIMER_M,
 		       HNS_ROCE_EQC_REPORT_TIMER_S,
 		       HNS_ROCE_EQ_INIT_REPORT_TIMER);
 
 	/* set eqe_ba [34:3] */
-	roce_set_field(eqc->eqe_ba0,
-		       HNS_ROCE_EQC_EQE_BA_L_M,
+	roce_set_field(eqc->eqe_ba0, HNS_ROCE_EQC_EQE_BA_L_M,
 		       HNS_ROCE_EQC_EQE_BA_L_S, eq->eqe_ba >> 3);
 
 	/* set eqe_ba [64:35] */
-	roce_set_field(eqc->eqe_ba1,
-		       HNS_ROCE_EQC_EQE_BA_H_M,
+	roce_set_field(eqc->eqe_ba1, HNS_ROCE_EQC_EQE_BA_H_M,
 		       HNS_ROCE_EQC_EQE_BA_H_S, eq->eqe_ba >> 35);
 
 	/* set eq shift */
-	roce_set_field(eqc->byte_28,
-		       HNS_ROCE_EQC_SHIFT_M,
-		       HNS_ROCE_EQC_SHIFT_S, eq->shift);
+	roce_set_field(eqc->byte_28, HNS_ROCE_EQC_SHIFT_M, HNS_ROCE_EQC_SHIFT_S,
+		       eq->shift);
 
 	/* set eq MSI_IDX */
-	roce_set_field(eqc->byte_28,
-		       HNS_ROCE_EQC_MSI_INDX_M,
-		       HNS_ROCE_EQC_MSI_INDX_S,
-		       HNS_ROCE_EQ_INIT_MSI_IDX);
+	roce_set_field(eqc->byte_28, HNS_ROCE_EQC_MSI_INDX_M,
+		       HNS_ROCE_EQC_MSI_INDX_S, HNS_ROCE_EQ_INIT_MSI_IDX);
 
 	/* set cur_eqe_ba [27:12] */
-	roce_set_field(eqc->byte_28,
-		       HNS_ROCE_EQC_CUR_EQE_BA_L_M,
+	roce_set_field(eqc->byte_28, HNS_ROCE_EQC_CUR_EQE_BA_L_M,
 		       HNS_ROCE_EQC_CUR_EQE_BA_L_S, eq->cur_eqe_ba >> 12);
 
 	/* set cur_eqe_ba [59:28] */
-	roce_set_field(eqc->byte_32,
-		       HNS_ROCE_EQC_CUR_EQE_BA_M_M,
+	roce_set_field(eqc->byte_32, HNS_ROCE_EQC_CUR_EQE_BA_M_M,
 		       HNS_ROCE_EQC_CUR_EQE_BA_M_S, eq->cur_eqe_ba >> 28);
 
 	/* set cur_eqe_ba [63:60] */
-	roce_set_field(eqc->byte_36,
-		       HNS_ROCE_EQC_CUR_EQE_BA_H_M,
+	roce_set_field(eqc->byte_36, HNS_ROCE_EQC_CUR_EQE_BA_H_M,
 		       HNS_ROCE_EQC_CUR_EQE_BA_H_S, eq->cur_eqe_ba >> 60);
 
 	/* set eq consumer idx */
-	roce_set_field(eqc->byte_36,
-		       HNS_ROCE_EQC_CONS_INDX_M,
-		       HNS_ROCE_EQC_CONS_INDX_S,
-		       HNS_ROCE_EQ_INIT_CONS_IDX);
+	roce_set_field(eqc->byte_36, HNS_ROCE_EQC_CONS_INDX_M,
+		       HNS_ROCE_EQC_CONS_INDX_S, HNS_ROCE_EQ_INIT_CONS_IDX);
 
 	/* set nex_eqe_ba[43:12] */
-	roce_set_field(eqc->nxt_eqe_ba0,
-		       HNS_ROCE_EQC_NXT_EQE_BA_L_M,
+	roce_set_field(eqc->nxt_eqe_ba0, HNS_ROCE_EQC_NXT_EQE_BA_L_M,
 		       HNS_ROCE_EQC_NXT_EQE_BA_L_S, eq->nxt_eqe_ba >> 12);
 
 	/* set nex_eqe_ba[63:44] */
-	roce_set_field(eqc->nxt_eqe_ba1,
-		       HNS_ROCE_EQC_NXT_EQE_BA_H_M,
+	roce_set_field(eqc->nxt_eqe_ba1, HNS_ROCE_EQC_NXT_EQE_BA_H_M,
 		       HNS_ROCE_EQC_NXT_EQE_BA_H_S, eq->nxt_eqe_ba >> 44);
 }
 
@@ -5828,18 +6156,16 @@ static int __hns_roce_request_irq(struct hns_roce_dev *hr_dev, int irq_num,
 
 	/* irq contains: abnormal + AEQ + CEQ */
 	for (j = 0; j < other_num; j++)
-		snprintf((char *)hr_dev->irq_names[j],
-			 HNS_ROCE_INT_NAME_LEN, "hns-abn-%d", j);
+		snprintf((char *)hr_dev->irq_names[j], HNS_ROCE_INT_NAME_LEN,
+			 "hns-abn-%d", j);
 
 	for (j = other_num; j < (other_num + aeq_num); j++)
-		snprintf((char *)hr_dev->irq_names[j],
-			 HNS_ROCE_INT_NAME_LEN, "hns-aeq-%d",
-			 j - other_num);
+		snprintf((char *)hr_dev->irq_names[j], HNS_ROCE_INT_NAME_LEN,
+			 "hns-aeq-%d", j - other_num);
 
 	for (j = (other_num + aeq_num); j < irq_num; j++)
-		snprintf((char *)hr_dev->irq_names[j],
-			 HNS_ROCE_INT_NAME_LEN, "hns-ceq-%d",
-			 j - other_num - aeq_num);
+		snprintf((char *)hr_dev->irq_names[j], HNS_ROCE_INT_NAME_LEN,
+			 "hns-ceq-%d", j - other_num - aeq_num);
 
 	for (j = 0; j < irq_num; j++) {
 		if (j < other_num)
@@ -6448,6 +6774,10 @@ static void __hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
 		return;
 
 	handle->priv = NULL;
+
+	hr_dev->state = HNS_ROCE_DEVICE_STATE_UNINIT;
+	hns_roce_handle_device_err(hr_dev);
+
 	hns_roce_exit(hr_dev);
 	kfree(hr_dev->priv);
 	ib_dealloc_device(&hr_dev->ib_dev);
@@ -6509,7 +6839,6 @@ static void hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
 static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle)
 {
 	struct hns_roce_dev *hr_dev;
-	struct ib_event event;
 
 	if (handle->rinfo.instance_state != HNS_ROCE_STATE_INITED) {
 		set_bit(HNS_ROCE_RST_DIRECT_RETURN, &handle->rinfo.state);
@@ -6527,10 +6856,7 @@ static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle)
 	hr_dev->active = false;
 	hr_dev->dis_db = true;
 
-	event.event = IB_EVENT_DEVICE_FATAL;
-	event.device = &hr_dev->ib_dev;
-	event.element.port_num = 1;
-	ib_dispatch_event(&event);
+	hr_dev->state = HNS_ROCE_DEVICE_STATE_RST_DOWN;
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index 76a14db7028d..2a117ff6a6be 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -81,10 +81,12 @@
 #define HNS_ROCE_V2_QPC_ENTRY_SZ		256
 #define HNS_ROCE_V2_IRRL_ENTRY_SZ		64
 #define HNS_ROCE_V2_TRRL_ENTRY_SZ		48
+#define HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ	100
 #define HNS_ROCE_V2_CQC_ENTRY_SZ		64
 #define HNS_ROCE_V2_SRQC_ENTRY_SZ		64
 #define HNS_ROCE_V2_MTPT_ENTRY_SZ		64
 #define HNS_ROCE_V2_MTT_ENTRY_SZ		64
+#define HNS_ROCE_V2_IDX_ENTRY_SZ		4
 #define HNS_ROCE_V2_CQE_ENTRY_SIZE		32
 #define HNS_ROCE_V2_SCCC_ENTRY_SZ		32
 #define HNS_ROCE_V2_QPC_TIMER_ENTRY_SZ		PAGE_SIZE
@@ -109,7 +111,12 @@
 #define HNS_ROCE_PBL_HOP_NUM			2
 #define HNS_ROCE_EQE_HOP_NUM			2
 #define HNS_ROCE_IDX_HOP_NUM			1
+#define HNS_ROCE_SQWQE_HOP_NUM			2
+#define HNS_ROCE_EXT_SGE_HOP_NUM		1
+#define HNS_ROCE_RQWQE_HOP_NUM			2
 
+#define HNS_ROCE_BA_PG_SZ_SUPPORTED_256K	6
+#define HNS_ROCE_BA_PG_SZ_SUPPORTED_16K		2
 #define HNS_ROCE_V2_GID_INDEX_NUM		256
 
 #define HNS_ROCE_V2_TABLE_CHUNK_SIZE		(1 << 18)
@@ -237,6 +244,7 @@ enum hns_roce_opcode_type {
 	HNS_ROCE_OPC_CFG_EXT_LLM			= 0x8403,
 	HNS_ROCE_OPC_CFG_TMOUT_LLM			= 0x8404,
 	HNS_ROCE_OPC_QUERY_PF_TIMER_RES			= 0x8406,
+	HNS_ROCE_OPC_QUERY_PF_CAPS_NUM                  = 0x8408,
 	HNS_ROCE_OPC_CFG_SGID_TB			= 0x8500,
 	HNS_ROCE_OPC_CFG_SMAC_TB			= 0x8501,
 	HNS_ROCE_OPC_POST_MB				= 0x8504,
@@ -643,7 +651,7 @@ struct hns_roce_v2_qp_context {
 #define	V2_QPC_BYTE_76_ATE_S 27
 
 #define	V2_QPC_BYTE_76_RQIE_S 28
-
+#define	V2_QPC_BYTE_76_EXT_ATE_S 29
 #define	V2_QPC_BYTE_76_RQ_VLAN_EN_S 30
 #define	V2_QPC_BYTE_80_RX_CQN_S 0
 #define V2_QPC_BYTE_80_RX_CQN_M GENMASK(23, 0)
@@ -1569,6 +1577,155 @@ struct hns_roce_cfg_smac_tb {
 #define CFG_SMAC_TB_VF_SMAC_H_S 0
 #define CFG_SMAC_TB_VF_SMAC_H_M GENMASK(15, 0)
 
+#define HNS_ROCE_QUERY_PF_CAPS_CMD_NUM 5
+struct hns_roce_query_pf_caps_a {
+	u8 number_ports;
+	u8 local_ca_ack_delay;
+	__le16 max_sq_sg;
+	__le16 max_sq_inline;
+	__le16 max_rq_sg;
+	__le32 max_extend_sg;
+	__le16 num_qpc_timer;
+	__le16 num_cqc_timer;
+	__le16 max_srq_sges;
+	u8 num_aeq_vectors;
+	u8 num_other_vectors;
+	u8 max_sq_desc_sz;
+	u8 max_rq_desc_sz;
+	u8 max_srq_desc_sz;
+	u8 cq_entry_sz;
+};
+
+struct hns_roce_query_pf_caps_b {
+	u8 mtpt_entry_sz;
+	u8 irrl_entry_sz;
+	u8 trrl_entry_sz;
+	u8 cqc_entry_sz;
+	u8 srqc_entry_sz;
+	u8 idx_entry_sz;
+	u8 scc_ctx_entry_sz;
+	u8 max_mtu;
+	__le16 qpc_entry_sz;
+	__le16 qpc_timer_entry_sz;
+	__le16 cqc_timer_entry_sz;
+	u8 min_cqes;
+	u8 min_wqes;
+	__le32 page_size_cap;
+	u8 pkey_table_len;
+	u8 phy_num_uars;
+	u8 ctx_hop_num;
+	u8 pbl_hop_num;
+};
+
+struct hns_roce_query_pf_caps_c {
+	__le32 cap_flags_num_pds;
+	__le32 max_gid_num_cqs;
+	__le32 cq_depth;
+	__le32 num_mrws;
+	__le32 ord_num_qps;
+	__le16 sq_depth;
+	__le16 rq_depth;
+};
+
+#define V2_QUERY_PF_CAPS_C_NUM_PDS_S 0
+#define V2_QUERY_PF_CAPS_C_NUM_PDS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_C_CAP_FLAGS_S 20
+#define V2_QUERY_PF_CAPS_C_CAP_FLAGS_M GENMASK(31, 20)
+
+#define V2_QUERY_PF_CAPS_C_NUM_CQS_S 0
+#define V2_QUERY_PF_CAPS_C_NUM_CQS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_C_MAX_GID_S 20
+#define V2_QUERY_PF_CAPS_C_MAX_GID_M GENMASK(28, 20)
+
+#define V2_QUERY_PF_CAPS_C_CQ_DEPTH_S 0
+#define V2_QUERY_PF_CAPS_C_CQ_DEPTH_M GENMASK(22, 0)
+
+#define V2_QUERY_PF_CAPS_C_NUM_MRWS_S 0
+#define V2_QUERY_PF_CAPS_C_NUM_MRWS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_C_NUM_QPS_S 0
+#define V2_QUERY_PF_CAPS_C_NUM_QPS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_C_MAX_ORD_S 20
+#define V2_QUERY_PF_CAPS_C_MAX_ORD_M GENMASK(27, 20)
+
+struct hns_roce_query_pf_caps_d {
+	__le32 wq_hop_num_max_srqs;
+	__le16 srq_depth;
+	__le16 rsv;
+	__le32 num_ceqs_ceq_depth;
+	__le32 arm_st_aeq_depth;
+	__le32 num_uars_rsv_pds;
+	__le32 rsv_uars_rsv_qps;
+};
+#define V2_QUERY_PF_CAPS_D_NUM_SRQS_S 0
+#define V2_QUERY_PF_CAPS_D_NUM_SRQS_M GENMASK(20, 0)
+
+#define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_S 20
+#define V2_QUERY_PF_CAPS_D_RQWQE_HOP_NUM_M GENMASK(21, 20)
+
+#define V2_QUERY_PF_CAPS_D_EX_SGE_HOP_NUM_S 22
+#define V2_QUERY_PF_CAPS_D_EX_SGE_HOP_NUM_M GENMASK(23, 22)
+
+#define V2_QUERY_PF_CAPS_D_SQWQE_HOP_NUM_S 24
+#define V2_QUERY_PF_CAPS_D_SQWQE_HOP_NUM_M GENMASK(25, 24)
+
+
+#define V2_QUERY_PF_CAPS_D_CEQ_DEPTH_S 0
+#define V2_QUERY_PF_CAPS_D_CEQ_DEPTH_M GENMASK(21, 0)
+
+#define V2_QUERY_PF_CAPS_D_NUM_CEQS_S 22
+#define V2_QUERY_PF_CAPS_D_NUM_CEQS_M GENMASK(31, 22)
+
+#define V2_QUERY_PF_CAPS_D_AEQ_DEPTH_S 0
+#define V2_QUERY_PF_CAPS_D_AEQ_DEPTH_M GENMASK(21, 0)
+
+#define V2_QUERY_PF_CAPS_D_AEQ_ARM_ST_S 22
+#define V2_QUERY_PF_CAPS_D_AEQ_ARM_ST_M GENMASK(23, 22)
+
+#define V2_QUERY_PF_CAPS_D_CEQ_ARM_ST_S 24
+#define V2_QUERY_PF_CAPS_D_CEQ_ARM_ST_M GENMASK(25, 24)
+
+#define V2_QUERY_PF_CAPS_D_RSV_PDS_S 0
+#define V2_QUERY_PF_CAPS_D_RSV_PDS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_D_NUM_UARS_S 20
+#define V2_QUERY_PF_CAPS_D_NUM_UARS_M GENMASK(27, 20)
+
+#define V2_QUERY_PF_CAPS_D_RSV_QPS_S 0
+#define V2_QUERY_PF_CAPS_D_RSV_QPS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_D_RSV_UARS_S 20
+#define V2_QUERY_PF_CAPS_D_RSV_UARS_M GENMASK(27, 20)
+
+struct hns_roce_query_pf_caps_e {
+	__le32 chunk_size_shift_rsv_mrws;
+	__le32 rsv_cqs;
+	__le32 rsv_srqs;
+	__le32 rsv_lkey;
+	__le16 ceq_max_cnt;
+	__le16 ceq_period;
+	__le16 aeq_max_cnt;
+	__le16 aeq_period;
+};
+
+#define V2_QUERY_PF_CAPS_E_RSV_MRWS_S 0
+#define V2_QUERY_PF_CAPS_E_RSV_MRWS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_E_CHUNK_SIZE_SHIFT_S 20
+#define V2_QUERY_PF_CAPS_E_CHUNK_SIZE_SHIFT_M GENMASK(31, 20)
+
+#define V2_QUERY_PF_CAPS_E_RSV_CQS_S 0
+#define V2_QUERY_PF_CAPS_E_RSV_CQS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_E_RSV_SRQS_S 0
+#define V2_QUERY_PF_CAPS_E_RSV_SRQS_M GENMASK(19, 0)
+
+#define V2_QUERY_PF_CAPS_E_RSV_LKEYS_S 0
+#define V2_QUERY_PF_CAPS_E_RSV_LKEYS_M GENMASK(19, 0)
+
 struct hns_roce_cmq_desc {
 	__le16 opcode;
 	__le16 flag;
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index 854ef6e74788..d0031d559213 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -90,7 +90,7 @@ static int hns_roce_add_gid(const struct ib_gid_attr *attr, void **context)
 static int hns_roce_del_gid(const struct ib_gid_attr *attr, void **context)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(attr->device);
-	struct ib_gid_attr zattr = { };
+	struct ib_gid_attr zattr = {};
 	u8 port = attr->port_num - 1;
 	int ret;
 
@@ -210,7 +210,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
 	props->max_pkeys = 1;
 	props->local_ca_ack_delay = hr_dev->caps.local_ca_ack_delay;
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) {
-		props->max_srq = hr_dev->caps.max_srqs;
+		props->max_srq = hr_dev->caps.num_srqs;
 		props->max_srq_wr = hr_dev->caps.max_srq_wrs;
 		props->max_srq_sge = hr_dev->caps.max_srq_sges;
 	}
@@ -259,11 +259,12 @@ static int hns_roce_query_port(struct ib_device *ib_dev, u8 port_num,
 
 	mtu = iboe_get_mtu(net_dev->mtu);
 	props->active_mtu = mtu ? min(props->max_mtu, mtu) : IB_MTU_256;
-	props->state = (netif_running(net_dev) && netif_carrier_ok(net_dev)) ?
-			IB_PORT_ACTIVE : IB_PORT_DOWN;
-	props->phys_state = (props->state == IB_PORT_ACTIVE) ?
-			     IB_PORT_PHYS_STATE_LINK_UP :
-			     IB_PORT_PHYS_STATE_DISABLED;
+	props->state = netif_running(net_dev) && netif_carrier_ok(net_dev) ?
+			       IB_PORT_ACTIVE :
+			       IB_PORT_DOWN;
+	props->phys_state = props->state == IB_PORT_ACTIVE ?
+				    IB_PORT_PHYS_STATE_LINK_UP :
+				    IB_PORT_PHYS_STATE_DISABLED;
 
 	spin_unlock_irqrestore(&hr_dev->iboe.lock, flags);
 
@@ -481,13 +482,13 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 
 	ib_dev = &hr_dev->ib_dev;
 
-	ib_dev->node_type		= RDMA_NODE_IB_CA;
-	ib_dev->dev.parent		= dev;
+	ib_dev->node_type = RDMA_NODE_IB_CA;
+	ib_dev->dev.parent = dev;
 
-	ib_dev->phys_port_cnt		= hr_dev->caps.num_ports;
-	ib_dev->local_dma_lkey		= hr_dev->caps.reserved_lkey;
-	ib_dev->num_comp_vectors	= hr_dev->caps.num_comp_vectors;
-	ib_dev->uverbs_cmd_mask		=
+	ib_dev->phys_port_cnt = hr_dev->caps.num_ports;
+	ib_dev->local_dma_lkey = hr_dev->caps.reserved_lkey;
+	ib_dev->num_comp_vectors = hr_dev->caps.num_comp_vectors;
+	ib_dev->uverbs_cmd_mask =
 		(1ULL << IB_USER_VERBS_CMD_GET_CONTEXT) |
 		(1ULL << IB_USER_VERBS_CMD_QUERY_DEVICE) |
 		(1ULL << IB_USER_VERBS_CMD_QUERY_PORT) |
@@ -503,8 +504,7 @@ static int hns_roce_register_device(struct hns_roce_dev *hr_dev)
 		(1ULL << IB_USER_VERBS_CMD_QUERY_QP) |
 		(1ULL << IB_USER_VERBS_CMD_DESTROY_QP);
 
-	ib_dev->uverbs_ex_cmd_mask |=
-		(1ULL << IB_USER_VERBS_EX_CMD_MODIFY_CQ);
+	ib_dev->uverbs_ex_cmd_mask |= (1ULL << IB_USER_VERBS_EX_CMD_MODIFY_CQ);
 
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_REREG_MR) {
 		ib_dev->uverbs_cmd_mask |= (1ULL << IB_USER_VERBS_CMD_REREG_MR);
@@ -589,11 +589,13 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 
 	if (hns_roce_check_whether_mhop(hr_dev, HEM_TYPE_CQE)) {
 		ret = hns_roce_init_hem_table(hr_dev,
-				      &hr_dev->mr_table.mtt_cqe_table,
-				      HEM_TYPE_CQE, hr_dev->caps.mtt_entry_sz,
-				      hr_dev->caps.num_cqe_segs, 1);
+					      &hr_dev->mr_table.mtt_cqe_table,
+					      HEM_TYPE_CQE,
+					      hr_dev->caps.mtt_entry_sz,
+					      hr_dev->caps.num_cqe_segs, 1);
 		if (ret) {
-			dev_err(dev, "Failed to init MTT CQE context memory, aborting.\n");
+			dev_err(dev,
+				"Failed to init CQE context memory, aborting.\n");
 			goto err_unmap_cqe;
 		}
 	}
@@ -633,7 +635,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 					      hr_dev->caps.num_qps, 1);
 		if (ret) {
 			dev_err(dev,
-			       "Failed to init trrl_table memory, aborting.\n");
+				"Failed to init trrl_table memory, aborting.\n");
 			goto err_unmap_irrl;
 		}
 	}
@@ -653,7 +655,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 					      hr_dev->caps.num_srqs, 1);
 		if (ret) {
 			dev_err(dev,
-			      "Failed to init SRQ context memory, aborting.\n");
+				"Failed to init SRQ context memory, aborting.\n");
 			goto err_unmap_cq;
 		}
 	}
@@ -692,33 +694,31 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 					      hr_dev->caps.num_qps, 1);
 		if (ret) {
 			dev_err(dev,
-			      "Failed to init SCC context memory, aborting.\n");
+				"Failed to init SCC context memory, aborting.\n");
 			goto err_unmap_idx;
 		}
 	}
 
 	if (hr_dev->caps.qpc_timer_entry_sz) {
-		ret = hns_roce_init_hem_table(hr_dev,
-					      &hr_dev->qpc_timer_table,
+		ret = hns_roce_init_hem_table(hr_dev, &hr_dev->qpc_timer_table,
 					      HEM_TYPE_QPC_TIMER,
 					      hr_dev->caps.qpc_timer_entry_sz,
 					      hr_dev->caps.num_qpc_timer, 1);
 		if (ret) {
 			dev_err(dev,
-			      "Failed to init QPC timer memory, aborting.\n");
+				"Failed to init QPC timer memory, aborting.\n");
 			goto err_unmap_ctx;
 		}
 	}
 
 	if (hr_dev->caps.cqc_timer_entry_sz) {
-		ret = hns_roce_init_hem_table(hr_dev,
-					      &hr_dev->cqc_timer_table,
+		ret = hns_roce_init_hem_table(hr_dev, &hr_dev->cqc_timer_table,
 					      HEM_TYPE_CQC_TIMER,
 					      hr_dev->caps.cqc_timer_entry_sz,
 					      hr_dev->caps.num_cqc_timer, 1);
 		if (ret) {
 			dev_err(dev,
-			      "Failed to init CQC timer memory, aborting.\n");
+				"Failed to init CQC timer memory, aborting.\n");
 			goto err_unmap_qpc_timer;
 		}
 	}
@@ -727,8 +727,7 @@ static int hns_roce_init_hem(struct hns_roce_dev *hr_dev)
 
 err_unmap_qpc_timer:
 	if (hr_dev->caps.qpc_timer_entry_sz)
-		hns_roce_cleanup_hem_table(hr_dev,
-					   &hr_dev->qpc_timer_table);
+		hns_roce_cleanup_hem_table(hr_dev, &hr_dev->qpc_timer_table);
 
 err_unmap_ctx:
 	if (hr_dev->caps.sccc_entry_sz)
@@ -863,6 +862,50 @@ err_uar_table_free:
 	return ret;
 }
 
+static void check_and_get_armed_cq(struct list_head *cq_list, struct ib_cq *cq)
+{
+	struct hns_roce_cq *hr_cq = to_hr_cq(cq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&hr_cq->lock, flags);
+	if (cq->comp_handler) {
+		if (!hr_cq->is_armed) {
+			hr_cq->is_armed = 1;
+			list_add_tail(&hr_cq->node, cq_list);
+		}
+	}
+	spin_unlock_irqrestore(&hr_cq->lock, flags);
+}
+
+void hns_roce_handle_device_err(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_qp *hr_qp;
+	struct hns_roce_cq *hr_cq;
+	struct list_head cq_list;
+	unsigned long flags_qp;
+	unsigned long flags;
+
+	INIT_LIST_HEAD(&cq_list);
+
+	spin_lock_irqsave(&hr_dev->qp_list_lock, flags);
+	list_for_each_entry(hr_qp, &hr_dev->qp_list, node) {
+		spin_lock_irqsave(&hr_qp->sq.lock, flags_qp);
+		if (hr_qp->sq.tail != hr_qp->sq.head)
+			check_and_get_armed_cq(&cq_list, hr_qp->ibqp.send_cq);
+		spin_unlock_irqrestore(&hr_qp->sq.lock, flags_qp);
+
+		spin_lock_irqsave(&hr_qp->rq.lock, flags_qp);
+		if ((!hr_qp->ibqp.srq) && (hr_qp->rq.tail != hr_qp->rq.head))
+			check_and_get_armed_cq(&cq_list, hr_qp->ibqp.recv_cq);
+		spin_unlock_irqrestore(&hr_qp->rq.lock, flags_qp);
+	}
+
+	list_for_each_entry(hr_cq, &cq_list, node)
+		hns_roce_cq_completion(hr_dev, hr_cq->cqn);
+
+	spin_unlock_irqrestore(&hr_dev->qp_list_lock, flags);
+}
+
 int hns_roce_init(struct hns_roce_dev *hr_dev)
 {
 	int ret;
@@ -933,6 +976,9 @@ int hns_roce_init(struct hns_roce_dev *hr_dev)
 		}
 	}
 
+	INIT_LIST_HEAD(&hr_dev->qp_list);
+	spin_lock_init(&hr_dev->qp_list_lock);
+
 	ret = hns_roce_register_device(hr_dev);
 	if (ret)
 		goto error_failed_register_device;
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 3ff610549c74..b9898e71655a 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -1064,8 +1064,8 @@ int hns_roce_ib_umem_write_mtt(struct hns_roce_dev *hr_dev,
 		if (!(npage % (1 << (mtt->page_shift - PAGE_SHIFT)))) {
 			if (page_addr & ((1 << mtt->page_shift) - 1)) {
 				dev_err(dev,
-					"page_addr 0x%llx is not page_shift %d alignment!\n",
-					page_addr, mtt->page_shift);
+					"page_addr is not page_shift %d alignment!\n",
+					mtt->page_shift);
 				ret = -EINVAL;
 				goto out;
 			}
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index eb2ee6a581aa..3257ad11be48 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -393,40 +393,38 @@ static int hns_roce_set_user_sq_size(struct hns_roce_dev *hr_dev,
 
 	/* Get buf size, SQ and RQ  are aligned to page_szie */
 	if (hr_dev->caps.max_sq_sg <= 2) {
-		hr_qp->buff_size = HNS_ROCE_ALIGN_UP((hr_qp->rq.wqe_cnt <<
+		hr_qp->buff_size = round_up((hr_qp->rq.wqe_cnt <<
 					     hr_qp->rq.wqe_shift), PAGE_SIZE) +
-				   HNS_ROCE_ALIGN_UP((hr_qp->sq.wqe_cnt <<
+				   round_up((hr_qp->sq.wqe_cnt <<
 					     hr_qp->sq.wqe_shift), PAGE_SIZE);
 
 		hr_qp->sq.offset = 0;
-		hr_qp->rq.offset = HNS_ROCE_ALIGN_UP((hr_qp->sq.wqe_cnt <<
+		hr_qp->rq.offset = round_up((hr_qp->sq.wqe_cnt <<
 					     hr_qp->sq.wqe_shift), PAGE_SIZE);
 	} else {
 		page_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + PAGE_SHIFT);
 		hr_qp->sge.sge_cnt = ex_sge_num ?
 		   max(page_size / (1 << hr_qp->sge.sge_shift), ex_sge_num) : 0;
-		hr_qp->buff_size = HNS_ROCE_ALIGN_UP((hr_qp->rq.wqe_cnt <<
+		hr_qp->buff_size = round_up((hr_qp->rq.wqe_cnt <<
 					     hr_qp->rq.wqe_shift), page_size) +
-				   HNS_ROCE_ALIGN_UP((hr_qp->sge.sge_cnt <<
+				   round_up((hr_qp->sge.sge_cnt <<
 					     hr_qp->sge.sge_shift), page_size) +
-				   HNS_ROCE_ALIGN_UP((hr_qp->sq.wqe_cnt <<
+				   round_up((hr_qp->sq.wqe_cnt <<
 					     hr_qp->sq.wqe_shift), page_size);
 
 		hr_qp->sq.offset = 0;
 		if (ex_sge_num) {
-			hr_qp->sge.offset = HNS_ROCE_ALIGN_UP(
-							(hr_qp->sq.wqe_cnt <<
-							hr_qp->sq.wqe_shift),
-							page_size);
+			hr_qp->sge.offset = round_up((hr_qp->sq.wqe_cnt <<
+						      hr_qp->sq.wqe_shift),
+						     page_size);
 			hr_qp->rq.offset = hr_qp->sge.offset +
-					HNS_ROCE_ALIGN_UP((hr_qp->sge.sge_cnt <<
-						hr_qp->sge.sge_shift),
-						page_size);
+					   round_up((hr_qp->sge.sge_cnt <<
+						     hr_qp->sge.sge_shift),
+						    page_size);
 		} else {
-			hr_qp->rq.offset = HNS_ROCE_ALIGN_UP(
-							(hr_qp->sq.wqe_cnt <<
-							hr_qp->sq.wqe_shift),
-							page_size);
+			hr_qp->rq.offset = round_up((hr_qp->sq.wqe_cnt <<
+						     hr_qp->sq.wqe_shift),
+						    page_size);
 		}
 	}
 
@@ -593,20 +591,18 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev,
 	/* Get buf size, SQ and RQ are aligned to PAGE_SIZE */
 	page_size = 1 << (hr_dev->caps.mtt_buf_pg_sz + PAGE_SHIFT);
 	hr_qp->sq.offset = 0;
-	size = HNS_ROCE_ALIGN_UP(hr_qp->sq.wqe_cnt << hr_qp->sq.wqe_shift,
-				 page_size);
+	size = round_up(hr_qp->sq.wqe_cnt << hr_qp->sq.wqe_shift, page_size);
 
 	if (hr_dev->caps.max_sq_sg > 2 && hr_qp->sge.sge_cnt) {
 		hr_qp->sge.sge_cnt = max(page_size/(1 << hr_qp->sge.sge_shift),
-					(u32)hr_qp->sge.sge_cnt);
+					 (u32)hr_qp->sge.sge_cnt);
 		hr_qp->sge.offset = size;
-		size += HNS_ROCE_ALIGN_UP(hr_qp->sge.sge_cnt <<
-					  hr_qp->sge.sge_shift, page_size);
+		size += round_up(hr_qp->sge.sge_cnt << hr_qp->sge.sge_shift,
+				 page_size);
 	}
 
 	hr_qp->rq.offset = size;
-	size += HNS_ROCE_ALIGN_UP((hr_qp->rq.wqe_cnt << hr_qp->rq.wqe_shift),
-				  page_size);
+	size += round_up((hr_qp->rq.wqe_cnt << hr_qp->rq.wqe_shift), page_size);
 	hr_qp->buff_size = size;
 
 	/* Get wr and sge number which send */
@@ -681,6 +677,29 @@ static void free_rq_inline_buf(struct hns_roce_qp *hr_qp)
 	kfree(hr_qp->rq_inl_buf.wqe_list);
 }
 
+static void add_qp_to_list(struct hns_roce_dev *hr_dev,
+			   struct hns_roce_qp *hr_qp,
+			   struct ib_cq *send_cq, struct ib_cq *recv_cq)
+{
+	struct hns_roce_cq *hr_send_cq, *hr_recv_cq;
+	unsigned long flags;
+
+	hr_send_cq = send_cq ? to_hr_cq(send_cq) : NULL;
+	hr_recv_cq = recv_cq ? to_hr_cq(recv_cq) : NULL;
+
+	spin_lock_irqsave(&hr_dev->qp_list_lock, flags);
+	hns_roce_lock_cqs(hr_send_cq, hr_recv_cq);
+
+	list_add_tail(&hr_qp->node, &hr_dev->qp_list);
+	if (hr_send_cq)
+		list_add_tail(&hr_qp->sq_node, &hr_send_cq->sq_list);
+	if (hr_recv_cq)
+		list_add_tail(&hr_qp->rq_node, &hr_recv_cq->rq_list);
+
+	hns_roce_unlock_cqs(hr_send_cq, hr_recv_cq);
+	spin_unlock_irqrestore(&hr_dev->qp_list_lock, flags);
+}
+
 static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 				     struct ib_pd *ib_pd,
 				     struct ib_qp_init_attr *init_attr,
@@ -950,6 +969,9 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 	}
 
 	hr_qp->event = hns_roce_ib_qp_event;
+
+	add_qp_to_list(hr_dev, hr_qp, init_attr->send_cq, init_attr->recv_cq);
+
 	hns_roce_free_buf_list(buf_list, hr_qp->region_cnt);
 
 	return 0;
@@ -1232,7 +1254,16 @@ out:
 void hns_roce_lock_cqs(struct hns_roce_cq *send_cq, struct hns_roce_cq *recv_cq)
 		       __acquires(&send_cq->lock) __acquires(&recv_cq->lock)
 {
-	if (send_cq == recv_cq) {
+	if (unlikely(send_cq == NULL && recv_cq == NULL)) {
+		__acquire(&send_cq->lock);
+		__acquire(&recv_cq->lock);
+	} else if (unlikely(send_cq != NULL && recv_cq == NULL)) {
+		spin_lock_irq(&send_cq->lock);
+		__acquire(&recv_cq->lock);
+	} else if (unlikely(send_cq == NULL && recv_cq != NULL)) {
+		spin_lock_irq(&recv_cq->lock);
+		__acquire(&send_cq->lock);
+	} else if (send_cq == recv_cq) {
 		spin_lock_irq(&send_cq->lock);
 		__acquire(&recv_cq->lock);
 	} else if (send_cq->cqn < recv_cq->cqn) {
@@ -1248,7 +1279,16 @@ void hns_roce_unlock_cqs(struct hns_roce_cq *send_cq,
 			 struct hns_roce_cq *recv_cq) __releases(&send_cq->lock)
 			 __releases(&recv_cq->lock)
 {
-	if (send_cq == recv_cq) {
+	if (unlikely(send_cq == NULL && recv_cq == NULL)) {
+		__release(&recv_cq->lock);
+		__release(&send_cq->lock);
+	} else if (unlikely(send_cq != NULL && recv_cq == NULL)) {
+		__release(&recv_cq->lock);
+		spin_unlock(&send_cq->lock);
+	} else if (unlikely(send_cq == NULL && recv_cq != NULL)) {
+		__release(&send_cq->lock);
+		spin_unlock(&recv_cq->lock);
+	} else if (send_cq == recv_cq) {
 		__release(&recv_cq->lock);
 		spin_unlock_irq(&send_cq->lock);
 	} else if (send_cq->cqn < recv_cq->cqn) {
diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c
index d44cf33df81a..238614370927 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_main.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_main.c
@@ -1225,6 +1225,8 @@ static void i40iw_add_ipv4_addr(struct i40iw_device *iwdev)
 			const struct in_ifaddr *ifa;
 
 			idev = in_dev_get(dev);
+			if (!idev)
+				continue;
 			in_dev_for_each_ifa_rtnl(ifa, idev) {
 				i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_CM,
 					    "IP=%pI4, vlan_id=%d, MAC=%pM\n", &ifa->ifa_address,
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index ecd6cadd529a..b591861934b3 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -186,23 +186,6 @@ out:
 	kfree(ent);
 }
 
-static void id_map_find_del(struct ib_device *ibdev, int pv_cm_id)
-{
-	struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
-	struct rb_root *sl_id_map = &sriov->sl_id_map;
-	struct id_map_entry *ent, *found_ent;
-
-	spin_lock(&sriov->id_map_lock);
-	ent = xa_erase(&sriov->pv_id_table, pv_cm_id);
-	if (!ent)
-		goto out;
-	found_ent = id_map_find_by_sl_id(ibdev, ent->slave_id, ent->sl_cm_id);
-	if (found_ent && found_ent == ent)
-		rb_erase(&found_ent->node, sl_id_map);
-out:
-	spin_unlock(&sriov->id_map_lock);
-}
-
 static void sl_id_map_add(struct ib_device *ibdev, struct id_map_entry *new)
 {
 	struct rb_root *sl_id_map = &to_mdev(ibdev)->sriov.sl_id_map;
@@ -294,7 +277,7 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
 	spin_lock(&sriov->id_map_lock);
 	spin_lock_irqsave(&sriov->going_down_lock, flags);
 	/*make sure that there is no schedule inside the scheduled work.*/
-	if (!sriov->is_going_down) {
+	if (!sriov->is_going_down && !id->scheduled_delete) {
 		id->scheduled_delete = 1;
 		schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
 	}
@@ -341,9 +324,6 @@ cont:
 
 	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
 		schedule_delayed(ibdev, id);
-	else if (mad->mad_hdr.attr_id == CM_DREP_ATTR_ID)
-		id_map_find_del(ibdev, pv_cm_id);
-
 	return 0;
 }
 
@@ -382,12 +362,9 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
 		*slave = id->slave_id;
 	set_remote_comm_id(mad, id->sl_cm_id);
 
-	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
+	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID ||
+	    mad->mad_hdr.attr_id == CM_REJ_ATTR_ID)
 		schedule_delayed(ibdev, id);
-	else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID ||
-			mad->mad_hdr.attr_id == CM_DREP_ATTR_ID) {
-		id_map_find_del(ibdev, (int) pv_cm_id);
-	}
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index a57033d4b0e5..f8b936b76dcd 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -568,18 +568,13 @@ static void mlx4_ib_handle_error_cqe(struct mlx4_err_cqe *cqe,
 	wc->vendor_err = cqe->vendor_err_syndrome;
 }
 
-static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum)
+static int mlx4_ib_ipoib_csum_ok(__be16 status, u8 badfcs_enc, __be16 checksum)
 {
-	return ((status & cpu_to_be16(MLX4_CQE_STATUS_IPV4      |
-				      MLX4_CQE_STATUS_IPV4F     |
-				      MLX4_CQE_STATUS_IPV4OPT   |
-				      MLX4_CQE_STATUS_IPV6      |
-				      MLX4_CQE_STATUS_IPOK)) ==
-		cpu_to_be16(MLX4_CQE_STATUS_IPV4        |
-			    MLX4_CQE_STATUS_IPOK))              &&
-		(status & cpu_to_be16(MLX4_CQE_STATUS_UDP       |
-				      MLX4_CQE_STATUS_TCP))     &&
-		checksum == cpu_to_be16(0xffff);
+	return ((badfcs_enc & MLX4_CQE_STATUS_L4_CSUM) ||
+		((status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
+		 (status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
+				       MLX4_CQE_STATUS_UDP)) &&
+		 (checksum == cpu_to_be16(0xffff))));
 }
 
 static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
@@ -855,6 +850,7 @@ repoll:
 		wc->wc_flags	  |= g_mlpath_rqpn & 0x80000000 ? IB_WC_GRH : 0;
 		wc->pkey_index     = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
 		wc->wc_flags	  |= mlx4_ib_ipoib_csum_ok(cqe->status,
+					cqe->badfcs_enc,
 					cqe->checksum) ? IB_WC_IP_CSUM_OK : 0;
 		if (is_eth) {
 			wc->slid = 0;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 34055cbab38c..2f5d9b181848 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -246,6 +246,13 @@ static int mlx4_ib_update_gids(struct gid_entry *gids,
 	return mlx4_ib_update_gids_v1(gids, ibdev, port_num);
 }
 
+static void free_gid_entry(struct gid_entry *entry)
+{
+	memset(&entry->gid, 0, sizeof(entry->gid));
+	kfree(entry->ctx);
+	entry->ctx = NULL;
+}
+
 static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(attr->device);
@@ -313,6 +320,8 @@ static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 				     GFP_ATOMIC);
 		if (!gids) {
 			ret = -ENOMEM;
+			*context = NULL;
+			free_gid_entry(&port_gid_table->gids[free]);
 		} else {
 			for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
 				memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
@@ -324,6 +333,12 @@ static int mlx4_ib_add_gid(const struct ib_gid_attr *attr, void **context)
 
 	if (!ret && hw_update) {
 		ret = mlx4_ib_update_gids(gids, ibdev, attr->port_num);
+		if (ret) {
+			spin_lock_bh(&iboe->lock);
+			*context = NULL;
+			free_gid_entry(&port_gid_table->gids[free]);
+			spin_unlock_bh(&iboe->lock);
+		}
 		kfree(gids);
 	}
 
@@ -353,10 +368,7 @@ static int mlx4_ib_del_gid(const struct ib_gid_attr *attr, void **context)
 		if (!ctx->refcount) {
 			unsigned int real_index = ctx->real_index;
 
-			memset(&port_gid_table->gids[real_index].gid, 0,
-			       sizeof(port_gid_table->gids[real_index].gid));
-			kfree(port_gid_table->gids[real_index].ctx);
-			port_gid_table->gids[real_index].ctx = NULL;
+			free_gid_entry(&port_gid_table->gids[real_index]);
 			hw_update = 1;
 		}
 	}
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index cb23cdb9389a..26425dd2d960 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -849,7 +849,7 @@ static void mlx4_ib_release_wqn(struct mlx4_ib_ucontext *context,
 	 * reused for further WQN allocations.
 	 * The next created WQ will allocate a new range.
 	 */
-		range->dirty = 1;
+		range->dirty = true;
 	}
 
 	mutex_unlock(&context->wqn_ranges_mutex);
@@ -3085,7 +3085,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr,
 		}
 		if (ah->av.eth.vlan != cpu_to_be16(0xffff)) {
 			vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
-			is_vlan = 1;
+			is_vlan = true;
 		}
 	}
 	err = ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh,
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 685b8ed96b4e..d7efc9f6daf0 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -30,7 +30,7 @@ enum devx_obj_flags {
 struct devx_async_data {
 	struct mlx5_ib_dev *mdev;
 	struct list_head list;
-	struct ib_uobject *fd_uobj;
+	struct devx_async_cmd_event_file *ev_file;
 	struct mlx5_async_work cb_work;
 	u16 cmd_out_len;
 	/* must be last field in this structure */
@@ -72,7 +72,6 @@ struct devx_event_subscription {
 	struct rcu_head	rcu;
 	u64 cookie;
 	struct devx_async_event_file *ev_file;
-	struct file *filp; /* Upon hot unplug we need a direct access to */
 	struct eventfd_ctx *eventfd;
 };
 
@@ -1674,21 +1673,20 @@ static void devx_query_callback(int status, struct mlx5_async_work *context)
 {
 	struct devx_async_data *async_data =
 		container_of(context, struct devx_async_data, cb_work);
-	struct ib_uobject *fd_uobj = async_data->fd_uobj;
-	struct devx_async_cmd_event_file *ev_file;
-	struct devx_async_event_queue *ev_queue;
+	struct devx_async_cmd_event_file *ev_file = async_data->ev_file;
+	struct devx_async_event_queue *ev_queue = &ev_file->ev_queue;
 	unsigned long flags;
 
-	ev_file = container_of(fd_uobj, struct devx_async_cmd_event_file,
-			       uobj);
-	ev_queue = &ev_file->ev_queue;
-
+	/*
+	 * Note that if the struct devx_async_cmd_event_file uobj begins to be
+	 * destroyed it will block at mlx5_cmd_cleanup_async_ctx() until this
+	 * routine returns, ensuring that it always remains valid here.
+	 */
 	spin_lock_irqsave(&ev_queue->lock, flags);
 	list_add_tail(&async_data->list, &ev_queue->event_list);
 	spin_unlock_irqrestore(&ev_queue->lock, flags);
 
 	wake_up_interruptible(&ev_queue->poll_wait);
-	fput(fd_uobj->object);
 }
 
 #define MAX_ASYNC_BYTES_IN_USE (1024 * 1024) /* 1MB */
@@ -1757,9 +1755,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY)(
 
 	async_data->cmd_out_len = cmd_out_len;
 	async_data->mdev = mdev;
-	async_data->fd_uobj = fd_uobj;
+	async_data->ev_file = ev_file;
 
-	get_file(fd_uobj->object);
 	MLX5_SET(general_obj_in_cmd_hdr, cmd_in, uid, uid);
 	err = mlx5_cmd_exec_cb(&ev_file->async_ctx, cmd_in,
 		    uverbs_attr_get_len(attrs,
@@ -1769,12 +1766,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY)(
 		    devx_query_callback, &async_data->cb_work);
 
 	if (err)
-		goto cb_err;
+		goto free_async;
 
 	return 0;
 
-cb_err:
-	fput(fd_uobj->object);
 free_async:
 	kvfree(async_data);
 sub_bytes:
@@ -2032,6 +2027,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)(
 			goto err;
 
 		list_add_tail(&event_sub->event_list, &sub_list);
+		uverbs_uobject_get(&ev_file->uobj);
 		if (use_eventfd) {
 			event_sub->eventfd =
 				eventfd_ctx_fdget(redirect_fd);
@@ -2045,7 +2041,6 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)(
 
 		event_sub->cookie = cookie;
 		event_sub->ev_file = ev_file;
-		event_sub->filp = fd_uobj->object;
 		/* May be needed upon cleanup the devx object/subscription */
 		event_sub->xa_key_level1 = key_level1;
 		event_sub->xa_key_level2 = obj_id;
@@ -2099,7 +2094,7 @@ err:
 
 		if (event_sub->eventfd)
 			eventfd_ctx_put(event_sub->eventfd);
-
+		uverbs_uobject_put(&event_sub->ev_file->uobj);
 		kfree(event_sub);
 	}
 
@@ -2329,6 +2324,9 @@ static int deliver_event(struct devx_event_subscription *event_sub,
 			return 0;
 		}
 
+		/* is_destroyed is ignored here because we don't have any memory
+		 * allocation to clean up for the omit_data case
+		 */
 		list_add_tail(&event_sub->event_list, &ev_file->event_list);
 		spin_unlock_irqrestore(&ev_file->lock, flags);
 		wake_up_interruptible(&ev_file->poll_wait);
@@ -2348,7 +2346,10 @@ static int deliver_event(struct devx_event_subscription *event_sub,
 	memcpy(event_data->hdr.out_data, data, sizeof(struct mlx5_eqe));
 
 	spin_lock_irqsave(&ev_file->lock, flags);
-	list_add_tail(&event_data->list, &ev_file->event_list);
+	if (!ev_file->is_destroyed)
+		list_add_tail(&event_data->list, &ev_file->event_list);
+	else
+		kfree(event_data);
 	spin_unlock_irqrestore(&ev_file->lock, flags);
 	wake_up_interruptible(&ev_file->poll_wait);
 
@@ -2361,17 +2362,10 @@ static void dispatch_event_fd(struct list_head *fd_list,
 	struct devx_event_subscription *item;
 
 	list_for_each_entry_rcu(item, fd_list, xa_list) {
-		if (!get_file_rcu(item->filp))
-			continue;
-
-		if (item->eventfd) {
+		if (item->eventfd)
 			eventfd_signal(item->eventfd, 1);
-			fput(item->filp);
-			continue;
-		}
-
-		deliver_event(item, data);
-		fput(item->filp);
+		else
+			deliver_event(item, data);
 	}
 }
 
@@ -2509,23 +2503,6 @@ static ssize_t devx_async_cmd_event_read(struct file *filp, char __user *buf,
 	return ret;
 }
 
-static int devx_async_cmd_event_close(struct inode *inode, struct file *filp)
-{
-	struct ib_uobject *uobj = filp->private_data;
-	struct devx_async_cmd_event_file *comp_ev_file = container_of(
-		uobj, struct devx_async_cmd_event_file, uobj);
-	struct devx_async_data *entry, *tmp;
-
-	spin_lock_irq(&comp_ev_file->ev_queue.lock);
-	list_for_each_entry_safe(entry, tmp,
-				 &comp_ev_file->ev_queue.event_list, list)
-		kvfree(entry);
-	spin_unlock_irq(&comp_ev_file->ev_queue.lock);
-
-	uverbs_close_fd(filp);
-	return 0;
-}
-
 static __poll_t devx_async_cmd_event_poll(struct file *filp,
 					      struct poll_table_struct *wait)
 {
@@ -2549,7 +2526,7 @@ static const struct file_operations devx_async_cmd_event_fops = {
 	.owner	 = THIS_MODULE,
 	.read	 = devx_async_cmd_event_read,
 	.poll    = devx_async_cmd_event_poll,
-	.release = devx_async_cmd_event_close,
+	.release = uverbs_uobject_fd_release,
 	.llseek	 = no_llseek,
 };
 
@@ -2653,81 +2630,85 @@ static __poll_t devx_async_event_poll(struct file *filp,
 	return pollflags;
 }
 
-static int devx_async_event_close(struct inode *inode, struct file *filp)
+static void devx_free_subscription(struct rcu_head *rcu)
 {
-	struct devx_async_event_file *ev_file = filp->private_data;
-	struct devx_event_subscription *event_sub, *event_sub_tmp;
-	struct devx_async_event_data *entry, *tmp;
-	struct mlx5_ib_dev *dev = ev_file->dev;
-
-	mutex_lock(&dev->devx_event_table.event_xa_lock);
-	/* delete the subscriptions which are related to this FD */
-	list_for_each_entry_safe(event_sub, event_sub_tmp,
-				 &ev_file->subscribed_events_list, file_list) {
-		devx_cleanup_subscription(dev, event_sub);
-		if (event_sub->eventfd)
-			eventfd_ctx_put(event_sub->eventfd);
-
-		list_del_rcu(&event_sub->file_list);
-		/* subscription may not be used by the read API any more */
-		kfree_rcu(event_sub, rcu);
-	}
-
-	mutex_unlock(&dev->devx_event_table.event_xa_lock);
+	struct devx_event_subscription *event_sub =
+		container_of(rcu, struct devx_event_subscription, rcu);
 
-	/* free the pending events allocation */
-	if (!ev_file->omit_data) {
-		spin_lock_irq(&ev_file->lock);
-		list_for_each_entry_safe(entry, tmp,
-					 &ev_file->event_list, list)
-			kfree(entry); /* read can't come any more */
-		spin_unlock_irq(&ev_file->lock);
-	}
-
-	uverbs_close_fd(filp);
-	put_device(&dev->ib_dev.dev);
-	return 0;
+	if (event_sub->eventfd)
+		eventfd_ctx_put(event_sub->eventfd);
+	uverbs_uobject_put(&event_sub->ev_file->uobj);
+	kfree(event_sub);
 }
 
 static const struct file_operations devx_async_event_fops = {
 	.owner	 = THIS_MODULE,
 	.read	 = devx_async_event_read,
 	.poll    = devx_async_event_poll,
-	.release = devx_async_event_close,
+	.release = uverbs_uobject_fd_release,
 	.llseek	 = no_llseek,
 };
 
-static int devx_hot_unplug_async_cmd_event_file(struct ib_uobject *uobj,
-						   enum rdma_remove_reason why)
+static int devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj,
+					     enum rdma_remove_reason why)
 {
 	struct devx_async_cmd_event_file *comp_ev_file =
 		container_of(uobj, struct devx_async_cmd_event_file,
 			     uobj);
 	struct devx_async_event_queue *ev_queue = &comp_ev_file->ev_queue;
+	struct devx_async_data *entry, *tmp;
 
 	spin_lock_irq(&ev_queue->lock);
 	ev_queue->is_destroyed = 1;
 	spin_unlock_irq(&ev_queue->lock);
-
-	if (why == RDMA_REMOVE_DRIVER_REMOVE)
-		wake_up_interruptible(&ev_queue->poll_wait);
+	wake_up_interruptible(&ev_queue->poll_wait);
 
 	mlx5_cmd_cleanup_async_ctx(&comp_ev_file->async_ctx);
+
+	spin_lock_irq(&comp_ev_file->ev_queue.lock);
+	list_for_each_entry_safe(entry, tmp,
+				 &comp_ev_file->ev_queue.event_list, list)
+		kvfree(entry);
+	spin_unlock_irq(&comp_ev_file->ev_queue.lock);
 	return 0;
 };
 
-static int devx_hot_unplug_async_event_file(struct ib_uobject *uobj,
-					    enum rdma_remove_reason why)
+static int devx_async_event_destroy_uobj(struct ib_uobject *uobj,
+					 enum rdma_remove_reason why)
 {
 	struct devx_async_event_file *ev_file =
 		container_of(uobj, struct devx_async_event_file,
 			     uobj);
+	struct devx_event_subscription *event_sub, *event_sub_tmp;
+	struct devx_async_event_data *entry, *tmp;
+	struct mlx5_ib_dev *dev = ev_file->dev;
 
 	spin_lock_irq(&ev_file->lock);
 	ev_file->is_destroyed = 1;
 	spin_unlock_irq(&ev_file->lock);
-
 	wake_up_interruptible(&ev_file->poll_wait);
+
+	mutex_lock(&dev->devx_event_table.event_xa_lock);
+	/* delete the subscriptions which are related to this FD */
+	list_for_each_entry_safe(event_sub, event_sub_tmp,
+				 &ev_file->subscribed_events_list, file_list) {
+		devx_cleanup_subscription(dev, event_sub);
+		list_del_rcu(&event_sub->file_list);
+		/* subscription may not be used by the read API any more */
+		call_rcu(&event_sub->rcu, devx_free_subscription);
+	}
+	mutex_unlock(&dev->devx_event_table.event_xa_lock);
+
+	/* free the pending events allocation */
+	if (!ev_file->omit_data) {
+		spin_lock_irq(&ev_file->lock);
+		list_for_each_entry_safe(entry, tmp,
+					 &ev_file->event_list, list)
+			kfree(entry); /* read can't come any more */
+		spin_unlock_irq(&ev_file->lock);
+	}
+
+	put_device(&dev->ib_dev.dev);
 	return 0;
 };
 
@@ -2913,7 +2894,7 @@ DECLARE_UVERBS_NAMED_METHOD(
 DECLARE_UVERBS_NAMED_OBJECT(
 	MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD,
 	UVERBS_TYPE_ALLOC_FD(sizeof(struct devx_async_cmd_event_file),
-			     devx_hot_unplug_async_cmd_event_file,
+			     devx_async_cmd_event_destroy_uobj,
 			     &devx_async_cmd_event_fops, "[devx_async_cmd]",
 			     O_RDONLY),
 	&UVERBS_METHOD(MLX5_IB_METHOD_DEVX_ASYNC_CMD_FD_ALLOC));
@@ -2931,7 +2912,7 @@ DECLARE_UVERBS_NAMED_METHOD(
 DECLARE_UVERBS_NAMED_OBJECT(
 	MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD,
 	UVERBS_TYPE_ALLOC_FD(sizeof(struct devx_async_event_file),
-			     devx_hot_unplug_async_event_file,
+			     devx_async_event_destroy_uobj,
 			     &devx_async_event_fops, "[devx_async_event]",
 			     O_RDONLY),
 	&UVERBS_METHOD(MLX5_IB_METHOD_DEVX_ASYNC_EVENT_FD_ALLOC));
diff --git a/drivers/infiniband/hw/mlx5/gsi.c b/drivers/infiniband/hw/mlx5/gsi.c
index ac4d8d1b9a07..1ae6fd95acaa 100644
--- a/drivers/infiniband/hw/mlx5/gsi.c
+++ b/drivers/infiniband/hw/mlx5/gsi.c
@@ -507,8 +507,7 @@ int mlx5_ib_gsi_post_send(struct ib_qp *qp, const struct ib_send_wr *wr,
 		ret = ib_post_send(tx_qp, &cur_wr.wr, bad_wr);
 		if (ret) {
 			/* Undo the effect of adding the outstanding wr */
-			gsi->outstanding_pi = (gsi->outstanding_pi - 1) %
-					      gsi->cap.max_send_wr;
+			gsi->outstanding_pi--;
 			goto err;
 		}
 		spin_unlock_irqrestore(&gsi->lock, flags);
diff --git a/drivers/infiniband/hw/mlx5/ib_virt.c b/drivers/infiniband/hw/mlx5/ib_virt.c
index 4f0edd4832bd..b61165359954 100644
--- a/drivers/infiniband/hw/mlx5/ib_virt.c
+++ b/drivers/infiniband/hw/mlx5/ib_virt.c
@@ -164,8 +164,10 @@ static int set_vf_node_guid(struct ib_device *device, int vf, u8 port, u64 guid)
 	in->field_select = MLX5_HCA_VPORT_SEL_NODE_GUID;
 	in->node_guid = guid;
 	err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in);
-	if (!err)
+	if (!err) {
 		vfs_ctx[vf].node_guid = guid;
+		vfs_ctx[vf].node_guid_valid = 1;
+	}
 	kfree(in);
 	return err;
 }
@@ -185,8 +187,10 @@ static int set_vf_port_guid(struct ib_device *device, int vf, u8 port, u64 guid)
 	in->field_select = MLX5_HCA_VPORT_SEL_PORT_GUID;
 	in->port_guid = guid;
 	err = mlx5_core_modify_hca_vport_context(mdev, 1, 1, vf + 1, in);
-	if (!err)
+	if (!err) {
 		vfs_ctx[vf].port_guid = guid;
+		vfs_ctx[vf].port_guid_valid = 1;
+	}
 	kfree(in);
 	return err;
 }
@@ -208,20 +212,12 @@ int mlx5_ib_get_vf_guid(struct ib_device *device, int vf, u8 port,
 {
 	struct mlx5_ib_dev *dev = to_mdev(device);
 	struct mlx5_core_dev *mdev = dev->mdev;
-	struct mlx5_hca_vport_context *rep;
-	int err;
-
-	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
-	if (!rep)
-		return -ENOMEM;
+	struct mlx5_vf_context *vfs_ctx = mdev->priv.sriov.vfs_ctx;
 
-	err = mlx5_query_hca_vport_context(mdev, 1, 1, vf+1, rep);
-	if (err)
-		goto ex;
+	node_guid->guid =
+		vfs_ctx[vf].node_guid_valid ? vfs_ctx[vf].node_guid : 0;
+	port_guid->guid =
+		vfs_ctx[vf].port_guid_valid ? vfs_ctx[vf].port_guid : 0;
 
-	port_guid->guid = rep->port_guid;
-	node_guid->guid = rep->node_guid;
-ex:
-	kfree(rep);
-	return err;
+	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ab4ec33409b8..e874d688d040 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2094,6 +2094,7 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
 {
 	struct mlx5_user_mmap_entry *mentry = to_mmmap(entry);
 	struct mlx5_ib_dev *dev = to_mdev(entry->ucontext->device);
+	struct mlx5_var_table *var_table = &dev->var_table;
 	struct mlx5_ib_dm *mdm;
 
 	switch (mentry->mmap_flag) {
@@ -2103,6 +2104,12 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
 				       mdm->size);
 		kfree(mdm);
 		break;
+	case MLX5_IB_MMAP_TYPE_VAR:
+		mutex_lock(&var_table->bitmap_lock);
+		clear_bit(mentry->page_idx, var_table->bitmap);
+		mutex_unlock(&var_table->bitmap_lock);
+		kfree(mentry);
+		break;
 	default:
 		WARN_ON(true);
 	}
@@ -2262,7 +2269,10 @@ static int mlx5_ib_mmap_offset(struct mlx5_ib_dev *dev,
 
 	mentry = to_mmmap(entry);
 	pfn = (mentry->address >> PAGE_SHIFT);
-	prot = pgprot_writecombine(vma->vm_page_prot);
+	if (mentry->mmap_flag == MLX5_IB_MMAP_TYPE_VAR)
+		prot = pgprot_noncached(vma->vm_page_prot);
+	else
+		prot = pgprot_writecombine(vma->vm_page_prot);
 	ret = rdma_user_mmap_io(ucontext, vma, pfn,
 				entry->npages * PAGE_SIZE,
 				prot,
@@ -2271,6 +2281,15 @@ static int mlx5_ib_mmap_offset(struct mlx5_ib_dev *dev,
 	return ret;
 }
 
+static u64 mlx5_entry_to_mmap_offset(struct mlx5_user_mmap_entry *entry)
+{
+	u16 cmd = entry->rdma_entry.start_pgoff >> 16;
+	u16 index = entry->rdma_entry.start_pgoff & 0xFFFF;
+
+	return (((index >> 8) << 16) | (cmd << MLX5_IB_MMAP_CMD_SHIFT) |
+		(index & 0xFF)) << PAGE_SHIFT;
+}
+
 static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
 {
 	struct mlx5_ib_ucontext *context = to_mucontext(ibcontext);
@@ -5368,6 +5387,14 @@ static const struct mlx5_ib_counter extended_err_cnts[] = {
 	INIT_Q_COUNTER(req_cqe_flush_error),
 };
 
+static const struct mlx5_ib_counter roce_accl_cnts[] = {
+	INIT_Q_COUNTER(roce_adp_retrans),
+	INIT_Q_COUNTER(roce_adp_retrans_to),
+	INIT_Q_COUNTER(roce_slow_restart),
+	INIT_Q_COUNTER(roce_slow_restart_cnps),
+	INIT_Q_COUNTER(roce_slow_restart_trans),
+};
+
 #define INIT_EXT_PPCNT_COUNTER(_name)		\
 	{ .name = #_name, .offset =	\
 	MLX5_BYTE_OFF(ppcnt_reg, \
@@ -5416,6 +5443,9 @@ static int __mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev,
 	if (MLX5_CAP_GEN(dev->mdev, enhanced_error_q_counters))
 		num_counters += ARRAY_SIZE(extended_err_cnts);
 
+	if (MLX5_CAP_GEN(dev->mdev, roce_accl))
+		num_counters += ARRAY_SIZE(roce_accl_cnts);
+
 	cnts->num_q_counters = num_counters;
 
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
@@ -5476,6 +5506,13 @@ static void mlx5_ib_fill_counters(struct mlx5_ib_dev *dev,
 		}
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, roce_accl)) {
+		for (i = 0; i < ARRAY_SIZE(roce_accl_cnts); i++, j++) {
+			names[j] = roce_accl_cnts[i].name;
+			offsets[j] = roce_accl_cnts[i].offset;
+		}
+	}
+
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
 		for (i = 0; i < ARRAY_SIZE(cong_cnts); i++, j++) {
 			names[j] = cong_cnts[i].name;
@@ -6051,6 +6088,145 @@ static void mlx5_ib_cleanup_multiport_master(struct mlx5_ib_dev *dev)
 	mlx5_nic_vport_disable_roce(dev->mdev);
 }
 
+static int var_obj_cleanup(struct ib_uobject *uobject,
+			   enum rdma_remove_reason why,
+			   struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_user_mmap_entry *obj = uobject->object;
+
+	rdma_user_mmap_entry_remove(&obj->rdma_entry);
+	return 0;
+}
+
+static struct mlx5_user_mmap_entry *
+alloc_var_entry(struct mlx5_ib_ucontext *c)
+{
+	struct mlx5_user_mmap_entry *entry;
+	struct mlx5_var_table *var_table;
+	u32 page_idx;
+	int err;
+
+	var_table = &to_mdev(c->ibucontext.device)->var_table;
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_lock(&var_table->bitmap_lock);
+	page_idx = find_first_zero_bit(var_table->bitmap,
+				       var_table->num_var_hw_entries);
+	if (page_idx >= var_table->num_var_hw_entries) {
+		err = -ENOSPC;
+		mutex_unlock(&var_table->bitmap_lock);
+		goto end;
+	}
+
+	set_bit(page_idx, var_table->bitmap);
+	mutex_unlock(&var_table->bitmap_lock);
+
+	entry->address = var_table->hw_start_addr +
+				(page_idx * var_table->stride_size);
+	entry->page_idx = page_idx;
+	entry->mmap_flag = MLX5_IB_MMAP_TYPE_VAR;
+
+	err = rdma_user_mmap_entry_insert_range(
+		&c->ibucontext, &entry->rdma_entry, var_table->stride_size,
+		MLX5_IB_MMAP_OFFSET_START << 16,
+		(MLX5_IB_MMAP_OFFSET_END << 16) + (1UL << 16) - 1);
+	if (err)
+		goto err_insert;
+
+	return entry;
+
+err_insert:
+	mutex_lock(&var_table->bitmap_lock);
+	clear_bit(page_idx, var_table->bitmap);
+	mutex_unlock(&var_table->bitmap_lock);
+end:
+	kfree(entry);
+	return ERR_PTR(err);
+}
+
+static int UVERBS_HANDLER(MLX5_IB_METHOD_VAR_OBJ_ALLOC)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *uobj = uverbs_attr_get_uobject(
+		attrs, MLX5_IB_ATTR_VAR_OBJ_ALLOC_HANDLE);
+	struct mlx5_ib_ucontext *c;
+	struct mlx5_user_mmap_entry *entry;
+	u64 mmap_offset;
+	u32 length;
+	int err;
+
+	c = to_mucontext(ib_uverbs_get_ucontext(attrs));
+	if (IS_ERR(c))
+		return PTR_ERR(c);
+
+	entry = alloc_var_entry(c);
+	if (IS_ERR(entry))
+		return PTR_ERR(entry);
+
+	mmap_offset = mlx5_entry_to_mmap_offset(entry);
+	length = entry->rdma_entry.npages * PAGE_SIZE;
+	uobj->object = entry;
+
+	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_VAR_OBJ_ALLOC_MMAP_OFFSET,
+			     &mmap_offset, sizeof(mmap_offset));
+	if (err)
+		goto err;
+
+	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_VAR_OBJ_ALLOC_PAGE_ID,
+			     &entry->page_idx, sizeof(entry->page_idx));
+	if (err)
+		goto err;
+
+	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_VAR_OBJ_ALLOC_MMAP_LENGTH,
+			     &length, sizeof(length));
+	if (err)
+		goto err;
+
+	return 0;
+
+err:
+	rdma_user_mmap_entry_remove(&entry->rdma_entry);
+	return err;
+}
+
+DECLARE_UVERBS_NAMED_METHOD(
+	MLX5_IB_METHOD_VAR_OBJ_ALLOC,
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_VAR_OBJ_ALLOC_HANDLE,
+			MLX5_IB_OBJECT_VAR,
+			UVERBS_ACCESS_NEW,
+			UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_VAR_OBJ_ALLOC_PAGE_ID,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_VAR_OBJ_ALLOC_MMAP_LENGTH,
+			   UVERBS_ATTR_TYPE(u32),
+			   UA_MANDATORY),
+	UVERBS_ATTR_PTR_OUT(MLX5_IB_ATTR_VAR_OBJ_ALLOC_MMAP_OFFSET,
+			    UVERBS_ATTR_TYPE(u64),
+			    UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_METHOD_DESTROY(
+	MLX5_IB_METHOD_VAR_OBJ_DESTROY,
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_VAR_OBJ_DESTROY_HANDLE,
+			MLX5_IB_OBJECT_VAR,
+			UVERBS_ACCESS_DESTROY,
+			UA_MANDATORY));
+
+DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_VAR,
+			    UVERBS_TYPE_ALLOC_IDR(var_obj_cleanup),
+			    &UVERBS_METHOD(MLX5_IB_METHOD_VAR_OBJ_ALLOC),
+			    &UVERBS_METHOD(MLX5_IB_METHOD_VAR_OBJ_DESTROY));
+
+static bool var_is_supported(struct ib_device *device)
+{
+	struct mlx5_ib_dev *dev = to_mdev(device);
+
+	return (MLX5_CAP_GEN_64(dev->mdev, general_obj_types) &
+			MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q);
+}
+
 ADD_UVERBS_ATTRIBUTES_SIMPLE(
 	mlx5_ib_dm,
 	UVERBS_OBJECT_DM,
@@ -6073,14 +6249,14 @@ ADD_UVERBS_ATTRIBUTES_SIMPLE(
 			     enum mlx5_ib_uapi_flow_action_flags));
 
 static const struct uapi_definition mlx5_ib_defs[] = {
-#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 	UAPI_DEF_CHAIN(mlx5_ib_devx_defs),
 	UAPI_DEF_CHAIN(mlx5_ib_flow_defs),
-#endif
 
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION,
 				&mlx5_ib_flow_action),
 	UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_DM, &mlx5_ib_dm),
+	UAPI_DEF_CHAIN_OBJ_TREE_NAMED(MLX5_IB_OBJECT_VAR,
+				UAPI_DEF_IS_OBJ_SUPPORTED(var_is_supported)),
 	{}
 };
 
@@ -6352,6 +6528,35 @@ static const struct ib_device_ops mlx5_ib_dev_dm_ops = {
 	.reg_dm_mr = mlx5_ib_reg_dm_mr,
 };
 
+static int mlx5_ib_init_var_table(struct mlx5_ib_dev *dev)
+{
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_var_table *var_table = &dev->var_table;
+	u8 log_doorbell_bar_size;
+	u8 log_doorbell_stride;
+	u64 bar_size;
+
+	log_doorbell_bar_size = MLX5_CAP_DEV_VDPA_EMULATION(mdev,
+					log_doorbell_bar_size);
+	log_doorbell_stride = MLX5_CAP_DEV_VDPA_EMULATION(mdev,
+					log_doorbell_stride);
+	var_table->hw_start_addr = dev->mdev->bar_addr +
+				MLX5_CAP64_DEV_VDPA_EMULATION(mdev,
+					doorbell_bar_offset);
+	bar_size = (1ULL << log_doorbell_bar_size) * 4096;
+	var_table->stride_size = 1ULL << log_doorbell_stride;
+	var_table->num_var_hw_entries = bar_size / var_table->stride_size;
+	mutex_init(&var_table->bitmap_lock);
+	var_table->bitmap = bitmap_zalloc(var_table->num_var_hw_entries,
+					  GFP_KERNEL);
+	return (var_table->bitmap) ? 0 : -ENOMEM;
+}
+
+static void mlx5_ib_stage_caps_cleanup(struct mlx5_ib_dev *dev)
+{
+	bitmap_free(dev->var_table.bitmap);
+}
+
 static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
@@ -6439,6 +6644,13 @@ static int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	     MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		mutex_init(&dev->lb.mutex);
 
+	if (MLX5_CAP_GEN_64(dev->mdev, general_obj_types) &
+			MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q) {
+		err = mlx5_ib_init_var_table(dev);
+		if (err)
+			return err;
+	}
+
 	dev->ib_dev.use_cq_dim = true;
 
 	return 0;
@@ -6742,6 +6954,8 @@ void __mlx5_ib_remove(struct mlx5_ib_dev *dev,
 		      const struct mlx5_ib_profile *profile,
 		      int stage)
 {
+	dev->ib_active = false;
+
 	/* Number of stages to cleanup */
 	while (stage) {
 		stage--;
@@ -6787,7 +7001,7 @@ static const struct mlx5_ib_profile pf_profile = {
 		     mlx5_ib_stage_flow_db_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_CAPS,
 		     mlx5_ib_stage_caps_init,
-		     NULL),
+		     mlx5_ib_stage_caps_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_NON_DEFAULT_CB,
 		     mlx5_ib_stage_non_default_cb,
 		     NULL),
@@ -6844,7 +7058,7 @@ const struct mlx5_ib_profile raw_eth_profile = {
 		     mlx5_ib_stage_flow_db_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_CAPS,
 		     mlx5_ib_stage_caps_init,
-		     NULL),
+		     mlx5_ib_stage_caps_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_NON_DEFAULT_CB,
 		     mlx5_ib_stage_raw_eth_non_default_cb,
 		     NULL),
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 048f4e974a61..b90a3649e7d1 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -101,18 +101,6 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr,
 	*count = i;
 }
 
-static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
-{
-	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
-
-	if (umem_dma & ODP_READ_ALLOWED_BIT)
-		mtt_entry |= MLX5_IB_MTT_READ;
-	if (umem_dma & ODP_WRITE_ALLOWED_BIT)
-		mtt_entry |= MLX5_IB_MTT_WRITE;
-
-	return mtt_entry;
-}
-
 /*
  * Populate the given array with bus addresses from the umem.
  *
@@ -139,19 +127,6 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	struct scatterlist *sg;
 	int entry;
 
-	if (umem->is_odp) {
-		WARN_ON(shift != 0);
-		WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
-
-		for (i = 0; i < num_pages; ++i) {
-			dma_addr_t pa =
-				to_ib_umem_odp(umem)->dma_list[offset + i];
-
-			pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
-		}
-		return;
-	}
-
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
 		len = sg_dma_len(sg) >> PAGE_SHIFT;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 77d495b2032d..d9bffcc93587 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -72,6 +72,11 @@
 #define MLX5_MKEY_PAGE_SHIFT_MASK __mlx5_mask(mkc, log_page_size)
 
 enum {
+	MLX5_IB_MMAP_OFFSET_START = 9,
+	MLX5_IB_MMAP_OFFSET_END = 255,
+};
+
+enum {
 	MLX5_IB_MMAP_CMD_SHIFT	= 8,
 	MLX5_IB_MMAP_CMD_MASK	= 0xff,
 };
@@ -120,6 +125,7 @@ enum {
 
 enum mlx5_ib_mmap_type {
 	MLX5_IB_MMAP_TYPE_MEMIC = 1,
+	MLX5_IB_MMAP_TYPE_VAR = 2,
 };
 
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)                                        \
@@ -563,6 +569,7 @@ struct mlx5_user_mmap_entry {
 	struct rdma_user_mmap_entry rdma_entry;
 	u8 mmap_flag;
 	u64 address;
+	u32 page_idx;
 };
 
 struct mlx5_ib_dm {
@@ -959,6 +966,15 @@ struct mlx5_devx_event_table {
 	struct xarray event_xa;
 };
 
+struct mlx5_var_table {
+	/* serialize updating the bitmap */
+	struct mutex bitmap_lock;
+	unsigned long *bitmap;
+	u64 hw_start_addr;
+	u32 stride_size;
+	u64 num_var_hw_entries;
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	struct mlx5_core_dev		*mdev;
@@ -1013,6 +1029,7 @@ struct mlx5_ib_dev {
 	struct mlx5_srq_table   srq_table;
 	struct mlx5_async_ctx   async_ctx;
 	struct mlx5_devx_event_table devx_event_table;
+	struct mlx5_var_table var_table;
 
 	struct xarray sig_mrs;
 };
@@ -1276,8 +1293,8 @@ void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev);
 int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
 void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent);
-void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
-			   size_t nentries, struct mlx5_ib_mr *mr, int flags);
+void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+			   struct mlx5_ib_mr *mr, int flags);
 
 int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
 			       enum ib_uverbs_advise_mr_advice advice,
@@ -1293,9 +1310,8 @@ static inline void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *ibdev) {}
 static inline int mlx5_ib_odp_init(void) { return 0; }
 static inline void mlx5_ib_odp_cleanup(void)				    {}
 static inline void mlx5_odp_init_mr_cache_entry(struct mlx5_cache_ent *ent) {}
-static inline void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
-					 size_t nentries, struct mlx5_ib_mr *mr,
-					 int flags) {}
+static inline void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+					 struct mlx5_ib_mr *mr, int flags) {}
 
 static inline int
 mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
@@ -1363,14 +1379,14 @@ int mlx5_ib_fill_res_entry(struct sk_buff *msg,
 int mlx5_ib_fill_stat_entry(struct sk_buff *msg,
 			    struct rdma_restrack_entry *res);
 
+extern const struct uapi_definition mlx5_ib_devx_defs[];
+extern const struct uapi_definition mlx5_ib_flow_defs[];
+
 #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user);
 void mlx5_ib_devx_destroy(struct mlx5_ib_dev *dev, u16 uid);
 void mlx5_ib_devx_init_event_table(struct mlx5_ib_dev *dev);
 void mlx5_ib_devx_cleanup_event_table(struct mlx5_ib_dev *dev);
-const struct uverbs_object_tree_def *mlx5_ib_get_devx_tree(void);
-extern const struct uapi_definition mlx5_ib_devx_defs[];
-extern const struct uapi_definition mlx5_ib_flow_defs[];
 struct mlx5_ib_flow_handler *mlx5_ib_raw_fs_rule_add(
 	struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher,
 	struct mlx5_flow_context *flow_context,
@@ -1378,7 +1394,6 @@ struct mlx5_ib_flow_handler *mlx5_ib_raw_fs_rule_add(
 	void *cmd_in, int inlen, int dest_id, int dest_type);
 bool mlx5_ib_devx_is_flow_dest(void *obj, int *dest_id, int *dest_type);
 bool mlx5_ib_devx_is_flow_counter(void *obj, u32 offset, u32 *counter_id);
-int mlx5_ib_get_flow_trees(const struct uverbs_object_tree_def **root);
 void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction);
 #else
 static inline int
@@ -1507,7 +1522,7 @@ int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
 u16 mlx5_ib_get_counters_id(struct mlx5_ib_dev *dev, u8 port_num);
 
 static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
-				       bool do_modify_atomic)
+				       bool do_modify_atomic, int access_flags)
 {
 	if (MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled))
 		return false;
@@ -1517,6 +1532,9 @@ static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
 	    MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled))
 		return false;
 
+	if (access_flags & IB_ACCESS_RELAXED_ORDERING)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 44a0ee6bd9f1..6fa0a83c19de 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -147,7 +147,7 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 			break;
 		}
 		mr->order = ent->order;
-		mr->allocated_from_cache = 1;
+		mr->allocated_from_cache = true;
 		mr->dev = dev;
 
 		MLX5_SET(mkc, mkc, free, 1);
@@ -661,12 +661,21 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
 static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr,
 					  struct ib_pd *pd)
 {
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+
 	MLX5_SET(mkc, mkc, a, !!(acc & IB_ACCESS_REMOTE_ATOMIC));
 	MLX5_SET(mkc, mkc, rw, !!(acc & IB_ACCESS_REMOTE_WRITE));
 	MLX5_SET(mkc, mkc, rr, !!(acc & IB_ACCESS_REMOTE_READ));
 	MLX5_SET(mkc, mkc, lw, !!(acc & IB_ACCESS_LOCAL_WRITE));
 	MLX5_SET(mkc, mkc, lr, 1);
 
+	if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write))
+		MLX5_SET(mkc, mkc, relaxed_ordering_write,
+			 !!(acc & IB_ACCESS_RELAXED_ORDERING));
+	if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read))
+		MLX5_SET(mkc, mkc, relaxed_ordering_read,
+			 !!(acc & IB_ACCESS_RELAXED_ORDERING));
+
 	MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn);
 	MLX5_SET(mkc, mkc, qpn, 0xffffff);
 	MLX5_SET64(mkc, mkc, start_addr, start_addr);
@@ -867,36 +876,6 @@ static struct mlx5_ib_mr *alloc_mr_from_cache(
 	return mr;
 }
 
-static inline int populate_xlt(struct mlx5_ib_mr *mr, int idx, int npages,
-			       void *xlt, int page_shift, size_t size,
-			       int flags)
-{
-	struct mlx5_ib_dev *dev = mr->dev;
-	struct ib_umem *umem = mr->umem;
-
-	if (flags & MLX5_IB_UPD_XLT_INDIRECT) {
-		if (!umr_can_use_indirect_mkey(dev))
-			return -EPERM;
-		mlx5_odp_populate_klm(xlt, idx, npages, mr, flags);
-		return npages;
-	}
-
-	npages = min_t(size_t, npages, ib_umem_num_pages(umem) - idx);
-
-	if (!(flags & MLX5_IB_UPD_XLT_ZAP)) {
-		__mlx5_ib_populate_pas(dev, umem, page_shift,
-				       idx, npages, xlt,
-				       MLX5_IB_MTT_PRESENT);
-		/* Clear padding after the pages
-		 * brought from the umem.
-		 */
-		memset(xlt + (npages * sizeof(struct mlx5_mtt)), 0,
-		       size - npages * sizeof(struct mlx5_mtt));
-	}
-
-	return npages;
-}
-
 #define MLX5_MAX_UMR_CHUNK ((1 << (MLX5_MAX_UMR_SHIFT + 4)) - \
 			    MLX5_UMR_MTT_ALIGNMENT)
 #define MLX5_SPARE_UMR_CHUNK 0x10000
@@ -920,6 +899,7 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 	size_t pages_mapped = 0;
 	size_t pages_to_map = 0;
 	size_t pages_iter = 0;
+	size_t size_to_map = 0;
 	gfp_t gfp;
 	bool use_emergency_page = false;
 
@@ -966,6 +946,15 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 		goto free_xlt;
 	}
 
+	if (mr->umem->is_odp) {
+		if (!(flags & MLX5_IB_UPD_XLT_INDIRECT)) {
+			struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
+			size_t max_pages = ib_umem_odp_num_pages(odp) - idx;
+
+			pages_to_map = min_t(size_t, pages_to_map, max_pages);
+		}
+	}
+
 	sg.addr = dma;
 	sg.lkey = dev->umrc.pd->local_dma_lkey;
 
@@ -988,14 +977,22 @@ int mlx5_ib_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages,
 	     pages_mapped < pages_to_map && !err;
 	     pages_mapped += pages_iter, idx += pages_iter) {
 		npages = min_t(int, pages_iter, pages_to_map - pages_mapped);
+		size_to_map = npages * desc_size;
 		dma_sync_single_for_cpu(ddev, dma, size, DMA_TO_DEVICE);
-		npages = populate_xlt(mr, idx, npages, xlt,
-				      page_shift, size, flags);
-
+		if (mr->umem->is_odp) {
+			mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags);
+		} else {
+			__mlx5_ib_populate_pas(dev, mr->umem, page_shift, idx,
+					       npages, xlt,
+					       MLX5_IB_MTT_PRESENT);
+			/* Clear padding after the pages
+			 * brought from the umem.
+			 */
+			memset(xlt + size_to_map, 0, size - size_to_map);
+		}
 		dma_sync_single_for_device(ddev, dma, size, DMA_TO_DEVICE);
 
-		sg.length = ALIGN(npages * desc_size,
-				  MLX5_UMR_MTT_ALIGNMENT);
+		sg.length = ALIGN(size_to_map, MLX5_UMR_MTT_ALIGNMENT);
 
 		if (pages_mapped + pages_iter >= pages_to_map) {
 			if (flags & MLX5_IB_UPD_XLT_ENABLE)
@@ -1074,6 +1071,12 @@ static struct mlx5_ib_mr *reg_create(struct ib_mr *ibmr, struct ib_pd *pd,
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	MLX5_SET(mkc, mkc, free, !populate);
 	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);
+	if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_write))
+		MLX5_SET(mkc, mkc, relaxed_ordering_write,
+			 !!(access_flags & IB_ACCESS_RELAXED_ORDERING));
+	if (MLX5_CAP_GEN(dev->mdev, relaxed_ordering_read))
+		MLX5_SET(mkc, mkc, relaxed_ordering_read,
+			 !!(access_flags & IB_ACCESS_RELAXED_ORDERING));
 	MLX5_SET(mkc, mkc, a, !!(access_flags & IB_ACCESS_REMOTE_ATOMIC));
 	MLX5_SET(mkc, mkc, rw, !!(access_flags & IB_ACCESS_REMOTE_WRITE));
 	MLX5_SET(mkc, mkc, rr, !!(access_flags & IB_ACCESS_REMOTE_READ));
@@ -1264,7 +1267,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	if (err < 0)
 		return ERR_PTR(err);
 
-	use_umr = mlx5_ib_can_use_umr(dev, true);
+	use_umr = mlx5_ib_can_use_umr(dev, true, access_flags);
 
 	if (order <= mr_cache_max_order(dev) && use_umr) {
 		mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont,
@@ -1431,7 +1434,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 			goto err;
 	}
 
-	if (!mlx5_ib_can_use_umr(dev, true) ||
+	if (!mlx5_ib_can_use_umr(dev, true, access_flags) ||
 	    (flags & IB_MR_REREG_TRANS && !use_umr_mtt_update(mr, addr, len))) {
 		/*
 		 * UMR can't be used - MKey needs to be replaced.
@@ -1452,7 +1455,7 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 			goto err;
 		}
 
-		mr->allocated_from_cache = 0;
+		mr->allocated_from_cache = false;
 	} else {
 		/*
 		 * Send a UMR WQE
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 0afb0042bd53..4216814ba871 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -93,8 +93,8 @@ struct mlx5_pagefault {
 
 static u64 mlx5_imr_ksm_entries;
 
-void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
-			   struct mlx5_ib_mr *imr, int flags)
+static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
+			struct mlx5_ib_mr *imr, int flags)
 {
 	struct mlx5_klm *end = pklm + nentries;
 
@@ -144,6 +144,44 @@ void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
 	}
 }
 
+static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
+{
+	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
+
+	if (umem_dma & ODP_READ_ALLOWED_BIT)
+		mtt_entry |= MLX5_IB_MTT_READ;
+	if (umem_dma & ODP_WRITE_ALLOWED_BIT)
+		mtt_entry |= MLX5_IB_MTT_WRITE;
+
+	return mtt_entry;
+}
+
+static void populate_mtt(__be64 *pas, size_t idx, size_t nentries,
+			 struct mlx5_ib_mr *mr, int flags)
+{
+	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
+	dma_addr_t pa;
+	size_t i;
+
+	if (flags & MLX5_IB_UPD_XLT_ZAP)
+		return;
+
+	for (i = 0; i < nentries; i++) {
+		pa = odp->dma_list[idx + i];
+		pas[i] = cpu_to_be64(umem_dma_to_mtt(pa));
+	}
+}
+
+void mlx5_odp_populate_xlt(void *xlt, size_t idx, size_t nentries,
+			   struct mlx5_ib_mr *mr, int flags)
+{
+	if (flags & MLX5_IB_UPD_XLT_INDIRECT) {
+		populate_klm(xlt, idx, nentries, mr, flags);
+	} else {
+		populate_mtt(xlt, idx, nentries, mr, flags);
+	}
+}
+
 static void dma_fence_odp_mr(struct mlx5_ib_mr *mr)
 {
 	struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem);
@@ -342,7 +380,7 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
 	memset(caps, 0, sizeof(*caps));
 
 	if (!MLX5_CAP_GEN(dev->mdev, pg) ||
-	    !mlx5_ib_can_use_umr(dev, true))
+	    !mlx5_ib_can_use_umr(dev, true, 0))
 		return;
 
 	caps->general_caps = IB_ODP_SUPPORT;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index ae7cbd9c9bca..a4f8e7030787 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1918,7 +1918,7 @@ static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,
 {
 	enum ib_qp_type qpt = init_attr->qp_type;
 	int scqe_sz;
-	bool allow_scat_cqe = 0;
+	bool allow_scat_cqe = false;
 
 	if (qpt == IB_QPT_UC || qpt == IB_QPT_UD)
 		return;
@@ -4870,7 +4870,7 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 	bool atomic = wr->access & IB_ACCESS_REMOTE_ATOMIC;
 	u8 flags = 0;
 
-	if (!mlx5_ib_can_use_umr(dev, atomic)) {
+	if (!mlx5_ib_can_use_umr(dev, atomic, wr->access)) {
 		mlx5_ib_warn(to_mdev(qp->ibqp.device),
 			     "Fast update of %s for MR is disabled\n",
 			     (MLX5_CAP_GEN(dev->mdev,
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index edccfd6e178f..78a48aea3faf 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/drivers/infiniband/hw/mthca/mthca_memfree.c
@@ -472,7 +472,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 		goto out;
 	}
 
-	ret = get_user_pages_fast(uaddr & PAGE_MASK, 1,
+	ret = pin_user_pages_fast(uaddr & PAGE_MASK, 1,
 				  FOLL_WRITE | FOLL_LONGTERM, pages);
 	if (ret < 0)
 		goto out;
@@ -482,7 +482,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 
 	ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
 	if (ret < 0) {
-		put_user_page(pages[0]);
+		unpin_user_page(pages[0]);
 		goto out;
 	}
 
@@ -490,7 +490,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
 				 mthca_uarc_virt(dev, uar, i));
 	if (ret) {
 		pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
-		put_user_page(sg_page(&db_tab->page[i].mem));
+		unpin_user_page(sg_page(&db_tab->page[i].mem));
 		goto out;
 	}
 
@@ -556,7 +556,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar,
 		if (db_tab->page[i].uvirt) {
 			mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1);
 			pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
-			put_user_page(sg_page(&db_tab->page[i].mem));
+			unpin_user_page(sg_page(&db_tab->page[i].mem));
 		}
 	}
 
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 920f35e28cfc..484b555150e0 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -312,7 +312,18 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 	}
 	ctx->db_mmap_entry = &entry->rdma_entry;
 
-	uresp.dpm_enabled = dev->user_dpm_enabled;
+	if (!dev->user_dpm_enabled)
+		uresp.dpm_flags = 0;
+	else if (rdma_protocol_iwarp(&dev->ibdev, 1))
+		uresp.dpm_flags = QEDR_DPM_TYPE_IWARP_LEGACY;
+	else
+		uresp.dpm_flags = QEDR_DPM_TYPE_ROCE_ENHANCED |
+				  QEDR_DPM_TYPE_ROCE_LEGACY;
+
+	uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
+	uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
+	uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+
 	uresp.wids_enabled = 1;
 	uresp.wid_count = oparams.wid_count;
 	uresp.db_pa = rdma_user_mmap_get_offset(ctx->db_mmap_entry);
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 6bf764e41891..342e3172ca40 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -40,7 +40,7 @@
 static void __qib_release_user_pages(struct page **p, size_t num_pages,
 				     int dirty)
 {
-	put_user_pages_dirty_lock(p, num_pages, dirty);
+	unpin_user_pages_dirty_lock(p, num_pages, dirty);
 }
 
 /**
@@ -108,7 +108,7 @@ int qib_get_user_pages(unsigned long start_page, size_t num_pages,
 
 	down_read(&current->mm->mmap_sem);
 	for (got = 0; got < num_pages; got += ret) {
-		ret = get_user_pages(start_page + got * PAGE_SIZE,
+		ret = pin_user_pages(start_page + got * PAGE_SIZE,
 				     num_pages - got,
 				     FOLL_LONGTERM | FOLL_WRITE | FOLL_FORCE,
 				     p + got, NULL);
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 05190edc2611..a67599b5a550 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -317,7 +317,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd,
 		 * the caller can ignore this page.
 		 */
 		if (put) {
-			put_user_page(page);
+			unpin_user_page(page);
 		} else {
 			/* coalesce case */
 			kunmap(page);
@@ -631,7 +631,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
 			kunmap(pkt->addr[i].page);
 
 		if (pkt->addr[i].put_page)
-			put_user_page(pkt->addr[i].page);
+			unpin_user_page(pkt->addr[i].page);
 		else
 			__free_page(pkt->addr[i].page);
 	} else if (pkt->addr[i].kvaddr) {
@@ -670,7 +670,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 		else
 			j = npages;
 
-		ret = get_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
+		ret = pin_user_pages_fast(addr, j, FOLL_LONGTERM, pages);
 		if (ret != j) {
 			i = 0;
 			j = ret;
@@ -706,7 +706,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 	/* if error, return all pages not managed by pkt */
 free_pages:
 	while (i < j)
-		put_user_page(pages[i++]);
+		unpin_user_page(pages[i++]);
 
 done:
 	return ret;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 62e6ffa9ad78..bd9f944b68fc 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -75,7 +75,7 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
 		for_each_sg(chunk->page_list, sg, chunk->nents, i) {
 			page = sg_page(sg);
 			pa = sg_phys(sg);
-			put_user_pages_dirty_lock(&page, 1, dirty);
+			unpin_user_pages_dirty_lock(&page, 1, dirty);
 			usnic_dbg("pa: %pa\n", &pa);
 		}
 		kfree(chunk);
@@ -141,7 +141,7 @@ static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
 	ret = 0;
 
 	while (npages) {
-		ret = get_user_pages(cur_base,
+		ret = pin_user_pages(cur_base,
 				     min_t(unsigned long, npages,
 				     PAGE_SIZE / sizeof(struct page *)),
 				     gup_flags | FOLL_LONGTERM,
diff --git a/drivers/infiniband/sw/rdmavt/rc.c b/drivers/infiniband/sw/rdmavt/rc.c
index 890d7b760d2e..977906cc0d11 100644
--- a/drivers/infiniband/sw/rdmavt/rc.c
+++ b/drivers/infiniband/sw/rdmavt/rc.c
@@ -195,7 +195,14 @@ void rvt_get_credit(struct rvt_qp *qp, u32 aeth)
 }
 EXPORT_SYMBOL(rvt_get_credit);
 
-/* rvt_restart_sge - rewind the sge state for a wqe */
+/**
+ * rvt_restart_sge - rewind the sge state for a wqe
+ * @ss: the sge state pointer
+ * @wqe: the wqe to rewind
+ * @len: the data length from the start of the wqe in bytes
+ *
+ * Returns the remaining data length.
+ */
 u32 rvt_restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, u32 len)
 {
 	ss->sge = wqe->sg_list[0];
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index 353c6668249e..f59616b02477 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -34,6 +34,8 @@
 #ifndef RXE_PARAM_H
 #define RXE_PARAM_H
 
+#include <uapi/rdma/rdma_user_rxe.h>
+
 static inline enum ib_mtu rxe_mtu_int_to_enum(int mtu)
 {
 	if (mtu < 256)
@@ -64,7 +66,6 @@ enum rxe_device_param {
 	RXE_PAGE_SIZE_CAP		= 0xfffff000,
 	RXE_MAX_QP			= 0x10000,
 	RXE_MAX_QP_WR			= 0x4000,
-	RXE_MAX_INLINE_DATA		= 400,
 	RXE_DEVICE_CAP_FLAGS		= IB_DEVICE_BAD_PKEY_CNTR
 					| IB_DEVICE_BAD_QKEY_CNTR
 					| IB_DEVICE_AUTO_PATH_MIG
@@ -77,6 +78,10 @@ enum rxe_device_param {
 					| IB_DEVICE_MEM_MGT_EXTENSIONS
 					| IB_DEVICE_ALLOW_USER_UNREG,
 	RXE_MAX_SGE			= 32,
+	RXE_MAX_WQE_SIZE		= sizeof(struct rxe_send_wqe) +
+					  sizeof(struct ib_sge) * RXE_MAX_SGE,
+	RXE_MAX_INLINE_DATA		= RXE_MAX_WQE_SIZE -
+					  sizeof(struct rxe_send_wqe),
 	RXE_MAX_SGE_RD			= 32,
 	RXE_MAX_CQ			= 16384,
 	RXE_MAX_LOG_CQE			= 15,
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index e2c6d1cedf41..ec21f616ac98 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -237,19 +237,17 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp,
 	 */
 	qp->src_port = RXE_ROCE_V2_SPORT +
 		(hash_32_generic(qp_num(qp), 14) & 0x3fff);
-
 	qp->sq.max_wr		= init->cap.max_send_wr;
-	qp->sq.max_sge		= init->cap.max_send_sge;
-	qp->sq.max_inline	= init->cap.max_inline_data;
 
-	wqe_size = max_t(int, sizeof(struct rxe_send_wqe) +
-			 qp->sq.max_sge * sizeof(struct ib_sge),
-			 sizeof(struct rxe_send_wqe) +
-			 qp->sq.max_inline);
+	/* These caps are limited by rxe_qp_chk_cap() done by the caller */
+	wqe_size = max_t(int, init->cap.max_send_sge * sizeof(struct ib_sge),
+			 init->cap.max_inline_data);
+	qp->sq.max_sge = init->cap.max_send_sge =
+		wqe_size / sizeof(struct ib_sge);
+	qp->sq.max_inline = init->cap.max_inline_data = wqe_size;
+	wqe_size += sizeof(struct rxe_send_wqe);
 
-	qp->sq.queue = rxe_queue_init(rxe,
-				      &qp->sq.max_wr,
-				      wqe_size);
+	qp->sq.queue = rxe_queue_init(rxe, &qp->sq.max_wr, wqe_size);
 	if (!qp->sq.queue)
 		return -ENOMEM;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 95834206c80c..92de39c4a7c1 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -408,7 +408,7 @@ struct rxe_dev {
 	struct list_head	pending_mmaps;
 
 	spinlock_t		mmap_offset_lock; /* guard mmap_offset */
-	int			mmap_offset;
+	u64			mmap_offset;
 
 	atomic64_t		stats_counters[RXE_NUM_OF_COUNTERS];
 
diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h
index b939f489cd46..af5e9f8c0fcd 100644
--- a/drivers/infiniband/sw/siw/siw.h
+++ b/drivers/infiniband/sw/siw/siw.h
@@ -7,6 +7,7 @@
 #define _SIW_H
 
 #include <rdma/ib_verbs.h>
+#include <rdma/restrack.h>
 #include <linux/socket.h>
 #include <linux/skbuff.h>
 #include <crypto/hash.h>
@@ -209,7 +210,6 @@ struct siw_cq {
 	u32 cq_put;
 	u32 cq_get;
 	u32 num_cqe;
-	bool kernel_verbs;
 	struct rdma_user_mmap_entry *cq_entry; /* mmap info for CQE array */
 	u32 id; /* For debugging only */
 };
@@ -254,8 +254,8 @@ struct siw_srq {
 	u32 rq_get;
 	u32 num_rqe; /* max # of wqe's allowed */
 	struct rdma_user_mmap_entry *srq_entry; /* mmap info for SRQ array */
-	char armed; /* inform user if limit hit */
-	char kernel_verbs; /* '1' if kernel client */
+	bool armed:1; /* inform user if limit hit */
+	bool is_kernel_res:1; /* true if kernel client */
 };
 
 struct siw_qp_attrs {
@@ -418,13 +418,11 @@ struct siw_iwarp_tx {
 };
 
 struct siw_qp {
+	struct ib_qp base_qp;
 	struct siw_device *sdev;
-	struct ib_qp *ib_qp;
 	struct kref ref;
-	u32 qp_num;
 	struct list_head devq;
 	int tx_cpu;
-	bool kernel_verbs;
 	struct siw_qp_attrs attrs;
 
 	struct siw_cep *cep;
@@ -472,11 +470,6 @@ struct siw_qp {
 	struct rcu_head rcu;
 };
 
-struct siw_base_qp {
-	struct ib_qp base_qp;
-	struct siw_qp *qp;
-};
-
 /* helper macros */
 #define rx_qp(rx) container_of(rx, struct siw_qp, rx_stream)
 #define tx_qp(tx) container_of(tx, struct siw_qp, tx_ctx)
@@ -572,14 +565,9 @@ static inline struct siw_ucontext *to_siw_ctx(struct ib_ucontext *base_ctx)
 	return container_of(base_ctx, struct siw_ucontext, base_ucontext);
 }
 
-static inline struct siw_base_qp *to_siw_base_qp(struct ib_qp *base_qp)
-{
-	return container_of(base_qp, struct siw_base_qp, base_qp);
-}
-
 static inline struct siw_qp *to_siw_qp(struct ib_qp *base_qp)
 {
-	return to_siw_base_qp(base_qp)->qp;
+	return container_of(base_qp, struct siw_qp, base_qp);
 }
 
 static inline struct siw_cq *to_siw_cq(struct ib_cq *base_cq)
@@ -624,7 +612,7 @@ static inline struct siw_qp *siw_qp_id2obj(struct siw_device *sdev, int id)
 
 static inline u32 qp_id(struct siw_qp *qp)
 {
-	return qp->qp_num;
+	return qp->base_qp.qp_num;
 }
 
 static inline void siw_qp_get(struct siw_qp *qp)
@@ -735,7 +723,7 @@ static inline void siw_crc_skb(struct siw_rx_stream *srx, unsigned int len)
 		  "MEM[0x%08x] %s: " fmt, mem->stag, __func__, ##__VA_ARGS__)
 
 #define siw_dbg_cep(cep, fmt, ...)                                             \
-	ibdev_dbg(&cep->sdev->base_dev, "CEP[0x%pK] %s: " fmt,                  \
+	ibdev_dbg(&cep->sdev->base_dev, "CEP[0x%pK] %s: " fmt,                 \
 		  cep, __func__, ##__VA_ARGS__)
 
 void siw_cq_flush(struct siw_cq *cq);
diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c
index 3bccfef40e7e..0c3f0588346e 100644
--- a/drivers/infiniband/sw/siw/siw_cm.c
+++ b/drivers/infiniband/sw/siw/siw_cm.c
@@ -29,7 +29,7 @@
  * MPA_V2_RDMA_NO_RTR, MPA_V2_RDMA_READ_RTR, MPA_V2_RDMA_WRITE_RTR
  */
 static __be16 rtr_type = MPA_V2_RDMA_READ_RTR | MPA_V2_RDMA_WRITE_RTR;
-static const bool relaxed_ird_negotiation = 1;
+static const bool relaxed_ird_negotiation = true;
 
 static void siw_cm_llp_state_change(struct sock *s);
 static void siw_cm_llp_data_ready(struct sock *s);
diff --git a/drivers/infiniband/sw/siw/siw_cq.c b/drivers/infiniband/sw/siw/siw_cq.c
index d8db3bee9da7..d68e37859e73 100644
--- a/drivers/infiniband/sw/siw/siw_cq.c
+++ b/drivers/infiniband/sw/siw/siw_cq.c
@@ -65,7 +65,7 @@ int siw_reap_cqe(struct siw_cq *cq, struct ib_wc *wc)
 		 * reaped here, which do not hold a QP reference
 		 * and do not qualify for memory extension verbs.
 		 */
-		if (likely(cq->kernel_verbs)) {
+		if (likely(rdma_is_kernel_res(&cq->base_cq.res))) {
 			if (cqe->flags & SIW_WQE_REM_INVAL) {
 				wc->ex.invalidate_rkey = cqe->inval_stag;
 				wc->wc_flags = IB_WC_WITH_INVALIDATE;
diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c
index c147f0613d95..96ed349c0939 100644
--- a/drivers/infiniband/sw/siw/siw_main.c
+++ b/drivers/infiniband/sw/siw/siw_main.c
@@ -244,7 +244,7 @@ static struct ib_qp *siw_get_base_qp(struct ib_device *base_dev, int id)
 		 * siw_qp_id2obj() increments object reference count
 		 */
 		siw_qp_put(qp);
-		return qp->ib_qp;
+		return &qp->base_qp;
 	}
 	return NULL;
 }
diff --git a/drivers/infiniband/sw/siw/siw_mem.c b/drivers/infiniband/sw/siw/siw_mem.c
index e99983f07663..e2061dc0b043 100644
--- a/drivers/infiniband/sw/siw/siw_mem.c
+++ b/drivers/infiniband/sw/siw/siw_mem.c
@@ -63,7 +63,7 @@ struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index)
 static void siw_free_plist(struct siw_page_chunk *chunk, int num_pages,
 			   bool dirty)
 {
-	put_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
+	unpin_user_pages_dirty_lock(chunk->plist, num_pages, dirty);
 }
 
 void siw_umem_release(struct siw_umem *umem, bool dirty)
@@ -426,7 +426,7 @@ struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable)
 		while (nents) {
 			struct page **plist = &umem->page_chunk[i].plist[got];
 
-			rv = get_user_pages(first_page_va, nents,
+			rv = pin_user_pages(first_page_va, nents,
 					    foll_flags | FOLL_LONGTERM,
 					    plist, NULL);
 			if (rv < 0)
diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c
index b4317480cee7..875d36d4b1c6 100644
--- a/drivers/infiniband/sw/siw/siw_qp.c
+++ b/drivers/infiniband/sw/siw/siw_qp.c
@@ -1070,8 +1070,8 @@ int siw_sqe_complete(struct siw_qp *qp, struct siw_sqe *sqe, u32 bytes,
 			cqe->imm_data = 0;
 			cqe->bytes = bytes;
 
-			if (cq->kernel_verbs)
-				cqe->base_qp = qp->ib_qp;
+			if (rdma_is_kernel_res(&cq->base_cq.res))
+				cqe->base_qp = &qp->base_qp;
 			else
 				cqe->qp_id = qp_id(qp);
 
@@ -1128,8 +1128,8 @@ int siw_rqe_complete(struct siw_qp *qp, struct siw_rqe *rqe, u32 bytes,
 			cqe->imm_data = 0;
 			cqe->bytes = bytes;
 
-			if (cq->kernel_verbs) {
-				cqe->base_qp = qp->ib_qp;
+			if (rdma_is_kernel_res(&cq->base_cq.res)) {
+				cqe->base_qp = &qp->base_qp;
 				if (inval_stag) {
 					cqe_flags |= SIW_WQE_REM_INVAL;
 					cqe->inval_stag = inval_stag;
@@ -1297,13 +1297,12 @@ void siw_rq_flush(struct siw_qp *qp)
 
 int siw_qp_add(struct siw_device *sdev, struct siw_qp *qp)
 {
-	int rv = xa_alloc(&sdev->qp_xa, &qp->ib_qp->qp_num, qp, xa_limit_32b,
+	int rv = xa_alloc(&sdev->qp_xa, &qp->base_qp.qp_num, qp, xa_limit_32b,
 			  GFP_KERNEL);
 
 	if (!rv) {
 		kref_init(&qp->ref);
 		qp->sdev = sdev;
-		qp->qp_num = qp->ib_qp->qp_num;
 		siw_dbg_qp(qp, "new QP\n");
 	}
 	return rv;
@@ -1312,7 +1311,6 @@ int siw_qp_add(struct siw_device *sdev, struct siw_qp *qp)
 void siw_free_qp(struct kref *ref)
 {
 	struct siw_qp *found, *qp = container_of(ref, struct siw_qp, ref);
-	struct siw_base_qp *siw_base_qp = to_siw_base_qp(qp->ib_qp);
 	struct siw_device *sdev = qp->sdev;
 	unsigned long flags;
 
@@ -1335,5 +1333,4 @@ void siw_free_qp(struct kref *ref)
 	atomic_dec(&sdev->num_qp);
 	siw_dbg_qp(qp, "free QP\n");
 	kfree_rcu(qp, rcu);
-	kfree(siw_base_qp);
 }
diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c
index c0a887240325..9ccce2909ac4 100644
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -68,7 +68,7 @@ static int siw_rx_umem(struct siw_rx_stream *srx, struct siw_umem *umem,
 			return -EFAULT;
 		}
 		if (srx->mpa_crc_hd) {
-			if (rx_qp(srx)->kernel_verbs) {
+			if (rdma_is_kernel_res(&rx_qp(srx)->base_qp.res)) {
 				crypto_shash_update(srx->mpa_crc_hd,
 					(u8 *)(dest + pg_off), bytes);
 				kunmap_atomic(dest);
@@ -388,7 +388,7 @@ static struct siw_wqe *siw_rqe_get(struct siw_qp *qp)
 				struct siw_rqe *rqe2 = &srq->recvq[off];
 
 				if (!(rqe2->flags & SIW_WQE_VALID)) {
-					srq->armed = 0;
+					srq->armed = false;
 					srq_event = true;
 				}
 			}
@@ -1264,7 +1264,7 @@ static int siw_rdmap_complete(struct siw_qp *qp, int error)
 
 			if (wc_status == SIW_WC_SUCCESS)
 				wc_status = SIW_WC_GENERAL_ERR;
-		} else if (qp->kernel_verbs &&
+		} else if (rdma_is_kernel_res(&qp->base_qp.res) &&
 			   rx_type(wqe) == SIW_OP_READ_LOCAL_INV) {
 			/*
 			 * Handle any STag invalidation request
diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 5d97bba0ce6d..ae92c8080967 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -817,7 +817,7 @@ static int siw_qp_sq_proc_tx(struct siw_qp *qp, struct siw_wqe *wqe)
 			}
 		} else {
 			wqe->bytes = wqe->sqe.sge[0].length;
-			if (!qp->kernel_verbs) {
+			if (!rdma_is_kernel_res(&qp->base_qp.res)) {
 				if (wqe->bytes > SIW_MAX_INLINE) {
 					rv = -EINVAL;
 					goto tx_error;
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 5fd6d6499b3d..07e30138aaa1 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -303,7 +303,6 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 			    struct ib_udata *udata)
 {
 	struct siw_qp *qp = NULL;
-	struct siw_base_qp *siw_base_qp = NULL;
 	struct ib_device *base_dev = pd->device;
 	struct siw_device *sdev = to_siw_dev(base_dev);
 	struct siw_ucontext *uctx =
@@ -357,26 +356,16 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 		rv = -EINVAL;
 		goto err_out;
 	}
-	siw_base_qp = kzalloc(sizeof(*siw_base_qp), GFP_KERNEL);
-	if (!siw_base_qp) {
-		rv = -ENOMEM;
-		goto err_out;
-	}
 	qp = kzalloc(sizeof(*qp), GFP_KERNEL);
 	if (!qp) {
 		rv = -ENOMEM;
 		goto err_out;
 	}
-	siw_base_qp->qp = qp;
-	qp->ib_qp = &siw_base_qp->base_qp;
-
 	init_rwsem(&qp->state_lock);
 	spin_lock_init(&qp->sq_lock);
 	spin_lock_init(&qp->rq_lock);
 	spin_lock_init(&qp->orq_lock);
 
-	qp->kernel_verbs = !udata;
-
 	rv = siw_qp_add(sdev, qp);
 	if (rv)
 		goto err_out;
@@ -389,10 +378,10 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 	num_sqe = roundup_pow_of_two(attrs->cap.max_send_wr);
 	num_rqe = roundup_pow_of_two(attrs->cap.max_recv_wr);
 
-	if (qp->kernel_verbs)
-		qp->sendq = vzalloc(num_sqe * sizeof(struct siw_sqe));
-	else
+	if (udata)
 		qp->sendq = vmalloc_user(num_sqe * sizeof(struct siw_sqe));
+	else
+		qp->sendq = vzalloc(num_sqe * sizeof(struct siw_sqe));
 
 	if (qp->sendq == NULL) {
 		siw_dbg(base_dev, "SQ size %d alloc failed\n", num_sqe);
@@ -419,13 +408,14 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 		 */
 		qp->srq = to_siw_srq(attrs->srq);
 		qp->attrs.rq_size = 0;
-		siw_dbg(base_dev, "QP [%u]: SRQ attached\n", qp->qp_num);
+		siw_dbg(base_dev, "QP [%u]: SRQ attached\n",
+			qp->base_qp.qp_num);
 	} else if (num_rqe) {
-		if (qp->kernel_verbs)
-			qp->recvq = vzalloc(num_rqe * sizeof(struct siw_rqe));
-		else
+		if (udata)
 			qp->recvq =
 				vmalloc_user(num_rqe * sizeof(struct siw_rqe));
+		else
+			qp->recvq = vzalloc(num_rqe * sizeof(struct siw_rqe));
 
 		if (qp->recvq == NULL) {
 			siw_dbg(base_dev, "RQ size %d alloc failed\n", num_rqe);
@@ -492,13 +482,11 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 	list_add_tail(&qp->devq, &sdev->qp_list);
 	spin_unlock_irqrestore(&sdev->lock, flags);
 
-	return qp->ib_qp;
+	return &qp->base_qp;
 
 err_out_xa:
 	xa_erase(&sdev->qp_xa, qp_id(qp));
 err_out:
-	kfree(siw_base_qp);
-
 	if (qp) {
 		if (uctx) {
 			rdma_user_mmap_entry_remove(qp->sq_entry);
@@ -742,7 +730,7 @@ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr,
 	unsigned long flags;
 	int rv = 0;
 
-	if (wr && !qp->kernel_verbs) {
+	if (wr && !rdma_is_kernel_res(&qp->base_qp.res)) {
 		siw_dbg_qp(qp, "wr must be empty for user mapped sq\n");
 		*bad_wr = wr;
 		return -EINVAL;
@@ -939,7 +927,7 @@ int siw_post_send(struct ib_qp *base_qp, const struct ib_send_wr *wr,
 	if (rv <= 0)
 		goto skip_direct_sending;
 
-	if (qp->kernel_verbs) {
+	if (rdma_is_kernel_res(&qp->base_qp.res)) {
 		rv = siw_sq_start(qp);
 	} else {
 		qp->tx_ctx.in_syscall = 1;
@@ -984,8 +972,8 @@ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr,
 		*bad_wr = wr;
 		return -EOPNOTSUPP; /* what else from errno.h? */
 	}
-	if (!qp->kernel_verbs) {
-		siw_dbg_qp(qp, "no kernel post_recv for user mapped sq\n");
+	if (!rdma_is_kernel_res(&qp->base_qp.res)) {
+		siw_dbg_qp(qp, "no kernel post_recv for user mapped rq\n");
 		*bad_wr = wr;
 		return -EINVAL;
 	}
@@ -1127,14 +1115,13 @@ int siw_create_cq(struct ib_cq *base_cq, const struct ib_cq_init_attr *attr,
 	cq->base_cq.cqe = size;
 	cq->num_cqe = size;
 
-	if (!udata) {
-		cq->kernel_verbs = 1;
-		cq->queue = vzalloc(size * sizeof(struct siw_cqe) +
-				    sizeof(struct siw_cq_ctrl));
-	} else {
+	if (udata)
 		cq->queue = vmalloc_user(size * sizeof(struct siw_cqe) +
 					 sizeof(struct siw_cq_ctrl));
-	}
+	else
+		cq->queue = vzalloc(size * sizeof(struct siw_cqe) +
+				    sizeof(struct siw_cq_ctrl));
+
 	if (cq->queue == NULL) {
 		rv = -ENOMEM;
 		goto err_out;
@@ -1589,9 +1576,9 @@ int siw_create_srq(struct ib_srq *base_srq,
 	srq->num_rqe = roundup_pow_of_two(attrs->max_wr);
 	srq->limit = attrs->srq_limit;
 	if (srq->limit)
-		srq->armed = 1;
+		srq->armed = true;
 
-	srq->kernel_verbs = !udata;
+	srq->is_kernel_res = !udata;
 
 	if (udata)
 		srq->recvq =
@@ -1671,9 +1658,9 @@ int siw_modify_srq(struct ib_srq *base_srq, struct ib_srq_attr *attrs,
 				rv = -EINVAL;
 				goto out;
 			}
-			srq->armed = 1;
+			srq->armed = true;
 		} else {
-			srq->armed = 0;
+			srq->armed = false;
 		}
 		srq->limit = attrs->srq_limit;
 	}
@@ -1745,7 +1732,7 @@ int siw_post_srq_recv(struct ib_srq *base_srq, const struct ib_recv_wr *wr,
 	unsigned long flags;
 	int rv = 0;
 
-	if (unlikely(!srq->kernel_verbs)) {
+	if (unlikely(!srq->is_kernel_res)) {
 		siw_dbg_pd(base_srq->pd,
 			   "[SRQ]: no kernel post_recv for mapped srq\n");
 		rv = -EINVAL;
@@ -1797,7 +1784,7 @@ out:
 void siw_qp_event(struct siw_qp *qp, enum ib_event_type etype)
 {
 	struct ib_event event;
-	struct ib_qp *base_qp = qp->ib_qp;
+	struct ib_qp *base_qp = &qp->base_qp;
 
 	/*
 	 * Do not report asynchronous errors on QP which gets
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 0f74dc6d12fa..7a8f24de3631 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -527,7 +527,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 		if (unlikely(err))
 			goto err_reg;
 
-		desc->sig_protected = 1;
+		desc->sig_protected = true;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 1f4a37a3c2b3..127887c6c03f 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -1093,7 +1093,7 @@ u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task,
 	int ret;
 
 	if (desc && desc->sig_protected) {
-		desc->sig_protected = 0;
+		desc->sig_protected = false;
 		ret = ib_check_mr_status(desc->rsc.sig_mr,
 					 IB_MR_CHECK_SIG_STATUS, &mr_status);
 		if (ret) {
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
index e4c9bf2ef7e2..4480092c68e0 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.h
@@ -358,7 +358,7 @@ struct opa_veswport_summary_counters {
  * @rx_drop_state: received packets in non-forwarding port state
  * @rx_logic: other receive errors
  *
- * All the above are counters of corresponding erorr conditions.
+ * All the above are counters of corresponding error conditions.
  */
 struct opa_veswport_error_counters {
 	__be16  vp_instance;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index b7f7a5f7bd98..cd1181c39ed2 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -2546,7 +2546,8 @@ static void srp_cm_rep_handler(struct ib_cm_id *cm_id,
 	if (lrsp->opcode == SRP_LOGIN_RSP) {
 		ch->max_ti_iu_len = be32_to_cpu(lrsp->max_ti_iu_len);
 		ch->req_lim       = be32_to_cpu(lrsp->req_lim_delta);
-		ch->use_imm_data  = lrsp->rsp_flags & SRP_LOGIN_RSP_IMMED_SUPP;
+		ch->use_imm_data  = srp_use_imm_data &&
+			(lrsp->rsp_flags & SRP_LOGIN_RSP_IMMED_SUPP);
 		ch->max_it_iu_len = srp_max_it_iu_len(target->cmd_sg_cnt,
 						      ch->use_imm_data,
 						      target->max_it_iu_size);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 23c782e3d49a..98552749d71c 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2810,8 +2810,6 @@ static void srpt_queue_response(struct se_cmd *cmd)
 	int resp_len, ret, i;
 	u8 srp_tm_status;
 
-	BUG_ON(!ch);
-
 	state = ioctx->state;
 	switch (state) {
 	case SRPT_STATE_NEW:
diff --git a/drivers/input/input.c b/drivers/input/input.c
index ee6c3234df36..fce43e62dd45 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1216,13 +1216,12 @@ static int input_proc_devices_open(struct inode *inode, struct file *file)
 	return seq_open(file, &input_devices_seq_ops);
 }
 
-static const struct file_operations input_devices_fileops = {
-	.owner		= THIS_MODULE,
-	.open		= input_proc_devices_open,
-	.poll		= input_proc_devices_poll,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops input_devices_proc_ops = {
+	.proc_open	= input_proc_devices_open,
+	.proc_poll	= input_proc_devices_poll,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static void *input_handlers_seq_start(struct seq_file *seq, loff_t *pos)
@@ -1280,12 +1279,11 @@ static int input_proc_handlers_open(struct inode *inode, struct file *file)
 	return seq_open(file, &input_handlers_seq_ops);
 }
 
-static const struct file_operations input_handlers_fileops = {
-	.owner		= THIS_MODULE,
-	.open		= input_proc_handlers_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops input_handlers_proc_ops = {
+	.proc_open	= input_proc_handlers_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static int __init input_proc_init(void)
@@ -1297,12 +1295,12 @@ static int __init input_proc_init(void)
 		return -ENOMEM;
 
 	entry = proc_create("devices", 0, proc_bus_input_dir,
-			    &input_devices_fileops);
+			    &input_devices_proc_ops);
 	if (!entry)
 		goto fail1;
 
 	entry = proc_create("handlers", 0, proc_bus_input_dir,
-			    &input_handlers_fileops);
+			    &input_handlers_proc_ops);
 	if (!entry)
 		goto fail2;
 
diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c
index 17c1cca74498..c8f87df93a50 100644
--- a/drivers/input/misc/axp20x-pek.c
+++ b/drivers/input/misc/axp20x-pek.c
@@ -191,9 +191,10 @@ static ssize_t axp20x_store_attr_shutdown(struct device *dev,
 				 axp20x_pek->info->shutdown_mask, buf, count);
 }
 
-DEVICE_ATTR(startup, 0644, axp20x_show_attr_startup, axp20x_store_attr_startup);
-DEVICE_ATTR(shutdown, 0644, axp20x_show_attr_shutdown,
-	    axp20x_store_attr_shutdown);
+static DEVICE_ATTR(startup, 0644, axp20x_show_attr_startup,
+		   axp20x_store_attr_startup);
+static DEVICE_ATTR(shutdown, 0644, axp20x_show_attr_shutdown,
+		   axp20x_store_attr_shutdown);
 
 static struct attribute *axp20x_attrs[] = {
 	&dev_attr_startup.attr,
@@ -279,8 +280,7 @@ static int axp20x_pek_probe_input_device(struct axp20x_pek *axp20x_pek,
 		return error;
 	}
 
-	if (axp20x_pek->axp20x->variant == AXP288_ID)
-		enable_irq_wake(axp20x_pek->irq_dbr);
+	device_init_wakeup(&pdev->dev, true);
 
 	return 0;
 }
@@ -352,6 +352,40 @@ static int axp20x_pek_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused axp20x_pek_suspend(struct device *dev)
+{
+	struct axp20x_pek *axp20x_pek = dev_get_drvdata(dev);
+
+	/*
+	 * As nested threaded IRQs are not automatically disabled during
+	 * suspend, we must explicitly disable non-wakeup IRQs.
+	 */
+	if (device_may_wakeup(dev)) {
+		enable_irq_wake(axp20x_pek->irq_dbf);
+		enable_irq_wake(axp20x_pek->irq_dbr);
+	} else {
+		disable_irq(axp20x_pek->irq_dbf);
+		disable_irq(axp20x_pek->irq_dbr);
+	}
+
+	return 0;
+}
+
+static int __maybe_unused axp20x_pek_resume(struct device *dev)
+{
+	struct axp20x_pek *axp20x_pek = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev)) {
+		disable_irq_wake(axp20x_pek->irq_dbf);
+		disable_irq_wake(axp20x_pek->irq_dbr);
+	} else {
+		enable_irq(axp20x_pek->irq_dbf);
+		enable_irq(axp20x_pek->irq_dbr);
+	}
+
+	return 0;
+}
+
 static int __maybe_unused axp20x_pek_resume_noirq(struct device *dev)
 {
 	struct axp20x_pek *axp20x_pek = dev_get_drvdata(dev);
@@ -371,6 +405,7 @@ static int __maybe_unused axp20x_pek_resume_noirq(struct device *dev)
 }
 
 static const struct dev_pm_ops axp20x_pek_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(axp20x_pek_suspend, axp20x_pek_resume)
 #ifdef CONFIG_PM_SLEEP
 	.resume_noirq = axp20x_pek_resume_noirq,
 #endif
diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c
index bbf9ae9f3f0c..6adea8a3e8fb 100644
--- a/drivers/input/rmi4/rmi_f11.c
+++ b/drivers/input/rmi4/rmi_f11.c
@@ -412,6 +412,10 @@ struct f11_2d_sensor_queries {
 
 /* Defs for Ctrl0. */
 #define RMI_F11_REPORT_MODE_MASK        0x07
+#define RMI_F11_REPORT_MODE_CONTINUOUS  (0 << 0)
+#define RMI_F11_REPORT_MODE_REDUCED     (1 << 0)
+#define RMI_F11_REPORT_MODE_FS_CHANGE   (2 << 0)
+#define RMI_F11_REPORT_MODE_FP_CHANGE   (3 << 0)
 #define RMI_F11_ABS_POS_FILT            (1 << 3)
 #define RMI_F11_REL_POS_FILT            (1 << 4)
 #define RMI_F11_REL_BALLISTICS          (1 << 5)
@@ -1195,6 +1199,16 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 		ctrl->ctrl0_11[RMI_F11_DELTA_Y_THRESHOLD] =
 			sensor->axis_align.delta_y_threshold;
 
+	/*
+	 * If distance threshold values are set, switch to reduced reporting
+	 * mode so they actually get used by the controller.
+	 */
+	if (ctrl->ctrl0_11[RMI_F11_DELTA_X_THRESHOLD] ||
+	    ctrl->ctrl0_11[RMI_F11_DELTA_Y_THRESHOLD]) {
+		ctrl->ctrl0_11[0] &= ~RMI_F11_REPORT_MODE_MASK;
+		ctrl->ctrl0_11[0] |= RMI_F11_REPORT_MODE_REDUCED;
+	}
+
 	if (f11->sens_query.has_dribble) {
 		switch (sensor->dribble) {
 		case RMI_REG_STATE_OFF:
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index f3e18f8ef9ca..373a1646019e 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -165,6 +165,16 @@ config SERIO_MACEPS2
 	  To compile this driver as a module, choose M here: the
 	  module will be called maceps2.
 
+config SERIO_SGI_IOC3
+	tristate "SGI IOC3 PS/2 controller"
+	depends on SGI_MFD_IOC3
+	help
+	  Say Y here if you have an SGI Onyx2, SGI Octane or IOC3 PCI card
+	  and you want to attach and use a keyboard, mouse, or both.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ioc3kbd.
+
 config SERIO_LIBPS2
 	tristate "PS/2 driver library"
 	depends on SERIO_I8042 || SERIO_I8042=n
diff --git a/drivers/input/serio/Makefile b/drivers/input/serio/Makefile
index 67950a5ccb3f..6d97bad7b844 100644
--- a/drivers/input/serio/Makefile
+++ b/drivers/input/serio/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_HIL_MLC)		+= hp_sdc_mlc.o hil_mlc.o
 obj-$(CONFIG_SERIO_PCIPS2)	+= pcips2.o
 obj-$(CONFIG_SERIO_PS2MULT)	+= ps2mult.o
 obj-$(CONFIG_SERIO_MACEPS2)	+= maceps2.o
+obj-$(CONFIG_SERIO_SGI_IOC3)	+= ioc3kbd.o
 obj-$(CONFIG_SERIO_LIBPS2)	+= libps2.o
 obj-$(CONFIG_SERIO_RAW)		+= serio_raw.o
 obj-$(CONFIG_SERIO_AMS_DELTA)	+= ams_delta_serio.o
diff --git a/drivers/input/serio/apbps2.c b/drivers/input/serio/apbps2.c
index f290d5d146c3..594ac4e6f8ea 100644
--- a/drivers/input/serio/apbps2.c
+++ b/drivers/input/serio/apbps2.c
@@ -51,7 +51,7 @@ struct apbps2_regs {
 
 struct apbps2_priv {
 	struct serio		*io;
-	struct apbps2_regs	*regs;
+	struct apbps2_regs	__iomem *regs;
 };
 
 static int apbps2_idx;
diff --git a/drivers/input/serio/hyperv-keyboard.c b/drivers/input/serio/hyperv-keyboard.c
index e486a8a74c40..df4e9f6f4529 100644
--- a/drivers/input/serio/hyperv-keyboard.c
+++ b/drivers/input/serio/hyperv-keyboard.c
@@ -259,6 +259,8 @@ static int hv_kbd_connect_to_vsp(struct hv_device *hv_dev)
 	u32 proto_status;
 	int error;
 
+	reinit_completion(&kbd_dev->wait_event);
+
 	request = &kbd_dev->protocol_req;
 	memset(request, 0, sizeof(struct synth_kbd_protocol_request));
 	request->header.type = __cpu_to_le32(SYNTH_KBD_PROTOCOL_REQUEST);
@@ -380,6 +382,29 @@ static int hv_kbd_remove(struct hv_device *hv_dev)
 	return 0;
 }
 
+static int hv_kbd_suspend(struct hv_device *hv_dev)
+{
+	vmbus_close(hv_dev->channel);
+
+	return 0;
+}
+
+static int hv_kbd_resume(struct hv_device *hv_dev)
+{
+	int ret;
+
+	ret = vmbus_open(hv_dev->channel,
+			 KBD_VSC_SEND_RING_BUFFER_SIZE,
+			 KBD_VSC_RECV_RING_BUFFER_SIZE,
+			 NULL, 0,
+			 hv_kbd_on_channel_callback,
+			 hv_dev);
+	if (ret == 0)
+		ret = hv_kbd_connect_to_vsp(hv_dev);
+
+	return ret;
+}
+
 static const struct hv_vmbus_device_id id_table[] = {
 	/* Keyboard guid */
 	{ HV_KBD_GUID, },
@@ -393,6 +418,8 @@ static struct  hv_driver hv_kbd_drv = {
 	.id_table = id_table,
 	.probe = hv_kbd_probe,
 	.remove = hv_kbd_remove,
+	.suspend = hv_kbd_suspend,
+	.resume = hv_kbd_resume,
 	.driver = {
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
diff --git a/drivers/input/serio/ioc3kbd.c b/drivers/input/serio/ioc3kbd.c
new file mode 100644
index 000000000000..d51bfe912db5
--- /dev/null
+++ b/drivers/input/serio/ioc3kbd.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SGI IOC3 PS/2 controller driver for linux
+ *
+ * Copyright (C) 2019 Thomas Bogendoerfer <tbogendoerfer@suse.de>
+ *
+ * Based on code Copyright (C) 2005 Stanislaw Skowronek <skylark@unaligned.org>
+ *               Copyright (C) 2009 Johannes Dickgreber <tanzy@gmx.de>
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/serio.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include <asm/sn/ioc3.h>
+
+struct ioc3kbd_data {
+	struct ioc3_serioregs __iomem *regs;
+	struct serio *kbd, *aux;
+	bool kbd_exists, aux_exists;
+	int irq;
+};
+
+static int ioc3kbd_wait(struct ioc3_serioregs __iomem *regs, u32 mask)
+{
+	unsigned long timeout = 0;
+
+	while ((readl(&regs->km_csr) & mask) && (timeout < 250)) {
+		udelay(50);
+		timeout++;
+	}
+	return (timeout >= 250) ? -ETIMEDOUT : 0;
+}
+
+static int ioc3kbd_write(struct serio *dev, u8 val)
+{
+	struct ioc3kbd_data *d = dev->port_data;
+	int ret;
+
+	ret = ioc3kbd_wait(d->regs, KM_CSR_K_WRT_PEND);
+	if (ret)
+		return ret;
+
+	writel(val, &d->regs->k_wd);
+
+	return 0;
+}
+
+static int ioc3kbd_start(struct serio *dev)
+{
+	struct ioc3kbd_data *d = dev->port_data;
+
+	d->kbd_exists = true;
+	return 0;
+}
+
+static void ioc3kbd_stop(struct serio *dev)
+{
+	struct ioc3kbd_data *d = dev->port_data;
+
+	d->kbd_exists = false;
+}
+
+static int ioc3aux_write(struct serio *dev, u8 val)
+{
+	struct ioc3kbd_data *d = dev->port_data;
+	int ret;
+
+	ret = ioc3kbd_wait(d->regs, KM_CSR_M_WRT_PEND);
+	if (ret)
+		return ret;
+
+	writel(val, &d->regs->m_wd);
+
+	return 0;
+}
+
+static int ioc3aux_start(struct serio *dev)
+{
+	struct ioc3kbd_data *d = dev->port_data;
+
+	d->aux_exists = true;
+	return 0;
+}
+
+static void ioc3aux_stop(struct serio *dev)
+{
+	struct ioc3kbd_data *d = dev->port_data;
+
+	d->aux_exists = false;
+}
+
+static void ioc3kbd_process_data(struct serio *dev, u32 data)
+{
+	if (data & KM_RD_VALID_0)
+		serio_interrupt(dev, (data >> KM_RD_DATA_0_SHIFT) & 0xff, 0);
+	if (data & KM_RD_VALID_1)
+		serio_interrupt(dev, (data >> KM_RD_DATA_1_SHIFT) & 0xff, 0);
+	if (data & KM_RD_VALID_2)
+		serio_interrupt(dev, (data >> KM_RD_DATA_2_SHIFT) & 0xff, 0);
+}
+
+static irqreturn_t ioc3kbd_intr(int itq, void *dev_id)
+{
+	struct ioc3kbd_data *d = dev_id;
+	u32 data_k, data_m;
+
+	data_k = readl(&d->regs->k_rd);
+	if (d->kbd_exists)
+		ioc3kbd_process_data(d->kbd, data_k);
+
+	data_m = readl(&d->regs->m_rd);
+	if (d->aux_exists)
+		ioc3kbd_process_data(d->aux, data_m);
+
+	return IRQ_HANDLED;
+}
+
+static int ioc3kbd_probe(struct platform_device *pdev)
+{
+	struct ioc3_serioregs __iomem *regs;
+	struct device *dev = &pdev->dev;
+	struct ioc3kbd_data *d;
+	struct serio *sk, *sa;
+	int irq, ret;
+
+	regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return -ENXIO;
+
+	d = devm_kzalloc(dev, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	sk = kzalloc(sizeof(*sk), GFP_KERNEL);
+	if (!sk)
+		return -ENOMEM;
+
+	sa = kzalloc(sizeof(*sa), GFP_KERNEL);
+	if (!sa) {
+		kfree(sk);
+		return -ENOMEM;
+	}
+
+	sk->id.type = SERIO_8042;
+	sk->write = ioc3kbd_write;
+	sk->start = ioc3kbd_start;
+	sk->stop = ioc3kbd_stop;
+	snprintf(sk->name, sizeof(sk->name), "IOC3 keyboard %d", pdev->id);
+	snprintf(sk->phys, sizeof(sk->phys), "ioc3/serio%dkbd", pdev->id);
+	sk->port_data = d;
+	sk->dev.parent = dev;
+
+	sa->id.type = SERIO_8042;
+	sa->write = ioc3aux_write;
+	sa->start = ioc3aux_start;
+	sa->stop = ioc3aux_stop;
+	snprintf(sa->name, sizeof(sa->name), "IOC3 auxiliary %d", pdev->id);
+	snprintf(sa->phys, sizeof(sa->phys), "ioc3/serio%daux", pdev->id);
+	sa->port_data = d;
+	sa->dev.parent = dev;
+
+	d->regs = regs;
+	d->kbd = sk;
+	d->aux = sa;
+	d->irq = irq;
+
+	platform_set_drvdata(pdev, d);
+	serio_register_port(d->kbd);
+	serio_register_port(d->aux);
+
+	ret = request_irq(irq, ioc3kbd_intr, IRQF_SHARED, "ioc3-kbd", d);
+	if (ret) {
+		dev_err(dev, "could not request IRQ %d\n", irq);
+		serio_unregister_port(d->kbd);
+		serio_unregister_port(d->aux);
+		return ret;
+	}
+
+	/* enable ports */
+	writel(KM_CSR_K_CLAMP_3 | KM_CSR_M_CLAMP_3, &regs->km_csr);
+
+	return 0;
+}
+
+static int ioc3kbd_remove(struct platform_device *pdev)
+{
+	struct ioc3kbd_data *d = platform_get_drvdata(pdev);
+
+	free_irq(d->irq, d);
+
+	serio_unregister_port(d->kbd);
+	serio_unregister_port(d->aux);
+
+	return 0;
+}
+
+static struct platform_driver ioc3kbd_driver = {
+	.probe          = ioc3kbd_probe,
+	.remove         = ioc3kbd_remove,
+	.driver = {
+		.name = "ioc3-kbd",
+	},
+};
+module_platform_driver(ioc3kbd_driver);
+
+MODULE_AUTHOR("Thomas Bogendoerfer <tbogendoerfer@suse.de>");
+MODULE_DESCRIPTION("SGI IOC3 serio driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index 51ddb204ca1b..8fd7fc39c4fd 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -333,7 +333,8 @@ static int ads7846_read12_ser(struct device *dev, unsigned command)
 		req->xfer[1].len = 2;
 
 		/* for 1uF, settle for 800 usec; no cap, 100 usec.  */
-		req->xfer[1].delay_usecs = ts->vref_delay_usecs;
+		req->xfer[1].delay.value = ts->vref_delay_usecs;
+		req->xfer[1].delay.unit = SPI_DELAY_UNIT_USECS;
 		spi_message_add_tail(&req->xfer[1], &req->msg);
 
 		/* Enable reference voltage */
@@ -1018,7 +1019,8 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts,
 	 * have had enough time to stabilize.
 	 */
 	if (pdata->settle_delay_usecs) {
-		x->delay_usecs = pdata->settle_delay_usecs;
+		x->delay.value = pdata->settle_delay_usecs;
+		x->delay.unit = SPI_DELAY_UNIT_USECS;
 
 		x++;
 		x->tx_buf = &packet->read_y;
@@ -1061,7 +1063,8 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts,
 
 	/* ... maybe discard first sample ... */
 	if (pdata->settle_delay_usecs) {
-		x->delay_usecs = pdata->settle_delay_usecs;
+		x->delay.value = pdata->settle_delay_usecs;
+		x->delay.unit = SPI_DELAY_UNIT_USECS;
 
 		x++;
 		x->tx_buf = &packet->read_x;
@@ -1094,7 +1097,8 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts,
 
 		/* ... maybe discard first sample ... */
 		if (pdata->settle_delay_usecs) {
-			x->delay_usecs = pdata->settle_delay_usecs;
+			x->delay.value = pdata->settle_delay_usecs;
+			x->delay.unit = SPI_DELAY_UNIT_USECS;
 
 			x++;
 			x->tx_buf = &packet->read_z1;
@@ -1125,7 +1129,8 @@ static void ads7846_setup_spi_msg(struct ads7846 *ts,
 
 		/* ... maybe discard first sample ... */
 		if (pdata->settle_delay_usecs) {
-			x->delay_usecs = pdata->settle_delay_usecs;
+			x->delay.value = pdata->settle_delay_usecs;
+			x->delay.unit = SPI_DELAY_UNIT_USECS;
 
 			x++;
 			x->tx_buf = &packet->read_z2;
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index d61731c0037d..d2587724c52a 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -13,22 +13,23 @@
  *    http://www.glyn.com/Products/Displays
  */
 
-#include <linux/module.h>
-#include <linux/ratelimit.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/input.h>
-#include <linux/i2c.h>
-#include <linux/kernel.h>
-#include <linux/uaccess.h>
-#include <linux/delay.h>
 #include <linux/debugfs.h>
-#include <linux/slab.h>
+#include <linux/delay.h>
 #include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/input.h>
 #include <linux/input/mt.h>
 #include <linux/input/touchscreen.h>
-#include <asm/unaligned.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/ratelimit.h>
 #include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <asm/unaligned.h>
 
 #define WORK_REGISTER_THRESHOLD		0x00
 #define WORK_REGISTER_REPORT_RATE	0x08
@@ -1050,6 +1051,7 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client,
 {
 	const struct edt_i2c_chip_data *chip_data;
 	struct edt_ft5x06_ts_data *tsdata;
+	u8 buf[2] = { 0xfc, 0x00 };
 	struct input_dev *input;
 	unsigned long irq_flags;
 	int error;
@@ -1140,6 +1142,12 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client,
 		return error;
 	}
 
+	/*
+	 * Dummy read access. EP0700MLP1 returns bogus data on the first
+	 * register read access and ignores writes.
+	 */
+	edt_ft5x06_ts_readwrite(tsdata->client, 2, buf, 2, buf);
+
 	edt_ft5x06_ts_set_regs(tsdata);
 	edt_ft5x06_ts_get_defaults(&client->dev, tsdata);
 	edt_ft5x06_ts_get_parameters(tsdata);
@@ -1200,7 +1208,6 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client,
 		return error;
 
 	edt_ft5x06_ts_prepare_debugfs(tsdata, dev_driver_string(&client->dev));
-	device_init_wakeup(&client->dev, 1);
 
 	dev_dbg(&client->dev,
 		"EDT FT5x06 initialized: IRQ %d, WAKE pin %d, Reset pin %d.\n",
@@ -1220,29 +1227,6 @@ static int edt_ft5x06_ts_remove(struct i2c_client *client)
 	return 0;
 }
 
-static int __maybe_unused edt_ft5x06_ts_suspend(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	if (device_may_wakeup(dev))
-		enable_irq_wake(client->irq);
-
-	return 0;
-}
-
-static int __maybe_unused edt_ft5x06_ts_resume(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	if (device_may_wakeup(dev))
-		disable_irq_wake(client->irq);
-
-	return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(edt_ft5x06_ts_pm_ops,
-			 edt_ft5x06_ts_suspend, edt_ft5x06_ts_resume);
-
 static const struct edt_i2c_chip_data edt_ft5x06_data = {
 	.max_support_points = 5,
 };
@@ -1281,7 +1265,6 @@ static struct i2c_driver edt_ft5x06_ts_driver = {
 	.driver = {
 		.name = "edt_ft5x06",
 		.of_match_table = edt_ft5x06_of_match,
-		.pm = &edt_ft5x06_ts_pm_ops,
 	},
 	.id_table = edt_ft5x06_ts_id,
 	.probe    = edt_ft5x06_ts_probe,
diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c
index d4ad24ea54c8..491179967b29 100644
--- a/drivers/input/touchscreen/elants_i2c.c
+++ b/drivers/input/touchscreen/elants_i2c.c
@@ -59,8 +59,10 @@
 #define CMD_HEADER_WRITE	0x54
 #define CMD_HEADER_READ		0x53
 #define CMD_HEADER_6B_READ	0x5B
+#define CMD_HEADER_ROM_READ	0x96
 #define CMD_HEADER_RESP		0x52
 #define CMD_HEADER_6B_RESP	0x9B
+#define CMD_HEADER_ROM_RESP	0x95
 #define CMD_HEADER_HELLO	0x55
 #define CMD_HEADER_REK		0x66
 
@@ -200,6 +202,10 @@ static int elants_i2c_execute_command(struct i2c_client *client,
 		expected_response = CMD_HEADER_6B_RESP;
 		break;
 
+	case CMD_HEADER_ROM_READ:
+		expected_response = CMD_HEADER_ROM_RESP;
+		break;
+
 	default:
 		dev_err(&client->dev, "%s: invalid command %*ph\n",
 			__func__, (int)cmd_size, cmd);
@@ -556,6 +562,8 @@ static int elants_i2c_initialize(struct elants_data *ts)
 
 	/* hw version is available even if device in recovery state */
 	error2 = elants_i2c_query_hw_version(ts);
+	if (!error2)
+		error2 = elants_i2c_query_bc_version(ts);
 	if (!error)
 		error = error2;
 
@@ -564,8 +572,6 @@ static int elants_i2c_initialize(struct elants_data *ts)
 	if (!error)
 		error = elants_i2c_query_test_version(ts);
 	if (!error)
-		error = elants_i2c_query_bc_version(ts);
-	if (!error)
 		error = elants_i2c_query_ts_info(ts);
 
 	if (error)
@@ -613,39 +619,94 @@ static int elants_i2c_fw_write_page(struct i2c_client *client,
 	return error;
 }
 
+static int elants_i2c_validate_remark_id(struct elants_data *ts,
+					 const struct firmware *fw)
+{
+	struct i2c_client *client = ts->client;
+	int error;
+	const u8 cmd[] = { CMD_HEADER_ROM_READ, 0x80, 0x1F, 0x00, 0x00, 0x21 };
+	u8 resp[6] = { 0 };
+	u16 ts_remark_id = 0;
+	u16 fw_remark_id = 0;
+
+	/* Compare TS Remark ID and FW Remark ID */
+	error = elants_i2c_execute_command(client, cmd, sizeof(cmd),
+					resp, sizeof(resp));
+	if (error) {
+		dev_err(&client->dev, "failed to query Remark ID: %d\n", error);
+		return error;
+	}
+
+	ts_remark_id = get_unaligned_be16(&resp[3]);
+
+	fw_remark_id = get_unaligned_le16(&fw->data[fw->size - 4]);
+
+	if (fw_remark_id != ts_remark_id) {
+		dev_err(&client->dev,
+			"Remark ID Mismatched: ts_remark_id=0x%04x, fw_remark_id=0x%04x.\n",
+			ts_remark_id, fw_remark_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int elants_i2c_do_update_firmware(struct i2c_client *client,
 					 const struct firmware *fw,
 					 bool force)
 {
+	struct elants_data *ts = i2c_get_clientdata(client);
 	const u8 enter_iap[] = { 0x45, 0x49, 0x41, 0x50 };
 	const u8 enter_iap2[] = { 0x54, 0x00, 0x12, 0x34 };
 	const u8 iap_ack[] = { 0x55, 0xaa, 0x33, 0xcc };
-	const u8 close_idle[] = {0x54, 0x2c, 0x01, 0x01};
+	const u8 close_idle[] = { 0x54, 0x2c, 0x01, 0x01 };
 	u8 buf[HEADER_SIZE];
 	u16 send_id;
 	int page, n_fw_pages;
 	int error;
+	bool check_remark_id = ts->iap_version >= 0x60;
 
 	/* Recovery mode detection! */
 	if (force) {
 		dev_dbg(&client->dev, "Recovery mode procedure\n");
+
+		if (check_remark_id) {
+			error = elants_i2c_validate_remark_id(ts, fw);
+			if (error)
+				return error;
+		}
+
 		error = elants_i2c_send(client, enter_iap2, sizeof(enter_iap2));
+		if (error) {
+			dev_err(&client->dev, "failed to enter IAP mode: %d\n",
+				error);
+			return error;
+		}
 	} else {
 		/* Start IAP Procedure */
 		dev_dbg(&client->dev, "Normal IAP procedure\n");
+
 		/* Close idle mode */
 		error = elants_i2c_send(client, close_idle, sizeof(close_idle));
 		if (error)
 			dev_err(&client->dev, "Failed close idle: %d\n", error);
 		msleep(60);
+
 		elants_i2c_sw_reset(client);
 		msleep(20);
-		error = elants_i2c_send(client, enter_iap, sizeof(enter_iap));
-	}
 
-	if (error) {
-		dev_err(&client->dev, "failed to enter IAP mode: %d\n", error);
-		return error;
+		if (check_remark_id) {
+			error = elants_i2c_validate_remark_id(ts, fw);
+			if (error)
+				return error;
+		}
+
+		error = elants_i2c_send(client, enter_iap, sizeof(enter_iap));
+		if (error) {
+			dev_err(&client->dev, "failed to enter IAP mode: %d\n",
+				error);
+			return error;
+		}
 	}
 
 	msleep(20);
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 0b9d78a0f3ac..d2fade984999 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -82,7 +82,7 @@ config IOMMU_DEBUGFS
 config IOMMU_DEFAULT_PASSTHROUGH
 	bool "IOMMU passthrough by default"
 	depends on IOMMU_API
-        help
+	help
 	  Enable passthrough by default, removing the need to pass in
 	  iommu.passthrough=on or iommu=pt through command line. If this
 	  is enabled, you can still disable with iommu.passthrough=off
@@ -91,8 +91,8 @@ config IOMMU_DEFAULT_PASSTHROUGH
 	  If unsure, say N here.
 
 config OF_IOMMU
-       def_bool y
-       depends on OF && IOMMU_API
+	def_bool y
+	depends on OF && IOMMU_API
 
 # IOMMU-agnostic DMA-mapping layer
 config IOMMU_DMA
@@ -214,6 +214,7 @@ config INTEL_IOMMU_SVM
 	select PCI_PASID
 	select PCI_PRI
 	select MMU_NOTIFIER
+	select IOASID
 	help
 	  Shared Virtual Memory (SVM) provides a facility for devices
 	  to access DMA resources through process address space by
@@ -248,6 +249,18 @@ config INTEL_IOMMU_FLOPPY_WA
 	  workaround will setup a 1:1 mapping for the first
 	  16MiB to make floppy (an ISA device) work.
 
+config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
+	bool "Enable Intel IOMMU scalable mode by default"
+	depends on INTEL_IOMMU
+	help
+	  Selecting this option will enable by default the scalable mode if
+	  hardware presents the capability. The scalable mode is defined in
+	  VT-d 3.0. The scalable mode capability could be checked by reading
+	  /sys/devices/virtual/iommu/dmar*/intel-iommu/ecap. If this option
+	  is not selected, scalable mode support could also be enabled by
+	  passing intel_iommu=sm_on to the kernel. If not sure, please use
+	  the default value.
+
 config IRQ_REMAP
 	bool "Support for Interrupt Remapping"
 	depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI
@@ -356,7 +369,7 @@ config SPAPR_TCE_IOMMU
 
 # ARM IOMMU support
 config ARM_SMMU
-	bool "ARM Ltd. System MMU (SMMU) Support"
+	tristate "ARM Ltd. System MMU (SMMU) Support"
 	depends on (ARM64 || ARM) && MMU
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
@@ -368,6 +381,18 @@ config ARM_SMMU
 	  Say Y here if your SoC includes an IOMMU device implementing
 	  the ARM SMMU architecture.
 
+config ARM_SMMU_LEGACY_DT_BINDINGS
+	bool "Support the legacy \"mmu-masters\" devicetree bindings"
+	depends on ARM_SMMU=y && OF
+	help
+	  Support for the badly designed and deprecated "mmu-masters"
+	  devicetree bindings. This allows some DMA masters to attach
+	  to the SMMU but does not provide any support via the DMA API.
+	  If you're lucky, you might be able to get VFIO up and running.
+
+	  If you say Y here then you'll make me very sad. Instead, say N
+	  and move your firmware to the utopian future that was 2016.
+
 config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT
 	bool "Default to disabling bypass on ARM SMMU v1 and v2"
 	depends on ARM_SMMU
@@ -394,7 +419,7 @@ config ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT
 	  config.
 
 config ARM_SMMU_V3
-	bool "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
+	tristate "ARM Ltd. System MMU Version 3 (SMMUv3) Support"
 	depends on ARM64
 	select IOMMU_API
 	select IOMMU_IO_PGTABLE_LPAE
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 97814cc861ea..2104fb8afc06 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -14,7 +14,8 @@ obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu-mod.o
+arm-smmu-mod-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index bd25674ee4db..aac132bd1ef0 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -230,11 +230,8 @@ static struct pci_dev *setup_aliases(struct device *dev)
 	 */
 	ivrs_alias = amd_iommu_alias_table[pci_dev_id(pdev)];
 	if (ivrs_alias != pci_dev_id(pdev) &&
-	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
-		pci_add_dma_alias(pdev, ivrs_alias & 0xff);
-		pci_info(pdev, "Added PCI DMA alias %02x.%d\n",
-			PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias));
-	}
+	    PCI_BUS_NUM(ivrs_alias) == pdev->bus->number)
+		pci_add_dma_alias(pdev, ivrs_alias & 0xff, 1);
 
 	clone_aliases(pdev);
 
@@ -2297,7 +2294,6 @@ int __init amd_iommu_init_api(void)
 int __init amd_iommu_init_dma_ops(void)
 {
 	swiotlb        = (iommu_default_passthrough() || sme_me_mask) ? 1 : 0;
-	iommu_detected = 1;
 
 	if (amd_iommu_unmap_flush)
 		pr_info("IO/TLB flush on unmap enabled\n");
@@ -2641,15 +2637,6 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 	list_add_tail(&region->list, head);
 }
 
-static void amd_iommu_put_resv_regions(struct device *dev,
-				     struct list_head *head)
-{
-	struct iommu_resv_region *entry, *next;
-
-	list_for_each_entry_safe(entry, next, head, list)
-		kfree(entry);
-}
-
 static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
 					 struct device *dev)
 {
@@ -2688,7 +2675,7 @@ const struct iommu_ops amd_iommu_ops = {
 	.device_group = amd_iommu_device_group,
 	.domain_get_attr = amd_iommu_domain_get_attr,
 	.get_resv_regions = amd_iommu_get_resv_regions,
-	.put_resv_regions = amd_iommu_put_resv_regions,
+	.put_resv_regions = generic_iommu_put_resv_regions,
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 823cc4ef51fd..2759a8d57b7f 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -71,6 +71,8 @@
 #define IVHD_FLAG_ISOC_EN_MASK          0x08
 
 #define IVMD_FLAG_EXCL_RANGE            0x08
+#define IVMD_FLAG_IW                    0x04
+#define IVMD_FLAG_IR                    0x02
 #define IVMD_FLAG_UNITY_MAP             0x01
 
 #define ACPI_DEVFLAG_INITPASS           0x01
@@ -147,7 +149,7 @@ bool amd_iommu_dump;
 bool amd_iommu_irq_remap __read_mostly;
 
 int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC;
-static int amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
+static int amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
 
 static bool amd_iommu_detected;
 static bool __initdata amd_iommu_disabled;
@@ -714,7 +716,7 @@ static void iommu_enable_ppr_log(struct amd_iommu *iommu)
 	writel(0x00, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
 	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 
-	iommu_feature_enable(iommu, CONTROL_PPFLOG_EN);
+	iommu_feature_enable(iommu, CONTROL_PPRLOG_EN);
 	iommu_feature_enable(iommu, CONTROL_PPR_EN);
 }
 
@@ -1116,21 +1118,17 @@ static int __init add_early_maps(void)
  */
 static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
 {
-	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
-
 	if (!(m->flags & IVMD_FLAG_EXCL_RANGE))
 		return;
 
-	if (iommu) {
-		/*
-		 * We only can configure exclusion ranges per IOMMU, not
-		 * per device. But we can enable the exclusion range per
-		 * device. This is done here
-		 */
-		set_dev_entry_bit(devid, DEV_ENTRY_EX);
-		iommu->exclusion_start = m->range_start;
-		iommu->exclusion_length = m->range_length;
-	}
+	/*
+	 * Treat per-device exclusion ranges as r/w unity-mapped regions
+	 * since some buggy BIOSes might lead to the overwritten exclusion
+	 * range (exclusion_start and exclusion_length members). This
+	 * happens when there are multiple exclusion ranges (IVMD entries)
+	 * defined in ACPI table.
+	 */
+	m->flags = (IVMD_FLAG_IW | IVMD_FLAG_IR | IVMD_FLAG_UNITY_MAP);
 }
 
 /*
@@ -1523,8 +1521,6 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
 		if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
-		if (((h->efr_attr & (0x1 << IOMMU_FEAT_XTSUP_SHIFT)) == 0))
-			amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
 		break;
 	case 0x11:
 	case 0x40:
@@ -1534,8 +1530,15 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
 		if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
-		if (((h->efr_reg & (0x1 << IOMMU_EFR_XTSUP_SHIFT)) == 0))
-			amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE;
+		/*
+		 * Note: Since iommu_update_intcapxt() leverages
+		 * the IOMMU MMIO access to MSI capability block registers
+		 * for MSI address lo/hi/data, we need to check both
+		 * EFR[XtSup] and EFR[MsiCapMmioSup] for x2APIC support.
+		 */
+		if ((h->efr_reg & BIT(IOMMU_EFR_XTSUP_SHIFT)) &&
+		    (h->efr_reg & BIT(IOMMU_EFR_MSICAPMMIOSUP_SHIFT)))
+			amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE;
 		break;
 	default:
 		return -EINVAL;
@@ -1727,7 +1730,6 @@ static const struct attribute_group *amd_iommu_groups[] = {
 static int __init iommu_init_pci(struct amd_iommu *iommu)
 {
 	int cap_ptr = iommu->cap_ptr;
-	u32 range, misc, low, high;
 	int ret;
 
 	iommu->dev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(iommu->devid),
@@ -1740,19 +1742,12 @@ static int __init iommu_init_pci(struct amd_iommu *iommu)
 
 	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
 			      &iommu->cap);
-	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET,
-			      &range);
-	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET,
-			      &misc);
 
 	if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
 		amd_iommu_iotlb_sup = false;
 
 	/* read extended feature bits */
-	low  = readl(iommu->mmio_base + MMIO_EXT_FEATURES);
-	high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4);
-
-	iommu->features = ((u64)high << 32) | low;
+	iommu->features = readq(iommu->mmio_base + MMIO_EXT_FEATURES);
 
 	if (iommu_feature(iommu, FEATURE_GT)) {
 		int glxval;
@@ -1996,8 +1991,8 @@ static int iommu_init_intcapxt(struct amd_iommu *iommu)
 	struct irq_affinity_notify *notify = &iommu->intcapxt_notify;
 
 	/**
-	 * IntCapXT requires XTSup=1, which can be inferred
-	 * amd_iommu_xt_mode.
+	 * IntCapXT requires XTSup=1 and MsiCapMmioSup=1,
+	 * which can be inferred from amd_iommu_xt_mode.
 	 */
 	if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE)
 		return 0;
@@ -2044,7 +2039,7 @@ enable_faults:
 	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
 
 	if (iommu->ppr_log != NULL)
-		iommu_feature_enable(iommu, CONTROL_PPFINT_EN);
+		iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
 
 	iommu_ga_log_enable(iommu);
 
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index f52f59d5c6bd..f8d01d6b00da 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -147,8 +147,8 @@
 #define CONTROL_COHERENT_EN     0x0aULL
 #define CONTROL_ISOC_EN         0x0bULL
 #define CONTROL_CMDBUF_EN       0x0cULL
-#define CONTROL_PPFLOG_EN       0x0dULL
-#define CONTROL_PPFINT_EN       0x0eULL
+#define CONTROL_PPRLOG_EN       0x0dULL
+#define CONTROL_PPRINT_EN       0x0eULL
 #define CONTROL_PPR_EN          0x0fULL
 #define CONTROL_GT_EN           0x10ULL
 #define CONTROL_GA_EN           0x11ULL
@@ -377,12 +377,12 @@
 #define IOMMU_CAP_EFR     27
 
 /* IOMMU Feature Reporting Field (for IVHD type 10h */
-#define IOMMU_FEAT_XTSUP_SHIFT	0
 #define IOMMU_FEAT_GASUP_SHIFT	6
 
 /* IOMMU Extended Feature Register (EFR) */
 #define IOMMU_EFR_XTSUP_SHIFT	2
 #define IOMMU_EFR_GASUP_SHIFT	7
+#define IOMMU_EFR_MSICAPMMIOSUP_SHIFT	46
 
 #define MAX_DOMAIN_ID 65536
 
@@ -463,7 +463,6 @@ struct amd_irte_ops;
  * independent of their use.
  */
 struct protection_domain {
-	struct list_head list;  /* for list of all protection domains */
 	struct list_head dev_list; /* List of all devices in this domain */
 	struct iommu_domain domain; /* generic domain handle used by
 				       iommu core code */
diff --git a/drivers/iommu/arm-smmu-impl.c b/drivers/iommu/arm-smmu-impl.c
index b2fe72a8f019..74d97a886e93 100644
--- a/drivers/iommu/arm-smmu-impl.c
+++ b/drivers/iommu/arm-smmu-impl.c
@@ -119,7 +119,7 @@ int arm_mmu500_reset(struct arm_smmu_device *smmu)
 	 * Secure has also cleared SACR.CACHE_LOCK for this to take effect...
 	 */
 	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID7);
-	major = FIELD_GET(ID7_MAJOR, reg);
+	major = FIELD_GET(ARM_SMMU_ID7_MAJOR, reg);
 	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sACR);
 	if (major >= 2)
 		reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index effe72eb89e7..aa3ac2a03807 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -21,8 +21,7 @@
 #include <linux/io-pgtable.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
-#include <linux/init.h>
-#include <linux/moduleparam.h>
+#include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
@@ -224,9 +223,15 @@
 
 #define STRTAB_STE_0_S1FMT		GENMASK_ULL(5, 4)
 #define STRTAB_STE_0_S1FMT_LINEAR	0
+#define STRTAB_STE_0_S1FMT_64K_L2	2
 #define STRTAB_STE_0_S1CTXPTR_MASK	GENMASK_ULL(51, 6)
 #define STRTAB_STE_0_S1CDMAX		GENMASK_ULL(63, 59)
 
+#define STRTAB_STE_1_S1DSS		GENMASK_ULL(1, 0)
+#define STRTAB_STE_1_S1DSS_TERMINATE	0x0
+#define STRTAB_STE_1_S1DSS_BYPASS	0x1
+#define STRTAB_STE_1_S1DSS_SSID0	0x2
+
 #define STRTAB_STE_1_S1C_CACHE_NC	0UL
 #define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
 #define STRTAB_STE_1_S1C_CACHE_WT	2UL
@@ -251,6 +256,13 @@
 
 #define STRTAB_STE_2_S2VMID		GENMASK_ULL(15, 0)
 #define STRTAB_STE_2_VTCR		GENMASK_ULL(50, 32)
+#define STRTAB_STE_2_VTCR_S2T0SZ	GENMASK_ULL(5, 0)
+#define STRTAB_STE_2_VTCR_S2SL0		GENMASK_ULL(7, 6)
+#define STRTAB_STE_2_VTCR_S2IR0		GENMASK_ULL(9, 8)
+#define STRTAB_STE_2_VTCR_S2OR0		GENMASK_ULL(11, 10)
+#define STRTAB_STE_2_VTCR_S2SH0		GENMASK_ULL(13, 12)
+#define STRTAB_STE_2_VTCR_S2TG		GENMASK_ULL(15, 14)
+#define STRTAB_STE_2_VTCR_S2PS		GENMASK_ULL(18, 16)
 #define STRTAB_STE_2_S2AA64		(1UL << 51)
 #define STRTAB_STE_2_S2ENDI		(1UL << 52)
 #define STRTAB_STE_2_S2PTW		(1UL << 54)
@@ -258,30 +270,34 @@
 
 #define STRTAB_STE_3_S2TTB_MASK		GENMASK_ULL(51, 4)
 
-/* Context descriptor (stage-1 only) */
+/*
+ * Context descriptors.
+ *
+ * Linear: when less than 1024 SSIDs are supported
+ * 2lvl: at most 1024 L1 entries,
+ *       1024 lazy entries per table.
+ */
+#define CTXDESC_SPLIT			10
+#define CTXDESC_L2_ENTRIES		(1 << CTXDESC_SPLIT)
+
+#define CTXDESC_L1_DESC_DWORDS		1
+#define CTXDESC_L1_DESC_V		(1UL << 0)
+#define CTXDESC_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 12)
+
 #define CTXDESC_CD_DWORDS		8
 #define CTXDESC_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
-#define ARM64_TCR_T0SZ			GENMASK_ULL(5, 0)
 #define CTXDESC_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
-#define ARM64_TCR_TG0			GENMASK_ULL(15, 14)
 #define CTXDESC_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
-#define ARM64_TCR_IRGN0			GENMASK_ULL(9, 8)
 #define CTXDESC_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
-#define ARM64_TCR_ORGN0			GENMASK_ULL(11, 10)
 #define CTXDESC_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
-#define ARM64_TCR_SH0			GENMASK_ULL(13, 12)
 #define CTXDESC_CD_0_TCR_EPD0		(1ULL << 14)
-#define ARM64_TCR_EPD0			(1ULL << 7)
 #define CTXDESC_CD_0_TCR_EPD1		(1ULL << 30)
-#define ARM64_TCR_EPD1			(1ULL << 23)
 
 #define CTXDESC_CD_0_ENDI		(1UL << 15)
 #define CTXDESC_CD_0_V			(1UL << 31)
 
 #define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
-#define ARM64_TCR_IPS			GENMASK_ULL(34, 32)
 #define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
-#define ARM64_TCR_TBI0			(1ULL << 37)
 
 #define CTXDESC_CD_0_AA64		(1UL << 41)
 #define CTXDESC_CD_0_S			(1UL << 44)
@@ -292,9 +308,11 @@
 
 #define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
 
-/* Convert between AArch64 (CPU) TCR format and SMMU CD format */
-#define ARM_SMMU_TCR2CD(tcr, fld)	FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \
-					FIELD_GET(ARM64_TCR_##fld, tcr))
+/*
+ * When the SMMU only supports linear context descriptor tables, pick a
+ * reasonable size limit (64kB).
+ */
+#define CTXDESC_LINEAR_CDMAX		ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3))
 
 /* Command queue */
 #define CMDQ_ENT_SZ_SHIFT		4
@@ -323,6 +341,7 @@
 #define CMDQ_PREFETCH_1_SIZE		GENMASK_ULL(4, 0)
 #define CMDQ_PREFETCH_1_ADDR_MASK	GENMASK_ULL(63, 12)
 
+#define CMDQ_CFGI_0_SSID		GENMASK_ULL(31, 12)
 #define CMDQ_CFGI_0_SID			GENMASK_ULL(63, 32)
 #define CMDQ_CFGI_1_LEAF		(1UL << 0)
 #define CMDQ_CFGI_1_RANGE		GENMASK_ULL(4, 0)
@@ -384,10 +403,6 @@
 #define MSI_IOVA_BASE			0x8000000
 #define MSI_IOVA_LENGTH			0x100000
 
-/*
- * not really modular, but the easiest way to keep compat with existing
- * bootargs behaviour is to continue using module_param_named here.
- */
 static bool disable_bypass = 1;
 module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
@@ -440,8 +455,11 @@ struct arm_smmu_cmdq_ent {
 
 		#define CMDQ_OP_CFGI_STE	0x3
 		#define CMDQ_OP_CFGI_ALL	0x4
+		#define CMDQ_OP_CFGI_CD		0x5
+		#define CMDQ_OP_CFGI_CD_ALL	0x6
 		struct {
 			u32			sid;
+			u32			ssid;
 			union {
 				bool		leaf;
 				u8		span;
@@ -547,16 +565,30 @@ struct arm_smmu_strtab_l1_desc {
 	dma_addr_t			l2ptr_dma;
 };
 
+struct arm_smmu_ctx_desc {
+	u16				asid;
+	u64				ttbr;
+	u64				tcr;
+	u64				mair;
+};
+
+struct arm_smmu_l1_ctx_desc {
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_ctx_desc_cfg {
+	__le64				*cdtab;
+	dma_addr_t			cdtab_dma;
+	struct arm_smmu_l1_ctx_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+};
+
 struct arm_smmu_s1_cfg {
-	__le64				*cdptr;
-	dma_addr_t			cdptr_dma;
-
-	struct arm_smmu_ctx_desc {
-		u16	asid;
-		u64	ttbr;
-		u64	tcr;
-		u64	mair;
-	}				cd;
+	struct arm_smmu_ctx_desc_cfg	cdcfg;
+	struct arm_smmu_ctx_desc	cd;
+	u8				s1fmt;
+	u8				s1cdmax;
 };
 
 struct arm_smmu_s2_cfg {
@@ -638,6 +670,7 @@ struct arm_smmu_master {
 	u32				*sids;
 	unsigned int			num_sids;
 	bool				ats_enabled;
+	unsigned int			ssid_bits;
 };
 
 /* SMMU private data for an IOMMU domain */
@@ -847,15 +880,22 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		cmd[1] |= FIELD_PREP(CMDQ_PREFETCH_1_SIZE, ent->prefetch.size);
 		cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK;
 		break;
+	case CMDQ_OP_CFGI_CD:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SSID, ent->cfgi.ssid);
+		/* Fallthrough */
 	case CMDQ_OP_CFGI_STE:
 		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf);
 		break;
+	case CMDQ_OP_CFGI_CD_ALL:
+		cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid);
+		break;
 	case CMDQ_OP_CFGI_ALL:
 		/* Cover the entire SID range */
 		cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31);
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
+		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid);
 		cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid);
 		cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf);
 		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
@@ -1443,50 +1483,238 @@ static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
 }
 
 /* Context descriptor manipulation functions */
-static u64 arm_smmu_cpu_tcr_to_cd(u64 tcr)
+static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
+			     int ssid, bool leaf)
 {
-	u64 val = 0;
+	size_t i;
+	unsigned long flags;
+	struct arm_smmu_master *master;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode	= CMDQ_OP_CFGI_CD,
+		.cfgi	= {
+			.ssid	= ssid,
+			.leaf	= leaf,
+		},
+	};
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
+		for (i = 0; i < master->num_sids; i++) {
+			cmd.cfgi.sid = master->sids[i];
+			arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+		}
+	}
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+
+	arm_smmu_cmdq_issue_sync(smmu);
+}
 
-	/* Repack the TCR. Just care about TTBR0 for now */
-	val |= ARM_SMMU_TCR2CD(tcr, T0SZ);
-	val |= ARM_SMMU_TCR2CD(tcr, TG0);
-	val |= ARM_SMMU_TCR2CD(tcr, IRGN0);
-	val |= ARM_SMMU_TCR2CD(tcr, ORGN0);
-	val |= ARM_SMMU_TCR2CD(tcr, SH0);
-	val |= ARM_SMMU_TCR2CD(tcr, EPD0);
-	val |= ARM_SMMU_TCR2CD(tcr, EPD1);
-	val |= ARM_SMMU_TCR2CD(tcr, IPS);
+static int arm_smmu_alloc_cd_leaf_table(struct arm_smmu_device *smmu,
+					struct arm_smmu_l1_ctx_desc *l1_desc)
+{
+	size_t size = CTXDESC_L2_ENTRIES * (CTXDESC_CD_DWORDS << 3);
 
-	return val;
+	l1_desc->l2ptr = dmam_alloc_coherent(smmu->dev, size,
+					     &l1_desc->l2ptr_dma, GFP_KERNEL);
+	if (!l1_desc->l2ptr) {
+		dev_warn(smmu->dev,
+			 "failed to allocate context descriptor table\n");
+		return -ENOMEM;
+	}
+	return 0;
 }
 
-static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
-				    struct arm_smmu_s1_cfg *cfg)
+static void arm_smmu_write_cd_l1_desc(__le64 *dst,
+				      struct arm_smmu_l1_ctx_desc *l1_desc)
 {
-	u64 val;
+	u64 val = (l1_desc->l2ptr_dma & CTXDESC_L1_DESC_L2PTR_MASK) |
+		  CTXDESC_L1_DESC_V;
+
+	WRITE_ONCE(*dst, cpu_to_le64(val));
+}
+
+static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain,
+				   u32 ssid)
+{
+	__le64 *l1ptr;
+	unsigned int idx;
+	struct arm_smmu_l1_ctx_desc *l1_desc;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &smmu_domain->s1_cfg.cdcfg;
 
+	if (smmu_domain->s1_cfg.s1fmt == STRTAB_STE_0_S1FMT_LINEAR)
+		return cdcfg->cdtab + ssid * CTXDESC_CD_DWORDS;
+
+	idx = ssid >> CTXDESC_SPLIT;
+	l1_desc = &cdcfg->l1_desc[idx];
+	if (!l1_desc->l2ptr) {
+		if (arm_smmu_alloc_cd_leaf_table(smmu, l1_desc))
+			return NULL;
+
+		l1ptr = cdcfg->cdtab + idx * CTXDESC_L1_DESC_DWORDS;
+		arm_smmu_write_cd_l1_desc(l1ptr, l1_desc);
+		/* An invalid L1CD can be cached */
+		arm_smmu_sync_cd(smmu_domain, ssid, false);
+	}
+	idx = ssid & (CTXDESC_L2_ENTRIES - 1);
+	return l1_desc->l2ptr + idx * CTXDESC_CD_DWORDS;
+}
+
+static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
+				   int ssid, struct arm_smmu_ctx_desc *cd)
+{
 	/*
-	 * We don't need to issue any invalidation here, as we'll invalidate
-	 * the STE when installing the new entry anyway.
+	 * This function handles the following cases:
+	 *
+	 * (1) Install primary CD, for normal DMA traffic (SSID = 0).
+	 * (2) Install a secondary CD, for SID+SSID traffic.
+	 * (3) Update ASID of a CD. Atomically write the first 64 bits of the
+	 *     CD, then invalidate the old entry and mappings.
+	 * (4) Remove a secondary CD.
 	 */
-	val = arm_smmu_cpu_tcr_to_cd(cfg->cd.tcr) |
+	u64 val;
+	bool cd_live;
+	__le64 *cdptr;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+
+	if (WARN_ON(ssid >= (1 << smmu_domain->s1_cfg.s1cdmax)))
+		return -E2BIG;
+
+	cdptr = arm_smmu_get_cd_ptr(smmu_domain, ssid);
+	if (!cdptr)
+		return -ENOMEM;
+
+	val = le64_to_cpu(cdptr[0]);
+	cd_live = !!(val & CTXDESC_CD_0_V);
+
+	if (!cd) { /* (4) */
+		val = 0;
+	} else if (cd_live) { /* (3) */
+		val &= ~CTXDESC_CD_0_ASID;
+		val |= FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid);
+		/*
+		 * Until CD+TLB invalidation, both ASIDs may be used for tagging
+		 * this substream's traffic
+		 */
+	} else { /* (1) and (2) */
+		cdptr[1] = cpu_to_le64(cd->ttbr & CTXDESC_CD_1_TTB0_MASK);
+		cdptr[2] = 0;
+		cdptr[3] = cpu_to_le64(cd->mair);
+
+		/*
+		 * STE is live, and the SMMU might read dwords of this CD in any
+		 * order. Ensure that it observes valid values before reading
+		 * V=1.
+		 */
+		arm_smmu_sync_cd(smmu_domain, ssid, true);
+
+		val = cd->tcr |
 #ifdef __BIG_ENDIAN
-	      CTXDESC_CD_0_ENDI |
+			CTXDESC_CD_0_ENDI |
 #endif
-	      CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET |
-	      CTXDESC_CD_0_AA64 | FIELD_PREP(CTXDESC_CD_0_ASID, cfg->cd.asid) |
-	      CTXDESC_CD_0_V;
+			CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET |
+			CTXDESC_CD_0_AA64 |
+			FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) |
+			CTXDESC_CD_0_V;
 
-	/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
-	if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
-		val |= CTXDESC_CD_0_S;
+		/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
+		if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
+			val |= CTXDESC_CD_0_S;
+	}
 
-	cfg->cdptr[0] = cpu_to_le64(val);
+	/*
+	 * The SMMU accesses 64-bit values atomically. See IHI0070Ca 3.21.3
+	 * "Configuration structures and configuration invalidation completion"
+	 *
+	 *   The size of single-copy atomic reads made by the SMMU is
+	 *   IMPLEMENTATION DEFINED but must be at least 64 bits. Any single
+	 *   field within an aligned 64-bit span of a structure can be altered
+	 *   without first making the structure invalid.
+	 */
+	WRITE_ONCE(cdptr[0], cpu_to_le64(val));
+	arm_smmu_sync_cd(smmu_domain, ssid, true);
+	return 0;
+}
+
+static int arm_smmu_alloc_cd_tables(struct arm_smmu_domain *smmu_domain)
+{
+	int ret;
+	size_t l1size;
+	size_t max_contexts;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &cfg->cdcfg;
+
+	max_contexts = 1 << cfg->s1cdmax;
+
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB) ||
+	    max_contexts <= CTXDESC_L2_ENTRIES) {
+		cfg->s1fmt = STRTAB_STE_0_S1FMT_LINEAR;
+		cdcfg->num_l1_ents = max_contexts;
 
-	val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK;
-	cfg->cdptr[1] = cpu_to_le64(val);
+		l1size = max_contexts * (CTXDESC_CD_DWORDS << 3);
+	} else {
+		cfg->s1fmt = STRTAB_STE_0_S1FMT_64K_L2;
+		cdcfg->num_l1_ents = DIV_ROUND_UP(max_contexts,
+						  CTXDESC_L2_ENTRIES);
+
+		cdcfg->l1_desc = devm_kcalloc(smmu->dev, cdcfg->num_l1_ents,
+					      sizeof(*cdcfg->l1_desc),
+					      GFP_KERNEL);
+		if (!cdcfg->l1_desc)
+			return -ENOMEM;
+
+		l1size = cdcfg->num_l1_ents * (CTXDESC_L1_DESC_DWORDS << 3);
+	}
+
+	cdcfg->cdtab = dmam_alloc_coherent(smmu->dev, l1size, &cdcfg->cdtab_dma,
+					   GFP_KERNEL);
+	if (!cdcfg->cdtab) {
+		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
+		ret = -ENOMEM;
+		goto err_free_l1;
+	}
+
+	return 0;
 
-	cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair);
+err_free_l1:
+	if (cdcfg->l1_desc) {
+		devm_kfree(smmu->dev, cdcfg->l1_desc);
+		cdcfg->l1_desc = NULL;
+	}
+	return ret;
+}
+
+static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain)
+{
+	int i;
+	size_t size, l1size;
+	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_ctx_desc_cfg *cdcfg = &smmu_domain->s1_cfg.cdcfg;
+
+	if (cdcfg->l1_desc) {
+		size = CTXDESC_L2_ENTRIES * (CTXDESC_CD_DWORDS << 3);
+
+		for (i = 0; i < cdcfg->num_l1_ents; i++) {
+			if (!cdcfg->l1_desc[i].l2ptr)
+				continue;
+
+			dmam_free_coherent(smmu->dev, size,
+					   cdcfg->l1_desc[i].l2ptr,
+					   cdcfg->l1_desc[i].l2ptr_dma);
+		}
+		devm_kfree(smmu->dev, cdcfg->l1_desc);
+		cdcfg->l1_desc = NULL;
+
+		l1size = cdcfg->num_l1_ents * (CTXDESC_L1_DESC_DWORDS << 3);
+	} else {
+		l1size = cdcfg->num_l1_ents * (CTXDESC_CD_DWORDS << 3);
+	}
+
+	dmam_free_coherent(smmu->dev, l1size, cdcfg->cdtab, cdcfg->cdtab_dma);
+	cdcfg->cdtab_dma = 0;
+	cdcfg->cdtab = NULL;
 }
 
 /* Stream table manipulation functions */
@@ -1608,6 +1836,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	if (s1_cfg) {
 		BUG_ON(ste_live);
 		dst[1] = cpu_to_le64(
+			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) |
@@ -1617,8 +1846,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
 			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
-		val |= (s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
-			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS);
+		val |= (s1_cfg->cdcfg.cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
+			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
+			FIELD_PREP(STRTAB_STE_0_S1CDMAX, s1_cfg->s1cdmax) |
+			FIELD_PREP(STRTAB_STE_0_S1FMT, s1_cfg->s1fmt);
 	}
 
 	if (s2_cfg) {
@@ -1642,7 +1873,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
-	dst[0] = cpu_to_le64(val);
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(dst[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -1675,7 +1907,7 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
 
 	desc->span = STRTAB_SPLIT + 1;
 	desc->l2ptr = dmam_alloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
-					  GFP_KERNEL | __GFP_ZERO);
+					  GFP_KERNEL);
 	if (!desc->l2ptr) {
 		dev_err(smmu->dev,
 			"failed to allocate l2 stream table for SID %u\n",
@@ -2131,12 +2363,8 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
 
-		if (cfg->cdptr) {
-			dmam_free_coherent(smmu_domain->smmu->dev,
-					   CTXDESC_CD_DWORDS << 3,
-					   cfg->cdptr,
-					   cfg->cdptr_dma);
-
+		if (cfg->cdcfg.cdtab) {
+			arm_smmu_free_cd_tables(smmu_domain);
 			arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
 		}
 	} else {
@@ -2149,55 +2377,82 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 }
 
 static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_master *master,
 				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	int ret;
 	int asid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 
 	asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
 	if (asid < 0)
 		return asid;
 
-	cfg->cdptr = dmam_alloc_coherent(smmu->dev, CTXDESC_CD_DWORDS << 3,
-					 &cfg->cdptr_dma,
-					 GFP_KERNEL | __GFP_ZERO);
-	if (!cfg->cdptr) {
-		dev_warn(smmu->dev, "failed to allocate context descriptor\n");
-		ret = -ENOMEM;
+	cfg->s1cdmax = master->ssid_bits;
+
+	ret = arm_smmu_alloc_cd_tables(smmu_domain);
+	if (ret)
 		goto out_free_asid;
-	}
 
 	cfg->cd.asid	= (u16)asid;
-	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
-	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
+	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+	cfg->cd.tcr	= FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, tcr->tsz) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_TG0, tcr->tg) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, tcr->irgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, tcr->orgn) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_SH0, tcr->sh) |
+			  FIELD_PREP(CTXDESC_CD_0_TCR_IPS, tcr->ips) |
+			  CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
 	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
+
+	/*
+	 * Note that this will end up calling arm_smmu_sync_cd() before
+	 * the master has been added to the devices list for this domain.
+	 * This isn't an issue because the STE hasn't been installed yet.
+	 */
+	ret = arm_smmu_write_ctx_desc(smmu_domain, 0, &cfg->cd);
+	if (ret)
+		goto out_free_cd_tables;
+
 	return 0;
 
+out_free_cd_tables:
+	arm_smmu_free_cd_tables(smmu_domain);
 out_free_asid:
 	arm_smmu_bitmap_free(smmu->asid_map, asid);
 	return ret;
 }
 
 static int arm_smmu_domain_finalise_s2(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_master *master,
 				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	int vmid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
+	typeof(&pgtbl_cfg->arm_lpae_s2_cfg.vtcr) vtcr;
 
 	vmid = arm_smmu_bitmap_alloc(smmu->vmid_map, smmu->vmid_bits);
 	if (vmid < 0)
 		return vmid;
 
+	vtcr = &pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
 	cfg->vmid	= (u16)vmid;
 	cfg->vttbr	= pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
-	cfg->vtcr	= pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+	cfg->vtcr	= FIELD_PREP(STRTAB_STE_2_VTCR_S2T0SZ, vtcr->tsz) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SL0, vtcr->sl) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2IR0, vtcr->irgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2OR0, vtcr->orgn) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2SH0, vtcr->sh) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2TG, vtcr->tg) |
+			  FIELD_PREP(STRTAB_STE_2_VTCR_S2PS, vtcr->ps);
 	return 0;
 }
 
-static int arm_smmu_domain_finalise(struct iommu_domain *domain)
+static int arm_smmu_domain_finalise(struct iommu_domain *domain,
+				    struct arm_smmu_master *master)
 {
 	int ret;
 	unsigned long ias, oas;
@@ -2205,6 +2460,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	struct io_pgtable_cfg pgtbl_cfg;
 	struct io_pgtable_ops *pgtbl_ops;
 	int (*finalise_stage_fn)(struct arm_smmu_domain *,
+				 struct arm_smmu_master *,
 				 struct io_pgtable_cfg *);
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
@@ -2259,7 +2515,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	domain->geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1;
 	domain->geometry.force_aperture = true;
 
-	ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg);
+	ret = finalise_stage_fn(smmu_domain, master, &pgtbl_cfg);
 	if (ret < 0) {
 		free_io_pgtable_ops(pgtbl_ops);
 		return ret;
@@ -2412,7 +2668,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	if (!smmu_domain->smmu) {
 		smmu_domain->smmu = smmu;
-		ret = arm_smmu_domain_finalise(domain);
+		ret = arm_smmu_domain_finalise(domain, master);
 		if (ret) {
 			smmu_domain->smmu = NULL;
 			goto out_unlock;
@@ -2424,6 +2680,13 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 			dev_name(smmu->dev));
 		ret = -ENXIO;
 		goto out_unlock;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
+		   master->ssid_bits != smmu_domain->s1_cfg.s1cdmax) {
+		dev_err(dev,
+			"cannot attach to incompatible domain (%u SSID bits != %u)\n",
+			smmu_domain->s1_cfg.s1cdmax, master->ssid_bits);
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	master->domain = smmu_domain;
@@ -2431,9 +2694,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	if (smmu_domain->stage != ARM_SMMU_DOMAIN_BYPASS)
 		master->ats_enabled = arm_smmu_ats_supported(master);
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1)
-		arm_smmu_write_ctx_desc(smmu, &smmu_domain->s1_cfg);
-
 	arm_smmu_install_ste_for_dev(master);
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
@@ -2534,51 +2794,66 @@ static int arm_smmu_add_device(struct device *dev)
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return -ENODEV;
-	/*
-	 * We _can_ actually withstand dodgy bus code re-calling add_device()
-	 * without an intervening remove_device()/of_xlate() sequence, but
-	 * we're not going to do so quietly...
-	 */
-	if (WARN_ON_ONCE(fwspec->iommu_priv)) {
-		master = fwspec->iommu_priv;
-		smmu = master->smmu;
-	} else {
-		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
-		if (!smmu)
-			return -ENODEV;
-		master = kzalloc(sizeof(*master), GFP_KERNEL);
-		if (!master)
-			return -ENOMEM;
 
-		master->dev = dev;
-		master->smmu = smmu;
-		master->sids = fwspec->ids;
-		master->num_sids = fwspec->num_ids;
-		fwspec->iommu_priv = master;
-	}
+	if (WARN_ON_ONCE(fwspec->iommu_priv))
+		return -EBUSY;
+
+	smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
+	if (!smmu)
+		return -ENODEV;
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return -ENOMEM;
+
+	master->dev = dev;
+	master->smmu = smmu;
+	master->sids = fwspec->ids;
+	master->num_sids = fwspec->num_ids;
+	fwspec->iommu_priv = master;
 
 	/* Check the SIDs are in range of the SMMU and our stream table */
 	for (i = 0; i < master->num_sids; i++) {
 		u32 sid = master->sids[i];
 
-		if (!arm_smmu_sid_in_range(smmu, sid))
-			return -ERANGE;
+		if (!arm_smmu_sid_in_range(smmu, sid)) {
+			ret = -ERANGE;
+			goto err_free_master;
+		}
 
 		/* Ensure l2 strtab is initialised */
 		if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
 			ret = arm_smmu_init_l2_strtab(smmu, sid);
 			if (ret)
-				return ret;
+				goto err_free_master;
 		}
 	}
 
+	master->ssid_bits = min(smmu->ssid_bits, fwspec->num_pasid_bits);
+
+	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB))
+		master->ssid_bits = min_t(u8, master->ssid_bits,
+					  CTXDESC_LINEAR_CDMAX);
+
+	ret = iommu_device_link(&smmu->iommu, dev);
+	if (ret)
+		goto err_free_master;
+
 	group = iommu_group_get_for_dev(dev);
-	if (!IS_ERR(group)) {
-		iommu_group_put(group);
-		iommu_device_link(&smmu->iommu, dev);
+	if (IS_ERR(group)) {
+		ret = PTR_ERR(group);
+		goto err_unlink;
 	}
 
-	return PTR_ERR_OR_ZERO(group);
+	iommu_group_put(group);
+	return 0;
+
+err_unlink:
+	iommu_device_unlink(&smmu->iommu, dev);
+err_free_master:
+	kfree(master);
+	fwspec->iommu_priv = NULL;
+	return ret;
 }
 
 static void arm_smmu_remove_device(struct device *dev)
@@ -2710,15 +2985,6 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 	iommu_dma_get_resv_regions(dev, head);
 }
 
-static void arm_smmu_put_resv_regions(struct device *dev,
-				      struct list_head *head)
-{
-	struct iommu_resv_region *entry, *next;
-
-	list_for_each_entry_safe(entry, next, head, list)
-		kfree(entry);
-}
-
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -2736,7 +3002,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
-	.put_resv_regions	= arm_smmu_put_resv_regions,
+	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -2883,7 +3149,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 
 	l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
 	strtab = dmam_alloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
-				     GFP_KERNEL | __GFP_ZERO);
+				     GFP_KERNEL);
 	if (!strtab) {
 		dev_err(smmu->dev,
 			"failed to allocate l1 stream table (%u bytes)\n",
@@ -2910,7 +3176,7 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu)
 
 	size = (1 << smmu->sid_bits) * (STRTAB_STE_DWORDS << 3);
 	strtab = dmam_alloc_coherent(smmu->dev, size, &cfg->strtab_dma,
-				     GFP_KERNEL | __GFP_ZERO);
+				     GFP_KERNEL);
 	if (!strtab) {
 		dev_err(smmu->dev,
 			"failed to allocate linear stream table (%u bytes)\n",
@@ -3570,6 +3836,43 @@ static unsigned long arm_smmu_resource_size(struct arm_smmu_device *smmu)
 		return SZ_128K;
 }
 
+static int arm_smmu_set_bus_ops(struct iommu_ops *ops)
+{
+	int err;
+
+#ifdef CONFIG_PCI
+	if (pci_bus_type.iommu_ops != ops) {
+		err = bus_set_iommu(&pci_bus_type, ops);
+		if (err)
+			return err;
+	}
+#endif
+#ifdef CONFIG_ARM_AMBA
+	if (amba_bustype.iommu_ops != ops) {
+		err = bus_set_iommu(&amba_bustype, ops);
+		if (err)
+			goto err_reset_pci_ops;
+	}
+#endif
+	if (platform_bus_type.iommu_ops != ops) {
+		err = bus_set_iommu(&platform_bus_type, ops);
+		if (err)
+			goto err_reset_amba_ops;
+	}
+
+	return 0;
+
+err_reset_amba_ops:
+#ifdef CONFIG_ARM_AMBA
+	bus_set_iommu(&amba_bustype, NULL);
+#endif
+err_reset_pci_ops: __maybe_unused;
+#ifdef CONFIG_PCI
+	bus_set_iommu(&pci_bus_type, NULL);
+#endif
+	return err;
+}
+
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	int irq, ret;
@@ -3599,7 +3902,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Base address */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (resource_size(res) + 1 < arm_smmu_resource_size(smmu)) {
+	if (resource_size(res) < arm_smmu_resource_size(smmu)) {
 		dev_err(dev, "MMIO region too small (%pr)\n", res);
 		return -EINVAL;
 	}
@@ -3660,48 +3963,45 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-#ifdef CONFIG_PCI
-	if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
-		pci_request_acs();
-		ret = bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
-		if (ret)
-			return ret;
-	}
-#endif
-#ifdef CONFIG_ARM_AMBA
-	if (amba_bustype.iommu_ops != &arm_smmu_ops) {
-		ret = bus_set_iommu(&amba_bustype, &arm_smmu_ops);
-		if (ret)
-			return ret;
-	}
-#endif
-	if (platform_bus_type.iommu_ops != &arm_smmu_ops) {
-		ret = bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
-		if (ret)
-			return ret;
-	}
-	return 0;
+	return arm_smmu_set_bus_ops(&arm_smmu_ops);
 }
 
-static void arm_smmu_device_shutdown(struct platform_device *pdev)
+static int arm_smmu_device_remove(struct platform_device *pdev)
 {
 	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
 
+	arm_smmu_set_bus_ops(NULL);
+	iommu_device_unregister(&smmu->iommu);
+	iommu_device_sysfs_remove(&smmu->iommu);
 	arm_smmu_device_disable(smmu);
+
+	return 0;
+}
+
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
+{
+	arm_smmu_device_remove(pdev);
 }
 
 static const struct of_device_id arm_smmu_of_match[] = {
 	{ .compatible = "arm,smmu-v3", },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
-		.name		= "arm-smmu-v3",
-		.of_match_table	= of_match_ptr(arm_smmu_of_match),
-		.suppress_bind_attrs = true,
+		.name			= "arm-smmu-v3",
+		.of_match_table		= arm_smmu_of_match,
+		.suppress_bind_attrs	= true,
 	},
 	.probe	= arm_smmu_device_probe,
+	.remove	= arm_smmu_device_remove,
 	.shutdown = arm_smmu_device_shutdown,
 };
-builtin_platform_driver(arm_smmu_driver);
+module_platform_driver(arm_smmu_driver);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
+MODULE_AUTHOR("Will Deacon <will@kernel.org>");
+MODULE_ALIAS("platform:arm-smmu-v3");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 4f1a350d9529..16c4b87af42b 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -27,8 +27,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
-#include <linux/init.h>
-#include <linux/moduleparam.h>
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
@@ -60,10 +59,6 @@
 #define MSI_IOVA_LENGTH			0x100000
 
 static int force_stage;
-/*
- * not really modular, but the easiest way to keep compat with existing
- * bootargs behaviour is to continue using module_param() here.
- */
 module_param(force_stage, int, S_IRUGO);
 MODULE_PARM_DESC(force_stage,
 	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
@@ -131,6 +126,12 @@ static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 	return container_of(dom, struct arm_smmu_domain, domain);
 }
 
+static struct platform_driver arm_smmu_driver;
+static struct iommu_ops arm_smmu_ops;
+
+#ifdef CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS
+static int arm_smmu_bus_init(struct iommu_ops *ops);
+
 static struct device_node *dev_get_dev_node(struct device *dev)
 {
 	if (dev_is_pci(dev)) {
@@ -166,9 +167,6 @@ static int __find_legacy_master_phandle(struct device *dev, void *data)
 	return err == -ENOENT ? 0 : err;
 }
 
-static struct platform_driver arm_smmu_driver;
-static struct iommu_ops arm_smmu_ops;
-
 static int arm_smmu_register_legacy_master(struct device *dev,
 					   struct arm_smmu_device **smmu)
 {
@@ -220,6 +218,27 @@ static int arm_smmu_register_legacy_master(struct device *dev,
 	return err;
 }
 
+/*
+ * With the legacy DT binding in play, we have no guarantees about
+ * probe order, but then we're also not doing default domains, so we can
+ * delay setting bus ops until we're sure every possible SMMU is ready,
+ * and that way ensure that no add_device() calls get missed.
+ */
+static int arm_smmu_legacy_bus_init(void)
+{
+	if (using_legacy_binding)
+		return arm_smmu_bus_init(&arm_smmu_ops);
+	return 0;
+}
+device_initcall_sync(arm_smmu_legacy_bus_init);
+#else
+static int arm_smmu_register_legacy_master(struct device *dev,
+					   struct arm_smmu_device **smmu)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS */
+
 static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
 {
 	int idx;
@@ -252,7 +271,7 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
 	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
 		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
 			reg = arm_smmu_readl(smmu, page, status);
-			if (!(reg & sTLBGSTATUS_GSACTIVE))
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
 				return;
 			cpu_relax();
 		}
@@ -459,7 +478,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	int idx = smmu_domain->cfg.cbndx;
 
 	fsr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSR);
-	if (!(fsr & FSR_FAULT))
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
 		return IRQ_NONE;
 
 	fsynr = arm_smmu_cb_read(smmu, idx, ARM_SMMU_CB_FSYNR0);
@@ -491,7 +510,7 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
 
 	if (__ratelimit(&rs)) {
 		if (IS_ENABLED(CONFIG_ARM_SMMU_DISABLE_BYPASS_BY_DEFAULT) &&
-		    (gfsr & sGFSR_USF))
+		    (gfsr & ARM_SMMU_sGFSR_USF))
 			dev_err(smmu->dev,
 				"Blocked unknown Stream ID 0x%hx; boot with \"arm-smmu.disable_bypass=0\" to allow, but this may have security implications\n",
 				(u16)gfsynr1);
@@ -521,26 +540,28 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
 			cb->tcr[0] = pgtbl_cfg->arm_v7s_cfg.tcr;
 		} else {
-			cb->tcr[0] = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
-			cb->tcr[1] = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
-			cb->tcr[1] |= FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM);
+			cb->tcr[0] = arm_smmu_lpae_tcr(pgtbl_cfg);
+			cb->tcr[1] = arm_smmu_lpae_tcr2(pgtbl_cfg);
 			if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
-				cb->tcr[1] |= TCR2_AS;
+				cb->tcr[1] |= ARM_SMMU_TCR2_AS;
+			else
+				cb->tcr[0] |= ARM_SMMU_TCR_EAE;
 		}
 	} else {
-		cb->tcr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vtcr;
+		cb->tcr[0] = arm_smmu_lpae_vtcr(pgtbl_cfg);
 	}
 
 	/* TTBRs */
 	if (stage1) {
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
-			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr[0];
-			cb->ttbr[1] = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
+			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
+			cb->ttbr[1] = 0;
 		} else {
-			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
-			cb->ttbr[0] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
-			cb->ttbr[1] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
-			cb->ttbr[1] |= FIELD_PREP(TTBRn_ASID, cfg->asid);
+			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+			cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						  cfg->asid);
+			cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						 cfg->asid);
 		}
 	} else {
 		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
@@ -576,31 +597,33 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
 	/* CBA2R */
 	if (smmu->version > ARM_SMMU_V1) {
 		if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
-			reg = CBA2R_VA64;
+			reg = ARM_SMMU_CBA2R_VA64;
 		else
 			reg = 0;
 		/* 16-bit VMIDs live in CBA2R */
 		if (smmu->features & ARM_SMMU_FEAT_VMID16)
-			reg |= FIELD_PREP(CBA2R_VMID16, cfg->vmid);
+			reg |= FIELD_PREP(ARM_SMMU_CBA2R_VMID16, cfg->vmid);
 
 		arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBA2R(idx), reg);
 	}
 
 	/* CBAR */
-	reg = FIELD_PREP(CBAR_TYPE, cfg->cbar);
+	reg = FIELD_PREP(ARM_SMMU_CBAR_TYPE, cfg->cbar);
 	if (smmu->version < ARM_SMMU_V2)
-		reg |= FIELD_PREP(CBAR_IRPTNDX, cfg->irptndx);
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_IRPTNDX, cfg->irptndx);
 
 	/*
 	 * Use the weakest shareability/memory types, so they are
 	 * overridden by the ttbcr/pte.
 	 */
 	if (stage1) {
-		reg |= FIELD_PREP(CBAR_S1_BPSHCFG, CBAR_S1_BPSHCFG_NSH) |
-			FIELD_PREP(CBAR_S1_MEMATTR, CBAR_S1_MEMATTR_WB);
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_S1_BPSHCFG,
+				  ARM_SMMU_CBAR_S1_BPSHCFG_NSH) |
+		       FIELD_PREP(ARM_SMMU_CBAR_S1_MEMATTR,
+				  ARM_SMMU_CBAR_S1_MEMATTR_WB);
 	} else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) {
 		/* 8-bit VMIDs live in CBAR */
-		reg |= FIELD_PREP(CBAR_VMID, cfg->vmid);
+		reg |= FIELD_PREP(ARM_SMMU_CBAR_VMID, cfg->vmid);
 	}
 	arm_smmu_gr1_write(smmu, ARM_SMMU_GR1_CBAR(idx), reg);
 
@@ -632,11 +655,12 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
 	}
 
 	/* SCTLR */
-	reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE | SCTLR_M;
+	reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE | ARM_SMMU_SCTLR_AFE |
+	      ARM_SMMU_SCTLR_TRE | ARM_SMMU_SCTLR_M;
 	if (stage1)
-		reg |= SCTLR_S1_ASIDPNE;
+		reg |= ARM_SMMU_SCTLR_S1_ASIDPNE;
 	if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
-		reg |= SCTLR_E;
+		reg |= ARM_SMMU_SCTLR_E;
 
 	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
 }
@@ -818,7 +842,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
-		cfg->irptndx = INVALID_IRPTNDX;
+		cfg->irptndx = ARM_SMMU_INVALID_IRPTNDX;
 	}
 
 	mutex_unlock(&smmu_domain->init_mutex);
@@ -856,7 +880,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 	smmu->cbs[cfg->cbndx].cfg = NULL;
 	arm_smmu_write_context_bank(smmu, cfg->cbndx);
 
-	if (cfg->irptndx != INVALID_IRPTNDX) {
+	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
 		irq = smmu->irqs[smmu->num_global_irqs + cfg->irptndx];
 		devm_free_irq(smmu->dev, irq, domain);
 	}
@@ -912,23 +936,24 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
 {
 	struct arm_smmu_smr *smr = smmu->smrs + idx;
-	u32 reg = FIELD_PREP(SMR_ID, smr->id) | FIELD_PREP(SMR_MASK, smr->mask);
+	u32 reg = FIELD_PREP(ARM_SMMU_SMR_ID, smr->id) |
+		  FIELD_PREP(ARM_SMMU_SMR_MASK, smr->mask);
 
 	if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
-		reg |= SMR_VALID;
+		reg |= ARM_SMMU_SMR_VALID;
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(idx), reg);
 }
 
 static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
 {
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
-	u32 reg = FIELD_PREP(S2CR_TYPE, s2cr->type) |
-		  FIELD_PREP(S2CR_CBNDX, s2cr->cbndx) |
-		  FIELD_PREP(S2CR_PRIVCFG, s2cr->privcfg);
+	u32 reg = FIELD_PREP(ARM_SMMU_S2CR_TYPE, s2cr->type) |
+		  FIELD_PREP(ARM_SMMU_S2CR_CBNDX, s2cr->cbndx) |
+		  FIELD_PREP(ARM_SMMU_S2CR_PRIVCFG, s2cr->privcfg);
 
 	if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
 	    smmu->smrs[idx].valid)
-		reg |= S2CR_EXIDVALID;
+		reg |= ARM_SMMU_S2CR_EXIDVALID;
 	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_S2CR(idx), reg);
 }
 
@@ -946,24 +971,37 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
 static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
 {
 	u32 smr;
+	int i;
 
 	if (!smmu->smrs)
 		return;
-
+	/*
+	 * If we've had to accommodate firmware memory regions, we may
+	 * have live SMRs by now; tread carefully...
+	 *
+	 * Somewhat perversely, not having a free SMR for this test implies we
+	 * can get away without it anyway, as we'll only be able to 'allocate'
+	 * these SMRs for the ID/mask values we're already trusting to be OK.
+	 */
+	for (i = 0; i < smmu->num_mapping_groups; i++)
+		if (!smmu->smrs[i].valid)
+			goto smr_ok;
+	return;
+smr_ok:
 	/*
 	 * SMR.ID bits may not be preserved if the corresponding MASK
 	 * bits are set, so check each one separately. We can reject
 	 * masters later if they try to claim IDs outside these masks.
 	 */
-	smr = FIELD_PREP(SMR_ID, smmu->streamid_mask);
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
-	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
-	smmu->streamid_mask = FIELD_GET(SMR_ID, smr);
+	smr = FIELD_PREP(ARM_SMMU_SMR_ID, smmu->streamid_mask);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr);
+	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+	smmu->streamid_mask = FIELD_GET(ARM_SMMU_SMR_ID, smr);
 
-	smr = FIELD_PREP(SMR_MASK, smmu->streamid_mask);
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(0), smr);
-	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(0));
-	smmu->smr_mask_mask = FIELD_GET(SMR_MASK, smr);
+	smr = FIELD_PREP(ARM_SMMU_SMR_MASK, smmu->streamid_mask);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_SMR(i), smr);
+	smr = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_SMR(i));
+	smmu->smr_mask_mask = FIELD_GET(ARM_SMMU_SMR_MASK, smr);
 }
 
 static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
@@ -1032,8 +1070,8 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
 	mutex_lock(&smmu->stream_map_mutex);
 	/* Figure out a viable stream map entry allocation */
 	for_each_cfg_sme(fwspec, i, idx) {
-		u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
-		u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+		u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
 
 		if (idx != INVALID_SMENDX) {
 			ret = -EEXIST;
@@ -1277,7 +1315,8 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 		arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_ATS1PR, va);
 
 	reg = arm_smmu_page(smmu, ARM_SMMU_CB(smmu, idx)) + ARM_SMMU_CB_ATSR;
-	if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ATSR_ACTIVE), 5, 50)) {
+	if (readl_poll_timeout_atomic(reg, tmp, !(tmp & ARM_SMMU_ATSR_ACTIVE),
+				      5, 50)) {
 		spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
 		dev_err(dev,
 			"iova to phys timed out on %pad. Falling back to software table walk.\n",
@@ -1287,7 +1326,7 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 
 	phys = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_PAR);
 	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
-	if (phys & CB_PAR_F) {
+	if (phys & ARM_SMMU_CB_PAR_F) {
 		dev_err(dev, "translation fault!\n");
 		dev_err(dev, "PAR = 0x%llx\n", phys);
 		return 0;
@@ -1368,8 +1407,8 @@ static int arm_smmu_add_device(struct device *dev)
 
 	ret = -EINVAL;
 	for (i = 0; i < fwspec->num_ids; i++) {
-		u16 sid = FIELD_GET(SMR_ID, fwspec->ids[i]);
-		u16 mask = FIELD_GET(SMR_MASK, fwspec->ids[i]);
+		u16 sid = FIELD_GET(ARM_SMMU_SMR_ID, fwspec->ids[i]);
+		u16 mask = FIELD_GET(ARM_SMMU_SMR_MASK, fwspec->ids[i]);
 
 		if (sid & ~smmu->streamid_mask) {
 			dev_err(dev, "stream ID 0x%x out of range for SMMU (0x%x)\n",
@@ -1550,12 +1589,12 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	u32 mask, fwid = 0;
 
 	if (args->args_count > 0)
-		fwid |= FIELD_PREP(SMR_ID, args->args[0]);
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_ID, args->args[0]);
 
 	if (args->args_count > 1)
-		fwid |= FIELD_PREP(SMR_MASK, args->args[1]);
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, args->args[1]);
 	else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
-		fwid |= FIELD_PREP(SMR_MASK, mask);
+		fwid |= FIELD_PREP(ARM_SMMU_SMR_MASK, mask);
 
 	return iommu_fwspec_add_ids(dev, &fwid, 1);
 }
@@ -1576,15 +1615,6 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 	iommu_dma_get_resv_regions(dev, head);
 }
 
-static void arm_smmu_put_resv_regions(struct device *dev,
-				      struct list_head *head)
-{
-	struct iommu_resv_region *entry, *next;
-
-	list_for_each_entry_safe(entry, next, head, list)
-		kfree(entry);
-}
-
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -1602,7 +1632,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
-	.put_resv_regions	= arm_smmu_put_resv_regions,
+	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -1625,7 +1655,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	/* Make sure all context banks are disabled and clear CB_FSR  */
 	for (i = 0; i < smmu->num_context_banks; ++i) {
 		arm_smmu_write_context_bank(smmu, i);
-		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, FSR_FAULT);
+		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_FSR, ARM_SMMU_FSR_FAULT);
 	}
 
 	/* Invalidate the TLB, just in case */
@@ -1635,29 +1665,30 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sCR0);
 
 	/* Enable fault reporting */
-	reg |= (sCR0_GFRE | sCR0_GFIE | sCR0_GCFGFRE | sCR0_GCFGFIE);
+	reg |= (ARM_SMMU_sCR0_GFRE | ARM_SMMU_sCR0_GFIE |
+		ARM_SMMU_sCR0_GCFGFRE | ARM_SMMU_sCR0_GCFGFIE);
 
 	/* Disable TLB broadcasting. */
-	reg |= (sCR0_VMIDPNE | sCR0_PTM);
+	reg |= (ARM_SMMU_sCR0_VMIDPNE | ARM_SMMU_sCR0_PTM);
 
 	/* Enable client access, handling unmatched streams as appropriate */
-	reg &= ~sCR0_CLIENTPD;
+	reg &= ~ARM_SMMU_sCR0_CLIENTPD;
 	if (disable_bypass)
-		reg |= sCR0_USFCFG;
+		reg |= ARM_SMMU_sCR0_USFCFG;
 	else
-		reg &= ~sCR0_USFCFG;
+		reg &= ~ARM_SMMU_sCR0_USFCFG;
 
 	/* Disable forced broadcasting */
-	reg &= ~sCR0_FB;
+	reg &= ~ARM_SMMU_sCR0_FB;
 
 	/* Don't upgrade barriers */
-	reg &= ~(sCR0_BSU);
+	reg &= ~(ARM_SMMU_sCR0_BSU);
 
 	if (smmu->features & ARM_SMMU_FEAT_VMID16)
-		reg |= sCR0_VMID16EN;
+		reg |= ARM_SMMU_sCR0_VMID16EN;
 
 	if (smmu->features & ARM_SMMU_FEAT_EXIDS)
-		reg |= sCR0_EXIDENABLE;
+		reg |= ARM_SMMU_sCR0_EXIDENABLE;
 
 	if (smmu->impl && smmu->impl->reset)
 		smmu->impl->reset(smmu);
@@ -1702,21 +1733,21 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* Restrict available stages based on module parameter */
 	if (force_stage == 1)
-		id &= ~(ID0_S2TS | ID0_NTS);
+		id &= ~(ARM_SMMU_ID0_S2TS | ARM_SMMU_ID0_NTS);
 	else if (force_stage == 2)
-		id &= ~(ID0_S1TS | ID0_NTS);
+		id &= ~(ARM_SMMU_ID0_S1TS | ARM_SMMU_ID0_NTS);
 
-	if (id & ID0_S1TS) {
+	if (id & ARM_SMMU_ID0_S1TS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S1;
 		dev_notice(smmu->dev, "\tstage 1 translation\n");
 	}
 
-	if (id & ID0_S2TS) {
+	if (id & ARM_SMMU_ID0_S2TS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_S2;
 		dev_notice(smmu->dev, "\tstage 2 translation\n");
 	}
 
-	if (id & ID0_NTS) {
+	if (id & ARM_SMMU_ID0_NTS) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_NESTED;
 		dev_notice(smmu->dev, "\tnested translation\n");
 	}
@@ -1727,8 +1758,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		return -ENODEV;
 	}
 
-	if ((id & ID0_S1TS) &&
-		((smmu->version < ARM_SMMU_V2) || !(id & ID0_ATOSNS))) {
+	if ((id & ARM_SMMU_ID0_S1TS) &&
+	    ((smmu->version < ARM_SMMU_V2) || !(id & ARM_SMMU_ID0_ATOSNS))) {
 		smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
 		dev_notice(smmu->dev, "\taddress translation ops\n");
 	}
@@ -1739,7 +1770,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	 * Fortunately, this also opens up a workaround for systems where the
 	 * ID register value has ended up configured incorrectly.
 	 */
-	cttw_reg = !!(id & ID0_CTTW);
+	cttw_reg = !!(id & ARM_SMMU_ID0_CTTW);
 	if (cttw_fw || cttw_reg)
 		dev_notice(smmu->dev, "\t%scoherent table walk\n",
 			   cttw_fw ? "" : "non-");
@@ -1748,16 +1779,16 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			   "\t(IDR0.CTTW overridden by FW configuration)\n");
 
 	/* Max. number of entries we have for stream matching/indexing */
-	if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+	if (smmu->version == ARM_SMMU_V2 && id & ARM_SMMU_ID0_EXIDS) {
 		smmu->features |= ARM_SMMU_FEAT_EXIDS;
 		size = 1 << 16;
 	} else {
-		size = 1 << FIELD_GET(ID0_NUMSIDB, id);
+		size = 1 << FIELD_GET(ARM_SMMU_ID0_NUMSIDB, id);
 	}
 	smmu->streamid_mask = size - 1;
-	if (id & ID0_SMS) {
+	if (id & ARM_SMMU_ID0_SMS) {
 		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
-		size = FIELD_GET(ID0_NUMSMRG, id);
+		size = FIELD_GET(ARM_SMMU_ID0_NUMSMRG, id);
 		if (size == 0) {
 			dev_err(smmu->dev,
 				"stream-matching supported, but no SMRs present!\n");
@@ -1785,18 +1816,19 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	mutex_init(&smmu->stream_map_mutex);
 	spin_lock_init(&smmu->global_sync_lock);
 
-	if (smmu->version < ARM_SMMU_V2 || !(id & ID0_PTFS_NO_AARCH32)) {
+	if (smmu->version < ARM_SMMU_V2 ||
+	    !(id & ARM_SMMU_ID0_PTFS_NO_AARCH32)) {
 		smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_L;
-		if (!(id & ID0_PTFS_NO_AARCH32S))
+		if (!(id & ARM_SMMU_ID0_PTFS_NO_AARCH32S))
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_S;
 	}
 
 	/* ID1 */
 	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID1);
-	smmu->pgshift = (id & ID1_PAGESIZE) ? 16 : 12;
+	smmu->pgshift = (id & ARM_SMMU_ID1_PAGESIZE) ? 16 : 12;
 
 	/* Check for size mismatch of SMMU address space from mapped region */
-	size = 1 << (FIELD_GET(ID1_NUMPAGENDXB, id) + 1);
+	size = 1 << (FIELD_GET(ARM_SMMU_ID1_NUMPAGENDXB, id) + 1);
 	if (smmu->numpage != 2 * size << smmu->pgshift)
 		dev_warn(smmu->dev,
 			"SMMU address space size (0x%x) differs from mapped region size (0x%x)!\n",
@@ -1804,8 +1836,8 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	/* Now properly encode NUMPAGE to subsequently derive SMMU_CB_BASE */
 	smmu->numpage = size;
 
-	smmu->num_s2_context_banks = FIELD_GET(ID1_NUMS2CB, id);
-	smmu->num_context_banks = FIELD_GET(ID1_NUMCB, id);
+	smmu->num_s2_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMS2CB, id);
+	smmu->num_context_banks = FIELD_GET(ARM_SMMU_ID1_NUMCB, id);
 	if (smmu->num_s2_context_banks > smmu->num_context_banks) {
 		dev_err(smmu->dev, "impossible number of S2 context banks!\n");
 		return -ENODEV;
@@ -1819,14 +1851,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	/* ID2 */
 	id = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID2);
-	size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_IAS, id));
+	size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_IAS, id));
 	smmu->ipa_size = size;
 
 	/* The output mask is also applied for bypass */
-	size = arm_smmu_id_size_to_bits(FIELD_GET(ID2_OAS, id));
+	size = arm_smmu_id_size_to_bits(FIELD_GET(ARM_SMMU_ID2_OAS, id));
 	smmu->pa_size = size;
 
-	if (id & ID2_VMID16)
+	if (id & ARM_SMMU_ID2_VMID16)
 		smmu->features |= ARM_SMMU_FEAT_VMID16;
 
 	/*
@@ -1843,13 +1875,13 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		if (smmu->version == ARM_SMMU_V1_64K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
 	} else {
-		size = FIELD_GET(ID2_UBS, id);
+		size = FIELD_GET(ARM_SMMU_ID2_UBS, id);
 		smmu->va_size = arm_smmu_id_size_to_bits(size);
-		if (id & ID2_PTFS_4K)
+		if (id & ARM_SMMU_ID2_PTFS_4K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_4K;
-		if (id & ID2_PTFS_16K)
+		if (id & ARM_SMMU_ID2_PTFS_16K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_16K;
-		if (id & ID2_PTFS_64K)
+		if (id & ARM_SMMU_ID2_PTFS_64K)
 			smmu->features |= ARM_SMMU_FEAT_FMT_AARCH64_64K;
 	}
 
@@ -1911,6 +1943,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
 	{ .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
 
 #ifdef CONFIG_ACPI
 static int acpi_smmu_get_data(u32 model, struct arm_smmu_device *smmu)
@@ -1997,8 +2030,10 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
 
 	legacy_binding = of_find_property(dev->of_node, "mmu-masters", NULL);
 	if (legacy_binding && !using_generic_binding) {
-		if (!using_legacy_binding)
-			pr_notice("deprecated \"mmu-masters\" DT property in use; DMA API support unavailable\n");
+		if (!using_legacy_binding) {
+			pr_notice("deprecated \"mmu-masters\" DT property in use; %s support unavailable\n",
+				  IS_ENABLED(CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS) ? "DMA API" : "SMMU");
+		}
 		using_legacy_binding = true;
 	} else if (!legacy_binding && !using_legacy_binding) {
 		using_generic_binding = true;
@@ -2013,25 +2048,50 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
 	return 0;
 }
 
-static void arm_smmu_bus_init(void)
+static int arm_smmu_bus_init(struct iommu_ops *ops)
 {
+	int err;
+
 	/* Oh, for a proper bus abstraction */
-	if (!iommu_present(&platform_bus_type))
-		bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+	if (!iommu_present(&platform_bus_type)) {
+		err = bus_set_iommu(&platform_bus_type, ops);
+		if (err)
+			return err;
+	}
 #ifdef CONFIG_ARM_AMBA
-	if (!iommu_present(&amba_bustype))
-		bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+	if (!iommu_present(&amba_bustype)) {
+		err = bus_set_iommu(&amba_bustype, ops);
+		if (err)
+			goto err_reset_platform_ops;
+	}
 #endif
 #ifdef CONFIG_PCI
 	if (!iommu_present(&pci_bus_type)) {
-		pci_request_acs();
-		bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+		err = bus_set_iommu(&pci_bus_type, ops);
+		if (err)
+			goto err_reset_amba_ops;
 	}
 #endif
 #ifdef CONFIG_FSL_MC_BUS
-	if (!iommu_present(&fsl_mc_bus_type))
-		bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops);
+	if (!iommu_present(&fsl_mc_bus_type)) {
+		err = bus_set_iommu(&fsl_mc_bus_type, ops);
+		if (err)
+			goto err_reset_pci_ops;
+	}
 #endif
+	return 0;
+
+err_reset_pci_ops: __maybe_unused;
+#ifdef CONFIG_PCI
+	bus_set_iommu(&pci_bus_type, NULL);
+#endif
+err_reset_amba_ops: __maybe_unused;
+#ifdef CONFIG_ARM_AMBA
+	bus_set_iommu(&amba_bustype, NULL);
+#endif
+err_reset_platform_ops: __maybe_unused;
+	bus_set_iommu(&platform_bus_type, NULL);
+	return err;
 }
 
 static int arm_smmu_device_probe(struct platform_device *pdev)
@@ -2177,38 +2237,28 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	 * ready to handle default domain setup as soon as any SMMU exists.
 	 */
 	if (!using_legacy_binding)
-		arm_smmu_bus_init();
+		return arm_smmu_bus_init(&arm_smmu_ops);
 
 	return 0;
 }
 
-/*
- * With the legacy DT binding in play, though, we have no guarantees about
- * probe order, but then we're also not doing default domains, so we can
- * delay setting bus ops until we're sure every possible SMMU is ready,
- * and that way ensure that no add_device() calls get missed.
- */
-static int arm_smmu_legacy_bus_init(void)
-{
-	if (using_legacy_binding)
-		arm_smmu_bus_init();
-	return 0;
-}
-device_initcall_sync(arm_smmu_legacy_bus_init);
-
-static void arm_smmu_device_shutdown(struct platform_device *pdev)
+static int arm_smmu_device_remove(struct platform_device *pdev)
 {
 	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
 
 	if (!smmu)
-		return;
+		return -ENODEV;
 
 	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
 		dev_err(&pdev->dev, "removing device with active domains!\n");
 
+	arm_smmu_bus_init(NULL);
+	iommu_device_unregister(&smmu->iommu);
+	iommu_device_sysfs_remove(&smmu->iommu);
+
 	arm_smmu_rpm_get(smmu);
 	/* Turn the thing off */
-	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, sCR0_CLIENTPD);
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD);
 	arm_smmu_rpm_put(smmu);
 
 	if (pm_runtime_enabled(smmu->dev))
@@ -2217,6 +2267,12 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev)
 		clk_bulk_disable(smmu->num_clks, smmu->clks);
 
 	clk_bulk_unprepare(smmu->num_clks, smmu->clks);
+	return 0;
+}
+
+static void arm_smmu_device_shutdown(struct platform_device *pdev)
+{
+	arm_smmu_device_remove(pdev);
 }
 
 static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
@@ -2267,11 +2323,17 @@ static const struct dev_pm_ops arm_smmu_pm_ops = {
 static struct platform_driver arm_smmu_driver = {
 	.driver	= {
 		.name			= "arm-smmu",
-		.of_match_table		= of_match_ptr(arm_smmu_of_match),
+		.of_match_table		= arm_smmu_of_match,
 		.pm			= &arm_smmu_pm_ops,
-		.suppress_bind_attrs	= true,
+		.suppress_bind_attrs    = true,
 	},
 	.probe	= arm_smmu_device_probe,
+	.remove	= arm_smmu_device_remove,
 	.shutdown = arm_smmu_device_shutdown,
 };
-builtin_platform_driver(arm_smmu_driver);
+module_platform_driver(arm_smmu_driver);
+
+MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
+MODULE_AUTHOR("Will Deacon <will@kernel.org>");
+MODULE_ALIAS("platform:arm-smmu");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/arm-smmu.h b/drivers/iommu/arm-smmu.h
index 62b9f0cec49b..8d1cd54d82a6 100644
--- a/drivers/iommu/arm-smmu.h
+++ b/drivers/iommu/arm-smmu.h
@@ -11,6 +11,7 @@
 #define _ARM_SMMU_H
 
 #include <linux/atomic.h>
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/clk.h>
 #include <linux/device.h>
@@ -23,51 +24,51 @@
 
 /* Configuration registers */
 #define ARM_SMMU_GR0_sCR0		0x0
-#define sCR0_VMID16EN			BIT(31)
-#define sCR0_BSU			GENMASK(15, 14)
-#define sCR0_FB				BIT(13)
-#define sCR0_PTM			BIT(12)
-#define sCR0_VMIDPNE			BIT(11)
-#define sCR0_USFCFG			BIT(10)
-#define sCR0_GCFGFIE			BIT(5)
-#define sCR0_GCFGFRE			BIT(4)
-#define sCR0_EXIDENABLE			BIT(3)
-#define sCR0_GFIE			BIT(2)
-#define sCR0_GFRE			BIT(1)
-#define sCR0_CLIENTPD			BIT(0)
+#define ARM_SMMU_sCR0_VMID16EN		BIT(31)
+#define ARM_SMMU_sCR0_BSU		GENMASK(15, 14)
+#define ARM_SMMU_sCR0_FB		BIT(13)
+#define ARM_SMMU_sCR0_PTM		BIT(12)
+#define ARM_SMMU_sCR0_VMIDPNE		BIT(11)
+#define ARM_SMMU_sCR0_USFCFG		BIT(10)
+#define ARM_SMMU_sCR0_GCFGFIE		BIT(5)
+#define ARM_SMMU_sCR0_GCFGFRE		BIT(4)
+#define ARM_SMMU_sCR0_EXIDENABLE	BIT(3)
+#define ARM_SMMU_sCR0_GFIE		BIT(2)
+#define ARM_SMMU_sCR0_GFRE		BIT(1)
+#define ARM_SMMU_sCR0_CLIENTPD		BIT(0)
 
 /* Auxiliary Configuration register */
 #define ARM_SMMU_GR0_sACR		0x10
 
 /* Identification registers */
 #define ARM_SMMU_GR0_ID0		0x20
-#define ID0_S1TS			BIT(30)
-#define ID0_S2TS			BIT(29)
-#define ID0_NTS				BIT(28)
-#define ID0_SMS				BIT(27)
-#define ID0_ATOSNS			BIT(26)
-#define ID0_PTFS_NO_AARCH32		BIT(25)
-#define ID0_PTFS_NO_AARCH32S		BIT(24)
-#define ID0_NUMIRPT			GENMASK(23, 16)
-#define ID0_CTTW			BIT(14)
-#define ID0_NUMSIDB			GENMASK(12, 9)
-#define ID0_EXIDS			BIT(8)
-#define ID0_NUMSMRG			GENMASK(7, 0)
+#define ARM_SMMU_ID0_S1TS		BIT(30)
+#define ARM_SMMU_ID0_S2TS		BIT(29)
+#define ARM_SMMU_ID0_NTS		BIT(28)
+#define ARM_SMMU_ID0_SMS		BIT(27)
+#define ARM_SMMU_ID0_ATOSNS		BIT(26)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32	BIT(25)
+#define ARM_SMMU_ID0_PTFS_NO_AARCH32S	BIT(24)
+#define ARM_SMMU_ID0_NUMIRPT		GENMASK(23, 16)
+#define ARM_SMMU_ID0_CTTW		BIT(14)
+#define ARM_SMMU_ID0_NUMSIDB		GENMASK(12, 9)
+#define ARM_SMMU_ID0_EXIDS		BIT(8)
+#define ARM_SMMU_ID0_NUMSMRG		GENMASK(7, 0)
 
 #define ARM_SMMU_GR0_ID1		0x24
-#define ID1_PAGESIZE			BIT(31)
-#define ID1_NUMPAGENDXB			GENMASK(30, 28)
-#define ID1_NUMS2CB			GENMASK(23, 16)
-#define ID1_NUMCB			GENMASK(7, 0)
+#define ARM_SMMU_ID1_PAGESIZE		BIT(31)
+#define ARM_SMMU_ID1_NUMPAGENDXB	GENMASK(30, 28)
+#define ARM_SMMU_ID1_NUMS2CB		GENMASK(23, 16)
+#define ARM_SMMU_ID1_NUMCB		GENMASK(7, 0)
 
 #define ARM_SMMU_GR0_ID2		0x28
-#define ID2_VMID16			BIT(15)
-#define ID2_PTFS_64K			BIT(14)
-#define ID2_PTFS_16K			BIT(13)
-#define ID2_PTFS_4K			BIT(12)
-#define ID2_UBS				GENMASK(11, 8)
-#define ID2_OAS				GENMASK(7, 4)
-#define ID2_IAS				GENMASK(3, 0)
+#define ARM_SMMU_ID2_VMID16		BIT(15)
+#define ARM_SMMU_ID2_PTFS_64K		BIT(14)
+#define ARM_SMMU_ID2_PTFS_16K		BIT(13)
+#define ARM_SMMU_ID2_PTFS_4K		BIT(12)
+#define ARM_SMMU_ID2_UBS		GENMASK(11, 8)
+#define ARM_SMMU_ID2_OAS		GENMASK(7, 4)
+#define ARM_SMMU_ID2_IAS		GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_ID3		0x2c
 #define ARM_SMMU_GR0_ID4		0x30
@@ -75,11 +76,11 @@
 #define ARM_SMMU_GR0_ID6		0x38
 
 #define ARM_SMMU_GR0_ID7		0x3c
-#define ID7_MAJOR			GENMASK(7, 4)
-#define ID7_MINOR			GENMASK(3, 0)
+#define ARM_SMMU_ID7_MAJOR		GENMASK(7, 4)
+#define ARM_SMMU_ID7_MINOR		GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_sGFSR		0x48
-#define sGFSR_USF			BIT(1)
+#define ARM_SMMU_sGFSR_USF		BIT(1)
 
 #define ARM_SMMU_GR0_sGFSYNR0		0x50
 #define ARM_SMMU_GR0_sGFSYNR1		0x54
@@ -92,106 +93,132 @@
 #define ARM_SMMU_GR0_sTLBGSYNC		0x70
 
 #define ARM_SMMU_GR0_sTLBGSTATUS	0x74
-#define sTLBGSTATUS_GSACTIVE		BIT(0)
+#define ARM_SMMU_sTLBGSTATUS_GSACTIVE	BIT(0)
 
 /* Stream mapping registers */
 #define ARM_SMMU_GR0_SMR(n)		(0x800 + ((n) << 2))
-#define SMR_VALID			BIT(31)
-#define SMR_MASK			GENMASK(31, 16)
-#define SMR_ID				GENMASK(15, 0)
+#define ARM_SMMU_SMR_VALID		BIT(31)
+#define ARM_SMMU_SMR_MASK		GENMASK(31, 16)
+#define ARM_SMMU_SMR_ID			GENMASK(15, 0)
 
 #define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
-#define S2CR_PRIVCFG			GENMASK(25, 24)
+#define ARM_SMMU_S2CR_PRIVCFG		GENMASK(25, 24)
 enum arm_smmu_s2cr_privcfg {
 	S2CR_PRIVCFG_DEFAULT,
 	S2CR_PRIVCFG_DIPAN,
 	S2CR_PRIVCFG_UNPRIV,
 	S2CR_PRIVCFG_PRIV,
 };
-#define S2CR_TYPE			GENMASK(17, 16)
+#define ARM_SMMU_S2CR_TYPE		GENMASK(17, 16)
 enum arm_smmu_s2cr_type {
 	S2CR_TYPE_TRANS,
 	S2CR_TYPE_BYPASS,
 	S2CR_TYPE_FAULT,
 };
-#define S2CR_EXIDVALID			BIT(10)
-#define S2CR_CBNDX			GENMASK(7, 0)
+#define ARM_SMMU_S2CR_EXIDVALID		BIT(10)
+#define ARM_SMMU_S2CR_CBNDX		GENMASK(7, 0)
 
 /* Context bank attribute registers */
 #define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
-#define CBAR_IRPTNDX			GENMASK(31, 24)
-#define CBAR_TYPE			GENMASK(17, 16)
+#define ARM_SMMU_CBAR_IRPTNDX		GENMASK(31, 24)
+#define ARM_SMMU_CBAR_TYPE		GENMASK(17, 16)
 enum arm_smmu_cbar_type {
 	CBAR_TYPE_S2_TRANS,
 	CBAR_TYPE_S1_TRANS_S2_BYPASS,
 	CBAR_TYPE_S1_TRANS_S2_FAULT,
 	CBAR_TYPE_S1_TRANS_S2_TRANS,
 };
-#define CBAR_S1_MEMATTR			GENMASK(15, 12)
-#define CBAR_S1_MEMATTR_WB		0xf
-#define CBAR_S1_BPSHCFG			GENMASK(9, 8)
-#define CBAR_S1_BPSHCFG_NSH		3
-#define CBAR_VMID			GENMASK(7, 0)
+#define ARM_SMMU_CBAR_S1_MEMATTR	GENMASK(15, 12)
+#define ARM_SMMU_CBAR_S1_MEMATTR_WB	0xf
+#define ARM_SMMU_CBAR_S1_BPSHCFG	GENMASK(9, 8)
+#define ARM_SMMU_CBAR_S1_BPSHCFG_NSH	3
+#define ARM_SMMU_CBAR_VMID		GENMASK(7, 0)
 
 #define ARM_SMMU_GR1_CBFRSYNRA(n)	(0x400 + ((n) << 2))
 
 #define ARM_SMMU_GR1_CBA2R(n)		(0x800 + ((n) << 2))
-#define CBA2R_VMID16			GENMASK(31, 16)
-#define CBA2R_VA64			BIT(0)
+#define ARM_SMMU_CBA2R_VMID16		GENMASK(31, 16)
+#define ARM_SMMU_CBA2R_VA64		BIT(0)
 
 #define ARM_SMMU_CB_SCTLR		0x0
-#define SCTLR_S1_ASIDPNE		BIT(12)
-#define SCTLR_CFCFG			BIT(7)
-#define SCTLR_CFIE			BIT(6)
-#define SCTLR_CFRE			BIT(5)
-#define SCTLR_E				BIT(4)
-#define SCTLR_AFE			BIT(2)
-#define SCTLR_TRE			BIT(1)
-#define SCTLR_M				BIT(0)
+#define ARM_SMMU_SCTLR_S1_ASIDPNE	BIT(12)
+#define ARM_SMMU_SCTLR_CFCFG		BIT(7)
+#define ARM_SMMU_SCTLR_CFIE		BIT(6)
+#define ARM_SMMU_SCTLR_CFRE		BIT(5)
+#define ARM_SMMU_SCTLR_E		BIT(4)
+#define ARM_SMMU_SCTLR_AFE		BIT(2)
+#define ARM_SMMU_SCTLR_TRE		BIT(1)
+#define ARM_SMMU_SCTLR_M		BIT(0)
 
 #define ARM_SMMU_CB_ACTLR		0x4
 
 #define ARM_SMMU_CB_RESUME		0x8
-#define RESUME_TERMINATE		BIT(0)
+#define ARM_SMMU_RESUME_TERMINATE	BIT(0)
 
 #define ARM_SMMU_CB_TCR2		0x10
-#define TCR2_SEP			GENMASK(17, 15)
-#define TCR2_SEP_UPSTREAM		0x7
-#define TCR2_AS				BIT(4)
+#define ARM_SMMU_TCR2_SEP		GENMASK(17, 15)
+#define ARM_SMMU_TCR2_SEP_UPSTREAM	0x7
+#define ARM_SMMU_TCR2_AS		BIT(4)
+#define ARM_SMMU_TCR2_PASIZE		GENMASK(3, 0)
 
 #define ARM_SMMU_CB_TTBR0		0x20
 #define ARM_SMMU_CB_TTBR1		0x28
-#define TTBRn_ASID			GENMASK_ULL(63, 48)
+#define ARM_SMMU_TTBRn_ASID		GENMASK_ULL(63, 48)
 
 #define ARM_SMMU_CB_TCR			0x30
+#define ARM_SMMU_TCR_EAE		BIT(31)
+#define ARM_SMMU_TCR_EPD1		BIT(23)
+#define ARM_SMMU_TCR_TG0		GENMASK(15, 14)
+#define ARM_SMMU_TCR_SH0		GENMASK(13, 12)
+#define ARM_SMMU_TCR_ORGN0		GENMASK(11, 10)
+#define ARM_SMMU_TCR_IRGN0		GENMASK(9, 8)
+#define ARM_SMMU_TCR_T0SZ		GENMASK(5, 0)
+
+#define ARM_SMMU_VTCR_RES1		BIT(31)
+#define ARM_SMMU_VTCR_PS		GENMASK(18, 16)
+#define ARM_SMMU_VTCR_TG0		ARM_SMMU_TCR_TG0
+#define ARM_SMMU_VTCR_SH0		ARM_SMMU_TCR_SH0
+#define ARM_SMMU_VTCR_ORGN0		ARM_SMMU_TCR_ORGN0
+#define ARM_SMMU_VTCR_IRGN0		ARM_SMMU_TCR_IRGN0
+#define ARM_SMMU_VTCR_SL0		GENMASK(7, 6)
+#define ARM_SMMU_VTCR_T0SZ		ARM_SMMU_TCR_T0SZ
+
 #define ARM_SMMU_CB_CONTEXTIDR		0x34
 #define ARM_SMMU_CB_S1_MAIR0		0x38
 #define ARM_SMMU_CB_S1_MAIR1		0x3c
 
 #define ARM_SMMU_CB_PAR			0x50
-#define CB_PAR_F			BIT(0)
+#define ARM_SMMU_CB_PAR_F		BIT(0)
 
 #define ARM_SMMU_CB_FSR			0x58
-#define FSR_MULTI			BIT(31)
-#define FSR_SS				BIT(30)
-#define FSR_UUT				BIT(8)
-#define FSR_ASF				BIT(7)
-#define FSR_TLBLKF			BIT(6)
-#define FSR_TLBMCF			BIT(5)
-#define FSR_EF				BIT(4)
-#define FSR_PF				BIT(3)
-#define FSR_AFF				BIT(2)
-#define FSR_TF				BIT(1)
-
-#define FSR_IGN				(FSR_AFF | FSR_ASF | \
-					 FSR_TLBMCF | FSR_TLBLKF)
-#define FSR_FAULT			(FSR_MULTI | FSR_SS | FSR_UUT | \
-					 FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
+#define ARM_SMMU_FSR_MULTI		BIT(31)
+#define ARM_SMMU_FSR_SS			BIT(30)
+#define ARM_SMMU_FSR_UUT		BIT(8)
+#define ARM_SMMU_FSR_ASF		BIT(7)
+#define ARM_SMMU_FSR_TLBLKF		BIT(6)
+#define ARM_SMMU_FSR_TLBMCF		BIT(5)
+#define ARM_SMMU_FSR_EF			BIT(4)
+#define ARM_SMMU_FSR_PF			BIT(3)
+#define ARM_SMMU_FSR_AFF		BIT(2)
+#define ARM_SMMU_FSR_TF			BIT(1)
+
+#define ARM_SMMU_FSR_IGN		(ARM_SMMU_FSR_AFF |		\
+					 ARM_SMMU_FSR_ASF |		\
+					 ARM_SMMU_FSR_TLBMCF |		\
+					 ARM_SMMU_FSR_TLBLKF)
+
+#define ARM_SMMU_FSR_FAULT		(ARM_SMMU_FSR_MULTI |		\
+					 ARM_SMMU_FSR_SS |		\
+					 ARM_SMMU_FSR_UUT |		\
+					 ARM_SMMU_FSR_EF |		\
+					 ARM_SMMU_FSR_PF |		\
+					 ARM_SMMU_FSR_TF |		\
+					 ARM_SMMU_FSR_IGN)
 
 #define ARM_SMMU_CB_FAR			0x60
 
 #define ARM_SMMU_CB_FSYNR0		0x68
-#define FSYNR0_WNR			BIT(4)
+#define ARM_SMMU_FSYNR0_WNR		BIT(4)
 
 #define ARM_SMMU_CB_S1_TLBIVA		0x600
 #define ARM_SMMU_CB_S1_TLBIASID		0x610
@@ -203,7 +230,7 @@ enum arm_smmu_cbar_type {
 #define ARM_SMMU_CB_ATS1PR		0x800
 
 #define ARM_SMMU_CB_ATSR		0x8f0
-#define ATSR_ACTIVE			BIT(0)
+#define ARM_SMMU_ATSR_ACTIVE		BIT(0)
 
 
 /* Maximum number of context banks per SMMU */
@@ -297,7 +324,7 @@ struct arm_smmu_cfg {
 	enum arm_smmu_cbar_type		cbar;
 	enum arm_smmu_context_fmt	fmt;
 };
-#define INVALID_IRPTNDX			0xff
+#define ARM_SMMU_INVALID_IRPTNDX	0xff
 
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
@@ -318,6 +345,33 @@ struct arm_smmu_domain {
 	struct iommu_domain		domain;
 };
 
+static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
+{
+	return ARM_SMMU_TCR_EPD1 |
+	       FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+	       FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+	       FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+	       FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+	       FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+}
+
+static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
+{
+	return FIELD_PREP(ARM_SMMU_TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
+	       FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
+}
+
+static inline u32 arm_smmu_lpae_vtcr(struct io_pgtable_cfg *cfg)
+{
+	return ARM_SMMU_VTCR_RES1 |
+	       FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) |
+	       FIELD_PREP(ARM_SMMU_VTCR_TG0, cfg->arm_lpae_s2_cfg.vtcr.tg) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SH0, cfg->arm_lpae_s2_cfg.vtcr.sh) |
+	       FIELD_PREP(ARM_SMMU_VTCR_ORGN0, cfg->arm_lpae_s2_cfg.vtcr.orgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_IRGN0, cfg->arm_lpae_s2_cfg.vtcr.irgn) |
+	       FIELD_PREP(ARM_SMMU_VTCR_SL0, cfg->arm_lpae_s2_cfg.vtcr.sl) |
+	       FIELD_PREP(ARM_SMMU_VTCR_T0SZ, cfg->arm_lpae_s2_cfg.vtcr.tsz);
+}
 
 /* Implementation details, yay! */
 struct arm_smmu_impl {
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 3acfa6a25fa2..071bb42bbbc5 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -244,7 +244,7 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
 		     info->dev->hdr_type != PCI_HEADER_TYPE_NORMAL) ||
 		    (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE &&
 		     (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL &&
-		      info->dev->class >> 8 != PCI_CLASS_BRIDGE_OTHER))) {
+		      info->dev->class >> 16 != PCI_BASE_CLASS_BRIDGE))) {
 			pr_warn("Device scope type does not match for %s\n",
 				pci_name(info->dev));
 			return -EINVAL;
@@ -1354,7 +1354,6 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	struct qi_desc desc;
 
 	if (mask) {
-		WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
 		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
 	} else
@@ -1371,6 +1370,47 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	qi_submit_sync(&desc, iommu);
 }
 
+/* PASID-based IOTLB invalidation */
+void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
+		     unsigned long npages, bool ih)
+{
+	struct qi_desc desc = {.qw2 = 0, .qw3 = 0};
+
+	/*
+	 * npages == -1 means a PASID-selective invalidation, otherwise,
+	 * a positive value for Page-selective-within-PASID invalidation.
+	 * 0 is not a valid input.
+	 */
+	if (WARN_ON(!npages)) {
+		pr_err("Invalid input npages = %ld\n", npages);
+		return;
+	}
+
+	if (npages == -1) {
+		desc.qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+				QI_EIOTLB_TYPE;
+		desc.qw1 = 0;
+	} else {
+		int mask = ilog2(__roundup_pow_of_two(npages));
+		unsigned long align = (1ULL << (VTD_PAGE_SHIFT + mask));
+
+		if (WARN_ON_ONCE(!ALIGN(addr, align)))
+			addr &= ~(align - 1);
+
+		desc.qw0 = QI_EIOTLB_PASID(pasid) |
+				QI_EIOTLB_DID(did) |
+				QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
+				QI_EIOTLB_TYPE;
+		desc.qw1 = QI_EIOTLB_ADDR(addr) |
+				QI_EIOTLB_IH(ih) |
+				QI_EIOTLB_AM(mask);
+	}
+
+	qi_submit_sync(&desc, iommu);
+}
+
 /*
  * Disable Queued Invalidation interface.
  */
diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index 471f05d452e0..c1257bef553c 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -5,6 +5,7 @@
  * Authors: Gayatri Kammela <gayatri.kammela@intel.com>
  *	    Sohil Mehta <sohil.mehta@intel.com>
  *	    Jacob Pan <jacob.jun.pan@linux.intel.com>
+ *	    Lu Baolu <baolu.lu@linux.intel.com>
  */
 
 #include <linux/debugfs.h>
@@ -283,6 +284,77 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(dmar_translation_struct);
 
+static inline unsigned long level_to_directory_size(int level)
+{
+	return BIT_ULL(VTD_PAGE_SHIFT + VTD_STRIDE_SHIFT * (level - 1));
+}
+
+static inline void
+dump_page_info(struct seq_file *m, unsigned long iova, u64 *path)
+{
+	seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\n",
+		   iova >> VTD_PAGE_SHIFT, path[5], path[4],
+		   path[3], path[2], path[1]);
+}
+
+static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
+			       int level, unsigned long start,
+			       u64 *path)
+{
+	int i;
+
+	if (level > 5 || level < 1)
+		return;
+
+	for (i = 0; i < BIT_ULL(VTD_STRIDE_SHIFT);
+			i++, pde++, start += level_to_directory_size(level)) {
+		if (!dma_pte_present(pde))
+			continue;
+
+		path[level] = pde->val;
+		if (dma_pte_superpage(pde) || level == 1)
+			dump_page_info(m, start, path);
+		else
+			pgtable_walk_level(m, phys_to_virt(dma_pte_addr(pde)),
+					   level - 1, start, path);
+		path[level] = 0;
+	}
+}
+
+static int show_device_domain_translation(struct device *dev, void *data)
+{
+	struct dmar_domain *domain = find_domain(dev);
+	struct seq_file *m = data;
+	u64 path[6] = { 0 };
+
+	if (!domain)
+		return 0;
+
+	seq_printf(m, "Device %s with pasid %d @0x%llx\n",
+		   dev_name(dev), domain->default_pasid,
+		   (u64)virt_to_phys(domain->pgd));
+	seq_puts(m, "IOVA_PFN\t\tPML5E\t\t\tPML4E\t\t\tPDPE\t\t\tPDE\t\t\tPTE\n");
+
+	pgtable_walk_level(m, domain->pgd, domain->agaw + 2, 0, path);
+	seq_putc(m, '\n');
+
+	return 0;
+}
+
+static int domain_translation_struct_show(struct seq_file *m, void *unused)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&device_domain_lock, flags);
+	ret = bus_for_each_dev(&pci_bus_type, NULL, m,
+			       show_device_domain_translation);
+	spin_unlock_irqrestore(&device_domain_lock, flags);
+
+	return ret;
+}
+DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
+
 #ifdef CONFIG_IRQ_REMAP
 static void ir_tbl_remap_entry_show(struct seq_file *m,
 				    struct intel_iommu *iommu)
@@ -396,6 +468,9 @@ void __init intel_iommu_debugfs_init(void)
 			    &iommu_regset_fops);
 	debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug,
 			    NULL, &dmar_translation_struct_fops);
+	debugfs_create_file("domain_translation_struct", 0444,
+			    intel_iommu_debug, NULL,
+			    &domain_translation_struct_fops);
 #ifdef CONFIG_IRQ_REMAP
 	debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug,
 			    NULL, &ir_translation_struct_fops);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 932267f49f9a..9dc37672bf89 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -307,6 +307,20 @@ static int hw_pass_through = 1;
  */
 #define DOMAIN_FLAG_LOSE_CHILDREN		BIT(1)
 
+/*
+ * When VT-d works in the scalable mode, it allows DMA translation to
+ * happen through either first level or second level page table. This
+ * bit marks that the DMA translation for the domain goes through the
+ * first level page table, otherwise, it goes through the second level.
+ */
+#define DOMAIN_FLAG_USE_FIRST_LEVEL		BIT(2)
+
+/*
+ * Domain represents a virtual machine which demands iommu nested
+ * translation mode support.
+ */
+#define DOMAIN_FLAG_NESTING_MODE		BIT(3)
+
 #define for_each_domain_iommu(idx, domain)			\
 	for (idx = 0; idx < g_num_of_iommus; idx++)		\
 		if (domain->iommu_refcnt[idx])
@@ -355,9 +369,14 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 int dmar_disabled = 0;
 #else
 int dmar_disabled = 1;
-#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
+#endif /* CONFIG_INTEL_IOMMU_DEFAULT_ON */
 
+#ifdef INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
+int intel_iommu_sm = 1;
+#else
 int intel_iommu_sm;
+#endif /* INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON */
+
 int intel_iommu_enabled = 0;
 EXPORT_SYMBOL_GPL(intel_iommu_enabled);
 
@@ -368,7 +387,6 @@ static int intel_iommu_superpage = 1;
 static int iommu_identity_mapping;
 static int intel_no_bounce;
 
-#define IDENTMAP_ALL		1
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
@@ -377,7 +395,7 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 #define DEFER_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-2))
-static DEFINE_SPINLOCK(device_domain_lock);
+DEFINE_SPINLOCK(device_domain_lock);
 static LIST_HEAD(device_domain_list);
 
 #define device_needs_bounce(d) (!intel_no_bounce && dev_is_pci(d) &&	\
@@ -552,6 +570,11 @@ static inline int domain_type_is_si(struct dmar_domain *domain)
 	return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY;
 }
 
+static inline bool domain_use_first_level(struct dmar_domain *domain)
+{
+	return domain->flags & DOMAIN_FLAG_USE_FIRST_LEVEL;
+}
+
 static inline int domain_pfn_supported(struct dmar_domain *domain,
 				       unsigned long pfn)
 {
@@ -661,11 +684,12 @@ static int domain_update_iommu_snooping(struct intel_iommu *skip)
 	return ret;
 }
 
-static int domain_update_iommu_superpage(struct intel_iommu *skip)
+static int domain_update_iommu_superpage(struct dmar_domain *domain,
+					 struct intel_iommu *skip)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
-	int mask = 0xf;
+	int mask = 0x3;
 
 	if (!intel_iommu_superpage) {
 		return 0;
@@ -675,7 +699,13 @@ static int domain_update_iommu_superpage(struct intel_iommu *skip)
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
 		if (iommu != skip) {
-			mask &= cap_super_page_val(iommu->cap);
+			if (domain && domain_use_first_level(domain)) {
+				if (!cap_fl1gp_support(iommu->cap))
+					mask = 0x1;
+			} else {
+				mask &= cap_super_page_val(iommu->cap);
+			}
+
 			if (!mask)
 				break;
 		}
@@ -690,7 +720,7 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
-	domain->iommu_superpage = domain_update_iommu_superpage(NULL);
+	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -774,13 +804,7 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pf_pdev;
 
-		pdev = to_pci_dev(dev);
-
-#ifdef CONFIG_X86
-		/* VMD child devices currently cannot be handled individually */
-		if (is_vmd(pdev->bus))
-			return NULL;
-#endif
+		pdev = pci_real_dma_dev(to_pci_dev(dev));
 
 		/* VFs aren't listed in scope tables; we need to look up
 		 * the PF instead to find the IOMMU. */
@@ -913,6 +937,8 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 
 			domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
 			pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+			if (domain_use_first_level(domain))
+				pteval |= DMA_FL_PTE_XD;
 			if (cmpxchg64(&pte->val, 0ULL, pteval))
 				/* Someone else set it while we were thinking; use theirs. */
 				free_pgtable_page(tmp_page);
@@ -1483,6 +1509,20 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain,
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
+static void domain_flush_piotlb(struct intel_iommu *iommu,
+				struct dmar_domain *domain,
+				u64 addr, unsigned long npages, bool ih)
+{
+	u16 did = domain->iommu_did[iommu->seq_id];
+
+	if (domain->default_pasid)
+		qi_flush_piotlb(iommu, did, domain->default_pasid,
+				addr, npages, ih);
+
+	if (!list_empty(&domain->devices))
+		qi_flush_piotlb(iommu, did, PASID_RID2PASID, addr, npages, ih);
+}
+
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 				  struct dmar_domain *domain,
 				  unsigned long pfn, unsigned int pages,
@@ -1496,18 +1536,23 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 
 	if (ih)
 		ih = 1 << 6;
-	/*
-	 * Fallback to domain selective flush if no PSI support or the size is
-	 * too big.
-	 * PSI requires page size to be 2 ^ x, and the base address is naturally
-	 * aligned to the size
-	 */
-	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
-		iommu->flush.flush_iotlb(iommu, did, 0, 0,
-						DMA_TLB_DSI_FLUSH);
-	else
-		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
-						DMA_TLB_PSI_FLUSH);
+
+	if (domain_use_first_level(domain)) {
+		domain_flush_piotlb(iommu, domain, addr, pages, ih);
+	} else {
+		/*
+		 * Fallback to domain selective flush if no PSI support or
+		 * the size is too big. PSI requires page size to be 2 ^ x,
+		 * and the base address is naturally aligned to the size.
+		 */
+		if (!cap_pgsel_inv(iommu->cap) ||
+		    mask > cap_max_amask_val(iommu->cap))
+			iommu->flush.flush_iotlb(iommu, did, 0, 0,
+							DMA_TLB_DSI_FLUSH);
+		else
+			iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+							DMA_TLB_PSI_FLUSH);
+	}
 
 	/*
 	 * In caching mode, changes of pages from non-present to present require
@@ -1522,8 +1567,11 @@ static inline void __mapping_notify_one(struct intel_iommu *iommu,
 					struct dmar_domain *domain,
 					unsigned long pfn, unsigned int pages)
 {
-	/* It's a non-present to present mapping. Only flush if caching mode */
-	if (cap_caching_mode(iommu->cap))
+	/*
+	 * It's a non-present to present mapping. Only flush if caching mode
+	 * and second level.
+	 */
+	if (cap_caching_mode(iommu->cap) && !domain_use_first_level(domain))
 		iommu_flush_iotlb_psi(iommu, domain, pfn, pages, 0, 1);
 	else
 		iommu_flush_write_buffer(iommu);
@@ -1540,7 +1588,11 @@ static void iommu_flush_iova(struct iova_domain *iovad)
 		struct intel_iommu *iommu = g_iommus[idx];
 		u16 did = domain->iommu_did[iommu->seq_id];
 
-		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+		if (domain_use_first_level(domain))
+			domain_flush_piotlb(iommu, domain, 0, -1, 0);
+		else
+			iommu->flush.flush_iotlb(iommu, did, 0, 0,
+						 DMA_TLB_DSI_FLUSH);
 
 		if (!cap_caching_mode(iommu->cap))
 			iommu_flush_dev_iotlb(get_iommu_domain(iommu, did),
@@ -1709,6 +1761,33 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 #endif
 }
 
+/*
+ * Check and return whether first level is used by default for
+ * DMA translation.
+ */
+static bool first_level_by_default(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	static int first_level_support = -1;
+
+	if (likely(first_level_support != -1))
+		return first_level_support;
+
+	first_level_support = 1;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!sm_supported(iommu) || !ecap_flts(iommu->ecap)) {
+			first_level_support = 0;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return first_level_support;
+}
+
 static struct dmar_domain *alloc_domain(int flags)
 {
 	struct dmar_domain *domain;
@@ -1720,6 +1799,8 @@ static struct dmar_domain *alloc_domain(int flags)
 	memset(domain, 0, sizeof(*domain));
 	domain->nid = NUMA_NO_NODE;
 	domain->flags = flags;
+	if (first_level_by_default())
+		domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL;
 	domain->has_iotlb_device = false;
 	INIT_LIST_HEAD(&domain->devices);
 
@@ -1849,14 +1930,16 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
 {
 	int adjust_width, agaw;
 	unsigned long sagaw;
-	int err;
+	int ret;
 
 	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
 
-	err = init_iova_flush_queue(&domain->iovad,
-				    iommu_flush_iova, iova_entry_free);
-	if (err)
-		return err;
+	if (!intel_iommu_strict) {
+		ret = init_iova_flush_queue(&domain->iovad,
+					    iommu_flush_iova, iova_entry_free);
+		if (ret)
+			pr_info("iova flush queue initialization failed\n");
+	}
 
 	domain_reserve_special_ranges(domain);
 
@@ -2229,17 +2312,20 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	unsigned long sg_res = 0;
 	unsigned int largepage_lvl = 0;
 	unsigned long lvl_pages = 0;
+	u64 attr;
 
 	BUG_ON(!domain_pfn_supported(domain, iov_pfn + nr_pages - 1));
 
 	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
 		return -EINVAL;
 
-	prot &= DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP;
+	attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+	if (domain_use_first_level(domain))
+		attr |= DMA_FL_PTE_PRESENT | DMA_FL_PTE_XD;
 
 	if (!sg) {
 		sg_res = nr_pages;
-		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
+		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | attr;
 	}
 
 	while (nr_pages > 0) {
@@ -2251,7 +2337,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			sg_res = aligned_nrpages(sg->offset, sg->length);
 			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + pgoff;
 			sg->dma_length = sg->length;
-			pteval = (sg_phys(sg) - pgoff) | prot;
+			pteval = (sg_phys(sg) - pgoff) | attr;
 			phys_pfn = pteval >> VTD_PAGE_SHIFT;
 		}
 
@@ -2420,7 +2506,7 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-static struct dmar_domain *find_domain(struct device *dev)
+struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
@@ -2428,6 +2514,9 @@ static struct dmar_domain *find_domain(struct device *dev)
 		     dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
 		return NULL;
 
+	if (dev_is_pci(dev))
+		dev = &pci_real_dma_dev(to_pci_dev(dev))->dev;
+
 	/* No lock here, assumes no domain exit in normal case */
 	info = dev->archdata.iommu;
 	if (likely(info))
@@ -2463,6 +2552,36 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 	return NULL;
 }
 
+static int domain_setup_first_level(struct intel_iommu *iommu,
+				    struct dmar_domain *domain,
+				    struct device *dev,
+				    int pasid)
+{
+	int flags = PASID_FLAG_SUPERVISOR_MODE;
+	struct dma_pte *pgd = domain->pgd;
+	int agaw, level;
+
+	/*
+	 * Skip top levels of page tables for iommu which has
+	 * less agaw than default. Unnecessary for PT mode.
+	 */
+	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+		pgd = phys_to_virt(dma_pte_addr(pgd));
+		if (!dma_pte_present(pgd))
+			return -ENOMEM;
+	}
+
+	level = agaw_to_level(agaw);
+	if (level != 4 && level != 5)
+		return -EINVAL;
+
+	flags |= (level == 5) ? PASID_FLAG_FL5LP : 0;
+
+	return intel_pasid_setup_first_level(iommu, dev, (pgd_t *)pgd, pasid,
+					     domain->iommu_did[iommu->seq_id],
+					     flags);
+}
+
 static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 						    int bus, int devfn,
 						    struct device *dev,
@@ -2562,6 +2681,9 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 		if (hw_pass_through && domain_type_is_si(domain))
 			ret = intel_pasid_setup_pass_through(iommu, domain,
 					dev, PASID_RID2PASID);
+		else if (domain_use_first_level(domain))
+			ret = domain_setup_first_level(iommu, domain, dev,
+					PASID_RID2PASID);
 		else
 			ret = intel_pasid_setup_second_level(iommu, domain,
 					dev, PASID_RID2PASID);
@@ -2767,10 +2889,8 @@ static int __init si_domain_init(int hw)
 	}
 
 	/*
-	 * Normally we use DMA domains for devices which have RMRRs. But we
-	 * loose this requirement for graphic and usb devices. Identity map
-	 * the RMRRs for graphic and USB devices so that they could use the
-	 * si_domain.
+	 * Identity map the RMRRs so that devices with RMRRs could also use
+	 * the si_domain.
 	 */
 	for_each_rmrr_units(rmrr) {
 		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
@@ -2778,9 +2898,6 @@ static int __init si_domain_init(int hw)
 			unsigned long long start = rmrr->base_address;
 			unsigned long long end = rmrr->end_address;
 
-			if (device_is_rmrr_locked(dev))
-				continue;
-
 			if (WARN_ON(end < start ||
 				    end >> agaw_to_width(si_domain->agaw)))
 				continue;
@@ -2919,9 +3036,6 @@ static int device_def_domain_type(struct device *dev)
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
-		if (device_is_rmrr_locked(dev))
-			return IOMMU_DOMAIN_DMA;
-
 		/*
 		 * Prevent any device marked as untrusted from getting
 		 * placed into the statically identity mapping domain.
@@ -2959,13 +3073,9 @@ static int device_def_domain_type(struct device *dev)
 				return IOMMU_DOMAIN_DMA;
 		} else if (pci_pcie_type(pdev) == PCI_EXP_TYPE_PCI_BRIDGE)
 			return IOMMU_DOMAIN_DMA;
-	} else {
-		if (device_has_rmrr(dev))
-			return IOMMU_DOMAIN_DMA;
 	}
 
-	return (iommu_identity_mapping & IDENTMAP_ALL) ?
-			IOMMU_DOMAIN_IDENTITY : 0;
+	return 0;
 }
 
 static void intel_iommu_init_qi(struct intel_iommu *iommu)
@@ -3294,10 +3404,7 @@ static int __init init_dmars(void)
 
 		if (!ecap_pass_through(iommu->ecap))
 			hw_pass_through = 0;
-#ifdef CONFIG_INTEL_IOMMU_SVM
-		if (pasid_supported(iommu))
-			intel_svm_init(iommu);
-#endif
+		intel_svm_check(iommu);
 	}
 
 	/*
@@ -3312,9 +3419,6 @@ static int __init init_dmars(void)
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
 	}
 
-	if (iommu_default_passthrough())
-		iommu_identity_mapping |= IDENTMAP_ALL;
-
 #ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
 	dmar_map_gfx = 0;
 #endif
@@ -3387,8 +3491,21 @@ static unsigned long intel_alloc_iova(struct device *dev,
 {
 	unsigned long iova_pfn;
 
-	/* Restrict dma_mask to the width that the iommu can handle */
-	dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+	/*
+	 * Restrict dma_mask to the width that the iommu can handle.
+	 * First-level translation restricts the input-address to a
+	 * canonical address (i.e., address bits 63:N have the same
+	 * value as address bit [N-1], where N is 48-bits with 4-level
+	 * paging and 57-bits with 5-level paging). Hence, skip bit
+	 * [N-1].
+	 */
+	if (domain_use_first_level(domain))
+		dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw - 1),
+				 dma_mask);
+	else
+		dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw),
+				 dma_mask);
+
 	/* Ensure we reserve the whole size-aligned region */
 	nrpages = __roundup_pow_of_two(nrpages);
 
@@ -3406,7 +3523,8 @@ static unsigned long intel_alloc_iova(struct device *dev,
 	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
 				   IOVA_PFN(dma_mask), true);
 	if (unlikely(!iova_pfn)) {
-		dev_err(dev, "Allocating %ld-page iova failed", nrpages);
+		dev_err_once(dev, "Allocating %ld-page iova failed\n",
+			     nrpages);
 		return 0;
 	}
 
@@ -3774,8 +3892,8 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 		return 0;
 	}
 
-	trace_map_sg(dev, iova_pfn << PAGE_SHIFT,
-		     sg_phys(sglist), size << VTD_PAGE_SHIFT);
+	for_each_sg(sglist, sg, nelems, i)
+		trace_map_sg(dev, i + 1, nelems, sg);
 
 	return nelems;
 }
@@ -3987,6 +4105,9 @@ bounce_map_sg(struct device *dev, struct scatterlist *sglist, int nelems,
 		sg_dma_len(sg) = sg->length;
 	}
 
+	for_each_sg(sglist, sg, nelems, i)
+		trace_bounce_map_sg(dev, i + 1, nelems, sg);
+
 	return nelems;
 
 out_unmap:
@@ -4315,16 +4436,31 @@ static void __init init_iommu_pm_ops(void)
 static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
+static int rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+{
+	if (!IS_ALIGNED(rmrr->base_address, PAGE_SIZE) ||
+	    !IS_ALIGNED(rmrr->end_address + 1, PAGE_SIZE) ||
+	    rmrr->end_address <= rmrr->base_address ||
+	    arch_rmrr_sanity_check(rmrr))
+		return -EINVAL;
+
+	return 0;
+}
+
 int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;
-	int ret;
 
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
-	ret = arch_rmrr_sanity_check(rmrr);
-	if (ret)
-		return ret;
+	if (rmrr_sanity_check(rmrr))
+		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+			   "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
+			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
+			   rmrr->base_address, rmrr->end_address,
+			   dmi_get_system_info(DMI_BIOS_VENDOR),
+			   dmi_get_system_info(DMI_BIOS_VERSION),
+			   dmi_get_system_info(DMI_PRODUCT_VERSION));
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
@@ -4470,7 +4606,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 			iommu->name);
 		return -ENXIO;
 	}
-	sp = domain_update_iommu_superpage(iommu) - 1;
+	sp = domain_update_iommu_superpage(NULL, iommu) - 1;
 	if (sp >= 0 && !(cap_super_page_val(iommu->cap) & (1 << sp))) {
 		pr_warn("%s: Doesn't support large page.\n",
 			iommu->name);
@@ -4490,10 +4626,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
 	if (ret)
 		goto out;
 
-#ifdef CONFIG_INTEL_IOMMU_SVM
-	if (pasid_supported(iommu))
-		intel_svm_init(iommu);
-#endif
+	intel_svm_check(iommu);
 
 	if (dmaru->ignored) {
 		/*
@@ -4898,7 +5031,7 @@ static int __init platform_optin_force_iommu(void)
 	 * map for all devices except those marked as being untrusted.
 	 */
 	if (dmar_disabled)
-		iommu_identity_mapping |= IDENTMAP_ALL;
+		iommu_set_default_passthrough(false);
 
 	dmar_disabled = 0;
 	no_iommu = 0;
@@ -5198,6 +5331,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 {
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
+	int ret;
 
 	switch (type) {
 	case IOMMU_DOMAIN_DMA:
@@ -5214,11 +5348,12 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 			return NULL;
 		}
 
-		if (type == IOMMU_DOMAIN_DMA &&
-		    init_iova_flush_queue(&dmar_domain->iovad,
-					  iommu_flush_iova, iova_entry_free)) {
-			pr_warn("iova flush queue initialization failed\n");
-			intel_iommu_strict = 1;
+		if (!intel_iommu_strict && type == IOMMU_DOMAIN_DMA) {
+			ret = init_iova_flush_queue(&dmar_domain->iovad,
+						    iommu_flush_iova,
+						    iova_entry_free);
+			if (ret)
+				pr_info("iova flush queue initialization failed\n");
 		}
 
 		domain_update_iommu_cap(dmar_domain);
@@ -5284,7 +5419,7 @@ static void auxiliary_unlink_device(struct dmar_domain *domain,
 	domain->auxd_refcnt--;
 
 	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		intel_pasid_free_id(domain->default_pasid);
+		ioasid_free(domain->default_pasid);
 }
 
 static int aux_domain_add_dev(struct dmar_domain *domain,
@@ -5302,10 +5437,11 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 	if (domain->default_pasid <= 0) {
 		int pasid;
 
-		pasid = intel_pasid_alloc_id(domain, PASID_MIN,
-					     pci_max_pasids(to_pci_dev(dev)),
-					     GFP_KERNEL);
-		if (pasid <= 0) {
+		/* No private data needed for the default pasid */
+		pasid = ioasid_alloc(NULL, PASID_MIN,
+				     pci_max_pasids(to_pci_dev(dev)) - 1,
+				     NULL);
+		if (pasid == INVALID_IOASID) {
 			pr_err("Can't allocate default pasid\n");
 			return -ENODEV;
 		}
@@ -5323,8 +5459,12 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
 		goto attach_failed;
 
 	/* Setup the PASID entry for mediated devices: */
-	ret = intel_pasid_setup_second_level(iommu, domain, dev,
-					     domain->default_pasid);
+	if (domain_use_first_level(domain))
+		ret = domain_setup_first_level(iommu, domain, dev,
+					       domain->default_pasid);
+	else
+		ret = intel_pasid_setup_second_level(iommu, domain, dev,
+						     domain->default_pasid);
 	if (ret)
 		goto table_failed;
 	spin_unlock(&iommu->lock);
@@ -5341,7 +5481,7 @@ attach_failed:
 	spin_unlock(&iommu->lock);
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 	if (!domain->auxd_refcnt && domain->default_pasid > 0)
-		intel_pasid_free_id(domain->default_pasid);
+		ioasid_free(domain->default_pasid);
 
 	return ret;
 }
@@ -5595,6 +5735,24 @@ static inline bool iommu_pasid_support(void)
 	return ret;
 }
 
+static inline bool nested_mode_support(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool ret = true;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!sm_supported(iommu) || !ecap_nest(iommu->ecap)) {
+			ret = false;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -5752,15 +5910,6 @@ static void intel_iommu_get_resv_regions(struct device *device,
 	list_add_tail(&reg->list, head);
 }
 
-static void intel_iommu_put_resv_regions(struct device *dev,
-					 struct list_head *head)
-{
-	struct iommu_resv_region *entry, *next;
-
-	list_for_each_entry_safe(entry, next, head, list)
-		kfree(entry);
-}
-
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev)
 {
 	struct device_domain_info *info;
@@ -5987,10 +6136,42 @@ static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
 	return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
 }
 
+static int
+intel_iommu_domain_set_attr(struct iommu_domain *domain,
+			    enum iommu_attr attr, void *data)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	unsigned long flags;
+	int ret = 0;
+
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
+	switch (attr) {
+	case DOMAIN_ATTR_NESTING:
+		spin_lock_irqsave(&device_domain_lock, flags);
+		if (nested_mode_support() &&
+		    list_empty(&dmar_domain->devices)) {
+			dmar_domain->flags |= DOMAIN_FLAG_NESTING_MODE;
+			dmar_domain->flags &= ~DOMAIN_FLAG_USE_FIRST_LEVEL;
+		} else {
+			ret = -ENODEV;
+		}
+		spin_unlock_irqrestore(&device_domain_lock, flags);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 const struct iommu_ops intel_iommu_ops = {
 	.capable		= intel_iommu_capable,
 	.domain_alloc		= intel_iommu_domain_alloc,
 	.domain_free		= intel_iommu_domain_free,
+	.domain_set_attr	= intel_iommu_domain_set_attr,
 	.attach_dev		= intel_iommu_attach_device,
 	.detach_dev		= intel_iommu_detach_device,
 	.aux_attach_dev		= intel_iommu_aux_attach_device,
@@ -6002,7 +6183,7 @@ const struct iommu_ops intel_iommu_ops = {
 	.add_device		= intel_iommu_add_device,
 	.remove_device		= intel_iommu_remove_device,
 	.get_resv_regions	= intel_iommu_get_resv_regions,
-	.put_resv_regions	= intel_iommu_put_resv_regions,
+	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.apply_resv_region	= intel_iommu_apply_resv_region,
 	.device_group		= intel_iommu_device_group,
 	.dev_has_feat		= intel_iommu_dev_has_feat,
diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c
index 040a445be300..22b30f10b396 100644
--- a/drivers/iommu/intel-pasid.c
+++ b/drivers/iommu/intel-pasid.c
@@ -26,42 +26,6 @@
  */
 static DEFINE_SPINLOCK(pasid_lock);
 u32 intel_pasid_max_id = PASID_MAX;
-static DEFINE_IDR(pasid_idr);
-
-int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp)
-{
-	int ret, min, max;
-
-	min = max_t(int, start, PASID_MIN);
-	max = min_t(int, end, intel_pasid_max_id);
-
-	WARN_ON(in_interrupt());
-	idr_preload(gfp);
-	spin_lock(&pasid_lock);
-	ret = idr_alloc(&pasid_idr, ptr, min, max, GFP_ATOMIC);
-	spin_unlock(&pasid_lock);
-	idr_preload_end();
-
-	return ret;
-}
-
-void intel_pasid_free_id(int pasid)
-{
-	spin_lock(&pasid_lock);
-	idr_remove(&pasid_idr, pasid);
-	spin_unlock(&pasid_lock);
-}
-
-void *intel_pasid_lookup_id(int pasid)
-{
-	void *p;
-
-	spin_lock(&pasid_lock);
-	p = idr_find(&pasid_idr, pasid);
-	spin_unlock(&pasid_lock);
-
-	return p;
-}
 
 /*
  * Per device pasid table management:
@@ -465,6 +429,21 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 		devtlb_invalidation_with_pasid(iommu, dev, pasid);
 }
 
+static void pasid_flush_caches(struct intel_iommu *iommu,
+				struct pasid_entry *pte,
+				int pasid, u16 did)
+{
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	if (cap_caching_mode(iommu->cap)) {
+		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+		iotlb_invalidation_with_pasid(iommu, did, pasid);
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
+}
+
 /*
  * Set up the scalable mode pasid table entry for first only
  * translation type.
@@ -498,10 +477,15 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 		pasid_set_sre(pte);
 	}
 
-#ifdef CONFIG_X86
-	if (cpu_feature_enabled(X86_FEATURE_LA57))
-		pasid_set_flpm(pte, 1);
-#endif /* CONFIG_X86 */
+	if (flags & PASID_FLAG_FL5LP) {
+		if (cap_5lp_support(iommu->cap)) {
+			pasid_set_flpm(pte, 1);
+		} else {
+			pr_err("No 5-level paging support for first-level\n");
+			pasid_clear_entry(pte);
+			return -EINVAL;
+		}
+	}
 
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, iommu->agaw);
@@ -510,16 +494,7 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	/* Setup Present and PASID Granular Transfer Type: */
 	pasid_set_translation_type(pte, 1);
 	pasid_set_present(pte);
-
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(pte, sizeof(*pte));
-
-	if (cap_caching_mode(iommu->cap)) {
-		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
-		iotlb_invalidation_with_pasid(iommu, did, pasid);
-	} else {
-		iommu_flush_write_buffer(iommu);
-	}
+	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
 }
@@ -583,16 +558,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	 */
 	pasid_set_sre(pte);
 	pasid_set_present(pte);
-
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(pte, sizeof(*pte));
-
-	if (cap_caching_mode(iommu->cap)) {
-		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
-		iotlb_invalidation_with_pasid(iommu, did, pasid);
-	} else {
-		iommu_flush_write_buffer(iommu);
-	}
+	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
 }
@@ -626,16 +592,7 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 	 */
 	pasid_set_sre(pte);
 	pasid_set_present(pte);
-
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(pte, sizeof(*pte));
-
-	if (cap_caching_mode(iommu->cap)) {
-		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
-		iotlb_invalidation_with_pasid(iommu, did, pasid);
-	} else {
-		iommu_flush_write_buffer(iommu);
-	}
+	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
 }
diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h
index fc8cd8f17de1..92de6df24ccb 100644
--- a/drivers/iommu/intel-pasid.h
+++ b/drivers/iommu/intel-pasid.h
@@ -37,6 +37,12 @@
  */
 #define PASID_FLAG_SUPERVISOR_MODE	BIT(0)
 
+/*
+ * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first-
+ * level translation, otherwise, 4-level paging will be used.
+ */
+#define PASID_FLAG_FL5LP		BIT(1)
+
 struct pasid_dir_entry {
 	u64 val;
 };
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index dca88f9fdf29..d7f2a5358900 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -17,25 +17,13 @@
 #include <linux/dmar.h>
 #include <linux/interrupt.h>
 #include <linux/mm_types.h>
+#include <linux/ioasid.h>
 #include <asm/page.h>
 
 #include "intel-pasid.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
 
-int intel_svm_init(struct intel_iommu *iommu)
-{
-	if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
-			!cap_fl1gp_support(iommu->cap))
-		return -EINVAL;
-
-	if (cpu_feature_enabled(X86_FEATURE_LA57) &&
-			!cap_5lp_support(iommu->cap))
-		return -EINVAL;
-
-	return 0;
-}
-
 #define PRQ_ORDER 0
 
 int intel_svm_enable_prq(struct intel_iommu *iommu)
@@ -99,6 +87,33 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 	return 0;
 }
 
+static inline bool intel_svm_capable(struct intel_iommu *iommu)
+{
+	return iommu->flags & VTD_FLAG_SVM_CAPABLE;
+}
+
+void intel_svm_check(struct intel_iommu *iommu)
+{
+	if (!pasid_supported(iommu))
+		return;
+
+	if (cpu_feature_enabled(X86_FEATURE_GBPAGES) &&
+	    !cap_fl1gp_support(iommu->cap)) {
+		pr_err("%s SVM disabled, incompatible 1GB page capability\n",
+		       iommu->name);
+		return;
+	}
+
+	if (cpu_feature_enabled(X86_FEATURE_LA57) &&
+	    !cap_5lp_support(iommu->cap)) {
+		pr_err("%s SVM disabled, incompatible paging mode\n",
+		       iommu->name);
+		return;
+	}
+
+	iommu->flags |= VTD_FLAG_SVM_CAPABLE;
+}
+
 static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
 				unsigned long address, unsigned long pages, int ih)
 {
@@ -207,6 +222,10 @@ static const struct mmu_notifier_ops intel_mmuops = {
 static DEFINE_MUTEX(pasid_mutex);
 static LIST_HEAD(global_svm_list);
 
+#define for_each_svm_dev(sdev, svm, d)			\
+	list_for_each_entry((sdev), &(svm)->devs, list)	\
+		if ((d) != (sdev)->dev) {} else
+
 int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops)
 {
 	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
@@ -220,6 +239,9 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 	if (!iommu || dmar_disabled)
 		return -EINVAL;
 
+	if (!intel_svm_capable(iommu))
+		return -ENOTSUPP;
+
 	if (dev_is_pci(dev)) {
 		pasid_max = pci_max_pasids(to_pci_dev(dev));
 		if (pasid_max < 0)
@@ -252,15 +274,14 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 				goto out;
 			}
 
-			list_for_each_entry(sdev, &svm->devs, list) {
-				if (dev == sdev->dev) {
-					if (sdev->ops != ops) {
-						ret = -EBUSY;
-						goto out;
-					}
-					sdev->users++;
-					goto success;
+			/* Find the matching device in svm list */
+			for_each_svm_dev(sdev, svm, dev) {
+				if (sdev->ops != ops) {
+					ret = -EBUSY;
+					goto out;
 				}
+				sdev->users++;
+				goto success;
 			}
 
 			break;
@@ -314,16 +335,15 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		if (pasid_max > intel_pasid_max_id)
 			pasid_max = intel_pasid_max_id;
 
-		/* Do not use PASID 0 in caching mode (virtualised IOMMU) */
-		ret = intel_pasid_alloc_id(svm,
-					   !!cap_caching_mode(iommu->cap),
-					   pasid_max - 1, GFP_KERNEL);
-		if (ret < 0) {
+		/* Do not use PASID 0, reserved for RID to PASID */
+		svm->pasid = ioasid_alloc(NULL, PASID_MIN,
+					  pasid_max - 1, svm);
+		if (svm->pasid == INVALID_IOASID) {
 			kfree(svm);
 			kfree(sdev);
+			ret = -ENOSPC;
 			goto out;
 		}
-		svm->pasid = ret;
 		svm->notifier.ops = &intel_mmuops;
 		svm->mm = mm;
 		svm->flags = flags;
@@ -333,7 +353,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		if (mm) {
 			ret = mmu_notifier_register(&svm->notifier, mm);
 			if (ret) {
-				intel_pasid_free_id(svm->pasid);
+				ioasid_free(svm->pasid);
 				kfree(svm);
 				kfree(sdev);
 				goto out;
@@ -344,12 +364,14 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		ret = intel_pasid_setup_first_level(iommu, dev,
 				mm ? mm->pgd : init_mm.pgd,
 				svm->pasid, FLPT_DEFAULT_DID,
-				mm ? 0 : PASID_FLAG_SUPERVISOR_MODE);
+				(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
+				(cpu_feature_enabled(X86_FEATURE_LA57) ?
+				 PASID_FLAG_FL5LP : 0));
 		spin_unlock(&iommu->lock);
 		if (ret) {
 			if (mm)
 				mmu_notifier_unregister(&svm->notifier, mm);
-			intel_pasid_free_id(svm->pasid);
+			ioasid_free(svm->pasid);
 			kfree(svm);
 			kfree(sdev);
 			goto out;
@@ -365,7 +387,9 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		ret = intel_pasid_setup_first_level(iommu, dev,
 						mm ? mm->pgd : init_mm.pgd,
 						svm->pasid, FLPT_DEFAULT_DID,
-						mm ? 0 : PASID_FLAG_SUPERVISOR_MODE);
+						(mm ? 0 : PASID_FLAG_SUPERVISOR_MODE) |
+						(cpu_feature_enabled(X86_FEATURE_LA57) ?
+						PASID_FLAG_FL5LP : 0));
 		spin_unlock(&iommu->lock);
 		if (ret) {
 			kfree(sdev);
@@ -397,44 +421,45 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 	if (!iommu)
 		goto out;
 
-	svm = intel_pasid_lookup_id(pasid);
+	svm = ioasid_find(NULL, pasid, NULL);
 	if (!svm)
 		goto out;
 
-	list_for_each_entry(sdev, &svm->devs, list) {
-		if (dev == sdev->dev) {
-			ret = 0;
-			sdev->users--;
-			if (!sdev->users) {
-				list_del_rcu(&sdev->list);
-				/* Flush the PASID cache and IOTLB for this device.
-				 * Note that we do depend on the hardware *not* using
-				 * the PASID any more. Just as we depend on other
-				 * devices never using PASIDs that they have no right
-				 * to use. We have a *shared* PASID table, because it's
-				 * large and has to be physically contiguous. So it's
-				 * hard to be as defensive as we might like. */
-				intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
-				intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
-				kfree_rcu(sdev, rcu);
-
-				if (list_empty(&svm->devs)) {
-					intel_pasid_free_id(svm->pasid);
-					if (svm->mm)
-						mmu_notifier_unregister(&svm->notifier, svm->mm);
-
-					list_del(&svm->list);
-
-					/* We mandate that no page faults may be outstanding
-					 * for the PASID when intel_svm_unbind_mm() is called.
-					 * If that is not obeyed, subtle errors will happen.
-					 * Let's make them less subtle... */
-					memset(svm, 0x6b, sizeof(*svm));
-					kfree(svm);
-				}
+	if (IS_ERR(svm)) {
+		ret = PTR_ERR(svm);
+		goto out;
+	}
+
+	for_each_svm_dev(sdev, svm, dev) {
+		ret = 0;
+		sdev->users--;
+		if (!sdev->users) {
+			list_del_rcu(&sdev->list);
+			/* Flush the PASID cache and IOTLB for this device.
+			 * Note that we do depend on the hardware *not* using
+			 * the PASID any more. Just as we depend on other
+			 * devices never using PASIDs that they have no right
+			 * to use. We have a *shared* PASID table, because it's
+			 * large and has to be physically contiguous. So it's
+			 * hard to be as defensive as we might like. */
+			intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
+			intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
+			kfree_rcu(sdev, rcu);
+
+			if (list_empty(&svm->devs)) {
+				ioasid_free(svm->pasid);
+				if (svm->mm)
+					mmu_notifier_unregister(&svm->notifier, svm->mm);
+				list_del(&svm->list);
+				/* We mandate that no page faults may be outstanding
+				 * for the PASID when intel_svm_unbind_mm() is called.
+				 * If that is not obeyed, subtle errors will happen.
+				 * Let's make them less subtle... */
+				memset(svm, 0x6b, sizeof(*svm));
+				kfree(svm);
 			}
-			break;
 		}
+		break;
 	}
  out:
 	mutex_unlock(&pasid_mutex);
@@ -454,10 +479,14 @@ int intel_svm_is_pasid_valid(struct device *dev, int pasid)
 	if (!iommu)
 		goto out;
 
-	svm = intel_pasid_lookup_id(pasid);
+	svm = ioasid_find(NULL, pasid, NULL);
 	if (!svm)
 		goto out;
 
+	if (IS_ERR(svm)) {
+		ret = PTR_ERR(svm);
+		goto out;
+	}
 	/* init_mm is used in this case */
 	if (!svm->mm)
 		ret = 1;
@@ -564,13 +593,12 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 
 		if (!svm || svm->pasid != req->pasid) {
 			rcu_read_lock();
-			svm = intel_pasid_lookup_id(req->pasid);
+			svm = ioasid_find(NULL, req->pasid, NULL);
 			/* It *can't* go away, because the driver is not permitted
 			 * to unbind the mm while any page faults are outstanding.
 			 * So we only need RCU to protect the internal idr code. */
 			rcu_read_unlock();
-
-			if (!svm) {
+			if (IS_ERR_OR_NULL(svm)) {
 				pr_err("%s: Page request for invalid PASID %d: %08llx %08llx\n",
 				       iommu->name, req->pasid, ((unsigned long long *)req)[0],
 				       ((unsigned long long *)req)[1]);
@@ -654,11 +682,10 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 			if (req->priv_data_present)
 				memcpy(&resp.qw2, req->priv_data,
 				       sizeof(req->priv_data));
+			resp.qw2 = 0;
+			resp.qw3 = 0;
+			qi_submit_sync(&resp, iommu);
 		}
-		resp.qw2 = 0;
-		resp.qw3 = 0;
-		qi_submit_sync(&resp, iommu);
-
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
 
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 7c3bd2c3cdca..4272fe4e17f4 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -149,8 +149,6 @@
 #define ARM_V7S_TTBR_IRGN_ATTR(attr)					\
 	((((attr) & 0x1) << 6) | (((attr) & 0x2) >> 1))
 
-#define ARM_V7S_TCR_PD1			BIT(5)
-
 #ifdef CONFIG_ZONE_DMA32
 #define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
 #define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
@@ -798,8 +796,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	 */
 	cfg->pgsize_bitmap &= SZ_4K | SZ_64K | SZ_1M | SZ_16M;
 
-	/* TCR: T0SZ=0, disable TTBR1 */
-	cfg->arm_v7s_cfg.tcr = ARM_V7S_TCR_PD1;
+	/* TCR: T0SZ=0, EAE=0 (if applicable) */
+	cfg->arm_v7s_cfg.tcr = 0;
 
 	/*
 	 * TEX remap: the indices used map to the closest equivalent types
@@ -822,15 +820,13 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	/* Ensure the empty pgd is visible before any actual TTBR write */
 	wmb();
 
-	/* TTBRs */
-	cfg->arm_v7s_cfg.ttbr[0] = virt_to_phys(data->pgd) |
-				   ARM_V7S_TTBR_S | ARM_V7S_TTBR_NOS |
-				   (cfg->coherent_walk ?
-				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
-				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
-				   (ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
-				    ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
-	cfg->arm_v7s_cfg.ttbr[1] = 0;
+	/* TTBR */
+	cfg->arm_v7s_cfg.ttbr = virt_to_phys(data->pgd) | ARM_V7S_TTBR_S |
+				(cfg->coherent_walk ? (ARM_V7S_TTBR_NOS |
+				 ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_WBWA) |
+				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_WBWA)) :
+				(ARM_V7S_TTBR_IRGN_ATTR(ARM_V7S_RGN_NC) |
+				 ARM_V7S_TTBR_ORGN_ATTR(ARM_V7S_RGN_NC)));
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index bdf47f745268..983b08477e64 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -100,40 +100,29 @@
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
 
 /* Register bits */
-#define ARM_32_LPAE_TCR_EAE		(1 << 31)
-#define ARM_64_LPAE_S2_TCR_RES1		(1 << 31)
+#define ARM_LPAE_TCR_TG0_4K		0
+#define ARM_LPAE_TCR_TG0_64K		1
+#define ARM_LPAE_TCR_TG0_16K		2
 
-#define ARM_LPAE_TCR_EPD1		(1 << 23)
+#define ARM_LPAE_TCR_TG1_16K		1
+#define ARM_LPAE_TCR_TG1_4K		2
+#define ARM_LPAE_TCR_TG1_64K		3
 
-#define ARM_LPAE_TCR_TG0_4K		(0 << 14)
-#define ARM_LPAE_TCR_TG0_64K		(1 << 14)
-#define ARM_LPAE_TCR_TG0_16K		(2 << 14)
-
-#define ARM_LPAE_TCR_SH0_SHIFT		12
-#define ARM_LPAE_TCR_SH0_MASK		0x3
 #define ARM_LPAE_TCR_SH_NS		0
 #define ARM_LPAE_TCR_SH_OS		2
 #define ARM_LPAE_TCR_SH_IS		3
 
-#define ARM_LPAE_TCR_ORGN0_SHIFT	10
-#define ARM_LPAE_TCR_IRGN0_SHIFT	8
-#define ARM_LPAE_TCR_RGN_MASK		0x3
 #define ARM_LPAE_TCR_RGN_NC		0
 #define ARM_LPAE_TCR_RGN_WBWA		1
 #define ARM_LPAE_TCR_RGN_WT		2
 #define ARM_LPAE_TCR_RGN_WB		3
 
-#define ARM_LPAE_TCR_SL0_SHIFT		6
-#define ARM_LPAE_TCR_SL0_MASK		0x3
+#define ARM_LPAE_VTCR_SL0_MASK		0x3
 
 #define ARM_LPAE_TCR_T0SZ_SHIFT		0
-#define ARM_LPAE_TCR_SZ_MASK		0xf
-
-#define ARM_LPAE_TCR_PS_SHIFT		16
-#define ARM_LPAE_TCR_PS_MASK		0x7
 
-#define ARM_LPAE_TCR_IPS_SHIFT		32
-#define ARM_LPAE_TCR_IPS_MASK		0x7
+#define ARM_LPAE_VTCR_PS_SHIFT		16
+#define ARM_LPAE_VTCR_PS_MASK		0x7
 
 #define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
 #define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
@@ -293,17 +282,11 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
 {
 	arm_lpae_iopte pte = prot;
 
-	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
-		pte |= ARM_LPAE_PTE_NS;
-
 	if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1)
 		pte |= ARM_LPAE_PTE_TYPE_PAGE;
 	else
 		pte |= ARM_LPAE_PTE_TYPE_BLOCK;
 
-	if (data->iop.fmt != ARM_MALI_LPAE)
-		pte |= ARM_LPAE_PTE_AF;
-	pte |= ARM_LPAE_PTE_SH_IS;
 	pte |= paddr_to_iopte(paddr, data);
 
 	__arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
@@ -460,9 +443,20 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
+	if (prot & IOMMU_CACHE)
+		pte |= ARM_LPAE_PTE_SH_IS;
+	else
+		pte |= ARM_LPAE_PTE_SH_OS;
+
 	if (prot & IOMMU_NOEXEC)
 		pte |= ARM_LPAE_PTE_XN;
 
+	if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_NS)
+		pte |= ARM_LPAE_PTE_NS;
+
+	if (data->iop.fmt != ARM_MALI_LPAE)
+		pte |= ARM_LPAE_PTE_AF;
+
 	return pte;
 }
 
@@ -474,6 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	arm_lpae_iopte *ptep = data->pgd;
 	int ret, lvl = data->start_level;
 	arm_lpae_iopte prot;
+	long iaext = (long)iova >> cfg->ias;
 
 	/* If no access, then nothing to do */
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
@@ -482,7 +477,9 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return -EINVAL;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias || paddr >> data->iop.cfg.oas))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext || paddr >> cfg->oas))
 		return -ERANGE;
 
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
@@ -648,11 +645,14 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
+	long iaext = (long)iova >> cfg->ias;
 
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return 0;
 
-	if (WARN_ON(iova >> data->iop.cfg.ias))
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+		iaext = ~iaext;
+	if (WARN_ON(iaext))
 		return 0;
 
 	return __arm_lpae_unmap(data, gather, iova, size, data->start_level, ptep);
@@ -787,9 +787,12 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s1_cfg.tcr) tcr = &cfg->arm_lpae_s1_cfg.tcr;
+	bool tg1;
 
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS |
-			    IO_PGTABLE_QUIRK_NON_STRICT))
+			    IO_PGTABLE_QUIRK_NON_STRICT |
+			    IO_PGTABLE_QUIRK_ARM_TTBR1))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -798,58 +801,55 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* TCR */
 	if (cfg->coherent_walk) {
-		reg = (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_IS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		tcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
 	} else {
-		reg = (ARM_LPAE_TCR_SH_OS << ARM_LPAE_TCR_SH0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_IRGN0_SHIFT) |
-		      (ARM_LPAE_TCR_RGN_NC << ARM_LPAE_TCR_ORGN0_SHIFT);
+		tcr->sh = ARM_LPAE_TCR_SH_OS;
+		tcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		tcr->orgn = ARM_LPAE_TCR_RGN_NC;
 	}
 
+	tg1 = cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1;
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_4K : ARM_LPAE_TCR_TG0_4K;
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_16K : ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		tcr->tg = tg1 ? ARM_LPAE_TCR_TG1_64K : ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT);
+		tcr->ips = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-
-	/* Disable speculative walks through TTBR1 */
-	reg |= ARM_LPAE_TCR_EPD1;
-	cfg->arm_lpae_s1_cfg.tcr = reg;
+	tcr->tsz = 64ULL - cfg->ias;
 
 	/* MAIRs */
 	reg = (ARM_LPAE_MAIR_ATTR_NC
@@ -872,9 +872,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	/* Ensure the empty pgd is visible before any actual TTBR write */
 	wmb();
 
-	/* TTBRs */
-	cfg->arm_lpae_s1_cfg.ttbr[0] = virt_to_phys(data->pgd);
-	cfg->arm_lpae_s1_cfg.ttbr[1] = 0;
+	/* TTBR */
+	cfg->arm_lpae_s1_cfg.ttbr = virt_to_phys(data->pgd);
 	return &data->iop;
 
 out_free_data:
@@ -885,8 +884,9 @@ out_free_data:
 static struct io_pgtable *
 arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	u64 reg, sl;
+	u64 sl;
 	struct arm_lpae_io_pgtable *data;
+	typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr;
 
 	/* The NS quirk doesn't apply at stage 2 */
 	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NON_STRICT))
@@ -911,55 +911,59 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	}
 
 	/* VTCR */
-	reg = ARM_64_LPAE_S2_TCR_RES1 |
-	     (ARM_LPAE_TCR_SH_IS << ARM_LPAE_TCR_SH0_SHIFT) |
-	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_IRGN0_SHIFT) |
-	     (ARM_LPAE_TCR_RGN_WBWA << ARM_LPAE_TCR_ORGN0_SHIFT);
+	if (cfg->coherent_walk) {
+		vtcr->sh = ARM_LPAE_TCR_SH_IS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_WBWA;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_WBWA;
+	} else {
+		vtcr->sh = ARM_LPAE_TCR_SH_OS;
+		vtcr->irgn = ARM_LPAE_TCR_RGN_NC;
+		vtcr->orgn = ARM_LPAE_TCR_RGN_NC;
+	}
 
 	sl = data->start_level;
 
 	switch (ARM_LPAE_GRANULE(data)) {
 	case SZ_4K:
-		reg |= ARM_LPAE_TCR_TG0_4K;
+		vtcr->tg = ARM_LPAE_TCR_TG0_4K;
 		sl++; /* SL0 format is different for 4K granule size */
 		break;
 	case SZ_16K:
-		reg |= ARM_LPAE_TCR_TG0_16K;
+		vtcr->tg = ARM_LPAE_TCR_TG0_16K;
 		break;
 	case SZ_64K:
-		reg |= ARM_LPAE_TCR_TG0_64K;
+		vtcr->tg = ARM_LPAE_TCR_TG0_64K;
 		break;
 	}
 
 	switch (cfg->oas) {
 	case 32:
-		reg |= (ARM_LPAE_TCR_PS_32_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_32_BIT;
 		break;
 	case 36:
-		reg |= (ARM_LPAE_TCR_PS_36_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_36_BIT;
 		break;
 	case 40:
-		reg |= (ARM_LPAE_TCR_PS_40_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_40_BIT;
 		break;
 	case 42:
-		reg |= (ARM_LPAE_TCR_PS_42_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_42_BIT;
 		break;
 	case 44:
-		reg |= (ARM_LPAE_TCR_PS_44_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_44_BIT;
 		break;
 	case 48:
-		reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_48_BIT;
 		break;
 	case 52:
-		reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT);
+		vtcr->ps = ARM_LPAE_TCR_PS_52_BIT;
 		break;
 	default:
 		goto out_free_data;
 	}
 
-	reg |= (64ULL - cfg->ias) << ARM_LPAE_TCR_T0SZ_SHIFT;
-	reg |= (~sl & ARM_LPAE_TCR_SL0_MASK) << ARM_LPAE_TCR_SL0_SHIFT;
-	cfg->arm_lpae_s2_cfg.vtcr = reg;
+	vtcr->tsz = 64ULL - cfg->ias;
+	vtcr->sl = ~sl & ARM_LPAE_VTCR_SL0_MASK;
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
@@ -982,35 +986,21 @@ out_free_data:
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 32 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		cfg->arm_lpae_s1_cfg.tcr |= ARM_32_LPAE_TCR_EAE;
-		cfg->arm_lpae_s1_cfg.tcr &= 0xffffffff;
-	}
-
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
 }
 
 static struct io_pgtable *
 arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
-
 	if (cfg->ias > 40 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
-	if (iop)
-		cfg->arm_lpae_s2_cfg.vtcr &= 0xffffffff;
-
-	return iop;
+	return arm_64_lpae_alloc_pgtable_s2(cfg, cookie);
 }
 
 static struct io_pgtable *
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index ced53e5b72b5..94394c81468f 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -63,7 +63,7 @@ void free_io_pgtable_ops(struct io_pgtable_ops *ops)
 	if (!ops)
 		return;
 
-	iop = container_of(ops, struct io_pgtable, ops);
+	iop = io_pgtable_ops_to_pgtable(ops);
 	io_pgtable_tlb_flush_all(iop);
 	io_pgtable_init_table[iop->fmt]->free(iop);
 }
diff --git a/drivers/iommu/iommu-sysfs.c b/drivers/iommu/iommu-sysfs.c
index e436ff813e7e..99869217fbec 100644
--- a/drivers/iommu/iommu-sysfs.c
+++ b/drivers/iommu/iommu-sysfs.c
@@ -87,6 +87,7 @@ error:
 	put_device(iommu->dev);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iommu_device_sysfs_add);
 
 void iommu_device_sysfs_remove(struct iommu_device *iommu)
 {
@@ -94,6 +95,8 @@ void iommu_device_sysfs_remove(struct iommu_device *iommu)
 	device_unregister(iommu->dev);
 	iommu->dev = NULL;
 }
+EXPORT_SYMBOL_GPL(iommu_device_sysfs_remove);
+
 /*
  * IOMMU drivers can indicate a device is managed by a given IOMMU using
  * this interface.  A link to the device will be created in the "devices"
@@ -119,6 +122,7 @@ int iommu_device_link(struct iommu_device *iommu, struct device *link)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iommu_device_link);
 
 void iommu_device_unlink(struct iommu_device *iommu, struct device *link)
 {
@@ -128,3 +132,4 @@ void iommu_device_unlink(struct iommu_device *iommu, struct device *link)
 	sysfs_remove_link(&link->kobj, "iommu");
 	sysfs_remove_link_from_group(&iommu->dev->kobj, "devices", dev_name(link));
 }
+EXPORT_SYMBOL_GPL(iommu_device_unlink);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 3ead597e1c57..3e3528436e0b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -22,6 +22,7 @@
 #include <linux/bitops.h>
 #include <linux/property.h>
 #include <linux/fsl/mc.h>
+#include <linux/module.h>
 #include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
@@ -141,6 +142,7 @@ int iommu_device_register(struct iommu_device *iommu)
 	spin_unlock(&iommu_device_lock);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(iommu_device_register);
 
 void iommu_device_unregister(struct iommu_device *iommu)
 {
@@ -148,6 +150,7 @@ void iommu_device_unregister(struct iommu_device *iommu)
 	list_del(&iommu->list);
 	spin_unlock(&iommu_device_lock);
 }
+EXPORT_SYMBOL_GPL(iommu_device_unregister);
 
 static struct iommu_param *iommu_get_dev_param(struct device *dev)
 {
@@ -183,10 +186,21 @@ int iommu_probe_device(struct device *dev)
 	if (!iommu_get_dev_param(dev))
 		return -ENOMEM;
 
+	if (!try_module_get(ops->owner)) {
+		ret = -EINVAL;
+		goto err_free_dev_param;
+	}
+
 	ret = ops->add_device(dev);
 	if (ret)
-		iommu_free_dev_param(dev);
+		goto err_module_put;
+
+	return 0;
 
+err_module_put:
+	module_put(ops->owner);
+err_free_dev_param:
+	iommu_free_dev_param(dev);
 	return ret;
 }
 
@@ -197,7 +211,10 @@ void iommu_release_device(struct device *dev)
 	if (dev->iommu_group)
 		ops->remove_device(dev);
 
-	iommu_free_dev_param(dev);
+	if (dev->iommu_param) {
+		module_put(ops->owner);
+		iommu_free_dev_param(dev);
+	}
 }
 
 static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
@@ -887,6 +904,7 @@ struct iommu_group *iommu_group_ref_get(struct iommu_group *group)
 	kobject_get(group->devices_kobj);
 	return group;
 }
+EXPORT_SYMBOL_GPL(iommu_group_ref_get);
 
 /**
  * iommu_group_put - Decrement group reference
@@ -1260,6 +1278,7 @@ struct iommu_group *generic_device_group(struct device *dev)
 {
 	return iommu_group_alloc();
 }
+EXPORT_SYMBOL_GPL(generic_device_group);
 
 /*
  * Use standard PCI bus topology, isolation features, and DMA alias quirks
@@ -1327,6 +1346,7 @@ struct iommu_group *pci_device_group(struct device *dev)
 	/* No shared group found, allocate new */
 	return iommu_group_alloc();
 }
+EXPORT_SYMBOL_GPL(pci_device_group);
 
 /* Get the IOMMU group for device on fsl-mc bus */
 struct iommu_group *fsl_mc_device_group(struct device *dev)
@@ -1339,6 +1359,7 @@ struct iommu_group *fsl_mc_device_group(struct device *dev)
 		group = iommu_group_alloc();
 	return group;
 }
+EXPORT_SYMBOL_GPL(fsl_mc_device_group);
 
 /**
  * iommu_group_get_for_dev - Find or create the IOMMU group for a device
@@ -1407,6 +1428,7 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 
 	return group;
 }
+EXPORT_SYMBOL(iommu_group_get_for_dev);
 
 struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
 {
@@ -1537,6 +1559,11 @@ int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops)
 {
 	int err;
 
+	if (ops == NULL) {
+		bus->iommu_ops = NULL;
+		return 0;
+	}
+
 	if (bus->iommu_ops != NULL)
 		return -EBUSY;
 
@@ -2230,6 +2257,25 @@ void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 		ops->put_resv_regions(dev, list);
 }
 
+/**
+ * generic_iommu_put_resv_regions - Reserved region driver helper
+ * @dev: device for which to free reserved regions
+ * @list: reserved region list for device
+ *
+ * IOMMU drivers can use this to implement their .put_resv_regions() callback
+ * for simple reservations. Memory allocated for each reserved region will be
+ * freed. If an IOMMU driver allocates additional resources per region, it is
+ * going to have to implement a custom callback.
+ */
+void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, list, list)
+		kfree(entry);
+}
+EXPORT_SYMBOL(generic_iommu_put_resv_regions);
+
 struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 						  size_t length, int prot,
 						  enum iommu_resv_type type)
@@ -2247,6 +2293,7 @@ struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 	region->type = type;
 	return region;
 }
+EXPORT_SYMBOL_GPL(iommu_alloc_resv_region);
 
 static int
 request_default_domain_for_dev(struct device *dev, unsigned long type)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index c7a914b9bbbc..0e6a9536eca6 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -233,7 +233,7 @@ static DEFINE_MUTEX(iova_cache_mutex);
 
 struct iova *alloc_iova_mem(void)
 {
-	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC);
+	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
 }
 EXPORT_SYMBOL(alloc_iova_mem);
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index d02edd2751f3..ecb3f9464dd5 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -374,7 +374,7 @@ static void ipmmu_domain_setup_context(struct ipmmu_vmsa_domain *domain)
 	u32 tmp;
 
 	/* TTBR0 */
-	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
+	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr;
 	ipmmu_ctx_write_root(domain, IMTTLBR0, ttbr);
 	ipmmu_ctx_write_root(domain, IMTTUBR0, ttbr >> 32);
 
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index 93f14bca26ee..94a6df1bddd6 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -279,8 +279,8 @@ static void __program_context(void __iomem *base, int ctx,
 	SET_V2PCFG(base, ctx, 0x3);
 
 	SET_TTBCR(base, ctx, priv->cfg.arm_v7s_cfg.tcr);
-	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[0]);
-	SET_TTBR1(base, ctx, priv->cfg.arm_v7s_cfg.ttbr[1]);
+	SET_TTBR0(base, ctx, priv->cfg.arm_v7s_cfg.ttbr);
+	SET_TTBR1(base, ctx, 0);
 
 	/* Set prrr and nmrr */
 	SET_PRRR(base, ctx, priv->cfg.arm_v7s_cfg.prrr);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 6fc1f5ecf91e..95945f467c03 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -367,7 +367,7 @@ static int mtk_iommu_attach_device(struct iommu_domain *domain,
 	/* Update the pgtable base address register of the M4U HW */
 	if (!data->m4u_dom) {
 		data->m4u_dom = dom;
-		writel(dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       data->base + REG_MMU_PT_BASE_ADDR);
 	}
 
@@ -765,7 +765,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev)
 	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
 	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
 	if (m4u_dom)
-		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr[0] & MMU_PT_ADDR_MASK,
+		writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
 		       base + REG_MMU_PT_BASE_ADDR);
 	return 0;
 }
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 026ad2b29dcd..20738aacac89 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -8,11 +8,12 @@
 #include <linux/export.h>
 #include <linux/iommu.h>
 #include <linux/limits.h>
-#include <linux/pci.h>
+#include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>
 #include <linux/of_pci.h>
+#include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/fsl/mc.h>
 
@@ -91,16 +92,16 @@ static int of_iommu_xlate(struct device *dev,
 {
 	const struct iommu_ops *ops;
 	struct fwnode_handle *fwnode = &iommu_spec->np->fwnode;
-	int err;
+	int ret;
 
 	ops = iommu_ops_from_fwnode(fwnode);
 	if ((ops && !ops->of_xlate) ||
 	    !of_device_is_available(iommu_spec->np))
 		return NO_IOMMU;
 
-	err = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
-	if (err)
-		return err;
+	ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
+	if (ret)
+		return ret;
 	/*
 	 * The otherwise-empty fwspec handily serves to indicate the specific
 	 * IOMMU device we're waiting for, which will be useful if we ever get
@@ -109,7 +110,12 @@ static int of_iommu_xlate(struct device *dev,
 	if (!ops)
 		return driver_deferred_probe_check_state(dev);
 
-	return ops->of_xlate(dev, iommu_spec);
+	if (!try_module_get(ops->owner))
+		return -ENODEV;
+
+	ret = ops->of_xlate(dev, iommu_spec);
+	module_put(ops->owner);
+	return ret;
 }
 
 struct of_pci_iommu_alias_info {
@@ -179,6 +185,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 			.np = master_np,
 		};
 
+		pci_request_acs();
 		err = pci_for_each_dma_alias(to_pci_dev(dev),
 					     of_pci_iommu_init, &info);
 	} else if (dev_is_fsl_mc(dev)) {
@@ -196,8 +203,12 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 			if (err)
 				break;
 		}
-	}
 
+		fwspec = dev_iommu_fwspec_get(dev);
+		if (!err && fwspec)
+			of_property_read_u32(master_np, "pasid-num-bits",
+					     &fwspec->num_pasid_bits);
+	}
 
 	/*
 	 * Two success conditions can be represented by non-negative err here:
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index 52f38292df5b..39759db4f003 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -201,7 +201,7 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
 
 	fsr = iommu_readl(ctx, ARM_SMMU_CB_FSR);
 
-	if (!(fsr & FSR_FAULT))
+	if (!(fsr & ARM_SMMU_FSR_FAULT))
 		return IRQ_NONE;
 
 	fsynr = iommu_readl(ctx, ARM_SMMU_CB_FSYNR0);
@@ -215,7 +215,7 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
 	}
 
 	iommu_writel(ctx, ARM_SMMU_CB_FSR, fsr);
-	iommu_writel(ctx, ARM_SMMU_CB_RESUME, RESUME_TERMINATE);
+	iommu_writel(ctx, ARM_SMMU_CB_RESUME, ARM_SMMU_RESUME_TERMINATE);
 
 	return IRQ_HANDLED;
 }
@@ -269,18 +269,15 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* TTBRs */
 		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
-				pgtbl_cfg.arm_lpae_s1_cfg.ttbr[0] |
-				FIELD_PREP(TTBRn_ASID, ctx->asid));
-		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1,
-				pgtbl_cfg.arm_lpae_s1_cfg.ttbr[1] |
-				FIELD_PREP(TTBRn_ASID, ctx->asid));
+				pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
+				FIELD_PREP(ARM_SMMU_TTBRn_ASID, ctx->asid));
+		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);
 
 		/* TCR */
 		iommu_writel(ctx, ARM_SMMU_CB_TCR2,
-				(pgtbl_cfg.arm_lpae_s1_cfg.tcr >> 32) |
-				FIELD_PREP(TCR2_SEP, TCR2_SEP_UPSTREAM));
+				arm_smmu_lpae_tcr2(&pgtbl_cfg));
 		iommu_writel(ctx, ARM_SMMU_CB_TCR,
-				pgtbl_cfg.arm_lpae_s1_cfg.tcr);
+			     arm_smmu_lpae_tcr(&pgtbl_cfg) | ARM_SMMU_TCR_EAE);
 
 		/* MAIRs (stage-1 only) */
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
@@ -289,11 +286,13 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
 
 		/* SCTLR */
-		reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
-			SCTLR_M | SCTLR_S1_ASIDPNE | SCTLR_CFCFG;
+		reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE |
+		      ARM_SMMU_SCTLR_AFE | ARM_SMMU_SCTLR_TRE |
+		      ARM_SMMU_SCTLR_M | ARM_SMMU_SCTLR_S1_ASIDPNE |
+		      ARM_SMMU_SCTLR_CFCFG;
 
 		if (IS_ENABLED(CONFIG_BIG_ENDIAN))
-			reg |= SCTLR_E;
+			reg |= ARM_SMMU_SCTLR_E;
 
 		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg);
 
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 315c7cc4f99d..cce329d71fba 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -837,14 +837,6 @@ static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 	iommu_dma_get_resv_regions(dev, head);
 }
 
-static void viommu_put_resv_regions(struct device *dev, struct list_head *head)
-{
-	struct iommu_resv_region *entry, *next;
-
-	list_for_each_entry_safe(entry, next, head, list)
-		kfree(entry);
-}
-
 static struct iommu_ops viommu_ops;
 static struct virtio_driver virtio_iommu_drv;
 
@@ -914,7 +906,7 @@ static int viommu_add_device(struct device *dev)
 err_unlink_dev:
 	iommu_device_unlink(&viommu->iommu, dev);
 err_free_dev:
-	viommu_put_resv_regions(dev, &vdev->resv_regions);
+	generic_iommu_put_resv_regions(dev, &vdev->resv_regions);
 	kfree(vdev);
 
 	return ret;
@@ -932,7 +924,7 @@ static void viommu_remove_device(struct device *dev)
 
 	iommu_group_remove_device(dev);
 	iommu_device_unlink(&vdev->viommu->iommu, dev);
-	viommu_put_resv_regions(dev, &vdev->resv_regions);
+	generic_iommu_put_resv_regions(dev, &vdev->resv_regions);
 	kfree(vdev);
 }
 
@@ -961,7 +953,7 @@ static struct iommu_ops viommu_ops = {
 	.remove_device		= viommu_remove_device,
 	.device_group		= viommu_device_group,
 	.get_resv_regions	= viommu_get_resv_regions,
-	.put_resv_regions	= viommu_put_resv_regions,
+	.put_resv_regions	= generic_iommu_put_resv_regions,
 	.of_xlate		= viommu_of_xlate,
 };
 
diff --git a/drivers/isdn/capi/kcapi_proc.c b/drivers/isdn/capi/kcapi_proc.c
index eadbe59b3753..b5ed4ea145cb 100644
--- a/drivers/isdn/capi/kcapi_proc.c
+++ b/drivers/isdn/capi/kcapi_proc.c
@@ -199,8 +199,8 @@ static ssize_t empty_read(struct file *file, char __user *buf,
 	return 0;
 }
 
-static const struct file_operations empty_fops = {
-	.read	= empty_read,
+static const struct proc_ops empty_proc_ops = {
+	.proc_read	= empty_read,
 };
 
 // ---------------------------------------------------------------------------
@@ -214,7 +214,7 @@ kcapi_proc_init(void)
 	proc_create_seq("capi/contrstats",   0, NULL, &seq_contrstats_ops);
 	proc_create_seq("capi/applications", 0, NULL, &seq_applications_ops);
 	proc_create_seq("capi/applstats",    0, NULL, &seq_applstats_ops);
-	proc_create("capi/driver",           0, NULL, &empty_fops);
+	proc_create("capi/driver",           0, NULL, &empty_proc_ops);
 }
 
 void
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 4b68520ac251..d82f1dea3711 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -836,6 +836,16 @@ config LEDS_LM36274
 	  Say Y to enable the LM36274 LED driver for TI LMU devices.
 	  This supports the LED device LM36274.
 
+config LEDS_TPS6105X
+	tristate "LED support for TI TPS6105X"
+	depends on LEDS_CLASS
+	depends on TPS6105X
+	default y if TPS6105X
+	help
+	  This driver supports TPS61050/TPS61052 LED chips.
+	  It is a single boost converter primarily for white LEDs and
+	  audio amplifiers.
+
 comment "LED Triggers"
 source "drivers/leds/trigger/Kconfig"
 
diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile
index 2da39e896ce8..d7e1107753fb 100644
--- a/drivers/leds/Makefile
+++ b/drivers/leds/Makefile
@@ -85,6 +85,7 @@ obj-$(CONFIG_LEDS_LM3601X)		+= leds-lm3601x.o
 obj-$(CONFIG_LEDS_TI_LMU_COMMON)	+= leds-ti-lmu-common.o
 obj-$(CONFIG_LEDS_LM3697)		+= leds-lm3697.o
 obj-$(CONFIG_LEDS_LM36274)		+= leds-lm36274.o
+obj-$(CONFIG_LEDS_TPS6105X)		+= leds-tps6105x.o
 
 # LED SPI Drivers
 obj-$(CONFIG_LEDS_CR0014114)		+= leds-cr0014114.o
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 438774315e6c..1fc40e8af75e 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -19,6 +19,7 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <uapi/linux/uleds.h>
+#include <linux/of.h>
 #include "leds.h"
 
 static struct class *leds_class;
@@ -214,6 +215,98 @@ static int led_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(leds_class_dev_pm_ops, led_suspend, led_resume);
 
+/**
+ * of_led_get() - request a LED device via the LED framework
+ * @np: device node to get the LED device from
+ * @index: the index of the LED
+ *
+ * Returns the LED device parsed from the phandle specified in the "leds"
+ * property of a device tree node or a negative error-code on failure.
+ */
+struct led_classdev *of_led_get(struct device_node *np, int index)
+{
+	struct device *led_dev;
+	struct led_classdev *led_cdev;
+	struct device_node *led_node;
+
+	led_node = of_parse_phandle(np, "leds", index);
+	if (!led_node)
+		return ERR_PTR(-ENOENT);
+
+	led_dev = class_find_device_by_of_node(leds_class, led_node);
+	of_node_put(led_node);
+
+	if (!led_dev)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	led_cdev = dev_get_drvdata(led_dev);
+
+	if (!try_module_get(led_cdev->dev->parent->driver->owner))
+		return ERR_PTR(-ENODEV);
+
+	return led_cdev;
+}
+EXPORT_SYMBOL_GPL(of_led_get);
+
+/**
+ * led_put() - release a LED device
+ * @led_cdev: LED device
+ */
+void led_put(struct led_classdev *led_cdev)
+{
+	module_put(led_cdev->dev->parent->driver->owner);
+}
+EXPORT_SYMBOL_GPL(led_put);
+
+static void devm_led_release(struct device *dev, void *res)
+{
+	struct led_classdev **p = res;
+
+	led_put(*p);
+}
+
+/**
+ * devm_of_led_get - Resource-managed request of a LED device
+ * @dev:	LED consumer
+ * @index:	index of the LED to obtain in the consumer
+ *
+ * The device node of the device is parse to find the request LED device.
+ * The LED device returned from this function is automatically released
+ * on driver detach.
+ *
+ * @return a pointer to a LED device or ERR_PTR(errno) on failure.
+ */
+struct led_classdev *__must_check devm_of_led_get(struct device *dev,
+						  int index)
+{
+	struct led_classdev *led;
+	struct led_classdev **dr;
+
+	if (!dev)
+		return ERR_PTR(-EINVAL);
+
+	/* Not using device tree? */
+	if (!IS_ENABLED(CONFIG_OF) || !dev->of_node)
+		return ERR_PTR(-ENOTSUPP);
+
+	led = of_led_get(dev->of_node, index);
+	if (IS_ERR(led))
+		return led;
+
+	dr = devres_alloc(devm_led_release, sizeof(struct led_classdev *),
+			  GFP_KERNEL);
+	if (!dr) {
+		led_put(led);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	*dr = led;
+	devres_add(dev, dr);
+
+	return led;
+}
+EXPORT_SYMBOL_GPL(devm_of_led_get);
+
 static int led_classdev_next_name(const char *init_name, char *name,
 				  size_t len)
 {
@@ -276,8 +369,10 @@ int led_classdev_register_ext(struct device *parent,
 		mutex_unlock(&led_cdev->led_access);
 		return PTR_ERR(led_cdev->dev);
 	}
-	if (init_data && init_data->fwnode)
+	if (init_data && init_data->fwnode) {
 		led_cdev->dev->fwnode = init_data->fwnode;
+		led_cdev->dev->of_node = to_of_node(init_data->fwnode);
+	}
 
 	if (ret)
 		dev_warn(parent, "Led %s renamed to %s due to name collision",
diff --git a/drivers/leds/leds-bd2802.c b/drivers/leds/leds-bd2802.c
index e7ec6bff2b5f..bd61a823d0ca 100644
--- a/drivers/leds/leds-bd2802.c
+++ b/drivers/leds/leds-bd2802.c
@@ -10,7 +10,7 @@
 
 #include <linux/module.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/delay.h>
 #include <linux/leds.h>
 #include <linux/leds-bd2802.h>
@@ -67,6 +67,7 @@ struct led_state {
 struct bd2802_led {
 	struct bd2802_led_platform_data	*pdata;
 	struct i2c_client		*client;
+	struct gpio_desc		*reset;
 	struct rw_semaphore		rwsem;
 
 	struct led_state		led[2];
@@ -200,7 +201,7 @@ static void bd2802_update_state(struct bd2802_led *led, enum led_ids id,
 		return;
 
 	if (bd2802_is_all_off(led) && !led->adf_on) {
-		gpio_set_value(led->pdata->reset_gpio, 0);
+		gpiod_set_value(led->reset, 1);
 		return;
 	}
 
@@ -226,7 +227,7 @@ static void bd2802_configure(struct bd2802_led *led)
 
 static void bd2802_reset_cancel(struct bd2802_led *led)
 {
-	gpio_set_value(led->pdata->reset_gpio, 1);
+	gpiod_set_value(led->reset, 0);
 	udelay(100);
 	bd2802_configure(led);
 }
@@ -420,7 +421,7 @@ static void bd2802_disable_adv_conf(struct bd2802_led *led)
 						bd2802_addr_attributes[i]);
 
 	if (bd2802_is_all_off(led))
-		gpio_set_value(led->pdata->reset_gpio, 0);
+		gpiod_set_value(led->reset, 1);
 
 	led->adf_on = 0;
 }
@@ -670,8 +671,16 @@ static int bd2802_probe(struct i2c_client *client,
 	pdata = led->pdata = dev_get_platdata(&client->dev);
 	i2c_set_clientdata(client, led);
 
-	/* Configure RESET GPIO (L: RESET, H: RESET cancel) */
-	gpio_request_one(pdata->reset_gpio, GPIOF_OUT_INIT_HIGH, "RGB_RESETB");
+	/*
+	 * Configure RESET GPIO (L: RESET, H: RESET cancel)
+	 *
+	 * We request the reset GPIO as OUT_LOW which means de-asserted,
+	 * board files specifying this GPIO line in a machine descriptor
+	 * table should take care to specify GPIO_ACTIVE_LOW for this line.
+	 */
+	led->reset = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(led->reset))
+		return PTR_ERR(led->reset);
 
 	/* Tacss = min 0.1ms */
 	udelay(100);
@@ -685,7 +694,7 @@ static int bd2802_probe(struct i2c_client *client,
 		dev_info(&client->dev, "return 0x%02x\n", ret);
 
 	/* To save the power, reset BD2802 after detecting */
-	gpio_set_value(led->pdata->reset_gpio, 0);
+	gpiod_set_value(led->reset, 1);
 
 	/* Default attributes */
 	led->wave_pattern = BD2802_PATTERN_HALF;
@@ -720,7 +729,7 @@ static int bd2802_remove(struct i2c_client *client)
 	struct bd2802_led *led = i2c_get_clientdata(client);
 	int i;
 
-	gpio_set_value(led->pdata->reset_gpio, 0);
+	gpiod_set_value(led->reset, 1);
 	bd2802_unregister_led_classdev(led);
 	if (led->adf_on)
 		bd2802_disable_adv_conf(led);
@@ -750,7 +759,7 @@ static int bd2802_suspend(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct bd2802_led *led = i2c_get_clientdata(client);
 
-	gpio_set_value(led->pdata->reset_gpio, 0);
+	gpiod_set_value(led->reset, 1);
 
 	return 0;
 }
diff --git a/drivers/leds/leds-lm3532.c b/drivers/leds/leds-lm3532.c
index 491268bb34a7..188a57da981a 100644
--- a/drivers/leds/leds-lm3532.c
+++ b/drivers/leds/leds-lm3532.c
@@ -578,6 +578,12 @@ static int lm3532_parse_node(struct lm3532_data *priv)
 		priv->runtime_ramp_down = lm3532_get_ramp_index(ramp_time);
 
 	device_for_each_child_node(priv->dev, child) {
+		struct led_init_data idata = {
+			.fwnode = child,
+			.default_label = ":",
+			.devicename = priv->client->name,
+		};
+
 		led = &priv->leds[i];
 
 		ret = fwnode_property_read_u32(child, "reg", &control_bank);
@@ -652,7 +658,7 @@ static int lm3532_parse_node(struct lm3532_data *priv)
 		led->led_dev.name = led->label;
 		led->led_dev.brightness_set_blocking = lm3532_brightness_set;
 
-		ret = devm_led_classdev_register(priv->dev, &led->led_dev);
+		ret = devm_led_classdev_register_ext(priv->dev, &led->led_dev, &idata);
 		if (ret) {
 			dev_err(&priv->client->dev, "led register err: %d\n",
 				ret);
diff --git a/drivers/leds/leds-lm3642.c b/drivers/leds/leds-lm3642.c
index 480575442ed8..4232906fcb75 100644
--- a/drivers/leds/leds-lm3642.c
+++ b/drivers/leds/leds-lm3642.c
@@ -106,7 +106,7 @@ static int lm3642_control(struct lm3642_chip_data *chip,
 	ret = regmap_read(chip->regmap, REG_FLAG, &chip->last_flag);
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to read REG_FLAG Register\n");
-		goto out;
+		return ret;
 	}
 
 	if (chip->last_flag)
@@ -146,11 +146,11 @@ static int lm3642_control(struct lm3642_chip_data *chip,
 		break;
 
 	default:
-		return ret;
+		return -EINVAL;
 	}
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to write REG_I_CTRL Register\n");
-		goto out;
+		return ret;
 	}
 
 	if (chip->tx_pin)
@@ -159,13 +159,12 @@ static int lm3642_control(struct lm3642_chip_data *chip,
 	ret = regmap_update_bits(chip->regmap, REG_ENABLE,
 				 MODE_BITS_MASK << MODE_BITS_SHIFT,
 				 opmode << MODE_BITS_SHIFT);
-out:
 	return ret;
 }
 
 /* torch */
 
-/* torch pin config for lm3642*/
+/* torch pin config for lm3642 */
 static ssize_t lm3642_torch_pin_store(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf, size_t size)
@@ -178,7 +177,7 @@ static ssize_t lm3642_torch_pin_store(struct device *dev,
 
 	ret = kstrtouint(buf, 10, &state);
 	if (ret)
-		goto out_strtoint;
+		return ret;
 	if (state != 0)
 		state = 0x01 << TORCH_PIN_EN_SHIFT;
 
@@ -186,16 +185,12 @@ static ssize_t lm3642_torch_pin_store(struct device *dev,
 	ret = regmap_update_bits(chip->regmap, REG_ENABLE,
 				 TORCH_PIN_EN_MASK << TORCH_PIN_EN_SHIFT,
 				 state);
-	if (ret < 0)
-		goto out;
+	if (ret < 0) {
+		dev_err(chip->dev, "%s:i2c access fail to register\n", __func__);
+		return ret;
+	}
 
 	return size;
-out:
-	dev_err(chip->dev, "%s:i2c access fail to register\n", __func__);
-	return ret;
-out_strtoint:
-	dev_err(chip->dev, "%s: fail to change str to int\n", __func__);
-	return ret;
 }
 
 static DEVICE_ATTR(torch_pin, S_IWUSR, NULL, lm3642_torch_pin_store);
@@ -229,7 +224,7 @@ static ssize_t lm3642_strobe_pin_store(struct device *dev,
 
 	ret = kstrtouint(buf, 10, &state);
 	if (ret)
-		goto out_strtoint;
+		return ret;
 	if (state != 0)
 		state = 0x01 << STROBE_PIN_EN_SHIFT;
 
@@ -237,16 +232,12 @@ static ssize_t lm3642_strobe_pin_store(struct device *dev,
 	ret = regmap_update_bits(chip->regmap, REG_ENABLE,
 				 STROBE_PIN_EN_MASK << STROBE_PIN_EN_SHIFT,
 				 state);
-	if (ret < 0)
-		goto out;
+	if (ret < 0) {
+		dev_err(chip->dev, "%s:i2c access fail to register\n", __func__);
+		return ret;
+	}
 
 	return size;
-out:
-	dev_err(chip->dev, "%s:i2c access fail to register\n", __func__);
-	return ret;
-out_strtoint:
-	dev_err(chip->dev, "%s: fail to change str to int\n", __func__);
-	return ret;
 }
 
 static DEVICE_ATTR(strobe_pin, S_IWUSR, NULL, lm3642_strobe_pin_store);
diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c
index 8b408102e138..28a51aeb28de 100644
--- a/drivers/leds/leds-lm3692x.c
+++ b/drivers/leds/leds-lm3692x.c
@@ -6,6 +6,7 @@
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/leds.h>
+#include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
@@ -114,6 +115,9 @@ struct lm3692x_led {
 	struct regulator *regulator;
 	int led_enable;
 	int model_id;
+
+	u8 boost_ctrl, brightness_ctrl;
+	bool enabled;
 };
 
 static const struct reg_default lm3692x_reg_defs[] = {
@@ -162,44 +166,14 @@ static int lm3692x_fault_check(struct lm3692x_led *led)
 	return read_buf;
 }
 
-static int lm3692x_brightness_set(struct led_classdev *led_cdev,
-				enum led_brightness brt_val)
-{
-	struct lm3692x_led *led =
-			container_of(led_cdev, struct lm3692x_led, led_dev);
-	int ret;
-	int led_brightness_lsb = (brt_val >> 5);
-
-	mutex_lock(&led->lock);
-
-	ret = lm3692x_fault_check(led);
-	if (ret) {
-		dev_err(&led->client->dev, "Cannot read/clear faults: %d\n",
-			ret);
-		goto out;
-	}
-
-	ret = regmap_write(led->regmap, LM3692X_BRT_MSB, brt_val);
-	if (ret) {
-		dev_err(&led->client->dev, "Cannot write MSB: %d\n", ret);
-		goto out;
-	}
-
-	ret = regmap_write(led->regmap, LM3692X_BRT_LSB, led_brightness_lsb);
-	if (ret) {
-		dev_err(&led->client->dev, "Cannot write LSB: %d\n", ret);
-		goto out;
-	}
-out:
-	mutex_unlock(&led->lock);
-	return ret;
-}
-
-static int lm3692x_init(struct lm3692x_led *led)
+static int lm3692x_leds_enable(struct lm3692x_led *led)
 {
 	int enable_state;
 	int ret, reg_ret;
 
+	if (led->enabled)
+		return 0;
+
 	if (led->regulator) {
 		ret = regulator_enable(led->regulator);
 		if (ret) {
@@ -249,10 +223,7 @@ static int lm3692x_init(struct lm3692x_led *led)
 	if (ret)
 		goto out;
 
-	ret = regmap_write(led->regmap, LM3692X_BOOST_CTRL,
-			LM3692X_BOOST_SW_1MHZ |
-			LM3692X_BOOST_SW_NO_SHIFT |
-			LM3692X_OCP_PROT_1_5A);
+	ret = regmap_write(led->regmap, LM3692X_BOOST_CTRL, led->boost_ctrl);
 	if (ret)
 		goto out;
 
@@ -305,6 +276,7 @@ static int lm3692x_init(struct lm3692x_led *led)
 	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_ENABLE_MASK,
 				 enable_state | LM3692X_DEVICE_EN);
 
+	led->enabled = true;
 	return ret;
 out:
 	dev_err(&led->client->dev, "Fail writing initialization values\n");
@@ -322,10 +294,92 @@ out:
 	return ret;
 }
 
+static int lm3692x_leds_disable(struct lm3692x_led *led)
+{
+	int ret;
+
+	if (!led->enabled)
+		return 0;
+
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN, 0);
+	if (ret) {
+		dev_err(&led->client->dev, "Failed to disable regulator: %d\n",
+			ret);
+		return ret;
+	}
+
+	if (led->enable_gpio)
+		gpiod_direction_output(led->enable_gpio, 0);
+
+	if (led->regulator) {
+		ret = regulator_disable(led->regulator);
+		if (ret)
+			dev_err(&led->client->dev,
+				"Failed to disable regulator: %d\n", ret);
+	}
+
+	led->enabled = false;
+	return ret;
+}
+
+static int lm3692x_brightness_set(struct led_classdev *led_cdev,
+				enum led_brightness brt_val)
+{
+	struct lm3692x_led *led =
+			container_of(led_cdev, struct lm3692x_led, led_dev);
+	int ret;
+	int led_brightness_lsb = (brt_val >> 5);
+
+	mutex_lock(&led->lock);
+
+	if (brt_val == 0) {
+		ret = lm3692x_leds_disable(led);
+		goto out;
+	} else {
+		lm3692x_leds_enable(led);
+	}
+
+	ret = lm3692x_fault_check(led);
+	if (ret) {
+		dev_err(&led->client->dev, "Cannot read/clear faults: %d\n",
+			ret);
+		goto out;
+	}
+
+	ret = regmap_write(led->regmap, LM3692X_BRT_MSB, brt_val);
+	if (ret) {
+		dev_err(&led->client->dev, "Cannot write MSB: %d\n", ret);
+		goto out;
+	}
+
+	ret = regmap_write(led->regmap, LM3692X_BRT_LSB, led_brightness_lsb);
+	if (ret) {
+		dev_err(&led->client->dev, "Cannot write LSB: %d\n", ret);
+		goto out;
+	}
+out:
+	mutex_unlock(&led->lock);
+	return ret;
+}
+
+static enum led_brightness lm3692x_max_brightness(struct lm3692x_led *led,
+						  u32 max_cur)
+{
+	u32 max_code;
+
+	/* see p.12 of LM36922 data sheet for brightness formula */
+	max_code = ((max_cur * 1000) - 37806) / 12195;
+	if (max_code > 0x7FF)
+		max_code = 0x7FF;
+
+	return max_code >> 3;
+}
+
 static int lm3692x_probe_dt(struct lm3692x_led *led)
 {
 	struct fwnode_handle *child = NULL;
 	struct led_init_data init_data = {};
+	u32 ovp, max_cur;
 	int ret;
 
 	led->enable_gpio = devm_gpiod_get_optional(&led->client->dev,
@@ -350,6 +404,32 @@ static int lm3692x_probe_dt(struct lm3692x_led *led)
 		led->regulator = NULL;
 	}
 
+	led->boost_ctrl = LM3692X_BOOST_SW_1MHZ |
+		LM3692X_BOOST_SW_NO_SHIFT |
+		LM3692X_OCP_PROT_1_5A;
+	ret = device_property_read_u32(&led->client->dev,
+				       "ti,ovp-microvolt", &ovp);
+	if (ret) {
+		led->boost_ctrl |= LM3692X_OVP_29V;
+	} else {
+		switch (ovp) {
+		case 17000000:
+			break;
+		case 21000000:
+			led->boost_ctrl |= LM3692X_OVP_21V;
+			break;
+		case 25000000:
+			led->boost_ctrl |= LM3692X_OVP_25V;
+			break;
+		case 29000000:
+			led->boost_ctrl |= LM3692X_OVP_29V;
+			break;
+		default:
+			dev_err(&led->client->dev, "Invalid OVP %d\n", ovp);
+			return -EINVAL;
+		}
+	}
+
 	child = device_get_next_child_node(&led->client->dev, child);
 	if (!child) {
 		dev_err(&led->client->dev, "No LED Child node\n");
@@ -365,6 +445,10 @@ static int lm3692x_probe_dt(struct lm3692x_led *led)
 		return ret;
 	}
 
+	ret = fwnode_property_read_u32(child, "led-max-microamp", &max_cur);
+	led->led_dev.max_brightness = ret ? LED_FULL :
+		lm3692x_max_brightness(led, max_cur);
+
 	init_data.fwnode = child;
 	init_data.devicename = led->client->name;
 	init_data.default_label = ":";
@@ -407,7 +491,7 @@ static int lm3692x_probe(struct i2c_client *client,
 	if (ret)
 		return ret;
 
-	ret = lm3692x_init(led);
+	ret = lm3692x_leds_enable(led);
 	if (ret)
 		return ret;
 
@@ -419,23 +503,9 @@ static int lm3692x_remove(struct i2c_client *client)
 	struct lm3692x_led *led = i2c_get_clientdata(client);
 	int ret;
 
-	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN, 0);
-	if (ret) {
-		dev_err(&led->client->dev, "Failed to disable regulator: %d\n",
-			ret);
+	ret = lm3692x_leds_disable(led);
+	if (ret)
 		return ret;
-	}
-
-	if (led->enable_gpio)
-		gpiod_direction_output(led->enable_gpio, 0);
-
-	if (led->regulator) {
-		ret = regulator_disable(led->regulator);
-		if (ret)
-			dev_err(&led->client->dev,
-				"Failed to disable regulator: %d\n", ret);
-	}
-
 	mutex_destroy(&led->lock);
 
 	return 0;
diff --git a/drivers/leds/leds-pca963x.c b/drivers/leds/leds-pca963x.c
index 4afc317901a8..66cdc003b8f4 100644
--- a/drivers/leds/leds-pca963x.c
+++ b/drivers/leds/leds-pca963x.c
@@ -40,6 +40,8 @@
 #define PCA963X_LED_PWM		0x2	/* Controlled through PWM */
 #define PCA963X_LED_GRP_PWM	0x3	/* Controlled through PWM/GRPPWM */
 
+#define PCA963X_MODE2_OUTDRV	0x04	/* Open-drain or totem pole */
+#define PCA963X_MODE2_INVRT	0x10	/* Normal or inverted direction */
 #define PCA963X_MODE2_DMBLNK	0x20	/* Enable blinking */
 
 #define PCA963X_MODE1		0x00
@@ -438,12 +440,12 @@ static int pca963x_probe(struct i2c_client *client,
 						    PCA963X_MODE2);
 		/* Configure output: open-drain or totem pole (push-pull) */
 		if (pdata->outdrv == PCA963X_OPEN_DRAIN)
-			mode2 |= 0x01;
+			mode2 &= ~PCA963X_MODE2_OUTDRV;
 		else
-			mode2 |= 0x05;
+			mode2 |= PCA963X_MODE2_OUTDRV;
 		/* Configure direction: normal or inverted */
 		if (pdata->dir == PCA963X_INVERTED)
-			mode2 |= 0x10;
+			mode2 |= PCA963X_MODE2_INVRT;
 		i2c_smbus_write_byte_data(pca963x->chip->client, PCA963X_MODE2,
 					  mode2);
 	}
diff --git a/drivers/leds/leds-tps6105x.c b/drivers/leds/leds-tps6105x.c
new file mode 100644
index 000000000000..09fd88a6c8f0
--- /dev/null
+++ b/drivers/leds/leds-tps6105x.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2019 Sven Van Asbroeck
+ */
+
+#include <linux/leds.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/tps6105x.h>
+#include <linux/regmap.h>
+
+struct tps6105x_priv {
+	struct regmap *regmap;
+	struct led_classdev cdev;
+	struct fwnode_handle *fwnode;
+};
+
+static void tps6105x_handle_put(void *data)
+{
+	struct tps6105x_priv *priv = data;
+
+	fwnode_handle_put(priv->fwnode);
+}
+
+static int tps6105x_brightness_set(struct led_classdev *cdev,
+				  enum led_brightness brightness)
+{
+	struct tps6105x_priv *priv = container_of(cdev, struct tps6105x_priv,
+							cdev);
+
+	return regmap_update_bits(priv->regmap, TPS6105X_REG_0,
+				  TPS6105X_REG0_TORCHC_MASK,
+				  brightness << TPS6105X_REG0_TORCHC_SHIFT);
+}
+
+static int tps6105x_led_probe(struct platform_device *pdev)
+{
+	struct tps6105x *tps6105x = dev_get_platdata(&pdev->dev);
+	struct tps6105x_platform_data *pdata = tps6105x->pdata;
+	struct led_init_data init_data = { };
+	struct tps6105x_priv *priv;
+	int ret;
+
+	/* This instance is not set for torch mode so bail out */
+	if (pdata->mode != TPS6105X_MODE_TORCH) {
+		dev_info(&pdev->dev,
+			"chip not in torch mode, exit probe");
+		return -EINVAL;
+	}
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	/* fwnode/devicetree is optional. NULL is allowed for priv->fwnode */
+	priv->fwnode = device_get_next_child_node(pdev->dev.parent, NULL);
+	ret = devm_add_action_or_reset(&pdev->dev, tps6105x_handle_put, priv);
+	if (ret)
+		return ret;
+	priv->regmap = tps6105x->regmap;
+	priv->cdev.brightness_set_blocking = tps6105x_brightness_set;
+	priv->cdev.max_brightness = 7;
+	init_data.devicename = "tps6105x";
+	init_data.default_label = ":torch";
+	init_data.fwnode = priv->fwnode;
+
+	ret = regmap_update_bits(tps6105x->regmap, TPS6105X_REG_0,
+				 TPS6105X_REG0_MODE_MASK |
+					TPS6105X_REG0_TORCHC_MASK,
+				 TPS6105X_REG0_MODE_TORCH <<
+					TPS6105X_REG0_MODE_SHIFT);
+	if (ret)
+		return ret;
+
+	return devm_led_classdev_register_ext(&pdev->dev, &priv->cdev,
+					      &init_data);
+}
+
+static struct platform_driver led_driver = {
+	.probe = tps6105x_led_probe,
+	.driver = {
+		.name = "tps6105x-leds",
+	},
+};
+
+module_platform_driver(led_driver);
+
+MODULE_DESCRIPTION("TPS6105x LED driver");
+MODULE_AUTHOR("Sven Van Asbroeck <TheSven73@gmail.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig
index 574e122ae105..cbd46c1c5bf7 100644
--- a/drivers/macintosh/Kconfig
+++ b/drivers/macintosh/Kconfig
@@ -178,7 +178,7 @@ config THERM_ADT746X
 	depends on I2C && I2C_POWERMAC && PPC_PMAC && !PPC_PMAC64
 	help
 	  This driver provides some thermostat and fan control for the
-          iBook G4, and the ATI based aluminium PowerBooks, allowing slightly
+	  iBook G4, and the ATI based aluminium PowerBooks, allowing slightly
 	  better fan behaviour by default, and some manual control.
 
 config WINDFARM
@@ -214,7 +214,7 @@ config WINDFARM_PM91
 	select I2C_POWERMAC
 	help
 	  This driver provides thermal control for the PowerMac9,1
-          which is the recent (SMU based) single CPU desktop G5
+	  which is the recent (SMU based) single CPU desktop G5
 
 config WINDFARM_PM112
 	tristate "Support for thermal management on PowerMac11,2"
@@ -242,7 +242,7 @@ config PMAC_RACKMETER
 	depends on PPC_PMAC
 	help
 	  This driver provides some support to control the front panel
-          blue LEDs "vu-meter" of the XServer macs.
+	  blue LEDs "vu-meter" of the XServer macs.
 
 config SENSORS_AMS
 	tristate "Apple Motion Sensor driver"
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 21d532a78fa4..d38fb78a3b23 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -212,7 +212,7 @@ static int pmu_info_proc_show(struct seq_file *m, void *v);
 static int pmu_irqstats_proc_show(struct seq_file *m, void *v);
 static int pmu_battery_proc_show(struct seq_file *m, void *v);
 static void pmu_pass_intr(unsigned char *data, int len);
-static const struct file_operations pmu_options_proc_fops;
+static const struct proc_ops pmu_options_proc_ops;
 
 #ifdef CONFIG_ADB
 const struct adb_driver via_pmu_driver = {
@@ -573,7 +573,7 @@ static int __init via_pmu_dev_init(void)
 		proc_pmu_irqstats = proc_create_single("interrupts", 0,
 				proc_pmu_root, pmu_irqstats_proc_show);
 		proc_pmu_options = proc_create("options", 0600, proc_pmu_root,
-						&pmu_options_proc_fops);
+						&pmu_options_proc_ops);
 	}
 	return 0;
 }
@@ -974,13 +974,12 @@ static ssize_t pmu_options_proc_write(struct file *file,
 	return fcount;
 }
 
-static const struct file_operations pmu_options_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pmu_options_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= pmu_options_proc_write,
+static const struct proc_ops pmu_options_proc_ops = {
+	.proc_open	= pmu_options_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= pmu_options_proc_write,
 };
 
 #ifdef CONFIG_ADB
diff --git a/drivers/md/dm-bio-prison-v2.c b/drivers/md/dm-bio-prison-v2.c
index 8ee019eda32d..9dec3b61cf70 100644
--- a/drivers/md/dm-bio-prison-v2.c
+++ b/drivers/md/dm-bio-prison-v2.c
@@ -324,7 +324,7 @@ static bool __unlock(struct dm_bio_prison_v2 *prison,
 	bio_list_init(&cell->bios);
 
 	if (cell->shared_count) {
-		cell->exclusive_lock = 0;
+		cell->exclusive_lock = false;
 		return false;
 	}
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index eb9782fc93fe..c6a529873d0f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1,8 +1,8 @@
 /*
  * Copyright (C) 2003 Jana Saout <jana@saout.de>
  * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
- * Copyright (C) 2006-2017 Red Hat, Inc. All rights reserved.
- * Copyright (C) 2013-2017 Milan Broz <gmazyland@gmail.com>
+ * Copyright (C) 2006-2020 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2013-2020 Milan Broz <gmazyland@gmail.com>
  *
  * This file is released under the GPL.
  */
@@ -115,6 +115,11 @@ struct iv_tcw_private {
 	u8 *whitening;
 };
 
+#define ELEPHANT_MAX_KEY_SIZE 32
+struct iv_elephant_private {
+	struct crypto_skcipher *tfm;
+};
+
 /*
  * Crypt: maps a linear range of a block device
  * and encrypts / decrypts at the same time.
@@ -125,6 +130,7 @@ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
 enum cipher_flags {
 	CRYPT_MODE_INTEGRITY_AEAD,	/* Use authenticated mode for cihper */
 	CRYPT_IV_LARGE_SECTORS,		/* Calculate IV from sector_size, not 512B sectors */
+	CRYPT_ENCRYPT_PREPROCESS,	/* Must preprocess data for encryption (elephant) */
 };
 
 /*
@@ -152,6 +158,7 @@ struct crypt_config {
 		struct iv_benbi_private benbi;
 		struct iv_lmk_private lmk;
 		struct iv_tcw_private tcw;
+		struct iv_elephant_private elephant;
 	} iv_gen_private;
 	u64 iv_offset;
 	unsigned int iv_size;
@@ -285,6 +292,11 @@ static struct crypto_aead *any_tfm_aead(struct crypt_config *cc)
  * eboiv: Encrypted byte-offset IV (used in Bitlocker in CBC mode)
  *        The IV is encrypted little-endian byte-offset (with the same key
  *        and cipher as the volume).
+ *
+ * elephant: The extended version of eboiv with additional Elephant diffuser
+ *           used with Bitlocker CBC mode.
+ *           This mode was used in older Windows systems
+ *           http://download.microsoft.com/download/0/2/3/0238acaf-d3bf-4a6d-b3d6-0a0be4bbb36e/bitlockercipher200608.pdf
  */
 
 static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv,
@@ -331,8 +343,14 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
 static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
-	unsigned bs = crypto_skcipher_blocksize(any_tfm(cc));
-	int log = ilog2(bs);
+	unsigned bs;
+	int log;
+
+	if (test_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags))
+		bs = crypto_aead_blocksize(any_tfm_aead(cc));
+	else
+		bs = crypto_skcipher_blocksize(any_tfm(cc));
+	log = ilog2(bs);
 
 	/* we need to calculate how far we must shift the sector count
 	 * to get the cipher block count, we use this shift in _gen */
@@ -717,7 +735,7 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv,
 	struct crypto_wait wait;
 	int err;
 
-	req = skcipher_request_alloc(any_tfm(cc), GFP_KERNEL | GFP_NOFS);
+	req = skcipher_request_alloc(any_tfm(cc), GFP_NOIO);
 	if (!req)
 		return -ENOMEM;
 
@@ -734,6 +752,290 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv,
 	return err;
 }
 
+static void crypt_iv_elephant_dtr(struct crypt_config *cc)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+
+	crypto_free_skcipher(elephant->tfm);
+	elephant->tfm = NULL;
+}
+
+static int crypt_iv_elephant_ctr(struct crypt_config *cc, struct dm_target *ti,
+			    const char *opts)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	int r;
+
+	elephant->tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+	if (IS_ERR(elephant->tfm)) {
+		r = PTR_ERR(elephant->tfm);
+		elephant->tfm = NULL;
+		return r;
+	}
+
+	r = crypt_iv_eboiv_ctr(cc, ti, NULL);
+	if (r)
+		crypt_iv_elephant_dtr(cc);
+	return r;
+}
+
+static void diffuser_disk_to_cpu(u32 *d, size_t n)
+{
+#ifndef __LITTLE_ENDIAN
+	int i;
+
+	for (i = 0; i < n; i++)
+		d[i] = le32_to_cpu((__le32)d[i]);
+#endif
+}
+
+static void diffuser_cpu_to_disk(__le32 *d, size_t n)
+{
+#ifndef __LITTLE_ENDIAN
+	int i;
+
+	for (i = 0; i < n; i++)
+		d[i] = cpu_to_le32((u32)d[i]);
+#endif
+}
+
+static void diffuser_a_decrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 5; i++) {
+		i1 = 0;
+		i2 = n - 2;
+		i3 = n - 5;
+
+		while (i1 < (n - 1)) {
+			d[i1] += d[i2] ^ (d[i3] << 9 | d[i3] >> 23);
+			i1++; i2++; i3++;
+
+			if (i3 >= n)
+				i3 -= n;
+
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+
+			if (i2 >= n)
+				i2 -= n;
+
+			d[i1] += d[i2] ^ (d[i3] << 13 | d[i3] >> 19);
+			i1++; i2++; i3++;
+
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+		}
+	}
+}
+
+static void diffuser_a_encrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 5; i++) {
+		i1 = n - 1;
+		i2 = n - 2 - 1;
+		i3 = n - 5 - 1;
+
+		while (i1 > 0) {
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+
+			d[i1] -= d[i2] ^ (d[i3] << 13 | d[i3] >> 19);
+			i1--; i2--; i3--;
+
+			if (i2 < 0)
+				i2 += n;
+
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+
+			if (i3 < 0)
+				i3 += n;
+
+			d[i1] -= d[i2] ^ (d[i3] << 9 | d[i3] >> 23);
+			i1--; i2--; i3--;
+		}
+	}
+}
+
+static void diffuser_b_decrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 3; i++) {
+		i1 = 0;
+		i2 = 2;
+		i3 = 5;
+
+		while (i1 < (n - 1)) {
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+
+			d[i1] += d[i2] ^ (d[i3] << 10 | d[i3] >> 22);
+			i1++; i2++; i3++;
+
+			if (i2 >= n)
+				i2 -= n;
+
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+
+			if (i3 >= n)
+				i3 -= n;
+
+			d[i1] += d[i2] ^ (d[i3] << 25 | d[i3] >> 7);
+			i1++; i2++; i3++;
+		}
+	}
+}
+
+static void diffuser_b_encrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 3; i++) {
+		i1 = n - 1;
+		i2 = 2 - 1;
+		i3 = 5 - 1;
+
+		while (i1 > 0) {
+			d[i1] -= d[i2] ^ (d[i3] << 25 | d[i3] >> 7);
+			i1--; i2--; i3--;
+
+			if (i3 < 0)
+				i3 += n;
+
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+
+			if (i2 < 0)
+				i2 += n;
+
+			d[i1] -= d[i2] ^ (d[i3] << 10 | d[i3] >> 22);
+			i1--; i2--; i3--;
+
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+		}
+	}
+}
+
+static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *dmreq)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	u8 *es, *ks, *data, *data2, *data_offset;
+	struct skcipher_request *req;
+	struct scatterlist *sg, *sg2, src, dst;
+	struct crypto_wait wait;
+	int i, r;
+
+	req = skcipher_request_alloc(elephant->tfm, GFP_NOIO);
+	es = kzalloc(16, GFP_NOIO); /* Key for AES */
+	ks = kzalloc(32, GFP_NOIO); /* Elephant sector key */
+
+	if (!req || !es || !ks) {
+		r = -ENOMEM;
+		goto out;
+	}
+
+	*(__le64 *)es = cpu_to_le64(dmreq->iv_sector * cc->sector_size);
+
+	/* E(Ks, e(s)) */
+	sg_init_one(&src, es, 16);
+	sg_init_one(&dst, ks, 16);
+	skcipher_request_set_crypt(req, &src, &dst, 16, NULL);
+	skcipher_request_set_callback(req, 0, crypto_req_done, &wait);
+	r = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	if (r)
+		goto out;
+
+	/* E(Ks, e'(s)) */
+	es[15] = 0x80;
+	sg_init_one(&dst, &ks[16], 16);
+	r = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	if (r)
+		goto out;
+
+	sg = crypt_get_sg_data(cc, dmreq->sg_out);
+	data = kmap_atomic(sg_page(sg));
+	data_offset = data + sg->offset;
+
+	/* Cannot modify original bio, copy to sg_out and apply Elephant to it */
+	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
+		sg2 = crypt_get_sg_data(cc, dmreq->sg_in);
+		data2 = kmap_atomic(sg_page(sg2));
+		memcpy(data_offset, data2 + sg2->offset, cc->sector_size);
+		kunmap_atomic(data2);
+	}
+
+	if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) {
+		diffuser_disk_to_cpu((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_b_decrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_a_decrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_cpu_to_disk((__le32*)data_offset, cc->sector_size / sizeof(u32));
+	}
+
+	for (i = 0; i < (cc->sector_size / 32); i++)
+		crypto_xor(data_offset + i * 32, ks, 32);
+
+	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
+		diffuser_disk_to_cpu((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_a_encrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_b_encrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_cpu_to_disk((__le32*)data_offset, cc->sector_size / sizeof(u32));
+	}
+
+	kunmap_atomic(data);
+out:
+	kzfree(ks);
+	kzfree(es);
+	skcipher_request_free(req);
+	return r;
+}
+
+static int crypt_iv_elephant_gen(struct crypt_config *cc, u8 *iv,
+			    struct dm_crypt_request *dmreq)
+{
+	int r;
+
+	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
+		r = crypt_iv_elephant(cc, dmreq);
+		if (r)
+			return r;
+	}
+
+	return crypt_iv_eboiv_gen(cc, iv, dmreq);
+}
+
+static int crypt_iv_elephant_post(struct crypt_config *cc, u8 *iv,
+				  struct dm_crypt_request *dmreq)
+{
+	if (bio_data_dir(dmreq->ctx->bio_in) != WRITE)
+		return crypt_iv_elephant(cc, dmreq);
+
+	return 0;
+}
+
+static int crypt_iv_elephant_init(struct crypt_config *cc)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	int key_offset = cc->key_size - cc->key_extra_size;
+
+	return crypto_skcipher_setkey(elephant->tfm, &cc->key[key_offset], cc->key_extra_size);
+}
+
+static int crypt_iv_elephant_wipe(struct crypt_config *cc)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	u8 key[ELEPHANT_MAX_KEY_SIZE];
+
+	memset(key, 0, cc->key_extra_size);
+	return crypto_skcipher_setkey(elephant->tfm, key, cc->key_extra_size);
+}
+
 static const struct crypt_iv_operations crypt_iv_plain_ops = {
 	.generator = crypt_iv_plain_gen
 };
@@ -787,6 +1089,15 @@ static struct crypt_iv_operations crypt_iv_eboiv_ops = {
 	.generator = crypt_iv_eboiv_gen
 };
 
+static struct crypt_iv_operations crypt_iv_elephant_ops = {
+	.ctr	   = crypt_iv_elephant_ctr,
+	.dtr	   = crypt_iv_elephant_dtr,
+	.init	   = crypt_iv_elephant_init,
+	.wipe	   = crypt_iv_elephant_wipe,
+	.generator = crypt_iv_elephant_gen,
+	.post	   = crypt_iv_elephant_post
+};
+
 /*
  * Integrity extensions
  */
@@ -1103,6 +1414,9 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc,
 			r = cc->iv_gen_ops->generator(cc, org_iv, dmreq);
 			if (r < 0)
 				return r;
+			/* Data can be already preprocessed in generator */
+			if (test_bit(CRYPT_ENCRYPT_PREPROCESS, &cc->cipher_flags))
+				sg_in = sg_out;
 			/* Store generated IV in integrity metadata */
 			if (cc->integrity_iv_size)
 				memcpy(tag_iv, org_iv, cc->integrity_iv_size);
@@ -2191,7 +2505,14 @@ static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode)
 		cc->iv_gen_ops = &crypt_iv_null_ops;
 	else if (strcmp(ivmode, "eboiv") == 0)
 		cc->iv_gen_ops = &crypt_iv_eboiv_ops;
-	else if (strcmp(ivmode, "lmk") == 0) {
+	else if (strcmp(ivmode, "elephant") == 0) {
+		cc->iv_gen_ops = &crypt_iv_elephant_ops;
+		cc->key_parts = 2;
+		cc->key_extra_size = cc->key_size / 2;
+		if (cc->key_extra_size > ELEPHANT_MAX_KEY_SIZE)
+			return -EINVAL;
+		set_bit(CRYPT_ENCRYPT_PREPROCESS, &cc->cipher_flags);
+	} else if (strcmp(ivmode, "lmk") == 0) {
 		cc->iv_gen_ops = &crypt_iv_lmk_ops;
 		/*
 		 * Version 2 and 3 is recognised according
@@ -2959,7 +3280,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 19, 0},
+	.version = {1, 20, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c
index eb37584427a4..ff03b90072c5 100644
--- a/drivers/md/dm-dust.c
+++ b/drivers/md/dm-dust.c
@@ -207,16 +207,16 @@ static int dust_map_write(struct dust_device *dd, sector_t thisblock,
 			  bool fail_read_on_bb)
 {
 	unsigned long flags;
-	int ret = DM_MAPIO_REMAPPED;
+	int r = DM_MAPIO_REMAPPED;
 
 	if (fail_read_on_bb) {
 		thisblock >>= dd->sect_per_block_shift;
 		spin_lock_irqsave(&dd->dust_lock, flags);
-		ret = __dust_map_write(dd, thisblock);
+		r = __dust_map_write(dd, thisblock);
 		spin_unlock_irqrestore(&dd->dust_lock, flags);
 	}
 
-	return ret;
+	return r;
 }
 
 static int dust_map(struct dm_target *ti, struct bio *bio)
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index e0c32793c248..2bc18c9c3abc 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -20,6 +20,7 @@
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/time.h>
+#include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <scsi/scsi_dh.h>
@@ -29,6 +30,9 @@
 #define DM_MSG_PREFIX "multipath"
 #define DM_PG_INIT_DELAY_MSECS 2000
 #define DM_PG_INIT_DELAY_DEFAULT ((unsigned) -1)
+#define QUEUE_IF_NO_PATH_TIMEOUT_DEFAULT 0
+
+static unsigned long queue_if_no_path_timeout_secs = QUEUE_IF_NO_PATH_TIMEOUT_DEFAULT;
 
 /* Path properties */
 struct pgpath {
@@ -91,6 +95,8 @@ struct multipath {
 
 	struct work_struct process_queued_bios;
 	struct bio_list queued_bios;
+
+	struct timer_list nopath_timer;	/* Timeout for queue_if_no_path */
 };
 
 /*
@@ -108,6 +114,7 @@ static void trigger_event(struct work_struct *work);
 static void activate_or_offline_path(struct pgpath *pgpath);
 static void activate_path_work(struct work_struct *work);
 static void process_queued_bios(struct work_struct *work);
+static void queue_if_no_path_timeout_work(struct timer_list *t);
 
 /*-----------------------------------------------
  * Multipath state flags.
@@ -195,6 +202,8 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 
 		m->ti = ti;
 		ti->private = m;
+
+		timer_setup(&m->nopath_timer, queue_if_no_path_timeout_work, 0);
 	}
 
 	return m;
@@ -718,6 +727,43 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
 }
 
 /*
+ * If the queue_if_no_path timeout fires, turn off queue_if_no_path and
+ * process any queued I/O.
+ */
+static void queue_if_no_path_timeout_work(struct timer_list *t)
+{
+	struct multipath *m = from_timer(m, t, nopath_timer);
+	struct mapped_device *md = dm_table_get_md(m->ti->table);
+
+	DMWARN("queue_if_no_path timeout on %s, failing queued IO", dm_device_name(md));
+	queue_if_no_path(m, false, false);
+}
+
+/*
+ * Enable the queue_if_no_path timeout if necessary.
+ * Called with m->lock held.
+ */
+static void enable_nopath_timeout(struct multipath *m)
+{
+	unsigned long queue_if_no_path_timeout =
+		READ_ONCE(queue_if_no_path_timeout_secs) * HZ;
+
+	lockdep_assert_held(&m->lock);
+
+	if (queue_if_no_path_timeout > 0 &&
+	    atomic_read(&m->nr_valid_paths) == 0 &&
+	    test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+		mod_timer(&m->nopath_timer,
+			  jiffies + queue_if_no_path_timeout);
+	}
+}
+
+static void disable_nopath_timeout(struct multipath *m)
+{
+	del_timer_sync(&m->nopath_timer);
+}
+
+/*
  * An event is triggered whenever a path is taken out of use.
  * Includes path failure and PG bypass.
  */
@@ -1090,6 +1136,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	struct dm_arg_set as;
 	unsigned pg_count = 0;
 	unsigned next_pg_num;
+	unsigned long flags;
 
 	as.argc = argc;
 	as.argv = argv;
@@ -1154,6 +1201,10 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
+	spin_lock_irqsave(&m->lock, flags);
+	enable_nopath_timeout(m);
+	spin_unlock_irqrestore(&m->lock, flags);
+
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
@@ -1208,6 +1259,7 @@ static void multipath_dtr(struct dm_target *ti)
 {
 	struct multipath *m = ti->private;
 
+	disable_nopath_timeout(m);
 	flush_multipath_work(m);
 	free_multipath(m);
 }
@@ -1241,6 +1293,8 @@ static int fail_path(struct pgpath *pgpath)
 
 	schedule_work(&m->trigger_event);
 
+	enable_nopath_timeout(m);
+
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
 
@@ -1291,6 +1345,9 @@ out:
 		process_queued_io_list(m);
 	}
 
+	if (pgpath->is_active)
+		disable_nopath_timeout(m);
+
 	return r;
 }
 
@@ -1444,7 +1501,7 @@ static void pg_init_done(void *data, int errors)
 		break;
 	case SCSI_DH_RETRY:
 		/* Wait before retrying. */
-		delay_retry = 1;
+		delay_retry = true;
 		/* fall through */
 	case SCSI_DH_IMM_RETRY:
 	case SCSI_DH_RES_TEMP_UNAVAIL:
@@ -1789,6 +1846,7 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv,
 	struct dm_dev *dev;
 	struct multipath *m = ti->private;
 	action_fn action;
+	unsigned long flags;
 
 	mutex_lock(&m->work_mutex);
 
@@ -1800,9 +1858,13 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv,
 	if (argc == 1) {
 		if (!strcasecmp(argv[0], "queue_if_no_path")) {
 			r = queue_if_no_path(m, true, false);
+			spin_lock_irqsave(&m->lock, flags);
+			enable_nopath_timeout(m);
+			spin_unlock_irqrestore(&m->lock, flags);
 			goto out;
 		} else if (!strcasecmp(argv[0], "fail_if_no_path")) {
 			r = queue_if_no_path(m, false, false);
+			disable_nopath_timeout(m);
 			goto out;
 		}
 	}
@@ -2065,6 +2127,10 @@ static void __exit dm_multipath_exit(void)
 module_init(dm_multipath_init);
 module_exit(dm_multipath_exit);
 
+module_param_named(queue_if_no_path_timeout_secs,
+		   queue_if_no_path_timeout_secs, ulong, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(queue_if_no_path_timeout_secs, "No available paths queue IO timeout in seconds");
+
 MODULE_DESCRIPTION(DM_NAME " multipath target");
 MODULE_AUTHOR("Sistina Software <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index c412eaa975fc..9a18bef0a5ff 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -129,7 +129,9 @@ struct raid_dev {
 				  CTR_FLAG_RAID10_COPIES | \
 				  CTR_FLAG_RAID10_FORMAT | \
 				  CTR_FLAG_DELTA_DISKS | \
-				  CTR_FLAG_DATA_OFFSET)
+				  CTR_FLAG_DATA_OFFSET | \
+				  CTR_FLAG_JOURNAL_DEV | \
+				  CTR_FLAG_JOURNAL_MODE)
 
 /* Valid options definitions per raid level... */
 
@@ -3001,7 +3003,6 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		{ 1, 254, "Cannot understand number of raid devices parameters" }
 	};
 
-	/* Must have <raid_type> */
 	arg = dm_shift_arg(&as);
 	if (!arg) {
 		ti->error = "No arguments";
@@ -3508,8 +3509,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	unsigned long recovery;
 	unsigned int raid_param_cnt = 1; /* at least 1 for chunksize */
 	unsigned int sz = 0;
-	unsigned int rebuild_disks;
-	unsigned int write_mostly_params = 0;
+	unsigned int rebuild_writemostly_count = 0;
 	sector_t progress, resync_max_sectors, resync_mismatches;
 	enum sync_state state;
 	struct raid_type *rt;
@@ -3593,18 +3593,20 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	case STATUSTYPE_TABLE:
 		/* Report the table line string you would use to construct this raid set */
 
-		/* Calculate raid parameter count */
-		for (i = 0; i < rs->raid_disks; i++)
-			if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
-				write_mostly_params += 2;
-		rebuild_disks = memweight(rs->rebuild_disks, DISKS_ARRAY_ELEMS * sizeof(*rs->rebuild_disks));
-		raid_param_cnt += rebuild_disks * 2 +
-				  write_mostly_params +
+		/*
+		 * Count any rebuild or writemostly argument pairs and subtract the
+		 * hweight count being added below of any rebuild and writemostly ctr flags.
+		 */
+		for (i = 0; i < rs->raid_disks; i++) {
+			rebuild_writemostly_count += (test_bit(i, (void *) rs->rebuild_disks) ? 2 : 0) +
+						     (test_bit(WriteMostly, &rs->dev[i].rdev.flags) ? 2 : 0);
+		}
+		rebuild_writemostly_count -= (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags) ? 2 : 0) +
+					     (test_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags) ? 2 : 0);
+		/* Calculate raid parameter count based on ^ rebuild/writemostly argument counts and ctr flags set. */
+		raid_param_cnt += rebuild_writemostly_count +
 				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_NO_ARGS) +
-				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_ONE_ARG) * 2 +
-				  (test_bit(__CTR_FLAG_JOURNAL_DEV, &rs->ctr_flags) ? 2 : 0) +
-				  (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags) ? 2 : 0);
-
+				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_ONE_ARG) * 2;
 		/* Emit table line */
 		/* This has to be in the documented order for userspace! */
 		DMEMIT("%s %u %u", rs->raid_type->name, raid_param_cnt, mddev->new_chunk_sectors);
@@ -3612,11 +3614,10 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_SYNC));
 		if (test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
 			DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC));
-		if (rebuild_disks)
+		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags))
 			for (i = 0; i < rs->raid_disks; i++)
-				if (test_bit(rs->dev[i].rdev.raid_disk, (void *) rs->rebuild_disks))
-					DMEMIT(" %s %u", dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD),
-							 rs->dev[i].rdev.raid_disk);
+				if (test_bit(i, (void *) rs->rebuild_disks))
+					DMEMIT(" %s %u", dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD), i);
 		if (test_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags))
 			DMEMIT(" %s %lu", dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP),
 					  mddev->bitmap_info.daemon_sleep);
@@ -3626,7 +3627,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		if (test_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags))
 			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE),
 					 mddev->sync_speed_max);
-		if (write_mostly_params)
+		if (test_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags))
 			for (i = 0; i < rs->raid_disks; i++)
 				if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
 					DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY),
@@ -4029,7 +4030,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 15, 0},
+	.version = {1, 15, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 4fb1a40e68a0..6b11a266299f 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1061,7 +1061,7 @@ static void snapshot_merge_next_chunks(struct dm_snapshot *s)
 			DMERR("Read error in exception store: "
 			      "shutting down merge");
 			down_write(&s->lock);
-			s->merge_failed = 1;
+			s->merge_failed = true;
 			up_write(&s->lock);
 		}
 		goto shut;
@@ -1149,7 +1149,7 @@ static void merge_callback(int read_err, unsigned long write_err, void *context)
 
 shut:
 	down_write(&s->lock);
-	s->merge_failed = 1;
+	s->merge_failed = true;
 	b = __release_queued_bios_after_merge(s);
 	up_write(&s->lock);
 	error_bios(b);
@@ -1314,7 +1314,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	INIT_LIST_HEAD(&s->list);
 	spin_lock_init(&s->pe_lock);
 	s->state_bits = 0;
-	s->merge_failed = 0;
+	s->merge_failed = false;
 	s->first_merging_chunk = 0;
 	s->num_merging_chunks = 0;
 	bio_list_init(&s->bios_queued_during_merge);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index b88d6d701f5b..fc9947d6210c 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -28,7 +28,7 @@
  *
  * - A hierarchical btree, with 2 levels which effectively maps (thin
  *   dev id, virtual block) -> block_time.  Block time is a 64-bit
- *   field holding the time in the low 24 bits, and block in the top 48
+ *   field holding the time in the low 24 bits, and block in the top 40
  *   bits.
  *
  * BTrees consist solely of btree_nodes, that fill a block.  Some are
@@ -387,16 +387,15 @@ static int subtree_equal(void *context, const void *value1_le, const void *value
  * Variant that is used for in-core only changes or code that
  * shouldn't put the pool in service on its own (e.g. commit).
  */
-static inline void __pmd_write_lock(struct dm_pool_metadata *pmd)
+static inline void pmd_write_lock_in_core(struct dm_pool_metadata *pmd)
 	__acquires(pmd->root_lock)
 {
 	down_write(&pmd->root_lock);
 }
-#define pmd_write_lock_in_core(pmd) __pmd_write_lock((pmd))
 
 static inline void pmd_write_lock(struct dm_pool_metadata *pmd)
 {
-	__pmd_write_lock(pmd);
+	pmd_write_lock_in_core(pmd);
 	if (unlikely(!pmd->in_service))
 		pmd->in_service = true;
 }
@@ -811,7 +810,7 @@ static int __write_changed_details(struct dm_pool_metadata *pmd)
 			return r;
 
 		if (td->open_count)
-			td->changed = 0;
+			td->changed = false;
 		else {
 			list_del(&td->list);
 			kfree(td);
@@ -831,6 +830,7 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	 * We need to know if the thin_disk_superblock exceeds a 512-byte sector.
 	 */
 	BUILD_BUG_ON(sizeof(struct thin_disk_superblock) > 512);
+	BUG_ON(!rwsem_is_locked(&pmd->root_lock));
 
 	if (unlikely(!pmd->in_service))
 		return 0;
@@ -953,6 +953,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 		return -EBUSY;
 	}
 
+	pmd_write_lock_in_core(pmd);
 	if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) {
 		r = __commit_transaction(pmd);
 		if (r < 0)
@@ -961,6 +962,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 	}
 	if (!pmd->fail_io)
 		__destroy_persistent_data_objects(pmd);
+	pmd_write_unlock(pmd);
 
 	kfree(pmd);
 	return 0;
@@ -1106,7 +1108,7 @@ static int __set_snapshot_details(struct dm_pool_metadata *pmd,
 	if (r)
 		return r;
 
-	td->changed = 1;
+	td->changed = true;
 	td->snapshotted_time = time;
 
 	snap->mapped_blocks = td->mapped_blocks;
@@ -1618,7 +1620,7 @@ static int __insert(struct dm_thin_device *td, dm_block_t block,
 	if (r)
 		return r;
 
-	td->changed = 1;
+	td->changed = true;
 	if (inserted)
 		td->mapped_blocks++;
 
@@ -1649,7 +1651,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block)
 		return r;
 
 	td->mapped_blocks--;
-	td->changed = 1;
+	td->changed = true;
 
 	return 0;
 }
@@ -1703,7 +1705,7 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_
 	}
 
 	td->mapped_blocks -= total_count;
-	td->changed = 1;
+	td->changed = true;
 
 	/*
 	 * Reinsert the mapping tree.
@@ -1841,7 +1843,7 @@ int dm_pool_commit_metadata(struct dm_pool_metadata *pmd)
 	 * Care is taken to not have commit be what
 	 * triggers putting the thin-pool in-service.
 	 */
-	__pmd_write_lock(pmd);
+	pmd_write_lock_in_core(pmd);
 	if (pmd->fail_io)
 		goto out;
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 57626c27a54b..fa8d5464c1fb 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -231,6 +231,7 @@ struct pool {
 	struct dm_target *ti;	/* Only set if a pool target is bound */
 
 	struct mapped_device *pool_md;
+	struct block_device *data_dev;
 	struct block_device *md_dev;
 	struct dm_pool_metadata *pmd;
 
@@ -281,6 +282,8 @@ struct pool {
 	struct dm_bio_prison_cell **cell_sort_array;
 
 	mempool_t mapping_pool;
+
+	struct bio flush_bio;
 };
 
 static void metadata_operation_failed(struct pool *pool, const char *op, int r);
@@ -328,7 +331,6 @@ struct pool_c {
 	dm_block_t low_water_blocks;
 	struct pool_features requested_pf; /* Features requested during table load */
 	struct pool_features adjusted_pf;  /* Features used after adjusting for constituent devices */
-	struct bio flush_bio;
 };
 
 /*
@@ -2924,6 +2926,7 @@ static void __pool_destroy(struct pool *pool)
 	if (pool->next_mapping)
 		mempool_free(pool->next_mapping, &pool->mapping_pool);
 	mempool_exit(&pool->mapping_pool);
+	bio_uninit(&pool->flush_bio);
 	dm_deferred_set_destroy(pool->shared_read_ds);
 	dm_deferred_set_destroy(pool->all_io_ds);
 	kfree(pool);
@@ -2933,6 +2936,7 @@ static struct kmem_cache *_new_mapping_cache;
 
 static struct pool *pool_create(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
+				struct block_device *data_dev,
 				unsigned long block_size,
 				int read_only, char **error)
 {
@@ -3003,6 +3007,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pool->low_water_triggered = false;
 	pool->suspended = true;
 	pool->out_of_data_space = false;
+	bio_init(&pool->flush_bio, NULL, 0);
 
 	pool->shared_read_ds = dm_deferred_set_create();
 	if (!pool->shared_read_ds) {
@@ -3040,6 +3045,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
 	pool->md_dev = metadata_dev;
+	pool->data_dev = data_dev;
 	__pool_table_insert(pool);
 
 	return pool;
@@ -3081,6 +3087,7 @@ static void __pool_dec(struct pool *pool)
 
 static struct pool *__pool_find(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
+				struct block_device *data_dev,
 				unsigned long block_size, int read_only,
 				char **error, int *created)
 {
@@ -3091,19 +3098,23 @@ static struct pool *__pool_find(struct mapped_device *pool_md,
 			*error = "metadata device already in use by a pool";
 			return ERR_PTR(-EBUSY);
 		}
+		if (pool->data_dev != data_dev) {
+			*error = "data device already in use by a pool";
+			return ERR_PTR(-EBUSY);
+		}
 		__pool_inc(pool);
 
 	} else {
 		pool = __pool_table_lookup(pool_md);
 		if (pool) {
-			if (pool->md_dev != metadata_dev) {
+			if (pool->md_dev != metadata_dev || pool->data_dev != data_dev) {
 				*error = "different pool cannot replace a pool";
 				return ERR_PTR(-EINVAL);
 			}
 			__pool_inc(pool);
 
 		} else {
-			pool = pool_create(pool_md, metadata_dev, block_size, read_only, error);
+			pool = pool_create(pool_md, metadata_dev, data_dev, block_size, read_only, error);
 			*created = 1;
 		}
 	}
@@ -3124,7 +3135,6 @@ static void pool_dtr(struct dm_target *ti)
 	__pool_dec(pt->pool);
 	dm_put_device(ti, pt->metadata_dev);
 	dm_put_device(ti, pt->data_dev);
-	bio_uninit(&pt->flush_bio);
 	kfree(pt);
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -3203,11 +3213,11 @@ static void metadata_low_callback(void *context)
  */
 static int metadata_pre_commit_callback(void *context)
 {
-	struct pool_c *pt = context;
-	struct bio *flush_bio = &pt->flush_bio;
+	struct pool *pool = context;
+	struct bio *flush_bio = &pool->flush_bio;
 
 	bio_reset(flush_bio);
-	bio_set_dev(flush_bio, pt->data_dev->bdev);
+	bio_set_dev(flush_bio, pool->data_dev);
 	flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
 	return submit_bio_wait(flush_bio);
@@ -3356,7 +3366,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto out;
 	}
 
-	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev,
+	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev, data_dev->bdev,
 			   block_size, pf.mode == PM_READ_ONLY, &ti->error, &pool_created);
 	if (IS_ERR(pool)) {
 		r = PTR_ERR(pool);
@@ -3381,7 +3391,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	pt->data_dev = data_dev;
 	pt->low_water_blocks = low_water_blocks;
 	pt->adjusted_pf = pt->requested_pf = pf;
-	bio_init(&pt->flush_bio, NULL, 0);
 	ti->num_flush_bios = 1;
 
 	/*
@@ -3408,9 +3417,8 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (r)
 		goto out_flags_changed;
 
-	dm_pool_register_pre_commit_callback(pt->pool->pmd,
-					     metadata_pre_commit_callback,
-					     pt);
+	dm_pool_register_pre_commit_callback(pool->pmd,
+					     metadata_pre_commit_callback, pool);
 
 	pt->callbacks.congested_fn = pool_is_congested;
 	dm_table_add_target_callbacks(ti->table, &pt->callbacks);
@@ -4099,7 +4107,7 @@ static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 21, 0},
+	.version = {1, 22, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4476,7 +4484,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 21, 0},
+	.version = {1, 22, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 4fb33e7562c5..0d61e9c67986 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -611,8 +611,22 @@ no_prefetch_cluster:
 
 static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
 {
+	sector_t block = io->block;
+	unsigned int n_blocks = io->n_blocks;
 	struct dm_verity_prefetch_work *pw;
 
+	if (v->validated_blocks) {
+		while (n_blocks && test_bit(block, v->validated_blocks)) {
+			block++;
+			n_blocks--;
+		}
+		while (n_blocks && test_bit(block + n_blocks - 1,
+					    v->validated_blocks))
+			n_blocks--;
+		if (!n_blocks)
+			return;
+	}
+
 	pw = kmalloc(sizeof(struct dm_verity_prefetch_work),
 		GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
@@ -621,8 +635,8 @@ static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
 
 	INIT_WORK(&pw->work, verity_prefetch_io);
 	pw->v = v;
-	pw->block = io->block;
-	pw->n_blocks = io->n_blocks;
+	pw->block = block;
+	pw->n_blocks = n_blocks;
 	queue_work(v->verify_wq, &pw->work);
 }
 
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 7d727a72aa13..b9e27e37a943 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -442,7 +442,13 @@ static void writecache_notify_io(unsigned long error, void *context)
 		complete(&endio->c);
 }
 
-static void ssd_commit_flushed(struct dm_writecache *wc)
+static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
+{
+	wait_event(wc->bio_in_progress_wait[direction],
+		   !atomic_read(&wc->bio_in_progress[direction]));
+}
+
+static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	struct dm_io_region region;
 	struct dm_io_request req;
@@ -488,17 +494,20 @@ static void ssd_commit_flushed(struct dm_writecache *wc)
 	writecache_notify_io(0, &endio);
 	wait_for_completion_io(&endio.c);
 
+	if (wait_for_ios)
+		writecache_wait_for_ios(wc, WRITE);
+
 	writecache_disk_flush(wc, wc->ssd_dev);
 
 	memset(wc->dirty_bitmap, 0, wc->dirty_bitmap_size);
 }
 
-static void writecache_commit_flushed(struct dm_writecache *wc)
+static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	if (WC_MODE_PMEM(wc))
 		wmb();
 	else
-		ssd_commit_flushed(wc);
+		ssd_commit_flushed(wc, wait_for_ios);
 }
 
 static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
@@ -522,12 +531,6 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
 		writecache_error(wc, r, "error flushing metadata: %d", r);
 }
 
-static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
-{
-	wait_event(wc->bio_in_progress_wait[direction],
-		   !atomic_read(&wc->bio_in_progress[direction]));
-}
-
 #define WFE_RETURN_FOLLOWING	1
 #define WFE_LOWEST_SEQ		2
 
@@ -622,7 +625,7 @@ static void writecache_add_to_freelist(struct dm_writecache *wc, struct wc_entry
 	wc->freelist_size++;
 }
 
-static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
+static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector)
 {
 	struct wc_entry *e;
 
@@ -631,6 +634,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
 		if (unlikely(!wc->current_free))
 			return NULL;
 		e = wc->current_free;
+		if (expected_sector != (sector_t)-1 && unlikely(cache_sector(wc, e) != expected_sector))
+			return NULL;
 		next = rb_next(&e->rb_node);
 		rb_erase(&e->rb_node, &wc->freetree);
 		if (unlikely(!next))
@@ -640,6 +645,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
 		if (unlikely(list_empty(&wc->freelist)))
 			return NULL;
 		e = container_of(wc->freelist.next, struct wc_entry, lru);
+		if (expected_sector != (sector_t)-1 && unlikely(cache_sector(wc, e) != expected_sector))
+			return NULL;
 		list_del(&e->lru);
 	}
 	wc->freelist_size--;
@@ -724,15 +731,12 @@ static void writecache_flush(struct dm_writecache *wc)
 		e = e2;
 		cond_resched();
 	}
-	writecache_commit_flushed(wc);
-
-	if (!WC_MODE_PMEM(wc))
-		writecache_wait_for_ios(wc, WRITE);
+	writecache_commit_flushed(wc, true);
 
 	wc->seq_count++;
 	pmem_assign(sb(wc)->seq_count, cpu_to_le64(wc->seq_count));
 	writecache_flush_region(wc, &sb(wc)->seq_count, sizeof sb(wc)->seq_count);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 
 	wc->overwrote_committed = false;
 
@@ -756,7 +760,7 @@ static void writecache_flush(struct dm_writecache *wc)
 	}
 
 	if (need_flush_after_free)
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 }
 
 static void writecache_flush_work(struct work_struct *work)
@@ -809,7 +813,7 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_
 	}
 
 	if (discarded_something)
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 }
 
 static bool writecache_wait_for_writeback(struct dm_writecache *wc)
@@ -958,7 +962,7 @@ erase_this:
 
 	if (need_flush) {
 		writecache_flush_all_metadata(wc);
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 	}
 
 	wc_unlock(wc);
@@ -1193,7 +1197,7 @@ read_next_block:
 					goto bio_copy;
 				}
 			}
-			e = writecache_pop_from_freelist(wc);
+			e = writecache_pop_from_freelist(wc, (sector_t)-1);
 			if (unlikely(!e)) {
 				writecache_wait_on_freelist(wc);
 				continue;
@@ -1205,9 +1209,26 @@ bio_copy:
 			if (WC_MODE_PMEM(wc)) {
 				bio_copy_block(wc, bio, memory_data(wc, e));
 			} else {
-				dm_accept_partial_bio(bio, wc->block_size >> SECTOR_SHIFT);
+				unsigned bio_size = wc->block_size;
+				sector_t start_cache_sec = cache_sector(wc, e);
+				sector_t current_cache_sec = start_cache_sec + (bio_size >> SECTOR_SHIFT);
+
+				while (bio_size < bio->bi_iter.bi_size) {
+					struct wc_entry *f = writecache_pop_from_freelist(wc, current_cache_sec);
+					if (!f)
+						break;
+					write_original_sector_seq_count(wc, f, bio->bi_iter.bi_sector +
+									(bio_size >> SECTOR_SHIFT), wc->seq_count);
+					writecache_insert_entry(wc, f);
+					wc->uncommitted_blocks++;
+					bio_size += wc->block_size;
+					current_cache_sec += wc->block_size >> SECTOR_SHIFT;
+				}
+
 				bio_set_dev(bio, wc->ssd_dev->bdev);
-				bio->bi_iter.bi_sector = cache_sector(wc, e);
+				bio->bi_iter.bi_sector = start_cache_sec;
+				dm_accept_partial_bio(bio, bio_size >> SECTOR_SHIFT);
+
 				if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) {
 					wc->uncommitted_blocks = 0;
 					queue_work(wc->writeback_wq, &wc->flush_work);
@@ -1342,7 +1363,7 @@ static void __writecache_endio_pmem(struct dm_writecache *wc, struct list_head *
 			wc->writeback_size--;
 			n_walked++;
 			if (unlikely(n_walked >= ENDIO_LATENCY)) {
-				writecache_commit_flushed(wc);
+				writecache_commit_flushed(wc, false);
 				wc_unlock(wc);
 				wc_lock(wc);
 				n_walked = 0;
@@ -1423,7 +1444,7 @@ pop_from_list:
 			writecache_wait_for_ios(wc, READ);
 		}
 
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 
 		wc_unlock(wc);
 	}
@@ -1766,10 +1787,10 @@ static int init_memory(struct dm_writecache *wc)
 		write_original_sector_seq_count(wc, &wc->entries[b], -1, -1);
 
 	writecache_flush_all_metadata(wc);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 	pmem_assign(sb(wc)->magic, cpu_to_le32(MEMORY_SUPERBLOCK_MAGIC));
 	writecache_flush_region(wc, &sb(wc)->magic, sizeof sb(wc)->magic);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 
 	return 0;
 }
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 22b3cb0050a7..516c7b671d25 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -134,6 +134,7 @@ struct dmz_metadata {
 
 	sector_t		zone_bitmap_size;
 	unsigned int		zone_nr_bitmap_blocks;
+	unsigned int		zone_bits_per_mblk;
 
 	unsigned int		nr_bitmap_blocks;
 	unsigned int		nr_map_blocks;
@@ -1161,7 +1162,10 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 
 	/* Init */
 	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
-	zmd->zone_nr_bitmap_blocks = zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT;
+	zmd->zone_nr_bitmap_blocks =
+		max_t(sector_t, 1, zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT);
+	zmd->zone_bits_per_mblk = min_t(sector_t, dev->zone_nr_blocks,
+					DMZ_BLOCK_SIZE_BITS);
 
 	/* Allocate zone array */
 	zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL);
@@ -1956,7 +1960,7 @@ int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
 		dmz_release_mblock(zmd, to_mblk);
 		dmz_release_mblock(zmd, from_mblk);
 
-		chunk_block += DMZ_BLOCK_SIZE_BITS;
+		chunk_block += zmd->zone_bits_per_mblk;
 	}
 
 	to_zone->weight = from_zone->weight;
@@ -2017,7 +2021,7 @@ int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Set bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_set_bits((unsigned long *)mblk->data, bit, nr_bits);
 		if (count) {
@@ -2096,7 +2100,7 @@ int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Clear bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_clear_bits((unsigned long *)mblk->data,
 				       bit, nr_bits);
@@ -2156,6 +2160,7 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 {
 	struct dmz_mblock *mblk;
 	unsigned int bit, set_bit, nr_bits;
+	unsigned int zone_bits = zmd->zone_bits_per_mblk;
 	unsigned long *bitmap;
 	int n = 0;
 
@@ -2170,15 +2175,15 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 		/* Get offset */
 		bitmap = (unsigned long *) mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zone_bits - bit);
 		if (set)
-			set_bit = find_next_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_bit(bitmap, zone_bits, bit);
 		else
-			set_bit = find_next_zero_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_zero_bit(bitmap, zone_bits, bit);
 		dmz_release_mblock(zmd, mblk);
 
 		n += set_bit - bit;
-		if (set_bit < DMZ_BLOCK_SIZE_BITS)
+		if (set_bit < zone_bits)
 			break;
 
 		nr_blocks -= nr_bits;
@@ -2281,7 +2286,7 @@ static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone)
 		/* Count bits in this block */
 		bitmap = mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 		n += dmz_count_bits(bitmap, bit, nr_bits);
 
 		dmz_release_mblock(zmd, mblk);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e8f9661a10a1..b89f07ee2eff 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1859,6 +1859,7 @@ static void dm_init_normal_md_queue(struct mapped_device *md)
 	/*
 	 * Initialize aspects of queue that aren't relevant for blk-mq
 	 */
+	md->queue->backing_dev_info->congested_data = md;
 	md->queue->backing_dev_info->congested_fn = dm_any_congested;
 }
 
@@ -1949,7 +1950,12 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->queue)
 		goto bad;
 	md->queue->queuedata = md;
-	md->queue->backing_dev_info->congested_data = md;
+	/*
+	 * default to bio-based required ->make_request_fn until DM
+	 * table is loaded and md->type established. If request-based
+	 * table is loaded: blk-mq will override accordingly.
+	 */
+	blk_queue_make_request(md->queue, dm_make_request);
 
 	md->disk = alloc_disk_node(1, md->numa_node_id);
 	if (!md->disk)
@@ -2264,7 +2270,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 	case DM_TYPE_DAX_BIO_BASED:
 	case DM_TYPE_NVME_BIO_BASED:
 		dm_init_normal_md_queue(md);
-		blk_queue_make_request(md->queue, dm_make_request);
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4824d50526fa..469f551863be 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8279,13 +8279,12 @@ static __poll_t mdstat_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
-static const struct file_operations md_seq_fops = {
-	.owner		= THIS_MODULE,
-	.open           = md_seq_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release	= seq_release,
-	.poll		= mdstat_poll,
+static const struct proc_ops mdstat_proc_ops = {
+	.proc_open	= md_seq_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
+	.proc_poll	= mdstat_poll,
 };
 
 int register_md_personality(struct md_personality *p)
@@ -9454,7 +9453,7 @@ static void md_geninit(void)
 {
 	pr_debug("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t));
 
-	proc_create("mdstat", S_IRUGO, NULL, &md_seq_fops);
+	proc_create("mdstat", S_IRUGO, NULL, &mdstat_proc_ops);
 }
 
 static int __init md_init(void)
diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c
index bd68f6fef694..d8b4125e338c 100644
--- a/drivers/md/persistent-data/dm-space-map-common.c
+++ b/drivers/md/persistent-data/dm-space-map-common.c
@@ -380,6 +380,33 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 	return -ENOSPC;
 }
 
+int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
+	                         dm_block_t begin, dm_block_t end, dm_block_t *b)
+{
+	int r;
+	uint32_t count;
+
+	do {
+		r = sm_ll_find_free_block(new_ll, begin, new_ll->nr_blocks, b);
+		if (r)
+			break;
+
+		/* double check this block wasn't used in the old transaction */
+		if (*b >= old_ll->nr_blocks)
+			count = 0;
+		else {
+			r = sm_ll_lookup(old_ll, *b, &count);
+			if (r)
+				break;
+
+			if (count)
+				begin = *b + 1;
+		}
+	} while (count);
+
+	return r;
+}
+
 static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b,
 			int (*mutator)(void *context, uint32_t old, uint32_t *new),
 			void *context, enum allocation_event *ev)
diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h
index b3078d5eda0c..8de63ce39bdd 100644
--- a/drivers/md/persistent-data/dm-space-map-common.h
+++ b/drivers/md/persistent-data/dm-space-map-common.h
@@ -109,6 +109,8 @@ int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 			  dm_block_t end, dm_block_t *result);
+int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
+	                         dm_block_t begin, dm_block_t end, dm_block_t *result);
 int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, enum allocation_event *ev);
 int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
 int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c
index 32adf6b4a9c7..bf4c5e2ccb6f 100644
--- a/drivers/md/persistent-data/dm-space-map-disk.c
+++ b/drivers/md/persistent-data/dm-space-map-disk.c
@@ -167,8 +167,10 @@ static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
 	enum allocation_event ev;
 	struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
 
-	/* FIXME: we should loop round a couple of times */
-	r = sm_ll_find_free_block(&smd->old_ll, smd->begin, smd->old_ll.nr_blocks, b);
+	/*
+	 * Any block we allocate has to be free in both the old and current ll.
+	 */
+	r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, smd->begin, smd->ll.nr_blocks, b);
 	if (r)
 		return r;
 
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 25328582cc48..9e3c64ec2026 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -448,7 +448,10 @@ static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b)
 	enum allocation_event ev;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	r = sm_ll_find_free_block(&smm->old_ll, smm->begin, smm->old_ll.nr_blocks, b);
+	/*
+	 * Any block we allocate has to be free in both the old and current ll.
+	 */
+	r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, smm->begin, smm->ll.nr_blocks, b);
 	if (r)
 		return r;
 
diff --git a/drivers/media/cec/cec-core.c b/drivers/media/cec/cec-core.c
index db7adffcdc76..0c52e1bb3910 100644
--- a/drivers/media/cec/cec-core.c
+++ b/drivers/media/cec/cec-core.c
@@ -183,24 +183,6 @@ static void cec_devnode_unregister(struct cec_adapter *adap)
 	put_device(&devnode->dev);
 }
 
-#ifdef CONFIG_CEC_NOTIFIER
-static void cec_cec_notify(struct cec_adapter *adap, u16 pa)
-{
-	cec_s_phys_addr(adap, pa, false);
-}
-
-void cec_register_cec_notifier(struct cec_adapter *adap,
-			       struct cec_notifier *notifier)
-{
-	if (WARN_ON(!cec_is_registered(adap)))
-		return;
-
-	adap->notifier = notifier;
-	cec_notifier_register(adap->notifier, adap, cec_cec_notify);
-}
-EXPORT_SYMBOL_GPL(cec_register_cec_notifier);
-#endif
-
 #ifdef CONFIG_DEBUG_FS
 static ssize_t cec_error_inj_write(struct file *file,
 	const char __user *ubuf, size_t count, loff_t *ppos)
@@ -416,8 +398,7 @@ void cec_unregister_adapter(struct cec_adapter *adap)
 #endif
 	debugfs_remove_recursive(adap->cec_dir);
 #ifdef CONFIG_CEC_NOTIFIER
-	if (adap->notifier)
-		cec_notifier_unregister(adap->notifier);
+	cec_notifier_cec_adap_unregister(adap->notifier, adap);
 #endif
 	cec_devnode_unregister(adap);
 }
diff --git a/drivers/media/cec/cec-notifier.c b/drivers/media/cec/cec-notifier.c
index 7cf42b133dbc..4a841bee5cc2 100644
--- a/drivers/media/cec/cec-notifier.c
+++ b/drivers/media/cec/cec-notifier.c
@@ -25,7 +25,6 @@ struct cec_notifier {
 	struct cec_connector_info conn_info;
 	const char *conn_name;
 	struct cec_adapter *cec_adap;
-	void (*callback)(struct cec_adapter *adap, u16 pa);
 
 	u16 phys_addr;
 };
@@ -81,13 +80,12 @@ static void cec_notifier_release(struct kref *kref)
 	kfree(n);
 }
 
-void cec_notifier_put(struct cec_notifier *n)
+static void cec_notifier_put(struct cec_notifier *n)
 {
 	mutex_lock(&cec_notifiers_lock);
 	kref_put(&n->kref, cec_notifier_release);
 	mutex_unlock(&cec_notifiers_lock);
 }
-EXPORT_SYMBOL_GPL(cec_notifier_put);
 
 struct cec_notifier *
 cec_notifier_conn_register(struct device *hdmi_dev, const char *conn_name,
@@ -162,7 +160,6 @@ void cec_notifier_cec_adap_unregister(struct cec_notifier *n,
 	mutex_lock(&n->lock);
 	adap->notifier = NULL;
 	n->cec_adap = NULL;
-	n->callback = NULL;
 	mutex_unlock(&n->lock);
 	cec_notifier_put(n);
 }
@@ -175,9 +172,7 @@ void cec_notifier_set_phys_addr(struct cec_notifier *n, u16 pa)
 
 	mutex_lock(&n->lock);
 	n->phys_addr = pa;
-	if (n->callback)
-		n->callback(n->cec_adap, n->phys_addr);
-	else if (n->cec_adap)
+	if (n->cec_adap)
 		cec_s_phys_addr(n->cec_adap, n->phys_addr, false);
 	mutex_unlock(&n->lock);
 }
@@ -198,34 +193,6 @@ void cec_notifier_set_phys_addr_from_edid(struct cec_notifier *n,
 }
 EXPORT_SYMBOL_GPL(cec_notifier_set_phys_addr_from_edid);
 
-void cec_notifier_register(struct cec_notifier *n,
-			   struct cec_adapter *adap,
-			   void (*callback)(struct cec_adapter *adap, u16 pa))
-{
-	kref_get(&n->kref);
-	mutex_lock(&n->lock);
-	n->cec_adap = adap;
-	n->callback = callback;
-	n->callback(adap, n->phys_addr);
-	mutex_unlock(&n->lock);
-}
-EXPORT_SYMBOL_GPL(cec_notifier_register);
-
-void cec_notifier_unregister(struct cec_notifier *n)
-{
-	/* Do nothing unless cec_notifier_register was called first */
-	if (!n->callback)
-		return;
-
-	mutex_lock(&n->lock);
-	n->callback = NULL;
-	n->cec_adap->notifier = NULL;
-	n->cec_adap = NULL;
-	mutex_unlock(&n->lock);
-	cec_notifier_put(n);
-}
-EXPORT_SYMBOL_GPL(cec_notifier_unregister);
-
 struct device *cec_notifier_parse_hdmi_phandle(struct device *dev)
 {
 	struct platform_device *hdmi_pdev;
diff --git a/drivers/media/cec/cec-priv.h b/drivers/media/cec/cec-priv.h
index 7bdf855aaecd..9bbd05053d42 100644
--- a/drivers/media/cec/cec-priv.h
+++ b/drivers/media/cec/cec-priv.h
@@ -9,7 +9,7 @@
 #define _CEC_PRIV_H
 
 #include <linux/cec-funcs.h>
-#include <media/cec.h>
+#include <media/cec-notifier.h>
 
 #define dprintk(lvl, fmt, arg...)					\
 	do {								\
diff --git a/drivers/media/common/saa7146/saa7146_video.c b/drivers/media/common/saa7146/saa7146_video.c
index d16122039b0c..ccd15b4d4920 100644
--- a/drivers/media/common/saa7146/saa7146_video.c
+++ b/drivers/media/common/saa7146/saa7146_video.c
@@ -345,7 +345,8 @@ static int video_begin(struct saa7146_fh *fh)
 
 	fmt = saa7146_format_by_fourcc(dev, vv->video_fmt.pixelformat);
 	/* we need to have a valid format set here */
-	BUG_ON(NULL == fmt);
+	if (!fmt)
+		return -EINVAL;
 
 	if (0 != (fmt->flags & FORMAT_IS_PLANAR)) {
 		resource = RESOURCE_DMA1_HPS|RESOURCE_DMA2_CLP|RESOURCE_DMA3_BRS;
@@ -398,7 +399,8 @@ static int video_end(struct saa7146_fh *fh, struct file *file)
 
 	fmt = saa7146_format_by_fourcc(dev, vv->video_fmt.pixelformat);
 	/* we need to have a valid format set here */
-	BUG_ON(NULL == fmt);
+	if (!fmt)
+		return -EINVAL;
 
 	if (0 != (fmt->flags & FORMAT_IS_PLANAR)) {
 		resource = RESOURCE_DMA1_HPS|RESOURCE_DMA2_CLP|RESOURCE_DMA3_BRS;
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index 44cd0e530bbd..d0c9dffe49e5 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -335,13 +335,6 @@ static void vb2_dc_dmabuf_ops_release(struct dma_buf *dbuf)
 	vb2_dc_put(dbuf->priv);
 }
 
-static void *vb2_dc_dmabuf_ops_kmap(struct dma_buf *dbuf, unsigned long pgnum)
-{
-	struct vb2_dc_buf *buf = dbuf->priv;
-
-	return buf->vaddr ? buf->vaddr + pgnum * PAGE_SIZE : NULL;
-}
-
 static void *vb2_dc_dmabuf_ops_vmap(struct dma_buf *dbuf)
 {
 	struct vb2_dc_buf *buf = dbuf->priv;
@@ -360,7 +353,6 @@ static const struct dma_buf_ops vb2_dc_dmabuf_ops = {
 	.detach = vb2_dc_dmabuf_ops_detach,
 	.map_dma_buf = vb2_dc_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_dc_dmabuf_ops_unmap,
-	.map = vb2_dc_dmabuf_ops_kmap,
 	.vmap = vb2_dc_dmabuf_ops_vmap,
 	.mmap = vb2_dc_dmabuf_ops_mmap,
 	.release = vb2_dc_dmabuf_ops_release,
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index ed706b2a263c..6db60e9d5183 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -470,13 +470,6 @@ static void vb2_dma_sg_dmabuf_ops_release(struct dma_buf *dbuf)
 	vb2_dma_sg_put(dbuf->priv);
 }
 
-static void *vb2_dma_sg_dmabuf_ops_kmap(struct dma_buf *dbuf, unsigned long pgnum)
-{
-	struct vb2_dma_sg_buf *buf = dbuf->priv;
-
-	return buf->vaddr ? buf->vaddr + pgnum * PAGE_SIZE : NULL;
-}
-
 static void *vb2_dma_sg_dmabuf_ops_vmap(struct dma_buf *dbuf)
 {
 	struct vb2_dma_sg_buf *buf = dbuf->priv;
@@ -495,7 +488,6 @@ static const struct dma_buf_ops vb2_dma_sg_dmabuf_ops = {
 	.detach = vb2_dma_sg_dmabuf_ops_detach,
 	.map_dma_buf = vb2_dma_sg_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_dma_sg_dmabuf_ops_unmap,
-	.map = vb2_dma_sg_dmabuf_ops_kmap,
 	.vmap = vb2_dma_sg_dmabuf_ops_vmap,
 	.mmap = vb2_dma_sg_dmabuf_ops_mmap,
 	.release = vb2_dma_sg_dmabuf_ops_release,
diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c
index e652f4318284..eb5d5db96552 100644
--- a/drivers/media/common/videobuf2/videobuf2-v4l2.c
+++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c
@@ -146,7 +146,7 @@ static void __copy_timestamp(struct vb2_buffer *vb, const void *pb)
 		 * and the timecode field and flag if needed.
 		 */
 		if (q->copy_timestamp)
-			vb->timestamp = v4l2_timeval_to_ns(&b->timestamp);
+			vb->timestamp = v4l2_buffer_get_timestamp(b);
 		vbuf->flags |= b->flags & V4L2_BUF_FLAG_TIMECODE;
 		if (b->flags & V4L2_BUF_FLAG_TIMECODE)
 			vbuf->timecode = b->timecode;
@@ -482,7 +482,7 @@ static void __fill_v4l2_buffer(struct vb2_buffer *vb, void *pb)
 
 	b->flags = vbuf->flags;
 	b->field = vbuf->field;
-	b->timestamp = ns_to_timeval(vb->timestamp);
+	v4l2_buffer_set_timestamp(b, vb->timestamp);
 	b->timecode = vbuf->timecode;
 	b->sequence = vbuf->sequence;
 	b->reserved2 = 0;
diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
index 4c8c96a35282..1a4f0ca87c7c 100644
--- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c
+++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
@@ -319,13 +319,6 @@ static void vb2_vmalloc_dmabuf_ops_release(struct dma_buf *dbuf)
 	vb2_vmalloc_put(dbuf->priv);
 }
 
-static void *vb2_vmalloc_dmabuf_ops_kmap(struct dma_buf *dbuf, unsigned long pgnum)
-{
-	struct vb2_vmalloc_buf *buf = dbuf->priv;
-
-	return buf->vaddr + pgnum * PAGE_SIZE;
-}
-
 static void *vb2_vmalloc_dmabuf_ops_vmap(struct dma_buf *dbuf)
 {
 	struct vb2_vmalloc_buf *buf = dbuf->priv;
@@ -344,7 +337,6 @@ static const struct dma_buf_ops vb2_vmalloc_dmabuf_ops = {
 	.detach = vb2_vmalloc_dmabuf_ops_detach,
 	.map_dma_buf = vb2_vmalloc_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_vmalloc_dmabuf_ops_unmap,
-	.map = vb2_vmalloc_dmabuf_ops_kmap,
 	.vmap = vb2_vmalloc_dmabuf_ops_vmap,
 	.mmap = vb2_vmalloc_dmabuf_ops_mmap,
 	.release = vb2_vmalloc_dmabuf_ops_release,
diff --git a/drivers/media/dvb-core/dvb_demux.c b/drivers/media/dvb-core/dvb_demux.c
index 39a2c6ccf31d..5fde1d38b3e3 100644
--- a/drivers/media/dvb-core/dvb_demux.c
+++ b/drivers/media/dvb-core/dvb_demux.c
@@ -971,6 +971,7 @@ static int dmx_section_feed_start_filtering(struct dmx_section_feed *feed)
 	dvbdmxfeed->feed.sec.secbuf = dvbdmxfeed->feed.sec.secbuf_base;
 	dvbdmxfeed->feed.sec.secbufp = 0;
 	dvbdmxfeed->feed.sec.seclen = 0;
+	dvbdmxfeed->pusi_seen = false;
 
 	if (!dvbdmx->start_feed) {
 		mutex_unlock(&dvbdmx->mutex);
diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 917fe034af37..80b6a71aa33e 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -983,8 +983,8 @@ struct i2c_client *dvb_module_probe(const char *module_name,
 	board_info->addr = addr;
 	board_info->platform_data = platform_data;
 	request_module(module_name);
-	client = i2c_new_device(adap, board_info);
-	if (client == NULL || client->dev.driver == NULL) {
+	client = i2c_new_client_device(adap, board_info);
+	if (!i2c_client_has_driver(client)) {
 		kfree(board_info);
 		return NULL;
 	}
diff --git a/drivers/media/dvb-frontends/as102_fe.c b/drivers/media/dvb-frontends/as102_fe.c
index 496ebb8176c0..bc72d954dc1f 100644
--- a/drivers/media/dvb-frontends/as102_fe.c
+++ b/drivers/media/dvb-frontends/as102_fe.c
@@ -290,7 +290,8 @@ static int as102_fe_get_frontend(struct dvb_frontend *fe,
 }
 
 static int as102_fe_get_tune_settings(struct dvb_frontend *fe,
-			struct dvb_frontend_tune_settings *settings) {
+			struct dvb_frontend_tune_settings *settings)
+{
 
 	settings->min_delay_ms = 1000;
 
diff --git a/drivers/media/dvb-frontends/au8522_decoder.c b/drivers/media/dvb-frontends/au8522_decoder.c
index c1717dde874b..8cdca051e51b 100644
--- a/drivers/media/dvb-frontends/au8522_decoder.c
+++ b/drivers/media/dvb-frontends/au8522_decoder.c
@@ -562,7 +562,7 @@ static int au8522_s_video_routing(struct v4l2_subdev *sd,
 {
 	struct au8522_state *state = to_state(sd);
 
-	switch(input) {
+	switch (input) {
 	case AU8522_COMPOSITE_CH1:
 	case AU8522_SVIDEO_CH13:
 	case AU8522_COMPOSITE_CH4_SIF:
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index d137199e13e6..b1618339eec0 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -530,8 +530,8 @@ struct dvb_frontend *cxd2820r_attach(const struct cxd2820r_config *config,
 	strscpy(board_info.type, "cxd2820r", I2C_NAME_SIZE);
 	board_info.addr = config->i2c_address;
 	board_info.platform_data = &pdata;
-	client = i2c_new_device(adapter, &board_info);
-	if (!client || !client->dev.driver)
+	client = i2c_new_client_device(adapter, &board_info);
+	if (!i2c_client_has_driver(client))
 		return NULL;
 
 	return pdata.get_dvb_frontend(client);
diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c
index 3b26f61785d8..cafb41dba861 100644
--- a/drivers/media/dvb-frontends/dib0070.c
+++ b/drivers/media/dvb-frontends/dib0070.c
@@ -189,7 +189,8 @@ static int dib0070_captrim(struct dib0070_state *state, enum frontend_tune_state
 
 		adc = dib0070_read_reg(state, 0x19);
 
-		dprintk("CAPTRIM=%hd; ADC = %hd (ADC) & %dmV\n", state->captrim, adc, (u32) adc*(u32)1800/(u32)1024);
+		dprintk("CAPTRIM=%d; ADC = %hd (ADC) & %dmV\n", state->captrim,
+			adc, (u32)adc * (u32)1800 / (u32)1024);
 
 		if (adc >= 400) {
 			adc -= 400;
@@ -200,7 +201,8 @@ static int dib0070_captrim(struct dib0070_state *state, enum frontend_tune_state
 		}
 
 		if (adc < state->adc_diff) {
-			dprintk("CAPTRIM=%hd is closer to target (%hd/%hd)\n", state->captrim, adc, state->adc_diff);
+			dprintk("CAPTRIM=%d is closer to target (%hd/%hd)\n",
+				state->captrim, adc, state->adc_diff);
 			state->adc_diff = adc;
 			state->fcaptrim = state->captrim;
 		}
@@ -364,7 +366,7 @@ static int dib0070_tune_digital(struct dvb_frontend *fe)
 	}
 
 	if (*tune_state == CT_TUNER_START) {
-		dprintk("Tuning for Band: %hd (%d kHz)\n", band, freq);
+		dprintk("Tuning for Band: %d (%d kHz)\n", band, freq);
 		if (state->current_rf != freq) {
 			u8 REFDIV;
 			u32 FBDiv, Rest, FREF, VCOF_kHz;
@@ -442,12 +444,17 @@ static int dib0070_tune_digital(struct dvb_frontend *fe)
 			dib0070_write_reg(state, 0x20,
 				0x0040 | 0x0020 | 0x0010 | 0x0008 | 0x0002 | 0x0001 | state->current_tune_table_index->tuner_enable);
 
-			dprintk("REFDIV: %hd, FREF: %d\n", REFDIV, FREF);
+			dprintk("REFDIV: %u, FREF: %d\n", REFDIV, FREF);
 			dprintk("FBDIV: %d, Rest: %d\n", FBDiv, Rest);
-			dprintk("Num: %hd, Den: %hd, SD: %hd\n", (u16) Rest, Den, (state->lo4 >> 12) & 0x1);
-			dprintk("HFDIV code: %hd\n", state->current_tune_table_index->hfdiv);
-			dprintk("VCO = %hd\n", state->current_tune_table_index->vco_band);
-			dprintk("VCOF: ((%hd*%d) << 1))\n", state->current_tune_table_index->vco_multi, freq);
+			dprintk("Num: %u, Den: %u, SD: %d\n", (u16)Rest, Den,
+				(state->lo4 >> 12) & 0x1);
+			dprintk("HFDIV code: %u\n",
+				state->current_tune_table_index->hfdiv);
+			dprintk("VCO = %u\n",
+				state->current_tune_table_index->vco_band);
+			dprintk("VCOF: ((%u*%d) << 1))\n",
+				state->current_tune_table_index->vco_multi,
+				freq);
 
 			*tune_state = CT_TUNER_STEP_0;
 		} else { /* we are already tuned to this frequency - the configuration is correct  */
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index d13d2e81f8c9..bc374750529b 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -1748,7 +1748,8 @@ static int dib0090_dc_offset_calibration(struct dib0090_state *state, enum front
 			}
 
 			dib0090_set_trim(state);
-			dprintk("BB Offset Cal, BBreg=%hd,Offset=%hd,Value Set=%hd\n", state->dc->addr, state->adc_diff, state->step);
+			dprintk("BB Offset Cal, BBreg=%u,Offset=%d,Value Set=%d\n",
+				state->dc->addr, state->adc_diff, state->step);
 
 			state->dc++;
 			if (state->dc->addr == 0)	/* done */
diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c
index e211830c9c99..97ce97789c9e 100644
--- a/drivers/media/dvb-frontends/dib7000m.c
+++ b/drivers/media/dvb-frontends/dib7000m.c
@@ -808,7 +808,7 @@ static int dib7000m_agc_startup(struct dvb_frontend *demod)
 
 			dib7000m_restart_agc(state);
 
-			dprintk("SPLIT %p: %hd\n", demod, agc_split);
+			dprintk("SPLIT %p: %u\n", demod, agc_split);
 
 			(*agc_state)++;
 			ret = 5;
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 0d22c700016d..0a7790c4bad3 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -915,7 +915,7 @@ static int dib7000p_agc_startup(struct dvb_frontend *demod)
 
 		dib7000p_restart_agc(state);
 
-		dprintk("SPLIT %p: %hd\n", demod, agc_split);
+		dprintk("SPLIT %p: %u\n", demod, agc_split);
 
 		(*agc_state)++;
 		ret = 5;
diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.c b/drivers/media/dvb-frontends/dvb_dummy_fe.c
index 4db679cb70ad..9ff1ebaa5e04 100644
--- a/drivers/media/dvb-frontends/dvb_dummy_fe.c
+++ b/drivers/media/dvb-frontends/dvb_dummy_fe.c
@@ -31,25 +31,26 @@ static int dvb_dummy_fe_read_status(struct dvb_frontend *fe,
 	return 0;
 }
 
-static int dvb_dummy_fe_read_ber(struct dvb_frontend* fe, u32* ber)
+static int dvb_dummy_fe_read_ber(struct dvb_frontend *fe, u32 *ber)
 {
 	*ber = 0;
 	return 0;
 }
 
-static int dvb_dummy_fe_read_signal_strength(struct dvb_frontend* fe, u16* strength)
+static int dvb_dummy_fe_read_signal_strength(struct dvb_frontend *fe,
+					     u16 *strength)
 {
 	*strength = 0;
 	return 0;
 }
 
-static int dvb_dummy_fe_read_snr(struct dvb_frontend* fe, u16* snr)
+static int dvb_dummy_fe_read_snr(struct dvb_frontend *fe, u16 *snr)
 {
 	*snr = 0;
 	return 0;
 }
 
-static int dvb_dummy_fe_read_ucblocks(struct dvb_frontend* fe, u32* ucblocks)
+static int dvb_dummy_fe_read_ucblocks(struct dvb_frontend *fe, u32 *ucblocks)
 {
 	*ucblocks = 0;
 	return 0;
@@ -77,12 +78,12 @@ static int dvb_dummy_fe_set_frontend(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int dvb_dummy_fe_sleep(struct dvb_frontend* fe)
+static int dvb_dummy_fe_sleep(struct dvb_frontend *fe)
 {
 	return 0;
 }
 
-static int dvb_dummy_fe_init(struct dvb_frontend* fe)
+static int dvb_dummy_fe_init(struct dvb_frontend *fe)
 {
 	return 0;
 }
@@ -99,17 +100,18 @@ static int dvb_dummy_fe_set_voltage(struct dvb_frontend *fe,
 	return 0;
 }
 
-static void dvb_dummy_fe_release(struct dvb_frontend* fe)
+static void dvb_dummy_fe_release(struct dvb_frontend *fe)
 {
-	struct dvb_dummy_fe_state* state = fe->demodulator_priv;
+	struct dvb_dummy_fe_state *state = fe->demodulator_priv;
+
 	kfree(state);
 }
 
 static const struct dvb_frontend_ops dvb_dummy_fe_ofdm_ops;
 
-struct dvb_frontend* dvb_dummy_fe_ofdm_attach(void)
+struct dvb_frontend *dvb_dummy_fe_ofdm_attach(void)
 {
-	struct dvb_dummy_fe_state* state = NULL;
+	struct dvb_dummy_fe_state *state = NULL;
 
 	/* allocate memory for the internal state */
 	state = kzalloc(sizeof(struct dvb_dummy_fe_state), GFP_KERNEL);
@@ -117,16 +119,20 @@ struct dvb_frontend* dvb_dummy_fe_ofdm_attach(void)
 		return NULL;
 
 	/* create dvb_frontend */
-	memcpy(&state->frontend.ops, &dvb_dummy_fe_ofdm_ops, sizeof(struct dvb_frontend_ops));
+	memcpy(&state->frontend.ops,
+	       &dvb_dummy_fe_ofdm_ops,
+	       sizeof(struct dvb_frontend_ops));
+
 	state->frontend.demodulator_priv = state;
 	return &state->frontend;
 }
+EXPORT_SYMBOL(dvb_dummy_fe_ofdm_attach);
 
 static const struct dvb_frontend_ops dvb_dummy_fe_qpsk_ops;
 
 struct dvb_frontend *dvb_dummy_fe_qpsk_attach(void)
 {
-	struct dvb_dummy_fe_state* state = NULL;
+	struct dvb_dummy_fe_state *state = NULL;
 
 	/* allocate memory for the internal state */
 	state = kzalloc(sizeof(struct dvb_dummy_fe_state), GFP_KERNEL);
@@ -134,16 +140,20 @@ struct dvb_frontend *dvb_dummy_fe_qpsk_attach(void)
 		return NULL;
 
 	/* create dvb_frontend */
-	memcpy(&state->frontend.ops, &dvb_dummy_fe_qpsk_ops, sizeof(struct dvb_frontend_ops));
+	memcpy(&state->frontend.ops,
+	       &dvb_dummy_fe_qpsk_ops,
+	       sizeof(struct dvb_frontend_ops));
+
 	state->frontend.demodulator_priv = state;
 	return &state->frontend;
 }
+EXPORT_SYMBOL(dvb_dummy_fe_qpsk_attach);
 
 static const struct dvb_frontend_ops dvb_dummy_fe_qam_ops;
 
 struct dvb_frontend *dvb_dummy_fe_qam_attach(void)
 {
-	struct dvb_dummy_fe_state* state = NULL;
+	struct dvb_dummy_fe_state *state = NULL;
 
 	/* allocate memory for the internal state */
 	state = kzalloc(sizeof(struct dvb_dummy_fe_state), GFP_KERNEL);
@@ -151,10 +161,14 @@ struct dvb_frontend *dvb_dummy_fe_qam_attach(void)
 		return NULL;
 
 	/* create dvb_frontend */
-	memcpy(&state->frontend.ops, &dvb_dummy_fe_qam_ops, sizeof(struct dvb_frontend_ops));
+	memcpy(&state->frontend.ops,
+	       &dvb_dummy_fe_qam_ops,
+	       sizeof(struct dvb_frontend_ops));
+
 	state->frontend.demodulator_priv = state;
 	return &state->frontend;
 }
+EXPORT_SYMBOL(dvb_dummy_fe_qam_attach);
 
 static const struct dvb_frontend_ops dvb_dummy_fe_ofdm_ops = {
 	.delsys = { SYS_DVBT },
@@ -163,13 +177,21 @@ static const struct dvb_frontend_ops dvb_dummy_fe_ofdm_ops = {
 		.frequency_min_hz	= 0,
 		.frequency_max_hz	= 863250 * kHz,
 		.frequency_stepsize_hz	= 62500,
-		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
-				FE_CAN_FEC_4_5 | FE_CAN_FEC_5_6 | FE_CAN_FEC_6_7 |
-				FE_CAN_FEC_7_8 | FE_CAN_FEC_8_9 | FE_CAN_FEC_AUTO |
-				FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
-				FE_CAN_TRANSMISSION_MODE_AUTO |
-				FE_CAN_GUARD_INTERVAL_AUTO |
-				FE_CAN_HIERARCHY_AUTO,
+		.caps = FE_CAN_FEC_1_2 |
+			FE_CAN_FEC_2_3 |
+			FE_CAN_FEC_3_4 |
+			FE_CAN_FEC_4_5 |
+			FE_CAN_FEC_5_6 |
+			FE_CAN_FEC_6_7 |
+			FE_CAN_FEC_7_8 |
+			FE_CAN_FEC_8_9 |
+			FE_CAN_FEC_AUTO |
+			FE_CAN_QAM_16 |
+			FE_CAN_QAM_64 |
+			FE_CAN_QAM_AUTO |
+			FE_CAN_TRANSMISSION_MODE_AUTO |
+			FE_CAN_GUARD_INTERVAL_AUTO |
+			FE_CAN_HIERARCHY_AUTO,
 	},
 
 	.release = dvb_dummy_fe_release,
@@ -194,11 +216,16 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qam_ops = {
 		.frequency_min_hz	=  51 * MHz,
 		.frequency_max_hz	= 858 * MHz,
 		.frequency_stepsize_hz	= 62500,
-		.symbol_rate_min	= (57840000 / 2) / 64,  /* SACLK/64 == (XIN/2)/64 */
+		/* symbol_rate_min: SACLK/64 == (XIN/2)/64 */
+		.symbol_rate_min	= (57840000 / 2) / 64,
 		.symbol_rate_max	= (57840000 / 2) / 4,   /* SACLK/4 */
-		.caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
-			FE_CAN_QAM_128 | FE_CAN_QAM_256 |
-			FE_CAN_FEC_AUTO | FE_CAN_INVERSION_AUTO
+		.caps = FE_CAN_QAM_16 |
+			FE_CAN_QAM_32 |
+			FE_CAN_QAM_64 |
+			FE_CAN_QAM_128 |
+			FE_CAN_QAM_256 |
+			FE_CAN_FEC_AUTO |
+			FE_CAN_INVERSION_AUTO
 	},
 
 	.release = dvb_dummy_fe_release,
@@ -227,8 +254,12 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qpsk_ops = {
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
-			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
-			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
+			FE_CAN_FEC_1_2 |
+			FE_CAN_FEC_2_3 |
+			FE_CAN_FEC_3_4 |
+			FE_CAN_FEC_5_6 |
+			FE_CAN_FEC_7_8 |
+			FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK
 	},
 
@@ -253,7 +284,3 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qpsk_ops = {
 MODULE_DESCRIPTION("DVB DUMMY Frontend");
 MODULE_AUTHOR("Emard");
 MODULE_LICENSE("GPL");
-
-EXPORT_SYMBOL(dvb_dummy_fe_ofdm_attach);
-EXPORT_SYMBOL(dvb_dummy_fe_qam_attach);
-EXPORT_SYMBOL(dvb_dummy_fe_qpsk_attach);
diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.h b/drivers/media/dvb-frontends/dvb_dummy_fe.h
index 526fabd7751f..463abf5ebd56 100644
--- a/drivers/media/dvb-frontends/dvb_dummy_fe.h
+++ b/drivers/media/dvb-frontends/dvb_dummy_fe.h
@@ -12,23 +12,23 @@
 #include <media/dvb_frontend.h>
 
 #if IS_REACHABLE(CONFIG_DVB_DUMMY_FE)
-extern struct dvb_frontend* dvb_dummy_fe_ofdm_attach(void);
-extern struct dvb_frontend* dvb_dummy_fe_qpsk_attach(void);
-extern struct dvb_frontend* dvb_dummy_fe_qam_attach(void);
+struct dvb_frontend *dvb_dummy_fe_ofdm_attach(void);
+struct dvb_frontend *dvb_dummy_fe_qpsk_attach(void);
+struct dvb_frontend *dvb_dummy_fe_qam_attach(void);
 #else
 static inline struct dvb_frontend *dvb_dummy_fe_ofdm_attach(void)
 {
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
 }
 static inline struct dvb_frontend *dvb_dummy_fe_qpsk_attach(void)
 {
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
 }
 static inline struct dvb_frontend *dvb_dummy_fe_qam_attach(void)
 {
-	printk(KERN_WARNING "%s: driver disabled by Kconfig\n", __func__);
+	pr_warn("%s: driver disabled by Kconfig\n", __func__);
 	return NULL;
 }
 #endif /* CONFIG_DVB_DUMMY_FE */
diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c
index 651c8aa75e17..da3a8c5e18d8 100644
--- a/drivers/media/dvb-frontends/lgdt330x.c
+++ b/drivers/media/dvb-frontends/lgdt330x.c
@@ -922,8 +922,8 @@ struct dvb_frontend *lgdt330x_attach(const struct lgdt330x_config *_config,
 	strscpy(board_info.type, "lgdt330x", sizeof(board_info.type));
 	board_info.addr = demod_address;
 	board_info.platform_data = &config;
-	client = i2c_new_device(i2c, &board_info);
-	if (!client || !client->dev.driver)
+	client = i2c_new_client_device(i2c, &board_info);
+	if (!i2c_client_has_driver(client))
 		return NULL;
 
 	return lgdt330x_get_dvb_frontend(client);
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index 3a367a585084..c96f05ff5f2f 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -1277,8 +1277,8 @@ struct dvb_frontend *m88ds3103_attach(const struct m88ds3103_config *cfg,
 	strscpy(board_info.type, "m88ds3103", I2C_NAME_SIZE);
 	board_info.addr = cfg->i2c_addr;
 	board_info.platform_data = &pdata;
-	client = i2c_new_device(i2c, &board_info);
-	if (!client || !client->dev.driver)
+	client = i2c_new_client_device(i2c, &board_info);
+	if (!i2c_client_has_driver(client))
 		return NULL;
 
 	*tuner_i2c_adapter = pdata.get_i2c_adapter(client);
diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c
index 6c24d6d0d4c9..234607b02edb 100644
--- a/drivers/media/dvb-frontends/ts2020.c
+++ b/drivers/media/dvb-frontends/ts2020.c
@@ -519,8 +519,8 @@ struct dvb_frontend *ts2020_attach(struct dvb_frontend *fe,
 	strscpy(board_info.type, "ts2020", I2C_NAME_SIZE);
 	board_info.addr = config->tuner_address;
 	board_info.platform_data = &pdata;
-	client = i2c_new_device(i2c, &board_info);
-	if (!client || !client->dev.driver)
+	client = i2c_new_client_device(i2c, &board_info);
+	if (!i2c_client_has_driver(client))
 		return NULL;
 
 	return fe;
diff --git a/drivers/media/i2c/adv748x/adv748x.h b/drivers/media/i2c/adv748x/adv748x.h
index 5042f9e94aee..fccb388ce179 100644
--- a/drivers/media/i2c/adv748x/adv748x.h
+++ b/drivers/media/i2c/adv748x/adv748x.h
@@ -394,10 +394,10 @@ int adv748x_write_block(struct adv748x_state *state, int client_page,
 
 #define io_read(s, r) adv748x_read(s, ADV748X_PAGE_IO, r)
 #define io_write(s, r, v) adv748x_write(s, ADV748X_PAGE_IO, r, v)
-#define io_clrset(s, r, m, v) io_write(s, r, (io_read(s, r) & ~m) | v)
+#define io_clrset(s, r, m, v) io_write(s, r, (io_read(s, r) & ~(m)) | (v))
 
 #define hdmi_read(s, r) adv748x_read(s, ADV748X_PAGE_HDMI, r)
-#define hdmi_read16(s, r, m) (((hdmi_read(s, r) << 8) | hdmi_read(s, r+1)) & m)
+#define hdmi_read16(s, r, m) (((hdmi_read(s, r) << 8) | hdmi_read(s, (r)+1)) & (m))
 #define hdmi_write(s, r, v) adv748x_write(s, ADV748X_PAGE_HDMI, r, v)
 
 #define repeater_read(s, r) adv748x_read(s, ADV748X_PAGE_REPEATER, r)
@@ -405,11 +405,11 @@ int adv748x_write_block(struct adv748x_state *state, int client_page,
 
 #define sdp_read(s, r) adv748x_read(s, ADV748X_PAGE_SDP, r)
 #define sdp_write(s, r, v) adv748x_write(s, ADV748X_PAGE_SDP, r, v)
-#define sdp_clrset(s, r, m, v) sdp_write(s, r, (sdp_read(s, r) & ~m) | v)
+#define sdp_clrset(s, r, m, v) sdp_write(s, r, (sdp_read(s, r) & ~(m)) | (v))
 
 #define cp_read(s, r) adv748x_read(s, ADV748X_PAGE_CP, r)
 #define cp_write(s, r, v) adv748x_write(s, ADV748X_PAGE_CP, r, v)
-#define cp_clrset(s, r, m, v) cp_write(s, r, (cp_read(s, r) & ~m) | v)
+#define cp_clrset(s, r, m, v) cp_write(s, r, (cp_read(s, r) & ~(m)) | (v))
 
 #define tx_read(t, r) adv748x_read(t->state, t->page, r)
 #define tx_write(t, r, v) adv748x_write(t->state, t->page, r, v)
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index 2dedd6ebb236..09004d928d11 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -1503,23 +1503,14 @@ static void adv76xx_fill_optional_dv_timings_fields(struct v4l2_subdev *sd,
 
 static unsigned int adv7604_read_hdmi_pixelclock(struct v4l2_subdev *sd)
 {
-	unsigned int freq;
 	int a, b;
 
 	a = hdmi_read(sd, 0x06);
 	b = hdmi_read(sd, 0x3b);
 	if (a < 0 || b < 0)
 		return 0;
-	freq =  a * 1000000 + ((b & 0x30) >> 4) * 250000;
 
-	if (is_hdmi(sd)) {
-		/* adjust for deep color mode */
-		unsigned bits_per_channel = ((hdmi_read(sd, 0x0b) & 0x60) >> 4) + 8;
-
-		freq = freq * 8 / bits_per_channel;
-	}
-
-	return freq;
+	return a * 1000000 + ((b & 0x30) >> 4) * 250000;
 }
 
 static unsigned int adv7611_read_hdmi_pixelclock(struct v4l2_subdev *sd)
@@ -1530,9 +1521,28 @@ static unsigned int adv7611_read_hdmi_pixelclock(struct v4l2_subdev *sd)
 	b = hdmi_read(sd, 0x52);
 	if (a < 0 || b < 0)
 		return 0;
+
 	return ((a << 1) | (b >> 7)) * 1000000 + (b & 0x7f) * 1000000 / 128;
 }
 
+static unsigned int adv76xx_read_hdmi_pixelclock(struct v4l2_subdev *sd)
+{
+	struct adv76xx_state *state = to_state(sd);
+	const struct adv76xx_chip_info *info = state->info;
+	unsigned int freq, bits_per_channel, pixelrepetition;
+
+	freq = info->read_hdmi_pixelclock(sd);
+	if (is_hdmi(sd)) {
+		/* adjust for deep color mode and pixel repetition */
+		bits_per_channel = ((hdmi_read(sd, 0x0b) & 0x60) >> 4) + 8;
+		pixelrepetition = (hdmi_read(sd, 0x05) & 0x0f) + 1;
+
+		freq = freq * 8 / bits_per_channel / pixelrepetition;
+	}
+
+	return freq;
+}
+
 static int adv76xx_query_dv_timings(struct v4l2_subdev *sd,
 			struct v4l2_dv_timings *timings)
 {
@@ -1579,7 +1589,7 @@ static int adv76xx_query_dv_timings(struct v4l2_subdev *sd,
 
 		bt->width = w;
 		bt->height = h;
-		bt->pixelclock = info->read_hdmi_pixelclock(sd);
+		bt->pixelclock = adv76xx_read_hdmi_pixelclock(sd);
 		bt->hfrontporch = hdmi_read16(sd, 0x20, info->hfrontporch_mask);
 		bt->hsync = hdmi_read16(sd, 0x22, info->hsync_mask);
 		bt->hbackporch = hdmi_read16(sd, 0x24, info->hbackporch_mask);
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 4b9b98cf6674..5bd3ae82992f 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -428,10 +428,12 @@ static int mt9v032_enum_mbus_code(struct v4l2_subdev *subdev,
 				  struct v4l2_subdev_pad_config *cfg,
 				  struct v4l2_subdev_mbus_code_enum *code)
 {
+	struct mt9v032 *mt9v032 = to_mt9v032(subdev);
+
 	if (code->index > 0)
 		return -EINVAL;
 
-	code->code = MEDIA_BUS_FMT_SGRBG10_1X10;
+	code->code = mt9v032->format.code;
 	return 0;
 }
 
@@ -439,7 +441,11 @@ static int mt9v032_enum_frame_size(struct v4l2_subdev *subdev,
 				   struct v4l2_subdev_pad_config *cfg,
 				   struct v4l2_subdev_frame_size_enum *fse)
 {
-	if (fse->index >= 3 || fse->code != MEDIA_BUS_FMT_SGRBG10_1X10)
+	struct mt9v032 *mt9v032 = to_mt9v032(subdev);
+
+	if (fse->index >= 3)
+		return -EINVAL;
+	if (mt9v032->format.code != fse->code)
 		return -EINVAL;
 
 	fse->min_width = MT9V032_WINDOW_WIDTH_DEF / (1 << fse->index);
diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index bb41bea950ac..61ae6a0d5679 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -103,7 +103,7 @@
 #define MT9V111_MAX_CLKIN				27000000
 
 /* The default sensor configuration at startup time. */
-static struct v4l2_mbus_framefmt mt9v111_def_fmt = {
+static const struct v4l2_mbus_framefmt mt9v111_def_fmt = {
 	.width		= 640,
 	.height		= 480,
 	.code		= MEDIA_BUS_FMT_UYVY8_2X8,
diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 5e495c833d32..854031f0b64a 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -189,6 +189,7 @@ struct ov5640_mode_info {
 	u32 vtot;
 	const struct reg_value *reg_data;
 	u32 reg_data_size;
+	u32 max_fps;
 };
 
 struct ov5640_ctrls {
@@ -544,6 +545,7 @@ static const struct ov5640_mode_info ov5640_mode_init_data = {
 	0, SUBSAMPLING, 640, 1896, 480, 984,
 	ov5640_init_setting_30fps_VGA,
 	ARRAY_SIZE(ov5640_init_setting_30fps_VGA),
+	OV5640_30_FPS,
 };
 
 static const struct ov5640_mode_info
@@ -551,39 +553,48 @@ ov5640_mode_data[OV5640_NUM_MODES] = {
 	{OV5640_MODE_QCIF_176_144, SUBSAMPLING,
 	 176, 1896, 144, 984,
 	 ov5640_setting_QCIF_176_144,
-	 ARRAY_SIZE(ov5640_setting_QCIF_176_144)},
+	 ARRAY_SIZE(ov5640_setting_QCIF_176_144),
+	 OV5640_30_FPS},
 	{OV5640_MODE_QVGA_320_240, SUBSAMPLING,
 	 320, 1896, 240, 984,
 	 ov5640_setting_QVGA_320_240,
-	 ARRAY_SIZE(ov5640_setting_QVGA_320_240)},
+	 ARRAY_SIZE(ov5640_setting_QVGA_320_240),
+	 OV5640_30_FPS},
 	{OV5640_MODE_VGA_640_480, SUBSAMPLING,
 	 640, 1896, 480, 1080,
 	 ov5640_setting_VGA_640_480,
-	 ARRAY_SIZE(ov5640_setting_VGA_640_480)},
+	 ARRAY_SIZE(ov5640_setting_VGA_640_480),
+	 OV5640_60_FPS},
 	{OV5640_MODE_NTSC_720_480, SUBSAMPLING,
 	 720, 1896, 480, 984,
 	 ov5640_setting_NTSC_720_480,
-	 ARRAY_SIZE(ov5640_setting_NTSC_720_480)},
+	 ARRAY_SIZE(ov5640_setting_NTSC_720_480),
+	OV5640_30_FPS},
 	{OV5640_MODE_PAL_720_576, SUBSAMPLING,
 	 720, 1896, 576, 984,
 	 ov5640_setting_PAL_720_576,
-	 ARRAY_SIZE(ov5640_setting_PAL_720_576)},
+	 ARRAY_SIZE(ov5640_setting_PAL_720_576),
+	 OV5640_30_FPS},
 	{OV5640_MODE_XGA_1024_768, SUBSAMPLING,
 	 1024, 1896, 768, 1080,
 	 ov5640_setting_XGA_1024_768,
-	 ARRAY_SIZE(ov5640_setting_XGA_1024_768)},
+	 ARRAY_SIZE(ov5640_setting_XGA_1024_768),
+	 OV5640_30_FPS},
 	{OV5640_MODE_720P_1280_720, SUBSAMPLING,
 	 1280, 1892, 720, 740,
 	 ov5640_setting_720P_1280_720,
-	 ARRAY_SIZE(ov5640_setting_720P_1280_720)},
+	 ARRAY_SIZE(ov5640_setting_720P_1280_720),
+	 OV5640_30_FPS},
 	{OV5640_MODE_1080P_1920_1080, SCALING,
 	 1920, 2500, 1080, 1120,
 	 ov5640_setting_1080P_1920_1080,
-	 ARRAY_SIZE(ov5640_setting_1080P_1920_1080)},
+	 ARRAY_SIZE(ov5640_setting_1080P_1920_1080),
+	 OV5640_30_FPS},
 	{OV5640_MODE_QSXGA_2592_1944, SCALING,
 	 2592, 2844, 1944, 1968,
 	 ov5640_setting_QSXGA_2592_1944,
-	 ARRAY_SIZE(ov5640_setting_QSXGA_2592_1944)},
+	 ARRAY_SIZE(ov5640_setting_QSXGA_2592_1944),
+	 OV5640_15_FPS},
 };
 
 static int ov5640_init_slave_id(struct ov5640_dev *sensor)
@@ -874,7 +885,7 @@ static unsigned long ov5640_calc_sys_clk(struct ov5640_dev *sensor,
 			 * We have reached the maximum allowed PLL1 output,
 			 * increase sysdiv.
 			 */
-			if (!rate)
+			if (!_rate)
 				break;
 
 			/*
@@ -1606,14 +1617,8 @@ ov5640_find_mode(struct ov5640_dev *sensor, enum ov5640_frame_rate fr,
 	    (!nearest && (mode->hact != width || mode->vact != height)))
 		return NULL;
 
-	/* Only 640x480 can operate at 60fps (for now) */
-	if (fr == OV5640_60_FPS &&
-	    !(mode->hact == 640 && mode->vact == 480))
-		return NULL;
-
-	/* 2592x1944 only works at 15fps max */
-	if ((mode->hact == 2592 && mode->vact == 1944) &&
-	    fr > OV5640_15_FPS)
+	/* Check to see if the current mode exceeds the max frame rate */
+	if (ov5640_framerates[fr] > ov5640_framerates[mode->max_fps])
 		return NULL;
 
 	return mode;
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 84f9771b5fed..a80d7701b519 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -413,21 +413,14 @@ static int smiapp_set_ctrl(struct v4l2_ctrl *ctrl)
 	struct smiapp_sensor *sensor =
 		container_of(ctrl->handler, struct smiapp_subdev, ctrl_handler)
 			->sensor;
+	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
+	int pm_status;
 	u32 orient = 0;
+	unsigned int i;
 	int exposure;
 	int rval;
 
 	switch (ctrl->id) {
-	case V4L2_CID_ANALOGUE_GAIN:
-		return smiapp_write(
-			sensor,
-			SMIAPP_REG_U16_ANALOGUE_GAIN_CODE_GLOBAL, ctrl->val);
-
-	case V4L2_CID_EXPOSURE:
-		return smiapp_write(
-			sensor,
-			SMIAPP_REG_U16_COARSE_INTEGRATION_TIME, ctrl->val);
-
 	case V4L2_CID_HFLIP:
 	case V4L2_CID_VFLIP:
 		if (sensor->streaming)
@@ -440,15 +433,10 @@ static int smiapp_set_ctrl(struct v4l2_ctrl *ctrl)
 			orient |= SMIAPP_IMAGE_ORIENTATION_VFLIP;
 
 		orient ^= sensor->hvflip_inv_mask;
-		rval = smiapp_write(sensor, SMIAPP_REG_U8_IMAGE_ORIENTATION,
-				    orient);
-		if (rval < 0)
-			return rval;
 
 		smiapp_update_mbus_formats(sensor);
 
-		return 0;
-
+		break;
 	case V4L2_CID_VBLANK:
 		exposure = sensor->exposure->val;
 
@@ -461,59 +449,105 @@ static int smiapp_set_ctrl(struct v4l2_ctrl *ctrl)
 				return rval;
 		}
 
-		return smiapp_write(
-			sensor, SMIAPP_REG_U16_FRAME_LENGTH_LINES,
-			sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height
-			+ ctrl->val);
-
-	case V4L2_CID_HBLANK:
-		return smiapp_write(
-			sensor, SMIAPP_REG_U16_LINE_LENGTH_PCK,
-			sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width
-			+ ctrl->val);
-
+		break;
 	case V4L2_CID_LINK_FREQ:
 		if (sensor->streaming)
 			return -EBUSY;
 
-		return smiapp_pll_update(sensor);
-
-	case V4L2_CID_TEST_PATTERN: {
-		unsigned int i;
+		rval = smiapp_pll_update(sensor);
+		if (rval)
+			return rval;
 
+		return 0;
+	case V4L2_CID_TEST_PATTERN:
 		for (i = 0; i < ARRAY_SIZE(sensor->test_data); i++)
 			v4l2_ctrl_activate(
 				sensor->test_data[i],
 				ctrl->val ==
 				V4L2_SMIAPP_TEST_PATTERN_MODE_SOLID_COLOUR);
 
-		return smiapp_write(
-			sensor, SMIAPP_REG_U16_TEST_PATTERN_MODE, ctrl->val);
+		break;
 	}
 
+	pm_runtime_get_noresume(&client->dev);
+	pm_status = pm_runtime_get_if_in_use(&client->dev);
+	pm_runtime_put_noidle(&client->dev);
+	if (!pm_status)
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_ANALOGUE_GAIN:
+		rval = smiapp_write(
+			sensor,
+			SMIAPP_REG_U16_ANALOGUE_GAIN_CODE_GLOBAL, ctrl->val);
+
+		break;
+	case V4L2_CID_EXPOSURE:
+		rval = smiapp_write(
+			sensor,
+			SMIAPP_REG_U16_COARSE_INTEGRATION_TIME, ctrl->val);
+
+		break;
+	case V4L2_CID_HFLIP:
+	case V4L2_CID_VFLIP:
+		rval = smiapp_write(sensor, SMIAPP_REG_U8_IMAGE_ORIENTATION,
+				    orient);
+
+		break;
+	case V4L2_CID_VBLANK:
+		rval = smiapp_write(
+			sensor, SMIAPP_REG_U16_FRAME_LENGTH_LINES,
+			sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].height
+			+ ctrl->val);
+
+		break;
+	case V4L2_CID_HBLANK:
+		rval = smiapp_write(
+			sensor, SMIAPP_REG_U16_LINE_LENGTH_PCK,
+			sensor->pixel_array->crop[SMIAPP_PA_PAD_SRC].width
+			+ ctrl->val);
+
+		break;
+	case V4L2_CID_TEST_PATTERN:
+		rval = smiapp_write(
+			sensor, SMIAPP_REG_U16_TEST_PATTERN_MODE, ctrl->val);
+
+		break;
 	case V4L2_CID_TEST_PATTERN_RED:
-		return smiapp_write(
+		rval = smiapp_write(
 			sensor, SMIAPP_REG_U16_TEST_DATA_RED, ctrl->val);
 
+		break;
 	case V4L2_CID_TEST_PATTERN_GREENR:
-		return smiapp_write(
+		rval = smiapp_write(
 			sensor, SMIAPP_REG_U16_TEST_DATA_GREENR, ctrl->val);
 
+		break;
 	case V4L2_CID_TEST_PATTERN_BLUE:
-		return smiapp_write(
+		rval = smiapp_write(
 			sensor, SMIAPP_REG_U16_TEST_DATA_BLUE, ctrl->val);
 
+		break;
 	case V4L2_CID_TEST_PATTERN_GREENB:
-		return smiapp_write(
+		rval = smiapp_write(
 			sensor, SMIAPP_REG_U16_TEST_DATA_GREENB, ctrl->val);
 
+		break;
 	case V4L2_CID_PIXEL_RATE:
 		/* For v4l2_ctrl_s_ctrl_int64() used internally. */
-		return 0;
+		rval = 0;
 
+		break;
 	default:
-		return -EINVAL;
+		rval = -EINVAL;
 	}
+
+	if (pm_status > 0) {
+		pm_runtime_mark_last_busy(&client->dev);
+		pm_runtime_put_autosuspend(&client->dev);
+	}
+
+	return rval;
 }
 
 static const struct v4l2_ctrl_ops smiapp_ctrl_ops = {
@@ -1184,10 +1218,6 @@ static int smiapp_power_on(struct device *dev)
 	sleep = SMIAPP_RESET_DELAY(sensor->hwcfg->ext_clk);
 	usleep_range(sleep, sleep);
 
-	mutex_lock(&sensor->mutex);
-
-	sensor->active = true;
-
 	/*
 	 * Failures to respond to the address change command have been noticed.
 	 * Those failures seem to be caused by the sensor requiring a longer
@@ -1270,24 +1300,9 @@ static int smiapp_power_on(struct device *dev)
 		goto out_cci_addr_fail;
 	}
 
-	/* Are we still initialising...? If not, proceed with control setup. */
-	if (sensor->pixel_array) {
-		rval = __v4l2_ctrl_handler_setup(
-			&sensor->pixel_array->ctrl_handler);
-		if (rval)
-			goto out_cci_addr_fail;
-
-		rval = __v4l2_ctrl_handler_setup(&sensor->src->ctrl_handler);
-		if (rval)
-			goto out_cci_addr_fail;
-	}
-
-	mutex_unlock(&sensor->mutex);
-
 	return 0;
 
 out_cci_addr_fail:
-	mutex_unlock(&sensor->mutex);
 	gpiod_set_value(sensor->xshutdown, 0);
 	clk_disable_unprepare(sensor->ext_clk);
 
@@ -1305,8 +1320,6 @@ static int smiapp_power_off(struct device *dev)
 	struct smiapp_sensor *sensor =
 		container_of(ssd, struct smiapp_sensor, ssds[0]);
 
-	mutex_lock(&sensor->mutex);
-
 	/*
 	 * Currently power/clock to lens are enable/disabled separately
 	 * but they are essentially the same signals. So if the sensor is
@@ -1319,10 +1332,6 @@ static int smiapp_power_off(struct device *dev)
 			     SMIAPP_REG_U8_SOFTWARE_RESET,
 			     SMIAPP_SOFTWARE_RESET);
 
-	sensor->active = false;
-
-	mutex_unlock(&sensor->mutex);
-
 	gpiod_set_value(sensor->xshutdown, 0);
 	clk_disable_unprepare(sensor->ext_clk);
 	usleep_range(5000, 5000);
@@ -1507,6 +1516,30 @@ out:
  * V4L2 subdev video operations
  */
 
+static int smiapp_pm_get_init(struct smiapp_sensor *sensor)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&sensor->src->sd);
+	int rval;
+
+	rval = pm_runtime_get_sync(&client->dev);
+	if (rval < 0) {
+		if (rval != -EBUSY && rval != -EAGAIN)
+			pm_runtime_set_active(&client->dev);
+		pm_runtime_put_noidle(&client->dev);
+
+		return rval;
+	} else if (!rval) {
+		rval = v4l2_ctrl_handler_setup(&sensor->pixel_array->
+					       ctrl_handler);
+		if (rval)
+			return rval;
+
+		return v4l2_ctrl_handler_setup(&sensor->src->ctrl_handler);
+	}
+
+	return 0;
+}
+
 static int smiapp_set_stream(struct v4l2_subdev *subdev, int enable)
 {
 	struct smiapp_sensor *sensor = to_smiapp_sensor(subdev);
@@ -1516,22 +1549,23 @@ static int smiapp_set_stream(struct v4l2_subdev *subdev, int enable)
 	if (sensor->streaming == enable)
 		return 0;
 
-	if (enable) {
-		rval = pm_runtime_get_sync(&client->dev);
-		if (rval < 0) {
-			if (rval != -EBUSY && rval != -EAGAIN)
-				pm_runtime_set_active(&client->dev);
-			pm_runtime_put(&client->dev);
-			return rval;
-		}
+	if (!enable) {
+		smiapp_stop_streaming(sensor);
+		sensor->streaming = false;
+		pm_runtime_mark_last_busy(&client->dev);
+		pm_runtime_put_autosuspend(&client->dev);
 
-		sensor->streaming = true;
+		return 0;
+	}
 
-		rval = smiapp_start_streaming(sensor);
-		if (rval < 0)
-			sensor->streaming = false;
-	} else {
-		rval = smiapp_stop_streaming(sensor);
+	rval = smiapp_pm_get_init(sensor);
+	if (rval)
+		return rval;
+
+	sensor->streaming = true;
+
+	rval = smiapp_start_streaming(sensor);
+	if (rval < 0) {
 		sensor->streaming = false;
 		pm_runtime_mark_last_busy(&client->dev);
 		pm_runtime_put_autosuspend(&client->dev);
@@ -2291,13 +2325,9 @@ smiapp_sysfs_nvm_read(struct device *dev, struct device_attribute *attr,
 	if (!sensor->dev_init_done)
 		return -EBUSY;
 
-	rval = pm_runtime_get_sync(&client->dev);
-	if (rval < 0) {
-		if (rval != -EBUSY && rval != -EAGAIN)
-			pm_runtime_set_active(&client->dev);
-		pm_runtime_put_noidle(&client->dev);
+	rval = smiapp_pm_get_init(sensor);
+	if (rval < 0)
 		return -ENODEV;
-	}
 
 	rval = smiapp_read_nvm(sensor, buf, PAGE_SIZE);
 	if (rval < 0) {
diff --git a/drivers/media/i2c/smiapp/smiapp-regs.c b/drivers/media/i2c/smiapp/smiapp-regs.c
index 0470e47c2f7a..ce8c1d47fbf0 100644
--- a/drivers/media/i2c/smiapp/smiapp-regs.c
+++ b/drivers/media/i2c/smiapp/smiapp-regs.c
@@ -223,9 +223,6 @@ int smiapp_write_no_quirk(struct smiapp_sensor *sensor, u32 reg, u32 val)
 	     len != SMIAPP_REG_32BIT) || flags)
 		return -EINVAL;
 
-	if (!sensor->active)
-		return 0;
-
 	msg.addr = client->addr;
 	msg.flags = 0; /* Write */
 	msg.len = 2 + len;
diff --git a/drivers/media/i2c/smiapp/smiapp.h b/drivers/media/i2c/smiapp/smiapp.h
index 3ab874a5deba..4837d80dc453 100644
--- a/drivers/media/i2c/smiapp/smiapp.h
+++ b/drivers/media/i2c/smiapp/smiapp.h
@@ -198,7 +198,6 @@ struct smiapp_sensor {
 
 	u8 hvflip_inv_mask; /* H/VFLIP inversion due to sensor orientation */
 	u8 frame_skip;
-	bool active; /* is the sensor powered on? */
 	u16 embedded_start; /* embedded data start line */
 	u16 embedded_end;
 	u16 image_start; /* image data start line */
diff --git a/drivers/media/pci/bt8xx/bttv-input.c b/drivers/media/pci/bt8xx/bttv-input.c
index 492bc85c2700..41226f1d0e5b 100644
--- a/drivers/media/pci/bt8xx/bttv-input.c
+++ b/drivers/media/pci/bt8xx/bttv-input.c
@@ -386,7 +386,7 @@ void init_bttv_i2c_ir(struct bttv *btv)
 
 	if (btv->init_data.name) {
 		info.platform_data = &btv->init_data;
-		i2c_dev = i2c_new_device(&btv->c.i2c_adap, &info);
+		i2c_dev = i2c_new_client_device(&btv->c.i2c_adap, &info);
 	} else {
 		/*
 		 * The external IR receiver is at i2c address 0x34 (0x35 for
@@ -396,9 +396,9 @@ void init_bttv_i2c_ir(struct bttv *btv)
 		 * internal.
 		 * That's why we probe 0x1a (~0x34) first. CB
 		 */
-		i2c_dev = i2c_new_probed_device(&btv->c.i2c_adap, &info, addr_list, NULL);
+		i2c_dev = i2c_new_scanned_device(&btv->c.i2c_adap, &info, addr_list, NULL);
 	}
-	if (NULL == i2c_dev)
+	if (IS_ERR(i2c_dev))
 		return;
 
 #if defined(CONFIG_MODULES) && defined(MODULE)
diff --git a/drivers/media/pci/cobalt/cobalt-alsa-pcm.c b/drivers/media/pci/cobalt/cobalt-alsa-pcm.c
index 38d00935a292..9e7504e3cfd8 100644
--- a/drivers/media/pci/cobalt/cobalt-alsa-pcm.c
+++ b/drivers/media/pci/cobalt/cobalt-alsa-pcm.c
@@ -9,7 +9,6 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/vmalloc.h>
 #include <linux/delay.h>
 
 #include <media/v4l2-device.h>
@@ -238,54 +237,6 @@ static int snd_cobalt_pcm_capture_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_cobalt_pcm_ioctl(struct snd_pcm_substream *substream,
-		     unsigned int cmd, void *arg)
-{
-	return snd_pcm_lib_ioctl(substream, cmd, arg);
-}
-
-
-static int snd_pcm_alloc_vmalloc_buffer(struct snd_pcm_substream *subs,
-					size_t size)
-{
-	struct snd_pcm_runtime *runtime = subs->runtime;
-
-	dprintk("Allocating vbuffer\n");
-	if (runtime->dma_area) {
-		if (runtime->dma_bytes > size)
-			return 0;
-
-		vfree(runtime->dma_area);
-	}
-	runtime->dma_area = vmalloc(size);
-	if (!runtime->dma_area)
-		return -ENOMEM;
-
-	runtime->dma_bytes = size;
-
-	return 0;
-}
-
-static int snd_cobalt_pcm_hw_params(struct snd_pcm_substream *substream,
-			 struct snd_pcm_hw_params *params)
-{
-	dprintk("%s called\n", __func__);
-
-	return snd_pcm_alloc_vmalloc_buffer(substream,
-					   params_buffer_bytes(params));
-}
-
-static int snd_cobalt_pcm_hw_free(struct snd_pcm_substream *substream)
-{
-	if (substream->runtime->dma_area) {
-		dprintk("freeing pcm capture region\n");
-		vfree(substream->runtime->dma_area);
-		substream->runtime->dma_area = NULL;
-	}
-
-	return 0;
-}
-
 static int snd_cobalt_pcm_prepare(struct snd_pcm_substream *substream)
 {
 	struct snd_cobalt_card *cobsc = snd_pcm_substream_chip(substream);
@@ -490,36 +441,20 @@ snd_pcm_uframes_t snd_cobalt_pcm_pb_pointer(struct snd_pcm_substream *substream)
 	       substream->runtime->buffer_size;
 }
 
-static struct page *snd_pcm_get_vmalloc_page(struct snd_pcm_substream *subs,
-					     unsigned long offset)
-{
-	void *pageptr = subs->runtime->dma_area + offset;
-
-	return vmalloc_to_page(pageptr);
-}
-
 static const struct snd_pcm_ops snd_cobalt_pcm_capture_ops = {
 	.open		= snd_cobalt_pcm_capture_open,
 	.close		= snd_cobalt_pcm_capture_close,
-	.ioctl		= snd_cobalt_pcm_ioctl,
-	.hw_params	= snd_cobalt_pcm_hw_params,
-	.hw_free	= snd_cobalt_pcm_hw_free,
 	.prepare	= snd_cobalt_pcm_prepare,
 	.trigger	= snd_cobalt_pcm_trigger,
 	.pointer	= snd_cobalt_pcm_pointer,
-	.page		= snd_pcm_get_vmalloc_page,
 };
 
 static const struct snd_pcm_ops snd_cobalt_pcm_playback_ops = {
 	.open		= snd_cobalt_pcm_playback_open,
 	.close		= snd_cobalt_pcm_playback_close,
-	.ioctl		= snd_cobalt_pcm_ioctl,
-	.hw_params	= snd_cobalt_pcm_hw_params,
-	.hw_free	= snd_cobalt_pcm_hw_free,
 	.prepare	= snd_cobalt_pcm_pb_prepare,
 	.trigger	= snd_cobalt_pcm_pb_trigger,
 	.pointer	= snd_cobalt_pcm_pb_pointer,
-	.page		= snd_pcm_get_vmalloc_page,
 };
 
 int snd_cobalt_pcm_create(struct snd_cobalt_card *cobsc)
@@ -555,6 +490,8 @@ int snd_cobalt_pcm_create(struct snd_cobalt_card *cobsc)
 
 		snd_pcm_set_ops(sp, SNDRV_PCM_STREAM_CAPTURE,
 				&snd_cobalt_pcm_capture_ops);
+		snd_pcm_set_managed_buffer_all(sp, SNDRV_DMA_TYPE_VMALLOC,
+					       NULL, 0, 0);
 		sp->info_flags = 0;
 		sp->private_data = cobsc;
 		strscpy(sp->name, "cobalt", sizeof(sp->name));
@@ -579,6 +516,8 @@ int snd_cobalt_pcm_create(struct snd_cobalt_card *cobsc)
 
 		snd_pcm_set_ops(sp, SNDRV_PCM_STREAM_PLAYBACK,
 				&snd_cobalt_pcm_playback_ops);
+		snd_pcm_set_managed_buffer_all(sp, SNDRV_DMA_TYPE_VMALLOC,
+					       NULL, 0, 0);
 		sp->info_flags = 0;
 		sp->private_data = cobsc;
 		strscpy(sp->name, "cobalt", sizeof(sp->name));
diff --git a/drivers/media/pci/cx18/cx18-alsa-pcm.c b/drivers/media/pci/cx18/cx18-alsa-pcm.c
index 13f858c41836..bed28b4b41f7 100644
--- a/drivers/media/pci/cx18/cx18-alsa-pcm.c
+++ b/drivers/media/pci/cx18/cx18-alsa-pcm.c
@@ -11,7 +11,6 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/vmalloc.h>
 
 #include <media/v4l2-device.h>
 
@@ -201,67 +200,6 @@ static int snd_cx18_pcm_capture_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_cx18_pcm_ioctl(struct snd_pcm_substream *substream,
-		     unsigned int cmd, void *arg)
-{
-	struct snd_cx18_card *cxsc = snd_pcm_substream_chip(substream);
-	int ret;
-
-	snd_cx18_lock(cxsc);
-	ret = snd_pcm_lib_ioctl(substream, cmd, arg);
-	snd_cx18_unlock(cxsc);
-	return ret;
-}
-
-
-static int snd_pcm_alloc_vmalloc_buffer(struct snd_pcm_substream *subs,
-					size_t size)
-{
-	struct snd_pcm_runtime *runtime = subs->runtime;
-
-	dprintk("Allocating vbuffer\n");
-	if (runtime->dma_area) {
-		if (runtime->dma_bytes > size)
-			return 0;
-
-		vfree(runtime->dma_area);
-	}
-	runtime->dma_area = vmalloc(size);
-	if (!runtime->dma_area)
-		return -ENOMEM;
-
-	runtime->dma_bytes = size;
-
-	return 0;
-}
-
-static int snd_cx18_pcm_hw_params(struct snd_pcm_substream *substream,
-			 struct snd_pcm_hw_params *params)
-{
-	dprintk("%s called\n", __func__);
-
-	return snd_pcm_alloc_vmalloc_buffer(substream,
-					   params_buffer_bytes(params));
-}
-
-static int snd_cx18_pcm_hw_free(struct snd_pcm_substream *substream)
-{
-	struct snd_cx18_card *cxsc = snd_pcm_substream_chip(substream);
-	unsigned long flags;
-	unsigned char *dma_area = NULL;
-
-	spin_lock_irqsave(&cxsc->slock, flags);
-	if (substream->runtime->dma_area) {
-		dprintk("freeing pcm capture region\n");
-		dma_area = substream->runtime->dma_area;
-		substream->runtime->dma_area = NULL;
-	}
-	spin_unlock_irqrestore(&cxsc->slock, flags);
-	vfree(dma_area);
-
-	return 0;
-}
-
 static int snd_cx18_pcm_prepare(struct snd_pcm_substream *substream)
 {
 	struct snd_cx18_card *cxsc = snd_pcm_substream_chip(substream);
@@ -291,24 +229,12 @@ snd_pcm_uframes_t snd_cx18_pcm_pointer(struct snd_pcm_substream *substream)
 	return hwptr_done;
 }
 
-static struct page *snd_pcm_get_vmalloc_page(struct snd_pcm_substream *subs,
-					     unsigned long offset)
-{
-	void *pageptr = subs->runtime->dma_area + offset;
-
-	return vmalloc_to_page(pageptr);
-}
-
 static const struct snd_pcm_ops snd_cx18_pcm_capture_ops = {
 	.open		= snd_cx18_pcm_capture_open,
 	.close		= snd_cx18_pcm_capture_close,
-	.ioctl		= snd_cx18_pcm_ioctl,
-	.hw_params	= snd_cx18_pcm_hw_params,
-	.hw_free	= snd_cx18_pcm_hw_free,
 	.prepare	= snd_cx18_pcm_prepare,
 	.trigger	= snd_cx18_pcm_trigger,
 	.pointer	= snd_cx18_pcm_pointer,
-	.page		= snd_pcm_get_vmalloc_page,
 };
 
 int snd_cx18_pcm_create(struct snd_cx18_card *cxsc)
@@ -334,6 +260,7 @@ int snd_cx18_pcm_create(struct snd_cx18_card *cxsc)
 
 	snd_pcm_set_ops(sp, SNDRV_PCM_STREAM_CAPTURE,
 			&snd_cx18_pcm_capture_ops);
+	snd_pcm_set_managed_buffer_all(sp, SNDRV_DMA_TYPE_VMALLOC, NULL, 0, 0);
 	sp->info_flags = 0;
 	sp->private_data = cxsc;
 	strscpy(sp->name, cx->card_name, sizeof(sp->name));
diff --git a/drivers/media/pci/cx18/cx18-cards.c b/drivers/media/pci/cx18/cx18-cards.c
index cf118760d124..ecbe76f1ca63 100644
--- a/drivers/media/pci/cx18/cx18-cards.c
+++ b/drivers/media/pci/cx18/cx18-cards.c
@@ -245,7 +245,7 @@ static const struct cx18_card cx18_card_mpc718 = {
 	.type = CX18_CARD_YUAN_MPC718,
 	.name = "Yuan MPC718 MiniPCI DVB-T/Analog",
 	.comment = "Experimenters needed for device to work well.\n"
-		  "\tTo help, mail the ivtv-devel list (www.ivtvdriver.org).\n",
+		  "\tTo help, mail the linux-media list (www.linuxtv.org).\n",
 	.v4l2_capabilities = CX18_CAP_ENCODER,
 	.hw_audio_ctrl = CX18_HW_418_AV,
 	.hw_muxer = CX18_HW_GPIO_MUX,
@@ -305,7 +305,7 @@ static const struct cx18_card cx18_card_gotview_dvd3 = {
 	.type = CX18_CARD_GOTVIEW_PCI_DVD3,
 	.name = "GoTView PCI DVD3 Hybrid",
 	.comment = "Experimenters needed for device to work well.\n"
-		  "\tTo help, mail the ivtv-devel list (www.ivtvdriver.org).\n",
+		  "\tTo help, mail the linux-media list (www.linuxtv.org).\n",
 	.v4l2_capabilities = CX18_CAP_ENCODER,
 	.hw_audio_ctrl = CX18_HW_418_AV,
 	.hw_muxer = CX18_HW_GPIO_MUX,
@@ -419,7 +419,7 @@ static const struct cx18_card cx18_card_toshiba_qosmio_dvbt = {
 	.type = CX18_CARD_TOSHIBA_QOSMIO_DVBT,
 	.name = "Toshiba Qosmio DVB-T/Analog",
 	.comment = "Experimenters and photos needed for device to work well.\n"
-		  "\tTo help, mail the ivtv-devel list (www.ivtvdriver.org).\n",
+		  "\tTo help, mail the linux-media list (www.linuxtv.org).\n",
 	.v4l2_capabilities = CX18_CAP_ENCODER,
 	.hw_audio_ctrl = CX18_HW_418_AV,
 	.hw_all = CX18_HW_418_AV | CX18_HW_TUNER | CX18_HW_GPIO_RESET_CTRL,
@@ -462,7 +462,7 @@ static const struct cx18_card cx18_card_leadtek_pvr2100 = {
 	.type = CX18_CARD_LEADTEK_PVR2100,
 	.name = "Leadtek WinFast PVR2100",
 	.comment = "Experimenters and photos needed for device to work well.\n"
-		  "\tTo help, mail the ivtv-devel list (www.ivtvdriver.org).\n",
+		  "\tTo help, mail the linux-media list (www.linuxtv.org).\n",
 	.v4l2_capabilities = CX18_CAP_ENCODER,
 	.hw_audio_ctrl = CX18_HW_418_AV,
 	.hw_muxer = CX18_HW_GPIO_MUX,
diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 2f1eeeb6e7c7..95aed00f353b 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -676,7 +676,7 @@ done:
 			 cx->pci_dev->subsystem_device);
 		CX18_ERR("Defaulting to %s card\n", cx->card->name);
 		CX18_ERR("Please mail the vendor/device and subsystem vendor/device IDs and what kind of\n");
-		CX18_ERR("card you have to the ivtv-devel mailinglist (www.ivtvdriver.org)\n");
+		CX18_ERR("card you have to the linux-media mailinglist (www.linuxtv.org)\n");
 		CX18_ERR("Prefix your subject line with [UNKNOWN CX18 CARD].\n");
 	}
 	cx->v4l2_cap = cx->card->v4l2_capabilities;
diff --git a/drivers/media/pci/cx18/cx18-i2c.c b/drivers/media/pci/cx18/cx18-i2c.c
index 1ef7ccf4a722..a83435245251 100644
--- a/drivers/media/pci/cx18/cx18-i2c.c
+++ b/drivers/media/pci/cx18/cx18-i2c.c
@@ -88,7 +88,7 @@ static int cx18_i2c_new_ir(struct cx18 *cx, struct i2c_adapter *adap, u32 hw,
 		break;
 	}
 
-	return i2c_new_probed_device(adap, &info, addr_list, NULL) == NULL ?
+	return IS_ERR(i2c_new_scanned_device(adap, &info, addr_list, NULL)) ?
 	       -1 : 0;
 }
 
diff --git a/drivers/media/pci/cx23885/cx23885-alsa.c b/drivers/media/pci/cx23885/cx23885-alsa.c
index a8e980c6dacb..df44ed7393a0 100644
--- a/drivers/media/pci/cx23885/cx23885-alsa.c
+++ b/drivers/media/pci/cx23885/cx23885-alsa.c
@@ -495,7 +495,6 @@ static struct page *snd_cx23885_page(struct snd_pcm_substream *substream,
 static const struct snd_pcm_ops snd_cx23885_pcm_ops = {
 	.open = snd_cx23885_pcm_open,
 	.close = snd_cx23885_close,
-	.ioctl = snd_pcm_lib_ioctl,
 	.hw_params = snd_cx23885_hw_params,
 	.hw_free = snd_cx23885_hw_free,
 	.prepare = snd_cx23885_prepare,
diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 8644205d3cd3..8e5a2c580821 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -801,6 +801,25 @@ struct cx23885_board cx23885_boards[] = {
 		.name		= "Hauppauge WinTV-Starburst2",
 		.portb		= CX23885_MPEG_DVB,
 	},
+	[CX23885_BOARD_AVERMEDIA_CE310B] = {
+		.name		= "AVerMedia CE310B",
+		.porta		= CX23885_ANALOG_VIDEO,
+		.force_bff	= 1,
+		.input          = {{
+			.type   = CX23885_VMUX_COMPOSITE1,
+			.vmux   = CX25840_VIN1_CH1 |
+				  CX25840_NONE_CH2 |
+				  CX25840_NONE0_CH3,
+			.amux   = CX25840_AUDIO7,
+		}, {
+			.type   = CX23885_VMUX_SVIDEO,
+			.vmux   = CX25840_VIN8_CH1 |
+				  CX25840_NONE_CH2 |
+				  CX25840_VIN7_CH3 |
+				  CX25840_SVIDEO_ON,
+			.amux   = CX25840_AUDIO7,
+		} },
+	},
 };
 const unsigned int cx23885_bcount = ARRAY_SIZE(cx23885_boards);
 
@@ -1124,6 +1143,10 @@ struct cx23885_subid cx23885_subids[] = {
 		.subvendor = 0x0070,
 		.subdevice = 0xf02a,
 		.card      = CX23885_BOARD_HAUPPAUGE_STARBURST2,
+	}, {
+		.subvendor = 0x1461,
+		.subdevice = 0x3100,
+		.card      = CX23885_BOARD_AVERMEDIA_CE310B,
 	},
 };
 const unsigned int cx23885_idcount = ARRAY_SIZE(cx23885_subids);
@@ -2348,6 +2371,7 @@ void cx23885_card_setup(struct cx23885_dev *dev)
 	case CX23885_BOARD_DVBSKY_T982:
 	case CX23885_BOARD_VIEWCAST_260E:
 	case CX23885_BOARD_VIEWCAST_460E:
+	case CX23885_BOARD_AVERMEDIA_CE310B:
 		dev->sd_cx25840 = v4l2_i2c_new_subdev(&dev->v4l2_dev,
 				&dev->i2c_bus[2].i2c_adap,
 				"cx25840", 0x88 >> 1, NULL);
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 4f386db33a11..494751a067a3 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -1159,8 +1159,8 @@ static int dvb_register_ci_mac(struct cx23885_tsport *port)
 		info.addr = 0x40;
 		info.platform_data = &sp2_config;
 		request_module(info.type);
-		client_ci = i2c_new_device(&i2c_bus->i2c_adap, &info);
-		if (client_ci == NULL || client_ci->dev.driver == NULL)
+		client_ci = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+		if (!i2c_client_has_driver(client_ci))
 			return -ENODEV;
 		if (!try_module_get(client_ci->dev.driver->owner)) {
 			i2c_unregister_device(client_ci);
@@ -1826,8 +1826,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x05;
 			info.platform_data = &tda10071_pdata;
 			request_module("tda10071");
-			client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-			if (!client_demod || !client_demod->dev.driver)
+			client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 			if (!try_module_get(client_demod->dev.driver->owner)) {
 				i2c_unregister_device(client_demod);
@@ -1843,8 +1843,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x0b;
 			info.platform_data = &a8293_pdata;
 			request_module("a8293");
-			client_sec = i2c_new_device(&i2c_bus->i2c_adap, &info);
-			if (!client_sec || !client_sec->dev.driver)
+			client_sec = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_sec))
 				goto frontend_detach;
 			if (!try_module_get(client_sec->dev.driver->owner)) {
 				i2c_unregister_device(client_sec);
@@ -1864,9 +1864,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x64;
 			info.platform_data = &si2165_pdata;
 			request_module(info.type);
-			client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-			if (client_demod == NULL ||
-					client_demod->dev.driver == NULL)
+			client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 			if (!try_module_get(client_demod->dev.driver->owner)) {
 				i2c_unregister_device(client_demod);
@@ -1898,8 +1897,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x05;
 		info.platform_data = &tda10071_pdata;
 		request_module("tda10071");
-		client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-		if (!client_demod || !client_demod->dev.driver)
+		client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+		if (!i2c_client_has_driver(client_demod))
 			goto frontend_detach;
 		if (!try_module_get(client_demod->dev.driver->owner)) {
 			i2c_unregister_device(client_demod);
@@ -1915,8 +1914,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x0b;
 		info.platform_data = &a8293_pdata;
 		request_module("a8293");
-		client_sec = i2c_new_device(&i2c_bus->i2c_adap, &info);
-		if (!client_sec || !client_sec->dev.driver)
+		client_sec = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+		if (!i2c_client_has_driver(client_sec))
 			goto frontend_detach;
 		if (!try_module_get(client_sec->dev.driver->owner)) {
 			i2c_unregister_device(client_sec);
@@ -1948,9 +1947,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x60;
 			info.platform_data = &ts2020_config;
 			request_module(info.type);
-			client_tuner = i2c_new_device(adapter, &info);
-			if (client_tuner == NULL ||
-					client_tuner->dev.driver == NULL)
+			client_tuner = i2c_new_client_device(adapter, &info);
+			if (!i2c_client_has_driver(client_tuner))
 				goto frontend_detach;
 			if (!try_module_get(client_tuner->dev.driver->owner)) {
 				i2c_unregister_device(client_tuner);
@@ -1985,9 +1983,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x64;
 			info.platform_data = &si2168_config;
 			request_module(info.type);
-			client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-			if (client_demod == NULL ||
-					client_demod->dev.driver == NULL)
+			client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 			if (!try_module_get(client_demod->dev.driver->owner)) {
 				i2c_unregister_device(client_demod);
@@ -2004,9 +2001,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x60;
 			info.platform_data = &si2157_config;
 			request_module(info.type);
-			client_tuner = i2c_new_device(adapter, &info);
-			if (client_tuner == NULL ||
-					client_tuner->dev.driver == NULL)
+			client_tuner = i2c_new_client_device(adapter, &info);
+			if (!i2c_client_has_driver(client_tuner))
 				goto frontend_detach;
 
 			if (!try_module_get(client_tuner->dev.driver->owner)) {
@@ -2032,8 +2028,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x64;
 		info.platform_data = &si2168_config;
 		request_module(info.type);
-		client_demod = i2c_new_device(&i2c_bus2->i2c_adap, &info);
-		if (client_demod == NULL || client_demod->dev.driver == NULL)
+		client_demod = i2c_new_client_device(&i2c_bus2->i2c_adap, &info);
+		if (!i2c_client_has_driver(client_demod))
 			goto frontend_detach;
 		if (!try_module_get(client_demod->dev.driver->owner)) {
 			i2c_unregister_device(client_demod);
@@ -2050,9 +2046,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x60;
 		info.platform_data = &si2157_config;
 		request_module(info.type);
-		client_tuner = i2c_new_device(adapter, &info);
-		if (client_tuner == NULL ||
-				client_tuner->dev.driver == NULL)
+		client_tuner = i2c_new_client_device(adapter, &info);
+		if (!i2c_client_has_driver(client_tuner))
 			goto frontend_detach;
 		if (!try_module_get(client_tuner->dev.driver->owner)) {
 			i2c_unregister_device(client_tuner);
@@ -2080,8 +2075,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x60;
 		info.platform_data = &ts2020_config;
 		request_module(info.type);
-		client_tuner = i2c_new_device(adapter, &info);
-		if (client_tuner == NULL || client_tuner->dev.driver == NULL)
+		client_tuner = i2c_new_client_device(adapter, &info);
+		if (!i2c_client_has_driver(client_tuner))
 			goto frontend_detach;
 		if (!try_module_get(client_tuner->dev.driver->owner)) {
 			i2c_unregister_device(client_tuner);
@@ -2129,8 +2124,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x68;
 		info.platform_data = &m88ds3103_pdata;
 		request_module(info.type);
-		client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-		if (client_demod == NULL || client_demod->dev.driver == NULL)
+		client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+		if (!i2c_client_has_driver(client_demod))
 			goto frontend_detach;
 		if (!try_module_get(client_demod->dev.driver->owner)) {
 			i2c_unregister_device(client_demod);
@@ -2149,8 +2144,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x60;
 		info.platform_data = &ts2020_config;
 		request_module(info.type);
-		client_tuner = i2c_new_device(adapter, &info);
-		if (client_tuner == NULL || client_tuner->dev.driver == NULL)
+		client_tuner = i2c_new_client_device(adapter, &info);
+		if (!i2c_client_has_driver(client_tuner))
 			goto frontend_detach;
 		if (!try_module_get(client_tuner->dev.driver->owner)) {
 			i2c_unregister_device(client_tuner);
@@ -2194,8 +2189,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x64;
 		info.platform_data = &si2168_config;
 		request_module(info.type);
-		client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-		if (client_demod == NULL || client_demod->dev.driver == NULL)
+		client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+		if (!i2c_client_has_driver(client_demod))
 			goto frontend_detach;
 		if (!try_module_get(client_demod->dev.driver->owner)) {
 			i2c_unregister_device(client_demod);
@@ -2212,9 +2207,8 @@ static int dvb_register(struct cx23885_tsport *port)
 		info.addr = 0x60;
 		info.platform_data = &si2157_config;
 		request_module(info.type);
-		client_tuner = i2c_new_device(adapter, &info);
-		if (client_tuner == NULL ||
-				client_tuner->dev.driver == NULL)
+		client_tuner = i2c_new_client_device(adapter, &info);
+		if (!i2c_client_has_driver(client_tuner))
 			goto frontend_detach;
 		if (!try_module_get(client_tuner->dev.driver->owner)) {
 			i2c_unregister_device(client_tuner);
@@ -2245,8 +2239,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x0b;
 			info.platform_data = &a8293_pdata;
 			request_module("a8293");
-			client_sec = i2c_new_device(&i2c_bus->i2c_adap, &info);
-			if (!client_sec || !client_sec->dev.driver)
+			client_sec = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_sec))
 				goto frontend_detach;
 			if (!try_module_get(client_sec->dev.driver->owner)) {
 				i2c_unregister_device(client_sec);
@@ -2262,8 +2256,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x21;
 			info.platform_data = &m88rs6000t_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(adapter, &info);
-			if (!client_tuner || !client_tuner->dev.driver)
+			client_tuner = i2c_new_client_device(adapter, &info);
+			if (!i2c_client_has_driver(client_tuner))
 				goto frontend_detach;
 			if (!try_module_get(client_tuner->dev.driver->owner)) {
 				i2c_unregister_device(client_tuner);
@@ -2287,8 +2281,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x64;
 			info.platform_data = &si2168_config;
 			request_module("%s", info.type);
-			client_demod = i2c_new_device(&i2c_bus->i2c_adap, &info);
-			if (!client_demod || !client_demod->dev.driver)
+			client_demod = i2c_new_client_device(&i2c_bus->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 			if (!try_module_get(client_demod->dev.driver->owner)) {
 				i2c_unregister_device(client_demod);
@@ -2305,8 +2299,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x60;
 			info.platform_data = &si2157_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(&i2c_bus2->i2c_adap, &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&i2c_bus2->i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				port->i2c_client_demod = NULL;
@@ -2340,8 +2334,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x64;
 			info.platform_data = &si2168_config;
 			request_module("%s", info.type);
-			client_demod = i2c_new_device(&dev->i2c_bus[0].i2c_adap, &info);
-			if (!client_demod || !client_demod->dev.driver)
+			client_demod = i2c_new_client_device(&dev->i2c_bus[0].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 			if (!try_module_get(client_demod->dev.driver->owner)) {
 				i2c_unregister_device(client_demod);
@@ -2358,8 +2352,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x60;
 			info.platform_data = &si2157_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				port->i2c_client_demod = NULL;
@@ -2387,8 +2381,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x66;
 			info.platform_data = &si2168_config;
 			request_module("%s", info.type);
-			client_demod = i2c_new_device(&dev->i2c_bus[0].i2c_adap, &info);
-			if (!client_demod || !client_demod->dev.driver)
+			client_demod = i2c_new_client_device(&dev->i2c_bus[0].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 			if (!try_module_get(client_demod->dev.driver->owner)) {
 				i2c_unregister_device(client_demod);
@@ -2405,8 +2399,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x62;
 			info.platform_data = &si2157_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				port->i2c_client_demod = NULL;
@@ -2447,8 +2441,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x60;
 			info.platform_data = &si2157_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				port->i2c_client_demod = NULL;
@@ -2483,8 +2477,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x62;
 			info.platform_data = &si2157_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				port->i2c_client_demod = NULL;
@@ -2523,8 +2517,8 @@ static int dvb_register(struct cx23885_tsport *port)
 			info.addr = 0x60;
 			info.platform_data = &si2157_config;
 			request_module("%s", info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap, &info);
-			if (!client_tuner || !client_tuner->dev.driver)
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner))
 				goto frontend_detach;
 
 			if (!try_module_get(client_tuner->dev.driver->owner)) {
diff --git a/drivers/media/pci/cx23885/cx23885-i2c.c b/drivers/media/pci/cx23885/cx23885-i2c.c
index 4f327ee9659e..f51fad33dc04 100644
--- a/drivers/media/pci/cx23885/cx23885-i2c.c
+++ b/drivers/media/pci/cx23885/cx23885-i2c.c
@@ -337,8 +337,8 @@ int cx23885_i2c_register(struct cx23885_i2c *bus)
 		strscpy(info.type, "ir_video", I2C_NAME_SIZE);
 		/* Use quick read command for probe, some IR chips don't
 		 * support writes */
-		i2c_new_probed_device(&bus->i2c_adap, &info, addr_list,
-				      i2c_probe_func_quick_read);
+		i2c_new_scanned_device(&bus->i2c_adap, &info, addr_list,
+				       i2c_probe_func_quick_read);
 	}
 
 	return bus->i2c_rc;
diff --git a/drivers/media/pci/cx23885/cx23885-video.c b/drivers/media/pci/cx23885/cx23885-video.c
index 8098b15493de..7fc408ee4934 100644
--- a/drivers/media/pci/cx23885/cx23885-video.c
+++ b/drivers/media/pci/cx23885/cx23885-video.c
@@ -257,7 +257,8 @@ static int cx23885_video_mux(struct cx23885_dev *dev, unsigned int input)
 		(dev->board == CX23885_BOARD_MYGICA_X8507) ||
 		(dev->board == CX23885_BOARD_AVERMEDIA_HC81R) ||
 		(dev->board == CX23885_BOARD_VIEWCAST_260E) ||
-		(dev->board == CX23885_BOARD_VIEWCAST_460E)) {
+		(dev->board == CX23885_BOARD_VIEWCAST_460E) ||
+		(dev->board == CX23885_BOARD_AVERMEDIA_CE310B)) {
 		/* Configure audio routing */
 		v4l2_subdev_call(dev->sd_cx25840, audio, s_routing,
 			INPUT(input)->amux, 0, 0);
diff --git a/drivers/media/pci/cx23885/cx23885.h b/drivers/media/pci/cx23885/cx23885.h
index a95a2e4c6a0d..c472498e57c4 100644
--- a/drivers/media/pci/cx23885/cx23885.h
+++ b/drivers/media/pci/cx23885/cx23885.h
@@ -101,6 +101,7 @@
 #define CX23885_BOARD_HAUPPAUGE_STARBURST2     59
 #define CX23885_BOARD_HAUPPAUGE_QUADHD_DVB_885 60
 #define CX23885_BOARD_HAUPPAUGE_QUADHD_ATSC_885 61
+#define CX23885_BOARD_AVERMEDIA_CE310B         62
 
 #define GPIO_0 0x00000001
 #define GPIO_1 0x00000002
diff --git a/drivers/media/pci/cx25821/cx25821-alsa.c b/drivers/media/pci/cx25821/cx25821-alsa.c
index c2f2d7c782c7..301616426d8a 100644
--- a/drivers/media/pci/cx25821/cx25821-alsa.c
+++ b/drivers/media/pci/cx25821/cx25821-alsa.c
@@ -639,7 +639,6 @@ static struct page *snd_cx25821_page(struct snd_pcm_substream *substream,
 static const struct snd_pcm_ops snd_cx25821_pcm_ops = {
 	.open = snd_cx25821_pcm_open,
 	.close = snd_cx25821_close,
-	.ioctl = snd_pcm_lib_ioctl,
 	.hw_params = snd_cx25821_hw_params,
 	.hw_free = snd_cx25821_hw_free,
 	.prepare = snd_cx25821_prepare,
diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index e1e71ae293ed..7d7aceecc985 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -585,7 +585,6 @@ static struct page *snd_cx88_page(struct snd_pcm_substream *substream,
 static const struct snd_pcm_ops snd_cx88_pcm_ops = {
 	.open = snd_cx88_pcm_open,
 	.close = snd_cx88_close,
-	.ioctl = snd_pcm_lib_ioctl,
 	.hw_params = snd_cx88_hw_params,
 	.hw_free = snd_cx88_hw_free,
 	.prepare = snd_cx88_prepare,
diff --git a/drivers/media/pci/cx88/cx88-input.c b/drivers/media/pci/cx88/cx88-input.c
index 589f52d961eb..c7c2acd55266 100644
--- a/drivers/media/pci/cx88/cx88-input.c
+++ b/drivers/media/pci/cx88/cx88-input.c
@@ -613,7 +613,7 @@ void cx88_i2c_init_ir(struct cx88_core *core)
 	}
 
 	/*
-	 * We can't call i2c_new_probed_device() because it uses
+	 * We can't call i2c_new_scanned_device() because it uses
 	 * quick writes for probing and at least some RC receiver
 	 * devices only reply to reads.
 	 * Also, Hauppauge XVR needs to be specified, as address 0x71
diff --git a/drivers/media/pci/ivtv/Kconfig b/drivers/media/pci/ivtv/Kconfig
index 36c089103cf9..c729e54692c4 100644
--- a/drivers/media/pci/ivtv/Kconfig
+++ b/drivers/media/pci/ivtv/Kconfig
@@ -24,7 +24,7 @@ config VIDEO_IVTV
 	  PCI personal video recorder devices.
 
 	  This is used in devices such as the Hauppauge PVR-150/250/350/500
-	  cards. There is a driver homepage at <http://www.ivtvdriver.org>.
+	  cards.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called ivtv.
@@ -67,8 +67,7 @@ config VIDEO_FB_IVTV
 	  This is a framebuffer driver for the Conexant cx23415 MPEG
 	  encoder/decoder.
 
-	  This is used in the Hauppauge PVR-350 card. There is a driver
-	  homepage at <http://www.ivtvdriver.org>.
+	  This is used in the Hauppauge PVR-350 card.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called ivtvfb.
diff --git a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
index 9e6019a159f4..8f346d7da9c8 100644
--- a/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
+++ b/drivers/media/pci/ivtv/ivtv-alsa-pcm.c
@@ -16,8 +16,6 @@
 #include "ivtv-alsa.h"
 #include "ivtv-alsa-pcm.h"
 
-#include <linux/vmalloc.h>
-
 #include <sound/core.h>
 #include <sound/pcm.h>
 
@@ -206,67 +204,6 @@ static int snd_ivtv_pcm_capture_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_ivtv_pcm_ioctl(struct snd_pcm_substream *substream,
-		     unsigned int cmd, void *arg)
-{
-	struct snd_ivtv_card *itvsc = snd_pcm_substream_chip(substream);
-	int ret;
-
-	snd_ivtv_lock(itvsc);
-	ret = snd_pcm_lib_ioctl(substream, cmd, arg);
-	snd_ivtv_unlock(itvsc);
-	return ret;
-}
-
-
-static int snd_pcm_alloc_vmalloc_buffer(struct snd_pcm_substream *subs,
-					size_t size)
-{
-	struct snd_pcm_runtime *runtime = subs->runtime;
-
-	dprintk("Allocating vbuffer\n");
-	if (runtime->dma_area) {
-		if (runtime->dma_bytes > size)
-			return 0;
-
-		vfree(runtime->dma_area);
-	}
-	runtime->dma_area = vmalloc(size);
-	if (!runtime->dma_area)
-		return -ENOMEM;
-
-	runtime->dma_bytes = size;
-
-	return 0;
-}
-
-static int snd_ivtv_pcm_hw_params(struct snd_pcm_substream *substream,
-			 struct snd_pcm_hw_params *params)
-{
-	dprintk("%s called\n", __func__);
-
-	return snd_pcm_alloc_vmalloc_buffer(substream,
-					   params_buffer_bytes(params));
-}
-
-static int snd_ivtv_pcm_hw_free(struct snd_pcm_substream *substream)
-{
-	struct snd_ivtv_card *itvsc = snd_pcm_substream_chip(substream);
-	unsigned long flags;
-	unsigned char *dma_area = NULL;
-
-	spin_lock_irqsave(&itvsc->slock, flags);
-	if (substream->runtime->dma_area) {
-		dprintk("freeing pcm capture region\n");
-		dma_area = substream->runtime->dma_area;
-		substream->runtime->dma_area = NULL;
-	}
-	spin_unlock_irqrestore(&itvsc->slock, flags);
-	vfree(dma_area);
-
-	return 0;
-}
-
 static int snd_ivtv_pcm_prepare(struct snd_pcm_substream *substream)
 {
 	struct snd_ivtv_card *itvsc = snd_pcm_substream_chip(substream);
@@ -296,24 +233,12 @@ snd_pcm_uframes_t snd_ivtv_pcm_pointer(struct snd_pcm_substream *substream)
 	return hwptr_done;
 }
 
-static struct page *snd_pcm_get_vmalloc_page(struct snd_pcm_substream *subs,
-					     unsigned long offset)
-{
-	void *pageptr = subs->runtime->dma_area + offset;
-
-	return vmalloc_to_page(pageptr);
-}
-
 static const struct snd_pcm_ops snd_ivtv_pcm_capture_ops = {
 	.open		= snd_ivtv_pcm_capture_open,
 	.close		= snd_ivtv_pcm_capture_close,
-	.ioctl		= snd_ivtv_pcm_ioctl,
-	.hw_params	= snd_ivtv_pcm_hw_params,
-	.hw_free	= snd_ivtv_pcm_hw_free,
 	.prepare	= snd_ivtv_pcm_prepare,
 	.trigger	= snd_ivtv_pcm_trigger,
 	.pointer	= snd_ivtv_pcm_pointer,
-	.page		= snd_pcm_get_vmalloc_page,
 };
 
 int snd_ivtv_pcm_create(struct snd_ivtv_card *itvsc)
@@ -339,6 +264,7 @@ int snd_ivtv_pcm_create(struct snd_ivtv_card *itvsc)
 
 	snd_pcm_set_ops(sp, SNDRV_PCM_STREAM_CAPTURE,
 			&snd_ivtv_pcm_capture_ops);
+	snd_pcm_set_managed_buffer_all(sp, SNDRV_DMA_TYPE_VMALLOC, NULL, 0, 0);
 	sp->info_flags = 0;
 	sp->private_data = itvsc;
 	strscpy(sp->name, itv->card_name, sizeof(sp->name));
diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c
index 1f79700a6307..b1dde1be6f5e 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.c
+++ b/drivers/media/pci/ivtv/ivtv-driver.c
@@ -23,7 +23,6 @@
  * Driver for the Conexant CX23415/CX23416 chip.
  * Author: Kevin Thayer (nufan_wfk at yahoo.com)
  * License: GPL
- * http://www.ivtvdriver.org
  *
  * -----
  * MPG600/MPG160 support by  T.Adachi <tadachi@tadachi-net.com>
@@ -723,7 +722,7 @@ done:
 		IVTV_ERR("              %s based\n", chipname);
 		IVTV_ERR("Defaulting to %s card\n", itv->card->name);
 		IVTV_ERR("Please mail the vendor/device and subsystem vendor/device IDs and what kind of\n");
-		IVTV_ERR("card you have to the ivtv-devel mailinglist (www.ivtvdriver.org)\n");
+		IVTV_ERR("card you have to the linux-media mailinglist (www.linuxtv.org)\n");
 		IVTV_ERR("Prefix your subject line with [UNKNOWN IVTV CARD].\n");
 	}
 	itv->v4l2_cap = itv->card->v4l2_capabilities;
diff --git a/drivers/media/pci/ivtv/ivtv-driver.h b/drivers/media/pci/ivtv/ivtv-driver.h
index cafba6b1055d..e5efe525ad7b 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.h
+++ b/drivers/media/pci/ivtv/ivtv-driver.h
@@ -28,7 +28,6 @@
  * Driver for the cx23415/6 chip.
  * Author: Kevin Thayer (nufan_wfk at yahoo.com)
  * License: GPL
- * http://www.ivtvdriver.org
  *
  * -----
  * MPG600/MPG160 support by  T.Adachi <tadachi@tadachi-net.com>
diff --git a/drivers/media/pci/ivtv/ivtv-i2c.c b/drivers/media/pci/ivtv/ivtv-i2c.c
index 0772d757a389..982045c4eea8 100644
--- a/drivers/media/pci/ivtv/ivtv-i2c.c
+++ b/drivers/media/pci/ivtv/ivtv-i2c.c
@@ -208,12 +208,12 @@ static int ivtv_i2c_new_ir(struct ivtv *itv, u32 hw, const char *type, u8 addr)
 	info.platform_data = init_data;
 	strscpy(info.type, type, I2C_NAME_SIZE);
 
-	return i2c_new_probed_device(adap, &info, addr_list, NULL) == NULL ?
+	return IS_ERR(i2c_new_scanned_device(adap, &info, addr_list, NULL)) ?
 	       -1 : 0;
 }
 
 /* Instantiate the IR receiver device using probing -- undesirable */
-struct i2c_client *ivtv_i2c_new_ir_legacy(struct ivtv *itv)
+void ivtv_i2c_new_ir_legacy(struct ivtv *itv)
 {
 	struct i2c_board_info info;
 	/*
@@ -235,7 +235,7 @@ struct i2c_client *ivtv_i2c_new_ir_legacy(struct ivtv *itv)
 
 	memset(&info, 0, sizeof(struct i2c_board_info));
 	strscpy(info.type, "ir_video", I2C_NAME_SIZE);
-	return i2c_new_probed_device(&itv->i2c_adap, &info, addr_list, NULL);
+	i2c_new_scanned_device(&itv->i2c_adap, &info, addr_list, NULL);
 }
 
 int ivtv_i2c_register(struct ivtv *itv, unsigned idx)
diff --git a/drivers/media/pci/ivtv/ivtv-i2c.h b/drivers/media/pci/ivtv/ivtv-i2c.h
index 462f73449a6e..2d9cdaa682c5 100644
--- a/drivers/media/pci/ivtv/ivtv-i2c.h
+++ b/drivers/media/pci/ivtv/ivtv-i2c.h
@@ -9,7 +9,7 @@
 #ifndef IVTV_I2C_H
 #define IVTV_I2C_H
 
-struct i2c_client *ivtv_i2c_new_ir_legacy(struct ivtv *itv);
+void ivtv_i2c_new_ir_legacy(struct ivtv *itv);
 int ivtv_i2c_register(struct ivtv *itv, unsigned idx);
 struct v4l2_subdev *ivtv_find_hw(struct ivtv *itv, u32 hw);
 
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index 1daf9e07cad7..0c2859844081 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -925,7 +925,7 @@ static int ivtvfb_blank(int blank_mode, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops ivtvfb_ops = {
+static const struct fb_ops ivtvfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_write       = ivtvfb_write,
 	.fb_check_var   = ivtvfb_check_var,
@@ -1049,7 +1049,6 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
 
 	oi->ivtvfb_info.node = -1;
 	oi->ivtvfb_info.flags = FBINFO_FLAG_DEFAULT;
-	oi->ivtvfb_info.fbops = &ivtvfb_ops;
 	oi->ivtvfb_info.par = itv;
 	oi->ivtvfb_info.var = oi->ivtvfb_defined;
 	oi->ivtvfb_info.fix = oi->ivtvfb_fix;
diff --git a/drivers/media/pci/meye/meye.c b/drivers/media/pci/meye/meye.c
index 0e61c81356ef..3a4c29bc0ba5 100644
--- a/drivers/media/pci/meye/meye.c
+++ b/drivers/media/pci/meye/meye.c
@@ -1266,7 +1266,7 @@ static int vidioc_querybuf(struct file *file, void *fh, struct v4l2_buffer *buf)
 		buf->flags |= V4L2_BUF_FLAG_DONE;
 
 	buf->field = V4L2_FIELD_NONE;
-	buf->timestamp = ns_to_timeval(meye.grab_buffer[index].ts);
+	v4l2_buffer_set_timestamp(buf, meye.grab_buffer[index].ts);
 	buf->sequence = meye.grab_buffer[index].sequence;
 	buf->memory = V4L2_MEMORY_MMAP;
 	buf->m.offset = index * gbufsize;
@@ -1332,7 +1332,7 @@ static int vidioc_dqbuf(struct file *file, void *fh, struct v4l2_buffer *buf)
 	buf->bytesused = meye.grab_buffer[reqnr].size;
 	buf->flags = V4L2_BUF_FLAG_MAPPED | V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	buf->field = V4L2_FIELD_NONE;
-	buf->timestamp = ns_to_timeval(meye.grab_buffer[reqnr].ts);
+	v4l2_buffer_set_timestamp(buf, meye.grab_buffer[reqnr].ts);
 	buf->sequence = meye.grab_buffer[reqnr].sequence;
 	buf->memory = V4L2_MEMORY_MMAP;
 	buf->m.offset = reqnr * gbufsize;
diff --git a/drivers/media/pci/saa7134/saa7134-alsa.c b/drivers/media/pci/saa7134/saa7134-alsa.c
index 0385127dd7ff..544ca57eee75 100644
--- a/drivers/media/pci/saa7134/saa7134-alsa.c
+++ b/drivers/media/pci/saa7134/saa7134-alsa.c
@@ -865,7 +865,6 @@ static struct page *snd_card_saa7134_page(struct snd_pcm_substream *substream,
 static const struct snd_pcm_ops snd_card_saa7134_capture_ops = {
 	.open =			snd_card_saa7134_capture_open,
 	.close =		snd_card_saa7134_capture_close,
-	.ioctl =		snd_pcm_lib_ioctl,
 	.hw_params =		snd_card_saa7134_hw_params,
 	.hw_free =		snd_card_saa7134_hw_free,
 	.prepare =		snd_card_saa7134_capture_prepare,
diff --git a/drivers/media/pci/saa7164/saa7164-dvb.c b/drivers/media/pci/saa7164/saa7164-dvb.c
index 05ab4734ea67..bf8c2bb8852e 100644
--- a/drivers/media/pci/saa7164/saa7164-dvb.c
+++ b/drivers/media/pci/saa7164/saa7164-dvb.c
@@ -116,8 +116,8 @@ static int si2157_attach(struct saa7164_port *port, struct i2c_adapter *adapter,
 
 	request_module(bi.type);
 
-	tuner = i2c_new_device(adapter, &bi);
-	if (tuner == NULL || tuner->dev.driver == NULL)
+	tuner = i2c_new_client_device(adapter, &bi);
+	if (!i2c_client_has_driver(tuner))
 		return -ENODEV;
 
 	if (!try_module_get(tuner->dev.driver->owner)) {
@@ -637,9 +637,8 @@ int saa7164_dvb_register(struct saa7164_port *port)
 			info.addr = 0xc8 >> 1;
 			info.platform_data = &si2168_config;
 			request_module(info.type);
-			client_demod = i2c_new_device(&dev->i2c_bus[2].i2c_adap,
-						      &info);
-			if (!client_demod || !client_demod->dev.driver)
+			client_demod = i2c_new_client_device(&dev->i2c_bus[2].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 
 			if (!try_module_get(client_demod->dev.driver->owner)) {
@@ -657,9 +656,8 @@ int saa7164_dvb_register(struct saa7164_port *port)
 			info.addr = 0xc0 >> 1;
 			info.platform_data = &si2157_config;
 			request_module(info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[0].i2c_adap,
-						      &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[0].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				goto frontend_detach;
@@ -682,9 +680,8 @@ int saa7164_dvb_register(struct saa7164_port *port)
 			info.addr = 0xcc >> 1;
 			info.platform_data = &si2168_config;
 			request_module(info.type);
-			client_demod = i2c_new_device(&dev->i2c_bus[2].i2c_adap,
-						      &info);
-			if (!client_demod || !client_demod->dev.driver)
+			client_demod = i2c_new_client_device(&dev->i2c_bus[2].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_demod))
 				goto frontend_detach;
 
 			if (!try_module_get(client_demod->dev.driver->owner)) {
@@ -702,9 +699,8 @@ int saa7164_dvb_register(struct saa7164_port *port)
 			info.addr = 0xc0 >> 1;
 			info.platform_data = &si2157_config;
 			request_module(info.type);
-			client_tuner = i2c_new_device(&dev->i2c_bus[1].i2c_adap,
-						      &info);
-			if (!client_tuner || !client_tuner->dev.driver) {
+			client_tuner = i2c_new_client_device(&dev->i2c_bus[1].i2c_adap, &info);
+			if (!i2c_client_has_driver(client_tuner)) {
 				module_put(client_demod->dev.driver->owner);
 				i2c_unregister_device(client_demod);
 				goto frontend_detach;
diff --git a/drivers/media/pci/smipcie/smipcie-main.c b/drivers/media/pci/smipcie/smipcie-main.c
index 1fb78462e081..9ca0fc3e6f80 100644
--- a/drivers/media/pci/smipcie/smipcie-main.c
+++ b/drivers/media/pci/smipcie/smipcie-main.c
@@ -484,8 +484,8 @@ static struct i2c_client *smi_add_i2c_client(struct i2c_adapter *adapter,
 	struct i2c_client *client;
 
 	request_module(info->type);
-	client = i2c_new_device(adapter, info);
-	if (client == NULL || client->dev.driver == NULL)
+	client = i2c_new_client_device(adapter, info);
+	if (!i2c_client_has_driver(client))
 		goto err_add_i2c_client;
 
 	if (!try_module_get(client->dev.driver->owner)) {
diff --git a/drivers/media/pci/solo6x10/solo6x10-g723.c b/drivers/media/pci/solo6x10/solo6x10-g723.c
index eaa57d835ea8..d6d16e8fd997 100644
--- a/drivers/media/pci/solo6x10/solo6x10-g723.c
+++ b/drivers/media/pci/solo6x10/solo6x10-g723.c
@@ -97,17 +97,6 @@ void solo_g723_isr(struct solo_dev *solo_dev)
 	}
 }
 
-static int snd_solo_hw_params(struct snd_pcm_substream *ss,
-			      struct snd_pcm_hw_params *hw_params)
-{
-	return snd_pcm_lib_malloc_pages(ss, params_buffer_bytes(hw_params));
-}
-
-static int snd_solo_hw_free(struct snd_pcm_substream *ss)
-{
-	return snd_pcm_lib_free_pages(ss);
-}
-
 static const struct snd_pcm_hardware snd_solo_pcm_hw = {
 	.info			= (SNDRV_PCM_INFO_MMAP |
 				   SNDRV_PCM_INFO_INTERLEAVED |
@@ -270,9 +259,6 @@ static int snd_solo_pcm_copy_kernel(struct snd_pcm_substream *ss, int channel,
 static const struct snd_pcm_ops snd_solo_pcm_ops = {
 	.open = snd_solo_pcm_open,
 	.close = snd_solo_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = snd_solo_hw_params,
-	.hw_free = snd_solo_hw_free,
 	.prepare = snd_solo_pcm_prepare,
 	.trigger = snd_solo_pcm_trigger,
 	.pointer = snd_solo_pcm_pointer,
@@ -351,11 +337,11 @@ static int solo_snd_pcm_init(struct solo_dev *solo_dev)
 	     ss; ss = ss->next, i++)
 		sprintf(ss->name, "Camera #%d Audio", i);
 
-	snd_pcm_lib_preallocate_pages_for_all(pcm,
-					SNDRV_DMA_TYPE_CONTINUOUS,
-					NULL,
-					G723_PERIOD_BYTES * PERIODS,
-					G723_PERIOD_BYTES * PERIODS);
+	snd_pcm_set_managed_buffer_all(pcm,
+				       SNDRV_DMA_TYPE_CONTINUOUS,
+				       NULL,
+				       G723_PERIOD_BYTES * PERIODS,
+				       G723_PERIOD_BYTES * PERIODS);
 
 	solo_dev->snd_pcm = pcm;
 
diff --git a/drivers/media/pci/tw686x/tw686x-audio.c b/drivers/media/pci/tw686x/tw686x-audio.c
index 7786e51d19ae..54144e23a487 100644
--- a/drivers/media/pci/tw686x/tw686x-audio.c
+++ b/drivers/media/pci/tw686x/tw686x-audio.c
@@ -78,17 +78,6 @@ void tw686x_audio_irq(struct tw686x_dev *dev, unsigned long requests,
 	}
 }
 
-static int tw686x_pcm_hw_params(struct snd_pcm_substream *ss,
-				struct snd_pcm_hw_params *hw_params)
-{
-	return snd_pcm_lib_malloc_pages(ss, params_buffer_bytes(hw_params));
-}
-
-static int tw686x_pcm_hw_free(struct snd_pcm_substream *ss)
-{
-	return snd_pcm_lib_free_pages(ss);
-}
-
 /*
  * Audio parameters are global and shared among all
  * capture channels. The driver prevents changes to
@@ -269,9 +258,6 @@ static snd_pcm_uframes_t tw686x_pcm_pointer(struct snd_pcm_substream *ss)
 static const struct snd_pcm_ops tw686x_pcm_ops = {
 	.open = tw686x_pcm_open,
 	.close = tw686x_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = tw686x_pcm_hw_params,
-	.hw_free = tw686x_pcm_hw_free,
 	.prepare = tw686x_pcm_prepare,
 	.trigger = tw686x_pcm_trigger,
 	.pointer = tw686x_pcm_pointer,
@@ -298,7 +284,7 @@ static int tw686x_snd_pcm_init(struct tw686x_dev *dev)
 	     ss; ss = ss->next, i++)
 		snprintf(ss->name, sizeof(ss->name), "vch%u audio", i);
 
-	snd_pcm_lib_preallocate_pages_for_all(pcm,
+	snd_pcm_set_managed_buffer_all(pcm,
 				SNDRV_DMA_TYPE_DEV,
 				&dev->pci_dev->dev,
 				TW686X_AUDIO_PAGE_MAX * AUDIO_DMA_SIZE_MAX,
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index e84f35d3a68e..f65e98d3adf2 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -151,7 +151,7 @@ source "drivers/media/platform/sunxi/Kconfig"
 config VIDEO_TI_CAL
 	tristate "TI CAL (Camera Adaptation Layer) driver"
 	depends on VIDEO_DEV && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
-	depends on SOC_DRA7XX || COMPILE_TEST
+	depends on SOC_DRA7XX || ARCH_K3 || COMPILE_TEST
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_FWNODE
 	help
@@ -200,7 +200,7 @@ config VIDEO_IMX_PXP
 
 config VIDEO_MEDIATEK_JPEG
 	tristate "Mediatek JPEG Codec driver"
-	depends on MTK_IOMMU_V1 || COMPILE_TEST
+	depends on MTK_IOMMU_V1 || MTK_IOMMU || COMPILE_TEST
 	depends on VIDEO_DEV && VIDEO_V4L2
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	select VIDEOBUF2_DMA_CONTIG
diff --git a/drivers/media/platform/atmel/atmel-isc-base.c b/drivers/media/platform/atmel/atmel-isc-base.c
index c1c776b348a9..d7669a03e98e 100644
--- a/drivers/media/platform/atmel/atmel-isc-base.c
+++ b/drivers/media/platform/atmel/atmel-isc-base.c
@@ -73,6 +73,9 @@ const struct isc_format controller_formats[] = {
 	{
 		.fourcc		= V4L2_PIX_FMT_GREY,
 	},
+	{
+		.fourcc		= V4L2_PIX_FMT_Y10,
+	},
 };
 
 /* This is a list of formats that the ISC can receive as *input* */
@@ -164,6 +167,12 @@ struct isc_format formats_list[] = {
 		.mbus_code	= MEDIA_BUS_FMT_RGB565_2X8_LE,
 		.pfe_cfg0_bps	= ISC_PFE_CFG0_BPS_EIGHT,
 	},
+	{
+		.fourcc		= V4L2_PIX_FMT_Y10,
+		.mbus_code	= MEDIA_BUS_FMT_Y10_1X10,
+		.pfe_cfg0_bps	= ISC_PFG_CFG0_BPS_TEN,
+	},
+
 };
 
 /* Gamma table with gamma 1/2.2 */
@@ -211,6 +220,10 @@ const u32 isc_gamma_table[GAMMA_MAX + 1][GAMMA_ENTRIES] = {
 #define ISC_IS_FORMAT_RAW(mbus_code) \
 	(((mbus_code) & 0xf000) == 0x3000)
 
+#define ISC_IS_FORMAT_GREY(mbus_code) \
+	(((mbus_code) == MEDIA_BUS_FMT_Y10_1X10) | \
+	(((mbus_code) == MEDIA_BUS_FMT_Y8_1X8)))
+
 static inline void isc_update_awb_ctrls(struct isc_device *isc)
 {
 	struct isc_ctrls *ctrls = &isc->ctrls;
@@ -1003,6 +1016,7 @@ static int isc_try_validate_formats(struct isc_device *isc)
 		rgb = true;
 		break;
 	case V4L2_PIX_FMT_GREY:
+	case V4L2_PIX_FMT_Y10:
 		ret = 0;
 		grey = true;
 		break;
@@ -1010,34 +1024,29 @@ static int isc_try_validate_formats(struct isc_device *isc)
 	/* any other different formats are not supported */
 		ret = -EINVAL;
 	}
-
-	/* we cannot output RAW/Grey if we do not receive RAW */
-	if ((bayer || grey) &&
-	    !ISC_IS_FORMAT_RAW(isc->try_config.sd_format->mbus_code))
-		return -EINVAL;
-
 	v4l2_dbg(1, debug, &isc->v4l2_dev,
 		 "Format validation, requested rgb=%u, yuv=%u, grey=%u, bayer=%u\n",
 		 rgb, yuv, grey, bayer);
 
+	/* we cannot output RAW if we do not receive RAW */
+	if ((bayer) && !ISC_IS_FORMAT_RAW(isc->try_config.sd_format->mbus_code))
+		return -EINVAL;
+
+	/* we cannot output GREY if we do not receive RAW/GREY */
+	if (grey && !ISC_IS_FORMAT_RAW(isc->try_config.sd_format->mbus_code) &&
+	    !ISC_IS_FORMAT_GREY(isc->try_config.sd_format->mbus_code))
+		return -EINVAL;
+
 	return ret;
 }
 
 /*
  * Configures the RLP and DMA modules, depending on the output format
  * configured for the ISC.
- * If direct_dump == true, just dump raw data 8 bits.
+ * If direct_dump == true, just dump raw data 8/16 bits depending on format.
  */
 static int isc_try_configure_rlp_dma(struct isc_device *isc, bool direct_dump)
 {
-	if (direct_dump) {
-		isc->try_config.rlp_cfg_mode = ISC_RLP_CFG_MODE_DAT8;
-		isc->try_config.dcfg_imode = ISC_DCFG_IMODE_PACKED8;
-		isc->try_config.dctrl_dview = ISC_DCTRL_DVIEW_PACKED;
-		isc->try_config.bpp = 16;
-		return 0;
-	}
-
 	switch (isc->try_config.fourcc) {
 	case V4L2_PIX_FMT_SBGGR8:
 	case V4L2_PIX_FMT_SGBRG8:
@@ -1115,9 +1124,23 @@ static int isc_try_configure_rlp_dma(struct isc_device *isc, bool direct_dump)
 		isc->try_config.dctrl_dview = ISC_DCTRL_DVIEW_PACKED;
 		isc->try_config.bpp = 8;
 		break;
+	case V4L2_PIX_FMT_Y10:
+		isc->try_config.rlp_cfg_mode = ISC_RLP_CFG_MODE_DATY10;
+		isc->try_config.dcfg_imode = ISC_DCFG_IMODE_PACKED16;
+		isc->try_config.dctrl_dview = ISC_DCTRL_DVIEW_PACKED;
+		isc->try_config.bpp = 16;
+		break;
 	default:
 		return -EINVAL;
 	}
+
+	if (direct_dump) {
+		isc->try_config.rlp_cfg_mode = ISC_RLP_CFG_MODE_DAT8;
+		isc->try_config.dcfg_imode = ISC_DCFG_IMODE_PACKED8;
+		isc->try_config.dctrl_dview = ISC_DCTRL_DVIEW_PACKED;
+		return 0;
+	}
+
 	return 0;
 }
 
@@ -1187,13 +1210,44 @@ static int isc_try_configure_pipeline(struct isc_device *isc)
 	return 0;
 }
 
+static void isc_try_fse(struct isc_device *isc,
+			struct v4l2_subdev_pad_config *pad_cfg)
+{
+	int ret;
+	struct v4l2_subdev_frame_size_enum fse = {};
+
+	/*
+	 * If we do not know yet which format the subdev is using, we cannot
+	 * do anything.
+	 */
+	if (!isc->try_config.sd_format)
+		return;
+
+	fse.code = isc->try_config.sd_format->mbus_code;
+	fse.which = V4L2_SUBDEV_FORMAT_TRY;
+
+	ret = v4l2_subdev_call(isc->current_subdev->sd, pad, enum_frame_size,
+			       pad_cfg, &fse);
+	/*
+	 * Attempt to obtain format size from subdev. If not available,
+	 * just use the maximum ISC can receive.
+	 */
+	if (ret) {
+		pad_cfg->try_crop.width = ISC_MAX_SUPPORT_WIDTH;
+		pad_cfg->try_crop.height = ISC_MAX_SUPPORT_HEIGHT;
+	} else {
+		pad_cfg->try_crop.width = fse.max_width;
+		pad_cfg->try_crop.height = fse.max_height;
+	}
+}
+
 static int isc_try_fmt(struct isc_device *isc, struct v4l2_format *f,
 			u32 *code)
 {
 	int i;
 	struct isc_format *sd_fmt = NULL, *direct_fmt = NULL;
 	struct v4l2_pix_format *pixfmt = &f->fmt.pix;
-	struct v4l2_subdev_pad_config pad_cfg;
+	struct v4l2_subdev_pad_config pad_cfg = {};
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
 	};
@@ -1290,6 +1344,9 @@ static int isc_try_fmt(struct isc_device *isc, struct v4l2_format *f,
 	if (ret)
 		goto isc_try_fmt_err;
 
+	/* Obtain frame sizes if possible to have crop requirements ready */
+	isc_try_fse(isc, &pad_cfg);
+
 	v4l2_fill_mbus_format(&format.format, pixfmt, mbus_code);
 	ret = v4l2_subdev_call(isc->current_subdev->sd, pad, set_fmt,
 			       &pad_cfg, &format);
@@ -1414,6 +1471,7 @@ static int isc_enum_framesizes(struct file *file, void *fh,
 {
 	struct isc_device *isc = video_drvdata(file);
 	struct v4l2_subdev_frame_size_enum fse = {
+		.code = isc->config.sd_format->mbus_code,
 		.index = fsize->index,
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
 	};
@@ -1436,8 +1494,6 @@ static int isc_enum_framesizes(struct file *file, void *fh,
 	if (ret)
 		return ret;
 
-	fse.code = isc->config.sd_format->mbus_code;
-
 	fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE;
 	fsize->discrete.width = fse.max_width;
 	fsize->discrete.height = fse.max_height;
@@ -1450,6 +1506,7 @@ static int isc_enum_frameintervals(struct file *file, void *fh,
 {
 	struct isc_device *isc = video_drvdata(file);
 	struct v4l2_subdev_frame_interval_enum fie = {
+		.code = isc->config.sd_format->mbus_code,
 		.index = fival->index,
 		.width = fival->width,
 		.height = fival->height,
@@ -1474,7 +1531,6 @@ static int isc_enum_frameintervals(struct file *file, void *fh,
 	if (ret)
 		return ret;
 
-	fie.code = isc->config.sd_format->mbus_code;
 	fival->type = V4L2_FRMIVAL_TYPE_DISCRETE;
 	fival->discrete = fie.interval;
 
diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c
index 428f117caa59..963dfd6e750e 100644
--- a/drivers/media/platform/atmel/atmel-isi.c
+++ b/drivers/media/platform/atmel/atmel-isi.c
@@ -148,7 +148,8 @@ static void configure_geometry(struct atmel_isi *isi)
 	u32 fourcc = isi->current_fmt->fourcc;
 
 	isi->enable_preview_path = fourcc == V4L2_PIX_FMT_RGB565 ||
-				   fourcc == V4L2_PIX_FMT_RGB32;
+				   fourcc == V4L2_PIX_FMT_RGB32 ||
+				   fourcc == V4L2_PIX_FMT_Y16;
 
 	/* According to sensor's output format to set cfg2 */
 	cfg2 = isi->current_fmt->swap;
@@ -554,12 +555,36 @@ static const struct isi_format *find_format_by_fourcc(struct atmel_isi *isi,
 	return NULL;
 }
 
+static void isi_try_fse(struct atmel_isi *isi, const struct isi_format *isi_fmt,
+			struct v4l2_subdev_pad_config *pad_cfg)
+{
+	int ret;
+	struct v4l2_subdev_frame_size_enum fse = {
+		.code = isi_fmt->mbus_code,
+		.which = V4L2_SUBDEV_FORMAT_TRY,
+	};
+
+	ret = v4l2_subdev_call(isi->entity.subdev, pad, enum_frame_size,
+			       pad_cfg, &fse);
+	/*
+	 * Attempt to obtain format size from subdev. If not available,
+	 * just use the maximum ISI can receive.
+	 */
+	if (ret) {
+		pad_cfg->try_crop.width = MAX_SUPPORT_WIDTH;
+		pad_cfg->try_crop.height = MAX_SUPPORT_HEIGHT;
+	} else {
+		pad_cfg->try_crop.width = fse.max_width;
+		pad_cfg->try_crop.height = fse.max_height;
+	}
+}
+
 static int isi_try_fmt(struct atmel_isi *isi, struct v4l2_format *f,
 		       const struct isi_format **current_fmt)
 {
 	const struct isi_format *isi_fmt;
 	struct v4l2_pix_format *pixfmt = &f->fmt.pix;
-	struct v4l2_subdev_pad_config pad_cfg;
+	struct v4l2_subdev_pad_config pad_cfg = {};
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_TRY,
 	};
@@ -576,6 +601,9 @@ static int isi_try_fmt(struct atmel_isi *isi, struct v4l2_format *f,
 	pixfmt->height = clamp(pixfmt->height, 0U, MAX_SUPPORT_HEIGHT);
 
 	v4l2_fill_mbus_format(&format.format, pixfmt, isi_fmt->mbus_code);
+
+	isi_try_fse(isi, isi_fmt, &pad_cfg);
+
 	ret = v4l2_subdev_call(isi->entity.subdev, pad, set_fmt,
 			       &pad_cfg, &format);
 	if (ret < 0)
@@ -990,6 +1018,16 @@ static const struct isi_format isi_formats[] = {
 		.mbus_code = MEDIA_BUS_FMT_VYUY8_2X8,
 		.bpp = 2,
 		.swap = ISI_CFG2_YCC_SWAP_MODE_1,
+	}, {
+		.fourcc = V4L2_PIX_FMT_GREY,
+		.mbus_code = MEDIA_BUS_FMT_Y10_1X10,
+		.bpp = 1,
+		.swap = ISI_CFG2_GS_MODE_2_PIXEL | ISI_CFG2_GRAYSCALE,
+	}, {
+		.fourcc = V4L2_PIX_FMT_Y16,
+		.mbus_code = MEDIA_BUS_FMT_Y10_1X10,
+		.bpp = 2,
+		.swap = ISI_CFG2_GS_MODE_2_PIXEL | ISI_CFG2_GRAYSCALE,
 	},
 };
 
diff --git a/drivers/media/platform/atmel/atmel-isi.h b/drivers/media/platform/atmel/atmel-isi.h
index 47a9108dba55..7ad3895a2c87 100644
--- a/drivers/media/platform/atmel/atmel-isi.h
+++ b/drivers/media/platform/atmel/atmel-isi.h
@@ -62,6 +62,8 @@
 #define		ISI_CFG1_THMASK_BEATS_16	(2 << 13)
 
 /* Bitfields in CFG2 */
+#define ISI_CFG2_GS_MODE_2_PIXEL		(0 << 11)
+#define ISI_CFG2_GS_MODE_1_PIXEL		(1 << 11)
 #define ISI_CFG2_GRAYSCALE			(1 << 13)
 #define ISI_CFG2_COL_SPACE_YCbCr		(0 << 15)
 #define ISI_CFG2_COL_SPACE_RGB			(1 << 15)
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 00c7bed3dd57..3443396ba5f3 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1629,6 +1629,9 @@ static void coda_finish_encode(struct coda_ctx *ctx)
 	struct coda_dev *dev = ctx->dev;
 	u32 wr_ptr, start_ptr;
 
+	if (ctx->aborting)
+		return;
+
 	/*
 	 * Lock to make sure that an encoder stop command running in parallel
 	 * will either already have marked src_buf as last, or it will wake up
@@ -2165,16 +2168,21 @@ static int coda_prepare_decode(struct coda_ctx *ctx)
 	} else {
 		if (dev->devtype->product == CODA_960) {
 			/*
-			 * The CODA960 seems to have an internal list of
-			 * buffers with 64 entries that includes the
-			 * registered frame buffers as well as the rotator
-			 * buffer output.
-			 *
-			 * ROT_INDEX needs to be < 0x40, but >
-			 * ctx->num_internal_frames.
+			 * It was previously assumed that the CODA960 has an
+			 * internal list of 64 buffer entries that contains
+			 * both the registered internal frame buffers as well
+			 * as the rotator buffer output, and that the ROT_INDEX
+			 * register must be set to a value between the last
+			 * internal frame buffers' index and 64.
+			 * At least on firmware version 3.1.1 it turns out that
+			 * setting ROT_INDEX to any value >= 32 causes CODA
+			 * hangups that it can not recover from with the SRC VPU
+			 * reset.
+			 * It does appear to work however, to just set it to a
+			 * fixed value in the [ctx->num_internal_frames, 31]
+			 * range, for example CODA_MAX_FRAMEBUFFERS.
 			 */
-			coda_write(dev,
-				   CODA_MAX_FRAMEBUFFERS + dst_buf->vb2_buf.index,
+			coda_write(dev, CODA_MAX_FRAMEBUFFERS,
 				   CODA9_CMD_DEC_PIC_ROT_INDEX);
 
 			reg_addr = CODA9_CMD_DEC_PIC_ROT_ADDR_Y;
@@ -2266,6 +2274,9 @@ static void coda_finish_decode(struct coda_ctx *ctx)
 	int err_vdoa = 0;
 	u32 val;
 
+	if (ctx->aborting)
+		return;
+
 	/* Update kfifo out pointer from coda bitstream read pointer */
 	coda_kfifo_sync_from_device(ctx);
 
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 94fb4d2ecc43..acff10ad257a 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -155,6 +155,7 @@ static const struct coda_codec coda7_codecs[] = {
 static const struct coda_codec coda9_codecs[] = {
 	CODA_CODEC(CODA9_MODE_ENCODE_H264, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_H264,   1920, 1088),
 	CODA_CODEC(CODA9_MODE_ENCODE_MP4,  V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_MPEG4,  1920, 1088),
+	CODA_CODEC(CODA9_MODE_ENCODE_MJPG, V4L2_PIX_FMT_YUV420, V4L2_PIX_FMT_JPEG,   8192, 8192),
 	CODA_CODEC(CODA9_MODE_DECODE_H264, V4L2_PIX_FMT_H264,   V4L2_PIX_FMT_YUV420, 1920, 1088),
 	CODA_CODEC(CODA9_MODE_DECODE_MP2,  V4L2_PIX_FMT_MPEG2,  V4L2_PIX_FMT_YUV420, 1920, 1088),
 	CODA_CODEC(CODA9_MODE_DECODE_MP4,  V4L2_PIX_FMT_MPEG4,  V4L2_PIX_FMT_YUV420, 1920, 1088),
@@ -235,6 +236,22 @@ static const struct coda_video_device coda_bit_jpeg_decoder = {
 	},
 };
 
+static const struct coda_video_device coda9_jpeg_encoder = {
+	.name = "coda-jpeg-encoder",
+	.type = CODA_INST_ENCODER,
+	.ops = &coda9_jpeg_encode_ops,
+	.direct = true,
+	.src_formats = {
+		V4L2_PIX_FMT_NV12,
+		V4L2_PIX_FMT_YUV420,
+		V4L2_PIX_FMT_YVU420,
+		V4L2_PIX_FMT_YUV422P,
+	},
+	.dst_formats = {
+		V4L2_PIX_FMT_JPEG,
+	},
+};
+
 static const struct coda_video_device *codadx6_video_devices[] = {
 	&coda_bit_encoder,
 };
@@ -252,6 +269,7 @@ static const struct coda_video_device *coda7_video_devices[] = {
 };
 
 static const struct coda_video_device *coda9_video_devices[] = {
+	&coda9_jpeg_encoder,
 	&coda_bit_encoder,
 	&coda_bit_decoder,
 };
@@ -721,7 +739,8 @@ static int coda_s_fmt(struct coda_ctx *ctx, struct v4l2_format *f,
 		ctx->tiled_map_type = GDI_TILED_FRAME_MB_RASTER_MAP;
 		break;
 	case V4L2_PIX_FMT_NV12:
-		if (!disable_tiling && ctx->dev->devtype->product == CODA_960) {
+		if (!disable_tiling && ctx->use_bit &&
+		    ctx->dev->devtype->product == CODA_960) {
 			ctx->tiled_map_type = GDI_TILED_FRAME_MB_RASTER_MAP;
 			break;
 		}
@@ -1421,7 +1440,7 @@ static void coda_pic_run_work(struct work_struct *work)
 
 		if (ctx->ops->run_timeout)
 			ctx->ops->run_timeout(ctx);
-	} else if (!ctx->aborting) {
+	} else {
 		ctx->ops->finish_run(ctx);
 	}
 
@@ -1787,7 +1806,7 @@ static void coda_buf_queue(struct vb2_buffer *vb)
 				coda_queue_source_change_event(ctx);
 		}
 	} else {
-		if (ctx->inst_type == CODA_INST_ENCODER &&
+		if ((ctx->inst_type == CODA_INST_ENCODER || !ctx->use_bit) &&
 		    vq->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
 			vbuf->sequence = ctx->qsequence++;
 		v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
@@ -2984,10 +3003,8 @@ static int coda_probe(struct platform_device *pdev)
 	irq = platform_get_irq_byname(pdev, "bit");
 	if (irq < 0)
 		irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "failed to get irq resource\n");
+	if (irq < 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(&pdev->dev, irq, coda_irq_handler, 0,
 			       dev_name(&pdev->dev), dev);
@@ -2996,6 +3013,22 @@ static int coda_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	/* JPEG IRQ */
+	if (dev->devtype->product == CODA_960) {
+		irq = platform_get_irq_byname(pdev, "jpeg");
+		if (irq < 0)
+			return irq;
+
+		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+						coda9_jpeg_irq_handler,
+						IRQF_ONESHOT, CODA_NAME " jpeg",
+						dev);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to request jpeg irq\n");
+			return ret;
+		}
+	}
+
 	dev->rstc = devm_reset_control_get_optional_exclusive(&pdev->dev,
 							      NULL);
 	if (IS_ERR(dev->rstc)) {
diff --git a/drivers/media/platform/coda/coda-jpeg.c b/drivers/media/platform/coda/coda-jpeg.c
index bf61a3ecc580..92234fd1f4fd 100644
--- a/drivers/media/platform/coda/coda-jpeg.c
+++ b/drivers/media/platform/coda/coda-jpeg.c
@@ -5,46 +5,68 @@
  * Copyright (C) 2014 Philipp Zabel, Pengutronix
  */
 
+#include <asm/unaligned.h>
+#include <linux/irqreturn.h>
 #include <linux/kernel.h>
+#include <linux/ktime.h>
+#include <linux/slab.h>
 #include <linux/swab.h>
+#include <linux/videodev2.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-dma-contig.h>
 
 #include "coda.h"
 #include "trace.h"
 
 #define SOI_MARKER	0xffd8
+#define DRI_MARKER	0xffdd
+#define DQT_MARKER	0xffdb
+#define DHT_MARKER	0xffc4
+#define SOF_MARKER	0xffc0
 #define EOI_MARKER	0xffd9
 
+enum {
+	CODA9_JPEG_FORMAT_420,
+	CODA9_JPEG_FORMAT_422,
+	CODA9_JPEG_FORMAT_224,
+	CODA9_JPEG_FORMAT_444,
+	CODA9_JPEG_FORMAT_400,
+};
+
+#define CODA9_JPEG_ENC_HUFF_DATA_SIZE	(256 + 256 + 16 + 16)
+
 /*
  * Typical Huffman tables for 8-bit precision luminance and
  * chrominance from JPEG ITU-T.81 (ISO/IEC 10918-1) Annex K.3
  */
 
-static const unsigned char luma_dc_bits[16] = {
+static const unsigned char luma_dc[16 + 12] = {
+	/* bits */
 	0x00, 0x01, 0x05, 0x01, 0x01, 0x01, 0x01, 0x01,
 	0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
-};
-
-static const unsigned char luma_dc_value[12] = {
+	/* values */
 	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
 	0x08, 0x09, 0x0a, 0x0b,
 };
 
-static const unsigned char chroma_dc_bits[16] = {
+static const unsigned char chroma_dc[16 + 12] = {
+	/* bits */
 	0x00, 0x03, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
 	0x01, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00,
-};
-
-static const unsigned char chroma_dc_value[12] = {
+	/* values */
 	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
 	0x08, 0x09, 0x0a, 0x0b,
 };
 
-static const unsigned char luma_ac_bits[16] = {
+static const unsigned char luma_ac[16 + 162 + 2] = {
+	/* bits */
 	0x00, 0x02, 0x01, 0x03, 0x03, 0x02, 0x04, 0x03,
 	0x05, 0x05, 0x04, 0x04, 0x00, 0x00, 0x01, 0x7d,
-};
-
-static const unsigned char luma_ac_value[162 + 2] = {
+	/* values */
 	0x01, 0x02, 0x03, 0x00, 0x04, 0x11, 0x05, 0x12,
 	0x21, 0x31, 0x41, 0x06, 0x13, 0x51, 0x61, 0x07,
 	0x22, 0x71, 0x14, 0x32, 0x81, 0x91, 0xa1, 0x08,
@@ -68,12 +90,11 @@ static const unsigned char luma_ac_value[162 + 2] = {
 	0xf9, 0xfa, /* padded to 32-bit */
 };
 
-static const unsigned char chroma_ac_bits[16] = {
+static const unsigned char chroma_ac[16 + 162 + 2] = {
+	/* bits */
 	0x00, 0x02, 0x01, 0x02, 0x04, 0x04, 0x03, 0x04,
 	0x07, 0x05, 0x04, 0x04, 0x00, 0x01, 0x02, 0x77,
-};
-
-static const unsigned char chroma_ac_value[162 + 2] = {
+	/* values */
 	0x00, 0x01, 0x02, 0x03, 0x11, 0x04, 0x05, 0x21,
 	0x31, 0x06, 0x12, 0x41, 0x51, 0x07, 0x61, 0x71,
 	0x13, 0x22, 0x32, 0x81, 0x08, 0x14, 0x42, 0x91,
@@ -124,6 +145,38 @@ static unsigned char chroma_q[64] = {
 	0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c, 0x0c,
 };
 
+static const unsigned char width_align[] = {
+	[CODA9_JPEG_FORMAT_420] = 16,
+	[CODA9_JPEG_FORMAT_422] = 16,
+	[CODA9_JPEG_FORMAT_224] = 8,
+	[CODA9_JPEG_FORMAT_444] = 8,
+	[CODA9_JPEG_FORMAT_400] = 8,
+};
+
+static const unsigned char height_align[] = {
+	[CODA9_JPEG_FORMAT_420] = 16,
+	[CODA9_JPEG_FORMAT_422] = 8,
+	[CODA9_JPEG_FORMAT_224] = 16,
+	[CODA9_JPEG_FORMAT_444] = 8,
+	[CODA9_JPEG_FORMAT_400] = 8,
+};
+
+static int coda9_jpeg_chroma_format(u32 pixfmt)
+{
+	switch (pixfmt) {
+	case V4L2_PIX_FMT_YUV420:
+	case V4L2_PIX_FMT_NV12:
+		return CODA9_JPEG_FORMAT_420;
+	case V4L2_PIX_FMT_YUV422P:
+		return CODA9_JPEG_FORMAT_422;
+	case V4L2_PIX_FMT_YUV444:
+		return CODA9_JPEG_FORMAT_444;
+	case V4L2_PIX_FMT_GREY:
+		return CODA9_JPEG_FORMAT_400;
+	}
+	return -EINVAL;
+}
+
 struct coda_memcpy_desc {
 	int offset;
 	const void *src;
@@ -148,14 +201,10 @@ int coda_jpeg_write_tables(struct coda_ctx *ctx)
 {
 	int i;
 	static const struct coda_memcpy_desc huff[8] = {
-		{ 0,   luma_dc_bits,    sizeof(luma_dc_bits)    },
-		{ 16,  luma_dc_value,   sizeof(luma_dc_value)   },
-		{ 32,  luma_ac_bits,    sizeof(luma_ac_bits)    },
-		{ 48,  luma_ac_value,   sizeof(luma_ac_value)   },
-		{ 216, chroma_dc_bits,  sizeof(chroma_dc_bits)  },
-		{ 232, chroma_dc_value, sizeof(chroma_dc_value) },
-		{ 248, chroma_ac_bits,  sizeof(chroma_ac_bits)  },
-		{ 264, chroma_ac_value, sizeof(chroma_ac_value) },
+		{ 0,   luma_dc,    sizeof(luma_dc)    },
+		{ 32,  luma_ac,    sizeof(luma_ac)    },
+		{ 216, chroma_dc,  sizeof(chroma_dc)  },
+		{ 248, chroma_ac,  sizeof(chroma_ac)  },
 	};
 	struct coda_memcpy_desc qmat[3] = {
 		{ 512, ctx->params.jpeg_qmat_tab[0], 64 },
@@ -198,6 +247,379 @@ bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_buffer *vb)
 	return false;
 }
 
+static const int bus_req_num[] = {
+	[CODA9_JPEG_FORMAT_420] = 2,
+	[CODA9_JPEG_FORMAT_422] = 3,
+	[CODA9_JPEG_FORMAT_224] = 3,
+	[CODA9_JPEG_FORMAT_444] = 4,
+	[CODA9_JPEG_FORMAT_400] = 4,
+};
+
+#define MCU_INFO(mcu_block_num, comp_num, comp0_info, comp1_info, comp2_info) \
+	(((mcu_block_num) << CODA9_JPEG_MCU_BLOCK_NUM_OFFSET) | \
+	 ((comp_num) << CODA9_JPEG_COMP_NUM_OFFSET) | \
+	 ((comp0_info) << CODA9_JPEG_COMP0_INFO_OFFSET) | \
+	 ((comp1_info) << CODA9_JPEG_COMP1_INFO_OFFSET) | \
+	 ((comp2_info) << CODA9_JPEG_COMP2_INFO_OFFSET))
+
+static const u32 mcu_info[] = {
+	[CODA9_JPEG_FORMAT_420] = MCU_INFO(6, 3, 10, 5, 5),
+	[CODA9_JPEG_FORMAT_422] = MCU_INFO(4, 3, 9, 5, 5),
+	[CODA9_JPEG_FORMAT_224] = MCU_INFO(4, 3, 6, 5, 5),
+	[CODA9_JPEG_FORMAT_444] = MCU_INFO(3, 3, 5, 5, 5),
+	[CODA9_JPEG_FORMAT_400] = MCU_INFO(1, 1, 5, 0, 0),
+};
+
+/*
+ * Convert Huffman table specifcations to tables of codes and code lengths.
+ * For reference, see JPEG ITU-T.81 (ISO/IEC 10918-1) [1]
+ *
+ * [1] https://www.w3.org/Graphics/JPEG/itu-t81.pdf
+ */
+static int coda9_jpeg_gen_enc_huff_tab(struct coda_ctx *ctx, int tab_num,
+				       int *ehufsi, int *ehufco)
+{
+	int i, j, k, lastk, si, code, maxsymbol;
+	const u8 *bits, *huffval;
+	struct {
+		int size[256];
+		int code[256];
+	} *huff;
+	static const unsigned char *huff_tabs[4] = {
+		luma_dc, luma_ac, chroma_dc, chroma_ac,
+	};
+	int ret = -EINVAL;
+
+	huff = kzalloc(sizeof(*huff), GFP_KERNEL);
+	if (!huff)
+		return -ENOMEM;
+
+	bits = huff_tabs[tab_num];
+	huffval = huff_tabs[tab_num] + 16;
+
+	maxsymbol = tab_num & 1 ? 256 : 16;
+
+	/* Figure C.1 - Generation of table of Huffman code sizes */
+	k = 0;
+	for (i = 1; i <= 16; i++) {
+		j = bits[i - 1];
+		if (k + j > maxsymbol)
+			goto out;
+		while (j--)
+			huff->size[k++] = i;
+	}
+	lastk = k;
+
+	/* Figure C.2 - Generation of table of Huffman codes */
+	k = 0;
+	code = 0;
+	si = huff->size[0];
+	while (k < lastk) {
+		while (huff->size[k] == si) {
+			huff->code[k++] = code;
+			code++;
+		}
+		if (code >= (1 << si))
+			goto out;
+		code <<= 1;
+		si++;
+	}
+
+	/* Figure C.3 - Ordering procedure for encoding procedure code tables */
+	for (k = 0; k < lastk; k++) {
+		i = huffval[k];
+		if (i >= maxsymbol || ehufsi[i])
+			goto out;
+		ehufco[i] = huff->code[k];
+		ehufsi[i] = huff->size[k];
+	}
+
+	ret = 0;
+out:
+	kfree(huff);
+	return ret;
+}
+
+#define DC_TABLE_INDEX0		    0
+#define AC_TABLE_INDEX0		    1
+#define DC_TABLE_INDEX1		    2
+#define AC_TABLE_INDEX1		    3
+
+static int coda9_jpeg_load_huff_tab(struct coda_ctx *ctx)
+{
+	struct {
+		int size[4][256];
+		int code[4][256];
+	} *huff;
+	u32 *huff_data;
+	int i, j;
+	int ret;
+
+	huff = kzalloc(sizeof(*huff), GFP_KERNEL);
+	if (!huff)
+		return -ENOMEM;
+
+	/* Generate all four (luma/chroma DC/AC) code/size lookup tables */
+	for (i = 0; i < 4; i++) {
+		ret = coda9_jpeg_gen_enc_huff_tab(ctx, i, huff->size[i],
+						  huff->code[i]);
+		if (ret)
+			goto out;
+	}
+
+	if (!ctx->params.jpeg_huff_data) {
+		ctx->params.jpeg_huff_data =
+			kzalloc(sizeof(u32) * CODA9_JPEG_ENC_HUFF_DATA_SIZE,
+				GFP_KERNEL);
+		if (!ctx->params.jpeg_huff_data) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+	huff_data = ctx->params.jpeg_huff_data;
+
+	for (j = 0; j < 4; j++) {
+		/* Store Huffman lookup tables in AC0, AC1, DC0, DC1 order */
+		int t = (j == 0) ? AC_TABLE_INDEX0 :
+			(j == 1) ? AC_TABLE_INDEX1 :
+			(j == 2) ? DC_TABLE_INDEX0 :
+				   DC_TABLE_INDEX1;
+		/* DC tables only have 16 entries */
+		int len = (j < 2) ? 256 : 16;
+
+		for (i = 0; i < len; i++) {
+			if (huff->size[t][i] == 0 && huff->code[t][i] == 0)
+				*(huff_data++) = 0;
+			else
+				*(huff_data++) =
+					((huff->size[t][i] - 1) << 16) |
+					huff->code[t][i];
+		}
+	}
+
+	ret = 0;
+out:
+	kfree(huff);
+	return ret;
+}
+
+static void coda9_jpeg_write_huff_tab(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	u32 *huff_data = ctx->params.jpeg_huff_data;
+	int i;
+
+	/* Write Huffman size/code lookup tables in AC0, AC1, DC0, DC1 order */
+	coda_write(dev, 0x3, CODA9_REG_JPEG_HUFF_CTRL);
+	for (i = 0; i < CODA9_JPEG_ENC_HUFF_DATA_SIZE; i++)
+		coda_write(dev, *(huff_data++), CODA9_REG_JPEG_HUFF_DATA);
+	coda_write(dev, 0x0, CODA9_REG_JPEG_HUFF_CTRL);
+}
+
+static inline void coda9_jpeg_write_qmat_quotients(struct coda_dev *dev,
+						   u8 *qmat, int index)
+{
+	int i;
+
+	coda_write(dev, index | 0x3, CODA9_REG_JPEG_QMAT_CTRL);
+	for (i = 0; i < 64; i++)
+		coda_write(dev, 0x80000 / qmat[i], CODA9_REG_JPEG_QMAT_DATA);
+	coda_write(dev, index, CODA9_REG_JPEG_QMAT_CTRL);
+}
+
+static void coda9_jpeg_load_qmat_tab(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	u8 *luma_tab;
+	u8 *chroma_tab;
+
+	luma_tab = ctx->params.jpeg_qmat_tab[0];
+	if (!luma_tab)
+		luma_tab = luma_q;
+
+	chroma_tab = ctx->params.jpeg_qmat_tab[1];
+	if (!chroma_tab)
+		chroma_tab = chroma_q;
+
+	coda9_jpeg_write_qmat_quotients(dev, luma_tab, 0x00);
+	coda9_jpeg_write_qmat_quotients(dev, chroma_tab, 0x40);
+	coda9_jpeg_write_qmat_quotients(dev, chroma_tab, 0x80);
+}
+
+struct coda_jpeg_stream {
+	u8 *curr;
+	u8 *end;
+};
+
+static inline int coda_jpeg_put_byte(u8 byte, struct coda_jpeg_stream *stream)
+{
+	if (stream->curr >= stream->end)
+		return -EINVAL;
+
+	*stream->curr++ = byte;
+
+	return 0;
+}
+
+static inline int coda_jpeg_put_word(u16 word, struct coda_jpeg_stream *stream)
+{
+	if (stream->curr + sizeof(__be16) > stream->end)
+		return -EINVAL;
+
+	put_unaligned_be16(word, stream->curr);
+	stream->curr += sizeof(__be16);
+
+	return 0;
+}
+
+static int coda_jpeg_put_table(u16 marker, u8 index, const u8 *table,
+			       size_t len, struct coda_jpeg_stream *stream)
+{
+	int i, ret;
+
+	ret = coda_jpeg_put_word(marker, stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_put_word(3 + len, stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_put_byte(index, stream);
+	for (i = 0; i < len && ret == 0; i++)
+		ret = coda_jpeg_put_byte(table[i], stream);
+
+	return ret;
+}
+
+static int coda_jpeg_define_quantization_table(struct coda_ctx *ctx, u8 index,
+					       struct coda_jpeg_stream *stream)
+{
+	return coda_jpeg_put_table(DQT_MARKER, index,
+				   ctx->params.jpeg_qmat_tab[index], 64,
+				   stream);
+}
+
+static int coda_jpeg_define_huffman_table(u8 index, const u8 *table, size_t len,
+					  struct coda_jpeg_stream *stream)
+{
+	return coda_jpeg_put_table(DHT_MARKER, index, table, len, stream);
+}
+
+static int coda9_jpeg_encode_header(struct coda_ctx *ctx, int len, u8 *buf)
+{
+	struct coda_jpeg_stream stream = { buf, buf + len };
+	struct coda_q_data *q_data_src;
+	int chroma_format, comp_num;
+	int i, ret, pad;
+
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	chroma_format = coda9_jpeg_chroma_format(q_data_src->fourcc);
+	if (chroma_format < 0)
+		return 0;
+
+	/* Start Of Image */
+	ret = coda_jpeg_put_word(SOI_MARKER, &stream);
+	if (ret < 0)
+		return ret;
+
+	/* Define Restart Interval */
+	if (ctx->params.jpeg_restart_interval) {
+		ret = coda_jpeg_put_word(DRI_MARKER, &stream);
+		if (ret < 0)
+			return ret;
+		ret = coda_jpeg_put_word(4, &stream);
+		if (ret < 0)
+			return ret;
+		ret = coda_jpeg_put_word(ctx->params.jpeg_restart_interval,
+					 &stream);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Define Quantization Tables */
+	ret = coda_jpeg_define_quantization_table(ctx, 0x00, &stream);
+	if (ret < 0)
+		return ret;
+	if (chroma_format != CODA9_JPEG_FORMAT_400) {
+		ret = coda_jpeg_define_quantization_table(ctx, 0x01, &stream);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Define Huffman Tables */
+	ret = coda_jpeg_define_huffman_table(0x00, luma_dc, 16 + 12, &stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_define_huffman_table(0x10, luma_ac, 16 + 162, &stream);
+	if (ret < 0)
+		return ret;
+	if (chroma_format != CODA9_JPEG_FORMAT_400) {
+		ret = coda_jpeg_define_huffman_table(0x01, chroma_dc, 16 + 12,
+						     &stream);
+		if (ret < 0)
+			return ret;
+		ret = coda_jpeg_define_huffman_table(0x11, chroma_ac, 16 + 162,
+						     &stream);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Start Of Frame */
+	ret = coda_jpeg_put_word(SOF_MARKER, &stream);
+	if (ret < 0)
+		return ret;
+	comp_num = (chroma_format == CODA9_JPEG_FORMAT_400) ? 1 : 3;
+	ret = coda_jpeg_put_word(8 + comp_num * 3, &stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_put_byte(0x08, &stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_put_word(q_data_src->height, &stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_put_word(q_data_src->width, &stream);
+	if (ret < 0)
+		return ret;
+	ret = coda_jpeg_put_byte(comp_num, &stream);
+	if (ret < 0)
+		return ret;
+	for (i = 0; i < comp_num; i++) {
+		static unsigned char subsampling[5][3] = {
+			[CODA9_JPEG_FORMAT_420] = { 0x22, 0x11, 0x11 },
+			[CODA9_JPEG_FORMAT_422] = { 0x21, 0x11, 0x11 },
+			[CODA9_JPEG_FORMAT_224] = { 0x12, 0x11, 0x11 },
+			[CODA9_JPEG_FORMAT_444] = { 0x11, 0x11, 0x11 },
+			[CODA9_JPEG_FORMAT_400] = { 0x11 },
+		};
+
+		/* Component identifier, matches SOS */
+		ret = coda_jpeg_put_byte(i + 1, &stream);
+		if (ret < 0)
+			return ret;
+		ret = coda_jpeg_put_byte(subsampling[chroma_format][i],
+					 &stream);
+		if (ret < 0)
+			return ret;
+		/* Chroma table index */
+		ret = coda_jpeg_put_byte((i == 0) ? 0 : 1, &stream);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Pad to multiple of 8 bytes */
+	pad = (stream.curr - buf) % 8;
+	if (pad) {
+		pad = 8 - pad;
+		while (pad--) {
+			ret = coda_jpeg_put_byte(0x00, &stream);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return stream.curr - buf;
+}
+
 /*
  * Scale quantization table using nonlinear scaling factor
  * u8 qtab[64], scale [50,190]
@@ -247,3 +669,279 @@ void coda_set_jpeg_compression_quality(struct coda_ctx *ctx, int quality)
 		coda_scale_quant_table(ctx->params.jpeg_qmat_tab[1], scale);
 	}
 }
+
+/*
+ * Encoder context operations
+ */
+
+static int coda9_jpeg_start_encoding(struct coda_ctx *ctx)
+{
+	struct coda_dev *dev = ctx->dev;
+	int ret;
+
+	ret = coda9_jpeg_load_huff_tab(ctx);
+	if (ret < 0) {
+		v4l2_err(&dev->v4l2_dev, "error loading Huffman tables\n");
+		return ret;
+	}
+	if (!ctx->params.jpeg_qmat_tab[0])
+		ctx->params.jpeg_qmat_tab[0] = kmalloc(64, GFP_KERNEL);
+	if (!ctx->params.jpeg_qmat_tab[1])
+		ctx->params.jpeg_qmat_tab[1] = kmalloc(64, GFP_KERNEL);
+	coda_set_jpeg_compression_quality(ctx, ctx->params.jpeg_quality);
+
+	return 0;
+}
+
+static int coda9_jpeg_prepare_encode(struct coda_ctx *ctx)
+{
+	struct coda_q_data *q_data_src;
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+	struct coda_dev *dev = ctx->dev;
+	u32 start_addr, end_addr;
+	u16 aligned_width, aligned_height;
+	bool chroma_interleave;
+	int chroma_format;
+	int header_len;
+	int ret;
+	ktime_t timeout;
+
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+	q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+
+	if (vb2_get_plane_payload(&src_buf->vb2_buf, 0) == 0)
+		vb2_set_plane_payload(&src_buf->vb2_buf, 0,
+				      vb2_plane_size(&src_buf->vb2_buf, 0));
+
+	src_buf->sequence = ctx->osequence;
+	dst_buf->sequence = ctx->osequence;
+	ctx->osequence++;
+
+	src_buf->flags |= V4L2_BUF_FLAG_KEYFRAME;
+	src_buf->flags &= ~V4L2_BUF_FLAG_PFRAME;
+
+	coda_set_gdi_regs(ctx);
+
+	start_addr = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
+	end_addr = start_addr + vb2_plane_size(&dst_buf->vb2_buf, 0);
+
+	chroma_format = coda9_jpeg_chroma_format(q_data_src->fourcc);
+	if (chroma_format < 0)
+		return chroma_format;
+
+	/* Round image dimensions to multiple of MCU size */
+	aligned_width = round_up(q_data_src->width, width_align[chroma_format]);
+	aligned_height = round_up(q_data_src->height,
+				  height_align[chroma_format]);
+	if (aligned_width != q_data_src->bytesperline) {
+		v4l2_err(&dev->v4l2_dev, "wrong stride: %d instead of %d\n",
+			 aligned_width, q_data_src->bytesperline);
+	}
+
+	header_len =
+		coda9_jpeg_encode_header(ctx,
+					 vb2_plane_size(&dst_buf->vb2_buf, 0),
+					 vb2_plane_vaddr(&dst_buf->vb2_buf, 0));
+	if (header_len < 0)
+		return header_len;
+
+	coda_write(dev, start_addr + header_len, CODA9_REG_JPEG_BBC_BAS_ADDR);
+	coda_write(dev, end_addr, CODA9_REG_JPEG_BBC_END_ADDR);
+	coda_write(dev, start_addr + header_len, CODA9_REG_JPEG_BBC_WR_PTR);
+	coda_write(dev, start_addr + header_len, CODA9_REG_JPEG_BBC_RD_PTR);
+	coda_write(dev, 0, CODA9_REG_JPEG_BBC_CUR_POS);
+	/* 64 words per 256-byte page */
+	coda_write(dev, 64, CODA9_REG_JPEG_BBC_DATA_CNT);
+	coda_write(dev, start_addr, CODA9_REG_JPEG_BBC_EXT_ADDR);
+	coda_write(dev, 0, CODA9_REG_JPEG_BBC_INT_ADDR);
+
+	coda_write(dev, 0, CODA9_REG_JPEG_GBU_BT_PTR);
+	coda_write(dev, 0, CODA9_REG_JPEG_GBU_WD_PTR);
+	coda_write(dev, 0, CODA9_REG_JPEG_GBU_BBSR);
+	coda_write(dev, 0, CODA9_REG_JPEG_BBC_STRM_CTRL);
+	coda_write(dev, 0, CODA9_REG_JPEG_GBU_CTRL);
+	coda_write(dev, 0, CODA9_REG_JPEG_GBU_FF_RPTR);
+	coda_write(dev, 127, CODA9_REG_JPEG_GBU_BBER);
+	coda_write(dev, 64, CODA9_REG_JPEG_GBU_BBIR);
+	coda_write(dev, 64, CODA9_REG_JPEG_GBU_BBHR);
+
+	chroma_interleave = (q_data_src->fourcc == V4L2_PIX_FMT_NV12);
+	coda_write(dev, CODA9_JPEG_PIC_CTRL_TC_DIRECTION |
+		   CODA9_JPEG_PIC_CTRL_ENCODER_EN, CODA9_REG_JPEG_PIC_CTRL);
+	coda_write(dev, 0, CODA9_REG_JPEG_SCL_INFO);
+	coda_write(dev, chroma_interleave, CODA9_REG_JPEG_DPB_CONFIG);
+	coda_write(dev, ctx->params.jpeg_restart_interval,
+		   CODA9_REG_JPEG_RST_INTVAL);
+	coda_write(dev, 1, CODA9_REG_JPEG_BBC_CTRL);
+
+	coda_write(dev, bus_req_num[chroma_format], CODA9_REG_JPEG_OP_INFO);
+
+	coda9_jpeg_write_huff_tab(ctx);
+	coda9_jpeg_load_qmat_tab(ctx);
+
+	if (ctx->params.rot_mode & CODA_ROT_90) {
+		aligned_width = aligned_height;
+		aligned_height = q_data_src->bytesperline;
+		if (chroma_format == CODA9_JPEG_FORMAT_422)
+			chroma_format = CODA9_JPEG_FORMAT_224;
+		else if (chroma_format == CODA9_JPEG_FORMAT_224)
+			chroma_format = CODA9_JPEG_FORMAT_422;
+	}
+	/* These need to be multiples of MCU size */
+	coda_write(dev, aligned_width << 16 | aligned_height,
+		   CODA9_REG_JPEG_PIC_SIZE);
+	coda_write(dev, ctx->params.rot_mode ?
+		   (CODA_ROT_MIR_ENABLE | ctx->params.rot_mode) : 0,
+		   CODA9_REG_JPEG_ROT_INFO);
+
+	coda_write(dev, mcu_info[chroma_format], CODA9_REG_JPEG_MCU_INFO);
+
+	coda_write(dev, 1, CODA9_GDI_CONTROL);
+	timeout = ktime_add_us(ktime_get(), 100000);
+	do {
+		ret = coda_read(dev, CODA9_GDI_STATUS);
+		if (ktime_compare(ktime_get(), timeout) > 0) {
+			v4l2_err(&dev->v4l2_dev, "timeout waiting for GDI\n");
+			return -ETIMEDOUT;
+		}
+	} while (!ret);
+
+	coda_write(dev, (chroma_format << 17) | (chroma_interleave << 16) |
+		   q_data_src->bytesperline, CODA9_GDI_INFO_CONTROL);
+	/* The content of this register seems to be irrelevant: */
+	coda_write(dev, aligned_width << 16 | aligned_height,
+		   CODA9_GDI_INFO_PIC_SIZE);
+
+	coda_write_base(ctx, q_data_src, src_buf, CODA9_GDI_INFO_BASE_Y);
+
+	coda_write(dev, 0, CODA9_REG_JPEG_DPB_BASE00);
+	coda_write(dev, 0, CODA9_GDI_CONTROL);
+	coda_write(dev, 1, CODA9_GDI_PIC_INIT_HOST);
+
+	coda_write(dev, 1, CODA9_GDI_WPROT_ERR_CLR);
+	coda_write(dev, 0, CODA9_GDI_WPROT_RGN_EN);
+
+	trace_coda_jpeg_run(ctx, src_buf);
+
+	coda_write(dev, 1, CODA9_REG_JPEG_PIC_START);
+
+	return 0;
+}
+
+static void coda9_jpeg_finish_encode(struct coda_ctx *ctx)
+{
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+	struct coda_dev *dev = ctx->dev;
+	u32 wr_ptr, start_ptr;
+	u32 err_mb;
+
+	if (ctx->aborting) {
+		coda_write(ctx->dev, 0, CODA9_REG_JPEG_BBC_FLUSH_CMD);
+		return;
+	}
+
+	/*
+	 * Lock to make sure that an encoder stop command running in parallel
+	 * will either already have marked src_buf as last, or it will wake up
+	 * the capture queue after the buffers are returned.
+	 */
+	mutex_lock(&ctx->wakeup_mutex);
+	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+
+	trace_coda_jpeg_done(ctx, dst_buf);
+
+	/*
+	 * Set plane payload to the number of bytes written out
+	 * by the JPEG processing unit
+	 */
+	start_ptr = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
+	wr_ptr = coda_read(dev, CODA9_REG_JPEG_BBC_WR_PTR);
+	vb2_set_plane_payload(&dst_buf->vb2_buf, 0, wr_ptr - start_ptr);
+
+	err_mb = coda_read(dev, CODA9_REG_JPEG_PIC_ERRMB);
+	if (err_mb)
+		coda_dbg(1, ctx, "ERRMB: 0x%x\n", err_mb);
+
+	coda_write(dev, 0, CODA9_REG_JPEG_BBC_FLUSH_CMD);
+
+	dst_buf->flags &= ~(V4L2_BUF_FLAG_PFRAME | V4L2_BUF_FLAG_LAST);
+	dst_buf->flags |= V4L2_BUF_FLAG_KEYFRAME;
+	dst_buf->flags |= src_buf->flags & V4L2_BUF_FLAG_LAST;
+
+	v4l2_m2m_buf_copy_metadata(src_buf, dst_buf, false);
+
+	v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
+	coda_m2m_buf_done(ctx, dst_buf, err_mb ? VB2_BUF_STATE_ERROR :
+						 VB2_BUF_STATE_DONE);
+	mutex_unlock(&ctx->wakeup_mutex);
+
+	coda_dbg(1, ctx, "job finished: encoded frame (%u)%s\n",
+		 dst_buf->sequence,
+		 (dst_buf->flags & V4L2_BUF_FLAG_LAST) ? " (last)" : "");
+}
+
+static void coda9_jpeg_release(struct coda_ctx *ctx)
+{
+	int i;
+
+	if (ctx->params.jpeg_qmat_tab[0] == luma_q)
+		ctx->params.jpeg_qmat_tab[0] = NULL;
+	if (ctx->params.jpeg_qmat_tab[1] == chroma_q)
+		ctx->params.jpeg_qmat_tab[1] = NULL;
+	for (i = 0; i < 3; i++)
+		kfree(ctx->params.jpeg_qmat_tab[i]);
+	kfree(ctx->params.jpeg_huff_data);
+}
+
+const struct coda_context_ops coda9_jpeg_encode_ops = {
+	.queue_init = coda_encoder_queue_init,
+	.start_streaming = coda9_jpeg_start_encoding,
+	.prepare_run = coda9_jpeg_prepare_encode,
+	.finish_run = coda9_jpeg_finish_encode,
+	.release = coda9_jpeg_release,
+};
+
+irqreturn_t coda9_jpeg_irq_handler(int irq, void *data)
+{
+	struct coda_dev *dev = data;
+	struct coda_ctx *ctx;
+	int status;
+	int err_mb;
+
+	status = coda_read(dev, CODA9_REG_JPEG_PIC_STATUS);
+	if (status == 0)
+		return IRQ_HANDLED;
+	coda_write(dev, status, CODA9_REG_JPEG_PIC_STATUS);
+
+	if (status & CODA9_JPEG_STATUS_OVERFLOW)
+		v4l2_err(&dev->v4l2_dev, "JPEG overflow\n");
+
+	if (status & CODA9_JPEG_STATUS_BBC_INT)
+		v4l2_err(&dev->v4l2_dev, "JPEG BBC interrupt\n");
+
+	if (status & CODA9_JPEG_STATUS_ERROR) {
+		v4l2_err(&dev->v4l2_dev, "JPEG error\n");
+
+		err_mb = coda_read(dev, CODA9_REG_JPEG_PIC_ERRMB);
+		if (err_mb) {
+			v4l2_err(&dev->v4l2_dev,
+				 "ERRMB: 0x%x: rst idx %d, mcu pos (%d,%d)\n",
+				 err_mb, err_mb >> 24, (err_mb >> 12) & 0xfff,
+				 err_mb & 0xfff);
+		}
+	}
+
+	ctx = v4l2_m2m_get_curr_priv(dev->m2m_dev);
+	if (!ctx) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Instance released before the end of transaction\n");
+		mutex_unlock(&dev->coda_mutex);
+		return IRQ_HANDLED;
+	}
+
+	complete(&ctx->completion);
+
+	return IRQ_HANDLED;
+}
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index 9f226140b486..43bda175f517 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -126,6 +126,7 @@ struct coda_params {
 	u8			jpeg_quality;
 	u8			jpeg_restart_interval;
 	u8			*jpeg_qmat_tab[3];
+	u32			*jpeg_huff_data;
 	int			codec_mode;
 	int			codec_mode_aux;
 	enum v4l2_mpeg_video_multi_slice_mode slice_mode;
@@ -366,7 +367,9 @@ void coda_set_jpeg_compression_quality(struct coda_ctx *ctx, int quality);
 
 extern const struct coda_context_ops coda_bit_encode_ops;
 extern const struct coda_context_ops coda_bit_decode_ops;
+extern const struct coda_context_ops coda9_jpeg_encode_ops;
 
 irqreturn_t coda_irq_handler(int irq, void *data);
+irqreturn_t coda9_jpeg_irq_handler(int irq, void *data);
 
 #endif /* __CODA_H__ */
diff --git a/drivers/media/platform/coda/coda_regs.h b/drivers/media/platform/coda/coda_regs.h
index b17464b56d3d..da5bb3212528 100644
--- a/drivers/media/platform/coda/coda_regs.h
+++ b/drivers/media/platform/coda/coda_regs.h
@@ -451,12 +451,21 @@
 #define CODA9_CMD_FIRMWARE_CODE_REV		0x1c4
 
 #define CODA9_GDMA_BASE				0x1000
+#define CODA9_GDI_CONTROL			(CODA9_GDMA_BASE + 0x034)
+#define CODA9_GDI_PIC_INIT_HOST			(CODA9_GDMA_BASE + 0x038)
+#define CODA9_GDI_STATUS			(CODA9_GDMA_BASE + 0x080)
 #define CODA9_GDI_WPROT_ERR_CLR			(CODA9_GDMA_BASE + 0x0a0)
 #define CODA9_GDI_WPROT_RGN_EN			(CODA9_GDMA_BASE + 0x0ac)
 
 #define CODA9_GDI_BUS_CTRL			(CODA9_GDMA_BASE + 0x0f0)
 #define CODA9_GDI_BUS_STATUS			(CODA9_GDMA_BASE + 0x0f4)
 
+#define CODA9_GDI_INFO_CONTROL			(CODA9_GDMA_BASE + 0x400)
+#define CODA9_GDI_INFO_PIC_SIZE			(CODA9_GDMA_BASE + 0x404)
+#define CODA9_GDI_INFO_BASE_Y			(CODA9_GDMA_BASE + 0x408)
+#define CODA9_GDI_INFO_BASE_CB			(CODA9_GDMA_BASE + 0x40c)
+#define CODA9_GDI_INFO_BASE_CR			(CODA9_GDMA_BASE + 0x410)
+
 #define CODA9_GDI_XY2_CAS_0			(CODA9_GDMA_BASE + 0x800)
 #define CODA9_GDI_XY2_CAS_F			(CODA9_GDMA_BASE + 0x83c)
 
@@ -477,4 +486,78 @@
 #define CODA9_GDI_RBC2_AXI_1F			(CODA9_GDMA_BASE + 0x91c)
 #define	CODA9_GDI_TILEDBUF_BASE			(CODA9_GDMA_BASE + 0x920)
 
+#define CODA9_JPEG_BASE				0x3000
+#define CODA9_REG_JPEG_PIC_START		(CODA9_JPEG_BASE + 0x000)
+#define CODA9_REG_JPEG_PIC_STATUS		(CODA9_JPEG_BASE + 0x004)
+#define		CODA9_JPEG_STATUS_OVERFLOW		BIT(3)
+#define		CODA9_JPEG_STATUS_BBC_INT		BIT(2)
+#define		CODA9_JPEG_STATUS_ERROR			BIT(1)
+#define		CODA9_JPEG_STATUS_DONE			BIT(0)
+#define CODA9_REG_JPEG_PIC_ERRMB		(CODA9_JPEG_BASE + 0x008)
+#define		CODA9_JPEG_ERRMB_RESTART_IDX_MASK	(0xf << 24)
+#define		CODA9_JPEG_ERRMB_MCU_POS_X_MASK		(0xfff << 12)
+#define		CODA9_JPEG_ERRMB_MCU_POS_Y_MASK		0xfff
+#define CODA9_REG_JPEG_PIC_CTRL			(CODA9_JPEG_BASE + 0x010)
+#define		CODA9_JPEG_PIC_CTRL_USER_HUFFMAN_EN	BIT(6)
+#define		CODA9_JPEG_PIC_CTRL_TC_DIRECTION	BIT(4)
+#define		CODA9_JPEG_PIC_CTRL_ENCODER_EN		BIT(3)
+#define CODA9_REG_JPEG_PIC_SIZE			(CODA9_JPEG_BASE + 0x014)
+#define CODA9_REG_JPEG_MCU_INFO			(CODA9_JPEG_BASE + 0x018)
+#define		CODA9_JPEG_MCU_BLOCK_NUM_OFFSET		16
+#define		CODA9_JPEG_COMP_NUM_OFFSET		12
+#define		CODA9_JPEG_COMP0_INFO_OFFSET		8
+#define		CODA9_JPEG_COMP1_INFO_OFFSET		4
+#define		CODA9_JPEG_COMP2_INFO_OFFSET		0
+#define CODA9_REG_JPEG_ROT_INFO			(CODA9_JPEG_BASE + 0x01c)
+#define		CODA9_JPEG_ROT_MIR_ENABLE		BIT(4)
+#define		CODA9_JPEG_ROT_MIR_MODE_MASK		0xf
+#define CODA9_REG_JPEG_SCL_INFO			(CODA9_JPEG_BASE + 0x020)
+#define		CODA9_JPEG_SCL_ENABLE			BIT(4)
+#define		CODA9_JPEG_SCL_HOR_MODE_MASK		(0x3 << 2)
+#define		CODA9_JPEG_SCL_VER_MODE_MASK		(0x3 << 0)
+#define CODA9_REG_JPEG_IF_INFO			(CODA9_JPEG_BASE + 0x024)
+#define		CODA9_JPEG_SENS_IF_CLR			BIT(1)
+#define		CODA9_JPEG_DISP_IF_CLR			BIT(0)
+#define CODA9_REG_JPEG_OP_INFO			(CODA9_JPEG_BASE + 0x02c)
+#define		CODA9_JPEG_BUS_REQ_NUM_OFFSET		0
+#define		CODA9_JPEG_BUS_REQ_NUM_MASK		0x7
+#define CODA9_REG_JPEG_DPB_CONFIG		(CODA9_JPEG_BASE + 0x030)
+#define CODA9_REG_JPEG_DPB_BASE00		(CODA9_JPEG_BASE + 0x040)
+#define CODA9_REG_JPEG_HUFF_CTRL		(CODA9_JPEG_BASE + 0x080)
+#define CODA9_REG_JPEG_HUFF_ADDR		(CODA9_JPEG_BASE + 0x084)
+#define CODA9_REG_JPEG_HUFF_DATA		(CODA9_JPEG_BASE + 0x088)
+#define CODA9_REG_JPEG_QMAT_CTRL		(CODA9_JPEG_BASE + 0x090)
+#define CODA9_REG_JPEG_QMAT_ADDR		(CODA9_JPEG_BASE + 0x094)
+#define CODA9_REG_JPEG_QMAT_DATA		(CODA9_JPEG_BASE + 0x098)
+#define CODA9_REG_JPEG_RST_INTVAL		(CODA9_JPEG_BASE + 0x0b0)
+#define CODA9_REG_JPEG_RST_INDEX		(CODA9_JPEG_BASE + 0x0b4)
+#define CODA9_REG_JPEG_RST_COUNT		(CODA9_JPEG_BASE + 0x0b8)
+#define CODA9_REG_JPEG_DPCM_DIFF_Y		(CODA9_JPEG_BASE + 0x0f0)
+#define CODA9_REG_JPEG_DPCM_DIFF_CB		(CODA9_JPEG_BASE + 0x0f4)
+#define CODA9_REG_JPEG_DPCM_DIFF_CR		(CODA9_JPEG_BASE + 0x0f8)
+#define CODA9_REG_JPEG_GBU_CTRL			(CODA9_JPEG_BASE + 0x100)
+#define CODA9_REG_JPEG_GBU_BT_PTR		(CODA9_JPEG_BASE + 0x110)
+#define CODA9_REG_JPEG_GBU_WD_PTR		(CODA9_JPEG_BASE + 0x114)
+#define CODA9_REG_JPEG_GBU_TT_CNT		(CODA9_JPEG_BASE + 0x118)
+#define CODA9_REG_JPEG_GBU_BBSR			(CODA9_JPEG_BASE + 0x140)
+#define CODA9_REG_JPEG_GBU_BBER			(CODA9_JPEG_BASE + 0x144)
+#define CODA9_REG_JPEG_GBU_BBIR			(CODA9_JPEG_BASE + 0x148)
+#define CODA9_REG_JPEG_GBU_BBHR			(CODA9_JPEG_BASE + 0x14c)
+#define CODA9_REG_JPEG_GBU_BCNT			(CODA9_JPEG_BASE + 0x158)
+#define CODA9_REG_JPEG_GBU_FF_RPTR		(CODA9_JPEG_BASE + 0x160)
+#define CODA9_REG_JPEG_GBU_FF_WPTR		(CODA9_JPEG_BASE + 0x164)
+#define CODA9_REG_JPEG_BBC_END_ADDR		(CODA9_JPEG_BASE + 0x208)
+#define CODA9_REG_JPEG_BBC_WR_PTR		(CODA9_JPEG_BASE + 0x20c)
+#define CODA9_REG_JPEG_BBC_RD_PTR		(CODA9_JPEG_BASE + 0x210)
+#define CODA9_REG_JPEG_BBC_EXT_ADDR		(CODA9_JPEG_BASE + 0x214)
+#define CODA9_REG_JPEG_BBC_INT_ADDR		(CODA9_JPEG_BASE + 0x218)
+#define CODA9_REG_JPEG_BBC_DATA_CNT		(CODA9_JPEG_BASE + 0x21c)
+#define CODA9_REG_JPEG_BBC_COMMAND		(CODA9_JPEG_BASE + 0x220)
+#define CODA9_REG_JPEG_BBC_BUSY			(CODA9_JPEG_BASE + 0x224)
+#define CODA9_REG_JPEG_BBC_CTRL			(CODA9_JPEG_BASE + 0x228)
+#define CODA9_REG_JPEG_BBC_CUR_POS		(CODA9_JPEG_BASE + 0x22c)
+#define CODA9_REG_JPEG_BBC_BAS_ADDR		(CODA9_JPEG_BASE + 0x230)
+#define CODA9_REG_JPEG_BBC_STRM_CTRL		(CODA9_JPEG_BASE + 0x234)
+#define CODA9_REG_JPEG_BBC_FLUSH_CMD		(CODA9_JPEG_BASE + 0x238)
+
 #endif
diff --git a/drivers/media/platform/coda/trace.h b/drivers/media/platform/coda/trace.h
index 6cf58237fff2..c0791c847f7c 100644
--- a/drivers/media/platform/coda/trace.h
+++ b/drivers/media/platform/coda/trace.h
@@ -154,6 +154,16 @@ DEFINE_EVENT(coda_buf_meta_class, coda_dec_rot_done,
 	TP_ARGS(ctx, buf, meta)
 );
 
+DEFINE_EVENT(coda_buf_class, coda_jpeg_run,
+	TP_PROTO(struct coda_ctx *ctx, struct vb2_v4l2_buffer *buf),
+	TP_ARGS(ctx, buf)
+);
+
+DEFINE_EVENT(coda_buf_class, coda_jpeg_done,
+	TP_PROTO(struct coda_ctx *ctx, struct vb2_v4l2_buffer *buf),
+	TP_ARGS(ctx, buf)
+);
+
 #endif /* __CODA_TRACE_H__ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/drivers/media/platform/cros-ec-cec/cros-ec-cec.c b/drivers/media/platform/cros-ec-cec/cros-ec-cec.c
index f048e8994785..0e7e2772f08f 100644
--- a/drivers/media/platform/cros-ec-cec/cros-ec-cec.c
+++ b/drivers/media/platform/cros-ec-cec/cros-ec-cec.c
@@ -14,7 +14,6 @@
 #include <linux/cec.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
 #include <media/cec.h>
diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c
index 916ed743d716..9b1d9643589b 100644
--- a/drivers/media/platform/davinci/vpfe_capture.c
+++ b/drivers/media/platform/davinci/vpfe_capture.c
@@ -168,21 +168,22 @@ int vpfe_register_ccdc_device(const struct ccdc_hw_device *dev)
 	int ret = 0;
 	printk(KERN_NOTICE "vpfe_register_ccdc_device: %s\n", dev->name);
 
-	BUG_ON(!dev->hw_ops.open);
-	BUG_ON(!dev->hw_ops.enable);
-	BUG_ON(!dev->hw_ops.set_hw_if_params);
-	BUG_ON(!dev->hw_ops.configure);
-	BUG_ON(!dev->hw_ops.set_buftype);
-	BUG_ON(!dev->hw_ops.get_buftype);
-	BUG_ON(!dev->hw_ops.enum_pix);
-	BUG_ON(!dev->hw_ops.set_frame_format);
-	BUG_ON(!dev->hw_ops.get_frame_format);
-	BUG_ON(!dev->hw_ops.get_pixel_format);
-	BUG_ON(!dev->hw_ops.set_pixel_format);
-	BUG_ON(!dev->hw_ops.set_image_window);
-	BUG_ON(!dev->hw_ops.get_image_window);
-	BUG_ON(!dev->hw_ops.get_line_length);
-	BUG_ON(!dev->hw_ops.getfid);
+	if (!dev->hw_ops.open ||
+	    !dev->hw_ops.enable ||
+	    !dev->hw_ops.set_hw_if_params ||
+	    !dev->hw_ops.configure ||
+	    !dev->hw_ops.set_buftype ||
+	    !dev->hw_ops.get_buftype ||
+	    !dev->hw_ops.enum_pix ||
+	    !dev->hw_ops.set_frame_format ||
+	    !dev->hw_ops.get_frame_format ||
+	    !dev->hw_ops.get_pixel_format ||
+	    !dev->hw_ops.set_pixel_format ||
+	    !dev->hw_ops.set_image_window ||
+	    !dev->hw_ops.get_image_window ||
+	    !dev->hw_ops.get_line_length ||
+	    !dev->hw_ops.getfid)
+		return -EINVAL;
 
 	mutex_lock(&ccdc_lock);
 	if (!ccdc_cfg) {
diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_core.c b/drivers/media/platform/mtk-mdp/mtk_mdp_core.c
index c1e29a46ae69..aeaed2cf4458 100644
--- a/drivers/media/platform/mtk-mdp/mtk_mdp_core.c
+++ b/drivers/media/platform/mtk-mdp/mtk_mdp_core.c
@@ -229,6 +229,9 @@ static int mtk_mdp_remove(struct platform_device *pdev)
 	mtk_mdp_unregister_m2m_device(mdp);
 	v4l2_device_unregister(&mdp->v4l2_dev);
 
+	flush_workqueue(mdp->wdt_wq);
+	destroy_workqueue(mdp->wdt_wq);
+
 	flush_workqueue(mdp->job_wq);
 	destroy_workqueue(mdp->job_wq);
 
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
index 858727824889..0f3e710aed4e 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
@@ -104,6 +104,7 @@ static struct vb2_buffer *get_display_buffer(struct mtk_vcodec_ctx *ctx)
 {
 	struct vdec_fb *disp_frame_buffer = NULL;
 	struct mtk_video_dec_buf *dstbuf;
+	struct vb2_v4l2_buffer *vb;
 
 	mtk_v4l2_debug(3, "[%d]", ctx->id);
 	if (vdec_if_get_param(ctx,
@@ -121,25 +122,26 @@ static struct vb2_buffer *get_display_buffer(struct mtk_vcodec_ctx *ctx)
 
 	dstbuf = container_of(disp_frame_buffer, struct mtk_video_dec_buf,
 				frame_buffer);
+	vb = &dstbuf->m2m_buf.vb;
 	mutex_lock(&ctx->lock);
 	if (dstbuf->used) {
-		vb2_set_plane_payload(&dstbuf->vb.vb2_buf, 0,
-					ctx->picinfo.fb_sz[0]);
+		vb2_set_plane_payload(&vb->vb2_buf, 0,
+				      ctx->picinfo.fb_sz[0]);
 		if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2)
-			vb2_set_plane_payload(&dstbuf->vb.vb2_buf, 1,
+			vb2_set_plane_payload(&vb->vb2_buf, 1,
 					      ctx->picinfo.fb_sz[1]);
 
 		mtk_v4l2_debug(2,
 				"[%d]status=%x queue id=%d to done_list %d",
 				ctx->id, disp_frame_buffer->status,
-				dstbuf->vb.vb2_buf.index,
+				vb->vb2_buf.index,
 				dstbuf->queued_in_vb2);
 
-		v4l2_m2m_buf_done(&dstbuf->vb, VB2_BUF_STATE_DONE);
+		v4l2_m2m_buf_done(vb, VB2_BUF_STATE_DONE);
 		ctx->decoded_frame_cnt++;
 	}
 	mutex_unlock(&ctx->lock);
-	return &dstbuf->vb.vb2_buf;
+	return &vb->vb2_buf;
 }
 
 /*
@@ -154,6 +156,7 @@ static struct vb2_buffer *get_free_buffer(struct mtk_vcodec_ctx *ctx)
 {
 	struct mtk_video_dec_buf *dstbuf;
 	struct vdec_fb *free_frame_buffer = NULL;
+	struct vb2_v4l2_buffer *vb;
 
 	if (vdec_if_get_param(ctx,
 				GET_PARAM_FREE_FRAME_BUFFER,
@@ -171,6 +174,7 @@ static struct vb2_buffer *get_free_buffer(struct mtk_vcodec_ctx *ctx)
 
 	dstbuf = container_of(free_frame_buffer, struct mtk_video_dec_buf,
 				frame_buffer);
+	vb = &dstbuf->m2m_buf.vb;
 
 	mutex_lock(&ctx->lock);
 	if (dstbuf->used) {
@@ -187,9 +191,9 @@ static struct vb2_buffer *get_free_buffer(struct mtk_vcodec_ctx *ctx)
 			mtk_v4l2_debug(2,
 				"[%d]status=%x queue id=%d to rdy_queue %d",
 				ctx->id, free_frame_buffer->status,
-				dstbuf->vb.vb2_buf.index,
+				vb->vb2_buf.index,
 				dstbuf->queued_in_vb2);
-			v4l2_m2m_buf_queue(ctx->m2m_ctx, &dstbuf->vb);
+			v4l2_m2m_buf_queue(ctx->m2m_ctx, vb);
 		} else if ((dstbuf->queued_in_vb2 == false) &&
 			   (dstbuf->queued_in_v4l2 == true)) {
 			/*
@@ -205,8 +209,8 @@ static struct vb2_buffer *get_free_buffer(struct mtk_vcodec_ctx *ctx)
 			mtk_v4l2_debug(2,
 					"[%d]status=%x queue id=%d to rdy_queue",
 					ctx->id, free_frame_buffer->status,
-					dstbuf->vb.vb2_buf.index);
-			v4l2_m2m_buf_queue(ctx->m2m_ctx, &dstbuf->vb);
+					vb->vb2_buf.index);
+			v4l2_m2m_buf_queue(ctx->m2m_ctx, vb);
 			dstbuf->queued_in_vb2 = true;
 		} else {
 			/*
@@ -219,14 +223,14 @@ static struct vb2_buffer *get_free_buffer(struct mtk_vcodec_ctx *ctx)
 			 */
 			mtk_v4l2_debug(3, "[%d]status=%x err queue id=%d %d %d",
 					ctx->id, free_frame_buffer->status,
-					dstbuf->vb.vb2_buf.index,
+					vb->vb2_buf.index,
 					dstbuf->queued_in_vb2,
 					dstbuf->queued_in_v4l2);
 		}
 		dstbuf->used = false;
 	}
 	mutex_unlock(&ctx->lock);
-	return &dstbuf->vb.vb2_buf;
+	return &vb->vb2_buf;
 }
 
 static void clean_display_buffer(struct mtk_vcodec_ctx *ctx)
@@ -365,8 +369,10 @@ static void mtk_vdec_worker(struct work_struct *work)
 		return;
 	}
 
-	src_buf_info = container_of(src_buf, struct mtk_video_dec_buf, vb);
-	dst_buf_info = container_of(dst_buf, struct mtk_video_dec_buf, vb);
+	src_buf_info = container_of(src_buf, struct mtk_video_dec_buf,
+				    m2m_buf.vb);
+	dst_buf_info = container_of(dst_buf, struct mtk_video_dec_buf,
+				    m2m_buf.vb);
 
 	pfb = &dst_buf_info->frame_buffer;
 	pfb->base_y.va = vb2_plane_vaddr(&dst_buf->vb2_buf, 0);
@@ -397,11 +403,11 @@ static void mtk_vdec_worker(struct work_struct *work)
 
 		vdec_if_decode(ctx, NULL, NULL, &res_chg);
 		clean_display_buffer(ctx);
-		vb2_set_plane_payload(&dst_buf_info->vb.vb2_buf, 0, 0);
+		vb2_set_plane_payload(&dst_buf->vb2_buf, 0, 0);
 		if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2)
-			vb2_set_plane_payload(&dst_buf_info->vb.vb2_buf, 1, 0);
+			vb2_set_plane_payload(&dst_buf->vb2_buf, 1, 0);
 		dst_buf->flags |= V4L2_BUF_FLAG_LAST;
-		v4l2_m2m_buf_done(&dst_buf_info->vb, VB2_BUF_STATE_DONE);
+		v4l2_m2m_buf_done(dst_buf, VB2_BUF_STATE_DONE);
 		clean_free_buffer(ctx);
 		v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx);
 		return;
@@ -417,10 +423,8 @@ static void mtk_vdec_worker(struct work_struct *work)
 	}
 	mtk_v4l2_debug(3, "[%d] Bitstream VA=%p DMA=%pad Size=%zx vb=%p",
 			ctx->id, buf.va, &buf.dma_addr, buf.size, src_buf);
-	dst_buf_info->vb.vb2_buf.timestamp
-			= src_buf_info->vb.vb2_buf.timestamp;
-	dst_buf_info->vb.timecode
-			= src_buf_info->vb.timecode;
+	dst_buf->vb2_buf.timestamp = src_buf->vb2_buf.timestamp;
+	dst_buf->timecode = src_buf->timecode;
 	mutex_lock(&ctx->lock);
 	dst_buf_info->used = true;
 	mutex_unlock(&ctx->lock);
@@ -434,7 +438,7 @@ static void mtk_vdec_worker(struct work_struct *work)
 			ctx->id,
 			src_buf->vb2_buf.index,
 			buf.size,
-			src_buf_info->vb.vb2_buf.timestamp,
+			src_buf->vb2_buf.timestamp,
 			dst_buf->vb2_buf.index,
 			ret, res_chg);
 		src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx);
@@ -443,14 +447,14 @@ static void mtk_vdec_worker(struct work_struct *work)
 			src_buf_info->error = true;
 			mutex_unlock(&ctx->lock);
 		}
-		v4l2_m2m_buf_done(&src_buf_info->vb, VB2_BUF_STATE_ERROR);
+		v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_ERROR);
 	} else if (res_chg == false) {
 		/*
 		 * we only return src buffer with VB2_BUF_STATE_DONE
 		 * when decode success without resolution change
 		 */
 		src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx);
-		v4l2_m2m_buf_done(&src_buf_info->vb, VB2_BUF_STATE_DONE);
+		v4l2_m2m_buf_done(src_buf, VB2_BUF_STATE_DONE);
 	}
 
 	dst_buf = v4l2_m2m_dst_buf_remove(ctx->m2m_ctx);
@@ -522,7 +526,8 @@ static int vidioc_decoder_cmd(struct file *file, void *priv,
 			mtk_v4l2_debug(1, "Capture stream is off. No need to flush.");
 			return 0;
 		}
-		v4l2_m2m_buf_queue(ctx->m2m_ctx, &ctx->empty_flush_buf->vb);
+		v4l2_m2m_buf_queue(ctx->m2m_ctx,
+				   &ctx->empty_flush_buf->m2m_buf.vb);
 		v4l2_m2m_try_schedule(ctx->m2m_ctx);
 		break;
 
@@ -1148,7 +1153,8 @@ static void vb2ops_vdec_buf_queue(struct vb2_buffer *vb)
 	 */
 	if (vb->vb2_queue->type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		vb2_v4l2 = to_vb2_v4l2_buffer(vb);
-		buf = container_of(vb2_v4l2, struct mtk_video_dec_buf, vb);
+		buf = container_of(vb2_v4l2, struct mtk_video_dec_buf,
+				   m2m_buf.vb);
 		mutex_lock(&ctx->lock);
 		if (buf->used == false) {
 			v4l2_m2m_buf_queue(ctx->m2m_ctx, vb2_v4l2);
@@ -1175,7 +1181,7 @@ static void vb2ops_vdec_buf_queue(struct vb2_buffer *vb)
 		mtk_v4l2_err("No src buffer");
 		return;
 	}
-	buf = container_of(src_buf, struct mtk_video_dec_buf, vb);
+	buf = container_of(src_buf, struct mtk_video_dec_buf, m2m_buf.vb);
 	if (buf->lastframe) {
 		/* This shouldn't happen. Just in case. */
 		mtk_v4l2_err("Invalid flush buffer.");
@@ -1256,7 +1262,7 @@ static void vb2ops_vdec_buf_finish(struct vb2_buffer *vb)
 	bool buf_error;
 
 	vb2_v4l2 = container_of(vb, struct vb2_v4l2_buffer, vb2_buf);
-	buf = container_of(vb2_v4l2, struct mtk_video_dec_buf, vb);
+	buf = container_of(vb2_v4l2, struct mtk_video_dec_buf, m2m_buf.vb);
 	mutex_lock(&ctx->lock);
 	if (vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		buf->queued_in_v4l2 = false;
@@ -1276,7 +1282,7 @@ static int vb2ops_vdec_buf_init(struct vb2_buffer *vb)
 	struct vb2_v4l2_buffer *vb2_v4l2 = container_of(vb,
 					struct vb2_v4l2_buffer, vb2_buf);
 	struct mtk_video_dec_buf *buf = container_of(vb2_v4l2,
-					struct mtk_video_dec_buf, vb);
+					struct mtk_video_dec_buf, m2m_buf.vb);
 
 	if (vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
 		buf->used = false;
@@ -1309,7 +1315,7 @@ static void vb2ops_vdec_stop_streaming(struct vb2_queue *q)
 	if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
 		while ((src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx))) {
 			struct mtk_video_dec_buf *buf_info = container_of(
-					src_buf, struct mtk_video_dec_buf, vb);
+				 src_buf, struct mtk_video_dec_buf, m2m_buf.vb);
 			if (!buf_info->lastframe)
 				v4l2_m2m_buf_done(src_buf,
 						VB2_BUF_STATE_ERROR);
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h
index e0c5338bde3d..cf26b6c1486a 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h
@@ -9,7 +9,7 @@
 #define _MTK_VCODEC_DEC_H_
 
 #include <media/videobuf2-core.h>
-#include <media/videobuf2-v4l2.h>
+#include <media/v4l2-mem2mem.h>
 
 #define VCODEC_CAPABILITY_4K_DISABLED	0x10
 #define VCODEC_DEC_4K_CODED_WIDTH	4096U
@@ -33,7 +33,7 @@ struct vdec_fb {
 
 /**
  * struct mtk_video_dec_buf - Private data related to each VB2 buffer.
- * @b:		VB2 buffer
+ * @m2m_buf:	M2M buffer
  * @list:	link list
  * @used:	Capture buffer contain decoded frame data and keep in
  *			codec data structure
@@ -47,8 +47,7 @@ struct vdec_fb {
  * Note : These status information help us track and debug buffer state
  */
 struct mtk_video_dec_buf {
-	struct vb2_v4l2_buffer	vb;
-	struct list_head	list;
+	struct v4l2_m2m_buffer	m2m_buf;
 
 	bool	used;
 	bool	queued_in_vb2;
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
index 944771ee5f5c..100ae8c5e702 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
@@ -137,7 +137,7 @@ static int fops_vcodec_open(struct file *file)
 	}
 	src_vq = v4l2_m2m_get_vq(ctx->m2m_ctx,
 				V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
-	ctx->empty_flush_buf->vb.vb2_buf.vb2_queue = src_vq;
+	ctx->empty_flush_buf->m2m_buf.vb.vb2_buf.vb2_queue = src_vq;
 	ctx->empty_flush_buf->lastframe = true;
 	mtk_vcodec_dec_set_default_params(ctx);
 
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
index fd8de027e83e..d469ff6464b2 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
@@ -332,14 +332,12 @@ static int vidioc_try_fmt(struct v4l2_format *f,
 
 		pix_fmt_mp->num_planes = fmt->num_planes;
 		pix_fmt_mp->plane_fmt[0].sizeimage =
-				pix_fmt_mp->width * pix_fmt_mp->height +
-				((ALIGN(pix_fmt_mp->width, 16) * 2) * 16);
+			pix_fmt_mp->width * pix_fmt_mp->height;
 		pix_fmt_mp->plane_fmt[0].bytesperline = pix_fmt_mp->width;
 
 		if (pix_fmt_mp->num_planes == 2) {
 			pix_fmt_mp->plane_fmt[1].sizeimage =
-				(pix_fmt_mp->width * pix_fmt_mp->height) / 2 +
-				(ALIGN(pix_fmt_mp->width, 16) * 16);
+				(pix_fmt_mp->width * pix_fmt_mp->height) / 2;
 			pix_fmt_mp->plane_fmt[2].sizeimage = 0;
 			pix_fmt_mp->plane_fmt[1].bytesperline =
 							pix_fmt_mp->width;
@@ -347,8 +345,7 @@ static int vidioc_try_fmt(struct v4l2_format *f,
 		} else if (pix_fmt_mp->num_planes == 3) {
 			pix_fmt_mp->plane_fmt[1].sizeimage =
 			pix_fmt_mp->plane_fmt[2].sizeimage =
-				(pix_fmt_mp->width * pix_fmt_mp->height) / 4 +
-				((ALIGN(pix_fmt_mp->width, 16) / 2) * 16);
+				(pix_fmt_mp->width * pix_fmt_mp->height) / 4;
 			pix_fmt_mp->plane_fmt[1].bytesperline =
 				pix_fmt_mp->plane_fmt[2].bytesperline =
 				pix_fmt_mp->width / 2;
@@ -798,13 +795,14 @@ static void vb2ops_venc_buf_queue(struct vb2_buffer *vb)
 			container_of(vb, struct vb2_v4l2_buffer, vb2_buf);
 
 	struct mtk_video_enc_buf *mtk_buf =
-			container_of(vb2_v4l2, struct mtk_video_enc_buf, vb);
+			container_of(vb2_v4l2, struct mtk_video_enc_buf,
+				     m2m_buf.vb);
 
 	if ((vb->vb2_queue->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) &&
 	    (ctx->param_change != MTK_ENCODE_PARAM_NONE)) {
 		mtk_v4l2_debug(1, "[%d] Before id=%d encode parameter change %x",
 			       ctx->id,
-			       mtk_buf->vb.vb2_buf.index,
+			       vb2_v4l2->vb2_buf.index,
 			       ctx->param_change);
 		mtk_buf->param_change = ctx->param_change;
 		mtk_buf->enc_params = ctx->enc_params;
@@ -986,7 +984,8 @@ static int mtk_venc_param_change(struct mtk_vcodec_ctx *ctx)
 	struct venc_enc_param enc_prm;
 	struct vb2_v4l2_buffer *vb2_v4l2 = v4l2_m2m_next_src_buf(ctx->m2m_ctx);
 	struct mtk_video_enc_buf *mtk_buf =
-			container_of(vb2_v4l2, struct mtk_video_enc_buf, vb);
+			container_of(vb2_v4l2, struct mtk_video_enc_buf,
+				     m2m_buf.vb);
 
 	int ret = 0;
 
@@ -998,7 +997,7 @@ static int mtk_venc_param_change(struct mtk_vcodec_ctx *ctx)
 		enc_prm.bitrate = mtk_buf->enc_params.bitrate;
 		mtk_v4l2_debug(1, "[%d] id=%d, change param br=%d",
 				ctx->id,
-				mtk_buf->vb.vb2_buf.index,
+				vb2_v4l2->vb2_buf.index,
 				enc_prm.bitrate);
 		ret |= venc_if_set_param(ctx,
 					 VENC_SET_PARAM_ADJUST_BITRATE,
@@ -1009,7 +1008,7 @@ static int mtk_venc_param_change(struct mtk_vcodec_ctx *ctx)
 				   mtk_buf->enc_params.framerate_denom;
 		mtk_v4l2_debug(1, "[%d] id=%d, change param fr=%d",
 			       ctx->id,
-			       mtk_buf->vb.vb2_buf.index,
+			       vb2_v4l2->vb2_buf.index,
 			       enc_prm.frm_rate);
 		ret |= venc_if_set_param(ctx,
 					 VENC_SET_PARAM_ADJUST_FRAMERATE,
@@ -1026,7 +1025,7 @@ static int mtk_venc_param_change(struct mtk_vcodec_ctx *ctx)
 	if (!ret && mtk_buf->param_change & MTK_ENCODE_PARAM_FORCE_INTRA) {
 		mtk_v4l2_debug(1, "[%d] id=%d, change param force I=%d",
 				ctx->id,
-				mtk_buf->vb.vb2_buf.index,
+				vb2_v4l2->vb2_buf.index,
 				mtk_buf->enc_params.force_intra);
 		if (mtk_buf->enc_params.force_intra)
 			ret |= venc_if_set_param(ctx,
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h
index a9c9f86b9c83..513ee7993e34 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.h
@@ -9,7 +9,7 @@
 #define _MTK_VCODEC_ENC_H_
 
 #include <media/videobuf2-core.h>
-#include <media/videobuf2-v4l2.h>
+#include <media/v4l2-mem2mem.h>
 
 #define MTK_VENC_IRQ_STATUS_SPS	0x1
 #define MTK_VENC_IRQ_STATUS_PPS	0x2
@@ -23,15 +23,15 @@
 
 /**
  * struct mtk_video_enc_buf - Private data related to each VB2 buffer.
- * @vb: Pointer to related VB2 buffer.
+ * @m2m_buf:	M2M buffer
  * @list:	list that buffer link to
  * @param_change: Types of encode parameter change before encoding this
  *				buffer
  * @enc_params: Encode parameters changed before encode this buffer
  */
 struct mtk_video_enc_buf {
-	struct vb2_v4l2_buffer vb;
-	struct list_head list;
+	struct v4l2_m2m_buffer m2m_buf;
+
 	u32 param_change;
 	struct mtk_enc_params enc_params;
 };
diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 327c5716922a..a4ee6b86663e 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -810,6 +810,10 @@ static int isp_pipeline_disable(struct isp_pipeline *pipe)
 
 		ret = v4l2_subdev_call(subdev, video, s_stream, 0);
 
+		/* Stop at the first external sub-device. */
+		if (subdev->dev != isp->dev)
+			break;
+
 		if (subdev == &isp->isp_res.subdev)
 			ret |= isp_pipeline_wait(isp, isp_pipeline_wait_resizer);
 		else if (subdev == &isp->isp_prev.subdev)
@@ -837,10 +841,6 @@ static int isp_pipeline_disable(struct isp_pipeline *pipe)
 						      &subdev->entity);
 			failure = -ETIMEDOUT;
 		}
-
-		/* Stop at the first external sub-device. */
-		if (subdev->dev != isp->dev)
-			break;
 	}
 
 	return failure;
diff --git a/drivers/media/platform/omap3isp/ispccdc.c b/drivers/media/platform/omap3isp/ispccdc.c
index e2f336c715a4..471ae7cdb813 100644
--- a/drivers/media/platform/omap3isp/ispccdc.c
+++ b/drivers/media/platform/omap3isp/ispccdc.c
@@ -1607,6 +1607,11 @@ static int ccdc_isr_buffer(struct isp_ccdc_device *ccdc)
 		return 0;
 	}
 
+	/* Don't restart CCDC if we're just about to stop streaming. */
+	if (ccdc->state == ISP_PIPELINE_STREAM_CONTINUOUS &&
+	    ccdc->stopping & CCDC_STOP_REQUEST)
+		return 0;
+
 	if (!ccdc_has_all_fields(ccdc))
 		return 1;
 
@@ -1661,16 +1666,15 @@ static void ccdc_vd0_isr(struct isp_ccdc_device *ccdc)
 		spin_unlock_irqrestore(&ccdc->lock, flags);
 	}
 
-	if (ccdc->output & CCDC_OUTPUT_MEMORY)
-		restart = ccdc_isr_buffer(ccdc);
-
 	spin_lock_irqsave(&ccdc->lock, flags);
-
 	if (ccdc_handle_stopping(ccdc, CCDC_EVENT_VD0)) {
 		spin_unlock_irqrestore(&ccdc->lock, flags);
 		return;
 	}
 
+	if (ccdc->output & CCDC_OUTPUT_MEMORY)
+		restart = ccdc_isr_buffer(ccdc);
+
 	if (!ccdc->shadow_update)
 		ccdc_apply_controls(ccdc);
 	spin_unlock_irqrestore(&ccdc->lock, flags);
diff --git a/drivers/media/platform/pxa_camera.c b/drivers/media/platform/pxa_camera.c
index 8d47ea0c33f8..43ae645d866b 100644
--- a/drivers/media/platform/pxa_camera.c
+++ b/drivers/media/platform/pxa_camera.c
@@ -2530,6 +2530,7 @@ exit_free_v4l2dev:
 	v4l2_device_unregister(&pcdev->v4l2_dev);
 exit_deactivate:
 	pxa_camera_deactivate(pcdev);
+	tasklet_kill(&pcdev->task_eof);
 exit_free_dma:
 	dma_release_channel(pcdev->dma_chans[2]);
 exit_free_dma_u:
@@ -2544,6 +2545,7 @@ static int pxa_camera_remove(struct platform_device *pdev)
 	struct pxa_camera_dev *pcdev = dev_get_drvdata(&pdev->dev);
 
 	pxa_camera_deactivate(pcdev);
+	tasklet_kill(&pcdev->task_eof);
 	dma_release_channel(pcdev->dma_chans[0]);
 	dma_release_channel(pcdev->dma_chans[1]);
 	dma_release_channel(pcdev->dma_chans[2]);
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
index 9e2e63ffcc47..5ff565e76bca 100644
--- a/drivers/media/platform/rcar-vin/rcar-v4l2.c
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -144,7 +144,7 @@ static void rvin_format_align(struct rvin_dev *vin, struct v4l2_pix_format *pix)
 	}
 
 	/* HW limit width to a multiple of 32 (2^5) for NV12/16 else 2 (2^1) */
-	switch (vin->format.pixelformat) {
+	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV16:
 		walign = 5;
diff --git a/drivers/media/platform/sti/bdisp/bdisp-hw.c b/drivers/media/platform/sti/bdisp/bdisp-hw.c
index 4372abbb5950..a74e9fd65238 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-hw.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-hw.c
@@ -14,8 +14,8 @@
 #define MAX_SRC_WIDTH           2048
 
 /* Reset & boot poll config */
-#define POLL_RST_MAX            50
-#define POLL_RST_DELAY_MS       20
+#define POLL_RST_MAX            500
+#define POLL_RST_DELAY_MS       2
 
 enum bdisp_target_plan {
 	BDISP_RGB,
@@ -382,7 +382,7 @@ int bdisp_hw_reset(struct bdisp_dev *bdisp)
 	for (i = 0; i < POLL_RST_MAX; i++) {
 		if (readl(bdisp->regs + BLT_STA1) & BLT_STA1_IDLE)
 			break;
-		msleep(POLL_RST_DELAY_MS);
+		udelay(POLL_RST_DELAY_MS * 1000);
 	}
 	if (i == POLL_RST_MAX)
 		dev_err(bdisp->dev, "Reset timeout\n");
diff --git a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
index 675b5f2b4c2e..d1025a53709f 100644
--- a/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
+++ b/drivers/media/platform/sti/bdisp/bdisp-v4l2.c
@@ -1274,6 +1274,8 @@ static int bdisp_remove(struct platform_device *pdev)
 	if (!IS_ERR(bdisp->clock))
 		clk_unprepare(bdisp->clock);
 
+	destroy_workqueue(bdisp->work_queue);
+
 	dev_dbg(&pdev->dev, "%s driver unloaded\n", pdev->name);
 
 	return 0;
@@ -1317,20 +1319,22 @@ static int bdisp_probe(struct platform_device *pdev)
 	bdisp->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(bdisp->regs)) {
 		dev_err(dev, "failed to get regs\n");
-		return PTR_ERR(bdisp->regs);
+		ret = PTR_ERR(bdisp->regs);
+		goto err_wq;
 	}
 
 	bdisp->clock = devm_clk_get(dev, BDISP_NAME);
 	if (IS_ERR(bdisp->clock)) {
 		dev_err(dev, "failed to get clock\n");
-		return PTR_ERR(bdisp->clock);
+		ret = PTR_ERR(bdisp->clock);
+		goto err_wq;
 	}
 
 	ret = clk_prepare(bdisp->clock);
 	if (ret < 0) {
 		dev_err(dev, "clock prepare failed\n");
 		bdisp->clock = ERR_PTR(-EINVAL);
-		return ret;
+		goto err_wq;
 	}
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
@@ -1402,7 +1406,8 @@ err_v4l2:
 err_clk:
 	if (!IS_ERR(bdisp->clock))
 		clk_unprepare(bdisp->clock);
-
+err_wq:
+	destroy_workqueue(bdisp->work_queue);
 	return ret;
 }
 
diff --git a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c
index a79250a7f812..0560a9cb004b 100644
--- a/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c
+++ b/drivers/media/platform/sti/c8sectpfe/c8sectpfe-dvb.c
@@ -170,8 +170,9 @@ int c8sectpfe_frontend_attach(struct dvb_frontend **fe,
 
 		/* attach tuner */
 		request_module("tda18212");
-		client = i2c_new_device(tsin->i2c_adapter, &tda18212_info);
-		if (!client || !client->dev.driver) {
+		client = i2c_new_client_device(tsin->i2c_adapter,
+					       &tda18212_info);
+		if (!i2c_client_has_driver(client)) {
 			dvb_frontend_detach(*fe);
 			return -ENODEV;
 		}
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
index f36dc6258900..eff34ded6305 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -28,6 +29,12 @@
 
 #include "sun4i_csi.h"
 
+struct sun4i_csi_traits {
+	unsigned int channels;
+	unsigned int max_width;
+	bool has_isp;
+};
+
 static const struct media_entity_operations sun4i_csi_video_entity_ops = {
 	.link_validate = v4l2_subdev_link_validate,
 };
@@ -155,6 +162,31 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 	subdev = &csi->subdev;
 	vdev = &csi->vdev;
 
+	csi->traits = of_device_get_match_data(&pdev->dev);
+	if (!csi->traits)
+		return -EINVAL;
+
+	/*
+	 * On Allwinner SoCs, some high memory bandwidth devices do DMA
+	 * directly over the memory bus (called MBUS), instead of the
+	 * system bus. The memory bus has a different addressing scheme
+	 * without the DRAM starting offset.
+	 *
+	 * In some cases this can be described by an interconnect in
+	 * the device tree. In other cases where the hardware is not
+	 * fully understood and the interconnect is left out of the
+	 * device tree, fall back to a default offset.
+	 */
+	if (of_find_property(csi->dev->of_node, "interconnects", NULL)) {
+		ret = of_dma_configure(csi->dev, csi->dev->of_node, true);
+		if (ret)
+			return ret;
+	} else {
+#ifdef PHYS_PFN_OFFSET
+		csi->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+#endif
+	}
+
 	csi->mdev.dev = csi->dev;
 	strscpy(csi->mdev.model, "Allwinner Video Capture Device",
 		sizeof(csi->mdev.model));
@@ -177,10 +209,12 @@ static int sun4i_csi_probe(struct platform_device *pdev)
 		return PTR_ERR(csi->bus_clk);
 	}
 
-	csi->isp_clk = devm_clk_get(&pdev->dev, "isp");
-	if (IS_ERR(csi->isp_clk)) {
-		dev_err(&pdev->dev, "Couldn't get our ISP clock\n");
-		return PTR_ERR(csi->isp_clk);
+	if (csi->traits->has_isp) {
+		csi->isp_clk = devm_clk_get(&pdev->dev, "isp");
+		if (IS_ERR(csi->isp_clk)) {
+			dev_err(&pdev->dev, "Couldn't get our ISP clock\n");
+			return PTR_ERR(csi->isp_clk);
+		}
 	}
 
 	csi->ram_clk = devm_clk_get(&pdev->dev, "ram");
@@ -258,8 +292,21 @@ static int sun4i_csi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct sun4i_csi_traits sun4i_a10_csi1_traits = {
+	.channels = 1,
+	.max_width = 24,
+	.has_isp = false,
+};
+
+static const struct sun4i_csi_traits sun7i_a20_csi0_traits = {
+	.channels = 4,
+	.max_width = 16,
+	.has_isp = true,
+};
+
 static const struct of_device_id sun4i_csi_of_match[] = {
-	{ .compatible = "allwinner,sun7i-a20-csi0" },
+	{ .compatible = "allwinner,sun4i-a10-csi1", .data = &sun4i_a10_csi1_traits },
+	{ .compatible = "allwinner,sun7i-a20-csi0", .data = &sun7i_a20_csi0_traits },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sun4i_csi_of_match);
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
index 001c8bde006c..0f67ff652c2e 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
@@ -22,8 +22,8 @@
 #define CSI_CFG_INPUT_FMT(fmt)			((fmt) << 20)
 #define CSI_CFG_OUTPUT_FMT(fmt)			((fmt) << 16)
 #define CSI_CFG_YUV_DATA_SEQ(seq)		((seq) << 8)
-#define CSI_CFG_VSYNC_POL(pol)			((pol) << 2)
-#define CSI_CFG_HSYNC_POL(pol)			((pol) << 1)
+#define CSI_CFG_VREF_POL(pol)			((pol) << 2)
+#define CSI_CFG_HREF_POL(pol)			((pol) << 1)
 #define CSI_CFG_PCLK_POL(pol)			((pol) << 0)
 
 #define CSI_CPT_CTRL_REG		0x08
@@ -108,6 +108,8 @@ struct sun4i_csi {
 	/* Device resources */
 	struct device			*dev;
 
+	const struct sun4i_csi_traits	*traits;
+
 	void __iomem			*regs;
 	struct clk			*bus_clk;
 	struct clk			*isp_clk;
diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c
index d6979e11a67b..78fa1c535ac6 100644
--- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c
+++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_dma.c
@@ -228,7 +228,7 @@ static int sun4i_csi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	struct sun4i_csi *csi = vb2_get_drv_priv(vq);
 	struct v4l2_fwnode_bus_parallel *bus = &csi->bus;
 	const struct sun4i_csi_format *csi_fmt;
-	unsigned long hsync_pol, pclk_pol, vsync_pol;
+	unsigned long href_pol, pclk_pol, vref_pol;
 	unsigned long flags;
 	unsigned int i;
 	int ret;
@@ -278,13 +278,21 @@ static int sun4i_csi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	writel(CSI_WIN_CTRL_H_ACTIVE(csi->fmt.height),
 	       csi->regs + CSI_WIN_CTRL_H_REG);
 
-	hsync_pol = !!(bus->flags & V4L2_MBUS_HSYNC_ACTIVE_HIGH);
-	pclk_pol = !!(bus->flags & V4L2_MBUS_DATA_ACTIVE_HIGH);
-	vsync_pol = !!(bus->flags & V4L2_MBUS_VSYNC_ACTIVE_HIGH);
+	/*
+	 * This hardware uses [HV]REF instead of [HV]SYNC. Based on the
+	 * provided timing diagrams in the manual, positive polarity
+	 * equals active high [HV]REF.
+	 *
+	 * When the back porch is 0, [HV]REF is more or less equivalent
+	 * to [HV]SYNC inverted.
+	 */
+	href_pol = !!(bus->flags & V4L2_MBUS_HSYNC_ACTIVE_LOW);
+	vref_pol = !!(bus->flags & V4L2_MBUS_VSYNC_ACTIVE_LOW);
+	pclk_pol = !!(bus->flags & V4L2_MBUS_PCLK_SAMPLE_RISING);
 	writel(CSI_CFG_INPUT_FMT(csi_fmt->input) |
 	       CSI_CFG_OUTPUT_FMT(csi_fmt->output) |
-	       CSI_CFG_VSYNC_POL(vsync_pol) |
-	       CSI_CFG_HSYNC_POL(hsync_pol) |
+	       CSI_CFG_VREF_POL(vref_pol) |
+	       CSI_CFG_HREF_POL(href_pol) |
 	       CSI_CFG_PCLK_POL(pclk_pol),
 	       csi->regs + CSI_CFG_REG);
 
diff --git a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
index aaa1dc159ac2..b61f3dea7c93 100644
--- a/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
+++ b/drivers/media/platform/sunxi/sun8i-di/sun8i-di.c
@@ -834,11 +834,8 @@ static int deinterlace_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dev->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(dev->base)) {
-		dev_err(dev->dev, "Failed to map registers\n");
-
+	if (IS_ERR(dev->base))
 		return PTR_ERR(dev->base);
-	}
 
 	dev->bus_clk = devm_clk_get(dev->dev, "bus");
 	if (IS_ERR(dev->bus_clk)) {
diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c
index 223161f9c403..be54806180a5 100644
--- a/drivers/media/platform/ti-vpe/cal.c
+++ b/drivers/media/platform/ti-vpe/cal.c
@@ -14,6 +14,8 @@
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 #include <linux/videodev2.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
@@ -32,8 +34,8 @@
 
 #define CAL_MODULE_NAME "cal"
 
-#define MAX_WIDTH 1920
-#define MAX_HEIGHT 1200
+#define MAX_WIDTH_BYTES (8192 * 8)
+#define MAX_HEIGHT_LINES 16383
 
 #define CAL_VERSION "0.1.0"
 
@@ -71,8 +73,6 @@ static const struct v4l2_fract
 #define CAL_NUM_INPUT 1
 #define CAL_NUM_CONTEXT 2
 
-#define bytes_per_line(pixel, bpp) (ALIGN(pixel * bpp, 16))
-
 #define reg_read(dev, offset) ioread32(dev->base + offset)
 #define reg_write(dev, offset, val) iowrite32(val, dev->base + offset)
 
@@ -91,102 +91,103 @@ static const struct v4l2_fract
 struct cal_fmt {
 	u32	fourcc;
 	u32	code;
-	u8	depth;
+	/* Bits per pixel */
+	u8	bpp;
 };
 
 static struct cal_fmt cal_formats[] = {
 	{
 		.fourcc		= V4L2_PIX_FMT_YUYV,
 		.code		= MEDIA_BUS_FMT_YUYV8_2X8,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_UYVY,
 		.code		= MEDIA_BUS_FMT_UYVY8_2X8,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_YVYU,
 		.code		= MEDIA_BUS_FMT_YVYU8_2X8,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_VYUY,
 		.code		= MEDIA_BUS_FMT_VYUY8_2X8,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB565, /* gggbbbbb rrrrrggg */
 		.code		= MEDIA_BUS_FMT_RGB565_2X8_LE,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB565X, /* rrrrrggg gggbbbbb */
 		.code		= MEDIA_BUS_FMT_RGB565_2X8_BE,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB555, /* gggbbbbb arrrrrgg */
 		.code		= MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB555X, /* arrrrrgg gggbbbbb */
 		.code		= MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE,
-		.depth		= 16,
+		.bpp		= 16,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB24, /* rgb */
 		.code		= MEDIA_BUS_FMT_RGB888_2X12_LE,
-		.depth		= 24,
+		.bpp		= 24,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_BGR24, /* bgr */
 		.code		= MEDIA_BUS_FMT_RGB888_2X12_BE,
-		.depth		= 24,
+		.bpp		= 24,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_RGB32, /* argb */
 		.code		= MEDIA_BUS_FMT_ARGB8888_1X32,
-		.depth		= 32,
+		.bpp		= 32,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SBGGR8,
 		.code		= MEDIA_BUS_FMT_SBGGR8_1X8,
-		.depth		= 8,
+		.bpp		= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGBRG8,
 		.code		= MEDIA_BUS_FMT_SGBRG8_1X8,
-		.depth		= 8,
+		.bpp		= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGRBG8,
 		.code		= MEDIA_BUS_FMT_SGRBG8_1X8,
-		.depth		= 8,
+		.bpp		= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SRGGB8,
 		.code		= MEDIA_BUS_FMT_SRGGB8_1X8,
-		.depth		= 8,
+		.bpp		= 8,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SBGGR10,
 		.code		= MEDIA_BUS_FMT_SBGGR10_1X10,
-		.depth		= 16,
+		.bpp		= 10,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGBRG10,
 		.code		= MEDIA_BUS_FMT_SGBRG10_1X10,
-		.depth		= 16,
+		.bpp		= 10,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGRBG10,
 		.code		= MEDIA_BUS_FMT_SGRBG10_1X10,
-		.depth		= 16,
+		.bpp		= 10,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SRGGB10,
 		.code		= MEDIA_BUS_FMT_SRGGB10_1X10,
-		.depth		= 16,
+		.bpp		= 10,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SBGGR12,
 		.code		= MEDIA_BUS_FMT_SBGGR12_1X12,
-		.depth		= 16,
+		.bpp		= 12,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGBRG12,
 		.code		= MEDIA_BUS_FMT_SGBRG12_1X12,
-		.depth		= 16,
+		.bpp		= 12,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SGRBG12,
 		.code		= MEDIA_BUS_FMT_SGRBG12_1X12,
-		.depth		= 16,
+		.bpp		= 12,
 	}, {
 		.fourcc		= V4L2_PIX_FMT_SRGGB12,
 		.code		= MEDIA_BUS_FMT_SRGGB12_1X12,
-		.depth		= 16,
+		.bpp		= 12,
 	},
 };
 
@@ -220,20 +221,118 @@ struct cal_dmaqueue {
 	int			ini_jiffies;
 };
 
-struct cm_data {
+struct cc_data {
 	void __iomem		*base;
 	struct resource		*res;
 
-	unsigned int		camerrx_control;
-
 	struct platform_device *pdev;
 };
 
-struct cc_data {
-	void __iomem		*base;
-	struct resource		*res;
+/* CTRL_CORE_CAMERRX_CONTROL register field id */
+enum cal_camerarx_field {
+	F_CTRLCLKEN,
+	F_CAMMODE,
+	F_LANEENABLE,
+	F_CSI_MODE,
 
-	struct platform_device *pdev;
+	F_MAX_FIELDS,
+};
+
+struct cal_csi2_phy {
+	struct regmap_field *fields[F_MAX_FIELDS];
+	struct reg_field *base_fields;
+	const int num_lanes;
+};
+
+struct cal_data {
+	const int num_csi2_phy;
+	struct cal_csi2_phy *csi2_phy_core;
+
+	const unsigned int flags;
+};
+
+static struct reg_field dra72x_ctrl_core_csi0_reg_fields[F_MAX_FIELDS] = {
+	[F_CTRLCLKEN] = REG_FIELD(0, 10, 10),
+	[F_CAMMODE] = REG_FIELD(0, 11, 12),
+	[F_LANEENABLE] = REG_FIELD(0, 13, 16),
+	[F_CSI_MODE] = REG_FIELD(0, 17, 17),
+};
+
+static struct reg_field dra72x_ctrl_core_csi1_reg_fields[F_MAX_FIELDS] = {
+	[F_CTRLCLKEN] = REG_FIELD(0, 0, 0),
+	[F_CAMMODE] = REG_FIELD(0, 1, 2),
+	[F_LANEENABLE] = REG_FIELD(0, 3, 4),
+	[F_CSI_MODE] = REG_FIELD(0, 5, 5),
+};
+
+static struct cal_csi2_phy dra72x_cal_csi_phy[] = {
+	{
+		.base_fields = dra72x_ctrl_core_csi0_reg_fields,
+		.num_lanes = 4,
+	},
+	{
+		.base_fields = dra72x_ctrl_core_csi1_reg_fields,
+		.num_lanes = 2,
+	},
+};
+
+static const struct cal_data dra72x_cal_data = {
+	.csi2_phy_core = dra72x_cal_csi_phy,
+	.num_csi2_phy = ARRAY_SIZE(dra72x_cal_csi_phy),
+};
+
+static const struct cal_data dra72x_es1_cal_data = {
+	.csi2_phy_core = dra72x_cal_csi_phy,
+	.num_csi2_phy = ARRAY_SIZE(dra72x_cal_csi_phy),
+	.flags = DRA72_CAL_PRE_ES2_LDO_DISABLE,
+};
+
+static struct reg_field dra76x_ctrl_core_csi0_reg_fields[F_MAX_FIELDS] = {
+	[F_CTRLCLKEN] = REG_FIELD(0, 8, 8),
+	[F_CAMMODE] = REG_FIELD(0, 9, 10),
+	[F_CSI_MODE] = REG_FIELD(0, 11, 11),
+	[F_LANEENABLE] = REG_FIELD(0, 27, 31),
+};
+
+static struct reg_field dra76x_ctrl_core_csi1_reg_fields[F_MAX_FIELDS] = {
+	[F_CTRLCLKEN] = REG_FIELD(0, 0, 0),
+	[F_CAMMODE] = REG_FIELD(0, 1, 2),
+	[F_CSI_MODE] = REG_FIELD(0, 3, 3),
+	[F_LANEENABLE] = REG_FIELD(0, 24, 26),
+};
+
+static struct cal_csi2_phy dra76x_cal_csi_phy[] = {
+	{
+		.base_fields = dra76x_ctrl_core_csi0_reg_fields,
+		.num_lanes = 5,
+	},
+	{
+		.base_fields = dra76x_ctrl_core_csi1_reg_fields,
+		.num_lanes = 3,
+	},
+};
+
+static const struct cal_data dra76x_cal_data = {
+	.csi2_phy_core = dra76x_cal_csi_phy,
+	.num_csi2_phy = ARRAY_SIZE(dra76x_cal_csi_phy),
+};
+
+static struct reg_field am654_ctrl_core_csi0_reg_fields[F_MAX_FIELDS] = {
+	[F_CTRLCLKEN] = REG_FIELD(0, 15, 15),
+	[F_CAMMODE] = REG_FIELD(0, 24, 25),
+	[F_LANEENABLE] = REG_FIELD(0, 0, 4),
+};
+
+static struct cal_csi2_phy am654_cal_csi_phy[] = {
+	{
+		.base_fields = am654_ctrl_core_csi0_reg_fields,
+		.num_lanes = 5,
+	},
+};
+
+static const struct cal_data am654_cal_data = {
+	.csi2_phy_core = am654_cal_csi_phy,
+	.num_csi2_phy = ARRAY_SIZE(am654_cal_csi_phy),
 };
 
 /*
@@ -247,8 +346,15 @@ struct cal_dev {
 	struct platform_device	*pdev;
 	struct v4l2_device	v4l2_dev;
 
+	/* Controller flags for special cases */
+	unsigned int		flags;
+
+	const struct cal_data	*data;
+
 	/* Control Module handle */
-	struct cm_data		*cm;
+	struct regmap		*syscon_camerrx;
+	u32			syscon_camerrx_offset;
+
 	/* Camera Core Module handle */
 	struct cc_data		*cc[CAL_NUM_CSI2_PORTS];
 
@@ -359,73 +465,115 @@ static inline void set_field(u32 *valp, u32 field, u32 mask)
 	*valp = val;
 }
 
-/*
- * Control Module block access
- */
-static struct cm_data *cm_create(struct cal_dev *dev)
+static u32 cal_data_get_phy_max_lanes(struct cal_ctx *ctx)
 {
-	struct platform_device *pdev = dev->pdev;
-	struct cm_data *cm;
+	struct cal_dev *dev = ctx->dev;
+	u32 phy_id = ctx->csi2_port - 1;
 
-	cm = devm_kzalloc(&pdev->dev, sizeof(*cm), GFP_KERNEL);
-	if (!cm)
-		return ERR_PTR(-ENOMEM);
+	return dev->data->csi2_phy_core[phy_id].num_lanes;
+}
+
+static u32 cal_data_get_num_csi2_phy(struct cal_dev *dev)
+{
+	return dev->data->num_csi2_phy;
+}
+
+static int cal_camerarx_regmap_init(struct cal_dev *dev)
+{
+	struct reg_field *field;
+	struct cal_csi2_phy *phy;
+	int i, j;
+
+	if (!dev->data)
+		return -EINVAL;
+
+	for (i = 0; i < cal_data_get_num_csi2_phy(dev); i++) {
+		phy = &dev->data->csi2_phy_core[i];
+		for (j = 0; j < F_MAX_FIELDS; j++) {
+			field = &phy->base_fields[j];
+			/*
+			 * Here we update the reg offset with the
+			 * value found in DT
+			 */
+			field->reg = dev->syscon_camerrx_offset;
+			phy->fields[j] =
+				devm_regmap_field_alloc(&dev->pdev->dev,
+							dev->syscon_camerrx,
+							*field);
+			if (IS_ERR(phy->fields[j])) {
+				cal_err(dev, "Unable to allocate regmap fields\n");
+				return PTR_ERR(phy->fields[j]);
+			}
+		}
+	}
+	return 0;
+}
+
+static const struct regmap_config cal_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
 
-	cm->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						"camerrx_control");
-	cm->base = devm_ioremap_resource(&pdev->dev, cm->res);
-	if (IS_ERR(cm->base)) {
+static struct regmap *cal_get_camerarx_regmap(struct cal_dev *dev)
+{
+	struct platform_device *pdev = dev->pdev;
+	struct regmap *regmap;
+	void __iomem *base;
+	u32 reg_io_width;
+	struct regmap_config r_config = cal_regmap_config;
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+					   "camerrx_control");
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base)) {
 		cal_err(dev, "failed to ioremap\n");
-		return ERR_CAST(cm->base);
+		return ERR_CAST(base);
 	}
 
 	cal_dbg(1, dev, "ioresource %s at %pa - %pa\n",
-		cm->res->name, &cm->res->start, &cm->res->end);
+		res->name, &res->start, &res->end);
 
-	return cm;
+	reg_io_width = 4;
+	r_config.reg_stride = reg_io_width;
+	r_config.val_bits = reg_io_width * 8;
+	r_config.max_register = resource_size(res) - reg_io_width;
+
+	regmap = regmap_init_mmio(NULL, base, &r_config);
+	if (IS_ERR(regmap))
+		pr_err("regmap init failed\n");
+
+	return regmap;
 }
 
+/*
+ * Control Module CAMERARX block access
+ */
 static void camerarx_phy_enable(struct cal_ctx *ctx)
 {
-	u32 val;
-
-	if (!ctx->dev->cm->base) {
-		ctx_err(ctx, "cm not mapped\n");
-		return;
-	}
-
-	val = reg_read(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL);
-	if (ctx->csi2_port == 1) {
-		set_field(&val, 1, CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK);
-		set_field(&val, 0, CM_CAMERRX_CTRL_CSI0_CAMMODE_MASK);
-		/* enable all lanes by default */
-		set_field(&val, 0xf, CM_CAMERRX_CTRL_CSI0_LANEENABLE_MASK);
-		set_field(&val, 1, CM_CAMERRX_CTRL_CSI0_MODE_MASK);
-	} else if (ctx->csi2_port == 2) {
-		set_field(&val, 1, CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK);
-		set_field(&val, 0, CM_CAMERRX_CTRL_CSI1_CAMMODE_MASK);
-		/* enable all lanes by default */
-		set_field(&val, 0x3, CM_CAMERRX_CTRL_CSI1_LANEENABLE_MASK);
-		set_field(&val, 1, CM_CAMERRX_CTRL_CSI1_MODE_MASK);
-	}
-	reg_write(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL, val);
+	struct cal_csi2_phy *phy;
+	u32 phy_id = ctx->csi2_port - 1;
+	u32 max_lanes;
+
+	phy = &ctx->dev->data->csi2_phy_core[phy_id];
+	regmap_field_write(phy->fields[F_CAMMODE], 0);
+	/* Always enable all lanes at the phy control level */
+	max_lanes = (1 << cal_data_get_phy_max_lanes(ctx)) - 1;
+	regmap_field_write(phy->fields[F_LANEENABLE], max_lanes);
+	/* F_CSI_MODE is not present on every architecture */
+	if (phy->fields[F_CSI_MODE])
+		regmap_field_write(phy->fields[F_CSI_MODE], 1);
+	regmap_field_write(phy->fields[F_CTRLCLKEN], 1);
 }
 
 static void camerarx_phy_disable(struct cal_ctx *ctx)
 {
-	u32 val;
-
-	if (!ctx->dev->cm->base) {
-		ctx_err(ctx, "cm not mapped\n");
-		return;
-	}
+	struct cal_csi2_phy *phy;
+	u32 phy_id = ctx->csi2_port - 1;
 
-	val = reg_read(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL);
-	if (ctx->csi2_port == 1)
-		set_field(&val, 0x0, CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK);
-	else if (ctx->csi2_port == 2)
-		set_field(&val, 0x0, CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK);
-	reg_write(ctx->dev->cm, CM_CTRL_CORE_CAMERRX_CONTROL, val);
+	phy = &ctx->dev->data->csi2_phy_core[phy_id];
+	regmap_field_write(phy->fields[F_CTRLCLKEN], 0);
 }
 
 /*
@@ -474,9 +622,52 @@ static void cal_get_hwinfo(struct cal_dev *dev)
 		hwinfo);
 }
 
-static inline int cal_runtime_get(struct cal_dev *dev)
+/*
+ *   Errata i913: CSI2 LDO Needs to be disabled when module is powered on
+ *
+ *   Enabling CSI2 LDO shorts it to core supply. It is crucial the 2 CSI2
+ *   LDOs on the device are disabled if CSI-2 module is powered on
+ *   (0x4845 B304 | 0x4845 B384 [28:27] = 0x1) or in ULPS (0x4845 B304
+ *   | 0x4845 B384 [28:27] = 0x2) mode. Common concerns include: high
+ *   current draw on the module supply in active mode.
+ *
+ *   Errata does not apply when CSI-2 module is powered off
+ *   (0x4845 B304 | 0x4845 B384 [28:27] = 0x0).
+ *
+ * SW Workaround:
+ *	Set the following register bits to disable the LDO,
+ *	which is essentially CSI2 REG10 bit 6:
+ *
+ *		Core 0:  0x4845 B828 = 0x0000 0040
+ *		Core 1:  0x4845 B928 = 0x0000 0040
+ */
+static void i913_errata(struct cal_dev *dev, unsigned int port)
+{
+	u32 reg10 = reg_read(dev->cc[port], CAL_CSI2_PHY_REG10);
+
+	set_field(&reg10, CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_DISABLE,
+		  CAL_CSI2_PHY_REG10_I933_LDO_DISABLE_MASK);
+
+	cal_dbg(1, dev, "CSI2_%d_REG10 = 0x%08x\n", port, reg10);
+	reg_write(dev->cc[port], CAL_CSI2_PHY_REG10, reg10);
+}
+
+static int cal_runtime_get(struct cal_dev *dev)
 {
-	return pm_runtime_get_sync(&dev->pdev->dev);
+	int r;
+
+	r = pm_runtime_get_sync(&dev->pdev->dev);
+
+	if (dev->flags & DRA72_CAL_PRE_ES2_LDO_DISABLE) {
+		/*
+		 * Apply errata on both port eveytime we (re-)enable
+		 * the clock
+		 */
+		i913_errata(dev, 0);
+		i913_errata(dev, 1);
+	}
+
+	return r;
 }
 
 static inline void cal_runtime_put(struct cal_dev *dev)
@@ -508,12 +699,6 @@ static void cal_quickdump_regs(struct cal_dev *dev)
 			       resource_size(dev->ctx[1]->cc->res),
 			       false);
 	}
-
-	cal_info(dev, "CAMERRX_Control Registers @ %pa:\n",
-		 &dev->cm->res->start);
-	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 4,
-		       (__force const void *)dev->cm->base,
-		       resource_size(dev->cm->res), false);
 }
 
 /*
@@ -551,29 +736,76 @@ static void disable_irqs(struct cal_ctx *ctx)
 	reg_write(ctx->dev, CAL_CSI2_VC_IRQENABLE(1), 0);
 }
 
-static void csi2_init(struct cal_ctx *ctx)
+static void csi2_phy_config(struct cal_ctx *ctx);
+
+static void csi2_phy_init(struct cal_ctx *ctx)
 {
 	int i;
 	u32 val;
 
+	/* Steps
+	 *  1. Configure D-PHY mode and enable required lanes
+	 *  2. Reset complex IO - Wait for completion of reset
+	 *          Note if the external sensor is not sending byte clock,
+	 *          the reset will timeout
+	 *  3 Program Stop States
+	 *      A. Program THS_TERM, THS_SETTLE, etc... Timings parameters
+	 *              in terms of DDR clock periods
+	 *      B. Enable stop state transition timeouts
+	 *  4.Force FORCERXMODE
+	 *      D. Enable pull down using pad control
+	 *      E. Power up PHY
+	 *      F. Wait for power up completion
+	 *      G. Wait for all enabled lane to reach stop state
+	 *      H. Disable pull down using pad control
+	 */
+
+	/* 1. Configure D-PHY mode and enable required lanes */
+	camerarx_phy_enable(ctx);
+
+	/* 2. Reset complex IO - Do not wait for reset completion */
+	val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
+	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL,
+		  CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK);
+	reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x De-assert Complex IO Reset\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)));
+
+	/* Dummy read to allow SCP to complete */
+	val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
+
+	/* 3.A. Program Phy Timing Parameters */
+	csi2_phy_config(ctx);
+
+	/* 3.B. Program Stop States */
 	val = reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port));
 	set_field(&val, CAL_GEN_ENABLE,
-		  CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK);
-	set_field(&val, CAL_GEN_ENABLE,
 		  CAL_CSI2_TIMING_STOP_STATE_X16_IO1_MASK);
 	set_field(&val, CAL_GEN_DISABLE,
 		  CAL_CSI2_TIMING_STOP_STATE_X4_IO1_MASK);
 	set_field(&val, 407, CAL_CSI2_TIMING_STOP_STATE_COUNTER_IO1_MASK);
 	reg_write(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port), val);
-	ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x\n", ctx->csi2_port,
+	ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x Stop States\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)));
+
+	/* 4. Force FORCERXMODE */
+	val = reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port));
+	set_field(&val, CAL_GEN_ENABLE,
+		  CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK);
+	reg_write(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port), val);
+	ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x Force RXMODE\n",
+		ctx->csi2_port,
 		reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)));
 
+	/* E. Power up the PHY using the complex IO */
 	val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
-	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL,
-		  CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK);
 	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ON,
 		  CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_MASK);
 	reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val);
+
+	/* F. Wait for power up completion */
 	for (i = 0; i < 10; i++) {
 		if (reg_read_field(ctx->dev,
 				   CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port),
@@ -582,18 +814,104 @@ static void csi2_init(struct cal_ctx *ctx)
 			break;
 		usleep_range(1000, 1100);
 	}
-	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x\n", ctx->csi2_port,
-		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)));
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Powered UP %s\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)),
+		(i >= 10) ? "(timeout)" : "");
+}
 
-	val = reg_read(ctx->dev, CAL_CTRL);
-	set_field(&val, CAL_CTRL_BURSTSIZE_BURST128, CAL_CTRL_BURSTSIZE_MASK);
-	set_field(&val, 0xF, CAL_CTRL_TAGCNT_MASK);
-	set_field(&val, CAL_CTRL_POSTED_WRITES_NONPOSTED,
-		  CAL_CTRL_POSTED_WRITES_MASK);
-	set_field(&val, 0xFF, CAL_CTRL_MFLAGL_MASK);
-	set_field(&val, 0xFF, CAL_CTRL_MFLAGH_MASK);
-	reg_write(ctx->dev, CAL_CTRL, val);
-	ctx_dbg(3, ctx, "CAL_CTRL = 0x%08x\n", reg_read(ctx->dev, CAL_CTRL));
+static void csi2_wait_for_phy(struct cal_ctx *ctx)
+{
+	int i;
+
+	/* Steps
+	 *  2. Wait for completion of reset
+	 *          Note if the external sensor is not sending byte clock,
+	 *          the reset will timeout
+	 *  4.Force FORCERXMODE
+	 *      G. Wait for all enabled lane to reach stop state
+	 *      H. Disable pull down using pad control
+	 */
+
+	/* 2. Wait for reset completion */
+	for (i = 0; i < 250; i++) {
+		if (reg_read_field(ctx->dev,
+				   CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port),
+				   CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK) ==
+		    CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETCOMPLETED)
+			break;
+		usleep_range(1000, 1100);
+	}
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Complex IO Reset Done (%d) %s\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)), i,
+		(i >= 250) ? "(timeout)" : "");
+
+	/* 4. G. Wait for all enabled lane to reach stop state */
+	for (i = 0; i < 10; i++) {
+		if (reg_read_field(ctx->dev,
+				   CAL_CSI2_TIMING(ctx->csi2_port),
+				   CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK) ==
+		    CAL_GEN_DISABLE)
+			break;
+		usleep_range(1000, 1100);
+	}
+	ctx_dbg(3, ctx, "CAL_CSI2_TIMING(%d) = 0x%08x Stop State Reached %s\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_TIMING(ctx->csi2_port)),
+		(i >= 10) ? "(timeout)" : "");
+
+	ctx_dbg(1, ctx, "CSI2_%d_REG1 = 0x%08x (Bit(31,28) should be set!)\n",
+		(ctx->csi2_port - 1), reg_read(ctx->cc, CAL_CSI2_PHY_REG1));
+}
+
+static void csi2_phy_deinit(struct cal_ctx *ctx)
+{
+	int i;
+	u32 val;
+
+	/* Power down the PHY using the complex IO */
+	val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
+	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_OFF,
+		  CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_MASK);
+	reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val);
+
+	/* Wait for power down completion */
+	for (i = 0; i < 10; i++) {
+		if (reg_read_field(ctx->dev,
+				   CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port),
+				   CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_MASK) ==
+		    CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_OFF)
+			break;
+		usleep_range(1000, 1100);
+	}
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Powered Down %s\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)),
+		(i >= 10) ? "(timeout)" : "");
+
+	/* Assert Comple IO Reset */
+	val = reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port));
+	set_field(&val, CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL,
+		  CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK);
+	reg_write(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port), val);
+
+	/* Wait for power down completion */
+	for (i = 0; i < 10; i++) {
+		if (reg_read_field(ctx->dev,
+				   CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port),
+				   CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK) ==
+		    CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETONGOING)
+			break;
+		usleep_range(1000, 1100);
+	}
+	ctx_dbg(3, ctx, "CAL_CSI2_COMPLEXIO_CFG(%d) = 0x%08x Complex IO in Reset (%d) %s\n",
+		ctx->csi2_port,
+		reg_read(ctx->dev, CAL_CSI2_COMPLEXIO_CFG(ctx->csi2_port)), i,
+		(i >= 10) ? "(timeout)" : "");
+
+	/* Disable the phy */
+	camerarx_phy_disable(ctx);
 }
 
 static void csi2_lane_config(struct cal_ctx *ctx)
@@ -665,13 +983,48 @@ static void csi2_ctx_config(struct cal_ctx *ctx)
 
 static void pix_proc_config(struct cal_ctx *ctx)
 {
-	u32 val;
+	u32 val, extract, pack;
+
+	switch (ctx->fmt->bpp) {
+	case 8:
+		extract = CAL_PIX_PROC_EXTRACT_B8;
+		pack = CAL_PIX_PROC_PACK_B8;
+		break;
+	case 10:
+		extract = CAL_PIX_PROC_EXTRACT_B10_MIPI;
+		pack = CAL_PIX_PROC_PACK_B16;
+		break;
+	case 12:
+		extract = CAL_PIX_PROC_EXTRACT_B12_MIPI;
+		pack = CAL_PIX_PROC_PACK_B16;
+		break;
+	case 16:
+		extract = CAL_PIX_PROC_EXTRACT_B16_LE;
+		pack = CAL_PIX_PROC_PACK_B16;
+		break;
+	default:
+		/*
+		 * If you see this warning then it means that you added
+		 * some new entry in the cal_formats[] array with a different
+		 * bit per pixel values then the one supported below.
+		 * Either add support for the new bpp value below or adjust
+		 * the new entry to use one of the value below.
+		 *
+		 * Instead of failing here just use 8 bpp as a default.
+		 */
+		dev_warn_once(&ctx->dev->pdev->dev,
+			      "%s:%d:%s: bpp:%d unsupported! Overwritten with 8.\n",
+			      __FILE__, __LINE__, __func__, ctx->fmt->bpp);
+		extract = CAL_PIX_PROC_EXTRACT_B8;
+		pack = CAL_PIX_PROC_PACK_B8;
+		break;
+	}
 
 	val = reg_read(ctx->dev, CAL_PIX_PROC(ctx->csi2_port));
-	set_field(&val, CAL_PIX_PROC_EXTRACT_B8, CAL_PIX_PROC_EXTRACT_MASK);
+	set_field(&val, extract, CAL_PIX_PROC_EXTRACT_MASK);
 	set_field(&val, CAL_PIX_PROC_DPCMD_BYPASS, CAL_PIX_PROC_DPCMD_MASK);
 	set_field(&val, CAL_PIX_PROC_DPCME_BYPASS, CAL_PIX_PROC_DPCME_MASK);
-	set_field(&val, CAL_PIX_PROC_PACK_B8, CAL_PIX_PROC_PACK_MASK);
+	set_field(&val, pack, CAL_PIX_PROC_PACK_MASK);
 	set_field(&val, ctx->csi2_port, CAL_PIX_PROC_CPORT_MASK);
 	set_field(&val, CAL_GEN_ENABLE, CAL_PIX_PROC_EN_MASK);
 	reg_write(ctx->dev, CAL_PIX_PROC(ctx->csi2_port), val);
@@ -680,12 +1033,13 @@ static void pix_proc_config(struct cal_ctx *ctx)
 }
 
 static void cal_wr_dma_config(struct cal_ctx *ctx,
-			      unsigned int width)
+			      unsigned int width, unsigned int height)
 {
 	u32 val;
 
 	val = reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port));
 	set_field(&val, ctx->csi2_port, CAL_WR_DMA_CTRL_CPORT_MASK);
+	set_field(&val, height, CAL_WR_DMA_CTRL_YSIZE_MASK);
 	set_field(&val, CAL_WR_DMA_CTRL_DTAG_PIX_DAT,
 		  CAL_WR_DMA_CTRL_DTAG_MASK);
 	set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST,
@@ -720,6 +1074,16 @@ static void cal_wr_dma_config(struct cal_ctx *ctx,
 	reg_write(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port), val);
 	ctx_dbg(3, ctx, "CAL_WR_DMA_XSIZE(%d) = 0x%08x\n", ctx->csi2_port,
 		reg_read(ctx->dev, CAL_WR_DMA_XSIZE(ctx->csi2_port)));
+
+	val = reg_read(ctx->dev, CAL_CTRL);
+	set_field(&val, CAL_CTRL_BURSTSIZE_BURST128, CAL_CTRL_BURSTSIZE_MASK);
+	set_field(&val, 0xF, CAL_CTRL_TAGCNT_MASK);
+	set_field(&val, CAL_CTRL_POSTED_WRITES_NONPOSTED,
+		  CAL_CTRL_POSTED_WRITES_MASK);
+	set_field(&val, 0xFF, CAL_CTRL_MFLAGL_MASK);
+	set_field(&val, 0xFF, CAL_CTRL_MFLAGH_MASK);
+	reg_write(ctx->dev, CAL_CTRL, val);
+	ctx_dbg(3, ctx, "CAL_CTRL = 0x%08x\n", reg_read(ctx->dev, CAL_CTRL));
 }
 
 static void cal_wr_dma_addr(struct cal_ctx *ctx, unsigned int dmaaddr)
@@ -733,41 +1097,28 @@ static void cal_wr_dma_addr(struct cal_ctx *ctx, unsigned int dmaaddr)
 #define TCLK_TERM	0
 #define TCLK_MISS	1
 #define TCLK_SETTLE	14
-#define THS_SETTLE	15
 
 static void csi2_phy_config(struct cal_ctx *ctx)
 {
 	unsigned int reg0, reg1;
 	unsigned int ths_term, ths_settle;
-	unsigned int ddrclkperiod_us;
+	unsigned int csi2_ddrclk_khz;
+	struct v4l2_fwnode_bus_mipi_csi2 *mipi_csi2 =
+			&ctx->endpoint.bus.mipi_csi2;
+	u32 num_lanes = mipi_csi2->num_data_lanes;
 
-	/*
-	 * THS_TERM: Programmed value = floor(20 ns/DDRClk period) - 2.
-	 */
-	ddrclkperiod_us = ctx->external_rate / 2000000;
-	ddrclkperiod_us = 1000000 / ddrclkperiod_us;
-	ctx_dbg(1, ctx, "ddrclkperiod_us: %d\n", ddrclkperiod_us);
+	/* DPHY timing configuration */
+	/* CSI-2 is DDR and we only count used lanes. */
+	csi2_ddrclk_khz = ctx->external_rate / 1000
+		/ (2 * num_lanes) * ctx->fmt->bpp;
+	ctx_dbg(1, ctx, "csi2_ddrclk_khz: %d\n", csi2_ddrclk_khz);
 
-	ths_term = 20000 / ddrclkperiod_us;
-	ths_term = (ths_term >= 2) ? ths_term - 2 : ths_term;
+	/* THS_TERM: Programmed value = floor(20 ns/DDRClk period) */
+	ths_term = 20 * csi2_ddrclk_khz / 1000000;
 	ctx_dbg(1, ctx, "ths_term: %d (0x%02x)\n", ths_term, ths_term);
 
-	/*
-	 * THS_SETTLE: Programmed value = floor(176.3 ns/CtrlClk period) - 1.
-	 *	Since CtrlClk is fixed at 96Mhz then we get
-	 *	ths_settle = floor(176.3 / 10.416) - 1 = 15
-	 * If we ever switch to a dynamic clock then this code might be useful
-	 *
-	 * unsigned int ctrlclkperiod_us;
-	 * ctrlclkperiod_us = 96000000 / 1000000;
-	 * ctrlclkperiod_us = 1000000 / ctrlclkperiod_us;
-	 * ctx_dbg(1, ctx, "ctrlclkperiod_us: %d\n", ctrlclkperiod_us);
-
-	 * ths_settle = 176300  / ctrlclkperiod_us;
-	 * ths_settle = (ths_settle > 1) ? ths_settle - 1 : ths_settle;
-	 */
-
-	ths_settle = THS_SETTLE;
+	/* THS_SETTLE: Programmed value = floor(105 ns/DDRClk period) + 4 */
+	ths_settle = (105 * csi2_ddrclk_khz / 1000000) + 4;
 	ctx_dbg(1, ctx, "ths_settle: %d (0x%02x)\n", ths_settle, ths_settle);
 
 	reg0 = reg_read(ctx->cc, CAL_CSI2_PHY_REG0);
@@ -979,15 +1330,25 @@ static int cal_calc_format_size(struct cal_ctx *ctx,
 				const struct cal_fmt *fmt,
 				struct v4l2_format *f)
 {
+	u32 bpl, max_width;
+
 	if (!fmt) {
 		ctx_dbg(3, ctx, "No cal_fmt provided!\n");
 		return -EINVAL;
 	}
 
-	v4l_bound_align_image(&f->fmt.pix.width, 48, MAX_WIDTH, 2,
-			      &f->fmt.pix.height, 32, MAX_HEIGHT, 0, 0);
-	f->fmt.pix.bytesperline = bytes_per_line(f->fmt.pix.width,
-						 fmt->depth >> 3);
+	/*
+	 * Maximum width is bound by the DMA max width in bytes.
+	 * We need to recalculate the actual maxi width depending on the
+	 * number of bytes per pixels required.
+	 */
+	max_width = MAX_WIDTH_BYTES / (ALIGN(fmt->bpp, 8) >> 3);
+	v4l_bound_align_image(&f->fmt.pix.width, 48, max_width, 2,
+			      &f->fmt.pix.height, 32, MAX_HEIGHT_LINES, 0, 0);
+
+	bpl = (f->fmt.pix.width * ALIGN(fmt->bpp, 8)) >> 3;
+	f->fmt.pix.bytesperline = ALIGN(bpl, 16);
+
 	f->fmt.pix.sizeimage = f->fmt.pix.height *
 			       f->fmt.pix.bytesperline;
 
@@ -1132,6 +1493,7 @@ static int cal_enum_framesizes(struct file *file, void *fh,
 	fse.index = fsize->index;
 	fse.pad = 0;
 	fse.code = fmt->code;
+	fse.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 
 	ret = v4l2_subdev_call(ctx->sensor, pad, enum_frame_size, NULL, &fse);
 	if (ret)
@@ -1299,36 +1661,50 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count)
 	if (ret < 0)
 		goto err;
 
+	ret = v4l2_subdev_call(ctx->sensor, core, s_power, 1);
+	if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV) {
+		ctx_err(ctx, "power on failed in subdev\n");
+		goto err;
+	}
+
 	cal_runtime_get(ctx->dev);
 
-	enable_irqs(ctx);
-	camerarx_phy_enable(ctx);
-	csi2_init(ctx);
-	csi2_phy_config(ctx);
-	csi2_lane_config(ctx);
 	csi2_ctx_config(ctx);
 	pix_proc_config(ctx);
-	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline);
-	cal_wr_dma_addr(ctx, addr);
-	csi2_ppi_enable(ctx);
+	cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline,
+			  ctx->v_fmt.fmt.pix.height);
+	csi2_lane_config(ctx);
+
+	enable_irqs(ctx);
+	csi2_phy_init(ctx);
 
 	ret = v4l2_subdev_call(ctx->sensor, video, s_stream, 1);
 	if (ret) {
+		v4l2_subdev_call(ctx->sensor, core, s_power, 0);
 		ctx_err(ctx, "stream on failed in subdev\n");
 		cal_runtime_put(ctx->dev);
 		goto err;
 	}
 
+	csi2_wait_for_phy(ctx);
+	cal_wr_dma_addr(ctx, addr);
+	csi2_ppi_enable(ctx);
+
 	if (debug >= 4)
 		cal_quickdump_regs(ctx->dev);
 
 	return 0;
 
 err:
+	spin_lock_irqsave(&ctx->slock, flags);
+	vb2_buffer_done(&ctx->cur_frm->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
+	ctx->cur_frm = NULL;
+	ctx->next_frm = NULL;
 	list_for_each_entry_safe(buf, tmp, &dma_q->active, list) {
 		list_del(&buf->list);
 		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
 	}
+	spin_unlock_irqrestore(&ctx->slock, flags);
 	return ret;
 }
 
@@ -1338,12 +1714,18 @@ static void cal_stop_streaming(struct vb2_queue *vq)
 	struct cal_dmaqueue *dma_q = &ctx->vidq;
 	struct cal_buffer *buf, *tmp;
 	unsigned long flags;
+	int ret;
+
+	csi2_ppi_disable(ctx);
+	disable_irqs(ctx);
+	csi2_phy_deinit(ctx);
 
 	if (v4l2_subdev_call(ctx->sensor, video, s_stream, 0))
 		ctx_err(ctx, "stream off failed in subdev\n");
 
-	csi2_ppi_disable(ctx);
-	disable_irqs(ctx);
+	ret = v4l2_subdev_call(ctx->sensor, core, s_power, 0);
+	if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV)
+		ctx_err(ctx, "power off failed in subdev\n");
 
 	/* Release all active buffers */
 	spin_lock_irqsave(&ctx->slock, flags);
@@ -1399,6 +1781,7 @@ static const struct v4l2_ioctl_ops cal_ioctl_ops = {
 	.vidioc_querybuf      = vb2_ioctl_querybuf,
 	.vidioc_qbuf          = vb2_ioctl_qbuf,
 	.vidioc_dqbuf         = vb2_ioctl_dqbuf,
+	.vidioc_expbuf        = vb2_ioctl_expbuf,
 	.vidioc_enum_input    = cal_enum_input,
 	.vidioc_g_input       = cal_g_input,
 	.vidioc_s_input       = cal_s_input,
@@ -1451,6 +1834,7 @@ static int cal_async_bound(struct v4l2_async_notifier *notifier,
 
 		memset(&mbus_code, 0, sizeof(mbus_code));
 		mbus_code.index = j;
+		mbus_code.which = V4L2_SUBDEV_FORMAT_ACTIVE;
 		ret = v4l2_subdev_call(subdev, pad, enum_mbus_code,
 				       NULL, &mbus_code);
 		if (ret)
@@ -1804,10 +2188,15 @@ err_exit:
 	return NULL;
 }
 
+static const struct of_device_id cal_of_match[];
+
 static int cal_probe(struct platform_device *pdev)
 {
 	struct cal_dev *dev;
 	struct cal_ctx *ctx;
+	struct device_node *parent = pdev->dev.of_node;
+	struct regmap *syscon_camerrx = NULL;
+	u32 syscon_camerrx_offset = 0;
 	int ret;
 	int irq;
 	int i;
@@ -1816,6 +2205,14 @@ static int cal_probe(struct platform_device *pdev)
 	if (!dev)
 		return -ENOMEM;
 
+	dev->data = of_device_get_match_data(&pdev->dev);
+	if (!dev->data) {
+		dev_err(&pdev->dev, "Could not get feature data based on compatible version\n");
+		return -ENODEV;
+	}
+
+	dev->flags = dev->data->flags;
+
 	/* set pseudo v4l2 device name so we can use v4l2_printk */
 	strscpy(dev->v4l2_dev.name, CAL_MODULE_NAME,
 		sizeof(dev->v4l2_dev.name));
@@ -1823,6 +2220,38 @@ static int cal_probe(struct platform_device *pdev)
 	/* save pdev pointer */
 	dev->pdev = pdev;
 
+	syscon_camerrx = syscon_regmap_lookup_by_phandle(parent,
+							 "ti,camerrx-control");
+	ret = of_property_read_u32_index(parent, "ti,camerrx-control", 1,
+					 &syscon_camerrx_offset);
+	if (IS_ERR(syscon_camerrx))
+		ret = PTR_ERR(syscon_camerrx);
+	if (ret) {
+		dev_warn(&pdev->dev, "failed to get ti,camerrx-control: %d\n",
+			 ret);
+
+		/*
+		 * Backward DTS compatibility.
+		 * If syscon entry is not present then check if the
+		 * camerrx_control resource is present.
+		 */
+		syscon_camerrx = cal_get_camerarx_regmap(dev);
+		if (IS_ERR(syscon_camerrx)) {
+			dev_err(&pdev->dev, "failed to get camerrx_control regmap\n");
+			return PTR_ERR(syscon_camerrx);
+		}
+		/* In this case the base already point to the direct
+		 * CM register so no need for an offset
+		 */
+		syscon_camerrx_offset = 0;
+	}
+
+	dev->syscon_camerrx = syscon_camerrx;
+	dev->syscon_camerrx_offset = syscon_camerrx_offset;
+	ret = cal_camerarx_regmap_init(dev);
+	if (ret)
+		return ret;
+
 	dev->res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 						"cal_top");
 	dev->base = devm_ioremap_resource(&pdev->dev, dev->res);
@@ -1841,23 +2270,24 @@ static int cal_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dev);
 
-	dev->cm = cm_create(dev);
-	if (IS_ERR(dev->cm))
-		return PTR_ERR(dev->cm);
-
 	dev->cc[0] = cc_create(dev, 0);
 	if (IS_ERR(dev->cc[0]))
 		return PTR_ERR(dev->cc[0]);
 
-	dev->cc[1] = cc_create(dev, 1);
-	if (IS_ERR(dev->cc[1]))
-		return PTR_ERR(dev->cc[1]);
+	if (cal_data_get_num_csi2_phy(dev) > 1) {
+		dev->cc[1] = cc_create(dev, 1);
+		if (IS_ERR(dev->cc[1]))
+			return PTR_ERR(dev->cc[1]);
+	} else {
+		dev->cc[1] = NULL;
+	}
 
 	dev->ctx[0] = NULL;
 	dev->ctx[1] = NULL;
 
 	dev->ctx[0] = cal_create_instance(dev, 0);
-	dev->ctx[1] = cal_create_instance(dev, 1);
+	if (cal_data_get_num_csi2_phy(dev) > 1)
+		dev->ctx[1] = cal_create_instance(dev, 1);
 	if (!dev->ctx[0] && !dev->ctx[1]) {
 		cal_err(dev, "Neither port is configured, no point in staying up\n");
 		return -ENODEV;
@@ -1924,7 +2354,22 @@ static int cal_remove(struct platform_device *pdev)
 
 #if defined(CONFIG_OF)
 static const struct of_device_id cal_of_match[] = {
-	{ .compatible = "ti,dra72-cal", },
+	{
+		.compatible = "ti,dra72-cal",
+		.data = (void *)&dra72x_cal_data,
+	},
+	{
+		.compatible = "ti,dra72-pre-es2-cal",
+		.data = (void *)&dra72x_es1_cal_data,
+	},
+	{
+		.compatible = "ti,dra76-cal",
+		.data = (void *)&dra76x_cal_data,
+	},
+	{
+		.compatible = "ti,am654-cal",
+		.data = (void *)&am654_cal_data,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, cal_of_match);
diff --git a/drivers/media/platform/ti-vpe/cal_regs.h b/drivers/media/platform/ti-vpe/cal_regs.h
index 68cfc922b422..0b76d1186074 100644
--- a/drivers/media/platform/ti-vpe/cal_regs.h
+++ b/drivers/media/platform/ti-vpe/cal_regs.h
@@ -10,6 +10,30 @@
 #ifndef __TI_CAL_REGS_H
 #define __TI_CAL_REGS_H
 
+/*
+ * struct cal_dev.flags possibilities
+ *
+ * DRA72_CAL_PRE_ES2_LDO_DISABLE:
+ *   Errata i913: CSI2 LDO Needs to be disabled when module is powered on
+ *
+ *   Enabling CSI2 LDO shorts it to core supply. It is crucial the 2 CSI2
+ *   LDOs on the device are disabled if CSI-2 module is powered on
+ *   (0x4845 B304 | 0x4845 B384 [28:27] = 0x1) or in ULPS (0x4845 B304
+ *   | 0x4845 B384 [28:27] = 0x2) mode. Common concerns include: high
+ *   current draw on the module supply in active mode.
+ *
+ *   Errata does not apply when CSI-2 module is powered off
+ *   (0x4845 B304 | 0x4845 B384 [28:27] = 0x0).
+ *
+ * SW Workaround:
+ *	Set the following register bits to disable the LDO,
+ *	which is essentially CSI2 REG10 bit 6:
+ *
+ *		Core 0:  0x4845 B828 = 0x0000 0040
+ *		Core 1:  0x4845 B928 = 0x0000 0040
+ */
+#define DRA72_CAL_PRE_ES2_LDO_DISABLE BIT(0)
+
 #define CAL_NUM_CSI2_PORTS		2
 
 /* CAL register offsets */
@@ -71,6 +95,7 @@
 #define CAL_CSI2_PHY_REG0		0x000
 #define CAL_CSI2_PHY_REG1		0x004
 #define CAL_CSI2_PHY_REG2		0x008
+#define CAL_CSI2_PHY_REG10		0x028
 
 /* CAL Control Module Core Camerrx Control register offsets */
 #define CM_CTRL_CORE_CAMERRX_CONTROL	0x000
@@ -110,7 +135,7 @@
 #define CAL_HL_HWINFO_NPPI_CONTEXTS_EIGHT		2
 #define CAL_HL_HWINFO_NPPI_CONTEXTS_RESERVED		3
 
-#define CAL_HL_SYSCONFIG_SOFTRESET_MASK		BIT_MASK(0)
+#define CAL_HL_SYSCONFIG_SOFTRESET_MASK		BIT(0)
 #define CAL_HL_SYSCONFIG_SOFTRESET_DONE			0x0
 #define CAL_HL_SYSCONFIG_SOFTRESET_PENDING		0x1
 #define CAL_HL_SYSCONFIG_SOFTRESET_NOACTION		0x0
@@ -121,11 +146,11 @@
 #define CAL_HL_SYSCONFIG_IDLEMODE_SMART1		2
 #define CAL_HL_SYSCONFIG_IDLEMODE_SMART2		3
 
-#define CAL_HL_IRQ_EOI_LINE_NUMBER_MASK		BIT_MASK(0)
+#define CAL_HL_IRQ_EOI_LINE_NUMBER_MASK		BIT(0)
 #define CAL_HL_IRQ_EOI_LINE_NUMBER_READ0		0
 #define CAL_HL_IRQ_EOI_LINE_NUMBER_EOI0			0
 
-#define CAL_HL_IRQ_MASK(m)			BIT_MASK(m-1)
+#define CAL_HL_IRQ_MASK(m)			BIT((m) - 1)
 #define CAL_HL_IRQ_NOACTION				0x0
 #define CAL_HL_IRQ_ENABLE				0x1
 #define CAL_HL_IRQ_CLEAR				0x1
@@ -133,7 +158,7 @@
 #define CAL_HL_IRQ_ENABLED				0x1
 #define CAL_HL_IRQ_PENDING				0x1
 
-#define CAL_PIX_PROC_EN_MASK			BIT_MASK(0)
+#define CAL_PIX_PROC_EN_MASK			BIT(0)
 #define CAL_PIX_PROC_EXTRACT_MASK		GENMASK(4, 1)
 #define CAL_PIX_PROC_EXTRACT_B6				0x0
 #define CAL_PIX_PROC_EXTRACT_B7				0x1
@@ -179,7 +204,7 @@
 #define CAL_PIX_PROC_PACK_ARGB				0x6
 #define CAL_PIX_PROC_CPORT_MASK			GENMASK(23, 19)
 
-#define CAL_CTRL_POSTED_WRITES_MASK		BIT_MASK(0)
+#define CAL_CTRL_POSTED_WRITES_MASK		BIT(0)
 #define CAL_CTRL_POSTED_WRITES_NONPOSTED		0
 #define CAL_CTRL_POSTED_WRITES				1
 #define CAL_CTRL_TAGCNT_MASK			GENMASK(4, 1)
@@ -190,10 +215,10 @@
 #define CAL_CTRL_BURSTSIZE_BURST128			0x3
 #define CAL_CTRL_LL_FORCE_STATE_MASK		GENMASK(12, 7)
 #define CAL_CTRL_MFLAGL_MASK			GENMASK(20, 13)
-#define CAL_CTRL_PWRSCPCLK_MASK			BIT_MASK(21)
+#define CAL_CTRL_PWRSCPCLK_MASK			BIT(21)
 #define CAL_CTRL_PWRSCPCLK_AUTO				0
 #define CAL_CTRL_PWRSCPCLK_FORCE			1
-#define CAL_CTRL_RD_DMA_STALL_MASK		BIT_MASK(22)
+#define CAL_CTRL_RD_DMA_STALL_MASK		BIT(22)
 #define CAL_CTRL_MFLAGH_MASK			GENMASK(31, 24)
 
 #define CAL_CTRL1_PPI_GROUPING_MASK		GENMASK(1, 0)
@@ -218,18 +243,18 @@
 #define CAL_VPORT_CTRL1_PCLK_MASK		GENMASK(16, 0)
 #define CAL_VPORT_CTRL1_XBLK_MASK		GENMASK(24, 17)
 #define CAL_VPORT_CTRL1_YBLK_MASK		GENMASK(30, 25)
-#define CAL_VPORT_CTRL1_WIDTH_MASK		BIT_MASK(31)
+#define CAL_VPORT_CTRL1_WIDTH_MASK		BIT(31)
 #define CAL_VPORT_CTRL1_WIDTH_ONE			0
 #define CAL_VPORT_CTRL1_WIDTH_TWO			1
 
 #define CAL_VPORT_CTRL2_CPORT_MASK		GENMASK(4, 0)
-#define CAL_VPORT_CTRL2_FREERUNNING_MASK	BIT_MASK(15)
+#define CAL_VPORT_CTRL2_FREERUNNING_MASK	BIT(15)
 #define CAL_VPORT_CTRL2_FREERUNNING_GATED		0
 #define CAL_VPORT_CTRL2_FREERUNNING_FREE		1
-#define CAL_VPORT_CTRL2_FS_RESETS_MASK		BIT_MASK(16)
+#define CAL_VPORT_CTRL2_FS_RESETS_MASK		BIT(16)
 #define CAL_VPORT_CTRL2_FS_RESETS_NO			0
 #define CAL_VPORT_CTRL2_FS_RESETS_YES			1
-#define CAL_VPORT_CTRL2_FSM_RESET_MASK		BIT_MASK(17)
+#define CAL_VPORT_CTRL2_FSM_RESET_MASK		BIT(17)
 #define CAL_VPORT_CTRL2_FSM_RESET_NOEFFECT		0
 #define CAL_VPORT_CTRL2_FSM_RESET			1
 #define CAL_VPORT_CTRL2_RDY_THR_MASK		GENMASK(31, 18)
@@ -237,23 +262,23 @@
 #define CAL_BYS_CTRL1_PCLK_MASK			GENMASK(16, 0)
 #define CAL_BYS_CTRL1_XBLK_MASK			GENMASK(24, 17)
 #define CAL_BYS_CTRL1_YBLK_MASK			GENMASK(30, 25)
-#define CAL_BYS_CTRL1_BYSINEN_MASK		BIT_MASK(31)
+#define CAL_BYS_CTRL1_BYSINEN_MASK		BIT(31)
 
 #define CAL_BYS_CTRL2_CPORTIN_MASK		GENMASK(4, 0)
 #define CAL_BYS_CTRL2_CPORTOUT_MASK		GENMASK(9, 5)
-#define CAL_BYS_CTRL2_DUPLICATEDDATA_MASK	BIT_MASK(10)
+#define CAL_BYS_CTRL2_DUPLICATEDDATA_MASK	BIT(10)
 #define CAL_BYS_CTRL2_DUPLICATEDDATA_NO			0
 #define CAL_BYS_CTRL2_DUPLICATEDDATA_YES		1
-#define CAL_BYS_CTRL2_FREERUNNING_MASK		BIT_MASK(11)
+#define CAL_BYS_CTRL2_FREERUNNING_MASK		BIT(11)
 #define CAL_BYS_CTRL2_FREERUNNING_NO			0
 #define CAL_BYS_CTRL2_FREERUNNING_YES			1
 
-#define CAL_RD_DMA_CTRL_GO_MASK			BIT_MASK(0)
+#define CAL_RD_DMA_CTRL_GO_MASK			BIT(0)
 #define CAL_RD_DMA_CTRL_GO_DIS				0
 #define CAL_RD_DMA_CTRL_GO_EN				1
 #define CAL_RD_DMA_CTRL_GO_IDLE				0
 #define CAL_RD_DMA_CTRL_GO_BUSY				1
-#define CAL_RD_DMA_CTRL_INIT_MASK		BIT_MASK(1)
+#define CAL_RD_DMA_CTRL_INIT_MASK		BIT(1)
 #define CAL_RD_DMA_CTRL_BW_LIMITER_MASK		GENMASK(10, 2)
 #define CAL_RD_DMA_CTRL_OCP_TAG_CNT_MASK	GENMASK(14, 11)
 #define CAL_RD_DMA_CTRL_PCLK_MASK		GENMASK(31, 15)
@@ -277,13 +302,13 @@
 #define CAL_RD_DMA_CTRL2_CIRC_MODE_SIXTEEN		3
 #define CAL_RD_DMA_CTRL2_CIRC_MODE_SIXTYFOUR		4
 #define CAL_RD_DMA_CTRL2_CIRC_MODE_RESERVED		5
-#define CAL_RD_DMA_CTRL2_ICM_CSTART_MASK	BIT_MASK(3)
+#define CAL_RD_DMA_CTRL2_ICM_CSTART_MASK	BIT(3)
 #define CAL_RD_DMA_CTRL2_PATTERN_MASK		GENMASK(5, 4)
 #define CAL_RD_DMA_CTRL2_PATTERN_LINEAR			0
 #define CAL_RD_DMA_CTRL2_PATTERN_YUV420			1
 #define CAL_RD_DMA_CTRL2_PATTERN_RD2SKIP2		2
 #define CAL_RD_DMA_CTRL2_PATTERN_RD2SKIP4		3
-#define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_MASK	BIT_MASK(6)
+#define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_MASK	BIT(6)
 #define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_FREERUNNING	0
 #define CAL_RD_DMA_CTRL2_BYSOUT_LE_WAIT_WAITFORBYSOUT	1
 #define CAL_RD_DMA_CTRL2_CIRC_SIZE_MASK		GENMASK(29, 16)
@@ -300,7 +325,7 @@
 #define CAL_WR_DMA_CTRL_PATTERN_WR2SKIP2		2
 #define CAL_WR_DMA_CTRL_PATTERN_WR2SKIP4		3
 #define CAL_WR_DMA_CTRL_PATTERN_RESERVED		1
-#define CAL_WR_DMA_CTRL_ICM_PSTART_MASK		BIT_MASK(5)
+#define CAL_WR_DMA_CTRL_ICM_PSTART_MASK		BIT(5)
 #define CAL_WR_DMA_CTRL_DTAG_MASK		GENMASK(8, 6)
 #define CAL_WR_DMA_CTRL_DTAG_ATT_HDR			0
 #define CAL_WR_DMA_CTRL_DTAG_ATT_DAT			1
@@ -311,7 +336,7 @@
 #define CAL_WR_DMA_CTRL_DTAG_D6				6
 #define CAL_WR_DMA_CTRL_DTAG_D7				7
 #define CAL_WR_DMA_CTRL_CPORT_MASK		GENMASK(13, 9)
-#define CAL_WR_DMA_CTRL_STALL_RD_MASK		BIT_MASK(14)
+#define CAL_WR_DMA_CTRL_STALL_RD_MASK		BIT(14)
 #define CAL_WR_DMA_CTRL_YSIZE_MASK		GENMASK(31, 18)
 
 #define CAL_WR_DMA_ADDR_MASK			GENMASK(31, 4)
@@ -327,9 +352,9 @@
 #define CAL_WR_DMA_XSIZE_XSKIP_MASK		GENMASK(15, 3)
 #define CAL_WR_DMA_XSIZE_MASK			GENMASK(31, 19)
 
-#define CAL_CSI2_PPI_CTRL_IF_EN_MASK		BIT_MASK(0)
-#define CAL_CSI2_PPI_CTRL_ECC_EN_MASK		BIT_MASK(2)
-#define CAL_CSI2_PPI_CTRL_FRAME_MASK		BIT_MASK(3)
+#define CAL_CSI2_PPI_CTRL_IF_EN_MASK		BIT(0)
+#define CAL_CSI2_PPI_CTRL_ECC_EN_MASK		BIT(2)
+#define CAL_CSI2_PPI_CTRL_FRAME_MASK		BIT(3)
 #define CAL_CSI2_PPI_CTRL_FRAME_IMMEDIATE		0
 #define CAL_CSI2_PPI_CTRL_FRAME				1
 
@@ -340,18 +365,18 @@
 #define CAL_CSI2_COMPLEXIO_CFG_POSITION_2			2
 #define CAL_CSI2_COMPLEXIO_CFG_POSITION_1			1
 #define CAL_CSI2_COMPLEXIO_CFG_POSITION_NOT_USED		0
-#define CAL_CSI2_COMPLEXIO_CFG_CLOCK_POL_MASK		BIT_MASK(3)
+#define CAL_CSI2_COMPLEXIO_CFG_CLOCK_POL_MASK		BIT(3)
 #define CAL_CSI2_COMPLEXIO_CFG_POL_PLUSMINUS			0
 #define CAL_CSI2_COMPLEXIO_CFG_POL_MINUSPLUS			1
 #define CAL_CSI2_COMPLEXIO_CFG_DATA1_POSITION_MASK	GENMASK(6, 4)
-#define CAL_CSI2_COMPLEXIO_CFG_DATA1_POL_MASK		BIT_MASK(7)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA1_POL_MASK		BIT(7)
 #define CAL_CSI2_COMPLEXIO_CFG_DATA2_POSITION_MASK	GENMASK(10, 8)
-#define CAL_CSI2_COMPLEXIO_CFG_DATA2_POL_MASK		BIT_MASK(11)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA2_POL_MASK		BIT(11)
 #define CAL_CSI2_COMPLEXIO_CFG_DATA3_POSITION_MASK	GENMASK(14, 12)
-#define CAL_CSI2_COMPLEXIO_CFG_DATA3_POL_MASK		BIT_MASK(15)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA3_POL_MASK		BIT(15)
 #define CAL_CSI2_COMPLEXIO_CFG_DATA4_POSITION_MASK	GENMASK(18, 16)
-#define CAL_CSI2_COMPLEXIO_CFG_DATA4_POL_MASK		BIT_MASK(19)
-#define CAL_CSI2_COMPLEXIO_CFG_PWR_AUTO_MASK		BIT_MASK(24)
+#define CAL_CSI2_COMPLEXIO_CFG_DATA4_POL_MASK		BIT(19)
+#define CAL_CSI2_COMPLEXIO_CFG_PWR_AUTO_MASK		BIT(24)
 #define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_MASK		GENMASK(26, 25)
 #define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_OFF		0
 #define CAL_CSI2_COMPLEXIO_CFG_PWR_STATUS_STATE_ON		1
@@ -360,83 +385,83 @@
 #define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_OFF		0
 #define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ON			1
 #define CAL_CSI2_COMPLEXIO_CFG_PWR_CMD_STATE_ULP		2
-#define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK		BIT_MASK(29)
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_MASK		BIT(29)
 #define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETCOMPLETED	1
 #define CAL_CSI2_COMPLEXIO_CFG_RESET_DONE_RESETONGOING		0
-#define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK		BIT_MASK(30)
+#define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_MASK		BIT(30)
 #define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL			0
 #define CAL_CSI2_COMPLEXIO_CFG_RESET_CTRL_OPERATIONAL		1
 
 #define CAL_CSI2_SHORT_PACKET_MASK	GENMASK(23, 0)
 
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS1_MASK		BIT_MASK(0)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS2_MASK		BIT_MASK(1)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS3_MASK		BIT_MASK(2)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS4_MASK		BIT_MASK(3)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS5_MASK		BIT_MASK(4)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS1_MASK	BIT_MASK(5)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS2_MASK	BIT_MASK(6)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS3_MASK	BIT_MASK(7)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS4_MASK	BIT_MASK(8)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS5_MASK	BIT_MASK(9)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC1_MASK		BIT_MASK(10)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC2_MASK		BIT_MASK(11)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC3_MASK		BIT_MASK(12)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC4_MASK		BIT_MASK(13)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC5_MASK		BIT_MASK(14)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL1_MASK		BIT_MASK(15)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL2_MASK		BIT_MASK(16)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL3_MASK		BIT_MASK(17)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL4_MASK		BIT_MASK(18)
-#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL5_MASK		BIT_MASK(19)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM1_MASK		BIT_MASK(20)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM2_MASK		BIT_MASK(21)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM3_MASK		BIT_MASK(22)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM4_MASK		BIT_MASK(23)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM5_MASK		BIT_MASK(24)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEALLULPMENTER_MASK	BIT_MASK(25)
-#define CAL_CSI2_COMPLEXIO_IRQ_STATEALLULPMEXIT_MASK	BIT_MASK(26)
-#define CAL_CSI2_COMPLEXIO_IRQ_FIFO_OVR_MASK		BIT_MASK(27)
-#define CAL_CSI2_COMPLEXIO_IRQ_SHORT_PACKET_MASK	BIT_MASK(28)
-#define CAL_CSI2_COMPLEXIO_IRQ_ECC_NO_CORRECTION_MASK	BIT_MASK(30)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS1_MASK		BIT(0)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS2_MASK		BIT(1)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS3_MASK		BIT(2)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS4_MASK		BIT(3)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTHS5_MASK		BIT(4)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS1_MASK	BIT(5)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS2_MASK	BIT(6)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS3_MASK	BIT(7)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS4_MASK	BIT(8)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRSOTSYNCHS5_MASK	BIT(9)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC1_MASK		BIT(10)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC2_MASK		BIT(11)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC3_MASK		BIT(12)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC4_MASK		BIT(13)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRESC5_MASK		BIT(14)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL1_MASK		BIT(15)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL2_MASK		BIT(16)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL3_MASK		BIT(17)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL4_MASK		BIT(18)
+#define CAL_CSI2_COMPLEXIO_IRQ_ERRCONTROL5_MASK		BIT(19)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM1_MASK		BIT(20)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM2_MASK		BIT(21)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM3_MASK		BIT(22)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM4_MASK		BIT(23)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEULPM5_MASK		BIT(24)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEALLULPMENTER_MASK	BIT(25)
+#define CAL_CSI2_COMPLEXIO_IRQ_STATEALLULPMEXIT_MASK	BIT(26)
+#define CAL_CSI2_COMPLEXIO_IRQ_FIFO_OVR_MASK		BIT(27)
+#define CAL_CSI2_COMPLEXIO_IRQ_SHORT_PACKET_MASK	BIT(28)
+#define CAL_CSI2_COMPLEXIO_IRQ_ECC_NO_CORRECTION_MASK	BIT(30)
 
 #define CAL_CSI2_TIMING_STOP_STATE_COUNTER_IO1_MASK	GENMASK(12, 0)
-#define CAL_CSI2_TIMING_STOP_STATE_X4_IO1_MASK		BIT_MASK(13)
-#define CAL_CSI2_TIMING_STOP_STATE_X16_IO1_MASK		BIT_MASK(14)
-#define CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK		BIT_MASK(15)
-
-#define CAL_CSI2_VC_IRQ_FS_IRQ_0_MASK			BIT_MASK(0)
-#define CAL_CSI2_VC_IRQ_FE_IRQ_0_MASK			BIT_MASK(1)
-#define CAL_CSI2_VC_IRQ_LS_IRQ_0_MASK			BIT_MASK(2)
-#define CAL_CSI2_VC_IRQ_LE_IRQ_0_MASK			BIT_MASK(3)
-#define CAL_CSI2_VC_IRQ_CS_IRQ_0_MASK			BIT_MASK(4)
-#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_0_MASK	BIT_MASK(5)
-#define CAL_CSI2_VC_IRQ_FS_IRQ_1_MASK			BIT_MASK(8)
-#define CAL_CSI2_VC_IRQ_FE_IRQ_1_MASK			BIT_MASK(9)
-#define CAL_CSI2_VC_IRQ_LS_IRQ_1_MASK			BIT_MASK(10)
-#define CAL_CSI2_VC_IRQ_LE_IRQ_1_MASK			BIT_MASK(11)
-#define CAL_CSI2_VC_IRQ_CS_IRQ_1_MASK			BIT_MASK(12)
-#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_1_MASK	BIT_MASK(13)
-#define CAL_CSI2_VC_IRQ_FS_IRQ_2_MASK			BIT_MASK(16)
-#define CAL_CSI2_VC_IRQ_FE_IRQ_2_MASK			BIT_MASK(17)
-#define CAL_CSI2_VC_IRQ_LS_IRQ_2_MASK			BIT_MASK(18)
-#define CAL_CSI2_VC_IRQ_LE_IRQ_2_MASK			BIT_MASK(19)
-#define CAL_CSI2_VC_IRQ_CS_IRQ_2_MASK			BIT_MASK(20)
-#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_2_MASK	BIT_MASK(21)
-#define CAL_CSI2_VC_IRQ_FS_IRQ_3_MASK			BIT_MASK(24)
-#define CAL_CSI2_VC_IRQ_FE_IRQ_3_MASK			BIT_MASK(25)
-#define CAL_CSI2_VC_IRQ_LS_IRQ_3_MASK			BIT_MASK(26)
-#define CAL_CSI2_VC_IRQ_LE_IRQ_3_MASK			BIT_MASK(27)
-#define CAL_CSI2_VC_IRQ_CS_IRQ_3_MASK			BIT_MASK(28)
-#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_3_MASK	BIT_MASK(29)
+#define CAL_CSI2_TIMING_STOP_STATE_X4_IO1_MASK		BIT(13)
+#define CAL_CSI2_TIMING_STOP_STATE_X16_IO1_MASK		BIT(14)
+#define CAL_CSI2_TIMING_FORCE_RX_MODE_IO1_MASK		BIT(15)
+
+#define CAL_CSI2_VC_IRQ_FS_IRQ_0_MASK			BIT(0)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_0_MASK			BIT(1)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_0_MASK			BIT(2)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_0_MASK			BIT(3)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_0_MASK			BIT(4)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_0_MASK	BIT(5)
+#define CAL_CSI2_VC_IRQ_FS_IRQ_1_MASK			BIT(8)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_1_MASK			BIT(9)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_1_MASK			BIT(10)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_1_MASK			BIT(11)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_1_MASK			BIT(12)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_1_MASK	BIT(13)
+#define CAL_CSI2_VC_IRQ_FS_IRQ_2_MASK			BIT(16)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_2_MASK			BIT(17)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_2_MASK			BIT(18)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_2_MASK			BIT(19)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_2_MASK			BIT(20)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_2_MASK	BIT(21)
+#define CAL_CSI2_VC_IRQ_FS_IRQ_3_MASK			BIT(24)
+#define CAL_CSI2_VC_IRQ_FE_IRQ_3_MASK			BIT(25)
+#define CAL_CSI2_VC_IRQ_LS_IRQ_3_MASK			BIT(26)
+#define CAL_CSI2_VC_IRQ_LE_IRQ_3_MASK			BIT(27)
+#define CAL_CSI2_VC_IRQ_CS_IRQ_3_MASK			BIT(28)
+#define CAL_CSI2_VC_IRQ_ECC_CORRECTION0_IRQ_3_MASK	BIT(29)
 
 #define CAL_CSI2_CTX_DT_MASK		GENMASK(5, 0)
 #define CAL_CSI2_CTX_VC_MASK		GENMASK(7, 6)
 #define CAL_CSI2_CTX_CPORT_MASK		GENMASK(12, 8)
-#define CAL_CSI2_CTX_ATT_MASK		BIT_MASK(13)
+#define CAL_CSI2_CTX_ATT_MASK		BIT(13)
 #define CAL_CSI2_CTX_ATT_PIX			0
 #define CAL_CSI2_CTX_ATT			1
-#define CAL_CSI2_CTX_PACK_MODE_MASK	BIT_MASK(14)
+#define CAL_CSI2_CTX_PACK_MODE_MASK	BIT(14)
 #define CAL_CSI2_CTX_PACK_MODE_LINE		0
 #define CAL_CSI2_CTX_PACK_MODE_FRAME		1
 #define CAL_CSI2_CTX_LINES_MASK		GENMASK(29, 16)
@@ -445,7 +470,7 @@
 
 #define CAL_CSI2_PHY_REG0_THS_SETTLE_MASK	GENMASK(7, 0)
 #define CAL_CSI2_PHY_REG0_THS_TERM_MASK		GENMASK(15, 8)
-#define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_MASK	BIT_MASK(24)
+#define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_MASK	BIT(24)
 #define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_DISABLE		1
 #define CAL_CSI2_PHY_REG0_HSCLOCKCONFIG_ENABLE		0
 
@@ -453,24 +478,26 @@
 #define CAL_CSI2_PHY_REG1_CTRLCLK_DIV_FACTOR_MASK		GENMASK(9, 8)
 #define CAL_CSI2_PHY_REG1_DPHY_HS_SYNC_PATTERN_MASK		GENMASK(17, 10)
 #define CAL_CSI2_PHY_REG1_TCLK_TERM_MASK			GENMASK(24, 18)
-#define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_MASK	BIT_MASK(25)
+#define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_MASK	BIT(25)
 #define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_ERROR		1
 #define CAL_CSI2_PHY_REG1_CLOCK_MISS_DETECTOR_STATUS_SUCCESS		0
 #define CAL_CSI2_PHY_REG1_RESET_DONE_STATUS_MASK		GENMASK(29, 28)
 
+#define CAL_CSI2_PHY_REG10_I933_LDO_DISABLE_MASK		BIT(6)
+
 #define CAL_CSI2_PHY_REG2_CCP2_SYNC_PATTERN_MASK		GENMASK(23, 0)
 #define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC3_MASK		GENMASK(25, 24)
 #define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC2_MASK		GENMASK(27, 26)
 #define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC1_MASK		GENMASK(29, 28)
 #define CAL_CSI2_PHY_REG2_TRIGGER_CMD_RXTRIGESC0_MASK		GENMASK(31, 30)
 
-#define CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK			BIT_MASK(0)
+#define CM_CAMERRX_CTRL_CSI1_CTRLCLKEN_MASK			BIT(0)
 #define CM_CAMERRX_CTRL_CSI1_CAMMODE_MASK			GENMASK(2, 1)
 #define CM_CAMERRX_CTRL_CSI1_LANEENABLE_MASK			GENMASK(4, 3)
-#define CM_CAMERRX_CTRL_CSI1_MODE_MASK				BIT_MASK(5)
-#define CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK			BIT_MASK(10)
+#define CM_CAMERRX_CTRL_CSI1_MODE_MASK				BIT(5)
+#define CM_CAMERRX_CTRL_CSI0_CTRLCLKEN_MASK			BIT(10)
 #define CM_CAMERRX_CTRL_CSI0_CAMMODE_MASK			GENMASK(12, 11)
 #define CM_CAMERRX_CTRL_CSI0_LANEENABLE_MASK			GENMASK(16, 13)
-#define CM_CAMERRX_CTRL_CSI0_MODE_MASK				BIT_MASK(17)
+#define CM_CAMERRX_CTRL_CSI0_MODE_MASK				BIT(17)
 
 #endif
diff --git a/drivers/media/platform/ti-vpe/csc.c b/drivers/media/platform/ti-vpe/csc.c
index 834114a4eebe..f4e0cf72d1cf 100644
--- a/drivers/media/platform/ti-vpe/csc.c
+++ b/drivers/media/platform/ti-vpe/csc.c
@@ -149,36 +149,28 @@ void csc_set_coeff(struct csc_data *csc, u32 *csc_reg0,
 	enum v4l2_quantization src_quantization, dst_quantization;
 	u32 src_pixelformat, dst_pixelformat;
 
-	switch (src_fmt->type) {
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		pix = &src_fmt->fmt.pix;
-		src_pixelformat = pix->pixelformat;
-		src_ycbcr_enc = pix->ycbcr_enc;
-		src_quantization = pix->quantization;
-		break;
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-	default:
+	if (V4L2_TYPE_IS_MULTIPLANAR(src_fmt->type)) {
 		mp = &src_fmt->fmt.pix_mp;
 		src_pixelformat = mp->pixelformat;
 		src_ycbcr_enc = mp->ycbcr_enc;
 		src_quantization = mp->quantization;
-		break;
+	} else {
+		pix = &src_fmt->fmt.pix;
+		src_pixelformat = pix->pixelformat;
+		src_ycbcr_enc = pix->ycbcr_enc;
+		src_quantization = pix->quantization;
 	}
 
-	switch (dst_fmt->type) {
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
-		pix = &dst_fmt->fmt.pix;
-		dst_pixelformat = pix->pixelformat;
-		dst_ycbcr_enc = pix->ycbcr_enc;
-		dst_quantization = pix->quantization;
-		break;
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
-	default:
+	if (V4L2_TYPE_IS_MULTIPLANAR(dst_fmt->type)) {
 		mp = &dst_fmt->fmt.pix_mp;
 		dst_pixelformat = mp->pixelformat;
 		dst_ycbcr_enc = mp->ycbcr_enc;
 		dst_quantization = mp->quantization;
-		break;
+	} else {
+		pix = &dst_fmt->fmt.pix;
+		dst_pixelformat = pix->pixelformat;
+		dst_ycbcr_enc = pix->ycbcr_enc;
+		dst_quantization = pix->quantization;
 	}
 
 	src_finfo = v4l2_format_info(src_pixelformat);
diff --git a/drivers/media/platform/vimc/vimc-scaler.c b/drivers/media/platform/vimc/vimc-scaler.c
index 2f88a7d9d67b..e2e551bc3ded 100644
--- a/drivers/media/platform/vimc/vimc-scaler.c
+++ b/drivers/media/platform/vimc/vimc-scaler.c
@@ -8,6 +8,7 @@
 #include <linux/moduleparam.h>
 #include <linux/vmalloc.h>
 #include <linux/v4l2-mediabus.h>
+#include <media/v4l2-rect.h>
 #include <media/v4l2-subdev.h>
 
 #include "vimc-common.h"
@@ -18,6 +19,9 @@ MODULE_PARM_DESC(sca_mult, " the image size multiplier");
 
 #define MAX_ZOOM	8
 
+#define VIMC_SCA_FMT_WIDTH_DEFAULT  640
+#define VIMC_SCA_FMT_HEIGHT_DEFAULT 480
+
 struct vimc_sca_device {
 	struct vimc_ent_device ved;
 	struct v4l2_subdev sd;
@@ -25,6 +29,7 @@ struct vimc_sca_device {
 	 * with the width and hight multiplied by mult
 	 */
 	struct v4l2_mbus_framefmt sink_fmt;
+	struct v4l2_rect crop_rect;
 	/* Values calculated when the stream starts */
 	u8 *src_frame;
 	unsigned int src_line_size;
@@ -33,22 +38,64 @@ struct vimc_sca_device {
 };
 
 static const struct v4l2_mbus_framefmt sink_fmt_default = {
-	.width = 640,
-	.height = 480,
+	.width = VIMC_SCA_FMT_WIDTH_DEFAULT,
+	.height = VIMC_SCA_FMT_HEIGHT_DEFAULT,
 	.code = MEDIA_BUS_FMT_RGB888_1X24,
 	.field = V4L2_FIELD_NONE,
 	.colorspace = V4L2_COLORSPACE_DEFAULT,
 };
 
+static const struct v4l2_rect crop_rect_default = {
+	.width = VIMC_SCA_FMT_WIDTH_DEFAULT,
+	.height = VIMC_SCA_FMT_HEIGHT_DEFAULT,
+	.top = 0,
+	.left = 0,
+};
+
+static const struct v4l2_rect crop_rect_min = {
+	.width = VIMC_FRAME_MIN_WIDTH,
+	.height = VIMC_FRAME_MIN_HEIGHT,
+	.top = 0,
+	.left = 0,
+};
+
+static struct v4l2_rect
+vimc_sca_get_crop_bound_sink(const struct v4l2_mbus_framefmt *sink_fmt)
+{
+	/* Get the crop bounds to clamp the crop rectangle correctly */
+	struct v4l2_rect r = {
+		.left = 0,
+		.top = 0,
+		.width = sink_fmt->width,
+		.height = sink_fmt->height,
+	};
+	return r;
+}
+
+static void vimc_sca_adjust_sink_crop(struct v4l2_rect *r,
+				      const struct v4l2_mbus_framefmt *sink_fmt)
+{
+	const struct v4l2_rect sink_rect =
+		vimc_sca_get_crop_bound_sink(sink_fmt);
+
+	/* Disallow rectangles smaller than the minimal one. */
+	v4l2_rect_set_min_size(r, &crop_rect_min);
+	v4l2_rect_map_inside(r, &sink_rect);
+}
+
 static int vimc_sca_init_cfg(struct v4l2_subdev *sd,
 			     struct v4l2_subdev_pad_config *cfg)
 {
 	struct v4l2_mbus_framefmt *mf;
+	struct v4l2_rect *r;
 	unsigned int i;
 
 	mf = v4l2_subdev_get_try_format(sd, cfg, 0);
 	*mf = sink_fmt_default;
 
+	r = v4l2_subdev_get_try_crop(sd, cfg, 0);
+	*r = crop_rect_default;
+
 	for (i = 1; i < sd->entity.num_pads; i++) {
 		mf = v4l2_subdev_get_try_format(sd, cfg, i);
 		*mf = sink_fmt_default;
@@ -107,16 +154,21 @@ static int vimc_sca_get_fmt(struct v4l2_subdev *sd,
 			    struct v4l2_subdev_format *format)
 {
 	struct vimc_sca_device *vsca = v4l2_get_subdevdata(sd);
+	struct v4l2_rect *crop_rect;
 
 	/* Get the current sink format */
-	format->format = (format->which == V4L2_SUBDEV_FORMAT_TRY) ?
-			 *v4l2_subdev_get_try_format(sd, cfg, 0) :
-			 vsca->sink_fmt;
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		format->format = *v4l2_subdev_get_try_format(sd, cfg, 0);
+		crop_rect = v4l2_subdev_get_try_crop(sd, cfg, 0);
+	} else {
+		format->format = vsca->sink_fmt;
+		crop_rect = &vsca->crop_rect;
+	}
 
 	/* Scale the frame size for the source pad */
 	if (VIMC_IS_SRC(format->pad)) {
-		format->format.width = vsca->sink_fmt.width * sca_mult;
-		format->format.height = vsca->sink_fmt.height * sca_mult;
+		format->format.width = crop_rect->width * sca_mult;
+		format->format.height = crop_rect->height * sca_mult;
 	}
 
 	return 0;
@@ -148,6 +200,7 @@ static int vimc_sca_set_fmt(struct v4l2_subdev *sd,
 {
 	struct vimc_sca_device *vsca = v4l2_get_subdevdata(sd);
 	struct v4l2_mbus_framefmt *sink_fmt;
+	struct v4l2_rect *crop_rect;
 
 	if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE) {
 		/* Do not change the format while stream is on */
@@ -155,8 +208,10 @@ static int vimc_sca_set_fmt(struct v4l2_subdev *sd,
 			return -EBUSY;
 
 		sink_fmt = &vsca->sink_fmt;
+		crop_rect = &vsca->crop_rect;
 	} else {
 		sink_fmt = v4l2_subdev_get_try_format(sd, cfg, 0);
+		crop_rect = v4l2_subdev_get_try_crop(sd, cfg, 0);
 	}
 
 	/*
@@ -165,8 +220,8 @@ static int vimc_sca_set_fmt(struct v4l2_subdev *sd,
 	 */
 	if (VIMC_IS_SRC(fmt->pad)) {
 		fmt->format = *sink_fmt;
-		fmt->format.width = sink_fmt->width * sca_mult;
-		fmt->format.height = sink_fmt->height * sca_mult;
+		fmt->format.width = crop_rect->width * sca_mult;
+		fmt->format.height = crop_rect->height * sca_mult;
 	} else {
 		/* Set the new format in the sink pad */
 		vimc_sca_adjust_sink_fmt(&fmt->format);
@@ -184,6 +239,78 @@ static int vimc_sca_set_fmt(struct v4l2_subdev *sd,
 			fmt->format.xfer_func, fmt->format.ycbcr_enc);
 
 		*sink_fmt = fmt->format;
+
+		/* Do the crop, but respect the current bounds */
+		vimc_sca_adjust_sink_crop(crop_rect, sink_fmt);
+	}
+
+	return 0;
+}
+
+static int vimc_sca_get_selection(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_selection *sel)
+{
+	struct vimc_sca_device *vsca = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *sink_fmt;
+	struct v4l2_rect *crop_rect;
+
+	if (VIMC_IS_SRC(sel->pad))
+		return -EINVAL;
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_ACTIVE) {
+		sink_fmt = &vsca->sink_fmt;
+		crop_rect = &vsca->crop_rect;
+	} else {
+		sink_fmt = v4l2_subdev_get_try_format(sd, cfg, 0);
+		crop_rect = v4l2_subdev_get_try_crop(sd, cfg, 0);
+	}
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP:
+		sel->r = *crop_rect;
+		break;
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		sel->r = vimc_sca_get_crop_bound_sink(sink_fmt);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vimc_sca_set_selection(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_selection *sel)
+{
+	struct vimc_sca_device *vsca = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *sink_fmt;
+	struct v4l2_rect *crop_rect;
+
+	if (VIMC_IS_SRC(sel->pad))
+		return -EINVAL;
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_ACTIVE) {
+		/* Do not change the format while stream is on */
+		if (vsca->src_frame)
+			return -EBUSY;
+
+		crop_rect = &vsca->crop_rect;
+		sink_fmt = &vsca->sink_fmt;
+	} else {
+		crop_rect = v4l2_subdev_get_try_crop(sd, cfg, 0);
+		sink_fmt = v4l2_subdev_get_try_format(sd, cfg, 0);
+	}
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP:
+		/* Do the crop, but respect the current bounds */
+		vimc_sca_adjust_sink_crop(&sel->r, sink_fmt);
+		*crop_rect = sel->r;
+		break;
+	default:
+		return -EINVAL;
 	}
 
 	return 0;
@@ -195,6 +322,8 @@ static const struct v4l2_subdev_pad_ops vimc_sca_pad_ops = {
 	.enum_frame_size	= vimc_sca_enum_frame_size,
 	.get_fmt		= vimc_sca_get_fmt,
 	.set_fmt		= vimc_sca_set_fmt,
+	.get_selection		= vimc_sca_get_selection,
+	.set_selection		= vimc_sca_set_selection,
 };
 
 static int vimc_sca_s_stream(struct v4l2_subdev *sd, int enable)
@@ -213,11 +342,11 @@ static int vimc_sca_s_stream(struct v4l2_subdev *sd, int enable)
 		vsca->bpp = vpix->bpp;
 
 		/* Calculate the width in bytes of the src frame */
-		vsca->src_line_size = vsca->sink_fmt.width *
+		vsca->src_line_size = vsca->crop_rect.width *
 				      sca_mult * vsca->bpp;
 
 		/* Calculate the frame size of the source pad */
-		frame_size = vsca->src_line_size * vsca->sink_fmt.height *
+		frame_size = vsca->src_line_size * vsca->crop_rect.height *
 			     sca_mult;
 
 		/* Allocate the frame buffer. Use vmalloc to be able to
@@ -259,9 +388,10 @@ static void vimc_sca_fill_pix(u8 *const ptr,
 }
 
 static void vimc_sca_scale_pix(const struct vimc_sca_device *const vsca,
-			       const unsigned int lin, const unsigned int col,
+			       unsigned int lin, unsigned int col,
 			       const u8 *const sink_frame)
 {
+	const struct v4l2_rect crop_rect = vsca->crop_rect;
 	unsigned int i, j, index;
 	const u8 *pixel;
 
@@ -278,8 +408,10 @@ static void vimc_sca_scale_pix(const struct vimc_sca_device *const vsca,
 	/* point to the place we are going to put the first pixel
 	 * in the scaled src frame
 	 */
+	lin -= crop_rect.top;
+	col -= crop_rect.left;
 	index = VIMC_FRAME_INDEX(lin * sca_mult, col * sca_mult,
-				 vsca->sink_fmt.width * sca_mult, vsca->bpp);
+				 crop_rect.width * sca_mult, vsca->bpp);
 
 	dev_dbg(vsca->ved.dev, "sca: %s: scale_pix src pos %dx%d, index %d\n",
 		vsca->sd.name, lin * sca_mult, col * sca_mult, index);
@@ -307,12 +439,13 @@ static void vimc_sca_scale_pix(const struct vimc_sca_device *const vsca,
 static void vimc_sca_fill_src_frame(const struct vimc_sca_device *const vsca,
 				    const u8 *const sink_frame)
 {
+	const struct v4l2_rect r = vsca->crop_rect;
 	unsigned int i, j;
 
 	/* Scale each pixel from the original sink frame */
 	/* TODO: implement scale down, only scale up is supported for now */
-	for (i = 0; i < vsca->sink_fmt.height; i++)
-		for (j = 0; j < vsca->sink_fmt.width; j++)
+	for (i = r.top; i < r.top + r.height; i++)
+		for (j = r.left; j < r.left + r.width; j++)
 			vimc_sca_scale_pix(vsca, i, j, sink_frame);
 }
 
@@ -384,5 +517,8 @@ struct vimc_ent_device *vimc_sca_add(struct vimc_device *vimc,
 	/* Initialize the frame format */
 	vsca->sink_fmt = sink_fmt_default;
 
+	/* Initialize the crop selection */
+	vsca->crop_rect = crop_rect_default;
+
 	return &vsca->ved;
 }
diff --git a/drivers/media/platform/vivid/Makefile b/drivers/media/platform/vivid/Makefile
index e8a50c506dc9..b12ad0152a3e 100644
--- a/drivers/media/platform/vivid/Makefile
+++ b/drivers/media/platform/vivid/Makefile
@@ -3,7 +3,8 @@ vivid-objs := vivid-core.o vivid-ctrls.o vivid-vid-common.o vivid-vbi-gen.o \
 		vivid-vid-cap.o vivid-vid-out.o vivid-kthread-cap.o vivid-kthread-out.o \
 		vivid-radio-rx.o vivid-radio-tx.o vivid-radio-common.o \
 		vivid-rds-gen.o vivid-sdr-cap.o vivid-vbi-cap.o vivid-vbi-out.o \
-		vivid-osd.o vivid-meta-cap.o vivid-meta-out.o
+		vivid-osd.o vivid-meta-cap.o vivid-meta-out.o \
+		vivid-kthread-touch.o vivid-touch-cap.o
 ifeq ($(CONFIG_VIDEO_VIVID_CEC),y)
   vivid-objs += vivid-cec.o
 endif
diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c
index c184f9b0be69..15091cbf6de7 100644
--- a/drivers/media/platform/vivid/vivid-core.c
+++ b/drivers/media/platform/vivid/vivid-core.c
@@ -39,6 +39,7 @@
 #include "vivid-ctrls.h"
 #include "vivid-meta-cap.h"
 #include "vivid-meta-out.h"
+#include "vivid-touch-cap.h"
 
 #define VIVID_MODULE_NAME "vivid"
 
@@ -89,6 +90,10 @@ static int meta_out_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
 module_param_array(meta_out_nr, int, NULL, 0444);
 MODULE_PARM_DESC(meta_out_nr, " videoX start number, -1 is autodetect");
 
+static int touch_cap_nr[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
+module_param_array(touch_cap_nr, int, NULL, 0444);
+MODULE_PARM_DESC(touch_cap_nr, " v4l-touchX start number, -1 is autodetect");
+
 static int ccs_cap_mode[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = -1 };
 module_param_array(ccs_cap_mode, int, NULL, 0444);
 MODULE_PARM_DESC(ccs_cap_mode, " capture crop/compose/scale mode:\n"
@@ -110,10 +115,10 @@ MODULE_PARM_DESC(multiplanar, " 1 (default) creates a single planar device, 2 cr
  * vbi-out + vid-out + meta-cap
  */
 static unsigned int node_types[VIVID_MAX_DEVS] = {
-	[0 ... (VIVID_MAX_DEVS - 1)] = 0x61d3d
+	[0 ... (VIVID_MAX_DEVS - 1)] = 0xe1d3d
 };
 module_param_array(node_types, uint, NULL, 0444);
-MODULE_PARM_DESC(node_types, " node types, default is 0x61d3d. Bitmask with the following meaning:\n"
+MODULE_PARM_DESC(node_types, " node types, default is 0xe1d3d. Bitmask with the following meaning:\n"
 			     "\t\t    bit 0: Video Capture node\n"
 			     "\t\t    bit 2-3: VBI Capture node: 0 = none, 1 = raw vbi, 2 = sliced vbi, 3 = both\n"
 			     "\t\t    bit 4: Radio Receiver node\n"
@@ -123,7 +128,8 @@ MODULE_PARM_DESC(node_types, " node types, default is 0x61d3d. Bitmask with the
 			     "\t\t    bit 12: Radio Transmitter node\n"
 			     "\t\t    bit 16: Framebuffer for testing overlays\n"
 			     "\t\t    bit 17: Metadata Capture node\n"
-			     "\t\t    bit 18: Metadata Output node\n");
+			     "\t\t    bit 18: Metadata Output node\n"
+			     "\t\t    bit 19: Touch Capture node\n");
 
 /* Default: 4 inputs */
 static unsigned num_inputs[VIVID_MAX_DEVS] = { [0 ... (VIVID_MAX_DEVS - 1)] = 4 };
@@ -223,7 +229,8 @@ static int vidioc_querycap(struct file *file, void  *priv,
 		dev->vbi_cap_caps | dev->vbi_out_caps |
 		dev->radio_rx_caps | dev->radio_tx_caps |
 		dev->sdr_cap_caps | dev->meta_cap_caps |
-		dev->meta_out_caps | V4L2_CAP_DEVICE_CAPS;
+		dev->meta_out_caps | dev->touch_cap_caps |
+		V4L2_CAP_DEVICE_CAPS;
 	return 0;
 }
 
@@ -377,6 +384,8 @@ static int vidioc_g_parm(struct file *file, void *fh,
 {
 	struct video_device *vdev = video_devdata(file);
 
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_parm_tch(file, fh, parm);
 	if (vdev->vfl_dir == VFL_DIR_RX)
 		return vivid_vid_cap_g_parm(file, fh, parm);
 	return vivid_vid_out_g_parm(file, fh, parm);
@@ -432,6 +441,104 @@ static __poll_t vivid_radio_poll(struct file *file, struct poll_table_struct *wa
 	return vivid_radio_tx_poll(file, wait);
 }
 
+static int vivid_enum_input(struct file *file, void *priv,
+			    struct v4l2_input *inp)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_enum_input_tch(file, priv, inp);
+	return vidioc_enum_input(file, priv, inp);
+}
+
+static int vivid_g_input(struct file *file, void *priv, unsigned int *i)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_input_tch(file, priv, i);
+	return vidioc_g_input(file, priv, i);
+}
+
+static int vivid_s_input(struct file *file, void *priv, unsigned int i)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_s_input_tch(file, priv, i);
+	return vidioc_s_input(file, priv, i);
+}
+
+static int vivid_enum_fmt_cap(struct file *file, void  *priv,
+			      struct v4l2_fmtdesc *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_enum_fmt_tch(file, priv, f);
+	return vivid_enum_fmt_vid(file, priv, f);
+}
+
+static int vivid_g_fmt_cap(struct file *file, void *priv,
+			   struct v4l2_format *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_fmt_tch(file, priv, f);
+	return vidioc_g_fmt_vid_cap(file, priv, f);
+}
+
+static int vivid_try_fmt_cap(struct file *file, void *priv,
+			     struct v4l2_format *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_fmt_tch(file, priv, f);
+	return vidioc_try_fmt_vid_cap(file, priv, f);
+}
+
+static int vivid_s_fmt_cap(struct file *file, void *priv,
+			   struct v4l2_format *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_fmt_tch(file, priv, f);
+	return vidioc_s_fmt_vid_cap(file, priv, f);
+}
+
+static int vivid_g_fmt_cap_mplane(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_fmt_tch_mplane(file, priv, f);
+	return vidioc_g_fmt_vid_cap_mplane(file, priv, f);
+}
+
+static int vivid_try_fmt_cap_mplane(struct file *file, void *priv,
+				    struct v4l2_format *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_fmt_tch_mplane(file, priv, f);
+	return vidioc_try_fmt_vid_cap_mplane(file, priv, f);
+}
+
+static int vivid_s_fmt_cap_mplane(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	if (vdev->vfl_type == VFL_TYPE_TOUCH)
+		return vivid_g_fmt_tch_mplane(file, priv, f);
+	return vidioc_s_fmt_vid_cap_mplane(file, priv, f);
+}
+
 static bool vivid_is_in_use(struct video_device *vdev)
 {
 	unsigned long flags;
@@ -453,7 +560,8 @@ static bool vivid_is_last_user(struct vivid_dev *dev)
 			vivid_is_in_use(&dev->radio_rx_dev) +
 			vivid_is_in_use(&dev->radio_tx_dev) +
 			vivid_is_in_use(&dev->meta_cap_dev) +
-			vivid_is_in_use(&dev->meta_out_dev);
+			vivid_is_in_use(&dev->meta_out_dev) +
+			vivid_is_in_use(&dev->touch_cap_dev);
 
 	return uses == 1;
 }
@@ -481,6 +589,7 @@ static int vivid_fop_release(struct file *file)
 		set_bit(V4L2_FL_REGISTERED, &dev->radio_tx_dev.flags);
 		set_bit(V4L2_FL_REGISTERED, &dev->meta_cap_dev.flags);
 		set_bit(V4L2_FL_REGISTERED, &dev->meta_out_dev.flags);
+		set_bit(V4L2_FL_REGISTERED, &dev->touch_cap_dev.flags);
 	}
 	mutex_unlock(&dev->mutex);
 	if (file->private_data == dev->overlay_cap_owner)
@@ -522,13 +631,13 @@ static const struct v4l2_file_operations vivid_radio_fops = {
 static const struct v4l2_ioctl_ops vivid_ioctl_ops = {
 	.vidioc_querycap		= vidioc_querycap,
 
-	.vidioc_enum_fmt_vid_cap	= vivid_enum_fmt_vid,
-	.vidioc_g_fmt_vid_cap		= vidioc_g_fmt_vid_cap,
-	.vidioc_try_fmt_vid_cap		= vidioc_try_fmt_vid_cap,
-	.vidioc_s_fmt_vid_cap		= vidioc_s_fmt_vid_cap,
-	.vidioc_g_fmt_vid_cap_mplane	= vidioc_g_fmt_vid_cap_mplane,
-	.vidioc_try_fmt_vid_cap_mplane	= vidioc_try_fmt_vid_cap_mplane,
-	.vidioc_s_fmt_vid_cap_mplane	= vidioc_s_fmt_vid_cap_mplane,
+	.vidioc_enum_fmt_vid_cap	= vivid_enum_fmt_cap,
+	.vidioc_g_fmt_vid_cap		= vivid_g_fmt_cap,
+	.vidioc_try_fmt_vid_cap		= vivid_try_fmt_cap,
+	.vidioc_s_fmt_vid_cap		= vivid_s_fmt_cap,
+	.vidioc_g_fmt_vid_cap_mplane	= vivid_g_fmt_cap_mplane,
+	.vidioc_try_fmt_vid_cap_mplane	= vivid_try_fmt_cap_mplane,
+	.vidioc_s_fmt_vid_cap_mplane	= vivid_s_fmt_cap_mplane,
 
 	.vidioc_enum_fmt_vid_out	= vivid_enum_fmt_vid,
 	.vidioc_g_fmt_vid_out		= vidioc_g_fmt_vid_out,
@@ -590,9 +699,9 @@ static const struct v4l2_ioctl_ops vivid_ioctl_ops = {
 	.vidioc_streamon		= vb2_ioctl_streamon,
 	.vidioc_streamoff		= vb2_ioctl_streamoff,
 
-	.vidioc_enum_input		= vidioc_enum_input,
-	.vidioc_g_input			= vidioc_g_input,
-	.vidioc_s_input			= vidioc_s_input,
+	.vidioc_enum_input		= vivid_enum_input,
+	.vidioc_g_input			= vivid_g_input,
+	.vidioc_s_input			= vivid_s_input,
 	.vidioc_s_audio			= vidioc_s_audio,
 	.vidioc_g_audio			= vidioc_g_audio,
 	.vidioc_enumaudio		= vidioc_enumaudio,
@@ -921,6 +1030,9 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 			dev->has_scaler_out ? 'Y' : 'N');
 	}
 
+	/* do we create a touch capture device */
+	dev->has_touch_cap = node_type & 0x80000;
+
 	/* end detecting feature set */
 
 	if (dev->has_vid_cap) {
@@ -994,6 +1106,13 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 		if (dev->has_audio_outputs)
 			dev->meta_out_caps |= V4L2_CAP_AUDIO;
 	}
+	/* set up the capabilities of the touch capture device */
+	if (dev->has_touch_cap) {
+		dev->touch_cap_caps = V4L2_CAP_TOUCH | V4L2_CAP_STREAMING |
+				      V4L2_CAP_READWRITE;
+		dev->touch_cap_caps |= dev->multiplanar ?
+			V4L2_CAP_VIDEO_CAPTURE_MPLANE : V4L2_CAP_VIDEO_CAPTURE;
+	}
 
 	ret = -ENOMEM;
 	/* initialize the test pattern generator */
@@ -1129,6 +1248,9 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	v4l2_disable_ioctl(&dev->vbi_out_dev, VIDIOC_G_FREQUENCY);
 	v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_S_FREQUENCY);
 	v4l2_disable_ioctl(&dev->meta_out_dev, VIDIOC_G_FREQUENCY);
+	v4l2_disable_ioctl(&dev->touch_cap_dev, VIDIOC_S_PARM);
+	v4l2_disable_ioctl(&dev->touch_cap_dev, VIDIOC_ENUM_FRAMESIZES);
+	v4l2_disable_ioctl(&dev->touch_cap_dev, VIDIOC_ENUM_FRAMEINTERVALS);
 
 	/* configure internal data */
 	dev->fmt_cap = &vivid_formats[0];
@@ -1201,6 +1323,11 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	dev->fb_cap.fmt.bytesperline = dev->src_rect.width * tpg_g_twopixelsize(&dev->tpg, 0) / 2;
 	dev->fb_cap.fmt.sizeimage = dev->src_rect.height * dev->fb_cap.fmt.bytesperline;
 
+	/* update touch configuration */
+	dev->timeperframe_tch_cap.numerator = 1;
+	dev->timeperframe_tch_cap.denominator = 10;
+	vivid_set_touch(dev, 0);
+
 	/* initialize locks */
 	spin_lock_init(&dev->slock);
 	mutex_init(&dev->mutex);
@@ -1213,6 +1340,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	INIT_LIST_HEAD(&dev->sdr_cap_active);
 	INIT_LIST_HEAD(&dev->meta_cap_active);
 	INIT_LIST_HEAD(&dev->meta_out_active);
+	INIT_LIST_HEAD(&dev->touch_cap_active);
 
 	INIT_LIST_HEAD(&dev->cec_work_list);
 	spin_lock_init(&dev->cec_slock);
@@ -1294,6 +1422,15 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 			goto unreg_dev;
 	}
 
+	if (dev->has_touch_cap) {
+		/* initialize touch_cap queue */
+		ret = vivid_create_queue(dev, &dev->vb_touch_cap_q,
+					 V4L2_BUF_TYPE_VIDEO_CAPTURE, 1,
+					 &vivid_touch_cap_qops);
+		if (ret)
+			goto unreg_dev;
+	}
+
 	if (dev->has_fb) {
 		/* Create framebuffer for testing capture/output overlay */
 		ret = vivid_fb_init(dev);
@@ -1345,6 +1482,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_sdr_cap);
 	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_meta_cap);
 	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_meta_out);
+	v4l2_ctrl_handler_setup(&dev->ctrl_hdl_touch_cap);
 
 	/* finally start creating the device nodes */
 	if (dev->has_vid_cap) {
@@ -1635,6 +1773,35 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 			  video_device_node_name(vfd));
 	}
 
+	if (dev->has_touch_cap) {
+		vfd = &dev->touch_cap_dev;
+		snprintf(vfd->name, sizeof(vfd->name),
+			 "vivid-%03d-touch-cap", inst);
+		vfd->fops = &vivid_fops;
+		vfd->ioctl_ops = &vivid_ioctl_ops;
+		vfd->device_caps = dev->touch_cap_caps;
+		vfd->release = video_device_release_empty;
+		vfd->v4l2_dev = &dev->v4l2_dev;
+		vfd->queue = &dev->vb_touch_cap_q;
+		vfd->tvnorms = tvnorms_cap;
+		vfd->lock = &dev->mutex;
+		video_set_drvdata(vfd, dev);
+#ifdef CONFIG_MEDIA_CONTROLLER
+		dev->touch_cap_pad.flags = MEDIA_PAD_FL_SINK;
+		ret = media_entity_pads_init(&vfd->entity, 1,
+					     &dev->touch_cap_pad);
+		if (ret)
+			goto unreg_dev;
+#endif
+		ret = video_register_device(vfd, VFL_TYPE_TOUCH,
+					    touch_cap_nr[inst]);
+		if (ret < 0)
+			goto unreg_dev;
+		v4l2_info(&dev->v4l2_dev,
+			  "V4L2 touch capture device registered as %s\n",
+			  video_device_node_name(vfd));
+	}
+
 #ifdef CONFIG_MEDIA_CONTROLLER
 	/* Register the media device */
 	ret = media_device_register(&dev->mdev);
@@ -1651,6 +1818,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	return 0;
 
 unreg_dev:
+	video_unregister_device(&dev->touch_cap_dev);
 	video_unregister_device(&dev->meta_out_dev);
 	video_unregister_device(&dev->meta_cap_dev);
 	video_unregister_device(&dev->radio_tx_dev);
@@ -1778,6 +1946,11 @@ static int vivid_remove(struct platform_device *pdev)
 				  video_device_node_name(&dev->meta_out_dev));
 			video_unregister_device(&dev->meta_out_dev);
 		}
+		if (dev->has_touch_cap) {
+			v4l2_info(&dev->v4l2_dev, "unregistering %s\n",
+				  video_device_node_name(&dev->touch_cap_dev));
+			video_unregister_device(&dev->touch_cap_dev);
+		}
 		cec_unregister_adapter(dev->cec_rx_adap);
 		for (j = 0; j < MAX_OUTPUTS; j++)
 			cec_unregister_adapter(dev->cec_tx_adap[j]);
diff --git a/drivers/media/platform/vivid/vivid-core.h b/drivers/media/platform/vivid/vivid-core.h
index 59192b67231c..99e69b8f770f 100644
--- a/drivers/media/platform/vivid/vivid-core.h
+++ b/drivers/media/platform/vivid/vivid-core.h
@@ -133,6 +133,7 @@ struct vivid_dev {
 	struct media_pad		sdr_cap_pad;
 	struct media_pad		meta_cap_pad;
 	struct media_pad		meta_out_pad;
+	struct media_pad		touch_cap_pad;
 #endif
 	struct v4l2_ctrl_handler	ctrl_hdl_user_gen;
 	struct v4l2_ctrl_handler	ctrl_hdl_user_vid;
@@ -159,6 +160,8 @@ struct vivid_dev {
 	struct v4l2_ctrl_handler	ctrl_hdl_meta_cap;
 	struct video_device		meta_out_dev;
 	struct v4l2_ctrl_handler	ctrl_hdl_meta_out;
+	struct video_device		touch_cap_dev;
+	struct v4l2_ctrl_handler	ctrl_hdl_touch_cap;
 
 	spinlock_t			slock;
 	struct mutex			mutex;
@@ -173,6 +176,7 @@ struct vivid_dev {
 	u32				radio_tx_caps;
 	u32				meta_cap_caps;
 	u32				meta_out_caps;
+	u32				touch_cap_caps;
 
 	/* supported features */
 	bool				multiplanar;
@@ -201,6 +205,7 @@ struct vivid_dev {
 	bool				has_meta_cap;
 	bool				has_meta_out;
 	bool				has_tv_tuner;
+	bool				has_touch_cap;
 
 	bool				can_loop_video;
 
@@ -404,6 +409,8 @@ struct vivid_dev {
 	struct list_head		vbi_cap_active;
 	struct vb2_queue		vb_meta_cap_q;
 	struct list_head		meta_cap_active;
+	struct vb2_queue		vb_touch_cap_q;
+	struct list_head		touch_cap_active;
 
 	/* thread for generating video capture stream */
 	struct task_struct		*kthread_vid_cap;
@@ -425,6 +432,19 @@ struct vivid_dev {
 	u32				meta_cap_seq_count;
 	bool				meta_cap_streaming;
 
+	/* Touch capture */
+	struct task_struct		*kthread_touch_cap;
+	unsigned long			jiffies_touch_cap;
+	u64				touch_cap_stream_start;
+	u32				touch_cap_seq_offset;
+	bool				touch_cap_seq_resync;
+	u32				touch_cap_seq_start;
+	u32				touch_cap_seq_count;
+	bool				touch_cap_streaming;
+	struct v4l2_fract		timeperframe_tch_cap;
+	struct v4l2_pix_format		tch_format;
+	int				tch_pat_random;
+
 	/* video output */
 	const struct vivid_fmt		*fmt_out;
 	struct v4l2_fract		timeperframe_vid_out;
diff --git a/drivers/media/platform/vivid/vivid-ctrls.c b/drivers/media/platform/vivid/vivid-ctrls.c
index 68e8124c7973..334130568dcb 100644
--- a/drivers/media/platform/vivid/vivid-ctrls.c
+++ b/drivers/media/platform/vivid/vivid-ctrls.c
@@ -1508,6 +1508,7 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 	struct v4l2_ctrl_handler *hdl_sdr_cap = &dev->ctrl_hdl_sdr_cap;
 	struct v4l2_ctrl_handler *hdl_meta_cap = &dev->ctrl_hdl_meta_cap;
 	struct v4l2_ctrl_handler *hdl_meta_out = &dev->ctrl_hdl_meta_out;
+	struct v4l2_ctrl_handler *hdl_tch_cap = &dev->ctrl_hdl_touch_cap;
 
 	struct v4l2_ctrl_config vivid_ctrl_dv_timings = {
 		.ops = &vivid_vid_cap_ctrl_ops,
@@ -1551,6 +1552,8 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 	v4l2_ctrl_new_custom(hdl_meta_cap, &vivid_ctrl_class, NULL);
 	v4l2_ctrl_handler_init(hdl_meta_out, 2);
 	v4l2_ctrl_new_custom(hdl_meta_out, &vivid_ctrl_class, NULL);
+	v4l2_ctrl_handler_init(hdl_tch_cap, 2);
+	v4l2_ctrl_new_custom(hdl_tch_cap, &vivid_ctrl_class, NULL);
 
 	/* User Controls */
 	dev->volume = v4l2_ctrl_new_std(hdl_user_aud, NULL,
@@ -1904,6 +1907,13 @@ int vivid_create_controls(struct vivid_dev *dev, bool show_ccs_cap,
 			return hdl_meta_out->error;
 		dev->meta_out_dev.ctrl_handler = hdl_meta_out;
 	}
+	if (dev->has_touch_cap) {
+		v4l2_ctrl_add_handler(hdl_tch_cap, hdl_user_gen, NULL, false);
+		v4l2_ctrl_add_handler(hdl_tch_cap, hdl_streaming, NULL, false);
+		if (hdl_tch_cap->error)
+			return hdl_tch_cap->error;
+		dev->touch_cap_dev.ctrl_handler = hdl_tch_cap;
+	}
 	return 0;
 }
 
@@ -1925,4 +1935,5 @@ void vivid_free_controls(struct vivid_dev *dev)
 	v4l2_ctrl_handler_free(&dev->ctrl_hdl_fb);
 	v4l2_ctrl_handler_free(&dev->ctrl_hdl_meta_cap);
 	v4l2_ctrl_handler_free(&dev->ctrl_hdl_meta_out);
+	v4l2_ctrl_handler_free(&dev->ctrl_hdl_touch_cap);
 }
diff --git a/drivers/media/platform/vivid/vivid-kthread-touch.c b/drivers/media/platform/vivid/vivid-kthread-touch.c
new file mode 100644
index 000000000000..674507b5ccb5
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-kthread-touch.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vivid-kthread-touch.c - touch capture thread support functions.
+ *
+ */
+
+#include <linux/freezer.h>
+#include "vivid-core.h"
+#include "vivid-kthread-touch.h"
+#include "vivid-touch-cap.h"
+
+static noinline_for_stack void vivid_thread_tch_cap_tick(struct vivid_dev *dev,
+							 int dropped_bufs)
+{
+	struct vivid_buffer *tch_cap_buf = NULL;
+
+	spin_lock(&dev->slock);
+	if (!list_empty(&dev->touch_cap_active)) {
+		tch_cap_buf = list_entry(dev->touch_cap_active.next,
+					 struct vivid_buffer, list);
+		list_del(&tch_cap_buf->list);
+	}
+
+	spin_unlock(&dev->slock);
+
+	if (tch_cap_buf) {
+		v4l2_ctrl_request_setup(tch_cap_buf->vb.vb2_buf.req_obj.req,
+					&dev->ctrl_hdl_touch_cap);
+
+		vivid_fillbuff_tch(dev, tch_cap_buf);
+		v4l2_ctrl_request_complete(tch_cap_buf->vb.vb2_buf.req_obj.req,
+					   &dev->ctrl_hdl_touch_cap);
+		vb2_buffer_done(&tch_cap_buf->vb.vb2_buf, dev->dqbuf_error ?
+				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+		dprintk(dev, 2, "touch_cap buffer %d done\n",
+			tch_cap_buf->vb.vb2_buf.index);
+
+		tch_cap_buf->vb.vb2_buf.timestamp = ktime_get_ns() + dev->time_wrap_offset;
+	}
+	dev->dqbuf_error = false;
+}
+
+static int vivid_thread_touch_cap(void *data)
+{
+	struct vivid_dev *dev = data;
+	u64 numerators_since_start;
+	u64 buffers_since_start;
+	u64 next_jiffies_since_start;
+	unsigned long jiffies_since_start;
+	unsigned long cur_jiffies;
+	unsigned int wait_jiffies;
+	unsigned int numerator;
+	unsigned int denominator;
+	int dropped_bufs;
+
+	dprintk(dev, 1, "Touch Capture Thread Start\n");
+
+	set_freezable();
+
+	/* Resets frame counters */
+	dev->touch_cap_seq_offset = 0;
+	dev->touch_cap_seq_count = 0;
+	dev->touch_cap_seq_resync = false;
+	dev->jiffies_touch_cap = jiffies;
+
+	for (;;) {
+		try_to_freeze();
+		if (kthread_should_stop())
+			break;
+
+		if (!mutex_trylock(&dev->mutex)) {
+			schedule_timeout_uninterruptible(1);
+			continue;
+		}
+		cur_jiffies = jiffies;
+		if (dev->touch_cap_seq_resync) {
+			dev->jiffies_touch_cap = cur_jiffies;
+			dev->touch_cap_seq_offset = dev->touch_cap_seq_count + 1;
+			dev->touch_cap_seq_count = 0;
+			dev->cap_seq_resync = false;
+		}
+		denominator = dev->timeperframe_tch_cap.denominator;
+		numerator = dev->timeperframe_tch_cap.numerator;
+
+		/* Calculate the number of jiffies since we started streaming */
+		jiffies_since_start = cur_jiffies - dev->jiffies_touch_cap;
+		/* Get the number of buffers streamed since the start */
+		buffers_since_start = (u64)jiffies_since_start * denominator +
+				      (HZ * numerator) / 2;
+		do_div(buffers_since_start, HZ * numerator);
+
+		/*
+		 * After more than 0xf0000000 (rounded down to a multiple of
+		 * 'jiffies-per-day' to ease jiffies_to_msecs calculation)
+		 * jiffies have passed since we started streaming reset the
+		 * counters and keep track of the sequence offset.
+		 */
+		if (jiffies_since_start > JIFFIES_RESYNC) {
+			dev->jiffies_touch_cap = cur_jiffies;
+			dev->cap_seq_offset = buffers_since_start;
+			buffers_since_start = 0;
+		}
+		dropped_bufs = buffers_since_start + dev->touch_cap_seq_offset - dev->touch_cap_seq_count;
+		dev->touch_cap_seq_count = buffers_since_start + dev->touch_cap_seq_offset;
+
+		vivid_thread_tch_cap_tick(dev, dropped_bufs);
+
+		/*
+		 * Calculate the number of 'numerators' streamed
+		 * since we started, including the current buffer.
+		 */
+		numerators_since_start = ++buffers_since_start * numerator;
+
+		/* And the number of jiffies since we started */
+		jiffies_since_start = jiffies - dev->jiffies_touch_cap;
+
+		mutex_unlock(&dev->mutex);
+
+		/*
+		 * Calculate when that next buffer is supposed to start
+		 * in jiffies since we started streaming.
+		 */
+		next_jiffies_since_start = numerators_since_start * HZ +
+					   denominator / 2;
+		do_div(next_jiffies_since_start, denominator);
+		/* If it is in the past, then just schedule asap */
+		if (next_jiffies_since_start < jiffies_since_start)
+			next_jiffies_since_start = jiffies_since_start;
+
+		wait_jiffies = next_jiffies_since_start - jiffies_since_start;
+		schedule_timeout_interruptible(wait_jiffies ? wait_jiffies : 1);
+	}
+	dprintk(dev, 1, "Touch Capture Thread End\n");
+	return 0;
+}
+
+int vivid_start_generating_touch_cap(struct vivid_dev *dev)
+{
+	if (dev->kthread_touch_cap) {
+		dev->touch_cap_streaming = true;
+		return 0;
+	}
+
+	dev->kthread_touch_cap = kthread_run(vivid_thread_touch_cap, dev,
+					     "%s-tch-cap", dev->v4l2_dev.name);
+
+	if (IS_ERR(dev->kthread_touch_cap)) {
+		int err = PTR_ERR(dev->kthread_touch_cap);
+
+		dev->kthread_touch_cap = NULL;
+		v4l2_err(&dev->v4l2_dev, "kernel_thread() failed\n");
+		return err;
+	}
+	dev->touch_cap_streaming = true;
+	dprintk(dev, 1, "returning from %s\n", __func__);
+	return 0;
+}
+
+void vivid_stop_generating_touch_cap(struct vivid_dev *dev)
+{
+	if (!dev->kthread_touch_cap)
+		return;
+
+	dev->touch_cap_streaming = false;
+
+	while (!list_empty(&dev->touch_cap_active)) {
+		struct vivid_buffer *buf;
+
+		buf = list_entry(dev->touch_cap_active.next,
+				 struct vivid_buffer, list);
+		list_del(&buf->list);
+		v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req,
+					   &dev->ctrl_hdl_touch_cap);
+		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+		dprintk(dev, 2, "touch_cap buffer %d done\n",
+			buf->vb.vb2_buf.index);
+	}
+
+	kthread_stop(dev->kthread_touch_cap);
+	dev->kthread_touch_cap = NULL;
+}
diff --git a/drivers/media/platform/vivid/vivid-kthread-touch.h b/drivers/media/platform/vivid/vivid-kthread-touch.h
new file mode 100644
index 000000000000..ecf79b46209e
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-kthread-touch.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * vivid-kthread-cap.h - video/vbi capture thread support functions.
+ *
+ */
+
+#ifndef _VIVID_KTHREAD_CAP_H_
+#define _VIVID_KTHREAD_CAP_H_
+
+int vivid_start_generating_touch_cap(struct vivid_dev *dev);
+void vivid_stop_generating_touch_cap(struct vivid_dev *dev);
+
+#endif
diff --git a/drivers/media/platform/vivid/vivid-osd.c b/drivers/media/platform/vivid/vivid-osd.c
index f2e789bdf4a6..fbaec8acc161 100644
--- a/drivers/media/platform/vivid/vivid-osd.c
+++ b/drivers/media/platform/vivid/vivid-osd.c
@@ -244,7 +244,7 @@ static int vivid_fb_blank(int blank_mode, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops vivid_fb_ops = {
+static const struct fb_ops vivid_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var   = vivid_fb_check_var,
 	.fb_set_par     = vivid_fb_set_par,
@@ -311,7 +311,6 @@ static int vivid_fb_init_vidmode(struct vivid_dev *dev)
 
 	dev->fb_info.node = -1;
 	dev->fb_info.flags = FBINFO_FLAG_DEFAULT;
-	dev->fb_info.fbops = &vivid_fb_ops;
 	dev->fb_info.par = dev;
 	dev->fb_info.var = dev->fb_defined;
 	dev->fb_info.fix = dev->fb_fix;
diff --git a/drivers/media/platform/vivid/vivid-touch-cap.c b/drivers/media/platform/vivid/vivid-touch-cap.c
new file mode 100644
index 000000000000..ebb00b128030
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-touch-cap.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vivid-touch-cap.c - touch support functions.
+ */
+
+#include "vivid-core.h"
+#include "vivid-kthread-touch.h"
+#include "vivid-vid-common.h"
+#include "vivid-touch-cap.h"
+
+static int touch_cap_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+				 unsigned int *nplanes, unsigned int sizes[],
+				 struct device *alloc_devs[])
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	struct v4l2_pix_format *f = &dev->tch_format;
+	unsigned int size = f->sizeimage;
+
+	if (*nplanes) {
+		if (sizes[0] < size)
+			return -EINVAL;
+	} else {
+		sizes[0] = size;
+	}
+
+	if (vq->num_buffers + *nbuffers < 2)
+		*nbuffers = 2 - vq->num_buffers;
+
+	*nplanes = 1;
+	return 0;
+}
+
+static int touch_cap_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct v4l2_pix_format *f = &dev->tch_format;
+	unsigned int size = f->sizeimage;
+
+	if (dev->buf_prepare_error) {
+		/*
+		 * Error injection: test what happens if buf_prepare() returns
+		 * an error.
+		 */
+		dev->buf_prepare_error = false;
+		return -EINVAL;
+	}
+	if (vb2_plane_size(vb, 0) < size) {
+		dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n",
+			__func__, vb2_plane_size(vb, 0), size);
+		return -EINVAL;
+	}
+	vb2_set_plane_payload(vb, 0, size);
+
+	return 0;
+}
+
+static void touch_cap_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+	struct vivid_buffer *buf = container_of(vbuf, struct vivid_buffer, vb);
+
+	vbuf->field = V4L2_FIELD_NONE;
+	spin_lock(&dev->slock);
+	list_add_tail(&buf->list, &dev->touch_cap_active);
+	spin_unlock(&dev->slock);
+}
+
+static int touch_cap_start_streaming(struct vb2_queue *vq, unsigned int count)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+	int err;
+
+	dev->touch_cap_seq_count = 0;
+	if (dev->start_streaming_error) {
+		dev->start_streaming_error = false;
+		err = -EINVAL;
+	} else {
+		err = vivid_start_generating_touch_cap(dev);
+	}
+	if (err) {
+		struct vivid_buffer *buf, *tmp;
+
+		list_for_each_entry_safe(buf, tmp,
+					 &dev->touch_cap_active, list) {
+			list_del(&buf->list);
+			vb2_buffer_done(&buf->vb.vb2_buf,
+					VB2_BUF_STATE_QUEUED);
+		}
+	}
+	return err;
+}
+
+/* abort streaming and wait for last buffer */
+static void touch_cap_stop_streaming(struct vb2_queue *vq)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vq);
+
+	vivid_stop_generating_touch_cap(dev);
+}
+
+static void touch_cap_buf_request_complete(struct vb2_buffer *vb)
+{
+	struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_ctrl_request_complete(vb->req_obj.req, &dev->ctrl_hdl_touch_cap);
+}
+
+const struct vb2_ops vivid_touch_cap_qops = {
+	.queue_setup		= touch_cap_queue_setup,
+	.buf_prepare		= touch_cap_buf_prepare,
+	.buf_queue		= touch_cap_buf_queue,
+	.start_streaming	= touch_cap_start_streaming,
+	.stop_streaming		= touch_cap_stop_streaming,
+	.buf_request_complete	= touch_cap_buf_request_complete,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
+};
+
+int vivid_enum_fmt_tch(struct file *file, void  *priv, struct v4l2_fmtdesc *f)
+{
+	if (f->index)
+		return -EINVAL;
+
+	f->pixelformat = V4L2_TCH_FMT_DELTA_TD16;
+	return 0;
+}
+
+int vivid_g_fmt_tch(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (dev->multiplanar)
+		return -ENOTTY;
+	f->fmt.pix = dev->tch_format;
+	return 0;
+}
+
+int vivid_g_fmt_tch_mplane(struct file *file, void *priv, struct v4l2_format *f)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+	struct v4l2_format sp_fmt;
+
+	if (!dev->multiplanar)
+		return -ENOTTY;
+	sp_fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	sp_fmt.fmt.pix = dev->tch_format;
+	fmt_sp2mp(&sp_fmt, f);
+	return 0;
+}
+
+int vivid_g_parm_tch(struct file *file, void *priv,
+		     struct v4l2_streamparm *parm)
+{
+	struct vivid_dev *dev = video_drvdata(file);
+
+	if (parm->type != (dev->multiplanar ?
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE))
+		return -EINVAL;
+
+	parm->parm.capture.capability   = V4L2_CAP_TIMEPERFRAME;
+	parm->parm.capture.timeperframe = dev->timeperframe_tch_cap;
+	parm->parm.capture.readbuffers  = 1;
+	return 0;
+}
+
+int vivid_enum_input_tch(struct file *file, void *priv, struct v4l2_input *inp)
+{
+	if (inp->index)
+		return -EINVAL;
+
+	inp->type = V4L2_INPUT_TYPE_TOUCH;
+	strscpy(inp->name, "Vivid Touch", sizeof(inp->name));
+	inp->capabilities = 0;
+	return 0;
+}
+
+int vivid_g_input_tch(struct file *file, void *priv, unsigned int *i)
+{
+	*i = 0;
+	return 0;
+}
+
+int vivid_set_touch(struct vivid_dev *dev, unsigned int i)
+{
+	struct v4l2_pix_format *f = &dev->tch_format;
+
+	if (i)
+		return -EINVAL;
+
+	f->pixelformat = V4L2_TCH_FMT_DELTA_TD16;
+	f->width =  VIVID_TCH_WIDTH;
+	f->height = VIVID_TCH_HEIGHT;
+	f->field = V4L2_FIELD_NONE;
+	f->colorspace = V4L2_COLORSPACE_RAW;
+	f->bytesperline = f->width * sizeof(s16);
+	f->sizeimage = f->width * f->height * sizeof(s16);
+	return 0;
+}
+
+int vivid_s_input_tch(struct file *file, void *priv, unsigned int i)
+{
+	return vivid_set_touch(video_drvdata(file), i);
+}
+
+static void vivid_fill_buff_noise(__s16 *tch_buf, int size)
+{
+	int i;
+
+	/* Fill 10% of the values within range -3 and 3, zero the others */
+	for (i = 0; i < size; i++) {
+		unsigned int rand = get_random_int();
+
+		if (rand % 10)
+			tch_buf[i] = 0;
+		else
+			tch_buf[i] = (rand / 10) % 7 - 3;
+	}
+}
+
+static inline int get_random_pressure(void)
+{
+	return get_random_int() % VIVID_PRESSURE_LIMIT;
+}
+
+static void vivid_tch_buf_set(struct v4l2_pix_format *f,
+			      __s16 *tch_buf,
+			      int index)
+{
+	unsigned int x = index % f->width;
+	unsigned int y = index / f->width;
+	unsigned int offset = VIVID_MIN_PRESSURE;
+
+	tch_buf[index] = offset + get_random_pressure();
+	offset /= 2;
+	if (x)
+		tch_buf[index - 1] = offset + get_random_pressure();
+	if (x < f->width - 1)
+		tch_buf[index + 1] = offset + get_random_pressure();
+	if (y)
+		tch_buf[index - f->width] = offset + get_random_pressure();
+	if (y < f->height - 1)
+		tch_buf[index + f->width] = offset + get_random_pressure();
+	offset /= 2;
+	if (x && y)
+		tch_buf[index - 1 - f->width] = offset + get_random_pressure();
+	if (x < f->width - 1 && y)
+		tch_buf[index + 1 - f->width] = offset + get_random_pressure();
+	if (x && y < f->height - 1)
+		tch_buf[index - 1 + f->width] = offset + get_random_pressure();
+	if (x < f->width - 1 && y < f->height - 1)
+		tch_buf[index + 1 + f->width] = offset + get_random_pressure();
+}
+
+void vivid_fillbuff_tch(struct vivid_dev *dev, struct vivid_buffer *buf)
+{
+	struct v4l2_pix_format *f = &dev->tch_format;
+	int size = f->width * f->height;
+	int x, y, xstart, ystart, offset_x, offset_y;
+	unsigned int test_pattern, test_pat_idx, rand;
+
+	__s16 *tch_buf = vb2_plane_vaddr(&buf->vb.vb2_buf, 0);
+
+	buf->vb.sequence = dev->touch_cap_seq_count;
+	test_pattern = (buf->vb.sequence / TCH_SEQ_COUNT) % TEST_CASE_MAX;
+	test_pat_idx = buf->vb.sequence % TCH_SEQ_COUNT;
+
+	vivid_fill_buff_noise(tch_buf, size);
+
+	if (test_pat_idx >= TCH_PATTERN_COUNT)
+		return;
+
+	if (test_pat_idx == 0)
+		dev->tch_pat_random = get_random_int();
+	rand = dev->tch_pat_random;
+
+	switch (test_pattern) {
+	case SINGLE_TAP:
+		if (test_pat_idx == 2)
+			vivid_tch_buf_set(f, tch_buf, rand % size);
+		break;
+	case DOUBLE_TAP:
+		if (test_pat_idx == 2 || test_pat_idx == 4)
+			vivid_tch_buf_set(f, tch_buf, rand % size);
+		break;
+	case TRIPLE_TAP:
+		if (test_pat_idx == 2 || test_pat_idx == 4 || test_pat_idx == 6)
+			vivid_tch_buf_set(f, tch_buf, rand % size);
+		break;
+	case MOVE_LEFT_TO_RIGHT:
+		vivid_tch_buf_set(f, tch_buf,
+				  (rand % f->height) * f->width +
+				  test_pat_idx *
+				  (f->width / TCH_PATTERN_COUNT));
+		break;
+	case ZOOM_IN:
+		x = f->width / 2;
+		y = f->height / 2;
+		offset_x = ((TCH_PATTERN_COUNT - 1 - test_pat_idx) * x) /
+				TCH_PATTERN_COUNT;
+		offset_y = ((TCH_PATTERN_COUNT - 1 - test_pat_idx) * y) /
+				TCH_PATTERN_COUNT;
+		vivid_tch_buf_set(f, tch_buf,
+				  (x - offset_x) + f->width * (y - offset_y));
+		vivid_tch_buf_set(f, tch_buf,
+				  (x + offset_x) + f->width * (y + offset_y));
+		break;
+	case ZOOM_OUT:
+		x = f->width / 2;
+		y = f->height / 2;
+		offset_x = (test_pat_idx * x) / TCH_PATTERN_COUNT;
+		offset_y = (test_pat_idx * y) / TCH_PATTERN_COUNT;
+		vivid_tch_buf_set(f, tch_buf,
+				  (x - offset_x) + f->width * (y - offset_y));
+		vivid_tch_buf_set(f, tch_buf,
+				  (x + offset_x) + f->width * (y + offset_y));
+		break;
+	case PALM_PRESS:
+		for (x = 0; x < f->width; x++)
+			for (y = f->height / 2; y < f->height; y++)
+				tch_buf[x + f->width * y] = VIVID_MIN_PRESSURE +
+							get_random_pressure();
+		break;
+	case MULTIPLE_PRESS:
+		/* 16 pressure points */
+		for (y = 0; y < 4; y++) {
+			for (x = 0; x < 4; x++) {
+				ystart = (y * f->height) / 4 + f->height / 8;
+				xstart = (x * f->width) / 4 + f->width / 8;
+				vivid_tch_buf_set(f, tch_buf,
+						  ystart * f->width + xstart);
+			}
+		}
+		break;
+	}
+#ifdef __BIG_ENDIAN__
+	for (x = 0; x < size; x++)
+		tch_buf[x] = (__force s16)__cpu_to_le16((u16)tch_buf[x]);
+#endif
+}
diff --git a/drivers/media/platform/vivid/vivid-touch-cap.h b/drivers/media/platform/vivid/vivid-touch-cap.h
new file mode 100644
index 000000000000..07e514046ae8
--- /dev/null
+++ b/drivers/media/platform/vivid/vivid-touch-cap.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * vivid-touch-cap.h - touch support functions.
+ */
+#ifndef _VIVID_TOUCH_CAP_H_
+#define _VIVID_TOUCH_CAP_H_
+
+#define VIVID_TCH_HEIGHT	12
+#define VIVID_TCH_WIDTH		21
+#define VIVID_MIN_PRESSURE	180
+#define VIVID_PRESSURE_LIMIT	40
+#define TCH_SEQ_COUNT		16
+#define TCH_PATTERN_COUNT	12
+
+enum vivid_tch_test {
+	SINGLE_TAP,
+	DOUBLE_TAP,
+	TRIPLE_TAP,
+	MOVE_LEFT_TO_RIGHT,
+	ZOOM_IN,
+	ZOOM_OUT,
+	PALM_PRESS,
+	MULTIPLE_PRESS,
+	TEST_CASE_MAX
+};
+
+extern const struct vb2_ops vivid_touch_cap_qops;
+
+int vivid_enum_fmt_tch(struct file *file, void  *priv, struct v4l2_fmtdesc *f);
+int vivid_g_fmt_tch(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_g_fmt_tch_mplane(struct file *file, void *priv, struct v4l2_format *f);
+int vivid_enum_input_tch(struct file *file, void *priv, struct v4l2_input *inp);
+int vivid_g_input_tch(struct file *file, void *priv, unsigned int *i);
+int vivid_s_input_tch(struct file *file, void *priv, unsigned int i);
+void vivid_fillbuff_tch(struct vivid_dev *dev, struct vivid_buffer *buf);
+int vivid_set_touch(struct vivid_dev *dev, unsigned int i);
+int vivid_g_parm_tch(struct file *file, void *priv,
+		     struct v4l2_streamparm *parm);
+#endif
diff --git a/drivers/media/platform/vivid/vivid-vid-common.c b/drivers/media/platform/vivid/vivid-vid-common.c
index 8665dfd25eb4..76b0be670ebb 100644
--- a/drivers/media/platform/vivid/vivid-vid-common.c
+++ b/drivers/media/platform/vivid/vivid-vid-common.c
@@ -813,7 +813,7 @@ void fmt_sp2mp(const struct v4l2_format *sp_fmt, struct v4l2_format *mp_fmt)
 
 	memset(mp->reserved, 0, sizeof(mp->reserved));
 	mp_fmt->type = is_out ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
-			   V4L2_CAP_VIDEO_CAPTURE_MPLANE;
+			   V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	mp->width = pix->width;
 	mp->height = pix->height;
 	mp->pixelformat = pix->pixelformat;
diff --git a/drivers/media/rc/iguanair.c b/drivers/media/rc/iguanair.c
index 872d6441e512..a7deca1fefb7 100644
--- a/drivers/media/rc/iguanair.c
+++ b/drivers/media/rc/iguanair.c
@@ -413,7 +413,7 @@ static int iguanair_probe(struct usb_interface *intf,
 	int ret, pipein, pipeout;
 	struct usb_host_interface *idesc;
 
-	idesc = intf->altsetting;
+	idesc = intf->cur_altsetting;
 	if (idesc->desc.bNumEndpoints < 2)
 		return -ENODEV;
 
diff --git a/drivers/media/rc/ir-hix5hd2.c b/drivers/media/rc/ir-hix5hd2.c
index 32ccefeff57d..d80cfa455c73 100644
--- a/drivers/media/rc/ir-hix5hd2.c
+++ b/drivers/media/rc/ir-hix5hd2.c
@@ -37,10 +37,13 @@
 #define INT_CLR_RCV		BIT(16)
 #define INT_CLR_RCVTIMEOUT	(BIT(16) | BIT(17))
 
-#define IR_CLK			0x48
 #define IR_CLK_ENABLE		BIT(4)
 #define IR_CLK_RESET		BIT(5)
 
+/* IR_ENABLE register bits */
+#define IR_ENABLE_EN		BIT(0)
+#define IR_ENABLE_EN_EXTRA	BIT(8)
+
 #define IR_CFG_WIDTH_MASK	0xffff
 #define IR_CFG_WIDTH_SHIFT	16
 #define IR_CFG_FORMAT_MASK	0x3
@@ -58,6 +61,23 @@
 
 #define IR_HIX5HD2_NAME		"hix5hd2-ir"
 
+/* Need to set extra bit for enabling IR */
+#define HIX5HD2_FLAG_EXTRA_ENABLE	BIT(0)
+
+struct hix5hd2_soc_data {
+	u32 clk_reg;
+	u32 flags;
+};
+
+static const struct hix5hd2_soc_data hix5hd2_data = {
+	.clk_reg = 0x48,
+};
+
+static const struct hix5hd2_soc_data hi3796cv300_data = {
+	.clk_reg = 0x60,
+	.flags = HIX5HD2_FLAG_EXTRA_ENABLE,
+};
+
 struct hix5hd2_ir_priv {
 	int			irq;
 	void __iomem		*base;
@@ -66,15 +86,17 @@ struct hix5hd2_ir_priv {
 	struct regmap		*regmap;
 	struct clk		*clock;
 	unsigned long		rate;
+	const struct hix5hd2_soc_data *socdata;
 };
 
-static int hix5hd2_ir_enable(struct hix5hd2_ir_priv *dev, bool on)
+static int hix5hd2_ir_clk_enable(struct hix5hd2_ir_priv *dev, bool on)
 {
+	u32 clk_reg = dev->socdata->clk_reg;
 	u32 val;
 	int ret = 0;
 
 	if (dev->regmap) {
-		regmap_read(dev->regmap, IR_CLK, &val);
+		regmap_read(dev->regmap, clk_reg, &val);
 		if (on) {
 			val &= ~IR_CLK_RESET;
 			val |= IR_CLK_ENABLE;
@@ -82,7 +104,7 @@ static int hix5hd2_ir_enable(struct hix5hd2_ir_priv *dev, bool on)
 			val &= ~IR_CLK_ENABLE;
 			val |= IR_CLK_RESET;
 		}
-		regmap_write(dev->regmap, IR_CLK, val);
+		regmap_write(dev->regmap, clk_reg, val);
 	} else {
 		if (on)
 			ret = clk_prepare_enable(dev->clock);
@@ -92,12 +114,23 @@ static int hix5hd2_ir_enable(struct hix5hd2_ir_priv *dev, bool on)
 	return ret;
 }
 
+static inline void hix5hd2_ir_enable(struct hix5hd2_ir_priv *priv)
+{
+	u32 val = IR_ENABLE_EN;
+
+	if (priv->socdata->flags & HIX5HD2_FLAG_EXTRA_ENABLE)
+		val |= IR_ENABLE_EN_EXTRA;
+
+	writel_relaxed(val, priv->base + IR_ENABLE);
+}
+
 static int hix5hd2_ir_config(struct hix5hd2_ir_priv *priv)
 {
 	int timeout = 10000;
 	u32 val, rate;
 
-	writel_relaxed(0x01, priv->base + IR_ENABLE);
+	hix5hd2_ir_enable(priv);
+
 	while (readl_relaxed(priv->base + IR_BUSY)) {
 		if (timeout--) {
 			udelay(1);
@@ -128,13 +161,13 @@ static int hix5hd2_ir_open(struct rc_dev *rdev)
 	struct hix5hd2_ir_priv *priv = rdev->priv;
 	int ret;
 
-	ret = hix5hd2_ir_enable(priv, true);
+	ret = hix5hd2_ir_clk_enable(priv, true);
 	if (ret)
 		return ret;
 
 	ret = hix5hd2_ir_config(priv);
 	if (ret) {
-		hix5hd2_ir_enable(priv, false);
+		hix5hd2_ir_clk_enable(priv, false);
 		return ret;
 	}
 	return 0;
@@ -144,7 +177,7 @@ static void hix5hd2_ir_close(struct rc_dev *rdev)
 {
 	struct hix5hd2_ir_priv *priv = rdev->priv;
 
-	hix5hd2_ir_enable(priv, false);
+	hix5hd2_ir_clk_enable(priv, false);
 }
 
 static irqreturn_t hix5hd2_ir_rx_interrupt(int irq, void *data)
@@ -205,6 +238,13 @@ static irqreturn_t hix5hd2_ir_rx_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static const struct of_device_id hix5hd2_ir_table[] = {
+	{ .compatible = "hisilicon,hix5hd2-ir", &hix5hd2_data, },
+	{ .compatible = "hisilicon,hi3796cv300-ir", &hi3796cv300_data, },
+	{},
+};
+MODULE_DEVICE_TABLE(of, hix5hd2_ir_table);
+
 static int hix5hd2_ir_probe(struct platform_device *pdev)
 {
 	struct rc_dev *rdev;
@@ -212,6 +252,7 @@ static int hix5hd2_ir_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct hix5hd2_ir_priv *priv;
 	struct device_node *node = pdev->dev.of_node;
+	const struct of_device_id *of_id;
 	const char *map_name;
 	int ret;
 
@@ -219,6 +260,13 @@ static int hix5hd2_ir_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
+	of_id = of_match_device(hix5hd2_ir_table, dev);
+	if (!of_id) {
+		dev_err(dev, "Unable to initialize IR data\n");
+		return -ENODEV;
+	}
+	priv->socdata = of_id->data;
+
 	priv->regmap = syscon_regmap_lookup_by_phandle(node,
 						       "hisilicon,power-syscon");
 	if (IS_ERR(priv->regmap)) {
@@ -309,7 +357,7 @@ static int hix5hd2_ir_suspend(struct device *dev)
 	struct hix5hd2_ir_priv *priv = dev_get_drvdata(dev);
 
 	clk_disable_unprepare(priv->clock);
-	hix5hd2_ir_enable(priv, false);
+	hix5hd2_ir_clk_enable(priv, false);
 
 	return 0;
 }
@@ -319,17 +367,18 @@ static int hix5hd2_ir_resume(struct device *dev)
 	struct hix5hd2_ir_priv *priv = dev_get_drvdata(dev);
 	int ret;
 
-	ret = hix5hd2_ir_enable(priv, true);
+	ret = hix5hd2_ir_clk_enable(priv, true);
 	if (ret)
 		return ret;
 
 	ret = clk_prepare_enable(priv->clock);
 	if (ret) {
-		hix5hd2_ir_enable(priv, false);
+		hix5hd2_ir_clk_enable(priv, false);
 		return ret;
 	}
 
-	writel_relaxed(0x01, priv->base + IR_ENABLE);
+	hix5hd2_ir_enable(priv);
+
 	writel_relaxed(0x00, priv->base + IR_INTM);
 	writel_relaxed(0xff, priv->base + IR_INTC);
 	writel_relaxed(0x01, priv->base + IR_START);
@@ -341,12 +390,6 @@ static int hix5hd2_ir_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(hix5hd2_ir_pm_ops, hix5hd2_ir_suspend,
 			 hix5hd2_ir_resume);
 
-static const struct of_device_id hix5hd2_ir_table[] = {
-	{ .compatible = "hisilicon,hix5hd2-ir", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, hix5hd2_ir_table);
-
 static struct platform_driver hix5hd2_ir_driver = {
 	.driver = {
 		.name = IR_HIX5HD2_NAME,
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 7741151606ef..6f80c251f641 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -1891,23 +1891,28 @@ int rc_register_device(struct rc_dev *dev)
 
 	dev->registered = true;
 
-	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
-		rc = rc_setup_rx_device(dev);
-		if (rc)
-			goto out_dev;
-	}
-
-	/* Ensure that the lirc kfifo is setup before we start the thread */
+	/*
+	 * once the the input device is registered in rc_setup_rx_device,
+	 * userspace can open the input device and rc_open() will be called
+	 * as a result. This results in driver code being allowed to submit
+	 * keycodes with rc_keydown, so lirc must be registered first.
+	 */
 	if (dev->allowed_protocols != RC_PROTO_BIT_CEC) {
 		rc = ir_lirc_register(dev);
 		if (rc < 0)
-			goto out_rx;
+			goto out_dev;
+	}
+
+	if (dev->driver_type != RC_DRIVER_IR_RAW_TX) {
+		rc = rc_setup_rx_device(dev);
+		if (rc)
+			goto out_lirc;
 	}
 
 	if (dev->driver_type == RC_DRIVER_IR_RAW) {
 		rc = ir_raw_event_register(dev);
 		if (rc < 0)
-			goto out_lirc;
+			goto out_rx;
 	}
 
 	dev_dbg(&dev->dev, "Registered rc%u (driver: %s)\n", dev->minor,
@@ -1915,11 +1920,11 @@ int rc_register_device(struct rc_dev *dev)
 
 	return 0;
 
+out_rx:
+	rc_free_rx_device(dev);
 out_lirc:
 	if (dev->allowed_protocols != RC_PROTO_BIT_CEC)
 		ir_lirc_unregister(dev);
-out_rx:
-	rc_free_rx_device(dev);
 out_dev:
 	device_del(&dev->dev);
 out_rx_free:
diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 7652e982173f..d77507ba0fb5 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -353,7 +353,7 @@ static irqreturn_t serial_ir_irq_handler(int i, void *blah)
 			dcd = (status & hardware[type].signal_pin) ? 1 : 0;
 
 			if (dcd == last_dcd) {
-				dev_err(&serial_ir.pdev->dev,
+				dev_dbg(&serial_ir.pdev->dev,
 					"ignoring spike: %d %d %lldns %lldns\n",
 					dcd, sense, ktime_to_ns(kt),
 					ktime_to_ns(serial_ir.lastkt));
diff --git a/drivers/media/usb/cpia2/cpia2_v4l.c b/drivers/media/usb/cpia2/cpia2_v4l.c
index 626264a56517..9d3d05125d7b 100644
--- a/drivers/media/usb/cpia2/cpia2_v4l.c
+++ b/drivers/media/usb/cpia2/cpia2_v4l.c
@@ -800,7 +800,7 @@ static int cpia2_querybuf(struct file *file, void *fh, struct v4l2_buffer *buf)
 		break;
 	case FRAME_READY:
 		buf->bytesused = cam->buffers[buf->index].length;
-		buf->timestamp = ns_to_timeval(cam->buffers[buf->index].ts);
+		v4l2_buffer_set_timestamp(buf, cam->buffers[buf->index].ts);
 		buf->sequence = cam->buffers[buf->index].seq;
 		buf->flags = V4L2_BUF_FLAG_DONE;
 		break;
@@ -907,7 +907,7 @@ static int cpia2_dqbuf(struct file *file, void *fh, struct v4l2_buffer *buf)
 	buf->flags = V4L2_BUF_FLAG_MAPPED | V4L2_BUF_FLAG_DONE
 		| V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	buf->field = V4L2_FIELD_NONE;
-	buf->timestamp = ns_to_timeval(cam->buffers[buf->index].ts);
+	v4l2_buffer_set_timestamp(buf, cam->buffers[buf->index].ts);
 	buf->sequence = cam->buffers[buf->index].seq;
 	buf->m.offset = cam->buffers[buf->index].data - cam->frame_buffer;
 	buf->length = cam->frame_size;
diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index fd6e2df3d1b7..de42db6f6ad1 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -13,7 +13,6 @@
 #include <linux/spinlock.h>
 #include <linux/soundcard.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -372,28 +371,6 @@ static int cx231xx_init_audio_bulk(struct cx231xx *dev)
 	return errCode;
 }
 
-static int snd_pcm_alloc_vmalloc_buffer(struct snd_pcm_substream *subs,
-					size_t size)
-{
-	struct snd_pcm_runtime *runtime = subs->runtime;
-	struct cx231xx *dev = snd_pcm_substream_chip(subs);
-
-	dev_dbg(dev->dev, "Allocating vbuffer\n");
-	if (runtime->dma_area) {
-		if (runtime->dma_bytes > size)
-			return 0;
-
-		vfree(runtime->dma_area);
-	}
-	runtime->dma_area = vmalloc(size);
-	if (!runtime->dma_area)
-		return -ENOMEM;
-
-	runtime->dma_bytes = size;
-
-	return 0;
-}
-
 static const struct snd_pcm_hardware snd_cx231xx_hw_capture = {
 	.info = SNDRV_PCM_INFO_BLOCK_TRANSFER	|
 	    SNDRV_PCM_INFO_MMAP			|
@@ -484,11 +461,6 @@ static int snd_cx231xx_pcm_close(struct snd_pcm_substream *substream)
 	}
 
 	dev->adev.users--;
-	if (substream->runtime->dma_area) {
-		dev_dbg(dev->dev, "freeing\n");
-		vfree(substream->runtime->dma_area);
-		substream->runtime->dma_area = NULL;
-	}
 	mutex_unlock(&dev->lock);
 
 	if (dev->adev.users == 0 && dev->adev.shutdown == 1) {
@@ -504,44 +476,6 @@ static int snd_cx231xx_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_cx231xx_hw_capture_params(struct snd_pcm_substream *substream,
-					 struct snd_pcm_hw_params *hw_params)
-{
-	struct cx231xx *dev = snd_pcm_substream_chip(substream);
-	int ret;
-
-	dev_dbg(dev->dev, "Setting capture parameters\n");
-
-	ret = snd_pcm_alloc_vmalloc_buffer(substream,
-					   params_buffer_bytes(hw_params));
-#if 0
-	/* TODO: set up cx231xx audio chip to deliver the correct audio format,
-	   current default is 48000hz multiplexed => 96000hz mono
-	   which shouldn't matter since analogue TV only supports mono */
-	unsigned int channels, rate, format;
-
-	format = params_format(hw_params);
-	rate = params_rate(hw_params);
-	channels = params_channels(hw_params);
-#endif
-
-	return ret;
-}
-
-static int snd_cx231xx_hw_capture_free(struct snd_pcm_substream *substream)
-{
-	struct cx231xx *dev = snd_pcm_substream_chip(substream);
-
-	dev_dbg(dev->dev, "Stop capture, if needed\n");
-
-	if (atomic_read(&dev->stream_started) > 0) {
-		atomic_set(&dev->stream_started, 0);
-		schedule_work(&dev->wq_trigger);
-	}
-
-	return 0;
-}
-
 static int snd_cx231xx_prepare(struct snd_pcm_substream *substream)
 {
 	struct cx231xx *dev = snd_pcm_substream_chip(substream);
@@ -614,24 +548,12 @@ static snd_pcm_uframes_t snd_cx231xx_capture_pointer(struct snd_pcm_substream
 	return hwptr_done;
 }
 
-static struct page *snd_pcm_get_vmalloc_page(struct snd_pcm_substream *subs,
-					     unsigned long offset)
-{
-	void *pageptr = subs->runtime->dma_area + offset;
-
-	return vmalloc_to_page(pageptr);
-}
-
 static const struct snd_pcm_ops snd_cx231xx_pcm_capture = {
 	.open = snd_cx231xx_capture_open,
 	.close = snd_cx231xx_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = snd_cx231xx_hw_capture_params,
-	.hw_free = snd_cx231xx_hw_capture_free,
 	.prepare = snd_cx231xx_prepare,
 	.trigger = snd_cx231xx_capture_trigger,
 	.pointer = snd_cx231xx_capture_pointer,
-	.page = snd_pcm_get_vmalloc_page,
 };
 
 static int cx231xx_audio_init(struct cx231xx *dev)
@@ -666,6 +588,7 @@ static int cx231xx_audio_init(struct cx231xx *dev)
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE,
 			&snd_cx231xx_pcm_capture);
+	snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC, NULL, 0, 0);
 	pcm->info_flags = 0;
 	pcm->private_data = dev;
 	strscpy(pcm->name, "Conexant cx231xx Capture", sizeof(pcm->name));
diff --git a/drivers/media/usb/cx231xx/cx231xx-i2c.c b/drivers/media/usb/cx231xx/cx231xx-i2c.c
index f33b6a077d57..c6659253c6fb 100644
--- a/drivers/media/usb/cx231xx/cx231xx-i2c.c
+++ b/drivers/media/usb/cx231xx/cx231xx-i2c.c
@@ -515,7 +515,8 @@ int cx231xx_i2c_register(struct cx231xx_i2c *bus)
 {
 	struct cx231xx *dev = bus->dev;
 
-	BUG_ON(!dev->cx231xx_send_usb_command);
+	if (!dev->cx231xx_send_usb_command)
+		return -EINVAL;
 
 	bus->i2c_adap = cx231xx_adap_template;
 	bus->i2c_adap.dev.parent = dev->dev;
diff --git a/drivers/media/usb/dvb-usb-v2/af9035.c b/drivers/media/usb/dvb-usb-v2/af9035.c
index 792667ee5ebc..b1f69c11c839 100644
--- a/drivers/media/usb/dvb-usb-v2/af9035.c
+++ b/drivers/media/usb/dvb-usb-v2/af9035.c
@@ -208,8 +208,8 @@ static int af9035_add_i2c_dev(struct dvb_usb_device *d, const char *type,
 	request_module("%s", board_info.type);
 
 	/* register I2C device */
-	client = i2c_new_device(adapter, &board_info);
-	if (client == NULL || client->dev.driver == NULL) {
+	client = i2c_new_client_device(adapter, &board_info);
+	if (!i2c_client_has_driver(client)) {
 		ret = -ENODEV;
 		goto err;
 	}
@@ -1621,9 +1621,10 @@ static int it930x_tuner_attach(struct dvb_usb_adapter *adap)
 	si2157_config.fe = adap->fe[0];
 
 	/*
-	 * HACK: The Logilink VG0022A has a bug: when the si2157
-	 * firmware that came with the device is replaced by a new
-	 * one, the I2C transfers to the tuner will return just 0xff.
+	 * HACK: The Logilink VG0022A and TerraTec TC2 Stick have
+	 * a bug: when the si2157 firmware that came with the device
+	 * is replaced by a new one, the I2C transfers to the tuner
+	 * will return just 0xff.
 	 *
 	 * Probably, the vendor firmware has some patch specifically
 	 * designed for this device. So, we can't replace by the
@@ -1633,8 +1634,10 @@ static int it930x_tuner_attach(struct dvb_usb_adapter *adap)
 	 * while we don't have that, the next best solution is to just
 	 * keep the original firmware at the device.
 	 */
-	if (le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_DEXATEK &&
-	    le16_to_cpu(d->udev->descriptor.idProduct) == 0x0100)
+	if ((le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_DEXATEK &&
+	     le16_to_cpu(d->udev->descriptor.idProduct) == 0x0100) ||
+	    (le16_to_cpu(d->udev->descriptor.idVendor) == USB_VID_TERRATEC &&
+	     le16_to_cpu(d->udev->descriptor.idProduct) == USB_PID_TERRATEC_CINERGY_TC2_STICK))
 		si2157_config.dont_load_firmware = true;
 
 	si2157_config.if_port = it930x_addresses_table[state->it930x_addresses].tuner_if_port;
@@ -2150,6 +2153,8 @@ static const struct usb_device_id af9035_id_table[] = {
 		&it930x_props, "AVerMedia TD310 DVB-T2", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_DEXATEK, 0x0100,
 		&it930x_props, "Logilink VG0022A", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_TERRATEC, USB_PID_TERRATEC_CINERGY_TC2_STICK,
+		&it930x_props, "TerraTec Cinergy TC2 Stick", NULL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, af9035_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/anysee.c b/drivers/media/usb/dvb-usb-v2/anysee.c
index fb6d99dea31a..0514e87405b6 100644
--- a/drivers/media/usb/dvb-usb-v2/anysee.c
+++ b/drivers/media/usb/dvb-usb-v2/anysee.c
@@ -649,8 +649,8 @@ static int anysee_add_i2c_dev(struct dvb_usb_device *d, const char *type,
 	request_module("%s", board_info.type);
 
 	/* register I2C device */
-	client = i2c_new_device(adapter, &board_info);
-	if (client == NULL || client->dev.driver == NULL) {
+	client = i2c_new_client_device(adapter, &board_info);
+	if (!i2c_client_has_driver(client)) {
 		ret = -ENODEV;
 		goto err;
 	}
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 5016ede7b35f..c6881a1b3232 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -697,8 +697,8 @@ static int rtl2831u_frontend_attach(struct dvb_usb_adapter *adap)
 	board_info.addr = 0x10;
 	board_info.platform_data = pdata;
 	request_module("%s", board_info.type);
-	client = i2c_new_device(&d->i2c_adap, &board_info);
-	if (client == NULL || client->dev.driver == NULL) {
+	client = i2c_new_client_device(&d->i2c_adap, &board_info);
+	if (!i2c_client_has_driver(client)) {
 		ret = -ENODEV;
 		goto err;
 	}
@@ -918,8 +918,8 @@ static int rtl2832u_frontend_attach(struct dvb_usb_adapter *adap)
 	board_info.addr = 0x10;
 	board_info.platform_data = pdata;
 	request_module("%s", board_info.type);
-	client = i2c_new_device(&d->i2c_adap, &board_info);
-	if (client == NULL || client->dev.driver == NULL) {
+	client = i2c_new_client_device(&d->i2c_adap, &board_info);
+	if (!i2c_client_has_driver(client)) {
 		ret = -ENODEV;
 		goto err;
 	}
@@ -960,8 +960,8 @@ static int rtl2832u_frontend_attach(struct dvb_usb_adapter *adap)
 			info.addr = 0x18;
 			info.platform_data = &mn88472_config;
 			request_module(info.type);
-			client = i2c_new_device(&d->i2c_adap, &info);
-			if (client == NULL || client->dev.driver == NULL) {
+			client = i2c_new_client_device(&d->i2c_adap, &info);
+			if (!i2c_client_has_driver(client)) {
 				dev->slave_demod = SLAVE_DEMOD_NONE;
 				goto err_slave_demod_failed;
 			}
@@ -982,8 +982,8 @@ static int rtl2832u_frontend_attach(struct dvb_usb_adapter *adap)
 			info.addr = 0x18;
 			info.platform_data = &mn88473_config;
 			request_module(info.type);
-			client = i2c_new_device(&d->i2c_adap, &info);
-			if (client == NULL || client->dev.driver == NULL) {
+			client = i2c_new_client_device(&d->i2c_adap, &info);
+			if (!i2c_client_has_driver(client)) {
 				dev->slave_demod = SLAVE_DEMOD_NONE;
 				goto err_slave_demod_failed;
 			}
@@ -1025,8 +1025,8 @@ static int rtl2832u_frontend_attach(struct dvb_usb_adapter *adap)
 			info.addr = 0x64;
 			info.platform_data = &si2168_config;
 			request_module(info.type);
-			client = i2c_new_device(&d->i2c_adap, &info);
-			if (client == NULL || client->dev.driver == NULL) {
+			client = i2c_new_client_device(&d->i2c_adap, &info);
+			if (!i2c_client_has_driver(client)) {
 				dev->slave_demod = SLAVE_DEMOD_NONE;
 				goto err_slave_demod_failed;
 			}
@@ -1217,8 +1217,9 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 			info.platform_data = &e4000_config;
 
 			request_module(info.type);
-			client = i2c_new_device(dev->demod_i2c_adapter, &info);
-			if (client == NULL || client->dev.driver == NULL)
+			client = i2c_new_client_device(dev->demod_i2c_adapter,
+						       &info);
+			if (!i2c_client_has_driver(client))
 				break;
 
 			if (!try_module_get(client->dev.driver->owner)) {
@@ -1240,9 +1241,9 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 			board_info.addr = 0x56;
 			board_info.platform_data = &fc2580_pdata;
 			request_module("fc2580");
-			client = i2c_new_device(dev->demod_i2c_adapter,
-						&board_info);
-			if (client == NULL || client->dev.driver == NULL)
+			client = i2c_new_client_device(dev->demod_i2c_adapter,
+						       &board_info);
+			if (!i2c_client_has_driver(client))
 				break;
 			if (!try_module_get(client->dev.driver->owner)) {
 				i2c_unregister_device(client);
@@ -1271,8 +1272,9 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 		board_info.addr = 0x60;
 		board_info.platform_data = &tua9001_pdata;
 		request_module("tua9001");
-		client = i2c_new_device(dev->demod_i2c_adapter, &board_info);
-		if (client == NULL || client->dev.driver == NULL)
+		client = i2c_new_client_device(dev->demod_i2c_adapter,
+					       &board_info);
+		if (!i2c_client_has_driver(client))
 			break;
 		if (!try_module_get(client->dev.driver->owner)) {
 			i2c_unregister_device(client);
@@ -1316,8 +1318,8 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 			info.addr = 0x60;
 			info.platform_data = &si2157_config;
 			request_module(info.type);
-			client = i2c_new_device(&d->i2c_adap, &info);
-			if (client == NULL || client->dev.driver == NULL)
+			client = i2c_new_client_device(&d->i2c_adap, &info);
+			if (!i2c_client_has_driver(client))
 				break;
 
 			if (!try_module_get(client->dev.driver->owner)) {
@@ -1955,6 +1957,8 @@ static const struct usb_device_id rtl28xxu_id_table[] = {
 		&rtl28xxu_props, "Sveon STV27", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_KWORLD_2, USB_PID_TURBOX_DTT_2000,
 		&rtl28xxu_props, "TURBO-X Pure TV Tuner DTT-2000", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_GTEK, USB_PID_PROLECTRIX_DV107669,
+		&rtl28xxu_props, "PROlectrix DV107669", NULL) },
 
 	/* RTL2832P devices: */
 	{ DVB_USB_DEVICE(USB_VID_HANFTEK, 0x0131,
diff --git a/drivers/media/usb/dvb-usb-v2/zd1301.c b/drivers/media/usb/dvb-usb-v2/zd1301.c
index 63b66b207b64..ba2c1b0d3989 100644
--- a/drivers/media/usb/dvb-usb-v2/zd1301.c
+++ b/drivers/media/usb/dvb-usb-v2/zd1301.c
@@ -172,8 +172,8 @@ static int zd1301_frontend_attach(struct dvb_usb_adapter *adap)
 	board_info.addr = 0x60;
 	board_info.platform_data = &dev->mt2060_pdata;
 	request_module("%s", "mt2060");
-	client = i2c_new_device(adapter, &board_info);
-	if (!client || !client->dev.driver) {
+	client = i2c_new_client_device(adapter, &board_info);
+	if (!i2c_client_has_driver(client)) {
 		ret = -ENODEV;
 		goto err_module_put_demod;
 	}
diff --git a/drivers/media/usb/dvb-usb/af9005.c b/drivers/media/usb/dvb-usb/af9005.c
index ac93e88d7038..89b4b5d84cdf 100644
--- a/drivers/media/usb/dvb-usb/af9005.c
+++ b/drivers/media/usb/dvb-usb/af9005.c
@@ -554,7 +554,7 @@ static int af9005_boot_packet(struct usb_device *udev, int type, u8 *reply,
 			      u8 *buf, int size)
 {
 	u16 checksum;
-	int act_len, i, ret;
+	int act_len = 0, i, ret;
 
 	memset(buf, 0, size);
 	buf[0] = (u8) (FW_BULKOUT_SIZE & 0xff);
diff --git a/drivers/media/usb/dvb-usb/cxusb.c b/drivers/media/usb/dvb-usb/cxusb.c
index fac19ec46089..c421b603be44 100644
--- a/drivers/media/usb/dvb-usb/cxusb.c
+++ b/drivers/media/usb/dvb-usb/cxusb.c
@@ -54,9 +54,6 @@ MODULE_PARM_DESC(debug, "set debugging level (see cxusb.h)."
 
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
-#define deb_info(args...)   dprintk(dvb_usb_cxusb_debug, CXUSB_DBG_MISC, args)
-#define deb_i2c(args...)    dprintk(dvb_usb_cxusb_debug, CXUSB_DBG_I2C, args)
-
 enum cxusb_table_index {
 	MEDION_MD95700,
 	DVICO_BLUEBIRD_LG064F_COLD,
@@ -125,7 +122,7 @@ static void cxusb_gpio_tuner(struct dvb_usb_device *d, int onoff)
 	cxusb_ctrl_msg(d, CMD_GPIO_WRITE, o, 2, &i, 1);
 
 	if (i != 0x01)
-		deb_info("gpio_write failed.\n");
+		dev_info(&d->udev->dev, "gpio_write failed.\n");
 
 	st->gpio_write_state[GPIO_TUNER] = onoff;
 	st->gpio_write_refresh[GPIO_TUNER] = false;
@@ -142,7 +139,7 @@ static int cxusb_bluebird_gpio_rw(struct dvb_usb_device *d, u8 changemask,
 
 	rc = cxusb_ctrl_msg(d, CMD_BLUEBIRD_GPIO_RW, o, 2, &gpio_state, 1);
 	if (rc < 0 || (gpio_state & changemask) != (newval & changemask))
-		deb_info("bluebird_gpio_write failed.\n");
+		dev_info(&d->udev->dev, "bluebird_gpio_write failed.\n");
 
 	return rc < 0 ? rc : gpio_state;
 }
@@ -174,7 +171,7 @@ static int cxusb_d680_dmb_gpio_tuner(struct dvb_usb_device *d,
 	if (i == 0x01)
 		return 0;
 
-	deb_info("gpio_write failed.\n");
+	dev_info(&d->udev->dev, "gpio_write failed.\n");
 	return -EIO;
 }
 
@@ -248,7 +245,7 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 				break;
 
 			if (ibuf[0] != 0x08)
-				deb_i2c("i2c read may have failed\n");
+				dev_info(&d->udev->dev, "i2c read may have failed\n");
 
 			memcpy(msg[i + 1].buf, &ibuf[1], msg[i + 1].len);
 
@@ -271,7 +268,7 @@ static int cxusb_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
 					   2 + msg[i].len, &ibuf, 1) < 0)
 				break;
 			if (ibuf != 0x08)
-				deb_i2c("i2c write may have failed\n");
+				dev_info(&d->udev->dev, "i2c write may have failed\n");
 		}
 	}
 
@@ -299,7 +296,7 @@ static int _cxusb_power_ctrl(struct dvb_usb_device *d, int onoff)
 {
 	u8 b = 0;
 
-	deb_info("setting power %s\n", onoff ? "ON" : "OFF");
+	dev_info(&d->udev->dev, "setting power %s\n", onoff ? "ON" : "OFF");
 
 	if (onoff)
 		return cxusb_ctrl_msg(d, CMD_POWER_ON, &b, 1, NULL, 0);
@@ -318,7 +315,7 @@ static int cxusb_power_ctrl(struct dvb_usb_device *d, int onoff)
 		mutex_lock(&cxdev->open_lock);
 
 		if (cxdev->open_type == CXUSB_OPEN_ANALOG) {
-			deb_info("preventing DVB core from setting power OFF while we are in analog mode\n");
+			dev_info(&d->udev->dev, "preventing DVB core from setting power OFF while we are in analog mode\n");
 			ret = -EBUSY;
 			goto ret_unlock;
 		}
@@ -754,16 +751,16 @@ static int dvico_bluebird_xc2028_callback(void *ptr, int component,
 
 	switch (command) {
 	case XC2028_TUNER_RESET:
-		deb_info("%s: XC2028_TUNER_RESET %d\n", __func__, arg);
+		dev_info(&d->udev->dev, "XC2028_TUNER_RESET %d\n", arg);
 		cxusb_bluebird_gpio_pulse(d, 0x01, 1);
 		break;
 	case XC2028_RESET_CLK:
-		deb_info("%s: XC2028_RESET_CLK %d\n", __func__, arg);
+		dev_info(&d->udev->dev, "XC2028_RESET_CLK %d\n", arg);
 		break;
 	case XC2028_I2C_FLUSH:
 		break;
 	default:
-		deb_info("%s: unknown command %d, arg %d\n", __func__,
+		dev_info(&d->udev->dev, "unknown command %d, arg %d\n",
 			 command, arg);
 		return -EINVAL;
 	}
@@ -1444,7 +1441,7 @@ int cxusb_medion_get(struct dvb_usb_device *dvbdev,
 
 	if (cxdev->open_ctr == 0) {
 		if (cxdev->open_type != open_type) {
-			deb_info("will acquire and switch to %s\n",
+			dev_info(&dvbdev->udev->dev, "will acquire and switch to %s\n",
 				 open_type == CXUSB_OPEN_ANALOG ?
 				 "analog" : "digital");
 
@@ -1476,7 +1473,7 @@ int cxusb_medion_get(struct dvb_usb_device *dvbdev,
 
 			cxdev->open_type = open_type;
 		} else {
-			deb_info("reacquired idle %s\n",
+			dev_info(&dvbdev->udev->dev, "reacquired idle %s\n",
 				 open_type == CXUSB_OPEN_ANALOG ?
 				 "analog" : "digital");
 		}
@@ -1484,8 +1481,8 @@ int cxusb_medion_get(struct dvb_usb_device *dvbdev,
 		cxdev->open_ctr = 1;
 	} else if (cxdev->open_type == open_type) {
 		cxdev->open_ctr++;
-		deb_info("acquired %s\n", open_type == CXUSB_OPEN_ANALOG ?
-			 "analog" : "digital");
+		dev_info(&dvbdev->udev->dev, "acquired %s\n",
+			 open_type == CXUSB_OPEN_ANALOG ? "analog" : "digital");
 	} else {
 		ret = -EBUSY;
 	}
@@ -1511,7 +1508,7 @@ void cxusb_medion_put(struct dvb_usb_device *dvbdev)
 	if (!WARN_ON(cxdev->open_ctr < 1)) {
 		cxdev->open_ctr--;
 
-		deb_info("release %s\n",
+		dev_info(&dvbdev->udev->dev, "release %s\n",
 			 cxdev->open_type == CXUSB_OPEN_ANALOG ?
 			 "analog" : "digital");
 	}
diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index ab7a100ec84f..4ef3fa98d20f 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -3772,8 +3772,8 @@ static int xbox_one_attach(struct dvb_usb_adapter *adap)
 	info.addr = 0x18;
 	info.platform_data = &mn88472_config;
 	request_module(info.type);
-	client_demod = i2c_new_device(&d->i2c_adap, &info);
-	if (client_demod == NULL || client_demod->dev.driver == NULL)
+	client_demod = i2c_new_client_device(&d->i2c_adap, &info);
+	if (!i2c_client_has_driver(client_demod))
 		goto fail_demod_device;
 	if (!try_module_get(client_demod->dev.driver->owner))
 		goto fail_demod_module;
@@ -3800,8 +3800,8 @@ static int xbox_one_attach(struct dvb_usb_adapter *adap)
 	info.platform_data = &tda18250_config;
 
 	request_module(info.type);
-	client_tuner = i2c_new_device(&adap->dev->i2c_adap, &info);
-	if (client_tuner == NULL || client_tuner->dev.driver == NULL)
+	client_tuner = i2c_new_client_device(&adap->dev->i2c_adap, &info);
+	if (!i2c_client_has_driver(client_tuner))
 		goto fail_tuner_device;
 	if (!try_module_get(client_tuner->dev.driver->owner))
 		goto fail_tuner_module;
diff --git a/drivers/media/usb/dvb-usb/digitv.c b/drivers/media/usb/dvb-usb/digitv.c
index dd5bb230cec1..99a39339d45d 100644
--- a/drivers/media/usb/dvb-usb/digitv.c
+++ b/drivers/media/usb/dvb-usb/digitv.c
@@ -230,18 +230,22 @@ static struct rc_map_table rc_map_digitv_table[] = {
 
 static int digitv_rc_query(struct dvb_usb_device *d, u32 *event, int *state)
 {
-	int i;
+	int ret, i;
 	u8 key[5];
 	u8 b[4] = { 0 };
 
 	*event = 0;
 	*state = REMOTE_NO_KEY_PRESSED;
 
-	digitv_ctrl_msg(d,USB_READ_REMOTE,0,NULL,0,&key[1],4);
+	ret = digitv_ctrl_msg(d, USB_READ_REMOTE, 0, NULL, 0, &key[1], 4);
+	if (ret)
+		return ret;
 
 	/* Tell the device we've read the remote. Not sure how necessary
 	   this is, but the Nebula SDK does it. */
-	digitv_ctrl_msg(d,USB_WRITE_REMOTE,0,b,4,NULL,0);
+	ret = digitv_ctrl_msg(d, USB_WRITE_REMOTE, 0, b, 4, NULL, 0);
+	if (ret)
+		return ret;
 
 	/* if something is inside the buffer, simulate key press */
 	if (key[1] != 0)
diff --git a/drivers/media/usb/dvb-usb/dvb-usb-urb.c b/drivers/media/usb/dvb-usb/dvb-usb-urb.c
index c1b4e94a37f8..2aabf90d8697 100644
--- a/drivers/media/usb/dvb-usb/dvb-usb-urb.c
+++ b/drivers/media/usb/dvb-usb/dvb-usb-urb.c
@@ -12,7 +12,7 @@
 int dvb_usb_generic_rw(struct dvb_usb_device *d, u8 *wbuf, u16 wlen, u8 *rbuf,
 	u16 rlen, int delay_ms)
 {
-	int actlen,ret = -ENOMEM;
+	int actlen = 0, ret = -ENOMEM;
 
 	if (!d || wbuf == NULL || wlen == 0)
 		return -EINVAL;
diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index b960abd00d48..8b584507dd59 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -1590,8 +1590,8 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
 	board_info.addr = 0x68;
 	board_info.platform_data = &m88ds3103_pdata;
 	request_module("m88ds3103");
-	client = i2c_new_device(&d->i2c_adap, &board_info);
-	if (client == NULL || client->dev.driver == NULL)
+	client = i2c_new_client_device(&d->i2c_adap, &board_info);
+	if (!i2c_client_has_driver(client))
 		return -ENODEV;
 	if (!try_module_get(client->dev.driver->owner)) {
 		i2c_unregister_device(client);
@@ -1609,9 +1609,9 @@ static int tt_s2_4600_frontend_attach(struct dvb_usb_adapter *adap)
 	board_info.addr = 0x60;
 	board_info.platform_data = &ts2020_config;
 	request_module("ts2020");
-	client = i2c_new_device(i2c_adapter, &board_info);
+	client = i2c_new_client_device(i2c_adapter, &board_info);
 
-	if (client == NULL || client->dev.driver == NULL) {
+	if (!i2c_client_has_driver(client)) {
 		dvb_frontend_detach(adap->fe_adap[0].fe);
 		return -ENODEV;
 	}
diff --git a/drivers/media/usb/dvb-usb/vp7045.c b/drivers/media/usb/dvb-usb/vp7045.c
index 80c1cf05384b..2baf57216d19 100644
--- a/drivers/media/usb/dvb-usb/vp7045.c
+++ b/drivers/media/usb/dvb-usb/vp7045.c
@@ -96,10 +96,14 @@ static int vp7045_power_ctrl(struct dvb_usb_device *d, int onoff)
 
 static int vp7045_rc_query(struct dvb_usb_device *d)
 {
+	int ret;
 	u8 key;
-	vp7045_usb_op(d,RC_VAL_READ,NULL,0,&key,1,20);
 
-	deb_rc("remote query key: %x %d\n",key,key);
+	ret = vp7045_usb_op(d, RC_VAL_READ, NULL, 0, &key, 1, 20);
+	if (ret)
+		return ret;
+
+	deb_rc("remote query key: %x\n", key);
 
 	if (key != 0x44) {
 		/*
@@ -115,15 +119,18 @@ static int vp7045_rc_query(struct dvb_usb_device *d)
 
 static int vp7045_read_eeprom(struct dvb_usb_device *d,u8 *buf, int len, int offset)
 {
-	int i = 0;
-	u8 v,br[2];
+	int i, ret;
+	u8 v, br[2];
 	for (i=0; i < len; i++) {
 		v = offset + i;
-		vp7045_usb_op(d,GET_EE_VALUE,&v,1,br,2,5);
+		ret = vp7045_usb_op(d, GET_EE_VALUE, &v, 1, br, 2, 5);
+		if (ret)
+			return ret;
+
 		buf[i] = br[1];
 	}
-	deb_info("VP7045 EEPROM read (offs: %d, len: %d) : ",offset, i);
-	debug_dump(buf,i,deb_info);
+	deb_info("VP7045 EEPROM read (offs: %d, len: %d) : ", offset, i);
+	debug_dump(buf, i, deb_info);
 	return 0;
 }
 
diff --git a/drivers/media/usb/em28xx/em28xx-audio.c b/drivers/media/usb/em28xx/em28xx-audio.c
index 79dfbb25714b..6833b5bfe293 100644
--- a/drivers/media/usb/em28xx/em28xx-audio.c
+++ b/drivers/media/usb/em28xx/em28xx-audio.c
@@ -30,7 +30,6 @@
 #include <linux/spinlock.h>
 #include <linux/soundcard.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
 #include <linux/module.h>
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -192,28 +191,6 @@ static int em28xx_init_audio_isoc(struct em28xx *dev)
 	return 0;
 }
 
-static int snd_pcm_alloc_vmalloc_buffer(struct snd_pcm_substream *subs,
-					size_t size)
-{
-	struct em28xx *dev = snd_pcm_substream_chip(subs);
-	struct snd_pcm_runtime *runtime = subs->runtime;
-
-	dprintk("Allocating vbuffer\n");
-	if (runtime->dma_area) {
-		if (runtime->dma_bytes > size)
-			return 0;
-
-		vfree(runtime->dma_area);
-	}
-	runtime->dma_area = vmalloc(size);
-	if (!runtime->dma_area)
-		return -ENOMEM;
-
-	runtime->dma_bytes = size;
-
-	return 0;
-}
-
 static const struct snd_pcm_hardware snd_em28xx_hw_capture = {
 	.info = SNDRV_PCM_INFO_BLOCK_TRANSFER |
 		SNDRV_PCM_INFO_MMAP           |
@@ -341,63 +318,12 @@ static int snd_em28xx_pcm_close(struct snd_pcm_substream *substream)
 	}
 
 	em28xx_audio_analog_set(dev);
-	if (substream->runtime->dma_area) {
-		dprintk("freeing\n");
-		vfree(substream->runtime->dma_area);
-		substream->runtime->dma_area = NULL;
-	}
 	mutex_unlock(&dev->lock);
 	kref_put(&dev->ref, em28xx_free_device);
 
 	return 0;
 }
 
-static int snd_em28xx_hw_capture_params(struct snd_pcm_substream *substream,
-					struct snd_pcm_hw_params *hw_params)
-{
-	int ret;
-	struct em28xx *dev = snd_pcm_substream_chip(substream);
-
-	if (dev->disconnected)
-		return -ENODEV;
-
-	dprintk("Setting capture parameters\n");
-
-	ret = snd_pcm_alloc_vmalloc_buffer(substream,
-					   params_buffer_bytes(hw_params));
-	if (ret < 0)
-		return ret;
-#if 0
-	/*
-	 * TODO: set up em28xx audio chip to deliver the correct audio format,
-	 * current default is 48000hz multiplexed => 96000hz mono
-	 * which shouldn't matter since analogue TV only supports mono
-	 */
-	unsigned int channels, rate, format;
-
-	format = params_format(hw_params);
-	rate = params_rate(hw_params);
-	channels = params_channels(hw_params);
-#endif
-
-	return 0;
-}
-
-static int snd_em28xx_hw_capture_free(struct snd_pcm_substream *substream)
-{
-	struct em28xx *dev = snd_pcm_substream_chip(substream);
-	struct em28xx_audio *adev = &dev->adev;
-
-	dprintk("Stop capture, if needed\n");
-
-	if (atomic_read(&adev->stream_started) > 0) {
-		atomic_set(&adev->stream_started, 0);
-		schedule_work(&adev->wq_trigger);
-	}
-
-	return 0;
-}
-
 static int snd_em28xx_prepare(struct snd_pcm_substream *substream)
 {
 	struct em28xx *dev = snd_pcm_substream_chip(substream);
@@ -471,14 +397,6 @@ static snd_pcm_uframes_t snd_em28xx_capture_pointer(struct snd_pcm_substream
 	return hwptr_done;
 }
 
-static struct page *snd_pcm_get_vmalloc_page(struct snd_pcm_substream *subs,
-					     unsigned long offset)
-{
-	void *pageptr = subs->runtime->dma_area + offset;
-
-	return vmalloc_to_page(pageptr);
-}
-
 /*
  * AC97 volume control support
  */
@@ -708,13 +626,9 @@ static int em28xx_cvol_new(struct snd_card *card, struct em28xx *dev,
 static const struct snd_pcm_ops snd_em28xx_pcm_capture = {
 	.open      = snd_em28xx_capture_open,
 	.close     = snd_em28xx_pcm_close,
-	.ioctl     = snd_pcm_lib_ioctl,
-	.hw_params = snd_em28xx_hw_capture_params,
-	.hw_free   = snd_em28xx_hw_capture_free,
 	.prepare   = snd_em28xx_prepare,
 	.trigger   = snd_em28xx_capture_trigger,
 	.pointer   = snd_em28xx_capture_pointer,
-	.page      = snd_pcm_get_vmalloc_page,
 };
 
 static void em28xx_audio_free_urb(struct em28xx *dev)
@@ -936,6 +850,7 @@ static int em28xx_audio_init(struct em28xx *dev)
 		goto card_free;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_em28xx_pcm_capture);
+	snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC, NULL, 0, 0);
 	pcm->info_flags = 0;
 	pcm->private_data = dev;
 	strscpy(pcm->name, "Empia 28xx Capture", sizeof(pcm->name));
diff --git a/drivers/media/usb/go7007/s2250-board.c b/drivers/media/usb/go7007/s2250-board.c
index 49e75a1a1f3f..b9e45124673b 100644
--- a/drivers/media/usb/go7007/s2250-board.c
+++ b/drivers/media/usb/go7007/s2250-board.c
@@ -607,6 +607,7 @@ static int s2250_remove(struct i2c_client *client)
 {
 	struct s2250 *state = to_state(i2c_get_clientdata(client));
 
+	i2c_unregister_device(state->audio);
 	v4l2_device_unregister_subdev(&state->sd);
 	v4l2_ctrl_handler_free(&state->hdl);
 	kfree(state);
diff --git a/drivers/media/usb/go7007/snd-go7007.c b/drivers/media/usb/go7007/snd-go7007.c
index b05fa227ffb2..2ce85ab38db5 100644
--- a/drivers/media/usb/go7007/snd-go7007.c
+++ b/drivers/media/usb/go7007/snd-go7007.c
@@ -9,7 +9,6 @@
 #include <linux/spinlock.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
-#include <linux/vmalloc.h>
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/i2c.h>
@@ -100,16 +99,7 @@ static int go7007_snd_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *hw_params)
 {
 	struct go7007 *go = snd_pcm_substream_chip(substream);
-	unsigned int bytes;
-
-	bytes = params_buffer_bytes(hw_params);
-	if (substream->runtime->dma_bytes > 0)
-		vfree(substream->runtime->dma_area);
-	substream->runtime->dma_bytes = 0;
-	substream->runtime->dma_area = vmalloc(bytes);
-	if (substream->runtime->dma_area == NULL)
-		return -ENOMEM;
-	substream->runtime->dma_bytes = bytes;
+
 	go->audio_deliver = parse_audio_stream_data;
 	return 0;
 }
@@ -119,9 +109,6 @@ static int go7007_snd_hw_free(struct snd_pcm_substream *substream)
 	struct go7007 *go = snd_pcm_substream_chip(substream);
 
 	go->audio_deliver = NULL;
-	if (substream->runtime->dma_bytes > 0)
-		vfree(substream->runtime->dma_area);
-	substream->runtime->dma_bytes = 0;
 	return 0;
 }
 
@@ -185,22 +172,14 @@ static snd_pcm_uframes_t go7007_snd_pcm_pointer(struct snd_pcm_substream *substr
 	return gosnd->hw_ptr;
 }
 
-static struct page *go7007_snd_pcm_page(struct snd_pcm_substream *substream,
-					unsigned long offset)
-{
-	return vmalloc_to_page(substream->runtime->dma_area + offset);
-}
-
 static const struct snd_pcm_ops go7007_snd_capture_ops = {
 	.open		= go7007_snd_capture_open,
 	.close		= go7007_snd_capture_close,
-	.ioctl		= snd_pcm_lib_ioctl,
 	.hw_params	= go7007_snd_hw_params,
 	.hw_free	= go7007_snd_hw_free,
 	.prepare	= go7007_snd_pcm_prepare,
 	.trigger	= go7007_snd_pcm_trigger,
 	.pointer	= go7007_snd_pcm_pointer,
-	.page		= go7007_snd_pcm_page,
 };
 
 static int go7007_snd_free(struct snd_device *device)
@@ -236,22 +215,18 @@ int go7007_snd_init(struct go7007 *go)
 	gosnd->capturing = 0;
 	ret = snd_card_new(go->dev, index[dev], id[dev], THIS_MODULE, 0,
 			   &gosnd->card);
-	if (ret < 0) {
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_snd;
+
 	ret = snd_device_new(gosnd->card, SNDRV_DEV_LOWLEVEL, go,
 			&go7007_snd_device_ops);
-	if (ret < 0) {
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
+
 	ret = snd_pcm_new(gosnd->card, "go7007", 0, 0, 1, &gosnd->pcm);
-	if (ret < 0) {
-		snd_card_free(gosnd->card);
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
+
 	strscpy(gosnd->card->driver, "go7007", sizeof(gosnd->card->driver));
 	strscpy(gosnd->card->shortname, go->name, sizeof(gosnd->card->shortname));
 	strscpy(gosnd->card->longname, gosnd->card->shortname,
@@ -260,13 +235,12 @@ int go7007_snd_init(struct go7007 *go)
 	gosnd->pcm->private_data = go;
 	snd_pcm_set_ops(gosnd->pcm, SNDRV_PCM_STREAM_CAPTURE,
 			&go7007_snd_capture_ops);
+	snd_pcm_set_managed_buffer_all(gosnd->pcm, SNDRV_DMA_TYPE_VMALLOC,
+				       NULL, 0, 0);
 
 	ret = snd_card_register(gosnd->card);
-	if (ret < 0) {
-		snd_card_free(gosnd->card);
-		kfree(gosnd);
-		return ret;
-	}
+	if (ret < 0)
+		goto free_card;
 
 	gosnd->substream = NULL;
 	go->snd_context = gosnd;
@@ -274,6 +248,12 @@ int go7007_snd_init(struct go7007 *go)
 	++dev;
 
 	return 0;
+
+free_card:
+	snd_card_free(gosnd->card);
+free_snd:
+	kfree(gosnd);
+	return ret;
 }
 EXPORT_SYMBOL(go7007_snd_init);
 
diff --git a/drivers/media/usb/gspca/gspca.c b/drivers/media/usb/gspca/gspca.c
index 4add2b12d330..c1b307bbe540 100644
--- a/drivers/media/usb/gspca/gspca.c
+++ b/drivers/media/usb/gspca/gspca.c
@@ -1461,7 +1461,7 @@ int gspca_dev_probe2(struct usb_interface *intf,
 		pr_err("couldn't kzalloc gspca struct\n");
 		return -ENOMEM;
 	}
-	gspca_dev->usb_buf = kmalloc(USB_BUF_SZ, GFP_KERNEL);
+	gspca_dev->usb_buf = kzalloc(USB_BUF_SZ, GFP_KERNEL);
 	if (!gspca_dev->usb_buf) {
 		pr_err("out of memory\n");
 		ret = -ENOMEM;
diff --git a/drivers/media/usb/pulse8-cec/pulse8-cec.c b/drivers/media/usb/pulse8-cec/pulse8-cec.c
index 59609556d969..afda438d4e0a 100644
--- a/drivers/media/usb/pulse8-cec/pulse8-cec.c
+++ b/drivers/media/usb/pulse8-cec/pulse8-cec.c
@@ -49,7 +49,7 @@ static int debug;
 static int persistent_config;
 module_param(debug, int, 0644);
 module_param(persistent_config, int, 0644);
-MODULE_PARM_DESC(debug, "debug level (0-1)");
+MODULE_PARM_DESC(debug, "debug level (0-2)");
 MODULE_PARM_DESC(persistent_config, "read config from persistent memory (0-1)");
 
 enum pulse8_msgcodes {
@@ -100,6 +100,61 @@ enum pulse8_msgcodes {
 	MSGCODE_FRAME_ACK = 0x40,
 };
 
+static const char * const pulse8_msgnames[] = {
+	"NOTHING",
+	"PING",
+	"TIMEOUT_ERROR",
+	"HIGH_ERROR",
+	"LOW_ERROR",
+	"FRAME_START",
+	"FRAME_DATA",
+	"RECEIVE_FAILED",
+	"COMMAND_ACCEPTED",
+	"COMMAND_REJECTED",
+	"SET_ACK_MASK",
+	"TRANSMIT",
+	"TRANSMIT_EOM",
+	"TRANSMIT_IDLETIME",
+	"TRANSMIT_ACK_POLARITY",
+	"TRANSMIT_LINE_TIMEOUT",
+	"TRANSMIT_SUCCEEDED",
+	"TRANSMIT_FAILED_LINE",
+	"TRANSMIT_FAILED_ACK",
+	"TRANSMIT_FAILED_TIMEOUT_DATA",
+	"TRANSMIT_FAILED_TIMEOUT_LINE",
+	"FIRMWARE_VERSION",
+	"START_BOOTLOADER",
+	"GET_BUILDDATE",
+	"SET_CONTROLLED",
+	"GET_AUTO_ENABLED",
+	"SET_AUTO_ENABLED",
+	"GET_DEFAULT_LOGICAL_ADDRESS",
+	"SET_DEFAULT_LOGICAL_ADDRESS",
+	"GET_LOGICAL_ADDRESS_MASK",
+	"SET_LOGICAL_ADDRESS_MASK",
+	"GET_PHYSICAL_ADDRESS",
+	"SET_PHYSICAL_ADDRESS",
+	"GET_DEVICE_TYPE",
+	"SET_DEVICE_TYPE",
+	"GET_HDMI_VERSION",
+	"SET_HDMI_VERSION",
+	"GET_OSD_NAME",
+	"SET_OSD_NAME",
+	"WRITE_EEPROM",
+	"GET_ADAPTER_TYPE",
+	"SET_ACTIVE_SOURCE",
+};
+
+static const char *pulse8_msgname(u8 cmd)
+{
+	static char unknown_msg[5];
+
+	if ((cmd & 0x3f) < ARRAY_SIZE(pulse8_msgnames))
+		return pulse8_msgnames[cmd & 0x3f];
+	snprintf(unknown_msg, sizeof(unknown_msg), "0x%02x", cmd);
+	return unknown_msg;
+}
+
 #define MSGSTART	0xff
 #define MSGEND		0xfe
 #define MSGESC		0xfd
@@ -109,60 +164,203 @@ enum pulse8_msgcodes {
 
 #define PING_PERIOD	(15 * HZ)
 
+#define NUM_MSGS 8
+
 struct pulse8 {
 	struct device *dev;
 	struct serio *serio;
 	struct cec_adapter *adap;
 	unsigned int vers;
-	struct completion cmd_done;
-	struct work_struct work;
-	u8 work_result;
+
 	struct delayed_work ping_eeprom_work;
-	struct cec_msg rx_msg;
+
+	struct work_struct irq_work;
+	struct cec_msg rx_msg[NUM_MSGS];
+	unsigned int rx_msg_cur_idx, rx_msg_num;
+	/* protect rx_msg_cur_idx and rx_msg_num */
+	spinlock_t msg_lock;
+	u8 new_rx_msg[CEC_MAX_MSG_SIZE];
+	u8 new_rx_msg_len;
+
+	struct work_struct tx_work;
+	u32 tx_done_status;
+	u32 tx_signal_free_time;
+	struct cec_msg tx_msg;
+	bool tx_msg_is_bcast;
+
+	struct completion cmd_done;
 	u8 data[DATA_SIZE];
 	unsigned int len;
 	u8 buf[DATA_SIZE];
 	unsigned int idx;
 	bool escape;
 	bool started;
-	struct mutex config_lock;
-	struct mutex write_lock;
+
+	/* locks access to the adapter */
+	struct mutex lock;
 	bool config_pending;
 	bool restoring_config;
 	bool autonomous;
 };
 
-static void pulse8_ping_eeprom_work_handler(struct work_struct *work);
+static int pulse8_send(struct serio *serio, const u8 *command, u8 cmd_len)
+{
+	int err = 0;
+
+	err = serio_write(serio, MSGSTART);
+	if (err)
+		return err;
+	for (; !err && cmd_len; command++, cmd_len--) {
+		if (*command >= MSGESC) {
+			err = serio_write(serio, MSGESC);
+			if (!err)
+				err = serio_write(serio, *command - MSGOFFSET);
+		} else {
+			err = serio_write(serio, *command);
+		}
+	}
+	if (!err)
+		err = serio_write(serio, MSGEND);
+
+	return err;
+}
+
+static int pulse8_send_and_wait_once(struct pulse8 *pulse8,
+				     const u8 *cmd, u8 cmd_len,
+				     u8 response, u8 size)
+{
+	int err;
+
+	if (debug > 1)
+		dev_info(pulse8->dev, "transmit %s: %*ph\n",
+			 pulse8_msgname(cmd[0]), cmd_len, cmd);
+	init_completion(&pulse8->cmd_done);
+
+	err = pulse8_send(pulse8->serio, cmd, cmd_len);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&pulse8->cmd_done, HZ))
+		return -ETIMEDOUT;
+	if ((pulse8->data[0] & 0x3f) == MSGCODE_COMMAND_REJECTED &&
+	    cmd[0] != MSGCODE_SET_CONTROLLED &&
+	    cmd[0] != MSGCODE_SET_AUTO_ENABLED &&
+	    cmd[0] != MSGCODE_GET_BUILDDATE)
+		return -ENOTTY;
+	if (response &&
+	    ((pulse8->data[0] & 0x3f) != response || pulse8->len < size + 1)) {
+		dev_info(pulse8->dev, "transmit %s failed with %s\n",
+			 pulse8_msgname(cmd[0]),
+			 pulse8_msgname(pulse8->data[0]));
+		return -EIO;
+	}
+	return 0;
+}
+
+static int pulse8_send_and_wait(struct pulse8 *pulse8,
+				const u8 *cmd, u8 cmd_len, u8 response, u8 size)
+{
+	u8 cmd_sc[2];
+	int err;
+
+	err = pulse8_send_and_wait_once(pulse8, cmd, cmd_len, response, size);
+	if (err != -ENOTTY)
+		return err;
+
+	cmd_sc[0] = MSGCODE_SET_CONTROLLED;
+	cmd_sc[1] = 1;
+	err = pulse8_send_and_wait_once(pulse8, cmd_sc, 2,
+					MSGCODE_COMMAND_ACCEPTED, 1);
+	if (!err)
+		err = pulse8_send_and_wait_once(pulse8, cmd, cmd_len,
+						response, size);
+	return err == -ENOTTY ? -EIO : err;
+}
+
+static void pulse8_tx_work_handler(struct work_struct *work)
+{
+	struct pulse8 *pulse8 = container_of(work, struct pulse8, tx_work);
+	struct cec_msg *msg = &pulse8->tx_msg;
+	unsigned int i;
+	u8 cmd[2];
+	int err;
+
+	if (msg->len == 0)
+		return;
+
+	mutex_lock(&pulse8->lock);
+	cmd[0] = MSGCODE_TRANSMIT_IDLETIME;
+	cmd[1] = pulse8->tx_signal_free_time;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 1);
+	cmd[0] = MSGCODE_TRANSMIT_ACK_POLARITY;
+	cmd[1] = cec_msg_is_broadcast(msg);
+	pulse8->tx_msg_is_bcast = cec_msg_is_broadcast(msg);
+	if (!err)
+		err = pulse8_send_and_wait(pulse8, cmd, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+	cmd[0] = msg->len == 1 ? MSGCODE_TRANSMIT_EOM : MSGCODE_TRANSMIT;
+	cmd[1] = msg->msg[0];
+	if (!err)
+		err = pulse8_send_and_wait(pulse8, cmd, 2,
+					   MSGCODE_COMMAND_ACCEPTED, 1);
+	if (!err && msg->len > 1) {
+		for (i = 1; !err && i < msg->len; i++) {
+			cmd[0] = ((i == msg->len - 1)) ?
+				MSGCODE_TRANSMIT_EOM : MSGCODE_TRANSMIT;
+			cmd[1] = msg->msg[i];
+			err = pulse8_send_and_wait(pulse8, cmd, 2,
+						   MSGCODE_COMMAND_ACCEPTED, 1);
+		}
+	}
+	if (err && debug)
+		dev_info(pulse8->dev, "%s(0x%02x) failed with error %d for msg %*ph\n",
+			 pulse8_msgname(cmd[0]), cmd[1],
+			 err, msg->len, msg->msg);
+	msg->len = 0;
+	mutex_unlock(&pulse8->lock);
+	if (err)
+		cec_transmit_attempt_done(pulse8->adap, CEC_TX_STATUS_ERROR);
+}
 
 static void pulse8_irq_work_handler(struct work_struct *work)
 {
 	struct pulse8 *pulse8 =
-		container_of(work, struct pulse8, work);
-	u8 result = pulse8->work_result;
+		container_of(work, struct pulse8, irq_work);
+	unsigned long flags;
+	u32 status;
 
-	pulse8->work_result = 0;
-	switch (result & 0x3f) {
-	case MSGCODE_FRAME_DATA:
-		cec_received_msg(pulse8->adap, &pulse8->rx_msg);
-		break;
-	case MSGCODE_TRANSMIT_SUCCEEDED:
-		cec_transmit_attempt_done(pulse8->adap, CEC_TX_STATUS_OK);
-		break;
-	case MSGCODE_TRANSMIT_FAILED_ACK:
-		cec_transmit_attempt_done(pulse8->adap, CEC_TX_STATUS_NACK);
-		break;
-	case MSGCODE_TRANSMIT_FAILED_LINE:
-	case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
-	case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
-		cec_transmit_attempt_done(pulse8->adap, CEC_TX_STATUS_ERROR);
-		break;
+	spin_lock_irqsave(&pulse8->msg_lock, flags);
+	while (pulse8->rx_msg_num) {
+		spin_unlock_irqrestore(&pulse8->msg_lock, flags);
+		if (debug)
+			dev_info(pulse8->dev, "adap received %*ph\n",
+				 pulse8->rx_msg[pulse8->rx_msg_cur_idx].len,
+				 pulse8->rx_msg[pulse8->rx_msg_cur_idx].msg);
+		cec_received_msg(pulse8->adap,
+				 &pulse8->rx_msg[pulse8->rx_msg_cur_idx]);
+		spin_lock_irqsave(&pulse8->msg_lock, flags);
+		if (pulse8->rx_msg_num)
+			pulse8->rx_msg_num--;
+		pulse8->rx_msg_cur_idx =
+			(pulse8->rx_msg_cur_idx + 1) % NUM_MSGS;
 	}
+	spin_unlock_irqrestore(&pulse8->msg_lock, flags);
+
+	mutex_lock(&pulse8->lock);
+	status = pulse8->tx_done_status;
+	pulse8->tx_done_status = 0;
+	mutex_unlock(&pulse8->lock);
+	if (status)
+		cec_transmit_attempt_done(pulse8->adap, status);
 }
 
 static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
 				    unsigned int flags)
 {
 	struct pulse8 *pulse8 = serio_get_drvdata(serio);
+	unsigned long irq_flags;
+	unsigned int idx;
 
 	if (!pulse8->started && data != MSGSTART)
 		return IRQ_HANDLED;
@@ -174,41 +372,80 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
 		data += MSGOFFSET;
 		pulse8->escape = false;
 	} else if (data == MSGEND) {
-		struct cec_msg *msg = &pulse8->rx_msg;
 		u8 msgcode = pulse8->buf[0];
 
-		if (debug)
-			dev_info(pulse8->dev, "received: %*ph\n",
+		if (debug > 1)
+			dev_info(pulse8->dev, "received %s: %*ph\n",
+				 pulse8_msgname(msgcode),
 				 pulse8->idx, pulse8->buf);
 		switch (msgcode & 0x3f) {
 		case MSGCODE_FRAME_START:
-			msg->len = 1;
-			msg->msg[0] = pulse8->buf[1];
-			break;
+			/*
+			 * Test if we are receiving a new msg when a previous
+			 * message is still pending.
+			 */
+			if (!(msgcode & MSGCODE_FRAME_EOM)) {
+				pulse8->new_rx_msg_len = 1;
+				pulse8->new_rx_msg[0] = pulse8->buf[1];
+				break;
+			}
+			/* fall through */
 		case MSGCODE_FRAME_DATA:
-			if (msg->len == CEC_MAX_MSG_SIZE)
+			if (pulse8->new_rx_msg_len < CEC_MAX_MSG_SIZE)
+				pulse8->new_rx_msg[pulse8->new_rx_msg_len++] =
+					pulse8->buf[1];
+			if (!(msgcode & MSGCODE_FRAME_EOM))
 				break;
-			msg->msg[msg->len++] = pulse8->buf[1];
-			if (msgcode & MSGCODE_FRAME_EOM) {
-				WARN_ON(pulse8->work_result);
-				pulse8->work_result = msgcode;
-				schedule_work(&pulse8->work);
+
+			spin_lock_irqsave(&pulse8->msg_lock, irq_flags);
+			idx = (pulse8->rx_msg_cur_idx + pulse8->rx_msg_num) %
+				NUM_MSGS;
+			if (pulse8->rx_msg_num == NUM_MSGS) {
+				dev_warn(pulse8->dev,
+					 "message queue is full, dropping %*ph\n",
+					 pulse8->new_rx_msg_len,
+					 pulse8->new_rx_msg);
+				spin_unlock_irqrestore(&pulse8->msg_lock,
+						       irq_flags);
+				pulse8->new_rx_msg_len = 0;
 				break;
 			}
+			pulse8->rx_msg_num++;
+			memcpy(pulse8->rx_msg[idx].msg, pulse8->new_rx_msg,
+			       pulse8->new_rx_msg_len);
+			pulse8->rx_msg[idx].len = pulse8->new_rx_msg_len;
+			spin_unlock_irqrestore(&pulse8->msg_lock, irq_flags);
+			schedule_work(&pulse8->irq_work);
+			pulse8->new_rx_msg_len = 0;
 			break;
 		case MSGCODE_TRANSMIT_SUCCEEDED:
-		case MSGCODE_TRANSMIT_FAILED_LINE:
+			WARN_ON(pulse8->tx_done_status);
+			pulse8->tx_done_status = CEC_TX_STATUS_OK;
+			schedule_work(&pulse8->irq_work);
+			break;
 		case MSGCODE_TRANSMIT_FAILED_ACK:
+			/*
+			 * A NACK for a broadcast message makes no sense, these
+			 * seem to be spurious messages and are skipped.
+			 */
+			if (pulse8->tx_msg_is_bcast)
+				break;
+			WARN_ON(pulse8->tx_done_status);
+			pulse8->tx_done_status = CEC_TX_STATUS_NACK;
+			schedule_work(&pulse8->irq_work);
+			break;
+		case MSGCODE_TRANSMIT_FAILED_LINE:
 		case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
 		case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
-			WARN_ON(pulse8->work_result);
-			pulse8->work_result = msgcode;
-			schedule_work(&pulse8->work);
+			WARN_ON(pulse8->tx_done_status);
+			pulse8->tx_done_status = CEC_TX_STATUS_ERROR;
+			schedule_work(&pulse8->irq_work);
 			break;
 		case MSGCODE_HIGH_ERROR:
 		case MSGCODE_LOW_ERROR:
 		case MSGCODE_RECEIVE_FAILED:
 		case MSGCODE_TIMEOUT_ERROR:
+			pulse8->new_rx_msg_len = 0;
 			break;
 		case MSGCODE_COMMAND_ACCEPTED:
 		case MSGCODE_COMMAND_REJECTED:
@@ -238,92 +475,183 @@ static irqreturn_t pulse8_interrupt(struct serio *serio, unsigned char data,
 	return IRQ_HANDLED;
 }
 
-static void pulse8_disconnect(struct serio *serio)
+static int pulse8_cec_adap_enable(struct cec_adapter *adap, bool enable)
 {
-	struct pulse8 *pulse8 = serio_get_drvdata(serio);
+	struct pulse8 *pulse8 = cec_get_drvdata(adap);
+	u8 cmd[16];
+	int err;
 
-	cec_unregister_adapter(pulse8->adap);
-	cancel_delayed_work_sync(&pulse8->ping_eeprom_work);
-	dev_info(&serio->dev, "disconnected\n");
-	serio_close(serio);
-	serio_set_drvdata(serio, NULL);
-	kfree(pulse8);
+	mutex_lock(&pulse8->lock);
+	cmd[0] = MSGCODE_SET_CONTROLLED;
+	cmd[1] = enable;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 1);
+	if (!enable) {
+		pulse8->rx_msg_num = 0;
+		pulse8->tx_done_status = 0;
+	}
+	mutex_unlock(&pulse8->lock);
+	return enable ? err : 0;
 }
 
-static int pulse8_send(struct serio *serio, const u8 *command, u8 cmd_len)
+static int pulse8_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
 {
+	struct pulse8 *pulse8 = cec_get_drvdata(adap);
+	u16 mask = 0;
+	u16 pa = adap->phys_addr;
+	u8 cmd[16];
 	int err = 0;
 
-	err = serio_write(serio, MSGSTART);
+	mutex_lock(&pulse8->lock);
+	if (log_addr != CEC_LOG_ADDR_INVALID)
+		mask = 1 << log_addr;
+	cmd[0] = MSGCODE_SET_ACK_MASK;
+	cmd[1] = mask >> 8;
+	cmd[2] = mask & 0xff;
+	err = pulse8_send_and_wait(pulse8, cmd, 3,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	if ((err && mask != 0) || pulse8->restoring_config)
+		goto unlock;
+
+	cmd[0] = MSGCODE_SET_AUTO_ENABLED;
+	cmd[1] = log_addr == CEC_LOG_ADDR_INVALID ? 0 : 1;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
 	if (err)
-		return err;
-	for (; !err && cmd_len; command++, cmd_len--) {
-		if (*command >= MSGESC) {
-			err = serio_write(serio, MSGESC);
-			if (!err)
-				err = serio_write(serio, *command - MSGOFFSET);
-		} else {
-			err = serio_write(serio, *command);
-		}
-	}
-	if (!err)
-		err = serio_write(serio, MSGEND);
+		goto unlock;
+	pulse8->autonomous = cmd[1];
+	if (log_addr == CEC_LOG_ADDR_INVALID)
+		goto unlock;
 
-	return err;
-}
+	cmd[0] = MSGCODE_SET_DEVICE_TYPE;
+	cmd[1] = adap->log_addrs.primary_device_type[0];
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	if (err)
+		goto unlock;
 
-static int pulse8_send_and_wait_once(struct pulse8 *pulse8,
-				     const u8 *cmd, u8 cmd_len,
-				     u8 response, u8 size)
-{
-	int err;
+	switch (adap->log_addrs.primary_device_type[0]) {
+	case CEC_OP_PRIM_DEVTYPE_TV:
+		mask = CEC_LOG_ADDR_MASK_TV;
+		break;
+	case CEC_OP_PRIM_DEVTYPE_RECORD:
+		mask = CEC_LOG_ADDR_MASK_RECORD;
+		break;
+	case CEC_OP_PRIM_DEVTYPE_TUNER:
+		mask = CEC_LOG_ADDR_MASK_TUNER;
+		break;
+	case CEC_OP_PRIM_DEVTYPE_PLAYBACK:
+		mask = CEC_LOG_ADDR_MASK_PLAYBACK;
+		break;
+	case CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM:
+		mask = CEC_LOG_ADDR_MASK_AUDIOSYSTEM;
+		break;
+	case CEC_OP_PRIM_DEVTYPE_SWITCH:
+		mask = CEC_LOG_ADDR_MASK_UNREGISTERED;
+		break;
+	case CEC_OP_PRIM_DEVTYPE_PROCESSOR:
+		mask = CEC_LOG_ADDR_MASK_SPECIFIC;
+		break;
+	default:
+		mask = 0;
+		break;
+	}
+	cmd[0] = MSGCODE_SET_LOGICAL_ADDRESS_MASK;
+	cmd[1] = mask >> 8;
+	cmd[2] = mask & 0xff;
+	err = pulse8_send_and_wait(pulse8, cmd, 3,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	if (err)
+		goto unlock;
 
-	/*dev_info(pulse8->dev, "transmit: %*ph\n", cmd_len, cmd);*/
-	init_completion(&pulse8->cmd_done);
+	cmd[0] = MSGCODE_SET_DEFAULT_LOGICAL_ADDRESS;
+	cmd[1] = log_addr;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	if (err)
+		goto unlock;
 
-	err = pulse8_send(pulse8->serio, cmd, cmd_len);
+	cmd[0] = MSGCODE_SET_PHYSICAL_ADDRESS;
+	cmd[1] = pa >> 8;
+	cmd[2] = pa & 0xff;
+	err = pulse8_send_and_wait(pulse8, cmd, 3,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
 	if (err)
-		return err;
+		goto unlock;
 
-	if (!wait_for_completion_timeout(&pulse8->cmd_done, HZ))
-		return -ETIMEDOUT;
-	if ((pulse8->data[0] & 0x3f) == MSGCODE_COMMAND_REJECTED &&
-	    cmd[0] != MSGCODE_SET_CONTROLLED &&
-	    cmd[0] != MSGCODE_SET_AUTO_ENABLED &&
-	    cmd[0] != MSGCODE_GET_BUILDDATE)
-		return -ENOTTY;
-	if (response &&
-	    ((pulse8->data[0] & 0x3f) != response || pulse8->len < size + 1)) {
-		dev_info(pulse8->dev, "transmit: failed %02x\n",
-			 pulse8->data[0] & 0x3f);
-		return -EIO;
+	cmd[0] = MSGCODE_SET_HDMI_VERSION;
+	cmd[1] = adap->log_addrs.cec_version;
+	err = pulse8_send_and_wait(pulse8, cmd, 2,
+				   MSGCODE_COMMAND_ACCEPTED, 0);
+	if (err)
+		goto unlock;
+
+	if (adap->log_addrs.osd_name[0]) {
+		size_t osd_len = strlen(adap->log_addrs.osd_name);
+		char *osd_str = cmd + 1;
+
+		cmd[0] = MSGCODE_SET_OSD_NAME;
+		strscpy(cmd + 1, adap->log_addrs.osd_name, sizeof(cmd) - 1);
+		if (osd_len < 4) {
+			memset(osd_str + osd_len, ' ', 4 - osd_len);
+			osd_len = 4;
+			osd_str[osd_len] = '\0';
+			strscpy(adap->log_addrs.osd_name, osd_str,
+				sizeof(adap->log_addrs.osd_name));
+		}
+		err = pulse8_send_and_wait(pulse8, cmd, 1 + osd_len,
+					   MSGCODE_COMMAND_ACCEPTED, 0);
+		if (err)
+			goto unlock;
 	}
+
+unlock:
+	if (pulse8->restoring_config)
+		pulse8->restoring_config = false;
+	else
+		pulse8->config_pending = true;
+	mutex_unlock(&pulse8->lock);
+	return log_addr == CEC_LOG_ADDR_INVALID ? 0 : err;
+}
+
+static int pulse8_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				    u32 signal_free_time, struct cec_msg *msg)
+{
+	struct pulse8 *pulse8 = cec_get_drvdata(adap);
+
+	pulse8->tx_msg = *msg;
+	if (debug)
+		dev_info(pulse8->dev, "adap transmit %*ph\n",
+			 msg->len, msg->msg);
+	pulse8->tx_signal_free_time = signal_free_time;
+	schedule_work(&pulse8->tx_work);
 	return 0;
 }
 
-static int pulse8_send_and_wait(struct pulse8 *pulse8,
-				const u8 *cmd, u8 cmd_len, u8 response, u8 size)
+static void pulse8_cec_adap_free(struct cec_adapter *adap)
 {
-	u8 cmd_sc[2];
-	int err;
+	struct pulse8 *pulse8 = cec_get_drvdata(adap);
 
-	mutex_lock(&pulse8->write_lock);
-	err = pulse8_send_and_wait_once(pulse8, cmd, cmd_len, response, size);
+	cancel_delayed_work_sync(&pulse8->ping_eeprom_work);
+	cancel_work_sync(&pulse8->irq_work);
+	cancel_work_sync(&pulse8->tx_work);
+	serio_close(pulse8->serio);
+	serio_set_drvdata(pulse8->serio, NULL);
+	kfree(pulse8);
+}
 
-	if (err == -ENOTTY) {
-		cmd_sc[0] = MSGCODE_SET_CONTROLLED;
-		cmd_sc[1] = 1;
-		err = pulse8_send_and_wait_once(pulse8, cmd_sc, 2,
-						MSGCODE_COMMAND_ACCEPTED, 1);
-		if (err)
-			goto unlock;
-		err = pulse8_send_and_wait_once(pulse8, cmd, cmd_len,
-						response, size);
-	}
+static const struct cec_adap_ops pulse8_cec_adap_ops = {
+	.adap_enable = pulse8_cec_adap_enable,
+	.adap_log_addr = pulse8_cec_adap_log_addr,
+	.adap_transmit = pulse8_cec_adap_transmit,
+	.adap_free = pulse8_cec_adap_free,
+};
 
-unlock:
-	mutex_unlock(&pulse8->write_lock);
-	return err == -ENOTTY ? -EIO : err;
+static void pulse8_disconnect(struct serio *serio)
+{
+	struct pulse8 *pulse8 = serio_get_drvdata(serio);
+
+	cec_unregister_adapter(pulse8->adap);
 }
 
 static int pulse8_setup(struct pulse8 *pulse8, struct serio *serio,
@@ -460,191 +788,34 @@ static int pulse8_apply_persistent_config(struct pulse8 *pulse8,
 	return 0;
 }
 
-static int pulse8_cec_adap_enable(struct cec_adapter *adap, bool enable)
-{
-	struct pulse8 *pulse8 = cec_get_drvdata(adap);
-	u8 cmd[16];
-	int err;
-
-	cmd[0] = MSGCODE_SET_CONTROLLED;
-	cmd[1] = enable;
-	err = pulse8_send_and_wait(pulse8, cmd, 2,
-				   MSGCODE_COMMAND_ACCEPTED, 1);
-	return enable ? err : 0;
-}
-
-static int pulse8_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
+static void pulse8_ping_eeprom_work_handler(struct work_struct *work)
 {
-	struct pulse8 *pulse8 = cec_get_drvdata(adap);
-	u16 mask = 0;
-	u16 pa = adap->phys_addr;
-	u8 cmd[16];
-	int err = 0;
-
-	mutex_lock(&pulse8->config_lock);
-	if (log_addr != CEC_LOG_ADDR_INVALID)
-		mask = 1 << log_addr;
-	cmd[0] = MSGCODE_SET_ACK_MASK;
-	cmd[1] = mask >> 8;
-	cmd[2] = mask & 0xff;
-	err = pulse8_send_and_wait(pulse8, cmd, 3,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if ((err && mask != 0) || pulse8->restoring_config)
-		goto unlock;
-
-	cmd[0] = MSGCODE_SET_AUTO_ENABLED;
-	cmd[1] = log_addr == CEC_LOG_ADDR_INVALID ? 0 : 1;
-	err = pulse8_send_and_wait(pulse8, cmd, 2,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if (err)
-		goto unlock;
-	pulse8->autonomous = cmd[1];
-	if (log_addr == CEC_LOG_ADDR_INVALID)
-		goto unlock;
-
-	cmd[0] = MSGCODE_SET_DEVICE_TYPE;
-	cmd[1] = adap->log_addrs.primary_device_type[0];
-	err = pulse8_send_and_wait(pulse8, cmd, 2,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if (err)
-		goto unlock;
-
-	switch (adap->log_addrs.primary_device_type[0]) {
-	case CEC_OP_PRIM_DEVTYPE_TV:
-		mask = CEC_LOG_ADDR_MASK_TV;
-		break;
-	case CEC_OP_PRIM_DEVTYPE_RECORD:
-		mask = CEC_LOG_ADDR_MASK_RECORD;
-		break;
-	case CEC_OP_PRIM_DEVTYPE_TUNER:
-		mask = CEC_LOG_ADDR_MASK_TUNER;
-		break;
-	case CEC_OP_PRIM_DEVTYPE_PLAYBACK:
-		mask = CEC_LOG_ADDR_MASK_PLAYBACK;
-		break;
-	case CEC_OP_PRIM_DEVTYPE_AUDIOSYSTEM:
-		mask = CEC_LOG_ADDR_MASK_AUDIOSYSTEM;
-		break;
-	case CEC_OP_PRIM_DEVTYPE_SWITCH:
-		mask = CEC_LOG_ADDR_MASK_UNREGISTERED;
-		break;
-	case CEC_OP_PRIM_DEVTYPE_PROCESSOR:
-		mask = CEC_LOG_ADDR_MASK_SPECIFIC;
-		break;
-	default:
-		mask = 0;
-		break;
-	}
-	cmd[0] = MSGCODE_SET_LOGICAL_ADDRESS_MASK;
-	cmd[1] = mask >> 8;
-	cmd[2] = mask & 0xff;
-	err = pulse8_send_and_wait(pulse8, cmd, 3,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if (err)
-		goto unlock;
-
-	cmd[0] = MSGCODE_SET_DEFAULT_LOGICAL_ADDRESS;
-	cmd[1] = log_addr;
-	err = pulse8_send_and_wait(pulse8, cmd, 2,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if (err)
-		goto unlock;
+	struct pulse8 *pulse8 =
+		container_of(work, struct pulse8, ping_eeprom_work.work);
+	u8 cmd;
 
-	cmd[0] = MSGCODE_SET_PHYSICAL_ADDRESS;
-	cmd[1] = pa >> 8;
-	cmd[2] = pa & 0xff;
-	err = pulse8_send_and_wait(pulse8, cmd, 3,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if (err)
-		goto unlock;
+	mutex_lock(&pulse8->lock);
+	cmd = MSGCODE_PING;
+	pulse8_send_and_wait(pulse8, &cmd, 1,
+			     MSGCODE_COMMAND_ACCEPTED, 0);
 
-	cmd[0] = MSGCODE_SET_HDMI_VERSION;
-	cmd[1] = adap->log_addrs.cec_version;
-	err = pulse8_send_and_wait(pulse8, cmd, 2,
-				   MSGCODE_COMMAND_ACCEPTED, 0);
-	if (err)
+	if (pulse8->vers < 2)
 		goto unlock;
 
-	if (adap->log_addrs.osd_name[0]) {
-		size_t osd_len = strlen(adap->log_addrs.osd_name);
-		char *osd_str = cmd + 1;
-
-		cmd[0] = MSGCODE_SET_OSD_NAME;
-		strscpy(cmd + 1, adap->log_addrs.osd_name, sizeof(cmd) - 1);
-		if (osd_len < 4) {
-			memset(osd_str + osd_len, ' ', 4 - osd_len);
-			osd_len = 4;
-			osd_str[osd_len] = '\0';
-			strscpy(adap->log_addrs.osd_name, osd_str,
-				sizeof(adap->log_addrs.osd_name));
-		}
-		err = pulse8_send_and_wait(pulse8, cmd, 1 + osd_len,
-					   MSGCODE_COMMAND_ACCEPTED, 0);
-		if (err)
-			goto unlock;
+	if (pulse8->config_pending && persistent_config) {
+		dev_dbg(pulse8->dev, "writing pending config to EEPROM\n");
+		cmd = MSGCODE_WRITE_EEPROM;
+		if (pulse8_send_and_wait(pulse8, &cmd, 1,
+					 MSGCODE_COMMAND_ACCEPTED, 0))
+			dev_info(pulse8->dev, "failed to write pending config to EEPROM\n");
+		else
+			pulse8->config_pending = false;
 	}
-
 unlock:
-	if (pulse8->restoring_config)
-		pulse8->restoring_config = false;
-	else
-		pulse8->config_pending = true;
-	mutex_unlock(&pulse8->config_lock);
-	return log_addr == CEC_LOG_ADDR_INVALID ? 0 : err;
-}
-
-static int pulse8_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
-				    u32 signal_free_time, struct cec_msg *msg)
-{
-	struct pulse8 *pulse8 = cec_get_drvdata(adap);
-	u8 cmd[2];
-	unsigned int i;
-	int err;
-
-	cmd[0] = MSGCODE_TRANSMIT_IDLETIME;
-	cmd[1] = signal_free_time;
-	err = pulse8_send_and_wait(pulse8, cmd, 2,
-				   MSGCODE_COMMAND_ACCEPTED, 1);
-	cmd[0] = MSGCODE_TRANSMIT_ACK_POLARITY;
-	cmd[1] = cec_msg_is_broadcast(msg);
-	if (!err)
-		err = pulse8_send_and_wait(pulse8, cmd, 2,
-					   MSGCODE_COMMAND_ACCEPTED, 1);
-	cmd[0] = msg->len == 1 ? MSGCODE_TRANSMIT_EOM : MSGCODE_TRANSMIT;
-	cmd[1] = msg->msg[0];
-	if (!err)
-		err = pulse8_send_and_wait(pulse8, cmd, 2,
-					   MSGCODE_COMMAND_ACCEPTED, 1);
-	if (!err && msg->len > 1) {
-		cmd[0] = msg->len == 2 ? MSGCODE_TRANSMIT_EOM :
-					 MSGCODE_TRANSMIT;
-		cmd[1] = msg->msg[1];
-		err = pulse8_send_and_wait(pulse8, cmd, 2,
-					   MSGCODE_COMMAND_ACCEPTED, 1);
-		for (i = 0; !err && i + 2 < msg->len; i++) {
-			cmd[0] = (i + 2 == msg->len - 1) ?
-				MSGCODE_TRANSMIT_EOM : MSGCODE_TRANSMIT;
-			cmd[1] = msg->msg[i + 2];
-			err = pulse8_send_and_wait(pulse8, cmd, 2,
-						   MSGCODE_COMMAND_ACCEPTED, 1);
-		}
-	}
-
-	return err;
-}
-
-static int pulse8_received(struct cec_adapter *adap, struct cec_msg *msg)
-{
-	return -ENOMSG;
+	schedule_delayed_work(&pulse8->ping_eeprom_work, PING_PERIOD);
+	mutex_unlock(&pulse8->lock);
 }
 
-static const struct cec_adap_ops pulse8_cec_adap_ops = {
-	.adap_enable = pulse8_cec_adap_enable,
-	.adap_log_addr = pulse8_cec_adap_log_addr,
-	.adap_transmit = pulse8_cec_adap_transmit,
-	.received = pulse8_received,
-};
-
 static int pulse8_connect(struct serio *serio, struct serio_driver *drv)
 {
 	u32 caps = CEC_CAP_DEFAULTS | CEC_CAP_PHYS_ADDR | CEC_CAP_MONITOR_ALL;
@@ -667,9 +838,10 @@ static int pulse8_connect(struct serio *serio, struct serio_driver *drv)
 
 	pulse8->dev = &serio->dev;
 	serio_set_drvdata(serio, pulse8);
-	INIT_WORK(&pulse8->work, pulse8_irq_work_handler);
-	mutex_init(&pulse8->write_lock);
-	mutex_init(&pulse8->config_lock);
+	INIT_WORK(&pulse8->irq_work, pulse8_irq_work_handler);
+	INIT_WORK(&pulse8->tx_work, pulse8_tx_work_handler);
+	mutex_init(&pulse8->lock);
+	spin_lock_init(&pulse8->msg_lock);
 	pulse8->config_pending = false;
 
 	err = serio_open(serio, drv);
@@ -709,33 +881,6 @@ free_device:
 	return err;
 }
 
-static void pulse8_ping_eeprom_work_handler(struct work_struct *work)
-{
-	struct pulse8 *pulse8 =
-		container_of(work, struct pulse8, ping_eeprom_work.work);
-	u8 cmd;
-
-	schedule_delayed_work(&pulse8->ping_eeprom_work, PING_PERIOD);
-	cmd = MSGCODE_PING;
-	pulse8_send_and_wait(pulse8, &cmd, 1,
-			     MSGCODE_COMMAND_ACCEPTED, 0);
-
-	if (pulse8->vers < 2)
-		return;
-
-	mutex_lock(&pulse8->config_lock);
-	if (pulse8->config_pending && persistent_config) {
-		dev_dbg(pulse8->dev, "writing pending config to EEPROM\n");
-		cmd = MSGCODE_WRITE_EEPROM;
-		if (pulse8_send_and_wait(pulse8, &cmd, 1,
-					 MSGCODE_COMMAND_ACCEPTED, 0))
-			dev_info(pulse8->dev, "failed to write pending config to EEPROM\n");
-		else
-			pulse8->config_pending = false;
-	}
-	mutex_unlock(&pulse8->config_lock);
-}
-
 static const struct serio_device_id pulse8_serio_ids[] = {
 	{
 		.type	= SERIO_RS232,
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-encoder.c b/drivers/media/usb/pvrusb2/pvrusb2-encoder.c
index fb3178d909ce..f6005d1296ef 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-encoder.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-encoder.c
@@ -284,8 +284,8 @@ rdData[0]);
 		wrData[0] = 0x0;
 		ret = pvr2_encoder_write_words(hdw,MBOX_BASE,wrData,1);
 		break;
-
-	}; LOCK_GIVE(hdw->ctl_lock);
+	}
+	LOCK_GIVE(hdw->ctl_lock);
 
 	return ret;
 }
diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c
index 21f90a887485..b22501f76b78 100644
--- a/drivers/media/usb/stkwebcam/stk-webcam.c
+++ b/drivers/media/usb/stkwebcam/stk-webcam.c
@@ -1125,7 +1125,7 @@ static int stk_vidioc_dqbuf(struct file *filp,
 	sbuf->v4lbuf.flags &= ~V4L2_BUF_FLAG_QUEUED;
 	sbuf->v4lbuf.flags |= V4L2_BUF_FLAG_DONE;
 	sbuf->v4lbuf.sequence = ++dev->sequence;
-	sbuf->v4lbuf.timestamp = ns_to_timeval(ktime_get_ns());
+	v4l2_buffer_set_timestamp(&sbuf->v4lbuf, ktime_get_ns());
 
 	*buf = sbuf->v4lbuf;
 	return 0;
diff --git a/drivers/media/usb/tm6000/tm6000-alsa.c b/drivers/media/usb/tm6000/tm6000-alsa.c
index d6c79c13b332..c26a0ff60a64 100644
--- a/drivers/media/usb/tm6000/tm6000-alsa.c
+++ b/drivers/media/usb/tm6000/tm6000-alsa.c
@@ -10,7 +10,6 @@
 #include <linux/interrupt.h>
 #include <linux/usb.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
 
 #include <linux/delay.h>
 #include <sound/core.h>
@@ -94,40 +93,6 @@ static int _tm6000_stop_audio_dma(struct snd_tm6000_card *chip)
 	return 0;
 }
 
-static void dsp_buffer_free(struct snd_pcm_substream *substream)
-{
-	struct snd_tm6000_card *chip = snd_pcm_substream_chip(substream);
-
-	dprintk(2, "Freeing buffer\n");
-
-	vfree(substream->runtime->dma_area);
-	substream->runtime->dma_area = NULL;
-	substream->runtime->dma_bytes = 0;
-}
-
-static int dsp_buffer_alloc(struct snd_pcm_substream *substream, int size)
-{
-	struct snd_tm6000_card *chip = snd_pcm_substream_chip(substream);
-
-	dprintk(2, "Allocating buffer\n");
-
-	if (substream->runtime->dma_area) {
-		if (substream->runtime->dma_bytes > size)
-			return 0;
-
-		dsp_buffer_free(substream);
-	}
-
-	substream->runtime->dma_area = vmalloc(size);
-	if (!substream->runtime->dma_area)
-		return -ENOMEM;
-
-	substream->runtime->dma_bytes = size;
-
-	return 0;
-}
-
-
 /****************************************************************************
 				ALSA PCM Interface
  ****************************************************************************/
@@ -269,40 +234,6 @@ static int tm6000_fillbuf(struct tm6000_core *core, char *buf, int size)
 }
 
 /*
- * hw_params callback
- */
-static int snd_tm6000_hw_params(struct snd_pcm_substream *substream,
-			      struct snd_pcm_hw_params *hw_params)
-{
-	int size, rc;
-
-	size = params_period_bytes(hw_params) * params_periods(hw_params);
-
-	rc = dsp_buffer_alloc(substream, size);
-	if (rc < 0)
-		return rc;
-
-	return 0;
-}
-
-/*
- * hw free callback
- */
-static int snd_tm6000_hw_free(struct snd_pcm_substream *substream)
-{
-	struct snd_tm6000_card *chip = snd_pcm_substream_chip(substream);
-	struct tm6000_core *core = chip->core;
-
-	if (atomic_read(&core->stream_started) > 0) {
-		atomic_set(&core->stream_started, 0);
-		schedule_work(&core->wq_trigger);
-	}
-
-	dsp_buffer_free(substream);
-	return 0;
-}
-
-/*
  * prepare callback
  */
 static int snd_tm6000_prepare(struct snd_pcm_substream *substream)
@@ -369,27 +300,15 @@ static snd_pcm_uframes_t snd_tm6000_pointer(struct snd_pcm_substream *substream)
 	return chip->buf_pos;
 }
 
-static struct page *snd_pcm_get_vmalloc_page(struct snd_pcm_substream *subs,
-					     unsigned long offset)
-{
-	void *pageptr = subs->runtime->dma_area + offset;
-
-	return vmalloc_to_page(pageptr);
-}
-
 /*
  * operators
  */
 static const struct snd_pcm_ops snd_tm6000_pcm_ops = {
 	.open = snd_tm6000_pcm_open,
 	.close = snd_tm6000_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = snd_tm6000_hw_params,
-	.hw_free = snd_tm6000_hw_free,
 	.prepare = snd_tm6000_prepare,
 	.trigger = snd_tm6000_card_trigger,
 	.pointer = snd_tm6000_pointer,
-	.page = snd_pcm_get_vmalloc_page,
 };
 
 /*
@@ -459,6 +378,7 @@ static int tm6000_audio_init(struct tm6000_core *dev)
 	strscpy(pcm->name, "Trident TM5600/60x0", sizeof(pcm->name));
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_tm6000_pcm_ops);
+	snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_VMALLOC, NULL, 0, 0);
 
 	INIT_WORK(&dev->wq_trigger, audio_trigger);
 	rc = snd_card_register(card);
diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index e746c8ddfc49..b57e94fb1977 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -85,30 +85,6 @@ static int snd_usbtv_pcm_close(struct snd_pcm_substream *substream)
 	return 0;
 }
 
-static int snd_usbtv_hw_params(struct snd_pcm_substream *substream,
-		struct snd_pcm_hw_params *hw_params)
-{
-	int rv;
-	struct usbtv *chip = snd_pcm_substream_chip(substream);
-
-	rv = snd_pcm_lib_malloc_pages(substream,
-		params_buffer_bytes(hw_params));
-
-	if (rv < 0) {
-		dev_warn(chip->dev, "pcm audio buffer allocation failure %i\n",
-			rv);
-		return rv;
-	}
-
-	return 0;
-}
-
-static int snd_usbtv_hw_free(struct snd_pcm_substream *substream)
-{
-	snd_pcm_lib_free_pages(substream);
-	return 0;
-}
-
 static int snd_usbtv_prepare(struct snd_pcm_substream *substream)
 {
 	struct usbtv *chip = snd_pcm_substream_chip(substream);
@@ -336,9 +312,6 @@ static snd_pcm_uframes_t snd_usbtv_pointer(struct snd_pcm_substream *substream)
 static const struct snd_pcm_ops snd_usbtv_pcm_ops = {
 	.open = snd_usbtv_pcm_open,
 	.close = snd_usbtv_pcm_close,
-	.ioctl = snd_pcm_lib_ioctl,
-	.hw_params = snd_usbtv_hw_params,
-	.hw_free = snd_usbtv_hw_free,
 	.prepare = snd_usbtv_prepare,
 	.trigger = snd_usbtv_card_trigger,
 	.pointer = snd_usbtv_pointer,
@@ -377,7 +350,7 @@ int usbtv_audio_init(struct usbtv *usbtv)
 	pcm->private_data = usbtv;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &snd_usbtv_pcm_ops);
-	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
+	snd_pcm_set_managed_buffer_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
 		NULL, USBTV_AUDIO_BUFFER, USBTV_AUDIO_BUFFER);
 
 	rv = snd_card_register(card);
diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c
index 93d36aab824f..5ca2c2f35fe2 100644
--- a/drivers/media/usb/usbvision/usbvision-video.c
+++ b/drivers/media/usb/usbvision/usbvision-video.c
@@ -696,7 +696,7 @@ static int vidioc_querybuf(struct file *file,
 	vb->length = usbvision->curwidth *
 		usbvision->curheight *
 		usbvision->palette.bytes_per_pixel;
-	vb->timestamp = ns_to_timeval(usbvision->frame[vb->index].ts);
+	v4l2_buffer_set_timestamp(vb, usbvision->frame[vb->index].ts);
 	vb->sequence = usbvision->frame[vb->index].sequence;
 	return 0;
 }
@@ -765,7 +765,7 @@ static int vidioc_dqbuf(struct file *file, void *priv, struct v4l2_buffer *vb)
 		V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vb->index = f->index;
 	vb->sequence = f->sequence;
-	vb->timestamp = ns_to_timeval(f->ts);
+	v4l2_buffer_set_timestamp(vb, f->ts);
 	vb->field = V4L2_FIELD_NONE;
 	vb->bytesused = f->scanlength;
 
diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 428235ca2635..99883550375e 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -497,6 +497,22 @@ static int uvc_parse_format(struct uvc_device *dev,
 			}
 		}
 
+		/* Some devices report bpp that doesn't match the format. */
+		if (dev->quirks & UVC_QUIRK_FORCE_BPP) {
+			const struct v4l2_format_info *info =
+				v4l2_format_info(format->fcc);
+
+			if (info) {
+				unsigned int div = info->hdiv * info->vdiv;
+
+				n = info->bpp[0] * div;
+				for (i = 1; i < info->comp_planes; i++)
+					n += info->bpp[i];
+
+				format->bpp = DIV_ROUND_UP(8 * n, div);
+			}
+		}
+
 		if (buffer[2] == UVC_VS_FORMAT_UNCOMPRESSED) {
 			ftype = UVC_VS_FRAME_UNCOMPRESSED;
 		} else {
@@ -1493,6 +1509,11 @@ static int uvc_scan_chain_forward(struct uvc_video_chain *chain,
 			break;
 		if (forward == prev)
 			continue;
+		if (forward->chain.next || forward->chain.prev) {
+			uvc_trace(UVC_TRACE_DESCR, "Found reference to "
+				"entity %d already in chain.\n", forward->id);
+			return -EINVAL;
+		}
 
 		switch (UVC_ENTITY_TYPE(forward)) {
 		case UVC_VC_EXTENSION_UNIT:
@@ -1574,6 +1595,13 @@ static int uvc_scan_chain_backward(struct uvc_video_chain *chain,
 				return -1;
 			}
 
+			if (term->chain.next || term->chain.prev) {
+				uvc_trace(UVC_TRACE_DESCR, "Found reference to "
+					"entity %d already in chain.\n",
+					term->id);
+				return -EINVAL;
+			}
+
 			if (uvc_trace_param & UVC_TRACE_PROBE)
 				printk(KERN_CONT " %d", term->id);
 
@@ -2862,6 +2890,15 @@ static const struct usb_device_id uvc_ids[] = {
 	  .bInterfaceSubClass	= 1,
 	  .bInterfaceProtocol	= 0,
 	  .driver_info		= (kernel_ulong_t)&uvc_quirk_force_y8 },
+	/* GEO Semiconductor GC6500 */
+	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
+				| USB_DEVICE_ID_MATCH_INT_INFO,
+	  .idVendor		= 0x29fe,
+	  .idProduct		= 0x4d53,
+	  .bInterfaceClass	= USB_CLASS_VIDEO,
+	  .bInterfaceSubClass	= 1,
+	  .bInterfaceProtocol	= 0,
+	  .driver_info		= UVC_INFO_QUIRK(UVC_QUIRK_FORCE_BPP) },
 	/* Intel RealSense D4M */
 	{ .match_flags		= USB_DEVICE_ID_MATCH_DEVICE
 				| USB_DEVICE_ID_MATCH_INT_INFO,
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index f773dc5d802c..6ab972c643e3 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -198,6 +198,7 @@
 #define UVC_QUIRK_RESTRICT_FRAME_RATE	0x00000200
 #define UVC_QUIRK_RESTORE_CTRLS_ON_INIT	0x00000400
 #define UVC_QUIRK_FORCE_Y8		0x00000800
+#define UVC_QUIRK_FORCE_BPP		0x00001000
 
 /* Format flags */
 #define UVC_FMT_FLAG_COMPRESSED		0x00000001
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index e1eaf1135c7f..a99e82ec9ab6 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -468,13 +468,43 @@ struct v4l2_plane32 {
 	__u32			reserved[11];
 };
 
+/*
+ * This is correct for all architectures including i386, but not x32,
+ * which has different alignment requirements for timestamp
+ */
 struct v4l2_buffer32 {
 	__u32			index;
 	__u32			type;	/* enum v4l2_buf_type */
 	__u32			bytesused;
 	__u32			flags;
 	__u32			field;	/* enum v4l2_field */
-	struct compat_timeval	timestamp;
+	struct {
+		compat_s64	tv_sec;
+		compat_s64	tv_usec;
+	}			timestamp;
+	struct v4l2_timecode	timecode;
+	__u32			sequence;
+
+	/* memory location */
+	__u32			memory;	/* enum v4l2_memory */
+	union {
+		__u32           offset;
+		compat_long_t   userptr;
+		compat_caddr_t  planes;
+		__s32		fd;
+	} m;
+	__u32			length;
+	__u32			reserved2;
+	__s32			request_fd;
+};
+
+struct v4l2_buffer32_time32 {
+	__u32			index;
+	__u32			type;	/* enum v4l2_buf_type */
+	__u32			bytesused;
+	__u32			flags;
+	__u32			field;	/* enum v4l2_field */
+	struct old_timeval32	timestamp;
 	struct v4l2_timecode	timecode;
 	__u32			sequence;
 
@@ -581,6 +611,31 @@ static int bufsize_v4l2_buffer(struct v4l2_buffer32 __user *p32, u32 *size)
 	return 0;
 }
 
+static int bufsize_v4l2_buffer_time32(struct v4l2_buffer32_time32 __user *p32, u32 *size)
+{
+	u32 type;
+	u32 length;
+
+	if (!access_ok(p32, sizeof(*p32)) ||
+	    get_user(type, &p32->type) ||
+	    get_user(length, &p32->length))
+		return -EFAULT;
+
+	if (V4L2_TYPE_IS_MULTIPLANAR(type)) {
+		if (length > VIDEO_MAX_PLANES)
+			return -EINVAL;
+
+		/*
+		 * We don't really care if userspace decides to kill itself
+		 * by passing a very big length value
+		 */
+		*size = length * sizeof(struct v4l2_plane);
+	} else {
+		*size = 0;
+	}
+	return 0;
+}
+
 static int get_v4l2_buffer32(struct v4l2_buffer __user *p64,
 			     struct v4l2_buffer32 __user *p32,
 			     void __user *aux_buf, u32 aux_space)
@@ -681,6 +736,106 @@ static int get_v4l2_buffer32(struct v4l2_buffer __user *p64,
 	return 0;
 }
 
+static int get_v4l2_buffer32_time32(struct v4l2_buffer_time32 __user *p64,
+				    struct v4l2_buffer32_time32 __user *p32,
+				    void __user *aux_buf, u32 aux_space)
+{
+	u32 type;
+	u32 length;
+	s32 request_fd;
+	enum v4l2_memory memory;
+	struct v4l2_plane32 __user *uplane32;
+	struct v4l2_plane __user *uplane;
+	compat_caddr_t p;
+	int ret;
+
+	if (!access_ok(p32, sizeof(*p32)) ||
+	    assign_in_user(&p64->index, &p32->index) ||
+	    get_user(type, &p32->type) ||
+	    put_user(type, &p64->type) ||
+	    assign_in_user(&p64->flags, &p32->flags) ||
+	    get_user(memory, &p32->memory) ||
+	    put_user(memory, &p64->memory) ||
+	    get_user(length, &p32->length) ||
+	    put_user(length, &p64->length) ||
+	    get_user(request_fd, &p32->request_fd) ||
+	    put_user(request_fd, &p64->request_fd))
+		return -EFAULT;
+
+	if (V4L2_TYPE_IS_OUTPUT(type))
+		if (assign_in_user(&p64->bytesused, &p32->bytesused) ||
+		    assign_in_user(&p64->field, &p32->field) ||
+		    assign_in_user(&p64->timestamp.tv_sec,
+				   &p32->timestamp.tv_sec) ||
+		    assign_in_user(&p64->timestamp.tv_usec,
+				   &p32->timestamp.tv_usec))
+			return -EFAULT;
+
+	if (V4L2_TYPE_IS_MULTIPLANAR(type)) {
+		u32 num_planes = length;
+
+		if (num_planes == 0) {
+			/*
+			 * num_planes == 0 is legal, e.g. when userspace doesn't
+			 * need planes array on DQBUF
+			 */
+			return put_user(NULL, &p64->m.planes);
+		}
+		if (num_planes > VIDEO_MAX_PLANES)
+			return -EINVAL;
+
+		if (get_user(p, &p32->m.planes))
+			return -EFAULT;
+
+		uplane32 = compat_ptr(p);
+		if (!access_ok(uplane32,
+			       num_planes * sizeof(*uplane32)))
+			return -EFAULT;
+
+		/*
+		 * We don't really care if userspace decides to kill itself
+		 * by passing a very big num_planes value
+		 */
+		if (aux_space < num_planes * sizeof(*uplane))
+			return -EFAULT;
+
+		uplane = aux_buf;
+		if (put_user_force(uplane, &p64->m.planes))
+			return -EFAULT;
+
+		while (num_planes--) {
+			ret = get_v4l2_plane32(uplane, uplane32, memory);
+			if (ret)
+				return ret;
+			uplane++;
+			uplane32++;
+		}
+	} else {
+		switch (memory) {
+		case V4L2_MEMORY_MMAP:
+		case V4L2_MEMORY_OVERLAY:
+			if (assign_in_user(&p64->m.offset, &p32->m.offset))
+				return -EFAULT;
+			break;
+		case V4L2_MEMORY_USERPTR: {
+			compat_ulong_t userptr;
+
+			if (get_user(userptr, &p32->m.userptr) ||
+			    put_user((unsigned long)compat_ptr(userptr),
+				     &p64->m.userptr))
+				return -EFAULT;
+			break;
+		}
+		case V4L2_MEMORY_DMABUF:
+			if (assign_in_user(&p64->m.fd, &p32->m.fd))
+				return -EFAULT;
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static int put_v4l2_buffer32(struct v4l2_buffer __user *p64,
 			     struct v4l2_buffer32 __user *p32)
 {
@@ -761,6 +916,86 @@ static int put_v4l2_buffer32(struct v4l2_buffer __user *p64,
 	return 0;
 }
 
+static int put_v4l2_buffer32_time32(struct v4l2_buffer_time32 __user *p64,
+				    struct v4l2_buffer32_time32 __user *p32)
+{
+	u32 type;
+	u32 length;
+	enum v4l2_memory memory;
+	struct v4l2_plane32 __user *uplane32;
+	struct v4l2_plane *uplane;
+	compat_caddr_t p;
+	int ret;
+
+	if (!access_ok(p32, sizeof(*p32)) ||
+	    assign_in_user(&p32->index, &p64->index) ||
+	    get_user(type, &p64->type) ||
+	    put_user(type, &p32->type) ||
+	    assign_in_user(&p32->flags, &p64->flags) ||
+	    get_user(memory, &p64->memory) ||
+	    put_user(memory, &p32->memory))
+		return -EFAULT;
+
+	if (assign_in_user(&p32->bytesused, &p64->bytesused) ||
+	    assign_in_user(&p32->field, &p64->field) ||
+	    assign_in_user(&p32->timestamp.tv_sec, &p64->timestamp.tv_sec) ||
+	    assign_in_user(&p32->timestamp.tv_usec, &p64->timestamp.tv_usec) ||
+	    copy_in_user(&p32->timecode, &p64->timecode, sizeof(p64->timecode)) ||
+	    assign_in_user(&p32->sequence, &p64->sequence) ||
+	    assign_in_user(&p32->reserved2, &p64->reserved2) ||
+	    assign_in_user(&p32->request_fd, &p64->request_fd) ||
+	    get_user(length, &p64->length) ||
+	    put_user(length, &p32->length))
+		return -EFAULT;
+
+	if (V4L2_TYPE_IS_MULTIPLANAR(type)) {
+		u32 num_planes = length;
+
+		if (num_planes == 0)
+			return 0;
+		/* We need to define uplane without __user, even though
+		 * it does point to data in userspace here. The reason is
+		 * that v4l2-ioctl.c copies it from userspace to kernelspace,
+		 * so its definition in videodev2.h doesn't have a
+		 * __user markup. Defining uplane with __user causes
+		 * smatch warnings, so instead declare it without __user
+		 * and cast it as a userspace pointer to put_v4l2_plane32().
+		 */
+		if (get_user(uplane, &p64->m.planes))
+			return -EFAULT;
+		if (get_user(p, &p32->m.planes))
+			return -EFAULT;
+		uplane32 = compat_ptr(p);
+
+		while (num_planes--) {
+			ret = put_v4l2_plane32((void __user *)uplane,
+					       uplane32, memory);
+			if (ret)
+				return ret;
+			++uplane;
+			++uplane32;
+		}
+	} else {
+		switch (memory) {
+		case V4L2_MEMORY_MMAP:
+		case V4L2_MEMORY_OVERLAY:
+			if (assign_in_user(&p32->m.offset, &p64->m.offset))
+				return -EFAULT;
+			break;
+		case V4L2_MEMORY_USERPTR:
+			if (assign_in_user(&p32->m.userptr, &p64->m.userptr))
+				return -EFAULT;
+			break;
+		case V4L2_MEMORY_DMABUF:
+			if (assign_in_user(&p32->m.fd, &p64->m.fd))
+				return -EFAULT;
+			break;
+		}
+	}
+
+	return 0;
+}
+
 struct v4l2_framebuffer32 {
 	__u32			capability;
 	__u32			flags;
@@ -1028,6 +1263,15 @@ static int put_v4l2_ext_controls32(struct file *file,
 	return 0;
 }
 
+#ifdef CONFIG_X86_64
+/*
+ * x86 is the only compat architecture with different struct alignment
+ * between 32-bit and 64-bit tasks.
+ *
+ * On all other architectures, v4l2_event32 and v4l2_event32_time32 are
+ * the same as v4l2_event and v4l2_event_time32, so we can use the native
+ * handlers, converting v4l2_event to v4l2_event_time32 if necessary.
+ */
 struct v4l2_event32 {
 	__u32				type;
 	union {
@@ -1036,7 +1280,23 @@ struct v4l2_event32 {
 	} u;
 	__u32				pending;
 	__u32				sequence;
-	struct compat_timespec		timestamp;
+	struct {
+		compat_s64		tv_sec;
+		compat_s64		tv_nsec;
+	} timestamp;
+	__u32				id;
+	__u32				reserved[8];
+};
+
+struct v4l2_event32_time32 {
+	__u32				type;
+	union {
+		compat_s64		value64;
+		__u8			data[64];
+	} u;
+	__u32				pending;
+	__u32				sequence;
+	struct old_timespec32		timestamp;
 	__u32				id;
 	__u32				reserved[8];
 };
@@ -1057,6 +1317,23 @@ static int put_v4l2_event32(struct v4l2_event __user *p64,
 	return 0;
 }
 
+static int put_v4l2_event32_time32(struct v4l2_event_time32 __user *p64,
+				   struct v4l2_event32_time32 __user *p32)
+{
+	if (!access_ok(p32, sizeof(*p32)) ||
+	    assign_in_user(&p32->type, &p64->type) ||
+	    copy_in_user(&p32->u, &p64->u, sizeof(p64->u)) ||
+	    assign_in_user(&p32->pending, &p64->pending) ||
+	    assign_in_user(&p32->sequence, &p64->sequence) ||
+	    assign_in_user(&p32->timestamp.tv_sec, &p64->timestamp.tv_sec) ||
+	    assign_in_user(&p32->timestamp.tv_nsec, &p64->timestamp.tv_nsec) ||
+	    assign_in_user(&p32->id, &p64->id) ||
+	    copy_in_user(p32->reserved, p64->reserved, sizeof(p32->reserved)))
+		return -EFAULT;
+	return 0;
+}
+#endif
+
 struct v4l2_edid32 {
 	__u32 pad;
 	__u32 start_block;
@@ -1108,10 +1385,13 @@ static int put_v4l2_edid32(struct v4l2_edid __user *p64,
 #define VIDIOC_G_FMT32		_IOWR('V',  4, struct v4l2_format32)
 #define VIDIOC_S_FMT32		_IOWR('V',  5, struct v4l2_format32)
 #define VIDIOC_QUERYBUF32	_IOWR('V',  9, struct v4l2_buffer32)
+#define VIDIOC_QUERYBUF32_TIME32 _IOWR('V',  9, struct v4l2_buffer32_time32)
 #define VIDIOC_G_FBUF32		_IOR ('V', 10, struct v4l2_framebuffer32)
 #define VIDIOC_S_FBUF32		_IOW ('V', 11, struct v4l2_framebuffer32)
 #define VIDIOC_QBUF32		_IOWR('V', 15, struct v4l2_buffer32)
+#define VIDIOC_QBUF32_TIME32	_IOWR('V', 15, struct v4l2_buffer32_time32)
 #define VIDIOC_DQBUF32		_IOWR('V', 17, struct v4l2_buffer32)
+#define VIDIOC_DQBUF32_TIME32	_IOWR('V', 17, struct v4l2_buffer32_time32)
 #define VIDIOC_ENUMSTD32	_IOWR('V', 25, struct v4l2_standard32)
 #define VIDIOC_ENUMINPUT32	_IOWR('V', 26, struct v4l2_input32)
 #define VIDIOC_G_EDID32		_IOWR('V', 40, struct v4l2_edid32)
@@ -1121,8 +1401,10 @@ static int put_v4l2_edid32(struct v4l2_edid __user *p64,
 #define VIDIOC_S_EXT_CTRLS32    _IOWR('V', 72, struct v4l2_ext_controls32)
 #define VIDIOC_TRY_EXT_CTRLS32  _IOWR('V', 73, struct v4l2_ext_controls32)
 #define	VIDIOC_DQEVENT32	_IOR ('V', 89, struct v4l2_event32)
+#define	VIDIOC_DQEVENT32_TIME32	_IOR ('V', 89, struct v4l2_event32_time32)
 #define VIDIOC_CREATE_BUFS32	_IOWR('V', 92, struct v4l2_create_buffers32)
 #define VIDIOC_PREPARE_BUF32	_IOWR('V', 93, struct v4l2_buffer32)
+#define VIDIOC_PREPARE_BUF32_TIME32 _IOWR('V', 93, struct v4l2_buffer32_time32)
 
 #define VIDIOC_OVERLAY32	_IOW ('V', 14, s32)
 #define VIDIOC_STREAMON32	_IOW ('V', 18, s32)
@@ -1183,36 +1465,45 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	u32 aux_space;
 	int compatible_arg = 1;
 	long err = 0;
+	unsigned int ncmd;
 
 	/*
 	 * 1. When struct size is different, converts the command.
 	 */
 	switch (cmd) {
-	case VIDIOC_G_FMT32: cmd = VIDIOC_G_FMT; break;
-	case VIDIOC_S_FMT32: cmd = VIDIOC_S_FMT; break;
-	case VIDIOC_QUERYBUF32: cmd = VIDIOC_QUERYBUF; break;
-	case VIDIOC_G_FBUF32: cmd = VIDIOC_G_FBUF; break;
-	case VIDIOC_S_FBUF32: cmd = VIDIOC_S_FBUF; break;
-	case VIDIOC_QBUF32: cmd = VIDIOC_QBUF; break;
-	case VIDIOC_DQBUF32: cmd = VIDIOC_DQBUF; break;
-	case VIDIOC_ENUMSTD32: cmd = VIDIOC_ENUMSTD; break;
-	case VIDIOC_ENUMINPUT32: cmd = VIDIOC_ENUMINPUT; break;
-	case VIDIOC_TRY_FMT32: cmd = VIDIOC_TRY_FMT; break;
-	case VIDIOC_G_EXT_CTRLS32: cmd = VIDIOC_G_EXT_CTRLS; break;
-	case VIDIOC_S_EXT_CTRLS32: cmd = VIDIOC_S_EXT_CTRLS; break;
-	case VIDIOC_TRY_EXT_CTRLS32: cmd = VIDIOC_TRY_EXT_CTRLS; break;
-	case VIDIOC_DQEVENT32: cmd = VIDIOC_DQEVENT; break;
-	case VIDIOC_OVERLAY32: cmd = VIDIOC_OVERLAY; break;
-	case VIDIOC_STREAMON32: cmd = VIDIOC_STREAMON; break;
-	case VIDIOC_STREAMOFF32: cmd = VIDIOC_STREAMOFF; break;
-	case VIDIOC_G_INPUT32: cmd = VIDIOC_G_INPUT; break;
-	case VIDIOC_S_INPUT32: cmd = VIDIOC_S_INPUT; break;
-	case VIDIOC_G_OUTPUT32: cmd = VIDIOC_G_OUTPUT; break;
-	case VIDIOC_S_OUTPUT32: cmd = VIDIOC_S_OUTPUT; break;
-	case VIDIOC_CREATE_BUFS32: cmd = VIDIOC_CREATE_BUFS; break;
-	case VIDIOC_PREPARE_BUF32: cmd = VIDIOC_PREPARE_BUF; break;
-	case VIDIOC_G_EDID32: cmd = VIDIOC_G_EDID; break;
-	case VIDIOC_S_EDID32: cmd = VIDIOC_S_EDID; break;
+	case VIDIOC_G_FMT32: ncmd = VIDIOC_G_FMT; break;
+	case VIDIOC_S_FMT32: ncmd = VIDIOC_S_FMT; break;
+	case VIDIOC_QUERYBUF32: ncmd = VIDIOC_QUERYBUF; break;
+	case VIDIOC_QUERYBUF32_TIME32: ncmd = VIDIOC_QUERYBUF_TIME32; break;
+	case VIDIOC_G_FBUF32: ncmd = VIDIOC_G_FBUF; break;
+	case VIDIOC_S_FBUF32: ncmd = VIDIOC_S_FBUF; break;
+	case VIDIOC_QBUF32: ncmd = VIDIOC_QBUF; break;
+	case VIDIOC_QBUF32_TIME32: ncmd = VIDIOC_QBUF_TIME32; break;
+	case VIDIOC_DQBUF32: ncmd = VIDIOC_DQBUF; break;
+	case VIDIOC_DQBUF32_TIME32: ncmd = VIDIOC_DQBUF_TIME32; break;
+	case VIDIOC_ENUMSTD32: ncmd = VIDIOC_ENUMSTD; break;
+	case VIDIOC_ENUMINPUT32: ncmd = VIDIOC_ENUMINPUT; break;
+	case VIDIOC_TRY_FMT32: ncmd = VIDIOC_TRY_FMT; break;
+	case VIDIOC_G_EXT_CTRLS32: ncmd = VIDIOC_G_EXT_CTRLS; break;
+	case VIDIOC_S_EXT_CTRLS32: ncmd = VIDIOC_S_EXT_CTRLS; break;
+	case VIDIOC_TRY_EXT_CTRLS32: ncmd = VIDIOC_TRY_EXT_CTRLS; break;
+#ifdef CONFIG_X86_64
+	case VIDIOC_DQEVENT32: ncmd = VIDIOC_DQEVENT; break;
+	case VIDIOC_DQEVENT32_TIME32: ncmd = VIDIOC_DQEVENT_TIME32; break;
+#endif
+	case VIDIOC_OVERLAY32: ncmd = VIDIOC_OVERLAY; break;
+	case VIDIOC_STREAMON32: ncmd = VIDIOC_STREAMON; break;
+	case VIDIOC_STREAMOFF32: ncmd = VIDIOC_STREAMOFF; break;
+	case VIDIOC_G_INPUT32: ncmd = VIDIOC_G_INPUT; break;
+	case VIDIOC_S_INPUT32: ncmd = VIDIOC_S_INPUT; break;
+	case VIDIOC_G_OUTPUT32: ncmd = VIDIOC_G_OUTPUT; break;
+	case VIDIOC_S_OUTPUT32: ncmd = VIDIOC_S_OUTPUT; break;
+	case VIDIOC_CREATE_BUFS32: ncmd = VIDIOC_CREATE_BUFS; break;
+	case VIDIOC_PREPARE_BUF32: ncmd = VIDIOC_PREPARE_BUF; break;
+	case VIDIOC_PREPARE_BUF32_TIME32: ncmd = VIDIOC_PREPARE_BUF_TIME32; break;
+	case VIDIOC_G_EDID32: ncmd = VIDIOC_G_EDID; break;
+	case VIDIOC_S_EDID32: ncmd = VIDIOC_S_EDID; break;
+	default: ncmd = cmd; break;
 	}
 
 	/*
@@ -1221,11 +1512,11 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * argument into it.
 	 */
 	switch (cmd) {
-	case VIDIOC_OVERLAY:
-	case VIDIOC_STREAMON:
-	case VIDIOC_STREAMOFF:
-	case VIDIOC_S_INPUT:
-	case VIDIOC_S_OUTPUT:
+	case VIDIOC_OVERLAY32:
+	case VIDIOC_STREAMON32:
+	case VIDIOC_STREAMOFF32:
+	case VIDIOC_S_INPUT32:
+	case VIDIOC_S_OUTPUT32:
 		err = alloc_userspace(sizeof(unsigned int), 0, &new_p64);
 		if (!err && assign_in_user((unsigned int __user *)new_p64,
 					   (compat_uint_t __user *)p32))
@@ -1233,23 +1524,23 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_INPUT:
-	case VIDIOC_G_OUTPUT:
+	case VIDIOC_G_INPUT32:
+	case VIDIOC_G_OUTPUT32:
 		err = alloc_userspace(sizeof(unsigned int), 0, &new_p64);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_EDID:
-	case VIDIOC_S_EDID:
+	case VIDIOC_G_EDID32:
+	case VIDIOC_S_EDID32:
 		err = alloc_userspace(sizeof(struct v4l2_edid), 0, &new_p64);
 		if (!err)
 			err = get_v4l2_edid32(new_p64, p32);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_FMT:
-	case VIDIOC_S_FMT:
-	case VIDIOC_TRY_FMT:
+	case VIDIOC_G_FMT32:
+	case VIDIOC_S_FMT32:
+	case VIDIOC_TRY_FMT32:
 		err = bufsize_v4l2_format(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_format),
@@ -1262,7 +1553,7 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_CREATE_BUFS:
+	case VIDIOC_CREATE_BUFS32:
 		err = bufsize_v4l2_create(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_create_buffers),
@@ -1275,10 +1566,10 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_PREPARE_BUF:
-	case VIDIOC_QUERYBUF:
-	case VIDIOC_QBUF:
-	case VIDIOC_DQBUF:
+	case VIDIOC_PREPARE_BUF32:
+	case VIDIOC_QUERYBUF32:
+	case VIDIOC_QBUF32:
+	case VIDIOC_DQBUF32:
 		err = bufsize_v4l2_buffer(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_buffer),
@@ -1291,7 +1582,23 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_S_FBUF:
+	case VIDIOC_PREPARE_BUF32_TIME32:
+	case VIDIOC_QUERYBUF32_TIME32:
+	case VIDIOC_QBUF32_TIME32:
+	case VIDIOC_DQBUF32_TIME32:
+		err = bufsize_v4l2_buffer_time32(p32, &aux_space);
+		if (!err)
+			err = alloc_userspace(sizeof(struct v4l2_buffer),
+					      aux_space, &new_p64);
+		if (!err) {
+			aux_buf = new_p64 + sizeof(struct v4l2_buffer);
+			err = get_v4l2_buffer32_time32(new_p64, p32,
+						       aux_buf, aux_space);
+		}
+		compatible_arg = 0;
+		break;
+
+	case VIDIOC_S_FBUF32:
 		err = alloc_userspace(sizeof(struct v4l2_framebuffer), 0,
 				      &new_p64);
 		if (!err)
@@ -1299,13 +1606,13 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_FBUF:
+	case VIDIOC_G_FBUF32:
 		err = alloc_userspace(sizeof(struct v4l2_framebuffer), 0,
 				      &new_p64);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_ENUMSTD:
+	case VIDIOC_ENUMSTD32:
 		err = alloc_userspace(sizeof(struct v4l2_standard), 0,
 				      &new_p64);
 		if (!err)
@@ -1313,16 +1620,16 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_ENUMINPUT:
+	case VIDIOC_ENUMINPUT32:
 		err = alloc_userspace(sizeof(struct v4l2_input), 0, &new_p64);
 		if (!err)
 			err = get_v4l2_input32(new_p64, p32);
 		compatible_arg = 0;
 		break;
 
-	case VIDIOC_G_EXT_CTRLS:
-	case VIDIOC_S_EXT_CTRLS:
-	case VIDIOC_TRY_EXT_CTRLS:
+	case VIDIOC_G_EXT_CTRLS32:
+	case VIDIOC_S_EXT_CTRLS32:
+	case VIDIOC_TRY_EXT_CTRLS32:
 		err = bufsize_v4l2_ext_controls(p32, &aux_space);
 		if (!err)
 			err = alloc_userspace(sizeof(struct v4l2_ext_controls),
@@ -1334,10 +1641,16 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 		}
 		compatible_arg = 0;
 		break;
-	case VIDIOC_DQEVENT:
+#ifdef CONFIG_X86_64
+	case VIDIOC_DQEVENT32:
 		err = alloc_userspace(sizeof(struct v4l2_event), 0, &new_p64);
 		compatible_arg = 0;
 		break;
+	case VIDIOC_DQEVENT32_TIME32:
+		err = alloc_userspace(sizeof(struct v4l2_event_time32), 0, &new_p64);
+		compatible_arg = 0;
+		break;
+#endif
 	}
 	if (err)
 		return err;
@@ -1352,9 +1665,9 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * Otherwise, it will pass the newly allocated @new_p64 argument.
 	 */
 	if (compatible_arg)
-		err = native_ioctl(file, cmd, (unsigned long)p32);
+		err = native_ioctl(file, ncmd, (unsigned long)p32);
 	else
-		err = native_ioctl(file, cmd, (unsigned long)new_p64);
+		err = native_ioctl(file, ncmd, (unsigned long)new_p64);
 
 	if (err == -ENOTTY)
 		return err;
@@ -1370,13 +1683,13 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * the blocks to maximum allowed value.
 	 */
 	switch (cmd) {
-	case VIDIOC_G_EXT_CTRLS:
-	case VIDIOC_S_EXT_CTRLS:
-	case VIDIOC_TRY_EXT_CTRLS:
+	case VIDIOC_G_EXT_CTRLS32:
+	case VIDIOC_S_EXT_CTRLS32:
+	case VIDIOC_TRY_EXT_CTRLS32:
 		if (put_v4l2_ext_controls32(file, new_p64, p32))
 			err = -EFAULT;
 		break;
-	case VIDIOC_S_EDID:
+	case VIDIOC_S_EDID32:
 		if (put_v4l2_edid32(new_p64, p32))
 			err = -EFAULT;
 		break;
@@ -1389,49 +1702,62 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	 * the original 32 bits structure.
 	 */
 	switch (cmd) {
-	case VIDIOC_S_INPUT:
-	case VIDIOC_S_OUTPUT:
-	case VIDIOC_G_INPUT:
-	case VIDIOC_G_OUTPUT:
+	case VIDIOC_S_INPUT32:
+	case VIDIOC_S_OUTPUT32:
+	case VIDIOC_G_INPUT32:
+	case VIDIOC_G_OUTPUT32:
 		if (assign_in_user((compat_uint_t __user *)p32,
 				   ((unsigned int __user *)new_p64)))
 			err = -EFAULT;
 		break;
 
-	case VIDIOC_G_FBUF:
+	case VIDIOC_G_FBUF32:
 		err = put_v4l2_framebuffer32(new_p64, p32);
 		break;
 
-	case VIDIOC_DQEVENT:
+#ifdef CONFIG_X86_64
+	case VIDIOC_DQEVENT32:
 		err = put_v4l2_event32(new_p64, p32);
 		break;
 
-	case VIDIOC_G_EDID:
+	case VIDIOC_DQEVENT32_TIME32:
+		err = put_v4l2_event32_time32(new_p64, p32);
+		break;
+#endif
+
+	case VIDIOC_G_EDID32:
 		err = put_v4l2_edid32(new_p64, p32);
 		break;
 
-	case VIDIOC_G_FMT:
-	case VIDIOC_S_FMT:
-	case VIDIOC_TRY_FMT:
+	case VIDIOC_G_FMT32:
+	case VIDIOC_S_FMT32:
+	case VIDIOC_TRY_FMT32:
 		err = put_v4l2_format32(new_p64, p32);
 		break;
 
-	case VIDIOC_CREATE_BUFS:
+	case VIDIOC_CREATE_BUFS32:
 		err = put_v4l2_create32(new_p64, p32);
 		break;
 
-	case VIDIOC_PREPARE_BUF:
-	case VIDIOC_QUERYBUF:
-	case VIDIOC_QBUF:
-	case VIDIOC_DQBUF:
+	case VIDIOC_PREPARE_BUF32:
+	case VIDIOC_QUERYBUF32:
+	case VIDIOC_QBUF32:
+	case VIDIOC_DQBUF32:
 		err = put_v4l2_buffer32(new_p64, p32);
 		break;
 
-	case VIDIOC_ENUMSTD:
+	case VIDIOC_PREPARE_BUF32_TIME32:
+	case VIDIOC_QUERYBUF32_TIME32:
+	case VIDIOC_QBUF32_TIME32:
+	case VIDIOC_DQBUF32_TIME32:
+		err = put_v4l2_buffer32_time32(new_p64, p32);
+		break;
+
+	case VIDIOC_ENUMSTD32:
 		err = put_v4l2_standard32(new_p64, p32);
 		break;
 
-	case VIDIOC_ENUMINPUT:
+	case VIDIOC_ENUMINPUT32:
 		err = put_v4l2_input32(new_p64, p32);
 		break;
 	}
diff --git a/drivers/media/v4l2-core/v4l2-event.c b/drivers/media/v4l2-core/v4l2-event.c
index 9d673d113d7a..290c6b213179 100644
--- a/drivers/media/v4l2-core/v4l2-event.c
+++ b/drivers/media/v4l2-core/v4l2-event.c
@@ -27,6 +27,7 @@ static unsigned sev_pos(const struct v4l2_subscribed_event *sev, unsigned idx)
 static int __v4l2_event_dequeue(struct v4l2_fh *fh, struct v4l2_event *event)
 {
 	struct v4l2_kevent *kev;
+	struct timespec64 ts;
 	unsigned long flags;
 
 	spin_lock_irqsave(&fh->vdev->fh_lock, flags);
@@ -44,7 +45,9 @@ static int __v4l2_event_dequeue(struct v4l2_fh *fh, struct v4l2_event *event)
 
 	kev->event.pending = fh->navailable;
 	*event = kev->event;
-	event->timestamp = ns_to_timespec(kev->ts);
+	ts = ns_to_timespec64(kev->ts);
+	event->timestamp.tv_sec = ts.tv_sec;
+	event->timestamp.tv_nsec = ts.tv_nsec;
 	kev->sev->first = sev_pos(kev->sev, 1);
 	kev->sev->in_use--;
 
diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c
index 192cac076761..6ece4320e1d2 100644
--- a/drivers/media/v4l2-core/v4l2-fwnode.c
+++ b/drivers/media/v4l2-core/v4l2-fwnode.c
@@ -422,7 +422,7 @@ static int __v4l2_fwnode_endpoint_parse(struct fwnode_handle *fwnode,
 		       sizeof(*vep) - offsetof(typeof(*vep), bus));
 	}
 
-	pr_debug("===== begin V4L2 endpoint properties\n");
+	pr_debug("===== begin parsing endpoint %pfw\n", fwnode);
 
 	/*
 	 * Zero the fwnode graph endpoint memory in case we don't end up parsing
@@ -500,7 +500,7 @@ int v4l2_fwnode_endpoint_parse(struct fwnode_handle *fwnode,
 
 	ret = __v4l2_fwnode_endpoint_parse(fwnode, vep);
 
-	pr_debug("===== end V4L2 endpoint properties\n");
+	pr_debug("===== end parsing endpoint %pfw\n", fwnode);
 
 	return ret;
 }
@@ -551,7 +551,7 @@ int v4l2_fwnode_endpoint_alloc_parse(struct fwnode_handle *fwnode,
 				vep->link_frequencies[i]);
 	}
 
-	pr_debug("===== end V4L2 endpoint properties\n");
+	pr_debug("===== end parsing endpoint %pfw\n", fwnode);
 
 	return 0;
 }
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 003b7422aeef..aaf83e254272 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -474,10 +474,10 @@ static void v4l_print_buffer(const void *arg, bool write_only)
 	const struct v4l2_plane *plane;
 	int i;
 
-	pr_cont("%02ld:%02d:%02d.%08ld index=%d, type=%s, request_fd=%d, flags=0x%08x, field=%s, sequence=%d, memory=%s",
-			p->timestamp.tv_sec / 3600,
-			(int)(p->timestamp.tv_sec / 60) % 60,
-			(int)(p->timestamp.tv_sec % 60),
+	pr_cont("%02d:%02d:%02d.%09ld index=%d, type=%s, request_fd=%d, flags=0x%08x, field=%s, sequence=%d, memory=%s",
+			(int)p->timestamp.tv_sec / 3600,
+			((int)p->timestamp.tv_sec / 60) % 60,
+			((int)p->timestamp.tv_sec % 60),
 			(long)p->timestamp.tv_usec,
 			p->index,
 			prt_names(p->type, v4l2_type_names), p->request_fd,
@@ -821,7 +821,7 @@ static void v4l_print_event(const void *arg, bool write_only)
 	const struct v4l2_event *p = arg;
 	const struct v4l2_event_ctrl *c;
 
-	pr_cont("type=0x%x, pending=%u, sequence=%u, id=%u, timestamp=%lu.%9.9lu\n",
+	pr_cont("type=0x%x, pending=%u, sequence=%u, id=%u, timestamp=%llu.%9.9llu\n",
 			p->type, p->pending, p->sequence, p->id,
 			p->timestamp.tv_sec, p->timestamp.tv_nsec);
 	switch (p->type) {
@@ -961,7 +961,7 @@ static int check_fmt(struct file *file, enum v4l2_buf_type type)
 			return 0;
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
-		if (is_vid && is_rx && ops->vidioc_g_fmt_vid_cap_mplane)
+		if ((is_vid || is_tch) && is_rx && ops->vidioc_g_fmt_vid_cap_mplane)
 			return 0;
 		break;
 	case V4L2_BUF_TYPE_VIDEO_OVERLAY:
@@ -3023,8 +3023,162 @@ static int check_array_args(unsigned int cmd, void *parg, size_t *array_size,
 	return ret;
 }
 
+static unsigned int video_translate_cmd(unsigned int cmd)
+{
+	switch (cmd) {
+#ifdef CONFIG_COMPAT_32BIT_TIME
+	case VIDIOC_DQEVENT_TIME32:
+		return VIDIOC_DQEVENT;
+	case VIDIOC_QUERYBUF_TIME32:
+		return VIDIOC_QUERYBUF;
+	case VIDIOC_QBUF_TIME32:
+		return VIDIOC_QBUF;
+	case VIDIOC_DQBUF_TIME32:
+		return VIDIOC_DQBUF;
+	case VIDIOC_PREPARE_BUF_TIME32:
+		return VIDIOC_PREPARE_BUF;
+#endif
+	}
+
+	return cmd;
+}
+
+static int video_get_user(void __user *arg, void *parg, unsigned int cmd,
+			  bool *always_copy)
+{
+	unsigned int n = _IOC_SIZE(cmd);
+
+	if (!(_IOC_DIR(cmd) & _IOC_WRITE)) {
+		/* read-only ioctl */
+		memset(parg, 0, n);
+		return 0;
+	}
+
+	switch (cmd) {
+#ifdef CONFIG_COMPAT_32BIT_TIME
+	case VIDIOC_QUERYBUF_TIME32:
+	case VIDIOC_QBUF_TIME32:
+	case VIDIOC_DQBUF_TIME32:
+	case VIDIOC_PREPARE_BUF_TIME32: {
+		struct v4l2_buffer_time32 vb32;
+		struct v4l2_buffer *vb = parg;
+
+		if (copy_from_user(&vb32, arg, sizeof(vb32)))
+			return -EFAULT;
+
+		*vb = (struct v4l2_buffer) {
+			.index		= vb32.index,
+			.type		= vb32.type,
+			.bytesused	= vb32.bytesused,
+			.flags		= vb32.flags,
+			.field		= vb32.field,
+			.timestamp.tv_sec	= vb32.timestamp.tv_sec,
+			.timestamp.tv_usec	= vb32.timestamp.tv_usec,
+			.timecode	= vb32.timecode,
+			.sequence	= vb32.sequence,
+			.memory		= vb32.memory,
+			.m.userptr	= vb32.m.userptr,
+			.length		= vb32.length,
+			.request_fd	= vb32.request_fd,
+		};
+
+		if (cmd == VIDIOC_QUERYBUF_TIME32)
+			vb->request_fd = 0;
+
+		break;
+	}
+#endif
+	default:
+		/*
+		 * In some cases, only a few fields are used as input,
+		 * i.e. when the app sets "index" and then the driver
+		 * fills in the rest of the structure for the thing
+		 * with that index.  We only need to copy up the first
+		 * non-input field.
+		 */
+		if (v4l2_is_known_ioctl(cmd)) {
+			u32 flags = v4l2_ioctls[_IOC_NR(cmd)].flags;
+
+			if (flags & INFO_FL_CLEAR_MASK)
+				n = (flags & INFO_FL_CLEAR_MASK) >> 16;
+			*always_copy = flags & INFO_FL_ALWAYS_COPY;
+		}
+
+		if (copy_from_user(parg, (void __user *)arg, n))
+			return -EFAULT;
+
+		/* zero out anything we don't copy from userspace */
+		if (n < _IOC_SIZE(cmd))
+			memset((u8 *)parg + n, 0, _IOC_SIZE(cmd) - n);
+		break;
+	}
+
+	return 0;
+}
+
+static int video_put_user(void __user *arg, void *parg, unsigned int cmd)
+{
+	if (!(_IOC_DIR(cmd) & _IOC_READ))
+		return 0;
+
+	switch (cmd) {
+#ifdef CONFIG_COMPAT_32BIT_TIME
+	case VIDIOC_DQEVENT_TIME32: {
+		struct v4l2_event *ev = parg;
+		struct v4l2_event_time32 ev32 = {
+			.type		= ev->type,
+			.pending	= ev->pending,
+			.sequence	= ev->sequence,
+			.timestamp.tv_sec  = ev->timestamp.tv_sec,
+			.timestamp.tv_nsec = ev->timestamp.tv_nsec,
+			.id		= ev->id,
+		};
+
+		memcpy(&ev32.u, &ev->u, sizeof(ev->u));
+		memcpy(&ev32.reserved, &ev->reserved, sizeof(ev->reserved));
+
+		if (copy_to_user(arg, &ev32, sizeof(ev32)))
+			return -EFAULT;
+		break;
+	}
+	case VIDIOC_QUERYBUF_TIME32:
+	case VIDIOC_QBUF_TIME32:
+	case VIDIOC_DQBUF_TIME32:
+	case VIDIOC_PREPARE_BUF_TIME32: {
+		struct v4l2_buffer *vb = parg;
+		struct v4l2_buffer_time32 vb32 = {
+			.index		= vb->index,
+			.type		= vb->type,
+			.bytesused	= vb->bytesused,
+			.flags		= vb->flags,
+			.field		= vb->field,
+			.timestamp.tv_sec	= vb->timestamp.tv_sec,
+			.timestamp.tv_usec	= vb->timestamp.tv_usec,
+			.timecode	= vb->timecode,
+			.sequence	= vb->sequence,
+			.memory		= vb->memory,
+			.m.userptr	= vb->m.userptr,
+			.length		= vb->length,
+			.request_fd	= vb->request_fd,
+		};
+
+		if (copy_to_user(arg, &vb32, sizeof(vb32)))
+			return -EFAULT;
+		break;
+	}
+#endif
+	default:
+		/*  Copy results into user buffer  */
+		if (copy_to_user(arg, parg, _IOC_SIZE(cmd)))
+			return -EFAULT;
+		break;
+	}
+
+	return 0;
+}
+
 long
-video_usercopy(struct file *file, unsigned int cmd, unsigned long arg,
+video_usercopy(struct file *file, unsigned int orig_cmd, unsigned long arg,
 	       v4l2_kioctl func)
 {
 	char	sbuf[128];
@@ -3036,6 +3190,7 @@ video_usercopy(struct file *file, unsigned int cmd, unsigned long arg,
 	size_t  array_size = 0;
 	void __user *user_ptr = NULL;
 	void	**kernel_ptr = NULL;
+	unsigned int cmd = video_translate_cmd(orig_cmd);
 	const size_t ioc_size = _IOC_SIZE(cmd);
 
 	/*  Copy arguments into temp kernel buffer  */
@@ -3050,35 +3205,10 @@ video_usercopy(struct file *file, unsigned int cmd, unsigned long arg,
 			parg = mbuf;
 		}
 
-		err = -EFAULT;
-		if (_IOC_DIR(cmd) & _IOC_WRITE) {
-			unsigned int n = ioc_size;
-
-			/*
-			 * In some cases, only a few fields are used as input,
-			 * i.e. when the app sets "index" and then the driver
-			 * fills in the rest of the structure for the thing
-			 * with that index.  We only need to copy up the first
-			 * non-input field.
-			 */
-			if (v4l2_is_known_ioctl(cmd)) {
-				u32 flags = v4l2_ioctls[_IOC_NR(cmd)].flags;
-
-				if (flags & INFO_FL_CLEAR_MASK)
-					n = (flags & INFO_FL_CLEAR_MASK) >> 16;
-				always_copy = flags & INFO_FL_ALWAYS_COPY;
-			}
-
-			if (copy_from_user(parg, (void __user *)arg, n))
-				goto out;
-
-			/* zero out anything we don't copy from userspace */
-			if (n < ioc_size)
-				memset((u8 *)parg + n, 0, ioc_size - n);
-		} else {
-			/* read-only ioctl */
-			memset(parg, 0, ioc_size);
-		}
+		err = video_get_user((void __user *)arg, parg, orig_cmd,
+				     &always_copy);
+		if (err)
+			goto out;
 	}
 
 	err = check_array_args(cmd, parg, &array_size, &user_ptr, &kernel_ptr);
@@ -3131,15 +3261,8 @@ video_usercopy(struct file *file, unsigned int cmd, unsigned long arg,
 		goto out;
 
 out_array_args:
-	/*  Copy results into user buffer  */
-	switch (_IOC_DIR(cmd)) {
-	case _IOC_READ:
-	case (_IOC_WRITE | _IOC_READ):
-		if (copy_to_user((void __user *)arg, parg, ioc_size))
-			err = -EFAULT;
-		break;
-	}
-
+	if (video_put_user((void __user *)arg, parg, orig_cmd))
+		err = -EFAULT;
 out:
 	kvfree(mbuf);
 	return err;
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 9e987c0f840e..a376b351135f 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -331,8 +331,8 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 	struct v4l2_fh *vfh = file->private_data;
 #if defined(CONFIG_VIDEO_V4L2_SUBDEV_API)
 	struct v4l2_subdev_fh *subdev_fh = to_v4l2_subdev_fh(vfh);
-	int rval;
 #endif
+	int rval;
 
 	switch (cmd) {
 	case VIDIOC_QUERYCTRL:
@@ -392,6 +392,30 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 
 		return v4l2_event_dequeue(vfh, arg, file->f_flags & O_NONBLOCK);
 
+	case VIDIOC_DQEVENT_TIME32: {
+		struct v4l2_event_time32 *ev32 = arg;
+		struct v4l2_event ev = { };
+
+		if (!(sd->flags & V4L2_SUBDEV_FL_HAS_EVENTS))
+			return -ENOIOCTLCMD;
+
+		rval = v4l2_event_dequeue(vfh, &ev, file->f_flags & O_NONBLOCK);
+
+		*ev32 = (struct v4l2_event_time32) {
+			.type		= ev.type,
+			.pending	= ev.pending,
+			.sequence	= ev.sequence,
+			.timestamp.tv_sec  = ev.timestamp.tv_sec,
+			.timestamp.tv_nsec = ev.timestamp.tv_nsec,
+			.id		= ev.id,
+		};
+
+		memcpy(&ev32->u, &ev.u, sizeof(ev.u));
+		memcpy(&ev32->reserved, &ev.reserved, sizeof(ev.reserved));
+
+		return rval;
+	}
+
 	case VIDIOC_SUBSCRIBE_EVENT:
 		return v4l2_subdev_call(sd, core, subscribe_event, vfh, arg);
 
diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c
index 939fc11cf080..2686f03b322e 100644
--- a/drivers/media/v4l2-core/videobuf-core.c
+++ b/drivers/media/v4l2-core/videobuf-core.c
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 
 #include <media/videobuf-core.h>
+#include <media/v4l2-common.h>
 
 #define MAGIC_BUFFER 0x20070728
 #define MAGIC_CHECK(is, should)						\
@@ -364,7 +365,7 @@ static void videobuf_status(struct videobuf_queue *q, struct v4l2_buffer *b,
 	}
 
 	b->field     = vb->field;
-	b->timestamp = ns_to_timeval(vb->ts);
+	v4l2_buffer_set_timestamp(b, vb->ts);
 	b->bytesused = vb->size;
 	b->sequence  = vb->field_count >> 1;
 }
@@ -578,7 +579,7 @@ int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b)
 		    || q->type == V4L2_BUF_TYPE_SDR_OUTPUT) {
 			buf->size = b->bytesused;
 			buf->field = b->field;
-			buf->ts = v4l2_timeval_to_ns(&b->timestamp);
+			buf->ts = v4l2_buffer_get_timestamp(b);
 		}
 		break;
 	case V4L2_MEMORY_USERPTR:
diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c
index 66a6c6c236a7..13b65ed9e74c 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -183,12 +183,12 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma,
 	dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n",
 		data, size, dma->nr_pages);
 
-	err = get_user_pages(data & PAGE_MASK, dma->nr_pages,
+	err = pin_user_pages(data & PAGE_MASK, dma->nr_pages,
 			     flags | FOLL_LONGTERM, dma->pages, NULL);
 
 	if (err != dma->nr_pages) {
 		dma->nr_pages = (err >= 0) ? err : 0;
-		dprintk(1, "get_user_pages: err=%d [%d]\n", err,
+		dprintk(1, "pin_user_pages: err=%d [%d]\n", err,
 			dma->nr_pages);
 		return err < 0 ? err : -EINVAL;
 	}
@@ -349,8 +349,8 @@ int videobuf_dma_free(struct videobuf_dmabuf *dma)
 	BUG_ON(dma->sglen);
 
 	if (dma->pages) {
-		for (i = 0; i < dma->nr_pages; i++)
-			put_page(dma->pages[i]);
+		unpin_user_pages_dirty_lock(dma->pages, dma->nr_pages,
+					    dma->direction == DMA_FROM_DEVICE);
 		kfree(dma->pages);
 		dma->pages = NULL;
 	}
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 420900852166..2b203290e7b9 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -758,6 +758,7 @@ config MFD_MAX77650
 	depends on OF || COMPILE_TEST
 	select MFD_CORE
 	select REGMAP_I2C
+	select REGMAP_IRQ
 	help
 	  Say Y here to add support for Maxim Semiconductor MAX77650 and
 	  MAX77651 Power Management ICs. This is the core multifunction
@@ -1065,7 +1066,7 @@ config MFD_RN5T618
 	  functionality of the device.
 
 config MFD_SEC_CORE
-	tristate "SAMSUNG Electronics PMIC Series Support"
+	tristate "Samsung Electronics PMIC Series Support"
 	depends on I2C=y
 	select MFD_CORE
 	select REGMAP_I2C
@@ -1906,6 +1907,21 @@ config MFD_ROHM_BD70528
 	  10 bits SAR ADC for battery temperature monitor and 1S battery
 	  charger.
 
+config MFD_ROHM_BD71828
+	tristate "ROHM BD71828 Power Management IC"
+	depends on I2C=y
+	depends on OF
+	select REGMAP_I2C
+	select REGMAP_IRQ
+	select MFD_CORE
+	help
+	  Select this option to get support for the ROHM BD71828 Power
+	  Management IC. BD71828GW is a single-chip power management IC for
+	  battery-powered portable devices. The IC integrates 7 buck
+	  converters, 7 LDOs, and a 1500 mA single-cell linear charger.
+	  Also included is a Coulomb counter, a real-time clock (RTC), and
+	  a 32.768 kHz clock gate.
+
 config MFD_STM32_LPTIMER
 	tristate "Support for STM32 Low-Power Timer"
 	depends on (ARCH_STM32 && OF) || COMPILE_TEST
@@ -1960,6 +1976,18 @@ config MFD_STMFX
 	  additional drivers must be enabled in order to use the functionality
 	  of the device.
 
+config MFD_WCD934X
+	tristate "Support for WCD9340/WCD9341 Codec"
+	depends on SLIMBUS
+	select REGMAP
+	select REGMAP_SLIMBUS
+	select REGMAP_IRQ
+	select MFD_CORE
+	help
+	  Support for the Qualcomm WCD9340/WCD9341 Codec.
+	  This driver provides common support WCD934x audio codec and its
+	  associated Pin Controller, Soundwire Controller and Audio codec.
+
 menu "Multimedia Capabilities Port drivers"
 	depends on ARCH_SA1100
 
@@ -2004,5 +2032,18 @@ config RAVE_SP_CORE
 	  Select this to get support for the Supervisory Processor
 	  device found on several devices in RAVE line of hardware.
 
+config SGI_MFD_IOC3
+	tristate "SGI IOC3 core driver"
+	depends on PCI && MIPS && 64BIT
+	select MFD_CORE
+	help
+	  This option enables basic support for the SGI IOC3-based
+	  controller cards.  This option does not enable any specific
+	  functions on such a card, but provides necessary infrastructure
+	  for other drivers to utilize.
+
+	  If you have an SGI Origin, Octane, or a PCI IOC3 card,
+	  then say Y. Otherwise say N.
+
 endmenu
 endif
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index aed99f08739f..b83f172545e1 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -58,6 +58,7 @@ endif
 ifeq ($(CONFIG_MFD_CS47L24),y)
 obj-$(CONFIG_MFD_ARIZONA)	+= cs47l24-tables.o
 endif
+obj-$(CONFIG_MFD_WCD934X)	+= wcd934x.o
 obj-$(CONFIG_MFD_WM8400)	+= wm8400-core.o
 wm831x-objs			:= wm831x-core.o wm831x-irq.o wm831x-otp.o
 wm831x-objs			+= wm831x-auxadc.o
@@ -252,6 +253,8 @@ obj-$(CONFIG_MFD_MXS_LRADC)     += mxs-lradc.o
 obj-$(CONFIG_MFD_SC27XX_PMIC)	+= sprd-sc27xx-spi.o
 obj-$(CONFIG_RAVE_SP_CORE)	+= rave-sp.o
 obj-$(CONFIG_MFD_ROHM_BD70528)	+= rohm-bd70528.o
+obj-$(CONFIG_MFD_ROHM_BD71828)	+= rohm-bd71828.o
 obj-$(CONFIG_MFD_ROHM_BD718XX)	+= rohm-bd718x7.o
 obj-$(CONFIG_MFD_STMFX) 	+= stmfx.o
 
+obj-$(CONFIG_SGI_MFD_IOC3)	+= ioc3.o
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index bafc729fc434..a3bac9da8cbb 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -631,8 +631,8 @@ static const struct mfd_cell ab8500_devs[] = {
 		    NULL, NULL, 0, 0, "stericsson,ab8500-ext-regulator"),
 	OF_MFD_CELL("ab8500-regulator",
 		    NULL, NULL, 0, 0, "stericsson,ab8500-regulator"),
-	OF_MFD_CELL("abx500-clk",
-		    NULL, NULL, 0, 0, "stericsson,abx500-clk"),
+	OF_MFD_CELL("ab8500-clk",
+		    NULL, NULL, 0, 0, "stericsson,ab8500-clk"),
 	OF_MFD_CELL("ab8500-gpadc",
 		    NULL, NULL, 0, 0, "stericsson,ab8500-gpadc"),
 	OF_MFD_CELL("ab8500-rtc",
@@ -718,17 +718,20 @@ static const struct mfd_cell ab8505_devs[] = {
 #ifdef CONFIG_DEBUG_FS
 	{
 		.name = "ab8500-debug",
+		.of_compatible = "stericsson,ab8500-debug",
 	},
 #endif
 	{
 		.name = "ab8500-sysctrl",
+		.of_compatible = "stericsson,ab8500-sysctrl",
 	},
 	{
 		.name = "ab8500-regulator",
+		.of_compatible = "stericsson,ab8505-regulator",
 	},
 	{
 		.name = "abx500-clk",
-		.of_compatible = "stericsson,abx500-clk",
+		.of_compatible = "stericsson,ab8500-clk",
 	},
 	{
 		.name = "ab8500-gpadc",
@@ -736,25 +739,32 @@ static const struct mfd_cell ab8505_devs[] = {
 	},
 	{
 		.name = "ab8500-rtc",
+		.of_compatible = "stericsson,ab8500-rtc",
 	},
 	{
 		.name = "ab8500-acc-det",
+		.of_compatible = "stericsson,ab8500-acc-det",
 	},
 	{
 		.name = "ab8500-poweron-key",
+		.of_compatible = "stericsson,ab8500-poweron-key",
 	},
 	{
 		.name = "ab8500-pwm",
+		.of_compatible = "stericsson,ab8500-pwm",
 		.id = 1,
 	},
 	{
 		.name = "pinctrl-ab8505",
+		.of_compatible = "stericsson,ab8505-gpio",
 	},
 	{
 		.name = "ab8500-usb",
+		.of_compatible = "stericsson,ab8500-usb",
 	},
 	{
 		.name = "ab8500-codec",
+		.of_compatible = "stericsson,ab8500-codec",
 	},
 	{
 		.name = "ab-iddet",
@@ -1276,7 +1286,7 @@ static int ab8500_probe(struct platform_device *pdev)
 
 static const struct platform_device_id ab8500_id[] = {
 	{ "ab8500-core", AB8500_VERSION_AB8500 },
-	{ "ab8505-i2c", AB8500_VERSION_AB8505 },
+	{ "ab8505-core", AB8500_VERSION_AB8505 },
 	{ "ab9540-i2c", AB8500_VERSION_AB9540 },
 	{ "ab8540-i2c", AB8500_VERSION_AB8540 },
 	{ }
diff --git a/drivers/mfd/atmel-hlcdc.c b/drivers/mfd/atmel-hlcdc.c
index 64013c57a920..3c2414ba4b01 100644
--- a/drivers/mfd/atmel-hlcdc.c
+++ b/drivers/mfd/atmel-hlcdc.c
@@ -19,6 +19,7 @@
 
 struct atmel_hlcdc_regmap {
 	void __iomem *regs;
+	struct device *dev;
 };
 
 static const struct mfd_cell atmel_hlcdc_cells[] = {
@@ -39,10 +40,17 @@ static int regmap_atmel_hlcdc_reg_write(void *context, unsigned int reg,
 
 	if (reg <= ATMEL_HLCDC_DIS) {
 		u32 status;
-
-		readl_poll_timeout_atomic(hregmap->regs + ATMEL_HLCDC_SR,
-					  status, !(status & ATMEL_HLCDC_SIP),
-					  1, 100);
+		int ret;
+
+		ret = readl_poll_timeout_atomic(hregmap->regs + ATMEL_HLCDC_SR,
+						status,
+						!(status & ATMEL_HLCDC_SIP),
+						1, 100);
+		if (ret) {
+			dev_err(hregmap->dev,
+				"Timeout! Clock domain synchronization is in progress!\n");
+			return ret;
+		}
 	}
 
 	writel(val, hregmap->regs + reg);
@@ -90,6 +98,8 @@ static int atmel_hlcdc_probe(struct platform_device *pdev)
 	if (IS_ERR(hregmap->regs))
 		return PTR_ERR(hregmap->regs);
 
+	hregmap->dev = &pdev->dev;
+
 	hlcdc->irq = platform_get_irq(pdev, 0);
 	if (hlcdc->irq < 0)
 		return hlcdc->irq;
diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c
index a4aaadaa0cb0..aa59496e4376 100644
--- a/drivers/mfd/axp20x.c
+++ b/drivers/mfd/axp20x.c
@@ -126,7 +126,7 @@ static const struct regmap_range axp288_writeable_ranges[] = {
 static const struct regmap_range axp288_volatile_ranges[] = {
 	regmap_reg_range(AXP20X_PWR_INPUT_STATUS, AXP288_POWER_REASON),
 	regmap_reg_range(AXP288_BC_GLOBAL, AXP288_BC_GLOBAL),
-	regmap_reg_range(AXP288_BC_DET_STAT, AXP288_BC_DET_STAT),
+	regmap_reg_range(AXP288_BC_DET_STAT, AXP20X_VBUS_IPSOUT_MGMT),
 	regmap_reg_range(AXP20X_CHRG_BAK_CTRL, AXP20X_CHRG_BAK_CTRL),
 	regmap_reg_range(AXP20X_IRQ1_EN, AXP20X_IPSOUT_V_HIGH_L),
 	regmap_reg_range(AXP20X_TIMER_CTRL, AXP20X_TIMER_CTRL),
diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c
index c4b977a5dd96..39e611695053 100644
--- a/drivers/mfd/cros_ec_dev.c
+++ b/drivers/mfd/cros_ec_dev.c
@@ -5,8 +5,8 @@
  * Copyright (C) 2014 Google, Inc.
  */
 
+#include <linux/kconfig.h>
 #include <linux/mfd/core.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/mod_devicetable.h>
 #include <linux/of_platform.h>
@@ -87,6 +87,10 @@ static const struct mfd_cell cros_usbpd_charger_cells[] = {
 	{ .name = "cros-usbpd-logger", },
 };
 
+static const struct mfd_cell cros_usbpd_notify_cells[] = {
+	{ .name = "cros-usbpd-notify", },
+};
+
 static const struct cros_feature_to_cells cros_subdevices[] = {
 	{
 		.id		= EC_FEATURE_CEC,
@@ -203,6 +207,23 @@ static int ec_device_probe(struct platform_device *pdev)
 	}
 
 	/*
+	 * The PD notifier driver cell is separate since it only needs to be
+	 * explicitly added on platforms that don't have the PD notifier ACPI
+	 * device entry defined.
+	 */
+	if (IS_ENABLED(CONFIG_OF)) {
+		if (cros_ec_check_features(ec, EC_FEATURE_USB_PD)) {
+			retval = mfd_add_hotplug_devices(ec->dev,
+					cros_usbpd_notify_cells,
+					ARRAY_SIZE(cros_usbpd_notify_cells));
+			if (retval)
+				dev_err(ec->dev,
+					"failed to add PD notify devices: %d\n",
+					retval);
+		}
+	}
+
+	/*
 	 * The following subdevices cannot be detected by sending the
 	 * EC_FEATURE_GET_CMD to the Embedded Controller device.
 	 */
diff --git a/drivers/mfd/cs47l15-tables.c b/drivers/mfd/cs47l15-tables.c
index f81b45336690..3c77f0a24e9b 100644
--- a/drivers/mfd/cs47l15-tables.c
+++ b/drivers/mfd/cs47l15-tables.c
@@ -112,6 +112,7 @@ static const struct reg_default cs47l15_reg_default[] = {
 	{ 0x000001dd, 0x0011 }, /* R477 (0x1DD) - FLL AO Control 11 */
 	{ 0x00000218, 0x00e6 }, /* R536 (0x218) - Mic Bias Ctrl 1 */
 	{ 0x0000021c, 0x0222 }, /* R540 (0x21C) - Mic Bias Ctrl 5 */
+	{ 0x00000293, 0x0080 }, /* R659 (0x293) - Accessory Detect Mode 1 */
 	{ 0x00000299, 0x0000 }, /* R665 (0x299) - Headphone Detect 0 */
 	{ 0x0000029b, 0x0000 }, /* R667 (0x29B) - Headphone Detect 1 */
 	{ 0x000002a2, 0x0010 }, /* R674 (0x2A2) - Mic Detect 1 Control 0 */
diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c
index e69626867c26..419c73533401 100644
--- a/drivers/mfd/da9062-core.c
+++ b/drivers/mfd/da9062-core.c
@@ -233,6 +233,14 @@ static struct resource da9062_onkey_resources[] = {
 	DEFINE_RES_NAMED(DA9062_IRQ_ONKEY, 1, "ONKEY", IORESOURCE_IRQ),
 };
 
+static struct resource da9062_gpio_resources[] = {
+	DEFINE_RES_NAMED(DA9062_IRQ_GPI0, 1, "GPI0", IORESOURCE_IRQ),
+	DEFINE_RES_NAMED(DA9062_IRQ_GPI1, 1, "GPI1", IORESOURCE_IRQ),
+	DEFINE_RES_NAMED(DA9062_IRQ_GPI2, 1, "GPI2", IORESOURCE_IRQ),
+	DEFINE_RES_NAMED(DA9062_IRQ_GPI3, 1, "GPI3", IORESOURCE_IRQ),
+	DEFINE_RES_NAMED(DA9062_IRQ_GPI4, 1, "GPI4", IORESOURCE_IRQ),
+};
+
 static const struct mfd_cell da9062_devs[] = {
 	{
 		.name		= "da9062-core",
@@ -248,7 +256,7 @@ static const struct mfd_cell da9062_devs[] = {
 		.name		= "da9062-watchdog",
 		.num_resources	= ARRAY_SIZE(da9062_wdt_resources),
 		.resources	= da9062_wdt_resources,
-		.of_compatible  = "dlg,da9062-wdt",
+		.of_compatible  = "dlg,da9062-watchdog",
 	},
 	{
 		.name		= "da9062-thermal",
@@ -266,7 +274,13 @@ static const struct mfd_cell da9062_devs[] = {
 		.name		= "da9062-onkey",
 		.num_resources	= ARRAY_SIZE(da9062_onkey_resources),
 		.resources	= da9062_onkey_resources,
-		.of_compatible = "dlg,da9062-onkey",
+		.of_compatible	= "dlg,da9062-onkey",
+	},
+	{
+		.name		= "da9062-gpio",
+		.num_resources	= ARRAY_SIZE(da9062_gpio_resources),
+		.resources	= da9062_gpio_resources,
+		.of_compatible	= "dlg,da9062-gpio",
 	},
 };
 
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index 57ac58b4b5f3..0452b43b0423 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -542,102 +542,6 @@ static struct dsiescclk dsiescclk[3] = {
 	}
 };
 
-
-/*
-* Used by MCDE to setup all necessary PRCMU registers
-*/
-#define PRCMU_RESET_DSIPLL		0x00004000
-#define PRCMU_UNCLAMP_DSIPLL		0x00400800
-
-#define PRCMU_CLK_PLL_DIV_SHIFT		0
-#define PRCMU_CLK_PLL_SW_SHIFT		5
-#define PRCMU_CLK_38			(1 << 9)
-#define PRCMU_CLK_38_SRC		(1 << 10)
-#define PRCMU_CLK_38_DIV		(1 << 11)
-
-/* PLLDIV=12, PLLSW=4 (PLLDDR) */
-#define PRCMU_DSI_CLOCK_SETTING		0x0000008C
-
-/* DPI 50000000 Hz */
-#define PRCMU_DPI_CLOCK_SETTING		((1 << PRCMU_CLK_PLL_SW_SHIFT) | \
-					  (16 << PRCMU_CLK_PLL_DIV_SHIFT))
-#define PRCMU_DSI_LP_CLOCK_SETTING	0x00000E00
-
-/* D=101, N=1, R=4, SELDIV2=0 */
-#define PRCMU_PLLDSI_FREQ_SETTING	0x00040165
-
-#define PRCMU_ENABLE_PLLDSI		0x00000001
-#define PRCMU_DISABLE_PLLDSI		0x00000000
-#define PRCMU_RELEASE_RESET_DSS		0x0000400C
-#define PRCMU_DSI_PLLOUT_SEL_SETTING	0x00000202
-/* ESC clk, div0=1, div1=1, div2=3 */
-#define PRCMU_ENABLE_ESCAPE_CLOCK_DIV	0x07030101
-#define PRCMU_DISABLE_ESCAPE_CLOCK_DIV	0x00030101
-#define PRCMU_DSI_RESET_SW		0x00000007
-
-#define PRCMU_PLLDSI_LOCKP_LOCKED	0x3
-
-int db8500_prcmu_enable_dsipll(void)
-{
-	int i;
-
-	/* Clear DSIPLL_RESETN */
-	writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_CLR);
-	/* Unclamp DSIPLL in/out */
-	writel(PRCMU_UNCLAMP_DSIPLL, PRCM_MMIP_LS_CLAMP_CLR);
-
-	/* Set DSI PLL FREQ */
-	writel(PRCMU_PLLDSI_FREQ_SETTING, PRCM_PLLDSI_FREQ);
-	writel(PRCMU_DSI_PLLOUT_SEL_SETTING, PRCM_DSI_PLLOUT_SEL);
-	/* Enable Escape clocks */
-	writel(PRCMU_ENABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
-
-	/* Start DSI PLL */
-	writel(PRCMU_ENABLE_PLLDSI, PRCM_PLLDSI_ENABLE);
-	/* Reset DSI PLL */
-	writel(PRCMU_DSI_RESET_SW, PRCM_DSI_SW_RESET);
-	for (i = 0; i < 10; i++) {
-		if ((readl(PRCM_PLLDSI_LOCKP) & PRCMU_PLLDSI_LOCKP_LOCKED)
-					== PRCMU_PLLDSI_LOCKP_LOCKED)
-			break;
-		udelay(100);
-	}
-	/* Set DSIPLL_RESETN */
-	writel(PRCMU_RESET_DSIPLL, PRCM_APE_RESETN_SET);
-	return 0;
-}
-
-int db8500_prcmu_disable_dsipll(void)
-{
-	/* Disable dsi pll */
-	writel(PRCMU_DISABLE_PLLDSI, PRCM_PLLDSI_ENABLE);
-	/* Disable  escapeclock */
-	writel(PRCMU_DISABLE_ESCAPE_CLOCK_DIV, PRCM_DSITVCLK_DIV);
-	return 0;
-}
-
-int db8500_prcmu_set_display_clocks(void)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&clk_mgt_lock, flags);
-
-	/* Grab the HW semaphore. */
-	while ((readl(PRCM_SEM) & PRCM_SEM_PRCM_SEM) != 0)
-		cpu_relax();
-
-	writel(PRCMU_DSI_CLOCK_SETTING, prcmu_base + PRCM_HDMICLK_MGT);
-	writel(PRCMU_DSI_LP_CLOCK_SETTING, prcmu_base + PRCM_TVCLK_MGT);
-	writel(PRCMU_DPI_CLOCK_SETTING, prcmu_base + PRCM_LCDCLK_MGT);
-
-	/* Release the HW semaphore. */
-	writel(0, PRCM_SEM);
-
-	spin_unlock_irqrestore(&clk_mgt_lock, flags);
-
-	return 0;
-}
-
 u32 db8500_prcmu_read(unsigned int reg)
 {
 	return readl(prcmu_base + reg);
@@ -3060,30 +2964,44 @@ static const struct mfd_cell db8500_prcmu_devs[] = {
 static int db8500_prcmu_register_ab8500(struct device *parent)
 {
 	struct device_node *np;
-	struct resource ab8500_resource;
+	struct resource ab850x_resource;
 	const struct mfd_cell ab8500_cell = {
 		.name = "ab8500-core",
 		.of_compatible = "stericsson,ab8500",
 		.id = AB8500_VERSION_AB8500,
-		.resources = &ab8500_resource,
+		.resources = &ab850x_resource,
 		.num_resources = 1,
 	};
+	const struct mfd_cell ab8505_cell = {
+		.name = "ab8505-core",
+		.of_compatible = "stericsson,ab8505",
+		.id = AB8500_VERSION_AB8505,
+		.resources = &ab850x_resource,
+		.num_resources = 1,
+	};
+	const struct mfd_cell *ab850x_cell;
 
 	if (!parent->of_node)
 		return -ENODEV;
 
 	/* Look up the device node, sneak the IRQ out of it */
 	for_each_child_of_node(parent->of_node, np) {
-		if (of_device_is_compatible(np, ab8500_cell.of_compatible))
+		if (of_device_is_compatible(np, ab8500_cell.of_compatible)) {
+			ab850x_cell = &ab8500_cell;
 			break;
+		}
+		if (of_device_is_compatible(np, ab8505_cell.of_compatible)) {
+			ab850x_cell = &ab8505_cell;
+			break;
+		}
 	}
 	if (!np) {
-		dev_info(parent, "could not find AB8500 node in the device tree\n");
+		dev_info(parent, "could not find AB850X node in the device tree\n");
 		return -ENODEV;
 	}
-	of_irq_to_resource_table(np, &ab8500_resource, 1);
+	of_irq_to_resource_table(np, &ab850x_resource, 1);
 
-	return mfd_add_devices(parent, 0, &ab8500_cell, 1, NULL, 0, NULL);
+	return mfd_add_devices(parent, 0, ab850x_cell, 1, NULL, 0, NULL);
 }
 
 /**
diff --git a/drivers/mfd/dln2.c b/drivers/mfd/dln2.c
index 381593fbe50f..7841c11411d0 100644
--- a/drivers/mfd/dln2.c
+++ b/drivers/mfd/dln2.c
@@ -722,6 +722,8 @@ static int dln2_probe(struct usb_interface *interface,
 		      const struct usb_device_id *usb_id)
 {
 	struct usb_host_interface *hostif = interface->cur_altsetting;
+	struct usb_endpoint_descriptor *epin;
+	struct usb_endpoint_descriptor *epout;
 	struct device *dev = &interface->dev;
 	struct dln2_dev *dln2;
 	int ret;
@@ -731,12 +733,19 @@ static int dln2_probe(struct usb_interface *interface,
 	    hostif->desc.bNumEndpoints < 2)
 		return -ENODEV;
 
+	epin = &hostif->endpoint[0].desc;
+	epout = &hostif->endpoint[1].desc;
+	if (!usb_endpoint_is_bulk_out(epout))
+		return -ENODEV;
+	if (!usb_endpoint_is_bulk_in(epin))
+		return -ENODEV;
+
 	dln2 = kzalloc(sizeof(*dln2), GFP_KERNEL);
 	if (!dln2)
 		return -ENOMEM;
 
-	dln2->ep_out = hostif->endpoint[0].desc.bEndpointAddress;
-	dln2->ep_in = hostif->endpoint[1].desc.bEndpointAddress;
+	dln2->ep_out = epout->bEndpointAddress;
+	dln2->ep_in = epin->bEndpointAddress;
 	dln2->usb_dev = usb_get_dev(interface_to_usbdev(interface));
 	dln2->interface = interface;
 	usb_set_intfdata(interface, dln2);
diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c
index b33030e3385c..c40a6c7d0cf8 100644
--- a/drivers/mfd/intel-lpss-pci.c
+++ b/drivers/mfd/intel-lpss-pci.c
@@ -240,6 +240,19 @@ static const struct pci_device_id intel_lpss_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x4b79), (kernel_ulong_t)&bxt_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x4b7a), (kernel_ulong_t)&bxt_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x4b7b), (kernel_ulong_t)&bxt_i2c_info },
+	/* JSL */
+	{ PCI_VDEVICE(INTEL, 0x4da8), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x4da9), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x4daa), (kernel_ulong_t)&spt_info },
+	{ PCI_VDEVICE(INTEL, 0x4dab), (kernel_ulong_t)&spt_info },
+	{ PCI_VDEVICE(INTEL, 0x4daf), (kernel_ulong_t)&spt_uart_info },
+	{ PCI_VDEVICE(INTEL, 0x4dc5), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x4dc6), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x4de8), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x4de9), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x4dea), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x4deb), (kernel_ulong_t)&bxt_i2c_info },
+	{ PCI_VDEVICE(INTEL, 0x4dfb), (kernel_ulong_t)&spt_info },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5aac), (kernel_ulong_t)&apl_i2c_info },
 	{ PCI_VDEVICE(INTEL, 0x5aae), (kernel_ulong_t)&apl_i2c_info },
diff --git a/drivers/mfd/intel_soc_pmic_core.c b/drivers/mfd/intel_soc_pmic_core.c
index c9f35378d391..ddd64f9e3341 100644
--- a/drivers/mfd/intel_soc_pmic_core.c
+++ b/drivers/mfd/intel_soc_pmic_core.c
@@ -9,8 +9,6 @@
  */
 
 #include <linux/acpi.h>
-#include <linux/gpio/consumer.h>
-#include <linux/gpio/machine.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -25,20 +23,9 @@
 #define BYT_CRC_HRV		2
 #define CHT_CRC_HRV		3
 
-/* Lookup table for the Panel Enable/Disable line as GPIO signals */
-static struct gpiod_lookup_table panel_gpio_table = {
-	/* Intel GFX is consumer */
-	.dev_id = "0000:00:02.0",
-	.table = {
-		/* Panel EN/DISABLE */
-		GPIO_LOOKUP("gpio_crystalcove", 94, "panel", GPIO_ACTIVE_HIGH),
-		{ },
-	},
-};
-
 /* PWM consumed by the Intel GFX */
 static struct pwm_lookup crc_pwm_lookup[] = {
-	PWM_LOOKUP("crystal_cove_pwm", 0, "0000:00:02.0", "pwm_backlight", 0, PWM_POLARITY_NORMAL),
+	PWM_LOOKUP("crystal_cove_pwm", 0, "0000:00:02.0", "pwm_pmic_backlight", 0, PWM_POLARITY_NORMAL),
 };
 
 static int intel_soc_pmic_i2c_probe(struct i2c_client *i2c,
@@ -96,9 +83,6 @@ static int intel_soc_pmic_i2c_probe(struct i2c_client *i2c,
 	if (ret)
 		dev_warn(dev, "Can't enable IRQ as wake source: %d\n", ret);
 
-	/* Add lookup table binding for Panel Control to the GPIO Chip */
-	gpiod_add_lookup_table(&panel_gpio_table);
-
 	/* Add lookup table for crc-pwm */
 	pwm_add_table(crc_pwm_lookup, ARRAY_SIZE(crc_pwm_lookup));
 
@@ -121,9 +105,6 @@ static int intel_soc_pmic_i2c_remove(struct i2c_client *i2c)
 
 	regmap_del_irq_chip(pmic->irq, pmic->irq_chip_data);
 
-	/* Remove lookup table for Panel Control from the GPIO Chip */
-	gpiod_remove_lookup_table(&panel_gpio_table);
-
 	/* remove crc-pwm lookup table */
 	pwm_remove_table(crc_pwm_lookup, ARRAY_SIZE(crc_pwm_lookup));
 
diff --git a/drivers/mfd/ioc3.c b/drivers/mfd/ioc3.c
new file mode 100644
index 000000000000..02998d4eb74b
--- /dev/null
+++ b/drivers/mfd/ioc3.c
@@ -0,0 +1,669 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SGI IOC3 multifunction device driver
+ *
+ * Copyright (C) 2018, 2019 Thomas Bogendoerfer <tbogendoerfer@suse.de>
+ *
+ * Based on work by:
+ *   Stanislaw Skowronek <skylark@unaligned.org>
+ *   Joshua Kinard <kumba@gentoo.org>
+ *   Brent Casavant <bcasavan@sgi.com> - IOC4 master driver
+ *   Pat Gefre <pfg@sgi.com> - IOC3 serial port IRQ demuxer
+ */
+
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/sgi-w1.h>
+#include <linux/rtc/ds1685.h>
+
+#include <asm/pci/bridge.h>
+#include <asm/sn/ioc3.h>
+
+#define IOC3_IRQ_SERIAL_A	6
+#define IOC3_IRQ_SERIAL_B	15
+#define IOC3_IRQ_KBD		22
+
+/* Bitmask for selecting which IRQs are level triggered */
+#define IOC3_LVL_MASK	(BIT(IOC3_IRQ_SERIAL_A) | BIT(IOC3_IRQ_SERIAL_B))
+
+#define M48T35_REG_SIZE	32768	/* size of m48t35 registers */
+
+/* 1.2 us latency timer (40 cycles at 33 MHz) */
+#define IOC3_LATENCY	40
+
+struct ioc3_priv_data {
+	struct irq_domain *domain;
+	struct ioc3 __iomem *regs;
+	struct pci_dev *pdev;
+	int domain_irq;
+};
+
+static void ioc3_irq_ack(struct irq_data *d)
+{
+	struct ioc3_priv_data *ipd = irq_data_get_irq_chip_data(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+
+	writel(BIT(hwirq), &ipd->regs->sio_ir);
+}
+
+static void ioc3_irq_mask(struct irq_data *d)
+{
+	struct ioc3_priv_data *ipd = irq_data_get_irq_chip_data(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+
+	writel(BIT(hwirq), &ipd->regs->sio_iec);
+}
+
+static void ioc3_irq_unmask(struct irq_data *d)
+{
+	struct ioc3_priv_data *ipd = irq_data_get_irq_chip_data(d);
+	unsigned int hwirq = irqd_to_hwirq(d);
+
+	writel(BIT(hwirq), &ipd->regs->sio_ies);
+}
+
+static struct irq_chip ioc3_irq_chip = {
+	.name		= "IOC3",
+	.irq_ack	= ioc3_irq_ack,
+	.irq_mask	= ioc3_irq_mask,
+	.irq_unmask	= ioc3_irq_unmask,
+};
+
+static int ioc3_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hwirq)
+{
+	/* Set level IRQs for every interrupt contained in IOC3_LVL_MASK */
+	if (BIT(hwirq) & IOC3_LVL_MASK)
+		irq_set_chip_and_handler(irq, &ioc3_irq_chip, handle_level_irq);
+	else
+		irq_set_chip_and_handler(irq, &ioc3_irq_chip, handle_edge_irq);
+
+	irq_set_chip_data(irq, d->host_data);
+	return 0;
+}
+
+static void ioc3_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops ioc3_irq_domain_ops = {
+	.map = ioc3_irq_domain_map,
+	.unmap = ioc3_irq_domain_unmap,
+};
+
+static void ioc3_irq_handler(struct irq_desc *desc)
+{
+	struct irq_domain *domain = irq_desc_get_handler_data(desc);
+	struct ioc3_priv_data *ipd = domain->host_data;
+	struct ioc3 __iomem *regs = ipd->regs;
+	u32 pending, mask;
+	unsigned int irq;
+
+	pending = readl(&regs->sio_ir);
+	mask = readl(&regs->sio_ies);
+	pending &= mask; /* Mask off not enabled interrupts */
+
+	if (pending) {
+		irq = irq_find_mapping(domain, __ffs(pending));
+		if (irq)
+			generic_handle_irq(irq);
+	} else  {
+		spurious_interrupt();
+	}
+}
+
+/*
+ * System boards/BaseIOs use more interrupt pins of the bridge ASIC
+ * to which the IOC3 is connected. Since the IOC3 MFD driver
+ * knows wiring of these extra pins, we use the map_irq function
+ * to get interrupts activated
+ */
+static int ioc3_map_irq(struct pci_dev *pdev, int slot, int pin)
+{
+	struct pci_host_bridge *hbrg = pci_find_host_bridge(pdev->bus);
+
+	return hbrg->map_irq(pdev, slot, pin);
+}
+
+static int ioc3_irq_domain_setup(struct ioc3_priv_data *ipd, int irq)
+{
+	struct irq_domain *domain;
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_fwnode("IOC3");
+	if (!fn)
+		goto err;
+
+	domain = irq_domain_create_linear(fn, 24, &ioc3_irq_domain_ops, ipd);
+	if (!domain)
+		goto err;
+
+	irq_domain_free_fwnode(fn);
+	ipd->domain = domain;
+
+	irq_set_chained_handler_and_data(irq, ioc3_irq_handler, domain);
+	ipd->domain_irq = irq;
+	return 0;
+
+err:
+	dev_err(&ipd->pdev->dev, "irq domain setup failed\n");
+	return -ENOMEM;
+}
+
+static struct resource ioc3_uarta_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, sregs.uarta),
+		       sizeof_field(struct ioc3, sregs.uarta)),
+	DEFINE_RES_IRQ(IOC3_IRQ_SERIAL_A)
+};
+
+static struct resource ioc3_uartb_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, sregs.uartb),
+		       sizeof_field(struct ioc3, sregs.uartb)),
+	DEFINE_RES_IRQ(IOC3_IRQ_SERIAL_B)
+};
+
+static struct mfd_cell ioc3_serial_cells[] = {
+	{
+		.name = "ioc3-serial8250",
+		.resources = ioc3_uarta_resources,
+		.num_resources = ARRAY_SIZE(ioc3_uarta_resources),
+	},
+	{
+		.name = "ioc3-serial8250",
+		.resources = ioc3_uartb_resources,
+		.num_resources = ARRAY_SIZE(ioc3_uartb_resources),
+	}
+};
+
+static int ioc3_serial_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	/* Set gpio pins for RS232/RS422 mode selection */
+	writel(GPCR_UARTA_MODESEL | GPCR_UARTB_MODESEL,
+		&ipd->regs->gpcr_s);
+	/* Select RS232 mode for uart a */
+	writel(0, &ipd->regs->gppr[6]);
+	/* Select RS232 mode for uart b */
+	writel(0, &ipd->regs->gppr[7]);
+
+	/* Switch both ports to 16650 mode */
+	writel(readl(&ipd->regs->port_a.sscr) & ~SSCR_DMA_EN,
+	       &ipd->regs->port_a.sscr);
+	writel(readl(&ipd->regs->port_b.sscr) & ~SSCR_DMA_EN,
+	       &ipd->regs->port_b.sscr);
+	udelay(1000); /* Wait until mode switch is done */
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_serial_cells, ARRAY_SIZE(ioc3_serial_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret) {
+		dev_err(&ipd->pdev->dev, "Failed to add 16550 subdevs\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct resource ioc3_kbd_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, serio),
+		       sizeof_field(struct ioc3, serio)),
+	DEFINE_RES_IRQ(IOC3_IRQ_KBD)
+};
+
+static struct mfd_cell ioc3_kbd_cells[] = {
+	{
+		.name = "ioc3-kbd",
+		.resources = ioc3_kbd_resources,
+		.num_resources = ARRAY_SIZE(ioc3_kbd_resources),
+	}
+};
+
+static int ioc3_kbd_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_kbd_cells, ARRAY_SIZE(ioc3_kbd_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret) {
+		dev_err(&ipd->pdev->dev, "Failed to add 16550 subdevs\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct resource ioc3_eth_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, eth),
+		       sizeof_field(struct ioc3, eth)),
+	DEFINE_RES_MEM(offsetof(struct ioc3, ssram),
+		       sizeof_field(struct ioc3, ssram)),
+	DEFINE_RES_IRQ(0)
+};
+
+static struct resource ioc3_w1_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, mcr),
+		       sizeof_field(struct ioc3, mcr)),
+};
+static struct sgi_w1_platform_data ioc3_w1_platform_data;
+
+static struct mfd_cell ioc3_eth_cells[] = {
+	{
+		.name = "ioc3-eth",
+		.resources = ioc3_eth_resources,
+		.num_resources = ARRAY_SIZE(ioc3_eth_resources),
+	},
+	{
+		.name = "sgi_w1",
+		.resources = ioc3_w1_resources,
+		.num_resources = ARRAY_SIZE(ioc3_w1_resources),
+		.platform_data = &ioc3_w1_platform_data,
+		.pdata_size = sizeof(ioc3_w1_platform_data),
+	}
+};
+
+static int ioc3_eth_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	/* Enable One-Wire bus */
+	writel(GPCR_MLAN_EN, &ipd->regs->gpcr_s);
+
+	/* Generate unique identifier */
+	snprintf(ioc3_w1_platform_data.dev_id,
+		 sizeof(ioc3_w1_platform_data.dev_id), "ioc3-%012llx",
+		 ipd->pdev->resource->start);
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_eth_cells, ARRAY_SIZE(ioc3_eth_cells),
+			      &ipd->pdev->resource[0], ipd->pdev->irq, NULL);
+	if (ret) {
+		dev_err(&ipd->pdev->dev, "Failed to add ETH/W1 subdev\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct resource ioc3_m48t35_resources[] = {
+	DEFINE_RES_MEM(IOC3_BYTEBUS_DEV0, M48T35_REG_SIZE)
+};
+
+static struct mfd_cell ioc3_m48t35_cells[] = {
+	{
+		.name = "rtc-m48t35",
+		.resources = ioc3_m48t35_resources,
+		.num_resources = ARRAY_SIZE(ioc3_m48t35_resources),
+	}
+};
+
+static int ioc3_m48t35_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = mfd_add_devices(&ipd->pdev->dev, PLATFORM_DEVID_AUTO,
+			      ioc3_m48t35_cells, ARRAY_SIZE(ioc3_m48t35_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret)
+		dev_err(&ipd->pdev->dev, "Failed to add M48T35 subdev\n");
+
+	return ret;
+}
+
+static struct ds1685_rtc_platform_data ip30_rtc_platform_data = {
+	.bcd_mode = false,
+	.no_irq = false,
+	.uie_unsupported = true,
+	.access_type = ds1685_reg_indirect,
+};
+
+static struct resource ioc3_rtc_ds1685_resources[] = {
+	DEFINE_RES_MEM(IOC3_BYTEBUS_DEV1, 1),
+	DEFINE_RES_MEM(IOC3_BYTEBUS_DEV2, 1),
+	DEFINE_RES_IRQ(0)
+};
+
+static struct mfd_cell ioc3_ds1685_cells[] = {
+	{
+		.name = "rtc-ds1685",
+		.resources = ioc3_rtc_ds1685_resources,
+		.num_resources = ARRAY_SIZE(ioc3_rtc_ds1685_resources),
+		.platform_data = &ip30_rtc_platform_data,
+		.pdata_size = sizeof(ip30_rtc_platform_data),
+		.id = PLATFORM_DEVID_NONE,
+	}
+};
+
+static int ioc3_ds1685_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, irq;
+
+	irq = ioc3_map_irq(ipd->pdev, 6, 0);
+
+	ret = mfd_add_devices(&ipd->pdev->dev, 0, ioc3_ds1685_cells,
+			      ARRAY_SIZE(ioc3_ds1685_cells),
+			      &ipd->pdev->resource[0], irq, NULL);
+	if (ret)
+		dev_err(&ipd->pdev->dev, "Failed to add DS1685 subdev\n");
+
+	return ret;
+};
+
+
+static struct resource ioc3_leds_resources[] = {
+	DEFINE_RES_MEM(offsetof(struct ioc3, gppr[0]),
+		       sizeof_field(struct ioc3, gppr[0])),
+	DEFINE_RES_MEM(offsetof(struct ioc3, gppr[1]),
+		       sizeof_field(struct ioc3, gppr[1])),
+};
+
+static struct mfd_cell ioc3_led_cells[] = {
+	{
+		.name = "ip30-leds",
+		.resources = ioc3_leds_resources,
+		.num_resources = ARRAY_SIZE(ioc3_leds_resources),
+		.id = PLATFORM_DEVID_NONE,
+	}
+};
+
+static int ioc3_led_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = mfd_add_devices(&ipd->pdev->dev, 0, ioc3_led_cells,
+			      ARRAY_SIZE(ioc3_led_cells),
+			      &ipd->pdev->resource[0], 0, ipd->domain);
+	if (ret)
+		dev_err(&ipd->pdev->dev, "Failed to add LED subdev\n");
+
+	return ret;
+}
+
+static int ip27_baseio_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_m48t35_setup(ipd);
+}
+
+static int ip27_baseio6g_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_m48t35_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_kbd_setup(ipd);
+}
+
+static int ip27_mio_setup(struct ioc3_priv_data *ipd)
+{
+	int ret;
+
+	ret = ioc3_irq_domain_setup(ipd, ipd->pdev->irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_kbd_setup(ipd);
+}
+
+static int ip30_sysboard_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_serial_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_kbd_setup(ipd);
+	if (ret)
+		return ret;
+
+	ret = ioc3_ds1685_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_led_setup(ipd);
+}
+
+static int ioc3_menet_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_serial_setup(ipd);
+}
+
+static int ioc3_menet4_setup(struct ioc3_priv_data *ipd)
+{
+	return ioc3_eth_setup(ipd);
+}
+
+static int ioc3_cad_duo_setup(struct ioc3_priv_data *ipd)
+{
+	int ret, io_irq;
+
+	io_irq = ioc3_map_irq(ipd->pdev, PCI_SLOT(ipd->pdev->devfn),
+			      PCI_INTERRUPT_INTB);
+	ret = ioc3_irq_domain_setup(ipd, io_irq);
+	if (ret)
+		return ret;
+
+	ret = ioc3_eth_setup(ipd);
+	if (ret)
+		return ret;
+
+	return ioc3_kbd_setup(ipd);
+}
+
+/* Helper macro for filling ioc3_info array */
+#define IOC3_SID(_name, _sid, _setup) \
+	{								   \
+		.name = _name,						   \
+		.sid = PCI_VENDOR_ID_SGI | (IOC3_SUBSYS_ ## _sid << 16),   \
+		.setup = _setup,					   \
+	}
+
+static struct {
+	const char *name;
+	u32 sid;
+	int (*setup)(struct ioc3_priv_data *ipd);
+} ioc3_infos[] = {
+	IOC3_SID("IP27 BaseIO6G", IP27_BASEIO6G, &ip27_baseio6g_setup),
+	IOC3_SID("IP27 MIO", IP27_MIO, &ip27_mio_setup),
+	IOC3_SID("IP27 BaseIO", IP27_BASEIO, &ip27_baseio_setup),
+	IOC3_SID("IP29 System Board", IP29_SYSBOARD, &ip27_baseio6g_setup),
+	IOC3_SID("IP30 System Board", IP30_SYSBOARD, &ip30_sysboard_setup),
+	IOC3_SID("MENET", MENET, &ioc3_menet_setup),
+	IOC3_SID("MENET4", MENET4, &ioc3_menet4_setup)
+};
+#undef IOC3_SID
+
+static int ioc3_setup(struct ioc3_priv_data *ipd)
+{
+	u32 sid;
+	int i;
+
+	/* Clear IRQs */
+	writel(~0, &ipd->regs->sio_iec);
+	writel(~0, &ipd->regs->sio_ir);
+	writel(0, &ipd->regs->eth.eier);
+	writel(~0, &ipd->regs->eth.eisr);
+
+	/* Read subsystem vendor id and subsystem id */
+	pci_read_config_dword(ipd->pdev, PCI_SUBSYSTEM_VENDOR_ID, &sid);
+
+	for (i = 0; i < ARRAY_SIZE(ioc3_infos); i++)
+		if (sid == ioc3_infos[i].sid) {
+			pr_info("ioc3: %s\n", ioc3_infos[i].name);
+			return ioc3_infos[i].setup(ipd);
+		}
+
+	/* Treat everything not identified by PCI subid as CAD DUO */
+	pr_info("ioc3: CAD DUO\n");
+	return ioc3_cad_duo_setup(ipd);
+}
+
+static int ioc3_mfd_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *pci_id)
+{
+	struct ioc3_priv_data *ipd;
+	struct ioc3 __iomem *regs;
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret)
+		return ret;
+
+	pci_write_config_byte(pdev, PCI_LATENCY_TIMER, IOC3_LATENCY);
+	pci_set_master(pdev);
+
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		pr_err("%s: No usable DMA configuration, aborting.\n",
+		       pci_name(pdev));
+		goto out_disable_device;
+	}
+
+	/* Set up per-IOC3 data */
+	ipd = devm_kzalloc(&pdev->dev, sizeof(struct ioc3_priv_data),
+			   GFP_KERNEL);
+	if (!ipd) {
+		ret = -ENOMEM;
+		goto out_disable_device;
+	}
+	ipd->pdev = pdev;
+
+	/*
+	 * Map all IOC3 registers.  These are shared between subdevices
+	 * so the main IOC3 module manages them.
+	 */
+	regs = pci_ioremap_bar(pdev, 0);
+	if (!regs) {
+		dev_warn(&pdev->dev, "ioc3: Unable to remap PCI BAR for %s.\n",
+			 pci_name(pdev));
+		ret = -ENOMEM;
+		goto out_disable_device;
+	}
+	ipd->regs = regs;
+
+	/* Track PCI-device specific data */
+	pci_set_drvdata(pdev, ipd);
+
+	ret = ioc3_setup(ipd);
+	if (ret) {
+		/* Remove all already added MFD devices */
+		mfd_remove_devices(&ipd->pdev->dev);
+		if (ipd->domain) {
+			irq_domain_remove(ipd->domain);
+			free_irq(ipd->domain_irq, (void *)ipd);
+		}
+		pci_iounmap(pdev, regs);
+		goto out_disable_device;
+	}
+
+	return 0;
+
+out_disable_device:
+	pci_disable_device(pdev);
+	return ret;
+}
+
+static void ioc3_mfd_remove(struct pci_dev *pdev)
+{
+	struct ioc3_priv_data *ipd;
+
+	ipd = pci_get_drvdata(pdev);
+
+	/* Clear and disable all IRQs */
+	writel(~0, &ipd->regs->sio_iec);
+	writel(~0, &ipd->regs->sio_ir);
+
+	/* Release resources */
+	mfd_remove_devices(&ipd->pdev->dev);
+	if (ipd->domain) {
+		irq_domain_remove(ipd->domain);
+		free_irq(ipd->domain_irq, (void *)ipd);
+	}
+	pci_iounmap(pdev, ipd->regs);
+	pci_disable_device(pdev);
+}
+
+static struct pci_device_id ioc3_mfd_id_table[] = {
+	{ PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3, PCI_ANY_ID, PCI_ANY_ID },
+	{ 0, },
+};
+MODULE_DEVICE_TABLE(pci, ioc3_mfd_id_table);
+
+static struct pci_driver ioc3_mfd_driver = {
+	.name = "IOC3",
+	.id_table = ioc3_mfd_id_table,
+	.probe = ioc3_mfd_probe,
+	.remove = ioc3_mfd_remove,
+};
+
+module_pci_driver(ioc3_mfd_driver);
+
+MODULE_AUTHOR("Thomas Bogendoerfer <tbogendoerfer@suse.de>");
+MODULE_DESCRIPTION("SGI IOC3 MFD driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/madera-core.c b/drivers/mfd/madera-core.c
index a8cfadc1fc01..7e0835cb062b 100644
--- a/drivers/mfd/madera-core.c
+++ b/drivers/mfd/madera-core.c
@@ -35,6 +35,9 @@
 
 #define MADERA_32KZ_MCLK2	1
 
+#define MADERA_RESET_MIN_US	2000
+#define MADERA_RESET_MAX_US	3000
+
 static const char * const madera_core_supplies[] = {
 	"AVDD",
 	"DBVDD1",
@@ -199,7 +202,7 @@ EXPORT_SYMBOL_GPL(madera_name_from_type);
 #define MADERA_BOOT_POLL_INTERVAL_USEC		5000
 #define MADERA_BOOT_POLL_TIMEOUT_USEC		25000
 
-static int madera_wait_for_boot(struct madera *madera)
+static int madera_wait_for_boot_noack(struct madera *madera)
 {
 	ktime_t timeout;
 	unsigned int val = 0;
@@ -226,6 +229,13 @@ static int madera_wait_for_boot(struct madera *madera)
 		ret = -ETIMEDOUT;
 	}
 
+	return ret;
+}
+
+static int madera_wait_for_boot(struct madera *madera)
+{
+	int ret = madera_wait_for_boot_noack(madera);
+
 	/*
 	 * BOOT_DONE defaults to unmasked on boot so we must ack it.
 	 * Do this even after a timeout to avoid interrupt storms.
@@ -249,16 +259,13 @@ static int madera_soft_reset(struct madera *madera)
 	}
 
 	/* Allow time for internal clocks to startup after reset */
-	usleep_range(1000, 2000);
+	usleep_range(MADERA_RESET_MIN_US, MADERA_RESET_MAX_US);
 
 	return 0;
 }
 
 static void madera_enable_hard_reset(struct madera *madera)
 {
-	if (!madera->pdata.reset)
-		return;
-
 	/*
 	 * There are many existing out-of-tree users of these codecs that we
 	 * can't break so preserve the expected behaviour of setting the line
@@ -269,11 +276,9 @@ static void madera_enable_hard_reset(struct madera *madera)
 
 static void madera_disable_hard_reset(struct madera *madera)
 {
-	if (!madera->pdata.reset)
-		return;
-
 	gpiod_set_raw_value_cansleep(madera->pdata.reset, 1);
-	usleep_range(1000, 2000);
+
+	usleep_range(MADERA_RESET_MIN_US, MADERA_RESET_MAX_US);
 }
 
 static int __maybe_unused madera_runtime_resume(struct device *dev)
@@ -292,6 +297,8 @@ static int __maybe_unused madera_runtime_resume(struct device *dev)
 	regcache_cache_only(madera->regmap, false);
 	regcache_cache_only(madera->regmap_32bit, false);
 
+	usleep_range(MADERA_RESET_MIN_US, MADERA_RESET_MAX_US);
+
 	ret = madera_wait_for_boot(madera);
 	if (ret)
 		goto err;
@@ -545,6 +552,12 @@ int madera_dev_init(struct madera *madera)
 	regcache_cache_only(madera->regmap, false);
 	regcache_cache_only(madera->regmap_32bit, false);
 
+	ret = madera_wait_for_boot_noack(madera);
+	if (ret) {
+		dev_err(madera->dev, "Device failed initial boot: %d\n", ret);
+		goto err_reset;
+	}
+
 	/*
 	 * Now we can power up and verify that this is a chip we know about
 	 * before we start doing any writes to its registers.
@@ -650,7 +663,7 @@ int madera_dev_init(struct madera *madera)
 
 	ret = madera_wait_for_boot(madera);
 	if (ret) {
-		dev_err(madera->dev, "Device failed initial boot: %d\n", ret);
+		dev_err(madera->dev, "Failed to clear boot done: %d\n", ret);
 		goto err_reset;
 	}
 
diff --git a/drivers/mfd/rn5t618.c b/drivers/mfd/rn5t618.c
index da5cd9c92a59..ead2e79036a9 100644
--- a/drivers/mfd/rn5t618.c
+++ b/drivers/mfd/rn5t618.c
@@ -26,6 +26,7 @@ static bool rn5t618_volatile_reg(struct device *dev, unsigned int reg)
 	case RN5T618_WATCHDOGCNT:
 	case RN5T618_DCIRQ:
 	case RN5T618_ILIMDATAH ... RN5T618_AIN0DATAL:
+	case RN5T618_ADCCNT3:
 	case RN5T618_IR_ADC1 ... RN5T618_IR_ADC3:
 	case RN5T618_IR_GPR:
 	case RN5T618_IR_GPF:
diff --git a/drivers/mfd/rohm-bd70528.c b/drivers/mfd/rohm-bd70528.c
index ef6786fd3b00..5c44d3b77b3e 100644
--- a/drivers/mfd/rohm-bd70528.c
+++ b/drivers/mfd/rohm-bd70528.c
@@ -48,7 +48,7 @@ static struct mfd_cell bd70528_mfd_cells[] = {
 	 * We use BD71837 driver to drive the clock block. Only differences to
 	 * BD70528 clock gate are the register address and mask.
 	 */
-	{ .name = "bd718xx-clk", },
+	{ .name = "bd70528-clk", },
 	{ .name = "bd70528-wdt", },
 	{
 		.name = "bd70528-power",
@@ -236,7 +236,6 @@ static int bd70528_i2c_probe(struct i2c_client *i2c,
 
 	dev_set_drvdata(&i2c->dev, &bd70528->chip);
 
-	bd70528->chip.chip_type = ROHM_CHIP_TYPE_BD70528;
 	bd70528->chip.regmap = devm_regmap_init_i2c(i2c, &bd70528_regmap);
 	if (IS_ERR(bd70528->chip.regmap)) {
 		dev_err(&i2c->dev, "Failed to initialize Regmap\n");
diff --git a/drivers/mfd/rohm-bd71828.c b/drivers/mfd/rohm-bd71828.c
new file mode 100644
index 000000000000..210261d026f2
--- /dev/null
+++ b/drivers/mfd/rohm-bd71828.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright (C) 2019 ROHM Semiconductors
+//
+// ROHM BD71828 PMIC driver
+
+#include <linux/gpio_keys.h>
+#include <linux/i2c.h>
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rohm-bd71828.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/types.h>
+
+static struct gpio_keys_button button = {
+	.code = KEY_POWER,
+	.gpio = -1,
+	.type = EV_KEY,
+};
+
+static struct gpio_keys_platform_data bd71828_powerkey_data = {
+	.buttons = &button,
+	.nbuttons = 1,
+	.name = "bd71828-pwrkey",
+};
+
+static const struct resource rtc_irqs[] = {
+	DEFINE_RES_IRQ_NAMED(BD71828_INT_RTC0, "bd71828-rtc-alm-0"),
+	DEFINE_RES_IRQ_NAMED(BD71828_INT_RTC1, "bd71828-rtc-alm-1"),
+	DEFINE_RES_IRQ_NAMED(BD71828_INT_RTC2, "bd71828-rtc-alm-2"),
+};
+
+static struct mfd_cell bd71828_mfd_cells[] = {
+	{ .name = "bd71828-pmic", },
+	{ .name = "bd71828-gpio", },
+	{ .name = "bd71828-led", .of_compatible = "rohm,bd71828-leds" },
+	/*
+	 * We use BD71837 driver to drive the clock block. Only differences to
+	 * BD70528 clock gate are the register address and mask.
+	 */
+	{ .name = "bd71828-clk", },
+	{ .name = "bd71827-power", },
+	{
+		.name = "bd71828-rtc",
+		.resources = rtc_irqs,
+		.num_resources = ARRAY_SIZE(rtc_irqs),
+	}, {
+		.name = "gpio-keys",
+		.platform_data = &bd71828_powerkey_data,
+		.pdata_size = sizeof(bd71828_powerkey_data),
+	},
+};
+
+static const struct regmap_range volatile_ranges[] = {
+	{
+		.range_min = BD71828_REG_PS_CTRL_1,
+		.range_max = BD71828_REG_PS_CTRL_1,
+	}, {
+		.range_min = BD71828_REG_PS_CTRL_3,
+		.range_max = BD71828_REG_PS_CTRL_3,
+	}, {
+		.range_min = BD71828_REG_RTC_SEC,
+		.range_max = BD71828_REG_RTC_YEAR,
+	}, {
+		/*
+		 * For now make all charger registers volatile because many
+		 * needs to be and because the charger block is not that
+		 * performance critical.
+		 */
+		.range_min = BD71828_REG_CHG_STATE,
+		.range_max = BD71828_REG_CHG_FULL,
+	}, {
+		.range_min = BD71828_REG_INT_MAIN,
+		.range_max = BD71828_REG_IO_STAT,
+	},
+};
+
+static const struct regmap_access_table volatile_regs = {
+	.yes_ranges = &volatile_ranges[0],
+	.n_yes_ranges = ARRAY_SIZE(volatile_ranges),
+};
+
+static struct regmap_config bd71828_regmap = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.volatile_table = &volatile_regs,
+	.max_register = BD71828_MAX_REGISTER,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+/*
+ * Mapping of main IRQ register bits to sub-IRQ register offsets so that we can
+ * access corect sub-IRQ registers based on bits that are set in main IRQ
+ * register.
+ */
+
+static unsigned int bit0_offsets[] = {11};		/* RTC IRQ */
+static unsigned int bit1_offsets[] = {10};		/* TEMP IRQ */
+static unsigned int bit2_offsets[] = {6, 7, 8, 9};	/* BAT MON IRQ */
+static unsigned int bit3_offsets[] = {5};		/* BAT IRQ */
+static unsigned int bit4_offsets[] = {4};		/* CHG IRQ */
+static unsigned int bit5_offsets[] = {3};		/* VSYS IRQ */
+static unsigned int bit6_offsets[] = {1, 2};		/* DCIN IRQ */
+static unsigned int bit7_offsets[] = {0};		/* BUCK IRQ */
+
+static struct regmap_irq_sub_irq_map bd71828_sub_irq_offsets[] = {
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit0_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit1_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit2_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit3_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit4_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit5_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit6_offsets),
+	REGMAP_IRQ_MAIN_REG_OFFSET(bit7_offsets),
+};
+
+static struct regmap_irq bd71828_irqs[] = {
+	REGMAP_IRQ_REG(BD71828_INT_BUCK1_OCP, 0, BD71828_INT_BUCK1_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BUCK2_OCP, 0, BD71828_INT_BUCK2_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BUCK3_OCP, 0, BD71828_INT_BUCK3_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BUCK4_OCP, 0, BD71828_INT_BUCK4_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BUCK5_OCP, 0, BD71828_INT_BUCK5_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BUCK6_OCP, 0, BD71828_INT_BUCK6_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BUCK7_OCP, 0, BD71828_INT_BUCK7_OCP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_PGFAULT, 0, BD71828_INT_PGFAULT_MASK),
+	/* DCIN1 interrupts */
+	REGMAP_IRQ_REG(BD71828_INT_DCIN_DET, 1, BD71828_INT_DCIN_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_DCIN_RMV, 1, BD71828_INT_DCIN_RMV_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CLPS_OUT, 1, BD71828_INT_CLPS_OUT_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CLPS_IN, 1, BD71828_INT_CLPS_IN_MASK),
+	/* DCIN2 interrupts */
+	REGMAP_IRQ_REG(BD71828_INT_DCIN_MON_RES, 2,
+		       BD71828_INT_DCIN_MON_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_DCIN_MON_DET, 2,
+		       BD71828_INT_DCIN_MON_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_LONGPUSH, 2, BD71828_INT_LONGPUSH_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_MIDPUSH, 2, BD71828_INT_MIDPUSH_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_SHORTPUSH, 2, BD71828_INT_SHORTPUSH_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_PUSH, 2, BD71828_INT_PUSH_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_WDOG, 2, BD71828_INT_WDOG_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_SWRESET, 2, BD71828_INT_SWRESET_MASK),
+	/* Vsys */
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_UV_RES, 3,
+		       BD71828_INT_VSYS_UV_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_UV_DET, 3,
+		       BD71828_INT_VSYS_UV_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_LOW_RES, 3,
+		       BD71828_INT_VSYS_LOW_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_LOW_DET, 3,
+		       BD71828_INT_VSYS_LOW_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_HALL_IN, 3,
+		       BD71828_INT_VSYS_HALL_IN_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_HALL_TOGGLE, 3,
+		       BD71828_INT_VSYS_HALL_TOGGLE_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_MON_RES, 3,
+		       BD71828_INT_VSYS_MON_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_VSYS_MON_DET, 3,
+		       BD71828_INT_VSYS_MON_DET_MASK),
+	/* Charger */
+	REGMAP_IRQ_REG(BD71828_INT_CHG_DCIN_ILIM, 4,
+		       BD71828_INT_CHG_DCIN_ILIM_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_TOPOFF_TO_DONE, 4,
+		       BD71828_INT_CHG_TOPOFF_TO_DONE_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_WDG_TEMP, 4,
+		       BD71828_INT_CHG_WDG_TEMP_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_WDG_TIME, 4,
+		       BD71828_INT_CHG_WDG_TIME_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_RECHARGE_RES, 4,
+		       BD71828_INT_CHG_RECHARGE_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_RECHARGE_DET, 4,
+		       BD71828_INT_CHG_RECHARGE_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_RANGED_TEMP_TRANSITION, 4,
+		       BD71828_INT_CHG_RANGED_TEMP_TRANSITION_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_CHG_STATE_TRANSITION, 4,
+		       BD71828_INT_CHG_STATE_TRANSITION_MASK),
+	/* Battery */
+	REGMAP_IRQ_REG(BD71828_INT_BAT_TEMP_NORMAL, 5,
+		       BD71828_INT_BAT_TEMP_NORMAL_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_TEMP_ERANGE, 5,
+		       BD71828_INT_BAT_TEMP_ERANGE_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_TEMP_WARN, 5,
+		       BD71828_INT_BAT_TEMP_WARN_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_REMOVED, 5,
+		       BD71828_INT_BAT_REMOVED_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_DETECTED, 5,
+		       BD71828_INT_BAT_DETECTED_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_THERM_REMOVED, 5,
+		       BD71828_INT_THERM_REMOVED_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_THERM_DETECTED, 5,
+		       BD71828_INT_THERM_DETECTED_MASK),
+	/* Battery Mon 1 */
+	REGMAP_IRQ_REG(BD71828_INT_BAT_DEAD, 6, BD71828_INT_BAT_DEAD_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_SHORTC_RES, 6,
+		       BD71828_INT_BAT_SHORTC_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_SHORTC_DET, 6,
+		       BD71828_INT_BAT_SHORTC_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_LOW_VOLT_RES, 6,
+		       BD71828_INT_BAT_LOW_VOLT_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_LOW_VOLT_DET, 6,
+		       BD71828_INT_BAT_LOW_VOLT_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_VOLT_RES, 6,
+		       BD71828_INT_BAT_OVER_VOLT_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_VOLT_DET, 6,
+		       BD71828_INT_BAT_OVER_VOLT_DET_MASK),
+	/* Battery Mon 2 */
+	REGMAP_IRQ_REG(BD71828_INT_BAT_MON_RES, 7,
+		       BD71828_INT_BAT_MON_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_MON_DET, 7,
+		       BD71828_INT_BAT_MON_DET_MASK),
+	/* Battery Mon 3 (Coulomb counter) */
+	REGMAP_IRQ_REG(BD71828_INT_BAT_CC_MON1, 8,
+		       BD71828_INT_BAT_CC_MON1_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_CC_MON2, 8,
+		       BD71828_INT_BAT_CC_MON2_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_CC_MON3, 8,
+		       BD71828_INT_BAT_CC_MON3_MASK),
+	/* Battery Mon 4 */
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_CURR_1_RES, 9,
+		       BD71828_INT_BAT_OVER_CURR_1_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_CURR_1_DET, 9,
+		       BD71828_INT_BAT_OVER_CURR_1_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_CURR_2_RES, 9,
+		       BD71828_INT_BAT_OVER_CURR_2_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_CURR_2_DET, 9,
+		       BD71828_INT_BAT_OVER_CURR_2_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_CURR_3_RES, 9,
+		       BD71828_INT_BAT_OVER_CURR_3_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_BAT_OVER_CURR_3_DET, 9,
+		       BD71828_INT_BAT_OVER_CURR_3_DET_MASK),
+	/* Temperature */
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_BAT_LOW_RES, 10,
+		       BD71828_INT_TEMP_BAT_LOW_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_BAT_LOW_DET, 10,
+		       BD71828_INT_TEMP_BAT_LOW_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_BAT_HI_RES, 10,
+		       BD71828_INT_TEMP_BAT_HI_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_BAT_HI_DET, 10,
+		       BD71828_INT_TEMP_BAT_HI_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_CHIP_OVER_125_RES, 10,
+		       BD71828_INT_TEMP_CHIP_OVER_125_RES_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_CHIP_OVER_125_DET, 10,
+		       BD71828_INT_TEMP_CHIP_OVER_125_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_CHIP_OVER_VF_DET, 10,
+		       BD71828_INT_TEMP_CHIP_OVER_VF_DET_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_TEMP_CHIP_OVER_VF_RES, 10,
+		       BD71828_INT_TEMP_CHIP_OVER_VF_RES_MASK),
+	/* RTC Alarm */
+	REGMAP_IRQ_REG(BD71828_INT_RTC0, 11, BD71828_INT_RTC0_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_RTC1, 11, BD71828_INT_RTC1_MASK),
+	REGMAP_IRQ_REG(BD71828_INT_RTC2, 11, BD71828_INT_RTC2_MASK),
+};
+
+static struct regmap_irq_chip bd71828_irq_chip = {
+	.name = "bd71828_irq",
+	.main_status = BD71828_REG_INT_MAIN,
+	.irqs = &bd71828_irqs[0],
+	.num_irqs = ARRAY_SIZE(bd71828_irqs),
+	.status_base = BD71828_REG_INT_BUCK,
+	.mask_base = BD71828_REG_INT_MASK_BUCK,
+	.ack_base = BD71828_REG_INT_BUCK,
+	.mask_invert = true,
+	.init_ack_masked = true,
+	.num_regs = 12,
+	.num_main_regs = 1,
+	.sub_reg_offsets = &bd71828_sub_irq_offsets[0],
+	.num_main_status_bits = 8,
+	.irq_reg_stride = 1,
+};
+
+static int bd71828_i2c_probe(struct i2c_client *i2c)
+{
+	struct rohm_regmap_dev *chip;
+	struct regmap_irq_chip_data *irq_data;
+	int ret;
+
+	if (!i2c->irq) {
+		dev_err(&i2c->dev, "No IRQ configured\n");
+		return -EINVAL;
+	}
+
+	chip = devm_kzalloc(&i2c->dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	dev_set_drvdata(&i2c->dev, chip);
+
+	chip->regmap = devm_regmap_init_i2c(i2c, &bd71828_regmap);
+	if (IS_ERR(chip->regmap)) {
+		dev_err(&i2c->dev, "Failed to initialize Regmap\n");
+		return PTR_ERR(chip->regmap);
+	}
+
+	ret = devm_regmap_add_irq_chip(&i2c->dev, chip->regmap,
+				       i2c->irq, IRQF_ONESHOT, 0,
+				       &bd71828_irq_chip, &irq_data);
+	if (ret) {
+		dev_err(&i2c->dev, "Failed to add IRQ chip\n");
+		return ret;
+	}
+
+	dev_dbg(&i2c->dev, "Registered %d IRQs for chip\n",
+		bd71828_irq_chip.num_irqs);
+
+	ret = regmap_irq_get_virq(irq_data, BD71828_INT_SHORTPUSH);
+	if (ret < 0) {
+		dev_err(&i2c->dev, "Failed to get the power-key IRQ\n");
+		return ret;
+	}
+
+	button.irq = ret;
+
+	ret = devm_mfd_add_devices(&i2c->dev, PLATFORM_DEVID_AUTO,
+				   bd71828_mfd_cells,
+				   ARRAY_SIZE(bd71828_mfd_cells), NULL, 0,
+				   regmap_irq_get_domain(irq_data));
+	if (ret)
+		dev_err(&i2c->dev, "Failed to create subdevices\n");
+
+	return ret;
+}
+
+static const struct of_device_id bd71828_of_match[] = {
+	{ .compatible = "rohm,bd71828", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, bd71828_of_match);
+
+static struct i2c_driver bd71828_drv = {
+	.driver = {
+		.name = "rohm-bd71828",
+		.of_match_table = bd71828_of_match,
+	},
+	.probe_new = &bd71828_i2c_probe,
+};
+module_i2c_driver(bd71828_drv);
+
+MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
+MODULE_DESCRIPTION("ROHM BD71828 Power Management IC driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/rohm-bd718x7.c b/drivers/mfd/rohm-bd718x7.c
index 85e7f5133365..c32c1b6c98fa 100644
--- a/drivers/mfd/rohm-bd718x7.c
+++ b/drivers/mfd/rohm-bd718x7.c
@@ -30,14 +30,24 @@ static struct gpio_keys_platform_data bd718xx_powerkey_data = {
 	.name = "bd718xx-pwrkey",
 };
 
-static struct mfd_cell bd718xx_mfd_cells[] = {
+static struct mfd_cell bd71837_mfd_cells[] = {
 	{
 		.name = "gpio-keys",
 		.platform_data = &bd718xx_powerkey_data,
 		.pdata_size = sizeof(bd718xx_powerkey_data),
 	},
-	{ .name = "bd718xx-clk", },
-	{ .name = "bd718xx-pmic", },
+	{ .name = "bd71837-clk", },
+	{ .name = "bd71837-pmic", },
+};
+
+static struct mfd_cell bd71847_mfd_cells[] = {
+	{
+		.name = "gpio-keys",
+		.platform_data = &bd718xx_powerkey_data,
+		.pdata_size = sizeof(bd718xx_powerkey_data),
+	},
+	{ .name = "bd71847-clk", },
+	{ .name = "bd71847-pmic", },
 };
 
 static const struct regmap_irq bd718xx_irqs[] = {
@@ -124,6 +134,9 @@ static int bd718xx_i2c_probe(struct i2c_client *i2c,
 {
 	struct bd718xx *bd718xx;
 	int ret;
+	unsigned int chip_type;
+	struct mfd_cell *mfd;
+	int cells;
 
 	if (!i2c->irq) {
 		dev_err(&i2c->dev, "No IRQ configured\n");
@@ -136,8 +149,21 @@ static int bd718xx_i2c_probe(struct i2c_client *i2c,
 		return -ENOMEM;
 
 	bd718xx->chip_irq = i2c->irq;
-	bd718xx->chip.chip_type = (unsigned int)(uintptr_t)
-				of_device_get_match_data(&i2c->dev);
+	chip_type = (unsigned int)(uintptr_t)
+		    of_device_get_match_data(&i2c->dev);
+	switch (chip_type) {
+	case ROHM_CHIP_TYPE_BD71837:
+		mfd = bd71837_mfd_cells;
+		cells = ARRAY_SIZE(bd71837_mfd_cells);
+		break;
+	case ROHM_CHIP_TYPE_BD71847:
+		mfd = bd71847_mfd_cells;
+		cells = ARRAY_SIZE(bd71847_mfd_cells);
+		break;
+	default:
+		dev_err(&i2c->dev, "Unknown device type");
+		return -EINVAL;
+	}
 	bd718xx->chip.dev = &i2c->dev;
 	dev_set_drvdata(&i2c->dev, bd718xx);
 
@@ -170,8 +196,7 @@ static int bd718xx_i2c_probe(struct i2c_client *i2c,
 	button.irq = ret;
 
 	ret = devm_mfd_add_devices(bd718xx->chip.dev, PLATFORM_DEVID_AUTO,
-				   bd718xx_mfd_cells,
-				   ARRAY_SIZE(bd718xx_mfd_cells), NULL, 0,
+				   mfd, cells, NULL, 0,
 				   regmap_irq_get_domain(bd718xx->irq_data));
 	if (ret)
 		dev_err(&i2c->dev, "Failed to create subdevices\n");
@@ -188,6 +213,10 @@ static const struct of_device_id bd718xx_of_match[] = {
 		.compatible = "rohm,bd71847",
 		.data = (void *)ROHM_CHIP_TYPE_BD71847,
 	},
+	{
+		.compatible = "rohm,bd71850",
+		.data = (void *)ROHM_CHIP_TYPE_BD71847,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, bd718xx_of_match);
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index 154270f8d8d7..e49787e6bb93 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -1086,8 +1086,7 @@ static int sm501_register_gpio(struct sm501_devdata *sm)
 	iounmap(gpio->regs);
 
  err_claimed:
-	release_resource(gpio->regs_res);
-	kfree(gpio->regs_res);
+	release_mem_region(iobase, 0x20);
 
 	return ret;
 }
@@ -1095,6 +1094,7 @@ static int sm501_register_gpio(struct sm501_devdata *sm)
 static void sm501_gpio_remove(struct sm501_devdata *sm)
 {
 	struct sm501_gpio *gpio = &sm->gpio;
+	resource_size_t iobase = sm->io_res->start + SM501_GPIO;
 
 	if (!sm->gpio.registered)
 		return;
@@ -1103,8 +1103,7 @@ static void sm501_gpio_remove(struct sm501_devdata *sm)
 	gpiochip_remove(&gpio->high.gpio);
 
 	iounmap(gpio->regs);
-	release_resource(gpio->regs_res);
-	kfree(gpio->regs_res);
+	release_mem_region(iobase, 0x20);
 }
 
 static inline int sm501_gpio_isregistered(struct sm501_devdata *sm)
@@ -1427,8 +1426,7 @@ static int sm501_plat_probe(struct platform_device *dev)
 	return sm501_init_dev(sm);
 
  err_claim:
-	release_resource(sm->regs_claim);
-	kfree(sm->regs_claim);
+	release_mem_region(sm->io_res->start, 0x100);
  err_res:
 	kfree(sm);
  err1:
@@ -1637,8 +1635,7 @@ static int sm501_pci_probe(struct pci_dev *dev,
 	return 0;
 
  err4:
-	release_resource(sm->regs_claim);
-	kfree(sm->regs_claim);
+	release_mem_region(sm->io_res->start, 0x100);
  err3:
 	pci_disable_device(dev);
  err2:
@@ -1673,8 +1670,7 @@ static void sm501_pci_remove(struct pci_dev *dev)
 	sm501_dev_remove(sm);
 	iounmap(sm->regs);
 
-	release_resource(sm->regs_claim);
-	kfree(sm->regs_claim);
+	release_mem_region(sm->io_res->start, 0x100);
 
 	pci_disable_device(dev);
 }
@@ -1686,8 +1682,7 @@ static int sm501_plat_remove(struct platform_device *dev)
 	sm501_dev_remove(sm);
 	iounmap(sm->regs);
 
-	release_resource(sm->regs_claim);
-	kfree(sm->regs_claim);
+	release_mem_region(sm->io_res->start, 0x100);
 
 	return 0;
 }
diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c
index e22197c832e8..3a97816d0cba 100644
--- a/drivers/mfd/syscon.c
+++ b/drivers/mfd/syscon.c
@@ -224,6 +224,35 @@ struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np,
 }
 EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle);
 
+struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np,
+					const char *property,
+					int arg_count,
+					unsigned int *out_args)
+{
+	struct device_node *syscon_np;
+	struct of_phandle_args args;
+	struct regmap *regmap;
+	unsigned int index;
+	int rc;
+
+	rc = of_parse_phandle_with_fixed_args(np, property, arg_count,
+			0, &args);
+	if (rc)
+		return ERR_PTR(rc);
+
+	syscon_np = args.np;
+	if (!syscon_np)
+		return ERR_PTR(-ENODEV);
+
+	regmap = syscon_node_to_regmap(syscon_np);
+	for (index = 0; index < arg_count; index++)
+		out_args[index] = args.args[index];
+	of_node_put(syscon_np);
+
+	return regmap;
+}
+EXPORT_SYMBOL_GPL(syscon_regmap_lookup_by_phandle_args);
+
 static int syscon_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -245,7 +274,7 @@ static int syscon_probe(struct platform_device *pdev)
 	if (!base)
 		return -ENOMEM;
 
-	syscon_config.max_register = res->end - res->start - 3;
+	syscon_config.max_register = resource_size(res) - 4;
 	if (pdata)
 		syscon_config.name = pdata->label;
 	syscon->regmap = devm_regmap_init_mmio(dev, base, &syscon_config);
diff --git a/drivers/mfd/tqmx86.c b/drivers/mfd/tqmx86.c
index 22d2f02d855c..b9f48e588d95 100644
--- a/drivers/mfd/tqmx86.c
+++ b/drivers/mfd/tqmx86.c
@@ -158,7 +158,7 @@ static int tqmx86_board_id_to_clk_rate(u8 board_id)
 
 static int tqmx86_probe(struct platform_device *pdev)
 {
-	u8 board_id, rev, i2c_det, i2c_ien, io_ext_int_val;
+	u8 board_id, rev, i2c_det, io_ext_int_val;
 	struct device *dev = &pdev->dev;
 	u8 gpio_irq_cfg, readback;
 	const char *board_name;
@@ -196,7 +196,6 @@ static int tqmx86_probe(struct platform_device *pdev)
 		 board_name, board_id, rev >> 4, rev & 0xf);
 
 	i2c_det = ioread8(io_base + TQMX86_REG_I2C_DETECT);
-	i2c_ien = ioread8(io_base + TQMX86_REG_I2C_INT_EN);
 
 	if (gpio_irq_cfg) {
 		io_ext_int_val =
diff --git a/drivers/mfd/wcd934x.c b/drivers/mfd/wcd934x.c
new file mode 100644
index 000000000000..90341f3c6810
--- /dev/null
+++ b/drivers/mfd/wcd934x.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019, Linaro Limited
+
+#include <linux/clk.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/wcd934x/registers.h>
+#include <linux/mfd/wcd934x/wcd934x.h>
+#include <linux/module.h>
+#include <linux/of_gpio.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slimbus.h>
+
+static const struct mfd_cell wcd934x_devices[] = {
+	{
+		.name = "wcd934x-codec",
+	}, {
+		.name = "wcd934x-gpio",
+		.of_compatible = "qcom,wcd9340-gpio",
+	}, {
+		.name = "wcd934x-soundwire",
+		.of_compatible = "qcom,soundwire-v1.3.0",
+	},
+};
+
+static const struct regmap_irq wcd934x_irqs[] = {
+	[WCD934X_IRQ_SLIMBUS] = {
+		.reg_offset = 0,
+		.mask = BIT(0),
+		.type = {
+			.type_reg_offset = 0,
+			.types_supported = IRQ_TYPE_EDGE_BOTH,
+			.type_reg_mask  = BIT(0),
+			.type_level_low_val = BIT(0),
+			.type_level_high_val = BIT(0),
+			.type_falling_val = 0,
+			.type_rising_val = 0,
+		},
+	},
+	[WCD934X_IRQ_SOUNDWIRE] = {
+		.reg_offset = 2,
+		.mask = BIT(4),
+		.type = {
+			.type_reg_offset = 2,
+			.types_supported = IRQ_TYPE_EDGE_BOTH,
+			.type_reg_mask  = BIT(4),
+			.type_level_low_val = BIT(4),
+			.type_level_high_val = BIT(4),
+			.type_falling_val = 0,
+			.type_rising_val = 0,
+		},
+	},
+};
+
+static const struct regmap_irq_chip wcd934x_regmap_irq_chip = {
+	.name = "wcd934x_irq",
+	.status_base = WCD934X_INTR_PIN1_STATUS0,
+	.mask_base = WCD934X_INTR_PIN1_MASK0,
+	.ack_base = WCD934X_INTR_PIN1_CLEAR0,
+	.type_base = WCD934X_INTR_LEVEL0,
+	.num_type_reg = 4,
+	.type_in_mask = false,
+	.num_regs = 4,
+	.irqs = wcd934x_irqs,
+	.num_irqs = ARRAY_SIZE(wcd934x_irqs),
+};
+
+static bool wcd934x_is_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case WCD934X_INTR_PIN1_STATUS0...WCD934X_INTR_PIN2_CLEAR3:
+	case WCD934X_SWR_AHB_BRIDGE_RD_DATA_0:
+	case WCD934X_SWR_AHB_BRIDGE_RD_DATA_1:
+	case WCD934X_SWR_AHB_BRIDGE_RD_DATA_2:
+	case WCD934X_SWR_AHB_BRIDGE_RD_DATA_3:
+	case WCD934X_SWR_AHB_BRIDGE_ACCESS_STATUS:
+	case WCD934X_ANA_MBHC_RESULT_3:
+	case WCD934X_ANA_MBHC_RESULT_2:
+	case WCD934X_ANA_MBHC_RESULT_1:
+	case WCD934X_ANA_MBHC_MECH:
+	case WCD934X_ANA_MBHC_ELECT:
+	case WCD934X_ANA_MBHC_ZDET:
+	case WCD934X_ANA_MICB2:
+	case WCD934X_ANA_RCO:
+	case WCD934X_ANA_BIAS:
+		return true;
+	default:
+		return false;
+	}
+};
+
+static const struct regmap_range_cfg wcd934x_ranges[] = {
+	{	.name = "WCD934X",
+		.range_min =  0x0,
+		.range_max =  WCD934X_MAX_REGISTER,
+		.selector_reg = WCD934X_SEL_REGISTER,
+		.selector_mask = WCD934X_SEL_MASK,
+		.selector_shift = WCD934X_SEL_SHIFT,
+		.window_start = WCD934X_WINDOW_START,
+		.window_len = WCD934X_WINDOW_LENGTH,
+	},
+};
+
+static struct regmap_config wcd934x_regmap_config = {
+	.reg_bits = 16,
+	.val_bits = 8,
+	.cache_type = REGCACHE_RBTREE,
+	.max_register = 0xffff,
+	.can_multi_write = true,
+	.ranges = wcd934x_ranges,
+	.num_ranges = ARRAY_SIZE(wcd934x_ranges),
+	.volatile_reg = wcd934x_is_volatile_register,
+};
+
+static int wcd934x_bring_up(struct wcd934x_ddata *ddata)
+{
+	struct regmap *regmap = ddata->regmap;
+	u16 id_minor, id_major;
+	int ret;
+
+	ret = regmap_bulk_read(regmap, WCD934X_CHIP_TIER_CTRL_CHIP_ID_BYTE0,
+			       (u8 *)&id_minor, sizeof(u16));
+	if (ret)
+		return ret;
+
+	ret = regmap_bulk_read(regmap, WCD934X_CHIP_TIER_CTRL_CHIP_ID_BYTE2,
+			       (u8 *)&id_major, sizeof(u16));
+	if (ret)
+		return ret;
+
+	dev_info(ddata->dev, "WCD934x chip id major 0x%x, minor 0x%x\n",
+		 id_major, id_minor);
+
+	regmap_write(regmap, WCD934X_CODEC_RPM_RST_CTL, 0x01);
+	regmap_write(regmap, WCD934X_SIDO_NEW_VOUT_A_STARTUP, 0x19);
+	regmap_write(regmap, WCD934X_SIDO_NEW_VOUT_D_STARTUP, 0x15);
+	/* Add 1msec delay for VOUT to settle */
+	usleep_range(1000, 1100);
+	regmap_write(regmap, WCD934X_CODEC_RPM_PWR_CDC_DIG_HM_CTL, 0x5);
+	regmap_write(regmap, WCD934X_CODEC_RPM_PWR_CDC_DIG_HM_CTL, 0x7);
+	regmap_write(regmap, WCD934X_CODEC_RPM_RST_CTL, 0x3);
+	regmap_write(regmap, WCD934X_CODEC_RPM_RST_CTL, 0x7);
+	regmap_write(regmap, WCD934X_CODEC_RPM_PWR_CDC_DIG_HM_CTL, 0x3);
+
+	return 0;
+}
+
+static int wcd934x_slim_status_up(struct slim_device *sdev)
+{
+	struct device *dev = &sdev->dev;
+	struct wcd934x_ddata *ddata;
+	int ret;
+
+	ddata = dev_get_drvdata(dev);
+
+	ddata->regmap = regmap_init_slimbus(sdev, &wcd934x_regmap_config);
+	if (IS_ERR(ddata->regmap)) {
+		dev_err(dev, "Error allocating slim regmap\n");
+		return PTR_ERR(ddata->regmap);
+	}
+
+	ret = wcd934x_bring_up(ddata);
+	if (ret) {
+		dev_err(dev, "Failed to bring up WCD934X: err = %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_regmap_add_irq_chip(dev, ddata->regmap, ddata->irq,
+				       IRQF_TRIGGER_HIGH, 0,
+				       &wcd934x_regmap_irq_chip,
+				       &ddata->irq_data);
+	if (ret) {
+		dev_err(dev, "Failed to add IRQ chip: err = %d\n", ret);
+		return ret;
+	}
+
+	ret = mfd_add_devices(dev, PLATFORM_DEVID_AUTO, wcd934x_devices,
+			      ARRAY_SIZE(wcd934x_devices), NULL, 0, NULL);
+	if (ret) {
+		dev_err(dev, "Failed to add child devices: err = %d\n",
+			ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int wcd934x_slim_status(struct slim_device *sdev,
+			       enum slim_device_status status)
+{
+	switch (status) {
+	case SLIM_DEVICE_STATUS_UP:
+		return wcd934x_slim_status_up(sdev);
+	case SLIM_DEVICE_STATUS_DOWN:
+		mfd_remove_devices(&sdev->dev);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int wcd934x_slim_probe(struct slim_device *sdev)
+{
+	struct device *dev = &sdev->dev;
+	struct device_node *np = dev->of_node;
+	struct wcd934x_ddata *ddata;
+	int reset_gpio, ret;
+
+	ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return	-ENOMEM;
+
+	ddata->irq = of_irq_get(np, 0);
+	if (ddata->irq < 0) {
+		if (ddata->irq != -EPROBE_DEFER)
+			dev_err(ddata->dev, "Failed to get IRQ: err = %d\n",
+				ddata->irq);
+		return ddata->irq;
+	}
+
+	reset_gpio = of_get_named_gpio(np, "reset-gpios", 0);
+	if (reset_gpio < 0) {
+		dev_err(dev, "Failed to get reset gpio: err = %d\n",
+			reset_gpio);
+		return reset_gpio;
+	}
+
+	ddata->extclk = devm_clk_get(dev, "extclk");
+	if (IS_ERR(ddata->extclk)) {
+		dev_err(dev, "Failed to get extclk");
+		return PTR_ERR(ddata->extclk);
+	}
+
+	ddata->supplies[0].supply = "vdd-buck";
+	ddata->supplies[1].supply = "vdd-buck-sido";
+	ddata->supplies[2].supply = "vdd-tx";
+	ddata->supplies[3].supply = "vdd-rx";
+	ddata->supplies[4].supply = "vdd-io";
+
+	ret = regulator_bulk_get(dev, WCD934X_MAX_SUPPLY, ddata->supplies);
+	if (ret) {
+		dev_err(dev, "Failed to get supplies: err = %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(WCD934X_MAX_SUPPLY, ddata->supplies);
+	if (ret) {
+		dev_err(dev, "Failed to enable supplies: err = %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * For WCD934X, it takes about 600us for the Vout_A and
+	 * Vout_D to be ready after BUCK_SIDO is powered up.
+	 * SYS_RST_N shouldn't be pulled high during this time
+	 */
+	usleep_range(600, 650);
+	gpio_direction_output(reset_gpio, 0);
+	msleep(20);
+	gpio_set_value(reset_gpio, 1);
+	msleep(20);
+
+	ddata->dev = dev;
+	dev_set_drvdata(dev, ddata);
+
+	return 0;
+}
+
+static void wcd934x_slim_remove(struct slim_device *sdev)
+{
+	struct wcd934x_ddata *ddata = dev_get_drvdata(&sdev->dev);
+
+	regulator_bulk_disable(WCD934X_MAX_SUPPLY, ddata->supplies);
+	mfd_remove_devices(&sdev->dev);
+	kfree(ddata);
+}
+
+static const struct slim_device_id wcd934x_slim_id[] = {
+	{ SLIM_MANF_ID_QCOM, SLIM_PROD_CODE_WCD9340,
+	  SLIM_DEV_IDX_WCD9340, SLIM_DEV_INSTANCE_ID_WCD9340 },
+	{}
+};
+
+static struct slim_driver wcd934x_slim_driver = {
+	.driver = {
+		.name = "wcd934x-slim",
+	},
+	.probe = wcd934x_slim_probe,
+	.remove = wcd934x_slim_remove,
+	.device_status = wcd934x_slim_status,
+	.id_table = wcd934x_slim_id,
+};
+
+module_slim_driver(wcd934x_slim_driver);
+MODULE_DESCRIPTION("WCD934X slim driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("slim:217:250:*");
+MODULE_AUTHOR("Srinivas Kandagatla <srinivas.kandagatla@linaro.org>");
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index ae4ee27a63c4..e3e085e33d46 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -581,13 +581,6 @@ static void fastrpc_dma_buf_detatch(struct dma_buf *dmabuf,
 	kfree(a);
 }
 
-static void *fastrpc_kmap(struct dma_buf *dmabuf, unsigned long pgnum)
-{
-	struct fastrpc_buf *buf = dmabuf->priv;
-
-	return buf->virt ? buf->virt + pgnum * PAGE_SIZE : NULL;
-}
-
 static void *fastrpc_vmap(struct dma_buf *dmabuf)
 {
 	struct fastrpc_buf *buf = dmabuf->priv;
@@ -611,7 +604,6 @@ static const struct dma_buf_ops fastrpc_dma_buf_ops = {
 	.map_dma_buf = fastrpc_map_dma_buf,
 	.unmap_dma_buf = fastrpc_unmap_dma_buf,
 	.mmap = fastrpc_mmap,
-	.map = fastrpc_kmap,
 	.vmap = fastrpc_vmap,
 	.release = fastrpc_release,
 };
diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig
index 1916fa65f2f2..2d2266c1439e 100644
--- a/drivers/misc/ocxl/Kconfig
+++ b/drivers/misc/ocxl/Kconfig
@@ -11,6 +11,7 @@ config OCXL
 	tristate "OpenCAPI coherent accelerator support"
 	depends on PPC_POWERNV && PCI && EEH
 	select OCXL_BASE
+	select HOTPLUG_PCI_POWERNV
 	default m
 	help
 	  Select this option to enable the ocxl driver for Open
diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c
index 2817f4751306..97b8b38ab47d 100644
--- a/drivers/misc/sgi-gru/gruprocfs.c
+++ b/drivers/misc/sgi-gru/gruprocfs.c
@@ -255,28 +255,28 @@ static int options_open(struct inode *inode, struct file *file)
 }
 
 /* *INDENT-OFF* */
-static const struct file_operations statistics_fops = {
-	.open 		= statistics_open,
-	.read 		= seq_read,
-	.write 		= statistics_write,
-	.llseek 	= seq_lseek,
-	.release 	= single_release,
+static const struct proc_ops statistics_proc_ops = {
+	.proc_open	= statistics_open,
+	.proc_read	= seq_read,
+	.proc_write	= statistics_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
-static const struct file_operations mcs_statistics_fops = {
-	.open 		= mcs_statistics_open,
-	.read 		= seq_read,
-	.write 		= mcs_statistics_write,
-	.llseek 	= seq_lseek,
-	.release 	= single_release,
+static const struct proc_ops mcs_statistics_proc_ops = {
+	.proc_open	= mcs_statistics_open,
+	.proc_read	= seq_read,
+	.proc_write	= mcs_statistics_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
-static const struct file_operations options_fops = {
-	.open 		= options_open,
-	.read 		= seq_read,
-	.write 		= options_write,
-	.llseek 	= seq_lseek,
-	.release 	= single_release,
+static const struct proc_ops options_proc_ops = {
+	.proc_open	= options_open,
+	.proc_read	= seq_read,
+	.proc_write	= options_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 static struct proc_dir_entry *proc_gru __read_mostly;
@@ -286,11 +286,11 @@ int gru_proc_init(void)
 	proc_gru = proc_mkdir("sgi_uv/gru", NULL);
 	if (!proc_gru)
 		return -1;
-	if (!proc_create("statistics", 0644, proc_gru, &statistics_fops))
+	if (!proc_create("statistics", 0644, proc_gru, &statistics_proc_ops))
 		goto err;
-	if (!proc_create("mcs_statistics", 0644, proc_gru, &mcs_statistics_fops))
+	if (!proc_create("mcs_statistics", 0644, proc_gru, &mcs_statistics_proc_ops))
 		goto err;
-	if (!proc_create("debug_options", 0644, proc_gru, &options_fops))
+	if (!proc_create("debug_options", 0644, proc_gru, &options_proc_ops))
 		goto err;
 	if (!proc_create_seq("cch_status", 0444, proc_gru, &cch_seq_ops))
 		goto err;
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 410a321682e6..36aa082f6db0 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -44,7 +44,7 @@ struct block2mtd_dev {
 static LIST_HEAD(blkmtd_device_list);
 
 
-static struct page *page_read(struct address_space *mapping, int index)
+static struct page *page_read(struct address_space *mapping, pgoff_t index)
 {
 	return read_mapping_page(mapping, index, NULL);
 }
@@ -54,7 +54,7 @@ static int _block2mtd_erase(struct block2mtd_dev *dev, loff_t to, size_t len)
 {
 	struct address_space *mapping = dev->blkdev->bd_inode->i_mapping;
 	struct page *page;
-	int index = to >> PAGE_SHIFT;	// page index
+	pgoff_t index = to >> PAGE_SHIFT;	// page index
 	int pages = len >> PAGE_SHIFT;
 	u_long *p;
 	u_long *max;
@@ -103,7 +103,7 @@ static int block2mtd_read(struct mtd_info *mtd, loff_t from, size_t len,
 {
 	struct block2mtd_dev *dev = mtd->priv;
 	struct page *page;
-	int index = from >> PAGE_SHIFT;
+	pgoff_t index = from >> PAGE_SHIFT;
 	int offset = from & (PAGE_SIZE-1);
 	int cpylen;
 
@@ -137,7 +137,7 @@ static int _block2mtd_write(struct block2mtd_dev *dev, const u_char *buf,
 {
 	struct page *page;
 	struct address_space *mapping = dev->blkdev->bd_inode->i_mapping;
-	int index = to >> PAGE_SHIFT;	// page index
+	pgoff_t index = to >> PAGE_SHIFT;	// page index
 	int offset = to & ~PAGE_MASK;	// page offset
 	int cpylen;
 
diff --git a/drivers/mtd/maps/pcmciamtd.c b/drivers/mtd/maps/pcmciamtd.c
index 70bb403f69f7..2ac79e1cedd9 100644
--- a/drivers/mtd/maps/pcmciamtd.c
+++ b/drivers/mtd/maps/pcmciamtd.c
@@ -294,16 +294,15 @@ static void pcmcia_copy_to(struct map_info *map, unsigned long to, const void *f
 }
 
 
-static DEFINE_SPINLOCK(pcmcia_vpp_lock);
+static DEFINE_MUTEX(pcmcia_vpp_lock);
 static int pcmcia_vpp_refcnt;
 static void pcmciamtd_set_vpp(struct map_info *map, int on)
 {
 	struct pcmciamtd_dev *dev = (struct pcmciamtd_dev *)map->map_priv_1;
 	struct pcmcia_device *link = dev->p_dev;
-	unsigned long flags;
 
 	pr_debug("dev = %p on = %d vpp = %d\n\n", dev, on, dev->vpp);
-	spin_lock_irqsave(&pcmcia_vpp_lock, flags);
+	mutex_lock(&pcmcia_vpp_lock);
 	if (on) {
 		if (++pcmcia_vpp_refcnt == 1)   /* first nested 'on' */
 			pcmcia_fixup_vpp(link, dev->vpp);
@@ -311,7 +310,7 @@ static void pcmciamtd_set_vpp(struct map_info *map, int on)
 		if (--pcmcia_vpp_refcnt == 0)   /* last nested 'off' */
 			pcmcia_fixup_vpp(link, 0);
 	}
-	spin_unlock_irqrestore(&pcmcia_vpp_lock, flags);
+	mutex_unlock(&pcmcia_vpp_lock);
 }
 
 
diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c
index a9f7964e2edb..8f7f966fa9a7 100644
--- a/drivers/mtd/maps/physmap-core.c
+++ b/drivers/mtd/maps/physmap-core.c
@@ -38,6 +38,7 @@
 #include <linux/mtd/cfi_endian.h>
 #include <linux/io.h>
 #include <linux/of_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/gpio/consumer.h>
 
 #include "physmap-gemini.h"
@@ -64,16 +65,16 @@ static int physmap_flash_remove(struct platform_device *dev)
 {
 	struct physmap_flash_info *info;
 	struct physmap_flash_data *physmap_data;
-	int i, err;
+	int i, err = 0;
 
 	info = platform_get_drvdata(dev);
 	if (!info)
-		return 0;
+		goto out;
 
 	if (info->cmtd) {
 		err = mtd_device_unregister(info->cmtd);
 		if (err)
-			return err;
+			goto out;
 
 		if (info->cmtd != info->mtds[0])
 			mtd_concat_destroy(info->cmtd);
@@ -88,7 +89,10 @@ static int physmap_flash_remove(struct platform_device *dev)
 	if (physmap_data && physmap_data->exit)
 		physmap_data->exit(dev);
 
-	return 0;
+out:
+	pm_runtime_put(&dev->dev);
+	pm_runtime_disable(&dev->dev);
+	return err;
 }
 
 static void physmap_set_vpp(struct map_info *map, int state)
@@ -484,13 +488,19 @@ static int physmap_flash_probe(struct platform_device *dev)
 		return -EINVAL;
 	}
 
+	pm_runtime_enable(&dev->dev);
+	pm_runtime_get_sync(&dev->dev);
+
 	if (dev->dev.of_node)
 		err = physmap_flash_of_init(dev);
 	else
 		err = physmap_flash_pdata_init(dev);
 
-	if (err)
+	if (err) {
+		pm_runtime_put(&dev->dev);
+		pm_runtime_disable(&dev->dev);
 		return err;
+	}
 
 	for (i = 0; i < info->nmaps; i++) {
 		struct resource *res;
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index 170a7221b35f..1d6c9e7e7b7d 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -841,10 +841,7 @@ struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to c
 	return &concat->mtd;
 }
 
-/*
- * This function destroys an MTD object obtained from concat_mtd_devs()
- */
-
+/* Cleans the context obtained from mtd_concat_create() */
 void mtd_concat_destroy(struct mtd_info *mtd)
 {
 	struct mtd_concat *concat = CONCAT(mtd);
diff --git a/drivers/mtd/nand/onenand/Kconfig b/drivers/mtd/nand/onenand/Kconfig
index ae0b8fe5b990..572b8fe69abb 100644
--- a/drivers/mtd/nand/onenand/Kconfig
+++ b/drivers/mtd/nand/onenand/Kconfig
@@ -25,7 +25,7 @@ config MTD_ONENAND_GENERIC
 
 config MTD_ONENAND_OMAP2
 	tristate "OneNAND on OMAP2/OMAP3 support"
-	depends on ARCH_OMAP2 || ARCH_OMAP3
+	depends on ARCH_OMAP2 || ARCH_OMAP3 || (COMPILE_TEST && ARM)
 	depends on OF || COMPILE_TEST
 	help
 	  Support for a OneNAND flash device connected to an OMAP2/OMAP3 SoC
@@ -33,12 +33,12 @@ config MTD_ONENAND_OMAP2
 	  Enable dmaengine and gpiolib for better performance.
 
 config MTD_ONENAND_SAMSUNG
-        tristate "OneNAND on Samsung SOC controller support"
-        depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS4
-        help
-          Support for a OneNAND flash device connected to an Samsung SOC.
-          S3C64XX uses command mapping method.
-          S5PC110/S5PC210 use generic OneNAND method.
+	tristate "OneNAND on Samsung SOC controller support"
+	depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS4 || COMPILE_TEST
+	help
+	  Support for a OneNAND flash device connected to an Samsung SOC.
+	  S3C64XX uses command mapping method.
+	  S5PC110/S5PC210 use generic OneNAND method.
 
 config MTD_ONENAND_OTP
 	bool "OneNAND OTP Support"
diff --git a/drivers/mtd/nand/onenand/Makefile b/drivers/mtd/nand/onenand/Makefile
index a27b635eb23a..a0761c7e0288 100644
--- a/drivers/mtd/nand/onenand/Makefile
+++ b/drivers/mtd/nand/onenand/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_MTD_ONENAND)		+= onenand.o
 
 # Board specific.
 obj-$(CONFIG_MTD_ONENAND_GENERIC)	+= generic.o
-obj-$(CONFIG_MTD_ONENAND_OMAP2)		+= omap2.o
-obj-$(CONFIG_MTD_ONENAND_SAMSUNG)       += samsung_mtd.o
+obj-$(CONFIG_MTD_ONENAND_OMAP2)		+= onenand_omap2.o
+obj-$(CONFIG_MTD_ONENAND_SAMSUNG)       += onenand_samsung.o
 
 onenand-objs = onenand_base.o onenand_bbt.o
diff --git a/drivers/mtd/nand/onenand/onenand_base.c b/drivers/mtd/nand/onenand/onenand_base.c
index 85640ee11c86..d5326d19b136 100644
--- a/drivers/mtd/nand/onenand/onenand_base.c
+++ b/drivers/mtd/nand/onenand/onenand_base.c
@@ -1248,44 +1248,44 @@ static int onenand_read_ops_nolock(struct mtd_info *mtd, loff_t from,
 
 	stats = mtd->ecc_stats;
 
- 	/* Read-while-load method */
+	/* Read-while-load method */
 
- 	/* Do first load to bufferRAM */
- 	if (read < len) {
- 		if (!onenand_check_bufferram(mtd, from)) {
+	/* Do first load to bufferRAM */
+	if (read < len) {
+		if (!onenand_check_bufferram(mtd, from)) {
 			this->command(mtd, ONENAND_CMD_READ, from, writesize);
- 			ret = this->wait(mtd, FL_READING);
- 			onenand_update_bufferram(mtd, from, !ret);
+			ret = this->wait(mtd, FL_READING);
+			onenand_update_bufferram(mtd, from, !ret);
 			if (mtd_is_eccerr(ret))
 				ret = 0;
- 		}
- 	}
+		}
+	}
 
 	thislen = min_t(int, writesize, len - read);
 	column = from & (writesize - 1);
 	if (column + thislen > writesize)
 		thislen = writesize - column;
 
- 	while (!ret) {
- 		/* If there is more to load then start next load */
- 		from += thislen;
- 		if (read + thislen < len) {
+	while (!ret) {
+		/* If there is more to load then start next load */
+		from += thislen;
+		if (read + thislen < len) {
 			this->command(mtd, ONENAND_CMD_READ, from, writesize);
- 			/*
- 			 * Chip boundary handling in DDP
- 			 * Now we issued chip 1 read and pointed chip 1
+			/*
+			 * Chip boundary handling in DDP
+			 * Now we issued chip 1 read and pointed chip 1
 			 * bufferram so we have to point chip 0 bufferram.
- 			 */
- 			if (ONENAND_IS_DDP(this) &&
- 			    unlikely(from == (this->chipsize >> 1))) {
- 				this->write_word(ONENAND_DDP_CHIP0, this->base + ONENAND_REG_START_ADDRESS2);
- 				boundary = 1;
- 			} else
- 				boundary = 0;
- 			ONENAND_SET_PREV_BUFFERRAM(this);
- 		}
- 		/* While load is going, read from last bufferRAM */
- 		this->read_bufferram(mtd, ONENAND_DATARAM, buf, column, thislen);
+			 */
+			if (ONENAND_IS_DDP(this) &&
+			    unlikely(from == (this->chipsize >> 1))) {
+				this->write_word(ONENAND_DDP_CHIP0, this->base + ONENAND_REG_START_ADDRESS2);
+				boundary = 1;
+			} else
+				boundary = 0;
+			ONENAND_SET_PREV_BUFFERRAM(this);
+		}
+		/* While load is going, read from last bufferRAM */
+		this->read_bufferram(mtd, ONENAND_DATARAM, buf, column, thislen);
 
 		/* Read oob area if needed */
 		if (oobbuf) {
@@ -1301,24 +1301,24 @@ static int onenand_read_ops_nolock(struct mtd_info *mtd, loff_t from,
 			oobcolumn = 0;
 		}
 
- 		/* See if we are done */
- 		read += thislen;
- 		if (read == len)
- 			break;
- 		/* Set up for next read from bufferRAM */
- 		if (unlikely(boundary))
- 			this->write_word(ONENAND_DDP_CHIP1, this->base + ONENAND_REG_START_ADDRESS2);
- 		ONENAND_SET_NEXT_BUFFERRAM(this);
- 		buf += thislen;
+		/* See if we are done */
+		read += thislen;
+		if (read == len)
+			break;
+		/* Set up for next read from bufferRAM */
+		if (unlikely(boundary))
+			this->write_word(ONENAND_DDP_CHIP1, this->base + ONENAND_REG_START_ADDRESS2);
+		ONENAND_SET_NEXT_BUFFERRAM(this);
+		buf += thislen;
 		thislen = min_t(int, writesize, len - read);
- 		column = 0;
- 		cond_resched();
- 		/* Now wait for load */
- 		ret = this->wait(mtd, FL_READING);
- 		onenand_update_bufferram(mtd, from, !ret);
+		column = 0;
+		cond_resched();
+		/* Now wait for load */
+		ret = this->wait(mtd, FL_READING);
+		onenand_update_bufferram(mtd, from, !ret);
 		if (mtd_is_eccerr(ret))
 			ret = 0;
- 	}
+	}
 
 	/*
 	 * Return success, if no ECC failures, else -EBADMSG
diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/onenand_omap2.c
index aa9368bf7a0c..aa9368bf7a0c 100644
--- a/drivers/mtd/nand/onenand/omap2.c
+++ b/drivers/mtd/nand/onenand/onenand_omap2.c
diff --git a/drivers/mtd/nand/onenand/samsung_mtd.c b/drivers/mtd/nand/onenand/onenand_samsung.c
index beb7987e4c2b..87b28e397d67 100644
--- a/drivers/mtd/nand/onenand/samsung_mtd.c
+++ b/drivers/mtd/nand/onenand/onenand_samsung.c
@@ -248,7 +248,7 @@ static unsigned short s3c_onenand_readw(void __iomem *addr)
 	}
 
 	/* BootRAM access control */
-	if ((unsigned int) addr < ONENAND_DATARAM && onenand->bootram_command) {
+	if ((unsigned long)addr < ONENAND_DATARAM && onenand->bootram_command) {
 		if (word_addr == 0)
 			return s3c_read_reg(MANUFACT_ID_OFFSET);
 		if (word_addr == 1)
@@ -289,7 +289,7 @@ static void s3c_onenand_writew(unsigned short value, void __iomem *addr)
 	}
 
 	/* BootRAM access control */
-	if ((unsigned int)addr < ONENAND_DATARAM) {
+	if ((unsigned long)addr < ONENAND_DATARAM) {
 		if (value == ONENAND_CMD_READID) {
 			onenand->bootram_command = 1;
 			return;
@@ -658,7 +658,7 @@ static int s5pc110_read_bufferram(struct mtd_info *mtd, int area,
 		dma_dst = dma_map_single(dev, buf, count, DMA_FROM_DEVICE);
 	}
 	if (dma_mapping_error(dev, dma_dst)) {
-		dev_err(dev, "Couldn't map a %d byte buffer for DMA\n", count);
+		dev_err(dev, "Couldn't map a %zu byte buffer for DMA\n", count);
 		goto normal;
 	}
 	err = s5pc110_dma_ops(dma_dst, dma_src,
@@ -728,13 +728,12 @@ static void s3c_onenand_check_lock_status(struct mtd_info *mtd)
 	struct onenand_chip *this = mtd->priv;
 	struct device *dev = &onenand->pdev->dev;
 	unsigned int block, end;
-	int tmp;
 
 	end = this->chipsize >> this->erase_shift;
 
 	for (block = 0; block < end; block++) {
 		unsigned int mem_addr = onenand->mem_addr(block, 0, 0);
-		tmp = s3c_read_cmd(CMD_MAP_01(onenand, mem_addr));
+		s3c_read_cmd(CMD_MAP_01(onenand, mem_addr));
 
 		if (s3c_read_reg(INT_ERR_STAT_OFFSET) & LOCKED_BLK) {
 			dev_err(dev, "block %d is write-protected!\n", block);
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 74fb91adeb46..a80a46bb5b8b 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -452,7 +452,7 @@ config MTD_NAND_PLATFORM
 
 config MTD_NAND_CADENCE
 	tristate "Support Cadence NAND (HPNFC) controller"
-	depends on OF || COMPILE_TEST
+	depends on (OF || COMPILE_TEST) && HAS_IOMEM
 	help
 	  Enable the driver for NAND flash on platforms using a Cadence NAND
 	  controller.
diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 8d6be90a6fe8..3ba17a98df4d 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1578,9 +1578,8 @@ static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 
 	nand->numcs = numcs;
 
-	gpio = devm_fwnode_get_index_gpiod_from_child(nc->dev, "det", 0,
-						      &np->fwnode, GPIOD_IN,
-						      "nand-det");
+	gpio = devm_fwnode_gpiod_get(nc->dev, of_fwnode_handle(np),
+				     "det", GPIOD_IN, "nand-det");
 	if (IS_ERR(gpio) && PTR_ERR(gpio) != -ENOENT) {
 		dev_err(nc->dev,
 			"Failed to get detect gpio (err = %ld)\n",
@@ -1624,9 +1623,10 @@ static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 			nand->cs[i].rb.type = ATMEL_NAND_NATIVE_RB;
 			nand->cs[i].rb.id = val;
 		} else {
-			gpio = devm_fwnode_get_index_gpiod_from_child(nc->dev,
-							"rb", i, &np->fwnode,
-							GPIOD_IN, "nand-rb");
+			gpio = devm_fwnode_gpiod_get_index(nc->dev,
+							   of_fwnode_handle(np),
+							   "rb", i, GPIOD_IN,
+							   "nand-rb");
 			if (IS_ERR(gpio) && PTR_ERR(gpio) != -ENOENT) {
 				dev_err(nc->dev,
 					"Failed to get R/B gpio (err = %ld)\n",
@@ -1640,10 +1640,10 @@ static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 			}
 		}
 
-		gpio = devm_fwnode_get_index_gpiod_from_child(nc->dev, "cs",
-							      i, &np->fwnode,
-							      GPIOD_OUT_HIGH,
-							      "nand-cs");
+		gpio = devm_fwnode_gpiod_get_index(nc->dev,
+						   of_fwnode_handle(np),
+						   "cs", i, GPIOD_OUT_HIGH,
+						   "nand-cs");
 		if (IS_ERR(gpio) && PTR_ERR(gpio) != -ENOENT) {
 			dev_err(nc->dev,
 				"Failed to get CS gpio (err = %ld)\n",
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 1a66b1cd51c0..44518dada75b 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2635,6 +2635,16 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
 		/* initialize the dma version */
 		brcmnand_flash_dma_revision_init(ctrl);
 
+		ret = -EIO;
+		if (ctrl->nand_version >= 0x0700)
+			ret = dma_set_mask_and_coherent(&pdev->dev,
+							DMA_BIT_MASK(40));
+		if (ret)
+			ret = dma_set_mask_and_coherent(&pdev->dev,
+							DMA_BIT_MASK(32));
+		if (ret)
+			goto err;
+
 		/* linked-list and stop on error */
 		flash_dma_writel(ctrl, FLASH_DMA_MODE, FLASH_DMA_MODE_MASK);
 		flash_dma_writel(ctrl, FLASH_DMA_ERROR_STATUS, 0);
diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 3102ddbd8abd..fafd0a0aa8e2 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -21,7 +21,6 @@
 #include "denali.h"
 
 #define DENALI_NAND_NAME    "denali-nand"
-#define DENALI_DEFAULT_OOB_SKIP_BYTES	8
 
 /* for Indexed Addressing */
 #define DENALI_INDEXED_CTRL	0x00
@@ -1302,15 +1301,16 @@ int denali_init(struct denali_controller *denali)
 
 	/*
 	 * Set how many bytes should be skipped before writing data in OOB.
-	 * If a non-zero value has already been set (by firmware or something),
-	 * just use it. Otherwise, set the driver's default.
+	 * If a platform requests a non-zero value, set it to the register.
+	 * Otherwise, read the value out, expecting it has already been set up
+	 * by firmware.
 	 */
-	denali->oob_skip_bytes = ioread32(denali->reg + SPARE_AREA_SKIP_BYTES);
-	if (!denali->oob_skip_bytes) {
-		denali->oob_skip_bytes = DENALI_DEFAULT_OOB_SKIP_BYTES;
+	if (denali->oob_skip_bytes)
 		iowrite32(denali->oob_skip_bytes,
 			  denali->reg + SPARE_AREA_SKIP_BYTES);
-	}
+	else
+		denali->oob_skip_bytes = ioread32(denali->reg +
+						  SPARE_AREA_SKIP_BYTES);
 
 	iowrite32(0, denali->reg + TRANSFER_SPARE_REG);
 	iowrite32(GENMASK(denali->nbanks - 1, 0), denali->reg + RB_PIN_ENABLED);
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 8b779a899dcf..f08740ae282b 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
@@ -14,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/reset.h>
 
 #include "denali.h"
 
@@ -22,11 +24,14 @@ struct denali_dt {
 	struct clk *clk;	/* core clock */
 	struct clk *clk_x;	/* bus interface clock */
 	struct clk *clk_ecc;	/* ECC circuit clock */
+	struct reset_control *rst;	/* core reset */
+	struct reset_control *rst_reg;	/* register reset */
 };
 
 struct denali_dt_data {
 	unsigned int revision;
 	unsigned int caps;
+	unsigned int oob_skip_bytes;
 	const struct nand_ecc_caps *ecc_caps;
 };
 
@@ -34,6 +39,7 @@ NAND_ECC_CAPS_SINGLE(denali_socfpga_ecc_caps, denali_calc_ecc_bytes,
 		     512, 8, 15);
 static const struct denali_dt_data denali_socfpga_data = {
 	.caps = DENALI_CAP_HW_ECC_FIXUP,
+	.oob_skip_bytes = 2,
 	.ecc_caps = &denali_socfpga_ecc_caps,
 };
 
@@ -42,6 +48,7 @@ NAND_ECC_CAPS_SINGLE(denali_uniphier_v5a_ecc_caps, denali_calc_ecc_bytes,
 static const struct denali_dt_data denali_uniphier_v5a_data = {
 	.caps = DENALI_CAP_HW_ECC_FIXUP |
 		DENALI_CAP_DMA_64BIT,
+	.oob_skip_bytes = 8,
 	.ecc_caps = &denali_uniphier_v5a_ecc_caps,
 };
 
@@ -51,6 +58,7 @@ static const struct denali_dt_data denali_uniphier_v5b_data = {
 	.revision = 0x0501,
 	.caps = DENALI_CAP_HW_ECC_FIXUP |
 		DENALI_CAP_DMA_64BIT,
+	.oob_skip_bytes = 8,
 	.ecc_caps = &denali_uniphier_v5b_ecc_caps,
 };
 
@@ -118,11 +126,13 @@ static int denali_dt_probe(struct platform_device *pdev)
 	denali = &dt->controller;
 
 	data = of_device_get_match_data(dev);
-	if (data) {
-		denali->revision = data->revision;
-		denali->caps = data->caps;
-		denali->ecc_caps = data->ecc_caps;
-	}
+	if (WARN_ON(!data))
+		return -EINVAL;
+
+	denali->revision = data->revision;
+	denali->caps = data->caps;
+	denali->oob_skip_bytes = data->oob_skip_bytes;
+	denali->ecc_caps = data->ecc_caps;
 
 	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
@@ -151,6 +161,14 @@ static int denali_dt_probe(struct platform_device *pdev)
 	if (IS_ERR(dt->clk_ecc))
 		return PTR_ERR(dt->clk_ecc);
 
+	dt->rst = devm_reset_control_get_optional_shared(dev, "nand");
+	if (IS_ERR(dt->rst))
+		return PTR_ERR(dt->rst);
+
+	dt->rst_reg = devm_reset_control_get_optional_shared(dev, "reg");
+	if (IS_ERR(dt->rst_reg))
+		return PTR_ERR(dt->rst_reg);
+
 	ret = clk_prepare_enable(dt->clk);
 	if (ret)
 		return ret;
@@ -166,10 +184,30 @@ static int denali_dt_probe(struct platform_device *pdev)
 	denali->clk_rate = clk_get_rate(dt->clk);
 	denali->clk_x_rate = clk_get_rate(dt->clk_x);
 
-	ret = denali_init(denali);
+	/*
+	 * Deassert the register reset, and the core reset in this order.
+	 * Deasserting the core reset while the register reset is asserted
+	 * will cause unpredictable behavior in the controller.
+	 */
+	ret = reset_control_deassert(dt->rst_reg);
 	if (ret)
 		goto out_disable_clk_ecc;
 
+	ret = reset_control_deassert(dt->rst);
+	if (ret)
+		goto out_assert_rst_reg;
+
+	/*
+	 * When the reset is deasserted, the initialization sequence is kicked
+	 * (bootstrap process). The driver must wait until it finished.
+	 * Otherwise, it will result in unpredictable behavior.
+	 */
+	usleep_range(200, 1000);
+
+	ret = denali_init(denali);
+	if (ret)
+		goto out_assert_rst;
+
 	for_each_child_of_node(dev->of_node, np) {
 		ret = denali_dt_chip_init(denali, np);
 		if (ret) {
@@ -184,6 +222,10 @@ static int denali_dt_probe(struct platform_device *pdev)
 
 out_remove_denali:
 	denali_remove(denali);
+out_assert_rst:
+	reset_control_assert(dt->rst);
+out_assert_rst_reg:
+	reset_control_assert(dt->rst_reg);
 out_disable_clk_ecc:
 	clk_disable_unprepare(dt->clk_ecc);
 out_disable_clk_x:
@@ -199,6 +241,8 @@ static int denali_dt_remove(struct platform_device *pdev)
 	struct denali_dt *dt = platform_get_drvdata(pdev);
 
 	denali_remove(&dt->controller);
+	reset_control_assert(dt->rst);
+	reset_control_assert(dt->rst_reg);
 	clk_disable_unprepare(dt->clk_ecc);
 	clk_disable_unprepare(dt->clk_x);
 	clk_disable_unprepare(dt->clk);
diff --git a/drivers/mtd/nand/raw/mpc5121_nfc.c b/drivers/mtd/nand/raw/mpc5121_nfc.c
index 8b90def6686f..a2fcb739e5f8 100644
--- a/drivers/mtd/nand/raw/mpc5121_nfc.c
+++ b/drivers/mtd/nand/raw/mpc5121_nfc.c
@@ -438,7 +438,7 @@ static void mpc5121_nfc_copy_spare(struct mtd_info *mtd, uint offset,
 		buffer += blksize;
 		offset += blksize;
 		size -= blksize;
-	};
+	}
 }
 
 /* Copy data from/to NFC main and spare buffers */
diff --git a/drivers/mtd/nand/raw/nand_macronix.c b/drivers/mtd/nand/raw/nand_macronix.c
index 58511aeb0c9a..3ff7ce00cbdb 100644
--- a/drivers/mtd/nand/raw/nand_macronix.c
+++ b/drivers/mtd/nand/raw/nand_macronix.c
@@ -59,7 +59,7 @@ static void macronix_nand_onfi_init(struct nand_chip *chip)
  */
 static void macronix_nand_fix_broken_get_timings(struct nand_chip *chip)
 {
-	unsigned int i;
+	int i;
 	static const char * const broken_get_timings[] = {
 		"MX30LF1G18AC",
 		"MX30LF1G28AC",
@@ -80,12 +80,9 @@ static void macronix_nand_fix_broken_get_timings(struct nand_chip *chip)
 	if (!chip->parameters.supports_set_get_features)
 		return;
 
-	for (i = 0; i < ARRAY_SIZE(broken_get_timings); i++) {
-		if (!strcmp(broken_get_timings[i], chip->parameters.model))
-			break;
-	}
-
-	if (i == ARRAY_SIZE(broken_get_timings))
+	i = match_string(broken_get_timings, ARRAY_SIZE(broken_get_timings),
+			 chip->parameters.model);
+	if (i < 0)
 		return;
 
 	bitmap_clear(chip->parameters.get_feature_list,
diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c
index 1cb3760ff779..0db5ee4e82af 100644
--- a/drivers/mtd/nand/spi/toshiba.c
+++ b/drivers/mtd/nand/spi/toshiba.c
@@ -124,6 +124,16 @@ static const struct spinand_info toshiba_spinand_table[] = {
 		     0,
 		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
 				     tc58cxgxsx_ecc_get_status)),
+	/* 3.3V 4Gb */
+	SPINAND_INFO("TC58CVG2S0", 0xED,
+		     NAND_MEMORG(1, 4096, 256, 64, 2048, 40, 1, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&tc58cxgxsx_ooblayout,
+				     tc58cxgxsx_ecc_get_status)),
 	/* 1.8V 1Gb */
 	SPINAND_INFO("TC58CYG0S3", 0xB2,
 		     NAND_MEMORG(1, 2048, 128, 64, 1024, 20, 1, 1, 1),
diff --git a/drivers/mtd/parsers/sharpslpart.c b/drivers/mtd/parsers/sharpslpart.c
index e5ea6127ab5a..671a61845bd5 100644
--- a/drivers/mtd/parsers/sharpslpart.c
+++ b/drivers/mtd/parsers/sharpslpart.c
@@ -165,10 +165,10 @@ static int sharpsl_nand_get_logical_num(u8 *oob)
 
 static int sharpsl_nand_init_ftl(struct mtd_info *mtd, struct sharpsl_ftl *ftl)
 {
-	unsigned int block_num, log_num, phymax;
+	unsigned int block_num, phymax;
+	int i, ret, log_num;
 	loff_t block_adr;
 	u8 *oob;
-	int i, ret;
 
 	oob = kzalloc(mtd->oobsize, GFP_KERNEL);
 	if (!oob)
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index f237fcdf7f86..c1eda67d1ad2 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -46,11 +46,11 @@ config SPI_CADENCE_QUADSPI
 	  Flash as an MTD device.
 
 config SPI_HISI_SFC
-	tristate "Hisilicon SPI-NOR Flash Controller(SFC)"
+	tristate "Hisilicon FMC SPI-NOR Flash Controller(SFC)"
 	depends on ARCH_HISI || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
-	  This enables support for hisilicon SPI-NOR flash controller.
+	  This enables support for HiSilicon FMC SPI-NOR flash controller.
 
 config SPI_MTK_QUADSPI
 	tristate "MediaTek Quad SPI controller"
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
index 2b7cabbb680c..395127349aa8 100644
--- a/drivers/mtd/spi-nor/aspeed-smc.c
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -305,7 +305,7 @@ static void aspeed_smc_stop_user(struct spi_nor *nor)
 	writel(ctl, chip->ctl);		/* default to fread or read mode */
 }
 
-static int aspeed_smc_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+static int aspeed_smc_prep(struct spi_nor *nor)
 {
 	struct aspeed_smc_chip *chip = nor->priv;
 
@@ -313,7 +313,7 @@ static int aspeed_smc_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 	return 0;
 }
 
-static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+static void aspeed_smc_unprep(struct spi_nor *nor)
 {
 	struct aspeed_smc_chip *chip = nor->priv;
 
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 06f997247d0f..494dcab4aaaa 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -1062,7 +1062,7 @@ static int cqspi_erase(struct spi_nor *nor, loff_t offs)
 	return 0;
 }
 
-static int cqspi_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+static int cqspi_prep(struct spi_nor *nor)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
@@ -1072,7 +1072,7 @@ static int cqspi_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 	return 0;
 }
 
-static void cqspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+static void cqspi_unprep(struct spi_nor *nor)
 {
 	struct cqspi_flash_pdata *f_pdata = nor->priv;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c
index a1258216f89d..6c7a4118752e 100644
--- a/drivers/mtd/spi-nor/hisi-sfc.c
+++ b/drivers/mtd/spi-nor/hisi-sfc.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * HiSilicon SPI Nor Flash Controller Driver
+ * HiSilicon FMC SPI-NOR flash controller driver
  *
  * Copyright (c) 2015-2016 HiSilicon Technologies Co., Ltd.
  */
@@ -144,7 +144,7 @@ static void hisi_spi_nor_init(struct hifmc_host *host)
 	writel(reg, host->regbase + FMC_SPI_TIMING_CFG);
 }
 
-static int hisi_spi_nor_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+static int hisi_spi_nor_prep(struct spi_nor *nor)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
@@ -167,7 +167,7 @@ out:
 	return ret;
 }
 
-static void hisi_spi_nor_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+static void hisi_spi_nor_unprep(struct spi_nor *nor)
 {
 	struct hifmc_priv *priv = nor->priv;
 	struct hifmc_host *host = priv->host;
diff --git a/drivers/mtd/spi-nor/intel-spi-pci.c b/drivers/mtd/spi-nor/intel-spi-pci.c
index 3d8987baea2a..81329f680bec 100644
--- a/drivers/mtd/spi-nor/intel-spi-pci.c
+++ b/drivers/mtd/spi-nor/intel-spi-pci.c
@@ -70,10 +70,12 @@ static const struct pci_device_id intel_spi_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x19e0), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x34a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x4b24), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0x4da4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa0a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa224), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info },
+	{ PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&bxt_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index b0cd443dd758..4fc632ec18fe 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -85,7 +85,7 @@ struct sfdp_header {
 #define BFPT_DWORD(i)		((i) - 1)
 #define BFPT_DWORD_MAX		16
 
-/* The first version of JESB216 defined only 9 DWORDs. */
+/* The first version of JESD216 defined only 9 DWORDs. */
 #define BFPT_DWORD_MAX_JESD216			9
 
 /* 1st DWORD. */
@@ -196,7 +196,7 @@ struct flash_info {
 	u16		page_size;
 	u16		addr_width;
 
-	u16		flags;
+	u32		flags;
 #define SECT_4K			BIT(0)	/* SPINOR_OP_BE_4K works uniformly */
 #define SPI_NOR_NO_ERASE	BIT(1)	/* No erase command needed */
 #define SST_WRITE		BIT(2)	/* use SST byte programming */
@@ -233,6 +233,11 @@ struct flash_info {
 #define SPI_NOR_SKIP_SFDP	BIT(13)	/* Skip parsing of SFDP tables */
 #define USE_CLSR		BIT(14)	/* use CLSR command */
 #define SPI_NOR_OCTAL_READ	BIT(15)	/* Flash supports Octal Read */
+#define SPI_NOR_TB_SR_BIT6	BIT(16)	/*
+					 * Top/Bottom (TB) is bit 6 of
+					 * status register. Must be used with
+					 * SPI_NOR_HAS_TB.
+					 */
 
 	/* Part specific fixup hooks. */
 	const struct spi_nor_fixups *fixups;
@@ -1307,14 +1312,14 @@ static void spi_nor_set_4byte_opcodes(struct spi_nor *nor)
 	}
 }
 
-static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+static int spi_nor_lock_and_prep(struct spi_nor *nor)
 {
 	int ret = 0;
 
 	mutex_lock(&nor->lock);
 
 	if (nor->controller_ops &&  nor->controller_ops->prepare) {
-		ret = nor->controller_ops->prepare(nor, ops);
+		ret = nor->controller_ops->prepare(nor);
 		if (ret) {
 			mutex_unlock(&nor->lock);
 			return ret;
@@ -1323,10 +1328,10 @@ static int spi_nor_lock_and_prep(struct spi_nor *nor, enum spi_nor_ops ops)
 	return ret;
 }
 
-static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+static void spi_nor_unlock_and_unprep(struct spi_nor *nor)
 {
 	if (nor->controller_ops && nor->controller_ops->unprepare)
-		nor->controller_ops->unprepare(nor, ops);
+		nor->controller_ops->unprepare(nor);
 	mutex_unlock(&nor->lock);
 }
 
@@ -1688,7 +1693,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	addr = instr->addr;
 	len = instr->len;
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_ERASE);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
@@ -1751,7 +1756,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 	ret = spi_nor_write_disable(nor);
 
 erase_err:
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_ERASE);
+	spi_nor_unlock_and_unprep(nor);
 
 	return ret;
 }
@@ -1761,9 +1766,13 @@ static void stm_get_locked_range(struct spi_nor *nor, u8 sr, loff_t *ofs,
 {
 	struct mtd_info *mtd = &nor->mtd;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
+	u8 tb_mask = SR_TB_BIT5;
 	int shift = ffs(mask) - 1;
 	int pow;
 
+	if (nor->flags & SNOR_F_HAS_SR_TB_BIT6)
+		tb_mask = SR_TB_BIT6;
+
 	if (!(sr & mask)) {
 		/* No protection */
 		*ofs = 0;
@@ -1771,7 +1780,7 @@ static void stm_get_locked_range(struct spi_nor *nor, u8 sr, loff_t *ofs,
 	} else {
 		pow = ((sr & mask) ^ mask) >> shift;
 		*len = mtd->size >> pow;
-		if (nor->flags & SNOR_F_HAS_SR_TB && sr & SR_TB)
+		if (nor->flags & SNOR_F_HAS_SR_TB && sr & tb_mask)
 			*ofs = 0;
 		else
 			*ofs = mtd->size - *len;
@@ -1850,6 +1859,7 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	struct mtd_info *mtd = &nor->mtd;
 	int ret, status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
+	u8 tb_mask = SR_TB_BIT5;
 	u8 shift = ffs(mask) - 1, pow, val;
 	loff_t lock_len;
 	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
@@ -1886,6 +1896,9 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	else
 		lock_len = ofs + len;
 
+	if (nor->flags & SNOR_F_HAS_SR_TB_BIT6)
+		tb_mask = SR_TB_BIT6;
+
 	/*
 	 * Need smallest pow such that:
 	 *
@@ -1903,13 +1916,13 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	if (!(val & mask))
 		return -EINVAL;
 
-	status_new = (status_old & ~mask & ~SR_TB) | val;
+	status_new = (status_old & ~mask & ~tb_mask) | val;
 
 	/* Disallow further writes if WP pin is asserted */
 	status_new |= SR_SRWD;
 
 	if (!use_top)
-		status_new |= SR_TB;
+		status_new |= tb_mask;
 
 	/* Don't bother if they're the same */
 	if (status_new == status_old)
@@ -1932,6 +1945,7 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	struct mtd_info *mtd = &nor->mtd;
 	int ret, status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
+	u8 tb_mask = SR_TB_BIT5;
 	u8 shift = ffs(mask) - 1, pow, val;
 	loff_t lock_len;
 	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
@@ -1968,6 +1982,8 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	else
 		lock_len = ofs;
 
+	if (nor->flags & SNOR_F_HAS_SR_TB_BIT6)
+		tb_mask = SR_TB_BIT6;
 	/*
 	 * Need largest pow such that:
 	 *
@@ -1987,14 +2003,14 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 			return -EINVAL;
 	}
 
-	status_new = (status_old & ~mask & ~SR_TB) | val;
+	status_new = (status_old & ~mask & ~tb_mask) | val;
 
 	/* Don't protect status register if we're fully unlocked */
 	if (lock_len == 0)
 		status_new &= ~SR_SRWD;
 
 	if (!use_top)
-		status_new |= SR_TB;
+		status_new |= tb_mask;
 
 	/* Don't bother if they're the same */
 	if (status_new == status_old)
@@ -2036,13 +2052,13 @@ static int spi_nor_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
 	int ret;
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_LOCK);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
 	ret = nor->params.locking_ops->lock(nor, ofs, len);
 
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_UNLOCK);
+	spi_nor_unlock_and_unprep(nor);
 	return ret;
 }
 
@@ -2051,13 +2067,13 @@ static int spi_nor_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
 	int ret;
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_UNLOCK);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
 	ret = nor->params.locking_ops->unlock(nor, ofs, len);
 
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK);
+	spi_nor_unlock_and_unprep(nor);
 	return ret;
 }
 
@@ -2066,13 +2082,13 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	struct spi_nor *nor = mtd_to_spi_nor(mtd);
 	int ret;
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_UNLOCK);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
 	ret = nor->params.locking_ops->is_locked(nor, ofs, len);
 
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_LOCK);
+	spi_nor_unlock_and_unprep(nor);
 	return ret;
 }
 
@@ -2309,6 +2325,9 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "at25df321a", INFO(0x1f4701, 0, 64 * 1024,  64, SECT_4K) },
 	{ "at25df641",  INFO(0x1f4800, 0, 64 * 1024, 128, SECT_4K) },
 
+	{ "at25sl321",	INFO(0x1f4216, 0, 64 * 1024, 64,
+			     SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+
 	{ "at26f004",   INFO(0x1f0400, 0, 64 * 1024,  8, SECT_4K) },
 	{ "at26df081a", INFO(0x1f4501, 0, 64 * 1024, 16, SECT_4K) },
 	{ "at26df161a", INFO(0x1f4601, 0, 64 * 1024, 32, SECT_4K) },
@@ -2374,6 +2393,11 @@ static const struct flash_info spi_nor_ids[] = {
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
 	},
 	{
+		"gd25lq128d", INFO(0xc86018, 0, 64 * 1024, 256,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
 		"gd25q128", INFO(0xc84018, 0, 64 * 1024, 256,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
@@ -2381,7 +2405,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{
 		"gd25q256", INFO(0xc84019, 0, 64 * 1024, 512,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
-			SPI_NOR_4B_OPCODES | SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+			SPI_NOR_4B_OPCODES | SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB |
+			SPI_NOR_TB_SR_BIT6)
 			.fixups = &gd25q256_fixups,
 	},
 
@@ -2436,6 +2461,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "mx25u6435f",  INFO(0xc22537, 0, 64 * 1024, 128, SECT_4K) },
 	{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
 	{ "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) },
+	{ "mx25r3235f",  INFO(0xc22816, 0, 64 * 1024,  64,
+			 SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "mx25u12835f", INFO(0xc22538, 0, 64 * 1024, 256,
 			 SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512,
@@ -2456,20 +2483,35 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "n25q032a",	 INFO(0x20bb16, 0, 64 * 1024,   64, SPI_NOR_QUAD_READ) },
 	{ "n25q064",     INFO(0x20ba17, 0, 64 * 1024,  128, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q064a",    INFO(0x20bb17, 0, 64 * 1024,  128, SECT_4K | SPI_NOR_QUAD_READ) },
-	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, SECT_4K | SPI_NOR_QUAD_READ) },
-	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, SECT_4K | SPI_NOR_QUAD_READ) },
-	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
-	{ "n25q256ax1",  INFO(0x20bb19, 0, 64 * 1024,  512, SECT_4K | SPI_NOR_QUAD_READ) },
+	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, SECT_4K |
+			      USE_FSR | SPI_NOR_QUAD_READ) },
+	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, SECT_4K |
+			      USE_FSR | SPI_NOR_QUAD_READ) },
+	{ "mt25ql256a",  INFO6(0x20ba19, 0x104400, 64 * 1024,  512,
+			       SECT_4K | USE_FSR | SPI_NOR_DUAL_READ |
+			       SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
+	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K |
+			      USE_FSR | SPI_NOR_DUAL_READ |
+			      SPI_NOR_QUAD_READ) },
+	{ "mt25qu256a",  INFO6(0x20bb19, 0x104400, 64 * 1024,  512,
+			       SECT_4K | USE_FSR | SPI_NOR_DUAL_READ |
+			       SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
+	{ "n25q256ax1",  INFO(0x20bb19, 0, 64 * 1024,  512, SECT_4K |
+			      USE_FSR | SPI_NOR_QUAD_READ) },
+	{ "mt25ql512a",  INFO6(0x20ba20, 0x104400, 64 * 1024, 1024,
+			       SECT_4K | USE_FSR | SPI_NOR_DUAL_READ |
+			       SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
 	{ "n25q512ax3",  INFO(0x20ba20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
+	{ "mt25qu512a",  INFO6(0x20bb20, 0x104400, 64 * 1024, 1024,
+			       SECT_4K | USE_FSR | SPI_NOR_DUAL_READ |
+			       SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
+	{ "n25q512a",    INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K |
+			      USE_FSR | SPI_NOR_QUAD_READ) },
 	{ "n25q00",      INFO(0x20ba21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
 	{ "n25q00a",     INFO(0x20bb21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
 	{ "mt25ql02g",   INFO(0x20ba22, 0, 64 * 1024, 4096,
 			      SECT_4K | USE_FSR | SPI_NOR_QUAD_READ |
 			      NO_CHIP_ERASE) },
-	{ "mt25qu512a (n25q512a)", INFO(0x20bb20, 0, 64 * 1024, 1024,
-					SECT_4K | USE_FSR | SPI_NOR_DUAL_READ |
-					SPI_NOR_QUAD_READ |
-					SPI_NOR_4B_OPCODES) },
 	{ "mt25qu02g",   INFO(0x20bb22, 0, 64 * 1024, 4096, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
 
 	/* Micron */
@@ -2540,6 +2582,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "sst25wf080",  INFO(0xbf2505, 0, 64 * 1024, 16, SECT_4K | SST_WRITE) },
 	{ "sst26wf016b", INFO(0xbf2651, 0, 64 * 1024, 32, SECT_4K |
 			      SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "sst26vf016b", INFO(0xbf2641, 0, 64 * 1024, 32, SECT_4K |
+			      SPI_NOR_DUAL_READ) },
 	{ "sst26vf064b", INFO(0xbf2643, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 
 	/* ST Microelectronics -- newer production may have feature updates */
@@ -2610,6 +2654,11 @@ static const struct flash_info spi_nor_ids[] = {
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
 	},
+	{
+		"w25q32jwm", INFO(0xef8016, 0, 64 * 1024,  64,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
 	{ "w25x64", INFO(0xef3017, 0, 64 * 1024, 128, SECT_4K) },
 	{ "w25q64", INFO(0xef4017, 0, 64 * 1024, 128, SECT_4K) },
 	{
@@ -2630,7 +2679,9 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "w25q80", INFO(0xef5014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
-	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512,
+			  SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			  SPI_NOR_4B_OPCODES) },
 	{ "w25q256jvm", INFO(0xef7019, 0, 64 * 1024, 512,
 			     SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "w25q256jw", INFO(0xef6019, 0, 64 * 1024, 512,
@@ -2701,7 +2752,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 
 	dev_dbg(nor->dev, "from 0x%08x, len %zd\n", (u32)from, len);
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_READ);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
@@ -2728,7 +2779,7 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 	ret = 0;
 
 read_err:
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_READ);
+	spi_nor_unlock_and_unprep(nor);
 	return ret;
 }
 
@@ -2741,7 +2792,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_WRITE);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
@@ -2814,7 +2865,7 @@ static int sst_write(struct mtd_info *mtd, loff_t to, size_t len,
 	}
 out:
 	*retlen += actual;
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
+	spi_nor_unlock_and_unprep(nor);
 	return ret;
 }
 
@@ -2832,7 +2883,7 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 	dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len);
 
-	ret = spi_nor_lock_and_prep(nor, SPI_NOR_OPS_WRITE);
+	ret = spi_nor_lock_and_prep(nor);
 	if (ret)
 		return ret;
 
@@ -2878,7 +2929,7 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 	}
 
 write_err:
-	spi_nor_unlock_and_unprep(nor, SPI_NOR_OPS_WRITE);
+	spi_nor_unlock_and_unprep(nor);
 	return ret;
 }
 
@@ -5143,8 +5194,12 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 
 	if (info->flags & USE_FSR)
 		nor->flags |= SNOR_F_USE_FSR;
-	if (info->flags & SPI_NOR_HAS_TB)
+	if (info->flags & SPI_NOR_HAS_TB) {
 		nor->flags |= SNOR_F_HAS_SR_TB;
+		if (info->flags & SPI_NOR_TB_SR_BIT6)
+			nor->flags |= SNOR_F_HAS_SR_TB_BIT6;
+	}
+
 	if (info->flags & NO_CHIP_ERASE)
 		nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
 	if (info->flags & USE_CLSR)
diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c
index 10b2459f8951..ea7440ac913b 100644
--- a/drivers/mtd/ubi/attach.c
+++ b/drivers/mtd/ubi/attach.c
@@ -1640,7 +1640,7 @@ int ubi_attach(struct ubi_device *ubi, int force_scan)
 out_wl:
 	ubi_wl_close(ubi);
 out_vtbl:
-	ubi_free_internal_volumes(ubi);
+	ubi_free_all_volumes(ubi);
 	vfree(ubi->vtbl);
 out_ai:
 	destroy_ai(ai);
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index d636bbe214cb..2f93c25bbaee 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -503,21 +503,42 @@ static void uif_close(struct ubi_device *ubi)
 }
 
 /**
- * ubi_free_internal_volumes - free internal volumes.
+ * ubi_free_volumes_from - free volumes from specific index.
  * @ubi: UBI device description object
+ * @from: the start index used for volume free.
  */
-void ubi_free_internal_volumes(struct ubi_device *ubi)
+static void ubi_free_volumes_from(struct ubi_device *ubi, int from)
 {
 	int i;
 
-	for (i = ubi->vtbl_slots;
-	     i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) {
+	for (i = from; i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) {
+		if (!ubi->volumes[i])
+			continue;
 		ubi_eba_replace_table(ubi->volumes[i], NULL);
 		ubi_fastmap_destroy_checkmap(ubi->volumes[i]);
 		kfree(ubi->volumes[i]);
+		ubi->volumes[i] = NULL;
 	}
 }
 
+/**
+ * ubi_free_all_volumes - free all volumes.
+ * @ubi: UBI device description object
+ */
+void ubi_free_all_volumes(struct ubi_device *ubi)
+{
+	ubi_free_volumes_from(ubi, 0);
+}
+
+/**
+ * ubi_free_internal_volumes - free internal volumes.
+ * @ubi: UBI device description object
+ */
+void ubi_free_internal_volumes(struct ubi_device *ubi)
+{
+	ubi_free_volumes_from(ubi, ubi->vtbl_slots);
+}
+
 static int get_bad_peb_limit(const struct ubi_device *ubi, int max_beb_per1024)
 {
 	int limit, device_pebs;
@@ -1013,7 +1034,7 @@ out_uif:
 out_detach:
 	ubi_devices[ubi_num] = NULL;
 	ubi_wl_close(ubi);
-	ubi_free_internal_volumes(ubi);
+	ubi_free_all_volumes(ubi);
 	vfree(ubi->vtbl);
 out_free:
 	vfree(ubi->peb_buf);
@@ -1159,7 +1180,7 @@ static struct mtd_info * __init open_mtd_device(const char *mtd_dev)
 		 * MTD device name.
 		 */
 		mtd = get_mtd_device_nm(mtd_dev);
-		if (IS_ERR(mtd) && PTR_ERR(mtd) == -ENODEV)
+		if (PTR_ERR(mtd) == -ENODEV)
 			/* Probably this is an MTD character device node path */
 			mtd = open_mtd_by_chdev(mtd_dev);
 	} else
diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c
index 1c7be4eb3ba6..53f448e7433a 100644
--- a/drivers/mtd/ubi/fastmap.c
+++ b/drivers/mtd/ubi/fastmap.c
@@ -64,7 +64,7 @@ static int self_check_seen(struct ubi_device *ubi, unsigned long *seen)
 		return 0;
 
 	for (pnum = 0; pnum < ubi->peb_count; pnum++) {
-		if (test_bit(pnum, seen) && ubi->lookuptbl[pnum]) {
+		if (!test_bit(pnum, seen) && ubi->lookuptbl[pnum]) {
 			ubi_err(ubi, "self-check failed for PEB %d, fastmap didn't see it", pnum);
 			ret = -EINVAL;
 		}
@@ -1137,7 +1137,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	struct rb_node *tmp_rb;
 	int ret, i, j, free_peb_count, used_peb_count, vol_count;
 	int scrub_peb_count, erase_peb_count;
-	unsigned long *seen_pebs = NULL;
+	unsigned long *seen_pebs;
 
 	fm_raw = ubi->fm_buf;
 	memset(ubi->fm_buf, 0, ubi->fm_size);
@@ -1151,7 +1151,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	dvbuf = new_fm_vbuf(ubi, UBI_FM_DATA_VOLUME_ID);
 	if (!dvbuf) {
 		ret = -ENOMEM;
-		goto out_kfree;
+		goto out_free_avbuf;
 	}
 
 	avhdr = ubi_get_vid_hdr(avbuf);
@@ -1160,7 +1160,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	seen_pebs = init_seen(ubi);
 	if (IS_ERR(seen_pebs)) {
 		ret = PTR_ERR(seen_pebs);
-		goto out_kfree;
+		goto out_free_dvbuf;
 	}
 
 	spin_lock(&ubi->volumes_lock);
@@ -1328,7 +1328,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	ret = ubi_io_write_vid_hdr(ubi, new_fm->e[0]->pnum, avbuf);
 	if (ret) {
 		ubi_err(ubi, "unable to write vid_hdr to fastmap SB!");
-		goto out_kfree;
+		goto out_free_seen;
 	}
 
 	for (i = 0; i < new_fm->used_blocks; i++) {
@@ -1350,7 +1350,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		if (ret) {
 			ubi_err(ubi, "unable to write vid_hdr to PEB %i!",
 				new_fm->e[i]->pnum);
-			goto out_kfree;
+			goto out_free_seen;
 		}
 	}
 
@@ -1360,7 +1360,7 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 		if (ret) {
 			ubi_err(ubi, "unable to write fastmap to PEB %i!",
 				new_fm->e[i]->pnum);
-			goto out_kfree;
+			goto out_free_seen;
 		}
 	}
 
@@ -1370,10 +1370,13 @@ static int ubi_write_fastmap(struct ubi_device *ubi,
 	ret = self_check_seen(ubi, seen_pebs);
 	dbg_bld("fastmap written!");
 
-out_kfree:
-	ubi_free_vid_buf(avbuf);
-	ubi_free_vid_buf(dvbuf);
+out_free_seen:
 	free_seen(seen_pebs);
+out_free_dvbuf:
+	ubi_free_vid_buf(dvbuf);
+out_free_avbuf:
+	ubi_free_vid_buf(avbuf);
+
 out:
 	return ret;
 }
diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h
index 9688b411c930..73c67e5c08f8 100644
--- a/drivers/mtd/ubi/ubi.h
+++ b/drivers/mtd/ubi/ubi.h
@@ -950,6 +950,7 @@ int ubi_volume_notify(struct ubi_device *ubi, struct ubi_volume *vol,
 int ubi_notify_all(struct ubi_device *ubi, int ntype,
 		   struct notifier_block *nb);
 int ubi_enumerate_volumes(struct notifier_block *nb);
+void ubi_free_all_volumes(struct ubi_device *ubi);
 void ubi_free_internal_volumes(struct ubi_device *ubi);
 
 /* kapi.c */
diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c
index 53d8ab54e181..f700f0e4f2ec 100644
--- a/drivers/mtd/ubi/vtbl.c
+++ b/drivers/mtd/ubi/vtbl.c
@@ -782,7 +782,7 @@ static int check_attaching_info(const struct ubi_device *ubi,
  */
 int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai)
 {
-	int i, err;
+	int err;
 	struct ubi_ainf_volume *av;
 
 	empty_vtbl_record.crc = cpu_to_be32(0xf116c36b);
@@ -851,11 +851,7 @@ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai)
 
 out_free:
 	vfree(ubi->vtbl);
-	for (i = 0; i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) {
-		ubi_fastmap_destroy_checkmap(ubi->volumes[i]);
-		kfree(ubi->volumes[i]);
-		ubi->volumes[i] = NULL;
-	}
+	ubi_free_all_volumes(ubi);
 	return err;
 }
 
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 5d77a38dba54..837d690a8c60 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -319,7 +319,7 @@ static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi,
 					  struct rb_root *root, int diff)
 {
 	struct rb_node *p;
-	struct ubi_wl_entry *e, *prev_e = NULL;
+	struct ubi_wl_entry *e;
 	int max;
 
 	e = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb);
@@ -334,7 +334,6 @@ static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi,
 			p = p->rb_left;
 		else {
 			p = p->rb_right;
-			prev_e = e;
 			e = e1;
 		}
 	}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
index 066765fbef06..0a59a09ef82f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
@@ -296,7 +296,6 @@ static inline void bnx2x_dcb_config_qm(struct bnx2x *bp, enum cos_mode mode,
  *    possible, the driver should only write the valid vnics into the internal
  *    ram according to the appropriate port mode.
  */
-#define BITS_TO_BYTES(x) ((x)/8)
 
 /* CMNG constants, as derived from system spec calculations */
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 483935b001c8..597e6fd5bfea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7893,7 +7893,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	int tcs, i;
 
 	tcs = netdev_get_num_tc(dev);
-	if (tcs > 1) {
+	if (tcs) {
 		int i, off, count;
 
 		for (i = 0; i < tcs; i++) {
@@ -9241,6 +9241,17 @@ void bnxt_half_close_nic(struct bnxt *bp)
 	bnxt_free_mem(bp, false);
 }
 
+static void bnxt_reenable_sriov(struct bnxt *bp)
+{
+	if (BNXT_PF(bp)) {
+		struct bnxt_pf_info *pf = &bp->pf;
+		int n = pf->active_vfs;
+
+		if (n)
+			bnxt_cfg_hw_sriov(bp, &n, true);
+	}
+}
+
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -9259,15 +9270,10 @@ static int bnxt_open(struct net_device *dev)
 		bnxt_hwrm_if_change(bp, false);
 	} else {
 		if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
-			if (BNXT_PF(bp)) {
-				struct bnxt_pf_info *pf = &bp->pf;
-				int n = pf->active_vfs;
-
-				if (n)
-					bnxt_cfg_hw_sriov(bp, &n, true);
-			}
-			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 				bnxt_ulp_start(bp, 0);
+				bnxt_reenable_sriov(bp);
+			}
 		}
 		bnxt_hwmon_open(bp);
 	}
@@ -9307,10 +9313,6 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
 	del_timer_sync(&bp->timer);
-	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) &&
-	    pci_is_enabled(bp->pdev))
-		pci_disable_device(bp->pdev);
-
 	bnxt_free_skbs(bp);
 
 	/* Save ring stats before shutdown */
@@ -10096,9 +10098,16 @@ static void bnxt_reset(struct bnxt *bp, bool silent)
 static void bnxt_fw_reset_close(struct bnxt *bp)
 {
 	bnxt_ulp_stop(bp);
+	/* When firmware is fatal state, disable PCI device to prevent
+	 * any potential bad DMAs before freeing kernel memory.
+	 */
+	if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+		pci_disable_device(bp->pdev);
 	__bnxt_close_nic(bp, true, false);
 	bnxt_clear_int_mode(bp);
 	bnxt_hwrm_func_drv_unrgtr(bp);
+	if (pci_is_enabled(bp->pdev))
+		pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
 	bp->ctx = NULL;
@@ -10831,6 +10840,8 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		smp_mb__before_atomic();
 		clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 		bnxt_ulp_start(bp, rc);
+		if (!rc)
+			bnxt_reenable_sriov(bp);
 		bnxt_dl_health_recovery_done(bp);
 		bnxt_dl_health_status_update(bp, true);
 		rtnl_unlock();
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 2dfbfdff45a8..037e054b01a2 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -324,8 +324,7 @@
 	      ETH_HLEN + ETH_FCS_LEN,			     \
 	      cache_line_size())
 
-#define MVNETA_SKB_HEADROOM	(max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + \
-				 NET_IP_ALIGN)
+#define MVNETA_SKB_HEADROOM	max(XDP_PACKET_HEADROOM, NET_SKB_PAD)
 #define MVNETA_SKB_PAD	(SKB_DATA_ALIGN(sizeof(struct skb_shared_info) + \
 			 MVNETA_SKB_HEADROOM))
 #define MVNETA_SKB_SIZE(len)	(SKB_DATA_ALIGN(len) + MVNETA_SKB_PAD)
@@ -1167,6 +1166,7 @@ bm_mtu_err:
 	mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id);
 
 	pp->bm_priv = NULL;
+	pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
 	mvreg_write(pp, MVNETA_ACC_MODE, MVNETA_ACC_MODE_EXT1);
 	netdev_info(pp->dev, "fail to update MTU, fall back to software BM\n");
 }
@@ -4948,7 +4948,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	pp->id = global_port_id++;
-	pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
 
 	/* Obtain access to BM resources if enabled and already initialized */
 	bm_node = of_parse_phandle(dn, "buffer-manager", 0);
@@ -4973,6 +4972,10 @@ static int mvneta_probe(struct platform_device *pdev)
 	}
 	of_node_put(bm_node);
 
+	/* sw buffer management */
+	if (!pp->bm_priv)
+		pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
+
 	err = mvneta_init(&pdev->dev, pp);
 	if (err < 0)
 		goto err_netdev;
@@ -5130,6 +5133,7 @@ static int mvneta_resume(struct device *device)
 		err = mvneta_bm_port_init(pdev, pp);
 		if (err < 0) {
 			dev_info(&pdev->dev, "use SW buffer management\n");
+			pp->rx_offset_correction = MVNETA_SKB_HEADROOM;
 			pp->bm_priv = NULL;
 		}
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 8247d21d0432..b945bd3d5d88 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -171,9 +171,9 @@ static int otx2_hw_get_mac_addr(struct otx2_nic *pfvf,
 	}
 
 	msghdr = otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr);
-	if (!msghdr) {
+	if (IS_ERR(msghdr)) {
 		otx2_mbox_unlock(&pfvf->mbox);
-		return -ENOMEM;
+		return PTR_ERR(msghdr);
 	}
 	rsp = (struct nix_get_mac_addr_rsp *)msghdr;
 	ether_addr_copy(netdev->dev_addr, rsp->mac_addr);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index 79a2801d59f6..02526c53d4f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -614,7 +614,7 @@ mlxsw_sp_qdisc_tbf_rate_kbps(struct tc_tbf_qopt_offload_replace_params *p)
 	/* TBF interface is in bytes/s, whereas Spectrum ASIC is configured in
 	 * Kbits/s.
 	 */
-	return p->rate.rate_bytes_ps / 1000 * 8;
+	return div_u64(p->rate.rate_bytes_ps, 1000) * 8;
 }
 
 static int
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h
index f131adad96e3..ce07c2931a72 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_if.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h
@@ -866,7 +866,7 @@ struct ionic_rxq_comp {
 #define IONIC_RXQ_COMP_CSUM_F_VLAN	0x40
 #define IONIC_RXQ_COMP_CSUM_F_CALC	0x80
 	u8     pkt_type_color;
-#define IONIC_RXQ_COMP_PKT_TYPE_MASK	0x0f
+#define IONIC_RXQ_COMP_PKT_TYPE_MASK	0x7f
 };
 
 enum ionic_pkt_type {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index fbfff2b1dc93..1a636bad717d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -1398,14 +1398,11 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn,
 {
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 	struct qed_qm_pf_rt_init_params params;
-	struct qed_mcp_link_state *p_link;
 	struct qed_qm_iids iids;
 
 	memset(&iids, 0, sizeof(iids));
 	qed_cxt_qm_iids(p_hwfn, &iids);
 
-	p_link = &QED_LEADING_HWFN(p_hwfn->cdev)->mcp_info->link_output;
-
 	memset(&params, 0, sizeof(params));
 	params.port_id = p_hwfn->port_id;
 	params.pf_id = p_hwfn->rel_pf_id;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 7912911337d4..03bdd2e26329 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -3114,6 +3114,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 		if (!p_hwfn->fw_overlay_mem) {
 			DP_NOTICE(p_hwfn,
 				  "Failed to allocate fw overlay memory\n");
+			rc = -ENOMEM;
 			goto load_err;
 		}
 
diff --git a/drivers/net/ethernet/sgi/Kconfig b/drivers/net/ethernet/sgi/Kconfig
index 37f048e1230c..bc26fa0d196f 100644
--- a/drivers/net/ethernet/sgi/Kconfig
+++ b/drivers/net/ethernet/sgi/Kconfig
@@ -6,7 +6,7 @@
 config NET_VENDOR_SGI
 	bool "SGI devices"
 	default y
-	depends on (PCI && SGI_IP27) || SGI_IP32
+	depends on (PCI && SGI_MFD_IOC3) ||  SGI_IP32
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -19,7 +19,8 @@ if NET_VENDOR_SGI
 
 config SGI_IOC3_ETH
 	bool "SGI IOC3 Ethernet"
-	depends on PCI && SGI_IP27
+	depends on PCI && SGI_MFD_IOC3
+	select CRC16
 	select CRC32
 	select MII
 	---help---
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 06637b03deed..e61eb891c0f7 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -14,7 +14,6 @@
  *  o Use prefetching for large packets.  What is a good lower limit for
  *    prefetching?
  *  o Use hardware checksums.
- *  o Convert to using a IOC3 meta driver.
  *  o Which PHYs might possibly be attached to the IOC3 in real live,
  *    which workarounds are required for them?  Do we ever have Lucent's?
  *  o For the 2.5 branch kill the mii-tool ioctls.
@@ -28,7 +27,8 @@
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/module.h>
-#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/crc16.h>
 #include <linux/crc32.h>
 #include <linux/mii.h>
 #include <linux/in.h>
@@ -37,28 +37,22 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/gfp.h>
-
-#ifdef CONFIG_SERIAL_8250
-#include <linux/serial_core.h>
-#include <linux/serial_8250.h>
-#include <linux/serial_reg.h>
-#endif
-
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/skbuff.h>
 #include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/nvmem-consumer.h>
 
 #include <net/ip.h>
 
-#include <asm/byteorder.h>
-#include <asm/pgtable.h>
-#include <linux/uaccess.h>
-#include <asm/sn/types.h>
 #include <asm/sn/ioc3.h>
 #include <asm/pci/bridge.h>
 
+#define CRC16_INIT	0
+#define CRC16_VALID	0xb001
+
 /* Number of RX buffers.  This is tunable in the range of 16 <= x < 512.
  * The value must be a power of two.
  */
@@ -85,7 +79,6 @@
 /* Private per NIC data of the driver.  */
 struct ioc3_private {
 	struct ioc3_ethregs *regs;
-	struct ioc3 *all_regs;
 	struct device *dma_dev;
 	u32 *ssram;
 	unsigned long *rxr;		/* pointer to receiver ring */
@@ -104,9 +97,6 @@ struct ioc3_private {
 	spinlock_t ioc3_lock;
 	struct mii_if_info mii;
 
-	struct net_device *dev;
-	struct pci_dev *pdev;
-
 	/* Members used by autonegotiation  */
 	struct timer_list ioc3_timer;
 };
@@ -123,10 +113,8 @@ static int ioc3_alloc_rx_bufs(struct net_device *dev);
 static void ioc3_free_rx_bufs(struct ioc3_private *ip);
 static inline void ioc3_clean_tx_ring(struct ioc3_private *ip);
 
-static const char ioc3_str[] = "IOC3 Ethernet";
 static const struct ethtool_ops ioc3_ethtool_ops;
 
-
 static inline unsigned long aligned_rx_skb_addr(unsigned long addr)
 {
 	return (~addr + 1) & (IOC3_DMA_XFER_LEN - 1UL);
@@ -179,225 +167,61 @@ static inline unsigned long ioc3_map(dma_addr_t addr, unsigned long attr)
 #define ERBAR_VAL	0
 #endif
 
-#define IOC3_SIZE 0x100000
-
-static inline u32 mcr_pack(u32 pulse, u32 sample)
-{
-	return (pulse << 10) | (sample << 2);
-}
-
-static int nic_wait(u32 __iomem *mcr)
-{
-	u32 m;
-
-	do {
-		m = readl(mcr);
-	} while (!(m & 2));
-
-	return m & 1;
-}
-
-static int nic_reset(u32 __iomem *mcr)
-{
-	int presence;
-
-	writel(mcr_pack(500, 65), mcr);
-	presence = nic_wait(mcr);
-
-	writel(mcr_pack(0, 500), mcr);
-	nic_wait(mcr);
-
-	return presence;
-}
-
-static inline int nic_read_bit(u32 __iomem *mcr)
-{
-	int result;
-
-	writel(mcr_pack(6, 13), mcr);
-	result = nic_wait(mcr);
-	writel(mcr_pack(0, 100), mcr);
-	nic_wait(mcr);
-
-	return result;
-}
-
-static inline void nic_write_bit(u32 __iomem *mcr, int bit)
+static int ioc3eth_nvmem_match(struct device *dev, const void *data)
 {
-	if (bit)
-		writel(mcr_pack(6, 110), mcr);
-	else
-		writel(mcr_pack(80, 30), mcr);
+	const char *name = dev_name(dev);
+	const char *prefix = data;
+	int prefix_len;
 
-	nic_wait(mcr);
-}
-
-/* Read a byte from an iButton device
- */
-static u32 nic_read_byte(u32 __iomem *mcr)
-{
-	u32 result = 0;
-	int i;
+	prefix_len = strlen(prefix);
+	if (strlen(name) < (prefix_len + 3))
+		return 0;
 
-	for (i = 0; i < 8; i++)
-		result = (result >> 1) | (nic_read_bit(mcr) << 7);
+	if (memcmp(prefix, name, prefix_len) != 0)
+		return 0;
 
-	return result;
-}
-
-/* Write a byte to an iButton device
- */
-static void nic_write_byte(u32 __iomem *mcr, int byte)
-{
-	int i, bit;
-
-	for (i = 8; i; i--) {
-		bit = byte & 1;
-		byte >>= 1;
-
-		nic_write_bit(mcr, bit);
-	}
-}
-
-static u64 nic_find(u32 __iomem *mcr, int *last)
-{
-	int a, b, index, disc;
-	u64 address = 0;
-
-	nic_reset(mcr);
-	/* Search ROM.  */
-	nic_write_byte(mcr, 0xf0);
-
-	/* Algorithm from ``Book of iButton Standards''.  */
-	for (index = 0, disc = 0; index < 64; index++) {
-		a = nic_read_bit(mcr);
-		b = nic_read_bit(mcr);
-
-		if (a && b) {
-			pr_warn("NIC search failed (not fatal).\n");
-			*last = 0;
-			return 0;
-		}
-
-		if (!a && !b) {
-			if (index == *last) {
-				address |= 1UL << index;
-			} else if (index > *last) {
-				address &= ~(1UL << index);
-				disc = index;
-			} else if ((address & (1UL << index)) == 0) {
-				disc = index;
-			}
-			nic_write_bit(mcr, address & (1UL << index));
-			continue;
-		} else {
-			if (a)
-				address |= 1UL << index;
-			else
-				address &= ~(1UL << index);
-			nic_write_bit(mcr, a);
-			continue;
-		}
-	}
-
-	*last = disc;
-
-	return address;
-}
-
-static int nic_init(u32 __iomem *mcr)
-{
-	const char *unknown = "unknown";
-	const char *type = unknown;
-	u8 crc;
-	u8 serial[6];
-	int save = 0, i;
-
-	while (1) {
-		u64 reg;
-
-		reg = nic_find(mcr, &save);
-
-		switch (reg & 0xff) {
-		case 0x91:
-			type = "DS1981U";
-			break;
-		default:
-			if (save == 0) {
-				/* Let the caller try again.  */
-				return -1;
-			}
-			continue;
-		}
-
-		nic_reset(mcr);
-
-		/* Match ROM.  */
-		nic_write_byte(mcr, 0x55);
-		for (i = 0; i < 8; i++)
-			nic_write_byte(mcr, (reg >> (i << 3)) & 0xff);
-
-		reg >>= 8; /* Shift out type.  */
-		for (i = 0; i < 6; i++) {
-			serial[i] = reg & 0xff;
-			reg >>= 8;
-		}
-		crc = reg & 0xff;
-		break;
-	}
-
-	pr_info("Found %s NIC", type);
-	if (type != unknown)
-		pr_cont(" registration number %pM, CRC %02x", serial, crc);
-	pr_cont(".\n");
+	/* found nvmem device which is attached to our ioc3
+	 * now check for one wire family code 09, 89 and 91
+	 */
+	if (memcmp(name + prefix_len, "09-", 3) == 0)
+		return 1;
+	if (memcmp(name + prefix_len, "89-", 3) == 0)
+		return 1;
+	if (memcmp(name + prefix_len, "91-", 3) == 0)
+		return 1;
 
 	return 0;
 }
 
-/* Read the NIC (Number-In-a-Can) device used to store the MAC address on
- * SN0 / SN00 nodeboards and PCI cards.
- */
-static void ioc3_get_eaddr_nic(struct ioc3_private *ip)
+static int ioc3eth_get_mac_addr(struct resource *res, u8 mac_addr[6])
 {
-	u32 __iomem *mcr = &ip->all_regs->mcr;
-	int tries = 2; /* There may be some problem with the battery?  */
-	u8 nic[14];
+	struct nvmem_device *nvmem;
+	char prefix[24];
+	u8 prom[16];
+	int ret;
 	int i;
 
-	writel(1 << 21, &ip->all_regs->gpcr_s);
+	snprintf(prefix, sizeof(prefix), "ioc3-%012llx-",
+		 res->start & ~0xffff);
 
-	while (tries--) {
-		if (!nic_init(mcr))
-			break;
-		udelay(500);
-	}
-
-	if (tries < 0) {
-		pr_err("Failed to read MAC address\n");
-		return;
-	}
+	nvmem = nvmem_device_find(prefix, ioc3eth_nvmem_match);
+	if (IS_ERR(nvmem))
+		return PTR_ERR(nvmem);
 
-	/* Read Memory.  */
-	nic_write_byte(mcr, 0xf0);
-	nic_write_byte(mcr, 0x00);
-	nic_write_byte(mcr, 0x00);
+	ret = nvmem_device_read(nvmem, 0, 16, prom);
+	nvmem_device_put(nvmem);
+	if (ret < 0)
+		return ret;
 
-	for (i = 13; i >= 0; i--)
-		nic[i] = nic_read_byte(mcr);
+	/* check, if content is valid */
+	if (prom[0] != 0x0a ||
+	    crc16(CRC16_INIT, prom, 13) != CRC16_VALID)
+		return -EINVAL;
 
-	for (i = 2; i < 8; i++)
-		ip->dev->dev_addr[i - 2] = nic[i];
-}
-
-/* Ok, this is hosed by design.  It's necessary to know what machine the
- * NIC is in in order to know how to read the NIC address.  We also have
- * to know if it's a PCI card or a NIC in on the node board ...
- */
-static void ioc3_get_eaddr(struct ioc3_private *ip)
-{
-	ioc3_get_eaddr_nic(ip);
+	for (i = 0; i < 6; i++)
+		mac_addr[i] = prom[10 - i];
 
-	pr_info("Ethernet address is %pM.\n", ip->dev->dev_addr);
+	return 0;
 }
 
 static void __ioc3_set_mac_address(struct net_device *dev)
@@ -770,7 +594,7 @@ static int ioc3_mii_init(struct ioc3_private *ip)
 	u16 word;
 
 	for (i = 0; i < 32; i++) {
-		word = ioc3_mdio_read(ip->dev, i, MII_PHYSID1);
+		word = ioc3_mdio_read(ip->mii.dev, i, MII_PHYSID1);
 
 		if (word != 0xffff && word != 0x0000) {
 			found = 1;
@@ -975,12 +799,6 @@ static int ioc3_open(struct net_device *dev)
 {
 	struct ioc3_private *ip = netdev_priv(dev);
 
-	if (request_irq(dev->irq, ioc3_interrupt, IRQF_SHARED, ioc3_str, dev)) {
-		netdev_err(dev, "Can't get irq %d\n", dev->irq);
-
-		return -EAGAIN;
-	}
-
 	ip->ehar_h = 0;
 	ip->ehar_l = 0;
 
@@ -1013,147 +831,6 @@ static int ioc3_close(struct net_device *dev)
 	return 0;
 }
 
-/* MENET cards have four IOC3 chips, which are attached to two sets of
- * PCI slot resources each: the primary connections are on slots
- * 0..3 and the secondaries are on 4..7
- *
- * All four ethernets are brought out to connectors; six serial ports
- * (a pair from each of the first three IOC3s) are brought out to
- * MiniDINs; all other subdevices are left swinging in the wind, leave
- * them disabled.
- */
-
-static int ioc3_adjacent_is_ioc3(struct pci_dev *pdev, int slot)
-{
-	struct pci_dev *dev = pci_get_slot(pdev->bus, PCI_DEVFN(slot, 0));
-	int ret = 0;
-
-	if (dev) {
-		if (dev->vendor == PCI_VENDOR_ID_SGI &&
-		    dev->device == PCI_DEVICE_ID_SGI_IOC3)
-			ret = 1;
-		pci_dev_put(dev);
-	}
-
-	return ret;
-}
-
-static int ioc3_is_menet(struct pci_dev *pdev)
-{
-	return !pdev->bus->parent &&
-	       ioc3_adjacent_is_ioc3(pdev, 0) &&
-	       ioc3_adjacent_is_ioc3(pdev, 1) &&
-	       ioc3_adjacent_is_ioc3(pdev, 2);
-}
-
-#ifdef CONFIG_SERIAL_8250
-/* Note about serial ports and consoles:
- * For console output, everyone uses the IOC3 UARTA (offset 0x178)
- * connected to the master node (look in ip27_setup_console() and
- * ip27prom_console_write()).
- *
- * For serial (/dev/ttyS0 etc), we can not have hardcoded serial port
- * addresses on a partitioned machine. Since we currently use the ioc3
- * serial ports, we use dynamic serial port discovery that the serial.c
- * driver uses for pci/pnp ports (there is an entry for the SGI ioc3
- * boards in pci_boards[]). Unfortunately, UARTA's pio address is greater
- * than UARTB's, although UARTA on o200s has traditionally been known as
- * port 0. So, we just use one serial port from each ioc3 (since the
- * serial driver adds addresses to get to higher ports).
- *
- * The first one to do a register_console becomes the preferred console
- * (if there is no kernel command line console= directive). /dev/console
- * (ie 5, 1) is then "aliased" into the device number returned by the
- * "device" routine referred to in this console structure
- * (ip27prom_console_dev).
- *
- * Also look in ip27-pci.c:pci_fixup_ioc3() for some comments on working
- * around ioc3 oddities in this respect.
- *
- * The IOC3 serials use a 22MHz clock rate with an additional divider which
- * can be programmed in the SCR register if the DLAB bit is set.
- *
- * Register to interrupt zero because we share the interrupt with
- * the serial driver which we don't properly support yet.
- *
- * Can't use UPF_IOREMAP as the whole of IOC3 resources have already been
- * registered.
- */
-static void ioc3_8250_register(struct ioc3_uartregs __iomem *uart)
-{
-#define COSMISC_CONSTANT 6
-
-	struct uart_8250_port port = {
-		.port = {
-			.irq		= 0,
-			.flags		= UPF_SKIP_TEST | UPF_BOOT_AUTOCONF,
-			.iotype		= UPIO_MEM,
-			.regshift	= 0,
-			.uartclk	= (22000000 << 1) / COSMISC_CONSTANT,
-
-			.membase	= (unsigned char __iomem *)uart,
-			.mapbase	= (unsigned long)uart,
-		}
-	};
-	unsigned char lcr;
-
-	lcr = readb(&uart->iu_lcr);
-	writeb(lcr | UART_LCR_DLAB, &uart->iu_lcr);
-	writeb(COSMISC_CONSTANT, &uart->iu_scr);
-	writeb(lcr, &uart->iu_lcr);
-	readb(&uart->iu_lcr);
-	serial8250_register_8250_port(&port);
-}
-
-static void ioc3_serial_probe(struct pci_dev *pdev, struct ioc3 *ioc3)
-{
-	u32 sio_iec;
-
-	/* We need to recognice and treat the fourth MENET serial as it
-	 * does not have an SuperIO chip attached to it, therefore attempting
-	 * to access it will result in bus errors.  We call something an
-	 * MENET if PCI slot 0, 1, 2 and 3 of a master PCI bus all have an IOC3
-	 * in it.  This is paranoid but we want to avoid blowing up on a
-	 * showhorn PCI box that happens to have 4 IOC3 cards in it so it's
-	 * not paranoid enough ...
-	 */
-	if (ioc3_is_menet(pdev) && PCI_SLOT(pdev->devfn) == 3)
-		return;
-
-	/* Switch IOC3 to PIO mode.  It probably already was but let's be
-	 * paranoid
-	 */
-	writel(GPCR_UARTA_MODESEL | GPCR_UARTB_MODESEL, &ioc3->gpcr_s);
-	readl(&ioc3->gpcr_s);
-	writel(0, &ioc3->gppr[6]);
-	readl(&ioc3->gppr[6]);
-	writel(0, &ioc3->gppr[7]);
-	readl(&ioc3->gppr[7]);
-	writel(readl(&ioc3->port_a.sscr) & ~SSCR_DMA_EN, &ioc3->port_a.sscr);
-	readl(&ioc3->port_a.sscr);
-	writel(readl(&ioc3->port_b.sscr) & ~SSCR_DMA_EN, &ioc3->port_b.sscr);
-	readl(&ioc3->port_b.sscr);
-	/* Disable all SA/B interrupts except for SA/B_INT in SIO_IEC. */
-	sio_iec = readl(&ioc3->sio_iec);
-	sio_iec &= ~(SIO_IR_SA_TX_MT | SIO_IR_SA_RX_FULL |
-		     SIO_IR_SA_RX_HIGH | SIO_IR_SA_RX_TIMER |
-		     SIO_IR_SA_DELTA_DCD | SIO_IR_SA_DELTA_CTS |
-		     SIO_IR_SA_TX_EXPLICIT | SIO_IR_SA_MEMERR);
-	sio_iec |= SIO_IR_SA_INT;
-	sio_iec &= ~(SIO_IR_SB_TX_MT | SIO_IR_SB_RX_FULL |
-		     SIO_IR_SB_RX_HIGH | SIO_IR_SB_RX_TIMER |
-		     SIO_IR_SB_DELTA_DCD | SIO_IR_SB_DELTA_CTS |
-		     SIO_IR_SB_TX_EXPLICIT | SIO_IR_SB_MEMERR);
-	sio_iec |= SIO_IR_SB_INT;
-	writel(sio_iec, &ioc3->sio_iec);
-	writel(0, &ioc3->port_a.sscr);
-	writel(0, &ioc3->port_b.sscr);
-
-	ioc3_8250_register(&ioc3->sregs.uarta);
-	ioc3_8250_register(&ioc3->sregs.uartb);
-}
-#endif
-
 static const struct net_device_ops ioc3_netdev_ops = {
 	.ndo_open		= ioc3_open,
 	.ndo_stop		= ioc3_close,
@@ -1166,61 +843,52 @@ static const struct net_device_ops ioc3_netdev_ops = {
 	.ndo_set_mac_address	= ioc3_set_mac_address,
 };
 
-static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+static int ioc3eth_probe(struct platform_device *pdev)
 {
-	unsigned int sw_physid1, sw_physid2;
-	struct net_device *dev = NULL;
+	u32 sw_physid1, sw_physid2, vendor, model, rev;
 	struct ioc3_private *ip;
-	struct ioc3 *ioc3;
-	unsigned long ioc3_base, ioc3_size;
-	u32 vendor, model, rev;
+	struct net_device *dev;
+	struct resource *regs;
+	u8 mac_addr[6];
 	int err;
 
-	/* Configure DMA attributes. */
-	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-	if (err) {
-		pr_err("%s: No usable DMA configuration, aborting.\n",
-		       pci_name(pdev));
-		goto out;
-	}
-
-	if (pci_enable_device(pdev))
-		return -ENODEV;
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	/* get mac addr from one wire prom */
+	if (ioc3eth_get_mac_addr(regs, mac_addr))
+		return -EPROBE_DEFER; /* not available yet */
 
 	dev = alloc_etherdev(sizeof(struct ioc3_private));
-	if (!dev) {
-		err = -ENOMEM;
-		goto out_disable;
-	}
-
-	err = pci_request_regions(pdev, "ioc3");
-	if (err)
-		goto out_free;
+	if (!dev)
+		return -ENOMEM;
 
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	ip = netdev_priv(dev);
-	ip->dev = dev;
-	ip->dma_dev = &pdev->dev;
-
-	dev->irq = pdev->irq;
+	ip->dma_dev = pdev->dev.parent;
+	ip->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (!ip->regs) {
+		err = -ENOMEM;
+		goto out_free;
+	}
 
-	ioc3_base = pci_resource_start(pdev, 0);
-	ioc3_size = pci_resource_len(pdev, 0);
-	ioc3 = (struct ioc3 *)ioremap(ioc3_base, ioc3_size);
-	if (!ioc3) {
-		pr_err("ioc3eth(%s): ioremap failed, goodbye.\n",
-		       pci_name(pdev));
+	ip->ssram = devm_platform_ioremap_resource(pdev, 1);
+	if (!ip->ssram) {
 		err = -ENOMEM;
-		goto out_res;
+		goto out_free;
 	}
-	ip->regs = &ioc3->eth;
-	ip->ssram = ioc3->ssram;
-	ip->all_regs = ioc3;
 
-#ifdef CONFIG_SERIAL_8250
-	ioc3_serial_probe(pdev, ioc3);
-#endif
+	dev->irq = platform_get_irq(pdev, 0);
+	if (dev->irq < 0) {
+		err = dev->irq;
+		goto out_free;
+	}
+
+	if (devm_request_irq(&pdev->dev, dev->irq, ioc3_interrupt,
+			     IRQF_SHARED, "ioc3-eth", dev)) {
+		dev_err(&pdev->dev, "Can't get irq %d\n", dev->irq);
+		err = -ENODEV;
+		goto out_free;
+	}
 
 	spin_lock_init(&ip->ioc3_lock);
 	timer_setup(&ip->ioc3_timer, ioc3_timer, 0);
@@ -1250,8 +918,6 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ioc3_init(dev);
 
-	ip->pdev = pdev;
-
 	ip->mii.phy_id_mask = 0x1f;
 	ip->mii.reg_num_mask = 0x1f;
 	ip->mii.dev = dev;
@@ -1261,15 +927,14 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ioc3_mii_init(ip);
 
 	if (ip->mii.phy_id == -1) {
-		pr_err("ioc3-eth(%s): Didn't find a PHY, goodbye.\n",
-		       pci_name(pdev));
+		netdev_err(dev, "Didn't find a PHY, goodbye.\n");
 		err = -ENODEV;
 		goto out_stop;
 	}
 
 	ioc3_mii_start(ip);
 	ioc3_ssram_disc(ip);
-	ioc3_get_eaddr(ip);
+	memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
 
 	/* The IOC3-specific entries in the device structure. */
 	dev->watchdog_timeo	= 5 * HZ;
@@ -1306,21 +971,14 @@ out_stop:
 	if (ip->tx_ring)
 		dma_free_coherent(ip->dma_dev, TX_RING_SIZE, ip->tx_ring,
 				  ip->txr_dma);
-out_res:
-	pci_release_regions(pdev);
 out_free:
 	free_netdev(dev);
-out_disable:
-	/* We should call pci_disable_device(pdev); here if the IOC3 wasn't
-	 * such a weird device ...
-	 */
-out:
 	return err;
 }
 
-static void ioc3_remove_one(struct pci_dev *pdev)
+static int ioc3eth_remove(struct platform_device *pdev)
 {
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = platform_get_drvdata(pdev);
 	struct ioc3_private *ip = netdev_priv(dev);
 
 	dma_free_coherent(ip->dma_dev, RX_RING_SIZE, ip->rxr, ip->rxr_dma);
@@ -1328,27 +986,11 @@ static void ioc3_remove_one(struct pci_dev *pdev)
 
 	unregister_netdev(dev);
 	del_timer_sync(&ip->ioc3_timer);
-
-	iounmap(ip->all_regs);
-	pci_release_regions(pdev);
 	free_netdev(dev);
-	/* We should call pci_disable_device(pdev); here if the IOC3 wasn't
-	 * such a weird device ...
-	 */
-}
 
-static const struct pci_device_id ioc3_pci_tbl[] = {
-	{ PCI_VENDOR_ID_SGI, PCI_DEVICE_ID_SGI_IOC3, PCI_ANY_ID, PCI_ANY_ID },
-	{ 0 }
-};
-MODULE_DEVICE_TABLE(pci, ioc3_pci_tbl);
+	return 0;
+}
 
-static struct pci_driver ioc3_driver = {
-	.name		= "ioc3-eth",
-	.id_table	= ioc3_pci_tbl,
-	.probe		= ioc3_probe,
-	.remove		= ioc3_remove_one,
-};
 
 static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -1530,11 +1172,10 @@ static inline unsigned int ioc3_hash(const unsigned char *addr)
 static void ioc3_get_drvinfo(struct net_device *dev,
 			     struct ethtool_drvinfo *info)
 {
-	struct ioc3_private *ip = netdev_priv(dev);
-
 	strlcpy(info->driver, IOC3_NAME, sizeof(info->driver));
 	strlcpy(info->version, IOC3_VERSION, sizeof(info->version));
-	strlcpy(info->bus_info, pci_name(ip->pdev), sizeof(info->bus_info));
+	strlcpy(info->bus_info, pci_name(to_pci_dev(dev->dev.parent)),
+		sizeof(info->bus_info));
 }
 
 static int ioc3_get_link_ksettings(struct net_device *dev,
@@ -1646,7 +1287,16 @@ static void ioc3_set_multicast_list(struct net_device *dev)
 	spin_unlock_irq(&ip->ioc3_lock);
 }
 
-module_pci_driver(ioc3_driver);
+static struct platform_driver ioc3eth_driver = {
+	.probe  = ioc3eth_probe,
+	.remove = ioc3eth_remove,
+	.driver = {
+		.name = "ioc3-eth",
+	}
+};
+
+module_platform_driver(ioc3eth_driver);
+
 MODULE_AUTHOR("Ralf Baechle <ralf@linux-mips.org>");
 MODULE_DESCRIPTION("SGI IOC3 Ethernet driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ff1cbfc834b0..5836b21edd7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4974,6 +4974,7 @@ int stmmac_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	u32 chan;
 
 	if (!ndev || !netif_running(ndev))
 		return 0;
@@ -4987,6 +4988,9 @@ int stmmac_suspend(struct device *dev)
 
 	stmmac_disable_all_queues(priv);
 
+	for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++)
+		del_timer_sync(&priv->tx_queue[chan].txtimer);
+
 	/* Stop TX/RX DMA */
 	stmmac_stop_all_dma(priv);
 
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 7032a2405e1a..af07ea760b35 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -767,12 +767,12 @@ static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
 	int i;
 
 	gtp->addr_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				       GFP_KERNEL);
+				       GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->addr_hash == NULL)
 		return -ENOMEM;
 
 	gtp->tid_hash = kmalloc_array(hsize, sizeof(struct hlist_head),
-				      GFP_KERNEL);
+				      GFP_KERNEL | __GFP_NOWARN);
 	if (gtp->tid_hash == NULL)
 		goto err1;
 
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 2b74425822ab..0b362b8dac17 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -218,6 +218,7 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev,
 {
 	struct nsim_bpf_bound_prog *state;
 	char name[16];
+	int ret;
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state)
@@ -230,9 +231,10 @@ static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev,
 	/* Program id is not populated yet when we create the state. */
 	sprintf(name, "%u", nsim_dev->prog_id_gen++);
 	state->ddir = debugfs_create_dir(name, nsim_dev->ddir_bpf_bound_progs);
-	if (IS_ERR_OR_NULL(state->ddir)) {
+	if (IS_ERR(state->ddir)) {
+		ret = PTR_ERR(state->ddir);
 		kfree(state);
-		return -ENOMEM;
+		return ret;
 	}
 
 	debugfs_create_u32("id", 0400, state->ddir, &prog->aux->id);
@@ -587,8 +589,8 @@ int nsim_bpf_dev_init(struct nsim_dev *nsim_dev)
 
 	nsim_dev->ddir_bpf_bound_progs = debugfs_create_dir("bpf_bound_progs",
 							    nsim_dev->ddir);
-	if (IS_ERR_OR_NULL(nsim_dev->ddir_bpf_bound_progs))
-		return -ENOMEM;
+	if (IS_ERR(nsim_dev->ddir_bpf_bound_progs))
+		return PTR_ERR(nsim_dev->ddir_bpf_bound_progs);
 
 	nsim_dev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, nsim_dev);
 	err = PTR_ERR_OR_ZERO(nsim_dev->bpf_dev);
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index 6aeed0c600f8..7971dc4f54f1 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -17,6 +17,7 @@
 static DEFINE_IDA(nsim_bus_dev_ids);
 static LIST_HEAD(nsim_bus_dev_list);
 static DEFINE_MUTEX(nsim_bus_dev_list_lock);
+static bool nsim_bus_enable;
 
 static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev)
 {
@@ -28,7 +29,7 @@ static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev,
 {
 	nsim_bus_dev->vfconfigs = kcalloc(num_vfs,
 					  sizeof(struct nsim_vf_config),
-					  GFP_KERNEL);
+					  GFP_KERNEL | __GFP_NOWARN);
 	if (!nsim_bus_dev->vfconfigs)
 		return -ENOMEM;
 	nsim_bus_dev->num_vfs = num_vfs;
@@ -96,13 +97,25 @@ new_port_store(struct device *dev, struct device_attribute *attr,
 	       const char *buf, size_t count)
 {
 	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+	struct nsim_dev *nsim_dev = dev_get_drvdata(dev);
+	struct devlink *devlink;
 	unsigned int port_index;
 	int ret;
 
+	/* Prevent to use nsim_bus_dev before initialization. */
+	if (!smp_load_acquire(&nsim_bus_dev->init))
+		return -EBUSY;
 	ret = kstrtouint(buf, 0, &port_index);
 	if (ret)
 		return ret;
+
+	devlink = priv_to_devlink(nsim_dev);
+
+	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
+	devlink_reload_disable(devlink);
 	ret = nsim_dev_port_add(nsim_bus_dev, port_index);
+	devlink_reload_enable(devlink);
+	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return ret ? ret : count;
 }
 
@@ -113,13 +126,25 @@ del_port_store(struct device *dev, struct device_attribute *attr,
 	       const char *buf, size_t count)
 {
 	struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev);
+	struct nsim_dev *nsim_dev = dev_get_drvdata(dev);
+	struct devlink *devlink;
 	unsigned int port_index;
 	int ret;
 
+	/* Prevent to use nsim_bus_dev before initialization. */
+	if (!smp_load_acquire(&nsim_bus_dev->init))
+		return -EBUSY;
 	ret = kstrtouint(buf, 0, &port_index);
 	if (ret)
 		return ret;
+
+	devlink = priv_to_devlink(nsim_dev);
+
+	mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock);
+	devlink_reload_disable(devlink);
 	ret = nsim_dev_port_del(nsim_bus_dev, port_index);
+	devlink_reload_enable(devlink);
+	mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock);
 	return ret ? ret : count;
 }
 
@@ -179,15 +204,30 @@ new_device_store(struct bus_type *bus, const char *buf, size_t count)
 		pr_err("Format for adding new device is \"id port_count\" (uint uint).\n");
 		return -EINVAL;
 	}
-	nsim_bus_dev = nsim_bus_dev_new(id, port_count);
-	if (IS_ERR(nsim_bus_dev))
-		return PTR_ERR(nsim_bus_dev);
 
 	mutex_lock(&nsim_bus_dev_list_lock);
+	/* Prevent to use resource before initialization. */
+	if (!smp_load_acquire(&nsim_bus_enable)) {
+		err = -EBUSY;
+		goto err;
+	}
+
+	nsim_bus_dev = nsim_bus_dev_new(id, port_count);
+	if (IS_ERR(nsim_bus_dev)) {
+		err = PTR_ERR(nsim_bus_dev);
+		goto err;
+	}
+
+	/* Allow using nsim_bus_dev */
+	smp_store_release(&nsim_bus_dev->init, true);
+
 	list_add_tail(&nsim_bus_dev->list, &nsim_bus_dev_list);
 	mutex_unlock(&nsim_bus_dev_list_lock);
 
 	return count;
+err:
+	mutex_unlock(&nsim_bus_dev_list_lock);
+	return err;
 }
 static BUS_ATTR_WO(new_device);
 
@@ -215,6 +255,11 @@ del_device_store(struct bus_type *bus, const char *buf, size_t count)
 
 	err = -ENOENT;
 	mutex_lock(&nsim_bus_dev_list_lock);
+	/* Prevent to use resource before initialization. */
+	if (!smp_load_acquire(&nsim_bus_enable)) {
+		mutex_unlock(&nsim_bus_dev_list_lock);
+		return -EBUSY;
+	}
 	list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) {
 		if (nsim_bus_dev->dev.id != id)
 			continue;
@@ -284,6 +329,9 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count)
 	nsim_bus_dev->dev.type = &nsim_bus_dev_type;
 	nsim_bus_dev->port_count = port_count;
 	nsim_bus_dev->initial_net = current->nsproxy->net_ns;
+	mutex_init(&nsim_bus_dev->nsim_bus_reload_lock);
+	/* Disallow using nsim_bus_dev */
+	smp_store_release(&nsim_bus_dev->init, false);
 
 	err = device_register(&nsim_bus_dev->dev);
 	if (err)
@@ -299,6 +347,8 @@ err_nsim_bus_dev_free:
 
 static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev)
 {
+	/* Disallow using nsim_bus_dev */
+	smp_store_release(&nsim_bus_dev->init, false);
 	device_unregister(&nsim_bus_dev->dev);
 	ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
 	kfree(nsim_bus_dev);
@@ -320,6 +370,8 @@ int nsim_bus_init(void)
 	err = driver_register(&nsim_driver);
 	if (err)
 		goto err_bus_unregister;
+	/* Allow using resources */
+	smp_store_release(&nsim_bus_enable, true);
 	return 0;
 
 err_bus_unregister:
@@ -331,12 +383,16 @@ void nsim_bus_exit(void)
 {
 	struct nsim_bus_dev *nsim_bus_dev, *tmp;
 
+	/* Disallow using resources */
+	smp_store_release(&nsim_bus_enable, false);
+
 	mutex_lock(&nsim_bus_dev_list_lock);
 	list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) {
 		list_del(&nsim_bus_dev->list);
 		nsim_bus_dev_del(nsim_bus_dev);
 	}
 	mutex_unlock(&nsim_bus_dev_list_lock);
+
 	driver_unregister(&nsim_driver);
 	bus_unregister(&nsim_bus);
 }
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index b53fbc06e104..5c5427c840b6 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -73,23 +73,26 @@ static const struct file_operations nsim_dev_take_snapshot_fops = {
 
 static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
 {
-	char dev_ddir_name[16];
+	char dev_ddir_name[sizeof(DRV_NAME) + 10];
 
 	sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id);
 	nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir);
-	if (IS_ERR_OR_NULL(nsim_dev->ddir))
-		return PTR_ERR_OR_ZERO(nsim_dev->ddir) ?: -EINVAL;
+	if (IS_ERR(nsim_dev->ddir))
+		return PTR_ERR(nsim_dev->ddir);
 	nsim_dev->ports_ddir = debugfs_create_dir("ports", nsim_dev->ddir);
-	if (IS_ERR_OR_NULL(nsim_dev->ports_ddir))
-		return PTR_ERR_OR_ZERO(nsim_dev->ports_ddir) ?: -EINVAL;
+	if (IS_ERR(nsim_dev->ports_ddir))
+		return PTR_ERR(nsim_dev->ports_ddir);
 	debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir,
 			    &nsim_dev->fw_update_status);
 	debugfs_create_u32("max_macs", 0600, nsim_dev->ddir,
 			   &nsim_dev->max_macs);
 	debugfs_create_bool("test1", 0600, nsim_dev->ddir,
 			    &nsim_dev->test1);
-	debugfs_create_file("take_snapshot", 0200, nsim_dev->ddir, nsim_dev,
-			    &nsim_dev_take_snapshot_fops);
+	nsim_dev->take_snapshot = debugfs_create_file("take_snapshot",
+						      0200,
+						      nsim_dev->ddir,
+						      nsim_dev,
+						&nsim_dev_take_snapshot_fops);
 	debugfs_create_bool("dont_allow_reload", 0600, nsim_dev->ddir,
 			    &nsim_dev->dont_allow_reload);
 	debugfs_create_bool("fail_reload", 0600, nsim_dev->ddir,
@@ -112,8 +115,8 @@ static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev,
 	sprintf(port_ddir_name, "%u", nsim_dev_port->port_index);
 	nsim_dev_port->ddir = debugfs_create_dir(port_ddir_name,
 						 nsim_dev->ports_ddir);
-	if (IS_ERR_OR_NULL(nsim_dev_port->ddir))
-		return -ENOMEM;
+	if (IS_ERR(nsim_dev_port->ddir))
+		return PTR_ERR(nsim_dev_port->ddir);
 
 	sprintf(dev_link_name, "../../../" DRV_NAME "%u",
 		nsim_dev->nsim_bus_dev->dev.id);
@@ -740,6 +743,11 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev,
 	if (err)
 		goto err_health_exit;
 
+	nsim_dev->take_snapshot = debugfs_create_file("take_snapshot",
+						      0200,
+						      nsim_dev->ddir,
+						      nsim_dev,
+						&nsim_dev_take_snapshot_fops);
 	return 0;
 
 err_health_exit:
@@ -853,6 +861,7 @@ static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev)
 
 	if (devlink_is_reload_failed(devlink))
 		return;
+	debugfs_remove(nsim_dev->take_snapshot);
 	nsim_dev_port_del_all(nsim_dev);
 	nsim_dev_health_exit(nsim_dev);
 	nsim_dev_traps_exit(devlink);
@@ -925,8 +934,8 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
 int nsim_dev_init(void)
 {
 	nsim_dev_ddir = debugfs_create_dir(DRV_NAME, NULL);
-	if (IS_ERR_OR_NULL(nsim_dev_ddir))
-		return -ENOMEM;
+	if (IS_ERR(nsim_dev_ddir))
+		return PTR_ERR(nsim_dev_ddir);
 	return 0;
 }
 
diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c
index 9aa637d162eb..ba8d9ad60feb 100644
--- a/drivers/net/netdevsim/health.c
+++ b/drivers/net/netdevsim/health.c
@@ -82,7 +82,7 @@ static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len)
 	if (err)
 		return err;
 
-	binary = kmalloc(binary_len, GFP_KERNEL);
+	binary = kmalloc(binary_len, GFP_KERNEL | __GFP_NOWARN);
 	if (!binary)
 		return -ENOMEM;
 	get_random_bytes(binary, binary_len);
@@ -285,8 +285,8 @@ int nsim_dev_health_init(struct nsim_dev *nsim_dev, struct devlink *devlink)
 	}
 
 	health->ddir = debugfs_create_dir("health", nsim_dev->ddir);
-	if (IS_ERR_OR_NULL(health->ddir)) {
-		err = PTR_ERR_OR_ZERO(health->ddir) ?: -EINVAL;
+	if (IS_ERR(health->ddir)) {
+		err = PTR_ERR(health->ddir);
 		goto err_dummy_reporter_destroy;
 	}
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 94df795ef4d3..2eb7b0dc1594 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -160,6 +160,7 @@ struct nsim_dev {
 	struct nsim_trap_data *trap_data;
 	struct dentry *ddir;
 	struct dentry *ports_ddir;
+	struct dentry *take_snapshot;
 	struct bpf_offload_dev *bpf_dev;
 	bool bpf_bind_accept;
 	u32 bpf_bind_verifier_delay;
@@ -240,6 +241,9 @@ struct nsim_bus_dev {
 				  */
 	unsigned int num_vfs;
 	struct nsim_vf_config *vfconfigs;
+	/* Lock for devlink->reload_enabled in netdevsim module */
+	struct mutex nsim_bus_reload_lock;
+	bool init;
 };
 
 int nsim_bus_init(void);
diff --git a/drivers/net/netdevsim/sdev.c b/drivers/net/netdevsim/sdev.c
deleted file mode 100644
index 6712da3340d6..000000000000
--- a/drivers/net/netdevsim/sdev.c
+++ /dev/null
@@ -1,69 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */
-
-#include <linux/debugfs.h>
-#include <linux/err.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-
-#include "netdevsim.h"
-
-static struct dentry *nsim_sdev_ddir;
-
-static u32 nsim_sdev_id;
-
-struct netdevsim_shared_dev *nsim_sdev_get(struct netdevsim *joinns)
-{
-	struct netdevsim_shared_dev *sdev;
-	char sdev_ddir_name[10];
-	int err;
-
-	if (joinns) {
-		if (WARN_ON(!joinns->sdev))
-			return ERR_PTR(-EINVAL);
-		sdev = joinns->sdev;
-		sdev->refcnt++;
-		return sdev;
-	}
-
-	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
-	if (!sdev)
-		return ERR_PTR(-ENOMEM);
-	sdev->refcnt = 1;
-	sdev->switch_id = nsim_sdev_id++;
-
-	sprintf(sdev_ddir_name, "%u", sdev->switch_id);
-	sdev->ddir = debugfs_create_dir(sdev_ddir_name, nsim_sdev_ddir);
-	if (IS_ERR_OR_NULL(sdev->ddir)) {
-		err = PTR_ERR_OR_ZERO(sdev->ddir) ?: -EINVAL;
-		goto err_sdev_free;
-	}
-
-	return sdev;
-
-err_sdev_free:
-	nsim_sdev_id--;
-	kfree(sdev);
-	return ERR_PTR(err);
-}
-
-void nsim_sdev_put(struct netdevsim_shared_dev *sdev)
-{
-	if (--sdev->refcnt)
-		return;
-	debugfs_remove_recursive(sdev->ddir);
-	kfree(sdev);
-}
-
-int nsim_sdev_init(void)
-{
-	nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
-	if (IS_ERR_OR_NULL(nsim_sdev_ddir))
-		return -ENOMEM;
-	return 0;
-}
-
-void nsim_sdev_exit(void)
-{
-	debugfs_remove_recursive(nsim_sdev_ddir);
-}
diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index aee62610bade..481cf48c9b9e 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -489,6 +489,14 @@ static int at803x_probe(struct phy_device *phydev)
 	return at803x_parse_dt(phydev);
 }
 
+static void at803x_remove(struct phy_device *phydev)
+{
+	struct at803x_priv *priv = phydev->priv;
+
+	if (priv->vddio)
+		regulator_disable(priv->vddio);
+}
+
 static int at803x_clk_out_config(struct phy_device *phydev)
 {
 	struct at803x_priv *priv = phydev->priv;
@@ -711,6 +719,7 @@ static struct phy_driver at803x_driver[] = {
 	.name			= "Qualcomm Atheros AR8035",
 	.phy_id_mask		= AT803X_PHY_ID_MASK,
 	.probe			= at803x_probe,
+	.remove			= at803x_remove,
 	.config_init		= at803x_config_init,
 	.set_wol		= at803x_set_wol,
 	.get_wol		= at803x_get_wol,
@@ -726,6 +735,7 @@ static struct phy_driver at803x_driver[] = {
 	.name			= "Qualcomm Atheros AR8030",
 	.phy_id_mask		= AT803X_PHY_ID_MASK,
 	.probe			= at803x_probe,
+	.remove			= at803x_remove,
 	.config_init		= at803x_config_init,
 	.link_change_notify	= at803x_link_change_notify,
 	.set_wol		= at803x_set_wol,
@@ -741,6 +751,7 @@ static struct phy_driver at803x_driver[] = {
 	.name			= "Qualcomm Atheros AR8031/AR8033",
 	.phy_id_mask		= AT803X_PHY_ID_MASK,
 	.probe			= at803x_probe,
+	.remove			= at803x_remove,
 	.config_init		= at803x_config_init,
 	.set_wol		= at803x_set_wol,
 	.get_wol		= at803x_get_wol,
diff --git a/drivers/net/phy/mdio-mux-meson-g12a.c b/drivers/net/phy/mdio-mux-meson-g12a.c
index 7a9ad54582e1..bf86c9c7a288 100644
--- a/drivers/net/phy/mdio-mux-meson-g12a.c
+++ b/drivers/net/phy/mdio-mux-meson-g12a.c
@@ -123,7 +123,7 @@ static int g12a_ephy_pll_is_enabled(struct clk_hw *hw)
 	return (val & PLL_CTL0_LOCK_DIG) ? 1 : 0;
 }
 
-static void g12a_ephy_pll_init(struct clk_hw *hw)
+static int g12a_ephy_pll_init(struct clk_hw *hw)
 {
 	struct g12a_ephy_pll *pll = g12a_ephy_pll_to_dev(hw);
 
@@ -136,6 +136,8 @@ static void g12a_ephy_pll_init(struct clk_hw *hw)
 	writel(0x20200000, pll->base + ETH_PLL_CTL5);
 	writel(0x0000c002, pll->base + ETH_PLL_CTL6);
 	writel(0x00000023, pll->base + ETH_PLL_CTL7);
+
+	return 0;
 }
 
 static const struct clk_ops g12a_ephy_pll_ops = {
diff --git a/drivers/net/phy/mii_timestamper.c b/drivers/net/phy/mii_timestamper.c
index 2f12c5d901df..b71b7456462d 100644
--- a/drivers/net/phy/mii_timestamper.c
+++ b/drivers/net/phy/mii_timestamper.c
@@ -111,6 +111,13 @@ void unregister_mii_timestamper(struct mii_timestamper *mii_ts)
 	struct mii_timestamping_desc *desc;
 	struct list_head *this;
 
+	/* mii_timestamper statically registered by the PHY driver won't use the
+	 * register_mii_timestamper() and thus don't have ->device set. Don't
+	 * try to unregister these.
+	 */
+	if (!mii_ts->device)
+		return;
+
 	mutex_lock(&tstamping_devices_lock);
 	list_for_each(this, &mii_timestamping_devices) {
 		desc = list_entry(this, struct mii_timestamping_desc, list);
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index e8cd8c05b156..78ddbaf6401b 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -698,6 +698,9 @@ enum rtl8152_flags {
 #define VENDOR_ID_NVIDIA		0x0955
 #define VENDOR_ID_TPLINK		0x2357
 
+#define DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2	0x3082
+#define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2		0xa387
+
 #define MCU_TYPE_PLA			0x0100
 #define MCU_TYPE_USB			0x0000
 
@@ -6759,9 +6762,13 @@ static int rtl8152_probe(struct usb_interface *intf,
 		netdev->hw_features &= ~NETIF_F_RXCSUM;
 	}
 
-	if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO &&
-	    le16_to_cpu(udev->descriptor.idProduct) == 0x3082)
-		set_bit(LENOVO_MACPASSTHRU, &tp->flags);
+	if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) {
+		switch (le16_to_cpu(udev->descriptor.idProduct)) {
+		case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2:
+		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
+			set_bit(LENOVO_MACPASSTHRU, &tp->flags);
+		}
+	}
 
 	if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial &&
 	    (!strcmp(udev->serial, "000001000000") ||
diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index c4c8f1b62e1e..8363f91df7ea 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -4420,73 +4420,65 @@ static int proc_BSSList_open( struct inode *inode, struct file *file );
 static int proc_config_open( struct inode *inode, struct file *file );
 static int proc_wepkey_open( struct inode *inode, struct file *file );
 
-static const struct file_operations proc_statsdelta_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.open		= proc_statsdelta_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_statsdelta_ops = {
+	.proc_read	= proc_read,
+	.proc_open	= proc_statsdelta_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_stats_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.open		= proc_stats_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_stats_ops = {
+	.proc_read	= proc_read,
+	.proc_open	= proc_stats_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_status_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.open		= proc_status_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_status_ops = {
+	.proc_read	= proc_read,
+	.proc_open	= proc_status_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_SSID_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.write		= proc_write,
-	.open		= proc_SSID_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_SSID_ops = {
+	.proc_read	= proc_read,
+	.proc_write	= proc_write,
+	.proc_open	= proc_SSID_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_BSSList_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.write		= proc_write,
-	.open		= proc_BSSList_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_BSSList_ops = {
+	.proc_read	= proc_read,
+	.proc_write	= proc_write,
+	.proc_open	= proc_BSSList_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_APList_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.write		= proc_write,
-	.open		= proc_APList_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_APList_ops = {
+	.proc_read	= proc_read,
+	.proc_write	= proc_write,
+	.proc_open	= proc_APList_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_config_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.write		= proc_write,
-	.open		= proc_config_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_config_ops = {
+	.proc_read	= proc_read,
+	.proc_write	= proc_write,
+	.proc_open	= proc_config_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
-static const struct file_operations proc_wepkey_ops = {
-	.owner		= THIS_MODULE,
-	.read		= proc_read,
-	.write		= proc_write,
-	.open		= proc_wepkey_open,
-	.release	= proc_close,
-	.llseek		= default_llseek,
+static const struct proc_ops proc_wepkey_ops = {
+	.proc_read	= proc_read,
+	.proc_write	= proc_write,
+	.proc_open	= proc_wepkey_open,
+	.proc_release	= proc_close,
+	.proc_lseek	= default_llseek,
 };
 
 static struct proc_dir_entry *airo_entry;
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_module.c b/drivers/net/wireless/intel/ipw2x00/libipw_module.c
index 436b819aeb36..43bab92a4148 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_module.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_module.c
@@ -240,13 +240,12 @@ static ssize_t debug_level_proc_write(struct file *file,
 	return strnlen(buf, len);
 }
 
-static const struct file_operations debug_level_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= debug_level_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= debug_level_proc_write,
+static const struct proc_ops debug_level_proc_ops = {
+	.proc_open	= debug_level_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= debug_level_proc_write,
 };
 #endif				/* CONFIG_LIBIPW_DEBUG */
 
@@ -263,7 +262,7 @@ static int __init libipw_init(void)
 		return -EIO;
 	}
 	e = proc_create("debug_level", 0644, libipw_proc,
-			&debug_level_proc_fops);
+			&debug_level_proc_ops);
 	if (!e) {
 		remove_proc_entry(DRV_PROCNAME, init_net.proc_net);
 		libipw_proc = NULL;
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index d1e17589dbeb..da6d4202611c 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -27,6 +27,7 @@
 #include <linux/firmware.h>
 #include <linux/etherdevice.h>
 #include <linux/if_arp.h>
+#include <linux/units.h>
 
 #include <net/mac80211.h>
 
@@ -6468,7 +6469,7 @@ il4965_set_hw_params(struct il_priv *il)
 	il->hw_params.valid_rx_ant = il->cfg->valid_rx_ant;
 
 	il->hw_params.ct_kill_threshold =
-	   CELSIUS_TO_KELVIN(CT_KILL_THRESHOLD_LEGACY);
+	   celsius_to_kelvin(CT_KILL_THRESHOLD_LEGACY);
 
 	il->hw_params.sens = &il4965_sensitivity;
 	il->hw_params.beacon_time_tsf_bits = IL4965_EXT_BEACON_TIME_POS;
diff --git a/drivers/net/wireless/intel/iwlegacy/4965.c b/drivers/net/wireless/intel/iwlegacy/4965.c
index 32699b6a68c2..34d0579132ce 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <linux/units.h>
 #include <net/mac80211.h>
 #include <linux/etherdevice.h>
 #include <asm/unaligned.h>
@@ -1104,7 +1105,7 @@ il4965_fill_txpower_tbl(struct il_priv *il, u8 band, u16 channel, u8 is_ht40,
 	/* get current temperature (Celsius) */
 	current_temp = max(il->temperature, IL_TX_POWER_TEMPERATURE_MIN);
 	current_temp = min(il->temperature, IL_TX_POWER_TEMPERATURE_MAX);
-	current_temp = KELVIN_TO_CELSIUS(current_temp);
+	current_temp = kelvin_to_celsius(current_temp);
 
 	/* select thermal txpower adjustment params, based on channel group
 	 *   (same frequency group used for mimo txatten adjustment) */
@@ -1610,8 +1611,8 @@ il4965_hw_get_temperature(struct il_priv *il)
 	temperature =
 	    (temperature * 97) / 100 + TEMPERATURE_CALIB_KELVIN_OFFSET;
 
-	D_TEMP("Calibrated temperature: %dK, %dC\n", temperature,
-	       KELVIN_TO_CELSIUS(temperature));
+	D_TEMP("Calibrated temperature: %dK, %ldC\n", temperature,
+	       kelvin_to_celsius(temperature));
 
 	return temperature;
 }
@@ -1670,12 +1671,12 @@ il4965_temperature_calib(struct il_priv *il)
 
 	if (il->temperature != temp) {
 		if (il->temperature)
-			D_TEMP("Temperature changed " "from %dC to %dC\n",
-			       KELVIN_TO_CELSIUS(il->temperature),
-			       KELVIN_TO_CELSIUS(temp));
+			D_TEMP("Temperature changed " "from %ldC to %ldC\n",
+			       kelvin_to_celsius(il->temperature),
+			       kelvin_to_celsius(temp));
 		else
-			D_TEMP("Temperature " "initialized to %dC\n",
-			       KELVIN_TO_CELSIUS(temp));
+			D_TEMP("Temperature " "initialized to %ldC\n",
+			       kelvin_to_celsius(temp));
 	}
 
 	il->temperature = temp;
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index e7fb8e6bb9e7..bc9cd7e5ccb8 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -779,9 +779,6 @@ struct il_sensitivity_ranges {
 	u16 nrg_th_cca;
 };
 
-#define KELVIN_TO_CELSIUS(x) ((x)-273)
-#define CELSIUS_TO_KELVIN(x) ((x)+273)
-
 /**
  * struct il_hw_params
  * @bcast_id: f/w broadcast station ID
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
index be5ef4c3e9d0..8d8380026180 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
@@ -237,11 +237,6 @@ struct iwl_sensitivity_ranges {
 	u16 nrg_th_cca;
 };
 
-
-#define KELVIN_TO_CELSIUS(x) ((x)-273)
-#define CELSIUS_TO_KELVIN(x) ((x)+273)
-
-
 /******************************************************************************
  *
  * Functions implemented in core module which are forward declared here
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
index dc3f197f94d9..d42bc46fe566 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/devices.c
@@ -10,6 +10,8 @@
  *
  *****************************************************************************/
 
+#include <linux/units.h>
+
 /*
  * DVM device-specific data & functions
  */
@@ -345,7 +347,7 @@ static s32 iwl_temp_calib_to_offset(struct iwl_priv *priv)
 static void iwl5150_set_ct_threshold(struct iwl_priv *priv)
 {
 	const s32 volt2temp_coef = IWL_5150_VOLTAGE_TO_TEMPERATURE_COEFF;
-	s32 threshold = (s32)CELSIUS_TO_KELVIN(CT_KILL_THRESHOLD_LEGACY) -
+	s32 threshold = (s32)celsius_to_kelvin(CT_KILL_THRESHOLD_LEGACY) -
 			iwl_temp_calib_to_offset(priv);
 
 	priv->hw_params.ct_kill_threshold = threshold * volt2temp_coef;
@@ -381,7 +383,7 @@ static void iwl5150_temperature(struct iwl_priv *priv)
 	vt = le32_to_cpu(priv->statistics.common.temperature);
 	vt = vt / IWL_5150_VOLTAGE_TO_TEMPERATURE_COEFF + offset;
 	/* now vt hold the temperature in Kelvin */
-	priv->temperature = KELVIN_TO_CELSIUS(vt);
+	priv->temperature = kelvin_to_celsius(vt);
 	iwl_tt_handler(priv);
 }
 
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index e323e9a5999f..58212c532c90 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -126,7 +126,7 @@ static void prism2_check_sta_fw_version(local_info_t *local);
 
 #ifdef PRISM2_DOWNLOAD_SUPPORT
 /* hostap_download.c */
-static const struct file_operations prism2_download_aux_dump_proc_fops;
+static const struct proc_ops prism2_download_aux_dump_proc_ops;
 static u8 * prism2_read_pda(struct net_device *dev);
 static int prism2_download(local_info_t *local,
 			   struct prism2_download_param *param);
@@ -3094,7 +3094,7 @@ prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx,
 	local->func->reset_port = prism2_reset_port;
 	local->func->schedule_reset = prism2_schedule_reset;
 #ifdef PRISM2_DOWNLOAD_SUPPORT
-	local->func->read_aux_fops = &prism2_download_aux_dump_proc_fops;
+	local->func->read_aux_proc_ops = &prism2_download_aux_dump_proc_ops;
 	local->func->download = prism2_download;
 #endif /* PRISM2_DOWNLOAD_SUPPORT */
 	local->func->tx = prism2_tx_80211;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c
index 6151d8db5924..a2ee4693eaed 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_proc.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c
@@ -211,9 +211,9 @@ static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf,
 	return count;
 }
 
-static const struct file_operations prism2_pda_proc_fops = {
-	.read		= prism2_pda_proc_read,
-	.llseek		= generic_file_llseek,
+static const struct proc_ops prism2_pda_proc_ops = {
+	.proc_read	= prism2_pda_proc_read,
+	.proc_lseek	= generic_file_llseek,
 };
 
 
@@ -223,8 +223,8 @@ static ssize_t prism2_aux_dump_proc_no_read(struct file *file, char __user *buf,
 	return 0;
 }
 
-static const struct file_operations prism2_aux_dump_proc_fops = {
-	.read		= prism2_aux_dump_proc_no_read,
+static const struct proc_ops prism2_aux_dump_proc_ops = {
+	.proc_read	= prism2_aux_dump_proc_no_read,
 };
 
 
@@ -379,9 +379,9 @@ void hostap_init_proc(local_info_t *local)
 	proc_create_seq_data("wds", 0, local->proc,
 			&prism2_wds_proc_seqops, local);
 	proc_create_data("pda", 0, local->proc,
-			 &prism2_pda_proc_fops, local);
+			 &prism2_pda_proc_ops, local);
 	proc_create_data("aux_dump", 0, local->proc,
-			 local->func->read_aux_fops ?: &prism2_aux_dump_proc_fops,
+			 local->func->read_aux_proc_ops ?: &prism2_aux_dump_proc_ops,
 			 local);
 	proc_create_seq_data("bss_list", 0, local->proc,
 			&prism2_bss_list_proc_seqops, local);
diff --git a/drivers/net/wireless/intersil/hostap/hostap_wlan.h b/drivers/net/wireless/intersil/hostap/hostap_wlan.h
index a8c4c1a8b29d..487883fbb58c 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_wlan.h
+++ b/drivers/net/wireless/intersil/hostap/hostap_wlan.h
@@ -599,7 +599,7 @@ struct prism2_helper_functions {
 			struct prism2_download_param *param);
 	int (*tx)(struct sk_buff *skb, struct net_device *dev);
 	int (*set_tim)(struct net_device *dev, int aid, int set);
-	const struct file_operations *read_aux_fops;
+	const struct proc_ops *read_aux_proc_ops;
 
 	int need_tx_headroom; /* number of bytes of headroom needed before
 			       * IEEE 802.11 header */
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index cf372684b681..c1d542bfa530 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -2717,10 +2717,9 @@ static ssize_t ray_cs_essid_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations ray_cs_essid_proc_fops = {
-	.owner		= THIS_MODULE,
-	.write		= ray_cs_essid_proc_write,
-	.llseek		= noop_llseek,
+static const struct proc_ops ray_cs_essid_proc_ops = {
+	.proc_write	= ray_cs_essid_proc_write,
+	.proc_lseek	= noop_llseek,
 };
 
 static ssize_t int_proc_write(struct file *file, const char __user *buffer,
@@ -2751,10 +2750,9 @@ static ssize_t int_proc_write(struct file *file, const char __user *buffer,
 	return count;
 }
 
-static const struct file_operations int_proc_fops = {
-	.owner		= THIS_MODULE,
-	.write		= int_proc_write,
-	.llseek		= noop_llseek,
+static const struct proc_ops int_proc_ops = {
+	.proc_write	= int_proc_write,
+	.proc_lseek	= noop_llseek,
 };
 #endif
 
@@ -2790,10 +2788,10 @@ static int __init init_ray_cs(void)
 	proc_mkdir("driver/ray_cs", NULL);
 
 	proc_create_single("driver/ray_cs/ray_cs", 0, NULL, ray_cs_proc_show);
-	proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_fops);
-	proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_fops,
+	proc_create("driver/ray_cs/essid", 0200, NULL, &ray_cs_essid_proc_ops);
+	proc_create_data("driver/ray_cs/net_type", 0200, NULL, &int_proc_ops,
 			 &net_type);
-	proc_create_data("driver/ray_cs/translate", 0200, NULL, &int_proc_fops,
+	proc_create_data("driver/ray_cs/translate", 0200, NULL, &int_proc_ops,
 			 &translate);
 #endif
 	if (translate != 0)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index ad8e4df1282b..4eae441f86c9 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -337,13 +337,7 @@ static void pmem_release_disk(void *__pmem)
 	put_disk(pmem->disk);
 }
 
-static void pmem_pagemap_page_free(struct page *page)
-{
-	wake_up_var(&page->_refcount);
-}
-
 static const struct dev_pagemap_ops fsdax_pagemap_ops = {
-	.page_free		= pmem_pagemap_page_free,
 	.kill			= pmem_pagemap_kill,
 	.cleanup		= pmem_pagemap_cleanup,
 };
diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c
index a5af21f5d370..2e6477ed420f 100644
--- a/drivers/nvme/host/hwmon.c
+++ b/drivers/nvme/host/hwmon.c
@@ -5,14 +5,11 @@
  */
 
 #include <linux/hwmon.h>
+#include <linux/units.h>
 #include <asm/unaligned.h>
 
 #include "nvme.h"
 
-/* These macros should be moved to linux/temperature.h */
-#define MILLICELSIUS_TO_KELVIN(t) DIV_ROUND_CLOSEST((t) + 273150, 1000)
-#define KELVIN_TO_MILLICELSIUS(t) ((t) * 1000L - 273150)
-
 struct nvme_hwmon_data {
 	struct nvme_ctrl *ctrl;
 	struct nvme_smart_log log;
@@ -35,7 +32,7 @@ static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
 		return -EIO;
 	if (ret < 0)
 		return ret;
-	*temp = KELVIN_TO_MILLICELSIUS(status & NVME_TEMP_THRESH_MASK);
+	*temp = kelvin_to_millicelsius(status & NVME_TEMP_THRESH_MASK);
 
 	return 0;
 }
@@ -46,7 +43,7 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
 	unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
 	int ret;
 
-	temp = MILLICELSIUS_TO_KELVIN(temp);
+	temp = millicelsius_to_kelvin(temp);
 	threshold |= clamp_val(temp, 0, NVME_TEMP_THRESH_MASK);
 
 	if (under)
@@ -88,7 +85,7 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 	case hwmon_temp_min:
 		return nvme_get_temp_thresh(data->ctrl, channel, true, val);
 	case hwmon_temp_crit:
-		*val = KELVIN_TO_MILLICELSIUS(data->ctrl->cctemp);
+		*val = kelvin_to_millicelsius(data->ctrl->cctemp);
 		return 0;
 	default:
 		break;
@@ -105,7 +102,7 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
 			temp = get_unaligned_le16(log->temperature);
 		else
 			temp = le16_to_cpu(log->temp_sensor[channel - 1]);
-		*val = KELVIN_TO_MILLICELSIUS(temp);
+		*val = kelvin_to_millicelsius(temp);
 		break;
 	case hwmon_temp_alarm:
 		*val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 37c2ccbefecd..d91618641be6 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -103,4 +103,8 @@ config OF_OVERLAY
 config OF_NUMA
 	bool
 
+config OF_DMA_DEFAULT_COHERENT
+	# arches should select this if DMA is coherent by default for OF devices
+	bool
+
 endif # OF
diff --git a/drivers/of/address.c b/drivers/of/address.c
index 99c1b8058559..e8a39c3ec4d4 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -995,12 +995,16 @@ out:
  * @np:	device node
  *
  * It returns true if "dma-coherent" property was found
- * for this device in DT.
+ * for this device in the DT, or if DMA is coherent by
+ * default for OF devices on the current platform.
  */
 bool of_dma_is_coherent(struct device_node *np)
 {
 	struct device_node *node = of_node_get(np);
 
+	if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT))
+		return true;
+
 	while (node) {
 		if (of_property_read_bool(node, "dma-coherent")) {
 			of_node_put(node);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index db7fbc0c0893..8d173fb3552a 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -135,115 +135,38 @@ int __weak of_node_to_nid(struct device_node *np)
 }
 #endif
 
-/*
- * Assumptions behind phandle_cache implementation:
- *   - phandle property values are in a contiguous range of 1..n
- *
- * If the assumptions do not hold, then
- *   - the phandle lookup overhead reduction provided by the cache
- *     will likely be less
- */
+#define OF_PHANDLE_CACHE_BITS	7
+#define OF_PHANDLE_CACHE_SZ	BIT(OF_PHANDLE_CACHE_BITS)
 
-static struct device_node **phandle_cache;
-static u32 phandle_cache_mask;
+static struct device_node *phandle_cache[OF_PHANDLE_CACHE_SZ];
 
-/*
- * Caller must hold devtree_lock.
- */
-static void __of_free_phandle_cache(void)
+static u32 of_phandle_cache_hash(phandle handle)
 {
-	u32 cache_entries = phandle_cache_mask + 1;
-	u32 k;
-
-	if (!phandle_cache)
-		return;
-
-	for (k = 0; k < cache_entries; k++)
-		of_node_put(phandle_cache[k]);
-
-	kfree(phandle_cache);
-	phandle_cache = NULL;
+	return hash_32(handle, OF_PHANDLE_CACHE_BITS);
 }
 
-int of_free_phandle_cache(void)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&devtree_lock, flags);
-
-	__of_free_phandle_cache();
-
-	raw_spin_unlock_irqrestore(&devtree_lock, flags);
-
-	return 0;
-}
-#if !defined(CONFIG_MODULES)
-late_initcall_sync(of_free_phandle_cache);
-#endif
-
 /*
  * Caller must hold devtree_lock.
  */
-void __of_free_phandle_cache_entry(phandle handle)
+void __of_phandle_cache_inv_entry(phandle handle)
 {
-	phandle masked_handle;
+	u32 handle_hash;
 	struct device_node *np;
 
 	if (!handle)
 		return;
 
-	masked_handle = handle & phandle_cache_mask;
-
-	if (phandle_cache) {
-		np = phandle_cache[masked_handle];
-		if (np && handle == np->phandle) {
-			of_node_put(np);
-			phandle_cache[masked_handle] = NULL;
-		}
-	}
-}
-
-void of_populate_phandle_cache(void)
-{
-	unsigned long flags;
-	u32 cache_entries;
-	struct device_node *np;
-	u32 phandles = 0;
-
-	raw_spin_lock_irqsave(&devtree_lock, flags);
-
-	__of_free_phandle_cache();
-
-	for_each_of_allnodes(np)
-		if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL)
-			phandles++;
-
-	if (!phandles)
-		goto out;
+	handle_hash = of_phandle_cache_hash(handle);
 
-	cache_entries = roundup_pow_of_two(phandles);
-	phandle_cache_mask = cache_entries - 1;
-
-	phandle_cache = kcalloc(cache_entries, sizeof(*phandle_cache),
-				GFP_ATOMIC);
-	if (!phandle_cache)
-		goto out;
-
-	for_each_of_allnodes(np)
-		if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) {
-			of_node_get(np);
-			phandle_cache[np->phandle & phandle_cache_mask] = np;
-		}
-
-out:
-	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+	np = phandle_cache[handle_hash];
+	if (np && handle == np->phandle)
+		phandle_cache[handle_hash] = NULL;
 }
 
 void __init of_core_init(void)
 {
 	struct device_node *np;
 
-	of_populate_phandle_cache();
 
 	/* Create the kset, and register existing nodes */
 	mutex_lock(&of_mutex);
@@ -253,8 +176,11 @@ void __init of_core_init(void)
 		pr_err("failed to register existing nodes\n");
 		return;
 	}
-	for_each_of_allnodes(np)
+	for_each_of_allnodes(np) {
 		__of_attach_node_sysfs(np);
+		if (np->phandle && !phandle_cache[of_phandle_cache_hash(np->phandle)])
+			phandle_cache[of_phandle_cache_hash(np->phandle)] = np;
+	}
 	mutex_unlock(&of_mutex);
 
 	/* Symlink in /proc as required by userspace ABI */
@@ -1235,36 +1161,24 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 {
 	struct device_node *np = NULL;
 	unsigned long flags;
-	phandle masked_handle;
+	u32 handle_hash;
 
 	if (!handle)
 		return NULL;
 
+	handle_hash = of_phandle_cache_hash(handle);
+
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 
-	masked_handle = handle & phandle_cache_mask;
-
-	if (phandle_cache) {
-		if (phandle_cache[masked_handle] &&
-		    handle == phandle_cache[masked_handle]->phandle)
-			np = phandle_cache[masked_handle];
-		if (np && of_node_check_flag(np, OF_DETACHED)) {
-			WARN_ON(1); /* did not uncache np on node removal */
-			of_node_put(np);
-			phandle_cache[masked_handle] = NULL;
-			np = NULL;
-		}
-	}
+	if (phandle_cache[handle_hash] &&
+	    handle == phandle_cache[handle_hash]->phandle)
+		np = phandle_cache[handle_hash];
 
 	if (!np) {
 		for_each_of_allnodes(np)
 			if (np->phandle == handle &&
 			    !of_node_check_flag(np, OF_DETACHED)) {
-				if (phandle_cache) {
-					/* will put when removed from cache */
-					of_node_get(np);
-					phandle_cache[masked_handle] = np;
-				}
+				phandle_cache[handle_hash] = np;
 				break;
 			}
 	}
diff --git a/drivers/of/device.c b/drivers/of/device.c
index e9127db7b067..27203bfd0b22 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -161,7 +161,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np);
-	if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER)
+	if (PTR_ERR(iommu) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 49b16f76d78e..08fd823edac9 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -276,7 +276,7 @@ void __of_detach_node(struct device_node *np)
 	of_node_set_flag(np, OF_DETACHED);
 
 	/* race with of_find_node_by_phandle() prevented by devtree_lock */
-	__of_free_phandle_cache_entry(np->phandle);
+	__of_phandle_cache_inv_entry(np->phandle);
 }
 
 /**
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index f5c2a5487761..8270bbf505fb 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -81,13 +81,15 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio,
 	else
 		phy = get_phy_device(mdio, addr, is_c45);
 	if (IS_ERR(phy)) {
-		unregister_mii_timestamper(mii_ts);
+		if (mii_ts)
+			unregister_mii_timestamper(mii_ts);
 		return PTR_ERR(phy);
 	}
 
 	rc = of_irq_get(child, 0);
 	if (rc == -EPROBE_DEFER) {
-		unregister_mii_timestamper(mii_ts);
+		if (mii_ts)
+			unregister_mii_timestamper(mii_ts);
 		phy_device_free(phy);
 		return rc;
 	}
@@ -116,12 +118,19 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio,
 	 * register it */
 	rc = phy_device_register(phy);
 	if (rc) {
-		unregister_mii_timestamper(mii_ts);
+		if (mii_ts)
+			unregister_mii_timestamper(mii_ts);
 		phy_device_free(phy);
 		of_node_put(child);
 		return rc;
 	}
-	phy->mii_ts = mii_ts;
+
+	/* phy->mii_ts may already be defined by the PHY driver. A
+	 * mii_timestamper probed via the device tree will still have
+	 * precedence.
+	 */
+	if (mii_ts)
+		phy->mii_ts = mii_ts;
 
 	dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n",
 		child, addr);
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 66294d29942a..207863c151a5 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -84,15 +84,11 @@ static inline void __of_detach_node_sysfs(struct device_node *np) {}
 int of_resolve_phandles(struct device_node *tree);
 #endif
 
-#if defined(CONFIG_OF_DYNAMIC)
-void __of_free_phandle_cache_entry(phandle handle);
-#endif
+void __of_phandle_cache_inv_entry(phandle handle);
 
 #if defined(CONFIG_OF_OVERLAY)
 void of_overlay_mutex_lock(void);
 void of_overlay_mutex_unlock(void);
-int of_free_phandle_cache(void);
-void of_populate_phandle_cache(void);
 #else
 static inline void of_overlay_mutex_lock(void) {};
 static inline void of_overlay_mutex_unlock(void) {};
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 9617b7df7c4d..c9219fddf44b 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -974,8 +974,6 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree,
 		goto err_free_overlay_changeset;
 	}
 
-	of_populate_phandle_cache();
-
 	ret = __of_changeset_apply_notify(&ovcs->cset);
 	if (ret)
 		pr_err("overlay apply changeset entry notify error %d\n", ret);
@@ -1218,17 +1216,8 @@ int of_overlay_remove(int *ovcs_id)
 
 	list_del(&ovcs->ovcs_list);
 
-	/*
-	 * Disable phandle cache.  Avoids race condition that would arise
-	 * from removing cache entry when the associated node is deleted.
-	 */
-	of_free_phandle_cache();
-
 	ret_apply = 0;
 	ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
-
-	of_populate_phandle_cache();
-
 	if (ret) {
 		if (ret_apply)
 			devicetree_state_flags |= DTSF_REVERT_FAIL;
diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
index 73e37bb877a4..36c6613f7a36 100644
--- a/drivers/parisc/led.c
+++ b/drivers/parisc/led.c
@@ -230,13 +230,12 @@ parse_error:
 	return -EINVAL;
 }
 
-static const struct file_operations led_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= led_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= led_proc_write,
+static const struct proc_ops led_proc_ops = {
+	.proc_open	= led_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= led_proc_write,
 };
 
 static int __init led_create_procfs(void)
@@ -252,14 +251,14 @@ static int __init led_create_procfs(void)
 	if (!lcd_no_led_support)
 	{
 		ent = proc_create_data("led", S_IRUGO|S_IWUSR, proc_pdc_root,
-					&led_proc_fops, (void *)LED_NOLCD); /* LED */
+					&led_proc_ops, (void *)LED_NOLCD); /* LED */
 		if (!ent) return -1;
 	}
 
 	if (led_type == LED_HASLCD)
 	{
 		ent = proc_create_data("lcd", S_IRUGO|S_IWUSR, proc_pdc_root,
-					&led_proc_fops, (void *)LED_HASLCD); /* LCD */
+					&led_proc_ops, (void *)LED_HASLCD); /* LCD */
 		if (!ent) return -1;
 	}
 
diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 982b46f0a54d..dcbcf1331bb2 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -69,6 +69,7 @@ int pci_enable_ats(struct pci_dev *dev, int ps)
 	dev->ats_enabled = 1;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_enable_ats);
 
 /**
  * pci_disable_ats - disable the ATS capability
@@ -87,6 +88,7 @@ void pci_disable_ats(struct pci_dev *dev)
 
 	dev->ats_enabled = 0;
 }
+EXPORT_SYMBOL_GPL(pci_disable_ats);
 
 void pci_restore_ats_state(struct pci_dev *dev)
 {
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index c77069c8ee5d..20bf00f587bd 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -239,7 +239,6 @@ config PCIE_TANGO_SMP8759
 
 config VMD
 	depends on PCI_MSI && X86_64 && SRCU
-	select X86_DEV_DMA_OPS
 	tristate "Intel Volume Management Device Driver"
 	---help---
 	  Adds support for the Intel Volume Management Device (VMD). VMD is a
@@ -253,6 +252,15 @@ config VMD
 	  To compile this driver as a module, choose M here: the
 	  module will be called vmd.
 
+config PCIE_BRCMSTB
+	tristate "Broadcom Brcmstb PCIe host controller"
+	depends on ARCH_BCM2835 || COMPILE_TEST
+	depends on OF
+	depends on PCI_MSI_IRQ_DOMAIN
+	help
+	  Say Y here to enable PCIe host controller support for
+	  Broadcom STB based SoCs, like the Raspberry Pi 4.
+
 config PCI_HYPERV_INTERFACE
 	tristate "Hyper-V PCI Interface"
 	depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index 3d4f597f15ce..01b2502a5323 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o
 obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o
 obj-$(CONFIG_PCIE_TANGO_SMP8759) += pcie-tango.o
 obj-$(CONFIG_VMD) += vmd.o
+obj-$(CONFIG_PCIE_BRCMSTB) += pcie-brcmstb.o
 # pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW
 obj-y				+= dwc/
 
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 625a031b2193..0830dfcfa43a 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -209,6 +209,17 @@ config PCIE_ARTPEC6_EP
 	  Enables support for the PCIe controller in the ARTPEC-6 SoC to work in
 	  endpoint mode. This uses the DesignWare core.
 
+config PCIE_INTEL_GW
+	bool "Intel Gateway PCIe host controller support"
+	depends on OF && (X86 || COMPILE_TEST)
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW_HOST
+	help
+	  Say 'Y' here to enable PCIe Host controller support on Intel
+	  Gateway SoCs.
+	  The PCIe controller uses the DesignWare core plus Intel-specific
+	  hardware wrappers.
+
 config PCIE_KIRIN
 	depends on OF && (ARM64 || COMPILE_TEST)
 	bool "HiSilicon Kirin series SoCs PCIe controllers"
diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile
index 69faff371f11..8a637cfcf6e9 100644
--- a/drivers/pci/controller/dwc/Makefile
+++ b/drivers/pci/controller/dwc/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_PCI_LAYERSCAPE_EP) += pci-layerscape-ep.o
 obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o
 obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o
 obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o
+obj-$(CONFIG_PCIE_INTEL_GW) += pcie-intel-gw.o
 obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o
 obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o
 obj-$(CONFIG_PCI_MESON) += pci-meson.o
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 14a6ba4067fb..c5043d951e80 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * PCIe host controller driver for Samsung EXYNOS SoCs
+ * PCIe host controller driver for Samsung Exynos SoCs
  *
  * Copyright (C) 2013 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index af677254a072..c8c702c494a2 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -422,7 +422,7 @@ static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
 				   lower_32_bits(start) | OB_ENABLEN);
 		ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i),
 				   upper_32_bits(start));
-		start += OB_WIN_SIZE;
+		start += OB_WIN_SIZE * SZ_1M;
 	}
 
 	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
@@ -510,7 +510,7 @@ static void ks_pcie_stop_link(struct dw_pcie *pci)
 	/* Disable Link training */
 	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
 	val &= ~LTSSM_EN_VAL;
-	ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
 }
 
 static int ks_pcie_start_link(struct dw_pcie *pci)
@@ -1354,7 +1354,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 		ret = of_property_read_u32(np, "num-viewport", &num_viewport);
 		if (ret < 0) {
 			dev_err(dev, "unable to read *num-viewport* property\n");
-			return ret;
+			goto err_get_sync;
 		}
 
 		/*
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 9e2482bd7b6d..28d5a1095200 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -51,9 +51,6 @@ static const struct of_device_id artpec6_pcie_of_match[];
 #define ACK_N_FTS_MASK			GENMASK(15, 8)
 #define ACK_N_FTS(x)			(((x) << 8) & ACK_N_FTS_MASK)
 
-#define FAST_TRAINING_SEQ_MASK		GENMASK(7, 0)
-#define FAST_TRAINING_SEQ(x)		(((x) << 0) & FAST_TRAINING_SEQ_MASK)
-
 /* ARTPEC-6 specific registers */
 #define PCIECFG				0x18
 #define  PCIECFG_DBG_OEN		BIT(24)
@@ -313,10 +310,7 @@ static void artpec6_pcie_set_nfts(struct artpec6_pcie *artpec6_pcie)
 	 * Set the Number of Fast Training Sequences that the core
 	 * advertises as its N_FTS during Gen2 or Gen3 link training.
 	 */
-	val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL);
-	val &= ~FAST_TRAINING_SEQ_MASK;
-	val |= FAST_TRAINING_SEQ(180);
-	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
+	dw_pcie_link_set_n_fts(pci, 180);
 }
 
 static void artpec6_pcie_assert_core_reset(struct artpec6_pcie *artpec6_pcie)
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 820488dfeaed..681548c88282 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -12,6 +12,7 @@
 #include <linux/of.h>
 #include <linux/types.h>
 
+#include "../../pci.h"
 #include "pcie-designware.h"
 
 /*
@@ -474,6 +475,61 @@ int dw_pcie_link_up(struct dw_pcie *pci)
 		(!(val & PCIE_PORT_DEBUG1_LINK_IN_TRAINING)));
 }
 
+void dw_pcie_upconfig_setup(struct dw_pcie *pci)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, PCIE_PORT_MULTI_LANE_CTRL);
+	val |= PORT_MLTI_UPCFG_SUPPORT;
+	dw_pcie_writel_dbi(pci, PCIE_PORT_MULTI_LANE_CTRL, val);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_upconfig_setup);
+
+void dw_pcie_link_set_max_speed(struct dw_pcie *pci, u32 link_gen)
+{
+	u32 reg, val;
+	u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+
+	reg = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCTL2);
+	reg &= ~PCI_EXP_LNKCTL2_TLS;
+
+	switch (pcie_link_speed[link_gen]) {
+	case PCIE_SPEED_2_5GT:
+		reg |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+		break;
+	case PCIE_SPEED_5_0GT:
+		reg |= PCI_EXP_LNKCTL2_TLS_5_0GT;
+		break;
+	case PCIE_SPEED_8_0GT:
+		reg |= PCI_EXP_LNKCTL2_TLS_8_0GT;
+		break;
+	case PCIE_SPEED_16_0GT:
+		reg |= PCI_EXP_LNKCTL2_TLS_16_0GT;
+		break;
+	default:
+		/* Use hardware capability */
+		val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
+		val = FIELD_GET(PCI_EXP_LNKCAP_SLS, val);
+		reg &= ~PCI_EXP_LNKCTL2_HASD;
+		reg |= FIELD_PREP(PCI_EXP_LNKCTL2_TLS, val);
+		break;
+	}
+
+	dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCTL2, reg);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_link_set_max_speed);
+
+void dw_pcie_link_set_n_fts(struct dw_pcie *pci, u32 n_fts)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL);
+	val &= ~PORT_LOGIC_N_FTS_MASK;
+	val |= n_fts & PORT_LOGIC_N_FTS_MASK;
+	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_link_set_n_fts);
+
 static u8 dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci)
 {
 	u32 val;
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 5accdd6bc388..a22ea5982817 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -30,7 +30,12 @@
 #define LINK_WAIT_IATU			9
 
 /* Synopsys-specific PCIe configuration registers */
+#define PCIE_PORT_AFR			0x70C
+#define PORT_AFR_N_FTS_MASK		GENMASK(15, 8)
+#define PORT_AFR_CC_N_FTS_MASK		GENMASK(23, 16)
+
 #define PCIE_PORT_LINK_CONTROL		0x710
+#define PORT_LINK_DLL_LINK_EN		BIT(5)
 #define PORT_LINK_MODE_MASK		GENMASK(21, 16)
 #define PORT_LINK_MODE(n)		FIELD_PREP(PORT_LINK_MODE_MASK, n)
 #define PORT_LINK_MODE_1_LANES		PORT_LINK_MODE(0x1)
@@ -46,6 +51,7 @@
 #define PCIE_PORT_DEBUG1_LINK_IN_TRAINING	BIT(29)
 
 #define PCIE_LINK_WIDTH_SPEED_CONTROL	0x80C
+#define PORT_LOGIC_N_FTS_MASK		GENMASK(7, 0)
 #define PORT_LOGIC_SPEED_CHANGE		BIT(17)
 #define PORT_LOGIC_LINK_WIDTH_MASK	GENMASK(12, 8)
 #define PORT_LOGIC_LINK_WIDTH(n)	FIELD_PREP(PORT_LOGIC_LINK_WIDTH_MASK, n)
@@ -60,6 +66,9 @@
 #define PCIE_MSI_INTR0_MASK		0x82C
 #define PCIE_MSI_INTR0_STATUS		0x830
 
+#define PCIE_PORT_MULTI_LANE_CTRL	0x8C0
+#define PORT_MLTI_UPCFG_SUPPORT		BIT(7)
+
 #define PCIE_ATU_VIEWPORT		0x900
 #define PCIE_ATU_REGION_INBOUND		BIT(31)
 #define PCIE_ATU_REGION_OUTBOUND	0
@@ -273,6 +282,9 @@ void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
 u32 dw_pcie_read_atu(struct dw_pcie *pci, u32 reg, size_t size);
 void dw_pcie_write_atu(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
 int dw_pcie_link_up(struct dw_pcie *pci);
+void dw_pcie_upconfig_setup(struct dw_pcie *pci);
+void dw_pcie_link_set_max_speed(struct dw_pcie *pci, u32 link_gen);
+void dw_pcie_link_set_n_fts(struct dw_pcie *pci, u32 n_fts);
 int dw_pcie_wait_for_link(struct dw_pcie *pci);
 void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index,
 			       int type, u64 cpu_addr, u64 pci_addr,
diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c
new file mode 100644
index 000000000000..fc2a12212dec
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-intel-gw.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCIe host controller driver for Intel Gateway SoCs
+ *
+ * Copyright (c) 2019 Intel Corporation.
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/gpio/consumer.h>
+#include <linux/iopoll.h>
+#include <linux/pci_regs.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "../../pci.h"
+#include "pcie-designware.h"
+
+#define PORT_AFR_N_FTS_GEN12_DFT	(SZ_128 - 1)
+#define PORT_AFR_N_FTS_GEN3		180
+#define PORT_AFR_N_FTS_GEN4		196
+
+/* PCIe Application logic Registers */
+#define PCIE_APP_CCR			0x10
+#define PCIE_APP_CCR_LTSSM_ENABLE	BIT(0)
+
+#define PCIE_APP_MSG_CR			0x30
+#define PCIE_APP_MSG_XMT_PM_TURNOFF	BIT(0)
+
+#define PCIE_APP_PMC			0x44
+#define PCIE_APP_PMC_IN_L2		BIT(20)
+
+#define PCIE_APP_IRNEN			0xF4
+#define PCIE_APP_IRNCR			0xF8
+#define PCIE_APP_IRN_AER_REPORT		BIT(0)
+#define PCIE_APP_IRN_PME		BIT(2)
+#define PCIE_APP_IRN_RX_VDM_MSG		BIT(4)
+#define PCIE_APP_IRN_PM_TO_ACK		BIT(9)
+#define PCIE_APP_IRN_LINK_AUTO_BW_STAT	BIT(11)
+#define PCIE_APP_IRN_BW_MGT		BIT(12)
+#define PCIE_APP_IRN_MSG_LTR		BIT(18)
+#define PCIE_APP_IRN_SYS_ERR_RC		BIT(29)
+#define PCIE_APP_INTX_OFST		12
+
+#define PCIE_APP_IRN_INT \
+	(PCIE_APP_IRN_AER_REPORT | PCIE_APP_IRN_PME | \
+	PCIE_APP_IRN_RX_VDM_MSG | PCIE_APP_IRN_SYS_ERR_RC | \
+	PCIE_APP_IRN_PM_TO_ACK | PCIE_APP_IRN_MSG_LTR | \
+	PCIE_APP_IRN_BW_MGT | PCIE_APP_IRN_LINK_AUTO_BW_STAT | \
+	(PCIE_APP_INTX_OFST + PCI_INTERRUPT_INTA) | \
+	(PCIE_APP_INTX_OFST + PCI_INTERRUPT_INTB) | \
+	(PCIE_APP_INTX_OFST + PCI_INTERRUPT_INTC) | \
+	(PCIE_APP_INTX_OFST + PCI_INTERRUPT_INTD))
+
+#define BUS_IATU_OFFSET			SZ_256M
+#define RESET_INTERVAL_MS		100
+
+struct intel_pcie_soc {
+	unsigned int	pcie_ver;
+	unsigned int	pcie_atu_offset;
+	u32		num_viewport;
+};
+
+struct intel_pcie_port {
+	struct dw_pcie		pci;
+	void __iomem		*app_base;
+	struct gpio_desc	*reset_gpio;
+	u32			rst_intrvl;
+	u32			max_speed;
+	u32			link_gen;
+	u32			max_width;
+	u32			n_fts;
+	struct clk		*core_clk;
+	struct reset_control	*core_rst;
+	struct phy		*phy;
+	u8			pcie_cap_ofst;
+};
+
+static void pcie_update_bits(void __iomem *base, u32 ofs, u32 mask, u32 val)
+{
+	u32 old;
+
+	old = readl(base + ofs);
+	val = (old & ~mask) | (val & mask);
+
+	if (val != old)
+		writel(val, base + ofs);
+}
+
+static inline u32 pcie_app_rd(struct intel_pcie_port *lpp, u32 ofs)
+{
+	return readl(lpp->app_base + ofs);
+}
+
+static inline void pcie_app_wr(struct intel_pcie_port *lpp, u32 ofs, u32 val)
+{
+	writel(val, lpp->app_base + ofs);
+}
+
+static void pcie_app_wr_mask(struct intel_pcie_port *lpp, u32 ofs,
+			     u32 mask, u32 val)
+{
+	pcie_update_bits(lpp->app_base, ofs, mask, val);
+}
+
+static inline u32 pcie_rc_cfg_rd(struct intel_pcie_port *lpp, u32 ofs)
+{
+	return dw_pcie_readl_dbi(&lpp->pci, ofs);
+}
+
+static inline void pcie_rc_cfg_wr(struct intel_pcie_port *lpp, u32 ofs, u32 val)
+{
+	dw_pcie_writel_dbi(&lpp->pci, ofs, val);
+}
+
+static void pcie_rc_cfg_wr_mask(struct intel_pcie_port *lpp, u32 ofs,
+				u32 mask, u32 val)
+{
+	pcie_update_bits(lpp->pci.dbi_base, ofs, mask, val);
+}
+
+static void intel_pcie_ltssm_enable(struct intel_pcie_port *lpp)
+{
+	pcie_app_wr_mask(lpp, PCIE_APP_CCR, PCIE_APP_CCR_LTSSM_ENABLE,
+			 PCIE_APP_CCR_LTSSM_ENABLE);
+}
+
+static void intel_pcie_ltssm_disable(struct intel_pcie_port *lpp)
+{
+	pcie_app_wr_mask(lpp, PCIE_APP_CCR, PCIE_APP_CCR_LTSSM_ENABLE, 0);
+}
+
+static void intel_pcie_link_setup(struct intel_pcie_port *lpp)
+{
+	u32 val;
+	u8 offset = lpp->pcie_cap_ofst;
+
+	val = pcie_rc_cfg_rd(lpp, offset + PCI_EXP_LNKCAP);
+	lpp->max_speed = FIELD_GET(PCI_EXP_LNKCAP_SLS, val);
+	lpp->max_width = FIELD_GET(PCI_EXP_LNKCAP_MLW, val);
+
+	val = pcie_rc_cfg_rd(lpp, offset + PCI_EXP_LNKCTL);
+
+	val &= ~(PCI_EXP_LNKCTL_LD | PCI_EXP_LNKCTL_ASPMC);
+	pcie_rc_cfg_wr(lpp, offset + PCI_EXP_LNKCTL, val);
+}
+
+static void intel_pcie_port_logic_setup(struct intel_pcie_port *lpp)
+{
+	u32 val, mask;
+
+	switch (pcie_link_speed[lpp->max_speed]) {
+	case PCIE_SPEED_8_0GT:
+		lpp->n_fts = PORT_AFR_N_FTS_GEN3;
+		break;
+	case PCIE_SPEED_16_0GT:
+		lpp->n_fts = PORT_AFR_N_FTS_GEN4;
+		break;
+	default:
+		lpp->n_fts = PORT_AFR_N_FTS_GEN12_DFT;
+		break;
+	}
+
+	mask = PORT_AFR_N_FTS_MASK | PORT_AFR_CC_N_FTS_MASK;
+	val = FIELD_PREP(PORT_AFR_N_FTS_MASK, lpp->n_fts) |
+	       FIELD_PREP(PORT_AFR_CC_N_FTS_MASK, lpp->n_fts);
+	pcie_rc_cfg_wr_mask(lpp, PCIE_PORT_AFR, mask, val);
+
+	/* Port Link Control Register */
+	pcie_rc_cfg_wr_mask(lpp, PCIE_PORT_LINK_CONTROL, PORT_LINK_DLL_LINK_EN,
+			    PORT_LINK_DLL_LINK_EN);
+}
+
+static void intel_pcie_rc_setup(struct intel_pcie_port *lpp)
+{
+	intel_pcie_ltssm_disable(lpp);
+	intel_pcie_link_setup(lpp);
+	dw_pcie_setup_rc(&lpp->pci.pp);
+	dw_pcie_upconfig_setup(&lpp->pci);
+	intel_pcie_port_logic_setup(lpp);
+	dw_pcie_link_set_max_speed(&lpp->pci, lpp->link_gen);
+	dw_pcie_link_set_n_fts(&lpp->pci, lpp->n_fts);
+}
+
+static int intel_pcie_ep_rst_init(struct intel_pcie_port *lpp)
+{
+	struct device *dev = lpp->pci.dev;
+	int ret;
+
+	lpp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(lpp->reset_gpio)) {
+		ret = PTR_ERR(lpp->reset_gpio);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to request PCIe GPIO: %d\n", ret);
+		return ret;
+	}
+
+	/* Make initial reset last for 100us */
+	usleep_range(100, 200);
+
+	return 0;
+}
+
+static void intel_pcie_core_rst_assert(struct intel_pcie_port *lpp)
+{
+	reset_control_assert(lpp->core_rst);
+}
+
+static void intel_pcie_core_rst_deassert(struct intel_pcie_port *lpp)
+{
+	/*
+	 * One micro-second delay to make sure the reset pulse
+	 * wide enough so that core reset is clean.
+	 */
+	udelay(1);
+	reset_control_deassert(lpp->core_rst);
+
+	/*
+	 * Some SoC core reset also reset PHY, more delay needed
+	 * to make sure the reset process is done.
+	 */
+	usleep_range(1000, 2000);
+}
+
+static void intel_pcie_device_rst_assert(struct intel_pcie_port *lpp)
+{
+	gpiod_set_value_cansleep(lpp->reset_gpio, 1);
+}
+
+static void intel_pcie_device_rst_deassert(struct intel_pcie_port *lpp)
+{
+	msleep(lpp->rst_intrvl);
+	gpiod_set_value_cansleep(lpp->reset_gpio, 0);
+}
+
+static int intel_pcie_app_logic_setup(struct intel_pcie_port *lpp)
+{
+	intel_pcie_device_rst_deassert(lpp);
+	intel_pcie_ltssm_enable(lpp);
+
+	return dw_pcie_wait_for_link(&lpp->pci);
+}
+
+static void intel_pcie_core_irq_disable(struct intel_pcie_port *lpp)
+{
+	pcie_app_wr(lpp, PCIE_APP_IRNEN, 0);
+	pcie_app_wr(lpp, PCIE_APP_IRNCR, PCIE_APP_IRN_INT);
+}
+
+static int intel_pcie_get_resources(struct platform_device *pdev)
+{
+	struct intel_pcie_port *lpp = platform_get_drvdata(pdev);
+	struct dw_pcie *pci = &lpp->pci;
+	struct device *dev = pci->dev;
+	struct resource *res;
+	int ret;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
+	pci->dbi_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(pci->dbi_base))
+		return PTR_ERR(pci->dbi_base);
+
+	lpp->core_clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(lpp->core_clk)) {
+		ret = PTR_ERR(lpp->core_clk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get clks: %d\n", ret);
+		return ret;
+	}
+
+	lpp->core_rst = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(lpp->core_rst)) {
+		ret = PTR_ERR(lpp->core_rst);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get resets: %d\n", ret);
+		return ret;
+	}
+
+	ret = device_property_match_string(dev, "device_type", "pci");
+	if (ret) {
+		dev_err(dev, "Failed to find pci device type: %d\n", ret);
+		return ret;
+	}
+
+	ret = device_property_read_u32(dev, "reset-assert-ms",
+				       &lpp->rst_intrvl);
+	if (ret)
+		lpp->rst_intrvl = RESET_INTERVAL_MS;
+
+	ret = of_pci_get_max_link_speed(dev->of_node);
+	lpp->link_gen = ret < 0 ? 0 : ret;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "app");
+	lpp->app_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(lpp->app_base))
+		return PTR_ERR(lpp->app_base);
+
+	lpp->phy = devm_phy_get(dev, "pcie");
+	if (IS_ERR(lpp->phy)) {
+		ret = PTR_ERR(lpp->phy);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Couldn't get pcie-phy: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void intel_pcie_deinit_phy(struct intel_pcie_port *lpp)
+{
+	phy_exit(lpp->phy);
+}
+
+static int intel_pcie_wait_l2(struct intel_pcie_port *lpp)
+{
+	u32 value;
+	int ret;
+
+	if (pcie_link_speed[lpp->max_speed] < PCIE_SPEED_8_0GT)
+		return 0;
+
+	/* Send PME_TURN_OFF message */
+	pcie_app_wr_mask(lpp, PCIE_APP_MSG_CR, PCIE_APP_MSG_XMT_PM_TURNOFF,
+			 PCIE_APP_MSG_XMT_PM_TURNOFF);
+
+	/* Read PMC status and wait for falling into L2 link state */
+	ret = readl_poll_timeout(lpp->app_base + PCIE_APP_PMC, value,
+				 value & PCIE_APP_PMC_IN_L2, 20,
+				 jiffies_to_usecs(5 * HZ));
+	if (ret)
+		dev_err(lpp->pci.dev, "PCIe link enter L2 timeout!\n");
+
+	return ret;
+}
+
+static void intel_pcie_turn_off(struct intel_pcie_port *lpp)
+{
+	if (dw_pcie_link_up(&lpp->pci))
+		intel_pcie_wait_l2(lpp);
+
+	/* Put endpoint device in reset state */
+	intel_pcie_device_rst_assert(lpp);
+	pcie_rc_cfg_wr_mask(lpp, PCI_COMMAND, PCI_COMMAND_MEMORY, 0);
+}
+
+static int intel_pcie_host_setup(struct intel_pcie_port *lpp)
+{
+	struct device *dev = lpp->pci.dev;
+	int ret;
+
+	intel_pcie_core_rst_assert(lpp);
+	intel_pcie_device_rst_assert(lpp);
+
+	ret = phy_init(lpp->phy);
+	if (ret)
+		return ret;
+
+	intel_pcie_core_rst_deassert(lpp);
+
+	ret = clk_prepare_enable(lpp->core_clk);
+	if (ret) {
+		dev_err(lpp->pci.dev, "Core clock enable failed: %d\n", ret);
+		goto clk_err;
+	}
+
+	if (!lpp->pcie_cap_ofst) {
+		ret = dw_pcie_find_capability(&lpp->pci, PCI_CAP_ID_EXP);
+		if (!ret) {
+			ret = -ENXIO;
+			dev_err(dev, "Invalid PCIe capability offset\n");
+			goto app_init_err;
+		}
+
+		lpp->pcie_cap_ofst = ret;
+	}
+
+	intel_pcie_rc_setup(lpp);
+	ret = intel_pcie_app_logic_setup(lpp);
+	if (ret)
+		goto app_init_err;
+
+	/* Enable integrated interrupts */
+	pcie_app_wr_mask(lpp, PCIE_APP_IRNEN, PCIE_APP_IRN_INT,
+			 PCIE_APP_IRN_INT);
+
+	return 0;
+
+app_init_err:
+	clk_disable_unprepare(lpp->core_clk);
+clk_err:
+	intel_pcie_core_rst_assert(lpp);
+	intel_pcie_deinit_phy(lpp);
+
+	return ret;
+}
+
+static void __intel_pcie_remove(struct intel_pcie_port *lpp)
+{
+	intel_pcie_core_irq_disable(lpp);
+	intel_pcie_turn_off(lpp);
+	clk_disable_unprepare(lpp->core_clk);
+	intel_pcie_core_rst_assert(lpp);
+	intel_pcie_deinit_phy(lpp);
+}
+
+static int intel_pcie_remove(struct platform_device *pdev)
+{
+	struct intel_pcie_port *lpp = platform_get_drvdata(pdev);
+	struct pcie_port *pp = &lpp->pci.pp;
+
+	dw_pcie_host_deinit(pp);
+	__intel_pcie_remove(lpp);
+
+	return 0;
+}
+
+static int __maybe_unused intel_pcie_suspend_noirq(struct device *dev)
+{
+	struct intel_pcie_port *lpp = dev_get_drvdata(dev);
+	int ret;
+
+	intel_pcie_core_irq_disable(lpp);
+	ret = intel_pcie_wait_l2(lpp);
+	if (ret)
+		return ret;
+
+	intel_pcie_deinit_phy(lpp);
+	clk_disable_unprepare(lpp->core_clk);
+	return ret;
+}
+
+static int __maybe_unused intel_pcie_resume_noirq(struct device *dev)
+{
+	struct intel_pcie_port *lpp = dev_get_drvdata(dev);
+
+	return intel_pcie_host_setup(lpp);
+}
+
+static int intel_pcie_rc_init(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct intel_pcie_port *lpp = dev_get_drvdata(pci->dev);
+
+	return intel_pcie_host_setup(lpp);
+}
+
+/*
+ * Dummy function so that DW core doesn't configure MSI
+ */
+static int intel_pcie_msi_init(struct pcie_port *pp)
+{
+	return 0;
+}
+
+u64 intel_pcie_cpu_addr(struct dw_pcie *pcie, u64 cpu_addr)
+{
+	return cpu_addr + BUS_IATU_OFFSET;
+}
+
+static const struct dw_pcie_ops intel_pcie_ops = {
+	.cpu_addr_fixup = intel_pcie_cpu_addr,
+};
+
+static const struct dw_pcie_host_ops intel_pcie_dw_ops = {
+	.host_init =		intel_pcie_rc_init,
+	.msi_host_init =	intel_pcie_msi_init,
+};
+
+static const struct intel_pcie_soc pcie_data = {
+	.pcie_ver =		0x520A,
+	.pcie_atu_offset =	0xC0000,
+	.num_viewport =		3,
+};
+
+static int intel_pcie_probe(struct platform_device *pdev)
+{
+	const struct intel_pcie_soc *data;
+	struct device *dev = &pdev->dev;
+	struct intel_pcie_port *lpp;
+	struct pcie_port *pp;
+	struct dw_pcie *pci;
+	int ret;
+
+	lpp = devm_kzalloc(dev, sizeof(*lpp), GFP_KERNEL);
+	if (!lpp)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, lpp);
+	pci = &lpp->pci;
+	pci->dev = dev;
+	pp = &pci->pp;
+
+	ret = intel_pcie_get_resources(pdev);
+	if (ret)
+		return ret;
+
+	ret = intel_pcie_ep_rst_init(lpp);
+	if (ret)
+		return ret;
+
+	data = device_get_match_data(dev);
+	if (!data)
+		return -ENODEV;
+
+	pci->ops = &intel_pcie_ops;
+	pci->version = data->pcie_ver;
+	pci->atu_base = pci->dbi_base + data->pcie_atu_offset;
+	pp->ops = &intel_pcie_dw_ops;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(dev, "Cannot initialize host\n");
+		return ret;
+	}
+
+	/*
+	 * Intel PCIe doesn't configure IO region, so set viewport
+	 * to not perform IO region access.
+	 */
+	pci->num_viewport = data->num_viewport;
+
+	return 0;
+}
+
+static const struct dev_pm_ops intel_pcie_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pcie_suspend_noirq,
+				      intel_pcie_resume_noirq)
+};
+
+static const struct of_device_id of_intel_pcie_match[] = {
+	{ .compatible = "intel,lgm-pcie", .data = &pcie_data },
+	{}
+};
+
+static struct platform_driver intel_pcie_driver = {
+	.probe = intel_pcie_probe,
+	.remove = intel_pcie_remove,
+	.driver = {
+		.name = "intel-gw-pcie",
+		.of_match_table = of_intel_pcie_match,
+		.pm = &intel_pcie_pm_ops,
+	},
+};
+builtin_platform_driver(intel_pcie_driver);
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 7e581748ee9f..5ea527a6bd9f 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -54,6 +54,7 @@
 #define PCIE20_PARF_LTSSM			0x1B0
 #define PCIE20_PARF_SID_OFFSET			0x234
 #define PCIE20_PARF_BDF_TRANSLATE_CFG		0x24C
+#define PCIE20_PARF_DEVICE_TYPE			0x1000
 
 #define PCIE20_ELBI_SYS_CTRL			0x04
 #define PCIE20_ELBI_SYS_CTRL_LT_ENABLE		BIT(0)
@@ -80,6 +81,8 @@
 #define PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE	0x358
 #define SLV_ADDR_SPACE_SZ			0x10000000
 
+#define DEVICE_TYPE_RC				0x4
+
 #define QCOM_PCIE_2_1_0_MAX_SUPPLY	3
 struct qcom_pcie_resources_2_1_0 {
 	struct clk *iface_clk;
@@ -139,12 +142,20 @@ struct qcom_pcie_resources_2_3_3 {
 	struct reset_control *rst[7];
 };
 
+struct qcom_pcie_resources_2_7_0 {
+	struct clk_bulk_data clks[6];
+	struct regulator_bulk_data supplies[2];
+	struct reset_control *pci_reset;
+	struct clk *pipe_clk;
+};
+
 union qcom_pcie_resources {
 	struct qcom_pcie_resources_1_0_0 v1_0_0;
 	struct qcom_pcie_resources_2_1_0 v2_1_0;
 	struct qcom_pcie_resources_2_3_2 v2_3_2;
 	struct qcom_pcie_resources_2_3_3 v2_3_3;
 	struct qcom_pcie_resources_2_4_0 v2_4_0;
+	struct qcom_pcie_resources_2_7_0 v2_7_0;
 };
 
 struct qcom_pcie;
@@ -1068,6 +1079,134 @@ err_clk_iface:
 	return ret;
 }
 
+static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	int ret;
+
+	res->pci_reset = devm_reset_control_get_exclusive(dev, "pci");
+	if (IS_ERR(res->pci_reset))
+		return PTR_ERR(res->pci_reset);
+
+	res->supplies[0].supply = "vdda";
+	res->supplies[1].supply = "vddpe-3v3";
+	ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(res->supplies),
+				      res->supplies);
+	if (ret)
+		return ret;
+
+	res->clks[0].id = "aux";
+	res->clks[1].id = "cfg";
+	res->clks[2].id = "bus_master";
+	res->clks[3].id = "bus_slave";
+	res->clks[4].id = "slave_q2a";
+	res->clks[5].id = "tbu";
+
+	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks);
+	if (ret < 0)
+		return ret;
+
+	res->pipe_clk = devm_clk_get(dev, "pipe");
+	return PTR_ERR_OR_ZERO(res->pipe_clk);
+}
+
+static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	u32 val;
+	int ret;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies);
+	if (ret < 0) {
+		dev_err(dev, "cannot enable regulators\n");
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	if (ret < 0)
+		goto err_disable_regulators;
+
+	ret = reset_control_assert(res->pci_reset);
+	if (ret < 0) {
+		dev_err(dev, "cannot deassert pci reset\n");
+		goto err_disable_clocks;
+	}
+
+	usleep_range(1000, 1500);
+
+	ret = reset_control_deassert(res->pci_reset);
+	if (ret < 0) {
+		dev_err(dev, "cannot deassert pci reset\n");
+		goto err_disable_clocks;
+	}
+
+	ret = clk_prepare_enable(res->pipe_clk);
+	if (ret) {
+		dev_err(dev, "cannot prepare/enable pipe clock\n");
+		goto err_disable_clocks;
+	}
+
+	/* configure PCIe to RC mode */
+	writel(DEVICE_TYPE_RC, pcie->parf + PCIE20_PARF_DEVICE_TYPE);
+
+	/* enable PCIe clocks and resets */
+	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
+	val &= ~BIT(0);
+	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
+
+	/* change DBI base address */
+	writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR);
+
+	/* MAC PHY_POWERDOWN MUX DISABLE  */
+	val = readl(pcie->parf + PCIE20_PARF_SYS_CTRL);
+	val &= ~BIT(29);
+	writel(val, pcie->parf + PCIE20_PARF_SYS_CTRL);
+
+	val = readl(pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL);
+	val |= BIT(4);
+	writel(val, pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL);
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
+		val |= BIT(31);
+		writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
+	}
+
+	return 0;
+err_disable_clocks:
+	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+err_disable_regulators:
+	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
+
+	return ret;
+}
+
+static void qcom_pcie_deinit_2_7_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+
+	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
+}
+
+static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+
+	return clk_prepare_enable(res->pipe_clk);
+}
+
+static void qcom_pcie_post_deinit_2_7_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+
+	clk_disable_unprepare(res->pipe_clk);
+}
+
 static int qcom_pcie_link_up(struct dw_pcie *pci)
 {
 	u16 val = readw(pci->dbi_base + PCIE20_CAP + PCI_EXP_LNKSTA);
@@ -1167,6 +1306,16 @@ static const struct qcom_pcie_ops ops_2_3_3 = {
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
 };
 
+/* Qcom IP rev.: 2.7.0	Synopsys IP rev.: 4.30a */
+static const struct qcom_pcie_ops ops_2_7_0 = {
+	.get_resources = qcom_pcie_get_resources_2_7_0,
+	.init = qcom_pcie_init_2_7_0,
+	.deinit = qcom_pcie_deinit_2_7_0,
+	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
+	.post_init = qcom_pcie_post_init_2_7_0,
+	.post_deinit = qcom_pcie_post_deinit_2_7_0,
+};
+
 static const struct dw_pcie_ops dw_pcie_ops = {
 	.link_up = qcom_pcie_link_up,
 };
@@ -1282,6 +1431,7 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-ipq8074", .data = &ops_2_3_3 },
 	{ .compatible = "qcom,pcie-ipq4019", .data = &ops_2_4_0 },
 	{ .compatible = "qcom,pcie-qcs404", .data = &ops_2_4_0 },
+	{ .compatible = "qcom,pcie-sdm845", .data = &ops_2_7_0 },
 	{ }
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
index 8fd7badd59c2..a5401a0b1e58 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -9,11 +9,11 @@
 #include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
-#include <linux/module.h>
 #include <linux/of_irq.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
@@ -171,12 +171,6 @@ static void uniphier_pcie_irq_enable(struct uniphier_pcie_priv *priv)
 	writel(PCL_RCV_INTX_ALL_ENABLE, priv->base + PCL_RCV_INTX);
 }
 
-static void uniphier_pcie_irq_disable(struct uniphier_pcie_priv *priv)
-{
-	writel(0, priv->base + PCL_RCV_INT);
-	writel(0, priv->base + PCL_RCV_INTX);
-}
-
 static void uniphier_pcie_irq_ack(struct irq_data *d)
 {
 	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
@@ -397,14 +391,6 @@ out_clk_disable:
 	return ret;
 }
 
-static void uniphier_pcie_host_disable(struct uniphier_pcie_priv *priv)
-{
-	uniphier_pcie_irq_disable(priv);
-	phy_exit(priv->phy);
-	reset_control_assert(priv->rst);
-	clk_disable_unprepare(priv->clk);
-}
-
 static const struct dw_pcie_ops dw_pcie_ops = {
 	.start_link = uniphier_pcie_establish_link,
 	.stop_link = uniphier_pcie_stop_link,
@@ -456,31 +442,16 @@ static int uniphier_pcie_probe(struct platform_device *pdev)
 	return uniphier_add_pcie_port(priv, pdev);
 }
 
-static int uniphier_pcie_remove(struct platform_device *pdev)
-{
-	struct uniphier_pcie_priv *priv = platform_get_drvdata(pdev);
-
-	uniphier_pcie_host_disable(priv);
-
-	return 0;
-}
-
 static const struct of_device_id uniphier_pcie_match[] = {
 	{ .compatible = "socionext,uniphier-pcie", },
 	{ /* sentinel */ },
 };
-MODULE_DEVICE_TABLE(of, uniphier_pcie_match);
 
 static struct platform_driver uniphier_pcie_driver = {
 	.probe  = uniphier_pcie_probe,
-	.remove = uniphier_pcie_remove,
 	.driver = {
 		.name = "uniphier-pcie",
 		.of_match_table = uniphier_pcie_match,
 	},
 };
 builtin_platform_driver(uniphier_pcie_driver);
-
-MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
-MODULE_DESCRIPTION("UniPhier PCIe host controller driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 673a1725ef38..0e03cef72840 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -1406,7 +1406,7 @@ static struct phy *devm_of_phy_optional_get_index(struct device *dev,
 	phy = devm_of_phy_get(dev, np, name);
 	kfree(name);
 
-	if (IS_ERR(phy) && PTR_ERR(phy) == -ENODEV)
+	if (PTR_ERR(phy) == -ENODEV)
 		phy = NULL;
 
 	return phy;
@@ -2499,7 +2499,6 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.num_ports = 2,
 	.ports = tegra20_pcie_ports,
 	.msi_base_shift = 0,
-	.afi_pex2_ctrl = 0x128,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA20,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10,
 	.pads_refclk_cfg0 = 0xfa5cfa5c,
@@ -2528,6 +2527,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.num_ports = 3,
 	.ports = tegra30_pcie_ports,
 	.msi_base_shift = 8,
+	.afi_pex2_ctrl = 0x128,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0xfa5cfa5c,
@@ -2798,7 +2798,7 @@ static int tegra_pcie_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(pcie->dev);
 	err = pm_runtime_get_sync(pcie->dev);
-	if (err) {
+	if (err < 0) {
 		dev_err(dev, "fail to enable pcie controller: %d\n", err);
 		goto teardown_msi;
 	}
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
new file mode 100644
index 000000000000..d20aabc26273
--- /dev/null
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -0,0 +1,1015 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2009 - 2019 Broadcom */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/compiler.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/log2.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/printk.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "../pci.h"
+
+/* BRCM_PCIE_CAP_REGS - Offset for the mandatory capability config regs */
+#define BRCM_PCIE_CAP_REGS				0x00ac
+
+/* Broadcom STB PCIe Register Offsets */
+#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1				0x0188
+#define  PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK	0xc
+#define  PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN			0x0
+
+#define PCIE_RC_CFG_PRIV1_ID_VAL3			0x043c
+#define  PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK	0xffffff
+
+#define PCIE_RC_DL_MDIO_ADDR				0x1100
+#define PCIE_RC_DL_MDIO_WR_DATA				0x1104
+#define PCIE_RC_DL_MDIO_RD_DATA				0x1108
+
+#define PCIE_MISC_MISC_CTRL				0x4008
+#define  PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK		0x1000
+#define  PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK	0x2000
+#define  PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK	0x300000
+#define  PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_128		0x0
+#define  PCIE_MISC_MISC_CTRL_SCB0_SIZE_MASK		0xf8000000
+
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO		0x400c
+#define PCIE_MEM_WIN0_LO(win)	\
+		PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO + ((win) * 4)
+
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI		0x4010
+#define PCIE_MEM_WIN0_HI(win)	\
+		PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI + ((win) * 4)
+
+#define PCIE_MISC_RC_BAR1_CONFIG_LO			0x402c
+#define  PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK		0x1f
+
+#define PCIE_MISC_RC_BAR2_CONFIG_LO			0x4034
+#define  PCIE_MISC_RC_BAR2_CONFIG_LO_SIZE_MASK		0x1f
+#define PCIE_MISC_RC_BAR2_CONFIG_HI			0x4038
+
+#define PCIE_MISC_RC_BAR3_CONFIG_LO			0x403c
+#define  PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_MASK		0x1f
+
+#define PCIE_MISC_MSI_BAR_CONFIG_LO			0x4044
+#define PCIE_MISC_MSI_BAR_CONFIG_HI			0x4048
+
+#define PCIE_MISC_MSI_DATA_CONFIG			0x404c
+#define  PCIE_MISC_MSI_DATA_CONFIG_VAL			0xffe06540
+
+#define PCIE_MISC_PCIE_CTRL				0x4064
+#define  PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK	0x1
+
+#define PCIE_MISC_PCIE_STATUS				0x4068
+#define  PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK		0x80
+#define  PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK	0x20
+#define  PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK	0x10
+#define  PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK	0x40
+
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT		0x4070
+#define  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK	0xfff00000
+#define  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK	0xfff0
+#define PCIE_MEM_WIN0_BASE_LIMIT(win)	\
+		PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT + ((win) * 4)
+
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI			0x4080
+#define  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK	0xff
+#define PCIE_MEM_WIN0_BASE_HI(win)	\
+		PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI + ((win) * 8)
+
+#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI			0x4084
+#define  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK	0xff
+#define PCIE_MEM_WIN0_LIMIT_HI(win)	\
+		PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI + ((win) * 8)
+
+#define PCIE_MISC_HARD_PCIE_HARD_DEBUG					0x4204
+#define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK	0x2
+#define  PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK		0x08000000
+
+#define PCIE_MSI_INTR2_STATUS				0x4500
+#define PCIE_MSI_INTR2_CLR				0x4508
+#define PCIE_MSI_INTR2_MASK_SET				0x4510
+#define PCIE_MSI_INTR2_MASK_CLR				0x4514
+
+#define PCIE_EXT_CFG_DATA				0x8000
+
+#define PCIE_EXT_CFG_INDEX				0x9000
+#define  PCIE_EXT_BUSNUM_SHIFT				20
+#define  PCIE_EXT_SLOT_SHIFT				15
+#define  PCIE_EXT_FUNC_SHIFT				12
+
+#define PCIE_RGR1_SW_INIT_1				0x9210
+#define  PCIE_RGR1_SW_INIT_1_PERST_MASK			0x1
+#define  PCIE_RGR1_SW_INIT_1_INIT_MASK			0x2
+
+/* PCIe parameters */
+#define BRCM_NUM_PCIE_OUT_WINS		0x4
+#define BRCM_INT_PCI_MSI_NR		32
+
+/* MSI target adresses */
+#define BRCM_MSI_TARGET_ADDR_LT_4GB	0x0fffffffcULL
+#define BRCM_MSI_TARGET_ADDR_GT_4GB	0xffffffffcULL
+
+/* MDIO registers */
+#define MDIO_PORT0			0x0
+#define MDIO_DATA_MASK			0x7fffffff
+#define MDIO_PORT_MASK			0xf0000
+#define MDIO_REGAD_MASK			0xffff
+#define MDIO_CMD_MASK			0xfff00000
+#define MDIO_CMD_READ			0x1
+#define MDIO_CMD_WRITE			0x0
+#define MDIO_DATA_DONE_MASK		0x80000000
+#define MDIO_RD_DONE(x)			(((x) & MDIO_DATA_DONE_MASK) ? 1 : 0)
+#define MDIO_WT_DONE(x)			(((x) & MDIO_DATA_DONE_MASK) ? 0 : 1)
+#define SSC_REGS_ADDR			0x1100
+#define SET_ADDR_OFFSET			0x1f
+#define SSC_CNTL_OFFSET			0x2
+#define SSC_CNTL_OVRD_EN_MASK		0x8000
+#define SSC_CNTL_OVRD_VAL_MASK		0x4000
+#define SSC_STATUS_OFFSET		0x1
+#define SSC_STATUS_SSC_MASK		0x400
+#define SSC_STATUS_PLL_LOCK_MASK	0x800
+
+struct brcm_msi {
+	struct device		*dev;
+	void __iomem		*base;
+	struct device_node	*np;
+	struct irq_domain	*msi_domain;
+	struct irq_domain	*inner_domain;
+	struct mutex		lock; /* guards the alloc/free operations */
+	u64			target_addr;
+	int			irq;
+	/* used indicates which MSI interrupts have been alloc'd */
+	unsigned long		used;
+};
+
+/* Internal PCIe Host Controller Information.*/
+struct brcm_pcie {
+	struct device		*dev;
+	void __iomem		*base;
+	struct clk		*clk;
+	struct pci_bus		*root_bus;
+	struct device_node	*np;
+	bool			ssc;
+	int			gen;
+	u64			msi_target_addr;
+	struct brcm_msi		*msi;
+};
+
+/*
+ * This is to convert the size of the inbound "BAR" region to the
+ * non-linear values of PCIE_X_MISC_RC_BAR[123]_CONFIG_LO.SIZE
+ */
+static int brcm_pcie_encode_ibar_size(u64 size)
+{
+	int log2_in = ilog2(size);
+
+	if (log2_in >= 12 && log2_in <= 15)
+		/* Covers 4KB to 32KB (inclusive) */
+		return (log2_in - 12) + 0x1c;
+	else if (log2_in >= 16 && log2_in <= 35)
+		/* Covers 64KB to 32GB, (inclusive) */
+		return log2_in - 15;
+	/* Something is awry so disable */
+	return 0;
+}
+
+static u32 brcm_pcie_mdio_form_pkt(int port, int regad, int cmd)
+{
+	u32 pkt = 0;
+
+	pkt |= FIELD_PREP(MDIO_PORT_MASK, port);
+	pkt |= FIELD_PREP(MDIO_REGAD_MASK, regad);
+	pkt |= FIELD_PREP(MDIO_CMD_MASK, cmd);
+
+	return pkt;
+}
+
+/* negative return value indicates error */
+static int brcm_pcie_mdio_read(void __iomem *base, u8 port, u8 regad, u32 *val)
+{
+	int tries;
+	u32 data;
+
+	writel(brcm_pcie_mdio_form_pkt(port, regad, MDIO_CMD_READ),
+		   base + PCIE_RC_DL_MDIO_ADDR);
+	readl(base + PCIE_RC_DL_MDIO_ADDR);
+
+	data = readl(base + PCIE_RC_DL_MDIO_RD_DATA);
+	for (tries = 0; !MDIO_RD_DONE(data) && tries < 10; tries++) {
+		udelay(10);
+		data = readl(base + PCIE_RC_DL_MDIO_RD_DATA);
+	}
+
+	*val = FIELD_GET(MDIO_DATA_MASK, data);
+	return MDIO_RD_DONE(data) ? 0 : -EIO;
+}
+
+/* negative return value indicates error */
+static int brcm_pcie_mdio_write(void __iomem *base, u8 port,
+				u8 regad, u16 wrdata)
+{
+	int tries;
+	u32 data;
+
+	writel(brcm_pcie_mdio_form_pkt(port, regad, MDIO_CMD_WRITE),
+		   base + PCIE_RC_DL_MDIO_ADDR);
+	readl(base + PCIE_RC_DL_MDIO_ADDR);
+	writel(MDIO_DATA_DONE_MASK | wrdata, base + PCIE_RC_DL_MDIO_WR_DATA);
+
+	data = readl(base + PCIE_RC_DL_MDIO_WR_DATA);
+	for (tries = 0; !MDIO_WT_DONE(data) && tries < 10; tries++) {
+		udelay(10);
+		data = readl(base + PCIE_RC_DL_MDIO_WR_DATA);
+	}
+
+	return MDIO_WT_DONE(data) ? 0 : -EIO;
+}
+
+/*
+ * Configures device for Spread Spectrum Clocking (SSC) mode; a negative
+ * return value indicates error.
+ */
+static int brcm_pcie_set_ssc(struct brcm_pcie *pcie)
+{
+	int pll, ssc;
+	int ret;
+	u32 tmp;
+
+	ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, SET_ADDR_OFFSET,
+				   SSC_REGS_ADDR);
+	if (ret < 0)
+		return ret;
+
+	ret = brcm_pcie_mdio_read(pcie->base, MDIO_PORT0,
+				  SSC_CNTL_OFFSET, &tmp);
+	if (ret < 0)
+		return ret;
+
+	u32p_replace_bits(&tmp, 1, SSC_CNTL_OVRD_EN_MASK);
+	u32p_replace_bits(&tmp, 1, SSC_CNTL_OVRD_VAL_MASK);
+	ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0,
+				   SSC_CNTL_OFFSET, tmp);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(1000, 2000);
+	ret = brcm_pcie_mdio_read(pcie->base, MDIO_PORT0,
+				  SSC_STATUS_OFFSET, &tmp);
+	if (ret < 0)
+		return ret;
+
+	ssc = FIELD_GET(SSC_STATUS_SSC_MASK, tmp);
+	pll = FIELD_GET(SSC_STATUS_PLL_LOCK_MASK, tmp);
+
+	return ssc && pll ? 0 : -EIO;
+}
+
+/* Limits operation to a specific generation (1, 2, or 3) */
+static void brcm_pcie_set_gen(struct brcm_pcie *pcie, int gen)
+{
+	u16 lnkctl2 = readw(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2);
+	u32 lnkcap = readl(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP);
+
+	lnkcap = (lnkcap & ~PCI_EXP_LNKCAP_SLS) | gen;
+	writel(lnkcap, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP);
+
+	lnkctl2 = (lnkctl2 & ~0xf) | gen;
+	writew(lnkctl2, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2);
+}
+
+static void brcm_pcie_set_outbound_win(struct brcm_pcie *pcie,
+				       unsigned int win, u64 cpu_addr,
+				       u64 pcie_addr, u64 size)
+{
+	u32 cpu_addr_mb_high, limit_addr_mb_high;
+	phys_addr_t cpu_addr_mb, limit_addr_mb;
+	int high_addr_shift;
+	u32 tmp;
+
+	/* Set the base of the pcie_addr window */
+	writel(lower_32_bits(pcie_addr), pcie->base + PCIE_MEM_WIN0_LO(win));
+	writel(upper_32_bits(pcie_addr), pcie->base + PCIE_MEM_WIN0_HI(win));
+
+	/* Write the addr base & limit lower bits (in MBs) */
+	cpu_addr_mb = cpu_addr / SZ_1M;
+	limit_addr_mb = (cpu_addr + size - 1) / SZ_1M;
+
+	tmp = readl(pcie->base + PCIE_MEM_WIN0_BASE_LIMIT(win));
+	u32p_replace_bits(&tmp, cpu_addr_mb,
+			  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK);
+	u32p_replace_bits(&tmp, limit_addr_mb,
+			  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK);
+	writel(tmp, pcie->base + PCIE_MEM_WIN0_BASE_LIMIT(win));
+
+	/* Write the cpu & limit addr upper bits */
+	high_addr_shift =
+		HWEIGHT32(PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK);
+
+	cpu_addr_mb_high = cpu_addr_mb >> high_addr_shift;
+	tmp = readl(pcie->base + PCIE_MEM_WIN0_BASE_HI(win));
+	u32p_replace_bits(&tmp, cpu_addr_mb_high,
+			  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK);
+	writel(tmp, pcie->base + PCIE_MEM_WIN0_BASE_HI(win));
+
+	limit_addr_mb_high = limit_addr_mb >> high_addr_shift;
+	tmp = readl(pcie->base + PCIE_MEM_WIN0_LIMIT_HI(win));
+	u32p_replace_bits(&tmp, limit_addr_mb_high,
+			  PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK);
+	writel(tmp, pcie->base + PCIE_MEM_WIN0_LIMIT_HI(win));
+}
+
+static struct irq_chip brcm_msi_irq_chip = {
+	.name            = "BRCM STB PCIe MSI",
+	.irq_ack         = irq_chip_ack_parent,
+	.irq_mask        = pci_msi_mask_irq,
+	.irq_unmask      = pci_msi_unmask_irq,
+};
+
+static struct msi_domain_info brcm_msi_domain_info = {
+	/* Multi MSI is supported by the controller, but not by this driver */
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS),
+	.chip	= &brcm_msi_irq_chip,
+};
+
+static void brcm_pcie_msi_isr(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned long status, virq;
+	struct brcm_msi *msi;
+	struct device *dev;
+	u32 bit;
+
+	chained_irq_enter(chip, desc);
+	msi = irq_desc_get_handler_data(desc);
+	dev = msi->dev;
+
+	status = readl(msi->base + PCIE_MSI_INTR2_STATUS);
+	for_each_set_bit(bit, &status, BRCM_INT_PCI_MSI_NR) {
+		virq = irq_find_mapping(msi->inner_domain, bit);
+		if (virq)
+			generic_handle_irq(virq);
+		else
+			dev_dbg(dev, "unexpected MSI\n");
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void brcm_msi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct brcm_msi *msi = irq_data_get_irq_chip_data(data);
+
+	msg->address_lo = lower_32_bits(msi->target_addr);
+	msg->address_hi = upper_32_bits(msi->target_addr);
+	msg->data = (0xffff & PCIE_MISC_MSI_DATA_CONFIG_VAL) | data->hwirq;
+}
+
+static int brcm_msi_set_affinity(struct irq_data *irq_data,
+				 const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
+}
+
+static void brcm_msi_ack_irq(struct irq_data *data)
+{
+	struct brcm_msi *msi = irq_data_get_irq_chip_data(data);
+
+	writel(1 << data->hwirq, msi->base + PCIE_MSI_INTR2_CLR);
+}
+
+
+static struct irq_chip brcm_msi_bottom_irq_chip = {
+	.name			= "BRCM STB MSI",
+	.irq_compose_msi_msg	= brcm_msi_compose_msi_msg,
+	.irq_set_affinity	= brcm_msi_set_affinity,
+	.irq_ack                = brcm_msi_ack_irq,
+};
+
+static int brcm_msi_alloc(struct brcm_msi *msi)
+{
+	int hwirq;
+
+	mutex_lock(&msi->lock);
+	hwirq = bitmap_find_free_region(&msi->used, BRCM_INT_PCI_MSI_NR, 0);
+	mutex_unlock(&msi->lock);
+
+	return hwirq;
+}
+
+static void brcm_msi_free(struct brcm_msi *msi, unsigned long hwirq)
+{
+	mutex_lock(&msi->lock);
+	bitmap_release_region(&msi->used, hwirq, 0);
+	mutex_unlock(&msi->lock);
+}
+
+static int brcm_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs, void *args)
+{
+	struct brcm_msi *msi = domain->host_data;
+	int hwirq;
+
+	hwirq = brcm_msi_alloc(msi);
+
+	if (hwirq < 0)
+		return hwirq;
+
+	irq_domain_set_info(domain, virq, (irq_hw_number_t)hwirq,
+			    &brcm_msi_bottom_irq_chip, domain->host_data,
+			    handle_edge_irq, NULL, NULL);
+	return 0;
+}
+
+static void brcm_irq_domain_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct brcm_msi *msi = irq_data_get_irq_chip_data(d);
+
+	brcm_msi_free(msi, d->hwirq);
+}
+
+static const struct irq_domain_ops msi_domain_ops = {
+	.alloc	= brcm_irq_domain_alloc,
+	.free	= brcm_irq_domain_free,
+};
+
+static int brcm_allocate_domains(struct brcm_msi *msi)
+{
+	struct fwnode_handle *fwnode = of_node_to_fwnode(msi->np);
+	struct device *dev = msi->dev;
+
+	msi->inner_domain = irq_domain_add_linear(NULL, BRCM_INT_PCI_MSI_NR,
+						  &msi_domain_ops, msi);
+	if (!msi->inner_domain) {
+		dev_err(dev, "failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	msi->msi_domain = pci_msi_create_irq_domain(fwnode,
+						    &brcm_msi_domain_info,
+						    msi->inner_domain);
+	if (!msi->msi_domain) {
+		dev_err(dev, "failed to create MSI domain\n");
+		irq_domain_remove(msi->inner_domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void brcm_free_domains(struct brcm_msi *msi)
+{
+	irq_domain_remove(msi->msi_domain);
+	irq_domain_remove(msi->inner_domain);
+}
+
+static void brcm_msi_remove(struct brcm_pcie *pcie)
+{
+	struct brcm_msi *msi = pcie->msi;
+
+	if (!msi)
+		return;
+	irq_set_chained_handler(msi->irq, NULL);
+	irq_set_handler_data(msi->irq, NULL);
+	brcm_free_domains(msi);
+}
+
+static void brcm_msi_set_regs(struct brcm_msi *msi)
+{
+	writel(0xffffffff, msi->base + PCIE_MSI_INTR2_MASK_CLR);
+
+	/*
+	 * The 0 bit of PCIE_MISC_MSI_BAR_CONFIG_LO is repurposed to MSI
+	 * enable, which we set to 1.
+	 */
+	writel(lower_32_bits(msi->target_addr) | 0x1,
+	       msi->base + PCIE_MISC_MSI_BAR_CONFIG_LO);
+	writel(upper_32_bits(msi->target_addr),
+	       msi->base + PCIE_MISC_MSI_BAR_CONFIG_HI);
+
+	writel(PCIE_MISC_MSI_DATA_CONFIG_VAL,
+	       msi->base + PCIE_MISC_MSI_DATA_CONFIG);
+}
+
+static int brcm_pcie_enable_msi(struct brcm_pcie *pcie)
+{
+	struct brcm_msi *msi;
+	int irq, ret;
+	struct device *dev = pcie->dev;
+
+	irq = irq_of_parse_and_map(dev->of_node, 1);
+	if (irq <= 0) {
+		dev_err(dev, "cannot map MSI interrupt\n");
+		return -ENODEV;
+	}
+
+	msi = devm_kzalloc(dev, sizeof(struct brcm_msi), GFP_KERNEL);
+	if (!msi)
+		return -ENOMEM;
+
+	mutex_init(&msi->lock);
+	msi->dev = dev;
+	msi->base = pcie->base;
+	msi->np = pcie->np;
+	msi->target_addr = pcie->msi_target_addr;
+	msi->irq = irq;
+
+	ret = brcm_allocate_domains(msi);
+	if (ret)
+		return ret;
+
+	irq_set_chained_handler_and_data(msi->irq, brcm_pcie_msi_isr, msi);
+
+	brcm_msi_set_regs(msi);
+	pcie->msi = msi;
+
+	return 0;
+}
+
+/* The controller is capable of serving in both RC and EP roles */
+static bool brcm_pcie_rc_mode(struct brcm_pcie *pcie)
+{
+	void __iomem *base = pcie->base;
+	u32 val = readl(base + PCIE_MISC_PCIE_STATUS);
+
+	return !!FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK, val);
+}
+
+static bool brcm_pcie_link_up(struct brcm_pcie *pcie)
+{
+	u32 val = readl(pcie->base + PCIE_MISC_PCIE_STATUS);
+	u32 dla = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK, val);
+	u32 plu = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK, val);
+
+	return dla && plu;
+}
+
+/* Configuration space read/write support */
+static inline int brcm_pcie_cfg_index(int busnr, int devfn, int reg)
+{
+	return ((PCI_SLOT(devfn) & 0x1f) << PCIE_EXT_SLOT_SHIFT)
+		| ((PCI_FUNC(devfn) & 0x07) << PCIE_EXT_FUNC_SHIFT)
+		| (busnr << PCIE_EXT_BUSNUM_SHIFT)
+		| (reg & ~3);
+}
+
+static void __iomem *brcm_pcie_map_conf(struct pci_bus *bus, unsigned int devfn,
+					int where)
+{
+	struct brcm_pcie *pcie = bus->sysdata;
+	void __iomem *base = pcie->base;
+	int idx;
+
+	/* Accesses to the RC go right to the RC registers if slot==0 */
+	if (pci_is_root_bus(bus))
+		return PCI_SLOT(devfn) ? NULL : base + where;
+
+	/* For devices, write to the config space index register */
+	idx = brcm_pcie_cfg_index(bus->number, devfn, 0);
+	writel(idx, pcie->base + PCIE_EXT_CFG_INDEX);
+	return base + PCIE_EXT_CFG_DATA + where;
+}
+
+static struct pci_ops brcm_pcie_ops = {
+	.map_bus = brcm_pcie_map_conf,
+	.read = pci_generic_config_read,
+	.write = pci_generic_config_write,
+};
+
+static inline void brcm_pcie_bridge_sw_init_set(struct brcm_pcie *pcie, u32 val)
+{
+	u32 tmp;
+
+	tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1);
+	u32p_replace_bits(&tmp, val, PCIE_RGR1_SW_INIT_1_INIT_MASK);
+	writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1);
+}
+
+static inline void brcm_pcie_perst_set(struct brcm_pcie *pcie, u32 val)
+{
+	u32 tmp;
+
+	tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1);
+	u32p_replace_bits(&tmp, val, PCIE_RGR1_SW_INIT_1_PERST_MASK);
+	writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1);
+}
+
+static inline int brcm_pcie_get_rc_bar2_size_and_offset(struct brcm_pcie *pcie,
+							u64 *rc_bar2_size,
+							u64 *rc_bar2_offset)
+{
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
+	struct device *dev = pcie->dev;
+	struct resource_entry *entry;
+
+	entry = resource_list_first_type(&bridge->dma_ranges, IORESOURCE_MEM);
+	if (!entry)
+		return -ENODEV;
+
+
+	/*
+	 * The controller expects the inbound window offset to be calculated as
+	 * the difference between PCIe's address space and CPU's. The offset
+	 * provided by the firmware is calculated the opposite way, so we
+	 * negate it.
+	 */
+	*rc_bar2_offset = -entry->offset;
+	*rc_bar2_size = 1ULL << fls64(entry->res->end - entry->res->start);
+
+	/*
+	 * We validate the inbound memory view even though we should trust
+	 * whatever the device-tree provides. This is because of an HW issue on
+	 * early Raspberry Pi 4's revisions (bcm2711). It turns out its
+	 * firmware has to dynamically edit dma-ranges due to a bug on the
+	 * PCIe controller integration, which prohibits any access above the
+	 * lower 3GB of memory. Given this, we decided to keep the dma-ranges
+	 * in check, avoiding hard to debug device-tree related issues in the
+	 * future:
+	 *
+	 * The PCIe host controller by design must set the inbound viewport to
+	 * be a contiguous arrangement of all of the system's memory.  In
+	 * addition, its size mut be a power of two.  To further complicate
+	 * matters, the viewport must start on a pcie-address that is aligned
+	 * on a multiple of its size.  If a portion of the viewport does not
+	 * represent system memory -- e.g. 3GB of memory requires a 4GB
+	 * viewport -- we can map the outbound memory in or after 3GB and even
+	 * though the viewport will overlap the outbound memory the controller
+	 * will know to send outbound memory downstream and everything else
+	 * upstream.
+	 *
+	 * For example:
+	 *
+	 * - The best-case scenario, memory up to 3GB, is to place the inbound
+	 *   region in the first 4GB of pcie-space, as some legacy devices can
+	 *   only address 32bits. We would also like to put the MSI under 4GB
+	 *   as well, since some devices require a 32bit MSI target address.
+	 *
+	 * - If the system memory is 4GB or larger we cannot start the inbound
+	 *   region at location 0 (since we have to allow some space for
+	 *   outbound memory @ 3GB). So instead it will  start at the 1x
+	 *   multiple of its size
+	 */
+	if (!*rc_bar2_size || *rc_bar2_offset % *rc_bar2_size ||
+	    (*rc_bar2_offset < SZ_4G && *rc_bar2_offset > SZ_2G)) {
+		dev_err(dev, "Invalid rc_bar2_offset/size: size 0x%llx, off 0x%llx\n",
+			*rc_bar2_size, *rc_bar2_offset);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int brcm_pcie_setup(struct brcm_pcie *pcie)
+{
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
+	u64 rc_bar2_offset, rc_bar2_size;
+	void __iomem *base = pcie->base;
+	struct device *dev = pcie->dev;
+	struct resource_entry *entry;
+	unsigned int scb_size_val;
+	bool ssc_good = false;
+	struct resource *res;
+	int num_out_wins = 0;
+	u16 nlw, cls, lnksta;
+	int i, ret;
+	u32 tmp;
+
+	/* Reset the bridge */
+	brcm_pcie_bridge_sw_init_set(pcie, 1);
+
+	usleep_range(100, 200);
+
+	/* Take the bridge out of reset */
+	brcm_pcie_bridge_sw_init_set(pcie, 0);
+
+	tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+	tmp &= ~PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK;
+	writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+	/* Wait for SerDes to be stable */
+	usleep_range(100, 200);
+
+	/* Set SCB_MAX_BURST_SIZE, CFG_READ_UR_MODE, SCB_ACCESS_EN */
+	u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK);
+	u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK);
+	u32p_replace_bits(&tmp, PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_128,
+			  PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK);
+	writel(tmp, base + PCIE_MISC_MISC_CTRL);
+
+	ret = brcm_pcie_get_rc_bar2_size_and_offset(pcie, &rc_bar2_size,
+						    &rc_bar2_offset);
+	if (ret)
+		return ret;
+
+	tmp = lower_32_bits(rc_bar2_offset);
+	u32p_replace_bits(&tmp, brcm_pcie_encode_ibar_size(rc_bar2_size),
+			  PCIE_MISC_RC_BAR2_CONFIG_LO_SIZE_MASK);
+	writel(tmp, base + PCIE_MISC_RC_BAR2_CONFIG_LO);
+	writel(upper_32_bits(rc_bar2_offset),
+	       base + PCIE_MISC_RC_BAR2_CONFIG_HI);
+
+	scb_size_val = rc_bar2_size ?
+		       ilog2(rc_bar2_size) - 15 : 0xf; /* 0xf is 1GB */
+	tmp = readl(base + PCIE_MISC_MISC_CTRL);
+	u32p_replace_bits(&tmp, scb_size_val,
+			  PCIE_MISC_MISC_CTRL_SCB0_SIZE_MASK);
+	writel(tmp, base + PCIE_MISC_MISC_CTRL);
+
+	/*
+	 * We ideally want the MSI target address to be located in the 32bit
+	 * addressable memory area. Some devices might depend on it. This is
+	 * possible either when the inbound window is located above the lower
+	 * 4GB or when the inbound area is smaller than 4GB (taking into
+	 * account the rounding-up we're forced to perform).
+	 */
+	if (rc_bar2_offset >= SZ_4G || (rc_bar2_size + rc_bar2_offset) < SZ_4G)
+		pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_LT_4GB;
+	else
+		pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_GT_4GB;
+
+	/* disable the PCIe->GISB memory window (RC_BAR1) */
+	tmp = readl(base + PCIE_MISC_RC_BAR1_CONFIG_LO);
+	tmp &= ~PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK;
+	writel(tmp, base + PCIE_MISC_RC_BAR1_CONFIG_LO);
+
+	/* disable the PCIe->SCB memory window (RC_BAR3) */
+	tmp = readl(base + PCIE_MISC_RC_BAR3_CONFIG_LO);
+	tmp &= ~PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_MASK;
+	writel(tmp, base + PCIE_MISC_RC_BAR3_CONFIG_LO);
+
+	/* Mask all interrupts since we are not handling any yet */
+	writel(0xffffffff, pcie->base + PCIE_MSI_INTR2_MASK_SET);
+
+	/* clear any interrupts we find on boot */
+	writel(0xffffffff, pcie->base + PCIE_MSI_INTR2_CLR);
+
+	if (pcie->gen)
+		brcm_pcie_set_gen(pcie, pcie->gen);
+
+	/* Unassert the fundamental reset */
+	brcm_pcie_perst_set(pcie, 0);
+
+	/*
+	 * Give the RC/EP time to wake up, before trying to configure RC.
+	 * Intermittently check status for link-up, up to a total of 100ms.
+	 */
+	for (i = 0; i < 100 && !brcm_pcie_link_up(pcie); i += 5)
+		msleep(5);
+
+	if (!brcm_pcie_link_up(pcie)) {
+		dev_err(dev, "link down\n");
+		return -ENODEV;
+	}
+
+	if (!brcm_pcie_rc_mode(pcie)) {
+		dev_err(dev, "PCIe misconfigured; is in EP mode\n");
+		return -EINVAL;
+	}
+
+	resource_list_for_each_entry(entry, &bridge->windows) {
+		res = entry->res;
+
+		if (resource_type(res) != IORESOURCE_MEM)
+			continue;
+
+		if (num_out_wins >= BRCM_NUM_PCIE_OUT_WINS) {
+			dev_err(pcie->dev, "too many outbound wins\n");
+			return -EINVAL;
+		}
+
+		brcm_pcie_set_outbound_win(pcie, num_out_wins, res->start,
+					   res->start - entry->offset,
+					   resource_size(res));
+		num_out_wins++;
+	}
+
+	/*
+	 * For config space accesses on the RC, show the right class for
+	 * a PCIe-PCIe bridge (the default setting is to be EP mode).
+	 */
+	tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3);
+	u32p_replace_bits(&tmp, 0x060400,
+			  PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK);
+	writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3);
+
+	if (pcie->ssc) {
+		ret = brcm_pcie_set_ssc(pcie);
+		if (ret == 0)
+			ssc_good = true;
+		else
+			dev_err(dev, "failed attempt to enter ssc mode\n");
+	}
+
+	lnksta = readw(base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKSTA);
+	cls = FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta);
+	nlw = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta);
+	dev_info(dev, "link up, %s x%u %s\n",
+		 PCIE_SPEED2STR(cls + PCI_SPEED_133MHz_PCIX_533),
+		 nlw, ssc_good ? "(SSC)" : "(!SSC)");
+
+	/* PCIe->SCB endian mode for BAR */
+	tmp = readl(base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1);
+	u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN,
+		PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK);
+	writel(tmp, base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1);
+
+	/*
+	 * Refclk from RC should be gated with CLKREQ# input when ASPM L0s,L1
+	 * is enabled => setting the CLKREQ_DEBUG_ENABLE field to 1.
+	 */
+	tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+	tmp |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK;
+	writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+
+	return 0;
+}
+
+/* L23 is a low-power PCIe link state */
+static void brcm_pcie_enter_l23(struct brcm_pcie *pcie)
+{
+	void __iomem *base = pcie->base;
+	int l23, i;
+	u32 tmp;
+
+	/* Assert request for L23 */
+	tmp = readl(base + PCIE_MISC_PCIE_CTRL);
+	u32p_replace_bits(&tmp, 1, PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK);
+	writel(tmp, base + PCIE_MISC_PCIE_CTRL);
+
+	/* Wait up to 36 msec for L23 */
+	tmp = readl(base + PCIE_MISC_PCIE_STATUS);
+	l23 = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK, tmp);
+	for (i = 0; i < 15 && !l23; i++) {
+		usleep_range(2000, 2400);
+		tmp = readl(base + PCIE_MISC_PCIE_STATUS);
+		l23 = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK,
+				tmp);
+	}
+
+	if (!l23)
+		dev_err(pcie->dev, "failed to enter low-power link state\n");
+}
+
+static void brcm_pcie_turn_off(struct brcm_pcie *pcie)
+{
+	void __iomem *base = pcie->base;
+	int tmp;
+
+	if (brcm_pcie_link_up(pcie))
+		brcm_pcie_enter_l23(pcie);
+	/* Assert fundamental reset */
+	brcm_pcie_perst_set(pcie, 1);
+
+	/* Deassert request for L23 in case it was asserted */
+	tmp = readl(base + PCIE_MISC_PCIE_CTRL);
+	u32p_replace_bits(&tmp, 0, PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK);
+	writel(tmp, base + PCIE_MISC_PCIE_CTRL);
+
+	/* Turn off SerDes */
+	tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+	u32p_replace_bits(&tmp, 1, PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK);
+	writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG);
+
+	/* Shutdown PCIe bridge */
+	brcm_pcie_bridge_sw_init_set(pcie, 1);
+}
+
+static void __brcm_pcie_remove(struct brcm_pcie *pcie)
+{
+	brcm_msi_remove(pcie);
+	brcm_pcie_turn_off(pcie);
+	clk_disable_unprepare(pcie->clk);
+	clk_put(pcie->clk);
+}
+
+static int brcm_pcie_remove(struct platform_device *pdev)
+{
+	struct brcm_pcie *pcie = platform_get_drvdata(pdev);
+
+	pci_stop_root_bus(pcie->root_bus);
+	pci_remove_root_bus(pcie->root_bus);
+	__brcm_pcie_remove(pcie);
+
+	return 0;
+}
+
+static int brcm_pcie_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node, *msi_np;
+	struct pci_host_bridge *bridge;
+	struct brcm_pcie *pcie;
+	struct pci_bus *child;
+	struct resource *res;
+	int ret;
+
+	bridge = devm_pci_alloc_host_bridge(&pdev->dev, sizeof(*pcie));
+	if (!bridge)
+		return -ENOMEM;
+
+	pcie = pci_host_bridge_priv(bridge);
+	pcie->dev = &pdev->dev;
+	pcie->np = np;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pcie->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(pcie->base))
+		return PTR_ERR(pcie->base);
+
+	pcie->clk = devm_clk_get_optional(&pdev->dev, "sw_pcie");
+	if (IS_ERR(pcie->clk))
+		return PTR_ERR(pcie->clk);
+
+	ret = of_pci_get_max_link_speed(np);
+	pcie->gen = (ret < 0) ? 0 : ret;
+
+	pcie->ssc = of_property_read_bool(np, "brcm,enable-ssc");
+
+	ret = pci_parse_request_of_pci_ranges(pcie->dev, &bridge->windows,
+					      &bridge->dma_ranges, NULL);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(pcie->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "could not enable clock\n");
+		return ret;
+	}
+
+	ret = brcm_pcie_setup(pcie);
+	if (ret)
+		goto fail;
+
+	msi_np = of_parse_phandle(pcie->np, "msi-parent", 0);
+	if (pci_msi_enabled() && msi_np == pcie->np) {
+		ret = brcm_pcie_enable_msi(pcie);
+		if (ret) {
+			dev_err(pcie->dev, "probe of internal MSI failed");
+			goto fail;
+		}
+	}
+
+	bridge->dev.parent = &pdev->dev;
+	bridge->busnr = 0;
+	bridge->ops = &brcm_pcie_ops;
+	bridge->sysdata = pcie;
+	bridge->map_irq = of_irq_parse_and_map_pci;
+	bridge->swizzle_irq = pci_common_swizzle;
+
+	ret = pci_scan_root_bus_bridge(bridge);
+	if (ret < 0) {
+		dev_err(pcie->dev, "Scanning root bridge failed\n");
+		goto fail;
+	}
+
+	pci_assign_unassigned_bus_resources(bridge->bus);
+	list_for_each_entry(child, &bridge->bus->children, node)
+		pcie_bus_configure_settings(child);
+	pci_bus_add_devices(bridge->bus);
+	platform_set_drvdata(pdev, pcie);
+	pcie->root_bus = bridge->bus;
+
+	return 0;
+fail:
+	__brcm_pcie_remove(pcie);
+	return ret;
+}
+
+static const struct of_device_id brcm_pcie_match[] = {
+	{ .compatible = "brcm,bcm2711-pcie" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, brcm_pcie_match);
+
+static struct platform_driver brcm_pcie_driver = {
+	.probe = brcm_pcie_probe,
+	.remove = brcm_pcie_remove,
+	.driver = {
+		.name = "brcm-pcie",
+		.of_match_table = brcm_pcie_match,
+	},
+};
+module_platform_driver(brcm_pcie_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Broadcom STB PCIe RC driver");
+MODULE_AUTHOR("Broadcom");
diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 0a468c73bae3..8c7f875acf7f 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -1588,6 +1588,30 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802,
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804,
 			quirk_paxc_disable_msi_parsing);
 
+static void quirk_paxc_bridge(struct pci_dev *pdev)
+{
+	/*
+	 * The PCI config space is shared with the PAXC root port and the first
+	 * Ethernet device.  So, we need to workaround this by telling the PCI
+	 * code that the bridge is not an Ethernet device.
+	 */
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		pdev->class = PCI_CLASS_BRIDGE_PCI << 8;
+
+	/*
+	 * MPSS is not being set properly (as it is currently 0).  This is
+	 * because that area of the PCI config space is hard coded to zero, and
+	 * is not modifiable by firmware.  Set this to 2 (e.g., 512 byte MPS)
+	 * so that the MPS can be set to the real max value.
+	 */
+	pdev->pcie_mpss = 2;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge);
+
 MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>");
 MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 212842263f55..dac91d60701d 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -98,9 +98,6 @@ struct vmd_dev {
 	struct irq_domain	*irq_domain;
 	struct pci_bus		*bus;
 	u8			busn_start;
-
-	struct dma_map_ops	dma_ops;
-	struct dma_domain	dma_domain;
 };
 
 static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -295,151 +292,6 @@ static struct msi_domain_info vmd_msi_domain_info = {
 	.chip		= &vmd_msi_controller,
 };
 
-/*
- * VMD replaces the requester ID with its own.  DMA mappings for devices in a
- * VMD domain need to be mapped for the VMD, not the device requiring
- * the mapping.
- */
-static struct device *to_vmd_dev(struct device *dev)
-{
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct vmd_dev *vmd = vmd_from_bus(pdev->bus);
-
-	return &vmd->dev->dev;
-}
-
-static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
-		       gfp_t flag, unsigned long attrs)
-{
-	return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
-}
-
-static void vmd_free(struct device *dev, size_t size, void *vaddr,
-		     dma_addr_t addr, unsigned long attrs)
-{
-	return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
-}
-
-static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
-		    void *cpu_addr, dma_addr_t addr, size_t size,
-		    unsigned long attrs)
-{
-	return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
-			attrs);
-}
-
-static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
-			   void *cpu_addr, dma_addr_t addr, size_t size,
-			   unsigned long attrs)
-{
-	return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
-			attrs);
-}
-
-static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
-			       unsigned long offset, size_t size,
-			       enum dma_data_direction dir,
-			       unsigned long attrs)
-{
-	return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir,
-			attrs);
-}
-
-static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
-			   enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs);
-}
-
-static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		      enum dma_data_direction dir, unsigned long attrs)
-{
-	return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-			 enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
-}
-
-static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-				    size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
-				       size_t size, enum dma_data_direction dir)
-{
-	dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir);
-}
-
-static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir)
-{
-	dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir)
-{
-	dma_sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static int vmd_dma_supported(struct device *dev, u64 mask)
-{
-	return dma_supported(to_vmd_dev(dev), mask);
-}
-
-static u64 vmd_get_required_mask(struct device *dev)
-{
-	return dma_get_required_mask(to_vmd_dev(dev));
-}
-
-static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
-{
-	struct dma_domain *domain = &vmd->dma_domain;
-
-	if (get_dma_ops(&vmd->dev->dev))
-		del_dma_domain(domain);
-}
-
-#define ASSIGN_VMD_DMA_OPS(source, dest, fn)	\
-	do {					\
-		if (source->fn)			\
-			dest->fn = vmd_##fn;	\
-	} while (0)
-
-static void vmd_setup_dma_ops(struct vmd_dev *vmd)
-{
-	const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev);
-	struct dma_map_ops *dest = &vmd->dma_ops;
-	struct dma_domain *domain = &vmd->dma_domain;
-
-	domain->domain_nr = vmd->sysdata.domain;
-	domain->dma_ops = dest;
-
-	if (!source)
-		return;
-	ASSIGN_VMD_DMA_OPS(source, dest, alloc);
-	ASSIGN_VMD_DMA_OPS(source, dest, free);
-	ASSIGN_VMD_DMA_OPS(source, dest, mmap);
-	ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable);
-	ASSIGN_VMD_DMA_OPS(source, dest, map_page);
-	ASSIGN_VMD_DMA_OPS(source, dest, unmap_page);
-	ASSIGN_VMD_DMA_OPS(source, dest, map_sg);
-	ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu);
-	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device);
-	ASSIGN_VMD_DMA_OPS(source, dest, dma_supported);
-	ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask);
-	add_dma_domain(domain);
-}
-#undef ASSIGN_VMD_DMA_OPS
-
 static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
 				  unsigned int devfn, int reg, int len)
 {
@@ -679,7 +531,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 		.parent = res,
 	};
 
-	sd->vmd_domain = true;
+	sd->vmd_dev = vmd->dev;
 	sd->domain = vmd_find_free_domain();
 	if (sd->domain < 0)
 		return sd->domain;
@@ -709,7 +561,6 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 	}
 
 	vmd_attach_resources(vmd);
-	vmd_setup_dma_ops(vmd);
 	dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain);
 
 	pci_scan_child_bus(vmd->bus);
@@ -824,7 +675,6 @@ static void vmd_remove(struct pci_dev *dev)
 	pci_stop_root_bus(vmd->bus);
 	pci_remove_root_bus(vmd->bus);
 	vmd_cleanup_srcu(vmd);
-	vmd_teardown_dma_ops(vmd);
 	vmd_detach_resources(vmd);
 	irq_domain_remove(vmd->irq_domain);
 }
@@ -868,6 +718,10 @@ static const struct pci_device_id vmd_ids[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW |
 				VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f),
+		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c3d),
+		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B),
 		.driver_data = VMD_FEAT_HAS_BUS_RESTRICTIONS,},
 	{0,}
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index d7b2b47bc33e..04565162a449 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -18,6 +18,9 @@
 #define DRIVER_AUTHOR	"Gavin Shan, IBM Corporation"
 #define DRIVER_DESC	"PowerPC PowerNV PCI Hotplug Driver"
 
+#define SLOT_WARN(sl, x...) \
+	((sl)->pdev ? pci_warn((sl)->pdev, x) : dev_warn(&(sl)->bus->dev, x))
+
 struct pnv_php_event {
 	bool			added;
 	struct pnv_php_slot	*php_slot;
@@ -151,17 +154,11 @@ static void pnv_php_rmv_pdns(struct device_node *dn)
 static void pnv_php_detach_device_nodes(struct device_node *parent)
 {
 	struct device_node *dn;
-	int refcount;
 
 	for_each_child_of_node(parent, dn) {
 		pnv_php_detach_device_nodes(dn);
 
 		of_node_put(dn);
-		refcount = kref_read(&dn->kobj.kref);
-		if (refcount != 1)
-			pr_warn("Invalid refcount %d on <%pOF>\n",
-				refcount, dn);
-
 		of_detach_node(dn);
 	}
 }
@@ -271,7 +268,7 @@ static int pnv_php_add_devtree(struct pnv_php_slot *php_slot)
 
 	ret = pnv_pci_get_device_tree(php_slot->dn->phandle, fdt1, 0x10000);
 	if (ret) {
-		pci_warn(php_slot->pdev, "Error %d getting FDT blob\n", ret);
+		SLOT_WARN(php_slot, "Error %d getting FDT blob\n", ret);
 		goto free_fdt1;
 	}
 
@@ -285,7 +282,7 @@ static int pnv_php_add_devtree(struct pnv_php_slot *php_slot)
 	dt = of_fdt_unflatten_tree(fdt, php_slot->dn, NULL);
 	if (!dt) {
 		ret = -EINVAL;
-		pci_warn(php_slot->pdev, "Cannot unflatten FDT\n");
+		SLOT_WARN(php_slot, "Cannot unflatten FDT\n");
 		goto free_fdt;
 	}
 
@@ -295,15 +292,15 @@ static int pnv_php_add_devtree(struct pnv_php_slot *php_slot)
 	ret = pnv_php_populate_changeset(&php_slot->ocs, php_slot->dn);
 	if (ret) {
 		pnv_php_reverse_nodes(php_slot->dn);
-		pci_warn(php_slot->pdev, "Error %d populating changeset\n",
-			 ret);
+		SLOT_WARN(php_slot, "Error %d populating changeset\n",
+			  ret);
 		goto free_dt;
 	}
 
 	php_slot->dn->child = NULL;
 	ret = of_changeset_apply(&php_slot->ocs);
 	if (ret) {
-		pci_warn(php_slot->pdev, "Error %d applying changeset\n", ret);
+		SLOT_WARN(php_slot, "Error %d applying changeset\n", ret);
 		goto destroy_changeset;
 	}
 
@@ -342,18 +339,19 @@ int pnv_php_set_slot_power_state(struct hotplug_slot *slot,
 	ret = pnv_pci_set_power_state(php_slot->id, state, &msg);
 	if (ret > 0) {
 		if (be64_to_cpu(msg.params[1]) != php_slot->dn->phandle	||
-		    be64_to_cpu(msg.params[2]) != state			||
-		    be64_to_cpu(msg.params[3]) != OPAL_SUCCESS) {
-			pci_warn(php_slot->pdev, "Wrong msg (%lld, %lld, %lld)\n",
-				 be64_to_cpu(msg.params[1]),
-				 be64_to_cpu(msg.params[2]),
-				 be64_to_cpu(msg.params[3]));
+		    be64_to_cpu(msg.params[2]) != state) {
+			SLOT_WARN(php_slot, "Wrong msg (%lld, %lld, %lld)\n",
+				  be64_to_cpu(msg.params[1]),
+				  be64_to_cpu(msg.params[2]),
+				  be64_to_cpu(msg.params[3]));
 			return -ENOMSG;
 		}
+		if (be64_to_cpu(msg.params[3]) != OPAL_SUCCESS) {
+			ret = -ENODEV;
+			goto error;
+		}
 	} else if (ret < 0) {
-		pci_warn(php_slot->pdev, "Error %d powering %s\n",
-			 ret, (state == OPAL_PCI_SLOT_POWER_ON) ? "on" : "off");
-		return ret;
+		goto error;
 	}
 
 	if (state == OPAL_PCI_SLOT_POWER_OFF || state == OPAL_PCI_SLOT_OFFLINE)
@@ -362,6 +360,11 @@ int pnv_php_set_slot_power_state(struct hotplug_slot *slot,
 		ret = pnv_php_add_devtree(php_slot);
 
 	return ret;
+
+error:
+	SLOT_WARN(php_slot, "Error %d powering %s\n",
+		  ret, (state == OPAL_PCI_SLOT_POWER_ON) ? "on" : "off");
+	return ret;
 }
 EXPORT_SYMBOL_GPL(pnv_php_set_slot_power_state);
 
@@ -378,8 +381,8 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state)
 	 */
 	ret = pnv_pci_get_power_state(php_slot->id, &power_state);
 	if (ret) {
-		pci_warn(php_slot->pdev, "Error %d getting power status\n",
-			 ret);
+		SLOT_WARN(php_slot, "Error %d getting power status\n",
+			  ret);
 	} else {
 		*state = power_state;
 	}
@@ -402,7 +405,7 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 		*state = presence;
 		ret = 0;
 	} else {
-		pci_warn(php_slot->pdev, "Error %d getting presence\n", ret);
+		SLOT_WARN(php_slot, "Error %d getting presence\n", ret);
 	}
 
 	return ret;
@@ -566,7 +569,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot)
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
 	int ret;
 
-	if (php_slot->state != PNV_PHP_STATE_POPULATED)
+	/*
+	 * Allow to disable a slot already in the registered state to
+	 * cover cases where the slot couldn't be enabled and never
+	 * reached the populated state
+	 */
+	if (php_slot->state != PNV_PHP_STATE_POPULATED &&
+	    php_slot->state != PNV_PHP_STATE_REGISTERED)
 		return 0;
 
 	/* Remove all devices behind the slot */
@@ -675,7 +684,7 @@ static int pnv_php_register_slot(struct pnv_php_slot *php_slot)
 	ret = pci_hp_register(&php_slot->slot, php_slot->bus,
 			      php_slot->slot_no, php_slot->name);
 	if (ret) {
-		pci_warn(php_slot->pdev, "Error %d registering slot\n", ret);
+		SLOT_WARN(php_slot, "Error %d registering slot\n", ret);
 		return ret;
 	}
 
@@ -728,7 +737,7 @@ static int pnv_php_enable_msix(struct pnv_php_slot *php_slot)
 	/* Enable MSIx */
 	ret = pci_enable_msix_exact(pdev, &entry, 1);
 	if (ret) {
-		pci_warn(pdev, "Error %d enabling MSIx\n", ret);
+		SLOT_WARN(php_slot, "Error %d enabling MSIx\n", ret);
 		return ret;
 	}
 
@@ -778,8 +787,9 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data)
 		   (sts & PCI_EXP_SLTSTA_PDC)) {
 		ret = pnv_pci_get_presence_state(php_slot->id, &presence);
 		if (ret) {
-			pci_warn(pdev, "PCI slot [%s] error %d getting presence (0x%04x), to retry the operation.\n",
-				 php_slot->name, ret, sts);
+			SLOT_WARN(php_slot,
+				  "PCI slot [%s] error %d getting presence (0x%04x), to retry the operation.\n",
+				  php_slot->name, ret, sts);
 			return IRQ_HANDLED;
 		}
 
@@ -809,8 +819,9 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data)
 	 */
 	event = kzalloc(sizeof(*event), GFP_ATOMIC);
 	if (!event) {
-		pci_warn(pdev, "PCI slot [%s] missed hotplug event 0x%04x\n",
-			 php_slot->name, sts);
+		SLOT_WARN(php_slot,
+			  "PCI slot [%s] missed hotplug event 0x%04x\n",
+			  php_slot->name, sts);
 		return IRQ_HANDLED;
 	}
 
@@ -834,7 +845,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	/* Allocate workqueue */
 	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
 	if (!php_slot->wq) {
-		pci_warn(pdev, "Cannot alloc workqueue\n");
+		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
 		pnv_php_disable_irq(php_slot, true);
 		return;
 	}
@@ -858,7 +869,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 			  php_slot->name, php_slot);
 	if (ret) {
 		pnv_php_disable_irq(php_slot, true);
-		pci_warn(pdev, "Error %d enabling IRQ %d\n", ret, irq);
+		SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq);
 		return;
 	}
 
@@ -894,7 +905,7 @@ static void pnv_php_enable_irq(struct pnv_php_slot *php_slot)
 
 	ret = pci_enable_device(pdev);
 	if (ret) {
-		pci_warn(pdev, "Error %d enabling device\n", ret);
+		SLOT_WARN(php_slot, "Error %d enabling device\n", ret);
 		return;
 	}
 
@@ -1009,6 +1020,8 @@ static int __init pnv_php_init(void)
 	for_each_compatible_node(dn, NULL, "ibm,ioda3-phb")
 		pnv_php_register(dn);
 
+	for_each_compatible_node(dn, NULL, "ibm,ioda2-npu2-opencapi-phb")
+		pnv_php_register_one(dn); /* slot directly under the PHB */
 	return 0;
 }
 
@@ -1021,6 +1034,9 @@ static void __exit pnv_php_exit(void)
 
 	for_each_compatible_node(dn, NULL, "ibm,ioda3-phb")
 		pnv_php_unregister(dn);
+
+	for_each_compatible_node(dn, NULL, "ibm,ioda2-npu2-opencapi-phb")
+		pnv_php_unregister_one(dn); /* slot directly under the PHB */
 }
 
 module_init(pnv_php_init);
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 1e88fd427757..4d1f392b05f9 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -186,10 +186,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 	sprintf(buf, "virtfn%u", id);
 	rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf);
 	if (rc)
-		goto failed2;
+		goto failed1;
 	rc = sysfs_create_link(&virtfn->dev.kobj, &dev->dev.kobj, "physfn");
 	if (rc)
-		goto failed3;
+		goto failed2;
 
 	kobject_uevent(&virtfn->dev.kobj, KOBJ_CHANGE);
 
@@ -197,11 +197,10 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
 
 	return 0;
 
-failed3:
-	sysfs_remove_link(&dev->dev.kobj, buf);
 failed2:
-	pci_stop_and_remove_bus_device(virtfn);
+	sysfs_remove_link(&dev->dev.kobj, buf);
 failed1:
+	pci_stop_and_remove_bus_device(virtfn);
 	pci_dev_put(dev);
 failed0:
 	virtfn_remove_bus(dev->bus, bus);
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 0608aae72ccc..9a8a38384121 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -289,6 +289,9 @@ static const struct pci_p2pdma_whitelist_entry {
 	/* Intel Xeon E7 v3/Xeon E5 v3/Core i7 */
 	{PCI_VENDOR_ID_INTEL,	0x2f00, REQ_SAME_HOST_BRIDGE},
 	{PCI_VENDOR_ID_INTEL,	0x2f01, REQ_SAME_HOST_BRIDGE},
+	/* Intel SkyLake-E */
+	{PCI_VENDOR_ID_INTEL,	0x2030, 0},
+	{PCI_VENDOR_ID_INTEL,	0x2020, 0},
 	{}
 };
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index df21e3227b57..d828ca835a98 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -131,6 +131,7 @@ bool pci_ats_disabled(void)
 {
 	return pcie_ats_disabled;
 }
+EXPORT_SYMBOL_GPL(pci_ats_disabled);
 
 /* Disable bridge_d3 for all PCIe ports */
 static bool pci_bridge_d3_disable;
@@ -1372,8 +1373,11 @@ int pci_save_state(struct pci_dev *dev)
 {
 	int i;
 	/* XXX: 100% dword access ok here? */
-	for (i = 0; i < 16; i++)
+	for (i = 0; i < 16; i++) {
 		pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]);
+		pci_dbg(dev, "saving config space at offset %#x (reading %#x)\n",
+			i * 4, dev->saved_config_space[i]);
+	}
 	dev->state_saved = true;
 
 	i = pci_save_pcie_state(dev);
@@ -5998,7 +6002,8 @@ EXPORT_SYMBOL_GPL(pci_pr3_present);
 /**
  * pci_add_dma_alias - Add a DMA devfn alias for a device
  * @dev: the PCI device for which alias is added
- * @devfn: alias slot and function
+ * @devfn_from: alias slot and function
+ * @nr_devfns: number of subsequent devfns to alias
  *
  * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask
  * which is used to program permissible bus-devfn source addresses for DMA
@@ -6014,18 +6019,29 @@ EXPORT_SYMBOL_GPL(pci_pr3_present);
  * cannot be left as a userspace activity).  DMA aliases should therefore
  * be configured via quirks, such as the PCI fixup header quirk.
  */
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns)
 {
+	int devfn_to;
+
+	nr_devfns = min(nr_devfns, (unsigned) MAX_NR_DEVFNS - devfn_from);
+	devfn_to = devfn_from + nr_devfns - 1;
+
 	if (!dev->dma_alias_mask)
-		dev->dma_alias_mask = bitmap_zalloc(U8_MAX, GFP_KERNEL);
+		dev->dma_alias_mask = bitmap_zalloc(MAX_NR_DEVFNS, GFP_KERNEL);
 	if (!dev->dma_alias_mask) {
 		pci_warn(dev, "Unable to allocate DMA alias mask\n");
 		return;
 	}
 
-	set_bit(devfn, dev->dma_alias_mask);
-	pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
-		 PCI_SLOT(devfn), PCI_FUNC(devfn));
+	bitmap_set(dev->dma_alias_mask, devfn_from, nr_devfns);
+
+	if (nr_devfns == 1)
+		pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
+				PCI_SLOT(devfn_from), PCI_FUNC(devfn_from));
+	else if (nr_devfns > 1)
+		pci_info(dev, "Enabling fixed DMA alias for devfn range from %02x.%d to %02x.%d\n",
+				PCI_SLOT(devfn_from), PCI_FUNC(devfn_from),
+				PCI_SLOT(devfn_to), PCI_FUNC(devfn_to));
 }
 
 bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2)
@@ -6033,7 +6049,9 @@ bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2)
 	return (dev1->dma_alias_mask &&
 		test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
 	       (dev2->dma_alias_mask &&
-		test_bit(dev1->devfn, dev2->dma_alias_mask));
+		test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+	       pci_real_dma_dev(dev1) == dev2 ||
+	       pci_real_dma_dev(dev2) == dev1;
 }
 
 bool pci_device_is_present(struct pci_dev *pdev)
@@ -6057,6 +6075,21 @@ void pci_ignore_hotplug(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
 
+/**
+ * pci_real_dma_dev - Get PCI DMA device for PCI device
+ * @dev: the PCI device that may have a PCI DMA alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias DMA to another PCI device on another PCI bus. If
+ * the PCI device is on the same bus, it is recommended to use
+ * pci_add_dma_alias(). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+struct pci_dev __weak *pci_real_dma_dev(struct pci_dev *dev)
+{
+	return dev;
+}
+
 resource_size_t __weak pcibios_default_alignment(void)
 {
 	return 0;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a0a53bd05a0b..6394e7746fb5 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -4,6 +4,9 @@
 
 #include <linux/pci.h>
 
+/* Number of possible devfns: 0.0 to 1f.7 inclusive */
+#define MAX_NR_DEVFNS 256
+
 #define PCI_FIND_CAP_TTL	48
 
 #define PCI_VSEC_ID_INTEL_TBT	0x1234	/* Thunderbolt */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 1ca86f2e0166..4a818b07a1af 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1445,6 +1445,7 @@ static int aer_probe(struct pcie_device *dev)
 		return -ENOMEM;
 
 	rpc->rpd = port;
+	INIT_KFIFO(rpc->aer_fifo);
 	set_service_data(dev, rpc);
 
 	status = devm_request_threaded_irq(device, dev->irq, aer_irq, aer_isr,
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index b0e6048a9208..01dfc8bb7ca0 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -10,6 +10,8 @@
  *	Zhang Yanmin (yanmin.zhang@intel.com)
  */
 
+#define dev_fmt(fmt) "AER: " fmt
+
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -61,10 +63,12 @@ static int report_error_detected(struct pci_dev *dev,
 		 * error callbacks of "any" device in the subtree, and will
 		 * exit in the disconnected error state.
 		 */
-		if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
+		if (dev->hdr_type != PCI_HEADER_TYPE_BRIDGE) {
 			vote = PCI_ERS_RESULT_NO_AER_DRIVER;
-		else
+			pci_info(dev, "can't recover (no error_detected callback)\n");
+		} else {
 			vote = PCI_ERS_RESULT_NONE;
+		}
 	} else {
 		err_handler = dev->driver->err_handler;
 		vote = err_handler->error_detected(dev, state);
@@ -233,12 +237,12 @@ void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
 
 	pci_aer_clear_device_status(dev);
 	pci_cleanup_aer_uncorrect_error_status(dev);
-	pci_info(dev, "AER: Device recovery successful\n");
+	pci_info(dev, "device recovery successful\n");
 	return;
 
 failed:
 	pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT);
 
 	/* TODO: Should kernel panic here? */
-	pci_info(dev, "AER: Device recovery failed\n");
+	pci_info(dev, "device recovery failed\n");
 }
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 6ef74bf5013f..bd2b691fa7a3 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -306,19 +306,20 @@ static int proc_bus_pci_release(struct inode *inode, struct file *file)
 }
 #endif /* HAVE_PCI_MMAP */
 
-static const struct file_operations proc_bus_pci_operations = {
-	.owner		= THIS_MODULE,
-	.llseek		= proc_bus_pci_lseek,
-	.read		= proc_bus_pci_read,
-	.write		= proc_bus_pci_write,
-	.unlocked_ioctl	= proc_bus_pci_ioctl,
-	.compat_ioctl	= proc_bus_pci_ioctl,
+static const struct proc_ops proc_bus_pci_ops = {
+	.proc_lseek	= proc_bus_pci_lseek,
+	.proc_read	= proc_bus_pci_read,
+	.proc_write	= proc_bus_pci_write,
+	.proc_ioctl	= proc_bus_pci_ioctl,
+#ifdef CONFIG_COMPAT
+	.proc_compat_ioctl = proc_bus_pci_ioctl,
+#endif
 #ifdef HAVE_PCI_MMAP
-	.open		= proc_bus_pci_open,
-	.release	= proc_bus_pci_release,
-	.mmap		= proc_bus_pci_mmap,
+	.proc_open	= proc_bus_pci_open,
+	.proc_release	= proc_bus_pci_release,
+	.proc_mmap	= proc_bus_pci_mmap,
 #ifdef HAVE_ARCH_PCI_GET_UNMAPPED_AREA
-	.get_unmapped_area = get_pci_unmapped_area,
+	.proc_get_unmapped_area = get_pci_unmapped_area,
 #endif /* HAVE_ARCH_PCI_GET_UNMAPPED_AREA */
 #endif /* HAVE_PCI_MMAP */
 };
@@ -424,7 +425,7 @@ int pci_proc_attach_device(struct pci_dev *dev)
 
 	sprintf(name, "%02x.%x", PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn));
 	e = proc_create_data(name, S_IFREG | S_IRUGO | S_IWUSR, bus->procdir,
-			     &proc_bus_pci_operations, dev);
+			     &proc_bus_pci_ops, dev);
 	if (!e)
 		return -ENOMEM;
 	proc_set_size(e, dev->cfg_size);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index a3a1a0ea64f4..29f473ebf20f 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1871,19 +1871,40 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2609, quirk_intel_pcie_pm);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260a, quirk_intel_pcie_pm);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260b, quirk_intel_pcie_pm);
 
+static void quirk_d3hot_delay(struct pci_dev *dev, unsigned int delay)
+{
+	if (dev->d3_delay >= delay)
+		return;
+
+	dev->d3_delay = delay;
+	pci_info(dev, "extending delay after power-on from D3hot to %d msec\n",
+		 dev->d3_delay);
+}
+
 static void quirk_radeon_pm(struct pci_dev *dev)
 {
 	if (dev->subsystem_vendor == PCI_VENDOR_ID_APPLE &&
-	    dev->subsystem_device == 0x00e2) {
-		if (dev->d3_delay < 20) {
-			dev->d3_delay = 20;
-			pci_info(dev, "extending delay after power-on from D3 to %d msec\n",
-				 dev->d3_delay);
-		}
-	}
+	    dev->subsystem_device == 0x00e2)
+		quirk_d3hot_delay(dev, 20);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6741, quirk_radeon_pm);
 
+/*
+ * Ryzen5/7 XHCI controllers fail upon resume from runtime suspend or s2idle.
+ * https://bugzilla.kernel.org/show_bug.cgi?id=205587
+ *
+ * The kernel attempts to transition these devices to D3cold, but that seems
+ * to be ineffective on the platforms in question; the PCI device appears to
+ * remain on in D3hot state. The D3hot-to-D0 transition then requires an
+ * extended delay in order to succeed.
+ */
+static void quirk_ryzen_xhci_d3hot(struct pci_dev *dev)
+{
+	quirk_d3hot_delay(dev, 20);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15e0, quirk_ryzen_xhci_d3hot);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x15e1, quirk_ryzen_xhci_d3hot);
+
 #ifdef CONFIG_X86_IO_APIC
 static int dmi_disable_ioapicreroute(const struct dmi_system_id *d)
 {
@@ -2381,32 +2402,6 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_BROADCOM,
 			 PCI_DEVICE_ID_TIGON3_5719,
 			 quirk_brcm_5719_limit_mrrs);
 
-#ifdef CONFIG_PCIE_IPROC_PLATFORM
-static void quirk_paxc_bridge(struct pci_dev *pdev)
-{
-	/*
-	 * The PCI config space is shared with the PAXC root port and the first
-	 * Ethernet device.  So, we need to workaround this by telling the PCI
-	 * code that the bridge is not an Ethernet device.
-	 */
-	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-		pdev->class = PCI_CLASS_BRIDGE_PCI << 8;
-
-	/*
-	 * MPSS is not being set properly (as it is currently 0).  This is
-	 * because that area of the PCI config space is hard coded to zero, and
-	 * is not modifiable by firmware.  Set this to 2 (e.g., 512 byte MPS)
-	 * so that the MPS can be set to the real max value.
-	 */
-	pdev->pcie_mpss = 2;
-}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge);
-#endif
-
 /*
  * Originally in EDAC sources for i82875P: Intel tells BIOS developers to
  * hide device 6 which configures the overflow device access containing the
@@ -3932,7 +3927,7 @@ int pci_dev_specific_reset(struct pci_dev *dev, int probe)
 static void quirk_dma_func0_alias(struct pci_dev *dev)
 {
 	if (PCI_FUNC(dev->devfn) != 0)
-		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 0), 1);
 }
 
 /*
@@ -3946,7 +3941,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_RICOH, 0xe476, quirk_dma_func0_alias);
 static void quirk_dma_func1_alias(struct pci_dev *dev)
 {
 	if (PCI_FUNC(dev->devfn) != 1)
-		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1));
+		pci_add_dma_alias(dev, PCI_DEVFN(PCI_SLOT(dev->devfn), 1), 1);
 }
 
 /*
@@ -4031,7 +4026,7 @@ static void quirk_fixed_dma_alias(struct pci_dev *dev)
 
 	id = pci_match_id(fixed_dma_alias_tbl, dev);
 	if (id)
-		pci_add_dma_alias(dev, id->driver_data);
+		pci_add_dma_alias(dev, id->driver_data, 1);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ADAPTEC2, 0x0285, quirk_fixed_dma_alias);
 
@@ -4072,9 +4067,9 @@ DECLARE_PCI_FIXUP_HEADER(0x8086, 0x244e, quirk_use_pcie_bridge_dma_alias);
  */
 static void quirk_mic_x200_dma_alias(struct pci_dev *pdev)
 {
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0));
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0));
-	pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3));
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x10, 0x0), 1);
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x11, 0x0), 1);
+	pci_add_dma_alias(pdev, PCI_DEVFN(0x12, 0x3), 1);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2260, quirk_mic_x200_dma_alias);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2264, quirk_mic_x200_dma_alias);
@@ -4098,13 +4093,8 @@ static void quirk_pex_vca_alias(struct pci_dev *pdev)
 	const unsigned int num_pci_slots = 0x20;
 	unsigned int slot;
 
-	for (slot = 0; slot < num_pci_slots; slot++) {
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x0));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x1));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x2));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x3));
-		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x4));
-	}
+	for (slot = 0; slot < num_pci_slots; slot++)
+		pci_add_dma_alias(pdev, PCI_DEVFN(slot, 0x0), 5);
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2954, quirk_pex_vca_alias);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2955, quirk_pex_vca_alias);
@@ -5339,7 +5329,7 @@ static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev)
 			pci_dbg(pdev,
 				"Aliasing Partition %d Proxy ID %02x.%d\n",
 				pp, PCI_SLOT(devfn), PCI_FUNC(devfn));
-			pci_add_dma_alias(pdev, devfn);
+			pci_add_dma_alias(pdev, devfn, 1);
 		}
 	}
 
@@ -5380,6 +5370,39 @@ SWITCHTEC_QUIRK(0x8573);  /* PFXI 48XG3 */
 SWITCHTEC_QUIRK(0x8574);  /* PFXI 64XG3 */
 SWITCHTEC_QUIRK(0x8575);  /* PFXI 80XG3 */
 SWITCHTEC_QUIRK(0x8576);  /* PFXI 96XG3 */
+SWITCHTEC_QUIRK(0x4000);  /* PFX 100XG4 */
+SWITCHTEC_QUIRK(0x4084);  /* PFX 84XG4  */
+SWITCHTEC_QUIRK(0x4068);  /* PFX 68XG4  */
+SWITCHTEC_QUIRK(0x4052);  /* PFX 52XG4  */
+SWITCHTEC_QUIRK(0x4036);  /* PFX 36XG4  */
+SWITCHTEC_QUIRK(0x4028);  /* PFX 28XG4  */
+SWITCHTEC_QUIRK(0x4100);  /* PSX 100XG4 */
+SWITCHTEC_QUIRK(0x4184);  /* PSX 84XG4  */
+SWITCHTEC_QUIRK(0x4168);  /* PSX 68XG4  */
+SWITCHTEC_QUIRK(0x4152);  /* PSX 52XG4  */
+SWITCHTEC_QUIRK(0x4136);  /* PSX 36XG4  */
+SWITCHTEC_QUIRK(0x4128);  /* PSX 28XG4  */
+SWITCHTEC_QUIRK(0x4200);  /* PAX 100XG4 */
+SWITCHTEC_QUIRK(0x4284);  /* PAX 84XG4  */
+SWITCHTEC_QUIRK(0x4268);  /* PAX 68XG4  */
+SWITCHTEC_QUIRK(0x4252);  /* PAX 52XG4  */
+SWITCHTEC_QUIRK(0x4236);  /* PAX 36XG4  */
+SWITCHTEC_QUIRK(0x4228);  /* PAX 28XG4  */
+
+/*
+ * The PLX NTB uses devfn proxy IDs to move TLPs between NT endpoints.
+ * These IDs are used to forward responses to the originator on the other
+ * side of the NTB.  Alias all possible IDs to the NTB to permit access when
+ * the IOMMU is turned on.
+ */
+static void quirk_plx_ntb_dma_alias(struct pci_dev *pdev)
+{
+	pci_info(pdev, "Setting PLX NTB proxy ID aliases\n");
+	/* PLX NTB may use all 256 devfns */
+	pci_add_dma_alias(pdev, 0, 256);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, 0x87b0, quirk_plx_ntb_dma_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PLX, 0x87b1, quirk_plx_ntb_dma_alias);
 
 /*
  * On Lenovo Thinkpad P50 SKUs with a Nvidia Quadro M1000M, the BIOS does
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index bade14002fd8..2061672954ee 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -32,6 +32,12 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 	struct pci_bus *bus;
 	int ret;
 
+	/*
+	 * The device may have an explicit alias requester ID for DMA where the
+	 * requester is on another PCI bus.
+	 */
+	pdev = pci_real_dma_dev(pdev);
+
 	ret = fn(pdev, pci_dev_id(pdev), data);
 	if (ret)
 		return ret;
@@ -41,9 +47,9 @@ int pci_for_each_dma_alias(struct pci_dev *pdev,
 	 * DMA, iterate over that too.
 	 */
 	if (unlikely(pdev->dma_alias_mask)) {
-		u8 devfn;
+		unsigned int devfn;
 
-		for_each_set_bit(devfn, pdev->dma_alias_mask, U8_MAX) {
+		for_each_set_bit(devfn, pdev->dma_alias_mask, MAX_NR_DEVFNS) {
 			ret = fn(pdev, PCI_DEVID(pdev->bus->number, devfn),
 				 data);
 			if (ret)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index f279826204eb..f2461bf9243d 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1803,12 +1803,18 @@ again:
 	/* Restore size and flags */
 	list_for_each_entry(fail_res, &fail_head, list) {
 		struct resource *res = fail_res->res;
+		int idx;
 
 		res->start = fail_res->start;
 		res->end = fail_res->end;
 		res->flags = fail_res->flags;
-		if (fail_res->dev->subordinate)
-			res->flags = 0;
+
+		if (pci_is_bridge(fail_res->dev)) {
+			idx = res - &fail_res->dev->resource[0];
+			if (idx >= PCI_BRIDGE_RESOURCES &&
+			    idx <= PCI_BRIDGE_RESOURCE_END)
+				res->flags = 0;
+		}
 	}
 	free_list(&fail_head);
 
@@ -1832,56 +1838,72 @@ void __init pci_assign_unassigned_resources(void)
 	}
 }
 
-static void extend_bridge_window(struct pci_dev *bridge, struct resource *res,
+static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res,
 				 struct list_head *add_list,
-				 resource_size_t available)
+				 resource_size_t new_size)
 {
-	struct pci_dev_resource *dev_res;
+	resource_size_t add_size, size = resource_size(res);
 
 	if (res->parent)
 		return;
 
-	if (resource_size(res) >= available)
+	if (!new_size)
 		return;
 
-	dev_res = res_to_dev_res(add_list, res);
-	if (!dev_res)
-		return;
-
-	/* Is there room to extend the window? */
-	if (available - resource_size(res) <= dev_res->add_size)
-		return;
+	if (new_size > size) {
+		add_size = new_size - size;
+		pci_dbg(bridge, "bridge window %pR extended by %pa\n", res,
+			&add_size);
+	} else if (new_size < size) {
+		add_size = size - new_size;
+		pci_dbg(bridge, "bridge window %pR shrunken by %pa\n", res,
+			&add_size);
+	}
 
-	dev_res->add_size = available - resource_size(res);
-	pci_dbg(bridge, "bridge window %pR extended by %pa\n", res,
-		&dev_res->add_size);
+	res->end = res->start + new_size - 1;
+	remove_from_list(add_list, res);
 }
 
 static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 					    struct list_head *add_list,
-					    resource_size_t available_io,
-					    resource_size_t available_mmio,
-					    resource_size_t available_mmio_pref)
+					    struct resource io,
+					    struct resource mmio,
+					    struct resource mmio_pref)
 {
-	resource_size_t remaining_io, remaining_mmio, remaining_mmio_pref;
 	unsigned int normal_bridges = 0, hotplug_bridges = 0;
 	struct resource *io_res, *mmio_res, *mmio_pref_res;
 	struct pci_dev *dev, *bridge = bus->self;
+	resource_size_t io_per_hp, mmio_per_hp, mmio_pref_per_hp, align;
 
 	io_res = &bridge->resource[PCI_BRIDGE_RESOURCES + 0];
 	mmio_res = &bridge->resource[PCI_BRIDGE_RESOURCES + 1];
 	mmio_pref_res = &bridge->resource[PCI_BRIDGE_RESOURCES + 2];
 
 	/*
-	 * Update additional resource list (add_list) to fill all the
-	 * extra resource space available for this port except the space
-	 * calculated in __pci_bus_size_bridges() which covers all the
-	 * devices currently connected to the port and below.
+	 * The alignment of this bridge is yet to be considered, hence it must
+	 * be done now before extending its bridge window.
+	 */
+	align = pci_resource_alignment(bridge, io_res);
+	if (!io_res->parent && align)
+		io.start = min(ALIGN(io.start, align), io.end + 1);
+
+	align = pci_resource_alignment(bridge, mmio_res);
+	if (!mmio_res->parent && align)
+		mmio.start = min(ALIGN(mmio.start, align), mmio.end + 1);
+
+	align = pci_resource_alignment(bridge, mmio_pref_res);
+	if (!mmio_pref_res->parent && align)
+		mmio_pref.start = min(ALIGN(mmio_pref.start, align),
+			mmio_pref.end + 1);
+
+	/*
+	 * Now that we have adjusted for alignment, update the bridge window
+	 * resources to fill as much remaining resource space as possible.
 	 */
-	extend_bridge_window(bridge, io_res, add_list, available_io);
-	extend_bridge_window(bridge, mmio_res, add_list, available_mmio);
-	extend_bridge_window(bridge, mmio_pref_res, add_list,
-			     available_mmio_pref);
+	adjust_bridge_window(bridge, io_res, add_list, resource_size(&io));
+	adjust_bridge_window(bridge, mmio_res, add_list, resource_size(&mmio));
+	adjust_bridge_window(bridge, mmio_pref_res, add_list,
+			     resource_size(&mmio_pref));
 
 	/*
 	 * Calculate how many hotplug bridges and normal bridges there
@@ -1902,11 +1924,9 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 	 */
 	if (hotplug_bridges + normal_bridges == 1) {
 		dev = list_first_entry(&bus->devices, struct pci_dev, bus_list);
-		if (dev->subordinate) {
+		if (dev->subordinate)
 			pci_bus_distribute_available_resources(dev->subordinate,
-				add_list, available_io, available_mmio,
-				available_mmio_pref);
-		}
+				add_list, io, mmio, mmio_pref);
 		return;
 	}
 
@@ -1919,12 +1939,9 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 	 * extra space reduced by the minimal required space for the
 	 * non-hotplug bridges.
 	 */
-	remaining_io = available_io;
-	remaining_mmio = available_mmio;
-	remaining_mmio_pref = available_mmio_pref;
-
 	for_each_pci_bridge(dev, bus) {
-		const struct resource *res;
+		resource_size_t used_size;
+		struct resource *res;
 
 		if (dev->is_hotplug_bridge)
 			continue;
@@ -1934,24 +1951,39 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 		 * bridge and devices below it occupy.
 		 */
 		res = &dev->resource[PCI_BRIDGE_RESOURCES + 0];
-		if (!res->parent && available_io > resource_size(res))
-			remaining_io -= resource_size(res);
+		align = pci_resource_alignment(dev, res);
+		align = align ? ALIGN(io.start, align) - io.start : 0;
+		used_size = align + resource_size(res);
+		if (!res->parent)
+			io.start = min(io.start + used_size, io.end + 1);
 
 		res = &dev->resource[PCI_BRIDGE_RESOURCES + 1];
-		if (!res->parent && available_mmio > resource_size(res))
-			remaining_mmio -= resource_size(res);
+		align = pci_resource_alignment(dev, res);
+		align = align ? ALIGN(mmio.start, align) - mmio.start : 0;
+		used_size = align + resource_size(res);
+		if (!res->parent)
+			mmio.start = min(mmio.start + used_size, mmio.end + 1);
 
 		res = &dev->resource[PCI_BRIDGE_RESOURCES + 2];
-		if (!res->parent && available_mmio_pref > resource_size(res))
-			remaining_mmio_pref -= resource_size(res);
+		align = pci_resource_alignment(dev, res);
+		align = align ? ALIGN(mmio_pref.start, align) -
+			mmio_pref.start : 0;
+		used_size = align + resource_size(res);
+		if (!res->parent)
+			mmio_pref.start = min(mmio_pref.start + used_size,
+				mmio_pref.end + 1);
 	}
 
+	io_per_hp = div64_ul(resource_size(&io), hotplug_bridges);
+	mmio_per_hp = div64_ul(resource_size(&mmio), hotplug_bridges);
+	mmio_pref_per_hp = div64_ul(resource_size(&mmio_pref),
+		hotplug_bridges);
+
 	/*
 	 * Go over devices on this bus and distribute the remaining
 	 * resource space between hotplug bridges.
 	 */
 	for_each_pci_bridge(dev, bus) {
-		resource_size_t align, io, mmio, mmio_pref;
 		struct pci_bus *b;
 
 		b = dev->subordinate;
@@ -1963,42 +1995,31 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 		 * hotplug-capable downstream ports taking alignment into
 		 * account.
 		 */
-		align = pci_resource_alignment(bridge, io_res);
-		io = div64_ul(available_io, hotplug_bridges);
-		io = min(ALIGN(io, align), remaining_io);
-		remaining_io -= io;
-
-		align = pci_resource_alignment(bridge, mmio_res);
-		mmio = div64_ul(available_mmio, hotplug_bridges);
-		mmio = min(ALIGN(mmio, align), remaining_mmio);
-		remaining_mmio -= mmio;
-
-		align = pci_resource_alignment(bridge, mmio_pref_res);
-		mmio_pref = div64_ul(available_mmio_pref, hotplug_bridges);
-		mmio_pref = min(ALIGN(mmio_pref, align), remaining_mmio_pref);
-		remaining_mmio_pref -= mmio_pref;
+		io.end = io.start + io_per_hp - 1;
+		mmio.end = mmio.start + mmio_per_hp - 1;
+		mmio_pref.end = mmio_pref.start + mmio_pref_per_hp - 1;
 
 		pci_bus_distribute_available_resources(b, add_list, io, mmio,
 						       mmio_pref);
+
+		io.start += io_per_hp;
+		mmio.start += mmio_per_hp;
+		mmio_pref.start += mmio_pref_per_hp;
 	}
 }
 
 static void pci_bridge_distribute_available_resources(struct pci_dev *bridge,
 						     struct list_head *add_list)
 {
-	resource_size_t available_io, available_mmio, available_mmio_pref;
-	const struct resource *res;
+	struct resource available_io, available_mmio, available_mmio_pref;
 
 	if (!bridge->is_hotplug_bridge)
 		return;
 
 	/* Take the initial extra resources from the hotplug port */
-	res = &bridge->resource[PCI_BRIDGE_RESOURCES + 0];
-	available_io = resource_size(res);
-	res = &bridge->resource[PCI_BRIDGE_RESOURCES + 1];
-	available_mmio = resource_size(res);
-	res = &bridge->resource[PCI_BRIDGE_RESOURCES + 2];
-	available_mmio_pref = resource_size(res);
+	available_io = bridge->resource[PCI_BRIDGE_RESOURCES + 0];
+	available_mmio = bridge->resource[PCI_BRIDGE_RESOURCES + 1];
+	available_mmio_pref = bridge->resource[PCI_BRIDGE_RESOURCES + 2];
 
 	pci_bus_distribute_available_resources(bridge->subordinate,
 					       add_list, available_io,
@@ -2055,12 +2076,18 @@ again:
 	/* Restore size and flags */
 	list_for_each_entry(fail_res, &fail_head, list) {
 		struct resource *res = fail_res->res;
+		int idx;
 
 		res->start = fail_res->start;
 		res->end = fail_res->end;
 		res->flags = fail_res->flags;
-		if (fail_res->dev->subordinate)
-			res->flags = 0;
+
+		if (pci_is_bridge(fail_res->dev)) {
+			idx = res - &fail_res->dev->resource[0];
+			if (idx >= PCI_BRIDGE_RESOURCES &&
+			    idx <= PCI_BRIDGE_RESOURCE_END)
+				res->flags = 0;
+		}
 	}
 	free_list(&fail_head);
 
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 88091bbfe77f..a823b4b8ef8a 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -317,8 +317,15 @@ static ssize_t field ## _show(struct device *dev, \
 	struct device_attribute *attr, char *buf) \
 { \
 	struct switchtec_dev *stdev = to_stdev(dev); \
-	return io_string_show(buf, &stdev->mmio_sys_info->field, \
-			    sizeof(stdev->mmio_sys_info->field)); \
+	struct sys_info_regs __iomem *si = stdev->mmio_sys_info; \
+	if (stdev->gen == SWITCHTEC_GEN3) \
+		return io_string_show(buf, &si->gen3.field, \
+				      sizeof(si->gen3.field)); \
+	else if (stdev->gen == SWITCHTEC_GEN4) \
+		return io_string_show(buf, &si->gen4.field, \
+				      sizeof(si->gen4.field)); \
+	else \
+		return -ENOTSUPP; \
 } \
 \
 static DEVICE_ATTR_RO(field)
@@ -326,13 +333,31 @@ static DEVICE_ATTR_RO(field)
 DEVICE_ATTR_SYS_INFO_STR(vendor_id);
 DEVICE_ATTR_SYS_INFO_STR(product_id);
 DEVICE_ATTR_SYS_INFO_STR(product_revision);
-DEVICE_ATTR_SYS_INFO_STR(component_vendor);
+
+static ssize_t component_vendor_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct switchtec_dev *stdev = to_stdev(dev);
+	struct sys_info_regs __iomem *si = stdev->mmio_sys_info;
+
+	/* component_vendor field not supported after gen3 */
+	if (stdev->gen != SWITCHTEC_GEN3)
+		return sprintf(buf, "none\n");
+
+	return io_string_show(buf, &si->gen3.component_vendor,
+			      sizeof(si->gen3.component_vendor));
+}
+static DEVICE_ATTR_RO(component_vendor);
 
 static ssize_t component_id_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
 {
 	struct switchtec_dev *stdev = to_stdev(dev);
-	int id = ioread16(&stdev->mmio_sys_info->component_id);
+	int id = ioread16(&stdev->mmio_sys_info->gen3.component_id);
+
+	/* component_id field not supported after gen3 */
+	if (stdev->gen != SWITCHTEC_GEN3)
+		return sprintf(buf, "none\n");
 
 	return sprintf(buf, "PM%04X\n", id);
 }
@@ -342,7 +367,11 @@ static ssize_t component_revision_show(struct device *dev,
 	struct device_attribute *attr, char *buf)
 {
 	struct switchtec_dev *stdev = to_stdev(dev);
-	int rev = ioread8(&stdev->mmio_sys_info->component_revision);
+	int rev = ioread8(&stdev->mmio_sys_info->gen3.component_revision);
+
+	/* component_revision field not supported after gen3 */
+	if (stdev->gen != SWITCHTEC_GEN3)
+		return sprintf(buf, "255\n");
 
 	return sprintf(buf, "%d\n", rev);
 }
@@ -450,6 +479,12 @@ static ssize_t switchtec_dev_write(struct file *filp, const char __user *data,
 		rc = -EFAULT;
 		goto out;
 	}
+	if (((MRPC_CMD_ID(stuser->cmd) == MRPC_GAS_WRITE) ||
+	     (MRPC_CMD_ID(stuser->cmd) == MRPC_GAS_READ)) &&
+	    !capable(CAP_SYS_ADMIN)) {
+		rc = -EPERM;
+		goto out;
+	}
 
 	data += sizeof(stuser->cmd);
 	rc = copy_from_user(&stuser->data, data, size - sizeof(stuser->cmd));
@@ -568,8 +603,15 @@ static int ioctl_flash_info(struct switchtec_dev *stdev,
 	struct switchtec_ioctl_flash_info info = {0};
 	struct flash_info_regs __iomem *fi = stdev->mmio_flash_info;
 
-	info.flash_length = ioread32(&fi->flash_length);
-	info.num_partitions = SWITCHTEC_IOCTL_NUM_PARTITIONS;
+	if (stdev->gen == SWITCHTEC_GEN3) {
+		info.flash_length = ioread32(&fi->gen3.flash_length);
+		info.num_partitions = SWITCHTEC_NUM_PARTITIONS_GEN3;
+	} else if (stdev->gen == SWITCHTEC_GEN4) {
+		info.flash_length = ioread32(&fi->gen4.flash_length);
+		info.num_partitions = SWITCHTEC_NUM_PARTITIONS_GEN4;
+	} else {
+		return -ENOTSUPP;
+	}
 
 	if (copy_to_user(uinfo, &info, sizeof(info)))
 		return -EFAULT;
@@ -584,75 +626,200 @@ static void set_fw_info_part(struct switchtec_ioctl_flash_part_info *info,
 	info->length = ioread32(&pi->length);
 }
 
-static int ioctl_flash_part_info(struct switchtec_dev *stdev,
-	struct switchtec_ioctl_flash_part_info __user *uinfo)
+static int flash_part_info_gen3(struct switchtec_dev *stdev,
+		struct switchtec_ioctl_flash_part_info *info)
 {
-	struct switchtec_ioctl_flash_part_info info = {0};
-	struct flash_info_regs __iomem *fi = stdev->mmio_flash_info;
-	struct sys_info_regs __iomem *si = stdev->mmio_sys_info;
+	struct flash_info_regs_gen3 __iomem *fi =
+		&stdev->mmio_flash_info->gen3;
+	struct sys_info_regs_gen3 __iomem *si = &stdev->mmio_sys_info->gen3;
 	u32 active_addr = -1;
 
-	if (copy_from_user(&info, uinfo, sizeof(info)))
-		return -EFAULT;
-
-	switch (info.flash_partition) {
+	switch (info->flash_partition) {
 	case SWITCHTEC_IOCTL_PART_CFG0:
 		active_addr = ioread32(&fi->active_cfg);
-		set_fw_info_part(&info, &fi->cfg0);
-		if (ioread16(&si->cfg_running) == SWITCHTEC_CFG0_RUNNING)
-			info.active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		set_fw_info_part(info, &fi->cfg0);
+		if (ioread16(&si->cfg_running) == SWITCHTEC_GEN3_CFG0_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
 		break;
 	case SWITCHTEC_IOCTL_PART_CFG1:
 		active_addr = ioread32(&fi->active_cfg);
-		set_fw_info_part(&info, &fi->cfg1);
-		if (ioread16(&si->cfg_running) == SWITCHTEC_CFG1_RUNNING)
-			info.active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		set_fw_info_part(info, &fi->cfg1);
+		if (ioread16(&si->cfg_running) == SWITCHTEC_GEN3_CFG1_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
 		break;
 	case SWITCHTEC_IOCTL_PART_IMG0:
 		active_addr = ioread32(&fi->active_img);
-		set_fw_info_part(&info, &fi->img0);
-		if (ioread16(&si->img_running) == SWITCHTEC_IMG0_RUNNING)
-			info.active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		set_fw_info_part(info, &fi->img0);
+		if (ioread16(&si->img_running) == SWITCHTEC_GEN3_IMG0_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
 		break;
 	case SWITCHTEC_IOCTL_PART_IMG1:
 		active_addr = ioread32(&fi->active_img);
-		set_fw_info_part(&info, &fi->img1);
-		if (ioread16(&si->img_running) == SWITCHTEC_IMG1_RUNNING)
-			info.active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		set_fw_info_part(info, &fi->img1);
+		if (ioread16(&si->img_running) == SWITCHTEC_GEN3_IMG1_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_NVLOG:
+		set_fw_info_part(info, &fi->nvlog);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR0:
+		set_fw_info_part(info, &fi->vendor[0]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR1:
+		set_fw_info_part(info, &fi->vendor[1]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR2:
+		set_fw_info_part(info, &fi->vendor[2]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR3:
+		set_fw_info_part(info, &fi->vendor[3]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR4:
+		set_fw_info_part(info, &fi->vendor[4]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR5:
+		set_fw_info_part(info, &fi->vendor[5]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR6:
+		set_fw_info_part(info, &fi->vendor[6]);
+		break;
+	case SWITCHTEC_IOCTL_PART_VENDOR7:
+		set_fw_info_part(info, &fi->vendor[7]);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (info->address == active_addr)
+		info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+
+	return 0;
+}
+
+static int flash_part_info_gen4(struct switchtec_dev *stdev,
+		struct switchtec_ioctl_flash_part_info *info)
+{
+	struct flash_info_regs_gen4 __iomem *fi = &stdev->mmio_flash_info->gen4;
+	struct sys_info_regs_gen4 __iomem *si = &stdev->mmio_sys_info->gen4;
+	struct active_partition_info_gen4 __iomem *af = &fi->active_flag;
+
+	switch (info->flash_partition) {
+	case SWITCHTEC_IOCTL_PART_MAP_0:
+		set_fw_info_part(info, &fi->map0);
+		break;
+	case SWITCHTEC_IOCTL_PART_MAP_1:
+		set_fw_info_part(info, &fi->map1);
+		break;
+	case SWITCHTEC_IOCTL_PART_KEY_0:
+		set_fw_info_part(info, &fi->key0);
+		if (ioread8(&af->key) == SWITCHTEC_GEN4_KEY0_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->key_running) == SWITCHTEC_GEN4_KEY0_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_KEY_1:
+		set_fw_info_part(info, &fi->key1);
+		if (ioread8(&af->key) == SWITCHTEC_GEN4_KEY1_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->key_running) == SWITCHTEC_GEN4_KEY1_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_BL2_0:
+		set_fw_info_part(info, &fi->bl2_0);
+		if (ioread8(&af->bl2) == SWITCHTEC_GEN4_BL2_0_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->bl2_running) == SWITCHTEC_GEN4_BL2_0_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_BL2_1:
+		set_fw_info_part(info, &fi->bl2_1);
+		if (ioread8(&af->bl2) == SWITCHTEC_GEN4_BL2_1_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->bl2_running) == SWITCHTEC_GEN4_BL2_1_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_CFG0:
+		set_fw_info_part(info, &fi->cfg0);
+		if (ioread8(&af->cfg) == SWITCHTEC_GEN4_CFG0_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->cfg_running) == SWITCHTEC_GEN4_CFG0_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_CFG1:
+		set_fw_info_part(info, &fi->cfg1);
+		if (ioread8(&af->cfg) == SWITCHTEC_GEN4_CFG1_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->cfg_running) == SWITCHTEC_GEN4_CFG1_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_IMG0:
+		set_fw_info_part(info, &fi->img0);
+		if (ioread8(&af->img) == SWITCHTEC_GEN4_IMG0_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->img_running) == SWITCHTEC_GEN4_IMG0_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
+		break;
+	case SWITCHTEC_IOCTL_PART_IMG1:
+		set_fw_info_part(info, &fi->img1);
+		if (ioread8(&af->img) == SWITCHTEC_GEN4_IMG1_ACTIVE)
+			info->active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+		if (ioread16(&si->img_running) == SWITCHTEC_GEN4_IMG1_RUNNING)
+			info->active |= SWITCHTEC_IOCTL_PART_RUNNING;
 		break;
 	case SWITCHTEC_IOCTL_PART_NVLOG:
-		set_fw_info_part(&info, &fi->nvlog);
+		set_fw_info_part(info, &fi->nvlog);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR0:
-		set_fw_info_part(&info, &fi->vendor[0]);
+		set_fw_info_part(info, &fi->vendor[0]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR1:
-		set_fw_info_part(&info, &fi->vendor[1]);
+		set_fw_info_part(info, &fi->vendor[1]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR2:
-		set_fw_info_part(&info, &fi->vendor[2]);
+		set_fw_info_part(info, &fi->vendor[2]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR3:
-		set_fw_info_part(&info, &fi->vendor[3]);
+		set_fw_info_part(info, &fi->vendor[3]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR4:
-		set_fw_info_part(&info, &fi->vendor[4]);
+		set_fw_info_part(info, &fi->vendor[4]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR5:
-		set_fw_info_part(&info, &fi->vendor[5]);
+		set_fw_info_part(info, &fi->vendor[5]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR6:
-		set_fw_info_part(&info, &fi->vendor[6]);
+		set_fw_info_part(info, &fi->vendor[6]);
 		break;
 	case SWITCHTEC_IOCTL_PART_VENDOR7:
-		set_fw_info_part(&info, &fi->vendor[7]);
+		set_fw_info_part(info, &fi->vendor[7]);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	if (info.address == active_addr)
-		info.active |= SWITCHTEC_IOCTL_PART_ACTIVE;
+	return 0;
+}
+
+static int ioctl_flash_part_info(struct switchtec_dev *stdev,
+		struct switchtec_ioctl_flash_part_info __user *uinfo)
+{
+	int ret;
+	struct switchtec_ioctl_flash_part_info info = {0};
+
+	if (copy_from_user(&info, uinfo, sizeof(info)))
+		return -EFAULT;
+
+	if (stdev->gen == SWITCHTEC_GEN3) {
+		ret = flash_part_info_gen3(stdev, &info);
+		if (ret)
+			return ret;
+	} else if (stdev->gen == SWITCHTEC_GEN4) {
+		ret = flash_part_info_gen4(stdev, &info);
+		if (ret)
+			return ret;
+	} else {
+		return -ENOTSUPP;
+	}
 
 	if (copy_to_user(uinfo, &info, sizeof(info)))
 		return -EFAULT;
@@ -683,11 +850,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev,
 		s->part[i] = reg;
 	}
 
-	for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) {
-		reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id);
-		if (reg != PCI_VENDOR_ID_MICROSEMI)
-			break;
-
+	for (i = 0; i < stdev->pff_csr_count; i++) {
 		reg = ioread32(&stdev->mmio_pff_csr[i].pff_event_summary);
 		s->pff[i] = reg;
 	}
@@ -751,10 +914,13 @@ static const struct event_reg {
 	EV_PAR(SWITCHTEC_IOCTL_EVENT_MRPC_COMP, mrpc_comp_hdr),
 	EV_PAR(SWITCHTEC_IOCTL_EVENT_MRPC_COMP_ASYNC, mrpc_comp_async_hdr),
 	EV_PAR(SWITCHTEC_IOCTL_EVENT_DYN_PART_BIND_COMP, dyn_binding_hdr),
+	EV_PAR(SWITCHTEC_IOCTL_EVENT_INTERCOMM_REQ_NOTIFY,
+	       intercomm_notify_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_AER_IN_P2P, aer_in_p2p_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_AER_IN_VEP, aer_in_vep_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_DPC, dpc_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_CTS, cts_hdr),
+	EV_PFF(SWITCHTEC_IOCTL_EVENT_UEC, uec_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_HOTPLUG, hotplug_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_IER, ier_hdr),
 	EV_PFF(SWITCHTEC_IOCTL_EVENT_THRESH, threshold_hdr),
@@ -1181,10 +1347,6 @@ static int mask_event(struct switchtec_dev *stdev, int eid, int idx)
 	if (!(hdr & SWITCHTEC_EVENT_OCCURRED && hdr & SWITCHTEC_EVENT_EN_IRQ))
 		return 0;
 
-	if (eid == SWITCHTEC_IOCTL_EVENT_LINK_STATE ||
-	    eid == SWITCHTEC_IOCTL_EVENT_MRPC_COMP)
-		return 0;
-
 	dev_dbg(&stdev->dev, "%s: %d %d %x\n", __func__, eid, idx, hdr);
 	hdr &= ~(SWITCHTEC_EVENT_EN_IRQ | SWITCHTEC_EVENT_OCCURRED);
 	iowrite32(hdr, hdr_reg);
@@ -1231,8 +1393,13 @@ static irqreturn_t switchtec_event_isr(int irq, void *dev)
 
 	check_link_state_events(stdev);
 
-	for (eid = 0; eid < SWITCHTEC_IOCTL_MAX_EVENTS; eid++)
+	for (eid = 0; eid < SWITCHTEC_IOCTL_MAX_EVENTS; eid++) {
+		if (eid == SWITCHTEC_IOCTL_EVENT_LINK_STATE ||
+		    eid == SWITCHTEC_IOCTL_EVENT_MRPC_COMP)
+			continue;
+
 		event_count += mask_all_events(stdev, eid);
+	}
 
 	if (event_count) {
 		atomic_inc(&stdev->event_cnt);
@@ -1276,7 +1443,7 @@ static int switchtec_init_isr(struct switchtec_dev *stdev)
 	if (nvecs < 0)
 		return nvecs;
 
-	event_irq = ioread32(&stdev->mmio_part_cfg->vep_vector_number);
+	event_irq = ioread16(&stdev->mmio_part_cfg->vep_vector_number);
 	if (event_irq < 0 || event_irq >= nvecs)
 		return -EFAULT;
 
@@ -1324,16 +1491,16 @@ static void init_pff(struct switchtec_dev *stdev)
 	stdev->pff_csr_count = i;
 
 	reg = ioread32(&pcfg->usp_pff_inst_id);
-	if (reg < SWITCHTEC_MAX_PFF_CSR)
+	if (reg < stdev->pff_csr_count)
 		stdev->pff_local[reg] = 1;
 
 	reg = ioread32(&pcfg->vep_pff_inst_id);
-	if (reg < SWITCHTEC_MAX_PFF_CSR)
+	if (reg < stdev->pff_csr_count)
 		stdev->pff_local[reg] = 1;
 
 	for (i = 0; i < ARRAY_SIZE(pcfg->dsp_pff_inst_id); i++) {
 		reg = ioread32(&pcfg->dsp_pff_inst_id[i]);
-		if (reg < SWITCHTEC_MAX_PFF_CSR)
+		if (reg < stdev->pff_csr_count)
 			stdev->pff_local[reg] = 1;
 	}
 }
@@ -1344,12 +1511,13 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	int rc;
 	void __iomem *map;
 	unsigned long res_start, res_len;
+	u32 __iomem *part_id;
 
 	rc = pcim_enable_device(pdev);
 	if (rc)
 		return rc;
 
-	rc = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (rc)
 		return rc;
 
@@ -1378,7 +1546,15 @@ static int switchtec_init_pci(struct switchtec_dev *stdev,
 	stdev->mmio_sys_info = stdev->mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET;
 	stdev->mmio_flash_info = stdev->mmio + SWITCHTEC_GAS_FLASH_INFO_OFFSET;
 	stdev->mmio_ntb = stdev->mmio + SWITCHTEC_GAS_NTB_OFFSET;
-	stdev->partition = ioread8(&stdev->mmio_sys_info->partition_id);
+
+	if (stdev->gen == SWITCHTEC_GEN3)
+		part_id = &stdev->mmio_sys_info->gen3.partition_id;
+	else if (stdev->gen == SWITCHTEC_GEN4)
+		part_id = &stdev->mmio_sys_info->gen4.partition_id;
+	else
+		return -ENOTSUPP;
+
+	stdev->partition = ioread8(part_id);
 	stdev->partition_count = ioread8(&stdev->mmio_ntb->partition_count);
 	stdev->mmio_part_cfg_all = stdev->mmio + SWITCHTEC_GAS_PART_CFG_OFFSET;
 	stdev->mmio_part_cfg = &stdev->mmio_part_cfg_all[stdev->partition];
@@ -1420,6 +1596,8 @@ static int switchtec_pci_probe(struct pci_dev *pdev,
 	if (IS_ERR(stdev))
 		return PTR_ERR(stdev);
 
+	stdev->gen = id->driver_data;
+
 	rc = switchtec_init_pci(stdev, pdev);
 	if (rc)
 		goto err_put;
@@ -1467,7 +1645,7 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 	put_device(&stdev->dev);
 }
 
-#define SWITCHTEC_PCI_DEVICE(device_id) \
+#define SWITCHTEC_PCI_DEVICE(device_id, gen) \
 	{ \
 		.vendor     = PCI_VENDOR_ID_MICROSEMI, \
 		.device     = device_id, \
@@ -1475,6 +1653,7 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 		.subdevice  = PCI_ANY_ID, \
 		.class      = (PCI_CLASS_MEMORY_OTHER << 8), \
 		.class_mask = 0xFFFFFFFF, \
+		.driver_data = gen, \
 	}, \
 	{ \
 		.vendor     = PCI_VENDOR_ID_MICROSEMI, \
@@ -1483,39 +1662,58 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 		.subdevice  = PCI_ANY_ID, \
 		.class      = (PCI_CLASS_BRIDGE_OTHER << 8), \
 		.class_mask = 0xFFFFFFFF, \
+		.driver_data = gen, \
 	}
 
 static const struct pci_device_id switchtec_pci_tbl[] = {
-	SWITCHTEC_PCI_DEVICE(0x8531),  //PFX 24xG3
-	SWITCHTEC_PCI_DEVICE(0x8532),  //PFX 32xG3
-	SWITCHTEC_PCI_DEVICE(0x8533),  //PFX 48xG3
-	SWITCHTEC_PCI_DEVICE(0x8534),  //PFX 64xG3
-	SWITCHTEC_PCI_DEVICE(0x8535),  //PFX 80xG3
-	SWITCHTEC_PCI_DEVICE(0x8536),  //PFX 96xG3
-	SWITCHTEC_PCI_DEVICE(0x8541),  //PSX 24xG3
-	SWITCHTEC_PCI_DEVICE(0x8542),  //PSX 32xG3
-	SWITCHTEC_PCI_DEVICE(0x8543),  //PSX 48xG3
-	SWITCHTEC_PCI_DEVICE(0x8544),  //PSX 64xG3
-	SWITCHTEC_PCI_DEVICE(0x8545),  //PSX 80xG3
-	SWITCHTEC_PCI_DEVICE(0x8546),  //PSX 96xG3
-	SWITCHTEC_PCI_DEVICE(0x8551),  //PAX 24XG3
-	SWITCHTEC_PCI_DEVICE(0x8552),  //PAX 32XG3
-	SWITCHTEC_PCI_DEVICE(0x8553),  //PAX 48XG3
-	SWITCHTEC_PCI_DEVICE(0x8554),  //PAX 64XG3
-	SWITCHTEC_PCI_DEVICE(0x8555),  //PAX 80XG3
-	SWITCHTEC_PCI_DEVICE(0x8556),  //PAX 96XG3
-	SWITCHTEC_PCI_DEVICE(0x8561),  //PFXL 24XG3
-	SWITCHTEC_PCI_DEVICE(0x8562),  //PFXL 32XG3
-	SWITCHTEC_PCI_DEVICE(0x8563),  //PFXL 48XG3
-	SWITCHTEC_PCI_DEVICE(0x8564),  //PFXL 64XG3
-	SWITCHTEC_PCI_DEVICE(0x8565),  //PFXL 80XG3
-	SWITCHTEC_PCI_DEVICE(0x8566),  //PFXL 96XG3
-	SWITCHTEC_PCI_DEVICE(0x8571),  //PFXI 24XG3
-	SWITCHTEC_PCI_DEVICE(0x8572),  //PFXI 32XG3
-	SWITCHTEC_PCI_DEVICE(0x8573),  //PFXI 48XG3
-	SWITCHTEC_PCI_DEVICE(0x8574),  //PFXI 64XG3
-	SWITCHTEC_PCI_DEVICE(0x8575),  //PFXI 80XG3
-	SWITCHTEC_PCI_DEVICE(0x8576),  //PFXI 96XG3
+	SWITCHTEC_PCI_DEVICE(0x8531, SWITCHTEC_GEN3),  //PFX 24xG3
+	SWITCHTEC_PCI_DEVICE(0x8532, SWITCHTEC_GEN3),  //PFX 32xG3
+	SWITCHTEC_PCI_DEVICE(0x8533, SWITCHTEC_GEN3),  //PFX 48xG3
+	SWITCHTEC_PCI_DEVICE(0x8534, SWITCHTEC_GEN3),  //PFX 64xG3
+	SWITCHTEC_PCI_DEVICE(0x8535, SWITCHTEC_GEN3),  //PFX 80xG3
+	SWITCHTEC_PCI_DEVICE(0x8536, SWITCHTEC_GEN3),  //PFX 96xG3
+	SWITCHTEC_PCI_DEVICE(0x8541, SWITCHTEC_GEN3),  //PSX 24xG3
+	SWITCHTEC_PCI_DEVICE(0x8542, SWITCHTEC_GEN3),  //PSX 32xG3
+	SWITCHTEC_PCI_DEVICE(0x8543, SWITCHTEC_GEN3),  //PSX 48xG3
+	SWITCHTEC_PCI_DEVICE(0x8544, SWITCHTEC_GEN3),  //PSX 64xG3
+	SWITCHTEC_PCI_DEVICE(0x8545, SWITCHTEC_GEN3),  //PSX 80xG3
+	SWITCHTEC_PCI_DEVICE(0x8546, SWITCHTEC_GEN3),  //PSX 96xG3
+	SWITCHTEC_PCI_DEVICE(0x8551, SWITCHTEC_GEN3),  //PAX 24XG3
+	SWITCHTEC_PCI_DEVICE(0x8552, SWITCHTEC_GEN3),  //PAX 32XG3
+	SWITCHTEC_PCI_DEVICE(0x8553, SWITCHTEC_GEN3),  //PAX 48XG3
+	SWITCHTEC_PCI_DEVICE(0x8554, SWITCHTEC_GEN3),  //PAX 64XG3
+	SWITCHTEC_PCI_DEVICE(0x8555, SWITCHTEC_GEN3),  //PAX 80XG3
+	SWITCHTEC_PCI_DEVICE(0x8556, SWITCHTEC_GEN3),  //PAX 96XG3
+	SWITCHTEC_PCI_DEVICE(0x8561, SWITCHTEC_GEN3),  //PFXL 24XG3
+	SWITCHTEC_PCI_DEVICE(0x8562, SWITCHTEC_GEN3),  //PFXL 32XG3
+	SWITCHTEC_PCI_DEVICE(0x8563, SWITCHTEC_GEN3),  //PFXL 48XG3
+	SWITCHTEC_PCI_DEVICE(0x8564, SWITCHTEC_GEN3),  //PFXL 64XG3
+	SWITCHTEC_PCI_DEVICE(0x8565, SWITCHTEC_GEN3),  //PFXL 80XG3
+	SWITCHTEC_PCI_DEVICE(0x8566, SWITCHTEC_GEN3),  //PFXL 96XG3
+	SWITCHTEC_PCI_DEVICE(0x8571, SWITCHTEC_GEN3),  //PFXI 24XG3
+	SWITCHTEC_PCI_DEVICE(0x8572, SWITCHTEC_GEN3),  //PFXI 32XG3
+	SWITCHTEC_PCI_DEVICE(0x8573, SWITCHTEC_GEN3),  //PFXI 48XG3
+	SWITCHTEC_PCI_DEVICE(0x8574, SWITCHTEC_GEN3),  //PFXI 64XG3
+	SWITCHTEC_PCI_DEVICE(0x8575, SWITCHTEC_GEN3),  //PFXI 80XG3
+	SWITCHTEC_PCI_DEVICE(0x8576, SWITCHTEC_GEN3),  //PFXI 96XG3
+	SWITCHTEC_PCI_DEVICE(0x4000, SWITCHTEC_GEN4),  //PFX 100XG4
+	SWITCHTEC_PCI_DEVICE(0x4084, SWITCHTEC_GEN4),  //PFX 84XG4
+	SWITCHTEC_PCI_DEVICE(0x4068, SWITCHTEC_GEN4),  //PFX 68XG4
+	SWITCHTEC_PCI_DEVICE(0x4052, SWITCHTEC_GEN4),  //PFX 52XG4
+	SWITCHTEC_PCI_DEVICE(0x4036, SWITCHTEC_GEN4),  //PFX 36XG4
+	SWITCHTEC_PCI_DEVICE(0x4028, SWITCHTEC_GEN4),  //PFX 28XG4
+	SWITCHTEC_PCI_DEVICE(0x4100, SWITCHTEC_GEN4),  //PSX 100XG4
+	SWITCHTEC_PCI_DEVICE(0x4184, SWITCHTEC_GEN4),  //PSX 84XG4
+	SWITCHTEC_PCI_DEVICE(0x4168, SWITCHTEC_GEN4),  //PSX 68XG4
+	SWITCHTEC_PCI_DEVICE(0x4152, SWITCHTEC_GEN4),  //PSX 52XG4
+	SWITCHTEC_PCI_DEVICE(0x4136, SWITCHTEC_GEN4),  //PSX 36XG4
+	SWITCHTEC_PCI_DEVICE(0x4128, SWITCHTEC_GEN4),  //PSX 28XG4
+	SWITCHTEC_PCI_DEVICE(0x4200, SWITCHTEC_GEN4),  //PAX 100XG4
+	SWITCHTEC_PCI_DEVICE(0x4284, SWITCHTEC_GEN4),  //PAX 84XG4
+	SWITCHTEC_PCI_DEVICE(0x4268, SWITCHTEC_GEN4),  //PAX 68XG4
+	SWITCHTEC_PCI_DEVICE(0x4252, SWITCHTEC_GEN4),  //PAX 52XG4
+	SWITCHTEC_PCI_DEVICE(0x4236, SWITCHTEC_GEN4),  //PAX 36XG4
+	SWITCHTEC_PCI_DEVICE(0x4228, SWITCHTEC_GEN4),  //PAX 28XG4
 	{0}
 };
 MODULE_DEVICE_TABLE(pci, switchtec_pci_tbl);
diff --git a/drivers/pcmcia/i82092.c b/drivers/pcmcia/i82092.c
index aad8a46605be..85887d885b5f 100644
--- a/drivers/pcmcia/i82092.c
+++ b/drivers/pcmcia/i82092.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* 
+/*
  * Driver for Intel I82092AA PCI-PCMCIA bridge.
  *
  * (C) 2001 Red Hat, Inc.
@@ -18,7 +18,7 @@
 
 #include <pcmcia/ss.h>
 
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include "i82092aa.h"
 #include "i82365.h"
@@ -33,16 +33,16 @@ static const struct pci_device_id i82092aa_pci_ids[] = {
 MODULE_DEVICE_TABLE(pci, i82092aa_pci_ids);
 
 static struct pci_driver i82092aa_pci_driver = {
-	.name           = "i82092aa",
-	.id_table       = i82092aa_pci_ids,
-	.probe          = i82092aa_pci_probe,
-	.remove         = i82092aa_pci_remove,
+	.name		= "i82092aa",
+	.id_table	= i82092aa_pci_ids,
+	.probe		= i82092aa_pci_probe,
+	.remove	= i82092aa_pci_remove,
 };
 
 
 /* the pccard structure and its functions */
 static struct pccard_operations i82092aa_operations = {
-	.init 		 	= i82092aa_init,
+	.init			= i82092aa_init,
 	.get_status		= i82092aa_get_status,
 	.set_socket		= i82092aa_set_socket,
 	.set_io_map		= i82092aa_set_io_map,
@@ -53,57 +53,63 @@ static struct pccard_operations i82092aa_operations = {
 
 struct socket_info {
 	int	number;
-	int	card_state; 	/*  0 = no socket,
-				    1 = empty socket, 
-				    2 = card but not initialized,
-				    3 = operational card */
-	unsigned int io_base; 	/* base io address of the socket */
-	
+	int	card_state;
+		/* 0 = no socket,
+		 * 1 = empty socket,
+		 * 2 = card but not initialized,
+		 * 3 = operational card
+		 */
+	unsigned int io_base;	/* base io address of the socket */
+
 	struct pcmcia_socket socket;
 	struct pci_dev *dev;	/* The PCI device for the socket */
 };
 
 #define MAX_SOCKETS 4
 static struct socket_info sockets[MAX_SOCKETS];
-static int socket_count;  /* shortcut */                                  	                                	
+static int socket_count;	/* shortcut */
 
 
-static int i82092aa_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
+static int i82092aa_pci_probe(struct pci_dev *dev,
+			      const struct pci_device_id *id)
 {
 	unsigned char configbyte;
 	int i, ret;
-	
-	enter("i82092aa_pci_probe");
-	
-	if ((ret = pci_enable_device(dev)))
+
+	ret = pci_enable_device(dev);
+	if (ret)
 		return ret;
-		
-	pci_read_config_byte(dev, 0x40, &configbyte);  /* PCI Configuration Control */
-	switch(configbyte&6) {
-		case 0:
-			socket_count = 2;
-			break;
-		case 2:
-			socket_count = 1;
-			break;
-		case 4:
-		case 6:
-			socket_count = 4;
-			break;
-			
-		default:
-			printk(KERN_ERR "i82092aa: Oops, you did something we didn't think of.\n");
-			ret = -EIO;
-			goto err_out_disable;
+
+	/* PCI Configuration Control */
+	pci_read_config_byte(dev, 0x40, &configbyte);
+
+	switch (configbyte&6) {
+	case 0:
+		socket_count = 2;
+		break;
+	case 2:
+		socket_count = 1;
+		break;
+	case 4:
+	case 6:
+		socket_count = 4;
+		break;
+
+	default:
+		dev_err(&dev->dev,
+			"Oops, you did something we didn't think of.\n");
+		ret = -EIO;
+		goto err_out_disable;
 	}
-	printk(KERN_INFO "i82092aa: configured as a %d socket device.\n", socket_count);
+	dev_info(&dev->dev, "configured as a %d socket device.\n",
+		 socket_count);
 
 	if (!request_region(pci_resource_start(dev, 0), 2, "i82092aa")) {
 		ret = -EBUSY;
 		goto err_out_disable;
 	}
-	
-	for (i = 0;i<socket_count;i++) {
+
+	for (i = 0; i < socket_count; i++) {
 		sockets[i].card_state = 1; /* 1 = present but empty */
 		sockets[i].io_base = pci_resource_start(dev, 0);
 		sockets[i].socket.features |= SS_CAP_PCCARD;
@@ -114,65 +120,65 @@ static int i82092aa_pci_probe(struct pci_dev *dev, const struct pci_device_id *i
 		sockets[i].socket.owner = THIS_MODULE;
 
 		sockets[i].number = i;
-		
+
 		if (card_present(i)) {
 			sockets[i].card_state = 3;
-			dev_dbg(&dev->dev, "i82092aa: slot %i is occupied\n", i);
+			dev_dbg(&dev->dev, "slot %i is occupied\n", i);
 		} else {
-			dev_dbg(&dev->dev, "i82092aa: slot %i is vacant\n", i);
+			dev_dbg(&dev->dev, "slot %i is vacant\n", i);
 		}
 	}
-		
-	/* Now, specifiy that all interrupts are to be done as PCI interrupts */
-	configbyte = 0xFF; /* bitmask, one bit per event, 1 = PCI interrupt, 0 = ISA interrupt */
-	pci_write_config_byte(dev, 0x50, configbyte); /* PCI Interrupt Routing Register */
+
+	/* Now, specifiy that all interrupts are to be done as PCI interrupts
+	 * bitmask, one bit per event, 1 = PCI interrupt, 0 = ISA interrupt
+	 */
+	configbyte = 0xFF;
+
+	/* PCI Interrupt Routing Register */
+	pci_write_config_byte(dev, 0x50, configbyte);
 
 	/* Register the interrupt handler */
 	dev_dbg(&dev->dev, "Requesting interrupt %i\n", dev->irq);
-	if ((ret = request_irq(dev->irq, i82092aa_interrupt, IRQF_SHARED, "i82092aa", i82092aa_interrupt))) {
-		printk(KERN_ERR "i82092aa: Failed to register IRQ %d, aborting\n", dev->irq);
+	ret = request_irq(dev->irq, i82092aa_interrupt, IRQF_SHARED,
+			  "i82092aa", i82092aa_interrupt);
+	if (ret) {
+		dev_err(&dev->dev, "Failed to register IRQ %d, aborting\n",
+			dev->irq);
 		goto err_out_free_res;
 	}
 
-	for (i = 0; i<socket_count; i++) {
+	for (i = 0; i < socket_count; i++) {
 		sockets[i].socket.dev.parent = &dev->dev;
 		sockets[i].socket.ops = &i82092aa_operations;
 		sockets[i].socket.resource_ops = &pccard_nonstatic_ops;
 		ret = pcmcia_register_socket(&sockets[i].socket);
-		if (ret) {
+		if (ret)
 			goto err_out_free_sockets;
-		}
 	}
 
-	leave("i82092aa_pci_probe");
 	return 0;
 
 err_out_free_sockets:
 	if (i) {
-		for (i--;i>=0;i--) {
+		for (i--; i >= 0; i--)
 			pcmcia_unregister_socket(&sockets[i].socket);
-		}
 	}
 	free_irq(dev->irq, i82092aa_interrupt);
 err_out_free_res:
 	release_region(pci_resource_start(dev, 0), 2);
 err_out_disable:
 	pci_disable_device(dev);
-	return ret;			
+	return ret;
 }
 
 static void i82092aa_pci_remove(struct pci_dev *dev)
 {
 	int i;
 
-	enter("i82092aa_pci_remove");
-	
 	free_irq(dev->irq, i82092aa_interrupt);
 
 	for (i = 0; i < socket_count; i++)
 		pcmcia_unregister_socket(&sockets[i].socket);
-
-	leave("i82092aa_pci_remove");
 }
 
 static DEFINE_SPINLOCK(port_lock);
@@ -184,44 +190,27 @@ static unsigned char indirect_read(int socket, unsigned short reg)
 	unsigned short int port;
 	unsigned char val;
 	unsigned long flags;
-	spin_lock_irqsave(&port_lock,flags);
+
+	spin_lock_irqsave(&port_lock, flags);
 	reg += socket * 0x40;
 	port = sockets[socket].io_base;
-	outb(reg,port);
+	outb(reg, port);
 	val = inb(port+1);
-	spin_unlock_irqrestore(&port_lock,flags);
+	spin_unlock_irqrestore(&port_lock, flags);
 	return val;
 }
 
-#if 0
-static unsigned short indirect_read16(int socket, unsigned short reg)
-{
-	unsigned short int port;
-	unsigned short tmp;
-	unsigned long flags;
-	spin_lock_irqsave(&port_lock,flags);
-	reg  = reg + socket * 0x40;
-	port = sockets[socket].io_base;
-	outb(reg,port);
-	tmp = inb(port+1);
-	reg++;
-	outb(reg,port);
-	tmp = tmp | (inb(port+1)<<8);
-	spin_unlock_irqrestore(&port_lock,flags);
-	return tmp;
-}
-#endif
-
 static void indirect_write(int socket, unsigned short reg, unsigned char value)
 {
 	unsigned short int port;
 	unsigned long flags;
-	spin_lock_irqsave(&port_lock,flags);
+
+	spin_lock_irqsave(&port_lock, flags);
 	reg = reg + socket * 0x40;
-	port = sockets[socket].io_base; 
-	outb(reg,port);
-	outb(value,port+1);
-	spin_unlock_irqrestore(&port_lock,flags);
+	port = sockets[socket].io_base;
+	outb(reg, port);
+	outb(value, port+1);
+	spin_unlock_irqrestore(&port_lock, flags);
 }
 
 static void indirect_setbit(int socket, unsigned short reg, unsigned char mask)
@@ -229,53 +218,58 @@ static void indirect_setbit(int socket, unsigned short reg, unsigned char mask)
 	unsigned short int port;
 	unsigned char val;
 	unsigned long flags;
-	spin_lock_irqsave(&port_lock,flags);
+
+	spin_lock_irqsave(&port_lock, flags);
 	reg = reg + socket * 0x40;
-	port = sockets[socket].io_base; 
-	outb(reg,port);
+	port = sockets[socket].io_base;
+	outb(reg, port);
 	val = inb(port+1);
 	val |= mask;
-	outb(reg,port);
-	outb(val,port+1);
-	spin_unlock_irqrestore(&port_lock,flags);
+	outb(reg, port);
+	outb(val, port+1);
+	spin_unlock_irqrestore(&port_lock, flags);
 }
 
 
-static void indirect_resetbit(int socket, unsigned short reg, unsigned char mask)
+static void indirect_resetbit(int socket,
+			      unsigned short reg, unsigned char mask)
 {
 	unsigned short int port;
 	unsigned char val;
 	unsigned long flags;
-	spin_lock_irqsave(&port_lock,flags);
+
+	spin_lock_irqsave(&port_lock, flags);
 	reg = reg + socket * 0x40;
-	port = sockets[socket].io_base; 
-	outb(reg,port);
+	port = sockets[socket].io_base;
+	outb(reg, port);
 	val = inb(port+1);
 	val &= ~mask;
-	outb(reg,port);
-	outb(val,port+1);
-	spin_unlock_irqrestore(&port_lock,flags);
+	outb(reg, port);
+	outb(val, port+1);
+	spin_unlock_irqrestore(&port_lock, flags);
 }
 
-static void indirect_write16(int socket, unsigned short reg, unsigned short value)
+static void indirect_write16(int socket,
+			     unsigned short reg, unsigned short value)
 {
 	unsigned short int port;
 	unsigned char val;
 	unsigned long flags;
-	spin_lock_irqsave(&port_lock,flags);
+
+	spin_lock_irqsave(&port_lock, flags);
 	reg = reg + socket * 0x40;
-	port = sockets[socket].io_base; 
-	
-	outb(reg,port);
+	port = sockets[socket].io_base;
+
+	outb(reg, port);
 	val = value & 255;
-	outb(val,port+1);
-	
+	outb(val, port+1);
+
 	reg++;
-	
-	outb(reg,port);
+
+	outb(reg, port);
 	val = value>>8;
-	outb(val,port+1);
-	spin_unlock_irqrestore(&port_lock,flags);
+	outb(val, port+1);
+	spin_unlock_irqrestore(&port_lock, flags);
 }
 
 /* simple helper functions */
@@ -284,12 +278,12 @@ static int cycle_time = 120;
 
 static int to_cycles(int ns)
 {
-	if (cycle_time!=0)
+	if (cycle_time != 0)
 		return ns/cycle_time;
 	else
 		return 0;
 }
-    
+
 
 /* Interrupt handler functionality */
 
@@ -299,58 +293,61 @@ static irqreturn_t i82092aa_interrupt(int irq, void *dev)
 	int loopcount = 0;
 	int handled = 0;
 
-	unsigned int events, active=0;
-	
-/*	enter("i82092aa_interrupt");*/
-	
+	unsigned int events, active = 0;
+
 	while (1) {
 		loopcount++;
-		if (loopcount>20) {
-			printk(KERN_ERR "i82092aa: infinite eventloop in interrupt \n");
+		if (loopcount > 20) {
+			pr_err("i82092aa: infinite eventloop in interrupt\n");
 			break;
 		}
-		
+
 		active = 0;
-		
-		for (i=0;i<socket_count;i++) {
+
+		for (i = 0; i < socket_count; i++) {
 			int csc;
-			if (sockets[i].card_state==0) /* Inactive socket, should not happen */
+
+			/* Inactive socket, should not happen */
+			if (sockets[i].card_state == 0)
+				continue;
+
+			/* card status change register */
+			csc = indirect_read(i, I365_CSC);
+
+			if (csc == 0)  /* no events on this socket */
 				continue;
-			
-			csc = indirect_read(i,I365_CSC); /* card status change register */
-			
-			if (csc==0)  /* no events on this socket */
-			   	continue;
 			handled = 1;
 			events = 0;
-			 
+
 			if (csc & I365_CSC_DETECT) {
 				events |= SS_DETECT;
-				printk("Card detected in socket %i!\n",i);
-			 }
-			
-			if (indirect_read(i,I365_INTCTL) & I365_PC_IOCARD) { 
+				dev_info(&sockets[i].dev->dev,
+					 "Card detected in socket %i!\n", i);
+			}
+
+			if (indirect_read(i, I365_INTCTL) & I365_PC_IOCARD) {
 				/* For IO/CARDS, bit 0 means "read the card" */
-				events |= (csc & I365_CSC_STSCHG) ? SS_STSCHG : 0; 
+				if (csc & I365_CSC_STSCHG)
+					events |= SS_STSCHG;
 			} else {
 				/* Check for battery/ready events */
-				events |= (csc & I365_CSC_BVD1) ? SS_BATDEAD : 0;
-				events |= (csc & I365_CSC_BVD2) ? SS_BATWARN : 0;
-				events |= (csc & I365_CSC_READY) ? SS_READY : 0;
+				if (csc & I365_CSC_BVD1)
+					events |= SS_BATDEAD;
+				if (csc & I365_CSC_BVD2)
+					events |= SS_BATWARN;
+				if (csc & I365_CSC_READY)
+					events |= SS_READY;
 			}
-			
-			if (events) {
+
+			if (events)
 				pcmcia_parse_events(&sockets[i].socket, events);
-			}
 			active |= events;
 		}
-				
-		if (active==0) /* no more events to handle */
-			break;				
-		
+
+		if (active == 0) /* no more events to handle */
+			break;
 	}
 	return IRQ_RETVAL(handled);
-/*	leave("i82092aa_interrupt");*/
 }
 
 
@@ -358,80 +355,67 @@ static irqreturn_t i82092aa_interrupt(int irq, void *dev)
 /* socket functions */
 
 static int card_present(int socketno)
-{	
+{
 	unsigned int val;
-	enter("card_present");
-	
-	if ((socketno<0) || (socketno >= MAX_SOCKETS))
+
+	if ((socketno < 0) || (socketno >= MAX_SOCKETS))
 		return 0;
 	if (sockets[socketno].io_base == 0)
 		return 0;
 
-		
+
 	val = indirect_read(socketno, 1); /* Interface status register */
-	if ((val&12)==12) {
-		leave("card_present 1");
+	if ((val&12) == 12)
 		return 1;
-	}
-		
-	leave("card_present 0");
+
 	return 0;
 }
 
 static void set_bridge_state(int sock)
 {
-	enter("set_bridge_state");
-	indirect_write(sock, I365_GBLCTL,0x00);
-	indirect_write(sock, I365_GENCTL,0x00);
-	
-	indirect_setbit(sock, I365_INTCTL,0x08);
-	leave("set_bridge_state");
-}
-
-
+	indirect_write(sock, I365_GBLCTL, 0x00);
+	indirect_write(sock, I365_GENCTL, 0x00);
 
+	indirect_setbit(sock, I365_INTCTL, 0x08);
+}
 
 
-      
 static int i82092aa_init(struct pcmcia_socket *sock)
 {
 	int i;
 	struct resource res = { .start = 0, .end = 0x0fff };
-        pccard_io_map io = { 0, 0, 0, 0, 1 };
+	pccard_io_map io = { 0, 0, 0, 0, 1 };
 	pccard_mem_map mem = { .res = &res, };
-        
-        enter("i82092aa_init");
-                        
-        for (i = 0; i < 2; i++) {
-        	io.map = i;
-                i82092aa_set_io_map(sock, &io);
+
+	for (i = 0; i < 2; i++) {
+		io.map = i;
+		i82092aa_set_io_map(sock, &io);
 	}
-        for (i = 0; i < 5; i++) {
-        	mem.map = i;
-                i82092aa_set_mem_map(sock, &mem);
+	for (i = 0; i < 5; i++) {
+		mem.map = i;
+		i82092aa_set_mem_map(sock, &mem);
 	}
-	
-	leave("i82092aa_init");
+
 	return 0;
 }
-                                                                                                                                                                                                                                              
+
 static int i82092aa_get_status(struct pcmcia_socket *socket, u_int *value)
 {
-	unsigned int sock = container_of(socket, struct socket_info, socket)->number;
+	unsigned int sock = container_of(socket,
+				struct socket_info, socket)->number;
 	unsigned int status;
-	
-	enter("i82092aa_get_status");
-	
-	status = indirect_read(sock,I365_STATUS); /* Interface Status Register */
+
+	/* Interface Status Register */
+	status = indirect_read(sock, I365_STATUS);
+
 	*value = 0;
-	
-	if ((status & I365_CS_DETECT) == I365_CS_DETECT) {
+
+	if ((status & I365_CS_DETECT) == I365_CS_DETECT)
 		*value |= SS_DETECT;
-	}
-		
+
 	/* IO cards have a different meaning of bits 0,1 */
 	/* Also notice the inverse-logic on the bits */
-	if (indirect_read(sock, I365_INTCTL) & I365_PC_IOCARD)	{
+	if (indirect_read(sock, I365_INTCTL) & I365_PC_IOCARD) {
 		/* IO card */
 		if (!(status & I365_CS_STSCHG))
 			*value |= SS_STSCHG;
@@ -441,246 +425,238 @@ static int i82092aa_get_status(struct pcmcia_socket *socket, u_int *value)
 		if (!(status & I365_CS_BVD2))
 			*value |= SS_BATWARN;
 	}
-	 
+
 	if (status & I365_CS_WRPROT)
 		(*value) |= SS_WRPROT;	/* card is write protected */
-	 
+
 	if (status & I365_CS_READY)
 		(*value) |= SS_READY;    /* card is not busy */
-	 	
+
 	if (status & I365_CS_POWERON)
 		(*value) |= SS_POWERON;  /* power is applied to the card */
 
-	leave("i82092aa_get_status");
 	return 0;
 }
 
 
-static int i82092aa_set_socket(struct pcmcia_socket *socket, socket_state_t *state) 
+static int i82092aa_set_socket(struct pcmcia_socket *socket,
+			       socket_state_t *state)
 {
-	unsigned int sock = container_of(socket, struct socket_info, socket)->number;
+	struct socket_info *sock_info = container_of(socket, struct socket_info,
+						     socket);
+	unsigned int sock = sock_info->number;
 	unsigned char reg;
-	
-	enter("i82092aa_set_socket");
-	
+
 	/* First, set the global controller options */
-	
+
 	set_bridge_state(sock);
-	
+
 	/* Values for the IGENC register */
-	
+
 	reg = 0;
-	if (!(state->flags & SS_RESET)) 	/* The reset bit has "inverse" logic */
-		reg = reg | I365_PC_RESET;  
-	if (state->flags & SS_IOCARD) 
+
+	/* The reset bit has "inverse" logic */
+	if (!(state->flags & SS_RESET))
+		reg = reg | I365_PC_RESET;
+	if (state->flags & SS_IOCARD)
 		reg = reg | I365_PC_IOCARD;
-		
-	indirect_write(sock,I365_INTCTL,reg); /* IGENC, Interrupt and General Control Register */
-	
+
+	/* IGENC, Interrupt and General Control Register */
+	indirect_write(sock, I365_INTCTL, reg);
+
 	/* Power registers */
-	
+
 	reg = I365_PWR_NORESET; /* default: disable resetdrv on resume */
-	
+
 	if (state->flags & SS_PWR_AUTO) {
-		printk("Auto power\n");
+		dev_info(&sock_info->dev->dev, "Auto power\n");
 		reg |= I365_PWR_AUTO;	/* automatic power mngmnt */
 	}
 	if (state->flags & SS_OUTPUT_ENA) {
-		printk("Power Enabled \n");
+		dev_info(&sock_info->dev->dev, "Power Enabled\n");
 		reg |= I365_PWR_OUT;	/* enable power */
 	}
-	
+
 	switch (state->Vcc) {
-		case 0:	
-			break;
-		case 50: 
-			printk("setting voltage to Vcc to 5V on socket %i\n",sock);
-			reg |= I365_VCC_5V;
-			break;
-		default:
-			printk("i82092aa: i82092aa_set_socket called with invalid VCC power value: %i ", state->Vcc);
-			leave("i82092aa_set_socket");
-			return -EINVAL;
+	case 0:
+		break;
+	case 50:
+		dev_info(&sock_info->dev->dev,
+			 "setting voltage to Vcc to 5V on socket %i\n",
+			 sock);
+		reg |= I365_VCC_5V;
+		break;
+	default:
+		dev_err(&sock_info->dev->dev,
+			"%s called with invalid VCC power value: %i",
+			__func__, state->Vcc);
+		return -EINVAL;
 	}
-	
-	
+
 	switch (state->Vpp) {
-		case 0:	
-			printk("not setting Vpp on socket %i\n",sock);
-			break;
-		case 50: 
-			printk("setting Vpp to 5.0 for socket %i\n",sock);
-			reg |= I365_VPP1_5V | I365_VPP2_5V;
-			break;
-		case 120: 
-			printk("setting Vpp to 12.0\n");
-			reg |= I365_VPP1_12V | I365_VPP2_12V;
-			break;
-		default:
-			printk("i82092aa: i82092aa_set_socket called with invalid VPP power value: %i ", state->Vcc);
-			leave("i82092aa_set_socket");
-			return -EINVAL;
+	case 0:
+		dev_info(&sock_info->dev->dev,
+			 "not setting Vpp on socket %i\n", sock);
+		break;
+	case 50:
+		dev_info(&sock_info->dev->dev,
+			 "setting Vpp to 5.0 for socket %i\n", sock);
+		reg |= I365_VPP1_5V | I365_VPP2_5V;
+		break;
+	case 120:
+		dev_info(&sock_info->dev->dev, "setting Vpp to 12.0\n");
+		reg |= I365_VPP1_12V | I365_VPP2_12V;
+		break;
+	default:
+		dev_err(&sock_info->dev->dev,
+			"%s called with invalid VPP power value: %i",
+			__func__, state->Vcc);
+		return -EINVAL;
 	}
-	
-	if (reg != indirect_read(sock,I365_POWER)) /* only write if changed */
-		indirect_write(sock,I365_POWER,reg);
-		
+
+	if (reg != indirect_read(sock, I365_POWER)) /* only write if changed */
+		indirect_write(sock, I365_POWER, reg);
+
 	/* Enable specific interrupt events */
-	
+
 	reg = 0x00;
-	if (state->csc_mask & SS_DETECT) {
+	if (state->csc_mask & SS_DETECT)
 		reg |= I365_CSC_DETECT;
-	}
 	if (state->flags & SS_IOCARD) {
 		if (state->csc_mask & SS_STSCHG)
 			reg |= I365_CSC_STSCHG;
 	} else {
-		if (state->csc_mask & SS_BATDEAD) 
+		if (state->csc_mask & SS_BATDEAD)
 			reg |= I365_CSC_BVD1;
-		if (state->csc_mask & SS_BATWARN) 
+		if (state->csc_mask & SS_BATWARN)
 			reg |= I365_CSC_BVD2;
-		if (state->csc_mask & SS_READY) 
-			reg |= I365_CSC_READY; 
-		                        
+		if (state->csc_mask & SS_READY)
+			reg |= I365_CSC_READY;
+
 	}
-	
-	/* now write the value and clear the (probably bogus) pending stuff by doing a dummy read*/
-	
-	indirect_write(sock,I365_CSCINT,reg);
-	(void)indirect_read(sock,I365_CSC);
 
-	leave("i82092aa_set_socket");
+	/* now write the value and clear the (probably bogus) pending stuff
+	 * by doing a dummy read
+	 */
+
+	indirect_write(sock, I365_CSCINT, reg);
+	(void)indirect_read(sock, I365_CSC);
+
 	return 0;
 }
 
-static int i82092aa_set_io_map(struct pcmcia_socket *socket, struct pccard_io_map *io)
+static int i82092aa_set_io_map(struct pcmcia_socket *socket,
+			       struct pccard_io_map *io)
 {
-	unsigned int sock = container_of(socket, struct socket_info, socket)->number;
+	struct socket_info *sock_info = container_of(socket, struct socket_info,
+						     socket);
+	unsigned int sock = sock_info->number;
 	unsigned char map, ioctl;
-	
-	enter("i82092aa_set_io_map");
-	
+
 	map = io->map;
-	
-	/* Check error conditions */	
-	if (map > 1) {
-		leave("i82092aa_set_io_map with invalid map");
+
+	/* Check error conditions */
+	if (map > 1)
 		return -EINVAL;
-	}
-	if ((io->start > 0xffff) || (io->stop > 0xffff) || (io->stop < io->start)){
-		leave("i82092aa_set_io_map with invalid io");
+
+	if ((io->start > 0xffff) || (io->stop > 0xffff)
+				 || (io->stop < io->start))
 		return -EINVAL;
-	}
 
-	/* Turn off the window before changing anything */ 
+	/* Turn off the window before changing anything */
 	if (indirect_read(sock, I365_ADDRWIN) & I365_ENA_IO(map))
 		indirect_resetbit(sock, I365_ADDRWIN, I365_ENA_IO(map));
 
-/*	printk("set_io_map: Setting range to %x - %x \n",io->start,io->stop);  */
-	
 	/* write the new values */
-	indirect_write16(sock,I365_IO(map)+I365_W_START,io->start);            	
-	indirect_write16(sock,I365_IO(map)+I365_W_STOP,io->stop);            	
-	            	
-	ioctl = indirect_read(sock,I365_IOCTL) & ~I365_IOCTL_MASK(map);
-	
+	indirect_write16(sock, I365_IO(map)+I365_W_START, io->start);
+	indirect_write16(sock, I365_IO(map)+I365_W_STOP, io->stop);
+
+	ioctl = indirect_read(sock, I365_IOCTL) & ~I365_IOCTL_MASK(map);
+
 	if (io->flags & (MAP_16BIT|MAP_AUTOSZ))
 		ioctl |= I365_IOCTL_16BIT(map);
-		
-	indirect_write(sock,I365_IOCTL,ioctl);
-	
+
+	indirect_write(sock, I365_IOCTL, ioctl);
+
 	/* Turn the window back on if needed */
 	if (io->flags & MAP_ACTIVE)
-		indirect_setbit(sock,I365_ADDRWIN,I365_ENA_IO(map));
-			
-	leave("i82092aa_set_io_map");	
+		indirect_setbit(sock, I365_ADDRWIN, I365_ENA_IO(map));
+
 	return 0;
 }
 
-static int i82092aa_set_mem_map(struct pcmcia_socket *socket, struct pccard_mem_map *mem)
+static int i82092aa_set_mem_map(struct pcmcia_socket *socket,
+				struct pccard_mem_map *mem)
 {
-	struct socket_info *sock_info = container_of(socket, struct socket_info, socket);
+	struct socket_info *sock_info = container_of(socket, struct socket_info,
+						     socket);
 	unsigned int sock = sock_info->number;
 	struct pci_bus_region region;
 	unsigned short base, i;
 	unsigned char map;
-	
-	enter("i82092aa_set_mem_map");
 
 	pcibios_resource_to_bus(sock_info->dev->bus, &region, mem->res);
-	
+
 	map = mem->map;
-	if (map > 4) {
-		leave("i82092aa_set_mem_map: invalid map");
+	if (map > 4)
 		return -EINVAL;
-	}
-	
-	
-	if ( (mem->card_start > 0x3ffffff) || (region.start > region.end) ||
-	     (mem->speed > 1000) ) {
-		leave("i82092aa_set_mem_map: invalid address / speed");
-		printk("invalid mem map for socket %i: %llx to %llx with a "
-			"start of %x\n",
+
+	if ((mem->card_start > 0x3ffffff) || (region.start > region.end) ||
+	     (mem->speed > 1000)) {
+		dev_err(&sock_info->dev->dev,
+			"invalid mem map for socket %i: %llx to %llx with a start of %x\n",
 			sock,
 			(unsigned long long)region.start,
 			(unsigned long long)region.end,
 			mem->card_start);
 		return -EINVAL;
 	}
-	
+
 	/* Turn off the window before changing anything */
 	if (indirect_read(sock, I365_ADDRWIN) & I365_ENA_MEM(map))
-	              indirect_resetbit(sock, I365_ADDRWIN, I365_ENA_MEM(map));
-	                 
-	                 
-/* 	printk("set_mem_map: Setting map %i range to %x - %x on socket %i, speed is %i, active = %i \n",map, region.start,region.end,sock,mem->speed,mem->flags & MAP_ACTIVE);  */
+		indirect_resetbit(sock, I365_ADDRWIN, I365_ENA_MEM(map));
 
 	/* write the start address */
 	base = I365_MEM(map);
 	i = (region.start >> 12) & 0x0fff;
-	if (mem->flags & MAP_16BIT) 
+	if (mem->flags & MAP_16BIT)
 		i |= I365_MEM_16BIT;
 	if (mem->flags & MAP_0WS)
-		i |= I365_MEM_0WS;	
-	indirect_write16(sock,base+I365_W_START,i);
-		               
+		i |= I365_MEM_0WS;
+	indirect_write16(sock, base+I365_W_START, i);
+
 	/* write the stop address */
-	
-	i= (region.end >> 12) & 0x0fff;
+
+	i = (region.end >> 12) & 0x0fff;
 	switch (to_cycles(mem->speed)) {
-		case 0:
-			break;
-		case 1:
-			i |= I365_MEM_WS0;
-			break;
-		case 2:
-			i |= I365_MEM_WS1;
-			break;
-		default:
-			i |= I365_MEM_WS1 | I365_MEM_WS0;
-			break;
+	case 0:
+		break;
+	case 1:
+		i |= I365_MEM_WS0;
+		break;
+	case 2:
+		i |= I365_MEM_WS1;
+		break;
+	default:
+		i |= I365_MEM_WS1 | I365_MEM_WS0;
+		break;
 	}
-	
-	indirect_write16(sock,base+I365_W_STOP,i);
-	
+
+	indirect_write16(sock, base+I365_W_STOP, i);
+
 	/* card start */
-	
+
 	i = ((mem->card_start - region.start) >> 12) & 0x3fff;
 	if (mem->flags & MAP_WRPROT)
 		i |= I365_MEM_WRPROT;
-	if (mem->flags & MAP_ATTRIB) {
-/*		printk("requesting attribute memory for socket %i\n",sock);*/
+	if (mem->flags & MAP_ATTRIB)
 		i |= I365_MEM_REG;
-	} else {
-/*		printk("requesting normal memory for socket %i\n",sock);*/
-	}
-	indirect_write16(sock,base+I365_W_OFF,i);
-	
+	indirect_write16(sock, base+I365_W_OFF, i);
+
 	/* Enable the window if necessary */
 	if (mem->flags & MAP_ACTIVE)
 		indirect_setbit(sock, I365_ADDRWIN, I365_ENA_MEM(map));
-	            
-	leave("i82092aa_set_mem_map");
+
 	return 0;
 }
 
@@ -691,11 +667,9 @@ static int i82092aa_module_init(void)
 
 static void i82092aa_module_exit(void)
 {
-	enter("i82092aa_module_exit");
 	pci_unregister_driver(&i82092aa_pci_driver);
-	if (sockets[0].io_base>0)
-			 release_region(sockets[0].io_base, 2);
-	leave("i82092aa_module_exit");
+	if (sockets[0].io_base > 0)
+		release_region(sockets[0].io_base, 2);
 }
 
 module_init(i82092aa_module_init);
diff --git a/drivers/pcmcia/i82092aa.h b/drivers/pcmcia/i82092aa.h
index 4586c43c78e2..0f851acab7e5 100644
--- a/drivers/pcmcia/i82092aa.h
+++ b/drivers/pcmcia/i82092aa.h
@@ -4,17 +4,6 @@
 
 #include <linux/interrupt.h>
 
-/* Debuging defines */
-#ifdef NOTRACE
-#define enter(x)   printk("Enter: %s, %s line %i\n",x,__FILE__,__LINE__)
-#define leave(x)   printk("Leave: %s, %s line %i\n",x,__FILE__,__LINE__)
-#else
-#define enter(x)   do {} while (0)
-#define leave(x)   do {} while (0)
-#endif
-
-
-
 /* prototypes */
 
 static int  i82092aa_pci_probe(struct pci_dev *dev, const struct pci_device_id *id);
diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 2eb28cc2d2dc..cd5a6c95dbdc 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -712,7 +712,7 @@ struct phy *phy_optional_get(struct device *dev, const char *string)
 {
 	struct phy *phy = phy_get(dev, string);
 
-	if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV))
+	if (PTR_ERR(phy) == -ENODEV)
 		phy = NULL;
 
 	return phy;
@@ -766,7 +766,7 @@ struct phy *devm_phy_optional_get(struct device *dev, const char *string)
 {
 	struct phy *phy = devm_phy_get(dev, string);
 
-	if (IS_ERR(phy) && (PTR_ERR(phy) == -ENODEV))
+	if (PTR_ERR(phy) == -ENODEV)
 		phy = NULL;
 
 	return phy;
diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
index 21c370dbbfba..bddf2c5dd3bf 100644
--- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
+++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c
@@ -10,6 +10,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/module.h>
+#include <linux/pinctrl/machine.h>
 #include <linux/pinctrl/pinconf.h>
 #include <linux/pinctrl/pinconf-generic.h>
 #include <linux/pinctrl/pinmux.h>
diff --git a/drivers/platform/chrome/chromeos_laptop.c b/drivers/platform/chrome/chromeos_laptop.c
index 8723bcf10c93..4f3651fcd9fe 100644
--- a/drivers/platform/chrome/chromeos_laptop.c
+++ b/drivers/platform/chrome/chromeos_laptop.c
@@ -63,7 +63,7 @@ struct acpi_peripheral {
 struct chromeos_laptop {
 	/*
 	 * Note that we can't mark this pointer as const because
-	 * i2c_new_probed_device() changes passed in I2C board info, so.
+	 * i2c_new_scanned_device() changes passed in I2C board info, so.
 	 */
 	struct i2c_peripheral *i2c_peripherals;
 	unsigned int num_i2c_peripherals;
@@ -87,8 +87,8 @@ chromes_laptop_instantiate_i2c_device(struct i2c_adapter *adapter,
 	 * address we scan secondary addresses. In any case the client
 	 * structure gets assigned primary address.
 	 */
-	client = i2c_new_probed_device(adapter, info, addr_list, NULL);
-	if (!client && alt_addr) {
+	client = i2c_new_scanned_device(adapter, info, addr_list, NULL);
+	if (IS_ERR(client) && alt_addr) {
 		struct i2c_board_info dummy_info = {
 			I2C_BOARD_INFO("dummy", info->addr),
 		};
@@ -97,9 +97,9 @@ chromes_laptop_instantiate_i2c_device(struct i2c_adapter *adapter,
 		};
 		struct i2c_client *dummy;
 
-		dummy = i2c_new_probed_device(adapter, &dummy_info,
-					      alt_addr_list, NULL);
-		if (dummy) {
+		dummy = i2c_new_scanned_device(adapter, &dummy_info,
+					       alt_addr_list, NULL);
+		if (!IS_ERR(dummy)) {
 			pr_debug("%d-%02x is probed at %02x\n",
 				 adapter->nr, info->addr, dummy->addr);
 			i2c_unregister_device(dummy);
@@ -107,12 +107,14 @@ chromes_laptop_instantiate_i2c_device(struct i2c_adapter *adapter,
 		}
 	}
 
-	if (!client)
+	if (IS_ERR(client)) {
+		client = NULL;
 		pr_debug("failed to register device %d-%02x\n",
 			 adapter->nr, info->addr);
-	else
+	} else {
 		pr_debug("added i2c device %d-%02x\n",
 			 adapter->nr, info->addr);
+	}
 
 	return client;
 }
diff --git a/drivers/platform/chrome/cros_ec.c b/drivers/platform/chrome/cros_ec.c
index 6d6ce86a1408..6fc8f2c3ac51 100644
--- a/drivers/platform/chrome/cros_ec.c
+++ b/drivers/platform/chrome/cros_ec.c
@@ -16,7 +16,8 @@
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
 #include <linux/suspend.h>
-#include <asm/unaligned.h>
+
+#include "cros_ec.h"
 
 #define CROS_EC_DEV_EC_INDEX 0
 #define CROS_EC_DEV_PD_INDEX 1
diff --git a/drivers/platform/chrome/cros_ec.h b/drivers/platform/chrome/cros_ec.h
new file mode 100644
index 000000000000..e69fc1ff68b4
--- /dev/null
+++ b/drivers/platform/chrome/cros_ec.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ChromeOS Embedded Controller core interface.
+ *
+ * Copyright (C) 2020 Google LLC
+ */
+
+#ifndef __CROS_EC_H
+#define __CROS_EC_H
+
+int cros_ec_register(struct cros_ec_device *ec_dev);
+int cros_ec_unregister(struct cros_ec_device *ec_dev);
+
+int cros_ec_suspend(struct cros_ec_device *ec_dev);
+int cros_ec_resume(struct cros_ec_device *ec_dev);
+
+bool cros_ec_handle_event(struct cros_ec_device *ec_dev);
+
+#endif /* __CROS_EC_H */
diff --git a/drivers/platform/chrome/cros_ec_chardev.c b/drivers/platform/chrome/cros_ec_chardev.c
index 74ded441bb50..c65e70bc168d 100644
--- a/drivers/platform/chrome/cros_ec_chardev.c
+++ b/drivers/platform/chrome/cros_ec_chardev.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/fs.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
 #include <linux/notifier.h>
diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c
index 6ae484989d1f..ecfada00e6c5 100644
--- a/drivers/platform/chrome/cros_ec_debugfs.c
+++ b/drivers/platform/chrome/cros_ec_debugfs.c
@@ -7,7 +7,6 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/platform_data/cros_ec_commands.h>
diff --git a/drivers/platform/chrome/cros_ec_i2c.c b/drivers/platform/chrome/cros_ec_i2c.c
index 9bd97bc8454b..6119eccd8a18 100644
--- a/drivers/platform/chrome/cros_ec_i2c.c
+++ b/drivers/platform/chrome/cros_ec_i2c.c
@@ -14,6 +14,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#include "cros_ec.h"
+
 /**
  * Request format for protocol v3
  * byte 0	0xda (EC_COMMAND_PROTOCOL_3)
diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c
index e5996821d08b..93a71e93a2f1 100644
--- a/drivers/platform/chrome/cros_ec_ishtp.c
+++ b/drivers/platform/chrome/cros_ec_ishtp.c
@@ -14,6 +14,8 @@
 #include <linux/platform_data/cros_ec_proto.h>
 #include <linux/intel-ish-client-if.h>
 
+#include "cros_ec.h"
+
 /*
  * ISH TX/RX ring buffer pool size
  *
@@ -76,7 +78,7 @@ struct cros_ish_in_msg {
  *
  * The writers are .reset() and .probe() function.
  */
-DECLARE_RWSEM(init_lock);
+static DECLARE_RWSEM(init_lock);
 
 /**
  * struct response_info - Encapsulate firmware response related
diff --git a/drivers/platform/chrome/cros_ec_lightbar.c b/drivers/platform/chrome/cros_ec_lightbar.c
index c0f2eec35a48..b4c110c5fee0 100644
--- a/drivers/platform/chrome/cros_ec_lightbar.c
+++ b/drivers/platform/chrome/cros_ec_lightbar.c
@@ -8,7 +8,6 @@
 #include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/kobject.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
index dccf479c6625..1f7861944044 100644
--- a/drivers/platform/chrome/cros_ec_lpc.c
+++ b/drivers/platform/chrome/cros_ec_lpc.c
@@ -23,6 +23,7 @@
 #include <linux/printk.h>
 #include <linux/suspend.h>
 
+#include "cros_ec.h"
 #include "cros_ec_lpc_mec.h"
 
 #define DRV_NAME "cros_ec_lpcs"
@@ -396,7 +397,7 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
 	 * Some boards do not have an IRQ allotted for cros_ec_lpc,
 	 * which makes ENXIO an expected (and safe) scenario.
 	 */
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq > 0)
 		ec_dev->irq = irq;
 	else if (irq != -ENXIO) {
diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
index da1b1c450433..3cfa643f1d07 100644
--- a/drivers/platform/chrome/cros_ec_proto.c
+++ b/drivers/platform/chrome/cros_ec_proto.c
@@ -54,8 +54,6 @@ static int send_command(struct cros_ec_device *ec_dev,
 	int ret;
 	int (*xfer_fxn)(struct cros_ec_device *ec, struct cros_ec_command *msg);
 
-	trace_cros_ec_cmd(msg);
-
 	if (ec_dev->proto_version > 2)
 		xfer_fxn = ec_dev->pkt_xfer;
 	else
@@ -72,7 +70,9 @@ static int send_command(struct cros_ec_device *ec_dev,
 		return -EIO;
 	}
 
+	trace_cros_ec_request_start(msg);
 	ret = (*xfer_fxn)(ec_dev, msg);
+	trace_cros_ec_request_done(msg, ret);
 	if (msg->result == EC_RES_IN_PROGRESS) {
 		int i;
 		struct cros_ec_command *status_msg;
@@ -95,7 +95,9 @@ static int send_command(struct cros_ec_device *ec_dev,
 		for (i = 0; i < EC_COMMAND_RETRIES; i++) {
 			usleep_range(10000, 11000);
 
+			trace_cros_ec_request_start(status_msg);
 			ret = (*xfer_fxn)(ec_dev, status_msg);
+			trace_cros_ec_request_done(status_msg, ret);
 			if (ret == -EAGAIN)
 				continue;
 			if (ret < 0)
diff --git a/drivers/platform/chrome/cros_ec_rpmsg.c b/drivers/platform/chrome/cros_ec_rpmsg.c
index bd068afe43b5..dbc3f5523b83 100644
--- a/drivers/platform/chrome/cros_ec_rpmsg.c
+++ b/drivers/platform/chrome/cros_ec_rpmsg.c
@@ -13,6 +13,8 @@
 #include <linux/rpmsg.h>
 #include <linux/slab.h>
 
+#include "cros_ec.h"
+
 #define EC_MSG_TIMEOUT_MS	200
 #define HOST_COMMAND_MARK	1
 #define HOST_EVENT_MARK		2
diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c
index 04d8879689e9..79fefd3bb0fa 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub.c
@@ -9,7 +9,6 @@
 #include <linux/init.h>
 #include <linux/device.h>
 #include <linux/module.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
 #include <linux/platform_data/cros_ec_sensorhub.h>
diff --git a/drivers/platform/chrome/cros_ec_spi.c b/drivers/platform/chrome/cros_ec_spi.c
index a831bd5a5b2f..46786d2d679a 100644
--- a/drivers/platform/chrome/cros_ec_spi.c
+++ b/drivers/platform/chrome/cros_ec_spi.c
@@ -14,6 +14,8 @@
 #include <linux/spi/spi.h>
 #include <uapi/linux/sched/types.h>
 
+#include "cros_ec.h"
+
 /* The header byte, which follows the preamble */
 #define EC_MSG_HEADER			0xec
 
diff --git a/drivers/platform/chrome/cros_ec_sysfs.c b/drivers/platform/chrome/cros_ec_sysfs.c
index 74d36b8d4f46..07dac97ad57c 100644
--- a/drivers/platform/chrome/cros_ec_sysfs.c
+++ b/drivers/platform/chrome/cros_ec_sysfs.c
@@ -8,7 +8,6 @@
 #include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/kobject.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
diff --git a/drivers/platform/chrome/cros_ec_trace.c b/drivers/platform/chrome/cros_ec_trace.c
index 5af1d66d9eca..523a39bd0ff6 100644
--- a/drivers/platform/chrome/cros_ec_trace.c
+++ b/drivers/platform/chrome/cros_ec_trace.c
@@ -8,6 +8,11 @@
 // Generate the list using the following script:
 // sed -n 's/^#define \(EC_CMD_[[:alnum:]_]*\)\s.*/\tTRACE_SYMBOL(\1), \\/p' include/linux/platform_data/cros_ec_commands.h
 #define EC_CMDS \
+	TRACE_SYMBOL(EC_CMD_ACPI_READ), \
+	TRACE_SYMBOL(EC_CMD_ACPI_WRITE), \
+	TRACE_SYMBOL(EC_CMD_ACPI_BURST_ENABLE), \
+	TRACE_SYMBOL(EC_CMD_ACPI_BURST_DISABLE), \
+	TRACE_SYMBOL(EC_CMD_ACPI_QUERY_EVENT), \
 	TRACE_SYMBOL(EC_CMD_PROTO_VERSION), \
 	TRACE_SYMBOL(EC_CMD_HELLO), \
 	TRACE_SYMBOL(EC_CMD_GET_VERSION), \
@@ -22,6 +27,8 @@
 	TRACE_SYMBOL(EC_CMD_GET_PROTOCOL_INFO), \
 	TRACE_SYMBOL(EC_CMD_GSV_PAUSE_IN_S5), \
 	TRACE_SYMBOL(EC_CMD_GET_FEATURES), \
+	TRACE_SYMBOL(EC_CMD_GET_SKU_ID), \
+	TRACE_SYMBOL(EC_CMD_SET_SKU_ID), \
 	TRACE_SYMBOL(EC_CMD_FLASH_INFO), \
 	TRACE_SYMBOL(EC_CMD_FLASH_READ), \
 	TRACE_SYMBOL(EC_CMD_FLASH_WRITE), \
@@ -29,6 +36,8 @@
 	TRACE_SYMBOL(EC_CMD_FLASH_PROTECT), \
 	TRACE_SYMBOL(EC_CMD_FLASH_REGION_INFO), \
 	TRACE_SYMBOL(EC_CMD_VBNV_CONTEXT), \
+	TRACE_SYMBOL(EC_CMD_FLASH_SPI_INFO), \
+	TRACE_SYMBOL(EC_CMD_FLASH_SELECT), \
 	TRACE_SYMBOL(EC_CMD_PWM_GET_FAN_TARGET_RPM), \
 	TRACE_SYMBOL(EC_CMD_PWM_SET_FAN_TARGET_RPM), \
 	TRACE_SYMBOL(EC_CMD_PWM_GET_KEYBOARD_BACKLIGHT), \
@@ -40,6 +49,8 @@
 	TRACE_SYMBOL(EC_CMD_LED_CONTROL), \
 	TRACE_SYMBOL(EC_CMD_VBOOT_HASH), \
 	TRACE_SYMBOL(EC_CMD_MOTION_SENSE_CMD), \
+	TRACE_SYMBOL(EC_CMD_FORCE_LID_OPEN), \
+	TRACE_SYMBOL(EC_CMD_CONFIG_POWER_BUTTON), \
 	TRACE_SYMBOL(EC_CMD_USB_CHARGE_SET_MODE), \
 	TRACE_SYMBOL(EC_CMD_PSTORE_INFO), \
 	TRACE_SYMBOL(EC_CMD_PSTORE_READ), \
@@ -50,6 +61,9 @@
 	TRACE_SYMBOL(EC_CMD_RTC_SET_ALARM), \
 	TRACE_SYMBOL(EC_CMD_PORT80_LAST_BOOT), \
 	TRACE_SYMBOL(EC_CMD_PORT80_READ), \
+	TRACE_SYMBOL(EC_CMD_VSTORE_INFO), \
+	TRACE_SYMBOL(EC_CMD_VSTORE_READ), \
+	TRACE_SYMBOL(EC_CMD_VSTORE_WRITE), \
 	TRACE_SYMBOL(EC_CMD_THERMAL_SET_THRESHOLD), \
 	TRACE_SYMBOL(EC_CMD_THERMAL_GET_THRESHOLD), \
 	TRACE_SYMBOL(EC_CMD_THERMAL_AUTO_FAN_CTRL), \
@@ -59,10 +73,12 @@
 	TRACE_SYMBOL(EC_CMD_MKBP_STATE), \
 	TRACE_SYMBOL(EC_CMD_MKBP_INFO), \
 	TRACE_SYMBOL(EC_CMD_MKBP_SIMULATE_KEY), \
+	TRACE_SYMBOL(EC_CMD_GET_KEYBOARD_ID), \
 	TRACE_SYMBOL(EC_CMD_MKBP_SET_CONFIG), \
 	TRACE_SYMBOL(EC_CMD_MKBP_GET_CONFIG), \
 	TRACE_SYMBOL(EC_CMD_KEYSCAN_SEQ_CTRL), \
 	TRACE_SYMBOL(EC_CMD_GET_NEXT_EVENT), \
+	TRACE_SYMBOL(EC_CMD_KEYBOARD_FACTORY_TEST), \
 	TRACE_SYMBOL(EC_CMD_TEMP_SENSOR_GET_INFO), \
 	TRACE_SYMBOL(EC_CMD_HOST_EVENT_GET_B), \
 	TRACE_SYMBOL(EC_CMD_HOST_EVENT_GET_SMI_MASK), \
@@ -73,6 +89,7 @@
 	TRACE_SYMBOL(EC_CMD_HOST_EVENT_CLEAR), \
 	TRACE_SYMBOL(EC_CMD_HOST_EVENT_SET_WAKE_MASK), \
 	TRACE_SYMBOL(EC_CMD_HOST_EVENT_CLEAR_B), \
+	TRACE_SYMBOL(EC_CMD_HOST_EVENT), \
 	TRACE_SYMBOL(EC_CMD_SWITCH_ENABLE_BKLIGHT), \
 	TRACE_SYMBOL(EC_CMD_SWITCH_ENABLE_WIRELESS), \
 	TRACE_SYMBOL(EC_CMD_GPIO_SET), \
@@ -92,36 +109,102 @@
 	TRACE_SYMBOL(EC_CMD_CHARGE_STATE), \
 	TRACE_SYMBOL(EC_CMD_CHARGE_CURRENT_LIMIT), \
 	TRACE_SYMBOL(EC_CMD_EXTERNAL_POWER_LIMIT), \
+	TRACE_SYMBOL(EC_CMD_OVERRIDE_DEDICATED_CHARGER_LIMIT), \
+	TRACE_SYMBOL(EC_CMD_HIBERNATION_DELAY), \
 	TRACE_SYMBOL(EC_CMD_HOST_SLEEP_EVENT), \
+	TRACE_SYMBOL(EC_CMD_DEVICE_EVENT), \
 	TRACE_SYMBOL(EC_CMD_SB_READ_WORD), \
 	TRACE_SYMBOL(EC_CMD_SB_WRITE_WORD), \
 	TRACE_SYMBOL(EC_CMD_SB_READ_BLOCK), \
 	TRACE_SYMBOL(EC_CMD_SB_WRITE_BLOCK), \
 	TRACE_SYMBOL(EC_CMD_BATTERY_VENDOR_PARAM), \
+	TRACE_SYMBOL(EC_CMD_SB_FW_UPDATE), \
+	TRACE_SYMBOL(EC_CMD_ENTERING_MODE), \
+	TRACE_SYMBOL(EC_CMD_I2C_PASSTHRU_PROTECT), \
+	TRACE_SYMBOL(EC_CMD_CEC_WRITE_MSG), \
+	TRACE_SYMBOL(EC_CMD_CEC_SET), \
+	TRACE_SYMBOL(EC_CMD_CEC_GET), \
 	TRACE_SYMBOL(EC_CMD_EC_CODEC), \
 	TRACE_SYMBOL(EC_CMD_EC_CODEC_DMIC), \
 	TRACE_SYMBOL(EC_CMD_EC_CODEC_I2S_RX), \
 	TRACE_SYMBOL(EC_CMD_EC_CODEC_WOV), \
 	TRACE_SYMBOL(EC_CMD_REBOOT_EC), \
 	TRACE_SYMBOL(EC_CMD_GET_PANIC_INFO), \
-	TRACE_SYMBOL(EC_CMD_ACPI_READ), \
-	TRACE_SYMBOL(EC_CMD_ACPI_WRITE), \
-	TRACE_SYMBOL(EC_CMD_ACPI_QUERY_EVENT), \
-	TRACE_SYMBOL(EC_CMD_CEC_WRITE_MSG), \
-	TRACE_SYMBOL(EC_CMD_CEC_SET), \
-	TRACE_SYMBOL(EC_CMD_CEC_GET), \
 	TRACE_SYMBOL(EC_CMD_REBOOT), \
 	TRACE_SYMBOL(EC_CMD_RESEND_RESPONSE), \
 	TRACE_SYMBOL(EC_CMD_VERSION0), \
 	TRACE_SYMBOL(EC_CMD_PD_EXCHANGE_STATUS), \
+	TRACE_SYMBOL(EC_CMD_PD_HOST_EVENT_STATUS), \
 	TRACE_SYMBOL(EC_CMD_USB_PD_CONTROL), \
 	TRACE_SYMBOL(EC_CMD_USB_PD_PORTS), \
 	TRACE_SYMBOL(EC_CMD_USB_PD_POWER_INFO), \
 	TRACE_SYMBOL(EC_CMD_CHARGE_PORT_COUNT), \
+	TRACE_SYMBOL(EC_CMD_USB_PD_FW_UPDATE), \
+	TRACE_SYMBOL(EC_CMD_USB_PD_RW_HASH_ENTRY), \
+	TRACE_SYMBOL(EC_CMD_USB_PD_DEV_INFO), \
 	TRACE_SYMBOL(EC_CMD_USB_PD_DISCOVERY), \
 	TRACE_SYMBOL(EC_CMD_PD_CHARGE_PORT_OVERRIDE), \
 	TRACE_SYMBOL(EC_CMD_PD_GET_LOG_ENTRY), \
-	TRACE_SYMBOL(EC_CMD_USB_PD_MUX_INFO)
+	TRACE_SYMBOL(EC_CMD_USB_PD_GET_AMODE), \
+	TRACE_SYMBOL(EC_CMD_USB_PD_SET_AMODE), \
+	TRACE_SYMBOL(EC_CMD_PD_WRITE_LOG_ENTRY), \
+	TRACE_SYMBOL(EC_CMD_PD_CONTROL), \
+	TRACE_SYMBOL(EC_CMD_USB_PD_MUX_INFO), \
+	TRACE_SYMBOL(EC_CMD_PD_CHIP_INFO), \
+	TRACE_SYMBOL(EC_CMD_RWSIG_CHECK_STATUS), \
+	TRACE_SYMBOL(EC_CMD_RWSIG_ACTION), \
+	TRACE_SYMBOL(EC_CMD_EFS_VERIFY), \
+	TRACE_SYMBOL(EC_CMD_GET_CROS_BOARD_INFO), \
+	TRACE_SYMBOL(EC_CMD_SET_CROS_BOARD_INFO), \
+	TRACE_SYMBOL(EC_CMD_GET_UPTIME_INFO), \
+	TRACE_SYMBOL(EC_CMD_ADD_ENTROPY), \
+	TRACE_SYMBOL(EC_CMD_ADC_READ), \
+	TRACE_SYMBOL(EC_CMD_ROLLBACK_INFO), \
+	TRACE_SYMBOL(EC_CMD_AP_RESET), \
+	TRACE_SYMBOL(EC_CMD_CR51_BASE), \
+	TRACE_SYMBOL(EC_CMD_CR51_LAST), \
+	TRACE_SYMBOL(EC_CMD_FP_PASSTHRU), \
+	TRACE_SYMBOL(EC_CMD_FP_MODE), \
+	TRACE_SYMBOL(EC_CMD_FP_INFO), \
+	TRACE_SYMBOL(EC_CMD_FP_FRAME), \
+	TRACE_SYMBOL(EC_CMD_FP_TEMPLATE), \
+	TRACE_SYMBOL(EC_CMD_FP_CONTEXT), \
+	TRACE_SYMBOL(EC_CMD_FP_STATS), \
+	TRACE_SYMBOL(EC_CMD_FP_SEED), \
+	TRACE_SYMBOL(EC_CMD_FP_ENC_STATUS), \
+	TRACE_SYMBOL(EC_CMD_TP_SELF_TEST), \
+	TRACE_SYMBOL(EC_CMD_TP_FRAME_INFO), \
+	TRACE_SYMBOL(EC_CMD_TP_FRAME_SNAPSHOT), \
+	TRACE_SYMBOL(EC_CMD_TP_FRAME_GET), \
+	TRACE_SYMBOL(EC_CMD_BATTERY_GET_STATIC), \
+	TRACE_SYMBOL(EC_CMD_BATTERY_GET_DYNAMIC), \
+	TRACE_SYMBOL(EC_CMD_CHARGER_CONTROL), \
+	TRACE_SYMBOL(EC_CMD_BOARD_SPECIFIC_BASE), \
+	TRACE_SYMBOL(EC_CMD_BOARD_SPECIFIC_LAST)
+
+/* See the enum ec_status in include/linux/platform_data/cros_ec_commands.h */
+#define EC_RESULT \
+	TRACE_SYMBOL(EC_RES_SUCCESS), \
+	TRACE_SYMBOL(EC_RES_INVALID_COMMAND), \
+	TRACE_SYMBOL(EC_RES_ERROR), \
+	TRACE_SYMBOL(EC_RES_INVALID_PARAM), \
+	TRACE_SYMBOL(EC_RES_ACCESS_DENIED), \
+	TRACE_SYMBOL(EC_RES_INVALID_RESPONSE), \
+	TRACE_SYMBOL(EC_RES_INVALID_VERSION), \
+	TRACE_SYMBOL(EC_RES_INVALID_CHECKSUM), \
+	TRACE_SYMBOL(EC_RES_IN_PROGRESS), \
+	TRACE_SYMBOL(EC_RES_UNAVAILABLE), \
+	TRACE_SYMBOL(EC_RES_TIMEOUT), \
+	TRACE_SYMBOL(EC_RES_OVERFLOW), \
+	TRACE_SYMBOL(EC_RES_INVALID_HEADER), \
+	TRACE_SYMBOL(EC_RES_REQUEST_TRUNCATED), \
+	TRACE_SYMBOL(EC_RES_RESPONSE_TOO_BIG), \
+	TRACE_SYMBOL(EC_RES_BUS_ERROR), \
+	TRACE_SYMBOL(EC_RES_BUSY), \
+	TRACE_SYMBOL(EC_RES_INVALID_HEADER_VERSION), \
+	TRACE_SYMBOL(EC_RES_INVALID_HEADER_CRC), \
+	TRACE_SYMBOL(EC_RES_INVALID_DATA_CRC), \
+	TRACE_SYMBOL(EC_RES_DUP_UNAVAILABLE)
 
 #define CREATE_TRACE_POINTS
 #include "cros_ec_trace.h"
diff --git a/drivers/platform/chrome/cros_ec_trace.h b/drivers/platform/chrome/cros_ec_trace.h
index 0dd4df30fa89..e9fb05f89ef0 100644
--- a/drivers/platform/chrome/cros_ec_trace.h
+++ b/drivers/platform/chrome/cros_ec_trace.h
@@ -18,7 +18,7 @@
 
 #include <linux/tracepoint.h>
 
-DECLARE_EVENT_CLASS(cros_ec_cmd_class,
+TRACE_EVENT(cros_ec_request_start,
 	TP_PROTO(struct cros_ec_command *cmd),
 	TP_ARGS(cmd),
 	TP_STRUCT__entry(
@@ -33,10 +33,26 @@ DECLARE_EVENT_CLASS(cros_ec_cmd_class,
 		  __print_symbolic(__entry->command, EC_CMDS))
 );
 
-
-DEFINE_EVENT(cros_ec_cmd_class, cros_ec_cmd,
-	TP_PROTO(struct cros_ec_command *cmd),
-	TP_ARGS(cmd)
+TRACE_EVENT(cros_ec_request_done,
+	TP_PROTO(struct cros_ec_command *cmd, int retval),
+	TP_ARGS(cmd, retval),
+	TP_STRUCT__entry(
+		__field(uint32_t, version)
+		__field(uint32_t, command)
+		__field(uint32_t, result)
+		__field(int, retval)
+	),
+	TP_fast_assign(
+		__entry->version = cmd->version;
+		__entry->command = cmd->command;
+		__entry->result = cmd->result;
+		__entry->retval = retval;
+	),
+	TP_printk("version: %u, command: %s, ec result: %s, retval: %d",
+		  __entry->version,
+		  __print_symbolic(__entry->command, EC_CMDS),
+		  __print_symbolic(__entry->result, EC_RESULT),
+		  __entry->retval)
 );
 
 
diff --git a/drivers/platform/chrome/cros_ec_vbc.c b/drivers/platform/chrome/cros_ec_vbc.c
index f11a1283e5c8..8edae465105c 100644
--- a/drivers/platform/chrome/cros_ec_vbc.c
+++ b/drivers/platform/chrome/cros_ec_vbc.c
@@ -6,7 +6,6 @@
 
 #include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
diff --git a/drivers/platform/chrome/cros_usbpd_logger.c b/drivers/platform/chrome/cros_usbpd_logger.c
index 374cdd1e868a..7de3ea75ef46 100644
--- a/drivers/platform/chrome/cros_usbpd_logger.c
+++ b/drivers/platform/chrome/cros_usbpd_logger.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/ktime.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/math64.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
diff --git a/drivers/platform/chrome/wilco_ec/Kconfig b/drivers/platform/chrome/wilco_ec/Kconfig
index 365f30e116ee..49e8530ca0ac 100644
--- a/drivers/platform/chrome/wilco_ec/Kconfig
+++ b/drivers/platform/chrome/wilco_ec/Kconfig
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config WILCO_EC
 	tristate "ChromeOS Wilco Embedded Controller"
-	depends on ACPI && X86 && CROS_EC_LPC && LEDS_CLASS
+	depends on X86 || COMPILE_TEST
+	depends on ACPI && CROS_EC_LPC && LEDS_CLASS
 	help
 	  If you say Y here, you get support for talking to the ChromeOS
 	  Wilco EC over an eSPI bus. This uses a simple byte-level protocol
diff --git a/drivers/platform/chrome/wilco_ec/core.c b/drivers/platform/chrome/wilco_ec/core.c
index 5210c357feef..5b42992bff38 100644
--- a/drivers/platform/chrome/wilco_ec/core.c
+++ b/drivers/platform/chrome/wilco_ec/core.c
@@ -94,7 +94,7 @@ static int wilco_ec_probe(struct platform_device *pdev)
 
 	ret = wilco_ec_add_sysfs(ec);
 	if (ret < 0) {
-		dev_err(dev, "Failed to create sysfs entries: %d", ret);
+		dev_err(dev, "Failed to create sysfs entries: %d\n", ret);
 		goto unregister_rtc;
 	}
 
@@ -137,9 +137,9 @@ static int wilco_ec_remove(struct platform_device *pdev)
 {
 	struct wilco_ec_device *ec = platform_get_drvdata(pdev);
 
+	platform_device_unregister(ec->telem_pdev);
 	platform_device_unregister(ec->charger_pdev);
 	wilco_ec_remove_sysfs(ec);
-	platform_device_unregister(ec->telem_pdev);
 	platform_device_unregister(ec->rtc_pdev);
 	if (ec->debugfs_pdev)
 		platform_device_unregister(ec->debugfs_pdev);
diff --git a/drivers/platform/chrome/wilco_ec/keyboard_leds.c b/drivers/platform/chrome/wilco_ec/keyboard_leds.c
index 5731d1b60e28..6ce9c6782065 100644
--- a/drivers/platform/chrome/wilco_ec/keyboard_leds.c
+++ b/drivers/platform/chrome/wilco_ec/keyboard_leds.c
@@ -69,7 +69,7 @@ static int send_kbbl_msg(struct wilco_ec_device *ec,
 	ret = wilco_ec_mailbox(ec, &msg);
 	if (ret < 0) {
 		dev_err(ec->dev,
-			"Failed sending keyboard LEDs command: %d", ret);
+			"Failed sending keyboard LEDs command: %d\n", ret);
 		return ret;
 	}
 
@@ -94,7 +94,7 @@ static int set_kbbl(struct wilco_ec_device *ec, enum led_brightness brightness)
 
 	if (response.status) {
 		dev_err(ec->dev,
-			"EC reported failure sending keyboard LEDs command: %d",
+			"EC reported failure sending keyboard LEDs command: %d\n",
 			response.status);
 		return -EIO;
 	}
@@ -147,7 +147,7 @@ static int kbbl_init(struct wilco_ec_device *ec)
 
 	if (response.status) {
 		dev_err(ec->dev,
-			"EC reported failure sending keyboard LEDs command: %d",
+			"EC reported failure sending keyboard LEDs command: %d\n",
 			response.status);
 		return -EIO;
 	}
@@ -179,7 +179,7 @@ int wilco_keyboard_leds_init(struct wilco_ec_device *ec)
 	ret = kbbl_exist(ec, &leds_exist);
 	if (ret < 0) {
 		dev_err(ec->dev,
-			"Failed checking keyboard LEDs support: %d", ret);
+			"Failed checking keyboard LEDs support: %d\n", ret);
 		return ret;
 	}
 	if (!leds_exist)
diff --git a/drivers/platform/chrome/wilco_ec/mailbox.c b/drivers/platform/chrome/wilco_ec/mailbox.c
index ced1f9f3dcee..0f98358ea824 100644
--- a/drivers/platform/chrome/wilco_ec/mailbox.c
+++ b/drivers/platform/chrome/wilco_ec/mailbox.c
@@ -163,13 +163,13 @@ static int wilco_ec_transfer(struct wilco_ec_device *ec,
 	}
 
 	if (rs->data_size != EC_MAILBOX_DATA_SIZE) {
-		dev_dbg(ec->dev, "unexpected packet size (%u != %u)",
+		dev_dbg(ec->dev, "unexpected packet size (%u != %u)\n",
 			rs->data_size, EC_MAILBOX_DATA_SIZE);
 		return -EMSGSIZE;
 	}
 
 	if (rs->data_size < msg->response_size) {
-		dev_dbg(ec->dev, "EC didn't return enough data (%u < %zu)",
+		dev_dbg(ec->dev, "EC didn't return enough data (%u < %zu)\n",
 			rs->data_size, msg->response_size);
 		return -EMSGSIZE;
 	}
diff --git a/drivers/platform/chrome/wilco_ec/telemetry.c b/drivers/platform/chrome/wilco_ec/telemetry.c
index 1176d543191a..e06d96fb9426 100644
--- a/drivers/platform/chrome/wilco_ec/telemetry.c
+++ b/drivers/platform/chrome/wilco_ec/telemetry.c
@@ -367,7 +367,7 @@ static int telem_device_probe(struct platform_device *pdev)
 	minor = ida_alloc_max(&telem_ida, TELEM_MAX_DEV-1, GFP_KERNEL);
 	if (minor < 0) {
 		error = minor;
-		dev_err(&pdev->dev, "Failed to find minor number: %d", error);
+		dev_err(&pdev->dev, "Failed to find minor number: %d\n", error);
 		return error;
 	}
 
@@ -427,14 +427,14 @@ static int __init telem_module_init(void)
 
 	ret = class_register(&telem_class);
 	if (ret) {
-		pr_err(DRV_NAME ": Failed registering class: %d", ret);
+		pr_err(DRV_NAME ": Failed registering class: %d\n", ret);
 		return ret;
 	}
 
 	/* Request the kernel for device numbers, starting with minor=0 */
 	ret = alloc_chrdev_region(&dev_num, 0, TELEM_MAX_DEV, TELEM_DEV_NAME);
 	if (ret) {
-		pr_err(DRV_NAME ": Failed allocating dev numbers: %d", ret);
+		pr_err(DRV_NAME ": Failed allocating dev numbers: %d\n", ret);
 		goto destroy_class;
 	}
 	telem_major = MAJOR(dev_num);
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index cef0133aa47a..1ab207ec9c94 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -257,12 +257,12 @@ static int goldfish_pipe_error_convert(int status)
 	}
 }
 
-static int pin_user_pages(unsigned long first_page,
-			  unsigned long last_page,
-			  unsigned int last_page_size,
-			  int is_write,
-			  struct page *pages[MAX_BUFFERS_PER_COMMAND],
-			  unsigned int *iter_last_page_size)
+static int goldfish_pin_pages(unsigned long first_page,
+			      unsigned long last_page,
+			      unsigned int last_page_size,
+			      int is_write,
+			      struct page *pages[MAX_BUFFERS_PER_COMMAND],
+			      unsigned int *iter_last_page_size)
 {
 	int ret;
 	int requested_pages = ((last_page - first_page) >> PAGE_SHIFT) + 1;
@@ -274,7 +274,7 @@ static int pin_user_pages(unsigned long first_page,
 		*iter_last_page_size = last_page_size;
 	}
 
-	ret = get_user_pages_fast(first_page, requested_pages,
+	ret = pin_user_pages_fast(first_page, requested_pages,
 				  !is_write ? FOLL_WRITE : 0,
 				  pages);
 	if (ret <= 0)
@@ -285,18 +285,6 @@ static int pin_user_pages(unsigned long first_page,
 	return ret;
 }
 
-static void release_user_pages(struct page **pages, int pages_count,
-			       int is_write, s32 consumed_size)
-{
-	int i;
-
-	for (i = 0; i < pages_count; i++) {
-		if (!is_write && consumed_size > 0)
-			set_page_dirty(pages[i]);
-		put_page(pages[i]);
-	}
-}
-
 /* Populate the call parameters, merging adjacent pages together */
 static void populate_rw_params(struct page **pages,
 			       int pages_count,
@@ -354,9 +342,9 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
 	if (mutex_lock_interruptible(&pipe->lock))
 		return -ERESTARTSYS;
 
-	pages_count = pin_user_pages(first_page, last_page,
-				     last_page_size, is_write,
-				     pipe->pages, &iter_last_page_size);
+	pages_count = goldfish_pin_pages(first_page, last_page,
+					 last_page_size, is_write,
+					 pipe->pages, &iter_last_page_size);
 	if (pages_count < 0) {
 		mutex_unlock(&pipe->lock);
 		return pages_count;
@@ -372,7 +360,8 @@ static int transfer_max_buffers(struct goldfish_pipe *pipe,
 
 	*consumed_size = pipe->command_buffer->rw_params.consumed_size;
 
-	release_user_pages(pipe->pages, pages_count, is_write, *consumed_size);
+	unpin_user_pages_dirty_lock(pipe->pages, pages_count,
+				    !is_write && *consumed_size > 0);
 
 	mutex_unlock(&pipe->lock);
 	return 0;
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 43bb15e05529..612ef5526226 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -33,9 +33,9 @@
 #include <linux/seq_file.h>
 #include <linux/platform_data/x86/asus-wmi.h>
 #include <linux/platform_device.h>
-#include <linux/thermal.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
+#include <linux/units.h>
 
 #include <acpi/battery.h>
 #include <acpi/video.h>
@@ -1514,9 +1514,8 @@ static ssize_t asus_hwmon_temp1(struct device *dev,
 	if (err < 0)
 		return err;
 
-	value = DECI_KELVIN_TO_CELSIUS((value & 0xFFFF)) * 1000;
-
-	return sprintf(buf, "%d\n", value);
+	return sprintf(buf, "%ld\n",
+		       deci_kelvin_to_millicelsius(value & 0xFFFF));
 }
 
 /* Fan1 */
diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index b102f6dd5693..101d7e791a13 100644
--- a/drivers/platform/x86/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/thermal.h>
 #include <linux/types.h>
+#include <linux/units.h>
 
 MODULE_AUTHOR("Thomas Sujith");
 MODULE_AUTHOR("Zhang Rui");
@@ -302,8 +303,10 @@ static ssize_t aux_show(struct device *dev, struct device_attribute *dev_attr,
 	int result;
 
 	result = sensor_get_auxtrip(attr->handle, idx, &value);
+	if (result)
+		return result;
 
-	return result ? result : sprintf(buf, "%lu", DECI_KELVIN_TO_CELSIUS(value));
+	return sprintf(buf, "%lu", deci_kelvin_to_celsius(value));
 }
 
 static ssize_t aux0_show(struct device *dev,
@@ -332,8 +335,8 @@ static ssize_t aux_store(struct device *dev, struct device_attribute *dev_attr,
 	if (value < 0)
 		return -EINVAL;
 
-	result = sensor_set_auxtrip(attr->handle, idx, 
-				    CELSIUS_TO_DECI_KELVIN(value));
+	result = sensor_set_auxtrip(attr->handle, idx,
+				    celsius_to_deci_kelvin(value));
 	return result ? result : count;
 }
 
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index da794dcfdd92..8eaadbaf8ffa 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -907,13 +907,12 @@ static ssize_t dispatch_proc_write(struct file *file,
 	return ret;
 }
 
-static const struct file_operations dispatch_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= dispatch_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= dispatch_proc_write,
+static const struct proc_ops dispatch_proc_ops = {
+	.proc_open	= dispatch_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= dispatch_proc_write,
 };
 
 static char *next_cmd(char **cmds)
@@ -9984,7 +9983,7 @@ static int __init ibm_init(struct ibm_init_struct *iibm)
 		if (ibm->write)
 			mode |= S_IWUSR;
 		entry = proc_create_data(ibm->name, mode, proc_dir,
-					 &dispatch_proc_fops, ibm);
+					 &dispatch_proc_ops, ibm);
 		if (!entry) {
 			pr_err("unable to create proc entry %s\n", ibm->name);
 			ret = -ENODEV;
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index a1e6569427c3..808944546739 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -1432,13 +1432,12 @@ static ssize_t lcd_proc_write(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations lcd_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= lcd_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= lcd_proc_write,
+static const struct proc_ops lcd_proc_ops = {
+	.proc_open	= lcd_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= lcd_proc_write,
 };
 
 /* Video-Out */
@@ -1539,13 +1538,12 @@ static ssize_t video_proc_write(struct file *file, const char __user *buf,
 	return ret ? -EIO : count;
 }
 
-static const struct file_operations video_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= video_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= video_proc_write,
+static const struct proc_ops video_proc_ops = {
+	.proc_open	= video_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= video_proc_write,
 };
 
 /* Fan status */
@@ -1617,13 +1615,12 @@ static ssize_t fan_proc_write(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations fan_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= fan_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= fan_proc_write,
+static const struct proc_ops fan_proc_ops = {
+	.proc_open	= fan_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= fan_proc_write,
 };
 
 static int keys_proc_show(struct seq_file *m, void *v)
@@ -1662,13 +1659,12 @@ static ssize_t keys_proc_write(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations keys_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= keys_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= keys_proc_write,
+static const struct proc_ops keys_proc_ops = {
+	.proc_open	= keys_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= keys_proc_write,
 };
 
 static int __maybe_unused version_proc_show(struct seq_file *m, void *v)
@@ -1688,16 +1684,16 @@ static void create_toshiba_proc_entries(struct toshiba_acpi_dev *dev)
 {
 	if (dev->backlight_dev)
 		proc_create_data("lcd", S_IRUGO | S_IWUSR, toshiba_proc_dir,
-				 &lcd_proc_fops, dev);
+				 &lcd_proc_ops, dev);
 	if (dev->video_supported)
 		proc_create_data("video", S_IRUGO | S_IWUSR, toshiba_proc_dir,
-				 &video_proc_fops, dev);
+				 &video_proc_ops, dev);
 	if (dev->fan_supported)
 		proc_create_data("fan", S_IRUGO | S_IWUSR, toshiba_proc_dir,
-				 &fan_proc_fops, dev);
+				 &fan_proc_ops, dev);
 	if (dev->hotkey_dev)
 		proc_create_data("keys", S_IRUGO | S_IWUSR, toshiba_proc_dir,
-				 &keys_proc_fops, dev);
+				 &keys_proc_ops, dev);
 	proc_create_single_data("version", S_IRUGO, toshiba_proc_dir,
 			version_proc_show, dev);
 }
diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c
index 36820979bd1c..785a796430fa 100644
--- a/drivers/pnp/isapnp/proc.c
+++ b/drivers/pnp/isapnp/proc.c
@@ -49,10 +49,9 @@ static ssize_t isapnp_proc_bus_read(struct file *file, char __user * buf,
 	return nbytes;
 }
 
-static const struct file_operations isapnp_proc_bus_file_operations = {
-	.owner	= THIS_MODULE,
-	.llseek = isapnp_proc_bus_lseek,
-	.read = isapnp_proc_bus_read,
+static const struct proc_ops isapnp_proc_bus_proc_ops = {
+	.proc_lseek	= isapnp_proc_bus_lseek,
+	.proc_read	= isapnp_proc_bus_read,
 };
 
 static int isapnp_proc_attach_device(struct pnp_dev *dev)
@@ -69,7 +68,7 @@ static int isapnp_proc_attach_device(struct pnp_dev *dev)
 	}
 	sprintf(name, "%02x", dev->number);
 	e = dev->procent = proc_create_data(name, S_IFREG | S_IRUGO, de,
-			&isapnp_proc_bus_file_operations, dev);
+					    &isapnp_proc_bus_proc_ops, dev);
 	if (!e)
 		return -ENOMEM;
 	proc_set_size(e, 256);
diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c
index fe1c8f5d9af0..a806830e3a40 100644
--- a/drivers/pnp/pnpbios/proc.c
+++ b/drivers/pnp/pnpbios/proc.c
@@ -210,13 +210,12 @@ out:
 	return ret;
 }
 
-static const struct file_operations pnpbios_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= pnpbios_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= pnpbios_proc_write,
+static const struct proc_ops pnpbios_proc_ops = {
+	.proc_open	= pnpbios_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= pnpbios_proc_write,
 };
 
 int pnpbios_interface_attach_device(struct pnp_bios_node *node)
@@ -228,13 +227,13 @@ int pnpbios_interface_attach_device(struct pnp_bios_node *node)
 	if (!proc_pnp)
 		return -EIO;
 	if (!pnpbios_dont_use_current_config) {
-		proc_create_data(name, 0644, proc_pnp, &pnpbios_proc_fops,
+		proc_create_data(name, 0644, proc_pnp, &pnpbios_proc_ops,
 				 (void *)(long)(node->handle));
 	}
 
 	if (!proc_pnp_boot)
 		return -EIO;
-	if (proc_create_data(name, 0644, proc_pnp_boot, &pnpbios_proc_fops,
+	if (proc_create_data(name, 0644, proc_pnp_boot, &pnpbios_proc_ops,
 			     (void *)(long)(node->handle + 0x100)))
 		return 0;
 	return -EIO;
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index c721939767eb..0498363203e8 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -141,14 +141,14 @@ config POWER_RESET_LTC2952
 	  down via the LTC2952. Bindings are made in the device tree.
 
 config POWER_RESET_MT6323
-       bool "MediaTek MT6323 power-off driver"
-       depends on MFD_MT6397
-       help
-         The power-off driver is responsible for externally shutdown down
-         the power of a remote MediaTek SoC MT6323 is connected to through
-         controlling a tiny circuit BBPU inside MT6323 RTC.
-
-         Say Y if you have a board where MT6323 could be found.
+	bool "MediaTek MT6323 power-off driver"
+	depends on MFD_MT6397
+	help
+	  The power-off driver is responsible for externally shutdown down
+	  the power of a remote MediaTek SoC MT6323 is connected to through
+	  controlling a tiny circuit BBPU inside MT6323 RTC.
+
+	  Say Y if you have a board where MT6323 could be found.
 
 config POWER_RESET_QNAP
 	bool "QNAP power-off driver"
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index 1c18f465a245..2fe3a627cb53 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -66,7 +66,7 @@
 
 #define SHDW_CFG_NOT_USED	(32)
 
-struct shdwc_config {
+struct shdwc_reg_config {
 	u8 wkup_pin_input;
 	u8 mr_rtcwk_shift;
 	u8 mr_rttwk_shift;
@@ -74,8 +74,17 @@ struct shdwc_config {
 	u8 sr_rttwk_shift;
 };
 
+struct pmc_reg_config {
+	u8 mckr;
+};
+
+struct reg_config {
+	struct shdwc_reg_config shdwc;
+	struct pmc_reg_config pmc;
+};
+
 struct shdwc {
-	const struct shdwc_config *cfg;
+	const struct reg_config *rcfg;
 	struct clk *sclk;
 	void __iomem *shdwc_base;
 	void __iomem *mpddrc_base;
@@ -95,6 +104,7 @@ static const unsigned long long sdwc_dbc_period[] = {
 static void __init at91_wakeup_status(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
+	const struct reg_config *rcfg = shdw->rcfg;
 	u32 reg;
 	char *reason = "unknown";
 
@@ -106,11 +116,11 @@ static void __init at91_wakeup_status(struct platform_device *pdev)
 	if (!reg)
 		return;
 
-	if (SHDW_WK_PIN(reg, shdw->cfg))
+	if (SHDW_WK_PIN(reg, &rcfg->shdwc))
 		reason = "WKUP pin";
-	else if (SHDW_RTCWK(reg, shdw->cfg))
+	else if (SHDW_RTCWK(reg, &rcfg->shdwc))
 		reason = "RTC";
-	else if (SHDW_RTTWK(reg, shdw->cfg))
+	else if (SHDW_RTTWK(reg, &rcfg->shdwc))
 		reason = "RTT";
 
 	pr_info("AT91: Wake-Up source: %s\n", reason);
@@ -131,9 +141,9 @@ static void at91_poweroff(void)
 		"	str	%1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t"
 
 		/* Switch the master clock source to slow clock. */
-		"1:	ldr	r6, [%4, #" __stringify(AT91_PMC_MCKR) "]\n\t"
+		"1:	ldr	r6, [%4, %5]\n\t"
 		"	bic	r6, r6,  #" __stringify(AT91_PMC_CSS) "\n\t"
-		"	str	r6, [%4, #" __stringify(AT91_PMC_MCKR) "]\n\t"
+		"	str	r6, [%4, %5]\n\t"
 		/* Wait for clock switch. */
 		"2:	ldr	r6, [%4, #" __stringify(AT91_PMC_SR) "]\n\t"
 		"	tst	r6, #"	    __stringify(AT91_PMC_MCKRDY) "\n\t"
@@ -148,7 +158,8 @@ static void at91_poweroff(void)
 		  "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF),
 		  "r" (at91_shdwc->shdwc_base),
 		  "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW),
-		  "r" (at91_shdwc->pmc_base)
+		  "r" (at91_shdwc->pmc_base),
+		  "r" (at91_shdwc->rcfg->pmc.mckr)
 		: "r6");
 }
 
@@ -215,6 +226,7 @@ static u32 at91_shdwc_get_wakeup_input(struct platform_device *pdev,
 static void at91_shdwc_dt_configure(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
+	const struct reg_config *rcfg = shdw->rcfg;
 	struct device_node *np = pdev->dev.of_node;
 	u32 mode = 0, tmp, input;
 
@@ -227,10 +239,10 @@ static void at91_shdwc_dt_configure(struct platform_device *pdev)
 		mode |= AT91_SHDW_WKUPDBC(at91_shdwc_debouncer_value(pdev, tmp));
 
 	if (of_property_read_bool(np, "atmel,wakeup-rtc-timer"))
-		mode |= SHDW_RTCWKEN(shdw->cfg);
+		mode |= SHDW_RTCWKEN(&rcfg->shdwc);
 
 	if (of_property_read_bool(np, "atmel,wakeup-rtt-timer"))
-		mode |= SHDW_RTTWKEN(shdw->cfg);
+		mode |= SHDW_RTTWKEN(&rcfg->shdwc);
 
 	dev_dbg(&pdev->dev, "%s: mode = %#x\n", __func__, mode);
 	writel(mode, shdw->shdwc_base + AT91_SHDW_MR);
@@ -239,30 +251,40 @@ static void at91_shdwc_dt_configure(struct platform_device *pdev)
 	writel(input, shdw->shdwc_base + AT91_SHDW_WUIR);
 }
 
-static const struct shdwc_config sama5d2_shdwc_config = {
-	.wkup_pin_input = 0,
-	.mr_rtcwk_shift = 17,
-	.mr_rttwk_shift	= SHDW_CFG_NOT_USED,
-	.sr_rtcwk_shift = 5,
-	.sr_rttwk_shift = SHDW_CFG_NOT_USED,
+static const struct reg_config sama5d2_reg_config = {
+	.shdwc = {
+		.wkup_pin_input = 0,
+		.mr_rtcwk_shift = 17,
+		.mr_rttwk_shift	= SHDW_CFG_NOT_USED,
+		.sr_rtcwk_shift = 5,
+		.sr_rttwk_shift = SHDW_CFG_NOT_USED,
+	},
+	.pmc = {
+		.mckr		= 0x30,
+	},
 };
 
-static const struct shdwc_config sam9x60_shdwc_config = {
-	.wkup_pin_input = 0,
-	.mr_rtcwk_shift = 17,
-	.mr_rttwk_shift = 16,
-	.sr_rtcwk_shift = 5,
-	.sr_rttwk_shift = 4,
+static const struct reg_config sam9x60_reg_config = {
+	.shdwc = {
+		.wkup_pin_input = 0,
+		.mr_rtcwk_shift = 17,
+		.mr_rttwk_shift = 16,
+		.sr_rtcwk_shift = 5,
+		.sr_rttwk_shift = 4,
+	},
+	.pmc = {
+		.mckr		= 0x28,
+	},
 };
 
 static const struct of_device_id at91_shdwc_of_match[] = {
 	{
 		.compatible = "atmel,sama5d2-shdwc",
-		.data = &sama5d2_shdwc_config,
+		.data = &sama5d2_reg_config,
 	},
 	{
 		.compatible = "microchip,sam9x60-shdwc",
-		.data = &sam9x60_shdwc_config,
+		.data = &sam9x60_reg_config,
 	}, {
 		/*sentinel*/
 	}
@@ -303,7 +325,7 @@ static int __init at91_shdwc_probe(struct platform_device *pdev)
 	}
 
 	match = of_match_node(at91_shdwc_of_match, pdev->dev.of_node);
-	at91_shdwc->cfg = match->data;
+	at91_shdwc->rcfg = match->data;
 
 	at91_shdwc->sclk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(at91_shdwc->sclk))
diff --git a/drivers/power/reset/gpio-restart.c b/drivers/power/reset/gpio-restart.c
index 308ca9d9d276..5466eeea261c 100644
--- a/drivers/power/reset/gpio-restart.c
+++ b/drivers/power/reset/gpio-restart.c
@@ -64,9 +64,11 @@ static int gpio_restart_probe(struct platform_device *pdev)
 
 	gpio_restart->reset_gpio = devm_gpiod_get(&pdev->dev, NULL,
 			open_source ? GPIOD_IN : GPIOD_OUT_LOW);
-	if (IS_ERR(gpio_restart->reset_gpio)) {
-		dev_err(&pdev->dev, "Could not get reset GPIO\n");
-		return PTR_ERR(gpio_restart->reset_gpio);
+	ret = PTR_ERR_OR_ZERO(gpio_restart->reset_gpio);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "Could not get reset GPIO\n");
+		return ret;
 	}
 
 	gpio_restart->restart_handler.notifier_call = gpio_restart_notify;
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index 27164a1d3c7c..9a5591ab90d0 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -73,10 +73,10 @@ config WM831X_POWER
 	  provided by Wolfson Microelectronics WM831x PMICs.
 
 config WM8350_POWER
-        tristate "WM8350 PMU support"
-        depends on MFD_WM8350
-        help
-          Say Y here to enable support for the power management unit
+	tristate "WM8350 PMU support"
+	depends on MFD_WM8350
+	help
+	  Say Y here to enable support for the power management unit
 	  provided by the Wolfson Microelectronics WM8350 PMIC.
 
 config TEST_POWER
@@ -209,16 +209,16 @@ config BATTERY_WM97XX
 	  Say Y to enable support for battery measured by WM97xx aux port.
 
 config BATTERY_SBS
-        tristate "SBS Compliant gas gauge"
-        depends on I2C
-        help
+	tristate "SBS Compliant gas gauge"
+	depends on I2C
+	help
 	  Say Y to include support for SBS battery driver for SBS-compliant
 	  gas gauges.
 
 config CHARGER_SBS
-        tristate "SBS Compliant charger"
-        depends on I2C
-        help
+	tristate "SBS Compliant charger"
+	depends on I2C
+	help
 	  Say Y to include support for SBS compliant battery chargers.
 
 config MANAGER_SBS
@@ -484,11 +484,11 @@ config CHARGER_MANAGER
 	depends on REGULATOR
 	select EXTCON
 	help
-          Say Y to enable charger-manager support, which allows multiple
-          chargers attached to a battery and multiple batteries attached to a
-          system. The charger-manager also can monitor charging status in
-          runtime and in suspend-to-RAM by waking up the system periodically
-          with help of suspend_again support.
+	  Say Y to enable charger-manager support, which allows multiple
+	  chargers attached to a battery and multiple batteries attached to a
+	  system. The charger-manager also can monitor charging status in
+	  runtime and in suspend-to-RAM by waking up the system periodically
+	  with help of suspend_again support.
 
 config CHARGER_LT3651
 	tristate "Analog Devices LT3651 charger"
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index 8a0f9d769690..f69550d64f09 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -789,7 +789,7 @@ static int ab8500_charger_max_usb_curr(struct ab8500_charger *di,
 		di->max_usb_in_curr.usb_type_max = USB_CH_IP_CUR_LVL_0P05;
 		ret = -ENXIO;
 		break;
-	};
+	}
 
 	di->max_usb_in_curr.set_max = di->max_usb_in_curr.usb_type_max;
 	dev_dbg(di->dev, "USB Type - 0x%02x MaxCurr: %d",
@@ -1079,7 +1079,7 @@ static int ab8500_charger_get_usb_cur(struct ab8500_charger *di)
 		di->max_usb_in_curr.usb_type_max = USB_CH_IP_CUR_LVL_0P05;
 		ret = -EPERM;
 		break;
-	};
+	}
 	di->max_usb_in_curr.set_max = di->max_usb_in_curr.usb_type_max;
 	return ret;
 }
@@ -2427,7 +2427,7 @@ static void ab8500_charger_usb_state_changed_work(struct work_struct *work)
 
 	default:
 		break;
-	};
+	}
 }
 
 /**
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index c3912ee9eb99..b96f90a82ecf 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -2221,10 +2221,10 @@ static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data)
 						ab8500_fg_update_cap_scalers(di);
 					queue_work(di->fg_wq, &di->fg_work);
 					break;
-				};
+				}
 			default:
 				break;
-			};
+			}
 			break;
 		case POWER_SUPPLY_PROP_TECHNOLOGY:
 			switch (ext->desc->type) {
@@ -2331,7 +2331,7 @@ static int ab8500_fg_init_hw_registers(struct ab8500_fg *di)
 		if (ret) {
 			dev_err(di->dev, "%s write failed AB8505_RTC_PCUT_MAX_TIME_REG\n", __func__);
 			goto out;
-		};
+		}
 
 		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
 			AB8505_RTC_PCUT_FLAG_TIME_REG, di->bm->fg_params->pcut_flag_time);
@@ -2339,7 +2339,7 @@ static int ab8500_fg_init_hw_registers(struct ab8500_fg *di)
 		if (ret) {
 			dev_err(di->dev, "%s write failed AB8505_RTC_PCUT_FLAG_TIME_REG\n", __func__);
 			goto out;
-		};
+		}
 
 		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
 			AB8505_RTC_PCUT_RESTART_REG, di->bm->fg_params->pcut_max_restart);
@@ -2347,7 +2347,7 @@ static int ab8500_fg_init_hw_registers(struct ab8500_fg *di)
 		if (ret) {
 			dev_err(di->dev, "%s write failed AB8505_RTC_PCUT_RESTART_REG\n", __func__);
 			goto out;
-		};
+		}
 
 		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
 			AB8505_RTC_PCUT_DEBOUNCE_REG, di->bm->fg_params->pcut_debounce_time);
@@ -2355,7 +2355,7 @@ static int ab8500_fg_init_hw_registers(struct ab8500_fg *di)
 		if (ret) {
 			dev_err(di->dev, "%s write failed AB8505_RTC_PCUT_DEBOUNCE_REG\n", __func__);
 			goto out;
-		};
+		}
 
 		ret = abx500_set_register_interruptible(di->dev, AB8500_RTC,
 			AB8505_RTC_PCUT_CTL_STATUS_REG, di->bm->fg_params->pcut_enable);
@@ -2363,7 +2363,7 @@ static int ab8500_fg_init_hw_registers(struct ab8500_fg *di)
 		if (ret) {
 			dev_err(di->dev, "%s write failed AB8505_RTC_PCUT_CTL_STATUS_REG\n", __func__);
 			goto out;
-		};
+		}
 	}
 out:
 	return ret;
diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c
index e6e37d4f20e4..2fb33a07879a 100644
--- a/drivers/power/supply/abx500_chargalg.c
+++ b/drivers/power/supply/abx500_chargalg.c
@@ -1823,7 +1823,7 @@ static ssize_t abx500_chargalg_en_store(struct abx500_chargalg *di,
 			"Enter 0. Disable AC/USB Charging\n"
 			"1. Enable AC charging\n"
 			"2. Enable USB Charging\n");
-	};
+	}
 	return strlen(buf);
 }
 
diff --git a/drivers/power/supply/axp20x_ac_power.c b/drivers/power/supply/axp20x_ac_power.c
index 0d34a932b6d5..ac360016b08a 100644
--- a/drivers/power/supply/axp20x_ac_power.c
+++ b/drivers/power/supply/axp20x_ac_power.c
@@ -15,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/power_supply.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
@@ -23,6 +24,9 @@
 #define AXP20X_PWR_STATUS_ACIN_PRESENT	BIT(7)
 #define AXP20X_PWR_STATUS_ACIN_AVAIL	BIT(6)
 
+#define AXP813_ACIN_PATH_SEL		BIT(7)
+#define AXP813_ACIN_PATH_SEL_TO_BIT(x)	(!!(x) << 7)
+
 #define AXP813_VHOLD_MASK		GENMASK(5, 3)
 #define AXP813_VHOLD_UV_TO_BIT(x)	((((x) / 100000) - 40) << 3)
 #define AXP813_VHOLD_REG_TO_UV(x)	\
@@ -40,6 +44,9 @@ struct axp20x_ac_power {
 	struct power_supply *supply;
 	struct iio_channel *acin_v;
 	struct iio_channel *acin_i;
+	bool has_acin_path_sel;
+	unsigned int num_irqs;
+	unsigned int irqs[];
 };
 
 static irqreturn_t axp20x_ac_power_irq(int irq, void *devid)
@@ -86,6 +93,17 @@ static int axp20x_ac_power_get_property(struct power_supply *psy,
 			return ret;
 
 		val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_AVAIL);
+
+		/* ACIN_PATH_SEL disables ACIN even if ACIN_AVAIL is set. */
+		if (val->intval && power->has_acin_path_sel) {
+			ret = regmap_read(power->regmap, AXP813_ACIN_PATH_CTRL,
+					  &reg);
+			if (ret)
+				return ret;
+
+			val->intval = !!(reg & AXP813_ACIN_PATH_SEL);
+		}
+
 		return 0;
 
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
@@ -143,6 +161,11 @@ static int axp813_ac_power_set_property(struct power_supply *psy,
 	struct axp20x_ac_power *power = power_supply_get_drvdata(psy);
 
 	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		return regmap_update_bits(power->regmap, AXP813_ACIN_PATH_CTRL,
+					  AXP813_ACIN_PATH_SEL,
+					  AXP813_ACIN_PATH_SEL_TO_BIT(val->intval));
+
 	case POWER_SUPPLY_PROP_VOLTAGE_MIN:
 		if (val->intval < 4000000 || val->intval > 4700000)
 			return -EINVAL;
@@ -169,7 +192,8 @@ static int axp813_ac_power_set_property(struct power_supply *psy,
 static int axp813_ac_power_prop_writeable(struct power_supply *psy,
 					  enum power_supply_property psp)
 {
-	return psp == POWER_SUPPLY_PROP_VOLTAGE_MIN ||
+	return psp == POWER_SUPPLY_PROP_ONLINE ||
+	       psp == POWER_SUPPLY_PROP_VOLTAGE_MIN ||
 	       psp == POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT;
 }
 
@@ -221,34 +245,86 @@ static const struct power_supply_desc axp813_ac_power_desc = {
 	.set_property = axp813_ac_power_set_property,
 };
 
+static const char * const axp20x_irq_names[] = {
+	"ACIN_PLUGIN",
+	"ACIN_REMOVAL",
+};
+
 struct axp_data {
 	const struct power_supply_desc	*power_desc;
+	const char * const		*irq_names;
+	unsigned int			num_irq_names;
 	bool				acin_adc;
+	bool				acin_path_sel;
 };
 
 static const struct axp_data axp20x_data = {
-	.power_desc = &axp20x_ac_power_desc,
-	.acin_adc = true,
+	.power_desc	= &axp20x_ac_power_desc,
+	.irq_names	= axp20x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp20x_irq_names),
+	.acin_adc	= true,
+	.acin_path_sel	= false,
 };
 
 static const struct axp_data axp22x_data = {
-	.power_desc = &axp22x_ac_power_desc,
-	.acin_adc = false,
+	.power_desc	= &axp22x_ac_power_desc,
+	.irq_names	= axp20x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp20x_irq_names),
+	.acin_adc	= false,
+	.acin_path_sel	= false,
 };
 
 static const struct axp_data axp813_data = {
-	.power_desc = &axp813_ac_power_desc,
-	.acin_adc = false,
+	.power_desc	= &axp813_ac_power_desc,
+	.irq_names	= axp20x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp20x_irq_names),
+	.acin_adc	= false,
+	.acin_path_sel	= true,
 };
 
+#ifdef CONFIG_PM_SLEEP
+static int axp20x_ac_power_suspend(struct device *dev)
+{
+	struct axp20x_ac_power *power = dev_get_drvdata(dev);
+	int i = 0;
+
+	/*
+	 * Allow wake via ACIN_PLUGIN only.
+	 *
+	 * As nested threaded IRQs are not automatically disabled during
+	 * suspend, we must explicitly disable the remainder of the IRQs.
+	 */
+	if (device_may_wakeup(&power->supply->dev))
+		enable_irq_wake(power->irqs[i++]);
+	while (i < power->num_irqs)
+		disable_irq(power->irqs[i++]);
+
+	return 0;
+}
+
+static int axp20x_ac_power_resume(struct device *dev)
+{
+	struct axp20x_ac_power *power = dev_get_drvdata(dev);
+	int i = 0;
+
+	if (device_may_wakeup(&power->supply->dev))
+		disable_irq_wake(power->irqs[i++]);
+	while (i < power->num_irqs)
+		enable_irq(power->irqs[i++]);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(axp20x_ac_power_pm_ops, axp20x_ac_power_suspend,
+						 axp20x_ac_power_resume);
+
 static int axp20x_ac_power_probe(struct platform_device *pdev)
 {
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
 	struct power_supply_config psy_cfg = {};
 	struct axp20x_ac_power *power;
 	const struct axp_data *axp_data;
-	static const char * const irq_names[] = { "ACIN_PLUGIN", "ACIN_REMOVAL",
-		NULL };
 	int i, irq, ret;
 
 	if (!of_device_is_available(pdev->dev.of_node))
@@ -259,12 +335,14 @@ static int axp20x_ac_power_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	power = devm_kzalloc(&pdev->dev, sizeof(*power), GFP_KERNEL);
+	axp_data = of_device_get_match_data(&pdev->dev);
+
+	power = devm_kzalloc(&pdev->dev,
+			     struct_size(power, irqs, axp_data->num_irq_names),
+			     GFP_KERNEL);
 	if (!power)
 		return -ENOMEM;
 
-	axp_data = of_device_get_match_data(&pdev->dev);
-
 	if (axp_data->acin_adc) {
 		power->acin_v = devm_iio_channel_get(&pdev->dev, "acin_v");
 		if (IS_ERR(power->acin_v)) {
@@ -282,6 +360,8 @@ static int axp20x_ac_power_probe(struct platform_device *pdev)
 	}
 
 	power->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+	power->has_acin_path_sel = axp_data->acin_path_sel;
+	power->num_irqs = axp_data->num_irq_names;
 
 	platform_set_drvdata(pdev, power);
 
@@ -295,20 +375,22 @@ static int axp20x_ac_power_probe(struct platform_device *pdev)
 		return PTR_ERR(power->supply);
 
 	/* Request irqs after registering, as irqs may trigger immediately */
-	for (i = 0; irq_names[i]; i++) {
-		irq = platform_get_irq_byname(pdev, irq_names[i]);
+	for (i = 0; i < axp_data->num_irq_names; i++) {
+		irq = platform_get_irq_byname(pdev, axp_data->irq_names[i]);
 		if (irq < 0) {
-			dev_warn(&pdev->dev, "No IRQ for %s: %d\n",
-				 irq_names[i], irq);
-			continue;
+			dev_err(&pdev->dev, "No IRQ for %s: %d\n",
+				axp_data->irq_names[i], irq);
+			return irq;
 		}
-		irq = regmap_irq_get_virq(axp20x->regmap_irqc, irq);
-		ret = devm_request_any_context_irq(&pdev->dev, irq,
+		power->irqs[i] = regmap_irq_get_virq(axp20x->regmap_irqc, irq);
+		ret = devm_request_any_context_irq(&pdev->dev, power->irqs[i],
 						   axp20x_ac_power_irq, 0,
 						   DRVNAME, power);
-		if (ret < 0)
-			dev_warn(&pdev->dev, "Error requesting %s IRQ: %d\n",
-				 irq_names[i], ret);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Error requesting %s IRQ: %d\n",
+				axp_data->irq_names[i], ret);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -331,8 +413,9 @@ MODULE_DEVICE_TABLE(of, axp20x_ac_power_match);
 static struct platform_driver axp20x_ac_power_driver = {
 	.probe = axp20x_ac_power_probe,
 	.driver = {
-		.name = DRVNAME,
-		.of_match_table = axp20x_ac_power_match,
+		.name		= DRVNAME,
+		.of_match_table	= axp20x_ac_power_match,
+		.pm		= &axp20x_ac_power_pm_ops,
 	},
 };
 
diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c
index 5f0a5722b19e..4fde24b5f35a 100644
--- a/drivers/power/supply/axp20x_usb_power.c
+++ b/drivers/power/supply/axp20x_usb_power.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm.h>
 #include <linux/power_supply.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
@@ -29,6 +30,9 @@
 
 #define AXP20X_USB_STATUS_VBUS_VALID	BIT(2)
 
+#define AXP20X_VBUS_PATH_SEL		BIT(7)
+#define AXP20X_VBUS_PATH_SEL_OFFSET	7
+
 #define AXP20X_VBUS_VHOLD_uV(b)		(4000000 + (((b) >> 3) & 7) * 100000)
 #define AXP20X_VBUS_VHOLD_MASK		GENMASK(5, 3)
 #define AXP20X_VBUS_VHOLD_OFFSET	3
@@ -57,7 +61,6 @@
 #define DEBOUNCE_TIME			msecs_to_jiffies(50)
 
 struct axp20x_usb_power {
-	struct device_node *np;
 	struct regmap *regmap;
 	struct power_supply *supply;
 	enum axp20x_variants axp20x_id;
@@ -65,14 +68,32 @@ struct axp20x_usb_power {
 	struct iio_channel *vbus_i;
 	struct delayed_work vbus_detect;
 	unsigned int old_status;
+	unsigned int online;
+	unsigned int num_irqs;
+	unsigned int irqs[];
 };
 
+static bool axp20x_usb_vbus_needs_polling(struct axp20x_usb_power *power)
+{
+	/*
+	 * Polling is only necessary while VBUS is offline. While online, a
+	 * present->absent transition implies an online->offline transition
+	 * and will triger the VBUS_REMOVAL IRQ.
+	 */
+	if (power->axp20x_id >= AXP221_ID && !power->online)
+		return true;
+
+	return false;
+}
+
 static irqreturn_t axp20x_usb_power_irq(int irq, void *devid)
 {
 	struct axp20x_usb_power *power = devid;
 
 	power_supply_changed(power->supply);
 
+	mod_delayed_work(system_wq, &power->vbus_detect, DEBOUNCE_TIME);
+
 	return IRQ_HANDLED;
 }
 
@@ -92,17 +113,11 @@ static void axp20x_usb_power_poll_vbus(struct work_struct *work)
 		power_supply_changed(power->supply);
 
 	power->old_status = val;
+	power->online = val & AXP20X_PWR_STATUS_VBUS_USED;
 
 out:
-	mod_delayed_work(system_wq, &power->vbus_detect, DEBOUNCE_TIME);
-}
-
-static bool axp20x_usb_vbus_needs_polling(struct axp20x_usb_power *power)
-{
-	if (power->axp20x_id >= AXP221_ID)
-		return true;
-
-	return false;
+	if (axp20x_usb_vbus_needs_polling(power))
+		mod_delayed_work(system_wq, &power->vbus_detect, DEBOUNCE_TIME);
 }
 
 static int axp20x_get_current_max(struct axp20x_usb_power *power, int *val)
@@ -264,6 +279,16 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 	return 0;
 }
 
+static int axp813_usb_power_set_online(struct axp20x_usb_power *power,
+				       int intval)
+{
+	int val = !intval << AXP20X_VBUS_PATH_SEL_OFFSET;
+
+	return regmap_update_bits(power->regmap,
+				  AXP20X_VBUS_IPSOUT_MGMT,
+				  AXP20X_VBUS_PATH_SEL, val);
+}
+
 static int axp20x_usb_power_set_voltage_min(struct axp20x_usb_power *power,
 					    int intval)
 {
@@ -345,6 +370,11 @@ static int axp20x_usb_power_set_property(struct power_supply *psy,
 	struct axp20x_usb_power *power = power_supply_get_drvdata(psy);
 
 	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		if (power->axp20x_id != AXP813_ID)
+			return -EINVAL;
+		return axp813_usb_power_set_online(power, val->intval);
+
 	case POWER_SUPPLY_PROP_VOLTAGE_MIN:
 		return axp20x_usb_power_set_voltage_min(power, val->intval);
 
@@ -364,6 +394,18 @@ static int axp20x_usb_power_set_property(struct power_supply *psy,
 static int axp20x_usb_power_prop_writeable(struct power_supply *psy,
 					   enum power_supply_property psp)
 {
+	struct axp20x_usb_power *power = power_supply_get_drvdata(psy);
+
+	/*
+	 * The VBUS path select flag works differently on on AXP288 and newer:
+	 *  - On AXP20x and AXP22x, the flag enables VBUS (ignoring N_VBUSEN).
+	 *  - On AXP288 and AXP8xx, the flag disables VBUS (ignoring N_VBUSEN).
+	 * We only expose the control on variants where it can be used to force
+	 * the VBUS input offline.
+	 */
+	if (psp == POWER_SUPPLY_PROP_ONLINE)
+		return power->axp20x_id == AXP813_ID;
+
 	return psp == POWER_SUPPLY_PROP_VOLTAGE_MIN ||
 	       psp == POWER_SUPPLY_PROP_CURRENT_MAX;
 }
@@ -406,6 +448,92 @@ static const struct power_supply_desc axp22x_usb_power_desc = {
 	.set_property = axp20x_usb_power_set_property,
 };
 
+static const char * const axp20x_irq_names[] = {
+	"VBUS_PLUGIN",
+	"VBUS_REMOVAL",
+	"VBUS_VALID",
+	"VBUS_NOT_VALID",
+};
+
+static const char * const axp22x_irq_names[] = {
+	"VBUS_PLUGIN",
+	"VBUS_REMOVAL",
+};
+
+struct axp_data {
+	const struct power_supply_desc	*power_desc;
+	const char * const		*irq_names;
+	unsigned int			num_irq_names;
+	enum axp20x_variants		axp20x_id;
+};
+
+static const struct axp_data axp202_data = {
+	.power_desc	= &axp20x_usb_power_desc,
+	.irq_names	= axp20x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp20x_irq_names),
+	.axp20x_id	= AXP202_ID,
+};
+
+static const struct axp_data axp221_data = {
+	.power_desc	= &axp22x_usb_power_desc,
+	.irq_names	= axp22x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp22x_irq_names),
+	.axp20x_id	= AXP221_ID,
+};
+
+static const struct axp_data axp223_data = {
+	.power_desc	= &axp22x_usb_power_desc,
+	.irq_names	= axp22x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp22x_irq_names),
+	.axp20x_id	= AXP223_ID,
+};
+
+static const struct axp_data axp813_data = {
+	.power_desc	= &axp22x_usb_power_desc,
+	.irq_names	= axp22x_irq_names,
+	.num_irq_names	= ARRAY_SIZE(axp22x_irq_names),
+	.axp20x_id	= AXP813_ID,
+};
+
+#ifdef CONFIG_PM_SLEEP
+static int axp20x_usb_power_suspend(struct device *dev)
+{
+	struct axp20x_usb_power *power = dev_get_drvdata(dev);
+	int i = 0;
+
+	/*
+	 * Allow wake via VBUS_PLUGIN only.
+	 *
+	 * As nested threaded IRQs are not automatically disabled during
+	 * suspend, we must explicitly disable the remainder of the IRQs.
+	 */
+	if (device_may_wakeup(&power->supply->dev))
+		enable_irq_wake(power->irqs[i++]);
+	while (i < power->num_irqs)
+		disable_irq(power->irqs[i++]);
+
+	return 0;
+}
+
+static int axp20x_usb_power_resume(struct device *dev)
+{
+	struct axp20x_usb_power *power = dev_get_drvdata(dev);
+	int i = 0;
+
+	if (device_may_wakeup(&power->supply->dev))
+		disable_irq_wake(power->irqs[i++]);
+	while (i < power->num_irqs)
+		enable_irq(power->irqs[i++]);
+
+	mod_delayed_work(system_wq, &power->vbus_detect, DEBOUNCE_TIME);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(axp20x_usb_power_pm_ops, axp20x_usb_power_suspend,
+						  axp20x_usb_power_resume);
+
 static int configure_iio_channels(struct platform_device *pdev,
 				  struct axp20x_usb_power *power)
 {
@@ -441,12 +569,7 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
 	struct power_supply_config psy_cfg = {};
 	struct axp20x_usb_power *power;
-	static const char * const axp20x_irq_names[] = { "VBUS_PLUGIN",
-		"VBUS_REMOVAL", "VBUS_VALID", "VBUS_NOT_VALID", NULL };
-	static const char * const axp22x_irq_names[] = {
-		"VBUS_PLUGIN", "VBUS_REMOVAL", NULL };
-	const char * const *irq_names;
-	const struct power_supply_desc *usb_power_desc;
+	const struct axp_data *axp_data;
 	int i, irq, ret;
 
 	if (!of_device_is_available(pdev->dev.of_node))
@@ -457,16 +580,19 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	power = devm_kzalloc(&pdev->dev, sizeof(*power), GFP_KERNEL);
+	axp_data = of_device_get_match_data(&pdev->dev);
+
+	power = devm_kzalloc(&pdev->dev,
+			     struct_size(power, irqs, axp_data->num_irq_names),
+			     GFP_KERNEL);
 	if (!power)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, power);
-	power->axp20x_id = (enum axp20x_variants)of_device_get_match_data(
-								&pdev->dev);
 
-	power->np = pdev->dev.of_node;
+	power->axp20x_id = axp_data->axp20x_id;
 	power->regmap = axp20x->regmap;
+	power->num_irqs = axp_data->num_irq_names;
 
 	if (power->axp20x_id == AXP202_ID) {
 		/* Enable vbus valid checking */
@@ -483,18 +609,6 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 
 		if (ret)
 			return ret;
-
-		usb_power_desc = &axp20x_usb_power_desc;
-		irq_names = axp20x_irq_names;
-	} else if (power->axp20x_id == AXP221_ID ||
-		   power->axp20x_id == AXP223_ID ||
-		   power->axp20x_id == AXP813_ID) {
-		usb_power_desc = &axp22x_usb_power_desc;
-		irq_names = axp22x_irq_names;
-	} else {
-		dev_err(&pdev->dev, "Unsupported AXP variant: %ld\n",
-			axp20x->variant);
-		return -EINVAL;
 	}
 
 	if (power->axp20x_id == AXP813_ID) {
@@ -506,25 +620,29 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 	psy_cfg.of_node = pdev->dev.of_node;
 	psy_cfg.drv_data = power;
 
-	power->supply = devm_power_supply_register(&pdev->dev, usb_power_desc,
+	power->supply = devm_power_supply_register(&pdev->dev,
+						   axp_data->power_desc,
 						   &psy_cfg);
 	if (IS_ERR(power->supply))
 		return PTR_ERR(power->supply);
 
 	/* Request irqs after registering, as irqs may trigger immediately */
-	for (i = 0; irq_names[i]; i++) {
-		irq = platform_get_irq_byname(pdev, irq_names[i]);
+	for (i = 0; i < axp_data->num_irq_names; i++) {
+		irq = platform_get_irq_byname(pdev, axp_data->irq_names[i]);
 		if (irq < 0) {
-			dev_warn(&pdev->dev, "No IRQ for %s: %d\n",
-				 irq_names[i], irq);
-			continue;
+			dev_err(&pdev->dev, "No IRQ for %s: %d\n",
+				axp_data->irq_names[i], irq);
+			return irq;
+		}
+		power->irqs[i] = regmap_irq_get_virq(axp20x->regmap_irqc, irq);
+		ret = devm_request_any_context_irq(&pdev->dev, power->irqs[i],
+						   axp20x_usb_power_irq, 0,
+						   DRVNAME, power);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Error requesting %s IRQ: %d\n",
+				axp_data->irq_names[i], ret);
+			return ret;
 		}
-		irq = regmap_irq_get_virq(axp20x->regmap_irqc, irq);
-		ret = devm_request_any_context_irq(&pdev->dev, irq,
-				axp20x_usb_power_irq, 0, DRVNAME, power);
-		if (ret < 0)
-			dev_warn(&pdev->dev, "Error requesting %s IRQ: %d\n",
-				 irq_names[i], ret);
 	}
 
 	INIT_DELAYED_WORK(&power->vbus_detect, axp20x_usb_power_poll_vbus);
@@ -546,16 +664,16 @@ static int axp20x_usb_power_remove(struct platform_device *pdev)
 static const struct of_device_id axp20x_usb_power_match[] = {
 	{
 		.compatible = "x-powers,axp202-usb-power-supply",
-		.data = (void *)AXP202_ID,
+		.data = &axp202_data,
 	}, {
 		.compatible = "x-powers,axp221-usb-power-supply",
-		.data = (void *)AXP221_ID,
+		.data = &axp221_data,
 	}, {
 		.compatible = "x-powers,axp223-usb-power-supply",
-		.data = (void *)AXP223_ID,
+		.data = &axp223_data,
 	}, {
 		.compatible = "x-powers,axp813-usb-power-supply",
-		.data = (void *)AXP813_ID,
+		.data = &axp813_data,
 	}, { /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, axp20x_usb_power_match);
@@ -564,8 +682,9 @@ static struct platform_driver axp20x_usb_power_driver = {
 	.probe = axp20x_usb_power_probe,
 	.remove = axp20x_usb_power_remove,
 	.driver = {
-		.name = DRVNAME,
-		.of_match_table = axp20x_usb_power_match,
+		.name		= DRVNAME,
+		.of_match_table	= axp20x_usb_power_match,
+		.pm		= &axp20x_usb_power_pm_ops,
 	},
 };
 
diff --git a/drivers/power/supply/bq25890_charger.c b/drivers/power/supply/bq25890_charger.c
index 9d1ec8d677de..aebd1253dbc9 100644
--- a/drivers/power/supply/bq25890_charger.c
+++ b/drivers/power/supply/bq25890_charger.c
@@ -25,12 +25,20 @@
 #define BQ25895_ID			7
 #define BQ25896_ID			0
 
+enum bq25890_chip_version {
+	BQ25890,
+	BQ25892,
+	BQ25895,
+	BQ25896,
+};
+
 enum bq25890_fields {
 	F_EN_HIZ, F_EN_ILIM, F_IILIM,				     /* Reg00 */
 	F_BHOT, F_BCOLD, F_VINDPM_OFS,				     /* Reg01 */
 	F_CONV_START, F_CONV_RATE, F_BOOSTF, F_ICO_EN,
 	F_HVDCP_EN, F_MAXC_EN, F_FORCE_DPM, F_AUTO_DPDM_EN,	     /* Reg02 */
-	F_BAT_LOAD_EN, F_WD_RST, F_OTG_CFG, F_CHG_CFG, F_SYSVMIN,    /* Reg03 */
+	F_BAT_LOAD_EN, F_WD_RST, F_OTG_CFG, F_CHG_CFG, F_SYSVMIN,
+	F_MIN_VBAT_SEL,						     /* Reg03 */
 	F_PUMPX_EN, F_ICHG,					     /* Reg04 */
 	F_IPRECHG, F_ITERM,					     /* Reg05 */
 	F_VREG, F_BATLOWV, F_VRECHG,				     /* Reg06 */
@@ -39,8 +47,9 @@ enum bq25890_fields {
 	F_BATCMP, F_VCLAMP, F_TREG,				     /* Reg08 */
 	F_FORCE_ICO, F_TMR2X_EN, F_BATFET_DIS, F_JEITA_VSET,
 	F_BATFET_DLY, F_BATFET_RST_EN, F_PUMPX_UP, F_PUMPX_DN,	     /* Reg09 */
-	F_BOOSTV, F_BOOSTI,					     /* Reg0A */
-	F_VBUS_STAT, F_CHG_STAT, F_PG_STAT, F_SDP_STAT, F_VSYS_STAT, /* Reg0B */
+	F_BOOSTV, F_PFM_OTG_DIS, F_BOOSTI,			     /* Reg0A */
+	F_VBUS_STAT, F_CHG_STAT, F_PG_STAT, F_SDP_STAT, F_0B_RSVD,
+	F_VSYS_STAT,						     /* Reg0B */
 	F_WD_FAULT, F_BOOST_FAULT, F_CHG_FAULT, F_BAT_FAULT,
 	F_NTC_FAULT,						     /* Reg0C */
 	F_FORCE_VINDPM, F_VINDPM,				     /* Reg0D */
@@ -91,7 +100,7 @@ struct bq25890_device {
 	struct regmap *rmap;
 	struct regmap_field *rmap_fields[F_MAX_FIELDS];
 
-	int chip_id;
+	enum bq25890_chip_version chip_version;
 	struct bq25890_init_data init_data;
 	struct bq25890_state state;
 
@@ -111,8 +120,7 @@ static const struct regmap_access_table bq25890_writeable_regs = {
 static const struct regmap_range bq25890_volatile_reg_ranges[] = {
 	regmap_reg_range(0x00, 0x00),
 	regmap_reg_range(0x09, 0x09),
-	regmap_reg_range(0x0b, 0x0c),
-	regmap_reg_range(0x0e, 0x14),
+	regmap_reg_range(0x0b, 0x14),
 };
 
 static const struct regmap_access_table bq25890_volatile_regs = {
@@ -155,7 +163,7 @@ static const struct reg_field bq25890_reg_fields[] = {
 	[F_OTG_CFG]		= REG_FIELD(0x03, 5, 5),
 	[F_CHG_CFG]		= REG_FIELD(0x03, 4, 4),
 	[F_SYSVMIN]		= REG_FIELD(0x03, 1, 3),
-	/* MIN_VBAT_SEL on BQ25896 */
+	[F_MIN_VBAT_SEL]	= REG_FIELD(0x03, 0, 0), // BQ25896 only
 	/* REG04 */
 	[F_PUMPX_EN]		= REG_FIELD(0x04, 7, 7),
 	[F_ICHG]		= REG_FIELD(0x04, 0, 6),
@@ -188,8 +196,8 @@ static const struct reg_field bq25890_reg_fields[] = {
 	[F_PUMPX_DN]		= REG_FIELD(0x09, 0, 0),
 	/* REG0A */
 	[F_BOOSTV]		= REG_FIELD(0x0A, 4, 7),
-	/* PFM_OTG_DIS 3 on BQ25896 */
 	[F_BOOSTI]		= REG_FIELD(0x0A, 0, 2), // reserved on BQ25895
+	[F_PFM_OTG_DIS]		= REG_FIELD(0x0A, 3, 3), // BQ25896 only
 	/* REG0B */
 	[F_VBUS_STAT]		= REG_FIELD(0x0B, 5, 7),
 	[F_CHG_STAT]		= REG_FIELD(0x0B, 3, 4),
@@ -275,6 +283,7 @@ static const union {
 	struct bq25890_lookup lt;
 } bq25890_tables[] = {
 	/* range tables */
+	/* TODO: BQ25896 has max ICHG 3008 mA */
 	[TBL_ICHG] =	{ .rt = {0,	  5056000, 64000} },	 /* uA */
 	[TBL_ITERM] =	{ .rt = {64000,   1024000, 64000} },	 /* uA */
 	[TBL_VREG] =	{ .rt = {3840000, 4608000, 16000} },	 /* uV */
@@ -391,11 +400,13 @@ static int bq25890_power_supply_get_property(struct power_supply *psy,
 		break;
 
 	case POWER_SUPPLY_PROP_MODEL_NAME:
-		if (bq->chip_id == BQ25890_ID)
+		if (bq->chip_version == BQ25890)
 			val->strval = "BQ25890";
-		else if (bq->chip_id == BQ25895_ID)
+		else if (bq->chip_version == BQ25892)
+			val->strval = "BQ25892";
+		else if (bq->chip_version == BQ25895)
 			val->strval = "BQ25895";
-		else if (bq->chip_id == BQ25896_ID)
+		else if (bq->chip_version == BQ25896)
 			val->strval = "BQ25896";
 		else
 			val->strval = "UNKNOWN";
@@ -741,6 +752,56 @@ static int bq25890_usb_notifier(struct notifier_block *nb, unsigned long val,
 	return NOTIFY_OK;
 }
 
+static int bq25890_get_chip_version(struct bq25890_device *bq)
+{
+	int id, rev;
+
+	id = bq25890_field_read(bq, F_PN);
+	if (id < 0) {
+		dev_err(bq->dev, "Cannot read chip ID.\n");
+		return id;
+	}
+
+	rev = bq25890_field_read(bq, F_DEV_REV);
+	if (rev < 0) {
+		dev_err(bq->dev, "Cannot read chip revision.\n");
+		return rev;
+	}
+
+	switch (id) {
+	case BQ25890_ID:
+		bq->chip_version = BQ25890;
+		break;
+
+	/* BQ25892 and BQ25896 share same ID 0 */
+	case BQ25896_ID:
+		switch (rev) {
+		case 2:
+			bq->chip_version = BQ25896;
+			break;
+		case 1:
+			bq->chip_version = BQ25892;
+			break;
+		default:
+			dev_err(bq->dev,
+				"Unknown device revision %d, assume BQ25892\n",
+				rev);
+			bq->chip_version = BQ25892;
+		}
+		break;
+
+	case BQ25895_ID:
+		bq->chip_version = BQ25895;
+		break;
+
+	default:
+		dev_err(bq->dev, "Unknown chip ID %d\n", id);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
 static int bq25890_irq_probe(struct bq25890_device *bq)
 {
 	struct gpio_desc *irq;
@@ -859,16 +920,10 @@ static int bq25890_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, bq);
 
-	bq->chip_id = bq25890_field_read(bq, F_PN);
-	if (bq->chip_id < 0) {
-		dev_err(dev, "Cannot read chip ID.\n");
-		return bq->chip_id;
-	}
-
-	if ((bq->chip_id != BQ25890_ID) && (bq->chip_id != BQ25895_ID)
-			&& (bq->chip_id != BQ25896_ID)) {
-		dev_err(dev, "Chip with ID=%d, not supported!\n", bq->chip_id);
-		return -ENODEV;
+	ret = bq25890_get_chip_version(bq);
+	if (ret) {
+		dev_err(dev, "Cannot read chip ID or unknown chip.\n");
+		return ret;
 	}
 
 	if (!dev->platform_data) {
@@ -986,12 +1041,18 @@ static const struct dev_pm_ops bq25890_pm = {
 
 static const struct i2c_device_id bq25890_i2c_ids[] = {
 	{ "bq25890", 0 },
+	{ "bq25892", 0 },
+	{ "bq25895", 0 },
+	{ "bq25896", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(i2c, bq25890_i2c_ids);
 
 static const struct of_device_id bq25890_of_match[] = {
 	{ .compatible = "ti,bq25890", },
+	{ .compatible = "ti,bq25892", },
+	{ .compatible = "ti,bq25895", },
+	{ .compatible = "ti,bq25896", },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, bq25890_of_match);
diff --git a/drivers/power/supply/cros_usbpd-charger.c b/drivers/power/supply/cros_usbpd-charger.c
index 6cc7c3910e09..30c3d37511c9 100644
--- a/drivers/power/supply/cros_usbpd-charger.c
+++ b/drivers/power/supply/cros_usbpd-charger.c
@@ -5,7 +5,6 @@
  * Copyright (c) 2014 - 2018 Google, Inc
  */
 
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
@@ -132,11 +131,8 @@ static int cros_usbpd_charger_get_num_ports(struct charger_data *charger)
 	ret = cros_usbpd_charger_ec_command(charger, 0,
 					    EC_CMD_CHARGE_PORT_COUNT,
 					    NULL, 0, &resp, sizeof(resp));
-	if (ret < 0) {
-		dev_err(charger->dev,
-			"Unable to get the number of ports (err:0x%x)\n", ret);
+	if (ret < 0)
 		return ret;
-	}
 
 	return resp.port_count;
 }
@@ -148,11 +144,8 @@ static int cros_usbpd_charger_get_usbpd_num_ports(struct charger_data *charger)
 
 	ret = cros_usbpd_charger_ec_command(charger, 0, EC_CMD_USB_PD_PORTS,
 					    NULL, 0, &resp, sizeof(resp));
-	if (ret < 0) {
-		dev_err(charger->dev,
-			"Unable to get the number or ports (err:0x%x)\n", ret);
+	if (ret < 0)
 		return ret;
-	}
 
 	return resp.num_ports;
 }
diff --git a/drivers/power/supply/ingenic-battery.c b/drivers/power/supply/ingenic-battery.c
index 35816d4b3012..2748715c4c75 100644
--- a/drivers/power/supply/ingenic-battery.c
+++ b/drivers/power/supply/ingenic-battery.c
@@ -100,10 +100,17 @@ static int ingenic_battery_set_scale(struct ingenic_battery *bat)
 		return -EINVAL;
 	}
 
-	return iio_write_channel_attribute(bat->channel,
-					   scale_raw[best_idx],
-					   scale_raw[best_idx + 1],
-					   IIO_CHAN_INFO_SCALE);
+	/* Only set scale if there is more than one (fractional) entry */
+	if (scale_len > 2) {
+		ret = iio_write_channel_attribute(bat->channel,
+						  scale_raw[best_idx],
+						  scale_raw[best_idx + 1],
+						  IIO_CHAN_INFO_SCALE);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
 }
 
 static enum power_supply_property ingenic_battery_properties[] = {
diff --git a/drivers/power/supply/ipaq_micro_battery.c b/drivers/power/supply/ipaq_micro_battery.c
index 03592ceaca88..192d9db0fb00 100644
--- a/drivers/power/supply/ipaq_micro_battery.c
+++ b/drivers/power/supply/ipaq_micro_battery.c
@@ -149,7 +149,7 @@ static int micro_batt_get_property(struct power_supply *b,
 		default:
 			val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN;
 			break;
-		};
+		}
 		break;
 	case POWER_SUPPLY_PROP_STATUS:
 		val->intval = get_status(b);
@@ -168,7 +168,7 @@ static int micro_batt_get_property(struct power_supply *b,
 		break;
 	default:
 		return -EINVAL;
-	};
+	}
 
 	return 0;
 }
@@ -185,7 +185,7 @@ static int micro_ac_get_property(struct power_supply *b,
 		break;
 	default:
 		return -EINVAL;
-	};
+	}
 
 	return 0;
 }
diff --git a/drivers/power/supply/ltc2941-battery-gauge.c b/drivers/power/supply/ltc2941-battery-gauge.c
index da49436176cd..30a9014b2f95 100644
--- a/drivers/power/supply/ltc2941-battery-gauge.c
+++ b/drivers/power/supply/ltc2941-battery-gauge.c
@@ -449,7 +449,7 @@ static int ltc294x_i2c_remove(struct i2c_client *client)
 {
 	struct ltc294x_info *info = i2c_get_clientdata(client);
 
-	cancel_delayed_work(&info->work);
+	cancel_delayed_work_sync(&info->work);
 	power_supply_unregister(info->supply);
 	return 0;
 }
diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c
index 62499018e68b..8a1f0ee493aa 100644
--- a/drivers/power/supply/max17040_battery.c
+++ b/drivers/power/supply/max17040_battery.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/i2c.h>
 #include <linux/delay.h>
+#include <linux/interrupt.h>
 #include <linux/power_supply.h>
 #include <linux/max17040_battery.h>
 #include <linux/slab.h>
@@ -28,6 +29,9 @@
 #define MAX17040_DELAY		1000
 #define MAX17040_BATTERY_FULL	95
 
+#define MAX17040_ATHD_MASK		0xFFC0
+#define MAX17040_ATHD_DEFAULT_POWER_UP	4
+
 struct max17040_chip {
 	struct i2c_client		*client;
 	struct delayed_work		work;
@@ -42,6 +46,8 @@ struct max17040_chip {
 	int soc;
 	/* State Of Charge */
 	int status;
+	/* Low alert threshold from 32% to 1% of the State of Charge */
+	u32 low_soc_alert;
 };
 
 static int max17040_get_property(struct power_supply *psy,
@@ -98,6 +104,21 @@ static void max17040_reset(struct i2c_client *client)
 	max17040_write_reg(client, MAX17040_CMD, 0x0054);
 }
 
+static int max17040_set_low_soc_alert(struct i2c_client *client, u32 level)
+{
+	int ret;
+	u16 data;
+
+	level = 32 - level;
+	data = max17040_read_reg(client, MAX17040_RCOMP);
+	/* clear the alrt bit and set LSb 5 bits */
+	data &= MAX17040_ATHD_MASK;
+	data |= level;
+	ret = max17040_write_reg(client, MAX17040_RCOMP, data);
+
+	return ret;
+}
+
 static void max17040_get_vcell(struct i2c_client *client)
 {
 	struct max17040_chip *chip = i2c_get_clientdata(client);
@@ -160,21 +181,81 @@ static void max17040_get_status(struct i2c_client *client)
 		chip->status = POWER_SUPPLY_STATUS_FULL;
 }
 
+static int max17040_get_of_data(struct max17040_chip *chip)
+{
+	struct device *dev = &chip->client->dev;
+
+	chip->low_soc_alert = MAX17040_ATHD_DEFAULT_POWER_UP;
+	device_property_read_u32(dev,
+				 "maxim,alert-low-soc-level",
+				 &chip->low_soc_alert);
+
+	if (chip->low_soc_alert <= 0 || chip->low_soc_alert >= 33)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void max17040_check_changes(struct i2c_client *client)
+{
+	max17040_get_vcell(client);
+	max17040_get_soc(client);
+	max17040_get_online(client);
+	max17040_get_status(client);
+}
+
 static void max17040_work(struct work_struct *work)
 {
 	struct max17040_chip *chip;
+	int last_soc, last_status;
 
 	chip = container_of(work, struct max17040_chip, work.work);
 
-	max17040_get_vcell(chip->client);
-	max17040_get_soc(chip->client);
-	max17040_get_online(chip->client);
-	max17040_get_status(chip->client);
+	/* store SOC and status to check changes */
+	last_soc = chip->soc;
+	last_status = chip->status;
+	max17040_check_changes(chip->client);
+
+	/* check changes and send uevent */
+	if (last_soc != chip->soc || last_status != chip->status)
+		power_supply_changed(chip->battery);
 
 	queue_delayed_work(system_power_efficient_wq, &chip->work,
 			   MAX17040_DELAY);
 }
 
+static irqreturn_t max17040_thread_handler(int id, void *dev)
+{
+	struct max17040_chip *chip = dev;
+	struct i2c_client *client = chip->client;
+
+	dev_warn(&client->dev, "IRQ: Alert battery low level");
+	/* read registers */
+	max17040_check_changes(chip->client);
+
+	/* send uevent */
+	power_supply_changed(chip->battery);
+
+	/* reset alert bit */
+	max17040_set_low_soc_alert(client, chip->low_soc_alert);
+
+	return IRQ_HANDLED;
+}
+
+static int max17040_enable_alert_irq(struct max17040_chip *chip)
+{
+	struct i2c_client *client = chip->client;
+	unsigned int flags;
+	int ret;
+
+	flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT;
+	ret = devm_request_threaded_irq(&client->dev, client->irq, NULL,
+					max17040_thread_handler, flags,
+					chip->battery->desc->name, chip);
+
+	return ret;
+}
+
 static enum power_supply_property max17040_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_ONLINE,
@@ -196,6 +277,7 @@ static int max17040_probe(struct i2c_client *client,
 	struct i2c_adapter *adapter = client->adapter;
 	struct power_supply_config psy_cfg = {};
 	struct max17040_chip *chip;
+	int ret;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE))
 		return -EIO;
@@ -206,6 +288,12 @@ static int max17040_probe(struct i2c_client *client,
 
 	chip->client = client;
 	chip->pdata = client->dev.platform_data;
+	ret = max17040_get_of_data(chip);
+	if (ret) {
+		dev_err(&client->dev,
+			"failed: low SOC alert OF data out of bounds\n");
+		return ret;
+	}
 
 	i2c_set_clientdata(client, chip);
 	psy_cfg.drv_data = chip;
@@ -220,6 +308,24 @@ static int max17040_probe(struct i2c_client *client,
 	max17040_reset(client);
 	max17040_get_version(client);
 
+	/* check interrupt */
+	if (client->irq && of_device_is_compatible(client->dev.of_node,
+						   "maxim,max77836-battery")) {
+		ret = max17040_set_low_soc_alert(client, chip->low_soc_alert);
+		if (ret) {
+			dev_err(&client->dev,
+				"Failed to set low SOC alert: err %d\n", ret);
+			return ret;
+		}
+
+		ret = max17040_enable_alert_irq(chip);
+		if (ret) {
+			client->irq = 0;
+			dev_warn(&client->dev,
+				 "Failed to get IRQ err %d\n", ret);
+		}
+	}
+
 	INIT_DEFERRABLE_WORK(&chip->work, max17040_work);
 	queue_delayed_work(system_power_efficient_wq, &chip->work,
 			   MAX17040_DELAY);
@@ -244,6 +350,10 @@ static int max17040_suspend(struct device *dev)
 	struct max17040_chip *chip = i2c_get_clientdata(client);
 
 	cancel_delayed_work(&chip->work);
+
+	if (client->irq && device_may_wakeup(dev))
+		enable_irq_wake(client->irq);
+
 	return 0;
 }
 
@@ -254,6 +364,10 @@ static int max17040_resume(struct device *dev)
 
 	queue_delayed_work(system_power_efficient_wq, &chip->work,
 			   MAX17040_DELAY);
+
+	if (client->irq && device_may_wakeup(dev))
+		disable_irq_wake(client->irq);
+
 	return 0;
 }
 
diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c
index 0dfad2cf13fe..69ec4295d55d 100644
--- a/drivers/power/supply/max17042_battery.c
+++ b/drivers/power/supply/max17042_battery.c
@@ -282,6 +282,8 @@ static int max17042_get_property(struct power_supply *psy,
 	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
 		if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042)
 			ret = regmap_read(map, MAX17042_V_empty, &data);
+		else if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17055)
+			ret = regmap_read(map, MAX17055_V_empty, &data);
 		else
 			ret = regmap_read(map, MAX17047_V_empty, &data);
 		if (ret < 0)
@@ -627,7 +629,8 @@ static void max17042_write_config_regs(struct max17042_chip *chip)
 			config->filter_cfg);
 	regmap_write(map, MAX17042_RelaxCFG, config->relax_cfg);
 	if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17047 ||
-			chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050)
+			chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050 ||
+			chip->chip_type == MAXIM_DEVICE_TYPE_MAX17055)
 		regmap_write(map, MAX17047_FullSOCThr,
 						config->full_soc_thresh);
 }
@@ -758,6 +761,8 @@ static inline void max17042_override_por_values(struct max17042_chip *chip)
 
 	if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042)
 		max17042_override_por(map, MAX17042_V_empty, config->vempty);
+	if (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17055)
+		max17042_override_por(map, MAX17055_V_empty, config->vempty);
 	else
 		max17042_override_por(map, MAX17047_V_empty, config->vempty);
 	max17042_override_por(map, MAX17042_TempNom, config->temp_nom);
@@ -765,7 +770,10 @@ static inline void max17042_override_por_values(struct max17042_chip *chip)
 	max17042_override_por(map, MAX17042_FCTC, config->fctc);
 	max17042_override_por(map, MAX17042_RCOMP0, config->rcomp0);
 	max17042_override_por(map, MAX17042_TempCo, config->tcompc0);
-	if (chip->chip_type) {
+	if (chip->chip_type &&
+	    ((chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) ||
+	    (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17047) ||
+	    (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050))) {
 		max17042_override_por(map, MAX17042_EmptyTempCo,
 						config->empty_tempco);
 		max17042_override_por(map, MAX17042_K_empty0,
@@ -929,7 +937,8 @@ max17042_get_default_pdata(struct max17042_chip *chip)
 	if (!pdata)
 		return pdata;
 
-	if (chip->chip_type != MAXIM_DEVICE_TYPE_MAX17042) {
+	if ((chip->chip_type == MAXIM_DEVICE_TYPE_MAX17047) ||
+	    (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050)) {
 		pdata->init_data = max17047_default_pdata_init_regs;
 		pdata->num_init_data =
 			ARRAY_SIZE(max17047_default_pdata_init_regs);
@@ -1167,6 +1176,7 @@ static const struct of_device_id max17042_dt_match[] = {
 	{ .compatible = "maxim,max17042" },
 	{ .compatible = "maxim,max17047" },
 	{ .compatible = "maxim,max17050" },
+	{ .compatible = "maxim,max17055" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, max17042_dt_match);
@@ -1176,6 +1186,7 @@ static const struct i2c_device_id max17042_id[] = {
 	{ "max17042", MAXIM_DEVICE_TYPE_MAX17042 },
 	{ "max17047", MAXIM_DEVICE_TYPE_MAX17047 },
 	{ "max17050", MAXIM_DEVICE_TYPE_MAX17050 },
+	{ "max17055", MAXIM_DEVICE_TYPE_MAX17055 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, max17042_id);
diff --git a/drivers/power/supply/max77650-charger.c b/drivers/power/supply/max77650-charger.c
index 5f9477c5cf5a..d913428bedc0 100644
--- a/drivers/power/supply/max77650-charger.c
+++ b/drivers/power/supply/max77650-charger.c
@@ -354,9 +354,16 @@ static int max77650_charger_remove(struct platform_device *pdev)
 	return max77650_charger_disable(chg);
 }
 
+static const struct of_device_id max77650_charger_of_match[] = {
+	{ .compatible = "maxim,max77650-charger" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max77650_charger_of_match);
+
 static struct platform_driver max77650_charger_driver = {
 	.driver = {
 		.name = "max77650-charger",
+		.of_match_table = max77650_charger_of_match,
 	},
 	.probe = max77650_charger_probe,
 	.remove = max77650_charger_remove,
diff --git a/drivers/power/supply/pda_power.c b/drivers/power/supply/pda_power.c
index 3ae5707d39fa..03a37fd6be27 100644
--- a/drivers/power/supply/pda_power.c
+++ b/drivers/power/supply/pda_power.c
@@ -429,6 +429,10 @@ wrongid:
 
 static int pda_power_remove(struct platform_device *pdev)
 {
+#if IS_ENABLED(CONFIG_USB_PHY)
+	if (!IS_ERR_OR_NULL(transceiver) && pdata->use_otg_notifier)
+		usb_unregister_notifier(transceiver, &otg_nb);
+#endif
 	if (pdata->is_usb_online && usb_irq)
 		free_irq(usb_irq->start, pda_psy_usb);
 	if (pdata->is_ac_online && ac_irq)
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 5c36c430ce8b..1a9a9fae73d3 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -565,9 +565,11 @@ EXPORT_SYMBOL_GPL(devm_power_supply_get_by_phandle);
 int power_supply_get_battery_info(struct power_supply *psy,
 				  struct power_supply_battery_info *info)
 {
+	struct power_supply_resistance_temp_table *resist_table;
 	struct device_node *battery_np;
 	const char *value;
 	int err, len, index;
+	const __be32 *list;
 
 	info->energy_full_design_uwh         = -EINVAL;
 	info->charge_full_design_uah         = -EINVAL;
@@ -578,6 +580,7 @@ int power_supply_get_battery_info(struct power_supply *psy,
 	info->constant_charge_current_max_ua = -EINVAL;
 	info->constant_charge_voltage_max_uv = -EINVAL;
 	info->factory_internal_resistance_uohm  = -EINVAL;
+	info->resist_table = NULL;
 
 	for (index = 0; index < POWER_SUPPLY_OCV_TEMP_MAX; index++) {
 		info->ocv_table[index]       = NULL;
@@ -644,7 +647,6 @@ int power_supply_get_battery_info(struct power_supply *psy,
 	for (index = 0; index < len; index++) {
 		struct power_supply_battery_ocv_table *table;
 		char *propname;
-		const __be32 *list;
 		int i, tab_len, size;
 
 		propname = kasprintf(GFP_KERNEL, "ocv-capacity-table-%d", index);
@@ -677,6 +679,26 @@ int power_supply_get_battery_info(struct power_supply *psy,
 		}
 	}
 
+	list = of_get_property(battery_np, "resistance-temp-table", &len);
+	if (!list || !len)
+		goto out_put_node;
+
+	info->resist_table_size = len / (2 * sizeof(__be32));
+	resist_table = info->resist_table = devm_kcalloc(&psy->dev,
+							 info->resist_table_size,
+							 sizeof(*resist_table),
+							 GFP_KERNEL);
+	if (!info->resist_table) {
+		power_supply_put_battery_info(psy, info);
+		err = -ENOMEM;
+		goto out_put_node;
+	}
+
+	for (index = 0; index < info->resist_table_size; index++) {
+		resist_table[index].temp = be32_to_cpu(*list++);
+		resist_table[index].resistance = be32_to_cpu(*list++);
+	}
+
 out_put_node:
 	of_node_put(battery_np);
 	return err;
@@ -692,10 +714,53 @@ void power_supply_put_battery_info(struct power_supply *psy,
 		if (info->ocv_table[i])
 			devm_kfree(&psy->dev, info->ocv_table[i]);
 	}
+
+	if (info->resist_table)
+		devm_kfree(&psy->dev, info->resist_table);
 }
 EXPORT_SYMBOL_GPL(power_supply_put_battery_info);
 
 /**
+ * power_supply_temp2resist_simple() - find the battery internal resistance
+ * percent
+ * @table: Pointer to battery resistance temperature table
+ * @table_len: The table length
+ * @ocv: Current temperature
+ *
+ * This helper function is used to look up battery internal resistance percent
+ * according to current temperature value from the resistance temperature table,
+ * and the table must be ordered descending. Then the actual battery internal
+ * resistance = the ideal battery internal resistance * percent / 100.
+ *
+ * Return: the battery internal resistance percent
+ */
+int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table,
+				    int table_len, int temp)
+{
+	int i, resist;
+
+	for (i = 0; i < table_len; i++)
+		if (temp > table[i].temp)
+			break;
+
+	if (i > 0 && i < table_len) {
+		int tmp;
+
+		tmp = (table[i - 1].resistance - table[i].resistance) *
+			(temp - table[i].temp);
+		tmp /= table[i - 1].temp - table[i].temp;
+		resist = tmp + table[i].resistance;
+	} else if (i == 0) {
+		resist = table[0].resistance;
+	} else {
+		resist = table[table_len - 1].resistance;
+	}
+
+	return resist;
+}
+EXPORT_SYMBOL_GPL(power_supply_temp2resist_simple);
+
+/**
  * power_supply_ocv2cap_simple() - find the battery capacity
  * @table: Pointer to battery OCV lookup table
  * @table_len: OCV table length
diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c
index f8d74e9f7931..6acd242eed48 100644
--- a/drivers/power/supply/sbs-battery.c
+++ b/drivers/power/supply/sbs-battery.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2010, NVIDIA Corporation.
  */
 
+#include <linux/bits.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
@@ -46,10 +47,10 @@ enum {
 
 /* Battery Mode defines */
 #define BATTERY_MODE_OFFSET		0x03
-#define BATTERY_MODE_MASK		0x8000
-enum sbs_battery_mode {
-	BATTERY_MODE_AMPS = 0,
-	BATTERY_MODE_WATTS = 0x8000
+#define BATTERY_MODE_CAPACITY_MASK	BIT(15)
+enum sbs_capacity_mode {
+	CAPACITY_MODE_AMPS = 0,
+	CAPACITY_MODE_WATTS = BATTERY_MODE_CAPACITY_MASK
 };
 
 /* manufacturer access defines */
@@ -518,8 +519,8 @@ static void  sbs_unit_adjustment(struct i2c_client *client,
 	}
 }
 
-static enum sbs_battery_mode sbs_set_battery_mode(struct i2c_client *client,
-	enum sbs_battery_mode mode)
+static enum sbs_capacity_mode sbs_set_capacity_mode(struct i2c_client *client,
+	enum sbs_capacity_mode mode)
 {
 	int ret, original_val;
 
@@ -527,13 +528,13 @@ static enum sbs_battery_mode sbs_set_battery_mode(struct i2c_client *client,
 	if (original_val < 0)
 		return original_val;
 
-	if ((original_val & BATTERY_MODE_MASK) == mode)
+	if ((original_val & BATTERY_MODE_CAPACITY_MASK) == mode)
 		return mode;
 
-	if (mode == BATTERY_MODE_AMPS)
-		ret = original_val & ~BATTERY_MODE_MASK;
+	if (mode == CAPACITY_MODE_AMPS)
+		ret = original_val & ~BATTERY_MODE_CAPACITY_MASK;
 	else
-		ret = original_val | BATTERY_MODE_MASK;
+		ret = original_val | BATTERY_MODE_CAPACITY_MASK;
 
 	ret = sbs_write_word_data(client, BATTERY_MODE_OFFSET, ret);
 	if (ret < 0)
@@ -541,7 +542,7 @@ static enum sbs_battery_mode sbs_set_battery_mode(struct i2c_client *client,
 
 	usleep_range(1000, 2000);
 
-	return original_val & BATTERY_MODE_MASK;
+	return original_val & BATTERY_MODE_CAPACITY_MASK;
 }
 
 static int sbs_get_battery_capacity(struct i2c_client *client,
@@ -549,13 +550,13 @@ static int sbs_get_battery_capacity(struct i2c_client *client,
 	union power_supply_propval *val)
 {
 	s32 ret;
-	enum sbs_battery_mode mode = BATTERY_MODE_WATTS;
+	enum sbs_capacity_mode mode = CAPACITY_MODE_WATTS;
 
 	if (power_supply_is_amp_property(psp))
-		mode = BATTERY_MODE_AMPS;
+		mode = CAPACITY_MODE_AMPS;
 
-	mode = sbs_set_battery_mode(client, mode);
-	if (mode < 0)
+	mode = sbs_set_capacity_mode(client, mode);
+	if ((int)mode < 0)
 		return mode;
 
 	ret = sbs_read_word_data(client, sbs_data[reg_offset].addr);
@@ -564,7 +565,7 @@ static int sbs_get_battery_capacity(struct i2c_client *client,
 
 	val->intval = ret;
 
-	ret = sbs_set_battery_mode(client, mode);
+	ret = sbs_set_capacity_mode(client, mode);
 	if (ret < 0)
 		return ret;
 
@@ -1001,6 +1002,6 @@ module_i2c_driver(sbs_battery_driver);
 MODULE_DESCRIPTION("SBS battery monitor driver");
 MODULE_LICENSE("GPL");
 
-module_param(force_load, bool, S_IRUSR | S_IRGRP | S_IROTH);
+module_param(force_load, bool, 0444);
 MODULE_PARM_DESC(force_load,
 		 "Attempt to load the driver even if no battery is connected");
diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c
index bc8f5bda5762..469c83fdaa8e 100644
--- a/drivers/power/supply/sc27xx_fuel_gauge.c
+++ b/drivers/power/supply/sc27xx_fuel_gauge.c
@@ -62,6 +62,8 @@
 
 #define SC27XX_FGU_CUR_BASIC_ADC	8192
 #define SC27XX_FGU_SAMPLE_HZ		2
+/* micro Ohms */
+#define SC27XX_FGU_IDEAL_RESISTANCE	20000
 
 /*
  * struct sc27xx_fgu_data: describe the FGU device
@@ -81,9 +83,12 @@
  * @max_volt: the maximum constant input voltage in millivolt
  * @min_volt: the minimum drained battery voltage in microvolt
  * @table_len: the capacity table length
+ * @resist_table_len: the resistance table length
  * @cur_1000ma_adc: ADC value corresponding to 1000 mA
  * @vol_1000mv_adc: ADC value corresponding to 1000 mV
+ * @calib_resist: the real resistance of coulomb counter chip in uOhm
  * @cap_table: capacity table with corresponding ocv
+ * @resist_table: resistance percent table with corresponding temperature
  */
 struct sc27xx_fgu_data {
 	struct regmap *regmap;
@@ -103,15 +108,19 @@ struct sc27xx_fgu_data {
 	int max_volt;
 	int min_volt;
 	int table_len;
+	int resist_table_len;
 	int cur_1000ma_adc;
 	int vol_1000mv_adc;
+	int calib_resist;
 	struct power_supply_battery_ocv_table *cap_table;
+	struct power_supply_resistance_temp_table *resist_table;
 };
 
 static int sc27xx_fgu_cap_to_clbcnt(struct sc27xx_fgu_data *data, int capacity);
 static void sc27xx_fgu_capacity_calibration(struct sc27xx_fgu_data *data,
 					    int cap, bool int_mode);
 static void sc27xx_fgu_adjust_cap(struct sc27xx_fgu_data *data, int cap);
+static int sc27xx_fgu_get_temp(struct sc27xx_fgu_data *data, int *temp);
 
 static const char * const sc27xx_charger_supply_name[] = {
 	"sc2731_charger",
@@ -434,7 +443,7 @@ static int sc27xx_fgu_get_current(struct sc27xx_fgu_data *data, int *val)
 
 static int sc27xx_fgu_get_vbat_ocv(struct sc27xx_fgu_data *data, int *val)
 {
-	int vol, cur, ret;
+	int vol, cur, ret, temp, resistance;
 
 	ret = sc27xx_fgu_get_vbat_vol(data, &vol);
 	if (ret)
@@ -444,8 +453,19 @@ static int sc27xx_fgu_get_vbat_ocv(struct sc27xx_fgu_data *data, int *val)
 	if (ret)
 		return ret;
 
+	resistance = data->internal_resist;
+	if (data->resist_table_len > 0) {
+		ret = sc27xx_fgu_get_temp(data, &temp);
+		if (ret)
+			return ret;
+
+		resistance = power_supply_temp2resist_simple(data->resist_table,
+						data->resist_table_len, temp);
+		resistance = data->internal_resist * resistance / 100;
+	}
+
 	/* Return the battery OCV in micro volts. */
-	*val = vol * 1000 - cur * data->internal_resist;
+	*val = vol * 1000 - cur * resistance;
 
 	return 0;
 }
@@ -884,7 +904,9 @@ static int sc27xx_fgu_calibration(struct sc27xx_fgu_data *data)
 	 */
 	cal_4200mv = (calib_data & 0x1ff) + 6963 - 4096 - 256;
 	data->vol_1000mv_adc = DIV_ROUND_CLOSEST(cal_4200mv * 10, 42);
-	data->cur_1000ma_adc = data->vol_1000mv_adc * 4;
+	data->cur_1000ma_adc =
+		DIV_ROUND_CLOSEST(data->vol_1000mv_adc * 4 * data->calib_resist,
+				  SC27XX_FGU_IDEAL_RESISTANCE);
 
 	kfree(buf);
 	return 0;
@@ -929,6 +951,18 @@ static int sc27xx_fgu_hw_init(struct sc27xx_fgu_data *data)
 	if (!data->alarm_cap)
 		data->alarm_cap += 1;
 
+	data->resist_table_len = info.resist_table_size;
+	if (data->resist_table_len > 0) {
+		data->resist_table = devm_kmemdup(data->dev, info.resist_table,
+						  data->resist_table_len *
+						  sizeof(struct power_supply_resistance_temp_table),
+						  GFP_KERNEL);
+		if (!data->resist_table) {
+			power_supply_put_battery_info(data->battery, &info);
+			return -ENOMEM;
+		}
+	}
+
 	power_supply_put_battery_info(data->battery, &info);
 
 	ret = sc27xx_fgu_calibration(data);
@@ -1051,6 +1085,15 @@ static int sc27xx_fgu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = device_property_read_u32(&pdev->dev,
+				       "sprd,calib-resistance-micro-ohms",
+				       &data->calib_resist);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"failed to get fgu calibration resistance\n");
+		return ret;
+	}
+
 	data->channel = devm_iio_channel_get(dev, "bat-temp");
 	if (IS_ERR(data->channel)) {
 		dev_err(dev, "failed to get IIO channel\n");
diff --git a/drivers/power/supply/ucs1002_power.c b/drivers/power/supply/ucs1002_power.c
index 1b80ae479e7d..cdb9a23d825f 100644
--- a/drivers/power/supply/ucs1002_power.c
+++ b/drivers/power/supply/ucs1002_power.c
@@ -100,7 +100,9 @@ struct ucs1002_info {
 	struct i2c_client *client;
 	struct regmap *regmap;
 	struct regulator_desc *regulator_descriptor;
+	struct regulator_dev *rdev;
 	bool present;
+	bool output_disable;
 };
 
 static enum power_supply_property ucs1002_props[] = {
@@ -233,6 +235,11 @@ static int ucs1002_get_max_current(struct ucs1002_info *info,
 	unsigned int reg;
 	int ret;
 
+	if (info->output_disable) {
+		val->intval = 0;
+		return 0;
+	}
+
 	ret = regmap_read(info->regmap, UCS1002_REG_ILIMIT, &reg);
 	if (ret)
 		return ret;
@@ -247,6 +254,12 @@ static int ucs1002_set_max_current(struct ucs1002_info *info, u32 val)
 	unsigned int reg;
 	int ret, idx;
 
+	if (val == 0) {
+		info->output_disable = true;
+		regulator_disable_regmap(info->rdev);
+		return 0;
+	}
+
 	for (idx = 0; idx < ARRAY_SIZE(ucs1002_current_limit_uA); idx++) {
 		if (val == ucs1002_current_limit_uA[idx])
 			break;
@@ -270,6 +283,12 @@ static int ucs1002_set_max_current(struct ucs1002_info *info, u32 val)
 	if (reg != idx)
 		return -EINVAL;
 
+	info->output_disable = false;
+
+	if (info->rdev && info->rdev->use_count &&
+	    !regulator_is_enabled_regmap(info->rdev))
+		regulator_enable_regmap(info->rdev);
+
 	return 0;
 }
 
@@ -470,9 +489,24 @@ static irqreturn_t ucs1002_alert_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static int ucs1002_regulator_enable(struct regulator_dev *rdev)
+{
+	struct ucs1002_info *info = rdev_get_drvdata(rdev);
+
+	/*
+	 * If the output is disabled due to 0 maximum current, just pretend the
+	 * enable did work. The regulator will be enabled as soon as we get a
+	 * a non-zero maximum current budget.
+	 */
+	if (info->output_disable)
+		return 0;
+
+	return regulator_enable_regmap(rdev);
+}
+
 static const struct regulator_ops ucs1002_regulator_ops = {
 	.is_enabled	= regulator_is_enabled_regmap,
-	.enable		= regulator_enable_regmap,
+	.enable		= ucs1002_regulator_enable,
 	.disable	= regulator_disable_regmap,
 };
 
@@ -499,7 +533,6 @@ static int ucs1002_probe(struct i2c_client *client,
 	};
 	struct regulator_config regulator_config = {};
 	int irq_a_det, irq_alert, ret;
-	struct regulator_dev *rdev;
 	struct ucs1002_info *info;
 	unsigned int regval;
 
@@ -589,10 +622,11 @@ static int ucs1002_probe(struct i2c_client *client,
 	regulator_config.dev = dev;
 	regulator_config.of_node = dev->of_node;
 	regulator_config.regmap = info->regmap;
+	regulator_config.driver_data = info;
 
-	rdev = devm_regulator_register(dev, info->regulator_descriptor,
+	info->rdev = devm_regulator_register(dev, info->regulator_descriptor,
 				       &regulator_config);
-	ret = PTR_ERR_OR_ZERO(rdev);
+	ret = PTR_ERR_OR_ZERO(info->rdev);
 	if (ret) {
 		dev_err(dev, "Failed to register VBUS regulator: %d\n", ret);
 		return ret;
diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
index bd21655c37a6..30190beeb6e9 100644
--- a/drivers/pwm/Kconfig
+++ b/drivers/pwm/Kconfig
@@ -100,7 +100,7 @@ config PWM_BCM_KONA
 
 config PWM_BCM2835
 	tristate "BCM2835 PWM support"
-	depends on ARCH_BCM2835
+	depends on ARCH_BCM2835 || ARCH_BRCMSTB
 	help
 	  PWM framework driver for BCM2835 controller (Raspberry Pi)
 
@@ -328,7 +328,8 @@ config PWM_MXS
 
 config PWM_OMAP_DMTIMER
 	tristate "OMAP Dual-Mode Timer PWM support"
-	depends on OF && ARCH_OMAP && OMAP_DM_TIMER
+	depends on OF
+	depends on OMAP_DM_TIMER || COMPILE_TEST
 	help
 	  Generic PWM framework driver for OMAP Dual-Mode Timer PWM output
 
@@ -490,7 +491,7 @@ config PWM_TEGRA
 	  To compile this driver as a module, choose M here: the module
 	  will be called pwm-tegra.
 
-config  PWM_TIECAP
+config PWM_TIECAP
 	tristate "ECAP PWM support"
 	depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_KEYSTONE || ARCH_K3
 	help
@@ -499,7 +500,7 @@ config  PWM_TIECAP
 	  To compile this driver as a module, choose M here: the module
 	  will be called pwm-tiecap.
 
-config  PWM_TIEHRPWM
+config PWM_TIEHRPWM
 	tristate "EHRPWM PWM support"
 	depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_K3
 	help
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index f877e77d9184..5a7f6598c05f 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -20,6 +20,9 @@
 
 #include <dt-bindings/pwm/pwm.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/pwm.h>
+
 #define MAX_PWMS 1024
 
 static DEFINE_MUTEX(pwm_lookup_lock);
@@ -114,6 +117,11 @@ static int pwm_device_request(struct pwm_device *pwm, const char *label)
 		}
 	}
 
+	if (pwm->chip->ops->get_state) {
+		pwm->chip->ops->get_state(pwm->chip, pwm, &pwm->state);
+		trace_pwm_get(pwm, &pwm->state);
+	}
+
 	set_bit(PWMF_REQUESTED, &pwm->flags);
 	pwm->label = label;
 
@@ -283,9 +291,6 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip,
 		pwm->hwpwm = i;
 		pwm->state.polarity = polarity;
 
-		if (chip->ops->get_state)
-			chip->ops->get_state(chip, pwm, &pwm->state);
-
 		radix_tree_insert(&pwm_tree, pwm->pwm, pwm);
 	}
 
@@ -472,6 +477,8 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
 		if (err)
 			return err;
 
+		trace_pwm_apply(pwm, state);
+
 		pwm->state = *state;
 	} else {
 		/*
diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index 9ba733467e26..6161e7e3e9ac 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -4,6 +4,19 @@
  *
  * Copyright (C) 2013 Atmel Corporation
  *		 Bo Shen <voice.shen@atmel.com>
+ *
+ * Links to reference manuals for the supported PWM chips can be found in
+ * Documentation/arm/microchip.rst.
+ *
+ * Limitations:
+ * - Periods start with the inactive level.
+ * - Hardware has to be stopped in general to update settings.
+ *
+ * Software bugs/possible improvements:
+ * - When atmel_pwm_apply() is called with state->enabled=false a change in
+ *   state->polarity isn't honored.
+ * - Instead of sleeping to wait for a completed period, the interrupt
+ *   functionality could be used.
  */
 
 #include <linux/clk.h>
@@ -47,6 +60,8 @@
 #define PWMV2_CPRD		0x0C
 #define PWMV2_CPRDUPD		0x10
 
+#define PWM_MAX_PRES		10
+
 struct atmel_pwm_registers {
 	u8 period;
 	u8 period_upd;
@@ -55,8 +70,7 @@ struct atmel_pwm_registers {
 };
 
 struct atmel_pwm_config {
-	u32 max_period;
-	u32 max_pres;
+	u32 period_bits;
 };
 
 struct atmel_pwm_data {
@@ -97,7 +111,7 @@ static inline u32 atmel_pwm_ch_readl(struct atmel_pwm_chip *chip,
 {
 	unsigned long base = PWM_CH_REG_OFFSET + ch * PWM_CH_REG_SIZE;
 
-	return readl_relaxed(chip->base + base + offset);
+	return atmel_pwm_readl(chip, base + offset);
 }
 
 static inline void atmel_pwm_ch_writel(struct atmel_pwm_chip *chip,
@@ -106,7 +120,7 @@ static inline void atmel_pwm_ch_writel(struct atmel_pwm_chip *chip,
 {
 	unsigned long base = PWM_CH_REG_OFFSET + ch * PWM_CH_REG_SIZE;
 
-	writel_relaxed(val, chip->base + base + offset);
+	atmel_pwm_writel(chip, base + offset, val);
 }
 
 static int atmel_pwm_calculate_cprd_and_pres(struct pwm_chip *chip,
@@ -115,17 +129,27 @@ static int atmel_pwm_calculate_cprd_and_pres(struct pwm_chip *chip,
 {
 	struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
 	unsigned long long cycles = state->period;
+	int shift;
 
 	/* Calculate the period cycles and prescale value */
 	cycles *= clk_get_rate(atmel_pwm->clk);
 	do_div(cycles, NSEC_PER_SEC);
 
-	for (*pres = 0; cycles > atmel_pwm->data->cfg.max_period; cycles >>= 1)
-		(*pres)++;
+	/*
+	 * The register for the period length is cfg.period_bits bits wide.
+	 * So for each bit the number of clock cycles is wider divide the input
+	 * clock frequency by two using pres and shift cprd accordingly.
+	 */
+	shift = fls(cycles) - atmel_pwm->data->cfg.period_bits;
 
-	if (*pres > atmel_pwm->data->cfg.max_pres) {
+	if (shift > PWM_MAX_PRES) {
 		dev_err(chip->dev, "pres exceeds the maximum value\n");
 		return -EINVAL;
+	} else if (shift > 0) {
+		*pres = shift;
+		cycles >>= *pres;
+	} else {
+		*pres = 0;
 	}
 
 	*cprd = cycles;
@@ -271,8 +295,48 @@ static int atmel_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	return 0;
 }
 
+static void atmel_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
+				struct pwm_state *state)
+{
+	struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
+	u32 sr, cmr;
+
+	sr = atmel_pwm_readl(atmel_pwm, PWM_SR);
+	cmr = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
+
+	if (sr & (1 << pwm->hwpwm)) {
+		unsigned long rate = clk_get_rate(atmel_pwm->clk);
+		u32 cdty, cprd, pres;
+		u64 tmp;
+
+		pres = cmr & PWM_CMR_CPRE_MSK;
+
+		cprd = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm,
+					  atmel_pwm->data->regs.period);
+		tmp = (u64)cprd * NSEC_PER_SEC;
+		tmp <<= pres;
+		state->period = DIV64_U64_ROUND_UP(tmp, rate);
+
+		cdty = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm,
+					  atmel_pwm->data->regs.duty);
+		tmp = (u64)cdty * NSEC_PER_SEC;
+		tmp <<= pres;
+		state->duty_cycle = DIV64_U64_ROUND_UP(tmp, rate);
+
+		state->enabled = true;
+	} else {
+		state->enabled = false;
+	}
+
+	if (cmr & PWM_CMR_CPOL)
+		state->polarity = PWM_POLARITY_INVERSED;
+	else
+		state->polarity = PWM_POLARITY_NORMAL;
+}
+
 static const struct pwm_ops atmel_pwm_ops = {
 	.apply = atmel_pwm_apply,
+	.get_state = atmel_pwm_get_state,
 	.owner = THIS_MODULE,
 };
 
@@ -285,8 +349,7 @@ static const struct atmel_pwm_data atmel_sam9rl_pwm_data = {
 	},
 	.cfg = {
 		/* 16 bits to keep period and duty. */
-		.max_period	= 0xffff,
-		.max_pres	= 10,
+		.period_bits	= 16,
 	},
 };
 
@@ -299,8 +362,7 @@ static const struct atmel_pwm_data atmel_sama5_pwm_data = {
 	},
 	.cfg = {
 		/* 16 bits to keep period and duty. */
-		.max_period	= 0xffff,
-		.max_pres	= 10,
+		.period_bits	= 16,
 	},
 };
 
@@ -313,8 +375,7 @@ static const struct atmel_pwm_data mchp_sam9x60_pwm_data = {
 	},
 	.cfg = {
 		/* 32 bits to keep period and duty. */
-		.max_period	= 0xffffffff,
-		.max_pres	= 10,
+		.period_bits	= 32,
 	},
 };
 
diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c
index 89497448d217..09c08dee099e 100644
--- a/drivers/pwm/pwm-cros-ec.c
+++ b/drivers/pwm/pwm-cros-ec.c
@@ -25,11 +25,39 @@ struct cros_ec_pwm_device {
 	struct pwm_chip chip;
 };
 
+/**
+ * struct cros_ec_pwm - per-PWM driver data
+ * @duty_cycle: cached duty cycle
+ */
+struct cros_ec_pwm {
+	u16 duty_cycle;
+};
+
 static inline struct cros_ec_pwm_device *pwm_to_cros_ec_pwm(struct pwm_chip *c)
 {
 	return container_of(c, struct cros_ec_pwm_device, chip);
 }
 
+static int cros_ec_pwm_request(struct pwm_chip *chip, struct pwm_device *pwm)
+{
+	struct cros_ec_pwm *channel;
+
+	channel = kzalloc(sizeof(*channel), GFP_KERNEL);
+	if (!channel)
+		return -ENOMEM;
+
+	pwm_set_chip_data(pwm, channel);
+
+	return 0;
+}
+
+static void cros_ec_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm)
+{
+	struct cros_ec_pwm *channel = pwm_get_chip_data(pwm);
+
+	kfree(channel);
+}
+
 static int cros_ec_pwm_set_duty(struct cros_ec_device *ec, u8 index, u16 duty)
 {
 	struct {
@@ -96,7 +124,9 @@ static int cros_ec_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			     const struct pwm_state *state)
 {
 	struct cros_ec_pwm_device *ec_pwm = pwm_to_cros_ec_pwm(chip);
-	int duty_cycle;
+	struct cros_ec_pwm *channel = pwm_get_chip_data(pwm);
+	u16 duty_cycle;
+	int ret;
 
 	/* The EC won't let us change the period */
 	if (state->period != EC_PWM_MAX_DUTY)
@@ -108,13 +138,20 @@ static int cros_ec_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 	 */
 	duty_cycle = state->enabled ? state->duty_cycle : 0;
 
-	return cros_ec_pwm_set_duty(ec_pwm->ec, pwm->hwpwm, duty_cycle);
+	ret = cros_ec_pwm_set_duty(ec_pwm->ec, pwm->hwpwm, duty_cycle);
+	if (ret < 0)
+		return ret;
+
+	channel->duty_cycle = state->duty_cycle;
+
+	return 0;
 }
 
 static void cros_ec_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 				  struct pwm_state *state)
 {
 	struct cros_ec_pwm_device *ec_pwm = pwm_to_cros_ec_pwm(chip);
+	struct cros_ec_pwm *channel = pwm_get_chip_data(pwm);
 	int ret;
 
 	ret = cros_ec_pwm_get_duty(ec_pwm->ec, pwm->hwpwm);
@@ -126,8 +163,19 @@ static void cros_ec_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
 	state->enabled = (ret > 0);
 	state->period = EC_PWM_MAX_DUTY;
 
-	/* Note that "disabled" and "duty cycle == 0" are treated the same */
-	state->duty_cycle = ret;
+	/*
+	 * Note that "disabled" and "duty cycle == 0" are treated the same. If
+	 * the cached duty cycle is not zero, used the cached duty cycle. This
+	 * ensures that the configured duty cycle is kept across a disable and
+	 * enable operation and avoids potentially confusing consumers.
+	 *
+	 * For the case of the initial hardware readout, channel->duty_cycle
+	 * will be 0 and the actual duty cycle read from the EC is used.
+	 */
+	if (ret == 0 && channel->duty_cycle > 0)
+		state->duty_cycle = channel->duty_cycle;
+	else
+		state->duty_cycle = ret;
 }
 
 static struct pwm_device *
@@ -149,6 +197,8 @@ cros_ec_pwm_xlate(struct pwm_chip *pc, const struct of_phandle_args *args)
 }
 
 static const struct pwm_ops cros_ec_pwm_ops = {
+	.request = cros_ec_pwm_request,
+	.free = cros_ec_pwm_free,
 	.get_state	= cros_ec_pwm_get_state,
 	.apply		= cros_ec_pwm_apply,
 	.owner		= THIS_MODULE,
diff --git a/drivers/pwm/pwm-imx27.c b/drivers/pwm/pwm-imx27.c
index ae11d8577f18..35a7ac42269c 100644
--- a/drivers/pwm/pwm-imx27.c
+++ b/drivers/pwm/pwm-imx27.c
@@ -85,6 +85,13 @@ struct pwm_imx27_chip {
 	struct clk	*clk_per;
 	void __iomem	*mmio_base;
 	struct pwm_chip	chip;
+
+	/*
+	 * The driver cannot read the current duty cycle from the hardware if
+	 * the hardware is disabled. Cache the last programmed duty cycle
+	 * value to return in that case.
+	 */
+	unsigned int duty_cycle;
 };
 
 #define to_pwm_imx27_chip(chip)	container_of(chip, struct pwm_imx27_chip, chip)
@@ -155,14 +162,17 @@ static void pwm_imx27_get_state(struct pwm_chip *chip,
 	tmp = NSEC_PER_SEC * (u64)(period + 2);
 	state->period = DIV_ROUND_CLOSEST_ULL(tmp, pwm_clk);
 
-	/* PWMSAR can be read only if PWM is enabled */
-	if (state->enabled) {
+	/*
+	 * PWMSAR can be read only if PWM is enabled. If the PWM is disabled,
+	 * use the cached value.
+	 */
+	if (state->enabled)
 		val = readl(imx->mmio_base + MX3_PWMSAR);
-		tmp = NSEC_PER_SEC * (u64)(val);
-		state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, pwm_clk);
-	} else {
-		state->duty_cycle = 0;
-	}
+	else
+		val = imx->duty_cycle;
+
+	tmp = NSEC_PER_SEC * (u64)(val);
+	state->duty_cycle = DIV_ROUND_CLOSEST_ULL(tmp, pwm_clk);
 
 	if (!state->enabled)
 		pwm_imx27_clk_disable_unprepare(chip);
@@ -220,63 +230,68 @@ static int pwm_imx27_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 
 	pwm_get_state(pwm, &cstate);
 
-	if (state->enabled) {
-		c = clk_get_rate(imx->clk_per);
-		c *= state->period;
-
-		do_div(c, 1000000000);
-		period_cycles = c;
-
-		prescale = period_cycles / 0x10000 + 1;
-
-		period_cycles /= prescale;
-		c = (unsigned long long)period_cycles * state->duty_cycle;
-		do_div(c, state->period);
-		duty_cycles = c;
-
-		/*
-		 * according to imx pwm RM, the real period value should be
-		 * PERIOD value in PWMPR plus 2.
-		 */
-		if (period_cycles > 2)
-			period_cycles -= 2;
-		else
-			period_cycles = 0;
-
-		/*
-		 * Wait for a free FIFO slot if the PWM is already enabled, and
-		 * flush the FIFO if the PWM was disabled and is about to be
-		 * enabled.
-		 */
-		if (cstate.enabled) {
-			pwm_imx27_wait_fifo_slot(chip, pwm);
-		} else {
-			ret = pwm_imx27_clk_prepare_enable(chip);
-			if (ret)
-				return ret;
-
-			pwm_imx27_sw_reset(chip);
-		}
-
-		writel(duty_cycles, imx->mmio_base + MX3_PWMSAR);
-		writel(period_cycles, imx->mmio_base + MX3_PWMPR);
-
-		cr = MX3_PWMCR_PRESCALER_SET(prescale) |
-		     MX3_PWMCR_STOPEN | MX3_PWMCR_DOZEN | MX3_PWMCR_WAITEN |
-		     FIELD_PREP(MX3_PWMCR_CLKSRC, MX3_PWMCR_CLKSRC_IPG_HIGH) |
-		     MX3_PWMCR_DBGEN | MX3_PWMCR_EN;
-
-		if (state->polarity == PWM_POLARITY_INVERSED)
-			cr |= FIELD_PREP(MX3_PWMCR_POUTC,
-					MX3_PWMCR_POUTC_INVERTED);
-
-		writel(cr, imx->mmio_base + MX3_PWMCR);
-	} else if (cstate.enabled) {
-		writel(0, imx->mmio_base + MX3_PWMCR);
+	c = clk_get_rate(imx->clk_per);
+	c *= state->period;
 
-		pwm_imx27_clk_disable_unprepare(chip);
+	do_div(c, 1000000000);
+	period_cycles = c;
+
+	prescale = period_cycles / 0x10000 + 1;
+
+	period_cycles /= prescale;
+	c = (unsigned long long)period_cycles * state->duty_cycle;
+	do_div(c, state->period);
+	duty_cycles = c;
+
+	/*
+	 * according to imx pwm RM, the real period value should be PERIOD
+	 * value in PWMPR plus 2.
+	 */
+	if (period_cycles > 2)
+		period_cycles -= 2;
+	else
+		period_cycles = 0;
+
+	/*
+	 * Wait for a free FIFO slot if the PWM is already enabled, and flush
+	 * the FIFO if the PWM was disabled and is about to be enabled.
+	 */
+	if (cstate.enabled) {
+		pwm_imx27_wait_fifo_slot(chip, pwm);
+	} else {
+		ret = pwm_imx27_clk_prepare_enable(chip);
+		if (ret)
+			return ret;
+
+		pwm_imx27_sw_reset(chip);
 	}
 
+	writel(duty_cycles, imx->mmio_base + MX3_PWMSAR);
+	writel(period_cycles, imx->mmio_base + MX3_PWMPR);
+
+	/*
+	 * Store the duty cycle for future reference in cases where the
+	 * MX3_PWMSAR register can't be read (i.e. when the PWM is disabled).
+	 */
+	imx->duty_cycle = duty_cycles;
+
+	cr = MX3_PWMCR_PRESCALER_SET(prescale) |
+	     MX3_PWMCR_STOPEN | MX3_PWMCR_DOZEN | MX3_PWMCR_WAITEN |
+	     FIELD_PREP(MX3_PWMCR_CLKSRC, MX3_PWMCR_CLKSRC_IPG_HIGH) |
+	     MX3_PWMCR_DBGEN;
+
+	if (state->polarity == PWM_POLARITY_INVERSED)
+		cr |= FIELD_PREP(MX3_PWMCR_POUTC,
+				MX3_PWMCR_POUTC_INVERTED);
+
+	if (state->enabled)
+		cr |= MX3_PWMCR_EN;
+
+	writel(cr, imx->mmio_base + MX3_PWMCR);
+
+	if (!state->enabled && cstate.enabled)
+		pwm_imx27_clk_disable_unprepare(chip);
+
 	return 0;
 }
 
@@ -304,9 +319,13 @@ static int pwm_imx27_probe(struct platform_device *pdev)
 
 	imx->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
 	if (IS_ERR(imx->clk_ipg)) {
-		dev_err(&pdev->dev, "getting ipg clock failed with %ld\n",
-				PTR_ERR(imx->clk_ipg));
-		return PTR_ERR(imx->clk_ipg);
+		int ret = PTR_ERR(imx->clk_ipg);
+
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev,
+				"getting ipg clock failed with %d\n",
+				ret);
+		return ret;
 	}
 
 	imx->clk_per = devm_clk_get(&pdev->dev, "per");
diff --git a/drivers/pwm/pwm-mxs.c b/drivers/pwm/pwm-mxs.c
index b14376b47ac8..f2e57fcf8f8b 100644
--- a/drivers/pwm/pwm-mxs.c
+++ b/drivers/pwm/pwm-mxs.c
@@ -25,12 +25,16 @@
 #define  PERIOD_PERIOD(p)	((p) & 0xffff)
 #define  PERIOD_PERIOD_MAX	0x10000
 #define  PERIOD_ACTIVE_HIGH	(3 << 16)
+#define  PERIOD_ACTIVE_LOW	(2 << 16)
+#define  PERIOD_INACTIVE_HIGH	(3 << 18)
 #define  PERIOD_INACTIVE_LOW	(2 << 18)
+#define  PERIOD_POLARITY_NORMAL	(PERIOD_ACTIVE_HIGH | PERIOD_INACTIVE_LOW)
+#define  PERIOD_POLARITY_INVERSE	(PERIOD_ACTIVE_LOW | PERIOD_INACTIVE_HIGH)
 #define  PERIOD_CDIV(div)	(((div) & 0x7) << 20)
 #define  PERIOD_CDIV_MAX	8
 
-static const unsigned int cdiv[PERIOD_CDIV_MAX] = {
-	1, 2, 4, 8, 16, 64, 256, 1024
+static const u8 cdiv_shift[PERIOD_CDIV_MAX] = {
+	0, 1, 2, 3, 4, 6, 8, 10
 };
 
 struct mxs_pwm_chip {
@@ -41,19 +45,34 @@ struct mxs_pwm_chip {
 
 #define to_mxs_pwm_chip(_chip) container_of(_chip, struct mxs_pwm_chip, chip)
 
-static int mxs_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
-			  int duty_ns, int period_ns)
+static int mxs_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+			 const struct pwm_state *state)
 {
 	struct mxs_pwm_chip *mxs = to_mxs_pwm_chip(chip);
 	int ret, div = 0;
 	unsigned int period_cycles, duty_cycles;
 	unsigned long rate;
 	unsigned long long c;
+	unsigned int pol_bits;
+
+	/*
+	 * If the PWM channel is disabled, make sure to turn on the
+	 * clock before calling clk_get_rate() and writing to the
+	 * registers. Otherwise, just keep it enabled.
+	 */
+	if (!pwm_is_enabled(pwm)) {
+		ret = clk_prepare_enable(mxs->clk);
+		if (ret)
+			return ret;
+	}
+
+	if (!state->enabled && pwm_is_enabled(pwm))
+		writel(1 << pwm->hwpwm, mxs->base + PWM_CTRL + CLR);
 
 	rate = clk_get_rate(mxs->clk);
 	while (1) {
-		c = rate / cdiv[div];
-		c = c * period_ns;
+		c = rate >> cdiv_shift[div];
+		c = c * state->period;
 		do_div(c, 1000000000);
 		if (c < PERIOD_PERIOD_MAX)
 			break;
@@ -63,62 +82,40 @@ static int mxs_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	}
 
 	period_cycles = c;
-	c *= duty_ns;
-	do_div(c, period_ns);
+	c *= state->duty_cycle;
+	do_div(c, state->period);
 	duty_cycles = c;
 
 	/*
-	 * If the PWM channel is disabled, make sure to turn on the clock
-	 * before writing the register. Otherwise, keep it enabled.
+	 * The data sheet the says registers must be written to in
+	 * this order (ACTIVEn, then PERIODn). Also, the new settings
+	 * only take effect at the beginning of a new period, avoiding
+	 * glitches.
 	 */
-	if (!pwm_is_enabled(pwm)) {
-		ret = clk_prepare_enable(mxs->clk);
-		if (ret)
-			return ret;
-	}
 
+	pol_bits = state->polarity == PWM_POLARITY_NORMAL ?
+		PERIOD_POLARITY_NORMAL : PERIOD_POLARITY_INVERSE;
 	writel(duty_cycles << 16,
-			mxs->base + PWM_ACTIVE0 + pwm->hwpwm * 0x20);
-	writel(PERIOD_PERIOD(period_cycles) | PERIOD_ACTIVE_HIGH |
-	       PERIOD_INACTIVE_LOW | PERIOD_CDIV(div),
-			mxs->base + PWM_PERIOD0 + pwm->hwpwm * 0x20);
-
-	/*
-	 * If the PWM is not enabled, turn the clock off again to save power.
-	 */
-	if (!pwm_is_enabled(pwm))
+	       mxs->base + PWM_ACTIVE0 + pwm->hwpwm * 0x20);
+	writel(PERIOD_PERIOD(period_cycles) | pol_bits | PERIOD_CDIV(div),
+	       mxs->base + PWM_PERIOD0 + pwm->hwpwm * 0x20);
+
+	if (state->enabled) {
+		if (!pwm_is_enabled(pwm)) {
+			/*
+			 * The clock was enabled above. Just enable
+			 * the channel in the control register.
+			 */
+			writel(1 << pwm->hwpwm, mxs->base + PWM_CTRL + SET);
+		}
+	} else {
 		clk_disable_unprepare(mxs->clk);
-
-	return 0;
-}
-
-static int mxs_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
-{
-	struct mxs_pwm_chip *mxs = to_mxs_pwm_chip(chip);
-	int ret;
-
-	ret = clk_prepare_enable(mxs->clk);
-	if (ret)
-		return ret;
-
-	writel(1 << pwm->hwpwm, mxs->base + PWM_CTRL + SET);
-
+	}
 	return 0;
 }
 
-static void mxs_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
-{
-	struct mxs_pwm_chip *mxs = to_mxs_pwm_chip(chip);
-
-	writel(1 << pwm->hwpwm, mxs->base + PWM_CTRL + CLR);
-
-	clk_disable_unprepare(mxs->clk);
-}
-
 static const struct pwm_ops mxs_pwm_ops = {
-	.config = mxs_pwm_config,
-	.enable = mxs_pwm_enable,
-	.disable = mxs_pwm_disable,
+	.apply = mxs_pwm_apply,
 	.owner = THIS_MODULE,
 };
 
@@ -142,6 +139,8 @@ static int mxs_pwm_probe(struct platform_device *pdev)
 
 	mxs->chip.dev = &pdev->dev;
 	mxs->chip.ops = &mxs_pwm_ops;
+	mxs->chip.of_xlate = of_pwm_xlate_with_flags;
+	mxs->chip.of_pwm_n_cells = 3;
 	mxs->chip.base = -1;
 
 	ret = of_property_read_u32(np, "fsl,pwm-number", &mxs->chip.npwm);
diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c
index 00772fc53490..88a3c5690fea 100644
--- a/drivers/pwm/pwm-omap-dmtimer.c
+++ b/drivers/pwm/pwm-omap-dmtimer.c
@@ -256,7 +256,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	if (!timer_pdev) {
 		dev_err(&pdev->dev, "Unable to find Timer pdev\n");
 		ret = -ENODEV;
-		goto put;
+		goto err_find_timer_pdev;
 	}
 
 	timer_pdata = dev_get_platdata(&timer_pdev->dev);
@@ -264,7 +264,7 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 		dev_dbg(&pdev->dev,
 			 "dmtimer pdata structure NULL, deferring probe\n");
 		ret = -EPROBE_DEFER;
-		goto put;
+		goto err_platdata;
 	}
 
 	pdata = timer_pdata->timer_ops;
@@ -283,30 +283,25 @@ static int pwm_omap_dmtimer_probe(struct platform_device *pdev)
 	    !pdata->write_counter) {
 		dev_err(&pdev->dev, "Incomplete dmtimer pdata structure\n");
 		ret = -EINVAL;
-		goto put;
+		goto err_platdata;
 	}
 
 	if (!of_get_property(timer, "ti,timer-pwm", NULL)) {
 		dev_err(&pdev->dev, "Missing ti,timer-pwm capability\n");
 		ret = -ENODEV;
-		goto put;
+		goto err_timer_property;
 	}
 
 	dm_timer = pdata->request_by_node(timer);
 	if (!dm_timer) {
 		ret = -EPROBE_DEFER;
-		goto put;
+		goto err_request_timer;
 	}
 
-put:
-	of_node_put(timer);
-	if (ret < 0)
-		return ret;
-
 	omap = devm_kzalloc(&pdev->dev, sizeof(*omap), GFP_KERNEL);
 	if (!omap) {
-		pdata->free(dm_timer);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_alloc_omap;
 	}
 
 	omap->pdata = pdata;
@@ -339,27 +334,56 @@ put:
 	ret = pwmchip_add(&omap->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register PWM\n");
-		omap->pdata->free(omap->dm_timer);
-		return ret;
+		goto err_pwmchip_add;
 	}
 
+	of_node_put(timer);
+
 	platform_set_drvdata(pdev, omap);
 
 	return 0;
+
+err_pwmchip_add:
+
+	/*
+	 * *omap is allocated using devm_kzalloc,
+	 * so no free necessary here
+	 */
+err_alloc_omap:
+
+	pdata->free(dm_timer);
+err_request_timer:
+
+err_timer_property:
+err_platdata:
+
+	put_device(&timer_pdev->dev);
+err_find_timer_pdev:
+
+	of_node_put(timer);
+
+	return ret;
 }
 
 static int pwm_omap_dmtimer_remove(struct platform_device *pdev)
 {
 	struct pwm_omap_dmtimer_chip *omap = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = pwmchip_remove(&omap->chip);
+	if (ret)
+		return ret;
 
 	if (pm_runtime_active(&omap->dm_timer_pdev->dev))
 		omap->pdata->stop(omap->dm_timer);
 
 	omap->pdata->free(omap->dm_timer);
 
+	put_device(&omap->dm_timer_pdev->dev);
+
 	mutex_destroy(&omap->mutex);
 
-	return pwmchip_remove(&omap->chip);
+	return 0;
 }
 
 static const struct of_device_id pwm_omap_dmtimer_of_match[] = {
diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c
index 168684b02ebc..b07bdca3d510 100644
--- a/drivers/pwm/pwm-pca9685.c
+++ b/drivers/pwm/pwm-pca9685.c
@@ -159,13 +159,9 @@ static void pca9685_pwm_gpio_set(struct gpio_chip *gpio, unsigned int offset,
 static void pca9685_pwm_gpio_free(struct gpio_chip *gpio, unsigned int offset)
 {
 	struct pca9685 *pca = gpiochip_get_data(gpio);
-	struct pwm_device *pwm;
 
 	pca9685_pwm_gpio_set(gpio, offset, 0);
 	pm_runtime_put(pca->chip.dev);
-	mutex_lock(&pca->lock);
-	pwm = &pca->chip.pwms[offset];
-	mutex_unlock(&pca->lock);
 }
 
 static int pca9685_pwm_gpio_get_direction(struct gpio_chip *chip,
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index 852eb2347954..2685577b6dd4 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -3,6 +3,9 @@
  * R-Car PWM Timer driver
  *
  * Copyright (C) 2015 Renesas Electronics Corporation
+ *
+ * Limitations:
+ * - The hardware cannot generate a 0% duty cycle.
  */
 
 #include <linux/clk.h>
@@ -161,11 +164,9 @@ static int rcar_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			  const struct pwm_state *state)
 {
 	struct rcar_pwm_chip *rp = to_rcar_pwm_chip(chip);
-	struct pwm_state cur_state;
 	int div, ret;
 
 	/* This HW/driver only supports normal polarity */
-	pwm_get_state(pwm, &cur_state);
 	if (state->polarity != PWM_POLARITY_NORMAL)
 		return -ENOTSUPP;
 
diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
index 7ff48c14fae8..d3be944f2ae9 100644
--- a/drivers/pwm/pwm-stm32.c
+++ b/drivers/pwm/pwm-stm32.c
@@ -377,9 +377,7 @@ static int stm32_pwm_config(struct stm32_pwm *priv, int ch,
 	else
 		regmap_update_bits(priv->regmap, TIM_CCMR2, mask, ccmr);
 
-	regmap_update_bits(priv->regmap, TIM_BDTR,
-			   TIM_BDTR_MOE | TIM_BDTR_AOE,
-			   TIM_BDTR_MOE | TIM_BDTR_AOE);
+	regmap_update_bits(priv->regmap, TIM_BDTR, TIM_BDTR_MOE, TIM_BDTR_MOE);
 
 	return 0;
 }
diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c
index 581d23287333..3e3efa6c768f 100644
--- a/drivers/pwm/pwm-sun4i.c
+++ b/drivers/pwm/pwm-sun4i.c
@@ -3,6 +3,10 @@
  * Driver for Allwinner sun4i Pulse Width Modulation Controller
  *
  * Copyright (C) 2014 Alexandre Belloni <alexandre.belloni@free-electrons.com>
+ *
+ * Limitations:
+ * - When outputing the source clock directly, the PWM logic will be bypassed
+ *   and the currently running period is not guaranteed to be completed
  */
 
 #include <linux/bitops.h>
@@ -16,6 +20,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pwm.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/time.h>
@@ -72,12 +77,15 @@ static const u32 prescaler_table[] = {
 
 struct sun4i_pwm_data {
 	bool has_prescaler_bypass;
+	bool has_direct_mod_clk_output;
 	unsigned int npwm;
 };
 
 struct sun4i_pwm_chip {
 	struct pwm_chip chip;
+	struct clk *bus_clk;
 	struct clk *clk;
+	struct reset_control *rst;
 	void __iomem *base;
 	spinlock_t ctrl_lock;
 	const struct sun4i_pwm_data *data;
@@ -115,6 +123,20 @@ static void sun4i_pwm_get_state(struct pwm_chip *chip,
 
 	val = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG);
 
+	/*
+	 * PWM chapter in H6 manual has a diagram which explains that if bypass
+	 * bit is set, no other setting has any meaning. Even more, experiment
+	 * proved that also enable bit is ignored in this case.
+	 */
+	if ((val & BIT_CH(PWM_BYPASS, pwm->hwpwm)) &&
+	    sun4i_pwm->data->has_direct_mod_clk_output) {
+		state->period = DIV_ROUND_UP_ULL(NSEC_PER_SEC, clk_rate);
+		state->duty_cycle = DIV_ROUND_UP_ULL(state->period, 2);
+		state->polarity = PWM_POLARITY_NORMAL;
+		state->enabled = true;
+		return;
+	}
+
 	if ((PWM_REG_PRESCAL(val, pwm->hwpwm) == PWM_PRESCAL_MASK) &&
 	    sun4i_pwm->data->has_prescaler_bypass)
 		prescaler = 1;
@@ -146,13 +168,24 @@ static void sun4i_pwm_get_state(struct pwm_chip *chip,
 
 static int sun4i_pwm_calculate(struct sun4i_pwm_chip *sun4i_pwm,
 			       const struct pwm_state *state,
-			       u32 *dty, u32 *prd, unsigned int *prsclr)
+			       u32 *dty, u32 *prd, unsigned int *prsclr,
+			       bool *bypass)
 {
 	u64 clk_rate, div = 0;
-	unsigned int pval, prescaler = 0;
+	unsigned int prescaler = 0;
 
 	clk_rate = clk_get_rate(sun4i_pwm->clk);
 
+	*bypass = sun4i_pwm->data->has_direct_mod_clk_output &&
+		  state->enabled &&
+		  (state->period * clk_rate >= NSEC_PER_SEC) &&
+		  (state->period * clk_rate < 2 * NSEC_PER_SEC) &&
+		  (state->duty_cycle * clk_rate * 2 >= NSEC_PER_SEC);
+
+	/* Skip calculation of other parameters if we bypass them */
+	if (*bypass)
+		return 0;
+
 	if (sun4i_pwm->data->has_prescaler_bypass) {
 		/* First, test without any prescaler when available */
 		prescaler = PWM_PRESCAL_MASK;
@@ -170,9 +203,11 @@ static int sun4i_pwm_calculate(struct sun4i_pwm_chip *sun4i_pwm,
 	if (prescaler == 0) {
 		/* Go up from the first divider */
 		for (prescaler = 0; prescaler < PWM_PRESCAL_MASK; prescaler++) {
-			if (!prescaler_table[prescaler])
+			unsigned int pval = prescaler_table[prescaler];
+
+			if (!pval)
 				continue;
-			pval = prescaler_table[prescaler];
+
 			div = clk_rate;
 			do_div(div, pval);
 			div = div * state->period;
@@ -199,10 +234,11 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 {
 	struct sun4i_pwm_chip *sun4i_pwm = to_sun4i_pwm_chip(chip);
 	struct pwm_state cstate;
-	u32 ctrl;
+	u32 ctrl, duty = 0, period = 0, val;
 	int ret;
-	unsigned int delay_us;
+	unsigned int delay_us, prescaler = 0;
 	unsigned long now;
+	bool bypass;
 
 	pwm_get_state(pwm, &cstate);
 
@@ -214,46 +250,52 @@ static int sun4i_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 		}
 	}
 
+	ret = sun4i_pwm_calculate(sun4i_pwm, state, &duty, &period, &prescaler,
+				  &bypass);
+	if (ret) {
+		dev_err(chip->dev, "period exceeds the maximum value\n");
+		if (!cstate.enabled)
+			clk_disable_unprepare(sun4i_pwm->clk);
+		return ret;
+	}
+
 	spin_lock(&sun4i_pwm->ctrl_lock);
 	ctrl = sun4i_pwm_readl(sun4i_pwm, PWM_CTRL_REG);
 
-	if ((cstate.period != state->period) ||
-	    (cstate.duty_cycle != state->duty_cycle)) {
-		u32 period, duty, val;
-		unsigned int prescaler;
-
-		ret = sun4i_pwm_calculate(sun4i_pwm, state,
-					  &duty, &period, &prescaler);
-		if (ret) {
-			dev_err(chip->dev, "period exceeds the maximum value\n");
+	if (sun4i_pwm->data->has_direct_mod_clk_output) {
+		if (bypass) {
+			ctrl |= BIT_CH(PWM_BYPASS, pwm->hwpwm);
+			/* We can skip other parameter */
+			sun4i_pwm_writel(sun4i_pwm, ctrl, PWM_CTRL_REG);
 			spin_unlock(&sun4i_pwm->ctrl_lock);
-			if (!cstate.enabled)
-				clk_disable_unprepare(sun4i_pwm->clk);
-			return ret;
+			return 0;
 		}
 
-		if (PWM_REG_PRESCAL(ctrl, pwm->hwpwm) != prescaler) {
-			/* Prescaler changed, the clock has to be gated */
-			ctrl &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm);
-			sun4i_pwm_writel(sun4i_pwm, ctrl, PWM_CTRL_REG);
+		ctrl &= ~BIT_CH(PWM_BYPASS, pwm->hwpwm);
+	}
 
-			ctrl &= ~BIT_CH(PWM_PRESCAL_MASK, pwm->hwpwm);
-			ctrl |= BIT_CH(prescaler, pwm->hwpwm);
-		}
+	if (PWM_REG_PRESCAL(ctrl, pwm->hwpwm) != prescaler) {
+		/* Prescaler changed, the clock has to be gated */
+		ctrl &= ~BIT_CH(PWM_CLK_GATING, pwm->hwpwm);
+		sun4i_pwm_writel(sun4i_pwm, ctrl, PWM_CTRL_REG);
 
-		val = (duty & PWM_DTY_MASK) | PWM_PRD(period);
-		sun4i_pwm_writel(sun4i_pwm, val, PWM_CH_PRD(pwm->hwpwm));
-		sun4i_pwm->next_period[pwm->hwpwm] = jiffies +
-			usecs_to_jiffies(cstate.period / 1000 + 1);
-		sun4i_pwm->needs_delay[pwm->hwpwm] = true;
+		ctrl &= ~BIT_CH(PWM_PRESCAL_MASK, pwm->hwpwm);
+		ctrl |= BIT_CH(prescaler, pwm->hwpwm);
 	}
 
+	val = (duty & PWM_DTY_MASK) | PWM_PRD(period);
+	sun4i_pwm_writel(sun4i_pwm, val, PWM_CH_PRD(pwm->hwpwm));
+	sun4i_pwm->next_period[pwm->hwpwm] = jiffies +
+		usecs_to_jiffies(cstate.period / 1000 + 1);
+	sun4i_pwm->needs_delay[pwm->hwpwm] = true;
+
 	if (state->polarity != PWM_POLARITY_NORMAL)
 		ctrl &= ~BIT_CH(PWM_ACT_STATE, pwm->hwpwm);
 	else
 		ctrl |= BIT_CH(PWM_ACT_STATE, pwm->hwpwm);
 
 	ctrl |= BIT_CH(PWM_CLK_GATING, pwm->hwpwm);
+
 	if (state->enabled) {
 		ctrl |= BIT_CH(PWM_EN, pwm->hwpwm);
 	} else if (!sun4i_pwm->needs_delay[pwm->hwpwm]) {
@@ -319,6 +361,12 @@ static const struct sun4i_pwm_data sun4i_pwm_single_bypass = {
 	.npwm = 1,
 };
 
+static const struct sun4i_pwm_data sun50i_h6_pwm_data = {
+	.has_prescaler_bypass = true,
+	.has_direct_mod_clk_output = true,
+	.npwm = 2,
+};
+
 static const struct of_device_id sun4i_pwm_dt_ids[] = {
 	{
 		.compatible = "allwinner,sun4i-a10-pwm",
@@ -336,6 +384,9 @@ static const struct of_device_id sun4i_pwm_dt_ids[] = {
 		.compatible = "allwinner,sun8i-h3-pwm",
 		.data = &sun4i_pwm_single_bypass,
 	}, {
+		.compatible = "allwinner,sun50i-h6-pwm",
+		.data = &sun50i_h6_pwm_data,
+	}, {
 		/* sentinel */
 	},
 };
@@ -360,9 +411,69 @@ static int sun4i_pwm_probe(struct platform_device *pdev)
 	if (IS_ERR(pwm->base))
 		return PTR_ERR(pwm->base);
 
-	pwm->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(pwm->clk))
+	/*
+	 * All hardware variants need a source clock that is divided and
+	 * then feeds the counter that defines the output wave form. In the
+	 * device tree this clock is either unnamed or called "mod".
+	 * Some variants (e.g. H6) need another clock to access the
+	 * hardware registers; this is called "bus".
+	 * So we request "mod" first (and ignore the corner case that a
+	 * parent provides a "mod" clock while the right one would be the
+	 * unnamed one of the PWM device) and if this is not found we fall
+	 * back to the first clock of the PWM.
+	 */
+	pwm->clk = devm_clk_get_optional(&pdev->dev, "mod");
+	if (IS_ERR(pwm->clk)) {
+		if (PTR_ERR(pwm->clk) != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "get mod clock failed %pe\n",
+				pwm->clk);
 		return PTR_ERR(pwm->clk);
+	}
+
+	if (!pwm->clk) {
+		pwm->clk = devm_clk_get(&pdev->dev, NULL);
+		if (IS_ERR(pwm->clk)) {
+			if (PTR_ERR(pwm->clk) != -EPROBE_DEFER)
+				dev_err(&pdev->dev, "get unnamed clock failed %pe\n",
+					pwm->clk);
+			return PTR_ERR(pwm->clk);
+		}
+	}
+
+	pwm->bus_clk = devm_clk_get_optional(&pdev->dev, "bus");
+	if (IS_ERR(pwm->bus_clk)) {
+		if (PTR_ERR(pwm->bus_clk) != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "get bus clock failed %pe\n",
+				pwm->bus_clk);
+		return PTR_ERR(pwm->bus_clk);
+	}
+
+	pwm->rst = devm_reset_control_get_optional_shared(&pdev->dev, NULL);
+	if (IS_ERR(pwm->rst)) {
+		if (PTR_ERR(pwm->rst) != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "get reset failed %pe\n",
+				pwm->rst);
+		return PTR_ERR(pwm->rst);
+	}
+
+	/* Deassert reset */
+	ret = reset_control_deassert(pwm->rst);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot deassert reset control: %pe\n",
+			ERR_PTR(ret));
+		return ret;
+	}
+
+	/*
+	 * We're keeping the bus clock on for the sake of simplicity.
+	 * Actually it only needs to be on for hardware register accesses.
+	 */
+	ret = clk_prepare_enable(pwm->bus_clk);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot prepare and enable bus_clk %pe\n",
+			ERR_PTR(ret));
+		goto err_bus;
+	}
 
 	pwm->chip.dev = &pdev->dev;
 	pwm->chip.ops = &sun4i_pwm_ops;
@@ -376,19 +487,34 @@ static int sun4i_pwm_probe(struct platform_device *pdev)
 	ret = pwmchip_add(&pwm->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret);
-		return ret;
+		goto err_pwm_add;
 	}
 
 	platform_set_drvdata(pdev, pwm);
 
 	return 0;
+
+err_pwm_add:
+	clk_disable_unprepare(pwm->bus_clk);
+err_bus:
+	reset_control_assert(pwm->rst);
+
+	return ret;
 }
 
 static int sun4i_pwm_remove(struct platform_device *pdev)
 {
 	struct sun4i_pwm_chip *pwm = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = pwmchip_remove(&pwm->chip);
+	if (ret)
+		return ret;
+
+	clk_disable_unprepare(pwm->bus_clk);
+	reset_control_assert(pwm->rst);
 
-	return pwmchip_remove(&pwm->chip);
+	return 0;
 }
 
 static struct platform_driver sun4i_pwm_driver = {
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 97bfdd47954f..074a2ef55943 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -209,6 +209,7 @@ config REGULATOR_BD71828
 config REGULATOR_BD718XX
 	tristate "ROHM BD71837 Power Regulator"
 	depends on MFD_ROHM_BD718XX
+	select REGULATOR_ROHM
 	help
 	  This driver supports voltage regulators on ROHM BD71837 PMIC.
 	  This will enable support for the software controllable buck
@@ -823,6 +824,9 @@ config REGULATOR_RN5T618
 	  Say y here to support the regulators found on Ricoh RN5T567,
 	  RN5T618 or RC5T619 PMIC.
 
+config REGULATOR_ROHM
+	tristate
+
 config REGULATOR_RT5033
 	tristate "Richtek RT5033 Regulators"
 	depends on MFD_RT5033
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 07bc977c52b0..c0d6b96ebd78 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -102,6 +102,7 @@ obj-$(CONFIG_REGULATOR_PCF50633) += pcf50633-regulator.o
 obj-$(CONFIG_REGULATOR_RC5T583)  += rc5t583-regulator.o
 obj-$(CONFIG_REGULATOR_RK808)   += rk808-regulator.o
 obj-$(CONFIG_REGULATOR_RN5T618) += rn5t618-regulator.o
+obj-$(CONFIG_REGULATOR_ROHM)	+= rohm-regulator.o
 obj-$(CONFIG_REGULATOR_RT5033)	+= rt5033-regulator.o
 obj-$(CONFIG_REGULATOR_S2MPA01) += s2mpa01.o
 obj-$(CONFIG_REGULATOR_S2MPS11) += s2mps11.o
diff --git a/drivers/regulator/bd718x7-regulator.c b/drivers/regulator/bd718x7-regulator.c
index 8f9b2d8eaf10..cf3872837abc 100644
--- a/drivers/regulator/bd718x7-regulator.c
+++ b/drivers/regulator/bd718x7-regulator.c
@@ -318,6 +318,7 @@ struct reg_init {
 };
 struct bd718xx_regulator_data {
 	struct regulator_desc desc;
+	const struct rohm_dvs_config dvs;
 	const struct reg_init init;
 	const struct reg_init *additional_inits;
 	int additional_init_amnt;
@@ -349,133 +350,15 @@ static const struct reg_init bd71837_ldo6_inits[] = {
 	},
 };
 
-#define NUM_DVS_BUCKS 4
-
-struct of_dvs_setting {
-	const char *prop;
-	unsigned int reg;
-};
-
-static int set_dvs_levels(const struct of_dvs_setting *dvs,
-			  struct device_node *np,
-			  const struct regulator_desc *desc,
-			  struct regmap *regmap)
-{
-	int ret, i;
-	unsigned int uv;
-
-	ret = of_property_read_u32(np, dvs->prop, &uv);
-	if (ret) {
-		if (ret != -EINVAL)
-			return ret;
-		return 0;
-	}
-
-	for (i = 0; i < desc->n_voltages; i++) {
-		ret = regulator_desc_list_voltage_linear_range(desc, i);
-		if (ret < 0)
-			continue;
-		if (ret == uv) {
-			i <<= ffs(desc->vsel_mask) - 1;
-			ret = regmap_update_bits(regmap, dvs->reg,
-						 DVS_BUCK_RUN_MASK, i);
-			break;
-		}
-	}
-	return ret;
-}
-
-static int buck4_set_hw_dvs_levels(struct device_node *np,
+static int buck_set_hw_dvs_levels(struct device_node *np,
 			    const struct regulator_desc *desc,
 			    struct regulator_config *cfg)
 {
-	int ret, i;
-	const struct of_dvs_setting dvs[] = {
-		{
-			.prop = "rohm,dvs-run-voltage",
-			.reg = BD71837_REG_BUCK4_VOLT_RUN,
-		},
-	};
+	struct bd718xx_regulator_data *data;
 
-	for (i = 0; i < ARRAY_SIZE(dvs); i++) {
-		ret = set_dvs_levels(&dvs[i], np, desc, cfg->regmap);
-		if (ret)
-			break;
-	}
-	return ret;
-}
-static int buck3_set_hw_dvs_levels(struct device_node *np,
-			    const struct regulator_desc *desc,
-			    struct regulator_config *cfg)
-{
-	int ret, i;
-	const struct of_dvs_setting dvs[] = {
-		{
-			.prop = "rohm,dvs-run-voltage",
-			.reg = BD71837_REG_BUCK3_VOLT_RUN,
-		},
-	};
+	data = container_of(desc, struct bd718xx_regulator_data, desc);
 
-	for (i = 0; i < ARRAY_SIZE(dvs); i++) {
-		ret = set_dvs_levels(&dvs[i], np, desc, cfg->regmap);
-		if (ret)
-			break;
-	}
-	return ret;
-}
-
-static int buck2_set_hw_dvs_levels(struct device_node *np,
-			    const struct regulator_desc *desc,
-			    struct regulator_config *cfg)
-{
-	int ret, i;
-	const struct of_dvs_setting dvs[] = {
-		{
-			.prop = "rohm,dvs-run-voltage",
-			.reg = BD718XX_REG_BUCK2_VOLT_RUN,
-		},
-		{
-			.prop = "rohm,dvs-idle-voltage",
-			.reg = BD718XX_REG_BUCK2_VOLT_IDLE,
-		},
-	};
-
-
-
-	for (i = 0; i < ARRAY_SIZE(dvs); i++) {
-		ret = set_dvs_levels(&dvs[i], np, desc, cfg->regmap);
-		if (ret)
-			break;
-	}
-	return ret;
-}
-
-static int buck1_set_hw_dvs_levels(struct device_node *np,
-			    const struct regulator_desc *desc,
-			    struct regulator_config *cfg)
-{
-	int ret, i;
-	const struct of_dvs_setting dvs[] = {
-		{
-			.prop = "rohm,dvs-run-voltage",
-			.reg = BD718XX_REG_BUCK1_VOLT_RUN,
-		},
-		{
-			.prop = "rohm,dvs-idle-voltage",
-			.reg = BD718XX_REG_BUCK1_VOLT_IDLE,
-		},
-		{
-			.prop = "rohm,dvs-suspend-voltage",
-			.reg = BD718XX_REG_BUCK1_VOLT_SUSP,
-		},
-	};
-
-	for (i = 0; i < ARRAY_SIZE(dvs); i++) {
-		ret = set_dvs_levels(&dvs[i], np, desc, cfg->regmap);
-		if (ret)
-			break;
-	}
-	return ret;
+	return rohm_regulator_set_dvs_levels(&data->dvs, np, desc, cfg->regmap);
 }
 
 static const struct bd718xx_regulator_data bd71847_regulators[] = {
@@ -496,7 +379,17 @@ static const struct bd718xx_regulator_data bd71847_regulators[] = {
 			.enable_reg = BD718XX_REG_BUCK1_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
 			.owner = THIS_MODULE,
-			.of_parse_cb = buck1_set_hw_dvs_levels,
+			.of_parse_cb = buck_set_hw_dvs_levels,
+		},
+		.dvs = {
+			.level_map = ROHM_DVS_LEVEL_RUN | ROHM_DVS_LEVEL_IDLE |
+				     ROHM_DVS_LEVEL_SUSPEND,
+			.run_reg = BD718XX_REG_BUCK1_VOLT_RUN,
+			.run_mask = DVS_BUCK_RUN_MASK,
+			.idle_reg = BD718XX_REG_BUCK1_VOLT_IDLE,
+			.idle_mask = DVS_BUCK_RUN_MASK,
+			.suspend_reg = BD718XX_REG_BUCK1_VOLT_SUSP,
+			.suspend_mask = DVS_BUCK_RUN_MASK,
 		},
 		.init = {
 			.reg = BD718XX_REG_BUCK1_CTRL,
@@ -520,7 +413,14 @@ static const struct bd718xx_regulator_data bd71847_regulators[] = {
 			.enable_reg = BD718XX_REG_BUCK2_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
 			.owner = THIS_MODULE,
-			.of_parse_cb = buck2_set_hw_dvs_levels,
+			.of_parse_cb = buck_set_hw_dvs_levels,
+		},
+		.dvs = {
+			.level_map = ROHM_DVS_LEVEL_RUN | ROHM_DVS_LEVEL_IDLE,
+			.run_reg = BD718XX_REG_BUCK2_VOLT_RUN,
+			.run_mask = DVS_BUCK_RUN_MASK,
+			.idle_reg = BD718XX_REG_BUCK2_VOLT_IDLE,
+			.idle_mask = DVS_BUCK_RUN_MASK,
 		},
 		.init = {
 			.reg = BD718XX_REG_BUCK2_CTRL,
@@ -792,7 +692,17 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.enable_reg = BD718XX_REG_BUCK1_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
 			.owner = THIS_MODULE,
-			.of_parse_cb = buck1_set_hw_dvs_levels,
+			.of_parse_cb = buck_set_hw_dvs_levels,
+		},
+		.dvs = {
+			.level_map = ROHM_DVS_LEVEL_RUN | ROHM_DVS_LEVEL_IDLE |
+				     ROHM_DVS_LEVEL_SUSPEND,
+			.run_reg = BD718XX_REG_BUCK1_VOLT_RUN,
+			.run_mask = DVS_BUCK_RUN_MASK,
+			.idle_reg = BD718XX_REG_BUCK1_VOLT_IDLE,
+			.idle_mask = DVS_BUCK_RUN_MASK,
+			.suspend_reg = BD718XX_REG_BUCK1_VOLT_SUSP,
+			.suspend_mask = DVS_BUCK_RUN_MASK,
 		},
 		.init = {
 			.reg = BD718XX_REG_BUCK1_CTRL,
@@ -816,7 +726,14 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.enable_reg = BD718XX_REG_BUCK2_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
 			.owner = THIS_MODULE,
-			.of_parse_cb = buck2_set_hw_dvs_levels,
+			.of_parse_cb = buck_set_hw_dvs_levels,
+		},
+		.dvs = {
+			.level_map = ROHM_DVS_LEVEL_RUN | ROHM_DVS_LEVEL_IDLE,
+			.run_reg = BD718XX_REG_BUCK2_VOLT_RUN,
+			.run_mask = DVS_BUCK_RUN_MASK,
+			.idle_reg = BD718XX_REG_BUCK2_VOLT_IDLE,
+			.idle_mask = DVS_BUCK_RUN_MASK,
 		},
 		.init = {
 			.reg = BD718XX_REG_BUCK2_CTRL,
@@ -840,7 +757,12 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.enable_reg = BD71837_REG_BUCK3_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
 			.owner = THIS_MODULE,
-			.of_parse_cb = buck3_set_hw_dvs_levels,
+			.of_parse_cb = buck_set_hw_dvs_levels,
+		},
+		.dvs = {
+			.level_map = ROHM_DVS_LEVEL_RUN,
+			.run_reg = BD71837_REG_BUCK3_VOLT_RUN,
+			.run_mask = DVS_BUCK_RUN_MASK,
 		},
 		.init = {
 			.reg = BD71837_REG_BUCK3_CTRL,
@@ -864,7 +786,12 @@ static const struct bd718xx_regulator_data bd71837_regulators[] = {
 			.enable_reg = BD71837_REG_BUCK4_CTRL,
 			.enable_mask = BD718XX_BUCK_EN,
 			.owner = THIS_MODULE,
-			.of_parse_cb = buck4_set_hw_dvs_levels,
+			.of_parse_cb = buck_set_hw_dvs_levels,
+		},
+		.dvs = {
+			.level_map = ROHM_DVS_LEVEL_RUN,
+			.run_reg = BD71837_REG_BUCK4_VOLT_RUN,
+			.run_mask = DVS_BUCK_RUN_MASK,
 		},
 		.init = {
 			.reg = BD71837_REG_BUCK4_CTRL,
@@ -1150,6 +1077,7 @@ static int bd718xx_probe(struct platform_device *pdev)
 	bool use_snvs;
 	const struct bd718xx_regulator_data *reg_data;
 	unsigned int num_reg_data;
+	enum rohm_chip_type chip = platform_get_device_id(pdev)->driver_data;
 
 	mfd = dev_get_drvdata(pdev->dev.parent);
 	if (!mfd) {
@@ -1158,7 +1086,7 @@ static int bd718xx_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	switch (mfd->chip.chip_type) {
+	switch (chip) {
 	case ROHM_CHIP_TYPE_BD71837:
 		reg_data = bd71837_regulators;
 		num_reg_data = ARRAY_SIZE(bd71837_regulators);
@@ -1275,11 +1203,19 @@ err:
 	return err;
 }
 
+static const struct platform_device_id bd718x7_pmic_id[] = {
+	{ "bd71837-pmic", ROHM_CHIP_TYPE_BD71837 },
+	{ "bd71847-pmic", ROHM_CHIP_TYPE_BD71847 },
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, bd718x7_pmic_id);
+
 static struct platform_driver bd718xx_regulator = {
 	.driver = {
 		.name = "bd718xx-pmic",
 	},
 	.probe = bd718xx_probe,
+	.id_table = bd718x7_pmic_id,
 };
 
 module_platform_driver(bd718xx_regulator);
diff --git a/drivers/regulator/rohm-regulator.c b/drivers/regulator/rohm-regulator.c
new file mode 100644
index 000000000000..399002383b28
--- /dev/null
+++ b/drivers/regulator/rohm-regulator.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2020 ROHM Semiconductors
+
+#include <linux/errno.h>
+#include <linux/mfd/rohm-generic.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+
+static int set_dvs_level(const struct regulator_desc *desc,
+			 struct device_node *np, struct regmap *regmap,
+			 char *prop, unsigned int reg, unsigned int mask,
+			 unsigned int omask, unsigned int oreg)
+{
+	int ret, i;
+	uint32_t uv;
+
+	ret = of_property_read_u32(np, prop, &uv);
+	if (ret) {
+		if (ret != -EINVAL)
+			return ret;
+		return 0;
+	}
+
+	if (uv == 0) {
+		if (omask)
+			return regmap_update_bits(regmap, oreg, omask, 0);
+	}
+	for (i = 0; i < desc->n_voltages; i++) {
+		ret = regulator_desc_list_voltage_linear_range(desc, i);
+		if (ret < 0)
+			continue;
+		if (ret == uv) {
+			i <<= ffs(desc->vsel_mask) - 1;
+			ret = regmap_update_bits(regmap, reg, mask, i);
+			if (omask && !ret)
+				ret = regmap_update_bits(regmap, oreg, omask,
+							 omask);
+			break;
+		}
+	}
+	return ret;
+}
+
+int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs,
+			  struct device_node *np,
+			  const struct regulator_desc *desc,
+			  struct regmap *regmap)
+{
+	int i, ret = 0;
+	char *prop;
+	unsigned int reg, mask, omask, oreg = desc->enable_reg;
+
+	for (i = 0; i < ROHM_DVS_LEVEL_MAX && !ret; i++) {
+		if (dvs->level_map & (1 << i)) {
+			switch (i + 1) {
+			case ROHM_DVS_LEVEL_RUN:
+				prop = "rohm,dvs-run-voltage";
+				reg = dvs->run_reg;
+				mask = dvs->run_mask;
+				omask = dvs->run_on_mask;
+				break;
+			case ROHM_DVS_LEVEL_IDLE:
+				prop = "rohm,dvs-idle-voltage";
+				reg = dvs->idle_reg;
+				mask = dvs->idle_mask;
+				omask = dvs->idle_on_mask;
+				break;
+			case ROHM_DVS_LEVEL_SUSPEND:
+				prop = "rohm,dvs-suspend-voltage";
+				reg = dvs->suspend_reg;
+				mask = dvs->suspend_mask;
+				omask = dvs->suspend_on_mask;
+				break;
+			case ROHM_DVS_LEVEL_LPSR:
+				prop = "rohm,dvs-lpsr-voltage";
+				reg = dvs->lpsr_reg;
+				mask = dvs->lpsr_mask;
+				omask = dvs->lpsr_on_mask;
+				break;
+			default:
+				return -EINVAL;
+			}
+			ret = set_dvs_level(desc, np, regmap, prop, reg, mask,
+					    omask, oreg);
+		}
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rohm_regulator_set_dvs_levels);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
+MODULE_DESCRIPTION("Generic helpers for ROHM PMIC regulator drivers");
diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig
index 94afdde4bc9f..de3862c15fcc 100644
--- a/drivers/remoteproc/Kconfig
+++ b/drivers/remoteproc/Kconfig
@@ -23,6 +23,16 @@ config IMX_REMOTEPROC
 
 	  It's safe to say N here.
 
+config MTK_SCP
+	tristate "Mediatek SCP support"
+	depends on ARCH_MEDIATEK
+	select RPMSG_MTK_SCP
+	help
+	  Say y here to support Mediatek's System Companion Processor (SCP) via
+	  the remote processor framework.
+
+	  It's safe to say N here.
+
 config OMAP_REMOTEPROC
 	tristate "OMAP remoteproc support"
 	depends on ARCH_OMAP4 || SOC_OMAP5
diff --git a/drivers/remoteproc/Makefile b/drivers/remoteproc/Makefile
index 00f09e658cb3..e30a1b15fbac 100644
--- a/drivers/remoteproc/Makefile
+++ b/drivers/remoteproc/Makefile
@@ -10,6 +10,7 @@ remoteproc-y				+= remoteproc_sysfs.o
 remoteproc-y				+= remoteproc_virtio.o
 remoteproc-y				+= remoteproc_elf_loader.o
 obj-$(CONFIG_IMX_REMOTEPROC)		+= imx_rproc.o
+obj-$(CONFIG_MTK_SCP)			+= mtk_scp.o mtk_scp_ipi.o
 obj-$(CONFIG_OMAP_REMOTEPROC)		+= omap_remoteproc.o
 obj-$(CONFIG_WKUP_M3_RPROC)		+= wkup_m3_rproc.o
 obj-$(CONFIG_DA8XX_REMOTEPROC)		+= da8xx_remoteproc.o
diff --git a/drivers/remoteproc/mtk_common.h b/drivers/remoteproc/mtk_common.h
new file mode 100644
index 000000000000..deb20096146a
--- /dev/null
+++ b/drivers/remoteproc/mtk_common.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019 MediaTek Inc.
+ */
+
+#ifndef __RPROC_MTK_COMMON_H
+#define __RPROC_MTK_COMMON_H
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+#include <linux/remoteproc/mtk_scp.h>
+
+#define MT8183_SW_RSTN			0x0
+#define MT8183_SW_RSTN_BIT		BIT(0)
+#define MT8183_SCP_TO_HOST		0x1C
+#define MT8183_SCP_IPC_INT_BIT		BIT(0)
+#define MT8183_SCP_WDT_INT_BIT		BIT(8)
+#define MT8183_HOST_TO_SCP		0x28
+#define MT8183_HOST_IPC_INT_BIT		BIT(0)
+#define MT8183_WDT_CFG			0x84
+#define MT8183_SCP_CLK_SW_SEL		0x4000
+#define MT8183_SCP_CLK_DIV_SEL		0x4024
+#define MT8183_SCP_SRAM_PDN		0x402C
+#define MT8183_SCP_L1_SRAM_PD		0x4080
+#define MT8183_SCP_TCM_TAIL_SRAM_PD	0x4094
+
+#define MT8183_SCP_CACHE_SEL(x)		(0x14000 + (x) * 0x3000)
+#define MT8183_SCP_CACHE_CON		MT8183_SCP_CACHE_SEL(0)
+#define MT8183_SCP_DCACHE_CON		MT8183_SCP_CACHE_SEL(1)
+#define MT8183_SCP_CACHESIZE_8KB	BIT(8)
+#define MT8183_SCP_CACHE_CON_WAYEN	BIT(10)
+
+#define SCP_FW_VER_LEN			32
+#define SCP_SHARE_BUFFER_SIZE		288
+
+struct scp_run {
+	u32 signaled;
+	s8 fw_ver[SCP_FW_VER_LEN];
+	u32 dec_capability;
+	u32 enc_capability;
+	wait_queue_head_t wq;
+};
+
+struct scp_ipi_desc {
+	/* For protecting handler. */
+	struct mutex lock;
+	scp_ipi_handler_t handler;
+	void *priv;
+};
+
+struct mtk_scp {
+	struct device *dev;
+	struct rproc *rproc;
+	struct clk *clk;
+	void __iomem *reg_base;
+	void __iomem *sram_base;
+	size_t sram_size;
+
+	struct mtk_share_obj __iomem *recv_buf;
+	struct mtk_share_obj __iomem *send_buf;
+	struct scp_run run;
+	/* To prevent multiple ipi_send run concurrently. */
+	struct mutex send_lock;
+	struct scp_ipi_desc ipi_desc[SCP_IPI_MAX];
+	bool ipi_id_ack[SCP_IPI_MAX];
+	wait_queue_head_t ack_wq;
+
+	void __iomem *cpu_addr;
+	phys_addr_t phys_addr;
+	size_t dram_size;
+
+	struct rproc_subdev *rpmsg_subdev;
+};
+
+/**
+ * struct mtk_share_obj - SRAM buffer shared with AP and SCP
+ *
+ * @id:		IPI id
+ * @len:	share buffer length
+ * @share_buf:	share buffer data
+ */
+struct mtk_share_obj {
+	u32 id;
+	u32 len;
+	u8 share_buf[SCP_SHARE_BUFFER_SIZE];
+};
+
+void scp_memcpy_aligned(void __iomem *dst, const void *src, unsigned int len);
+void scp_ipi_lock(struct mtk_scp *scp, u32 id);
+void scp_ipi_unlock(struct mtk_scp *scp, u32 id);
+
+#endif
diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
new file mode 100644
index 000000000000..7ccdf64ff3ea
--- /dev/null
+++ b/drivers/remoteproc/mtk_scp.c
@@ -0,0 +1,663 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2019 MediaTek Inc.
+
+#include <asm/barrier.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+#include <linux/remoteproc/mtk_scp.h>
+#include <linux/rpmsg/mtk_rpmsg.h>
+
+#include "mtk_common.h"
+#include "remoteproc_internal.h"
+
+#define MAX_CODE_SIZE 0x500000
+#define SCP_FW_END 0x7C000
+
+/**
+ * scp_get() - get a reference to SCP.
+ *
+ * @pdev:	the platform device of the module requesting SCP platform
+ *		device for using SCP API.
+ *
+ * Return: Return NULL if failed.  otherwise reference to SCP.
+ **/
+struct mtk_scp *scp_get(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *scp_node;
+	struct platform_device *scp_pdev;
+
+	scp_node = of_parse_phandle(dev->of_node, "mediatek,scp", 0);
+	if (!scp_node) {
+		dev_err(dev, "can't get SCP node\n");
+		return NULL;
+	}
+
+	scp_pdev = of_find_device_by_node(scp_node);
+	of_node_put(scp_node);
+
+	if (WARN_ON(!scp_pdev)) {
+		dev_err(dev, "SCP pdev failed\n");
+		return NULL;
+	}
+
+	return platform_get_drvdata(scp_pdev);
+}
+EXPORT_SYMBOL_GPL(scp_get);
+
+/**
+ * scp_put() - "free" the SCP
+ *
+ * @scp:	mtk_scp structure from scp_get().
+ **/
+void scp_put(struct mtk_scp *scp)
+{
+	put_device(scp->dev);
+}
+EXPORT_SYMBOL_GPL(scp_put);
+
+static void scp_wdt_handler(struct mtk_scp *scp, u32 scp_to_host)
+{
+	dev_err(scp->dev, "SCP watchdog timeout! 0x%x", scp_to_host);
+	rproc_report_crash(scp->rproc, RPROC_WATCHDOG);
+}
+
+static void scp_init_ipi_handler(void *data, unsigned int len, void *priv)
+{
+	struct mtk_scp *scp = (struct mtk_scp *)priv;
+	struct scp_run *run = (struct scp_run *)data;
+
+	scp->run.signaled = run->signaled;
+	strscpy(scp->run.fw_ver, run->fw_ver, SCP_FW_VER_LEN);
+	scp->run.dec_capability = run->dec_capability;
+	scp->run.enc_capability = run->enc_capability;
+	wake_up_interruptible(&scp->run.wq);
+}
+
+static void scp_ipi_handler(struct mtk_scp *scp)
+{
+	struct mtk_share_obj __iomem *rcv_obj = scp->recv_buf;
+	struct scp_ipi_desc *ipi_desc = scp->ipi_desc;
+	u8 tmp_data[SCP_SHARE_BUFFER_SIZE];
+	scp_ipi_handler_t handler;
+	u32 id = readl(&rcv_obj->id);
+	u32 len = readl(&rcv_obj->len);
+
+	if (len > SCP_SHARE_BUFFER_SIZE) {
+		dev_err(scp->dev, "ipi message too long (len %d, max %d)", len,
+			SCP_SHARE_BUFFER_SIZE);
+		return;
+	}
+	if (id >= SCP_IPI_MAX) {
+		dev_err(scp->dev, "No such ipi id = %d\n", id);
+		return;
+	}
+
+	scp_ipi_lock(scp, id);
+	handler = ipi_desc[id].handler;
+	if (!handler) {
+		dev_err(scp->dev, "No such ipi id = %d\n", id);
+		scp_ipi_unlock(scp, id);
+		return;
+	}
+
+	memcpy_fromio(tmp_data, &rcv_obj->share_buf, len);
+	handler(tmp_data, len, ipi_desc[id].priv);
+	scp_ipi_unlock(scp, id);
+
+	scp->ipi_id_ack[id] = true;
+	wake_up(&scp->ack_wq);
+}
+
+static int scp_ipi_init(struct mtk_scp *scp)
+{
+	size_t send_offset = SCP_FW_END - sizeof(struct mtk_share_obj);
+	size_t recv_offset = send_offset - sizeof(struct mtk_share_obj);
+
+	/* Disable SCP to host interrupt */
+	writel(MT8183_SCP_IPC_INT_BIT, scp->reg_base + MT8183_SCP_TO_HOST);
+
+	/* shared buffer initialization */
+	scp->recv_buf =
+		(struct mtk_share_obj __iomem *)(scp->sram_base + recv_offset);
+	scp->send_buf =
+		(struct mtk_share_obj __iomem *)(scp->sram_base + send_offset);
+	memset_io(scp->recv_buf, 0, sizeof(scp->recv_buf));
+	memset_io(scp->send_buf, 0, sizeof(scp->send_buf));
+
+	return 0;
+}
+
+static void scp_reset_assert(const struct mtk_scp *scp)
+{
+	u32 val;
+
+	val = readl(scp->reg_base + MT8183_SW_RSTN);
+	val &= ~MT8183_SW_RSTN_BIT;
+	writel(val, scp->reg_base + MT8183_SW_RSTN);
+}
+
+static void scp_reset_deassert(const struct mtk_scp *scp)
+{
+	u32 val;
+
+	val = readl(scp->reg_base + MT8183_SW_RSTN);
+	val |= MT8183_SW_RSTN_BIT;
+	writel(val, scp->reg_base + MT8183_SW_RSTN);
+}
+
+static irqreturn_t scp_irq_handler(int irq, void *priv)
+{
+	struct mtk_scp *scp = priv;
+	u32 scp_to_host;
+	int ret;
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(scp->dev, "failed to enable clocks\n");
+		return IRQ_NONE;
+	}
+
+	scp_to_host = readl(scp->reg_base + MT8183_SCP_TO_HOST);
+	if (scp_to_host & MT8183_SCP_IPC_INT_BIT)
+		scp_ipi_handler(scp);
+	else
+		scp_wdt_handler(scp, scp_to_host);
+
+	/* SCP won't send another interrupt until we set SCP_TO_HOST to 0. */
+	writel(MT8183_SCP_IPC_INT_BIT | MT8183_SCP_WDT_INT_BIT,
+	       scp->reg_base + MT8183_SCP_TO_HOST);
+	clk_disable_unprepare(scp->clk);
+
+	return IRQ_HANDLED;
+}
+
+static int scp_elf_load_segments(struct rproc *rproc, const struct firmware *fw)
+{
+	struct device *dev = &rproc->dev;
+	struct elf32_hdr *ehdr;
+	struct elf32_phdr *phdr;
+	int i, ret = 0;
+	const u8 *elf_data = fw->data;
+
+	ehdr = (struct elf32_hdr *)elf_data;
+	phdr = (struct elf32_phdr *)(elf_data + ehdr->e_phoff);
+
+	/* go through the available ELF segments */
+	for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
+		u32 da = phdr->p_paddr;
+		u32 memsz = phdr->p_memsz;
+		u32 filesz = phdr->p_filesz;
+		u32 offset = phdr->p_offset;
+		void __iomem *ptr;
+
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		dev_dbg(dev, "phdr: type %d da 0x%x memsz 0x%x filesz 0x%x\n",
+			phdr->p_type, da, memsz, filesz);
+
+		if (filesz > memsz) {
+			dev_err(dev, "bad phdr filesz 0x%x memsz 0x%x\n",
+				filesz, memsz);
+			ret = -EINVAL;
+			break;
+		}
+
+		if (offset + filesz > fw->size) {
+			dev_err(dev, "truncated fw: need 0x%x avail 0x%zx\n",
+				offset + filesz, fw->size);
+			ret = -EINVAL;
+			break;
+		}
+
+		/* grab the kernel address for this device address */
+		ptr = (void __iomem *)rproc_da_to_va(rproc, da, memsz);
+		if (!ptr) {
+			dev_err(dev, "bad phdr da 0x%x mem 0x%x\n", da, memsz);
+			ret = -EINVAL;
+			break;
+		}
+
+		/* put the segment where the remote processor expects it */
+		if (phdr->p_filesz)
+			scp_memcpy_aligned(ptr, elf_data + phdr->p_offset,
+					   filesz);
+	}
+
+	return ret;
+}
+
+static int scp_load(struct rproc *rproc, const struct firmware *fw)
+{
+	const struct mtk_scp *scp = rproc->priv;
+	struct device *dev = scp->dev;
+	int ret;
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clocks\n");
+		return ret;
+	}
+
+	/* Hold SCP in reset while loading FW. */
+	scp_reset_assert(scp);
+
+	/* Reset clocks before loading FW */
+	writel(0x0, scp->reg_base + MT8183_SCP_CLK_SW_SEL);
+	writel(0x0, scp->reg_base + MT8183_SCP_CLK_DIV_SEL);
+
+	/* Initialize TCM before loading FW. */
+	writel(0x0, scp->reg_base + MT8183_SCP_L1_SRAM_PD);
+	writel(0x0, scp->reg_base + MT8183_SCP_TCM_TAIL_SRAM_PD);
+
+	/* Turn on the power of SCP's SRAM before using it. */
+	writel(0x0, scp->reg_base + MT8183_SCP_SRAM_PDN);
+
+	/*
+	 * Set I-cache and D-cache size before loading SCP FW.
+	 * SCP SRAM logical address may change when cache size setting differs.
+	 */
+	writel(MT8183_SCP_CACHE_CON_WAYEN | MT8183_SCP_CACHESIZE_8KB,
+	       scp->reg_base + MT8183_SCP_CACHE_CON);
+	writel(MT8183_SCP_CACHESIZE_8KB, scp->reg_base + MT8183_SCP_DCACHE_CON);
+
+	ret = scp_elf_load_segments(rproc, fw);
+	clk_disable_unprepare(scp->clk);
+
+	return ret;
+}
+
+static int scp_start(struct rproc *rproc)
+{
+	struct mtk_scp *scp = (struct mtk_scp *)rproc->priv;
+	struct device *dev = scp->dev;
+	struct scp_run *run = &scp->run;
+	int ret;
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clocks\n");
+		return ret;
+	}
+
+	run->signaled = false;
+
+	scp_reset_deassert(scp);
+
+	ret = wait_event_interruptible_timeout(
+					run->wq,
+					run->signaled,
+					msecs_to_jiffies(2000));
+
+	if (ret == 0) {
+		dev_err(dev, "wait SCP initialization timeout!\n");
+		ret = -ETIME;
+		goto stop;
+	}
+	if (ret == -ERESTARTSYS) {
+		dev_err(dev, "wait SCP interrupted by a signal!\n");
+		goto stop;
+	}
+	clk_disable_unprepare(scp->clk);
+	dev_info(dev, "SCP is ready. FW version %s\n", run->fw_ver);
+
+	return 0;
+
+stop:
+	scp_reset_assert(scp);
+	clk_disable_unprepare(scp->clk);
+	return ret;
+}
+
+static void *scp_da_to_va(struct rproc *rproc, u64 da, int len)
+{
+	struct mtk_scp *scp = (struct mtk_scp *)rproc->priv;
+	int offset;
+
+	if (da < scp->sram_size) {
+		offset = da;
+		if (offset >= 0 && (offset + len) < scp->sram_size)
+			return (void __force *)scp->sram_base + offset;
+	} else {
+		offset = da - scp->phys_addr;
+		if (offset >= 0 && (offset + len) < scp->dram_size)
+			return (void __force *)scp->cpu_addr + offset;
+	}
+
+	return NULL;
+}
+
+static int scp_stop(struct rproc *rproc)
+{
+	struct mtk_scp *scp = (struct mtk_scp *)rproc->priv;
+	int ret;
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(scp->dev, "failed to enable clocks\n");
+		return ret;
+	}
+
+	scp_reset_assert(scp);
+	/* Disable SCP watchdog */
+	writel(0, scp->reg_base + MT8183_WDT_CFG);
+	clk_disable_unprepare(scp->clk);
+
+	return 0;
+}
+
+static const struct rproc_ops scp_ops = {
+	.start		= scp_start,
+	.stop		= scp_stop,
+	.load		= scp_load,
+	.da_to_va	= scp_da_to_va,
+};
+
+/**
+ * scp_get_device() - get device struct of SCP
+ *
+ * @scp:	mtk_scp structure
+ **/
+struct device *scp_get_device(struct mtk_scp *scp)
+{
+	return scp->dev;
+}
+EXPORT_SYMBOL_GPL(scp_get_device);
+
+/**
+ * scp_get_rproc() - get rproc struct of SCP
+ *
+ * @scp:	mtk_scp structure
+ **/
+struct rproc *scp_get_rproc(struct mtk_scp *scp)
+{
+	return scp->rproc;
+}
+EXPORT_SYMBOL_GPL(scp_get_rproc);
+
+/**
+ * scp_get_vdec_hw_capa() - get video decoder hardware capability
+ *
+ * @scp:	mtk_scp structure
+ *
+ * Return: video decoder hardware capability
+ **/
+unsigned int scp_get_vdec_hw_capa(struct mtk_scp *scp)
+{
+	return scp->run.dec_capability;
+}
+EXPORT_SYMBOL_GPL(scp_get_vdec_hw_capa);
+
+/**
+ * scp_get_venc_hw_capa() - get video encoder hardware capability
+ *
+ * @scp:	mtk_scp structure
+ *
+ * Return: video encoder hardware capability
+ **/
+unsigned int scp_get_venc_hw_capa(struct mtk_scp *scp)
+{
+	return scp->run.enc_capability;
+}
+EXPORT_SYMBOL_GPL(scp_get_venc_hw_capa);
+
+/**
+ * scp_mapping_dm_addr() - Mapping SRAM/DRAM to kernel virtual address
+ *
+ * @scp:	mtk_scp structure
+ * @mem_addr:	SCP views memory address
+ *
+ * Mapping the SCP's SRAM address /
+ * DMEM (Data Extended Memory) memory address /
+ * Working buffer memory address to
+ * kernel virtual address.
+ *
+ * Return: Return ERR_PTR(-EINVAL) if mapping failed,
+ * otherwise the mapped kernel virtual address
+ **/
+void *scp_mapping_dm_addr(struct mtk_scp *scp, u32 mem_addr)
+{
+	void *ptr;
+
+	ptr = scp_da_to_va(scp->rproc, mem_addr, 0);
+	if (!ptr)
+		return ERR_PTR(-EINVAL);
+
+	return ptr;
+}
+EXPORT_SYMBOL_GPL(scp_mapping_dm_addr);
+
+static int scp_map_memory_region(struct mtk_scp *scp)
+{
+	int ret;
+
+	ret = of_reserved_mem_device_init(scp->dev);
+	if (ret) {
+		dev_err(scp->dev, "failed to assign memory-region: %d\n", ret);
+		return -ENOMEM;
+	}
+
+	/* Reserved SCP code size */
+	scp->dram_size = MAX_CODE_SIZE;
+	scp->cpu_addr = dma_alloc_coherent(scp->dev, scp->dram_size,
+					   &scp->phys_addr, GFP_KERNEL);
+	if (!scp->cpu_addr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void scp_unmap_memory_region(struct mtk_scp *scp)
+{
+	dma_free_coherent(scp->dev, scp->dram_size, scp->cpu_addr,
+			  scp->phys_addr);
+	of_reserved_mem_device_release(scp->dev);
+}
+
+static int scp_register_ipi(struct platform_device *pdev, u32 id,
+			    ipi_handler_t handler, void *priv)
+{
+	struct mtk_scp *scp = platform_get_drvdata(pdev);
+
+	return scp_ipi_register(scp, id, handler, priv);
+}
+
+static void scp_unregister_ipi(struct platform_device *pdev, u32 id)
+{
+	struct mtk_scp *scp = platform_get_drvdata(pdev);
+
+	scp_ipi_unregister(scp, id);
+}
+
+static int scp_send_ipi(struct platform_device *pdev, u32 id, void *buf,
+			unsigned int len, unsigned int wait)
+{
+	struct mtk_scp *scp = platform_get_drvdata(pdev);
+
+	return scp_ipi_send(scp, id, buf, len, wait);
+}
+
+static struct mtk_rpmsg_info mtk_scp_rpmsg_info = {
+	.send_ipi = scp_send_ipi,
+	.register_ipi = scp_register_ipi,
+	.unregister_ipi = scp_unregister_ipi,
+	.ns_ipi_id = SCP_IPI_NS_SERVICE,
+};
+
+static void scp_add_rpmsg_subdev(struct mtk_scp *scp)
+{
+	scp->rpmsg_subdev =
+		mtk_rpmsg_create_rproc_subdev(to_platform_device(scp->dev),
+					      &mtk_scp_rpmsg_info);
+	if (scp->rpmsg_subdev)
+		rproc_add_subdev(scp->rproc, scp->rpmsg_subdev);
+}
+
+static void scp_remove_rpmsg_subdev(struct mtk_scp *scp)
+{
+	if (scp->rpmsg_subdev) {
+		rproc_remove_subdev(scp->rproc, scp->rpmsg_subdev);
+		mtk_rpmsg_destroy_rproc_subdev(scp->rpmsg_subdev);
+		scp->rpmsg_subdev = NULL;
+	}
+}
+
+static int scp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct mtk_scp *scp;
+	struct rproc *rproc;
+	struct resource *res;
+	char *fw_name = "scp.img";
+	int ret, i;
+
+	rproc = rproc_alloc(dev,
+			    np->name,
+			    &scp_ops,
+			    fw_name,
+			    sizeof(*scp));
+	if (!rproc) {
+		dev_err(dev, "unable to allocate remoteproc\n");
+		return -ENOMEM;
+	}
+
+	scp = (struct mtk_scp *)rproc->priv;
+	scp->rproc = rproc;
+	scp->dev = dev;
+	platform_set_drvdata(pdev, scp);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sram");
+	scp->sram_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR((__force void *)scp->sram_base)) {
+		dev_err(dev, "Failed to parse and map sram memory\n");
+		ret = PTR_ERR((__force void *)scp->sram_base);
+		goto free_rproc;
+	}
+	scp->sram_size = resource_size(res);
+
+	mutex_init(&scp->send_lock);
+	for (i = 0; i < SCP_IPI_MAX; i++)
+		mutex_init(&scp->ipi_desc[i].lock);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg");
+	scp->reg_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR((__force void *)scp->reg_base)) {
+		dev_err(dev, "Failed to parse and map cfg memory\n");
+		ret = PTR_ERR((__force void *)scp->reg_base);
+		goto destroy_mutex;
+	}
+
+	ret = scp_map_memory_region(scp);
+	if (ret)
+		goto destroy_mutex;
+
+	scp->clk = devm_clk_get(dev, "main");
+	if (IS_ERR(scp->clk)) {
+		dev_err(dev, "Failed to get clock\n");
+		ret = PTR_ERR(scp->clk);
+		goto release_dev_mem;
+	}
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(dev, "failed to enable clocks\n");
+		goto release_dev_mem;
+	}
+
+	ret = scp_ipi_init(scp);
+	clk_disable_unprepare(scp->clk);
+	if (ret) {
+		dev_err(dev, "Failed to init ipi\n");
+		goto release_dev_mem;
+	}
+
+	/* register SCP initialization IPI */
+	ret = scp_ipi_register(scp, SCP_IPI_INIT, scp_init_ipi_handler, scp);
+	if (ret) {
+		dev_err(dev, "Failed to register IPI_SCP_INIT\n");
+		goto release_dev_mem;
+	}
+
+	init_waitqueue_head(&scp->run.wq);
+	init_waitqueue_head(&scp->ack_wq);
+
+	scp_add_rpmsg_subdev(scp);
+
+	ret = devm_request_threaded_irq(dev, platform_get_irq(pdev, 0), NULL,
+					scp_irq_handler, IRQF_ONESHOT,
+					pdev->name, scp);
+
+	if (ret) {
+		dev_err(dev, "failed to request irq\n");
+		goto remove_subdev;
+	}
+
+	ret = rproc_add(rproc);
+	if (ret)
+		goto remove_subdev;
+
+	return 0;
+
+remove_subdev:
+	scp_remove_rpmsg_subdev(scp);
+	scp_ipi_unregister(scp, SCP_IPI_INIT);
+release_dev_mem:
+	scp_unmap_memory_region(scp);
+destroy_mutex:
+	for (i = 0; i < SCP_IPI_MAX; i++)
+		mutex_destroy(&scp->ipi_desc[i].lock);
+	mutex_destroy(&scp->send_lock);
+free_rproc:
+	rproc_free(rproc);
+
+	return ret;
+}
+
+static int scp_remove(struct platform_device *pdev)
+{
+	struct mtk_scp *scp = platform_get_drvdata(pdev);
+	int i;
+
+	rproc_del(scp->rproc);
+	scp_remove_rpmsg_subdev(scp);
+	scp_ipi_unregister(scp, SCP_IPI_INIT);
+	scp_unmap_memory_region(scp);
+	for (i = 0; i < SCP_IPI_MAX; i++)
+		mutex_destroy(&scp->ipi_desc[i].lock);
+	mutex_destroy(&scp->send_lock);
+	rproc_free(scp->rproc);
+
+	return 0;
+}
+
+static const struct of_device_id mtk_scp_of_match[] = {
+	{ .compatible = "mediatek,mt8183-scp"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtk_scp_of_match);
+
+static struct platform_driver mtk_scp_driver = {
+	.probe = scp_probe,
+	.remove = scp_remove,
+	.driver = {
+		.name = "mtk-scp",
+		.of_match_table = of_match_ptr(mtk_scp_of_match),
+	},
+};
+
+module_platform_driver(mtk_scp_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MediaTek SCP control driver");
diff --git a/drivers/remoteproc/mtk_scp_ipi.c b/drivers/remoteproc/mtk_scp_ipi.c
new file mode 100644
index 000000000000..3d3d87210ef2
--- /dev/null
+++ b/drivers/remoteproc/mtk_scp_ipi.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2019 MediaTek Inc.
+
+#include <asm/barrier.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc/mtk_scp.h>
+
+#include "mtk_common.h"
+
+/**
+ * scp_ipi_register() - register an ipi function
+ *
+ * @scp:	mtk_scp structure
+ * @id:		IPI ID
+ * @handler:	IPI handler
+ * @priv:	private data for IPI handler
+ *
+ * Register an ipi function to receive ipi interrupt from SCP.
+ *
+ * Returns 0 if ipi registers successfully, -error on error.
+ */
+int scp_ipi_register(struct mtk_scp *scp,
+		     u32 id,
+		     scp_ipi_handler_t handler,
+		     void *priv)
+{
+	if (!scp) {
+		dev_err(scp->dev, "scp device is not ready\n");
+		return -EPROBE_DEFER;
+	}
+
+	if (WARN_ON(id >= SCP_IPI_MAX) || WARN_ON(handler == NULL))
+		return -EINVAL;
+
+	scp_ipi_lock(scp, id);
+	scp->ipi_desc[id].handler = handler;
+	scp->ipi_desc[id].priv = priv;
+	scp_ipi_unlock(scp, id);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(scp_ipi_register);
+
+/**
+ * scp_ipi_unregister() - unregister an ipi function
+ *
+ * @scp:	mtk_scp structure
+ * @id:		IPI ID
+ *
+ * Unregister an ipi function to receive ipi interrupt from SCP.
+ */
+void scp_ipi_unregister(struct mtk_scp *scp, u32 id)
+{
+	if (!scp)
+		return;
+
+	if (WARN_ON(id >= SCP_IPI_MAX))
+		return;
+
+	scp_ipi_lock(scp, id);
+	scp->ipi_desc[id].handler = NULL;
+	scp->ipi_desc[id].priv = NULL;
+	scp_ipi_unlock(scp, id);
+}
+EXPORT_SYMBOL_GPL(scp_ipi_unregister);
+
+/*
+ * scp_memcpy_aligned() - Copy src to dst, where dst is in SCP SRAM region.
+ *
+ * @dst:	Pointer to the destination buffer, should be in SCP SRAM region.
+ * @src:	Pointer to the source buffer.
+ * @len:	Length of the source buffer to be copied.
+ *
+ * Since AP access of SCP SRAM don't support byte write, this always write a
+ * full word at a time, and may cause some extra bytes to be written at the
+ * beginning & ending of dst.
+ */
+void scp_memcpy_aligned(void __iomem *dst, const void *src, unsigned int len)
+{
+	void __iomem *ptr;
+	u32 val;
+	unsigned int i = 0, remain;
+
+	if (!IS_ALIGNED((unsigned long)dst, 4)) {
+		ptr = (void __iomem *)ALIGN_DOWN((unsigned long)dst, 4);
+		i = 4 - (dst - ptr);
+		val = readl_relaxed(ptr);
+		memcpy((u8 *)&val + (4 - i), src, i);
+		writel_relaxed(val, ptr);
+	}
+
+	__iowrite32_copy(dst + i, src + i, (len - i) / 4);
+	remain = (len - i) % 4;
+
+	if (remain > 0) {
+		val = readl_relaxed(dst + len - remain);
+		memcpy(&val, src + len - remain, remain);
+		writel_relaxed(val, dst + len - remain);
+	}
+}
+EXPORT_SYMBOL_GPL(scp_memcpy_aligned);
+
+/**
+ * scp_ipi_lock() - Lock before operations of an IPI ID
+ *
+ * @scp:	mtk_scp structure
+ * @id:		IPI ID
+ *
+ * Note: This should not be used by drivers other than mtk_scp.
+ */
+void scp_ipi_lock(struct mtk_scp *scp, u32 id)
+{
+	if (WARN_ON(id >= SCP_IPI_MAX))
+		return;
+	mutex_lock(&scp->ipi_desc[id].lock);
+}
+EXPORT_SYMBOL_GPL(scp_ipi_lock);
+
+/**
+ * scp_ipi_lock() - Unlock after operations of an IPI ID
+ *
+ * @scp:	mtk_scp structure
+ * @id:		IPI ID
+ *
+ * Note: This should not be used by drivers other than mtk_scp.
+ */
+void scp_ipi_unlock(struct mtk_scp *scp, u32 id)
+{
+	if (WARN_ON(id >= SCP_IPI_MAX))
+		return;
+	mutex_unlock(&scp->ipi_desc[id].lock);
+}
+EXPORT_SYMBOL_GPL(scp_ipi_unlock);
+
+/**
+ * scp_ipi_send() - send data from AP to scp.
+ *
+ * @scp:	mtk_scp structure
+ * @id:		IPI ID
+ * @buf:	the data buffer
+ * @len:	the data buffer length
+ * @wait:	number of msecs to wait for ack. 0 to skip waiting.
+ *
+ * This function is thread-safe. When this function returns,
+ * SCP has received the data and starts the processing.
+ * When the processing completes, IPI handler registered
+ * by scp_ipi_register will be called in interrupt context.
+ *
+ * Returns 0 if sending data successfully, -error on error.
+ **/
+int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
+		 unsigned int wait)
+{
+	struct mtk_share_obj __iomem *send_obj = scp->send_buf;
+	unsigned long timeout;
+	int ret;
+
+	if (WARN_ON(id <= SCP_IPI_INIT) || WARN_ON(id >= SCP_IPI_MAX) ||
+	    WARN_ON(id == SCP_IPI_NS_SERVICE) ||
+	    WARN_ON(len > sizeof(send_obj->share_buf)) || WARN_ON(!buf))
+		return -EINVAL;
+
+	mutex_lock(&scp->send_lock);
+
+	ret = clk_prepare_enable(scp->clk);
+	if (ret) {
+		dev_err(scp->dev, "failed to enable clock\n");
+		goto unlock_mutex;
+	}
+
+	 /* Wait until SCP receives the last command */
+	timeout = jiffies + msecs_to_jiffies(2000);
+	do {
+		if (time_after(jiffies, timeout)) {
+			dev_err(scp->dev, "%s: IPI timeout!\n", __func__);
+			ret = -ETIMEDOUT;
+			goto clock_disable;
+		}
+	} while (readl(scp->reg_base + MT8183_HOST_TO_SCP));
+
+	scp_memcpy_aligned(send_obj->share_buf, buf, len);
+
+	writel(len, &send_obj->len);
+	writel(id, &send_obj->id);
+
+	scp->ipi_id_ack[id] = false;
+	/* send the command to SCP */
+	writel(MT8183_HOST_IPC_INT_BIT, scp->reg_base + MT8183_HOST_TO_SCP);
+
+	if (wait) {
+		/* wait for SCP's ACK */
+		timeout = msecs_to_jiffies(wait);
+		ret = wait_event_timeout(scp->ack_wq,
+					 scp->ipi_id_ack[id],
+					 timeout);
+		scp->ipi_id_ack[id] = false;
+		if (WARN(!ret, "scp ipi %d ack time out !", id))
+			ret = -EIO;
+		else
+			ret = 0;
+	}
+
+clock_disable:
+	clk_disable_unprepare(scp->clk);
+unlock_mutex:
+	mutex_unlock(&scp->send_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(scp_ipi_send);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MediaTek scp IPI interface");
diff --git a/drivers/remoteproc/qcom_q6v5_mss.c b/drivers/remoteproc/qcom_q6v5_mss.c
index 471128a2e723..a1cc9cbe038f 100644
--- a/drivers/remoteproc/qcom_q6v5_mss.c
+++ b/drivers/remoteproc/qcom_q6v5_mss.c
@@ -68,14 +68,24 @@
 #define AXI_HALTREQ_REG			0x0
 #define AXI_HALTACK_REG			0x4
 #define AXI_IDLE_REG			0x8
+#define NAV_AXI_HALTREQ_BIT		BIT(0)
+#define NAV_AXI_HALTACK_BIT		BIT(1)
+#define NAV_AXI_IDLE_BIT		BIT(2)
+#define AXI_GATING_VALID_OVERRIDE	BIT(0)
 
-#define HALT_ACK_TIMEOUT_MS		100
+#define HALT_ACK_TIMEOUT_US		100000
+#define NAV_HALT_ACK_TIMEOUT_US		200
 
 /* QDSP6SS_RESET */
 #define Q6SS_STOP_CORE			BIT(0)
 #define Q6SS_CORE_ARES			BIT(1)
 #define Q6SS_BUS_ARES_ENABLE		BIT(2)
 
+/* QDSP6SS CBCR */
+#define Q6SS_CBCR_CLKEN			BIT(0)
+#define Q6SS_CBCR_CLKOFF		BIT(31)
+#define Q6SS_CBCR_TIMEOUT_US		200
+
 /* QDSP6SS_GFMUX_CTL */
 #define Q6SS_CLK_ENABLE			BIT(1)
 
@@ -96,15 +106,16 @@
 #define QDSP6v56_BHS_ON		BIT(24)
 #define QDSP6v56_CLAMP_WL		BIT(21)
 #define QDSP6v56_CLAMP_QMC_MEM		BIT(22)
-#define HALT_CHECK_MAX_LOOPS		200
 #define QDSP6SS_XO_CBCR		0x0038
 #define QDSP6SS_ACC_OVERRIDE_VAL		0x20
 
 /* QDSP6v65 parameters */
+#define QDSP6SS_CORE_CBCR		0x20
 #define QDSP6SS_SLEEP                   0x3C
 #define QDSP6SS_BOOT_CORE_START         0x400
 #define QDSP6SS_BOOT_CMD                0x404
-#define SLEEP_CHECK_MAX_LOOPS           200
+#define QDSP6SS_BOOT_STATUS		0x408
+#define BOOT_STATUS_TIMEOUT_US		200
 #define BOOT_FSM_TIMEOUT                10000
 
 struct reg_info {
@@ -131,6 +142,7 @@ struct rproc_hexagon_res {
 	int version;
 	bool need_mem_protection;
 	bool has_alt_reset;
+	bool has_halt_nav;
 };
 
 struct q6v5 {
@@ -141,9 +153,14 @@ struct q6v5 {
 	void __iomem *rmb_base;
 
 	struct regmap *halt_map;
+	struct regmap *halt_nav_map;
+	struct regmap *conn_map;
+
 	u32 halt_q6;
 	u32 halt_modem;
 	u32 halt_nc;
+	u32 halt_nav;
+	u32 conn_box;
 
 	struct reset_control *mss_restart;
 	struct reset_control *pdc_reset;
@@ -187,6 +204,7 @@ struct q6v5 {
 	struct qcom_sysmon *sysmon;
 	bool need_mem_protection;
 	bool has_alt_reset;
+	bool has_halt_nav;
 	int mpss_perm;
 	int mba_perm;
 	const char *hexagon_mdt_image;
@@ -198,6 +216,7 @@ enum {
 	MSS_MSM8974,
 	MSS_MSM8996,
 	MSS_MSM8998,
+	MSS_SC7180,
 	MSS_SDM845,
 };
 
@@ -396,6 +415,26 @@ static int q6v5_reset_assert(struct q6v5 *qproc)
 		reset_control_assert(qproc->pdc_reset);
 		ret = reset_control_reset(qproc->mss_restart);
 		reset_control_deassert(qproc->pdc_reset);
+	} else if (qproc->has_halt_nav) {
+		/*
+		 * When the AXI pipeline is being reset with the Q6 modem partly
+		 * operational there is possibility of AXI valid signal to
+		 * glitch, leading to spurious transactions and Q6 hangs. A work
+		 * around is employed by asserting the AXI_GATING_VALID_OVERRIDE
+		 * BIT before triggering Q6 MSS reset. Both the HALTREQ and
+		 * AXI_GATING_VALID_OVERRIDE are withdrawn post MSS assert
+		 * followed by a MSS deassert, while holding the PDC reset.
+		 */
+		reset_control_assert(qproc->pdc_reset);
+		regmap_update_bits(qproc->conn_map, qproc->conn_box,
+				   AXI_GATING_VALID_OVERRIDE, 1);
+		regmap_update_bits(qproc->halt_nav_map, qproc->halt_nav,
+				   NAV_AXI_HALTREQ_BIT, 0);
+		reset_control_assert(qproc->mss_restart);
+		reset_control_deassert(qproc->pdc_reset);
+		regmap_update_bits(qproc->conn_map, qproc->conn_box,
+				   AXI_GATING_VALID_OVERRIDE, 0);
+		ret = reset_control_deassert(qproc->mss_restart);
 	} else {
 		ret = reset_control_assert(qproc->mss_restart);
 	}
@@ -413,6 +452,8 @@ static int q6v5_reset_deassert(struct q6v5 *qproc)
 		ret = reset_control_reset(qproc->mss_restart);
 		writel(0, qproc->rmb_base + RMB_MBA_ALT_RESET);
 		reset_control_deassert(qproc->pdc_reset);
+	} else if (qproc->has_halt_nav) {
+		ret = reset_control_reset(qproc->mss_restart);
 	} else {
 		ret = reset_control_deassert(qproc->mss_restart);
 	}
@@ -474,12 +515,12 @@ static int q6v5proc_reset(struct q6v5 *qproc)
 
 	if (qproc->version == MSS_SDM845) {
 		val = readl(qproc->reg_base + QDSP6SS_SLEEP);
-		val |= 0x1;
+		val |= Q6SS_CBCR_CLKEN;
 		writel(val, qproc->reg_base + QDSP6SS_SLEEP);
 
 		ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_SLEEP,
-					 val, !(val & BIT(31)), 1,
-					 SLEEP_CHECK_MAX_LOOPS);
+					 val, !(val & Q6SS_CBCR_CLKOFF), 1,
+					 Q6SS_CBCR_TIMEOUT_US);
 		if (ret) {
 			dev_err(qproc->dev, "QDSP6SS Sleep clock timed out\n");
 			return -ETIMEDOUT;
@@ -500,6 +541,54 @@ static int q6v5proc_reset(struct q6v5 *qproc)
 		}
 
 		goto pbl_wait;
+	} else if (qproc->version == MSS_SC7180) {
+		val = readl(qproc->reg_base + QDSP6SS_SLEEP);
+		val |= Q6SS_CBCR_CLKEN;
+		writel(val, qproc->reg_base + QDSP6SS_SLEEP);
+
+		ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_SLEEP,
+					 val, !(val & Q6SS_CBCR_CLKOFF), 1,
+					 Q6SS_CBCR_TIMEOUT_US);
+		if (ret) {
+			dev_err(qproc->dev, "QDSP6SS Sleep clock timed out\n");
+			return -ETIMEDOUT;
+		}
+
+		/* Turn on the XO clock needed for PLL setup */
+		val = readl(qproc->reg_base + QDSP6SS_XO_CBCR);
+		val |= Q6SS_CBCR_CLKEN;
+		writel(val, qproc->reg_base + QDSP6SS_XO_CBCR);
+
+		ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_XO_CBCR,
+					 val, !(val & Q6SS_CBCR_CLKOFF), 1,
+					 Q6SS_CBCR_TIMEOUT_US);
+		if (ret) {
+			dev_err(qproc->dev, "QDSP6SS XO clock timed out\n");
+			return -ETIMEDOUT;
+		}
+
+		/* Configure Q6 core CBCR to auto-enable after reset sequence */
+		val = readl(qproc->reg_base + QDSP6SS_CORE_CBCR);
+		val |= Q6SS_CBCR_CLKEN;
+		writel(val, qproc->reg_base + QDSP6SS_CORE_CBCR);
+
+		/* De-assert the Q6 stop core signal */
+		writel(1, qproc->reg_base + QDSP6SS_BOOT_CORE_START);
+
+		/* Trigger the boot FSM to start the Q6 out-of-reset sequence */
+		writel(1, qproc->reg_base + QDSP6SS_BOOT_CMD);
+
+		/* Poll the QDSP6SS_BOOT_STATUS for FSM completion */
+		ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_BOOT_STATUS,
+					 val, (val & BIT(0)) != 0, 1,
+					 BOOT_STATUS_TIMEOUT_US);
+		if (ret) {
+			dev_err(qproc->dev, "Boot FSM failed to complete.\n");
+			/* Reset the modem so that boot FSM is in reset state */
+			q6v5_reset_deassert(qproc);
+			return ret;
+		}
+		goto pbl_wait;
 	} else if (qproc->version == MSS_MSM8996 ||
 		   qproc->version == MSS_MSM8998) {
 		int mem_pwr_ctl;
@@ -515,13 +604,13 @@ static int q6v5proc_reset(struct q6v5 *qproc)
 
 		/* BHS require xo cbcr to be enabled */
 		val = readl(qproc->reg_base + QDSP6SS_XO_CBCR);
-		val |= 0x1;
+		val |= Q6SS_CBCR_CLKEN;
 		writel(val, qproc->reg_base + QDSP6SS_XO_CBCR);
 
 		/* Read CLKOFF bit to go low indicating CLK is enabled */
 		ret = readl_poll_timeout(qproc->reg_base + QDSP6SS_XO_CBCR,
-					 val, !(val & BIT(31)), 1,
-					 HALT_CHECK_MAX_LOOPS);
+					 val, !(val & Q6SS_CBCR_CLKOFF), 1,
+					 Q6SS_CBCR_TIMEOUT_US);
 		if (ret) {
 			dev_err(qproc->dev,
 				"xo cbcr enabling timed out (rc:%d)\n", ret);
@@ -637,7 +726,6 @@ static void q6v5proc_halt_axi_port(struct q6v5 *qproc,
 				   struct regmap *halt_map,
 				   u32 offset)
 {
-	unsigned long timeout;
 	unsigned int val;
 	int ret;
 
@@ -650,14 +738,8 @@ static void q6v5proc_halt_axi_port(struct q6v5 *qproc,
 	regmap_write(halt_map, offset + AXI_HALTREQ_REG, 1);
 
 	/* Wait for halt */
-	timeout = jiffies + msecs_to_jiffies(HALT_ACK_TIMEOUT_MS);
-	for (;;) {
-		ret = regmap_read(halt_map, offset + AXI_HALTACK_REG, &val);
-		if (ret || val || time_after(jiffies, timeout))
-			break;
-
-		msleep(1);
-	}
+	regmap_read_poll_timeout(halt_map, offset + AXI_HALTACK_REG, val,
+				 val, 1000, HALT_ACK_TIMEOUT_US);
 
 	ret = regmap_read(halt_map, offset + AXI_IDLE_REG, &val);
 	if (ret || !val)
@@ -667,6 +749,32 @@ static void q6v5proc_halt_axi_port(struct q6v5 *qproc,
 	regmap_write(halt_map, offset + AXI_HALTREQ_REG, 0);
 }
 
+static void q6v5proc_halt_nav_axi_port(struct q6v5 *qproc,
+				       struct regmap *halt_map,
+				       u32 offset)
+{
+	unsigned int val;
+	int ret;
+
+	/* Check if we're already idle */
+	ret = regmap_read(halt_map, offset, &val);
+	if (!ret && (val & NAV_AXI_IDLE_BIT))
+		return;
+
+	/* Assert halt request */
+	regmap_update_bits(halt_map, offset, NAV_AXI_HALTREQ_BIT,
+			   NAV_AXI_HALTREQ_BIT);
+
+	/* Wait for halt ack*/
+	regmap_read_poll_timeout(halt_map, offset, val,
+				 (val & NAV_AXI_HALTACK_BIT),
+				 5, NAV_HALT_ACK_TIMEOUT_US);
+
+	ret = regmap_read(halt_map, offset, &val);
+	if (ret || !(val & NAV_AXI_IDLE_BIT))
+		dev_err(qproc->dev, "port failed halt\n");
+}
+
 static int q6v5_mpss_init_image(struct q6v5 *qproc, const struct firmware *fw)
 {
 	unsigned long dma_attrs = DMA_ATTR_FORCE_CONTIGUOUS;
@@ -829,6 +937,9 @@ static int q6v5_mba_load(struct q6v5 *qproc)
 halt_axi_ports:
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem);
+	if (qproc->has_halt_nav)
+		q6v5proc_halt_nav_axi_port(qproc, qproc->halt_nav_map,
+					   qproc->halt_nav);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc);
 
 reclaim_mba:
@@ -876,6 +987,9 @@ static void q6v5_mba_reclaim(struct q6v5 *qproc)
 
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_q6);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_modem);
+	if (qproc->has_halt_nav)
+		q6v5proc_halt_nav_axi_port(qproc, qproc->halt_nav_map,
+					   qproc->halt_nav);
 	q6v5proc_halt_axi_port(qproc, qproc->halt_map, qproc->halt_nc);
 	if (qproc->version == MSS_MSM8996) {
 		/*
@@ -1253,6 +1367,47 @@ static int q6v5_init_mem(struct q6v5 *qproc, struct platform_device *pdev)
 	qproc->halt_modem = args.args[1];
 	qproc->halt_nc = args.args[2];
 
+	if (qproc->has_halt_nav) {
+		struct platform_device *nav_pdev;
+
+		ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node,
+						       "qcom,halt-nav-regs",
+						       1, 0, &args);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to parse halt-nav-regs\n");
+			return -EINVAL;
+		}
+
+		nav_pdev = of_find_device_by_node(args.np);
+		of_node_put(args.np);
+		if (!nav_pdev) {
+			dev_err(&pdev->dev, "failed to get mss clock device\n");
+			return -EPROBE_DEFER;
+		}
+
+		qproc->halt_nav_map = dev_get_regmap(&nav_pdev->dev, NULL);
+		if (!qproc->halt_nav_map) {
+			dev_err(&pdev->dev, "failed to get map from device\n");
+			return -EINVAL;
+		}
+		qproc->halt_nav = args.args[0];
+
+		ret = of_parse_phandle_with_fixed_args(pdev->dev.of_node,
+						       "qcom,halt-nav-regs",
+						       1, 1, &args);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to parse halt-nav-regs\n");
+			return -EINVAL;
+		}
+
+		qproc->conn_map = syscon_node_to_regmap(args.np);
+		of_node_put(args.np);
+		if (IS_ERR(qproc->conn_map))
+			return PTR_ERR(qproc->conn_map);
+
+		qproc->conn_box = args.args[0];
+	}
+
 	return 0;
 }
 
@@ -1327,7 +1482,7 @@ static int q6v5_init_reset(struct q6v5 *qproc)
 		return PTR_ERR(qproc->mss_restart);
 	}
 
-	if (qproc->has_alt_reset) {
+	if (qproc->has_alt_reset || qproc->has_halt_nav) {
 		qproc->pdc_reset = devm_reset_control_get_exclusive(qproc->dev,
 								    "pdc_reset");
 		if (IS_ERR(qproc->pdc_reset)) {
@@ -1426,6 +1581,7 @@ static int q6v5_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, qproc);
 
+	qproc->has_halt_nav = desc->has_halt_nav;
 	ret = q6v5_init_mem(qproc, pdev);
 	if (ret)
 		goto free_rproc;
@@ -1549,6 +1705,41 @@ static int q6v5_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct rproc_hexagon_res sc7180_mss = {
+	.hexagon_mba_image = "mba.mbn",
+	.proxy_clk_names = (char*[]){
+		"xo",
+		NULL
+	},
+	.reset_clk_names = (char*[]){
+		"iface",
+		"bus",
+		"snoc_axi",
+		NULL
+	},
+	.active_clk_names = (char*[]){
+		"mnoc_axi",
+		"nav",
+		"mss_nav",
+		"mss_crypto",
+		NULL
+	},
+	.active_pd_names = (char*[]){
+		"load_state",
+		NULL
+	},
+	.proxy_pd_names = (char*[]){
+		"cx",
+		"mx",
+		"mss",
+		NULL
+	},
+	.need_mem_protection = true,
+	.has_alt_reset = false,
+	.has_halt_nav = true,
+	.version = MSS_SC7180,
+};
+
 static const struct rproc_hexagon_res sdm845_mss = {
 	.hexagon_mba_image = "mba.mbn",
 	.proxy_clk_names = (char*[]){
@@ -1580,6 +1771,7 @@ static const struct rproc_hexagon_res sdm845_mss = {
 	},
 	.need_mem_protection = true,
 	.has_alt_reset = true,
+	.has_halt_nav = false,
 	.version = MSS_SDM845,
 };
 
@@ -1594,7 +1786,6 @@ static const struct rproc_hexagon_res msm8998_mss = {
 	.active_clk_names = (char*[]){
 			"iface",
 			"bus",
-			"mem",
 			"gpll0_mss",
 			"mnoc_axi",
 			"snoc_axi",
@@ -1607,6 +1798,7 @@ static const struct rproc_hexagon_res msm8998_mss = {
 	},
 	.need_mem_protection = true,
 	.has_alt_reset = false,
+	.has_halt_nav = false,
 	.version = MSS_MSM8998,
 };
 
@@ -1636,6 +1828,7 @@ static const struct rproc_hexagon_res msm8996_mss = {
 	},
 	.need_mem_protection = true,
 	.has_alt_reset = false,
+	.has_halt_nav = false,
 	.version = MSS_MSM8996,
 };
 
@@ -1668,6 +1861,7 @@ static const struct rproc_hexagon_res msm8916_mss = {
 	},
 	.need_mem_protection = false,
 	.has_alt_reset = false,
+	.has_halt_nav = false,
 	.version = MSS_MSM8916,
 };
 
@@ -1708,6 +1902,7 @@ static const struct rproc_hexagon_res msm8974_mss = {
 	},
 	.need_mem_protection = false,
 	.has_alt_reset = false,
+	.has_halt_nav = false,
 	.version = MSS_MSM8974,
 };
 
@@ -1717,6 +1912,7 @@ static const struct of_device_id q6v5_of_match[] = {
 	{ .compatible = "qcom,msm8974-mss-pil", .data = &msm8974_mss},
 	{ .compatible = "qcom,msm8996-mss-pil", .data = &msm8996_mss},
 	{ .compatible = "qcom,msm8998-mss-pil", .data = &msm8998_mss},
+	{ .compatible = "qcom,sc7180-mss-pil", .data = &sc7180_mss},
 	{ .compatible = "qcom,sdm845-mss-pil", .data = &sdm845_mss},
 	{ },
 };
diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
index db4b3c4bacd7..edf9d0e1a235 100644
--- a/drivers/remoteproc/qcom_q6v5_pas.c
+++ b/drivers/remoteproc/qcom_q6v5_pas.c
@@ -15,6 +15,8 @@
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
 #include <linux/qcom_scm.h>
 #include <linux/regulator/consumer.h>
 #include <linux/remoteproc.h>
@@ -31,6 +33,10 @@ struct adsp_data {
 	const char *firmware_name;
 	int pas_id;
 	bool has_aggre2_clk;
+	bool auto_boot;
+
+	char **active_pd_names;
+	char **proxy_pd_names;
 
 	const char *ssr_name;
 	const char *sysmon_name;
@@ -49,6 +55,12 @@ struct qcom_adsp {
 	struct regulator *cx_supply;
 	struct regulator *px_supply;
 
+	struct device *active_pds[1];
+	struct device *proxy_pds[3];
+
+	int active_pd_count;
+	int proxy_pd_count;
+
 	int pas_id;
 	int crash_reason_smem;
 	bool has_aggre2_clk;
@@ -67,6 +79,41 @@ struct qcom_adsp {
 	struct qcom_sysmon *sysmon;
 };
 
+static int adsp_pds_enable(struct qcom_adsp *adsp, struct device **pds,
+			   size_t pd_count)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < pd_count; i++) {
+		dev_pm_genpd_set_performance_state(pds[i], INT_MAX);
+		ret = pm_runtime_get_sync(pds[i]);
+		if (ret < 0)
+			goto unroll_pd_votes;
+	}
+
+	return 0;
+
+unroll_pd_votes:
+	for (i--; i >= 0; i--) {
+		dev_pm_genpd_set_performance_state(pds[i], 0);
+		pm_runtime_put(pds[i]);
+	}
+
+	return ret;
+};
+
+static void adsp_pds_disable(struct qcom_adsp *adsp, struct device **pds,
+			     size_t pd_count)
+{
+	int i;
+
+	for (i = 0; i < pd_count; i++) {
+		dev_pm_genpd_set_performance_state(pds[i], 0);
+		pm_runtime_put(pds[i]);
+	}
+}
+
 static int adsp_load(struct rproc *rproc, const struct firmware *fw)
 {
 	struct qcom_adsp *adsp = (struct qcom_adsp *)rproc->priv;
@@ -84,9 +131,17 @@ static int adsp_start(struct rproc *rproc)
 
 	qcom_q6v5_prepare(&adsp->q6v5);
 
+	ret = adsp_pds_enable(adsp, adsp->active_pds, adsp->active_pd_count);
+	if (ret < 0)
+		goto disable_irqs;
+
+	ret = adsp_pds_enable(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
+	if (ret < 0)
+		goto disable_active_pds;
+
 	ret = clk_prepare_enable(adsp->xo);
 	if (ret)
-		return ret;
+		goto disable_proxy_pds;
 
 	ret = clk_prepare_enable(adsp->aggre2_clk);
 	if (ret)
@@ -124,6 +179,12 @@ disable_aggre2_clk:
 	clk_disable_unprepare(adsp->aggre2_clk);
 disable_xo_clk:
 	clk_disable_unprepare(adsp->xo);
+disable_proxy_pds:
+	adsp_pds_disable(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
+disable_active_pds:
+	adsp_pds_disable(adsp, adsp->active_pds, adsp->active_pd_count);
+disable_irqs:
+	qcom_q6v5_unprepare(&adsp->q6v5);
 
 	return ret;
 }
@@ -136,6 +197,7 @@ static void qcom_pas_handover(struct qcom_q6v5 *q6v5)
 	regulator_disable(adsp->cx_supply);
 	clk_disable_unprepare(adsp->aggre2_clk);
 	clk_disable_unprepare(adsp->xo);
+	adsp_pds_disable(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
 }
 
 static int adsp_stop(struct rproc *rproc)
@@ -152,6 +214,7 @@ static int adsp_stop(struct rproc *rproc)
 	if (ret)
 		dev_err(adsp->dev, "failed to shutdown: %d\n", ret);
 
+	adsp_pds_disable(adsp, adsp->active_pds, adsp->active_pd_count);
 	handover = qcom_q6v5_unprepare(&adsp->q6v5);
 	if (handover)
 		qcom_pas_handover(&adsp->q6v5);
@@ -217,6 +280,59 @@ static int adsp_init_regulator(struct qcom_adsp *adsp)
 	return PTR_ERR_OR_ZERO(adsp->px_supply);
 }
 
+static int adsp_pds_attach(struct device *dev, struct device **devs,
+			   char **pd_names)
+{
+	size_t num_pds = 0;
+	int ret;
+	int i;
+
+	if (!pd_names)
+		return 0;
+
+	/* Handle single power domain */
+	if (dev->pm_domain) {
+		devs[0] = dev;
+		pm_runtime_enable(dev);
+		return 1;
+	}
+
+	while (pd_names[num_pds])
+		num_pds++;
+
+	for (i = 0; i < num_pds; i++) {
+		devs[i] = dev_pm_domain_attach_by_name(dev, pd_names[i]);
+		if (IS_ERR_OR_NULL(devs[i])) {
+			ret = PTR_ERR(devs[i]) ? : -ENODATA;
+			goto unroll_attach;
+		}
+	}
+
+	return num_pds;
+
+unroll_attach:
+	for (i--; i >= 0; i--)
+		dev_pm_domain_detach(devs[i], false);
+
+	return ret;
+};
+
+static void adsp_pds_detach(struct qcom_adsp *adsp, struct device **pds,
+			    size_t pd_count)
+{
+	struct device *dev = adsp->dev;
+	int i;
+
+	/* Handle single power domain */
+	if (dev->pm_domain && pd_count) {
+		pm_runtime_disable(dev);
+		return;
+	}
+
+	for (i = 0; i < pd_count; i++)
+		dev_pm_domain_detach(pds[i], false);
+}
+
 static int adsp_alloc_memory_region(struct qcom_adsp *adsp)
 {
 	struct device_node *node;
@@ -273,6 +389,8 @@ static int adsp_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	rproc->auto_boot = desc->auto_boot;
+
 	adsp = (struct qcom_adsp *)rproc->priv;
 	adsp->dev = &pdev->dev;
 	adsp->rproc = rproc;
@@ -292,10 +410,22 @@ static int adsp_probe(struct platform_device *pdev)
 	if (ret)
 		goto free_rproc;
 
+	ret = adsp_pds_attach(&pdev->dev, adsp->active_pds,
+			      desc->active_pd_names);
+	if (ret < 0)
+		goto free_rproc;
+	adsp->active_pd_count = ret;
+
+	ret = adsp_pds_attach(&pdev->dev, adsp->proxy_pds,
+			      desc->proxy_pd_names);
+	if (ret < 0)
+		goto detach_active_pds;
+	adsp->proxy_pd_count = ret;
+
 	ret = qcom_q6v5_init(&adsp->q6v5, pdev, rproc, desc->crash_reason_smem,
 			     qcom_pas_handover);
 	if (ret)
-		goto free_rproc;
+		goto detach_proxy_pds;
 
 	qcom_add_glink_subdev(rproc, &adsp->glink_subdev);
 	qcom_add_smd_subdev(rproc, &adsp->smd_subdev);
@@ -305,15 +435,19 @@ static int adsp_probe(struct platform_device *pdev)
 					      desc->ssctl_id);
 	if (IS_ERR(adsp->sysmon)) {
 		ret = PTR_ERR(adsp->sysmon);
-		goto free_rproc;
+		goto detach_proxy_pds;
 	}
 
 	ret = rproc_add(rproc);
 	if (ret)
-		goto free_rproc;
+		goto detach_proxy_pds;
 
 	return 0;
 
+detach_proxy_pds:
+	adsp_pds_detach(adsp, adsp->proxy_pds, adsp->proxy_pd_count);
+detach_active_pds:
+	adsp_pds_detach(adsp, adsp->active_pds, adsp->active_pd_count);
 free_rproc:
 	rproc_free(rproc);
 
@@ -340,6 +474,41 @@ static const struct adsp_data adsp_resource_init = {
 		.firmware_name = "adsp.mdt",
 		.pas_id = 1,
 		.has_aggre2_clk = false,
+		.auto_boot = true,
+		.ssr_name = "lpass",
+		.sysmon_name = "adsp",
+		.ssctl_id = 0x14,
+};
+
+static const struct adsp_data sm8150_adsp_resource = {
+		.crash_reason_smem = 423,
+		.firmware_name = "adsp.mdt",
+		.pas_id = 1,
+		.has_aggre2_clk = false,
+		.auto_boot = true,
+		.active_pd_names = (char*[]){
+			"load_state",
+			NULL
+		},
+		.proxy_pd_names = (char*[]){
+			"cx",
+			NULL
+		},
+		.ssr_name = "lpass",
+		.sysmon_name = "adsp",
+		.ssctl_id = 0x14,
+};
+
+static const struct adsp_data msm8998_adsp_resource = {
+		.crash_reason_smem = 423,
+		.firmware_name = "adsp.mdt",
+		.pas_id = 1,
+		.has_aggre2_clk = false,
+		.auto_boot = true,
+		.proxy_pd_names = (char*[]){
+			"cx",
+			NULL
+		},
 		.ssr_name = "lpass",
 		.sysmon_name = "adsp",
 		.ssctl_id = 0x14,
@@ -350,16 +519,92 @@ static const struct adsp_data cdsp_resource_init = {
 	.firmware_name = "cdsp.mdt",
 	.pas_id = 18,
 	.has_aggre2_clk = false,
+	.auto_boot = true,
+	.ssr_name = "cdsp",
+	.sysmon_name = "cdsp",
+	.ssctl_id = 0x17,
+};
+
+static const struct adsp_data sm8150_cdsp_resource = {
+	.crash_reason_smem = 601,
+	.firmware_name = "cdsp.mdt",
+	.pas_id = 18,
+	.has_aggre2_clk = false,
+	.auto_boot = true,
+	.active_pd_names = (char*[]){
+		"load_state",
+		NULL
+	},
+	.proxy_pd_names = (char*[]){
+		"cx",
+		NULL
+	},
 	.ssr_name = "cdsp",
 	.sysmon_name = "cdsp",
 	.ssctl_id = 0x17,
 };
 
+static const struct adsp_data mpss_resource_init = {
+	.crash_reason_smem = 421,
+	.firmware_name = "modem.mdt",
+	.pas_id = 4,
+	.has_aggre2_clk = false,
+	.auto_boot = false,
+	.active_pd_names = (char*[]){
+		"load_state",
+		NULL
+	},
+	.proxy_pd_names = (char*[]){
+		"cx",
+		"mss",
+		NULL
+	},
+	.ssr_name = "mpss",
+	.sysmon_name = "modem",
+	.ssctl_id = 0x12,
+};
+
 static const struct adsp_data slpi_resource_init = {
 		.crash_reason_smem = 424,
 		.firmware_name = "slpi.mdt",
 		.pas_id = 12,
 		.has_aggre2_clk = true,
+		.auto_boot = true,
+		.ssr_name = "dsps",
+		.sysmon_name = "slpi",
+		.ssctl_id = 0x16,
+};
+
+static const struct adsp_data sm8150_slpi_resource = {
+		.crash_reason_smem = 424,
+		.firmware_name = "slpi.mdt",
+		.pas_id = 12,
+		.has_aggre2_clk = false,
+		.auto_boot = true,
+		.active_pd_names = (char*[]){
+			"load_state",
+			NULL
+		},
+		.proxy_pd_names = (char*[]){
+			"lcx",
+			"lmx",
+			NULL
+		},
+		.ssr_name = "dsps",
+		.sysmon_name = "slpi",
+		.ssctl_id = 0x16,
+};
+
+static const struct adsp_data msm8998_slpi_resource = {
+		.crash_reason_smem = 424,
+		.firmware_name = "slpi.mdt",
+		.pas_id = 12,
+		.has_aggre2_clk = true,
+		.auto_boot = true,
+		.proxy_pd_names = (char*[]){
+			"ssc_cx",
+			NULL
+		},
 		.ssr_name = "dsps",
 		.sysmon_name = "slpi",
 		.ssctl_id = 0x16,
@@ -369,6 +614,7 @@ static const struct adsp_data wcss_resource_init = {
 	.crash_reason_smem = 421,
 	.firmware_name = "wcnss.mdt",
 	.pas_id = 6,
+	.auto_boot = true,
 	.ssr_name = "mpss",
 	.sysmon_name = "wcnss",
 	.ssctl_id = 0x12,
@@ -378,11 +624,17 @@ static const struct of_device_id adsp_of_match[] = {
 	{ .compatible = "qcom,msm8974-adsp-pil", .data = &adsp_resource_init},
 	{ .compatible = "qcom,msm8996-adsp-pil", .data = &adsp_resource_init},
 	{ .compatible = "qcom,msm8996-slpi-pil", .data = &slpi_resource_init},
+	{ .compatible = "qcom,msm8998-adsp-pas", .data = &msm8998_adsp_resource},
+	{ .compatible = "qcom,msm8998-slpi-pas", .data = &msm8998_slpi_resource},
 	{ .compatible = "qcom,qcs404-adsp-pas", .data = &adsp_resource_init },
 	{ .compatible = "qcom,qcs404-cdsp-pas", .data = &cdsp_resource_init },
 	{ .compatible = "qcom,qcs404-wcss-pas", .data = &wcss_resource_init },
 	{ .compatible = "qcom,sdm845-adsp-pas", .data = &adsp_resource_init},
 	{ .compatible = "qcom,sdm845-cdsp-pas", .data = &cdsp_resource_init},
+	{ .compatible = "qcom,sm8150-adsp-pas", .data = &sm8150_adsp_resource},
+	{ .compatible = "qcom,sm8150-cdsp-pas", .data = &sm8150_cdsp_resource},
+	{ .compatible = "qcom,sm8150-mpss-pas", .data = &mpss_resource_init},
+	{ .compatible = "qcom,sm8150-slpi-pas", .data = &sm8150_slpi_resource},
 	{ },
 };
 MODULE_DEVICE_TABLE(of, adsp_of_match);
diff --git a/drivers/remoteproc/qcom_sysmon.c b/drivers/remoteproc/qcom_sysmon.c
index c231314eab66..faf3822d8791 100644
--- a/drivers/remoteproc/qcom_sysmon.c
+++ b/drivers/remoteproc/qcom_sysmon.c
@@ -394,7 +394,7 @@ static int ssctl_new_server(struct qmi_handle *qmi, struct qmi_service *svc)
 		break;
 	default:
 		return -EINVAL;
-	};
+	}
 
 	sysmon->ssctl_version = svc->version;
 
diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c
index 307df98347ba..097f33e4f1f3 100644
--- a/drivers/remoteproc/remoteproc_core.c
+++ b/drivers/remoteproc/remoteproc_core.c
@@ -477,8 +477,8 @@ static int rproc_handle_vdev(struct rproc *rproc, struct fw_rsc_vdev *rsc,
 	char name[16];
 
 	/* make sure resource isn't truncated */
-	if (sizeof(*rsc) + rsc->num_of_vrings * sizeof(struct fw_rsc_vdev_vring)
-			+ rsc->config_len > avail) {
+	if (struct_size(rsc, vring, rsc->num_of_vrings) + rsc->config_len >
+			avail) {
 		dev_err(dev, "vdev rsc is truncated\n");
 		return -EINVAL;
 	}
@@ -2223,7 +2223,7 @@ static int __init remoteproc_init(void)
 
 	return 0;
 }
-module_init(remoteproc_init);
+subsys_initcall(remoteproc_init);
 
 static void __exit remoteproc_exit(void)
 {
diff --git a/drivers/rpmsg/Kconfig b/drivers/rpmsg/Kconfig
index 709276540ef1..a9108ff563dc 100644
--- a/drivers/rpmsg/Kconfig
+++ b/drivers/rpmsg/Kconfig
@@ -15,6 +15,15 @@ config RPMSG_CHAR
 	  in /dev. They make it possible for user-space programs to send and
 	  receive rpmsg packets.
 
+config RPMSG_MTK_SCP
+	tristate "MediaTek SCP"
+	depends on MTK_SCP
+	select RPMSG
+	help
+	  Say y here to enable support providing communication channels to
+	  remote processors in MediaTek platforms.
+	  This use IPI and IPC to communicate with remote processors.
+
 config RPMSG_QCOM_GLINK_NATIVE
 	tristate
 	select RPMSG
diff --git a/drivers/rpmsg/Makefile b/drivers/rpmsg/Makefile
index 9aa859502d27..ae92a7fb08f6 100644
--- a/drivers/rpmsg/Makefile
+++ b/drivers/rpmsg/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_RPMSG)		+= rpmsg_core.o
 obj-$(CONFIG_RPMSG_CHAR)	+= rpmsg_char.o
+obj-$(CONFIG_RPMSG_MTK_SCP)	+= mtk_rpmsg.o
 obj-$(CONFIG_RPMSG_QCOM_GLINK_RPM) += qcom_glink_rpm.o
 obj-$(CONFIG_RPMSG_QCOM_GLINK_NATIVE) += qcom_glink_native.o
 obj-$(CONFIG_RPMSG_QCOM_GLINK_SMEM) += qcom_glink_smem.o
diff --git a/drivers/rpmsg/mtk_rpmsg.c b/drivers/rpmsg/mtk_rpmsg.c
new file mode 100644
index 000000000000..232aa4e40133
--- /dev/null
+++ b/drivers/rpmsg/mtk_rpmsg.c
@@ -0,0 +1,414 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright 2019 Google LLC.
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+#include <linux/rpmsg/mtk_rpmsg.h>
+#include <linux/workqueue.h>
+
+#include "rpmsg_internal.h"
+
+struct mtk_rpmsg_rproc_subdev {
+	struct platform_device *pdev;
+	struct mtk_rpmsg_info *info;
+	struct rpmsg_endpoint *ns_ept;
+	struct rproc_subdev subdev;
+
+	struct work_struct register_work;
+	struct list_head channels;
+	struct mutex channels_lock;
+};
+
+#define to_mtk_subdev(d) container_of(d, struct mtk_rpmsg_rproc_subdev, subdev)
+
+struct mtk_rpmsg_channel_info {
+	struct rpmsg_channel_info info;
+	bool registered;
+	struct list_head list;
+};
+
+/**
+ * struct rpmsg_ns_msg - dynamic name service announcement message
+ * @name: name of remote service that is published
+ * @addr: address of remote service that is published
+ *
+ * This message is sent across to publish a new service. When we receive these
+ * messages, an appropriate rpmsg channel (i.e device) is created. In turn, the
+ * ->probe() handler of the appropriate rpmsg driver will be invoked
+ *  (if/as-soon-as one is registered).
+ */
+struct rpmsg_ns_msg {
+	char name[RPMSG_NAME_SIZE];
+	u32 addr;
+} __packed;
+
+struct mtk_rpmsg_device {
+	struct rpmsg_device rpdev;
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev;
+};
+
+struct mtk_rpmsg_endpoint {
+	struct rpmsg_endpoint ept;
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev;
+};
+
+#define to_mtk_rpmsg_device(r) container_of(r, struct mtk_rpmsg_device, rpdev)
+#define to_mtk_rpmsg_endpoint(r) container_of(r, struct mtk_rpmsg_endpoint, ept)
+
+static const struct rpmsg_endpoint_ops mtk_rpmsg_endpoint_ops;
+
+static void __mtk_ept_release(struct kref *kref)
+{
+	struct rpmsg_endpoint *ept = container_of(kref, struct rpmsg_endpoint,
+						  refcount);
+	kfree(to_mtk_rpmsg_endpoint(ept));
+}
+
+static void mtk_rpmsg_ipi_handler(void *data, unsigned int len, void *priv)
+{
+	struct mtk_rpmsg_endpoint *mept = priv;
+	struct rpmsg_endpoint *ept = &mept->ept;
+	int ret;
+
+	ret = (*ept->cb)(ept->rpdev, data, len, ept->priv, ept->addr);
+	if (ret)
+		dev_warn(&ept->rpdev->dev, "rpmsg handler return error = %d",
+			 ret);
+}
+
+static struct rpmsg_endpoint *
+__mtk_create_ept(struct mtk_rpmsg_rproc_subdev *mtk_subdev,
+		 struct rpmsg_device *rpdev, rpmsg_rx_cb_t cb, void *priv,
+		 u32 id)
+{
+	struct mtk_rpmsg_endpoint *mept;
+	struct rpmsg_endpoint *ept;
+	struct platform_device *pdev = mtk_subdev->pdev;
+	int ret;
+
+	mept = kzalloc(sizeof(*mept), GFP_KERNEL);
+	if (!mept)
+		return NULL;
+	mept->mtk_subdev = mtk_subdev;
+
+	ept = &mept->ept;
+	kref_init(&ept->refcount);
+
+	ept->rpdev = rpdev;
+	ept->cb = cb;
+	ept->priv = priv;
+	ept->ops = &mtk_rpmsg_endpoint_ops;
+	ept->addr = id;
+
+	ret = mtk_subdev->info->register_ipi(pdev, id, mtk_rpmsg_ipi_handler,
+					     mept);
+	if (ret) {
+		dev_err(&pdev->dev, "IPI register failed, id = %d", id);
+		kref_put(&ept->refcount, __mtk_ept_release);
+		return NULL;
+	}
+
+	return ept;
+}
+
+static struct rpmsg_endpoint *
+mtk_rpmsg_create_ept(struct rpmsg_device *rpdev, rpmsg_rx_cb_t cb, void *priv,
+		     struct rpmsg_channel_info chinfo)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev =
+		to_mtk_rpmsg_device(rpdev)->mtk_subdev;
+
+	return __mtk_create_ept(mtk_subdev, rpdev, cb, priv, chinfo.src);
+}
+
+static void mtk_rpmsg_destroy_ept(struct rpmsg_endpoint *ept)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev =
+		to_mtk_rpmsg_endpoint(ept)->mtk_subdev;
+
+	mtk_subdev->info->unregister_ipi(mtk_subdev->pdev, ept->addr);
+	kref_put(&ept->refcount, __mtk_ept_release);
+}
+
+static int mtk_rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev =
+		to_mtk_rpmsg_endpoint(ept)->mtk_subdev;
+
+	return mtk_subdev->info->send_ipi(mtk_subdev->pdev, ept->addr, data,
+					  len, 0);
+}
+
+static int mtk_rpmsg_trysend(struct rpmsg_endpoint *ept, void *data, int len)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev =
+		to_mtk_rpmsg_endpoint(ept)->mtk_subdev;
+
+	/*
+	 * TODO: This currently is same as mtk_rpmsg_send, and wait until SCP
+	 * received the last command.
+	 */
+	return mtk_subdev->info->send_ipi(mtk_subdev->pdev, ept->addr, data,
+					  len, 0);
+}
+
+static const struct rpmsg_endpoint_ops mtk_rpmsg_endpoint_ops = {
+	.destroy_ept = mtk_rpmsg_destroy_ept,
+	.send = mtk_rpmsg_send,
+	.trysend = mtk_rpmsg_trysend,
+};
+
+static void mtk_rpmsg_release_device(struct device *dev)
+{
+	struct rpmsg_device *rpdev = to_rpmsg_device(dev);
+	struct mtk_rpmsg_device *mdev = to_mtk_rpmsg_device(rpdev);
+
+	kfree(mdev);
+}
+
+static const struct rpmsg_device_ops mtk_rpmsg_device_ops = {
+	.create_ept = mtk_rpmsg_create_ept,
+};
+
+static struct device_node *
+mtk_rpmsg_match_device_subnode(struct device_node *node, const char *channel)
+{
+	struct device_node *child;
+	const char *name;
+	int ret;
+
+	for_each_available_child_of_node(node, child) {
+		ret = of_property_read_string(child, "mtk,rpmsg-name", &name);
+		if (ret)
+			continue;
+
+		if (strcmp(name, channel) == 0)
+			return child;
+	}
+
+	return NULL;
+}
+
+static int mtk_rpmsg_register_device(struct mtk_rpmsg_rproc_subdev *mtk_subdev,
+				     struct rpmsg_channel_info *info)
+{
+	struct rpmsg_device *rpdev;
+	struct mtk_rpmsg_device *mdev;
+	struct platform_device *pdev = mtk_subdev->pdev;
+	int ret;
+
+	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
+	if (!mdev)
+		return -ENOMEM;
+
+	mdev->mtk_subdev = mtk_subdev;
+
+	rpdev = &mdev->rpdev;
+	rpdev->ops = &mtk_rpmsg_device_ops;
+	rpdev->src = info->src;
+	rpdev->dst = info->dst;
+	strscpy(rpdev->id.name, info->name, RPMSG_NAME_SIZE);
+
+	rpdev->dev.of_node =
+		mtk_rpmsg_match_device_subnode(pdev->dev.of_node, info->name);
+	rpdev->dev.parent = &pdev->dev;
+	rpdev->dev.release = mtk_rpmsg_release_device;
+
+	ret = rpmsg_register_device(rpdev);
+	if (ret) {
+		kfree(mdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mtk_register_device_work_function(struct work_struct *register_work)
+{
+	struct mtk_rpmsg_rproc_subdev *subdev = container_of(
+		register_work, struct mtk_rpmsg_rproc_subdev, register_work);
+	struct platform_device *pdev = subdev->pdev;
+	struct mtk_rpmsg_channel_info *info;
+	int ret;
+
+	mutex_lock(&subdev->channels_lock);
+	list_for_each_entry(info, &subdev->channels, list) {
+		if (info->registered)
+			continue;
+
+		ret = mtk_rpmsg_register_device(subdev, &info->info);
+		if (ret) {
+			dev_err(&pdev->dev, "Can't create rpmsg_device\n");
+			continue;
+		}
+
+		info->registered = true;
+	}
+	mutex_unlock(&subdev->channels_lock);
+}
+
+static int mtk_rpmsg_create_device(struct mtk_rpmsg_rproc_subdev *mtk_subdev,
+				   char *name, u32 addr)
+{
+	struct mtk_rpmsg_channel_info *info;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	strscpy(info->info.name, name, RPMSG_NAME_SIZE);
+	info->info.src = addr;
+	info->info.dst = RPMSG_ADDR_ANY;
+	mutex_lock(&mtk_subdev->channels_lock);
+	list_add(&info->list, &mtk_subdev->channels);
+	mutex_unlock(&mtk_subdev->channels_lock);
+
+	schedule_work(&mtk_subdev->register_work);
+	return 0;
+}
+
+static int mtk_rpmsg_ns_cb(struct rpmsg_device *rpdev, void *data, int len,
+			   void *priv, u32 src)
+{
+	struct rpmsg_ns_msg *msg = data;
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev = priv;
+	struct device *dev = &mtk_subdev->pdev->dev;
+
+	int ret;
+
+	if (len != sizeof(*msg)) {
+		dev_err(dev, "malformed ns msg (%d)\n", len);
+		return -EINVAL;
+	}
+
+	/*
+	 * the name service ept does _not_ belong to a real rpmsg channel,
+	 * and is handled by the rpmsg bus itself.
+	 * for sanity reasons, make sure a valid rpdev has _not_ sneaked
+	 * in somehow.
+	 */
+	if (rpdev) {
+		dev_err(dev, "anomaly: ns ept has an rpdev handle\n");
+		return -EINVAL;
+	}
+
+	/* don't trust the remote processor for null terminating the name */
+	msg->name[RPMSG_NAME_SIZE - 1] = '\0';
+
+	dev_info(dev, "creating channel %s addr 0x%x\n", msg->name, msg->addr);
+
+	ret = mtk_rpmsg_create_device(mtk_subdev, msg->name, msg->addr);
+	if (ret) {
+		dev_err(dev, "create rpmsg device failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int mtk_rpmsg_prepare(struct rproc_subdev *subdev)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev = to_mtk_subdev(subdev);
+
+	/* a dedicated endpoint handles the name service msgs */
+	if (mtk_subdev->info->ns_ipi_id >= 0) {
+		mtk_subdev->ns_ept =
+			__mtk_create_ept(mtk_subdev, NULL, mtk_rpmsg_ns_cb,
+					 mtk_subdev,
+					 mtk_subdev->info->ns_ipi_id);
+		if (!mtk_subdev->ns_ept) {
+			dev_err(&mtk_subdev->pdev->dev,
+				"failed to create name service endpoint\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static void mtk_rpmsg_unprepare(struct rproc_subdev *subdev)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev = to_mtk_subdev(subdev);
+
+	if (mtk_subdev->ns_ept) {
+		mtk_rpmsg_destroy_ept(mtk_subdev->ns_ept);
+		mtk_subdev->ns_ept = NULL;
+	}
+}
+
+static void mtk_rpmsg_stop(struct rproc_subdev *subdev, bool crashed)
+{
+	struct mtk_rpmsg_channel_info *info, *next;
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev = to_mtk_subdev(subdev);
+	struct device *dev = &mtk_subdev->pdev->dev;
+
+	/*
+	 * Destroy the name service endpoint here, to avoid new channel being
+	 * created after the rpmsg_unregister_device loop below.
+	 */
+	if (mtk_subdev->ns_ept) {
+		mtk_rpmsg_destroy_ept(mtk_subdev->ns_ept);
+		mtk_subdev->ns_ept = NULL;
+	}
+
+	cancel_work_sync(&mtk_subdev->register_work);
+
+	mutex_lock(&mtk_subdev->channels_lock);
+	list_for_each_entry(info, &mtk_subdev->channels, list) {
+		if (!info->registered)
+			continue;
+		if (rpmsg_unregister_device(dev, &info->info)) {
+			dev_warn(
+				dev,
+				"rpmsg_unregister_device failed for %s.%d.%d\n",
+				info->info.name, info->info.src,
+				info->info.dst);
+		}
+	}
+
+	list_for_each_entry_safe(info, next,
+				 &mtk_subdev->channels, list) {
+		list_del(&info->list);
+		kfree(info);
+	}
+	mutex_unlock(&mtk_subdev->channels_lock);
+}
+
+struct rproc_subdev *
+mtk_rpmsg_create_rproc_subdev(struct platform_device *pdev,
+			      struct mtk_rpmsg_info *info)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev;
+
+	mtk_subdev = kzalloc(sizeof(*mtk_subdev), GFP_KERNEL);
+	if (!mtk_subdev)
+		return NULL;
+
+	mtk_subdev->pdev = pdev;
+	mtk_subdev->subdev.prepare = mtk_rpmsg_prepare;
+	mtk_subdev->subdev.stop = mtk_rpmsg_stop;
+	mtk_subdev->subdev.unprepare = mtk_rpmsg_unprepare;
+	mtk_subdev->info = info;
+	INIT_LIST_HEAD(&mtk_subdev->channels);
+	INIT_WORK(&mtk_subdev->register_work,
+		  mtk_register_device_work_function);
+	mutex_init(&mtk_subdev->channels_lock);
+
+	return &mtk_subdev->subdev;
+}
+EXPORT_SYMBOL_GPL(mtk_rpmsg_create_rproc_subdev);
+
+void mtk_rpmsg_destroy_rproc_subdev(struct rproc_subdev *subdev)
+{
+	struct mtk_rpmsg_rproc_subdev *mtk_subdev = to_mtk_subdev(subdev);
+
+	kfree(mtk_subdev);
+}
+EXPORT_SYMBOL_GPL(mtk_rpmsg_destroy_rproc_subdev);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("MediaTek scp rpmsg driver");
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index d77515d8382c..34c8b6c7e095 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -240,6 +240,7 @@ config RTC_DRV_AS3722
 
 config RTC_DRV_DS1307
 	tristate "Dallas/Maxim DS1307/37/38/39/40/41, ST M41T00, EPSON RX-8025, ISL12057"
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for various compatible RTC
 	  chips (often with battery backup) connected with I2C. This driver
@@ -498,12 +499,13 @@ config RTC_DRV_M41T80_WDT
 	help
 	  If you say Y here you will get support for the
 	  watchdog timer in the ST M41T60 and M41T80 RTC chips series.
+
 config RTC_DRV_BD70528
 	tristate "ROHM BD70528 PMIC RTC"
 	depends on MFD_ROHM_BD70528 && (BD70528_WATCHDOG || !BD70528_WATCHDOG)
 	help
 	  If you say Y here you will get support for the RTC
-	  on ROHM BD70528 Power Management IC.
+	  block on ROHM BD70528 and BD71828 Power Management IC.
 
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-bd70528.
@@ -621,6 +623,7 @@ config RTC_DRV_RX8010
 
 config RTC_DRV_RX8581
 	tristate "Epson RX-8571/RX-8581"
+	select REGMAP_I2C
 	help
 	  If you say yes here you will get support for the Epson RX-8571/
 	  RX-8581.
@@ -648,6 +651,7 @@ config RTC_DRV_EM3027
 
 config RTC_DRV_RV3028
 	tristate "Micro Crystal RV3028"
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for the Micro Crystal
 	  RV3028.
@@ -676,13 +680,14 @@ config RTC_DRV_S5M
 	  will be called rtc-s5m.
 
 config RTC_DRV_SD3078
-    tristate "ZXW Shenzhen whwave SD3078"
-    help
-      If you say yes here you get support for the ZXW Shenzhen whwave
-      SD3078 RTC chips.
+	tristate "ZXW Shenzhen whwave SD3078"
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the ZXW Shenzhen whwave
+	  SD3078 RTC chips.
 
-      This driver can also be built as a module. If so, the module
-      will be called rtc-sd3078
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-sd3078
 
 endif # I2C
 
@@ -848,14 +853,14 @@ config RTC_I2C_AND_SPI
 	default m if I2C=m
 	default y if I2C=y
 	default y if SPI_MASTER=y
-	select REGMAP_I2C if I2C
-	select REGMAP_SPI if SPI_MASTER
 
 comment "SPI and I2C RTC drivers"
 
 config RTC_DRV_DS3232
 	tristate "Dallas/Maxim DS3232/DS3234"
 	depends on RTC_I2C_AND_SPI
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
 	help
 	  If you say yes here you get support for Dallas Semiconductor
 	  DS3232 and DS3234 real-time clock chips. If an interrupt is associated
@@ -875,6 +880,8 @@ config RTC_DRV_DS3232_HWMON
 config RTC_DRV_PCF2127
 	tristate "NXP PCF2127"
 	depends on RTC_I2C_AND_SPI
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
 	select WATCHDOG_CORE if WATCHDOG
 	help
 	  If you say yes here you get support for the NXP PCF2127/29 RTC
@@ -891,6 +898,8 @@ config RTC_DRV_PCF2127
 config RTC_DRV_RV3029C2
 	tristate "Micro Crystal RV3029/3049"
 	depends on RTC_I2C_AND_SPI
+	select REGMAP_I2C if I2C
+	select REGMAP_SPI if SPI_MASTER
 	help
 	  If you say yes here you get support for the Micro Crystal
 	  RV3029 and RV3049 RTC chips.
diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c
index 73830670a41f..3521d8e8dc38 100644
--- a/drivers/rtc/rtc-abx80x.c
+++ b/drivers/rtc/rtc-abx80x.c
@@ -523,12 +523,9 @@ static int abx80x_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 		if (status < 0)
 			return status;
 
-		tmp = !!(status & ABX8XX_STATUS_BLF);
+		tmp = status & ABX8XX_STATUS_BLF ? RTC_VL_BACKUP_LOW : 0;
 
-		if (copy_to_user((void __user *)arg, &tmp, sizeof(int)))
-			return -EFAULT;
-
-		return 0;
+		return put_user(tmp, (unsigned int __user *)arg);
 
 	case RTC_VL_CLR:
 		status = i2c_smbus_read_byte_data(client, ABX8XX_REG_STATUS);
diff --git a/drivers/rtc/rtc-asm9260.c b/drivers/rtc/rtc-asm9260.c
index 10064bdabdff..3ab81cdec00b 100644
--- a/drivers/rtc/rtc-asm9260.c
+++ b/drivers/rtc/rtc-asm9260.c
@@ -264,6 +264,9 @@ static int asm9260_rtc_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->iobase);
 
 	priv->clk = devm_clk_get(dev, "ahb");
+	if (IS_ERR(priv->clk))
+		return PTR_ERR(priv->clk);
+
 	ret = clk_prepare_enable(priv->clk);
 	if (ret) {
 		dev_err(dev, "Failed to enable clk!\n");
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 3b833e02a657..5e811e04cb21 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/bcd.h>
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/interrupt.h>
@@ -30,7 +31,51 @@
 #include <linux/time.h>
 #include <linux/uaccess.h>
 
-#include "rtc-at91rm9200.h"
+#define	AT91_RTC_CR		0x00			/* Control Register */
+#define		AT91_RTC_UPDTIM		BIT(0)		/* Update Request Time Register */
+#define		AT91_RTC_UPDCAL		BIT(1)		/* Update Request Calendar Register */
+
+#define	AT91_RTC_MR		0x04			/* Mode Register */
+
+#define	AT91_RTC_TIMR		0x08			/* Time Register */
+#define		AT91_RTC_SEC		GENMASK(6, 0)	/* Current Second */
+#define		AT91_RTC_MIN		GENMASK(14, 8)	/* Current Minute */
+#define		AT91_RTC_HOUR		GENMASK(21, 16)	/* Current Hour */
+#define		AT91_RTC_AMPM		BIT(22)		/* Ante Meridiem Post Meridiem Indicator */
+
+#define	AT91_RTC_CALR		0x0c			/* Calendar Register */
+#define		AT91_RTC_CENT		GENMASK(6, 0)	/* Current Century */
+#define		AT91_RTC_YEAR		GENMASK(15, 8)	/* Current Year */
+#define		AT91_RTC_MONTH		GENMASK(20, 16)	/* Current Month */
+#define		AT91_RTC_DAY		GENMASK(23, 21)	/* Current Day */
+#define		AT91_RTC_DATE		GENMASK(29, 24)	/* Current Date */
+
+#define	AT91_RTC_TIMALR		0x10			/* Time Alarm Register */
+#define		AT91_RTC_SECEN		BIT(7)		/* Second Alarm Enable */
+#define		AT91_RTC_MINEN		BIT(15)		/* Minute Alarm Enable */
+#define		AT91_RTC_HOUREN		BIT(23)		/* Hour Alarm Enable */
+
+#define	AT91_RTC_CALALR		0x14			/* Calendar Alarm Register */
+#define		AT91_RTC_MTHEN		BIT(23)		/* Month Alarm Enable */
+#define		AT91_RTC_DATEEN		BIT(31)		/* Date Alarm Enable */
+
+#define	AT91_RTC_SR		0x18			/* Status Register */
+#define		AT91_RTC_ACKUPD		BIT(0)		/* Acknowledge for Update */
+#define		AT91_RTC_ALARM		BIT(1)		/* Alarm Flag */
+#define		AT91_RTC_SECEV		BIT(2)		/* Second Event */
+#define		AT91_RTC_TIMEV		BIT(3)		/* Time Event */
+#define		AT91_RTC_CALEV		BIT(4)		/* Calendar Event */
+
+#define	AT91_RTC_SCCR		0x1c			/* Status Clear Command Register */
+#define	AT91_RTC_IER		0x20			/* Interrupt Enable Register */
+#define	AT91_RTC_IDR		0x24			/* Interrupt Disable Register */
+#define	AT91_RTC_IMR		0x28			/* Interrupt Mask Register */
+
+#define	AT91_RTC_VER		0x2c			/* Valid Entry Register */
+#define		AT91_RTC_NVTIM		BIT(0)		/* Non valid Time */
+#define		AT91_RTC_NVCAL		BIT(1)		/* Non valid Calendar */
+#define		AT91_RTC_NVTIMALR	BIT(2)		/* Non valid Time Alarm */
+#define		AT91_RTC_NVCALALR	BIT(3)		/* Non valid Calendar Alarm */
 
 #define at91_rtc_read(field) \
 	readl_relaxed(at91_rtc_regs + field)
@@ -117,20 +162,20 @@ static void at91_rtc_decodetime(unsigned int timereg, unsigned int calreg,
 	} while ((time != at91_rtc_read(timereg)) ||
 			(date != at91_rtc_read(calreg)));
 
-	tm->tm_sec  = bcd2bin((time & AT91_RTC_SEC) >> 0);
-	tm->tm_min  = bcd2bin((time & AT91_RTC_MIN) >> 8);
-	tm->tm_hour = bcd2bin((time & AT91_RTC_HOUR) >> 16);
+	tm->tm_sec  = bcd2bin(FIELD_GET(AT91_RTC_SEC, time));
+	tm->tm_min  = bcd2bin(FIELD_GET(AT91_RTC_MIN, time));
+	tm->tm_hour = bcd2bin(FIELD_GET(AT91_RTC_HOUR, time));
 
 	/*
 	 * The Calendar Alarm register does not have a field for
 	 * the year - so these will return an invalid value.
 	 */
 	tm->tm_year  = bcd2bin(date & AT91_RTC_CENT) * 100;	/* century */
-	tm->tm_year += bcd2bin((date & AT91_RTC_YEAR) >> 8);	/* year */
+	tm->tm_year += bcd2bin(FIELD_GET(AT91_RTC_YEAR, date));	/* year */
 
-	tm->tm_wday = bcd2bin((date & AT91_RTC_DAY) >> 21) - 1;	/* day of the week [0-6], Sunday=0 */
-	tm->tm_mon  = bcd2bin((date & AT91_RTC_MONTH) >> 16) - 1;
-	tm->tm_mday = bcd2bin((date & AT91_RTC_DATE) >> 24);
+	tm->tm_wday = bcd2bin(FIELD_GET(AT91_RTC_DAY, date)) - 1;	/* day of the week [0-6], Sunday=0 */
+	tm->tm_mon  = bcd2bin(FIELD_GET(AT91_RTC_MONTH, date)) - 1;
+	tm->tm_mday = bcd2bin(FIELD_GET(AT91_RTC_DATE, date));
 }
 
 /*
@@ -167,16 +212,17 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 	at91_rtc_write_idr(AT91_RTC_ACKUPD);
 
 	at91_rtc_write(AT91_RTC_TIMR,
-			  bin2bcd(tm->tm_sec) << 0
-			| bin2bcd(tm->tm_min) << 8
-			| bin2bcd(tm->tm_hour) << 16);
+			  FIELD_PREP(AT91_RTC_SEC, bin2bcd(tm->tm_sec))
+			| FIELD_PREP(AT91_RTC_MIN, bin2bcd(tm->tm_min))
+			| FIELD_PREP(AT91_RTC_HOUR, bin2bcd(tm->tm_hour)));
 
 	at91_rtc_write(AT91_RTC_CALR,
-			  bin2bcd((tm->tm_year + 1900) / 100)	/* century */
-			| bin2bcd(tm->tm_year % 100) << 8	/* year */
-			| bin2bcd(tm->tm_mon + 1) << 16		/* tm_mon starts at zero */
-			| bin2bcd(tm->tm_wday + 1) << 21	/* day of the week [0-6], Sunday=0 */
-			| bin2bcd(tm->tm_mday) << 24);
+			  FIELD_PREP(AT91_RTC_CENT,
+				     bin2bcd((tm->tm_year + 1900) / 100))
+			| FIELD_PREP(AT91_RTC_YEAR, bin2bcd(tm->tm_year % 100))
+			| FIELD_PREP(AT91_RTC_MONTH, bin2bcd(tm->tm_mon + 1))
+			| FIELD_PREP(AT91_RTC_DAY, bin2bcd(tm->tm_wday + 1))
+			| FIELD_PREP(AT91_RTC_DATE, bin2bcd(tm->tm_mday)));
 
 	/* Restart Time/Calendar */
 	cr = at91_rtc_read(AT91_RTC_CR);
@@ -211,25 +257,17 @@ static int at91_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm)
  */
 static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 {
-	struct rtc_time tm;
-
-	at91_rtc_decodetime(AT91_RTC_TIMR, AT91_RTC_CALR, &tm);
-
-	tm.tm_mon = alrm->time.tm_mon;
-	tm.tm_mday = alrm->time.tm_mday;
-	tm.tm_hour = alrm->time.tm_hour;
-	tm.tm_min = alrm->time.tm_min;
-	tm.tm_sec = alrm->time.tm_sec;
+	struct rtc_time tm = alrm->time;
 
 	at91_rtc_write_idr(AT91_RTC_ALARM);
 	at91_rtc_write(AT91_RTC_TIMALR,
-		  bin2bcd(tm.tm_sec) << 0
-		| bin2bcd(tm.tm_min) << 8
-		| bin2bcd(tm.tm_hour) << 16
+		  FIELD_PREP(AT91_RTC_SEC, bin2bcd(alrm->time.tm_sec))
+		| FIELD_PREP(AT91_RTC_MIN, bin2bcd(alrm->time.tm_min))
+		| FIELD_PREP(AT91_RTC_HOUR, bin2bcd(alrm->time.tm_hour))
 		| AT91_RTC_HOUREN | AT91_RTC_MINEN | AT91_RTC_SECEN);
 	at91_rtc_write(AT91_RTC_CALALR,
-		  bin2bcd(tm.tm_mon + 1) << 16		/* tm_mon starts at zero */
-		| bin2bcd(tm.tm_mday) << 24
+		  FIELD_PREP(AT91_RTC_MONTH, bin2bcd(alrm->time.tm_mon + 1))
+		| FIELD_PREP(AT91_RTC_DATE, bin2bcd(alrm->time.tm_mday))
 		| AT91_RTC_DATEEN | AT91_RTC_MTHEN);
 
 	if (alrm->enabled) {
@@ -254,20 +292,6 @@ static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 
 	return 0;
 }
-/*
- * Provide additional RTC information in /proc/driver/rtc
- */
-static int at91_rtc_proc(struct device *dev, struct seq_file *seq)
-{
-	unsigned long imr = at91_rtc_read_imr();
-
-	seq_printf(seq, "update_IRQ\t: %s\n",
-			(imr & AT91_RTC_ACKUPD) ? "yes" : "no");
-	seq_printf(seq, "periodic_IRQ\t: %s\n",
-			(imr & AT91_RTC_SECEV) ? "yes" : "no");
-
-	return 0;
-}
 
 /*
  * IRQ handler for the RTC
@@ -327,6 +351,12 @@ static const struct of_device_id at91_rtc_dt_ids[] = {
 		.compatible = "atmel,at91sam9x5-rtc",
 		.data = &at91sam9x5_config,
 	}, {
+		.compatible = "atmel,sama5d4-rtc",
+		.data = &at91rm9200_config,
+	}, {
+		.compatible = "atmel,sama5d2-rtc",
+		.data = &at91rm9200_config,
+	}, {
 		/* sentinel */
 	}
 };
@@ -337,7 +367,6 @@ static const struct rtc_class_ops at91_rtc_ops = {
 	.set_time	= at91_rtc_settime,
 	.read_alarm	= at91_rtc_readalarm,
 	.set_alarm	= at91_rtc_setalarm,
-	.proc		= at91_rtc_proc,
 	.alarm_irq_enable = at91_rtc_alarm_irq_enable,
 };
 
diff --git a/drivers/rtc/rtc-at91rm9200.h b/drivers/rtc/rtc-at91rm9200.h
deleted file mode 100644
index 8be5289da8e2..000000000000
--- a/drivers/rtc/rtc-at91rm9200.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * arch/arm/mach-at91/include/mach/at91_rtc.h
- *
- * Copyright (C) 2005 Ivan Kokshaysky
- * Copyright (C) SAN People
- *
- * Real Time Clock (RTC) - System peripheral registers.
- * Based on AT91RM9200 datasheet revision E.
- */
-
-#ifndef AT91_RTC_H
-#define AT91_RTC_H
-
-#define	AT91_RTC_CR		0x00			/* Control Register */
-#define		AT91_RTC_UPDTIM		(1 <<  0)		/* Update Request Time Register */
-#define		AT91_RTC_UPDCAL		(1 <<  1)		/* Update Request Calendar Register */
-#define		AT91_RTC_TIMEVSEL	(3 <<  8)		/* Time Event Selection */
-#define			AT91_RTC_TIMEVSEL_MINUTE	(0 << 8)
-#define			AT91_RTC_TIMEVSEL_HOUR		(1 << 8)
-#define			AT91_RTC_TIMEVSEL_DAY24		(2 << 8)
-#define			AT91_RTC_TIMEVSEL_DAY12		(3 << 8)
-#define		AT91_RTC_CALEVSEL	(3 << 16)		/* Calendar Event Selection */
-#define			AT91_RTC_CALEVSEL_WEEK		(0 << 16)
-#define			AT91_RTC_CALEVSEL_MONTH		(1 << 16)
-#define			AT91_RTC_CALEVSEL_YEAR		(2 << 16)
-
-#define	AT91_RTC_MR		0x04			/* Mode Register */
-#define			AT91_RTC_HRMOD		(1 <<  0)		/* 12/24 Hour Mode */
-
-#define	AT91_RTC_TIMR		0x08			/* Time Register */
-#define		AT91_RTC_SEC		(0x7f <<  0)		/* Current Second */
-#define		AT91_RTC_MIN		(0x7f <<  8)		/* Current Minute */
-#define		AT91_RTC_HOUR		(0x3f << 16)		/* Current Hour */
-#define		AT91_RTC_AMPM		(1    << 22)		/* Ante Meridiem Post Meridiem Indicator */
-
-#define	AT91_RTC_CALR		0x0c			/* Calendar Register */
-#define		AT91_RTC_CENT		(0x7f <<  0)		/* Current Century */
-#define		AT91_RTC_YEAR		(0xff <<  8)		/* Current Year */
-#define		AT91_RTC_MONTH		(0x1f << 16)		/* Current Month */
-#define		AT91_RTC_DAY		(7    << 21)		/* Current Day */
-#define		AT91_RTC_DATE		(0x3f << 24)		/* Current Date */
-
-#define	AT91_RTC_TIMALR		0x10			/* Time Alarm Register */
-#define		AT91_RTC_SECEN		(1 <<  7)		/* Second Alarm Enable */
-#define		AT91_RTC_MINEN		(1 << 15)		/* Minute Alarm Enable */
-#define		AT91_RTC_HOUREN		(1 << 23)		/* Hour Alarm Enable */
-
-#define	AT91_RTC_CALALR		0x14			/* Calendar Alarm Register */
-#define		AT91_RTC_MTHEN		(1 << 23)		/* Month Alarm Enable */
-#define		AT91_RTC_DATEEN		(1 << 31)		/* Date Alarm Enable */
-
-#define	AT91_RTC_SR		0x18			/* Status Register */
-#define		AT91_RTC_ACKUPD		(1 <<  0)		/* Acknowledge for Update */
-#define		AT91_RTC_ALARM		(1 <<  1)		/* Alarm Flag */
-#define		AT91_RTC_SECEV		(1 <<  2)		/* Second Event */
-#define		AT91_RTC_TIMEV		(1 <<  3)		/* Time Event */
-#define		AT91_RTC_CALEV		(1 <<  4)		/* Calendar Event */
-
-#define	AT91_RTC_SCCR		0x1c			/* Status Clear Command Register */
-#define	AT91_RTC_IER		0x20			/* Interrupt Enable Register */
-#define	AT91_RTC_IDR		0x24			/* Interrupt Disable Register */
-#define	AT91_RTC_IMR		0x28			/* Interrupt Mask Register */
-
-#define	AT91_RTC_VER		0x2c			/* Valid Entry Register */
-#define		AT91_RTC_NVTIM		(1 <<  0)		/* Non valid Time */
-#define		AT91_RTC_NVCAL		(1 <<  1)		/* Non valid Calendar */
-#define		AT91_RTC_NVTIMALR	(1 <<  2)		/* Non valid Time Alarm */
-#define		AT91_RTC_NVCALALR	(1 <<  3)		/* Non valid Calendar Alarm */
-
-#endif
diff --git a/drivers/rtc/rtc-bd70528.c b/drivers/rtc/rtc-bd70528.c
index 627037aa66a8..bbbb1f07c91f 100644
--- a/drivers/rtc/rtc-bd70528.c
+++ b/drivers/rtc/rtc-bd70528.c
@@ -6,6 +6,7 @@
 
 #include <linux/bcd.h>
 #include <linux/mfd/rohm-bd70528.h>
+#include <linux/mfd/rohm-bd71828.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -15,7 +16,7 @@
 /*
  * We read regs RTC_SEC => RTC_YEAR
  * this struct is ordered according to chip registers.
- * Keep it u8 only to avoid padding issues.
+ * Keep it u8 only (or packed) to avoid padding issues.
  */
 struct bd70528_rtc_day {
 	u8 sec;
@@ -36,6 +37,13 @@ struct bd70528_rtc_wake {
 	u8 ctrl;
 } __packed;
 
+struct bd71828_rtc_alm {
+	struct bd70528_rtc_data alm0;
+	struct bd70528_rtc_data alm1;
+	u8 alm_mask;
+	u8 alm1_mask;
+} __packed;
+
 struct bd70528_rtc_alm {
 	struct bd70528_rtc_data data;
 	u8 alm_mask;
@@ -43,8 +51,10 @@ struct bd70528_rtc_alm {
 } __packed;
 
 struct bd70528_rtc {
-	struct rohm_regmap_dev *mfd;
+	struct rohm_regmap_dev *parent;
 	struct device *dev;
+	u8 reg_time_start;
+	bool has_rtc_timers;
 };
 
 static int bd70528_set_wake(struct rohm_regmap_dev *bd70528,
@@ -123,14 +133,14 @@ static int bd70528_set_rtc_based_timers(struct bd70528_rtc *r, int new_state,
 {
 	int ret;
 
-	ret = bd70528_wdt_set(r->mfd, new_state & BD70528_WDT_STATE_BIT,
+	ret = bd70528_wdt_set(r->parent, new_state & BD70528_WDT_STATE_BIT,
 			      old_state);
 	if (ret) {
 		dev_err(r->dev,
 			"Failed to disable WDG for RTC setting (%d)\n", ret);
 		return ret;
 	}
-	ret = bd70528_set_elapsed_tmr(r->mfd,
+	ret = bd70528_set_elapsed_tmr(r->parent,
 				      new_state & BD70528_ELAPSED_STATE_BIT,
 				      old_state);
 	if (ret) {
@@ -138,7 +148,7 @@ static int bd70528_set_rtc_based_timers(struct bd70528_rtc *r, int new_state,
 			"Failed to disable 'elapsed timer' for RTC setting\n");
 		return ret;
 	}
-	ret = bd70528_set_wake(r->mfd, new_state & BD70528_WAKE_STATE_BIT,
+	ret = bd70528_set_wake(r->parent, new_state & BD70528_WAKE_STATE_BIT,
 			       old_state);
 	if (ret) {
 		dev_err(r->dev,
@@ -152,12 +162,18 @@ static int bd70528_set_rtc_based_timers(struct bd70528_rtc *r, int new_state,
 static int bd70528_re_enable_rtc_based_timers(struct bd70528_rtc *r,
 					      int old_state)
 {
+	if (!r->has_rtc_timers)
+		return 0;
+
 	return bd70528_set_rtc_based_timers(r, old_state, NULL);
 }
 
 static int bd70528_disable_rtc_based_timers(struct bd70528_rtc *r,
 					    int *old_state)
 {
+	if (!r->has_rtc_timers)
+		return 0;
+
 	return bd70528_set_rtc_based_timers(r, 0, old_state);
 }
 
@@ -213,22 +229,52 @@ static inline void rtc2tm(struct bd70528_rtc_data *r, struct rtc_time *t)
 	t->tm_wday = bcd2bin(r->week & BD70528_MASK_RTC_WEEK);
 }
 
+static int bd71828_set_alarm(struct device *dev, struct rtc_wkalrm *a)
+{
+	int ret;
+	struct bd71828_rtc_alm alm;
+	struct bd70528_rtc *r = dev_get_drvdata(dev);
+	struct rohm_regmap_dev *parent = r->parent;
+
+	ret = regmap_bulk_read(parent->regmap, BD71828_REG_RTC_ALM_START,
+			       &alm, sizeof(alm));
+	if (ret) {
+		dev_err(dev, "Failed to read alarm regs\n");
+		return ret;
+	}
+
+	tm2rtc(&a->time, &alm.alm0);
+
+	if (!a->enabled)
+		alm.alm_mask &= ~BD70528_MASK_ALM_EN;
+	else
+		alm.alm_mask |= BD70528_MASK_ALM_EN;
+
+	ret = regmap_bulk_write(parent->regmap, BD71828_REG_RTC_ALM_START,
+				&alm, sizeof(alm));
+	if (ret)
+		dev_err(dev, "Failed to set alarm time\n");
+
+	return ret;
+
+}
+
 static int bd70528_set_alarm(struct device *dev, struct rtc_wkalrm *a)
 {
 	struct bd70528_rtc_wake wake;
 	struct bd70528_rtc_alm alm;
 	int ret;
 	struct bd70528_rtc *r = dev_get_drvdata(dev);
-	struct rohm_regmap_dev *bd70528 = r->mfd;
+	struct rohm_regmap_dev *parent = r->parent;
 
-	ret = regmap_bulk_read(bd70528->regmap, BD70528_REG_RTC_WAKE_START,
+	ret = regmap_bulk_read(parent->regmap, BD70528_REG_RTC_WAKE_START,
 			       &wake, sizeof(wake));
 	if (ret) {
 		dev_err(dev, "Failed to read wake regs\n");
 		return ret;
 	}
 
-	ret = regmap_bulk_read(bd70528->regmap, BD70528_REG_RTC_ALM_START,
+	ret = regmap_bulk_read(parent->regmap, BD70528_REG_RTC_ALM_START,
 			       &alm, sizeof(alm));
 	if (ret) {
 		dev_err(dev, "Failed to read alarm regs\n");
@@ -246,14 +292,14 @@ static int bd70528_set_alarm(struct device *dev, struct rtc_wkalrm *a)
 		wake.ctrl &= ~BD70528_MASK_WAKE_EN;
 	}
 
-	ret = regmap_bulk_write(bd70528->regmap,
+	ret = regmap_bulk_write(parent->regmap,
 				BD70528_REG_RTC_WAKE_START, &wake,
 				sizeof(wake));
 	if (ret) {
 		dev_err(dev, "Failed to set wake time\n");
 		return ret;
 	}
-	ret = regmap_bulk_write(bd70528->regmap, BD70528_REG_RTC_ALM_START,
+	ret = regmap_bulk_write(parent->regmap, BD70528_REG_RTC_ALM_START,
 				&alm, sizeof(alm));
 	if (ret)
 		dev_err(dev, "Failed to set alarm time\n");
@@ -261,14 +307,38 @@ static int bd70528_set_alarm(struct device *dev, struct rtc_wkalrm *a)
 	return ret;
 }
 
+static int bd71828_read_alarm(struct device *dev, struct rtc_wkalrm *a)
+{
+	int ret;
+	struct bd71828_rtc_alm alm;
+	struct bd70528_rtc *r = dev_get_drvdata(dev);
+	struct rohm_regmap_dev *parent = r->parent;
+
+	ret = regmap_bulk_read(parent->regmap, BD71828_REG_RTC_ALM_START,
+			       &alm, sizeof(alm));
+	if (ret) {
+		dev_err(dev, "Failed to read alarm regs\n");
+		return ret;
+	}
+
+	rtc2tm(&alm.alm0, &a->time);
+	a->time.tm_mday = -1;
+	a->time.tm_mon = -1;
+	a->time.tm_year = -1;
+	a->enabled = !!(alm.alm_mask & BD70528_MASK_ALM_EN);
+	a->pending = 0;
+
+	return 0;
+}
+
 static int bd70528_read_alarm(struct device *dev, struct rtc_wkalrm *a)
 {
 	struct bd70528_rtc_alm alm;
 	int ret;
 	struct bd70528_rtc *r = dev_get_drvdata(dev);
-	struct rohm_regmap_dev *bd70528 = r->mfd;
+	struct rohm_regmap_dev *parent = r->parent;
 
-	ret = regmap_bulk_read(bd70528->regmap, BD70528_REG_RTC_ALM_START,
+	ret = regmap_bulk_read(parent->regmap, BD70528_REG_RTC_ALM_START,
 			       &alm, sizeof(alm));
 	if (ret) {
 		dev_err(dev, "Failed to read alarm regs\n");
@@ -290,14 +360,14 @@ static int bd70528_set_time_locked(struct device *dev, struct rtc_time *t)
 	int ret, tmpret, old_states;
 	struct bd70528_rtc_data rtc_data;
 	struct bd70528_rtc *r = dev_get_drvdata(dev);
-	struct rohm_regmap_dev *bd70528 = r->mfd;
+	struct rohm_regmap_dev *parent = r->parent;
 
 	ret = bd70528_disable_rtc_based_timers(r, &old_states);
 	if (ret)
 		return ret;
 
-	tmpret = regmap_bulk_read(bd70528->regmap,
-				  BD70528_REG_RTC_START, &rtc_data,
+	tmpret = regmap_bulk_read(parent->regmap,
+				  r->reg_time_start, &rtc_data,
 				  sizeof(rtc_data));
 	if (tmpret) {
 		dev_err(dev, "Failed to read RTC time registers\n");
@@ -305,8 +375,8 @@ static int bd70528_set_time_locked(struct device *dev, struct rtc_time *t)
 	}
 	tm2rtc(t, &rtc_data);
 
-	tmpret = regmap_bulk_write(bd70528->regmap,
-				   BD70528_REG_RTC_START, &rtc_data,
+	tmpret = regmap_bulk_write(parent->regmap,
+				   r->reg_time_start, &rtc_data,
 				   sizeof(rtc_data));
 	if (tmpret) {
 		dev_err(dev, "Failed to set RTC time\n");
@@ -321,27 +391,32 @@ renable_out:
 	return ret;
 }
 
+static int bd71828_set_time(struct device *dev, struct rtc_time *t)
+{
+	return bd70528_set_time_locked(dev, t);
+}
+
 static int bd70528_set_time(struct device *dev, struct rtc_time *t)
 {
 	int ret;
 	struct bd70528_rtc *r = dev_get_drvdata(dev);
 
-	bd70528_wdt_lock(r->mfd);
+	bd70528_wdt_lock(r->parent);
 	ret = bd70528_set_time_locked(dev, t);
-	bd70528_wdt_unlock(r->mfd);
+	bd70528_wdt_unlock(r->parent);
 	return ret;
 }
 
 static int bd70528_get_time(struct device *dev, struct rtc_time *t)
 {
 	struct bd70528_rtc *r = dev_get_drvdata(dev);
-	struct rohm_regmap_dev *bd70528 = r->mfd;
+	struct rohm_regmap_dev *parent = r->parent;
 	struct bd70528_rtc_data rtc_data;
 	int ret;
 
 	/* read the RTC date and time registers all at once */
-	ret = regmap_bulk_read(bd70528->regmap,
-			       BD70528_REG_RTC_START, &rtc_data,
+	ret = regmap_bulk_read(parent->regmap,
+			       r->reg_time_start, &rtc_data,
 			       sizeof(rtc_data));
 	if (ret) {
 		dev_err(dev, "Failed to read RTC time (err %d)\n", ret);
@@ -362,19 +437,36 @@ static int bd70528_alm_enable(struct device *dev, unsigned int enabled)
 	if (enabled)
 		enableval = 0;
 
-	bd70528_wdt_lock(r->mfd);
-	ret = bd70528_set_wake(r->mfd, enabled, NULL);
+	bd70528_wdt_lock(r->parent);
+	ret = bd70528_set_wake(r->parent, enabled, NULL);
 	if (ret) {
 		dev_err(dev, "Failed to change wake state\n");
 		goto out_unlock;
 	}
-	ret = regmap_update_bits(r->mfd->regmap, BD70528_REG_RTC_ALM_MASK,
+	ret = regmap_update_bits(r->parent->regmap, BD70528_REG_RTC_ALM_MASK,
 				 BD70528_MASK_ALM_EN, enableval);
 	if (ret)
 		dev_err(dev, "Failed to change alarm state\n");
 
 out_unlock:
-	bd70528_wdt_unlock(r->mfd);
+	bd70528_wdt_unlock(r->parent);
+	return ret;
+}
+
+static int bd71828_alm_enable(struct device *dev, unsigned int enabled)
+{
+	int ret;
+	struct bd70528_rtc *r = dev_get_drvdata(dev);
+	unsigned int enableval = BD70528_MASK_ALM_EN;
+
+	if (!enabled)
+		enableval = 0;
+
+	ret = regmap_update_bits(r->parent->regmap, BD71828_REG_RTC_ALM0_MASK,
+				 BD70528_MASK_ALM_EN, enableval);
+	if (ret)
+		dev_err(dev, "Failed to change alarm state\n");
+
 	return ret;
 }
 
@@ -386,6 +478,14 @@ static const struct rtc_class_ops bd70528_rtc_ops = {
 	.alarm_irq_enable	= bd70528_alm_enable,
 };
 
+static const struct rtc_class_ops bd71828_rtc_ops = {
+	.read_time		= bd70528_get_time,
+	.set_time		= bd71828_set_time,
+	.read_alarm		= bd71828_read_alarm,
+	.set_alarm		= bd71828_set_alarm,
+	.alarm_irq_enable	= bd71828_alm_enable,
+};
+
 static irqreturn_t alm_hndlr(int irq, void *data)
 {
 	struct rtc_device *rtc = data;
@@ -397,14 +497,19 @@ static irqreturn_t alm_hndlr(int irq, void *data)
 static int bd70528_probe(struct platform_device *pdev)
 {
 	struct bd70528_rtc *bd_rtc;
-	struct rohm_regmap_dev *mfd;
+	const struct rtc_class_ops *rtc_ops;
+	struct rohm_regmap_dev *parent;
+	const char *irq_name;
 	int ret;
 	struct rtc_device *rtc;
 	int irq;
 	unsigned int hr;
+	bool enable_main_irq = false;
+	u8 hour_reg;
+	enum rohm_chip_type chip = platform_get_device_id(pdev)->driver_data;
 
-	mfd = dev_get_drvdata(pdev->dev.parent);
-	if (!mfd) {
+	parent = dev_get_drvdata(pdev->dev.parent);
+	if (!parent) {
 		dev_err(&pdev->dev, "No MFD driver data\n");
 		return -EINVAL;
 	}
@@ -412,16 +517,39 @@ static int bd70528_probe(struct platform_device *pdev)
 	if (!bd_rtc)
 		return -ENOMEM;
 
-	bd_rtc->mfd = mfd;
+	bd_rtc->parent = parent;
 	bd_rtc->dev = &pdev->dev;
 
-	irq = platform_get_irq_byname(pdev, "bd70528-rtc-alm");
-	if (irq < 0)
+	switch (chip) {
+	case ROHM_CHIP_TYPE_BD70528:
+		irq_name = "bd70528-rtc-alm";
+		bd_rtc->has_rtc_timers = true;
+		bd_rtc->reg_time_start = BD70528_REG_RTC_START;
+		hour_reg = BD70528_REG_RTC_HOUR;
+		enable_main_irq = true;
+		rtc_ops = &bd70528_rtc_ops;
+		break;
+	case ROHM_CHIP_TYPE_BD71828:
+		irq_name = "bd71828-rtc-alm-0";
+		bd_rtc->reg_time_start = BD71828_REG_RTC_START;
+		hour_reg = BD71828_REG_RTC_HOUR;
+		rtc_ops = &bd71828_rtc_ops;
+		break;
+	default:
+		dev_err(&pdev->dev, "Unknown chip\n");
+		return -ENOENT;
+	}
+
+	irq = platform_get_irq_byname(pdev, irq_name);
+
+	if (irq < 0) {
+		dev_err(&pdev->dev, "Failed to get irq\n");
 		return irq;
+	}
 
 	platform_set_drvdata(pdev, bd_rtc);
 
-	ret = regmap_read(mfd->regmap, BD70528_REG_RTC_HOUR, &hr);
+	ret = regmap_read(parent->regmap, hour_reg, &hr);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to reag RTC clock\n");
@@ -431,10 +559,10 @@ static int bd70528_probe(struct platform_device *pdev)
 	if (!(hr & BD70528_MASK_RTC_HOUR_24H)) {
 		struct rtc_time t;
 
-		ret = bd70528_get_time(&pdev->dev, &t);
+		ret = rtc_ops->read_time(&pdev->dev, &t);
 
 		if (!ret)
-			ret = bd70528_set_time(&pdev->dev, &t);
+			ret = rtc_ops->set_time(&pdev->dev, &t);
 
 		if (ret) {
 			dev_err(&pdev->dev,
@@ -454,7 +582,7 @@ static int bd70528_probe(struct platform_device *pdev)
 
 	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
 	rtc->range_max = RTC_TIMESTAMP_END_2099;
-	rtc->ops = &bd70528_rtc_ops;
+	rtc->ops = rtc_ops;
 
 	/* Request alarm IRQ prior to registerig the RTC */
 	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, &alm_hndlr,
@@ -468,27 +596,37 @@ static int bd70528_probe(struct platform_device *pdev)
 	 *  leave them enabled as irq-controller should disable irqs
 	 *  from sub-registers when IRQ is disabled or freed.
 	 */
-	ret = regmap_update_bits(mfd->regmap,
+	if (enable_main_irq) {
+		ret = regmap_update_bits(parent->regmap,
 				 BD70528_REG_INT_MAIN_MASK,
 				 BD70528_INT_RTC_MASK, 0);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to enable RTC interrupts\n");
-		return ret;
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to enable RTC interrupts\n");
+			return ret;
+		}
 	}
 
 	return rtc_register_device(rtc);
 }
 
+static const struct platform_device_id bd718x7_rtc_id[] = {
+	{ "bd70528-rtc", ROHM_CHIP_TYPE_BD70528 },
+	{ "bd71828-rtc", ROHM_CHIP_TYPE_BD71828 },
+	{ },
+};
+MODULE_DEVICE_TABLE(platform, bd718x7_rtc_id);
+
 static struct platform_driver bd70528_rtc = {
 	.driver = {
 		.name = "bd70528-rtc"
 	},
 	.probe = bd70528_probe,
+	.id_table = bd718x7_rtc_id,
 };
 
 module_platform_driver(bd70528_rtc);
 
 MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
-MODULE_DESCRIPTION("BD70528 RTC driver");
+MODULE_DESCRIPTION("ROHM BD70528 and BD71828 PMIC RTC driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:bd70528-rtc");
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 033303708c8b..b795fe4cbd2e 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -850,7 +850,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 			rtc_cmos_int_handler = cmos_interrupt;
 
 		retval = request_irq(rtc_irq, rtc_cmos_int_handler,
-				IRQF_SHARED, dev_name(&cmos_rtc.rtc->dev),
+				0, dev_name(&cmos_rtc.rtc->dev),
 				cmos_rtc.rtc);
 		if (retval < 0) {
 			dev_dbg(dev, "IRQ %d is already in use\n", rtc_irq);
@@ -1197,8 +1197,6 @@ static void rtc_wake_off(struct device *dev)
 /* Enable use_acpi_alarm mode for Intel platforms no earlier than 2015 */
 static void use_acpi_alarm_quirks(void)
 {
-	int year;
-
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return;
 
@@ -1208,8 +1206,10 @@ static void use_acpi_alarm_quirks(void)
 	if (!is_hpet_enabled())
 		return;
 
-	if (dmi_get_date(DMI_BIOS_DATE, &year, NULL, NULL) && year >= 2015)
-		use_acpi_alarm = true;
+	if (dmi_get_bios_year() < 2015)
+		return;
+
+	use_acpi_alarm = true;
 }
 #else
 static inline void use_acpi_alarm_quirks(void) { }
@@ -1305,7 +1305,7 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
 		 * hardcode it on systems with a legacy PIC.
 		 */
 		if (nr_legacy_irqs())
-			irq = 8;
+			irq = RTC_IRQ;
 #endif
 		return cmos_do_probe(&pnp->dev,
 				pnp_get_resource(pnp, IORESOURCE_IO, 0), irq);
diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c
index d043d30f05bc..f7343c289cab 100644
--- a/drivers/rtc/rtc-cros-ec.c
+++ b/drivers/rtc/rtc-cros-ec.c
@@ -5,7 +5,6 @@
 // Author: Stephen Barber <smbarber@chromium.org>
 
 #include <linux/kernel.h>
-#include <linux/mfd/cros_ec.h>
 #include <linux/module.h>
 #include <linux/platform_data/cros_ec_commands.h>
 #include <linux/platform_data/cros_ec_proto.h>
diff --git a/drivers/rtc/rtc-ds1343.c b/drivers/rtc/rtc-ds1343.c
index d21004a68ee0..ba143423875b 100644
--- a/drivers/rtc/rtc-ds1343.c
+++ b/drivers/rtc/rtc-ds1343.c
@@ -75,7 +75,6 @@ static const struct spi_device_id ds1343_id[] = {
 MODULE_DEVICE_TABLE(spi, ds1343_id);
 
 struct ds1343_priv {
-	struct spi_device *spi;
 	struct rtc_device *rtc;
 	struct regmap *map;
 	int irq;
@@ -362,12 +361,13 @@ static int ds1343_probe(struct spi_device *spi)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->spi = spi;
-
 	/* RTC DS1347 works in spi mode 3 and
-	 * its chip select is active high
+	 * its chip select is active high. Active high should be defined as
+	 * "inverse polarity" as GPIO-based chip selects can be logically
+	 * active high but inverted by the GPIO library.
 	 */
-	spi->mode = SPI_MODE_3 | SPI_CS_HIGH;
+	spi->mode |= SPI_MODE_3;
+	spi->mode ^= SPI_CS_HIGH;
 	spi->bits_per_word = 8;
 	res = spi_setup(spi);
 	if (res)
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index 443f6d05ce29..0fb79c4afb46 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -78,7 +78,6 @@
 struct hym8563 {
 	struct i2c_client	*client;
 	struct rtc_device	*rtc;
-	bool			valid;
 #ifdef CONFIG_COMMON_CLK
 	struct clk_hw		clkout_hw;
 #endif
@@ -91,19 +90,19 @@ struct hym8563 {
 static int hym8563_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
-	struct hym8563 *hym8563 = i2c_get_clientdata(client);
 	u8 buf[7];
 	int ret;
 
-	if (!hym8563->valid) {
-		dev_warn(&client->dev, "no valid clock/calendar values available\n");
-		return -EPERM;
-	}
-
 	ret = i2c_smbus_read_i2c_block_data(client, HYM8563_SEC, 7, buf);
 	if (ret < 0)
 		return ret;
 
+	if (buf[0] & HYM8563_SEC_VL) {
+		dev_warn(&client->dev,
+			 "no valid clock/calendar values available\n");
+		return -EINVAL;
+	}
+
 	tm->tm_sec = bcd2bin(buf[0] & HYM8563_SEC_MASK);
 	tm->tm_min = bcd2bin(buf[1] & HYM8563_MIN_MASK);
 	tm->tm_hour = bcd2bin(buf[2] & HYM8563_HOUR_MASK);
@@ -118,7 +117,6 @@ static int hym8563_rtc_read_time(struct device *dev, struct rtc_time *tm)
 static int hym8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
 	struct i2c_client *client = to_i2c_client(dev);
-	struct hym8563 *hym8563 = i2c_get_clientdata(client);
 	u8 buf[7];
 	int ret;
 
@@ -157,8 +155,6 @@ static int hym8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	if (ret < 0)
 		return ret;
 
-	hym8563->valid = true;
-
 	return 0;
 }
 
@@ -556,9 +552,8 @@ static int hym8563_probe(struct i2c_client *client,
 	if (ret < 0)
 		return ret;
 
-	hym8563->valid = !(ret & HYM8563_SEC_VL);
 	dev_dbg(&client->dev, "rtc information is %s\n",
-		hym8563->valid ? "valid" : "invalid");
+		(ret & HYM8563_SEC_VL) ? "invalid" : "valid");
 
 	hym8563->rtc = devm_rtc_device_register(&client->dev, client->name,
 						&hym8563_rtc_ops, THIS_MODULE);
diff --git a/drivers/rtc/rtc-m48t35.c b/drivers/rtc/rtc-m48t35.c
index d3a75d447fce..e8194f1f01a8 100644
--- a/drivers/rtc/rtc-m48t35.c
+++ b/drivers/rtc/rtc-m48t35.c
@@ -20,6 +20,16 @@
 
 struct m48t35_rtc {
 	u8	pad[0x7ff8];    /* starts at 0x7ff8 */
+#ifdef CONFIG_SGI_IP27
+	u8	hour;
+	u8	min;
+	u8	sec;
+	u8	control;
+	u8	year;
+	u8	month;
+	u8	date;
+	u8	day;
+#else
 	u8	control;
 	u8	sec;
 	u8	min;
@@ -28,6 +38,7 @@ struct m48t35_rtc {
 	u8	date;
 	u8	month;
 	u8	year;
+#endif
 };
 
 #define M48T35_RTC_SET		0x80
diff --git a/drivers/rtc/rtc-moxart.c b/drivers/rtc/rtc-moxart.c
index 07b30a373a92..6b24ac9e1cfa 100644
--- a/drivers/rtc/rtc-moxart.c
+++ b/drivers/rtc/rtc-moxart.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * MOXA ART RTC driver.
  *
@@ -7,10 +8,6 @@
  *
  * Based on code from
  * Moxa Technology Co., Ltd. <www.moxa.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/init.h>
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index 9135e2101752..cda238dfe69b 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -297,15 +297,7 @@ static int mtk_rtc_probe(struct platform_device *pdev)
 
 	rtc->rtc_dev->ops = &mtk_rtc_ops;
 
-	ret = rtc_register_device(rtc->rtc_dev);
-	if (ret)
-		goto out_free_irq;
-
-	return 0;
-
-out_free_irq:
-	free_irq(rtc->irq, rtc);
-	return ret;
+	return rtc_register_device(rtc->rtc_dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index 988a4dfcfaf8..d4ed20fb3194 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -616,7 +616,7 @@ static int rtc_pinconf_get(struct pinctrl_dev *pctldev,
 		break;
 	default:
 		return -ENOTSUPP;
-	};
+	}
 
 	*config = pinconf_to_config_packed(param, arg);
 
diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index ba5baaca47be..4e50d6768f13 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -199,11 +199,9 @@ static int pcf2127_rtc_ioctl(struct device *dev,
 		if (ret)
 			return ret;
 
-		touser = touser & PCF2127_BIT_CTRL3_BLF ? 1 : 0;
+		touser = touser & PCF2127_BIT_CTRL3_BLF ? RTC_VL_BACKUP_LOW : 0;
 
-		if (copy_to_user((void __user *)arg, &touser, sizeof(int)))
-			return -EFAULT;
-		return 0;
+		return put_user(touser, (unsigned int __user *)arg);
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c
index 1afa6d9fa9fb..1db17ba1fc64 100644
--- a/drivers/rtc/rtc-pcf85063.c
+++ b/drivers/rtc/rtc-pcf85063.c
@@ -289,21 +289,9 @@ static int pcf85063_ioctl(struct device *dev, unsigned int cmd,
 		if (ret < 0)
 			return ret;
 
-		if (status & PCF85063_REG_SC_OS)
-			dev_warn(&pcf85063->rtc->dev, "Voltage low, data loss detected.\n");
+		status = status & PCF85063_REG_SC_OS ? RTC_VL_DATA_INVALID : 0;
 
-		status &= PCF85063_REG_SC_OS;
-
-		if (copy_to_user((void __user *)arg, &status, sizeof(int)))
-			return -EFAULT;
-
-		return 0;
-
-	case RTC_VL_CLR:
-		ret = regmap_update_bits(pcf85063->regmap, PCF85063_REG_SC,
-					 PCF85063_REG_SC_OS, 0);
-
-		return ret;
+		return put_user(status, (unsigned int __user *)arg);
 
 	default:
 		return -ENOIOCTLCMD;
diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c
index b24c908f5f06..47e0f411dd5c 100644
--- a/drivers/rtc/rtc-pcf8523.c
+++ b/drivers/rtc/rtc-pcf8523.c
@@ -282,11 +282,11 @@ static int pcf8523_rtc_ioctl(struct device *dev, unsigned int cmd,
 		ret = pcf8523_voltage_low(client);
 		if (ret < 0)
 			return ret;
+		if (ret)
+			ret = RTC_VL_BACKUP_LOW;
 
-		if (copy_to_user((void __user *)arg, &ret, sizeof(int)))
-			return -EFAULT;
+		return put_user(ret, (unsigned int __user *)arg);
 
-		return 0;
 	default:
 		return -ENOIOCTLCMD;
 	}
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index 3c322f3079b0..2dc30eafa639 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -22,8 +22,8 @@
 
 #define PCF8563_REG_ST1		0x00 /* status */
 #define PCF8563_REG_ST2		0x01
-#define PCF8563_BIT_AIE		(1 << 1)
-#define PCF8563_BIT_AF		(1 << 3)
+#define PCF8563_BIT_AIE		BIT(1)
+#define PCF8563_BIT_AF		BIT(3)
 #define PCF8563_BITS_ST2_N	(7 << 5)
 
 #define PCF8563_REG_SC		0x02 /* datetime */
@@ -76,7 +76,6 @@ struct pcf8563 {
 	 * 1970...2069.
 	 */
 	int c_polarity;	/* 0: MO_C=1 means 19xx, otherwise MO_C=1 means 20xx */
-	int voltage_low; /* incicates if a low_voltage was detected */
 
 	struct i2c_client *client;
 #ifdef CONFIG_COMMON_CLK
@@ -208,7 +207,6 @@ static int pcf8563_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		return err;
 
 	if (buf[PCF8563_REG_SC] & PCF8563_SC_LV) {
-		pcf8563->voltage_low = 1;
 		dev_err(&client->dev,
 			"low voltage detected, date/time is not reliable.\n");
 		return -EINVAL;
@@ -276,43 +274,23 @@ static int pcf8563_rtc_set_time(struct device *dev, struct rtc_time *tm)
 				9 - PCF8563_REG_SC, buf + PCF8563_REG_SC);
 }
 
-#ifdef CONFIG_RTC_INTF_DEV
 static int pcf8563_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 {
-	struct pcf8563 *pcf8563 = i2c_get_clientdata(to_i2c_client(dev));
-	struct rtc_time tm;
+	struct i2c_client *client = to_i2c_client(dev);
+	int ret;
 
 	switch (cmd) {
 	case RTC_VL_READ:
-		if (pcf8563->voltage_low)
-			dev_info(dev, "low voltage detected, date/time is not reliable.\n");
-
-		if (copy_to_user((void __user *)arg, &pcf8563->voltage_low,
-					sizeof(int)))
-			return -EFAULT;
-		return 0;
-	case RTC_VL_CLR:
-		/*
-		 * Clear the VL bit in the seconds register in case
-		 * the time has not been set already (which would
-		 * have cleared it). This does not really matter
-		 * because of the cached voltage_low value but do it
-		 * anyway for consistency.
-		 */
-		if (pcf8563_rtc_read_time(dev, &tm))
-			pcf8563_rtc_set_time(dev, &tm);
-
-		/* Clear the cached value. */
-		pcf8563->voltage_low = 0;
+		ret = i2c_smbus_read_byte_data(client, PCF8563_REG_SC);
+		if (ret < 0)
+			return ret;
 
-		return 0;
+		return put_user(ret & PCF8563_SC_LV ? RTC_VL_DATA_INVALID : 0,
+				(unsigned int __user *)arg);
 	default:
 		return -ENOIOCTLCMD;
 	}
 }
-#else
-#define pcf8563_rtc_ioctl NULL
-#endif
 
 static int pcf8563_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *tm)
 {
diff --git a/drivers/rtc/rtc-rv3028.c b/drivers/rtc/rtc-rv3028.c
index 6b7b3a69601a..a0ddc86c975a 100644
--- a/drivers/rtc/rtc-rv3028.c
+++ b/drivers/rtc/rtc-rv3028.c
@@ -428,21 +428,8 @@ static int rv3028_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 		if (ret < 0)
 			return ret;
 
-		if (status & RV3028_STATUS_PORF)
-			dev_warn(&rv3028->rtc->dev, "Voltage low, data loss detected.\n");
-
-		status &= RV3028_STATUS_PORF;
-
-		if (copy_to_user((void __user *)arg, &status, sizeof(int)))
-			return -EFAULT;
-
-		return 0;
-
-	case RTC_VL_CLR:
-		ret = regmap_update_bits(rv3028->regmap, RV3028_STATUS,
-					 RV3028_STATUS_PORF, 0);
-
-		return ret;
+		status = status & RV3028_STATUS_PORF ? RTC_VL_DATA_INVALID : 0;
+		return put_user(status, (unsigned int __user *)arg);
 
 	default:
 		return -ENOIOCTLCMD;
diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c
index 4cdf6588e1d9..62718231731b 100644
--- a/drivers/rtc/rtc-rv3029c2.c
+++ b/drivers/rtc/rtc-rv3029c2.c
@@ -109,10 +109,8 @@
 #define RV3029_CONTROL_E2P_TOV_MASK	0x3F /* XTAL turnover temp mask */
 
 /* user ram section */
-#define RV3029_USR1_RAM_PAGE		0x38
-#define RV3029_USR1_SECTION_LEN		0x04
-#define RV3029_USR2_RAM_PAGE		0x3C
-#define RV3029_USR2_SECTION_LEN		0x04
+#define RV3029_RAM_PAGE			0x38
+#define RV3029_RAM_SECTION_LEN		8
 
 struct rv3029_data {
 	struct device		*dev;
@@ -121,77 +119,13 @@ struct rv3029_data {
 	int irq;
 };
 
-static int rv3029_read_regs(struct device *dev, u8 reg, u8 *buf,
-			    unsigned int len)
-{
-	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
-
-	if ((reg > RV3029_USR1_RAM_PAGE + 7) ||
-	    (reg + len > RV3029_USR1_RAM_PAGE + 8))
-		return -EINVAL;
-
-	return regmap_bulk_read(rv3029->regmap, reg, buf, len);
-}
-
-static int rv3029_write_regs(struct device *dev, u8 reg, u8 const buf[],
-			     unsigned int len)
-{
-	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
-
-	if ((reg > RV3029_USR1_RAM_PAGE + 7) ||
-	    (reg + len > RV3029_USR1_RAM_PAGE + 8))
-		return -EINVAL;
-
-	return regmap_bulk_write(rv3029->regmap, reg, buf, len);
-}
-
-static int rv3029_update_bits(struct device *dev, u8 reg, u8 mask, u8 set)
-{
-	u8 buf;
-	int ret;
-
-	ret = rv3029_read_regs(dev, reg, &buf, 1);
-	if (ret < 0)
-		return ret;
-	buf &= ~mask;
-	buf |= set & mask;
-	ret = rv3029_write_regs(dev, reg, &buf, 1);
-	if (ret < 0)
-		return ret;
-
-	return 0;
-}
-
-static int rv3029_get_sr(struct device *dev, u8 *buf)
-{
-	int ret = rv3029_read_regs(dev, RV3029_STATUS, buf, 1);
-
-	if (ret < 0)
-		return -EIO;
-	dev_dbg(dev, "status = 0x%.2x (%d)\n", buf[0], buf[0]);
-	return 0;
-}
-
-static int rv3029_set_sr(struct device *dev, u8 val)
-{
-	u8 buf[1];
-	int sr;
-
-	buf[0] = val;
-	sr = rv3029_write_regs(dev, RV3029_STATUS, buf, 1);
-	dev_dbg(dev, "status = 0x%.2x (%d)\n", buf[0], buf[0]);
-	if (sr < 0)
-		return -EIO;
-	return 0;
-}
-
-static int rv3029_eeprom_busywait(struct device *dev)
+static int rv3029_eeprom_busywait(struct rv3029_data *rv3029)
 {
+	unsigned int sr;
 	int i, ret;
-	u8 sr;
 
 	for (i = 100; i > 0; i--) {
-		ret = rv3029_get_sr(dev, &sr);
+		ret = regmap_read(rv3029->regmap, RV3029_STATUS, &sr);
 		if (ret < 0)
 			break;
 		if (!(sr & RV3029_STATUS_EEBUSY))
@@ -199,126 +133,128 @@ static int rv3029_eeprom_busywait(struct device *dev)
 		usleep_range(1000, 10000);
 	}
 	if (i <= 0) {
-		dev_err(dev, "EEPROM busy wait timeout.\n");
+		dev_err(rv3029->dev, "EEPROM busy wait timeout.\n");
 		return -ETIMEDOUT;
 	}
 
 	return ret;
 }
 
-static int rv3029_eeprom_exit(struct device *dev)
+static int rv3029_eeprom_exit(struct rv3029_data *rv3029)
 {
 	/* Re-enable eeprom refresh */
-	return rv3029_update_bits(dev, RV3029_ONOFF_CTRL,
+	return regmap_update_bits(rv3029->regmap, RV3029_ONOFF_CTRL,
 				  RV3029_ONOFF_CTRL_EERE,
 				  RV3029_ONOFF_CTRL_EERE);
 }
 
-static int rv3029_eeprom_enter(struct device *dev)
+static int rv3029_eeprom_enter(struct rv3029_data *rv3029)
 {
+	unsigned int sr;
 	int ret;
-	u8 sr;
 
 	/* Check whether we are in the allowed voltage range. */
-	ret = rv3029_get_sr(dev, &sr);
+	ret = regmap_read(rv3029->regmap, RV3029_STATUS, &sr);
 	if (ret < 0)
 		return ret;
-	if (sr & (RV3029_STATUS_VLOW1 | RV3029_STATUS_VLOW2)) {
+	if (sr & RV3029_STATUS_VLOW2)
+		return -ENODEV;
+	if (sr & RV3029_STATUS_VLOW1) {
 		/* We clear the bits and retry once just in case
 		 * we had a brown out in early startup.
 		 */
-		sr &= ~RV3029_STATUS_VLOW1;
-		sr &= ~RV3029_STATUS_VLOW2;
-		ret = rv3029_set_sr(dev, sr);
+		ret = regmap_update_bits(rv3029->regmap, RV3029_STATUS,
+					 RV3029_STATUS_VLOW1, 0);
 		if (ret < 0)
 			return ret;
 		usleep_range(1000, 10000);
-		ret = rv3029_get_sr(dev, &sr);
+		ret = regmap_read(rv3029->regmap, RV3029_STATUS, &sr);
 		if (ret < 0)
 			return ret;
-		if (sr & (RV3029_STATUS_VLOW1 | RV3029_STATUS_VLOW2)) {
-			dev_err(dev,
+		if (sr & RV3029_STATUS_VLOW1) {
+			dev_err(rv3029->dev,
 				"Supply voltage is too low to safely access the EEPROM.\n");
 			return -ENODEV;
 		}
 	}
 
 	/* Disable eeprom refresh. */
-	ret = rv3029_update_bits(dev, RV3029_ONOFF_CTRL, RV3029_ONOFF_CTRL_EERE,
-				 0);
+	ret = regmap_update_bits(rv3029->regmap, RV3029_ONOFF_CTRL,
+				 RV3029_ONOFF_CTRL_EERE, 0);
 	if (ret < 0)
 		return ret;
 
 	/* Wait for any previous eeprom accesses to finish. */
-	ret = rv3029_eeprom_busywait(dev);
+	ret = rv3029_eeprom_busywait(rv3029);
 	if (ret < 0)
-		rv3029_eeprom_exit(dev);
+		rv3029_eeprom_exit(rv3029);
 
 	return ret;
 }
 
-static int rv3029_eeprom_read(struct device *dev, u8 reg,
+static int rv3029_eeprom_read(struct rv3029_data *rv3029, u8 reg,
 			      u8 buf[], size_t len)
 {
 	int ret, err;
 
-	err = rv3029_eeprom_enter(dev);
+	err = rv3029_eeprom_enter(rv3029);
 	if (err < 0)
 		return err;
 
-	ret = rv3029_read_regs(dev, reg, buf, len);
+	ret = regmap_bulk_read(rv3029->regmap, reg, buf, len);
 
-	err = rv3029_eeprom_exit(dev);
+	err = rv3029_eeprom_exit(rv3029);
 	if (err < 0)
 		return err;
 
 	return ret;
 }
 
-static int rv3029_eeprom_write(struct device *dev, u8 reg,
+static int rv3029_eeprom_write(struct rv3029_data *rv3029, u8 reg,
 			       u8 const buf[], size_t len)
 {
+	unsigned int tmp;
 	int ret, err;
 	size_t i;
-	u8 tmp;
 
-	err = rv3029_eeprom_enter(dev);
+	err = rv3029_eeprom_enter(rv3029);
 	if (err < 0)
 		return err;
 
 	for (i = 0; i < len; i++, reg++) {
-		ret = rv3029_read_regs(dev, reg, &tmp, 1);
+		ret = regmap_read(rv3029->regmap, reg, &tmp);
 		if (ret < 0)
 			break;
 		if (tmp != buf[i]) {
-			ret = rv3029_write_regs(dev, reg, &buf[i], 1);
+			tmp = buf[i];
+			ret = regmap_write(rv3029->regmap, reg, tmp);
 			if (ret < 0)
 				break;
 		}
-		ret = rv3029_eeprom_busywait(dev);
+		ret = rv3029_eeprom_busywait(rv3029);
 		if (ret < 0)
 			break;
 	}
 
-	err = rv3029_eeprom_exit(dev);
+	err = rv3029_eeprom_exit(rv3029);
 	if (err < 0)
 		return err;
 
 	return ret;
 }
 
-static int rv3029_eeprom_update_bits(struct device *dev,
+static int rv3029_eeprom_update_bits(struct rv3029_data *rv3029,
 				     u8 reg, u8 mask, u8 set)
 {
 	u8 buf;
 	int ret;
 
-	ret = rv3029_eeprom_read(dev, reg, &buf, 1);
+	ret = rv3029_eeprom_read(rv3029, reg, &buf, 1);
 	if (ret < 0)
 		return ret;
 	buf &= ~mask;
 	buf |= set & mask;
-	ret = rv3029_eeprom_write(dev, reg, &buf, 1);
+	ret = rv3029_eeprom_write(rv3029, reg, &buf, 1);
 	if (ret < 0)
 		return ret;
 
@@ -330,20 +266,20 @@ static irqreturn_t rv3029_handle_irq(int irq, void *dev_id)
 	struct device *dev = dev_id;
 	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	struct mutex *lock = &rv3029->rtc->ops_lock;
+	unsigned int flags, controls;
 	unsigned long events = 0;
-	u8 flags, controls;
 	int ret;
 
 	mutex_lock(lock);
 
-	ret = rv3029_read_regs(dev, RV3029_IRQ_CTRL, &controls, 1);
+	ret = regmap_read(rv3029->regmap, RV3029_IRQ_CTRL, &controls);
 	if (ret) {
 		dev_warn(dev, "Read IRQ Control Register error %d\n", ret);
 		mutex_unlock(lock);
 		return IRQ_NONE;
 	}
 
-	ret = rv3029_read_regs(dev, RV3029_IRQ_FLAGS, &flags, 1);
+	ret = regmap_read(rv3029->regmap, RV3029_IRQ_FLAGS, &flags);
 	if (ret) {
 		dev_warn(dev, "Read IRQ Flags Register error %d\n", ret);
 		mutex_unlock(lock);
@@ -358,8 +294,8 @@ static irqreturn_t rv3029_handle_irq(int irq, void *dev_id)
 
 	if (events) {
 		rtc_update_irq(rv3029->rtc, 1, events);
-		rv3029_write_regs(dev, RV3029_IRQ_FLAGS, &flags, 1);
-		rv3029_write_regs(dev, RV3029_IRQ_CTRL, &controls, 1);
+		regmap_write(rv3029->regmap, RV3029_IRQ_FLAGS, flags);
+		regmap_write(rv3029->regmap, RV3029_IRQ_CTRL, controls);
 	}
 	mutex_unlock(lock);
 
@@ -368,22 +304,22 @@ static irqreturn_t rv3029_handle_irq(int irq, void *dev_id)
 
 static int rv3029_read_time(struct device *dev, struct rtc_time *tm)
 {
-	u8 buf[1];
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
+	unsigned int sr;
 	int ret;
 	u8 regs[RV3029_WATCH_SECTION_LEN] = { 0, };
 
-	ret = rv3029_get_sr(dev, buf);
-	if (ret < 0) {
-		dev_err(dev, "%s: reading SR failed\n", __func__);
-		return -EIO;
-	}
+	ret = regmap_read(rv3029->regmap, RV3029_STATUS, &sr);
+	if (ret < 0)
+		return ret;
+
+	if (sr & (RV3029_STATUS_VLOW2 | RV3029_STATUS_PON))
+		return -EINVAL;
 
-	ret = rv3029_read_regs(dev, RV3029_W_SEC, regs,
+	ret = regmap_bulk_read(rv3029->regmap, RV3029_W_SEC, regs,
 			       RV3029_WATCH_SECTION_LEN);
-	if (ret < 0) {
-		dev_err(dev, "%s: reading RTC section failed\n", __func__);
+	if (ret < 0)
 		return ret;
-	}
 
 	tm->tm_sec = bcd2bin(regs[RV3029_W_SEC - RV3029_W_SEC]);
 	tm->tm_min = bcd2bin(regs[RV3029_W_MINUTES - RV3029_W_SEC]);
@@ -411,34 +347,24 @@ static int rv3029_read_time(struct device *dev, struct rtc_time *tm)
 
 static int rv3029_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	struct rtc_time *const tm = &alarm->time;
+	unsigned int controls, flags;
 	int ret;
-	u8 regs[8], controls, flags;
-
-	ret = rv3029_get_sr(dev, regs);
-	if (ret < 0) {
-		dev_err(dev, "%s: reading SR failed\n", __func__);
-		return -EIO;
-	}
+	u8 regs[8];
 
-	ret = rv3029_read_regs(dev, RV3029_A_SC, regs,
+	ret = regmap_bulk_read(rv3029->regmap, RV3029_A_SC, regs,
 			       RV3029_ALARM_SECTION_LEN);
-
-	if (ret < 0) {
-		dev_err(dev, "%s: reading alarm section failed\n", __func__);
+	if (ret < 0)
 		return ret;
-	}
 
-	ret = rv3029_read_regs(dev, RV3029_IRQ_CTRL, &controls, 1);
-	if (ret) {
-		dev_err(dev, "Read IRQ Control Register error %d\n", ret);
+	ret = regmap_read(rv3029->regmap, RV3029_IRQ_CTRL, &controls);
+	if (ret)
 		return ret;
-	}
-	ret = rv3029_read_regs(dev, RV3029_IRQ_FLAGS, &flags, 1);
-	if (ret < 0) {
-		dev_err(dev, "Read IRQ Flags Register error %d\n", ret);
+
+	ret = regmap_read(rv3029->regmap, RV3029_IRQ_FLAGS, &flags);
+	if (ret < 0)
 		return ret;
-	}
 
 	tm->tm_sec = bcd2bin(regs[RV3029_A_SC - RV3029_A_SC] & 0x7f);
 	tm->tm_min = bcd2bin(regs[RV3029_A_MN - RV3029_A_SC] & 0x7f);
@@ -456,50 +382,20 @@ static int rv3029_read_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 
 static int rv3029_alarm_irq_enable(struct device *dev, unsigned int enable)
 {
-	int ret;
-	u8 controls;
-
-	ret = rv3029_read_regs(dev, RV3029_IRQ_CTRL, &controls, 1);
-	if (ret < 0) {
-		dev_warn(dev, "Read IRQ Control Register error %d\n", ret);
-		return ret;
-	}
-
-	/* enable/disable AIE irq */
-	if (enable)
-		controls |= RV3029_IRQ_CTRL_AIE;
-	else
-		controls &= ~RV3029_IRQ_CTRL_AIE;
-
-	ret = rv3029_write_regs(dev, RV3029_IRQ_CTRL, &controls, 1);
-	if (ret < 0) {
-		dev_err(dev, "can't update INT reg\n");
-		return ret;
-	}
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 
-	return 0;
+	return regmap_update_bits(rv3029->regmap, RV3029_IRQ_CTRL,
+				  RV3029_IRQ_CTRL_AIE,
+				  enable ? RV3029_IRQ_CTRL_AIE : 0);
 }
 
 static int rv3029_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	struct rtc_time *const tm = &alarm->time;
 	int ret;
 	u8 regs[8];
 
-	/*
-	 * The clock has an 8 bit wide bcd-coded register (they never learn)
-	 * for the year. tm_year is an offset from 1900 and we are interested
-	 * in the 2000-2099 range, so any value less than 100 is invalid.
-	*/
-	if (tm->tm_year < 100)
-		return -EINVAL;
-
-	ret = rv3029_get_sr(dev, regs);
-	if (ret < 0) {
-		dev_err(dev, "%s: reading SR failed\n", __func__);
-		return -EIO;
-	}
-
 	/* Activate all the alarms with AE_x bit */
 	regs[RV3029_A_SC - RV3029_A_SC] = bin2bcd(tm->tm_sec) | RV3029_A_AE_X;
 	regs[RV3029_A_MN - RV3029_A_SC] = bin2bcd(tm->tm_min) | RV3029_A_AE_X;
@@ -515,39 +411,20 @@ static int rv3029_set_alarm(struct device *dev, struct rtc_wkalrm *alarm)
 		| RV3029_A_AE_X;
 
 	/* Write the alarm */
-	ret = rv3029_write_regs(dev, RV3029_A_SC, regs,
+	ret = regmap_bulk_write(rv3029->regmap, RV3029_A_SC, regs,
 				RV3029_ALARM_SECTION_LEN);
 	if (ret < 0)
 		return ret;
 
-	if (alarm->enabled) {
-		/* enable AIE irq */
-		ret = rv3029_alarm_irq_enable(dev, 1);
-		if (ret)
-			return ret;
-	} else {
-		/* disable AIE irq */
-		ret = rv3029_alarm_irq_enable(dev, 0);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	return rv3029_alarm_irq_enable(dev, alarm->enabled);
 }
 
 static int rv3029_set_time(struct device *dev, struct rtc_time *tm)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	u8 regs[8];
 	int ret;
 
-	/*
-	 * The clock has an 8 bit wide bcd-coded register (they never learn)
-	 * for the year. tm_year is an offset from 1900 and we are interested
-	 * in the 2000-2099 range, so any value less than 100 is invalid.
-	*/
-	if (tm->tm_year < 100)
-		return -EINVAL;
-
 	regs[RV3029_W_SEC - RV3029_W_SEC] = bin2bcd(tm->tm_sec);
 	regs[RV3029_W_MINUTES - RV3029_W_SEC] = bin2bcd(tm->tm_min);
 	regs[RV3029_W_HOURS - RV3029_W_SEC] = bin2bcd(tm->tm_hour);
@@ -556,24 +433,55 @@ static int rv3029_set_time(struct device *dev, struct rtc_time *tm)
 	regs[RV3029_W_DAYS - RV3029_W_SEC] = bin2bcd(tm->tm_wday + 1) & 0x7;
 	regs[RV3029_W_YEARS - RV3029_W_SEC] = bin2bcd(tm->tm_year - 100);
 
-	ret = rv3029_write_regs(dev, RV3029_W_SEC, regs,
+	ret = regmap_bulk_write(rv3029->regmap, RV3029_W_SEC, regs,
 				RV3029_WATCH_SECTION_LEN);
 	if (ret < 0)
 		return ret;
 
-	ret = rv3029_get_sr(dev, regs);
-	if (ret < 0) {
-		dev_err(dev, "%s: reading SR failed\n", __func__);
-		return ret;
-	}
-	/* clear PON bit */
-	ret = rv3029_set_sr(dev, (regs[0] & ~RV3029_STATUS_PON));
-	if (ret < 0) {
-		dev_err(dev, "%s: reading SR failed\n", __func__);
-		return ret;
+	/* clear PON and VLOW2 bits */
+	return regmap_update_bits(rv3029->regmap, RV3029_STATUS,
+				  RV3029_STATUS_PON | RV3029_STATUS_VLOW2, 0);
+}
+
+static int rv3029_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
+{
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
+	unsigned long vl = 0;
+	int sr, ret = 0;
+
+	switch (cmd) {
+	case RTC_VL_READ:
+		ret = regmap_read(rv3029->regmap, RV3029_STATUS, &sr);
+		if (ret < 0)
+			return ret;
+
+		if (sr & RV3029_STATUS_VLOW1)
+			vl = RTC_VL_ACCURACY_LOW;
+
+		if (sr & (RV3029_STATUS_VLOW2 | RV3029_STATUS_PON))
+			vl |= RTC_VL_DATA_INVALID;
+
+		return put_user(vl, (unsigned int __user *)arg);
+
+	case RTC_VL_CLR:
+		return regmap_update_bits(rv3029->regmap, RV3029_STATUS,
+					  RV3029_STATUS_VLOW1, 0);
+
+	default:
+		return -ENOIOCTLCMD;
 	}
+}
 
-	return 0;
+static int rv3029_nvram_write(void *priv, unsigned int offset, void *val,
+			      size_t bytes)
+{
+	return regmap_bulk_write(priv, RV3029_RAM_PAGE + offset, val, bytes);
+}
+
+static int rv3029_nvram_read(void *priv, unsigned int offset, void *val,
+			     size_t bytes)
+{
+	return regmap_bulk_read(priv, RV3029_RAM_PAGE + offset, val, bytes);
 }
 
 static const struct rv3029_trickle_tab_elem {
@@ -635,6 +543,7 @@ static const struct rv3029_trickle_tab_elem {
 
 static void rv3029_trickle_config(struct device *dev)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	struct device_node *of_node = dev->of_node;
 	const struct rv3029_trickle_tab_elem *elem;
 	int i, err;
@@ -661,7 +570,7 @@ static void rv3029_trickle_config(struct device *dev)
 			 "Trickle charger enabled at %d ohms resistance.\n",
 			 elem->r);
 	}
-	err = rv3029_eeprom_update_bits(dev, RV3029_CONTROL_E2P_EECTRL,
+	err = rv3029_eeprom_update_bits(rv3029, RV3029_CONTROL_E2P_EECTRL,
 					RV3029_TRICKLE_MASK,
 					trickle_set_bits);
 	if (err < 0)
@@ -670,12 +579,12 @@ static void rv3029_trickle_config(struct device *dev)
 
 #ifdef CONFIG_RTC_DRV_RV3029_HWMON
 
-static int rv3029_read_temp(struct device *dev, int *temp_mC)
+static int rv3029_read_temp(struct rv3029_data *rv3029, int *temp_mC)
 {
+	unsigned int temp;
 	int ret;
-	u8 temp;
 
-	ret = rv3029_read_regs(dev, RV3029_TEMP_PAGE, &temp, 1);
+	ret = regmap_read(rv3029->regmap, RV3029_TEMP_PAGE, &temp);
 	if (ret < 0)
 		return ret;
 
@@ -688,9 +597,10 @@ static ssize_t rv3029_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
 				      char *buf)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	int ret, temp_mC;
 
-	ret = rv3029_read_temp(dev, &temp_mC);
+	ret = rv3029_read_temp(rv3029, &temp_mC);
 	if (ret < 0)
 		return ret;
 
@@ -702,9 +612,10 @@ static ssize_t rv3029_hwmon_set_update_interval(struct device *dev,
 						const char *buf,
 						size_t count)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
+	unsigned int th_set_bits = 0;
 	unsigned long interval_ms;
 	int ret;
-	u8 th_set_bits = 0;
 
 	ret = kstrtoul(buf, 10, &interval_ms);
 	if (ret < 0)
@@ -715,7 +626,7 @@ static ssize_t rv3029_hwmon_set_update_interval(struct device *dev,
 		if (interval_ms >= 16000)
 			th_set_bits |= RV3029_EECTRL_THP;
 	}
-	ret = rv3029_eeprom_update_bits(dev, RV3029_CONTROL_E2P_EECTRL,
+	ret = rv3029_eeprom_update_bits(rv3029, RV3029_CONTROL_E2P_EECTRL,
 					RV3029_EECTRL_THE | RV3029_EECTRL_THP,
 					th_set_bits);
 	if (ret < 0)
@@ -728,10 +639,11 @@ static ssize_t rv3029_hwmon_show_update_interval(struct device *dev,
 						 struct device_attribute *attr,
 						 char *buf)
 {
+	struct rv3029_data *rv3029 = dev_get_drvdata(dev);
 	int ret, interval_ms;
 	u8 eectrl;
 
-	ret = rv3029_eeprom_read(dev, RV3029_CONTROL_E2P_EECTRL,
+	ret = rv3029_eeprom_read(rv3029, RV3029_CONTROL_E2P_EECTRL,
 				 &eectrl, 1);
 	if (ret < 0)
 		return ret;
@@ -785,14 +697,23 @@ static void rv3029_hwmon_register(struct device *dev, const char *name)
 static struct rtc_class_ops rv3029_rtc_ops = {
 	.read_time	= rv3029_read_time,
 	.set_time	= rv3029_set_time,
+	.ioctl		= rv3029_ioctl,
 };
 
 static int rv3029_probe(struct device *dev, struct regmap *regmap, int irq,
 			const char *name)
 {
 	struct rv3029_data *rv3029;
+	struct nvmem_config nvmem_cfg = {
+		.name = "rv3029_nvram",
+		.word_size = 1,
+		.stride = 1,
+		.size = RV3029_RAM_SECTION_LEN,
+		.type = NVMEM_TYPE_BATTERY_BACKED,
+		.reg_read = rv3029_nvram_read,
+		.reg_write = rv3029_nvram_write,
+	};
 	int rc = 0;
-	u8 buf[1];
 
 	rv3029 = devm_kzalloc(dev, sizeof(*rv3029), GFP_KERNEL);
 	if (!rv3029)
@@ -803,21 +724,12 @@ static int rv3029_probe(struct device *dev, struct regmap *regmap, int irq,
 	rv3029->dev = dev;
 	dev_set_drvdata(dev, rv3029);
 
-	rc = rv3029_get_sr(dev, buf);
-	if (rc < 0) {
-		dev_err(dev, "reading status failed\n");
-		return rc;
-	}
-
 	rv3029_trickle_config(dev);
 	rv3029_hwmon_register(dev, name);
 
-	rv3029->rtc = devm_rtc_device_register(dev, name, &rv3029_rtc_ops,
-					       THIS_MODULE);
-	if (IS_ERR(rv3029->rtc)) {
-		dev_err(dev, "unable to register the class device\n");
+	rv3029->rtc = devm_rtc_allocate_device(dev);
+	if (IS_ERR(rv3029->rtc))
 		return PTR_ERR(rv3029->rtc);
-	}
 
 	if (rv3029->irq > 0) {
 		rc = devm_request_threaded_irq(dev, rv3029->irq,
@@ -834,20 +746,48 @@ static int rv3029_probe(struct device *dev, struct regmap *regmap, int irq,
 		}
 	}
 
+	rv3029->rtc->ops = &rv3029_rtc_ops;
+	rv3029->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rv3029->rtc->range_max = RTC_TIMESTAMP_END_2079;
+
+	rc = rtc_register_device(rv3029->rtc);
+	if (rc)
+		return rc;
+
+	nvmem_cfg.priv = rv3029->regmap;
+	rtc_nvmem_register(rv3029->rtc, &nvmem_cfg);
+
 	return 0;
 }
 
+static const struct regmap_range rv3029_holes_range[] = {
+	regmap_reg_range(0x05, 0x07),
+	regmap_reg_range(0x0f, 0x0f),
+	regmap_reg_range(0x17, 0x17),
+	regmap_reg_range(0x1a, 0x1f),
+	regmap_reg_range(0x21, 0x27),
+	regmap_reg_range(0x34, 0x37),
+};
+
+static const struct regmap_access_table rv3029_regs = {
+	.no_ranges =	rv3029_holes_range,
+	.n_no_ranges =	ARRAY_SIZE(rv3029_holes_range),
+};
+
+static const struct regmap_config config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.rd_table = &rv3029_regs,
+	.wr_table = &rv3029_regs,
+	.max_register = 0x3f,
+};
+
 #if IS_ENABLED(CONFIG_I2C)
 
 static int rv3029_i2c_probe(struct i2c_client *client,
 			    const struct i2c_device_id *id)
 {
 	struct regmap *regmap;
-	static const struct regmap_config config = {
-		.reg_bits = 8,
-		.val_bits = 8,
-	};
-
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_I2C_BLOCK |
 				     I2C_FUNC_SMBUS_BYTE)) {
 		dev_err(&client->dev, "Adapter does not support SMBUS_I2C_BLOCK or SMBUS_I2C_BYTE\n");
@@ -855,11 +795,8 @@ static int rv3029_i2c_probe(struct i2c_client *client,
 	}
 
 	regmap = devm_regmap_init_i2c(client, &config);
-	if (IS_ERR(regmap)) {
-		dev_err(&client->dev, "%s: regmap allocation failed: %ld\n",
-			__func__, PTR_ERR(regmap));
+	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
-	}
 
 	return rv3029_probe(&client->dev, regmap, client->irq, client->name);
 }
@@ -873,24 +810,20 @@ MODULE_DEVICE_TABLE(i2c, rv3029_id);
 
 static const struct of_device_id rv3029_of_match[] = {
 	{ .compatible = "microcrystal,rv3029" },
-	/* Backward compatibility only, do not use compatibles below: */
-	{ .compatible = "rv3029" },
-	{ .compatible = "rv3029c2" },
-	{ .compatible = "mc,rv3029c2" },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, rv3029_of_match);
 
 static struct i2c_driver rv3029_driver = {
 	.driver = {
-		.name = "rtc-rv3029c2",
+		.name = "rv3029",
 		.of_match_table = of_match_ptr(rv3029_of_match),
 	},
 	.probe		= rv3029_i2c_probe,
 	.id_table	= rv3029_id,
 };
 
-static int rv3029_register_driver(void)
+static int __init rv3029_register_driver(void)
 {
 	return i2c_add_driver(&rv3029_driver);
 }
@@ -902,7 +835,7 @@ static void rv3029_unregister_driver(void)
 
 #else
 
-static int rv3029_register_driver(void)
+static int __init rv3029_register_driver(void)
 {
 	return 0;
 }
@@ -917,18 +850,11 @@ static void rv3029_unregister_driver(void)
 
 static int rv3049_probe(struct spi_device *spi)
 {
-	static const struct regmap_config config = {
-		.reg_bits = 8,
-		.val_bits = 8,
-	};
 	struct regmap *regmap;
 
 	regmap = devm_regmap_init_spi(spi, &config);
-	if (IS_ERR(regmap)) {
-		dev_err(&spi->dev, "%s: regmap allocation failed: %ld\n",
-			__func__, PTR_ERR(regmap));
+	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
-	}
 
 	return rv3029_probe(&spi->dev, regmap, spi->irq, "rv3049");
 }
@@ -940,24 +866,24 @@ static struct spi_driver rv3049_driver = {
 	.probe   = rv3049_probe,
 };
 
-static int rv3049_register_driver(void)
+static int __init rv3049_register_driver(void)
 {
 	return spi_register_driver(&rv3049_driver);
 }
 
-static void rv3049_unregister_driver(void)
+static void __exit rv3049_unregister_driver(void)
 {
 	spi_unregister_driver(&rv3049_driver);
 }
 
 #else
 
-static int rv3049_register_driver(void)
+static int __init rv3049_register_driver(void)
 {
 	return 0;
 }
 
-static void rv3049_unregister_driver(void)
+static void __exit rv3049_unregister_driver(void)
 {
 }
 
@@ -968,16 +894,12 @@ static int __init rv30x9_init(void)
 	int ret;
 
 	ret = rv3029_register_driver();
-	if (ret) {
-		pr_err("Failed to register rv3029 driver: %d\n", ret);
+	if (ret)
 		return ret;
-	}
 
 	ret = rv3049_register_driver();
-	if (ret) {
-		pr_err("Failed to register rv3049 driver: %d\n", ret);
+	if (ret)
 		rv3029_unregister_driver();
-	}
 
 	return ret;
 }
diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c
index 4960f0a2b249..93c3a6b627bd 100644
--- a/drivers/rtc/rtc-rv8803.c
+++ b/drivers/rtc/rtc-rv8803.c
@@ -411,6 +411,7 @@ static int rv8803_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct rv8803_data *rv8803 = dev_get_drvdata(dev);
+	unsigned int vl = 0;
 	int flags, ret = 0;
 
 	switch (cmd) {
@@ -419,18 +420,15 @@ static int rv8803_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 		if (flags < 0)
 			return flags;
 
-		if (flags & RV8803_FLAG_V1F)
+		if (flags & RV8803_FLAG_V1F) {
 			dev_warn(&client->dev, "Voltage low, temperature compensation stopped.\n");
+			vl = RTC_VL_ACCURACY_LOW;
+		}
 
 		if (flags & RV8803_FLAG_V2F)
-			dev_warn(&client->dev, "Voltage low, data loss detected.\n");
-
-		flags &= RV8803_FLAG_V1F | RV8803_FLAG_V2F;
+			vl |= RTC_VL_DATA_INVALID;
 
-		if (copy_to_user((void __user *)arg, &flags, sizeof(int)))
-			return -EFAULT;
-
-		return 0;
+		return put_user(vl, (unsigned int __user *)arg);
 
 	case RTC_VL_CLR:
 		mutex_lock(&rv8803->flags_lock);
@@ -440,7 +438,7 @@ static int rv8803_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 			return flags;
 		}
 
-		flags &= ~(RV8803_FLAG_V1F | RV8803_FLAG_V2F);
+		flags &= ~RV8803_FLAG_V1F;
 		ret = rv8803_write_reg(client, RV8803_FLAG, flags);
 		mutex_unlock(&rv8803->flags_lock);
 		if (ret)
diff --git a/drivers/rtc/rtc-rx8010.c b/drivers/rtc/rtc-rx8010.c
index 8102469e27c0..fe010151ec8f 100644
--- a/drivers/rtc/rtc-rx8010.c
+++ b/drivers/rtc/rtc-rx8010.c
@@ -389,9 +389,8 @@ static int rx8010_alarm_irq_enable(struct device *dev,
 
 static int rx8010_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 {
-	struct i2c_client *client = to_i2c_client(dev);
 	struct rx8010_data *rx8010 = dev_get_drvdata(dev);
-	int ret, tmp;
+	int tmp;
 	int flagreg;
 
 	switch (cmd) {
@@ -400,24 +399,8 @@ static int rx8010_ioctl(struct device *dev, unsigned int cmd, unsigned long arg)
 		if (flagreg < 0)
 			return flagreg;
 
-		tmp = !!(flagreg & RX8010_FLAG_VLF);
-		if (copy_to_user((void __user *)arg, &tmp, sizeof(int)))
-			return -EFAULT;
-
-		return 0;
-
-	case RTC_VL_CLR:
-		flagreg = i2c_smbus_read_byte_data(rx8010->client, RX8010_FLAG);
-		if (flagreg < 0) {
-			return flagreg;
-		}
-
-		flagreg &= ~RX8010_FLAG_VLF;
-		ret = i2c_smbus_write_byte_data(client, RX8010_FLAG, flagreg);
-		if (ret < 0)
-			return ret;
-
-		return 0;
+		tmp = flagreg & RX8010_FLAG_VLF ? RTC_VL_DATA_INVALID : 0;
+		return put_user(tmp, (unsigned int __user *)arg);
 
 	default:
 		return -ENOIOCTLCMD;
@@ -482,7 +465,7 @@ static int rx8010_probe(struct i2c_client *client,
 
 	rx8010->rtc->max_user_freq = 1;
 
-	return err;
+	return 0;
 }
 
 static struct i2c_driver rx8010_driver = {
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index b9bda10589e0..a24f85893f90 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -67,7 +67,6 @@ static const struct i2c_device_id rx8025_id[] = {
 MODULE_DEVICE_TABLE(i2c, rx8025_id);
 
 struct rx8025_data {
-	struct i2c_client *client;
 	struct rtc_device *rtc;
 	u8 ctrl1;
 };
@@ -103,10 +102,10 @@ static s32 rx8025_write_regs(const struct i2c_client *client,
 
 static int rx8025_check_validity(struct device *dev)
 {
-	struct rx8025_data *rx8025 = dev_get_drvdata(dev);
+	struct i2c_client *client = to_i2c_client(dev);
 	int ctrl2;
 
-	ctrl2 = rx8025_read_reg(rx8025->client, RX8025_REG_CTRL2);
+	ctrl2 = rx8025_read_reg(client, RX8025_REG_CTRL2);
 	if (ctrl2 < 0)
 		return ctrl2;
 
@@ -178,6 +177,7 @@ out:
 
 static int rx8025_get_time(struct device *dev, struct rtc_time *dt)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct rx8025_data *rx8025 = dev_get_drvdata(dev);
 	u8 date[7];
 	int err;
@@ -186,7 +186,7 @@ static int rx8025_get_time(struct device *dev, struct rtc_time *dt)
 	if (err)
 		return err;
 
-	err = rx8025_read_regs(rx8025->client, RX8025_REG_SEC, 7, date);
+	err = rx8025_read_regs(client, RX8025_REG_SEC, 7, date);
 	if (err)
 		return err;
 
@@ -211,6 +211,7 @@ static int rx8025_get_time(struct device *dev, struct rtc_time *dt)
 
 static int rx8025_set_time(struct device *dev, struct rtc_time *dt)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct rx8025_data *rx8025 = dev_get_drvdata(dev);
 	u8 date[7];
 	int ret;
@@ -237,11 +238,11 @@ static int rx8025_set_time(struct device *dev, struct rtc_time *dt)
 
 	dev_dbg(dev, "%s: write %7ph\n", __func__, date);
 
-	ret = rx8025_write_regs(rx8025->client, RX8025_REG_SEC, 7, date);
+	ret = rx8025_write_regs(client, RX8025_REG_SEC, 7, date);
 	if (ret < 0)
 		return ret;
 
-	return rx8025_reset_validity(rx8025->client);
+	return rx8025_reset_validity(client);
 }
 
 static int rx8025_init_client(struct i2c_client *client)
@@ -251,7 +252,7 @@ static int rx8025_init_client(struct i2c_client *client)
 	int need_clear = 0;
 	int err;
 
-	err = rx8025_read_regs(rx8025->client, RX8025_REG_CTRL1, 2, ctrl);
+	err = rx8025_read_regs(client, RX8025_REG_CTRL1, 2, ctrl);
 	if (err)
 		goto out;
 
@@ -280,8 +281,8 @@ out:
 /* Alarm support */
 static int rx8025_read_alarm(struct device *dev, struct rtc_wkalrm *t)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct rx8025_data *rx8025 = dev_get_drvdata(dev);
-	struct i2c_client *client = rx8025->client;
 	u8 ald[2];
 	int ctrl2, err;
 
@@ -347,18 +348,18 @@ static int rx8025_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 
 	if (rx8025->ctrl1 & RX8025_BIT_CTRL1_DALE) {
 		rx8025->ctrl1 &= ~RX8025_BIT_CTRL1_DALE;
-		err = rx8025_write_reg(rx8025->client, RX8025_REG_CTRL1,
+		err = rx8025_write_reg(client, RX8025_REG_CTRL1,
 				       rx8025->ctrl1);
 		if (err)
 			return err;
 	}
-	err = rx8025_write_regs(rx8025->client, RX8025_REG_ALDMIN, 2, ald);
+	err = rx8025_write_regs(client, RX8025_REG_ALDMIN, 2, ald);
 	if (err)
 		return err;
 
 	if (t->enabled) {
 		rx8025->ctrl1 |= RX8025_BIT_CTRL1_DALE;
-		err = rx8025_write_reg(rx8025->client, RX8025_REG_CTRL1,
+		err = rx8025_write_reg(client, RX8025_REG_CTRL1,
 				       rx8025->ctrl1);
 		if (err)
 			return err;
@@ -369,6 +370,7 @@ static int rx8025_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 
 static int rx8025_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct rx8025_data *rx8025 = dev_get_drvdata(dev);
 	u8 ctrl1;
 	int err;
@@ -381,7 +383,7 @@ static int rx8025_alarm_irq_enable(struct device *dev, unsigned int enabled)
 
 	if (ctrl1 != rx8025->ctrl1) {
 		rx8025->ctrl1 = ctrl1;
-		err = rx8025_write_reg(rx8025->client, RX8025_REG_CTRL1,
+		err = rx8025_write_reg(client, RX8025_REG_CTRL1,
 				       rx8025->ctrl1);
 		if (err)
 			return err;
@@ -516,7 +518,6 @@ static int rx8025_probe(struct i2c_client *client,
 	if (!rx8025)
 		return -ENOMEM;
 
-	rx8025->client = client;
 	i2c_set_clientdata(client, rx8025);
 
 	err = rx8025_init_client(client);
diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c
index 781cabb2afca..d774aa18f57a 100644
--- a/drivers/rtc/rtc-stm32.c
+++ b/drivers/rtc/rtc-stm32.c
@@ -897,8 +897,11 @@ static int stm32_rtc_resume(struct device *dev)
 	}
 
 	ret = stm32_rtc_wait_sync(rtc);
-	if (ret < 0)
+	if (ret < 0) {
+		if (rtc->data->has_pclk)
+			clk_disable_unprepare(rtc->pclk);
 		return ret;
+	}
 
 	if (device_may_wakeup(dev))
 		return disable_irq_wake(rtc->irq_alarm);
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index 859d901fa6cb..e39af2d67051 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -23,6 +23,7 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/mfd/tps6586x.h>
 #include <linux/module.h>
@@ -267,6 +268,8 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 	rtc->rtc->start_secs = mktime64(2009, 1, 1, 0, 0, 0);
 	rtc->rtc->set_start_time = true;
 
+	irq_set_status_flags(rtc->irq, IRQ_NOAUTOEN);
+
 	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
 				tps6586x_rtc_irq,
 				IRQF_ONESHOT,
@@ -276,7 +279,6 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 				rtc->irq, ret);
 		goto fail_rtc_register;
 	}
-	disable_irq(rtc->irq);
 
 	ret = rtc_register_device(rtc->rtc);
 	if (ret)
diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c
index 539690568298..5786866c09e9 100644
--- a/drivers/rtc/rtc-zynqmp.c
+++ b/drivers/rtc/rtc-zynqmp.c
@@ -94,7 +94,7 @@ static int xlnx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		 * RTC has updated the CURRENT_TIME with the time written into
 		 * SET_TIME_WRITE register.
 		 */
-		rtc_time64_to_tm(readl(xrtcdev->reg_base + RTC_CUR_TM), tm);
+		read_time = readl(xrtcdev->reg_base + RTC_CUR_TM);
 	} else {
 		/*
 		 * Time written in SET_TIME_WRITE has not yet updated into
@@ -104,8 +104,8 @@ static int xlnx_rtc_read_time(struct device *dev, struct rtc_time *tm)
 		 * reading.
 		 */
 		read_time = readl(xrtcdev->reg_base + RTC_SET_TM_RD) - 1;
-		rtc_time64_to_tm(read_time, tm);
 	}
+	rtc_time64_to_tm(read_time, tm);
 
 	return 0;
 }
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index 8d4d69ea5baf..62a859ea67f8 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -320,13 +320,12 @@ out_error:
 #endif				/* CONFIG_DASD_PROFILE */
 }
 
-static const struct file_operations dasd_stats_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= dasd_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= dasd_stats_proc_write,
+static const struct proc_ops dasd_stats_proc_ops = {
+	.proc_open	= dasd_stats_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= dasd_stats_proc_write,
 };
 
 /*
@@ -347,7 +346,7 @@ dasd_proc_init(void)
 	dasd_statistics_entry = proc_create("statistics",
 					    S_IFREG | S_IRUGO | S_IWUSR,
 					    dasd_proc_root_entry,
-					    &dasd_stats_proc_fops);
+					    &dasd_stats_proc_ops);
 	if (!dasd_statistics_entry)
 		goto out_nostatistics;
 	return 0;
diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index 2a3f874a21d5..da642e811f7f 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -398,12 +398,12 @@ cio_ignore_proc_open(struct inode *inode, struct file *file)
 				sizeof(struct ccwdev_iter));
 }
 
-static const struct file_operations cio_ignore_proc_fops = {
-	.open    = cio_ignore_proc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release_private,
-	.write   = cio_ignore_write,
+static const struct proc_ops cio_ignore_proc_ops = {
+	.proc_open	= cio_ignore_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release_private,
+	.proc_write	= cio_ignore_write,
 };
 
 static int
@@ -412,7 +412,7 @@ cio_ignore_proc_init (void)
 	struct proc_dir_entry *entry;
 
 	entry = proc_create("cio_ignore", S_IFREG | S_IRUGO | S_IWUSR, NULL,
-			    &cio_ignore_proc_fops);
+			    &cio_ignore_proc_ops);
 	if (!entry)
 		return -ENOENT;
 	return 0;
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 831850435c23..94edbb33d0d1 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -1372,18 +1372,17 @@ static ssize_t cio_settle_write(struct file *file, const char __user *buf,
 	return ret ? ret : count;
 }
 
-static const struct file_operations cio_settle_proc_fops = {
-	.open = nonseekable_open,
-	.write = cio_settle_write,
-	.llseek = no_llseek,
+static const struct proc_ops cio_settle_proc_ops = {
+	.proc_open	= nonseekable_open,
+	.proc_write	= cio_settle_write,
+	.proc_lseek	= no_llseek,
 };
 
 static int __init cio_settle_init(void)
 {
 	struct proc_dir_entry *entry;
 
-	entry = proc_create("cio_settle", S_IWUSR, NULL,
-			    &cio_settle_proc_fops);
+	entry = proc_create("cio_settle", S_IWUSR, NULL, &cio_settle_proc_ops);
 	if (!entry)
 		return -ENOMEM;
 	return 0;
diff --git a/drivers/s390/crypto/Makefile b/drivers/s390/crypto/Makefile
index 52aa95c8af4b..22d2db690cd3 100644
--- a/drivers/s390/crypto/Makefile
+++ b/drivers/s390/crypto/Makefile
@@ -7,7 +7,8 @@ ap-objs := ap_bus.o ap_card.o ap_queue.o
 obj-$(subst m,y,$(CONFIG_ZCRYPT)) += ap.o
 # zcrypt_api.o and zcrypt_msgtype*.o depend on ap.o
 zcrypt-objs := zcrypt_api.o zcrypt_card.o zcrypt_queue.o
-zcrypt-objs += zcrypt_msgtype6.o zcrypt_msgtype50.o zcrypt_ccamisc.o
+zcrypt-objs += zcrypt_msgtype6.o zcrypt_msgtype50.o
+zcrypt-objs += zcrypt_ccamisc.o zcrypt_ep11misc.o
 obj-$(CONFIG_ZCRYPT) += zcrypt.o
 # adapter drivers depend on ap.o and zcrypt.o
 obj-$(CONFIG_ZCRYPT) += zcrypt_cex2c.o zcrypt_cex2a.o zcrypt_cex4.o
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index d78d77686d7b..71dae64ba994 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -25,6 +25,7 @@
 
 #include "zcrypt_api.h"
 #include "zcrypt_ccamisc.h"
+#include "zcrypt_ep11misc.h"
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("IBM Corporation");
@@ -71,6 +72,17 @@ struct protaeskeytoken {
 	u8  protkey[MAXPROTKEYSIZE]; /* the protected key blob */
 } __packed;
 
+/* inside view of a clear key token (type 0x00 version 0x02) */
+struct clearaeskeytoken {
+	u8  type;	 /* 0x00 for PAES specific key tokens */
+	u8  res0[3];
+	u8  version;	 /* 0x02 for clear AES key token */
+	u8  res1[3];
+	u32 keytype;	 /* key type, one of the PKEY_KEYTYPE values */
+	u32 len;	 /* bytes actually stored in clearkey[] */
+	u8  clearkey[0]; /* clear key value */
+} __packed;
+
 /*
  * Create a protected key from a clear key value.
  */
@@ -173,6 +185,72 @@ static int pkey_skey2pkey(const u8 *key, struct pkey_protkey *pkey)
 }
 
 /*
+ * Construct EP11 key with given clear key value.
+ */
+static int pkey_clr2ep11key(const u8 *clrkey, size_t clrkeylen,
+			    u8 *keybuf, size_t *keybuflen)
+{
+	int i, rc;
+	u16 card, dom;
+	u32 nr_apqns, *apqns = NULL;
+
+	/* build a list of apqns suitable for ep11 keys with cpacf support */
+	rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
+			    ZCRYPT_CEX7, EP11_API_V, NULL);
+	if (rc)
+		goto out;
+
+	/* go through the list of apqns and try to bild an ep11 key */
+	for (rc = -ENODEV, i = 0; i < nr_apqns; i++) {
+		card = apqns[i] >> 16;
+		dom = apqns[i] & 0xFFFF;
+		rc = ep11_clr2keyblob(card, dom, clrkeylen * 8,
+				      0, clrkey, keybuf, keybuflen);
+		if (rc == 0)
+			break;
+	}
+
+out:
+	kfree(apqns);
+	if (rc)
+		DEBUG_DBG("%s failed rc=%d\n", __func__, rc);
+	return rc;
+}
+
+/*
+ * Find card and transform EP11 secure key into protected key.
+ */
+static int pkey_ep11key2pkey(const u8 *key, struct pkey_protkey *pkey)
+{
+	int i, rc;
+	u16 card, dom;
+	u32 nr_apqns, *apqns = NULL;
+	struct ep11keyblob *kb = (struct ep11keyblob *) key;
+
+	/* build a list of apqns suitable for this key */
+	rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
+			    ZCRYPT_CEX7, EP11_API_V, kb->wkvp);
+	if (rc)
+		goto out;
+
+	/* go through the list of apqns and try to derive an pkey */
+	for (rc = -ENODEV, i = 0; i < nr_apqns; i++) {
+		card = apqns[i] >> 16;
+		dom = apqns[i] & 0xFFFF;
+		rc = ep11_key2protkey(card, dom, key, kb->head.len,
+				      pkey->protkey, &pkey->len, &pkey->type);
+		if (rc == 0)
+			break;
+	}
+
+out:
+	kfree(apqns);
+	if (rc)
+		DEBUG_DBG("%s failed rc=%d\n", __func__, rc);
+	return rc;
+}
+
+/*
  * Verify key and give back some info about the key.
  */
 static int pkey_verifykey(const struct pkey_seckey *seckey,
@@ -305,26 +383,90 @@ static int pkey_verifyprotkey(const struct pkey_protkey *protkey)
 static int pkey_nonccatok2pkey(const u8 *key, u32 keylen,
 			       struct pkey_protkey *protkey)
 {
+	int rc = -EINVAL;
+	u8 *tmpbuf = NULL;
 	struct keytoken_header *hdr = (struct keytoken_header *)key;
-	struct protaeskeytoken *t;
 
 	switch (hdr->version) {
-	case TOKVER_PROTECTED_KEY:
-		if (keylen != sizeof(struct protaeskeytoken))
-			return -EINVAL;
+	case TOKVER_PROTECTED_KEY: {
+		struct protaeskeytoken *t;
 
+		if (keylen != sizeof(struct protaeskeytoken))
+			goto out;
 		t = (struct protaeskeytoken *)key;
 		protkey->len = t->len;
 		protkey->type = t->keytype;
 		memcpy(protkey->protkey, t->protkey,
 		       sizeof(protkey->protkey));
-
-		return pkey_verifyprotkey(protkey);
+		rc = pkey_verifyprotkey(protkey);
+		break;
+	}
+	case TOKVER_CLEAR_KEY: {
+		struct clearaeskeytoken *t;
+		struct pkey_clrkey ckey;
+		union u_tmpbuf {
+			u8 skey[SECKEYBLOBSIZE];
+			u8 ep11key[MAXEP11AESKEYBLOBSIZE];
+		};
+		size_t tmpbuflen = sizeof(union u_tmpbuf);
+
+		if (keylen < sizeof(struct clearaeskeytoken))
+			goto out;
+		t = (struct clearaeskeytoken *)key;
+		if (keylen != sizeof(*t) + t->len)
+			goto out;
+		if ((t->keytype == PKEY_KEYTYPE_AES_128 && t->len == 16)
+		    || (t->keytype == PKEY_KEYTYPE_AES_192 && t->len == 24)
+		    || (t->keytype == PKEY_KEYTYPE_AES_256 && t->len == 32))
+			memcpy(ckey.clrkey, t->clearkey, t->len);
+		else
+			goto out;
+		/* alloc temp key buffer space */
+		tmpbuf = kmalloc(tmpbuflen, GFP_ATOMIC);
+		if (!tmpbuf) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		/* try direct way with the PCKMO instruction */
+		rc = pkey_clr2protkey(t->keytype, &ckey, protkey);
+		if (rc == 0)
+			break;
+		/* PCKMO failed, so try the CCA secure key way */
+		rc = cca_clr2seckey(0xFFFF, 0xFFFF, t->keytype,
+				    ckey.clrkey, tmpbuf);
+		if (rc == 0)
+			rc = pkey_skey2pkey(tmpbuf, protkey);
+		if (rc == 0)
+			break;
+		/* if the CCA way also failed, let's try via EP11 */
+		rc = pkey_clr2ep11key(ckey.clrkey, t->len,
+				      tmpbuf, &tmpbuflen);
+		if (rc == 0)
+			rc = pkey_ep11key2pkey(tmpbuf, protkey);
+		/* now we should really have an protected key */
+		DEBUG_ERR("%s unable to build protected key from clear",
+			  __func__);
+		break;
+	}
+	case TOKVER_EP11_AES: {
+		if (keylen < MINEP11AESKEYBLOBSIZE)
+			goto out;
+		/* check ep11 key for exportable as protected key */
+		rc = ep11_check_aeskeyblob(debug_info, 3, key, 0, 1);
+		if (rc)
+			goto out;
+		rc = pkey_ep11key2pkey(key, protkey);
+		break;
+	}
 	default:
 		DEBUG_ERR("%s unknown/unsupported non-CCA token version %d\n",
 			  __func__, hdr->version);
-		return -EINVAL;
+		rc = -EINVAL;
 	}
+
+out:
+	kfree(tmpbuf);
+	return rc;
 }
 
 /*
@@ -403,6 +545,10 @@ static int pkey_genseckey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 		if (*keybufsize < SECKEYBLOBSIZE)
 			return -EINVAL;
 		break;
+	case PKEY_TYPE_EP11:
+		if (*keybufsize < MINEP11AESKEYBLOBSIZE)
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -419,7 +565,10 @@ static int pkey_genseckey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 	for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
 		card = apqns[i].card;
 		dom = apqns[i].domain;
-		if (ktype == PKEY_TYPE_CCA_DATA) {
+		if (ktype == PKEY_TYPE_EP11) {
+			rc = ep11_genaeskey(card, dom, ksize, kflags,
+					    keybuf, keybufsize);
+		} else if (ktype == PKEY_TYPE_CCA_DATA) {
 			rc = cca_genseckey(card, dom, ksize, keybuf);
 			*keybufsize = (rc ? 0 : SECKEYBLOBSIZE);
 		} else /* TOKVER_CCA_VLSC */
@@ -450,6 +599,10 @@ static int pkey_clr2seckey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 		if (*keybufsize < SECKEYBLOBSIZE)
 			return -EINVAL;
 		break;
+	case PKEY_TYPE_EP11:
+		if (*keybufsize < MINEP11AESKEYBLOBSIZE)
+			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -466,7 +619,10 @@ static int pkey_clr2seckey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 	for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
 		card = apqns[i].card;
 		dom = apqns[i].domain;
-		if (ktype == PKEY_TYPE_CCA_DATA) {
+		if (ktype == PKEY_TYPE_EP11) {
+			rc = ep11_clr2keyblob(card, dom, ksize, kflags,
+					      clrkey, keybuf, keybufsize);
+		} else if (ktype == PKEY_TYPE_CCA_DATA) {
 			rc = cca_clr2seckey(card, dom, ksize,
 					    clrkey, keybuf);
 			*keybufsize = (rc ? 0 : SECKEYBLOBSIZE);
@@ -489,11 +645,11 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 	u32 _nr_apqns, *_apqns = NULL;
 	struct keytoken_header *hdr = (struct keytoken_header *)key;
 
-	if (keylen < sizeof(struct keytoken_header) ||
-	    hdr->type != TOKTYPE_CCA_INTERNAL)
+	if (keylen < sizeof(struct keytoken_header))
 		return -EINVAL;
 
-	if (hdr->version == TOKVER_CCA_AES) {
+	if (hdr->type == TOKTYPE_CCA_INTERNAL
+	    && hdr->version == TOKVER_CCA_AES) {
 		struct secaeskeytoken *t = (struct secaeskeytoken *)key;
 
 		rc = cca_check_secaeskeytoken(debug_info, 3, key, 0);
@@ -521,7 +677,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 		*cardnr = ((struct pkey_apqn *)_apqns)->card;
 		*domain = ((struct pkey_apqn *)_apqns)->domain;
 
-	} else if (hdr->version == TOKVER_CCA_VLSC) {
+	} else if (hdr->type == TOKTYPE_CCA_INTERNAL
+		   && hdr->version == TOKVER_CCA_VLSC) {
 		struct cipherkeytoken *t = (struct cipherkeytoken *)key;
 
 		rc = cca_check_secaescipherkey(debug_info, 3, key, 0, 1);
@@ -556,6 +713,29 @@ static int pkey_verifykey2(const u8 *key, size_t keylen,
 		*cardnr = ((struct pkey_apqn *)_apqns)->card;
 		*domain = ((struct pkey_apqn *)_apqns)->domain;
 
+	} else if (hdr->type == TOKTYPE_NON_CCA
+		   && hdr->version == TOKVER_EP11_AES) {
+		struct ep11keyblob *kb = (struct ep11keyblob *)key;
+
+		rc = ep11_check_aeskeyblob(debug_info, 3, key, 0, 1);
+		if (rc)
+			goto out;
+		if (ktype)
+			*ktype = PKEY_TYPE_EP11;
+		if (ksize)
+			*ksize = kb->head.keybitlen;
+
+		rc = ep11_findcard2(&_apqns, &_nr_apqns, *cardnr, *domain,
+				    ZCRYPT_CEX7, EP11_API_V, kb->wkvp);
+		if (rc)
+			goto out;
+
+		if (flags)
+			*flags = PKEY_FLAGS_MATCH_CUR_MKVP;
+
+		*cardnr = ((struct pkey_apqn *)_apqns)->card;
+		*domain = ((struct pkey_apqn *)_apqns)->domain;
+
 	} else
 		rc = -EINVAL;
 
@@ -578,30 +758,32 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 	if (keylen < sizeof(struct keytoken_header))
 		return -EINVAL;
 
-	switch (hdr->type) {
-	case TOKTYPE_NON_CCA:
-		return pkey_nonccatok2pkey(key, keylen, pkey);
-	case TOKTYPE_CCA_INTERNAL:
-		switch (hdr->version) {
-		case TOKVER_CCA_AES:
+	if (hdr->type == TOKTYPE_CCA_INTERNAL) {
+		if (hdr->version == TOKVER_CCA_AES) {
 			if (keylen != sizeof(struct secaeskeytoken))
 				return -EINVAL;
 			if (cca_check_secaeskeytoken(debug_info, 3, key, 0))
 				return -EINVAL;
-			break;
-		case TOKVER_CCA_VLSC:
+		} else if (hdr->version == TOKVER_CCA_VLSC) {
 			if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE)
 				return -EINVAL;
 			if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1))
 				return -EINVAL;
-			break;
-		default:
+		} else {
 			DEBUG_ERR("%s unknown CCA internal token version %d\n",
 				  __func__, hdr->version);
 			return -EINVAL;
 		}
-		break;
-	default:
+	} else if (hdr->type == TOKTYPE_NON_CCA) {
+		if (hdr->version == TOKVER_EP11_AES) {
+			if (keylen < sizeof(struct ep11keyblob))
+				return -EINVAL;
+			if (ep11_check_aeskeyblob(debug_info, 3, key, 0, 1))
+				return -EINVAL;
+		} else {
+			return pkey_nonccatok2pkey(key, keylen, pkey);
+		}
+	} else {
 		DEBUG_ERR("%s unknown/unsupported blob type %d\n",
 			  __func__, hdr->type);
 		return -EINVAL;
@@ -611,12 +793,21 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns,
 	for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
 		card = apqns[i].card;
 		dom = apqns[i].domain;
-		if (hdr->version == TOKVER_CCA_AES)
+		if (hdr->type == TOKTYPE_CCA_INTERNAL
+		    && hdr->version == TOKVER_CCA_AES)
 			rc = cca_sec2protkey(card, dom, key, pkey->protkey,
 					     &pkey->len, &pkey->type);
-		else /* TOKVER_CCA_VLSC */
+		else if (hdr->type == TOKTYPE_CCA_INTERNAL
+			 && hdr->version == TOKVER_CCA_VLSC)
 			rc = cca_cipher2protkey(card, dom, key, pkey->protkey,
 						&pkey->len, &pkey->type);
+		else { /* EP11 AES secure key blob */
+			struct ep11keyblob *kb = (struct ep11keyblob *) key;
+
+			rc = ep11_key2protkey(card, dom, key, kb->head.len,
+					      pkey->protkey, &pkey->len,
+					      &pkey->type);
+		}
 		if (rc == 0)
 			break;
 	}
@@ -631,12 +822,24 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags,
 	u32 _nr_apqns, *_apqns = NULL;
 	struct keytoken_header *hdr = (struct keytoken_header *)key;
 
-	if (keylen < sizeof(struct keytoken_header) ||
-	    hdr->type != TOKTYPE_CCA_INTERNAL ||
-	    flags == 0)
+	if (keylen < sizeof(struct keytoken_header) || flags == 0)
 		return -EINVAL;
 
-	if (hdr->version == TOKVER_CCA_AES || hdr->version == TOKVER_CCA_VLSC) {
+	if (hdr->type == TOKTYPE_NON_CCA && hdr->version == TOKVER_EP11_AES) {
+		int minhwtype = 0, api = 0;
+		struct ep11keyblob *kb = (struct ep11keyblob *) key;
+
+		if (flags != PKEY_FLAGS_MATCH_CUR_MKVP)
+			return -EINVAL;
+		if (kb->attr & EP11_BLOB_PKEY_EXTRACTABLE) {
+			minhwtype = ZCRYPT_CEX7;
+			api = EP11_API_V;
+		}
+		rc = ep11_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF,
+				    minhwtype, api, kb->wkvp);
+		if (rc)
+			goto out;
+	} else if (hdr->type == TOKTYPE_CCA_INTERNAL) {
 		int minhwtype = ZCRYPT_CEX3C;
 		u64 cur_mkvp = 0, old_mkvp = 0;
 
@@ -647,7 +850,7 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags,
 				cur_mkvp = t->mkvp;
 			if (flags & PKEY_FLAGS_MATCH_ALT_MKVP)
 				old_mkvp = t->mkvp;
-		} else {
+		} else if (hdr->version == TOKVER_CCA_VLSC) {
 			struct cipherkeytoken *t = (struct cipherkeytoken *)key;
 
 			minhwtype = ZCRYPT_CEX6;
@@ -655,19 +858,24 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags,
 				cur_mkvp = t->mkvp0;
 			if (flags & PKEY_FLAGS_MATCH_ALT_MKVP)
 				old_mkvp = t->mkvp0;
+		} else {
+			/* unknown cca internal token type */
+			return -EINVAL;
 		}
 		rc = cca_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF,
 				   minhwtype, cur_mkvp, old_mkvp, 1);
 		if (rc)
 			goto out;
-		if (apqns) {
-			if (*nr_apqns < _nr_apqns)
-				rc = -ENOSPC;
-			else
-				memcpy(apqns, _apqns, _nr_apqns * sizeof(u32));
-		}
-		*nr_apqns = _nr_apqns;
+	} else
+		return -EINVAL;
+
+	if (apqns) {
+		if (*nr_apqns < _nr_apqns)
+			rc = -ENOSPC;
+		else
+			memcpy(apqns, _apqns, _nr_apqns * sizeof(u32));
 	}
+	*nr_apqns = _nr_apqns;
 
 out:
 	kfree(_apqns);
@@ -695,14 +903,26 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype,
 				   minhwtype, cur_mkvp, old_mkvp, 1);
 		if (rc)
 			goto out;
-		if (apqns) {
-			if (*nr_apqns < _nr_apqns)
-				rc = -ENOSPC;
-			else
-				memcpy(apqns, _apqns, _nr_apqns * sizeof(u32));
-		}
-		*nr_apqns = _nr_apqns;
+	} else if (ktype == PKEY_TYPE_EP11) {
+		u8 *wkvp = NULL;
+
+		if (flags & PKEY_FLAGS_MATCH_CUR_MKVP)
+			wkvp = cur_mkvp;
+		rc = ep11_findcard2(&_apqns, &_nr_apqns, 0xFFFF, 0xFFFF,
+				    ZCRYPT_CEX7, EP11_API_V, wkvp);
+		if (rc)
+			goto out;
+
+	} else
+		return -EINVAL;
+
+	if (apqns) {
+		if (*nr_apqns < _nr_apqns)
+			rc = -ENOSPC;
+		else
+			memcpy(apqns, _apqns, _nr_apqns * sizeof(u32));
 	}
+	*nr_apqns = _nr_apqns;
 
 out:
 	kfree(_apqns);
@@ -1357,8 +1577,9 @@ static ssize_t pkey_ccacipher_aes_attr_read(enum pkey_key_size keybits,
 					    bool is_xts, char *buf, loff_t off,
 					    size_t count)
 {
-	size_t keysize;
-	int rc;
+	int i, rc, card, dom;
+	u32 nr_apqns, *apqns = NULL;
+	size_t keysize = CCACIPHERTOKENSIZE;
 
 	if (off != 0 || count < CCACIPHERTOKENSIZE)
 		return -EINVAL;
@@ -1366,22 +1587,31 @@ static ssize_t pkey_ccacipher_aes_attr_read(enum pkey_key_size keybits,
 		if (count < 2 * CCACIPHERTOKENSIZE)
 			return -EINVAL;
 
-	keysize = CCACIPHERTOKENSIZE;
-	rc = cca_gencipherkey(-1, -1, keybits, 0, buf, &keysize);
+	/* build a list of apqns able to generate an cipher key */
+	rc = cca_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
+			   ZCRYPT_CEX6, 0, 0, 0);
 	if (rc)
 		return rc;
-	memset(buf + keysize, 0, CCACIPHERTOKENSIZE - keysize);
 
-	if (is_xts) {
-		keysize = CCACIPHERTOKENSIZE;
-		rc = cca_gencipherkey(-1, -1, keybits, 0,
-				      buf + CCACIPHERTOKENSIZE, &keysize);
+	memset(buf, 0, is_xts ? 2 * keysize : keysize);
+
+	/* simple try all apqns from the list */
+	for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
+		card = apqns[i] >> 16;
+		dom = apqns[i] & 0xFFFF;
+		rc = cca_gencipherkey(card, dom, keybits, 0, buf, &keysize);
+		if (rc == 0)
+			break;
+	}
 		if (rc)
 			return rc;
-		memset(buf + CCACIPHERTOKENSIZE + keysize, 0,
-		       CCACIPHERTOKENSIZE - keysize);
 
-		return 2 * CCACIPHERTOKENSIZE;
+	if (is_xts) {
+		keysize = CCACIPHERTOKENSIZE;
+		buf += CCACIPHERTOKENSIZE;
+		rc = cca_gencipherkey(card, dom, keybits, 0, buf, &keysize);
+		if (rc == 0)
+			return 2 * CCACIPHERTOKENSIZE;
 	}
 
 	return CCACIPHERTOKENSIZE;
@@ -1457,10 +1687,134 @@ static struct attribute_group ccacipher_attr_group = {
 	.bin_attrs = ccacipher_attrs,
 };
 
+/*
+ * Sysfs attribute read function for all ep11 aes key binary attributes.
+ * The implementation can not deal with partial reads, because a new random
+ * secure key blob is generated with each read. In case of partial reads
+ * (i.e. off != 0 or count < key blob size) -EINVAL is returned.
+ * This function and the sysfs attributes using it provide EP11 key blobs
+ * padded to the upper limit of MAXEP11AESKEYBLOBSIZE which is currently
+ * 320 bytes.
+ */
+static ssize_t pkey_ep11_aes_attr_read(enum pkey_key_size keybits,
+				       bool is_xts, char *buf, loff_t off,
+				       size_t count)
+{
+	int i, rc, card, dom;
+	u32 nr_apqns, *apqns = NULL;
+	size_t keysize = MAXEP11AESKEYBLOBSIZE;
+
+	if (off != 0 || count < MAXEP11AESKEYBLOBSIZE)
+		return -EINVAL;
+	if (is_xts)
+		if (count < 2 * MAXEP11AESKEYBLOBSIZE)
+			return -EINVAL;
+
+	/* build a list of apqns able to generate an cipher key */
+	rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
+			    ZCRYPT_CEX7, EP11_API_V, NULL);
+	if (rc)
+		return rc;
+
+	memset(buf, 0, is_xts ? 2 * keysize : keysize);
+
+	/* simple try all apqns from the list */
+	for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
+		card = apqns[i] >> 16;
+		dom = apqns[i] & 0xFFFF;
+		rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize);
+		if (rc == 0)
+			break;
+	}
+	if (rc)
+		return rc;
+
+	if (is_xts) {
+		keysize = MAXEP11AESKEYBLOBSIZE;
+		buf += MAXEP11AESKEYBLOBSIZE;
+		rc = ep11_genaeskey(card, dom, keybits, 0, buf, &keysize);
+		if (rc == 0)
+			return 2 * MAXEP11AESKEYBLOBSIZE;
+	}
+
+	return MAXEP11AESKEYBLOBSIZE;
+}
+
+static ssize_t ep11_aes_128_read(struct file *filp,
+				 struct kobject *kobj,
+				 struct bin_attribute *attr,
+				 char *buf, loff_t off,
+				 size_t count)
+{
+	return pkey_ep11_aes_attr_read(PKEY_SIZE_AES_128, false, buf,
+				       off, count);
+}
+
+static ssize_t ep11_aes_192_read(struct file *filp,
+				 struct kobject *kobj,
+				 struct bin_attribute *attr,
+				 char *buf, loff_t off,
+				 size_t count)
+{
+	return pkey_ep11_aes_attr_read(PKEY_SIZE_AES_192, false, buf,
+				       off, count);
+}
+
+static ssize_t ep11_aes_256_read(struct file *filp,
+				 struct kobject *kobj,
+				 struct bin_attribute *attr,
+				 char *buf, loff_t off,
+				 size_t count)
+{
+	return pkey_ep11_aes_attr_read(PKEY_SIZE_AES_256, false, buf,
+				       off, count);
+}
+
+static ssize_t ep11_aes_128_xts_read(struct file *filp,
+				     struct kobject *kobj,
+				     struct bin_attribute *attr,
+				     char *buf, loff_t off,
+				     size_t count)
+{
+	return pkey_ep11_aes_attr_read(PKEY_SIZE_AES_128, true, buf,
+				       off, count);
+}
+
+static ssize_t ep11_aes_256_xts_read(struct file *filp,
+				     struct kobject *kobj,
+				     struct bin_attribute *attr,
+				     char *buf, loff_t off,
+				     size_t count)
+{
+	return pkey_ep11_aes_attr_read(PKEY_SIZE_AES_256, true, buf,
+				       off, count);
+}
+
+static BIN_ATTR_RO(ep11_aes_128, MAXEP11AESKEYBLOBSIZE);
+static BIN_ATTR_RO(ep11_aes_192, MAXEP11AESKEYBLOBSIZE);
+static BIN_ATTR_RO(ep11_aes_256, MAXEP11AESKEYBLOBSIZE);
+static BIN_ATTR_RO(ep11_aes_128_xts, 2 * MAXEP11AESKEYBLOBSIZE);
+static BIN_ATTR_RO(ep11_aes_256_xts, 2 * MAXEP11AESKEYBLOBSIZE);
+
+static struct bin_attribute *ep11_attrs[] = {
+	&bin_attr_ep11_aes_128,
+	&bin_attr_ep11_aes_192,
+	&bin_attr_ep11_aes_256,
+	&bin_attr_ep11_aes_128_xts,
+	&bin_attr_ep11_aes_256_xts,
+	NULL
+};
+
+static struct attribute_group ep11_attr_group = {
+	.name	   = "ep11",
+	.bin_attrs = ep11_attrs,
+};
+
 static const struct attribute_group *pkey_attr_groups[] = {
 	&protkey_attr_group,
 	&ccadata_attr_group,
 	&ccacipher_attr_group,
+	&ep11_attr_group,
 	NULL,
 };
 
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 9157e728a362..a42257d6c79e 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -36,6 +36,7 @@
 #include "zcrypt_msgtype6.h"
 #include "zcrypt_msgtype50.h"
 #include "zcrypt_ccamisc.h"
+#include "zcrypt_ep11misc.h"
 
 /*
  * Module description.
@@ -849,7 +850,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 			/* check if device is online and eligible */
 			if (!zq->online ||
 			    !zq->ops->send_cprb ||
-			    (tdom != (unsigned short) AUTOSELECT &&
+			    (tdom != AUTOSEL_DOM &&
 			     tdom != AP_QID_QUEUE(zq->queue->qid)))
 				continue;
 			/* check if device node has admission for this queue */
@@ -874,7 +875,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 
 	/* in case of auto select, provide the correct domain */
 	qid = pref_zq->queue->qid;
-	if (*domain == (unsigned short) AUTOSELECT)
+	if (*domain == AUTOSEL_DOM)
 		*domain = AP_QID_QUEUE(qid);
 
 	rc = pref_zq->ops->send_cprb(pref_zq, xcRB, &ap_msg);
@@ -901,7 +902,7 @@ static bool is_desired_ep11_card(unsigned int dev_id,
 				 struct ep11_target_dev *targets)
 {
 	while (target_num-- > 0) {
-		if (dev_id == targets->ap_id)
+		if (targets->ap_id == dev_id || targets->ap_id == AUTOSEL_AP)
 			return true;
 		targets++;
 	}
@@ -912,16 +913,19 @@ static bool is_desired_ep11_queue(unsigned int dev_qid,
 				  unsigned short target_num,
 				  struct ep11_target_dev *targets)
 {
+	int card = AP_QID_CARD(dev_qid), dom = AP_QID_QUEUE(dev_qid);
+
 	while (target_num-- > 0) {
-		if (AP_MKQID(targets->ap_id, targets->dom_id) == dev_qid)
+		if ((targets->ap_id == card || targets->ap_id == AUTOSEL_AP) &&
+		    (targets->dom_id == dom || targets->dom_id == AUTOSEL_DOM))
 			return true;
 		targets++;
 	}
 	return false;
 }
 
-static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
-				  struct ep11_urb *xcrb)
+static long _zcrypt_send_ep11_cprb(struct ap_perms *perms,
+				   struct ep11_urb *xcrb)
 {
 	struct zcrypt_card *zc, *pref_zc;
 	struct zcrypt_queue *zq, *pref_zq;
@@ -1026,6 +1030,12 @@ out:
 	return rc;
 }
 
+long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
+{
+	return _zcrypt_send_ep11_cprb(&ap_perms, xcrb);
+}
+EXPORT_SYMBOL(zcrypt_send_ep11_cprb);
+
 static long zcrypt_rng(char *buffer)
 {
 	struct zcrypt_card *zc, *pref_zc;
@@ -1366,12 +1376,12 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
 		if (copy_from_user(&xcrb, uxcrb, sizeof(xcrb)))
 			return -EFAULT;
 		do {
-			rc = zcrypt_send_ep11_cprb(perms, &xcrb);
+			rc = _zcrypt_send_ep11_cprb(perms, &xcrb);
 		} while (rc == -EAGAIN);
 		/* on failure: retry once again after a requested rescan */
 		if ((rc == -ENODEV) && (zcrypt_process_rescan()))
 			do {
-				rc = zcrypt_send_ep11_cprb(perms, &xcrb);
+				rc = _zcrypt_send_ep11_cprb(perms, &xcrb);
 			} while (rc == -EAGAIN);
 		if (rc)
 			ZCRYPT_DBF(DBF_DEBUG, "ioctl ZSENDEP11CPRB rc=%d\n", rc);
@@ -1885,6 +1895,7 @@ void __exit zcrypt_api_exit(void)
 	zcrypt_msgtype6_exit();
 	zcrypt_msgtype50_exit();
 	zcrypt_ccamisc_exit();
+	zcrypt_ep11misc_exit();
 	zcrypt_debug_exit();
 }
 
diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h
index d464618cd84f..599e68bf53f7 100644
--- a/drivers/s390/crypto/zcrypt_api.h
+++ b/drivers/s390/crypto/zcrypt_api.h
@@ -140,6 +140,7 @@ struct zcrypt_ops *zcrypt_msgtype(unsigned char *, int);
 int zcrypt_api_init(void);
 void zcrypt_api_exit(void);
 long zcrypt_send_cprb(struct ica_xcRB *xcRB);
+long zcrypt_send_ep11_cprb(struct ep11_urb *urb);
 void zcrypt_device_status_mask_ext(struct zcrypt_device_status_ext *devstatus);
 int zcrypt_device_status_ext(int card, int queue,
 			     struct zcrypt_device_status_ext *devstatus);
diff --git a/drivers/s390/crypto/zcrypt_ccamisc.h b/drivers/s390/crypto/zcrypt_ccamisc.h
index 77b6cc7b8f82..3a9876d5ab0e 100644
--- a/drivers/s390/crypto/zcrypt_ccamisc.h
+++ b/drivers/s390/crypto/zcrypt_ccamisc.h
@@ -19,6 +19,7 @@
 
 /* For TOKTYPE_NON_CCA: */
 #define TOKVER_PROTECTED_KEY	0x01 /* Protected key token */
+#define TOKVER_CLEAR_KEY	0x02 /* Clear key token */
 
 /* For TOKTYPE_CCA_INTERNAL: */
 #define TOKVER_CCA_AES		0x04 /* CCA AES key token */
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index 6fabc906114c..9a9d02e19774 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -19,6 +19,7 @@
 #include "zcrypt_error.h"
 #include "zcrypt_cex4.h"
 #include "zcrypt_ccamisc.h"
+#include "zcrypt_ep11misc.h"
 
 #define CEX4A_MIN_MOD_SIZE	  1	/*    8 bits	*/
 #define CEX4A_MAX_MOD_SIZE_2K	256	/* 2048 bits	*/
@@ -71,11 +72,11 @@ static struct ap_device_id zcrypt_cex4_queue_ids[] = {
 MODULE_DEVICE_TABLE(ap, zcrypt_cex4_queue_ids);
 
 /*
- * CCA card addditional device attributes
+ * CCA card additional device attributes
  */
-static ssize_t serialnr_show(struct device *dev,
-			     struct device_attribute *attr,
-			     char *buf)
+static ssize_t cca_serialnr_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
 {
 	struct cca_info ci;
 	struct ap_card *ac = to_ap_card(dev);
@@ -88,23 +89,25 @@ static ssize_t serialnr_show(struct device *dev,
 
 	return snprintf(buf, PAGE_SIZE, "%s\n", ci.serial);
 }
-static DEVICE_ATTR_RO(serialnr);
+
+static struct device_attribute dev_attr_cca_serialnr =
+	__ATTR(serialnr, 0444, cca_serialnr_show, NULL);
 
 static struct attribute *cca_card_attrs[] = {
-	&dev_attr_serialnr.attr,
+	&dev_attr_cca_serialnr.attr,
 	NULL,
 };
 
-static const struct attribute_group cca_card_attr_group = {
+static const struct attribute_group cca_card_attr_grp = {
 	.attrs = cca_card_attrs,
 };
 
-/*
- * CCA queue addditional device attributes
- */
-static ssize_t mkvps_show(struct device *dev,
-			  struct device_attribute *attr,
-			  char *buf)
+ /*
+  * CCA queue additional device attributes
+  */
+static ssize_t cca_mkvps_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
 {
 	int n = 0;
 	struct cca_info ci;
@@ -138,17 +141,233 @@ static ssize_t mkvps_show(struct device *dev,
 
 	return n;
 }
-static DEVICE_ATTR_RO(mkvps);
+
+static struct device_attribute dev_attr_cca_mkvps =
+	__ATTR(mkvps, 0444, cca_mkvps_show, NULL);
 
 static struct attribute *cca_queue_attrs[] = {
-	&dev_attr_mkvps.attr,
+	&dev_attr_cca_mkvps.attr,
 	NULL,
 };
 
-static const struct attribute_group cca_queue_attr_group = {
+static const struct attribute_group cca_queue_attr_grp = {
 	.attrs = cca_queue_attrs,
 };
 
+/*
+ * EP11 card additional device attributes
+ */
+static ssize_t ep11_api_ordinalnr_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct ep11_card_info ci;
+	struct ap_card *ac = to_ap_card(dev);
+	struct zcrypt_card *zc = ac->private;
+
+	memset(&ci, 0, sizeof(ci));
+
+	ep11_get_card_info(ac->id, &ci, zc->online);
+
+	if (ci.API_ord_nr > 0)
+		return snprintf(buf, PAGE_SIZE, "%u\n", ci.API_ord_nr);
+	else
+		return snprintf(buf, PAGE_SIZE, "\n");
+}
+
+static struct device_attribute dev_attr_ep11_api_ordinalnr =
+	__ATTR(API_ordinalnr, 0444, ep11_api_ordinalnr_show, NULL);
+
+static ssize_t ep11_fw_version_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct ep11_card_info ci;
+	struct ap_card *ac = to_ap_card(dev);
+	struct zcrypt_card *zc = ac->private;
+
+	memset(&ci, 0, sizeof(ci));
+
+	ep11_get_card_info(ac->id, &ci, zc->online);
+
+	if (ci.FW_version > 0)
+		return snprintf(buf, PAGE_SIZE, "%d.%d\n",
+				(int)(ci.FW_version >> 8),
+				(int)(ci.FW_version & 0xFF));
+	else
+		return snprintf(buf, PAGE_SIZE, "\n");
+}
+
+static struct device_attribute dev_attr_ep11_fw_version =
+	__ATTR(FW_version, 0444, ep11_fw_version_show, NULL);
+
+static ssize_t ep11_serialnr_show(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	struct ep11_card_info ci;
+	struct ap_card *ac = to_ap_card(dev);
+	struct zcrypt_card *zc = ac->private;
+
+	memset(&ci, 0, sizeof(ci));
+
+	ep11_get_card_info(ac->id, &ci, zc->online);
+
+	if (ci.serial[0])
+		return snprintf(buf, PAGE_SIZE, "%16.16s\n", ci.serial);
+	else
+		return snprintf(buf, PAGE_SIZE, "\n");
+}
+
+static struct device_attribute dev_attr_ep11_serialnr =
+	__ATTR(serialnr, 0444, ep11_serialnr_show, NULL);
+
+static const struct {
+	int	    mode_bit;
+	const char *mode_txt;
+} ep11_op_modes[] = {
+	{ 0, "FIPS2009" },
+	{ 1, "BSI2009" },
+	{ 2, "FIPS2011" },
+	{ 3, "BSI2011" },
+	{ 6, "BSICC2017" },
+	{ 0, NULL }
+};
+
+static ssize_t ep11_card_op_modes_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	int i, n = 0;
+	struct ep11_card_info ci;
+	struct ap_card *ac = to_ap_card(dev);
+	struct zcrypt_card *zc = ac->private;
+
+	memset(&ci, 0, sizeof(ci));
+
+	ep11_get_card_info(ac->id, &ci, zc->online);
+
+	for (i = 0; ep11_op_modes[i].mode_txt; i++) {
+		if (ci.op_mode & (1 << ep11_op_modes[i].mode_bit)) {
+			if (n > 0)
+				buf[n++] = ' ';
+			n += snprintf(buf + n, PAGE_SIZE - n,
+				      "%s", ep11_op_modes[i].mode_txt);
+		}
+	}
+	n += snprintf(buf + n, PAGE_SIZE - n, "\n");
+
+	return n;
+}
+
+static struct device_attribute dev_attr_ep11_card_op_modes =
+	__ATTR(op_modes, 0444, ep11_card_op_modes_show, NULL);
+
+static struct attribute *ep11_card_attrs[] = {
+	&dev_attr_ep11_api_ordinalnr.attr,
+	&dev_attr_ep11_fw_version.attr,
+	&dev_attr_ep11_serialnr.attr,
+	&dev_attr_ep11_card_op_modes.attr,
+	NULL,
+};
+
+static const struct attribute_group ep11_card_attr_grp = {
+	.attrs = ep11_card_attrs,
+};
+
+/*
+ * EP11 queue additional device attributes
+ */
+
+static ssize_t ep11_mkvps_show(struct device *dev,
+			       struct device_attribute *attr,
+			       char *buf)
+{
+	int n = 0;
+	struct ep11_domain_info di;
+	struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+	static const char * const cwk_state[] = { "invalid", "valid" };
+	static const char * const nwk_state[] = { "empty", "uncommitted",
+						  "committed" };
+
+	memset(&di, 0, sizeof(di));
+
+	if (zq->online)
+		ep11_get_domain_info(AP_QID_CARD(zq->queue->qid),
+				     AP_QID_QUEUE(zq->queue->qid),
+				     &di);
+
+	if (di.cur_wk_state == '0') {
+		n = snprintf(buf, PAGE_SIZE, "WK CUR: %s -\n",
+			     cwk_state[di.cur_wk_state - '0']);
+	} else if (di.cur_wk_state == '1') {
+		n = snprintf(buf, PAGE_SIZE, "WK CUR: %s 0x",
+			     cwk_state[di.cur_wk_state - '0']);
+		bin2hex(buf + n, di.cur_wkvp, sizeof(di.cur_wkvp));
+		n += 2 * sizeof(di.cur_wkvp);
+		n += snprintf(buf + n, PAGE_SIZE - n, "\n");
+	} else
+		n = snprintf(buf, PAGE_SIZE, "WK CUR: - -\n");
+
+	if (di.new_wk_state == '0') {
+		n += snprintf(buf + n, PAGE_SIZE - n, "WK NEW: %s -\n",
+			      nwk_state[di.new_wk_state - '0']);
+	} else if (di.new_wk_state >= '1' && di.new_wk_state <= '2') {
+		n += snprintf(buf + n, PAGE_SIZE - n, "WK NEW: %s 0x",
+			      nwk_state[di.new_wk_state - '0']);
+		bin2hex(buf + n, di.new_wkvp, sizeof(di.new_wkvp));
+		n += 2 * sizeof(di.new_wkvp);
+		n += snprintf(buf + n, PAGE_SIZE - n, "\n");
+	} else
+		n += snprintf(buf + n, PAGE_SIZE - n, "WK NEW: - -\n");
+
+	return n;
+}
+
+static struct device_attribute dev_attr_ep11_mkvps =
+	__ATTR(mkvps, 0444, ep11_mkvps_show, NULL);
+
+static ssize_t ep11_queue_op_modes_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	int i, n = 0;
+	struct ep11_domain_info di;
+	struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+
+	memset(&di, 0, sizeof(di));
+
+	if (zq->online)
+		ep11_get_domain_info(AP_QID_CARD(zq->queue->qid),
+				     AP_QID_QUEUE(zq->queue->qid),
+				     &di);
+
+	for (i = 0; ep11_op_modes[i].mode_txt; i++) {
+		if (di.op_mode & (1 << ep11_op_modes[i].mode_bit)) {
+			if (n > 0)
+				buf[n++] = ' ';
+			n += snprintf(buf + n, PAGE_SIZE - n,
+				      "%s", ep11_op_modes[i].mode_txt);
+		}
+	}
+	n += snprintf(buf + n, PAGE_SIZE - n, "\n");
+
+	return n;
+}
+
+static struct device_attribute dev_attr_ep11_queue_op_modes =
+	__ATTR(op_modes, 0444, ep11_queue_op_modes_show, NULL);
+
+static struct attribute *ep11_queue_attrs[] = {
+	&dev_attr_ep11_mkvps.attr,
+	&dev_attr_ep11_queue_op_modes.attr,
+	NULL,
+};
+
+static const struct attribute_group ep11_queue_attr_grp = {
+	.attrs = ep11_queue_attrs,
+};
+
 /**
  * Probe function for CEX4/CEX5/CEX6/CEX7 card device. It always
  * accepts the AP device since the bus_match already checked
@@ -313,7 +532,12 @@ static int zcrypt_cex4_card_probe(struct ap_device *ap_dev)
 
 	if (ap_test_bit(&ac->functions, AP_FUNC_COPRO)) {
 		rc = sysfs_create_group(&ap_dev->device.kobj,
-					&cca_card_attr_group);
+					&cca_card_attr_grp);
+		if (rc)
+			zcrypt_card_unregister(zc);
+	} else if (ap_test_bit(&ac->functions, AP_FUNC_EP11)) {
+		rc = sysfs_create_group(&ap_dev->device.kobj,
+					&ep11_card_attr_grp);
 		if (rc)
 			zcrypt_card_unregister(zc);
 	}
@@ -332,7 +556,9 @@ static void zcrypt_cex4_card_remove(struct ap_device *ap_dev)
 	struct zcrypt_card *zc = ac->private;
 
 	if (ap_test_bit(&ac->functions, AP_FUNC_COPRO))
-		sysfs_remove_group(&ap_dev->device.kobj, &cca_card_attr_group);
+		sysfs_remove_group(&ap_dev->device.kobj, &cca_card_attr_grp);
+	else if (ap_test_bit(&ac->functions, AP_FUNC_EP11))
+		sysfs_remove_group(&ap_dev->device.kobj, &ep11_card_attr_grp);
 	if (zc)
 		zcrypt_card_unregister(zc);
 }
@@ -394,7 +620,12 @@ static int zcrypt_cex4_queue_probe(struct ap_device *ap_dev)
 
 	if (ap_test_bit(&aq->card->functions, AP_FUNC_COPRO)) {
 		rc = sysfs_create_group(&ap_dev->device.kobj,
-					&cca_queue_attr_group);
+					&cca_queue_attr_grp);
+		if (rc)
+			zcrypt_queue_unregister(zq);
+	} else if (ap_test_bit(&aq->card->functions, AP_FUNC_EP11)) {
+		rc = sysfs_create_group(&ap_dev->device.kobj,
+					&ep11_queue_attr_grp);
 		if (rc)
 			zcrypt_queue_unregister(zq);
 	}
@@ -413,7 +644,9 @@ static void zcrypt_cex4_queue_remove(struct ap_device *ap_dev)
 	struct zcrypt_queue *zq = aq->private;
 
 	if (ap_test_bit(&aq->card->functions, AP_FUNC_COPRO))
-		sysfs_remove_group(&ap_dev->device.kobj, &cca_queue_attr_group);
+		sysfs_remove_group(&ap_dev->device.kobj, &cca_queue_attr_grp);
+	else if (ap_test_bit(&aq->card->functions, AP_FUNC_EP11))
+		sysfs_remove_group(&ap_dev->device.kobj, &ep11_queue_attr_grp);
 	if (zq)
 		zcrypt_queue_unregister(zq);
 }
diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c
new file mode 100644
index 000000000000..d4caf46ff9df
--- /dev/null
+++ b/drivers/s390/crypto/zcrypt_ep11misc.c
@@ -0,0 +1,1293 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *  Copyright IBM Corp. 2019
+ *  Author(s): Harald Freudenberger <freude@linux.ibm.com>
+ *
+ *  Collection of EP11 misc functions used by zcrypt and pkey
+ */
+
+#define KMSG_COMPONENT "zcrypt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/random.h>
+#include <asm/zcrypt.h>
+#include <asm/pkey.h>
+
+#include "ap_bus.h"
+#include "zcrypt_api.h"
+#include "zcrypt_debug.h"
+#include "zcrypt_msgtype6.h"
+#include "zcrypt_ep11misc.h"
+#include "zcrypt_ccamisc.h"
+
+#define DEBUG_DBG(...)	ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__)
+#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__)
+#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__)
+#define DEBUG_ERR(...)	ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__)
+
+/* default iv used here */
+static const u8 def_iv[16] = { 0x00, 0x11, 0x22, 0x33, 0x44, 0x55, 0x66, 0x77,
+			       0x88, 0x99, 0xaa, 0xbb, 0xcc, 0xdd, 0xee, 0xff };
+
+/* ep11 card info cache */
+struct card_list_entry {
+	struct list_head list;
+	u16 cardnr;
+	struct ep11_card_info info;
+};
+static LIST_HEAD(card_list);
+static DEFINE_SPINLOCK(card_list_lock);
+
+static int card_cache_fetch(u16 cardnr, struct ep11_card_info *ci)
+{
+	int rc = -ENOENT;
+	struct card_list_entry *ptr;
+
+	spin_lock_bh(&card_list_lock);
+	list_for_each_entry(ptr, &card_list, list) {
+		if (ptr->cardnr == cardnr) {
+			memcpy(ci, &ptr->info, sizeof(*ci));
+			rc = 0;
+			break;
+		}
+	}
+	spin_unlock_bh(&card_list_lock);
+
+	return rc;
+}
+
+static void card_cache_update(u16 cardnr, const struct ep11_card_info *ci)
+{
+	int found = 0;
+	struct card_list_entry *ptr;
+
+	spin_lock_bh(&card_list_lock);
+	list_for_each_entry(ptr, &card_list, list) {
+		if (ptr->cardnr == cardnr) {
+			memcpy(&ptr->info, ci, sizeof(*ci));
+			found = 1;
+			break;
+		}
+	}
+	if (!found) {
+		ptr = kmalloc(sizeof(*ptr), GFP_ATOMIC);
+		if (!ptr) {
+			spin_unlock_bh(&card_list_lock);
+			return;
+		}
+		ptr->cardnr = cardnr;
+		memcpy(&ptr->info, ci, sizeof(*ci));
+		list_add(&ptr->list, &card_list);
+	}
+	spin_unlock_bh(&card_list_lock);
+}
+
+static void card_cache_scrub(u16 cardnr)
+{
+	struct card_list_entry *ptr;
+
+	spin_lock_bh(&card_list_lock);
+	list_for_each_entry(ptr, &card_list, list) {
+		if (ptr->cardnr == cardnr) {
+			list_del(&ptr->list);
+			kfree(ptr);
+			break;
+		}
+	}
+	spin_unlock_bh(&card_list_lock);
+}
+
+static void __exit card_cache_free(void)
+{
+	struct card_list_entry *ptr, *pnext;
+
+	spin_lock_bh(&card_list_lock);
+	list_for_each_entry_safe(ptr, pnext, &card_list, list) {
+		list_del(&ptr->list);
+		kfree(ptr);
+	}
+	spin_unlock_bh(&card_list_lock);
+}
+
+/*
+ * Simple check if the key blob is a valid EP11 secure AES key.
+ */
+int ep11_check_aeskeyblob(debug_info_t *dbg, int dbflvl,
+			  const u8 *key, int keybitsize,
+			  int checkcpacfexport)
+{
+	struct ep11keyblob *kb = (struct ep11keyblob *) key;
+
+#define DBF(...) debug_sprintf_event(dbg, dbflvl, ##__VA_ARGS__)
+
+	if (kb->head.type != TOKTYPE_NON_CCA) {
+		if (dbg)
+			DBF("%s key check failed, type 0x%02x != 0x%02x\n",
+			    __func__, (int) kb->head.type, TOKTYPE_NON_CCA);
+		return -EINVAL;
+	}
+	if (kb->head.version != TOKVER_EP11_AES) {
+		if (dbg)
+			DBF("%s key check failed, version 0x%02x != 0x%02x\n",
+			    __func__, (int) kb->head.version, TOKVER_EP11_AES);
+		return -EINVAL;
+	}
+	if (kb->version != EP11_STRUCT_MAGIC) {
+		if (dbg)
+			DBF("%s key check failed, magic 0x%04x != 0x%04x\n",
+			    __func__, (int) kb->version, EP11_STRUCT_MAGIC);
+		return -EINVAL;
+	}
+	switch (kb->head.keybitlen) {
+	case 128:
+	case 192:
+	case 256:
+		break;
+	default:
+		if (dbg)
+			DBF("%s key check failed, keybitlen %d invalid\n",
+			    __func__, (int) kb->head.keybitlen);
+		return -EINVAL;
+	}
+	if (keybitsize > 0 && keybitsize != (int) kb->head.keybitlen) {
+		DBF("%s key check failed, keybitsize %d\n",
+		    __func__, keybitsize);
+		return -EINVAL;
+	}
+	if (checkcpacfexport && !(kb->attr & EP11_BLOB_PKEY_EXTRACTABLE)) {
+		if (dbg)
+			DBF("%s key check failed, PKEY_EXTRACTABLE is 0\n",
+			    __func__);
+		return -EINVAL;
+	}
+#undef DBF
+
+	return 0;
+}
+EXPORT_SYMBOL(ep11_check_aeskeyblob);
+
+/*
+ * Helper function which calls zcrypt_send_ep11_cprb with
+ * memory management segment adjusted to kernel space
+ * so that the copy_from_user called within this
+ * function do in fact copy from kernel space.
+ */
+static inline int _zcrypt_send_ep11_cprb(struct ep11_urb *urb)
+{
+	int rc;
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
+	rc = zcrypt_send_ep11_cprb(urb);
+	set_fs(old_fs);
+
+	return rc;
+}
+
+/*
+ * Allocate and prepare ep11 cprb plus additional payload.
+ */
+static inline struct ep11_cprb *alloc_cprb(size_t payload_len)
+{
+	size_t len = sizeof(struct ep11_cprb) + payload_len;
+	struct ep11_cprb *cprb;
+
+	cprb = kmalloc(len, GFP_KERNEL);
+	if (!cprb)
+		return NULL;
+
+	memset(cprb, 0, len);
+	cprb->cprb_len = sizeof(struct ep11_cprb);
+	cprb->cprb_ver_id = 0x04;
+	memcpy(cprb->func_id, "T4", 2);
+	cprb->ret_code = 0xFFFFFFFF;
+	cprb->payload_len = payload_len;
+
+	return cprb;
+}
+
+/*
+ * Some helper functions related to ASN1 encoding.
+ * Limited to length info <= 2 byte.
+ */
+
+#define ASN1TAGLEN(x) (2 + (x) + ((x) > 127 ? 1 : 0) + ((x) > 255 ? 1 : 0))
+
+static int asn1tag_write(u8 *ptr, u8 tag, const u8 *pvalue, u16 valuelen)
+{
+	ptr[0] = tag;
+	if (valuelen > 255) {
+		ptr[1] = 0x82;
+		*((u16 *)(ptr + 2)) = valuelen;
+		memcpy(ptr + 4, pvalue, valuelen);
+		return 4 + valuelen;
+	}
+	if (valuelen > 127) {
+		ptr[1] = 0x81;
+		ptr[2] = (u8) valuelen;
+		memcpy(ptr + 3, pvalue, valuelen);
+		return 3 + valuelen;
+	}
+	ptr[1] = (u8) valuelen;
+	memcpy(ptr + 2, pvalue, valuelen);
+	return 2 + valuelen;
+}
+
+/* EP11 payload > 127 bytes starts with this struct */
+struct pl_head {
+	u8  tag;
+	u8  lenfmt;
+	u16 len;
+	u8  func_tag;
+	u8  func_len;
+	u32 func;
+	u8  dom_tag;
+	u8  dom_len;
+	u32 dom;
+} __packed;
+
+/* prep ep11 payload head helper function */
+static inline void prep_head(struct pl_head *h,
+			     size_t pl_size, int api, int func)
+{
+	h->tag = 0x30;
+	h->lenfmt = 0x82;
+	h->len = pl_size - 4;
+	h->func_tag = 0x04;
+	h->func_len = sizeof(u32);
+	h->func = (api << 16) + func;
+	h->dom_tag = 0x04;
+	h->dom_len = sizeof(u32);
+}
+
+/* prep urb helper function */
+static inline void prep_urb(struct ep11_urb *u,
+			    struct ep11_target_dev *t, int nt,
+			    struct ep11_cprb *req, size_t req_len,
+			    struct ep11_cprb *rep, size_t rep_len)
+{
+	u->targets = (u8 __user *) t;
+	u->targets_num = nt;
+	u->req = (u8 __user *) req;
+	u->req_len = req_len;
+	u->resp = (u8 __user *) rep;
+	u->resp_len = rep_len;
+}
+
+/* Check ep11 reply payload, return 0 or suggested errno value. */
+static int check_reply_pl(const u8 *pl, const char *func)
+{
+	int len;
+	u32 ret;
+
+	/* start tag */
+	if (*pl++ != 0x30) {
+		DEBUG_ERR("%s reply start tag mismatch\n", func);
+		return -EIO;
+	}
+
+	/* payload length format */
+	if (*pl < 127) {
+		len = *pl;
+		pl++;
+	} else if (*pl == 0x81) {
+		pl++;
+		len = *pl;
+		pl++;
+	} else if (*pl == 0x82) {
+		pl++;
+		len = *((u16 *)pl);
+		pl += 2;
+	} else {
+		DEBUG_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n",
+			  func, *pl);
+		return -EIO;
+	}
+
+	/* len should cover at least 3 fields with 32 bit value each */
+	if (len < 3 * 6) {
+		DEBUG_ERR("%s reply length %d too small\n", func, len);
+		return -EIO;
+	}
+
+	/* function tag, length and value */
+	if (pl[0] != 0x04 || pl[1] != 0x04) {
+		DEBUG_ERR("%s function tag or length mismatch\n", func);
+		return -EIO;
+	}
+	pl += 6;
+
+	/* dom tag, length and value */
+	if (pl[0] != 0x04 || pl[1] != 0x04) {
+		DEBUG_ERR("%s dom tag or length mismatch\n", func);
+		return -EIO;
+	}
+	pl += 6;
+
+	/* return value tag, length and value */
+	if (pl[0] != 0x04 || pl[1] != 0x04) {
+		DEBUG_ERR("%s return value tag or length mismatch\n", func);
+		return -EIO;
+	}
+	pl += 2;
+	ret = *((u32 *)pl);
+	if (ret != 0) {
+		DEBUG_ERR("%s return value 0x%04x != 0\n", func, ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+
+/*
+ * Helper function which does an ep11 query with given query type.
+ */
+static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type,
+			   size_t buflen, u8 *buf)
+{
+	struct ep11_info_req_pl {
+		struct pl_head head;
+		u8  query_type_tag;
+		u8  query_type_len;
+		u32 query_type;
+		u8  query_subtype_tag;
+		u8  query_subtype_len;
+		u32 query_subtype;
+	} __packed * req_pl;
+	struct ep11_info_rep_pl {
+		struct pl_head head;
+		u8  rc_tag;
+		u8  rc_len;
+		u32 rc;
+		u8  data_tag;
+		u8  data_lenfmt;
+		u16 data_len;
+	} __packed * rep_pl;
+	struct ep11_cprb *req = NULL, *rep = NULL;
+	struct ep11_target_dev target;
+	struct ep11_urb *urb = NULL;
+	int api = 1, rc = -ENOMEM;
+
+	/* request cprb and payload */
+	req = alloc_cprb(sizeof(struct ep11_info_req_pl));
+	if (!req)
+		goto out;
+	req_pl = (struct ep11_info_req_pl *) (((u8 *) req) + sizeof(*req));
+	prep_head(&req_pl->head, sizeof(*req_pl), api, 38); /* get xcp info */
+	req_pl->query_type_tag = 0x04;
+	req_pl->query_type_len = sizeof(u32);
+	req_pl->query_type = query_type;
+	req_pl->query_subtype_tag = 0x04;
+	req_pl->query_subtype_len = sizeof(u32);
+
+	/* reply cprb and payload */
+	rep = alloc_cprb(sizeof(struct ep11_info_rep_pl) + buflen);
+	if (!rep)
+		goto out;
+	rep_pl = (struct ep11_info_rep_pl *) (((u8 *) rep) + sizeof(*rep));
+
+	/* urb and target */
+	urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL);
+	if (!urb)
+		goto out;
+	target.ap_id = cardnr;
+	target.dom_id = domain;
+	prep_urb(urb, &target, 1,
+		 req, sizeof(*req) + sizeof(*req_pl),
+		 rep, sizeof(*rep) + sizeof(*rep_pl) + buflen);
+
+	rc = _zcrypt_send_ep11_cprb(urb);
+	if (rc) {
+		DEBUG_ERR(
+			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			__func__, (int) cardnr, (int) domain, rc);
+		goto out;
+	}
+
+	rc = check_reply_pl((u8 *)rep_pl, __func__);
+	if (rc)
+		goto out;
+	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
+		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		rc = -EIO;
+		goto out;
+	}
+	if (rep_pl->data_len > buflen) {
+		DEBUG_ERR("%s mismatch between reply data len and buffer len\n",
+			  __func__);
+		rc = -ENOSPC;
+		goto out;
+	}
+
+	memcpy(buf, ((u8 *) rep_pl) + sizeof(*rep_pl), rep_pl->data_len);
+
+out:
+	kfree(req);
+	kfree(rep);
+	kfree(urb);
+	return rc;
+}
+
+/*
+ * Provide information about an EP11 card.
+ */
+int ep11_get_card_info(u16 card, struct ep11_card_info *info, int verify)
+{
+	int rc;
+	struct ep11_module_query_info {
+		u32 API_ord_nr;
+		u32 firmware_id;
+		u8  FW_major_vers;
+		u8  FW_minor_vers;
+		u8  CSP_major_vers;
+		u8  CSP_minor_vers;
+		u8  fwid[32];
+		u8  xcp_config_hash[32];
+		u8  CSP_config_hash[32];
+		u8  serial[16];
+		u8  module_date_time[16];
+		u64 op_mode;
+		u32 PKCS11_flags;
+		u32 ext_flags;
+		u32 domains;
+		u32 sym_state_bytes;
+		u32 digest_state_bytes;
+		u32 pin_blob_bytes;
+		u32 SPKI_bytes;
+		u32 priv_key_blob_bytes;
+		u32 sym_blob_bytes;
+		u32 max_payload_bytes;
+		u32 CP_profile_bytes;
+		u32 max_CP_index;
+	} __packed * pmqi = NULL;
+
+	rc = card_cache_fetch(card, info);
+	if (rc || verify) {
+		pmqi = kmalloc(sizeof(*pmqi), GFP_KERNEL);
+		if (!pmqi)
+			return -ENOMEM;
+		rc = ep11_query_info(card, AUTOSEL_DOM,
+				     0x01 /* module info query */,
+				     sizeof(*pmqi), (u8 *) pmqi);
+		if (rc) {
+			if (rc == -ENODEV)
+				card_cache_scrub(card);
+			goto out;
+		}
+		memset(info, 0, sizeof(*info));
+		info->API_ord_nr = pmqi->API_ord_nr;
+		info->FW_version =
+			(pmqi->FW_major_vers << 8) + pmqi->FW_minor_vers;
+		memcpy(info->serial, pmqi->serial, sizeof(info->serial));
+		info->op_mode = pmqi->op_mode;
+		card_cache_update(card, info);
+	}
+
+out:
+	kfree(pmqi);
+	return rc;
+}
+EXPORT_SYMBOL(ep11_get_card_info);
+
+/*
+ * Provide information about a domain within an EP11 card.
+ */
+int ep11_get_domain_info(u16 card, u16 domain, struct ep11_domain_info *info)
+{
+	int rc;
+	struct ep11_domain_query_info {
+		u32 dom_index;
+		u8  cur_WK_VP[32];
+		u8  new_WK_VP[32];
+		u32 dom_flags;
+		u64 op_mode;
+	} __packed * p_dom_info;
+
+	p_dom_info = kmalloc(sizeof(*p_dom_info), GFP_KERNEL);
+	if (!p_dom_info)
+		return -ENOMEM;
+
+	rc = ep11_query_info(card, domain, 0x03 /* domain info query */,
+			     sizeof(*p_dom_info), (u8 *) p_dom_info);
+	if (rc)
+		goto out;
+
+	memset(info, 0, sizeof(*info));
+	info->cur_wk_state = '0';
+	info->new_wk_state = '0';
+	if (p_dom_info->dom_flags & 0x10 /* left imprint mode */) {
+		if (p_dom_info->dom_flags & 0x02 /* cur wk valid */) {
+			info->cur_wk_state = '1';
+			memcpy(info->cur_wkvp, p_dom_info->cur_WK_VP, 32);
+		}
+		if (p_dom_info->dom_flags & 0x04 /* new wk present */
+		    || p_dom_info->dom_flags & 0x08 /* new wk committed */) {
+			info->new_wk_state =
+				p_dom_info->dom_flags & 0x08 ? '2' : '1';
+			memcpy(info->new_wkvp, p_dom_info->new_WK_VP, 32);
+		}
+	}
+	info->op_mode = p_dom_info->op_mode;
+
+out:
+	kfree(p_dom_info);
+	return rc;
+}
+EXPORT_SYMBOL(ep11_get_domain_info);
+
+/*
+ * Default EP11 AES key generate attributes, used when no keygenflags given:
+ * XCP_BLOB_ENCRYPT | XCP_BLOB_DECRYPT | XCP_BLOB_PROTKEY_EXTRACTABLE
+ */
+#define KEY_ATTR_DEFAULTS 0x00200c00
+
+int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
+		   u8 *keybuf, size_t *keybufsize)
+{
+	struct keygen_req_pl {
+		struct pl_head head;
+		u8  var_tag;
+		u8  var_len;
+		u32 var;
+		u8  keybytes_tag;
+		u8  keybytes_len;
+		u32 keybytes;
+		u8  mech_tag;
+		u8  mech_len;
+		u32 mech;
+		u8  attr_tag;
+		u8  attr_len;
+		u32 attr_header;
+		u32 attr_bool_mask;
+		u32 attr_bool_bits;
+		u32 attr_val_len_type;
+		u32 attr_val_len_value;
+		u8  pin_tag;
+		u8  pin_len;
+	} __packed * req_pl;
+	struct keygen_rep_pl {
+		struct pl_head head;
+		u8  rc_tag;
+		u8  rc_len;
+		u32 rc;
+		u8  data_tag;
+		u8  data_lenfmt;
+		u16 data_len;
+		u8  data[512];
+	} __packed * rep_pl;
+	struct ep11_cprb *req = NULL, *rep = NULL;
+	struct ep11_target_dev target;
+	struct ep11_urb *urb = NULL;
+	struct ep11keyblob *kb;
+	int api, rc = -ENOMEM;
+
+	switch (keybitsize) {
+	case 128:
+	case 192:
+	case 256:
+		break;
+	default:
+		DEBUG_ERR(
+			"%s unknown/unsupported keybitsize %d\n",
+			__func__, keybitsize);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/* request cprb and payload */
+	req = alloc_cprb(sizeof(struct keygen_req_pl));
+	if (!req)
+		goto out;
+	req_pl = (struct keygen_req_pl *) (((u8 *) req) + sizeof(*req));
+	api = (!keygenflags || keygenflags & 0x00200000) ? 4 : 1;
+	prep_head(&req_pl->head, sizeof(*req_pl), api, 21); /* GenerateKey */
+	req_pl->var_tag = 0x04;
+	req_pl->var_len = sizeof(u32);
+	req_pl->keybytes_tag = 0x04;
+	req_pl->keybytes_len = sizeof(u32);
+	req_pl->keybytes = keybitsize / 8;
+	req_pl->mech_tag = 0x04;
+	req_pl->mech_len = sizeof(u32);
+	req_pl->mech = 0x00001080; /* CKM_AES_KEY_GEN */
+	req_pl->attr_tag = 0x04;
+	req_pl->attr_len = 5 * sizeof(u32);
+	req_pl->attr_header = 0x10010000;
+	req_pl->attr_bool_mask = keygenflags ? keygenflags : KEY_ATTR_DEFAULTS;
+	req_pl->attr_bool_bits = keygenflags ? keygenflags : KEY_ATTR_DEFAULTS;
+	req_pl->attr_val_len_type = 0x00000161; /* CKA_VALUE_LEN */
+	req_pl->attr_val_len_value = keybitsize / 8;
+	req_pl->pin_tag = 0x04;
+
+	/* reply cprb and payload */
+	rep = alloc_cprb(sizeof(struct keygen_rep_pl));
+	if (!rep)
+		goto out;
+	rep_pl = (struct keygen_rep_pl *) (((u8 *) rep) + sizeof(*rep));
+
+	/* urb and target */
+	urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL);
+	if (!urb)
+		goto out;
+	target.ap_id = card;
+	target.dom_id = domain;
+	prep_urb(urb, &target, 1,
+		 req, sizeof(*req) + sizeof(*req_pl),
+		 rep, sizeof(*rep) + sizeof(*rep_pl));
+
+	rc = _zcrypt_send_ep11_cprb(urb);
+	if (rc) {
+		DEBUG_ERR(
+			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			__func__, (int) card, (int) domain, rc);
+		goto out;
+	}
+
+	rc = check_reply_pl((u8 *)rep_pl, __func__);
+	if (rc)
+		goto out;
+	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
+		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		rc = -EIO;
+		goto out;
+	}
+	if (rep_pl->data_len > *keybufsize) {
+		DEBUG_ERR("%s mismatch reply data len / key buffer len\n",
+			  __func__);
+		rc = -ENOSPC;
+		goto out;
+	}
+
+	/* copy key blob and set header values */
+	memcpy(keybuf, rep_pl->data, rep_pl->data_len);
+	*keybufsize = rep_pl->data_len;
+	kb = (struct ep11keyblob *) keybuf;
+	kb->head.type = TOKTYPE_NON_CCA;
+	kb->head.len = rep_pl->data_len;
+	kb->head.version = TOKVER_EP11_AES;
+	kb->head.keybitlen = keybitsize;
+
+out:
+	kfree(req);
+	kfree(rep);
+	kfree(urb);
+	return rc;
+}
+EXPORT_SYMBOL(ep11_genaeskey);
+
+static int ep11_cryptsingle(u16 card, u16 domain,
+			    u16 mode, u32 mech, const u8 *iv,
+			    const u8 *key, size_t keysize,
+			    const u8 *inbuf, size_t inbufsize,
+			    u8 *outbuf, size_t *outbufsize)
+{
+	struct crypt_req_pl {
+		struct pl_head head;
+		u8  var_tag;
+		u8  var_len;
+		u32 var;
+		u8  mech_tag;
+		u8  mech_len;
+		u32 mech;
+		/*
+		 * maybe followed by iv data
+		 * followed by key tag + key blob
+		 * followed by plaintext tag + plaintext
+		 */
+	} __packed * req_pl;
+	struct crypt_rep_pl {
+		struct pl_head head;
+		u8  rc_tag;
+		u8  rc_len;
+		u32 rc;
+		u8  data_tag;
+		u8  data_lenfmt;
+		/* data follows */
+	} __packed * rep_pl;
+	struct ep11_cprb *req = NULL, *rep = NULL;
+	struct ep11_target_dev target;
+	struct ep11_urb *urb = NULL;
+	size_t req_pl_size, rep_pl_size;
+	int n, api = 1, rc = -ENOMEM;
+	u8 *p;
+
+	/* the simple asn1 coding used has length limits */
+	if (keysize > 0xFFFF || inbufsize > 0xFFFF)
+		return -EINVAL;
+
+	/* request cprb and payload */
+	req_pl_size = sizeof(struct crypt_req_pl) + (iv ? 16 : 0)
+		+ ASN1TAGLEN(keysize) + ASN1TAGLEN(inbufsize);
+	req = alloc_cprb(req_pl_size);
+	if (!req)
+		goto out;
+	req_pl = (struct crypt_req_pl *) (((u8 *) req) + sizeof(*req));
+	prep_head(&req_pl->head, req_pl_size, api, (mode ? 20 : 19));
+	req_pl->var_tag = 0x04;
+	req_pl->var_len = sizeof(u32);
+	/* mech is mech + mech params (iv here) */
+	req_pl->mech_tag = 0x04;
+	req_pl->mech_len = sizeof(u32) + (iv ? 16 : 0);
+	req_pl->mech = (mech ? mech : 0x00001085); /* CKM_AES_CBC_PAD */
+	p = ((u8 *) req_pl) + sizeof(*req_pl);
+	if (iv) {
+		memcpy(p, iv, 16);
+		p += 16;
+	}
+	/* key and input data */
+	p += asn1tag_write(p, 0x04, key, keysize);
+	p += asn1tag_write(p, 0x04, inbuf, inbufsize);
+
+	/* reply cprb and payload, assume out data size <= in data size + 32 */
+	rep_pl_size = sizeof(struct crypt_rep_pl) + ASN1TAGLEN(inbufsize + 32);
+	rep = alloc_cprb(rep_pl_size);
+	if (!rep)
+		goto out;
+	rep_pl = (struct crypt_rep_pl *) (((u8 *) rep) + sizeof(*rep));
+
+	/* urb and target */
+	urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL);
+	if (!urb)
+		goto out;
+	target.ap_id = card;
+	target.dom_id = domain;
+	prep_urb(urb, &target, 1,
+		 req, sizeof(*req) + req_pl_size,
+		 rep, sizeof(*rep) + rep_pl_size);
+
+	rc = _zcrypt_send_ep11_cprb(urb);
+	if (rc) {
+		DEBUG_ERR(
+			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			__func__, (int) card, (int) domain, rc);
+		goto out;
+	}
+
+	rc = check_reply_pl((u8 *)rep_pl, __func__);
+	if (rc)
+		goto out;
+	if (rep_pl->data_tag != 0x04) {
+		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		rc = -EIO;
+		goto out;
+	}
+	p = ((u8 *) rep_pl) + sizeof(*rep_pl);
+	if (rep_pl->data_lenfmt <= 127)
+		n = rep_pl->data_lenfmt;
+	else if (rep_pl->data_lenfmt == 0x81)
+		n = *p++;
+	else if (rep_pl->data_lenfmt == 0x82) {
+		n = *((u16 *) p);
+		p += 2;
+	} else {
+		DEBUG_ERR("%s unknown reply data length format 0x%02hhx\n",
+			  __func__, rep_pl->data_lenfmt);
+		rc = -EIO;
+		goto out;
+	}
+	if (n > *outbufsize) {
+		DEBUG_ERR("%s mismatch reply data len %d / output buffer %zu\n",
+			  __func__, n, *outbufsize);
+		rc = -ENOSPC;
+		goto out;
+	}
+
+	memcpy(outbuf, p, n);
+	*outbufsize = n;
+
+out:
+	kfree(req);
+	kfree(rep);
+	kfree(urb);
+	return rc;
+}
+
+static int ep11_unwrapkey(u16 card, u16 domain,
+			  const u8 *kek, size_t keksize,
+			  const u8 *enckey, size_t enckeysize,
+			  u32 mech, const u8 *iv,
+			  u32 keybitsize, u32 keygenflags,
+			  u8 *keybuf, size_t *keybufsize)
+{
+	struct uw_req_pl {
+		struct pl_head head;
+		u8  attr_tag;
+		u8  attr_len;
+		u32 attr_header;
+		u32 attr_bool_mask;
+		u32 attr_bool_bits;
+		u32 attr_key_type;
+		u32 attr_key_type_value;
+		u32 attr_val_len;
+		u32 attr_val_len_value;
+		u8  mech_tag;
+		u8  mech_len;
+		u32 mech;
+		/*
+		 * maybe followed by iv data
+		 * followed by kek tag + kek blob
+		 * followed by empty mac tag
+		 * followed by empty pin tag
+		 * followed by encryted key tag + bytes
+		 */
+	} __packed * req_pl;
+	struct uw_rep_pl {
+		struct pl_head head;
+		u8  rc_tag;
+		u8  rc_len;
+		u32 rc;
+		u8  data_tag;
+		u8  data_lenfmt;
+		u16 data_len;
+		u8  data[512];
+	} __packed * rep_pl;
+	struct ep11_cprb *req = NULL, *rep = NULL;
+	struct ep11_target_dev target;
+	struct ep11_urb *urb = NULL;
+	struct ep11keyblob *kb;
+	size_t req_pl_size;
+	int api, rc = -ENOMEM;
+	u8 *p;
+
+	/* request cprb and payload */
+	req_pl_size = sizeof(struct uw_req_pl) + (iv ? 16 : 0)
+		+ ASN1TAGLEN(keksize) + 4 + ASN1TAGLEN(enckeysize);
+	req = alloc_cprb(req_pl_size);
+	if (!req)
+		goto out;
+	req_pl = (struct uw_req_pl *) (((u8 *) req) + sizeof(*req));
+	api = (!keygenflags || keygenflags & 0x00200000) ? 4 : 1;
+	prep_head(&req_pl->head, req_pl_size, api, 34); /* UnwrapKey */
+	req_pl->attr_tag = 0x04;
+	req_pl->attr_len = 7 * sizeof(u32);
+	req_pl->attr_header = 0x10020000;
+	req_pl->attr_bool_mask = keygenflags ? keygenflags : KEY_ATTR_DEFAULTS;
+	req_pl->attr_bool_bits = keygenflags ? keygenflags : KEY_ATTR_DEFAULTS;
+	req_pl->attr_key_type = 0x00000100; /* CKA_KEY_TYPE */
+	req_pl->attr_key_type_value = 0x0000001f; /* CKK_AES */
+	req_pl->attr_val_len = 0x00000161; /* CKA_VALUE_LEN */
+	req_pl->attr_val_len_value = keybitsize / 8;
+	/* mech is mech + mech params (iv here) */
+	req_pl->mech_tag = 0x04;
+	req_pl->mech_len = sizeof(u32) + (iv ? 16 : 0);
+	req_pl->mech = (mech ? mech : 0x00001085); /* CKM_AES_CBC_PAD */
+	p = ((u8 *) req_pl) + sizeof(*req_pl);
+	if (iv) {
+		memcpy(p, iv, 16);
+		p += 16;
+	}
+	/* kek */
+	p += asn1tag_write(p, 0x04, kek, keksize);
+	/* empty mac key tag */
+	*p++ = 0x04;
+	*p++ = 0;
+	/* empty pin tag */
+	*p++ = 0x04;
+	*p++ = 0;
+	/* encrytped key value tag and bytes */
+	p += asn1tag_write(p, 0x04, enckey, enckeysize);
+
+	/* reply cprb and payload */
+	rep = alloc_cprb(sizeof(struct uw_rep_pl));
+	if (!rep)
+		goto out;
+	rep_pl = (struct uw_rep_pl *) (((u8 *) rep) + sizeof(*rep));
+
+	/* urb and target */
+	urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL);
+	if (!urb)
+		goto out;
+	target.ap_id = card;
+	target.dom_id = domain;
+	prep_urb(urb, &target, 1,
+		 req, sizeof(*req) + req_pl_size,
+		 rep, sizeof(*rep) + sizeof(*rep_pl));
+
+	rc = _zcrypt_send_ep11_cprb(urb);
+	if (rc) {
+		DEBUG_ERR(
+			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			__func__, (int) card, (int) domain, rc);
+		goto out;
+	}
+
+	rc = check_reply_pl((u8 *)rep_pl, __func__);
+	if (rc)
+		goto out;
+	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
+		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		rc = -EIO;
+		goto out;
+	}
+	if (rep_pl->data_len > *keybufsize) {
+		DEBUG_ERR("%s mismatch reply data len / key buffer len\n",
+			  __func__);
+		rc = -ENOSPC;
+		goto out;
+	}
+
+	/* copy key blob and set header values */
+	memcpy(keybuf, rep_pl->data, rep_pl->data_len);
+	*keybufsize = rep_pl->data_len;
+	kb = (struct ep11keyblob *) keybuf;
+	kb->head.type = TOKTYPE_NON_CCA;
+	kb->head.len = rep_pl->data_len;
+	kb->head.version = TOKVER_EP11_AES;
+	kb->head.keybitlen = keybitsize;
+
+out:
+	kfree(req);
+	kfree(rep);
+	kfree(urb);
+	return rc;
+}
+
+static int ep11_wrapkey(u16 card, u16 domain,
+			const u8 *key, size_t keysize,
+			u32 mech, const u8 *iv,
+			u8 *databuf, size_t *datasize)
+{
+	struct wk_req_pl {
+		struct pl_head head;
+		u8  var_tag;
+		u8  var_len;
+		u32 var;
+		u8  mech_tag;
+		u8  mech_len;
+		u32 mech;
+		/*
+		 * followed by iv data
+		 * followed by key tag + key blob
+		 * followed by dummy kek param
+		 * followed by dummy mac param
+		 */
+	} __packed * req_pl;
+	struct wk_rep_pl {
+		struct pl_head head;
+		u8  rc_tag;
+		u8  rc_len;
+		u32 rc;
+		u8  data_tag;
+		u8  data_lenfmt;
+		u16 data_len;
+		u8  data[512];
+	} __packed * rep_pl;
+	struct ep11_cprb *req = NULL, *rep = NULL;
+	struct ep11_target_dev target;
+	struct ep11_urb *urb = NULL;
+	struct ep11keyblob *kb;
+	size_t req_pl_size;
+	int api, rc = -ENOMEM;
+	u8 *p;
+
+	/* request cprb and payload */
+	req_pl_size = sizeof(struct wk_req_pl) + (iv ? 16 : 0)
+		+ ASN1TAGLEN(keysize) + 4;
+	req = alloc_cprb(req_pl_size);
+	if (!req)
+		goto out;
+	if (!mech || mech == 0x80060001)
+		req->flags |= 0x20; /* CPACF_WRAP needs special bit */
+	req_pl = (struct wk_req_pl *) (((u8 *) req) + sizeof(*req));
+	api = (!mech || mech == 0x80060001) ? 4 : 1; /* CKM_IBM_CPACF_WRAP */
+	prep_head(&req_pl->head, req_pl_size, api, 33); /* WrapKey */
+	req_pl->var_tag = 0x04;
+	req_pl->var_len = sizeof(u32);
+	/* mech is mech + mech params (iv here) */
+	req_pl->mech_tag = 0x04;
+	req_pl->mech_len = sizeof(u32) + (iv ? 16 : 0);
+	req_pl->mech = (mech ? mech : 0x80060001); /* CKM_IBM_CPACF_WRAP */
+	p = ((u8 *) req_pl) + sizeof(*req_pl);
+	if (iv) {
+		memcpy(p, iv, 16);
+		p += 16;
+	}
+	/* key blob */
+	p += asn1tag_write(p, 0x04, key, keysize);
+	/* maybe the key argument needs the head data cleaned out */
+	kb = (struct ep11keyblob *)(p - keysize);
+	if (kb->head.version == TOKVER_EP11_AES)
+		memset(&kb->head, 0, sizeof(kb->head));
+	/* empty kek tag */
+	*p++ = 0x04;
+	*p++ = 0;
+	/* empty mac tag */
+	*p++ = 0x04;
+	*p++ = 0;
+
+	/* reply cprb and payload */
+	rep = alloc_cprb(sizeof(struct wk_rep_pl));
+	if (!rep)
+		goto out;
+	rep_pl = (struct wk_rep_pl *) (((u8 *) rep) + sizeof(*rep));
+
+	/* urb and target */
+	urb = kmalloc(sizeof(struct ep11_urb), GFP_KERNEL);
+	if (!urb)
+		goto out;
+	target.ap_id = card;
+	target.dom_id = domain;
+	prep_urb(urb, &target, 1,
+		 req, sizeof(*req) + req_pl_size,
+		 rep, sizeof(*rep) + sizeof(*rep_pl));
+
+	rc = _zcrypt_send_ep11_cprb(urb);
+	if (rc) {
+		DEBUG_ERR(
+			"%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n",
+			__func__, (int) card, (int) domain, rc);
+		goto out;
+	}
+
+	rc = check_reply_pl((u8 *)rep_pl, __func__);
+	if (rc)
+		goto out;
+	if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) {
+		DEBUG_ERR("%s unknown reply data format\n", __func__);
+		rc = -EIO;
+		goto out;
+	}
+	if (rep_pl->data_len > *datasize) {
+		DEBUG_ERR("%s mismatch reply data len / data buffer len\n",
+			  __func__);
+		rc = -ENOSPC;
+		goto out;
+	}
+
+	/* copy the data from the cprb to the data buffer */
+	memcpy(databuf, rep_pl->data, rep_pl->data_len);
+	*datasize = rep_pl->data_len;
+
+out:
+	kfree(req);
+	kfree(rep);
+	kfree(urb);
+	return rc;
+}
+
+int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
+		     const u8 *clrkey, u8 *keybuf, size_t *keybufsize)
+{
+	int rc;
+	struct ep11keyblob *kb;
+	u8 encbuf[64], *kek = NULL;
+	size_t clrkeylen, keklen, encbuflen = sizeof(encbuf);
+
+	if (keybitsize == 128 || keybitsize == 192 || keybitsize == 256)
+		clrkeylen = keybitsize / 8;
+	else {
+		DEBUG_ERR(
+			"%s unknown/unsupported keybitsize %d\n",
+			__func__, keybitsize);
+		return -EINVAL;
+	}
+
+	/* allocate memory for the temp kek */
+	keklen = MAXEP11AESKEYBLOBSIZE;
+	kek = kmalloc(keklen, GFP_ATOMIC);
+	if (!kek) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Step 1: generate AES 256 bit random kek key */
+	rc = ep11_genaeskey(card, domain, 256,
+			    0x00006c00, /* EN/DECRYTP, WRAP/UNWRAP */
+			    kek, &keklen);
+	if (rc) {
+		DEBUG_ERR(
+			"%s generate kek key failed, rc=%d\n",
+			__func__, rc);
+		goto out;
+	}
+	kb = (struct ep11keyblob *) kek;
+	memset(&kb->head, 0, sizeof(kb->head));
+
+	/* Step 2: encrypt clear key value with the kek key */
+	rc = ep11_cryptsingle(card, domain, 0, 0, def_iv, kek, keklen,
+			      clrkey, clrkeylen, encbuf, &encbuflen);
+	if (rc) {
+		DEBUG_ERR(
+			"%s encrypting key value with kek key failed, rc=%d\n",
+			__func__, rc);
+		goto out;
+	}
+
+	/* Step 3: import the encrypted key value as a new key */
+	rc = ep11_unwrapkey(card, domain, kek, keklen,
+			    encbuf, encbuflen, 0, def_iv,
+			    keybitsize, 0, keybuf, keybufsize);
+	if (rc) {
+		DEBUG_ERR(
+			"%s importing key value as new key failed,, rc=%d\n",
+			__func__, rc);
+		goto out;
+	}
+
+out:
+	kfree(kek);
+	return rc;
+}
+EXPORT_SYMBOL(ep11_clr2keyblob);
+
+int ep11_key2protkey(u16 card, u16 dom, const u8 *key, size_t keylen,
+		     u8 *protkey, u32 *protkeylen, u32 *protkeytype)
+{
+	int rc = -EIO;
+	u8 *wkbuf = NULL;
+	size_t wkbuflen = 256;
+	struct wk_info {
+		u16 version;
+		u8  res1[16];
+		u32 pkeytype;
+		u32 pkeybitsize;
+		u64 pkeysize;
+		u8  res2[8];
+		u8  pkey[0];
+	} __packed * wki;
+
+	/* alloc temp working buffer */
+	wkbuf = kmalloc(wkbuflen, GFP_ATOMIC);
+	if (!wkbuf)
+		return -ENOMEM;
+
+	/* ep11 secure key -> protected key + info */
+	rc = ep11_wrapkey(card, dom, key, keylen,
+			  0, def_iv, wkbuf, &wkbuflen);
+	if (rc) {
+		DEBUG_ERR(
+			"%s rewrapping ep11 key to pkey failed, rc=%d\n",
+			__func__, rc);
+		goto out;
+	}
+	wki = (struct wk_info *) wkbuf;
+
+	/* check struct version and pkey type */
+	if (wki->version != 1 || wki->pkeytype != 1) {
+		DEBUG_ERR("%s wk info version %d or pkeytype %d mismatch.\n",
+			  __func__, (int) wki->version, (int) wki->pkeytype);
+		rc = -EIO;
+		goto out;
+	}
+
+	/* copy the tanslated protected key */
+	switch (wki->pkeysize) {
+	case 16+32:
+		/* AES 128 protected key */
+		if (protkeytype)
+			*protkeytype = PKEY_KEYTYPE_AES_128;
+		break;
+	case 24+32:
+		/* AES 192 protected key */
+		if (protkeytype)
+			*protkeytype = PKEY_KEYTYPE_AES_192;
+		break;
+	case 32+32:
+		/* AES 256 protected key */
+		if (protkeytype)
+			*protkeytype = PKEY_KEYTYPE_AES_256;
+		break;
+	default:
+		DEBUG_ERR("%s unknown/unsupported pkeysize %d\n",
+			  __func__, (int) wki->pkeysize);
+		rc = -EIO;
+		goto out;
+	}
+	memcpy(protkey, wki->pkey, wki->pkeysize);
+	if (protkeylen)
+		*protkeylen = (u32) wki->pkeysize;
+	rc = 0;
+
+out:
+	kfree(wkbuf);
+	return rc;
+}
+EXPORT_SYMBOL(ep11_key2protkey);
+
+int ep11_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain,
+		   int minhwtype, int minapi, const u8 *wkvp)
+{
+	struct zcrypt_device_status_ext *device_status;
+	u32 *_apqns = NULL, _nr_apqns = 0;
+	int i, card, dom, rc = -ENOMEM;
+	struct ep11_domain_info edi;
+	struct ep11_card_info eci;
+
+	/* fetch status of all crypto cards */
+	device_status = kmalloc_array(MAX_ZDEV_ENTRIES_EXT,
+				      sizeof(struct zcrypt_device_status_ext),
+				      GFP_KERNEL);
+	if (!device_status)
+		return -ENOMEM;
+	zcrypt_device_status_mask_ext(device_status);
+
+	/* allocate 1k space for up to 256 apqns */
+	_apqns = kmalloc_array(256, sizeof(u32), GFP_KERNEL);
+	if (!_apqns) {
+		kfree(device_status);
+		return -ENOMEM;
+	}
+
+	/* walk through all the crypto apqnss */
+	for (i = 0; i < MAX_ZDEV_ENTRIES_EXT; i++) {
+		card = AP_QID_CARD(device_status[i].qid);
+		dom = AP_QID_QUEUE(device_status[i].qid);
+		/* check online state */
+		if (!device_status[i].online)
+			continue;
+		/* check for ep11 functions */
+		if (!(device_status[i].functions & 0x01))
+			continue;
+		/* check cardnr */
+		if (cardnr != 0xFFFF && card != cardnr)
+			continue;
+		/* check domain */
+		if (domain != 0xFFFF && dom != domain)
+			continue;
+		/* check min hardware type */
+		if (minhwtype && device_status[i].hwtype < minhwtype)
+			continue;
+		/* check min api version if given */
+		if (minapi > 0) {
+			if (ep11_get_card_info(card, &eci, 0))
+				continue;
+			if (minapi > eci.API_ord_nr)
+				continue;
+		}
+		/* check wkvp if given */
+		if (wkvp) {
+			if (ep11_get_domain_info(card, dom, &edi))
+				continue;
+			if (edi.cur_wk_state != '1')
+				continue;
+			if (memcmp(wkvp, edi.cur_wkvp, 16))
+				continue;
+		}
+		/* apqn passed all filtering criterons, add to the array */
+		if (_nr_apqns < 256)
+			_apqns[_nr_apqns++] = (((u16)card) << 16) | ((u16) dom);
+	}
+
+	/* nothing found ? */
+	if (!_nr_apqns) {
+		kfree(_apqns);
+		rc = -ENODEV;
+	} else {
+		/* no re-allocation, simple return the _apqns array */
+		*apqns = _apqns;
+		*nr_apqns = _nr_apqns;
+		rc = 0;
+	}
+
+	kfree(device_status);
+	return rc;
+}
+EXPORT_SYMBOL(ep11_findcard2);
+
+void __exit zcrypt_ep11misc_exit(void)
+{
+	card_cache_free();
+}
diff --git a/drivers/s390/crypto/zcrypt_ep11misc.h b/drivers/s390/crypto/zcrypt_ep11misc.h
new file mode 100644
index 000000000000..e3ed5ed1de86
--- /dev/null
+++ b/drivers/s390/crypto/zcrypt_ep11misc.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  Copyright IBM Corp. 2019
+ *  Author(s): Harald Freudenberger <freude@linux.ibm.com>
+ *
+ *  Collection of EP11 misc functions used by zcrypt and pkey
+ */
+
+#ifndef _ZCRYPT_EP11MISC_H_
+#define _ZCRYPT_EP11MISC_H_
+
+#include <asm/zcrypt.h>
+#include <asm/pkey.h>
+
+#define TOKVER_EP11_AES  0x03  /* EP11 AES key blob */
+
+#define EP11_API_V 4  /* highest known and supported EP11 API version */
+
+#define EP11_STRUCT_MAGIC 0x1234
+#define EP11_BLOB_PKEY_EXTRACTABLE 0x200000
+
+/* inside view of an EP11 secure key blob */
+struct ep11keyblob {
+	union {
+		u8 session[32];
+		struct {
+			u8  type;      /* 0x00 (TOKTYPE_NON_CCA) */
+			u8  res0;      /* unused */
+			u16 len;       /* total length in bytes of this blob */
+			u8  version;   /* 0x06 (TOKVER_EP11_AES) */
+			u8  res1;      /* unused */
+			u16 keybitlen; /* clear key bit len, 0 for unknown */
+		} head;
+	};
+	u8  wkvp[16];  /* wrapping key verification pattern */
+	u64 attr;      /* boolean key attributes */
+	u64 mode;      /* mode bits */
+	u16 version;   /* 0x1234, EP11_STRUCT_MAGIC */
+	u8  iv[14];
+	u8  encrypted_key_data[144];
+	u8  mac[32];
+} __packed;
+
+/*
+ * Simple check if the key blob is a valid EP11 secure AES key.
+ * If keybitsize is given, the bitsize of the key is also checked.
+ * If checkcpacfexport is enabled, the key is also checked for the
+ * attributes needed to export this key for CPACF use.
+ * Returns 0 on success or errno value on failure.
+ */
+int ep11_check_aeskeyblob(debug_info_t *dbg, int dbflvl,
+			  const u8 *key, int keybitsize,
+			  int checkcpacfexport);
+
+/* EP11 card info struct */
+struct ep11_card_info {
+	u32  API_ord_nr;    /* API ordinal number */
+	u16  FW_version;    /* Firmware major and minor version */
+	char serial[16];    /* serial number string (16 ascii, no 0x00 !) */
+	u64  op_mode;	    /* card operational mode(s) */
+};
+
+/* EP11 domain info struct */
+struct ep11_domain_info {
+	char cur_wk_state;  /* '0' invalid, '1' valid */
+	char new_wk_state;  /* '0' empty, '1' uncommitted, '2' committed */
+	u8   cur_wkvp[32];  /* current wrapping key verification pattern */
+	u8   new_wkvp[32];  /* new wrapping key verification pattern */
+	u64  op_mode;	    /* domain operational mode(s) */
+};
+
+/*
+ * Provide information about an EP11 card.
+ */
+int ep11_get_card_info(u16 card, struct ep11_card_info *info, int verify);
+
+/*
+ * Provide information about a domain within an EP11 card.
+ */
+int ep11_get_domain_info(u16 card, u16 domain, struct ep11_domain_info *info);
+
+/*
+ * Generate (random) EP11 AES secure key.
+ */
+int ep11_genaeskey(u16 card, u16 domain, u32 keybitsize, u32 keygenflags,
+		   u8 *keybuf, size_t *keybufsize);
+
+/*
+ * Generate EP11 AES secure key with given clear key value.
+ */
+int ep11_clr2keyblob(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags,
+		     const u8 *clrkey, u8 *keybuf, size_t *keybufsize);
+
+/*
+ * Derive proteced key from EP11 AES secure key blob.
+ */
+int ep11_key2protkey(u16 cardnr, u16 domain, const u8 *key, size_t keylen,
+		     u8 *protkey, u32 *protkeylen, u32 *protkeytype);
+
+/*
+ * Build a list of ep11 apqns meeting the following constrains:
+ * - apqn is online and is in fact an EP11 apqn
+ * - if cardnr is not FFFF only apqns with this cardnr
+ * - if domain is not FFFF only apqns with this domainnr
+ * - if minhwtype > 0 only apqns with hwtype >= minhwtype
+ * - if minapi > 0 only apqns with API_ord_nr >= minapi
+ * - if wkvp != NULL only apqns where the wkvp (EP11_WKVPLEN bytes) matches
+ *   to the first EP11_WKVPLEN bytes of the wkvp of the current wrapping
+ *   key for this domain. When a wkvp is given there will aways be a re-fetch
+ *   of the domain info for the potential apqn - so this triggers an request
+ *   reply to each apqn eligible.
+ * The array of apqn entries is allocated with kmalloc and returned in *apqns;
+ * the number of apqns stored into the list is returned in *nr_apqns. One apqn
+ * entry is simple a 32 bit value with 16 bit cardnr and 16 bit domain nr and
+ * may be casted to struct pkey_apqn. The return value is either 0 for success
+ * or a negative errno value. If no apqn meeting the criterias is found,
+ * -ENODEV is returned.
+ */
+int ep11_findcard2(u32 **apqns, u32 *nr_apqns, u16 cardnr, u16 domain,
+		   int minhwtype, int minapi, const u8 *wkvp);
+
+void zcrypt_ep11misc_exit(void);
+
+#endif /* _ZCRYPT_EP11MISC_H_ */
diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c
index c25e8a54e869..3170b295a5da 100644
--- a/drivers/scsi/BusLogic.c
+++ b/drivers/scsi/BusLogic.c
@@ -134,7 +134,7 @@ static char *blogic_cmd_failure_reason;
 static void blogic_announce_drvr(struct blogic_adapter *adapter)
 {
 	blogic_announce("***** BusLogic SCSI Driver Version " blogic_drvr_version " of " blogic_drvr_date " *****\n", adapter);
-	blogic_announce("Copyright 1995-1998 by Leonard N. Zubkoff " "<lnz@dandelion.com>\n", adapter);
+	blogic_announce("Copyright 1995-1998 by Leonard N. Zubkoff <lnz@dandelion.com>\n", adapter);
 }
 
 
@@ -440,7 +440,7 @@ static int blogic_cmd(struct blogic_adapter *adapter, enum blogic_opcode opcode,
 			goto done;
 		}
 		if (blogic_global_options.trace_config)
-			blogic_notice("blogic_cmd(%02X) Status = %02X: " "(Modify I/O Address)\n", adapter, opcode, statusreg.all);
+			blogic_notice("blogic_cmd(%02X) Status = %02X: (Modify I/O Address)\n", adapter, opcode, statusreg.all);
 		result = 0;
 		goto done;
 	}
@@ -716,23 +716,23 @@ static int __init blogic_init_mm_probeinfo(struct blogic_adapter *adapter)
 		pci_addr = base_addr1 = pci_resource_start(pci_device, 1);
 
 		if (pci_resource_flags(pci_device, 0) & IORESOURCE_MEM) {
-			blogic_err("BusLogic: Base Address0 0x%X not I/O for " "MultiMaster Host Adapter\n", NULL, base_addr0);
-			blogic_err("at PCI Bus %d Device %d I/O Address 0x%X\n", NULL, bus, device, io_addr);
+			blogic_err("BusLogic: Base Address0 0x%lX not I/O for MultiMaster Host Adapter\n", NULL, base_addr0);
+			blogic_err("at PCI Bus %d Device %d I/O Address 0x%lX\n", NULL, bus, device, io_addr);
 			continue;
 		}
 		if (pci_resource_flags(pci_device, 1) & IORESOURCE_IO) {
-			blogic_err("BusLogic: Base Address1 0x%X not Memory for " "MultiMaster Host Adapter\n", NULL, base_addr1);
-			blogic_err("at PCI Bus %d Device %d PCI Address 0x%X\n", NULL, bus, device, pci_addr);
+			blogic_err("BusLogic: Base Address1 0x%lX not Memory for MultiMaster Host Adapter\n", NULL, base_addr1);
+			blogic_err("at PCI Bus %d Device %d PCI Address 0x%lX\n", NULL, bus, device, pci_addr);
 			continue;
 		}
 		if (irq_ch == 0) {
-			blogic_err("BusLogic: IRQ Channel %d invalid for " "MultiMaster Host Adapter\n", NULL, irq_ch);
-			blogic_err("at PCI Bus %d Device %d I/O Address 0x%X\n", NULL, bus, device, io_addr);
+			blogic_err("BusLogic: IRQ Channel %d invalid for MultiMaster Host Adapter\n", NULL, irq_ch);
+			blogic_err("at PCI Bus %d Device %d I/O Address 0x%lX\n", NULL, bus, device, io_addr);
 			continue;
 		}
 		if (blogic_global_options.trace_probe) {
-			blogic_notice("BusLogic: PCI MultiMaster Host Adapter " "detected at\n", NULL);
-			blogic_notice("BusLogic: PCI Bus %d Device %d I/O Address " "0x%X PCI Address 0x%X\n", NULL, bus, device, io_addr, pci_addr);
+			blogic_notice("BusLogic: PCI MultiMaster Host Adapter detected at\n", NULL);
+			blogic_notice("BusLogic: PCI Bus %d Device %d I/O Address 0x%lX PCI Address 0x%lX\n", NULL, bus, device, io_addr, pci_addr);
 		}
 		/*
 		   Issue the Inquire PCI Host Adapter Information command to determine
@@ -818,7 +818,7 @@ static int __init blogic_init_mm_probeinfo(struct blogic_adapter *adapter)
 			nonpr_mmcount++;
 			mmcount++;
 		} else
-			blogic_warn("BusLogic: Too many Host Adapters " "detected\n", NULL);
+			blogic_warn("BusLogic: Too many Host Adapters detected\n", NULL);
 	}
 	/*
 	   If the AutoSCSI "Use Bus And Device # For PCI Scanning Seq."
@@ -956,23 +956,23 @@ static int __init blogic_init_fp_probeinfo(struct blogic_adapter *adapter)
 		pci_addr = base_addr1 = pci_resource_start(pci_device, 1);
 #ifdef CONFIG_SCSI_FLASHPOINT
 		if (pci_resource_flags(pci_device, 0) & IORESOURCE_MEM) {
-			blogic_err("BusLogic: Base Address0 0x%X not I/O for " "FlashPoint Host Adapter\n", NULL, base_addr0);
-			blogic_err("at PCI Bus %d Device %d I/O Address 0x%X\n", NULL, bus, device, io_addr);
+			blogic_err("BusLogic: Base Address0 0x%lX not I/O for FlashPoint Host Adapter\n", NULL, base_addr0);
+			blogic_err("at PCI Bus %d Device %d I/O Address 0x%lX\n", NULL, bus, device, io_addr);
 			continue;
 		}
 		if (pci_resource_flags(pci_device, 1) & IORESOURCE_IO) {
-			blogic_err("BusLogic: Base Address1 0x%X not Memory for " "FlashPoint Host Adapter\n", NULL, base_addr1);
-			blogic_err("at PCI Bus %d Device %d PCI Address 0x%X\n", NULL, bus, device, pci_addr);
+			blogic_err("BusLogic: Base Address1 0x%lX not Memory for FlashPoint Host Adapter\n", NULL, base_addr1);
+			blogic_err("at PCI Bus %d Device %d PCI Address 0x%lX\n", NULL, bus, device, pci_addr);
 			continue;
 		}
 		if (irq_ch == 0) {
-			blogic_err("BusLogic: IRQ Channel %d invalid for " "FlashPoint Host Adapter\n", NULL, irq_ch);
-			blogic_err("at PCI Bus %d Device %d I/O Address 0x%X\n", NULL, bus, device, io_addr);
+			blogic_err("BusLogic: IRQ Channel %d invalid for FlashPoint Host Adapter\n", NULL, irq_ch);
+			blogic_err("at PCI Bus %d Device %d I/O Address 0x%lX\n", NULL, bus, device, io_addr);
 			continue;
 		}
 		if (blogic_global_options.trace_probe) {
-			blogic_notice("BusLogic: FlashPoint Host Adapter " "detected at\n", NULL);
-			blogic_notice("BusLogic: PCI Bus %d Device %d I/O Address " "0x%X PCI Address 0x%X\n", NULL, bus, device, io_addr, pci_addr);
+			blogic_notice("BusLogic: FlashPoint Host Adapter detected at\n", NULL);
+			blogic_notice("BusLogic: PCI Bus %d Device %d I/O Address 0x%lX PCI Address 0x%lX\n", NULL, bus, device, io_addr, pci_addr);
 		}
 		if (blogic_probeinfo_count < BLOGIC_MAX_ADAPTERS) {
 			struct blogic_probeinfo *probeinfo =
@@ -987,11 +987,11 @@ static int __init blogic_init_fp_probeinfo(struct blogic_adapter *adapter)
 			probeinfo->pci_device = pci_dev_get(pci_device);
 			fpcount++;
 		} else
-			blogic_warn("BusLogic: Too many Host Adapters " "detected\n", NULL);
+			blogic_warn("BusLogic: Too many Host Adapters detected\n", NULL);
 #else
-		blogic_err("BusLogic: FlashPoint Host Adapter detected at " "PCI Bus %d Device %d\n", NULL, bus, device);
-		blogic_err("BusLogic: I/O Address 0x%X PCI Address 0x%X, irq %d, " "but FlashPoint\n", NULL, io_addr, pci_addr, irq_ch);
-		blogic_err("BusLogic: support was omitted in this kernel " "configuration.\n", NULL);
+		blogic_err("BusLogic: FlashPoint Host Adapter detected at PCI Bus %d Device %d\n", NULL, bus, device);
+		blogic_err("BusLogic: I/O Address 0x%lX PCI Address 0x%lX, irq %d, but FlashPoint\n", NULL, io_addr, pci_addr, irq_ch);
+		blogic_err("BusLogic: support was omitted in this kernel configuration.\n", NULL);
 #endif
 	}
 	/*
@@ -1099,9 +1099,9 @@ static bool blogic_failure(struct blogic_adapter *adapter, char *msg)
 	if (adapter->adapter_bus_type == BLOGIC_PCI_BUS) {
 		blogic_err("While configuring BusLogic PCI Host Adapter at\n",
 				adapter);
-		blogic_err("Bus %d Device %d I/O Address 0x%X PCI Address 0x%X:\n", adapter, adapter->bus, adapter->dev, adapter->io_addr, adapter->pci_addr);
+		blogic_err("Bus %d Device %d I/O Address 0x%lX PCI Address 0x%lX:\n", adapter, adapter->bus, adapter->dev, adapter->io_addr, adapter->pci_addr);
 	} else
-		blogic_err("While configuring BusLogic Host Adapter at " "I/O Address 0x%X:\n", adapter, adapter->io_addr);
+		blogic_err("While configuring BusLogic Host Adapter at I/O Address 0x%lX:\n", adapter, adapter->io_addr);
 	blogic_err("%s FAILED - DETACHING\n", adapter, msg);
 	if (blogic_cmd_failure_reason != NULL)
 		blogic_err("ADDITIONAL FAILURE INFO - %s\n", adapter,
@@ -1129,13 +1129,13 @@ static bool __init blogic_probe(struct blogic_adapter *adapter)
 		fpinfo->present = false;
 		if (!(FlashPoint_ProbeHostAdapter(fpinfo) == 0 &&
 					fpinfo->present)) {
-			blogic_err("BusLogic: FlashPoint Host Adapter detected at " "PCI Bus %d Device %d\n", adapter, adapter->bus, adapter->dev);
-			blogic_err("BusLogic: I/O Address 0x%X PCI Address 0x%X, " "but FlashPoint\n", adapter, adapter->io_addr, adapter->pci_addr);
+			blogic_err("BusLogic: FlashPoint Host Adapter detected at PCI Bus %d Device %d\n", adapter, adapter->bus, adapter->dev);
+			blogic_err("BusLogic: I/O Address 0x%lX PCI Address 0x%lX, but FlashPoint\n", adapter, adapter->io_addr, adapter->pci_addr);
 			blogic_err("BusLogic: Probe Function failed to validate it.\n", adapter);
 			return false;
 		}
 		if (blogic_global_options.trace_probe)
-			blogic_notice("BusLogic_Probe(0x%X): FlashPoint Found\n", adapter, adapter->io_addr);
+			blogic_notice("BusLogic_Probe(0x%lX): FlashPoint Found\n", adapter, adapter->io_addr);
 		/*
 		   Indicate the Host Adapter Probe completed successfully.
 		 */
@@ -1152,7 +1152,7 @@ static bool __init blogic_probe(struct blogic_adapter *adapter)
 	intreg.all = blogic_rdint(adapter);
 	georeg.all = blogic_rdgeom(adapter);
 	if (blogic_global_options.trace_probe)
-		blogic_notice("BusLogic_Probe(0x%X): Status 0x%02X, Interrupt 0x%02X, " "Geometry 0x%02X\n", adapter, adapter->io_addr, statusreg.all, intreg.all, georeg.all);
+		blogic_notice("BusLogic_Probe(0x%lX): Status 0x%02X, Interrupt 0x%02X, Geometry 0x%02X\n", adapter, adapter->io_addr, statusreg.all, intreg.all, georeg.all);
 	if (statusreg.all == 0 || statusreg.sr.diag_active ||
 			statusreg.sr.cmd_param_busy || statusreg.sr.rsvd ||
 			statusreg.sr.cmd_invalid || intreg.ir.rsvd != 0)
@@ -1231,7 +1231,7 @@ static bool blogic_hwreset(struct blogic_adapter *adapter, bool hard_reset)
 		udelay(100);
 	}
 	if (blogic_global_options.trace_hw_reset)
-		blogic_notice("BusLogic_HardwareReset(0x%X): Diagnostic Active, " "Status 0x%02X\n", adapter, adapter->io_addr, statusreg.all);
+		blogic_notice("BusLogic_HardwareReset(0x%lX): Diagnostic Active, Status 0x%02X\n", adapter, adapter->io_addr, statusreg.all);
 	if (timeout < 0)
 		return false;
 	/*
@@ -1251,7 +1251,7 @@ static bool blogic_hwreset(struct blogic_adapter *adapter, bool hard_reset)
 		udelay(100);
 	}
 	if (blogic_global_options.trace_hw_reset)
-		blogic_notice("BusLogic_HardwareReset(0x%X): Diagnostic Completed, " "Status 0x%02X\n", adapter, adapter->io_addr, statusreg.all);
+		blogic_notice("BusLogic_HardwareReset(0x%lX): Diagnostic Completed, Status 0x%02X\n", adapter, adapter->io_addr, statusreg.all);
 	if (timeout < 0)
 		return false;
 	/*
@@ -1267,7 +1267,7 @@ static bool blogic_hwreset(struct blogic_adapter *adapter, bool hard_reset)
 		udelay(100);
 	}
 	if (blogic_global_options.trace_hw_reset)
-		blogic_notice("BusLogic_HardwareReset(0x%X): Host Adapter Ready, " "Status 0x%02X\n", adapter, adapter->io_addr, statusreg.all);
+		blogic_notice("BusLogic_HardwareReset(0x%lX): Host Adapter Ready, Status 0x%02X\n", adapter, adapter->io_addr, statusreg.all);
 	if (timeout < 0)
 		return false;
 	/*
@@ -1323,7 +1323,7 @@ static bool __init blogic_checkadapter(struct blogic_adapter *adapter)
 	   Provide tracing information if requested and return.
 	 */
 	if (blogic_global_options.trace_probe)
-		blogic_notice("BusLogic_Check(0x%X): MultiMaster %s\n", adapter,
+		blogic_notice("BusLogic_Check(0x%lX): MultiMaster %s\n", adapter,
 				adapter->io_addr,
 				(result ? "Found" : "Not Found"));
 	return result;
@@ -1836,7 +1836,7 @@ static bool __init blogic_reportconfig(struct blogic_adapter *adapter)
 	int tgt_id;
 
 	blogic_info("Configuring BusLogic Model %s %s%s%s%s SCSI Host Adapter\n", adapter, adapter->model, blogic_adapter_busnames[adapter->adapter_bus_type], (adapter->wide ? " Wide" : ""), (adapter->differential ? " Differential" : ""), (adapter->ultra ? " Ultra" : ""));
-	blogic_info("  Firmware Version: %s, I/O Address: 0x%X, " "IRQ Channel: %d/%s\n", adapter, adapter->fw_ver, adapter->io_addr, adapter->irq_ch, (adapter->level_int ? "Level" : "Edge"));
+	blogic_info("  Firmware Version: %s, I/O Address: 0x%lX, IRQ Channel: %d/%s\n", adapter, adapter->fw_ver, adapter->io_addr, adapter->irq_ch, (adapter->level_int ? "Level" : "Edge"));
 	if (adapter->adapter_bus_type != BLOGIC_PCI_BUS) {
 		blogic_info("  DMA Channel: ", adapter);
 		if (adapter->dma_ch > 0)
@@ -1844,7 +1844,7 @@ static bool __init blogic_reportconfig(struct blogic_adapter *adapter)
 		else
 			blogic_info("None, ", adapter);
 		if (adapter->bios_addr > 0)
-			blogic_info("BIOS Address: 0x%X, ", adapter,
+			blogic_info("BIOS Address: 0x%lX, ", adapter,
 					adapter->bios_addr);
 		else
 			blogic_info("BIOS Address: None, ", adapter);
@@ -1852,7 +1852,7 @@ static bool __init blogic_reportconfig(struct blogic_adapter *adapter)
 		blogic_info("  PCI Bus: %d, Device: %d, Address: ", adapter,
 				adapter->bus, adapter->dev);
 		if (adapter->pci_addr > 0)
-			blogic_info("0x%X, ", adapter, adapter->pci_addr);
+			blogic_info("0x%lX, ", adapter, adapter->pci_addr);
 		else
 			blogic_info("Unassigned, ", adapter);
 	}
@@ -1932,10 +1932,10 @@ static bool __init blogic_reportconfig(struct blogic_adapter *adapter)
 	blogic_info("  Disconnect/Reconnect: %s, Tagged Queuing: %s\n", adapter,
 			discon_msg, tagq_msg);
 	if (blogic_multimaster_type(adapter)) {
-		blogic_info("  Scatter/Gather Limit: %d of %d segments, " "Mailboxes: %d\n", adapter, adapter->drvr_sglimit, adapter->adapter_sglimit, adapter->mbox_count);
-		blogic_info("  Driver Queue Depth: %d, " "Host Adapter Queue Depth: %d\n", adapter, adapter->drvr_qdepth, adapter->adapter_qdepth);
+		blogic_info("  Scatter/Gather Limit: %d of %d segments, Mailboxes: %d\n", adapter, adapter->drvr_sglimit, adapter->adapter_sglimit, adapter->mbox_count);
+		blogic_info("  Driver Queue Depth: %d, Host Adapter Queue Depth: %d\n", adapter, adapter->drvr_qdepth, adapter->adapter_qdepth);
 	} else
-		blogic_info("  Driver Queue Depth: %d, " "Scatter/Gather Limit: %d segments\n", adapter, adapter->drvr_qdepth, adapter->drvr_sglimit);
+		blogic_info("  Driver Queue Depth: %d, Scatter/Gather Limit: %d segments\n", adapter, adapter->drvr_qdepth, adapter->drvr_sglimit);
 	blogic_info("  Tagged Queue Depth: ", adapter);
 	common_tagq_depth = true;
 	for (tgt_id = 1; tgt_id < adapter->maxdev; tgt_id++)
@@ -2717,7 +2717,7 @@ static void blogic_scan_inbox(struct blogic_adapter *adapter)
 				   then there is most likely a bug in
 				   the Host Adapter firmware.
 				 */
-				blogic_warn("Illegal CCB #%ld status %d in " "Incoming Mailbox\n", adapter, ccb->serial, ccb->status);
+				blogic_warn("Illegal CCB #%ld status %d in Incoming Mailbox\n", adapter, ccb->serial, ccb->status);
 			}
 		}
 		next_inbox->comp_code = BLOGIC_INBOX_FREE;
@@ -2752,7 +2752,7 @@ static void blogic_process_ccbs(struct blogic_adapter *adapter)
 		if (ccb->opcode == BLOGIC_BDR) {
 			int tgt_id = ccb->tgt_id;
 
-			blogic_warn("Bus Device Reset CCB #%ld to Target " "%d Completed\n", adapter, ccb->serial, tgt_id);
+			blogic_warn("Bus Device Reset CCB #%ld to Target %d Completed\n", adapter, ccb->serial, tgt_id);
 			blogic_inc_count(&adapter->tgt_stats[tgt_id].bdr_done);
 			adapter->tgt_flags[tgt_id].tagq_active = false;
 			adapter->cmds_since_rst[tgt_id] = 0;
@@ -2829,7 +2829,7 @@ static void blogic_process_ccbs(struct blogic_adapter *adapter)
 					if (blogic_global_options.trace_err) {
 						int i;
 						blogic_notice("CCB #%ld Target %d: Result %X Host "
-								"Adapter Status %02X " "Target Status %02X\n", adapter, ccb->serial, ccb->tgt_id, command->result, ccb->adapter_status, ccb->tgt_status);
+								"Adapter Status %02X Target Status %02X\n", adapter, ccb->serial, ccb->tgt_id, command->result, ccb->adapter_status, ccb->tgt_status);
 						blogic_notice("CDB   ", adapter);
 						for (i = 0; i < ccb->cdblen; i++)
 							blogic_notice(" %02X", adapter, ccb->cdb[i]);
@@ -3203,12 +3203,12 @@ static int blogic_qcmd_lck(struct scsi_cmnd *command,
 		 */
 		if (!blogic_write_outbox(adapter, BLOGIC_MBOX_START, ccb)) {
 			spin_unlock_irq(adapter->scsi_host->host_lock);
-			blogic_warn("Unable to write Outgoing Mailbox - " "Pausing for 1 second\n", adapter);
+			blogic_warn("Unable to write Outgoing Mailbox - Pausing for 1 second\n", adapter);
 			blogic_delay(1);
 			spin_lock_irq(adapter->scsi_host->host_lock);
 			if (!blogic_write_outbox(adapter, BLOGIC_MBOX_START,
 						ccb)) {
-				blogic_warn("Still unable to write Outgoing Mailbox - " "Host Adapter Dead?\n", adapter);
+				blogic_warn("Still unable to write Outgoing Mailbox - Host Adapter Dead?\n", adapter);
 				blogic_dealloc_ccb(ccb, 1);
 				command->result = DID_ERROR << 16;
 				command->scsi_done(command);
@@ -3443,8 +3443,8 @@ static int blogic_diskparam(struct scsi_device *sdev, struct block_device *dev,
 			if (diskparam->cylinders != saved_cyl)
 				blogic_warn("Adopting Geometry %d/%d from Partition Table\n", adapter, diskparam->heads, diskparam->sectors);
 		} else if (part_end_head > 0 || part_end_sector > 0) {
-			blogic_warn("Warning: Partition Table appears to " "have Geometry %d/%d which is\n", adapter, part_end_head + 1, part_end_sector);
-			blogic_warn("not compatible with current BusLogic " "Host Adapter Geometry %d/%d\n", adapter, diskparam->heads, diskparam->sectors);
+			blogic_warn("Warning: Partition Table appears to have Geometry %d/%d which is\n", adapter, part_end_head + 1, part_end_sector);
+			blogic_warn("not compatible with current BusLogic Host Adapter Geometry %d/%d\n", adapter, diskparam->heads, diskparam->sectors);
 		}
 	}
 	kfree(buf);
@@ -3689,7 +3689,7 @@ static int __init blogic_parseopts(char *options)
 					blogic_probe_options.probe134 = true;
 					break;
 				default:
-					blogic_err("BusLogic: Invalid Driver Options " "(invalid I/O Address 0x%X)\n", NULL, io_addr);
+					blogic_err("BusLogic: Invalid Driver Options (invalid I/O Address 0x%lX)\n", NULL, io_addr);
 					return 0;
 				}
 			} else if (blogic_parse(&options, "NoProbeISA"))
@@ -3710,7 +3710,7 @@ static int __init blogic_parseopts(char *options)
 				for (tgt_id = 0; tgt_id < BLOGIC_MAXDEV; tgt_id++) {
 					unsigned short qdepth = simple_strtoul(options, &options, 0);
 					if (qdepth > BLOGIC_MAX_TAG_DEPTH) {
-						blogic_err("BusLogic: Invalid Driver Options " "(invalid Queue Depth %d)\n", NULL, qdepth);
+						blogic_err("BusLogic: Invalid Driver Options (invalid Queue Depth %d)\n", NULL, qdepth);
 						return 0;
 					}
 					drvr_opts->qdepth[tgt_id] = qdepth;
@@ -3719,12 +3719,12 @@ static int __init blogic_parseopts(char *options)
 					else if (*options == ']')
 						break;
 					else {
-						blogic_err("BusLogic: Invalid Driver Options " "(',' or ']' expected at '%s')\n", NULL, options);
+						blogic_err("BusLogic: Invalid Driver Options (',' or ']' expected at '%s')\n", NULL, options);
 						return 0;
 					}
 				}
 				if (*options != ']') {
-					blogic_err("BusLogic: Invalid Driver Options " "(']' expected at '%s')\n", NULL, options);
+					blogic_err("BusLogic: Invalid Driver Options (']' expected at '%s')\n", NULL, options);
 					return 0;
 				} else
 					options++;
@@ -3732,7 +3732,7 @@ static int __init blogic_parseopts(char *options)
 				unsigned short qdepth = simple_strtoul(options, &options, 0);
 				if (qdepth == 0 ||
 						qdepth > BLOGIC_MAX_TAG_DEPTH) {
-					blogic_err("BusLogic: Invalid Driver Options " "(invalid Queue Depth %d)\n", NULL, qdepth);
+					blogic_err("BusLogic: Invalid Driver Options (invalid Queue Depth %d)\n", NULL, qdepth);
 					return 0;
 				}
 				drvr_opts->common_qdepth = qdepth;
@@ -3778,7 +3778,7 @@ static int __init blogic_parseopts(char *options)
 				unsigned short bus_settle_time =
 					simple_strtoul(options, &options, 0);
 				if (bus_settle_time > 5 * 60) {
-					blogic_err("BusLogic: Invalid Driver Options " "(invalid Bus Settle Time %d)\n", NULL, bus_settle_time);
+					blogic_err("BusLogic: Invalid Driver Options (invalid Bus Settle Time %d)\n", NULL, bus_settle_time);
 					return 0;
 				}
 				drvr_opts->bus_settle_time = bus_settle_time;
@@ -3803,14 +3803,14 @@ static int __init blogic_parseopts(char *options)
 			if (*options == ',')
 				options++;
 			else if (*options != ';' && *options != '\0') {
-				blogic_err("BusLogic: Unexpected Driver Option '%s' " "ignored\n", NULL, options);
+				blogic_err("BusLogic: Unexpected Driver Option '%s' ignored\n", NULL, options);
 				*options = '\0';
 			}
 		}
 		if (!(blogic_drvr_options_count == 0 ||
 			blogic_probeinfo_count == 0 ||
 			blogic_drvr_options_count == blogic_probeinfo_count)) {
-			blogic_err("BusLogic: Invalid Driver Options " "(all or no I/O Addresses must be specified)\n", NULL);
+			blogic_err("BusLogic: Invalid Driver Options (all or no I/O Addresses must be specified)\n", NULL);
 			return 0;
 		}
 		/*
@@ -3864,7 +3864,7 @@ static int __init blogic_setup(char *str)
 	(void) get_options(str, ARRAY_SIZE(ints), ints);
 
 	if (ints[0] != 0) {
-		blogic_err("BusLogic: Obsolete Command Line Entry " "Format Ignored\n", NULL);
+		blogic_err("BusLogic: Obsolete Command Line Entry Format Ignored\n", NULL);
 		return 0;
 	}
 	if (str == NULL || *str == '\0')
diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c
index a9d40d3b90ef..4190a025381a 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_core.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_core.c
@@ -2314,7 +2314,7 @@ ahc_find_syncrate(struct ahc_softc *ahc, u_int *period,
 			 * At some speeds, we only support
 			 * ST transfers.
 			 */
-		 	if ((syncrate->sxfr_u2 & ST_SXFR) != 0)
+			if ((syncrate->sxfr_u2 & ST_SXFR) != 0)
 				*ppr_options &= ~MSG_EXT_PPR_DT_REQ;
 			break;
 		}
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index f5781e31f57c..d022407e5645 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -54,6 +54,9 @@ static struct scsi_host_template aic94xx_sht = {
 	.eh_target_reset_handler	= sas_eh_target_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= sas_ioctl,
+#endif
 	.track_queue_depth	= 1,
 };
 
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 76751d6c7f0d..ed5f4a6ae270 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -872,6 +872,10 @@ static long ch_ioctl_compat(struct file * file,
 			    unsigned int cmd, unsigned long arg)
 {
 	scsi_changer *ch = file->private_data;
+	int retval = scsi_ioctl_block_when_processing_errors(ch->device, cmd,
+							file->f_flags & O_NDELAY);
+	if (retval)
+		return retval;
 
 	switch (cmd) {
 	case CHIOGPARAMS:
@@ -883,7 +887,7 @@ static long ch_ioctl_compat(struct file * file,
 	case CHIOINITELEM:
 	case CHIOSVOLTAG:
 		/* compatible */
-		return ch_ioctl(file, cmd, arg);
+		return ch_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
 	case CHIOGSTATUS32:
 	{
 		struct changer_element_status32 ces32;
@@ -898,8 +902,7 @@ static long ch_ioctl_compat(struct file * file,
 		return ch_gstatus(ch, ces32.ces_type, data);
 	}
 	default:
-		// return scsi_ioctl_compat(ch->device, cmd, (void*)arg);
-		return -ENOIOCTLCMD;
+		return scsi_compat_ioctl(ch->device, cmd, compat_ptr(arg));
 
 	}
 }
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 469d0bc9f5fe..00cf33573136 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -1383,7 +1383,7 @@ csio_device_reset(struct device *dev,
 		return -EINVAL;
 
 	/* Delete NPIV lnodes */
-	 csio_lnodes_exit(hw, 1);
+	csio_lnodes_exit(hw, 1);
 
 	/* Block upper IOs */
 	csio_lnodes_block_request(hw);
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 80c5a235d193..7b49e2e9fcde 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -617,6 +617,13 @@ static const struct file_operations esas2r_proc_fops = {
 	.unlocked_ioctl = esas2r_proc_ioctl,
 };
 
+static const struct proc_ops esas2r_proc_ops = {
+	.proc_ioctl		= esas2r_proc_ioctl,
+#ifdef CONFIG_COMPAT
+	.proc_compat_ioctl	= compat_ptr_ioctl,
+#endif
+};
+
 static struct Scsi_Host *esas2r_proc_host;
 static int esas2r_proc_major;
 
@@ -728,7 +735,7 @@ const char *esas2r_info(struct Scsi_Host *sh)
 
 			pde = proc_create(ATTONODE_NAME, 0,
 					  sh->hostt->proc_dir,
-					  &esas2r_proc_fops);
+					  &esas2r_proc_ops);
 
 			if (!pde) {
 				esas2r_log_dev(ESAS2R_LOG_WARN,
diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index bb88995a12c7..89afa31e33cb 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -243,8 +243,6 @@ static void esp_set_all_config3(struct esp *esp, u8 val)
 /* Reset the ESP chip, _not_ the SCSI bus. */
 static void esp_reset_esp(struct esp *esp)
 {
-	u8 family_code, version;
-
 	/* Now reset the ESP chip */
 	scsi_esp_cmd(esp, ESP_CMD_RC);
 	scsi_esp_cmd(esp, ESP_CMD_NULL | ESP_CMD_DMA);
@@ -257,14 +255,19 @@ static void esp_reset_esp(struct esp *esp)
 	 */
 	esp->max_period = ((35 * esp->ccycle) / 1000);
 	if (esp->rev == FAST) {
-		version = esp_read8(ESP_UID);
-		family_code = (version & 0xf8) >> 3;
-		if (family_code == 0x02)
+		u8 family_code = ESP_FAMILY(esp_read8(ESP_UID));
+
+		if (family_code == ESP_UID_F236) {
 			esp->rev = FAS236;
-		else if (family_code == 0x0a)
+		} else if (family_code == ESP_UID_HME) {
 			esp->rev = FASHME; /* Version is usually '5'. */
-		else
+		} else if (family_code == ESP_UID_FSC) {
+			esp->rev = FSC;
+			/* Enable Active Negation */
+			esp_write8(ESP_CONFIG4_RADE, ESP_CFG4);
+		} else {
 			esp->rev = FAS100A;
+		}
 		esp->min_period = ((4 * esp->ccycle) / 1000);
 	} else {
 		esp->min_period = ((5 * esp->ccycle) / 1000);
@@ -308,7 +311,7 @@ static void esp_reset_esp(struct esp *esp)
 
 	case FAS236:
 	case PCSCSI:
-		/* Fast 236, AM53c974 or HME */
+	case FSC:
 		esp_write8(esp->config2, ESP_CFG2);
 		if (esp->rev == FASHME) {
 			u8 cfg3 = esp->target[0].esp_config3;
@@ -2373,10 +2376,11 @@ static const char *esp_chip_names[] = {
 	"ESP100A",
 	"ESP236",
 	"FAS236",
+	"AM53C974",
+	"53CF9x-2",
 	"FAS100A",
 	"FAST",
 	"FASHME",
-	"AM53C974",
 };
 
 static struct scsi_transport_template *esp_transport_template;
diff --git a/drivers/scsi/esp_scsi.h b/drivers/scsi/esp_scsi.h
index 91b32f2a1a1b..446a3d18c022 100644
--- a/drivers/scsi/esp_scsi.h
+++ b/drivers/scsi/esp_scsi.h
@@ -78,12 +78,14 @@
 #define ESP_CONFIG3_IMS       0x80     /* ID msg chk'ng        (esp/fas236)  */
 #define ESP_CONFIG3_OBPUSH    0x80     /* Push odd-byte to dma (hme)         */
 
-/* ESP config register 4 read-write, found only on am53c974 chips */
-#define ESP_CONFIG4_RADE      0x04     /* Active negation */
-#define ESP_CONFIG4_RAE       0x08     /* Active negation on REQ and ACK */
-#define ESP_CONFIG4_PWD       0x20     /* Reduced power feature */
-#define ESP_CONFIG4_GE0       0x40     /* Glitch eater bit 0 */
-#define ESP_CONFIG4_GE1       0x80     /* Glitch eater bit 1 */
+/* ESP config register 4 read-write */
+#define ESP_CONFIG4_BBTE      0x01     /* Back-to-back transfers     (fsc)   */
+#define ESP_CONGIG4_TEST      0x02     /* Transfer counter test mode (fsc)   */
+#define ESP_CONFIG4_RADE      0x04     /* Active negation   (am53c974/fsc)   */
+#define ESP_CONFIG4_RAE       0x08     /* Act. negation REQ/ACK (am53c974)   */
+#define ESP_CONFIG4_PWD       0x20     /* Reduced power feature (am53c974)   */
+#define ESP_CONFIG4_GE0       0x40     /* Glitch eater bit 0    (am53c974)   */
+#define ESP_CONFIG4_GE1       0x80     /* Glitch eater bit 1    (am53c974)   */
 
 #define ESP_CONFIG_GE_12NS    (0)
 #define ESP_CONFIG_GE_25NS    (ESP_CONFIG_GE1)
@@ -209,10 +211,15 @@
 #define ESP_TEST_TS           0x04     /* Tristate test mode */
 
 /* ESP unique ID register read-only, found on fas236+fas100a only */
+#define ESP_UID_FAM           0xf8     /* ESP family bitmask */
+
+#define ESP_FAMILY(uid) (((uid) & ESP_UID_FAM) >> 3)
+
+/* Values for the ESP family bits */
 #define ESP_UID_F100A         0x00     /* ESP FAS100A  */
 #define ESP_UID_F236          0x02     /* ESP FAS236   */
-#define ESP_UID_REV           0x07     /* ESP revision */
-#define ESP_UID_FAM           0xf8     /* ESP family   */
+#define ESP_UID_HME           0x0a     /* FAS HME      */
+#define ESP_UID_FSC           0x14     /* NCR/Symbios Logic 53CF9x-2 */
 
 /* ESP fifo flags register read-only */
 /* Note that the following implies a 16 byte FIFO on the ESP. */
@@ -257,15 +264,17 @@ struct esp_cmd_priv {
 };
 #define ESP_CMD_PRIV(CMD)	((struct esp_cmd_priv *)(&(CMD)->SCp))
 
+/* NOTE: this enum is ordered based on chip features! */
 enum esp_rev {
-	ESP100     = 0x00,  /* NCR53C90 - very broken */
-	ESP100A    = 0x01,  /* NCR53C90A */
-	ESP236     = 0x02,
-	FAS236     = 0x03,
-	FAS100A    = 0x04,
-	FAST       = 0x05,
-	FASHME     = 0x06,
-	PCSCSI     = 0x07,  /* AM53c974 */
+	ESP100,  /* NCR53C90 - very broken */
+	ESP100A, /* NCR53C90A */
+	ESP236,
+	FAS236,
+	PCSCSI,  /* AM53c974 */
+	FSC,     /* NCR/Symbios Logic 53CF9x-2 */
+	FAS100A,
+	FAST,
+	FASHME,
 };
 
 struct esp_cmd_entry {
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 233c73e01246..2bdd64648ef0 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -180,10 +180,10 @@ struct hisi_sas_port {
 
 struct hisi_sas_cq {
 	struct hisi_hba *hisi_hba;
-	const struct cpumask *pci_irq_mask;
-	struct tasklet_struct tasklet;
+	const struct cpumask *irq_mask;
 	int	rd_point;
 	int	id;
+	int	irq_no;
 };
 
 struct hisi_sas_dq {
@@ -627,7 +627,7 @@ extern void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba,
 extern void hisi_sas_init_mem(struct hisi_hba *hisi_hba);
 extern void hisi_sas_rst_work_handler(struct work_struct *work);
 extern void hisi_sas_sync_rst_work_handler(struct work_struct *work);
-extern void hisi_sas_kill_tasklets(struct hisi_hba *hisi_hba);
+extern void hisi_sas_sync_irqs(struct hisi_hba *hisi_hba);
 extern void hisi_sas_phy_oob_ready(struct hisi_hba *hisi_hba, int phy_no);
 extern bool hisi_sas_notify_phy_event(struct hisi_sas_phy *phy,
 				enum hisi_sas_phy_event event);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 03588ec3c394..9a6deb21fe4d 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -163,13 +163,11 @@ static void hisi_sas_slot_index_clear(struct hisi_hba *hisi_hba, int slot_idx)
 
 static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx)
 {
-	unsigned long flags;
-
 	if (hisi_hba->hw->slot_index_alloc ||
 	    slot_idx >= HISI_SAS_UNRESERVED_IPTT) {
-		spin_lock_irqsave(&hisi_hba->lock, flags);
+		spin_lock(&hisi_hba->lock);
 		hisi_sas_slot_index_clear(hisi_hba, slot_idx);
-		spin_unlock_irqrestore(&hisi_hba->lock, flags);
+		spin_unlock(&hisi_hba->lock);
 	}
 }
 
@@ -185,12 +183,11 @@ static int hisi_sas_slot_index_alloc(struct hisi_hba *hisi_hba,
 {
 	int index;
 	void *bitmap = hisi_hba->slot_index_tags;
-	unsigned long flags;
 
 	if (scsi_cmnd)
 		return scsi_cmnd->request->tag;
 
-	spin_lock_irqsave(&hisi_hba->lock, flags);
+	spin_lock(&hisi_hba->lock);
 	index = find_next_zero_bit(bitmap, hisi_hba->slot_index_count,
 				   hisi_hba->last_slot_index + 1);
 	if (index >= hisi_hba->slot_index_count) {
@@ -198,13 +195,13 @@ static int hisi_sas_slot_index_alloc(struct hisi_hba *hisi_hba,
 				hisi_hba->slot_index_count,
 				HISI_SAS_UNRESERVED_IPTT);
 		if (index >= hisi_hba->slot_index_count) {
-			spin_unlock_irqrestore(&hisi_hba->lock, flags);
+			spin_unlock(&hisi_hba->lock);
 			return -SAS_QUEUE_FULL;
 		}
 	}
 	hisi_sas_slot_index_set(hisi_hba, index);
 	hisi_hba->last_slot_index = index;
-	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+	spin_unlock(&hisi_hba->lock);
 
 	return index;
 }
@@ -220,7 +217,6 @@ static void hisi_sas_slot_index_init(struct hisi_hba *hisi_hba)
 void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 			     struct hisi_sas_slot *slot)
 {
-	unsigned long flags;
 	int device_id = slot->device_id;
 	struct hisi_sas_device *sas_dev = &hisi_hba->devices[device_id];
 
@@ -247,9 +243,9 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 		}
 	}
 
-	spin_lock_irqsave(&sas_dev->lock, flags);
+	spin_lock(&sas_dev->lock);
 	list_del_init(&slot->entry);
-	spin_unlock_irqrestore(&sas_dev->lock, flags);
+	spin_unlock(&sas_dev->lock);
 
 	memset(slot, 0, offsetof(struct hisi_sas_slot, buf));
 
@@ -489,14 +485,14 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	slot_idx = rc;
 	slot = &hisi_hba->slot_info[slot_idx];
 
-	spin_lock_irqsave(&dq->lock, flags);
+	spin_lock(&dq->lock);
 	wr_q_index = dq->wr_point;
 	dq->wr_point = (dq->wr_point + 1) % HISI_SAS_QUEUE_SLOTS;
 	list_add_tail(&slot->delivery, &dq->list);
-	spin_unlock_irqrestore(&dq->lock, flags);
-	spin_lock_irqsave(&sas_dev->lock, flags);
+	spin_unlock(&dq->lock);
+	spin_lock(&sas_dev->lock);
 	list_add_tail(&slot->entry, &sas_dev->list);
-	spin_unlock_irqrestore(&sas_dev->lock, flags);
+	spin_unlock(&sas_dev->lock);
 
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
@@ -562,7 +558,6 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 {
 	u32 rc;
 	u32 pass = 0;
-	unsigned long flags;
 	struct hisi_hba *hisi_hba;
 	struct device *dev;
 	struct domain_device *device = task->dev;
@@ -606,9 +601,9 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 		dev_err(dev, "task exec: failed[%d]!\n", rc);
 
 	if (likely(pass)) {
-		spin_lock_irqsave(&dq->lock, flags);
+		spin_lock(&dq->lock);
 		hisi_hba->hw->start_delivery(dq);
-		spin_unlock_irqrestore(&dq->lock, flags);
+		spin_unlock(&dq->lock);
 	}
 
 	return rc;
@@ -659,12 +654,11 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device)
 {
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(device);
 	struct hisi_sas_device *sas_dev = NULL;
-	unsigned long flags;
 	int last = hisi_hba->last_dev_id;
 	int first = (hisi_hba->last_dev_id + 1) % HISI_SAS_MAX_DEVICES;
 	int i;
 
-	spin_lock_irqsave(&hisi_hba->lock, flags);
+	spin_lock(&hisi_hba->lock);
 	for (i = first; i != last; i %= HISI_SAS_MAX_DEVICES) {
 		if (hisi_hba->devices[i].dev_type == SAS_PHY_UNUSED) {
 			int queue = i % hisi_hba->queue_count;
@@ -684,7 +678,7 @@ static struct hisi_sas_device *hisi_sas_alloc_dev(struct domain_device *device)
 		i++;
 	}
 	hisi_hba->last_dev_id = i;
-	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+	spin_unlock(&hisi_hba->lock);
 
 	return sas_dev;
 }
@@ -1233,10 +1227,10 @@ static int hisi_sas_exec_internal_tmf_task(struct domain_device *device,
 					struct hisi_sas_cq *cq =
 					       &hisi_hba->cq[slot->dlvry_queue];
 					/*
-					 * flush tasklet to avoid free'ing task
+					 * sync irq to avoid free'ing task
 					 * before using task in IO completion
 					 */
-					tasklet_kill(&cq->tasklet);
+					synchronize_irq(cq->irq_no);
 					slot->task = NULL;
 				}
 
@@ -1626,11 +1620,11 @@ static int hisi_sas_abort_task(struct sas_task *task)
 
 		if (slot) {
 			/*
-			 * flush tasklet to avoid free'ing task
+			 * sync irq to avoid free'ing task
 			 * before using task in IO completion
 			 */
 			cq = &hisi_hba->cq[slot->dlvry_queue];
-			tasklet_kill(&cq->tasklet);
+			synchronize_irq(cq->irq_no);
 		}
 		spin_unlock_irqrestore(&task->task_state_lock, flags);
 		rc = TMF_RESP_FUNC_COMPLETE;
@@ -1694,10 +1688,10 @@ static int hisi_sas_abort_task(struct sas_task *task)
 		if (((rc < 0) || (rc == TMF_RESP_FUNC_FAILED)) &&
 					task->lldd_task) {
 			/*
-			 * flush tasklet to avoid free'ing task
+			 * sync irq to avoid free'ing task
 			 * before using task in IO completion
 			 */
-			tasklet_kill(&cq->tasklet);
+			synchronize_irq(cq->irq_no);
 			slot->task = NULL;
 		}
 	}
@@ -1965,14 +1959,14 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	slot_idx = rc;
 	slot = &hisi_hba->slot_info[slot_idx];
 
-	spin_lock_irqsave(&dq->lock, flags);
+	spin_lock(&dq->lock);
 	wr_q_index = dq->wr_point;
 	dq->wr_point = (dq->wr_point + 1) % HISI_SAS_QUEUE_SLOTS;
 	list_add_tail(&slot->delivery, &dq->list);
-	spin_unlock_irqrestore(&dq->lock, flags);
-	spin_lock_irqsave(&sas_dev->lock, flags);
+	spin_unlock(&dq->lock);
+	spin_lock(&sas_dev->lock);
 	list_add_tail(&slot->entry, &sas_dev->list);
-	spin_unlock_irqrestore(&sas_dev->lock, flags);
+	spin_unlock(&sas_dev->lock);
 
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
@@ -2001,9 +1995,9 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 	WRITE_ONCE(slot->ready, 1);
 	/* send abort command to the chip */
-	spin_lock_irqsave(&dq->lock, flags);
+	spin_lock(&dq->lock);
 	hisi_hba->hw->start_delivery(dq);
-	spin_unlock_irqrestore(&dq->lock, flags);
+	spin_unlock(&dq->lock);
 
 	return 0;
 
@@ -2076,10 +2070,10 @@ _hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 				struct hisi_sas_cq *cq =
 					&hisi_hba->cq[slot->dlvry_queue];
 				/*
-				 * flush tasklet to avoid free'ing task
+				 * sync irq to avoid free'ing task
 				 * before using task in IO completion
 				 */
-				tasklet_kill(&cq->tasklet);
+				synchronize_irq(cq->irq_no);
 				slot->task = NULL;
 			}
 			dev_err(dev, "internal task abort: timeout and not done.\n");
@@ -2131,7 +2125,7 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	case HISI_SAS_INT_ABT_DEV:
 		for (i = 0; i < hisi_hba->cq_nvecs; i++) {
 			struct hisi_sas_cq *cq = &hisi_hba->cq[i];
-			const struct cpumask *mask = cq->pci_irq_mask;
+			const struct cpumask *mask = cq->irq_mask;
 
 			if (mask && !cpumask_intersects(cpu_online_mask, mask))
 				continue;
@@ -2225,17 +2219,17 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy)
 }
 EXPORT_SYMBOL_GPL(hisi_sas_phy_down);
 
-void hisi_sas_kill_tasklets(struct hisi_hba *hisi_hba)
+void hisi_sas_sync_irqs(struct hisi_hba *hisi_hba)
 {
 	int i;
 
 	for (i = 0; i < hisi_hba->cq_nvecs; i++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
 
-		tasklet_kill(&cq->tasklet);
+		synchronize_irq(cq->irq_no);
 	}
 }
-EXPORT_SYMBOL_GPL(hisi_sas_kill_tasklets);
+EXPORT_SYMBOL_GPL(hisi_sas_sync_irqs);
 
 int hisi_sas_host_reset(struct Scsi_Host *shost, int reset_type)
 {
@@ -3936,7 +3930,7 @@ void hisi_sas_debugfs_init(struct hisi_hba *hisi_hba)
 
 	hisi_hba->debugfs_dir = debugfs_create_dir(dev_name(dev),
 						   hisi_sas_debugfs_dir);
-	debugfs_create_file("trigger_dump", 0600,
+	debugfs_create_file("trigger_dump", 0200,
 			    hisi_hba->debugfs_dir,
 			    hisi_hba,
 			    &hisi_sas_debugfs_trigger_dump_fops);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 3af53cc42bd6..fa25766502a2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1772,6 +1772,9 @@ static struct scsi_host_template sht_v1_hw = {
 	.eh_target_reset_handler = sas_eh_target_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= sas_ioctl,
+#endif
 	.shost_attrs		= host_attrs_v1_hw,
 	.host_reset             = hisi_sas_host_reset,
 };
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 61b1e2693b08..e05faf315dcd 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -773,7 +773,6 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba,
 	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	int sata_idx = sas_dev->sata_idx;
 	int start, end;
-	unsigned long flags;
 
 	if (!sata_dev) {
 		/*
@@ -797,12 +796,12 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba,
 		end = 64 * (sata_idx + 2);
 	}
 
-	spin_lock_irqsave(&hisi_hba->lock, flags);
+	spin_lock(&hisi_hba->lock);
 	while (1) {
 		start = find_next_zero_bit(bitmap,
 					hisi_hba->slot_index_count, start);
 		if (start >= end) {
-			spin_unlock_irqrestore(&hisi_hba->lock, flags);
+			spin_unlock(&hisi_hba->lock);
 			return -SAS_QUEUE_FULL;
 		}
 		/*
@@ -814,7 +813,7 @@ slot_index_alloc_quirk_v2_hw(struct hisi_hba *hisi_hba,
 	}
 
 	set_bit(start, bitmap);
-	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+	spin_unlock(&hisi_hba->lock);
 	return start;
 }
 
@@ -843,9 +842,8 @@ hisi_sas_device *alloc_dev_quirk_v2_hw(struct domain_device *device)
 	struct hisi_sas_device *sas_dev = NULL;
 	int i, sata_dev = dev_is_sata(device);
 	int sata_idx = -1;
-	unsigned long flags;
 
-	spin_lock_irqsave(&hisi_hba->lock, flags);
+	spin_lock(&hisi_hba->lock);
 
 	if (sata_dev)
 		if (!sata_index_alloc_v2_hw(hisi_hba, &sata_idx))
@@ -876,7 +874,7 @@ hisi_sas_device *alloc_dev_quirk_v2_hw(struct domain_device *device)
 	}
 
 out:
-	spin_unlock_irqrestore(&hisi_hba->lock, flags);
+	spin_unlock(&hisi_hba->lock);
 
 	return sas_dev;
 }
@@ -3111,9 +3109,9 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
 	return IRQ_HANDLED;
 }
 
-static void cq_tasklet_v2_hw(unsigned long val)
+static irqreturn_t  cq_thread_v2_hw(int irq_no, void *p)
 {
-	struct hisi_sas_cq *cq = (struct hisi_sas_cq *)val;
+	struct hisi_sas_cq *cq = p;
 	struct hisi_hba *hisi_hba = cq->hisi_hba;
 	struct hisi_sas_slot *slot;
 	struct hisi_sas_itct *itct;
@@ -3181,6 +3179,8 @@ static void cq_tasklet_v2_hw(unsigned long val)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
@@ -3191,9 +3191,7 @@ static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
 
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
 
-	tasklet_schedule(&cq->tasklet);
-
-	return IRQ_HANDLED;
+	return IRQ_WAKE_THREAD;
 }
 
 static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
@@ -3360,18 +3358,18 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 
 	for (queue_no = 0; queue_no < hisi_hba->queue_count; queue_no++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[queue_no];
-		struct tasklet_struct *t = &cq->tasklet;
 
-		irq = irq_map[queue_no + 96];
-		rc = devm_request_irq(dev, irq, cq_interrupt_v2_hw, 0,
-				      DRV_NAME " cq", cq);
+		cq->irq_no = irq_map[queue_no + 96];
+		rc = devm_request_threaded_irq(dev, cq->irq_no,
+					       cq_interrupt_v2_hw,
+					       cq_thread_v2_hw, IRQF_ONESHOT,
+					       DRV_NAME " cq", cq);
 		if (rc) {
 			dev_err(dev, "irq init: could not request cq interrupt %d, rc=%d\n",
 				irq, rc);
 			rc = -ENOENT;
 			goto err_out;
 		}
-		tasklet_init(t, cq_tasklet_v2_hw, (unsigned long)cq);
 	}
 
 	hisi_hba->cq_nvecs = hisi_hba->queue_count;
@@ -3432,7 +3430,6 @@ static int soft_reset_v2_hw(struct hisi_hba *hisi_hba)
 
 	interrupt_disable_v2_hw(hisi_hba);
 	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
-	hisi_sas_kill_tasklets(hisi_hba);
 
 	hisi_sas_stop_phys(hisi_hba);
 
@@ -3551,6 +3548,9 @@ static struct scsi_host_template sht_v2_hw = {
 	.eh_target_reset_handler = sas_eh_target_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= sas_ioctl,
+#endif
 	.shost_attrs		= host_attrs_v2_hw,
 	.host_reset		= hisi_sas_host_reset,
 };
@@ -3603,11 +3603,6 @@ static int hisi_sas_v2_probe(struct platform_device *pdev)
 
 static int hisi_sas_v2_remove(struct platform_device *pdev)
 {
-	struct sas_ha_struct *sha = platform_get_drvdata(pdev);
-	struct hisi_hba *hisi_hba = sha->lldd_ha;
-
-	hisi_sas_kill_tasklets(hisi_hba);
-
 	return hisi_sas_remove(pdev);
 }
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index bf5d5f138437..a2debe0c8185 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -495,6 +495,13 @@ struct hisi_sas_err_record_v3 {
 #define BASE_VECTORS_V3_HW  16
 #define MIN_AFFINE_VECTORS_V3_HW  (BASE_VECTORS_V3_HW + 1)
 
+#define CHNL_INT_STS_MSK	0xeeeeeeee
+#define CHNL_INT_STS_PHY_MSK	0xe
+#define CHNL_INT_STS_INT0_MSK BIT(1)
+#define CHNL_INT_STS_INT1_MSK BIT(2)
+#define CHNL_INT_STS_INT2_MSK BIT(3)
+#define CHNL_WIDTH 4
+
 enum {
 	DSM_FUNC_ERR_HANDLE_MSI = 0,
 };
@@ -1819,19 +1826,19 @@ static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
 	int phy_no = 0;
 
 	irq_msk = hisi_sas_read32(hisi_hba, CHNL_INT_STATUS)
-				& 0xeeeeeeee;
+		  & CHNL_INT_STS_MSK;
 
 	while (irq_msk) {
-		if (irq_msk & (2 << (phy_no * 4)))
+		if (irq_msk & (CHNL_INT_STS_INT0_MSK << (phy_no * CHNL_WIDTH)))
 			handle_chl_int0_v3_hw(hisi_hba, phy_no);
 
-		if (irq_msk & (4 << (phy_no * 4)))
+		if (irq_msk & (CHNL_INT_STS_INT1_MSK << (phy_no * CHNL_WIDTH)))
 			handle_chl_int1_v3_hw(hisi_hba, phy_no);
 
-		if (irq_msk & (8 << (phy_no * 4)))
+		if (irq_msk & (CHNL_INT_STS_INT2_MSK << (phy_no * CHNL_WIDTH)))
 			handle_chl_int2_v3_hw(hisi_hba, phy_no);
 
-		irq_msk &= ~(0xe << (phy_no * 4));
+		irq_msk &= ~(CHNL_INT_STS_PHY_MSK << (phy_no * CHNL_WIDTH));
 		phy_no++;
 	}
 
@@ -2299,9 +2306,9 @@ out:
 	return sts;
 }
 
-static void cq_tasklet_v3_hw(unsigned long val)
+static irqreturn_t  cq_thread_v3_hw(int irq_no, void *p)
 {
-	struct hisi_sas_cq *cq = (struct hisi_sas_cq *)val;
+	struct hisi_sas_cq *cq = p;
 	struct hisi_hba *hisi_hba = cq->hisi_hba;
 	struct hisi_sas_slot *slot;
 	struct hisi_sas_complete_v3_hdr *complete_queue;
@@ -2338,6 +2345,8 @@ static void cq_tasklet_v3_hw(unsigned long val)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t cq_interrupt_v3_hw(int irq_no, void *p)
@@ -2348,9 +2357,7 @@ static irqreturn_t cq_interrupt_v3_hw(int irq_no, void *p)
 
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
 
-	tasklet_schedule(&cq->tasklet);
-
-	return IRQ_HANDLED;
+	return IRQ_WAKE_THREAD;
 }
 
 static void setup_reply_map_v3_hw(struct hisi_hba *hisi_hba, int nvecs)
@@ -2365,7 +2372,7 @@ static void setup_reply_map_v3_hw(struct hisi_hba *hisi_hba, int nvecs)
 					    BASE_VECTORS_V3_HW);
 		if (!mask)
 			goto fallback;
-		cq->pci_irq_mask = mask;
+		cq->irq_mask = mask;
 		for_each_cpu(cpu, mask)
 			hisi_hba->reply_map[cpu] = queue;
 	}
@@ -2389,6 +2396,8 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
 			.pre_vectors = BASE_VECTORS_V3_HW,
 		};
 
+		dev_info(dev, "Enable MSI auto-affinity\n");
+
 		min_msi = MIN_AFFINE_VECTORS_V3_HW;
 
 		hisi_hba->reply_map = devm_kcalloc(dev, nr_cpu_ids,
@@ -2441,15 +2450,20 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
 		goto free_irq_vectors;
 	}
 
-	/* Init tasklets for cq only */
+	if (hisi_sas_intr_conv)
+		dev_info(dev, "Enable interrupt converge\n");
+
 	for (i = 0; i < hisi_hba->cq_nvecs; i++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
-		struct tasklet_struct *t = &cq->tasklet;
 		int nr = hisi_sas_intr_conv ? 16 : 16 + i;
-		unsigned long irqflags = hisi_sas_intr_conv ? IRQF_SHARED : 0;
-
-		rc = devm_request_irq(dev, pci_irq_vector(pdev, nr),
-				      cq_interrupt_v3_hw, irqflags,
+		unsigned long irqflags = hisi_sas_intr_conv ? IRQF_SHARED :
+							      IRQF_ONESHOT;
+
+		cq->irq_no = pci_irq_vector(pdev, nr);
+		rc = devm_request_threaded_irq(dev, cq->irq_no,
+				      cq_interrupt_v3_hw,
+				      cq_thread_v3_hw,
+				      irqflags,
 				      DRV_NAME " cq", cq);
 		if (rc) {
 			dev_err(dev, "could not request cq%d interrupt, rc=%d\n",
@@ -2457,8 +2471,6 @@ static int interrupt_init_v3_hw(struct hisi_hba *hisi_hba)
 			rc = -ENOENT;
 			goto free_irq_vectors;
 		}
-
-		tasklet_init(t, cq_tasklet_v3_hw, (unsigned long)cq);
 	}
 
 	return 0;
@@ -2534,7 +2546,6 @@ static int disable_host_v3_hw(struct hisi_hba *hisi_hba)
 
 	interrupt_disable_v3_hw(hisi_hba);
 	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
-	hisi_sas_kill_tasklets(hisi_hba);
 
 	hisi_sas_stop_phys(hisi_hba);
 
@@ -2910,7 +2921,7 @@ static void debugfs_snapshot_prepare_v3_hw(struct hisi_hba *hisi_hba)
 
 	wait_cmds_complete_timeout_v3_hw(hisi_hba, 100, 5000);
 
-	hisi_sas_kill_tasklets(hisi_hba);
+	hisi_sas_sync_irqs(hisi_hba);
 }
 
 static void debugfs_snapshot_restore_v3_hw(struct hisi_hba *hisi_hba)
@@ -3075,6 +3086,9 @@ static struct scsi_host_template sht_v3_hw = {
 	.eh_target_reset_handler = sas_eh_target_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= sas_ioctl,
+#endif
 	.shost_attrs		= host_attrs_v3_hw,
 	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,
 	.host_reset             = hisi_sas_host_reset,
@@ -3309,7 +3323,6 @@ static void hisi_sas_v3_remove(struct pci_dev *pdev)
 	sas_remove_host(sha->core.shost);
 
 	hisi_sas_v3_destroy_irqs(pdev, hisi_hba);
-	hisi_sas_kill_tasklets(hisi_hba);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	hisi_sas_free(hisi_hba);
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 54b8c6f9daf4..d9e94e81da01 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -1877,7 +1877,6 @@ static void ibmvscsis_send_messages(struct scsi_info *vscsi)
 	 */
 	struct viosrp_crq *crq = (struct viosrp_crq *)&msg_hi;
 	struct ibmvscsis_cmd *cmd, *nxt;
-	struct iu_entry *iue;
 	long rc = ADAPT_SUCCESS;
 	bool retry = false;
 
@@ -1931,8 +1930,6 @@ static void ibmvscsis_send_messages(struct scsi_info *vscsi)
 					 */
 					vscsi->credit += 1;
 				} else {
-					iue = cmd->iue;
-
 					crq->valid = VALID_CMD_RESP_EL;
 					crq->format = cmd->rsp.format;
 
@@ -3796,7 +3793,6 @@ static int ibmvscsis_queue_data_in(struct se_cmd *se_cmd)
 						 se_cmd);
 	struct iu_entry *iue = cmd->iue;
 	struct scsi_info *vscsi = cmd->adapter;
-	char *sd;
 	uint len = 0;
 	int rc;
 
@@ -3804,7 +3800,6 @@ static int ibmvscsis_queue_data_in(struct se_cmd *se_cmd)
 			       1);
 	if (rc) {
 		dev_err(&vscsi->dev, "srp_transfer_data failed: %d\n", rc);
-		sd = se_cmd->sense_buffer;
 		se_cmd->scsi_sense_length = 18;
 		memset(se_cmd->sense_buffer, 0, se_cmd->scsi_sense_length);
 		/* Logical Unit Communication Time-out asc/ascq = 0x0801 */
diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c
index 41fd64c9c8e9..1d39628ac947 100644
--- a/drivers/scsi/initio.c
+++ b/drivers/scsi/initio.c
@@ -1640,7 +1640,7 @@ static int initio_state_6(struct initio_host * host)
  *
  */
 
-int initio_state_7(struct initio_host * host)
+static int initio_state_7(struct initio_host * host)
 {
 	int cnt, i;
 
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 079c04bc448a..ae45cbe98ae2 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -6727,6 +6727,9 @@ static struct scsi_host_template driver_template = {
 	.name = "IPR",
 	.info = ipr_ioa_info,
 	.ioctl = ipr_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl = ipr_ioctl,
+#endif
 	.queuecommand = ipr_queuecommand,
 	.eh_abort_handler = ipr_eh_abort,
 	.eh_device_reset_handler = ipr_eh_dev_reset,
diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c
index 1727d0c71b12..b48aac8dfcb8 100644
--- a/drivers/scsi/isci/init.c
+++ b/drivers/scsi/isci/init.c
@@ -168,6 +168,9 @@ static struct scsi_host_template isci_sht = {
 	.eh_target_reset_handler        = sas_eh_target_reset_handler,
 	.target_destroy			= sas_target_destroy,
 	.ioctl				= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl			= sas_ioctl,
+#endif
 	.shost_attrs			= isci_host_attrs,
 	.track_queue_depth		= 1,
 };
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 0bc63a7ab41c..b5dd1caae5e9 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -887,6 +887,10 @@ free_host:
 static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session)
 {
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
+	struct iscsi_session *session = cls_session->dd_data;
+
+	if (WARN_ON_ONCE(session->leadconn))
+		return;
 
 	iscsi_tcp_r2tpool_free(cls_session->dd_data);
 	iscsi_session_teardown(cls_session);
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index e9e00740f7ca..c5a828a041e0 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -137,7 +137,7 @@ static void sas_ata_task_done(struct sas_task *task)
 	} else {
 		ac = sas_to_ata_err(stat);
 		if (ac) {
-			pr_warn("%s: SAS error %x\n", __func__, stat->stat);
+			pr_warn("%s: SAS error 0x%x\n", __func__, stat->stat);
 			/* We saw a SAS error. Send a vague error. */
 			if (!link->sactive) {
 				qc->err_mask = ac;
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index d7302c2052f9..daf951b0b3f5 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -179,7 +179,7 @@ int sas_notify_lldd_dev_found(struct domain_device *dev)
 
 	res = i->dft->lldd_dev_found(dev);
 	if (res) {
-		pr_warn("driver on host %s cannot handle device %llx, error:%d\n",
+		pr_warn("driver on host %s cannot handle device %016llx, error:%d\n",
 			dev_name(sas_ha->dev),
 			SAS_ADDR(dev->sas_addr), res);
 	}
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 9fdb9c9fbda4..ab671cdd4cfb 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -500,7 +500,7 @@ static int sas_ex_general(struct domain_device *dev)
 		ex_assign_report_general(dev, rg_resp);
 
 		if (dev->ex_dev.configuring) {
-			pr_debug("RG: ex %llx self-configuring...\n",
+			pr_debug("RG: ex %016llx self-configuring...\n",
 				 SAS_ADDR(dev->sas_addr));
 			schedule_timeout_interruptible(5*HZ);
 		} else
@@ -881,7 +881,7 @@ static struct domain_device *sas_ex_discover_end_dev(
 
 		res = sas_discover_end_dev(child);
 		if (res) {
-			pr_notice("sas_discover_end_dev() for device %16llx at %016llx:%02d returned 0x%x\n",
+			pr_notice("sas_discover_end_dev() for device %016llx at %016llx:%02d returned 0x%x\n",
 				  SAS_ADDR(child->sas_addr),
 				  SAS_ADDR(parent->sas_addr), phy_id, res);
 			goto out_list_del;
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index 01f1738ce6df..1f1d01901978 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -107,7 +107,7 @@ static inline void sas_smp_host_handler(struct bsg_job *job,
 
 static inline void sas_fail_probe(struct domain_device *dev, const char *func, int err)
 {
-	pr_warn("%s: for %s device %16llx returned %d\n",
+	pr_warn("%s: for %s device %016llx returned %d\n",
 		func, dev->parent ? "exp-attached" :
 		"direct-attached",
 		SAS_ADDR(dev->sas_addr), err);
diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c
index 7c86fd248129..19cf418928fa 100644
--- a/drivers/scsi/libsas/sas_port.c
+++ b/drivers/scsi/libsas/sas_port.c
@@ -165,7 +165,7 @@ static void sas_form_port(struct asd_sas_phy *phy)
 	}
 	sas_port_add_phy(port->port, phy->phy);
 
-	pr_debug("%s added to %s, phy_mask:0x%x (%16llx)\n",
+	pr_debug("%s added to %s, phy_mask:0x%x (%016llx)\n",
 		 dev_name(&phy->phy->dev), dev_name(&port->port->dev),
 		 port->phy_mask,
 		 SAS_ADDR(port->attached_sas_addr));
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index bec83eb8ab87..9e0975e55c27 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -330,7 +330,7 @@ static int sas_recover_lu(struct domain_device *dev, struct scsi_cmnd *cmd)
 
 	int_to_scsilun(cmd->device->lun, &lun);
 
-	pr_notice("eh: device %llx LUN %llx has the task\n",
+	pr_notice("eh: device %016llx LUN 0x%llx has the task\n",
 		  SAS_ADDR(dev->sas_addr),
 		  cmd->device->lun);
 
@@ -615,7 +615,7 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
  reset:
 			tmf_resp = sas_recover_lu(task->dev, cmd);
 			if (tmf_resp == TMF_RESP_FUNC_COMPLETE) {
-				pr_notice("dev %016llx LU %llx is recovered\n",
+				pr_notice("dev %016llx LU 0x%llx is recovered\n",
 					  SAS_ADDR(task->dev),
 					  cmd->device->lun);
 				sas_eh_finish_cmd(cmd);
@@ -666,7 +666,7 @@ static void sas_eh_handle_sas_errors(struct Scsi_Host *shost, struct list_head *
 			 * of effort could recover from errors.  Quite
 			 * possibly the HA just disappeared.
 			 */
-			pr_err("error from  device %llx, LUN %llx couldn't be recovered in any way\n",
+			pr_err("error from device %016llx, LUN 0x%llx couldn't be recovered in any way\n",
 			       SAS_ADDR(task->dev->sas_addr),
 			       cmd->device->lun);
 
@@ -851,7 +851,7 @@ int sas_slave_configure(struct scsi_device *scsi_dev)
 	if (scsi_dev->tagged_supported) {
 		scsi_change_queue_depth(scsi_dev, SAS_DEF_QD);
 	} else {
-		pr_notice("device %llx, LUN %llx doesn't support TCQ\n",
+		pr_notice("device %016llx, LUN 0x%llx doesn't support TCQ\n",
 			  SAS_ADDR(dev->sas_addr), scsi_dev->lun);
 		scsi_change_queue_depth(scsi_dev, 1);
 	}
diff --git a/drivers/scsi/libsas/sas_task.c b/drivers/scsi/libsas/sas_task.c
index 1ded7d85027e..e2d42593ce52 100644
--- a/drivers/scsi/libsas/sas_task.c
+++ b/drivers/scsi/libsas/sas_task.c
@@ -27,7 +27,7 @@ void sas_ssp_task_response(struct device *dev, struct sas_task *task,
 		memcpy(tstat->buf, iu->sense_data, tstat->buf_valid_size);
 
 		if (iu->status != SAM_STAT_CHECK_CONDITION)
-			dev_warn(dev, "dev %llx sent sense data, but stat(%x) is not CHECK CONDITION\n",
+			dev_warn(dev, "dev %016llx sent sense data, but stat(0x%x) is not CHECK CONDITION\n",
 				 SAS_ADDR(task->dev->sas_addr), iu->status);
 	}
 	else
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 935f98804198..04d73e2be373 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -1223,6 +1223,8 @@ struct lpfc_hba {
 #define LPFC_POLL_HB	1		/* slowpath heartbeat */
 #define LPFC_POLL_FASTPATH	0	/* called from fastpath */
 #define LPFC_POLL_SLOWPATH	1	/* called from slowpath */
+
+	char os_host_name[MAXHOSTNAMELEN];
 };
 
 static inline struct Scsi_Host *
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 4ff82b36a37a..46f56f30f77e 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -4123,14 +4123,13 @@ lpfc_topology_store(struct device *dev, struct device_attribute *attr,
 		/*
 		 * The 'topology' is not a configurable parameter if :
 		 *   - persistent topology enabled
-		 *   - G7 adapters
-		 *   - G6 with no private loop support
+		 *   - G7/G6 with no private loop support
 		 */
 
-		if (((phba->hba_flag & HBA_PERSISTENT_TOPO) ||
+		if ((phba->hba_flag & HBA_PERSISTENT_TOPO ||
 		     (!phba->sli4_hba.pc_sli4_params.pls &&
-		     phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC) ||
-		     phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC) &&
+		     (phba->pcidev->device == PCI_DEVICE_ID_LANCER_G6_FC ||
+		     phba->pcidev->device == PCI_DEVICE_ID_LANCER_G7_FC))) &&
 		    val == 4) {
 			lpfc_printf_vlog(vport, KERN_ERR, LOG_INIT,
 				"3114 Loop mode not supported\n");
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index ee353c84a097..25d3dd39bc05 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -180,7 +180,7 @@ int lpfc_issue_gidft(struct lpfc_vport *vport);
 int lpfc_get_gidft_type(struct lpfc_vport *vport, struct lpfc_iocbq *iocbq);
 int lpfc_ns_cmd(struct lpfc_vport *, int, uint8_t, uint32_t);
 int lpfc_fdmi_cmd(struct lpfc_vport *, struct lpfc_nodelist *, int, uint32_t);
-void lpfc_fdmi_num_disc_check(struct lpfc_vport *);
+void lpfc_fdmi_change_check(struct lpfc_vport *vport);
 void lpfc_delayed_disc_tmo(struct timer_list *);
 void lpfc_delayed_disc_timeout_handler(struct lpfc_vport *);
 
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 99c9bb249758..58b35a1442c1 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -1493,33 +1493,35 @@ int
 lpfc_vport_symbolic_node_name(struct lpfc_vport *vport, char *symbol,
 	size_t size)
 {
-	char fwrev[FW_REV_STR_SIZE];
-	int n;
+	char fwrev[FW_REV_STR_SIZE] = {0};
+	char tmp[MAXHOSTNAMELEN] = {0};
 
-	lpfc_decode_firmware_rev(vport->phba, fwrev, 0);
+	memset(symbol, 0, size);
 
-	n = scnprintf(symbol, size, "Emulex %s", vport->phba->ModelName);
-	if (size < n)
-		return n;
+	scnprintf(tmp, sizeof(tmp), "Emulex %s", vport->phba->ModelName);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
-	n += scnprintf(symbol + n, size - n, " FV%s", fwrev);
-	if (size < n)
-		return n;
+	lpfc_decode_firmware_rev(vport->phba, fwrev, 0);
+	scnprintf(tmp, sizeof(tmp), " FV%s", fwrev);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
-	n += scnprintf(symbol + n, size - n, " DV%s.",
-		      lpfc_release_version);
-	if (size < n)
-		return n;
+	scnprintf(tmp, sizeof(tmp), " DV%s", lpfc_release_version);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
-	n += scnprintf(symbol + n, size - n, " HN:%s.",
-		      init_utsname()->nodename);
-	if (size < n)
-		return n;
+	scnprintf(tmp, sizeof(tmp), " HN:%s", vport->phba->os_host_name);
+	if (strlcat(symbol, tmp, size) >= size)
+		goto buffer_done;
 
 	/* Note :- OS name is "Linux" */
-	n += scnprintf(symbol + n, size - n, " OS:%s",
-		      init_utsname()->sysname);
-	return n;
+	scnprintf(tmp, sizeof(tmp), " OS:%s", init_utsname()->sysname);
+	strlcat(symbol, tmp, size);
+
+buffer_done:
+	return strnlen(symbol, size);
+
 }
 
 static uint32_t
@@ -1998,14 +2000,16 @@ lpfc_cmpl_ct_disc_fdmi(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 
 /**
- * lpfc_fdmi_num_disc_check - Check how many mapped NPorts we are connected to
+ * lpfc_fdmi_change_check - Check for changed FDMI parameters
  * @vport: pointer to a host virtual N_Port data structure.
  *
- * Called from hbeat timeout routine to check if the number of discovered
- * ports has changed. If so, re-register thar port Attribute.
+ * Check how many mapped NPorts we are connected to
+ * Check if our hostname changed
+ * Called from hbeat timeout routine to check if any FDMI parameters
+ * changed. If so, re-register those Attributes.
  */
 void
-lpfc_fdmi_num_disc_check(struct lpfc_vport *vport)
+lpfc_fdmi_change_check(struct lpfc_vport *vport)
 {
 	struct lpfc_hba *phba = vport->phba;
 	struct lpfc_nodelist *ndlp;
@@ -2018,17 +2022,41 @@ lpfc_fdmi_num_disc_check(struct lpfc_vport *vport)
 	if (!(vport->fc_flag & FC_FABRIC))
 		return;
 
+	ndlp = lpfc_findnode_did(vport, FDMI_DID);
+	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
+		return;
+
+	/* Check if system hostname changed */
+	if (strcmp(phba->os_host_name, init_utsname()->nodename)) {
+		memset(phba->os_host_name, 0, sizeof(phba->os_host_name));
+		scnprintf(phba->os_host_name, sizeof(phba->os_host_name), "%s",
+			  init_utsname()->nodename);
+		lpfc_ns_cmd(vport, SLI_CTNS_RSNN_NN, 0, 0);
+
+		/* Since this effects multiple HBA and PORT attributes, we need
+		 * de-register and go thru the whole FDMI registration cycle.
+		 * DHBA -> DPRT -> RHBA -> RPA  (physical port)
+		 * DPRT -> RPRT (vports)
+		 */
+		if (vport->port_type == LPFC_PHYSICAL_PORT)
+			lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_DHBA, 0);
+		else
+			lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_DPRT, 0);
+
+		/* Since this code path registers all the port attributes
+		 * we can just return without further checking.
+		 */
+		return;
+	}
+
 	if (!(vport->fdmi_port_mask & LPFC_FDMI_PORT_ATTR_num_disc))
 		return;
 
+	/* Check if the number of mapped NPorts changed */
 	cnt = lpfc_find_map_node(vport);
 	if (cnt == vport->fdmi_num_disc)
 		return;
 
-	ndlp = lpfc_findnode_did(vport, FDMI_DID);
-	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
-		return;
-
 	if (vport->port_type == LPFC_PHYSICAL_PORT) {
 		lpfc_fdmi_cmd(vport, ndlp, SLI_MGMT_RPA,
 			      LPFC_FDMI_PORT_ATTR_num_disc);
@@ -2616,8 +2644,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport,
 	ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue;
 	memset(ae, 0, 256);
 
-	snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s",
-		 init_utsname()->nodename);
+	scnprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s",
+		  vport->phba->os_host_name);
 
 	len = strnlen(ae->un.AttrString, sizeof(ae->un.AttrString));
 	len += (len & 3) ? (4 - (len & 3)) : 4;
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index a5ecbce4eda2..819335b16c2e 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -2085,6 +2085,8 @@ static int lpfc_debugfs_ras_log_data(struct lpfc_hba *phba,
 	int copied = 0;
 	struct lpfc_dmabuf *dmabuf, *next;
 
+	memset(buffer, 0, size);
+
 	spin_lock_irq(&phba->hbalock);
 	if (phba->ras_fwlog.state != ACTIVE) {
 		spin_unlock_irq(&phba->hbalock);
@@ -2094,10 +2096,15 @@ static int lpfc_debugfs_ras_log_data(struct lpfc_hba *phba,
 
 	list_for_each_entry_safe(dmabuf, next,
 				 &phba->ras_fwlog.fwlog_buff_list, list) {
+		/* Check if copying will go over size and a '\0' char */
+		if ((copied + LPFC_RAS_MAX_ENTRY_SIZE) >= (size - 1)) {
+			memcpy(buffer + copied, dmabuf->virt,
+			       size - copied - 1);
+			copied += size - copied - 1;
+			break;
+		}
 		memcpy(buffer + copied, dmabuf->virt, LPFC_RAS_MAX_ENTRY_SIZE);
 		copied += LPFC_RAS_MAX_ENTRY_SIZE;
-		if (size > copied)
-			break;
 	}
 	return copied;
 }
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 85ada3deb47d..dcc8999c6a68 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -28,6 +28,7 @@
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/lockdep.h>
+#include <linux/utsname.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_device.h>
@@ -3315,6 +3316,10 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la)
 		lpfc_sli4_clear_fcf_rr_bmask(phba);
 	}
 
+	/* Prepare for LINK up registrations */
+	memset(phba->os_host_name, 0, sizeof(phba->os_host_name));
+	scnprintf(phba->os_host_name, sizeof(phba->os_host_name), "%s",
+		  init_utsname()->nodename);
 	return;
 out:
 	lpfc_vport_set_state(vport, FC_VPORT_FAILED);
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index 25cdcbc2b02f..9a064b96e570 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -3925,6 +3925,9 @@ struct lpfc_mbx_wr_object {
 #define LPFC_CHANGE_STATUS_FW_RESET		0x02
 #define LPFC_CHANGE_STATUS_PORT_MIGRATION	0x04
 #define LPFC_CHANGE_STATUS_PCI_RESET		0x05
+#define lpfc_wr_object_csf_SHIFT		8
+#define lpfc_wr_object_csf_MASK			0x00000001
+#define lpfc_wr_object_csf_WORD			word5
 		} response;
 	} u;
 };
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 6a04fdb3fbf2..5a605773dd0a 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -1362,7 +1362,7 @@ lpfc_hb_timeout_handler(struct lpfc_hba *phba)
 	if (vports != NULL)
 		for (i = 0; i <= phba->max_vports && vports[i] != NULL; i++) {
 			lpfc_rcv_seq_check_edtov(vports[i]);
-			lpfc_fdmi_num_disc_check(vports[i]);
+			lpfc_fdmi_change_check(vports[i]);
 		}
 	lpfc_destroy_vport_work_array(phba, vports);
 
@@ -8320,14 +8320,6 @@ lpfc_map_topology(struct lpfc_hba *phba, struct lpfc_mbx_read_config *rd_config)
 	phba->hba_flag |= HBA_PERSISTENT_TOPO;
 	switch (phba->pcidev->device) {
 	case PCI_DEVICE_ID_LANCER_G7_FC:
-		if (tf || (pt == LINK_FLAGS_LOOP)) {
-			/* Invalid values from FW - use driver params */
-			phba->hba_flag &= ~HBA_PERSISTENT_TOPO;
-		} else {
-			/* Prism only supports PT2PT topology */
-			phba->cfg_topology = FLAGS_TOPOLOGY_MODE_PT_PT;
-		}
-		break;
 	case PCI_DEVICE_ID_LANCER_G6_FC:
 		if (!tf) {
 			phba->cfg_topology = ((pt == LINK_FLAGS_LOOP)
@@ -10449,6 +10441,8 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba)
 	case LPFC_SLI_INTF_IF_TYPE_6:
 		iounmap(phba->sli4_hba.drbl_regs_memmap_p);
 		iounmap(phba->sli4_hba.conf_regs_memmap_p);
+		if (phba->sli4_hba.dpp_regs_memmap_p)
+			iounmap(phba->sli4_hba.dpp_regs_memmap_p);
 		break;
 	case LPFC_SLI_INTF_IF_TYPE_1:
 	default:
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index ae4359013846..a024e5a3918f 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -308,7 +308,7 @@ lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox)
 				mb->mbxStatus);
 		mempool_free(login_mbox, phba->mbox_mem_pool);
 		mempool_free(link_mbox, phba->mbox_mem_pool);
-		lpfc_sli_release_iocbq(phba, save_iocb);
+		kfree(save_iocb);
 		return;
 	}
 
@@ -325,7 +325,61 @@ lpfc_defer_pt2pt_acc(struct lpfc_hba *phba, LPFC_MBOXQ_t *link_mbox)
 	}
 
 	mempool_free(link_mbox, phba->mbox_mem_pool);
-	lpfc_sli_release_iocbq(phba, save_iocb);
+	kfree(save_iocb);
+}
+
+/**
+ * lpfc_defer_tgt_acc - Progress SLI4 target rcv PLOGI handler
+ * @phba: Pointer to HBA context object.
+ * @pmb: Pointer to mailbox object.
+ *
+ * This function provides the unreg rpi mailbox completion handler for a tgt.
+ * The routine frees the memory resources associated with the completed
+ * mailbox command and transmits the ELS ACC.
+ *
+ * This routine is only called if we are SLI4, acting in target
+ * mode and the remote NPort issues the PLOGI after link up.
+ **/
+static void
+lpfc_defer_acc_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
+{
+	struct lpfc_vport *vport = pmb->vport;
+	struct lpfc_nodelist *ndlp = pmb->ctx_ndlp;
+	LPFC_MBOXQ_t *mbox = pmb->context3;
+	struct lpfc_iocbq *piocb = NULL;
+	int rc;
+
+	if (mbox) {
+		pmb->context3 = NULL;
+		piocb = mbox->context3;
+		mbox->context3 = NULL;
+	}
+
+	/*
+	 * Complete the unreg rpi mbx request, and update flags.
+	 * This will also restart any deferred events.
+	 */
+	lpfc_nlp_get(ndlp);
+	lpfc_sli4_unreg_rpi_cmpl_clr(phba, pmb);
+
+	if (!piocb) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY | LOG_ELS,
+				 "4578 PLOGI ACC fail\n");
+		if (mbox)
+			mempool_free(mbox, phba->mbox_mem_pool);
+		goto out;
+	}
+
+	rc = lpfc_els_rsp_acc(vport, ELS_CMD_PLOGI, piocb, ndlp, mbox);
+	if (rc) {
+		lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY | LOG_ELS,
+				 "4579 PLOGI ACC fail %x\n", rc);
+		if (mbox)
+			mempool_free(mbox, phba->mbox_mem_pool);
+	}
+	kfree(piocb);
+out:
+	lpfc_nlp_put(ndlp);
 }
 
 static int
@@ -345,6 +399,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	struct lpfc_iocbq *save_iocb;
 	struct ls_rjt stat;
 	uint32_t vid, flag;
+	u16 rpi;
 	int rc, defer_acc;
 
 	memset(&stat, 0, sizeof (struct ls_rjt));
@@ -488,7 +543,7 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			link_mbox->vport = vport;
 			link_mbox->ctx_ndlp = ndlp;
 
-			save_iocb = lpfc_sli_get_iocbq(phba);
+			save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL);
 			if (!save_iocb)
 				goto out;
 			/* Save info from cmd IOCB used in rsp */
@@ -513,7 +568,36 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 		goto out;
 
 	/* Registering an existing RPI behaves differently for SLI3 vs SLI4 */
-	if (phba->sli_rev == LPFC_SLI_REV4)
+	if (phba->nvmet_support && !defer_acc) {
+		link_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL);
+		if (!link_mbox)
+			goto out;
+
+		/* As unique identifiers such as iotag would be overwritten
+		 * with those from the cmdiocb, allocate separate temporary
+		 * storage for the copy.
+		 */
+		save_iocb = kzalloc(sizeof(*save_iocb), GFP_KERNEL);
+		if (!save_iocb)
+			goto out;
+
+		/* Unreg RPI is required for SLI4. */
+		rpi = phba->sli4_hba.rpi_ids[ndlp->nlp_rpi];
+		lpfc_unreg_login(phba, vport->vpi, rpi, link_mbox);
+		link_mbox->vport = vport;
+		link_mbox->ctx_ndlp = ndlp;
+		link_mbox->mbox_cmpl = lpfc_defer_acc_rsp;
+
+		if (((ndlp->nlp_DID & Fabric_DID_MASK) != Fabric_DID_MASK) &&
+		    (!(vport->fc_flag & FC_OFFLINE_MODE)))
+			ndlp->nlp_flag |= NLP_UNREG_INP;
+
+		/* Save info from cmd IOCB used in rsp */
+		memcpy(save_iocb, cmdiocb, sizeof(*save_iocb));
+
+		/* Delay sending ACC till unreg RPI completes. */
+		defer_acc = 1;
+	} else if (phba->sli_rev == LPFC_SLI_REV4)
 		lpfc_unreg_rpi(vport, ndlp);
 
 	rc = lpfc_reg_rpi(phba, vport->vpi, icmd->un.rcvels.remoteID,
@@ -553,6 +637,9 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	if ((vport->port_type == LPFC_NPIV_PORT &&
 	     vport->cfg_restrict_login)) {
 
+		/* no deferred ACC */
+		kfree(save_iocb);
+
 		/* In order to preserve RPIs, we want to cleanup
 		 * the default RPI the firmware created to rcv
 		 * this ELS request. The only way to do this is
@@ -571,8 +658,12 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 	}
 	if (defer_acc) {
 		/* So the order here should be:
-		 * Issue CONFIG_LINK mbox
-		 * CONFIG_LINK cmpl
+		 * SLI3 pt2pt
+		 *   Issue CONFIG_LINK mbox
+		 *   CONFIG_LINK cmpl
+		 * SLI4 tgt
+		 *   Issue UNREG RPI mbx
+		 *   UNREG RPI cmpl
 		 * Issue PLOGI ACC
 		 * PLOGI ACC cmpl
 		 * Issue REG_LOGIN mbox
@@ -596,10 +687,9 @@ lpfc_rcv_plogi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 out:
 	if (defer_acc)
 		lpfc_printf_log(phba, KERN_ERR, LOG_DISCOVERY,
-				"4577 pt2pt discovery failure: %p %p %p\n",
+				"4577 discovery failure: %p %p %p\n",
 				save_iocb, link_mbox, login_mbox);
-	if (save_iocb)
-		lpfc_sli_release_iocbq(phba, save_iocb);
+	kfree(save_iocb);
 	if (link_mbox)
 		mempool_free(link_mbox, phba->mbox_mem_pool);
 	if (login_mbox)
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index b138d9fee675..2c7e0b22db2f 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -481,7 +481,7 @@ lpfc_sli4_vport_delete_fcp_xri_aborted(struct lpfc_vport *vport)
 		spin_lock(&qp->abts_io_buf_list_lock);
 		list_for_each_entry_safe(psb, next_psb,
 					 &qp->lpfc_abts_io_buf_list, list) {
-			if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME)
+			if (psb->cur_iocbq.iocb_flag & LPFC_IO_NVME)
 				continue;
 
 			if (psb->rdata && psb->rdata->pnode &&
@@ -528,7 +528,7 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 			list_del_init(&psb->list);
 			psb->flags &= ~LPFC_SBUF_XBUSY;
 			psb->status = IOSTAT_SUCCESS;
-			if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME) {
+			if (psb->cur_iocbq.iocb_flag & LPFC_IO_NVME) {
 				qp->abts_nvme_io_bufs--;
 				spin_unlock(&qp->abts_io_buf_list_lock);
 				spin_unlock_irqrestore(&phba->hbalock, iflag);
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 625c046ac4ef..64002b0cb02d 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -4918,8 +4918,17 @@ static int
 lpfc_sli4_rb_setup(struct lpfc_hba *phba)
 {
 	phba->hbq_in_use = 1;
-	phba->hbqs[LPFC_ELS_HBQ].entry_count =
-		lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count;
+	/**
+	 * Specific case when the MDS diagnostics is enabled and supported.
+	 * The receive buffer count is truncated to manage the incoming
+	 * traffic.
+	 **/
+	if (phba->cfg_enable_mds_diags && phba->mds_diags_support)
+		phba->hbqs[LPFC_ELS_HBQ].entry_count =
+			lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count >> 1;
+	else
+		phba->hbqs[LPFC_ELS_HBQ].entry_count =
+			lpfc_hbq_defs[LPFC_ELS_HBQ]->entry_count;
 	phba->hbq_count = 1;
 	lpfc_sli_hbqbuf_init_hbqs(phba, LPFC_ELS_HBQ);
 	/* Initially populate or replenish the HBQs */
@@ -19449,7 +19458,7 @@ lpfc_wr_object(struct lpfc_hba *phba, struct list_head *dmabuf_list,
 	struct lpfc_mbx_wr_object *wr_object;
 	LPFC_MBOXQ_t *mbox;
 	int rc = 0, i = 0;
-	uint32_t shdr_status, shdr_add_status, shdr_change_status;
+	uint32_t shdr_status, shdr_add_status, shdr_change_status, shdr_csf;
 	uint32_t mbox_tmo;
 	struct lpfc_dmabuf *dmabuf;
 	uint32_t written = 0;
@@ -19506,6 +19515,16 @@ lpfc_wr_object(struct lpfc_hba *phba, struct list_head *dmabuf_list,
 	if (check_change_status) {
 		shdr_change_status = bf_get(lpfc_wr_object_change_status,
 					    &wr_object->u.response);
+
+		if (shdr_change_status == LPFC_CHANGE_STATUS_FW_RESET ||
+		    shdr_change_status == LPFC_CHANGE_STATUS_PORT_MIGRATION) {
+			shdr_csf = bf_get(lpfc_wr_object_csf,
+					  &wr_object->u.response);
+			if (shdr_csf)
+				shdr_change_status =
+						   LPFC_CHANGE_STATUS_PCI_RESET;
+		}
+
 		switch (shdr_change_status) {
 		case (LPFC_CHANGE_STATUS_PHYS_DEV_RESET):
 			lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 9e5ff58edaca..9563c49f36ab 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.6.0.2"
+#define LPFC_DRIVER_VERSION "12.6.0.3"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index bd8184072bed..83d8c4cb1ad5 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -21,8 +21,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"07.710.50.00-rc1"
-#define MEGASAS_RELDATE				"June 28, 2019"
+#define MEGASAS_VERSION				"07.713.01.00-rc1"
+#define MEGASAS_RELDATE				"Dec 27, 2019"
 
 #define MEGASAS_MSIX_NAME_LEN			32
 
@@ -2233,9 +2233,9 @@ enum MR_PD_TYPE {
 
 /* JBOD Queue depth definitions */
 #define MEGASAS_SATA_QD	32
-#define MEGASAS_SAS_QD	64
+#define MEGASAS_SAS_QD 256
 #define MEGASAS_DEFAULT_PD_QD	64
-#define MEGASAS_NVME_QD		32
+#define MEGASAS_NVME_QD        64
 
 #define MR_DEFAULT_NVME_PAGE_SIZE	4096
 #define MR_DEFAULT_NVME_PAGE_SHIFT	12
@@ -2640,10 +2640,11 @@ enum MEGASAS_OCR_CAUSE {
 };
 
 enum DCMD_RETURN_STATUS {
-	DCMD_SUCCESS		= 0,
-	DCMD_TIMEOUT		= 1,
-	DCMD_FAILED		= 2,
-	DCMD_NOT_FIRED		= 3,
+	DCMD_SUCCESS    = 0x00,
+	DCMD_TIMEOUT    = 0x01,
+	DCMD_FAILED     = 0x02,
+	DCMD_BUSY       = 0x03,
+	DCMD_INIT       = 0xff,
 };
 
 u8
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index c60cd9fc4240..acb82181f70f 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -1099,7 +1099,7 @@ megasas_issue_polled(struct megasas_instance *instance, struct megasas_cmd *cmd)
 	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 			__func__, __LINE__);
-		return DCMD_NOT_FIRED;
+		return DCMD_INIT;
 	}
 
 	instance->instancet->issue_dcmd(instance, cmd);
@@ -1123,19 +1123,19 @@ megasas_issue_blocked_cmd(struct megasas_instance *instance,
 			  struct megasas_cmd *cmd, int timeout)
 {
 	int ret = 0;
-	cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
+	cmd->cmd_status_drv = DCMD_INIT;
 
 	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 			__func__, __LINE__);
-		return DCMD_NOT_FIRED;
+		return DCMD_INIT;
 	}
 
 	instance->instancet->issue_dcmd(instance, cmd);
 
 	if (timeout) {
 		ret = wait_event_timeout(instance->int_cmd_wait_q,
-				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS, timeout * HZ);
+		cmd->cmd_status_drv != DCMD_INIT, timeout * HZ);
 		if (!ret) {
 			dev_err(&instance->pdev->dev,
 				"DCMD(opcode: 0x%x) is timed out, func:%s\n",
@@ -1144,10 +1144,9 @@ megasas_issue_blocked_cmd(struct megasas_instance *instance,
 		}
 	} else
 		wait_event(instance->int_cmd_wait_q,
-				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS);
+				cmd->cmd_status_drv != DCMD_INIT);
 
-	return (cmd->cmd_status_drv == MFI_STAT_OK) ?
-		DCMD_SUCCESS : DCMD_FAILED;
+	return cmd->cmd_status_drv;
 }
 
 /**
@@ -1190,19 +1189,19 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 		cpu_to_le32(upper_32_bits(cmd_to_abort->frame_phys_addr));
 
 	cmd->sync_cmd = 1;
-	cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
+	cmd->cmd_status_drv = DCMD_INIT;
 
 	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 			__func__, __LINE__);
-		return DCMD_NOT_FIRED;
+		return DCMD_INIT;
 	}
 
 	instance->instancet->issue_dcmd(instance, cmd);
 
 	if (timeout) {
 		ret = wait_event_timeout(instance->abort_cmd_wait_q,
-				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS, timeout * HZ);
+		cmd->cmd_status_drv != DCMD_INIT, timeout * HZ);
 		if (!ret) {
 			opcode = cmd_to_abort->frame->dcmd.opcode;
 			dev_err(&instance->pdev->dev,
@@ -1212,13 +1211,12 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 		}
 	} else
 		wait_event(instance->abort_cmd_wait_q,
-				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS);
+		cmd->cmd_status_drv != DCMD_INIT);
 
 	cmd->sync_cmd = 0;
 
 	megasas_return_cmd(instance, cmd);
-	return (cmd->cmd_status_drv == MFI_STAT_OK) ?
-		DCMD_SUCCESS : DCMD_FAILED;
+	return cmd->cmd_status_drv;
 }
 
 /**
@@ -1887,6 +1885,10 @@ void megasas_set_dynamic_target_properties(struct scsi_device *sdev,
 
 		mr_device_priv_data->is_tm_capable =
 			raid->capability.tmCapable;
+
+		if (!raid->flags.isEPD)
+			sdev->no_write_same = 1;
+
 	} else if (instance->use_seqnum_jbod_fp) {
 		pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
 			sdev->id;
@@ -2150,6 +2152,12 @@ static void megasas_complete_outstanding_ioctls(struct megasas_instance *instanc
 
 void megaraid_sas_kill_hba(struct megasas_instance *instance)
 {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
+		dev_warn(&instance->pdev->dev,
+			 "Adapter already dead, skipping kill HBA\n");
+		return;
+	}
+
 	/* Set critical error to block I/O & ioctls in case caller didn't */
 	atomic_set(&instance->adprecovery, MEGASAS_HW_CRITICAL_ERROR);
 	/* Wait 1 second to ensure IO or ioctls in build have posted */
@@ -2726,7 +2734,7 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 						"reset queue\n",
 						reset_cmd);
 
-				reset_cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
+				reset_cmd->cmd_status_drv = DCMD_INIT;
 				instance->instancet->fire_cmd(instance,
 						reset_cmd->frame_phys_addr,
 						0, instance->reg_set);
@@ -3416,7 +3424,6 @@ static struct scsi_host_template megasas_template = {
 	.bios_param = megasas_bios_param,
 	.change_queue_depth = scsi_change_queue_depth,
 	.max_segment_size = 0xffffffff,
-	.no_write_same = 1,
 };
 
 /**
@@ -3432,7 +3439,11 @@ static void
 megasas_complete_int_cmd(struct megasas_instance *instance,
 			 struct megasas_cmd *cmd)
 {
-	cmd->cmd_status_drv = cmd->frame->io.cmd_status;
+	if (cmd->cmd_status_drv == DCMD_INIT)
+		cmd->cmd_status_drv =
+		(cmd->frame->io.cmd_status == MFI_STAT_OK) ?
+		DCMD_SUCCESS : DCMD_FAILED;
+
 	wake_up(&instance->int_cmd_wait_q);
 }
 
@@ -3451,7 +3462,7 @@ megasas_complete_abort(struct megasas_instance *instance,
 {
 	if (cmd->sync_cmd) {
 		cmd->sync_cmd = 0;
-		cmd->cmd_status_drv = 0;
+		cmd->cmd_status_drv = DCMD_SUCCESS;
 		wake_up(&instance->abort_cmd_wait_q);
 	}
 }
@@ -3727,7 +3738,7 @@ megasas_issue_pending_cmds_again(struct megasas_instance *instance)
 			dev_notice(&instance->pdev->dev, "%p synchronous cmd"
 						"on the internal reset queue,"
 						"issue it again.\n", cmd);
-			cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
+			cmd->cmd_status_drv = DCMD_INIT;
 			instance->instancet->fire_cmd(instance,
 							cmd->frame_phys_addr,
 							0, instance->reg_set);
@@ -4392,7 +4403,8 @@ dcmd_timeout_ocr_possible(struct megasas_instance *instance) {
 	if (instance->adapter_type == MFI_SERIES)
 		return KILL_ADAPTER;
 	else if (instance->unload ||
-			test_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags))
+			test_bit(MEGASAS_FUSION_OCR_NOT_POSSIBLE,
+				 &instance->reset_flags))
 		return IGNORE_TIMEOUT;
 	else
 		return INITIATE_OCR;
@@ -7593,6 +7605,7 @@ megasas_resume(struct pci_dev *pdev)
 	struct Scsi_Host *host;
 	struct megasas_instance *instance;
 	int irq_flags = PCI_IRQ_LEGACY;
+	u32 status_reg;
 
 	instance = pci_get_drvdata(pdev);
 
@@ -7620,9 +7633,35 @@ megasas_resume(struct pci_dev *pdev)
 	/*
 	 * We expect the FW state to be READY
 	 */
-	if (megasas_transition_to_ready(instance, 0))
-		goto fail_ready_state;
 
+	if (megasas_transition_to_ready(instance, 0)) {
+		dev_info(&instance->pdev->dev,
+			 "Failed to transition controller to ready from %s!\n",
+			 __func__);
+		if (instance->adapter_type != MFI_SERIES) {
+			status_reg =
+				instance->instancet->read_fw_status_reg(instance);
+			if (!(status_reg & MFI_RESET_ADAPTER) ||
+				((megasas_adp_reset_wait_for_ready
+				(instance, true, 0)) == FAILED))
+				goto fail_ready_state;
+		} else {
+			atomic_set(&instance->fw_reset_no_pci_access, 1);
+			instance->instancet->adp_reset
+				(instance, instance->reg_set);
+			atomic_set(&instance->fw_reset_no_pci_access, 0);
+
+			/* waiting for about 30 seconds before retry */
+			ssleep(30);
+
+			if (megasas_transition_to_ready(instance, 0))
+				goto fail_ready_state;
+		}
+
+		dev_info(&instance->pdev->dev,
+			 "FW restarted successfully from %s!\n",
+			 __func__);
+	}
 	if (megasas_set_dma_mask(instance))
 		goto fail_set_dma_mask;
 
@@ -8036,6 +8075,7 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 	dma_addr_t sense_handle;
 	unsigned long *sense_ptr;
 	u32 opcode = 0;
+	int ret = DCMD_SUCCESS;
 
 	memset(kbuff_arr, 0, sizeof(kbuff_arr));
 
@@ -8176,13 +8216,18 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 	 * cmd to the SCSI mid-layer
 	 */
 	cmd->sync_cmd = 1;
-	if (megasas_issue_blocked_cmd(instance, cmd, 0) == DCMD_NOT_FIRED) {
+
+	ret = megasas_issue_blocked_cmd(instance, cmd, 0);
+	switch (ret) {
+	case DCMD_INIT:
+	case DCMD_BUSY:
 		cmd->sync_cmd = 0;
 		dev_err(&instance->pdev->dev,
 			"return -EBUSY from %s %d cmd 0x%x opcode 0x%x cmd->cmd_status_drv 0x%x\n",
-			__func__, __LINE__, cmd->frame->hdr.cmd, opcode,
-			cmd->cmd_status_drv);
-		return -EBUSY;
+			 __func__, __LINE__, cmd->frame->hdr.cmd, opcode,
+			 cmd->cmd_status_drv);
+			error = -EBUSY;
+			goto out;
 	}
 
 	cmd->sync_cmd = 0;
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index e301458bcbae..f3b36fd0a0eb 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -364,6 +364,35 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 		instance->max_fw_cmds = instance->max_fw_cmds-1;
 	}
 }
+
+static inline void
+megasas_get_msix_index(struct megasas_instance *instance,
+		       struct scsi_cmnd *scmd,
+		       struct megasas_cmd_fusion *cmd,
+		       u8 data_arms)
+{
+	int sdev_busy;
+
+	/* nr_hw_queue = 1 for MegaRAID */
+	struct blk_mq_hw_ctx *hctx =
+		scmd->device->request_queue->queue_hw_ctx[0];
+
+	sdev_busy = atomic_read(&hctx->nr_active);
+
+	if (instance->perf_mode == MR_BALANCED_PERF_MODE &&
+	    sdev_busy > (data_arms * MR_DEVICE_HIGH_IOPS_DEPTH))
+		cmd->request_desc->SCSIIO.MSIxIndex =
+			mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) /
+					MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start);
+	else if (instance->msix_load_balance)
+		cmd->request_desc->SCSIIO.MSIxIndex =
+			(mega_mod64(atomic64_add_return(1, &instance->total_io_count),
+				instance->msix_vectors));
+	else
+		cmd->request_desc->SCSIIO.MSIxIndex =
+			instance->reply_map[raw_smp_processor_id()];
+}
+
 /**
  * megasas_free_cmds_fusion -	Free all the cmds in the free cmd pool
  * @instance:		Adapter soft state
@@ -1312,7 +1341,9 @@ megasas_sync_pd_seq_num(struct megasas_instance *instance, bool pend) {
 	}
 
 	if (ret == DCMD_TIMEOUT)
-		megaraid_sas_kill_hba(instance);
+		dev_warn(&instance->pdev->dev,
+			 "%s DCMD timed out, continue without JBOD sequence map\n",
+			 __func__);
 
 	if (ret == DCMD_SUCCESS)
 		instance->pd_seq_map_id++;
@@ -1394,7 +1425,9 @@ megasas_get_ld_map_info(struct megasas_instance *instance)
 		ret = megasas_issue_polled(instance, cmd);
 
 	if (ret == DCMD_TIMEOUT)
-		megaraid_sas_kill_hba(instance);
+		dev_warn(&instance->pdev->dev,
+			 "%s DCMD timed out, RAID map is disabled\n",
+			 __func__);
 
 	megasas_return_cmd(instance, cmd);
 
@@ -2825,19 +2858,7 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			fp_possible = (io_info.fpOkForIo > 0) ? true : false;
 	}
 
-	if ((instance->perf_mode == MR_BALANCED_PERF_MODE) &&
-		atomic_read(&scp->device->device_busy) >
-		(io_info.data_arms * MR_DEVICE_HIGH_IOPS_DEPTH))
-		cmd->request_desc->SCSIIO.MSIxIndex =
-			mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) /
-				MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start);
-	else if (instance->msix_load_balance)
-		cmd->request_desc->SCSIIO.MSIxIndex =
-			(mega_mod64(atomic64_add_return(1, &instance->total_io_count),
-				    instance->msix_vectors));
-	else
-		cmd->request_desc->SCSIIO.MSIxIndex =
-			instance->reply_map[raw_smp_processor_id()];
+	megasas_get_msix_index(instance, scp, cmd, io_info.data_arms);
 
 	if (instance->adapter_type >= VENTURA_SERIES) {
 		/* FP for Optimal raid level 1.
@@ -3158,18 +3179,7 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 
 	cmd->request_desc->SCSIIO.DevHandle = io_request->DevHandle;
 
-	if ((instance->perf_mode == MR_BALANCED_PERF_MODE) &&
-		atomic_read(&scmd->device->device_busy) > MR_DEVICE_HIGH_IOPS_DEPTH)
-		cmd->request_desc->SCSIIO.MSIxIndex =
-			mega_mod64((atomic64_add_return(1, &instance->high_iops_outstanding) /
-				MR_HIGH_IOPS_BATCH_COUNT), instance->low_latency_index_start);
-	else if (instance->msix_load_balance)
-		cmd->request_desc->SCSIIO.MSIxIndex =
-			(mega_mod64(atomic64_add_return(1, &instance->total_io_count),
-				    instance->msix_vectors));
-	else
-		cmd->request_desc->SCSIIO.MSIxIndex =
-			instance->reply_map[raw_smp_processor_id()];
+	megasas_get_msix_index(instance, scmd, cmd, 1);
 
 	if (!fp_possible) {
 		/* system pd firmware path */
@@ -4219,7 +4229,8 @@ void  megasas_reset_reply_desc(struct megasas_instance *instance)
  * megasas_refire_mgmt_cmd :	Re-fire management commands
  * @instance:				Controller's soft instance
 */
-static void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
+void megasas_refire_mgmt_cmd(struct megasas_instance *instance,
+			     bool return_ioctl)
 {
 	int j;
 	struct megasas_cmd_fusion *cmd_fusion;
@@ -4283,6 +4294,16 @@ static void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 			break;
 		}
 
+		if (return_ioctl && cmd_mfi->sync_cmd &&
+		    cmd_mfi->frame->hdr.cmd != MFI_CMD_ABORT) {
+			dev_err(&instance->pdev->dev,
+				"return -EBUSY from %s %d cmd 0x%x opcode 0x%x\n",
+				__func__, __LINE__, cmd_mfi->frame->hdr.cmd,
+				le32_to_cpu(cmd_mfi->frame->dcmd.opcode));
+			cmd_mfi->cmd_status_drv = DCMD_BUSY;
+			result = COMPLETE_CMD;
+		}
+
 		switch (result) {
 		case REFIRE_CMD:
 			megasas_fire_cmd_fusion(instance, req_desc);
@@ -4298,6 +4319,37 @@ static void megasas_refire_mgmt_cmd(struct megasas_instance *instance)
 }
 
 /*
+ * megasas_return_polled_cmds: Return polled mode commands back to the pool
+ *			       before initiating an OCR.
+ * @instance:                  Controller's soft instance
+ */
+static void
+megasas_return_polled_cmds(struct megasas_instance *instance)
+{
+	int i;
+	struct megasas_cmd_fusion *cmd_fusion;
+	struct fusion_context *fusion;
+	struct megasas_cmd *cmd_mfi;
+
+	fusion = instance->ctrl_context;
+
+	for (i = instance->max_scsi_cmds; i < instance->max_fw_cmds; i++) {
+		cmd_fusion = fusion->cmd_list[i];
+		cmd_mfi = instance->cmd_list[cmd_fusion->sync_cmd_idx];
+
+		if (cmd_mfi->flags & DRV_DCMD_POLLED_MODE) {
+			if (megasas_dbg_lvl & OCR_DEBUG)
+				dev_info(&instance->pdev->dev,
+					 "%s %d return cmd 0x%x opcode 0x%x\n",
+					 __func__, __LINE__, cmd_mfi->frame->hdr.cmd,
+					 le32_to_cpu(cmd_mfi->frame->dcmd.opcode));
+			cmd_mfi->flags &= ~DRV_DCMD_POLLED_MODE;
+			megasas_return_cmd(instance, cmd_mfi);
+		}
+	}
+}
+
+/*
  * megasas_track_scsiio : Track SCSI IOs outstanding to a SCSI device
  * @instance: per adapter struct
  * @channel: the channel assigned by the OS
@@ -4847,6 +4899,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 	if (instance->requestorId && !instance->skip_heartbeat_timer_del)
 		del_timer_sync(&instance->sriov_heartbeat_timer);
 	set_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
+	set_bit(MEGASAS_FUSION_OCR_NOT_POSSIBLE, &instance->reset_flags);
 	atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_POLLING);
 	instance->instancet->disable_intr(instance);
 	megasas_sync_irqs((unsigned long)instance);
@@ -4951,7 +5004,9 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 				goto kill_hba;
 			}
 
-			megasas_refire_mgmt_cmd(instance);
+			megasas_refire_mgmt_cmd(instance,
+						(i == (MEGASAS_FUSION_MAX_RESET_TRIES - 1)
+							? 1 : 0));
 
 			/* Reset load balance info */
 			if (fusion->load_balance_info)
@@ -4959,8 +5014,16 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 				       (sizeof(struct LD_LOAD_BALANCE_INFO) *
 				       MAX_LOGICAL_DRIVES_EXT));
 
-			if (!megasas_get_map_info(instance))
+			if (!megasas_get_map_info(instance)) {
 				megasas_sync_map_info(instance);
+			} else {
+				/*
+				 * Return pending polled mode cmds before
+				 * retrying OCR
+				 */
+				megasas_return_polled_cmds(instance);
+				continue;
+			}
 
 			megasas_setup_jbod_map(instance);
 
@@ -4987,6 +5050,15 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 				megasas_set_dynamic_target_properties(sdev, is_target_prop);
 			}
 
+			status_reg = instance->instancet->read_fw_status_reg
+					(instance);
+			abs_state = status_reg & MFI_STATE_MASK;
+			if (abs_state != MFI_STATE_OPERATIONAL) {
+				dev_info(&instance->pdev->dev,
+					 "Adapter is not OPERATIONAL, state 0x%x for scsi:%d\n",
+					 abs_state, instance->host->host_no);
+				goto out;
+			}
 			atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 
 			dev_info(&instance->pdev->dev,
@@ -5046,7 +5118,7 @@ kill_hba:
 	instance->skip_heartbeat_timer_del = 1;
 	retval = FAILED;
 out:
-	clear_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
+	clear_bit(MEGASAS_FUSION_OCR_NOT_POSSIBLE, &instance->reset_flags);
 	mutex_unlock(&instance->reset_mutex);
 	return retval;
 }
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index c013c80fe4e6..d57ecc7f88d8 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -89,6 +89,7 @@ enum MR_RAID_FLAGS_IO_SUB_TYPE {
 
 #define MEGASAS_FP_CMD_LEN	16
 #define MEGASAS_FUSION_IN_RESET 0
+#define MEGASAS_FUSION_OCR_NOT_POSSIBLE 1
 #define RAID_1_PEER_CMDS 2
 #define JBOD_MAPS_COUNT	2
 #define MEGASAS_REDUCE_QD_COUNT 64
@@ -864,9 +865,20 @@ struct MR_LD_RAID {
 	u8	regTypeReqOnRead;
 	__le16     seqNum;
 
-	struct {
-		u32 ldSyncRequired:1;
-		u32 reserved:31;
+struct {
+#ifndef MFI_BIG_ENDIAN
+	u32 ldSyncRequired:1;
+	u32 regTypeReqOnReadIsValid:1;
+	u32 isEPD:1;
+	u32 enableSLDOnAllRWIOs:1;
+	u32 reserved:28;
+#else
+	u32 reserved:28;
+	u32 enableSLDOnAllRWIOs:1;
+	u32 isEPD:1;
+	u32 regTypeReqOnReadIsValid:1;
+	u32 ldSyncRequired:1;
+#endif
 	} flags;
 
 	u8	LUN[8]; /* 0x24 8 byte LUN field used for SCSI IO's */
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2.h b/drivers/scsi/mpt3sas/mpi/mpi2.h
index 18b1e31b5eb8..ed3923f8db4f 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2.h
@@ -122,6 +122,9 @@
  * 08-28-18  02.00.53  Bumped MPI2_HEADER_VERSION_UNIT.
  *                     Added MPI2_IOCSTATUS_FAILURE
  * 12-17-18  02.00.54  Bumped MPI2_HEADER_VERSION_UNIT
+ * 06-24-19  02.00.55  Bumped MPI2_HEADER_VERSION_UNIT
+ * 08-01-19  02.00.56  Bumped MPI2_HEADER_VERSION_UNIT
+ * 10-02-19  02.00.57  Bumped MPI2_HEADER_VERSION_UNIT
  *  --------------------------------------------------------------------------
  */
 
@@ -162,7 +165,7 @@
 
 
 /* Unit and Dev versioning for this MPI header set */
-#define MPI2_HEADER_VERSION_UNIT            (0x36)
+#define MPI2_HEADER_VERSION_UNIT            (0x39)
 #define MPI2_HEADER_VERSION_DEV             (0x00)
 #define MPI2_HEADER_VERSION_UNIT_MASK       (0xFF00)
 #define MPI2_HEADER_VERSION_UNIT_SHIFT      (8)
@@ -181,6 +184,7 @@
 #define MPI2_IOC_STATE_READY               (0x10000000)
 #define MPI2_IOC_STATE_OPERATIONAL         (0x20000000)
 #define MPI2_IOC_STATE_FAULT               (0x40000000)
+#define MPI2_IOC_STATE_COREDUMP            (0x50000000)
 
 #define MPI2_IOC_STATE_MASK                (0xF0000000)
 #define MPI2_IOC_STATE_SHIFT               (28)
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
index 3a6871aecada..43a3bf8ff428 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_cnfg.h
@@ -249,6 +249,8 @@
  * 08-28-18  02.00.46  Added NVMs Write Cache flag to IOUnitPage1
  *                     Added DMDReport Delay Time defines to PCIeIOUnitPage1
  * 12-17-18  02.00.47  Swap locations of Slotx2 and Slotx4 in ManPage 7.
+ * 08-01-19  02.00.49  Add MPI26_MANPAGE7_FLAG_X2_X4_SLOT_INFO_VALID
+ *                     Add MPI26_IOUNITPAGE1_NVME_WRCACHE_SHIFT
  */
 
 #ifndef MPI2_CNFG_H
@@ -891,6 +893,8 @@ typedef struct _MPI2_CONFIG_PAGE_MAN_7 {
 #define MPI2_MANPAGE7_FLAG_EVENTREPLAY_SLOT_ORDER       (0x00000002)
 #define MPI2_MANPAGE7_FLAG_USE_SLOT_INFO                (0x00000001)
 
+#define MPI26_MANPAGE7_FLAG_CONN_LANE_USE_PINOUT        (0x00000020)
+#define MPI26_MANPAGE7_FLAG_X2_X4_SLOT_INFO_VALID       (0x00000010)
 
 /*
  *Generic structure to use for product-specific manufacturing pages
@@ -962,9 +966,10 @@ typedef struct _MPI2_CONFIG_PAGE_IO_UNIT_1 {
 
 /* IO Unit Page 1 Flags defines */
 #define MPI26_IOUNITPAGE1_NVME_WRCACHE_MASK             (0x00030000)
-#define MPI26_IOUNITPAGE1_NVME_WRCACHE_ENABLE           (0x00000000)
-#define MPI26_IOUNITPAGE1_NVME_WRCACHE_DISABLE          (0x00010000)
-#define MPI26_IOUNITPAGE1_NVME_WRCACHE_NO_CHANGE        (0x00020000)
+#define MPI26_IOUNITPAGE1_NVME_WRCACHE_SHIFT            (16)
+#define MPI26_IOUNITPAGE1_NVME_WRCACHE_NO_CHANGE        (0x00000000)
+#define MPI26_IOUNITPAGE1_NVME_WRCACHE_ENABLE           (0x00010000)
+#define MPI26_IOUNITPAGE1_NVME_WRCACHE_DISABLE          (0x00020000)
 #define MPI2_IOUNITPAGE1_ATA_SECURITY_FREEZE_LOCK       (0x00004000)
 #define MPI25_IOUNITPAGE1_NEW_DEVICE_FAST_PATH_DISABLE  (0x00002000)
 #define MPI25_IOUNITPAGE1_DISABLE_FAST_PATH             (0x00001000)
@@ -3931,7 +3936,13 @@ typedef struct _MPI26_CONFIG_PAGE_PCIEDEV_2 {
 	U32	MaximumDataTransferSize;	/*0x0C */
 	U32	Capabilities;		/*0x10 */
 	U16	NOIOB;		/* 0x14 */
-	U16	Reserved2;		/* 0x16 */
+	U16     ShutdownLatency;        /* 0x16 */
+	U16     VendorID;               /* 0x18 */
+	U16     DeviceID;               /* 0x1A */
+	U16     SubsystemVendorID;      /* 0x1C */
+	U16     SubsystemID;            /* 0x1E */
+	U8      RevisionID;             /* 0x20 */
+	U8      Reserved21[3];          /* 0x21 */
 } MPI26_CONFIG_PAGE_PCIEDEV_2, *PTR_MPI26_CONFIG_PAGE_PCIEDEV_2,
 	Mpi26PCIeDevicePage2_t, *pMpi26PCIeDevicePage2_t;
 
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_image.h b/drivers/scsi/mpt3sas/mpi/mpi2_image.h
index a3f677853098..33b9c3a6fd40 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_image.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_image.h
@@ -19,6 +19,10 @@
  * 09-07-18  02.06.03  Added MPI26_EVENT_PCIE_TOPO_PI_16_LANES
  * 12-17-18  02.06.04  Addd MPI2_EXT_IMAGE_TYPE_PBLP
  *			Shorten some defines to be compatible with DOS
+ * 06-24-19  02.06.05  Whitespace adjustments to help with identifier
+ *			checking tool.
+ * 10-02-19  02.06.06  Added MPI26_IMAGE_HEADER_SIG1_COREDUMP
+ *                     Added MPI2_FLASH_REGION_COREDUMP
  */
 #ifndef MPI2_IMAGE_H
 #define MPI2_IMAGE_H
@@ -213,6 +217,8 @@ typedef struct _MPI26_COMPONENT_IMAGE_HEADER {
 #define MPI26_IMAGE_HEADER_SIG1_NVDATA                   (0x5444564E)
 #define MPI26_IMAGE_HEADER_SIG1_GAS_GAUGE                (0x20534147)
 #define MPI26_IMAGE_HEADER_SIG1_PBLP                     (0x504C4250)
+/* little-endian "DUMP" */
+#define MPI26_IMAGE_HEADER_SIG1_COREDUMP                 (0x504D5544)
 
 /**** Definitions for Signature2 field ****/
 #define MPI26_IMAGE_HEADER_SIGNATURE2_VALUE                    (0x50584546)
@@ -359,6 +365,7 @@ typedef struct _MPI2_FLASH_LAYOUT_DATA {
 #define MPI2_FLASH_REGION_MR_NVDATA             (0x14)
 #define MPI2_FLASH_REGION_CPLD                  (0x15)
 #define MPI2_FLASH_REGION_PSOC                  (0x16)
+#define MPI2_FLASH_REGION_COREDUMP              (0x17)
 
 /*ImageRevision */
 #define MPI2_FLASH_LAYOUT_IMAGE_REVISION        (0x00)
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
index 68ea408cd5c5..e83c7c529dc9 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
@@ -175,6 +175,10 @@
  *                     Moved FW image definitions ionto new mpi2_image,h
  * 08-14-18   02.00.36 Fixed definition of MPI2_FW_DOWNLOAD_ITYPE_PSOC (0x16)
  * 09-07-18   02.00.37 Added MPI26_EVENT_PCIE_TOPO_PI_16_LANES
+ * 10-02-19   02.00.38 Added MPI26_IOCINIT_CFGFLAGS_COREDUMP_ENABLE
+ *                     Added MPI26_IOCFACTS_CAPABILITY_COREDUMP_ENABLED
+ *                     Added MPI2_FW_DOWNLOAD_ITYPE_COREDUMP
+ *                     Added MPI2_FW_UPLOAD_ITYPE_COREDUMP
  * --------------------------------------------------------------------------
  */
 
@@ -248,6 +252,7 @@ typedef struct _MPI2_IOC_INIT_REQUEST {
 
 /*ConfigurationFlags */
 #define MPI26_IOCINIT_CFGFLAGS_NVME_SGL_FORMAT  (0x0001)
+#define MPI26_IOCINIT_CFGFLAGS_COREDUMP_ENABLE  (0x0002)
 
 /*minimum depth for a Reply Descriptor Post Queue */
 #define MPI2_RDPQ_DEPTH_MIN                     (16)
@@ -377,6 +382,7 @@ typedef struct _MPI2_IOC_FACTS_REPLY {
 /*ProductID field uses MPI2_FW_HEADER_PID_ */
 
 /*IOCCapabilities */
+#define MPI26_IOCFACTS_CAPABILITY_COREDUMP_ENABLED      (0x00200000)
 #define MPI26_IOCFACTS_CAPABILITY_PCIE_SRIOV            (0x00100000)
 #define MPI26_IOCFACTS_CAPABILITY_ATOMIC_REQ            (0x00080000)
 #define MPI2_IOCFACTS_CAPABILITY_RDPQ_ARRAY_CAPABLE     (0x00040000)
@@ -1458,8 +1464,8 @@ typedef struct _MPI2_FW_DOWNLOAD_REQUEST {
 /*MPI v2.6 and newer */
 #define MPI2_FW_DOWNLOAD_ITYPE_CPLD                 (0x15)
 #define MPI2_FW_DOWNLOAD_ITYPE_PSOC                 (0x16)
+#define MPI2_FW_DOWNLOAD_ITYPE_COREDUMP             (0x17)
 #define MPI2_FW_DOWNLOAD_ITYPE_MIN_PRODUCT_SPECIFIC (0xF0)
-#define MPI2_FW_DOWNLOAD_ITYPE_TERMINATE            (0xFF)
 
 /*MPI v2.0 FWDownload TransactionContext Element */
 typedef struct _MPI2_FW_DOWNLOAD_TCSGE {
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 45fd8dfb7c40..663782bb790d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -124,7 +124,14 @@ enum mpt3sas_perf_mode {
 };
 
 static int
+_base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc,
+		u32 ioc_state, int timeout);
+static int
 _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
+static void
+_base_mask_interrupts(struct MPT3SAS_ADAPTER *ioc);
+static void
+_base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc);
 
 /**
  * mpt3sas_base_check_cmd_timeout - Function
@@ -609,7 +616,8 @@ _base_fault_reset_work(struct work_struct *work)
 
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
-	if (ioc->shost_recovery || ioc->pci_error_recovery)
+	if ((ioc->shost_recovery && (ioc->ioc_coredump_loop == 0)) ||
+			ioc->pci_error_recovery)
 		goto rearm_timer;
 	spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);
 
@@ -656,20 +664,64 @@ _base_fault_reset_work(struct work_struct *work)
 		return; /* don't rearm timer */
 	}
 
-	ioc->non_operational_loop = 0;
+	if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_COREDUMP) {
+		u8 timeout = (ioc->manu_pg11.CoreDumpTOSec) ?
+		    ioc->manu_pg11.CoreDumpTOSec :
+		    MPT3SAS_DEFAULT_COREDUMP_TIMEOUT_SECONDS;
+
+		timeout /= (FAULT_POLLING_INTERVAL/1000);
+
+		if (ioc->ioc_coredump_loop == 0) {
+			mpt3sas_print_coredump_info(ioc,
+			    doorbell & MPI2_DOORBELL_DATA_MASK);
+			/* do not accept any IOs and disable the interrupts */
+			spin_lock_irqsave(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			ioc->shost_recovery = 1;
+			spin_unlock_irqrestore(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			_base_mask_interrupts(ioc);
+			_base_clear_outstanding_commands(ioc);
+		}
+
+		ioc_info(ioc, "%s: CoreDump loop %d.",
+		    __func__, ioc->ioc_coredump_loop);
 
+		/* Wait until CoreDump completes or times out */
+		if (ioc->ioc_coredump_loop++ < timeout) {
+			spin_lock_irqsave(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			goto rearm_timer;
+		}
+	}
+
+	if (ioc->ioc_coredump_loop) {
+		if ((doorbell & MPI2_IOC_STATE_MASK) != MPI2_IOC_STATE_COREDUMP)
+			ioc_err(ioc, "%s: CoreDump completed. LoopCount: %d",
+			    __func__, ioc->ioc_coredump_loop);
+		else
+			ioc_err(ioc, "%s: CoreDump Timed out. LoopCount: %d",
+			    __func__, ioc->ioc_coredump_loop);
+		ioc->ioc_coredump_loop = MPT3SAS_COREDUMP_LOOP_DONE;
+	}
+	ioc->non_operational_loop = 0;
 	if ((doorbell & MPI2_IOC_STATE_MASK) != MPI2_IOC_STATE_OPERATIONAL) {
 		rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 		ioc_warn(ioc, "%s: hard reset: %s\n",
 			 __func__, rc == 0 ? "success" : "failed");
 		doorbell = mpt3sas_base_get_iocstate(ioc, 0);
-		if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
-			mpt3sas_base_fault_info(ioc, doorbell &
+		if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
+			mpt3sas_print_fault_code(ioc, doorbell &
+			    MPI2_DOORBELL_DATA_MASK);
+		} else if ((doorbell & MPI2_IOC_STATE_MASK) ==
+		    MPI2_IOC_STATE_COREDUMP)
+			mpt3sas_print_coredump_info(ioc, doorbell &
 			    MPI2_DOORBELL_DATA_MASK);
 		if (rc && (doorbell & MPI2_IOC_STATE_MASK) !=
 		    MPI2_IOC_STATE_OPERATIONAL)
 			return; /* don't rearm timer */
 	}
+	ioc->ioc_coredump_loop = 0;
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
  rearm_timer:
@@ -749,6 +801,49 @@ mpt3sas_base_fault_info(struct MPT3SAS_ADAPTER *ioc , u16 fault_code)
 }
 
 /**
+ * mpt3sas_base_coredump_info - verbose translation of firmware CoreDump state
+ * @ioc: per adapter object
+ * @fault_code: fault code
+ *
+ * Return nothing.
+ */
+void
+mpt3sas_base_coredump_info(struct MPT3SAS_ADAPTER *ioc, u16 fault_code)
+{
+	ioc_err(ioc, "coredump_state(0x%04x)!\n", fault_code);
+}
+
+/**
+ * mpt3sas_base_wait_for_coredump_completion - Wait until coredump
+ * completes or times out
+ * @ioc: per adapter object
+ *
+ * Returns 0 for success, non-zero for failure.
+ */
+int
+mpt3sas_base_wait_for_coredump_completion(struct MPT3SAS_ADAPTER *ioc,
+		const char *caller)
+{
+	u8 timeout = (ioc->manu_pg11.CoreDumpTOSec) ?
+			ioc->manu_pg11.CoreDumpTOSec :
+			MPT3SAS_DEFAULT_COREDUMP_TIMEOUT_SECONDS;
+
+	int ioc_state = _base_wait_on_iocstate(ioc, MPI2_IOC_STATE_FAULT,
+					timeout);
+
+	if (ioc_state)
+		ioc_err(ioc,
+		    "%s: CoreDump timed out. (ioc_state=0x%x)\n",
+		    caller, ioc_state);
+	else
+		ioc_info(ioc,
+		    "%s: CoreDump completed. (ioc_state=0x%x)\n",
+		    caller, ioc_state);
+
+	return ioc_state;
+}
+
+/**
  * mpt3sas_halt_firmware - halt's mpt controller firmware
  * @ioc: per adapter object
  *
@@ -768,9 +863,14 @@ mpt3sas_halt_firmware(struct MPT3SAS_ADAPTER *ioc)
 	dump_stack();
 
 	doorbell = ioc->base_readl(&ioc->chip->Doorbell);
-	if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
-		mpt3sas_base_fault_info(ioc , doorbell);
-	else {
+	if ((doorbell & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
+		mpt3sas_print_fault_code(ioc, doorbell &
+		    MPI2_DOORBELL_DATA_MASK);
+	} else if ((doorbell & MPI2_IOC_STATE_MASK) ==
+	    MPI2_IOC_STATE_COREDUMP) {
+		mpt3sas_print_coredump_info(ioc, doorbell &
+		    MPI2_DOORBELL_DATA_MASK);
+	} else {
 		writel(0xC0FFEE00, &ioc->chip->Doorbell);
 		ioc_err(ioc, "Firmware is halted due to command timeout\n");
 	}
@@ -3103,6 +3203,8 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 	 */
 	if (!ioc->combined_reply_queue &&
 	    ioc->hba_mpi_version_belonged != MPI2_VERSION) {
+		ioc_info(ioc,
+		    "combined ReplyQueue is off, Enabling msix load balance\n");
 		ioc->msix_load_balance = true;
 	}
 
@@ -3115,9 +3217,7 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
 
 	r = _base_alloc_irq_vectors(ioc);
 	if (r < 0) {
-		dfailprintk(ioc,
-			    ioc_info(ioc, "pci_alloc_irq_vectors failed (r=%d) !!!\n",
-				     r));
+		ioc_info(ioc, "pci_alloc_irq_vectors failed (r=%d) !!!\n", r);
 		goto try_ioapic;
 	}
 
@@ -3206,9 +3306,15 @@ _base_check_for_fault_and_issue_reset(struct MPT3SAS_ADAPTER *ioc)
 	dhsprintk(ioc, pr_info("%s: ioc_state(0x%08x)\n", __func__, ioc_state));
 
 	if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
-		mpt3sas_base_fault_info(ioc, ioc_state &
+		mpt3sas_print_fault_code(ioc, ioc_state &
 		    MPI2_DOORBELL_DATA_MASK);
 		rc = _base_diag_reset(ioc);
+	} else if ((ioc_state & MPI2_IOC_STATE_MASK) ==
+	    MPI2_IOC_STATE_COREDUMP) {
+		mpt3sas_print_coredump_info(ioc, ioc_state &
+		     MPI2_DOORBELL_DATA_MASK);
+		mpt3sas_base_wait_for_coredump_completion(ioc, __func__);
+		rc = _base_diag_reset(ioc);
 	}
 
 	return rc;
@@ -3279,7 +3385,8 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 	}
 
 	if (ioc->chip == NULL) {
-		ioc_err(ioc, "unable to map adapter memory! or resource not found\n");
+		ioc_err(ioc,
+		    "unable to map adapter memory! or resource not found\n");
 		r = -EINVAL;
 		goto out_fail;
 	}
@@ -3318,8 +3425,8 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 		     ioc->combined_reply_index_count,
 		     sizeof(resource_size_t *), GFP_KERNEL);
 		if (!ioc->replyPostRegisterIndex) {
-			dfailprintk(ioc,
-				    ioc_warn(ioc, "allocation for reply Post Register Index failed!!!\n"));
+			ioc_err(ioc,
+			    "allocation for replyPostRegisterIndex failed!\n");
 			r = -ENOMEM;
 			goto out_fail;
 		}
@@ -3467,6 +3574,22 @@ _base_get_msix_index(struct MPT3SAS_ADAPTER *ioc,
 }
 
 /**
+ * _base_sdev_nr_inflight_request -get number of inflight requests
+ *				   of a request queue.
+ * @q: request_queue object
+ *
+ * returns number of inflight request of a request queue.
+ */
+inline unsigned long
+_base_sdev_nr_inflight_request(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx = q->queue_hw_ctx[0];
+
+	return atomic_read(&hctx->nr_active);
+}
+
+
+/**
  * _base_get_high_iops_msix_index - get the msix index of
  *				high iops queues
  * @ioc: per adapter object
@@ -3485,7 +3608,7 @@ _base_get_high_iops_msix_index(struct MPT3SAS_ADAPTER *ioc,
 	 * reply queues in terms of batch count 16 when outstanding
 	 * IOs on the target device is >=8.
 	 */
-	if (atomic_read(&scmd->device->device_busy) >
+	if (_base_sdev_nr_inflight_request(scmd->device->request_queue) >
 	    MPT3SAS_DEVICE_HIGH_IOPS_DEPTH)
 		return base_mod64((
 		    atomic64_add_return(1, &ioc->high_iops_outstanding) /
@@ -4264,7 +4387,8 @@ _base_display_fwpkg_version(struct MPT3SAS_ADAPTER *ioc)
 	fwpkg_data = dma_alloc_coherent(&ioc->pdev->dev, data_length,
 			&fwpkg_data_dma, GFP_KERNEL);
 	if (!fwpkg_data) {
-		ioc_err(ioc, "failure at %s:%d/%s()!\n",
+		ioc_err(ioc,
+		    "Memory allocation for fwpkg data failed at %s:%d/%s()!\n",
 			__FILE__, __LINE__, __func__);
 		return -ENOMEM;
 	}
@@ -4994,12 +5118,13 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 		ioc->reply_free_queue_depth = ioc->hba_queue_depth + 64;
 	}
 
-	dinitprintk(ioc,
-		    ioc_info(ioc, "scatter gather: sge_in_main_msg(%d), sge_per_chain(%d), sge_per_io(%d), chains_per_io(%d)\n",
-			     ioc->max_sges_in_main_message,
-			     ioc->max_sges_in_chain_message,
-			     ioc->shost->sg_tablesize,
-			     ioc->chains_needed_per_io));
+	ioc_info(ioc,
+	    "scatter gather: sge_in_main_msg(%d), sge_per_chain(%d), "
+	    "sge_per_io(%d), chains_per_io(%d)\n",
+	    ioc->max_sges_in_main_message,
+	    ioc->max_sges_in_chain_message,
+	    ioc->shost->sg_tablesize,
+	    ioc->chains_needed_per_io);
 
 	/* reply post queue, 16 byte align */
 	reply_post_free_sz = ioc->reply_post_queue_depth *
@@ -5109,15 +5234,13 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 	ioc->internal_dma = ioc->hi_priority_dma + (ioc->hi_priority_depth *
 	    ioc->request_sz);
 
-	dinitprintk(ioc,
-		    ioc_info(ioc, "request pool(0x%p): depth(%d), frame_size(%d), pool_size(%d kB)\n",
-			     ioc->request, ioc->hba_queue_depth,
-			     ioc->request_sz,
-			     (ioc->hba_queue_depth * ioc->request_sz) / 1024));
+	ioc_info(ioc,
+	    "request pool(0x%p) - dma(0x%llx): "
+	    "depth(%d), frame_size(%d), pool_size(%d kB)\n",
+	    ioc->request, (unsigned long long) ioc->request_dma,
+	    ioc->hba_queue_depth, ioc->request_sz,
+	    (ioc->hba_queue_depth * ioc->request_sz) / 1024);
 
-	dinitprintk(ioc,
-		    ioc_info(ioc, "request pool: dma(0x%llx)\n",
-			     (unsigned long long)ioc->request_dma));
 	total_sz += sz;
 
 	dinitprintk(ioc,
@@ -5302,13 +5425,12 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 			goto out;
 		}
 	}
-	dinitprintk(ioc,
-		    ioc_info(ioc, "sense pool(0x%p): depth(%d), element_size(%d), pool_size(%d kB)\n",
-			     ioc->sense, ioc->scsiio_depth,
-			     SCSI_SENSE_BUFFERSIZE, sz / 1024));
-	dinitprintk(ioc,
-		    ioc_info(ioc, "sense_dma(0x%llx)\n",
-			     (unsigned long long)ioc->sense_dma));
+	ioc_info(ioc,
+	    "sense pool(0x%p)- dma(0x%llx): depth(%d),"
+	    "element_size(%d), pool_size(%d kB)\n",
+	    ioc->sense, (unsigned long long)ioc->sense_dma, ioc->scsiio_depth,
+	    SCSI_SENSE_BUFFERSIZE, sz / 1024);
+
 	total_sz += sz;
 
 	/* reply pool, 4 byte align */
@@ -5386,12 +5508,10 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
 		ioc_err(ioc, "config page: dma_pool_alloc failed\n");
 		goto out;
 	}
-	dinitprintk(ioc,
-		    ioc_info(ioc, "config page(0x%p): size(%d)\n",
-			     ioc->config_page, ioc->config_page_sz));
-	dinitprintk(ioc,
-		    ioc_info(ioc, "config_page_dma(0x%llx)\n",
-			     (unsigned long long)ioc->config_page_dma));
+
+	ioc_info(ioc, "config page(0x%p) - dma(0x%llx): size(%d)\n",
+	    ioc->config_page, (unsigned long long)ioc->config_page_dma,
+	    ioc->config_page_sz);
 	total_sz += ioc->config_page_sz;
 
 	ioc_info(ioc, "Allocated physical memory: size(%d kB)\n",
@@ -5446,6 +5566,8 @@ _base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc, u32 ioc_state, int timeout)
 			return 0;
 		if (count && current_state == MPI2_IOC_STATE_FAULT)
 			break;
+		if (count && current_state == MPI2_IOC_STATE_COREDUMP)
+			break;
 
 		usleep_range(1000, 1500);
 		count++;
@@ -5547,7 +5669,12 @@ _base_wait_for_doorbell_ack(struct MPT3SAS_ADAPTER *ioc, int timeout)
 			doorbell = ioc->base_readl(&ioc->chip->Doorbell);
 			if ((doorbell & MPI2_IOC_STATE_MASK) ==
 			    MPI2_IOC_STATE_FAULT) {
-				mpt3sas_base_fault_info(ioc , doorbell);
+				mpt3sas_print_fault_code(ioc, doorbell);
+				return -EFAULT;
+			}
+			if ((doorbell & MPI2_IOC_STATE_MASK) ==
+			    MPI2_IOC_STATE_COREDUMP) {
+				mpt3sas_print_coredump_info(ioc, doorbell);
 				return -EFAULT;
 			}
 		} else if (int_status == 0xFFFFFFFF)
@@ -5609,6 +5736,7 @@ _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
 {
 	u32 ioc_state;
 	int r = 0;
+	unsigned long flags;
 
 	if (reset_type != MPI2_FUNCTION_IOC_MESSAGE_UNIT_RESET) {
 		ioc_err(ioc, "%s: unknown reset_type\n", __func__);
@@ -5627,6 +5755,7 @@ _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
 		r = -EFAULT;
 		goto out;
 	}
+
 	ioc_state = _base_wait_on_iocstate(ioc, MPI2_IOC_STATE_READY, timeout);
 	if (ioc_state) {
 		ioc_err(ioc, "%s: failed going to ready state (ioc_state=0x%x)\n",
@@ -5635,6 +5764,26 @@ _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
 		goto out;
 	}
  out:
+	if (r != 0) {
+		ioc_state = mpt3sas_base_get_iocstate(ioc, 0);
+		spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
+		/*
+		 * Wait for IOC state CoreDump to clear only during
+		 * HBA initialization & release time.
+		 */
+		if ((ioc_state & MPI2_IOC_STATE_MASK) ==
+		    MPI2_IOC_STATE_COREDUMP && (ioc->is_driver_loading == 1 ||
+		    ioc->fault_reset_work_q == NULL)) {
+			spin_unlock_irqrestore(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+			mpt3sas_print_coredump_info(ioc, ioc_state);
+			mpt3sas_base_wait_for_coredump_completion(ioc,
+			    __func__);
+			spin_lock_irqsave(
+			    &ioc->ioc_reset_in_progress_lock, flags);
+		}
+		spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);
+	}
 	ioc_info(ioc, "message unit reset: %s\n",
 		 r == 0 ? "SUCCESS" : "FAILED");
 	return r;
@@ -5782,7 +5931,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 		mfp = (__le32 *)reply;
 		pr_info("\toffset:data\n");
 		for (i = 0; i < reply_bytes/4; i++)
-			pr_info("\t[0x%02x]:%08x\n", i*4,
+			ioc_info(ioc, "\t[0x%02x]:%08x\n", i*4,
 			    le32_to_cpu(mfp[i]));
 	}
 	return 0;
@@ -5850,10 +5999,9 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 	    ioc->ioc_link_reset_in_progress)
 		ioc->ioc_link_reset_in_progress = 0;
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
-		issue_reset =
-			mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->base_cmds.status, mpi_request,
-				sizeof(Mpi2SasIoUnitControlRequest_t)/4);
+		mpt3sas_check_cmd_timeout(ioc, ioc->base_cmds.status,
+		    mpi_request, sizeof(Mpi2SasIoUnitControlRequest_t)/4,
+		    issue_reset);
 		goto issue_host_reset;
 	}
 	if (ioc->base_cmds.status & MPT3_CMD_REPLY_VALID)
@@ -5926,10 +6074,9 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 	wait_for_completion_timeout(&ioc->base_cmds.done,
 	    msecs_to_jiffies(10000));
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
-		issue_reset =
-			mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->base_cmds.status, mpi_request,
-				sizeof(Mpi2SepRequest_t)/4);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->base_cmds.status, mpi_request,
+		    sizeof(Mpi2SepRequest_t)/4, issue_reset);
 		goto issue_host_reset;
 	}
 	if (ioc->base_cmds.status & MPT3_CMD_REPLY_VALID)
@@ -6028,9 +6175,15 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
 	}
 
 	if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
-		mpt3sas_base_fault_info(ioc, ioc_state &
+		mpt3sas_print_fault_code(ioc, ioc_state &
 		    MPI2_DOORBELL_DATA_MASK);
 		goto issue_diag_reset;
+	} else if ((ioc_state & MPI2_IOC_STATE_MASK) ==
+	    MPI2_IOC_STATE_COREDUMP) {
+		ioc_info(ioc,
+		    "%s: Skipping the diag reset here. (ioc_state=0x%x)\n",
+		    __func__, ioc_state);
+		return -EFAULT;
 	}
 
 	ioc_state = _base_wait_on_iocstate(ioc, MPI2_IOC_STATE_READY, timeout);
@@ -6209,6 +6362,12 @@ _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc)
 		    cpu_to_le64((u64)ioc->reply_post[0].reply_post_free_dma);
 	}
 
+	/*
+	 * Set the flag to enable CoreDump state feature in IOC firmware.
+	 */
+	mpi_request.ConfigurationFlags |=
+	    cpu_to_le16(MPI26_IOCINIT_CFGFLAGS_COREDUMP_ENABLE);
+
 	/* This time stamp specifies number of milliseconds
 	 * since epoch ~ midnight January 1, 1970.
 	 */
@@ -6220,9 +6379,9 @@ _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc)
 		int i;
 
 		mfp = (__le32 *)&mpi_request;
-		pr_info("\toffset:data\n");
+		ioc_info(ioc, "\toffset:data\n");
 		for (i = 0; i < sizeof(Mpi2IOCInitRequest_t)/4; i++)
-			pr_info("\t[0x%02x]:%08x\n", i*4,
+			ioc_info(ioc, "\t[0x%02x]:%08x\n", i*4,
 			    le32_to_cpu(mfp[i]));
 	}
 
@@ -6592,8 +6751,11 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
 		/* wait 100 msec */
 		msleep(100);
 
-		if (count++ > 20)
+		if (count++ > 20) {
+			ioc_info(ioc,
+			    "Stop writing magic sequence after 20 retries\n");
 			goto out;
+		}
 
 		host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic);
 		drsprintk(ioc,
@@ -6617,8 +6779,11 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
 
 		host_diagnostic = ioc->base_readl(&ioc->chip->HostDiagnostic);
 
-		if (host_diagnostic == 0xFFFFFFFF)
+		if (host_diagnostic == 0xFFFFFFFF) {
+			ioc_info(ioc,
+			    "Invalid host diagnostic register value\n");
 			goto out;
+		}
 		if (!(host_diagnostic & MPI2_DIAG_RESET_ADAPTER))
 			break;
 
@@ -6705,16 +6870,33 @@ _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
 		return 0;
 
 	if (ioc_state & MPI2_DOORBELL_USED) {
-		dhsprintk(ioc, ioc_info(ioc, "unexpected doorbell active!\n"));
+		ioc_info(ioc, "unexpected doorbell active!\n");
 		goto issue_diag_reset;
 	}
 
 	if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
-		mpt3sas_base_fault_info(ioc, ioc_state &
+		mpt3sas_print_fault_code(ioc, ioc_state &
 		    MPI2_DOORBELL_DATA_MASK);
 		goto issue_diag_reset;
 	}
 
+	if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_COREDUMP) {
+		/*
+		 * if host reset is invoked while watch dog thread is waiting
+		 * for IOC state to be changed to Fault state then driver has
+		 * to wait here for CoreDump state to clear otherwise reset
+		 * will be issued to the FW and FW move the IOC state to
+		 * reset state without copying the FW logs to coredump region.
+		 */
+		if (ioc->ioc_coredump_loop != MPT3SAS_COREDUMP_LOOP_DONE) {
+			mpt3sas_print_coredump_info(ioc, ioc_state &
+			    MPI2_DOORBELL_DATA_MASK);
+			mpt3sas_base_wait_for_coredump_completion(ioc,
+			    __func__);
+		}
+		goto issue_diag_reset;
+	}
+
 	if (type == FORCE_BIG_HAMMER)
 		goto issue_diag_reset;
 
@@ -6958,8 +7140,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 	ioc->cpu_msix_table = kzalloc(ioc->cpu_msix_table_sz, GFP_KERNEL);
 	ioc->reply_queue_count = 1;
 	if (!ioc->cpu_msix_table) {
-		dfailprintk(ioc,
-			    ioc_info(ioc, "allocation for cpu_msix_table failed!!!\n"));
+		ioc_info(ioc, "Allocation for cpu_msix_table failed!!!\n");
 		r = -ENOMEM;
 		goto out_free_resources;
 	}
@@ -6968,8 +7149,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		ioc->reply_post_host_index = kcalloc(ioc->cpu_msix_table_sz,
 		    sizeof(resource_size_t *), GFP_KERNEL);
 		if (!ioc->reply_post_host_index) {
-			dfailprintk(ioc,
-				    ioc_info(ioc, "allocation for reply_post_host_index failed!!!\n"));
+			ioc_info(ioc, "Allocation for reply_post_host_index failed!!!\n");
 			r = -ENOMEM;
 			goto out_free_resources;
 		}
@@ -7195,6 +7375,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 	    sizeof(struct mpt3sas_facts));
 
 	ioc->non_operational_loop = 0;
+	ioc->ioc_coredump_loop = 0;
 	ioc->got_task_abort_from_ioctl = 0;
 	return 0;
 
@@ -7276,14 +7457,14 @@ static void _base_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 }
 
 /**
- * _base_after_reset_handler - after reset handler
+ * _base_clear_outstanding_mpt_commands - clears outstanding mpt commands
  * @ioc: per adapter object
  */
-static void _base_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+static void
+_base_clear_outstanding_mpt_commands(struct MPT3SAS_ADAPTER *ioc)
 {
-	mpt3sas_scsih_after_reset_handler(ioc);
-	mpt3sas_ctl_after_reset_handler(ioc);
-	dtmprintk(ioc, ioc_info(ioc, "%s: MPT3_IOC_AFTER_RESET\n", __func__));
+	dtmprintk(ioc,
+	    ioc_info(ioc, "%s: clear outstanding mpt cmds\n", __func__));
 	if (ioc->transport_cmds.status & MPT3_CMD_PENDING) {
 		ioc->transport_cmds.status |= MPT3_CMD_RESET;
 		mpt3sas_base_free_smid(ioc, ioc->transport_cmds.smid);
@@ -7317,6 +7498,17 @@ static void _base_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 }
 
 /**
+ * _base_clear_outstanding_commands - clear all outstanding commands
+ * @ioc: per adapter object
+ */
+static void _base_clear_outstanding_commands(struct MPT3SAS_ADAPTER *ioc)
+{
+	mpt3sas_scsih_clear_outstanding_scsi_tm_commands(ioc);
+	mpt3sas_ctl_clear_outstanding_ioctls(ioc);
+	_base_clear_outstanding_mpt_commands(ioc);
+}
+
+/**
  * _base_reset_done_handler - reset done handler
  * @ioc: per adapter object
  */
@@ -7474,7 +7666,9 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 	    MPT3_DIAG_BUFFER_IS_RELEASED))) {
 		is_trigger = 1;
 		ioc_state = mpt3sas_base_get_iocstate(ioc, 0);
-		if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
+		if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT ||
+		    (ioc_state & MPI2_IOC_STATE_MASK) ==
+		    MPI2_IOC_STATE_COREDUMP)
 			is_fault = 1;
 	}
 	_base_pre_reset_handler(ioc);
@@ -7483,7 +7677,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 	r = _base_make_ioc_ready(ioc, type);
 	if (r)
 		goto out;
-	_base_after_reset_handler(ioc);
+	_base_clear_outstanding_commands(ioc);
 
 	/* If this hard reset is called while port enable is active, then
 	 * there is no reason to call make_ioc_operational
@@ -7514,9 +7708,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 		_base_reset_done_handler(ioc);
 
  out:
-	dtmprintk(ioc,
-		  ioc_info(ioc, "%s: %s\n",
-			   __func__, r == 0 ? "SUCCESS" : "FAILED"));
+	ioc_info(ioc, "%s: %s\n", __func__, r == 0 ? "SUCCESS" : "FAILED");
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
 	ioc->shost_recovery = 0;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 4ebf81ea4d2f..e7197150721f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -76,8 +76,8 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"32.100.00.00"
-#define MPT3SAS_MAJOR_VERSION		32
+#define MPT3SAS_DRIVER_VERSION		"33.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		33
 #define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
@@ -90,6 +90,10 @@
 #define MPT2SAS_BUILD_VERSION		0
 #define MPT2SAS_RELEASE_VERSION	00
 
+/* CoreDump: Default timeout */
+#define MPT3SAS_DEFAULT_COREDUMP_TIMEOUT_SECONDS	(15) /*15 seconds*/
+#define MPT3SAS_COREDUMP_LOOP_DONE                     (0xFF)
+
 /*
  * Set MPT3SAS_SG_DEPTH value based on user input.
  */
@@ -140,6 +144,7 @@
 #define MAX_CHAIN_ELEMT_SZ		16
 #define DEFAULT_NUM_FWCHAIN_ELEMTS	8
 
+#define IO_UNIT_CONTROL_SHUTDOWN_TIMEOUT 6
 #define FW_IMG_HDR_READ_TIMEOUT	15
 
 #define IOC_OPERATIONAL_WAIT_COUNT	10
@@ -398,7 +403,10 @@ struct Mpi2ManufacturingPage11_t {
 	u8	HostTraceBufferFlags;		/* 4Fh */
 	u16	HostTraceBufferMaxSizeKB;	/* 50h */
 	u16	HostTraceBufferMinSizeKB;	/* 52h */
-	__le32	Reserved10[2];			/* 54h - 5Bh */
+	u8	CoreDumpTOSec;			/* 54h */
+	u8	Reserved8;			/* 55h */
+	u16	Reserved9;			/* 56h */
+	__le32	Reserved10;			/* 58h */
 };
 
 /**
@@ -589,6 +597,7 @@ static inline void sas_device_put(struct _sas_device *s)
  * @connector_name: ASCII value of the Connector's name
  * @serial_number: pointer of serial number string allocated runtime
  * @access_status: Device's Access Status
+ * @shutdown_latency: NVMe device's RTD3 Entry Latency
  * @refcount: reference count for deletion
  */
 struct _pcie_device {
@@ -611,6 +620,7 @@ struct _pcie_device {
 	u8	*serial_number;
 	u8	reset_timeout;
 	u8	access_status;
+	u16	shutdown_latency;
 	struct kref refcount;
 };
 /**
@@ -1045,6 +1055,7 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc);
  * @cpu_msix_table: table for mapping cpus to msix index
  * @cpu_msix_table_sz: table size
  * @total_io_cnt: Gives total IO count, used to load balance the interrupts
+ * @ioc_coredump_loop: will have non-zero value when FW is in CoreDump state
  * @high_iops_outstanding: used to load balance the interrupts
  *				within high iops reply queues
  * @msix_load_balance: Enables load balancing of interrupts across
@@ -1073,6 +1084,10 @@ typedef void (*MPT3SAS_FLUSH_RUNNING_CMDS)(struct MPT3SAS_ADAPTER *ioc);
  * @event_context: unique id for each logged event
  * @event_log: event log pointer
  * @event_masks: events that are masked
+ * @max_shutdown_latency: timeout value for NVMe shutdown operation,
+ *			which is equal that NVMe drive's RTD3 Entry Latency
+ *			which has reported maximum RTD3 Entry Latency value
+ *			among attached NVMe drives.
  * @facts: static facts data
  * @prev_fw_facts: previous fw facts data
  * @pfacts: static port facts data
@@ -1231,6 +1246,7 @@ struct MPT3SAS_ADAPTER {
 	u32		ioc_reset_count;
 	MPT3SAS_FLUSH_RUNNING_CMDS schedule_dead_ioc_flush_running_cmds;
 	u32             non_operational_loop;
+	u8              ioc_coredump_loop;
 	atomic64_t      total_io_cnt;
 	atomic64_t	high_iops_outstanding;
 	bool            msix_load_balance;
@@ -1283,7 +1299,7 @@ struct MPT3SAS_ADAPTER {
 
 	u8		tm_custom_handling;
 	u8		nvme_abort_timeout;
-
+	u16		max_shutdown_latency;
 
 	/* static config pages */
 	struct mpt3sas_facts facts;
@@ -1531,6 +1547,17 @@ void *mpt3sas_base_get_reply_virt_addr(struct MPT3SAS_ADAPTER *ioc,
 u32 mpt3sas_base_get_iocstate(struct MPT3SAS_ADAPTER *ioc, int cooked);
 
 void mpt3sas_base_fault_info(struct MPT3SAS_ADAPTER *ioc , u16 fault_code);
+#define mpt3sas_print_fault_code(ioc, fault_code) \
+do { pr_err("%s fault info from func: %s\n", ioc->name, __func__); \
+	mpt3sas_base_fault_info(ioc, fault_code); } while (0)
+
+void mpt3sas_base_coredump_info(struct MPT3SAS_ADAPTER *ioc, u16 fault_code);
+#define mpt3sas_print_coredump_info(ioc, fault_code) \
+do { pr_err("%s fault info from func: %s\n", ioc->name, __func__); \
+	mpt3sas_base_coredump_info(ioc, fault_code); } while (0)
+
+int mpt3sas_base_wait_for_coredump_completion(struct MPT3SAS_ADAPTER *ioc,
+		const char *caller);
 int mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 	Mpi2SasIoUnitControlReply_t *mpi_reply,
 	Mpi2SasIoUnitControlRequest_t *mpi_request);
@@ -1552,6 +1579,11 @@ mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc);
 
 u8 mpt3sas_base_check_cmd_timeout(struct MPT3SAS_ADAPTER *ioc,
 	u8 status, void *mpi_request, int sz);
+#define mpt3sas_check_cmd_timeout(ioc, status, mpi_request, sz, issue_reset) \
+do {	ioc_err(ioc, "In func: %s\n", __func__); \
+	issue_reset = mpt3sas_base_check_cmd_timeout(ioc, \
+	status, mpi_request, sz); } while (0)
+
 int mpt3sas_wait_for_ioc(struct MPT3SAS_ADAPTER *ioc, int wait_count);
 
 /* scsih shared API */
@@ -1560,7 +1592,8 @@ struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
 u8 mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 	u32 reply);
 void mpt3sas_scsih_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
-void mpt3sas_scsih_after_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_scsih_clear_outstanding_scsi_tm_commands(
+	struct MPT3SAS_ADAPTER *ioc);
 void mpt3sas_scsih_reset_done_handler(struct MPT3SAS_ADAPTER *ioc);
 
 int mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
@@ -1694,7 +1727,7 @@ void mpt3sas_ctl_exit(ushort hbas_to_enumerate);
 u8 mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	u32 reply);
 void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
-void mpt3sas_ctl_after_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_ctl_clear_outstanding_ioctls(struct MPT3SAS_ADAPTER *ioc);
 void mpt3sas_ctl_reset_done_handler(struct MPT3SAS_ADAPTER *ioc);
 u8 mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc,
 	u8 msix_index, u32 reply);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index 14a1a2793dd5..62ddf53ab3ae 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -101,9 +101,6 @@ _config_display_some_debug(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	Mpi2ConfigRequest_t *mpi_request;
 	char *desc = NULL;
 
-	if (!(ioc->logging_level & MPT_DEBUG_CONFIG))
-		return;
-
 	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
 	switch (mpi_request->Header.PageType & MPI2_CONFIG_PAGETYPE_MASK) {
 	case MPI2_CONFIG_PAGETYPE_IO_UNIT:
@@ -269,7 +266,8 @@ mpt3sas_config_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 		    mpi_reply->MsgLength*4);
 	}
 	ioc->config_cmds.status &= ~MPT3_CMD_PENDING;
-	_config_display_some_debug(ioc, smid, "config_done", mpi_reply);
+	if (ioc->logging_level & MPT_DEBUG_CONFIG)
+		_config_display_some_debug(ioc, smid, "config_done", mpi_reply);
 	ioc->config_cmds.smid = USHRT_MAX;
 	complete(&ioc->config_cmds.done);
 	return 1;
@@ -305,6 +303,7 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 	u8 retry_count, issue_host_reset = 0;
 	struct config_request mem;
 	u32 ioc_status = UINT_MAX;
+	u8 issue_reset = 0;
 
 	mutex_lock(&ioc->config_cmds.mutex);
 	if (ioc->config_cmds.status != MPT3_CMD_NOT_USED) {
@@ -378,14 +377,18 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 	config_request = mpt3sas_base_get_msg_frame(ioc, smid);
 	ioc->config_cmds.smid = smid;
 	memcpy(config_request, mpi_request, sizeof(Mpi2ConfigRequest_t));
-	_config_display_some_debug(ioc, smid, "config_request", NULL);
+	if (ioc->logging_level & MPT_DEBUG_CONFIG)
+		_config_display_some_debug(ioc, smid, "config_request", NULL);
 	init_completion(&ioc->config_cmds.done);
 	ioc->put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->config_cmds.done, timeout*HZ);
 	if (!(ioc->config_cmds.status & MPT3_CMD_COMPLETE)) {
-		mpt3sas_base_check_cmd_timeout(ioc,
-			ioc->config_cmds.status, mpi_request,
-			sizeof(Mpi2ConfigRequest_t)/4);
+		if (!(ioc->logging_level & MPT_DEBUG_CONFIG))
+			_config_display_some_debug(ioc,
+			    smid, "config_request", NULL);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->config_cmds.status, mpi_request,
+		    sizeof(Mpi2ConfigRequest_t)/4, issue_reset);
 		retry_count++;
 		if (ioc->config_cmds.smid == smid)
 			mpt3sas_base_free_smid(ioc, smid);
@@ -404,8 +407,11 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 		/* Reply Frame Sanity Checks to workaround FW issues */
 		if ((mpi_request->Header.PageType & 0xF) !=
 		    (mpi_reply->Header.PageType & 0xF)) {
+			if (!(ioc->logging_level & MPT_DEBUG_CONFIG))
+				_config_display_some_debug(ioc,
+				    smid, "config_request", NULL);
 			_debug_dump_mf(mpi_request, ioc->request_sz/4);
-			_debug_dump_reply(mpi_reply, ioc->request_sz/4);
+			_debug_dump_reply(mpi_reply, ioc->reply_sz/4);
 			panic("%s: %s: Firmware BUG: mpi_reply mismatch: Requested PageType(0x%02x) Reply PageType(0x%02x)\n",
 			      ioc->name, __func__,
 			      mpi_request->Header.PageType & 0xF,
@@ -415,8 +421,11 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 		if (((mpi_request->Header.PageType & 0xF) ==
 		    MPI2_CONFIG_PAGETYPE_EXTENDED) &&
 		    mpi_request->ExtPageType != mpi_reply->ExtPageType) {
+			if (!(ioc->logging_level & MPT_DEBUG_CONFIG))
+				_config_display_some_debug(ioc,
+				    smid, "config_request", NULL);
 			_debug_dump_mf(mpi_request, ioc->request_sz/4);
-			_debug_dump_reply(mpi_reply, ioc->request_sz/4);
+			_debug_dump_reply(mpi_reply, ioc->reply_sz/4);
 			panic("%s: %s: Firmware BUG: mpi_reply mismatch: Requested ExtPageType(0x%02x) Reply ExtPageType(0x%02x)\n",
 			      ioc->name, __func__,
 			      mpi_request->ExtPageType,
@@ -439,8 +448,11 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 		if (p) {
 			if ((mpi_request->Header.PageType & 0xF) !=
 			    (p[3] & 0xF)) {
+				if (!(ioc->logging_level & MPT_DEBUG_CONFIG))
+					_config_display_some_debug(ioc,
+					    smid, "config_request", NULL);
 				_debug_dump_mf(mpi_request, ioc->request_sz/4);
-				_debug_dump_reply(mpi_reply, ioc->request_sz/4);
+				_debug_dump_reply(mpi_reply, ioc->reply_sz/4);
 				_debug_dump_config(p, min_t(u16, mem.sz,
 				    config_page_sz)/4);
 				panic("%s: %s: Firmware BUG: config page mismatch: Requested PageType(0x%02x) Reply PageType(0x%02x)\n",
@@ -452,8 +464,11 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 			if (((mpi_request->Header.PageType & 0xF) ==
 			    MPI2_CONFIG_PAGETYPE_EXTENDED) &&
 			    (mpi_request->ExtPageType != p[6])) {
+				if (!(ioc->logging_level & MPT_DEBUG_CONFIG))
+					_config_display_some_debug(ioc,
+					    smid, "config_request", NULL);
 				_debug_dump_mf(mpi_request, ioc->request_sz/4);
-				_debug_dump_reply(mpi_reply, ioc->request_sz/4);
+				_debug_dump_reply(mpi_reply, ioc->reply_sz/4);
 				_debug_dump_config(p, min_t(u16, mem.sz,
 				    config_page_sz)/4);
 				panic("%s: %s: Firmware BUG: config page mismatch: Requested ExtPageType(0x%02x) Reply ExtPageType(0x%02x)\n",
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 6874cf017739..62e552838565 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -180,6 +180,12 @@ _ctl_display_some_debug(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	case MPI2_FUNCTION_SMP_PASSTHROUGH:
 		desc = "smp_passthrough";
 		break;
+	case MPI2_FUNCTION_TOOLBOX:
+		desc = "toolbox";
+		break;
+	case MPI2_FUNCTION_NVME_ENCAPSULATED:
+		desc = "nvme_encapsulated";
+		break;
 	}
 
 	if (!desc)
@@ -478,14 +484,15 @@ void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 }
 
 /**
- * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
+ * mpt3sas_ctl_reset_handler - clears outstanding ioctl cmd.
  * @ioc: per adapter object
  *
  * The handler for doing any required cleanup or initialization.
  */
-void mpt3sas_ctl_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+void mpt3sas_ctl_clear_outstanding_ioctls(struct MPT3SAS_ADAPTER *ioc)
 {
-	dtmprintk(ioc, ioc_info(ioc, "%s: MPT3_IOC_AFTER_RESET\n", __func__));
+	dtmprintk(ioc,
+	    ioc_info(ioc, "%s: clear outstanding ioctl cmd\n", __func__));
 	if (ioc->ctl_cmds.status & MPT3_CMD_PENDING) {
 		ioc->ctl_cmds.status |= MPT3_CMD_RESET;
 		mpt3sas_base_free_smid(ioc, ioc->ctl_cmds.smid);
@@ -1021,10 +1028,9 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		ioc->ignore_loginfos = 0;
 	}
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		issue_reset =
-			mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->ctl_cmds.status, mpi_request,
-				karg.data_sge_offset);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->ctl_cmds.status, mpi_request,
+		    karg.data_sge_offset, issue_reset);
 		goto issue_host_reset;
 	}
 
@@ -1325,7 +1331,8 @@ _ctl_do_reset(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 				 __func__));
 
 	retval = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
-	ioc_info(ioc, "host reset: %s\n", ((!retval) ? "SUCCESS" : "FAILED"));
+	ioc_info(ioc,
+	    "Ioctl: host reset: %s\n", ((!retval) ? "SUCCESS" : "FAILED"));
 	return 0;
 }
 
@@ -1733,10 +1740,9 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		issue_reset =
-			mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->ctl_cmds.status, mpi_request,
-				sizeof(Mpi2DiagBufferPostRequest_t)/4);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->ctl_cmds.status, mpi_request,
+		    sizeof(Mpi2DiagBufferPostRequest_t)/4, issue_reset);
 		goto issue_host_reset;
 	}
 
@@ -2108,6 +2114,7 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 	u16 ioc_status;
 	u32 ioc_state;
 	int rc;
+	u8 reset_needed = 0;
 
 	dctlprintk(ioc, ioc_info(ioc, "%s\n",
 				 __func__));
@@ -2115,6 +2122,7 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 	rc = 0;
 	*issue_reset = 0;
 
+
 	ioc_state = mpt3sas_base_get_iocstate(ioc, 1);
 	if (ioc_state != MPI2_IOC_STATE_OPERATIONAL) {
 		if (ioc->diag_buffer_status[buffer_type] &
@@ -2157,9 +2165,10 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		*issue_reset = mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->ctl_cmds.status, mpi_request,
-				sizeof(Mpi2DiagReleaseRequest_t)/4);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->ctl_cmds.status, mpi_request,
+		    sizeof(Mpi2DiagReleaseRequest_t)/4, reset_needed);
+		 *issue_reset = reset_needed;
 		rc = -EFAULT;
 		goto out;
 	}
@@ -2417,10 +2426,9 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		issue_reset =
-			mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->ctl_cmds.status, mpi_request,
-				sizeof(Mpi2DiagBufferPostRequest_t)/4);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->ctl_cmds.status, mpi_request,
+		    sizeof(Mpi2DiagBufferPostRequest_t)/4, issue_reset);
 		goto issue_host_reset;
 	}
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index a038be8a0e90..c597d544eb39 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1050,6 +1050,34 @@ mpt3sas_get_pdev_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 }
 
 /**
+ * _scsih_set_nvme_max_shutdown_latency - Update max_shutdown_latency.
+ * @ioc: per adapter object
+ * Context: This function will acquire ioc->pcie_device_lock
+ *
+ * Update ioc->max_shutdown_latency to that NVMe drives RTD3 Entry Latency
+ * which has reported maximum among all available NVMe drives.
+ * Minimum max_shutdown_latency will be six seconds.
+ */
+static void
+_scsih_set_nvme_max_shutdown_latency(struct MPT3SAS_ADAPTER *ioc)
+{
+	struct _pcie_device *pcie_device;
+	unsigned long flags;
+	u16 shutdown_latency = IO_UNIT_CONTROL_SHUTDOWN_TIMEOUT;
+
+	spin_lock_irqsave(&ioc->pcie_device_lock, flags);
+	list_for_each_entry(pcie_device, &ioc->pcie_device_list, list) {
+		if (pcie_device->shutdown_latency) {
+			if (shutdown_latency < pcie_device->shutdown_latency)
+				shutdown_latency =
+					pcie_device->shutdown_latency;
+		}
+	}
+	ioc->max_shutdown_latency = shutdown_latency;
+	spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
+}
+
+/**
  * _scsih_pcie_device_remove - remove pcie_device from list.
  * @ioc: per adapter object
  * @pcie_device: the pcie_device object
@@ -1063,6 +1091,7 @@ _scsih_pcie_device_remove(struct MPT3SAS_ADAPTER *ioc,
 {
 	unsigned long flags;
 	int was_on_pcie_device_list = 0;
+	u8 update_latency = 0;
 
 	if (!pcie_device)
 		return;
@@ -1082,11 +1111,21 @@ _scsih_pcie_device_remove(struct MPT3SAS_ADAPTER *ioc,
 		list_del_init(&pcie_device->list);
 		was_on_pcie_device_list = 1;
 	}
+	if (pcie_device->shutdown_latency == ioc->max_shutdown_latency)
+		update_latency = 1;
 	spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
 	if (was_on_pcie_device_list) {
 		kfree(pcie_device->serial_number);
 		pcie_device_put(pcie_device);
 	}
+
+	/*
+	 * This device's RTD3 Entry Latency matches IOC's
+	 * max_shutdown_latency. Recalculate IOC's max_shutdown_latency
+	 * from the available drives as current drive is getting removed.
+	 */
+	if (update_latency)
+		_scsih_set_nvme_max_shutdown_latency(ioc);
 }
 
 
@@ -1101,6 +1140,7 @@ _scsih_pcie_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	struct _pcie_device *pcie_device;
 	unsigned long flags;
 	int was_on_pcie_device_list = 0;
+	u8 update_latency = 0;
 
 	if (ioc->shost_recovery)
 		return;
@@ -1113,12 +1153,22 @@ _scsih_pcie_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 			was_on_pcie_device_list = 1;
 			pcie_device_put(pcie_device);
 		}
+		if (pcie_device->shutdown_latency == ioc->max_shutdown_latency)
+			update_latency = 1;
 	}
 	spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
 	if (was_on_pcie_device_list) {
 		_scsih_pcie_device_remove_from_sml(ioc, pcie_device);
 		pcie_device_put(pcie_device);
 	}
+
+	/*
+	 * This device's RTD3 Entry Latency matches IOC's
+	 * max_shutdown_latency. Recalculate IOC's max_shutdown_latency
+	 * from the available drives as current drive is getting removed.
+	 */
+	if (update_latency)
+		_scsih_set_nvme_max_shutdown_latency(ioc);
 }
 
 /**
@@ -1554,7 +1604,12 @@ scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
 		max_depth = 1;
 	if (qdepth > max_depth)
 		qdepth = max_depth;
-	return scsi_change_queue_depth(sdev, qdepth);
+	scsi_change_queue_depth(sdev, qdepth);
+	sdev_printk(KERN_INFO, sdev,
+	    "qdepth(%d), tagged(%d), scsi_level(%d), cmd_que(%d)\n",
+	    sdev->queue_depth, sdev->tagged_supported,
+	    sdev->scsi_level, ((sdev->inquiry[7] & 2) >> 1));
+	return sdev->queue_depth;
 }
 
 /**
@@ -2673,6 +2728,7 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	u16 smid = 0;
 	u32 ioc_state;
 	int rc;
+	u8 issue_reset = 0;
 
 	lockdep_assert_held(&ioc->tm_cmds.mutex);
 
@@ -2695,7 +2751,13 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	}
 
 	if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT) {
-		mpt3sas_base_fault_info(ioc, ioc_state &
+		mpt3sas_print_fault_code(ioc, ioc_state &
+		    MPI2_DOORBELL_DATA_MASK);
+		rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
+		return (!rc) ? SUCCESS : FAILED;
+	} else if ((ioc_state & MPI2_IOC_STATE_MASK) ==
+	    MPI2_IOC_STATE_COREDUMP) {
+		mpt3sas_print_coredump_info(ioc, ioc_state &
 		    MPI2_DOORBELL_DATA_MASK);
 		rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 		return (!rc) ? SUCCESS : FAILED;
@@ -2726,9 +2788,10 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	ioc->put_smid_hi_priority(ioc, smid, msix_task);
 	wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
-		if (mpt3sas_base_check_cmd_timeout(ioc,
-			ioc->tm_cmds.status, mpi_request,
-			sizeof(Mpi2SCSITaskManagementRequest_t)/4)) {
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->tm_cmds.status, mpi_request,
+		    sizeof(Mpi2SCSITaskManagementRequest_t)/4, issue_reset);
+		if (issue_reset) {
 			rc = mpt3sas_base_hard_reset_handler(ioc,
 					FORCE_BIG_HAMMER);
 			rc = (!rc) ? SUCCESS : FAILED;
@@ -2875,15 +2938,17 @@ scsih_abort(struct scsi_cmnd *scmd)
 
 	u8 timeout = 30;
 	struct _pcie_device *pcie_device = NULL;
-	sdev_printk(KERN_INFO, scmd->device,
-		"attempting task abort! scmd(%p)\n", scmd);
+	sdev_printk(KERN_INFO, scmd->device, "attempting task abort!"
+	    "scmd(0x%p), outstanding for %u ms & timeout %u ms\n",
+	    scmd, jiffies_to_msecs(jiffies - scmd->jiffies_at_alloc),
+	    (scmd->request->timeout / HZ) * 1000);
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
 	    ioc->remove_host) {
 		sdev_printk(KERN_INFO, scmd->device,
-			"device been deleted! scmd(%p)\n", scmd);
+		    "device been deleted! scmd(0x%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		r = SUCCESS;
@@ -2892,6 +2957,8 @@ scsih_abort(struct scsi_cmnd *scmd)
 
 	/* check for completed command */
 	if (st == NULL || st->cb_idx == 0xFF) {
+		sdev_printk(KERN_INFO, scmd->device, "No reference found at "
+		    "driver, assuming scmd(0x%p) might have completed\n", scmd);
 		scmd->result = DID_RESET << 16;
 		r = SUCCESS;
 		goto out;
@@ -2920,7 +2987,7 @@ scsih_abort(struct scsi_cmnd *scmd)
 	if (r == SUCCESS && st->cb_idx != 0xFF)
 		r = FAILED;
  out:
-	sdev_printk(KERN_INFO, scmd->device, "task abort: %s scmd(%p)\n",
+	sdev_printk(KERN_INFO, scmd->device, "task abort: %s scmd(0x%p)\n",
 	    ((r == SUCCESS) ? "SUCCESS" : "FAILED"), scmd);
 	if (pcie_device)
 		pcie_device_put(pcie_device);
@@ -2949,14 +3016,14 @@ scsih_dev_reset(struct scsi_cmnd *scmd)
 	struct MPT3SAS_TARGET *target_priv_data = starget->hostdata;
 
 	sdev_printk(KERN_INFO, scmd->device,
-		"attempting device reset! scmd(%p)\n", scmd);
+	    "attempting device reset! scmd(0x%p)\n", scmd);
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
 	    ioc->remove_host) {
 		sdev_printk(KERN_INFO, scmd->device,
-			"device been deleted! scmd(%p)\n", scmd);
+		    "device been deleted! scmd(0x%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		r = SUCCESS;
@@ -2996,7 +3063,7 @@ scsih_dev_reset(struct scsi_cmnd *scmd)
 	if (r == SUCCESS && atomic_read(&scmd->device->device_busy))
 		r = FAILED;
  out:
-	sdev_printk(KERN_INFO, scmd->device, "device reset: %s scmd(%p)\n",
+	sdev_printk(KERN_INFO, scmd->device, "device reset: %s scmd(0x%p)\n",
 	    ((r == SUCCESS) ? "SUCCESS" : "FAILED"), scmd);
 
 	if (sas_device)
@@ -3027,15 +3094,15 @@ scsih_target_reset(struct scsi_cmnd *scmd)
 	struct scsi_target *starget = scmd->device->sdev_target;
 	struct MPT3SAS_TARGET *target_priv_data = starget->hostdata;
 
-	starget_printk(KERN_INFO, starget, "attempting target reset! scmd(%p)\n",
-		scmd);
+	starget_printk(KERN_INFO, starget,
+	    "attempting target reset! scmd(0x%p)\n", scmd);
 	_scsih_tm_display_info(ioc, scmd);
 
 	sas_device_priv_data = scmd->device->hostdata;
 	if (!sas_device_priv_data || !sas_device_priv_data->sas_target ||
 	    ioc->remove_host) {
-		starget_printk(KERN_INFO, starget, "target been deleted! scmd(%p)\n",
-			scmd);
+		starget_printk(KERN_INFO, starget,
+		    "target been deleted! scmd(0x%p)\n", scmd);
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		r = SUCCESS;
@@ -3074,7 +3141,7 @@ scsih_target_reset(struct scsi_cmnd *scmd)
 	if (r == SUCCESS && atomic_read(&starget->target_busy))
 		r = FAILED;
  out:
-	starget_printk(KERN_INFO, starget, "target reset: %s scmd(%p)\n",
+	starget_printk(KERN_INFO, starget, "target reset: %s scmd(0x%p)\n",
 	    ((r == SUCCESS) ? "SUCCESS" : "FAILED"), scmd);
 
 	if (sas_device)
@@ -3097,7 +3164,7 @@ scsih_host_reset(struct scsi_cmnd *scmd)
 	struct MPT3SAS_ADAPTER *ioc = shost_priv(scmd->device->host);
 	int r, retval;
 
-	ioc_info(ioc, "attempting host reset! scmd(%p)\n", scmd);
+	ioc_info(ioc, "attempting host reset! scmd(0x%p)\n", scmd);
 	scsi_print_command(scmd);
 
 	if (ioc->is_driver_loading || ioc->remove_host) {
@@ -3109,7 +3176,7 @@ scsih_host_reset(struct scsi_cmnd *scmd)
 	retval = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 	r = (retval < 0) ? FAILED : SUCCESS;
 out:
-	ioc_info(ioc, "host reset: %s scmd(%p)\n",
+	ioc_info(ioc, "host reset: %s scmd(0x%p)\n",
 		 r == SUCCESS ? "SUCCESS" : "FAILED", scmd);
 
 	return r;
@@ -4475,6 +4542,7 @@ static void
 _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 	Mpi2EventDataTemperature_t *event_data)
 {
+	u32 doorbell;
 	if (ioc->temp_sensors_count >= event_data->SensorNum) {
 		ioc_err(ioc, "Temperature Threshold flags %s%s%s%s exceeded for Sensor: %d !!!\n",
 			le16_to_cpu(event_data->Status) & 0x1 ? "0 " : " ",
@@ -4484,6 +4552,18 @@ _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
 			event_data->SensorNum);
 		ioc_err(ioc, "Current Temp In Celsius: %d\n",
 			event_data->CurrentTemperature);
+		if (ioc->hba_mpi_version_belonged != MPI2_VERSION) {
+			doorbell = mpt3sas_base_get_iocstate(ioc, 0);
+			if ((doorbell & MPI2_IOC_STATE_MASK) ==
+			    MPI2_IOC_STATE_FAULT) {
+				mpt3sas_print_fault_code(ioc,
+				    doorbell & MPI2_DOORBELL_DATA_MASK);
+			} else if ((doorbell & MPI2_IOC_STATE_MASK) ==
+			    MPI2_IOC_STATE_COREDUMP) {
+				mpt3sas_print_coredump_info(ioc,
+				    doorbell & MPI2_DOORBELL_DATA_MASK);
+			}
+		}
 	}
 }
 
@@ -6933,6 +7013,16 @@ _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	    le32_to_cpu(pcie_device_pg0.DeviceInfo)))) {
 		pcie_device->nvme_mdts =
 		    le32_to_cpu(pcie_device_pg2.MaximumDataTransferSize);
+		pcie_device->shutdown_latency =
+			le16_to_cpu(pcie_device_pg2.ShutdownLatency);
+		/*
+		 * Set IOC's max_shutdown_latency to drive's RTD3 Entry Latency
+		 * if drive's RTD3 Entry Latency is greater then IOC's
+		 * max_shutdown_latency.
+		 */
+		if (pcie_device->shutdown_latency > ioc->max_shutdown_latency)
+			ioc->max_shutdown_latency =
+				pcie_device->shutdown_latency;
 		if (pcie_device_pg2.ControllerResetTO)
 			pcie_device->reset_timeout =
 			    pcie_device_pg2.ControllerResetTO;
@@ -7669,10 +7759,9 @@ _scsih_ir_fastpath(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phys_disk_num)
 	wait_for_completion_timeout(&ioc->scsih_cmds.done, 10*HZ);
 
 	if (!(ioc->scsih_cmds.status & MPT3_CMD_COMPLETE)) {
-		issue_reset =
-			mpt3sas_base_check_cmd_timeout(ioc,
-				ioc->scsih_cmds.status, mpi_request,
-				sizeof(Mpi2RaidActionRequest_t)/4);
+		mpt3sas_check_cmd_timeout(ioc,
+		    ioc->scsih_cmds.status, mpi_request,
+		    sizeof(Mpi2RaidActionRequest_t)/4, issue_reset);
 		rc = -EFAULT;
 		goto out;
 	}
@@ -9272,15 +9361,17 @@ void mpt3sas_scsih_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 }
 
 /**
- * mpt3sas_scsih_after_reset_handler - reset callback handler (for scsih)
+ * mpt3sas_scsih_clear_outstanding_scsi_tm_commands - clears outstanding
+ *							scsi & tm cmds.
  * @ioc: per adapter object
  *
  * The handler for doing any required cleanup or initialization.
  */
 void
-mpt3sas_scsih_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+mpt3sas_scsih_clear_outstanding_scsi_tm_commands(struct MPT3SAS_ADAPTER *ioc)
 {
-	dtmprintk(ioc, ioc_info(ioc, "%s: MPT3_IOC_AFTER_RESET\n", __func__));
+	dtmprintk(ioc,
+	    ioc_info(ioc, "%s: clear outstanding scsi & tm cmds\n", __func__));
 	if (ioc->scsih_cmds.status & MPT3_CMD_PENDING) {
 		ioc->scsih_cmds.status |= MPT3_CMD_RESET;
 		mpt3sas_base_free_smid(ioc, ioc->scsih_cmds.smid);
@@ -9357,6 +9448,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
 		}
 		_scsih_remove_unresponding_devices(ioc);
 		_scsih_scan_for_devices_after_reset(ioc);
+		_scsih_set_nvme_max_shutdown_latency(ioc);
 		break;
 	case MPT3SAS_PORT_ENABLE_COMPLETE:
 		ioc->start_scan = 0;
@@ -9660,6 +9752,75 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
 }
 
 /**
+ * _scsih_nvme_shutdown - NVMe shutdown notification
+ * @ioc: per adapter object
+ *
+ * Sending IoUnitControl request with shutdown operation code to alert IOC that
+ * the host system is shutting down so that IOC can issue NVMe shutdown to
+ * NVMe drives attached to it.
+ */
+static void
+_scsih_nvme_shutdown(struct MPT3SAS_ADAPTER *ioc)
+{
+	Mpi26IoUnitControlRequest_t *mpi_request;
+	Mpi26IoUnitControlReply_t *mpi_reply;
+	u16 smid;
+
+	/* are there any NVMe devices ? */
+	if (list_empty(&ioc->pcie_device_list))
+		return;
+
+	mutex_lock(&ioc->scsih_cmds.mutex);
+
+	if (ioc->scsih_cmds.status != MPT3_CMD_NOT_USED) {
+		ioc_err(ioc, "%s: scsih_cmd in use\n", __func__);
+		goto out;
+	}
+
+	ioc->scsih_cmds.status = MPT3_CMD_PENDING;
+
+	smid = mpt3sas_base_get_smid(ioc, ioc->scsih_cb_idx);
+	if (!smid) {
+		ioc_err(ioc,
+		    "%s: failed obtaining a smid\n", __func__);
+		ioc->scsih_cmds.status = MPT3_CMD_NOT_USED;
+		goto out;
+	}
+
+	mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
+	ioc->scsih_cmds.smid = smid;
+	memset(mpi_request, 0, sizeof(Mpi26IoUnitControlRequest_t));
+	mpi_request->Function = MPI2_FUNCTION_IO_UNIT_CONTROL;
+	mpi_request->Operation = MPI26_CTRL_OP_SHUTDOWN;
+
+	init_completion(&ioc->scsih_cmds.done);
+	ioc->put_smid_default(ioc, smid);
+	/* Wait for max_shutdown_latency seconds */
+	ioc_info(ioc,
+		"Io Unit Control shutdown (sending), Shutdown latency %d sec\n",
+		ioc->max_shutdown_latency);
+	wait_for_completion_timeout(&ioc->scsih_cmds.done,
+			ioc->max_shutdown_latency*HZ);
+
+	if (!(ioc->scsih_cmds.status & MPT3_CMD_COMPLETE)) {
+		ioc_err(ioc, "%s: timeout\n", __func__);
+		goto out;
+	}
+
+	if (ioc->scsih_cmds.status & MPT3_CMD_REPLY_VALID) {
+		mpi_reply = ioc->scsih_cmds.reply;
+		ioc_info(ioc, "Io Unit Control shutdown (complete):"
+			"ioc_status(0x%04x), loginfo(0x%08x)\n",
+			le16_to_cpu(mpi_reply->IOCStatus),
+			le32_to_cpu(mpi_reply->IOCLogInfo));
+	}
+ out:
+	ioc->scsih_cmds.status = MPT3_CMD_NOT_USED;
+	mutex_unlock(&ioc->scsih_cmds.mutex);
+}
+
+
+/**
  * _scsih_ir_shutdown - IR shutdown notification
  * @ioc: per adapter object
  *
@@ -9851,6 +10012,7 @@ scsih_shutdown(struct pci_dev *pdev)
 				&ioc->ioc_pg1_copy);
 
 	_scsih_ir_shutdown(ioc);
+	_scsih_nvme_shutdown(ioc);
 	mpt3sas_base_detach(ioc);
 }
 
@@ -10533,6 +10695,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ioc->tm_sas_control_cb_idx = tm_sas_control_cb_idx;
 	ioc->logging_level = logging_level;
 	ioc->schedule_dead_ioc_flush_running_cmds = &_scsih_flush_running_cmds;
+	/* Host waits for minimum of six seconds */
+	ioc->max_shutdown_latency = IO_UNIT_CONTROL_SHUTDOWN_TIMEOUT;
 	/*
 	 * Enable MEMORY MOVE support flag.
 	 */
@@ -10681,6 +10845,7 @@ scsih_suspend(struct pci_dev *pdev, pm_message_t state)
 	mpt3sas_base_stop_watchdog(ioc);
 	flush_scheduled_work();
 	scsi_block_requests(shost);
+	_scsih_nvme_shutdown(ioc);
 	device_state = pci_choose_state(pdev, state);
 	ioc_info(ioc, "pdev=0x%p, slot=%s, entering operating state [D%d]\n",
 		 pdev, pci_name(pdev), device_state);
@@ -10715,7 +10880,7 @@ scsih_resume(struct pci_dev *pdev)
 	r = mpt3sas_base_map_resources(ioc);
 	if (r)
 		return r;
-
+	ioc_info(ioc, "Issuing Hard Reset as part of OS Resume\n");
 	mpt3sas_base_hard_reset_handler(ioc, SOFT_RESET);
 	scsi_unblock_requests(shost);
 	mpt3sas_base_start_watchdog(ioc);
@@ -10784,6 +10949,7 @@ scsih_pci_slot_reset(struct pci_dev *pdev)
 	if (rc)
 		return PCI_ERS_RESULT_DISCONNECT;
 
+	ioc_info(ioc, "Issuing Hard Reset as part of PCI Slot Reset\n");
 	rc = mpt3sas_base_hard_reset_handler(ioc, FORCE_BIG_HAMMER);
 
 	ioc_warn(ioc, "hard reset: %s\n",
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 5324662751bf..6ec5b7f33dfd 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -719,11 +719,10 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle,
 		sas_device_put(sas_device);
 	}
 
-	if ((ioc->logging_level & MPT_DEBUG_TRANSPORT))
-		dev_printk(KERN_INFO, &rphy->dev,
-			"add: handle(0x%04x), sas_addr(0x%016llx)\n",
-			handle, (unsigned long long)
-		    mpt3sas_port->remote_identify.sas_address);
+	dev_info(&rphy->dev,
+	    "add: handle(0x%04x), sas_addr(0x%016llx)\n", handle,
+	    (unsigned long long)mpt3sas_port->remote_identify.sas_address);
+
 	mpt3sas_port->rphy = rphy;
 	spin_lock_irqsave(&ioc->sas_node_lock, flags);
 	list_add_tail(&mpt3sas_port->port_list, &sas_node->sas_port_list);
@@ -813,6 +812,8 @@ mpt3sas_transport_port_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
 	}
 	if (!ioc->remove_host)
 		sas_port_delete(mpt3sas_port->port);
+	ioc_info(ioc, "%s: removed: sas_addr(0x%016llx)\n",
+	    __func__, (unsigned long long)sas_address);
 	kfree(mpt3sas_port);
 }
 
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index da719b0694dc..7af9173c4925 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -47,6 +47,9 @@ static struct scsi_host_template mvs_sht = {
 	.eh_target_reset_handler = sas_eh_target_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= sas_ioctl,
+#endif
 	.shost_attrs		= mvst_host_attrs,
 	.track_queue_depth	= 1,
 };
diff --git a/drivers/scsi/myrb.h b/drivers/scsi/myrb.h
index 9289c19fcb2f..fb8eacfceee8 100644
--- a/drivers/scsi/myrb.h
+++ b/drivers/scsi/myrb.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Linux Driver for Mylex DAC960/AcceleRAID/eXtremeRAID PCI RAID Controllers
  *
  * Copyright 2017 Hannes Reinecke, SUSE Linux GmbH <hare@suse.com>
diff --git a/drivers/scsi/myrs.h b/drivers/scsi/myrs.h
index e6702ee85e9f..9f6696d0ddd5 100644
--- a/drivers/scsi/myrs.h
+++ b/drivers/scsi/myrs.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Linux Driver for Mylex DAC960/AcceleRAID/eXtremeRAID PCI RAID Controllers
  *
  * This driver supports the newer, SCSI-based firmware interface only.
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index ff618ad80ebd..3c6076e4c6d2 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -101,6 +101,9 @@ static struct scsi_host_template pm8001_sht = {
 	.eh_target_reset_handler = sas_eh_target_reset_handler,
 	.target_destroy		= sas_target_destroy,
 	.ioctl			= sas_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= sas_ioctl,
+#endif
 	.shost_attrs		= pm8001_host_attrs,
 	.track_queue_depth	= 1,
 };
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 832af4213046..3337cd341d21 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -1699,6 +1699,16 @@ qla1280_load_firmware_pio(struct scsi_qla_host *ha)
 	return err;
 }
 
+#ifdef QLA_64BIT_PTR
+#define LOAD_CMD	MBC_LOAD_RAM_A64_ROM
+#define DUMP_CMD	MBC_DUMP_RAM_A64_ROM
+#define CMD_ARGS	(BIT_7 | BIT_6 | BIT_4 | BIT_3 | BIT_2 | BIT_1 | BIT_0)
+#else
+#define LOAD_CMD	MBC_LOAD_RAM
+#define DUMP_CMD	MBC_DUMP_RAM
+#define CMD_ARGS	(BIT_4 | BIT_3 | BIT_2 | BIT_1 | BIT_0)
+#endif
+
 #define DUMP_IT_BACK 0		/* for debug of RISC loading */
 static int
 qla1280_load_firmware_dma(struct scsi_qla_host *ha)
@@ -1748,7 +1758,7 @@ qla1280_load_firmware_dma(struct scsi_qla_host *ha)
 		for(i = 0; i < cnt; i++)
 			((__le16 *)ha->request_ring)[i] = fw_data[i];
 
-		mb[0] = MBC_LOAD_RAM;
+		mb[0] = LOAD_CMD;
 		mb[1] = risc_address;
 		mb[4] = cnt;
 		mb[3] = ha->request_dma & 0xffff;
@@ -1759,8 +1769,7 @@ qla1280_load_firmware_dma(struct scsi_qla_host *ha)
 				__func__, mb[0],
 				(void *)(long)ha->request_dma,
 				mb[6], mb[7], mb[2], mb[3]);
-		err = qla1280_mailbox_command(ha, BIT_4 | BIT_3 | BIT_2 |
-				BIT_1 | BIT_0, mb);
+		err = qla1280_mailbox_command(ha, CMD_ARGS, mb);
 		if (err) {
 			printk(KERN_ERR "scsi(%li): Failed to load partial "
 			       "segment of f\n", ha->host_no);
@@ -1768,7 +1777,7 @@ qla1280_load_firmware_dma(struct scsi_qla_host *ha)
 		}
 
 #if DUMP_IT_BACK
-		mb[0] = MBC_DUMP_RAM;
+		mb[0] = DUMP_CMD;
 		mb[1] = risc_address;
 		mb[4] = cnt;
 		mb[3] = p_tbuf & 0xffff;
@@ -1776,8 +1785,7 @@ qla1280_load_firmware_dma(struct scsi_qla_host *ha)
 		mb[7] = upper_32_bits(p_tbuf) & 0xffff;
 		mb[6] = upper_32_bits(p_tbuf) >> 16;
 
-		err = qla1280_mailbox_command(ha, BIT_4 | BIT_3 | BIT_2 |
-				BIT_1 | BIT_0, mb);
+		err = qla1280_mailbox_command(ha, CMD_ARGS, mb);
 		if (err) {
 			printk(KERN_ERR
 			       "Failed to dump partial segment of f/w\n");
diff --git a/drivers/scsi/qla1280.h b/drivers/scsi/qla1280.h
index a1a8aefc7cc3..e7820b5bca38 100644
--- a/drivers/scsi/qla1280.h
+++ b/drivers/scsi/qla1280.h
@@ -277,6 +277,8 @@ struct device_reg {
 #define MBC_MAILBOX_REGISTER_TEST	6	/* Wrap incoming mailboxes */
 #define MBC_VERIFY_CHECKSUM		7	/* Verify checksum */
 #define MBC_ABOUT_FIRMWARE		8	/* Get firmware revision */
+#define MBC_LOAD_RAM_A64_ROM		9	/* Load RAM 64bit ROM version */
+#define MBC_DUMP_RAM_A64_ROM		0x0a	/* Dump RAM 64bit ROM version */
 #define MBC_INIT_REQUEST_QUEUE		0x10	/* Initialize request queue */
 #define MBC_INIT_RESPONSE_QUEUE		0x11	/* Initialize response queue */
 #define MBC_EXECUTE_IOCB		0x12	/* Execute IOCB command */
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index cbaf178fc979..d7169e43f5e1 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -54,7 +54,8 @@ void qla2x00_bsg_sp_free(srb_t *sp)
 	if (sp->type == SRB_CT_CMD ||
 	    sp->type == SRB_FXIOCB_BCMD ||
 	    sp->type == SRB_ELS_CMD_HST)
-		kfree(sp->fcport);
+		qla2x00_free_fcport(sp->fcport);
+
 	qla2x00_rel_sp(sp);
 }
 
@@ -405,7 +406,7 @@ done_unmap_sg:
 
 done_free_fcport:
 	if (bsg_request->msgcode == FC_BSG_RPT_ELS)
-		kfree(fcport);
+		qla2x00_free_fcport(fcport);
 done:
 	return rval;
 }
@@ -545,7 +546,7 @@ qla2x00_process_ct(struct bsg_job *bsg_job)
 	return rval;
 
 done_free_fcport:
-	kfree(fcport);
+	qla2x00_free_fcport(fcport);
 done_unmap_sg:
 	dma_unmap_sg(&ha->pdev->dev, bsg_job->request_payload.sg_list,
 		bsg_job->request_payload.sg_cnt, DMA_TO_DEVICE);
@@ -796,7 +797,7 @@ qla2x00_process_loopback(struct bsg_job *bsg_job)
 
 	if (atomic_read(&vha->loop_state) == LOOP_READY &&
 	    (ha->current_topology == ISP_CFG_F ||
-	    (le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE &&
+	    (get_unaligned_le32(req_data) == ELS_OPCODE_BYTE &&
 	     req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
 	    elreq.options == EXTERNAL_LOOPBACK) {
 		type = "FC_BSG_HST_VENDOR_ECHO_DIAG";
@@ -2049,7 +2050,7 @@ qlafx00_mgmt_cmd(struct bsg_job *bsg_job)
 	return rval;
 
 done_free_fcport:
-	kfree(fcport);
+	qla2x00_free_fcport(fcport);
 
 done_unmap_rsp_sg:
 	if (piocb_rqst->flags & SRB_FXDISC_RESP_DMA_VALID)
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 30afc59c1870..e5500bba06ca 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -18,7 +18,7 @@
  * | Device Discovery             |       0x2134       | 0x210e-0x2116  |
  * |				  | 		       | 0x211a         |
  * |                              |                    | 0x211c-0x2128  |
- * |                              |                    | 0x212a-0x2130  |
+ * |                              |                    | 0x212a-0x2134  |
  * | Queue Command and IO tracing |       0x3074       | 0x300b         |
  * |                              |                    | 0x3027-0x3028  |
  * |                              |                    | 0x303d-0x3041  |
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 2edd9f7b3074..ed32e9715794 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2402,6 +2402,7 @@ typedef struct fc_port {
 	unsigned int scan_needed:1;
 	unsigned int n2n_flag:1;
 	unsigned int explicit_logout:1;
+	unsigned int prli_pend_timer:1;
 
 	struct completion nvme_del_done;
 	uint32_t nvme_prli_service_param;
@@ -2428,6 +2429,7 @@ typedef struct fc_port {
 	struct work_struct free_work;
 	struct work_struct reg_work;
 	uint64_t jiffies_at_registration;
+	unsigned long prli_expired;
 	struct qlt_plogi_ack_t *plogi_link[QLT_PLOGI_LINK_MAX];
 
 	uint16_t tgt_id;
@@ -2464,6 +2466,7 @@ typedef struct fc_port {
 	struct qla_tgt_sess *tgt_session;
 	struct ct_sns_desc ct_desc;
 	enum discovery_state disc_state;
+	atomic_t shadow_disc_state;
 	enum discovery_state next_disc_state;
 	enum login_state fw_login_state;
 	unsigned long dm_login_expire;
@@ -2510,6 +2513,19 @@ struct event_arg {
 
 extern const char *const port_state_str[5];
 
+static const char * const port_dstate_str[] = {
+	"DELETED",
+	"GNN_ID",
+	"GNL",
+	"LOGIN_PEND",
+	"LOGIN_FAILED",
+	"GPDB",
+	"UPD_FCPORT",
+	"LOGIN_COMPLETE",
+	"ADISC",
+	"DELETE_PEND"
+};
+
 /*
  * FC port flags.
  */
@@ -3263,7 +3279,6 @@ enum qla_work_type {
 	QLA_EVT_IDC_ACK,
 	QLA_EVT_ASYNC_LOGIN,
 	QLA_EVT_ASYNC_LOGOUT,
-	QLA_EVT_ASYNC_LOGOUT_DONE,
 	QLA_EVT_ASYNC_ADISC,
 	QLA_EVT_UEVENT,
 	QLA_EVT_AENFX,
@@ -3953,7 +3968,7 @@ struct qla_hw_data {
 	void		*sfp_data;
 	dma_addr_t	sfp_data_dma;
 
-	void		*flt;
+	struct qla_flt_header *flt;
 	dma_addr_t	flt_dma;
 
 #define XGMAC_DATA_SIZE	4096
@@ -4845,6 +4860,9 @@ struct sff_8247_a0 {
 	(ha->fc4_type_priority == FC4_PRIORITY_NVME)) || \
 	NVME_ONLY_TARGET(fcport)) \
 
+#define PRLI_PHASE(_cls) \
+	((_cls == DSC_LS_PRLI_PEND) || (_cls == DSC_LS_PRLI_COMP))
+
 #include "qla_target.h"
 #include "qla_gbl.h"
 #include "qla_dbg.h"
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 9dc09c117416..d641918cdd46 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -1354,12 +1354,12 @@ struct vp_rpt_id_entry_24xx {
 	uint8_t port_id[3];
 	uint8_t format;
 	union {
-		struct {
+		struct _f0 {
 			/* format 0 loop */
 			uint8_t vp_idx_map[16];
 			uint8_t reserved_4[32];
 		} f0;
-		struct {
+		struct _f1 {
 			/* format 1 fabric */
 			uint8_t vpstat1_subcode; /* vp_status=1 subcode */
 			uint8_t flags;
@@ -1381,21 +1381,22 @@ struct vp_rpt_id_entry_24xx {
 			uint16_t bbcr;
 			uint8_t reserved_5[6];
 		} f1;
-		struct { /* format 2: N2N direct connect */
-		    uint8_t vpstat1_subcode;
-		    uint8_t flags;
-		    uint16_t rsv6;
-		    uint8_t rsv2[12];
-
-		    uint8_t ls_rjt_vendor;
-		    uint8_t ls_rjt_explanation;
-		    uint8_t ls_rjt_reason;
-		    uint8_t rsv3[5];
-
-		    uint8_t port_name[8];
-		    uint8_t node_name[8];
-		    uint8_t remote_nport_id[4];
-		    uint32_t reserved_5;
+		struct _f2 { /* format 2: N2N direct connect */
+			uint8_t vpstat1_subcode;
+			uint8_t flags;
+			uint16_t fip_flags;
+			uint8_t rsv2[12];
+
+			uint8_t ls_rjt_vendor;
+			uint8_t ls_rjt_explanation;
+			uint8_t ls_rjt_reason;
+			uint8_t rsv3[5];
+
+			uint8_t port_name[8];
+			uint8_t node_name[8];
+			uint16_t bbcr;
+			uint8_t reserved_5[2];
+			uint8_t remote_nport_id[4];
 		} f2;
 	} u;
 };
@@ -1470,13 +1471,6 @@ struct qla_flt_location {
 	uint16_t checksum;
 };
 
-struct qla_flt_header {
-	uint16_t version;
-	uint16_t length;
-	uint16_t checksum;
-	uint16_t unused;
-};
-
 #define FLT_REG_FW		0x01
 #define FLT_REG_BOOT_CODE	0x07
 #define FLT_REG_VPD_0		0x14
@@ -1537,6 +1531,14 @@ struct qla_flt_region {
 	uint32_t end;
 };
 
+struct qla_flt_header {
+	uint16_t version;
+	uint16_t length;
+	uint16_t checksum;
+	uint16_t unused;
+	struct qla_flt_region region[0];
+};
+
 #define FLT_REGION_SIZE		16
 #define FLT_MAX_REGIONS		0xFF
 #define FLT_REGIONS_SIZE	(FLT_REGION_SIZE * FLT_MAX_REGIONS)
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 5b163ad85c34..2a64729a2bc5 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -72,14 +72,13 @@ extern int qla2x00_async_adisc(struct scsi_qla_host *, fc_port_t *,
 extern int qla2x00_async_tm_cmd(fc_port_t *, uint32_t, uint32_t, uint32_t);
 extern void qla2x00_async_login_done(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
-extern void qla2x00_async_logout_done(struct scsi_qla_host *, fc_port_t *,
-    uint16_t *);
 struct qla_work_evt *qla2x00_alloc_work(struct scsi_qla_host *,
     enum qla_work_type);
 extern int qla24xx_async_gnl(struct scsi_qla_host *, fc_port_t *);
 int qla2x00_post_work(struct scsi_qla_host *vha, struct qla_work_evt *e);
 extern void *qla2x00_alloc_iocbs_ready(struct qla_qpair *, srb_t *);
 extern int qla24xx_update_fcport_fcp_prio(scsi_qla_host_t *, fc_port_t *);
+extern int qla24xx_async_abort_cmd(srb_t *, bool);
 
 extern void qla2x00_set_fcport_state(fc_port_t *fcport, int state);
 extern fc_port_t *
@@ -182,8 +181,6 @@ extern int qla2x00_post_async_login_work(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
 extern int qla2x00_post_async_logout_work(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
-extern int qla2x00_post_async_logout_done_work(struct scsi_qla_host *,
-    fc_port_t *, uint16_t *);
 extern int qla2x00_post_async_adisc_work(struct scsi_qla_host *, fc_port_t *,
     uint16_t *);
 extern int qla2x00_post_async_adisc_done_work(struct scsi_qla_host *,
@@ -201,6 +198,7 @@ extern void qla2x00_free_host(struct scsi_qla_host *);
 extern void qla2x00_relogin(struct scsi_qla_host *);
 extern void qla2x00_do_work(struct scsi_qla_host *);
 extern void qla2x00_free_fcports(struct scsi_qla_host *);
+extern void qla2x00_free_fcport(fc_port_t *);
 
 extern void qla83xx_schedule_work(scsi_qla_host_t *, int);
 extern void qla83xx_service_idc_aen(struct work_struct *);
@@ -253,8 +251,9 @@ extern scsi_qla_host_t *qla24xx_create_vhost(struct fc_vport *);
 extern void qla2x00_sp_free_dma(srb_t *sp);
 extern char *qla2x00_get_fw_version_str(struct scsi_qla_host *, char *);
 
-extern void qla2x00_mark_device_lost(scsi_qla_host_t *, fc_port_t *, int, int);
-extern void qla2x00_mark_all_devices_lost(scsi_qla_host_t *, int);
+extern void qla2x00_mark_device_lost(scsi_qla_host_t *, fc_port_t *, int);
+extern void qla2x00_mark_all_devices_lost(scsi_qla_host_t *);
+extern int qla24xx_async_abort_cmd(srb_t *, bool);
 
 extern struct fw_blob *qla2x00_request_firmware(scsi_qla_host_t *);
 
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 446a9d6ba255..aaa4a5bbf2ff 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -2963,7 +2963,6 @@ int qla24xx_post_gpsc_work(struct scsi_qla_host *vha, fc_port_t *fcport)
 		return QLA_FUNCTION_FAILED;
 
 	e->u.fcport.fcport = fcport;
-	fcport->flags |= FCF_ASYNC_ACTIVE;
 	return qla2x00_post_work(vha, e);
 }
 
@@ -3097,9 +3096,7 @@ int qla24xx_async_gpsc(scsi_qla_host_t *vha, fc_port_t *fcport)
 
 done_free_sp:
 	sp->free(sp);
-	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
-	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	return rval;
 }
 
@@ -4290,7 +4287,7 @@ int qla24xx_async_gnnid(scsi_qla_host_t *vha, fc_port_t *fcport)
 	if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT))
 		return rval;
 
-	fcport->disc_state = DSC_GNN_ID;
+	qla2x00_set_fcport_disc_state(fcport, DSC_GNN_ID);
 	sp = qla2x00_get_sp(vha, fcport, GFP_ATOMIC);
 	if (!sp)
 		goto done;
@@ -4464,7 +4461,6 @@ int qla24xx_async_gfpnid(scsi_qla_host_t *vha, fc_port_t *fcport)
 
 done_free_sp:
 	sp->free(sp);
-	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
 	return rval;
 }
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index aa5204163bec..9e6b56527b25 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -49,16 +49,9 @@ qla2x00_sp_timeout(struct timer_list *t)
 {
 	srb_t *sp = from_timer(sp, t, u.iocb_cmd.timer);
 	struct srb_iocb *iocb;
-	struct req_que *req;
-	unsigned long flags;
-	struct qla_hw_data *ha = sp->vha->hw;
 
-	WARN_ON_ONCE(irqs_disabled());
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	req = sp->qpair->req;
-	req->outstanding_cmds[sp->handle] = NULL;
+	WARN_ON(irqs_disabled());
 	iocb = &sp->u.iocb_cmd;
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 	iocb->timeout(sp);
 }
 
@@ -142,7 +135,7 @@ static void qla24xx_abort_sp_done(srb_t *sp, int res)
 		sp->free(sp);
 }
 
-static int qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
+int qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
 {
 	scsi_qla_host_t *vha = cmd_sp->vha;
 	struct srb_iocb *abt_iocb;
@@ -242,6 +235,7 @@ qla2x00_async_iocb_timeout(void *data)
 	case SRB_NACK_PRLI:
 	case SRB_NACK_LOGO:
 	case SRB_CTRL_VP:
+	default:
 		rc = qla24xx_async_abort_cmd(sp, false);
 		if (rc) {
 			spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
@@ -258,10 +252,6 @@ qla2x00_async_iocb_timeout(void *data)
 			sp->done(sp, QLA_FUNCTION_TIMEOUT);
 		}
 		break;
-	default:
-		WARN_ON_ONCE(true);
-		sp->done(sp, QLA_FUNCTION_TIMEOUT);
-		break;
 	}
 }
 
@@ -326,10 +316,10 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	if (!sp)
 		goto done;
 
+	qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_PEND);
 	fcport->flags |= FCF_ASYNC_SENT;
 	fcport->logout_completed = 0;
 
-	fcport->disc_state = DSC_LOGIN_PEND;
 	sp->type = SRB_LOGIN_CMD;
 	sp->name = "login";
 	sp->gen1 = fcport->rscn_gen;
@@ -425,7 +415,7 @@ qla2x00_async_prlo_done(struct scsi_qla_host *vha, fc_port_t *fcport,
 	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	/* Don't re-login in target mode */
 	if (!fcport->tgt_session)
-		qla2x00_mark_device_lost(vha, fcport, 1, 0);
+		qla2x00_mark_device_lost(vha, fcport, 1);
 	qlt_logo_completion_handler(fcport, data[0]);
 }
 
@@ -533,7 +523,7 @@ static int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport)
 
 	e->u.fcport.fcport = fcport;
 	fcport->flags |= FCF_ASYNC_ACTIVE;
-	fcport->disc_state = DSC_LOGIN_PEND;
+	qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_PEND);
 	return qla2x00_post_work(vha, e);
 }
 
@@ -685,7 +675,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 	port_id_t id;
 	u64 wwn;
 	u16 data[2];
-	u8 current_login_state;
+	u8 current_login_state, nvme_cls;
 
 	fcport = ea->fcport;
 	ql_dbg(ql_dbg_disc, vha, 0xffff,
@@ -744,10 +734,17 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 
 		loop_id = le16_to_cpu(e->nport_handle);
 		loop_id = (loop_id & 0x7fff);
-		if (NVME_TARGET(vha->hw, fcport))
-			current_login_state = e->current_login_state >> 4;
-		else
-			current_login_state = e->current_login_state & 0xf;
+		nvme_cls = e->current_login_state >> 4;
+		current_login_state = e->current_login_state & 0xf;
+
+		if (PRLI_PHASE(nvme_cls)) {
+			current_login_state = nvme_cls;
+			fcport->fc4_type &= ~FS_FC4TYPE_FCP;
+			fcport->fc4_type |= FS_FC4TYPE_NVME;
+		} else if (PRLI_PHASE(current_login_state)) {
+			fcport->fc4_type |= FS_FC4TYPE_FCP;
+			fcport->fc4_type &= ~FS_FC4TYPE_NVME;
+		}
 
 		ql_dbg(ql_dbg_disc, vha, 0x20e2,
 		    "%s found %8phC CLS [%x|%x] fc4_type %d ID[%06x|%06x] lid[%d|%d]\n",
@@ -836,7 +833,8 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 				 * with GNL. Push disc_state back to DELETED
 				 * so GNL can go out again
 				 */
-				fcport->disc_state = DSC_DELETED;
+				qla2x00_set_fcport_disc_state(fcport,
+				    DSC_DELETED);
 				break;
 			case DSC_LS_PRLI_COMP:
 				if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
@@ -912,7 +910,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			qla24xx_fcport_handle_login(vha, fcport);
 			break;
 		case ISP_CFG_N:
-			fcport->disc_state = DSC_DELETED;
+			qla2x00_set_fcport_disc_state(fcport, DSC_DELETED);
 			if (time_after_eq(jiffies, fcport->dm_login_expire)) {
 				if (fcport->n2n_link_reset_cnt < 2) {
 					fcport->n2n_link_reset_cnt++;
@@ -992,7 +990,7 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res)
 		set_bit(loop_id, vha->hw->loop_id_map);
 		wwn = wwn_to_u64(e->port_name);
 
-		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x20e8,
+		ql_dbg(ql_dbg_disc, vha, 0x20e8,
 		    "%s %8phC %02x:%02x:%02x CLS %x/%x lid %x \n",
 		    __func__, (void *)&wwn, e->port_id[2], e->port_id[1],
 		    e->port_id[0], e->current_login_state, e->last_login_state,
@@ -1051,6 +1049,16 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res)
 
 	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 	vha->gnl.sent = 0;
+	if (!list_empty(&vha->gnl.fcports)) {
+		/* retrigger gnl */
+		list_for_each_entry_safe(fcport, tf, &vha->gnl.fcports,
+		    gnl_entry) {
+			list_del_init(&fcport->gnl_entry);
+			fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+			if (qla24xx_post_gnl_work(vha, fcport) == QLA_SUCCESS)
+				break;
+		}
+	}
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
 	sp->free(sp);
@@ -1072,7 +1080,7 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
 
 	spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 	fcport->flags |= FCF_ASYNC_SENT;
-	fcport->disc_state = DSC_GNL;
+	qla2x00_set_fcport_disc_state(fcport, DSC_GNL);
 	fcport->last_rscn_gen = fcport->rscn_gen;
 	fcport->last_login_gen = fcport->login_gen;
 
@@ -1121,8 +1129,8 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
 
 done_free_sp:
 	sp->free(sp);
-	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
+	fcport->flags &= ~(FCF_ASYNC_ACTIVE | FCF_ASYNC_SENT);
 	return rval;
 }
 
@@ -1216,12 +1224,19 @@ qla24xx_async_prli(struct scsi_qla_host *vha, fc_port_t *fcport)
 	struct srb_iocb *lio;
 	int rval = QLA_FUNCTION_FAILED;
 
-	if (!vha->flags.online)
+	if (!vha->flags.online) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC exit\n",
+		    __func__, __LINE__, fcport->port_name);
 		return rval;
+	}
 
-	if (fcport->fw_login_state == DSC_LS_PLOGI_PEND ||
-	    fcport->fw_login_state == DSC_LS_PRLI_PEND)
+	if ((fcport->fw_login_state == DSC_LS_PLOGI_PEND ||
+	    fcport->fw_login_state == DSC_LS_PRLI_PEND) &&
+	    qla_dual_mode_enabled(vha)) {
+		ql_dbg(ql_dbg_disc, vha, 0xffff, "%s %d %8phC exit\n",
+		    __func__, __LINE__, fcport->port_name);
 		return rval;
+	}
 
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
@@ -1295,12 +1310,12 @@ int qla24xx_async_gpdb(struct scsi_qla_host *vha, fc_port_t *fcport, u8 opt)
 		return rval;
 	}
 
-	fcport->disc_state = DSC_GPDB;
-
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp)
 		goto done;
 
+	qla2x00_set_fcport_disc_state(fcport, DSC_GPDB);
+
 	fcport->flags |= FCF_ASYNC_SENT;
 	sp->type = SRB_MB_IOCB;
 	sp->name = "gpdb";
@@ -1349,6 +1364,7 @@ done_free_sp:
 	sp->free(sp);
 	fcport->flags &= ~FCF_ASYNC_SENT;
 done:
+	fcport->flags &= ~FCF_ASYNC_ACTIVE;
 	qla24xx_post_gpdb_work(vha, fcport, opt);
 	return rval;
 }
@@ -1379,7 +1395,7 @@ void __qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 		ql_dbg(ql_dbg_disc, vha, 0x20d6,
 		    "%s %d %8phC session revalidate success\n",
 		    __func__, __LINE__, ea->fcport->port_name);
-		ea->fcport->disc_state = DSC_LOGIN_COMPLETE;
+		qla2x00_set_fcport_disc_state(ea->fcport, DSC_LOGIN_COMPLETE);
 	}
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 }
@@ -1433,7 +1449,7 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 		/* Set discovery state back to GNL to Relogin attempt */
 		if (qla_dual_mode_enabled(vha) ||
 		    qla_ini_mode_enabled(vha)) {
-			fcport->disc_state = DSC_GNL;
+			qla2x00_set_fcport_disc_state(fcport, DSC_GNL);
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 		}
 		return;
@@ -1600,6 +1616,10 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 			break;
 		default:
 			if (fcport->login_pause) {
+				ql_dbg(ql_dbg_disc, vha, 0x20d8,
+				    "%s %d %8phC exit\n",
+				    __func__, __LINE__,
+				    fcport->port_name);
 				fcport->last_rscn_gen = fcport->rscn_gen;
 				fcport->last_login_gen = fcport->login_gen;
 				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
@@ -1758,9 +1778,23 @@ qla2x00_tmf_iocb_timeout(void *data)
 {
 	srb_t *sp = data;
 	struct srb_iocb *tmf = &sp->u.iocb_cmd;
+	int rc, h;
+	unsigned long flags;
 
-	tmf->u.tmf.comp_status = CS_TIMEOUT;
-	complete(&tmf->u.tmf.comp);
+	rc = qla24xx_async_abort_cmd(sp, false);
+	if (rc) {
+		spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+		for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) {
+			if (sp->qpair->req->outstanding_cmds[h] == sp) {
+				sp->qpair->req->outstanding_cmds[h] = NULL;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+		tmf->u.tmf.comp_status = CS_TIMEOUT;
+		tmf->u.tmf.data = QLA_FUNCTION_FAILED;
+		complete(&tmf->u.tmf.comp);
+	}
 }
 
 static void qla2x00_tmf_sp_done(srb_t *sp, int res)
@@ -1976,7 +2010,7 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 			qla24xx_post_prli_work(vha, ea->fcport);
 		} else {
 			ql_dbg(ql_dbg_disc, vha, 0x20ea,
-			    "%s %d %8phC LoopID 0x%x in use with %06x. post gnl\n",
+			    "%s %d %8phC LoopID 0x%x in use with %06x. post gpdb\n",
 			    __func__, __LINE__, ea->fcport->port_name,
 			    ea->fcport->loop_id, ea->fcport->d_id.b24);
 
@@ -1996,11 +2030,11 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 		    __func__, __LINE__, ea->fcport->port_name, ea->data[1]);
 
 		ea->fcport->flags &= ~FCF_ASYNC_SENT;
-		ea->fcport->disc_state = DSC_LOGIN_FAILED;
+		qla2x00_set_fcport_disc_state(ea->fcport, DSC_LOGIN_FAILED);
 		if (ea->data[1] & QLA_LOGIO_LOGIN_RETRIED)
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 		else
-			qla2x00_mark_device_lost(vha, ea->fcport, 1, 0);
+			qla2x00_mark_device_lost(vha, ea->fcport, 1);
 		break;
 	case MBS_LOOP_ID_USED:
 		/* data[1] = IO PARAM 1 = nport ID  */
@@ -2047,6 +2081,7 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 			set_bit(lid, vha->hw->loop_id_map);
 			ea->fcport->loop_id = lid;
 			ea->fcport->keep_nport_handle = 0;
+			ea->fcport->logout_on_delete = 1;
 			qlt_schedule_sess_for_deletion(ea->fcport);
 		}
 		break;
@@ -2054,16 +2089,6 @@ qla24xx_handle_plogi_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 	return;
 }
 
-void
-qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
-    uint16_t *data)
-{
-	qlt_logo_completion_handler(fcport, data[0]);
-	fcport->login_gen++;
-	fcport->flags &= ~FCF_ASYNC_ACTIVE;
-	return;
-}
-
 /****************************************************************************/
 /*                QLogic ISP2x00 Hardware Support Functions.                */
 /****************************************************************************/
@@ -4925,12 +4950,8 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 	qla2x00_get_data_rate(vha);
 
 	/* Determine what we need to do */
-	if (ha->current_topology == ISP_CFG_FL &&
-	    (test_bit(LOCAL_LOOP_UPDATE, &flags))) {
-
-		set_bit(RSCN_UPDATE, &flags);
-
-	} else if (ha->current_topology == ISP_CFG_F &&
+	if ((ha->current_topology == ISP_CFG_FL ||
+	    ha->current_topology == ISP_CFG_F) &&
 	    (test_bit(LOCAL_LOOP_UPDATE, &flags))) {
 
 		set_bit(RSCN_UPDATE, &flags);
@@ -5087,7 +5108,7 @@ skip_login:
 	rval = qla2x00_get_id_list(vha, ha->gid_list, ha->gid_list_dma,
 	    &entries);
 	if (rval != QLA_SUCCESS)
-		goto cleanup_allocation;
+		goto err;
 
 	ql_dbg(ql_dbg_disc, vha, 0x2011,
 	    "Entries in ID list (%d).\n", entries);
@@ -5117,7 +5138,7 @@ skip_login:
 		ql_log(ql_log_warn, vha, 0x2012,
 		    "Memory allocation failed for fcport.\n");
 		rval = QLA_MEMORY_ALLOC_FAILED;
-		goto cleanup_allocation;
+		goto err;
 	}
 	new_fcport->flags &= ~FCF_FABRIC_DEVICE;
 
@@ -5207,7 +5228,7 @@ skip_login:
 				ql_log(ql_log_warn, vha, 0xd031,
 				    "Failed to allocate memory for fcport.\n");
 				rval = QLA_MEMORY_ALLOC_FAILED;
-				goto cleanup_allocation;
+				goto err;
 			}
 			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 			new_fcport->flags &= ~FCF_FABRIC_DEVICE;
@@ -5230,7 +5251,7 @@ skip_login:
 			    qla_ini_mode_enabled(vha)) &&
 			    atomic_read(&fcport->state) == FCS_ONLINE) {
 				qla2x00_mark_device_lost(vha, fcport,
-					ql2xplogiabsentdevice, 0);
+					ql2xplogiabsentdevice);
 				if (fcport->loop_id != FC_NO_LOOP_ID &&
 				    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
 				    fcport->port_type != FCT_INITIATOR &&
@@ -5250,15 +5271,14 @@ skip_login:
 			qla24xx_fcport_handle_login(vha, fcport);
 	}
 
-cleanup_allocation:
-	kfree(new_fcport);
+	qla2x00_free_fcport(new_fcport);
 
-	if (rval != QLA_SUCCESS) {
-		ql_dbg(ql_dbg_disc, vha, 0x2098,
-		    "Configure local loop error exit: rval=%x.\n", rval);
-	}
+	return rval;
 
-	return (rval);
+err:
+	ql_dbg(ql_dbg_disc, vha, 0x2098,
+	       "Configure local loop error exit: rval=%x.\n", rval);
+	return rval;
 }
 
 static void
@@ -5385,11 +5405,14 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	ql_dbg(ql_dbg_disc, vha, 0x20ef, "%s %8phC\n",
 	    __func__, fcport->port_name);
 
-	fcport->disc_state = DSC_UPD_FCPORT;
+	qla2x00_set_fcport_disc_state(fcport, DSC_UPD_FCPORT);
 	fcport->login_retry = vha->hw->login_retry_count;
 	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
 	fcport->deleted = 0;
-	fcport->logout_on_delete = 1;
+	if (vha->hw->current_topology == ISP_CFG_NL)
+		fcport->logout_on_delete = 0;
+	else
+		fcport->logout_on_delete = 1;
 	fcport->n2n_chip_reset = fcport->n2n_link_reset_cnt = 0;
 
 	switch (vha->hw->current_topology) {
@@ -5405,7 +5428,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 
 	if (NVME_TARGET(vha->hw, fcport)) {
 		qla_nvme_register_remote(vha, fcport);
-		fcport->disc_state = DSC_LOGIN_COMPLETE;
+		qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_COMPLETE);
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 		return;
 	}
@@ -5450,7 +5473,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 		}
 	}
 
-	fcport->disc_state = DSC_LOGIN_COMPLETE;
+	qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_COMPLETE);
 }
 
 void qla_register_fcport_fn(struct work_struct *work)
@@ -5859,7 +5882,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 
 		if (NVME_TARGET(vha->hw, fcport)) {
 			if (fcport->disc_state == DSC_DELETE_PEND) {
-				fcport->disc_state = DSC_GNL;
+				qla2x00_set_fcport_disc_state(fcport, DSC_GNL);
 				vha->fcport_count--;
 				fcport->login_succ = 0;
 			}
@@ -5905,7 +5928,7 @@ qla2x00_find_all_fabric_devs(scsi_qla_host_t *vha)
 			    qla_ini_mode_enabled(vha)) &&
 			    atomic_read(&fcport->state) == FCS_ONLINE) {
 				qla2x00_mark_device_lost(vha, fcport,
-					ql2xplogiabsentdevice, 0);
+					ql2xplogiabsentdevice);
 				if (fcport->loop_id != FC_NO_LOOP_ID &&
 				    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
 				    fcport->port_type != FCT_INITIATOR &&
@@ -6071,7 +6094,7 @@ qla2x00_fabric_login(scsi_qla_host_t *vha, fc_port_t *fcport,
 			ha->isp_ops->fabric_logout(vha, fcport->loop_id,
 			    fcport->d_id.b.domain, fcport->d_id.b.area,
 			    fcport->d_id.b.al_pa);
-			qla2x00_mark_device_lost(vha, fcport, 1, 0);
+			qla2x00_mark_device_lost(vha, fcport, 1);
 
 			rval = 1;
 			break;
@@ -6585,9 +6608,9 @@ qla2x00_quiesce_io(scsi_qla_host_t *vha)
 	atomic_set(&ha->loop_down_timer, LOOP_DOWN_TIME);
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
-		qla2x00_mark_all_devices_lost(vha, 0);
+		qla2x00_mark_all_devices_lost(vha);
 		list_for_each_entry(vp, &ha->vp_list, list)
-			qla2x00_mark_all_devices_lost(vp, 0);
+			qla2x00_mark_all_devices_lost(vp);
 	} else {
 		if (!atomic_read(&vha->loop_down_timer))
 			atomic_set(&vha->loop_down_timer,
@@ -6663,14 +6686,14 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
-		qla2x00_mark_all_devices_lost(vha, 0);
+		qla2x00_mark_all_devices_lost(vha);
 
 		spin_lock_irqsave(&ha->vport_slock, flags);
 		list_for_each_entry(vp, &ha->vp_list, list) {
 			atomic_inc(&vp->vref_count);
 			spin_unlock_irqrestore(&ha->vport_slock, flags);
 
-			qla2x00_mark_all_devices_lost(vp, 0);
+			qla2x00_mark_all_devices_lost(vp);
 
 			spin_lock_irqsave(&ha->vport_slock, flags);
 			atomic_dec(&vp->vref_count);
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 352aba4127f7..364b3db8b2dc 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -105,6 +105,30 @@ qla2x00_clean_dsd_pool(struct qla_hw_data *ha, struct crc_context *ctx)
 	INIT_LIST_HEAD(&ctx->dsd_list);
 }
 
+static inline void
+qla2x00_set_fcport_disc_state(fc_port_t *fcport, int state)
+{
+	int old_val;
+	uint8_t shiftbits, mask;
+
+	/* This will have to change when the max no. of states > 16 */
+	shiftbits = 4;
+	mask = (1 << shiftbits) - 1;
+
+	fcport->disc_state = state;
+	while (1) {
+		old_val = atomic_read(&fcport->shadow_disc_state);
+		if (old_val == atomic_cmpxchg(&fcport->shadow_disc_state,
+		    old_val, (old_val << shiftbits) | state)) {
+			ql_dbg(ql_dbg_disc, fcport->vha, 0x2134,
+			    "FCPort %8phC disc_state transition: %s to %s - portid=%06x.\n",
+			    fcport->port_name, port_dstate_str[old_val & mask],
+			    port_dstate_str[state], fcport->d_id.b24);
+			return;
+		}
+	}
+}
+
 static inline int
 qla2x00_hba_err_chk_enabled(srb_t *sp)
 {
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 8b050f0b4333..47bf60a9490a 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2537,13 +2537,32 @@ qla2x00_els_dcmd_iocb_timeout(void *data)
 	fc_port_t *fcport = sp->fcport;
 	struct scsi_qla_host *vha = sp->vha;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
+	unsigned long flags = 0;
+	int res, h;
 
 	ql_dbg(ql_dbg_io, vha, 0x3069,
 	    "%s Timeout, hdl=%x, portid=%02x%02x%02x\n",
 	    sp->name, sp->handle, fcport->d_id.b.domain, fcport->d_id.b.area,
 	    fcport->d_id.b.al_pa);
 
-	complete(&lio->u.els_logo.comp);
+	/* Abort the exchange */
+	res = qla24xx_async_abort_cmd(sp, false);
+	if (res) {
+		ql_dbg(ql_dbg_io, vha, 0x3070,
+		    "mbx abort_command failed.\n");
+		spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+		for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) {
+			if (sp->qpair->req->outstanding_cmds[h] == sp) {
+				sp->qpair->req->outstanding_cmds[h] = NULL;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+		complete(&lio->u.els_logo.comp);
+	} else {
+		ql_dbg(ql_dbg_io, vha, 0x3071,
+		    "mbx abort_command success.\n");
+	}
 }
 
 static void qla2x00_els_dcmd_sp_done(srb_t *sp, int res)
@@ -2717,23 +2736,29 @@ qla2x00_els_dcmd2_iocb_timeout(void *data)
 	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
 	struct scsi_qla_host *vha = sp->vha;
-	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags = 0;
-	int res;
+	int res, h;
 
 	ql_dbg(ql_dbg_io + ql_dbg_disc, vha, 0x3069,
 	    "%s hdl=%x ELS Timeout, %8phC portid=%06x\n",
 	    sp->name, sp->handle, fcport->port_name, fcport->d_id.b24);
 
 	/* Abort the exchange */
-	spin_lock_irqsave(&ha->hardware_lock, flags);
-	res = ha->isp_ops->abort_command(sp);
+	res = qla24xx_async_abort_cmd(sp, false);
 	ql_dbg(ql_dbg_io, vha, 0x3070,
 	    "mbx abort_command %s\n",
 	    (res == QLA_SUCCESS) ? "successful" : "failed");
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
-
-	sp->done(sp, QLA_FUNCTION_TIMEOUT);
+	if (res) {
+		spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+		for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) {
+			if (sp->qpair->req->outstanding_cmds[h] == sp) {
+				sp->qpair->req->outstanding_cmds[h] = NULL;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+		sp->done(sp, QLA_FUNCTION_TIMEOUT);
+	}
 }
 
 void qla2x00_els_dcmd2_free(scsi_qla_host_t *vha, struct els_plogi *els_plogi)
@@ -2852,7 +2877,8 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 				    fw_status[0], fw_status[1], fw_status[2]);
 
 				fcport->flags &= ~FCF_ASYNC_SENT;
-				fcport->disc_state = DSC_LOGIN_FAILED;
+				qla2x00_set_fcport_disc_state(fcport,
+				    DSC_LOGIN_FAILED);
 				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 				break;
 			}
@@ -2865,7 +2891,7 @@ static void qla2x00_els_dcmd2_sp_done(srb_t *sp, int res)
 			    fw_status[0], fw_status[1], fw_status[2]);
 
 			sp->fcport->flags &= ~FCF_ASYNC_SENT;
-			sp->fcport->disc_state = DSC_LOGIN_FAILED;
+			qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_FAILED);
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 			break;
 		}
@@ -2898,11 +2924,12 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	if (!sp) {
 		ql_log(ql_log_info, vha, 0x70e6,
 		 "SRB allocation failed\n");
+		fcport->flags &= ~FCF_ASYNC_ACTIVE;
 		return -ENOMEM;
 	}
 
 	fcport->flags |= FCF_ASYNC_SENT;
-	fcport->disc_state = DSC_LOGIN_PEND;
+	qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_PEND);
 	elsio = &sp->u.iocb_cmd;
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	    "Enter: PLOGI portid=%06x\n", fcport->d_id.b24);
@@ -2975,7 +3002,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	}
 
 out:
-	fcport->flags &= ~(FCF_ASYNC_SENT);
+	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 	qla2x00_els_dcmd2_free(vha, &elsio->u.els_plogi);
 	sp->free(sp);
 done:
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 7b8a6bfcf08d..e7bad0bfffda 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -788,7 +788,7 @@ skip_rio:
 		if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 			atomic_set(&vha->loop_state, LOOP_DOWN);
 			atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
-			qla2x00_mark_all_devices_lost(vha, 1);
+			qla2x00_mark_all_devices_lost(vha);
 		}
 
 		if (vha->vp_idx) {
@@ -861,7 +861,7 @@ skip_rio:
 			}
 
 			vha->device_flags |= DFLG_NO_CABLE;
-			qla2x00_mark_all_devices_lost(vha, 1);
+			qla2x00_mark_all_devices_lost(vha);
 		}
 
 		if (vha->vp_idx) {
@@ -881,7 +881,7 @@ skip_rio:
 		if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 			atomic_set(&vha->loop_state, LOOP_DOWN);
 			atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
-			qla2x00_mark_all_devices_lost(vha, 1);
+			qla2x00_mark_all_devices_lost(vha);
 		}
 
 		if (vha->vp_idx) {
@@ -924,7 +924,7 @@ skip_rio:
 				atomic_set(&vha->loop_down_timer,
 				    LOOP_DOWN_TIME);
 			if (!N2N_TOPO(ha))
-				qla2x00_mark_all_devices_lost(vha, 1);
+				qla2x00_mark_all_devices_lost(vha);
 		}
 
 		if (vha->vp_idx) {
@@ -953,7 +953,7 @@ skip_rio:
 			if (!atomic_read(&vha->loop_down_timer))
 				atomic_set(&vha->loop_down_timer,
 				    LOOP_DOWN_TIME);
-			qla2x00_mark_all_devices_lost(vha, 1);
+			qla2x00_mark_all_devices_lost(vha);
 		}
 
 		if (vha->vp_idx) {
@@ -1022,7 +1022,6 @@ skip_rio:
 			    "Marking port lost loopid=%04x portid=%06x.\n",
 			    fcport->loop_id, fcport->d_id.b24);
 			if (qla_ini_mode_enabled(vha)) {
-				qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1);
 				fcport->logout_on_delete = 0;
 				qlt_schedule_sess_for_deletion(fcport);
 			}
@@ -1034,14 +1033,14 @@ global_port_update:
 				atomic_set(&vha->loop_down_timer,
 				    LOOP_DOWN_TIME);
 				vha->device_flags |= DFLG_NO_CABLE;
-				qla2x00_mark_all_devices_lost(vha, 1);
+				qla2x00_mark_all_devices_lost(vha);
 			}
 
 			if (vha->vp_idx) {
 				atomic_set(&vha->vp_state, VP_FAILED);
 				fc_vport_set_state(vha->fc_vport,
 				    FC_VPORT_FAILED);
-				qla2x00_mark_all_devices_lost(vha, 1);
+				qla2x00_mark_all_devices_lost(vha);
 			}
 
 			vha->flags.management_server_logged_in = 0;
@@ -1253,11 +1252,33 @@ global_port_update:
 
 	case MBA_DPORT_DIAGNOSTICS:
 		ql_dbg(ql_dbg_async, vha, 0x5052,
-		    "D-Port Diagnostics: %04x result=%s\n",
-		    mb[0],
-		    mb[1] == 0 ? "start" :
-		    mb[1] == 1 ? "done (pass)" :
-		    mb[1] == 2 ? "done (error)" : "other");
+		    "D-Port Diagnostics: %04x %04x %04x %04x\n",
+		    mb[0], mb[1], mb[2], mb[3]);
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
+			static char *results[] = {
+			    "start", "done(pass)", "done(error)", "undefined" };
+			static char *types[] = {
+			    "none", "dynamic", "static", "other" };
+			uint result = mb[1] >> 0 & 0x3;
+			uint type = mb[1] >> 6 & 0x3;
+			uint sw = mb[1] >> 15 & 0x1;
+			ql_dbg(ql_dbg_async, vha, 0x5052,
+			    "D-Port Diagnostics: result=%s type=%s [sw=%u]\n",
+			    results[result], types[type], sw);
+			if (result == 2) {
+				static char *reasons[] = {
+				    "reserved", "unexpected reject",
+				    "unexpected phase", "retry exceeded",
+				    "timed out", "not supported",
+				    "user stopped" };
+				uint reason = mb[2] >> 0 & 0xf;
+				uint phase = mb[2] >> 12 & 0xf;
+				ql_dbg(ql_dbg_async, vha, 0x5052,
+				    "D-Port Diagnostics: reason=%s phase=%u \n",
+				    reason < 7 ? reasons[reason] : "other",
+				    phase >> 1);
+			}
+		}
 		break;
 
 	case MBA_TEMPERATURE_ALERT:
@@ -2152,12 +2173,12 @@ qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24)
 	 * swab32 of the "data" field in the beginning of qla2x00_status_entry()
 	 * would make guard field appear at offset 2
 	 */
-	a_guard   = le16_to_cpu(*(uint16_t *)(ap + 2));
-	a_app_tag = le16_to_cpu(*(uint16_t *)(ap + 0));
-	a_ref_tag = le32_to_cpu(*(uint32_t *)(ap + 4));
-	e_guard   = le16_to_cpu(*(uint16_t *)(ep + 2));
-	e_app_tag = le16_to_cpu(*(uint16_t *)(ep + 0));
-	e_ref_tag = le32_to_cpu(*(uint32_t *)(ep + 4));
+	a_guard   = get_unaligned_le16(ap + 2);
+	a_app_tag = get_unaligned_le16(ap + 0);
+	a_ref_tag = get_unaligned_le32(ap + 4);
+	e_guard   = get_unaligned_le16(ep + 2);
+	e_app_tag = get_unaligned_le16(ep + 0);
+	e_ref_tag = get_unaligned_le32(ep + 4);
 
 	ql_dbg(ql_dbg_io, vha, 0x3023,
 	    "iocb(s) %p Returned STATUS.\n", sts24);
@@ -2745,7 +2766,6 @@ check_scsi_status:
 				port_state_str[FCS_ONLINE],
 				comp_status);
 
-			qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1);
 			qlt_schedule_sess_for_deletion(fcport);
 		}
 
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index b7c1108c48e2..9e09964f5c0e 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -6152,9 +6152,8 @@ qla2x00_dump_mctp_data(scsi_qla_host_t *vha, dma_addr_t req_dma, uint32_t addr,
 	mcp->mb[7] = LSW(MSD(req_dma));
 	mcp->mb[8] = MSW(addr);
 	/* Setting RAM ID to valid */
-	mcp->mb[10] |= BIT_7;
 	/* For MCTP RAM ID is 0x40 */
-	mcp->mb[10] |= 0x40;
+	mcp->mb[10] = BIT_7 | 0x40;
 
 	mcp->out_mb |= MBX_10|MBX_8|MBX_7|MBX_6|MBX_5|MBX_4|MBX_3|MBX_2|MBX_1|
 	    MBX_0;
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index eabc5127174e..8ae639d089d1 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -147,7 +147,7 @@ qla2x00_mark_vp_devices_dead(scsi_qla_host_t *vha)
 		    "Marking port dead, loop_id=0x%04x : %x.\n",
 		    fcport->loop_id, fcport->vha->vp_idx);
 
-		qla2x00_mark_device_lost(vha, fcport, 0, 0);
+		qla2x00_mark_device_lost(vha, fcport, 0);
 		qla2x00_set_fcport_state(fcport, FCS_UNCONFIGURED);
 	}
 }
@@ -167,7 +167,7 @@ qla24xx_disable_vp(scsi_qla_host_t *vha)
 	list_for_each_entry(fcport, &vha->vp_fcports, list)
 		fcport->logout_on_delete = 0;
 
-	qla2x00_mark_all_devices_lost(vha, 0);
+	qla2x00_mark_all_devices_lost(vha);
 
 	/* Remove port id from vp target map */
 	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
@@ -327,7 +327,7 @@ qla2x00_vp_abort_isp(scsi_qla_host_t *vha)
 	 */
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
-		qla2x00_mark_all_devices_lost(vha, 0);
+		qla2x00_mark_all_devices_lost(vha);
 	} else {
 		if (!atomic_read(&vha->loop_down_timer))
 			atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index a3a44d4ace1e..cad1fc2a1b28 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -1210,9 +1210,9 @@ qlafx00_find_all_targets(scsi_qla_host_t *vha,
 				    " Existing TGT-ID %x did not get "
 				    " offline event from firmware.\n",
 				    fcport->old_tgt_id);
-				qla2x00_mark_device_lost(vha, fcport, 0, 0);
+				qla2x00_mark_device_lost(vha, fcport, 0);
 				set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
-				kfree(new_fcport);
+				qla2x00_free_fcport(new_fcport);
 				return rval;
 			}
 			break;
@@ -1230,7 +1230,7 @@ qlafx00_find_all_targets(scsi_qla_host_t *vha,
 			return QLA_MEMORY_ALLOC_FAILED;
 	}
 
-	kfree(new_fcport);
+	qla2x00_free_fcport(new_fcport);
 	return rval;
 }
 
@@ -1274,7 +1274,7 @@ qlafx00_configure_all_targets(scsi_qla_host_t *vha)
 
 		if (atomic_read(&fcport->state) == FCS_DEVICE_LOST) {
 			if (fcport->port_type != FCT_INITIATOR)
-				qla2x00_mark_device_lost(vha, fcport, 0, 0);
+				qla2x00_mark_device_lost(vha, fcport, 0);
 		}
 	}
 
@@ -1298,7 +1298,7 @@ qlafx00_configure_all_targets(scsi_qla_host_t *vha)
 	/* Free all new device structures not processed. */
 	list_for_each_entry_safe(fcport, rmptemp, &new_fcports, list) {
 		list_del(&fcport->list);
-		kfree(fcport);
+		qla2x00_free_fcport(fcport);
 	}
 
 	return rval;
@@ -1706,7 +1706,7 @@ qlafx00_tgt_detach(struct scsi_qla_host *vha, int tgt_id)
 	if (!fcport)
 		return;
 
-	qla2x00_mark_device_lost(vha, fcport, 0, 0);
+	qla2x00_mark_device_lost(vha, fcport, 0);
 
 	return;
 }
@@ -1740,7 +1740,7 @@ qlafx00_process_aen(struct scsi_qla_host *vha, struct qla_work_evt *evt)
 				set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 			} else if (evt->u.aenfx.mbx[2] == 2) {
 				vha->device_flags |= DFLG_NO_CABLE;
-				qla2x00_mark_all_devices_lost(vha, 1);
+				qla2x00_mark_all_devices_lost(vha);
 			}
 		}
 		break;
@@ -2513,7 +2513,7 @@ check_scsi_status:
 		    atomic_read(&fcport->state));
 
 		if (atomic_read(&fcport->state) == FCS_ONLINE)
-			qla2x00_mark_device_lost(fcport->vha, fcport, 1, 1);
+			qla2x00_mark_device_lost(fcport->vha, fcport, 1);
 		break;
 
 	case CS_ABORTED:
diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c
index 2b2028f2383e..185c5f34d4c1 100644
--- a/drivers/scsi/qla2xxx/qla_nx.c
+++ b/drivers/scsi/qla2xxx/qla_nx.c
@@ -1612,8 +1612,7 @@ qla82xx_get_bootld_offset(struct qla_hw_data *ha)
 	return (u8 *)&ha->hablob->fw->data[offset];
 }
 
-static __le32
-qla82xx_get_fw_size(struct qla_hw_data *ha)
+static u32 qla82xx_get_fw_size(struct qla_hw_data *ha)
 {
 	struct qla82xx_uri_data_desc *uri_desc = NULL;
 
@@ -1624,7 +1623,7 @@ qla82xx_get_fw_size(struct qla_hw_data *ha)
 			return cpu_to_le32(uri_desc->size);
 	}
 
-	return cpu_to_le32(*(u32 *)&ha->hablob->fw->data[FW_SIZE_OFFSET]);
+	return get_unaligned_le32(&ha->hablob->fw->data[FW_SIZE_OFFSET]);
 }
 
 static u8 *
@@ -1816,7 +1815,7 @@ qla82xx_fw_load_from_blob(struct qla_hw_data *ha)
 	}
 
 	flashaddr = FLASH_ADDR_START;
-	size = (__force u32)qla82xx_get_fw_size(ha) / 8;
+	size = qla82xx_get_fw_size(ha) / 8;
 	ptr64 = (u64 *)qla82xx_get_fw_offs(ha);
 
 	for (i = 0; i < size; i++) {
@@ -1883,7 +1882,7 @@ qla82xx_set_product_offset(struct qla_hw_data *ha)
 static int
 qla82xx_validate_firmware_blob(scsi_qla_host_t *vha, uint8_t fw_type)
 {
-	__le32 val;
+	uint32_t val;
 	uint32_t min_size;
 	struct qla_hw_data *ha = vha->hw;
 	const struct firmware *fw = ha->hablob->fw;
@@ -1896,8 +1895,8 @@ qla82xx_validate_firmware_blob(scsi_qla_host_t *vha, uint8_t fw_type)
 
 		min_size = QLA82XX_URI_FW_MIN_SIZE;
 	} else {
-		val = cpu_to_le32(*(u32 *)&fw->data[QLA82XX_FW_MAGIC_OFFSET]);
-		if ((__force u32)val != QLA82XX_BDINFO_MAGIC)
+		val = get_unaligned_le32(&fw->data[QLA82XX_FW_MAGIC_OFFSET]);
+		if (val != QLA82XX_BDINFO_MAGIC)
 			return -EINVAL;
 
 		min_size = QLA82XX_FW_MIN_SIZE;
@@ -3030,7 +3029,7 @@ qla8xxx_dev_failed_handler(scsi_qla_host_t *vha)
 	/* Set DEV_FAILED flag to disable timer */
 	vha->device_flags |= DFLG_DEV_FAILED;
 	qla2x00_abort_all_cmds(vha, DID_NO_CONNECT << 16);
-	qla2x00_mark_all_devices_lost(vha, 0);
+	qla2x00_mark_all_devices_lost(vha);
 	vha->flags.online = 0;
 	vha->flags.init_done = 0;
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 8b84bc4a6ac8..b520a980d1dc 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1110,7 +1110,7 @@ qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
 {
 	u8 i;
 
-	qla2x00_mark_all_devices_lost(vha, 0);
+	qla2x00_mark_all_devices_lost(vha);
 
 	for (i = 0; i < 10; i++) {
 		if (wait_event_timeout(vha->fcport_waitQ,
@@ -1667,7 +1667,7 @@ qla2x00_loop_reset(scsi_qla_host_t *vha)
 	if (ha->flags.enable_lip_full_login && !IS_CNA_CAPABLE(ha)) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
 		atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
-		qla2x00_mark_all_devices_lost(vha, 0);
+		qla2x00_mark_all_devices_lost(vha);
 		ret = qla2x00_full_login_lip(vha);
 		if (ret != QLA_SUCCESS) {
 			ql_dbg(ql_dbg_taskm, vha, 0x802d,
@@ -3854,37 +3854,21 @@ void qla2x00_free_fcports(struct scsi_qla_host *vha)
 }
 
 static inline void
-qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport,
-    int defer)
+qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
-	struct fc_rport *rport;
-	scsi_qla_host_t *base_vha;
-	unsigned long flags;
+	int now;
 
 	if (!fcport->rport)
 		return;
 
-	rport = fcport->rport;
-	if (defer) {
-		base_vha = pci_get_drvdata(vha->hw->pdev);
-		spin_lock_irqsave(vha->host->host_lock, flags);
-		fcport->drport = rport;
-		spin_unlock_irqrestore(vha->host->host_lock, flags);
-		qlt_do_generation_tick(vha, &base_vha->total_fcport_update_gen);
-		set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags);
-		qla2xxx_wake_dpc(base_vha);
-	} else {
-		int now;
-
-		if (rport) {
-			ql_dbg(ql_dbg_disc, fcport->vha, 0x2109,
-			    "%s %8phN. rport %p roles %x\n",
-			    __func__, fcport->port_name, rport,
-			    rport->roles);
-			fc_remote_port_delete(rport);
-		}
-		qlt_do_generation_tick(vha, &now);
+	if (fcport->rport) {
+		ql_dbg(ql_dbg_disc, fcport->vha, 0x2109,
+		    "%s %8phN. rport %p roles %x\n",
+		    __func__, fcport->port_name, fcport->rport,
+		    fcport->rport->roles);
+		fc_remote_port_delete(fcport->rport);
 	}
+	qlt_do_generation_tick(vha, &now);
 }
 
 /*
@@ -3897,18 +3881,18 @@ qla2x00_schedule_rport_del(struct scsi_qla_host *vha, fc_port_t *fcport,
  * Context:
  */
 void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport,
-    int do_login, int defer)
+    int do_login)
 {
 	if (IS_QLAFX00(vha->hw)) {
 		qla2x00_set_fcport_state(fcport, FCS_DEVICE_LOST);
-		qla2x00_schedule_rport_del(vha, fcport, defer);
+		qla2x00_schedule_rport_del(vha, fcport);
 		return;
 	}
 
 	if (atomic_read(&fcport->state) == FCS_ONLINE &&
 	    vha->vp_idx == fcport->vha->vp_idx) {
 		qla2x00_set_fcport_state(fcport, FCS_DEVICE_LOST);
-		qla2x00_schedule_rport_del(vha, fcport, defer);
+		qla2x00_schedule_rport_del(vha, fcport);
 	}
 	/*
 	 * We may need to retry the login, so don't change the state of the
@@ -3937,7 +3921,7 @@ void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport,
  * Context:
  */
 void
-qla2x00_mark_all_devices_lost(scsi_qla_host_t *vha, int defer)
+qla2x00_mark_all_devices_lost(scsi_qla_host_t *vha)
 {
 	fc_port_t *fcport;
 
@@ -3957,13 +3941,6 @@ qla2x00_mark_all_devices_lost(scsi_qla_host_t *vha, int defer)
 		 */
 		if (atomic_read(&fcport->state) == FCS_DEVICE_DEAD)
 			continue;
-		if (atomic_read(&fcport->state) == FCS_ONLINE) {
-			qla2x00_set_fcport_state(fcport, FCS_DEVICE_LOST);
-			if (defer)
-				qla2x00_schedule_rport_del(vha, fcport, defer);
-			else if (vha->vp_idx == fcport->vha->vp_idx)
-				qla2x00_schedule_rport_del(vha, fcport, defer);
-		}
 	}
 }
 
@@ -4965,7 +4942,6 @@ int qla2x00_post_async_##name##_work(		\
 
 qla2x00_post_async_work(login, QLA_EVT_ASYNC_LOGIN);
 qla2x00_post_async_work(logout, QLA_EVT_ASYNC_LOGOUT);
-qla2x00_post_async_work(logout_done, QLA_EVT_ASYNC_LOGOUT_DONE);
 qla2x00_post_async_work(adisc, QLA_EVT_ASYNC_ADISC);
 qla2x00_post_async_work(prlo, QLA_EVT_ASYNC_PRLO);
 qla2x00_post_async_work(prlo_done, QLA_EVT_ASYNC_PRLO_DONE);
@@ -5032,7 +5008,7 @@ void qla24xx_sched_upd_fcport(fc_port_t *fcport)
 	fcport->jiffies_at_registration = jiffies;
 	fcport->sec_since_registration = 0;
 	fcport->next_disc_state = DSC_DELETED;
-	fcport->disc_state = DSC_UPD_FCPORT;
+	qla2x00_set_fcport_disc_state(fcport, DSC_UPD_FCPORT);
 	spin_unlock_irqrestore(&fcport->vha->work_lock, flags);
 
 	queue_work(system_unbound_wq, &fcport->reg_work);
@@ -5253,10 +5229,6 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 		case QLA_EVT_ASYNC_LOGOUT:
 			rc = qla2x00_async_logout(vha, e->u.logio.fcport);
 			break;
-		case QLA_EVT_ASYNC_LOGOUT_DONE:
-			qla2x00_async_logout_done(vha, e->u.logio.fcport,
-			    e->u.logio.data);
-			break;
 		case QLA_EVT_ASYNC_ADISC:
 			qla2x00_async_adisc(vha, e->u.logio.fcport,
 			    e->u.logio.data);
@@ -6899,13 +6871,13 @@ static void qla_pci_error_cleanup(scsi_qla_host_t *vha)
 		qpair->online = 0;
 	mutex_unlock(&ha->mq_lock);
 
-	qla2x00_mark_all_devices_lost(vha, 0);
+	qla2x00_mark_all_devices_lost(vha);
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
 	list_for_each_entry(vp, &ha->vp_list, list) {
 		atomic_inc(&vp->vref_count);
 		spin_unlock_irqrestore(&ha->vport_slock, flags);
-		qla2x00_mark_all_devices_lost(vp, 0);
+		qla2x00_mark_all_devices_lost(vp);
 		spin_lock_irqsave(&ha->vport_slock, flags);
 		atomic_dec(&vp->vref_count);
 	}
@@ -7270,6 +7242,8 @@ qla2x00_module_init(void)
 	BUILD_BUG_ON(sizeof(struct sns_cmd_pkt) != 2064);
 	BUILD_BUG_ON(sizeof(struct verify_chip_entry_84xx) != 64);
 	BUILD_BUG_ON(sizeof(struct vf_evfp_entry_24xx) != 56);
+	BUILD_BUG_ON(sizeof(struct qla_flt_region) != 16);
+	BUILD_BUG_ON(sizeof(struct qla_flt_header) != 8);
 
 	/* Allocate cache for SRBs. */
 	srb_cachep = kmem_cache_create("qla2xxx_srbs", sizeof(srb_t), 0,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index bbe90354f49b..76a38bf86cbc 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -669,8 +669,8 @@ qla2xxx_get_flt_info(scsi_qla_host_t *vha, uint32_t flt_addr)
 
 	struct qla_hw_data *ha = vha->hw;
 	uint32_t def = IS_QLA81XX(ha) ? 2 : IS_QLA25XX(ha) ? 1 : 0;
-	struct qla_flt_header *flt = (void *)ha->flt;
-	struct qla_flt_region *region = (void *)&flt[1];
+	struct qla_flt_header *flt = ha->flt;
+	struct qla_flt_region *region = &flt->region[0];
 	uint16_t *wptr, cnt, chksum;
 	uint32_t start;
 
@@ -2652,18 +2652,15 @@ qla28xx_get_flash_region(struct scsi_qla_host *vha, uint32_t start,
     struct qla_flt_region *region)
 {
 	struct qla_hw_data *ha = vha->hw;
-	struct qla_flt_header *flt;
-	struct qla_flt_region *flt_reg;
+	struct qla_flt_header *flt = ha->flt;
+	struct qla_flt_region *flt_reg = &flt->region[0];
 	uint16_t cnt;
 	int rval = QLA_FUNCTION_FAILED;
 
 	if (!ha->flt)
 		return QLA_FUNCTION_FAILED;
 
-	flt = (struct qla_flt_header *)ha->flt;
-	flt_reg = (struct qla_flt_region *)&flt[1];
 	cnt = le16_to_cpu(flt->length) / sizeof(struct qla_flt_region);
-
 	for (; cnt; cnt--, flt_reg++) {
 		if (flt_reg->start == start) {
 			memcpy((uint8_t *)region, flt_reg,
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 68c14143e50e..70081b395fb2 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -596,7 +596,8 @@ static void qla2x00_async_nack_sp_done(srb_t *sp, int res)
 			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
 		} else {
 			sp->fcport->login_retry = 0;
-			sp->fcport->disc_state = DSC_LOGIN_COMPLETE;
+			qla2x00_set_fcport_disc_state(sp->fcport,
+			    DSC_LOGIN_COMPLETE);
 			sp->fcport->deleted = 0;
 			sp->fcport->logout_on_delete = 1;
 		}
@@ -957,7 +958,7 @@ void qlt_free_session_done(struct work_struct *work)
 	struct qlt_plogi_ack_t *own =
 		sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN];
 
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084,
+	ql_dbg(ql_dbg_disc, vha, 0xf084,
 		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
 		" s_id %02x:%02x:%02x logout %d keep %d els_logo %d\n",
 		__func__, sess->se_sess, sess, sess->port_name, sess->loop_id,
@@ -966,7 +967,7 @@ void qlt_free_session_done(struct work_struct *work)
 		sess->send_els_logo);
 
 	if (!IS_SW_RESV_ADDR(sess->d_id)) {
-		qla2x00_mark_device_lost(vha, sess, 0, 0);
+		qla2x00_mark_device_lost(vha, sess, 0);
 
 		if (sess->send_els_logo) {
 			qlt_port_logo_t logo;
@@ -1024,7 +1025,7 @@ void qlt_free_session_done(struct work_struct *work)
 
 		while (!READ_ONCE(sess->logout_completed)) {
 			if (!traced) {
-				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086,
+				ql_dbg(ql_dbg_disc, vha, 0xf086,
 					"%s: waiting for sess %p logout\n",
 					__func__, sess);
 				traced = true;
@@ -1045,6 +1046,10 @@ void qlt_free_session_done(struct work_struct *work)
 			(struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO);
 	}
 
+	spin_lock_irqsave(&vha->work_lock, flags);
+	sess->flags &= ~FCF_ASYNC_SENT;
+	spin_unlock_irqrestore(&vha->work_lock, flags);
+
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
 	if (sess->se_sess) {
 		sess->se_sess = NULL;
@@ -1052,7 +1057,7 @@ void qlt_free_session_done(struct work_struct *work)
 			tgt->sess_count--;
 	}
 
-	sess->disc_state = DSC_DELETED;
+	qla2x00_set_fcport_disc_state(sess, DSC_DELETED);
 	sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
 	sess->deleted = QLA_SESS_DELETED;
 
@@ -1108,7 +1113,7 @@ void qlt_free_session_done(struct work_struct *work)
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
 	sess->free_pending = 0;
 
-	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
+	ql_dbg(ql_dbg_disc, vha, 0xf001,
 	    "Unregistration of sess %p %8phC finished fcp_cnt %d\n",
 		sess, sess->port_name, vha->fcport_count);
 
@@ -1151,13 +1156,18 @@ void qlt_unreg_sess(struct fc_port *sess)
 		return;
 	}
 	sess->free_pending = 1;
+	/*
+	 * Use FCF_ASYNC_SENT flag to block other cmds used in sess
+	 * management from being sent.
+	 */
+	sess->flags |= FCF_ASYNC_SENT;
 	spin_unlock_irqrestore(&sess->vha->work_lock, flags);
 
 	if (sess->se_sess)
 		vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
-	sess->disc_state = DSC_DELETE_PEND;
+	qla2x00_set_fcport_disc_state(sess, DSC_DELETE_PEND);
 	sess->last_rscn_gen = sess->rscn_gen;
 	sess->last_login_gen = sess->login_gen;
 
@@ -1257,7 +1267,8 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess)
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 	spin_unlock_irqrestore(&sess->vha->work_lock, flags);
 
-	sess->disc_state = DSC_DELETE_PEND;
+	sess->prli_pend_timer = 0;
+	qla2x00_set_fcport_disc_state(sess, DSC_DELETE_PEND);
 
 	qla24xx_chk_fcp_state(sess);
 
@@ -3446,13 +3457,13 @@ qlt_handle_dif_error(struct qla_qpair *qpair, struct qla_tgt_cmd *cmd,
 
 	cmd->trc_flags |= TRC_DIF_ERR;
 
-	cmd->a_guard   = be16_to_cpu(*(uint16_t *)(ap + 0));
-	cmd->a_app_tag = be16_to_cpu(*(uint16_t *)(ap + 2));
-	cmd->a_ref_tag = be32_to_cpu(*(uint32_t *)(ap + 4));
+	cmd->a_guard   = get_unaligned_be16(ap + 0);
+	cmd->a_app_tag = get_unaligned_be16(ap + 2);
+	cmd->a_ref_tag = get_unaligned_be32(ap + 4);
 
-	cmd->e_guard   = be16_to_cpu(*(uint16_t *)(ep + 0));
-	cmd->e_app_tag = be16_to_cpu(*(uint16_t *)(ep + 2));
-	cmd->e_ref_tag = be32_to_cpu(*(uint32_t *)(ep + 4));
+	cmd->e_guard   = get_unaligned_be16(ep + 0);
+	cmd->e_app_tag = get_unaligned_be16(ep + 2);
+	cmd->e_ref_tag = get_unaligned_be32(ep + 4);
 
 	ql_dbg(ql_dbg_tgt_dif, vha, 0xf075,
 	    "%s: aborted %d state %d\n", __func__, cmd->aborted, cmd->state);
@@ -4579,7 +4590,7 @@ qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn,
 		/* find other sess with nport_id collision */
 		if (port_id.b24 == other_sess->d_id.b24) {
 			if (loop_id != other_sess->loop_id) {
-				ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000c,
+				ql_dbg(ql_dbg_disc, vha, 0x1000c,
 				    "Invalidating sess %p loop_id %d wwn %llx.\n",
 				    other_sess, other_sess->loop_id, other_wwn);
 
@@ -4595,7 +4606,7 @@ qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn,
 				 * Another wwn used to have our s_id/loop_id
 				 * kill the session, but don't free the loop_id
 				 */
-				ql_dbg(ql_dbg_tgt_tmr, vha, 0xf01b,
+				ql_dbg(ql_dbg_disc, vha, 0xf01b,
 				    "Invalidating sess %p loop_id %d wwn %llx.\n",
 				    other_sess, other_sess->loop_id, other_wwn);
 
@@ -4610,7 +4621,7 @@ qlt_find_sess_invalidate_other(scsi_qla_host_t *vha, uint64_t wwn,
 		/* find other sess with nport handle collision */
 		if ((loop_id == other_sess->loop_id) &&
 			(loop_id != FC_NO_LOOP_ID)) {
-			ql_dbg(ql_dbg_tgt_tmr, vha, 0x1000d,
+			ql_dbg(ql_dbg_disc, vha, 0x1000d,
 			       "Invalidating sess %p loop_id %d wwn %llx.\n",
 			       other_sess, other_sess->loop_id, other_wwn);
 
@@ -6053,7 +6064,7 @@ static fc_port_t *qlt_get_port_database(struct scsi_qla_host *vha,
 		if (!IS_SW_RESV_ADDR(fcport->d_id))
 		   vha->fcport_count++;
 		fcport->login_gen++;
-		fcport->disc_state = DSC_LOGIN_COMPLETE;
+		qla2x00_set_fcport_disc_state(fcport, DSC_LOGIN_COMPLETE);
 		fcport->login_succ = 1;
 		newfcport = 1;
 	}
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index d006f0a97b8c..6539499e9e95 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -379,8 +379,7 @@ static inline int get_datalen_for_atio(struct atio_from_isp *atio)
 {
 	int len = atio->u.isp24.fcp_cmnd.add_cdb_len;
 
-	return (be32_to_cpu(get_unaligned((uint32_t *)
-	    &atio->u.isp24.fcp_cmnd.add_cdb[len * 4])));
+	return get_unaligned_be32(&atio->u.isp24.fcp_cmnd.add_cdb[len * 4]);
 }
 
 #define CTIO_TYPE7 0x12 /* Continue target I/O entry (for 24xx) */
diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 03bd3b712b77..bb03c022e023 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,7 +7,7 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "10.01.00.21-k"
+#define QLA2XXX_VERSION      "10.01.00.22-k"
 
 #define QLA_DRIVER_MAJOR_VER	10
 #define QLA_DRIVER_MINOR_VER	1
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 2323432a0edb..5504ab11decc 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -4145,7 +4145,7 @@ static void qla4xxx_mem_free(struct scsi_qla_host *ha)
 		dma_free_coherent(&ha->pdev->dev, ha->queues_len, ha->queues,
 				  ha->queues_dma);
 
-	 if (ha->fw_dump)
+	if (ha->fw_dump)
 		vfree(ha->fw_dump);
 
 	ha->queues_len = 0;
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index df14597752ec..eed31021e788 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -736,13 +736,12 @@ out:
 	return err;
 }
 
-static const struct file_operations scsi_devinfo_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= proc_scsi_devinfo_open,
-	.read		= seq_read,
-	.write		= proc_scsi_devinfo_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops scsi_devinfo_proc_ops = {
+	.proc_open	= proc_scsi_devinfo_open,
+	.proc_read	= seq_read,
+	.proc_write	= proc_scsi_devinfo_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 #endif /* CONFIG_SCSI_PROC_FS */
 
@@ -867,7 +866,7 @@ int __init scsi_init_devinfo(void)
 	}
 
 #ifdef CONFIG_SCSI_PROC_FS
-	p = proc_create("scsi/device_info", 0, NULL, &scsi_devinfo_proc_fops);
+	p = proc_create("scsi/device_info", 0, NULL, &scsi_devinfo_proc_ops);
 	if (!p) {
 		error = -ENOMEM;
 		goto out;
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 57bcd05605bf..8f3af87b6bb0 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -189,17 +189,7 @@ static int scsi_ioctl_get_pci(struct scsi_device *sdev, void __user *arg)
 }
 
 
-/**
- * scsi_ioctl - Dispatch ioctl to scsi device
- * @sdev: scsi device receiving ioctl
- * @cmd: which ioctl is it
- * @arg: data associated with ioctl
- *
- * Description: The scsi_ioctl() function differs from most ioctls in that it
- * does not take a major/minor number as the dev field.  Rather, it takes
- * a pointer to a &struct scsi_device.
- */
-int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
+static int scsi_ioctl_common(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	char scsi_cmd[MAX_COMMAND_SIZE];
 	struct scsi_sense_hdr sense_hdr;
@@ -266,14 +256,50 @@ int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
                 return scsi_ioctl_get_pci(sdev, arg);
 	case SG_SCSI_RESET:
 		return scsi_ioctl_reset(sdev, arg);
-	default:
-		if (sdev->host->hostt->ioctl)
-			return sdev->host->hostt->ioctl(sdev, cmd, arg);
 	}
+	return -ENOIOCTLCMD;
+}
+
+/**
+ * scsi_ioctl - Dispatch ioctl to scsi device
+ * @sdev: scsi device receiving ioctl
+ * @cmd: which ioctl is it
+ * @arg: data associated with ioctl
+ *
+ * Description: The scsi_ioctl() function differs from most ioctls in that it
+ * does not take a major/minor number as the dev field.  Rather, it takes
+ * a pointer to a &struct scsi_device.
+ */
+int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
+{
+	int ret = scsi_ioctl_common(sdev, cmd, arg);
+
+	if (ret != -ENOIOCTLCMD)
+		return ret;
+
+	if (sdev->host->hostt->ioctl)
+		return sdev->host->hostt->ioctl(sdev, cmd, arg);
+
 	return -EINVAL;
 }
 EXPORT_SYMBOL(scsi_ioctl);
 
+#ifdef CONFIG_COMPAT
+int scsi_compat_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
+{
+	int ret = scsi_ioctl_common(sdev, cmd, arg);
+
+	if (ret != -ENOIOCTLCMD)
+		return ret;
+
+	if (sdev->host->hostt->compat_ioctl)
+		return sdev->host->hostt->compat_ioctl(sdev, cmd, arg);
+
+	return ret;
+}
+EXPORT_SYMBOL(scsi_compat_ioctl);
+#endif
+
 /*
  * We can process a reset even when a device isn't fully operable.
  */
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 3e7a45d0daca..610ee41fa54c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2108,6 +2108,8 @@ scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
 
 	memset(data, 0, sizeof(*data));
 	memset(&cmd[0], 0, 12);
+
+	dbd = sdev->set_dbd_for_ms ? 8 : dbd;
 	cmd[1] = dbd & 0x18;	/* allows DBD and LLBA bits */
 	cmd[2] = modepage;
 
diff --git a/drivers/scsi/scsi_logging.h b/drivers/scsi/scsi_logging.h
index 836185de28c4..3df877886119 100644
--- a/drivers/scsi/scsi_logging.h
+++ b/drivers/scsi/scsi_logging.h
@@ -53,7 +53,7 @@ do {								\
 } while (0)
 #else
 #define SCSI_LOG_LEVEL(SHIFT, BITS) 0
-#define SCSI_CHECK_LOGGING(SHIFT, BITS, LEVEL, CMD)
+#define SCSI_CHECK_LOGGING(SHIFT, BITS, LEVEL, CMD) do { } while (0)
 #endif /* CONFIG_SCSI_LOGGING */
 
 /*
diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c
index 5b313226f11c..d6982d355739 100644
--- a/drivers/scsi/scsi_proc.c
+++ b/drivers/scsi/scsi_proc.c
@@ -83,12 +83,12 @@ static int proc_scsi_host_open(struct inode *inode, struct file *file)
 				4 * PAGE_SIZE);
 }
 
-static const struct file_operations proc_scsi_fops = {
-	.open = proc_scsi_host_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.write = proc_scsi_host_write
+static const struct proc_ops proc_scsi_ops = {
+	.proc_open	= proc_scsi_host_open,
+	.proc_release	= single_release,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= proc_scsi_host_write
 };
 
 /**
@@ -146,7 +146,7 @@ void scsi_proc_host_add(struct Scsi_Host *shost)
 
 	sprintf(name,"%d", shost->host_no);
 	p = proc_create_data(name, S_IRUGO | S_IWUSR,
-		sht->proc_dir, &proc_scsi_fops, shost);
+		sht->proc_dir, &proc_scsi_ops, shost);
 	if (!p)
 		printk(KERN_ERR "%s: Failed to register host %d in"
 		       "%s\n", __func__, shost->host_no,
@@ -436,13 +436,12 @@ static int proc_scsi_open(struct inode *inode, struct file *file)
 	return seq_open(file, &scsi_seq_ops);
 }
 
-static const struct file_operations proc_scsi_operations = {
-	.owner		= THIS_MODULE,
-	.open		= proc_scsi_open,
-	.read		= seq_read,
-	.write		= proc_scsi_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops scsi_scsi_proc_ops = {
+	.proc_open	= proc_scsi_open,
+	.proc_read	= seq_read,
+	.proc_write	= proc_scsi_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 /**
@@ -456,7 +455,7 @@ int __init scsi_init_procfs(void)
 	if (!proc_scsi)
 		goto err1;
 
-	pde = proc_create("scsi/scsi", 0, NULL, &proc_scsi_operations);
+	pde = proc_create("scsi/scsi", 0, NULL, &scsi_scsi_proc_ops);
 	if (!pde)
 		goto err2;
 
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index ed8d9709b9b9..dfc726fa34e3 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2093,7 +2093,12 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id)
 					 "could not register session's dev\n");
 		goto release_ida;
 	}
-	transport_register_device(&session->dev);
+	err = transport_register_device(&session->dev);
+	if (err) {
+		iscsi_cls_session_printk(KERN_ERR, session,
+					 "could not register transport's dev\n");
+		goto release_dev;
+	}
 
 	spin_lock_irqsave(&sesslock, flags);
 	list_add(&session->sess_list, &sesslist);
@@ -2103,6 +2108,8 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id)
 	ISCSI_DBG_TRANS_SESSION(session, "Completed session adding\n");
 	return 0;
 
+release_dev:
+	device_del(&session->dev);
 release_ida:
 	if (session->ida_used)
 		ida_simple_remove(&iscsi_sess_ida, session->target_id);
@@ -2263,7 +2270,12 @@ iscsi_create_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid)
 					 "register connection's dev\n");
 		goto release_parent_ref;
 	}
-	transport_register_device(&conn->dev);
+	err = transport_register_device(&conn->dev);
+	if (err) {
+		iscsi_cls_session_printk(KERN_ERR, session, "could not "
+					 "register transport's dev\n");
+		goto release_conn_ref;
+	}
 
 	spin_lock_irqsave(&connlock, flags);
 	list_add(&conn->conn_list, &connlist);
@@ -2272,6 +2284,8 @@ iscsi_create_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid)
 	ISCSI_DBG_TRANS_CONN(conn, "Completed conn creation\n");
 	return conn;
 
+release_conn_ref:
+	put_device(&conn->dev);
 release_parent_ref:
 	put_device(&session->dev);
 free_conn:
@@ -2947,6 +2961,24 @@ iscsi_set_path(struct iscsi_transport *transport, struct iscsi_uevent *ev)
 	return err;
 }
 
+static int iscsi_session_has_conns(int sid)
+{
+	struct iscsi_cls_conn *conn;
+	unsigned long flags;
+	int found = 0;
+
+	spin_lock_irqsave(&connlock, flags);
+	list_for_each_entry(conn, &connlist, conn_list) {
+		if (iscsi_conn_get_sid(conn) == sid) {
+			found = 1;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&connlock, flags);
+
+	return found;
+}
+
 static int
 iscsi_set_iface_params(struct iscsi_transport *transport,
 		       struct iscsi_uevent *ev, uint32_t len)
@@ -3524,10 +3556,12 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group)
 		break;
 	case ISCSI_UEVENT_DESTROY_SESSION:
 		session = iscsi_session_lookup(ev->u.d_session.sid);
-		if (session)
-			transport->destroy_session(session);
-		else
+		if (!session)
 			err = -EINVAL;
+		else if (iscsi_session_has_conns(ev->u.d_session.sid))
+			err = -EBUSY;
+		else
+			transport->destroy_session(session);
 		break;
 	case ISCSI_UEVENT_UNBIND_SESSION:
 		session = iscsi_session_lookup(ev->u.d_session.sid);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 902b649fc8ef..8ca9299ffd36 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1465,13 +1465,12 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
  *	Note: most ioctls are forward onto the block subsystem or further
  *	down in the scsi subsystem.
  **/
-static int sd_ioctl(struct block_device *bdev, fmode_t mode,
-		    unsigned int cmd, unsigned long arg)
+static int sd_ioctl_common(struct block_device *bdev, fmode_t mode,
+			   unsigned int cmd, void __user *p)
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
-	void __user *p = (void __user *)arg;
 	int error;
     
 	SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, "
@@ -1507,9 +1506,6 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode,
 			break;
 		default:
 			error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p);
-			if (error != -ENOTTY)
-				break;
-			error = scsi_ioctl(sdp, cmd, p);
 			break;
 	}
 out:
@@ -1691,39 +1687,31 @@ static void sd_rescan(struct device *dev)
 	revalidate_disk(sdkp->disk);
 }
 
+static int sd_ioctl(struct block_device *bdev, fmode_t mode,
+		    unsigned int cmd, unsigned long arg)
+{
+	void __user *p = (void __user *)arg;
+	int ret;
+
+	ret = sd_ioctl_common(bdev, mode, cmd, p);
+	if (ret != -ENOTTY)
+		return ret;
+
+	return scsi_ioctl(scsi_disk(bdev->bd_disk)->device, cmd, p);
+}
 
 #ifdef CONFIG_COMPAT
-/* 
- * This gets directly called from VFS. When the ioctl 
- * is not recognized we go back to the other translation paths. 
- */
 static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode,
 			   unsigned int cmd, unsigned long arg)
 {
-	struct gendisk *disk = bdev->bd_disk;
-	struct scsi_disk *sdkp = scsi_disk(disk);
-	struct scsi_device *sdev = sdkp->device;
 	void __user *p = compat_ptr(arg);
-	int error;
-
-	error = scsi_verify_blk_ioctl(bdev, cmd);
-	if (error < 0)
-		return error;
+	int ret;
 
-	error = scsi_ioctl_block_when_processing_errors(sdev, cmd,
-			(mode & FMODE_NDELAY) != 0);
-	if (error)
-		return error;
+	ret = sd_ioctl_common(bdev, mode, cmd, p);
+	if (ret != -ENOTTY)
+		return ret;
 
-	if (is_sed_ioctl(cmd))
-		return sed_ioctl(sdkp->opal_dev, cmd, p);
-	       
-	/* 
-	 * Let the static ioctl translation table take care of it.
-	 */
-	if (!sdev->host->hostt->compat_ioctl)
-		return -ENOIOCTLCMD; 
-	return sdev->host->hostt->compat_ioctl(sdev, cmd, p);
+	return scsi_compat_ioctl(scsi_disk(bdev->bd_disk)->device, cmd, p);
 }
 #endif
 
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index e0bd4cf17230..e4282bce5834 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -325,22 +325,21 @@ static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
 }
 
 /**
- * sd_zbc_check_zones - Check the device capacity and zone sizes
+ * sd_zbc_check_capacity - Check the device capacity
  * @sdkp: Target disk
+ * @buf: command buffer
+ * @zblock: zone size in number of blocks
  *
- * Check that the device capacity as reported by READ CAPACITY matches the
- * max_lba value (plus one)of the report zones command reply. Also check that
- * all zones of the device have an equal size, only allowing the last zone of
- * the disk to have a smaller size (runt zone). The zone size must also be a
- * power of two.
+ * Get the device zone size and check that the device capacity as reported
+ * by READ CAPACITY matches the max_lba value (plus one) of the report zones
+ * command reply for devices with RC_BASIS == 0.
  *
- * Returns the zone size in number of blocks upon success or an error code
- * upon failure.
+ * Returns 0 upon success or an error code upon failure.
  */
-static int sd_zbc_check_zones(struct scsi_disk *sdkp, unsigned char *buf,
-			      u32 *zblocks)
+static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf,
+				 u32 *zblocks)
 {
-	u64 zone_blocks = 0;
+	u64 zone_blocks;
 	sector_t max_lba;
 	unsigned char *rec;
 	int ret;
@@ -363,17 +362,9 @@ static int sd_zbc_check_zones(struct scsi_disk *sdkp, unsigned char *buf,
 		}
 	}
 
-	/* Parse REPORT ZONES header */
+	/* Get the size of the first reported zone */
 	rec = buf + 64;
 	zone_blocks = get_unaligned_be64(&rec[8]);
-	if (!zone_blocks || !is_power_of_2(zone_blocks)) {
-		if (sdkp->first_scan)
-			sd_printk(KERN_NOTICE, sdkp,
-				  "Devices with non power of 2 zone "
-				  "size are not supported\n");
-		return -ENODEV;
-	}
-
 	if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
@@ -405,11 +396,8 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	if (ret)
 		goto err;
 
-	/*
-	 * Check zone size: only devices with a constant zone size (except
-	 * an eventual last runt zone) that is a power of 2 are supported.
-	 */
-	ret = sd_zbc_check_zones(sdkp, buf, &zone_blocks);
+	/* Check the device capacity reported by report zones */
+	ret = sd_zbc_check_capacity(sdkp, buf, &zone_blocks);
 	if (ret != 0)
 		goto err;
 
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 160748ad9c0f..4e6af592f018 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -405,6 +405,38 @@ sg_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static int get_sg_io_pack_id(int *pack_id, void __user *buf, size_t count)
+{
+	struct sg_header __user *old_hdr = buf;
+	int reply_len;
+
+	if (count >= SZ_SG_HEADER) {
+		/* negative reply_len means v3 format, otherwise v1/v2 */
+		if (get_user(reply_len, &old_hdr->reply_len))
+			return -EFAULT;
+
+		if (reply_len >= 0)
+			return get_user(*pack_id, &old_hdr->pack_id);
+
+		if (in_compat_syscall() &&
+		    count >= sizeof(struct compat_sg_io_hdr)) {
+			struct compat_sg_io_hdr __user *hp = buf;
+
+			return get_user(*pack_id, &hp->pack_id);
+		}
+
+		if (count >= sizeof(struct sg_io_hdr)) {
+			struct sg_io_hdr __user *hp = buf;
+
+			return get_user(*pack_id, &hp->pack_id);
+		}
+	}
+
+	/* no valid header was passed, so ignore the pack_id */
+	*pack_id = -1;
+	return 0;
+}
+
 static ssize_t
 sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 {
@@ -413,8 +445,8 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	Sg_request *srp;
 	int req_pack_id = -1;
 	sg_io_hdr_t *hp;
-	struct sg_header *old_hdr = NULL;
-	int retval = 0;
+	struct sg_header *old_hdr;
+	int retval;
 
 	/*
 	 * This could cause a response to be stranded. Close the associated
@@ -429,79 +461,34 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
 				      "sg_read: count=%d\n", (int) count));
 
-	if (sfp->force_packid && (count >= SZ_SG_HEADER)) {
-		old_hdr = memdup_user(buf, SZ_SG_HEADER);
-		if (IS_ERR(old_hdr))
-			return PTR_ERR(old_hdr);
-		if (old_hdr->reply_len < 0) {
-			if (count >= SZ_SG_IO_HDR) {
-				/*
-				 * This is stupid.
-				 *
-				 * We're copying the whole sg_io_hdr_t from user
-				 * space just to get the 'pack_id' field. But the
-				 * field is at different offsets for the compat
-				 * case, so we'll use "get_sg_io_hdr()" to copy
-				 * the whole thing and convert it.
-				 *
-				 * We could do something like just calculating the
-				 * offset based of 'in_compat_syscall()', but the
-				 * 'compat_sg_io_hdr' definition is in the wrong
-				 * place for that.
-				 */
-				sg_io_hdr_t *new_hdr;
-				new_hdr = kmalloc(SZ_SG_IO_HDR, GFP_KERNEL);
-				if (!new_hdr) {
-					retval = -ENOMEM;
-					goto free_old_hdr;
-				}
-				retval = get_sg_io_hdr(new_hdr, buf);
-				req_pack_id = new_hdr->pack_id;
-				kfree(new_hdr);
-				if (retval) {
-					retval = -EFAULT;
-					goto free_old_hdr;
-				}
-			}
-		} else
-			req_pack_id = old_hdr->pack_id;
-	}
+	if (sfp->force_packid)
+		retval = get_sg_io_pack_id(&req_pack_id, buf, count);
+	if (retval)
+		return retval;
+
 	srp = sg_get_rq_mark(sfp, req_pack_id);
 	if (!srp) {		/* now wait on packet to arrive */
-		if (atomic_read(&sdp->detaching)) {
-			retval = -ENODEV;
-			goto free_old_hdr;
-		}
-		if (filp->f_flags & O_NONBLOCK) {
-			retval = -EAGAIN;
-			goto free_old_hdr;
-		}
+		if (atomic_read(&sdp->detaching))
+			return -ENODEV;
+		if (filp->f_flags & O_NONBLOCK)
+			return -EAGAIN;
 		retval = wait_event_interruptible(sfp->read_wait,
 			(atomic_read(&sdp->detaching) ||
 			(srp = sg_get_rq_mark(sfp, req_pack_id))));
-		if (atomic_read(&sdp->detaching)) {
-			retval = -ENODEV;
-			goto free_old_hdr;
-		}
-		if (retval) {
+		if (atomic_read(&sdp->detaching))
+			return -ENODEV;
+		if (retval)
 			/* -ERESTARTSYS as signal hit process */
-			goto free_old_hdr;
-		}
-	}
-	if (srp->header.interface_id != '\0') {
-		retval = sg_new_read(sfp, buf, count, srp);
-		goto free_old_hdr;
+			return retval;
 	}
+	if (srp->header.interface_id != '\0')
+		return sg_new_read(sfp, buf, count, srp);
 
 	hp = &srp->header;
-	if (old_hdr == NULL) {
-		old_hdr = kmalloc(SZ_SG_HEADER, GFP_KERNEL);
-		if (! old_hdr) {
-			retval = -ENOMEM;
-			goto free_old_hdr;
-		}
-	}
-	memset(old_hdr, 0, SZ_SG_HEADER);
+	old_hdr = kzalloc(SZ_SG_HEADER, GFP_KERNEL);
+	if (!old_hdr)
+		return -ENOMEM;
+
 	old_hdr->reply_len = (int) hp->timeout;
 	old_hdr->pack_len = old_hdr->reply_len; /* old, strange behaviour */
 	old_hdr->pack_id = hp->pack_id;
@@ -575,7 +562,12 @@ sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp)
 	int err = 0, err2;
 	int len;
 
-	if (count < SZ_SG_IO_HDR) {
+	if (in_compat_syscall()) {
+		if (count < sizeof(struct compat_sg_io_hdr)) {
+			err = -EINVAL;
+			goto err_out;
+		}
+	} else if (count < SZ_SG_IO_HDR) {
 		err = -EINVAL;
 		goto err_out;
 	}
@@ -919,19 +911,14 @@ static int put_compat_request_table(struct compat_sg_req_info __user *o,
 #endif
 
 static long
-sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
+sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp,
+		unsigned int cmd_in, void __user *p)
 {
-	void __user *p = (void __user *)arg;
 	int __user *ip = p;
 	int result, val, read_only;
-	Sg_device *sdp;
-	Sg_fd *sfp;
 	Sg_request *srp;
 	unsigned long iflags;
 
-	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
-		return -ENXIO;
-
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
 				   "sg_ioctl: cmd=0x%x\n", (int) cmd_in));
 	read_only = (O_RDWR != (filp->f_flags & O_ACCMODE));
@@ -1154,29 +1141,44 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 			cmd_in, filp->f_flags & O_NDELAY);
 	if (result)
 		return result;
+
+	return -ENOIOCTLCMD;
+}
+
+static long
+sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
+{
+	void __user *p = (void __user *)arg;
+	Sg_device *sdp;
+	Sg_fd *sfp;
+	int ret;
+
+	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
+		return -ENXIO;
+
+	ret = sg_ioctl_common(filp, sdp, sfp, cmd_in, p);
+	if (ret != -ENOIOCTLCMD)
+		return ret;
+
 	return scsi_ioctl(sdp->device, cmd_in, p);
 }
 
 #ifdef CONFIG_COMPAT
 static long sg_compat_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 {
+	void __user *p = compat_ptr(arg);
 	Sg_device *sdp;
 	Sg_fd *sfp;
-	struct scsi_device *sdev;
+	int ret;
 
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 
-	sdev = sdp->device;
-	if (sdev->host->hostt->compat_ioctl) { 
-		int ret;
-
-		ret = sdev->host->hostt->compat_ioctl(sdev, cmd_in, (void __user *)arg);
-
+	ret = sg_ioctl_common(filp, sdp, sfp, cmd_in, p);
+	if (ret != -ENOIOCTLCMD)
 		return ret;
-	}
-	
-	return -ENOIOCTLCMD;
+
+	return scsi_compat_ioctl(sdp->device, cmd_in, p);
 }
 #endif
 
@@ -2320,25 +2322,23 @@ static int sg_proc_seq_show_int(struct seq_file *s, void *v);
 static int sg_proc_single_open_adio(struct inode *inode, struct file *file);
 static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer,
 			          size_t count, loff_t *off);
-static const struct file_operations adio_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_single_open_adio,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.write = sg_proc_write_adio,
-	.release = single_release,
+static const struct proc_ops adio_proc_ops = {
+	.proc_open	= sg_proc_single_open_adio,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= sg_proc_write_adio,
+	.proc_release	= single_release,
 };
 
 static int sg_proc_single_open_dressz(struct inode *inode, struct file *file);
 static ssize_t sg_proc_write_dressz(struct file *filp, 
 		const char __user *buffer, size_t count, loff_t *off);
-static const struct file_operations dressz_fops = {
-	.owner = THIS_MODULE,
-	.open = sg_proc_single_open_dressz,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.write = sg_proc_write_dressz,
-	.release = single_release,
+static const struct proc_ops dressz_proc_ops = {
+	.proc_open	= sg_proc_single_open_dressz,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= sg_proc_write_dressz,
+	.proc_release	= single_release,
 };
 
 static int sg_proc_seq_show_version(struct seq_file *s, void *v);
@@ -2379,9 +2379,9 @@ sg_proc_init(void)
 	if (!p)
 		return 1;
 
-	proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_fops);
+	proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_proc_ops);
 	proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops);
-	proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_fops);
+	proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_proc_ops);
 	proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr);
 	proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops);
 	proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops);
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 4664fdf75c0f..0fbb8fe6e521 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -38,6 +38,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/bio.h>
+#include <linux/compat.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/cdrom.h>
@@ -598,6 +599,51 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_COMPAT
+static int sr_block_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
+			  unsigned long arg)
+{
+	struct scsi_cd *cd = scsi_cd(bdev->bd_disk);
+	struct scsi_device *sdev = cd->device;
+	void __user *argp = compat_ptr(arg);
+	int ret;
+
+	mutex_lock(&sr_mutex);
+
+	ret = scsi_ioctl_block_when_processing_errors(sdev, cmd,
+			(mode & FMODE_NDELAY) != 0);
+	if (ret)
+		goto out;
+
+	scsi_autopm_get_device(sdev);
+
+	/*
+	 * Send SCSI addressing ioctls directly to mid level, send other
+	 * ioctls to cdrom/block level.
+	 */
+	switch (cmd) {
+	case SCSI_IOCTL_GET_IDLUN:
+	case SCSI_IOCTL_GET_BUS_NUMBER:
+		ret = scsi_compat_ioctl(sdev, cmd, argp);
+		goto put;
+	}
+
+	ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, (unsigned long)argp);
+	if (ret != -ENOSYS)
+		goto put;
+
+	ret = scsi_compat_ioctl(sdev, cmd, argp);
+
+put:
+	scsi_autopm_put_device(sdev);
+
+out:
+	mutex_unlock(&sr_mutex);
+	return ret;
+
+}
+#endif
+
 static unsigned int sr_block_check_events(struct gendisk *disk,
 					  unsigned int clearing)
 {
@@ -641,12 +687,11 @@ static const struct block_device_operations sr_bdops =
 	.open		= sr_block_open,
 	.release	= sr_block_release,
 	.ioctl		= sr_block_ioctl,
+#ifdef CONFIG_COMPAT
+	.ioctl		= sr_block_compat_ioctl,
+#endif
 	.check_events	= sr_block_check_events,
 	.revalidate_disk = sr_block_revalidate_disk,
-	/* 
-	 * No compat_ioctl for now because sr_block_ioctl never
-	 * seems to pass arbitrary ioctls down to host drivers.
-	 */
 };
 
 static int sr_open(struct cdrom_device_info *cdi, int purpose)
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 9e3fff2de83e..393f3019ccac 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3501,7 +3501,7 @@ out:
 
 
 /* The ioctl command */
-static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
+static long st_ioctl_common(struct file *file, unsigned int cmd_in, void __user *p)
 {
 	int i, cmd_nr, cmd_type, bt;
 	int retval = 0;
@@ -3509,7 +3509,6 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 	struct scsi_tape *STp = file->private_data;
 	struct st_modedef *STm;
 	struct st_partstat *STps;
-	void __user *p = (void __user *)arg;
 
 	if (mutex_lock_interruptible(&STp->lock))
 		return -ERESTARTSYS;
@@ -3824,9 +3823,19 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 	}
 	mutex_unlock(&STp->lock);
 	switch (cmd_in) {
+		case SCSI_IOCTL_STOP_UNIT:
+			/* unload */
+			retval = scsi_ioctl(STp->device, cmd_in, p);
+			if (!retval) {
+				STp->rew_at_close = 0;
+				STp->ready = ST_NO_TAPE;
+			}
+			return retval;
+
 		case SCSI_IOCTL_GET_IDLUN:
 		case SCSI_IOCTL_GET_BUS_NUMBER:
 			break;
+
 		default:
 			if ((cmd_in == SG_IO ||
 			     cmd_in == SCSI_IOCTL_SEND_COMMAND ||
@@ -3840,42 +3849,46 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 				return i;
 			break;
 	}
-	retval = scsi_ioctl(STp->device, cmd_in, p);
-	if (!retval && cmd_in == SCSI_IOCTL_STOP_UNIT) { /* unload */
-		STp->rew_at_close = 0;
-		STp->ready = ST_NO_TAPE;
-	}
-	return retval;
+	return -ENOTTY;
 
  out:
 	mutex_unlock(&STp->lock);
 	return retval;
 }
 
+static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
+{
+	void __user *p = (void __user *)arg;
+	struct scsi_tape *STp = file->private_data;
+	int ret;
+
+	ret = st_ioctl_common(file, cmd_in, p);
+	if (ret != -ENOTTY)
+		return ret;
+
+	return scsi_ioctl(STp->device, cmd_in, p);
+}
+
 #ifdef CONFIG_COMPAT
 static long st_compat_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 {
 	void __user *p = compat_ptr(arg);
 	struct scsi_tape *STp = file->private_data;
-	struct scsi_device *sdev = STp->device;
-	int ret = -ENOIOCTLCMD;
+	int ret;
 
 	/* argument conversion is handled using put_user_mtpos/put_user_mtget */
 	switch (cmd_in) {
-	case MTIOCTOP:
-		return st_ioctl(file, MTIOCTOP, (unsigned long)p);
 	case MTIOCPOS32:
-		return st_ioctl(file, MTIOCPOS, (unsigned long)p);
+		return st_ioctl_common(file, MTIOCPOS, p);
 	case MTIOCGET32:
-		return st_ioctl(file, MTIOCGET, (unsigned long)p);
+		return st_ioctl_common(file, MTIOCGET, p);
 	}
 
-	if (sdev->host->hostt->compat_ioctl) { 
+	ret = st_ioctl_common(file, cmd_in, p);
+	if (ret != -ENOTTY)
+		return ret;
 
-		ret = sdev->host->hostt->compat_ioctl(sdev, cmd_in, (void __user *)arg);
-
-	}
-	return ret;
+	return scsi_compat_ioctl(STp->device, cmd_in, p);
 }
 #endif
 
diff --git a/drivers/scsi/sym53c8xx_2/sym_nvram.c b/drivers/scsi/sym53c8xx_2/sym_nvram.c
index 9dc17f1288f9..d37e2a69136a 100644
--- a/drivers/scsi/sym53c8xx_2/sym_nvram.c
+++ b/drivers/scsi/sym53c8xx_2/sym_nvram.c
@@ -227,7 +227,7 @@ static void sym_display_Tekram_nvram(struct sym_device *np, Tekram_nvram *nvram)
 /*
  *  24C16 EEPROM reading.
  *
- *  GPOI0 - data in/data out
+ *  GPIO0 - data in/data out
  *  GPIO1 - clock
  *  Symbios NVRAM wiring now also used by Tekram.
  */
@@ -524,7 +524,7 @@ static int sym_read_Symbios_nvram(struct sym_device *np, Symbios_nvram *nvram)
 /*
  *  93C46 EEPROM reading.
  *
- *  GPOI0 - data in
+ *  GPIO0 - data in
  *  GPIO1 - data out
  *  GPIO2 - clock
  *  GPIO4 - chip select
diff --git a/drivers/scsi/ufs/cdns-pltfrm.c b/drivers/scsi/ufs/cdns-pltfrm.c
index 6feeb0faf123..56a6a1ed5ec2 100644
--- a/drivers/scsi/ufs/cdns-pltfrm.c
+++ b/drivers/scsi/ufs/cdns-pltfrm.c
@@ -19,6 +19,85 @@
 
 #define CDNS_UFS_REG_HCLKDIV	0xFC
 #define CDNS_UFS_REG_PHY_XCFGD1	0x113C
+#define CDNS_UFS_MAX_L4_ATTRS 12
+
+struct cdns_ufs_host {
+	/**
+	 * cdns_ufs_dme_attr_val - for storing L4 attributes
+	 */
+	u32 cdns_ufs_dme_attr_val[CDNS_UFS_MAX_L4_ATTRS];
+};
+
+/**
+ * cdns_ufs_get_l4_attr - get L4 attributes on local side
+ * @hba: per adapter instance
+ *
+ */
+static void cdns_ufs_get_l4_attr(struct ufs_hba *hba)
+{
+	struct cdns_ufs_host *host = ufshcd_get_variant(hba);
+
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_PEERDEVICEID),
+		       &host->cdns_ufs_dme_attr_val[0]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_PEERCPORTID),
+		       &host->cdns_ufs_dme_attr_val[1]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_TRAFFICCLASS),
+		       &host->cdns_ufs_dme_attr_val[2]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_PROTOCOLID),
+		       &host->cdns_ufs_dme_attr_val[3]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_CPORTFLAGS),
+		       &host->cdns_ufs_dme_attr_val[4]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_TXTOKENVALUE),
+		       &host->cdns_ufs_dme_attr_val[5]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_RXTOKENVALUE),
+		       &host->cdns_ufs_dme_attr_val[6]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_LOCALBUFFERSPACE),
+		       &host->cdns_ufs_dme_attr_val[7]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_PEERBUFFERSPACE),
+		       &host->cdns_ufs_dme_attr_val[8]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_CREDITSTOSEND),
+		       &host->cdns_ufs_dme_attr_val[9]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_CPORTMODE),
+		       &host->cdns_ufs_dme_attr_val[10]);
+	ufshcd_dme_get(hba, UIC_ARG_MIB(T_CONNECTIONSTATE),
+		       &host->cdns_ufs_dme_attr_val[11]);
+}
+
+/**
+ * cdns_ufs_set_l4_attr - set L4 attributes on local side
+ * @hba: per adapter instance
+ *
+ */
+static void cdns_ufs_set_l4_attr(struct ufs_hba *hba)
+{
+	struct cdns_ufs_host *host = ufshcd_get_variant(hba);
+
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_CONNECTIONSTATE), 0);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_PEERDEVICEID),
+		       host->cdns_ufs_dme_attr_val[0]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_PEERCPORTID),
+		       host->cdns_ufs_dme_attr_val[1]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_TRAFFICCLASS),
+		       host->cdns_ufs_dme_attr_val[2]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_PROTOCOLID),
+		       host->cdns_ufs_dme_attr_val[3]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_CPORTFLAGS),
+		       host->cdns_ufs_dme_attr_val[4]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_TXTOKENVALUE),
+		       host->cdns_ufs_dme_attr_val[5]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_RXTOKENVALUE),
+		       host->cdns_ufs_dme_attr_val[6]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_LOCALBUFFERSPACE),
+		       host->cdns_ufs_dme_attr_val[7]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_PEERBUFFERSPACE),
+		       host->cdns_ufs_dme_attr_val[8]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_CREDITSTOSEND),
+		       host->cdns_ufs_dme_attr_val[9]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_CPORTMODE),
+		       host->cdns_ufs_dme_attr_val[10]);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(T_CONNECTIONSTATE),
+		       host->cdns_ufs_dme_attr_val[11]);
+}
 
 /**
  * Sets HCLKDIV register value based on the core_clk
@@ -78,6 +157,22 @@ static int cdns_ufs_hce_enable_notify(struct ufs_hba *hba,
 }
 
 /**
+ * Called around hibern8 enter/exit.
+ * @hba: host controller instance
+ * @cmd: UIC Command
+ * @status: notify stage (pre, post change)
+ *
+ */
+static void cdns_ufs_hibern8_notify(struct ufs_hba *hba, enum uic_cmd_dme cmd,
+				    enum ufs_notify_change_status status)
+{
+	if (status == PRE_CHANGE && cmd == UIC_CMD_DME_HIBER_ENTER)
+		cdns_ufs_get_l4_attr(hba);
+	if (status == POST_CHANGE && cmd == UIC_CMD_DME_HIBER_EXIT)
+		cdns_ufs_set_l4_attr(hba);
+}
+
+/**
  * Called before and after Link startup is carried out.
  * @hba: host controller instance
  * @status: notify stage (pre, post change)
@@ -117,6 +212,14 @@ static int cdns_ufs_link_startup_notify(struct ufs_hba *hba,
 static int cdns_ufs_init(struct ufs_hba *hba)
 {
 	int status = 0;
+	struct cdns_ufs_host *host;
+	struct device *dev = hba->dev;
+
+	host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+
+	if (!host)
+		return -ENOMEM;
+	ufshcd_set_variant(hba, host);
 
 	if (hba->vops && hba->vops->phy_initialization)
 		status = hba->vops->phy_initialization(hba);
@@ -144,8 +247,10 @@ static int cdns_ufs_m31_16nm_phy_initialization(struct ufs_hba *hba)
 
 static const struct ufs_hba_variant_ops cdns_ufs_pltfm_hba_vops = {
 	.name = "cdns-ufs-pltfm",
+	.init = cdns_ufs_init,
 	.hce_enable_notify = cdns_ufs_hce_enable_notify,
 	.link_startup_notify = cdns_ufs_link_startup_notify,
+	.hibern8_notify = cdns_ufs_hibern8_notify,
 };
 
 static const struct ufs_hba_variant_ops cdns_ufs_m31_16nm_pltfm_hba_vops = {
@@ -154,6 +259,7 @@ static const struct ufs_hba_variant_ops cdns_ufs_m31_16nm_pltfm_hba_vops = {
 	.hce_enable_notify = cdns_ufs_hce_enable_notify,
 	.link_startup_notify = cdns_ufs_link_startup_notify,
 	.phy_initialization = cdns_ufs_m31_16nm_phy_initialization,
+	.hibern8_notify = cdns_ufs_hibern8_notify,
 };
 
 static const struct of_device_id cdns_ufs_of_match[] = {
@@ -219,6 +325,7 @@ static const struct dev_pm_ops cdns_ufs_dev_pm_ops = {
 static struct platform_driver cdns_ufs_pltfrm_driver = {
 	.probe	= cdns_ufs_pltfrm_probe,
 	.remove	= cdns_ufs_pltfrm_remove,
+	.shutdown = ufshcd_pltfrm_shutdown,
 	.driver	= {
 		.name   = "cdns-ufshcd",
 		.pm     = &cdns_ufs_dev_pm_ops,
diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c
index 83e28edc3ac5..53eae5fe2ade 100644
--- a/drivers/scsi/ufs/ufs-mediatek.c
+++ b/drivers/scsi/ufs/ufs-mediatek.c
@@ -6,16 +6,30 @@
  *	Peter Wang <peter.wang@mediatek.com>
  */
 
+#include <linux/arm-smccc.h>
+#include <linux/bitfield.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/soc/mediatek/mtk_sip_svc.h>
 
 #include "ufshcd.h"
 #include "ufshcd-pltfrm.h"
+#include "ufs_quirks.h"
 #include "unipro.h"
 #include "ufs-mediatek.h"
 
+#define ufs_mtk_smc(cmd, val, res) \
+	arm_smccc_smc(MTK_SIP_UFS_CONTROL, \
+		      cmd, val, 0, 0, 0, 0, 0, &(res))
+
+#define ufs_mtk_ref_clk_notify(on, res) \
+	ufs_mtk_smc(UFS_MTK_SIP_REF_CLK_NOTIFICATION, on, res)
+
+#define ufs_mtk_device_reset_ctrl(high, res) \
+	ufs_mtk_smc(UFS_MTK_SIP_DEVICE_RESET, high, res)
+
 static void ufs_mtk_cfg_unipro_cg(struct ufs_hba *hba, bool enable)
 {
 	u32 tmp;
@@ -81,6 +95,49 @@ static int ufs_mtk_bind_mphy(struct ufs_hba *hba)
 	return err;
 }
 
+static int ufs_mtk_setup_ref_clk(struct ufs_hba *hba, bool on)
+{
+	struct ufs_mtk_host *host = ufshcd_get_variant(hba);
+	struct arm_smccc_res res;
+	unsigned long timeout;
+	u32 value;
+
+	if (host->ref_clk_enabled == on)
+		return 0;
+
+	if (on) {
+		ufs_mtk_ref_clk_notify(on, res);
+		ufshcd_writel(hba, REFCLK_REQUEST, REG_UFS_REFCLK_CTRL);
+	} else {
+		ufshcd_writel(hba, REFCLK_RELEASE, REG_UFS_REFCLK_CTRL);
+	}
+
+	/* Wait for ack */
+	timeout = jiffies + msecs_to_jiffies(REFCLK_REQ_TIMEOUT_MS);
+	do {
+		value = ufshcd_readl(hba, REG_UFS_REFCLK_CTRL);
+
+		/* Wait until ack bit equals to req bit */
+		if (((value & REFCLK_ACK) >> 1) == (value & REFCLK_REQUEST))
+			goto out;
+
+		usleep_range(100, 200);
+	} while (time_before(jiffies, timeout));
+
+	dev_err(hba->dev, "missing ack of refclk req, reg: 0x%x\n", value);
+
+	ufs_mtk_ref_clk_notify(host->ref_clk_enabled, res);
+
+	return -ETIMEDOUT;
+
+out:
+	host->ref_clk_enabled = on;
+	if (!on)
+		ufs_mtk_ref_clk_notify(on, res);
+
+	return 0;
+}
+
 /**
  * ufs_mtk_setup_clocks - enables/disable clocks
  * @hba: host controller instance
@@ -105,12 +162,16 @@ static int ufs_mtk_setup_clocks(struct ufs_hba *hba, bool on,
 
 	switch (status) {
 	case PRE_CHANGE:
-		if (!on)
+		if (!on) {
+			ufs_mtk_setup_ref_clk(hba, on);
 			ret = phy_power_off(host->mphy);
+		}
 		break;
 	case POST_CHANGE:
-		if (on)
+		if (on) {
 			ret = phy_power_on(host->mphy);
+			ufs_mtk_setup_ref_clk(hba, on);
+		}
 		break;
 	}
 
@@ -150,6 +211,9 @@ static int ufs_mtk_init(struct ufs_hba *hba)
 	/* Enable runtime autosuspend */
 	hba->caps |= UFSHCD_CAP_RPM_AUTOSUSPEND;
 
+	/* Enable clock-gating */
+	hba->caps |= UFSHCD_CAP_CLK_GATING;
+
 	/*
 	 * ufshcd_vops_init() is invoked after
 	 * ufshcd_setup_clock(true) in ufshcd_hba_init() thus
@@ -238,6 +302,23 @@ static int ufs_mtk_pre_link(struct ufs_hba *hba)
 	return ret;
 }
 
+static void ufs_mtk_setup_clk_gating(struct ufs_hba *hba)
+{
+	unsigned long flags;
+	u32 ah_ms;
+
+	if (ufshcd_is_clkgating_allowed(hba)) {
+		if (ufshcd_is_auto_hibern8_supported(hba) && hba->ahit)
+			ah_ms = FIELD_GET(UFSHCI_AHIBERN8_TIMER_MASK,
+					  hba->ahit);
+		else
+			ah_ms = 10;
+		spin_lock_irqsave(hba->host->host_lock, flags);
+		hba->clk_gating.delay_ms = ah_ms + 5;
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+	}
+}
+
 static int ufs_mtk_post_link(struct ufs_hba *hba)
 {
 	/* disable device LCC */
@@ -246,6 +327,15 @@ static int ufs_mtk_post_link(struct ufs_hba *hba)
 	/* enable unipro clock gating feature */
 	ufs_mtk_cfg_unipro_cg(hba, true);
 
+	/* configure auto-hibern8 timer to 10ms */
+	if (ufshcd_is_auto_hibern8_supported(hba)) {
+		ufshcd_auto_hibern8_update(hba,
+			FIELD_PREP(UFSHCI_AHIBERN8_TIMER_MASK, 10) |
+			FIELD_PREP(UFSHCI_AHIBERN8_SCALE_MASK, 3));
+	}
+
+	ufs_mtk_setup_clk_gating(hba);
+
 	return 0;
 }
 
@@ -269,12 +359,86 @@ static int ufs_mtk_link_startup_notify(struct ufs_hba *hba,
 	return ret;
 }
 
+static void ufs_mtk_device_reset(struct ufs_hba *hba)
+{
+	struct arm_smccc_res res;
+
+	ufs_mtk_device_reset_ctrl(0, res);
+
+	/*
+	 * The reset signal is active low. UFS devices shall detect
+	 * more than or equal to 1us of positive or negative RST_n
+	 * pulse width.
+	 *
+	 * To be on safe side, keep the reset low for at least 10us.
+	 */
+	usleep_range(10, 15);
+
+	ufs_mtk_device_reset_ctrl(1, res);
+
+	/* Some devices may need time to respond to rst_n */
+	usleep_range(10000, 15000);
+
+	dev_info(hba->dev, "device reset done\n");
+}
+
+static int ufs_mtk_link_set_hpm(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_hba_enable(hba);
+	if (err)
+		return err;
+
+	err = ufshcd_dme_set(hba,
+			     UIC_ARG_MIB_SEL(VS_UNIPROPOWERDOWNCONTROL, 0),
+			     0);
+	if (err)
+		return err;
+
+	err = ufshcd_uic_hibern8_exit(hba);
+	if (!err)
+		ufshcd_set_link_active(hba);
+	else
+		return err;
+
+	err = ufshcd_make_hba_operational(hba);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int ufs_mtk_link_set_lpm(struct ufs_hba *hba)
+{
+	int err;
+
+	err = ufshcd_dme_set(hba,
+			     UIC_ARG_MIB_SEL(VS_UNIPROPOWERDOWNCONTROL, 0),
+			     1);
+	if (err) {
+		/* Resume UniPro state for following error recovery */
+		ufshcd_dme_set(hba,
+			       UIC_ARG_MIB_SEL(VS_UNIPROPOWERDOWNCONTROL, 0),
+			       0);
+		return err;
+	}
+
+	return 0;
+}
+
 static int ufs_mtk_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 {
+	int err;
 	struct ufs_mtk_host *host = ufshcd_get_variant(hba);
 
-	if (ufshcd_is_link_hibern8(hba))
+	if (ufshcd_is_link_hibern8(hba)) {
+		err = ufs_mtk_link_set_lpm(hba);
+		if (err)
+			return -EAGAIN;
 		phy_power_off(host->mphy);
+		ufs_mtk_setup_ref_clk(hba, false);
+	}
 
 	return 0;
 }
@@ -282,9 +446,40 @@ static int ufs_mtk_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 static int ufs_mtk_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 {
 	struct ufs_mtk_host *host = ufshcd_get_variant(hba);
+	int err;
 
-	if (ufshcd_is_link_hibern8(hba))
+	if (ufshcd_is_link_hibern8(hba)) {
+		ufs_mtk_setup_ref_clk(hba, true);
 		phy_power_on(host->mphy);
+		err = ufs_mtk_link_set_hpm(hba);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void ufs_mtk_dbg_register_dump(struct ufs_hba *hba)
+{
+	ufshcd_dump_regs(hba, REG_UFS_REFCLK_CTRL, 0x4, "Ref-Clk Ctrl ");
+
+	ufshcd_dump_regs(hba, REG_UFS_EXTREG, 0x4, "Ext Reg ");
+
+	ufshcd_dump_regs(hba, REG_UFS_MPHYCTRL,
+			 REG_UFS_REJECT_MON - REG_UFS_MPHYCTRL + 4,
+			 "MPHY Ctrl ");
+
+	/* Direct debugging information to REG_MTK_PROBE */
+	ufshcd_writel(hba, 0x20, REG_UFS_DEBUG_SEL);
+	ufshcd_dump_regs(hba, REG_UFS_PROBE, 0x4, "Debug Probe ");
+}
+
+static int ufs_mtk_apply_dev_quirks(struct ufs_hba *hba)
+{
+	struct ufs_dev_info *dev_info = &hba->dev_info;
+
+	if (dev_info->wmanufacturerid == UFS_VENDOR_SAMSUNG)
+		ufshcd_dme_set(hba, UIC_ARG_MIB(PA_TACTIVATE), 6);
 
 	return 0;
 }
@@ -301,8 +496,11 @@ static struct ufs_hba_variant_ops ufs_hba_mtk_vops = {
 	.setup_clocks        = ufs_mtk_setup_clocks,
 	.link_startup_notify = ufs_mtk_link_startup_notify,
 	.pwr_change_notify   = ufs_mtk_pwr_change_notify,
+	.apply_dev_quirks    = ufs_mtk_apply_dev_quirks,
 	.suspend             = ufs_mtk_suspend,
 	.resume              = ufs_mtk_resume,
+	.dbg_register_dump   = ufs_mtk_dbg_register_dump,
+	.device_reset        = ufs_mtk_device_reset,
 };
 
 /**
diff --git a/drivers/scsi/ufs/ufs-mediatek.h b/drivers/scsi/ufs/ufs-mediatek.h
index 19f8c42fe06f..fccdd979d6fb 100644
--- a/drivers/scsi/ufs/ufs-mediatek.h
+++ b/drivers/scsi/ufs/ufs-mediatek.h
@@ -6,6 +6,30 @@
 #ifndef _UFS_MEDIATEK_H
 #define _UFS_MEDIATEK_H
 
+#include <linux/bitops.h>
+#include <linux/soc/mediatek/mtk_sip_svc.h>
+
+/*
+ * Vendor specific UFSHCI Registers
+ */
+#define REG_UFS_REFCLK_CTRL         0x144
+#define REG_UFS_EXTREG              0x2100
+#define REG_UFS_MPHYCTRL            0x2200
+#define REG_UFS_REJECT_MON          0x22AC
+#define REG_UFS_DEBUG_SEL           0x22C0
+#define REG_UFS_PROBE               0x22C8
+
+/*
+ * Ref-clk control
+ *
+ * Values for register REG_UFS_REFCLK_CTRL
+ */
+#define REFCLK_RELEASE              0x0
+#define REFCLK_REQUEST              BIT(0)
+#define REFCLK_ACK                  BIT(1)
+
+#define REFCLK_REQ_TIMEOUT_MS       3
+
 /*
  * Vendor specific pre-defined parameters
  */
@@ -30,6 +54,13 @@
 #define VS_UNIPROPOWERDOWNCONTROL   0xD0A8
 
 /*
+ * SiP commands
+ */
+#define MTK_SIP_UFS_CONTROL               MTK_SIP_SMC_CMD(0x276)
+#define UFS_MTK_SIP_DEVICE_RESET          BIT(1)
+#define UFS_MTK_SIP_REF_CLK_NOTIFICATION  BIT(3)
+
+/*
  * VS_DEBUGCLOCKENABLE
  */
 enum {
@@ -48,6 +79,7 @@ enum {
 struct ufs_mtk_host {
 	struct ufs_hba *hba;
 	struct phy *mphy;
+	bool ref_clk_enabled;
 };
 
 #endif /* !_UFS_MEDIATEK_H */
diff --git a/drivers/scsi/ufs/ufs-sysfs.c b/drivers/scsi/ufs/ufs-sysfs.c
index ad2abc96c0f1..dbdf8b01abed 100644
--- a/drivers/scsi/ufs/ufs-sysfs.c
+++ b/drivers/scsi/ufs/ufs-sysfs.c
@@ -118,26 +118,6 @@ static ssize_t spm_target_link_state_show(struct device *dev,
 				ufs_pm_lvl_states[hba->spm_lvl].link_state));
 }
 
-static void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
-{
-	unsigned long flags;
-
-	if (!ufshcd_is_auto_hibern8_supported(hba))
-		return;
-
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->ahit != ahit)
-		hba->ahit = ahit;
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	if (!pm_runtime_suspended(hba->dev)) {
-		pm_runtime_get_sync(hba->dev);
-		ufshcd_hold(hba, false);
-		ufshcd_auto_hibern8_enable(hba);
-		ufshcd_release(hba);
-		pm_runtime_put(hba->dev);
-	}
-}
-
 /* Convert Auto-Hibernate Idle Timer register value to microseconds */
 static int ufshcd_ahit_to_us(u32 ahit)
 {
@@ -733,7 +713,7 @@ static ssize_t _pname##_show(struct device *dev,			\
 	struct scsi_device *sdev = to_scsi_device(dev);			\
 	struct ufs_hba *hba = shost_priv(sdev->host);			\
 	u8 lun = ufshcd_scsi_to_upiu_lun(sdev->lun);			\
-	if (!ufs_is_valid_unit_desc_lun(lun))				\
+	if (!ufs_is_valid_unit_desc_lun(&hba->dev_info, lun))		\
 		return -EINVAL;						\
 	return ufs_sysfs_read_desc_param(hba, QUERY_DESC_IDN_##_duname,	\
 		lun, _duname##_DESC_PARAM##_puname, buf, _size);	\
diff --git a/drivers/scsi/ufs/ufs-sysfs.h b/drivers/scsi/ufs/ufs-sysfs.h
index e5621e59a432..0f4e750a6748 100644
--- a/drivers/scsi/ufs/ufs-sysfs.h
+++ b/drivers/scsi/ufs/ufs-sysfs.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (C) 2018 Western Digital Corporation
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018 Western Digital Corporation
  */
 
 #ifndef __UFS_SYSFS_H__
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 3327981ef894..dde2eb02f76f 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -63,7 +63,6 @@
 #define UFS_UPIU_MAX_UNIT_NUM_ID	0x7F
 #define UFS_MAX_LUNS		(SCSI_W_LUN_BASE + UFS_UPIU_MAX_UNIT_NUM_ID)
 #define UFS_UPIU_WLUN_ID	(1 << 7)
-#define UFS_UPIU_MAX_GENERAL_LUN	8
 
 /* Well known logical unit id in LUN field of UPIU */
 enum {
@@ -499,9 +498,9 @@ struct ufs_query_res {
 #define UFS_VREG_VCC_MAX_UV	   3600000 /* uV */
 #define UFS_VREG_VCC_1P8_MIN_UV    1700000 /* uV */
 #define UFS_VREG_VCC_1P8_MAX_UV    1950000 /* uV */
-#define UFS_VREG_VCCQ_MIN_UV	   1100000 /* uV */
-#define UFS_VREG_VCCQ_MAX_UV	   1300000 /* uV */
-#define UFS_VREG_VCCQ2_MIN_UV	   1650000 /* uV */
+#define UFS_VREG_VCCQ_MIN_UV	   1140000 /* uV */
+#define UFS_VREG_VCCQ_MAX_UV	   1260000 /* uV */
+#define UFS_VREG_VCCQ2_MIN_UV	   1700000 /* uV */
 #define UFS_VREG_VCCQ2_MAX_UV	   1950000 /* uV */
 
 /*
@@ -530,28 +529,28 @@ struct ufs_dev_info {
 	bool f_power_on_wp_en;
 	/* Keeps information if any of the LU is power on write protected */
 	bool is_lu_power_on_wp;
-};
-
-#define MAX_MODEL_LEN 16
-/**
- * ufs_dev_desc - ufs device details from the device descriptor
- *
- * @wmanufacturerid: card details
- * @model: card model
- */
-struct ufs_dev_desc {
+	/* Maximum number of general LU supported by the UFS device */
+	u8 max_lu_supported;
 	u16 wmanufacturerid;
+	/*UFS device Product Name */
 	u8 *model;
 };
 
 /**
  * ufs_is_valid_unit_desc_lun - checks if the given LUN has a unit descriptor
+ * @dev_info: pointer of instance of struct ufs_dev_info
  * @lun: LU number to check
  * @return: true if the lun has a matching unit descriptor, false otherwise
  */
-static inline bool ufs_is_valid_unit_desc_lun(u8 lun)
+static inline bool ufs_is_valid_unit_desc_lun(struct ufs_dev_info *dev_info,
+		u8 lun)
 {
-	return lun == UFS_UPIU_RPMB_WLUN || (lun < UFS_UPIU_MAX_GENERAL_LUN);
+	if (!dev_info || !dev_info->max_lu_supported) {
+		pr_err("Max General LU supported by UFS isn't initilized\n");
+		return false;
+	}
+
+	return lun == UFS_UPIU_RPMB_WLUN || (lun < dev_info->max_lu_supported);
 }
 
 #endif /* End of Header */
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index fe6cad9b2a0d..d0ab147f98d3 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -22,16 +22,17 @@
  * @quirk: device quirk
  */
 struct ufs_dev_fix {
-	struct ufs_dev_desc card;
+	u16 wmanufacturerid;
+	u8 *model;
 	unsigned int quirk;
 };
 
-#define END_FIX { { 0 }, 0 }
+#define END_FIX { }
 
 /* add specific device quirk */
 #define UFS_FIX(_vendor, _model, _quirk) { \
-	.card.wmanufacturerid = (_vendor),\
-	.card.model = (_model),		   \
+	.wmanufacturerid = (_vendor),\
+	.model = (_model),		   \
 	.quirk = (_quirk),		   \
 }
 
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index b5966faf3e98..abd0e6b05f79 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -246,11 +246,10 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba);
 static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd);
 static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
 static void ufshcd_hba_exit(struct ufs_hba *hba);
-static int ufshcd_probe_hba(struct ufs_hba *hba);
+static int ufshcd_probe_hba(struct ufs_hba *hba, bool async);
 static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 				 bool skip_ref_clk);
 static int ufshcd_setup_clocks(struct ufs_hba *hba, bool on);
-static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba);
 static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba);
 static inline void ufshcd_add_delay_before_dme_cmd(struct ufs_hba *hba);
 static int ufshcd_host_reset_and_restore(struct ufs_hba *hba);
@@ -266,26 +265,18 @@ static inline bool ufshcd_valid_tag(struct ufs_hba *hba, int tag)
 	return tag >= 0 && tag < hba->nutrs;
 }
 
-static inline int ufshcd_enable_irq(struct ufs_hba *hba)
+static inline void ufshcd_enable_irq(struct ufs_hba *hba)
 {
-	int ret = 0;
-
 	if (!hba->is_irq_enabled) {
-		ret = request_irq(hba->irq, ufshcd_intr, IRQF_SHARED, UFSHCD,
-				hba);
-		if (ret)
-			dev_err(hba->dev, "%s: request_irq failed, ret=%d\n",
-				__func__, ret);
+		enable_irq(hba->irq);
 		hba->is_irq_enabled = true;
 	}
-
-	return ret;
 }
 
 static inline void ufshcd_disable_irq(struct ufs_hba *hba)
 {
 	if (hba->is_irq_enabled) {
-		free_irq(hba->irq, hba);
+		disable_irq(hba->irq);
 		hba->is_irq_enabled = false;
 	}
 }
@@ -335,27 +326,27 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
 	u8 opcode = 0;
 	u32 intr, doorbell;
 	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
+	struct scsi_cmnd *cmd = lrbp->cmd;
 	int transfer_len = -1;
 
 	if (!trace_ufshcd_command_enabled()) {
 		/* trace UPIU W/O tracing command */
-		if (lrbp->cmd)
+		if (cmd)
 			ufshcd_add_cmd_upiu_trace(hba, tag, str);
 		return;
 	}
 
-	if (lrbp->cmd) { /* data phase exists */
+	if (cmd) { /* data phase exists */
 		/* trace UPIU also */
 		ufshcd_add_cmd_upiu_trace(hba, tag, str);
-		opcode = (u8)(*lrbp->cmd->cmnd);
+		opcode = cmd->cmnd[0];
 		if ((opcode == READ_10) || (opcode == WRITE_10)) {
 			/*
 			 * Currently we only fully trace read(10) and write(10)
 			 * commands
 			 */
-			if (lrbp->cmd->request && lrbp->cmd->request->bio)
-				lba =
-				  lrbp->cmd->request->bio->bi_iter.bi_sector;
+			if (cmd->request && cmd->request->bio)
+				lba = cmd->request->bio->bi_iter.bi_sector;
 			transfer_len = be32_to_cpu(
 				lrbp->ucd_req_ptr->sc.exp_data_transfer_len);
 		}
@@ -393,7 +384,7 @@ static void ufshcd_print_err_hist(struct ufs_hba *hba,
 	for (i = 0; i < UFS_ERR_REG_HIST_LENGTH; i++) {
 		int p = (i + err_hist->pos) % UFS_ERR_REG_HIST_LENGTH;
 
-		if (err_hist->reg[p] == 0)
+		if (err_hist->tstamp[p] == 0)
 			continue;
 		dev_err(hba->dev, "%s[%d] = 0x%x at %lld us\n", err_name, p,
 			err_hist->reg[p], ktime_to_us(err_hist->tstamp[p]));
@@ -401,7 +392,7 @@ static void ufshcd_print_err_hist(struct ufs_hba *hba,
 	}
 
 	if (!found)
-		dev_err(hba->dev, "No record of %s errors\n", err_name);
+		dev_err(hba->dev, "No record of %s\n", err_name);
 }
 
 static void ufshcd_print_host_regs(struct ufs_hba *hba)
@@ -436,8 +427,7 @@ static void ufshcd_print_host_regs(struct ufs_hba *hba)
 
 	ufshcd_print_clk_freqs(hba);
 
-	if (hba->vops && hba->vops->dbg_register_dump)
-		hba->vops->dbg_register_dump(hba);
+	ufshcd_vops_dbg_register_dump(hba);
 }
 
 static
@@ -497,8 +487,8 @@ static void ufshcd_print_tmrs(struct ufs_hba *hba, unsigned long bitmap)
 static void ufshcd_print_host_state(struct ufs_hba *hba)
 {
 	dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
-	dev_err(hba->dev, "lrb in use=0x%lx, outstanding reqs=0x%lx tasks=0x%lx\n",
-		hba->lrb_in_use, hba->outstanding_reqs, hba->outstanding_tasks);
+	dev_err(hba->dev, "outstanding reqs=0x%lx tasks=0x%lx\n",
+		hba->outstanding_reqs, hba->outstanding_tasks);
 	dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
 		hba->saved_err, hba->saved_uic_err);
 	dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
@@ -646,40 +636,6 @@ static inline int ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp)
 }
 
 /**
- * ufshcd_get_tm_free_slot - get a free slot for task management request
- * @hba: per adapter instance
- * @free_slot: pointer to variable with available slot value
- *
- * Get a free tag and lock it until ufshcd_put_tm_slot() is called.
- * Returns 0 if free slot is not available, else return 1 with tag value
- * in @free_slot.
- */
-static bool ufshcd_get_tm_free_slot(struct ufs_hba *hba, int *free_slot)
-{
-	int tag;
-	bool ret = false;
-
-	if (!free_slot)
-		goto out;
-
-	do {
-		tag = find_first_zero_bit(&hba->tm_slots_in_use, hba->nutmrs);
-		if (tag >= hba->nutmrs)
-			goto out;
-	} while (test_and_set_bit_lock(tag, &hba->tm_slots_in_use));
-
-	*free_slot = tag;
-	ret = true;
-out:
-	return ret;
-}
-
-static inline void ufshcd_put_tm_slot(struct ufs_hba *hba, int slot)
-{
-	clear_bit_unlock(slot, &hba->tm_slots_in_use);
-}
-
-/**
  * ufshcd_utrl_clear - Clear a bit in UTRLCLR register
  * @hba: per adapter instance
  * @pos: position of the bit to be cleared
@@ -1273,6 +1229,24 @@ out:
 	return ret;
 }
 
+static bool ufshcd_is_busy(struct request *req, void *priv, bool reserved)
+{
+	int *busy = priv;
+
+	WARN_ON_ONCE(reserved);
+	(*busy)++;
+	return false;
+}
+
+/* Whether or not any tag is in use by a request that is in progress. */
+static bool ufshcd_any_tag_in_use(struct ufs_hba *hba)
+{
+	struct request_queue *q = hba->cmd_queue;
+	int busy = 0;
+
+	blk_mq_tagset_busy_iter(q->tag_set, ufshcd_is_busy, &busy);
+	return busy;
+}
 
 static int ufshcd_devfreq_get_dev_status(struct device *dev,
 		struct devfreq_dev_status *stat)
@@ -1490,6 +1464,8 @@ static void ufshcd_ungate_work(struct work_struct *work)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	ufshcd_setup_clocks(hba, true);
 
+	ufshcd_enable_irq(hba);
+
 	/* Exit from hibern8 */
 	if (ufshcd_can_hibern8_during_gating(hba)) {
 		/* Prevent gating in this path */
@@ -1619,7 +1595,7 @@ static void ufshcd_gate_work(struct work_struct *work)
 
 	if (hba->clk_gating.active_reqs
 		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
-		|| hba->lrb_in_use || hba->outstanding_tasks
+		|| ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks
 		|| hba->active_uic_cmd || hba->uic_async_done)
 		goto rel_lock;
 
@@ -1636,6 +1612,8 @@ static void ufshcd_gate_work(struct work_struct *work)
 		ufshcd_set_link_hibern8(hba);
 	}
 
+	ufshcd_disable_irq(hba);
+
 	if (!ufshcd_is_link_active(hba))
 		ufshcd_setup_clocks(hba, false);
 	else
@@ -1673,7 +1651,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
 
 	if (hba->clk_gating.active_reqs || hba->clk_gating.is_suspended
 		|| hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL
-		|| hba->lrb_in_use || hba->outstanding_tasks
+		|| ufshcd_any_tag_in_use(hba) || hba->outstanding_tasks
 		|| hba->active_uic_cmd || hba->uic_async_done
 		|| ufshcd_eh_in_progress(hba))
 		return;
@@ -1881,12 +1859,12 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 {
 	hba->lrb[task_tag].issue_time_stamp = ktime_get();
 	hba->lrb[task_tag].compl_time_stamp = ktime_set(0, 0);
+	ufshcd_add_command_trace(hba, task_tag, "send");
 	ufshcd_clk_scaling_start_busy(hba);
 	__set_bit(task_tag, &hba->outstanding_reqs);
 	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* Make sure that doorbell is committed immediately */
 	wmb();
-	ufshcd_add_command_trace(hba, task_tag, "send");
 }
 
 /**
@@ -2239,6 +2217,7 @@ static void ufshcd_prepare_req_desc_hdr(struct ufshcd_lrb *lrbp,
 static
 void ufshcd_prepare_utp_scsi_cmd_upiu(struct ufshcd_lrb *lrbp, u32 upiu_flags)
 {
+	struct scsi_cmnd *cmd = lrbp->cmd;
 	struct utp_upiu_req *ucd_req_ptr = lrbp->ucd_req_ptr;
 	unsigned short cdb_len;
 
@@ -2252,12 +2231,11 @@ void ufshcd_prepare_utp_scsi_cmd_upiu(struct ufshcd_lrb *lrbp, u32 upiu_flags)
 	/* Total EHS length and Data segment length will be zero */
 	ucd_req_ptr->header.dword_2 = 0;
 
-	ucd_req_ptr->sc.exp_data_transfer_len =
-		cpu_to_be32(lrbp->cmd->sdb.length);
+	ucd_req_ptr->sc.exp_data_transfer_len = cpu_to_be32(cmd->sdb.length);
 
-	cdb_len = min_t(unsigned short, lrbp->cmd->cmd_len, UFS_CDB_SIZE);
+	cdb_len = min_t(unsigned short, cmd->cmd_len, UFS_CDB_SIZE);
 	memset(ucd_req_ptr->sc.cdb, 0, UFS_CDB_SIZE);
-	memcpy(ucd_req_ptr->sc.cdb, lrbp->cmd->cmnd, cdb_len);
+	memcpy(ucd_req_ptr->sc.cdb, cmd->cmnd, cdb_len);
 
 	memset(lrbp->ucd_rsp_ptr, 0, sizeof(struct utp_upiu_rsp));
 }
@@ -2443,22 +2421,9 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 
 	hba->req_abort_count = 0;
 
-	/* acquire the tag to make sure device cmds don't use it */
-	if (test_and_set_bit_lock(tag, &hba->lrb_in_use)) {
-		/*
-		 * Dev manage command in progress, requeue the command.
-		 * Requeuing the command helps in cases where the request *may*
-		 * find different tag instead of waiting for dev manage command
-		 * completion.
-		 */
-		err = SCSI_MLQUEUE_HOST_BUSY;
-		goto out;
-	}
-
 	err = ufshcd_hold(hba, true);
 	if (err) {
 		err = SCSI_MLQUEUE_HOST_BUSY;
-		clear_bit_unlock(tag, &hba->lrb_in_use);
 		goto out;
 	}
 	WARN_ON(hba->clk_gating.state != CLKS_ON);
@@ -2479,7 +2444,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	err = ufshcd_map_sg(hba, lrbp);
 	if (err) {
 		lrbp->cmd = NULL;
-		clear_bit_unlock(tag, &hba->lrb_in_use);
+		ufshcd_release(hba);
 		goto out;
 	}
 	/* Make sure descriptors are ready before ringing the doorbell */
@@ -2627,44 +2592,6 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
 }
 
 /**
- * ufshcd_get_dev_cmd_tag - Get device management command tag
- * @hba: per-adapter instance
- * @tag_out: pointer to variable with available slot value
- *
- * Get a free slot and lock it until device management command
- * completes.
- *
- * Returns false if free slot is unavailable for locking, else
- * return true with tag value in @tag.
- */
-static bool ufshcd_get_dev_cmd_tag(struct ufs_hba *hba, int *tag_out)
-{
-	int tag;
-	bool ret = false;
-	unsigned long tmp;
-
-	if (!tag_out)
-		goto out;
-
-	do {
-		tmp = ~hba->lrb_in_use;
-		tag = find_last_bit(&tmp, hba->nutrs);
-		if (tag >= hba->nutrs)
-			goto out;
-	} while (test_and_set_bit_lock(tag, &hba->lrb_in_use));
-
-	*tag_out = tag;
-	ret = true;
-out:
-	return ret;
-}
-
-static inline void ufshcd_put_dev_cmd_tag(struct ufs_hba *hba, int tag)
-{
-	clear_bit_unlock(tag, &hba->lrb_in_use);
-}
-
-/**
  * ufshcd_exec_dev_cmd - API for sending device management requests
  * @hba: UFS hba
  * @cmd_type: specifies the type (NOP, Query...)
@@ -2676,6 +2603,8 @@ static inline void ufshcd_put_dev_cmd_tag(struct ufs_hba *hba, int tag)
 static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 		enum dev_cmd_type cmd_type, int timeout)
 {
+	struct request_queue *q = hba->cmd_queue;
+	struct request *req;
 	struct ufshcd_lrb *lrbp;
 	int err;
 	int tag;
@@ -2689,7 +2618,13 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 	 * Even though we use wait_event() which sleeps indefinitely,
 	 * the maximum wait time is bounded by SCSI request timeout.
 	 */
-	wait_event(hba->dev_cmd.tag_wq, ufshcd_get_dev_cmd_tag(hba, &tag));
+	req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out_unlock;
+	}
+	tag = req->tag;
+	WARN_ON_ONCE(!ufshcd_valid_tag(hba, tag));
 
 	init_completion(&wait);
 	lrbp = &hba->lrb[tag];
@@ -2714,8 +2649,8 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 			err ? "query_complete_err" : "query_complete");
 
 out_put_tag:
-	ufshcd_put_dev_cmd_tag(hba, tag);
-	wake_up(&hba->dev_cmd.tag_wq);
+	blk_put_request(req);
+out_unlock:
 	up_read(&hba->clk_scaling_lock);
 	return err;
 }
@@ -2918,7 +2853,7 @@ static int ufshcd_query_attr_retry(struct ufs_hba *hba,
 	int ret = 0;
 	u32 retries;
 
-	 for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
+	for (retries = QUERY_REQ_RETRIES; retries > 0; retries--) {
 		ret = ufshcd_query_attr(hba, opcode, idn, index,
 						selector, attr_val);
 		if (ret)
@@ -3210,17 +3145,6 @@ static inline int ufshcd_read_desc(struct ufs_hba *hba,
 	return ufshcd_read_desc_param(hba, desc_id, desc_index, 0, buf, size);
 }
 
-static inline int ufshcd_read_power_desc(struct ufs_hba *hba,
-					 u8 *buf,
-					 u32 size)
-{
-	return ufshcd_read_desc(hba, QUERY_DESC_IDN_POWER, 0, buf, size);
-}
-
-static int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size)
-{
-	return ufshcd_read_desc(hba, QUERY_DESC_IDN_DEVICE, 0, buf, size);
-}
 
 /**
  * struct uc_string_id - unicode string
@@ -3345,7 +3269,7 @@ static inline int ufshcd_read_unit_desc_param(struct ufs_hba *hba,
 	 * Unit descriptors are only available for general purpose LUs (LUN id
 	 * from 0 to 7) and RPMB Well known LU.
 	 */
-	if (!ufs_is_valid_unit_desc_lun(lun))
+	if (!ufs_is_valid_unit_desc_lun(&hba->dev_info, lun))
 		return -EOPNOTSUPP;
 
 	return ufshcd_read_desc_param(hba, QUERY_DESC_IDN_UNIT, lun,
@@ -3929,7 +3853,7 @@ out:
 	return ret;
 }
 
-static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
+int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 {
 	struct uic_command uic_cmd = {0};
 	int ret;
@@ -3955,6 +3879,25 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ufshcd_uic_hibern8_exit);
+
+void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit)
+{
+	unsigned long flags;
+
+	if (!(hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT))
+		return;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (hba->ahit == ahit)
+		goto out_unlock;
+	hba->ahit = ahit;
+	if (!pm_runtime_suspended(hba->dev))
+		ufshcd_writel(hba, hba->ahit, REG_AUTO_HIBERNATE_IDLE_TIMER);
+out_unlock:
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+}
+EXPORT_SYMBOL_GPL(ufshcd_auto_hibern8_update);
 
 void ufshcd_auto_hibern8_enable(struct ufs_hba *hba)
 {
@@ -4095,6 +4038,26 @@ static int ufshcd_change_power_mode(struct ufs_hba *hba,
 		ufshcd_dme_set(hba, UIC_ARG_MIB(PA_HSSERIES),
 						pwr_mode->hs_rate);
 
+	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA0),
+			DL_FC0ProtectionTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA1),
+			DL_TC0ReplayTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA2),
+			DL_AFC0ReqTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA3),
+			DL_FC1ProtectionTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA4),
+			DL_TC1ReplayTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA5),
+			DL_AFC1ReqTimeOutVal_Default);
+
+	ufshcd_dme_set(hba, UIC_ARG_MIB(DME_LocalFC0ProtectionTimeOutVal),
+			DL_FC0ProtectionTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(DME_LocalTC0ReplayTimeOutVal),
+			DL_TC0ReplayTimeOutVal_Default);
+	ufshcd_dme_set(hba, UIC_ARG_MIB(DME_LocalAFC0ReqTimeOutVal),
+			DL_AFC0ReqTimeOutVal_Default);
+
 	ret = ufshcd_uic_change_pwr_mode(hba, pwr_mode->pwr_rx << 4
 			| pwr_mode->pwr_tx);
 
@@ -4188,7 +4151,7 @@ out:
  *
  * Returns 0 on success, non-zero value on failure
  */
-static int ufshcd_make_hba_operational(struct ufs_hba *hba)
+int ufshcd_make_hba_operational(struct ufs_hba *hba)
 {
 	int err = 0;
 	u32 reg;
@@ -4234,6 +4197,7 @@ static int ufshcd_make_hba_operational(struct ufs_hba *hba)
 out:
 	return err;
 }
+EXPORT_SYMBOL_GPL(ufshcd_make_hba_operational);
 
 /**
  * ufshcd_hba_stop - Send controller to reset state
@@ -4311,7 +4275,7 @@ static int ufshcd_hba_execute_hce(struct ufs_hba *hba)
 	return 0;
 }
 
-static int ufshcd_hba_enable(struct ufs_hba *hba)
+int ufshcd_hba_enable(struct ufs_hba *hba)
 {
 	int ret;
 
@@ -4336,6 +4300,8 @@ static int ufshcd_hba_enable(struct ufs_hba *hba)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ufshcd_hba_enable);
+
 static int ufshcd_disable_tx_lcc(struct ufs_hba *hba, bool peer)
 {
 	int tx_lanes, i, err = 0;
@@ -4372,13 +4338,14 @@ static inline int ufshcd_disable_device_tx_lcc(struct ufs_hba *hba)
 	return ufshcd_disable_tx_lcc(hba, true);
 }
 
-static void ufshcd_update_reg_hist(struct ufs_err_reg_hist *reg_hist,
-				   u32 reg)
+void ufshcd_update_reg_hist(struct ufs_err_reg_hist *reg_hist,
+			    u32 reg)
 {
 	reg_hist->reg[reg_hist->pos] = reg;
 	reg_hist->tstamp[reg_hist->pos] = ktime_get();
 	reg_hist->pos = (reg_hist->pos + 1) % UFS_ERR_REG_HIST_LENGTH;
 }
+EXPORT_SYMBOL_GPL(ufshcd_update_reg_hist);
 
 /**
  * ufshcd_link_startup - Initialize unipro link startup
@@ -4561,7 +4528,7 @@ static int ufshcd_get_lu_wp(struct ufs_hba *hba,
 	 * protected so skip reading bLUWriteProtect parameter for
 	 * it. For other W-LUs, UNIT DESCRIPTOR is not available.
 	 */
-	else if (lun >= UFS_UPIU_MAX_GENERAL_LUN)
+	else if (lun >= hba->dev_info.max_lu_supported)
 		ret = -ENOTSUPP;
 	else
 		ret = ufshcd_read_unit_desc_param(hba,
@@ -4608,6 +4575,9 @@ static int ufshcd_slave_alloc(struct scsi_device *sdev)
 	/* Mode sense(6) is not supported by UFS, so use Mode sense(10) */
 	sdev->use_10_for_ms = 1;
 
+	/* DBD field should be set to 1 in mode sense(10) */
+	sdev->set_dbd_for_ms = 1;
+
 	/* allow SCSI layer to restart the device in case of errors */
 	sdev->allow_restart = 1;
 
@@ -4799,7 +4769,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 		break;
 	} /* end of switch */
 
-	if (host_byte(result) != DID_OK)
+	if ((host_byte(result) != DID_OK) && !hba->silence_err_logs)
 		ufshcd_print_trs(hba, 1 << lrbp->task_tag, true);
 	return result;
 }
@@ -4856,12 +4826,13 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 			cmd->result = result;
 			/* Mark completed command as NULL in LRB */
 			lrbp->cmd = NULL;
-			clear_bit_unlock(index, &hba->lrb_in_use);
+			lrbp->compl_time_stamp = ktime_get();
 			/* Do not touch lrbp after scsi done */
 			cmd->scsi_done(cmd);
 			__ufshcd_release(hba);
 		} else if (lrbp->command_type == UTP_CMD_TYPE_DEV_MANAGE ||
 			lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) {
+			lrbp->compl_time_stamp = ktime_get();
 			if (hba->dev_cmd.complete) {
 				ufshcd_add_command_trace(hba, index,
 						"dev_complete");
@@ -4870,17 +4841,12 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 		}
 		if (ufshcd_is_clkscaling_supported(hba))
 			hba->clk_scaling.active_reqs--;
-
-		lrbp->compl_time_stamp = ktime_get();
 	}
 
 	/* clear corresponding bits of completed commands */
 	hba->outstanding_reqs ^= completed_reqs;
 
 	ufshcd_clk_scaling_update_busy(hba);
-
-	/* we might have free'd some tags above */
-	wake_up(&hba->dev_cmd.tag_wq);
 }
 
 /**
@@ -5053,6 +5019,7 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 
 	hba->auto_bkops_enabled = false;
 	trace_ufshcd_auto_bkops_state(dev_name(hba->dev), "Disabled");
+	hba->is_urgent_bkops_lvl_checked = false;
 out:
 	return err;
 }
@@ -5077,6 +5044,7 @@ static void ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
 		hba->ee_ctrl_mask &= ~MASK_EE_URGENT_BKOPS;
 		ufshcd_disable_auto_bkops(hba);
 	}
+	hba->is_urgent_bkops_lvl_checked = false;
 }
 
 static inline int ufshcd_get_bkops_status(struct ufs_hba *hba, u32 *status)
@@ -5123,6 +5091,7 @@ static int ufshcd_bkops_ctrl(struct ufs_hba *hba,
 		err = ufshcd_enable_auto_bkops(hba);
 	else
 		err = ufshcd_disable_auto_bkops(hba);
+	hba->urgent_bkops_lvl = curr_status;
 out:
 	return err;
 }
@@ -5200,7 +5169,7 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
 	hba = container_of(work, struct ufs_hba, eeh_work);
 
 	pm_runtime_get_sync(hba->dev);
-	scsi_block_requests(hba->host);
+	ufshcd_scsi_block_requests(hba);
 	err = ufshcd_get_ee_status(hba, &status);
 	if (err) {
 		dev_err(hba->dev, "%s: failed to get exception status %d\n",
@@ -5214,7 +5183,7 @@ static void ufshcd_exception_event_handler(struct work_struct *work)
 		ufshcd_bkops_exception_event_handler(hba);
 
 out:
-	scsi_unblock_requests(hba->host);
+	ufshcd_scsi_unblock_requests(hba);
 	pm_runtime_put_sync(hba->dev);
 	return;
 }
@@ -5348,8 +5317,8 @@ static void ufshcd_err_handler(struct work_struct *work)
 
 	/*
 	 * if host reset is required then skip clearing the pending
-	 * transfers forcefully because they will automatically get
-	 * cleared after link startup.
+	 * transfers forcefully because they will get cleared during
+	 * host reset and restore
 	 */
 	if (needs_reset)
 		goto skip_pending_xfer_clear;
@@ -5603,6 +5572,27 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba)
 	return retval;
 }
 
+struct ctm_info {
+	struct ufs_hba	*hba;
+	unsigned long	pending;
+	unsigned int	ncpl;
+};
+
+static bool ufshcd_compl_tm(struct request *req, void *priv, bool reserved)
+{
+	struct ctm_info *const ci = priv;
+	struct completion *c;
+
+	WARN_ON_ONCE(reserved);
+	if (test_bit(req->tag, &ci->pending))
+		return true;
+	ci->ncpl++;
+	c = req->end_io_data;
+	if (c)
+		complete(c);
+	return true;
+}
+
 /**
  * ufshcd_tmc_handler - handle task management function completion
  * @hba: per adapter instance
@@ -5613,16 +5603,14 @@ static irqreturn_t ufshcd_check_errors(struct ufs_hba *hba)
  */
 static irqreturn_t ufshcd_tmc_handler(struct ufs_hba *hba)
 {
-	u32 tm_doorbell;
+	struct request_queue *q = hba->tmf_queue;
+	struct ctm_info ci = {
+		.hba	 = hba,
+		.pending = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL),
+	};
 
-	tm_doorbell = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
-	hba->tm_condition = tm_doorbell ^ hba->outstanding_tasks;
-	if (hba->tm_condition) {
-		wake_up(&hba->tm_wq);
-		return IRQ_HANDLED;
-	} else {
-		return IRQ_NONE;
-	}
+	blk_mq_tagset_busy_iter(q->tag_set, ufshcd_compl_tm, &ci);
+	return ci.ncpl ? IRQ_HANDLED : IRQ_NONE;
 }
 
 /**
@@ -5728,7 +5716,10 @@ out:
 static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 		struct utp_task_req_desc *treq, u8 tm_function)
 {
+	struct request_queue *q = hba->tmf_queue;
 	struct Scsi_Host *host = hba->host;
+	DECLARE_COMPLETION_ONSTACK(wait);
+	struct request *req;
 	unsigned long flags;
 	int free_slot, task_tag, err;
 
@@ -5737,7 +5728,10 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	 * Even though we use wait_event() which sleeps indefinitely,
 	 * the maximum wait time is bounded by %TM_CMD_TIMEOUT.
 	 */
-	wait_event(hba->tm_tag_wq, ufshcd_get_tm_free_slot(hba, &free_slot));
+	req = blk_get_request(q, REQ_OP_DRV_OUT, BLK_MQ_REQ_RESERVED);
+	req->end_io_data = &wait;
+	free_slot = req->tag;
+	WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs);
 	ufshcd_hold(hba, false);
 
 	spin_lock_irqsave(host->host_lock, flags);
@@ -5763,10 +5757,14 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_send");
 
 	/* wait until the task management command is completed */
-	err = wait_event_timeout(hba->tm_wq,
-			test_bit(free_slot, &hba->tm_condition),
+	err = wait_for_completion_io_timeout(&wait,
 			msecs_to_jiffies(TM_CMD_TIMEOUT));
 	if (!err) {
+		/*
+		 * Make sure that ufshcd_compl_tm() does not trigger a
+		 * use-after-free.
+		 */
+		req->end_io_data = NULL;
 		ufshcd_add_tm_upiu_trace(hba, task_tag, "tm_complete_err");
 		dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
 				__func__, tm_function);
@@ -5785,9 +5783,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba,
 	__clear_bit(free_slot, &hba->outstanding_tasks);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
-	clear_bit(free_slot, &hba->tm_condition);
-	ufshcd_put_tm_slot(hba, free_slot);
-	wake_up(&hba->tm_tag_wq);
+	blk_put_request(req);
 
 	ufshcd_release(hba);
 	return err;
@@ -5863,6 +5859,8 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 					enum dev_cmd_type cmd_type,
 					enum query_opcode desc_op)
 {
+	struct request_queue *q = hba->cmd_queue;
+	struct request *req;
 	struct ufshcd_lrb *lrbp;
 	int err = 0;
 	int tag;
@@ -5872,7 +5870,13 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 
 	down_read(&hba->clk_scaling_lock);
 
-	wait_event(hba->dev_cmd.tag_wq, ufshcd_get_dev_cmd_tag(hba, &tag));
+	req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto out_unlock;
+	}
+	tag = req->tag;
+	WARN_ON_ONCE(!ufshcd_valid_tag(hba, tag));
 
 	init_completion(&wait);
 	lrbp = &hba->lrb[tag];
@@ -5948,8 +5952,8 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba,
 		}
 	}
 
-	ufshcd_put_dev_cmd_tag(hba, tag);
-	wake_up(&hba->dev_cmd.tag_wq);
+	blk_put_request(req);
+out_unlock:
 	up_read(&hba->clk_scaling_lock);
 	return err;
 }
@@ -6244,9 +6248,6 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	hba->lrb[tag].cmd = NULL;
 	spin_unlock_irqrestore(host->host_lock, flags);
 
-	clear_bit_unlock(tag, &hba->lrb_in_use);
-	wake_up(&hba->dev_cmd.tag_wq);
-
 out:
 	if (!err) {
 		err = SUCCESS;
@@ -6279,9 +6280,15 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	int err;
 	unsigned long flags;
 
-	/* Reset the host controller */
+	/*
+	 * Stop the host controller and complete the requests
+	 * cleared by h/w
+	 */
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_hba_stop(hba, false);
+	hba->silence_err_logs = true;
+	ufshcd_complete_requests(hba);
+	hba->silence_err_logs = false;
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
 	/* scale up clocks to max frequency before full reinitialization */
@@ -6292,7 +6299,7 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 		goto out;
 
 	/* Establish the link again and restore the device */
-	err = ufshcd_probe_hba(hba);
+	err = ufshcd_probe_hba(hba, false);
 
 	if (!err && (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL))
 		err = -EIO;
@@ -6315,7 +6322,6 @@ out:
 static int ufshcd_reset_and_restore(struct ufs_hba *hba)
 {
 	int err = 0;
-	unsigned long flags;
 	int retries = MAX_HOST_RESET_RETRIES;
 
 	do {
@@ -6325,15 +6331,6 @@ static int ufshcd_reset_and_restore(struct ufs_hba *hba)
 		err = ufshcd_host_reset_and_restore(hba);
 	} while (err && --retries);
 
-	/*
-	 * After reset the door-bell might be cleared, complete
-	 * outstanding requests in s/w here.
-	 */
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	ufshcd_transfer_req_compl(hba);
-	ufshcd_tmc_handler(hba);
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-
 	return err;
 }
 
@@ -6488,7 +6485,8 @@ static void ufshcd_init_icc_levels(struct ufs_hba *hba)
 	if (!desc_buf)
 		return;
 
-	ret = ufshcd_read_power_desc(hba, desc_buf, buff_len);
+	ret = ufshcd_read_desc(hba, QUERY_DESC_IDN_POWER, 0,
+			desc_buf, buff_len);
 	if (ret) {
 		dev_err(hba->dev,
 			"%s: Failed reading power descriptor.len = %d ret = %d",
@@ -6578,16 +6576,13 @@ out:
 	return ret;
 }
 
-static int ufs_get_device_desc(struct ufs_hba *hba,
-			       struct ufs_dev_desc *dev_desc)
+static int ufs_get_device_desc(struct ufs_hba *hba)
 {
 	int err;
 	size_t buff_len;
 	u8 model_index;
 	u8 *desc_buf;
-
-	if (!dev_desc)
-		return -EINVAL;
+	struct ufs_dev_info *dev_info = &hba->dev_info;
 
 	buff_len = max_t(size_t, hba->desc_size.dev_desc,
 			 QUERY_DESC_MAX_SIZE + 1);
@@ -6597,7 +6592,8 @@ static int ufs_get_device_desc(struct ufs_hba *hba,
 		goto out;
 	}
 
-	err = ufshcd_read_device_desc(hba, desc_buf, hba->desc_size.dev_desc);
+	err = ufshcd_read_desc(hba, QUERY_DESC_IDN_DEVICE, 0, desc_buf,
+			hba->desc_size.dev_desc);
 	if (err) {
 		dev_err(hba->dev, "%s: Failed reading Device Desc. err = %d\n",
 			__func__, err);
@@ -6608,12 +6604,12 @@ static int ufs_get_device_desc(struct ufs_hba *hba,
 	 * getting vendor (manufacturerID) and Bank Index in big endian
 	 * format
 	 */
-	dev_desc->wmanufacturerid = desc_buf[DEVICE_DESC_PARAM_MANF_ID] << 8 |
+	dev_info->wmanufacturerid = desc_buf[DEVICE_DESC_PARAM_MANF_ID] << 8 |
 				     desc_buf[DEVICE_DESC_PARAM_MANF_ID + 1];
 
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
 	err = ufshcd_read_string_desc(hba, model_index,
-				      &dev_desc->model, SD_ASCII_STD);
+				      &dev_info->model, SD_ASCII_STD);
 	if (err < 0) {
 		dev_err(hba->dev, "%s: Failed reading Product Name. err = %d\n",
 			__func__, err);
@@ -6631,23 +6627,25 @@ out:
 	return err;
 }
 
-static void ufs_put_device_desc(struct ufs_dev_desc *dev_desc)
+static void ufs_put_device_desc(struct ufs_hba *hba)
 {
-	kfree(dev_desc->model);
-	dev_desc->model = NULL;
+	struct ufs_dev_info *dev_info = &hba->dev_info;
+
+	kfree(dev_info->model);
+	dev_info->model = NULL;
 }
 
-static void ufs_fixup_device_setup(struct ufs_hba *hba,
-				   struct ufs_dev_desc *dev_desc)
+static void ufs_fixup_device_setup(struct ufs_hba *hba)
 {
 	struct ufs_dev_fix *f;
+	struct ufs_dev_info *dev_info = &hba->dev_info;
 
 	for (f = ufs_fixups; f->quirk; f++) {
-		if ((f->card.wmanufacturerid == dev_desc->wmanufacturerid ||
-		     f->card.wmanufacturerid == UFS_ANY_VENDOR) &&
-		     ((dev_desc->model &&
-		       STR_PRFX_EQUAL(f->card.model, dev_desc->model)) ||
-		      !strcmp(f->card.model, UFS_ANY_MODEL)))
+		if ((f->wmanufacturerid == dev_info->wmanufacturerid ||
+		     f->wmanufacturerid == UFS_ANY_VENDOR) &&
+		     ((dev_info->model &&
+		       STR_PRFX_EQUAL(f->model, dev_info->model)) ||
+		      !strcmp(f->model, UFS_ANY_MODEL)))
 			hba->dev_quirks |= f->quirk;
 	}
 }
@@ -6863,6 +6861,37 @@ static void ufshcd_init_desc_sizes(struct ufs_hba *hba)
 		hba->desc_size.hlth_desc = QUERY_DESC_HEALTH_DEF_SIZE;
 }
 
+static int ufshcd_device_geo_params_init(struct ufs_hba *hba)
+{
+	int err;
+	size_t buff_len;
+	u8 *desc_buf;
+
+	buff_len = hba->desc_size.geom_desc;
+	desc_buf = kmalloc(buff_len, GFP_KERNEL);
+	if (!desc_buf) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = ufshcd_read_desc(hba, QUERY_DESC_IDN_GEOMETRY, 0,
+			desc_buf, buff_len);
+	if (err) {
+		dev_err(hba->dev, "%s: Failed reading Geometry Desc. err = %d\n",
+				__func__, err);
+		goto out;
+	}
+
+	if (desc_buf[GEOMETRY_DESC_PARAM_MAX_NUM_LUN] == 1)
+		hba->dev_info.max_lu_supported = 32;
+	else if (desc_buf[GEOMETRY_DESC_PARAM_MAX_NUM_LUN] == 0)
+		hba->dev_info.max_lu_supported = 8;
+
+out:
+	kfree(desc_buf);
+	return err;
+}
+
 static struct ufs_ref_clk ufs_ref_clk_freqs[] = {
 	{19200000, REF_CLK_FREQ_19_2_MHZ},
 	{26000000, REF_CLK_FREQ_26_MHZ},
@@ -6931,15 +6960,92 @@ out:
 	return err;
 }
 
+static int ufshcd_device_params_init(struct ufs_hba *hba)
+{
+	bool flag;
+	int ret;
+
+	/* Clear any previous UFS device information */
+	memset(&hba->dev_info, 0, sizeof(hba->dev_info));
+
+	/* Init check for device descriptor sizes */
+	ufshcd_init_desc_sizes(hba);
+
+	/* Init UFS geometry descriptor related parameters */
+	ret = ufshcd_device_geo_params_init(hba);
+	if (ret)
+		goto out;
+
+	/* Check and apply UFS device quirks */
+	ret = ufs_get_device_desc(hba);
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
+			__func__, ret);
+		goto out;
+	}
+
+	ufs_fixup_device_setup(hba);
+
+	if (!ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_READ_FLAG,
+			QUERY_FLAG_IDN_PWR_ON_WPE, &flag))
+		hba->dev_info.f_power_on_wp_en = flag;
+
+	/* Probe maximum power mode co-supported by both UFS host and device */
+	if (ufshcd_get_max_pwr_mode(hba))
+		dev_err(hba->dev,
+			"%s: Failed getting max supported power mode\n",
+			__func__);
+out:
+	return ret;
+}
+
+/**
+ * ufshcd_add_lus - probe and add UFS logical units
+ * @hba: per-adapter instance
+ */
+static int ufshcd_add_lus(struct ufs_hba *hba)
+{
+	int ret;
+
+	ufshcd_init_icc_levels(hba);
+
+	/* Add required well known logical units to scsi mid layer */
+	ret = ufshcd_scsi_add_wlus(hba);
+	if (ret)
+		goto out;
+
+	/* Initialize devfreq after UFS device is detected */
+	if (ufshcd_is_clkscaling_supported(hba)) {
+		memcpy(&hba->clk_scaling.saved_pwr_info.info,
+			&hba->pwr_info,
+			sizeof(struct ufs_pa_layer_attr));
+		hba->clk_scaling.saved_pwr_info.is_valid = true;
+		if (!hba->devfreq) {
+			ret = ufshcd_devfreq_init(hba);
+			if (ret)
+				goto out;
+		}
+
+		hba->clk_scaling.is_allowed = true;
+	}
+
+	ufs_bsg_probe(hba);
+	scsi_scan_host(hba->host);
+	pm_runtime_put_sync(hba->dev);
+
+out:
+	return ret;
+}
+
 /**
  * ufshcd_probe_hba - probe hba to detect device and initialize
  * @hba: per-adapter instance
+ * @async: asynchronous execution or not
  *
  * Execute link-startup and verify device initialization
  */
-static int ufshcd_probe_hba(struct ufs_hba *hba)
+static int ufshcd_probe_hba(struct ufs_hba *hba, bool async)
 {
-	struct ufs_dev_desc card = {0};
 	int ret;
 	ktime_t start = ktime_get();
 
@@ -6957,27 +7063,26 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	/* UniPro link is active now */
 	ufshcd_set_link_active(hba);
 
+	/* Verify device initialization by sending NOP OUT UPIU */
 	ret = ufshcd_verify_dev_init(hba);
 	if (ret)
 		goto out;
 
+	/* Initiate UFS initialization, and waiting until completion */
 	ret = ufshcd_complete_dev_init(hba);
 	if (ret)
 		goto out;
 
-	/* Init check for device descriptor sizes */
-	ufshcd_init_desc_sizes(hba);
-
-	ret = ufs_get_device_desc(hba, &card);
-	if (ret) {
-		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
-			__func__, ret);
-		goto out;
+	/*
+	 * Initialize UFS device parameters used by driver, these
+	 * parameters are associated with UFS descriptors.
+	 */
+	if (async) {
+		ret = ufshcd_device_params_init(hba);
+		if (ret)
+			goto out;
 	}
 
-	ufs_fixup_device_setup(hba, &card);
-	ufs_put_device_desc(&card);
-
 	ufshcd_tune_unipro_params(hba);
 
 	/* UFS device is also active now */
@@ -6985,11 +7090,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	ufshcd_force_reset_auto_bkops(hba);
 	hba->wlun_dev_clr_ua = true;
 
-	if (ufshcd_get_max_pwr_mode(hba)) {
-		dev_err(hba->dev,
-			"%s: Failed getting max supported power mode\n",
-			__func__);
-	} else {
+	/* Gear up to HS gear if supported */
+	if (hba->max_pwr_info.is_valid) {
 		/*
 		 * Set the right value to bRefClkFreq before attempting to
 		 * switch to HS gears.
@@ -7010,59 +7112,7 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	/* Enable Auto-Hibernate if configured */
 	ufshcd_auto_hibern8_enable(hba);
 
-	/*
-	 * If we are in error handling context or in power management callbacks
-	 * context, no need to scan the host
-	 */
-	if (!ufshcd_eh_in_progress(hba) && !hba->pm_op_in_progress) {
-		bool flag;
-
-		/* clear any previous UFS device information */
-		memset(&hba->dev_info, 0, sizeof(hba->dev_info));
-		if (!ufshcd_query_flag_retry(hba, UPIU_QUERY_OPCODE_READ_FLAG,
-				QUERY_FLAG_IDN_PWR_ON_WPE, &flag))
-			hba->dev_info.f_power_on_wp_en = flag;
-
-		if (!hba->is_init_prefetch)
-			ufshcd_init_icc_levels(hba);
-
-		/* Add required well known logical units to scsi mid layer */
-		if (ufshcd_scsi_add_wlus(hba))
-			goto out;
-
-		/* Initialize devfreq after UFS device is detected */
-		if (ufshcd_is_clkscaling_supported(hba)) {
-			memcpy(&hba->clk_scaling.saved_pwr_info.info,
-				&hba->pwr_info,
-				sizeof(struct ufs_pa_layer_attr));
-			hba->clk_scaling.saved_pwr_info.is_valid = true;
-			if (!hba->devfreq) {
-				ret = ufshcd_devfreq_init(hba);
-				if (ret)
-					goto out;
-			}
-			hba->clk_scaling.is_allowed = true;
-		}
-
-		ufs_bsg_probe(hba);
-
-		scsi_scan_host(hba->host);
-		pm_runtime_put_sync(hba->dev);
-	}
-
-	if (!hba->is_init_prefetch)
-		hba->is_init_prefetch = true;
-
 out:
-	/*
-	 * If we failed to initialize the device or the device is not
-	 * present, turn off the power/clocks etc.
-	 */
-	if (ret && !ufshcd_eh_in_progress(hba) && !hba->pm_op_in_progress) {
-		pm_runtime_put_sync(hba->dev);
-		ufshcd_exit_clk_scaling(hba);
-		ufshcd_hba_exit(hba);
-	}
 
 	trace_ufshcd_init(dev_name(hba->dev), ret,
 		ktime_to_us(ktime_sub(ktime_get(), start)),
@@ -7078,43 +7128,25 @@ out:
 static void ufshcd_async_scan(void *data, async_cookie_t cookie)
 {
 	struct ufs_hba *hba = (struct ufs_hba *)data;
+	int ret;
 
-	ufshcd_probe_hba(hba);
-}
-
-static enum blk_eh_timer_return ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
-{
-	unsigned long flags;
-	struct Scsi_Host *host;
-	struct ufs_hba *hba;
-	int index;
-	bool found = false;
-
-	if (!scmd || !scmd->device || !scmd->device->host)
-		return BLK_EH_DONE;
-
-	host = scmd->device->host;
-	hba = shost_priv(host);
-	if (!hba)
-		return BLK_EH_DONE;
-
-	spin_lock_irqsave(host->host_lock, flags);
-
-	for_each_set_bit(index, &hba->outstanding_reqs, hba->nutrs) {
-		if (hba->lrb[index].cmd == scmd) {
-			found = true;
-			break;
-		}
-	}
-
-	spin_unlock_irqrestore(host->host_lock, flags);
+	/* Initialize hba, detect and initialize UFS device */
+	ret = ufshcd_probe_hba(hba, true);
+	if (ret)
+		goto out;
 
+	/* Probe and add UFS logical units  */
+	ret = ufshcd_add_lus(hba);
+out:
 	/*
-	 * Bypass SCSI error handling and reset the block layer timer if this
-	 * SCSI command was not actually dispatched to UFS driver, otherwise
-	 * let SCSI layer handle the error as usual.
+	 * If we failed to initialize the device or the device is not
+	 * present, turn off the power/clocks etc.
 	 */
-	return found ? BLK_EH_DONE : BLK_EH_RESET_TIMER;
+	if (ret) {
+		pm_runtime_put_sync(hba->dev);
+		ufshcd_exit_clk_scaling(hba);
+		ufshcd_hba_exit(hba);
+	}
 }
 
 static const struct attribute_group *ufshcd_driver_groups[] = {
@@ -7135,7 +7167,6 @@ static struct scsi_host_template ufshcd_driver_template = {
 	.eh_abort_handler	= ufshcd_abort,
 	.eh_device_reset_handler = ufshcd_eh_device_reset_handler,
 	.eh_host_reset_handler   = ufshcd_eh_host_reset_handler,
-	.eh_timed_out		= ufshcd_eh_timed_out,
 	.this_id		= -1,
 	.sg_tablesize		= SG_ALL,
 	.cmd_per_lun		= UFSHCD_CMD_PER_LUN,
@@ -7574,6 +7605,7 @@ static void ufshcd_hba_exit(struct ufs_hba *hba)
 		ufshcd_setup_clocks(hba, false);
 		ufshcd_setup_hba_vreg(hba, false);
 		hba->is_powered = false;
+		ufs_put_device_desc(hba);
 	}
 }
 
@@ -7701,8 +7733,7 @@ static int ufshcd_link_state_transition(struct ufs_hba *hba,
 	 * turning off the link would also turn off the device.
 	 */
 	else if ((req_link_state == UIC_LINK_OFF_STATE) &&
-		   (!check_for_bkops || (check_for_bkops &&
-		    !hba->auto_bkops_enabled))) {
+		 (!check_for_bkops || !hba->auto_bkops_enabled)) {
 		/*
 		 * Let's make sure that link is in low power mode, we are doing
 		 * this currently by putting the link in Hibern8. Otherway to
@@ -7908,6 +7939,11 @@ disable_clks:
 	ret = ufshcd_vops_suspend(hba, pm_op);
 	if (ret)
 		goto set_link_active;
+	/*
+	 * Disable the host irq as host controller as there won't be any
+	 * host controller transaction expected till resume.
+	 */
+	ufshcd_disable_irq(hba);
 
 	if (!ufshcd_is_link_active(hba))
 		ufshcd_setup_clocks(hba, false);
@@ -7917,11 +7953,7 @@ disable_clks:
 
 	hba->clk_gating.state = CLKS_OFF;
 	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
-	/*
-	 * Disable the host irq as host controller as there won't be any
-	 * host controller transaction expected till resume.
-	 */
-	ufshcd_disable_irq(hba);
+
 	/* Put the host controller in low power mode if possible */
 	ufshcd_hba_vreg_set_lpm(hba);
 	goto out;
@@ -7974,9 +8006,7 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 		goto out;
 
 	/* enable the host irq as host controller would be active soon */
-	ret = ufshcd_enable_irq(hba);
-	if (ret)
-		goto disable_irq_and_vops_clks;
+	ufshcd_enable_irq(hba);
 
 	ret = ufshcd_vreg_set_hpm(hba);
 	if (ret)
@@ -8250,6 +8280,9 @@ void ufshcd_remove(struct ufs_hba *hba)
 {
 	ufs_bsg_remove(hba);
 	ufs_sysfs_remove_nodes(hba->dev);
+	blk_cleanup_queue(hba->tmf_queue);
+	blk_mq_free_tag_set(&hba->tmf_tag_set);
+	blk_cleanup_queue(hba->cmd_queue);
 	scsi_remove_host(hba->host);
 	/* disable interrupts */
 	ufshcd_disable_intr(hba, hba->intr_mask);
@@ -8328,6 +8361,18 @@ out_error:
 }
 EXPORT_SYMBOL(ufshcd_alloc_host);
 
+/* This function exists because blk_mq_alloc_tag_set() requires this. */
+static blk_status_t ufshcd_queue_tmf(struct blk_mq_hw_ctx *hctx,
+				     const struct blk_mq_queue_data *qd)
+{
+	WARN_ON_ONCE(true);
+	return BLK_STS_NOTSUPP;
+}
+
+static const struct blk_mq_ops ufshcd_tmf_ops = {
+	.queue_rq = ufshcd_queue_tmf,
+};
+
 /**
  * ufshcd_init - Driver initialization routine
  * @hba: per-adapter instance
@@ -8397,10 +8442,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	hba->max_pwr_info.is_valid = false;
 
-	/* Initailize wait queue for task management */
-	init_waitqueue_head(&hba->tm_wq);
-	init_waitqueue_head(&hba->tm_tag_wq);
-
 	/* Initialize work queues */
 	INIT_WORK(&hba->eh_work, ufshcd_err_handler);
 	INIT_WORK(&hba->eeh_work, ufshcd_exception_event_handler);
@@ -8413,9 +8454,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	init_rwsem(&hba->clk_scaling_lock);
 
-	/* Initialize device management tag acquire wait queue */
-	init_waitqueue_head(&hba->dev_cmd.tag_wq);
-
 	ufshcd_init_clk_gating(hba);
 
 	ufshcd_init_clk_scaling(hba);
@@ -8449,6 +8487,27 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		goto exit_gating;
 	}
 
+	hba->cmd_queue = blk_mq_init_queue(&hba->host->tag_set);
+	if (IS_ERR(hba->cmd_queue)) {
+		err = PTR_ERR(hba->cmd_queue);
+		goto out_remove_scsi_host;
+	}
+
+	hba->tmf_tag_set = (struct blk_mq_tag_set) {
+		.nr_hw_queues	= 1,
+		.queue_depth	= hba->nutmrs,
+		.ops		= &ufshcd_tmf_ops,
+		.flags		= BLK_MQ_F_NO_SCHED,
+	};
+	err = blk_mq_alloc_tag_set(&hba->tmf_tag_set);
+	if (err < 0)
+		goto free_cmd_queue;
+	hba->tmf_queue = blk_mq_init_queue(&hba->tmf_tag_set);
+	if (IS_ERR(hba->tmf_queue)) {
+		err = PTR_ERR(hba->tmf_queue);
+		goto free_tmf_tag_set;
+	}
+
 	/* Reset the attached device */
 	ufshcd_vops_device_reset(hba);
 
@@ -8458,7 +8517,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		dev_err(hba->dev, "Host controller enable failed\n");
 		ufshcd_print_host_regs(hba);
 		ufshcd_print_host_state(hba);
-		goto out_remove_scsi_host;
+		goto free_tmf_queue;
 	}
 
 	/*
@@ -8495,6 +8554,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 
 	return 0;
 
+free_tmf_queue:
+	blk_cleanup_queue(hba->tmf_queue);
+free_tmf_tag_set:
+	blk_mq_free_tag_set(&hba->tmf_tag_set);
+free_cmd_queue:
+	blk_cleanup_queue(hba->cmd_queue);
 out_remove_scsi_host:
 	scsi_remove_host(hba->host);
 exit_gating:
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 2740f6941ec6..2ae6c7c8528c 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -212,13 +212,11 @@ struct ufs_query {
  * @type: device management command type - Query, NOP OUT
  * @lock: lock to allow one command at a time
  * @complete: internal commands completion
- * @tag_wq: wait queue until free command slot is available
  */
 struct ufs_dev_cmd {
 	enum dev_cmd_type type;
 	struct mutex lock;
 	struct completion *complete;
-	wait_queue_head_t tag_wq;
 	struct ufs_query query;
 };
 
@@ -322,7 +320,7 @@ struct ufs_hba_variant_ops {
 	void	(*setup_task_mgmt)(struct ufs_hba *, int, u8);
 	void    (*hibern8_notify)(struct ufs_hba *, enum uic_cmd_dme,
 					enum ufs_notify_change_status);
-	int	(*apply_dev_quirks)(struct ufs_hba *);
+	int	(*apply_dev_quirks)(struct ufs_hba *hba);
 	int     (*suspend)(struct ufs_hba *, enum ufs_pm_op);
 	int     (*resume)(struct ufs_hba *, enum ufs_pm_op);
 	void	(*dbg_register_dump)(struct ufs_hba *hba);
@@ -483,7 +481,7 @@ struct ufs_stats {
  * @host: Scsi_Host instance of the driver
  * @dev: device handle
  * @lrb: local reference block
- * @lrb_in_use: lrb in use
+ * @cmd_queue: Used to allocate command tags from hba->host->tag_set.
  * @outstanding_tasks: Bits representing outstanding task requests
  * @outstanding_reqs: Bits representing outstanding transfer requests
  * @capabilities: UFS Controller Capabilities
@@ -495,17 +493,14 @@ struct ufs_stats {
  * @irq: Irq number of the controller
  * @active_uic_cmd: handle of active UIC command
  * @uic_cmd_mutex: mutex for uic command
- * @tm_wq: wait queue for task management
- * @tm_tag_wq: wait queue for free task management slots
- * @tm_slots_in_use: bit map of task management request slots in use
+ * @tmf_tag_set: TMF tag set.
+ * @tmf_queue: Used to allocate TMF tags.
  * @pwr_done: completion for power mode change
- * @tm_condition: condition variable for task management
  * @ufshcd_state: UFSHCD states
  * @eh_flags: Error handling flags
  * @intr_mask: Interrupt Mask Bits
  * @ee_ctrl_mask: Exception event control mask
  * @is_powered: flag to check if HBA is powered
- * @is_init_prefetch: flag to check if data was pre-fetched in initialization
  * @init_prefetch_data: data pre-fetched during initialization
  * @eh_work: Worker to handle UFS errors that require s/w attention
  * @eeh_work: Worker to handle exception events
@@ -513,6 +508,7 @@ struct ufs_stats {
  * @uic_error: UFS interconnect layer error status
  * @saved_err: sticky error mask
  * @saved_uic_err: sticky UIC error mask
+ * @silence_err_logs: flag to silence error logs
  * @dev_cmd: ufs device management command information
  * @last_dme_cmd_tstamp: time stamp of the last completed DME command
  * @auto_bkops_enabled: to track whether bkops is enabled in device
@@ -541,6 +537,7 @@ struct ufs_hba {
 
 	struct Scsi_Host *host;
 	struct device *dev;
+	struct request_queue *cmd_queue;
 	/*
 	 * This field is to keep a reference to "scsi_device" corresponding to
 	 * "UFS device" W-LU.
@@ -561,7 +558,6 @@ struct ufs_hba {
 	u32 ahit;
 
 	struct ufshcd_lrb *lrb;
-	unsigned long lrb_in_use;
 
 	unsigned long outstanding_tasks;
 	unsigned long outstanding_reqs;
@@ -643,10 +639,8 @@ struct ufs_hba {
 	/* Device deviations from standard UFS device spec. */
 	unsigned int dev_quirks;
 
-	wait_queue_head_t tm_wq;
-	wait_queue_head_t tm_tag_wq;
-	unsigned long tm_condition;
-	unsigned long tm_slots_in_use;
+	struct blk_mq_tag_set tmf_tag_set;
+	struct request_queue *tmf_queue;
 
 	struct uic_command *active_uic_cmd;
 	struct mutex uic_cmd_mutex;
@@ -657,7 +651,6 @@ struct ufs_hba {
 	u32 intr_mask;
 	u16 ee_ctrl_mask;
 	bool is_powered;
-	bool is_init_prefetch;
 	struct ufs_init_prefetch init_prefetch_data;
 
 	/* Work Queues */
@@ -670,6 +663,7 @@ struct ufs_hba {
 	u32 saved_err;
 	u32 saved_uic_err;
 	struct ufs_stats ufs_stats;
+	bool silence_err_logs;
 
 	/* Device management request data */
 	struct ufs_dev_cmd dev_cmd;
@@ -803,12 +797,17 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg)
 
 int ufshcd_alloc_host(struct device *, struct ufs_hba **);
 void ufshcd_dealloc_host(struct ufs_hba *);
+int ufshcd_hba_enable(struct ufs_hba *hba);
 int ufshcd_init(struct ufs_hba * , void __iomem * , unsigned int);
+int ufshcd_make_hba_operational(struct ufs_hba *hba);
 void ufshcd_remove(struct ufs_hba *);
+int ufshcd_uic_hibern8_exit(struct ufs_hba *hba);
 int ufshcd_wait_for_register(struct ufs_hba *hba, u32 reg, u32 mask,
 				u32 val, unsigned long interval_us,
 				unsigned long timeout_ms, bool can_sleep);
 void ufshcd_parse_dev_ref_clk_freq(struct ufs_hba *hba, struct clk *refclk);
+void ufshcd_update_reg_hist(struct ufs_err_reg_hist *reg_hist,
+			    u32 reg);
 
 static inline void check_upiu_size(void)
 {
@@ -927,6 +926,7 @@ int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	enum flag_idn idn, bool *flag_res);
 
 void ufshcd_auto_hibern8_enable(struct ufs_hba *hba);
+void ufshcd_auto_hibern8_update(struct ufs_hba *hba, u32 ahit);
 
 #define SD_ASCII_STD true
 #define SD_RAW false
@@ -1086,8 +1086,10 @@ static inline void ufshcd_vops_dbg_register_dump(struct ufs_hba *hba)
 
 static inline void ufshcd_vops_device_reset(struct ufs_hba *hba)
 {
-	if (hba->vops && hba->vops->device_reset)
+	if (hba->vops && hba->vops->device_reset) {
 		hba->vops->device_reset(hba);
+		ufshcd_update_reg_hist(&hba->ufs_stats.dev_reset, 0);
+	}
 }
 
 extern struct ufs_pm_lvl_states ufs_pm_lvl_states[];
diff --git a/drivers/scsi/ufs/unipro.h b/drivers/scsi/ufs/unipro.h
index f539f873f94d..3dc4d8b76509 100644
--- a/drivers/scsi/ufs/unipro.h
+++ b/drivers/scsi/ufs/unipro.h
@@ -161,6 +161,17 @@
 /* PHY Adapter Protocol Constants */
 #define PA_MAXDATALANES	4
 
+#define DL_FC0ProtectionTimeOutVal_Default	8191
+#define DL_TC0ReplayTimeOutVal_Default		65535
+#define DL_AFC0ReqTimeOutVal_Default		32767
+#define DL_FC1ProtectionTimeOutVal_Default	8191
+#define DL_TC1ReplayTimeOutVal_Default		65535
+#define DL_AFC1ReqTimeOutVal_Default		32767
+
+#define DME_LocalFC0ProtectionTimeOutVal	0xD041
+#define DME_LocalTC0ReplayTimeOutVal		0xD042
+#define DME_LocalAFC0ReqTimeOutVal		0xD043
+
 /* PA power modes */
 enum {
 	FAST_MODE	= 1,
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 70008816c91f..c3f010df641e 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -365,7 +365,7 @@ static int pvscsi_map_buffers(struct pvscsi_adapter *adapter,
 		int segs = scsi_dma_map(cmd);
 
 		if (segs == -ENOMEM) {
-			scmd_printk(KERN_ERR, cmd,
+			scmd_printk(KERN_DEBUG, cmd,
 				    "vmw_pvscsi: Failed to map cmd sglist for DMA.\n");
 			return -ENOMEM;
 		} else if (segs > 1) {
@@ -392,7 +392,7 @@ static int pvscsi_map_buffers(struct pvscsi_adapter *adapter,
 		ctx->dataPA = dma_map_single(&adapter->dev->dev, sg, bufflen,
 					     cmd->sc_data_direction);
 		if (dma_mapping_error(&adapter->dev->dev, ctx->dataPA)) {
-			scmd_printk(KERN_ERR, cmd,
+			scmd_printk(KERN_DEBUG, cmd,
 				    "vmw_pvscsi: Failed to map direct data buffer for DMA.\n");
 			return -ENOMEM;
 		}
@@ -402,6 +402,17 @@ static int pvscsi_map_buffers(struct pvscsi_adapter *adapter,
 	return 0;
 }
 
+/*
+ * The device incorrectly doesn't clear the first byte of the sense
+ * buffer in some cases. We have to do it ourselves.
+ * Otherwise we run into trouble when SWIOTLB is forced.
+ */
+static void pvscsi_patch_sense(struct scsi_cmnd *cmd)
+{
+	if (cmd->sense_buffer)
+		cmd->sense_buffer[0] = 0;
+}
+
 static void pvscsi_unmap_buffers(const struct pvscsi_adapter *adapter,
 				 struct pvscsi_ctx *ctx)
 {
@@ -544,6 +555,8 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,
 	cmd = ctx->cmd;
 	abort_cmp = ctx->abort_cmp;
 	pvscsi_unmap_buffers(adapter, ctx);
+	if (sdstat != SAM_STAT_CHECK_CONDITION)
+		pvscsi_patch_sense(cmd);
 	pvscsi_release_context(adapter, ctx);
 	if (abort_cmp) {
 		/*
@@ -712,7 +725,7 @@ static int pvscsi_queue_ring(struct pvscsi_adapter *adapter,
 				cmd->sense_buffer, SCSI_SENSE_BUFFERSIZE,
 				DMA_FROM_DEVICE);
 		if (dma_mapping_error(&adapter->dev->dev, ctx->sensePA)) {
-			scmd_printk(KERN_ERR, cmd,
+			scmd_printk(KERN_DEBUG, cmd,
 				    "vmw_pvscsi: Failed to map sense buffer for DMA.\n");
 			ctx->sensePA = 0;
 			return -ENOMEM;
@@ -873,6 +886,7 @@ static void pvscsi_reset_all(struct pvscsi_adapter *adapter)
 			scmd_printk(KERN_ERR, cmd,
 				    "Forced reset on cmd %p\n", cmd);
 			pvscsi_unmap_buffers(adapter, ctx);
+			pvscsi_patch_sense(cmd);
 			pvscsi_release_context(adapter, ctx);
 			cmd->result = (DID_RESET << 16);
 			cmd->scsi_done(cmd);
diff --git a/drivers/soc/lantiq/fpi-bus.c b/drivers/soc/lantiq/fpi-bus.c
index cb0303a0fe60..dff1375851cf 100644
--- a/drivers/soc/lantiq/fpi-bus.c
+++ b/drivers/soc/lantiq/fpi-bus.c
@@ -28,14 +28,12 @@ static int ltq_fpi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct resource *res_xbar;
 	struct regmap *rcu_regmap;
 	void __iomem *xbar_membase;
 	u32 rcu_ahb_endianness_reg_offset;
 	int ret;
 
-	res_xbar = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	xbar_membase = devm_ioremap_resource(dev, res_xbar);
+	xbar_membase = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(xbar_membase))
 		return PTR_ERR(xbar_membase);
 
diff --git a/drivers/soc/mediatek/mtk-cmdq-helper.c b/drivers/soc/mediatek/mtk-cmdq-helper.c
index 3c82de5f9417..9add0fd5fa6c 100644
--- a/drivers/soc/mediatek/mtk-cmdq-helper.c
+++ b/drivers/soc/mediatek/mtk-cmdq-helper.c
@@ -9,12 +9,54 @@
 #include <linux/mailbox_controller.h>
 #include <linux/soc/mediatek/mtk-cmdq.h>
 
-#define CMDQ_ARG_A_WRITE_MASK	0xffff
 #define CMDQ_WRITE_ENABLE_MASK	BIT(0)
+#define CMDQ_POLL_ENABLE_MASK	BIT(0)
 #define CMDQ_EOC_IRQ_EN		BIT(0)
 #define CMDQ_EOC_CMD		((u64)((CMDQ_CODE_EOC << CMDQ_OP_CODE_SHIFT)) \
 				<< 32 | CMDQ_EOC_IRQ_EN)
 
+struct cmdq_instruction {
+	union {
+		u32 value;
+		u32 mask;
+	};
+	union {
+		u16 offset;
+		u16 event;
+	};
+	u8 subsys;
+	u8 op;
+};
+
+int cmdq_dev_get_client_reg(struct device *dev,
+			    struct cmdq_client_reg *client_reg, int idx)
+{
+	struct of_phandle_args spec;
+	int err;
+
+	if (!client_reg)
+		return -ENOENT;
+
+	err = of_parse_phandle_with_fixed_args(dev->of_node,
+					       "mediatek,gce-client-reg",
+					       3, idx, &spec);
+	if (err < 0) {
+		dev_err(dev,
+			"error %d can't parse gce-client-reg property (%d)",
+			err, idx);
+
+		return err;
+	}
+
+	client_reg->subsys = (u8)spec.args[0];
+	client_reg->offset = (u16)spec.args[1];
+	client_reg->size = (u16)spec.args[2];
+	of_node_put(spec.np);
+
+	return 0;
+}
+EXPORT_SYMBOL(cmdq_dev_get_client_reg);
+
 static void cmdq_client_timeout(struct timer_list *t)
 {
 	struct cmdq_client *client = from_timer(client, t, timer);
@@ -110,10 +152,10 @@ void cmdq_pkt_destroy(struct cmdq_pkt *pkt)
 }
 EXPORT_SYMBOL(cmdq_pkt_destroy);
 
-static int cmdq_pkt_append_command(struct cmdq_pkt *pkt, enum cmdq_code code,
-				   u32 arg_a, u32 arg_b)
+static int cmdq_pkt_append_command(struct cmdq_pkt *pkt,
+				   struct cmdq_instruction inst)
 {
-	u64 *cmd_ptr;
+	struct cmdq_instruction *cmd_ptr;
 
 	if (unlikely(pkt->cmd_buf_size + CMDQ_INST_SIZE > pkt->buf_size)) {
 		/*
@@ -129,8 +171,9 @@ static int cmdq_pkt_append_command(struct cmdq_pkt *pkt, enum cmdq_code code,
 			__func__, (u32)pkt->buf_size);
 		return -ENOMEM;
 	}
+
 	cmd_ptr = pkt->va_base + pkt->cmd_buf_size;
-	(*cmd_ptr) = (u64)((code << CMDQ_OP_CODE_SHIFT) | arg_a) << 32 | arg_b;
+	*cmd_ptr = inst;
 	pkt->cmd_buf_size += CMDQ_INST_SIZE;
 
 	return 0;
@@ -138,24 +181,34 @@ static int cmdq_pkt_append_command(struct cmdq_pkt *pkt, enum cmdq_code code,
 
 int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value)
 {
-	u32 arg_a = (offset & CMDQ_ARG_A_WRITE_MASK) |
-		    (subsys << CMDQ_SUBSYS_SHIFT);
+	struct cmdq_instruction inst;
 
-	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WRITE, arg_a, value);
+	inst.op = CMDQ_CODE_WRITE;
+	inst.value = value;
+	inst.offset = offset;
+	inst.subsys = subsys;
+
+	return cmdq_pkt_append_command(pkt, inst);
 }
 EXPORT_SYMBOL(cmdq_pkt_write);
 
 int cmdq_pkt_write_mask(struct cmdq_pkt *pkt, u8 subsys,
 			u16 offset, u32 value, u32 mask)
 {
-	u32 offset_mask = offset;
-	int err = 0;
+	struct cmdq_instruction inst = { {0} };
+	u16 offset_mask = offset;
+	int err;
 
 	if (mask != 0xffffffff) {
-		err = cmdq_pkt_append_command(pkt, CMDQ_CODE_MASK, 0, ~mask);
+		inst.op = CMDQ_CODE_MASK;
+		inst.mask = ~mask;
+		err = cmdq_pkt_append_command(pkt, inst);
+		if (err < 0)
+			return err;
+
 		offset_mask |= CMDQ_WRITE_ENABLE_MASK;
 	}
-	err |= cmdq_pkt_write(pkt, subsys, offset_mask, value);
+	err = cmdq_pkt_write(pkt, subsys, offset_mask, value);
 
 	return err;
 }
@@ -163,43 +216,85 @@ EXPORT_SYMBOL(cmdq_pkt_write_mask);
 
 int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event)
 {
-	u32 arg_b;
+	struct cmdq_instruction inst = { {0} };
 
 	if (event >= CMDQ_MAX_EVENT)
 		return -EINVAL;
 
-	/*
-	 * WFE arg_b
-	 * bit 0-11: wait value
-	 * bit 15: 1 - wait, 0 - no wait
-	 * bit 16-27: update value
-	 * bit 31: 1 - update, 0 - no update
-	 */
-	arg_b = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
+	inst.op = CMDQ_CODE_WFE;
+	inst.value = CMDQ_WFE_OPTION;
+	inst.event = event;
 
-	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WFE, event, arg_b);
+	return cmdq_pkt_append_command(pkt, inst);
 }
 EXPORT_SYMBOL(cmdq_pkt_wfe);
 
 int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event)
 {
+	struct cmdq_instruction inst = { {0} };
+
 	if (event >= CMDQ_MAX_EVENT)
 		return -EINVAL;
 
-	return cmdq_pkt_append_command(pkt, CMDQ_CODE_WFE, event,
-				       CMDQ_WFE_UPDATE);
+	inst.op = CMDQ_CODE_WFE;
+	inst.value = CMDQ_WFE_UPDATE;
+	inst.event = event;
+
+	return cmdq_pkt_append_command(pkt, inst);
 }
 EXPORT_SYMBOL(cmdq_pkt_clear_event);
 
+int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys,
+		  u16 offset, u32 value)
+{
+	struct cmdq_instruction inst = { {0} };
+	int err;
+
+	inst.op = CMDQ_CODE_POLL;
+	inst.value = value;
+	inst.offset = offset;
+	inst.subsys = subsys;
+	err = cmdq_pkt_append_command(pkt, inst);
+
+	return err;
+}
+EXPORT_SYMBOL(cmdq_pkt_poll);
+
+int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
+		       u16 offset, u32 value, u32 mask)
+{
+	struct cmdq_instruction inst = { {0} };
+	int err;
+
+	inst.op = CMDQ_CODE_MASK;
+	inst.mask = ~mask;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
+
+	offset = offset | CMDQ_POLL_ENABLE_MASK;
+	err = cmdq_pkt_poll(pkt, subsys, offset, value);
+
+	return err;
+}
+EXPORT_SYMBOL(cmdq_pkt_poll_mask);
+
 static int cmdq_pkt_finalize(struct cmdq_pkt *pkt)
 {
+	struct cmdq_instruction inst = { {0} };
 	int err;
 
 	/* insert EOC and generate IRQ for each command iteration */
-	err = cmdq_pkt_append_command(pkt, CMDQ_CODE_EOC, 0, CMDQ_EOC_IRQ_EN);
+	inst.op = CMDQ_CODE_EOC;
+	inst.value = CMDQ_EOC_IRQ_EN;
+	err = cmdq_pkt_append_command(pkt, inst);
+	if (err < 0)
+		return err;
 
 	/* JUMP to end */
-	err |= cmdq_pkt_append_command(pkt, CMDQ_CODE_JUMP, 0, CMDQ_JUMP_PASS);
+	inst.op = CMDQ_CODE_JUMP;
+	inst.value = CMDQ_JUMP_PASS;
+	err = cmdq_pkt_append_command(pkt, inst);
 
 	return err;
 }
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index c7266ef295fd..1f59beb7d27e 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -646,8 +646,7 @@ static int orion_spi_probe(struct platform_device *pdev)
 
 	/* The following clock is only used by some SoCs */
 	spi->axi_clk = devm_clk_get(&pdev->dev, "axi");
-	if (IS_ERR(spi->axi_clk) &&
-	    PTR_ERR(spi->axi_clk) == -EPROBE_DEFER) {
+	if (PTR_ERR(spi->axi_clk) == -EPROBE_DEFER) {
 		status = -EPROBE_DEFER;
 		goto out_rel_clk;
 	}
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index c394686a8e7d..38b51eace4f9 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -274,18 +274,6 @@ static void ion_dma_buf_release(struct dma_buf *dmabuf)
 	_ion_buffer_destroy(buffer);
 }
 
-static void *ion_dma_buf_kmap(struct dma_buf *dmabuf, unsigned long offset)
-{
-	struct ion_buffer *buffer = dmabuf->priv;
-
-	return buffer->vaddr + offset * PAGE_SIZE;
-}
-
-static void ion_dma_buf_kunmap(struct dma_buf *dmabuf, unsigned long offset,
-			       void *ptr)
-{
-}
-
 static int ion_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
 					enum dma_data_direction direction)
 {
@@ -349,8 +337,6 @@ static const struct dma_buf_ops dma_buf_ops = {
 	.detach = ion_dma_buf_detatch,
 	.begin_cpu_access = ion_dma_buf_begin_cpu_access,
 	.end_cpu_access = ion_dma_buf_end_cpu_access,
-	.map = ion_dma_buf_kmap,
-	.unmap = ion_dma_buf_kunmap,
 };
 
 static int ion_alloc(size_t len, unsigned int heap_id_mask, unsigned int flags)
diff --git a/drivers/staging/media/Kconfig b/drivers/staging/media/Kconfig
index 642adc4c24d2..c394abffea86 100644
--- a/drivers/staging/media/Kconfig
+++ b/drivers/staging/media/Kconfig
@@ -38,4 +38,8 @@ source "drivers/staging/media/ipu3/Kconfig"
 
 source "drivers/staging/media/soc_camera/Kconfig"
 
+source "drivers/staging/media/phy-rockchip-dphy-rx0/Kconfig"
+
+source "drivers/staging/media/rkisp1/Kconfig"
+
 endif
diff --git a/drivers/staging/media/Makefile b/drivers/staging/media/Makefile
index 2f1711a8aeed..ea9fce8014bb 100644
--- a/drivers/staging/media/Makefile
+++ b/drivers/staging/media/Makefile
@@ -8,3 +8,5 @@ obj-$(CONFIG_TEGRA_VDE)		+= tegra-vde/
 obj-$(CONFIG_VIDEO_HANTRO)	+= hantro/
 obj-$(CONFIG_VIDEO_IPU3_IMGU)	+= ipu3/
 obj-$(CONFIG_SOC_CAMERA)	+= soc_camera/
+obj-$(CONFIG_PHY_ROCKCHIP_DPHY_RX0)	+= phy-rockchip-dphy-rx0/
+obj-$(CONFIG_VIDEO_ROCKCHIP_ISP1)	+= rkisp1/
diff --git a/drivers/staging/media/hantro/Makefile b/drivers/staging/media/hantro/Makefile
index 5d6b0383d280..496b30c3c396 100644
--- a/drivers/staging/media/hantro/Makefile
+++ b/drivers/staging/media/hantro/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_VIDEO_HANTRO) += hantro-vpu.o
 hantro-vpu-y += \
 		hantro_drv.o \
 		hantro_v4l2.o \
+		hantro_postproc.o \
 		hantro_h1_jpeg_enc.o \
 		hantro_g1_h264_dec.o \
 		hantro_g1_mpeg2_dec.o \
diff --git a/drivers/staging/media/hantro/hantro.h b/drivers/staging/media/hantro/hantro.h
index deb90ae37859..b0faa43b3f79 100644
--- a/drivers/staging/media/hantro/hantro.h
+++ b/drivers/staging/media/hantro/hantro.h
@@ -60,6 +60,8 @@ struct hantro_irq {
  * @num_enc_fmts:		Number of encoder formats.
  * @dec_fmts:			Decoder formats.
  * @num_dec_fmts:		Number of decoder formats.
+ * @postproc_fmts:		Post-processor formats.
+ * @num_postproc_fmts:		Number of post-processor formats.
  * @codec:			Supported codecs
  * @codec_ops:			Codec ops.
  * @init:			Initialize hardware.
@@ -70,6 +72,7 @@ struct hantro_irq {
  * @num_clocks:			number of clocks in the array
  * @reg_names:			array of register range names
  * @num_regs:			number of register range names in the array
+ * @postproc_regs:		&struct hantro_postproc_regs pointer
  */
 struct hantro_variant {
 	unsigned int enc_offset;
@@ -78,6 +81,8 @@ struct hantro_variant {
 	unsigned int num_enc_fmts;
 	const struct hantro_fmt *dec_fmts;
 	unsigned int num_dec_fmts;
+	const struct hantro_fmt *postproc_fmts;
+	unsigned int num_postproc_fmts;
 	unsigned int codec;
 	const struct hantro_codec_ops *codec_ops;
 	int (*init)(struct hantro_dev *vpu);
@@ -88,6 +93,7 @@ struct hantro_variant {
 	int num_clocks;
 	const char * const *reg_names;
 	int num_regs;
+	const struct hantro_postproc_regs *postproc_regs;
 };
 
 /**
@@ -213,6 +219,7 @@ struct hantro_dev {
  *			context, and it's called right before
  *			calling v4l2_m2m_job_finish.
  * @codec_ops:		Set of operations related to codec mode.
+ * @postproc:		Post-processing context.
  * @jpeg_enc:		JPEG-encoding context.
  * @mpeg2_dec:		MPEG-2-decoding context.
  * @vp8_dec:		VP8-decoding context.
@@ -237,6 +244,7 @@ struct hantro_ctx {
 			  unsigned int bytesused);
 
 	const struct hantro_codec_ops *codec_ops;
+	struct hantro_postproc_ctx postproc;
 
 	/* Specific for particular codec modes. */
 	union {
@@ -274,6 +282,23 @@ struct hantro_reg {
 	u32 mask;
 };
 
+struct hantro_postproc_regs {
+	struct hantro_reg pipeline_en;
+	struct hantro_reg max_burst;
+	struct hantro_reg clk_gate;
+	struct hantro_reg out_swap32;
+	struct hantro_reg out_endian;
+	struct hantro_reg out_luma_base;
+	struct hantro_reg input_width;
+	struct hantro_reg input_height;
+	struct hantro_reg output_width;
+	struct hantro_reg output_height;
+	struct hantro_reg input_fmt;
+	struct hantro_reg output_fmt;
+	struct hantro_reg orig_width;
+	struct hantro_reg display_width;
+};
+
 /* Logging helpers */
 
 /**
@@ -352,16 +377,30 @@ static inline u32 vdpu_read(struct hantro_dev *vpu, u32 reg)
 	return val;
 }
 
-static inline void hantro_reg_write(struct hantro_dev *vpu,
-				    const struct hantro_reg *reg,
-				    u32 val)
+static inline u32 vdpu_read_mask(struct hantro_dev *vpu,
+				 const struct hantro_reg *reg,
+				 u32 val)
 {
 	u32 v;
 
 	v = vdpu_read(vpu, reg->base);
 	v &= ~(reg->mask << reg->shift);
 	v |= ((val & reg->mask) << reg->shift);
-	vdpu_write_relaxed(vpu, v, reg->base);
+	return v;
+}
+
+static inline void hantro_reg_write(struct hantro_dev *vpu,
+				    const struct hantro_reg *reg,
+				    u32 val)
+{
+	vdpu_write_relaxed(vpu, vdpu_read_mask(vpu, reg, val), reg->base);
+}
+
+static inline void hantro_reg_write_s(struct hantro_dev *vpu,
+				      const struct hantro_reg *reg,
+				      u32 val)
+{
+	vdpu_write(vpu, vdpu_read_mask(vpu, reg, val), reg->base);
 }
 
 bool hantro_is_encoder_ctx(const struct hantro_ctx *ctx);
@@ -381,4 +420,23 @@ hantro_get_dst_buf(struct hantro_ctx *ctx)
 	return v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
 }
 
+static inline bool
+hantro_needs_postproc(struct hantro_ctx *ctx, const struct hantro_fmt *fmt)
+{
+	return fmt->fourcc != V4L2_PIX_FMT_NV12;
+}
+
+static inline dma_addr_t
+hantro_get_dec_buf_addr(struct hantro_ctx *ctx, struct vb2_buffer *vb)
+{
+	if (hantro_needs_postproc(ctx, ctx->vpu_dst_fmt))
+		return ctx->postproc.dec_q[vb->index].dma;
+	return vb2_dma_contig_plane_dma_addr(vb, 0);
+}
+
+void hantro_postproc_disable(struct hantro_ctx *ctx);
+void hantro_postproc_enable(struct hantro_ctx *ctx);
+void hantro_postproc_free(struct hantro_ctx *ctx);
+int hantro_postproc_alloc(struct hantro_ctx *ctx);
+
 #endif /* HANTRO_H_ */
diff --git a/drivers/staging/media/hantro/hantro_drv.c b/drivers/staging/media/hantro/hantro_drv.c
index 26108c96b674..97c615a2f057 100644
--- a/drivers/staging/media/hantro/hantro_drv.c
+++ b/drivers/staging/media/hantro/hantro_drv.c
@@ -53,7 +53,7 @@ dma_addr_t hantro_get_ref(struct hantro_ctx *ctx, u64 ts)
 	if (index < 0)
 		return 0;
 	buf = vb2_get_buffer(q, index);
-	return vb2_dma_contig_plane_dma_addr(buf, 0);
+	return hantro_get_dec_buf_addr(ctx, buf);
 }
 
 static int
@@ -152,16 +152,21 @@ void hantro_watchdog(struct work_struct *work)
 	}
 }
 
-void hantro_prepare_run(struct hantro_ctx *ctx)
+void hantro_start_prepare_run(struct hantro_ctx *ctx)
 {
 	struct vb2_v4l2_buffer *src_buf;
 
 	src_buf = hantro_get_src_buf(ctx);
 	v4l2_ctrl_request_setup(src_buf->vb2_buf.req_obj.req,
 				&ctx->ctrl_handler);
+
+	if (hantro_needs_postproc(ctx, ctx->vpu_dst_fmt))
+		hantro_postproc_enable(ctx);
+	else
+		hantro_postproc_disable(ctx);
 }
 
-void hantro_finish_run(struct hantro_ctx *ctx)
+void hantro_end_prepare_run(struct hantro_ctx *ctx)
 {
 	struct vb2_v4l2_buffer *src_buf;
 
diff --git a/drivers/staging/media/hantro/hantro_g1_h264_dec.c b/drivers/staging/media/hantro/hantro_g1_h264_dec.c
index 3cd40a8f0daa..424c648ce9fc 100644
--- a/drivers/staging/media/hantro/hantro_g1_h264_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_h264_dec.c
@@ -244,7 +244,7 @@ static void set_buffers(struct hantro_ctx *ctx)
 	vdpu_write_relaxed(vpu, src_dma, G1_REG_ADDR_STR);
 
 	/* Destination (decoded frame) buffer. */
-	dst_dma = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
+	dst_dma = hantro_get_dec_buf_addr(ctx, &dst_buf->vb2_buf);
 	/* Adjust dma addr to start at second line for bottom field */
 	if (ctrls->slices[0].flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)
 		offset = ALIGN(ctx->src_fmt.width, MB_DIM);
@@ -288,7 +288,7 @@ void hantro_g1_h264_dec_run(struct hantro_ctx *ctx)
 	set_ref(ctx);
 	set_buffers(ctx);
 
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 
 	/* Start decoding! */
 	vdpu_write_relaxed(vpu,
diff --git a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
index f3bf67d8a289..24041849384a 100644
--- a/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_mpeg2_dec.c
@@ -121,7 +121,7 @@ hantro_g1_mpeg2_dec_set_buffers(struct hantro_dev *vpu, struct hantro_ctx *ctx,
 	vdpu_write_relaxed(vpu, addr, G1_REG_RLC_VLC_BASE);
 
 	/* Destination frame buffer */
-	addr = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+	addr = hantro_get_dec_buf_addr(ctx, dst_buf);
 	current_addr = addr;
 
 	if (picture->picture_structure == PICT_BOTTOM_FIELD)
@@ -168,7 +168,7 @@ void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx)
 	dst_buf = hantro_get_dst_buf(ctx);
 
 	/* Apply request controls if any */
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	slice_params = hantro_get_ctrl(ctx,
 				       V4L2_CID_MPEG_VIDEO_MPEG2_SLICE_PARAMS);
@@ -244,7 +244,7 @@ void hantro_g1_mpeg2_dec_run(struct hantro_ctx *ctx)
 					&dst_buf->vb2_buf,
 					sequence, picture, slice_params);
 
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 
 	reg = G1_REG_DEC_E(1);
 	vdpu_write(vpu, reg, G1_SWREG(1));
diff --git a/drivers/staging/media/hantro/hantro_g1_regs.h b/drivers/staging/media/hantro/hantro_g1_regs.h
index 5c0ea7994336..c1756e3d5391 100644
--- a/drivers/staging/media/hantro/hantro_g1_regs.h
+++ b/drivers/staging/media/hantro/hantro_g1_regs.h
@@ -9,6 +9,8 @@
 #ifndef HANTRO_G1_REGS_H_
 #define HANTRO_G1_REGS_H_
 
+#define G1_SWREG(nr)                 ((nr) * 4)
+
 /* Decoder registers. */
 #define G1_REG_INTERRUPT				0x004
 #define     G1_REG_INTERRUPT_DEC_PIC_INF		BIT(24)
@@ -298,4 +300,55 @@
 #define     G1_REG_REF_BUF_CTRL2_APF_THRESHOLD(x)	(((x) & 0x3fff) << 0)
 #define G1_REG_SOFT_RESET				0x194
 
+/* Post-processor registers. */
+#define G1_REG_PP_INTERRUPT		G1_SWREG(60)
+#define    G1_REG_PP_READY_IRQ		BIT(12)
+#define    G1_REG_PP_IRQ		BIT(8)
+#define    G1_REG_PP_IRQ_DIS		BIT(4)
+#define    G1_REG_PP_PIPELINE_EN	BIT(1)
+#define    G1_REG_PP_EXTERNAL_TRIGGER	BIT(0)
+#define G1_REG_PP_DEV_CONFIG		G1_SWREG(61)
+#define     G1_REG_PP_AXI_RD_ID(v)	(((v) << 24) & GENMASK(31, 24))
+#define     G1_REG_PP_AXI_WR_ID(v)	(((v) << 16) & GENMASK(23, 16))
+#define     G1_REG_PP_INSWAP32_E(v)	((v) ? BIT(10) : 0)
+#define     G1_REG_PP_DATA_DISC_E(v)	((v) ? BIT(9) : 0)
+#define     G1_REG_PP_CLK_GATE_E(v)	((v) ? BIT(8) : 0)
+#define     G1_REG_PP_IN_ENDIAN(v)	((v) ? BIT(7) : 0)
+#define     G1_REG_PP_OUT_ENDIAN(v)	((v) ? BIT(6) : 0)
+#define     G1_REG_PP_OUTSWAP32_E(v)	((v) ? BIT(5) : 0)
+#define     G1_REG_PP_MAX_BURST(v)	(((v) << 0) & GENMASK(4, 0))
+#define G1_REG_PP_IN_LUMA_BASE		G1_SWREG(63)
+#define G1_REG_PP_IN_CB_BASE		G1_SWREG(64)
+#define G1_REG_PP_IN_CR_BASE		G1_SWREG(65)
+#define G1_REG_PP_OUT_LUMA_BASE		G1_SWREG(66)
+#define G1_REG_PP_OUT_CHROMA_BASE	G1_SWREG(67)
+#define G1_REG_PP_CONTRAST_ADJUST	G1_SWREG(68)
+#define G1_REG_PP_COLOR_CONVERSION	G1_SWREG(69)
+#define G1_REG_PP_COLOR_CONVERSION0	G1_SWREG(70)
+#define G1_REG_PP_COLOR_CONVERSION1	G1_SWREG(71)
+#define G1_REG_PP_INPUT_SIZE		G1_SWREG(72)
+#define    G1_REG_PP_INPUT_SIZE_HEIGHT(v) (((v) << 9) & GENMASK(16, 9))
+#define    G1_REG_PP_INPUT_SIZE_WIDTH(v)  (((v) << 0) & GENMASK(8, 0))
+#define G1_REG_PP_SCALING0		G1_SWREG(79)
+#define     G1_REG_PP_PADD_R(v)	(((v) << 23) & GENMASK(27, 23))
+#define     G1_REG_PP_PADD_G(v)	(((v) << 18) & GENMASK(22, 18))
+#define     G1_REG_PP_RANGEMAP_Y(v) ((v) ? BIT(31) : 0)
+#define     G1_REG_PP_RANGEMAP_C(v) ((v) ? BIT(30) : 0)
+#define     G1_REG_PP_YCBCR_RANGE(v) ((v) ? BIT(29) : 0)
+#define     G1_REG_PP_RGB_16(v) ((v) ? BIT(28) : 0)
+#define G1_REG_PP_SCALING1		G1_SWREG(80)
+#define     G1_REG_PP_PADD_B(v)	(((v) << 18) & GENMASK(22, 18))
+#define G1_REG_PP_MASK_R		G1_SWREG(82)
+#define G1_REG_PP_MASK_G		G1_SWREG(83)
+#define G1_REG_PP_MASK_B		G1_SWREG(84)
+#define G1_REG_PP_CONTROL		G1_SWREG(85)
+#define     G1_REG_PP_CONTROL_IN_FMT(v)	(((v) << 29) & GENMASK(31, 29))
+#define     G1_REG_PP_CONTROL_OUT_FMT(v) (((v) << 26) & GENMASK(28, 26))
+#define     G1_REG_PP_CONTROL_OUT_HEIGHT(v) (((v) << 15) & GENMASK(25, 15))
+#define     G1_REG_PP_CONTROL_OUT_WIDTH(v) (((v) << 4) & GENMASK(14, 4))
+#define G1_REG_PP_MASK1_ORIG_WIDTH	G1_SWREG(88)
+#define     G1_REG_PP_ORIG_WIDTH(v)	(((v) << 23) & GENMASK(31, 23))
+#define G1_REG_PP_DISPLAY_WIDTH		G1_SWREG(92)
+#define G1_REG_PP_FUSE			G1_SWREG(99)
+
 #endif /* HANTRO_G1_REGS_H_ */
diff --git a/drivers/staging/media/hantro/hantro_g1_vp8_dec.c b/drivers/staging/media/hantro/hantro_g1_vp8_dec.c
index cad18094fee0..a5cdf150cd16 100644
--- a/drivers/staging/media/hantro/hantro_g1_vp8_dec.c
+++ b/drivers/staging/media/hantro/hantro_g1_vp8_dec.c
@@ -422,7 +422,7 @@ static void cfg_buffers(struct hantro_ctx *ctx,
 	}
 	vdpu_write_relaxed(vpu, reg, G1_REG_FWD_PIC(0));
 
-	dst_dma = vb2_dma_contig_plane_dma_addr(&vb2_dst->vb2_buf, 0);
+	dst_dma = hantro_get_dec_buf_addr(ctx, &vb2_dst->vb2_buf);
 	vdpu_write_relaxed(vpu, dst_dma, G1_REG_ADDR_DST);
 }
 
@@ -435,7 +435,7 @@ void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx)
 	u32 mb_width, mb_height;
 	u32 reg;
 
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	hdr = hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER);
 	if (WARN_ON(!hdr))
@@ -496,7 +496,7 @@ void hantro_g1_vp8_dec_run(struct hantro_ctx *ctx)
 	cfg_ref(ctx, hdr);
 	cfg_buffers(ctx, hdr);
 
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 
 	vdpu_write(vpu, G1_REG_INTERRUPT_DEC_E, G1_REG_INTERRUPT);
 }
diff --git a/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c b/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c
index 938b48d4d3d9..0d8afc3e5d71 100644
--- a/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c
+++ b/drivers/staging/media/hantro/hantro_h1_jpeg_enc.c
@@ -87,7 +87,7 @@ void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx)
 	src_buf = hantro_get_src_buf(ctx);
 	dst_buf = hantro_get_dst_buf(ctx);
 
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	memset(&jpeg_ctx, 0, sizeof(jpeg_ctx));
 	jpeg_ctx.buffer = vb2_plane_vaddr(&dst_buf->vb2_buf, 0);
@@ -122,7 +122,7 @@ void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx)
 		| H1_REG_ENC_PIC_INTRA
 		| H1_REG_ENC_CTRL_EN_BIT;
 
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 
 	vepu_write(vpu, reg, H1_REG_ENC_CTRL);
 }
diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c
index 568640eab3a6..f2d3e81fb6ce 100644
--- a/drivers/staging/media/hantro/hantro_h264.c
+++ b/drivers/staging/media/hantro/hantro_h264.c
@@ -562,7 +562,7 @@ int hantro_h264_dec_prepare_run(struct hantro_ctx *ctx)
 	struct hantro_h264_dec_ctrls *ctrls = &h264_ctx->ctrls;
 	struct hantro_h264_reflist_builder reflist_builder;
 
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	ctrls->scaling =
 		hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_H264_SCALING_MATRIX);
diff --git a/drivers/staging/media/hantro/hantro_hw.h b/drivers/staging/media/hantro/hantro_hw.h
index fa91dd1848b7..2398d4c1f207 100644
--- a/drivers/staging/media/hantro/hantro_hw.h
+++ b/drivers/staging/media/hantro/hantro_hw.h
@@ -28,11 +28,13 @@ struct hantro_variant;
  * @cpu:	CPU pointer to the buffer.
  * @dma:	DMA address of the buffer.
  * @size:	Size of the buffer.
+ * @attrs:	Attributes of the DMA mapping.
  */
 struct hantro_aux_buf {
 	void *cpu;
 	dma_addr_t dma;
 	size_t size;
+	unsigned long attrs;
 };
 
 /**
@@ -107,6 +109,15 @@ struct hantro_vp8_dec_hw_ctx {
 };
 
 /**
+ * struct hantro_postproc_ctx
+ *
+ * @dec_q:		References buffers, in decoder format.
+ */
+struct hantro_postproc_ctx {
+	struct hantro_aux_buf dec_q[VB2_MAX_FRAME];
+};
+
+/**
  * struct hantro_codec_ops - codec mode specific operations
  *
  * @init:	If needed, can be used for initialization.
@@ -141,14 +152,16 @@ extern const struct hantro_variant rk3399_vpu_variant;
 extern const struct hantro_variant rk3328_vpu_variant;
 extern const struct hantro_variant rk3288_vpu_variant;
 
+extern const struct hantro_postproc_regs hantro_g1_postproc_regs;
+
 extern const u32 hantro_vp8_dec_mc_filter[8][6];
 
 void hantro_watchdog(struct work_struct *work);
 void hantro_run(struct hantro_ctx *ctx);
 void hantro_irq_done(struct hantro_dev *vpu, unsigned int bytesused,
 		     enum vb2_buffer_state result);
-void hantro_prepare_run(struct hantro_ctx *ctx);
-void hantro_finish_run(struct hantro_ctx *ctx);
+void hantro_start_prepare_run(struct hantro_ctx *ctx);
+void hantro_end_prepare_run(struct hantro_ctx *ctx);
 
 void hantro_h1_jpeg_enc_run(struct hantro_ctx *ctx);
 void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx);
diff --git a/drivers/staging/media/hantro/hantro_postproc.c b/drivers/staging/media/hantro/hantro_postproc.c
new file mode 100644
index 000000000000..28a85d301d7f
--- /dev/null
+++ b/drivers/staging/media/hantro/hantro_postproc.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hantro G1 post-processor support
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/types.h>
+
+#include "hantro.h"
+#include "hantro_hw.h"
+#include "hantro_g1_regs.h"
+
+#define HANTRO_PP_REG_WRITE(vpu, reg_name, val) \
+{ \
+	hantro_reg_write((vpu), \
+			 &((vpu)->variant->postproc_regs->reg_name), \
+			 (val)); \
+}
+
+#define HANTRO_PP_REG_WRITE_S(vpu, reg_name, val) \
+{ \
+	hantro_reg_write_s((vpu), \
+			   &((vpu)->variant->postproc_regs->reg_name), \
+			   (val)); \
+}
+
+#define VPU_PP_IN_YUYV			0x0
+#define VPU_PP_IN_NV12			0x1
+#define VPU_PP_IN_YUV420		0x2
+#define VPU_PP_IN_YUV240_TILED		0x5
+#define VPU_PP_OUT_RGB			0x0
+#define VPU_PP_OUT_YUYV			0x3
+
+const struct hantro_postproc_regs hantro_g1_postproc_regs = {
+	.pipeline_en = {G1_REG_PP_INTERRUPT, 1, 0x1},
+	.max_burst = {G1_REG_PP_DEV_CONFIG, 0, 0x1f},
+	.clk_gate = {G1_REG_PP_DEV_CONFIG, 1, 0x1},
+	.out_swap32 = {G1_REG_PP_DEV_CONFIG, 5, 0x1},
+	.out_endian = {G1_REG_PP_DEV_CONFIG, 6, 0x1},
+	.out_luma_base = {G1_REG_PP_OUT_LUMA_BASE, 0, 0xffffffff},
+	.input_width = {G1_REG_PP_INPUT_SIZE, 0, 0x1ff},
+	.input_height = {G1_REG_PP_INPUT_SIZE, 9, 0x1ff},
+	.output_width = {G1_REG_PP_CONTROL, 4, 0x7ff},
+	.output_height = {G1_REG_PP_CONTROL, 15, 0x7ff},
+	.input_fmt = {G1_REG_PP_CONTROL, 29, 0x7},
+	.output_fmt = {G1_REG_PP_CONTROL, 26, 0x7},
+	.orig_width = {G1_REG_PP_MASK1_ORIG_WIDTH, 23, 0x1ff},
+	.display_width = {G1_REG_PP_DISPLAY_WIDTH, 0, 0xfff},
+};
+
+void hantro_postproc_enable(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct vb2_v4l2_buffer *dst_buf;
+	u32 src_pp_fmt, dst_pp_fmt;
+	dma_addr_t dst_dma;
+
+	if (!vpu->variant->postproc_regs)
+		return;
+
+	/* Turn on pipeline mode. Must be done first. */
+	HANTRO_PP_REG_WRITE_S(vpu, pipeline_en, 0x1);
+
+	src_pp_fmt = VPU_PP_IN_NV12;
+
+	switch (ctx->vpu_dst_fmt->fourcc) {
+	case V4L2_PIX_FMT_YUYV:
+		dst_pp_fmt = VPU_PP_OUT_YUYV;
+		break;
+	default:
+		WARN(1, "output format %d not supported by the post-processor, this wasn't expected.",
+		     ctx->vpu_dst_fmt->fourcc);
+		dst_pp_fmt = 0;
+		break;
+	}
+
+	dst_buf = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
+	dst_dma = vb2_dma_contig_plane_dma_addr(&dst_buf->vb2_buf, 0);
+
+	HANTRO_PP_REG_WRITE(vpu, clk_gate, 0x1);
+	HANTRO_PP_REG_WRITE(vpu, out_endian, 0x1);
+	HANTRO_PP_REG_WRITE(vpu, out_swap32, 0x1);
+	HANTRO_PP_REG_WRITE(vpu, max_burst, 16);
+	HANTRO_PP_REG_WRITE(vpu, out_luma_base, dst_dma);
+	HANTRO_PP_REG_WRITE(vpu, input_width, MB_WIDTH(ctx->dst_fmt.width));
+	HANTRO_PP_REG_WRITE(vpu, input_height, MB_HEIGHT(ctx->dst_fmt.height));
+	HANTRO_PP_REG_WRITE(vpu, input_fmt, src_pp_fmt);
+	HANTRO_PP_REG_WRITE(vpu, output_fmt, dst_pp_fmt);
+	HANTRO_PP_REG_WRITE(vpu, output_width, ctx->dst_fmt.width);
+	HANTRO_PP_REG_WRITE(vpu, output_height, ctx->dst_fmt.height);
+	HANTRO_PP_REG_WRITE(vpu, orig_width, MB_WIDTH(ctx->dst_fmt.width));
+	HANTRO_PP_REG_WRITE(vpu, display_width, ctx->dst_fmt.width);
+}
+
+void hantro_postproc_free(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	unsigned int i;
+
+	for (i = 0; i < VB2_MAX_FRAME; ++i) {
+		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
+
+		if (priv->cpu) {
+			dma_free_attrs(vpu->dev, priv->size, priv->cpu,
+				       priv->dma, priv->attrs);
+			priv->cpu = NULL;
+		}
+	}
+}
+
+int hantro_postproc_alloc(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	struct v4l2_m2m_ctx *m2m_ctx = ctx->fh.m2m_ctx;
+	struct vb2_queue *cap_queue = &m2m_ctx->cap_q_ctx.q;
+	unsigned int num_buffers = cap_queue->num_buffers;
+	unsigned int i, buf_size;
+
+	buf_size = ctx->dst_fmt.plane_fmt[0].sizeimage;
+
+	for (i = 0; i < num_buffers; ++i) {
+		struct hantro_aux_buf *priv = &ctx->postproc.dec_q[i];
+
+		/*
+		 * The buffers on this queue are meant as intermediate
+		 * buffers for the decoder, so no mapping is needed.
+		 */
+		priv->attrs = DMA_ATTR_NO_KERNEL_MAPPING;
+		priv->cpu = dma_alloc_attrs(vpu->dev, buf_size, &priv->dma,
+					    GFP_KERNEL, priv->attrs);
+		if (!priv->cpu)
+			return -ENOMEM;
+		priv->size = buf_size;
+	}
+	return 0;
+}
+
+void hantro_postproc_disable(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+
+	if (!vpu->variant->postproc_regs)
+		return;
+
+	HANTRO_PP_REG_WRITE_S(vpu, pipeline_en, 0x0);
+}
diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c
index 1dae76f20034..0198bcda26b7 100644
--- a/drivers/staging/media/hantro/hantro_v4l2.c
+++ b/drivers/staging/media/hantro/hantro_v4l2.c
@@ -47,11 +47,30 @@ hantro_get_formats(const struct hantro_ctx *ctx, unsigned int *num_fmts)
 }
 
 static const struct hantro_fmt *
-hantro_find_format(const struct hantro_fmt *formats, unsigned int num_fmts,
-		   u32 fourcc)
+hantro_get_postproc_formats(const struct hantro_ctx *ctx,
+			    unsigned int *num_fmts)
 {
-	unsigned int i;
+	if (hantro_is_encoder_ctx(ctx)) {
+		*num_fmts = 0;
+		return NULL;
+	}
+
+	*num_fmts = ctx->dev->variant->num_postproc_fmts;
+	return ctx->dev->variant->postproc_fmts;
+}
+
+static const struct hantro_fmt *
+hantro_find_format(const struct hantro_ctx *ctx, u32 fourcc)
+{
+	const struct hantro_fmt *formats;
+	unsigned int i, num_fmts;
+
+	formats = hantro_get_formats(ctx, &num_fmts);
+	for (i = 0; i < num_fmts; i++)
+		if (formats[i].fourcc == fourcc)
+			return &formats[i];
 
+	formats = hantro_get_postproc_formats(ctx, &num_fmts);
 	for (i = 0; i < num_fmts; i++)
 		if (formats[i].fourcc == fourcc)
 			return &formats[i];
@@ -59,11 +78,12 @@ hantro_find_format(const struct hantro_fmt *formats, unsigned int num_fmts,
 }
 
 static const struct hantro_fmt *
-hantro_get_default_fmt(const struct hantro_fmt *formats, unsigned int num_fmts,
-		       bool bitstream)
+hantro_get_default_fmt(const struct hantro_ctx *ctx, bool bitstream)
 {
-	unsigned int i;
+	const struct hantro_fmt *formats;
+	unsigned int i, num_fmts;
 
+	formats = hantro_get_formats(ctx, &num_fmts);
 	for (i = 0; i < num_fmts; i++) {
 		if (bitstream == (formats[i].codec_mode !=
 				  HANTRO_MODE_NONE))
@@ -89,8 +109,7 @@ static int vidioc_enum_framesizes(struct file *file, void *priv,
 				  struct v4l2_frmsizeenum *fsize)
 {
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
-	const struct hantro_fmt *formats, *fmt;
-	unsigned int num_fmts;
+	const struct hantro_fmt *fmt;
 
 	if (fsize->index != 0) {
 		vpu_debug(0, "invalid frame size index (expected 0, got %d)\n",
@@ -98,8 +117,7 @@ static int vidioc_enum_framesizes(struct file *file, void *priv,
 		return -EINVAL;
 	}
 
-	formats = hantro_get_formats(ctx, &num_fmts);
-	fmt = hantro_find_format(formats, num_fmts, fsize->pixel_format);
+	fmt = hantro_find_format(ctx, fsize->pixel_format);
 	if (!fmt) {
 		vpu_debug(0, "unsupported bitstream format (%08x)\n",
 			  fsize->pixel_format);
@@ -150,6 +168,24 @@ static int vidioc_enum_fmt(struct file *file, void *priv,
 		}
 		++j;
 	}
+
+	/*
+	 * Enumerate post-processed formats. As per the specification,
+	 * we enumerated these formats after natively decoded formats
+	 * as a hint for applications on what's the preferred fomat.
+	 */
+	if (!capture)
+		return -EINVAL;
+	formats = hantro_get_postproc_formats(ctx, &num_fmts);
+	for (i = 0; i < num_fmts; i++) {
+		if (j == f->index) {
+			fmt = &formats[i];
+			f->pixelformat = fmt->fourcc;
+			return 0;
+		}
+		++j;
+	}
+
 	return -EINVAL;
 }
 
@@ -196,8 +232,7 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f,
 {
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
 	struct v4l2_pix_format_mplane *pix_mp = &f->fmt.pix_mp;
-	const struct hantro_fmt *formats, *fmt, *vpu_fmt;
-	unsigned int num_fmts;
+	const struct hantro_fmt *fmt, *vpu_fmt;
 	bool coded;
 
 	coded = capture == hantro_is_encoder_ctx(ctx);
@@ -208,10 +243,9 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f,
 		  (pix_mp->pixelformat >> 16) & 0x7f,
 		  (pix_mp->pixelformat >> 24) & 0x7f);
 
-	formats = hantro_get_formats(ctx, &num_fmts);
-	fmt = hantro_find_format(formats, num_fmts, pix_mp->pixelformat);
+	fmt = hantro_find_format(ctx, pix_mp->pixelformat);
 	if (!fmt) {
-		fmt = hantro_get_default_fmt(formats, num_fmts, coded);
+		fmt = hantro_get_default_fmt(ctx, coded);
 		f->fmt.pix_mp.pixelformat = fmt->fourcc;
 	}
 
@@ -246,7 +280,7 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f,
 		 *
 		 * The H264 decoder needs extra space on the output buffers
 		 * to store motion vectors. This is needed for reference
-		 * frames.
+		 * frames and only if the format is non-post-processed NV12.
 		 *
 		 * Memory layout is as follow:
 		 *
@@ -260,7 +294,8 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f,
 		 * | MC sync          32 bytes |
 		 * +---------------------------+
 		 */
-		if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE)
+		if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE &&
+		    !hantro_needs_postproc(ctx, ctx->vpu_dst_fmt))
 			pix_mp->plane_fmt[0].sizeimage +=
 				64 * MB_WIDTH(pix_mp->width) *
 				     MB_WIDTH(pix_mp->height) + 32;
@@ -306,12 +341,10 @@ hantro_reset_fmt(struct v4l2_pix_format_mplane *fmt,
 static void
 hantro_reset_encoded_fmt(struct hantro_ctx *ctx)
 {
-	const struct hantro_fmt *vpu_fmt, *formats;
+	const struct hantro_fmt *vpu_fmt;
 	struct v4l2_pix_format_mplane *fmt;
-	unsigned int num_fmts;
 
-	formats = hantro_get_formats(ctx, &num_fmts);
-	vpu_fmt = hantro_get_default_fmt(formats, num_fmts, true);
+	vpu_fmt = hantro_get_default_fmt(ctx, true);
 
 	if (hantro_is_encoder_ctx(ctx)) {
 		ctx->vpu_dst_fmt = vpu_fmt;
@@ -332,12 +365,10 @@ hantro_reset_encoded_fmt(struct hantro_ctx *ctx)
 static void
 hantro_reset_raw_fmt(struct hantro_ctx *ctx)
 {
-	const struct hantro_fmt *raw_vpu_fmt, *formats;
+	const struct hantro_fmt *raw_vpu_fmt;
 	struct v4l2_pix_format_mplane *raw_fmt, *encoded_fmt;
-	unsigned int num_fmts;
 
-	formats = hantro_get_formats(ctx, &num_fmts);
-	raw_vpu_fmt = hantro_get_default_fmt(formats, num_fmts, false);
+	raw_vpu_fmt = hantro_get_default_fmt(ctx, false);
 
 	if (hantro_is_encoder_ctx(ctx)) {
 		ctx->vpu_src_fmt = raw_vpu_fmt;
@@ -384,8 +415,6 @@ vidioc_s_fmt_out_mplane(struct file *file, void *priv, struct v4l2_format *f)
 	struct v4l2_pix_format_mplane *pix_mp = &f->fmt.pix_mp;
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
 	struct vb2_queue *vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
-	const struct hantro_fmt *formats;
-	unsigned int num_fmts;
 	int ret;
 
 	ret = vidioc_try_fmt_out_mplane(file, priv, f);
@@ -421,9 +450,7 @@ vidioc_s_fmt_out_mplane(struct file *file, void *priv, struct v4l2_format *f)
 			return -EBUSY;
 	}
 
-	formats = hantro_get_formats(ctx, &num_fmts);
-	ctx->vpu_src_fmt = hantro_find_format(formats, num_fmts,
-					      pix_mp->pixelformat);
+	ctx->vpu_src_fmt = hantro_find_format(ctx, pix_mp->pixelformat);
 	ctx->src_fmt = *pix_mp;
 
 	/*
@@ -457,9 +484,7 @@ static int vidioc_s_fmt_cap_mplane(struct file *file, void *priv,
 {
 	struct v4l2_pix_format_mplane *pix_mp = &f->fmt.pix_mp;
 	struct hantro_ctx *ctx = fh_to_ctx(priv);
-	const struct hantro_fmt *formats;
 	struct vb2_queue *vq;
-	unsigned int num_fmts;
 	int ret;
 
 	/* Change not allowed if queue is busy. */
@@ -488,9 +513,7 @@ static int vidioc_s_fmt_cap_mplane(struct file *file, void *priv,
 	if (ret)
 		return ret;
 
-	formats = hantro_get_formats(ctx, &num_fmts);
-	ctx->vpu_dst_fmt = hantro_find_format(formats, num_fmts,
-					      pix_mp->pixelformat);
+	ctx->vpu_dst_fmt = hantro_find_format(ctx, pix_mp->pixelformat);
 	ctx->dst_fmt = *pix_mp;
 
 	/*
@@ -650,10 +673,23 @@ static int hantro_start_streaming(struct vb2_queue *q, unsigned int count)
 
 		vpu_debug(4, "Codec mode = %d\n", codec_mode);
 		ctx->codec_ops = &ctx->dev->variant->codec_ops[codec_mode];
-		if (ctx->codec_ops->init)
+		if (ctx->codec_ops->init) {
 			ret = ctx->codec_ops->init(ctx);
+			if (ret)
+				return ret;
+		}
+
+		if (hantro_needs_postproc(ctx, ctx->vpu_dst_fmt)) {
+			ret = hantro_postproc_alloc(ctx);
+			if (ret)
+				goto err_codec_exit;
+		}
 	}
+	return ret;
 
+err_codec_exit:
+	if (ctx->codec_ops->exit)
+		ctx->codec_ops->exit(ctx);
 	return ret;
 }
 
@@ -680,6 +716,7 @@ static void hantro_stop_streaming(struct vb2_queue *q)
 	struct hantro_ctx *ctx = vb2_get_drv_priv(q);
 
 	if (hantro_vq_is_coded(q)) {
+		hantro_postproc_free(ctx);
 		if (ctx->codec_ops && ctx->codec_ops->exit)
 			ctx->codec_ops->exit(ctx);
 	}
diff --git a/drivers/staging/media/hantro/rk3288_vpu_hw.c b/drivers/staging/media/hantro/rk3288_vpu_hw.c
index f8db6fcaad73..2f914b37b9e5 100644
--- a/drivers/staging/media/hantro/rk3288_vpu_hw.c
+++ b/drivers/staging/media/hantro/rk3288_vpu_hw.c
@@ -56,6 +56,13 @@ static const struct hantro_fmt rk3288_vpu_enc_fmts[] = {
 	},
 };
 
+static const struct hantro_fmt rk3288_vpu_postproc_fmts[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_YUYV,
+		.codec_mode = HANTRO_MODE_NONE,
+	},
+};
+
 static const struct hantro_fmt rk3288_vpu_dec_fmts[] = {
 	{
 		.fourcc = V4L2_PIX_FMT_NV12,
@@ -215,6 +222,9 @@ const struct hantro_variant rk3288_vpu_variant = {
 	.dec_offset = 0x400,
 	.dec_fmts = rk3288_vpu_dec_fmts,
 	.num_dec_fmts = ARRAY_SIZE(rk3288_vpu_dec_fmts),
+	.postproc_fmts = rk3288_vpu_postproc_fmts,
+	.num_postproc_fmts = ARRAY_SIZE(rk3288_vpu_postproc_fmts),
+	.postproc_regs = &hantro_g1_postproc_regs,
 	.codec = HANTRO_JPEG_ENCODER | HANTRO_MPEG2_DECODER |
 		 HANTRO_VP8_DECODER | HANTRO_H264_DECODER,
 	.codec_ops = rk3288_vpu_codec_ops,
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c b/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c
index 067892345b5d..4c2d43fb6fd1 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_jpeg_enc.c
@@ -118,7 +118,7 @@ void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx)
 	src_buf = hantro_get_src_buf(ctx);
 	dst_buf = hantro_get_dst_buf(ctx);
 
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	memset(&jpeg_ctx, 0, sizeof(jpeg_ctx));
 	jpeg_ctx.buffer = vb2_plane_vaddr(&dst_buf->vb2_buf, 0);
@@ -156,6 +156,6 @@ void rk3399_vpu_jpeg_enc_run(struct hantro_ctx *ctx)
 		| VEPU_REG_ENCODE_ENABLE;
 
 	/* Kick the watchdog and start encoding */
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 	vepu_write(vpu, reg, VEPU_REG_ENCODE_START);
 }
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
index b40d2cdf832f..7e9aad671489 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_mpeg2_dec.c
@@ -169,7 +169,7 @@ void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx)
 	src_buf = hantro_get_src_buf(ctx);
 	dst_buf = hantro_get_dst_buf(ctx);
 
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	slice_params = hantro_get_ctrl(ctx,
 				       V4L2_CID_MPEG_VIDEO_MPEG2_SLICE_PARAMS);
@@ -250,7 +250,7 @@ void rk3399_vpu_mpeg2_dec_run(struct hantro_ctx *ctx)
 					 sequence, picture, slice_params);
 
 	/* Kick the watchdog and start decoding */
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 
 	reg = vdpu_read(vpu, VDPU_SWREG(57)) | VDPU_REG_DEC_E(1);
 	vdpu_write(vpu, reg, VDPU_SWREG(57));
diff --git a/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c b/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c
index 76d7ed3fd69a..a4a792f00b11 100644
--- a/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c
+++ b/drivers/staging/media/hantro/rk3399_vpu_hw_vp8_dec.c
@@ -513,7 +513,7 @@ void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx)
 	u32 mb_width, mb_height;
 	u32 reg;
 
-	hantro_prepare_run(ctx);
+	hantro_start_prepare_run(ctx);
 
 	hdr = hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_VP8_FRAME_HEADER);
 	if (WARN_ON(!hdr))
@@ -587,7 +587,7 @@ void rk3399_vpu_vp8_dec_run(struct hantro_ctx *ctx)
 	cfg_ref(ctx, hdr);
 	cfg_buffers(ctx, hdr);
 
-	hantro_finish_run(ctx);
+	hantro_end_prepare_run(ctx);
 
 	hantro_reg_write(vpu, &vp8_dec_start_dec, 1);
 }
diff --git a/drivers/staging/media/imx/imx7-mipi-csis.c b/drivers/staging/media/imx/imx7-mipi-csis.c
index 99166afca071..383abecb3bec 100644
--- a/drivers/staging/media/imx/imx7-mipi-csis.c
+++ b/drivers/staging/media/imx/imx7-mipi-csis.c
@@ -251,8 +251,6 @@ struct csi_state {
 
 	struct mipi_csis_event events[MIPI_CSIS_NUM_EVENTS];
 
-	struct v4l2_async_notifier subdev_notifier;
-
 	struct csis_hw_reset hw_reset;
 	struct regulator *mipi_phy_regulator;
 	bool sink_linked;
@@ -1104,7 +1102,6 @@ static int mipi_csis_remove(struct platform_device *pdev)
 
 	mipi_csis_debugfs_exit(state);
 	v4l2_async_unregister_subdev(&state->mipi_sd);
-	v4l2_async_notifier_unregister(&state->subdev_notifier);
 
 	pm_runtime_disable(&pdev->dev);
 	mipi_csis_pm_suspend(&pdev->dev, true);
diff --git a/drivers/staging/media/ipu3/TODO b/drivers/staging/media/ipu3/TODO
index b44bb4a72ca7..dc356d6f03c4 100644
--- a/drivers/staging/media/ipu3/TODO
+++ b/drivers/staging/media/ipu3/TODO
@@ -5,15 +5,9 @@ staging directory.
   as well as formats and the binary used to a request. Remove the
   opportunistic buffer management. (Sakari)
 
-- Using ENABLED and IMMUTABLE link flags for the links where those are
-  relevant. (Sakari)
-
 - IPU3 driver documentation (Laurent)
   Comments on configuring v4l2 subdevs for CIO2 and ImgU.
 
-- uAPI documentation:
-  Move acronyms to doc-rst file. (Mauro)
-
 - Switch to yavta from v4l2n in driver docs.
 
 - Elaborate the functionality of different selection rectangles in driver
diff --git a/drivers/staging/media/ipu3/ipu3-css.c b/drivers/staging/media/ipu3/ipu3-css.c
index fd1ed84c400c..f36de501edc6 100644
--- a/drivers/staging/media/ipu3/ipu3-css.c
+++ b/drivers/staging/media/ipu3/ipu3-css.c
@@ -1450,7 +1450,7 @@ bool imgu_css_pipe_queue_empty(struct imgu_css *css, unsigned int pipe)
 bool imgu_css_queue_empty(struct imgu_css *css)
 {
 	unsigned int pipe;
-	bool ret = 0;
+	bool ret = false;
 
 	for (pipe = 0; pipe < IMGU_MAX_PIPE_NUM; pipe++)
 		ret &= imgu_css_pipe_queue_empty(css, pipe);
diff --git a/drivers/staging/media/ipu3/ipu3-v4l2.c b/drivers/staging/media/ipu3/ipu3-v4l2.c
index 3c7ad1eed434..569e27b824c8 100644
--- a/drivers/staging/media/ipu3/ipu3-v4l2.c
+++ b/drivers/staging/media/ipu3/ipu3-v4l2.c
@@ -1260,6 +1260,11 @@ static int imgu_v4l2_node_setup(struct imgu_device *imgu, unsigned int pipe,
 		r = media_create_pad_link(&vdev->entity, 0, &sd->entity,
 					  node_num, flags);
 	} else {
+		if (node->id == IMGU_NODE_OUT) {
+			flags |= MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE;
+			node->enabled = true;
+		}
+
 		r = media_create_pad_link(&sd->entity, node_num, &vdev->entity,
 					  0, flags);
 	}
diff --git a/drivers/staging/media/meson/vdec/vdec.c b/drivers/staging/media/meson/vdec/vdec.c
index 0a1a04fd5d13..5c5dabed2f09 100644
--- a/drivers/staging/media/meson/vdec/vdec.c
+++ b/drivers/staging/media/meson/vdec/vdec.c
@@ -133,6 +133,8 @@ vdec_queue_recycle(struct amvdec_session *sess, struct vb2_buffer *vb)
 	struct amvdec_buffer *new_buf;
 
 	new_buf = kmalloc(sizeof(*new_buf), GFP_KERNEL);
+	if (!new_buf)
+		return;
 	new_buf->vb = vb;
 
 	mutex_lock(&sess->bufs_recycle_lock);
@@ -956,6 +958,10 @@ static const struct of_device_id vdec_dt_match[] = {
 	  .data = &vdec_platform_gxm },
 	{ .compatible = "amlogic,gxl-vdec",
 	  .data = &vdec_platform_gxl },
+	{ .compatible = "amlogic,g12a-vdec",
+	  .data = &vdec_platform_g12a },
+	{ .compatible = "amlogic,sm1-vdec",
+	  .data = &vdec_platform_sm1 },
 	{}
 };
 MODULE_DEVICE_TABLE(of, vdec_dt_match);
@@ -1003,6 +1009,16 @@ static int vdec_probe(struct platform_device *pdev)
 	if (IS_ERR(core->canvas))
 		return PTR_ERR(core->canvas);
 
+	of_id = of_match_node(vdec_dt_match, dev->of_node);
+	core->platform = of_id->data;
+
+	if (core->platform->revision == VDEC_REVISION_G12A ||
+	    core->platform->revision == VDEC_REVISION_SM1) {
+		core->vdec_hevcf_clk = devm_clk_get(dev, "vdec_hevcf");
+		if (IS_ERR(core->vdec_hevcf_clk))
+			return -EPROBE_DEFER;
+	}
+
 	core->dos_parser_clk = devm_clk_get(dev, "dos_parser");
 	if (IS_ERR(core->dos_parser_clk))
 		return -EPROBE_DEFER;
@@ -1045,8 +1061,6 @@ static int vdec_probe(struct platform_device *pdev)
 		goto err_vdev_release;
 	}
 
-	of_id = of_match_node(vdec_dt_match, dev->of_node);
-	core->platform = of_id->data;
 	core->vdev_dec = vdev;
 	core->dev_dec = dev;
 	mutex_init(&core->lock);
diff --git a/drivers/staging/media/meson/vdec/vdec.h b/drivers/staging/media/meson/vdec/vdec.h
index d811e7976519..0faa1ec4858e 100644
--- a/drivers/staging/media/meson/vdec/vdec.h
+++ b/drivers/staging/media/meson/vdec/vdec.h
@@ -74,6 +74,7 @@ struct amvdec_core {
 	struct clk *dos_clk;
 	struct clk *vdec_1_clk;
 	struct clk *vdec_hevc_clk;
+	struct clk *vdec_hevcf_clk;
 
 	struct reset_control *esparser_reset;
 
diff --git a/drivers/staging/media/meson/vdec/vdec_1.c b/drivers/staging/media/meson/vdec/vdec_1.c
index 3a15c6fc0567..3fe2de0c9331 100644
--- a/drivers/staging/media/meson/vdec/vdec_1.c
+++ b/drivers/staging/media/meson/vdec/vdec_1.c
@@ -18,6 +18,7 @@
 #define AO_RTI_GEN_PWR_SLEEP0	0xe8
 #define AO_RTI_GEN_PWR_ISO0	0xec
 	#define GEN_PWR_VDEC_1 (BIT(3) | BIT(2))
+	#define GEN_PWR_VDEC_1_SM1 (BIT(1))
 
 #define MC_SIZE			(4096 * 4)
 
@@ -142,12 +143,20 @@ static int vdec_1_stop(struct amvdec_session *sess)
 	amvdec_read_dos(core, DOS_SW_RESET0);
 
 	/* enable vdec1 isolation */
-	regmap_write(core->regmap_ao, AO_RTI_GEN_PWR_ISO0, 0xc0);
+	if (core->platform->revision == VDEC_REVISION_SM1)
+		regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_ISO0,
+				   GEN_PWR_VDEC_1_SM1, GEN_PWR_VDEC_1_SM1);
+	else
+		regmap_write(core->regmap_ao, AO_RTI_GEN_PWR_ISO0, 0xc0);
 	/* power off vdec1 memories */
 	amvdec_write_dos(core, DOS_MEM_PD_VDEC, 0xffffffff);
 	/* power off vdec1 */
-	regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0,
-			   GEN_PWR_VDEC_1, GEN_PWR_VDEC_1);
+	if (core->platform->revision == VDEC_REVISION_SM1)
+		regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0,
+				   GEN_PWR_VDEC_1_SM1, GEN_PWR_VDEC_1_SM1);
+	else
+		regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0,
+				   GEN_PWR_VDEC_1, GEN_PWR_VDEC_1);
 
 	clk_disable_unprepare(core->vdec_1_clk);
 
@@ -170,8 +179,12 @@ static int vdec_1_start(struct amvdec_session *sess)
 		return ret;
 
 	/* Enable power for VDEC_1 */
-	regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0,
-			   GEN_PWR_VDEC_1, 0);
+	if (core->platform->revision == VDEC_REVISION_SM1)
+		regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0,
+				   GEN_PWR_VDEC_1_SM1, 0);
+	else
+		regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_SLEEP0,
+				   GEN_PWR_VDEC_1, 0);
 	usleep_range(10, 20);
 
 	/* Reset VDEC1 */
@@ -183,7 +196,11 @@ static int vdec_1_start(struct amvdec_session *sess)
 	/* enable VDEC Memories */
 	amvdec_write_dos(core, DOS_MEM_PD_VDEC, 0);
 	/* Remove VDEC1 Isolation */
-	regmap_write(core->regmap_ao, AO_RTI_GEN_PWR_ISO0, 0);
+	if (core->platform->revision == VDEC_REVISION_SM1)
+		regmap_update_bits(core->regmap_ao, AO_RTI_GEN_PWR_ISO0,
+				   GEN_PWR_VDEC_1_SM1, 0);
+	else
+		regmap_write(core->regmap_ao, AO_RTI_GEN_PWR_ISO0, 0);
 	/* Reset DOS top registers */
 	amvdec_write_dos(core, DOS_VDEC_MCRCC_STALL_CTRL, 0);
 
diff --git a/drivers/staging/media/meson/vdec/vdec_platform.c b/drivers/staging/media/meson/vdec/vdec_platform.c
index 824dbc7f46f5..ea39f8209ec7 100644
--- a/drivers/staging/media/meson/vdec/vdec_platform.c
+++ b/drivers/staging/media/meson/vdec/vdec_platform.c
@@ -82,6 +82,54 @@ static const struct amvdec_format vdec_formats_gxm[] = {
 	},
 };
 
+static const struct amvdec_format vdec_formats_g12a[] = {
+	{
+		.pixfmt = V4L2_PIX_FMT_MPEG1,
+		.min_buffers = 8,
+		.max_buffers = 8,
+		.max_width = 1920,
+		.max_height = 1080,
+		.vdec_ops = &vdec_1_ops,
+		.codec_ops = &codec_mpeg12_ops,
+		.firmware_path = "meson/vdec/gxl_mpeg12.bin",
+		.pixfmts_cap = { V4L2_PIX_FMT_NV12M, V4L2_PIX_FMT_YUV420M, 0 },
+	}, {
+		.pixfmt = V4L2_PIX_FMT_MPEG2,
+		.min_buffers = 8,
+		.max_buffers = 8,
+		.max_width = 1920,
+		.max_height = 1080,
+		.vdec_ops = &vdec_1_ops,
+		.codec_ops = &codec_mpeg12_ops,
+		.firmware_path = "meson/vdec/gxl_mpeg12.bin",
+		.pixfmts_cap = { V4L2_PIX_FMT_NV12M, V4L2_PIX_FMT_YUV420M, 0 },
+	},
+};
+
+static const struct amvdec_format vdec_formats_sm1[] = {
+	{
+		.pixfmt = V4L2_PIX_FMT_MPEG1,
+		.min_buffers = 8,
+		.max_buffers = 8,
+		.max_width = 1920,
+		.max_height = 1080,
+		.vdec_ops = &vdec_1_ops,
+		.codec_ops = &codec_mpeg12_ops,
+		.firmware_path = "meson/vdec/gxl_mpeg12.bin",
+		.pixfmts_cap = { V4L2_PIX_FMT_NV12M, V4L2_PIX_FMT_YUV420M, 0 },
+	}, {
+		.pixfmt = V4L2_PIX_FMT_MPEG2,
+		.min_buffers = 8,
+		.max_buffers = 8,
+		.max_width = 1920,
+		.max_height = 1080,
+		.vdec_ops = &vdec_1_ops,
+		.codec_ops = &codec_mpeg12_ops,
+		.firmware_path = "meson/vdec/gxl_mpeg12.bin",
+		.pixfmts_cap = { V4L2_PIX_FMT_NV12M, V4L2_PIX_FMT_YUV420M, 0 },
+	},
+};
+
 const struct vdec_platform vdec_platform_gxbb = {
 	.formats = vdec_formats_gxbb,
 	.num_formats = ARRAY_SIZE(vdec_formats_gxbb),
@@ -99,3 +147,15 @@ const struct vdec_platform vdec_platform_gxm = {
 	.num_formats = ARRAY_SIZE(vdec_formats_gxm),
 	.revision = VDEC_REVISION_GXM,
 };
+
+const struct vdec_platform vdec_platform_g12a = {
+	.formats = vdec_formats_g12a,
+	.num_formats = ARRAY_SIZE(vdec_formats_g12a),
+	.revision = VDEC_REVISION_G12A,
+};
+
+const struct vdec_platform vdec_platform_sm1 = {
+	.formats = vdec_formats_sm1,
+	.num_formats = ARRAY_SIZE(vdec_formats_sm1),
+	.revision = VDEC_REVISION_SM1,
+};
diff --git a/drivers/staging/media/meson/vdec/vdec_platform.h b/drivers/staging/media/meson/vdec/vdec_platform.h
index f6025326db1d..731877a771f4 100644
--- a/drivers/staging/media/meson/vdec/vdec_platform.h
+++ b/drivers/staging/media/meson/vdec/vdec_platform.h
@@ -15,6 +15,8 @@ enum vdec_revision {
 	VDEC_REVISION_GXBB,
 	VDEC_REVISION_GXL,
 	VDEC_REVISION_GXM,
+	VDEC_REVISION_G12A,
+	VDEC_REVISION_SM1,
 };
 
 struct vdec_platform {
@@ -26,5 +28,7 @@ struct vdec_platform {
 extern const struct vdec_platform vdec_platform_gxbb;
 extern const struct vdec_platform vdec_platform_gxm;
 extern const struct vdec_platform vdec_platform_gxl;
+extern const struct vdec_platform vdec_platform_g12a;
+extern const struct vdec_platform vdec_platform_sm1;
 
 #endif
diff --git a/drivers/staging/media/phy-rockchip-dphy-rx0/Documentation/devicetree/bindings/phy/rockchip-mipi-dphy-rx0.yaml b/drivers/staging/media/phy-rockchip-dphy-rx0/Documentation/devicetree/bindings/phy/rockchip-mipi-dphy-rx0.yaml
new file mode 100644
index 000000000000..5dacece35702
--- /dev/null
+++ b/drivers/staging/media/phy-rockchip-dphy-rx0/Documentation/devicetree/bindings/phy/rockchip-mipi-dphy-rx0.yaml
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/rockchip-mipi-dphy-rx0.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip SoC MIPI RX0 D-PHY Device Tree Bindings
+
+maintainers:
+  - Helen Koike <helen.koike@collabora.com>
+  - Ezequiel Garcia <ezequiel@collabora.com>
+
+description: |
+  The Rockchip SoC has a MIPI D-PHY bus with an RX0 entry which connects to
+  the ISP1 (Image Signal Processing unit v1.0) for CSI cameras.
+
+properties:
+  compatible:
+    const: rockchip,rk3399-mipi-dphy-rx0
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: MIPI D-PHY ref clock
+      - description: MIPI D-PHY RX0 cfg clock
+      - description: Video in/out general register file clock
+
+  clock-names:
+    items:
+      - const: dphy-ref
+      - const: dphy-cfg
+      - const: grf
+
+  '#phy-cells':
+    const: 0
+
+  power-domains:
+    description: Video in/out power domain.
+    maxItems: 1
+
+required:
+  - compatible
+  - clocks
+  - clock-names
+  - '#phy-cells'
+  - power-domains
+
+additionalProperties: false
+
+examples:
+  - |
+
+    /*
+     * MIPI D-PHY RX0 use registers in "general register files", it
+     * should be a child of the GRF.
+     *
+     * grf: syscon@ff770000 {
+     *  compatible = "rockchip,rk3399-grf", "syscon", "simple-mfd";
+     *  ...
+     * };
+     */
+
+    #include <dt-bindings/clock/rk3399-cru.h>
+    #include <dt-bindings/power/rk3399-power.h>
+
+    mipi_dphy_rx0: mipi-dphy-rx0 {
+        compatible = "rockchip,rk3399-mipi-dphy-rx0";
+        clocks = <&cru SCLK_MIPIDPHY_REF>,
+                 <&cru SCLK_DPHY_RX0_CFG>,
+                 <&cru PCLK_VIO_GRF>;
+        clock-names = "dphy-ref", "dphy-cfg", "grf";
+        power-domains = <&power RK3399_PD_VIO>;
+        #phy-cells = <0>;
+    };
diff --git a/drivers/staging/media/phy-rockchip-dphy-rx0/Kconfig b/drivers/staging/media/phy-rockchip-dphy-rx0/Kconfig
new file mode 100644
index 000000000000..bd0147624de1
--- /dev/null
+++ b/drivers/staging/media/phy-rockchip-dphy-rx0/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config PHY_ROCKCHIP_DPHY_RX0
+	tristate "Rockchip MIPI Synopsys DPHY RX0 driver"
+	depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF
+	select GENERIC_PHY_MIPI_DPHY
+	select GENERIC_PHY
+	help
+	  Enable this to support the Rockchip MIPI Synopsys DPHY RX0
+	  associated to the Rockchip ISP module present in RK3399 SoCs.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called phy-rockchip-dphy-rx0.
diff --git a/drivers/staging/media/phy-rockchip-dphy-rx0/Makefile b/drivers/staging/media/phy-rockchip-dphy-rx0/Makefile
new file mode 100644
index 000000000000..507e5d0593ab
--- /dev/null
+++ b/drivers/staging/media/phy-rockchip-dphy-rx0/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_PHY_ROCKCHIP_DPHY_RX0)		+= phy-rockchip-dphy-rx0.o
diff --git a/drivers/staging/media/phy-rockchip-dphy-rx0/TODO b/drivers/staging/media/phy-rockchip-dphy-rx0/TODO
new file mode 100644
index 000000000000..ab612e5b27dc
--- /dev/null
+++ b/drivers/staging/media/phy-rockchip-dphy-rx0/TODO
@@ -0,0 +1,6 @@
+The main reason for keeping this in staging is because the only driver
+that uses this is rkisp1, which is also in staging. It should be moved together
+with rkisp1.
+
+Please CC patches to Linux Media <linux-media@vger.kernel.org> and
+Helen Koike <helen.koike@collabora.com>.
diff --git a/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c b/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c
new file mode 100644
index 000000000000..7c4df6d48c43
--- /dev/null
+++ b/drivers/staging/media/phy-rockchip-dphy-rx0/phy-rockchip-dphy-rx0.c
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip MIPI Synopsys DPHY RX0 driver
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ *
+ * Based on:
+ *
+ * drivers/media/platform/rockchip/isp1/mipi_dphy_sy.c
+ * in https://chromium.googlesource.com/chromiumos/third_party/kernel,
+ * chromeos-4.4 branch.
+ *
+ * Copyright (C) 2017 Fuzhou Rockchip Electronics Co., Ltd.
+ *   Jacob Chen <jacob2.chen@rock-chips.com>
+ *   Shunqian Zheng <zhengsq@rock-chips.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/phy/phy.h>
+#include <linux/phy/phy-mipi-dphy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define RK3399_GRF_SOC_CON9		0x6224
+#define RK3399_GRF_SOC_CON21		0x6254
+#define RK3399_GRF_SOC_CON22		0x6258
+#define RK3399_GRF_SOC_CON23		0x625c
+#define RK3399_GRF_SOC_CON24		0x6260
+#define RK3399_GRF_SOC_CON25		0x6264
+#define RK3399_GRF_SOC_STATUS1		0xe2a4
+
+#define CLOCK_LANE_HS_RX_CONTROL	0x34
+#define LANE0_HS_RX_CONTROL		0x44
+#define LANE1_HS_RX_CONTROL		0x54
+#define LANE2_HS_RX_CONTROL		0x84
+#define LANE3_HS_RX_CONTROL		0x94
+#define LANES_THS_SETTLE_CONTROL	0x75
+#define THS_SETTLE_COUNTER_THRESHOLD	0x04
+
+struct hsfreq_range {
+	u16 range_h;
+	u8 cfg_bit;
+};
+
+static const struct hsfreq_range rk3399_mipidphy_hsfreq_ranges[] = {
+	{   89, 0x00 }, {   99, 0x10 }, {  109, 0x20 }, {  129, 0x01 },
+	{  139, 0x11 }, {  149, 0x21 }, {  169, 0x02 }, {  179, 0x12 },
+	{  199, 0x22 }, {  219, 0x03 }, {  239, 0x13 }, {  249, 0x23 },
+	{  269, 0x04 }, {  299, 0x14 }, {  329, 0x05 }, {  359, 0x15 },
+	{  399, 0x25 }, {  449, 0x06 }, {  499, 0x16 }, {  549, 0x07 },
+	{  599, 0x17 }, {  649, 0x08 }, {  699, 0x18 }, {  749, 0x09 },
+	{  799, 0x19 }, {  849, 0x29 }, {  899, 0x39 }, {  949, 0x0a },
+	{  999, 0x1a }, { 1049, 0x2a }, { 1099, 0x3a }, { 1149, 0x0b },
+	{ 1199, 0x1b }, { 1249, 0x2b }, { 1299, 0x3b }, { 1349, 0x0c },
+	{ 1399, 0x1c }, { 1449, 0x2c }, { 1500, 0x3c }
+};
+
+static const char * const rk3399_mipidphy_clks[] = {
+	"dphy-ref",
+	"dphy-cfg",
+	"grf",
+};
+
+enum dphy_reg_id {
+	GRF_DPHY_RX0_TURNDISABLE = 0,
+	GRF_DPHY_RX0_FORCERXMODE,
+	GRF_DPHY_RX0_FORCETXSTOPMODE,
+	GRF_DPHY_RX0_ENABLE,
+	GRF_DPHY_RX0_TESTCLR,
+	GRF_DPHY_RX0_TESTCLK,
+	GRF_DPHY_RX0_TESTEN,
+	GRF_DPHY_RX0_TESTDIN,
+	GRF_DPHY_RX0_TURNREQUEST,
+	GRF_DPHY_RX0_TESTDOUT,
+	GRF_DPHY_TX0_TURNDISABLE,
+	GRF_DPHY_TX0_FORCERXMODE,
+	GRF_DPHY_TX0_FORCETXSTOPMODE,
+	GRF_DPHY_TX0_TURNREQUEST,
+	GRF_DPHY_TX1RX1_TURNDISABLE,
+	GRF_DPHY_TX1RX1_FORCERXMODE,
+	GRF_DPHY_TX1RX1_FORCETXSTOPMODE,
+	GRF_DPHY_TX1RX1_ENABLE,
+	GRF_DPHY_TX1RX1_MASTERSLAVEZ,
+	GRF_DPHY_TX1RX1_BASEDIR,
+	GRF_DPHY_TX1RX1_ENABLECLK,
+	GRF_DPHY_TX1RX1_TURNREQUEST,
+	GRF_DPHY_RX1_SRC_SEL,
+	/* rk3288 only */
+	GRF_CON_DISABLE_ISP,
+	GRF_CON_ISP_DPHY_SEL,
+	GRF_DSI_CSI_TESTBUS_SEL,
+	GRF_DVP_V18SEL,
+	/* below is for rk3399 only */
+	GRF_DPHY_RX0_CLK_INV_SEL,
+	GRF_DPHY_RX1_CLK_INV_SEL,
+};
+
+struct dphy_reg {
+	u16 offset;
+	u8 mask;
+	u8 shift;
+};
+
+#define PHY_REG(_offset, _width, _shift) \
+	{ .offset = _offset, .mask = BIT(_width) - 1, .shift = _shift, }
+
+static const struct dphy_reg rk3399_grf_dphy_regs[] = {
+	[GRF_DPHY_RX0_TURNREQUEST] = PHY_REG(RK3399_GRF_SOC_CON9, 4, 0),
+	[GRF_DPHY_RX0_CLK_INV_SEL] = PHY_REG(RK3399_GRF_SOC_CON9, 1, 10),
+	[GRF_DPHY_RX1_CLK_INV_SEL] = PHY_REG(RK3399_GRF_SOC_CON9, 1, 11),
+	[GRF_DPHY_RX0_ENABLE] = PHY_REG(RK3399_GRF_SOC_CON21, 4, 0),
+	[GRF_DPHY_RX0_FORCERXMODE] = PHY_REG(RK3399_GRF_SOC_CON21, 4, 4),
+	[GRF_DPHY_RX0_FORCETXSTOPMODE] = PHY_REG(RK3399_GRF_SOC_CON21, 4, 8),
+	[GRF_DPHY_RX0_TURNDISABLE] = PHY_REG(RK3399_GRF_SOC_CON21, 4, 12),
+	[GRF_DPHY_TX0_FORCERXMODE] = PHY_REG(RK3399_GRF_SOC_CON22, 4, 0),
+	[GRF_DPHY_TX0_FORCETXSTOPMODE] = PHY_REG(RK3399_GRF_SOC_CON22, 4, 4),
+	[GRF_DPHY_TX0_TURNDISABLE] = PHY_REG(RK3399_GRF_SOC_CON22, 4, 8),
+	[GRF_DPHY_TX0_TURNREQUEST] = PHY_REG(RK3399_GRF_SOC_CON22, 4, 12),
+	[GRF_DPHY_TX1RX1_ENABLE] = PHY_REG(RK3399_GRF_SOC_CON23, 4, 0),
+	[GRF_DPHY_TX1RX1_FORCERXMODE] = PHY_REG(RK3399_GRF_SOC_CON23, 4, 4),
+	[GRF_DPHY_TX1RX1_FORCETXSTOPMODE] = PHY_REG(RK3399_GRF_SOC_CON23, 4, 8),
+	[GRF_DPHY_TX1RX1_TURNDISABLE] = PHY_REG(RK3399_GRF_SOC_CON23, 4, 12),
+	[GRF_DPHY_TX1RX1_TURNREQUEST] = PHY_REG(RK3399_GRF_SOC_CON24, 4, 0),
+	[GRF_DPHY_RX1_SRC_SEL] = PHY_REG(RK3399_GRF_SOC_CON24, 1, 4),
+	[GRF_DPHY_TX1RX1_BASEDIR] = PHY_REG(RK3399_GRF_SOC_CON24, 1, 5),
+	[GRF_DPHY_TX1RX1_ENABLECLK] = PHY_REG(RK3399_GRF_SOC_CON24, 1, 6),
+	[GRF_DPHY_TX1RX1_MASTERSLAVEZ] = PHY_REG(RK3399_GRF_SOC_CON24, 1, 7),
+	[GRF_DPHY_RX0_TESTDIN] = PHY_REG(RK3399_GRF_SOC_CON25, 8, 0),
+	[GRF_DPHY_RX0_TESTEN] = PHY_REG(RK3399_GRF_SOC_CON25, 1, 8),
+	[GRF_DPHY_RX0_TESTCLK] = PHY_REG(RK3399_GRF_SOC_CON25, 1, 9),
+	[GRF_DPHY_RX0_TESTCLR] = PHY_REG(RK3399_GRF_SOC_CON25, 1, 10),
+	[GRF_DPHY_RX0_TESTDOUT] = PHY_REG(RK3399_GRF_SOC_STATUS1, 8, 0),
+};
+
+struct rk_dphy_drv_data {
+	const char * const *clks;
+	unsigned int num_clks;
+	const struct hsfreq_range *hsfreq_ranges;
+	unsigned int num_hsfreq_ranges;
+	const struct dphy_reg *regs;
+};
+
+struct rk_dphy {
+	struct device *dev;
+	struct regmap *grf;
+	struct clk_bulk_data *clks;
+
+	const struct rk_dphy_drv_data *drv_data;
+	struct phy_configure_opts_mipi_dphy config;
+
+	u8 hsfreq;
+};
+
+static inline void rk_dphy_write_grf(struct rk_dphy *priv,
+				     unsigned int index, u8 value)
+{
+	const struct dphy_reg *reg = &priv->drv_data->regs[index];
+	/* Update high word */
+	unsigned int val = (value << reg->shift) |
+			   (reg->mask << (reg->shift + 16));
+
+	if (WARN_ON(!reg->offset))
+		return;
+	regmap_write(priv->grf, reg->offset, val);
+}
+
+static void rk_dphy_write(struct rk_dphy *priv, u8 test_code, u8 test_data)
+{
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTDIN, test_code);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTEN, 1);
+	/*
+	 * With the falling edge on TESTCLK, the TESTDIN[7:0] signal content
+	 * is latched internally as the current test code. Test data is
+	 * programmed internally by rising edge on TESTCLK.
+	 * This code assumes that TESTCLK is already 1.
+	 */
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTCLK, 0);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTEN, 0);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTDIN, test_data);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTCLK, 1);
+}
+
+static void rk_dphy_enable(struct rk_dphy *priv)
+{
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_FORCERXMODE, 0);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_FORCETXSTOPMODE, 0);
+
+	/* Disable lane turn around, which is ignored in receive mode */
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TURNREQUEST, 0);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TURNDISABLE, 0xf);
+
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_ENABLE,
+			  GENMASK(priv->config.lanes - 1, 0));
+
+	/* dphy start */
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTCLK, 1);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTCLR, 1);
+	usleep_range(100, 150);
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_TESTCLR, 0);
+	usleep_range(100, 150);
+
+	/* set clock lane */
+	/* HS hsfreq_range & lane 0  settle bypass */
+	rk_dphy_write(priv, CLOCK_LANE_HS_RX_CONTROL, 0);
+	/* HS RX Control of lane0 */
+	rk_dphy_write(priv, LANE0_HS_RX_CONTROL, priv->hsfreq << 1);
+	/* HS RX Control of lane1 */
+	rk_dphy_write(priv, LANE1_HS_RX_CONTROL, priv->hsfreq << 1);
+	/* HS RX Control of lane2 */
+	rk_dphy_write(priv, LANE2_HS_RX_CONTROL, priv->hsfreq << 1);
+	/* HS RX Control of lane3 */
+	rk_dphy_write(priv, LANE3_HS_RX_CONTROL, priv->hsfreq << 1);
+	/* HS RX Data Lanes Settle State Time Control */
+	rk_dphy_write(priv, LANES_THS_SETTLE_CONTROL,
+		      THS_SETTLE_COUNTER_THRESHOLD);
+
+	/* Normal operation */
+	rk_dphy_write(priv, 0x0, 0);
+}
+
+static int rk_dphy_configure(struct phy *phy, union phy_configure_opts *opts)
+{
+	struct rk_dphy *priv = phy_get_drvdata(phy);
+	const struct rk_dphy_drv_data *drv_data = priv->drv_data;
+	struct phy_configure_opts_mipi_dphy *config = &opts->mipi_dphy;
+	unsigned int hsfreq = 0;
+	unsigned int i;
+	u64 data_rate_mbps;
+	int ret;
+
+	/* pass with phy_mipi_dphy_get_default_config (with pixel rate?) */
+	ret = phy_mipi_dphy_config_validate(config);
+	if (ret)
+		return ret;
+
+	data_rate_mbps = div_u64(config->hs_clk_rate, 1000 * 1000);
+
+	dev_dbg(priv->dev, "lanes %d - data_rate_mbps %llu\n",
+		config->lanes, data_rate_mbps);
+	for (i = 0; i < drv_data->num_hsfreq_ranges; i++) {
+		if (drv_data->hsfreq_ranges[i].range_h >= data_rate_mbps) {
+			hsfreq = drv_data->hsfreq_ranges[i].cfg_bit;
+			break;
+		}
+	}
+	if (!hsfreq)
+		return -EINVAL;
+
+	priv->hsfreq = hsfreq;
+	priv->config = *config;
+	return 0;
+}
+
+static int rk_dphy_power_on(struct phy *phy)
+{
+	struct rk_dphy *priv = phy_get_drvdata(phy);
+	int ret;
+
+	ret = clk_bulk_enable(priv->drv_data->num_clks, priv->clks);
+	if (ret)
+		return ret;
+
+	rk_dphy_enable(priv);
+
+	return 0;
+}
+
+static int rk_dphy_power_off(struct phy *phy)
+{
+	struct rk_dphy *priv = phy_get_drvdata(phy);
+
+	rk_dphy_write_grf(priv, GRF_DPHY_RX0_ENABLE, 0);
+	clk_bulk_disable(priv->drv_data->num_clks, priv->clks);
+	return 0;
+}
+
+static int rk_dphy_init(struct phy *phy)
+{
+	struct rk_dphy *priv = phy_get_drvdata(phy);
+
+	return clk_bulk_prepare(priv->drv_data->num_clks, priv->clks);
+}
+
+static int rk_dphy_exit(struct phy *phy)
+{
+	struct rk_dphy *priv = phy_get_drvdata(phy);
+
+	clk_bulk_unprepare(priv->drv_data->num_clks, priv->clks);
+	return 0;
+}
+
+static const struct phy_ops rk_dphy_ops = {
+	.power_on	= rk_dphy_power_on,
+	.power_off	= rk_dphy_power_off,
+	.init		= rk_dphy_init,
+	.exit		= rk_dphy_exit,
+	.configure	= rk_dphy_configure,
+	.owner		= THIS_MODULE,
+};
+
+static const struct rk_dphy_drv_data rk3399_mipidphy_drv_data = {
+	.clks = rk3399_mipidphy_clks,
+	.num_clks = ARRAY_SIZE(rk3399_mipidphy_clks),
+	.hsfreq_ranges = rk3399_mipidphy_hsfreq_ranges,
+	.num_hsfreq_ranges = ARRAY_SIZE(rk3399_mipidphy_hsfreq_ranges),
+	.regs = rk3399_grf_dphy_regs,
+};
+
+static const struct of_device_id rk_dphy_dt_ids[] = {
+	{
+		.compatible = "rockchip,rk3399-mipi-dphy-rx0",
+		.data = &rk3399_mipidphy_drv_data,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, rk_dphy_dt_ids);
+
+static int rk_dphy_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	const struct rk_dphy_drv_data *drv_data;
+	struct phy_provider *phy_provider;
+	const struct of_device_id *of_id;
+	struct rk_dphy *priv;
+	struct phy *phy;
+	unsigned int i;
+	int ret;
+
+	if (!dev->parent || !dev->parent->of_node)
+		return -ENODEV;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	priv->dev = dev;
+
+	priv->grf = syscon_node_to_regmap(dev->parent->of_node);
+	if (IS_ERR(priv->grf)) {
+		dev_err(dev, "Can't find GRF syscon\n");
+		return -ENODEV;
+	}
+
+	of_id = of_match_device(rk_dphy_dt_ids, dev);
+	if (!of_id)
+		return -EINVAL;
+
+	drv_data = of_id->data;
+	priv->drv_data = drv_data;
+	priv->clks = devm_kcalloc(&pdev->dev, drv_data->num_clks,
+				  sizeof(*priv->clks), GFP_KERNEL);
+	if (!priv->clks)
+		return -ENOMEM;
+	for (i = 0; i < drv_data->num_clks; i++)
+		priv->clks[i].id = drv_data->clks[i];
+	ret = devm_clk_bulk_get(&pdev->dev, drv_data->num_clks, priv->clks);
+	if (ret)
+		return ret;
+
+	phy = devm_phy_create(dev, np, &rk_dphy_ops);
+	if (IS_ERR(phy)) {
+		dev_err(dev, "failed to create phy\n");
+		return PTR_ERR(phy);
+	}
+	phy_set_drvdata(phy, priv);
+
+	phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate);
+
+	return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static struct platform_driver rk_dphy_driver = {
+	.probe = rk_dphy_probe,
+	.driver = {
+		.name	= "rockchip-mipi-dphy-rx0",
+		.of_match_table = rk_dphy_dt_ids,
+	},
+};
+module_platform_driver(rk_dphy_driver);
+
+MODULE_AUTHOR("Ezequiel Garcia <ezequiel@collabora.com>");
+MODULE_DESCRIPTION("Rockchip MIPI Synopsys DPHY RX0 driver");
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/staging/media/rkisp1/Documentation/devicetree/bindings/media/rockchip-isp1.yaml b/drivers/staging/media/rkisp1/Documentation/devicetree/bindings/media/rockchip-isp1.yaml
new file mode 100644
index 000000000000..af246b71eac6
--- /dev/null
+++ b/drivers/staging/media/rkisp1/Documentation/devicetree/bindings/media/rockchip-isp1.yaml
@@ -0,0 +1,192 @@
+# SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/rockchip-isp1.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Rockchip SoC Image Signal Processing unit v1
+
+maintainers:
+  - Helen Koike <helen.koike@collabora.com>
+
+description: |
+  Rockchip ISP1 is the Camera interface for the Rockchip series of SoCs
+  which contains image processing, scaling, and compression functions.
+
+properties:
+  compatible:
+    const: rockchip,rk3399-cif-isp
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  iommus:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  phys:
+    maxItems: 1
+    description: phandle for the PHY port
+
+  phy-names:
+    const: dphy
+
+  clocks:
+    items:
+      - description: ISP clock
+      - description: ISP AXI clock clock
+      - description: ISP AXI clock  wrapper clock
+      - description: ISP AHB clock clock
+      - description: ISP AHB wrapper clock
+
+  clock-names:
+    items:
+      - const: clk_isp
+      - const: aclk_isp
+      - const: aclk_isp_wrap
+      - const: hclk_isp
+      - const: hclk_isp_wrap
+
+  # See ./video-interfaces.txt for details
+  ports:
+    type: object
+    additionalProperties: false
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
+
+      port@0:
+        type: object
+        description: connection point for sensors at MIPI-DPHY RX0
+        additionalProperties: false
+
+        properties:
+          "#address-cells":
+            const: 1
+
+          "#size-cells":
+            const: 0
+
+          reg:
+            const: 0
+
+        patternProperties:
+          endpoint:
+            type: object
+            additionalProperties: false
+
+            properties:
+              reg:
+                maxItems: 1
+
+              data-lanes:
+                minItems: 1
+                maxItems: 4
+
+              remote-endpoint: true
+
+    required:
+      - port@0
+
+required:
+  - compatible
+  - interrupts
+  - clocks
+  - clock-names
+  - power-domains
+  - iommus
+  - phys
+  - phy-names
+  - ports
+
+additionalProperties: false
+
+examples:
+  - |
+
+    #include <dt-bindings/clock/rk3399-cru.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/rk3399-power.h>
+
+    parent0: parent@0 {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        isp0: isp0@ff910000 {
+            compatible = "rockchip,rk3399-cif-isp";
+            reg = <0x0 0xff910000 0x0 0x4000>;
+            interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH 0>;
+            clocks = <&cru SCLK_ISP0>,
+                     <&cru ACLK_ISP0>, <&cru ACLK_ISP0_WRAPPER>,
+                     <&cru HCLK_ISP0>, <&cru HCLK_ISP0_WRAPPER>;
+            clock-names = "clk_isp",
+                          "aclk_isp", "aclk_isp_wrap",
+                          "hclk_isp", "hclk_isp_wrap";
+            power-domains = <&power RK3399_PD_ISP0>;
+            iommus = <&isp0_mmu>;
+            phys = <&dphy>;
+            phy-names = "dphy";
+
+            ports {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                port@0 {
+                    #address-cells = <1>;
+                    #size-cells = <0>;
+                    reg = <0>;
+
+                    mipi_in_wcam: endpoint@0 {
+                        reg = <0>;
+                        remote-endpoint = <&wcam_out>;
+                        data-lanes = <1 2>;
+                    };
+
+                    mipi_in_ucam: endpoint@1 {
+                        reg = <1>;
+                        remote-endpoint = <&ucam_out>;
+                        data-lanes = <1>;
+                    };
+                };
+            };
+        };
+
+        i2c7: i2c@ff160000 {
+            clock-frequency = <400000>;
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            wcam: camera@36 {
+                compatible = "ovti,ov5695";
+                reg = <0x36>;
+
+                port {
+                    wcam_out: endpoint {
+                        remote-endpoint = <&mipi_in_wcam>;
+                        data-lanes = <1 2>;
+                    };
+                };
+            };
+
+            ucam: camera@3c {
+                compatible = "ovti,ov2685";
+                reg = <0x3c>;
+
+                  port {
+                      ucam_out: endpoint {
+                          remote-endpoint = <&mipi_in_ucam>;
+                          data-lanes = <1>;
+                      };
+                  };
+            };
+        };
+    };
diff --git a/drivers/staging/media/rkisp1/Documentation/media/uapi/v4l/pixfmt-meta-rkisp1-params.rst b/drivers/staging/media/rkisp1/Documentation/media/uapi/v4l/pixfmt-meta-rkisp1-params.rst
new file mode 100644
index 000000000000..32034e481357
--- /dev/null
+++ b/drivers/staging/media/rkisp1/Documentation/media/uapi/v4l/pixfmt-meta-rkisp1-params.rst
@@ -0,0 +1,23 @@
+.. SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+.. _v4l2-meta-fmt-rkisp1-params:
+
+============================
+V4L2_META_FMT_RK_ISP1_PARAMS
+============================
+
+Rockchip ISP1 Parameters Data
+
+Description
+===========
+
+This format describes input parameters for the Rockchip ISP1.
+
+It uses c-struct :c:type:`rkisp1_params_cfg`, which is defined in
+the ``linux/rkisp1-config.h`` header file.
+
+The parameters consist of multiple modules.
+The module won't be updated if the corresponding bit was not set in module_*_update.
+
+.. kernel-doc:: include/uapi/linux/rkisp1-config.h
+   :functions: rkisp1_params_cfg
diff --git a/drivers/staging/media/rkisp1/Documentation/media/uapi/v4l/pixfmt-meta-rkisp1-stat.rst b/drivers/staging/media/rkisp1/Documentation/media/uapi/v4l/pixfmt-meta-rkisp1-stat.rst
new file mode 100644
index 000000000000..4ad303f96421
--- /dev/null
+++ b/drivers/staging/media/rkisp1/Documentation/media/uapi/v4l/pixfmt-meta-rkisp1-stat.rst
@@ -0,0 +1,22 @@
+.. SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+
+.. _v4l2-meta-fmt-rkisp1-stat:
+
+=============================
+V4L2_META_FMT_RK_ISP1_STAT_3A
+=============================
+
+
+Rockchip ISP1 Statistics Data
+
+Description
+===========
+
+This format describes image color statistics information generated by the Rockchip
+ISP1.
+
+It uses c-struct :c:type:`rkisp1_stat_buffer`, which is defined in
+the ``linux/rkisp1-config.h`` header file.
+
+.. kernel-doc:: include/uapi/linux/rkisp1-config.h
+   :functions: rkisp1_stat_buffer
diff --git a/drivers/staging/media/rkisp1/Kconfig b/drivers/staging/media/rkisp1/Kconfig
new file mode 100644
index 000000000000..b859a493caba
--- /dev/null
+++ b/drivers/staging/media/rkisp1/Kconfig
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config VIDEO_ROCKCHIP_ISP1
+	tristate "Rockchip Image Signal Processing v1 Unit driver"
+	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	depends on ARCH_ROCKCHIP || COMPILE_TEST
+	select VIDEOBUF2_DMA_CONTIG
+	select VIDEOBUF2_VMALLOC
+	select V4L2_FWNODE
+	select PHY_ROCKCHIP_DPHY_RX0
+	default n
+	help
+	  Enable this to support the Image Signal Processing (ISP) module
+	  present in RK3399 SoCs.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called rockchip-isp1.
diff --git a/drivers/staging/media/rkisp1/Makefile b/drivers/staging/media/rkisp1/Makefile
new file mode 100644
index 000000000000..69ca59c7ef34
--- /dev/null
+++ b/drivers/staging/media/rkisp1/Makefile
@@ -0,0 +1,8 @@
+obj-$(CONFIG_VIDEO_ROCKCHIP_ISP1) += rockchip-isp1.o
+rockchip-isp1-objs += 	rkisp1-capture.o \
+			rkisp1-common.o \
+			rkisp1-dev.o \
+			rkisp1-isp.o \
+			rkisp1-resizer.o \
+			rkisp1-stats.o \
+			rkisp1-params.o
diff --git a/drivers/staging/media/rkisp1/TODO b/drivers/staging/media/rkisp1/TODO
new file mode 100644
index 000000000000..03cd9a4e70f7
--- /dev/null
+++ b/drivers/staging/media/rkisp1/TODO
@@ -0,0 +1,23 @@
+* Fix serialization on subdev ops.
+* Don't use v4l2_async_notifier_parse_fwnode_endpoints_by_port().
+e.g. isp_parse_of_endpoints in drivers/media/platform/omap3isp/isp.c
+cio2_parse_firmware in drivers/media/pci/intel/ipu3/ipu3-cio2.c.
+* Fix pad format size for statistics and parameters entities.
+* Use threaded interrupt for rkisp1_stats_isr(), remove work queue.
+* Fix checkpatch errors.
+* Make sure uapi structs have the same size and layout in 32 and 62 bits,
+and that there are no holes in the structures (pahole is a utility that
+can be used to test this).
+* Review and comment every lock
+* Handle quantization
+* Document rkisp1-common.h
+* streaming paths (mainpath and selfpath) check if the other path is streaming
+in several places of the code, review this, specially that it doesn't seem it
+supports streaming from both paths at the same time.
+
+NOTES:
+* All v4l2-compliance test must pass.
+* Stats and params can be tested with libcamera and ChromiumOS stack.
+
+Please CC patches to Linux Media <linux-media@vger.kernel.org> and
+Helen Koike <helen.koike@collabora.com>.
diff --git a/drivers/staging/media/rkisp1/rkisp1-capture.c b/drivers/staging/media/rkisp1/rkisp1-capture.c
new file mode 100644
index 000000000000..524e0dd38c1b
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-capture.c
@@ -0,0 +1,1437 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - V4l capture device
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ *
+ * Based on Rockchip ISP1 driver by Rockchip Electronics Co., Ltd.
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#include <linux/delay.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mc.h>
+#include <media/v4l2-subdev.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "rkisp1-common.h"
+
+/*
+ * NOTE: There are two capture video devices in rkisp1, selfpath and mainpath.
+ *
+ * differences between selfpath and mainpath
+ * available mp sink input: isp
+ * available sp sink input : isp, dma(TODO)
+ * available mp sink pad fmts: yuv422, raw
+ * available sp sink pad fmts: yuv422, yuv420......
+ * available mp source fmts: yuv, raw, jpeg(TODO)
+ * available sp source fmts: yuv, rgb
+ */
+
+#define RKISP1_SP_DEV_NAME	RKISP1_DRIVER_NAME "_selfpath"
+#define RKISP1_MP_DEV_NAME	RKISP1_DRIVER_NAME "_mainpath"
+
+#define RKISP1_MIN_BUFFERS_NEEDED 3
+
+enum rkisp1_plane {
+	RKISP1_PLANE_Y	= 0,
+	RKISP1_PLANE_CB	= 1,
+	RKISP1_PLANE_CR	= 2
+};
+
+/*
+ * @fourcc: pixel format
+ * @fmt_type: helper filed for pixel format
+ * @uv_swap: if cb cr swaped, for yuv
+ * @write_format: defines how YCbCr self picture data is written to memory
+ * @output_format: defines sp output format
+ */
+struct rkisp1_capture_fmt_cfg {
+	u32 fourcc;
+	u8 fmt_type;
+	u8 uv_swap;
+	u32 write_format;
+	u32 output_format;
+};
+
+struct rkisp1_capture_ops {
+	void (*config)(struct rkisp1_capture *cap);
+	void (*stop)(struct rkisp1_capture *cap);
+	void (*enable)(struct rkisp1_capture *cap);
+	void (*disable)(struct rkisp1_capture *cap);
+	void (*set_data_path)(struct rkisp1_capture *cap);
+	bool (*is_stopped)(struct rkisp1_capture *cap);
+};
+
+struct rkisp1_capture_config {
+	const struct rkisp1_capture_fmt_cfg *fmts;
+	int fmt_size;
+	struct {
+		u32 y_size_init;
+		u32 cb_size_init;
+		u32 cr_size_init;
+		u32 y_base_ad_init;
+		u32 cb_base_ad_init;
+		u32 cr_base_ad_init;
+		u32 y_offs_cnt_init;
+		u32 cb_offs_cnt_init;
+		u32 cr_offs_cnt_init;
+	} mi;
+};
+
+static const struct rkisp1_capture_fmt_cfg rkisp1_mp_fmts[] = {
+	/* yuv422 */
+	{
+		.fourcc = V4L2_PIX_FMT_YUYV,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUVINT,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YVYU,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUVINT,
+	}, {
+		.fourcc = V4L2_PIX_FMT_VYUY,
+		.fmt_type = RKISP1_FMT_YUV,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUVINT,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YUV422P,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV16,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV61,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YVU422M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	},
+	/* yuv420 */
+	{
+		.fourcc = V4L2_PIX_FMT_NV21,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV12,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV21M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YUV420,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YVU420,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	},
+	/* yuv444 */
+	{
+		.fourcc = V4L2_PIX_FMT_YUV444M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	},
+	/* yuv400 */
+	{
+		.fourcc = V4L2_PIX_FMT_GREY,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUVINT,
+	},
+	/* raw */
+	{
+		.fourcc = V4L2_PIX_FMT_SRGGB8,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SGRBG8,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SGBRG8,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SBGGR8,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SRGGB10,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SGRBG10,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SGBRG10,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SBGGR10,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SRGGB12,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SGRBG12,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SGBRG12,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	}, {
+		.fourcc = V4L2_PIX_FMT_SBGGR12,
+		.fmt_type = RKISP1_FMT_BAYER,
+		.write_format = RKISP1_MI_CTRL_MP_WRITE_RAW12,
+	},
+};
+
+static const struct rkisp1_capture_fmt_cfg rkisp1_sp_fmts[] = {
+	/* yuv422 */
+	{
+		.fourcc = V4L2_PIX_FMT_YUYV,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_INT,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YVYU,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_INT,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	}, {
+		.fourcc = V4L2_PIX_FMT_VYUY,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_INT,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YUV422P,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV16,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_SPLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV61,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_SPLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YVU422M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV422,
+	},
+	/* yuv420 */
+	{
+		.fourcc = V4L2_PIX_FMT_NV21,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_SPLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV420,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV12,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_SPLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV420,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV21M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_SPLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV420,
+	}, {
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_SPLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV420,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YUV420,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV420,
+	}, {
+		.fourcc = V4L2_PIX_FMT_YVU420,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 1,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV420,
+	},
+	/* yuv444 */
+	{
+		.fourcc = V4L2_PIX_FMT_YUV444M,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV444,
+	},
+	/* yuv400 */
+	{
+		.fourcc = V4L2_PIX_FMT_GREY,
+		.fmt_type = RKISP1_FMT_YUV,
+		.uv_swap = 0,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_INT,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_YUV400,
+	},
+	/* rgb */
+	{
+		.fourcc = V4L2_PIX_FMT_RGB24,
+		.fmt_type = RKISP1_FMT_RGB,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_RGB888,
+	}, {
+		.fourcc = V4L2_PIX_FMT_RGB565,
+		.fmt_type = RKISP1_FMT_RGB,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_RGB565,
+	}, {
+		.fourcc = V4L2_PIX_FMT_BGR666,
+		.fmt_type = RKISP1_FMT_RGB,
+		.write_format = RKISP1_MI_CTRL_SP_WRITE_PLA,
+		.output_format = RKISP1_MI_CTRL_SP_OUTPUT_RGB666,
+	},
+};
+
+static const struct rkisp1_capture_config rkisp1_capture_config_mp = {
+	.fmts = rkisp1_mp_fmts,
+	.fmt_size = ARRAY_SIZE(rkisp1_mp_fmts),
+	.mi = {
+		.y_size_init =		RKISP1_CIF_MI_MP_Y_SIZE_INIT,
+		.cb_size_init =		RKISP1_CIF_MI_MP_CB_SIZE_INIT,
+		.cr_size_init =		RKISP1_CIF_MI_MP_CR_SIZE_INIT,
+		.y_base_ad_init =	RKISP1_CIF_MI_MP_Y_BASE_AD_INIT,
+		.cb_base_ad_init =	RKISP1_CIF_MI_MP_CB_BASE_AD_INIT,
+		.cr_base_ad_init =	RKISP1_CIF_MI_MP_CR_BASE_AD_INIT,
+		.y_offs_cnt_init =	RKISP1_CIF_MI_MP_Y_OFFS_CNT_INIT,
+		.cb_offs_cnt_init =	RKISP1_CIF_MI_MP_CB_OFFS_CNT_INIT,
+		.cr_offs_cnt_init =	RKISP1_CIF_MI_MP_CR_OFFS_CNT_INIT,
+	},
+};
+
+static const struct rkisp1_capture_config rkisp1_capture_config_sp = {
+	.fmts = rkisp1_sp_fmts,
+	.fmt_size = ARRAY_SIZE(rkisp1_sp_fmts),
+	.mi = {
+		.y_size_init =		RKISP1_CIF_MI_SP_Y_SIZE_INIT,
+		.cb_size_init =		RKISP1_CIF_MI_SP_CB_SIZE_INIT,
+		.cr_size_init =		RKISP1_CIF_MI_SP_CR_SIZE_INIT,
+		.y_base_ad_init =	RKISP1_CIF_MI_SP_Y_BASE_AD_INIT,
+		.cb_base_ad_init =	RKISP1_CIF_MI_SP_CB_BASE_AD_INIT,
+		.cr_base_ad_init =	RKISP1_CIF_MI_SP_CR_BASE_AD_INIT,
+		.y_offs_cnt_init =	RKISP1_CIF_MI_SP_Y_OFFS_CNT_INIT,
+		.cb_offs_cnt_init =	RKISP1_CIF_MI_SP_CB_OFFS_CNT_INIT,
+		.cr_offs_cnt_init =	RKISP1_CIF_MI_SP_CR_OFFS_CNT_INIT,
+	},
+};
+
+static inline struct rkisp1_vdev_node *
+rkisp1_vdev_to_node(struct video_device *vdev)
+{
+	return container_of(vdev, struct rkisp1_vdev_node, vdev);
+}
+
+/* ----------------------------------------------------------------------------
+ * Stream operations for self-picture path (sp) and main-picture path (mp)
+ */
+
+static void rkisp1_mi_config_ctrl(struct rkisp1_capture *cap)
+{
+	u32 mi_ctrl = rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL);
+
+	mi_ctrl &= ~GENMASK(17, 16);
+	mi_ctrl |= RKISP1_CIF_MI_CTRL_BURST_LEN_LUM_64;
+
+	mi_ctrl &= ~GENMASK(19, 18);
+	mi_ctrl |= RKISP1_CIF_MI_CTRL_BURST_LEN_CHROM_64;
+
+	mi_ctrl |= RKISP1_CIF_MI_CTRL_INIT_BASE_EN |
+		   RKISP1_CIF_MI_CTRL_INIT_OFFSET_EN;
+
+	rkisp1_write(cap->rkisp1, mi_ctrl, RKISP1_CIF_MI_CTRL);
+}
+
+static u32 rkisp1_pixfmt_comp_size(const struct v4l2_pix_format_mplane *pixm,
+				   unsigned int component)
+{
+	/*
+	 * If packed format, then plane_fmt[0].sizeimage is the sum of all
+	 * components, so we need to calculate just the size of Y component.
+	 * See rkisp1_fill_pixfmt().
+	 */
+	if (!component && pixm->num_planes == 1)
+		return pixm->plane_fmt[0].bytesperline * pixm->height;
+	return pixm->plane_fmt[component].sizeimage;
+}
+
+static void rkisp1_irq_frame_end_enable(struct rkisp1_capture *cap)
+{
+	u32 mi_imsc = rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_IMSC);
+
+	mi_imsc |= RKISP1_CIF_MI_FRAME(cap);
+	rkisp1_write(cap->rkisp1, mi_imsc, RKISP1_CIF_MI_IMSC);
+}
+
+static void rkisp1_mp_config(struct rkisp1_capture *cap)
+{
+	const struct v4l2_pix_format_mplane *pixm = &cap->pix.fmt;
+	struct rkisp1_device *rkisp1 = cap->rkisp1;
+	u32 reg;
+
+	rkisp1_write(rkisp1, rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_Y),
+		     cap->config->mi.y_size_init);
+	rkisp1_write(rkisp1, rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CB),
+		     cap->config->mi.cb_size_init);
+	rkisp1_write(rkisp1, rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CR),
+		     cap->config->mi.cr_size_init);
+
+	rkisp1_irq_frame_end_enable(cap);
+	if (cap->pix.cfg->uv_swap) {
+		reg = rkisp1_read(rkisp1, RKISP1_CIF_MI_XTD_FORMAT_CTRL);
+
+		reg = (reg & ~BIT(0)) |
+		      RKISP1_CIF_MI_XTD_FMT_CTRL_MP_CB_CR_SWAP;
+		rkisp1_write(rkisp1, reg, RKISP1_CIF_MI_XTD_FORMAT_CTRL);
+	}
+
+	rkisp1_mi_config_ctrl(cap);
+
+	reg = rkisp1_read(rkisp1, RKISP1_CIF_MI_CTRL);
+	reg &= ~RKISP1_MI_CTRL_MP_FMT_MASK;
+	reg |= cap->pix.cfg->write_format;
+	rkisp1_write(rkisp1, reg, RKISP1_CIF_MI_CTRL);
+
+	reg = rkisp1_read(rkisp1, RKISP1_CIF_MI_CTRL);
+	reg |= RKISP1_CIF_MI_MP_AUTOUPDATE_ENABLE;
+	rkisp1_write(rkisp1, reg, RKISP1_CIF_MI_CTRL);
+}
+
+static void rkisp1_sp_config(struct rkisp1_capture *cap)
+{
+	const struct v4l2_pix_format_mplane *pixm = &cap->pix.fmt;
+	struct rkisp1_device *rkisp1 = cap->rkisp1;
+	u32 mi_ctrl;
+
+	rkisp1_write(rkisp1, rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_Y),
+		     cap->config->mi.y_size_init);
+	rkisp1_write(rkisp1, rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CB),
+		     cap->config->mi.cb_size_init);
+	rkisp1_write(rkisp1, rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CR),
+		     cap->config->mi.cr_size_init);
+
+	rkisp1_write(rkisp1, pixm->width, RKISP1_CIF_MI_SP_Y_PIC_WIDTH);
+	rkisp1_write(rkisp1, pixm->height, RKISP1_CIF_MI_SP_Y_PIC_HEIGHT);
+	rkisp1_write(rkisp1, cap->sp_y_stride, RKISP1_CIF_MI_SP_Y_LLENGTH);
+
+	rkisp1_irq_frame_end_enable(cap);
+	if (cap->pix.cfg->uv_swap) {
+		u32 reg = rkisp1_read(rkisp1, RKISP1_CIF_MI_XTD_FORMAT_CTRL);
+
+		rkisp1_write(rkisp1, reg & ~BIT(1),
+			     RKISP1_CIF_MI_XTD_FORMAT_CTRL);
+	}
+
+	rkisp1_mi_config_ctrl(cap);
+
+	mi_ctrl = rkisp1_read(rkisp1, RKISP1_CIF_MI_CTRL);
+	mi_ctrl &= ~RKISP1_MI_CTRL_SP_FMT_MASK;
+	mi_ctrl |= cap->pix.cfg->write_format |
+		   RKISP1_MI_CTRL_SP_INPUT_YUV422 |
+		   cap->pix.cfg->output_format |
+		   RKISP1_CIF_MI_SP_AUTOUPDATE_ENABLE;
+	rkisp1_write(rkisp1, mi_ctrl, RKISP1_CIF_MI_CTRL);
+}
+
+static void rkisp1_mp_disable(struct rkisp1_capture *cap)
+{
+	u32 mi_ctrl = rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL);
+
+	mi_ctrl &= ~(RKISP1_CIF_MI_CTRL_MP_ENABLE |
+		     RKISP1_CIF_MI_CTRL_RAW_ENABLE);
+	rkisp1_write(cap->rkisp1, mi_ctrl, RKISP1_CIF_MI_CTRL);
+}
+
+static void rkisp1_sp_disable(struct rkisp1_capture *cap)
+{
+	u32 mi_ctrl = rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL);
+
+	mi_ctrl &= ~RKISP1_CIF_MI_CTRL_SP_ENABLE;
+	rkisp1_write(cap->rkisp1, mi_ctrl, RKISP1_CIF_MI_CTRL);
+}
+
+static void rkisp1_mp_enable(struct rkisp1_capture *cap)
+{
+	const struct rkisp1_capture_fmt_cfg *isp_fmt = cap->pix.cfg;
+	u32 mi_ctrl;
+
+	rkisp1_mp_disable(cap);
+
+	mi_ctrl = rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL);
+	if (isp_fmt->fmt_type == RKISP1_FMT_BAYER)
+		mi_ctrl |= RKISP1_CIF_MI_CTRL_RAW_ENABLE;
+	/* YUV */
+	else
+		mi_ctrl |= RKISP1_CIF_MI_CTRL_MP_ENABLE;
+
+	rkisp1_write(cap->rkisp1, mi_ctrl, RKISP1_CIF_MI_CTRL);
+}
+
+static void rkisp1_sp_enable(struct rkisp1_capture *cap)
+{
+	u32 mi_ctrl = rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL);
+
+	mi_ctrl |= RKISP1_CIF_MI_CTRL_SP_ENABLE;
+	rkisp1_write(cap->rkisp1, mi_ctrl, RKISP1_CIF_MI_CTRL);
+}
+
+static void rkisp1_mp_sp_stop(struct rkisp1_capture *cap)
+{
+	if (!cap->is_streaming)
+		return;
+	rkisp1_write(cap->rkisp1,
+		     RKISP1_CIF_MI_FRAME(cap), RKISP1_CIF_MI_ICR);
+	cap->ops->disable(cap);
+}
+
+static bool rkisp1_mp_is_stopped(struct rkisp1_capture *cap)
+{
+	u32 en = RKISP1_CIF_MI_CTRL_SHD_MP_IN_ENABLED |
+		 RKISP1_CIF_MI_CTRL_SHD_RAW_OUT_ENABLED;
+
+	return !(rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL_SHD) & en);
+}
+
+static bool rkisp1_sp_is_stopped(struct rkisp1_capture *cap)
+{
+	return !(rkisp1_read(cap->rkisp1, RKISP1_CIF_MI_CTRL_SHD) &
+		 RKISP1_CIF_MI_CTRL_SHD_SP_IN_ENABLED);
+}
+
+static void rkisp1_mp_set_data_path(struct rkisp1_capture *cap)
+{
+	u32 dpcl = rkisp1_read(cap->rkisp1, RKISP1_CIF_VI_DPCL);
+
+	dpcl = dpcl | RKISP1_CIF_VI_DPCL_CHAN_MODE_MP |
+	       RKISP1_CIF_VI_DPCL_MP_MUX_MRSZ_MI;
+	rkisp1_write(cap->rkisp1, dpcl, RKISP1_CIF_VI_DPCL);
+}
+
+static void rkisp1_sp_set_data_path(struct rkisp1_capture *cap)
+{
+	u32 dpcl = rkisp1_read(cap->rkisp1, RKISP1_CIF_VI_DPCL);
+
+	dpcl |= RKISP1_CIF_VI_DPCL_CHAN_MODE_SP;
+	rkisp1_write(cap->rkisp1, dpcl, RKISP1_CIF_VI_DPCL);
+}
+
+static struct rkisp1_capture_ops rkisp1_capture_ops_mp = {
+	.config = rkisp1_mp_config,
+	.enable = rkisp1_mp_enable,
+	.disable = rkisp1_mp_disable,
+	.stop = rkisp1_mp_sp_stop,
+	.set_data_path = rkisp1_mp_set_data_path,
+	.is_stopped = rkisp1_mp_is_stopped,
+};
+
+static struct rkisp1_capture_ops rkisp1_capture_ops_sp = {
+	.config = rkisp1_sp_config,
+	.enable = rkisp1_sp_enable,
+	.disable = rkisp1_sp_disable,
+	.stop = rkisp1_mp_sp_stop,
+	.set_data_path = rkisp1_sp_set_data_path,
+	.is_stopped = rkisp1_sp_is_stopped,
+};
+
+/* ----------------------------------------------------------------------------
+ * Frame buffer operations
+ */
+
+static int rkisp1_dummy_buf_create(struct rkisp1_capture *cap)
+{
+	const struct v4l2_pix_format_mplane *pixm = &cap->pix.fmt;
+	struct rkisp1_dummy_buffer *dummy_buf = &cap->buf.dummy;
+
+	dummy_buf->size = max3(rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_Y),
+			       rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CB),
+			       rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CR));
+
+	/* The driver never access vaddr, no mapping is required */
+	dummy_buf->vaddr = dma_alloc_attrs(cap->rkisp1->dev,
+					   dummy_buf->size,
+					   &dummy_buf->dma_addr,
+					   GFP_KERNEL,
+					   DMA_ATTR_NO_KERNEL_MAPPING);
+	if (!dummy_buf->vaddr)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void rkisp1_dummy_buf_destroy(struct rkisp1_capture *cap)
+{
+	dma_free_attrs(cap->rkisp1->dev,
+		       cap->buf.dummy.size, cap->buf.dummy.vaddr,
+		       cap->buf.dummy.dma_addr, DMA_ATTR_NO_KERNEL_MAPPING);
+}
+
+static void rkisp1_set_next_buf(struct rkisp1_capture *cap)
+{
+	/*
+	 * Use the dummy space allocated by dma_alloc_coherent to
+	 * throw data if there is no available buffer.
+	 */
+	if (cap->buf.next) {
+		u32 *buff_addr = cap->buf.next->buff_addr;
+
+		rkisp1_write(cap->rkisp1,
+			     buff_addr[RKISP1_PLANE_Y],
+			     cap->config->mi.y_base_ad_init);
+		rkisp1_write(cap->rkisp1,
+			     buff_addr[RKISP1_PLANE_CB],
+			     cap->config->mi.cb_base_ad_init);
+		rkisp1_write(cap->rkisp1,
+			     buff_addr[RKISP1_PLANE_CR],
+			     cap->config->mi.cr_base_ad_init);
+	} else {
+		rkisp1_write(cap->rkisp1,
+			     cap->buf.dummy.dma_addr,
+			     cap->config->mi.y_base_ad_init);
+		rkisp1_write(cap->rkisp1,
+			     cap->buf.dummy.dma_addr,
+			     cap->config->mi.cb_base_ad_init);
+		rkisp1_write(cap->rkisp1,
+			     cap->buf.dummy.dma_addr,
+			     cap->config->mi.cr_base_ad_init);
+	}
+
+	/* Set plane offsets */
+	rkisp1_write(cap->rkisp1, 0, cap->config->mi.y_offs_cnt_init);
+	rkisp1_write(cap->rkisp1, 0, cap->config->mi.cb_offs_cnt_init);
+	rkisp1_write(cap->rkisp1, 0, cap->config->mi.cr_offs_cnt_init);
+}
+
+/*
+ * This function is called when a frame end comes. The next frame
+ * is processing and we should set up buffer for next-next frame,
+ * otherwise it will overflow.
+ */
+static void rkisp1_handle_buffer(struct rkisp1_capture *cap)
+{
+	struct rkisp1_isp *isp = &cap->rkisp1->isp;
+	struct rkisp1_buffer *curr_buf = cap->buf.curr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cap->buf.lock, flags);
+
+	if (curr_buf) {
+		curr_buf->vb.sequence = atomic_read(&isp->frame_sequence);
+		curr_buf->vb.vb2_buf.timestamp = ktime_get_boottime_ns();
+		curr_buf->vb.field = V4L2_FIELD_NONE;
+		vb2_buffer_done(&curr_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
+	} else {
+		cap->rkisp1->debug.frame_drop[cap->id]++;
+	}
+
+	cap->buf.curr = cap->buf.next;
+	cap->buf.next = NULL;
+
+	if (!list_empty(&cap->buf.queue)) {
+		cap->buf.next = list_first_entry(&cap->buf.queue,
+						 struct rkisp1_buffer,
+						 queue);
+		list_del(&cap->buf.next->queue);
+	}
+	spin_unlock_irqrestore(&cap->buf.lock, flags);
+
+	rkisp1_set_next_buf(cap);
+}
+
+void rkisp1_capture_isr(struct rkisp1_device *rkisp1)
+{
+	unsigned int i;
+	u32 status;
+
+	status = rkisp1_read(rkisp1, RKISP1_CIF_MI_MIS);
+	rkisp1_write(rkisp1, status, RKISP1_CIF_MI_ICR);
+
+	for (i = 0; i < ARRAY_SIZE(rkisp1->capture_devs); ++i) {
+		struct rkisp1_capture *cap = &rkisp1->capture_devs[i];
+
+		if (!(status & RKISP1_CIF_MI_FRAME(cap)))
+			continue;
+		if (!cap->is_stopping) {
+			rkisp1_handle_buffer(cap);
+			continue;
+		}
+		/*
+		 * Make sure stream is actually stopped, whose state
+		 * can be read from the shadow register, before
+		 * wake_up() thread which would immediately free all
+		 * frame buffers. stop() takes effect at the next
+		 * frame end that sync the configurations to shadow
+		 * regs.
+		 */
+		if (!cap->ops->is_stopped(cap)) {
+			cap->ops->stop(cap);
+			continue;
+		}
+		cap->is_stopping = false;
+		cap->is_streaming = false;
+		wake_up(&cap->done);
+	}
+}
+
+/* ----------------------------------------------------------------------------
+ * Vb2 operations
+ */
+
+static int rkisp1_vb2_queue_setup(struct vb2_queue *queue,
+				  unsigned int *num_buffers,
+				  unsigned int *num_planes,
+				  unsigned int sizes[],
+				  struct device *alloc_devs[])
+{
+	struct rkisp1_capture *cap = queue->drv_priv;
+	const struct v4l2_pix_format_mplane *pixm = &cap->pix.fmt;
+	unsigned int i;
+
+	if (*num_planes) {
+		if (*num_planes != pixm->num_planes)
+			return -EINVAL;
+
+		for (i = 0; i < pixm->num_planes; i++)
+			if (sizes[i] < pixm->plane_fmt[i].sizeimage)
+				return -EINVAL;
+	} else {
+		*num_planes = pixm->num_planes;
+		for (i = 0; i < pixm->num_planes; i++)
+			sizes[i] = pixm->plane_fmt[i].sizeimage;
+	}
+
+	return 0;
+}
+
+static void rkisp1_vb2_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rkisp1_buffer *ispbuf =
+		container_of(vbuf, struct rkisp1_buffer, vb);
+	struct rkisp1_capture *cap = vb->vb2_queue->drv_priv;
+	const struct v4l2_pix_format_mplane *pixm = &cap->pix.fmt;
+	unsigned long flags;
+	unsigned int i;
+
+	memset(ispbuf->buff_addr, 0, sizeof(ispbuf->buff_addr));
+	for (i = 0; i < pixm->num_planes; i++)
+		ispbuf->buff_addr[i] = vb2_dma_contig_plane_dma_addr(vb, i);
+
+	/* Convert to non-MPLANE */
+	if (pixm->num_planes == 1) {
+		ispbuf->buff_addr[RKISP1_PLANE_CB] =
+			ispbuf->buff_addr[RKISP1_PLANE_Y] +
+			rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_Y);
+		ispbuf->buff_addr[RKISP1_PLANE_CR] =
+			ispbuf->buff_addr[RKISP1_PLANE_CB] +
+			rkisp1_pixfmt_comp_size(pixm, RKISP1_PLANE_CB);
+	}
+
+	spin_lock_irqsave(&cap->buf.lock, flags);
+
+	/*
+	 * If there's no next buffer assigned, queue this buffer directly
+	 * as the next buffer, and update the memory interface.
+	 */
+	if (cap->is_streaming && !cap->buf.next &&
+	    atomic_read(&cap->rkisp1->isp.frame_sequence) == -1) {
+		cap->buf.next = ispbuf;
+		rkisp1_set_next_buf(cap);
+	} else {
+		list_add_tail(&ispbuf->queue, &cap->buf.queue);
+	}
+	spin_unlock_irqrestore(&cap->buf.lock, flags);
+}
+
+static int rkisp1_vb2_buf_prepare(struct vb2_buffer *vb)
+{
+	struct rkisp1_capture *cap = vb->vb2_queue->drv_priv;
+	unsigned int i;
+
+	for (i = 0; i < cap->pix.fmt.num_planes; i++) {
+		unsigned long size = cap->pix.fmt.plane_fmt[i].sizeimage;
+
+		if (vb2_plane_size(vb, i) < size) {
+			dev_err(cap->rkisp1->dev,
+				"User buffer too small (%ld < %ld)\n",
+				vb2_plane_size(vb, i), size);
+			return -EINVAL;
+		}
+		vb2_set_plane_payload(vb, i, size);
+	}
+
+	return 0;
+}
+
+static void rkisp1_return_all_buffers(struct rkisp1_capture *cap,
+				      enum vb2_buffer_state state)
+{
+	unsigned long flags;
+	struct rkisp1_buffer *buf;
+
+	spin_lock_irqsave(&cap->buf.lock, flags);
+	if (cap->buf.curr) {
+		vb2_buffer_done(&cap->buf.curr->vb.vb2_buf, state);
+		cap->buf.curr = NULL;
+	}
+	if (cap->buf.next) {
+		vb2_buffer_done(&cap->buf.next->vb.vb2_buf, state);
+		cap->buf.next = NULL;
+	}
+	while (!list_empty(&cap->buf.queue)) {
+		buf = list_first_entry(&cap->buf.queue,
+				       struct rkisp1_buffer, queue);
+		list_del(&buf->queue);
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+	}
+	spin_unlock_irqrestore(&cap->buf.lock, flags);
+}
+
+/*
+ * rkisp1_pipeline_sink_walk - Walk through the pipeline and call cb
+ * @from: entity at which to start pipeline walk
+ * @until: entity at which to stop pipeline walk
+ *
+ * Walk the entities chain starting at the pipeline video node and stop
+ * all subdevices in the chain.
+ *
+ * If the until argument isn't NULL, stop the pipeline walk when reaching the
+ * until entity. This is used to disable a partially started pipeline due to a
+ * subdev start error.
+ */
+static int rkisp1_pipeline_sink_walk(struct media_entity *from,
+				     struct media_entity *until,
+				     int (*cb)(struct media_entity *from,
+					       struct media_entity *curr))
+{
+	struct media_entity *entity = from;
+	struct media_pad *pad;
+	unsigned int i;
+	int ret;
+
+	while (1) {
+		pad = NULL;
+		/* Find remote source pad */
+		for (i = 0; i < entity->num_pads; i++) {
+			struct media_pad *spad = &entity->pads[i];
+
+			if (!(spad->flags & MEDIA_PAD_FL_SINK))
+				continue;
+			pad = media_entity_remote_pad(spad);
+			if (pad && is_media_entity_v4l2_subdev(pad->entity))
+				break;
+		}
+		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
+			break;
+
+		entity = pad->entity;
+		if (entity == until)
+			break;
+
+		ret = cb(from, entity);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int rkisp1_pipeline_disable_cb(struct media_entity *from,
+				      struct media_entity *curr)
+{
+	struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(curr);
+
+	return v4l2_subdev_call(sd, video, s_stream, false);
+}
+
+static int rkisp1_pipeline_enable_cb(struct media_entity *from,
+				     struct media_entity *curr)
+{
+	struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(curr);
+
+	return v4l2_subdev_call(sd, video, s_stream, true);
+}
+
+static void rkisp1_stream_stop(struct rkisp1_capture *cap)
+{
+	int ret;
+
+	/* Stream should stop in interrupt. If it dosn't, stop it by force. */
+	cap->is_stopping = true;
+	ret = wait_event_timeout(cap->done,
+				 !cap->is_streaming,
+				 msecs_to_jiffies(1000));
+	if (!ret) {
+		cap->rkisp1->debug.stop_timeout[cap->id]++;
+		cap->ops->stop(cap);
+		cap->is_stopping = false;
+		cap->is_streaming = false;
+	}
+}
+
+static void rkisp1_vb2_stop_streaming(struct vb2_queue *queue)
+{
+	struct rkisp1_capture *cap = queue->drv_priv;
+	struct rkisp1_vdev_node *node = &cap->vnode;
+	struct rkisp1_device *rkisp1 = cap->rkisp1;
+	int ret;
+
+	rkisp1_stream_stop(cap);
+	media_pipeline_stop(&node->vdev.entity);
+	ret = rkisp1_pipeline_sink_walk(&node->vdev.entity, NULL,
+					rkisp1_pipeline_disable_cb);
+	if (ret)
+		dev_err(rkisp1->dev,
+			"pipeline stream-off failed error:%d\n", ret);
+
+	rkisp1_return_all_buffers(cap, VB2_BUF_STATE_ERROR);
+
+	ret = v4l2_pipeline_pm_use(&node->vdev.entity, 0);
+	if (ret)
+		dev_err(rkisp1->dev, "pipeline close failed error:%d\n", ret);
+
+	ret = pm_runtime_put(rkisp1->dev);
+	if (ret)
+		dev_err(rkisp1->dev, "power down failed error:%d\n", ret);
+
+	rkisp1_dummy_buf_destroy(cap);
+}
+
+/*
+ * Most of registers inside rockchip ISP1 have shadow register since
+ * they must be not be changed during processing a frame.
+ * Usually, each sub-module updates its shadow register after
+ * processing the last pixel of a frame.
+ */
+static void rkisp1_stream_start(struct rkisp1_capture *cap)
+{
+	struct rkisp1_device *rkisp1 = cap->rkisp1;
+	struct rkisp1_capture *other = &rkisp1->capture_devs[cap->id ^ 1];
+
+	cap->ops->set_data_path(cap);
+	cap->ops->config(cap);
+
+	/* Setup a buffer for the next frame */
+	rkisp1_handle_buffer(cap);
+	cap->ops->enable(cap);
+	/* It's safe to config ACTIVE and SHADOW regs for the
+	 * first stream. While when the second is starting, do NOT
+	 * force update because it also update the first one.
+	 *
+	 * The latter case would drop one more buf(that is 2) since
+	 * there's not buf in shadow when the second FE received. This's
+	 * also required because the second FE maybe corrupt especially
+	 * when run at 120fps.
+	 */
+	if (!other->is_streaming) {
+		/* force cfg update */
+		rkisp1_write(rkisp1,
+			     RKISP1_CIF_MI_INIT_SOFT_UPD, RKISP1_CIF_MI_INIT);
+		rkisp1_handle_buffer(cap);
+	}
+	cap->is_streaming = true;
+}
+
+static int
+rkisp1_vb2_start_streaming(struct vb2_queue *queue, unsigned int count)
+{
+	struct rkisp1_capture *cap = queue->drv_priv;
+	struct media_entity *entity = &cap->vnode.vdev.entity;
+	int ret;
+
+	ret = rkisp1_dummy_buf_create(cap);
+	if (ret)
+		goto err_ret_buffers;
+
+	ret = pm_runtime_get_sync(cap->rkisp1->dev);
+	if (ret) {
+		dev_err(cap->rkisp1->dev, "power up failed %d\n", ret);
+		goto err_destroy_dummy;
+	}
+	ret = v4l2_pipeline_pm_use(entity, 1);
+	if (ret) {
+		dev_err(cap->rkisp1->dev, "open cif pipeline failed %d\n", ret);
+		goto err_pipe_pm_put;
+	}
+
+	rkisp1_stream_start(cap);
+
+	/* start sub-devices */
+	ret = rkisp1_pipeline_sink_walk(entity, NULL,
+					rkisp1_pipeline_enable_cb);
+	if (ret)
+		goto err_stop_stream;
+
+	ret = media_pipeline_start(entity, &cap->rkisp1->pipe);
+	if (ret) {
+		dev_err(cap->rkisp1->dev, "start pipeline failed %d\n", ret);
+		goto err_pipe_disable;
+	}
+
+	return 0;
+
+err_pipe_disable:
+	rkisp1_pipeline_sink_walk(entity, NULL, rkisp1_pipeline_disable_cb);
+err_stop_stream:
+	rkisp1_stream_stop(cap);
+	v4l2_pipeline_pm_use(entity, 0);
+err_pipe_pm_put:
+	pm_runtime_put(cap->rkisp1->dev);
+err_destroy_dummy:
+	rkisp1_dummy_buf_destroy(cap);
+err_ret_buffers:
+	rkisp1_return_all_buffers(cap, VB2_BUF_STATE_QUEUED);
+
+	return ret;
+}
+
+static struct vb2_ops rkisp1_vb2_ops = {
+	.queue_setup = rkisp1_vb2_queue_setup,
+	.buf_queue = rkisp1_vb2_buf_queue,
+	.buf_prepare = rkisp1_vb2_buf_prepare,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.stop_streaming = rkisp1_vb2_stop_streaming,
+	.start_streaming = rkisp1_vb2_start_streaming,
+};
+
+/* ----------------------------------------------------------------------------
+ * IOCTLs operations
+ */
+
+static const struct v4l2_format_info *
+rkisp1_fill_pixfmt(struct v4l2_pix_format_mplane *pixm,
+		   enum rkisp1_stream_id id)
+{
+	struct v4l2_plane_pix_format *plane_y = &pixm->plane_fmt[0];
+	const struct v4l2_format_info *info;
+	unsigned int i;
+	u32 stride;
+
+	info = v4l2_format_info(pixm->pixelformat);
+	pixm->num_planes = info->mem_planes;
+	stride = info->bpp[0] * pixm->width;
+	/* Self path supports custom stride but Main path doesn't */
+	if (id == RKISP1_MAINPATH || plane_y->bytesperline < stride)
+		plane_y->bytesperline = stride;
+	plane_y->sizeimage = plane_y->bytesperline * pixm->height;
+
+	/* normalize stride to pixels per line */
+	stride = DIV_ROUND_UP(plane_y->bytesperline, info->bpp[0]);
+
+	for (i = 1; i < info->comp_planes; i++) {
+		struct v4l2_plane_pix_format *plane = &pixm->plane_fmt[i];
+
+		/* bytesperline for other components derive from Y component */
+		plane->bytesperline = DIV_ROUND_UP(stride, info->hdiv) *
+				      info->bpp[i];
+		plane->sizeimage = plane->bytesperline *
+				   DIV_ROUND_UP(pixm->height, info->vdiv);
+	}
+
+	/*
+	 * If pixfmt is packed, then plane_fmt[0] should contain the total size
+	 * considering all components. plane_fmt[i] for i > 0 should be ignored
+	 * by userspace as mem_planes == 1, but we are keeping information there
+	 * for convenience.
+	 */
+	if (info->mem_planes == 1)
+		for (i = 1; i < info->comp_planes; i++)
+			plane_y->sizeimage += pixm->plane_fmt[i].sizeimage;
+
+	return info;
+}
+
+static const struct rkisp1_capture_fmt_cfg *
+rkisp1_find_fmt_cfg(const struct rkisp1_capture *cap, const u32 pixelfmt)
+{
+	unsigned int i;
+
+	for (i = 0; i < cap->config->fmt_size; i++) {
+		if (cap->config->fmts[i].fourcc == pixelfmt)
+			return &cap->config->fmts[i];
+	}
+	return NULL;
+}
+
+static void rkisp1_try_fmt(const struct rkisp1_capture *cap,
+			   struct v4l2_pix_format_mplane *pixm,
+			   const struct rkisp1_capture_fmt_cfg **fmt_cfg,
+			   const struct v4l2_format_info **fmt_info)
+{
+	const struct rkisp1_capture_config *config = cap->config;
+	struct rkisp1_capture *other_cap =
+			&cap->rkisp1->capture_devs[cap->id ^ 1];
+	const struct rkisp1_capture_fmt_cfg *fmt;
+	const struct v4l2_format_info *info;
+	const unsigned int max_widths[] = { RKISP1_RSZ_MP_SRC_MAX_WIDTH,
+					    RKISP1_RSZ_SP_SRC_MAX_WIDTH };
+	const unsigned int max_heights[] = { RKISP1_RSZ_MP_SRC_MAX_HEIGHT,
+					     RKISP1_RSZ_SP_SRC_MAX_HEIGHT};
+
+	fmt = rkisp1_find_fmt_cfg(cap, pixm->pixelformat);
+	if (!fmt) {
+		fmt = config->fmts;
+		pixm->pixelformat = fmt->fourcc;
+	}
+
+	pixm->width = clamp_t(u32, pixm->width,
+			      RKISP1_RSZ_SRC_MIN_WIDTH, max_widths[cap->id]);
+	pixm->height = clamp_t(u32, pixm->height,
+			       RKISP1_RSZ_SRC_MIN_HEIGHT, max_heights[cap->id]);
+
+	pixm->field = V4L2_FIELD_NONE;
+	pixm->colorspace = V4L2_COLORSPACE_DEFAULT;
+	pixm->ycbcr_enc = V4L2_YCBCR_ENC_DEFAULT;
+
+	info = rkisp1_fill_pixfmt(pixm, cap->id);
+
+	/* can not change quantization when stream-on */
+	if (other_cap->is_streaming)
+		pixm->quantization = other_cap->pix.fmt.quantization;
+	/* output full range by default, take effect in params */
+	else if (!pixm->quantization ||
+		 pixm->quantization > V4L2_QUANTIZATION_LIM_RANGE)
+		pixm->quantization = V4L2_QUANTIZATION_FULL_RANGE;
+
+	if (fmt_cfg)
+		*fmt_cfg = fmt;
+	if (fmt_info)
+		*fmt_info = info;
+}
+
+static void rkisp1_set_fmt(struct rkisp1_capture *cap,
+			   struct v4l2_pix_format_mplane *pixm)
+{
+	rkisp1_try_fmt(cap, pixm, &cap->pix.cfg, &cap->pix.info);
+	cap->pix.fmt = *pixm;
+
+	/* SP supports custom stride in number of pixels of the Y plane */
+	if (cap->id == RKISP1_SELFPATH)
+		cap->sp_y_stride = pixm->plane_fmt[0].bytesperline /
+				   cap->pix.info->bpp[0];
+}
+
+static int rkisp1_try_fmt_vid_cap_mplane(struct file *file, void *fh,
+					 struct v4l2_format *f)
+{
+	struct rkisp1_capture *cap = video_drvdata(file);
+
+	rkisp1_try_fmt(cap, &f->fmt.pix_mp, NULL, NULL);
+
+	return 0;
+}
+
+static int rkisp1_enum_fmt_vid_cap_mplane(struct file *file, void *priv,
+					  struct v4l2_fmtdesc *f)
+{
+	struct rkisp1_capture *cap = video_drvdata(file);
+	const struct rkisp1_capture_fmt_cfg *fmt = NULL;
+
+	if (f->index >= cap->config->fmt_size)
+		return -EINVAL;
+
+	fmt = &cap->config->fmts[f->index];
+	f->pixelformat = fmt->fourcc;
+
+	return 0;
+}
+
+static int rkisp1_s_fmt_vid_cap_mplane(struct file *file,
+				       void *priv, struct v4l2_format *f)
+{
+	struct rkisp1_capture *cap = video_drvdata(file);
+	struct rkisp1_vdev_node *node =
+				rkisp1_vdev_to_node(&cap->vnode.vdev);
+
+	if (vb2_is_busy(&node->buf_queue))
+		return -EBUSY;
+
+	rkisp1_set_fmt(cap, &f->fmt.pix_mp);
+
+	return 0;
+}
+
+static int rkisp1_g_fmt_vid_cap_mplane(struct file *file, void *fh,
+				       struct v4l2_format *f)
+{
+	struct rkisp1_capture *cap = video_drvdata(file);
+
+	f->fmt.pix_mp = cap->pix.fmt;
+
+	return 0;
+}
+
+static int
+rkisp1_querycap(struct file *file, void *priv, struct v4l2_capability *cap)
+{
+	struct rkisp1_capture *cap_dev = video_drvdata(file);
+	struct rkisp1_device *rkisp1 = cap_dev->rkisp1;
+
+	strscpy(cap->driver, rkisp1->dev->driver->name, sizeof(cap->driver));
+	strscpy(cap->card, rkisp1->dev->driver->name, sizeof(cap->card));
+	strscpy(cap->bus_info, RKISP1_BUS_INFO, sizeof(cap->bus_info));
+
+	return 0;
+}
+
+static const struct v4l2_ioctl_ops rkisp1_v4l2_ioctl_ops = {
+	.vidioc_reqbufs = vb2_ioctl_reqbufs,
+	.vidioc_querybuf = vb2_ioctl_querybuf,
+	.vidioc_create_bufs = vb2_ioctl_create_bufs,
+	.vidioc_qbuf = vb2_ioctl_qbuf,
+	.vidioc_expbuf = vb2_ioctl_expbuf,
+	.vidioc_dqbuf = vb2_ioctl_dqbuf,
+	.vidioc_prepare_buf = vb2_ioctl_prepare_buf,
+	.vidioc_streamon = vb2_ioctl_streamon,
+	.vidioc_streamoff = vb2_ioctl_streamoff,
+	.vidioc_try_fmt_vid_cap_mplane = rkisp1_try_fmt_vid_cap_mplane,
+	.vidioc_s_fmt_vid_cap_mplane = rkisp1_s_fmt_vid_cap_mplane,
+	.vidioc_g_fmt_vid_cap_mplane = rkisp1_g_fmt_vid_cap_mplane,
+	.vidioc_enum_fmt_vid_cap = rkisp1_enum_fmt_vid_cap_mplane,
+	.vidioc_querycap = rkisp1_querycap,
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+static int rkisp1_capture_link_validate(struct media_link *link)
+{
+	struct video_device *vdev =
+		media_entity_to_video_device(link->sink->entity);
+	struct v4l2_subdev *sd =
+		media_entity_to_v4l2_subdev(link->source->entity);
+	struct rkisp1_capture *cap = video_get_drvdata(vdev);
+	struct rkisp1_isp *isp = &cap->rkisp1->isp;
+	struct v4l2_subdev_format sd_fmt;
+	int ret;
+
+	if (cap->id == RKISP1_SELFPATH &&
+	    isp->src_fmt->mbus_code != MEDIA_BUS_FMT_YUYV8_2X8) {
+		dev_err(cap->rkisp1->dev,
+			"selfpath only supports MEDIA_BUS_FMT_YUYV8_2X8\n");
+		return -EPIPE;
+	}
+
+	if (cap->pix.cfg->fmt_type != isp->src_fmt->fmt_type) {
+		dev_err(cap->rkisp1->dev,
+			"format type mismatch in link '%s:%d->%s:%d'\n",
+			link->source->entity->name, link->source->index,
+			link->sink->entity->name, link->sink->index);
+		return -EPIPE;
+	}
+
+	sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+	sd_fmt.pad = link->source->index;
+	ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &sd_fmt);
+	if (ret)
+		return ret;
+
+	if (sd_fmt.format.height != cap->pix.fmt.height ||
+	    sd_fmt.format.width != cap->pix.fmt.width)
+		return -EPIPE;
+
+	return 0;
+}
+
+/* ----------------------------------------------------------------------------
+ * core functions
+ */
+
+static const struct media_entity_operations rkisp1_media_ops = {
+	.link_validate = rkisp1_capture_link_validate,
+};
+
+static const struct v4l2_file_operations rkisp1_fops = {
+	.open = v4l2_fh_open,
+	.release = vb2_fop_release,
+	.unlocked_ioctl = video_ioctl2,
+	.poll = vb2_fop_poll,
+	.mmap = vb2_fop_mmap,
+};
+
+static void rkisp1_unregister_capture(struct rkisp1_capture *cap)
+{
+	media_entity_cleanup(&cap->vnode.vdev.entity);
+	video_unregister_device(&cap->vnode.vdev);
+}
+
+void rkisp1_capture_devs_unregister(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_capture *mp = &rkisp1->capture_devs[RKISP1_MAINPATH];
+	struct rkisp1_capture *sp = &rkisp1->capture_devs[RKISP1_SELFPATH];
+
+	rkisp1_unregister_capture(mp);
+	rkisp1_unregister_capture(sp);
+}
+
+static int rkisp1_register_capture(struct rkisp1_capture *cap)
+{
+	const char * const dev_names[] = {RKISP1_MP_DEV_NAME,
+					  RKISP1_SP_DEV_NAME};
+	struct v4l2_device *v4l2_dev = &cap->rkisp1->v4l2_dev;
+	struct video_device *vdev = &cap->vnode.vdev;
+	struct rkisp1_vdev_node *node;
+	struct vb2_queue *q;
+	int ret;
+
+	strscpy(vdev->name, dev_names[cap->id], sizeof(vdev->name));
+	node = rkisp1_vdev_to_node(vdev);
+	mutex_init(&node->vlock);
+
+	vdev->ioctl_ops = &rkisp1_v4l2_ioctl_ops;
+	vdev->release = video_device_release_empty;
+	vdev->fops = &rkisp1_fops;
+	vdev->minor = -1;
+	vdev->v4l2_dev = v4l2_dev;
+	vdev->lock = &node->vlock;
+	vdev->device_caps = V4L2_CAP_VIDEO_CAPTURE_MPLANE |
+			    V4L2_CAP_STREAMING;
+	vdev->entity.ops = &rkisp1_media_ops;
+	video_set_drvdata(vdev, cap);
+	vdev->vfl_dir = VFL_DIR_RX;
+	node->pad.flags = MEDIA_PAD_FL_SINK;
+
+	q = &node->buf_queue;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+	q->io_modes = VB2_MMAP | VB2_DMABUF | VB2_USERPTR;
+	q->drv_priv = cap;
+	q->ops = &rkisp1_vb2_ops;
+	q->mem_ops = &vb2_dma_contig_memops;
+	q->buf_struct_size = sizeof(struct rkisp1_buffer);
+	q->min_buffers_needed = RKISP1_MIN_BUFFERS_NEEDED;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &node->vlock;
+	q->dev = cap->rkisp1->dev;
+	ret = vb2_queue_init(q);
+	if (ret) {
+		dev_err(cap->rkisp1->dev,
+			"vb2 queue init failed (err=%d)\n", ret);
+		return ret;
+	}
+
+	vdev->queue = q;
+
+	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
+	if (ret) {
+		dev_err(cap->rkisp1->dev,
+			"failed to register %s, ret=%d\n", vdev->name, ret);
+		return ret;
+	}
+	v4l2_info(v4l2_dev, "registered %s as /dev/video%d\n", vdev->name,
+		  vdev->num);
+
+	ret = media_entity_pads_init(&vdev->entity, 1, &node->pad);
+	if (ret) {
+		video_unregister_device(vdev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void
+rkisp1_capture_init(struct rkisp1_device *rkisp1, enum rkisp1_stream_id id)
+{
+	struct rkisp1_capture *cap = &rkisp1->capture_devs[id];
+	struct v4l2_pix_format_mplane pixm;
+
+	memset(cap, 0, sizeof(*cap));
+	cap->id = id;
+	cap->rkisp1 = rkisp1;
+
+	INIT_LIST_HEAD(&cap->buf.queue);
+	init_waitqueue_head(&cap->done);
+	spin_lock_init(&cap->buf.lock);
+	if (cap->id == RKISP1_SELFPATH) {
+		cap->ops = &rkisp1_capture_ops_sp;
+		cap->config = &rkisp1_capture_config_sp;
+	} else {
+		cap->ops = &rkisp1_capture_ops_mp;
+		cap->config = &rkisp1_capture_config_mp;
+	}
+
+	cap->is_streaming = false;
+
+	memset(&pixm, 0, sizeof(pixm));
+	pixm.pixelformat = V4L2_PIX_FMT_YUYV;
+	pixm.width = RKISP1_DEFAULT_WIDTH;
+	pixm.height = RKISP1_DEFAULT_HEIGHT;
+	rkisp1_set_fmt(cap, &pixm);
+}
+
+int rkisp1_capture_devs_register(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_capture *cap;
+	unsigned int i, j;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(rkisp1->capture_devs); i++) {
+		rkisp1_capture_init(rkisp1, i);
+		cap = &rkisp1->capture_devs[i];
+		cap->rkisp1 = rkisp1;
+		ret = rkisp1_register_capture(cap);
+		if (ret)
+			goto err_unreg_capture_devs;
+	}
+
+	return 0;
+
+err_unreg_capture_devs:
+	for (j = 0; j < i; j++) {
+		cap = &rkisp1->capture_devs[j];
+		rkisp1_unregister_capture(cap);
+	}
+
+	return ret;
+}
diff --git a/drivers/staging/media/rkisp1/rkisp1-common.c b/drivers/staging/media/rkisp1/rkisp1-common.c
new file mode 100644
index 000000000000..cf889666e166
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-common.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - Common definitions
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ */
+
+#include <media/v4l2-rect.h>
+
+#include "rkisp1-common.h"
+
+static const struct v4l2_rect rkisp1_sd_min_crop = {
+	.width = RKISP1_ISP_MIN_WIDTH,
+	.height = RKISP1_ISP_MIN_HEIGHT,
+	.top = 0,
+	.left = 0,
+};
+
+void rkisp1_sd_adjust_crop_rect(struct v4l2_rect *crop,
+				const struct v4l2_rect *bounds)
+{
+	v4l2_rect_set_min_size(crop, &rkisp1_sd_min_crop);
+	v4l2_rect_map_inside(crop, bounds);
+}
+
+void rkisp1_sd_adjust_crop(struct v4l2_rect *crop,
+			   const struct v4l2_mbus_framefmt *bounds)
+{
+	struct v4l2_rect crop_bounds = {
+		.left = 0,
+		.top = 0,
+		.width = bounds->width,
+		.height = bounds->height,
+	};
+
+	rkisp1_sd_adjust_crop_rect(crop, &crop_bounds);
+}
diff --git a/drivers/staging/media/rkisp1/rkisp1-common.h b/drivers/staging/media/rkisp1/rkisp1-common.h
new file mode 100644
index 000000000000..369a401b098a
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-common.h
@@ -0,0 +1,337 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+/*
+ * Rockchip ISP1 Driver - Common definitions
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ *
+ * Based on Rockchip ISP1 driver by Rockchip Electronics Co., Ltd.
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#ifndef _RKISP1_COMMON_H
+#define _RKISP1_COMMON_H
+
+#include <linux/clk.h>
+#include <linux/mutex.h>
+#include <media/media-device.h>
+#include <media/media-entity.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/videobuf2-v4l2.h>
+
+#include "rkisp1-regs.h"
+#include "uapi/rkisp1-config.h"
+
+#define RKISP1_ISP_MAX_WIDTH		4032
+#define RKISP1_ISP_MAX_HEIGHT		3024
+#define RKISP1_ISP_MIN_WIDTH		32
+#define RKISP1_ISP_MIN_HEIGHT		32
+
+#define RKISP1_RSZ_MP_SRC_MAX_WIDTH		4416
+#define RKISP1_RSZ_MP_SRC_MAX_HEIGHT		3312
+#define RKISP1_RSZ_SP_SRC_MAX_WIDTH		1920
+#define RKISP1_RSZ_SP_SRC_MAX_HEIGHT		1920
+#define RKISP1_RSZ_SRC_MIN_WIDTH		32
+#define RKISP1_RSZ_SRC_MIN_HEIGHT		16
+
+#define RKISP1_DEFAULT_WIDTH		800
+#define RKISP1_DEFAULT_HEIGHT		600
+
+#define RKISP1_DRIVER_NAME	"rkisp1"
+#define RKISP1_BUS_INFO		"platform:" RKISP1_DRIVER_NAME
+
+#define RKISP1_MAX_BUS_CLK	8
+
+enum rkisp1_rsz_pad {
+	RKISP1_RSZ_PAD_SINK,
+	RKISP1_RSZ_PAD_SRC,
+};
+
+enum rkisp1_stream_id {
+	RKISP1_MAINPATH,
+	RKISP1_SELFPATH,
+};
+
+enum rkisp1_fmt_pix_type {
+	RKISP1_FMT_YUV,
+	RKISP1_FMT_RGB,
+	RKISP1_FMT_BAYER,
+	RKISP1_FMT_JPEG,
+};
+
+enum rkisp1_fmt_raw_pat_type {
+	RKISP1_RAW_RGGB = 0,
+	RKISP1_RAW_GRBG,
+	RKISP1_RAW_GBRG,
+	RKISP1_RAW_BGGR,
+};
+
+enum rkisp1_isp_pad {
+	RKISP1_ISP_PAD_SINK_VIDEO,
+	RKISP1_ISP_PAD_SINK_PARAMS,
+	RKISP1_ISP_PAD_SOURCE_VIDEO,
+	RKISP1_ISP_PAD_SOURCE_STATS,
+	RKISP1_ISP_PAD_MAX
+};
+
+/*
+ * struct rkisp1_sensor_async - Sensor information
+ * @mbus: media bus configuration
+ */
+struct rkisp1_sensor_async {
+	struct v4l2_async_subdev asd;
+	struct v4l2_mbus_config mbus;
+	unsigned int lanes;
+	struct v4l2_subdev *sd;
+	struct v4l2_ctrl *pixel_rate_ctrl;
+	struct phy *dphy;
+};
+
+/*
+ * struct rkisp1_isp - ISP sub-device
+ *
+ * See Cropping regions of ISP in rkisp1.c for details
+ * @sink_frm: input size, don't have to be equal to sensor size
+ * @sink_fmt: input format
+ * @sink_crop: crop for sink pad
+ * @src_fmt: output format
+ * @src_crop: output size
+ *
+ * @is_dphy_errctrl_disabled : if dphy errctrl is disabled (avoid endless interrupt)
+ * @frame_sequence: used to synchronize frame_id between video devices.
+ * @quantization: output quantization
+ */
+struct rkisp1_isp {
+	struct v4l2_subdev sd;
+	struct media_pad pads[RKISP1_ISP_PAD_MAX];
+	struct v4l2_subdev_pad_config pad_cfg[RKISP1_ISP_PAD_MAX];
+	const struct rkisp1_isp_mbus_info *sink_fmt;
+	const struct rkisp1_isp_mbus_info *src_fmt;
+	bool is_dphy_errctrl_disabled;
+	atomic_t frame_sequence;
+};
+
+struct rkisp1_vdev_node {
+	struct vb2_queue buf_queue;
+	struct mutex vlock; /* ioctl serialization mutex */
+	struct video_device vdev;
+	struct media_pad pad;
+};
+
+struct rkisp1_buffer {
+	struct vb2_v4l2_buffer vb;
+	struct list_head queue;
+	union {
+		u32 buff_addr[VIDEO_MAX_PLANES];
+		void *vaddr[VIDEO_MAX_PLANES];
+	};
+};
+
+struct rkisp1_dummy_buffer {
+	void *vaddr;
+	dma_addr_t dma_addr;
+	u32 size;
+};
+
+struct rkisp1_device;
+
+/*
+ * struct rkisp1_capture - ISP capture video device
+ *
+ * @pix.fmt: buffer format
+ * @pix.info: pixel information
+ * @pix.cfg: pixel configuration
+ *
+ * @buf.lock: lock to protect buf_queue
+ * @buf.queue: queued buffer list
+ * @buf.dummy: dummy space to store dropped data
+ *
+ * rkisp1 use shadowsock registers, so it need two buffer at a time
+ * @buf.curr: the buffer used for current frame
+ * @buf.next: the buffer used for next frame
+ */
+struct rkisp1_capture {
+	struct rkisp1_vdev_node vnode;
+	struct rkisp1_device *rkisp1;
+	enum rkisp1_stream_id id;
+	struct rkisp1_capture_ops *ops;
+	const struct rkisp1_capture_config *config;
+	bool is_streaming;
+	bool is_stopping;
+	wait_queue_head_t done;
+	unsigned int sp_y_stride;
+	struct {
+		/* protects queue, curr and next */
+		spinlock_t lock;
+		struct list_head queue;
+		struct rkisp1_dummy_buffer dummy;
+		struct rkisp1_buffer *curr;
+		struct rkisp1_buffer *next;
+	} buf;
+	struct {
+		const struct rkisp1_capture_fmt_cfg *cfg;
+		const struct v4l2_format_info *info;
+		struct v4l2_pix_format_mplane fmt;
+	} pix;
+};
+
+/*
+ * struct rkisp1_stats - ISP Statistics device
+ *
+ * @irq_lock: buffer queue lock
+ * @stat: stats buffer list
+ * @readout_wq: workqueue for statistics information read
+ */
+struct rkisp1_stats {
+	struct rkisp1_vdev_node vnode;
+	struct rkisp1_device *rkisp1;
+
+	spinlock_t irq_lock;
+	struct list_head stat;
+	struct v4l2_format vdev_fmt;
+	bool is_streaming;
+
+	struct workqueue_struct *readout_wq;
+	struct mutex wq_lock;
+};
+
+/*
+ * struct rkisp1_params - ISP input parameters device
+ *
+ * @cur_params: Current ISP parameters
+ * @is_first_params: the first params should take effect immediately
+ */
+struct rkisp1_params {
+	struct rkisp1_vdev_node vnode;
+	struct rkisp1_device *rkisp1;
+
+	spinlock_t config_lock;
+	struct list_head params;
+	struct rkisp1_params_cfg cur_params;
+	struct v4l2_format vdev_fmt;
+	bool is_streaming;
+	bool is_first_params;
+
+	enum v4l2_quantization quantization;
+	enum rkisp1_fmt_raw_pat_type raw_type;
+};
+
+struct rkisp1_resizer {
+	struct v4l2_subdev sd;
+	enum rkisp1_stream_id id;
+	struct rkisp1_device *rkisp1;
+	struct media_pad pads[RKISP1_ISP_PAD_MAX];
+	struct v4l2_subdev_pad_config pad_cfg[RKISP1_ISP_PAD_MAX];
+	const struct rkisp1_rsz_config *config;
+	enum rkisp1_fmt_pix_type fmt_type;
+};
+
+struct rkisp1_debug {
+	struct dentry *debugfs_dir;
+	unsigned long data_loss;
+	unsigned long pic_size_error;
+	unsigned long mipi_error;
+	unsigned long stats_error;
+	unsigned long stop_timeout[2];
+	unsigned long frame_drop[2];
+};
+
+/*
+ * struct rkisp1_device - ISP platform device
+ * @base_addr: base register address
+ * @active_sensor: sensor in-use, set when streaming on
+ * @isp: ISP sub-device
+ * @rkisp1_capture: capture video device
+ * @stats: ISP statistics output device
+ * @params: ISP input parameters device
+ */
+struct rkisp1_device {
+	void __iomem *base_addr;
+	int irq;
+	struct device *dev;
+	unsigned int clk_size;
+	struct clk_bulk_data clks[RKISP1_MAX_BUS_CLK];
+	struct v4l2_device v4l2_dev;
+	struct v4l2_ctrl_handler ctrl_handler;
+	struct media_device media_dev;
+	struct v4l2_async_notifier notifier;
+	struct rkisp1_sensor_async *active_sensor;
+	struct rkisp1_isp isp;
+	struct rkisp1_resizer resizer_devs[2];
+	struct rkisp1_capture capture_devs[2];
+	struct rkisp1_stats stats;
+	struct rkisp1_params params;
+	struct media_pipeline pipe;
+	struct vb2_alloc_ctx *alloc_ctx;
+	struct rkisp1_debug debug;
+};
+
+/*
+ * struct rkisp1_isp_mbus_info - ISP pad format info
+ *
+ * Translate mbus_code to hardware format values
+ *
+ * @bus_width: used for parallel
+ */
+struct rkisp1_isp_mbus_info {
+	u32 mbus_code;
+	enum rkisp1_fmt_pix_type fmt_type;
+	u32 mipi_dt;
+	u32 yuv_seq;
+	u8 bus_width;
+	enum rkisp1_fmt_raw_pat_type bayer_pat;
+	unsigned int direction;
+};
+
+static inline void
+rkisp1_write(struct rkisp1_device *rkisp1, u32 val, unsigned int addr)
+{
+	writel(val, rkisp1->base_addr + addr);
+}
+
+static inline u32 rkisp1_read(struct rkisp1_device *rkisp1, unsigned int addr)
+{
+	return readl(rkisp1->base_addr + addr);
+}
+
+void rkisp1_sd_adjust_crop_rect(struct v4l2_rect *crop,
+				const struct v4l2_rect *bounds);
+
+void rkisp1_sd_adjust_crop(struct v4l2_rect *crop,
+			   const struct v4l2_mbus_framefmt *bounds);
+
+int rkisp1_isp_register(struct rkisp1_device *rkisp1,
+			struct v4l2_device *v4l2_dev);
+void rkisp1_isp_unregister(struct rkisp1_device *rkisp1);
+
+const struct rkisp1_isp_mbus_info *rkisp1_isp_mbus_info_get(u32 mbus_code);
+
+void rkisp1_isp_isr(struct rkisp1_device *rkisp1);
+void rkisp1_mipi_isr(struct rkisp1_device *rkisp1);
+void rkisp1_capture_isr(struct rkisp1_device *rkisp1);
+void rkisp1_stats_isr(struct rkisp1_stats *stats, u32 isp_ris);
+void rkisp1_params_isr(struct rkisp1_device *rkisp1, u32 isp_mis);
+
+int rkisp1_capture_devs_register(struct rkisp1_device *rkisp1);
+void rkisp1_capture_devs_unregister(struct rkisp1_device *rkisp1);
+
+int rkisp1_resizer_devs_register(struct rkisp1_device *rkisp1);
+void rkisp1_resizer_devs_unregister(struct rkisp1_device *rkisp1);
+
+int rkisp1_stats_register(struct rkisp1_stats *stats,
+			  struct v4l2_device *v4l2_dev,
+			  struct rkisp1_device *rkisp1);
+void rkisp1_stats_unregister(struct rkisp1_stats *stats);
+
+void rkisp1_params_configure(struct rkisp1_params *params,
+			     enum rkisp1_fmt_raw_pat_type bayer_pat,
+			     enum v4l2_quantization quantization);
+void rkisp1_params_disable(struct rkisp1_params *params);
+int rkisp1_params_register(struct rkisp1_params *params,
+			   struct v4l2_device *v4l2_dev,
+			   struct rkisp1_device *rkisp1);
+void rkisp1_params_unregister(struct rkisp1_params *params);
+
+void rkisp1_params_isr_handler(struct rkisp1_device *rkisp1, u32 isp_mis);
+
+#endif /* _RKISP1_COMMON_H */
diff --git a/drivers/staging/media/rkisp1/rkisp1-dev.c b/drivers/staging/media/rkisp1/rkisp1-dev.c
new file mode 100644
index 000000000000..558126e66465
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-dev.c
@@ -0,0 +1,574 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - Base driver
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ *
+ * Based on Rockchip ISP1 driver by Rockchip Electronics Co., Ltd.
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#include <linux/clk.h>
+#include <linux/debugfs.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/phy/phy.h>
+#include <linux/phy/phy-mipi-dphy.h>
+#include <media/v4l2-fwnode.h>
+
+#include "rkisp1-common.h"
+
+/*
+ * ISP Details
+ * -----------
+ *
+ * ISP Comprises with:
+ *	MIPI serial camera interface
+ *	Image Signal Processing
+ *	Many Image Enhancement Blocks
+ *	Crop
+ *	Resizer
+ *	RBG display ready image
+ *	Image Rotation
+ *
+ * ISP Block Diagram
+ * -----------------
+ *                                                             rkisp1-resizer.c          rkisp1-capture.c
+ *                                                          |====================|  |=======================|
+ *                                rkisp1-isp.c                              Main Picture Path
+ *                        |==========================|      |===============================================|
+ *                        +-----------+  +--+--+--+--+      +--------+  +--------+              +-----------+
+ *                        |           |  |  |  |  |  |      |        |  |        |              |           |
+ * +--------+    |\       |           |  |  |  |  |  |   -->|  Crop  |->|  RSZ   |------------->|           |
+ * |  MIPI  |--->|  \     |           |  |  |  |  |  |   |  |        |  |        |              |           |
+ * +--------+    |   |    |           |  |IE|IE|IE|IE|   |  +--------+  +--------+              |  Memory   |
+ *               |MUX|--->|    ISP    |->|0 |1 |2 |3 |---+                                      | Interface |
+ * +--------+    |   |    |           |  |  |  |  |  |   |  +--------+  +--------+  +--------+  |           |
+ * |Parallel|--->|  /     |           |  |  |  |  |  |   |  |        |  |        |  |        |  |           |
+ * +--------+    |/       |           |  |  |  |  |  |   -->|  Crop  |->|  RSZ   |->|  RGB   |->|           |
+ *                        |           |  |  |  |  |  |      |        |  |        |  | Rotate |  |           |
+ *                        +-----------+  +--+--+--+--+      +--------+  +--------+  +--------+  +-----------+
+ *                                               ^
+ * +--------+                                    |          |===============================================|
+ * |  DMA   |------------------------------------+                          Self Picture Path
+ * +--------+
+ *
+ *         rkisp1-stats.c        rkisp1-params.c
+ *       |===============|      |===============|
+ *       +---------------+      +---------------+
+ *       |               |      |               |
+ *       |      ISP      |      |      ISP      |
+ *       |               |      |               |
+ *       +---------------+      +---------------+
+ *
+ *
+ * Media Topology
+ * --------------
+ *      +----------+     +----------+
+ *      | Sensor 2 |     | Sensor X |
+ *      ------------ ... ------------
+ *      |    0     |     |    0     |
+ *      +----------+     +----------+      +-----------+
+ *                  \      |               |  params   |
+ *                   \     |               | (output)  |
+ *    +----------+    \    |               +-----------+
+ *    | Sensor 1 |     v   v                     |
+ *    ------------      +------+------+          |
+ *    |    0     |----->|  0   |  1   |<---------+
+ *    +----------+      |------+------|
+ *                      |     ISP     |
+ *                      |------+------|
+ *        +-------------|  2   |  3   |----------+
+ *        |             +------+------+          |
+ *        |                |                     |
+ *        v                v                     v
+ *  +- ---------+    +-----------+         +-----------+
+ *  |     0     |    |     0     |         |   stats   |
+ *  -------------    -------------         | (capture) |
+ *  |  Resizer  |    |  Resizer  |         +-----------+
+ *  ------------|    ------------|
+ *  |     1     |    |     1     |
+ *  +-----------+    +-----------+
+ *        |                |
+ *        v                v
+ *  +-----------+    +-----------+
+ *  | selfpath  |    | mainpath  |
+ *  | (capture) |    | (capture) |
+ *  +-----------+    +-----------+
+ */
+
+struct rkisp1_match_data {
+	const char * const *clks;
+	unsigned int size;
+};
+
+/* ----------------------------------------------------------------------------
+ * Sensor DT bindings
+ */
+
+static int rkisp1_create_links(struct rkisp1_device *rkisp1)
+{
+	struct media_entity *source, *sink;
+	unsigned int flags, source_pad;
+	struct v4l2_subdev *sd;
+	unsigned int i;
+	int ret;
+
+	/* sensor links */
+	flags = MEDIA_LNK_FL_ENABLED;
+	list_for_each_entry(sd, &rkisp1->v4l2_dev.subdevs, list) {
+		if (sd == &rkisp1->isp.sd ||
+		    sd == &rkisp1->resizer_devs[RKISP1_MAINPATH].sd ||
+		    sd == &rkisp1->resizer_devs[RKISP1_SELFPATH].sd)
+			continue;
+
+		ret = media_entity_get_fwnode_pad(&sd->entity, sd->fwnode,
+						  MEDIA_PAD_FL_SOURCE);
+		if (ret) {
+			dev_err(sd->dev, "failed to find src pad for %s\n",
+				sd->name);
+			return ret;
+		}
+		source_pad = ret;
+
+		ret = media_create_pad_link(&sd->entity, source_pad,
+					    &rkisp1->isp.sd.entity,
+					    RKISP1_ISP_PAD_SINK_VIDEO,
+					    flags);
+		if (ret)
+			return ret;
+
+		flags = 0;
+	}
+
+	flags = MEDIA_LNK_FL_ENABLED;
+
+	/* create ISP->RSZ->CAP links */
+	for (i = 0; i < 2; i++) {
+		source = &rkisp1->isp.sd.entity;
+		sink = &rkisp1->resizer_devs[i].sd.entity;
+		ret = media_create_pad_link(source, RKISP1_ISP_PAD_SOURCE_VIDEO,
+					    sink, RKISP1_RSZ_PAD_SINK, flags);
+		if (ret)
+			return ret;
+
+		source = sink;
+		sink = &rkisp1->capture_devs[i].vnode.vdev.entity;
+		ret = media_create_pad_link(source, RKISP1_RSZ_PAD_SRC,
+					    sink, 0, flags);
+		if (ret)
+			return ret;
+	}
+
+	/* params links */
+	source = &rkisp1->params.vnode.vdev.entity;
+	sink = &rkisp1->isp.sd.entity;
+	ret = media_create_pad_link(source, 0, sink,
+				    RKISP1_ISP_PAD_SINK_PARAMS, flags);
+	if (ret)
+		return ret;
+
+	/* 3A stats links */
+	source = &rkisp1->isp.sd.entity;
+	sink = &rkisp1->stats.vnode.vdev.entity;
+	return media_create_pad_link(source, RKISP1_ISP_PAD_SOURCE_STATS,
+				     sink, 0, flags);
+}
+
+static int rkisp1_subdev_notifier_bound(struct v4l2_async_notifier *notifier,
+					struct v4l2_subdev *sd,
+					struct v4l2_async_subdev *asd)
+{
+	struct rkisp1_device *rkisp1 =
+		container_of(notifier, struct rkisp1_device, notifier);
+	struct rkisp1_sensor_async *s_asd =
+		container_of(asd, struct rkisp1_sensor_async, asd);
+
+	s_asd->pixel_rate_ctrl = v4l2_ctrl_find(sd->ctrl_handler,
+						V4L2_CID_PIXEL_RATE);
+	s_asd->sd = sd;
+	s_asd->dphy = devm_phy_get(rkisp1->dev, "dphy");
+	if (IS_ERR(s_asd->dphy)) {
+		if (PTR_ERR(s_asd->dphy) != -EPROBE_DEFER)
+			dev_err(rkisp1->dev, "Couldn't get the MIPI D-PHY\n");
+		return PTR_ERR(s_asd->dphy);
+	}
+
+	phy_init(s_asd->dphy);
+
+	return 0;
+}
+
+static void rkisp1_subdev_notifier_unbind(struct v4l2_async_notifier *notifier,
+					  struct v4l2_subdev *sd,
+					  struct v4l2_async_subdev *asd)
+{
+	struct rkisp1_sensor_async *s_asd =
+		container_of(asd, struct rkisp1_sensor_async, asd);
+
+	phy_exit(s_asd->dphy);
+}
+
+static int rkisp1_subdev_notifier_complete(struct v4l2_async_notifier *notifier)
+{
+	struct rkisp1_device *rkisp1 =
+		container_of(notifier, struct rkisp1_device, notifier);
+	int ret;
+
+	mutex_lock(&rkisp1->media_dev.graph_mutex);
+	ret = rkisp1_create_links(rkisp1);
+	if (ret)
+		goto unlock;
+	ret = v4l2_device_register_subdev_nodes(&rkisp1->v4l2_dev);
+	if (ret)
+		goto unlock;
+
+	dev_dbg(rkisp1->dev, "Async subdev notifier completed\n");
+
+unlock:
+	mutex_unlock(&rkisp1->media_dev.graph_mutex);
+	return ret;
+}
+
+static int rkisp1_fwnode_parse(struct device *dev,
+			       struct v4l2_fwnode_endpoint *vep,
+			       struct v4l2_async_subdev *asd)
+{
+	struct rkisp1_sensor_async *s_asd =
+			container_of(asd, struct rkisp1_sensor_async, asd);
+
+	if (vep->bus_type != V4L2_MBUS_CSI2_DPHY) {
+		dev_err(dev, "Only CSI2 bus type is currently supported\n");
+		return -EINVAL;
+	}
+
+	if (vep->base.port != 0) {
+		dev_err(dev, "The ISP has only port 0\n");
+		return -EINVAL;
+	}
+
+	s_asd->mbus.type = vep->bus_type;
+	s_asd->mbus.flags = vep->bus.mipi_csi2.flags;
+	s_asd->lanes = vep->bus.mipi_csi2.num_data_lanes;
+
+	switch (vep->bus.mipi_csi2.num_data_lanes) {
+	case 1:
+		s_asd->mbus.flags |= V4L2_MBUS_CSI2_1_LANE;
+		break;
+	case 2:
+		s_asd->mbus.flags |= V4L2_MBUS_CSI2_2_LANE;
+		break;
+	case 3:
+		s_asd->mbus.flags |= V4L2_MBUS_CSI2_3_LANE;
+		break;
+	case 4:
+		s_asd->mbus.flags |= V4L2_MBUS_CSI2_4_LANE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct v4l2_async_notifier_operations rkisp1_subdev_notifier_ops = {
+	.bound = rkisp1_subdev_notifier_bound,
+	.unbind = rkisp1_subdev_notifier_unbind,
+	.complete = rkisp1_subdev_notifier_complete,
+};
+
+static int rkisp1_subdev_notifier(struct rkisp1_device *rkisp1)
+{
+	struct v4l2_async_notifier *ntf = &rkisp1->notifier;
+	struct device *dev = rkisp1->dev;
+	int ret;
+
+	v4l2_async_notifier_init(ntf);
+
+	ret = v4l2_async_notifier_parse_fwnode_endpoints_by_port(dev, ntf,
+					sizeof(struct rkisp1_sensor_async),
+					0, rkisp1_fwnode_parse);
+	if (ret)
+		return ret;
+
+	if (list_empty(&ntf->asd_list))
+		return -ENODEV;
+
+	ntf->ops = &rkisp1_subdev_notifier_ops;
+
+	return v4l2_async_notifier_register(&rkisp1->v4l2_dev, ntf);
+}
+
+/* ----------------------------------------------------------------------------
+ * Power
+ */
+
+static int __maybe_unused rkisp1_runtime_suspend(struct device *dev)
+{
+	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
+
+	clk_bulk_disable_unprepare(rkisp1->clk_size, rkisp1->clks);
+	return pinctrl_pm_select_sleep_state(dev);
+}
+
+static int __maybe_unused rkisp1_runtime_resume(struct device *dev)
+{
+	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pinctrl_pm_select_default_state(dev);
+	if (ret)
+		return ret;
+	ret = clk_bulk_prepare_enable(rkisp1->clk_size, rkisp1->clks);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct dev_pm_ops rkisp1_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(rkisp1_runtime_suspend, rkisp1_runtime_resume, NULL)
+};
+
+/* ----------------------------------------------------------------------------
+ * Core
+ */
+
+static int rkisp1_entities_register(struct rkisp1_device *rkisp1)
+{
+	int ret;
+
+	ret = rkisp1_isp_register(rkisp1, &rkisp1->v4l2_dev);
+	if (ret)
+		return ret;
+
+	ret = rkisp1_resizer_devs_register(rkisp1);
+	if (ret)
+		goto err_unreg_isp_subdev;
+
+	ret = rkisp1_capture_devs_register(rkisp1);
+	if (ret)
+		goto err_unreg_resizer_devs;
+
+	ret = rkisp1_stats_register(&rkisp1->stats, &rkisp1->v4l2_dev, rkisp1);
+	if (ret)
+		goto err_unreg_capture_devs;
+
+	ret = rkisp1_params_register(&rkisp1->params,
+				     &rkisp1->v4l2_dev, rkisp1);
+	if (ret)
+		goto err_unreg_stats;
+
+	ret = rkisp1_subdev_notifier(rkisp1);
+	if (ret) {
+		dev_err(rkisp1->dev,
+			"Failed to register subdev notifier(%d)\n", ret);
+		goto err_unreg_params;
+	}
+
+	return 0;
+err_unreg_params:
+	rkisp1_params_unregister(&rkisp1->params);
+err_unreg_stats:
+	rkisp1_stats_unregister(&rkisp1->stats);
+err_unreg_capture_devs:
+	rkisp1_capture_devs_unregister(rkisp1);
+err_unreg_resizer_devs:
+	rkisp1_resizer_devs_unregister(rkisp1);
+err_unreg_isp_subdev:
+	rkisp1_isp_unregister(rkisp1);
+	return ret;
+}
+
+static irqreturn_t rkisp1_isr(int irq, void *ctx)
+{
+	struct device *dev = ctx;
+	struct rkisp1_device *rkisp1 = dev_get_drvdata(dev);
+
+	/*
+	 * Call rkisp1_capture_isr() first to handle the frame that
+	 * potentially completed using the current frame_sequence number before
+	 * it is potentially incremented by rkisp1_isp_isr() in the vertical
+	 * sync.
+	 */
+	rkisp1_capture_isr(rkisp1);
+	rkisp1_isp_isr(rkisp1);
+	rkisp1_mipi_isr(rkisp1);
+
+	return IRQ_HANDLED;
+}
+
+static const char * const rk3399_isp_clks[] = {
+	"clk_isp",
+	"aclk_isp",
+	"hclk_isp",
+	"aclk_isp_wrap",
+	"hclk_isp_wrap",
+};
+
+static const struct rkisp1_match_data rk3399_isp_clk_data = {
+	.clks = rk3399_isp_clks,
+	.size = ARRAY_SIZE(rk3399_isp_clks),
+};
+
+static const struct of_device_id rkisp1_of_match[] = {
+	{
+		.compatible = "rockchip,rk3399-cif-isp",
+		.data = &rk3399_isp_clk_data,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, rkisp1_of_match);
+
+static void rkisp1_debug_init(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_debug *debug = &rkisp1->debug;
+
+	debug->debugfs_dir = debugfs_create_dir(RKISP1_DRIVER_NAME, NULL);
+	if (!debug->debugfs_dir) {
+		dev_dbg(rkisp1->dev, "failed to create debugfs directory\n");
+		return;
+	}
+	debugfs_create_ulong("data_loss", 0444, debug->debugfs_dir,
+			     &debug->data_loss);
+	debugfs_create_ulong("pic_size_error", 0444,  debug->debugfs_dir,
+			     &debug->pic_size_error);
+	debugfs_create_ulong("mipi_error", 0444, debug->debugfs_dir,
+			     &debug->mipi_error);
+	debugfs_create_ulong("stats_error", 0444, debug->debugfs_dir,
+			     &debug->stats_error);
+	debugfs_create_ulong("mp_stop_timeout", 0444, debug->debugfs_dir,
+			     &debug->stop_timeout[RKISP1_MAINPATH]);
+	debugfs_create_ulong("sp_stop_timeout", 0444, debug->debugfs_dir,
+			     &debug->stop_timeout[RKISP1_SELFPATH]);
+	debugfs_create_ulong("mp_frame_drop", 0444, debug->debugfs_dir,
+			     &debug->frame_drop[RKISP1_MAINPATH]);
+	debugfs_create_ulong("sp_frame_drop", 0444, debug->debugfs_dir,
+			     &debug->frame_drop[RKISP1_SELFPATH]);
+}
+
+static int rkisp1_probe(struct platform_device *pdev)
+{
+	struct device_node *node = pdev->dev.of_node;
+	const struct rkisp1_match_data *clk_data;
+	const struct of_device_id *match;
+	struct device *dev = &pdev->dev;
+	struct rkisp1_device *rkisp1;
+	struct v4l2_device *v4l2_dev;
+	unsigned int i;
+	int ret, irq;
+
+	match = of_match_node(rkisp1_of_match, node);
+	rkisp1 = devm_kzalloc(dev, sizeof(*rkisp1), GFP_KERNEL);
+	if (!rkisp1)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, rkisp1);
+	rkisp1->dev = dev;
+
+	rkisp1->base_addr = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(rkisp1->base_addr))
+		return PTR_ERR(rkisp1->base_addr);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(dev, irq, rkisp1_isr, IRQF_SHARED,
+			       dev_driver_string(dev), dev);
+	if (ret) {
+		dev_err(dev, "request irq failed: %d\n", ret);
+		return ret;
+	}
+
+	rkisp1->irq = irq;
+	clk_data = match->data;
+
+	for (i = 0; i < clk_data->size; i++)
+		rkisp1->clks[i].id = clk_data->clks[i];
+	ret = devm_clk_bulk_get(dev, clk_data->size, rkisp1->clks);
+	if (ret)
+		return ret;
+	rkisp1->clk_size = clk_data->size;
+
+	pm_runtime_enable(&pdev->dev);
+
+	strscpy(rkisp1->media_dev.model, RKISP1_DRIVER_NAME,
+		sizeof(rkisp1->media_dev.model));
+	rkisp1->media_dev.dev = &pdev->dev;
+	strscpy(rkisp1->media_dev.bus_info,
+		"platform: " RKISP1_DRIVER_NAME,
+		sizeof(rkisp1->media_dev.bus_info));
+	media_device_init(&rkisp1->media_dev);
+
+	v4l2_dev = &rkisp1->v4l2_dev;
+	v4l2_dev->mdev = &rkisp1->media_dev;
+	strscpy(v4l2_dev->name, RKISP1_DRIVER_NAME, sizeof(v4l2_dev->name));
+
+	ret = v4l2_device_register(rkisp1->dev, &rkisp1->v4l2_dev);
+	if (ret)
+		return ret;
+
+	ret = media_device_register(&rkisp1->media_dev);
+	if (ret) {
+		dev_err(dev, "Failed to register media device: %d\n", ret);
+		goto err_unreg_v4l2_dev;
+	}
+
+	ret = rkisp1_entities_register(rkisp1);
+	if (ret)
+		goto err_unreg_media_dev;
+
+	rkisp1_debug_init(rkisp1);
+
+	return 0;
+
+err_unreg_media_dev:
+	media_device_unregister(&rkisp1->media_dev);
+err_unreg_v4l2_dev:
+	v4l2_device_unregister(&rkisp1->v4l2_dev);
+	pm_runtime_disable(&pdev->dev);
+	return ret;
+}
+
+static int rkisp1_remove(struct platform_device *pdev)
+{
+	struct rkisp1_device *rkisp1 = platform_get_drvdata(pdev);
+
+	v4l2_async_notifier_unregister(&rkisp1->notifier);
+	v4l2_async_notifier_cleanup(&rkisp1->notifier);
+
+	rkisp1_params_unregister(&rkisp1->params);
+	rkisp1_stats_unregister(&rkisp1->stats);
+	rkisp1_capture_devs_unregister(rkisp1);
+	rkisp1_resizer_devs_unregister(rkisp1);
+	rkisp1_isp_unregister(rkisp1);
+
+	media_device_unregister(&rkisp1->media_dev);
+	v4l2_device_unregister(&rkisp1->v4l2_dev);
+
+	pm_runtime_disable(&pdev->dev);
+
+	debugfs_remove_recursive(rkisp1->debug.debugfs_dir);
+	return 0;
+}
+
+static struct platform_driver rkisp1_drv = {
+	.driver = {
+		.name = RKISP1_DRIVER_NAME,
+		.of_match_table = of_match_ptr(rkisp1_of_match),
+		.pm = &rkisp1_pm_ops,
+	},
+	.probe = rkisp1_probe,
+	.remove = rkisp1_remove,
+};
+
+module_platform_driver(rkisp1_drv);
+MODULE_DESCRIPTION("Rockchip ISP1 platform driver");
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/staging/media/rkisp1/rkisp1-isp.c b/drivers/staging/media/rkisp1/rkisp1-isp.c
new file mode 100644
index 000000000000..328c7ea60971
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-isp.c
@@ -0,0 +1,1164 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - ISP Subdevice
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ *
+ * Based on Rockchip ISP1 driver by Rockchip Electronics Co., Ltd.
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#include <linux/iopoll.h>
+#include <linux/phy/phy.h>
+#include <linux/phy/phy-mipi-dphy.h>
+#include <linux/pm_runtime.h>
+#include <linux/videodev2.h>
+#include <linux/vmalloc.h>
+#include <media/v4l2-event.h>
+
+#include "rkisp1-common.h"
+
+#define RKISP1_DEF_SINK_PAD_FMT MEDIA_BUS_FMT_SRGGB10_1X10
+#define RKISP1_DEF_SRC_PAD_FMT MEDIA_BUS_FMT_YUYV8_2X8
+
+#define RKISP1_ISP_DEV_NAME	RKISP1_DRIVER_NAME "_isp"
+
+#define RKISP1_DIR_SRC BIT(0)
+#define RKISP1_DIR_SINK BIT(1)
+#define RKISP1_DIR_SINK_SRC (RKISP1_DIR_SINK | RKISP1_DIR_SRC)
+
+/*
+ * NOTE: MIPI controller and input MUX are also configured in this file,
+ * because ISP Subdev is not only describe ISP submodule(input size,format,
+ * output size, format), but also a virtual route device.
+ */
+
+/*
+ * There are many variables named with format/frame in below code,
+ * please see here for their meaning.
+ * Cropping in the sink pad defines the image region from the sensor.
+ * Cropping in the source pad defines the region for the Image Stabilizer (IS)
+ *
+ * Cropping regions of ISP
+ *
+ * +---------------------------------------------------------+
+ * | Sensor image                                            |
+ * | +---------------------------------------------------+   |
+ * | | CIF_ISP_ACQ (for black level)                     |   |
+ * | | sink pad format                                   |   |
+ * | | +--------------------------------------------+    |   |
+ * | | |    CIF_ISP_OUT                             |    |   |
+ * | | |    sink pad crop                           |    |   |
+ * | | |    +---------------------------------+     |    |   |
+ * | | |    |   CIF_ISP_IS                    |     |    |   |
+ * | | |    |   source pad crop and format    |     |    |   |
+ * | | |    +---------------------------------+     |    |   |
+ * | | +--------------------------------------------+    |   |
+ * | +---------------------------------------------------+   |
+ * +---------------------------------------------------------+
+ */
+
+static const struct rkisp1_isp_mbus_info rkisp1_isp_formats[] = {
+	{
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_2X8,
+		.fmt_type	= RKISP1_FMT_YUV,
+		.direction	= RKISP1_DIR_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SRGGB10_1X10,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW10,
+		.bayer_pat	= RKISP1_RAW_RGGB,
+		.bus_width	= 10,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SBGGR10_1X10,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW10,
+		.bayer_pat	= RKISP1_RAW_BGGR,
+		.bus_width	= 10,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SGBRG10_1X10,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW10,
+		.bayer_pat	= RKISP1_RAW_GBRG,
+		.bus_width	= 10,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG10_1X10,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW10,
+		.bayer_pat	= RKISP1_RAW_GRBG,
+		.bus_width	= 10,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SRGGB12_1X12,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW12,
+		.bayer_pat	= RKISP1_RAW_RGGB,
+		.bus_width	= 12,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SBGGR12_1X12,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW12,
+		.bayer_pat	= RKISP1_RAW_BGGR,
+		.bus_width	= 12,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SGBRG12_1X12,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW12,
+		.bayer_pat	= RKISP1_RAW_GBRG,
+		.bus_width	= 12,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG12_1X12,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW12,
+		.bayer_pat	= RKISP1_RAW_GRBG,
+		.bus_width	= 12,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SRGGB8_1X8,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW8,
+		.bayer_pat	= RKISP1_RAW_RGGB,
+		.bus_width	= 8,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SBGGR8_1X8,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW8,
+		.bayer_pat	= RKISP1_RAW_BGGR,
+		.bus_width	= 8,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SGBRG8_1X8,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW8,
+		.bayer_pat	= RKISP1_RAW_GBRG,
+		.bus_width	= 8,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_SGRBG8_1X8,
+		.fmt_type	= RKISP1_FMT_BAYER,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_RAW8,
+		.bayer_pat	= RKISP1_RAW_GRBG,
+		.bus_width	= 8,
+		.direction	= RKISP1_DIR_SINK_SRC,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_YUYV8_1X16,
+		.fmt_type	= RKISP1_FMT_YUV,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_YUV422_8b,
+		.yuv_seq	= RKISP1_CIF_ISP_ACQ_PROP_YCBYCR,
+		.bus_width	= 16,
+		.direction	= RKISP1_DIR_SINK,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_YVYU8_1X16,
+		.fmt_type	= RKISP1_FMT_YUV,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_YUV422_8b,
+		.yuv_seq	= RKISP1_CIF_ISP_ACQ_PROP_YCRYCB,
+		.bus_width	= 16,
+		.direction	= RKISP1_DIR_SINK,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_UYVY8_1X16,
+		.fmt_type	= RKISP1_FMT_YUV,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_YUV422_8b,
+		.yuv_seq	= RKISP1_CIF_ISP_ACQ_PROP_CBYCRY,
+		.bus_width	= 16,
+		.direction	= RKISP1_DIR_SINK,
+	}, {
+		.mbus_code	= MEDIA_BUS_FMT_VYUY8_1X16,
+		.fmt_type	= RKISP1_FMT_YUV,
+		.mipi_dt	= RKISP1_CIF_CSI2_DT_YUV422_8b,
+		.yuv_seq	= RKISP1_CIF_ISP_ACQ_PROP_CRYCBY,
+		.bus_width	= 16,
+		.direction	= RKISP1_DIR_SINK,
+	},
+};
+
+/* ----------------------------------------------------------------------------
+ * Helpers
+ */
+
+const struct rkisp1_isp_mbus_info *rkisp1_isp_mbus_info_get(u32 mbus_code)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(rkisp1_isp_formats); i++) {
+		const struct rkisp1_isp_mbus_info *fmt = &rkisp1_isp_formats[i];
+
+		if (fmt->mbus_code == mbus_code)
+			return fmt;
+	}
+
+	return NULL;
+}
+
+static struct v4l2_subdev *rkisp1_get_remote_sensor(struct v4l2_subdev *sd)
+{
+	struct media_pad *local, *remote;
+	struct media_entity *sensor_me;
+
+	local = &sd->entity.pads[RKISP1_ISP_PAD_SINK_VIDEO];
+	remote = media_entity_remote_pad(local);
+	if (!remote) {
+		dev_warn(sd->dev, "No link between isp and sensor\n");
+		return NULL;
+	}
+
+	sensor_me = remote->entity;
+	return media_entity_to_v4l2_subdev(sensor_me);
+}
+
+static struct v4l2_mbus_framefmt *
+rkisp1_isp_get_pad_fmt(struct rkisp1_isp *isp,
+		       struct v4l2_subdev_pad_config *cfg,
+		       unsigned int pad, u32 which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_format(&isp->sd, cfg, pad);
+	else
+		return v4l2_subdev_get_try_format(&isp->sd, isp->pad_cfg, pad);
+}
+
+static struct v4l2_rect *
+rkisp1_isp_get_pad_crop(struct rkisp1_isp *isp,
+			struct v4l2_subdev_pad_config *cfg,
+			unsigned int pad, u32 which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_crop(&isp->sd, cfg, pad);
+	else
+		return v4l2_subdev_get_try_crop(&isp->sd, isp->pad_cfg, pad);
+}
+
+/* ----------------------------------------------------------------------------
+ * Camera Interface registers configurations
+ */
+
+/*
+ * Image Stabilization.
+ * This should only be called when configuring CIF
+ * or at the frame end interrupt
+ */
+static void rkisp1_config_ism(struct rkisp1_device *rkisp1)
+{
+	struct v4l2_rect *src_crop =
+		rkisp1_isp_get_pad_crop(&rkisp1->isp, NULL,
+					RKISP1_ISP_PAD_SOURCE_VIDEO,
+					V4L2_SUBDEV_FORMAT_ACTIVE);
+	u32 val;
+
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_IS_RECENTER);
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_IS_MAX_DX);
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_IS_MAX_DY);
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_IS_DISPLACE);
+	rkisp1_write(rkisp1, src_crop->left, RKISP1_CIF_ISP_IS_H_OFFS);
+	rkisp1_write(rkisp1, src_crop->top, RKISP1_CIF_ISP_IS_V_OFFS);
+	rkisp1_write(rkisp1, src_crop->width, RKISP1_CIF_ISP_IS_H_SIZE);
+	rkisp1_write(rkisp1, src_crop->height, RKISP1_CIF_ISP_IS_V_SIZE);
+
+	/* IS(Image Stabilization) is always on, working as output crop */
+	rkisp1_write(rkisp1, 1, RKISP1_CIF_ISP_IS_CTRL);
+	val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_CTRL);
+	val |= RKISP1_CIF_ISP_CTRL_ISP_CFG_UPD;
+	rkisp1_write(rkisp1, val, RKISP1_CIF_ISP_CTRL);
+}
+
+/*
+ * configure ISP blocks with input format, size......
+ */
+static int rkisp1_config_isp(struct rkisp1_device *rkisp1)
+{
+	u32 isp_ctrl = 0, irq_mask = 0, acq_mult = 0, signal = 0;
+	const struct rkisp1_isp_mbus_info *src_fmt, *sink_fmt;
+	struct rkisp1_sensor_async *sensor;
+	struct v4l2_mbus_framefmt *sink_frm;
+	struct v4l2_rect *sink_crop;
+
+	sensor = rkisp1->active_sensor;
+	sink_fmt = rkisp1->isp.sink_fmt;
+	src_fmt = rkisp1->isp.src_fmt;
+	sink_frm = rkisp1_isp_get_pad_fmt(&rkisp1->isp, NULL,
+					  RKISP1_ISP_PAD_SINK_VIDEO,
+					  V4L2_SUBDEV_FORMAT_ACTIVE);
+	sink_crop = rkisp1_isp_get_pad_crop(&rkisp1->isp, NULL,
+					    RKISP1_ISP_PAD_SINK_VIDEO,
+					    V4L2_SUBDEV_FORMAT_ACTIVE);
+
+	if (sink_fmt->fmt_type == RKISP1_FMT_BAYER) {
+		acq_mult = 1;
+		if (src_fmt->fmt_type == RKISP1_FMT_BAYER) {
+			if (sensor->mbus.type == V4L2_MBUS_BT656)
+				isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_RAW_PICT_ITU656;
+			else
+				isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_RAW_PICT;
+		} else {
+			rkisp1_write(rkisp1, RKISP1_CIF_ISP_DEMOSAIC_TH(0xc),
+				     RKISP1_CIF_ISP_DEMOSAIC);
+
+			if (sensor->mbus.type == V4L2_MBUS_BT656)
+				isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_BAYER_ITU656;
+			else
+				isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_BAYER_ITU601;
+		}
+	} else if (sink_fmt->fmt_type == RKISP1_FMT_YUV) {
+		acq_mult = 2;
+		if (sensor->mbus.type == V4L2_MBUS_CSI2_DPHY) {
+			isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_ITU601;
+		} else {
+			if (sensor->mbus.type == V4L2_MBUS_BT656)
+				isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_ITU656;
+			else
+				isp_ctrl = RKISP1_CIF_ISP_CTRL_ISP_MODE_ITU601;
+		}
+
+		irq_mask |= RKISP1_CIF_ISP_DATA_LOSS;
+	}
+
+	/* Set up input acquisition properties */
+	if (sensor->mbus.type == V4L2_MBUS_BT656 ||
+	    sensor->mbus.type == V4L2_MBUS_PARALLEL) {
+		if (sensor->mbus.flags & V4L2_MBUS_PCLK_SAMPLE_RISING)
+			signal = RKISP1_CIF_ISP_ACQ_PROP_POS_EDGE;
+	}
+
+	if (sensor->mbus.type == V4L2_MBUS_PARALLEL) {
+		if (sensor->mbus.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW)
+			signal |= RKISP1_CIF_ISP_ACQ_PROP_VSYNC_LOW;
+
+		if (sensor->mbus.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW)
+			signal |= RKISP1_CIF_ISP_ACQ_PROP_HSYNC_LOW;
+	}
+
+	rkisp1_write(rkisp1, isp_ctrl, RKISP1_CIF_ISP_CTRL);
+	rkisp1_write(rkisp1, signal | sink_fmt->yuv_seq |
+		     RKISP1_CIF_ISP_ACQ_PROP_BAYER_PAT(sink_fmt->bayer_pat) |
+		     RKISP1_CIF_ISP_ACQ_PROP_FIELD_SEL_ALL,
+		     RKISP1_CIF_ISP_ACQ_PROP);
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_ACQ_NR_FRAMES);
+
+	/* Acquisition Size */
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_ACQ_H_OFFS);
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_ACQ_V_OFFS);
+	rkisp1_write(rkisp1,
+		     acq_mult * sink_frm->width, RKISP1_CIF_ISP_ACQ_H_SIZE);
+	rkisp1_write(rkisp1, sink_frm->height, RKISP1_CIF_ISP_ACQ_V_SIZE);
+
+	/* ISP Out Area */
+	rkisp1_write(rkisp1, sink_crop->left, RKISP1_CIF_ISP_OUT_H_OFFS);
+	rkisp1_write(rkisp1, sink_crop->top, RKISP1_CIF_ISP_OUT_V_OFFS);
+	rkisp1_write(rkisp1, sink_crop->width, RKISP1_CIF_ISP_OUT_H_SIZE);
+	rkisp1_write(rkisp1, sink_crop->height, RKISP1_CIF_ISP_OUT_V_SIZE);
+
+	irq_mask |= RKISP1_CIF_ISP_FRAME | RKISP1_CIF_ISP_V_START |
+		    RKISP1_CIF_ISP_PIC_SIZE_ERROR | RKISP1_CIF_ISP_FRAME_IN;
+	rkisp1_write(rkisp1, irq_mask, RKISP1_CIF_ISP_IMSC);
+
+	if (src_fmt->fmt_type == RKISP1_FMT_BAYER) {
+		rkisp1_params_disable(&rkisp1->params);
+	} else {
+		struct v4l2_mbus_framefmt *src_frm;
+
+		src_frm = rkisp1_isp_get_pad_fmt(&rkisp1->isp, NULL,
+						 RKISP1_ISP_PAD_SINK_VIDEO,
+						 V4L2_SUBDEV_FORMAT_ACTIVE);
+		rkisp1_params_configure(&rkisp1->params, sink_fmt->bayer_pat,
+					src_frm->quantization);
+	}
+
+	return 0;
+}
+
+static int rkisp1_config_dvp(struct rkisp1_device *rkisp1)
+{
+	const struct rkisp1_isp_mbus_info *sink_fmt = rkisp1->isp.sink_fmt;
+	u32 val, input_sel;
+
+	switch (sink_fmt->bus_width) {
+	case 8:
+		input_sel = RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_8B_ZERO;
+		break;
+	case 10:
+		input_sel = RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_10B_ZERO;
+		break;
+	case 12:
+		input_sel = RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_12B;
+		break;
+	default:
+		dev_err(rkisp1->dev, "Invalid bus width\n");
+		return -EINVAL;
+	}
+
+	val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_ACQ_PROP);
+	rkisp1_write(rkisp1, val | input_sel, RKISP1_CIF_ISP_ACQ_PROP);
+
+	return 0;
+}
+
+static int rkisp1_config_mipi(struct rkisp1_device *rkisp1)
+{
+	const struct rkisp1_isp_mbus_info *sink_fmt = rkisp1->isp.sink_fmt;
+	unsigned int lanes;
+	u32 mipi_ctrl;
+
+	/*
+	 * rkisp1->active_sensor->mbus is set in isp or d-phy notifier_bound
+	 * function
+	 */
+	switch (rkisp1->active_sensor->mbus.flags & V4L2_MBUS_CSI2_LANES) {
+	case V4L2_MBUS_CSI2_4_LANE:
+		lanes = 4;
+		break;
+	case V4L2_MBUS_CSI2_3_LANE:
+		lanes = 3;
+		break;
+	case V4L2_MBUS_CSI2_2_LANE:
+		lanes = 2;
+		break;
+	case V4L2_MBUS_CSI2_1_LANE:
+		lanes = 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	mipi_ctrl = RKISP1_CIF_MIPI_CTRL_NUM_LANES(lanes - 1) |
+		    RKISP1_CIF_MIPI_CTRL_SHUTDOWNLANES(0xf) |
+		    RKISP1_CIF_MIPI_CTRL_ERR_SOT_SYNC_HS_SKIP |
+		    RKISP1_CIF_MIPI_CTRL_CLOCKLANE_ENA;
+
+	rkisp1_write(rkisp1, mipi_ctrl, RKISP1_CIF_MIPI_CTRL);
+
+	/* Configure Data Type and Virtual Channel */
+	rkisp1_write(rkisp1,
+		     RKISP1_CIF_MIPI_DATA_SEL_DT(sink_fmt->mipi_dt) |
+		     RKISP1_CIF_MIPI_DATA_SEL_VC(0),
+		     RKISP1_CIF_MIPI_IMG_DATA_SEL);
+
+	/* Clear MIPI interrupts */
+	rkisp1_write(rkisp1, ~0, RKISP1_CIF_MIPI_ICR);
+	/*
+	 * Disable RKISP1_CIF_MIPI_ERR_DPHY interrupt here temporary for
+	 * isp bus may be dead when switch isp.
+	 */
+	rkisp1_write(rkisp1,
+		     RKISP1_CIF_MIPI_FRAME_END | RKISP1_CIF_MIPI_ERR_CSI |
+		     RKISP1_CIF_MIPI_ERR_DPHY |
+		     RKISP1_CIF_MIPI_SYNC_FIFO_OVFLW(0x03) |
+		     RKISP1_CIF_MIPI_ADD_DATA_OVFLW,
+		     RKISP1_CIF_MIPI_IMSC);
+
+	dev_dbg(rkisp1->dev, "\n  MIPI_CTRL 0x%08x\n"
+		"  MIPI_IMG_DATA_SEL 0x%08x\n"
+		"  MIPI_STATUS 0x%08x\n"
+		"  MIPI_IMSC 0x%08x\n",
+		rkisp1_read(rkisp1, RKISP1_CIF_MIPI_CTRL),
+		rkisp1_read(rkisp1, RKISP1_CIF_MIPI_IMG_DATA_SEL),
+		rkisp1_read(rkisp1, RKISP1_CIF_MIPI_STATUS),
+		rkisp1_read(rkisp1, RKISP1_CIF_MIPI_IMSC));
+
+	return 0;
+}
+
+/* Configure MUX */
+static int rkisp1_config_path(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_sensor_async *sensor = rkisp1->active_sensor;
+	u32 dpcl = rkisp1_read(rkisp1, RKISP1_CIF_VI_DPCL);
+	int ret = 0;
+
+	if (sensor->mbus.type == V4L2_MBUS_BT656 ||
+	    sensor->mbus.type == V4L2_MBUS_PARALLEL) {
+		ret = rkisp1_config_dvp(rkisp1);
+		dpcl |= RKISP1_CIF_VI_DPCL_IF_SEL_PARALLEL;
+	} else if (sensor->mbus.type == V4L2_MBUS_CSI2_DPHY) {
+		ret = rkisp1_config_mipi(rkisp1);
+		dpcl |= RKISP1_CIF_VI_DPCL_IF_SEL_MIPI;
+	}
+
+	rkisp1_write(rkisp1, dpcl, RKISP1_CIF_VI_DPCL);
+
+	return ret;
+}
+
+/* Hardware configure Entry */
+static int rkisp1_config_cif(struct rkisp1_device *rkisp1)
+{
+	u32 cif_id;
+	int ret;
+
+	cif_id = rkisp1_read(rkisp1, RKISP1_CIF_VI_ID);
+	dev_dbg(rkisp1->dev, "CIF_ID 0x%08x\n", cif_id);
+
+	ret = rkisp1_config_isp(rkisp1);
+	if (ret)
+		return ret;
+	ret = rkisp1_config_path(rkisp1);
+	if (ret)
+		return ret;
+	rkisp1_config_ism(rkisp1);
+
+	return 0;
+}
+
+static int rkisp1_isp_stop(struct rkisp1_device *rkisp1)
+{
+	u32 val;
+
+	/*
+	 * ISP(mi) stop in mi frame end -> Stop ISP(mipi) ->
+	 * Stop ISP(isp) ->wait for ISP isp off
+	 */
+	/* stop and clear MI, MIPI, and ISP interrupts */
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_MIPI_IMSC);
+	rkisp1_write(rkisp1, ~0, RKISP1_CIF_MIPI_ICR);
+
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_ISP_IMSC);
+	rkisp1_write(rkisp1, ~0, RKISP1_CIF_ISP_ICR);
+
+	rkisp1_write(rkisp1, 0, RKISP1_CIF_MI_IMSC);
+	rkisp1_write(rkisp1, ~0, RKISP1_CIF_MI_ICR);
+	val = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_CTRL);
+	rkisp1_write(rkisp1, val & (~RKISP1_CIF_MIPI_CTRL_OUTPUT_ENA),
+		     RKISP1_CIF_MIPI_CTRL);
+	/* stop ISP */
+	val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_CTRL);
+	val &= ~(RKISP1_CIF_ISP_CTRL_ISP_INFORM_ENABLE |
+		 RKISP1_CIF_ISP_CTRL_ISP_ENABLE);
+	rkisp1_write(rkisp1, val, RKISP1_CIF_ISP_CTRL);
+
+	val = rkisp1_read(rkisp1,	RKISP1_CIF_ISP_CTRL);
+	rkisp1_write(rkisp1, val | RKISP1_CIF_ISP_CTRL_ISP_CFG_UPD,
+		     RKISP1_CIF_ISP_CTRL);
+
+	readx_poll_timeout(readl, rkisp1->base_addr + RKISP1_CIF_ISP_RIS,
+			   val, val & RKISP1_CIF_ISP_OFF, 20, 100);
+	rkisp1_write(rkisp1,
+		     RKISP1_CIF_IRCL_MIPI_SW_RST | RKISP1_CIF_IRCL_ISP_SW_RST,
+		     RKISP1_CIF_IRCL);
+	rkisp1_write(rkisp1, 0x0, RKISP1_CIF_IRCL);
+
+	return 0;
+}
+
+static void rkisp1_config_clk(struct rkisp1_device *rkisp1)
+{
+	u32 val = RKISP1_CIF_ICCL_ISP_CLK | RKISP1_CIF_ICCL_CP_CLK |
+		  RKISP1_CIF_ICCL_MRSZ_CLK | RKISP1_CIF_ICCL_SRSZ_CLK |
+		  RKISP1_CIF_ICCL_JPEG_CLK | RKISP1_CIF_ICCL_MI_CLK |
+		  RKISP1_CIF_ICCL_IE_CLK | RKISP1_CIF_ICCL_MIPI_CLK |
+		  RKISP1_CIF_ICCL_DCROP_CLK;
+
+	rkisp1_write(rkisp1, val, RKISP1_CIF_ICCL);
+}
+
+static int rkisp1_isp_start(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_sensor_async *sensor = rkisp1->active_sensor;
+	u32 val;
+
+	rkisp1_config_clk(rkisp1);
+
+	/* Activate MIPI */
+	if (sensor->mbus.type == V4L2_MBUS_CSI2_DPHY) {
+		val = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_CTRL);
+		rkisp1_write(rkisp1, val | RKISP1_CIF_MIPI_CTRL_OUTPUT_ENA,
+			     RKISP1_CIF_MIPI_CTRL);
+	}
+	/* Activate ISP */
+	val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_CTRL);
+	val |= RKISP1_CIF_ISP_CTRL_ISP_CFG_UPD |
+	       RKISP1_CIF_ISP_CTRL_ISP_ENABLE |
+	       RKISP1_CIF_ISP_CTRL_ISP_INFORM_ENABLE;
+	rkisp1_write(rkisp1, val, RKISP1_CIF_ISP_CTRL);
+
+	/*
+	 * CIF spec says to wait for sufficient time after enabling
+	 * the MIPI interface and before starting the sensor output.
+	 */
+	usleep_range(1000, 1200);
+
+	return 0;
+}
+
+/* ----------------------------------------------------------------------------
+ * Subdev pad operations
+ */
+
+static int rkisp1_isp_enum_mbus_code(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_pad_config *cfg,
+				     struct v4l2_subdev_mbus_code_enum *code)
+{
+	unsigned int i, dir;
+	int pos = 0;
+
+	if (code->pad == RKISP1_ISP_PAD_SINK_VIDEO) {
+		dir = RKISP1_DIR_SINK;
+	} else if (code->pad == RKISP1_ISP_PAD_SOURCE_VIDEO) {
+		dir = RKISP1_DIR_SRC;
+	} else {
+		if (code->index > 0)
+			return -EINVAL;
+		code->code = MEDIA_BUS_FMT_FIXED;
+		return 0;
+	}
+
+	if (code->index >= ARRAY_SIZE(rkisp1_isp_formats))
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(rkisp1_isp_formats); i++) {
+		const struct rkisp1_isp_mbus_info *fmt = &rkisp1_isp_formats[i];
+
+		if (fmt->direction & dir)
+			pos++;
+
+		if (code->index == pos - 1) {
+			code->code = fmt->mbus_code;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int rkisp1_isp_init_config(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg)
+{
+	struct v4l2_mbus_framefmt *sink_fmt, *src_fmt;
+	struct v4l2_rect *sink_crop, *src_crop;
+
+	sink_fmt = v4l2_subdev_get_try_format(sd, cfg,
+					      RKISP1_ISP_PAD_SINK_VIDEO);
+	sink_fmt->width = RKISP1_DEFAULT_WIDTH;
+	sink_fmt->height = RKISP1_DEFAULT_HEIGHT;
+	sink_fmt->field = V4L2_FIELD_NONE;
+	sink_fmt->code = RKISP1_DEF_SINK_PAD_FMT;
+
+	sink_crop = v4l2_subdev_get_try_crop(sd, cfg,
+					     RKISP1_ISP_PAD_SINK_VIDEO);
+	sink_crop->width = RKISP1_DEFAULT_WIDTH;
+	sink_crop->height = RKISP1_DEFAULT_HEIGHT;
+	sink_crop->left = 0;
+	sink_crop->top = 0;
+
+	src_fmt = v4l2_subdev_get_try_format(sd, cfg,
+					     RKISP1_ISP_PAD_SOURCE_VIDEO);
+	*src_fmt = *sink_fmt;
+	src_fmt->code = RKISP1_DEF_SRC_PAD_FMT;
+	src_fmt->quantization = V4L2_QUANTIZATION_FULL_RANGE;
+
+	src_crop = v4l2_subdev_get_try_crop(sd, cfg,
+					    RKISP1_ISP_PAD_SOURCE_VIDEO);
+	*src_crop = *sink_crop;
+
+	sink_fmt = v4l2_subdev_get_try_format(sd, cfg,
+					      RKISP1_ISP_PAD_SINK_PARAMS);
+	src_fmt = v4l2_subdev_get_try_format(sd, cfg,
+					     RKISP1_ISP_PAD_SOURCE_STATS);
+	sink_fmt->width = RKISP1_DEFAULT_WIDTH;
+	sink_fmt->height = RKISP1_DEFAULT_HEIGHT;
+	sink_fmt->field = V4L2_FIELD_NONE;
+	sink_fmt->code = MEDIA_BUS_FMT_FIXED;
+	*src_fmt = *sink_fmt;
+
+	return 0;
+}
+
+static void rkisp1_isp_set_src_fmt(struct rkisp1_isp *isp,
+				   struct v4l2_subdev_pad_config *cfg,
+				   struct v4l2_mbus_framefmt *format,
+				   unsigned int which)
+{
+	const struct rkisp1_isp_mbus_info *mbus_info;
+	struct v4l2_mbus_framefmt *src_fmt;
+	const struct v4l2_rect *src_crop;
+
+	src_fmt = rkisp1_isp_get_pad_fmt(isp, cfg,
+					 RKISP1_ISP_PAD_SOURCE_VIDEO, which);
+	src_crop = rkisp1_isp_get_pad_crop(isp, cfg,
+					   RKISP1_ISP_PAD_SOURCE_VIDEO, which);
+
+	src_fmt->code = format->code;
+	mbus_info = rkisp1_isp_mbus_info_get(src_fmt->code);
+	if (!mbus_info) {
+		src_fmt->code = RKISP1_DEF_SRC_PAD_FMT;
+		mbus_info = rkisp1_isp_mbus_info_get(src_fmt->code);
+	}
+	if (which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		isp->src_fmt = mbus_info;
+	src_fmt->width  = src_crop->width;
+	src_fmt->height = src_crop->height;
+	src_fmt->quantization = format->quantization;
+	/* full range by default */
+	if (!src_fmt->quantization)
+		src_fmt->quantization = V4L2_QUANTIZATION_FULL_RANGE;
+
+	*format = *src_fmt;
+}
+
+static void rkisp1_isp_set_src_crop(struct rkisp1_isp *isp,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_rect *r, unsigned int which)
+{
+	struct v4l2_mbus_framefmt *src_fmt;
+	const struct v4l2_rect *sink_crop;
+	struct v4l2_rect *src_crop;
+
+	src_crop = rkisp1_isp_get_pad_crop(isp, cfg,
+					   RKISP1_ISP_PAD_SOURCE_VIDEO,
+					   which);
+	sink_crop = rkisp1_isp_get_pad_crop(isp, cfg,
+					    RKISP1_ISP_PAD_SINK_VIDEO,
+					    which);
+
+	src_crop->left = ALIGN(r->left, 2);
+	src_crop->width = ALIGN(r->width, 2);
+	src_crop->top = r->top;
+	src_crop->height = r->height;
+	rkisp1_sd_adjust_crop_rect(src_crop, sink_crop);
+
+	*r = *src_crop;
+
+	/* Propagate to out format */
+	src_fmt = rkisp1_isp_get_pad_fmt(isp, cfg,
+					 RKISP1_ISP_PAD_SOURCE_VIDEO, which);
+	rkisp1_isp_set_src_fmt(isp, cfg, src_fmt, which);
+}
+
+static void rkisp1_isp_set_sink_crop(struct rkisp1_isp *isp,
+				     struct v4l2_subdev_pad_config *cfg,
+				     struct v4l2_rect *r, unsigned int which)
+{
+	struct v4l2_rect *sink_crop, *src_crop;
+	struct v4l2_mbus_framefmt *sink_fmt;
+
+	sink_crop = rkisp1_isp_get_pad_crop(isp, cfg, RKISP1_ISP_PAD_SINK_VIDEO,
+					    which);
+	sink_fmt = rkisp1_isp_get_pad_fmt(isp, cfg, RKISP1_ISP_PAD_SINK_VIDEO,
+					  which);
+
+	sink_crop->left = ALIGN(r->left, 2);
+	sink_crop->width = ALIGN(r->width, 2);
+	sink_crop->top = r->top;
+	sink_crop->height = r->height;
+	rkisp1_sd_adjust_crop(sink_crop, sink_fmt);
+
+	*r = *sink_crop;
+
+	/* Propagate to out crop */
+	src_crop = rkisp1_isp_get_pad_crop(isp, cfg,
+					   RKISP1_ISP_PAD_SOURCE_VIDEO, which);
+	rkisp1_isp_set_src_crop(isp, cfg, src_crop, which);
+}
+
+static void rkisp1_isp_set_sink_fmt(struct rkisp1_isp *isp,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_mbus_framefmt *format,
+				    unsigned int which)
+{
+	const struct rkisp1_isp_mbus_info *mbus_info;
+	struct v4l2_mbus_framefmt *sink_fmt;
+	struct v4l2_rect *sink_crop;
+
+	sink_fmt = rkisp1_isp_get_pad_fmt(isp, cfg, RKISP1_ISP_PAD_SINK_VIDEO,
+					  which);
+	sink_fmt->code = format->code;
+	mbus_info = rkisp1_isp_mbus_info_get(sink_fmt->code);
+	if (!mbus_info) {
+		sink_fmt->code = RKISP1_DEF_SINK_PAD_FMT;
+		mbus_info = rkisp1_isp_mbus_info_get(sink_fmt->code);
+	}
+	if (which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		isp->sink_fmt = mbus_info;
+
+	sink_fmt->width = clamp_t(u32, format->width,
+				  RKISP1_ISP_MIN_WIDTH,
+				  RKISP1_ISP_MAX_WIDTH);
+	sink_fmt->height = clamp_t(u32, format->height,
+				   RKISP1_ISP_MIN_HEIGHT,
+				   RKISP1_ISP_MAX_HEIGHT);
+
+	*format = *sink_fmt;
+
+	/* Propagate to in crop */
+	sink_crop = rkisp1_isp_get_pad_crop(isp, cfg, RKISP1_ISP_PAD_SINK_VIDEO,
+					    which);
+	rkisp1_isp_set_sink_crop(isp, cfg, sink_crop, which);
+}
+
+static int rkisp1_isp_get_fmt(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *fmt)
+{
+	struct rkisp1_isp *isp = container_of(sd, struct rkisp1_isp, sd);
+
+	fmt->format = *rkisp1_isp_get_pad_fmt(isp, cfg, fmt->pad, fmt->which);
+	return 0;
+}
+
+static int rkisp1_isp_set_fmt(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *fmt)
+{
+	struct rkisp1_isp *isp = container_of(sd, struct rkisp1_isp, sd);
+
+	if (fmt->pad == RKISP1_ISP_PAD_SINK_VIDEO)
+		rkisp1_isp_set_sink_fmt(isp, cfg, &fmt->format, fmt->which);
+	else if (fmt->pad == RKISP1_ISP_PAD_SOURCE_VIDEO)
+		rkisp1_isp_set_src_fmt(isp, cfg, &fmt->format, fmt->which);
+	else
+		fmt->format = *rkisp1_isp_get_pad_fmt(isp, cfg, fmt->pad,
+						      fmt->which);
+
+	return 0;
+}
+
+static int rkisp1_isp_get_selection(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_subdev_selection *sel)
+{
+	struct rkisp1_isp *isp = container_of(sd, struct rkisp1_isp, sd);
+
+	if (sel->pad != RKISP1_ISP_PAD_SOURCE_VIDEO &&
+	    sel->pad != RKISP1_ISP_PAD_SINK_VIDEO)
+		return -EINVAL;
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		if (sel->pad == RKISP1_ISP_PAD_SINK_VIDEO) {
+			struct v4l2_mbus_framefmt *fmt;
+
+			fmt = rkisp1_isp_get_pad_fmt(isp, cfg, sel->pad,
+						     sel->which);
+			sel->r.height = fmt->height;
+			sel->r.width = fmt->width;
+			sel->r.left = 0;
+			sel->r.top = 0;
+		} else {
+			sel->r = *rkisp1_isp_get_pad_crop(isp, cfg,
+						RKISP1_ISP_PAD_SINK_VIDEO,
+						sel->which);
+		}
+		break;
+	case V4L2_SEL_TGT_CROP:
+		sel->r = *rkisp1_isp_get_pad_crop(isp, cfg, sel->pad,
+						  sel->which);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rkisp1_isp_set_selection(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_subdev_selection *sel)
+{
+	struct rkisp1_device *rkisp1 =
+		container_of(sd->v4l2_dev, struct rkisp1_device, v4l2_dev);
+	struct rkisp1_isp *isp = container_of(sd, struct rkisp1_isp, sd);
+
+	if (sel->target != V4L2_SEL_TGT_CROP)
+		return -EINVAL;
+
+	dev_dbg(rkisp1->dev, "%s: pad: %d sel(%d,%d)/%dx%d\n", __func__,
+		sel->pad, sel->r.left, sel->r.top, sel->r.width, sel->r.height);
+
+	if (sel->pad == RKISP1_ISP_PAD_SINK_VIDEO)
+		rkisp1_isp_set_sink_crop(isp, cfg, &sel->r, sel->which);
+	else if (sel->pad == RKISP1_ISP_PAD_SOURCE_VIDEO)
+		rkisp1_isp_set_src_crop(isp, cfg, &sel->r, sel->which);
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int rkisp1_subdev_link_validate(struct media_link *link)
+{
+	if (link->sink->index == RKISP1_ISP_PAD_SINK_PARAMS)
+		return 0;
+
+	return v4l2_subdev_link_validate(link);
+}
+
+static const struct v4l2_subdev_pad_ops rkisp1_isp_pad_ops = {
+	.enum_mbus_code = rkisp1_isp_enum_mbus_code,
+	.get_selection = rkisp1_isp_get_selection,
+	.set_selection = rkisp1_isp_set_selection,
+	.init_cfg = rkisp1_isp_init_config,
+	.get_fmt = rkisp1_isp_get_fmt,
+	.set_fmt = rkisp1_isp_set_fmt,
+	.link_validate = v4l2_subdev_link_validate_default,
+};
+
+/* ----------------------------------------------------------------------------
+ * Stream operations
+ */
+
+static int rkisp1_mipi_csi2_start(struct rkisp1_isp *isp,
+				  struct rkisp1_sensor_async *sensor)
+{
+	union phy_configure_opts opts;
+	struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy;
+	s64 pixel_clock;
+
+	if (!sensor->pixel_rate_ctrl) {
+		dev_warn(sensor->sd->dev, "No pixel rate control in subdev\n");
+		return -EPIPE;
+	}
+
+	pixel_clock = v4l2_ctrl_g_ctrl_int64(sensor->pixel_rate_ctrl);
+	if (!pixel_clock) {
+		dev_err(sensor->sd->dev, "Invalid pixel rate value\n");
+		return -EINVAL;
+	}
+
+	phy_mipi_dphy_get_default_config(pixel_clock, isp->sink_fmt->bus_width,
+					 sensor->lanes, cfg);
+	phy_set_mode(sensor->dphy, PHY_MODE_MIPI_DPHY);
+	phy_configure(sensor->dphy, &opts);
+	phy_power_on(sensor->dphy);
+
+	return 0;
+}
+
+static void rkisp1_mipi_csi2_stop(struct rkisp1_sensor_async *sensor)
+{
+	phy_power_off(sensor->dphy);
+}
+
+static int rkisp1_isp_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct rkisp1_device *rkisp1 =
+		container_of(sd->v4l2_dev, struct rkisp1_device, v4l2_dev);
+	struct v4l2_subdev *sensor_sd;
+	int ret = 0;
+
+	if (!enable) {
+		ret = rkisp1_isp_stop(rkisp1);
+		if (ret)
+			return ret;
+		rkisp1_mipi_csi2_stop(rkisp1->active_sensor);
+		return 0;
+	}
+
+	sensor_sd = rkisp1_get_remote_sensor(sd);
+	if (!sensor_sd)
+		return -ENODEV;
+	rkisp1->active_sensor = container_of(sensor_sd->asd,
+					     struct rkisp1_sensor_async, asd);
+
+	atomic_set(&rkisp1->isp.frame_sequence, -1);
+	ret = rkisp1_config_cif(rkisp1);
+	if (ret)
+		return ret;
+
+	if (rkisp1->active_sensor->mbus.type != V4L2_MBUS_CSI2_DPHY)
+		return -EINVAL;
+
+	ret = rkisp1_mipi_csi2_start(&rkisp1->isp, rkisp1->active_sensor);
+	if (ret)
+		return ret;
+
+	ret = rkisp1_isp_start(rkisp1);
+	if (ret)
+		rkisp1_mipi_csi2_stop(rkisp1->active_sensor);
+
+	return ret;
+}
+
+static int rkisp1_isp_subs_evt(struct v4l2_subdev *sd, struct v4l2_fh *fh,
+			       struct v4l2_event_subscription *sub)
+{
+	if (sub->type != V4L2_EVENT_FRAME_SYNC)
+		return -EINVAL;
+
+	/* V4L2_EVENT_FRAME_SYNC doesn't require an id, so zero should be set */
+	if (sub->id != 0)
+		return -EINVAL;
+
+	return v4l2_event_subscribe(fh, sub, 0, NULL);
+}
+
+static const struct media_entity_operations rkisp1_isp_media_ops = {
+	.link_validate = rkisp1_subdev_link_validate,
+};
+
+static const struct v4l2_subdev_video_ops rkisp1_isp_video_ops = {
+	.s_stream = rkisp1_isp_s_stream,
+};
+
+static const struct v4l2_subdev_core_ops rkisp1_isp_core_ops = {
+	.subscribe_event = rkisp1_isp_subs_evt,
+	.unsubscribe_event = v4l2_event_subdev_unsubscribe,
+};
+
+static const struct v4l2_subdev_ops rkisp1_isp_ops = {
+	.core = &rkisp1_isp_core_ops,
+	.video = &rkisp1_isp_video_ops,
+	.pad = &rkisp1_isp_pad_ops,
+};
+
+int rkisp1_isp_register(struct rkisp1_device *rkisp1,
+			struct v4l2_device *v4l2_dev)
+{
+	struct rkisp1_isp *isp = &rkisp1->isp;
+	struct media_pad *pads = isp->pads;
+	struct v4l2_subdev *sd = &isp->sd;
+	int ret;
+
+	v4l2_subdev_init(sd, &rkisp1_isp_ops);
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
+	sd->entity.ops = &rkisp1_isp_media_ops;
+	sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER;
+	sd->owner = THIS_MODULE;
+	strscpy(sd->name, RKISP1_ISP_DEV_NAME, sizeof(sd->name));
+
+	pads[RKISP1_ISP_PAD_SINK_VIDEO].flags = MEDIA_PAD_FL_SINK |
+						MEDIA_PAD_FL_MUST_CONNECT;
+	pads[RKISP1_ISP_PAD_SINK_PARAMS].flags = MEDIA_PAD_FL_SINK;
+	pads[RKISP1_ISP_PAD_SOURCE_VIDEO].flags = MEDIA_PAD_FL_SOURCE;
+	pads[RKISP1_ISP_PAD_SOURCE_STATS].flags = MEDIA_PAD_FL_SOURCE;
+
+	isp->sink_fmt = rkisp1_isp_mbus_info_get(RKISP1_DEF_SINK_PAD_FMT);
+	isp->src_fmt = rkisp1_isp_mbus_info_get(RKISP1_DEF_SRC_PAD_FMT);
+
+	ret = media_entity_pads_init(&sd->entity, RKISP1_ISP_PAD_MAX, pads);
+	if (ret)
+		return ret;
+
+	ret = v4l2_device_register_subdev(v4l2_dev, sd);
+	if (ret) {
+		dev_err(sd->dev, "Failed to register isp subdev\n");
+		goto err_cleanup_media_entity;
+	}
+
+	rkisp1_isp_init_config(sd, rkisp1->isp.pad_cfg);
+	return 0;
+
+err_cleanup_media_entity:
+	media_entity_cleanup(&sd->entity);
+
+	return ret;
+}
+
+void rkisp1_isp_unregister(struct rkisp1_device *rkisp1)
+{
+	struct v4l2_subdev *sd = &rkisp1->isp.sd;
+
+	v4l2_device_unregister_subdev(sd);
+	media_entity_cleanup(&sd->entity);
+}
+
+/* ----------------------------------------------------------------------------
+ * Interrupt handlers
+ */
+
+void rkisp1_mipi_isr(struct rkisp1_device *rkisp1)
+{
+	u32 val, status;
+
+	status = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_MIS);
+	if (!status)
+		return;
+
+	rkisp1_write(rkisp1, status, RKISP1_CIF_MIPI_ICR);
+
+	/*
+	 * Disable DPHY errctrl interrupt, because this dphy
+	 * erctrl signal is asserted until the next changes
+	 * of line state. This time is may be too long and cpu
+	 * is hold in this interrupt.
+	 */
+	if (status & RKISP1_CIF_MIPI_ERR_CTRL(0x0f)) {
+		val = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_IMSC);
+		rkisp1_write(rkisp1, val & ~RKISP1_CIF_MIPI_ERR_CTRL(0x0f),
+			     RKISP1_CIF_MIPI_IMSC);
+		rkisp1->isp.is_dphy_errctrl_disabled = true;
+	}
+
+	/*
+	 * Enable DPHY errctrl interrupt again, if mipi have receive
+	 * the whole frame without any error.
+	 */
+	if (status == RKISP1_CIF_MIPI_FRAME_END) {
+		/*
+		 * Enable DPHY errctrl interrupt again, if mipi have receive
+		 * the whole frame without any error.
+		 */
+		if (rkisp1->isp.is_dphy_errctrl_disabled) {
+			val = rkisp1_read(rkisp1, RKISP1_CIF_MIPI_IMSC);
+			val |= RKISP1_CIF_MIPI_ERR_CTRL(0x0f);
+			rkisp1_write(rkisp1, val, RKISP1_CIF_MIPI_IMSC);
+			rkisp1->isp.is_dphy_errctrl_disabled = false;
+		}
+	} else {
+		rkisp1->debug.mipi_error++;
+	}
+}
+
+static void rkisp1_isp_queue_event_sof(struct rkisp1_isp *isp)
+{
+	struct v4l2_event event = {
+		.type = V4L2_EVENT_FRAME_SYNC,
+	};
+
+	/*
+	 * Increment the frame sequence on the vsync signal.
+	 * This will allow applications to detect dropped.
+	 * Note that there is a debugfs counter for dropped
+	 * frames, but using this event is more accurate.
+	 */
+	event.u.frame_sync.frame_sequence =
+		atomic_inc_return(&isp->frame_sequence);
+	v4l2_event_queue(isp->sd.devnode, &event);
+}
+
+void rkisp1_isp_isr(struct rkisp1_device *rkisp1)
+{
+	u32 status, isp_err;
+
+	status = rkisp1_read(rkisp1, RKISP1_CIF_ISP_MIS);
+	if (!status)
+		return;
+
+	rkisp1_write(rkisp1, status, RKISP1_CIF_ISP_ICR);
+
+	/* Vertical sync signal, starting generating new frame */
+	if (status & RKISP1_CIF_ISP_V_START)
+		rkisp1_isp_queue_event_sof(&rkisp1->isp);
+
+	if (status & RKISP1_CIF_ISP_PIC_SIZE_ERROR) {
+		/* Clear pic_size_error */
+		isp_err = rkisp1_read(rkisp1, RKISP1_CIF_ISP_ERR);
+		rkisp1_write(rkisp1, isp_err, RKISP1_CIF_ISP_ERR_CLR);
+		rkisp1->debug.pic_size_error++;
+	} else if (status & RKISP1_CIF_ISP_DATA_LOSS) {
+		/* keep track of data_loss in debugfs */
+		rkisp1->debug.data_loss++;
+	}
+
+	if (status & RKISP1_CIF_ISP_FRAME) {
+		u32 isp_ris;
+
+		/* New frame from the sensor received */
+		isp_ris = rkisp1_read(rkisp1, RKISP1_CIF_ISP_RIS);
+		if (isp_ris & (RKISP1_CIF_ISP_AWB_DONE |
+			       RKISP1_CIF_ISP_AFM_FIN |
+			       RKISP1_CIF_ISP_EXP_END |
+			       RKISP1_CIF_ISP_HIST_MEASURE_RDY))
+			rkisp1_stats_isr(&rkisp1->stats, isp_ris);
+	}
+
+	/*
+	 * Then update changed configs. Some of them involve
+	 * lot of register writes. Do those only one per frame.
+	 * Do the updates in the order of the processing flow.
+	 */
+	rkisp1_params_isr(rkisp1, status);
+}
diff --git a/drivers/staging/media/rkisp1/rkisp1-params.c b/drivers/staging/media/rkisp1/rkisp1-params.c
new file mode 100644
index 000000000000..781f0ca85af1
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-params.c
@@ -0,0 +1,1630 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - Params subdevice
+ *
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-vmalloc.h>	/* for ISP params */
+
+#include "rkisp1-common.h"
+
+#define RKISP1_PARAMS_DEV_NAME	RKISP1_DRIVER_NAME "_params"
+
+#define RKISP1_ISP_PARAMS_REQ_BUFS_MIN	2
+#define RKISP1_ISP_PARAMS_REQ_BUFS_MAX	8
+
+#define RKISP1_ISP_DPCC_LINE_THRESH(n) \
+			(RKISP1_CIF_ISP_DPCC_LINE_THRESH_1 + 0x14 * (n))
+#define RKISP1_ISP_DPCC_LINE_MAD_FAC(n) \
+			(RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_1 + 0x14 * (n))
+#define RKISP1_ISP_DPCC_PG_FAC(n) \
+			(RKISP1_CIF_ISP_DPCC_PG_FAC_1 + 0x14 * (n))
+#define RKISP1_ISP_DPCC_RND_THRESH(n) \
+			(RKISP1_CIF_ISP_DPCC_RND_THRESH_1 + 0x14 * (n))
+#define RKISP1_ISP_DPCC_RG_FAC(n) \
+			(RKISP1_CIF_ISP_DPCC_RG_FAC_1 + 0x14 * (n))
+#define RKISP1_ISP_CC_COEFF(n) \
+			(RKISP1_CIF_ISP_CC_COEFF_0 + (n) * 4)
+
+static inline void
+rkisp1_param_set_bits(struct rkisp1_params *params, u32 reg, u32 bit_mask)
+{
+	u32 val;
+
+	val = rkisp1_read(params->rkisp1, reg);
+	rkisp1_write(params->rkisp1, val | bit_mask, reg);
+}
+
+static inline void
+rkisp1_param_clear_bits(struct rkisp1_params *params, u32 reg, u32 bit_mask)
+{
+	u32 val;
+
+	val = rkisp1_read(params->rkisp1, reg);
+	rkisp1_write(params->rkisp1, val & ~bit_mask, reg);
+}
+
+/* ISP BP interface function */
+static void rkisp1_dpcc_config(struct rkisp1_params *params,
+			       const struct rkisp1_cif_isp_dpcc_config *arg)
+{
+	unsigned int i;
+	u32 mode;
+
+	/* avoid to override the old enable value */
+	mode = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_DPCC_MODE);
+	mode &= RKISP1_CIF_ISP_DPCC_ENA;
+	mode |= arg->mode & ~RKISP1_CIF_ISP_DPCC_ENA;
+	rkisp1_write(params->rkisp1, mode, RKISP1_CIF_ISP_DPCC_MODE);
+	rkisp1_write(params->rkisp1, arg->output_mode,
+		     RKISP1_CIF_ISP_DPCC_OUTPUT_MODE);
+	rkisp1_write(params->rkisp1, arg->set_use,
+		     RKISP1_CIF_ISP_DPCC_SET_USE);
+
+	rkisp1_write(params->rkisp1, arg->methods[0].method,
+		     RKISP1_CIF_ISP_DPCC_METHODS_SET_1);
+	rkisp1_write(params->rkisp1, arg->methods[1].method,
+		     RKISP1_CIF_ISP_DPCC_METHODS_SET_2);
+	rkisp1_write(params->rkisp1, arg->methods[2].method,
+		     RKISP1_CIF_ISP_DPCC_METHODS_SET_3);
+	for (i = 0; i < RKISP1_CIF_ISP_DPCC_METHODS_MAX; i++) {
+		rkisp1_write(params->rkisp1, arg->methods[i].line_thresh,
+			     RKISP1_ISP_DPCC_LINE_THRESH(i));
+		rkisp1_write(params->rkisp1, arg->methods[i].line_mad_fac,
+			     RKISP1_ISP_DPCC_LINE_MAD_FAC(i));
+		rkisp1_write(params->rkisp1, arg->methods[i].pg_fac,
+			     RKISP1_ISP_DPCC_PG_FAC(i));
+		rkisp1_write(params->rkisp1, arg->methods[i].rnd_thresh,
+			     RKISP1_ISP_DPCC_RND_THRESH(i));
+		rkisp1_write(params->rkisp1, arg->methods[i].rg_fac,
+			     RKISP1_ISP_DPCC_RG_FAC(i));
+	}
+
+	rkisp1_write(params->rkisp1, arg->rnd_offs,
+		     RKISP1_CIF_ISP_DPCC_RND_OFFS);
+	rkisp1_write(params->rkisp1, arg->ro_limits,
+		     RKISP1_CIF_ISP_DPCC_RO_LIMITS);
+}
+
+/* ISP black level subtraction interface function */
+static void rkisp1_bls_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_bls_config *arg)
+{
+	/* avoid to override the old enable value */
+	u32 new_control;
+
+	new_control = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_BLS_CTRL);
+	new_control &= RKISP1_CIF_ISP_BLS_ENA;
+	/* fixed subtraction values */
+	if (!arg->enable_auto) {
+		const struct rkisp1_cif_isp_bls_fixed_val *pval =
+								&arg->fixed_val;
+
+		switch (params->raw_type) {
+		case RKISP1_RAW_BGGR:
+			rkisp1_write(params->rkisp1,
+				     pval->r, RKISP1_CIF_ISP_BLS_D_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gr, RKISP1_CIF_ISP_BLS_C_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gb, RKISP1_CIF_ISP_BLS_B_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->b, RKISP1_CIF_ISP_BLS_A_FIXED);
+			break;
+		case RKISP1_RAW_GBRG:
+			rkisp1_write(params->rkisp1,
+				     pval->r, RKISP1_CIF_ISP_BLS_C_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gr, RKISP1_CIF_ISP_BLS_D_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gb, RKISP1_CIF_ISP_BLS_A_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->b, RKISP1_CIF_ISP_BLS_B_FIXED);
+			break;
+		case RKISP1_RAW_GRBG:
+			rkisp1_write(params->rkisp1,
+				     pval->r, RKISP1_CIF_ISP_BLS_B_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gr, RKISP1_CIF_ISP_BLS_A_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gb, RKISP1_CIF_ISP_BLS_D_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->b, RKISP1_CIF_ISP_BLS_C_FIXED);
+			break;
+		case RKISP1_RAW_RGGB:
+			rkisp1_write(params->rkisp1,
+				     pval->r, RKISP1_CIF_ISP_BLS_A_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gr, RKISP1_CIF_ISP_BLS_B_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->gb, RKISP1_CIF_ISP_BLS_C_FIXED);
+			rkisp1_write(params->rkisp1,
+				     pval->b, RKISP1_CIF_ISP_BLS_D_FIXED);
+			break;
+		default:
+			break;
+		}
+
+	} else {
+		if (arg->en_windows & BIT(1)) {
+			rkisp1_write(params->rkisp1, arg->bls_window2.h_offs,
+				     RKISP1_CIF_ISP_BLS_H2_START);
+			rkisp1_write(params->rkisp1, arg->bls_window2.h_size,
+				     RKISP1_CIF_ISP_BLS_H2_STOP);
+			rkisp1_write(params->rkisp1, arg->bls_window2.v_offs,
+				     RKISP1_CIF_ISP_BLS_V2_START);
+			rkisp1_write(params->rkisp1, arg->bls_window2.v_size,
+				     RKISP1_CIF_ISP_BLS_V2_STOP);
+			new_control |= RKISP1_CIF_ISP_BLS_WINDOW_2;
+		}
+
+		if (arg->en_windows & BIT(0)) {
+			rkisp1_write(params->rkisp1, arg->bls_window1.h_offs,
+				     RKISP1_CIF_ISP_BLS_H1_START);
+			rkisp1_write(params->rkisp1, arg->bls_window1.h_size,
+				     RKISP1_CIF_ISP_BLS_H1_STOP);
+			rkisp1_write(params->rkisp1, arg->bls_window1.v_offs,
+				     RKISP1_CIF_ISP_BLS_V1_START);
+			rkisp1_write(params->rkisp1, arg->bls_window1.v_size,
+				     RKISP1_CIF_ISP_BLS_V1_STOP);
+			new_control |= RKISP1_CIF_ISP_BLS_WINDOW_1;
+		}
+
+		rkisp1_write(params->rkisp1, arg->bls_samples,
+			     RKISP1_CIF_ISP_BLS_SAMPLES);
+
+		new_control |= RKISP1_CIF_ISP_BLS_MODE_MEASURED;
+	}
+	rkisp1_write(params->rkisp1, new_control, RKISP1_CIF_ISP_BLS_CTRL);
+}
+
+/* ISP LS correction interface function */
+static void
+rkisp1_lsc_correct_matrix_config(struct rkisp1_params *params,
+				const struct rkisp1_cif_isp_lsc_config *pconfig)
+{
+	unsigned int isp_lsc_status, sram_addr, isp_lsc_table_sel, i, j, data;
+
+	isp_lsc_status = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_LSC_STATUS);
+
+	/* RKISP1_CIF_ISP_LSC_TABLE_ADDRESS_153 = ( 17 * 18 ) >> 1 */
+	sram_addr = (isp_lsc_status & RKISP1_CIF_ISP_LSC_ACTIVE_TABLE) ?
+		    RKISP1_CIF_ISP_LSC_TABLE_ADDRESS_0 :
+		    RKISP1_CIF_ISP_LSC_TABLE_ADDRESS_153;
+	rkisp1_write(params->rkisp1, sram_addr,
+		     RKISP1_CIF_ISP_LSC_R_TABLE_ADDR);
+	rkisp1_write(params->rkisp1, sram_addr,
+		     RKISP1_CIF_ISP_LSC_GR_TABLE_ADDR);
+	rkisp1_write(params->rkisp1, sram_addr,
+		     RKISP1_CIF_ISP_LSC_GB_TABLE_ADDR);
+	rkisp1_write(params->rkisp1, sram_addr,
+		     RKISP1_CIF_ISP_LSC_B_TABLE_ADDR);
+
+	/* program data tables (table size is 9 * 17 = 153) */
+	for (i = 0;
+	     i < RKISP1_CIF_ISP_LSC_SECTORS_MAX * RKISP1_CIF_ISP_LSC_SECTORS_MAX;
+	     i += RKISP1_CIF_ISP_LSC_SECTORS_MAX) {
+		/*
+		 * 17 sectors with 2 values in one DWORD = 9
+		 * DWORDs (2nd value of last DWORD unused)
+		 */
+		for (j = 0; j < RKISP1_CIF_ISP_LSC_SECTORS_MAX - 1; j += 2) {
+			data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->r_data_tbl[i + j],
+							     pconfig->r_data_tbl[i + j + 1]);
+			rkisp1_write(params->rkisp1, data,
+				     RKISP1_CIF_ISP_LSC_R_TABLE_DATA);
+
+			data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->gr_data_tbl[i + j],
+							     pconfig->gr_data_tbl[i + j + 1]);
+			rkisp1_write(params->rkisp1, data,
+				     RKISP1_CIF_ISP_LSC_GR_TABLE_DATA);
+
+			data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->gb_data_tbl[i + j],
+							     pconfig->gb_data_tbl[i + j + 1]);
+			rkisp1_write(params->rkisp1, data,
+				     RKISP1_CIF_ISP_LSC_GB_TABLE_DATA);
+
+			data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->b_data_tbl[i + j],
+							     pconfig->b_data_tbl[i + j + 1]);
+			rkisp1_write(params->rkisp1, data,
+				     RKISP1_CIF_ISP_LSC_B_TABLE_DATA);
+		}
+		data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->r_data_tbl[i + j], 0);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_R_TABLE_DATA);
+
+		data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->gr_data_tbl[i + j], 0);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_GR_TABLE_DATA);
+
+		data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->gb_data_tbl[i + j], 0);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_GB_TABLE_DATA);
+
+		data = RKISP1_CIF_ISP_LSC_TABLE_DATA(pconfig->b_data_tbl[i + j], 0);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_B_TABLE_DATA);
+	}
+	isp_lsc_table_sel = (isp_lsc_status & RKISP1_CIF_ISP_LSC_ACTIVE_TABLE) ?
+			    RKISP1_CIF_ISP_LSC_TABLE_0 :
+			    RKISP1_CIF_ISP_LSC_TABLE_1;
+	rkisp1_write(params->rkisp1, isp_lsc_table_sel,
+		     RKISP1_CIF_ISP_LSC_TABLE_SEL);
+}
+
+static void rkisp1_lsc_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_lsc_config *arg)
+{
+	unsigned int i, data;
+	u32 lsc_ctrl;
+
+	/* To config must be off , store the current status firstly */
+	lsc_ctrl = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_LSC_CTRL);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_LSC_CTRL,
+				RKISP1_CIF_ISP_LSC_CTRL_ENA);
+	rkisp1_lsc_correct_matrix_config(params, arg);
+
+	for (i = 0; i < 4; i++) {
+		/* program x size tables */
+		data = RKISP1_CIF_ISP_LSC_SECT_SIZE(arg->x_size_tbl[i * 2],
+						    arg->x_size_tbl[i * 2 + 1]);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_XSIZE_01 + i * 4);
+
+		/* program x grad tables */
+		data = RKISP1_CIF_ISP_LSC_SECT_SIZE(arg->x_grad_tbl[i * 2],
+						    arg->x_grad_tbl[i * 2 + 1]);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_XGRAD_01 + i * 4);
+
+		/* program y size tables */
+		data = RKISP1_CIF_ISP_LSC_SECT_SIZE(arg->y_size_tbl[i * 2],
+						    arg->y_size_tbl[i * 2 + 1]);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_YSIZE_01 + i * 4);
+
+		/* program y grad tables */
+		data = RKISP1_CIF_ISP_LSC_SECT_SIZE(arg->y_grad_tbl[i * 2],
+						    arg->y_grad_tbl[i * 2 + 1]);
+		rkisp1_write(params->rkisp1, data,
+			     RKISP1_CIF_ISP_LSC_YGRAD_01 + i * 4);
+	}
+
+	/* restore the lsc ctrl status */
+	if (lsc_ctrl & RKISP1_CIF_ISP_LSC_CTRL_ENA) {
+		rkisp1_param_set_bits(params,
+				      RKISP1_CIF_ISP_LSC_CTRL,
+				      RKISP1_CIF_ISP_LSC_CTRL_ENA);
+	} else {
+		rkisp1_param_clear_bits(params,
+					RKISP1_CIF_ISP_LSC_CTRL,
+					RKISP1_CIF_ISP_LSC_CTRL_ENA);
+	}
+}
+
+/* ISP Filtering function */
+static void rkisp1_flt_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_flt_config *arg)
+{
+	u32 filt_mode;
+
+	rkisp1_write(params->rkisp1,
+		     arg->thresh_bl0, RKISP1_CIF_ISP_FILT_THRESH_BL0);
+	rkisp1_write(params->rkisp1,
+		     arg->thresh_bl1, RKISP1_CIF_ISP_FILT_THRESH_BL1);
+	rkisp1_write(params->rkisp1,
+		     arg->thresh_sh0, RKISP1_CIF_ISP_FILT_THRESH_SH0);
+	rkisp1_write(params->rkisp1,
+		     arg->thresh_sh1, RKISP1_CIF_ISP_FILT_THRESH_SH1);
+	rkisp1_write(params->rkisp1, arg->fac_bl0, RKISP1_CIF_ISP_FILT_FAC_BL0);
+	rkisp1_write(params->rkisp1, arg->fac_bl1, RKISP1_CIF_ISP_FILT_FAC_BL1);
+	rkisp1_write(params->rkisp1, arg->fac_mid, RKISP1_CIF_ISP_FILT_FAC_MID);
+	rkisp1_write(params->rkisp1, arg->fac_sh0, RKISP1_CIF_ISP_FILT_FAC_SH0);
+	rkisp1_write(params->rkisp1, arg->fac_sh1, RKISP1_CIF_ISP_FILT_FAC_SH1);
+	rkisp1_write(params->rkisp1,
+		     arg->lum_weight, RKISP1_CIF_ISP_FILT_LUM_WEIGHT);
+
+	rkisp1_write(params->rkisp1,
+		     (arg->mode ? RKISP1_CIF_ISP_FLT_MODE_DNR : 0) |
+		     RKISP1_CIF_ISP_FLT_CHROMA_V_MODE(arg->chr_v_mode) |
+		     RKISP1_CIF_ISP_FLT_CHROMA_H_MODE(arg->chr_h_mode) |
+		     RKISP1_CIF_ISP_FLT_GREEN_STAGE1(arg->grn_stage1),
+		     RKISP1_CIF_ISP_FILT_MODE);
+
+	/* avoid to override the old enable value */
+	filt_mode = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_FILT_MODE);
+	filt_mode &= RKISP1_CIF_ISP_FLT_ENA;
+	if (arg->mode)
+		filt_mode |= RKISP1_CIF_ISP_FLT_MODE_DNR;
+	filt_mode |= RKISP1_CIF_ISP_FLT_CHROMA_V_MODE(arg->chr_v_mode) |
+		     RKISP1_CIF_ISP_FLT_CHROMA_H_MODE(arg->chr_h_mode) |
+		     RKISP1_CIF_ISP_FLT_GREEN_STAGE1(arg->grn_stage1);
+	rkisp1_write(params->rkisp1, filt_mode, RKISP1_CIF_ISP_FILT_MODE);
+}
+
+/* ISP demosaic interface function */
+static int rkisp1_bdm_config(struct rkisp1_params *params,
+			     const struct rkisp1_cif_isp_bdm_config *arg)
+{
+	u32 bdm_th;
+
+	/* avoid to override the old enable value */
+	bdm_th = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_DEMOSAIC);
+	bdm_th &= RKISP1_CIF_ISP_DEMOSAIC_BYPASS;
+	bdm_th |= arg->demosaic_th & ~RKISP1_CIF_ISP_DEMOSAIC_BYPASS;
+	/* set demosaic threshold */
+	rkisp1_write(params->rkisp1, bdm_th, RKISP1_CIF_ISP_DEMOSAIC);
+	return 0;
+}
+
+/* ISP GAMMA correction interface function */
+static void rkisp1_sdg_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_sdg_config *arg)
+{
+	unsigned int i;
+
+	rkisp1_write(params->rkisp1,
+		     arg->xa_pnts.gamma_dx0, RKISP1_CIF_ISP_GAMMA_DX_LO);
+	rkisp1_write(params->rkisp1,
+		     arg->xa_pnts.gamma_dx1, RKISP1_CIF_ISP_GAMMA_DX_HI);
+
+	for (i = 0; i < RKISP1_CIF_ISP_DEGAMMA_CURVE_SIZE; i++) {
+		rkisp1_write(params->rkisp1, arg->curve_r.gamma_y[i],
+			     RKISP1_CIF_ISP_GAMMA_R_Y0 + i * 4);
+		rkisp1_write(params->rkisp1, arg->curve_g.gamma_y[i],
+			     RKISP1_CIF_ISP_GAMMA_G_Y0 + i * 4);
+		rkisp1_write(params->rkisp1, arg->curve_b.gamma_y[i],
+			     RKISP1_CIF_ISP_GAMMA_B_Y0 + i * 4);
+	}
+}
+
+/* ISP GAMMA correction interface function */
+static void rkisp1_goc_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_goc_config *arg)
+{
+	unsigned int i;
+
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CTRL,
+				RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA);
+	rkisp1_write(params->rkisp1, arg->mode, RKISP1_CIF_ISP_GAMMA_OUT_MODE);
+
+	for (i = 0; i < RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES; i++)
+		rkisp1_write(params->rkisp1, arg->gamma_y[i],
+			     RKISP1_CIF_ISP_GAMMA_OUT_Y_0 + i * 4);
+}
+
+/* ISP Cross Talk */
+static void rkisp1_ctk_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_ctk_config *arg)
+{
+	rkisp1_write(params->rkisp1, arg->coeff0, RKISP1_CIF_ISP_CT_COEFF_0);
+	rkisp1_write(params->rkisp1, arg->coeff1, RKISP1_CIF_ISP_CT_COEFF_1);
+	rkisp1_write(params->rkisp1, arg->coeff2, RKISP1_CIF_ISP_CT_COEFF_2);
+	rkisp1_write(params->rkisp1, arg->coeff3, RKISP1_CIF_ISP_CT_COEFF_3);
+	rkisp1_write(params->rkisp1, arg->coeff4, RKISP1_CIF_ISP_CT_COEFF_4);
+	rkisp1_write(params->rkisp1, arg->coeff5, RKISP1_CIF_ISP_CT_COEFF_5);
+	rkisp1_write(params->rkisp1, arg->coeff6, RKISP1_CIF_ISP_CT_COEFF_6);
+	rkisp1_write(params->rkisp1, arg->coeff7, RKISP1_CIF_ISP_CT_COEFF_7);
+	rkisp1_write(params->rkisp1, arg->coeff8, RKISP1_CIF_ISP_CT_COEFF_8);
+	rkisp1_write(params->rkisp1, arg->ct_offset_r,
+		     RKISP1_CIF_ISP_CT_OFFSET_R);
+	rkisp1_write(params->rkisp1, arg->ct_offset_g,
+		     RKISP1_CIF_ISP_CT_OFFSET_G);
+	rkisp1_write(params->rkisp1, arg->ct_offset_b,
+		     RKISP1_CIF_ISP_CT_OFFSET_B);
+}
+
+static void rkisp1_ctk_enable(struct rkisp1_params *params, bool en)
+{
+	if (en)
+		return;
+
+	/* Write back the default values. */
+	rkisp1_write(params->rkisp1, 0x80, RKISP1_CIF_ISP_CT_COEFF_0);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_COEFF_1);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_COEFF_2);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_COEFF_3);
+	rkisp1_write(params->rkisp1, 0x80, RKISP1_CIF_ISP_CT_COEFF_4);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_COEFF_5);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_COEFF_6);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_COEFF_7);
+	rkisp1_write(params->rkisp1, 0x80, RKISP1_CIF_ISP_CT_COEFF_8);
+
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_OFFSET_R);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_OFFSET_G);
+	rkisp1_write(params->rkisp1, 0, RKISP1_CIF_ISP_CT_OFFSET_B);
+}
+
+/* ISP White Balance Mode */
+static void rkisp1_awb_meas_config(struct rkisp1_params *params,
+			const struct rkisp1_cif_isp_awb_meas_config *arg)
+{
+	u32 reg_val = 0;
+	/* based on the mode,configure the awb module */
+	if (arg->awb_mode == RKISP1_CIF_ISP_AWB_MODE_YCBCR) {
+		/* Reference Cb and Cr */
+		rkisp1_write(params->rkisp1,
+			     RKISP1_CIF_ISP_AWB_REF_CR_SET(arg->awb_ref_cr) |
+			     arg->awb_ref_cb, RKISP1_CIF_ISP_AWB_REF);
+		/* Yc Threshold */
+		rkisp1_write(params->rkisp1,
+			     RKISP1_CIF_ISP_AWB_MAX_Y_SET(arg->max_y) |
+			     RKISP1_CIF_ISP_AWB_MIN_Y_SET(arg->min_y) |
+			     RKISP1_CIF_ISP_AWB_MAX_CS_SET(arg->max_csum) |
+			     arg->min_c, RKISP1_CIF_ISP_AWB_THRESH);
+	}
+
+	reg_val = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_AWB_PROP);
+	if (arg->enable_ymax_cmp)
+		reg_val |= RKISP1_CIF_ISP_AWB_YMAX_CMP_EN;
+	else
+		reg_val &= ~RKISP1_CIF_ISP_AWB_YMAX_CMP_EN;
+	rkisp1_write(params->rkisp1, reg_val, RKISP1_CIF_ISP_AWB_PROP);
+
+	/* window offset */
+	rkisp1_write(params->rkisp1,
+		     arg->awb_wnd.v_offs, RKISP1_CIF_ISP_AWB_WND_V_OFFS);
+	rkisp1_write(params->rkisp1,
+		     arg->awb_wnd.h_offs, RKISP1_CIF_ISP_AWB_WND_H_OFFS);
+	/* AWB window size */
+	rkisp1_write(params->rkisp1,
+		     arg->awb_wnd.v_size, RKISP1_CIF_ISP_AWB_WND_V_SIZE);
+	rkisp1_write(params->rkisp1,
+		     arg->awb_wnd.h_size, RKISP1_CIF_ISP_AWB_WND_H_SIZE);
+	/* Number of frames */
+	rkisp1_write(params->rkisp1,
+		     arg->frames, RKISP1_CIF_ISP_AWB_FRAMES);
+}
+
+static void
+rkisp1_awb_meas_enable(struct rkisp1_params *params,
+		       const struct rkisp1_cif_isp_awb_meas_config *arg,
+		       bool en)
+{
+	u32 reg_val = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_AWB_PROP);
+
+	/* switch off */
+	reg_val &= RKISP1_CIF_ISP_AWB_MODE_MASK_NONE;
+
+	if (en) {
+		if (arg->awb_mode == RKISP1_CIF_ISP_AWB_MODE_RGB)
+			reg_val |= RKISP1_CIF_ISP_AWB_MODE_RGB_EN;
+		else
+			reg_val |= RKISP1_CIF_ISP_AWB_MODE_YCBCR_EN;
+
+		rkisp1_write(params->rkisp1, reg_val, RKISP1_CIF_ISP_AWB_PROP);
+
+		/* Measurements require AWB block be active. */
+		rkisp1_param_set_bits(params, RKISP1_CIF_ISP_CTRL,
+				      RKISP1_CIF_ISP_CTRL_ISP_AWB_ENA);
+	} else {
+		rkisp1_write(params->rkisp1,
+			     reg_val, RKISP1_CIF_ISP_AWB_PROP);
+		rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_AWB_ENA);
+	}
+}
+
+static void
+rkisp1_awb_gain_config(struct rkisp1_params *params,
+		       const struct rkisp1_cif_isp_awb_gain_config *arg)
+{
+	rkisp1_write(params->rkisp1,
+		     RKISP1_CIF_ISP_AWB_GAIN_R_SET(arg->gain_green_r) |
+		     arg->gain_green_b, RKISP1_CIF_ISP_AWB_GAIN_G);
+
+	rkisp1_write(params->rkisp1,
+		     RKISP1_CIF_ISP_AWB_GAIN_R_SET(arg->gain_red) |
+		     arg->gain_blue, RKISP1_CIF_ISP_AWB_GAIN_RB);
+}
+
+static void rkisp1_aec_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_aec_config *arg)
+{
+	unsigned int block_hsize, block_vsize;
+	u32 exp_ctrl;
+
+	/* avoid to override the old enable value */
+	exp_ctrl = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_EXP_CTRL);
+	exp_ctrl &= RKISP1_CIF_ISP_EXP_ENA;
+	if (arg->autostop)
+		exp_ctrl |= RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP;
+	if (arg->mode == RKISP1_CIF_ISP_EXP_MEASURING_MODE_1)
+		exp_ctrl |= RKISP1_CIF_ISP_EXP_CTRL_MEASMODE_1;
+	rkisp1_write(params->rkisp1, exp_ctrl, RKISP1_CIF_ISP_EXP_CTRL);
+
+	rkisp1_write(params->rkisp1,
+		     arg->meas_window.h_offs, RKISP1_CIF_ISP_EXP_H_OFFSET);
+	rkisp1_write(params->rkisp1,
+		     arg->meas_window.v_offs, RKISP1_CIF_ISP_EXP_V_OFFSET);
+
+	block_hsize = arg->meas_window.h_size /
+		      RKISP1_CIF_ISP_EXP_COLUMN_NUM - 1;
+	block_vsize = arg->meas_window.v_size /
+		      RKISP1_CIF_ISP_EXP_ROW_NUM - 1;
+
+	rkisp1_write(params->rkisp1,
+		     RKISP1_CIF_ISP_EXP_H_SIZE_SET(block_hsize),
+		     RKISP1_CIF_ISP_EXP_H_SIZE);
+	rkisp1_write(params->rkisp1,
+		     RKISP1_CIF_ISP_EXP_V_SIZE_SET(block_vsize),
+		     RKISP1_CIF_ISP_EXP_V_SIZE);
+}
+
+static void rkisp1_cproc_config(struct rkisp1_params *params,
+				const struct rkisp1_cif_isp_cproc_config *arg)
+{
+	struct rkisp1_cif_isp_isp_other_cfg *cur_other_cfg =
+						&params->cur_params.others;
+	struct rkisp1_cif_isp_ie_config *cur_ie_config =
+						&cur_other_cfg->ie_config;
+	u32 effect = cur_ie_config->effect;
+	u32 quantization = params->quantization;
+
+	rkisp1_write(params->rkisp1, arg->contrast, RKISP1_CIF_C_PROC_CONTRAST);
+	rkisp1_write(params->rkisp1, arg->hue, RKISP1_CIF_C_PROC_HUE);
+	rkisp1_write(params->rkisp1, arg->sat, RKISP1_CIF_C_PROC_SATURATION);
+	rkisp1_write(params->rkisp1, arg->brightness,
+		     RKISP1_CIF_C_PROC_BRIGHTNESS);
+
+	if (quantization != V4L2_QUANTIZATION_FULL_RANGE ||
+	    effect != V4L2_COLORFX_NONE) {
+		rkisp1_param_clear_bits(params, RKISP1_CIF_C_PROC_CTRL,
+					RKISP1_CIF_C_PROC_YOUT_FULL |
+					RKISP1_CIF_C_PROC_YIN_FULL |
+					RKISP1_CIF_C_PROC_COUT_FULL);
+	} else {
+		rkisp1_param_set_bits(params, RKISP1_CIF_C_PROC_CTRL,
+				      RKISP1_CIF_C_PROC_YOUT_FULL |
+				      RKISP1_CIF_C_PROC_YIN_FULL |
+				      RKISP1_CIF_C_PROC_COUT_FULL);
+	}
+}
+
+static void rkisp1_hst_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_hst_config *arg)
+{
+	unsigned int block_hsize, block_vsize;
+	static const u32 hist_weight_regs[] = {
+		RKISP1_CIF_ISP_HIST_WEIGHT_00TO30,
+		RKISP1_CIF_ISP_HIST_WEIGHT_40TO21,
+		RKISP1_CIF_ISP_HIST_WEIGHT_31TO12,
+		RKISP1_CIF_ISP_HIST_WEIGHT_22TO03,
+		RKISP1_CIF_ISP_HIST_WEIGHT_13TO43,
+		RKISP1_CIF_ISP_HIST_WEIGHT_04TO34,
+		RKISP1_CIF_ISP_HIST_WEIGHT_44,
+	};
+	const u8 *weight;
+	unsigned int i;
+	u32 hist_prop;
+
+	/* avoid to override the old enable value */
+	hist_prop = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_HIST_PROP);
+	hist_prop &= RKISP1_CIF_ISP_HIST_PROP_MODE_MASK;
+	hist_prop |= RKISP1_CIF_ISP_HIST_PREDIV_SET(arg->histogram_predivider);
+	rkisp1_write(params->rkisp1, hist_prop, RKISP1_CIF_ISP_HIST_PROP);
+	rkisp1_write(params->rkisp1,
+		     arg->meas_window.h_offs,
+		     RKISP1_CIF_ISP_HIST_H_OFFS);
+	rkisp1_write(params->rkisp1,
+		     arg->meas_window.v_offs,
+		     RKISP1_CIF_ISP_HIST_V_OFFS);
+
+	block_hsize = arg->meas_window.h_size /
+		      RKISP1_CIF_ISP_HIST_COLUMN_NUM - 1;
+	block_vsize = arg->meas_window.v_size / RKISP1_CIF_ISP_HIST_ROW_NUM - 1;
+
+	rkisp1_write(params->rkisp1, block_hsize, RKISP1_CIF_ISP_HIST_H_SIZE);
+	rkisp1_write(params->rkisp1, block_vsize, RKISP1_CIF_ISP_HIST_V_SIZE);
+
+	weight = arg->hist_weight;
+	for (i = 0; i < ARRAY_SIZE(hist_weight_regs); ++i, weight += 4)
+		rkisp1_write(params->rkisp1,
+			     RKISP1_CIF_ISP_HIST_WEIGHT_SET(weight[0],
+							    weight[1],
+							    weight[2],
+							    weight[3]),
+				 hist_weight_regs[i]);
+}
+
+static void
+rkisp1_hst_enable(struct rkisp1_params *params,
+		  const struct rkisp1_cif_isp_hst_config *arg, bool en)
+{
+	if (en)	{
+		u32 hist_prop = rkisp1_read(params->rkisp1,
+					    RKISP1_CIF_ISP_HIST_PROP);
+
+		hist_prop &= ~RKISP1_CIF_ISP_HIST_PROP_MODE_MASK;
+		hist_prop |= arg->mode;
+		rkisp1_param_set_bits(params, RKISP1_CIF_ISP_HIST_PROP,
+				      hist_prop);
+	} else {
+		rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_HIST_PROP,
+					RKISP1_CIF_ISP_HIST_PROP_MODE_MASK);
+	}
+}
+
+static void rkisp1_afm_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_afc_config *arg)
+{
+	size_t num_of_win = min_t(size_t, ARRAY_SIZE(arg->afm_win),
+				  arg->num_afm_win);
+	u32 afm_ctrl = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_AFM_CTRL);
+	unsigned int i;
+
+	/* Switch off to configure. */
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_AFM_CTRL,
+				RKISP1_CIF_ISP_AFM_ENA);
+
+	for (i = 0; i < num_of_win; i++) {
+		rkisp1_write(params->rkisp1,
+			     RKISP1_CIF_ISP_AFM_WINDOW_X(arg->afm_win[i].h_offs) |
+			     RKISP1_CIF_ISP_AFM_WINDOW_Y(arg->afm_win[i].v_offs),
+			     RKISP1_CIF_ISP_AFM_LT_A + i * 8);
+		rkisp1_write(params->rkisp1,
+			     RKISP1_CIF_ISP_AFM_WINDOW_X(arg->afm_win[i].h_size +
+							 arg->afm_win[i].h_offs) |
+			     RKISP1_CIF_ISP_AFM_WINDOW_Y(arg->afm_win[i].v_size +
+							 arg->afm_win[i].v_offs),
+			     RKISP1_CIF_ISP_AFM_RB_A + i * 8);
+	}
+	rkisp1_write(params->rkisp1, arg->thres, RKISP1_CIF_ISP_AFM_THRES);
+	rkisp1_write(params->rkisp1, arg->var_shift,
+		     RKISP1_CIF_ISP_AFM_VAR_SHIFT);
+	/* restore afm status */
+	rkisp1_write(params->rkisp1, afm_ctrl, RKISP1_CIF_ISP_AFM_CTRL);
+}
+
+static void rkisp1_ie_config(struct rkisp1_params *params,
+			     const struct rkisp1_cif_isp_ie_config *arg)
+{
+	u32 eff_ctrl;
+
+	eff_ctrl = rkisp1_read(params->rkisp1, RKISP1_CIF_IMG_EFF_CTRL);
+	eff_ctrl &= ~RKISP1_CIF_IMG_EFF_CTRL_MODE_MASK;
+
+	if (params->quantization == V4L2_QUANTIZATION_FULL_RANGE)
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_YCBCR_FULL;
+
+	switch (arg->effect) {
+	case V4L2_COLORFX_SEPIA:
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_SEPIA;
+		break;
+	case V4L2_COLORFX_SET_CBCR:
+		rkisp1_write(params->rkisp1, arg->eff_tint,
+			     RKISP1_CIF_IMG_EFF_TINT);
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_SEPIA;
+		break;
+		/*
+		 * Color selection is similar to water color(AQUA):
+		 * grayscale + selected color w threshold
+		 */
+	case V4L2_COLORFX_AQUA:
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_COLOR_SEL;
+		rkisp1_write(params->rkisp1, arg->color_sel,
+			     RKISP1_CIF_IMG_EFF_COLOR_SEL);
+		break;
+	case V4L2_COLORFX_EMBOSS:
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_EMBOSS;
+		rkisp1_write(params->rkisp1, arg->eff_mat_1,
+			     RKISP1_CIF_IMG_EFF_MAT_1);
+		rkisp1_write(params->rkisp1, arg->eff_mat_2,
+			     RKISP1_CIF_IMG_EFF_MAT_2);
+		rkisp1_write(params->rkisp1, arg->eff_mat_3,
+			     RKISP1_CIF_IMG_EFF_MAT_3);
+		break;
+	case V4L2_COLORFX_SKETCH:
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_SKETCH;
+		rkisp1_write(params->rkisp1, arg->eff_mat_3,
+			     RKISP1_CIF_IMG_EFF_MAT_3);
+		rkisp1_write(params->rkisp1, arg->eff_mat_4,
+			     RKISP1_CIF_IMG_EFF_MAT_4);
+		rkisp1_write(params->rkisp1, arg->eff_mat_5,
+			     RKISP1_CIF_IMG_EFF_MAT_5);
+		break;
+	case V4L2_COLORFX_BW:
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_BLACKWHITE;
+		break;
+	case V4L2_COLORFX_NEGATIVE:
+		eff_ctrl |= RKISP1_CIF_IMG_EFF_CTRL_MODE_NEGATIVE;
+		break;
+	default:
+		break;
+	}
+
+	rkisp1_write(params->rkisp1, eff_ctrl, RKISP1_CIF_IMG_EFF_CTRL);
+}
+
+static void rkisp1_ie_enable(struct rkisp1_params *params, bool en)
+{
+	if (en) {
+		rkisp1_param_set_bits(params, RKISP1_CIF_ICCL,
+				      RKISP1_CIF_ICCL_IE_CLK);
+		rkisp1_write(params->rkisp1, RKISP1_CIF_IMG_EFF_CTRL_ENABLE,
+			     RKISP1_CIF_IMG_EFF_CTRL);
+		rkisp1_param_set_bits(params, RKISP1_CIF_IMG_EFF_CTRL,
+				      RKISP1_CIF_IMG_EFF_CTRL_CFG_UPD);
+	} else {
+		rkisp1_param_clear_bits(params, RKISP1_CIF_IMG_EFF_CTRL,
+					RKISP1_CIF_IMG_EFF_CTRL_ENABLE);
+		rkisp1_param_clear_bits(params, RKISP1_CIF_ICCL,
+					RKISP1_CIF_ICCL_IE_CLK);
+	}
+}
+
+static void rkisp1_csm_config(struct rkisp1_params *params, bool full_range)
+{
+	static const u16 full_range_coeff[] = {
+		0x0026, 0x004b, 0x000f,
+		0x01ea, 0x01d6, 0x0040,
+		0x0040, 0x01ca, 0x01f6
+	};
+	static const u16 limited_range_coeff[] = {
+		0x0021, 0x0040, 0x000d,
+		0x01ed, 0x01db, 0x0038,
+		0x0038, 0x01d1, 0x01f7,
+	};
+	unsigned int i;
+
+	if (full_range) {
+		for (i = 0; i < ARRAY_SIZE(full_range_coeff); i++)
+			rkisp1_write(params->rkisp1, full_range_coeff[i],
+				     RKISP1_CIF_ISP_CC_COEFF_0 + i * 4);
+
+		rkisp1_param_set_bits(params, RKISP1_CIF_ISP_CTRL,
+				      RKISP1_CIF_ISP_CTRL_ISP_CSM_Y_FULL_ENA |
+				      RKISP1_CIF_ISP_CTRL_ISP_CSM_C_FULL_ENA);
+	} else {
+		for (i = 0; i < ARRAY_SIZE(limited_range_coeff); i++)
+			rkisp1_write(params->rkisp1, limited_range_coeff[i],
+				     RKISP1_CIF_ISP_CC_COEFF_0 + i * 4);
+
+		rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_CSM_Y_FULL_ENA |
+					RKISP1_CIF_ISP_CTRL_ISP_CSM_C_FULL_ENA);
+	}
+}
+
+/* ISP De-noise Pre-Filter(DPF) function */
+static void rkisp1_dpf_config(struct rkisp1_params *params,
+			      const struct rkisp1_cif_isp_dpf_config *arg)
+{
+	unsigned int isp_dpf_mode, spatial_coeff, i;
+
+	switch (arg->gain.mode) {
+	case RKISP1_CIF_ISP_DPF_GAIN_USAGE_NF_GAINS:
+		isp_dpf_mode = RKISP1_CIF_ISP_DPF_MODE_USE_NF_GAIN |
+			       RKISP1_CIF_ISP_DPF_MODE_AWB_GAIN_COMP;
+		break;
+	case RKISP1_CIF_ISP_DPF_GAIN_USAGE_LSC_GAINS:
+		isp_dpf_mode = RKISP1_CIF_ISP_DPF_MODE_LSC_GAIN_COMP;
+		break;
+	case RKISP1_CIF_ISP_DPF_GAIN_USAGE_NF_LSC_GAINS:
+		isp_dpf_mode = RKISP1_CIF_ISP_DPF_MODE_USE_NF_GAIN |
+			       RKISP1_CIF_ISP_DPF_MODE_AWB_GAIN_COMP |
+			       RKISP1_CIF_ISP_DPF_MODE_LSC_GAIN_COMP;
+		break;
+	case RKISP1_CIF_ISP_DPF_GAIN_USAGE_AWB_GAINS:
+		isp_dpf_mode = RKISP1_CIF_ISP_DPF_MODE_AWB_GAIN_COMP;
+		break;
+	case RKISP1_CIF_ISP_DPF_GAIN_USAGE_AWB_LSC_GAINS:
+		isp_dpf_mode = RKISP1_CIF_ISP_DPF_MODE_LSC_GAIN_COMP |
+			       RKISP1_CIF_ISP_DPF_MODE_AWB_GAIN_COMP;
+		break;
+	case RKISP1_CIF_ISP_DPF_GAIN_USAGE_DISABLED:
+	default:
+		isp_dpf_mode = 0;
+		break;
+	}
+
+	if (arg->nll.scale_mode == RKISP1_CIF_ISP_NLL_SCALE_LOGARITHMIC)
+		isp_dpf_mode |= RKISP1_CIF_ISP_DPF_MODE_NLL_SEGMENTATION;
+	if (arg->rb_flt.fltsize == RKISP1_CIF_ISP_DPF_RB_FILTERSIZE_9x9)
+		isp_dpf_mode |= RKISP1_CIF_ISP_DPF_MODE_RB_FLTSIZE_9x9;
+	if (!arg->rb_flt.r_enable)
+		isp_dpf_mode |= RKISP1_CIF_ISP_DPF_MODE_R_FLT_DIS;
+	if (!arg->rb_flt.b_enable)
+		isp_dpf_mode |= RKISP1_CIF_ISP_DPF_MODE_B_FLT_DIS;
+	if (!arg->g_flt.gb_enable)
+		isp_dpf_mode |= RKISP1_CIF_ISP_DPF_MODE_GB_FLT_DIS;
+	if (!arg->g_flt.gr_enable)
+		isp_dpf_mode |= RKISP1_CIF_ISP_DPF_MODE_GR_FLT_DIS;
+
+	rkisp1_param_set_bits(params, RKISP1_CIF_ISP_DPF_MODE,
+			      isp_dpf_mode);
+	rkisp1_write(params->rkisp1, arg->gain.nf_b_gain,
+		     RKISP1_CIF_ISP_DPF_NF_GAIN_B);
+	rkisp1_write(params->rkisp1, arg->gain.nf_r_gain,
+		     RKISP1_CIF_ISP_DPF_NF_GAIN_R);
+	rkisp1_write(params->rkisp1, arg->gain.nf_gb_gain,
+		     RKISP1_CIF_ISP_DPF_NF_GAIN_GB);
+	rkisp1_write(params->rkisp1, arg->gain.nf_gr_gain,
+		     RKISP1_CIF_ISP_DPF_NF_GAIN_GR);
+
+	for (i = 0; i < RKISP1_CIF_ISP_DPF_MAX_NLF_COEFFS; i++) {
+		rkisp1_write(params->rkisp1, arg->nll.coeff[i],
+			     RKISP1_CIF_ISP_DPF_NULL_COEFF_0 + i * 4);
+	}
+
+	spatial_coeff = arg->g_flt.spatial_coeff[0] |
+			(arg->g_flt.spatial_coeff[1] << 8) |
+			(arg->g_flt.spatial_coeff[2] << 16) |
+			(arg->g_flt.spatial_coeff[3] << 24);
+	rkisp1_write(params->rkisp1, spatial_coeff,
+		     RKISP1_CIF_ISP_DPF_S_WEIGHT_G_1_4);
+
+	spatial_coeff = arg->g_flt.spatial_coeff[4] |
+			(arg->g_flt.spatial_coeff[5] << 8);
+	rkisp1_write(params->rkisp1, spatial_coeff,
+		     RKISP1_CIF_ISP_DPF_S_WEIGHT_G_5_6);
+
+	spatial_coeff = arg->rb_flt.spatial_coeff[0] |
+			(arg->rb_flt.spatial_coeff[1] << 8) |
+			(arg->rb_flt.spatial_coeff[2] << 16) |
+			(arg->rb_flt.spatial_coeff[3] << 24);
+	rkisp1_write(params->rkisp1, spatial_coeff,
+		     RKISP1_CIF_ISP_DPF_S_WEIGHT_RB_1_4);
+
+	spatial_coeff = arg->rb_flt.spatial_coeff[4] |
+			(arg->rb_flt.spatial_coeff[5] << 8);
+	rkisp1_write(params->rkisp1, spatial_coeff,
+		     RKISP1_CIF_ISP_DPF_S_WEIGHT_RB_5_6);
+}
+
+static void
+rkisp1_dpf_strength_config(struct rkisp1_params *params,
+			   const struct rkisp1_cif_isp_dpf_strength_config *arg)
+{
+	rkisp1_write(params->rkisp1, arg->b, RKISP1_CIF_ISP_DPF_STRENGTH_B);
+	rkisp1_write(params->rkisp1, arg->g, RKISP1_CIF_ISP_DPF_STRENGTH_G);
+	rkisp1_write(params->rkisp1, arg->r, RKISP1_CIF_ISP_DPF_STRENGTH_R);
+}
+
+static void
+rkisp1_isp_isr_other_config(struct rkisp1_params *params,
+			    const struct rkisp1_params_cfg *new_params)
+{
+	unsigned int module_en_update, module_cfg_update, module_ens;
+
+	module_en_update = new_params->module_en_update;
+	module_cfg_update = new_params->module_cfg_update;
+	module_ens = new_params->module_ens;
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_DPCC) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_DPCC)) {
+		/*update dpc config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_DPCC))
+			rkisp1_dpcc_config(params,
+					   &new_params->others.dpcc_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_DPCC) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_DPCC))
+				rkisp1_param_set_bits(params,
+						      RKISP1_CIF_ISP_DPCC_MODE,
+						      RKISP1_CIF_ISP_DPCC_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+						RKISP1_CIF_ISP_DPCC_MODE,
+						RKISP1_CIF_ISP_DPCC_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_BLS) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_BLS)) {
+		/* update bls config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_BLS))
+			rkisp1_bls_config(params,
+					  &new_params->others.bls_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_BLS) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_BLS))
+				rkisp1_param_set_bits(params,
+						      RKISP1_CIF_ISP_BLS_CTRL,
+						      RKISP1_CIF_ISP_BLS_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+							RKISP1_CIF_ISP_BLS_CTRL,
+							RKISP1_CIF_ISP_BLS_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_SDG) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_SDG)) {
+		/* update sdg config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_SDG))
+			rkisp1_sdg_config(params,
+					  &new_params->others.sdg_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_SDG) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_SDG))
+				rkisp1_param_set_bits(params,
+					RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_GAMMA_IN_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+					RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_GAMMA_IN_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_LSC) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_LSC)) {
+		/* update lsc config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_LSC))
+			rkisp1_lsc_config(params,
+					  &new_params->others.lsc_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_LSC) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_LSC))
+				rkisp1_param_set_bits(params,
+						RKISP1_CIF_ISP_LSC_CTRL,
+						RKISP1_CIF_ISP_LSC_CTRL_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+						RKISP1_CIF_ISP_LSC_CTRL,
+						RKISP1_CIF_ISP_LSC_CTRL_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_AWB_GAIN) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_AWB_GAIN)) {
+		/* update awb gains */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_AWB_GAIN))
+			rkisp1_awb_gain_config(params,
+					&new_params->others.awb_gain_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_AWB_GAIN) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_AWB_GAIN))
+				rkisp1_param_set_bits(params,
+					RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_AWB_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+					RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_AWB_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_BDM) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_BDM)) {
+		/* update bdm config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_BDM))
+			rkisp1_bdm_config(params,
+					  &new_params->others.bdm_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_BDM) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_BDM))
+				rkisp1_param_set_bits(params,
+						RKISP1_CIF_ISP_DEMOSAIC,
+						RKISP1_CIF_ISP_DEMOSAIC_BYPASS);
+			else
+				rkisp1_param_clear_bits(params,
+						RKISP1_CIF_ISP_DEMOSAIC,
+						RKISP1_CIF_ISP_DEMOSAIC_BYPASS);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_FLT) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_FLT)) {
+		/* update filter config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_FLT))
+			rkisp1_flt_config(params,
+					  &new_params->others.flt_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_FLT) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_FLT))
+				rkisp1_param_set_bits(params,
+						      RKISP1_CIF_ISP_FILT_MODE,
+						      RKISP1_CIF_ISP_FLT_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+						RKISP1_CIF_ISP_FILT_MODE,
+						RKISP1_CIF_ISP_FLT_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_CTK) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_CTK)) {
+		/* update ctk config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_CTK))
+			rkisp1_ctk_config(params,
+					  &new_params->others.ctk_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_CTK)
+			rkisp1_ctk_enable(params,
+				!!(module_ens & RKISP1_CIF_ISP_MODULE_CTK));
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_GOC) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_GOC)) {
+		/* update goc config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_GOC))
+			rkisp1_goc_config(params,
+					  &new_params->others.goc_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_GOC) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_GOC))
+				rkisp1_param_set_bits(params,
+					RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+					RKISP1_CIF_ISP_CTRL,
+					RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_CPROC) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_CPROC)) {
+		/* update cproc config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_CPROC)) {
+			rkisp1_cproc_config(params,
+					    &new_params->others.cproc_config);
+		}
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_CPROC) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_CPROC))
+				rkisp1_param_set_bits(params,
+						RKISP1_CIF_C_PROC_CTRL,
+						RKISP1_CIF_C_PROC_CTR_ENABLE);
+			else
+				rkisp1_param_clear_bits(params,
+						RKISP1_CIF_C_PROC_CTRL,
+						RKISP1_CIF_C_PROC_CTR_ENABLE);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_IE) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_IE)) {
+		/* update ie config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_IE))
+			rkisp1_ie_config(params,
+					 &new_params->others.ie_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_IE)
+			rkisp1_ie_enable(params,
+				!!(module_ens & RKISP1_CIF_ISP_MODULE_IE));
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_DPF) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_DPF)) {
+		/* update dpf  config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_DPF))
+			rkisp1_dpf_config(params,
+					  &new_params->others.dpf_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_DPF) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_DPF))
+				rkisp1_param_set_bits(params,
+						   RKISP1_CIF_ISP_DPF_MODE,
+						   RKISP1_CIF_ISP_DPF_MODE_EN);
+			else
+				rkisp1_param_clear_bits(params,
+						RKISP1_CIF_ISP_DPF_MODE,
+						RKISP1_CIF_ISP_DPF_MODE_EN);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_DPF_STRENGTH) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_DPF_STRENGTH)) {
+		/* update dpf strength config */
+		rkisp1_dpf_strength_config(params,
+				&new_params->others.dpf_strength_config);
+	}
+}
+
+static void rkisp1_isp_isr_meas_config(struct rkisp1_params *params,
+				       struct  rkisp1_params_cfg *new_params)
+{
+	unsigned int module_en_update, module_cfg_update, module_ens;
+
+	module_en_update = new_params->module_en_update;
+	module_cfg_update = new_params->module_cfg_update;
+	module_ens = new_params->module_ens;
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_AWB) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_AWB)) {
+		/* update awb config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_AWB))
+			rkisp1_awb_meas_config(params,
+					&new_params->meas.awb_meas_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_AWB)
+			rkisp1_awb_meas_enable(params,
+				&new_params->meas.awb_meas_config,
+				!!(module_ens & RKISP1_CIF_ISP_MODULE_AWB));
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_AFC) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_AFC)) {
+		/* update afc config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_AFC))
+			rkisp1_afm_config(params,
+					  &new_params->meas.afc_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_AFC) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_AFC))
+				rkisp1_param_set_bits(params,
+						      RKISP1_CIF_ISP_AFM_CTRL,
+						      RKISP1_CIF_ISP_AFM_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+							RKISP1_CIF_ISP_AFM_CTRL,
+							RKISP1_CIF_ISP_AFM_ENA);
+		}
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_HST) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_HST)) {
+		/* update hst config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_HST))
+			rkisp1_hst_config(params,
+					  &new_params->meas.hst_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_HST)
+			rkisp1_hst_enable(params,
+				&new_params->meas.hst_config,
+				!!(module_ens & RKISP1_CIF_ISP_MODULE_HST));
+	}
+
+	if ((module_en_update & RKISP1_CIF_ISP_MODULE_AEC) ||
+	    (module_cfg_update & RKISP1_CIF_ISP_MODULE_AEC)) {
+		/* update aec config */
+		if ((module_cfg_update & RKISP1_CIF_ISP_MODULE_AEC))
+			rkisp1_aec_config(params,
+					  &new_params->meas.aec_config);
+
+		if (module_en_update & RKISP1_CIF_ISP_MODULE_AEC) {
+			if (!!(module_ens & RKISP1_CIF_ISP_MODULE_AEC))
+				rkisp1_param_set_bits(params,
+						      RKISP1_CIF_ISP_EXP_CTRL,
+						      RKISP1_CIF_ISP_EXP_ENA);
+			else
+				rkisp1_param_clear_bits(params,
+							RKISP1_CIF_ISP_EXP_CTRL,
+							RKISP1_CIF_ISP_EXP_ENA);
+		}
+	}
+}
+
+void rkisp1_params_isr(struct rkisp1_device *rkisp1, u32 isp_mis)
+{
+	unsigned int frame_sequence = atomic_read(&rkisp1->isp.frame_sequence);
+	struct rkisp1_params *params = &rkisp1->params;
+	struct rkisp1_params_cfg *new_params;
+	struct rkisp1_buffer *cur_buf = NULL;
+
+	spin_lock(&params->config_lock);
+	if (!params->is_streaming) {
+		spin_unlock(&params->config_lock);
+		return;
+	}
+
+	/* get one empty buffer */
+	if (!list_empty(&params->params))
+		cur_buf = list_first_entry(&params->params,
+					   struct rkisp1_buffer, queue);
+	spin_unlock(&params->config_lock);
+
+	if (!cur_buf)
+		return;
+
+	new_params = (struct rkisp1_params_cfg *)(cur_buf->vaddr[0]);
+
+	if (isp_mis & RKISP1_CIF_ISP_FRAME) {
+		u32 isp_ctrl;
+
+		rkisp1_isp_isr_other_config(params, new_params);
+		rkisp1_isp_isr_meas_config(params, new_params);
+
+		/* update shadow register immediately */
+		isp_ctrl = rkisp1_read(params->rkisp1, RKISP1_CIF_ISP_CTRL);
+		isp_ctrl |= RKISP1_CIF_ISP_CTRL_ISP_CFG_UPD;
+		rkisp1_write(params->rkisp1, isp_ctrl, RKISP1_CIF_ISP_CTRL);
+
+		spin_lock(&params->config_lock);
+		list_del(&cur_buf->queue);
+		spin_unlock(&params->config_lock);
+
+		cur_buf->vb.sequence = frame_sequence;
+		vb2_buffer_done(&cur_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
+	}
+}
+
+static const struct rkisp1_cif_isp_awb_meas_config rkisp1_awb_params_default_config = {
+	{
+		0, 0, RKISP1_DEFAULT_WIDTH, RKISP1_DEFAULT_HEIGHT
+	},
+	RKISP1_CIF_ISP_AWB_MODE_YCBCR, 200, 30, 20, 20, 0, 128, 128
+};
+
+static const struct rkisp1_cif_isp_aec_config rkisp1_aec_params_default_config = {
+	RKISP1_CIF_ISP_EXP_MEASURING_MODE_0,
+	RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP_0,
+	{
+		RKISP1_DEFAULT_WIDTH >> 2, RKISP1_DEFAULT_HEIGHT >> 2,
+		RKISP1_DEFAULT_WIDTH >> 1, RKISP1_DEFAULT_HEIGHT >> 1
+	}
+};
+
+static const struct rkisp1_cif_isp_hst_config rkisp1_hst_params_default_config = {
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_RGB_COMBINED,
+	3,
+	{
+		RKISP1_DEFAULT_WIDTH >> 2, RKISP1_DEFAULT_HEIGHT >> 2,
+		RKISP1_DEFAULT_WIDTH >> 1, RKISP1_DEFAULT_HEIGHT >> 1
+	},
+	{
+		0, /* To be filled in with 0x01 at runtime. */
+	}
+};
+
+static const struct rkisp1_cif_isp_afc_config rkisp1_afc_params_default_config = {
+	1,
+	{
+		{
+			300, 225, 200, 150
+		}
+	},
+	4,
+	14
+};
+
+static void rkisp1_params_config_parameter(struct rkisp1_params *params)
+{
+	struct rkisp1_cif_isp_hst_config hst = rkisp1_hst_params_default_config;
+
+	spin_lock(&params->config_lock);
+
+	rkisp1_awb_meas_config(params, &rkisp1_awb_params_default_config);
+	rkisp1_awb_meas_enable(params, &rkisp1_awb_params_default_config,
+			       true);
+
+	rkisp1_aec_config(params, &rkisp1_aec_params_default_config);
+	rkisp1_param_set_bits(params, RKISP1_CIF_ISP_EXP_CTRL,
+			      RKISP1_CIF_ISP_EXP_ENA);
+
+	rkisp1_afm_config(params, &rkisp1_afc_params_default_config);
+	rkisp1_param_set_bits(params, RKISP1_CIF_ISP_AFM_CTRL,
+			      RKISP1_CIF_ISP_AFM_ENA);
+
+	memset(hst.hist_weight, 0x01, sizeof(hst.hist_weight));
+	rkisp1_hst_config(params, &hst);
+	rkisp1_param_set_bits(params, RKISP1_CIF_ISP_HIST_PROP,
+			      ~RKISP1_CIF_ISP_HIST_PROP_MODE_MASK |
+			      rkisp1_hst_params_default_config.mode);
+
+	/* set the  range */
+	if (params->quantization == V4L2_QUANTIZATION_FULL_RANGE)
+		rkisp1_csm_config(params, true);
+	else
+		rkisp1_csm_config(params, false);
+
+	/* override the default things */
+	rkisp1_isp_isr_other_config(params, &params->cur_params);
+	rkisp1_isp_isr_meas_config(params, &params->cur_params);
+
+	spin_unlock(&params->config_lock);
+}
+
+/* Not called when the camera active, thus not isr protection. */
+void rkisp1_params_configure(struct rkisp1_params *params,
+			     enum rkisp1_fmt_raw_pat_type bayer_pat,
+			     enum v4l2_quantization quantization)
+{
+	params->quantization = quantization;
+	params->raw_type = bayer_pat;
+	rkisp1_params_config_parameter(params);
+}
+
+/* Not called when the camera active, thus not isr protection. */
+void rkisp1_params_disable(struct rkisp1_params *params)
+{
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_DPCC_MODE,
+				RKISP1_CIF_ISP_DPCC_ENA);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_LSC_CTRL,
+				RKISP1_CIF_ISP_LSC_CTRL_ENA);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_BLS_CTRL,
+				RKISP1_CIF_ISP_BLS_ENA);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CTRL,
+				RKISP1_CIF_ISP_CTRL_ISP_GAMMA_IN_ENA);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CTRL,
+				RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_DEMOSAIC,
+				RKISP1_CIF_ISP_DEMOSAIC_BYPASS);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_FILT_MODE,
+				RKISP1_CIF_ISP_FLT_ENA);
+	rkisp1_awb_meas_enable(params, NULL, false);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_CTRL,
+				RKISP1_CIF_ISP_CTRL_ISP_AWB_ENA);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_EXP_CTRL,
+				RKISP1_CIF_ISP_EXP_ENA);
+	rkisp1_ctk_enable(params, false);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_C_PROC_CTRL,
+				RKISP1_CIF_C_PROC_CTR_ENABLE);
+	rkisp1_hst_enable(params, NULL, false);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_AFM_CTRL,
+				RKISP1_CIF_ISP_AFM_ENA);
+	rkisp1_ie_enable(params, false);
+	rkisp1_param_clear_bits(params, RKISP1_CIF_ISP_DPF_MODE,
+				RKISP1_CIF_ISP_DPF_MODE_EN);
+}
+
+static int rkisp1_params_enum_fmt_meta_out(struct file *file, void *priv,
+					   struct v4l2_fmtdesc *f)
+{
+	struct video_device *video = video_devdata(file);
+	struct rkisp1_params *params = video_get_drvdata(video);
+
+	if (f->index > 0 || f->type != video->queue->type)
+		return -EINVAL;
+
+	f->pixelformat = params->vdev_fmt.fmt.meta.dataformat;
+
+	return 0;
+}
+
+static int rkisp1_params_g_fmt_meta_out(struct file *file, void *fh,
+					struct v4l2_format *f)
+{
+	struct video_device *video = video_devdata(file);
+	struct rkisp1_params *params = video_get_drvdata(video);
+	struct v4l2_meta_format *meta = &f->fmt.meta;
+
+	if (f->type != video->queue->type)
+		return -EINVAL;
+
+	memset(meta, 0, sizeof(*meta));
+	meta->dataformat = params->vdev_fmt.fmt.meta.dataformat;
+	meta->buffersize = params->vdev_fmt.fmt.meta.buffersize;
+
+	return 0;
+}
+
+static int rkisp1_params_querycap(struct file *file,
+				  void *priv, struct v4l2_capability *cap)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	strscpy(cap->driver, RKISP1_DRIVER_NAME, sizeof(cap->driver));
+	strscpy(cap->card, vdev->name, sizeof(cap->card));
+	strscpy(cap->bus_info, RKISP1_BUS_INFO, sizeof(cap->bus_info));
+
+	return 0;
+}
+
+/* ISP params video device IOCTLs */
+static const struct v4l2_ioctl_ops rkisp1_params_ioctl = {
+	.vidioc_reqbufs = vb2_ioctl_reqbufs,
+	.vidioc_querybuf = vb2_ioctl_querybuf,
+	.vidioc_create_bufs = vb2_ioctl_create_bufs,
+	.vidioc_qbuf = vb2_ioctl_qbuf,
+	.vidioc_dqbuf = vb2_ioctl_dqbuf,
+	.vidioc_prepare_buf = vb2_ioctl_prepare_buf,
+	.vidioc_expbuf = vb2_ioctl_expbuf,
+	.vidioc_streamon = vb2_ioctl_streamon,
+	.vidioc_streamoff = vb2_ioctl_streamoff,
+	.vidioc_enum_fmt_meta_out = rkisp1_params_enum_fmt_meta_out,
+	.vidioc_g_fmt_meta_out = rkisp1_params_g_fmt_meta_out,
+	.vidioc_s_fmt_meta_out = rkisp1_params_g_fmt_meta_out,
+	.vidioc_try_fmt_meta_out = rkisp1_params_g_fmt_meta_out,
+	.vidioc_querycap = rkisp1_params_querycap,
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+static int rkisp1_params_vb2_queue_setup(struct vb2_queue *vq,
+					 unsigned int *num_buffers,
+					 unsigned int *num_planes,
+					 unsigned int sizes[],
+					 struct device *alloc_devs[])
+{
+	struct rkisp1_params *params = vq->drv_priv;
+
+	*num_buffers = clamp_t(u32, *num_buffers,
+			       RKISP1_ISP_PARAMS_REQ_BUFS_MIN,
+			       RKISP1_ISP_PARAMS_REQ_BUFS_MAX);
+
+	*num_planes = 1;
+
+	sizes[0] = sizeof(struct rkisp1_params_cfg);
+
+	INIT_LIST_HEAD(&params->params);
+	params->is_first_params = true;
+
+	return 0;
+}
+
+static void rkisp1_params_vb2_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rkisp1_buffer *params_buf =
+		container_of(vbuf, struct rkisp1_buffer, vb);
+	struct vb2_queue *vq = vb->vb2_queue;
+	struct rkisp1_params *params = vq->drv_priv;
+	struct rkisp1_params_cfg *new_params;
+	unsigned long flags;
+	unsigned int frame_sequence =
+		atomic_read(&params->rkisp1->isp.frame_sequence);
+
+	if (params->is_first_params) {
+		new_params = (struct rkisp1_params_cfg *)
+			(vb2_plane_vaddr(vb, 0));
+		vbuf->sequence = frame_sequence;
+		vb2_buffer_done(&params_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
+		params->is_first_params = false;
+		params->cur_params = *new_params;
+		return;
+	}
+
+	params_buf->vaddr[0] = vb2_plane_vaddr(vb, 0);
+	spin_lock_irqsave(&params->config_lock, flags);
+	list_add_tail(&params_buf->queue, &params->params);
+	spin_unlock_irqrestore(&params->config_lock, flags);
+}
+
+static int rkisp1_params_vb2_buf_prepare(struct vb2_buffer *vb)
+{
+	if (vb2_plane_size(vb, 0) < sizeof(struct rkisp1_params_cfg))
+		return -EINVAL;
+
+	vb2_set_plane_payload(vb, 0, sizeof(struct rkisp1_params_cfg));
+
+	return 0;
+}
+
+static void rkisp1_params_vb2_stop_streaming(struct vb2_queue *vq)
+{
+	struct rkisp1_params *params = vq->drv_priv;
+	struct rkisp1_buffer *buf;
+	unsigned long flags;
+	unsigned int i;
+
+	/* stop params input firstly */
+	spin_lock_irqsave(&params->config_lock, flags);
+	params->is_streaming = false;
+	spin_unlock_irqrestore(&params->config_lock, flags);
+
+	for (i = 0; i < RKISP1_ISP_PARAMS_REQ_BUFS_MAX; i++) {
+		spin_lock_irqsave(&params->config_lock, flags);
+		if (!list_empty(&params->params)) {
+			buf = list_first_entry(&params->params,
+					       struct rkisp1_buffer, queue);
+			list_del(&buf->queue);
+			spin_unlock_irqrestore(&params->config_lock,
+					       flags);
+		} else {
+			spin_unlock_irqrestore(&params->config_lock,
+					       flags);
+			break;
+		}
+
+		if (buf)
+			vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+		buf = NULL;
+	}
+}
+
+static int
+rkisp1_params_vb2_start_streaming(struct vb2_queue *queue, unsigned int count)
+{
+	struct rkisp1_params *params = queue->drv_priv;
+	unsigned long flags;
+
+	spin_lock_irqsave(&params->config_lock, flags);
+	params->is_streaming = true;
+	spin_unlock_irqrestore(&params->config_lock, flags);
+
+	return 0;
+}
+
+static struct vb2_ops rkisp1_params_vb2_ops = {
+	.queue_setup = rkisp1_params_vb2_queue_setup,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.buf_queue = rkisp1_params_vb2_buf_queue,
+	.buf_prepare = rkisp1_params_vb2_buf_prepare,
+	.start_streaming = rkisp1_params_vb2_start_streaming,
+	.stop_streaming = rkisp1_params_vb2_stop_streaming,
+
+};
+
+static struct v4l2_file_operations rkisp1_params_fops = {
+	.mmap = vb2_fop_mmap,
+	.unlocked_ioctl = video_ioctl2,
+	.poll = vb2_fop_poll,
+	.open = v4l2_fh_open,
+	.release = vb2_fop_release
+};
+
+static int rkisp1_params_init_vb2_queue(struct vb2_queue *q,
+					struct rkisp1_params *params)
+{
+	struct rkisp1_vdev_node *node;
+
+	node = container_of(q, struct rkisp1_vdev_node, buf_queue);
+
+	q->type = V4L2_BUF_TYPE_META_OUTPUT;
+	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
+	q->drv_priv = params;
+	q->ops = &rkisp1_params_vb2_ops;
+	q->mem_ops = &vb2_vmalloc_memops;
+	q->buf_struct_size = sizeof(struct rkisp1_buffer);
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &node->vlock;
+
+	return vb2_queue_init(q);
+}
+
+static void rkisp1_init_params(struct rkisp1_params *params)
+{
+	params->vdev_fmt.fmt.meta.dataformat =
+		V4L2_META_FMT_RK_ISP1_PARAMS;
+	params->vdev_fmt.fmt.meta.buffersize =
+		sizeof(struct rkisp1_params_cfg);
+}
+
+int rkisp1_params_register(struct rkisp1_params *params,
+			   struct v4l2_device *v4l2_dev,
+			   struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_vdev_node *node = &params->vnode;
+	struct video_device *vdev = &node->vdev;
+	int ret;
+
+	params->rkisp1 = rkisp1;
+	mutex_init(&node->vlock);
+	spin_lock_init(&params->config_lock);
+
+	strscpy(vdev->name, RKISP1_PARAMS_DEV_NAME, sizeof(vdev->name));
+
+	video_set_drvdata(vdev, params);
+	vdev->ioctl_ops = &rkisp1_params_ioctl;
+	vdev->fops = &rkisp1_params_fops;
+	vdev->release = video_device_release_empty;
+	/*
+	 * Provide a mutex to v4l2 core. It will be used
+	 * to protect all fops and v4l2 ioctls.
+	 */
+	vdev->lock = &node->vlock;
+	vdev->v4l2_dev = v4l2_dev;
+	vdev->queue = &node->buf_queue;
+	vdev->device_caps = V4L2_CAP_STREAMING | V4L2_CAP_META_OUTPUT;
+	vdev->vfl_dir = VFL_DIR_TX;
+	rkisp1_params_init_vb2_queue(vdev->queue, params);
+	rkisp1_init_params(params);
+	video_set_drvdata(vdev, params);
+
+	node->pad.flags = MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_pads_init(&vdev->entity, 1, &node->pad);
+	if (ret)
+		goto err_release_queue;
+	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
+	if (ret) {
+		dev_err(&vdev->dev,
+			"failed to register %s, ret=%d\n", vdev->name, ret);
+		goto err_cleanup_media_entity;
+	}
+	return 0;
+err_cleanup_media_entity:
+	media_entity_cleanup(&vdev->entity);
+err_release_queue:
+	vb2_queue_release(vdev->queue);
+	return ret;
+}
+
+void rkisp1_params_unregister(struct rkisp1_params *params)
+{
+	struct rkisp1_vdev_node *node = &params->vnode;
+	struct video_device *vdev = &node->vdev;
+
+	video_unregister_device(vdev);
+	media_entity_cleanup(&vdev->entity);
+	vb2_queue_release(vdev->queue);
+}
diff --git a/drivers/staging/media/rkisp1/rkisp1-regs.h b/drivers/staging/media/rkisp1/rkisp1-regs.h
new file mode 100644
index 000000000000..46018f435b6f
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-regs.h
@@ -0,0 +1,1264 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+/*
+ * Rockchip ISP1 Driver - Registers header
+ *
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#ifndef _RKISP1_REGS_H
+#define _RKISP1_REGS_H
+
+/* ISP_CTRL */
+#define RKISP1_CIF_ISP_CTRL_ISP_ENABLE			BIT(0)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_RAW_PICT		(0 << 1)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_ITU656		BIT(1)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_ITU601		(2 << 1)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_BAYER_ITU601	(3 << 1)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_DATA_MODE		(4 << 1)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_BAYER_ITU656	(5 << 1)
+#define RKISP1_CIF_ISP_CTRL_ISP_MODE_RAW_PICT_ITU656	(6 << 1)
+#define RKISP1_CIF_ISP_CTRL_ISP_INFORM_ENABLE		BIT(4)
+#define RKISP1_CIF_ISP_CTRL_ISP_GAMMA_IN_ENA		BIT(6)
+#define RKISP1_CIF_ISP_CTRL_ISP_AWB_ENA			BIT(7)
+#define RKISP1_CIF_ISP_CTRL_ISP_CFG_UPD_PERMANENT	BIT(8)
+#define RKISP1_CIF_ISP_CTRL_ISP_CFG_UPD			BIT(9)
+#define RKISP1_CIF_ISP_CTRL_ISP_GEN_CFG_UPD		BIT(10)
+#define RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA		BIT(11)
+#define RKISP1_CIF_ISP_CTRL_ISP_FLASH_MODE_ENA		BIT(12)
+#define RKISP1_CIF_ISP_CTRL_ISP_CSM_Y_FULL_ENA		BIT(13)
+#define RKISP1_CIF_ISP_CTRL_ISP_CSM_C_FULL_ENA		BIT(14)
+
+/* ISP_ACQ_PROP */
+#define RKISP1_CIF_ISP_ACQ_PROP_POS_EDGE		BIT(0)
+#define RKISP1_CIF_ISP_ACQ_PROP_HSYNC_LOW		BIT(1)
+#define RKISP1_CIF_ISP_ACQ_PROP_VSYNC_LOW		BIT(2)
+#define RKISP1_CIF_ISP_ACQ_PROP_BAYER_PAT_RGGB		(0 << 3)
+#define RKISP1_CIF_ISP_ACQ_PROP_BAYER_PAT_GRBG		BIT(3)
+#define RKISP1_CIF_ISP_ACQ_PROP_BAYER_PAT_GBRG		(2 << 3)
+#define RKISP1_CIF_ISP_ACQ_PROP_BAYER_PAT_BGGR		(3 << 3)
+#define RKISP1_CIF_ISP_ACQ_PROP_BAYER_PAT(pat)		((pat) << 3)
+#define RKISP1_CIF_ISP_ACQ_PROP_YCBYCR			(0 << 7)
+#define RKISP1_CIF_ISP_ACQ_PROP_YCRYCB			BIT(7)
+#define RKISP1_CIF_ISP_ACQ_PROP_CBYCRY			(2 << 7)
+#define RKISP1_CIF_ISP_ACQ_PROP_CRYCBY			(3 << 7)
+#define RKISP1_CIF_ISP_ACQ_PROP_FIELD_SEL_ALL		(0 << 9)
+#define RKISP1_CIF_ISP_ACQ_PROP_FIELD_SEL_EVEN		BIT(9)
+#define RKISP1_CIF_ISP_ACQ_PROP_FIELD_SEL_ODD		(2 << 9)
+#define RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_12B		(0 << 12)
+#define RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_10B_ZERO		BIT(12)
+#define RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_10B_MSB		(2 << 12)
+#define RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_8B_ZERO		(3 << 12)
+#define RKISP1_CIF_ISP_ACQ_PROP_IN_SEL_8B_MSB		(4 << 12)
+
+/* VI_DPCL */
+#define RKISP1_CIF_VI_DPCL_DMA_JPEG			(0 << 0)
+#define RKISP1_CIF_VI_DPCL_MP_MUX_MRSZ_MI		BIT(0)
+#define RKISP1_CIF_VI_DPCL_MP_MUX_MRSZ_JPEG		(2 << 0)
+#define RKISP1_CIF_VI_DPCL_CHAN_MODE_MP			BIT(2)
+#define RKISP1_CIF_VI_DPCL_CHAN_MODE_SP			(2 << 2)
+#define RKISP1_CIF_VI_DPCL_CHAN_MODE_MPSP		(3 << 2)
+#define RKISP1_CIF_VI_DPCL_DMA_SW_SPMUX			(0 << 4)
+#define RKISP1_CIF_VI_DPCL_DMA_SW_SI			BIT(4)
+#define RKISP1_CIF_VI_DPCL_DMA_SW_IE			(2 << 4)
+#define RKISP1_CIF_VI_DPCL_DMA_SW_JPEG			(3 << 4)
+#define RKISP1_CIF_VI_DPCL_DMA_SW_ISP			(4 << 4)
+#define RKISP1_CIF_VI_DPCL_IF_SEL_PARALLEL		(0 << 8)
+#define RKISP1_CIF_VI_DPCL_IF_SEL_SMIA			BIT(8)
+#define RKISP1_CIF_VI_DPCL_IF_SEL_MIPI			(2 << 8)
+#define RKISP1_CIF_VI_DPCL_DMA_IE_MUX_DMA		BIT(10)
+#define RKISP1_CIF_VI_DPCL_DMA_SP_MUX_DMA		BIT(11)
+
+/* ISP_IMSC - ISP_MIS - ISP_RIS - ISP_ICR - ISP_ISR */
+#define RKISP1_CIF_ISP_OFF				BIT(0)
+#define RKISP1_CIF_ISP_FRAME				BIT(1)
+#define RKISP1_CIF_ISP_DATA_LOSS			BIT(2)
+#define RKISP1_CIF_ISP_PIC_SIZE_ERROR			BIT(3)
+#define RKISP1_CIF_ISP_AWB_DONE				BIT(4)
+#define RKISP1_CIF_ISP_FRAME_IN				BIT(5)
+#define RKISP1_CIF_ISP_V_START				BIT(6)
+#define RKISP1_CIF_ISP_H_START				BIT(7)
+#define RKISP1_CIF_ISP_FLASH_ON				BIT(8)
+#define RKISP1_CIF_ISP_FLASH_OFF			BIT(9)
+#define RKISP1_CIF_ISP_SHUTTER_ON			BIT(10)
+#define RKISP1_CIF_ISP_SHUTTER_OFF			BIT(11)
+#define RKISP1_CIF_ISP_AFM_SUM_OF			BIT(12)
+#define RKISP1_CIF_ISP_AFM_LUM_OF			BIT(13)
+#define RKISP1_CIF_ISP_AFM_FIN				BIT(14)
+#define RKISP1_CIF_ISP_HIST_MEASURE_RDY			BIT(15)
+#define RKISP1_CIF_ISP_FLASH_CAP			BIT(17)
+#define RKISP1_CIF_ISP_EXP_END				BIT(18)
+#define RKISP1_CIF_ISP_VSM_END				BIT(19)
+
+/* ISP_ERR */
+#define RKISP1_CIF_ISP_ERR_INFORM_SIZE			BIT(0)
+#define RKISP1_CIF_ISP_ERR_IS_SIZE			BIT(1)
+#define RKISP1_CIF_ISP_ERR_OUTFORM_SIZE			BIT(2)
+
+/* MI_CTRL */
+#define RKISP1_CIF_MI_CTRL_MP_ENABLE			BIT(0)
+#define RKISP1_CIF_MI_CTRL_SP_ENABLE			(2 << 0)
+#define RKISP1_CIF_MI_CTRL_JPEG_ENABLE			(4 << 0)
+#define RKISP1_CIF_MI_CTRL_RAW_ENABLE			(8 << 0)
+#define RKISP1_CIF_MI_CTRL_HFLIP			BIT(4)
+#define RKISP1_CIF_MI_CTRL_VFLIP			BIT(5)
+#define RKISP1_CIF_MI_CTRL_ROT				BIT(6)
+#define RKISP1_CIF_MI_BYTE_SWAP				BIT(7)
+#define RKISP1_CIF_MI_SP_Y_FULL_YUV2RGB			BIT(8)
+#define RKISP1_CIF_MI_SP_CBCR_FULL_YUV2RGB		BIT(9)
+#define RKISP1_CIF_MI_SP_422NONCOSITEED			BIT(10)
+#define RKISP1_CIF_MI_MP_PINGPONG_ENABEL		BIT(11)
+#define RKISP1_CIF_MI_SP_PINGPONG_ENABEL		BIT(12)
+#define RKISP1_CIF_MI_MP_AUTOUPDATE_ENABLE		BIT(13)
+#define RKISP1_CIF_MI_SP_AUTOUPDATE_ENABLE		BIT(14)
+#define RKISP1_CIF_MI_LAST_PIXEL_SIG_ENABLE		BIT(15)
+#define RKISP1_CIF_MI_CTRL_BURST_LEN_LUM_16		(0 << 16)
+#define RKISP1_CIF_MI_CTRL_BURST_LEN_LUM_32		BIT(16)
+#define RKISP1_CIF_MI_CTRL_BURST_LEN_LUM_64		(2 << 16)
+#define RKISP1_CIF_MI_CTRL_BURST_LEN_CHROM_16		(0 << 18)
+#define RKISP1_CIF_MI_CTRL_BURST_LEN_CHROM_32		BIT(18)
+#define RKISP1_CIF_MI_CTRL_BURST_LEN_CHROM_64		(2 << 18)
+#define RKISP1_CIF_MI_CTRL_INIT_BASE_EN			BIT(20)
+#define RKISP1_CIF_MI_CTRL_INIT_OFFSET_EN		BIT(21)
+#define RKISP1_MI_CTRL_MP_WRITE_YUV_PLA_OR_RAW8		(0 << 22)
+#define RKISP1_MI_CTRL_MP_WRITE_YUV_SPLA		BIT(22)
+#define RKISP1_MI_CTRL_MP_WRITE_YUVINT			(2 << 22)
+#define RKISP1_MI_CTRL_MP_WRITE_RAW12			(2 << 22)
+#define RKISP1_MI_CTRL_SP_WRITE_PLA			(0 << 24)
+#define RKISP1_MI_CTRL_SP_WRITE_SPLA			BIT(24)
+#define RKISP1_MI_CTRL_SP_WRITE_INT			(2 << 24)
+#define RKISP1_MI_CTRL_SP_INPUT_YUV400			(0 << 26)
+#define RKISP1_MI_CTRL_SP_INPUT_YUV420			BIT(26)
+#define RKISP1_MI_CTRL_SP_INPUT_YUV422			(2 << 26)
+#define RKISP1_MI_CTRL_SP_INPUT_YUV444			(3 << 26)
+#define RKISP1_MI_CTRL_SP_OUTPUT_YUV400			(0 << 28)
+#define RKISP1_MI_CTRL_SP_OUTPUT_YUV420			BIT(28)
+#define RKISP1_MI_CTRL_SP_OUTPUT_YUV422			(2 << 28)
+#define RKISP1_MI_CTRL_SP_OUTPUT_YUV444			(3 << 28)
+#define RKISP1_MI_CTRL_SP_OUTPUT_RGB565			(4 << 28)
+#define RKISP1_MI_CTRL_SP_OUTPUT_RGB666			(5 << 28)
+#define RKISP1_MI_CTRL_SP_OUTPUT_RGB888			(6 << 28)
+
+#define RKISP1_MI_CTRL_MP_FMT_MASK			GENMASK(23, 22)
+#define RKISP1_MI_CTRL_SP_FMT_MASK			GENMASK(30, 24)
+
+/* MI_INIT */
+#define RKISP1_CIF_MI_INIT_SKIP				BIT(2)
+#define RKISP1_CIF_MI_INIT_SOFT_UPD			BIT(4)
+
+/* MI_CTRL_SHD */
+#define RKISP1_CIF_MI_CTRL_SHD_MP_IN_ENABLED		BIT(0)
+#define RKISP1_CIF_MI_CTRL_SHD_SP_IN_ENABLED		BIT(1)
+#define RKISP1_CIF_MI_CTRL_SHD_JPEG_IN_ENABLED		BIT(2)
+#define RKISP1_CIF_MI_CTRL_SHD_RAW_IN_ENABLED		BIT(3)
+#define RKISP1_CIF_MI_CTRL_SHD_MP_OUT_ENABLED		BIT(16)
+#define RKISP1_CIF_MI_CTRL_SHD_SP_OUT_ENABLED		BIT(17)
+#define RKISP1_CIF_MI_CTRL_SHD_JPEG_OUT_ENABLED		BIT(18)
+#define RKISP1_CIF_MI_CTRL_SHD_RAW_OUT_ENABLED		BIT(19)
+
+/* RSZ_CTRL */
+#define RKISP1_CIF_RSZ_CTRL_SCALE_HY_ENABLE		BIT(0)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_HC_ENABLE		BIT(1)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_VY_ENABLE		BIT(2)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_VC_ENABLE		BIT(3)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_HY_UP			BIT(4)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_HC_UP			BIT(5)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_VY_UP			BIT(6)
+#define RKISP1_CIF_RSZ_CTRL_SCALE_VC_UP			BIT(7)
+#define RKISP1_CIF_RSZ_CTRL_CFG_UPD			BIT(8)
+#define RKISP1_CIF_RSZ_CTRL_CFG_UPD_AUTO		BIT(9)
+#define RKISP1_CIF_RSZ_SCALER_FACTOR			BIT(16)
+
+/* MI_IMSC - MI_MIS - MI_RIS - MI_ICR - MI_ISR */
+#define RKISP1_CIF_MI_FRAME(stream)			BIT((stream)->id)
+#define RKISP1_CIF_MI_MBLK_LINE				BIT(2)
+#define RKISP1_CIF_MI_FILL_MP_Y				BIT(3)
+#define RKISP1_CIF_MI_WRAP_MP_Y				BIT(4)
+#define RKISP1_CIF_MI_WRAP_MP_CB			BIT(5)
+#define RKISP1_CIF_MI_WRAP_MP_CR			BIT(6)
+#define RKISP1_CIF_MI_WRAP_SP_Y				BIT(7)
+#define RKISP1_CIF_MI_WRAP_SP_CB			BIT(8)
+#define RKISP1_CIF_MI_WRAP_SP_CR			BIT(9)
+#define RKISP1_CIF_MI_DMA_READY				BIT(11)
+
+/* MI_STATUS */
+#define RKISP1_CIF_MI_STATUS_MP_Y_FIFO_FULL		BIT(0)
+#define RKISP1_CIF_MI_STATUS_SP_Y_FIFO_FULL		BIT(4)
+
+/* MI_DMA_CTRL */
+#define RKISP1_CIF_MI_DMA_CTRL_BURST_LEN_LUM_16		(0 << 0)
+#define RKISP1_CIF_MI_DMA_CTRL_BURST_LEN_LUM_32		BIT(0)
+#define RKISP1_CIF_MI_DMA_CTRL_BURST_LEN_LUM_64		(2 << 0)
+#define RKISP1_CIF_MI_DMA_CTRL_BURST_LEN_CHROM_16	(0 << 2)
+#define RKISP1_CIF_MI_DMA_CTRL_BURST_LEN_CHROM_32	BIT(2)
+#define RKISP1_CIF_MI_DMA_CTRL_BURST_LEN_CHROM_64	(2 << 2)
+#define RKISP1_CIF_MI_DMA_CTRL_READ_FMT_PLANAR		(0 << 4)
+#define RKISP1_CIF_MI_DMA_CTRL_READ_FMT_SPLANAR		BIT(4)
+#define RKISP1_CIF_MI_DMA_CTRL_FMT_YUV400		(0 << 6)
+#define RKISP1_CIF_MI_DMA_CTRL_FMT_YUV420		BIT(6)
+#define RKISP1_CIF_MI_DMA_CTRL_READ_FMT_PACKED		(2 << 4)
+#define RKISP1_CIF_MI_DMA_CTRL_FMT_YUV422		(2 << 6)
+#define RKISP1_CIF_MI_DMA_CTRL_FMT_YUV444		(3 << 6)
+#define RKISP1_CIF_MI_DMA_CTRL_BYTE_SWAP		BIT(8)
+#define RKISP1_CIF_MI_DMA_CTRL_CONTINUOUS_ENA		BIT(9)
+#define RKISP1_CIF_MI_DMA_CTRL_RGB_BAYER_NO		(0 << 12)
+#define RKISP1_CIF_MI_DMA_CTRL_RGB_BAYER_8BIT		BIT(12)
+#define RKISP1_CIF_MI_DMA_CTRL_RGB_BAYER_16BIT		(2 << 12)
+/* MI_DMA_START */
+#define RKISP1_CIF_MI_DMA_START_ENABLE			BIT(0)
+/* MI_XTD_FORMAT_CTRL  */
+#define RKISP1_CIF_MI_XTD_FMT_CTRL_MP_CB_CR_SWAP	BIT(0)
+#define RKISP1_CIF_MI_XTD_FMT_CTRL_SP_CB_CR_SWAP	BIT(1)
+#define RKISP1_CIF_MI_XTD_FMT_CTRL_DMA_CB_CR_SWAP	BIT(2)
+
+/* CCL */
+#define RKISP1_CIF_CCL_CIF_CLK_DIS			BIT(2)
+/* ICCL */
+#define RKISP1_CIF_ICCL_ISP_CLK				BIT(0)
+#define RKISP1_CIF_ICCL_CP_CLK				BIT(1)
+#define RKISP1_CIF_ICCL_RES_2				BIT(2)
+#define RKISP1_CIF_ICCL_MRSZ_CLK			BIT(3)
+#define RKISP1_CIF_ICCL_SRSZ_CLK			BIT(4)
+#define RKISP1_CIF_ICCL_JPEG_CLK			BIT(5)
+#define RKISP1_CIF_ICCL_MI_CLK				BIT(6)
+#define RKISP1_CIF_ICCL_RES_7				BIT(7)
+#define RKISP1_CIF_ICCL_IE_CLK				BIT(8)
+#define RKISP1_CIF_ICCL_SIMP_CLK			BIT(9)
+#define RKISP1_CIF_ICCL_SMIA_CLK			BIT(10)
+#define RKISP1_CIF_ICCL_MIPI_CLK			BIT(11)
+#define RKISP1_CIF_ICCL_DCROP_CLK			BIT(12)
+/* IRCL */
+#define RKISP1_CIF_IRCL_ISP_SW_RST			BIT(0)
+#define RKISP1_CIF_IRCL_CP_SW_RST			BIT(1)
+#define RKISP1_CIF_IRCL_YCS_SW_RST			BIT(2)
+#define RKISP1_CIF_IRCL_MRSZ_SW_RST			BIT(3)
+#define RKISP1_CIF_IRCL_SRSZ_SW_RST			BIT(4)
+#define RKISP1_CIF_IRCL_JPEG_SW_RST			BIT(5)
+#define RKISP1_CIF_IRCL_MI_SW_RST			BIT(6)
+#define RKISP1_CIF_IRCL_CIF_SW_RST			BIT(7)
+#define RKISP1_CIF_IRCL_IE_SW_RST			BIT(8)
+#define RKISP1_CIF_IRCL_SI_SW_RST			BIT(9)
+#define RKISP1_CIF_IRCL_MIPI_SW_RST			BIT(11)
+
+/* C_PROC_CTR */
+#define RKISP1_CIF_C_PROC_CTR_ENABLE			BIT(0)
+#define RKISP1_CIF_C_PROC_YOUT_FULL			BIT(1)
+#define RKISP1_CIF_C_PROC_YIN_FULL			BIT(2)
+#define RKISP1_CIF_C_PROC_COUT_FULL			BIT(3)
+#define RKISP1_CIF_C_PROC_CTRL_RESERVED			0xFFFFFFFE
+#define RKISP1_CIF_C_PROC_CONTRAST_RESERVED		0xFFFFFF00
+#define RKISP1_CIF_C_PROC_BRIGHTNESS_RESERVED		0xFFFFFF00
+#define RKISP1_CIF_C_PROC_HUE_RESERVED			0xFFFFFF00
+#define RKISP1_CIF_C_PROC_SATURATION_RESERVED		0xFFFFFF00
+#define RKISP1_CIF_C_PROC_MACC_RESERVED			0xE000E000
+#define RKISP1_CIF_C_PROC_TONE_RESERVED			0xF000
+/* DUAL_CROP_CTRL */
+#define RKISP1_CIF_DUAL_CROP_MP_MODE_BYPASS		(0 << 0)
+#define RKISP1_CIF_DUAL_CROP_MP_MODE_YUV		BIT(0)
+#define RKISP1_CIF_DUAL_CROP_MP_MODE_RAW		(2 << 0)
+#define RKISP1_CIF_DUAL_CROP_SP_MODE_BYPASS		(0 << 2)
+#define RKISP1_CIF_DUAL_CROP_SP_MODE_YUV		BIT(2)
+#define RKISP1_CIF_DUAL_CROP_SP_MODE_RAW		(2 << 2)
+#define RKISP1_CIF_DUAL_CROP_CFG_UPD_PERMANENT		BIT(4)
+#define RKISP1_CIF_DUAL_CROP_CFG_UPD			BIT(5)
+#define RKISP1_CIF_DUAL_CROP_GEN_CFG_UPD		BIT(6)
+
+/* IMG_EFF_CTRL */
+#define RKISP1_CIF_IMG_EFF_CTRL_ENABLE			BIT(0)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_BLACKWHITE		(0 << 1)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_NEGATIVE		BIT(1)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_SEPIA		(2 << 1)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_COLOR_SEL		(3 << 1)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_EMBOSS		(4 << 1)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_SKETCH		(5 << 1)
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_SHARPEN		(6 << 1)
+#define RKISP1_CIF_IMG_EFF_CTRL_CFG_UPD			BIT(4)
+#define RKISP1_CIF_IMG_EFF_CTRL_YCBCR_FULL		BIT(5)
+
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_BLACKWHITE_SHIFT	0
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_NEGATIVE_SHIFT	1
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_SEPIA_SHIFT	2
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_COLOR_SEL_SHIFT	3
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_EMBOSS_SHIFT	4
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_SKETCH_SHIFT	5
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_SHARPEN_SHIFT	6
+#define RKISP1_CIF_IMG_EFF_CTRL_MODE_MASK		0xE
+
+/* IMG_EFF_COLOR_SEL */
+#define RKISP1_CIF_IMG_EFF_COLOR_RGB			0
+#define RKISP1_CIF_IMG_EFF_COLOR_B			BIT(0)
+#define RKISP1_CIF_IMG_EFF_COLOR_G			(2 << 0)
+#define RKISP1_CIF_IMG_EFF_COLOR_GB			(3 << 0)
+#define RKISP1_CIF_IMG_EFF_COLOR_R			(4 << 0)
+#define RKISP1_CIF_IMG_EFF_COLOR_RB			(5 << 0)
+#define RKISP1_CIF_IMG_EFF_COLOR_RG			(6 << 0)
+#define RKISP1_CIF_IMG_EFF_COLOR_RGB2			(7 << 0)
+
+/* MIPI_CTRL */
+#define RKISP1_CIF_MIPI_CTRL_OUTPUT_ENA			BIT(0)
+#define RKISP1_CIF_MIPI_CTRL_SHUTDOWNLANES(a)		(((a) & 0xF) << 8)
+#define RKISP1_CIF_MIPI_CTRL_NUM_LANES(a)		(((a) & 0x3) << 12)
+#define RKISP1_CIF_MIPI_CTRL_ERR_SOT_HS_SKIP		BIT(16)
+#define RKISP1_CIF_MIPI_CTRL_ERR_SOT_SYNC_HS_SKIP	BIT(17)
+#define RKISP1_CIF_MIPI_CTRL_CLOCKLANE_ENA		BIT(18)
+
+/* MIPI_DATA_SEL */
+#define RKISP1_CIF_MIPI_DATA_SEL_VC(a)			(((a) & 0x3) << 6)
+#define RKISP1_CIF_MIPI_DATA_SEL_DT(a)			(((a) & 0x3F) << 0)
+/* MIPI DATA_TYPE */
+#define RKISP1_CIF_CSI2_DT_YUV420_8b			0x18
+#define RKISP1_CIF_CSI2_DT_YUV420_10b			0x19
+#define RKISP1_CIF_CSI2_DT_YUV422_8b			0x1E
+#define RKISP1_CIF_CSI2_DT_YUV422_10b			0x1F
+#define RKISP1_CIF_CSI2_DT_RGB565			0x22
+#define RKISP1_CIF_CSI2_DT_RGB666			0x23
+#define RKISP1_CIF_CSI2_DT_RGB888			0x24
+#define RKISP1_CIF_CSI2_DT_RAW8				0x2A
+#define RKISP1_CIF_CSI2_DT_RAW10			0x2B
+#define RKISP1_CIF_CSI2_DT_RAW12			0x2C
+
+/* MIPI_IMSC, MIPI_RIS, MIPI_MIS, MIPI_ICR, MIPI_ISR */
+#define RKISP1_CIF_MIPI_SYNC_FIFO_OVFLW(a)		(((a) & 0xF) << 0)
+#define RKISP1_CIF_MIPI_ERR_SOT(a)			(((a) & 0xF) << 4)
+#define RKISP1_CIF_MIPI_ERR_SOT_SYNC(a)			(((a) & 0xF) << 8)
+#define RKISP1_CIF_MIPI_ERR_EOT_SYNC(a)			(((a) & 0xF) << 12)
+#define RKISP1_CIF_MIPI_ERR_CTRL(a)			(((a) & 0xF) << 16)
+#define RKISP1_CIF_MIPI_ERR_PROTOCOL			BIT(20)
+#define RKISP1_CIF_MIPI_ERR_ECC1			BIT(21)
+#define RKISP1_CIF_MIPI_ERR_ECC2			BIT(22)
+#define RKISP1_CIF_MIPI_ERR_CS				BIT(23)
+#define RKISP1_CIF_MIPI_FRAME_END			BIT(24)
+#define RKISP1_CIF_MIPI_ADD_DATA_OVFLW			BIT(25)
+#define RKISP1_CIF_MIPI_ADD_DATA_WATER_MARK		BIT(26)
+
+#define RKISP1_CIF_MIPI_ERR_CSI  (RKISP1_CIF_MIPI_ERR_PROTOCOL | \
+	RKISP1_CIF_MIPI_ERR_ECC1 | \
+	RKISP1_CIF_MIPI_ERR_ECC2 | \
+	RKISP1_CIF_MIPI_ERR_CS)
+
+#define RKISP1_CIF_MIPI_ERR_DPHY  (RKISP1_CIF_MIPI_ERR_SOT(3) | \
+	RKISP1_CIF_MIPI_ERR_SOT_SYNC(3) | \
+	RKISP1_CIF_MIPI_ERR_EOT_SYNC(3) | \
+	RKISP1_CIF_MIPI_ERR_CTRL(3))
+
+/* SUPER_IMPOSE */
+#define RKISP1_CIF_SUPER_IMP_CTRL_NORMAL_MODE		BIT(0)
+#define RKISP1_CIF_SUPER_IMP_CTRL_REF_IMG_MEM		BIT(1)
+#define RKISP1_CIF_SUPER_IMP_CTRL_TRANSP_DIS		BIT(2)
+
+/* ISP HISTOGRAM CALCULATION : ISP_HIST_PROP */
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_DIS		(0 << 0)
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_RGB		BIT(0)
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_RED		(2 << 0)
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_GREEN		(3 << 0)
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_BLUE		(4 << 0)
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_LUM		(5 << 0)
+#define RKISP1_CIF_ISP_HIST_PROP_MODE_MASK		0x7
+#define RKISP1_CIF_ISP_HIST_PREDIV_SET(x)		(((x) & 0x7F) << 3)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_SET(v0, v1, v2, v3)	\
+				     (((v0) & 0x1F) | (((v1) & 0x1F) << 8)  |\
+				     (((v2) & 0x1F) << 16) | \
+				     (((v3) & 0x1F) << 24))
+
+#define RKISP1_CIF_ISP_HIST_WINDOW_OFFSET_RESERVED	0xFFFFF000
+#define RKISP1_CIF_ISP_HIST_WINDOW_SIZE_RESERVED	0xFFFFF800
+#define RKISP1_CIF_ISP_HIST_WEIGHT_RESERVED		0xE0E0E0E0
+#define RKISP1_CIF_ISP_MAX_HIST_PREDIVIDER		0x0000007F
+#define RKISP1_CIF_ISP_HIST_ROW_NUM			5
+#define RKISP1_CIF_ISP_HIST_COLUMN_NUM			5
+
+/* AUTO FOCUS MEASUREMENT:  ISP_AFM_CTRL */
+#define RKISP1_ISP_AFM_CTRL_ENABLE			BIT(0)
+
+/* SHUTTER CONTROL */
+#define RKISP1_CIF_ISP_SH_CTRL_SH_ENA			BIT(0)
+#define RKISP1_CIF_ISP_SH_CTRL_REP_EN			BIT(1)
+#define RKISP1_CIF_ISP_SH_CTRL_SRC_SH_TRIG		BIT(2)
+#define RKISP1_CIF_ISP_SH_CTRL_EDGE_POS			BIT(3)
+#define RKISP1_CIF_ISP_SH_CTRL_POL_LOW			BIT(4)
+
+/* FLASH MODULE */
+/* ISP_FLASH_CMD */
+#define RKISP1_CIFFLASH_CMD_PRELIGHT_ON			BIT(0)
+#define RKISP1_CIFFLASH_CMD_FLASH_ON			BIT(1)
+#define RKISP1_CIFFLASH_CMD_PRE_FLASH_ON		BIT(2)
+/* ISP_FLASH_CONFIG */
+#define RKISP1_CIFFLASH_CONFIG_PRELIGHT_END		BIT(0)
+#define RKISP1_CIFFLASH_CONFIG_VSYNC_POS		BIT(1)
+#define RKISP1_CIFFLASH_CONFIG_PRELIGHT_LOW		BIT(2)
+#define RKISP1_CIFFLASH_CONFIG_SRC_FL_TRIG		BIT(3)
+#define RKISP1_CIFFLASH_CONFIG_DELAY(a)			(((a) & 0xF) << 4)
+
+/* Demosaic:  ISP_DEMOSAIC */
+#define RKISP1_CIF_ISP_DEMOSAIC_BYPASS			BIT(10)
+#define RKISP1_CIF_ISP_DEMOSAIC_TH(x)			((x) & 0xFF)
+
+/* AWB */
+/* ISP_AWB_PROP */
+#define RKISP1_CIF_ISP_AWB_YMAX_CMP_EN			BIT(2)
+#define RKISP1_CIF_ISP_AWB_YMAX_READ(x)			(((x) >> 2) & 1)
+#define RKISP1_CIF_ISP_AWB_MODE_RGB_EN			((1 << 31) | (0x2 << 0))
+#define RKISP1_CIF_ISP_AWB_MODE_YCBCR_EN		((0 << 31) | (0x2 << 0))
+#define RKISP1_CIF_ISP_AWB_MODE_YCBCR_EN		((0 << 31) | (0x2 << 0))
+#define RKISP1_CIF_ISP_AWB_MODE_MASK_NONE		0xFFFFFFFC
+#define RKISP1_CIF_ISP_AWB_MODE_READ(x)			((x) & 3)
+/* ISP_AWB_GAIN_RB, ISP_AWB_GAIN_G  */
+#define RKISP1_CIF_ISP_AWB_GAIN_R_SET(x)		(((x) & 0x3FF) << 16)
+#define RKISP1_CIF_ISP_AWB_GAIN_R_READ(x)		(((x) >> 16) & 0x3FF)
+#define RKISP1_CIF_ISP_AWB_GAIN_B_SET(x)		((x) & 0x3FFF)
+#define RKISP1_CIF_ISP_AWB_GAIN_B_READ(x)		((x) & 0x3FFF)
+/* ISP_AWB_REF */
+#define RKISP1_CIF_ISP_AWB_REF_CR_SET(x)		(((x) & 0xFF) << 8)
+#define RKISP1_CIF_ISP_AWB_REF_CR_READ(x)		(((x) >> 8) & 0xFF)
+#define RKISP1_CIF_ISP_AWB_REF_CB_READ(x)		((x) & 0xFF)
+/* ISP_AWB_THRESH */
+#define RKISP1_CIF_ISP_AWB_MAX_CS_SET(x)		(((x) & 0xFF) << 8)
+#define RKISP1_CIF_ISP_AWB_MAX_CS_READ(x)		(((x) >> 8) & 0xFF)
+#define RKISP1_CIF_ISP_AWB_MIN_C_READ(x)		((x) & 0xFF)
+#define RKISP1_CIF_ISP_AWB_MIN_Y_SET(x)			(((x) & 0xFF) << 16)
+#define RKISP1_CIF_ISP_AWB_MIN_Y_READ(x)		(((x) >> 16) & 0xFF)
+#define RKISP1_CIF_ISP_AWB_MAX_Y_SET(x)			(((x) & 0xFF) << 24)
+#define RKISP1_CIF_ISP_AWB_MAX_Y_READ(x)			(((x) >> 24) & 0xFF)
+/* ISP_AWB_MEAN */
+#define RKISP1_CIF_ISP_AWB_GET_MEAN_CR_R(x)		((x) & 0xFF)
+#define RKISP1_CIF_ISP_AWB_GET_MEAN_CB_B(x)		(((x) >> 8) & 0xFF)
+#define RKISP1_CIF_ISP_AWB_GET_MEAN_Y_G(x)		(((x) >> 16) & 0xFF)
+/* ISP_AWB_WHITE_CNT */
+#define RKISP1_CIF_ISP_AWB_GET_PIXEL_CNT(x)		((x) & 0x3FFFFFF)
+
+#define RKISP1_CIF_ISP_AWB_GAINS_MAX_VAL		0x000003FF
+#define RKISP1_CIF_ISP_AWB_WINDOW_OFFSET_MAX		0x00000FFF
+#define RKISP1_CIF_ISP_AWB_WINDOW_MAX_SIZE		0x00001FFF
+#define RKISP1_CIF_ISP_AWB_CBCR_MAX_REF			0x000000FF
+#define RKISP1_CIF_ISP_AWB_THRES_MAX_YC			0x000000FF
+
+/* AE */
+/* ISP_EXP_CTRL */
+#define RKISP1_CIF_ISP_EXP_ENA				BIT(0)
+#define RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP		BIT(1)
+/*
+ *'1' luminance calculation according to  Y=(R+G+B) x 0.332 (85/256)
+ *'0' luminance calculation according to Y=16+0.25R+0.5G+0.1094B
+ */
+#define RKISP1_CIF_ISP_EXP_CTRL_MEASMODE_1		BIT(31)
+
+/* ISP_EXP_H_SIZE */
+#define RKISP1_CIF_ISP_EXP_H_SIZE_SET(x)		((x) & 0x7FF)
+#define RKISP1_CIF_ISP_EXP_HEIGHT_MASK			0x000007FF
+/* ISP_EXP_V_SIZE : vertical size must be a multiple of 2). */
+#define RKISP1_CIF_ISP_EXP_V_SIZE_SET(x)		((x) & 0x7FE)
+
+/* ISP_EXP_H_OFFSET */
+#define RKISP1_CIF_ISP_EXP_H_OFFSET_SET(x)		((x) & 0x1FFF)
+#define RKISP1_CIF_ISP_EXP_MAX_HOFFS			2424
+/* ISP_EXP_V_OFFSET */
+#define RKISP1_CIF_ISP_EXP_V_OFFSET_SET(x)		((x) & 0x1FFF)
+#define RKISP1_CIF_ISP_EXP_MAX_VOFFS			1806
+
+#define RKISP1_CIF_ISP_EXP_ROW_NUM			5
+#define RKISP1_CIF_ISP_EXP_COLUMN_NUM			5
+#define RKISP1_CIF_ISP_EXP_NUM_LUMA_REGS \
+	(RKISP1_CIF_ISP_EXP_ROW_NUM * RKISP1_CIF_ISP_EXP_COLUMN_NUM)
+#define RKISP1_CIF_ISP_EXP_BLOCK_MAX_HSIZE		516
+#define RKISP1_CIF_ISP_EXP_BLOCK_MIN_HSIZE		35
+#define RKISP1_CIF_ISP_EXP_BLOCK_MAX_VSIZE		390
+#define RKISP1_CIF_ISP_EXP_BLOCK_MIN_VSIZE		28
+#define RKISP1_CIF_ISP_EXP_MAX_HSIZE	\
+	(RKISP1_CIF_ISP_EXP_BLOCK_MAX_HSIZE * RKISP1_CIF_ISP_EXP_COLUMN_NUM + 1)
+#define RKISP1_CIF_ISP_EXP_MIN_HSIZE	\
+	(RKISP1_CIF_ISP_EXP_BLOCK_MIN_HSIZE * RKISP1_CIF_ISP_EXP_COLUMN_NUM + 1)
+#define RKISP1_CIF_ISP_EXP_MAX_VSIZE	\
+	(RKISP1_CIF_ISP_EXP_BLOCK_MAX_VSIZE * RKISP1_CIF_ISP_EXP_ROW_NUM + 1)
+#define RKISP1_CIF_ISP_EXP_MIN_VSIZE	\
+	(RKISP1_CIF_ISP_EXP_BLOCK_MIN_VSIZE * RKISP1_CIF_ISP_EXP_ROW_NUM + 1)
+
+/* LSC: ISP_LSC_CTRL */
+#define RKISP1_CIF_ISP_LSC_CTRL_ENA			BIT(0)
+#define RKISP1_CIF_ISP_LSC_SECT_SIZE_RESERVED		0xFC00FC00
+#define RKISP1_CIF_ISP_LSC_GRAD_RESERVED		0xF000F000
+#define RKISP1_CIF_ISP_LSC_SAMPLE_RESERVED		0xF000F000
+#define RKISP1_CIF_ISP_LSC_SECTORS_MAX			17
+#define RKISP1_CIF_ISP_LSC_TABLE_DATA(v0, v1)     \
+	(((v0) & 0xFFF) | (((v1) & 0xFFF) << 12))
+#define RKISP1_CIF_ISP_LSC_SECT_SIZE(v0, v1)      \
+	(((v0) & 0xFFF) | (((v1) & 0xFFF) << 16))
+#define RKISP1_CIF_ISP_LSC_GRAD_SIZE(v0, v1)      \
+	(((v0) & 0xFFF) | (((v1) & 0xFFF) << 16))
+
+/* LSC: ISP_LSC_TABLE_SEL */
+#define RKISP1_CIF_ISP_LSC_TABLE_0			0
+#define RKISP1_CIF_ISP_LSC_TABLE_1			1
+
+/* LSC: ISP_LSC_STATUS */
+#define RKISP1_CIF_ISP_LSC_ACTIVE_TABLE			BIT(1)
+#define RKISP1_CIF_ISP_LSC_TABLE_ADDRESS_0		0
+#define RKISP1_CIF_ISP_LSC_TABLE_ADDRESS_153		153
+
+/* FLT */
+/* ISP_FILT_MODE */
+#define RKISP1_CIF_ISP_FLT_ENA				BIT(0)
+
+/*
+ * 0: green filter static mode (active filter factor = FILT_FAC_MID)
+ * 1: dynamic noise reduction/sharpen Default
+ */
+#define RKISP1_CIF_ISP_FLT_MODE_DNR			BIT(1)
+#define RKISP1_CIF_ISP_FLT_MODE_MAX			1
+#define RKISP1_CIF_ISP_FLT_CHROMA_V_MODE(x)		(((x) & 0x3) << 4)
+#define RKISP1_CIF_ISP_FLT_CHROMA_H_MODE(x)		(((x) & 0x3) << 6)
+#define RKISP1_CIF_ISP_FLT_CHROMA_MODE_MAX		3
+#define RKISP1_CIF_ISP_FLT_GREEN_STAGE1(x)		(((x) & 0xF) << 8)
+#define RKISP1_CIF_ISP_FLT_GREEN_STAGE1_MAX		8
+#define RKISP1_CIF_ISP_FLT_THREAD_RESERVED		0xFFFFFC00
+#define RKISP1_CIF_ISP_FLT_FAC_RESERVED			0xFFFFFFC0
+#define RKISP1_CIF_ISP_FLT_LUM_WEIGHT_RESERVED		0xFFF80000
+
+#define RKISP1_CIF_ISP_CTK_COEFF_RESERVED		0xFFFFF800
+#define RKISP1_CIF_ISP_XTALK_OFFSET_RESERVED		0xFFFFF000
+
+/* GOC */
+#define RKISP1_CIF_ISP_GAMMA_OUT_MODE_EQU		BIT(0)
+#define RKISP1_CIF_ISP_GOC_MODE_MAX			1
+#define RKISP1_CIF_ISP_GOC_RESERVED			0xFFFFF800
+/* ISP_CTRL BIT 11*/
+#define RKISP1_CIF_ISP_CTRL_ISP_GAMMA_OUT_ENA_READ(x)	(((x) >> 11) & 1)
+
+/* DPCC */
+/* ISP_DPCC_MODE */
+#define RKISP1_CIF_ISP_DPCC_ENA				BIT(0)
+#define RKISP1_CIF_ISP_DPCC_MODE_MAX			0x07
+#define RKISP1_CIF_ISP_DPCC_OUTPUTMODE_MAX		0x0F
+#define RKISP1_CIF_ISP_DPCC_SETUSE_MAX			0x0F
+#define RKISP1_CIF_ISP_DPCC_METHODS_SET_RESERVED	0xFFFFE000
+#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_RESERVED	0xFFFF0000
+#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_RESERVED	0xFFFFC0C0
+#define RKISP1_CIF_ISP_DPCC_PG_FAC_RESERVED		0xFFFFC0C0
+#define RKISP1_CIF_ISP_DPCC_RND_THRESH_RESERVED		0xFFFF0000
+#define RKISP1_CIF_ISP_DPCC_RG_FAC_RESERVED		0xFFFFC0C0
+#define RKISP1_CIF_ISP_DPCC_RO_LIMIT_RESERVED		0xFFFFF000
+#define RKISP1_CIF_ISP_DPCC_RND_OFFS_RESERVED		0xFFFFF000
+
+/* BLS */
+/* ISP_BLS_CTRL */
+#define RKISP1_CIF_ISP_BLS_ENA				BIT(0)
+#define RKISP1_CIF_ISP_BLS_MODE_MEASURED		BIT(1)
+#define RKISP1_CIF_ISP_BLS_MODE_FIXED			0
+#define RKISP1_CIF_ISP_BLS_WINDOW_1			BIT(2)
+#define RKISP1_CIF_ISP_BLS_WINDOW_2			(2 << 2)
+
+/* GAMMA-IN */
+#define RKISP1_CIFISP_DEGAMMA_X_RESERVED	\
+	((1 << 31) | (1 << 27) | (1 << 23) | (1 << 19) |\
+	(1 << 15) | (1 << 11) | (1 << 7) | (1 << 3))
+#define RKISP1_CIFISP_DEGAMMA_Y_RESERVED		0xFFFFF000
+
+/* AFM */
+#define RKISP1_CIF_ISP_AFM_ENA				BIT(0)
+#define RKISP1_CIF_ISP_AFM_THRES_RESERVED		0xFFFF0000
+#define RKISP1_CIF_ISP_AFM_VAR_SHIFT_RESERVED		0xFFF8FFF8
+#define RKISP1_CIF_ISP_AFM_WINDOW_X_RESERVED		0xE000
+#define RKISP1_CIF_ISP_AFM_WINDOW_Y_RESERVED		0xF000
+#define RKISP1_CIF_ISP_AFM_WINDOW_X_MIN			0x5
+#define RKISP1_CIF_ISP_AFM_WINDOW_Y_MIN			0x2
+#define RKISP1_CIF_ISP_AFM_WINDOW_X(x)			(((x) & 0x1FFF) << 16)
+#define RKISP1_CIF_ISP_AFM_WINDOW_Y(x)			((x) & 0x1FFF)
+
+/* DPF */
+#define RKISP1_CIF_ISP_DPF_MODE_EN			BIT(0)
+#define RKISP1_CIF_ISP_DPF_MODE_B_FLT_DIS		BIT(1)
+#define RKISP1_CIF_ISP_DPF_MODE_GB_FLT_DIS		BIT(2)
+#define RKISP1_CIF_ISP_DPF_MODE_GR_FLT_DIS		BIT(3)
+#define RKISP1_CIF_ISP_DPF_MODE_R_FLT_DIS		BIT(4)
+#define RKISP1_CIF_ISP_DPF_MODE_RB_FLTSIZE_9x9		BIT(5)
+#define RKISP1_CIF_ISP_DPF_MODE_NLL_SEGMENTATION	BIT(6)
+#define RKISP1_CIF_ISP_DPF_MODE_AWB_GAIN_COMP		BIT(7)
+#define RKISP1_CIF_ISP_DPF_MODE_LSC_GAIN_COMP		BIT(8)
+#define RKISP1_CIF_ISP_DPF_MODE_USE_NF_GAIN		BIT(9)
+#define RKISP1_CIF_ISP_DPF_NF_GAIN_RESERVED		0xFFFFF000
+#define RKISP1_CIF_ISP_DPF_SPATIAL_COEFF_MAX		0x1F
+#define RKISP1_CIF_ISP_DPF_NLL_COEFF_N_MAX		0x3FF
+
+/* =================================================================== */
+/*                            CIF Registers                            */
+/* =================================================================== */
+#define RKISP1_CIF_CTRL_BASE			0x00000000
+#define RKISP1_CIF_CCL				(RKISP1_CIF_CTRL_BASE + 0x00000000)
+#define RKISP1_CIF_VI_ID			(RKISP1_CIF_CTRL_BASE + 0x00000008)
+#define RKISP1_CIF_ICCL				(RKISP1_CIF_CTRL_BASE + 0x00000010)
+#define RKISP1_CIF_IRCL				(RKISP1_CIF_CTRL_BASE + 0x00000014)
+#define RKISP1_CIF_VI_DPCL			(RKISP1_CIF_CTRL_BASE + 0x00000018)
+
+#define RKISP1_CIF_IMG_EFF_BASE			0x00000200
+#define RKISP1_CIF_IMG_EFF_CTRL			(RKISP1_CIF_IMG_EFF_BASE + 0x00000000)
+#define RKISP1_CIF_IMG_EFF_COLOR_SEL		(RKISP1_CIF_IMG_EFF_BASE + 0x00000004)
+#define RKISP1_CIF_IMG_EFF_MAT_1		(RKISP1_CIF_IMG_EFF_BASE + 0x00000008)
+#define RKISP1_CIF_IMG_EFF_MAT_2		(RKISP1_CIF_IMG_EFF_BASE + 0x0000000C)
+#define RKISP1_CIF_IMG_EFF_MAT_3		(RKISP1_CIF_IMG_EFF_BASE + 0x00000010)
+#define RKISP1_CIF_IMG_EFF_MAT_4		(RKISP1_CIF_IMG_EFF_BASE + 0x00000014)
+#define RKISP1_CIF_IMG_EFF_MAT_5		(RKISP1_CIF_IMG_EFF_BASE + 0x00000018)
+#define RKISP1_CIF_IMG_EFF_TINT			(RKISP1_CIF_IMG_EFF_BASE + 0x0000001C)
+#define RKISP1_CIF_IMG_EFF_CTRL_SHD		(RKISP1_CIF_IMG_EFF_BASE + 0x00000020)
+#define RKISP1_CIF_IMG_EFF_SHARPEN		(RKISP1_CIF_IMG_EFF_BASE + 0x00000024)
+
+#define RKISP1_CIF_SUPER_IMP_BASE		0x00000300
+#define RKISP1_CIF_SUPER_IMP_CTRL		(RKISP1_CIF_SUPER_IMP_BASE + 0x00000000)
+#define RKISP1_CIF_SUPER_IMP_OFFSET_X		(RKISP1_CIF_SUPER_IMP_BASE + 0x00000004)
+#define RKISP1_CIF_SUPER_IMP_OFFSET_Y		(RKISP1_CIF_SUPER_IMP_BASE + 0x00000008)
+#define RKISP1_CIF_SUPER_IMP_COLOR_Y		(RKISP1_CIF_SUPER_IMP_BASE + 0x0000000C)
+#define RKISP1_CIF_SUPER_IMP_COLOR_CB		(RKISP1_CIF_SUPER_IMP_BASE + 0x00000010)
+#define RKISP1_CIF_SUPER_IMP_COLOR_CR		(RKISP1_CIF_SUPER_IMP_BASE + 0x00000014)
+
+#define RKISP1_CIF_ISP_BASE			0x00000400
+#define RKISP1_CIF_ISP_CTRL			(RKISP1_CIF_ISP_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_ACQ_PROP			(RKISP1_CIF_ISP_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_ACQ_H_OFFS		(RKISP1_CIF_ISP_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_ACQ_V_OFFS		(RKISP1_CIF_ISP_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_ACQ_H_SIZE		(RKISP1_CIF_ISP_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_ACQ_V_SIZE		(RKISP1_CIF_ISP_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_ACQ_NR_FRAMES		(RKISP1_CIF_ISP_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_GAMMA_DX_LO		(RKISP1_CIF_ISP_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_GAMMA_DX_HI		(RKISP1_CIF_ISP_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_GAMMA_R_Y0		(RKISP1_CIF_ISP_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_GAMMA_R_Y1		(RKISP1_CIF_ISP_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_GAMMA_R_Y2		(RKISP1_CIF_ISP_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_GAMMA_R_Y3		(RKISP1_CIF_ISP_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_GAMMA_R_Y4		(RKISP1_CIF_ISP_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_GAMMA_R_Y5		(RKISP1_CIF_ISP_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_GAMMA_R_Y6		(RKISP1_CIF_ISP_BASE + 0x0000003C)
+#define RKISP1_CIF_ISP_GAMMA_R_Y7		(RKISP1_CIF_ISP_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_GAMMA_R_Y8		(RKISP1_CIF_ISP_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_GAMMA_R_Y9		(RKISP1_CIF_ISP_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_GAMMA_R_Y10		(RKISP1_CIF_ISP_BASE + 0x0000004C)
+#define RKISP1_CIF_ISP_GAMMA_R_Y11		(RKISP1_CIF_ISP_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_GAMMA_R_Y12		(RKISP1_CIF_ISP_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_GAMMA_R_Y13		(RKISP1_CIF_ISP_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_GAMMA_R_Y14		(RKISP1_CIF_ISP_BASE + 0x0000005C)
+#define RKISP1_CIF_ISP_GAMMA_R_Y15		(RKISP1_CIF_ISP_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_GAMMA_R_Y16		(RKISP1_CIF_ISP_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_GAMMA_G_Y0		(RKISP1_CIF_ISP_BASE + 0x00000068)
+#define RKISP1_CIF_ISP_GAMMA_G_Y1		(RKISP1_CIF_ISP_BASE + 0x0000006C)
+#define RKISP1_CIF_ISP_GAMMA_G_Y2		(RKISP1_CIF_ISP_BASE + 0x00000070)
+#define RKISP1_CIF_ISP_GAMMA_G_Y3		(RKISP1_CIF_ISP_BASE + 0x00000074)
+#define RKISP1_CIF_ISP_GAMMA_G_Y4		(RKISP1_CIF_ISP_BASE + 0x00000078)
+#define RKISP1_CIF_ISP_GAMMA_G_Y5		(RKISP1_CIF_ISP_BASE + 0x0000007C)
+#define RKISP1_CIF_ISP_GAMMA_G_Y6		(RKISP1_CIF_ISP_BASE + 0x00000080)
+#define RKISP1_CIF_ISP_GAMMA_G_Y7		(RKISP1_CIF_ISP_BASE + 0x00000084)
+#define RKISP1_CIF_ISP_GAMMA_G_Y8		(RKISP1_CIF_ISP_BASE + 0x00000088)
+#define RKISP1_CIF_ISP_GAMMA_G_Y9		(RKISP1_CIF_ISP_BASE + 0x0000008C)
+#define RKISP1_CIF_ISP_GAMMA_G_Y10		(RKISP1_CIF_ISP_BASE + 0x00000090)
+#define RKISP1_CIF_ISP_GAMMA_G_Y11		(RKISP1_CIF_ISP_BASE + 0x00000094)
+#define RKISP1_CIF_ISP_GAMMA_G_Y12		(RKISP1_CIF_ISP_BASE + 0x00000098)
+#define RKISP1_CIF_ISP_GAMMA_G_Y13		(RKISP1_CIF_ISP_BASE + 0x0000009C)
+#define RKISP1_CIF_ISP_GAMMA_G_Y14		(RKISP1_CIF_ISP_BASE + 0x000000A0)
+#define RKISP1_CIF_ISP_GAMMA_G_Y15		(RKISP1_CIF_ISP_BASE + 0x000000A4)
+#define RKISP1_CIF_ISP_GAMMA_G_Y16		(RKISP1_CIF_ISP_BASE + 0x000000A8)
+#define RKISP1_CIF_ISP_GAMMA_B_Y0		(RKISP1_CIF_ISP_BASE + 0x000000AC)
+#define RKISP1_CIF_ISP_GAMMA_B_Y1		(RKISP1_CIF_ISP_BASE + 0x000000B0)
+#define RKISP1_CIF_ISP_GAMMA_B_Y2		(RKISP1_CIF_ISP_BASE + 0x000000B4)
+#define RKISP1_CIF_ISP_GAMMA_B_Y3		(RKISP1_CIF_ISP_BASE + 0x000000B8)
+#define RKISP1_CIF_ISP_GAMMA_B_Y4		(RKISP1_CIF_ISP_BASE + 0x000000BC)
+#define RKISP1_CIF_ISP_GAMMA_B_Y5		(RKISP1_CIF_ISP_BASE + 0x000000C0)
+#define RKISP1_CIF_ISP_GAMMA_B_Y6		(RKISP1_CIF_ISP_BASE + 0x000000C4)
+#define RKISP1_CIF_ISP_GAMMA_B_Y7		(RKISP1_CIF_ISP_BASE + 0x000000C8)
+#define RKISP1_CIF_ISP_GAMMA_B_Y8		(RKISP1_CIF_ISP_BASE + 0x000000CC)
+#define RKISP1_CIF_ISP_GAMMA_B_Y9		(RKISP1_CIF_ISP_BASE + 0x000000D0)
+#define RKISP1_CIF_ISP_GAMMA_B_Y10		(RKISP1_CIF_ISP_BASE + 0x000000D4)
+#define RKISP1_CIF_ISP_GAMMA_B_Y11		(RKISP1_CIF_ISP_BASE + 0x000000D8)
+#define RKISP1_CIF_ISP_GAMMA_B_Y12		(RKISP1_CIF_ISP_BASE + 0x000000DC)
+#define RKISP1_CIF_ISP_GAMMA_B_Y13		(RKISP1_CIF_ISP_BASE + 0x000000E0)
+#define RKISP1_CIF_ISP_GAMMA_B_Y14		(RKISP1_CIF_ISP_BASE + 0x000000E4)
+#define RKISP1_CIF_ISP_GAMMA_B_Y15		(RKISP1_CIF_ISP_BASE + 0x000000E8)
+#define RKISP1_CIF_ISP_GAMMA_B_Y16		(RKISP1_CIF_ISP_BASE + 0x000000EC)
+#define RKISP1_CIF_ISP_AWB_PROP			(RKISP1_CIF_ISP_BASE + 0x00000110)
+#define RKISP1_CIF_ISP_AWB_WND_H_OFFS		(RKISP1_CIF_ISP_BASE + 0x00000114)
+#define RKISP1_CIF_ISP_AWB_WND_V_OFFS		(RKISP1_CIF_ISP_BASE + 0x00000118)
+#define RKISP1_CIF_ISP_AWB_WND_H_SIZE		(RKISP1_CIF_ISP_BASE + 0x0000011C)
+#define RKISP1_CIF_ISP_AWB_WND_V_SIZE		(RKISP1_CIF_ISP_BASE + 0x00000120)
+#define RKISP1_CIF_ISP_AWB_FRAMES		(RKISP1_CIF_ISP_BASE + 0x00000124)
+#define RKISP1_CIF_ISP_AWB_REF			(RKISP1_CIF_ISP_BASE + 0x00000128)
+#define RKISP1_CIF_ISP_AWB_THRESH		(RKISP1_CIF_ISP_BASE + 0x0000012C)
+#define RKISP1_CIF_ISP_AWB_GAIN_G		(RKISP1_CIF_ISP_BASE + 0x00000138)
+#define RKISP1_CIF_ISP_AWB_GAIN_RB		(RKISP1_CIF_ISP_BASE + 0x0000013C)
+#define RKISP1_CIF_ISP_AWB_WHITE_CNT		(RKISP1_CIF_ISP_BASE + 0x00000140)
+#define RKISP1_CIF_ISP_AWB_MEAN			(RKISP1_CIF_ISP_BASE + 0x00000144)
+#define RKISP1_CIF_ISP_CC_COEFF_0		(RKISP1_CIF_ISP_BASE + 0x00000170)
+#define RKISP1_CIF_ISP_CC_COEFF_1		(RKISP1_CIF_ISP_BASE + 0x00000174)
+#define RKISP1_CIF_ISP_CC_COEFF_2		(RKISP1_CIF_ISP_BASE + 0x00000178)
+#define RKISP1_CIF_ISP_CC_COEFF_3		(RKISP1_CIF_ISP_BASE + 0x0000017C)
+#define RKISP1_CIF_ISP_CC_COEFF_4		(RKISP1_CIF_ISP_BASE + 0x00000180)
+#define RKISP1_CIF_ISP_CC_COEFF_5		(RKISP1_CIF_ISP_BASE + 0x00000184)
+#define RKISP1_CIF_ISP_CC_COEFF_6		(RKISP1_CIF_ISP_BASE + 0x00000188)
+#define RKISP1_CIF_ISP_CC_COEFF_7		(RKISP1_CIF_ISP_BASE + 0x0000018C)
+#define RKISP1_CIF_ISP_CC_COEFF_8		(RKISP1_CIF_ISP_BASE + 0x00000190)
+#define RKISP1_CIF_ISP_OUT_H_OFFS		(RKISP1_CIF_ISP_BASE + 0x00000194)
+#define RKISP1_CIF_ISP_OUT_V_OFFS		(RKISP1_CIF_ISP_BASE + 0x00000198)
+#define RKISP1_CIF_ISP_OUT_H_SIZE		(RKISP1_CIF_ISP_BASE + 0x0000019C)
+#define RKISP1_CIF_ISP_OUT_V_SIZE		(RKISP1_CIF_ISP_BASE + 0x000001A0)
+#define RKISP1_CIF_ISP_DEMOSAIC			(RKISP1_CIF_ISP_BASE + 0x000001A4)
+#define RKISP1_CIF_ISP_FLAGS_SHD		(RKISP1_CIF_ISP_BASE + 0x000001A8)
+#define RKISP1_CIF_ISP_OUT_H_OFFS_SHD		(RKISP1_CIF_ISP_BASE + 0x000001AC)
+#define RKISP1_CIF_ISP_OUT_V_OFFS_SHD		(RKISP1_CIF_ISP_BASE + 0x000001B0)
+#define RKISP1_CIF_ISP_OUT_H_SIZE_SHD		(RKISP1_CIF_ISP_BASE + 0x000001B4)
+#define RKISP1_CIF_ISP_OUT_V_SIZE_SHD		(RKISP1_CIF_ISP_BASE + 0x000001B8)
+#define RKISP1_CIF_ISP_IMSC			(RKISP1_CIF_ISP_BASE + 0x000001BC)
+#define RKISP1_CIF_ISP_RIS			(RKISP1_CIF_ISP_BASE + 0x000001C0)
+#define RKISP1_CIF_ISP_MIS			(RKISP1_CIF_ISP_BASE + 0x000001C4)
+#define RKISP1_CIF_ISP_ICR			(RKISP1_CIF_ISP_BASE + 0x000001C8)
+#define RKISP1_CIF_ISP_ISR			(RKISP1_CIF_ISP_BASE + 0x000001CC)
+#define RKISP1_CIF_ISP_CT_COEFF_0		(RKISP1_CIF_ISP_BASE + 0x000001D0)
+#define RKISP1_CIF_ISP_CT_COEFF_1		(RKISP1_CIF_ISP_BASE + 0x000001D4)
+#define RKISP1_CIF_ISP_CT_COEFF_2		(RKISP1_CIF_ISP_BASE + 0x000001D8)
+#define RKISP1_CIF_ISP_CT_COEFF_3		(RKISP1_CIF_ISP_BASE + 0x000001DC)
+#define RKISP1_CIF_ISP_CT_COEFF_4		(RKISP1_CIF_ISP_BASE + 0x000001E0)
+#define RKISP1_CIF_ISP_CT_COEFF_5		(RKISP1_CIF_ISP_BASE + 0x000001E4)
+#define RKISP1_CIF_ISP_CT_COEFF_6		(RKISP1_CIF_ISP_BASE + 0x000001E8)
+#define RKISP1_CIF_ISP_CT_COEFF_7		(RKISP1_CIF_ISP_BASE + 0x000001EC)
+#define RKISP1_CIF_ISP_CT_COEFF_8		(RKISP1_CIF_ISP_BASE + 0x000001F0)
+#define RKISP1_CIF_ISP_GAMMA_OUT_MODE		(RKISP1_CIF_ISP_BASE + 0x000001F4)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_0		(RKISP1_CIF_ISP_BASE + 0x000001F8)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_1		(RKISP1_CIF_ISP_BASE + 0x000001FC)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_2		(RKISP1_CIF_ISP_BASE + 0x00000200)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_3		(RKISP1_CIF_ISP_BASE + 0x00000204)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_4		(RKISP1_CIF_ISP_BASE + 0x00000208)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_5		(RKISP1_CIF_ISP_BASE + 0x0000020C)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_6		(RKISP1_CIF_ISP_BASE + 0x00000210)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_7		(RKISP1_CIF_ISP_BASE + 0x00000214)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_8		(RKISP1_CIF_ISP_BASE + 0x00000218)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_9		(RKISP1_CIF_ISP_BASE + 0x0000021C)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_10		(RKISP1_CIF_ISP_BASE + 0x00000220)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_11		(RKISP1_CIF_ISP_BASE + 0x00000224)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_12		(RKISP1_CIF_ISP_BASE + 0x00000228)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_13		(RKISP1_CIF_ISP_BASE + 0x0000022C)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_14		(RKISP1_CIF_ISP_BASE + 0x00000230)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_15		(RKISP1_CIF_ISP_BASE + 0x00000234)
+#define RKISP1_CIF_ISP_GAMMA_OUT_Y_16		(RKISP1_CIF_ISP_BASE + 0x00000238)
+#define RKISP1_CIF_ISP_ERR			(RKISP1_CIF_ISP_BASE + 0x0000023C)
+#define RKISP1_CIF_ISP_ERR_CLR			(RKISP1_CIF_ISP_BASE + 0x00000240)
+#define RKISP1_CIF_ISP_FRAME_COUNT		(RKISP1_CIF_ISP_BASE + 0x00000244)
+#define RKISP1_CIF_ISP_CT_OFFSET_R		(RKISP1_CIF_ISP_BASE + 0x00000248)
+#define RKISP1_CIF_ISP_CT_OFFSET_G		(RKISP1_CIF_ISP_BASE + 0x0000024C)
+#define RKISP1_CIF_ISP_CT_OFFSET_B		(RKISP1_CIF_ISP_BASE + 0x00000250)
+
+#define RKISP1_CIF_ISP_FLASH_BASE		0x00000660
+#define RKISP1_CIF_ISP_FLASH_CMD		(RKISP1_CIF_ISP_FLASH_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_FLASH_CONFIG		(RKISP1_CIF_ISP_FLASH_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_FLASH_PREDIV		(RKISP1_CIF_ISP_FLASH_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_FLASH_DELAY		(RKISP1_CIF_ISP_FLASH_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_FLASH_TIME		(RKISP1_CIF_ISP_FLASH_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_FLASH_MAXP		(RKISP1_CIF_ISP_FLASH_BASE + 0x00000014)
+
+#define RKISP1_CIF_ISP_SH_BASE			0x00000680
+#define RKISP1_CIF_ISP_SH_CTRL			(RKISP1_CIF_ISP_SH_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_SH_PREDIV		(RKISP1_CIF_ISP_SH_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_SH_DELAY			(RKISP1_CIF_ISP_SH_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_SH_TIME			(RKISP1_CIF_ISP_SH_BASE + 0x0000000C)
+
+#define RKISP1_CIF_C_PROC_BASE			0x00000800
+#define RKISP1_CIF_C_PROC_CTRL			(RKISP1_CIF_C_PROC_BASE + 0x00000000)
+#define RKISP1_CIF_C_PROC_CONTRAST		(RKISP1_CIF_C_PROC_BASE + 0x00000004)
+#define RKISP1_CIF_C_PROC_BRIGHTNESS		(RKISP1_CIF_C_PROC_BASE + 0x00000008)
+#define RKISP1_CIF_C_PROC_SATURATION		(RKISP1_CIF_C_PROC_BASE + 0x0000000C)
+#define RKISP1_CIF_C_PROC_HUE			(RKISP1_CIF_C_PROC_BASE + 0x00000010)
+
+#define RKISP1_CIF_DUAL_CROP_BASE		0x00000880
+#define RKISP1_CIF_DUAL_CROP_CTRL		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000000)
+#define RKISP1_CIF_DUAL_CROP_M_H_OFFS		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000004)
+#define RKISP1_CIF_DUAL_CROP_M_V_OFFS		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000008)
+#define RKISP1_CIF_DUAL_CROP_M_H_SIZE		(RKISP1_CIF_DUAL_CROP_BASE + 0x0000000C)
+#define RKISP1_CIF_DUAL_CROP_M_V_SIZE		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000010)
+#define RKISP1_CIF_DUAL_CROP_S_H_OFFS		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000014)
+#define RKISP1_CIF_DUAL_CROP_S_V_OFFS		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000018)
+#define RKISP1_CIF_DUAL_CROP_S_H_SIZE		(RKISP1_CIF_DUAL_CROP_BASE + 0x0000001C)
+#define RKISP1_CIF_DUAL_CROP_S_V_SIZE		(RKISP1_CIF_DUAL_CROP_BASE + 0x00000020)
+#define RKISP1_CIF_DUAL_CROP_M_H_OFFS_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x00000024)
+#define RKISP1_CIF_DUAL_CROP_M_V_OFFS_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x00000028)
+#define RKISP1_CIF_DUAL_CROP_M_H_SIZE_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x0000002C)
+#define RKISP1_CIF_DUAL_CROP_M_V_SIZE_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x00000030)
+#define RKISP1_CIF_DUAL_CROP_S_H_OFFS_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x00000034)
+#define RKISP1_CIF_DUAL_CROP_S_V_OFFS_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x00000038)
+#define RKISP1_CIF_DUAL_CROP_S_H_SIZE_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x0000003C)
+#define RKISP1_CIF_DUAL_CROP_S_V_SIZE_SHD	(RKISP1_CIF_DUAL_CROP_BASE + 0x00000040)
+
+#define RKISP1_CIF_MRSZ_BASE			0x00000C00
+#define RKISP1_CIF_MRSZ_CTRL			(RKISP1_CIF_MRSZ_BASE + 0x00000000)
+#define RKISP1_CIF_MRSZ_SCALE_HY		(RKISP1_CIF_MRSZ_BASE + 0x00000004)
+#define RKISP1_CIF_MRSZ_SCALE_HCB		(RKISP1_CIF_MRSZ_BASE + 0x00000008)
+#define RKISP1_CIF_MRSZ_SCALE_HCR		(RKISP1_CIF_MRSZ_BASE + 0x0000000C)
+#define RKISP1_CIF_MRSZ_SCALE_VY		(RKISP1_CIF_MRSZ_BASE + 0x00000010)
+#define RKISP1_CIF_MRSZ_SCALE_VC		(RKISP1_CIF_MRSZ_BASE + 0x00000014)
+#define RKISP1_CIF_MRSZ_PHASE_HY		(RKISP1_CIF_MRSZ_BASE + 0x00000018)
+#define RKISP1_CIF_MRSZ_PHASE_HC		(RKISP1_CIF_MRSZ_BASE + 0x0000001C)
+#define RKISP1_CIF_MRSZ_PHASE_VY		(RKISP1_CIF_MRSZ_BASE + 0x00000020)
+#define RKISP1_CIF_MRSZ_PHASE_VC		(RKISP1_CIF_MRSZ_BASE + 0x00000024)
+#define RKISP1_CIF_MRSZ_SCALE_LUT_ADDR		(RKISP1_CIF_MRSZ_BASE + 0x00000028)
+#define RKISP1_CIF_MRSZ_SCALE_LUT		(RKISP1_CIF_MRSZ_BASE + 0x0000002C)
+#define RKISP1_CIF_MRSZ_CTRL_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000030)
+#define RKISP1_CIF_MRSZ_SCALE_HY_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000034)
+#define RKISP1_CIF_MRSZ_SCALE_HCB_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000038)
+#define RKISP1_CIF_MRSZ_SCALE_HCR_SHD		(RKISP1_CIF_MRSZ_BASE + 0x0000003C)
+#define RKISP1_CIF_MRSZ_SCALE_VY_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000040)
+#define RKISP1_CIF_MRSZ_SCALE_VC_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000044)
+#define RKISP1_CIF_MRSZ_PHASE_HY_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000048)
+#define RKISP1_CIF_MRSZ_PHASE_HC_SHD		(RKISP1_CIF_MRSZ_BASE + 0x0000004C)
+#define RKISP1_CIF_MRSZ_PHASE_VY_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000050)
+#define RKISP1_CIF_MRSZ_PHASE_VC_SHD		(RKISP1_CIF_MRSZ_BASE + 0x00000054)
+
+#define RKISP1_CIF_SRSZ_BASE			0x00001000
+#define RKISP1_CIF_SRSZ_CTRL			(RKISP1_CIF_SRSZ_BASE + 0x00000000)
+#define RKISP1_CIF_SRSZ_SCALE_HY		(RKISP1_CIF_SRSZ_BASE + 0x00000004)
+#define RKISP1_CIF_SRSZ_SCALE_HCB		(RKISP1_CIF_SRSZ_BASE + 0x00000008)
+#define RKISP1_CIF_SRSZ_SCALE_HCR		(RKISP1_CIF_SRSZ_BASE + 0x0000000C)
+#define RKISP1_CIF_SRSZ_SCALE_VY		(RKISP1_CIF_SRSZ_BASE + 0x00000010)
+#define RKISP1_CIF_SRSZ_SCALE_VC		(RKISP1_CIF_SRSZ_BASE + 0x00000014)
+#define RKISP1_CIF_SRSZ_PHASE_HY		(RKISP1_CIF_SRSZ_BASE + 0x00000018)
+#define RKISP1_CIF_SRSZ_PHASE_HC		(RKISP1_CIF_SRSZ_BASE + 0x0000001C)
+#define RKISP1_CIF_SRSZ_PHASE_VY		(RKISP1_CIF_SRSZ_BASE + 0x00000020)
+#define RKISP1_CIF_SRSZ_PHASE_VC		(RKISP1_CIF_SRSZ_BASE + 0x00000024)
+#define RKISP1_CIF_SRSZ_SCALE_LUT_ADDR		(RKISP1_CIF_SRSZ_BASE + 0x00000028)
+#define RKISP1_CIF_SRSZ_SCALE_LUT		(RKISP1_CIF_SRSZ_BASE + 0x0000002C)
+#define RKISP1_CIF_SRSZ_CTRL_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000030)
+#define RKISP1_CIF_SRSZ_SCALE_HY_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000034)
+#define RKISP1_CIF_SRSZ_SCALE_HCB_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000038)
+#define RKISP1_CIF_SRSZ_SCALE_HCR_SHD		(RKISP1_CIF_SRSZ_BASE + 0x0000003C)
+#define RKISP1_CIF_SRSZ_SCALE_VY_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000040)
+#define RKISP1_CIF_SRSZ_SCALE_VC_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000044)
+#define RKISP1_CIF_SRSZ_PHASE_HY_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000048)
+#define RKISP1_CIF_SRSZ_PHASE_HC_SHD		(RKISP1_CIF_SRSZ_BASE + 0x0000004C)
+#define RKISP1_CIF_SRSZ_PHASE_VY_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000050)
+#define RKISP1_CIF_SRSZ_PHASE_VC_SHD		(RKISP1_CIF_SRSZ_BASE + 0x00000054)
+
+#define RKISP1_CIF_MI_BASE			0x00001400
+#define RKISP1_CIF_MI_CTRL			(RKISP1_CIF_MI_BASE + 0x00000000)
+#define RKISP1_CIF_MI_INIT			(RKISP1_CIF_MI_BASE + 0x00000004)
+#define RKISP1_CIF_MI_MP_Y_BASE_AD_INIT		(RKISP1_CIF_MI_BASE + 0x00000008)
+#define RKISP1_CIF_MI_MP_Y_SIZE_INIT		(RKISP1_CIF_MI_BASE + 0x0000000C)
+#define RKISP1_CIF_MI_MP_Y_OFFS_CNT_INIT	(RKISP1_CIF_MI_BASE + 0x00000010)
+#define RKISP1_CIF_MI_MP_Y_OFFS_CNT_START	(RKISP1_CIF_MI_BASE + 0x00000014)
+#define RKISP1_CIF_MI_MP_Y_IRQ_OFFS_INIT	(RKISP1_CIF_MI_BASE + 0x00000018)
+#define RKISP1_CIF_MI_MP_CB_BASE_AD_INIT	(RKISP1_CIF_MI_BASE + 0x0000001C)
+#define RKISP1_CIF_MI_MP_CB_SIZE_INIT		(RKISP1_CIF_MI_BASE + 0x00000020)
+#define RKISP1_CIF_MI_MP_CB_OFFS_CNT_INIT	(RKISP1_CIF_MI_BASE + 0x00000024)
+#define RKISP1_CIF_MI_MP_CB_OFFS_CNT_START	(RKISP1_CIF_MI_BASE + 0x00000028)
+#define RKISP1_CIF_MI_MP_CR_BASE_AD_INIT	(RKISP1_CIF_MI_BASE + 0x0000002C)
+#define RKISP1_CIF_MI_MP_CR_SIZE_INIT		(RKISP1_CIF_MI_BASE + 0x00000030)
+#define RKISP1_CIF_MI_MP_CR_OFFS_CNT_INIT	(RKISP1_CIF_MI_BASE + 0x00000034)
+#define RKISP1_CIF_MI_MP_CR_OFFS_CNT_START	(RKISP1_CIF_MI_BASE + 0x00000038)
+#define RKISP1_CIF_MI_SP_Y_BASE_AD_INIT		(RKISP1_CIF_MI_BASE + 0x0000003C)
+#define RKISP1_CIF_MI_SP_Y_SIZE_INIT		(RKISP1_CIF_MI_BASE + 0x00000040)
+#define RKISP1_CIF_MI_SP_Y_OFFS_CNT_INIT	(RKISP1_CIF_MI_BASE + 0x00000044)
+#define RKISP1_CIF_MI_SP_Y_OFFS_CNT_START	(RKISP1_CIF_MI_BASE + 0x00000048)
+#define RKISP1_CIF_MI_SP_Y_LLENGTH		(RKISP1_CIF_MI_BASE + 0x0000004C)
+#define RKISP1_CIF_MI_SP_CB_BASE_AD_INIT	(RKISP1_CIF_MI_BASE + 0x00000050)
+#define RKISP1_CIF_MI_SP_CB_SIZE_INIT		(RKISP1_CIF_MI_BASE + 0x00000054)
+#define RKISP1_CIF_MI_SP_CB_OFFS_CNT_INIT	(RKISP1_CIF_MI_BASE + 0x00000058)
+#define RKISP1_CIF_MI_SP_CB_OFFS_CNT_START	(RKISP1_CIF_MI_BASE + 0x0000005C)
+#define RKISP1_CIF_MI_SP_CR_BASE_AD_INIT	(RKISP1_CIF_MI_BASE + 0x00000060)
+#define RKISP1_CIF_MI_SP_CR_SIZE_INIT		(RKISP1_CIF_MI_BASE + 0x00000064)
+#define RKISP1_CIF_MI_SP_CR_OFFS_CNT_INIT	(RKISP1_CIF_MI_BASE + 0x00000068)
+#define RKISP1_CIF_MI_SP_CR_OFFS_CNT_START	(RKISP1_CIF_MI_BASE + 0x0000006C)
+#define RKISP1_CIF_MI_BYTE_CNT			(RKISP1_CIF_MI_BASE + 0x00000070)
+#define RKISP1_CIF_MI_CTRL_SHD			(RKISP1_CIF_MI_BASE + 0x00000074)
+#define RKISP1_CIF_MI_MP_Y_BASE_AD_SHD		(RKISP1_CIF_MI_BASE + 0x00000078)
+#define RKISP1_CIF_MI_MP_Y_SIZE_SHD		(RKISP1_CIF_MI_BASE + 0x0000007C)
+#define RKISP1_CIF_MI_MP_Y_OFFS_CNT_SHD		(RKISP1_CIF_MI_BASE + 0x00000080)
+#define RKISP1_CIF_MI_MP_Y_IRQ_OFFS_SHD		(RKISP1_CIF_MI_BASE + 0x00000084)
+#define RKISP1_CIF_MI_MP_CB_BASE_AD_SHD		(RKISP1_CIF_MI_BASE + 0x00000088)
+#define RKISP1_CIF_MI_MP_CB_SIZE_SHD		(RKISP1_CIF_MI_BASE + 0x0000008C)
+#define RKISP1_CIF_MI_MP_CB_OFFS_CNT_SHD	(RKISP1_CIF_MI_BASE + 0x00000090)
+#define RKISP1_CIF_MI_MP_CR_BASE_AD_SHD		(RKISP1_CIF_MI_BASE + 0x00000094)
+#define RKISP1_CIF_MI_MP_CR_SIZE_SHD		(RKISP1_CIF_MI_BASE + 0x00000098)
+#define RKISP1_CIF_MI_MP_CR_OFFS_CNT_SHD	(RKISP1_CIF_MI_BASE + 0x0000009C)
+#define RKISP1_CIF_MI_SP_Y_BASE_AD_SHD		(RKISP1_CIF_MI_BASE + 0x000000A0)
+#define RKISP1_CIF_MI_SP_Y_SIZE_SHD		(RKISP1_CIF_MI_BASE + 0x000000A4)
+#define RKISP1_CIF_MI_SP_Y_OFFS_CNT_SHD		(RKISP1_CIF_MI_BASE + 0x000000A8)
+#define RKISP1_CIF_MI_SP_CB_BASE_AD_SHD		(RKISP1_CIF_MI_BASE + 0x000000B0)
+#define RKISP1_CIF_MI_SP_CB_SIZE_SHD		(RKISP1_CIF_MI_BASE + 0x000000B4)
+#define RKISP1_CIF_MI_SP_CB_OFFS_CNT_SHD	(RKISP1_CIF_MI_BASE + 0x000000B8)
+#define RKISP1_CIF_MI_SP_CR_BASE_AD_SHD		(RKISP1_CIF_MI_BASE + 0x000000BC)
+#define RKISP1_CIF_MI_SP_CR_SIZE_SHD		(RKISP1_CIF_MI_BASE + 0x000000C0)
+#define RKISP1_CIF_MI_SP_CR_OFFS_CNT_SHD	(RKISP1_CIF_MI_BASE + 0x000000C4)
+#define RKISP1_CIF_MI_DMA_Y_PIC_START_AD	(RKISP1_CIF_MI_BASE + 0x000000C8)
+#define RKISP1_CIF_MI_DMA_Y_PIC_WIDTH		(RKISP1_CIF_MI_BASE + 0x000000CC)
+#define RKISP1_CIF_MI_DMA_Y_LLENGTH		(RKISP1_CIF_MI_BASE + 0x000000D0)
+#define RKISP1_CIF_MI_DMA_Y_PIC_SIZE		(RKISP1_CIF_MI_BASE + 0x000000D4)
+#define RKISP1_CIF_MI_DMA_CB_PIC_START_AD	(RKISP1_CIF_MI_BASE + 0x000000D8)
+#define RKISP1_CIF_MI_DMA_CR_PIC_START_AD	(RKISP1_CIF_MI_BASE + 0x000000E8)
+#define RKISP1_CIF_MI_IMSC			(RKISP1_CIF_MI_BASE + 0x000000F8)
+#define RKISP1_CIF_MI_RIS			(RKISP1_CIF_MI_BASE + 0x000000FC)
+#define RKISP1_CIF_MI_MIS			(RKISP1_CIF_MI_BASE + 0x00000100)
+#define RKISP1_CIF_MI_ICR			(RKISP1_CIF_MI_BASE + 0x00000104)
+#define RKISP1_CIF_MI_ISR			(RKISP1_CIF_MI_BASE + 0x00000108)
+#define RKISP1_CIF_MI_STATUS			(RKISP1_CIF_MI_BASE + 0x0000010C)
+#define RKISP1_CIF_MI_STATUS_CLR		(RKISP1_CIF_MI_BASE + 0x00000110)
+#define RKISP1_CIF_MI_SP_Y_PIC_WIDTH		(RKISP1_CIF_MI_BASE + 0x00000114)
+#define RKISP1_CIF_MI_SP_Y_PIC_HEIGHT		(RKISP1_CIF_MI_BASE + 0x00000118)
+#define RKISP1_CIF_MI_SP_Y_PIC_SIZE		(RKISP1_CIF_MI_BASE + 0x0000011C)
+#define RKISP1_CIF_MI_DMA_CTRL			(RKISP1_CIF_MI_BASE + 0x00000120)
+#define RKISP1_CIF_MI_DMA_START			(RKISP1_CIF_MI_BASE + 0x00000124)
+#define RKISP1_CIF_MI_DMA_STATUS		(RKISP1_CIF_MI_BASE + 0x00000128)
+#define RKISP1_CIF_MI_PIXEL_COUNT		(RKISP1_CIF_MI_BASE + 0x0000012C)
+#define RKISP1_CIF_MI_MP_Y_BASE_AD_INIT2	(RKISP1_CIF_MI_BASE + 0x00000130)
+#define RKISP1_CIF_MI_MP_CB_BASE_AD_INIT2	(RKISP1_CIF_MI_BASE + 0x00000134)
+#define RKISP1_CIF_MI_MP_CR_BASE_AD_INIT2	(RKISP1_CIF_MI_BASE + 0x00000138)
+#define RKISP1_CIF_MI_SP_Y_BASE_AD_INIT2	(RKISP1_CIF_MI_BASE + 0x0000013C)
+#define RKISP1_CIF_MI_SP_CB_BASE_AD_INIT2	(RKISP1_CIF_MI_BASE + 0x00000140)
+#define RKISP1_CIF_MI_SP_CR_BASE_AD_INIT2	(RKISP1_CIF_MI_BASE + 0x00000144)
+#define RKISP1_CIF_MI_XTD_FORMAT_CTRL		(RKISP1_CIF_MI_BASE + 0x00000148)
+
+#define RKISP1_CIF_SMIA_BASE			0x00001A00
+#define RKISP1_CIF_SMIA_CTRL			(RKISP1_CIF_SMIA_BASE + 0x00000000)
+#define RKISP1_CIF_SMIA_STATUS			(RKISP1_CIF_SMIA_BASE + 0x00000004)
+#define RKISP1_CIF_SMIA_IMSC			(RKISP1_CIF_SMIA_BASE + 0x00000008)
+#define RKISP1_CIF_SMIA_RIS			(RKISP1_CIF_SMIA_BASE + 0x0000000C)
+#define RKISP1_CIF_SMIA_MIS			(RKISP1_CIF_SMIA_BASE + 0x00000010)
+#define RKISP1_CIF_SMIA_ICR			(RKISP1_CIF_SMIA_BASE + 0x00000014)
+#define RKISP1_CIF_SMIA_ISR			(RKISP1_CIF_SMIA_BASE + 0x00000018)
+#define RKISP1_CIF_SMIA_DATA_FORMAT_SEL		(RKISP1_CIF_SMIA_BASE + 0x0000001C)
+#define RKISP1_CIF_SMIA_SOF_EMB_DATA_LINES	(RKISP1_CIF_SMIA_BASE + 0x00000020)
+#define RKISP1_CIF_SMIA_EMB_HSTART		(RKISP1_CIF_SMIA_BASE + 0x00000024)
+#define RKISP1_CIF_SMIA_EMB_HSIZE		(RKISP1_CIF_SMIA_BASE + 0x00000028)
+#define RKISP1_CIF_SMIA_EMB_VSTART		(RKISP1_CIF_SMIA_BASE + 0x0000002c)
+#define RKISP1_CIF_SMIA_NUM_LINES		(RKISP1_CIF_SMIA_BASE + 0x00000030)
+#define RKISP1_CIF_SMIA_EMB_DATA_FIFO		(RKISP1_CIF_SMIA_BASE + 0x00000034)
+#define RKISP1_CIF_SMIA_EMB_DATA_WATERMARK	(RKISP1_CIF_SMIA_BASE + 0x00000038)
+
+#define RKISP1_CIF_MIPI_BASE			0x00001C00
+#define RKISP1_CIF_MIPI_CTRL			(RKISP1_CIF_MIPI_BASE + 0x00000000)
+#define RKISP1_CIF_MIPI_STATUS			(RKISP1_CIF_MIPI_BASE + 0x00000004)
+#define RKISP1_CIF_MIPI_IMSC			(RKISP1_CIF_MIPI_BASE + 0x00000008)
+#define RKISP1_CIF_MIPI_RIS			(RKISP1_CIF_MIPI_BASE + 0x0000000C)
+#define RKISP1_CIF_MIPI_MIS			(RKISP1_CIF_MIPI_BASE + 0x00000010)
+#define RKISP1_CIF_MIPI_ICR			(RKISP1_CIF_MIPI_BASE + 0x00000014)
+#define RKISP1_CIF_MIPI_ISR			(RKISP1_CIF_MIPI_BASE + 0x00000018)
+#define RKISP1_CIF_MIPI_CUR_DATA_ID		(RKISP1_CIF_MIPI_BASE + 0x0000001C)
+#define RKISP1_CIF_MIPI_IMG_DATA_SEL		(RKISP1_CIF_MIPI_BASE + 0x00000020)
+#define RKISP1_CIF_MIPI_ADD_DATA_SEL_1		(RKISP1_CIF_MIPI_BASE + 0x00000024)
+#define RKISP1_CIF_MIPI_ADD_DATA_SEL_2		(RKISP1_CIF_MIPI_BASE + 0x00000028)
+#define RKISP1_CIF_MIPI_ADD_DATA_SEL_3		(RKISP1_CIF_MIPI_BASE + 0x0000002C)
+#define RKISP1_CIF_MIPI_ADD_DATA_SEL_4		(RKISP1_CIF_MIPI_BASE + 0x00000030)
+#define RKISP1_CIF_MIPI_ADD_DATA_FIFO		(RKISP1_CIF_MIPI_BASE + 0x00000034)
+#define RKISP1_CIF_MIPI_FIFO_FILL_LEVEL		(RKISP1_CIF_MIPI_BASE + 0x00000038)
+#define RKISP1_CIF_MIPI_COMPRESSED_MODE		(RKISP1_CIF_MIPI_BASE + 0x0000003C)
+#define RKISP1_CIF_MIPI_FRAME			(RKISP1_CIF_MIPI_BASE + 0x00000040)
+#define RKISP1_CIF_MIPI_GEN_SHORT_DT		(RKISP1_CIF_MIPI_BASE + 0x00000044)
+#define RKISP1_CIF_MIPI_GEN_SHORT_8_9		(RKISP1_CIF_MIPI_BASE + 0x00000048)
+#define RKISP1_CIF_MIPI_GEN_SHORT_A_B		(RKISP1_CIF_MIPI_BASE + 0x0000004C)
+#define RKISP1_CIF_MIPI_GEN_SHORT_C_D		(RKISP1_CIF_MIPI_BASE + 0x00000050)
+#define RKISP1_CIF_MIPI_GEN_SHORT_E_F		(RKISP1_CIF_MIPI_BASE + 0x00000054)
+
+#define RKISP1_CIF_ISP_AFM_BASE			0x00002000
+#define RKISP1_CIF_ISP_AFM_CTRL			(RKISP1_CIF_ISP_AFM_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_AFM_LT_A			(RKISP1_CIF_ISP_AFM_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_AFM_RB_A			(RKISP1_CIF_ISP_AFM_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_AFM_LT_B			(RKISP1_CIF_ISP_AFM_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_AFM_RB_B			(RKISP1_CIF_ISP_AFM_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_AFM_LT_C			(RKISP1_CIF_ISP_AFM_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_AFM_RB_C			(RKISP1_CIF_ISP_AFM_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_AFM_THRES		(RKISP1_CIF_ISP_AFM_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_AFM_VAR_SHIFT		(RKISP1_CIF_ISP_AFM_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_AFM_SUM_A		(RKISP1_CIF_ISP_AFM_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_AFM_SUM_B		(RKISP1_CIF_ISP_AFM_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_AFM_SUM_C		(RKISP1_CIF_ISP_AFM_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_AFM_LUM_A		(RKISP1_CIF_ISP_AFM_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_AFM_LUM_B		(RKISP1_CIF_ISP_AFM_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_AFM_LUM_C		(RKISP1_CIF_ISP_AFM_BASE + 0x00000038)
+
+#define RKISP1_CIF_ISP_LSC_BASE			0x00002200
+#define RKISP1_CIF_ISP_LSC_CTRL			(RKISP1_CIF_ISP_LSC_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_LSC_R_TABLE_ADDR		(RKISP1_CIF_ISP_LSC_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_LSC_GR_TABLE_ADDR	(RKISP1_CIF_ISP_LSC_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_LSC_B_TABLE_ADDR		(RKISP1_CIF_ISP_LSC_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_LSC_GB_TABLE_ADDR	(RKISP1_CIF_ISP_LSC_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_LSC_R_TABLE_DATA		(RKISP1_CIF_ISP_LSC_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_LSC_GR_TABLE_DATA	(RKISP1_CIF_ISP_LSC_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_LSC_B_TABLE_DATA		(RKISP1_CIF_ISP_LSC_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_LSC_GB_TABLE_DATA	(RKISP1_CIF_ISP_LSC_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_LSC_XGRAD_01		(RKISP1_CIF_ISP_LSC_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_LSC_XGRAD_23		(RKISP1_CIF_ISP_LSC_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_LSC_XGRAD_45		(RKISP1_CIF_ISP_LSC_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_LSC_XGRAD_67		(RKISP1_CIF_ISP_LSC_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_LSC_YGRAD_01		(RKISP1_CIF_ISP_LSC_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_LSC_YGRAD_23		(RKISP1_CIF_ISP_LSC_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_LSC_YGRAD_45		(RKISP1_CIF_ISP_LSC_BASE + 0x0000003C)
+#define RKISP1_CIF_ISP_LSC_YGRAD_67		(RKISP1_CIF_ISP_LSC_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_LSC_XSIZE_01		(RKISP1_CIF_ISP_LSC_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_LSC_XSIZE_23		(RKISP1_CIF_ISP_LSC_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_LSC_XSIZE_45		(RKISP1_CIF_ISP_LSC_BASE + 0x0000004C)
+#define RKISP1_CIF_ISP_LSC_XSIZE_67		(RKISP1_CIF_ISP_LSC_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_LSC_YSIZE_01		(RKISP1_CIF_ISP_LSC_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_LSC_YSIZE_23		(RKISP1_CIF_ISP_LSC_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_LSC_YSIZE_45		(RKISP1_CIF_ISP_LSC_BASE + 0x0000005C)
+#define RKISP1_CIF_ISP_LSC_YSIZE_67		(RKISP1_CIF_ISP_LSC_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_LSC_TABLE_SEL		(RKISP1_CIF_ISP_LSC_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_LSC_STATUS		(RKISP1_CIF_ISP_LSC_BASE + 0x00000068)
+
+#define RKISP1_CIF_ISP_IS_BASE			0x00002300
+#define RKISP1_CIF_ISP_IS_CTRL			(RKISP1_CIF_ISP_IS_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_IS_RECENTER		(RKISP1_CIF_ISP_IS_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_IS_H_OFFS		(RKISP1_CIF_ISP_IS_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_IS_V_OFFS		(RKISP1_CIF_ISP_IS_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_IS_H_SIZE		(RKISP1_CIF_ISP_IS_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_IS_V_SIZE		(RKISP1_CIF_ISP_IS_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_IS_MAX_DX		(RKISP1_CIF_ISP_IS_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_IS_MAX_DY		(RKISP1_CIF_ISP_IS_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_IS_DISPLACE		(RKISP1_CIF_ISP_IS_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_IS_H_OFFS_SHD		(RKISP1_CIF_ISP_IS_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_IS_V_OFFS_SHD		(RKISP1_CIF_ISP_IS_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_IS_H_SIZE_SHD		(RKISP1_CIF_ISP_IS_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_IS_V_SIZE_SHD		(RKISP1_CIF_ISP_IS_BASE + 0x00000030)
+
+#define RKISP1_CIF_ISP_HIST_BASE		0x00002400
+
+#define RKISP1_CIF_ISP_HIST_PROP		(RKISP1_CIF_ISP_HIST_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_HIST_H_OFFS		(RKISP1_CIF_ISP_HIST_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_HIST_V_OFFS		(RKISP1_CIF_ISP_HIST_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_HIST_H_SIZE		(RKISP1_CIF_ISP_HIST_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_HIST_V_SIZE		(RKISP1_CIF_ISP_HIST_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_HIST_BIN_0		(RKISP1_CIF_ISP_HIST_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_HIST_BIN_1		(RKISP1_CIF_ISP_HIST_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_HIST_BIN_2		(RKISP1_CIF_ISP_HIST_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_HIST_BIN_3		(RKISP1_CIF_ISP_HIST_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_HIST_BIN_4		(RKISP1_CIF_ISP_HIST_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_HIST_BIN_5		(RKISP1_CIF_ISP_HIST_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_HIST_BIN_6		(RKISP1_CIF_ISP_HIST_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_HIST_BIN_7		(RKISP1_CIF_ISP_HIST_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_HIST_BIN_8		(RKISP1_CIF_ISP_HIST_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_HIST_BIN_9		(RKISP1_CIF_ISP_HIST_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_HIST_BIN_10		(RKISP1_CIF_ISP_HIST_BASE + 0x0000003C)
+#define RKISP1_CIF_ISP_HIST_BIN_11		(RKISP1_CIF_ISP_HIST_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_HIST_BIN_12		(RKISP1_CIF_ISP_HIST_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_HIST_BIN_13		(RKISP1_CIF_ISP_HIST_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_HIST_BIN_14		(RKISP1_CIF_ISP_HIST_BASE + 0x0000004C)
+#define RKISP1_CIF_ISP_HIST_BIN_15		(RKISP1_CIF_ISP_HIST_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_00TO30	(RKISP1_CIF_ISP_HIST_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_40TO21	(RKISP1_CIF_ISP_HIST_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_31TO12	(RKISP1_CIF_ISP_HIST_BASE + 0x0000005C)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_22TO03	(RKISP1_CIF_ISP_HIST_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_13TO43	(RKISP1_CIF_ISP_HIST_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_04TO34	(RKISP1_CIF_ISP_HIST_BASE + 0x00000068)
+#define RKISP1_CIF_ISP_HIST_WEIGHT_44		(RKISP1_CIF_ISP_HIST_BASE + 0x0000006C)
+
+#define RKISP1_CIF_ISP_FILT_BASE		0x00002500
+#define RKISP1_CIF_ISP_FILT_MODE		(RKISP1_CIF_ISP_FILT_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_FILT_THRESH_BL0		(RKISP1_CIF_ISP_FILT_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_FILT_THRESH_BL1		(RKISP1_CIF_ISP_FILT_BASE + 0x0000002c)
+#define RKISP1_CIF_ISP_FILT_THRESH_SH0		(RKISP1_CIF_ISP_FILT_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_FILT_THRESH_SH1		(RKISP1_CIF_ISP_FILT_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_FILT_LUM_WEIGHT		(RKISP1_CIF_ISP_FILT_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_FILT_FAC_SH1		(RKISP1_CIF_ISP_FILT_BASE + 0x0000003c)
+#define RKISP1_CIF_ISP_FILT_FAC_SH0		(RKISP1_CIF_ISP_FILT_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_FILT_FAC_MID		(RKISP1_CIF_ISP_FILT_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_FILT_FAC_BL0		(RKISP1_CIF_ISP_FILT_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_FILT_FAC_BL1		(RKISP1_CIF_ISP_FILT_BASE + 0x0000004C)
+
+#define RKISP1_CIF_ISP_CAC_BASE			0x00002580
+#define RKISP1_CIF_ISP_CAC_CTRL			(RKISP1_CIF_ISP_CAC_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_CAC_COUNT_START		(RKISP1_CIF_ISP_CAC_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_CAC_A			(RKISP1_CIF_ISP_CAC_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_CAC_B			(RKISP1_CIF_ISP_CAC_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_CAC_C			(RKISP1_CIF_ISP_CAC_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_X_NORM			(RKISP1_CIF_ISP_CAC_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_Y_NORM			(RKISP1_CIF_ISP_CAC_BASE + 0x00000018)
+
+#define RKISP1_CIF_ISP_EXP_BASE			0x00002600
+#define RKISP1_CIF_ISP_EXP_CTRL			(RKISP1_CIF_ISP_EXP_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_EXP_H_OFFSET		(RKISP1_CIF_ISP_EXP_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_EXP_V_OFFSET		(RKISP1_CIF_ISP_EXP_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_EXP_H_SIZE		(RKISP1_CIF_ISP_EXP_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_EXP_V_SIZE		(RKISP1_CIF_ISP_EXP_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_EXP_MEAN_00		(RKISP1_CIF_ISP_EXP_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_EXP_MEAN_10		(RKISP1_CIF_ISP_EXP_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_EXP_MEAN_20		(RKISP1_CIF_ISP_EXP_BASE + 0x0000001c)
+#define RKISP1_CIF_ISP_EXP_MEAN_30		(RKISP1_CIF_ISP_EXP_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_EXP_MEAN_40		(RKISP1_CIF_ISP_EXP_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_EXP_MEAN_01		(RKISP1_CIF_ISP_EXP_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_EXP_MEAN_11		(RKISP1_CIF_ISP_EXP_BASE + 0x0000002c)
+#define RKISP1_CIF_ISP_EXP_MEAN_21		(RKISP1_CIF_ISP_EXP_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_EXP_MEAN_31		(RKISP1_CIF_ISP_EXP_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_EXP_MEAN_41		(RKISP1_CIF_ISP_EXP_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_EXP_MEAN_02		(RKISP1_CIF_ISP_EXP_BASE + 0x0000003c)
+#define RKISP1_CIF_ISP_EXP_MEAN_12		(RKISP1_CIF_ISP_EXP_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_EXP_MEAN_22		(RKISP1_CIF_ISP_EXP_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_EXP_MEAN_32		(RKISP1_CIF_ISP_EXP_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_EXP_MEAN_42		(RKISP1_CIF_ISP_EXP_BASE + 0x0000004c)
+#define RKISP1_CIF_ISP_EXP_MEAN_03		(RKISP1_CIF_ISP_EXP_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_EXP_MEAN_13		(RKISP1_CIF_ISP_EXP_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_EXP_MEAN_23		(RKISP1_CIF_ISP_EXP_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_EXP_MEAN_33		(RKISP1_CIF_ISP_EXP_BASE + 0x0000005c)
+#define RKISP1_CIF_ISP_EXP_MEAN_43		(RKISP1_CIF_ISP_EXP_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_EXP_MEAN_04		(RKISP1_CIF_ISP_EXP_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_EXP_MEAN_14		(RKISP1_CIF_ISP_EXP_BASE + 0x00000068)
+#define RKISP1_CIF_ISP_EXP_MEAN_24		(RKISP1_CIF_ISP_EXP_BASE + 0x0000006c)
+#define RKISP1_CIF_ISP_EXP_MEAN_34		(RKISP1_CIF_ISP_EXP_BASE + 0x00000070)
+#define RKISP1_CIF_ISP_EXP_MEAN_44		(RKISP1_CIF_ISP_EXP_BASE + 0x00000074)
+
+#define RKISP1_CIF_ISP_BLS_BASE			0x00002700
+#define RKISP1_CIF_ISP_BLS_CTRL			(RKISP1_CIF_ISP_BLS_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_BLS_SAMPLES		(RKISP1_CIF_ISP_BLS_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_BLS_H1_START		(RKISP1_CIF_ISP_BLS_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_BLS_H1_STOP		(RKISP1_CIF_ISP_BLS_BASE + 0x0000000c)
+#define RKISP1_CIF_ISP_BLS_V1_START		(RKISP1_CIF_ISP_BLS_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_BLS_V1_STOP		(RKISP1_CIF_ISP_BLS_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_BLS_H2_START		(RKISP1_CIF_ISP_BLS_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_BLS_H2_STOP		(RKISP1_CIF_ISP_BLS_BASE + 0x0000001c)
+#define RKISP1_CIF_ISP_BLS_V2_START		(RKISP1_CIF_ISP_BLS_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_BLS_V2_STOP		(RKISP1_CIF_ISP_BLS_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_BLS_A_FIXED		(RKISP1_CIF_ISP_BLS_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_BLS_B_FIXED		(RKISP1_CIF_ISP_BLS_BASE + 0x0000002c)
+#define RKISP1_CIF_ISP_BLS_C_FIXED		(RKISP1_CIF_ISP_BLS_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_BLS_D_FIXED		(RKISP1_CIF_ISP_BLS_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_BLS_A_MEASURED		(RKISP1_CIF_ISP_BLS_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_BLS_B_MEASURED		(RKISP1_CIF_ISP_BLS_BASE + 0x0000003c)
+#define RKISP1_CIF_ISP_BLS_C_MEASURED		(RKISP1_CIF_ISP_BLS_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_BLS_D_MEASURED		(RKISP1_CIF_ISP_BLS_BASE + 0x00000044)
+
+#define RKISP1_CIF_ISP_DPF_BASE			0x00002800
+#define RKISP1_CIF_ISP_DPF_MODE			(RKISP1_CIF_ISP_DPF_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_DPF_STRENGTH_R		(RKISP1_CIF_ISP_DPF_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_DPF_STRENGTH_G		(RKISP1_CIF_ISP_DPF_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_DPF_STRENGTH_B		(RKISP1_CIF_ISP_DPF_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_DPF_S_WEIGHT_G_1_4	(RKISP1_CIF_ISP_DPF_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_DPF_S_WEIGHT_G_5_6	(RKISP1_CIF_ISP_DPF_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_DPF_S_WEIGHT_RB_1_4	(RKISP1_CIF_ISP_DPF_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_DPF_S_WEIGHT_RB_5_6	(RKISP1_CIF_ISP_DPF_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_0		(RKISP1_CIF_ISP_DPF_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_1		(RKISP1_CIF_ISP_DPF_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_2		(RKISP1_CIF_ISP_DPF_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_3		(RKISP1_CIF_ISP_DPF_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_4		(RKISP1_CIF_ISP_DPF_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_5		(RKISP1_CIF_ISP_DPF_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_6		(RKISP1_CIF_ISP_DPF_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_7		(RKISP1_CIF_ISP_DPF_BASE + 0x0000003C)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_8		(RKISP1_CIF_ISP_DPF_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_9		(RKISP1_CIF_ISP_DPF_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_10	(RKISP1_CIF_ISP_DPF_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_11	(RKISP1_CIF_ISP_DPF_BASE + 0x0000004C)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_12	(RKISP1_CIF_ISP_DPF_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_13	(RKISP1_CIF_ISP_DPF_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_14	(RKISP1_CIF_ISP_DPF_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_15	(RKISP1_CIF_ISP_DPF_BASE + 0x0000005C)
+#define RKISP1_CIF_ISP_DPF_NULL_COEFF_16	(RKISP1_CIF_ISP_DPF_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_DPF_NF_GAIN_R		(RKISP1_CIF_ISP_DPF_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_DPF_NF_GAIN_GR		(RKISP1_CIF_ISP_DPF_BASE + 0x00000068)
+#define RKISP1_CIF_ISP_DPF_NF_GAIN_GB		(RKISP1_CIF_ISP_DPF_BASE + 0x0000006C)
+#define RKISP1_CIF_ISP_DPF_NF_GAIN_B		(RKISP1_CIF_ISP_DPF_BASE + 0x00000070)
+
+#define RKISP1_CIF_ISP_DPCC_BASE		0x00002900
+#define RKISP1_CIF_ISP_DPCC_MODE		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_DPCC_OUTPUT_MODE		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_DPCC_SET_USE		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_DPCC_METHODS_SET_1	(RKISP1_CIF_ISP_DPCC_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_DPCC_METHODS_SET_2	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_DPCC_METHODS_SET_3	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_1	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_1	(RKISP1_CIF_ISP_DPCC_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_DPCC_PG_FAC_1		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_DPCC_RND_THRESH_1	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_DPCC_RG_FAC_1		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_2	(RKISP1_CIF_ISP_DPCC_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_2	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_DPCC_PG_FAC_2		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_DPCC_RND_THRESH_2	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_DPCC_RG_FAC_2		(RKISP1_CIF_ISP_DPCC_BASE + 0x0000003C)
+#define RKISP1_CIF_ISP_DPCC_LINE_THRESH_3	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_DPCC_LINE_MAD_FAC_3	(RKISP1_CIF_ISP_DPCC_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_DPCC_PG_FAC_3		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_DPCC_RND_THRESH_3	(RKISP1_CIF_ISP_DPCC_BASE + 0x0000004C)
+#define RKISP1_CIF_ISP_DPCC_RG_FAC_3		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_DPCC_RO_LIMITS		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_DPCC_RND_OFFS		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_DPCC_BPT_CTRL		(RKISP1_CIF_ISP_DPCC_BASE + 0x0000005C)
+#define RKISP1_CIF_ISP_DPCC_BPT_NUMBER		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_DPCC_BPT_ADDR		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_DPCC_BPT_DATA		(RKISP1_CIF_ISP_DPCC_BASE + 0x00000068)
+
+#define RKISP1_CIF_ISP_WDR_BASE			0x00002A00
+#define RKISP1_CIF_ISP_WDR_CTRL			(RKISP1_CIF_ISP_WDR_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_1		(RKISP1_CIF_ISP_WDR_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_2		(RKISP1_CIF_ISP_WDR_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_3		(RKISP1_CIF_ISP_WDR_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_4		(RKISP1_CIF_ISP_WDR_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_0	(RKISP1_CIF_ISP_WDR_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_1	(RKISP1_CIF_ISP_WDR_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_2	(RKISP1_CIF_ISP_WDR_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_3	(RKISP1_CIF_ISP_WDR_BASE + 0x00000020)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_4	(RKISP1_CIF_ISP_WDR_BASE + 0x00000024)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_5	(RKISP1_CIF_ISP_WDR_BASE + 0x00000028)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_6	(RKISP1_CIF_ISP_WDR_BASE + 0x0000002C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_7	(RKISP1_CIF_ISP_WDR_BASE + 0x00000030)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_8	(RKISP1_CIF_ISP_WDR_BASE + 0x00000034)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_9	(RKISP1_CIF_ISP_WDR_BASE + 0x00000038)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_10	(RKISP1_CIF_ISP_WDR_BASE + 0x0000003C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_11	(RKISP1_CIF_ISP_WDR_BASE + 0x00000040)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_12	(RKISP1_CIF_ISP_WDR_BASE + 0x00000044)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_13	(RKISP1_CIF_ISP_WDR_BASE + 0x00000048)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_14	(RKISP1_CIF_ISP_WDR_BASE + 0x0000004C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_15	(RKISP1_CIF_ISP_WDR_BASE + 0x00000050)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_16	(RKISP1_CIF_ISP_WDR_BASE + 0x00000054)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_17	(RKISP1_CIF_ISP_WDR_BASE + 0x00000058)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_18	(RKISP1_CIF_ISP_WDR_BASE + 0x0000005C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_19	(RKISP1_CIF_ISP_WDR_BASE + 0x00000060)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_20	(RKISP1_CIF_ISP_WDR_BASE + 0x00000064)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_21	(RKISP1_CIF_ISP_WDR_BASE + 0x00000068)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_22	(RKISP1_CIF_ISP_WDR_BASE + 0x0000006C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_23	(RKISP1_CIF_ISP_WDR_BASE + 0x00000070)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_24	(RKISP1_CIF_ISP_WDR_BASE + 0x00000074)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_25	(RKISP1_CIF_ISP_WDR_BASE + 0x00000078)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_26	(RKISP1_CIF_ISP_WDR_BASE + 0x0000007C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_27	(RKISP1_CIF_ISP_WDR_BASE + 0x00000080)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_28	(RKISP1_CIF_ISP_WDR_BASE + 0x00000084)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_29	(RKISP1_CIF_ISP_WDR_BASE + 0x00000088)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_30	(RKISP1_CIF_ISP_WDR_BASE + 0x0000008C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_31	(RKISP1_CIF_ISP_WDR_BASE + 0x00000090)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_32	(RKISP1_CIF_ISP_WDR_BASE + 0x00000094)
+#define RKISP1_CIF_ISP_WDR_OFFSET		(RKISP1_CIF_ISP_WDR_BASE + 0x00000098)
+#define RKISP1_CIF_ISP_WDR_DELTAMIN		(RKISP1_CIF_ISP_WDR_BASE + 0x0000009C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_1_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000A0)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_2_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000A4)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_3_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000A8)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_4_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000AC)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_0_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000B0)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_1_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000B4)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_2_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000B8)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_3_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000BC)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_4_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000C0)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_5_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000C4)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_6_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000C8)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_7_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000CC)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_8_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000D0)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_9_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000D4)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_10_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000D8)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_11_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000DC)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_12_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000E0)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_13_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000E4)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_14_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000E8)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_15_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000EC)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_16_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000F0)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_17_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000F4)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_18_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000F8)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_19_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x000000FC)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_20_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000100)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_21_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000104)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_22_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000108)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_23_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x0000010C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_24_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000110)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_25_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000114)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_26_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000118)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_27_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x0000011C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_28_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000120)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_29_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000124)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_30_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000128)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_31_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x0000012C)
+#define RKISP1_CIF_ISP_WDR_TONECURVE_YM_32_SHD	(RKISP1_CIF_ISP_WDR_BASE + 0x00000130)
+
+#define RKISP1_CIF_ISP_VSM_BASE			0x00002F00
+#define RKISP1_CIF_ISP_VSM_MODE			(RKISP1_CIF_ISP_VSM_BASE + 0x00000000)
+#define RKISP1_CIF_ISP_VSM_H_OFFS		(RKISP1_CIF_ISP_VSM_BASE + 0x00000004)
+#define RKISP1_CIF_ISP_VSM_V_OFFS		(RKISP1_CIF_ISP_VSM_BASE + 0x00000008)
+#define RKISP1_CIF_ISP_VSM_H_SIZE		(RKISP1_CIF_ISP_VSM_BASE + 0x0000000C)
+#define RKISP1_CIF_ISP_VSM_V_SIZE		(RKISP1_CIF_ISP_VSM_BASE + 0x00000010)
+#define RKISP1_CIF_ISP_VSM_H_SEGMENTS		(RKISP1_CIF_ISP_VSM_BASE + 0x00000014)
+#define RKISP1_CIF_ISP_VSM_V_SEGMENTS		(RKISP1_CIF_ISP_VSM_BASE + 0x00000018)
+#define RKISP1_CIF_ISP_VSM_DELTA_H		(RKISP1_CIF_ISP_VSM_BASE + 0x0000001C)
+#define RKISP1_CIF_ISP_VSM_DELTA_V		(RKISP1_CIF_ISP_VSM_BASE + 0x00000020)
+
+#endif /* _RKISP1_REGS_H */
diff --git a/drivers/staging/media/rkisp1/rkisp1-resizer.c b/drivers/staging/media/rkisp1/rkisp1-resizer.c
new file mode 100644
index 000000000000..8cdc29c1a178
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-resizer.c
@@ -0,0 +1,775 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - V4l resizer device
+ *
+ * Copyright (C) 2019 Collabora, Ltd.
+ *
+ * Based on Rockchip ISP1 driver by Rockchip Electronics Co., Ltd.
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#include "rkisp1-common.h"
+
+#define RKISP1_RSZ_SP_DEV_NAME	RKISP1_DRIVER_NAME "_resizer_selfpath"
+#define RKISP1_RSZ_MP_DEV_NAME	RKISP1_DRIVER_NAME "_resizer_mainpath"
+
+#define RKISP1_DEF_FMT MEDIA_BUS_FMT_YUYV8_2X8
+#define RKISP1_DEF_FMT_TYPE RKISP1_FMT_YUV
+
+#define RKISP1_MBUS_FMT_HDIV 2
+#define RKISP1_MBUS_FMT_VDIV 1
+
+enum rkisp1_shadow_regs_when {
+	RKISP1_SHADOW_REGS_SYNC,
+	RKISP1_SHADOW_REGS_ASYNC,
+};
+
+struct rkisp1_rsz_config {
+	/* constrains */
+	const int max_rsz_width;
+	const int max_rsz_height;
+	const int min_rsz_width;
+	const int min_rsz_height;
+	/* registers */
+	struct {
+		u32 ctrl;
+		u32 ctrl_shd;
+		u32 scale_hy;
+		u32 scale_hcr;
+		u32 scale_hcb;
+		u32 scale_vy;
+		u32 scale_vc;
+		u32 scale_lut;
+		u32 scale_lut_addr;
+		u32 scale_hy_shd;
+		u32 scale_hcr_shd;
+		u32 scale_hcb_shd;
+		u32 scale_vy_shd;
+		u32 scale_vc_shd;
+		u32 phase_hy;
+		u32 phase_hc;
+		u32 phase_vy;
+		u32 phase_vc;
+		u32 phase_hy_shd;
+		u32 phase_hc_shd;
+		u32 phase_vy_shd;
+		u32 phase_vc_shd;
+	} rsz;
+	struct {
+		u32 ctrl;
+		u32 yuvmode_mask;
+		u32 rawmode_mask;
+		u32 h_offset;
+		u32 v_offset;
+		u32 h_size;
+		u32 v_size;
+	} dual_crop;
+};
+
+static const struct rkisp1_rsz_config rkisp1_rsz_config_mp = {
+	/* constraints */
+	.max_rsz_width = RKISP1_RSZ_MP_SRC_MAX_WIDTH,
+	.max_rsz_height = RKISP1_RSZ_MP_SRC_MAX_HEIGHT,
+	.min_rsz_width = RKISP1_RSZ_SRC_MIN_WIDTH,
+	.min_rsz_height = RKISP1_RSZ_SRC_MIN_HEIGHT,
+	/* registers */
+	.rsz = {
+		.ctrl =			RKISP1_CIF_MRSZ_CTRL,
+		.scale_hy =		RKISP1_CIF_MRSZ_SCALE_HY,
+		.scale_hcr =		RKISP1_CIF_MRSZ_SCALE_HCR,
+		.scale_hcb =		RKISP1_CIF_MRSZ_SCALE_HCB,
+		.scale_vy =		RKISP1_CIF_MRSZ_SCALE_VY,
+		.scale_vc =		RKISP1_CIF_MRSZ_SCALE_VC,
+		.scale_lut =		RKISP1_CIF_MRSZ_SCALE_LUT,
+		.scale_lut_addr =	RKISP1_CIF_MRSZ_SCALE_LUT_ADDR,
+		.scale_hy_shd =		RKISP1_CIF_MRSZ_SCALE_HY_SHD,
+		.scale_hcr_shd =	RKISP1_CIF_MRSZ_SCALE_HCR_SHD,
+		.scale_hcb_shd =	RKISP1_CIF_MRSZ_SCALE_HCB_SHD,
+		.scale_vy_shd =		RKISP1_CIF_MRSZ_SCALE_VY_SHD,
+		.scale_vc_shd =		RKISP1_CIF_MRSZ_SCALE_VC_SHD,
+		.phase_hy =		RKISP1_CIF_MRSZ_PHASE_HY,
+		.phase_hc =		RKISP1_CIF_MRSZ_PHASE_HC,
+		.phase_vy =		RKISP1_CIF_MRSZ_PHASE_VY,
+		.phase_vc =		RKISP1_CIF_MRSZ_PHASE_VC,
+		.ctrl_shd =		RKISP1_CIF_MRSZ_CTRL_SHD,
+		.phase_hy_shd =		RKISP1_CIF_MRSZ_PHASE_HY_SHD,
+		.phase_hc_shd =		RKISP1_CIF_MRSZ_PHASE_HC_SHD,
+		.phase_vy_shd =		RKISP1_CIF_MRSZ_PHASE_VY_SHD,
+		.phase_vc_shd =		RKISP1_CIF_MRSZ_PHASE_VC_SHD,
+	},
+	.dual_crop = {
+		.ctrl =			RKISP1_CIF_DUAL_CROP_CTRL,
+		.yuvmode_mask =		RKISP1_CIF_DUAL_CROP_MP_MODE_YUV,
+		.rawmode_mask =		RKISP1_CIF_DUAL_CROP_MP_MODE_RAW,
+		.h_offset =		RKISP1_CIF_DUAL_CROP_M_H_OFFS,
+		.v_offset =		RKISP1_CIF_DUAL_CROP_M_V_OFFS,
+		.h_size =		RKISP1_CIF_DUAL_CROP_M_H_SIZE,
+		.v_size =		RKISP1_CIF_DUAL_CROP_M_V_SIZE,
+	},
+};
+
+static const struct rkisp1_rsz_config rkisp1_rsz_config_sp = {
+	/* constraints */
+	.max_rsz_width = RKISP1_RSZ_SP_SRC_MAX_WIDTH,
+	.max_rsz_height = RKISP1_RSZ_SP_SRC_MAX_HEIGHT,
+	.min_rsz_width = RKISP1_RSZ_SRC_MIN_WIDTH,
+	.min_rsz_height = RKISP1_RSZ_SRC_MIN_HEIGHT,
+	/* registers */
+	.rsz = {
+		.ctrl =			RKISP1_CIF_SRSZ_CTRL,
+		.scale_hy =		RKISP1_CIF_SRSZ_SCALE_HY,
+		.scale_hcr =		RKISP1_CIF_SRSZ_SCALE_HCR,
+		.scale_hcb =		RKISP1_CIF_SRSZ_SCALE_HCB,
+		.scale_vy =		RKISP1_CIF_SRSZ_SCALE_VY,
+		.scale_vc =		RKISP1_CIF_SRSZ_SCALE_VC,
+		.scale_lut =		RKISP1_CIF_SRSZ_SCALE_LUT,
+		.scale_lut_addr =	RKISP1_CIF_SRSZ_SCALE_LUT_ADDR,
+		.scale_hy_shd =		RKISP1_CIF_SRSZ_SCALE_HY_SHD,
+		.scale_hcr_shd =	RKISP1_CIF_SRSZ_SCALE_HCR_SHD,
+		.scale_hcb_shd =	RKISP1_CIF_SRSZ_SCALE_HCB_SHD,
+		.scale_vy_shd =		RKISP1_CIF_SRSZ_SCALE_VY_SHD,
+		.scale_vc_shd =		RKISP1_CIF_SRSZ_SCALE_VC_SHD,
+		.phase_hy =		RKISP1_CIF_SRSZ_PHASE_HY,
+		.phase_hc =		RKISP1_CIF_SRSZ_PHASE_HC,
+		.phase_vy =		RKISP1_CIF_SRSZ_PHASE_VY,
+		.phase_vc =		RKISP1_CIF_SRSZ_PHASE_VC,
+		.ctrl_shd =		RKISP1_CIF_SRSZ_CTRL_SHD,
+		.phase_hy_shd =		RKISP1_CIF_SRSZ_PHASE_HY_SHD,
+		.phase_hc_shd =		RKISP1_CIF_SRSZ_PHASE_HC_SHD,
+		.phase_vy_shd =		RKISP1_CIF_SRSZ_PHASE_VY_SHD,
+		.phase_vc_shd =		RKISP1_CIF_SRSZ_PHASE_VC_SHD,
+	},
+	.dual_crop = {
+		.ctrl =			RKISP1_CIF_DUAL_CROP_CTRL,
+		.yuvmode_mask =		RKISP1_CIF_DUAL_CROP_SP_MODE_YUV,
+		.rawmode_mask =		RKISP1_CIF_DUAL_CROP_SP_MODE_RAW,
+		.h_offset =		RKISP1_CIF_DUAL_CROP_S_H_OFFS,
+		.v_offset =		RKISP1_CIF_DUAL_CROP_S_V_OFFS,
+		.h_size =		RKISP1_CIF_DUAL_CROP_S_H_SIZE,
+		.v_size =		RKISP1_CIF_DUAL_CROP_S_V_SIZE,
+	},
+};
+
+static struct v4l2_mbus_framefmt *
+rkisp1_rsz_get_pad_fmt(struct rkisp1_resizer *rsz,
+		       struct v4l2_subdev_pad_config *cfg,
+		       unsigned int pad, u32 which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_format(&rsz->sd, cfg, pad);
+	else
+		return v4l2_subdev_get_try_format(&rsz->sd, rsz->pad_cfg, pad);
+}
+
+static struct v4l2_rect *
+rkisp1_rsz_get_pad_crop(struct rkisp1_resizer *rsz,
+			struct v4l2_subdev_pad_config *cfg,
+			unsigned int pad, u32 which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_crop(&rsz->sd, cfg, pad);
+	else
+		return v4l2_subdev_get_try_crop(&rsz->sd, rsz->pad_cfg, pad);
+}
+
+/* ----------------------------------------------------------------------------
+ * Dual crop hw configs
+ */
+
+static void rkisp1_dcrop_disable(struct rkisp1_resizer *rsz,
+				 enum rkisp1_shadow_regs_when when)
+{
+	u32 dc_ctrl = rkisp1_read(rsz->rkisp1, rsz->config->dual_crop.ctrl);
+	u32 mask = ~(rsz->config->dual_crop.yuvmode_mask |
+		     rsz->config->dual_crop.rawmode_mask);
+
+	dc_ctrl &= mask;
+	if (when == RKISP1_SHADOW_REGS_ASYNC)
+		dc_ctrl |= RKISP1_CIF_DUAL_CROP_GEN_CFG_UPD;
+	else
+		dc_ctrl |= RKISP1_CIF_DUAL_CROP_CFG_UPD;
+	rkisp1_write(rsz->rkisp1, dc_ctrl, rsz->config->dual_crop.ctrl);
+}
+
+/* configure dual-crop unit */
+static void rkisp1_dcrop_config(struct rkisp1_resizer *rsz)
+{
+	struct rkisp1_device *rkisp1 = rsz->rkisp1;
+	struct v4l2_mbus_framefmt *sink_fmt;
+	struct v4l2_rect *sink_crop;
+	u32 dc_ctrl;
+
+	sink_crop = rkisp1_rsz_get_pad_crop(rsz, NULL, RKISP1_RSZ_PAD_SINK,
+					    V4L2_SUBDEV_FORMAT_ACTIVE);
+	sink_fmt = rkisp1_rsz_get_pad_fmt(rsz, NULL, RKISP1_RSZ_PAD_SINK,
+					  V4L2_SUBDEV_FORMAT_ACTIVE);
+
+	if (sink_crop->width == sink_fmt->width &&
+	    sink_crop->height == sink_fmt->height &&
+	    sink_crop->left == 0 && sink_crop->top == 0) {
+		rkisp1_dcrop_disable(rsz, RKISP1_SHADOW_REGS_SYNC);
+		dev_dbg(rkisp1->dev, "capture %d crop disabled\n", rsz->id);
+		return;
+	}
+
+	dc_ctrl = rkisp1_read(rkisp1, rsz->config->dual_crop.ctrl);
+	rkisp1_write(rkisp1, sink_crop->left, rsz->config->dual_crop.h_offset);
+	rkisp1_write(rkisp1, sink_crop->top, rsz->config->dual_crop.v_offset);
+	rkisp1_write(rkisp1, sink_crop->width, rsz->config->dual_crop.h_size);
+	rkisp1_write(rkisp1, sink_crop->height, rsz->config->dual_crop.v_size);
+	dc_ctrl |= rsz->config->dual_crop.yuvmode_mask;
+	dc_ctrl |= RKISP1_CIF_DUAL_CROP_CFG_UPD;
+	rkisp1_write(rkisp1, dc_ctrl, rsz->config->dual_crop.ctrl);
+
+	dev_dbg(rkisp1->dev, "stream %d crop: %dx%d -> %dx%d\n", rsz->id,
+		sink_fmt->width, sink_fmt->height,
+		sink_crop->width, sink_crop->height);
+}
+
+/* ----------------------------------------------------------------------------
+ * Resizer hw configs
+ */
+
+static void rkisp1_rsz_dump_regs(struct rkisp1_resizer *rsz)
+{
+	dev_dbg(rsz->rkisp1->dev,
+		"RSZ_CTRL 0x%08x/0x%08x\n"
+		"RSZ_SCALE_HY %d/%d\n"
+		"RSZ_SCALE_HCB %d/%d\n"
+		"RSZ_SCALE_HCR %d/%d\n"
+		"RSZ_SCALE_VY %d/%d\n"
+		"RSZ_SCALE_VC %d/%d\n"
+		"RSZ_PHASE_HY %d/%d\n"
+		"RSZ_PHASE_HC %d/%d\n"
+		"RSZ_PHASE_VY %d/%d\n"
+		"RSZ_PHASE_VC %d/%d\n",
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.ctrl),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.ctrl_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_hy),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_hy_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_hcb),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_hcb_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_hcr),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_hcr_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_vy),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_vy_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_vc),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.scale_vc_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_hy),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_hy_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_hc),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_hc_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_vy),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_vy_shd),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_vc),
+		rkisp1_read(rsz->rkisp1, rsz->config->rsz.phase_vc_shd));
+}
+
+static void rkisp1_rsz_update_shadow(struct rkisp1_resizer *rsz,
+				     enum rkisp1_shadow_regs_when when)
+{
+	u32 ctrl_cfg = rkisp1_read(rsz->rkisp1, rsz->config->rsz.ctrl);
+
+	if (when == RKISP1_SHADOW_REGS_ASYNC)
+		ctrl_cfg |= RKISP1_CIF_RSZ_CTRL_CFG_UPD_AUTO;
+	else
+		ctrl_cfg |= RKISP1_CIF_RSZ_CTRL_CFG_UPD;
+
+	rkisp1_write(rsz->rkisp1, ctrl_cfg, rsz->config->rsz.ctrl);
+}
+
+static u32 rkisp1_rsz_calc_ratio(u32 len_sink, u32 len_src)
+{
+	if (len_sink < len_src)
+		return ((len_sink - 1) * RKISP1_CIF_RSZ_SCALER_FACTOR) /
+		       (len_src - 1);
+
+	return ((len_src - 1) * RKISP1_CIF_RSZ_SCALER_FACTOR) /
+	       (len_sink - 1) + 1;
+}
+
+static void rkisp1_rsz_disable(struct rkisp1_resizer *rsz,
+			       enum rkisp1_shadow_regs_when when)
+{
+	rkisp1_write(rsz->rkisp1, 0, rsz->config->rsz.ctrl);
+
+	if (when == RKISP1_SHADOW_REGS_SYNC)
+		rkisp1_rsz_update_shadow(rsz, when);
+}
+
+static void rkisp1_rsz_config_regs(struct rkisp1_resizer *rsz,
+				   struct v4l2_rect *sink_y,
+				   struct v4l2_rect *sink_c,
+				   struct v4l2_rect *src_y,
+				   struct v4l2_rect *src_c,
+				   enum rkisp1_shadow_regs_when when)
+{
+	struct rkisp1_device *rkisp1 = rsz->rkisp1;
+	u32 ratio, rsz_ctrl = 0;
+	unsigned int i;
+
+	/* No phase offset */
+	rkisp1_write(rkisp1, 0, rsz->config->rsz.phase_hy);
+	rkisp1_write(rkisp1, 0, rsz->config->rsz.phase_hc);
+	rkisp1_write(rkisp1, 0, rsz->config->rsz.phase_vy);
+	rkisp1_write(rkisp1, 0, rsz->config->rsz.phase_vc);
+
+	/* Linear interpolation */
+	for (i = 0; i < 64; i++) {
+		rkisp1_write(rkisp1, i, rsz->config->rsz.scale_lut_addr);
+		rkisp1_write(rkisp1, i, rsz->config->rsz.scale_lut);
+	}
+
+	if (sink_y->width != src_y->width) {
+		rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_HY_ENABLE;
+		if (sink_y->width < src_y->width)
+			rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_HY_UP;
+		ratio = rkisp1_rsz_calc_ratio(sink_y->width, src_y->width);
+		rkisp1_write(rkisp1, ratio, rsz->config->rsz.scale_hy);
+	}
+
+	if (sink_c->width != src_c->width) {
+		rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_HC_ENABLE;
+		if (sink_c->width < src_c->width)
+			rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_HC_UP;
+		ratio = rkisp1_rsz_calc_ratio(sink_c->width, src_c->width);
+		rkisp1_write(rkisp1, ratio, rsz->config->rsz.scale_hcb);
+		rkisp1_write(rkisp1, ratio, rsz->config->rsz.scale_hcr);
+	}
+
+	if (sink_y->height != src_y->height) {
+		rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_VY_ENABLE;
+		if (sink_y->height < src_y->height)
+			rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_VY_UP;
+		ratio = rkisp1_rsz_calc_ratio(sink_y->height, src_y->height);
+		rkisp1_write(rkisp1, ratio, rsz->config->rsz.scale_vy);
+	}
+
+	if (sink_c->height != src_c->height) {
+		rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_VC_ENABLE;
+		if (sink_c->height < src_c->height)
+			rsz_ctrl |= RKISP1_CIF_RSZ_CTRL_SCALE_VC_UP;
+		ratio = rkisp1_rsz_calc_ratio(sink_c->height, src_c->height);
+		rkisp1_write(rkisp1, ratio, rsz->config->rsz.scale_vc);
+	}
+
+	rkisp1_write(rkisp1, rsz_ctrl, rsz->config->rsz.ctrl);
+
+	rkisp1_rsz_update_shadow(rsz, when);
+}
+
+static void rkisp1_rsz_config(struct rkisp1_resizer *rsz,
+			      enum rkisp1_shadow_regs_when when)
+{
+	u8 hdiv = RKISP1_MBUS_FMT_HDIV, vdiv = RKISP1_MBUS_FMT_VDIV;
+	struct v4l2_rect sink_y, sink_c, src_y, src_c;
+	struct v4l2_mbus_framefmt *src_fmt;
+	struct v4l2_rect *sink_crop;
+
+	sink_crop = rkisp1_rsz_get_pad_crop(rsz, NULL, RKISP1_RSZ_PAD_SINK,
+					    V4L2_SUBDEV_FORMAT_ACTIVE);
+	src_fmt = rkisp1_rsz_get_pad_fmt(rsz, NULL, RKISP1_RSZ_PAD_SRC,
+					 V4L2_SUBDEV_FORMAT_ACTIVE);
+
+	if (rsz->fmt_type == RKISP1_FMT_BAYER) {
+		rkisp1_rsz_disable(rsz, when);
+		return;
+	}
+
+	sink_y.width = sink_crop->width;
+	sink_y.height = sink_crop->height;
+	src_y.width = src_fmt->width;
+	src_y.height = src_fmt->height;
+
+	sink_c.width = sink_y.width / RKISP1_MBUS_FMT_HDIV;
+	sink_c.height = sink_y.height / RKISP1_MBUS_FMT_VDIV;
+
+	if (rsz->fmt_type == RKISP1_FMT_YUV) {
+		struct rkisp1_capture *cap =
+			&rsz->rkisp1->capture_devs[rsz->id];
+		const struct v4l2_format_info *pixfmt_info =
+			v4l2_format_info(cap->pix.fmt.pixelformat);
+
+		hdiv = pixfmt_info->hdiv;
+		vdiv = pixfmt_info->vdiv;
+	}
+	src_c.width = src_y.width / hdiv;
+	src_c.height = src_y.height / vdiv;
+
+	if (sink_c.width == src_c.width && sink_c.height == src_c.height) {
+		rkisp1_rsz_disable(rsz, when);
+		return;
+	}
+
+	dev_dbg(rsz->rkisp1->dev, "stream %d rsz/scale: %dx%d -> %dx%d\n",
+		rsz->id, sink_crop->width, sink_crop->height,
+		src_fmt->width, src_fmt->height);
+	dev_dbg(rsz->rkisp1->dev, "chroma scaling %dx%d -> %dx%d\n",
+		sink_c.width, sink_c.height, src_c.width, src_c.height);
+
+	/* set values in the hw */
+	rkisp1_rsz_config_regs(rsz, &sink_y, &sink_c, &src_y, &src_c, when);
+
+	rkisp1_rsz_dump_regs(rsz);
+}
+
+/* ----------------------------------------------------------------------------
+ * Subdev pad operations
+ */
+
+static int rkisp1_rsz_enum_mbus_code(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_pad_config *cfg,
+				     struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct rkisp1_resizer *rsz =
+		container_of(sd, struct rkisp1_resizer, sd);
+	struct v4l2_subdev_pad_config dummy_cfg;
+	u32 pad = code->pad;
+	int ret;
+
+	/* supported mbus codes are the same in isp sink pad */
+	code->pad = RKISP1_ISP_PAD_SINK_VIDEO;
+	ret = v4l2_subdev_call(&rsz->rkisp1->isp.sd, pad, enum_mbus_code,
+			       &dummy_cfg, code);
+
+	/* restore pad */
+	code->pad = pad;
+	return ret;
+}
+
+static int rkisp1_rsz_init_config(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg)
+{
+	struct v4l2_mbus_framefmt *sink_fmt, *src_fmt;
+	struct v4l2_rect *sink_crop;
+
+	sink_fmt = v4l2_subdev_get_try_format(sd, cfg, RKISP1_RSZ_PAD_SRC);
+	sink_fmt->width = RKISP1_DEFAULT_WIDTH;
+	sink_fmt->height = RKISP1_DEFAULT_HEIGHT;
+	sink_fmt->field = V4L2_FIELD_NONE;
+	sink_fmt->code = RKISP1_DEF_FMT;
+
+	sink_crop = v4l2_subdev_get_try_crop(sd, cfg, RKISP1_RSZ_PAD_SINK);
+	sink_crop->width = RKISP1_DEFAULT_WIDTH;
+	sink_crop->height = RKISP1_DEFAULT_HEIGHT;
+	sink_crop->left = 0;
+	sink_crop->top = 0;
+
+	src_fmt = v4l2_subdev_get_try_format(sd, cfg, RKISP1_RSZ_PAD_SINK);
+	*src_fmt = *sink_fmt;
+
+	/* NOTE: there is no crop in the source pad, only in the sink */
+
+	return 0;
+}
+
+static void rkisp1_rsz_set_src_fmt(struct rkisp1_resizer *rsz,
+				   struct v4l2_subdev_pad_config *cfg,
+				   struct v4l2_mbus_framefmt *format,
+				   unsigned int which)
+{
+	struct v4l2_mbus_framefmt *src_fmt;
+
+	src_fmt = rkisp1_rsz_get_pad_fmt(rsz, cfg, RKISP1_RSZ_PAD_SRC, which);
+	src_fmt->width = clamp_t(u32, format->width,
+				 rsz->config->min_rsz_width,
+				 rsz->config->max_rsz_width);
+	src_fmt->height = clamp_t(u32, format->height,
+				  rsz->config->min_rsz_height,
+				  rsz->config->max_rsz_height);
+
+	*format = *src_fmt;
+}
+
+static void rkisp1_rsz_set_sink_crop(struct rkisp1_resizer *rsz,
+				     struct v4l2_subdev_pad_config *cfg,
+				     struct v4l2_rect *r,
+				     unsigned int which)
+{
+	const struct rkisp1_isp_mbus_info *mbus_info;
+	struct v4l2_mbus_framefmt *sink_fmt;
+	struct v4l2_rect *sink_crop;
+
+	sink_fmt = rkisp1_rsz_get_pad_fmt(rsz, cfg, RKISP1_RSZ_PAD_SINK, which);
+	sink_crop = rkisp1_rsz_get_pad_crop(rsz, cfg, RKISP1_RSZ_PAD_SINK,
+					    which);
+
+	/* Not crop for MP bayer raw data */
+	mbus_info = rkisp1_isp_mbus_info_get(sink_fmt->code);
+
+	if (rsz->id == RKISP1_MAINPATH &&
+	    mbus_info->fmt_type == RKISP1_FMT_BAYER) {
+		sink_crop->left = 0;
+		sink_crop->top = 0;
+		sink_crop->width = sink_fmt->width;
+		sink_crop->height = sink_fmt->height;
+		return;
+	}
+
+	sink_crop->left = ALIGN(r->left, 2);
+	sink_crop->width = ALIGN(r->width, 2);
+	sink_crop->top = r->top;
+	sink_crop->height = r->height;
+	rkisp1_sd_adjust_crop(sink_crop, sink_fmt);
+
+	*r = *sink_crop;
+}
+
+static void rkisp1_rsz_set_sink_fmt(struct rkisp1_resizer *rsz,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_mbus_framefmt *format,
+				    unsigned int which)
+{
+	const struct rkisp1_isp_mbus_info *mbus_info;
+	struct v4l2_mbus_framefmt *sink_fmt, *src_fmt;
+	struct v4l2_rect *sink_crop;
+
+	sink_fmt = rkisp1_rsz_get_pad_fmt(rsz, cfg, RKISP1_RSZ_PAD_SINK, which);
+	src_fmt = rkisp1_rsz_get_pad_fmt(rsz, cfg, RKISP1_RSZ_PAD_SRC, which);
+	sink_crop = rkisp1_rsz_get_pad_crop(rsz, cfg, RKISP1_RSZ_PAD_SINK,
+					    which);
+	sink_fmt->code = format->code;
+	mbus_info = rkisp1_isp_mbus_info_get(sink_fmt->code);
+	if (!mbus_info) {
+		sink_fmt->code = RKISP1_DEF_FMT;
+		mbus_info = rkisp1_isp_mbus_info_get(sink_fmt->code);
+	}
+	if (which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		rsz->fmt_type = mbus_info->fmt_type;
+
+	if (rsz->id == RKISP1_MAINPATH &&
+	    mbus_info->fmt_type == RKISP1_FMT_BAYER) {
+		sink_crop->left = 0;
+		sink_crop->top = 0;
+		sink_crop->width = sink_fmt->width;
+		sink_crop->height = sink_fmt->height;
+		return;
+	}
+
+	/* Propagete to source pad */
+	src_fmt->code = sink_fmt->code;
+
+	sink_fmt->width = clamp_t(u32, format->width,
+				  rsz->config->min_rsz_width,
+				  rsz->config->max_rsz_width);
+	sink_fmt->height = clamp_t(u32, format->height,
+				   rsz->config->min_rsz_height,
+				   rsz->config->max_rsz_height);
+
+	*format = *sink_fmt;
+
+	/* Update sink crop */
+	rkisp1_rsz_set_sink_crop(rsz, cfg, sink_crop, which);
+}
+
+static int rkisp1_rsz_get_fmt(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *fmt)
+{
+	struct rkisp1_resizer *rsz =
+		container_of(sd, struct rkisp1_resizer, sd);
+
+	fmt->format = *rkisp1_rsz_get_pad_fmt(rsz, cfg, fmt->pad, fmt->which);
+	return 0;
+}
+
+static int rkisp1_rsz_set_fmt(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *fmt)
+{
+	struct rkisp1_resizer *rsz =
+		container_of(sd, struct rkisp1_resizer, sd);
+
+	if (fmt->pad == RKISP1_RSZ_PAD_SINK)
+		rkisp1_rsz_set_sink_fmt(rsz, cfg, &fmt->format, fmt->which);
+	else
+		rkisp1_rsz_set_src_fmt(rsz, cfg, &fmt->format, fmt->which);
+
+	return 0;
+}
+
+static int rkisp1_rsz_get_selection(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_subdev_selection *sel)
+{
+	struct rkisp1_resizer *rsz =
+		container_of(sd, struct rkisp1_resizer, sd);
+	struct v4l2_mbus_framefmt *mf_sink;
+
+	if (sel->pad == RKISP1_RSZ_PAD_SRC)
+		return -EINVAL;
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+		mf_sink = rkisp1_rsz_get_pad_fmt(rsz, cfg, RKISP1_RSZ_PAD_SINK,
+						 sel->which);
+		sel->r.height = mf_sink->height;
+		sel->r.width = mf_sink->width;
+		sel->r.left = 0;
+		sel->r.top = 0;
+		break;
+	case V4L2_SEL_TGT_CROP:
+		sel->r = *rkisp1_rsz_get_pad_crop(rsz, cfg, RKISP1_RSZ_PAD_SINK,
+						  sel->which);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rkisp1_rsz_set_selection(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_pad_config *cfg,
+				    struct v4l2_subdev_selection *sel)
+{
+	struct rkisp1_resizer *rsz =
+		container_of(sd, struct rkisp1_resizer, sd);
+
+	if (sel->target != V4L2_SEL_TGT_CROP || sel->pad == RKISP1_RSZ_PAD_SRC)
+		return -EINVAL;
+
+	dev_dbg(sd->dev, "%s: pad: %d sel(%d,%d)/%dx%d\n", __func__,
+		sel->pad, sel->r.left, sel->r.top, sel->r.width, sel->r.height);
+
+	rkisp1_rsz_set_sink_crop(rsz, cfg, &sel->r, sel->which);
+
+	return 0;
+}
+
+static const struct media_entity_operations rkisp1_rsz_media_ops = {
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+static const struct v4l2_subdev_pad_ops rkisp1_rsz_pad_ops = {
+	.enum_mbus_code = rkisp1_rsz_enum_mbus_code,
+	.get_selection = rkisp1_rsz_get_selection,
+	.set_selection = rkisp1_rsz_set_selection,
+	.init_cfg = rkisp1_rsz_init_config,
+	.get_fmt = rkisp1_rsz_get_fmt,
+	.set_fmt = rkisp1_rsz_set_fmt,
+	.link_validate = v4l2_subdev_link_validate_default,
+};
+
+/* ----------------------------------------------------------------------------
+ * Stream operations
+ */
+
+static int rkisp1_rsz_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct rkisp1_resizer *rsz =
+		container_of(sd, struct rkisp1_resizer, sd);
+	struct rkisp1_device *rkisp1 = rsz->rkisp1;
+	struct rkisp1_capture *other = &rkisp1->capture_devs[rsz->id ^ 1];
+	enum rkisp1_shadow_regs_when when = RKISP1_SHADOW_REGS_SYNC;
+
+	if (!enable) {
+		rkisp1_dcrop_disable(rsz, RKISP1_SHADOW_REGS_ASYNC);
+		rkisp1_rsz_disable(rsz, RKISP1_SHADOW_REGS_ASYNC);
+		return 0;
+	}
+
+	if (other->is_streaming)
+		when = RKISP1_SHADOW_REGS_ASYNC;
+
+	rkisp1_rsz_config(rsz, when);
+	rkisp1_dcrop_config(rsz);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_video_ops rkisp1_rsz_video_ops = {
+	.s_stream = rkisp1_rsz_s_stream,
+};
+
+static const struct v4l2_subdev_ops rkisp1_rsz_ops = {
+	.video = &rkisp1_rsz_video_ops,
+	.pad = &rkisp1_rsz_pad_ops,
+};
+
+static void rkisp1_rsz_unregister(struct rkisp1_resizer *rsz)
+{
+	v4l2_device_unregister_subdev(&rsz->sd);
+	media_entity_cleanup(&rsz->sd.entity);
+}
+
+static int rkisp1_rsz_register(struct rkisp1_resizer *rsz)
+{
+	const char * const dev_names[] = {RKISP1_RSZ_MP_DEV_NAME,
+					  RKISP1_RSZ_SP_DEV_NAME};
+	struct media_pad *pads = rsz->pads;
+	struct v4l2_subdev *sd = &rsz->sd;
+	int ret;
+
+	if (rsz->id == RKISP1_SELFPATH)
+		rsz->config = &rkisp1_rsz_config_sp;
+	else
+		rsz->config = &rkisp1_rsz_config_mp;
+
+	v4l2_subdev_init(sd, &rkisp1_rsz_ops);
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	sd->entity.ops = &rkisp1_rsz_media_ops;
+	sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_SCALER;
+	sd->owner = THIS_MODULE;
+	strscpy(sd->name, dev_names[rsz->id], sizeof(sd->name));
+
+	pads[RKISP1_RSZ_PAD_SINK].flags = MEDIA_PAD_FL_SINK |
+					  MEDIA_PAD_FL_MUST_CONNECT;
+	pads[RKISP1_RSZ_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE |
+					 MEDIA_PAD_FL_MUST_CONNECT;
+
+	rsz->fmt_type = RKISP1_DEF_FMT_TYPE;
+
+	ret = media_entity_pads_init(&sd->entity, 2, pads);
+	if (ret)
+		return ret;
+
+	ret = v4l2_device_register_subdev(&rsz->rkisp1->v4l2_dev, sd);
+	if (ret) {
+		dev_err(sd->dev, "Failed to register resizer subdev\n");
+		goto err_cleanup_media_entity;
+	}
+
+	rkisp1_rsz_init_config(sd, rsz->pad_cfg);
+	return 0;
+
+err_cleanup_media_entity:
+	media_entity_cleanup(&sd->entity);
+
+	return ret;
+}
+
+int rkisp1_resizer_devs_register(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_resizer *rsz;
+	unsigned int i, j;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(rkisp1->resizer_devs); i++) {
+		rsz = &rkisp1->resizer_devs[i];
+		rsz->rkisp1 = rkisp1;
+		rsz->id = i;
+		ret = rkisp1_rsz_register(rsz);
+		if (ret)
+			goto err_unreg_resizer_devs;
+	}
+
+	return 0;
+
+err_unreg_resizer_devs:
+	for (j = 0; j < i; j++) {
+		rsz = &rkisp1->resizer_devs[j];
+		rkisp1_rsz_unregister(rsz);
+	}
+
+	return ret;
+}
+
+void rkisp1_resizer_devs_unregister(struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_resizer *mp = &rkisp1->resizer_devs[RKISP1_MAINPATH];
+	struct rkisp1_resizer *sp = &rkisp1->resizer_devs[RKISP1_SELFPATH];
+
+	rkisp1_rsz_unregister(mp);
+	rkisp1_rsz_unregister(sp);
+}
diff --git a/drivers/staging/media/rkisp1/rkisp1-stats.c b/drivers/staging/media/rkisp1/rkisp1-stats.c
new file mode 100644
index 000000000000..d98ea15837de
--- /dev/null
+++ b/drivers/staging/media/rkisp1/rkisp1-stats.c
@@ -0,0 +1,530 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Rockchip ISP1 Driver - Stats subdevice
+ *
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-ioctl.h>
+#include <media/videobuf2-core.h>
+#include <media/videobuf2-vmalloc.h>	/* for ISP statistics */
+
+#include "rkisp1-common.h"
+
+#define RKISP1_STATS_DEV_NAME	RKISP1_DRIVER_NAME "_stats"
+
+#define RKISP1_ISP_STATS_REQ_BUFS_MIN 2
+#define RKISP1_ISP_STATS_REQ_BUFS_MAX 8
+
+enum rkisp1_isp_readout_cmd {
+	RKISP1_ISP_READOUT_MEAS,
+	RKISP1_ISP_READOUT_META,
+};
+
+struct rkisp1_isp_readout_work {
+	struct work_struct work;
+	struct rkisp1_stats *stats;
+
+	unsigned int frame_id;
+	unsigned int isp_ris;
+	enum rkisp1_isp_readout_cmd readout;
+	struct vb2_buffer *vb;
+};
+
+static int rkisp1_stats_enum_fmt_meta_cap(struct file *file, void *priv,
+					  struct v4l2_fmtdesc *f)
+{
+	struct video_device *video = video_devdata(file);
+	struct rkisp1_stats *stats = video_get_drvdata(video);
+
+	if (f->index > 0 || f->type != video->queue->type)
+		return -EINVAL;
+
+	f->pixelformat = stats->vdev_fmt.fmt.meta.dataformat;
+	return 0;
+}
+
+static int rkisp1_stats_g_fmt_meta_cap(struct file *file, void *priv,
+				       struct v4l2_format *f)
+{
+	struct video_device *video = video_devdata(file);
+	struct rkisp1_stats *stats = video_get_drvdata(video);
+	struct v4l2_meta_format *meta = &f->fmt.meta;
+
+	if (f->type != video->queue->type)
+		return -EINVAL;
+
+	memset(meta, 0, sizeof(*meta));
+	meta->dataformat = stats->vdev_fmt.fmt.meta.dataformat;
+	meta->buffersize = stats->vdev_fmt.fmt.meta.buffersize;
+
+	return 0;
+}
+
+static int rkisp1_stats_querycap(struct file *file,
+				 void *priv, struct v4l2_capability *cap)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	strscpy(cap->driver, RKISP1_DRIVER_NAME, sizeof(cap->driver));
+	strscpy(cap->card, vdev->name, sizeof(cap->card));
+	strscpy(cap->bus_info, "platform: " RKISP1_DRIVER_NAME,
+		sizeof(cap->bus_info));
+
+	return 0;
+}
+
+/* ISP video device IOCTLs */
+static const struct v4l2_ioctl_ops rkisp1_stats_ioctl = {
+	.vidioc_reqbufs = vb2_ioctl_reqbufs,
+	.vidioc_querybuf = vb2_ioctl_querybuf,
+	.vidioc_create_bufs = vb2_ioctl_create_bufs,
+	.vidioc_qbuf = vb2_ioctl_qbuf,
+	.vidioc_dqbuf = vb2_ioctl_dqbuf,
+	.vidioc_prepare_buf = vb2_ioctl_prepare_buf,
+	.vidioc_expbuf = vb2_ioctl_expbuf,
+	.vidioc_streamon = vb2_ioctl_streamon,
+	.vidioc_streamoff = vb2_ioctl_streamoff,
+	.vidioc_enum_fmt_meta_cap = rkisp1_stats_enum_fmt_meta_cap,
+	.vidioc_g_fmt_meta_cap = rkisp1_stats_g_fmt_meta_cap,
+	.vidioc_s_fmt_meta_cap = rkisp1_stats_g_fmt_meta_cap,
+	.vidioc_try_fmt_meta_cap = rkisp1_stats_g_fmt_meta_cap,
+	.vidioc_querycap = rkisp1_stats_querycap,
+	.vidioc_subscribe_event = v4l2_ctrl_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+static const struct v4l2_file_operations rkisp1_stats_fops = {
+	.mmap = vb2_fop_mmap,
+	.unlocked_ioctl = video_ioctl2,
+	.poll = vb2_fop_poll,
+	.open = v4l2_fh_open,
+	.release = vb2_fop_release
+};
+
+static int rkisp1_stats_vb2_queue_setup(struct vb2_queue *vq,
+					unsigned int *num_buffers,
+					unsigned int *num_planes,
+					unsigned int sizes[],
+					struct device *alloc_devs[])
+{
+	struct rkisp1_stats *stats = vq->drv_priv;
+
+	*num_planes = 1;
+
+	*num_buffers = clamp_t(u32, *num_buffers, RKISP1_ISP_STATS_REQ_BUFS_MIN,
+			       RKISP1_ISP_STATS_REQ_BUFS_MAX);
+
+	sizes[0] = sizeof(struct rkisp1_stat_buffer);
+
+	INIT_LIST_HEAD(&stats->stat);
+
+	return 0;
+}
+
+static void rkisp1_stats_vb2_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rkisp1_buffer *stats_buf =
+		container_of(vbuf, struct rkisp1_buffer, vb);
+	struct vb2_queue *vq = vb->vb2_queue;
+	struct rkisp1_stats *stats_dev = vq->drv_priv;
+
+	stats_buf->vaddr[0] = vb2_plane_vaddr(vb, 0);
+
+	mutex_lock(&stats_dev->wq_lock);
+	list_add_tail(&stats_buf->queue, &stats_dev->stat);
+	mutex_unlock(&stats_dev->wq_lock);
+}
+
+static int rkisp1_stats_vb2_buf_prepare(struct vb2_buffer *vb)
+{
+	if (vb2_plane_size(vb, 0) < sizeof(struct rkisp1_stat_buffer))
+		return -EINVAL;
+
+	vb2_set_plane_payload(vb, 0, sizeof(struct rkisp1_stat_buffer));
+
+	return 0;
+}
+
+static void rkisp1_stats_vb2_stop_streaming(struct vb2_queue *vq)
+{
+	struct rkisp1_stats *stats = vq->drv_priv;
+	struct rkisp1_buffer *buf;
+	unsigned long flags;
+	unsigned int i;
+
+	/* Make sure no new work queued in isr before draining wq */
+	spin_lock_irqsave(&stats->irq_lock, flags);
+	stats->is_streaming = false;
+	spin_unlock_irqrestore(&stats->irq_lock, flags);
+
+	drain_workqueue(stats->readout_wq);
+
+	mutex_lock(&stats->wq_lock);
+	for (i = 0; i < RKISP1_ISP_STATS_REQ_BUFS_MAX; i++) {
+		if (list_empty(&stats->stat))
+			break;
+		buf = list_first_entry(&stats->stat,
+				       struct rkisp1_buffer, queue);
+		list_del(&buf->queue);
+		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
+	}
+	mutex_unlock(&stats->wq_lock);
+}
+
+static int
+rkisp1_stats_vb2_start_streaming(struct vb2_queue *queue, unsigned int count)
+{
+	struct rkisp1_stats *stats = queue->drv_priv;
+
+	stats->is_streaming = true;
+
+	return 0;
+}
+
+static const struct vb2_ops rkisp1_stats_vb2_ops = {
+	.queue_setup = rkisp1_stats_vb2_queue_setup,
+	.buf_queue = rkisp1_stats_vb2_buf_queue,
+	.buf_prepare = rkisp1_stats_vb2_buf_prepare,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
+	.stop_streaming = rkisp1_stats_vb2_stop_streaming,
+	.start_streaming = rkisp1_stats_vb2_start_streaming,
+};
+
+static int
+rkisp1_stats_init_vb2_queue(struct vb2_queue *q, struct rkisp1_stats *stats)
+{
+	struct rkisp1_vdev_node *node;
+
+	node = container_of(q, struct rkisp1_vdev_node, buf_queue);
+
+	q->type = V4L2_BUF_TYPE_META_CAPTURE;
+	q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
+	q->drv_priv = stats;
+	q->ops = &rkisp1_stats_vb2_ops;
+	q->mem_ops = &vb2_vmalloc_memops;
+	q->buf_struct_size = sizeof(struct rkisp1_buffer);
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->lock = &node->vlock;
+
+	return vb2_queue_init(q);
+}
+
+static void rkisp1_stats_get_awb_meas(struct rkisp1_stats *stats,
+				      struct rkisp1_stat_buffer *pbuf)
+{
+	/* Protect against concurrent access from ISR? */
+	struct rkisp1_device *rkisp1 = stats->rkisp1;
+	u32 reg_val;
+
+	pbuf->meas_type |= RKISP1_CIF_ISP_STAT_AWB;
+	reg_val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AWB_WHITE_CNT);
+	pbuf->params.awb.awb_mean[0].cnt =
+				RKISP1_CIF_ISP_AWB_GET_PIXEL_CNT(reg_val);
+	reg_val = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AWB_MEAN);
+
+	pbuf->params.awb.awb_mean[0].mean_cr_or_r =
+				RKISP1_CIF_ISP_AWB_GET_MEAN_CR_R(reg_val);
+	pbuf->params.awb.awb_mean[0].mean_cb_or_b =
+				RKISP1_CIF_ISP_AWB_GET_MEAN_CB_B(reg_val);
+	pbuf->params.awb.awb_mean[0].mean_y_or_g =
+				RKISP1_CIF_ISP_AWB_GET_MEAN_Y_G(reg_val);
+}
+
+static void rkisp1_stats_get_aec_meas(struct rkisp1_stats *stats,
+				      struct rkisp1_stat_buffer *pbuf)
+{
+	struct rkisp1_device *rkisp1 = stats->rkisp1;
+	unsigned int i;
+
+	pbuf->meas_type |= RKISP1_CIF_ISP_STAT_AUTOEXP;
+	for (i = 0; i < RKISP1_CIF_ISP_AE_MEAN_MAX; i++)
+		pbuf->params.ae.exp_mean[i] =
+			(u8)rkisp1_read(rkisp1,
+					RKISP1_CIF_ISP_EXP_MEAN_00 + i * 4);
+}
+
+static void rkisp1_stats_get_afc_meas(struct rkisp1_stats *stats,
+				      struct rkisp1_stat_buffer *pbuf)
+{
+	struct rkisp1_device *rkisp1 = stats->rkisp1;
+	struct rkisp1_cif_isp_af_stat *af;
+
+	pbuf->meas_type = RKISP1_CIF_ISP_STAT_AFM_FIN;
+
+	af = &pbuf->params.af;
+	af->window[0].sum = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AFM_SUM_A);
+	af->window[0].lum = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AFM_LUM_A);
+	af->window[1].sum = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AFM_SUM_B);
+	af->window[1].lum = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AFM_LUM_B);
+	af->window[2].sum = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AFM_SUM_C);
+	af->window[2].lum = rkisp1_read(rkisp1, RKISP1_CIF_ISP_AFM_LUM_C);
+}
+
+static void rkisp1_stats_get_hst_meas(struct rkisp1_stats *stats,
+				      struct rkisp1_stat_buffer *pbuf)
+{
+	struct rkisp1_device *rkisp1 = stats->rkisp1;
+	unsigned int i;
+
+	pbuf->meas_type |= RKISP1_CIF_ISP_STAT_HIST;
+	for (i = 0; i < RKISP1_CIF_ISP_HIST_BIN_N_MAX; i++)
+		pbuf->params.hist.hist_bins[i] =
+			(u8)rkisp1_read(rkisp1,
+					RKISP1_CIF_ISP_HIST_BIN_0 + i * 4);
+}
+
+static void rkisp1_stats_get_bls_meas(struct rkisp1_stats *stats,
+				      struct rkisp1_stat_buffer *pbuf)
+{
+	struct rkisp1_device *rkisp1 = stats->rkisp1;
+	const struct rkisp1_isp_mbus_info *in_fmt = rkisp1->isp.sink_fmt;
+	struct rkisp1_cif_isp_bls_meas_val *bls_val;
+
+	bls_val = &pbuf->params.ae.bls_val;
+	if (in_fmt->bayer_pat == RKISP1_RAW_BGGR) {
+		bls_val->meas_b =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_A_MEASURED);
+		bls_val->meas_gb =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_B_MEASURED);
+		bls_val->meas_gr =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_C_MEASURED);
+		bls_val->meas_r =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_D_MEASURED);
+	} else if (in_fmt->bayer_pat == RKISP1_RAW_GBRG) {
+		bls_val->meas_gb =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_A_MEASURED);
+		bls_val->meas_b =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_B_MEASURED);
+		bls_val->meas_r =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_C_MEASURED);
+		bls_val->meas_gr =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_D_MEASURED);
+	} else if (in_fmt->bayer_pat == RKISP1_RAW_GRBG) {
+		bls_val->meas_gr =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_A_MEASURED);
+		bls_val->meas_r =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_B_MEASURED);
+		bls_val->meas_b =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_C_MEASURED);
+		bls_val->meas_gb =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_D_MEASURED);
+	} else if (in_fmt->bayer_pat == RKISP1_RAW_RGGB) {
+		bls_val->meas_r =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_A_MEASURED);
+		bls_val->meas_gr =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_B_MEASURED);
+		bls_val->meas_gb =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_C_MEASURED);
+		bls_val->meas_b =
+			rkisp1_read(rkisp1, RKISP1_CIF_ISP_BLS_D_MEASURED);
+	}
+}
+
+static void
+rkisp1_stats_send_measurement(struct rkisp1_stats *stats,
+			      struct rkisp1_isp_readout_work *meas_work)
+{
+	struct rkisp1_stat_buffer *cur_stat_buf;
+	struct rkisp1_buffer *cur_buf = NULL;
+	unsigned int frame_sequence =
+		atomic_read(&stats->rkisp1->isp.frame_sequence);
+	u64 timestamp = ktime_get_ns();
+
+	if (frame_sequence != meas_work->frame_id) {
+		dev_warn(stats->rkisp1->dev,
+			 "Measurement late(%d, %d)\n",
+			 frame_sequence, meas_work->frame_id);
+		frame_sequence = meas_work->frame_id;
+	}
+
+	mutex_lock(&stats->wq_lock);
+	/* get one empty buffer */
+	if (!list_empty(&stats->stat)) {
+		cur_buf = list_first_entry(&stats->stat,
+					   struct rkisp1_buffer, queue);
+		list_del(&cur_buf->queue);
+	}
+	mutex_unlock(&stats->wq_lock);
+
+	if (!cur_buf)
+		return;
+
+	cur_stat_buf =
+		(struct rkisp1_stat_buffer *)(cur_buf->vaddr[0]);
+
+	if (meas_work->isp_ris & RKISP1_CIF_ISP_AWB_DONE) {
+		rkisp1_stats_get_awb_meas(stats, cur_stat_buf);
+		cur_stat_buf->meas_type |= RKISP1_CIF_ISP_STAT_AWB;
+	}
+
+	if (meas_work->isp_ris & RKISP1_CIF_ISP_AFM_FIN) {
+		rkisp1_stats_get_afc_meas(stats, cur_stat_buf);
+		cur_stat_buf->meas_type |= RKISP1_CIF_ISP_STAT_AFM_FIN;
+	}
+
+	if (meas_work->isp_ris & RKISP1_CIF_ISP_EXP_END) {
+		rkisp1_stats_get_aec_meas(stats, cur_stat_buf);
+		rkisp1_stats_get_bls_meas(stats, cur_stat_buf);
+		cur_stat_buf->meas_type |= RKISP1_CIF_ISP_STAT_AUTOEXP;
+	}
+
+	if (meas_work->isp_ris & RKISP1_CIF_ISP_HIST_MEASURE_RDY) {
+		rkisp1_stats_get_hst_meas(stats, cur_stat_buf);
+		cur_stat_buf->meas_type |= RKISP1_CIF_ISP_STAT_HIST;
+	}
+
+	vb2_set_plane_payload(&cur_buf->vb.vb2_buf, 0,
+			      sizeof(struct rkisp1_stat_buffer));
+	cur_buf->vb.sequence = frame_sequence;
+	cur_buf->vb.vb2_buf.timestamp = timestamp;
+	vb2_buffer_done(&cur_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
+}
+
+static void rkisp1_stats_readout_work(struct work_struct *work)
+{
+	struct rkisp1_isp_readout_work *readout_work =
+		container_of(work, struct rkisp1_isp_readout_work, work);
+	struct rkisp1_stats *stats = readout_work->stats;
+
+	if (readout_work->readout == RKISP1_ISP_READOUT_MEAS)
+		rkisp1_stats_send_measurement(stats, readout_work);
+
+	kfree(readout_work);
+}
+
+void rkisp1_stats_isr(struct rkisp1_stats *stats, u32 isp_ris)
+{
+	unsigned int frame_sequence =
+		atomic_read(&stats->rkisp1->isp.frame_sequence);
+	struct rkisp1_device *rkisp1 = stats->rkisp1;
+	struct rkisp1_isp_readout_work *work;
+	unsigned int isp_mis_tmp = 0;
+	u32 val;
+
+	spin_lock(&stats->irq_lock);
+
+	val = RKISP1_CIF_ISP_AWB_DONE | RKISP1_CIF_ISP_AFM_FIN |
+	      RKISP1_CIF_ISP_EXP_END | RKISP1_CIF_ISP_HIST_MEASURE_RDY;
+	rkisp1_write(rkisp1, val, RKISP1_CIF_ISP_ICR);
+
+	isp_mis_tmp = rkisp1_read(rkisp1, RKISP1_CIF_ISP_MIS);
+	if (isp_mis_tmp &
+	    (RKISP1_CIF_ISP_AWB_DONE | RKISP1_CIF_ISP_AFM_FIN |
+	     RKISP1_CIF_ISP_EXP_END | RKISP1_CIF_ISP_HIST_MEASURE_RDY))
+		rkisp1->debug.stats_error++;
+
+	if (!stats->is_streaming)
+		goto unlock;
+	if (isp_ris & (RKISP1_CIF_ISP_AWB_DONE |
+		       RKISP1_CIF_ISP_AFM_FIN |
+		       RKISP1_CIF_ISP_EXP_END |
+		       RKISP1_CIF_ISP_HIST_MEASURE_RDY)) {
+		work = kzalloc(sizeof(*work), GFP_ATOMIC);
+		if (work) {
+			INIT_WORK(&work->work,
+				  rkisp1_stats_readout_work);
+			work->readout = RKISP1_ISP_READOUT_MEAS;
+			work->stats = stats;
+			work->frame_id = frame_sequence;
+			work->isp_ris = isp_ris;
+			if (!queue_work(stats->readout_wq,
+					&work->work))
+				kfree(work);
+		} else {
+			dev_err(stats->rkisp1->dev,
+				"Could not allocate work\n");
+		}
+	}
+
+unlock:
+	spin_unlock(&stats->irq_lock);
+}
+
+static void rkisp1_init_stats(struct rkisp1_stats *stats)
+{
+	stats->vdev_fmt.fmt.meta.dataformat =
+		V4L2_META_FMT_RK_ISP1_STAT_3A;
+	stats->vdev_fmt.fmt.meta.buffersize =
+		sizeof(struct rkisp1_stat_buffer);
+}
+
+int rkisp1_stats_register(struct rkisp1_stats *stats,
+			  struct v4l2_device *v4l2_dev,
+			  struct rkisp1_device *rkisp1)
+{
+	struct rkisp1_vdev_node *node = &stats->vnode;
+	struct video_device *vdev = &node->vdev;
+	int ret;
+
+	stats->rkisp1 = rkisp1;
+	mutex_init(&stats->wq_lock);
+	mutex_init(&node->vlock);
+	INIT_LIST_HEAD(&stats->stat);
+	spin_lock_init(&stats->irq_lock);
+
+	strscpy(vdev->name, RKISP1_STATS_DEV_NAME, sizeof(vdev->name));
+
+	video_set_drvdata(vdev, stats);
+	vdev->ioctl_ops = &rkisp1_stats_ioctl;
+	vdev->fops = &rkisp1_stats_fops;
+	vdev->release = video_device_release_empty;
+	vdev->lock = &node->vlock;
+	vdev->v4l2_dev = v4l2_dev;
+	vdev->queue = &node->buf_queue;
+	vdev->device_caps = V4L2_CAP_META_CAPTURE | V4L2_CAP_STREAMING;
+	vdev->vfl_dir =  VFL_DIR_RX;
+	rkisp1_stats_init_vb2_queue(vdev->queue, stats);
+	rkisp1_init_stats(stats);
+	video_set_drvdata(vdev, stats);
+
+	node->pad.flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_pads_init(&vdev->entity, 1, &node->pad);
+	if (ret)
+		goto err_release_queue;
+
+	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
+	if (ret) {
+		dev_err(&vdev->dev,
+			"failed to register %s, ret=%d\n", vdev->name, ret);
+		goto err_cleanup_media_entity;
+	}
+
+	stats->readout_wq = alloc_workqueue("measurement_queue",
+					    WQ_UNBOUND | WQ_MEM_RECLAIM,
+					    1);
+
+	if (!stats->readout_wq) {
+		ret = -ENOMEM;
+		goto err_unreg_vdev;
+	}
+
+	return 0;
+
+err_unreg_vdev:
+	video_unregister_device(vdev);
+err_cleanup_media_entity:
+	media_entity_cleanup(&vdev->entity);
+err_release_queue:
+	vb2_queue_release(vdev->queue);
+	mutex_destroy(&node->vlock);
+	mutex_destroy(&stats->wq_lock);
+	return ret;
+}
+
+void rkisp1_stats_unregister(struct rkisp1_stats *stats)
+{
+	struct rkisp1_vdev_node *node = &stats->vnode;
+	struct video_device *vdev = &node->vdev;
+
+	destroy_workqueue(stats->readout_wq);
+	video_unregister_device(vdev);
+	media_entity_cleanup(&vdev->entity);
+	vb2_queue_release(vdev->queue);
+	mutex_destroy(&node->vlock);
+	mutex_destroy(&stats->wq_lock);
+}
diff --git a/drivers/staging/media/rkisp1/uapi/rkisp1-config.h b/drivers/staging/media/rkisp1/uapi/rkisp1-config.h
new file mode 100644
index 000000000000..ca0d031b14ac
--- /dev/null
+++ b/drivers/staging/media/rkisp1/uapi/rkisp1-config.h
@@ -0,0 +1,819 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+/*
+ * Rockchip ISP1 userspace API
+ * Copyright (C) 2017 Rockchip Electronics Co., Ltd.
+ */
+
+/*
+ * TODO: Improve documentation, mostly regarding abbreviation and hardware
+ * specificities. Reference: "REF_01 - ISP_user_manual, Rev 2.57" (not public)
+ */
+
+#ifndef _UAPI_RKISP1_CONFIG_H
+#define _UAPI_RKISP1_CONFIG_H
+
+#include <linux/types.h>
+
+/* Vendor specific - used for RK_ISP1 camera sub-system */
+#define V4L2_META_FMT_RK_ISP1_PARAMS   v4l2_fourcc('R', 'K', '1', 'P') /* Rockchip ISP1 params */
+#define V4L2_META_FMT_RK_ISP1_STAT_3A  v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A statistics */
+
+#define RKISP1_CIF_ISP_MODULE_DPCC		BIT(0)
+#define RKISP1_CIF_ISP_MODULE_BLS		BIT(1)
+#define RKISP1_CIF_ISP_MODULE_SDG		BIT(2)
+#define RKISP1_CIF_ISP_MODULE_HST		BIT(3)
+#define RKISP1_CIF_ISP_MODULE_LSC		BIT(4)
+#define RKISP1_CIF_ISP_MODULE_AWB_GAIN		BIT(5)
+#define RKISP1_CIF_ISP_MODULE_FLT		BIT(6)
+#define RKISP1_CIF_ISP_MODULE_BDM		BIT(7)
+#define RKISP1_CIF_ISP_MODULE_CTK		BIT(8)
+#define RKISP1_CIF_ISP_MODULE_GOC		BIT(9)
+#define RKISP1_CIF_ISP_MODULE_CPROC		BIT(10)
+#define RKISP1_CIF_ISP_MODULE_AFC		BIT(11)
+#define RKISP1_CIF_ISP_MODULE_AWB		BIT(12)
+#define RKISP1_CIF_ISP_MODULE_IE		BIT(13)
+#define RKISP1_CIF_ISP_MODULE_AEC		BIT(14)
+#define RKISP1_CIF_ISP_MODULE_WDR		BIT(15)
+#define RKISP1_CIF_ISP_MODULE_DPF		BIT(16)
+#define RKISP1_CIF_ISP_MODULE_DPF_STRENGTH	BIT(17)
+
+#define RKISP1_CIF_ISP_CTK_COEFF_MAX            0x100
+#define RKISP1_CIF_ISP_CTK_OFFSET_MAX           0x800
+
+#define RKISP1_CIF_ISP_AE_MEAN_MAX              25
+#define RKISP1_CIF_ISP_HIST_BIN_N_MAX           16
+#define RKISP1_CIF_ISP_AFM_MAX_WINDOWS          3
+#define RKISP1_CIF_ISP_DEGAMMA_CURVE_SIZE       17
+
+#define RKISP1_CIF_ISP_BDM_MAX_TH               0xff
+
+/*
+ * Black level compensation
+ */
+/* maximum value for horizontal start address */
+#define RKISP1_CIF_ISP_BLS_START_H_MAX             0x00000fff
+/* maximum value for horizontal stop address */
+#define RKISP1_CIF_ISP_BLS_STOP_H_MAX              0x00000fff
+/* maximum value for vertical start address */
+#define RKISP1_CIF_ISP_BLS_START_V_MAX             0x00000fff
+/* maximum value for vertical stop address */
+#define RKISP1_CIF_ISP_BLS_STOP_V_MAX              0x00000fff
+/* maximum is 2^18 = 262144*/
+#define RKISP1_CIF_ISP_BLS_SAMPLES_MAX             0x00000012
+/* maximum value for fixed black level */
+#define RKISP1_CIF_ISP_BLS_FIX_SUB_MAX             0x00000fff
+/* minimum value for fixed black level */
+#define RKISP1_CIF_ISP_BLS_FIX_SUB_MIN             0xfffff000
+/* 13 bit range (signed)*/
+#define RKISP1_CIF_ISP_BLS_FIX_MASK                0x00001fff
+
+/*
+ * Automatic white balance measurments
+ */
+#define RKISP1_CIF_ISP_AWB_MAX_GRID                1
+#define RKISP1_CIF_ISP_AWB_MAX_FRAMES              7
+
+/*
+ * Gamma out
+ */
+/* Maximum number of color samples supported */
+#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES       17
+
+/*
+ * Lens shade correction
+ */
+#define RKISP1_CIF_ISP_LSC_GRAD_TBL_SIZE           8
+#define RKISP1_CIF_ISP_LSC_SIZE_TBL_SIZE           8
+/*
+ * The following matches the tuning process,
+ * not the max capabilities of the chip.
+ * Last value unused.
+ */
+#define	RKISP1_CIF_ISP_LSC_DATA_TBL_SIZE           290
+
+/*
+ * Histogram calculation
+ */
+/* Last 3 values unused. */
+#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 28
+
+/*
+ * Defect Pixel Cluster Correction
+ */
+#define RKISP1_CIF_ISP_DPCC_METHODS_MAX       3
+
+/*
+ * Denoising pre filter
+ */
+#define RKISP1_CIF_ISP_DPF_MAX_NLF_COEFFS      17
+#define RKISP1_CIF_ISP_DPF_MAX_SPATIAL_COEFFS  6
+
+/*
+ * Measurement types
+ */
+#define RKISP1_CIF_ISP_STAT_AWB           BIT(0)
+#define RKISP1_CIF_ISP_STAT_AUTOEXP       BIT(1)
+#define RKISP1_CIF_ISP_STAT_AFM_FIN       BIT(2)
+#define RKISP1_CIF_ISP_STAT_HIST          BIT(3)
+
+enum rkisp1_cif_isp_histogram_mode {
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_DISABLE,
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_RGB_COMBINED,
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_R_HISTOGRAM,
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_G_HISTOGRAM,
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_B_HISTOGRAM,
+	RKISP1_CIF_ISP_HISTOGRAM_MODE_Y_HISTOGRAM
+};
+
+enum rkisp1_cif_isp_awb_mode_type {
+	RKISP1_CIF_ISP_AWB_MODE_MANUAL,
+	RKISP1_CIF_ISP_AWB_MODE_RGB,
+	RKISP1_CIF_ISP_AWB_MODE_YCBCR
+};
+
+enum rkisp1_cif_isp_flt_mode {
+	RKISP1_CIF_ISP_FLT_STATIC_MODE,
+	RKISP1_CIF_ISP_FLT_DYNAMIC_MODE
+};
+
+/**
+ * enum rkisp1_cif_isp_exp_ctrl_autostop - stop modes
+ * @RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP_0: continuous measurement
+ * @RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP_1: stop measuring after a complete frame
+ */
+enum rkisp1_cif_isp_exp_ctrl_autostop {
+	RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP_0 = 0,
+	RKISP1_CIF_ISP_EXP_CTRL_AUTOSTOP_1 = 1,
+};
+
+/**
+ * enum rkisp1_cif_isp_exp_meas_mode - Exposure measure mode
+ * @RKISP1_CIF_ISP_EXP_MEASURING_MODE_0: Y = 16 + 0.25R + 0.5G + 0.1094B
+ * @RKISP1_CIF_ISP_EXP_MEASURING_MODE_1: Y = (R + G + B) x (85/256)
+ */
+enum rkisp1_cif_isp_exp_meas_mode {
+	RKISP1_CIF_ISP_EXP_MEASURING_MODE_0,
+	RKISP1_CIF_ISP_EXP_MEASURING_MODE_1,
+};
+
+/*---------- PART1: Input Parameters ------------*/
+
+struct rkisp1_cif_isp_window {
+	__u16 h_offs;
+	__u16 v_offs;
+	__u16 h_size;
+	__u16 v_size;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_bls_fixed_val - BLS fixed subtraction values
+ *
+ * The values will be subtracted from the sensor
+ * values. Therefore a negative value means addition instead of subtraction!
+ *
+ * @r: Fixed (signed!) subtraction value for Bayer pattern R
+ * @gr: Fixed (signed!) subtraction value for Bayer pattern Gr
+ * @gb: Fixed (signed!) subtraction value for Bayer pattern Gb
+ * @b: Fixed (signed!) subtraction value for Bayer pattern B
+ */
+struct rkisp1_cif_isp_bls_fixed_val {
+	__s16 r;
+	__s16 gr;
+	__s16 gb;
+	__s16 b;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_bls_config - Configuration used by black level subtraction
+ *
+ * @enable_auto: Automatic mode activated means that the measured values
+ *		 are subtracted. Otherwise the fixed subtraction
+ *		 values will be subtracted.
+ * @en_windows: enabled window
+ * @bls_window1: Measurement window 1 size
+ * @bls_window2: Measurement window 2 size
+ * @bls_samples: Set amount of measured pixels for each Bayer position
+ *		 (A, B,C and D) to 2^bls_samples.
+ * @fixed_val: Fixed subtraction values
+ */
+struct rkisp1_cif_isp_bls_config {
+	__u8 enable_auto;
+	__u8 en_windows;
+	struct rkisp1_cif_isp_window bls_window1;
+	struct rkisp1_cif_isp_window bls_window2;
+	__u8 bls_samples;
+	struct rkisp1_cif_isp_bls_fixed_val fixed_val;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpcc_methods_config - Methods Configuration used by DPCC
+ *
+ * Methods Configuration used by Defect Pixel Cluster Correction
+ *
+ * @method: Method enable bits
+ * @line_thresh: Line threshold
+ * @line_mad_fac: Line MAD factor
+ * @pg_fac: Peak gradient factor
+ * @rnd_thresh: Rank Neighbor Difference threshold
+ * @rg_fac: Rank gradient factor
+ */
+struct rkisp1_cif_isp_dpcc_methods_config {
+	__u32 method;
+	__u32 line_thresh;
+	__u32 line_mad_fac;
+	__u32 pg_fac;
+	__u32 rnd_thresh;
+	__u32 rg_fac;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpcc_config - Configuration used by DPCC
+ *
+ * Configuration used by Defect Pixel Cluster Correction
+ *
+ * @mode: dpcc output mode
+ * @output_mode: whether use hard coded methods
+ * @set_use: stage1 methods set
+ * @methods: methods config
+ * @ro_limits: rank order limits
+ * @rnd_offs: differential rank offsets for rank neighbor difference
+ */
+struct rkisp1_cif_isp_dpcc_config {
+	__u32 mode;
+	__u32 output_mode;
+	__u32 set_use;
+	struct rkisp1_cif_isp_dpcc_methods_config methods[RKISP1_CIF_ISP_DPCC_METHODS_MAX];
+	__u32 ro_limits;
+	__u32 rnd_offs;
+} __packed;
+
+struct rkisp1_cif_isp_gamma_corr_curve {
+	__u16 gamma_y[RKISP1_CIF_ISP_DEGAMMA_CURVE_SIZE];
+} __packed;
+
+struct rkisp1_cif_isp_gamma_curve_x_axis_pnts {
+	__u32 gamma_dx0;
+	__u32 gamma_dx1;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_sdg_config - Configuration used by sensor degamma
+ *
+ * @curve_x: gamma curve point definition axis for x
+ * @xa_pnts: x increments
+ */
+struct rkisp1_cif_isp_sdg_config {
+	struct rkisp1_cif_isp_gamma_corr_curve curve_r;
+	struct rkisp1_cif_isp_gamma_corr_curve curve_g;
+	struct rkisp1_cif_isp_gamma_corr_curve curve_b;
+	struct rkisp1_cif_isp_gamma_curve_x_axis_pnts xa_pnts;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_lsc_config - Configuration used by Lens shading correction
+ *
+ * refer to REF_01 for details
+ */
+struct rkisp1_cif_isp_lsc_config {
+	__u32 r_data_tbl[RKISP1_CIF_ISP_LSC_DATA_TBL_SIZE];
+	__u32 gr_data_tbl[RKISP1_CIF_ISP_LSC_DATA_TBL_SIZE];
+	__u32 gb_data_tbl[RKISP1_CIF_ISP_LSC_DATA_TBL_SIZE];
+	__u32 b_data_tbl[RKISP1_CIF_ISP_LSC_DATA_TBL_SIZE];
+
+	__u32 x_grad_tbl[RKISP1_CIF_ISP_LSC_GRAD_TBL_SIZE];
+	__u32 y_grad_tbl[RKISP1_CIF_ISP_LSC_GRAD_TBL_SIZE];
+
+	__u32 x_size_tbl[RKISP1_CIF_ISP_LSC_SIZE_TBL_SIZE];
+	__u32 y_size_tbl[RKISP1_CIF_ISP_LSC_SIZE_TBL_SIZE];
+	__u16 config_width;
+	__u16 config_height;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_ie_config - Configuration used by image effects
+ *
+ * @eff_mat_1: 3x3 Matrix Coefficients for Emboss Effect 1
+ * @eff_mat_2: 3x3 Matrix Coefficients for Emboss Effect 2
+ * @eff_mat_3: 3x3 Matrix Coefficients for Emboss 3/Sketch 1
+ * @eff_mat_4: 3x3 Matrix Coefficients for Sketch Effect 2
+ * @eff_mat_5: 3x3 Matrix Coefficients for Sketch Effect 3
+ * @eff_tint: Chrominance increment values of tint (used for sepia effect)
+ */
+struct rkisp1_cif_isp_ie_config {
+	__u16 effect;
+	__u16 color_sel;
+	__u16 eff_mat_1;
+	__u16 eff_mat_2;
+	__u16 eff_mat_3;
+	__u16 eff_mat_4;
+	__u16 eff_mat_5;
+	__u16 eff_tint;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_cproc_config - Configuration used by Color Processing
+ *
+ * @c_out_range: Chrominance pixel clipping range at output.
+ *		 (0 for limit, 1 for full)
+ * @y_in_range: Luminance pixel clipping range at output.
+ * @y_out_range: Luminance pixel clipping range at output.
+ * @contrast: 00~ff, 0.0~1.992
+ * @brightness: 80~7F, -128~+127
+ * @sat: saturation, 00~FF, 0.0~1.992
+ * @hue: 80~7F, -90~+87.188
+ */
+struct rkisp1_cif_isp_cproc_config {
+	__u8 c_out_range;
+	__u8 y_in_range;
+	__u8 y_out_range;
+	__u8 contrast;
+	__u8 brightness;
+	__u8 sat;
+	__u8 hue;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_awb_meas_config - Configuration used by auto white balance
+ *
+ * @awb_wnd: white balance measurement window (in pixels)
+ *	     (from enum rkisp1_cif_isp_awb_mode_type)
+ * @max_y: only pixels values < max_y contribute to awb measurement, set to 0
+ *	   to disable this feature
+ * @min_y: only pixels values > min_y contribute to awb measurement
+ * @max_csum: Chrominance sum maximum value, only consider pixels with Cb+Cr,
+ *	      smaller than threshold for awb measurements
+ * @min_c: Chrominance minimum value, only consider pixels with Cb/Cr
+ *	   each greater than threshold value for awb measurements
+ * @frames: number of frames - 1 used for mean value calculation
+ *	    (ucFrames=0 means 1 Frame)
+ * @awb_ref_cr: reference Cr value for AWB regulation, target for AWB
+ * @awb_ref_cb: reference Cb value for AWB regulation, target for AWB
+ */
+struct rkisp1_cif_isp_awb_meas_config {
+	/*
+	 * Note: currently the h and v offsets are mapped to grid offsets
+	 */
+	struct rkisp1_cif_isp_window awb_wnd;
+	__u32 awb_mode;
+	__u8 max_y;
+	__u8 min_y;
+	__u8 max_csum;
+	__u8 min_c;
+	__u8 frames;
+	__u8 awb_ref_cr;
+	__u8 awb_ref_cb;
+	__u8 enable_ymax_cmp;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_awb_gain_config - Configuration used by auto white balance gain
+ *
+ * out_data_x = ( AWB_GEAIN_X * in_data + 128) >> 8
+ */
+struct rkisp1_cif_isp_awb_gain_config {
+	__u16 gain_red;
+	__u16 gain_green_r;
+	__u16 gain_blue;
+	__u16 gain_green_b;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_flt_config - Configuration used by ISP filtering
+ *
+ * @mode: ISP_FILT_MODE register fields (from enum rkisp1_cif_isp_flt_mode)
+ * @grn_stage1: ISP_FILT_MODE register fields
+ * @chr_h_mode: ISP_FILT_MODE register fields
+ * @chr_v_mode: ISP_FILT_MODE register fields
+ *
+ * refer to REF_01 for details.
+ */
+
+struct rkisp1_cif_isp_flt_config {
+	__u32 mode;
+	__u8 grn_stage1;
+	__u8 chr_h_mode;
+	__u8 chr_v_mode;
+	__u32 thresh_bl0;
+	__u32 thresh_bl1;
+	__u32 thresh_sh0;
+	__u32 thresh_sh1;
+	__u32 lum_weight;
+	__u32 fac_sh1;
+	__u32 fac_sh0;
+	__u32 fac_mid;
+	__u32 fac_bl0;
+	__u32 fac_bl1;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_bdm_config - Configuration used by Bayer DeMosaic
+ *
+ * @demosaic_th: threshod for bayer demosaicing texture detection
+ */
+struct rkisp1_cif_isp_bdm_config {
+	__u8 demosaic_th;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_ctk_config - Configuration used by Cross Talk correction
+ *
+ * @coeff: color correction matrix
+ * @ct_offset_b: offset for the crosstalk correction matrix
+ */
+struct rkisp1_cif_isp_ctk_config {
+	__u16 coeff0;
+	__u16 coeff1;
+	__u16 coeff2;
+	__u16 coeff3;
+	__u16 coeff4;
+	__u16 coeff5;
+	__u16 coeff6;
+	__u16 coeff7;
+	__u16 coeff8;
+	__u16 ct_offset_r;
+	__u16 ct_offset_g;
+	__u16 ct_offset_b;
+} __packed;
+
+enum rkisp1_cif_isp_goc_mode {
+	RKISP1_CIF_ISP_GOC_MODE_LOGARITHMIC,
+	RKISP1_CIF_ISP_GOC_MODE_EQUIDISTANT
+};
+
+/**
+ * struct rkisp1_cif_isp_goc_config - Configuration used by Gamma Out correction
+ *
+ * @mode: goc mode (from enum rkisp1_cif_isp_goc_mode)
+ * @gamma_y: gamma out curve y-axis for all color components
+ */
+struct rkisp1_cif_isp_goc_config {
+	__u32 mode;
+	__u16 gamma_y[RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES];
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_hst_config - Configuration used by Histogram
+ *
+ * @mode: histogram mode (from enum rkisp1_cif_isp_histogram_mode)
+ * @histogram_predivider: process every stepsize pixel, all other pixels are
+ *			  skipped
+ * @meas_window: coordinates of the measure window
+ * @hist_weight: weighting factor for sub-windows
+ */
+struct rkisp1_cif_isp_hst_config {
+	__u32 mode;
+	__u8 histogram_predivider;
+	struct rkisp1_cif_isp_window meas_window;
+	__u8 hist_weight[RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE];
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_aec_config - Configuration used by Auto Exposure Control
+ *
+ * @mode: Exposure measure mode (from enum rkisp1_cif_isp_exp_meas_mode)
+ * @autostop: stop mode (from enum rkisp1_cif_isp_exp_ctrl_autostop)
+ * @meas_window: coordinates of the measure window
+ */
+struct rkisp1_cif_isp_aec_config {
+	__u32 mode;
+	__u32 autostop;
+	struct rkisp1_cif_isp_window meas_window;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_afc_config - Configuration used by Auto Focus Control
+ *
+ * @num_afm_win: max RKISP1_CIF_ISP_AFM_MAX_WINDOWS
+ * @afm_win: coordinates of the meas window
+ * @thres: threshold used for minimizing the influence of noise
+ * @var_shift: the number of bits for the shift operation at the end of the
+ *	       calculation chain.
+ */
+struct rkisp1_cif_isp_afc_config {
+	__u8 num_afm_win;
+	struct rkisp1_cif_isp_window afm_win[RKISP1_CIF_ISP_AFM_MAX_WINDOWS];
+	__u32 thres;
+	__u32 var_shift;
+} __packed;
+
+/**
+ * enum rkisp1_cif_isp_dpf_gain_usage - dpf gain usage
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_DISABLED: don't use any gains in preprocessing stage
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_NF_GAINS: use only the noise function gains from
+ *				    registers DPF_NF_GAIN_R, ...
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_LSC_GAINS:  use only the gains from LSC module
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_NF_LSC_GAINS: use the noise function gains and the
+ *					gains from LSC module
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_AWB_GAINS: use only the gains from AWB module
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_AWB_LSC_GAINS: use the gains from AWB and LSC module
+ * @RKISP1_CIF_ISP_DPF_GAIN_USAGE_MAX: upper border (only for an internal evaluation)
+ */
+enum rkisp1_cif_isp_dpf_gain_usage {
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_DISABLED,
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_NF_GAINS,
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_LSC_GAINS,
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_NF_LSC_GAINS,
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_AWB_GAINS,
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_AWB_LSC_GAINS,
+	RKISP1_CIF_ISP_DPF_GAIN_USAGE_MAX
+};
+
+/**
+ * enum rkisp1_cif_isp_dpf_rb_filtersize - Red and blue filter sizes
+ * @RKISP1_CIF_ISP_DPF_RB_FILTERSIZE_13x9: red and blue filter kernel size 13x9
+ *				   (means 7x5 active pixel)
+ * @RKISP1_CIF_ISP_DPF_RB_FILTERSIZE_9x9: red and blue filter kernel size 9x9
+ *				   (means 5x5 active pixel)
+ */
+enum rkisp1_cif_isp_dpf_rb_filtersize {
+	RKISP1_CIF_ISP_DPF_RB_FILTERSIZE_13x9,
+	RKISP1_CIF_ISP_DPF_RB_FILTERSIZE_9x9,
+};
+
+/**
+ * enum rkisp1_cif_isp_dpf_nll_scale_mode - dpf noise level scale mode
+ * @RKISP1_CIF_ISP_NLL_SCALE_LINEAR: use a linear scaling
+ * @RKISP1_CIF_ISP_NLL_SCALE_LOGARITHMIC: use a logarithmic scaling
+ */
+enum rkisp1_cif_isp_dpf_nll_scale_mode {
+	RKISP1_CIF_ISP_NLL_SCALE_LINEAR,
+	RKISP1_CIF_ISP_NLL_SCALE_LOGARITHMIC,
+};
+
+/**
+ * struct rkisp1_cif_isp_dpf_nll - Noise level lookup
+ *
+ * @coeff: Noise level Lookup coefficient
+ * @scale_mode: dpf noise level scale mode (from enum rkisp1_cif_isp_dpf_nll_scale_mode)
+ */
+struct rkisp1_cif_isp_dpf_nll {
+	__u16 coeff[RKISP1_CIF_ISP_DPF_MAX_NLF_COEFFS];
+	__u32 scale_mode;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpf_rb_flt - Red blue filter config
+ *
+ * @fltsize: The filter size for the red and blue pixels
+ *	     (from enum rkisp1_cif_isp_dpf_rb_filtersize)
+ * @spatial_coeff: Spatial weights
+ * @r_enable: enable filter processing for red pixels
+ * @b_enable: enable filter processing for blue pixels
+ */
+struct rkisp1_cif_isp_dpf_rb_flt {
+	__u32 fltsize;
+	__u8 spatial_coeff[RKISP1_CIF_ISP_DPF_MAX_SPATIAL_COEFFS];
+	__u8 r_enable;
+	__u8 b_enable;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpf_g_flt - Green filter Configuration
+ *
+ * @spatial_coeff: Spatial weights
+ * @gr_enable: enable filter processing for green pixels in green/red lines
+ * @gb_enable: enable filter processing for green pixels in green/blue lines
+ */
+struct rkisp1_cif_isp_dpf_g_flt {
+	__u8 spatial_coeff[RKISP1_CIF_ISP_DPF_MAX_SPATIAL_COEFFS];
+	__u8 gr_enable;
+	__u8 gb_enable;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpf_gain - Noise function Configuration
+ *
+ * @mode: dpf gain usage  (from enum rkisp1_cif_isp_dpf_gain_usage)
+ * @nf_r_gain: Noise function Gain that replaces the AWB gain for red pixels
+ * @nf_b_gain: Noise function Gain that replaces the AWB gain for blue pixels
+ * @nf_gr_gain: Noise function Gain that replaces the AWB gain
+ *		for green pixels in a red line
+ * @nf_gb_gain: Noise function Gain that replaces the AWB gain
+ *		for green pixels in a blue line
+ */
+struct rkisp1_cif_isp_dpf_gain {
+	__u32 mode;
+	__u16 nf_r_gain;
+	__u16 nf_b_gain;
+	__u16 nf_gr_gain;
+	__u16 nf_gb_gain;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpf_config - Configuration used by De-noising pre-filter
+ *
+ * @gain: noise function gain
+ * @g_flt: green filter config
+ * @rb_flt: red blue filter config
+ * @nll: noise level lookup
+ */
+struct rkisp1_cif_isp_dpf_config {
+	struct rkisp1_cif_isp_dpf_gain gain;
+	struct rkisp1_cif_isp_dpf_g_flt g_flt;
+	struct rkisp1_cif_isp_dpf_rb_flt rb_flt;
+	struct rkisp1_cif_isp_dpf_nll nll;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_dpf_strength_config - strength of the filter
+ *
+ * @r: filter strength of the RED filter
+ * @g: filter strength of the GREEN filter
+ * @b: filter strength of the BLUE filter
+ */
+struct rkisp1_cif_isp_dpf_strength_config {
+	__u8 r;
+	__u8 g;
+	__u8 b;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_isp_other_cfg - Parameters for some blocks in rockchip isp1
+ *
+ * @dpcc_config: Defect Pixel Cluster Correction config
+ * @bls_config: Black Level Subtraction config
+ * @sdg_config: sensor degamma config
+ * @lsc_config: Lens Shade config
+ * @awb_gain_config: Auto White balance gain config
+ * @flt_config: filter config
+ * @bdm_config: demosaic config
+ * @ctk_config: cross talk config
+ * @goc_config: gamma out config
+ * @bls_config: black level subtraction config
+ * @dpf_config: De-noising pre-filter config
+ * @dpf_strength_config: dpf strength config
+ * @cproc_config: color process config
+ * @ie_config: image effects config
+ */
+struct rkisp1_cif_isp_isp_other_cfg {
+	struct rkisp1_cif_isp_dpcc_config dpcc_config;
+	struct rkisp1_cif_isp_bls_config bls_config;
+	struct rkisp1_cif_isp_sdg_config sdg_config;
+	struct rkisp1_cif_isp_lsc_config lsc_config;
+	struct rkisp1_cif_isp_awb_gain_config awb_gain_config;
+	struct rkisp1_cif_isp_flt_config flt_config;
+	struct rkisp1_cif_isp_bdm_config bdm_config;
+	struct rkisp1_cif_isp_ctk_config ctk_config;
+	struct rkisp1_cif_isp_goc_config goc_config;
+	struct rkisp1_cif_isp_dpf_config dpf_config;
+	struct rkisp1_cif_isp_dpf_strength_config dpf_strength_config;
+	struct rkisp1_cif_isp_cproc_config cproc_config;
+	struct rkisp1_cif_isp_ie_config ie_config;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_isp_meas_cfg - Rockchip ISP1 Measure Parameters
+ *
+ * @awb_meas_config: auto white balance config
+ * @hst_config: histogram config
+ * @aec_config: auto exposure config
+ * @afc_config: auto focus config
+ */
+struct rkisp1_cif_isp_isp_meas_cfg {
+	struct rkisp1_cif_isp_awb_meas_config awb_meas_config;
+	struct rkisp1_cif_isp_hst_config hst_config;
+	struct rkisp1_cif_isp_aec_config aec_config;
+	struct rkisp1_cif_isp_afc_config afc_config;
+} __packed;
+
+/**
+ * struct rkisp1_params_cfg - Rockchip ISP1 Input Parameters Meta Data
+ *
+ * @module_en_update: mask the enable bits of which module should be updated
+ * @module_ens: mask the enable value of each module, only update the module
+ *		which correspond bit was set in module_en_update
+ * @module_cfg_update: mask the config bits of which module should be updated
+ * @meas: measurement config
+ * @others: other config
+ */
+struct rkisp1_params_cfg {
+	__u32 module_en_update;
+	__u32 module_ens;
+	__u32 module_cfg_update;
+
+	struct rkisp1_cif_isp_isp_meas_cfg meas;
+	struct rkisp1_cif_isp_isp_other_cfg others;
+} __packed;
+
+/*---------- PART2: Measurement Statistics ------------*/
+
+/**
+ * struct rkisp1_cif_isp_awb_meas - AWB measured values
+ *
+ * @cnt: White pixel count, number of "white pixels" found during last
+ *	 measurement
+ * @mean_y_or_g: Mean value of Y within window and frames,
+ *		 Green if RGB is selected.
+ * @mean_cb_or_b: Mean value of Cb within window and frames,
+ *		  Blue if RGB is selected.
+ * @mean_cr_or_r: Mean value of Cr within window and frames,
+ *		  Red if RGB is selected.
+ */
+struct rkisp1_cif_isp_awb_meas {
+	__u32 cnt;
+	__u8 mean_y_or_g;
+	__u8 mean_cb_or_b;
+	__u8 mean_cr_or_r;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_awb_stat - statistics automatic white balance data
+ *
+ * @awb_mean: Mean measured data
+ */
+struct rkisp1_cif_isp_awb_stat {
+	struct rkisp1_cif_isp_awb_meas awb_mean[RKISP1_CIF_ISP_AWB_MAX_GRID];
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_bls_meas_val - BLS measured values
+ *
+ * @meas_r: Mean measured value for Bayer pattern R
+ * @meas_gr: Mean measured value for Bayer pattern Gr
+ * @meas_gb: Mean measured value for Bayer pattern Gb
+ * @meas_b: Mean measured value for Bayer pattern B
+ */
+struct rkisp1_cif_isp_bls_meas_val {
+	__u16 meas_r;
+	__u16 meas_gr;
+	__u16 meas_gb;
+	__u16 meas_b;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_ae_stat - statistics auto exposure data
+ *
+ * @exp_mean: Mean luminance value of block xx
+ * @bls_val:  BLS measured values
+ *
+ * Image is divided into 5x5 blocks.
+ */
+struct rkisp1_cif_isp_ae_stat {
+	__u8 exp_mean[RKISP1_CIF_ISP_AE_MEAN_MAX];
+	struct rkisp1_cif_isp_bls_meas_val bls_val;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_af_meas_val - AF measured values
+ *
+ * @sum: sharpness, refer to REF_01 for definition
+ * @lum: luminance, refer to REF_01 for definition
+ */
+struct rkisp1_cif_isp_af_meas_val {
+	__u32 sum;
+	__u32 lum;
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_af_stat - statistics auto focus data
+ *
+ * @window: AF measured value of window x
+ *
+ * The module measures the sharpness in 3 windows of selectable size via
+ * register settings(ISP_AFM_*_A/B/C)
+ */
+struct rkisp1_cif_isp_af_stat {
+	struct rkisp1_cif_isp_af_meas_val window[RKISP1_CIF_ISP_AFM_MAX_WINDOWS];
+} __packed;
+
+/**
+ * struct rkisp1_cif_isp_hist_stat - statistics histogram data
+ *
+ * @hist_bins: measured bin counters
+ *
+ * Measurement window divided into 25 sub-windows, set
+ * with ISP_HIST_XXX
+ */
+struct rkisp1_cif_isp_hist_stat {
+	__u16 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX];
+} __packed;
+
+/**
+ * struct rkisp1_stat_buffer - Rockchip ISP1 Statistics Data
+ *
+ * @rkisp1_cif_isp_awb_stat: statistics data for automatic white balance
+ * @rkisp1_cif_isp_ae_stat: statistics data for auto exposure
+ * @rkisp1_cif_isp_af_stat: statistics data for auto focus
+ * @rkisp1_cif_isp_hist_stat: statistics histogram data
+ */
+struct rkisp1_cif_isp_stat {
+	struct rkisp1_cif_isp_awb_stat awb;
+	struct rkisp1_cif_isp_ae_stat ae;
+	struct rkisp1_cif_isp_af_stat af;
+	struct rkisp1_cif_isp_hist_stat hist;
+} __packed;
+
+/**
+ * struct rkisp1_stat_buffer - Rockchip ISP1 Statistics Meta Data
+ *
+ * @meas_type: measurement types (RKISP1_CIF_ISP_STAT_ definitions)
+ * @frame_id: frame ID for sync
+ * @params: statistics data
+ */
+struct rkisp1_stat_buffer {
+	__u32 meas_type;
+	__u32 frame_id;
+	struct rkisp1_cif_isp_stat params;
+} __packed;
+
+#endif /* _UAPI_RKISP1_CONFIG_H */
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
index 6945dc74e1d7..ce497d0197df 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_h265.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2018 Bootlin
  */
 
+#include <linux/delay.h>
 #include <linux/types.h>
 
 #include <media/videobuf2-dma-contig.h>
@@ -220,6 +221,23 @@ static void cedrus_h265_pred_weight_write(struct cedrus_dev *dev,
 	}
 }
 
+static void cedrus_h265_skip_bits(struct cedrus_dev *dev, int num)
+{
+	int count = 0;
+
+	while (count < num) {
+		int tmp = min(num - count, 32);
+
+		cedrus_write(dev, VE_DEC_H265_TRIGGER,
+			     VE_DEC_H265_TRIGGER_FLUSH_BITS |
+			     VE_DEC_H265_TRIGGER_TYPE_N_BITS(tmp));
+		while (cedrus_read(dev, VE_DEC_H265_STATUS) & VE_DEC_H265_STATUS_VLD_BUSY)
+			udelay(1);
+
+		count += tmp;
+	}
+}
+
 static void cedrus_h265_setup(struct cedrus_ctx *ctx,
 			      struct cedrus_run *run)
 {
@@ -280,10 +298,9 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx,
 
 	/* Source offset and length in bits. */
 
-	reg = slice_params->data_bit_offset;
-	cedrus_write(dev, VE_DEC_H265_BITS_OFFSET, reg);
+	cedrus_write(dev, VE_DEC_H265_BITS_OFFSET, 0);
 
-	reg = slice_params->bit_size - slice_params->data_bit_offset;
+	reg = slice_params->bit_size;
 	cedrus_write(dev, VE_DEC_H265_BITS_LEN, reg);
 
 	/* Source beginning and end addresses. */
@@ -316,6 +333,8 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx,
 	/* Initialize bitstream access. */
 	cedrus_write(dev, VE_DEC_H265_TRIGGER, VE_DEC_H265_TRIGGER_INIT_SWDEC);
 
+	cedrus_h265_skip_bits(dev, slice_params->data_bit_offset);
+
 	/* Bitstream parameters. */
 
 	reg = VE_DEC_H265_DEC_NAL_HDR_NAL_UNIT_TYPE(slice_params->nal_unit_type) |
@@ -332,6 +351,7 @@ static void cedrus_h265_setup(struct cedrus_ctx *ctx,
 	      VE_DEC_H265_DEC_SPS_HDR_LOG2_DIFF_MAX_MIN_LUMA_CODING_BLOCK_SIZE(sps->log2_diff_max_min_luma_coding_block_size) |
 	      VE_DEC_H265_DEC_SPS_HDR_LOG2_MIN_LUMA_CODING_BLOCK_SIZE_MINUS3(sps->log2_min_luma_coding_block_size_minus3) |
 	      VE_DEC_H265_DEC_SPS_HDR_BIT_DEPTH_CHROMA_MINUS8(sps->bit_depth_chroma_minus8) |
+	      VE_DEC_H265_DEC_SPS_HDR_BIT_DEPTH_LUMA_MINUS8(sps->bit_depth_luma_minus8) |
 	      VE_DEC_H265_DEC_SPS_HDR_CHROMA_FORMAT_IDC(sps->chroma_format_idc);
 
 	reg |= VE_DEC_H265_FLAG(VE_DEC_H265_DEC_SPS_HDR_FLAG_STRONG_INTRA_SMOOTHING_ENABLE,
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
index 7beb03d3bb39..66b152f18d17 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_regs.h
@@ -424,6 +424,7 @@
 
 #define VE_DEC_H265_TRIGGER			(VE_ENGINE_DEC_H265 + 0x34)
 
+#define VE_DEC_H265_TRIGGER_TYPE_N_BITS(x)	(((x) & 0x3f) << 8)
 #define VE_DEC_H265_TRIGGER_STCD_VC1		(0x02 << 4)
 #define VE_DEC_H265_TRIGGER_STCD_AVS		(0x01 << 4)
 #define VE_DEC_H265_TRIGGER_STCD_HEVC		(0x00 << 4)
diff --git a/drivers/staging/media/tegra-vde/Kconfig b/drivers/staging/media/tegra-vde/Kconfig
index ba49ea50b8c0..0dc78afd09e0 100644
--- a/drivers/staging/media/tegra-vde/Kconfig
+++ b/drivers/staging/media/tegra-vde/Kconfig
@@ -3,7 +3,7 @@ config TEGRA_VDE
 	tristate "NVIDIA Tegra Video Decoder Engine driver"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	select DMA_SHARED_BUFFER
-	select IOMMU_IOVA if (IOMMU_SUPPORT || COMPILE_TEST)
+	select IOMMU_IOVA
 	select SRAM
 	help
 	    Say Y here to enable support for the NVIDIA Tegra video decoder
diff --git a/drivers/staging/media/tegra-vde/vde.c b/drivers/staging/media/tegra-vde/vde.c
index 3466daddf663..e18fd48981da 100644
--- a/drivers/staging/media/tegra-vde/vde.c
+++ b/drivers/staging/media/tegra-vde/vde.c
@@ -1150,8 +1150,7 @@ static int tegra_vde_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int tegra_vde_pm_suspend(struct device *dev)
+static __maybe_unused int tegra_vde_pm_suspend(struct device *dev)
 {
 	struct tegra_vde *vde = dev_get_drvdata(dev);
 	int err;
@@ -1165,7 +1164,7 @@ static int tegra_vde_pm_suspend(struct device *dev)
 	return 0;
 }
 
-static int tegra_vde_pm_resume(struct device *dev)
+static __maybe_unused int tegra_vde_pm_resume(struct device *dev)
 {
 	struct tegra_vde *vde = dev_get_drvdata(dev);
 	int err;
@@ -1178,7 +1177,6 @@ static int tegra_vde_pm_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops tegra_vde_pm_ops = {
 	SET_RUNTIME_PM_OPS(tegra_vde_runtime_suspend,
diff --git a/drivers/staging/media/tegra-vde/vde.h b/drivers/staging/media/tegra-vde/vde.h
index d369f1466bc7..5561291b0c88 100644
--- a/drivers/staging/media/tegra-vde/vde.h
+++ b/drivers/staging/media/tegra-vde/vde.h
@@ -10,11 +10,11 @@
 
 #include <linux/completion.h>
 #include <linux/dma-direction.h>
+#include <linux/iova.h>
 #include <linux/list.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
 #include <linux/types.h>
-#include <linux/iova.h>
 
 struct clk;
 struct dma_buf;
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c
index 4a6c3f674431..aa9dab8a4ae8 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_module.c
@@ -264,12 +264,12 @@ static int open_debug_level(struct inode *inode, struct file *file)
 	return single_open(file, show_debug_level, NULL);
 }
 
-static const struct file_operations fops = {
-	.open = open_debug_level,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.write = write_debug_level,
-	.release = single_release,
+static const struct proc_ops debug_level_proc_ops = {
+	.proc_open	= open_debug_level,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= write_debug_level,
+	.proc_release	= single_release,
 };
 
 int __init ieee80211_debug_init(void)
@@ -284,7 +284,7 @@ int __init ieee80211_debug_init(void)
 				" proc directory\n");
 		return -EIO;
 	}
-	e = proc_create("debug_level", 0644, ieee80211_proc, &fops);
+	e = proc_create("debug_level", 0644, ieee80211_proc, &debug_level_proc_ops);
 	if (!e) {
 		remove_proc_entry(DRV_NAME, init_net.proc_net);
 		ieee80211_proc = NULL;
diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c
index 1354a157e9af..6a38ff936389 100644
--- a/drivers/target/tcm_fc/tfc_io.c
+++ b/drivers/target/tcm_fc/tfc_io.c
@@ -221,7 +221,6 @@ void ft_recv_write_data(struct ft_cmd *cmd, struct fc_frame *fp)
 	ep = fc_seq_exch(seq);
 	lport = ep->lp;
 	if (cmd->was_ddp_setup) {
-		BUG_ON(!ep);
 		BUG_ON(!lport);
 		/*
 		 * Since DDP (Large Rx offload) was setup for this request,
diff --git a/drivers/tc/tc-driver.c b/drivers/tc/tc-driver.c
index 16b5bae63c74..d45f2c1ff341 100644
--- a/drivers/tc/tc-driver.c
+++ b/drivers/tc/tc-driver.c
@@ -56,8 +56,8 @@ EXPORT_SYMBOL(tc_unregister_driver);
  * system is in its list of supported devices.  Returns the matching
  * tc_device_id structure or %NULL if there is no match.
  */
-const struct tc_device_id *tc_match_device(struct tc_driver *tdrv,
-					   struct tc_dev *tdev)
+static const struct tc_device_id *tc_match_device(struct tc_driver *tdrv,
+						  struct tc_dev *tdev)
 {
 	const struct tc_device_id *id = tdrv->id_table;
 
@@ -71,7 +71,6 @@ const struct tc_device_id *tc_match_device(struct tc_driver *tdrv,
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(tc_match_device);
 
 /**
  * tc_bus_match - Tell if a device structure has a matching
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 09ddcd06c715..937ac5aaa6d8 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -71,11 +71,6 @@ static void tee_shm_op_release(struct dma_buf *dmabuf)
 	tee_shm_release(shm);
 }
 
-static void *tee_shm_op_map(struct dma_buf *dmabuf, unsigned long pgnum)
-{
-	return NULL;
-}
-
 static int tee_shm_op_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
 {
 	struct tee_shm *shm = dmabuf->priv;
@@ -93,7 +88,6 @@ static const struct dma_buf_ops tee_shm_dma_buf_ops = {
 	.map_dma_buf = tee_shm_op_map_dma_buf,
 	.unmap_dma_buf = tee_shm_op_unmap_dma_buf,
 	.release = tee_shm_op_release,
-	.map = tee_shm_op_map,
 	.mmap = tee_shm_op_mmap,
 };
 
diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 8c4d1244ee7a..7c447cd149e7 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -21,8 +21,6 @@
 
 #include "thermal_core.h"
 
-#define TO_MCELSIUS(c)			((c) * 1000)
-
 /* Thermal Manager Control and Status Register */
 #define PMU_TDC0_SW_RST_MASK		(0x1 << 1)
 #define PMU_TM_DISABLE_OFFS		0
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 75484d6c5056..432213272f1e 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/thermal.h>
+#include <linux/units.h>
 #include "int340x_thermal_zone.h"
 
 static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone,
@@ -34,7 +35,7 @@ static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone,
 		*temp = (unsigned long)conv_temp * 10;
 	} else
 		/* _TMP returns the temperature in tenths of degrees Kelvin */
-		*temp = DECI_KELVIN_TO_MILLICELSIUS(tmp);
+		*temp = deci_kelvin_to_millicelsius(tmp);
 
 	return 0;
 }
@@ -116,7 +117,7 @@ static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
 
 	snprintf(name, sizeof(name), "PAT%d", trip);
 	status = acpi_execute_simple_method(d->adev->handle, name,
-			MILLICELSIUS_TO_DECI_KELVIN(temp));
+			millicelsius_to_deci_kelvin(temp));
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
@@ -163,7 +164,7 @@ static int int340x_thermal_get_trip_config(acpi_handle handle, char *name,
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
-	*temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+	*temp = deci_kelvin_to_millicelsius(r);
 
 	return 0;
 }
diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c
index ed75a0c603e7..56401fd4708d 100644
--- a/drivers/thermal/intel/intel_pch_thermal.c
+++ b/drivers/thermal/intel/intel_pch_thermal.c
@@ -13,6 +13,7 @@
 #include <linux/pci.h>
 #include <linux/acpi.h>
 #include <linux/thermal.h>
+#include <linux/units.h>
 #include <linux/pm.h>
 
 /* Intel PCH thermal Device IDs */
@@ -93,7 +94,7 @@ static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
 		if (ACPI_SUCCESS(status)) {
 			unsigned long trip_temp;
 
-			trip_temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+			trip_temp = deci_kelvin_to_millicelsius(r);
 			if (trip_temp) {
 				ptd->psv_temp = trip_temp;
 				ptd->psv_trip_id = *nr_trips;
diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c
index 1cc5e6c5709e..ad9e3bf8fdf6 100644
--- a/drivers/thermal/st/stm_thermal.c
+++ b/drivers/thermal/st/stm_thermal.c
@@ -535,7 +535,7 @@ static int stm_thermal_probe(struct platform_device *pdev)
 	/* Configure and enable HW sensor */
 	ret = stm_thermal_prepare(sensor);
 	if (ret) {
-		dev_err(&pdev->dev, "Error preprare sensor: %d\n", ret);
+		dev_err(&pdev->dev, "Error prepare sensor: %d\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/tty/serial/8250/8250_ioc3.c b/drivers/tty/serial/8250/8250_ioc3.c
new file mode 100644
index 000000000000..4c405f1b9c67
--- /dev/null
+++ b/drivers/tty/serial/8250/8250_ioc3.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SGI IOC3 8250 UART driver
+ *
+ * Copyright (C) 2019 Thomas Bogendoerfer <tbogendoerfer@suse.de>
+ *
+ * based on code Copyright (C) 2005 Stanislaw Skowronek <skylark@unaligned.org>
+ *               Copyright (C) 2014 Joshua Kinard <kumba@gentoo.org>
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+
+#include "8250.h"
+
+#define IOC3_UARTCLK (22000000 / 3)
+
+struct ioc3_8250_data {
+	int line;
+};
+
+static unsigned int ioc3_serial_in(struct uart_port *p, int offset)
+{
+	return readb(p->membase + (offset ^ 3));
+}
+
+static void ioc3_serial_out(struct uart_port *p, int offset, int value)
+{
+	writeb(value, p->membase + (offset ^ 3));
+}
+
+static int serial8250_ioc3_probe(struct platform_device *pdev)
+{
+	struct ioc3_8250_data *data;
+	struct uart_8250_port up;
+	struct resource *r;
+	void __iomem *membase;
+	int irq, line;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r)
+		return -ENODEV;
+
+	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	membase = devm_ioremap_nocache(&pdev->dev, r->start, resource_size(r));
+	if (!membase)
+		return -ENOMEM;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		irq = 0; /* no interrupt -> use polling */
+
+	/* Register serial ports with 8250.c */
+	memset(&up, 0, sizeof(struct uart_8250_port));
+	up.port.iotype = UPIO_MEM;
+	up.port.uartclk = IOC3_UARTCLK;
+	up.port.type = PORT_16550A;
+	up.port.irq = irq;
+	up.port.flags = (UPF_BOOT_AUTOCONF | UPF_SHARE_IRQ);
+	up.port.dev = &pdev->dev;
+	up.port.membase = membase;
+	up.port.mapbase = r->start;
+	up.port.serial_in = ioc3_serial_in;
+	up.port.serial_out = ioc3_serial_out;
+	line = serial8250_register_8250_port(&up);
+	if (line < 0)
+		return line;
+
+	platform_set_drvdata(pdev, data);
+	return 0;
+}
+
+static int serial8250_ioc3_remove(struct platform_device *pdev)
+{
+	struct ioc3_8250_data *data = platform_get_drvdata(pdev);
+
+	serial8250_unregister_port(data->line);
+	return 0;
+}
+
+static struct platform_driver serial8250_ioc3_driver = {
+	.probe  = serial8250_ioc3_probe,
+	.remove = serial8250_ioc3_remove,
+	.driver = {
+		.name = "ioc3-serial8250",
+	}
+};
+
+module_platform_driver(serial8250_ioc3_driver);
+
+MODULE_AUTHOR("Thomas Bogendoerfer <tbogendoerfer@suse.de>");
+MODULE_DESCRIPTION("SGI IOC3 8250 UART driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index ffd167e886ae..f16824bbb573 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -381,6 +381,17 @@ config SERIAL_8250_EM
 	  port hardware found on the Emma Mobile line of processors.
 	  If unsure, say N.
 
+config SERIAL_8250_IOC3
+	tristate "SGI IOC3 8250 UART support"
+	depends on SGI_MFD_IOC3 && SERIAL_8250
+	select SERIAL_8250_EXTENDED
+	select SERIAL_8250_SHARE_IRQ
+	help
+	  Enable this if you have a SGI Origin or Octane machine. This module
+	  provides basic serial support by directly driving the UART chip
+	  behind the IOC3 device on those systems.  Maximum baud speed is
+	  38400bps using this driver.
+
 config SERIAL_8250_RT288X
 	bool "Ralink RT288x/RT305x/RT3662/RT3883 serial port support"
 	depends on SERIAL_8250
diff --git a/drivers/tty/serial/8250/Makefile b/drivers/tty/serial/8250/Makefile
index 08c1d8117506..51a6079d3f1f 100644
--- a/drivers/tty/serial/8250/Makefile
+++ b/drivers/tty/serial/8250/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_SERIAL_8250_FSL)		+= 8250_fsl.o
 obj-$(CONFIG_SERIAL_8250_MEN_MCB)	+= 8250_men_mcb.o
 obj-$(CONFIG_SERIAL_8250_DW)		+= 8250_dw.o
 obj-$(CONFIG_SERIAL_8250_EM)		+= 8250_em.o
+obj-$(CONFIG_SERIAL_8250_IOC3)		+= 8250_ioc3.o
 obj-$(CONFIG_SERIAL_8250_OMAP)		+= 8250_omap.o
 obj-$(CONFIG_SERIAL_8250_LPC18XX)	+= 8250_lpc18xx.o
 obj-$(CONFIG_SERIAL_8250_MT6577)	+= 8250_mtk.o
diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c
index 1d4f317a0e42..f724962a5906 100644
--- a/drivers/tty/sysrq.c
+++ b/drivers/tty/sysrq.c
@@ -1101,15 +1101,15 @@ static ssize_t write_sysrq_trigger(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations proc_sysrq_trigger_operations = {
-	.write		= write_sysrq_trigger,
-	.llseek		= noop_llseek,
+static const struct proc_ops sysrq_trigger_proc_ops = {
+	.proc_write	= write_sysrq_trigger,
+	.proc_lseek	= noop_llseek,
 };
 
 static void sysrq_init_procfs(void)
 {
 	if (!proc_create("sysrq-trigger", S_IWUSR, NULL,
-			 &proc_sysrq_trigger_operations))
+			 &sysrq_trigger_proc_ops))
 		pr_err("Failed to register proc interface\n");
 }
 
diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c
index 04c142c13075..64de9f1b874c 100644
--- a/drivers/usb/gadget/function/rndis.c
+++ b/drivers/usb/gadget/function/rndis.c
@@ -72,7 +72,7 @@ static rndis_resp_t *rndis_add_response(struct rndis_params *params,
 
 #ifdef CONFIG_USB_GADGET_DEBUG_FILES
 
-static const struct file_operations rndis_proc_fops;
+static const struct proc_ops rndis_proc_ops;
 
 #endif /* CONFIG_USB_GADGET_DEBUG_FILES */
 
@@ -902,7 +902,7 @@ struct rndis_params *rndis_register(void (*resp_avail)(void *v), void *v)
 
 		sprintf(name, NAME_TEMPLATE, i);
 		proc_entry = proc_create_data(name, 0660, NULL,
-					      &rndis_proc_fops, params);
+					      &rndis_proc_ops, params);
 		if (!proc_entry) {
 			kfree(params);
 			rndis_put_nr(i);
@@ -1164,13 +1164,12 @@ static int rndis_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, rndis_proc_show, PDE_DATA(inode));
 }
 
-static const struct file_operations rndis_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= rndis_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= rndis_proc_write,
+static const struct proc_ops rndis_proc_ops = {
+	.proc_open	= rndis_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= rndis_proc_write,
 };
 
 #define	NAME_TEMPLATE "driver/rndis-%03d"
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 7570c7602ab4..8ad14e5c02bf 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -74,7 +74,7 @@ static ssize_t create_store(struct kobject *kobj, struct device *dev,
 	return count;
 }
 
-MDEV_TYPE_ATTR_WO(create);
+static MDEV_TYPE_ATTR_WO(create);
 
 static void mdev_type_release(struct kobject *kobj)
 {
diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c
index f2983f0f84be..df4d96038cd4 100644
--- a/drivers/vfio/pci/vfio_pci_nvlink2.c
+++ b/drivers/vfio/pci/vfio_pci_nvlink2.c
@@ -97,8 +97,10 @@ static void vfio_pci_nvgpu_release(struct vfio_pci_device *vdev,
 
 	/* If there were any mappings at all... */
 	if (data->mm) {
-		ret = mm_iommu_put(data->mm, data->mem);
-		WARN_ON(ret);
+		if (data->mem) {
+			ret = mm_iommu_put(data->mm, data->mem);
+			WARN_ON(ret);
+		}
 
 		mmdrop(data->mm);
 	}
@@ -159,7 +161,7 @@ static int vfio_pci_nvgpu_mmap(struct vfio_pci_device *vdev,
 	data->useraddr = vma->vm_start;
 	data->mm = current->mm;
 
-	atomic_inc(&data->mm->mm_count);
+	mmgrab(data->mm);
 	ret = (int) mm_iommu_newdev(data->mm, data->useraddr,
 			vma_pages(vma), data->gpu_hpa, &data->mem);
 
diff --git a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
index 40d4fb9276ba..abdca900802d 100644
--- a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
+++ b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
@@ -24,7 +24,7 @@
 #define MDIO_AN_INT		0x8002
 #define MDIO_AN_INTMASK		0x8001
 
-static unsigned int xmdio_read(void *ioaddr, unsigned int mmd,
+static unsigned int xmdio_read(void __iomem *ioaddr, unsigned int mmd,
 			       unsigned int reg)
 {
 	unsigned int mmd_address, value;
@@ -35,7 +35,7 @@ static unsigned int xmdio_read(void *ioaddr, unsigned int mmd,
 	return value;
 }
 
-static void xmdio_write(void *ioaddr, unsigned int mmd,
+static void xmdio_write(void __iomem *ioaddr, unsigned int mmd,
 			unsigned int reg, unsigned int value)
 {
 	unsigned int mmd_address;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 26cef65b41e7..16b3adc508db 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -79,7 +79,7 @@ static long tce_iommu_mm_set(struct tce_container *container)
 	}
 	BUG_ON(!current->mm);
 	container->mm = current->mm;
-	atomic_inc(&container->mm->mm_count);
+	mmgrab(container->mm);
 
 	return 0;
 }
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 2ada8e6cdb88..a177bf2c6683 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -309,9 +309,8 @@ static int put_pfn(unsigned long pfn, int prot)
 {
 	if (!is_invalid_reserved_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
-		if (prot & IOMMU_WRITE)
-			SetPageDirty(page);
-		put_page(page);
+
+		unpin_user_pages_dirty_lock(&page, 1, prot & IOMMU_WRITE);
 		return 1;
 	}
 	return 0;
@@ -322,7 +321,6 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 {
 	struct page *page[1];
 	struct vm_area_struct *vma;
-	struct vm_area_struct *vmas[1];
 	unsigned int flags = 0;
 	int ret;
 
@@ -330,33 +328,14 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		flags |= FOLL_WRITE;
 
 	down_read(&mm->mmap_sem);
-	if (mm == current->mm) {
-		ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
-				     vmas);
-	} else {
-		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
-					    vmas, NULL);
-		/*
-		 * The lifetime of a vaddr_get_pfn() page pin is
-		 * userspace-controlled. In the fs-dax case this could
-		 * lead to indefinite stalls in filesystem operations.
-		 * Disallow attempts to pin fs-dax pages via this
-		 * interface.
-		 */
-		if (ret > 0 && vma_is_fsdax(vmas[0])) {
-			ret = -EOPNOTSUPP;
-			put_page(page[0]);
-		}
-	}
-	up_read(&mm->mmap_sem);
-
+	ret = pin_user_pages_remote(NULL, mm, vaddr, 1, flags | FOLL_LONGTERM,
+				    page, NULL, NULL);
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
-		return 0;
+		ret = 0;
+		goto done;
 	}
 
-	down_read(&mm->mmap_sem);
-
 	vaddr = untagged_addr(vaddr);
 
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
@@ -366,7 +345,7 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 		if (is_invalid_reserved_pfn(*pfn))
 			ret = 0;
 	}
-
+done:
 	up_read(&mm->mmap_sem);
 	return ret;
 }
diff --git a/drivers/video/backlight/ams369fg06.c b/drivers/video/backlight/ams369fg06.c
index 94ccb9042440..8a4361e95a11 100644
--- a/drivers/video/backlight/ams369fg06.c
+++ b/drivers/video/backlight/ams369fg06.c
@@ -11,7 +11,6 @@
 #include <linux/backlight.h>
 #include <linux/delay.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
 #include <linux/lcd.h>
 #include <linux/module.h>
 #include <linux/spi/spi.h>
diff --git a/drivers/video/backlight/bd6107.c b/drivers/video/backlight/bd6107.c
index d344fb03cb86..d5d5fb457e78 100644
--- a/drivers/video/backlight/bd6107.c
+++ b/drivers/video/backlight/bd6107.c
@@ -11,7 +11,7 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/fb.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/platform_data/bd6107.h>
@@ -71,6 +71,7 @@ struct bd6107 {
 	struct i2c_client *client;
 	struct backlight_device *backlight;
 	struct bd6107_platform_data *pdata;
+	struct gpio_desc *reset;
 };
 
 static int bd6107_write(struct bd6107 *bd, u8 reg, u8 data)
@@ -94,9 +95,10 @@ static int bd6107_backlight_update_status(struct backlight_device *backlight)
 		bd6107_write(bd, BD6107_MAINCNT1, brightness);
 		bd6107_write(bd, BD6107_LEDCNT1, BD6107_LEDCNT1_LEDONOFF1);
 	} else {
-		gpio_set_value(bd->pdata->reset, 0);
+		/* Assert the reset line (gpiolib will handle active low) */
+		gpiod_set_value(bd->reset, 1);
 		msleep(24);
-		gpio_set_value(bd->pdata->reset, 1);
+		gpiod_set_value(bd->reset, 0);
 	}
 
 	return 0;
@@ -125,8 +127,8 @@ static int bd6107_probe(struct i2c_client *client,
 	struct bd6107 *bd;
 	int ret;
 
-	if (pdata == NULL || !pdata->reset) {
-		dev_err(&client->dev, "No reset GPIO in platform data\n");
+	if (pdata == NULL) {
+		dev_err(&client->dev, "No platform data\n");
 		return -EINVAL;
 	}
 
@@ -144,10 +146,16 @@ static int bd6107_probe(struct i2c_client *client,
 	bd->client = client;
 	bd->pdata = pdata;
 
-	ret = devm_gpio_request_one(&client->dev, pdata->reset,
-				    GPIOF_DIR_OUT | GPIOF_INIT_LOW, "reset");
-	if (ret < 0) {
+	/*
+	 * Request the reset GPIO line with GPIOD_OUT_HIGH meaning asserted,
+	 * so in the machine descriptor table (or other hardware description),
+	 * the line should be flagged as active low so this will assert
+	 * the reset.
+	 */
+	bd->reset = devm_gpiod_get(&client->dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(bd->reset)) {
 		dev_err(&client->dev, "unable to request reset GPIO\n");
+		ret = PTR_ERR(bd->reset);
 		return ret;
 	}
 
diff --git a/drivers/video/backlight/qcom-wled.c b/drivers/video/backlight/qcom-wled.c
index d46052d8ff41..3d276b30a78c 100644
--- a/drivers/video/backlight/qcom-wled.c
+++ b/drivers/video/backlight/qcom-wled.c
@@ -956,8 +956,8 @@ static int wled_configure(struct wled *wled, int version)
 	struct wled_config *cfg = &wled->cfg;
 	struct device *dev = wled->dev;
 	const __be32 *prop_addr;
-	u32 size, val, c, string_len;
-	int rc, i, j;
+	u32 size, val, c;
+	int rc, i, j, string_len;
 
 	const struct wled_u32_opts *u32_opts = NULL;
 	const struct wled_u32_opts wled3_opts[] = {
diff --git a/drivers/video/fbdev/68328fb.c b/drivers/video/fbdev/68328fb.c
index d48e96088f76..9811f1bad8d4 100644
--- a/drivers/video/fbdev/68328fb.c
+++ b/drivers/video/fbdev/68328fb.c
@@ -96,7 +96,7 @@ static int mc68x328fb_pan_display(struct fb_var_screeninfo *var,
 			   struct fb_info *info);
 static int mc68x328fb_mmap(struct fb_info *info, struct vm_area_struct *vma);
 
-static struct fb_ops mc68x328fb_ops = {
+static const struct fb_ops mc68x328fb_ops = {
 	.fb_check_var	= mc68x328fb_check_var,
 	.fb_set_par	= mc68x328fb_set_par,
 	.fb_setcolreg	= mc68x328fb_setcolreg,
@@ -405,20 +405,8 @@ static int mc68x328fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
 int __init mc68x328fb_setup(char *options)
 {
-#if 0
-	char *this_opt;
-#endif
-
 	if (!options || !*options)
 		return 1;
-#if 0
-	while ((this_opt = strsep(&options, ",")) != NULL) {
-		if (!*this_opt)
-			continue;
-		if (!strncmp(this_opt, "disable", 7))
-			mc68x328fb_enable = 0;
-	}
-#endif
 	return 1;
 }
 
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index aa9541bf964b..f65991a67af2 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -2215,6 +2215,7 @@ config FB_HYPERV
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
 	select FB_DEFERRED_IO
+	select DMA_CMA if HAVE_DMA_CONTIGUOUS && CMA
 	help
 	  This framebuffer driver supports Microsoft Hyper-V Synthetic Video.
 
diff --git a/drivers/video/fbdev/acornfb.c b/drivers/video/fbdev/acornfb.c
index 7cacae5a8797..a3af49529173 100644
--- a/drivers/video/fbdev/acornfb.c
+++ b/drivers/video/fbdev/acornfb.c
@@ -604,7 +604,7 @@ acornfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops acornfb_ops = {
+static const struct fb_ops acornfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= acornfb_check_var,
 	.fb_set_par	= acornfb_set_par,
diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c
index 7de43be6ef2c..c3d55fc6c4e0 100644
--- a/drivers/video/fbdev/amba-clcd.c
+++ b/drivers/video/fbdev/amba-clcd.c
@@ -423,7 +423,7 @@ static int clcdfb_mmap(struct fb_info *info,
 	return ret;
 }
 
-static struct fb_ops clcdfb_ops = {
+static const struct fb_ops clcdfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= clcdfb_check_var,
 	.fb_set_par	= clcdfb_set_par,
diff --git a/drivers/video/fbdev/amifb.c b/drivers/video/fbdev/amifb.c
index 91ddc9602014..20e03e00b66d 100644
--- a/drivers/video/fbdev/amifb.c
+++ b/drivers/video/fbdev/amifb.c
@@ -3493,7 +3493,7 @@ static irqreturn_t amifb_interrupt(int irq, void *dev_id)
 }
 
 
-static struct fb_ops amifb_ops = {
+static const struct fb_ops amifb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= amifb_check_var,
 	.fb_set_par	= amifb_set_par,
diff --git a/drivers/video/fbdev/arcfb.c b/drivers/video/fbdev/arcfb.c
index a48741aab240..314ab82e01c0 100644
--- a/drivers/video/fbdev/arcfb.c
+++ b/drivers/video/fbdev/arcfb.c
@@ -491,7 +491,7 @@ static ssize_t arcfb_write(struct fb_info *info, const char __user *buf,
 	return err;
 }
 
-static struct fb_ops arcfb_ops = {
+static const struct fb_ops arcfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= arcfb_open,
 	.fb_read        = fb_sys_read,
diff --git a/drivers/video/fbdev/arkfb.c b/drivers/video/fbdev/arkfb.c
index f940e8b66b85..11ab9a153860 100644
--- a/drivers/video/fbdev/arkfb.c
+++ b/drivers/video/fbdev/arkfb.c
@@ -917,7 +917,7 @@ static int arkfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info
 
 /* Frame buffer operations */
 
-static struct fb_ops arkfb_ops = {
+static const struct fb_ops arkfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= arkfb_open,
 	.fb_release	= arkfb_release,
diff --git a/drivers/video/fbdev/asiliantfb.c b/drivers/video/fbdev/asiliantfb.c
index ea31054a28ca..3e006da47752 100644
--- a/drivers/video/fbdev/asiliantfb.c
+++ b/drivers/video/fbdev/asiliantfb.c
@@ -95,7 +95,7 @@ static int asiliantfb_set_par(struct fb_info *info);
 static int asiliantfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 				u_int transp, struct fb_info *info);
 
-static struct fb_ops asiliantfb_ops = {
+static const struct fb_ops asiliantfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= asiliantfb_check_var,
 	.fb_set_par	= asiliantfb_set_par,
diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c
index 5ff8e0320d95..d567f5d56c13 100644
--- a/drivers/video/fbdev/atmel_lcdfb.c
+++ b/drivers/video/fbdev/atmel_lcdfb.c
@@ -824,7 +824,7 @@ static int atmel_lcdfb_blank(int blank_mode, struct fb_info *info)
 	return ((blank_mode == FB_BLANK_NORMAL) ? 1 : 0);
 }
 
-static struct fb_ops atmel_lcdfb_ops = {
+static const struct fb_ops atmel_lcdfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= atmel_lcdfb_check_var,
 	.fb_set_par	= atmel_lcdfb_set_par,
diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c
index fc1e45d44719..d7e41c8dd533 100644
--- a/drivers/video/fbdev/aty/aty128fb.c
+++ b/drivers/video/fbdev/aty/aty128fb.c
@@ -509,7 +509,7 @@ static void aty128_bl_set_power(struct fb_info *info, int power);
 			  (readb(bios + (v) + 3) << 24))
 
 
-static struct fb_ops aty128fb_ops = {
+static const struct fb_ops aty128fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= aty128fb_check_var,
 	.fb_set_par	= aty128fb_set_par,
diff --git a/drivers/video/fbdev/aty/atyfb.h b/drivers/video/fbdev/aty/atyfb.h
index e5a347c58180..a7833bc98225 100644
--- a/drivers/video/fbdev/aty/atyfb.h
+++ b/drivers/video/fbdev/aty/atyfb.h
@@ -341,7 +341,7 @@ extern const u8 aty_postdividers[8];
      *  Hardware cursor support
      */
 
-extern int aty_init_cursor(struct fb_info *info);
+extern int aty_init_cursor(struct fb_info *info, struct fb_ops *atyfb_ops);
 
     /*
      *  Hardware acceleration
diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index 79d548746efd..175d2598f28e 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -1326,10 +1326,10 @@ static int atyfb_set_par(struct fb_info *info)
 	par->accel_flags = var->accel_flags; /* hack */
 
 	if (var->accel_flags) {
-		info->fbops->fb_sync = atyfb_sync;
+		atyfb_ops.fb_sync = atyfb_sync;
 		info->flags &= ~FBINFO_HWACCEL_DISABLED;
 	} else {
-		info->fbops->fb_sync = NULL;
+		atyfb_ops.fb_sync = NULL;
 		info->flags |= FBINFO_HWACCEL_DISABLED;
 	}
 
@@ -2712,7 +2712,7 @@ static int aty_init(struct fb_info *info)
 
 #ifdef CONFIG_FB_ATY_CT
 	if (!noaccel && M64_HAS(INTEGRATED))
-		aty_init_cursor(info);
+		aty_init_cursor(info, &atyfb_ops);
 #endif /* CONFIG_FB_ATY_CT */
 	info->var = var;
 
diff --git a/drivers/video/fbdev/aty/mach64_cursor.c b/drivers/video/fbdev/aty/mach64_cursor.c
index 4cde25eab8e8..b06fa6e42e6e 100644
--- a/drivers/video/fbdev/aty/mach64_cursor.c
+++ b/drivers/video/fbdev/aty/mach64_cursor.c
@@ -194,7 +194,7 @@ static int atyfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 	return 0;
 }
 
-int aty_init_cursor(struct fb_info *info)
+int aty_init_cursor(struct fb_info *info, struct fb_ops *atyfb_ops)
 {
 	unsigned long addr;
 
@@ -219,7 +219,7 @@ int aty_init_cursor(struct fb_info *info)
 	info->sprite.buf_align = 16; 	/* and 64 lines tall. */
 	info->sprite.flags = FB_PIXMAP_IO;
 
-	info->fbops->fb_cursor = atyfb_cursor;
+	atyfb_ops->fb_cursor = atyfb_cursor;
 
 	return 0;
 }
diff --git a/drivers/video/fbdev/aty/radeon_base.c b/drivers/video/fbdev/aty/radeon_base.c
index 4ca07866f2f6..3af00e3b965e 100644
--- a/drivers/video/fbdev/aty/radeon_base.c
+++ b/drivers/video/fbdev/aty/radeon_base.c
@@ -1965,7 +1965,7 @@ static int radeonfb_set_par(struct fb_info *info)
 }
 
 
-static struct fb_ops radeonfb_ops = {
+static const struct fb_ops radeonfb_ops = {
 	.owner			= THIS_MODULE,
 	.fb_check_var		= radeonfb_check_var,
 	.fb_set_par		= radeonfb_set_par,
diff --git a/drivers/video/fbdev/au1100fb.c b/drivers/video/fbdev/au1100fb.c
index 99941ae1f3a1..37a6512feda0 100644
--- a/drivers/video/fbdev/au1100fb.c
+++ b/drivers/video/fbdev/au1100fb.c
@@ -348,7 +348,7 @@ int au1100fb_fb_mmap(struct fb_info *fbi, struct vm_area_struct *vma)
 			fbdev->fb_len);
 }
 
-static struct fb_ops au1100fb_ops =
+static const struct fb_ops au1100fb_ops =
 {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= au1100fb_fb_setcolreg,
diff --git a/drivers/video/fbdev/au1200fb.c b/drivers/video/fbdev/au1200fb.c
index 265d3b45efd0..c00e01a17368 100644
--- a/drivers/video/fbdev/au1200fb.c
+++ b/drivers/video/fbdev/au1200fb.c
@@ -1483,7 +1483,7 @@ static int au1200fb_ioctl(struct fb_info *info, unsigned int cmd,
 }
 
 
-static struct fb_ops au1200fb_fb_ops = {
+static const struct fb_ops au1200fb_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= au1200fb_fb_check_var,
 	.fb_set_par	= au1200fb_fb_set_par,
diff --git a/drivers/video/fbdev/broadsheetfb.c b/drivers/video/fbdev/broadsheetfb.c
index d6ba348deb9f..fd66f4d4a621 100644
--- a/drivers/video/fbdev/broadsheetfb.c
+++ b/drivers/video/fbdev/broadsheetfb.c
@@ -1048,7 +1048,7 @@ static ssize_t broadsheetfb_write(struct fb_info *info, const char __user *buf,
 	return (err) ? err : count;
 }
 
-static struct fb_ops broadsheetfb_ops = {
+static const struct fb_ops broadsheetfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_read        = fb_sys_read,
 	.fb_write	= broadsheetfb_write,
diff --git a/drivers/video/fbdev/bw2.c b/drivers/video/fbdev/bw2.c
index 436f10f3d375..0d9a6bb57a09 100644
--- a/drivers/video/fbdev/bw2.c
+++ b/drivers/video/fbdev/bw2.c
@@ -37,7 +37,7 @@ static int bw2_ioctl(struct fb_info *, unsigned int, unsigned long);
  *  Frame buffer operations
  */
 
-static struct fb_ops bw2_ops = {
+static const struct fb_ops bw2_ops = {
 	.owner			= THIS_MODULE,
 	.fb_blank		= bw2_blank,
 	.fb_fillrect		= cfb_fillrect,
diff --git a/drivers/video/fbdev/carminefb.c b/drivers/video/fbdev/carminefb.c
index 27ba2ed4138a..3a1c2e0739a1 100644
--- a/drivers/video/fbdev/carminefb.c
+++ b/drivers/video/fbdev/carminefb.c
@@ -527,7 +527,7 @@ static int init_hardware(struct carmine_hw *hw)
 	return 0;
 }
 
-static struct fb_ops carminefb_ops = {
+static const struct fb_ops carminefb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_fillrect	= cfb_fillrect,
 	.fb_copyarea	= cfb_copyarea,
diff --git a/drivers/video/fbdev/cg14.c b/drivers/video/fbdev/cg14.c
index d80d99db3a46..a620b51cf7d0 100644
--- a/drivers/video/fbdev/cg14.c
+++ b/drivers/video/fbdev/cg14.c
@@ -39,7 +39,7 @@ static int cg14_pan_display(struct fb_var_screeninfo *, struct fb_info *);
  *  Frame buffer operations
  */
 
-static struct fb_ops cg14_ops = {
+static const struct fb_ops cg14_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= cg14_setcolreg,
 	.fb_pan_display		= cg14_pan_display,
diff --git a/drivers/video/fbdev/cg3.c b/drivers/video/fbdev/cg3.c
index 09f616dddfd7..77f6470ce665 100644
--- a/drivers/video/fbdev/cg3.c
+++ b/drivers/video/fbdev/cg3.c
@@ -39,7 +39,7 @@ static int cg3_ioctl(struct fb_info *, unsigned int, unsigned long);
  *  Frame buffer operations
  */
 
-static struct fb_ops cg3_ops = {
+static const struct fb_ops cg3_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= cg3_setcolreg,
 	.fb_blank		= cg3_blank,
diff --git a/drivers/video/fbdev/cg6.c b/drivers/video/fbdev/cg6.c
index d5888aecc2fb..a1c68cd48d7e 100644
--- a/drivers/video/fbdev/cg6.c
+++ b/drivers/video/fbdev/cg6.c
@@ -44,7 +44,7 @@ static int cg6_pan_display(struct fb_var_screeninfo *, struct fb_info *);
  *  Frame buffer operations
  */
 
-static struct fb_ops cg6_ops = {
+static const struct fb_ops cg6_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= cg6_setcolreg,
 	.fb_blank		= cg6_blank,
diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c
index f4dc320dcafe..998067b701fa 100644
--- a/drivers/video/fbdev/chipsfb.c
+++ b/drivers/video/fbdev/chipsfb.c
@@ -79,7 +79,7 @@ static int chipsfb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
 			     u_int transp, struct fb_info *info);
 static int chipsfb_blank(int blank, struct fb_info *info);
 
-static struct fb_ops chipsfb_ops = {
+static const struct fb_ops chipsfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= chipsfb_check_var,
 	.fb_set_par	= chipsfb_set_par,
diff --git a/drivers/video/fbdev/cirrusfb.c b/drivers/video/fbdev/cirrusfb.c
index e4ce5667b125..c3a3e344cee3 100644
--- a/drivers/video/fbdev/cirrusfb.c
+++ b/drivers/video/fbdev/cirrusfb.c
@@ -1956,7 +1956,7 @@ static void cirrusfb_zorro_unmap(struct fb_info *info)
 #endif /* CONFIG_ZORRO */
 
 /* function table of the above functions */
-static struct fb_ops cirrusfb_ops = {
+static const struct fb_ops cirrusfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= cirrusfb_open,
 	.fb_release	= cirrusfb_release,
diff --git a/drivers/video/fbdev/clps711x-fb.c b/drivers/video/fbdev/clps711x-fb.c
index cabbc721f894..c5d15c6db287 100644
--- a/drivers/video/fbdev/clps711x-fb.c
+++ b/drivers/video/fbdev/clps711x-fb.c
@@ -153,7 +153,7 @@ static int clps711x_fb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops clps711x_fb_ops = {
+static const struct fb_ops clps711x_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= clps711x_fb_setcolreg,
 	.fb_check_var	= clps711x_fb_check_var,
diff --git a/drivers/video/fbdev/cobalt_lcdfb.c b/drivers/video/fbdev/cobalt_lcdfb.c
index 544946901e8b..5f8b6324d2e8 100644
--- a/drivers/video/fbdev/cobalt_lcdfb.c
+++ b/drivers/video/fbdev/cobalt_lcdfb.c
@@ -269,7 +269,7 @@ static int cobalt_lcdfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 	return 0;
 }
 
-static struct fb_ops cobalt_lcd_fbops = {
+static const struct fb_ops cobalt_lcd_fbops = {
 	.owner		= THIS_MODULE,
 	.fb_read	= cobalt_lcdfb_read,
 	.fb_write	= cobalt_lcdfb_write,
diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c
index 9a680ef3ffc3..38b61cdb5ca4 100644
--- a/drivers/video/fbdev/controlfb.c
+++ b/drivers/video/fbdev/controlfb.c
@@ -157,7 +157,7 @@ static int default_vmode __initdata = VMODE_NVRAM;
 static int default_cmode __initdata = CMODE_NVRAM;
 
 
-static struct fb_ops controlfb_ops = {
+static const struct fb_ops controlfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= controlfb_check_var,
 	.fb_set_par	= controlfb_set_par,
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index 82c20c6047b0..a591d291b231 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -171,7 +171,6 @@ int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma)
 	vma->vm_private_data = info;
 	return 0;
 }
-EXPORT_SYMBOL(fb_deferred_io_mmap);
 
 /* workqueue callback */
 static void fb_deferred_io_work(struct work_struct *work)
@@ -206,7 +205,6 @@ void fb_deferred_io_init(struct fb_info *info)
 
 	BUG_ON(!fbdefio);
 	mutex_init(&fbdefio->lock);
-	info->fbops->fb_mmap = fb_deferred_io_mmap;
 	INIT_DELAYED_WORK(&info->deferred_work, fb_deferred_io_work);
 	INIT_LIST_HEAD(&fbdefio->pagelist);
 	if (fbdefio->delay == 0) /* set a default of 1 s */
@@ -237,7 +235,6 @@ void fb_deferred_io_cleanup(struct fb_info *info)
 		page->mapping = NULL;
 	}
 
-	info->fbops->fb_mmap = NULL;
 	mutex_destroy(&fbdefio->lock);
 }
 EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup);
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index c9235a2f42f8..bb6ae995c2e5 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -536,6 +536,13 @@ static int __init fb_console_setup(char *this_opt)
 				fb_center_logo = true;
 			continue;
 		}
+
+		if (!strncmp(options, "logo-count:", 11)) {
+			options += 11;
+			if (*options)
+				fb_logo_count = simple_strtol(options, &options, 0);
+			continue;
+		}
 	}
 	return 1;
 }
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 6f6fc785b545..d04554959ea7 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -54,7 +54,8 @@ int num_registered_fb __read_mostly;
 EXPORT_SYMBOL(num_registered_fb);
 
 bool fb_center_logo __read_mostly;
-EXPORT_SYMBOL(fb_center_logo);
+
+int fb_logo_count __read_mostly = -1;
 
 static struct fb_info *get_fb_info(unsigned int idx)
 {
@@ -620,7 +621,7 @@ int fb_prepare_logo(struct fb_info *info, int rotate)
 	memset(&fb_logo, 0, sizeof(struct logo_data));
 
 	if (info->flags & FBINFO_MISC_TILEBLITTING ||
-	    info->fbops->owner)
+	    info->fbops->owner || !fb_logo_count)
 		return 0;
 
 	if (info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
@@ -686,10 +687,14 @@ int fb_prepare_logo(struct fb_info *info, int rotate)
 
 int fb_show_logo(struct fb_info *info, int rotate)
 {
+	unsigned int count;
 	int y;
 
-	y = fb_show_logo_line(info, rotate, fb_logo.logo, 0,
-			      num_online_cpus());
+	if (!fb_logo_count)
+		return 0;
+
+	count = fb_logo_count < 0 ? num_online_cpus() : fb_logo_count;
+	y = fb_show_logo_line(info, rotate, fb_logo.logo, 0, count);
 	y = fb_show_extra_logos(info, y, rotate);
 
 	return y;
@@ -1079,7 +1084,7 @@ EXPORT_SYMBOL(fb_blank);
 static long do_fb_ioctl(struct fb_info *info, unsigned int cmd,
 			unsigned long arg)
 {
-	struct fb_ops *fb;
+	const struct fb_ops *fb;
 	struct fb_var_screeninfo var;
 	struct fb_fix_screeninfo fix;
 	struct fb_cmap cmap_from;
@@ -1292,7 +1297,7 @@ static long fb_compat_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg)
 {
 	struct fb_info *info = file_fb_info(file);
-	struct fb_ops *fb;
+	const struct fb_ops *fb;
 	long ret = -ENOIOCTLCMD;
 
 	if (!info)
@@ -1332,16 +1337,23 @@ static int
 fb_mmap(struct file *file, struct vm_area_struct * vma)
 {
 	struct fb_info *info = file_fb_info(file);
-	struct fb_ops *fb;
+	int (*fb_mmap_fn)(struct fb_info *info, struct vm_area_struct *vma);
 	unsigned long mmio_pgoff;
 	unsigned long start;
 	u32 len;
 
 	if (!info)
 		return -ENODEV;
-	fb = info->fbops;
 	mutex_lock(&info->mm_lock);
-	if (fb->fb_mmap) {
+
+	fb_mmap_fn = info->fbops->fb_mmap;
+
+#if IS_ENABLED(CONFIG_FB_DEFERRED_IO)
+	if (info->fbdefio)
+		fb_mmap_fn = fb_deferred_io_mmap;
+#endif
+
+	if (fb_mmap_fn) {
 		int res;
 
 		/*
@@ -1349,7 +1361,7 @@ fb_mmap(struct file *file, struct vm_area_struct * vma)
 		 * SME protection is removed ahead of the call
 		 */
 		vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
-		res = fb->fb_mmap(info, vma);
+		res = fb_mmap_fn(info, vma);
 		mutex_unlock(&info->mm_lock);
 		return res;
 	}
@@ -1673,7 +1685,7 @@ static void unbind_console(struct fb_info *fb_info)
 	console_unlock();
 }
 
-void unlink_framebuffer(struct fb_info *fb_info)
+static void unlink_framebuffer(struct fb_info *fb_info)
 {
 	int i;
 
@@ -1692,7 +1704,6 @@ void unlink_framebuffer(struct fb_info *fb_info)
 
 	fb_info->dev = NULL;
 }
-EXPORT_SYMBOL(unlink_framebuffer);
 
 static void do_unregister_framebuffer(struct fb_info *fb_info)
 {
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index 3a2d9ff0aa42..460826a7ad55 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -1060,7 +1060,7 @@ static int cyber2000fb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops cyber2000fb_ops = {
+static const struct fb_ops cyber2000fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= cyber2000fb_check_var,
 	.fb_set_par	= cyber2000fb_set_par,
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index 2d3dcc52fcf3..73c3c4c8cc12 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -1294,7 +1294,7 @@ static int da8xxfb_set_par(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops da8xx_fb_ops = {
+static const struct fb_ops da8xx_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = fb_check_var,
 	.fb_set_par = da8xxfb_set_par,
diff --git a/drivers/video/fbdev/dnfb.c b/drivers/video/fbdev/dnfb.c
index 8da517eaa4a3..3688f9165848 100644
--- a/drivers/video/fbdev/dnfb.c
+++ b/drivers/video/fbdev/dnfb.c
@@ -108,7 +108,7 @@
 static int dnfb_blank(int blank, struct fb_info *info);
 static void dnfb_copyarea(struct fb_info *info, const struct fb_copyarea *area);
 
-static struct fb_ops dn_fb_ops = {
+static const struct fb_ops dn_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_blank	= dnfb_blank,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 1caa3726cb45..65491ae74808 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -255,7 +255,7 @@ static void efifb_destroy(struct fb_info *info)
 	fb_dealloc_cmap(&info->cmap);
 }
 
-static struct fb_ops efifb_ops = {
+static const struct fb_ops efifb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_destroy	= efifb_destroy,
 	.fb_setcolreg	= efifb_setcolreg,
diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c
index d04a047094fc..cda2ef337423 100644
--- a/drivers/video/fbdev/ep93xx-fb.c
+++ b/drivers/video/fbdev/ep93xx-fb.c
@@ -402,7 +402,7 @@ static int ep93xxfb_setcolreg(unsigned int regno, unsigned int red,
 	return 0;
 }
 
-static struct fb_ops ep93xxfb_ops = {
+static const struct fb_ops ep93xxfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= ep93xxfb_check_var,
 	.fb_set_par	= ep93xxfb_set_par,
diff --git a/drivers/video/fbdev/fb-puv3.c b/drivers/video/fbdev/fb-puv3.c
index fa62c4dff7d1..75df6aabac21 100644
--- a/drivers/video/fbdev/fb-puv3.c
+++ b/drivers/video/fbdev/fb-puv3.c
@@ -644,7 +644,7 @@ int unifb_mmap(struct fb_info *info,
 	return vm_iomap_memory(vma, info->fix.smem_start, info->fix.smem_len);
 }
 
-static struct fb_ops unifb_ops = {
+static const struct fb_ops unifb_ops = {
 	.fb_read        = fb_sys_read,
 	.fb_write       = fb_sys_write,
 	.fb_check_var	= unifb_check_var,
diff --git a/drivers/video/fbdev/ffb.c b/drivers/video/fbdev/ffb.c
index cd2d1db239a2..948b73184433 100644
--- a/drivers/video/fbdev/ffb.c
+++ b/drivers/video/fbdev/ffb.c
@@ -44,7 +44,7 @@ static int ffb_pan_display(struct fb_var_screeninfo *, struct fb_info *);
  *  Frame buffer operations
  */
 
-static struct fb_ops ffb_ops = {
+static const struct fb_ops ffb_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= ffb_setcolreg,
 	.fb_blank		= ffb_blank,
diff --git a/drivers/video/fbdev/fm2fb.c b/drivers/video/fbdev/fm2fb.c
index ac7a4ebfd390..3b727d528fde 100644
--- a/drivers/video/fbdev/fm2fb.c
+++ b/drivers/video/fbdev/fm2fb.c
@@ -165,7 +165,7 @@ static int fm2fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue,
                            u_int transp, struct fb_info *info);
 static int fm2fb_blank(int blank, struct fb_info *info);
 
-static struct fb_ops fm2fb_ops = {
+static const struct fb_ops fm2fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= fm2fb_setcolreg,
 	.fb_blank	= fm2fb_blank,
diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c
index d19f58263b4e..67ebfe5c9f1d 100644
--- a/drivers/video/fbdev/fsl-diu-fb.c
+++ b/drivers/video/fbdev/fsl-diu-fb.c
@@ -1287,6 +1287,7 @@ static int fsl_diu_ioctl(struct fb_info *info, unsigned int cmd,
 		dev_warn(info->dev,
 			 "MFB_SET_PIXFMT value of 0x%08x is deprecated.\n",
 			 MFB_SET_PIXFMT_OLD);
+		/* fall through */
 	case MFB_SET_PIXFMT:
 		if (copy_from_user(&pix_fmt, buf, sizeof(pix_fmt)))
 			return -EFAULT;
@@ -1296,6 +1297,7 @@ static int fsl_diu_ioctl(struct fb_info *info, unsigned int cmd,
 		dev_warn(info->dev,
 			 "MFB_GET_PIXFMT value of 0x%08x is deprecated.\n",
 			 MFB_GET_PIXFMT_OLD);
+		/* fall through */
 	case MFB_GET_PIXFMT:
 		pix_fmt = ad->pix_fmt;
 		if (copy_to_user(buf, &pix_fmt, sizeof(pix_fmt)))
@@ -1448,7 +1450,7 @@ static int fsl_diu_release(struct fb_info *info, int user)
 	return res;
 }
 
-static struct fb_ops fsl_diu_ops = {
+static const struct fb_ops fsl_diu_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = fsl_diu_check_var,
 	.fb_set_par = fsl_diu_set_par,
diff --git a/drivers/video/fbdev/g364fb.c b/drivers/video/fbdev/g364fb.c
index 223896cc5f7d..845b79da2a7c 100644
--- a/drivers/video/fbdev/g364fb.c
+++ b/drivers/video/fbdev/g364fb.c
@@ -111,7 +111,7 @@ static int g364fb_setcolreg(u_int regno, u_int red, u_int green,
 static int g364fb_cursor(struct fb_info *info, struct fb_cursor *cursor);
 static int g364fb_blank(int blank, struct fb_info *info);
 
-static struct fb_ops g364fb_ops = {
+static const struct fb_ops g364fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= g364fb_setcolreg,
 	.fb_pan_display	= g364fb_pan_display,
diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c
index b9f6a82a0495..31270a8986e8 100644
--- a/drivers/video/fbdev/gbefb.c
+++ b/drivers/video/fbdev/gbefb.c
@@ -1044,7 +1044,7 @@ static int gbefb_mmap(struct fb_info *info,
 	return 0;
 }
 
-static struct fb_ops gbefb_ops = {
+static const struct fb_ops gbefb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= gbefb_check_var,
 	.fb_set_par	= gbefb_set_par,
diff --git a/drivers/video/fbdev/geode/gx1fb_core.c b/drivers/video/fbdev/geode/gx1fb_core.c
index 737e472fac14..5d34d89fb665 100644
--- a/drivers/video/fbdev/geode/gx1fb_core.c
+++ b/drivers/video/fbdev/geode/gx1fb_core.c
@@ -252,7 +252,7 @@ static int parse_panel_option(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops gx1fb_ops = {
+static const struct fb_ops gx1fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= gx1fb_check_var,
 	.fb_set_par	= gx1fb_set_par,
diff --git a/drivers/video/fbdev/geode/gxfb_core.c b/drivers/video/fbdev/geode/gxfb_core.c
index 435ce2aa4240..d38a148d4746 100644
--- a/drivers/video/fbdev/geode/gxfb_core.c
+++ b/drivers/video/fbdev/geode/gxfb_core.c
@@ -265,7 +265,7 @@ static int gxfb_map_video_memory(struct fb_info *info, struct pci_dev *dev)
 	return 0;
 }
 
-static struct fb_ops gxfb_ops = {
+static const struct fb_ops gxfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= gxfb_check_var,
 	.fb_set_par	= gxfb_set_par,
diff --git a/drivers/video/fbdev/geode/lxfb_core.c b/drivers/video/fbdev/geode/lxfb_core.c
index b0f07d676eb3..adc2d9c2395e 100644
--- a/drivers/video/fbdev/geode/lxfb_core.c
+++ b/drivers/video/fbdev/geode/lxfb_core.c
@@ -386,7 +386,7 @@ static int lxfb_map_video_memory(struct fb_info *info, struct pci_dev *dev)
 	return 0;
 }
 
-static struct fb_ops lxfb_ops = {
+static const struct fb_ops lxfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= lxfb_check_var,
 	.fb_set_par	= lxfb_set_par,
diff --git a/drivers/video/fbdev/goldfishfb.c b/drivers/video/fbdev/goldfishfb.c
index f60ac276703d..9c83ec3f8e1f 100644
--- a/drivers/video/fbdev/goldfishfb.c
+++ b/drivers/video/fbdev/goldfishfb.c
@@ -160,7 +160,7 @@ static int goldfish_fb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops goldfish_fb_ops = {
+static const struct fb_ops goldfish_fb_ops = {
 	.owner          = THIS_MODULE,
 	.fb_check_var   = goldfish_fb_check_var,
 	.fb_set_par     = goldfish_fb_set_par,
diff --git a/drivers/video/fbdev/grvga.c b/drivers/video/fbdev/grvga.c
index d22e8b0c906d..07dda03e0957 100644
--- a/drivers/video/fbdev/grvga.c
+++ b/drivers/video/fbdev/grvga.c
@@ -251,7 +251,7 @@ static int grvga_pan_display(struct fb_var_screeninfo *var,
 	return 0;
 }
 
-static struct fb_ops grvga_ops = {
+static const struct fb_ops grvga_ops = {
 	.owner          = THIS_MODULE,
 	.fb_check_var   = grvga_check_var,
 	.fb_set_par	= grvga_set_par,
diff --git a/drivers/video/fbdev/gxt4500.c b/drivers/video/fbdev/gxt4500.c
index c7502fd8f447..13ded3a10708 100644
--- a/drivers/video/fbdev/gxt4500.c
+++ b/drivers/video/fbdev/gxt4500.c
@@ -599,7 +599,7 @@ static const struct fb_fix_screeninfo gxt4500_fix = {
 	.mmio_len = 0x20000,
 };
 
-static struct fb_ops gxt4500_ops = {
+static const struct fb_ops gxt4500_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = gxt4500_check_var,
 	.fb_set_par = gxt4500_set_par,
diff --git a/drivers/video/fbdev/hecubafb.c b/drivers/video/fbdev/hecubafb.c
index 8577195cb533..00d77105161a 100644
--- a/drivers/video/fbdev/hecubafb.c
+++ b/drivers/video/fbdev/hecubafb.c
@@ -197,7 +197,7 @@ static ssize_t hecubafb_write(struct fb_info *info, const char __user *buf,
 	return (err) ? err : count;
 }
 
-static struct fb_ops hecubafb_ops = {
+static const struct fb_ops hecubafb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_read        = fb_sys_read,
 	.fb_write	= hecubafb_write,
diff --git a/drivers/video/fbdev/hgafb.c b/drivers/video/fbdev/hgafb.c
index 59e1cae57948..a45fcff1461f 100644
--- a/drivers/video/fbdev/hgafb.c
+++ b/drivers/video/fbdev/hgafb.c
@@ -523,7 +523,7 @@ static void hgafb_imageblit(struct fb_info *info, const struct fb_image *image)
 	}
 }
 
-static struct fb_ops hgafb_ops = {
+static const struct fb_ops hgafb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= hgafb_open,
 	.fb_release	= hgafb_release,
diff --git a/drivers/video/fbdev/hitfb.c b/drivers/video/fbdev/hitfb.c
index abe3e54d4506..009e5d2aa100 100644
--- a/drivers/video/fbdev/hitfb.c
+++ b/drivers/video/fbdev/hitfb.c
@@ -311,7 +311,7 @@ static int hitfb_set_par(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops hitfb_ops = {
+static const struct fb_ops hitfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= hitfb_check_var,
 	.fb_set_par		= hitfb_set_par,
diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c
index a79af8f069d1..f02be0db335e 100644
--- a/drivers/video/fbdev/hpfb.c
+++ b/drivers/video/fbdev/hpfb.c
@@ -184,7 +184,7 @@ static int hpfb_sync(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops hpfb_ops = {
+static const struct fb_ops hpfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= hpfb_setcolreg,
 	.fb_blank	= hpfb_blank,
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 4cd27e5172a1..f47d50e560c0 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -31,6 +31,16 @@
  * "set-vmvideo" command. For example
  *     set-vmvideo -vmname name -horizontalresolution:1920 \
  * -verticalresolution:1200 -resolutiontype single
+ *
+ * Gen 1 VMs also support direct using VM's physical memory for framebuffer.
+ * It could improve the efficiency and performance for framebuffer and VM.
+ * This requires to allocate contiguous physical memory from Linux kernel's
+ * CMA memory allocator. To enable this, supply a kernel parameter to give
+ * enough memory space to CMA allocator for framebuffer. For example:
+ *    cma=130m
+ * This gives 130MB memory to CMA allocator that can be allocated to
+ * framebuffer. For reference, 8K resolution (7680x4320) takes about
+ * 127MB memory.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -228,7 +238,6 @@ struct synthvid_msg {
 } __packed;
 
 
-
 /* FB driver definitions and structures */
 #define HVFB_WIDTH 1152 /* default screen width */
 #define HVFB_HEIGHT 864 /* default screen height */
@@ -258,12 +267,15 @@ struct hvfb_par {
 	/* If true, the VSC notifies the VSP on every framebuffer change */
 	bool synchronous_fb;
 
+	/* If true, need to copy from deferred IO mem to framebuffer mem */
+	bool need_docopy;
+
 	struct notifier_block hvfb_panic_nb;
 
 	/* Memory for deferred IO and frame buffer itself */
 	unsigned char *dio_vp;
 	unsigned char *mmio_vp;
-	unsigned long mmio_pp;
+	phys_addr_t mmio_pp;
 
 	/* Dirty rectangle, protected by delayed_refresh_lock */
 	int x1, y1, x2, y2;
@@ -434,7 +446,7 @@ static void synthvid_deferred_io(struct fb_info *p,
 		maxy = max_t(int, maxy, y2);
 
 		/* Copy from dio space to mmio address */
-		if (par->fb_ready)
+		if (par->fb_ready && par->need_docopy)
 			hvfb_docopy(par, start, PAGE_SIZE);
 	}
 
@@ -751,12 +763,12 @@ static void hvfb_update_work(struct work_struct *w)
 		return;
 
 	/* Copy the dirty rectangle to frame buffer memory */
-	for (j = y1; j < y2; j++) {
-		hvfb_docopy(par,
-			    j * info->fix.line_length +
-			    (x1 * screen_depth / 8),
-			    (x2 - x1) * screen_depth / 8);
-	}
+	if (par->need_docopy)
+		for (j = y1; j < y2; j++)
+			hvfb_docopy(par,
+				    j * info->fix.line_length +
+				    (x1 * screen_depth / 8),
+				    (x2 - x1) * screen_depth / 8);
 
 	/* Refresh */
 	if (par->fb_ready && par->update)
@@ -801,7 +813,8 @@ static int hvfb_on_panic(struct notifier_block *nb,
 	par = container_of(nb, struct hvfb_par, hvfb_panic_nb);
 	par->synchronous_fb = true;
 	info = par->info;
-	hvfb_docopy(par, 0, dio_fb_size);
+	if (par->need_docopy)
+		hvfb_docopy(par, 0, dio_fb_size);
 	synthvid_update(info, 0, 0, INT_MAX, INT_MAX);
 
 	return NOTIFY_DONE;
@@ -895,7 +908,7 @@ static void hvfb_cfb_imageblit(struct fb_info *p,
 					       image->width, image->height);
 }
 
-static struct fb_ops hvfb_ops = {
+static const struct fb_ops hvfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = hvfb_check_var,
 	.fb_set_par = hvfb_set_par,
@@ -940,6 +953,62 @@ static void hvfb_get_option(struct fb_info *info)
 	return;
 }
 
+/*
+ * Allocate enough contiguous physical memory.
+ * Return physical address if succeeded or -1 if failed.
+ */
+static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
+				   unsigned int request_size)
+{
+	struct page *page = NULL;
+	dma_addr_t dma_handle;
+	void *vmem;
+	phys_addr_t paddr = 0;
+	unsigned int order = get_order(request_size);
+
+	if (request_size == 0)
+		return -1;
+
+	if (order < MAX_ORDER) {
+		/* Call alloc_pages if the size is less than 2^MAX_ORDER */
+		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+		if (!page)
+			return -1;
+
+		paddr = (page_to_pfn(page) << PAGE_SHIFT);
+	} else {
+		/* Allocate from CMA */
+		hdev->device.coherent_dma_mask = DMA_BIT_MASK(64);
+
+		vmem = dma_alloc_coherent(&hdev->device,
+					  round_up(request_size, PAGE_SIZE),
+					  &dma_handle,
+					  GFP_KERNEL | __GFP_NOWARN);
+
+		if (!vmem)
+			return -1;
+
+		paddr = virt_to_phys(vmem);
+	}
+
+	return paddr;
+}
+
+/* Release contiguous physical memory */
+static void hvfb_release_phymem(struct hv_device *hdev,
+				phys_addr_t paddr, unsigned int size)
+{
+	unsigned int order = get_order(size);
+
+	if (order < MAX_ORDER)
+		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
+	else
+		dma_free_coherent(&hdev->device,
+				  round_up(size, PAGE_SIZE),
+				  phys_to_virt(paddr),
+				  paddr);
+}
+
 
 /* Get framebuffer memory from Hyper-V video pci space */
 static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
@@ -949,22 +1018,61 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	void __iomem *fb_virt;
 	int gen2vm = efi_enabled(EFI_BOOT);
 	resource_size_t pot_start, pot_end;
+	phys_addr_t paddr;
 	int ret;
 
-	dio_fb_size =
-		screen_width * screen_height * screen_depth / 8;
+	info->apertures = alloc_apertures(1);
+	if (!info->apertures)
+		return -ENOMEM;
 
-	if (gen2vm) {
-		pot_start = 0;
-		pot_end = -1;
-	} else {
+	if (!gen2vm) {
 		pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT,
-			      PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
+			PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
 		if (!pdev) {
 			pr_err("Unable to find PCI Hyper-V video\n");
+			kfree(info->apertures);
 			return -ENODEV;
 		}
 
+		info->apertures->ranges[0].base = pci_resource_start(pdev, 0);
+		info->apertures->ranges[0].size = pci_resource_len(pdev, 0);
+
+		/*
+		 * For Gen 1 VM, we can directly use the contiguous memory
+		 * from VM. If we succeed, deferred IO happens directly
+		 * on this allocated framebuffer memory, avoiding extra
+		 * memory copy.
+		 */
+		paddr = hvfb_get_phymem(hdev, screen_fb_size);
+		if (paddr != (phys_addr_t) -1) {
+			par->mmio_pp = paddr;
+			par->mmio_vp = par->dio_vp = __va(paddr);
+
+			info->fix.smem_start = paddr;
+			info->fix.smem_len = screen_fb_size;
+			info->screen_base = par->mmio_vp;
+			info->screen_size = screen_fb_size;
+
+			par->need_docopy = false;
+			goto getmem_done;
+		}
+		pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n");
+	} else {
+		info->apertures->ranges[0].base = screen_info.lfb_base;
+		info->apertures->ranges[0].size = screen_info.lfb_size;
+	}
+
+	/*
+	 * Cannot use the contiguous physical memory.
+	 * Allocate mmio space for framebuffer.
+	 */
+	dio_fb_size =
+		screen_width * screen_height * screen_depth / 8;
+
+	if (gen2vm) {
+		pot_start = 0;
+		pot_end = -1;
+	} else {
 		if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM) ||
 		    pci_resource_len(pdev, 0) < screen_fb_size) {
 			pr_err("Resource not available or (0x%lx < 0x%lx)\n",
@@ -993,20 +1101,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	if (par->dio_vp == NULL)
 		goto err3;
 
-	info->apertures = alloc_apertures(1);
-	if (!info->apertures)
-		goto err4;
-
-	if (gen2vm) {
-		info->apertures->ranges[0].base = screen_info.lfb_base;
-		info->apertures->ranges[0].size = screen_info.lfb_size;
-		remove_conflicting_framebuffers(info->apertures,
-						KBUILD_MODNAME, false);
-	} else {
-		info->apertures->ranges[0].base = pci_resource_start(pdev, 0);
-		info->apertures->ranges[0].size = pci_resource_len(pdev, 0);
-	}
-
 	/* Physical address of FB device */
 	par->mmio_pp = par->mem->start;
 	/* Virtual address of FB device */
@@ -1017,13 +1111,15 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	info->screen_base = par->dio_vp;
 	info->screen_size = dio_fb_size;
 
+getmem_done:
+	remove_conflicting_framebuffers(info->apertures,
+					KBUILD_MODNAME, false);
 	if (!gen2vm)
 		pci_dev_put(pdev);
+	kfree(info->apertures);
 
 	return 0;
 
-err4:
-	vfree(par->dio_vp);
 err3:
 	iounmap(fb_virt);
 err2:
@@ -1032,18 +1128,25 @@ err2:
 err1:
 	if (!gen2vm)
 		pci_dev_put(pdev);
+	kfree(info->apertures);
 
 	return -ENOMEM;
 }
 
 /* Release the framebuffer */
-static void hvfb_putmem(struct fb_info *info)
+static void hvfb_putmem(struct hv_device *hdev, struct fb_info *info)
 {
 	struct hvfb_par *par = info->par;
 
-	vfree(par->dio_vp);
-	iounmap(info->screen_base);
-	vmbus_free_mmio(par->mem->start, screen_fb_size);
+	if (par->need_docopy) {
+		vfree(par->dio_vp);
+		iounmap(info->screen_base);
+		vmbus_free_mmio(par->mem->start, screen_fb_size);
+	} else {
+		hvfb_release_phymem(hdev, info->fix.smem_start,
+				    screen_fb_size);
+	}
+
 	par->mem = NULL;
 }
 
@@ -1062,6 +1165,7 @@ static int hvfb_probe(struct hv_device *hdev,
 	par = info->par;
 	par->info = info;
 	par->fb_ready = false;
+	par->need_docopy = true;
 	init_completion(&par->wait);
 	INIT_DELAYED_WORK(&par->dwork, hvfb_update_work);
 
@@ -1147,7 +1251,7 @@ static int hvfb_probe(struct hv_device *hdev,
 
 error:
 	fb_deferred_io_cleanup(info);
-	hvfb_putmem(info);
+	hvfb_putmem(hdev, info);
 error2:
 	vmbus_close(hdev->channel);
 error1:
@@ -1177,7 +1281,7 @@ static int hvfb_remove(struct hv_device *hdev)
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
 
-	hvfb_putmem(info);
+	hvfb_putmem(hdev, info);
 	framebuffer_release(info);
 
 	return 0;
@@ -1194,6 +1298,7 @@ static int hvfb_suspend(struct hv_device *hdev)
 	fb_set_suspend(info, 1);
 
 	cancel_delayed_work_sync(&par->dwork);
+	cancel_delayed_work_sync(&info->deferred_work);
 
 	par->update_saved = par->update;
 	par->update = false;
@@ -1227,6 +1332,7 @@ static int hvfb_resume(struct hv_device *hdev)
 	par->fb_ready = true;
 	par->update = par->update_saved;
 
+	schedule_delayed_work(&info->deferred_work, info->fbdefio->delay);
 	schedule_delayed_work(&par->dwork, HVFB_UPDATE_DELAY);
 
 	/* 0 means do resume */
diff --git a/drivers/video/fbdev/i740fb.c b/drivers/video/fbdev/i740fb.c
index 347cf8babc3e..c65ec7386e87 100644
--- a/drivers/video/fbdev/i740fb.c
+++ b/drivers/video/fbdev/i740fb.c
@@ -981,7 +981,7 @@ static int i740fb_blank(int blank_mode, struct fb_info *info)
 	return (blank_mode == FB_BLANK_NORMAL) ? 1 : 0;
 }
 
-static struct fb_ops i740fb_ops = {
+static const struct fb_ops i740fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= i740fb_open,
 	.fb_release	= i740fb_release,
diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c
index 58b01c7d9056..3ac053b88495 100644
--- a/drivers/video/fbdev/imsttfb.c
+++ b/drivers/video/fbdev/imsttfb.c
@@ -1333,7 +1333,7 @@ static struct pci_driver imsttfb_pci_driver = {
 	.remove =	imsttfb_remove,
 };
 
-static struct fb_ops imsttfb_ops = {
+static const struct fb_ops imsttfb_ops = {
 	.owner 		= THIS_MODULE,
 	.fb_check_var	= imsttfb_check_var,
 	.fb_set_par 	= imsttfb_set_par,
diff --git a/drivers/video/fbdev/imxfb.c b/drivers/video/fbdev/imxfb.c
index b3286d1fa543..370bf2553d43 100644
--- a/drivers/video/fbdev/imxfb.c
+++ b/drivers/video/fbdev/imxfb.c
@@ -566,7 +566,7 @@ static int imxfb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops imxfb_ops = {
+static const struct fb_ops imxfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= imxfb_check_var,
 	.fb_set_par	= imxfb_set_par,
@@ -1017,7 +1017,7 @@ static int imxfb_probe(struct platform_device *pdev)
 	}
 
 	fbi->lcd_pwr = devm_regulator_get(&pdev->dev, "lcd");
-	if (IS_ERR(fbi->lcd_pwr) && (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER)) {
+	if (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER) {
 		ret = -EPROBE_DEFER;
 		goto failed_lcd;
 	}
diff --git a/drivers/video/fbdev/intelfb/intelfb.h b/drivers/video/fbdev/intelfb/intelfb.h
index b54db05f028d..5de703902a21 100644
--- a/drivers/video/fbdev/intelfb/intelfb.h
+++ b/drivers/video/fbdev/intelfb/intelfb.h
@@ -273,7 +273,7 @@ struct intelfb_vsync {
 
 struct intelfb_info {
 	struct fb_info *info;
-	struct fb_ops  *fbops;
+	const struct fb_ops *fbops;
 	struct pci_dev *pdev;
 
 	struct intelfb_hwstate save_state;
diff --git a/drivers/video/fbdev/intelfb/intelfbdrv.c b/drivers/video/fbdev/intelfb/intelfbdrv.c
index a09fc2eaa40d..a9579964eaba 100644
--- a/drivers/video/fbdev/intelfb/intelfbdrv.c
+++ b/drivers/video/fbdev/intelfb/intelfbdrv.c
@@ -193,7 +193,7 @@ static const struct pci_device_id intelfb_pci_table[] = {
 static int num_registered = 0;
 
 /* fb ops */
-static struct fb_ops intel_fb_ops = {
+static const struct fb_ops intel_fb_ops = {
 	.owner =		THIS_MODULE,
 	.fb_open =              intelfb_open,
 	.fb_release =           intelfb_release,
diff --git a/drivers/video/fbdev/kyro/fbdev.c b/drivers/video/fbdev/kyro/fbdev.c
index a8660926924b..8fbde92ae8b9 100644
--- a/drivers/video/fbdev/kyro/fbdev.c
+++ b/drivers/video/fbdev/kyro/fbdev.c
@@ -648,7 +648,7 @@ static struct pci_driver kyrofb_pci_driver = {
 	.remove		= kyrofb_remove,
 };
 
-static struct fb_ops kyrofb_ops = {
+static const struct fb_ops kyrofb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= kyrofb_check_var,
 	.fb_set_par	= kyrofb_set_par,
diff --git a/drivers/video/fbdev/leo.c b/drivers/video/fbdev/leo.c
index 5b1141ac182b..40b11cce0ad6 100644
--- a/drivers/video/fbdev/leo.c
+++ b/drivers/video/fbdev/leo.c
@@ -39,7 +39,7 @@ static int leo_pan_display(struct fb_var_screeninfo *, struct fb_info *);
  *  Frame buffer operations
  */
 
-static struct fb_ops leo_ops = {
+static const struct fb_ops leo_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= leo_setcolreg,
 	.fb_blank		= leo_blank,
diff --git a/drivers/video/fbdev/macfb.c b/drivers/video/fbdev/macfb.c
index 9a6feee96133..e05a97662ca8 100644
--- a/drivers/video/fbdev/macfb.c
+++ b/drivers/video/fbdev/macfb.c
@@ -496,7 +496,7 @@ static int macfb_setcolreg(unsigned regno, unsigned red, unsigned green,
 	return 0;
 }
 
-static struct fb_ops macfb_ops = {
+static const struct fb_ops macfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= macfb_setcolreg,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/matrox/matroxfb_crtc2.c b/drivers/video/fbdev/matrox/matroxfb_crtc2.c
index d2a81a2c3ac0..7655afa3fd50 100644
--- a/drivers/video/fbdev/matrox/matroxfb_crtc2.c
+++ b/drivers/video/fbdev/matrox/matroxfb_crtc2.c
@@ -563,7 +563,7 @@ static int matroxfb_dh_blank(int blank, struct fb_info* info) {
 #undef m2info
 }
 
-static struct fb_ops matroxfb_dh_ops = {
+static const struct fb_ops matroxfb_dh_ops = {
 	.owner =	THIS_MODULE,
 	.fb_open =	matroxfb_dh_open,
 	.fb_release =	matroxfb_dh_release,
diff --git a/drivers/video/fbdev/matrox/matroxfb_misc.c b/drivers/video/fbdev/matrox/matroxfb_misc.c
index c7aaca12805e..8f159a2ad8d0 100644
--- a/drivers/video/fbdev/matrox/matroxfb_misc.c
+++ b/drivers/video/fbdev/matrox/matroxfb_misc.c
@@ -673,7 +673,10 @@ static int parse_pins5(struct matrox_fb_info *minfo,
 	if (bd->pins[115] & 4) {
 		minfo->values.reg.mctlwtst_core = minfo->values.reg.mctlwtst;
 	} else {
-		u_int32_t wtst_xlat[] = { 0, 1, 5, 6, 7, 5, 2, 3 };
+		static const u8 wtst_xlat[] = {
+			0, 1, 5, 6, 7, 5, 2, 3
+		};
+
 		minfo->values.reg.mctlwtst_core = (minfo->values.reg.mctlwtst & ~7) |
 						  wtst_xlat[minfo->values.reg.mctlwtst & 7];
 	}
diff --git a/drivers/video/fbdev/maxinefb.c b/drivers/video/fbdev/maxinefb.c
index 5bb1b5c308a7..ae1a42bcb0ea 100644
--- a/drivers/video/fbdev/maxinefb.c
+++ b/drivers/video/fbdev/maxinefb.c
@@ -105,7 +105,7 @@ static int maxinefb_setcolreg(unsigned regno, unsigned red, unsigned green,
 	return 0;
 }
 
-static struct fb_ops maxinefb_ops = {
+static const struct fb_ops maxinefb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= maxinefb_setcolreg,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/mb862xx/mb862xxfb.h b/drivers/video/fbdev/mb862xx/mb862xxfb.h
index 50bc9b584ca1..52a77ea4e849 100644
--- a/drivers/video/fbdev/mb862xx/mb862xxfb.h
+++ b/drivers/video/fbdev/mb862xx/mb862xxfb.h
@@ -89,7 +89,7 @@ struct mb862xxfb_par {
 	u32			pseudo_palette[16];
 };
 
-extern void mb862xxfb_init_accel(struct fb_info *info, int xres);
+extern void mb862xxfb_init_accel(struct fb_info *info, struct fb_ops *fbops, int xres);
 #ifdef CONFIG_FB_MB862XX_I2C
 extern int mb862xx_i2c_init(struct mb862xxfb_par *par);
 extern void mb862xx_i2c_exit(struct mb862xxfb_par *par);
diff --git a/drivers/video/fbdev/mb862xx/mb862xxfb_accel.c b/drivers/video/fbdev/mb862xx/mb862xxfb_accel.c
index f58ff900e82a..42569264801f 100644
--- a/drivers/video/fbdev/mb862xx/mb862xxfb_accel.c
+++ b/drivers/video/fbdev/mb862xx/mb862xxfb_accel.c
@@ -303,19 +303,19 @@ static void mb86290fb_fillrect(struct fb_info *info,
 	mb862xxfb_write_fifo(7, cmd, info);
 }
 
-void mb862xxfb_init_accel(struct fb_info *info, int xres)
+void mb862xxfb_init_accel(struct fb_info *info, struct fb_ops *fbops, int xres)
 {
 	struct mb862xxfb_par *par = info->par;
 
 	if (info->var.bits_per_pixel == 32) {
-		info->fbops->fb_fillrect = cfb_fillrect;
-		info->fbops->fb_copyarea = cfb_copyarea;
-		info->fbops->fb_imageblit = cfb_imageblit;
+		fbops->fb_fillrect = cfb_fillrect;
+		fbops->fb_copyarea = cfb_copyarea;
+		fbops->fb_imageblit = cfb_imageblit;
 	} else {
 		outreg(disp, GC_L0EM, 3);
-		info->fbops->fb_fillrect = mb86290fb_fillrect;
-		info->fbops->fb_copyarea = mb86290fb_copyarea;
-		info->fbops->fb_imageblit = mb86290fb_imageblit;
+		fbops->fb_fillrect = mb86290fb_fillrect;
+		fbops->fb_copyarea = mb86290fb_copyarea;
+		fbops->fb_imageblit = mb86290fb_imageblit;
 	}
 	outreg(draw, GDC_REG_DRAW_BASE, 0);
 	outreg(draw, GDC_REG_MODE_MISC, 0x8000);
@@ -326,6 +326,5 @@ void mb862xxfb_init_accel(struct fb_info *info, int xres)
 	    FBINFO_HWACCEL_IMAGEBLIT;
 	info->fix.accel = 0xff;	/*FIXME: add right define */
 }
-EXPORT_SYMBOL(mb862xxfb_init_accel);
 
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c
index 962c0171d271..52755b591c14 100644
--- a/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c
+++ b/drivers/video/fbdev/mb862xx/mb862xxfbdrv.c
@@ -194,6 +194,8 @@ static int mb862xxfb_check_var(struct fb_var_screeninfo *var,
 	return 0;
 }
 
+static struct fb_ops mb862xxfb_ops;
+
 /*
  * set display parameters
  */
@@ -204,7 +206,7 @@ static int mb862xxfb_set_par(struct fb_info *fbi)
 
 	dev_dbg(par->dev, "%s\n", __func__);
 	if (par->type == BT_CORALP)
-		mb862xxfb_init_accel(fbi, fbi->var.xres);
+		mb862xxfb_init_accel(fbi, &mb862xxfb_ops, fbi->var.xres);
 
 	if (par->pre_init)
 		return 0;
diff --git a/drivers/video/fbdev/mbx/mbxfb.c b/drivers/video/fbdev/mbx/mbxfb.c
index 3de4b3ed990a..6dc287c819cb 100644
--- a/drivers/video/fbdev/mbx/mbxfb.c
+++ b/drivers/video/fbdev/mbx/mbxfb.c
@@ -671,7 +671,7 @@ static int mbxfb_ioctl(struct fb_info *info, unsigned int cmd,
 	return -EINVAL;
 }
 
-static struct fb_ops mbxfb_ops = {
+static const struct fb_ops mbxfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = mbxfb_check_var,
 	.fb_set_par = mbxfb_set_par,
diff --git a/drivers/video/fbdev/metronomefb.c b/drivers/video/fbdev/metronomefb.c
index bb4fee52e501..a42e2eceee48 100644
--- a/drivers/video/fbdev/metronomefb.c
+++ b/drivers/video/fbdev/metronomefb.c
@@ -558,7 +558,7 @@ static ssize_t metronomefb_write(struct fb_info *info, const char __user *buf,
 	return (err) ? err : count;
 }
 
-static struct fb_ops metronomefb_ops = {
+static const struct fb_ops metronomefb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_write	= metronomefb_write,
 	.fb_fillrect	= metronomefb_fillrect,
diff --git a/drivers/video/fbdev/mmp/Kconfig b/drivers/video/fbdev/mmp/Kconfig
index 9041ffd2cfcf..5c6cc97c96f0 100644
--- a/drivers/video/fbdev/mmp/Kconfig
+++ b/drivers/video/fbdev/mmp/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig MMP_DISP
 	tristate "Marvell MMP Display Subsystem support"
-	depends on CPU_PXA910 || CPU_MMP2
+	depends on CPU_PXA910 || CPU_MMP2 || COMPILE_TEST
 	help
 	  Marvell Display Subsystem support.
 
diff --git a/drivers/video/fbdev/mmp/fb/Kconfig b/drivers/video/fbdev/mmp/fb/Kconfig
index 39944eb23ef8..0ec2e3fb9e17 100644
--- a/drivers/video/fbdev/mmp/fb/Kconfig
+++ b/drivers/video/fbdev/mmp/fb/Kconfig
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-if MMP_DISP
-
 config MMP_FB
 	tristate "fb driver for Marvell MMP Display Subsystem"
 	depends on FB
@@ -10,5 +8,3 @@ config MMP_FB
 	default y
 	help
 		fb driver for Marvell MMP Display Subsystem
-
-endif
diff --git a/drivers/video/fbdev/mmp/fb/mmpfb.c b/drivers/video/fbdev/mmp/fb/mmpfb.c
index 47bc7c59bbd8..01c75c031cb6 100644
--- a/drivers/video/fbdev/mmp/fb/mmpfb.c
+++ b/drivers/video/fbdev/mmp/fb/mmpfb.c
@@ -454,7 +454,7 @@ static int mmpfb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops mmpfb_ops = {
+static const struct fb_ops mmpfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_blank	= mmpfb_blank,
 	.fb_check_var	= mmpfb_check_var,
@@ -522,7 +522,7 @@ static int fb_info_setup(struct fb_info *info,
 		info->var.bits_per_pixel / 8;
 	info->fbops = &mmpfb_ops;
 	info->pseudo_palette = fbi->pseudo_palette;
-	info->screen_base = fbi->fb_start;
+	info->screen_buffer = fbi->fb_start;
 	info->screen_size = fbi->fb_size;
 
 	/* For FB framework: Allocate color map and Register framebuffer*/
diff --git a/drivers/video/fbdev/mmp/hw/Kconfig b/drivers/video/fbdev/mmp/hw/Kconfig
index 4d018cf661ec..7ebe125093d5 100644
--- a/drivers/video/fbdev/mmp/hw/Kconfig
+++ b/drivers/video/fbdev/mmp/hw/Kconfig
@@ -1,9 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
-if MMP_DISP
-
 config MMP_DISP_CONTROLLER
 	bool "mmp display controller hw support"
-	depends on CPU_PXA910 || CPU_MMP2
+	depends on HAVE_CLK && HAS_IOMEM
+	depends on CPU_PXA910 || CPU_MMP2 || COMPILE_TEST
 	help
 		Marvell MMP display hw controller support
 		this controller is used on Marvell PXA910 and
@@ -16,5 +15,3 @@ config MMP_DISP_SPI
 	help
 		Marvell MMP display hw controller spi port support
 		will register as a spi master for panel usage
-
-endif
diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
index 974e4c28b08b..061a105afb86 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
+++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.c
@@ -136,19 +136,26 @@ static void overlay_set_win(struct mmp_overlay *overlay, struct mmp_win *win)
 	mutex_lock(&overlay->access_ok);
 
 	if (overlay_is_vid(overlay)) {
-		writel_relaxed(win->pitch[0], &regs->v_pitch_yc);
-		writel_relaxed(win->pitch[2] << 16 |
-				win->pitch[1], &regs->v_pitch_uv);
-
-		writel_relaxed((win->ysrc << 16) | win->xsrc, &regs->v_size);
-		writel_relaxed((win->ydst << 16) | win->xdst, &regs->v_size_z);
-		writel_relaxed(win->ypos << 16 | win->xpos, &regs->v_start);
+		writel_relaxed(win->pitch[0],
+				(void __iomem *)&regs->v_pitch_yc);
+		writel_relaxed(win->pitch[2] << 16 | win->pitch[1],
+				(void __iomem *)&regs->v_pitch_uv);
+
+		writel_relaxed((win->ysrc << 16) | win->xsrc,
+				(void __iomem *)&regs->v_size);
+		writel_relaxed((win->ydst << 16) | win->xdst,
+				(void __iomem *)&regs->v_size_z);
+		writel_relaxed(win->ypos << 16 | win->xpos,
+				(void __iomem *)&regs->v_start);
 	} else {
-		writel_relaxed(win->pitch[0], &regs->g_pitch);
-
-		writel_relaxed((win->ysrc << 16) | win->xsrc, &regs->g_size);
-		writel_relaxed((win->ydst << 16) | win->xdst, &regs->g_size_z);
-		writel_relaxed(win->ypos << 16 | win->xpos, &regs->g_start);
+		writel_relaxed(win->pitch[0], (void __iomem *)&regs->g_pitch);
+
+		writel_relaxed((win->ysrc << 16) | win->xsrc,
+				(void __iomem *)&regs->g_size);
+		writel_relaxed((win->ydst << 16) | win->xdst,
+				(void __iomem *)&regs->g_size_z);
+		writel_relaxed(win->ypos << 16 | win->xpos,
+				(void __iomem *)&regs->g_start);
 	}
 
 	dmafetch_set_fmt(overlay);
@@ -233,11 +240,11 @@ static int overlay_set_addr(struct mmp_overlay *overlay, struct mmp_addr *addr)
 	memcpy(&overlay->addr, addr, sizeof(struct mmp_addr));
 
 	if (overlay_is_vid(overlay)) {
-		writel_relaxed(addr->phys[0], &regs->v_y0);
-		writel_relaxed(addr->phys[1], &regs->v_u0);
-		writel_relaxed(addr->phys[2], &regs->v_v0);
+		writel_relaxed(addr->phys[0], (void __iomem *)&regs->v_y0);
+		writel_relaxed(addr->phys[1], (void __iomem *)&regs->v_u0);
+		writel_relaxed(addr->phys[2], (void __iomem *)&regs->v_v0);
 	} else
-		writel_relaxed(addr->phys[0], &regs->g_0);
+		writel_relaxed(addr->phys[0], (void __iomem *)&regs->g_0);
 
 	return overlay->addr.phys[0];
 }
@@ -268,16 +275,18 @@ static void path_set_mode(struct mmp_path *path, struct mmp_mode *mode)
 	tmp |= dsi_rbswap & CFG_INTFRBSWAP_MASK;
 	writel_relaxed(tmp, ctrl_regs(path) + intf_rbswap_ctrl(path->id));
 
-	writel_relaxed((mode->yres << 16) | mode->xres, &regs->screen_active);
+	writel_relaxed((mode->yres << 16) | mode->xres,
+		(void __iomem *)&regs->screen_active);
 	writel_relaxed((mode->left_margin << 16) | mode->right_margin,
-		&regs->screen_h_porch);
+		(void __iomem *)&regs->screen_h_porch);
 	writel_relaxed((mode->upper_margin << 16) | mode->lower_margin,
-		&regs->screen_v_porch);
+		(void __iomem *)&regs->screen_v_porch);
 	total_x = mode->xres + mode->left_margin + mode->right_margin +
 		mode->hsync_len;
 	total_y = mode->yres + mode->upper_margin + mode->lower_margin +
 		mode->vsync_len;
-	writel_relaxed((total_y << 16) | total_x, &regs->screen_size);
+	writel_relaxed((total_y << 16) | total_x,
+		(void __iomem *)&regs->screen_size);
 
 	/* vsync ctrl */
 	if (path->output_type == PATH_OUT_DSI)
@@ -285,7 +294,7 @@ static void path_set_mode(struct mmp_path *path, struct mmp_mode *mode)
 	else
 		vsync_ctrl = ((mode->xres + mode->right_margin) << 16)
 					| (mode->xres + mode->right_margin);
-	writel_relaxed(vsync_ctrl, &regs->vsync_ctrl);
+	writel_relaxed(vsync_ctrl, (void __iomem *)&regs->vsync_ctrl);
 
 	/* set pixclock div */
 	sclk_src = clk_get_rate(path_to_ctrl(path)->clk);
@@ -366,9 +375,9 @@ static void path_set_default(struct mmp_path *path)
 	writel_relaxed(dma_ctrl1, ctrl_regs(path) + dma_ctrl(1, path->id));
 
 	/* Configure default register values */
-	writel_relaxed(0x00000000, &regs->blank_color);
-	writel_relaxed(0x00000000, &regs->g_1);
-	writel_relaxed(0x00000000, &regs->g_start);
+	writel_relaxed(0x00000000, (void __iomem *)&regs->blank_color);
+	writel_relaxed(0x00000000, (void __iomem *)&regs->g_1);
+	writel_relaxed(0x00000000, (void __iomem *)&regs->g_start);
 
 	/*
 	 * 1.enable multiple burst request in DMA AXI
@@ -447,7 +456,6 @@ static int mmphw_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
-		dev_err(&pdev->dev, "%s: no IRQ defined\n", __func__);
 		ret = -ENOENT;
 		goto failed;
 	}
diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.h b/drivers/video/fbdev/mmp/hw/mmp_ctrl.h
index e9ec45c118fb..335d4983dc52 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.h
+++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.h
@@ -1393,7 +1393,7 @@ struct mmphw_ctrl {
 	/* platform related, get from config */
 	const char *name;
 	int irq;
-	void *reg_base;
+	void __iomem *reg_base;
 	struct clk *clk;
 
 	/* sys info */
@@ -1429,7 +1429,7 @@ static inline struct mmphw_ctrl *overlay_to_ctrl(struct mmp_overlay *overlay)
 	return path_to_ctrl(overlay->path);
 }
 
-static inline void *ctrl_regs(struct mmp_path *path)
+static inline void __iomem *ctrl_regs(struct mmp_path *path)
 {
 	return path_to_ctrl(path)->reg_base;
 }
@@ -1438,11 +1438,11 @@ static inline void *ctrl_regs(struct mmp_path *path)
 static inline struct lcd_regs *path_regs(struct mmp_path *path)
 {
 	if (path->id == PATH_PN)
-		return (struct lcd_regs *)(ctrl_regs(path) + 0xc0);
+		return (struct lcd_regs __force *)(ctrl_regs(path) + 0xc0);
 	else if (path->id == PATH_TV)
-		return (struct lcd_regs *)ctrl_regs(path);
+		return (struct lcd_regs __force  *)ctrl_regs(path);
 	else if (path->id == PATH_P2)
-		return (struct lcd_regs *)(ctrl_regs(path) + 0x200);
+		return (struct lcd_regs __force *)(ctrl_regs(path) + 0x200);
 	else {
 		dev_err(path->dev, "path id %d invalid\n", path->id);
 		BUG_ON(1);
diff --git a/drivers/video/fbdev/mmp/hw/mmp_spi.c b/drivers/video/fbdev/mmp/hw/mmp_spi.c
index bbb75de5e441..1911a47769b6 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_spi.c
+++ b/drivers/video/fbdev/mmp/hw/mmp_spi.c
@@ -31,7 +31,7 @@ static inline int lcd_spi_write(struct spi_device *spi, u32 data)
 {
 	int timeout = 100000, isr, ret = 0;
 	u32 tmp;
-	void *reg_base =
+	void __iomem *reg_base = (void __iomem *)
 		*(void **)spi_master_get_devdata(spi->master);
 
 	/* clear ISR */
@@ -80,7 +80,7 @@ static inline int lcd_spi_write(struct spi_device *spi, u32 data)
 
 static int lcd_spi_setup(struct spi_device *spi)
 {
-	void *reg_base =
+	void __iomem *reg_base = (void __iomem *)
 		*(void **)spi_master_get_devdata(spi->master);
 	u32 tmp;
 
@@ -146,7 +146,7 @@ int lcd_spi_register(struct mmphw_ctrl *ctrl)
 		return -ENOMEM;
 	}
 	p_regbase = spi_master_get_devdata(master);
-	*p_regbase = ctrl->reg_base;
+	*p_regbase = (void __force *)ctrl->reg_base;
 
 	/* set bus num to 5 to avoid conflict with other spi hosts */
 	master->bus_num = 5;
diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c
index bafd5f5fac5a..4af28e4421e5 100644
--- a/drivers/video/fbdev/mx3fb.c
+++ b/drivers/video/fbdev/mx3fb.c
@@ -1249,7 +1249,7 @@ static int mx3fb_pan_display(struct fb_var_screeninfo *var,
  * invoked by the core framebuffer driver to perform operations like
  * blitting, rectangle filling, copy regions and cursor definition.
  */
-static struct fb_ops mx3fb_ops = {
+static const struct fb_ops mx3fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_set_par = mx3fb_set_par,
 	.fb_check_var = mx3fb_check_var,
@@ -1389,7 +1389,8 @@ static int mx3fb_unmap_video_memory(struct fb_info *fbi)
  * mx3fb_init_fbinfo() - initialize framebuffer information object.
  * @return:	initialized framebuffer structure.
  */
-static struct fb_info *mx3fb_init_fbinfo(struct device *dev, struct fb_ops *ops)
+static struct fb_info *mx3fb_init_fbinfo(struct device *dev,
+					 const struct fb_ops *ops)
 {
 	struct fb_info *fbi;
 	struct mx3fb_info *mx3fbi;
diff --git a/drivers/video/fbdev/neofb.c b/drivers/video/fbdev/neofb.c
index b770946a0920..e6ea853c1723 100644
--- a/drivers/video/fbdev/neofb.c
+++ b/drivers/video/fbdev/neofb.c
@@ -1610,7 +1610,7 @@ neofb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 }
 */
 
-static struct fb_ops neofb_ops = {
+static const struct fb_ops neofb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= neofb_open,
 	.fb_release	= neofb_release,
diff --git a/drivers/video/fbdev/nvidia/nvidia.c b/drivers/video/fbdev/nvidia/nvidia.c
index fbeeed5afe35..c583c018304d 100644
--- a/drivers/video/fbdev/nvidia/nvidia.c
+++ b/drivers/video/fbdev/nvidia/nvidia.c
@@ -607,6 +607,8 @@ static int nvidiafb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 	return 0;
 }
 
+static struct fb_ops nvidia_fb_ops;
+
 static int nvidiafb_set_par(struct fb_info *info)
 {
 	struct nvidia_par *par = info->par;
@@ -660,19 +662,19 @@ static int nvidiafb_set_par(struct fb_info *info)
 	info->fix.line_length = (info->var.xres_virtual *
 				 info->var.bits_per_pixel) >> 3;
 	if (info->var.accel_flags) {
-		info->fbops->fb_imageblit = nvidiafb_imageblit;
-		info->fbops->fb_fillrect = nvidiafb_fillrect;
-		info->fbops->fb_copyarea = nvidiafb_copyarea;
-		info->fbops->fb_sync = nvidiafb_sync;
+		nvidia_fb_ops.fb_imageblit = nvidiafb_imageblit;
+		nvidia_fb_ops.fb_fillrect = nvidiafb_fillrect;
+		nvidia_fb_ops.fb_copyarea = nvidiafb_copyarea;
+		nvidia_fb_ops.fb_sync = nvidiafb_sync;
 		info->pixmap.scan_align = 4;
 		info->flags &= ~FBINFO_HWACCEL_DISABLED;
 		info->flags |= FBINFO_READS_FAST;
 		NVResetGraphics(info);
 	} else {
-		info->fbops->fb_imageblit = cfb_imageblit;
-		info->fbops->fb_fillrect = cfb_fillrect;
-		info->fbops->fb_copyarea = cfb_copyarea;
-		info->fbops->fb_sync = NULL;
+		nvidia_fb_ops.fb_imageblit = cfb_imageblit;
+		nvidia_fb_ops.fb_fillrect = cfb_fillrect;
+		nvidia_fb_ops.fb_copyarea = cfb_copyarea;
+		nvidia_fb_ops.fb_sync = NULL;
 		info->pixmap.scan_align = 1;
 		info->flags |= FBINFO_HWACCEL_DISABLED;
 		info->flags &= ~FBINFO_READS_FAST;
@@ -1165,7 +1167,7 @@ static int nvidia_set_fbinfo(struct fb_info *info)
 	info->pixmap.flags = FB_PIXMAP_SYSTEM;
 
 	if (!hwcur)
-	    info->fbops->fb_cursor = NULL;
+	    nvidia_fb_ops.fb_cursor = NULL;
 
 	info->var.accel_flags = (!noaccel);
 
diff --git a/drivers/video/fbdev/ocfb.c b/drivers/video/fbdev/ocfb.c
index a970edc2a6f8..bfa4ed421148 100644
--- a/drivers/video/fbdev/ocfb.c
+++ b/drivers/video/fbdev/ocfb.c
@@ -285,7 +285,7 @@ static int ocfb_init_var(struct ocfb_dev *fbdev)
 	return 0;
 }
 
-static struct fb_ops ocfb_ops = {
+static const struct fb_ops ocfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= ocfb_setcolreg,
 	.fb_fillrect	= cfb_fillrect,
@@ -297,7 +297,6 @@ static int ocfb_probe(struct platform_device *pdev)
 {
 	int ret = 0;
 	struct ocfb_dev *fbdev;
-	struct resource *res;
 	int fbsize;
 
 	fbdev = devm_kzalloc(&pdev->dev, sizeof(*fbdev), GFP_KERNEL);
@@ -319,13 +318,7 @@ static int ocfb_probe(struct platform_device *pdev)
 	ocfb_init_var(fbdev);
 	ocfb_init_fix(fbdev);
 
-	/* Request I/O resource */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "I/O resource request failed\n");
-		return -ENXIO;
-	}
-	fbdev->regs = devm_ioremap_resource(&pdev->dev, res);
+	fbdev->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(fbdev->regs))
 		return PTR_ERR(fbdev->regs);
 
diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c
index fbc6eafb63c7..5cd0f5f6a4ae 100644
--- a/drivers/video/fbdev/offb.c
+++ b/drivers/video/fbdev/offb.c
@@ -286,7 +286,7 @@ static void offb_destroy(struct fb_info *info)
 	framebuffer_release(info);
 }
 
-static struct fb_ops offb_ops = {
+static const struct fb_ops offb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_destroy	= offb_destroy,
 	.fb_setcolreg	= offb_setcolreg,
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index 702cca59bda1..e8a304f84ea8 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -1052,7 +1052,7 @@ static int omapfb_ioctl(struct fb_info *fbi, unsigned int cmd,
 {
 	struct omapfb_plane_struct *plane = fbi->par;
 	struct omapfb_device	*fbdev = plane->fbdev;
-	struct fb_ops		*ops = fbi->fbops;
+	const struct fb_ops *ops = fbi->fbops;
 	union {
 		struct omapfb_update_window	update_window;
 		struct omapfb_plane_info	plane_info;
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
index 376ee5bc3ddc..ce37da85cc45 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c
@@ -1635,7 +1635,7 @@ static void dispc_ovl_set_scaling_uv(enum omap_plane plane,
 {
 	int scale_x = out_width != orig_width;
 	int scale_y = out_height != orig_height;
-	bool chroma_upscale = plane != OMAP_DSS_WB ? true : false;
+	bool chroma_upscale = plane != OMAP_DSS_WB;
 
 	if (!dss_has_feature(FEAT_HANDLE_UV_SEPARATE))
 		return;
@@ -3100,9 +3100,9 @@ static bool _dispc_mgr_pclk_ok(enum omap_channel channel,
 		unsigned long pclk)
 {
 	if (dss_mgr_is_lcd(channel))
-		return pclk <= dispc.feat->max_lcd_pclk ? true : false;
+		return pclk <= dispc.feat->max_lcd_pclk;
 	else
-		return pclk <= dispc.feat->max_tv_pclk ? true : false;
+		return pclk <= dispc.feat->max_tv_pclk;
 }
 
 bool dispc_mgr_timings_ok(enum omap_channel channel,
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
index 858c2c011d19..8dfa9158ba78 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
@@ -1280,7 +1280,7 @@ ssize_t omapfb_write(struct fb_info *info, const char __user *buf,
 }
 #endif
 
-static struct fb_ops omapfb_ops = {
+static const struct fb_ops omapfb_ops = {
 	.owner          = THIS_MODULE,
 	.fb_open        = omapfb_open,
 	.fb_release     = omapfb_release,
diff --git a/drivers/video/fbdev/omap2/omapfb/vrfb.c b/drivers/video/fbdev/omap2/omapfb/vrfb.c
index 819e0bc35b2d..ee0dd4c6a646 100644
--- a/drivers/video/fbdev/omap2/omapfb/vrfb.c
+++ b/drivers/video/fbdev/omap2/omapfb/vrfb.c
@@ -339,9 +339,7 @@ static int __init vrfb_probe(struct platform_device *pdev)
 	int i;
 
 	/* first resource is the register res, the rest are vrfb contexts */
-
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	vrfb_base = devm_ioremap_resource(&pdev->dev, mem);
+	vrfb_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(vrfb_base))
 		return PTR_ERR(vrfb_base);
 
diff --git a/drivers/video/fbdev/p9100.c b/drivers/video/fbdev/p9100.c
index 8c18cc51aae2..6da672e92643 100644
--- a/drivers/video/fbdev/p9100.c
+++ b/drivers/video/fbdev/p9100.c
@@ -37,7 +37,7 @@ static int p9100_ioctl(struct fb_info *, unsigned int, unsigned long);
  *  Frame buffer operations
  */
 
-static struct fb_ops p9100_ops = {
+static const struct fb_ops p9100_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= p9100_setcolreg,
 	.fb_blank		= p9100_blank,
diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c
index 632b246ca35f..ce413a9df06e 100644
--- a/drivers/video/fbdev/platinumfb.c
+++ b/drivers/video/fbdev/platinumfb.c
@@ -96,7 +96,7 @@ static int platinum_var_to_par(struct fb_var_screeninfo *var,
  * Interface used by the world
  */
 
-static struct fb_ops platinumfb_ops = {
+static const struct fb_ops platinumfb_ops = {
 	.owner =	THIS_MODULE,
 	.fb_check_var	= platinumfb_check_var,
 	.fb_set_par	= platinumfb_set_par,
diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c
index 7cc1216b1389..fe2cadeb1b66 100644
--- a/drivers/video/fbdev/pm2fb.c
+++ b/drivers/video/fbdev/pm2fb.c
@@ -1483,7 +1483,7 @@ static int pm2fb_cursor(struct fb_info *info, struct fb_cursor *cursor)
  *  Frame buffer operations
  */
 
-static struct fb_ops pm2fb_ops = {
+static const struct fb_ops pm2fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= pm2fb_check_var,
 	.fb_set_par	= pm2fb_set_par,
diff --git a/drivers/video/fbdev/pm3fb.c b/drivers/video/fbdev/pm3fb.c
index 2fa46607e0fc..2f5e23c8f8ec 100644
--- a/drivers/video/fbdev/pm3fb.c
+++ b/drivers/video/fbdev/pm3fb.c
@@ -1200,7 +1200,7 @@ static int pm3fb_blank(int blank_mode, struct fb_info *info)
 	 *  Frame buffer operations
 	 */
 
-static struct fb_ops pm3fb_ops = {
+static const struct fb_ops pm3fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= pm3fb_check_var,
 	.fb_set_par	= pm3fb_set_par,
diff --git a/drivers/video/fbdev/pmag-aa-fb.c b/drivers/video/fbdev/pmag-aa-fb.c
index d5bf185fc376..62c8de99af0b 100644
--- a/drivers/video/fbdev/pmag-aa-fb.c
+++ b/drivers/video/fbdev/pmag-aa-fb.c
@@ -147,7 +147,7 @@ static int aafb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops aafb_ops = {
+static const struct fb_ops aafb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_blank	= aafb_blank,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/pmag-ba-fb.c b/drivers/video/fbdev/pmag-ba-fb.c
index 2ddcdf7919a2..1296f9b370c2 100644
--- a/drivers/video/fbdev/pmag-ba-fb.c
+++ b/drivers/video/fbdev/pmag-ba-fb.c
@@ -117,7 +117,7 @@ static int pmagbafb_setcolreg(unsigned int regno, unsigned int red,
 	return 0;
 }
 
-static struct fb_ops pmagbafb_ops = {
+static const struct fb_ops pmagbafb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= pmagbafb_setcolreg,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/pmagb-b-fb.c b/drivers/video/fbdev/pmagb-b-fb.c
index 90d2b04feb42..9dccd51ee65a 100644
--- a/drivers/video/fbdev/pmagb-b-fb.c
+++ b/drivers/video/fbdev/pmagb-b-fb.c
@@ -121,7 +121,7 @@ static int pmagbbfb_setcolreg(unsigned int regno, unsigned int red,
 	return 0;
 }
 
-static struct fb_ops pmagbbfb_ops = {
+static const struct fb_ops pmagbbfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= pmagbbfb_setcolreg,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/ps3fb.c b/drivers/video/fbdev/ps3fb.c
index 5ed2db39d823..834f63edf700 100644
--- a/drivers/video/fbdev/ps3fb.c
+++ b/drivers/video/fbdev/ps3fb.c
@@ -934,7 +934,7 @@ static irqreturn_t ps3fb_vsync_interrupt(int irq, void *ptr)
 }
 
 
-static struct fb_ops ps3fb_ops = {
+static const struct fb_ops ps3fb_ops = {
 	.fb_open	= ps3fb_open,
 	.fb_release	= ps3fb_release,
 	.fb_read        = fb_sys_read,
diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c
index c680b3e651cb..f18d457175d9 100644
--- a/drivers/video/fbdev/pvr2fb.c
+++ b/drivers/video/fbdev/pvr2fb.c
@@ -707,7 +707,7 @@ out_unmap:
 }
 #endif /* CONFIG_PVR2_DMA */
 
-static struct fb_ops pvr2fb_ops = {
+static const struct fb_ops pvr2fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= pvr2fb_setcolreg,
 	.fb_blank	= pvr2fb_blank,
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index 5615054a0cad..9b9ec1468347 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -545,7 +545,7 @@ static irqreturn_t pxa168fb_handle_irq(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-static struct fb_ops pxa168fb_ops = {
+static const struct fb_ops pxa168fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= pxa168fb_check_var,
 	.fb_set_par	= pxa168fb_set_par,
@@ -766,8 +766,8 @@ failed_free_cmap:
 failed_free_clk:
 	clk_disable_unprepare(fbi->clk);
 failed_free_fbmem:
-	dma_free_coherent(fbi->dev, info->fix.smem_len,
-			info->screen_base, fbi->fb_start_dma);
+	dma_free_wc(fbi->dev, info->fix.smem_len,
+		    info->screen_base, fbi->fb_start_dma);
 failed_free_info:
 	kfree(info);
 
@@ -801,7 +801,7 @@ static int pxa168fb_remove(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 
-	dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
+	dma_free_wc(fbi->dev, info->fix.smem_len,
 		    info->screen_base, info->fix.smem_start);
 
 	clk_disable_unprepare(fbi->clk);
diff --git a/drivers/video/fbdev/pxafb.c b/drivers/video/fbdev/pxafb.c
index f70c9f79622e..00b96a78676e 100644
--- a/drivers/video/fbdev/pxafb.c
+++ b/drivers/video/fbdev/pxafb.c
@@ -597,7 +597,7 @@ static int pxafb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops pxafb_ops = {
+static const struct fb_ops pxafb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= pxafb_check_var,
 	.fb_set_par	= pxafb_set_par,
@@ -865,7 +865,7 @@ static int overlayfb_set_par(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops overlay_fb_ops = {
+static const struct fb_ops overlay_fb_ops = {
 	.owner			= THIS_MODULE,
 	.fb_open		= overlayfb_open,
 	.fb_release		= overlayfb_release,
@@ -2237,7 +2237,6 @@ static int pxafb_probe(struct platform_device *dev)
 {
 	struct pxafb_info *fbi;
 	struct pxafb_mach_info *inf, *pdata;
-	struct resource *r;
 	int i, irq, ret;
 
 	dev_dbg(&dev->dev, "pxafb_probe\n");
@@ -2303,14 +2302,7 @@ static int pxafb_probe(struct platform_device *dev)
 		fbi->lcd_supply = NULL;
 	}
 
-	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (r == NULL) {
-		dev_err(&dev->dev, "no I/O memory resource defined\n");
-		ret = -ENODEV;
-		goto failed;
-	}
-
-	fbi->mmio_base = devm_ioremap_resource(&dev->dev, r);
+	fbi->mmio_base = devm_platform_ioremap_resource(dev, 0);
 	if (IS_ERR(fbi->mmio_base)) {
 		dev_err(&dev->dev, "failed to get I/O memory\n");
 		ret = -EBUSY;
diff --git a/drivers/video/fbdev/q40fb.c b/drivers/video/fbdev/q40fb.c
index 0b93aa964d43..79ff14a35c85 100644
--- a/drivers/video/fbdev/q40fb.c
+++ b/drivers/video/fbdev/q40fb.c
@@ -75,7 +75,7 @@ static int q40fb_setcolreg(unsigned regno, unsigned red, unsigned green,
     return 0;
 }
 
-static struct fb_ops q40fb_ops = {
+static const struct fb_ops q40fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= q40fb_setcolreg,
 	.fb_fillrect	= cfb_fillrect,
diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c
index ca593a3e41d7..764ec3285e62 100644
--- a/drivers/video/fbdev/riva/fbdev.c
+++ b/drivers/video/fbdev/riva/fbdev.c
@@ -1673,7 +1673,7 @@ static int rivafb_sync(struct fb_info *info)
  * ------------------------------------------------------------------------- */
 
 /* kernel interface */
-static struct fb_ops riva_fb_ops = {
+static const struct fb_ops riva_fb_ops = {
 	.owner 		= THIS_MODULE,
 	.fb_open	= rivafb_open,
 	.fb_release	= rivafb_release,
diff --git a/drivers/video/fbdev/s3c-fb.c b/drivers/video/fbdev/s3c-fb.c
index ba04d7a67829..9dc925054930 100644
--- a/drivers/video/fbdev/s3c-fb.c
+++ b/drivers/video/fbdev/s3c-fb.c
@@ -1035,7 +1035,7 @@ static int s3c_fb_ioctl(struct fb_info *info, unsigned int cmd,
 	return ret;
 }
 
-static struct fb_ops s3c_fb_ops = {
+static const struct fb_ops s3c_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= s3c_fb_check_var,
 	.fb_set_par	= s3c_fb_set_par,
@@ -1411,8 +1411,7 @@ static int s3c_fb_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(sfb->dev);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	sfb->regs = devm_ioremap_resource(dev, res);
+	sfb->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(sfb->regs)) {
 		ret = PTR_ERR(sfb->regs);
 		goto err_lcd_clk;
diff --git a/drivers/video/fbdev/s3c2410fb.c b/drivers/video/fbdev/s3c2410fb.c
index a702da89910b..2fb15a540167 100644
--- a/drivers/video/fbdev/s3c2410fb.c
+++ b/drivers/video/fbdev/s3c2410fb.c
@@ -618,7 +618,7 @@ static int s3c2410fb_debug_store(struct device *dev,
 
 static DEVICE_ATTR(debug, 0664, s3c2410fb_debug_show, s3c2410fb_debug_store);
 
-static struct fb_ops s3c2410fb_ops = {
+static const struct fb_ops s3c2410fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= s3c2410fb_check_var,
 	.fb_set_par	= s3c2410fb_set_par,
diff --git a/drivers/video/fbdev/s3fb.c b/drivers/video/fbdev/s3fb.c
index be16c349c10f..60c424fae988 100644
--- a/drivers/video/fbdev/s3fb.c
+++ b/drivers/video/fbdev/s3fb.c
@@ -1037,7 +1037,7 @@ static int s3fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *info)
 
 /* Frame buffer operations */
 
-static struct fb_ops s3fb_ops = {
+static const struct fb_ops s3fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= s3fb_open,
 	.fb_release	= s3fb_release,
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index 81ad3aa1ca06..5bb653db0cec 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -574,7 +574,7 @@ static int sa1100fb_mmap(struct fb_info *info,
 	return vm_iomap_memory(vma, info->fix.mmio_start, info->fix.mmio_len);
 }
 
-static struct fb_ops sa1100fb_ops = {
+static const struct fb_ops sa1100fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= sa1100fb_check_var,
 	.fb_set_par	= sa1100fb_set_par,
@@ -1143,7 +1143,6 @@ static struct sa1100fb_info *sa1100fb_init_fbinfo(struct device *dev)
 static int sa1100fb_probe(struct platform_device *pdev)
 {
 	struct sa1100fb_info *fbi;
-	struct resource *res;
 	int ret, irq;
 
 	if (!dev_get_platdata(&pdev->dev)) {
@@ -1159,8 +1158,7 @@ static int sa1100fb_probe(struct platform_device *pdev)
 	if (!fbi)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	fbi->base = devm_ioremap_resource(&pdev->dev, res);
+	fbi->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(fbi->base))
 		return PTR_ERR(fbi->base);
 
diff --git a/drivers/video/fbdev/savage/savagefb_driver.c b/drivers/video/fbdev/savage/savagefb_driver.c
index 512789f5f884..aab312a7d9da 100644
--- a/drivers/video/fbdev/savage/savagefb_driver.c
+++ b/drivers/video/fbdev/savage/savagefb_driver.c
@@ -1637,7 +1637,7 @@ static int savagefb_release(struct fb_info *info, int user)
 	return 0;
 }
 
-static struct fb_ops savagefb_ops = {
+static const struct fb_ops savagefb_ops = {
 	.owner          = THIS_MODULE,
 	.fb_open        = savagefb_open,
 	.fb_release     = savagefb_release,
diff --git a/drivers/video/fbdev/sh7760fb.c b/drivers/video/fbdev/sh7760fb.c
index f72b03594719..5978a8921232 100644
--- a/drivers/video/fbdev/sh7760fb.c
+++ b/drivers/video/fbdev/sh7760fb.c
@@ -341,7 +341,7 @@ static int sh7760fb_set_par(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops sh7760fb_ops = {
+static const struct fb_ops sh7760fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_blank = sh7760fb_blank,
 	.fb_check_var = sh7760fb_check_var,
diff --git a/drivers/video/fbdev/sh_mobile_lcdcfb.c b/drivers/video/fbdev/sh_mobile_lcdcfb.c
index 54ee7e02a244..4ea6f932b334 100644
--- a/drivers/video/fbdev/sh_mobile_lcdcfb.c
+++ b/drivers/video/fbdev/sh_mobile_lcdcfb.c
@@ -1490,7 +1490,7 @@ sh_mobile_lcdc_overlay_mmap(struct fb_info *info, struct vm_area_struct *vma)
 				 ovl->dma_handle, ovl->fb_size);
 }
 
-static struct fb_ops sh_mobile_lcdc_overlay_ops = {
+static const struct fb_ops sh_mobile_lcdc_overlay_ops = {
 	.owner          = THIS_MODULE,
 	.fb_read        = fb_sys_read,
 	.fb_write       = fb_sys_write,
@@ -1964,7 +1964,7 @@ sh_mobile_lcdc_mmap(struct fb_info *info, struct vm_area_struct *vma)
 				 ch->dma_handle, ch->fb_size);
 }
 
-static struct fb_ops sh_mobile_lcdc_ops = {
+static const struct fb_ops sh_mobile_lcdc_ops = {
 	.owner          = THIS_MODULE,
 	.fb_setcolreg	= sh_mobile_lcdc_setcolreg,
 	.fb_read        = fb_sys_read,
diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
index 7dc0105f700d..533a047d07a2 100644
--- a/drivers/video/fbdev/simplefb.c
+++ b/drivers/video/fbdev/simplefb.c
@@ -78,7 +78,7 @@ static void simplefb_destroy(struct fb_info *info)
 		iounmap(info->screen_base);
 }
 
-static struct fb_ops simplefb_ops = {
+static const struct fb_ops simplefb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_destroy	= simplefb_destroy,
 	.fb_setcolreg	= simplefb_setcolreg,
diff --git a/drivers/video/fbdev/sis/sis_main.c b/drivers/video/fbdev/sis/sis_main.c
index b443a8ed4600..ac140962b1bf 100644
--- a/drivers/video/fbdev/sis/sis_main.c
+++ b/drivers/video/fbdev/sis/sis_main.c
@@ -1906,7 +1906,7 @@ sisfb_get_fix(struct fb_fix_screeninfo *fix, int con, struct fb_info *info)
 
 /* ----------------  fb_ops structures ----------------- */
 
-static struct fb_ops sisfb_ops = {
+static const struct fb_ops sisfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= sisfb_open,
 	.fb_release	= sisfb_release,
diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c
index 812a36cb60c3..bcacfb6934fa 100644
--- a/drivers/video/fbdev/skeletonfb.c
+++ b/drivers/video/fbdev/skeletonfb.c
@@ -634,7 +634,7 @@ int xxxfb_sync(struct fb_info *info)
      *  Frame buffer operations
      */
 
-static struct fb_ops xxxfb_ops = {
+static const struct fb_ops xxxfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= xxxfb_open,
 	.fb_read	= xxxfb_read,
diff --git a/drivers/video/fbdev/sm712fb.c b/drivers/video/fbdev/sm712fb.c
index 207d0add684b..6a1b4a853d9e 100644
--- a/drivers/video/fbdev/sm712fb.c
+++ b/drivers/video/fbdev/sm712fb.c
@@ -1369,7 +1369,7 @@ static int smtc_set_par(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops smtcfb_ops = {
+static const struct fb_ops smtcfb_ops = {
 	.owner        = THIS_MODULE,
 	.fb_check_var = smtc_check_var,
 	.fb_set_par   = smtc_set_par,
diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c
index 0e0f5bbfc5ef..bfac3ee4a642 100644
--- a/drivers/video/fbdev/smscufx.c
+++ b/drivers/video/fbdev/smscufx.c
@@ -1170,7 +1170,6 @@ static int ufx_ops_release(struct fb_info *info, int user)
 		fb_deferred_io_cleanup(info);
 		kfree(info->fbdefio);
 		info->fbdefio = NULL;
-		info->fbops->fb_mmap = ufx_ops_mmap;
 	}
 
 	pr_debug("released /dev/fb%d user=%d count=%d",
@@ -1269,7 +1268,7 @@ static int ufx_ops_blank(int blank_mode, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops ufx_ops = {
+static const struct fb_ops ufx_ops = {
 	.owner = THIS_MODULE,
 	.fb_read = fb_sys_read,
 	.fb_write = ufx_ops_write,
diff --git a/drivers/video/fbdev/ssd1307fb.c b/drivers/video/fbdev/ssd1307fb.c
index 78ca7ffc40c2..142535267fec 100644
--- a/drivers/video/fbdev/ssd1307fb.c
+++ b/drivers/video/fbdev/ssd1307fb.c
@@ -280,7 +280,7 @@ static void ssd1307fb_imageblit(struct fb_info *info, const struct fb_image *ima
 	ssd1307fb_update_display(par);
 }
 
-static struct fb_ops ssd1307fb_ops = {
+static const struct fb_ops ssd1307fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_read	= fb_sys_read,
 	.fb_write	= ssd1307fb_write,
diff --git a/drivers/video/fbdev/sstfb.c b/drivers/video/fbdev/sstfb.c
index 1f171a527174..afe6d1b7c3a0 100644
--- a/drivers/video/fbdev/sstfb.c
+++ b/drivers/video/fbdev/sstfb.c
@@ -1307,7 +1307,7 @@ static int sstfb_setup(char *options)
 }
 
 
-static struct fb_ops sstfb_ops = {
+static const struct fb_ops sstfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= sstfb_check_var,
 	.fb_set_par	= sstfb_set_par,
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 46709443a82f..de953ddb6312 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1101,7 +1101,7 @@ stifb_init_display(struct stifb_info *fb)
 
 /* ------------ Interfaces to hardware functions ------------ */
 
-static struct fb_ops stifb_ops = {
+static const struct fb_ops stifb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_setcolreg	= stifb_setcolreg,
 	.fb_blank	= stifb_blank,
diff --git a/drivers/video/fbdev/sunxvr1000.c b/drivers/video/fbdev/sunxvr1000.c
index 784c9bd5d502..15b079505a00 100644
--- a/drivers/video/fbdev/sunxvr1000.c
+++ b/drivers/video/fbdev/sunxvr1000.c
@@ -59,7 +59,7 @@ static int gfb_setcolreg(unsigned regno,
 	return 0;
 }
 
-static struct fb_ops gfb_ops = {
+static const struct fb_ops gfb_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= gfb_setcolreg,
 	.fb_fillrect		= cfb_fillrect,
diff --git a/drivers/video/fbdev/sunxvr2500.c b/drivers/video/fbdev/sunxvr2500.c
index 31683e5a8b79..1d3bacd9d5ac 100644
--- a/drivers/video/fbdev/sunxvr2500.c
+++ b/drivers/video/fbdev/sunxvr2500.c
@@ -63,7 +63,7 @@ static int s3d_setcolreg(unsigned regno,
 	return 0;
 }
 
-static struct fb_ops s3d_ops = {
+static const struct fb_ops s3d_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= s3d_setcolreg,
 	.fb_fillrect		= cfb_fillrect,
diff --git a/drivers/video/fbdev/sunxvr500.c b/drivers/video/fbdev/sunxvr500.c
index d392976126a6..9daf17b11106 100644
--- a/drivers/video/fbdev/sunxvr500.c
+++ b/drivers/video/fbdev/sunxvr500.c
@@ -186,7 +186,7 @@ static void e3d_copyarea(struct fb_info *info, const struct fb_copyarea *area)
 	spin_unlock_irqrestore(&ep->lock, flags);
 }
 
-static struct fb_ops e3d_ops = {
+static const struct fb_ops e3d_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= e3d_setcolreg,
 	.fb_fillrect		= e3d_fillrect,
diff --git a/drivers/video/fbdev/tcx.c b/drivers/video/fbdev/tcx.c
index 7897f86fb23e..34b2e5b6e84a 100644
--- a/drivers/video/fbdev/tcx.c
+++ b/drivers/video/fbdev/tcx.c
@@ -40,7 +40,7 @@ static int tcx_pan_display(struct fb_var_screeninfo *, struct fb_info *);
  *  Frame buffer operations
  */
 
-static struct fb_ops tcx_ops = {
+static const struct fb_ops tcx_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= tcx_setcolreg,
 	.fb_blank		= tcx_blank,
diff --git a/drivers/video/fbdev/tdfxfb.c b/drivers/video/fbdev/tdfxfb.c
index 0337d1a1a70b..f73e26c18c09 100644
--- a/drivers/video/fbdev/tdfxfb.c
+++ b/drivers/video/fbdev/tdfxfb.c
@@ -1141,7 +1141,7 @@ static int tdfxfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 	return 0;
 }
 
-static struct fb_ops tdfxfb_ops = {
+static const struct fb_ops tdfxfb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_check_var	= tdfxfb_check_var,
 	.fb_set_par	= tdfxfb_set_par,
diff --git a/drivers/video/fbdev/tgafb.c b/drivers/video/fbdev/tgafb.c
index 1966f1d70899..e9869135d833 100644
--- a/drivers/video/fbdev/tgafb.c
+++ b/drivers/video/fbdev/tgafb.c
@@ -70,7 +70,7 @@ static struct tc_driver tgafb_tc_driver;
  *  Frame buffer operations
  */
 
-static struct fb_ops tgafb_ops = {
+static const struct fb_ops tgafb_ops = {
 	.owner			= THIS_MODULE,
 	.fb_check_var		= tgafb_check_var,
 	.fb_set_par		= tgafb_set_par,
diff --git a/drivers/video/fbdev/tmiofb.c b/drivers/video/fbdev/tmiofb.c
index 4f2fcea10d2b..50111966c981 100644
--- a/drivers/video/fbdev/tmiofb.c
+++ b/drivers/video/fbdev/tmiofb.c
@@ -646,7 +646,7 @@ static int tmiofb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops tmiofb_ops = {
+static const struct fb_ops tmiofb_ops = {
 	.owner		= THIS_MODULE,
 
 	.fb_ioctl	= tmiofb_ioctl,
diff --git a/drivers/video/fbdev/tridentfb.c b/drivers/video/fbdev/tridentfb.c
index 91b2f6ca2607..4d20cb557ff0 100644
--- a/drivers/video/fbdev/tridentfb.c
+++ b/drivers/video/fbdev/tridentfb.c
@@ -1443,7 +1443,7 @@ static int tridentfb_blank(int blank_mode, struct fb_info *info)
 	return (blank_mode == FB_BLANK_NORMAL) ? 1 : 0;
 }
 
-static struct fb_ops tridentfb_ops = {
+static const struct fb_ops tridentfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_setcolreg = tridentfb_setcolreg,
 	.fb_pan_display = tridentfb_pan_display,
diff --git a/drivers/video/fbdev/udlfb.c b/drivers/video/fbdev/udlfb.c
index fe373b63ddd6..07905d385949 100644
--- a/drivers/video/fbdev/udlfb.c
+++ b/drivers/video/fbdev/udlfb.c
@@ -1037,7 +1037,6 @@ static int dlfb_ops_release(struct fb_info *info, int user)
 		fb_deferred_io_cleanup(info);
 		kfree(info->fbdefio);
 		info->fbdefio = NULL;
-		info->fbops->fb_mmap = dlfb_ops_mmap;
 	}
 
 	dev_dbg(info->dev, "release, user=%d count=%d\n", user, dlfb->fb_count);
diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c
index 439565cae7ab..53d08d1b56f5 100644
--- a/drivers/video/fbdev/uvesafb.c
+++ b/drivers/video/fbdev/uvesafb.c
@@ -1440,7 +1440,7 @@ static void uvesafb_init_info(struct fb_info *info, struct vbe_mode_ib *mode)
 
 	/* Disable blanking if the user requested so. */
 	if (!blank)
-		info->fbops->fb_blank = NULL;
+		uvesafb_ops.fb_blank = NULL;
 
 	/*
 	 * Find out how much IO memory is required for the mode with
@@ -1510,7 +1510,7 @@ static void uvesafb_init_info(struct fb_info *info, struct vbe_mode_ib *mode)
 			(par->ypan ? FBINFO_HWACCEL_YPAN : 0);
 
 	if (!par->ypan)
-		info->fbops->fb_pan_display = NULL;
+		uvesafb_ops.fb_pan_display = NULL;
 }
 
 static void uvesafb_init_mtrr(struct fb_info *info)
diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c
index 97a59b5a4570..4d20c4603e5a 100644
--- a/drivers/video/fbdev/valkyriefb.c
+++ b/drivers/video/fbdev/valkyriefb.c
@@ -113,7 +113,7 @@ static int valkyrie_init_info(struct fb_info *info, struct fb_info_valkyrie *p);
 static void valkyrie_par_to_fix(struct fb_par_valkyrie *par, struct fb_fix_screeninfo *fix);
 static void valkyrie_init_fix(struct fb_fix_screeninfo *fix, struct fb_info_valkyrie *p);
 
-static struct fb_ops valkyriefb_ops = {
+static const struct fb_ops valkyriefb_ops = {
 	.owner =	THIS_MODULE,
 	.fb_check_var =	valkyriefb_check_var,
 	.fb_set_par =	valkyriefb_set_par,
diff --git a/drivers/video/fbdev/vesafb.c b/drivers/video/fbdev/vesafb.c
index d9c08f6c2155..a1fe24ea869b 100644
--- a/drivers/video/fbdev/vesafb.c
+++ b/drivers/video/fbdev/vesafb.c
@@ -447,15 +447,15 @@ static int vesafb_probe(struct platform_device *dev)
 	       vesafb_fix.smem_start, info->screen_base,
 	       size_remap/1024, size_total/1024);
 
+	if (!ypan)
+		vesafb_ops.fb_pan_display = NULL;
+
 	info->fbops = &vesafb_ops;
 	info->var = vesafb_defined;
 	info->fix = vesafb_fix;
 	info->flags = FBINFO_FLAG_DEFAULT | FBINFO_MISC_FIRMWARE |
 		(ypan ? FBINFO_HWACCEL_YPAN : 0);
 
-	if (!ypan)
-		info->fbops->fb_pan_display = NULL;
-
 	if (fb_alloc_cmap(&info->cmap, 256, 0) < 0) {
 		err = -ENOMEM;
 		goto err;
diff --git a/drivers/video/fbdev/vfb.c b/drivers/video/fbdev/vfb.c
index 54127905bfe7..95d3c59867d0 100644
--- a/drivers/video/fbdev/vfb.c
+++ b/drivers/video/fbdev/vfb.c
@@ -78,7 +78,7 @@ static int vfb_pan_display(struct fb_var_screeninfo *var,
 static int vfb_mmap(struct fb_info *info,
 		    struct vm_area_struct *vma);
 
-static struct fb_ops vfb_ops = {
+static const struct fb_ops vfb_ops = {
 	.fb_read        = fb_sys_read,
 	.fb_write       = fb_sys_write,
 	.fb_check_var	= vfb_check_var,
diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c
index 2c6a576ed84c..a20eeb8308ff 100644
--- a/drivers/video/fbdev/vga16fb.c
+++ b/drivers/video/fbdev/vga16fb.c
@@ -1270,7 +1270,7 @@ static void vga16fb_destroy(struct fb_info *info)
 	framebuffer_release(info);
 }
 
-static struct fb_ops vga16fb_ops = {
+static const struct fb_ops vga16fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open        = vga16fb_open,
 	.fb_release     = vga16fb_release,
diff --git a/drivers/video/fbdev/via/viafbdev.c b/drivers/video/fbdev/via/viafbdev.c
index f815f98190bc..852673c40a2f 100644
--- a/drivers/video/fbdev/via/viafbdev.c
+++ b/drivers/video/fbdev/via/viafbdev.c
@@ -1173,13 +1173,12 @@ static ssize_t viafb_dvp0_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations viafb_dvp0_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_dvp0_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_dvp0_proc_write,
+static const struct proc_ops viafb_dvp0_proc_ops = {
+	.proc_open	= viafb_dvp0_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_dvp0_proc_write,
 };
 
 static int viafb_dvp1_proc_show(struct seq_file *m, void *v)
@@ -1238,13 +1237,12 @@ static ssize_t viafb_dvp1_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations viafb_dvp1_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_dvp1_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_dvp1_proc_write,
+static const struct proc_ops viafb_dvp1_proc_ops = {
+	.proc_open	= viafb_dvp1_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_dvp1_proc_write,
 };
 
 static int viafb_dfph_proc_show(struct seq_file *m, void *v)
@@ -1273,13 +1271,12 @@ static ssize_t viafb_dfph_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations viafb_dfph_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_dfph_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_dfph_proc_write,
+static const struct proc_ops viafb_dfph_proc_ops = {
+	.proc_open	= viafb_dfph_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_dfph_proc_write,
 };
 
 static int viafb_dfpl_proc_show(struct seq_file *m, void *v)
@@ -1308,13 +1305,12 @@ static ssize_t viafb_dfpl_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations viafb_dfpl_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_dfpl_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_dfpl_proc_write,
+static const struct proc_ops viafb_dfpl_proc_ops = {
+	.proc_open	= viafb_dfpl_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_dfpl_proc_write,
 };
 
 static int viafb_vt1636_proc_show(struct seq_file *m, void *v)
@@ -1444,13 +1440,12 @@ static ssize_t viafb_vt1636_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations viafb_vt1636_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_vt1636_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_vt1636_proc_write,
+static const struct proc_ops viafb_vt1636_proc_ops = {
+	.proc_open	= viafb_vt1636_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_vt1636_proc_write,
 };
 
 #endif /* CONFIG_FB_VIA_DIRECT_PROCFS */
@@ -1522,13 +1517,12 @@ static ssize_t viafb_iga1_odev_proc_write(struct file *file,
 	return res;
 }
 
-static const struct file_operations viafb_iga1_odev_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_iga1_odev_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_iga1_odev_proc_write,
+static const struct proc_ops viafb_iga1_odev_proc_ops = {
+	.proc_open	= viafb_iga1_odev_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_iga1_odev_proc_write,
 };
 
 static int viafb_iga2_odev_proc_show(struct seq_file *m, void *v)
@@ -1562,13 +1556,12 @@ static ssize_t viafb_iga2_odev_proc_write(struct file *file,
 	return res;
 }
 
-static const struct file_operations viafb_iga2_odev_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= viafb_iga2_odev_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= viafb_iga2_odev_proc_write,
+static const struct proc_ops viafb_iga2_odev_proc_ops = {
+	.proc_open	= viafb_iga2_odev_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= viafb_iga2_odev_proc_write,
 };
 
 #define IS_VT1636(lvds_chip)	((lvds_chip).lvds_chip_name == VT1636_LVDS)
@@ -1580,14 +1573,14 @@ static void viafb_init_proc(struct viafb_shared *shared)
 	shared->proc_entry = viafb_entry;
 	if (viafb_entry) {
 #ifdef CONFIG_FB_VIA_DIRECT_PROCFS
-		proc_create("dvp0", 0, viafb_entry, &viafb_dvp0_proc_fops);
-		proc_create("dvp1", 0, viafb_entry, &viafb_dvp1_proc_fops);
-		proc_create("dfph", 0, viafb_entry, &viafb_dfph_proc_fops);
-		proc_create("dfpl", 0, viafb_entry, &viafb_dfpl_proc_fops);
+		proc_create("dvp0", 0, viafb_entry, &viafb_dvp0_proc_ops);
+		proc_create("dvp1", 0, viafb_entry, &viafb_dvp1_proc_ops);
+		proc_create("dfph", 0, viafb_entry, &viafb_dfph_proc_ops);
+		proc_create("dfpl", 0, viafb_entry, &viafb_dfpl_proc_ops);
 		if (IS_VT1636(shared->chip_info.lvds_chip_info)
 			|| IS_VT1636(shared->chip_info.lvds_chip_info2))
 			proc_create("vt1636", 0, viafb_entry,
-				&viafb_vt1636_proc_fops);
+				    &viafb_vt1636_proc_ops);
 #endif /* CONFIG_FB_VIA_DIRECT_PROCFS */
 
 		proc_create_single("supported_output_devices", 0, viafb_entry,
@@ -1595,11 +1588,11 @@ static void viafb_init_proc(struct viafb_shared *shared)
 		iga1_entry = proc_mkdir("iga1", viafb_entry);
 		shared->iga1_proc_entry = iga1_entry;
 		proc_create("output_devices", 0, iga1_entry,
-			&viafb_iga1_odev_proc_fops);
+			    &viafb_iga1_odev_proc_ops);
 		iga2_entry = proc_mkdir("iga2", viafb_entry);
 		shared->iga2_proc_entry = iga2_entry;
 		proc_create("output_devices", 0, iga2_entry,
-			&viafb_iga2_odev_proc_fops);
+			    &viafb_iga2_odev_proc_ops);
 	}
 }
 static void viafb_remove_proc(struct viafb_shared *shared)
diff --git a/drivers/video/fbdev/vt8500lcdfb.c b/drivers/video/fbdev/vt8500lcdfb.c
index be8d9702cbb2..f744479dc7df 100644
--- a/drivers/video/fbdev/vt8500lcdfb.c
+++ b/drivers/video/fbdev/vt8500lcdfb.c
@@ -238,7 +238,7 @@ static int vt8500lcd_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops vt8500lcd_ops = {
+static const struct fb_ops vt8500lcd_ops = {
 	.owner		= THIS_MODULE,
 	.fb_set_par	= vt8500lcd_set_par,
 	.fb_setcolreg	= vt8500lcd_setcolreg,
diff --git a/drivers/video/fbdev/vt8623fb.c b/drivers/video/fbdev/vt8623fb.c
index c339a8fbad81..7b3eef1b893f 100644
--- a/drivers/video/fbdev/vt8623fb.c
+++ b/drivers/video/fbdev/vt8623fb.c
@@ -634,7 +634,7 @@ static int vt8623fb_pan_display(struct fb_var_screeninfo *var, struct fb_info *i
 
 /* Frame buffer operations */
 
-static struct fb_ops vt8623fb_ops = {
+static const struct fb_ops vt8623fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_open	= vt8623fb_open,
 	.fb_release	= vt8623fb_release,
diff --git a/drivers/video/fbdev/w100fb.c b/drivers/video/fbdev/w100fb.c
index 0796b1d90981..ad26cbffbc6f 100644
--- a/drivers/video/fbdev/w100fb.c
+++ b/drivers/video/fbdev/w100fb.c
@@ -549,7 +549,7 @@ static int w100fb_set_par(struct fb_info *info)
 /*
  *  Frame buffer operations
  */
-static struct fb_ops w100fb_ops = {
+static const struct fb_ops w100fb_ops = {
 	.owner        = THIS_MODULE,
 	.fb_check_var = w100fb_check_var,
 	.fb_set_par   = w100fb_set_par,
diff --git a/drivers/video/fbdev/wm8505fb.c b/drivers/video/fbdev/wm8505fb.c
index 17c780315ca5..b656eff58c23 100644
--- a/drivers/video/fbdev/wm8505fb.c
+++ b/drivers/video/fbdev/wm8505fb.c
@@ -246,7 +246,7 @@ static int wm8505fb_blank(int blank, struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops wm8505fb_ops = {
+static const struct fb_ops wm8505fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_set_par	= wm8505fb_set_par,
 	.fb_setcolreg	= wm8505fb_setcolreg,
diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
index a3d6b6db221b..00307b8693bf 100644
--- a/drivers/video/fbdev/xen-fbfront.c
+++ b/drivers/video/fbdev/xen-fbfront.c
@@ -328,7 +328,7 @@ static int xenfb_set_par(struct fb_info *info)
 	return 0;
 }
 
-static struct fb_ops xenfb_fb_ops = {
+static const struct fb_ops xenfb_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_read	= fb_sys_read,
 	.fb_write	= xenfb_write,
diff --git a/drivers/video/fbdev/xilinxfb.c b/drivers/video/fbdev/xilinxfb.c
index 8628829b470d..ca4ff658cad0 100644
--- a/drivers/video/fbdev/xilinxfb.c
+++ b/drivers/video/fbdev/xilinxfb.c
@@ -247,7 +247,7 @@ xilinx_fb_blank(int blank_mode, struct fb_info *fbi)
 	return 0; /* success */
 }
 
-static struct fb_ops xilinxfb_ops = {
+static const struct fb_ops xilinxfb_ops = {
 	.owner			= THIS_MODULE,
 	.fb_setcolreg		= xilinx_fb_setcolreg,
 	.fb_blank		= xilinx_fb_blank,
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index 63f0857bf62d..75d3bb948bf3 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -342,35 +342,12 @@ static void dmabuf_exp_ops_release(struct dma_buf *dma_buf)
 	mutex_unlock(&priv->lock);
 }
 
-static void *dmabuf_exp_ops_kmap(struct dma_buf *dma_buf,
-				 unsigned long page_num)
-{
-	/* Not implemented. */
-	return NULL;
-}
-
-static void dmabuf_exp_ops_kunmap(struct dma_buf *dma_buf,
-				  unsigned long page_num, void *addr)
-{
-	/* Not implemented. */
-}
-
-static int dmabuf_exp_ops_mmap(struct dma_buf *dma_buf,
-			       struct vm_area_struct *vma)
-{
-	/* Not implemented. */
-	return 0;
-}
-
 static const struct dma_buf_ops dmabuf_exp_ops =  {
 	.attach = dmabuf_exp_ops_attach,
 	.detach = dmabuf_exp_ops_detach,
 	.map_dma_buf = dmabuf_exp_ops_map_dma_buf,
 	.unmap_dma_buf = dmabuf_exp_ops_unmap_dma_buf,
 	.release = dmabuf_exp_ops_release,
-	.map = dmabuf_exp_ops_kmap,
-	.unmap = dmabuf_exp_ops_kunmap,
-	.mmap = dmabuf_exp_ops_mmap,
 };
 
 struct gntdev_dmabuf_export_args {
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 4fc83e3f5ad3..0258415ca0b2 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -1006,19 +1006,19 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	}
 	mutex_unlock(&priv->lock);
 
-	/*
-	 * gntdev takes the address of the PTE in find_grant_ptes() and passes
-	 * it to the hypervisor in gntdev_map_grant_pages(). The purpose of
-	 * the notifier is to prevent the hypervisor pointer to the PTE from
-	 * going stale.
-	 *
-	 * Since this vma's mappings can't be touched without the mmap_sem,
-	 * and we are holding it now, there is no need for the notifier_range
-	 * locking pattern.
-	 */
-	mmu_interval_read_begin(&map->notifier);
-
 	if (use_ptemod) {
+		/*
+		 * gntdev takes the address of the PTE in find_grant_ptes() and
+		 * passes it to the hypervisor in gntdev_map_grant_pages(). The
+		 * purpose of the notifier is to prevent the hypervisor pointer
+		 * to the PTE from going stale.
+		 *
+		 * Since this vma's mappings can't be touched without the
+		 * mmap_sem, and we are holding it now, there is no need for
+		 * the notifier_range locking pattern.
+		 */
+		mmu_interval_read_begin(&map->notifier);
+
 		map->pages_vm_start = vma->vm_start;
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
 					  vma->vm_end - vma->vm_start,
diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index 6d12fc368210..a8d24433c8e9 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -94,7 +94,7 @@ static void watch_target(struct xenbus_watch *watch,
 				  "%llu", &static_max) == 1))
 			static_max >>= PAGE_SHIFT - 10;
 		else
-			static_max = new_target;
+			static_max = balloon_stats.current_pages;
 
 		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c
index 60111719b01f..b20e43e148ce 100644
--- a/drivers/xen/xen-pciback/conf_space.c
+++ b/drivers/xen/xen-pciback/conf_space.c
@@ -286,6 +286,43 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value)
 	return xen_pcibios_err_to_errno(err);
 }
 
+int xen_pcibk_get_interrupt_type(struct pci_dev *dev)
+{
+	int err;
+	u16 val;
+	int ret = 0;
+
+	err = pci_read_config_word(dev, PCI_COMMAND, &val);
+	if (err)
+		return err;
+	if (!(val & PCI_COMMAND_INTX_DISABLE))
+		ret |= INTERRUPT_TYPE_INTX;
+
+	/*
+	 * Do not trust dev->msi(x)_enabled here, as enabling could be done
+	 * bypassing the pci_*msi* functions, by the qemu.
+	 */
+	if (dev->msi_cap) {
+		err = pci_read_config_word(dev,
+				dev->msi_cap + PCI_MSI_FLAGS,
+				&val);
+		if (err)
+			return err;
+		if (val & PCI_MSI_FLAGS_ENABLE)
+			ret |= INTERRUPT_TYPE_MSI;
+	}
+	if (dev->msix_cap) {
+		err = pci_read_config_word(dev,
+				dev->msix_cap + PCI_MSIX_FLAGS,
+				&val);
+		if (err)
+			return err;
+		if (val & PCI_MSIX_FLAGS_ENABLE)
+			ret |= INTERRUPT_TYPE_MSIX;
+	}
+	return ret;
+}
+
 void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev)
 {
 	struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
diff --git a/drivers/xen/xen-pciback/conf_space.h b/drivers/xen/xen-pciback/conf_space.h
index 22db630717ea..28c45180a12e 100644
--- a/drivers/xen/xen-pciback/conf_space.h
+++ b/drivers/xen/xen-pciback/conf_space.h
@@ -65,6 +65,11 @@ struct config_field_entry {
 	void *data;
 };
 
+#define INTERRUPT_TYPE_NONE (1<<0)
+#define INTERRUPT_TYPE_INTX (1<<1)
+#define INTERRUPT_TYPE_MSI  (1<<2)
+#define INTERRUPT_TYPE_MSIX (1<<3)
+
 extern bool xen_pcibk_permissive;
 
 #define OFFSET(cfg_entry) ((cfg_entry)->base_offset+(cfg_entry)->field->offset)
@@ -126,4 +131,6 @@ int xen_pcibk_config_capability_init(void);
 int xen_pcibk_config_header_add_fields(struct pci_dev *dev);
 int xen_pcibk_config_capability_add_fields(struct pci_dev *dev);
 
+int xen_pcibk_get_interrupt_type(struct pci_dev *dev);
+
 #endif				/* __XEN_PCIBACK_CONF_SPACE_H__ */
diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c
index e5694133ebe5..22f13abbe913 100644
--- a/drivers/xen/xen-pciback/conf_space_capability.c
+++ b/drivers/xen/xen-pciback/conf_space_capability.c
@@ -189,6 +189,85 @@ static const struct config_field caplist_pm[] = {
 	{}
 };
 
+static struct msi_msix_field_config {
+	u16          enable_bit; /* bit for enabling MSI/MSI-X */
+	unsigned int int_type;   /* interrupt type for exclusiveness check */
+} msi_field_config = {
+	.enable_bit	= PCI_MSI_FLAGS_ENABLE,
+	.int_type	= INTERRUPT_TYPE_MSI,
+}, msix_field_config = {
+	.enable_bit	= PCI_MSIX_FLAGS_ENABLE,
+	.int_type	= INTERRUPT_TYPE_MSIX,
+};
+
+static void *msi_field_init(struct pci_dev *dev, int offset)
+{
+	return &msi_field_config;
+}
+
+static void *msix_field_init(struct pci_dev *dev, int offset)
+{
+	return &msix_field_config;
+}
+
+static int msi_msix_flags_write(struct pci_dev *dev, int offset, u16 new_value,
+				void *data)
+{
+	int err;
+	u16 old_value;
+	const struct msi_msix_field_config *field_config = data;
+	const struct xen_pcibk_dev_data *dev_data = pci_get_drvdata(dev);
+
+	if (xen_pcibk_permissive || dev_data->permissive)
+		goto write;
+
+	err = pci_read_config_word(dev, offset, &old_value);
+	if (err)
+		return err;
+
+	if (new_value == old_value)
+		return 0;
+
+	if (!dev_data->allow_interrupt_control ||
+	    (new_value ^ old_value) & ~field_config->enable_bit)
+		return PCIBIOS_SET_FAILED;
+
+	if (new_value & field_config->enable_bit) {
+		/* don't allow enabling together with other interrupt types */
+		int int_type = xen_pcibk_get_interrupt_type(dev);
+
+		if (int_type == INTERRUPT_TYPE_NONE ||
+		    int_type == field_config->int_type)
+			goto write;
+		return PCIBIOS_SET_FAILED;
+	}
+
+write:
+	return pci_write_config_word(dev, offset, new_value);
+}
+
+static const struct config_field caplist_msix[] = {
+	{
+		.offset    = PCI_MSIX_FLAGS,
+		.size      = 2,
+		.init      = msix_field_init,
+		.u.w.read  = xen_pcibk_read_config_word,
+		.u.w.write = msi_msix_flags_write,
+	},
+	{}
+};
+
+static const struct config_field caplist_msi[] = {
+	{
+		.offset    = PCI_MSI_FLAGS,
+		.size      = 2,
+		.init      = msi_field_init,
+		.u.w.read  = xen_pcibk_read_config_word,
+		.u.w.write = msi_msix_flags_write,
+	},
+	{}
+};
+
 static struct xen_pcibk_config_capability xen_pcibk_config_capability_pm = {
 	.capability = PCI_CAP_ID_PM,
 	.fields = caplist_pm,
@@ -197,11 +276,21 @@ static struct xen_pcibk_config_capability xen_pcibk_config_capability_vpd = {
 	.capability = PCI_CAP_ID_VPD,
 	.fields = caplist_vpd,
 };
+static struct xen_pcibk_config_capability xen_pcibk_config_capability_msi = {
+	.capability = PCI_CAP_ID_MSI,
+	.fields = caplist_msi,
+};
+static struct xen_pcibk_config_capability xen_pcibk_config_capability_msix = {
+	.capability = PCI_CAP_ID_MSIX,
+	.fields = caplist_msix,
+};
 
 int xen_pcibk_config_capability_init(void)
 {
 	register_capability(&xen_pcibk_config_capability_vpd);
 	register_capability(&xen_pcibk_config_capability_pm);
+	register_capability(&xen_pcibk_config_capability_msi);
+	register_capability(&xen_pcibk_config_capability_msix);
 
 	return 0;
 }
diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c
index 10ae24b5a76e..fb4fccb4aecc 100644
--- a/drivers/xen/xen-pciback/conf_space_header.c
+++ b/drivers/xen/xen-pciback/conf_space_header.c
@@ -117,6 +117,25 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data)
 		pci_clear_mwi(dev);
 	}
 
+	if (dev_data && dev_data->allow_interrupt_control) {
+		if ((cmd->val ^ value) & PCI_COMMAND_INTX_DISABLE) {
+			if (value & PCI_COMMAND_INTX_DISABLE) {
+				pci_intx(dev, 0);
+			} else {
+				/* Do not allow enabling INTx together with MSI or MSI-X. */
+				switch (xen_pcibk_get_interrupt_type(dev)) {
+				case INTERRUPT_TYPE_NONE:
+					pci_intx(dev, 1);
+					break;
+				case INTERRUPT_TYPE_INTX:
+					break;
+				default:
+					return PCIBIOS_SET_FAILED;
+				}
+			}
+		}
+	}
+
 	cmd->val = value;
 
 	if (!xen_pcibk_permissive && (!dev_data || !dev_data->permissive))
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 097410a7cdb7..7af93d65ed51 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -304,6 +304,8 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
 	xen_pcibk_config_reset_dev(dev);
 	xen_pcibk_config_free_dyn_fields(dev);
 
+	dev_data->allow_interrupt_control = 0;
+
 	xen_unregister_device_domain_owner(dev);
 
 	spin_lock_irqsave(&found_psdev->lock, flags);
@@ -1431,6 +1433,65 @@ static ssize_t permissive_show(struct device_driver *drv, char *buf)
 }
 static DRIVER_ATTR_RW(permissive);
 
+static ssize_t allow_interrupt_control_store(struct device_driver *drv,
+					     const char *buf, size_t count)
+{
+	int domain, bus, slot, func;
+	int err;
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+
+	err = str_to_slot(buf, &domain, &bus, &slot, &func);
+	if (err)
+		goto out;
+
+	psdev = pcistub_device_find(domain, bus, slot, func);
+	if (!psdev) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	dev_data = pci_get_drvdata(psdev->dev);
+	/* the driver data for a device should never be null at this point */
+	if (!dev_data) {
+		err = -ENXIO;
+		goto release;
+	}
+	dev_data->allow_interrupt_control = 1;
+release:
+	pcistub_device_put(psdev);
+out:
+	if (!err)
+		err = count;
+	return err;
+}
+
+static ssize_t allow_interrupt_control_show(struct device_driver *drv,
+					    char *buf)
+{
+	struct pcistub_device *psdev;
+	struct xen_pcibk_dev_data *dev_data;
+	size_t count = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pcistub_devices_lock, flags);
+	list_for_each_entry(psdev, &pcistub_devices, dev_list) {
+		if (count >= PAGE_SIZE)
+			break;
+		if (!psdev->dev)
+			continue;
+		dev_data = pci_get_drvdata(psdev->dev);
+		if (!dev_data || !dev_data->allow_interrupt_control)
+			continue;
+		count +=
+		    scnprintf(buf + count, PAGE_SIZE - count, "%s\n",
+			      pci_name(psdev->dev));
+	}
+	spin_unlock_irqrestore(&pcistub_devices_lock, flags);
+	return count;
+}
+static DRIVER_ATTR_RW(allow_interrupt_control);
+
 static void pcistub_exit(void)
 {
 	driver_remove_file(&xen_pcibk_pci_driver.driver, &driver_attr_new_slot);
@@ -1441,6 +1502,8 @@ static void pcistub_exit(void)
 	driver_remove_file(&xen_pcibk_pci_driver.driver,
 			   &driver_attr_permissive);
 	driver_remove_file(&xen_pcibk_pci_driver.driver,
+			   &driver_attr_allow_interrupt_control);
+	driver_remove_file(&xen_pcibk_pci_driver.driver,
 			   &driver_attr_irq_handlers);
 	driver_remove_file(&xen_pcibk_pci_driver.driver,
 			   &driver_attr_irq_handler_state);
@@ -1530,6 +1593,9 @@ static int __init pcistub_init(void)
 	if (!err)
 		err = driver_create_file(&xen_pcibk_pci_driver.driver,
 					 &driver_attr_permissive);
+	if (!err)
+		err = driver_create_file(&xen_pcibk_pci_driver.driver,
+					 &driver_attr_allow_interrupt_control);
 
 	if (!err)
 		err = driver_create_file(&xen_pcibk_pci_driver.driver,
diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h
index 263c059bff90..ce1077e32466 100644
--- a/drivers/xen/xen-pciback/pciback.h
+++ b/drivers/xen/xen-pciback/pciback.h
@@ -45,6 +45,7 @@ struct xen_pcibk_dev_data {
 	struct list_head config_fields;
 	struct pci_saved_state *pci_saved_state;
 	unsigned int permissive:1;
+	unsigned int allow_interrupt_control:1;
 	unsigned int warned_on_write:1;
 	unsigned int enable_intx:1;
 	unsigned int isr_on:1; /* Whether the IRQ handler is installed. */
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 378486b79f96..66975da4f3b6 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -239,7 +239,9 @@ int xenbus_dev_probe(struct device *_dev)
 		goto fail;
 	}
 
+	spin_lock(&dev->reclaim_lock);
 	err = drv->probe(dev, id);
+	spin_unlock(&dev->reclaim_lock);
 	if (err)
 		goto fail_put;
 
@@ -268,8 +270,11 @@ int xenbus_dev_remove(struct device *_dev)
 
 	free_otherend_watch(dev);
 
-	if (drv->remove)
+	if (drv->remove) {
+		spin_lock(&dev->reclaim_lock);
 		drv->remove(dev);
+		spin_unlock(&dev->reclaim_lock);
+	}
 
 	module_put(drv->driver.owner);
 
@@ -468,6 +473,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 		goto fail;
 
 	dev_set_name(&xendev->dev, "%s", devname);
+	spin_lock_init(&xendev->reclaim_lock);
 
 	/* Register with generic device framework. */
 	err = device_register(&xendev->dev);
diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c
index 14876faff3b0..791f6fe01e91 100644
--- a/drivers/xen/xenbus/xenbus_probe_backend.c
+++ b/drivers/xen/xenbus/xenbus_probe_backend.c
@@ -247,6 +247,41 @@ static int backend_probe_and_watch(struct notifier_block *notifier,
 	return NOTIFY_DONE;
 }
 
+static int backend_reclaim_memory(struct device *dev, void *data)
+{
+	const struct xenbus_driver *drv;
+	struct xenbus_device *xdev;
+
+	if (!dev->driver)
+		return 0;
+	drv = to_xenbus_driver(dev->driver);
+	if (drv && drv->reclaim_memory) {
+		xdev = to_xenbus_device(dev);
+		if (!spin_trylock(&xdev->reclaim_lock))
+			return 0;
+		drv->reclaim_memory(xdev);
+		spin_unlock(&xdev->reclaim_lock);
+	}
+	return 0;
+}
+
+/*
+ * Returns 0 always because we are using shrinker to only detect memory
+ * pressure.
+ */
+static unsigned long backend_shrink_memory_count(struct shrinker *shrinker,
+				struct shrink_control *sc)
+{
+	bus_for_each_dev(&xenbus_backend.bus, NULL, NULL,
+			backend_reclaim_memory);
+	return 0;
+}
+
+static struct shrinker backend_memory_shrinker = {
+	.count_objects = backend_shrink_memory_count,
+	.seeks = DEFAULT_SEEKS,
+};
+
 static int __init xenbus_probe_backend_init(void)
 {
 	static struct notifier_block xenstore_notifier = {
@@ -263,6 +298,9 @@ static int __init xenbus_probe_backend_init(void)
 
 	register_xenstore_notifier(&xenstore_notifier);
 
+	if (register_shrinker(&backend_memory_shrinker))
+		pr_warn("shrinker registration failed\n");
+
 	return 0;
 }
 subsys_initcall(xenbus_probe_backend_init);
diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index 2e4ca4dc0960..1c9ae08225d8 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -56,10 +56,9 @@ proc_bus_zorro_read(struct file *file, char __user *buf, size_t nbytes, loff_t *
 	return nbytes;
 }
 
-static const struct file_operations proc_bus_zorro_operations = {
-	.owner		= THIS_MODULE,
-	.llseek		= proc_bus_zorro_lseek,
-	.read		= proc_bus_zorro_read,
+static const struct proc_ops bus_zorro_proc_ops = {
+	.proc_lseek	= proc_bus_zorro_lseek,
+	.proc_read	= proc_bus_zorro_read,
 };
 
 static void * zorro_seq_start(struct seq_file *m, loff_t *pos)
@@ -105,7 +104,7 @@ static int __init zorro_proc_attach_device(unsigned int slot)
 
 	sprintf(name, "%02x", slot);
 	entry = proc_create_data(name, 0, proc_bus_zorro_dir,
-				 &proc_bus_zorro_operations,
+				 &bus_zorro_proc_ops,
 				 &zorro_autocon[slot]);
 	if (!entry)
 		return -ENOMEM;
diff --git a/fs/Makefile b/fs/Makefile
index 1148c555c4d3..98be354fdb61 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -37,7 +37,7 @@ obj-$(CONFIG_FS_DAX)		+= dax.o
 obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FS_VERITY)		+= verity/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
-obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
+obj-$(CONFIG_COMPAT)		+= compat.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
 obj-$(CONFIG_BINFMT_EM86)	+= binfmt_em86.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o
diff --git a/fs/attr.c b/fs/attr.c
index df28035aa23e..b4bbdbd4c8ca 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -183,18 +183,12 @@ void setattr_copy(struct inode *inode, const struct iattr *attr)
 		inode->i_uid = attr->ia_uid;
 	if (ia_valid & ATTR_GID)
 		inode->i_gid = attr->ia_gid;
-	if (ia_valid & ATTR_ATIME) {
-		inode->i_atime = timestamp_truncate(attr->ia_atime,
-						  inode);
-	}
-	if (ia_valid & ATTR_MTIME) {
-		inode->i_mtime = timestamp_truncate(attr->ia_mtime,
-						  inode);
-	}
-	if (ia_valid & ATTR_CTIME) {
-		inode->i_ctime = timestamp_truncate(attr->ia_ctime,
-						  inode);
-	}
+	if (ia_valid & ATTR_ATIME)
+		inode->i_atime = attr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		inode->i_mtime = attr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		inode->i_ctime = attr->ia_ctime;
 	if (ia_valid & ATTR_MODE) {
 		umode_t mode = attr->ia_mode;
 
@@ -268,8 +262,13 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de
 	attr->ia_ctime = now;
 	if (!(ia_valid & ATTR_ATIME_SET))
 		attr->ia_atime = now;
+	else
+		attr->ia_atime = timestamp_truncate(attr->ia_atime, inode);
 	if (!(ia_valid & ATTR_MTIME_SET))
 		attr->ia_mtime = now;
+	else
+		attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode);
+
 	if (ia_valid & ATTR_KILL_PRIV) {
 		error = security_inode_need_killpriv(dentry);
 		if (error < 0)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index ecd8d2698515..f4713ea76e82 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -97,7 +97,7 @@ static struct linux_binfmt elf_format = {
 	.min_coredump	= ELF_EXEC_PAGESIZE,
 };
 
-#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
+#define BAD_ADDR(x) (unlikely((unsigned long)(x) >= TASK_SIZE))
 
 static int set_brk(unsigned long start, unsigned long end, int prot)
 {
@@ -161,9 +161,11 @@ static int padzero(unsigned long elf_bss)
 #endif
 
 static int
-create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
-		unsigned long load_addr, unsigned long interp_load_addr)
+create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
+		unsigned long load_addr, unsigned long interp_load_addr,
+		unsigned long e_entry)
 {
+	struct mm_struct *mm = current->mm;
 	unsigned long p = bprm->p;
 	int argc = bprm->argc;
 	int envc = bprm->envc;
@@ -176,7 +178,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	unsigned char k_rand_bytes[16];
 	int items;
 	elf_addr_t *elf_info;
-	int ei_index = 0;
+	int ei_index;
 	const struct cred *cred = current_cred();
 	struct vm_area_struct *vma;
 
@@ -226,12 +228,12 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 		return -EFAULT;
 
 	/* Create the ELF interpreter info */
-	elf_info = (elf_addr_t *)current->mm->saved_auxv;
+	elf_info = (elf_addr_t *)mm->saved_auxv;
 	/* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
 #define NEW_AUX_ENT(id, val) \
 	do { \
-		elf_info[ei_index++] = id; \
-		elf_info[ei_index++] = val; \
+		*elf_info++ = id; \
+		*elf_info++ = val; \
 	} while (0)
 
 #ifdef ARCH_DLINFO
@@ -251,7 +253,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	NEW_AUX_ENT(AT_PHNUM, exec->e_phnum);
 	NEW_AUX_ENT(AT_BASE, interp_load_addr);
 	NEW_AUX_ENT(AT_FLAGS, 0);
-	NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
+	NEW_AUX_ENT(AT_ENTRY, e_entry);
 	NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid));
 	NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid));
 	NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid));
@@ -275,12 +277,13 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	}
 #undef NEW_AUX_ENT
 	/* AT_NULL is zero; clear the rest too */
-	memset(&elf_info[ei_index], 0,
-	       sizeof current->mm->saved_auxv - ei_index * sizeof elf_info[0]);
+	memset(elf_info, 0, (char *)mm->saved_auxv +
+			sizeof(mm->saved_auxv) - (char *)elf_info);
 
 	/* And advance past the AT_NULL entry.  */
-	ei_index += 2;
+	elf_info += 2;
 
+	ei_index = elf_info - (elf_addr_t *)mm->saved_auxv;
 	sp = STACK_ADD(p, ei_index);
 
 	items = (argc + 1) + (envc + 1) + 1;
@@ -299,7 +302,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	 * Grow the stack manually; some architectures have a limit on how
 	 * far ahead a user-space access may be in order to grow the stack.
 	 */
-	vma = find_extend_vma(current->mm, bprm->p);
+	vma = find_extend_vma(mm, bprm->p);
 	if (!vma)
 		return -EFAULT;
 
@@ -308,7 +311,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 		return -EFAULT;
 
 	/* Populate list of argv pointers back to argv strings. */
-	p = current->mm->arg_end = current->mm->arg_start;
+	p = mm->arg_end = mm->arg_start;
 	while (argc-- > 0) {
 		size_t len;
 		if (__put_user((elf_addr_t)p, sp++))
@@ -320,10 +323,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	}
 	if (__put_user(0, sp++))
 		return -EFAULT;
-	current->mm->arg_end = p;
+	mm->arg_end = p;
 
 	/* Populate list of envp pointers back to envp strings. */
-	current->mm->env_end = current->mm->env_start = p;
+	mm->env_end = mm->env_start = p;
 	while (envc-- > 0) {
 		size_t len;
 		if (__put_user((elf_addr_t)p, sp++))
@@ -335,10 +338,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	}
 	if (__put_user(0, sp++))
 		return -EFAULT;
-	current->mm->env_end = p;
+	mm->env_end = p;
 
 	/* Put the elf_info on the stack in the right place.  */
-	if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t)))
+	if (copy_to_user(sp, mm->saved_auxv, ei_index * sizeof(elf_addr_t)))
 		return -EFAULT;
 	return 0;
 }
@@ -689,15 +692,17 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	int bss_prot = 0;
 	int retval, i;
 	unsigned long elf_entry;
+	unsigned long e_entry;
 	unsigned long interp_load_addr = 0;
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long reloc_func_desc __maybe_unused = 0;
 	int executable_stack = EXSTACK_DEFAULT;
+	struct elfhdr *elf_ex = (struct elfhdr *)bprm->buf;
 	struct {
-		struct elfhdr elf_ex;
 		struct elfhdr interp_elf_ex;
 	} *loc;
 	struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE;
+	struct mm_struct *mm;
 	struct pt_regs *regs;
 
 	loc = kmalloc(sizeof(*loc), GFP_KERNEL);
@@ -705,30 +710,27 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		retval = -ENOMEM;
 		goto out_ret;
 	}
-	
-	/* Get the exec-header */
-	loc->elf_ex = *((struct elfhdr *)bprm->buf);
 
 	retval = -ENOEXEC;
 	/* First of all, some simple consistency checks */
-	if (memcmp(loc->elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
+	if (memcmp(elf_ex->e_ident, ELFMAG, SELFMAG) != 0)
 		goto out;
 
-	if (loc->elf_ex.e_type != ET_EXEC && loc->elf_ex.e_type != ET_DYN)
+	if (elf_ex->e_type != ET_EXEC && elf_ex->e_type != ET_DYN)
 		goto out;
-	if (!elf_check_arch(&loc->elf_ex))
+	if (!elf_check_arch(elf_ex))
 		goto out;
-	if (elf_check_fdpic(&loc->elf_ex))
+	if (elf_check_fdpic(elf_ex))
 		goto out;
 	if (!bprm->file->f_op->mmap)
 		goto out;
 
-	elf_phdata = load_elf_phdrs(&loc->elf_ex, bprm->file);
+	elf_phdata = load_elf_phdrs(elf_ex, bprm->file);
 	if (!elf_phdata)
 		goto out;
 
 	elf_ppnt = elf_phdata;
-	for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
+	for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++) {
 		char *elf_interpreter;
 
 		if (elf_ppnt->p_type != PT_INTERP)
@@ -782,7 +784,7 @@ out_free_interp:
 	}
 
 	elf_ppnt = elf_phdata;
-	for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
+	for (i = 0; i < elf_ex->e_phnum; i++, elf_ppnt++)
 		switch (elf_ppnt->p_type) {
 		case PT_GNU_STACK:
 			if (elf_ppnt->p_flags & PF_X)
@@ -792,7 +794,7 @@ out_free_interp:
 			break;
 
 		case PT_LOPROC ... PT_HIPROC:
-			retval = arch_elf_pt_proc(&loc->elf_ex, elf_ppnt,
+			retval = arch_elf_pt_proc(elf_ex, elf_ppnt,
 						  bprm->file, false,
 						  &arch_state);
 			if (retval)
@@ -836,7 +838,7 @@ out_free_interp:
 	 * still possible to return an error to the code that invoked
 	 * the exec syscall.
 	 */
-	retval = arch_check_elf(&loc->elf_ex,
+	retval = arch_check_elf(elf_ex,
 				!!interpreter, &loc->interp_elf_ex,
 				&arch_state);
 	if (retval)
@@ -849,8 +851,8 @@ out_free_interp:
 
 	/* Do this immediately, since STACK_TOP as used in setup_arg_pages
 	   may depend on the personality.  */
-	SET_PERSONALITY2(loc->elf_ex, &arch_state);
-	if (elf_read_implies_exec(loc->elf_ex, executable_stack))
+	SET_PERSONALITY2(*elf_ex, &arch_state);
+	if (elf_read_implies_exec(*elf_ex, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
 
 	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
@@ -877,7 +879,7 @@ out_free_interp:
 	/* Now we do a little grungy work by mmapping the ELF image into
 	   the correct location in memory. */
 	for(i = 0, elf_ppnt = elf_phdata;
-	    i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
+	    i < elf_ex->e_phnum; i++, elf_ppnt++) {
 		int elf_prot, elf_flags;
 		unsigned long k, vaddr;
 		unsigned long total_size = 0;
@@ -921,9 +923,9 @@ out_free_interp:
 		 * If we are loading ET_EXEC or we have already performed
 		 * the ET_DYN load_addr calculations, proceed normally.
 		 */
-		if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
+		if (elf_ex->e_type == ET_EXEC || load_addr_set) {
 			elf_flags |= MAP_FIXED;
-		} else if (loc->elf_ex.e_type == ET_DYN) {
+		} else if (elf_ex->e_type == ET_DYN) {
 			/*
 			 * This logic is run once for the first LOAD Program
 			 * Header for ET_DYN binaries to calculate the
@@ -972,7 +974,7 @@ out_free_interp:
 			load_bias = ELF_PAGESTART(load_bias - vaddr);
 
 			total_size = total_mapping_size(elf_phdata,
-							loc->elf_ex.e_phnum);
+							elf_ex->e_phnum);
 			if (!total_size) {
 				retval = -EINVAL;
 				goto out_free_dentry;
@@ -990,7 +992,7 @@ out_free_interp:
 		if (!load_addr_set) {
 			load_addr_set = 1;
 			load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
-			if (loc->elf_ex.e_type == ET_DYN) {
+			if (elf_ex->e_type == ET_DYN) {
 				load_bias += error -
 				             ELF_PAGESTART(load_bias + vaddr);
 				load_addr += load_bias;
@@ -998,7 +1000,7 @@ out_free_interp:
 			}
 		}
 		k = elf_ppnt->p_vaddr;
-		if (k < start_code)
+		if ((elf_ppnt->p_flags & PF_X) && k < start_code)
 			start_code = k;
 		if (start_data < k)
 			start_data = k;
@@ -1031,7 +1033,7 @@ out_free_interp:
 		}
 	}
 
-	loc->elf_ex.e_entry += load_bias;
+	e_entry = elf_ex->e_entry + load_bias;
 	elf_bss += load_bias;
 	elf_brk += load_bias;
 	start_code += load_bias;
@@ -1074,7 +1076,7 @@ out_free_interp:
 		allow_write_access(interpreter);
 		fput(interpreter);
 	} else {
-		elf_entry = loc->elf_ex.e_entry;
+		elf_entry = e_entry;
 		if (BAD_ADDR(elf_entry)) {
 			retval = -EINVAL;
 			goto out_free_dentry;
@@ -1092,15 +1094,17 @@ out_free_interp:
 		goto out;
 #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
 
-	retval = create_elf_tables(bprm, &loc->elf_ex,
-			  load_addr, interp_load_addr);
+	retval = create_elf_tables(bprm, elf_ex,
+			  load_addr, interp_load_addr, e_entry);
 	if (retval < 0)
 		goto out;
-	current->mm->end_code = end_code;
-	current->mm->start_code = start_code;
-	current->mm->start_data = start_data;
-	current->mm->end_data = end_data;
-	current->mm->start_stack = bprm->p;
+
+	mm = current->mm;
+	mm->end_code = end_code;
+	mm->start_code = start_code;
+	mm->start_data = start_data;
+	mm->end_data = end_data;
+	mm->start_stack = bprm->p;
 
 	if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
 		/*
@@ -1111,12 +1115,11 @@ out_free_interp:
 		 * growing down), and into the unused ELF_ET_DYN_BASE region.
 		 */
 		if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) &&
-		    loc->elf_ex.e_type == ET_DYN && !interpreter)
-			current->mm->brk = current->mm->start_brk =
-				ELF_ET_DYN_BASE;
+		    elf_ex->e_type == ET_DYN && !interpreter) {
+			mm->brk = mm->start_brk = ELF_ET_DYN_BASE;
+		}
 
-		current->mm->brk = current->mm->start_brk =
-			arch_randomize_brk(current->mm);
+		mm->brk = mm->start_brk = arch_randomize_brk(mm);
 #ifdef compat_brk_randomized
 		current->brk_randomized = 1;
 #endif
@@ -1574,6 +1577,7 @@ static void fill_siginfo_note(struct memelfnote *note, user_siginfo_t *csigdata,
  */
 static int fill_files_note(struct memelfnote *note)
 {
+	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned count, size, names_ofs, remaining, n;
 	user_long_t *data;
@@ -1581,7 +1585,7 @@ static int fill_files_note(struct memelfnote *note)
 	char *name_base, *name_curpos;
 
 	/* *Estimated* file count and total data size needed */
-	count = current->mm->map_count;
+	count = mm->map_count;
 	if (count > UINT_MAX / 64)
 		return -EINVAL;
 	size = count * 64;
@@ -1591,6 +1595,10 @@ static int fill_files_note(struct memelfnote *note)
 	if (size >= MAX_FILE_NOTE_SIZE) /* paranoia check */
 		return -EINVAL;
 	size = round_up(size, PAGE_SIZE);
+	/*
+	 * "size" can be 0 here legitimately.
+	 * Let it ENOMEM and omit NT_FILE section which will be empty anyway.
+	 */
 	data = kvmalloc(size, GFP_KERNEL);
 	if (ZERO_OR_NULL_PTR(data))
 		return -ENOMEM;
@@ -1599,7 +1607,7 @@ static int fill_files_note(struct memelfnote *note)
 	name_base = name_curpos = ((char *)data) + names_ofs;
 	remaining = size - names_ofs;
 	count = 0;
-	for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
+	for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) {
 		struct file *file;
 		const char *filename;
 
@@ -1633,10 +1641,10 @@ static int fill_files_note(struct memelfnote *note)
 	data[0] = count;
 	data[1] = PAGE_SIZE;
 	/*
-	 * Count usually is less than current->mm->map_count,
+	 * Count usually is less than mm->map_count,
 	 * we need to move filenames down.
 	 */
-	n = current->mm->map_count - count;
+	n = mm->map_count - count;
 	if (n != 0) {
 		unsigned shift_bytes = n * 3 * sizeof(data[0]);
 		memmove(name_base - shift_bytes, name_base,
@@ -2182,7 +2190,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	int segs, i;
 	size_t vma_data_size = 0;
 	struct vm_area_struct *vma, *gate_vma;
-	struct elfhdr *elf = NULL;
+	struct elfhdr elf;
 	loff_t offset = 0, dataoff;
 	struct elf_note_info info = { };
 	struct elf_phdr *phdr4note = NULL;
@@ -2203,10 +2211,6 @@ static int elf_core_dump(struct coredump_params *cprm)
 	 * exists while dumping the mm->vm_next areas to the core file.
 	 */
   
-	/* alloc memory for large data structures: too large to be on stack */
-	elf = kmalloc(sizeof(*elf), GFP_KERNEL);
-	if (!elf)
-		goto out;
 	/*
 	 * The number of segs are recored into ELF header as 16bit value.
 	 * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here.
@@ -2230,7 +2234,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	 * Collect all the non-memory information about the process for the
 	 * notes.  This also sets up the file header.
 	 */
-	if (!fill_note_info(elf, e_phnum, &info, cprm->siginfo, cprm->regs))
+	if (!fill_note_info(&elf, e_phnum, &info, cprm->siginfo, cprm->regs))
 		goto cleanup;
 
 	has_dumped = 1;
@@ -2238,7 +2242,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 
-	offset += sizeof(*elf);				/* Elf header */
+	offset += sizeof(elf);				/* Elf header */
 	offset += segs * sizeof(struct elf_phdr);	/* Program headers */
 
 	/* Write notes phdr entry */
@@ -2257,11 +2261,13 @@ static int elf_core_dump(struct coredump_params *cprm)
 
 	dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
 
-	if (segs - 1 > ULONG_MAX / sizeof(*vma_filesz))
-		goto end_coredump;
+	/*
+	 * Zero vma process will get ZERO_SIZE_PTR here.
+	 * Let coredump continue for register state at least.
+	 */
 	vma_filesz = kvmalloc(array_size(sizeof(*vma_filesz), (segs - 1)),
 			      GFP_KERNEL);
-	if (ZERO_OR_NULL_PTR(vma_filesz))
+	if (!vma_filesz)
 		goto end_coredump;
 
 	for (i = 0, vma = first_vma(current, gate_vma); vma != NULL;
@@ -2281,12 +2287,12 @@ static int elf_core_dump(struct coredump_params *cprm)
 		shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL);
 		if (!shdr4extnum)
 			goto end_coredump;
-		fill_extnum_info(elf, shdr4extnum, e_shoff, segs);
+		fill_extnum_info(&elf, shdr4extnum, e_shoff, segs);
 	}
 
 	offset = dataoff;
 
-	if (!dump_emit(cprm, elf, sizeof(*elf)))
+	if (!dump_emit(cprm, &elf, sizeof(elf)))
 		goto end_coredump;
 
 	if (!dump_emit(cprm, phdr4note, sizeof(*phdr4note)))
@@ -2370,8 +2376,6 @@ cleanup:
 	kfree(shdr4extnum);
 	kvfree(vma_filesz);
 	kfree(phdr4note);
-	kfree(elf);
-out:
 	return has_dumped;
 }
 
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 14851584e245..404e050ce8ee 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1191,7 +1191,6 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
-	u64 sinfo_used;
 	int ret = -ENOSPC;
 
 	spin_lock(&sinfo->lock);
@@ -1205,19 +1204,38 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 
 	num_bytes = cache->length - cache->reserved - cache->pinned -
 		    cache->bytes_super - cache->used;
-	sinfo_used = btrfs_space_info_used(sinfo, true);
 
 	/*
-	 * sinfo_used + num_bytes should always <= sinfo->total_bytes.
-	 *
-	 * Here we make sure if we mark this bg RO, we still have enough
-	 * free space as buffer.
+	 * Data never overcommits, even in mixed mode, so do just the straight
+	 * check of left over space in how much we have allocated.
 	 */
-	if (sinfo_used + num_bytes <= sinfo->total_bytes) {
+	if (force) {
+		ret = 0;
+	} else if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) {
+		u64 sinfo_used = btrfs_space_info_used(sinfo, true);
+
+		/*
+		 * Here we make sure if we mark this bg RO, we still have enough
+		 * free space as buffer.
+		 */
+		if (sinfo_used + num_bytes <= sinfo->total_bytes)
+			ret = 0;
+	} else {
+		/*
+		 * We overcommit metadata, so we need to do the
+		 * btrfs_can_overcommit check here, and we need to pass in
+		 * BTRFS_RESERVE_NO_FLUSH to give ourselves the most amount of
+		 * leeway to allow us to mark this block group as read only.
+		 */
+		if (btrfs_can_overcommit(cache->fs_info, sinfo, num_bytes,
+					 BTRFS_RESERVE_NO_FLUSH))
+			ret = 0;
+	}
+
+	if (!ret) {
 		sinfo->bytes_readonly += num_bytes;
 		cache->ro++;
 		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
-		ret = 0;
 	}
 out:
 	spin_unlock(&cache->lock);
@@ -1225,9 +1243,6 @@ out:
 	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(cache->fs_info,
 			"unable to make block group %llu ro", cache->start);
-		btrfs_info(cache->fs_info,
-			"sinfo_used=%llu bg_num_bytes=%llu",
-			sinfo_used, num_bytes);
 		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0);
 	}
 	return ret;
@@ -2225,7 +2240,7 @@ again:
 		}
 	}
 
-	ret = inc_block_group_ro(cache, !do_chunk_alloc);
+	ret = inc_block_group_ro(cache, 0);
 	if (!do_chunk_alloc)
 		goto unlock_out;
 	if (!ret)
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index de95ad27722f..9ab610cc9114 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1290,7 +1290,7 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 	/* copy bytes from the working buffer into the pages */
 	while (working_bytes > 0) {
 		bytes = min_t(unsigned long, bvec.bv_len,
-				PAGE_SIZE - buf_offset);
+				PAGE_SIZE - (buf_offset % PAGE_SIZE));
 		bytes = min(bytes, working_bytes);
 
 		kaddr = kmap_atomic(bvec.bv_page);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 24658b5a5787..f2ec1a9bae28 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -326,12 +326,10 @@ u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
 			   struct seq_list *elem)
 {
 	write_lock(&fs_info->tree_mod_log_lock);
-	spin_lock(&fs_info->tree_mod_seq_lock);
 	if (!elem->seq) {
 		elem->seq = btrfs_inc_tree_mod_seq(fs_info);
 		list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
 	write_unlock(&fs_info->tree_mod_log_lock);
 
 	return elem->seq;
@@ -351,7 +349,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 	if (!seq_putting)
 		return;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	write_lock(&fs_info->tree_mod_log_lock);
 	list_del(&elem->list);
 	elem->seq = 0;
 
@@ -362,19 +360,17 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 				 * blocker with lower sequence number exists, we
 				 * cannot remove anything from the log
 				 */
-				spin_unlock(&fs_info->tree_mod_seq_lock);
+				write_unlock(&fs_info->tree_mod_log_lock);
 				return;
 			}
 			min_seq = cur_elem->seq;
 		}
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
 
 	/*
 	 * anything that's lower than the lowest existing (read: blocked)
 	 * sequence number can be removed from the tree.
 	 */
-	write_lock(&fs_info->tree_mod_log_lock);
 	tm_root = &fs_info->tree_mod_log;
 	for (node = rb_first(tm_root); node; node = next) {
 		next = rb_next(node);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f90b82050d2d..36df977b64d9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -714,14 +714,12 @@ struct btrfs_fs_info {
 	atomic_t nr_delayed_iputs;
 	wait_queue_head_t delayed_iputs_wait;
 
-	/* this protects tree_mod_seq_list */
-	spinlock_t tree_mod_seq_lock;
 	atomic64_t tree_mod_seq;
-	struct list_head tree_mod_seq_list;
 
-	/* this protects tree_mod_log */
+	/* this protects tree_mod_log and tree_mod_seq_list */
 	rwlock_t tree_mod_log_lock;
 	struct rb_root tree_mod_log;
+	struct list_head tree_mod_seq_list;
 
 	atomic_t async_delalloc_pages;
 
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index df3bd880061d..dfdb7d4f8406 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -492,7 +492,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 	if (head->is_data)
 		return;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	read_lock(&fs_info->tree_mod_log_lock);
 	if (!list_empty(&fs_info->tree_mod_seq_list)) {
 		struct seq_list *elem;
 
@@ -500,7 +500,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 					struct seq_list, list);
 		seq = elem->seq;
 	}
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	read_unlock(&fs_info->tree_mod_log_lock);
 
 again:
 	for (node = rb_first_cached(&head->ref_tree); node;
@@ -518,7 +518,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
 	struct seq_list *elem;
 	int ret = 0;
 
-	spin_lock(&fs_info->tree_mod_seq_lock);
+	read_lock(&fs_info->tree_mod_log_lock);
 	if (!list_empty(&fs_info->tree_mod_seq_list)) {
 		elem = list_first_entry(&fs_info->tree_mod_seq_list,
 					struct seq_list, list);
@@ -531,7 +531,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, u64 seq)
 		}
 	}
 
-	spin_unlock(&fs_info->tree_mod_seq_lock);
+	read_unlock(&fs_info->tree_mod_log_lock);
 	return ret;
 }
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index aea48d6ddc0c..7fa9bb79ad08 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2697,7 +2697,6 @@ int __cold open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e2d30287e2d5..c0f202741e09 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1593,21 +1593,25 @@ void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
 	/* Find first extent with bits cleared */
 	while (1) {
 		node = __etree_search(tree, start, &next, &prev, NULL, NULL);
-		if (!node) {
+		if (!node && !next && !prev) {
+			/*
+			 * Tree is completely empty, send full range and let
+			 * caller deal with it
+			 */
+			*start_ret = 0;
+			*end_ret = -1;
+			goto out;
+		} else if (!node && !next) {
+			/*
+			 * We are past the last allocated chunk, set start at
+			 * the end of the last extent.
+			 */
+			state = rb_entry(prev, struct extent_state, rb_node);
+			*start_ret = state->end + 1;
+			*end_ret = -1;
+			goto out;
+		} else if (!node) {
 			node = next;
-			if (!node) {
-				/*
-				 * We are past the last allocated chunk,
-				 * set start at the end of the last extent. The
-				 * device alloc tree should never be empty so
-				 * prev is always set.
-				 */
-				ASSERT(prev);
-				state = rb_entry(prev, struct extent_state, rb_node);
-				*start_ret = state->end + 1;
-				*end_ret = -1;
-				goto out;
-			}
 		}
 		/*
 		 * At this point 'node' either contains 'start' or start is
@@ -3438,11 +3442,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	ret = btrfs_writepage_cow_fixup(page, start, page_end);
 	if (ret) {
 		/* Fixup worker will requeue */
-		if (ret == -EBUSY)
-			wbc->pages_skipped++;
-		else
-			redirty_page_for_writepage(wbc, page);
-
+		redirty_page_for_writepage(wbc, page);
 		update_nr_written(wbc, nr_written);
 		unlock_page(page);
 		return 1;
@@ -4166,7 +4166,16 @@ retry:
 		 */
 		scanned = 1;
 		index = 0;
-		goto retry;
+
+		/*
+		 * If we're looping we could run into a page that is locked by a
+		 * writer and that writer could be waiting on writeback for a
+		 * page in our current bio, and thus deadlock, so flush the
+		 * write bio here.
+		 */
+		ret = flush_write_bio(epd);
+		if (!ret)
+			goto retry;
 	}
 
 	if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6d2bb58d277a..5b3ec93ff911 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2189,6 +2189,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 /* see btrfs_writepage_start_hook for details on why this is required */
 struct btrfs_writepage_fixup {
 	struct page *page;
+	struct inode *inode;
 	struct btrfs_work work;
 };
 
@@ -2202,27 +2203,71 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	struct inode *inode;
 	u64 page_start;
 	u64 page_end;
-	int ret;
+	int ret = 0;
+	bool free_delalloc_space = true;
 
 	fixup = container_of(work, struct btrfs_writepage_fixup, work);
 	page = fixup->page;
+	inode = fixup->inode;
+	page_start = page_offset(page);
+	page_end = page_offset(page) + PAGE_SIZE - 1;
+
+	/*
+	 * This is similar to page_mkwrite, we need to reserve the space before
+	 * we take the page lock.
+	 */
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
+					   PAGE_SIZE);
 again:
 	lock_page(page);
+
+	/*
+	 * Before we queued this fixup, we took a reference on the page.
+	 * page->mapping may go NULL, but it shouldn't be moved to a different
+	 * address space.
+	 */
 	if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
-		ClearPageChecked(page);
+		/*
+		 * Unfortunately this is a little tricky, either
+		 *
+		 * 1) We got here and our page had already been dealt with and
+		 *    we reserved our space, thus ret == 0, so we need to just
+		 *    drop our space reservation and bail.  This can happen the
+		 *    first time we come into the fixup worker, or could happen
+		 *    while waiting for the ordered extent.
+		 * 2) Our page was already dealt with, but we happened to get an
+		 *    ENOSPC above from the btrfs_delalloc_reserve_space.  In
+		 *    this case we obviously don't have anything to release, but
+		 *    because the page was already dealt with we don't want to
+		 *    mark the page with an error, so make sure we're resetting
+		 *    ret to 0.  This is why we have this check _before_ the ret
+		 *    check, because we do not want to have a surprise ENOSPC
+		 *    when the page was already properly dealt with.
+		 */
+		if (!ret) {
+			btrfs_delalloc_release_extents(BTRFS_I(inode),
+						       PAGE_SIZE);
+			btrfs_delalloc_release_space(inode, data_reserved,
+						     page_start, PAGE_SIZE,
+						     true);
+		}
+		ret = 0;
 		goto out_page;
 	}
 
-	inode = page->mapping->host;
-	page_start = page_offset(page);
-	page_end = page_offset(page) + PAGE_SIZE - 1;
+	/*
+	 * We can't mess with the page state unless it is locked, so now that
+	 * it is locked bail if we failed to make our space reservation.
+	 */
+	if (ret)
+		goto out_page;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			 &cached_state);
 
 	/* already ordered? We're done */
 	if (PagePrivate2(page))
-		goto out;
+		goto out_reserved;
 
 	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
 					PAGE_SIZE);
@@ -2235,39 +2280,49 @@ again:
 		goto again;
 	}
 
-	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
-					   PAGE_SIZE);
-	if (ret) {
-		mapping_set_error(page->mapping, ret);
-		end_extent_writepage(page, ret, page_start, page_end);
-		ClearPageChecked(page);
-		goto out;
-	 }
-
 	ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
 					&cached_state);
-	if (ret) {
-		mapping_set_error(page->mapping, ret);
-		end_extent_writepage(page, ret, page_start, page_end);
-		ClearPageChecked(page);
+	if (ret)
 		goto out_reserved;
-	}
 
-	ClearPageChecked(page);
-	set_page_dirty(page);
+	/*
+	 * Everything went as planned, we're now the owner of a dirty page with
+	 * delayed allocation bits set and space reserved for our COW
+	 * destination.
+	 *
+	 * The page was dirty when we started, nothing should have cleaned it.
+	 */
+	BUG_ON(!PageDirty(page));
+	free_delalloc_space = false;
 out_reserved:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
-	if (ret)
+	if (free_delalloc_space)
 		btrfs_delalloc_release_space(inode, data_reserved, page_start,
 					     PAGE_SIZE, true);
-out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			     &cached_state);
 out_page:
+	if (ret) {
+		/*
+		 * We hit ENOSPC or other errors.  Update the mapping and page
+		 * to reflect the errors and clean the page.
+		 */
+		mapping_set_error(page->mapping, ret);
+		end_extent_writepage(page, ret, page_start, page_end);
+		clear_page_dirty_for_io(page);
+		SetPageError(page);
+	}
+	ClearPageChecked(page);
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
 	extent_changeset_free(data_reserved);
+	/*
+	 * As a precaution, do a delayed iput in case it would be the last iput
+	 * that could need flushing space. Recursing back to fixup worker would
+	 * deadlock.
+	 */
+	btrfs_add_delayed_iput(inode);
 }
 
 /*
@@ -2291,6 +2346,13 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 	if (TestClearPagePrivate2(page))
 		return 0;
 
+	/*
+	 * PageChecked is set below when we create a fixup worker for this page,
+	 * don't try to create another one if we're already PageChecked()
+	 *
+	 * The extent_io writepage code will redirty the page if we send back
+	 * EAGAIN.
+	 */
 	if (PageChecked(page))
 		return -EAGAIN;
 
@@ -2298,12 +2360,21 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 	if (!fixup)
 		return -EAGAIN;
 
+	/*
+	 * We are already holding a reference to this inode from
+	 * write_cache_pages.  We need to hold it because the space reservation
+	 * takes place outside of the page lock, and we can't trust
+	 * page->mapping outside of the page lock.
+	 */
+	ihold(inode);
 	SetPageChecked(page);
 	get_page(page);
 	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
+	fixup->inode = inode;
 	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
-	return -EBUSY;
+
+	return -EAGAIN;
 }
 
 static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 091e5bc8c7ea..a055b657cb85 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1269,7 +1269,8 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_)
 		 * destination of the stream.
 		 */
 		if (ino == bctx->cur_objectid &&
-		    offset >= bctx->sctx->cur_inode_next_write_offset)
+		    offset + bctx->extent_len >
+		    bctx->sctx->cur_inode_next_write_offset)
 			return 0;
 	}
 
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 537bc310a673..01297c5b2666 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -159,9 +159,9 @@ static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
 	return (global->size << 1);
 }
 
-static int can_overcommit(struct btrfs_fs_info *fs_info,
-			  struct btrfs_space_info *space_info, u64 bytes,
-			  enum btrfs_reserve_flush_enum flush)
+int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
+			 struct btrfs_space_info *space_info, u64 bytes,
+			 enum btrfs_reserve_flush_enum flush)
 {
 	u64 profile;
 	u64 avail;
@@ -226,7 +226,8 @@ again:
 
 		/* Check and see if our ticket can be satisified now. */
 		if ((used + ticket->bytes <= space_info->total_bytes) ||
-		    can_overcommit(fs_info, space_info, ticket->bytes, flush)) {
+		    btrfs_can_overcommit(fs_info, space_info, ticket->bytes,
+					 flush)) {
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
@@ -639,13 +640,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
 		return to_reclaim;
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
-	if (can_overcommit(fs_info, space_info, to_reclaim,
-			   BTRFS_RESERVE_FLUSH_ALL))
+	if (btrfs_can_overcommit(fs_info, space_info, to_reclaim,
+				 BTRFS_RESERVE_FLUSH_ALL))
 		return 0;
 
 	used = btrfs_space_info_used(space_info, true);
 
-	if (can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
+	if (btrfs_can_overcommit(fs_info, space_info, SZ_1M,
+				 BTRFS_RESERVE_FLUSH_ALL))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -1004,7 +1006,7 @@ static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 	 */
 	if (!pending_tickets &&
 	    ((used + orig_bytes <= space_info->total_bytes) ||
-	     can_overcommit(fs_info, space_info, orig_bytes, flush))) {
+	     btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) {
 		btrfs_space_info_update_bytes_may_use(fs_info, space_info,
 						      orig_bytes);
 		ret = 0;
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 1a349e3f9cc1..24514cd2c6c1 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -127,6 +127,9 @@ int btrfs_reserve_metadata_bytes(struct btrfs_root *root,
 				 enum btrfs_reserve_flush_enum flush);
 void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
 				struct btrfs_space_info *space_info);
+int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
+			 struct btrfs_space_info *space_info, u64 bytes,
+			 enum btrfs_reserve_flush_enum flush);
 
 static inline void btrfs_space_info_free_bytes_may_use(
 				struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a906315efd19..0616a5434793 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2135,7 +2135,15 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	 */
 	thresh = SZ_4M;
 
-	if (!mixed && total_free_meta - thresh < block_rsv->size)
+	/*
+	 * We only want to claim there's no available space if we can no longer
+	 * allocate chunks for our metadata profile and our global reserve will
+	 * not fit in the free metadata space.  If we aren't ->full then we
+	 * still can allocate chunks and thus are fine using the currently
+	 * calculated f_bavail.
+	 */
+	if (!mixed && block_rsv->space_info->full &&
+	    total_free_meta - thresh < block_rsv->size)
 		buf->f_bavail = 0;
 
 	buf->f_type = BTRFS_SUPER_MAGIC;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index c12b91ff5f56..84fb3fa940a6 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -142,7 +142,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
 	spin_lock_init(&fs_info->qgroup_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
-	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	mutex_init(&fs_info->qgroup_ioctl_lock);
 	mutex_init(&fs_info->qgroup_rescan_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 123d9a614357..df7ce874a74b 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -441,8 +441,17 @@ static int test_find_first_clear_extent_bit(void)
 	int ret = -EINVAL;
 
 	test_msg("running find_first_clear_extent_bit test");
+
 	extent_io_tree_init(NULL, &tree, IO_TREE_SELFTEST, NULL);
 
+	/* Test correct handling of empty tree */
+	find_first_clear_extent_bit(&tree, 0, &start, &end, CHUNK_TRIMMED);
+	if (start != 0 || end != -1) {
+		test_err(
+	"error getting a range from completely empty tree: start %llu end %llu",
+			 start, end);
+		goto out;
+	}
 	/*
 	 * Set 1M-4M alloc/discard and 32M-64M thus leaving a hole between
 	 * 4M-32M
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index a6c90a003c12..05615a1099db 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -20,9 +20,13 @@
 #include <linux/refcount.h>
 #include "compression.h"
 
+/* workspace buffer size for s390 zlib hardware support */
+#define ZLIB_DFLTCC_BUF_SIZE    (4 * PAGE_SIZE)
+
 struct workspace {
 	z_stream strm;
 	char *buf;
+	unsigned int buf_size;
 	struct list_head list;
 	int level;
 };
@@ -61,7 +65,21 @@ struct list_head *zlib_alloc_workspace(unsigned int level)
 			zlib_inflate_workspacesize());
 	workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL);
 	workspace->level = level;
-	workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	workspace->buf = NULL;
+	/*
+	 * In case of s390 zlib hardware support, allocate lager workspace
+	 * buffer. If allocator fails, fall back to a single page buffer.
+	 */
+	if (zlib_deflate_dfltcc_enabled()) {
+		workspace->buf = kmalloc(ZLIB_DFLTCC_BUF_SIZE,
+					 __GFP_NOMEMALLOC | __GFP_NORETRY |
+					 __GFP_NOWARN | GFP_NOIO);
+		workspace->buf_size = ZLIB_DFLTCC_BUF_SIZE;
+	}
+	if (!workspace->buf) {
+		workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		workspace->buf_size = PAGE_SIZE;
+	}
 	if (!workspace->strm.workspace || !workspace->buf)
 		goto fail;
 
@@ -85,6 +103,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 	struct page *in_page = NULL;
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
+	unsigned int in_buf_pages;
 	unsigned long len = *total_out;
 	unsigned long nr_dest_pages = *out_pages;
 	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
@@ -102,9 +121,6 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 	workspace->strm.total_in = 0;
 	workspace->strm.total_out = 0;
 
-	in_page = find_get_page(mapping, start >> PAGE_SHIFT);
-	data_in = kmap(in_page);
-
 	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
 	if (out_page == NULL) {
 		ret = -ENOMEM;
@@ -114,12 +130,51 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 	pages[0] = out_page;
 	nr_pages = 1;
 
-	workspace->strm.next_in = data_in;
+	workspace->strm.next_in = workspace->buf;
+	workspace->strm.avail_in = 0;
 	workspace->strm.next_out = cpage_out;
 	workspace->strm.avail_out = PAGE_SIZE;
-	workspace->strm.avail_in = min(len, PAGE_SIZE);
 
 	while (workspace->strm.total_in < len) {
+		/*
+		 * Get next input pages and copy the contents to
+		 * the workspace buffer if required.
+		 */
+		if (workspace->strm.avail_in == 0) {
+			bytes_left = len - workspace->strm.total_in;
+			in_buf_pages = min(DIV_ROUND_UP(bytes_left, PAGE_SIZE),
+					   workspace->buf_size / PAGE_SIZE);
+			if (in_buf_pages > 1) {
+				int i;
+
+				for (i = 0; i < in_buf_pages; i++) {
+					if (in_page) {
+						kunmap(in_page);
+						put_page(in_page);
+					}
+					in_page = find_get_page(mapping,
+								start >> PAGE_SHIFT);
+					data_in = kmap(in_page);
+					memcpy(workspace->buf + i * PAGE_SIZE,
+					       data_in, PAGE_SIZE);
+					start += PAGE_SIZE;
+				}
+				workspace->strm.next_in = workspace->buf;
+			} else {
+				if (in_page) {
+					kunmap(in_page);
+					put_page(in_page);
+				}
+				in_page = find_get_page(mapping,
+							start >> PAGE_SHIFT);
+				data_in = kmap(in_page);
+				start += PAGE_SIZE;
+				workspace->strm.next_in = data_in;
+			}
+			workspace->strm.avail_in = min(bytes_left,
+						       (unsigned long) workspace->buf_size);
+		}
+
 		ret = zlib_deflate(&workspace->strm, Z_SYNC_FLUSH);
 		if (ret != Z_OK) {
 			pr_debug("BTRFS: deflate in loop returned %d\n",
@@ -161,33 +216,43 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
 		/* we're all done */
 		if (workspace->strm.total_in >= len)
 			break;
-
-		/* we've read in a full page, get a new one */
-		if (workspace->strm.avail_in == 0) {
-			if (workspace->strm.total_out > max_out)
-				break;
-
-			bytes_left = len - workspace->strm.total_in;
-			kunmap(in_page);
-			put_page(in_page);
-
-			start += PAGE_SIZE;
-			in_page = find_get_page(mapping,
-						start >> PAGE_SHIFT);
-			data_in = kmap(in_page);
-			workspace->strm.avail_in = min(bytes_left,
-							   PAGE_SIZE);
-			workspace->strm.next_in = data_in;
-		}
+		if (workspace->strm.total_out > max_out)
+			break;
 	}
 	workspace->strm.avail_in = 0;
-	ret = zlib_deflate(&workspace->strm, Z_FINISH);
-	zlib_deflateEnd(&workspace->strm);
-
-	if (ret != Z_STREAM_END) {
-		ret = -EIO;
-		goto out;
+	/*
+	 * Call deflate with Z_FINISH flush parameter providing more output
+	 * space but no more input data, until it returns with Z_STREAM_END.
+	 */
+	while (ret != Z_STREAM_END) {
+		ret = zlib_deflate(&workspace->strm, Z_FINISH);
+		if (ret == Z_STREAM_END)
+			break;
+		if (ret != Z_OK && ret != Z_BUF_ERROR) {
+			zlib_deflateEnd(&workspace->strm);
+			ret = -EIO;
+			goto out;
+		} else if (workspace->strm.avail_out == 0) {
+			/* get another page for the stream end */
+			kunmap(out_page);
+			if (nr_pages == nr_dest_pages) {
+				out_page = NULL;
+				ret = -E2BIG;
+				goto out;
+			}
+			out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+			if (out_page == NULL) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			cpage_out = kmap(out_page);
+			pages[nr_pages] = out_page;
+			nr_pages++;
+			workspace->strm.avail_out = PAGE_SIZE;
+			workspace->strm.next_out = cpage_out;
+		}
 	}
+	zlib_deflateEnd(&workspace->strm);
 
 	if (workspace->strm.total_out >= workspace->strm.total_in) {
 		ret = -E2BIG;
@@ -231,7 +296,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 
 	workspace->strm.total_out = 0;
 	workspace->strm.next_out = workspace->buf;
-	workspace->strm.avail_out = PAGE_SIZE;
+	workspace->strm.avail_out = workspace->buf_size;
 
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
@@ -270,7 +335,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 		}
 
 		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = PAGE_SIZE;
+		workspace->strm.avail_out = workspace->buf_size;
 
 		if (workspace->strm.avail_in == 0) {
 			unsigned long tmp;
@@ -320,7 +385,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 	workspace->strm.total_in = 0;
 
 	workspace->strm.next_out = workspace->buf;
-	workspace->strm.avail_out = PAGE_SIZE;
+	workspace->strm.avail_out = workspace->buf_size;
 	workspace->strm.total_out = 0;
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
@@ -364,7 +429,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 			buf_offset = 0;
 
 		bytes = min(PAGE_SIZE - pg_offset,
-			    PAGE_SIZE - buf_offset);
+			    PAGE_SIZE - (buf_offset % PAGE_SIZE));
 		bytes = min(bytes, bytes_left);
 
 		kaddr = kmap_atomic(dest_page);
@@ -375,7 +440,7 @@ int zlib_decompress(struct list_head *ws, unsigned char *data_in,
 		bytes_left -= bytes;
 next:
 		workspace->strm.next_out = workspace->buf;
-		workspace->strm.avail_out = PAGE_SIZE;
+		workspace->strm.avail_out = workspace->buf_size;
 	}
 
 	if (ret != Z_STREAM_END && bytes_left != 0)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 145d46ba25ae..21ada2c4a88c 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -2072,7 +2072,6 @@ struct ceph_mds_request *
 ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 {
 	struct ceph_mds_request *req = kzalloc(sizeof(*req), GFP_NOFS);
-	struct timespec64 ts;
 
 	if (!req)
 		return ERR_PTR(-ENOMEM);
@@ -2091,8 +2090,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	init_completion(&req->r_safe_completion);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 
-	ktime_get_coarse_real_ts64(&ts);
-	req->r_stamp = timespec64_trunc(ts, mdsc->fsc->sb->s_time_gran);
+	ktime_get_coarse_real_ts64(&req->r_stamp);
 
 	req->r_op = op;
 	req->r_direct_mode = mode;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 19f6e592b941..276e4b5ea8e0 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -611,12 +611,12 @@ static int cifs_stats_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, cifs_stats_proc_show, NULL);
 }
 
-static const struct file_operations cifs_stats_proc_fops = {
-	.open		= cifs_stats_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= cifs_stats_proc_write,
+static const struct proc_ops cifs_stats_proc_ops = {
+	.proc_open	= cifs_stats_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= cifs_stats_proc_write,
 };
 
 #ifdef CONFIG_CIFS_SMB_DIRECT
@@ -640,12 +640,12 @@ static int name##_open(struct inode *inode, struct file *file) \
 	return single_open(file, name##_proc_show, NULL); \
 } \
 \
-static const struct file_operations cifs_##name##_proc_fops = { \
-	.open		= name##_open, \
-	.read		= seq_read, \
-	.llseek		= seq_lseek, \
-	.release	= single_release, \
-	.write		= name##_write, \
+static const struct proc_ops cifs_##name##_proc_fops = { \
+	.proc_open	= name##_open, \
+	.proc_read	= seq_read, \
+	.proc_lseek	= seq_lseek, \
+	.proc_release	= single_release, \
+	.proc_write	= name##_write, \
 }
 
 PROC_FILE_DEFINE(rdma_readwrite_threshold);
@@ -659,11 +659,11 @@ PROC_FILE_DEFINE(smbd_receive_credit_max);
 #endif
 
 static struct proc_dir_entry *proc_fs_cifs;
-static const struct file_operations cifsFYI_proc_fops;
-static const struct file_operations cifs_lookup_cache_proc_fops;
-static const struct file_operations traceSMB_proc_fops;
-static const struct file_operations cifs_security_flags_proc_fops;
-static const struct file_operations cifs_linux_ext_proc_fops;
+static const struct proc_ops cifsFYI_proc_ops;
+static const struct proc_ops cifs_lookup_cache_proc_ops;
+static const struct proc_ops traceSMB_proc_ops;
+static const struct proc_ops cifs_security_flags_proc_ops;
+static const struct proc_ops cifs_linux_ext_proc_ops;
 
 void
 cifs_proc_init(void)
@@ -678,18 +678,18 @@ cifs_proc_init(void)
 	proc_create_single("open_files", 0400, proc_fs_cifs,
 			cifs_debug_files_proc_show);
 
-	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
-	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
-	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
+	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_ops);
+	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_ops);
+	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_ops);
 	proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs,
-		    &cifs_linux_ext_proc_fops);
+		    &cifs_linux_ext_proc_ops);
 	proc_create("SecurityFlags", 0644, proc_fs_cifs,
-		    &cifs_security_flags_proc_fops);
+		    &cifs_security_flags_proc_ops);
 	proc_create("LookupCacheEnabled", 0644, proc_fs_cifs,
-		    &cifs_lookup_cache_proc_fops);
+		    &cifs_lookup_cache_proc_ops);
 
 #ifdef CONFIG_CIFS_DFS_UPCALL
-	proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_fops);
+	proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_ops);
 #endif
 
 #ifdef CONFIG_CIFS_SMB_DIRECT
@@ -774,12 +774,12 @@ static ssize_t cifsFYI_proc_write(struct file *file, const char __user *buffer,
 	return count;
 }
 
-static const struct file_operations cifsFYI_proc_fops = {
-	.open		= cifsFYI_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= cifsFYI_proc_write,
+static const struct proc_ops cifsFYI_proc_ops = {
+	.proc_open	= cifsFYI_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= cifsFYI_proc_write,
 };
 
 static int cifs_linux_ext_proc_show(struct seq_file *m, void *v)
@@ -805,12 +805,12 @@ static ssize_t cifs_linux_ext_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations cifs_linux_ext_proc_fops = {
-	.open		= cifs_linux_ext_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= cifs_linux_ext_proc_write,
+static const struct proc_ops cifs_linux_ext_proc_ops = {
+	.proc_open	= cifs_linux_ext_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= cifs_linux_ext_proc_write,
 };
 
 static int cifs_lookup_cache_proc_show(struct seq_file *m, void *v)
@@ -836,12 +836,12 @@ static ssize_t cifs_lookup_cache_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations cifs_lookup_cache_proc_fops = {
-	.open		= cifs_lookup_cache_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= cifs_lookup_cache_proc_write,
+static const struct proc_ops cifs_lookup_cache_proc_ops = {
+	.proc_open	= cifs_lookup_cache_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= cifs_lookup_cache_proc_write,
 };
 
 static int traceSMB_proc_show(struct seq_file *m, void *v)
@@ -867,12 +867,12 @@ static ssize_t traceSMB_proc_write(struct file *file, const char __user *buffer,
 	return count;
 }
 
-static const struct file_operations traceSMB_proc_fops = {
-	.open		= traceSMB_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= traceSMB_proc_write,
+static const struct proc_ops traceSMB_proc_ops = {
+	.proc_open	= traceSMB_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= traceSMB_proc_write,
 };
 
 static int cifs_security_flags_proc_show(struct seq_file *m, void *v)
@@ -978,12 +978,12 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations cifs_security_flags_proc_fops = {
-	.open		= cifs_security_flags_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= cifs_security_flags_proc_write,
+static const struct proc_ops cifs_security_flags_proc_ops = {
+	.proc_open	= cifs_security_flags_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= cifs_security_flags_proc_write,
 };
 #else
 inline void cifs_proc_init(void)
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 096a4c18fbd0..b87456bae1a1 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -156,5 +156,5 @@ extern int cifs_truncate_page(struct address_space *mapping, loff_t from);
 extern const struct export_operations cifs_export_ops;
 #endif /* CONFIG_CIFS_NFSD_EXPORT */
 
-#define CIFS_VERSION   "2.24"
+#define CIFS_VERSION   "2.25"
 #endif				/* _CIFSFS_H */
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 9a384d1e27b4..43c1b43a07ec 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -8,6 +8,7 @@
 #include <linux/jhash.h>
 #include <linux/ktime.h>
 #include <linux/slab.h>
+#include <linux/proc_fs.h>
 #include <linux/nls.h>
 #include <linux/workqueue.h>
 #include "cifsglob.h"
@@ -211,12 +212,12 @@ static int dfscache_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, dfscache_proc_show, NULL);
 }
 
-const struct file_operations dfscache_proc_fops = {
-	.open		= dfscache_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= dfscache_proc_write,
+const struct proc_ops dfscache_proc_ops = {
+	.proc_open	= dfscache_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= dfscache_proc_write,
 };
 
 #ifdef CONFIG_CIFS_DEBUG2
diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h
index 76c732943f5f..99ee44f8ad07 100644
--- a/fs/cifs/dfs_cache.h
+++ b/fs/cifs/dfs_cache.h
@@ -24,7 +24,7 @@ struct dfs_cache_tgt_iterator {
 
 extern int dfs_cache_init(void);
 extern void dfs_cache_destroy(void);
-extern const struct file_operations dfscache_proc_fops;
+extern const struct proc_ops dfscache_proc_ops;
 
 extern int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses,
 			  const struct nls_table *nls_codepage, int remap,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9b547f7f5f5d..676e96a7a9f0 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -113,6 +113,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 	}
 
 	 /* revalidate if mtime or size have changed */
+	fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode);
 	if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) &&
 	    cifs_i->server_eof == fattr->cf_eof) {
 		cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
@@ -162,6 +163,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	cifs_revalidate_cache(inode, fattr);
 
 	spin_lock(&inode->i_lock);
+	fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode);
+	fattr->cf_atime = timestamp_truncate(fattr->cf_atime, inode);
+	fattr->cf_ctime = timestamp_truncate(fattr->cf_ctime, inode);
 	/* we do not want atime to be less than mtime, it broke some apps */
 	if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime) < 0)
 		inode->i_atime = fattr->cf_mtime;
@@ -329,8 +333,7 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb)
 	fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
 	fattr->cf_uid = cifs_sb->mnt_uid;
 	fattr->cf_gid = cifs_sb->mnt_gid;
-	ktime_get_real_ts64(&fattr->cf_mtime);
-	fattr->cf_mtime = timespec64_trunc(fattr->cf_mtime, sb->s_time_gran);
+	ktime_get_coarse_real_ts64(&fattr->cf_mtime);
 	fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime;
 	fattr->cf_nlink = 2;
 	fattr->cf_flags = CIFS_FATTR_DFS_REFERRAL;
@@ -609,10 +612,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 
 	if (info->LastAccessTime)
 		fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
-	else {
-		ktime_get_real_ts64(&fattr->cf_atime);
-		fattr->cf_atime = timespec64_trunc(fattr->cf_atime, sb->s_time_gran);
-	}
+	else
+		ktime_get_coarse_real_ts64(&fattr->cf_atime);
 
 	fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
 	fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7edba3e6d5e6..14f209f7376f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -312,7 +312,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 		if (server->tcpStatus != CifsNeedReconnect)
 			break;
 
-		if (--retries)
+		if (retries && --retries)
 			continue;
 
 		/*
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
deleted file mode 100644
index 358ea2ecf36b..000000000000
--- a/fs/compat_ioctl.c
+++ /dev/null
@@ -1,261 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * ioctl32.c: Conversion between 32bit and 64bit native ioctls.
- *
- * Copyright (C) 1997-2000  Jakub Jelinek  (jakub@redhat.com)
- * Copyright (C) 1998  Eddie C. Dost  (ecd@skynet.be)
- * Copyright (C) 2001,2002  Andi Kleen, SuSE Labs 
- * Copyright (C) 2003       Pavel Machek (pavel@ucw.cz)
- *
- * These routines maintain argument size conversion between 32bit and 64bit
- * ioctls.
- */
-
-#include <linux/types.h>
-#include <linux/compat.h>
-#include <linux/kernel.h>
-#include <linux/capability.h>
-#include <linux/compiler.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/ioctl.h>
-#include <linux/if.h>
-#include <linux/raid/md_u.h>
-#include <linux/falloc.h>
-#include <linux/file.h>
-#include <linux/ppp-ioctl.h>
-#include <linux/if_pppox.h>
-#include <linux/tty.h>
-#include <linux/vt_kern.h>
-#include <linux/blkdev.h>
-#include <linux/serial.h>
-#include <linux/ctype.h>
-#include <linux/syscalls.h>
-#include <linux/gfp.h>
-#include <linux/cec.h>
-
-#include "internal.h"
-
-#ifdef CONFIG_BLOCK
-#include <linux/cdrom.h>
-#include <linux/fd.h>
-#include <scsi/scsi.h>
-#include <scsi/scsi_ioctl.h>
-#include <scsi/sg.h>
-#endif
-
-#include <linux/uaccess.h>
-#include <linux/watchdog.h>
-
-#include <linux/hiddev.h>
-
-
-#include <linux/sort.h>
-
-/*
- * simple reversible transform to make our table more evenly
- * distributed after sorting.
- */
-#define XFORM(i) (((i) ^ ((i) << 27) ^ ((i) << 17)) & 0xffffffff)
-
-#define COMPATIBLE_IOCTL(cmd) XFORM((u32)cmd),
-static unsigned int ioctl_pointer[] = {
-#ifdef CONFIG_BLOCK
-/* Big S */
-COMPATIBLE_IOCTL(SCSI_IOCTL_GET_IDLUN)
-COMPATIBLE_IOCTL(SCSI_IOCTL_DOORLOCK)
-COMPATIBLE_IOCTL(SCSI_IOCTL_DOORUNLOCK)
-COMPATIBLE_IOCTL(SCSI_IOCTL_TEST_UNIT_READY)
-COMPATIBLE_IOCTL(SCSI_IOCTL_GET_BUS_NUMBER)
-COMPATIBLE_IOCTL(SCSI_IOCTL_SEND_COMMAND)
-COMPATIBLE_IOCTL(SCSI_IOCTL_PROBE_HOST)
-COMPATIBLE_IOCTL(SCSI_IOCTL_GET_PCI)
-#endif
-#ifdef CONFIG_BLOCK
-/* SG stuff */
-COMPATIBLE_IOCTL(SG_IO)
-COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
-COMPATIBLE_IOCTL(SG_SET_TIMEOUT)
-COMPATIBLE_IOCTL(SG_GET_TIMEOUT)
-COMPATIBLE_IOCTL(SG_EMULATED_HOST)
-COMPATIBLE_IOCTL(SG_GET_TRANSFORM)
-COMPATIBLE_IOCTL(SG_SET_RESERVED_SIZE)
-COMPATIBLE_IOCTL(SG_GET_RESERVED_SIZE)
-COMPATIBLE_IOCTL(SG_GET_SCSI_ID)
-COMPATIBLE_IOCTL(SG_SET_FORCE_LOW_DMA)
-COMPATIBLE_IOCTL(SG_GET_LOW_DMA)
-COMPATIBLE_IOCTL(SG_SET_FORCE_PACK_ID)
-COMPATIBLE_IOCTL(SG_GET_PACK_ID)
-COMPATIBLE_IOCTL(SG_GET_NUM_WAITING)
-COMPATIBLE_IOCTL(SG_SET_DEBUG)
-COMPATIBLE_IOCTL(SG_GET_SG_TABLESIZE)
-COMPATIBLE_IOCTL(SG_GET_COMMAND_Q)
-COMPATIBLE_IOCTL(SG_SET_COMMAND_Q)
-COMPATIBLE_IOCTL(SG_GET_VERSION_NUM)
-COMPATIBLE_IOCTL(SG_NEXT_CMD_LEN)
-COMPATIBLE_IOCTL(SG_SCSI_RESET)
-COMPATIBLE_IOCTL(SG_GET_REQUEST_TABLE)
-COMPATIBLE_IOCTL(SG_SET_KEEP_ORPHAN)
-COMPATIBLE_IOCTL(SG_GET_KEEP_ORPHAN)
-#endif
-};
-
-/*
- * Convert common ioctl arguments based on their command number
- *
- * Please do not add any code in here. Instead, implement
- * a compat_ioctl operation in the place that handleѕ the
- * ioctl for the native case.
- */
-static long do_ioctl_trans(unsigned int cmd,
-		 unsigned long arg, struct file *file)
-{
-	return -ENOIOCTLCMD;
-}
-
-static int compat_ioctl_check_table(unsigned int xcmd)
-{
-#ifdef CONFIG_BLOCK
-	int i;
-	const int max = ARRAY_SIZE(ioctl_pointer) - 1;
-
-	BUILD_BUG_ON(max >= (1 << 16));
-
-	/* guess initial offset into table, assuming a
-	   normalized distribution */
-	i = ((xcmd >> 16) * max) >> 16;
-
-	/* do linear search up first, until greater or equal */
-	while (ioctl_pointer[i] < xcmd && i < max)
-		i++;
-
-	/* then do linear search down */
-	while (ioctl_pointer[i] > xcmd && i > 0)
-		i--;
-
-	return ioctl_pointer[i] == xcmd;
-#else
-	return 0;
-#endif
-}
-
-COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
-		       compat_ulong_t, arg32)
-{
-	unsigned long arg = arg32;
-	struct fd f = fdget(fd);
-	int error = -EBADF;
-	if (!f.file)
-		goto out;
-
-	/* RED-PEN how should LSM module know it's handling 32bit? */
-	error = security_file_ioctl(f.file, cmd, arg);
-	if (error)
-		goto out_fput;
-
-	switch (cmd) {
-	/* these are never seen by ->ioctl(), no argument or int argument */
-	case FIOCLEX:
-	case FIONCLEX:
-	case FIFREEZE:
-	case FITHAW:
-	case FICLONE:
-		goto do_ioctl;
-	/* these are never seen by ->ioctl(), pointer argument */
-	case FIONBIO:
-	case FIOASYNC:
-	case FIOQSIZE:
-	case FS_IOC_FIEMAP:
-	case FIGETBSZ:
-	case FICLONERANGE:
-	case FIDEDUPERANGE:
-		goto found_handler;
-	/*
-	 * The next group is the stuff handled inside file_ioctl().
-	 * For regular files these never reach ->ioctl(); for
-	 * devices, sockets, etc. they do and one (FIONREAD) is
-	 * even accepted in some cases.  In all those cases
-	 * argument has the same type, so we can handle these
-	 * here, shunting them towards do_vfs_ioctl().
-	 * ->compat_ioctl() will never see any of those.
-	 */
-	/* pointer argument, never actually handled by ->ioctl() */
-	case FIBMAP:
-		goto found_handler;
-	/* handled by some ->ioctl(); always a pointer to int */
-	case FIONREAD:
-		goto found_handler;
-	/* these get messy on amd64 due to alignment differences */
-#if defined(CONFIG_X86_64)
-	case FS_IOC_RESVSP_32:
-	case FS_IOC_RESVSP64_32:
-		error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg));
-		goto out_fput;
-	case FS_IOC_UNRESVSP_32:
-	case FS_IOC_UNRESVSP64_32:
-		error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE,
-				compat_ptr(arg));
-		goto out_fput;
-	case FS_IOC_ZERO_RANGE_32:
-		error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE,
-				compat_ptr(arg));
-		goto out_fput;
-#else
-	case FS_IOC_RESVSP:
-	case FS_IOC_RESVSP64:
-	case FS_IOC_UNRESVSP:
-	case FS_IOC_UNRESVSP64:
-	case FS_IOC_ZERO_RANGE:
-		goto found_handler;
-#endif
-
-	default:
-		if (f.file->f_op->compat_ioctl) {
-			error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
-			if (error != -ENOIOCTLCMD)
-				goto out_fput;
-		}
-
-		if (!f.file->f_op->unlocked_ioctl)
-			goto do_ioctl;
-		break;
-	}
-
-	if (compat_ioctl_check_table(XFORM(cmd)))
-		goto found_handler;
-
-	error = do_ioctl_trans(cmd, arg, f.file);
-	if (error == -ENOIOCTLCMD)
-		error = -ENOTTY;
-
-	goto out_fput;
-
- found_handler:
-	arg = (unsigned long)compat_ptr(arg);
- do_ioctl:
-	error = do_vfs_ioctl(f.file, fd, cmd, arg);
- out_fput:
-	fdput(f);
- out:
-	return error;
-}
-
-static int __init init_sys32_ioctl_cmp(const void *p, const void *q)
-{
-	unsigned int a, b;
-	a = *(unsigned int *)p;
-	b = *(unsigned int *)q;
-	if (a > b)
-		return 1;
-	if (a < b)
-		return -1;
-	return 0;
-}
-
-static int __init init_sys32_ioctl(void)
-{
-	sort(ioctl_pointer, ARRAY_SIZE(ioctl_pointer), sizeof(*ioctl_pointer),
-		init_sys32_ioctl_cmp, NULL);
-	return 0;
-}
-__initcall(init_sys32_ioctl);
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 680aba9c00d5..fd0b5dd68f9e 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -76,14 +76,11 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr)
 	if (ia_valid & ATTR_GID)
 		sd_iattr->ia_gid = iattr->ia_gid;
 	if (ia_valid & ATTR_ATIME)
-		sd_iattr->ia_atime = timestamp_truncate(iattr->ia_atime,
-						      inode);
+		sd_iattr->ia_atime = iattr->ia_atime;
 	if (ia_valid & ATTR_MTIME)
-		sd_iattr->ia_mtime = timestamp_truncate(iattr->ia_mtime,
-						      inode);
+		sd_iattr->ia_mtime = iattr->ia_mtime;
 	if (ia_valid & ATTR_CTIME)
-		sd_iattr->ia_ctime = timestamp_truncate(iattr->ia_ctime,
-						      inode);
+		sd_iattr->ia_ctime = iattr->ia_ctime;
 	if (ia_valid & ATTR_MODE) {
 		umode_t mode = iattr->ia_mode;
 
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index dc6cffc4feba..e742dfc66933 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -332,7 +332,10 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 		parent = debugfs_mount->mnt_root;
 
 	inode_lock(d_inode(parent));
-	dentry = lookup_one_len(name, parent, strlen(name));
+	if (unlikely(IS_DEADDIR(d_inode(parent))))
+		dentry = ERR_PTR(-ENOENT);
+	else
+		dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
 		if (d_is_dir(dentry))
 			pr_err("Directory '%s' with parent '%s' already present!\n",
@@ -681,62 +684,15 @@ static void __debugfs_file_removed(struct dentry *dentry)
 		wait_for_completion(&fsd->active_users_drained);
 }
 
-static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
-{
-	int ret = 0;
-
-	if (simple_positive(dentry)) {
-		dget(dentry);
-		if (d_is_dir(dentry)) {
-			ret = simple_rmdir(d_inode(parent), dentry);
-			if (!ret)
-				fsnotify_rmdir(d_inode(parent), dentry);
-		} else {
-			simple_unlink(d_inode(parent), dentry);
-			fsnotify_unlink(d_inode(parent), dentry);
-		}
-		if (!ret)
-			d_delete(dentry);
-		if (d_is_reg(dentry))
-			__debugfs_file_removed(dentry);
-		dput(dentry);
-	}
-	return ret;
-}
-
-/**
- * debugfs_remove - removes a file or directory from the debugfs filesystem
- * @dentry: a pointer to a the dentry of the file or directory to be
- *          removed.  If this parameter is NULL or an error value, nothing
- *          will be done.
- *
- * This function removes a file or directory in debugfs that was previously
- * created with a call to another debugfs function (like
- * debugfs_create_file() or variants thereof.)
- *
- * This function is required to be called in order for the file to be
- * removed, no automatic cleanup of files will happen when a module is
- * removed, you are responsible here.
- */
-void debugfs_remove(struct dentry *dentry)
+static void remove_one(struct dentry *victim)
 {
-	struct dentry *parent;
-	int ret;
-
-	if (IS_ERR_OR_NULL(dentry))
-		return;
-
-	parent = dentry->d_parent;
-	inode_lock(d_inode(parent));
-	ret = __debugfs_remove(dentry, parent);
-	inode_unlock(d_inode(parent));
-	if (!ret)
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+        if (d_is_reg(victim))
+		__debugfs_file_removed(victim);
+	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
-EXPORT_SYMBOL_GPL(debugfs_remove);
 
 /**
- * debugfs_remove_recursive - recursively removes a directory
+ * debugfs_remove - recursively removes a directory
  * @dentry: a pointer to a the dentry of the directory to be removed.  If this
  *          parameter is NULL or an error value, nothing will be done.
  *
@@ -748,65 +704,16 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
  * removed, no automatic cleanup of files will happen when a module is
  * removed, you are responsible here.
  */
-void debugfs_remove_recursive(struct dentry *dentry)
+void debugfs_remove(struct dentry *dentry)
 {
-	struct dentry *child, *parent;
-
 	if (IS_ERR_OR_NULL(dentry))
 		return;
 
-	parent = dentry;
- down:
-	inode_lock(d_inode(parent));
- loop:
-	/*
-	 * The parent->d_subdirs is protected by the d_lock. Outside that
-	 * lock, the child can be unlinked and set to be freed which can
-	 * use the d_u.d_child as the rcu head and corrupt this list.
-	 */
-	spin_lock(&parent->d_lock);
-	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!simple_positive(child))
-			continue;
-
-		/* perhaps simple_empty(child) makes more sense */
-		if (!list_empty(&child->d_subdirs)) {
-			spin_unlock(&parent->d_lock);
-			inode_unlock(d_inode(parent));
-			parent = child;
-			goto down;
-		}
-
-		spin_unlock(&parent->d_lock);
-
-		if (!__debugfs_remove(child, parent))
-			simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-
-		/*
-		 * The parent->d_lock protects agaist child from unlinking
-		 * from d_subdirs. When releasing the parent->d_lock we can
-		 * no longer trust that the next pointer is valid.
-		 * Restart the loop. We'll skip this one with the
-		 * simple_positive() check.
-		 */
-		goto loop;
-	}
-	spin_unlock(&parent->d_lock);
-
-	inode_unlock(d_inode(parent));
-	child = parent;
-	parent = parent->d_parent;
-	inode_lock(d_inode(parent));
-
-	if (child != dentry)
-		/* go up */
-		goto loop;
-
-	if (!__debugfs_remove(child, parent))
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
-	inode_unlock(d_inode(parent));
+	simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count);
+	simple_recursive_removal(dentry, remove_one);
+	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 }
-EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
+EXPORT_SYMBOL_GPL(debugfs_remove);
 
 /**
  * debugfs_rename - rename a file/directory in the debugfs filesystem
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 67a395039268..b041b66002db 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -354,12 +354,6 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p)
 	return container_of(p, struct ep_pqueue, pt)->epi;
 }
 
-/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
-static inline int ep_op_has_event(int op)
-{
-	return op != EPOLL_CTL_DEL;
-}
-
 /* Initialize the poll safe wake up structure */
 static void ep_nested_calls_init(struct nested_calls *ncalls)
 {
@@ -2074,27 +2068,28 @@ SYSCALL_DEFINE1(epoll_create, int, size)
 	return do_epoll_create(0);
 }
 
-/*
- * The following function implements the controller interface for
- * the eventpoll file that enables the insertion/removal/change of
- * file descriptors inside the interest set.
- */
-SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
-		struct epoll_event __user *, event)
+static inline int epoll_mutex_lock(struct mutex *mutex, int depth,
+				   bool nonblock)
+{
+	if (!nonblock) {
+		mutex_lock_nested(mutex, depth);
+		return 0;
+	}
+	if (mutex_trylock(mutex))
+		return 0;
+	return -EAGAIN;
+}
+
+int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
+		 bool nonblock)
 {
 	int error;
 	int full_check = 0;
 	struct fd f, tf;
 	struct eventpoll *ep;
 	struct epitem *epi;
-	struct epoll_event epds;
 	struct eventpoll *tep = NULL;
 
-	error = -EFAULT;
-	if (ep_op_has_event(op) &&
-	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
-		goto error_return;
-
 	error = -EBADF;
 	f = fdget(epfd);
 	if (!f.file)
@@ -2112,7 +2107,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 
 	/* Check if EPOLLWAKEUP is allowed */
 	if (ep_op_has_event(op))
-		ep_take_care_of_epollwakeup(&epds);
+		ep_take_care_of_epollwakeup(epds);
 
 	/*
 	 * We have to check that the file structure underneath the file descriptor
@@ -2128,11 +2123,11 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
 	 * Also, we do not currently supported nested exclusive wakeups.
 	 */
-	if (ep_op_has_event(op) && (epds.events & EPOLLEXCLUSIVE)) {
+	if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) {
 		if (op == EPOLL_CTL_MOD)
 			goto error_tgt_fput;
 		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
-				(epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
+				(epds->events & ~EPOLLEXCLUSIVE_OK_BITS)))
 			goto error_tgt_fput;
 	}
 
@@ -2157,13 +2152,17 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * deep wakeup paths from forming in parallel through multiple
 	 * EPOLL_CTL_ADD operations.
 	 */
-	mutex_lock_nested(&ep->mtx, 0);
+	error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
+	if (error)
+		goto error_tgt_fput;
 	if (op == EPOLL_CTL_ADD) {
 		if (!list_empty(&f.file->f_ep_links) ||
 						is_file_epoll(tf.file)) {
-			full_check = 1;
 			mutex_unlock(&ep->mtx);
-			mutex_lock(&epmutex);
+			error = epoll_mutex_lock(&epmutex, 0, nonblock);
+			if (error)
+				goto error_tgt_fput;
+			full_check = 1;
 			if (is_file_epoll(tf.file)) {
 				error = -ELOOP;
 				if (ep_loop_check(ep, tf.file) != 0) {
@@ -2173,10 +2172,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 			} else
 				list_add(&tf.file->f_tfile_llink,
 							&tfile_check_list);
-			mutex_lock_nested(&ep->mtx, 0);
+			error = epoll_mutex_lock(&ep->mtx, 0, nonblock);
+			if (error) {
+out_del:
+				list_del(&tf.file->f_tfile_llink);
+				goto error_tgt_fput;
+			}
 			if (is_file_epoll(tf.file)) {
 				tep = tf.file->private_data;
-				mutex_lock_nested(&tep->mtx, 1);
+				error = epoll_mutex_lock(&tep->mtx, 1, nonblock);
+				if (error) {
+					mutex_unlock(&ep->mtx);
+					goto out_del;
+				}
 			}
 		}
 	}
@@ -2192,8 +2200,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	switch (op) {
 	case EPOLL_CTL_ADD:
 		if (!epi) {
-			epds.events |= EPOLLERR | EPOLLHUP;
-			error = ep_insert(ep, &epds, tf.file, fd, full_check);
+			epds->events |= EPOLLERR | EPOLLHUP;
+			error = ep_insert(ep, epds, tf.file, fd, full_check);
 		} else
 			error = -EEXIST;
 		if (full_check)
@@ -2208,8 +2216,8 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	case EPOLL_CTL_MOD:
 		if (epi) {
 			if (!(epi->event.events & EPOLLEXCLUSIVE)) {
-				epds.events |= EPOLLERR | EPOLLHUP;
-				error = ep_modify(ep, epi, &epds);
+				epds->events |= EPOLLERR | EPOLLHUP;
+				error = ep_modify(ep, epi, epds);
 			}
 		} else
 			error = -ENOENT;
@@ -2232,6 +2240,23 @@ error_return:
 }
 
 /*
+ * The following function implements the controller interface for
+ * the eventpoll file that enables the insertion/removal/change of
+ * file descriptors inside the interest set.
+ */
+SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
+		struct epoll_event __user *, event)
+{
+	struct epoll_event epds;
+
+	if (ep_op_has_event(op) &&
+	    copy_from_user(&epds, event, sizeof(struct epoll_event)))
+		return -EFAULT;
+
+	return do_epoll_ctl(epfd, op, fd, &epds, false);
+}
+
+/*
  * Implement the event wait interface for the eventpoll file. It is the kernel
  * part of the user space epoll_wait(2).
  */
diff --git a/fs/exec.c b/fs/exec.c
index 74d88dab98dd..db17be51b112 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -272,7 +272,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 		goto err;
 
 	mm->stack_vm = mm->total_vm = 1;
-	arch_bprm_mm_init(mm, vma);
 	up_write(&mm->mmap_sem);
 	bprm->p = vma->vm_end - sizeof(void *);
 	return 0;
@@ -761,6 +760,11 @@ int setup_arg_pages(struct linux_binprm *bprm,
 		goto out_unlock;
 	BUG_ON(prev != vma);
 
+	if (unlikely(vm_flags & VM_EXEC)) {
+		pr_warn_once("process '%pD4' started with executable stack\n",
+			     bprm->file);
+	}
+
 	/* Move stack pages down in memory. */
 	if (stack_shift) {
 		ret = shift_arg_pages(vma, stack_shift);
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index bcffe25da2f0..4a4ab683250d 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1073,9 +1073,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
 		goto cantfind_ext2;
- 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
- 				le32_to_cpu(es->s_first_data_block) - 1)
- 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
+				le32_to_cpu(es->s_first_data_block) - 1)
+					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
 	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
 		   EXT2_DESC_PER_BLOCK(sb);
 	sbi->s_group_desc = kmalloc_array (db_count,
@@ -1138,6 +1138,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 				ext2_count_dirs(sb), GFP_KERNEL);
 	}
 	if (err) {
+		ret = err;
 		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
 		goto failed_mount3;
 	}
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 2de970cfc33c..2a592e38cdfe 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -4,12 +4,7 @@
 # kernels after the removal of ext3 driver.
 config EXT3_FS
 	tristate "The Extended 3 (ext3) filesystem"
-	# These must match EXT4_FS selects...
 	select EXT4_FS
-	select JBD2
-	select CRC16
-	select CRYPTO
-	select CRYPTO_CRC32C
 	help
 	  This config option is here only for backward compatibility. ext3
 	  filesystem is now handled by the ext4 driver.
@@ -33,7 +28,6 @@ config EXT3_FS_SECURITY
 
 config EXT4_FS
 	tristate "The Extended 4 (ext4) filesystem"
-	# Please update EXT3_FS selects when changing these
 	select JBD2
 	select CRC16
 	select CRYPTO
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 0b202e00d93f..5f993a411251 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -371,7 +371,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 	if (buffer_verified(bh))
 		goto verified;
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
-			desc, bh))) {
+						    desc, bh) ||
+		     ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_CRC))) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
 		ext4_mark_group_bitmap_corrupted(sb, block_group,
@@ -505,7 +506,9 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 	if (!desc)
 		return -EFSCORRUPTED;
 	wait_on_buffer(bh);
+	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
 	if (!buffer_uptodate(bh)) {
+		ext4_set_errno(sb, EIO);
 		ext4_error(sb, "Cannot read block bitmap - "
 			   "block_group = %u, block_bitmap = %llu",
 			   block_group, (unsigned long long) bh->b_blocknr);
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 4e093277c8bf..1f340743c9a8 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -462,7 +462,6 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 	new_fn->name_len = ent_name->len;
 	new_fn->file_type = dirent->file_type;
 	memcpy(new_fn->name, ent_name->name, ent_name->len);
-	new_fn->name[ent_name->len] = 0;
 
 	while (*p) {
 		parent = *p;
@@ -672,9 +671,11 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
 			  const char *str, const struct qstr *name)
 {
 	struct qstr qstr = {.name = str, .len = len };
-	struct inode *inode = dentry->d_parent->d_inode;
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
 
-	if (!IS_CASEFOLDED(inode) || !EXT4_SB(inode->i_sb)->s_encoding) {
+	if (!inode || !IS_CASEFOLDED(inode) ||
+	    !EXT4_SB(inode->i_sb)->s_encoding) {
 		if (len != name->len)
 			return -1;
 		return memcmp(str, name->name, len);
@@ -687,10 +688,11 @@ static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
 {
 	const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
 	const struct unicode_map *um = sbi->s_encoding;
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
 	unsigned char *norm;
 	int len, ret = 0;
 
-	if (!IS_CASEFOLDED(dentry->d_inode) || !um)
+	if (!inode || !IS_CASEFOLDED(inode) || !um)
 		return 0;
 
 	norm = kmalloc(PATH_MAX, GFP_ATOMIC);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f8578caba40d..9a2ee2428ecc 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1052,8 +1052,6 @@ struct ext4_inode_info {
 	/* allocation reservation info for delalloc */
 	/* In case of bigalloc, this refer to clusters rather than blocks */
 	unsigned int i_reserved_data_blocks;
-	ext4_lblk_t i_da_metadata_calc_last_lblock;
-	int i_da_metadata_calc_len;
 
 	/* pending cluster reservations for bigalloc file systems */
 	struct ext4_pending_tree i_pending_tree;
@@ -1343,7 +1341,8 @@ struct ext4_super_block {
 	__u8	s_lastcheck_hi;
 	__u8	s_first_error_time_hi;
 	__u8	s_last_error_time_hi;
-	__u8	s_pad[2];
+	__u8	s_first_error_errcode;
+	__u8    s_last_error_errcode;
 	__le16  s_encoding;		/* Filename charset encoding */
 	__le16  s_encoding_flags;	/* Filename charset encoding flags */
 	__le32	s_reserved[95];		/* Padding to the end of the block */
@@ -1556,6 +1555,9 @@ struct ext4_sb_info {
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
 	struct dax_device *s_daxdev;
+#ifdef CONFIG_EXT4_DEBUG
+	unsigned long s_simulate_fail;
+#endif
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1575,6 +1577,66 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 }
 
 /*
+ * Simulate_fail codes
+ */
+#define EXT4_SIM_BBITMAP_EIO	1
+#define EXT4_SIM_BBITMAP_CRC	2
+#define EXT4_SIM_IBITMAP_EIO	3
+#define EXT4_SIM_IBITMAP_CRC	4
+#define EXT4_SIM_INODE_EIO	5
+#define EXT4_SIM_INODE_CRC	6
+#define EXT4_SIM_DIRBLOCK_EIO	7
+#define EXT4_SIM_DIRBLOCK_CRC	8
+
+static inline bool ext4_simulate_fail(struct super_block *sb,
+				     unsigned long code)
+{
+#ifdef CONFIG_EXT4_DEBUG
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (unlikely(sbi->s_simulate_fail == code)) {
+		sbi->s_simulate_fail = 0;
+		return true;
+	}
+#endif
+	return false;
+}
+
+static inline void ext4_simulate_fail_bh(struct super_block *sb,
+					 struct buffer_head *bh,
+					 unsigned long code)
+{
+	if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
+		clear_buffer_uptodate(bh);
+}
+
+/*
+ * Error number codes for s_{first,last}_error_errno
+ *
+ * Linux errno numbers are architecture specific, so we need to translate
+ * them into something which is architecture independent.   We don't define
+ * codes for all errno's; just the ones which are most likely to be the cause
+ * of an ext4_error() call.
+ */
+#define EXT4_ERR_UNKNOWN	 1
+#define EXT4_ERR_EIO		 2
+#define EXT4_ERR_ENOMEM		 3
+#define EXT4_ERR_EFSBADCRC	 4
+#define EXT4_ERR_EFSCORRUPTED	 5
+#define EXT4_ERR_ENOSPC		 6
+#define EXT4_ERR_ENOKEY		 7
+#define EXT4_ERR_EROFS		 8
+#define EXT4_ERR_EFBIG		 9
+#define EXT4_ERR_EEXIST		10
+#define EXT4_ERR_ERANGE		11
+#define EXT4_ERR_EOVERFLOW	12
+#define EXT4_ERR_EBUSY		13
+#define EXT4_ERR_ENOTDIR	14
+#define EXT4_ERR_ENOTEMPTY	15
+#define EXT4_ERR_ESHUTDOWN	16
+#define EXT4_ERR_EFAULT		17
+
+/*
  * Inode dynamic state flags
  */
 enum {
@@ -2628,7 +2690,6 @@ extern int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk,
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				struct ext4_map_blocks *map, int flags);
-extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
 extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
@@ -2679,8 +2740,6 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
 extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
 extern int ext4_calculate_overhead(struct super_block *sb);
 extern void ext4_superblock_csum_set(struct super_block *sb);
-extern void *ext4_kvmalloc(size_t size, gfp_t flags);
-extern void *ext4_kvzalloc(size_t size, gfp_t flags);
 extern int ext4_alloc_flex_bg_array(struct super_block *sb,
 				    ext4_group_t ngroup);
 extern const char *ext4_decode_error(struct super_block *sb, int errno,
@@ -2688,6 +2747,7 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno,
 extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 					     ext4_group_t block_group,
 					     unsigned int flags);
+extern void ext4_set_errno(struct super_block *sb, int err);
 
 extern __printf(4, 5)
 void __ext4_error(struct super_block *, const char *, unsigned int,
@@ -3254,7 +3314,6 @@ struct ext4_extent;
 #define EXT_MAX_BLOCKS	0xffffffff
 
 extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
-extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			       struct ext4_map_blocks *map, int flags);
@@ -3271,14 +3330,9 @@ extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
 					     ext4_io_end_t *io_end);
 extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map, int flags);
-extern int ext4_ext_calc_metadata_amount(struct inode *inode,
-					 ext4_lblk_t lblocks);
 extern int ext4_ext_calc_credits_for_single_extent(struct inode *inode,
 						   int num,
 						   struct ext4_ext_path *path);
-extern int ext4_can_extents_be_merged(struct inode *inode,
-				      struct ext4_extent *ex1,
-				      struct ext4_extent *ex2);
 extern int ext4_ext_insert_extent(handle_t *, struct inode *,
 				  struct ext4_ext_path **,
 				  struct ext4_extent *, int);
@@ -3294,8 +3348,6 @@ extern int ext4_get_es_cache(struct inode *inode,
 			     struct fiemap_extent_info *fieinfo,
 			     __u64 start, __u64 len);
 extern int ext4_ext_precache(struct inode *inode);
-extern int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
-extern int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
 extern int ext4_swap_extents(handle_t *handle, struct inode *inode1,
 				struct inode *inode2, ext4_lblk_t lblk1,
 			     ext4_lblk_t lblk2,  ext4_lblk_t count,
@@ -3390,6 +3442,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 }
 
 extern const struct iomap_ops ext4_iomap_ops;
+extern const struct iomap_ops ext4_iomap_overwrite_ops;
 extern const struct iomap_ops ext4_iomap_report_ops;
 
 static inline int ext4_buffer_uptodate(struct buffer_head *bh)
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 98bd0e9ee7df..1c216fcc202a 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -267,10 +267,5 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
 				     0xffff);
 }
 
-#define ext4_ext_dirty(handle, inode, path) \
-		__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
-int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
-		     struct inode *inode, struct ext4_ext_path *path);
-
 #endif /* _EXT4_EXTENTS */
 
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index d3b8cdea5df7..1f53d64e42a5 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -7,6 +7,28 @@
 
 #include <trace/events/ext4.h>
 
+int ext4_inode_journal_mode(struct inode *inode)
+{
+	if (EXT4_JOURNAL(inode) == NULL)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	/* We do not support data journalling with delayed allocation */
+	if (!S_ISREG(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))) {
+		/* We do not support data journalling for encrypted data */
+		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
+			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
+		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	}
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
+	BUG();
+}
+
 /* Just increment the non-pointer handle value */
 static handle_t *ext4_get_nojournal(void)
 {
@@ -58,6 +80,7 @@ static int ext4_journal_check_start(struct super_block *sb)
 	 * take the FS itself readonly cleanly.
 	 */
 	if (journal && is_journal_aborted(journal)) {
+		ext4_set_errno(sb, -journal->j_errno);
 		ext4_abort(sb, "Detected aborted journal");
 		return -EROFS;
 	}
@@ -249,6 +272,7 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
 	if (err) {
 		ext4_journal_abort_handle(where, line, __func__,
 					  bh, handle, err);
+		ext4_set_errno(inode->i_sb, -err);
 		__ext4_abort(inode->i_sb, where, line,
 			   "error %d when attempting revoke", err);
 	}
@@ -320,6 +344,7 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 				es = EXT4_SB(inode->i_sb)->s_es;
 				es->s_last_error_block =
 					cpu_to_le64(bh->b_blocknr);
+				ext4_set_errno(inode->i_sb, EIO);
 				ext4_error_inode(inode, where, line,
 						 bh->b_blocknr,
 					"IO error syncing itable block");
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a6b9b66dbfad..7ea4f6fa173b 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -463,27 +463,7 @@ int ext4_force_commit(struct super_block *sb);
 #define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
 #define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
 
-static inline int ext4_inode_journal_mode(struct inode *inode)
-{
-	if (EXT4_JOURNAL(inode) == NULL)
-		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	/* We do not support data journalling with delayed allocation */
-	if (!S_ISREG(inode->i_mode) ||
-	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
-	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
-	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
-	    !test_opt(inode->i_sb, DELALLOC))) {
-		/* We do not support data journalling for encrypted data */
-		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
-			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
-		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
-	}
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	BUG();
-}
+int ext4_inode_journal_mode(struct inode *inode);
 
 static inline int ext4_should_journal_data(struct inode *inode)
 {
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0e8708b77da6..954013d6076b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -161,8 +161,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode,
  *  - ENOMEM
  *  - EIO
  */
-int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
-		     struct inode *inode, struct ext4_ext_path *path)
+static int __ext4_ext_dirty(const char *where, unsigned int line,
+			    handle_t *handle, struct inode *inode,
+			    struct ext4_ext_path *path)
 {
 	int err;
 
@@ -179,6 +180,9 @@ int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle,
 	return err;
 }
 
+#define ext4_ext_dirty(handle, inode, path) \
+		__ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path))
+
 static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode,
 			      struct ext4_ext_path *path,
 			      ext4_lblk_t block)
@@ -309,53 +313,6 @@ ext4_force_split_extent_at(handle_t *handle, struct inode *inode,
 			(nofail ? EXT4_GET_BLOCKS_METADATA_NOFAIL:0));
 }
 
-/*
- * Calculate the number of metadata blocks needed
- * to allocate @blocks
- * Worse case is one block per extent
- */
-int ext4_ext_calc_metadata_amount(struct inode *inode, ext4_lblk_t lblock)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	int idxs;
-
-	idxs = ((inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header))
-		/ sizeof(struct ext4_extent_idx));
-
-	/*
-	 * If the new delayed allocation block is contiguous with the
-	 * previous da block, it can share index blocks with the
-	 * previous block, so we only need to allocate a new index
-	 * block every idxs leaf blocks.  At ldxs**2 blocks, we need
-	 * an additional index block, and at ldxs**3 blocks, yet
-	 * another index blocks.
-	 */
-	if (ei->i_da_metadata_calc_len &&
-	    ei->i_da_metadata_calc_last_lblock+1 == lblock) {
-		int num = 0;
-
-		if ((ei->i_da_metadata_calc_len % idxs) == 0)
-			num++;
-		if ((ei->i_da_metadata_calc_len % (idxs*idxs)) == 0)
-			num++;
-		if ((ei->i_da_metadata_calc_len % (idxs*idxs*idxs)) == 0) {
-			num++;
-			ei->i_da_metadata_calc_len = 0;
-		} else
-			ei->i_da_metadata_calc_len++;
-		ei->i_da_metadata_calc_last_lblock++;
-		return num;
-	}
-
-	/*
-	 * In the worst case we need a new set of index blocks at
-	 * every level of the inode's extent tree.
-	 */
-	ei->i_da_metadata_calc_len = 1;
-	ei->i_da_metadata_calc_last_lblock = lblock;
-	return ext_depth(inode) + 1;
-}
-
 static int
 ext4_ext_max_entries(struct inode *inode, int depth)
 {
@@ -492,6 +449,7 @@ static int __ext4_ext_check(const char *function, unsigned int line,
 	return 0;
 
 corrupted:
+	ext4_set_errno(inode->i_sb, -err);
 	ext4_error_inode(inode, function, line, 0,
 			 "pblk %llu bad header/extent: %s - magic %x, "
 			 "entries %u, max %u(%u), depth %u(%u)",
@@ -510,6 +468,30 @@ int ext4_ext_check_inode(struct inode *inode)
 	return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
 }
 
+static void ext4_cache_extents(struct inode *inode,
+			       struct ext4_extent_header *eh)
+{
+	struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+	ext4_lblk_t prev = 0;
+	int i;
+
+	for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+		unsigned int status = EXTENT_STATUS_WRITTEN;
+		ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+		int len = ext4_ext_get_actual_len(ex);
+
+		if (prev && (prev != lblk))
+			ext4_es_cache_extent(inode, prev, lblk - prev, ~0,
+					     EXTENT_STATUS_HOLE);
+
+		if (ext4_ext_is_unwritten(ex))
+			status = EXTENT_STATUS_UNWRITTEN;
+		ext4_es_cache_extent(inode, lblk, len,
+				     ext4_ext_pblock(ex), status);
+		prev = lblk + len;
+	}
+}
+
 static struct buffer_head *
 __read_extent_tree_block(const char *function, unsigned int line,
 			 struct inode *inode, ext4_fsblk_t pblk, int depth,
@@ -544,26 +526,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
 	 */
 	if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
 		struct ext4_extent_header *eh = ext_block_hdr(bh);
-		struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
-		ext4_lblk_t prev = 0;
-		int i;
-
-		for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
-			unsigned int status = EXTENT_STATUS_WRITTEN;
-			ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
-			int len = ext4_ext_get_actual_len(ex);
-
-			if (prev && (prev != lblk))
-				ext4_es_cache_extent(inode, prev,
-						     lblk - prev, ~0,
-						     EXTENT_STATUS_HOLE);
-
-			if (ext4_ext_is_unwritten(ex))
-				status = EXTENT_STATUS_UNWRITTEN;
-			ext4_es_cache_extent(inode, lblk, len,
-					     ext4_ext_pblock(ex), status);
-			prev = lblk + len;
-		}
+		ext4_cache_extents(inode, eh);
 	}
 	return bh;
 errout:
@@ -649,8 +612,9 @@ static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
 	ext_debug("path:");
 	for (k = 0; k <= l; k++, path++) {
 		if (path->p_idx) {
-		  ext_debug("  %d->%llu", le32_to_cpu(path->p_idx->ei_block),
-			    ext4_idx_pblock(path->p_idx));
+			ext_debug("  %d->%llu",
+				  le32_to_cpu(path->p_idx->ei_block),
+				  ext4_idx_pblock(path->p_idx));
 		} else if (path->p_ext) {
 			ext_debug("  %d:[%d]%d:%llu ",
 				  le32_to_cpu(path->p_ext->ee_block),
@@ -731,11 +695,12 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path)
 	if (!path)
 		return;
 	depth = path->p_depth;
-	for (i = 0; i <= depth; i++, path++)
+	for (i = 0; i <= depth; i++, path++) {
 		if (path->p_bh) {
 			brelse(path->p_bh);
 			path->p_bh = NULL;
 		}
+	}
 }
 
 /*
@@ -777,8 +742,8 @@ ext4_ext_binsearch_idx(struct inode *inode,
 
 		chix = ix = EXT_FIRST_INDEX(eh);
 		for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) {
-		  if (k != 0 &&
-		      le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) {
+			if (k != 0 && le32_to_cpu(ix->ei_block) <=
+			    le32_to_cpu(ix[-1].ei_block)) {
 				printk(KERN_DEBUG "k=%d, ix=0x%p, "
 				       "first=0x%p\n", k,
 				       ix, EXT_FIRST_INDEX(eh));
@@ -911,6 +876,8 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
 	path[0].p_bh = NULL;
 
 	i = depth;
+	if (!(flags & EXT4_EX_NOCACHE) && depth == 0)
+		ext4_cache_extents(inode, eh);
 	/* walk through the tree */
 	while (i) {
 		ext_debug("depth %d: num %d, max %d\n",
@@ -1632,17 +1599,16 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path)
 		return EXT_MAX_BLOCKS;
 
 	while (depth >= 0) {
+		struct ext4_ext_path *p = &path[depth];
+
 		if (depth == path->p_depth) {
 			/* leaf */
-			if (path[depth].p_ext &&
-				path[depth].p_ext !=
-					EXT_LAST_EXTENT(path[depth].p_hdr))
-			  return le32_to_cpu(path[depth].p_ext[1].ee_block);
+			if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr))
+				return le32_to_cpu(p->p_ext[1].ee_block);
 		} else {
 			/* index */
-			if (path[depth].p_idx !=
-					EXT_LAST_INDEX(path[depth].p_hdr))
-			  return le32_to_cpu(path[depth].p_idx[1].ei_block);
+			if (p->p_idx != EXT_LAST_INDEX(p->p_hdr))
+				return le32_to_cpu(p->p_idx[1].ei_block);
 		}
 		depth--;
 	}
@@ -1742,9 +1708,9 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode,
 	return err;
 }
 
-int
-ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
-				struct ext4_extent *ex2)
+static int ext4_can_extents_be_merged(struct inode *inode,
+				      struct ext4_extent *ex1,
+				      struct ext4_extent *ex2)
 {
 	unsigned short ext1_ee_len, ext2_ee_len;
 
@@ -1758,11 +1724,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 			le32_to_cpu(ex2->ee_block))
 		return 0;
 
-	/*
-	 * To allow future support for preallocated extents to be added
-	 * as an RO_COMPAT feature, refuse to merge to extents if
-	 * this can result in the top bit of ee_len being set.
-	 */
 	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
 		return 0;
 
@@ -1870,13 +1831,14 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
 }
 
 /*
- * This function tries to merge the @ex extent to neighbours in the tree.
- * return 1 if merge left else 0.
+ * This function tries to merge the @ex extent to neighbours in the tree, then
+ * tries to collapse the extent tree into the inode.
  */
 static void ext4_ext_try_to_merge(handle_t *handle,
 				  struct inode *inode,
 				  struct ext4_ext_path *path,
-				  struct ext4_extent *ex) {
+				  struct ext4_extent *ex)
+{
 	struct ext4_extent_header *eh;
 	unsigned int depth;
 	int merge_done = 0;
@@ -3718,9 +3680,6 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		max_zeroout = sbi->s_extent_max_zeroout_kb >>
 			(inode->i_sb->s_blocksize_bits - 10);
 
-	if (IS_ENCRYPTED(inode))
-		max_zeroout = 0;
-
 	/*
 	 * five cases:
 	 * 1. split the extent into three extents.
@@ -4706,6 +4665,10 @@ retry:
 	return ret > 0 ? ret2 : ret;
 }
 
+static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len);
+
+static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len);
+
 static long ext4_zero_range(struct file *file, loff_t offset,
 			    loff_t len, int mode)
 {
@@ -4723,9 +4686,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	trace_ext4_zero_range(inode, offset, len, mode);
 
-	if (!S_ISREG(inode->i_mode))
-		return -EINVAL;
-
 	/* Call ext4_force_commit to flush all data in case of data=journal. */
 	if (ext4_should_journal_data(inode)) {
 		ret = ext4_force_commit(inode->i_sb);
@@ -4765,7 +4725,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-	    (offset + len > i_size_read(inode) ||
+	    (offset + len > inode->i_size ||
 	     offset + len > EXT4_I(inode)->i_disksize)) {
 		new_size = offset + len;
 		ret = inode_newsize_ok(inode, new_size);
@@ -4849,7 +4809,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		* Mark that we allocate beyond EOF so the subsequent truncate
 		* can proceed even if the new size is the same as i_size.
 		*/
-		if ((offset + len) > i_size_read(inode))
+		if (offset + len > inode->i_size)
 			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
 	ext4_mark_inode_dirty(handle, inode);
@@ -4890,14 +4850,9 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	 * range since we would need to re-encrypt blocks with a
 	 * different IV or XTS tweak (which are based on the logical
 	 * block number).
-	 *
-	 * XXX It's not clear why zero range isn't working, but we'll
-	 * leave it disabled for encrypted inodes for now.  This is a
-	 * bug we should fix....
 	 */
 	if (IS_ENCRYPTED(inode) &&
-	    (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE |
-		     FALLOC_FL_ZERO_RANGE)))
+	    (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
 		return -EOPNOTSUPP;
 
 	/* Return error if mode is not supported */
@@ -4941,7 +4896,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	}
 
 	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
-	    (offset + len > i_size_read(inode) ||
+	    (offset + len > inode->i_size ||
 	     offset + len > EXT4_I(inode)->i_disksize)) {
 		new_size = offset + len;
 		ret = inode_newsize_ok(inode, new_size);
@@ -5268,7 +5223,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
 {
 	int depth, err = 0;
 	struct ext4_extent *ex_start, *ex_last;
-	bool update = 0;
+	bool update = false;
 	depth = path->p_depth;
 
 	while (depth >= 0) {
@@ -5284,7 +5239,7 @@ ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
 				goto out;
 
 			if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
-				update = 1;
+				update = true;
 
 			while (ex_start <= ex_last) {
 				if (SHIFT == SHIFT_LEFT) {
@@ -5472,7 +5427,7 @@ out:
  * This implements the fallocate's collapse range functionality for ext4
  * Returns: 0 and non-zero on error.
  */
-int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
 	ext4_lblk_t punch_start, punch_stop;
@@ -5489,12 +5444,8 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		return -EOPNOTSUPP;
 
-	/* Collapse range works only on fs block size aligned offsets. */
-	if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
-	    len & (EXT4_CLUSTER_SIZE(sb) - 1))
-		return -EINVAL;
-
-	if (!S_ISREG(inode->i_mode))
+	/* Collapse range works only on fs cluster size aligned regions. */
+	if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
 		return -EINVAL;
 
 	trace_ext4_collapse_range(inode, offset, len);
@@ -5514,7 +5465,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * There is no need to overlap collapse range with EOF, in which case
 	 * it is effectively a truncate operation
 	 */
-	if (offset + len >= i_size_read(inode)) {
+	if (offset + len >= inode->i_size) {
 		ret = -EINVAL;
 		goto out_mutex;
 	}
@@ -5592,7 +5543,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_stop;
 	}
 
-	new_size = i_size_read(inode) - len;
+	new_size = inode->i_size - len;
 	i_size_write(inode, new_size);
 	EXT4_I(inode)->i_disksize = new_size;
 
@@ -5620,7 +5571,7 @@ out_mutex:
  * by len bytes.
  * Returns 0 on success, error otherwise.
  */
-int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
+static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 {
 	struct super_block *sb = inode->i_sb;
 	handle_t *handle;
@@ -5639,14 +5590,10 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		return -EOPNOTSUPP;
 
-	/* Insert range works only on fs block size aligned offsets. */
-	if (offset & (EXT4_CLUSTER_SIZE(sb) - 1) ||
-			len & (EXT4_CLUSTER_SIZE(sb) - 1))
+	/* Insert range works only on fs cluster size aligned regions. */
+	if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb)))
 		return -EINVAL;
 
-	if (!S_ISREG(inode->i_mode))
-		return -EOPNOTSUPP;
-
 	trace_ext4_insert_range(inode, offset, len);
 
 	offset_lblk = offset >> EXT4_BLOCK_SIZE_BITS(sb);
@@ -5666,14 +5613,14 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 		goto out_mutex;
 	}
 
-	/* Check for wrap through zero */
-	if (inode->i_size + len > inode->i_sb->s_maxbytes) {
+	/* Check whether the maximum file size would be exceeded */
+	if (len > inode->i_sb->s_maxbytes - inode->i_size) {
 		ret = -EFBIG;
 		goto out_mutex;
 	}
 
-	/* Offset should be less than i_size */
-	if (offset >= i_size_read(inode)) {
+	/* Offset must be less than i_size */
+	if (offset >= inode->i_size) {
 		ret = -EINVAL;
 		goto out_mutex;
 	}
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 825313c59752..4ec30a798260 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -209,6 +209,12 @@ static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
 	return es->es_pblk & ~ES_MASK;
 }
 
+static inline ext4_fsblk_t ext4_es_show_pblock(struct extent_status *es)
+{
+	ext4_fsblk_t pblock = ext4_es_pblock(es);
+	return pblock == ~ES_MASK ? 0 : pblock;
+}
+
 static inline void ext4_es_store_pblock(struct extent_status *es,
 					ext4_fsblk_t pb)
 {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6a7293a5cda2..5f225881176b 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -88,9 +88,10 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	if (!inode_trylock_shared(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock_shared(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock_shared(inode);
 	}
 	/*
@@ -165,19 +166,25 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
  * threads are at work on the same unwritten block, they must be synchronized
  * or one thread will zero the other's data, causing corruption.
  */
-static int
-ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
+static bool
+ext4_unaligned_io(struct inode *inode, struct iov_iter *from, loff_t pos)
 {
 	struct super_block *sb = inode->i_sb;
-	int blockmask = sb->s_blocksize - 1;
-
-	if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize))
-		return 0;
+	unsigned long blockmask = sb->s_blocksize - 1;
 
 	if ((pos | iov_iter_alignment(from)) & blockmask)
-		return 1;
+		return true;
 
-	return 0;
+	return false;
+}
+
+static bool
+ext4_extending_io(struct inode *inode, loff_t offset, size_t len)
+{
+	if (offset + len > i_size_read(inode) ||
+	    offset + len > EXT4_I(inode)->i_disksize)
+		return true;
+	return false;
 }
 
 /* Is IO overwriting allocated and initialized blocks? */
@@ -203,7 +210,8 @@ static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
 	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
 }
 
-static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+static ssize_t ext4_generic_write_checks(struct kiocb *iocb,
+					 struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
@@ -227,11 +235,21 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
 		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
 	}
 
+	return iov_iter_count(from);
+}
+
+static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	ssize_t ret, count;
+
+	count = ext4_generic_write_checks(iocb, from);
+	if (count <= 0)
+		return count;
+
 	ret = file_modified(iocb->ki_filp);
 	if (ret)
 		return ret;
-
-	return iov_iter_count(from);
+	return count;
 }
 
 static ssize_t ext4_buffered_write_iter(struct kiocb *iocb,
@@ -363,62 +381,137 @@ static const struct iomap_dio_ops ext4_dio_write_ops = {
 	.end_io = ext4_dio_write_end_io,
 };
 
+/*
+ * The intention here is to start with shared lock acquired then see if any
+ * condition requires an exclusive inode lock. If yes, then we restart the
+ * whole operation by releasing the shared lock and acquiring exclusive lock.
+ *
+ * - For unaligned_io we never take shared lock as it may cause data corruption
+ *   when two unaligned IO tries to modify the same block e.g. while zeroing.
+ *
+ * - For extending writes case we don't take the shared lock, since it requires
+ *   updating inode i_disksize and/or orphan handling with exclusive lock.
+ *
+ * - shared locking will only be true mostly with overwrites. Otherwise we will
+ *   switch to exclusive i_rwsem lock.
+ */
+static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
+				     bool *ilock_shared, bool *extend)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	loff_t offset;
+	size_t count;
+	ssize_t ret;
+
+restart:
+	ret = ext4_generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	offset = iocb->ki_pos;
+	count = ret;
+	if (ext4_extending_io(inode, offset, count))
+		*extend = true;
+	/*
+	 * Determine whether the IO operation will overwrite allocated
+	 * and initialized blocks.
+	 * We need exclusive i_rwsem for changing security info
+	 * in file_modified().
+	 */
+	if (*ilock_shared && (!IS_NOSEC(inode) || *extend ||
+	     !ext4_overwrite_io(inode, offset, count))) {
+		inode_unlock_shared(inode);
+		*ilock_shared = false;
+		inode_lock(inode);
+		goto restart;
+	}
+
+	ret = file_modified(file);
+	if (ret < 0)
+		goto out;
+
+	return count;
+out:
+	if (*ilock_shared)
+		inode_unlock_shared(inode);
+	else
+		inode_unlock(inode);
+	return ret;
+}
+
 static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	ssize_t ret;
-	size_t count;
-	loff_t offset;
 	handle_t *handle;
 	struct inode *inode = file_inode(iocb->ki_filp);
-	bool extend = false, overwrite = false, unaligned_aio = false;
+	loff_t offset = iocb->ki_pos;
+	size_t count = iov_iter_count(from);
+	const struct iomap_ops *iomap_ops = &ext4_iomap_ops;
+	bool extend = false, unaligned_io = false;
+	bool ilock_shared = true;
+
+	/*
+	 * We initially start with shared inode lock unless it is
+	 * unaligned IO which needs exclusive lock anyways.
+	 */
+	if (ext4_unaligned_io(inode, from, offset)) {
+		unaligned_io = true;
+		ilock_shared = false;
+	}
+	/*
+	 * Quick check here without any i_rwsem lock to see if it is extending
+	 * IO. A more reliable check is done in ext4_dio_write_checks() with
+	 * proper locking in place.
+	 */
+	if (offset + count > i_size_read(inode))
+		ilock_shared = false;
 
 	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (!inode_trylock(inode))
-			return -EAGAIN;
+		if (ilock_shared) {
+			if (!inode_trylock_shared(inode))
+				return -EAGAIN;
+		} else {
+			if (!inode_trylock(inode))
+				return -EAGAIN;
+		}
 	} else {
-		inode_lock(inode);
+		if (ilock_shared)
+			inode_lock_shared(inode);
+		else
+			inode_lock(inode);
 	}
 
+	/* Fallback to buffered I/O if the inode does not support direct I/O. */
 	if (!ext4_dio_supported(inode)) {
-		inode_unlock(inode);
-		/*
-		 * Fallback to buffered I/O if the inode does not support
-		 * direct I/O.
-		 */
+		if (ilock_shared)
+			inode_unlock_shared(inode);
+		else
+			inode_unlock(inode);
 		return ext4_buffered_write_iter(iocb, from);
 	}
 
-	ret = ext4_write_checks(iocb, from);
-	if (ret <= 0) {
-		inode_unlock(inode);
+	ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend);
+	if (ret <= 0)
 		return ret;
-	}
 
-	/*
-	 * Unaligned asynchronous direct I/O must be serialized among each
-	 * other as the zeroing of partial blocks of two competing unaligned
-	 * asynchronous direct I/O writes can result in data corruption.
-	 */
 	offset = iocb->ki_pos;
-	count = iov_iter_count(from);
-	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
-	    !is_sync_kiocb(iocb) && ext4_unaligned_aio(inode, from, offset)) {
-		unaligned_aio = true;
-		inode_dio_wait(inode);
-	}
+	count = ret;
 
 	/*
-	 * Determine whether the I/O will overwrite allocated and initialized
-	 * blocks. If so, check to see whether it is possible to take the
-	 * dioread_nolock path.
+	 * Unaligned direct IO must be serialized among each other as zeroing
+	 * of partial blocks of two competing unaligned IOs can result in data
+	 * corruption.
+	 *
+	 * So we make sure we don't allow any unaligned IO in flight.
+	 * For IOs where we need not wait (like unaligned non-AIO DIO),
+	 * below inode_dio_wait() may anyway become a no-op, since we start
+	 * with exclusive lock.
 	 */
-	if (!unaligned_aio && ext4_overwrite_io(inode, offset, count) &&
-	    ext4_should_dioread_nolock(inode)) {
-		overwrite = true;
-		downgrade_write(&inode->i_rwsem);
-	}
+	if (unaligned_io)
+		inode_dio_wait(inode);
 
-	if (offset + count > EXT4_I(inode)->i_disksize) {
+	if (extend) {
 		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
@@ -431,18 +524,19 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 			goto out;
 		}
 
-		extend = true;
 		ext4_journal_stop(handle);
 	}
 
-	ret = iomap_dio_rw(iocb, from, &ext4_iomap_ops, &ext4_dio_write_ops,
-			   is_sync_kiocb(iocb) || unaligned_aio || extend);
+	if (ilock_shared)
+		iomap_ops = &ext4_iomap_overwrite_ops;
+	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
+			   is_sync_kiocb(iocb) || unaligned_io || extend);
 
 	if (extend)
 		ret = ext4_handle_inode_extension(inode, offset, ret, count);
 
 out:
-	if (overwrite)
+	if (ilock_shared)
 		inode_unlock_shared(inode);
 	else
 		inode_unlock(inode);
@@ -487,9 +581,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	bool extend = false;
 	struct inode *inode = file_inode(iocb->ki_filp);
 
-	if (!inode_trylock(inode)) {
-		if (iocb->ki_flags & IOCB_NOWAIT)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!inode_trylock(inode))
 			return -EAGAIN;
+	} else {
 		inode_lock(inode);
 	}
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 8ca4a23129aa..c66e8f9451a2 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -94,7 +94,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		goto verified;
 	blk = ext4_inode_bitmap(sb, desc);
 	if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
-					   EXT4_INODES_PER_GROUP(sb) / 8)) {
+					   EXT4_INODES_PER_GROUP(sb) / 8) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_CRC)) {
 		ext4_unlock_group(sb, block_group);
 		ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
 			   "inode_bitmap = %llu", block_group, blk);
@@ -192,8 +193,10 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	get_bh(bh);
 	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
 	wait_on_buffer(bh);
+	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO);
 	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
+		ext4_set_errno(sb, EIO);
 		ext4_error(sb, "Cannot read inode bitmap - "
 			   "block_group = %u, inode_bitmap = %llu",
 			   block_group, bitmap_blk);
@@ -1223,6 +1226,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
 	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		ext4_set_errno(sb, -err);
 		ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
 			   ino, err);
 		return inode;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 3a4ab70fe9e0..569fc68e8975 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -660,32 +660,6 @@ out:
 }
 
 /*
- * Calculate the number of metadata blocks need to reserve
- * to allocate a new block at @lblocks for non extent file based file
- */
-int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock)
-{
-	struct ext4_inode_info *ei = EXT4_I(inode);
-	sector_t dind_mask = ~((sector_t)EXT4_ADDR_PER_BLOCK(inode->i_sb) - 1);
-	int blk_bits;
-
-	if (lblock < EXT4_NDIR_BLOCKS)
-		return 0;
-
-	lblock -= EXT4_NDIR_BLOCKS;
-
-	if (ei->i_da_metadata_calc_len &&
-	    (lblock & dind_mask) == ei->i_da_metadata_calc_last_lblock) {
-		ei->i_da_metadata_calc_len++;
-		return 0;
-	}
-	ei->i_da_metadata_calc_last_lblock = lblock & dind_mask;
-	ei->i_da_metadata_calc_len = 1;
-	blk_bits = order_base_2(lblock);
-	return (blk_bits / EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb)) + 1;
-}
-
-/*
  * Calculate number of indirect blocks touched by mapping @nrblocks logically
  * contiguous blocks
  */
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 2fec62d764fa..fad82d08fca5 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -98,6 +98,7 @@ int ext4_get_max_inline_size(struct inode *inode)
 
 	error = ext4_get_inode_loc(inode, &iloc);
 	if (error) {
+		ext4_set_errno(inode->i_sb, -error);
 		ext4_error_inode(inode, __func__, __LINE__, 0,
 				 "can't get inode location %lu",
 				 inode->i_ino);
@@ -849,7 +850,7 @@ out:
 
 /*
  * Prepare the write for the inline data.
- * If the the data can be written into the inode, we just read
+ * If the data can be written into the inode, we just read
  * the page and make it uptodate, and start the journal.
  * Otherwise read the page, makes it dirty so that it can be
  * handle in writepages(the i_disksize update is left to the
@@ -1761,6 +1762,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data)
 
 	err = ext4_get_inode_loc(dir, &iloc);
 	if (err) {
+		ext4_set_errno(dir->i_sb, -err);
 		EXT4_ERROR_INODE(dir, "error %d getting inode %lu block",
 				 err, dir->i_ino);
 		return true;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 629a25d999f0..3313168b680f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -48,8 +48,6 @@
 
 #include <trace/events/ext4.h>
 
-#define MPAGE_DA_EXTENT_TAIL 0x01
-
 static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
 			      struct ext4_inode_info *ei)
 {
@@ -271,6 +269,7 @@ void ext4_evict_inode(struct inode *inode)
 	if (inode->i_blocks) {
 		err = ext4_truncate(inode);
 		if (err) {
+			ext4_set_errno(inode->i_sb, -err);
 			ext4_error(inode->i_sb,
 				   "couldn't truncate inode %lu (err %d)",
 				   inode->i_ino, err);
@@ -402,7 +401,7 @@ int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk,
 {
 	int ret;
 
-	if (IS_ENCRYPTED(inode))
+	if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
 		return fscrypt_zeroout_range(inode, lblk, pblk, len);
 
 	ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
@@ -2478,10 +2477,12 @@ update_disksize:
 			EXT4_I(inode)->i_disksize = disksize;
 		up_write(&EXT4_I(inode)->i_data_sem);
 		err2 = ext4_mark_inode_dirty(handle, inode);
-		if (err2)
+		if (err2) {
+			ext4_set_errno(inode->i_sb, -err2);
 			ext4_error(inode->i_sb,
 				   "Failed to mark inode %lu dirty",
 				   inode->i_ino);
+		}
 		if (!err)
 			err = err2;
 	}
@@ -3448,6 +3449,22 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	return 0;
 }
 
+static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
+		loff_t length, unsigned flags, struct iomap *iomap,
+		struct iomap *srcmap)
+{
+	int ret;
+
+	/*
+	 * Even for writes we don't need to allocate blocks, so just pretend
+	 * we are reading to save overhead of starting a transaction.
+	 */
+	flags &= ~IOMAP_WRITE;
+	ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
+	WARN_ON_ONCE(iomap->type != IOMAP_MAPPED);
+	return ret;
+}
+
 static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 			  ssize_t written, unsigned flags, struct iomap *iomap)
 {
@@ -3469,6 +3486,11 @@ const struct iomap_ops ext4_iomap_ops = {
 	.iomap_end		= ext4_iomap_end,
 };
 
+const struct iomap_ops ext4_iomap_overwrite_ops = {
+	.iomap_begin		= ext4_iomap_overwrite_begin,
+	.iomap_end		= ext4_iomap_end,
+};
+
 static bool ext4_iomap_is_delalloc(struct inode *inode,
 				   struct ext4_map_blocks *map)
 {
@@ -3701,8 +3723,12 @@ static int __ext4_block_zero_page_range(handle_t *handle,
 		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) {
 			/* We expect the key to be set. */
 			BUG_ON(!fscrypt_has_encryption_key(inode));
-			WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks(
-					page, blocksize, bh_offset(bh)));
+			err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+							       bh_offset(bh));
+			if (err) {
+				clear_buffer_uptodate(bh);
+				goto unlock;
+			}
 		}
 	}
 	if (ext4_should_journal_data(inode)) {
@@ -3912,9 +3938,6 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	unsigned int credits;
 	int ret = 0;
 
-	if (!S_ISREG(inode->i_mode))
-		return -EOPNOTSUPP;
-
 	trace_ext4_punch_hole(inode, offset, length, 0);
 
 	ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
@@ -4240,6 +4263,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	bh = sb_getblk(sb, block);
 	if (unlikely(!bh))
 		return -ENOMEM;
+	if (ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO))
+		goto simulate_eio;
 	if (!buffer_uptodate(bh)) {
 		lock_buffer(bh);
 
@@ -4338,6 +4363,8 @@ make_io:
 		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
+		simulate_eio:
+			ext4_set_errno(inode->i_sb, EIO);
 			EXT4_ERROR_INODE_BLOCK(inode, block,
 					       "unable to read itable block");
 			brelse(bh);
@@ -4551,7 +4578,9 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 					      sizeof(gen));
 	}
 
-	if (!ext4_inode_csum_verify(inode, raw_inode, ei)) {
+	if (!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+	    ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) {
+		ext4_set_errno(inode->i_sb, EFSBADCRC);
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: checksum invalid");
 		ret = -EFSBADCRC;
@@ -5090,6 +5119,7 @@ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc)
 		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
 			sync_dirty_buffer(iloc.bh);
 		if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
+			ext4_set_errno(inode->i_sb, EIO);
 			EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
 					 "IO error syncing inode");
 			err = -EIO;
@@ -5368,7 +5398,8 @@ int ext4_getattr(const struct path *path, struct kstat *stat,
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int flags;
 
-	if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+	if ((request_mask & STATX_BTIME) &&
+	    EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
 		stat->result_mask |= STATX_BTIME;
 		stat->btime.tv_sec = ei->i_crtime.tv_sec;
 		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index e8870fff8224..a0ec750018dd 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1377,6 +1377,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_CLEAR_ES_CACHE:
 	case EXT4_IOC_GETSTATE:
 	case EXT4_IOC_GET_ES_CACHE:
+	case EXT4_IOC_FSGETXATTR:
+	case EXT4_IOC_FSSETXATTR:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a3e2767bdf2f..f64838187559 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3895,6 +3895,7 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 	bitmap_bh = ext4_read_block_bitmap(sb, group);
 	if (IS_ERR(bitmap_bh)) {
 		err = PTR_ERR(bitmap_bh);
+		ext4_set_errno(sb, -err);
 		ext4_error(sb, "Error %d reading block bitmap for %u",
 			   err, group);
 		return 0;
@@ -4063,6 +4064,7 @@ repeat:
 		err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
 					     GFP_NOFS|__GFP_NOFAIL);
 		if (err) {
+			ext4_set_errno(sb, -err);
 			ext4_error(sb, "Error %d loading buddy information for %u",
 				   err, group);
 			continue;
@@ -4071,6 +4073,7 @@ repeat:
 		bitmap_bh = ext4_read_block_bitmap(sb, group);
 		if (IS_ERR(bitmap_bh)) {
 			err = PTR_ERR(bitmap_bh);
+			ext4_set_errno(sb, -err);
 			ext4_error(sb, "Error %d reading block bitmap for %u",
 					err, group);
 			ext4_mb_unload_buddy(&e4b);
@@ -4325,6 +4328,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 		err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
 					     GFP_NOFS|__GFP_NOFAIL);
 		if (err) {
+			ext4_set_errno(sb, -err);
 			ext4_error(sb, "Error %d loading buddy information for %u",
 				   err, group);
 			continue;
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 2305b4374fd3..1c44b1a32001 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -173,8 +173,10 @@ static int kmmpd(void *data)
 		 * (s_mmp_update_interval * 60) seconds.
 		 */
 		if (retval) {
-			if ((failed_writes % 60) == 0)
+			if ((failed_writes % 60) == 0) {
+				ext4_set_errno(sb, -retval);
 				ext4_error(sb, "Error writing to MMP block");
+			}
 			failed_writes++;
 		}
 
@@ -205,6 +207,7 @@ static int kmmpd(void *data)
 
 			retval = read_mmp_block(sb, &bh_check, mmp_block);
 			if (retval) {
+				ext4_set_errno(sb, -retval);
 				ext4_error(sb, "error reading MMP data: %d",
 					   retval);
 				goto exit_thread;
@@ -218,6 +221,7 @@ static int kmmpd(void *data)
 					     "Error while updating MMP info. "
 					     "The filesystem seems to have been"
 					     " multiply mounted.");
+				ext4_set_errno(sb, EBUSY);
 				ext4_error(sb, "abort");
 				put_bh(bh_check);
 				retval = -EBUSY;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 1cb42d940784..129d2ebae00d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -109,7 +109,10 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 	struct ext4_dir_entry *dirent;
 	int is_dx_block = 0;
 
-	bh = ext4_bread(NULL, inode, block, 0);
+	if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO))
+		bh = ERR_PTR(-EIO);
+	else
+		bh = ext4_bread(NULL, inode, block, 0);
 	if (IS_ERR(bh)) {
 		__ext4_warning(inode->i_sb, func, line,
 			       "inode #%lu: lblock %lu: comm %s: "
@@ -153,9 +156,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 	 * caller is sure it should be an index block.
 	 */
 	if (is_dx_block && type == INDEX) {
-		if (ext4_dx_csum_verify(inode, dirent))
+		if (ext4_dx_csum_verify(inode, dirent) &&
+		    !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC))
 			set_buffer_verified(bh);
 		else {
+			ext4_set_errno(inode->i_sb, EFSBADCRC);
 			ext4_error_inode(inode, func, line, block,
 					 "Directory index failed checksum");
 			brelse(bh);
@@ -163,9 +168,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
 		}
 	}
 	if (!is_dx_block) {
-		if (ext4_dirblock_csum_verify(inode, bh))
+		if (ext4_dirblock_csum_verify(inode, bh) &&
+		    !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC))
 			set_buffer_verified(bh);
 		else {
+			ext4_set_errno(inode->i_sb, EFSBADCRC);
 			ext4_error_inode(inode, func, line, block,
 					 "Directory block failed checksum");
 			brelse(bh);
@@ -1002,7 +1009,6 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 	top = (struct ext4_dir_entry_2 *) ((char *) de +
 					   dir->i_sb->s_blocksize -
 					   EXT4_DIR_REC_LEN(0));
-#ifdef CONFIG_FS_ENCRYPTION
 	/* Check if the directory is encrypted */
 	if (IS_ENCRYPTED(dir)) {
 		err = fscrypt_get_encryption_info(dir);
@@ -1017,7 +1023,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 			return err;
 		}
 	}
-#endif
+
 	for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
 				bh->b_data, bh->b_size,
@@ -1065,9 +1071,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
 	}
 errout:
 	brelse(bh);
-#ifdef CONFIG_FS_ENCRYPTION
 	fscrypt_fname_free_buffer(&fname_crypto_str);
-#endif
 	return count;
 }
 
@@ -1527,6 +1531,7 @@ restart:
 			goto next;
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
+			ext4_set_errno(sb, EIO);
 			EXT4_ERROR_INODE(dir, "reading directory lblock %lu",
 					 (unsigned long) block);
 			brelse(bh);
@@ -1537,6 +1542,7 @@ restart:
 		    !is_dx_internal_node(dir, block,
 					 (struct ext4_dir_entry *)bh->b_data) &&
 		    !ext4_dirblock_csum_verify(dir, bh)) {
+			ext4_set_errno(sb, EFSBADCRC);
 			EXT4_ERROR_INODE(dir, "checksumming directory "
 					 "block %lu", (unsigned long)block);
 			brelse(bh);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 24aeedb8fc75..68b39e75446a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -512,17 +512,26 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		gfp_t gfp_flags = GFP_NOFS;
 		unsigned int enc_bytes = round_up(len, i_blocksize(inode));
 
+		/*
+		 * Since bounce page allocation uses a mempool, we can only use
+		 * a waiting mask (i.e. request guaranteed allocation) on the
+		 * first page of the bio.  Otherwise it can deadlock.
+		 */
+		if (io->io_bio)
+			gfp_flags = GFP_NOWAIT | __GFP_NOWARN;
 	retry_encrypt:
 		bounce_page = fscrypt_encrypt_pagecache_blocks(page, enc_bytes,
 							       0, gfp_flags);
 		if (IS_ERR(bounce_page)) {
 			ret = PTR_ERR(bounce_page);
-			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {
-				if (io->io_bio) {
+			if (ret == -ENOMEM &&
+			    (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) {
+				gfp_flags = GFP_NOFS;
+				if (io->io_bio)
 					ext4_io_submit(io);
-					congestion_wait(BLK_RW_ASYNC, HZ/50);
-				}
-				gfp_flags |= __GFP_NOFAIL;
+				else
+					gfp_flags |= __GFP_NOFAIL;
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
 				goto retry_encrypt;
 			}
 
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index fef7755300c3..c1769afbf799 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -57,6 +57,7 @@ enum bio_post_read_step {
 	STEP_INITIAL = 0,
 	STEP_DECRYPT,
 	STEP_VERITY,
+	STEP_MAX,
 };
 
 struct bio_post_read_ctx {
@@ -106,10 +107,22 @@ static void verity_work(struct work_struct *work)
 {
 	struct bio_post_read_ctx *ctx =
 		container_of(work, struct bio_post_read_ctx, work);
+	struct bio *bio = ctx->bio;
 
-	fsverity_verify_bio(ctx->bio);
+	/*
+	 * fsverity_verify_bio() may call readpages() again, and although verity
+	 * will be disabled for that, decryption may still be needed, causing
+	 * another bio_post_read_ctx to be allocated.  So to guarantee that
+	 * mempool_alloc() never deadlocks we must free the current ctx first.
+	 * This is safe because verity is the last post-read step.
+	 */
+	BUILD_BUG_ON(STEP_VERITY + 1 != STEP_MAX);
+	mempool_free(ctx, bio_post_read_ctx_pool);
+	bio->bi_private = NULL;
 
-	bio_post_read_processing(ctx);
+	fsverity_verify_bio(bio);
+
+	__read_end_io(bio);
 }
 
 static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
@@ -176,12 +189,11 @@ static inline bool ext4_need_verity(const struct inode *inode, pgoff_t idx)
 	       idx < DIV_ROUND_UP(inode->i_size, PAGE_SIZE);
 }
 
-static struct bio_post_read_ctx *get_bio_post_read_ctx(struct inode *inode,
-						       struct bio *bio,
-						       pgoff_t first_idx)
+static void ext4_set_bio_post_read_ctx(struct bio *bio,
+				       const struct inode *inode,
+				       pgoff_t first_idx)
 {
 	unsigned int post_read_steps = 0;
-	struct bio_post_read_ctx *ctx = NULL;
 
 	if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
 		post_read_steps |= 1 << STEP_DECRYPT;
@@ -190,14 +202,14 @@ static struct bio_post_read_ctx *get_bio_post_read_ctx(struct inode *inode,
 		post_read_steps |= 1 << STEP_VERITY;
 
 	if (post_read_steps) {
-		ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
-		if (!ctx)
-			return ERR_PTR(-ENOMEM);
+		/* Due to the mempool, this never fails. */
+		struct bio_post_read_ctx *ctx =
+			mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
+
 		ctx->bio = bio;
 		ctx->enabled_steps = post_read_steps;
 		bio->bi_private = ctx;
 	}
-	return ctx;
 }
 
 static inline loff_t ext4_readpage_limit(struct inode *inode)
@@ -358,24 +370,16 @@ int ext4_mpage_readpages(struct address_space *mapping,
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct bio_post_read_ctx *ctx;
-
 			/*
 			 * bio_alloc will _always_ be able to allocate a bio if
 			 * __GFP_DIRECT_RECLAIM is set, see bio_alloc_bioset().
 			 */
 			bio = bio_alloc(GFP_KERNEL,
 				min_t(int, nr_pages, BIO_MAX_PAGES));
-			ctx = get_bio_post_read_ctx(inode, bio, page->index);
-			if (IS_ERR(ctx)) {
-				bio_put(bio);
-				bio = NULL;
-				goto set_error_page;
-			}
+			ext4_set_bio_post_read_ctx(bio, inode, page->index);
 			bio_set_dev(bio, bdev);
 			bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
 			bio->bi_end_io = mpage_end_io;
-			bio->bi_private = ctx;
 			bio_set_op_attrs(bio, REQ_OP_READ,
 						is_readahead ? REQ_RAHEAD : 0);
 		}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index a8c0f2b5b6e1..86a2500ed292 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -824,9 +824,8 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	if (unlikely(err))
 		goto errout;
 
-	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
-				     sizeof(struct buffer_head *),
-				     GFP_NOFS);
+	n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
+				GFP_KERNEL);
 	if (!n_group_desc) {
 		err = -ENOMEM;
 		ext4_warning(sb, "not enough memory for %lu groups",
@@ -900,9 +899,8 @@ static int add_new_gdb_meta_bg(struct super_block *sb,
 	gdb_bh = ext4_sb_bread(sb, gdblock, 0);
 	if (IS_ERR(gdb_bh))
 		return PTR_ERR(gdb_bh);
-	n_group_desc = ext4_kvmalloc((gdb_num + 1) *
-				     sizeof(struct buffer_head *),
-				     GFP_NOFS);
+	n_group_desc = kvmalloc((gdb_num + 1) * sizeof(struct buffer_head *),
+				GFP_KERNEL);
 	if (!n_group_desc) {
 		brelse(gdb_bh);
 		err = -ENOMEM;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 2937a8873fe1..8434217549b3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -154,7 +154,7 @@ ext4_sb_bread(struct super_block *sb, sector_t block, int op_flags)
 
 	if (bh == NULL)
 		return ERR_PTR(-ENOMEM);
-	if (buffer_uptodate(bh))
+	if (ext4_buffer_uptodate(bh))
 		return bh;
 	ll_rw_block(REQ_OP_READ, REQ_META | op_flags, 1, &bh);
 	wait_on_buffer(bh);
@@ -204,26 +204,6 @@ void ext4_superblock_csum_set(struct super_block *sb)
 	es->s_checksum = ext4_superblock_csum(sb, es);
 }
 
-void *ext4_kvmalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kmalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags, PAGE_KERNEL);
-	return ret;
-}
-
-void *ext4_kvzalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kzalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
-	return ret;
-}
-
 ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
 			       struct ext4_group_desc *bg)
 {
@@ -367,6 +347,8 @@ static void __save_error_info(struct super_block *sb, const char *func,
 	ext4_update_tstamp(es, s_last_error_time);
 	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
 	es->s_last_error_line = cpu_to_le32(line);
+	if (es->s_last_error_errcode == 0)
+		es->s_last_error_errcode = EXT4_ERR_EFSCORRUPTED;
 	if (!es->s_first_error_time) {
 		es->s_first_error_time = es->s_last_error_time;
 		es->s_first_error_time_hi = es->s_last_error_time_hi;
@@ -375,6 +357,7 @@ static void __save_error_info(struct super_block *sb, const char *func,
 		es->s_first_error_line = cpu_to_le32(line);
 		es->s_first_error_ino = es->s_last_error_ino;
 		es->s_first_error_block = es->s_last_error_block;
+		es->s_first_error_errcode = es->s_last_error_errcode;
 	}
 	/*
 	 * Start the daily error reporting function if it hasn't been
@@ -631,6 +614,66 @@ const char *ext4_decode_error(struct super_block *sb, int errno,
 	return errstr;
 }
 
+void ext4_set_errno(struct super_block *sb, int err)
+{
+	if (err < 0)
+		err = -err;
+
+	switch (err) {
+	case EIO:
+		err = EXT4_ERR_EIO;
+		break;
+	case ENOMEM:
+		err = EXT4_ERR_ENOMEM;
+		break;
+	case EFSBADCRC:
+		err = EXT4_ERR_EFSBADCRC;
+		break;
+	case EFSCORRUPTED:
+		err = EXT4_ERR_EFSCORRUPTED;
+		break;
+	case ENOSPC:
+		err = EXT4_ERR_ENOSPC;
+		break;
+	case ENOKEY:
+		err = EXT4_ERR_ENOKEY;
+		break;
+	case EROFS:
+		err = EXT4_ERR_EROFS;
+		break;
+	case EFBIG:
+		err = EXT4_ERR_EFBIG;
+		break;
+	case EEXIST:
+		err = EXT4_ERR_EEXIST;
+		break;
+	case ERANGE:
+		err = EXT4_ERR_ERANGE;
+		break;
+	case EOVERFLOW:
+		err = EXT4_ERR_EOVERFLOW;
+		break;
+	case EBUSY:
+		err = EXT4_ERR_EBUSY;
+		break;
+	case ENOTDIR:
+		err = EXT4_ERR_ENOTDIR;
+		break;
+	case ENOTEMPTY:
+		err = EXT4_ERR_ENOTEMPTY;
+		break;
+	case ESHUTDOWN:
+		err = EXT4_ERR_ESHUTDOWN;
+		break;
+	case EFAULT:
+		err = EXT4_ERR_EFAULT;
+		break;
+	default:
+		err = EXT4_ERR_UNKNOWN;
+	}
+	EXT4_SB(sb)->s_es->s_last_error_errcode = err;
+}
+
 /* __ext4_std_error decodes expected errors from journaling functions
  * automatically and invokes the appropriate error response.  */
 
@@ -655,6 +698,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 		       sb->s_id, function, line, errstr);
 	}
 
+	ext4_set_errno(sb, -errno);
 	save_error_info(sb, function, line);
 	ext4_handle_error(sb);
 }
@@ -982,8 +1026,10 @@ static void ext4_put_super(struct super_block *sb)
 		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
-		if ((err < 0) && !aborted)
+		if ((err < 0) && !aborted) {
+			ext4_set_errno(sb, -err);
 			ext4_abort(sb, "Couldn't clean up the journal");
+		}
 	}
 
 	ext4_unregister_sysfs(sb);
@@ -1085,8 +1131,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	ei->i_es_shk_nr = 0;
 	ei->i_es_shrink_lblk = 0;
 	ei->i_reserved_data_blocks = 0;
-	ei->i_da_metadata_calc_len = 0;
-	ei->i_da_metadata_calc_last_lblock = 0;
 	spin_lock_init(&(ei->i_block_reservation_lock));
 	ext4_init_pending_tree(&ei->i_pending_tree);
 #ifdef CONFIG_QUOTA
@@ -1548,6 +1592,7 @@ static const match_table_t tokens = {
 	{Opt_auto_da_alloc, "auto_da_alloc"},
 	{Opt_noauto_da_alloc, "noauto_da_alloc"},
 	{Opt_dioread_nolock, "dioread_nolock"},
+	{Opt_dioread_lock, "nodioread_nolock"},
 	{Opt_dioread_lock, "dioread_lock"},
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
@@ -3720,6 +3765,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		set_opt(sb, NO_UID32);
 	/* xattr user namespace & acls are now defaulted on */
 	set_opt(sb, XATTR_USER);
+	set_opt(sb, DIOREAD_NOLOCK);
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
@@ -3887,9 +3933,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 #endif
 
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
-		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
-			    "with data=journal disables delayed "
-			    "allocation and O_DIRECT support!\n");
+		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n");
+		clear_opt(sb, DIOREAD_NOLOCK);
 		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and delalloc");
@@ -5540,9 +5585,15 @@ static int ext4_statfs_project(struct super_block *sb,
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = (dquot->dq_dqb.dqb_bsoftlimit ?
-		 dquot->dq_dqb.dqb_bsoftlimit :
-		 dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+	limit = 0;
+	if (dquot->dq_dqb.dqb_bsoftlimit &&
+	    (!limit || dquot->dq_dqb.dqb_bsoftlimit < limit))
+		limit = dquot->dq_dqb.dqb_bsoftlimit;
+	if (dquot->dq_dqb.dqb_bhardlimit &&
+	    (!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
+		limit = dquot->dq_dqb.dqb_bhardlimit;
+	limit >>= sb->s_blocksize_bits;
+
 	if (limit && buf->f_blocks > limit) {
 		curblock = (dquot->dq_dqb.dqb_curspace +
 			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
@@ -5552,9 +5603,14 @@ static int ext4_statfs_project(struct super_block *sb,
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = dquot->dq_dqb.dqb_isoftlimit ?
-		dquot->dq_dqb.dqb_isoftlimit :
-		dquot->dq_dqb.dqb_ihardlimit;
+	limit = 0;
+	if (dquot->dq_dqb.dqb_isoftlimit &&
+	    (!limit || dquot->dq_dqb.dqb_isoftlimit < limit))
+		limit = dquot->dq_dqb.dqb_isoftlimit;
+	if (dquot->dq_dqb.dqb_ihardlimit &&
+	    (!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
+		limit = dquot->dq_dqb.dqb_ihardlimit;
+
 	if (limit && buf->f_files > limit) {
 		buf->f_files = limit;
 		buf->f_ffree =
@@ -5987,7 +6043,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 		bh = ext4_bread(handle, inode, blk,
 				EXT4_GET_BLOCKS_CREATE |
 				EXT4_GET_BLOCKS_METADATA_NOFAIL);
-	} while (IS_ERR(bh) && (PTR_ERR(bh) == -ENOSPC) &&
+	} while (PTR_ERR(bh) == -ENOSPC &&
 		 ext4_should_retry_alloc(inode->i_sb, &retries));
 	if (IS_ERR(bh))
 		return PTR_ERR(bh);
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index eb1efad0e20a..d218ebdafa4a 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -29,6 +29,10 @@ typedef enum {
 	attr_last_error_time,
 	attr_feature,
 	attr_pointer_ui,
+	attr_pointer_ul,
+	attr_pointer_u64,
+	attr_pointer_u8,
+	attr_pointer_string,
 	attr_pointer_atomic,
 	attr_journal_task,
 } attr_id_t;
@@ -46,6 +50,7 @@ struct ext4_attr {
 	struct attribute attr;
 	short attr_id;
 	short attr_ptr;
+	unsigned short attr_size;
 	union {
 		int offset;
 		void *explicit_ptr;
@@ -154,12 +159,35 @@ static struct ext4_attr ext4_attr_##_name = {			\
 	},							\
 }
 
+#define EXT4_ATTR_STRING(_name,_mode,_size,_struct,_elname)	\
+static struct ext4_attr ext4_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.attr_id = attr_pointer_string,				\
+	.attr_size = _size,					\
+	.attr_ptr = ptr_##_struct##_offset,			\
+	.u = {							\
+		.offset = offsetof(struct _struct, _elname),\
+	},							\
+}
+
 #define EXT4_RO_ATTR_ES_UI(_name,_elname)				\
 	EXT4_ATTR_OFFSET(_name, 0444, pointer_ui, ext4_super_block, _elname)
 
+#define EXT4_RO_ATTR_ES_U8(_name,_elname)				\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_u8, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_U64(_name,_elname)				\
+	EXT4_ATTR_OFFSET(_name, 0444, pointer_u64, ext4_super_block, _elname)
+
+#define EXT4_RO_ATTR_ES_STRING(_name,_elname,_size)			\
+	EXT4_ATTR_STRING(_name, 0444, _size, ext4_super_block, _elname)
+
 #define EXT4_RW_ATTR_SBI_UI(_name,_elname)	\
 	EXT4_ATTR_OFFSET(_name, 0644, pointer_ui, ext4_sb_info, _elname)
 
+#define EXT4_RW_ATTR_SBI_UL(_name,_elname)	\
+	EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname)
+
 #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \
 static struct ext4_attr ext4_attr_##_name = {			\
 	.attr = {.name = __stringify(_name), .mode = _mode },	\
@@ -194,7 +222,20 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.int
 EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
+#ifdef CONFIG_EXT4_DEBUG
+EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail);
+#endif
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
+EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode);
+EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode);
+EXT4_RO_ATTR_ES_UI(first_error_ino, s_first_error_ino);
+EXT4_RO_ATTR_ES_UI(last_error_ino, s_last_error_ino);
+EXT4_RO_ATTR_ES_U64(first_error_block, s_first_error_block);
+EXT4_RO_ATTR_ES_U64(last_error_block, s_last_error_block);
+EXT4_RO_ATTR_ES_UI(first_error_line, s_first_error_line);
+EXT4_RO_ATTR_ES_UI(last_error_line, s_last_error_line);
+EXT4_RO_ATTR_ES_STRING(first_error_func, s_first_error_func, 32);
+EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32);
 EXT4_ATTR(first_error_time, 0444, first_error_time);
 EXT4_ATTR(last_error_time, 0444, last_error_time);
 EXT4_ATTR(journal_task, 0444, journal_task);
@@ -225,9 +266,22 @@ static struct attribute *ext4_attrs[] = {
 	ATTR_LIST(msg_ratelimit_interval_ms),
 	ATTR_LIST(msg_ratelimit_burst),
 	ATTR_LIST(errors_count),
+	ATTR_LIST(first_error_ino),
+	ATTR_LIST(last_error_ino),
+	ATTR_LIST(first_error_block),
+	ATTR_LIST(last_error_block),
+	ATTR_LIST(first_error_line),
+	ATTR_LIST(last_error_line),
+	ATTR_LIST(first_error_func),
+	ATTR_LIST(last_error_func),
+	ATTR_LIST(first_error_errcode),
+	ATTR_LIST(last_error_errcode),
 	ATTR_LIST(first_error_time),
 	ATTR_LIST(last_error_time),
 	ATTR_LIST(journal_task),
+#ifdef CONFIG_EXT4_DEBUG
+	ATTR_LIST(simulate_fail),
+#endif
 	NULL,
 };
 ATTRIBUTE_GROUPS(ext4);
@@ -280,7 +334,7 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
 
 static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
 {
-	return snprintf(buf, PAGE_SIZE, "%lld",
+	return snprintf(buf, PAGE_SIZE, "%lld\n",
 			((time64_t)hi << 32) + le32_to_cpu(lo));
 }
 
@@ -318,6 +372,30 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 		else
 			return snprintf(buf, PAGE_SIZE, "%u\n",
 					*((unsigned int *) ptr));
+	case attr_pointer_ul:
+		if (!ptr)
+			return 0;
+		return snprintf(buf, PAGE_SIZE, "%lu\n",
+				*((unsigned long *) ptr));
+	case attr_pointer_u8:
+		if (!ptr)
+			return 0;
+		return snprintf(buf, PAGE_SIZE, "%u\n",
+				*((unsigned char *) ptr));
+	case attr_pointer_u64:
+		if (!ptr)
+			return 0;
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			return snprintf(buf, PAGE_SIZE, "%llu\n",
+					le64_to_cpup(ptr));
+		else
+			return snprintf(buf, PAGE_SIZE, "%llu\n",
+					*((unsigned long long *) ptr));
+	case attr_pointer_string:
+		if (!ptr)
+			return 0;
+		return snprintf(buf, PAGE_SIZE, "%.*s\n", a->attr_size,
+				(char *) ptr);
 	case attr_pointer_atomic:
 		if (!ptr)
 			return 0;
@@ -361,6 +439,14 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 		else
 			*((unsigned int *) ptr) = t;
 		return len;
+	case attr_pointer_ul:
+		if (!ptr)
+			return 0;
+		ret = kstrtoul(skip_spaces(buf), 0, &t);
+		if (ret)
+			return ret;
+		*((unsigned long *) ptr) = t;
+		return len;
 	case attr_inode_readahead:
 		return inode_readahead_blks_store(sbi, buf, len);
 	case attr_trigger_test_error:
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 8966a5439a22..8cac7d95c3ad 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1456,7 +1456,7 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
 	if (!ce)
 		return NULL;
 
-	ea_data = ext4_kvmalloc(value_len, GFP_NOFS);
+	ea_data = kvmalloc(value_len, GFP_KERNEL);
 	if (!ea_data) {
 		mb_cache_entry_put(ea_inode_cache, ce);
 		return NULL;
@@ -2879,9 +2879,11 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
 		bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO);
 		if (IS_ERR(bh)) {
 			error = PTR_ERR(bh);
-			if (error == -EIO)
+			if (error == -EIO) {
+				ext4_set_errno(inode->i_sb, EIO);
 				EXT4_ERROR_INODE(inode, "block %llu read error",
 						 EXT4_I(inode)->i_file_acl);
+			}
 			bh = NULL;
 			goto cleanup;
 		}
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 599fb9194c6a..f0faada30f30 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -22,7 +22,7 @@ config F2FS_FS
 
 config F2FS_STAT_FS
 	bool "F2FS Status Information"
-	depends on F2FS_FS && DEBUG_FS
+	depends on F2FS_FS
 	default y
 	help
 	  /sys/kernel/debug/f2fs/ contains information about all the partitions
@@ -93,3 +93,28 @@ config F2FS_FAULT_INJECTION
 	  Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
 
 	  If unsure, say N.
+
+config F2FS_FS_COMPRESSION
+	bool "F2FS compression feature"
+	depends on F2FS_FS
+	help
+	  Enable filesystem-level compression on f2fs regular files,
+	  multiple back-end compression algorithms are supported.
+
+config F2FS_FS_LZO
+	bool "LZO compression support"
+	depends on F2FS_FS_COMPRESSION
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
+	default y
+	help
+	  Support LZO compress algorithm, if unsure, say Y.
+
+config F2FS_FS_LZ4
+	bool "LZ4 compression support"
+	depends on F2FS_FS_COMPRESSION
+	select LZ4_COMPRESS
+	select LZ4_DECOMPRESS
+	default y
+	help
+	  Support LZ4 compress algorithm, if unsure, say Y.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 2aaecc63834f..ee7316b42f69 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -9,3 +9,4 @@ f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
 f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
 f2fs-$(CONFIG_FS_VERITY) += verity.o
+f2fs-$(CONFIG_F2FS_FS_COMPRESSION) += compress.o
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index ffdaba0c55d2..44e84ac5c941 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1509,10 +1509,10 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_wait_on_all_pages_writeback(sbi);
 
 	/*
-	 * invalidate intermediate page cache borrowed from meta inode
-	 * which are used for migration of encrypted inode's blocks.
+	 * invalidate intermediate page cache borrowed from meta inode which are
+	 * used for migration of encrypted or verity inode's blocks.
 	 */
-	if (f2fs_sb_has_encrypt(sbi))
+	if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi))
 		invalidate_mapping_pages(META_MAPPING(sbi),
 				MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
 
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
new file mode 100644
index 000000000000..d8a64be90a50
--- /dev/null
+++ b/fs/f2fs/compress.c
@@ -0,0 +1,1176 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * f2fs compress support
+ *
+ * Copyright (c) 2019 Chao Yu <chao@kernel.org>
+ */
+
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/lzo.h>
+#include <linux/lz4.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include <trace/events/f2fs.h>
+
+struct f2fs_compress_ops {
+	int (*init_compress_ctx)(struct compress_ctx *cc);
+	void (*destroy_compress_ctx)(struct compress_ctx *cc);
+	int (*compress_pages)(struct compress_ctx *cc);
+	int (*decompress_pages)(struct decompress_io_ctx *dic);
+};
+
+static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index)
+{
+	return index & (cc->cluster_size - 1);
+}
+
+static pgoff_t cluster_idx(struct compress_ctx *cc, pgoff_t index)
+{
+	return index >> cc->log_cluster_size;
+}
+
+static pgoff_t start_idx_of_cluster(struct compress_ctx *cc)
+{
+	return cc->cluster_idx << cc->log_cluster_size;
+}
+
+bool f2fs_is_compressed_page(struct page *page)
+{
+	if (!PagePrivate(page))
+		return false;
+	if (!page_private(page))
+		return false;
+	if (IS_ATOMIC_WRITTEN_PAGE(page) || IS_DUMMY_WRITTEN_PAGE(page))
+		return false;
+	f2fs_bug_on(F2FS_M_SB(page->mapping),
+		*((u32 *)page_private(page)) != F2FS_COMPRESSED_PAGE_MAGIC);
+	return true;
+}
+
+static void f2fs_set_compressed_page(struct page *page,
+		struct inode *inode, pgoff_t index, void *data, refcount_t *r)
+{
+	SetPagePrivate(page);
+	set_page_private(page, (unsigned long)data);
+
+	/* i_crypto_info and iv index */
+	page->index = index;
+	page->mapping = inode->i_mapping;
+	if (r)
+		refcount_inc(r);
+}
+
+static void f2fs_put_compressed_page(struct page *page)
+{
+	set_page_private(page, (unsigned long)NULL);
+	ClearPagePrivate(page);
+	page->mapping = NULL;
+	unlock_page(page);
+	put_page(page);
+}
+
+static void f2fs_drop_rpages(struct compress_ctx *cc, int len, bool unlock)
+{
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (!cc->rpages[i])
+			continue;
+		if (unlock)
+			unlock_page(cc->rpages[i]);
+		else
+			put_page(cc->rpages[i]);
+	}
+}
+
+static void f2fs_put_rpages(struct compress_ctx *cc)
+{
+	f2fs_drop_rpages(cc, cc->cluster_size, false);
+}
+
+static void f2fs_unlock_rpages(struct compress_ctx *cc, int len)
+{
+	f2fs_drop_rpages(cc, len, true);
+}
+
+static void f2fs_put_rpages_mapping(struct compress_ctx *cc,
+				struct address_space *mapping,
+				pgoff_t start, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++) {
+		struct page *page = find_get_page(mapping, start + i);
+
+		put_page(page);
+		put_page(page);
+	}
+}
+
+static void f2fs_put_rpages_wbc(struct compress_ctx *cc,
+		struct writeback_control *wbc, bool redirty, int unlock)
+{
+	unsigned int i;
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		if (!cc->rpages[i])
+			continue;
+		if (redirty)
+			redirty_page_for_writepage(wbc, cc->rpages[i]);
+		f2fs_put_page(cc->rpages[i], unlock);
+	}
+}
+
+struct page *f2fs_compress_control_page(struct page *page)
+{
+	return ((struct compress_io_ctx *)page_private(page))->rpages[0];
+}
+
+int f2fs_init_compress_ctx(struct compress_ctx *cc)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+
+	if (cc->nr_rpages)
+		return 0;
+
+	cc->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
+					cc->log_cluster_size, GFP_NOFS);
+	return cc->rpages ? 0 : -ENOMEM;
+}
+
+void f2fs_destroy_compress_ctx(struct compress_ctx *cc)
+{
+	kfree(cc->rpages);
+	cc->rpages = NULL;
+	cc->nr_rpages = 0;
+	cc->nr_cpages = 0;
+	cc->cluster_idx = NULL_CLUSTER;
+}
+
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page)
+{
+	unsigned int cluster_ofs;
+
+	if (!f2fs_cluster_can_merge_page(cc, page->index))
+		f2fs_bug_on(F2FS_I_SB(cc->inode), 1);
+
+	cluster_ofs = offset_in_cluster(cc, page->index);
+	cc->rpages[cluster_ofs] = page;
+	cc->nr_rpages++;
+	cc->cluster_idx = cluster_idx(cc, page->index);
+}
+
+#ifdef CONFIG_F2FS_FS_LZO
+static int lzo_init_compress_ctx(struct compress_ctx *cc)
+{
+	cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
+				LZO1X_MEM_COMPRESS, GFP_NOFS);
+	if (!cc->private)
+		return -ENOMEM;
+
+	cc->clen = lzo1x_worst_compress(PAGE_SIZE << cc->log_cluster_size);
+	return 0;
+}
+
+static void lzo_destroy_compress_ctx(struct compress_ctx *cc)
+{
+	kvfree(cc->private);
+	cc->private = NULL;
+}
+
+static int lzo_compress_pages(struct compress_ctx *cc)
+{
+	int ret;
+
+	ret = lzo1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata,
+					&cc->clen, cc->private);
+	if (ret != LZO_E_OK) {
+		printk_ratelimited("%sF2FS-fs (%s): lzo compress failed, ret:%d\n",
+				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret);
+		return -EIO;
+	}
+	return 0;
+}
+
+static int lzo_decompress_pages(struct decompress_io_ctx *dic)
+{
+	int ret;
+
+	ret = lzo1x_decompress_safe(dic->cbuf->cdata, dic->clen,
+						dic->rbuf, &dic->rlen);
+	if (ret != LZO_E_OK) {
+		printk_ratelimited("%sF2FS-fs (%s): lzo decompress failed, ret:%d\n",
+				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+		return -EIO;
+	}
+
+	if (dic->rlen != PAGE_SIZE << dic->log_cluster_size) {
+		printk_ratelimited("%sF2FS-fs (%s): lzo invalid rlen:%zu, "
+					"expected:%lu\n", KERN_ERR,
+					F2FS_I_SB(dic->inode)->sb->s_id,
+					dic->rlen,
+					PAGE_SIZE << dic->log_cluster_size);
+		return -EIO;
+	}
+	return 0;
+}
+
+static const struct f2fs_compress_ops f2fs_lzo_ops = {
+	.init_compress_ctx	= lzo_init_compress_ctx,
+	.destroy_compress_ctx	= lzo_destroy_compress_ctx,
+	.compress_pages		= lzo_compress_pages,
+	.decompress_pages	= lzo_decompress_pages,
+};
+#endif
+
+#ifdef CONFIG_F2FS_FS_LZ4
+static int lz4_init_compress_ctx(struct compress_ctx *cc)
+{
+	cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
+				LZ4_MEM_COMPRESS, GFP_NOFS);
+	if (!cc->private)
+		return -ENOMEM;
+
+	cc->clen = LZ4_compressBound(PAGE_SIZE << cc->log_cluster_size);
+	return 0;
+}
+
+static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
+{
+	kvfree(cc->private);
+	cc->private = NULL;
+}
+
+static int lz4_compress_pages(struct compress_ctx *cc)
+{
+	int len;
+
+	len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
+						cc->clen, cc->private);
+	if (!len) {
+		printk_ratelimited("%sF2FS-fs (%s): lz4 compress failed\n",
+				KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id);
+		return -EIO;
+	}
+	cc->clen = len;
+	return 0;
+}
+
+static int lz4_decompress_pages(struct decompress_io_ctx *dic)
+{
+	int ret;
+
+	ret = LZ4_decompress_safe(dic->cbuf->cdata, dic->rbuf,
+						dic->clen, dic->rlen);
+	if (ret < 0) {
+		printk_ratelimited("%sF2FS-fs (%s): lz4 decompress failed, ret:%d\n",
+				KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+		return -EIO;
+	}
+
+	if (ret != PAGE_SIZE << dic->log_cluster_size) {
+		printk_ratelimited("%sF2FS-fs (%s): lz4 invalid rlen:%zu, "
+					"expected:%lu\n", KERN_ERR,
+					F2FS_I_SB(dic->inode)->sb->s_id,
+					dic->rlen,
+					PAGE_SIZE << dic->log_cluster_size);
+		return -EIO;
+	}
+	return 0;
+}
+
+static const struct f2fs_compress_ops f2fs_lz4_ops = {
+	.init_compress_ctx	= lz4_init_compress_ctx,
+	.destroy_compress_ctx	= lz4_destroy_compress_ctx,
+	.compress_pages		= lz4_compress_pages,
+	.decompress_pages	= lz4_decompress_pages,
+};
+#endif
+
+static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = {
+#ifdef CONFIG_F2FS_FS_LZO
+	&f2fs_lzo_ops,
+#else
+	NULL,
+#endif
+#ifdef CONFIG_F2FS_FS_LZ4
+	&f2fs_lz4_ops,
+#else
+	NULL,
+#endif
+};
+
+bool f2fs_is_compress_backend_ready(struct inode *inode)
+{
+	if (!f2fs_compressed_file(inode))
+		return true;
+	return f2fs_cops[F2FS_I(inode)->i_compress_algorithm];
+}
+
+static struct page *f2fs_grab_page(void)
+{
+	struct page *page;
+
+	page = alloc_page(GFP_NOFS);
+	if (!page)
+		return NULL;
+	lock_page(page);
+	return page;
+}
+
+static int f2fs_compress_pages(struct compress_ctx *cc)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+	struct f2fs_inode_info *fi = F2FS_I(cc->inode);
+	const struct f2fs_compress_ops *cops =
+				f2fs_cops[fi->i_compress_algorithm];
+	unsigned int max_len, nr_cpages;
+	int i, ret;
+
+	trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx,
+				cc->cluster_size, fi->i_compress_algorithm);
+
+	ret = cops->init_compress_ctx(cc);
+	if (ret)
+		goto out;
+
+	max_len = COMPRESS_HEADER_SIZE + cc->clen;
+	cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE);
+
+	cc->cpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+					cc->nr_cpages, GFP_NOFS);
+	if (!cc->cpages) {
+		ret = -ENOMEM;
+		goto destroy_compress_ctx;
+	}
+
+	for (i = 0; i < cc->nr_cpages; i++) {
+		cc->cpages[i] = f2fs_grab_page();
+		if (!cc->cpages[i]) {
+			ret = -ENOMEM;
+			goto out_free_cpages;
+		}
+	}
+
+	cc->rbuf = vmap(cc->rpages, cc->cluster_size, VM_MAP, PAGE_KERNEL_RO);
+	if (!cc->rbuf) {
+		ret = -ENOMEM;
+		goto out_free_cpages;
+	}
+
+	cc->cbuf = vmap(cc->cpages, cc->nr_cpages, VM_MAP, PAGE_KERNEL);
+	if (!cc->cbuf) {
+		ret = -ENOMEM;
+		goto out_vunmap_rbuf;
+	}
+
+	ret = cops->compress_pages(cc);
+	if (ret)
+		goto out_vunmap_cbuf;
+
+	max_len = PAGE_SIZE * (cc->cluster_size - 1) - COMPRESS_HEADER_SIZE;
+
+	if (cc->clen > max_len) {
+		ret = -EAGAIN;
+		goto out_vunmap_cbuf;
+	}
+
+	cc->cbuf->clen = cpu_to_le32(cc->clen);
+	cc->cbuf->chksum = cpu_to_le32(0);
+
+	for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++)
+		cc->cbuf->reserved[i] = cpu_to_le32(0);
+
+	vunmap(cc->cbuf);
+	vunmap(cc->rbuf);
+
+	nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE);
+
+	for (i = nr_cpages; i < cc->nr_cpages; i++) {
+		f2fs_put_compressed_page(cc->cpages[i]);
+		cc->cpages[i] = NULL;
+	}
+
+	cc->nr_cpages = nr_cpages;
+
+	trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
+							cc->clen, ret);
+	return 0;
+
+out_vunmap_cbuf:
+	vunmap(cc->cbuf);
+out_vunmap_rbuf:
+	vunmap(cc->rbuf);
+out_free_cpages:
+	for (i = 0; i < cc->nr_cpages; i++) {
+		if (cc->cpages[i])
+			f2fs_put_compressed_page(cc->cpages[i]);
+	}
+	kfree(cc->cpages);
+	cc->cpages = NULL;
+destroy_compress_ctx:
+	cops->destroy_compress_ctx(cc);
+out:
+	trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
+							cc->clen, ret);
+	return ret;
+}
+
+void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
+{
+	struct decompress_io_ctx *dic =
+			(struct decompress_io_ctx *)page_private(page);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dic->inode);
+	struct f2fs_inode_info *fi= F2FS_I(dic->inode);
+	const struct f2fs_compress_ops *cops =
+			f2fs_cops[fi->i_compress_algorithm];
+	int ret;
+
+	dec_page_count(sbi, F2FS_RD_DATA);
+
+	if (bio->bi_status || PageError(page))
+		dic->failed = true;
+
+	if (refcount_dec_not_one(&dic->ref))
+		return;
+
+	trace_f2fs_decompress_pages_start(dic->inode, dic->cluster_idx,
+				dic->cluster_size, fi->i_compress_algorithm);
+
+	/* submit partial compressed pages */
+	if (dic->failed) {
+		ret = -EIO;
+		goto out_free_dic;
+	}
+
+	dic->rbuf = vmap(dic->tpages, dic->cluster_size, VM_MAP, PAGE_KERNEL);
+	if (!dic->rbuf) {
+		ret = -ENOMEM;
+		goto out_free_dic;
+	}
+
+	dic->cbuf = vmap(dic->cpages, dic->nr_cpages, VM_MAP, PAGE_KERNEL_RO);
+	if (!dic->cbuf) {
+		ret = -ENOMEM;
+		goto out_vunmap_rbuf;
+	}
+
+	dic->clen = le32_to_cpu(dic->cbuf->clen);
+	dic->rlen = PAGE_SIZE << dic->log_cluster_size;
+
+	if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) {
+		ret = -EFSCORRUPTED;
+		goto out_vunmap_cbuf;
+	}
+
+	ret = cops->decompress_pages(dic);
+
+out_vunmap_cbuf:
+	vunmap(dic->cbuf);
+out_vunmap_rbuf:
+	vunmap(dic->rbuf);
+out_free_dic:
+	if (!verity)
+		f2fs_decompress_end_io(dic->rpages, dic->cluster_size,
+								ret, false);
+
+	trace_f2fs_decompress_pages_end(dic->inode, dic->cluster_idx,
+							dic->clen, ret);
+	if (!verity)
+		f2fs_free_dic(dic);
+}
+
+static bool is_page_in_cluster(struct compress_ctx *cc, pgoff_t index)
+{
+	if (cc->cluster_idx == NULL_CLUSTER)
+		return true;
+	return cc->cluster_idx == cluster_idx(cc, index);
+}
+
+bool f2fs_cluster_is_empty(struct compress_ctx *cc)
+{
+	return cc->nr_rpages == 0;
+}
+
+static bool f2fs_cluster_is_full(struct compress_ctx *cc)
+{
+	return cc->cluster_size == cc->nr_rpages;
+}
+
+bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
+{
+	if (f2fs_cluster_is_empty(cc))
+		return true;
+	return is_page_in_cluster(cc, index);
+}
+
+static bool __cluster_may_compress(struct compress_ctx *cc)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+	loff_t i_size = i_size_read(cc->inode);
+	unsigned nr_pages = DIV_ROUND_UP(i_size, PAGE_SIZE);
+	int i;
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		struct page *page = cc->rpages[i];
+
+		f2fs_bug_on(sbi, !page);
+
+		if (unlikely(f2fs_cp_error(sbi)))
+			return false;
+		if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+			return false;
+
+		/* beyond EOF */
+		if (page->index >= nr_pages)
+			return false;
+	}
+	return true;
+}
+
+/* return # of compressed block addresses */
+static int f2fs_compressed_blocks(struct compress_ctx *cc)
+{
+	struct dnode_of_data dn;
+	int ret;
+
+	set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+	ret = f2fs_get_dnode_of_data(&dn, start_idx_of_cluster(cc),
+							LOOKUP_NODE);
+	if (ret) {
+		if (ret == -ENOENT)
+			ret = 0;
+		goto fail;
+	}
+
+	if (dn.data_blkaddr == COMPRESS_ADDR) {
+		int i;
+
+		ret = 1;
+		for (i = 1; i < cc->cluster_size; i++) {
+			block_t blkaddr;
+
+			blkaddr = datablock_addr(dn.inode,
+					dn.node_page, dn.ofs_in_node + i);
+			if (blkaddr != NULL_ADDR)
+				ret++;
+		}
+	}
+fail:
+	f2fs_put_dnode(&dn);
+	return ret;
+}
+
+int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
+{
+	struct compress_ctx cc = {
+		.inode = inode,
+		.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+		.cluster_size = F2FS_I(inode)->i_cluster_size,
+		.cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
+	};
+
+	return f2fs_compressed_blocks(&cc);
+}
+
+static bool cluster_may_compress(struct compress_ctx *cc)
+{
+	if (!f2fs_compressed_file(cc->inode))
+		return false;
+	if (f2fs_is_atomic_file(cc->inode))
+		return false;
+	if (f2fs_is_mmap_file(cc->inode))
+		return false;
+	if (!f2fs_cluster_is_full(cc))
+		return false;
+	return __cluster_may_compress(cc);
+}
+
+static void set_cluster_writeback(struct compress_ctx *cc)
+{
+	int i;
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		if (cc->rpages[i])
+			set_page_writeback(cc->rpages[i]);
+	}
+}
+
+static void set_cluster_dirty(struct compress_ctx *cc)
+{
+	int i;
+
+	for (i = 0; i < cc->cluster_size; i++)
+		if (cc->rpages[i])
+			set_page_dirty(cc->rpages[i]);
+}
+
+static int prepare_compress_overwrite(struct compress_ctx *cc,
+		struct page **pagep, pgoff_t index, void **fsdata)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+	struct address_space *mapping = cc->inode->i_mapping;
+	struct page *page;
+	struct dnode_of_data dn;
+	sector_t last_block_in_bio;
+	unsigned fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT;
+	pgoff_t start_idx = start_idx_of_cluster(cc);
+	int i, ret;
+	bool prealloc;
+
+retry:
+	ret = f2fs_compressed_blocks(cc);
+	if (ret <= 0)
+		return ret;
+
+	/* compressed case */
+	prealloc = (ret < cc->cluster_size);
+
+	ret = f2fs_init_compress_ctx(cc);
+	if (ret)
+		return ret;
+
+	/* keep page reference to avoid page reclaim */
+	for (i = 0; i < cc->cluster_size; i++) {
+		page = f2fs_pagecache_get_page(mapping, start_idx + i,
+							fgp_flag, GFP_NOFS);
+		if (!page) {
+			ret = -ENOMEM;
+			goto unlock_pages;
+		}
+
+		if (PageUptodate(page))
+			unlock_page(page);
+		else
+			f2fs_compress_ctx_add_page(cc, page);
+	}
+
+	if (!f2fs_cluster_is_empty(cc)) {
+		struct bio *bio = NULL;
+
+		ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size,
+						&last_block_in_bio, false);
+		f2fs_destroy_compress_ctx(cc);
+		if (ret)
+			goto release_pages;
+		if (bio)
+			f2fs_submit_bio(sbi, bio, DATA);
+
+		ret = f2fs_init_compress_ctx(cc);
+		if (ret)
+			goto release_pages;
+	}
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		f2fs_bug_on(sbi, cc->rpages[i]);
+
+		page = find_lock_page(mapping, start_idx + i);
+		f2fs_bug_on(sbi, !page);
+
+		f2fs_wait_on_page_writeback(page, DATA, true, true);
+
+		f2fs_compress_ctx_add_page(cc, page);
+		f2fs_put_page(page, 0);
+
+		if (!PageUptodate(page)) {
+			f2fs_unlock_rpages(cc, i + 1);
+			f2fs_put_rpages_mapping(cc, mapping, start_idx,
+					cc->cluster_size);
+			f2fs_destroy_compress_ctx(cc);
+			goto retry;
+		}
+	}
+
+	if (prealloc) {
+		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+
+		set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+
+		for (i = cc->cluster_size - 1; i > 0; i--) {
+			ret = f2fs_get_block(&dn, start_idx + i);
+			if (ret) {
+				i = cc->cluster_size;
+				break;
+			}
+
+			if (dn.data_blkaddr != NEW_ADDR)
+				break;
+		}
+
+		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+	}
+
+	if (likely(!ret)) {
+		*fsdata = cc->rpages;
+		*pagep = cc->rpages[offset_in_cluster(cc, index)];
+		return cc->cluster_size;
+	}
+
+unlock_pages:
+	f2fs_unlock_rpages(cc, i);
+release_pages:
+	f2fs_put_rpages_mapping(cc, mapping, start_idx, i);
+	f2fs_destroy_compress_ctx(cc);
+	return ret;
+}
+
+int f2fs_prepare_compress_overwrite(struct inode *inode,
+		struct page **pagep, pgoff_t index, void **fsdata)
+{
+	struct compress_ctx cc = {
+		.inode = inode,
+		.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+		.cluster_size = F2FS_I(inode)->i_cluster_size,
+		.cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
+		.rpages = NULL,
+		.nr_rpages = 0,
+	};
+
+	return prepare_compress_overwrite(&cc, pagep, index, fsdata);
+}
+
+bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
+					pgoff_t index, unsigned copied)
+
+{
+	struct compress_ctx cc = {
+		.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+		.cluster_size = F2FS_I(inode)->i_cluster_size,
+		.rpages = fsdata,
+	};
+	bool first_index = (index == cc.rpages[0]->index);
+
+	if (copied)
+		set_cluster_dirty(&cc);
+
+	f2fs_put_rpages_wbc(&cc, NULL, false, 1);
+	f2fs_destroy_compress_ctx(&cc);
+
+	return first_index;
+}
+
+static int f2fs_write_compressed_pages(struct compress_ctx *cc,
+					int *submitted,
+					struct writeback_control *wbc,
+					enum iostat_type io_type)
+{
+	struct inode *inode = cc->inode;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_io_info fio = {
+		.sbi = sbi,
+		.ino = cc->inode->i_ino,
+		.type = DATA,
+		.op = REQ_OP_WRITE,
+		.op_flags = wbc_to_write_flags(wbc),
+		.old_blkaddr = NEW_ADDR,
+		.page = NULL,
+		.encrypted_page = NULL,
+		.compressed_page = NULL,
+		.submitted = false,
+		.need_lock = LOCK_RETRY,
+		.io_type = io_type,
+		.io_wbc = wbc,
+		.encrypted = f2fs_encrypted_file(cc->inode),
+	};
+	struct dnode_of_data dn;
+	struct node_info ni;
+	struct compress_io_ctx *cic;
+	pgoff_t start_idx = start_idx_of_cluster(cc);
+	unsigned int last_index = cc->cluster_size - 1;
+	loff_t psize;
+	int i, err;
+
+	set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
+
+	f2fs_lock_op(sbi);
+
+	err = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
+	if (err)
+		goto out_unlock_op;
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		if (datablock_addr(dn.inode, dn.node_page,
+					dn.ofs_in_node + i) == NULL_ADDR)
+			goto out_put_dnode;
+	}
+
+	psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT;
+
+	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+	if (err)
+		goto out_put_dnode;
+
+	fio.version = ni.version;
+
+	cic = f2fs_kzalloc(sbi, sizeof(struct compress_io_ctx), GFP_NOFS);
+	if (!cic)
+		goto out_put_dnode;
+
+	cic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
+	cic->inode = inode;
+	refcount_set(&cic->ref, 1);
+	cic->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
+			cc->log_cluster_size, GFP_NOFS);
+	if (!cic->rpages)
+		goto out_put_cic;
+
+	cic->nr_rpages = cc->cluster_size;
+
+	for (i = 0; i < cc->nr_cpages; i++) {
+		f2fs_set_compressed_page(cc->cpages[i], inode,
+					cc->rpages[i + 1]->index,
+					cic, i ? &cic->ref : NULL);
+		fio.compressed_page = cc->cpages[i];
+		if (fio.encrypted) {
+			fio.page = cc->rpages[i + 1];
+			err = f2fs_encrypt_one_page(&fio);
+			if (err)
+				goto out_destroy_crypt;
+			cc->cpages[i] = fio.encrypted_page;
+		}
+	}
+
+	set_cluster_writeback(cc);
+
+	for (i = 0; i < cc->cluster_size; i++)
+		cic->rpages[i] = cc->rpages[i];
+
+	for (i = 0; i < cc->cluster_size; i++, dn.ofs_in_node++) {
+		block_t blkaddr;
+
+		blkaddr = datablock_addr(dn.inode, dn.node_page,
+							dn.ofs_in_node);
+		fio.page = cic->rpages[i];
+		fio.old_blkaddr = blkaddr;
+
+		/* cluster header */
+		if (i == 0) {
+			if (blkaddr == COMPRESS_ADDR)
+				fio.compr_blocks++;
+			if (__is_valid_data_blkaddr(blkaddr))
+				f2fs_invalidate_blocks(sbi, blkaddr);
+			f2fs_update_data_blkaddr(&dn, COMPRESS_ADDR);
+			goto unlock_continue;
+		}
+
+		if (fio.compr_blocks && __is_valid_data_blkaddr(blkaddr))
+			fio.compr_blocks++;
+
+		if (i > cc->nr_cpages) {
+			if (__is_valid_data_blkaddr(blkaddr)) {
+				f2fs_invalidate_blocks(sbi, blkaddr);
+				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
+			}
+			goto unlock_continue;
+		}
+
+		f2fs_bug_on(fio.sbi, blkaddr == NULL_ADDR);
+
+		if (fio.encrypted)
+			fio.encrypted_page = cc->cpages[i - 1];
+		else
+			fio.compressed_page = cc->cpages[i - 1];
+
+		cc->cpages[i - 1] = NULL;
+		f2fs_outplace_write_data(&dn, &fio);
+		(*submitted)++;
+unlock_continue:
+		inode_dec_dirty_pages(cc->inode);
+		unlock_page(fio.page);
+	}
+
+	if (fio.compr_blocks)
+		f2fs_i_compr_blocks_update(inode, fio.compr_blocks - 1, false);
+	f2fs_i_compr_blocks_update(inode, cc->nr_cpages, true);
+
+	set_inode_flag(cc->inode, FI_APPEND_WRITE);
+	if (cc->cluster_idx == 0)
+		set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
+
+	f2fs_put_dnode(&dn);
+	f2fs_unlock_op(sbi);
+
+	down_write(&fi->i_sem);
+	if (fi->last_disk_size < psize)
+		fi->last_disk_size = psize;
+	up_write(&fi->i_sem);
+
+	f2fs_put_rpages(cc);
+	f2fs_destroy_compress_ctx(cc);
+	return 0;
+
+out_destroy_crypt:
+	kfree(cic->rpages);
+
+	for (--i; i >= 0; i--)
+		fscrypt_finalize_bounce_page(&cc->cpages[i]);
+	for (i = 0; i < cc->nr_cpages; i++) {
+		if (!cc->cpages[i])
+			continue;
+		f2fs_put_page(cc->cpages[i], 1);
+	}
+out_put_cic:
+	kfree(cic);
+out_put_dnode:
+	f2fs_put_dnode(&dn);
+out_unlock_op:
+	f2fs_unlock_op(sbi);
+	return -EAGAIN;
+}
+
+void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
+{
+	struct f2fs_sb_info *sbi = bio->bi_private;
+	struct compress_io_ctx *cic =
+			(struct compress_io_ctx *)page_private(page);
+	int i;
+
+	if (unlikely(bio->bi_status))
+		mapping_set_error(cic->inode->i_mapping, -EIO);
+
+	f2fs_put_compressed_page(page);
+
+	dec_page_count(sbi, F2FS_WB_DATA);
+
+	if (refcount_dec_not_one(&cic->ref))
+		return;
+
+	for (i = 0; i < cic->nr_rpages; i++) {
+		WARN_ON(!cic->rpages[i]);
+		clear_cold_data(cic->rpages[i]);
+		end_page_writeback(cic->rpages[i]);
+	}
+
+	kfree(cic->rpages);
+	kfree(cic);
+}
+
+static int f2fs_write_raw_pages(struct compress_ctx *cc,
+					int *submitted,
+					struct writeback_control *wbc,
+					enum iostat_type io_type)
+{
+	struct address_space *mapping = cc->inode->i_mapping;
+	int _submitted, compr_blocks, ret;
+	int i = -1, err = 0;
+
+	compr_blocks = f2fs_compressed_blocks(cc);
+	if (compr_blocks < 0) {
+		err = compr_blocks;
+		goto out_err;
+	}
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		if (!cc->rpages[i])
+			continue;
+retry_write:
+		if (cc->rpages[i]->mapping != mapping) {
+			unlock_page(cc->rpages[i]);
+			continue;
+		}
+
+		BUG_ON(!PageLocked(cc->rpages[i]));
+
+		ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted,
+						NULL, NULL, wbc, io_type,
+						compr_blocks);
+		if (ret) {
+			if (ret == AOP_WRITEPAGE_ACTIVATE) {
+				unlock_page(cc->rpages[i]);
+				ret = 0;
+			} else if (ret == -EAGAIN) {
+				ret = 0;
+				cond_resched();
+				congestion_wait(BLK_RW_ASYNC, HZ/50);
+				lock_page(cc->rpages[i]);
+				clear_page_dirty_for_io(cc->rpages[i]);
+				goto retry_write;
+			}
+			err = ret;
+			goto out_fail;
+		}
+
+		*submitted += _submitted;
+	}
+	return 0;
+
+out_fail:
+	/* TODO: revoke partially updated block addresses */
+	BUG_ON(compr_blocks);
+out_err:
+	for (++i; i < cc->cluster_size; i++) {
+		if (!cc->rpages[i])
+			continue;
+		redirty_page_for_writepage(wbc, cc->rpages[i]);
+		unlock_page(cc->rpages[i]);
+	}
+	return err;
+}
+
+int f2fs_write_multi_pages(struct compress_ctx *cc,
+					int *submitted,
+					struct writeback_control *wbc,
+					enum iostat_type io_type)
+{
+	struct f2fs_inode_info *fi = F2FS_I(cc->inode);
+	const struct f2fs_compress_ops *cops =
+			f2fs_cops[fi->i_compress_algorithm];
+	int err;
+
+	*submitted = 0;
+	if (cluster_may_compress(cc)) {
+		err = f2fs_compress_pages(cc);
+		if (err == -EAGAIN) {
+			goto write;
+		} else if (err) {
+			f2fs_put_rpages_wbc(cc, wbc, true, 1);
+			goto destroy_out;
+		}
+
+		err = f2fs_write_compressed_pages(cc, submitted,
+							wbc, io_type);
+		cops->destroy_compress_ctx(cc);
+		if (!err)
+			return 0;
+		f2fs_bug_on(F2FS_I_SB(cc->inode), err != -EAGAIN);
+	}
+write:
+	f2fs_bug_on(F2FS_I_SB(cc->inode), *submitted);
+
+	err = f2fs_write_raw_pages(cc, submitted, wbc, io_type);
+	f2fs_put_rpages_wbc(cc, wbc, false, 0);
+destroy_out:
+	f2fs_destroy_compress_ctx(cc);
+	return err;
+}
+
+struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
+	struct decompress_io_ctx *dic;
+	pgoff_t start_idx = start_idx_of_cluster(cc);
+	int i;
+
+	dic = f2fs_kzalloc(sbi, sizeof(struct decompress_io_ctx), GFP_NOFS);
+	if (!dic)
+		return ERR_PTR(-ENOMEM);
+
+	dic->rpages = f2fs_kzalloc(sbi, sizeof(struct page *) <<
+			cc->log_cluster_size, GFP_NOFS);
+	if (!dic->rpages) {
+		kfree(dic);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	dic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
+	dic->inode = cc->inode;
+	refcount_set(&dic->ref, 1);
+	dic->cluster_idx = cc->cluster_idx;
+	dic->cluster_size = cc->cluster_size;
+	dic->log_cluster_size = cc->log_cluster_size;
+	dic->nr_cpages = cc->nr_cpages;
+	dic->failed = false;
+
+	for (i = 0; i < dic->cluster_size; i++)
+		dic->rpages[i] = cc->rpages[i];
+	dic->nr_rpages = cc->cluster_size;
+
+	dic->cpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+					dic->nr_cpages, GFP_NOFS);
+	if (!dic->cpages)
+		goto out_free;
+
+	for (i = 0; i < dic->nr_cpages; i++) {
+		struct page *page;
+
+		page = f2fs_grab_page();
+		if (!page)
+			goto out_free;
+
+		f2fs_set_compressed_page(page, cc->inode,
+					start_idx + i + 1,
+					dic, i ? &dic->ref : NULL);
+		dic->cpages[i] = page;
+	}
+
+	dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+					dic->cluster_size, GFP_NOFS);
+	if (!dic->tpages)
+		goto out_free;
+
+	for (i = 0; i < dic->cluster_size; i++) {
+		if (cc->rpages[i])
+			continue;
+
+		dic->tpages[i] = f2fs_grab_page();
+		if (!dic->tpages[i])
+			goto out_free;
+	}
+
+	for (i = 0; i < dic->cluster_size; i++) {
+		if (dic->tpages[i])
+			continue;
+		dic->tpages[i] = cc->rpages[i];
+	}
+
+	return dic;
+
+out_free:
+	f2fs_free_dic(dic);
+	return ERR_PTR(-ENOMEM);
+}
+
+void f2fs_free_dic(struct decompress_io_ctx *dic)
+{
+	int i;
+
+	if (dic->tpages) {
+		for (i = 0; i < dic->cluster_size; i++) {
+			if (dic->rpages[i])
+				continue;
+			f2fs_put_page(dic->tpages[i], 1);
+		}
+		kfree(dic->tpages);
+	}
+
+	if (dic->cpages) {
+		for (i = 0; i < dic->nr_cpages; i++) {
+			if (!dic->cpages[i])
+				continue;
+			f2fs_put_compressed_page(dic->cpages[i]);
+		}
+		kfree(dic->cpages);
+	}
+
+	kfree(dic->rpages);
+	kfree(dic);
+}
+
+void f2fs_decompress_end_io(struct page **rpages,
+			unsigned int cluster_size, bool err, bool verity)
+{
+	int i;
+
+	for (i = 0; i < cluster_size; i++) {
+		struct page *rpage = rpages[i];
+
+		if (!rpage)
+			continue;
+
+		if (err || PageError(rpage)) {
+			ClearPageUptodate(rpage);
+			ClearPageError(rpage);
+		} else {
+			if (!verity || fsverity_verify_page(rpage))
+				SetPageUptodate(rpage);
+			else
+				SetPageError(rpage);
+		}
+		unlock_page(rpage);
+	}
+}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0fa356e94ef5..8bd9afa81c54 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -31,6 +31,47 @@
 static struct kmem_cache *bio_post_read_ctx_cache;
 static struct kmem_cache *bio_entry_slab;
 static mempool_t *bio_post_read_ctx_pool;
+static struct bio_set f2fs_bioset;
+
+#define	F2FS_BIO_POOL_SIZE	NR_CURSEG_TYPE
+
+int __init f2fs_init_bioset(void)
+{
+	if (bioset_init(&f2fs_bioset, F2FS_BIO_POOL_SIZE,
+					0, BIOSET_NEED_BVECS))
+		return -ENOMEM;
+	return 0;
+}
+
+void f2fs_destroy_bioset(void)
+{
+	bioset_exit(&f2fs_bioset);
+}
+
+static inline struct bio *__f2fs_bio_alloc(gfp_t gfp_mask,
+						unsigned int nr_iovecs)
+{
+	return bio_alloc_bioset(gfp_mask, nr_iovecs, &f2fs_bioset);
+}
+
+struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail)
+{
+	struct bio *bio;
+
+	if (no_fail) {
+		/* No failure on bio allocation */
+		bio = __f2fs_bio_alloc(GFP_NOIO, npages);
+		if (!bio)
+			bio = __f2fs_bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
+		return bio;
+	}
+	if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
+		f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
+		return NULL;
+	}
+
+	return __f2fs_bio_alloc(GFP_KERNEL, npages);
+}
 
 static bool __is_cp_guaranteed(struct page *page)
 {
@@ -41,6 +82,9 @@ static bool __is_cp_guaranteed(struct page *page)
 	if (!mapping)
 		return false;
 
+	if (f2fs_is_compressed_page(page))
+		return false;
+
 	inode = mapping->host;
 	sbi = F2FS_I_SB(inode);
 
@@ -73,19 +117,19 @@ static enum count_type __read_io_type(struct page *page)
 
 /* postprocessing steps for read bios */
 enum bio_post_read_step {
-	STEP_INITIAL = 0,
 	STEP_DECRYPT,
+	STEP_DECOMPRESS,
 	STEP_VERITY,
 };
 
 struct bio_post_read_ctx {
 	struct bio *bio;
+	struct f2fs_sb_info *sbi;
 	struct work_struct work;
-	unsigned int cur_step;
 	unsigned int enabled_steps;
 };
 
-static void __read_end_io(struct bio *bio)
+static void __read_end_io(struct bio *bio, bool compr, bool verity)
 {
 	struct page *page;
 	struct bio_vec *bv;
@@ -94,6 +138,13 @@ static void __read_end_io(struct bio *bio)
 	bio_for_each_segment_all(bv, bio, iter_all) {
 		page = bv->bv_page;
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		if (compr && f2fs_is_compressed_page(page)) {
+			f2fs_decompress_pages(bio, page, verity);
+			continue;
+		}
+#endif
+
 		/* PG_error was set if any post_read step failed */
 		if (bio->bi_status || PageError(page)) {
 			ClearPageUptodate(page);
@@ -105,31 +156,107 @@ static void __read_end_io(struct bio *bio)
 		dec_page_count(F2FS_P_SB(page), __read_io_type(page));
 		unlock_page(page);
 	}
-	if (bio->bi_private)
-		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
-	bio_put(bio);
+}
+
+static void f2fs_release_read_bio(struct bio *bio);
+static void __f2fs_read_end_io(struct bio *bio, bool compr, bool verity)
+{
+	if (!compr)
+		__read_end_io(bio, false, verity);
+	f2fs_release_read_bio(bio);
+}
+
+static void f2fs_decompress_bio(struct bio *bio, bool verity)
+{
+	__read_end_io(bio, true, verity);
 }
 
 static void bio_post_read_processing(struct bio_post_read_ctx *ctx);
 
-static void decrypt_work(struct work_struct *work)
+static void f2fs_decrypt_work(struct bio_post_read_ctx *ctx)
+{
+	fscrypt_decrypt_bio(ctx->bio);
+}
+
+static void f2fs_decompress_work(struct bio_post_read_ctx *ctx)
+{
+	f2fs_decompress_bio(ctx->bio, ctx->enabled_steps & (1 << STEP_VERITY));
+}
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+static void f2fs_verify_pages(struct page **rpages, unsigned int cluster_size)
+{
+	f2fs_decompress_end_io(rpages, cluster_size, false, true);
+}
+
+static void f2fs_verify_bio(struct bio *bio)
+{
+	struct page *page = bio_first_page_all(bio);
+	struct decompress_io_ctx *dic =
+			(struct decompress_io_ctx *)page_private(page);
+
+	f2fs_verify_pages(dic->rpages, dic->cluster_size);
+	f2fs_free_dic(dic);
+}
+#endif
+
+static void f2fs_verity_work(struct work_struct *work)
 {
 	struct bio_post_read_ctx *ctx =
 		container_of(work, struct bio_post_read_ctx, work);
+	struct bio *bio = ctx->bio;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	unsigned int enabled_steps = ctx->enabled_steps;
+#endif
 
-	fscrypt_decrypt_bio(ctx->bio);
+	/*
+	 * fsverity_verify_bio() may call readpages() again, and while verity
+	 * will be disabled for this, decryption may still be needed, resulting
+	 * in another bio_post_read_ctx being allocated.  So to prevent
+	 * deadlocks we need to release the current ctx to the mempool first.
+	 * This assumes that verity is the last post-read step.
+	 */
+	mempool_free(ctx, bio_post_read_ctx_pool);
+	bio->bi_private = NULL;
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	/* previous step is decompression */
+	if (enabled_steps & (1 << STEP_DECOMPRESS)) {
+		f2fs_verify_bio(bio);
+		f2fs_release_read_bio(bio);
+		return;
+	}
+#endif
 
-	bio_post_read_processing(ctx);
+	fsverity_verify_bio(bio);
+	__f2fs_read_end_io(bio, false, false);
 }
 
-static void verity_work(struct work_struct *work)
+static void f2fs_post_read_work(struct work_struct *work)
 {
 	struct bio_post_read_ctx *ctx =
 		container_of(work, struct bio_post_read_ctx, work);
 
-	fsverity_verify_bio(ctx->bio);
+	if (ctx->enabled_steps & (1 << STEP_DECRYPT))
+		f2fs_decrypt_work(ctx);
 
-	bio_post_read_processing(ctx);
+	if (ctx->enabled_steps & (1 << STEP_DECOMPRESS))
+		f2fs_decompress_work(ctx);
+
+	if (ctx->enabled_steps & (1 << STEP_VERITY)) {
+		INIT_WORK(&ctx->work, f2fs_verity_work);
+		fsverity_enqueue_verify_work(&ctx->work);
+		return;
+	}
+
+	__f2fs_read_end_io(ctx->bio,
+		ctx->enabled_steps & (1 << STEP_DECOMPRESS), false);
+}
+
+static void f2fs_enqueue_post_read_work(struct f2fs_sb_info *sbi,
+						struct work_struct *work)
+{
+	queue_work(sbi->post_read_wq, work);
 }
 
 static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
@@ -139,31 +266,26 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx)
 	 * verity may require reading metadata pages that need decryption, and
 	 * we shouldn't recurse to the same workqueue.
 	 */
-	switch (++ctx->cur_step) {
-	case STEP_DECRYPT:
-		if (ctx->enabled_steps & (1 << STEP_DECRYPT)) {
-			INIT_WORK(&ctx->work, decrypt_work);
-			fscrypt_enqueue_decrypt_work(&ctx->work);
-			return;
-		}
-		ctx->cur_step++;
-		/* fall-through */
-	case STEP_VERITY:
-		if (ctx->enabled_steps & (1 << STEP_VERITY)) {
-			INIT_WORK(&ctx->work, verity_work);
-			fsverity_enqueue_verify_work(&ctx->work);
-			return;
-		}
-		ctx->cur_step++;
-		/* fall-through */
-	default:
-		__read_end_io(ctx->bio);
+
+	if (ctx->enabled_steps & (1 << STEP_DECRYPT) ||
+		ctx->enabled_steps & (1 << STEP_DECOMPRESS)) {
+		INIT_WORK(&ctx->work, f2fs_post_read_work);
+		f2fs_enqueue_post_read_work(ctx->sbi, &ctx->work);
+		return;
 	}
+
+	if (ctx->enabled_steps & (1 << STEP_VERITY)) {
+		INIT_WORK(&ctx->work, f2fs_verity_work);
+		fsverity_enqueue_verify_work(&ctx->work);
+		return;
+	}
+
+	__f2fs_read_end_io(ctx->bio, false, false);
 }
 
 static bool f2fs_bio_post_read_required(struct bio *bio)
 {
-	return bio->bi_private && !bio->bi_status;
+	return bio->bi_private;
 }
 
 static void f2fs_read_end_io(struct bio *bio)
@@ -178,12 +300,11 @@ static void f2fs_read_end_io(struct bio *bio)
 	if (f2fs_bio_post_read_required(bio)) {
 		struct bio_post_read_ctx *ctx = bio->bi_private;
 
-		ctx->cur_step = STEP_INITIAL;
 		bio_post_read_processing(ctx);
 		return;
 	}
 
-	__read_end_io(bio);
+	__f2fs_read_end_io(bio, false, false);
 }
 
 static void f2fs_write_end_io(struct bio *bio)
@@ -214,6 +335,13 @@ static void f2fs_write_end_io(struct bio *bio)
 
 		fscrypt_finalize_bounce_page(&page);
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		if (f2fs_is_compressed_page(page)) {
+			f2fs_compress_write_end_io(bio, page);
+			continue;
+		}
+#endif
+
 		if (unlikely(bio->bi_status)) {
 			mapping_set_error(page->mapping, -EIO);
 			if (type == F2FS_WB_CP_DATA)
@@ -358,6 +486,12 @@ submit_io:
 	submit_bio(bio);
 }
 
+void f2fs_submit_bio(struct f2fs_sb_info *sbi,
+				struct bio *bio, enum page_type type)
+{
+	__submit_bio(sbi, bio, type);
+}
+
 static void __submit_merged_bio(struct f2fs_bio_info *io)
 {
 	struct f2fs_io_info *fio = &io->fio;
@@ -380,7 +514,6 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
 						struct page *page, nid_t ino)
 {
 	struct bio_vec *bvec;
-	struct page *target;
 	struct bvec_iter_all iter_all;
 
 	if (!bio)
@@ -390,10 +523,18 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode,
 		return true;
 
 	bio_for_each_segment_all(bvec, bio, iter_all) {
+		struct page *target = bvec->bv_page;
 
-		target = bvec->bv_page;
-		if (fscrypt_is_bounce_page(target))
+		if (fscrypt_is_bounce_page(target)) {
 			target = fscrypt_pagecache_page(target);
+			if (IS_ERR(target))
+				continue;
+		}
+		if (f2fs_is_compressed_page(target)) {
+			target = f2fs_compress_control_page(target);
+			if (IS_ERR(target))
+				continue;
+		}
 
 		if (inode && inode == target->mapping->host)
 			return true;
@@ -588,7 +729,8 @@ static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
 
 			found = true;
 
-			if (bio_add_page(*bio, page, PAGE_SIZE, 0) == PAGE_SIZE) {
+			if (bio_add_page(*bio, page, PAGE_SIZE, 0) ==
+							PAGE_SIZE) {
 				ret = 0;
 				break;
 			}
@@ -728,7 +870,12 @@ next:
 
 	verify_fio_blkaddr(fio);
 
-	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+	if (fio->encrypted_page)
+		bio_page = fio->encrypted_page;
+	else if (fio->compressed_page)
+		bio_page = fio->compressed_page;
+	else
+		bio_page = fio->page;
 
 	/* set submitted = true as a return value */
 	fio->submitted = true;
@@ -797,17 +944,16 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 
 	if (f2fs_encrypted_file(inode))
 		post_read_steps |= 1 << STEP_DECRYPT;
-
+	if (f2fs_compressed_file(inode))
+		post_read_steps |= 1 << STEP_DECOMPRESS;
 	if (f2fs_need_verity(inode, first_idx))
 		post_read_steps |= 1 << STEP_VERITY;
 
 	if (post_read_steps) {
+		/* Due to the mempool, this never fails. */
 		ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS);
-		if (!ctx) {
-			bio_put(bio);
-			return ERR_PTR(-ENOMEM);
-		}
 		ctx->bio = bio;
+		ctx->sbi = sbi;
 		ctx->enabled_steps = post_read_steps;
 		bio->bi_private = ctx;
 	}
@@ -815,6 +961,13 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
 	return bio;
 }
 
+static void f2fs_release_read_bio(struct bio *bio)
+{
+	if (bio->bi_private)
+		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
+	bio_put(bio);
+}
+
 /* This can handle encryption stuffs */
 static int f2fs_submit_page_read(struct inode *inode, struct page *page,
 							block_t blkaddr)
@@ -1180,19 +1333,6 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	int err = 0;
 	bool direct_io = iocb->ki_flags & IOCB_DIRECT;
 
-	/* convert inline data for Direct I/O*/
-	if (direct_io) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
-	}
-
-	if (direct_io && allow_outplace_dio(inode, iocb, from))
-		return 0;
-
-	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
-		return 0;
-
 	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
 	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
 	if (map.m_len > map.m_lblk)
@@ -1872,6 +2012,144 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
+				unsigned nr_pages, sector_t *last_block_in_bio,
+				bool is_readahead)
+{
+	struct dnode_of_data dn;
+	struct inode *inode = cc->inode;
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct bio *bio = *bio_ret;
+	unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size;
+	sector_t last_block_in_file;
+	const unsigned blkbits = inode->i_blkbits;
+	const unsigned blocksize = 1 << blkbits;
+	struct decompress_io_ctx *dic = NULL;
+	int i;
+	int ret = 0;
+
+	f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
+
+	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
+
+	/* get rid of pages beyond EOF */
+	for (i = 0; i < cc->cluster_size; i++) {
+		struct page *page = cc->rpages[i];
+
+		if (!page)
+			continue;
+		if ((sector_t)page->index >= last_block_in_file) {
+			zero_user_segment(page, 0, PAGE_SIZE);
+			if (!PageUptodate(page))
+				SetPageUptodate(page);
+		} else if (!PageUptodate(page)) {
+			continue;
+		}
+		unlock_page(page);
+		cc->rpages[i] = NULL;
+		cc->nr_rpages--;
+	}
+
+	/* we are done since all pages are beyond EOF */
+	if (f2fs_cluster_is_empty(cc))
+		goto out;
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
+	if (ret)
+		goto out;
+
+	/* cluster was overwritten as normal cluster */
+	if (dn.data_blkaddr != COMPRESS_ADDR)
+		goto out;
+
+	for (i = 1; i < cc->cluster_size; i++) {
+		block_t blkaddr;
+
+		blkaddr = datablock_addr(dn.inode, dn.node_page,
+						dn.ofs_in_node + i);
+
+		if (!__is_valid_data_blkaddr(blkaddr))
+			break;
+
+		if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
+			ret = -EFAULT;
+			goto out_put_dnode;
+		}
+		cc->nr_cpages++;
+	}
+
+	/* nothing to decompress */
+	if (cc->nr_cpages == 0) {
+		ret = 0;
+		goto out_put_dnode;
+	}
+
+	dic = f2fs_alloc_dic(cc);
+	if (IS_ERR(dic)) {
+		ret = PTR_ERR(dic);
+		goto out_put_dnode;
+	}
+
+	for (i = 0; i < dic->nr_cpages; i++) {
+		struct page *page = dic->cpages[i];
+		block_t blkaddr;
+
+		blkaddr = datablock_addr(dn.inode, dn.node_page,
+						dn.ofs_in_node + i + 1);
+
+		if (bio && !page_is_mergeable(sbi, bio,
+					*last_block_in_bio, blkaddr)) {
+submit_and_realloc:
+			__submit_bio(sbi, bio, DATA);
+			bio = NULL;
+		}
+
+		if (!bio) {
+			bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
+					is_readahead ? REQ_RAHEAD : 0,
+					page->index);
+			if (IS_ERR(bio)) {
+				ret = PTR_ERR(bio);
+				bio = NULL;
+				dic->failed = true;
+				if (refcount_sub_and_test(dic->nr_cpages - i,
+							&dic->ref))
+					f2fs_decompress_end_io(dic->rpages,
+							cc->cluster_size, true,
+							false);
+				f2fs_free_dic(dic);
+				f2fs_put_dnode(&dn);
+				*bio_ret = bio;
+				return ret;
+			}
+		}
+
+		f2fs_wait_on_block_writeback(inode, blkaddr);
+
+		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+			goto submit_and_realloc;
+
+		inc_page_count(sbi, F2FS_RD_DATA);
+		ClearPageError(page);
+		*last_block_in_bio = blkaddr;
+	}
+
+	f2fs_put_dnode(&dn);
+
+	*bio_ret = bio;
+	return 0;
+
+out_put_dnode:
+	f2fs_put_dnode(&dn);
+out:
+	f2fs_decompress_end_io(cc->rpages, cc->cluster_size, true, false);
+	*bio_ret = bio;
+	return ret;
+}
+#endif
+
 /*
  * This function was originally taken from fs/mpage.c, and customized for f2fs.
  * Major change was from block_size == page_size in f2fs by default.
@@ -1889,6 +2167,19 @@ int f2fs_mpage_readpages(struct address_space *mapping,
 	sector_t last_block_in_bio = 0;
 	struct inode *inode = mapping->host;
 	struct f2fs_map_blocks map;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	struct compress_ctx cc = {
+		.inode = inode,
+		.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+		.cluster_size = F2FS_I(inode)->i_cluster_size,
+		.cluster_idx = NULL_CLUSTER,
+		.rpages = NULL,
+		.cpages = NULL,
+		.nr_rpages = 0,
+		.nr_cpages = 0,
+	};
+#endif
+	unsigned max_nr_pages = nr_pages;
 	int ret = 0;
 
 	map.m_pblk = 0;
@@ -1912,9 +2203,41 @@ int f2fs_mpage_readpages(struct address_space *mapping,
 				goto next_page;
 		}
 
-		ret = f2fs_read_single_page(inode, page, nr_pages, &map, &bio,
-					&last_block_in_bio, is_readahead);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		if (f2fs_compressed_file(inode)) {
+			/* there are remained comressed pages, submit them */
+			if (!f2fs_cluster_can_merge_page(&cc, page->index)) {
+				ret = f2fs_read_multi_pages(&cc, &bio,
+							max_nr_pages,
+							&last_block_in_bio,
+							is_readahead);
+				f2fs_destroy_compress_ctx(&cc);
+				if (ret)
+					goto set_error_page;
+			}
+			ret = f2fs_is_compressed_cluster(inode, page->index);
+			if (ret < 0)
+				goto set_error_page;
+			else if (!ret)
+				goto read_single_page;
+
+			ret = f2fs_init_compress_ctx(&cc);
+			if (ret)
+				goto set_error_page;
+
+			f2fs_compress_ctx_add_page(&cc, page);
+
+			goto next_page;
+		}
+read_single_page:
+#endif
+
+		ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
+					&bio, &last_block_in_bio, is_readahead);
 		if (ret) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+set_error_page:
+#endif
 			SetPageError(page);
 			zero_user_segment(page, 0, PAGE_SIZE);
 			unlock_page(page);
@@ -1922,6 +2245,19 @@ int f2fs_mpage_readpages(struct address_space *mapping,
 next_page:
 		if (pages)
 			put_page(page);
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+		if (f2fs_compressed_file(inode)) {
+			/* last page */
+			if (nr_pages == 1 && !f2fs_cluster_is_empty(&cc)) {
+				ret = f2fs_read_multi_pages(&cc, &bio,
+							max_nr_pages,
+							&last_block_in_bio,
+							is_readahead);
+				f2fs_destroy_compress_ctx(&cc);
+			}
+		}
+#endif
 	}
 	BUG_ON(pages && !list_empty(pages));
 	if (bio)
@@ -1936,6 +2272,11 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
 
 	trace_f2fs_readpage(page, DATA);
 
+	if (!f2fs_is_compress_backend_ready(inode)) {
+		unlock_page(page);
+		return -EOPNOTSUPP;
+	}
+
 	/* If the file has inline data, try to read it directly */
 	if (f2fs_has_inline_data(inode))
 		ret = f2fs_read_inline_data(inode, page);
@@ -1954,6 +2295,9 @@ static int f2fs_read_data_pages(struct file *file,
 
 	trace_f2fs_readpages(inode, page, nr_pages);
 
+	if (!f2fs_is_compress_backend_ready(inode))
+		return 0;
+
 	/* If the file has inline data, skip readpages */
 	if (f2fs_has_inline_data(inode))
 		return 0;
@@ -1961,22 +2305,23 @@ static int f2fs_read_data_pages(struct file *file,
 	return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
 }
 
-static int encrypt_one_page(struct f2fs_io_info *fio)
+int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
 {
 	struct inode *inode = fio->page->mapping->host;
-	struct page *mpage;
+	struct page *mpage, *page;
 	gfp_t gfp_flags = GFP_NOFS;
 
 	if (!f2fs_encrypted_file(inode))
 		return 0;
 
+	page = fio->compressed_page ? fio->compressed_page : fio->page;
+
 	/* wait for GCed page writeback via META_MAPPING */
 	f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
 
 retry_encrypt:
-	fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(fio->page,
-							       PAGE_SIZE, 0,
-							       gfp_flags);
+	fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page,
+					PAGE_SIZE, 0, gfp_flags);
 	if (IS_ERR(fio->encrypted_page)) {
 		/* flush pending IOs and wait for a while in the ENOMEM case */
 		if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
@@ -2136,7 +2481,7 @@ got_it:
 	if (ipu_force ||
 		(__is_valid_data_blkaddr(fio->old_blkaddr) &&
 					need_inplace_update(fio))) {
-		err = encrypt_one_page(fio);
+		err = f2fs_encrypt_one_page(fio);
 		if (err)
 			goto out_writepage;
 
@@ -2172,13 +2517,16 @@ got_it:
 
 	fio->version = ni.version;
 
-	err = encrypt_one_page(fio);
+	err = f2fs_encrypt_one_page(fio);
 	if (err)
 		goto out_writepage;
 
 	set_page_writeback(page);
 	ClearPageError(page);
 
+	if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
+		f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
+
 	/* LFS mode write path */
 	f2fs_outplace_write_data(&dn, fio);
 	trace_f2fs_do_write_data_page(page, OPU);
@@ -2193,16 +2541,17 @@ out:
 	return err;
 }
 
-static int __write_data_page(struct page *page, bool *submitted,
+int f2fs_write_single_data_page(struct page *page, int *submitted,
 				struct bio **bio,
 				sector_t *last_block,
 				struct writeback_control *wbc,
-				enum iostat_type io_type)
+				enum iostat_type io_type,
+				int compr_blocks)
 {
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	loff_t i_size = i_size_read(inode);
-	const pgoff_t end_index = ((unsigned long long) i_size)
+	const pgoff_t end_index = ((unsigned long long)i_size)
 							>> PAGE_SHIFT;
 	loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
 	unsigned offset = 0;
@@ -2218,6 +2567,7 @@ static int __write_data_page(struct page *page, bool *submitted,
 		.page = page,
 		.encrypted_page = NULL,
 		.submitted = false,
+		.compr_blocks = compr_blocks,
 		.need_lock = LOCK_RETRY,
 		.io_type = io_type,
 		.io_wbc = wbc,
@@ -2242,7 +2592,9 @@ static int __write_data_page(struct page *page, bool *submitted,
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 
-	if (page->index < end_index || f2fs_verity_in_progress(inode))
+	if (page->index < end_index ||
+			f2fs_verity_in_progress(inode) ||
+			compr_blocks)
 		goto write;
 
 	/*
@@ -2318,7 +2670,6 @@ out:
 		f2fs_remove_dirty_inode(inode);
 		submitted = NULL;
 	}
-
 	unlock_page(page);
 	if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
 					!F2FS_I(inode)->cp_task)
@@ -2331,7 +2682,7 @@ out:
 	}
 
 	if (submitted)
-		*submitted = fio.submitted;
+		*submitted = fio.submitted ? 1 : 0;
 
 	return 0;
 
@@ -2352,7 +2703,23 @@ redirty_out:
 static int f2fs_write_data_page(struct page *page,
 					struct writeback_control *wbc)
 {
-	return __write_data_page(page, NULL, NULL, NULL, wbc, FS_DATA_IO);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	struct inode *inode = page->mapping->host;
+
+	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
+		goto out;
+
+	if (f2fs_compressed_file(inode)) {
+		if (f2fs_is_compressed_cluster(inode, page->index)) {
+			redirty_page_for_writepage(wbc, page);
+			return AOP_WRITEPAGE_ACTIVATE;
+		}
+	}
+out:
+#endif
+
+	return f2fs_write_single_data_page(page, NULL, NULL, NULL,
+						wbc, FS_DATA_IO, 0);
 }
 
 /*
@@ -2365,11 +2732,27 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 					enum iostat_type io_type)
 {
 	int ret = 0;
-	int done = 0;
+	int done = 0, retry = 0;
 	struct pagevec pvec;
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	struct bio *bio = NULL;
 	sector_t last_block;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	struct inode *inode = mapping->host;
+	struct compress_ctx cc = {
+		.inode = inode,
+		.log_cluster_size = F2FS_I(inode)->i_log_cluster_size,
+		.cluster_size = F2FS_I(inode)->i_cluster_size,
+		.cluster_idx = NULL_CLUSTER,
+		.rpages = NULL,
+		.nr_rpages = 0,
+		.cpages = NULL,
+		.rbuf = NULL,
+		.cbuf = NULL,
+		.rlen = PAGE_SIZE * F2FS_I(inode)->i_cluster_size,
+		.private = NULL,
+	};
+#endif
 	int nr_pages;
 	pgoff_t uninitialized_var(writeback_index);
 	pgoff_t index;
@@ -2379,6 +2762,8 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	int range_whole = 0;
 	xa_mark_t tag;
 	int nwritten = 0;
+	int submitted = 0;
+	int i;
 
 	pagevec_init(&pvec);
 
@@ -2408,12 +2793,11 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	else
 		tag = PAGECACHE_TAG_DIRTY;
 retry:
+	retry = 0;
 	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
 		tag_pages_for_writeback(mapping, index, end);
 	done_index = index;
-	while (!done && (index <= end)) {
-		int i;
-
+	while (!done && !retry && (index <= end)) {
 		nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
 				tag);
 		if (nr_pages == 0)
@@ -2421,15 +2805,62 @@ retry:
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
-			bool submitted = false;
+			bool need_readd;
+readd:
+			need_readd = false;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+			if (f2fs_compressed_file(inode)) {
+				ret = f2fs_init_compress_ctx(&cc);
+				if (ret) {
+					done = 1;
+					break;
+				}
+
+				if (!f2fs_cluster_can_merge_page(&cc,
+								page->index)) {
+					ret = f2fs_write_multi_pages(&cc,
+						&submitted, wbc, io_type);
+					if (!ret)
+						need_readd = true;
+					goto result;
+				}
 
+				if (unlikely(f2fs_cp_error(sbi)))
+					goto lock_page;
+
+				if (f2fs_cluster_is_empty(&cc)) {
+					void *fsdata = NULL;
+					struct page *pagep;
+					int ret2;
+
+					ret2 = f2fs_prepare_compress_overwrite(
+							inode, &pagep,
+							page->index, &fsdata);
+					if (ret2 < 0) {
+						ret = ret2;
+						done = 1;
+						break;
+					} else if (ret2 &&
+						!f2fs_compress_write_end(inode,
+								fsdata, page->index,
+								1)) {
+						retry = 1;
+						break;
+					}
+				} else {
+					goto lock_page;
+				}
+			}
+#endif
 			/* give a priority to WB_SYNC threads */
 			if (atomic_read(&sbi->wb_sync_req[DATA]) &&
 					wbc->sync_mode == WB_SYNC_NONE) {
 				done = 1;
 				break;
 			}
-
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+lock_page:
+#endif
 			done_index = page->index;
 retry_write:
 			lock_page(page);
@@ -2456,45 +2887,71 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = __write_data_page(page, &submitted, &bio,
-					&last_block, wbc, io_type);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+			if (f2fs_compressed_file(inode)) {
+				get_page(page);
+				f2fs_compress_ctx_add_page(&cc, page);
+				continue;
+			}
+#endif
+			ret = f2fs_write_single_data_page(page, &submitted,
+					&bio, &last_block, wbc, io_type, 0);
+			if (ret == AOP_WRITEPAGE_ACTIVATE)
+				unlock_page(page);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+result:
+#endif
+			nwritten += submitted;
+			wbc->nr_to_write -= submitted;
+
 			if (unlikely(ret)) {
 				/*
 				 * keep nr_to_write, since vfs uses this to
 				 * get # of written pages.
 				 */
 				if (ret == AOP_WRITEPAGE_ACTIVATE) {
-					unlock_page(page);
 					ret = 0;
-					continue;
+					goto next;
 				} else if (ret == -EAGAIN) {
 					ret = 0;
 					if (wbc->sync_mode == WB_SYNC_ALL) {
 						cond_resched();
 						congestion_wait(BLK_RW_ASYNC,
-									HZ/50);
+								HZ/50);
 						goto retry_write;
 					}
-					continue;
+					goto next;
 				}
 				done_index = page->index + 1;
 				done = 1;
 				break;
-			} else if (submitted) {
-				nwritten++;
 			}
 
-			if (--wbc->nr_to_write <= 0 &&
+			if (wbc->nr_to_write <= 0 &&
 					wbc->sync_mode == WB_SYNC_NONE) {
 				done = 1;
 				break;
 			}
+next:
+			if (need_readd)
+				goto readd;
 		}
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-
-	if (!cycled && !done) {
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	/* flush remained pages in compress cluster */
+	if (f2fs_compressed_file(inode) && !f2fs_cluster_is_empty(&cc)) {
+		ret = f2fs_write_multi_pages(&cc, &submitted, wbc, io_type);
+		nwritten += submitted;
+		wbc->nr_to_write -= submitted;
+		if (ret) {
+			done = 1;
+			retry = 0;
+		}
+	}
+#endif
+	if ((!cycled && !done) || retry) {
 		cycled = 1;
 		index = 0;
 		end = writeback_index - 1;
@@ -2518,6 +2975,8 @@ static inline bool __should_serialize_io(struct inode *inode,
 {
 	if (!S_ISREG(inode->i_mode))
 		return false;
+	if (f2fs_compressed_file(inode))
+		return true;
 	if (IS_NOQUOTA(inode))
 		return false;
 	/* to avoid deadlock in path of data flush */
@@ -2613,14 +3072,16 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 	struct inode *inode = mapping->host;
 	loff_t i_size = i_size_read(inode);
 
+	if (IS_NOQUOTA(inode))
+		return;
+
 	/* In the fs-verity case, f2fs_end_enable_verity() does the truncate */
 	if (to > i_size && !f2fs_verity_in_progress(inode)) {
 		down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 		down_write(&F2FS_I(inode)->i_mmap_sem);
 
 		truncate_pagecache(inode, i_size);
-		if (!IS_NOQUOTA(inode))
-			f2fs_truncate_blocks(inode, i_size, true);
+		f2fs_truncate_blocks(inode, i_size, true);
 
 		up_write(&F2FS_I(inode)->i_mmap_sem);
 		up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
@@ -2660,6 +3121,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 		__do_map_lock(sbi, flag, true);
 		locked = true;
 	}
+
 restart:
 	/* check inline_data */
 	ipage = f2fs_get_node_page(sbi, inode->i_ino);
@@ -2750,6 +3212,24 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 		if (err)
 			goto fail;
 	}
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (f2fs_compressed_file(inode)) {
+		int ret;
+
+		*fsdata = NULL;
+
+		ret = f2fs_prepare_compress_overwrite(inode, pagep,
+							index, fsdata);
+		if (ret < 0) {
+			err = ret;
+			goto fail;
+		} else if (ret) {
+			return 0;
+		}
+	}
+#endif
+
 repeat:
 	/*
 	 * Do not use grab_cache_page_write_begin() to avoid deadlock due to
@@ -2762,6 +3242,8 @@ repeat:
 		goto fail;
 	}
 
+	/* TODO: cluster can be compressed due to race with .writepage */
+
 	*pagep = page;
 
 	err = prepare_write_begin(sbi, page, pos, len,
@@ -2845,6 +3327,16 @@ static int f2fs_write_end(struct file *file,
 		else
 			SetPageUptodate(page);
 	}
+
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	/* overwrite compressed file */
+	if (f2fs_compressed_file(inode) && fsdata) {
+		f2fs_compress_write_end(inode, fsdata, page->index, copied);
+		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+		return copied;
+	}
+#endif
+
 	if (!copied)
 		goto unlock_out;
 
@@ -3145,7 +3637,8 @@ int f2fs_migrate_page(struct address_space *mapping,
 
 #ifdef CONFIG_SWAP
 /* Copied from generic_swapfile_activate() to check any holes */
-static int check_swap_activate(struct file *swap_file, unsigned int max)
+static int check_swap_activate(struct swap_info_struct *sis,
+				struct file *swap_file, sector_t *span)
 {
 	struct address_space *mapping = swap_file->f_mapping;
 	struct inode *inode = mapping->host;
@@ -3156,6 +3649,8 @@ static int check_swap_activate(struct file *swap_file, unsigned int max)
 	sector_t last_block;
 	sector_t lowest_block = -1;
 	sector_t highest_block = 0;
+	int nr_extents = 0;
+	int ret;
 
 	blkbits = inode->i_blkbits;
 	blocks_per_page = PAGE_SIZE >> blkbits;
@@ -3167,7 +3662,8 @@ static int check_swap_activate(struct file *swap_file, unsigned int max)
 	probe_block = 0;
 	page_no = 0;
 	last_block = i_size_read(inode) >> blkbits;
-	while ((probe_block + blocks_per_page) <= last_block && page_no < max) {
+	while ((probe_block + blocks_per_page) <= last_block &&
+			page_no < sis->max) {
 		unsigned block_in_page;
 		sector_t first_block;
 
@@ -3207,13 +3703,27 @@ static int check_swap_activate(struct file *swap_file, unsigned int max)
 				highest_block = first_block;
 		}
 
+		/*
+		 * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+		 */
+		ret = add_swap_extent(sis, page_no, 1, first_block);
+		if (ret < 0)
+			goto out;
+		nr_extents += ret;
 		page_no++;
 		probe_block += blocks_per_page;
 reprobe:
 		continue;
 	}
-	return 0;
-
+	ret = nr_extents;
+	*span = 1 + highest_block - lowest_block;
+	if (page_no == 0)
+		page_no = 1;	/* force Empty message */
+	sis->max = page_no;
+	sis->pages = page_no - 1;
+	sis->highest_bit = page_no - 1;
+out:
+	return ret;
 bad_bmap:
 	pr_err("swapon: swapfile has holes\n");
 	return -EINVAL;
@@ -3235,14 +3745,17 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	if (ret)
 		return ret;
 
-	ret = check_swap_activate(file, sis->max);
-	if (ret)
+	if (f2fs_disable_compressed_file(inode))
+		return -EINVAL;
+
+	ret = check_swap_activate(sis, file, span);
+	if (ret < 0)
 		return ret;
 
 	set_inode_flag(inode, FI_PIN_FILE);
 	f2fs_precache_extents(inode);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-	return 0;
+	return ret;
 }
 
 static void f2fs_swap_deactivate(struct file *file)
@@ -3319,6 +3832,27 @@ void f2fs_destroy_post_read_processing(void)
 	kmem_cache_destroy(bio_post_read_ctx_cache);
 }
 
+int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi)
+{
+	if (!f2fs_sb_has_encrypt(sbi) &&
+		!f2fs_sb_has_verity(sbi) &&
+		!f2fs_sb_has_compression(sbi))
+		return 0;
+
+	sbi->post_read_wq = alloc_workqueue("f2fs_post_read_wq",
+						 WQ_UNBOUND | WQ_HIGHPRI,
+						 num_online_cpus());
+	if (!sbi->post_read_wq)
+		return -ENOMEM;
+	return 0;
+}
+
+void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi)
+{
+	if (sbi->post_read_wq)
+		destroy_workqueue(sbi->post_read_wq);
+}
+
 int __init f2fs_init_bio_entry_cache(void)
 {
 	bio_entry_slab = f2fs_kmem_cache_create("bio_entry_slab",
@@ -3328,7 +3862,7 @@ int __init f2fs_init_bio_entry_cache(void)
 	return 0;
 }
 
-void __exit f2fs_destroy_bio_entry_cache(void)
+void f2fs_destroy_bio_entry_cache(void)
 {
 	kmem_cache_destroy(bio_entry_slab);
 }
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 9b0bedd82581..6b89eae5e4ca 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -21,9 +21,45 @@
 #include "gc.h"
 
 static LIST_HEAD(f2fs_stat_list);
-static struct dentry *f2fs_debugfs_root;
 static DEFINE_MUTEX(f2fs_stat_mutex);
+#ifdef CONFIG_DEBUG_FS
+static struct dentry *f2fs_debugfs_root;
+#endif
+
+/*
+ * This function calculates BDF of every segments
+ */
+void f2fs_update_sit_info(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+	unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
+	unsigned long long bimodal, dist;
+	unsigned int segno, vblocks;
+	int ndirty = 0;
+
+	bimodal = 0;
+	total_vblocks = 0;
+	blks_per_sec = BLKS_PER_SEC(sbi);
+	hblks_per_sec = blks_per_sec / 2;
+	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
+		vblocks = get_valid_blocks(sbi, segno, true);
+		dist = abs(vblocks - hblks_per_sec);
+		bimodal += dist * dist;
+
+		if (vblocks > 0 && vblocks < blks_per_sec) {
+			total_vblocks += vblocks;
+			ndirty++;
+		}
+	}
+	dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
+	si->bimodal = div64_u64(bimodal, dist);
+	if (si->dirty_count)
+		si->avg_vblocks = div_u64(total_vblocks, ndirty);
+	else
+		si->avg_vblocks = 0;
+}
 
+#ifdef CONFIG_DEBUG_FS
 static void update_general_status(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = F2FS_STAT(sbi);
@@ -56,7 +92,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->nquota_files = sbi->nquota_files;
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
-	si->aw_cnt = atomic_read(&sbi->aw_cnt);
+	si->aw_cnt = sbi->atomic_files;
 	si->vw_cnt = atomic_read(&sbi->vw_cnt);
 	si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
 	si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
@@ -94,6 +130,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->inline_xattr = atomic_read(&sbi->inline_xattr);
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->compr_inode = atomic_read(&sbi->compr_inode);
+	si->compr_blocks = atomic_read(&sbi->compr_blocks);
 	si->append = sbi->im[APPEND_INO].ino_num;
 	si->update = sbi->im[UPDATE_INO].ino_num;
 	si->orphans = sbi->im[ORPHAN_INO].ino_num;
@@ -114,7 +152,6 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
 	si->avail_nids = NM_I(sbi)->available_nids;
 	si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
-	si->bg_gc = sbi->bg_gc;
 	si->io_skip_bggc = sbi->io_skip_bggc;
 	si->other_skip_bggc = sbi->other_skip_bggc;
 	si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC];
@@ -146,39 +183,6 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 }
 
 /*
- * This function calculates BDF of every segments
- */
-static void update_sit_info(struct f2fs_sb_info *sbi)
-{
-	struct f2fs_stat_info *si = F2FS_STAT(sbi);
-	unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
-	unsigned long long bimodal, dist;
-	unsigned int segno, vblocks;
-	int ndirty = 0;
-
-	bimodal = 0;
-	total_vblocks = 0;
-	blks_per_sec = BLKS_PER_SEC(sbi);
-	hblks_per_sec = blks_per_sec / 2;
-	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
-		vblocks = get_valid_blocks(sbi, segno, true);
-		dist = abs(vblocks - hblks_per_sec);
-		bimodal += dist * dist;
-
-		if (vblocks > 0 && vblocks < blks_per_sec) {
-			total_vblocks += vblocks;
-			ndirty++;
-		}
-	}
-	dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
-	si->bimodal = div64_u64(bimodal, dist);
-	if (si->dirty_count)
-		si->avg_vblocks = div_u64(total_vblocks, ndirty);
-	else
-		si->avg_vblocks = 0;
-}
-
-/*
  * This function calculates memory footprint.
  */
 static void update_mem_info(struct f2fs_sb_info *sbi)
@@ -315,6 +319,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
+		seq_printf(s, "  - Compressed Inode: %u, Blocks: %u\n",
+			   si->compr_inode, si->compr_blocks);
 		seq_printf(s, "  - Orphan/Append/Update Inode: %u, %u, %u\n",
 			   si->orphans, si->append, si->update);
 		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
@@ -441,7 +447,7 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->block_count[LFS], si->segment_count[LFS]);
 
 		/* segment usage info */
-		update_sit_info(si->sbi);
+		f2fs_update_sit_info(si->sbi);
 		seq_printf(s, "\nBDF: %u, avg. vblocks: %u\n",
 			   si->bimodal, si->avg_vblocks);
 
@@ -461,6 +467,7 @@ static int stat_show(struct seq_file *s, void *v)
 }
 
 DEFINE_SHOW_ATTRIBUTE(stat);
+#endif
 
 int f2fs_build_stats(struct f2fs_sb_info *sbi)
 {
@@ -491,11 +498,12 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	atomic_set(&sbi->inline_xattr, 0);
 	atomic_set(&sbi->inline_inode, 0);
 	atomic_set(&sbi->inline_dir, 0);
+	atomic_set(&sbi->compr_inode, 0);
+	atomic_set(&sbi->compr_blocks, 0);
 	atomic_set(&sbi->inplace_count, 0);
 	for (i = META_CP; i < META_MAX; i++)
 		atomic_set(&sbi->meta_count[i], 0);
 
-	atomic_set(&sbi->aw_cnt, 0);
 	atomic_set(&sbi->vw_cnt, 0);
 	atomic_set(&sbi->max_aw_cnt, 0);
 	atomic_set(&sbi->max_vw_cnt, 0);
@@ -520,14 +528,18 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 
 void __init f2fs_create_root_stats(void)
 {
+#ifdef CONFIG_DEBUG_FS
 	f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
 
 	debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL,
 			    &stat_fops);
+#endif
 }
 
 void f2fs_destroy_root_stats(void)
 {
+#ifdef CONFIG_DEBUG_FS
 	debugfs_remove_recursive(f2fs_debugfs_root);
 	f2fs_debugfs_root = NULL;
+#endif
 }
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index d9ad842945df..27d0dd7a16d6 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -578,6 +578,20 @@ next:
 	goto next;
 }
 
+bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
+					struct fscrypt_name *fname)
+{
+	struct f2fs_dentry_ptr d;
+	unsigned int bit_pos;
+	int slots = GET_DENTRY_SLOTS(fname_len(fname));
+
+	make_dentry_ptr_inline(dir, &d, inline_data_addr(dir, ipage));
+
+	bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
+
+	return bit_pos < d.max;
+}
+
 void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 				const struct qstr *name, f2fs_hash_t name_hash,
 				unsigned int bit_pos)
@@ -1069,24 +1083,27 @@ static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
 			  const char *str, const struct qstr *name)
 {
 	struct qstr qstr = {.name = str, .len = len };
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
 
-	if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) {
+	if (!inode || !IS_CASEFOLDED(inode)) {
 		if (len != name->len)
 			return -1;
-		return memcmp(str, name, len);
+		return memcmp(str, name->name, len);
 	}
 
-	return f2fs_ci_compare(dentry->d_parent->d_inode, name, &qstr, false);
+	return f2fs_ci_compare(inode, name, &qstr, false);
 }
 
 static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
 	const struct unicode_map *um = sbi->s_encoding;
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
 	unsigned char *norm;
 	int len, ret = 0;
 
-	if (!IS_CASEFOLDED(dentry->d_inode))
+	if (!inode || !IS_CASEFOLDED(inode))
 		return 0;
 
 	norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 059ade83bfb1..5355be6b6755 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -116,6 +116,8 @@ typedef u32 block_t;	/*
 			 */
 typedef u32 nid_t;
 
+#define COMPRESS_EXT_NUM		16
+
 struct f2fs_mount_info {
 	unsigned int opt;
 	int write_io_size_bits;		/* Write IO size bits */
@@ -140,6 +142,12 @@ struct f2fs_mount_info {
 	block_t unusable_cap;		/* Amount of space allowed to be
 					 * unusable when disabling checkpoint
 					 */
+
+	/* For compression */
+	unsigned char compress_algorithm;	/* algorithm type */
+	unsigned compress_log_size;		/* cluster log size */
+	unsigned char compress_ext_cnt;		/* extension count */
+	unsigned char extensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN];	/* extensions */
 };
 
 #define F2FS_FEATURE_ENCRYPT		0x0001
@@ -155,6 +163,7 @@ struct f2fs_mount_info {
 #define F2FS_FEATURE_VERITY		0x0400
 #define F2FS_FEATURE_SB_CHKSUM		0x0800
 #define F2FS_FEATURE_CASEFOLD		0x1000
+#define F2FS_FEATURE_COMPRESSION	0x2000
 
 #define __F2FS_HAS_FEATURE(raw_super, mask)				\
 	((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -712,6 +721,12 @@ struct f2fs_inode_info {
 	int i_inline_xattr_size;	/* inline xattr size */
 	struct timespec64 i_crtime;	/* inode creation time */
 	struct timespec64 i_disk_time[4];/* inode disk times */
+
+	/* for file compress */
+	u64 i_compr_blocks;			/* # of compressed blocks */
+	unsigned char i_compress_algorithm;	/* algorithm type */
+	unsigned char i_log_cluster_size;	/* log of cluster size */
+	unsigned int i_cluster_size;		/* cluster size */
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -1018,6 +1033,7 @@ enum need_lock_type {
 enum cp_reason_type {
 	CP_NO_NEEDED,
 	CP_NON_REGULAR,
+	CP_COMPRESSED,
 	CP_HARDLINK,
 	CP_SB_NEED_CP,
 	CP_WRONG_PINO,
@@ -1056,12 +1072,15 @@ struct f2fs_io_info {
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
+	struct page *compressed_page;	/* compressed page */
 	struct list_head list;		/* serialize IOs */
 	bool submitted;		/* indicate IO submission */
 	int need_lock;		/* indicate we need to lock cp_rwsem */
 	bool in_list;		/* indicate fio is in io_list */
 	bool is_por;		/* indicate IO is from recovery or not */
 	bool retry;		/* need to reallocate block address */
+	int compr_blocks;	/* # of compressed block addresses */
+	bool encrypted;		/* indicate file is encrypted */
 	enum iostat_type io_type;	/* io type */
 	struct writeback_control *io_wbc; /* writeback control */
 	struct bio **bio;		/* bio for ipu */
@@ -1169,6 +1188,18 @@ enum fsync_mode {
 	FSYNC_MODE_NOBARRIER,	/* fsync behaves nobarrier based on posix */
 };
 
+/*
+ * this value is set in page as a private data which indicate that
+ * the page is atomically written, and it is in inmem_pages list.
+ */
+#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
+#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
+
+#define IS_ATOMIC_WRITTEN_PAGE(page)			\
+		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page)			\
+		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+
 #ifdef CONFIG_FS_ENCRYPTION
 #define DUMMY_ENCRYPTION_ENABLED(sbi) \
 			(unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
@@ -1176,6 +1207,75 @@ enum fsync_mode {
 #define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
 #endif
 
+/* For compression */
+enum compress_algorithm_type {
+	COMPRESS_LZO,
+	COMPRESS_LZ4,
+	COMPRESS_MAX,
+};
+
+#define COMPRESS_DATA_RESERVED_SIZE		4
+struct compress_data {
+	__le32 clen;			/* compressed data size */
+	__le32 chksum;			/* checksum of compressed data */
+	__le32 reserved[COMPRESS_DATA_RESERVED_SIZE];	/* reserved */
+	u8 cdata[];			/* compressed data */
+};
+
+#define COMPRESS_HEADER_SIZE	(sizeof(struct compress_data))
+
+#define F2FS_COMPRESSED_PAGE_MAGIC	0xF5F2C000
+
+/* compress context */
+struct compress_ctx {
+	struct inode *inode;		/* inode the context belong to */
+	pgoff_t cluster_idx;		/* cluster index number */
+	unsigned int cluster_size;	/* page count in cluster */
+	unsigned int log_cluster_size;	/* log of cluster size */
+	struct page **rpages;		/* pages store raw data in cluster */
+	unsigned int nr_rpages;		/* total page number in rpages */
+	struct page **cpages;		/* pages store compressed data in cluster */
+	unsigned int nr_cpages;		/* total page number in cpages */
+	void *rbuf;			/* virtual mapped address on rpages */
+	struct compress_data *cbuf;	/* virtual mapped address on cpages */
+	size_t rlen;			/* valid data length in rbuf */
+	size_t clen;			/* valid data length in cbuf */
+	void *private;			/* payload buffer for specified compression algorithm */
+};
+
+/* compress context for write IO path */
+struct compress_io_ctx {
+	u32 magic;			/* magic number to indicate page is compressed */
+	struct inode *inode;		/* inode the context belong to */
+	struct page **rpages;		/* pages store raw data in cluster */
+	unsigned int nr_rpages;		/* total page number in rpages */
+	refcount_t ref;			/* referrence count of raw page */
+};
+
+/* decompress io context for read IO path */
+struct decompress_io_ctx {
+	u32 magic;			/* magic number to indicate page is compressed */
+	struct inode *inode;		/* inode the context belong to */
+	pgoff_t cluster_idx;		/* cluster index number */
+	unsigned int cluster_size;	/* page count in cluster */
+	unsigned int log_cluster_size;	/* log of cluster size */
+	struct page **rpages;		/* pages store raw data in cluster */
+	unsigned int nr_rpages;		/* total page number in rpages */
+	struct page **cpages;		/* pages store compressed data in cluster */
+	unsigned int nr_cpages;		/* total page number in cpages */
+	struct page **tpages;		/* temp pages to pad holes in cluster */
+	void *rbuf;			/* virtual mapped address on rpages */
+	struct compress_data *cbuf;	/* virtual mapped address on cpages */
+	size_t rlen;			/* valid data length in rbuf */
+	size_t clen;			/* valid data length in cbuf */
+	refcount_t ref;			/* referrence count of compressed page */
+	bool failed;			/* indicate IO error during decompression */
+};
+
+#define NULL_CLUSTER			((unsigned int)(~0))
+#define MIN_COMPRESS_LOG_SIZE		2
+#define MAX_COMPRESS_LOG_SIZE		8
+
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
@@ -1291,7 +1391,10 @@ struct f2fs_sb_info {
 	struct f2fs_mount_info mount_opt;	/* mount options */
 
 	/* for cleaning operations */
-	struct mutex gc_mutex;			/* mutex for GC */
+	struct rw_semaphore gc_lock;		/*
+						 * semaphore for GC, avoid
+						 * race between GC and GC or CP
+						 */
 	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
 	unsigned int cur_victim_sec;		/* current victim section num */
 	unsigned int gc_mode;			/* current GC state */
@@ -1327,11 +1430,11 @@ struct f2fs_sb_info {
 	atomic_t inline_xattr;			/* # of inline_xattr inodes */
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
-	atomic_t aw_cnt;			/* # of atomic writes */
+	atomic_t compr_inode;			/* # of compressed inodes */
+	atomic_t compr_blocks;			/* # of compressed blocks */
 	atomic_t vw_cnt;			/* # of volatile writes */
 	atomic_t max_aw_cnt;			/* max # of atomic writes */
 	atomic_t max_vw_cnt;			/* max # of volatile writes */
-	int bg_gc;				/* background gc calls */
 	unsigned int io_skip_bggc;		/* skip background gc for in-flight IO */
 	unsigned int other_skip_bggc;		/* skip background gc for other reasons */
 	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
@@ -1365,6 +1468,8 @@ struct f2fs_sb_info {
 
 	/* Precomputed FS UUID checksum for seeding other checksums */
 	__u32 s_chksum_seed;
+
+	struct workqueue_struct *post_read_wq;	/* post read workqueue */
 };
 
 struct f2fs_private_dio {
@@ -2222,26 +2327,6 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
 	return entry;
 }
 
-static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi,
-						int npages, bool no_fail)
-{
-	struct bio *bio;
-
-	if (no_fail) {
-		/* No failure on bio allocation */
-		bio = bio_alloc(GFP_NOIO, npages);
-		if (!bio)
-			bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
-		return bio;
-	}
-	if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
-		f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
-		return NULL;
-	}
-
-	return bio_alloc(GFP_KERNEL, npages);
-}
-
 static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
 {
 	if (sbi->gc_mode == GC_URGENT)
@@ -2378,11 +2463,13 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
 /*
  * On-disk inode flags (f2fs_inode::i_flags)
  */
+#define F2FS_COMPR_FL			0x00000004 /* Compress file */
 #define F2FS_SYNC_FL			0x00000008 /* Synchronous updates */
 #define F2FS_IMMUTABLE_FL		0x00000010 /* Immutable file */
 #define F2FS_APPEND_FL			0x00000020 /* writes to file may only append */
 #define F2FS_NODUMP_FL			0x00000040 /* do not dump file */
 #define F2FS_NOATIME_FL			0x00000080 /* do not update atime */
+#define F2FS_NOCOMP_FL			0x00000400 /* Don't compress */
 #define F2FS_INDEX_FL			0x00001000 /* hash-indexed directory */
 #define F2FS_DIRSYNC_FL			0x00010000 /* dirsync behaviour (directories only) */
 #define F2FS_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
@@ -2391,7 +2478,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
 /* Flags that should be inherited by new inodes from their parent. */
 #define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \
 			   F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
-			   F2FS_CASEFOLD_FL)
+			   F2FS_CASEFOLD_FL | F2FS_COMPR_FL | F2FS_NOCOMP_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
 #define F2FS_REG_FLMASK		(~(F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \
@@ -2443,6 +2530,8 @@ enum {
 	FI_PIN_FILE,		/* indicate file should not be gced */
 	FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */
 	FI_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
+	FI_COMPRESSED_FILE,	/* indicate file's data can be compressed */
+	FI_MMAP_FILE,		/* indicate file was mmapped */
 };
 
 static inline void __mark_inode_dirty_flag(struct inode *inode,
@@ -2459,6 +2548,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
 	case FI_DATA_EXIST:
 	case FI_INLINE_DOTS:
 	case FI_PIN_FILE:
+	case FI_COMPRESSED_FILE:
 		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 }
@@ -2614,16 +2704,27 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
 	return is_inode_flag_set(inode, FI_INLINE_XATTR);
 }
 
+static inline int f2fs_compressed_file(struct inode *inode)
+{
+	return S_ISREG(inode->i_mode) &&
+		is_inode_flag_set(inode, FI_COMPRESSED_FILE);
+}
+
 static inline unsigned int addrs_per_inode(struct inode *inode)
 {
 	unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
 				get_inline_xattr_addrs(inode);
-	return ALIGN_DOWN(addrs, 1);
+
+	if (!f2fs_compressed_file(inode))
+		return addrs;
+	return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
 }
 
 static inline unsigned int addrs_per_block(struct inode *inode)
 {
-	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, 1);
+	if (!f2fs_compressed_file(inode))
+		return DEF_ADDRS_PER_BLOCK;
+	return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size);
 }
 
 static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
@@ -2656,6 +2757,11 @@ static inline int f2fs_has_inline_dots(struct inode *inode)
 	return is_inode_flag_set(inode, FI_INLINE_DOTS);
 }
 
+static inline int f2fs_is_mmap_file(struct inode *inode)
+{
+	return is_inode_flag_set(inode, FI_MMAP_FILE);
+}
+
 static inline bool f2fs_is_pinned_file(struct inode *inode)
 {
 	return is_inode_flag_set(inode, FI_PIN_FILE);
@@ -2783,7 +2889,8 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 
 	if (!test_opt(sbi, EXTENT_CACHE) ||
-			is_inode_flag_set(inode, FI_NO_EXTENT))
+			is_inode_flag_set(inode, FI_NO_EXTENT) ||
+			is_inode_flag_set(inode, FI_COMPRESSED_FILE))
 		return false;
 
 	/*
@@ -2903,7 +3010,8 @@ static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
 
 static inline bool __is_valid_data_blkaddr(block_t blkaddr)
 {
-	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR ||
+			blkaddr == COMPRESS_ADDR)
 		return false;
 	return true;
 }
@@ -3001,6 +3109,8 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
 			struct page **page);
 void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 			struct page *page, struct inode *inode);
+bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
+			struct fscrypt_name *fname);
 void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 			const struct qstr *name, f2fs_hash_t name_hash,
 			unsigned int bit_pos);
@@ -3155,6 +3265,8 @@ void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
 int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 			unsigned int val, int alloc);
 void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
 int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
 void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
 int __init f2fs_create_segment_manager_caches(void);
@@ -3205,10 +3317,13 @@ void f2fs_destroy_checkpoint_caches(void);
 /*
  * data.c
  */
-int f2fs_init_post_read_processing(void);
-void f2fs_destroy_post_read_processing(void);
+int __init f2fs_init_bioset(void);
+void f2fs_destroy_bioset(void);
+struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, int npages, bool no_fail);
 int f2fs_init_bio_entry_cache(void);
 void f2fs_destroy_bio_entry_cache(void);
+void f2fs_submit_bio(struct f2fs_sb_info *sbi,
+				struct bio *bio, enum page_type type);
 void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
 void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
 				struct inode *inode, struct page *page,
@@ -3245,8 +3360,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 			int create, int flag);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			u64 start, u64 len);
+int f2fs_encrypt_one_page(struct f2fs_io_info *fio);
 bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
 bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
+int f2fs_write_single_data_page(struct page *page, int *submitted,
+				struct bio **bio, sector_t *last_block,
+				struct writeback_control *wbc,
+				enum iostat_type io_type,
+				int compr_blocks);
 void f2fs_invalidate_page(struct page *page, unsigned int offset,
 			unsigned int length);
 int f2fs_release_page(struct page *page, gfp_t wait);
@@ -3256,6 +3377,10 @@ int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
 #endif
 bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
 void f2fs_clear_page_cache_dirty_tag(struct page *page);
+int f2fs_init_post_read_processing(void);
+void f2fs_destroy_post_read_processing(void);
+int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
+void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
 
 /*
  * gc.c
@@ -3302,6 +3427,7 @@ struct f2fs_stat_info {
 	int nr_discard_cmd;
 	unsigned int undiscard_blks;
 	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
+	int compr_inode, compr_blocks;
 	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
 	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
 	unsigned int bimodal, avg_vblocks;
@@ -3333,7 +3459,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 #define stat_inc_cp_count(si)		((si)->cp_count++)
 #define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
 #define stat_inc_call_count(si)		((si)->call_count++)
-#define stat_inc_bggc_count(sbi)	((sbi)->bg_gc++)
+#define stat_inc_bggc_count(si)		((si)->bg_gc++)
 #define stat_io_skip_bggc_count(sbi)	((sbi)->io_skip_bggc++)
 #define stat_other_skip_bggc_count(sbi)	((sbi)->other_skip_bggc++)
 #define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
@@ -3372,6 +3498,20 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		if (f2fs_has_inline_dentry(inode))			\
 			(atomic_dec(&F2FS_I_SB(inode)->inline_dir));	\
 	} while (0)
+#define stat_inc_compr_inode(inode)					\
+	do {								\
+		if (f2fs_compressed_file(inode))			\
+			(atomic_inc(&F2FS_I_SB(inode)->compr_inode));	\
+	} while (0)
+#define stat_dec_compr_inode(inode)					\
+	do {								\
+		if (f2fs_compressed_file(inode))			\
+			(atomic_dec(&F2FS_I_SB(inode)->compr_inode));	\
+	} while (0)
+#define stat_add_compr_blocks(inode, blocks)				\
+		(atomic_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
+#define stat_sub_compr_blocks(inode, blocks)				\
+		(atomic_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
 #define stat_inc_meta_count(sbi, blkaddr)				\
 	do {								\
 		if (blkaddr < SIT_I(sbi)->sit_base_addr)		\
@@ -3389,13 +3529,9 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		((sbi)->block_count[(curseg)->alloc_type]++)
 #define stat_inc_inplace_blocks(sbi)					\
 		(atomic_inc(&(sbi)->inplace_count))
-#define stat_inc_atomic_write(inode)					\
-		(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
-#define stat_dec_atomic_write(inode)					\
-		(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
 #define stat_update_max_atomic_write(inode)				\
 	do {								\
-		int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt);	\
+		int cur = F2FS_I_SB(inode)->atomic_files;	\
 		int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt);	\
 		if (cur > max)						\
 			atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);	\
@@ -3447,6 +3583,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi);
 void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
 void __init f2fs_create_root_stats(void);
 void f2fs_destroy_root_stats(void);
+void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
 #else
 #define stat_inc_cp_count(si)				do { } while (0)
 #define stat_inc_bg_cp_count(si)			do { } while (0)
@@ -3456,8 +3593,8 @@ void f2fs_destroy_root_stats(void);
 #define stat_other_skip_bggc_count(sbi)			do { } while (0)
 #define stat_inc_dirty_inode(sbi, type)			do { } while (0)
 #define stat_dec_dirty_inode(sbi, type)			do { } while (0)
-#define stat_inc_total_hit(sb)				do { } while (0)
-#define stat_inc_rbtree_node_hit(sb)			do { } while (0)
+#define stat_inc_total_hit(sbi)				do { } while (0)
+#define stat_inc_rbtree_node_hit(sbi)			do { } while (0)
 #define stat_inc_largest_node_hit(sbi)			do { } while (0)
 #define stat_inc_cached_node_hit(sbi)			do { } while (0)
 #define stat_inc_inline_xattr(inode)			do { } while (0)
@@ -3466,6 +3603,10 @@ void f2fs_destroy_root_stats(void);
 #define stat_dec_inline_inode(inode)			do { } while (0)
 #define stat_inc_inline_dir(inode)			do { } while (0)
 #define stat_dec_inline_dir(inode)			do { } while (0)
+#define stat_inc_compr_inode(inode)			do { } while (0)
+#define stat_dec_compr_inode(inode)			do { } while (0)
+#define stat_add_compr_blocks(inode, blocks)		do { } while (0)
+#define stat_sub_compr_blocks(inode, blocks)		do { } while (0)
 #define stat_inc_atomic_write(inode)			do { } while (0)
 #define stat_dec_atomic_write(inode)			do { } while (0)
 #define stat_update_max_atomic_write(inode)		do { } while (0)
@@ -3485,6 +3626,7 @@ static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
 static inline void __init f2fs_create_root_stats(void) { }
 static inline void f2fs_destroy_root_stats(void) { }
+static inline void update_sit_info(struct f2fs_sb_info *sbi) {}
 #endif
 
 extern const struct file_operations f2fs_dir_operations;
@@ -3513,6 +3655,7 @@ void f2fs_truncate_inline_inode(struct inode *inode,
 int f2fs_read_inline_data(struct inode *inode, struct page *page);
 int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
 int f2fs_convert_inline_inode(struct inode *inode);
+int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
 int f2fs_write_inline_data(struct inode *inode, struct page *page);
 bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
 struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
@@ -3605,7 +3748,85 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode)
  */
 static inline bool f2fs_post_read_required(struct inode *inode)
 {
-	return f2fs_encrypted_file(inode) || fsverity_active(inode);
+	return f2fs_encrypted_file(inode) || fsverity_active(inode) ||
+		f2fs_compressed_file(inode);
+}
+
+/*
+ * compress.c
+ */
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+bool f2fs_is_compressed_page(struct page *page);
+struct page *f2fs_compress_control_page(struct page *page);
+int f2fs_prepare_compress_overwrite(struct inode *inode,
+			struct page **pagep, pgoff_t index, void **fsdata);
+bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
+					pgoff_t index, unsigned copied);
+void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
+bool f2fs_is_compress_backend_ready(struct inode *inode);
+void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
+bool f2fs_cluster_is_empty(struct compress_ctx *cc);
+bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
+int f2fs_write_multi_pages(struct compress_ctx *cc,
+						int *submitted,
+						struct writeback_control *wbc,
+						enum iostat_type io_type);
+int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
+int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
+				unsigned nr_pages, sector_t *last_block_in_bio,
+				bool is_readahead);
+struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
+void f2fs_free_dic(struct decompress_io_ctx *dic);
+void f2fs_decompress_end_io(struct page **rpages,
+			unsigned int cluster_size, bool err, bool verity);
+int f2fs_init_compress_ctx(struct compress_ctx *cc);
+void f2fs_destroy_compress_ctx(struct compress_ctx *cc);
+void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
+#else
+static inline bool f2fs_is_compressed_page(struct page *page) { return false; }
+static inline bool f2fs_is_compress_backend_ready(struct inode *inode)
+{
+	if (!f2fs_compressed_file(inode))
+		return true;
+	/* not support compression */
+	return false;
+}
+static inline struct page *f2fs_compress_control_page(struct page *page)
+{
+	WARN_ON_ONCE(1);
+	return ERR_PTR(-EINVAL);
+}
+#endif
+
+static inline void set_compress_context(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+	F2FS_I(inode)->i_compress_algorithm =
+			F2FS_OPTION(sbi).compress_algorithm;
+	F2FS_I(inode)->i_log_cluster_size =
+			F2FS_OPTION(sbi).compress_log_size;
+	F2FS_I(inode)->i_cluster_size =
+			1 << F2FS_I(inode)->i_log_cluster_size;
+	F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
+	set_inode_flag(inode, FI_COMPRESSED_FILE);
+	stat_inc_compr_inode(inode);
+}
+
+static inline u64 f2fs_disable_compressed_file(struct inode *inode)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
+	if (!f2fs_compressed_file(inode))
+		return 0;
+	if (fi->i_compr_blocks)
+		return fi->i_compr_blocks;
+
+	fi->i_flags &= ~F2FS_COMPR_FL;
+	clear_inode_flag(inode, FI_COMPRESSED_FILE);
+	stat_dec_compr_inode(inode);
+	return 0;
 }
 
 #define F2FS_FEATURE_FUNCS(name, flagname) \
@@ -3626,6 +3847,7 @@ F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
 F2FS_FEATURE_FUNCS(verity, VERITY);
 F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
 F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
+F2FS_FEATURE_FUNCS(compression, COMPRESSION);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
@@ -3707,6 +3929,30 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #endif
 }
 
+static inline bool f2fs_may_compress(struct inode *inode)
+{
+	if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
+				f2fs_is_atomic_file(inode) ||
+				f2fs_is_volatile_file(inode))
+		return false;
+	return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
+}
+
+static inline void f2fs_i_compr_blocks_update(struct inode *inode,
+						u64 blocks, bool add)
+{
+	int diff = F2FS_I(inode)->i_cluster_size - blocks;
+
+	if (add) {
+		F2FS_I(inode)->i_compr_blocks += diff;
+		stat_add_compr_blocks(inode, diff);
+	} else {
+		F2FS_I(inode)->i_compr_blocks -= diff;
+		stat_sub_compr_blocks(inode, diff);
+	}
+	f2fs_mark_inode_dirty_sync(inode, true);
+}
+
 static inline int block_unaligned_IO(struct inode *inode,
 				struct kiocb *iocb, struct iov_iter *iter)
 {
@@ -3738,6 +3984,8 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
 		return true;
 	if (f2fs_is_multi_device(sbi))
 		return true;
+	if (f2fs_compressed_file(inode))
+		return true;
 	/*
 	 * for blkzoned device, fallback direct IO to buffered IO, so
 	 * all IOs can be serialized by log-structured write.
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 85af112e868d..0d4da644df3b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -50,8 +50,9 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct dnode_of_data dn = { .node_changed = false };
-	int err;
+	struct dnode_of_data dn;
+	bool need_alloc = true;
+	int err = 0;
 
 	if (unlikely(f2fs_cp_error(sbi))) {
 		err = -EIO;
@@ -63,6 +64,26 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		goto err;
 	}
 
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+	if (f2fs_compressed_file(inode)) {
+		int ret = f2fs_is_compressed_cluster(inode, page->index);
+
+		if (ret < 0) {
+			err = ret;
+			goto err;
+		} else if (ret) {
+			if (ret < F2FS_I(inode)->i_cluster_size) {
+				err = -EAGAIN;
+				goto err;
+			}
+			need_alloc = false;
+		}
+	}
+#endif
+	/* should do out of any locked page */
+	if (need_alloc)
+		f2fs_balance_fs(sbi, true);
+
 	sb_start_pagefault(inode->i_sb);
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
@@ -78,15 +99,17 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 		goto out_sem;
 	}
 
-	/* block allocation */
-	__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = f2fs_get_block(&dn, page->index);
-	f2fs_put_dnode(&dn);
-	__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
-	if (err) {
-		unlock_page(page);
-		goto out_sem;
+	if (need_alloc) {
+		/* block allocation */
+		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		err = f2fs_get_block(&dn, page->index);
+		f2fs_put_dnode(&dn);
+		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+		if (err) {
+			unlock_page(page);
+			goto out_sem;
+		}
 	}
 
 	/* fill the page */
@@ -120,8 +143,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 out_sem:
 	up_read(&F2FS_I(inode)->i_mmap_sem);
 
-	f2fs_balance_fs(sbi, dn.node_changed);
-
 	sb_end_pagefault(inode->i_sb);
 err:
 	return block_page_mkwrite_return(err);
@@ -155,6 +176,8 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
 
 	if (!S_ISREG(inode->i_mode))
 		cp_reason = CP_NON_REGULAR;
+	else if (f2fs_compressed_file(inode))
+		cp_reason = CP_COMPRESSED;
 	else if (inode->i_nlink != 1)
 		cp_reason = CP_HARDLINK;
 	else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
@@ -485,6 +508,9 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
 		return -EIO;
 
+	if (!f2fs_is_compress_backend_ready(inode))
+		return -EOPNOTSUPP;
+
 	/* we don't need to use inline_data strictly */
 	err = f2fs_convert_inline_inode(inode);
 	if (err)
@@ -492,6 +518,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &f2fs_file_vm_ops;
+	set_inode_flag(inode, FI_MMAP_FILE);
 	return 0;
 }
 
@@ -502,6 +529,9 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 	if (err)
 		return err;
 
+	if (!f2fs_is_compress_backend_ready(inode))
+		return -EOPNOTSUPP;
+
 	err = fsverity_file_open(inode, filp);
 	if (err)
 		return err;
@@ -518,6 +548,9 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 	int nr_free = 0, ofs = dn->ofs_in_node, len = count;
 	__le32 *addr;
 	int base = 0;
+	bool compressed_cluster = false;
+	int cluster_index = 0, valid_blocks = 0;
+	int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
 
 	if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
 		base = get_extra_isize(dn->inode);
@@ -525,26 +558,43 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 	raw_node = F2FS_NODE(dn->node_page);
 	addr = blkaddr_in_node(raw_node) + base + ofs;
 
-	for (; count > 0; count--, addr++, dn->ofs_in_node++) {
+	/* Assumption: truncateion starts with cluster */
+	for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) {
 		block_t blkaddr = le32_to_cpu(*addr);
 
+		if (f2fs_compressed_file(dn->inode) &&
+					!(cluster_index & (cluster_size - 1))) {
+			if (compressed_cluster)
+				f2fs_i_compr_blocks_update(dn->inode,
+							valid_blocks, false);
+			compressed_cluster = (blkaddr == COMPRESS_ADDR);
+			valid_blocks = 0;
+		}
+
 		if (blkaddr == NULL_ADDR)
 			continue;
 
 		dn->data_blkaddr = NULL_ADDR;
 		f2fs_set_data_blkaddr(dn);
 
-		if (__is_valid_data_blkaddr(blkaddr) &&
-			!f2fs_is_valid_blkaddr(sbi, blkaddr,
+		if (__is_valid_data_blkaddr(blkaddr)) {
+			if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
 					DATA_GENERIC_ENHANCE))
-			continue;
+				continue;
+			if (compressed_cluster)
+				valid_blocks++;
+		}
 
-		f2fs_invalidate_blocks(sbi, blkaddr);
 		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
 			clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
+
+		f2fs_invalidate_blocks(sbi, blkaddr);
 		nr_free++;
 	}
 
+	if (compressed_cluster)
+		f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false);
+
 	if (nr_free) {
 		pgoff_t fofs;
 		/*
@@ -587,6 +637,9 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 		return 0;
 	}
 
+	if (f2fs_compressed_file(inode))
+		return 0;
+
 	page = f2fs_get_lock_data_page(inode, index, true);
 	if (IS_ERR(page))
 		return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
@@ -602,7 +655,7 @@ truncate_out:
 	return 0;
 }
 
-int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
+static int do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
@@ -667,6 +720,28 @@ free_partial:
 	return err;
 }
 
+int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
+{
+	u64 free_from = from;
+
+	/*
+	 * for compressed file, only support cluster size
+	 * aligned truncation.
+	 */
+	if (f2fs_compressed_file(inode)) {
+		size_t cluster_shift = PAGE_SHIFT +
+					F2FS_I(inode)->i_log_cluster_size;
+		size_t cluster_mask = (1 << cluster_shift) - 1;
+
+		free_from = from >> cluster_shift;
+		if (from & cluster_mask)
+			free_from++;
+		free_from <<= cluster_shift;
+	}
+
+	return do_truncate_blocks(inode, free_from, lock);
+}
+
 int f2fs_truncate(struct inode *inode)
 {
 	int err;
@@ -754,18 +829,12 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr)
 		inode->i_uid = attr->ia_uid;
 	if (ia_valid & ATTR_GID)
 		inode->i_gid = attr->ia_gid;
-	if (ia_valid & ATTR_ATIME) {
-		inode->i_atime = timestamp_truncate(attr->ia_atime,
-						  inode);
-	}
-	if (ia_valid & ATTR_MTIME) {
-		inode->i_mtime = timestamp_truncate(attr->ia_mtime,
-						  inode);
-	}
-	if (ia_valid & ATTR_CTIME) {
-		inode->i_ctime = timestamp_truncate(attr->ia_ctime,
-						  inode);
-	}
+	if (ia_valid & ATTR_ATIME)
+		inode->i_atime = attr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		inode->i_mtime = attr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		inode->i_ctime = attr->ia_ctime;
 	if (ia_valid & ATTR_MODE) {
 		umode_t mode = attr->ia_mode;
 
@@ -786,6 +855,10 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 	if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
 		return -EIO;
 
+	if ((attr->ia_valid & ATTR_SIZE) &&
+		!f2fs_is_compress_backend_ready(inode))
+		return -EOPNOTSUPP;
+
 	err = setattr_prepare(dentry, attr);
 	if (err)
 		return err;
@@ -1026,8 +1099,8 @@ next_dnode:
 	} else if (ret == -ENOENT) {
 		if (dn.max_level == 0)
 			return -ENOENT;
-		done = min((pgoff_t)ADDRS_PER_BLOCK(inode) - dn.ofs_in_node,
-									len);
+		done = min((pgoff_t)ADDRS_PER_BLOCK(inode) -
+						dn.ofs_in_node, len);
 		blkaddr += done;
 		do_replace += done;
 		goto next;
@@ -1190,13 +1263,13 @@ static int __exchange_data_block(struct inode *src_inode,
 
 		src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode),
 					array_size(olen, sizeof(block_t)),
-					GFP_KERNEL);
+					GFP_NOFS);
 		if (!src_blkaddr)
 			return -ENOMEM;
 
 		do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode),
 					array_size(olen, sizeof(int)),
-					GFP_KERNEL);
+					GFP_NOFS);
 		if (!do_replace) {
 			kvfree(src_blkaddr);
 			return -ENOMEM;
@@ -1563,7 +1636,7 @@ static int expand_inode_data(struct inode *inode, loff_t offset,
 next_alloc:
 		if (has_not_enough_free_secs(sbi, 0,
 			GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
-			mutex_lock(&sbi->gc_mutex);
+			down_write(&sbi->gc_lock);
 			err = f2fs_gc(sbi, true, false, NULL_SEGNO);
 			if (err && err != -ENODATA && err != -EAGAIN)
 				goto out_err;
@@ -1621,6 +1694,8 @@ static long f2fs_fallocate(struct file *file, int mode,
 		return -EIO;
 	if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
 		return -ENOSPC;
+	if (!f2fs_is_compress_backend_ready(inode))
+		return -EOPNOTSUPP;
 
 	/* f2fs only support ->fallocate for regular file */
 	if (!S_ISREG(inode->i_mode))
@@ -1630,6 +1705,11 @@ static long f2fs_fallocate(struct file *file, int mode,
 		(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
 		return -EOPNOTSUPP;
 
+	if (f2fs_compressed_file(inode) &&
+		(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
+			FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)))
+		return -EOPNOTSUPP;
+
 	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
 			FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
 			FALLOC_FL_INSERT_RANGE))
@@ -1719,7 +1799,40 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
 			return -ENOTEMPTY;
 	}
 
+	if (iflags & (F2FS_COMPR_FL | F2FS_NOCOMP_FL)) {
+		if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+			return -EOPNOTSUPP;
+		if ((iflags & F2FS_COMPR_FL) && (iflags & F2FS_NOCOMP_FL))
+			return -EINVAL;
+	}
+
+	if ((iflags ^ fi->i_flags) & F2FS_COMPR_FL) {
+		if (S_ISREG(inode->i_mode) &&
+			(fi->i_flags & F2FS_COMPR_FL || i_size_read(inode) ||
+						F2FS_HAS_BLOCKS(inode)))
+			return -EINVAL;
+		if (iflags & F2FS_NOCOMP_FL)
+			return -EINVAL;
+		if (iflags & F2FS_COMPR_FL) {
+			int err = f2fs_convert_inline_inode(inode);
+
+			if (err)
+				return err;
+
+			if (!f2fs_may_compress(inode))
+				return -EINVAL;
+
+			set_compress_context(inode);
+		}
+	}
+	if ((iflags ^ fi->i_flags) & F2FS_NOCOMP_FL) {
+		if (fi->i_flags & F2FS_COMPR_FL)
+			return -EINVAL;
+	}
+
 	fi->i_flags = iflags | (fi->i_flags & ~mask);
+	f2fs_bug_on(F2FS_I_SB(inode), (fi->i_flags & F2FS_COMPR_FL) &&
+					(fi->i_flags & F2FS_NOCOMP_FL));
 
 	if (fi->i_flags & F2FS_PROJINHERIT_FL)
 		set_inode_flag(inode, FI_PROJ_INHERIT);
@@ -1745,11 +1858,13 @@ static const struct {
 	u32 iflag;
 	u32 fsflag;
 } f2fs_fsflags_map[] = {
+	{ F2FS_COMPR_FL,	FS_COMPR_FL },
 	{ F2FS_SYNC_FL,		FS_SYNC_FL },
 	{ F2FS_IMMUTABLE_FL,	FS_IMMUTABLE_FL },
 	{ F2FS_APPEND_FL,	FS_APPEND_FL },
 	{ F2FS_NODUMP_FL,	FS_NODUMP_FL },
 	{ F2FS_NOATIME_FL,	FS_NOATIME_FL },
+	{ F2FS_NOCOMP_FL,	FS_NOCOMP_FL },
 	{ F2FS_INDEX_FL,	FS_INDEX_FL },
 	{ F2FS_DIRSYNC_FL,	FS_DIRSYNC_FL },
 	{ F2FS_PROJINHERIT_FL,	FS_PROJINHERIT_FL },
@@ -1757,11 +1872,13 @@ static const struct {
 };
 
 #define F2FS_GETTABLE_FS_FL (		\
+		FS_COMPR_FL |		\
 		FS_SYNC_FL |		\
 		FS_IMMUTABLE_FL |	\
 		FS_APPEND_FL |		\
 		FS_NODUMP_FL |		\
 		FS_NOATIME_FL |		\
+		FS_NOCOMP_FL |		\
 		FS_INDEX_FL |		\
 		FS_DIRSYNC_FL |		\
 		FS_PROJINHERIT_FL |	\
@@ -1772,11 +1889,13 @@ static const struct {
 		FS_CASEFOLD_FL)
 
 #define F2FS_SETTABLE_FS_FL (		\
+		FS_COMPR_FL |		\
 		FS_SYNC_FL |		\
 		FS_IMMUTABLE_FL |	\
 		FS_APPEND_FL |		\
 		FS_NODUMP_FL |		\
 		FS_NOATIME_FL |		\
+		FS_NOCOMP_FL |		\
 		FS_DIRSYNC_FL |		\
 		FS_PROJINHERIT_FL |	\
 		FS_CASEFOLD_FL)
@@ -1897,6 +2016,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 
 	inode_lock(inode);
 
+	f2fs_disable_compressed_file(inode);
+
 	if (f2fs_is_atomic_file(inode)) {
 		if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST))
 			ret = -EINVAL;
@@ -1935,7 +2056,6 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	F2FS_I(inode)->inmem_task = current;
-	stat_inc_atomic_write(inode);
 	stat_update_max_atomic_write(inode);
 out:
 	inode_unlock(inode);
@@ -2324,12 +2444,12 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 		return ret;
 
 	if (!sync) {
-		if (!mutex_trylock(&sbi->gc_mutex)) {
+		if (!down_write_trylock(&sbi->gc_lock)) {
 			ret = -EBUSY;
 			goto out;
 		}
 	} else {
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 	}
 
 	ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
@@ -2367,12 +2487,12 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
 
 do_more:
 	if (!range.sync) {
-		if (!mutex_trylock(&sbi->gc_mutex)) {
+		if (!down_write_trylock(&sbi->gc_lock)) {
 			ret = -EBUSY;
 			goto out;
 		}
 	} else {
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 	}
 
 	ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
@@ -2803,7 +2923,7 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
 	end_segno = min(start_segno + range.segments, dev_end_segno);
 
 	while (start_segno < end_segno) {
-		if (!mutex_trylock(&sbi->gc_mutex)) {
+		if (!down_write_trylock(&sbi->gc_lock)) {
 			ret = -EBUSY;
 			goto out;
 		}
@@ -3098,10 +3218,16 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
 		ret = -EAGAIN;
 		goto out;
 	}
+
 	ret = f2fs_convert_inline_inode(inode);
 	if (ret)
 		goto out;
 
+	if (f2fs_disable_compressed_file(inode)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	set_inode_flag(inode, FI_PIN_FILE);
 	ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
 done:
@@ -3350,6 +3476,17 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 }
 
+static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+
+	if (!f2fs_is_compress_backend_ready(inode))
+		return -EOPNOTSUPP;
+
+	return generic_file_read_iter(iocb, iter);
+}
+
 static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
@@ -3361,6 +3498,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		goto out;
 	}
 
+	if (!f2fs_is_compress_backend_ready(inode))
+		return -EOPNOTSUPP;
+
 	if (iocb->ki_flags & IOCB_NOWAIT) {
 		if (!inode_trylock(inode)) {
 			ret = -EAGAIN;
@@ -3389,18 +3529,41 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 				ret = -EAGAIN;
 				goto out;
 			}
-		} else {
-			preallocated = true;
-			target_size = iocb->ki_pos + iov_iter_count(from);
+			goto write;
+		}
 
-			err = f2fs_preallocate_blocks(iocb, from);
-			if (err) {
-				clear_inode_flag(inode, FI_NO_PREALLOC);
-				inode_unlock(inode);
-				ret = err;
-				goto out;
-			}
+		if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+			goto write;
+
+		if (iocb->ki_flags & IOCB_DIRECT) {
+			/*
+			 * Convert inline data for Direct I/O before entering
+			 * f2fs_direct_IO().
+			 */
+			err = f2fs_convert_inline_inode(inode);
+			if (err)
+				goto out_err;
+			/*
+			 * If force_buffere_io() is true, we have to allocate
+			 * blocks all the time, since f2fs_direct_IO will fall
+			 * back to buffered IO.
+			 */
+			if (!f2fs_force_buffered_io(inode, iocb, from) &&
+					allow_outplace_dio(inode, iocb, from))
+				goto write;
+		}
+		preallocated = true;
+		target_size = iocb->ki_pos + iov_iter_count(from);
+
+		err = f2fs_preallocate_blocks(iocb, from);
+		if (err) {
+out_err:
+			clear_inode_flag(inode, FI_NO_PREALLOC);
+			inode_unlock(inode);
+			ret = err;
+			goto out;
 		}
+write:
 		ret = __generic_file_write_iter(iocb, from);
 		clear_inode_flag(inode, FI_NO_PREALLOC);
 
@@ -3475,7 +3638,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 const struct file_operations f2fs_file_operations = {
 	.llseek		= f2fs_llseek,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= f2fs_file_read_iter,
 	.write_iter	= f2fs_file_write_iter,
 	.open		= f2fs_file_open,
 	.release	= f2fs_release_file,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index b3d399623290..db8725d473b5 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -78,18 +78,18 @@ static int gc_thread_func(void *data)
 		 */
 		if (sbi->gc_mode == GC_URGENT) {
 			wait_ms = gc_th->urgent_sleep_time;
-			mutex_lock(&sbi->gc_mutex);
+			down_write(&sbi->gc_lock);
 			goto do_gc;
 		}
 
-		if (!mutex_trylock(&sbi->gc_mutex)) {
+		if (!down_write_trylock(&sbi->gc_lock)) {
 			stat_other_skip_bggc_count(sbi);
 			goto next;
 		}
 
 		if (!is_idle(sbi, GC_TIME)) {
 			increase_sleep_time(gc_th, &wait_ms);
-			mutex_unlock(&sbi->gc_mutex);
+			up_write(&sbi->gc_lock);
 			stat_io_skip_bggc_count(sbi);
 			goto next;
 		}
@@ -99,7 +99,7 @@ static int gc_thread_func(void *data)
 		else
 			increase_sleep_time(gc_th, &wait_ms);
 do_gc:
-		stat_inc_bggc_count(sbi);
+		stat_inc_bggc_count(sbi->stat_info);
 
 		/* if return value is not zero, no victim was selected */
 		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true, NULL_SEGNO))
@@ -1049,8 +1049,10 @@ next_step:
 
 		if (phase == 3) {
 			inode = f2fs_iget(sb, dni.ino);
-			if (IS_ERR(inode) || is_bad_inode(inode))
+			if (IS_ERR(inode) || is_bad_inode(inode)) {
+				set_sbi_flag(sbi, SBI_NEED_FSCK);
 				continue;
+			}
 
 			if (!down_write_trylock(
 				&F2FS_I(inode)->i_gc_rwsem[WRITE])) {
@@ -1368,7 +1370,7 @@ stop:
 				reserved_segments(sbi),
 				prefree_segments(sbi));
 
-	mutex_unlock(&sbi->gc_mutex);
+	up_write(&sbi->gc_lock);
 
 	put_gc_inode(&gc_list);
 
@@ -1407,9 +1409,9 @@ static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
 			.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
 		};
 
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 		do_garbage_collect(sbi, segno, &gc_list, FG_GC);
-		mutex_unlock(&sbi->gc_mutex);
+		up_write(&sbi->gc_lock);
 		put_gc_inode(&gc_list);
 
 		if (get_valid_blocks(sbi, segno, true))
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 896db0416f0e..4167e5408151 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -368,7 +368,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 	struct f2fs_dentry_ptr src, dst;
 	int err;
 
-	page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
+	page = f2fs_grab_cache_page(dir->i_mapping, 0, true);
 	if (!page) {
 		f2fs_put_page(ipage, 1);
 		return -ENOMEM;
@@ -530,7 +530,7 @@ recover:
 	return err;
 }
 
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int do_convert_inline_dir(struct inode *dir, struct page *ipage,
 							void *inline_dentry)
 {
 	if (!F2FS_I(dir)->i_dir_level)
@@ -539,6 +539,44 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 		return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
 }
 
+int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+	struct page *ipage;
+	struct fscrypt_name fname;
+	void *inline_dentry = NULL;
+	int err = 0;
+
+	if (!f2fs_has_inline_dentry(dir))
+		return 0;
+
+	f2fs_lock_op(sbi);
+
+	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname);
+	if (err)
+		goto out;
+
+	ipage = f2fs_get_node_page(sbi, dir->i_ino);
+	if (IS_ERR(ipage)) {
+		err = PTR_ERR(ipage);
+		goto out;
+	}
+
+	if (f2fs_has_enough_room(dir, ipage, &fname)) {
+		f2fs_put_page(ipage, 1);
+		goto out;
+	}
+
+	inline_dentry = inline_data_addr(dir, ipage);
+
+	err = do_convert_inline_dir(dir, ipage, inline_dentry);
+	if (!err)
+		f2fs_put_page(ipage, 1);
+out:
+	f2fs_unlock_op(sbi);
+	return err;
+}
+
 int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 				const struct qstr *orig_name,
 				struct inode *inode, nid_t ino, umode_t mode)
@@ -562,7 +600,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 
 	bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max);
 	if (bit_pos >= d.max) {
-		err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
+		err = do_convert_inline_dir(dir, ipage, inline_dentry);
 		if (err)
 			return err;
 		err = -EAGAIN;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 502bd491336a..78c3f1d70f1d 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -200,6 +200,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_inode *ri = F2FS_INODE(node_page);
 	unsigned long long iblocks;
 
 	iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
@@ -286,6 +287,19 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
 		return false;
 	}
 
+	if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) &&
+			fi->i_flags & F2FS_COMPR_FL &&
+			F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
+						i_log_cluster_size)) {
+		if (ri->i_compress_algorithm >= COMPRESS_MAX)
+			return false;
+		if (le64_to_cpu(ri->i_compr_blocks) > inode->i_blocks)
+			return false;
+		if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
+			ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE)
+			return false;
+	}
+
 	return true;
 }
 
@@ -407,6 +421,18 @@ static int do_read_inode(struct inode *inode)
 		fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
 	}
 
+	if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) &&
+					(fi->i_flags & F2FS_COMPR_FL)) {
+		if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
+					i_log_cluster_size)) {
+			fi->i_compr_blocks = le64_to_cpu(ri->i_compr_blocks);
+			fi->i_compress_algorithm = ri->i_compress_algorithm;
+			fi->i_log_cluster_size = ri->i_log_cluster_size;
+			fi->i_cluster_size = 1 << fi->i_log_cluster_size;
+			set_inode_flag(inode, FI_COMPRESSED_FILE);
+		}
+	}
+
 	F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
 	F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
 	F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
@@ -416,6 +442,8 @@ static int do_read_inode(struct inode *inode)
 	stat_inc_inline_xattr(inode);
 	stat_inc_inline_inode(inode);
 	stat_inc_inline_dir(inode);
+	stat_inc_compr_inode(inode);
+	stat_add_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
 
 	return 0;
 }
@@ -569,6 +597,17 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
 			ri->i_crtime_nsec =
 				cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
 		}
+
+		if (f2fs_sb_has_compression(F2FS_I_SB(inode)) &&
+			F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+							i_log_cluster_size)) {
+			ri->i_compr_blocks =
+				cpu_to_le64(F2FS_I(inode)->i_compr_blocks);
+			ri->i_compress_algorithm =
+				F2FS_I(inode)->i_compress_algorithm;
+			ri->i_log_cluster_size =
+				F2FS_I(inode)->i_log_cluster_size;
+		}
 	}
 
 	__set_inode_rdev(inode, ri);
@@ -711,6 +750,8 @@ no_delete:
 	stat_dec_inline_xattr(inode);
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
+	stat_dec_compr_inode(inode);
+	stat_sub_compr_blocks(inode, F2FS_I(inode)->i_compr_blocks);
 
 	if (likely(!f2fs_cp_error(sbi) &&
 				!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a1c507b0b4ac..2aa035422c0f 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -119,6 +119,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
 		set_inode_flag(inode, FI_PROJ_INHERIT);
 
+	if (f2fs_sb_has_compression(sbi)) {
+		/* Inherit the compression flag in directory */
+		if ((F2FS_I(dir)->i_flags & F2FS_COMPR_FL) &&
+					f2fs_may_compress(inode))
+			set_compress_context(inode);
+	}
+
 	f2fs_set_inode_flags(inode);
 
 	trace_f2fs_new_inode(inode, 0);
@@ -149,6 +156,9 @@ static inline int is_extension_exist(const unsigned char *s, const char *sub)
 	size_t sublen = strlen(sub);
 	int i;
 
+	if (sublen == 1 && *sub == '*')
+		return 1;
+
 	/*
 	 * filename format of multimedia file should be defined as:
 	 * "filename + '.' + extension + (optional: '.' + temp extension)".
@@ -262,6 +272,45 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
 	return 0;
 }
 
+static void set_compress_inode(struct f2fs_sb_info *sbi, struct inode *inode,
+						const unsigned char *name)
+{
+	__u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list;
+	unsigned char (*ext)[F2FS_EXTENSION_LEN];
+	unsigned int ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt;
+	int i, cold_count, hot_count;
+
+	if (!f2fs_sb_has_compression(sbi) ||
+			is_inode_flag_set(inode, FI_COMPRESSED_FILE) ||
+			F2FS_I(inode)->i_flags & F2FS_NOCOMP_FL ||
+			!f2fs_may_compress(inode))
+		return;
+
+	down_read(&sbi->sb_lock);
+
+	cold_count = le32_to_cpu(sbi->raw_super->extension_count);
+	hot_count = sbi->raw_super->hot_ext_count;
+
+	for (i = cold_count; i < cold_count + hot_count; i++) {
+		if (is_extension_exist(name, extlist[i])) {
+			up_read(&sbi->sb_lock);
+			return;
+		}
+	}
+
+	up_read(&sbi->sb_lock);
+
+	ext = F2FS_OPTION(sbi).extensions;
+
+	for (i = 0; i < ext_cnt; i++) {
+		if (!is_extension_exist(name, ext[i]))
+			continue;
+
+		set_compress_context(inode);
+		return;
+	}
+}
+
 static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 						bool excl)
 {
@@ -286,6 +335,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	if (!test_opt(sbi, DISABLE_EXT_IDENTIFY))
 		set_file_temperature(sbi, inode, dentry->d_name.name);
 
+	set_compress_inode(sbi, inode, dentry->d_name.name);
+
 	inode->i_op = &f2fs_file_inode_operations;
 	inode->i_fop = &f2fs_file_operations;
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
@@ -797,6 +848,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 
 	if (whiteout) {
 		f2fs_i_links_write(inode, false);
+		inode->i_state |= I_LINKABLE;
 		*whiteout = inode;
 	} else {
 		d_tmpfile(dentry, inode);
@@ -849,12 +901,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct inode *old_inode = d_inode(old_dentry);
 	struct inode *new_inode = d_inode(new_dentry);
 	struct inode *whiteout = NULL;
-	struct page *old_dir_page;
+	struct page *old_dir_page = NULL;
 	struct page *old_page, *new_page = NULL;
 	struct f2fs_dir_entry *old_dir_entry = NULL;
 	struct f2fs_dir_entry *old_entry;
 	struct f2fs_dir_entry *new_entry;
-	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err;
 
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -867,6 +918,26 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			F2FS_I(old_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
+	/*
+	 * If new_inode is null, the below renaming flow will
+	 * add a link in old_dir which can conver inline_dir.
+	 * After then, if we failed to get the entry due to other
+	 * reasons like ENOMEM, we had to remove the new entry.
+	 * Instead of adding such the error handling routine, let's
+	 * simply convert first here.
+	 */
+	if (old_dir == new_dir && !new_inode) {
+		err = f2fs_try_convert_inline_dir(old_dir, new_dentry);
+		if (err)
+			return err;
+	}
+
+	if (flags & RENAME_WHITEOUT) {
+		err = f2fs_create_whiteout(old_dir, &whiteout);
+		if (err)
+			return err;
+	}
+
 	err = dquot_initialize(old_dir);
 	if (err)
 		goto out;
@@ -898,17 +969,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
-	if (flags & RENAME_WHITEOUT) {
-		err = f2fs_create_whiteout(old_dir, &whiteout);
-		if (err)
-			goto out_dir;
-	}
-
 	if (new_inode) {
 
 		err = -ENOTEMPTY;
 		if (old_dir_entry && !f2fs_empty_dir(new_inode))
-			goto out_whiteout;
+			goto out_dir;
 
 		err = -ENOENT;
 		new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
@@ -916,7 +981,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!new_entry) {
 			if (IS_ERR(new_page))
 				err = PTR_ERR(new_page);
-			goto out_whiteout;
+			goto out_dir;
 		}
 
 		f2fs_balance_fs(sbi, true);
@@ -928,6 +993,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto put_out_dir;
 
 		f2fs_set_link(new_dir, new_entry, new_page, old_inode);
+		new_page = NULL;
 
 		new_inode->i_ctime = current_time(new_inode);
 		down_write(&F2FS_I(new_inode)->i_sem);
@@ -948,33 +1014,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		err = f2fs_add_link(new_dentry, old_inode);
 		if (err) {
 			f2fs_unlock_op(sbi);
-			goto out_whiteout;
+			goto out_dir;
 		}
 
 		if (old_dir_entry)
 			f2fs_i_links_write(new_dir, true);
-
-		/*
-		 * old entry and new entry can locate in the same inline
-		 * dentry in inode, when attaching new entry in inline dentry,
-		 * it could force inline dentry conversion, after that,
-		 * old_entry and old_page will point to wrong address, in
-		 * order to avoid this, let's do the check and update here.
-		 */
-		if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
-			f2fs_put_page(old_page, 0);
-			old_page = NULL;
-
-			old_entry = f2fs_find_entry(old_dir,
-						&old_dentry->d_name, &old_page);
-			if (!old_entry) {
-				err = -ENOENT;
-				if (IS_ERR(old_page))
-					err = PTR_ERR(old_page);
-				f2fs_unlock_op(sbi);
-				goto out_whiteout;
-			}
-		}
 	}
 
 	down_write(&F2FS_I(old_inode)->i_sem);
@@ -989,9 +1033,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	f2fs_mark_inode_dirty_sync(old_inode, false);
 
 	f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
+	old_page = NULL;
 
 	if (whiteout) {
-		whiteout->i_state |= I_LINKABLE;
 		set_inode_flag(whiteout, FI_INC_LINK);
 		err = f2fs_add_link(old_dentry, whiteout);
 		if (err)
@@ -1025,17 +1069,15 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 put_out_dir:
 	f2fs_unlock_op(sbi);
-	if (new_page)
-		f2fs_put_page(new_page, 0);
-out_whiteout:
-	if (whiteout)
-		iput(whiteout);
+	f2fs_put_page(new_page, 0);
 out_dir:
 	if (old_dir_entry)
 		f2fs_put_page(old_dir_page, 0);
 out_old:
 	f2fs_put_page(old_page, 0);
 out:
+	if (whiteout)
+		iput(whiteout);
 	return err;
 }
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 3314a0f3405e..9d02cdcdbb07 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -875,7 +875,7 @@ static int truncate_dnode(struct dnode_of_data *dn)
 
 	/* get direct node */
 	page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid);
-	if (IS_ERR(page) && PTR_ERR(page) == -ENOENT)
+	if (PTR_ERR(page) == -ENOENT)
 		return 1;
 	else if (IS_ERR(page))
 		return PTR_ERR(page);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 76477f71d4ee..763d5c0951d1 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -723,6 +723,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	int ret = 0;
 	unsigned long s_flags = sbi->sb->s_flags;
 	bool need_writecp = false;
+	bool fix_curseg_write_pointer = false;
 #ifdef CONFIG_QUOTA
 	int quota_enabled;
 #endif
@@ -774,6 +775,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 		sbi->sb->s_flags = s_flags;
 	}
 skip:
+	fix_curseg_write_pointer = !check_only || list_empty(&inode_list);
+
 	destroy_fsync_dnodes(&inode_list, err);
 	destroy_fsync_dnodes(&tmp_inode_list, err);
 
@@ -784,9 +787,22 @@ skip:
 	if (err) {
 		truncate_inode_pages_final(NODE_MAPPING(sbi));
 		truncate_inode_pages_final(META_MAPPING(sbi));
-	} else {
-		clear_sbi_flag(sbi, SBI_POR_DOING);
 	}
+
+	/*
+	 * If fsync data succeeds or there is no fsync data to recover,
+	 * and the f2fs is not read only, check and fix zoned block devices'
+	 * write pointer consistency.
+	 */
+	if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) &&
+			f2fs_sb_has_blkzoned(sbi)) {
+		err = f2fs_fix_curseg_write_pointer(sbi);
+		ret = err;
+	}
+
+	if (!err)
+		clear_sbi_flag(sbi, SBI_POR_DOING);
+
 	mutex_unlock(&sbi->cp_mutex);
 
 	/* let's drop all the directory inodes for clean checkpoint */
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 56e81447e2f3..cf0eb002cfd4 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -334,7 +334,6 @@ void f2fs_drop_inmem_pages(struct inode *inode)
 	}
 
 	fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
-	stat_dec_atomic_write(inode);
 
 	spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
 	if (!list_empty(&fi->inmem_ilist))
@@ -505,7 +504,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	 * dir/node pages without enough free segments.
 	 */
 	if (has_not_enough_free_secs(sbi, 0, 0)) {
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 		f2fs_gc(sbi, false, false, NULL_SEGNO);
 	}
 }
@@ -2225,7 +2224,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 	struct sit_info *sit_i = SIT_I(sbi);
 
 	f2fs_bug_on(sbi, addr == NULL_ADDR);
-	if (addr == NEW_ADDR)
+	if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
 		return;
 
 	invalidate_mapping_pages(META_MAPPING(sbi), addr, addr);
@@ -2861,9 +2860,9 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	if (sbi->discard_blks == 0)
 		goto out;
 
-	mutex_lock(&sbi->gc_mutex);
+	down_write(&sbi->gc_lock);
 	err = f2fs_write_checkpoint(sbi, &cpc);
-	mutex_unlock(&sbi->gc_mutex);
+	up_write(&sbi->gc_lock);
 	if (err)
 		goto out;
 
@@ -3036,7 +3035,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 	if (fio->type == DATA) {
 		struct inode *inode = fio->page->mapping->host;
 
-		if (is_cold_data(fio->page) || file_is_cold(inode))
+		if (is_cold_data(fio->page) || file_is_cold(inode) ||
+				f2fs_compressed_file(inode))
 			return CURSEG_COLD_DATA;
 		if (file_is_hot(inode) ||
 				is_inode_flag_set(inode, FI_HOT_DATA) ||
@@ -3289,7 +3289,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
 
 	stat_inc_inplace_blocks(fio->sbi);
 
-	if (fio->bio)
+	if (fio->bio && !(SM_I(sbi)->ipu_policy & (1 << F2FS_IPU_NOCACHE)))
 		err = f2fs_merge_page_bio(fio);
 	else
 		err = f2fs_submit_page_bio(fio);
@@ -4368,6 +4368,263 @@ out:
 	return 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+
+static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
+				    struct f2fs_dev_info *fdev,
+				    struct blk_zone *zone)
+{
+	unsigned int wp_segno, wp_blkoff, zone_secno, zone_segno, segno;
+	block_t zone_block, wp_block, last_valid_block;
+	unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
+	int i, s, b, ret;
+	struct seg_entry *se;
+
+	if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+		return 0;
+
+	wp_block = fdev->start_blk + (zone->wp >> log_sectors_per_block);
+	wp_segno = GET_SEGNO(sbi, wp_block);
+	wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
+	zone_block = fdev->start_blk + (zone->start >> log_sectors_per_block);
+	zone_segno = GET_SEGNO(sbi, zone_block);
+	zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno);
+
+	if (zone_segno >= MAIN_SEGS(sbi))
+		return 0;
+
+	/*
+	 * Skip check of zones cursegs point to, since
+	 * fix_curseg_write_pointer() checks them.
+	 */
+	for (i = 0; i < NO_CHECK_TYPE; i++)
+		if (zone_secno == GET_SEC_FROM_SEG(sbi,
+						   CURSEG_I(sbi, i)->segno))
+			return 0;
+
+	/*
+	 * Get last valid block of the zone.
+	 */
+	last_valid_block = zone_block - 1;
+	for (s = sbi->segs_per_sec - 1; s >= 0; s--) {
+		segno = zone_segno + s;
+		se = get_seg_entry(sbi, segno);
+		for (b = sbi->blocks_per_seg - 1; b >= 0; b--)
+			if (f2fs_test_bit(b, se->cur_valid_map)) {
+				last_valid_block = START_BLOCK(sbi, segno) + b;
+				break;
+			}
+		if (last_valid_block >= zone_block)
+			break;
+	}
+
+	/*
+	 * If last valid block is beyond the write pointer, report the
+	 * inconsistency. This inconsistency does not cause write error
+	 * because the zone will not be selected for write operation until
+	 * it get discarded. Just report it.
+	 */
+	if (last_valid_block >= wp_block) {
+		f2fs_notice(sbi, "Valid block beyond write pointer: "
+			    "valid block[0x%x,0x%x] wp[0x%x,0x%x]",
+			    GET_SEGNO(sbi, last_valid_block),
+			    GET_BLKOFF_FROM_SEG0(sbi, last_valid_block),
+			    wp_segno, wp_blkoff);
+		return 0;
+	}
+
+	/*
+	 * If there is no valid block in the zone and if write pointer is
+	 * not at zone start, reset the write pointer.
+	 */
+	if (last_valid_block + 1 == zone_block && zone->wp != zone->start) {
+		f2fs_notice(sbi,
+			    "Zone without valid block has non-zero write "
+			    "pointer. Reset the write pointer: wp[0x%x,0x%x]",
+			    wp_segno, wp_blkoff);
+		ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block,
+					zone->len >> log_sectors_per_block);
+		if (ret) {
+			f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
+				 fdev->path, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi,
+						  block_t zone_blkaddr)
+{
+	int i;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (!bdev_is_zoned(FDEV(i).bdev))
+			continue;
+		if (sbi->s_ndevs == 1 || (FDEV(i).start_blk <= zone_blkaddr &&
+				zone_blkaddr <= FDEV(i).end_blk))
+			return &FDEV(i);
+	}
+
+	return NULL;
+}
+
+static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
+			      void *data) {
+	memcpy(data, zone, sizeof(struct blk_zone));
+	return 0;
+}
+
+static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *cs = CURSEG_I(sbi, type);
+	struct f2fs_dev_info *zbd;
+	struct blk_zone zone;
+	unsigned int cs_section, wp_segno, wp_blkoff, wp_sector_off;
+	block_t cs_zone_block, wp_block;
+	unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
+	sector_t zone_sector;
+	int err;
+
+	cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
+	cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
+
+	zbd = get_target_zoned_dev(sbi, cs_zone_block);
+	if (!zbd)
+		return 0;
+
+	/* report zone for the sector the curseg points to */
+	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
+		<< log_sectors_per_block;
+	err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
+				  report_one_zone_cb, &zone);
+	if (err != 1) {
+		f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
+			 zbd->path, err);
+		return err;
+	}
+
+	if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+		return 0;
+
+	wp_block = zbd->start_blk + (zone.wp >> log_sectors_per_block);
+	wp_segno = GET_SEGNO(sbi, wp_block);
+	wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno);
+	wp_sector_off = zone.wp & GENMASK(log_sectors_per_block - 1, 0);
+
+	if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff &&
+		wp_sector_off == 0)
+		return 0;
+
+	f2fs_notice(sbi, "Unaligned curseg[%d] with write pointer: "
+		    "curseg[0x%x,0x%x] wp[0x%x,0x%x]",
+		    type, cs->segno, cs->next_blkoff, wp_segno, wp_blkoff);
+
+	f2fs_notice(sbi, "Assign new section to curseg[%d]: "
+		    "curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff);
+	allocate_segment_by_default(sbi, type, true);
+
+	/* check consistency of the zone curseg pointed to */
+	if (check_zone_write_pointer(sbi, zbd, &zone))
+		return -EIO;
+
+	/* check newly assigned zone */
+	cs_section = GET_SEC_FROM_SEG(sbi, cs->segno);
+	cs_zone_block = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, cs_section));
+
+	zbd = get_target_zoned_dev(sbi, cs_zone_block);
+	if (!zbd)
+		return 0;
+
+	zone_sector = (sector_t)(cs_zone_block - zbd->start_blk)
+		<< log_sectors_per_block;
+	err = blkdev_report_zones(zbd->bdev, zone_sector, 1,
+				  report_one_zone_cb, &zone);
+	if (err != 1) {
+		f2fs_err(sbi, "Report zone failed: %s errno=(%d)",
+			 zbd->path, err);
+		return err;
+	}
+
+	if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ)
+		return 0;
+
+	if (zone.wp != zone.start) {
+		f2fs_notice(sbi,
+			    "New zone for curseg[%d] is not yet discarded. "
+			    "Reset the zone: curseg[0x%x,0x%x]",
+			    type, cs->segno, cs->next_blkoff);
+		err = __f2fs_issue_discard_zone(sbi, zbd->bdev,
+				zone_sector >> log_sectors_per_block,
+				zone.len >> log_sectors_per_block);
+		if (err) {
+			f2fs_err(sbi, "Discard zone failed: %s (errno=%d)",
+				 zbd->path, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+{
+	int i, ret;
+
+	for (i = 0; i < NO_CHECK_TYPE; i++) {
+		ret = fix_curseg_write_pointer(sbi, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct check_zone_write_pointer_args {
+	struct f2fs_sb_info *sbi;
+	struct f2fs_dev_info *fdev;
+};
+
+static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
+				      void *data) {
+	struct check_zone_write_pointer_args *args;
+	args = (struct check_zone_write_pointer_args *)data;
+
+	return check_zone_write_pointer(args->sbi, args->fdev, zone);
+}
+
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+{
+	int i, ret;
+	struct check_zone_write_pointer_args args;
+
+	for (i = 0; i < sbi->s_ndevs; i++) {
+		if (!bdev_is_zoned(FDEV(i).bdev))
+			continue;
+
+		args.sbi = sbi;
+		args.fdev = &FDEV(i);
+		ret = blkdev_report_zones(FDEV(i).bdev, 0, BLK_ALL_ZONES,
+					  check_zone_write_pointer_cb, &args);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+#else
+int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+{
+	return 0;
+}
+
+int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+{
+	return 0;
+}
+#endif
+
 /*
  * Update min, max modified time for cost-benefit GC algorithm
  */
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index a95467b202ea..459dc3901a57 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -200,18 +200,6 @@ struct segment_allocation {
 	void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
 };
 
-/*
- * this value is set in page as a private data which indicate that
- * the page is atomically written, and it is in inmem_pages list.
- */
-#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
-#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
-
-#define IS_ATOMIC_WRITTEN_PAGE(page)			\
-		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
-#define IS_DUMMY_WRITTEN_PAGE(page)			\
-		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
-
 #define MAX_SKIP_GC_COUNT			16
 
 struct inmem_pages {
@@ -619,8 +607,10 @@ static inline int utilization(struct f2fs_sb_info *sbi)
  *                     threashold,
  * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
  *                     storages. IPU will be triggered only if the # of dirty
- *                     pages over min_fsync_blocks.
- * F2FS_IPUT_DISABLE - disable IPU. (=default option)
+ *                     pages over min_fsync_blocks. (=default option)
+ * F2FS_IPU_ASYNC - do IPU given by asynchronous write requests.
+ * F2FS_IPU_NOCACHE - disable IPU bio cache.
+ * F2FS_IPUT_DISABLE - disable IPU. (=default option in LFS mode)
  */
 #define DEF_MIN_IPU_UTIL	70
 #define DEF_MIN_FSYNC_BLOCKS	8
@@ -635,6 +625,7 @@ enum {
 	F2FS_IPU_SSR_UTIL,
 	F2FS_IPU_FSYNC,
 	F2FS_IPU_ASYNC,
+	F2FS_IPU_NOCACHE,
 };
 
 static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 5111e1ffe58a..65a7a432dfee 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -141,6 +141,9 @@ enum {
 	Opt_checkpoint_disable_cap,
 	Opt_checkpoint_disable_cap_perc,
 	Opt_checkpoint_enable,
+	Opt_compress_algorithm,
+	Opt_compress_log_size,
+	Opt_compress_extension,
 	Opt_err,
 };
 
@@ -203,6 +206,9 @@ static match_table_t f2fs_tokens = {
 	{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},
 	{Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"},
 	{Opt_checkpoint_enable, "checkpoint=enable"},
+	{Opt_compress_algorithm, "compress_algorithm=%s"},
+	{Opt_compress_log_size, "compress_log_size=%u"},
+	{Opt_compress_extension, "compress_extension=%s"},
 	{Opt_err, NULL},
 };
 
@@ -391,8 +397,9 @@ static int parse_options(struct super_block *sb, char *options)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	substring_t args[MAX_OPT_ARGS];
+	unsigned char (*ext)[F2FS_EXTENSION_LEN];
 	char *p, *name;
-	int arg = 0;
+	int arg = 0, ext_cnt;
 	kuid_t uid;
 	kgid_t gid;
 #ifdef CONFIG_QUOTA
@@ -810,6 +817,66 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_checkpoint_enable:
 			clear_opt(sbi, DISABLE_CHECKPOINT);
 			break;
+		case Opt_compress_algorithm:
+			if (!f2fs_sb_has_compression(sbi)) {
+				f2fs_err(sbi, "Compression feature if off");
+				return -EINVAL;
+			}
+			name = match_strdup(&args[0]);
+			if (!name)
+				return -ENOMEM;
+			if (strlen(name) == 3 && !strcmp(name, "lzo")) {
+				F2FS_OPTION(sbi).compress_algorithm =
+								COMPRESS_LZO;
+			} else if (strlen(name) == 3 &&
+					!strcmp(name, "lz4")) {
+				F2FS_OPTION(sbi).compress_algorithm =
+								COMPRESS_LZ4;
+			} else {
+				kfree(name);
+				return -EINVAL;
+			}
+			kfree(name);
+			break;
+		case Opt_compress_log_size:
+			if (!f2fs_sb_has_compression(sbi)) {
+				f2fs_err(sbi, "Compression feature is off");
+				return -EINVAL;
+			}
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			if (arg < MIN_COMPRESS_LOG_SIZE ||
+				arg > MAX_COMPRESS_LOG_SIZE) {
+				f2fs_err(sbi,
+					"Compress cluster log size is out of range");
+				return -EINVAL;
+			}
+			F2FS_OPTION(sbi).compress_log_size = arg;
+			break;
+		case Opt_compress_extension:
+			if (!f2fs_sb_has_compression(sbi)) {
+				f2fs_err(sbi, "Compression feature is off");
+				return -EINVAL;
+			}
+			name = match_strdup(&args[0]);
+			if (!name)
+				return -ENOMEM;
+
+			ext = F2FS_OPTION(sbi).extensions;
+			ext_cnt = F2FS_OPTION(sbi).compress_ext_cnt;
+
+			if (strlen(name) >= F2FS_EXTENSION_LEN ||
+				ext_cnt >= COMPRESS_EXT_NUM) {
+				f2fs_err(sbi,
+					"invalid extension length/number");
+				kfree(name);
+				return -EINVAL;
+			}
+
+			strcpy(ext[ext_cnt], name);
+			F2FS_OPTION(sbi).compress_ext_cnt++;
+			kfree(name);
+			break;
 		default:
 			f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
 				 p);
@@ -1125,6 +1192,8 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_destroy_node_manager(sbi);
 	f2fs_destroy_segment_manager(sbi);
 
+	f2fs_destroy_post_read_wq(sbi);
+
 	kvfree(sbi->ckpt);
 
 	f2fs_unregister_sysfs(sbi);
@@ -1169,9 +1238,9 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 
 		cpc.reason = __get_cp_reason(sbi);
 
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 		err = f2fs_write_checkpoint(sbi, &cpc);
-		mutex_unlock(&sbi->gc_mutex);
+		up_write(&sbi->gc_lock);
 	}
 	f2fs_trace_ios(NULL, 1);
 
@@ -1213,12 +1282,10 @@ static int f2fs_statfs_project(struct super_block *sb,
 		return PTR_ERR(dquot);
 	spin_lock(&dquot->dq_dqb_lock);
 
-	limit = 0;
-	if (dquot->dq_dqb.dqb_bsoftlimit)
-		limit = dquot->dq_dqb.dqb_bsoftlimit;
-	if (dquot->dq_dqb.dqb_bhardlimit &&
-			(!limit || dquot->dq_dqb.dqb_bhardlimit < limit))
-		limit = dquot->dq_dqb.dqb_bhardlimit;
+	limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit,
+					dquot->dq_dqb.dqb_bhardlimit);
+	if (limit)
+		limit >>= sb->s_blocksize_bits;
 
 	if (limit && buf->f_blocks > limit) {
 		curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
@@ -1228,12 +1295,8 @@ static int f2fs_statfs_project(struct super_block *sb,
 			 (buf->f_blocks - curblock) : 0;
 	}
 
-	limit = 0;
-	if (dquot->dq_dqb.dqb_isoftlimit)
-		limit = dquot->dq_dqb.dqb_isoftlimit;
-	if (dquot->dq_dqb.dqb_ihardlimit &&
-			(!limit || dquot->dq_dqb.dqb_ihardlimit < limit))
-		limit = dquot->dq_dqb.dqb_ihardlimit;
+	limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
+					dquot->dq_dqb.dqb_ihardlimit);
 
 	if (limit && buf->f_files > limit) {
 		buf->f_files = limit;
@@ -1340,6 +1403,35 @@ static inline void f2fs_show_quota_options(struct seq_file *seq,
 #endif
 }
 
+static inline void f2fs_show_compress_options(struct seq_file *seq,
+							struct super_block *sb)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	char *algtype = "";
+	int i;
+
+	if (!f2fs_sb_has_compression(sbi))
+		return;
+
+	switch (F2FS_OPTION(sbi).compress_algorithm) {
+	case COMPRESS_LZO:
+		algtype = "lzo";
+		break;
+	case COMPRESS_LZ4:
+		algtype = "lz4";
+		break;
+	}
+	seq_printf(seq, ",compress_algorithm=%s", algtype);
+
+	seq_printf(seq, ",compress_log_size=%u",
+			F2FS_OPTION(sbi).compress_log_size);
+
+	for (i = 0; i < F2FS_OPTION(sbi).compress_ext_cnt; i++) {
+		seq_printf(seq, ",compress_extension=%s",
+			F2FS_OPTION(sbi).extensions[i]);
+	}
+}
+
 static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
@@ -1462,6 +1554,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_printf(seq, ",fsync_mode=%s", "strict");
 	else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
 		seq_printf(seq, ",fsync_mode=%s", "nobarrier");
+
+	f2fs_show_compress_options(seq, sbi->sb);
 	return 0;
 }
 
@@ -1476,6 +1570,9 @@ static void default_options(struct f2fs_sb_info *sbi)
 	F2FS_OPTION(sbi).test_dummy_encryption = false;
 	F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
 	F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
+	F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZO;
+	F2FS_OPTION(sbi).compress_log_size = MIN_COMPRESS_LOG_SIZE;
+	F2FS_OPTION(sbi).compress_ext_cnt = 0;
 
 	set_opt(sbi, BG_GC);
 	set_opt(sbi, INLINE_XATTR);
@@ -1524,7 +1621,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 	f2fs_update_time(sbi, DISABLE_TIME);
 
 	while (!f2fs_time_over(sbi, DISABLE_TIME)) {
-		mutex_lock(&sbi->gc_mutex);
+		down_write(&sbi->gc_lock);
 		err = f2fs_gc(sbi, true, false, NULL_SEGNO);
 		if (err == -ENODATA) {
 			err = 0;
@@ -1546,7 +1643,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 		goto restore_flag;
 	}
 
-	mutex_lock(&sbi->gc_mutex);
+	down_write(&sbi->gc_lock);
 	cpc.reason = CP_PAUSE;
 	set_sbi_flag(sbi, SBI_CP_DISABLED);
 	err = f2fs_write_checkpoint(sbi, &cpc);
@@ -1558,7 +1655,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
 	spin_unlock(&sbi->stat_lock);
 
 out_unlock:
-	mutex_unlock(&sbi->gc_mutex);
+	up_write(&sbi->gc_lock);
 restore_flag:
 	sbi->sb->s_flags = s_flags;	/* Restore MS_RDONLY status */
 	return err;
@@ -1566,12 +1663,12 @@ restore_flag:
 
 static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
 {
-	mutex_lock(&sbi->gc_mutex);
+	down_write(&sbi->gc_lock);
 	f2fs_dirty_to_prefree(sbi);
 
 	clear_sbi_flag(sbi, SBI_CP_DISABLED);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
-	mutex_unlock(&sbi->gc_mutex);
+	up_write(&sbi->gc_lock);
 
 	f2fs_sync_fs(sbi->sb, 1);
 }
@@ -2158,7 +2255,7 @@ static int f2fs_dquot_commit(struct dquot *dquot)
 	struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb);
 	int ret;
 
-	down_read(&sbi->quota_sem);
+	down_read_nested(&sbi->quota_sem, SINGLE_DEPTH_NESTING);
 	ret = dquot_commit(dquot);
 	if (ret < 0)
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
@@ -2182,13 +2279,10 @@ static int f2fs_dquot_acquire(struct dquot *dquot)
 static int f2fs_dquot_release(struct dquot *dquot)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dquot->dq_sb);
-	int ret;
+	int ret = dquot_release(dquot);
 
-	down_read(&sbi->quota_sem);
-	ret = dquot_release(dquot);
 	if (ret < 0)
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
-	up_read(&sbi->quota_sem);
 	return ret;
 }
 
@@ -2196,29 +2290,22 @@ static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot)
 {
 	struct super_block *sb = dquot->dq_sb;
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	int ret;
-
-	down_read(&sbi->quota_sem);
-	ret = dquot_mark_dquot_dirty(dquot);
+	int ret = dquot_mark_dquot_dirty(dquot);
 
 	/* if we are using journalled quota */
 	if (is_journalled_quota(sbi))
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
 
-	up_read(&sbi->quota_sem);
 	return ret;
 }
 
 static int f2fs_dquot_commit_info(struct super_block *sb, int type)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	int ret;
+	int ret = dquot_commit_info(sb, type);
 
-	down_read(&sbi->quota_sem);
-	ret = dquot_commit_info(sb, type);
 	if (ret < 0)
 		set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
-	up_read(&sbi->quota_sem);
 	return ret;
 }
 
@@ -3311,7 +3398,7 @@ try_onemore:
 
 	/* init f2fs-specific super block info */
 	sbi->valid_super_block = valid_super_block;
-	mutex_init(&sbi->gc_mutex);
+	init_rwsem(&sbi->gc_lock);
 	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	mutex_init(&sbi->resize_mutex);
@@ -3400,6 +3487,12 @@ try_onemore:
 		goto free_devices;
 	}
 
+	err = f2fs_init_post_read_wq(sbi);
+	if (err) {
+		f2fs_err(sbi, "Failed to initialize post read workqueue");
+		goto free_devices;
+	}
+
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	percpu_counter_set(&sbi->total_valid_inode_count,
@@ -3544,6 +3637,17 @@ try_onemore:
 			goto free_meta;
 		}
 	}
+
+	/*
+	 * If the f2fs is not readonly and fsync data recovery succeeds,
+	 * check zoned block devices' write pointer consistency.
+	 */
+	if (!err && !f2fs_readonly(sb) && f2fs_sb_has_blkzoned(sbi)) {
+		err = f2fs_check_write_pointer(sbi);
+		if (err)
+			goto free_meta;
+	}
+
 reset_checkpoint:
 	/* f2fs_recover_fsync_data() cleared this already */
 	clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -3621,6 +3725,7 @@ free_nm:
 	f2fs_destroy_node_manager(sbi);
 free_sm:
 	f2fs_destroy_segment_manager(sbi);
+	f2fs_destroy_post_read_wq(sbi);
 free_devices:
 	destroy_device_list(sbi);
 	kvfree(sbi->ckpt);
@@ -3762,8 +3867,12 @@ static int __init init_f2fs_fs(void)
 	err = f2fs_init_bio_entry_cache();
 	if (err)
 		goto free_post_read;
+	err = f2fs_init_bioset();
+	if (err)
+		goto free_bio_enrty_cache;
 	return 0;
-
+free_bio_enrty_cache:
+	f2fs_destroy_bio_entry_cache();
 free_post_read:
 	f2fs_destroy_post_read_processing();
 free_root_stats:
@@ -3789,6 +3898,7 @@ fail:
 
 static void __exit exit_f2fs_fs(void)
 {
+	f2fs_destroy_bioset();
 	f2fs_destroy_bio_entry_cache();
 	f2fs_destroy_post_read_processing();
 	f2fs_destroy_root_stats();
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 70945ceb9c0c..91d649790b1b 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -25,6 +25,9 @@ enum {
 	DCC_INFO,	/* struct discard_cmd_control */
 	NM_INFO,	/* struct f2fs_nm_info */
 	F2FS_SBI,	/* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_STAT_FS
+	STAT_INFO,      /* struct f2fs_stat_info */
+#endif
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
 	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
@@ -42,6 +45,9 @@ struct f2fs_attr {
 	int id;
 };
 
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+			     struct f2fs_sb_info *sbi, char *buf);
+
 static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 {
 	if (struct_type == GC_THREAD)
@@ -59,41 +65,25 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 					struct_type == FAULT_INFO_TYPE)
 		return (unsigned char *)&F2FS_OPTION(sbi).fault_info;
 #endif
+#ifdef CONFIG_F2FS_STAT_FS
+	else if (struct_type == STAT_INFO)
+		return (unsigned char *)F2FS_STAT(sbi);
+#endif
 	return NULL;
 }
 
 static ssize_t dirty_segments_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)(dirty_segments(sbi)));
+	return sprintf(buf, "%llu\n",
+			(unsigned long long)(dirty_segments(sbi)));
 }
 
-static ssize_t unusable_show(struct f2fs_attr *a,
+static ssize_t free_segments_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
-	block_t unusable;
-
-	if (test_opt(sbi, DISABLE_CHECKPOINT))
-		unusable = sbi->unusable_block_count;
-	else
-		unusable = f2fs_get_unusable_blocks(sbi);
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)unusable);
-}
-
-static ssize_t encoding_show(struct f2fs_attr *a,
-		struct f2fs_sb_info *sbi, char *buf)
-{
-#ifdef CONFIG_UNICODE
-	if (f2fs_sb_has_casefold(sbi))
-		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
-			sbi->s_encoding->charset,
-			(sbi->s_encoding->version >> 16) & 0xff,
-			(sbi->s_encoding->version >> 8) & 0xff,
-			sbi->s_encoding->version & 0xff);
-#endif
-	return snprintf(buf, PAGE_SIZE, "(none)");
+	return sprintf(buf, "%llu\n",
+			(unsigned long long)(free_segments(sbi)));
 }
 
 static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
@@ -102,10 +92,10 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
 	struct super_block *sb = sbi->sb;
 
 	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
+		return sprintf(buf, "0\n");
 
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)(sbi->kbytes_written +
+	return sprintf(buf, "%llu\n",
+			(unsigned long long)(sbi->kbytes_written +
 			BD_PART_WRITTEN(sbi)));
 }
 
@@ -116,7 +106,7 @@ static ssize_t features_show(struct f2fs_attr *a,
 	int len = 0;
 
 	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
+		return sprintf(buf, "0\n");
 
 	if (f2fs_sb_has_encrypt(sbi))
 		len += snprintf(buf, PAGE_SIZE - len, "%s",
@@ -154,6 +144,9 @@ static ssize_t features_show(struct f2fs_attr *a,
 	if (f2fs_sb_has_casefold(sbi))
 		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "casefold");
+	if (f2fs_sb_has_compression(sbi))
+		len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+				len ? ", " : "", "compression");
 	len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
 				len ? ", " : "", "pin_file");
 	len += snprintf(buf + len, PAGE_SIZE - len, "\n");
@@ -163,9 +156,66 @@ static ssize_t features_show(struct f2fs_attr *a,
 static ssize_t current_reserved_blocks_show(struct f2fs_attr *a,
 					struct f2fs_sb_info *sbi, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%u\n", sbi->current_reserved_blocks);
+	return sprintf(buf, "%u\n", sbi->current_reserved_blocks);
+}
+
+static ssize_t unusable_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	block_t unusable;
+
+	if (test_opt(sbi, DISABLE_CHECKPOINT))
+		unusable = sbi->unusable_block_count;
+	else
+		unusable = f2fs_get_unusable_blocks(sbi);
+	return sprintf(buf, "%llu\n", (unsigned long long)unusable);
+}
+
+static ssize_t encoding_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+#ifdef CONFIG_UNICODE
+	if (f2fs_sb_has_casefold(sbi))
+		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
+			sbi->s_encoding->charset,
+			(sbi->s_encoding->version >> 16) & 0xff,
+			(sbi->s_encoding->version >> 8) & 0xff,
+			sbi->s_encoding->version & 0xff);
+#endif
+	return sprintf(buf, "(none)");
 }
 
+#ifdef CONFIG_F2FS_STAT_FS
+static ssize_t moved_blocks_foreground_show(struct f2fs_attr *a,
+				struct f2fs_sb_info *sbi, char *buf)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+	return sprintf(buf, "%llu\n",
+		(unsigned long long)(si->tot_blks -
+			(si->bg_data_blks + si->bg_node_blks)));
+}
+
+static ssize_t moved_blocks_background_show(struct f2fs_attr *a,
+				struct f2fs_sb_info *sbi, char *buf)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+	return sprintf(buf, "%llu\n",
+		(unsigned long long)(si->bg_data_blks + si->bg_node_blks));
+}
+
+static ssize_t avg_vblocks_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	struct f2fs_stat_info *si = F2FS_STAT(sbi);
+
+	si->dirty_count = dirty_segments(sbi);
+	f2fs_update_sit_info(sbi);
+	return sprintf(buf, "%llu\n", (unsigned long long)(si->avg_vblocks));
+}
+#endif
+
 static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 			struct f2fs_sb_info *sbi, char *buf)
 {
@@ -199,7 +249,7 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 
 	ui = (unsigned int *)(ptr + a->offset);
 
-	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+	return sprintf(buf, "%u\n", *ui);
 }
 
 static ssize_t __sbi_store(struct f2fs_attr *a,
@@ -389,6 +439,7 @@ enum feat_id {
 	FEAT_VERITY,
 	FEAT_SB_CHECKSUM,
 	FEAT_CASEFOLD,
+	FEAT_COMPRESSION,
 };
 
 static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@@ -408,7 +459,8 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
 	case FEAT_VERITY:
 	case FEAT_SB_CHECKSUM:
 	case FEAT_CASEFOLD:
-		return snprintf(buf, PAGE_SIZE, "supported\n");
+	case FEAT_COMPRESSION:
+		return sprintf(buf, "supported\n");
 	}
 	return 0;
 }
@@ -437,6 +489,14 @@ static struct f2fs_attr f2fs_attr_##_name = {			\
 	.id	= _id,						\
 }
 
+#define F2FS_STAT_ATTR(_struct_type, _struct_name, _name, _elname)	\
+static struct f2fs_attr f2fs_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = 0444 },	\
+	.show = f2fs_sbi_show,					\
+	.struct_type = _struct_type,				\
+	.offset = offsetof(struct _struct_name, _elname),       \
+}
+
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time,
 							urgent_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
@@ -478,11 +538,21 @@ F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
 F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
 #endif
 F2FS_GENERAL_RO_ATTR(dirty_segments);
+F2FS_GENERAL_RO_ATTR(free_segments);
 F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 F2FS_GENERAL_RO_ATTR(features);
 F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
 F2FS_GENERAL_RO_ATTR(unusable);
 F2FS_GENERAL_RO_ATTR(encoding);
+#ifdef CONFIG_F2FS_STAT_FS
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, gc_foreground_calls, call_count);
+F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, gc_background_calls, bg_gc);
+F2FS_GENERAL_RO_ATTR(moved_blocks_background);
+F2FS_GENERAL_RO_ATTR(moved_blocks_foreground);
+F2FS_GENERAL_RO_ATTR(avg_vblocks);
+#endif
 
 #ifdef CONFIG_FS_ENCRYPTION
 F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
@@ -503,6 +573,7 @@ F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY);
 #endif
 F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
 F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
+F2FS_FEATURE_RO_ATTR(compression, FEAT_COMPRESSION);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -543,12 +614,22 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(inject_type),
 #endif
 	ATTR_LIST(dirty_segments),
+	ATTR_LIST(free_segments),
 	ATTR_LIST(unusable),
 	ATTR_LIST(lifetime_write_kbytes),
 	ATTR_LIST(features),
 	ATTR_LIST(reserved_blocks),
 	ATTR_LIST(current_reserved_blocks),
 	ATTR_LIST(encoding),
+#ifdef CONFIG_F2FS_STAT_FS
+	ATTR_LIST(cp_foreground_calls),
+	ATTR_LIST(cp_background_calls),
+	ATTR_LIST(gc_foreground_calls),
+	ATTR_LIST(gc_background_calls),
+	ATTR_LIST(moved_blocks_foreground),
+	ATTR_LIST(moved_blocks_background),
+	ATTR_LIST(avg_vblocks),
+#endif
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs);
@@ -573,6 +654,7 @@ static struct attribute *f2fs_feat_attrs[] = {
 #endif
 	ATTR_LIST(sb_checksum),
 	ATTR_LIST(casefold),
+	ATTR_LIST(compression),
 	NULL,
 };
 ATTRIBUTE_GROUPS(f2fs_feat);
@@ -733,10 +815,12 @@ int __init f2fs_init_sysfs(void)
 
 	ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype,
 				   NULL, "features");
-	if (ret)
+	if (ret) {
+		kobject_put(&f2fs_feat);
 		kset_unregister(&f2fs_kset);
-	else
+	} else {
 		f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+	}
 	return ret;
 }
 
@@ -757,8 +841,11 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
 	init_completion(&sbi->s_kobj_unregister);
 	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL,
 				"%s", sb->s_id);
-	if (err)
+	if (err) {
+		kobject_put(&sbi->s_kobj);
+		wait_for_completion(&sbi->s_kobj_unregister);
 		return err;
+	}
 
 	if (f2fs_proc_root)
 		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
@@ -786,4 +873,5 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
 		remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
 	}
 	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
 }
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 1e08bd54c5fb..f1b2a1fc2a6a 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -271,6 +271,14 @@ static inline struct timespec64 fat_timespec64_trunc_2secs(struct timespec64 ts)
 {
 	return (struct timespec64){ ts.tv_sec & ~1ULL, 0 };
 }
+
+static inline struct timespec64 fat_timespec64_trunc_10ms(struct timespec64 ts)
+{
+	if (ts.tv_nsec)
+		ts.tv_nsec -= ts.tv_nsec % 10000000UL;
+	return ts;
+}
+
 /*
  * truncate the various times with appropriate granularity:
  *   root inode:
@@ -308,7 +316,7 @@ int fat_truncate_time(struct inode *inode, struct timespec64 *now, int flags)
 	}
 	if (flags & S_CTIME) {
 		if (sbi->options.isvfat)
-			inode->i_ctime = timespec64_trunc(*now, 10000000);
+			inode->i_ctime = fat_timespec64_trunc_10ms(*now);
 		else
 			inode->i_ctime = fat_timespec64_trunc_2secs(*now);
 	}
diff --git a/fs/file.c b/fs/file.c
index 3da91a112bab..a364e1a9b7e8 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -642,7 +642,9 @@ out_unlock:
 EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
 
 /*
- * variant of __close_fd that gets a ref on the file for later fput
+ * variant of __close_fd that gets a ref on the file for later fput.
+ * The caller must ensure that filp_close() called on the file, and then
+ * an fput().
  */
 int __close_fd_get_file(unsigned int fd, struct file **res)
 {
@@ -662,7 +664,7 @@ int __close_fd_get_file(unsigned int fd, struct file **res)
 	spin_unlock(&files->file_lock);
 	get_file(file);
 	*res = file;
-	return filp_close(file, files);
+	return 0;
 
 out_unlock:
 	spin_unlock(&files->file_lock);
@@ -706,9 +708,9 @@ void do_close_on_exec(struct files_struct *files)
 	spin_unlock(&files->file_lock);
 }
 
-static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
+static struct file *__fget_files(struct files_struct *files, unsigned int fd,
+				 fmode_t mask, unsigned int refs)
 {
-	struct files_struct *files = current->files;
 	struct file *file;
 
 	rcu_read_lock();
@@ -729,6 +731,12 @@ loop:
 	return file;
 }
 
+static inline struct file *__fget(unsigned int fd, fmode_t mask,
+				  unsigned int refs)
+{
+	return __fget_files(current->files, fd, mask, refs);
+}
+
 struct file *fget_many(unsigned int fd, unsigned int refs)
 {
 	return __fget(fd, FMODE_PATH, refs);
@@ -746,6 +754,18 @@ struct file *fget_raw(unsigned int fd)
 }
 EXPORT_SYMBOL(fget_raw);
 
+struct file *fget_task(struct task_struct *task, unsigned int fd)
+{
+	struct file *file = NULL;
+
+	task_lock(task);
+	if (task->files)
+		file = __fget_files(task->files, fd, 0, 1);
+	task_unlock(task);
+
+	return file;
+}
+
 /*
  * Lightweight file lookup - no refcnt increment if fd table isn't shared.
  *
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 335607b8c5c0..76ac9c7d32ec 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2063,7 +2063,7 @@ void wb_workfn(struct work_struct *work)
 						struct bdi_writeback, dwork);
 	long pages_written;
 
-	set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
+	set_worker_desc("flush-%s", bdi_dev_name(wb->bdi));
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 9616af3768e1..08e91efbce53 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -111,7 +111,7 @@ extern void fscache_enqueue_object(struct fscache_object *);
  * object-list.c
  */
 #ifdef CONFIG_FSCACHE_OBJECT_LIST
-extern const struct file_operations fscache_objlist_fops;
+extern const struct proc_ops fscache_objlist_proc_ops;
 
 extern void fscache_objlist_add(struct fscache_object *);
 extern void fscache_objlist_remove(struct fscache_object *);
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 72ebfe578f40..e106a1a1600d 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -7,6 +7,7 @@
 
 #define FSCACHE_DEBUG_LEVEL COOKIE
 #include <linux/module.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/key.h>
@@ -405,9 +406,9 @@ static int fscache_objlist_release(struct inode *inode, struct file *file)
 	return seq_release(inode, file);
 }
 
-const struct file_operations fscache_objlist_fops = {
-	.open		= fscache_objlist_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= fscache_objlist_release,
+const struct proc_ops fscache_objlist_proc_ops = {
+	.proc_open	= fscache_objlist_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= fscache_objlist_release,
 };
diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c
index 5523446e2952..90a7bc22f7e1 100644
--- a/fs/fscache/proc.c
+++ b/fs/fscache/proc.c
@@ -35,7 +35,7 @@ int __init fscache_proc_init(void)
 
 #ifdef CONFIG_FSCACHE_OBJECT_LIST
 	if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL,
-			 &fscache_objlist_fops))
+			 &fscache_objlist_proc_ops))
 		goto error_objects;
 #endif
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9c6df721321a..ba83b49ce18c 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -183,14 +183,12 @@ static int gfs2_jdata_writepage(struct page *page, struct writeback_control *wbc
 	struct inode *inode = page->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int ret;
 
 	if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(ip->i_gl)))
 		goto out;
 	if (PageChecked(page) || current->journal_info)
 		goto out_ignore;
-	ret = __gfs2_jdata_writepage(page, wbc);
-	return ret;
+	return __gfs2_jdata_writepage(page, wbc);
 
 out_ignore:
 	redirty_page_for_writepage(wbc, page);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index eb9c0578978f..c8b62577e2f2 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -73,9 +73,6 @@
 #include "bmap.h"
 #include "util.h"
 
-#define IS_LEAF     1 /* Hashed (leaf) directory */
-#define IS_DINODE   2 /* Linear (stuffed dinode block) directory */
-
 #define MAX_RA_BLOCKS 32 /* max read-ahead blocks */
 
 #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index b7123de7c180..d0eceaff3cea 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -826,7 +826,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
 
 	if (glops->go_flags & GLOF_LVB) {
-		gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS);
+		gl->gl_lksb.sb_lvbptr = kzalloc(GDLM_LVB_SIZE, GFP_NOFS);
 		if (!gl->gl_lksb.sb_lvbptr) {
 			kmem_cache_free(cachep, gl);
 			return -ENOMEM;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 4ede1f18de85..061d22e1ceb6 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -95,7 +95,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	/* A shortened, inline version of gfs2_trans_begin()
          * tr->alloced is not set since the transaction structure is
          * on the stack */
-	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
+	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes);
 	tr.tr_ip = _RET_IP_;
 	if (gfs2_log_reserve(sdp, tr.tr_reserved) < 0)
 		return;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 5f89c515f5bb..9fd88ed18807 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -387,8 +387,6 @@ struct gfs2_glock {
 	struct rhash_head gl_node;
 };
 
-#define GFS2_MIN_LVB_SIZE 32	/* Min size of LVB that gfs2 supports */
-
 enum {
 	GIF_INVALID		= 0,
 	GIF_QD_LOCKED		= 1,
@@ -505,6 +503,7 @@ struct gfs2_trans {
 	unsigned int tr_num_buf_rm;
 	unsigned int tr_num_databuf_rm;
 	unsigned int tr_num_revoke;
+	unsigned int tr_num_revoke_rm;
 
 	struct list_head tr_list;
 	struct list_head tr_databuf;
@@ -703,6 +702,7 @@ struct gfs2_sbd {
 	u32 sd_fsb2bb_shift;
 	u32 sd_diptrs;	/* Number of pointers in a dinode */
 	u32 sd_inptrs;	/* Number of pointers in a indirect block */
+	u32 sd_ldptrs;  /* Number of pointers in a log descriptor block */
 	u32 sd_jbsize;	/* Size of a journaled data block */
 	u32 sd_hash_bsize;	/* sizeof(exhash block) */
 	u32 sd_hash_bsize_shift;
@@ -803,7 +803,7 @@ struct gfs2_sbd {
 
 	struct gfs2_trans *sd_log_tr;
 	unsigned int sd_log_blks_reserved;
-	int sd_log_commited_revoke;
+	int sd_log_committed_revoke;
 
 	atomic_t sd_log_pinned;
 	unsigned int sd_log_num_revoke;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index dafef10b91f1..2716d56ed0a0 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -136,7 +136,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 
 	if (inode->i_state & I_NEW) {
 		struct gfs2_sbd *sdp = GFS2_SB(inode);
-		ip->i_no_formal_ino = no_formal_ino;
 
 		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
 		if (unlikely(error))
@@ -175,21 +174,22 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 		gfs2_glock_put(io_gl);
 		io_gl = NULL;
 
+		/* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */
+		inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1);
+		inode->i_atime.tv_nsec = 0;
+
 		if (type == DT_UNKNOWN) {
 			/* Inode glock must be locked already */
 			error = gfs2_inode_refresh(GFS2_I(inode));
 			if (error)
 				goto fail_refresh;
 		} else {
+			ip->i_no_formal_ino = no_formal_ino;
 			inode->i_mode = DT2IF(type);
 		}
 
 		gfs2_set_iop(inode);
 
-		/* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */
-		inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1);
-		inode->i_atime.tv_nsec = 0;
-
 		unlock_new_inode(inode);
 	}
 
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index eb3f2e7b8085..00a2e721a374 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -37,7 +37,6 @@ static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
  * gfs2_struct2blk - compute stuff
  * @sdp: the filesystem
  * @nstruct: the number of structures
- * @ssize: the size of the structures
  *
  * Compute the number of log descriptor blocks needed to hold a certain number
  * of structures of a certain size.
@@ -45,18 +44,16 @@ static void gfs2_log_shutdown(struct gfs2_sbd *sdp);
  * Returns: the number of blocks needed (minimum is always 1)
  */
 
-unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
-			     unsigned int ssize)
+unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct)
 {
 	unsigned int blks;
 	unsigned int first, second;
 
 	blks = 1;
-	first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
+	first = sdp->sd_ldptrs;
 
 	if (nstruct > first) {
-		second = (sdp->sd_sb.sb_bsize -
-			  sizeof(struct gfs2_meta_header)) / ssize;
+		second = sdp->sd_inptrs;
 		blks += DIV_ROUND_UP(nstruct - first, second);
 	}
 
@@ -472,9 +469,8 @@ static unsigned int calc_reserved(struct gfs2_sbd *sdp)
 		reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
 	}
 
-	if (sdp->sd_log_commited_revoke > 0)
-		reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
-					  sizeof(u64));
+	if (sdp->sd_log_committed_revoke > 0)
+		reserved += gfs2_struct2blk(sdp, sdp->sd_log_committed_revoke);
 	/* One for the overall header */
 	if (reserved)
 		reserved++;
@@ -829,7 +825,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 	if (unlikely(state == SFS_FROZEN))
 		gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
 	gfs2_assert_withdraw(sdp,
-			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
+			sdp->sd_log_num_revoke == sdp->sd_log_committed_revoke);
 
 	gfs2_ordered_write(sdp);
 	lops_before_commit(sdp, tr);
@@ -848,7 +844,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 	gfs2_log_lock(sdp);
 	sdp->sd_log_head = sdp->sd_log_flush_head;
 	sdp->sd_log_blks_reserved = 0;
-	sdp->sd_log_commited_revoke = 0;
+	sdp->sd_log_committed_revoke = 0;
 
 	spin_lock(&sdp->sd_ail_lock);
 	if (tr && !list_empty(&tr->tr_ail1_list)) {
@@ -899,6 +895,7 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 	old->tr_num_buf_rm	+= new->tr_num_buf_rm;
 	old->tr_num_databuf_rm	+= new->tr_num_databuf_rm;
 	old->tr_num_revoke	+= new->tr_num_revoke;
+	old->tr_num_revoke_rm	+= new->tr_num_revoke_rm;
 
 	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
 	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
@@ -920,7 +917,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 		set_bit(TR_ATTACHED, &tr->tr_flags);
 	}
 
-	sdp->sd_log_commited_revoke += tr->tr_num_revoke;
+	sdp->sd_log_committed_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
 	reserved = calc_reserved(sdp);
 	maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
 	gfs2_assert_withdraw(sdp, maxres >= reserved);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 2ff163a8dce1..c0a65e5a126b 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -60,9 +60,9 @@ static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
 		spin_unlock(&sdp->sd_ordered_lock);
 	}
 }
+
 extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
-extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
-			    unsigned int ssize);
+extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct);
 
 extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
 extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 55fed7daf2b1..d9431724b788 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -259,7 +259,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
 	struct super_block *sb = sdp->sd_vfs;
 	struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
 
-	bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
+	bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9);
 	bio_set_dev(bio, sb->s_bdev);
 	bio->bi_end_io = end_io;
 	bio->bi_private = sdp;
@@ -472,6 +472,20 @@ static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index,
 	put_page(page); /* Once more for find_or_create_page */
 }
 
+static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs)
+{
+	struct bio *new;
+
+	new = bio_alloc(GFP_NOIO, nr_iovecs);
+	bio_copy_dev(new, prev);
+	new->bi_iter.bi_sector = bio_end_sector(prev);
+	new->bi_opf = prev->bi_opf;
+	new->bi_write_hint = prev->bi_write_hint;
+	bio_chain(new, prev);
+	submit_bio(prev);
+	return new;
+}
+
 /**
  * gfs2_find_jhead - find the head of a log
  * @jd: The journal descriptor
@@ -488,15 +502,15 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 	struct address_space *mapping = jd->jd_inode->i_mapping;
 	unsigned int block = 0, blocks_submitted = 0, blocks_read = 0;
-	unsigned int bsize = sdp->sd_sb.sb_bsize;
+	unsigned int bsize = sdp->sd_sb.sb_bsize, off;
 	unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
 	unsigned int shift = PAGE_SHIFT - bsize_shift;
-	unsigned int readhead_blocks = BIO_MAX_PAGES << shift;
+	unsigned int readahead_blocks = BIO_MAX_PAGES << shift;
 	struct gfs2_journal_extent *je;
 	int sz, ret = 0;
 	struct bio *bio = NULL;
 	struct page *page = NULL;
-	bool done = false;
+	bool bio_chained = false, done = false;
 	errseq_t since;
 
 	memset(head, 0, sizeof(*head));
@@ -505,9 +519,9 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 
 	since = filemap_sample_wb_err(mapping);
 	list_for_each_entry(je, &jd->extent_list, list) {
-		for (; block < je->lblock + je->blocks; block++) {
-			u64 dblock;
+		u64 dblock = je->dblock;
 
+		for (; block < je->lblock + je->blocks; block++, dblock++) {
 			if (!page) {
 				page = find_or_create_page(mapping,
 						block >> shift, GFP_NOFS);
@@ -516,35 +530,41 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
 					done = true;
 					goto out;
 				}
+				off = 0;
 			}
 
-			if (bio) {
-				unsigned int off;
-
-				off = (block << bsize_shift) & ~PAGE_MASK;
+			if (!bio || (bio_chained && !off)) {
+				/* start new bio */
+			} else {
 				sz = bio_add_page(bio, page, bsize, off);
-				if (sz == bsize) { /* block added */
-					if (off + bsize == PAGE_SIZE) {
-						page = NULL;
-						goto page_added;
-					}
-					continue;
+				if (sz == bsize)
+					goto block_added;
+				if (off) {
+					unsigned int blocks =
+						(PAGE_SIZE - off) >> bsize_shift;
+
+					bio = gfs2_chain_bio(bio, blocks);
+					bio_chained = true;
+					goto add_block_to_new_bio;
 				}
+			}
+
+			if (bio) {
 				blocks_submitted = block + 1;
 				submit_bio(bio);
-				bio = NULL;
 			}
 
-			dblock = je->dblock + (block - je->lblock);
 			bio = gfs2_log_alloc_bio(sdp, dblock, gfs2_end_log_read);
 			bio->bi_opf = REQ_OP_READ;
-			sz = bio_add_page(bio, page, bsize, 0);
-			gfs2_assert_warn(sdp, sz == bsize);
-			if (bsize == PAGE_SIZE)
+			bio_chained = false;
+add_block_to_new_bio:
+			sz = bio_add_page(bio, page, bsize, off);
+			BUG_ON(sz != bsize);
+block_added:
+			off += bsize;
+			if (off == PAGE_SIZE)
 				page = NULL;
-
-page_added:
-			if (blocks_submitted < blocks_read + readhead_blocks) {
+			if (blocks_submitted < blocks_read + readahead_blocks) {
 				/* Keep at least one bio in flight */
 				continue;
 			}
@@ -846,7 +866,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	if (!sdp->sd_log_num_revoke)
 		return;
 
-	length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64));
+	length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke);
 	page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke);
 	offset = sizeof(struct gfs2_log_descriptor);
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index e8b7b0ce8404..b3e904bcc02c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -298,6 +298,8 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
 			  sizeof(struct gfs2_dinode)) / sizeof(u64);
 	sdp->sd_inptrs = (sdp->sd_sb.sb_bsize -
 			  sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	sdp->sd_ldptrs = (sdp->sd_sb.sb_bsize -
+			  sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
 	sdp->sd_jbsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header);
 	sdp->sd_hash_bsize = sdp->sd_sb.sb_bsize / 2;
 	sdp->sd_hash_bsize_shift = sdp->sd_sb.sb_bsize_shift - 1;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 2466bb44a23c..e7bf91ec231c 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -36,16 +36,6 @@
 #define BFITNOENT ((u32)~0)
 #define NO_BLOCK ((u64)~0)
 
-#if BITS_PER_LONG == 32
-#define LBITMASK   (0x55555555UL)
-#define LBITSKIP55 (0x55555555UL)
-#define LBITSKIP00 (0x00000000UL)
-#else
-#define LBITMASK   (0x5555555555555555UL)
-#define LBITSKIP55 (0x5555555555555555UL)
-#define LBITSKIP00 (0x0000000000000000UL)
-#endif
-
 /*
  * These routines are used by the resource group routines (rgrp.c)
  * to keep track of block allocation.  Each block is represented by two
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 9d4227330de4..a685637a5b55 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -49,8 +49,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	if (blocks)
 		tr->tr_reserved += 6 + blocks;
 	if (revokes)
-		tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
-						   sizeof(u64));
+		tr->tr_reserved += gfs2_struct2blk(sdp, revokes);
 	INIT_LIST_HEAD(&tr->tr_databuf);
 	INIT_LIST_HEAD(&tr->tr_buf);
 
@@ -77,10 +76,10 @@ static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr)
 	fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n",
 		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
 		test_bit(TR_TOUCHED, &tr->tr_flags));
-	fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u\n",
+	fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
 		tr->tr_num_buf_new, tr->tr_num_buf_rm,
 		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
-		tr->tr_num_revoke);
+		tr->tr_num_revoke, tr->tr_num_revoke_rm);
 }
 
 void gfs2_trans_end(struct gfs2_sbd *sdp)
@@ -265,7 +264,7 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
 			if (bd->bd_gl)
 				gfs2_glock_remove_revoke(bd->bd_gl);
 			kmem_cache_free(gfs2_bufdata_cachep, bd);
-			tr->tr_num_revoke--;
+			tr->tr_num_revoke_rm++;
 			if (--n == 0)
 				break;
 		}
diff --git a/fs/inode.c b/fs/inode.c
index ea15c6d9f274..c7418b0b4168 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1683,12 +1683,9 @@ EXPORT_SYMBOL(generic_update_time);
  */
 static int update_time(struct inode *inode, struct timespec64 *time, int flags)
 {
-	int (*update_time)(struct inode *, struct timespec64 *, int);
-
-	update_time = inode->i_op->update_time ? inode->i_op->update_time :
-		generic_update_time;
-
-	return update_time(inode, time, flags);
+	if (inode->i_op->update_time)
+		return inode->i_op->update_time(inode, time, flags);
+	return generic_update_time(inode, time, flags);
 }
 
 /**
@@ -2154,30 +2151,6 @@ void inode_nohighmem(struct inode *inode)
 EXPORT_SYMBOL(inode_nohighmem);
 
 /**
- * timespec64_trunc - Truncate timespec64 to a granularity
- * @t: Timespec64
- * @gran: Granularity in ns.
- *
- * Truncate a timespec64 to a granularity. Always rounds down. gran must
- * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns).
- */
-struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran)
-{
-	/* Avoid division in the common cases 1 ns and 1 s. */
-	if (gran == 1) {
-		/* nothing */
-	} else if (gran == NSEC_PER_SEC) {
-		t.tv_nsec = 0;
-	} else if (gran > 1 && gran < NSEC_PER_SEC) {
-		t.tv_nsec -= t.tv_nsec % gran;
-	} else {
-		WARN(1, "illegal file time granularity: %u", gran);
-	}
-	return t;
-}
-EXPORT_SYMBOL(timespec64_trunc);
-
-/**
  * timestamp_truncate - Truncate timespec to a granularity
  * @t: Timespec
  * @inode: inode being updated
diff --git a/fs/internal.h b/fs/internal.h
index e3fa69544b66..f3f280b952a3 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -124,6 +124,8 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname,
 		const struct open_flags *op);
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *);
+extern struct open_how build_open_how(int flags, umode_t mode);
+extern int build_open_flags(const struct open_how *how, struct open_flags *op);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 long do_faccessat(int dfd, const char __user *filename, int mode);
@@ -180,11 +182,11 @@ extern void mnt_pin_kill(struct mount *m);
  */
 extern const struct dentry_operations ns_dentry_operations;
 
-/*
- * fs/ioctl.c
- */
-extern int do_vfs_ioctl(struct file *file, unsigned int fd, unsigned int cmd,
-		    unsigned long arg);
-
 /* direct-io.c: */
 int sb_init_dio_done_wq(struct super_block *sb);
+
+/*
+ * fs/stat.c:
+ */
+unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags);
+int cp_statx(const struct kstat *stat, struct statx __user *buffer);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 5147d2213b01..cb60a42b9fdf 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -56,7 +56,8 @@ struct io_worker {
 
 	struct rcu_head rcu;
 	struct mm_struct *mm;
-	const struct cred *creds;
+	const struct cred *cur_creds;
+	const struct cred *saved_creds;
 	struct files_struct *restore_files;
 };
 
@@ -109,10 +110,10 @@ struct io_wq {
 
 	struct task_struct *manager;
 	struct user_struct *user;
-	const struct cred *creds;
-	struct mm_struct *mm;
 	refcount_t refs;
 	struct completion done;
+
+	refcount_t use_refs;
 };
 
 static bool io_worker_get(struct io_worker *worker)
@@ -135,9 +136,9 @@ static bool __io_worker_unuse(struct io_wqe *wqe, struct io_worker *worker)
 {
 	bool dropped_lock = false;
 
-	if (worker->creds) {
-		revert_creds(worker->creds);
-		worker->creds = NULL;
+	if (worker->saved_creds) {
+		revert_creds(worker->saved_creds);
+		worker->cur_creds = worker->saved_creds = NULL;
 	}
 
 	if (current->files != worker->restore_files) {
@@ -396,6 +397,43 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe, unsigned *hash)
 	return NULL;
 }
 
+static void io_wq_switch_mm(struct io_worker *worker, struct io_wq_work *work)
+{
+	if (worker->mm) {
+		unuse_mm(worker->mm);
+		mmput(worker->mm);
+		worker->mm = NULL;
+	}
+	if (!work->mm) {
+		set_fs(KERNEL_DS);
+		return;
+	}
+	if (mmget_not_zero(work->mm)) {
+		use_mm(work->mm);
+		if (!worker->mm)
+			set_fs(USER_DS);
+		worker->mm = work->mm;
+		/* hang on to this mm */
+		work->mm = NULL;
+		return;
+	}
+
+	/* failed grabbing mm, ensure work gets cancelled */
+	work->flags |= IO_WQ_WORK_CANCEL;
+}
+
+static void io_wq_switch_creds(struct io_worker *worker,
+			       struct io_wq_work *work)
+{
+	const struct cred *old_creds = override_creds(work->creds);
+
+	worker->cur_creds = work->creds;
+	if (worker->saved_creds)
+		put_cred(old_creds); /* creds set by previous switch */
+	else
+		worker->saved_creds = old_creds;
+}
+
 static void io_worker_handle_work(struct io_worker *worker)
 	__releases(wqe->lock)
 {
@@ -438,24 +476,19 @@ next:
 		if (work->flags & IO_WQ_WORK_CB)
 			work->func(&work);
 
-		if ((work->flags & IO_WQ_WORK_NEEDS_FILES) &&
-		    current->files != work->files) {
+		if (work->files && current->files != work->files) {
 			task_lock(current);
 			current->files = work->files;
 			task_unlock(current);
 		}
-		if ((work->flags & IO_WQ_WORK_NEEDS_USER) && !worker->mm &&
-		    wq->mm) {
-			if (mmget_not_zero(wq->mm)) {
-				use_mm(wq->mm);
-				set_fs(USER_DS);
-				worker->mm = wq->mm;
-			} else {
-				work->flags |= IO_WQ_WORK_CANCEL;
-			}
-		}
-		if (!worker->creds)
-			worker->creds = override_creds(wq->creds);
+		if (work->mm != worker->mm)
+			io_wq_switch_mm(worker, work);
+		if (worker->cur_creds != work->creds)
+			io_wq_switch_creds(worker, work);
+		/*
+		 * OK to set IO_WQ_WORK_CANCEL even for uncancellable work,
+		 * the worker function will do the right thing.
+		 */
 		if (test_bit(IO_WQ_BIT_CANCEL, &wq->state))
 			work->flags |= IO_WQ_WORK_CANCEL;
 		if (worker->mm)
@@ -720,6 +753,7 @@ static bool io_wq_can_queue(struct io_wqe *wqe, struct io_wqe_acct *acct,
 static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 {
 	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
+	int work_flags;
 	unsigned long flags;
 
 	/*
@@ -734,12 +768,14 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 		return;
 	}
 
+	work_flags = work->flags;
 	spin_lock_irqsave(&wqe->lock, flags);
 	wq_list_add_tail(&work->list, &wqe->work_list);
 	wqe->flags &= ~IO_WQE_FLAG_STALLED;
 	spin_unlock_irqrestore(&wqe->lock, flags);
 
-	if (!atomic_read(&acct->nr_running))
+	if ((work_flags & IO_WQ_WORK_CONCURRENT) ||
+	    !atomic_read(&acct->nr_running))
 		io_wqe_wake_worker(wqe, acct);
 }
 
@@ -828,6 +864,7 @@ static bool io_work_cancel(struct io_worker *worker, void *cancel_data)
 	 */
 	spin_lock_irqsave(&worker->lock, flags);
 	if (worker->cur_work &&
+	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL) &&
 	    data->cancel(worker->cur_work, data->caller_data)) {
 		send_sig(SIGINT, worker->task, 1);
 		ret = true;
@@ -902,7 +939,8 @@ static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
 		return false;
 
 	spin_lock_irqsave(&worker->lock, flags);
-	if (worker->cur_work == work) {
+	if (worker->cur_work == work &&
+	    !(worker->cur_work->flags & IO_WQ_WORK_NO_CANCEL)) {
 		send_sig(SIGINT, worker->task, 1);
 		ret = true;
 	}
@@ -1026,7 +1064,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 
 	/* caller must already hold a reference to this */
 	wq->user = data->user;
-	wq->creds = data->creds;
 
 	for_each_node(node) {
 		struct io_wqe *wqe;
@@ -1053,9 +1090,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 
 	init_completion(&wq->done);
 
-	/* caller must have already done mmgrab() on this mm */
-	wq->mm = data->mm;
-
 	wq->manager = kthread_create(io_wq_manager, wq, "io_wq_manager");
 	if (!IS_ERR(wq->manager)) {
 		wake_up_process(wq->manager);
@@ -1064,6 +1098,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 			ret = -ENOMEM;
 			goto err;
 		}
+		refcount_set(&wq->use_refs, 1);
 		reinit_completion(&wq->done);
 		return wq;
 	}
@@ -1078,13 +1113,21 @@ err:
 	return ERR_PTR(ret);
 }
 
+bool io_wq_get(struct io_wq *wq, struct io_wq_data *data)
+{
+	if (data->get_work != wq->get_work || data->put_work != wq->put_work)
+		return false;
+
+	return refcount_inc_not_zero(&wq->use_refs);
+}
+
 static bool io_wq_worker_wake(struct io_worker *worker, void *data)
 {
 	wake_up_process(worker->task);
 	return false;
 }
 
-void io_wq_destroy(struct io_wq *wq)
+static void __io_wq_destroy(struct io_wq *wq)
 {
 	int node;
 
@@ -1104,3 +1147,9 @@ void io_wq_destroy(struct io_wq *wq)
 	kfree(wq->wqes);
 	kfree(wq);
 }
+
+void io_wq_destroy(struct io_wq *wq)
+{
+	if (refcount_dec_and_test(&wq->use_refs))
+		__io_wq_destroy(wq);
+}
diff --git a/fs/io-wq.h b/fs/io-wq.h
index 3f5e356de980..50b3378febf2 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -7,11 +7,11 @@ enum {
 	IO_WQ_WORK_CANCEL	= 1,
 	IO_WQ_WORK_HAS_MM	= 2,
 	IO_WQ_WORK_HASHED	= 4,
-	IO_WQ_WORK_NEEDS_USER	= 8,
-	IO_WQ_WORK_NEEDS_FILES	= 16,
 	IO_WQ_WORK_UNBOUND	= 32,
 	IO_WQ_WORK_INTERNAL	= 64,
 	IO_WQ_WORK_CB		= 128,
+	IO_WQ_WORK_NO_CANCEL	= 256,
+	IO_WQ_WORK_CONCURRENT	= 512,
 
 	IO_WQ_HASH_SHIFT	= 24,	/* upper 8 bits are used for hash key */
 };
@@ -72,6 +72,8 @@ struct io_wq_work {
 	};
 	void (*func)(struct io_wq_work **);
 	struct files_struct *files;
+	struct mm_struct *mm;
+	const struct cred *creds;
 	unsigned flags;
 };
 
@@ -81,21 +83,22 @@ struct io_wq_work {
 		(work)->func = _func;			\
 		(work)->flags = 0;			\
 		(work)->files = NULL;			\
+		(work)->mm = NULL;			\
+		(work)->creds = NULL;			\
 	} while (0)					\
 
 typedef void (get_work_fn)(struct io_wq_work *);
 typedef void (put_work_fn)(struct io_wq_work *);
 
 struct io_wq_data {
-	struct mm_struct *mm;
 	struct user_struct *user;
-	const struct cred *creds;
 
 	get_work_fn *get_work;
 	put_work_fn *put_work;
 };
 
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
+bool io_wq_get(struct io_wq *wq, struct io_wq_data *data);
 void io_wq_destroy(struct io_wq *wq);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e54556b0fcc6..1806afddfea5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -46,6 +46,7 @@
 #include <linux/compat.h>
 #include <linux/refcount.h>
 #include <linux/uio.h>
+#include <linux/bits.h>
 
 #include <linux/sched/signal.h>
 #include <linux/fs.h>
@@ -70,6 +71,10 @@
 #include <linux/sizes.h>
 #include <linux/hugetlb.h>
 #include <linux/highmem.h>
+#include <linux/namei.h>
+#include <linux/fsnotify.h>
+#include <linux/fadvise.h>
+#include <linux/eventpoll.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/io_uring.h>
@@ -177,6 +182,21 @@ struct fixed_file_table {
 	struct file		**files;
 };
 
+enum {
+	FFD_F_ATOMIC,
+};
+
+struct fixed_file_data {
+	struct fixed_file_table		*table;
+	struct io_ring_ctx		*ctx;
+
+	struct percpu_ref		refs;
+	struct llist_head		put_llist;
+	unsigned long			state;
+	struct work_struct		ref_work;
+	struct completion		done;
+};
+
 struct io_ring_ctx {
 	struct {
 		struct percpu_ref	refs;
@@ -184,10 +204,11 @@ struct io_ring_ctx {
 
 	struct {
 		unsigned int		flags;
-		bool			compat;
-		bool			account_mem;
-		bool			cq_overflow_flushed;
-		bool			drain_next;
+		int			compat: 1;
+		int			account_mem: 1;
+		int			cq_overflow_flushed: 1;
+		int			drain_next: 1;
+		int			eventfd_async: 1;
 
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
@@ -207,13 +228,14 @@ struct io_ring_ctx {
 		unsigned		sq_thread_idle;
 		unsigned		cached_sq_dropped;
 		atomic_t		cached_cq_overflow;
-		struct io_uring_sqe	*sq_sqes;
+		unsigned long		sq_check_overflow;
 
 		struct list_head	defer_list;
 		struct list_head	timeout_list;
 		struct list_head	cq_overflow_list;
 
 		wait_queue_head_t	inflight_wait;
+		struct io_uring_sqe	*sq_sqes;
 	} ____cacheline_aligned_in_smp;
 
 	struct io_rings	*rings;
@@ -229,8 +251,10 @@ struct io_ring_ctx {
 	 * readers must ensure that ->refs is alive as long as the file* is
 	 * used. Only updated through io_uring_register(2).
 	 */
-	struct fixed_file_table	*file_table;
+	struct fixed_file_data	*file_data;
 	unsigned		nr_user_files;
+	int 			ring_fd;
+	struct file 		*ring_file;
 
 	/* if used, fixed mapped user buffers */
 	unsigned		nr_user_bufs;
@@ -250,11 +274,14 @@ struct io_ring_ctx {
 	struct socket		*ring_sock;
 #endif
 
+	struct idr		personality_idr;
+
 	struct {
 		unsigned		cached_cq_tail;
 		unsigned		cq_entries;
 		unsigned		cq_mask;
 		atomic_t		cq_timeouts;
+		unsigned long		cq_check_overflow;
 		struct wait_queue_head	cq_wait;
 		struct fasync_struct	*cq_fasync;
 		struct eventfd_ctx	*cq_ev_fd;
@@ -267,7 +294,8 @@ struct io_ring_ctx {
 
 	struct {
 		spinlock_t		completion_lock;
-		bool			poll_multi_file;
+		struct llist_head	poll_llist;
+
 		/*
 		 * ->poll_list is protected by the ctx->uring_lock for
 		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
@@ -277,6 +305,7 @@ struct io_ring_ctx {
 		struct list_head	poll_list;
 		struct hlist_head	*cancel_hash;
 		unsigned		cancel_hash_bits;
+		bool			poll_multi_file;
 
 		spinlock_t		inflight_lock;
 		struct list_head	inflight_list;
@@ -299,6 +328,12 @@ struct io_poll_iocb {
 	struct wait_queue_entry		wait;
 };
 
+struct io_close {
+	struct file			*file;
+	struct file			*put_file;
+	int				fd;
+};
+
 struct io_timeout_data {
 	struct io_kiocb			*req;
 	struct hrtimer			timer;
@@ -319,6 +354,7 @@ struct io_sync {
 	loff_t				len;
 	loff_t				off;
 	int				flags;
+	int				mode;
 };
 
 struct io_cancel {
@@ -348,8 +384,52 @@ struct io_connect {
 
 struct io_sr_msg {
 	struct file			*file;
-	struct user_msghdr __user	*msg;
+	union {
+		struct user_msghdr __user *msg;
+		void __user		*buf;
+	};
 	int				msg_flags;
+	size_t				len;
+};
+
+struct io_open {
+	struct file			*file;
+	int				dfd;
+	union {
+		unsigned		mask;
+	};
+	struct filename			*filename;
+	struct statx __user		*buffer;
+	struct open_how			how;
+};
+
+struct io_files_update {
+	struct file			*file;
+	u64				arg;
+	u32				nr_args;
+	u32				offset;
+};
+
+struct io_fadvise {
+	struct file			*file;
+	u64				offset;
+	u32				len;
+	u32				advice;
+};
+
+struct io_madvise {
+	struct file			*file;
+	u64				addr;
+	u32				len;
+	u32				advice;
+};
+
+struct io_epoll {
+	struct file			*file;
+	int				epfd;
+	int				op;
+	int				fd;
+	struct epoll_event		event;
 };
 
 struct io_async_connect {
@@ -370,15 +450,79 @@ struct io_async_rw {
 	ssize_t				size;
 };
 
+struct io_async_open {
+	struct filename			*filename;
+};
+
 struct io_async_ctx {
 	union {
 		struct io_async_rw	rw;
 		struct io_async_msghdr	msg;
 		struct io_async_connect	connect;
 		struct io_timeout_data	timeout;
+		struct io_async_open	open;
 	};
 };
 
+enum {
+	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
+	REQ_F_IO_DRAIN_BIT	= IOSQE_IO_DRAIN_BIT,
+	REQ_F_LINK_BIT		= IOSQE_IO_LINK_BIT,
+	REQ_F_HARDLINK_BIT	= IOSQE_IO_HARDLINK_BIT,
+	REQ_F_FORCE_ASYNC_BIT	= IOSQE_ASYNC_BIT,
+
+	REQ_F_LINK_NEXT_BIT,
+	REQ_F_FAIL_LINK_BIT,
+	REQ_F_INFLIGHT_BIT,
+	REQ_F_CUR_POS_BIT,
+	REQ_F_NOWAIT_BIT,
+	REQ_F_IOPOLL_COMPLETED_BIT,
+	REQ_F_LINK_TIMEOUT_BIT,
+	REQ_F_TIMEOUT_BIT,
+	REQ_F_ISREG_BIT,
+	REQ_F_MUST_PUNT_BIT,
+	REQ_F_TIMEOUT_NOSEQ_BIT,
+	REQ_F_COMP_LOCKED_BIT,
+};
+
+enum {
+	/* ctx owns file */
+	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
+	/* drain existing IO first */
+	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
+	/* linked sqes */
+	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
+	/* doesn't sever on completion < 0 */
+	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
+	/* IOSQE_ASYNC */
+	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+
+	/* already grabbed next link */
+	REQ_F_LINK_NEXT		= BIT(REQ_F_LINK_NEXT_BIT),
+	/* fail rest of links */
+	REQ_F_FAIL_LINK		= BIT(REQ_F_FAIL_LINK_BIT),
+	/* on inflight list */
+	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
+	/* read/write uses file position */
+	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
+	/* must not punt to workers */
+	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
+	/* polled IO has completed */
+	REQ_F_IOPOLL_COMPLETED	= BIT(REQ_F_IOPOLL_COMPLETED_BIT),
+	/* has linked timeout */
+	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
+	/* timeout request */
+	REQ_F_TIMEOUT		= BIT(REQ_F_TIMEOUT_BIT),
+	/* regular file */
+	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
+	/* must be punted even for NONBLOCK */
+	REQ_F_MUST_PUNT		= BIT(REQ_F_MUST_PUNT_BIT),
+	/* no timeout sequence */
+	REQ_F_TIMEOUT_NOSEQ	= BIT(REQ_F_TIMEOUT_NOSEQ_BIT),
+	/* completion under lock */
+	REQ_F_COMP_LOCKED	= BIT(REQ_F_COMP_LOCKED_BIT),
+};
+
 /*
  * NOTE! Each of the iocb union members has the file pointer
  * as the first entry in their struct definition. So you can
@@ -396,11 +540,19 @@ struct io_kiocb {
 		struct io_timeout	timeout;
 		struct io_connect	connect;
 		struct io_sr_msg	sr_msg;
+		struct io_open		open;
+		struct io_close		close;
+		struct io_files_update	files_update;
+		struct io_fadvise	fadvise;
+		struct io_madvise	madvise;
+		struct io_epoll		epoll;
 	};
 
 	struct io_async_ctx		*io;
-	struct file			*ring_file;
-	int				ring_fd;
+	/*
+	 * llist_node is only used for poll deferred completions
+	 */
+	struct llist_node		llist_node;
 	bool				has_user;
 	bool				in_async;
 	bool				needs_fixed_file;
@@ -414,23 +566,6 @@ struct io_kiocb {
 	struct list_head	link_list;
 	unsigned int		flags;
 	refcount_t		refs;
-#define REQ_F_NOWAIT		1	/* must not punt to workers */
-#define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
-#define REQ_F_FIXED_FILE	4	/* ctx owns file */
-#define REQ_F_LINK_NEXT		8	/* already grabbed next link */
-#define REQ_F_IO_DRAIN		16	/* drain existing IO first */
-#define REQ_F_IO_DRAINED	32	/* drain done */
-#define REQ_F_LINK		64	/* linked sqes */
-#define REQ_F_LINK_TIMEOUT	128	/* has linked timeout */
-#define REQ_F_FAIL_LINK		256	/* fail rest of links */
-#define REQ_F_DRAIN_LINK	512	/* link should be fully drained */
-#define REQ_F_TIMEOUT		1024	/* timeout request */
-#define REQ_F_ISREG		2048	/* regular file */
-#define REQ_F_MUST_PUNT		4096	/* must be punted even for NONBLOCK */
-#define REQ_F_TIMEOUT_NOSEQ	8192	/* no timeout sequence */
-#define REQ_F_INFLIGHT		16384	/* on inflight list */
-#define REQ_F_COMP_LOCKED	32768	/* completion under lock */
-#define REQ_F_HARDLINK		65536	/* doesn't sever on completion < 0 */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -463,14 +598,162 @@ struct io_submit_state {
 	unsigned int		ios_left;
 };
 
+struct io_op_def {
+	/* needs req->io allocated for deferral/async */
+	unsigned		async_ctx : 1;
+	/* needs current->mm setup, does mm access */
+	unsigned		needs_mm : 1;
+	/* needs req->file assigned */
+	unsigned		needs_file : 1;
+	/* needs req->file assigned IFF fd is >= 0 */
+	unsigned		fd_non_neg : 1;
+	/* hash wq insertion if file is a regular file */
+	unsigned		hash_reg_file : 1;
+	/* unbound wq insertion if file is a non-regular file */
+	unsigned		unbound_nonreg_file : 1;
+	/* opcode is not supported by this kernel */
+	unsigned		not_supported : 1;
+	/* needs file table */
+	unsigned		file_table : 1;
+};
+
+static const struct io_op_def io_op_defs[] = {
+	[IORING_OP_NOP] = {},
+	[IORING_OP_READV] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_WRITEV] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_FSYNC] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_READ_FIXED] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_WRITE_FIXED] = {
+		.needs_file		= 1,
+		.hash_reg_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_POLL_ADD] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_POLL_REMOVE] = {},
+	[IORING_OP_SYNC_FILE_RANGE] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_SENDMSG] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_RECVMSG] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_TIMEOUT] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+	},
+	[IORING_OP_TIMEOUT_REMOVE] = {},
+	[IORING_OP_ACCEPT] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_ASYNC_CANCEL] = {},
+	[IORING_OP_LINK_TIMEOUT] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+	},
+	[IORING_OP_CONNECT] = {
+		.async_ctx		= 1,
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_FALLOCATE] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_OPENAT] = {
+		.needs_file		= 1,
+		.fd_non_neg		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_CLOSE] = {
+		.needs_file		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_FILES_UPDATE] = {
+		.needs_mm		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_STATX] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.fd_non_neg		= 1,
+	},
+	[IORING_OP_READ] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_WRITE] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_FADVISE] = {
+		.needs_file		= 1,
+	},
+	[IORING_OP_MADVISE] = {
+		.needs_mm		= 1,
+	},
+	[IORING_OP_SEND] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_RECV] = {
+		.needs_mm		= 1,
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+	},
+	[IORING_OP_OPENAT2] = {
+		.needs_file		= 1,
+		.fd_non_neg		= 1,
+		.file_table		= 1,
+	},
+	[IORING_OP_EPOLL_CTL] = {
+		.unbound_nonreg_file	= 1,
+		.file_table		= 1,
+	},
+};
+
 static void io_wq_submit_work(struct io_wq_work **workptr);
 static void io_cqring_fill_event(struct io_kiocb *req, long res);
-static void __io_free_req(struct io_kiocb *req);
 static void io_put_req(struct io_kiocb *req);
-static void io_double_put_req(struct io_kiocb *req);
 static void __io_double_put_req(struct io_kiocb *req);
 static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req);
 static void io_queue_linked_timeout(struct io_kiocb *req);
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+				 struct io_uring_files_update *ip,
+				 unsigned nr_args);
+static int io_grab_files(struct io_kiocb *req);
 
 static struct kmem_cache *req_cachep;
 
@@ -537,9 +820,11 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	INIT_LIST_HEAD(&ctx->cq_overflow_list);
 	init_completion(&ctx->completions[0]);
 	init_completion(&ctx->completions[1]);
+	idr_init(&ctx->personality_idr);
 	mutex_init(&ctx->uring_lock);
 	init_waitqueue_head(&ctx->wait);
 	spin_lock_init(&ctx->completion_lock);
+	init_llist_head(&ctx->poll_llist);
 	INIT_LIST_HEAD(&ctx->poll_list);
 	INIT_LIST_HEAD(&ctx->defer_list);
 	INIT_LIST_HEAD(&ctx->timeout_list);
@@ -566,7 +851,7 @@ static inline bool __req_need_defer(struct io_kiocb *req)
 
 static inline bool req_need_defer(struct io_kiocb *req)
 {
-	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) == REQ_F_IO_DRAIN)
+	if (unlikely(req->flags & REQ_F_IO_DRAIN))
 		return __req_need_defer(req);
 
 	return false;
@@ -606,53 +891,53 @@ static void __io_commit_cqring(struct io_ring_ctx *ctx)
 {
 	struct io_rings *rings = ctx->rings;
 
-	if (ctx->cached_cq_tail != READ_ONCE(rings->cq.tail)) {
-		/* order cqe stores with ring update */
-		smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
+	/* order cqe stores with ring update */
+	smp_store_release(&rings->cq.tail, ctx->cached_cq_tail);
 
-		if (wq_has_sleeper(&ctx->cq_wait)) {
-			wake_up_interruptible(&ctx->cq_wait);
-			kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
-		}
+	if (wq_has_sleeper(&ctx->cq_wait)) {
+		wake_up_interruptible(&ctx->cq_wait);
+		kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+	}
+}
+
+static inline void io_req_work_grab_env(struct io_kiocb *req,
+					const struct io_op_def *def)
+{
+	if (!req->work.mm && def->needs_mm) {
+		mmgrab(current->mm);
+		req->work.mm = current->mm;
 	}
+	if (!req->work.creds)
+		req->work.creds = get_current_cred();
 }
 
-static inline bool io_req_needs_user(struct io_kiocb *req)
+static inline void io_req_work_drop_env(struct io_kiocb *req)
 {
-	return !(req->opcode == IORING_OP_READ_FIXED ||
-		 req->opcode == IORING_OP_WRITE_FIXED);
+	if (req->work.mm) {
+		mmdrop(req->work.mm);
+		req->work.mm = NULL;
+	}
+	if (req->work.creds) {
+		put_cred(req->work.creds);
+		req->work.creds = NULL;
+	}
 }
 
 static inline bool io_prep_async_work(struct io_kiocb *req,
 				      struct io_kiocb **link)
 {
+	const struct io_op_def *def = &io_op_defs[req->opcode];
 	bool do_hashed = false;
 
-	switch (req->opcode) {
-	case IORING_OP_WRITEV:
-	case IORING_OP_WRITE_FIXED:
-		/* only regular files should be hashed for writes */
-		if (req->flags & REQ_F_ISREG)
+	if (req->flags & REQ_F_ISREG) {
+		if (def->hash_reg_file)
 			do_hashed = true;
-		/* fall-through */
-	case IORING_OP_READV:
-	case IORING_OP_READ_FIXED:
-	case IORING_OP_SENDMSG:
-	case IORING_OP_RECVMSG:
-	case IORING_OP_ACCEPT:
-	case IORING_OP_POLL_ADD:
-	case IORING_OP_CONNECT:
-		/*
-		 * We know REQ_F_ISREG is not set on some of these
-		 * opcodes, but this enables us to keep the check in
-		 * just one place.
-		 */
-		if (!(req->flags & REQ_F_ISREG))
+	} else {
+		if (def->unbound_nonreg_file)
 			req->work.flags |= IO_WQ_WORK_UNBOUND;
-		break;
 	}
-	if (io_req_needs_user(req))
-		req->work.flags |= IO_WQ_WORK_NEEDS_USER;
+
+	io_req_work_grab_env(req, def);
 
 	*link = io_prep_linked_timeout(req);
 	return do_hashed;
@@ -711,10 +996,8 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 
 	__io_commit_cqring(ctx);
 
-	while ((req = io_get_deferred_req(ctx)) != NULL) {
-		req->flags |= REQ_F_IO_DRAINED;
+	while ((req = io_get_deferred_req(ctx)) != NULL)
 		io_queue_async_work(req);
-	}
 }
 
 static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
@@ -735,13 +1018,20 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	return &rings->cqes[tail & ctx->cq_mask];
 }
 
+static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx)
+{
+	if (!ctx->eventfd_async)
+		return true;
+	return io_wq_current_is_worker() || in_interrupt();
+}
+
 static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
 {
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
 	if (waitqueue_active(&ctx->sqo_wait))
 		wake_up(&ctx->sqo_wait);
-	if (ctx->cq_ev_fd)
+	if (ctx->cq_ev_fd && io_should_trigger_evfd(ctx))
 		eventfd_signal(ctx->cq_ev_fd, 1);
 }
 
@@ -766,7 +1056,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 
 	/* if force is set, the ring is going away. always drop after that */
 	if (force)
-		ctx->cq_overflow_flushed = true;
+		ctx->cq_overflow_flushed = 1;
 
 	cqe = NULL;
 	while (!list_empty(&ctx->cq_overflow_list)) {
@@ -788,6 +1078,10 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force)
 	}
 
 	io_commit_cqring(ctx);
+	if (cqe) {
+		clear_bit(0, &ctx->sq_check_overflow);
+		clear_bit(0, &ctx->cq_check_overflow);
+	}
 	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 	io_cqring_ev_posted(ctx);
 
@@ -821,6 +1115,10 @@ static void io_cqring_fill_event(struct io_kiocb *req, long res)
 		WRITE_ONCE(ctx->rings->cq_overflow,
 				atomic_inc_return(&ctx->cached_cq_overflow));
 	} else {
+		if (list_empty(&ctx->cq_overflow_list)) {
+			set_bit(0, &ctx->sq_check_overflow);
+			set_bit(0, &ctx->cq_check_overflow);
+		}
 		refcount_inc(&req->refs);
 		req->result = res;
 		list_add_tail(&req->list, &ctx->cq_overflow_list);
@@ -863,9 +1161,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct io_kiocb *req;
 
-	if (!percpu_ref_tryget(&ctx->refs))
-		return NULL;
-
 	if (!state) {
 		req = kmem_cache_alloc(req_cachep, gfp);
 		if (unlikely(!req))
@@ -898,7 +1193,6 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 
 got_it:
 	req->io = NULL;
-	req->ring_file = NULL;
 	req->file = NULL;
 	req->ctx = ctx;
 	req->flags = 0;
@@ -915,24 +1209,35 @@ fallback:
 	return NULL;
 }
 
-static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
+static void __io_req_do_free(struct io_kiocb *req)
 {
-	if (*nr) {
-		kmem_cache_free_bulk(req_cachep, *nr, reqs);
-		percpu_ref_put_many(&ctx->refs, *nr);
-		*nr = 0;
+	if (likely(!io_is_fallback_req(req)))
+		kmem_cache_free(req_cachep, req);
+	else
+		clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+}
+
+static void __io_req_aux_free(struct io_kiocb *req)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	kfree(req->io);
+	if (req->file) {
+		if (req->flags & REQ_F_FIXED_FILE)
+			percpu_ref_put(&ctx->file_data->refs);
+		else
+			fput(req->file);
 	}
+
+	io_req_work_drop_env(req);
 }
 
 static void __io_free_req(struct io_kiocb *req)
 {
-	struct io_ring_ctx *ctx = req->ctx;
+	__io_req_aux_free(req);
 
-	if (req->io)
-		kfree(req->io);
-	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
-		fput(req->file);
 	if (req->flags & REQ_F_INFLIGHT) {
+		struct io_ring_ctx *ctx = req->ctx;
 		unsigned long flags;
 
 		spin_lock_irqsave(&ctx->inflight_lock, flags);
@@ -941,11 +1246,63 @@ static void __io_free_req(struct io_kiocb *req)
 			wake_up(&ctx->inflight_wait);
 		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
 	}
-	percpu_ref_put(&ctx->refs);
-	if (likely(!io_is_fallback_req(req)))
-		kmem_cache_free(req_cachep, req);
-	else
-		clear_bit_unlock(0, (unsigned long *) ctx->fallback_req);
+
+	percpu_ref_put(&req->ctx->refs);
+	__io_req_do_free(req);
+}
+
+struct req_batch {
+	void *reqs[IO_IOPOLL_BATCH];
+	int to_free;
+	int need_iter;
+};
+
+static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
+{
+	int fixed_refs = rb->to_free;
+
+	if (!rb->to_free)
+		return;
+	if (rb->need_iter) {
+		int i, inflight = 0;
+		unsigned long flags;
+
+		fixed_refs = 0;
+		for (i = 0; i < rb->to_free; i++) {
+			struct io_kiocb *req = rb->reqs[i];
+
+			if (req->flags & REQ_F_FIXED_FILE) {
+				req->file = NULL;
+				fixed_refs++;
+			}
+			if (req->flags & REQ_F_INFLIGHT)
+				inflight++;
+			__io_req_aux_free(req);
+		}
+		if (!inflight)
+			goto do_free;
+
+		spin_lock_irqsave(&ctx->inflight_lock, flags);
+		for (i = 0; i < rb->to_free; i++) {
+			struct io_kiocb *req = rb->reqs[i];
+
+			if (req->flags & REQ_F_INFLIGHT) {
+				list_del(&req->inflight_entry);
+				if (!--inflight)
+					break;
+			}
+		}
+		spin_unlock_irqrestore(&ctx->inflight_lock, flags);
+
+		if (waitqueue_active(&ctx->inflight_wait))
+			wake_up(&ctx->inflight_wait);
+	}
+do_free:
+	kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs);
+	if (fixed_refs)
+		percpu_ref_put_many(&ctx->file_data->refs, fixed_refs);
+	percpu_ref_put_many(&ctx->refs, rb->to_free);
+	rb->to_free = rb->need_iter = 0;
 }
 
 static bool io_link_cancel_timeout(struct io_kiocb *req)
@@ -1118,19 +1475,21 @@ static unsigned io_cqring_events(struct io_ring_ctx *ctx, bool noflush)
 {
 	struct io_rings *rings = ctx->rings;
 
-	/*
-	 * noflush == true is from the waitqueue handler, just ensure we wake
-	 * up the task, and the next invocation will flush the entries. We
-	 * cannot safely to it from here.
-	 */
-	if (noflush && !list_empty(&ctx->cq_overflow_list))
-		return -1U;
+	if (test_bit(0, &ctx->cq_check_overflow)) {
+		/*
+		 * noflush == true is from the waitqueue handler, just ensure
+		 * we wake up the task, and the next invocation will flush the
+		 * entries. We cannot safely to it from here.
+		 */
+		if (noflush && !list_empty(&ctx->cq_overflow_list))
+			return -1U;
 
-	io_cqring_overflow_flush(ctx, false);
+		io_cqring_overflow_flush(ctx, false);
+	}
 
 	/* See comment at the top of this file */
 	smp_rmb();
-	return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
+	return ctx->cached_cq_tail - READ_ONCE(rings->cq.head);
 }
 
 static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
@@ -1141,17 +1500,30 @@ static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
 	return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
 }
 
+static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
+{
+	if ((req->flags & REQ_F_LINK) || io_is_fallback_req(req))
+		return false;
+
+	if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+		rb->need_iter++;
+
+	rb->reqs[rb->to_free++] = req;
+	if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
+		io_free_req_many(req->ctx, rb);
+	return true;
+}
+
 /*
  * Find and free completed poll iocbs
  */
 static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 			       struct list_head *done)
 {
-	void *reqs[IO_IOPOLL_BATCH];
+	struct req_batch rb;
 	struct io_kiocb *req;
-	int to_free;
 
-	to_free = 0;
+	rb.to_free = rb.need_iter = 0;
 	while (!list_empty(done)) {
 		req = list_first_entry(done, struct io_kiocb, list);
 		list_del(&req->list);
@@ -1159,26 +1531,13 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		io_cqring_fill_event(req, req->result);
 		(*nr_events)++;
 
-		if (refcount_dec_and_test(&req->refs)) {
-			/* If we're not using fixed files, we have to pair the
-			 * completion part with the file put. Use regular
-			 * completions for those, only batch free for fixed
-			 * file and non-linked commands.
-			 */
-			if (((req->flags & (REQ_F_FIXED_FILE|REQ_F_LINK)) ==
-			    REQ_F_FIXED_FILE) && !io_is_fallback_req(req) &&
-			    !req->io) {
-				reqs[to_free++] = req;
-				if (to_free == ARRAY_SIZE(reqs))
-					io_free_req_many(ctx, reqs, &to_free);
-			} else {
-				io_free_req(req);
-			}
-		}
+		if (refcount_dec_and_test(&req->refs) &&
+		    !io_req_multi_free(&rb, req))
+			io_free_req(req);
 	}
 
 	io_commit_cqring(ctx);
-	io_free_req_many(ctx, reqs, &to_free);
+	io_free_req_many(ctx, &rb);
 }
 
 static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
@@ -1503,6 +1862,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		req->flags |= REQ_F_ISREG;
 
 	kiocb->ki_pos = READ_ONCE(sqe->off);
+	if (kiocb->ki_pos == -1 && !(req->file->f_mode & FMODE_STREAM)) {
+		req->flags |= REQ_F_CUR_POS;
+		kiocb->ki_pos = req->file->f_pos;
+	}
 	kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
 	kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
 
@@ -1574,6 +1937,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_kiocb **nxt,
 		       bool in_async)
 {
+	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
+
+	if (req->flags & REQ_F_CUR_POS)
+		req->file->f_pos = kiocb->ki_pos;
 	if (in_async && ret >= 0 && kiocb->ki_complete == io_complete_rw)
 		*nxt = __io_complete_rw(kiocb, ret);
 	else
@@ -1671,6 +2038,13 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
 	if (req->rw.kiocb.private)
 		return -EINVAL;
 
+	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
+		ssize_t ret;
+		ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
+		*iovec = NULL;
+		return ret;
+	}
+
 	if (req->io) {
 		struct io_async_rw *iorw = &req->io->rw;
 
@@ -1767,6 +2141,8 @@ static void io_req_map_rw(struct io_kiocb *req, ssize_t io_size,
 
 static int io_alloc_async_ctx(struct io_kiocb *req)
 {
+	if (!io_op_defs[req->opcode].async_ctx)
+		return 0;
 	req->io = kmalloc(sizeof(*req->io), GFP_KERNEL);
 	return req->io == NULL;
 }
@@ -1786,8 +2162,7 @@ static int io_setup_async_rw(struct io_kiocb *req, ssize_t io_size,
 			     struct iovec *iovec, struct iovec *fast_iov,
 			     struct iov_iter *iter)
 {
-	if (req->opcode == IORING_OP_READ_FIXED ||
-	    req->opcode == IORING_OP_WRITE_FIXED)
+	if (!io_op_defs[req->opcode].async_ctx)
 		return 0;
 	if (!req->io && io_alloc_async_ctx(req))
 		return -ENOMEM;
@@ -2101,6 +2476,421 @@ static int io_fsync(struct io_kiocb *req, struct io_kiocb **nxt,
 	return 0;
 }
 
+static void io_fallocate_finish(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	struct io_kiocb *nxt = NULL;
+	int ret;
+
+	ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off,
+				req->sync.len);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, &nxt);
+	if (nxt)
+		io_wq_assign_next(workptr, nxt);
+}
+
+static int io_fallocate_prep(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+	if (sqe->ioprio || sqe->buf_index || sqe->rw_flags)
+		return -EINVAL;
+
+	req->sync.off = READ_ONCE(sqe->off);
+	req->sync.len = READ_ONCE(sqe->addr);
+	req->sync.mode = READ_ONCE(sqe->len);
+	return 0;
+}
+
+static int io_fallocate(struct io_kiocb *req, struct io_kiocb **nxt,
+			bool force_nonblock)
+{
+	struct io_wq_work *work, *old_work;
+
+	/* fallocate always requiring blocking context */
+	if (force_nonblock) {
+		io_put_req(req);
+		req->work.func = io_fallocate_finish;
+		return -EAGAIN;
+	}
+
+	work = old_work = &req->work;
+	io_fallocate_finish(&work);
+	if (work && work != old_work)
+		*nxt = container_of(work, struct io_kiocb, work);
+
+	return 0;
+}
+
+static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	const char __user *fname;
+	int ret;
+
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->open.dfd = READ_ONCE(sqe->fd);
+	req->open.how.mode = READ_ONCE(sqe->len);
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	req->open.how.flags = READ_ONCE(sqe->open_flags);
+
+	req->open.filename = getname(fname);
+	if (IS_ERR(req->open.filename)) {
+		ret = PTR_ERR(req->open.filename);
+		req->open.filename = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct open_how __user *how;
+	const char __user *fname;
+	size_t len;
+	int ret;
+
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->open.dfd = READ_ONCE(sqe->fd);
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	how = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	len = READ_ONCE(sqe->len);
+
+	if (len < OPEN_HOW_SIZE_VER0)
+		return -EINVAL;
+
+	ret = copy_struct_from_user(&req->open.how, sizeof(req->open.how), how,
+					len);
+	if (ret)
+		return ret;
+
+	if (!(req->open.how.flags & O_PATH) && force_o_largefile())
+		req->open.how.flags |= O_LARGEFILE;
+
+	req->open.filename = getname(fname);
+	if (IS_ERR(req->open.filename)) {
+		ret = PTR_ERR(req->open.filename);
+		req->open.filename = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int io_openat2(struct io_kiocb *req, struct io_kiocb **nxt,
+		      bool force_nonblock)
+{
+	struct open_flags op;
+	struct file *file;
+	int ret;
+
+	if (force_nonblock)
+		return -EAGAIN;
+
+	ret = build_open_flags(&req->open.how, &op);
+	if (ret)
+		goto err;
+
+	ret = get_unused_fd_flags(req->open.how.flags);
+	if (ret < 0)
+		goto err;
+
+	file = do_filp_open(req->open.dfd, req->open.filename, &op);
+	if (IS_ERR(file)) {
+		put_unused_fd(ret);
+		ret = PTR_ERR(file);
+	} else {
+		fsnotify_open(file);
+		fd_install(ret, file);
+	}
+err:
+	putname(req->open.filename);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+}
+
+static int io_openat(struct io_kiocb *req, struct io_kiocb **nxt,
+		     bool force_nonblock)
+{
+	req->open.how = build_open_how(req->open.how.flags, req->open.how.mode);
+	return io_openat2(req, nxt, force_nonblock);
+}
+
+static int io_epoll_ctl_prep(struct io_kiocb *req,
+			     const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_EPOLL)
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->epoll.epfd = READ_ONCE(sqe->fd);
+	req->epoll.op = READ_ONCE(sqe->len);
+	req->epoll.fd = READ_ONCE(sqe->off);
+
+	if (ep_op_has_event(req->epoll.op)) {
+		struct epoll_event __user *ev;
+
+		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
+		if (copy_from_user(&req->epoll.event, ev, sizeof(*ev)))
+			return -EFAULT;
+	}
+
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_epoll_ctl(struct io_kiocb *req, struct io_kiocb **nxt,
+			bool force_nonblock)
+{
+#if defined(CONFIG_EPOLL)
+	struct io_epoll *ie = &req->epoll;
+	int ret;
+
+	ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
+	if (force_nonblock && ret == -EAGAIN)
+		return -EAGAIN;
+
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_madvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	if (sqe->ioprio || sqe->buf_index || sqe->off)
+		return -EINVAL;
+
+	req->madvise.addr = READ_ONCE(sqe->addr);
+	req->madvise.len = READ_ONCE(sqe->len);
+	req->madvise.advice = READ_ONCE(sqe->fadvise_advice);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_madvise(struct io_kiocb *req, struct io_kiocb **nxt,
+		      bool force_nonblock)
+{
+#if defined(CONFIG_ADVISE_SYSCALLS) && defined(CONFIG_MMU)
+	struct io_madvise *ma = &req->madvise;
+	int ret;
+
+	if (force_nonblock)
+		return -EAGAIN;
+
+	ret = do_madvise(ma->addr, ma->len, ma->advice);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static int io_fadvise_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	if (sqe->ioprio || sqe->buf_index || sqe->addr)
+		return -EINVAL;
+
+	req->fadvise.offset = READ_ONCE(sqe->off);
+	req->fadvise.len = READ_ONCE(sqe->len);
+	req->fadvise.advice = READ_ONCE(sqe->fadvise_advice);
+	return 0;
+}
+
+static int io_fadvise(struct io_kiocb *req, struct io_kiocb **nxt,
+		      bool force_nonblock)
+{
+	struct io_fadvise *fa = &req->fadvise;
+	int ret;
+
+	/* DONTNEED may block, others _should_ not */
+	if (fa->advice == POSIX_FADV_DONTNEED && force_nonblock)
+		return -EAGAIN;
+
+	ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+}
+
+static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	const char __user *fname;
+	unsigned lookup_flags;
+	int ret;
+
+	if (sqe->ioprio || sqe->buf_index)
+		return -EINVAL;
+
+	req->open.dfd = READ_ONCE(sqe->fd);
+	req->open.mask = READ_ONCE(sqe->len);
+	fname = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	req->open.buffer = u64_to_user_ptr(READ_ONCE(sqe->addr2));
+	req->open.how.flags = READ_ONCE(sqe->statx_flags);
+
+	if (vfs_stat_set_lookup_flags(&lookup_flags, req->open.how.flags))
+		return -EINVAL;
+
+	req->open.filename = getname_flags(fname, lookup_flags, NULL);
+	if (IS_ERR(req->open.filename)) {
+		ret = PTR_ERR(req->open.filename);
+		req->open.filename = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int io_statx(struct io_kiocb *req, struct io_kiocb **nxt,
+		    bool force_nonblock)
+{
+	struct io_open *ctx = &req->open;
+	unsigned lookup_flags;
+	struct path path;
+	struct kstat stat;
+	int ret;
+
+	if (force_nonblock)
+		return -EAGAIN;
+
+	if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
+		return -EINVAL;
+
+retry:
+	/* filename_lookup() drops it, keep a reference */
+	ctx->filename->refcnt++;
+
+	ret = filename_lookup(ctx->dfd, ctx->filename, lookup_flags, &path,
+				NULL);
+	if (ret)
+		goto err;
+
+	ret = vfs_getattr(&path, &stat, ctx->mask, ctx->how.flags);
+	path_put(&path);
+	if (retry_estale(ret, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	if (!ret)
+		ret = cp_statx(&stat, ctx->buffer);
+err:
+	putname(ctx->filename);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req_find_next(req, nxt);
+	return 0;
+}
+
+static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	/*
+	 * If we queue this for async, it must not be cancellable. That would
+	 * leave the 'file' in an undeterminate state.
+	 */
+	req->work.flags |= IO_WQ_WORK_NO_CANCEL;
+
+	if (sqe->ioprio || sqe->off || sqe->addr || sqe->len ||
+	    sqe->rw_flags || sqe->buf_index)
+		return -EINVAL;
+	if (sqe->flags & IOSQE_FIXED_FILE)
+		return -EINVAL;
+
+	req->close.fd = READ_ONCE(sqe->fd);
+	if (req->file->f_op == &io_uring_fops ||
+	    req->close.fd == req->ctx->ring_fd)
+		return -EBADF;
+
+	return 0;
+}
+
+static void io_close_finish(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	struct io_kiocb *nxt = NULL;
+
+	/* Invoked with files, we need to do the close */
+	if (req->work.files) {
+		int ret;
+
+		ret = filp_close(req->close.put_file, req->work.files);
+		if (ret < 0) {
+			req_set_fail_links(req);
+		}
+		io_cqring_add_event(req, ret);
+	}
+
+	fput(req->close.put_file);
+
+	/* we bypassed the re-issue, drop the submission reference */
+	io_put_req(req);
+	io_put_req_find_next(req, &nxt);
+	if (nxt)
+		io_wq_assign_next(workptr, nxt);
+}
+
+static int io_close(struct io_kiocb *req, struct io_kiocb **nxt,
+		    bool force_nonblock)
+{
+	int ret;
+
+	req->close.put_file = NULL;
+	ret = __close_fd_get_file(req->close.fd, &req->close.put_file);
+	if (ret < 0)
+		return ret;
+
+	/* if the file has a flush method, be safe and punt to async */
+	if (req->close.put_file->f_op->flush && !io_wq_current_is_worker())
+		goto eagain;
+
+	/*
+	 * No ->flush(), safely close from here and just punt the
+	 * fput() to async context.
+	 */
+	ret = filp_close(req->close.put_file, current->files);
+
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+
+	if (io_wq_current_is_worker()) {
+		struct io_wq_work *old_work, *work;
+
+		old_work = work = &req->work;
+		io_close_finish(&work);
+		if (work && work != old_work)
+			*nxt = container_of(work, struct io_kiocb, work);
+		return 0;
+	}
+
+eagain:
+	req->work.func = io_close_finish;
+	return -EAGAIN;
+}
+
 static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_ring_ctx *ctx = req->ctx;
@@ -2178,8 +2968,9 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
+	sr->len = READ_ONCE(sqe->len);
 
-	if (!io)
+	if (!io || req->opcode == IORING_OP_SEND)
 		return 0;
 
 	io->msg.iov = io->msg.fast_iov;
@@ -2259,6 +3050,56 @@ static int io_sendmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 #endif
 }
 
+static int io_send(struct io_kiocb *req, struct io_kiocb **nxt,
+		   bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	struct socket *sock;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
+	sock = sock_from_file(req->file, &ret);
+	if (sock) {
+		struct io_sr_msg *sr = &req->sr_msg;
+		struct msghdr msg;
+		struct iovec iov;
+		unsigned flags;
+
+		ret = import_single_range(WRITE, sr->buf, sr->len, &iov,
+						&msg.msg_iter);
+		if (ret)
+			return ret;
+
+		msg.msg_name = NULL;
+		msg.msg_control = NULL;
+		msg.msg_controllen = 0;
+		msg.msg_namelen = 0;
+
+		flags = req->sr_msg.msg_flags;
+		if (flags & MSG_DONTWAIT)
+			req->flags |= REQ_F_NOWAIT;
+		else if (force_nonblock)
+			flags |= MSG_DONTWAIT;
+
+		ret = __sys_sendmsg_sock(sock, &msg, flags);
+		if (force_nonblock && ret == -EAGAIN)
+			return -EAGAIN;
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+	}
+
+	io_cqring_add_event(req, ret);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_put_req_find_next(req, nxt);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
 static int io_recvmsg_prep(struct io_kiocb *req,
 			   const struct io_uring_sqe *sqe)
 {
@@ -2269,7 +3110,7 @@ static int io_recvmsg_prep(struct io_kiocb *req,
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->msg = u64_to_user_ptr(READ_ONCE(sqe->addr));
 
-	if (!io)
+	if (!io || req->opcode == IORING_OP_RECV)
 		return 0;
 
 	io->msg.iov = io->msg.fast_iov;
@@ -2351,6 +3192,59 @@ static int io_recvmsg(struct io_kiocb *req, struct io_kiocb **nxt,
 #endif
 }
 
+static int io_recv(struct io_kiocb *req, struct io_kiocb **nxt,
+		   bool force_nonblock)
+{
+#if defined(CONFIG_NET)
+	struct socket *sock;
+	int ret;
+
+	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+		return -EINVAL;
+
+	sock = sock_from_file(req->file, &ret);
+	if (sock) {
+		struct io_sr_msg *sr = &req->sr_msg;
+		struct msghdr msg;
+		struct iovec iov;
+		unsigned flags;
+
+		ret = import_single_range(READ, sr->buf, sr->len, &iov,
+						&msg.msg_iter);
+		if (ret)
+			return ret;
+
+		msg.msg_name = NULL;
+		msg.msg_control = NULL;
+		msg.msg_controllen = 0;
+		msg.msg_namelen = 0;
+		msg.msg_iocb = NULL;
+		msg.msg_flags = 0;
+
+		flags = req->sr_msg.msg_flags;
+		if (flags & MSG_DONTWAIT)
+			req->flags |= REQ_F_NOWAIT;
+		else if (force_nonblock)
+			flags |= MSG_DONTWAIT;
+
+		ret = __sys_recvmsg_sock(sock, &msg, NULL, NULL, flags);
+		if (force_nonblock && ret == -EAGAIN)
+			return -EAGAIN;
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+	}
+
+	io_cqring_add_event(req, ret);
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_put_req_find_next(req, nxt);
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+
 static int io_accept_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 #if defined(CONFIG_NET)
@@ -2414,7 +3308,6 @@ static int io_accept(struct io_kiocb *req, struct io_kiocb **nxt,
 	ret = __io_accept(req, nxt, force_nonblock);
 	if (ret == -EAGAIN && force_nonblock) {
 		req->work.func = io_accept_finish;
-		req->work.flags |= IO_WQ_WORK_NEEDS_FILES;
 		io_put_req(req);
 		return -EAGAIN;
 	}
@@ -2635,6 +3528,39 @@ static void io_poll_complete_work(struct io_wq_work **workptr)
 		io_wq_assign_next(workptr, nxt);
 }
 
+static void __io_poll_flush(struct io_ring_ctx *ctx, struct llist_node *nodes)
+{
+	struct io_kiocb *req, *tmp;
+	struct req_batch rb;
+
+	rb.to_free = rb.need_iter = 0;
+	spin_lock_irq(&ctx->completion_lock);
+	llist_for_each_entry_safe(req, tmp, nodes, llist_node) {
+		hash_del(&req->hash_node);
+		io_poll_complete(req, req->result, 0);
+
+		if (refcount_dec_and_test(&req->refs) &&
+		    !io_req_multi_free(&rb, req)) {
+			req->flags |= REQ_F_COMP_LOCKED;
+			io_free_req(req);
+		}
+	}
+	spin_unlock_irq(&ctx->completion_lock);
+
+	io_cqring_ev_posted(ctx);
+	io_free_req_many(ctx, &rb);
+}
+
+static void io_poll_flush(struct io_wq_work **workptr)
+{
+	struct io_kiocb *req = container_of(*workptr, struct io_kiocb, work);
+	struct llist_node *nodes;
+
+	nodes = llist_del_all(&req->ctx->poll_llist);
+	if (nodes)
+		__io_poll_flush(req->ctx, nodes);
+}
+
 static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 			void *key)
 {
@@ -2642,7 +3568,6 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	struct io_kiocb *req = container_of(poll, struct io_kiocb, poll);
 	struct io_ring_ctx *ctx = req->ctx;
 	__poll_t mask = key_to_poll(key);
-	unsigned long flags;
 
 	/* for instances that support it check for an event match first: */
 	if (mask && !(mask & poll->events))
@@ -2656,17 +3581,31 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	 * If we have a link timeout we're going to need the completion_lock
 	 * for finalizing the request, mark us as having grabbed that already.
 	 */
-	if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) {
-		hash_del(&req->hash_node);
-		io_poll_complete(req, mask, 0);
-		req->flags |= REQ_F_COMP_LOCKED;
-		io_put_req(req);
-		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	if (mask) {
+		unsigned long flags;
 
-		io_cqring_ev_posted(ctx);
-	} else {
-		io_queue_async_work(req);
+		if (llist_empty(&ctx->poll_llist) &&
+		    spin_trylock_irqsave(&ctx->completion_lock, flags)) {
+			hash_del(&req->hash_node);
+			io_poll_complete(req, mask, 0);
+			req->flags |= REQ_F_COMP_LOCKED;
+			io_put_req(req);
+			spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+			io_cqring_ev_posted(ctx);
+			req = NULL;
+		} else {
+			req->result = mask;
+			req->llist_node.next = NULL;
+			/* if the list wasn't empty, we're done */
+			if (!llist_add(&req->llist_node, &ctx->poll_llist))
+				req = NULL;
+			else
+				req->work.func = io_poll_flush;
+		}
 	}
+	if (req)
+		io_queue_async_work(req);
 
 	return 1;
 }
@@ -3071,20 +4010,67 @@ static int io_async_cancel(struct io_kiocb *req, struct io_kiocb **nxt)
 	return 0;
 }
 
+static int io_files_update_prep(struct io_kiocb *req,
+				const struct io_uring_sqe *sqe)
+{
+	if (sqe->flags || sqe->ioprio || sqe->rw_flags)
+		return -EINVAL;
+
+	req->files_update.offset = READ_ONCE(sqe->off);
+	req->files_update.nr_args = READ_ONCE(sqe->len);
+	if (!req->files_update.nr_args)
+		return -EINVAL;
+	req->files_update.arg = READ_ONCE(sqe->addr);
+	return 0;
+}
+
+static int io_files_update(struct io_kiocb *req, bool force_nonblock)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_uring_files_update up;
+	int ret;
+
+	if (force_nonblock)
+		return -EAGAIN;
+
+	up.offset = req->files_update.offset;
+	up.fds = req->files_update.arg;
+
+	mutex_lock(&ctx->uring_lock);
+	ret = __io_sqe_files_update(ctx, &up, req->files_update.nr_args);
+	mutex_unlock(&ctx->uring_lock);
+
+	if (ret < 0)
+		req_set_fail_links(req);
+	io_cqring_add_event(req, ret);
+	io_put_req(req);
+	return 0;
+}
+
 static int io_req_defer_prep(struct io_kiocb *req,
 			     const struct io_uring_sqe *sqe)
 {
 	ssize_t ret = 0;
 
+	if (io_op_defs[req->opcode].file_table) {
+		ret = io_grab_files(req);
+		if (unlikely(ret))
+			return ret;
+	}
+
+	io_req_work_grab_env(req, &io_op_defs[req->opcode]);
+
 	switch (req->opcode) {
 	case IORING_OP_NOP:
 		break;
 	case IORING_OP_READV:
 	case IORING_OP_READ_FIXED:
+	case IORING_OP_READ:
 		ret = io_read_prep(req, sqe, true);
 		break;
 	case IORING_OP_WRITEV:
 	case IORING_OP_WRITE_FIXED:
+	case IORING_OP_WRITE:
 		ret = io_write_prep(req, sqe, true);
 		break;
 	case IORING_OP_POLL_ADD:
@@ -3100,9 +4086,11 @@ static int io_req_defer_prep(struct io_kiocb *req,
 		ret = io_prep_sfr(req, sqe);
 		break;
 	case IORING_OP_SENDMSG:
+	case IORING_OP_SEND:
 		ret = io_sendmsg_prep(req, sqe);
 		break;
 	case IORING_OP_RECVMSG:
+	case IORING_OP_RECV:
 		ret = io_recvmsg_prep(req, sqe);
 		break;
 	case IORING_OP_CONNECT:
@@ -3123,6 +4111,33 @@ static int io_req_defer_prep(struct io_kiocb *req,
 	case IORING_OP_ACCEPT:
 		ret = io_accept_prep(req, sqe);
 		break;
+	case IORING_OP_FALLOCATE:
+		ret = io_fallocate_prep(req, sqe);
+		break;
+	case IORING_OP_OPENAT:
+		ret = io_openat_prep(req, sqe);
+		break;
+	case IORING_OP_CLOSE:
+		ret = io_close_prep(req, sqe);
+		break;
+	case IORING_OP_FILES_UPDATE:
+		ret = io_files_update_prep(req, sqe);
+		break;
+	case IORING_OP_STATX:
+		ret = io_statx_prep(req, sqe);
+		break;
+	case IORING_OP_FADVISE:
+		ret = io_fadvise_prep(req, sqe);
+		break;
+	case IORING_OP_MADVISE:
+		ret = io_madvise_prep(req, sqe);
+		break;
+	case IORING_OP_OPENAT2:
+		ret = io_openat2_prep(req, sqe);
+		break;
+	case IORING_OP_EPOLL_CTL:
+		ret = io_epoll_ctl_prep(req, sqe);
+		break;
 	default:
 		printk_once(KERN_WARNING "io_uring: unhandled opcode %d\n",
 				req->opcode);
@@ -3173,6 +4188,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		break;
 	case IORING_OP_READV:
 	case IORING_OP_READ_FIXED:
+	case IORING_OP_READ:
 		if (sqe) {
 			ret = io_read_prep(req, sqe, force_nonblock);
 			if (ret < 0)
@@ -3182,6 +4198,7 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		break;
 	case IORING_OP_WRITEV:
 	case IORING_OP_WRITE_FIXED:
+	case IORING_OP_WRITE:
 		if (sqe) {
 			ret = io_write_prep(req, sqe, force_nonblock);
 			if (ret < 0)
@@ -3222,20 +4239,28 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		ret = io_sync_file_range(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_SENDMSG:
+	case IORING_OP_SEND:
 		if (sqe) {
 			ret = io_sendmsg_prep(req, sqe);
 			if (ret < 0)
 				break;
 		}
-		ret = io_sendmsg(req, nxt, force_nonblock);
+		if (req->opcode == IORING_OP_SENDMSG)
+			ret = io_sendmsg(req, nxt, force_nonblock);
+		else
+			ret = io_send(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_RECVMSG:
+	case IORING_OP_RECV:
 		if (sqe) {
 			ret = io_recvmsg_prep(req, sqe);
 			if (ret)
 				break;
 		}
-		ret = io_recvmsg(req, nxt, force_nonblock);
+		if (req->opcode == IORING_OP_RECVMSG)
+			ret = io_recvmsg(req, nxt, force_nonblock);
+		else
+			ret = io_recv(req, nxt, force_nonblock);
 		break;
 	case IORING_OP_TIMEOUT:
 		if (sqe) {
@@ -3277,6 +4302,78 @@ static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		}
 		ret = io_async_cancel(req, nxt);
 		break;
+	case IORING_OP_FALLOCATE:
+		if (sqe) {
+			ret = io_fallocate_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_fallocate(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_OPENAT:
+		if (sqe) {
+			ret = io_openat_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_openat(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_CLOSE:
+		if (sqe) {
+			ret = io_close_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_close(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_FILES_UPDATE:
+		if (sqe) {
+			ret = io_files_update_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_files_update(req, force_nonblock);
+		break;
+	case IORING_OP_STATX:
+		if (sqe) {
+			ret = io_statx_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_statx(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_FADVISE:
+		if (sqe) {
+			ret = io_fadvise_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_fadvise(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_MADVISE:
+		if (sqe) {
+			ret = io_madvise_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_madvise(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_OPENAT2:
+		if (sqe) {
+			ret = io_openat2_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_openat2(req, nxt, force_nonblock);
+		break;
+	case IORING_OP_EPOLL_CTL:
+		if (sqe) {
+			ret = io_epoll_ctl_prep(req, sqe);
+			if (ret)
+				break;
+		}
+		ret = io_epoll_ctl(req, nxt, force_nonblock);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -3311,8 +4408,11 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 	struct io_kiocb *nxt = NULL;
 	int ret = 0;
 
-	if (work->flags & IO_WQ_WORK_CANCEL)
+	/* if NO_CANCEL is set, we must still run the work */
+	if ((work->flags & (IO_WQ_WORK_CANCEL|IO_WQ_WORK_NO_CANCEL)) ==
+				IO_WQ_WORK_CANCEL) {
 		ret = -ECANCELED;
+	}
 
 	if (!ret) {
 		req->has_user = (work->flags & IO_WQ_WORK_HAS_MM) != 0;
@@ -3344,26 +4444,13 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
 		io_wq_assign_next(workptr, nxt);
 }
 
-static bool io_req_op_valid(int op)
-{
-	return op >= IORING_OP_NOP && op < IORING_OP_LAST;
-}
-
-static int io_req_needs_file(struct io_kiocb *req)
+static int io_req_needs_file(struct io_kiocb *req, int fd)
 {
-	switch (req->opcode) {
-	case IORING_OP_NOP:
-	case IORING_OP_POLL_REMOVE:
-	case IORING_OP_TIMEOUT:
-	case IORING_OP_TIMEOUT_REMOVE:
-	case IORING_OP_ASYNC_CANCEL:
-	case IORING_OP_LINK_TIMEOUT:
+	if (!io_op_defs[req->opcode].needs_file)
 		return 0;
-	default:
-		if (io_req_op_valid(req->opcode))
-			return 1;
-		return -EINVAL;
-	}
+	if (fd == -1 && io_op_defs[req->opcode].fd_non_neg)
+		return 0;
+	return 1;
 }
 
 static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
@@ -3371,8 +4458,8 @@ static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
 {
 	struct fixed_file_table *table;
 
-	table = &ctx->file_table[index >> IORING_FILE_TABLE_SHIFT];
-	return table->files[index & IORING_FILE_TABLE_MASK];
+	table = &ctx->file_data->table[index >> IORING_FILE_TABLE_SHIFT];
+	return table->files[index & IORING_FILE_TABLE_MASK];;
 }
 
 static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
@@ -3380,20 +4467,16 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
 {
 	struct io_ring_ctx *ctx = req->ctx;
 	unsigned flags;
-	int fd, ret;
+	int fd;
 
 	flags = READ_ONCE(sqe->flags);
 	fd = READ_ONCE(sqe->fd);
 
-	if (flags & IOSQE_IO_DRAIN)
-		req->flags |= REQ_F_IO_DRAIN;
-
-	ret = io_req_needs_file(req);
-	if (ret <= 0)
-		return ret;
+	if (!io_req_needs_file(req, fd))
+		return 0;
 
 	if (flags & IOSQE_FIXED_FILE) {
-		if (unlikely(!ctx->file_table ||
+		if (unlikely(!ctx->file_data ||
 		    (unsigned) fd >= ctx->nr_user_files))
 			return -EBADF;
 		fd = array_index_nospec(fd, ctx->nr_user_files);
@@ -3401,6 +4484,7 @@ static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
 		if (!req->file)
 			return -EBADF;
 		req->flags |= REQ_F_FIXED_FILE;
+		percpu_ref_get(&ctx->file_data->refs);
 	} else {
 		if (req->needs_fixed_file)
 			return -EBADF;
@@ -3418,6 +4502,11 @@ static int io_grab_files(struct io_kiocb *req)
 	int ret = -EBADF;
 	struct io_ring_ctx *ctx = req->ctx;
 
+	if (req->work.files)
+		return 0;
+	if (!ctx->ring_file)
+		return -EBADF;
+
 	rcu_read_lock();
 	spin_lock_irq(&ctx->inflight_lock);
 	/*
@@ -3426,7 +4515,7 @@ static int io_grab_files(struct io_kiocb *req)
 	 * the fd has changed since we started down this path, and disallow
 	 * this operation if it has.
 	 */
-	if (fcheck(req->ring_fd) == req->ring_file) {
+	if (fcheck(ctx->ring_fd) == ctx->ring_file) {
 		list_add(&req->inflight_entry, &ctx->inflight_list);
 		req->flags |= REQ_F_INFLIGHT;
 		req->work.files = current->files;
@@ -3532,7 +4621,8 @@ again:
 	 */
 	if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
 	    (req->flags & REQ_F_MUST_PUNT))) {
-		if (req->work.flags & IO_WQ_WORK_NEEDS_FILES) {
+punt:
+		if (io_op_defs[req->opcode].file_table) {
 			ret = io_grab_files(req);
 			if (ret)
 				goto err;
@@ -3567,6 +4657,9 @@ done_req:
 	if (nxt) {
 		req = nxt;
 		nxt = NULL;
+
+		if (req->flags & REQ_F_FORCE_ASYNC)
+			goto punt;
 		goto again;
 	}
 }
@@ -3575,21 +4668,27 @@ static void io_queue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	int ret;
 
-	if (unlikely(req->ctx->drain_next)) {
-		req->flags |= REQ_F_IO_DRAIN;
-		req->ctx->drain_next = false;
-	}
-	req->ctx->drain_next = (req->flags & REQ_F_DRAIN_LINK);
-
 	ret = io_req_defer(req, sqe);
 	if (ret) {
 		if (ret != -EIOCBQUEUED) {
+fail_req:
 			io_cqring_add_event(req, ret);
 			req_set_fail_links(req);
 			io_double_put_req(req);
 		}
-	} else
+	} else if (req->flags & REQ_F_FORCE_ASYNC) {
+		ret = io_req_defer_prep(req, sqe);
+		if (unlikely(ret < 0))
+			goto fail_req;
+		/*
+		 * Never try inline submit of IOSQE_ASYNC is set, go straight
+		 * to async execution.
+		 */
+		req->work.flags |= IO_WQ_WORK_CONCURRENT;
+		io_queue_async_work(req);
+	} else {
 		__io_queue_sqe(req, sqe);
+	}
 }
 
 static inline void io_queue_link_head(struct io_kiocb *req)
@@ -3602,25 +4701,47 @@ static inline void io_queue_link_head(struct io_kiocb *req)
 }
 
 #define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK|	\
-				IOSQE_IO_HARDLINK)
+				IOSQE_IO_HARDLINK | IOSQE_ASYNC)
 
 static bool io_submit_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 			  struct io_submit_state *state, struct io_kiocb **link)
 {
+	const struct cred *old_creds = NULL;
 	struct io_ring_ctx *ctx = req->ctx;
-	int ret;
+	unsigned int sqe_flags;
+	int ret, id;
+
+	sqe_flags = READ_ONCE(sqe->flags);
 
 	/* enforce forwards compatibility on users */
-	if (unlikely(sqe->flags & ~SQE_VALID_FLAGS)) {
+	if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
 		ret = -EINVAL;
 		goto err_req;
 	}
 
+	id = READ_ONCE(sqe->personality);
+	if (id) {
+		const struct cred *personality_creds;
+
+		personality_creds = idr_find(&ctx->personality_idr, id);
+		if (unlikely(!personality_creds)) {
+			ret = -EINVAL;
+			goto err_req;
+		}
+		old_creds = override_creds(personality_creds);
+	}
+
+	/* same numerical values with corresponding REQ_F_*, safe to copy */
+	req->flags |= sqe_flags & (IOSQE_IO_DRAIN|IOSQE_IO_HARDLINK|
+					IOSQE_ASYNC);
+
 	ret = io_req_set_file(state, req, sqe);
 	if (unlikely(ret)) {
 err_req:
 		io_cqring_add_event(req, ret);
 		io_double_put_req(req);
+		if (old_creds)
+			revert_creds(old_creds);
 		return false;
 	}
 
@@ -3632,14 +4753,19 @@ err_req:
 	 * conditions are true (normal request), then just queue it.
 	 */
 	if (*link) {
-		struct io_kiocb *prev = *link;
-
-		if (sqe->flags & IOSQE_IO_DRAIN)
-			(*link)->flags |= REQ_F_DRAIN_LINK | REQ_F_IO_DRAIN;
-
-		if (sqe->flags & IOSQE_IO_HARDLINK)
-			req->flags |= REQ_F_HARDLINK;
+		struct io_kiocb *head = *link;
 
+		/*
+		 * Taking sequential execution of a link, draining both sides
+		 * of the link also fullfils IOSQE_IO_DRAIN semantics for all
+		 * requests in the link. So, it drains the head and the
+		 * next after the link request. The last one is done via
+		 * drain_next flag to persist the effect across calls.
+		 */
+		if (sqe_flags & IOSQE_IO_DRAIN) {
+			head->flags |= REQ_F_IO_DRAIN;
+			ctx->drain_next = 1;
+		}
 		if (io_alloc_async_ctx(req)) {
 			ret = -EAGAIN;
 			goto err_req;
@@ -3648,25 +4774,36 @@ err_req:
 		ret = io_req_defer_prep(req, sqe);
 		if (ret) {
 			/* fail even hard links since we don't submit */
-			prev->flags |= REQ_F_FAIL_LINK;
+			head->flags |= REQ_F_FAIL_LINK;
 			goto err_req;
 		}
-		trace_io_uring_link(ctx, req, prev);
-		list_add_tail(&req->link_list, &prev->link_list);
-	} else if (sqe->flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
-		req->flags |= REQ_F_LINK;
-		if (sqe->flags & IOSQE_IO_HARDLINK)
-			req->flags |= REQ_F_HARDLINK;
-
-		INIT_LIST_HEAD(&req->link_list);
-		ret = io_req_defer_prep(req, sqe);
-		if (ret)
-			req->flags |= REQ_F_FAIL_LINK;
-		*link = req;
+		trace_io_uring_link(ctx, req, head);
+		list_add_tail(&req->link_list, &head->link_list);
+
+		/* last request of a link, enqueue the link */
+		if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK))) {
+			io_queue_link_head(head);
+			*link = NULL;
+		}
 	} else {
-		io_queue_sqe(req, sqe);
+		if (unlikely(ctx->drain_next)) {
+			req->flags |= REQ_F_IO_DRAIN;
+			req->ctx->drain_next = 0;
+		}
+		if (sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) {
+			req->flags |= REQ_F_LINK;
+			INIT_LIST_HEAD(&req->link_list);
+			ret = io_req_defer_prep(req, sqe);
+			if (ret)
+				req->flags |= REQ_F_FAIL_LINK;
+			*link = req;
+		} else {
+			io_queue_sqe(req, sqe);
+		}
 	}
 
+	if (old_creds)
+		revert_creds(old_creds);
 	return true;
 }
 
@@ -3698,14 +4835,12 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
 {
 	struct io_rings *rings = ctx->rings;
 
-	if (ctx->cached_sq_head != READ_ONCE(rings->sq.head)) {
-		/*
-		 * Ensure any loads from the SQEs are done at this point,
-		 * since once we write the new head, the application could
-		 * write new data to them.
-		 */
-		smp_store_release(&rings->sq.head, ctx->cached_sq_head);
-	}
+	/*
+	 * Ensure any loads from the SQEs are done at this point,
+	 * since once we write the new head, the application could
+	 * write new data to them.
+	 */
+	smp_store_release(&rings->sq.head, ctx->cached_sq_head);
 }
 
 /*
@@ -3719,7 +4854,6 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
 static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			  const struct io_uring_sqe **sqe_ptr)
 {
-	struct io_rings *rings = ctx->rings;
 	u32 *sq_array = ctx->sq_array;
 	unsigned head;
 
@@ -3731,12 +4865,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	 * 2) allows the kernel side to track the head on its own, even
 	 *    though the application is the one updating it.
 	 */
-	head = ctx->cached_sq_head;
-	/* make sure SQ entry isn't read before tail */
-	if (unlikely(head == smp_load_acquire(&rings->sq.tail)))
-		return false;
-
-	head = READ_ONCE(sq_array[head & ctx->sq_mask]);
+	head = READ_ONCE(sq_array[ctx->cached_sq_head & ctx->sq_mask]);
 	if (likely(head < ctx->sq_entries)) {
 		/*
 		 * All io need record the previous position, if LINK vs DARIN,
@@ -3754,7 +4883,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	/* drop invalid entries */
 	ctx->cached_sq_head++;
 	ctx->cached_sq_dropped++;
-	WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped);
+	WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped);
 	return false;
 }
 
@@ -3768,19 +4897,29 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 	bool mm_fault = false;
 
 	/* if we have a backlog and couldn't flush it all, return BUSY */
-	if (!list_empty(&ctx->cq_overflow_list) &&
-	    !io_cqring_overflow_flush(ctx, false))
-		return -EBUSY;
+	if (test_bit(0, &ctx->sq_check_overflow)) {
+		if (!list_empty(&ctx->cq_overflow_list) &&
+		    !io_cqring_overflow_flush(ctx, false))
+			return -EBUSY;
+	}
+
+	/* make sure SQ entry isn't read before tail */
+	nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx));
+
+	if (!percpu_ref_tryget_many(&ctx->refs, nr))
+		return -EAGAIN;
 
 	if (nr > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, nr);
 		statep = &state;
 	}
 
+	ctx->ring_fd = ring_fd;
+	ctx->ring_file = ring_file;
+
 	for (i = 0; i < nr; i++) {
 		const struct io_uring_sqe *sqe;
 		struct io_kiocb *req;
-		unsigned int sqe_flags;
 
 		req = io_get_req(ctx, statep);
 		if (unlikely(!req)) {
@@ -3789,11 +4928,20 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 			break;
 		}
 		if (!io_get_sqring(ctx, req, &sqe)) {
-			__io_free_req(req);
+			__io_req_do_free(req);
 			break;
 		}
 
-		if (io_req_needs_user(req) && !*mm) {
+		/* will complete beyond this point, count as submitted */
+		submitted++;
+
+		if (unlikely(req->opcode >= IORING_OP_LAST)) {
+			io_cqring_add_event(req, -EINVAL);
+			io_double_put_req(req);
+			break;
+		}
+
+		if (io_op_defs[req->opcode].needs_mm && !*mm) {
 			mm_fault = mm_fault || !mmget_not_zero(ctx->sqo_mm);
 			if (!mm_fault) {
 				use_mm(ctx->sqo_mm);
@@ -3801,27 +4949,20 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
 			}
 		}
 
-		submitted++;
-		sqe_flags = sqe->flags;
-
-		req->ring_file = ring_file;
-		req->ring_fd = ring_fd;
 		req->has_user = *mm != NULL;
 		req->in_async = async;
 		req->needs_fixed_file = async;
-		trace_io_uring_submit_sqe(ctx, req->user_data, true, async);
+		trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data,
+						true, async);
 		if (!io_submit_sqe(req, sqe, statep, &link))
 			break;
-		/*
-		 * If previous wasn't linked and we have a linked command,
-		 * that's the end of the chain. Submit the previous link.
-		 */
-		if (!(sqe_flags & (IOSQE_IO_LINK|IOSQE_IO_HARDLINK)) && link) {
-			io_queue_link_head(link);
-			link = NULL;
-		}
 	}
 
+	if (unlikely(submitted != nr)) {
+		int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
+
+		percpu_ref_put_many(&ctx->refs, nr - ref_used);
+	}
 	if (link)
 		io_queue_link_head(link);
 	if (statep)
@@ -3944,7 +5085,6 @@ static int io_sq_thread(void *data)
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
 		}
 
-		to_submit = min(to_submit, ctx->sq_entries);
 		mutex_lock(&ctx->uring_lock);
 		ret = io_submit_sqes(ctx, to_submit, NULL, -1, &cur_mm, true);
 		mutex_unlock(&ctx->uring_lock);
@@ -4075,19 +5215,40 @@ static void __io_sqe_files_unregister(struct io_ring_ctx *ctx)
 #endif
 }
 
+static void io_file_ref_kill(struct percpu_ref *ref)
+{
+	struct fixed_file_data *data;
+
+	data = container_of(ref, struct fixed_file_data, refs);
+	complete(&data->done);
+}
+
 static int io_sqe_files_unregister(struct io_ring_ctx *ctx)
 {
+	struct fixed_file_data *data = ctx->file_data;
 	unsigned nr_tables, i;
 
-	if (!ctx->file_table)
+	if (!data)
 		return -ENXIO;
 
+	/* protect against inflight atomic switch, which drops the ref */
+	percpu_ref_get(&data->refs);
+	/* wait for existing switches */
+	flush_work(&data->ref_work);
+	percpu_ref_kill_and_confirm(&data->refs, io_file_ref_kill);
+	wait_for_completion(&data->done);
+	percpu_ref_put(&data->refs);
+	/* flush potential new switch */
+	flush_work(&data->ref_work);
+	percpu_ref_exit(&data->refs);
+
 	__io_sqe_files_unregister(ctx);
 	nr_tables = DIV_ROUND_UP(ctx->nr_user_files, IORING_MAX_FILES_TABLE);
 	for (i = 0; i < nr_tables; i++)
-		kfree(ctx->file_table[i].files);
-	kfree(ctx->file_table);
-	ctx->file_table = NULL;
+		kfree(data->table[i].files);
+	kfree(data->table);
+	kfree(data);
+	ctx->file_data = NULL;
 	ctx->nr_user_files = 0;
 	return 0;
 }
@@ -4118,16 +5279,6 @@ static void io_finish_async(struct io_ring_ctx *ctx)
 }
 
 #if defined(CONFIG_UNIX)
-static void io_destruct_skb(struct sk_buff *skb)
-{
-	struct io_ring_ctx *ctx = skb->sk->sk_user_data;
-
-	if (ctx->io_wq)
-		io_wq_flush(ctx->io_wq);
-
-	unix_destruct_scm(skb);
-}
-
 /*
  * Ensure the UNIX gc is aware of our file set, so we are certain that
  * the io_uring can be safely unregistered on process exit, even if we have
@@ -4175,7 +5326,7 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset)
 		fpl->max = SCM_MAX_FD;
 		fpl->count = nr_files;
 		UNIXCB(skb).fp = fpl;
-		skb->destructor = io_destruct_skb;
+		skb->destructor = unix_destruct_scm;
 		refcount_add(skb->truesize, &sk->sk_wmem_alloc);
 		skb_queue_head(&sk->sk_receive_queue, skb);
 
@@ -4237,7 +5388,7 @@ static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables,
 	int i;
 
 	for (i = 0; i < nr_tables; i++) {
-		struct fixed_file_table *table = &ctx->file_table[i];
+		struct fixed_file_table *table = &ctx->file_data->table[i];
 		unsigned this_files;
 
 		this_files = min(nr_files, IORING_MAX_FILES_TABLE);
@@ -4252,36 +5403,159 @@ static int io_sqe_alloc_file_tables(struct io_ring_ctx *ctx, unsigned nr_tables,
 		return 0;
 
 	for (i = 0; i < nr_tables; i++) {
-		struct fixed_file_table *table = &ctx->file_table[i];
+		struct fixed_file_table *table = &ctx->file_data->table[i];
 		kfree(table->files);
 	}
 	return 1;
 }
 
+static void io_ring_file_put(struct io_ring_ctx *ctx, struct file *file)
+{
+#if defined(CONFIG_UNIX)
+	struct sock *sock = ctx->ring_sock->sk;
+	struct sk_buff_head list, *head = &sock->sk_receive_queue;
+	struct sk_buff *skb;
+	int i;
+
+	__skb_queue_head_init(&list);
+
+	/*
+	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
+	 * remove this entry and rearrange the file array.
+	 */
+	skb = skb_dequeue(head);
+	while (skb) {
+		struct scm_fp_list *fp;
+
+		fp = UNIXCB(skb).fp;
+		for (i = 0; i < fp->count; i++) {
+			int left;
+
+			if (fp->fp[i] != file)
+				continue;
+
+			unix_notinflight(fp->user, fp->fp[i]);
+			left = fp->count - 1 - i;
+			if (left) {
+				memmove(&fp->fp[i], &fp->fp[i + 1],
+						left * sizeof(struct file *));
+			}
+			fp->count--;
+			if (!fp->count) {
+				kfree_skb(skb);
+				skb = NULL;
+			} else {
+				__skb_queue_tail(&list, skb);
+			}
+			fput(file);
+			file = NULL;
+			break;
+		}
+
+		if (!file)
+			break;
+
+		__skb_queue_tail(&list, skb);
+
+		skb = skb_dequeue(head);
+	}
+
+	if (skb_peek(&list)) {
+		spin_lock_irq(&head->lock);
+		while ((skb = __skb_dequeue(&list)) != NULL)
+			__skb_queue_tail(head, skb);
+		spin_unlock_irq(&head->lock);
+	}
+#else
+	fput(file);
+#endif
+}
+
+struct io_file_put {
+	struct llist_node llist;
+	struct file *file;
+	struct completion *done;
+};
+
+static void io_ring_file_ref_switch(struct work_struct *work)
+{
+	struct io_file_put *pfile, *tmp;
+	struct fixed_file_data *data;
+	struct llist_node *node;
+
+	data = container_of(work, struct fixed_file_data, ref_work);
+
+	while ((node = llist_del_all(&data->put_llist)) != NULL) {
+		llist_for_each_entry_safe(pfile, tmp, node, llist) {
+			io_ring_file_put(data->ctx, pfile->file);
+			if (pfile->done)
+				complete(pfile->done);
+			else
+				kfree(pfile);
+		}
+	}
+
+	percpu_ref_get(&data->refs);
+	percpu_ref_switch_to_percpu(&data->refs);
+}
+
+static void io_file_data_ref_zero(struct percpu_ref *ref)
+{
+	struct fixed_file_data *data;
+
+	data = container_of(ref, struct fixed_file_data, refs);
+
+	/* we can't safely switch from inside this context, punt to wq */
+	queue_work(system_wq, &data->ref_work);
+}
+
 static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 				 unsigned nr_args)
 {
 	__s32 __user *fds = (__s32 __user *) arg;
 	unsigned nr_tables;
+	struct file *file;
 	int fd, ret = 0;
 	unsigned i;
 
-	if (ctx->file_table)
+	if (ctx->file_data)
 		return -EBUSY;
 	if (!nr_args)
 		return -EINVAL;
 	if (nr_args > IORING_MAX_FIXED_FILES)
 		return -EMFILE;
 
+	ctx->file_data = kzalloc(sizeof(*ctx->file_data), GFP_KERNEL);
+	if (!ctx->file_data)
+		return -ENOMEM;
+	ctx->file_data->ctx = ctx;
+	init_completion(&ctx->file_data->done);
+
 	nr_tables = DIV_ROUND_UP(nr_args, IORING_MAX_FILES_TABLE);
-	ctx->file_table = kcalloc(nr_tables, sizeof(struct fixed_file_table),
+	ctx->file_data->table = kcalloc(nr_tables,
+					sizeof(struct fixed_file_table),
 					GFP_KERNEL);
-	if (!ctx->file_table)
+	if (!ctx->file_data->table) {
+		kfree(ctx->file_data);
+		ctx->file_data = NULL;
 		return -ENOMEM;
+	}
+
+	if (percpu_ref_init(&ctx->file_data->refs, io_file_data_ref_zero,
+				PERCPU_REF_ALLOW_REINIT, GFP_KERNEL)) {
+		kfree(ctx->file_data->table);
+		kfree(ctx->file_data);
+		ctx->file_data = NULL;
+		return -ENOMEM;
+	}
+	ctx->file_data->put_llist.first = NULL;
+	INIT_WORK(&ctx->file_data->ref_work, io_ring_file_ref_switch);
 
 	if (io_sqe_alloc_file_tables(ctx, nr_tables, nr_args)) {
-		kfree(ctx->file_table);
-		ctx->file_table = NULL;
+		percpu_ref_exit(&ctx->file_data->refs);
+		kfree(ctx->file_data->table);
+		kfree(ctx->file_data);
+		ctx->file_data = NULL;
 		return -ENOMEM;
 	}
 
@@ -4298,13 +5572,14 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			continue;
 		}
 
-		table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+		table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
 		index = i & IORING_FILE_TABLE_MASK;
-		table->files[index] = fget(fd);
+		file = fget(fd);
 
 		ret = -EBADF;
-		if (!table->files[index])
+		if (!file)
 			break;
+
 		/*
 		 * Don't allow io_uring instances to be registered. If UNIX
 		 * isn't enabled, then this causes a reference cycle and this
@@ -4312,26 +5587,26 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 		 * handle it just fine, but there's still no point in allowing
 		 * a ring fd as it doesn't support regular read/write anyway.
 		 */
-		if (table->files[index]->f_op == &io_uring_fops) {
-			fput(table->files[index]);
+		if (file->f_op == &io_uring_fops) {
+			fput(file);
 			break;
 		}
 		ret = 0;
+		table->files[index] = file;
 	}
 
 	if (ret) {
 		for (i = 0; i < ctx->nr_user_files; i++) {
-			struct file *file;
-
 			file = io_file_from_index(ctx, i);
 			if (file)
 				fput(file);
 		}
 		for (i = 0; i < nr_tables; i++)
-			kfree(ctx->file_table[i].files);
+			kfree(ctx->file_data->table[i].files);
 
-		kfree(ctx->file_table);
-		ctx->file_table = NULL;
+		kfree(ctx->file_data->table);
+		kfree(ctx->file_data);
+		ctx->file_data = NULL;
 		ctx->nr_user_files = 0;
 		return ret;
 	}
@@ -4343,69 +5618,6 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 	return ret;
 }
 
-static void io_sqe_file_unregister(struct io_ring_ctx *ctx, int index)
-{
-#if defined(CONFIG_UNIX)
-	struct file *file = io_file_from_index(ctx, index);
-	struct sock *sock = ctx->ring_sock->sk;
-	struct sk_buff_head list, *head = &sock->sk_receive_queue;
-	struct sk_buff *skb;
-	int i;
-
-	__skb_queue_head_init(&list);
-
-	/*
-	 * Find the skb that holds this file in its SCM_RIGHTS. When found,
-	 * remove this entry and rearrange the file array.
-	 */
-	skb = skb_dequeue(head);
-	while (skb) {
-		struct scm_fp_list *fp;
-
-		fp = UNIXCB(skb).fp;
-		for (i = 0; i < fp->count; i++) {
-			int left;
-
-			if (fp->fp[i] != file)
-				continue;
-
-			unix_notinflight(fp->user, fp->fp[i]);
-			left = fp->count - 1 - i;
-			if (left) {
-				memmove(&fp->fp[i], &fp->fp[i + 1],
-						left * sizeof(struct file *));
-			}
-			fp->count--;
-			if (!fp->count) {
-				kfree_skb(skb);
-				skb = NULL;
-			} else {
-				__skb_queue_tail(&list, skb);
-			}
-			fput(file);
-			file = NULL;
-			break;
-		}
-
-		if (!file)
-			break;
-
-		__skb_queue_tail(&list, skb);
-
-		skb = skb_dequeue(head);
-	}
-
-	if (skb_peek(&list)) {
-		spin_lock_irq(&head->lock);
-		while ((skb = __skb_dequeue(&list)) != NULL)
-			__skb_queue_tail(head, skb);
-		spin_unlock_irq(&head->lock);
-	}
-#else
-	fput(io_file_from_index(ctx, index));
-#endif
-}
-
 static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
 				int index)
 {
@@ -4449,29 +5661,65 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file,
 #endif
 }
 
-static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
-			       unsigned nr_args)
+static void io_atomic_switch(struct percpu_ref *ref)
 {
-	struct io_uring_files_update up;
+	struct fixed_file_data *data;
+
+	data = container_of(ref, struct fixed_file_data, refs);
+	clear_bit(FFD_F_ATOMIC, &data->state);
+}
+
+static bool io_queue_file_removal(struct fixed_file_data *data,
+				  struct file *file)
+{
+	struct io_file_put *pfile, pfile_stack;
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	/*
+	 * If we fail allocating the struct we need for doing async reomval
+	 * of this file, just punt to sync and wait for it.
+	 */
+	pfile = kzalloc(sizeof(*pfile), GFP_KERNEL);
+	if (!pfile) {
+		pfile = &pfile_stack;
+		pfile->done = &done;
+	}
+
+	pfile->file = file;
+	llist_add(&pfile->llist, &data->put_llist);
+
+	if (pfile == &pfile_stack) {
+		if (!test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
+			percpu_ref_put(&data->refs);
+			percpu_ref_switch_to_atomic(&data->refs,
+							io_atomic_switch);
+		}
+		wait_for_completion(&done);
+		flush_work(&data->ref_work);
+		return false;
+	}
+
+	return true;
+}
+
+static int __io_sqe_files_update(struct io_ring_ctx *ctx,
+				 struct io_uring_files_update *up,
+				 unsigned nr_args)
+{
+	struct fixed_file_data *data = ctx->file_data;
+	bool ref_switch = false;
+	struct file *file;
 	__s32 __user *fds;
 	int fd, i, err;
 	__u32 done;
 
-	if (!ctx->file_table)
-		return -ENXIO;
-	if (!nr_args)
-		return -EINVAL;
-	if (copy_from_user(&up, arg, sizeof(up)))
-		return -EFAULT;
-	if (up.resv)
-		return -EINVAL;
-	if (check_add_overflow(up.offset, nr_args, &done))
+	if (check_add_overflow(up->offset, nr_args, &done))
 		return -EOVERFLOW;
 	if (done > ctx->nr_user_files)
 		return -EINVAL;
 
 	done = 0;
-	fds = u64_to_user_ptr(up.fds);
+	fds = u64_to_user_ptr(up->fds);
 	while (nr_args) {
 		struct fixed_file_table *table;
 		unsigned index;
@@ -4481,16 +5729,16 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
 			err = -EFAULT;
 			break;
 		}
-		i = array_index_nospec(up.offset, ctx->nr_user_files);
-		table = &ctx->file_table[i >> IORING_FILE_TABLE_SHIFT];
+		i = array_index_nospec(up->offset, ctx->nr_user_files);
+		table = &ctx->file_data->table[i >> IORING_FILE_TABLE_SHIFT];
 		index = i & IORING_FILE_TABLE_MASK;
 		if (table->files[index]) {
-			io_sqe_file_unregister(ctx, i);
+			file = io_file_from_index(ctx, index);
 			table->files[index] = NULL;
+			if (io_queue_file_removal(data, file))
+				ref_switch = true;
 		}
 		if (fd != -1) {
-			struct file *file;
-
 			file = fget(fd);
 			if (!file) {
 				err = -EBADF;
@@ -4516,11 +5764,32 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
 		}
 		nr_args--;
 		done++;
-		up.offset++;
+		up->offset++;
+	}
+
+	if (ref_switch && !test_and_set_bit(FFD_F_ATOMIC, &data->state)) {
+		percpu_ref_put(&data->refs);
+		percpu_ref_switch_to_atomic(&data->refs, io_atomic_switch);
 	}
 
 	return done ? done : err;
 }
+static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg,
+			       unsigned nr_args)
+{
+	struct io_uring_files_update up;
+
+	if (!ctx->file_data)
+		return -ENXIO;
+	if (!nr_args)
+		return -EINVAL;
+	if (copy_from_user(&up, arg, sizeof(up)))
+		return -EFAULT;
+	if (up.resv)
+		return -EINVAL;
+
+	return __io_sqe_files_update(ctx, &up, nr_args);
+}
 
 static void io_put_work(struct io_wq_work *work)
 {
@@ -4536,11 +5805,56 @@ static void io_get_work(struct io_wq_work *work)
 	refcount_inc(&req->refs);
 }
 
+static int io_init_wq_offload(struct io_ring_ctx *ctx,
+			      struct io_uring_params *p)
+{
+	struct io_wq_data data;
+	struct fd f;
+	struct io_ring_ctx *ctx_attach;
+	unsigned int concurrency;
+	int ret = 0;
+
+	data.user = ctx->user;
+	data.get_work = io_get_work;
+	data.put_work = io_put_work;
+
+	if (!(p->flags & IORING_SETUP_ATTACH_WQ)) {
+		/* Do QD, or 4 * CPUS, whatever is smallest */
+		concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
+
+		ctx->io_wq = io_wq_create(concurrency, &data);
+		if (IS_ERR(ctx->io_wq)) {
+			ret = PTR_ERR(ctx->io_wq);
+			ctx->io_wq = NULL;
+		}
+		return ret;
+	}
+
+	f = fdget(p->wq_fd);
+	if (!f.file)
+		return -EBADF;
+
+	if (f.file->f_op != &io_uring_fops) {
+		ret = -EINVAL;
+		goto out_fput;
+	}
+
+	ctx_attach = f.file->private_data;
+	/* @io_wq is protected by holding the fd */
+	if (!io_wq_get(ctx_attach->io_wq, &data)) {
+		ret = -EINVAL;
+		goto out_fput;
+	}
+
+	ctx->io_wq = ctx_attach->io_wq;
+out_fput:
+	fdput(f);
+	return ret;
+}
+
 static int io_sq_offload_start(struct io_ring_ctx *ctx,
 			       struct io_uring_params *p)
 {
-	struct io_wq_data data;
-	unsigned concurrency;
 	int ret;
 
 	init_waitqueue_head(&ctx->sqo_wait);
@@ -4584,20 +5898,9 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 		goto err;
 	}
 
-	data.mm = ctx->sqo_mm;
-	data.user = ctx->user;
-	data.creds = ctx->creds;
-	data.get_work = io_get_work;
-	data.put_work = io_put_work;
-
-	/* Do QD, or 4 * CPUS, whatever is smallest */
-	concurrency = min(ctx->sq_entries, 4 * num_online_cpus());
-	ctx->io_wq = io_wq_create(concurrency, &data);
-	if (IS_ERR(ctx->io_wq)) {
-		ret = PTR_ERR(ctx->io_wq);
-		ctx->io_wq = NULL;
+	ret = io_init_wq_offload(ctx, p);
+	if (ret)
 		goto err;
-	}
 
 	return 0;
 err:
@@ -4702,7 +6005,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
 		struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
 
 		for (j = 0; j < imu->nr_bvecs; j++)
-			put_user_page(imu->bvec[j].bv_page);
+			unpin_user_page(imu->bvec[j].bv_page);
 
 		if (ctx->account_mem)
 			io_unaccount_mem(ctx->user, imu->nr_bvecs);
@@ -4823,7 +6126,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ret = 0;
 		down_read(&current->mm->mmap_sem);
-		pret = get_user_pages(ubuf, nr_pages,
+		pret = pin_user_pages(ubuf, nr_pages,
 				      FOLL_WRITE | FOLL_LONGTERM,
 				      pages, vmas);
 		if (pret == nr_pages) {
@@ -4847,7 +6150,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			 * release any pages we did get
 			 */
 			if (pret > 0)
-				put_user_pages(pages, pret);
+				unpin_user_pages(pages, pret);
 			if (ctx->account_mem)
 				io_unaccount_mem(ctx->user, nr_pages);
 			kvfree(imu->bvec);
@@ -4975,6 +6278,17 @@ static int io_uring_fasync(int fd, struct file *file, int on)
 	return fasync_helper(fd, file, on, &ctx->cq_fasync);
 }
 
+static int io_remove_personalities(int id, void *p, void *data)
+{
+	struct io_ring_ctx *ctx = data;
+	const struct cred *cred;
+
+	cred = idr_remove(&ctx->personality_idr, id);
+	if (cred)
+		put_cred(cred);
+	return 0;
+}
+
 static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 {
 	mutex_lock(&ctx->uring_lock);
@@ -4991,6 +6305,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 	/* if we failed setting up the ctx, we might not have any rings */
 	if (ctx->rings)
 		io_cqring_overflow_flush(ctx, true);
+	idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
 	wait_for_completion(&ctx->completions[0]);
 	io_ring_ctx_free(ctx);
 }
@@ -5157,7 +6472,6 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	} else if (to_submit) {
 		struct mm_struct *cur_mm;
 
-		to_submit = min(to_submit, ctx->sq_entries);
 		mutex_lock(&ctx->uring_lock);
 		/* already have mm, so io_submit_sqes() won't try to grab it */
 		cur_mm = ctx->sqo_mm;
@@ -5273,7 +6587,6 @@ static int io_uring_get_fd(struct io_ring_ctx *ctx)
 
 #if defined(CONFIG_UNIX)
 	ctx->ring_sock->file = file;
-	ctx->ring_sock->sk->sk_user_data = ctx;
 #endif
 	fd_install(ret, file);
 	return ret;
@@ -5292,8 +6605,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	bool account_mem;
 	int ret;
 
-	if (!entries || entries > IORING_MAX_ENTRIES)
+	if (!entries)
 		return -EINVAL;
+	if (entries > IORING_MAX_ENTRIES) {
+		if (!(p->flags & IORING_SETUP_CLAMP))
+			return -EINVAL;
+		entries = IORING_MAX_ENTRIES;
+	}
 
 	/*
 	 * Use twice as many entries for the CQ ring. It's possible for the
@@ -5310,8 +6628,13 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 		 * to a power-of-two, if it isn't already. We do NOT impose
 		 * any cq vs sq ring sizing.
 		 */
-		if (p->cq_entries < p->sq_entries || p->cq_entries > IORING_MAX_CQ_ENTRIES)
+		if (p->cq_entries < p->sq_entries)
 			return -EINVAL;
+		if (p->cq_entries > IORING_MAX_CQ_ENTRIES) {
+			if (!(p->flags & IORING_SETUP_CLAMP))
+				return -EINVAL;
+			p->cq_entries = IORING_MAX_CQ_ENTRIES;
+		}
 		p->cq_entries = roundup_pow_of_two(p->cq_entries);
 	} else {
 		p->cq_entries = 2 * p->sq_entries;
@@ -5376,7 +6699,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 		goto err;
 
 	p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
-			IORING_FEAT_SUBMIT_STABLE;
+			IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+			IORING_FEAT_CUR_PERSONALITY;
 	trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
 	return ret;
 err:
@@ -5403,7 +6727,8 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
 	}
 
 	if (p.flags & ~(IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL |
-			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE))
+			IORING_SETUP_SQ_AFF | IORING_SETUP_CQSIZE |
+			IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
 		return -EINVAL;
 
 	ret = io_uring_create(entries, &p);
@@ -5422,6 +6747,84 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
 	return io_uring_setup(entries, params);
 }
 
+static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
+{
+	struct io_uring_probe *p;
+	size_t size;
+	int i, ret;
+
+	size = struct_size(p, ops, nr_args);
+	if (size == SIZE_MAX)
+		return -EOVERFLOW;
+	p = kzalloc(size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	ret = -EFAULT;
+	if (copy_from_user(p, arg, size))
+		goto out;
+	ret = -EINVAL;
+	if (memchr_inv(p, 0, size))
+		goto out;
+
+	p->last_op = IORING_OP_LAST - 1;
+	if (nr_args > IORING_OP_LAST)
+		nr_args = IORING_OP_LAST;
+
+	for (i = 0; i < nr_args; i++) {
+		p->ops[i].op = i;
+		if (!io_op_defs[i].not_supported)
+			p->ops[i].flags = IO_URING_OP_SUPPORTED;
+	}
+	p->ops_len = i;
+
+	ret = 0;
+	if (copy_to_user(arg, p, size))
+		ret = -EFAULT;
+out:
+	kfree(p);
+	return ret;
+}
+
+static int io_register_personality(struct io_ring_ctx *ctx)
+{
+	const struct cred *creds = get_current_cred();
+	int id;
+
+	id = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1,
+				USHRT_MAX, GFP_KERNEL);
+	if (id < 0)
+		put_cred(creds);
+	return id;
+}
+
+static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
+{
+	const struct cred *old_creds;
+
+	old_creds = idr_remove(&ctx->personality_idr, id);
+	if (old_creds) {
+		put_cred(old_creds);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static bool io_register_op_must_quiesce(int op)
+{
+	switch (op) {
+	case IORING_UNREGISTER_FILES:
+	case IORING_REGISTER_FILES_UPDATE:
+	case IORING_REGISTER_PROBE:
+	case IORING_REGISTER_PERSONALITY:
+	case IORING_UNREGISTER_PERSONALITY:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			       void __user *arg, unsigned nr_args)
 	__releases(ctx->uring_lock)
@@ -5437,18 +6840,26 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 	if (percpu_ref_is_dying(&ctx->refs))
 		return -ENXIO;
 
-	percpu_ref_kill(&ctx->refs);
+	if (io_register_op_must_quiesce(opcode)) {
+		percpu_ref_kill(&ctx->refs);
 
-	/*
-	 * Drop uring mutex before waiting for references to exit. If another
-	 * thread is currently inside io_uring_enter() it might need to grab
-	 * the uring_lock to make progress. If we hold it here across the drain
-	 * wait, then we can deadlock. It's safe to drop the mutex here, since
-	 * no new references will come in after we've killed the percpu ref.
-	 */
-	mutex_unlock(&ctx->uring_lock);
-	wait_for_completion(&ctx->completions[0]);
-	mutex_lock(&ctx->uring_lock);
+		/*
+		 * Drop uring mutex before waiting for references to exit. If
+		 * another thread is currently inside io_uring_enter() it might
+		 * need to grab the uring_lock to make progress. If we hold it
+		 * here across the drain wait, then we can deadlock. It's safe
+		 * to drop the mutex here, since no new references will come in
+		 * after we've killed the percpu ref.
+		 */
+		mutex_unlock(&ctx->uring_lock);
+		ret = wait_for_completion_interruptible(&ctx->completions[0]);
+		mutex_lock(&ctx->uring_lock);
+		if (ret) {
+			percpu_ref_resurrect(&ctx->refs);
+			ret = -EINTR;
+			goto out;
+		}
+	}
 
 	switch (opcode) {
 	case IORING_REGISTER_BUFFERS:
@@ -5473,10 +6884,17 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 		ret = io_sqe_files_update(ctx, arg, nr_args);
 		break;
 	case IORING_REGISTER_EVENTFD:
+	case IORING_REGISTER_EVENTFD_ASYNC:
 		ret = -EINVAL;
 		if (nr_args != 1)
 			break;
 		ret = io_eventfd_register(ctx, arg);
+		if (ret)
+			break;
+		if (opcode == IORING_REGISTER_EVENTFD_ASYNC)
+			ctx->eventfd_async = 1;
+		else
+			ctx->eventfd_async = 0;
 		break;
 	case IORING_UNREGISTER_EVENTFD:
 		ret = -EINVAL;
@@ -5484,14 +6902,35 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_eventfd_unregister(ctx);
 		break;
+	case IORING_REGISTER_PROBE:
+		ret = -EINVAL;
+		if (!arg || nr_args > 256)
+			break;
+		ret = io_probe(ctx, arg, nr_args);
+		break;
+	case IORING_REGISTER_PERSONALITY:
+		ret = -EINVAL;
+		if (arg || nr_args)
+			break;
+		ret = io_register_personality(ctx);
+		break;
+	case IORING_UNREGISTER_PERSONALITY:
+		ret = -EINVAL;
+		if (arg)
+			break;
+		ret = io_unregister_personality(ctx, nr_args);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
 
-	/* bring the ctx back to life */
-	reinit_completion(&ctx->completions[0]);
-	percpu_ref_reinit(&ctx->refs);
+	if (io_register_op_must_quiesce(opcode)) {
+		/* bring the ctx back to life */
+		percpu_ref_reinit(&ctx->refs);
+out:
+		reinit_completion(&ctx->completions[0]);
+	}
 	return ret;
 }
 
@@ -5524,6 +6963,7 @@ out_fput:
 
 static int __init io_uring_init(void)
 {
+	BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
 	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
 	return 0;
 };
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 2f5e4e5b97e1..7c9a5df5a597 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -467,7 +467,7 @@ EXPORT_SYMBOL(generic_block_fiemap);
  * Only the l_start, l_len and l_whence fields of the 'struct space_resv'
  * are used here, rest are ignored.
  */
-int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
+static int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
 {
 	struct inode *inode = file_inode(filp);
 	struct space_resv sr;
@@ -495,8 +495,8 @@ int ioctl_preallocate(struct file *filp, int mode, void __user *argp)
 /* on ia32 l_start is on a 32-bit boundary */
 #if defined CONFIG_COMPAT && defined(CONFIG_X86_64)
 /* just account for different alignment */
-int compat_ioctl_preallocate(struct file *file, int mode,
-				struct space_resv_32 __user *argp)
+static int compat_ioctl_preallocate(struct file *file, int mode,
+				    struct space_resv_32 __user *argp)
 {
 	struct inode *inode = file_inode(file);
 	struct space_resv_32 sr;
@@ -521,11 +521,9 @@ int compat_ioctl_preallocate(struct file *file, int mode,
 }
 #endif
 
-static int file_ioctl(struct file *filp, unsigned int cmd,
-		unsigned long arg)
+static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p)
 {
 	struct inode *inode = file_inode(filp);
-	int __user *p = (int __user *)arg;
 
 	switch (cmd) {
 	case FIBMAP:
@@ -542,7 +540,7 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
 		return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p);
 	}
 
-	return vfs_ioctl(filp, cmd, arg);
+	return -ENOIOCTLCMD;
 }
 
 static int ioctl_fionbio(struct file *filp, int __user *argp)
@@ -661,53 +659,48 @@ out:
 }
 
 /*
- * When you add any new common ioctls to the switches above and below
- * please update compat_sys_ioctl() too.
- *
  * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d.
  * It's just a simple helper for sys_ioctl and compat_sys_ioctl.
+ *
+ * When you add any new common ioctls to the switches above and below,
+ * please ensure they have compatible arguments in compat mode.
  */
-int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
-	     unsigned long arg)
+static int do_vfs_ioctl(struct file *filp, unsigned int fd,
+			unsigned int cmd, unsigned long arg)
 {
-	int error = 0;
 	void __user *argp = (void __user *)arg;
 	struct inode *inode = file_inode(filp);
 
 	switch (cmd) {
 	case FIOCLEX:
 		set_close_on_exec(fd, 1);
-		break;
+		return 0;
 
 	case FIONCLEX:
 		set_close_on_exec(fd, 0);
-		break;
+		return 0;
 
 	case FIONBIO:
-		error = ioctl_fionbio(filp, argp);
-		break;
+		return ioctl_fionbio(filp, argp);
 
 	case FIOASYNC:
-		error = ioctl_fioasync(fd, filp, argp);
-		break;
+		return ioctl_fioasync(fd, filp, argp);
 
 	case FIOQSIZE:
 		if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) ||
 		    S_ISLNK(inode->i_mode)) {
 			loff_t res = inode_get_bytes(inode);
-			error = copy_to_user(argp, &res, sizeof(res)) ?
-					-EFAULT : 0;
-		} else
-			error = -ENOTTY;
-		break;
+			return copy_to_user(argp, &res, sizeof(res)) ?
+					    -EFAULT : 0;
+		}
+
+		return -ENOTTY;
 
 	case FIFREEZE:
-		error = ioctl_fsfreeze(filp);
-		break;
+		return ioctl_fsfreeze(filp);
 
 	case FITHAW:
-		error = ioctl_fsthaw(filp);
-		break;
+		return ioctl_fsthaw(filp);
 
 	case FS_IOC_FIEMAP:
 		return ioctl_fiemap(filp, argp);
@@ -716,6 +709,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		/* anon_bdev filesystems may not have a block size */
 		if (!inode->i_sb->s_blocksize)
 			return -EINVAL;
+
 		return put_user(inode->i_sb->s_blocksize, (int __user *)argp);
 
 	case FICLONE:
@@ -729,24 +723,30 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 
 	default:
 		if (S_ISREG(inode->i_mode))
-			error = file_ioctl(filp, cmd, arg);
-		else
-			error = vfs_ioctl(filp, cmd, arg);
+			return file_ioctl(filp, cmd, argp);
 		break;
 	}
-	return error;
+
+	return -ENOIOCTLCMD;
 }
 
 int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg)
 {
-	int error;
 	struct fd f = fdget(fd);
+	int error;
 
 	if (!f.file)
 		return -EBADF;
+
 	error = security_file_ioctl(f.file, cmd, arg);
-	if (!error)
-		error = do_vfs_ioctl(f.file, fd, cmd, arg);
+	if (error)
+		goto out;
+
+	error = do_vfs_ioctl(f.file, fd, cmd, arg);
+	if (error == -ENOIOCTLCMD)
+		error = vfs_ioctl(f.file, cmd, arg);
+
+out:
 	fdput(f);
 	return error;
 }
@@ -788,4 +788,65 @@ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
 }
 EXPORT_SYMBOL(compat_ptr_ioctl);
+
+COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
+{
+	struct fd f = fdget(fd);
+	int error;
+
+	if (!f.file)
+		return -EBADF;
+
+	/* RED-PEN how should LSM module know it's handling 32bit? */
+	error = security_file_ioctl(f.file, cmd, arg);
+	if (error)
+		goto out;
+
+	switch (cmd) {
+	/* FICLONE takes an int argument, so don't use compat_ptr() */
+	case FICLONE:
+		error = ioctl_file_clone(f.file, arg, 0, 0, 0);
+		break;
+
+#if defined(CONFIG_X86_64)
+	/* these get messy on amd64 due to alignment differences */
+	case FS_IOC_RESVSP_32:
+	case FS_IOC_RESVSP64_32:
+		error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg));
+		break;
+	case FS_IOC_UNRESVSP_32:
+	case FS_IOC_UNRESVSP64_32:
+		error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE,
+				compat_ptr(arg));
+		break;
+	case FS_IOC_ZERO_RANGE_32:
+		error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE,
+				compat_ptr(arg));
+		break;
+#endif
+
+	/*
+	 * everything else in do_vfs_ioctl() takes either a compatible
+	 * pointer argument or no argument -- call it with a modified
+	 * argument.
+	 */
+	default:
+		error = do_vfs_ioctl(f.file, fd, cmd,
+				     (unsigned long)compat_ptr(arg));
+		if (error != -ENOIOCTLCMD)
+			break;
+
+		if (f.file->f_op->compat_ioctl)
+			error = f.file->f_op->compat_ioctl(f.file, cmd, arg);
+		if (error == -ENOIOCTLCMD)
+			error = -ENOTTY;
+		break;
+	}
+
+ out:
+	fdput(f);
+
+	return error;
+}
 #endif
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 828444e14d09..7c84c4c027c4 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1077,24 +1077,16 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	unsigned long length;
-	loff_t offset, size;
+	loff_t offset;
 	ssize_t ret;
 
 	lock_page(page);
-	size = i_size_read(inode);
-	offset = page_offset(page);
-	if (page->mapping != inode->i_mapping || offset > size) {
-		/* We overload EFAULT to mean page got truncated */
-		ret = -EFAULT;
+	ret = page_mkwrite_check_truncate(page, inode);
+	if (ret < 0)
 		goto out_unlock;
-	}
-
-	/* page is wholly or partially inside EOF */
-	if (offset > size - PAGE_SIZE)
-		length = offset_in_page(size);
-	else
-		length = PAGE_SIZE;
+	length = ret;
 
+	offset = page_offset(page);
 	while (length > 0) {
 		ret = iomap_apply(inode, offset, length,
 				IOMAP_WRITE | IOMAP_FAULT, ops, page,
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 8fff6677a5da..96bf33986d03 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -164,7 +164,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 				       "journal space in %s\n", __func__,
 				       journal->j_devname);
 				WARN_ON(1);
-				jbd2_journal_abort(journal, 0);
+				jbd2_journal_abort(journal, -EIO);
 			}
 			write_lock(&journal->j_state_lock);
 		} else {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 7f0b362b3842..2494095e0340 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -782,7 +782,7 @@ start_journal_io:
 		err = journal_submit_commit_record(journal, commit_transaction,
 						 &cbh, crc32_sum);
 		if (err)
-			__jbd2_journal_abort_hard(journal);
+			jbd2_journal_abort(journal, err);
 	}
 
 	blk_finish_plug(&plug);
@@ -875,7 +875,7 @@ start_journal_io:
 		err = journal_submit_commit_record(journal, commit_transaction,
 						&cbh, crc32_sum);
 		if (err)
-			__jbd2_journal_abort_hard(journal);
+			jbd2_journal_abort(journal, err);
 	}
 	if (cbh)
 		err = journal_wait_on_commit_record(journal, cbh);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 5e408ee24a1a..eb8ca446d1ab 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -96,7 +96,6 @@ EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
 EXPORT_SYMBOL(jbd2_inode_cache);
 
-static void __journal_abort_soft (journal_t *journal, int errno);
 static int jbd2_journal_create_slab(size_t slab_size);
 
 #ifdef CONFIG_JBD2_DEBUG
@@ -805,7 +804,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
 					"at offset %lu on %s\n",
 			       __func__, blocknr, journal->j_devname);
 			err = -EIO;
-			__journal_abort_soft(journal, err);
+			jbd2_journal_abort(journal, err);
 		}
 	} else {
 		*retp = blocknr; /* +journal->j_blk_offset */
@@ -982,6 +981,7 @@ static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
 
 static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+	(*pos)++;
 	return NULL;
 }
 
@@ -1074,12 +1074,11 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file)
 	return seq_release(inode, file);
 }
 
-static const struct file_operations jbd2_seq_info_fops = {
-	.owner		= THIS_MODULE,
-	.open           = jbd2_seq_info_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = jbd2_seq_info_release,
+static const struct proc_ops jbd2_info_proc_ops = {
+	.proc_open	= jbd2_seq_info_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= jbd2_seq_info_release,
 };
 
 static struct proc_dir_entry *proc_jbd2_stats;
@@ -1089,7 +1088,7 @@ static void jbd2_stats_proc_init(journal_t *journal)
 	journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
 	if (journal->j_proc_entry) {
 		proc_create_data("info", S_IRUGO, journal->j_proc_entry,
-				 &jbd2_seq_info_fops, journal);
+				 &jbd2_info_proc_ops, journal);
 	}
 }
 
@@ -1710,6 +1709,11 @@ int jbd2_journal_load(journal_t *journal)
 		       journal->j_devname);
 		return -EFSCORRUPTED;
 	}
+	/*
+	 * clear JBD2_ABORT flag initialized in journal_init_common
+	 * here to update log tail information with the newest seq.
+	 */
+	journal->j_flags &= ~JBD2_ABORT;
 
 	/* OK, we've finished with the dynamic journal bits:
 	 * reinitialise the dynamic contents of the superblock in memory
@@ -1717,7 +1721,6 @@ int jbd2_journal_load(journal_t *journal)
 	if (journal_reset(journal))
 		goto recovery_error;
 
-	journal->j_flags &= ~JBD2_ABORT;
 	journal->j_flags |= JBD2_LOADED;
 	return 0;
 
@@ -2098,67 +2101,6 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	return err;
 }
 
-/*
- * Journal abort has very specific semantics, which we describe
- * for journal abort.
- *
- * Two internal functions, which provide abort to the jbd layer
- * itself are here.
- */
-
-/*
- * Quick version for internal journal use (doesn't lock the journal).
- * Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
- * and don't attempt to make any other journal updates.
- */
-void __jbd2_journal_abort_hard(journal_t *journal)
-{
-	transaction_t *transaction;
-
-	if (journal->j_flags & JBD2_ABORT)
-		return;
-
-	printk(KERN_ERR "Aborting journal on device %s.\n",
-	       journal->j_devname);
-
-	write_lock(&journal->j_state_lock);
-	journal->j_flags |= JBD2_ABORT;
-	transaction = journal->j_running_transaction;
-	if (transaction)
-		__jbd2_log_start_commit(journal, transaction->t_tid);
-	write_unlock(&journal->j_state_lock);
-}
-
-/* Soft abort: record the abort error status in the journal superblock,
- * but don't do any other IO. */
-static void __journal_abort_soft (journal_t *journal, int errno)
-{
-	int old_errno;
-
-	write_lock(&journal->j_state_lock);
-	old_errno = journal->j_errno;
-	if (!journal->j_errno || errno == -ESHUTDOWN)
-		journal->j_errno = errno;
-
-	if (journal->j_flags & JBD2_ABORT) {
-		write_unlock(&journal->j_state_lock);
-		if (!old_errno && old_errno != -ESHUTDOWN &&
-		    errno == -ESHUTDOWN)
-			jbd2_journal_update_sb_errno(journal);
-		return;
-	}
-	write_unlock(&journal->j_state_lock);
-
-	__jbd2_journal_abort_hard(journal);
-
-	if (errno) {
-		jbd2_journal_update_sb_errno(journal);
-		write_lock(&journal->j_state_lock);
-		journal->j_flags |= JBD2_REC_ERR;
-		write_unlock(&journal->j_state_lock);
-	}
-}
-
 /**
  * void jbd2_journal_abort () - Shutdown the journal immediately.
  * @journal: the journal to shutdown.
@@ -2198,16 +2140,51 @@ static void __journal_abort_soft (journal_t *journal, int errno)
  * failure to disk.  ext3_error, for example, now uses this
  * functionality.
  *
- * Errors which originate from within the journaling layer will NOT
- * supply an errno; a null errno implies that absolutely no further
- * writes are done to the journal (unless there are any already in
- * progress).
- *
  */
 
 void jbd2_journal_abort(journal_t *journal, int errno)
 {
-	__journal_abort_soft(journal, errno);
+	transaction_t *transaction;
+
+	/*
+	 * ESHUTDOWN always takes precedence because a file system check
+	 * caused by any other journal abort error is not required after
+	 * a shutdown triggered.
+	 */
+	write_lock(&journal->j_state_lock);
+	if (journal->j_flags & JBD2_ABORT) {
+		int old_errno = journal->j_errno;
+
+		write_unlock(&journal->j_state_lock);
+		if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) {
+			journal->j_errno = errno;
+			jbd2_journal_update_sb_errno(journal);
+		}
+		return;
+	}
+
+	/*
+	 * Mark the abort as occurred and start current running transaction
+	 * to release all journaled buffer.
+	 */
+	pr_err("Aborting journal on device %s.\n", journal->j_devname);
+
+	journal->j_flags |= JBD2_ABORT;
+	journal->j_errno = errno;
+	transaction = journal->j_running_transaction;
+	if (transaction)
+		__jbd2_log_start_commit(journal, transaction->t_tid);
+	write_unlock(&journal->j_state_lock);
+
+	/*
+	 * Record errno to the journal super block, so that fsck and jbd2
+	 * layer could realise that a filesystem check is needed.
+	 */
+	jbd2_journal_update_sb_errno(journal);
+
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_REC_ERR;
+	write_unlock(&journal->j_state_lock);
 }
 
 /**
@@ -2556,7 +2533,6 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 {
 	struct journal_head *jh = bh2jh(bh);
 
-	J_ASSERT_JH(jh, jh->b_jcount >= 0);
 	J_ASSERT_JH(jh, jh->b_transaction == NULL);
 	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
 	J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 27b9f9dee434..e77a5a0b4e46 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -525,7 +525,7 @@ EXPORT_SYMBOL(jbd2__journal_start);
  * modified buffers in the log.  We block until the log can guarantee
  * that much space. Additionally, if rsv_blocks > 0, we also create another
  * handle with rsv_blocks reserved blocks in the journal. This handle is
- * is stored in h_rsv_handle. It is not attached to any particular transaction
+ * stored in h_rsv_handle. It is not attached to any particular transaction
  * and thus doesn't block transaction commit. If the caller uses this reserved
  * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop()
  * on the parent handle will dispose the reserved one. Reserved handle has to
@@ -1595,7 +1595,7 @@ out:
  * Allow this call even if the handle has aborted --- it may be part of
  * the caller's cleanup after an abort.
  */
-int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
+int jbd2_journal_forget(handle_t *handle, struct buffer_head *bh)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal;
diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c
index 888cdd685a1e..44b62b3c322e 100644
--- a/fs/jfs/jfs_debug.c
+++ b/fs/jfs/jfs_debug.c
@@ -43,12 +43,12 @@ static ssize_t jfs_loglevel_proc_write(struct file *file,
 	return count;
 }
 
-static const struct file_operations jfs_loglevel_proc_fops = {
-	.open		= jfs_loglevel_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= jfs_loglevel_proc_write,
+static const struct proc_ops jfs_loglevel_proc_ops = {
+	.proc_open	= jfs_loglevel_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= jfs_loglevel_proc_write,
 };
 #endif
 
@@ -68,7 +68,7 @@ void jfs_proc_init(void)
 #endif
 #ifdef CONFIG_JFS_DEBUG
 	proc_create_single("TxAnchor", 0, base, jfs_txanchor_proc_show);
-	proc_create("loglevel", 0, base, &jfs_loglevel_proc_fops);
+	proc_create("loglevel", 0, base, &jfs_loglevel_proc_ops);
 #endif
 }
 
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index caade185e568..7dfcab2a2da6 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -4027,7 +4027,6 @@ static int dbGetL2AGSize(s64 nblocks)
  */
 #define MAXL0PAGES	(1 + LPERCTL)
 #define MAXL1PAGES	(1 + LPERCTL * MAXL0PAGES)
-#define MAXL2PAGES	(1 + LPERCTL * MAXL1PAGES)
 
 /*
  * convert number of map pages to the zero origin top dmapctl level
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index eac277c63d42..d0f7a5abd9a9 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -160,9 +160,9 @@ static inline void set_inode_attr(struct inode *inode,
 {
 	inode->i_uid = attrs->ia_uid;
 	inode->i_gid = attrs->ia_gid;
-	inode->i_atime = timestamp_truncate(attrs->ia_atime, inode);
-	inode->i_mtime = timestamp_truncate(attrs->ia_mtime, inode);
-	inode->i_ctime = timestamp_truncate(attrs->ia_ctime, inode);
+	inode->i_atime = attrs->ia_atime;
+	inode->i_mtime = attrs->ia_mtime;
+	inode->i_ctime = attrs->ia_ctime;
 }
 
 static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
diff --git a/fs/libfs.c b/fs/libfs.c
index 1463b038ffc4..c686bd9caac6 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -19,6 +19,7 @@
 #include <linux/buffer_head.h> /* sync_mapping_buffers */
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
+#include <linux/fsnotify.h>
 
 #include <linux/uaccess.h>
 
@@ -239,6 +240,75 @@ const struct inode_operations simple_dir_inode_operations = {
 };
 EXPORT_SYMBOL(simple_dir_inode_operations);
 
+static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
+{
+	struct dentry *child = NULL;
+	struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs;
+
+	spin_lock(&parent->d_lock);
+	while ((p = p->next) != &parent->d_subdirs) {
+		struct dentry *d = container_of(p, struct dentry, d_child);
+		if (simple_positive(d)) {
+			spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
+			if (simple_positive(d))
+				child = dget_dlock(d);
+			spin_unlock(&d->d_lock);
+			if (likely(child))
+				break;
+		}
+	}
+	spin_unlock(&parent->d_lock);
+	dput(prev);
+	return child;
+}
+
+void simple_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *))
+{
+	struct dentry *this = dget(dentry);
+	while (true) {
+		struct dentry *victim = NULL, *child;
+		struct inode *inode = this->d_inode;
+
+		inode_lock(inode);
+		if (d_is_dir(this))
+			inode->i_flags |= S_DEAD;
+		while ((child = find_next_child(this, victim)) == NULL) {
+			// kill and ascend
+			// update metadata while it's still locked
+			inode->i_ctime = current_time(inode);
+			clear_nlink(inode);
+			inode_unlock(inode);
+			victim = this;
+			this = this->d_parent;
+			inode = this->d_inode;
+			inode_lock(inode);
+			if (simple_positive(victim)) {
+				d_invalidate(victim);	// avoid lost mounts
+				if (d_is_dir(victim))
+					fsnotify_rmdir(inode, victim);
+				else
+					fsnotify_unlink(inode, victim);
+				if (callback)
+					callback(victim);
+				dput(victim);		// unpin it
+			}
+			if (victim == dentry) {
+				inode->i_ctime = inode->i_mtime =
+					current_time(inode);
+				if (d_is_dir(dentry))
+					drop_nlink(inode);
+				inode_unlock(inode);
+				dput(dentry);
+				return;
+			}
+		}
+		inode_unlock(inode);
+		this = child;
+	}
+}
+EXPORT_SYMBOL(simple_recursive_removal);
+
 static const struct super_operations simple_super_operations = {
 	.statfs		= simple_statfs,
 };
diff --git a/fs/lockd/procfs.c b/fs/lockd/procfs.c
index ca9228a56d65..a01f08c8c2f3 100644
--- a/fs/lockd/procfs.c
+++ b/fs/lockd/procfs.c
@@ -60,11 +60,11 @@ nlm_end_grace_read(struct file *file, char __user *buf, size_t size,
 	return simple_read_from_buffer(buf, size, pos, resp, sizeof(resp));
 }
 
-static const struct file_operations lockd_end_grace_operations = {
-	.write		= nlm_end_grace_write,
-	.read		= nlm_end_grace_read,
-	.llseek		= default_llseek,
-	.release	= simple_transaction_release,
+static const struct proc_ops lockd_end_grace_proc_ops = {
+	.proc_write	= nlm_end_grace_write,
+	.proc_read	= nlm_end_grace_read,
+	.proc_lseek	= default_llseek,
+	.proc_release	= simple_transaction_release,
 };
 
 int __init
@@ -76,7 +76,7 @@ lockd_create_procfs(void)
 	if (!entry)
 		return -ENOMEM;
 	entry = proc_create("nlm_end_grace", S_IRUGO|S_IWUSR, entry,
-				 &lockd_end_grace_operations);
+			    &lockd_end_grace_proc_ops);
 	if (!entry) {
 		remove_proc_entry("fs/lockd", NULL);
 		return -ENOMEM;
diff --git a/fs/namei.c b/fs/namei.c
index 4167109297e0..db6565c99825 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3333,8 +3333,8 @@ static int do_last(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op)
 {
 	struct dentry *dir = nd->path.dentry;
-	kuid_t dir_uid = dir->d_inode->i_uid;
-	umode_t dir_mode = dir->d_inode->i_mode;
+	kuid_t dir_uid = nd->inode->i_uid;
+	umode_t dir_mode = nd->inode->i_mode;
 	int open_flag = op->open_flag;
 	bool will_truncate = (open_flag & O_TRUNC) != 0;
 	bool got_write = false;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 11b42c523f04..7eb919f1b13f 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -157,11 +157,11 @@ static int exports_proc_open(struct inode *inode, struct file *file)
 	return exports_net_open(current->nsproxy->net_ns, file);
 }
 
-static const struct file_operations exports_proc_operations = {
-	.open		= exports_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops exports_proc_ops = {
+	.proc_open	= exports_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static int exports_nfsd_open(struct inode *inode, struct file *file)
@@ -1431,8 +1431,7 @@ static int create_proc_exports_entry(void)
 	entry = proc_mkdir("fs/nfs", NULL);
 	if (!entry)
 		return -ENOMEM;
-	entry = proc_create("exports", 0, entry,
-				 &exports_proc_operations);
+	entry = proc_create("exports", 0, entry, &exports_proc_ops);
 	if (!entry) {
 		remove_proc_entry("fs/nfs", NULL);
 		return -ENOMEM;
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 9bce3b913189..b1bc582b0493 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -84,17 +84,17 @@ static int nfsd_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, nfsd_proc_show, NULL);
 }
 
-static const struct file_operations nfsd_proc_fops = {
-	.open = nfsd_proc_open,
-	.read  = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
+static const struct proc_ops nfsd_proc_ops = {
+	.proc_open	= nfsd_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 void
 nfsd_stat_init(void)
 {
-	svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_fops);
+	svc_proc_register(&init_net, &nfsd_svcstats, &nfsd_proc_ops);
 }
 
 void
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 6c7388430ad3..d4359a1df3d5 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2899,18 +2899,12 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr)
 			ia_valid |= ATTR_MTIME | ATTR_CTIME;
 		}
 	}
-	if (ia_valid & ATTR_ATIME) {
-		vi->i_atime = timestamp_truncate(attr->ia_atime,
-					       vi);
-	}
-	if (ia_valid & ATTR_MTIME) {
-		vi->i_mtime = timestamp_truncate(attr->ia_mtime,
-					       vi);
-	}
-	if (ia_valid & ATTR_CTIME) {
-		vi->i_ctime = timestamp_truncate(attr->ia_ctime,
-					       vi);
-	}
+	if (ia_valid & ATTR_ATIME)
+		vi->i_atime = attr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		vi->i_mtime = attr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		vi->i_ctime = attr->ia_ctime;
 	mark_inode_dirty(vi);
 out:
 	return err;
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 5c424a099280..1ef24574f481 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -73,7 +73,7 @@ static void o2quo_fence_self(void)
 		       "system by restarting ***\n");
 		emergency_restart();
 		break;
-	};
+	}
 }
 
 /* Indicate that a timeout occurred on a heartbeat region write. The
diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile
index 38b224372776..5e700b45d32d 100644
--- a/fs/ocfs2/dlm/Makefile
+++ b/fs/ocfs2/dlm/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
 obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o
 
 ocfs2_dlm-objs := dlmdomain.o dlmdebug.o dlmthread.o dlmrecovery.o \
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index 4de89af96abf..6abaded3ff6b 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -23,15 +23,15 @@
 #include <linux/spinlock.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 			   struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index aaf24548b02a..0463dce65bb2 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -688,10 +688,6 @@ struct dlm_begin_reco
 	__be32 pad2;
 };
 
-
-#define BITS_PER_BYTE 8
-#define BITS_TO_BYTES(bits) (((bits)+BITS_PER_BYTE-1)/BITS_PER_BYTE)
-
 struct dlm_query_join_request
 {
 	u8 node_idx;
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index 965f45dbe17b..6051edc33aef 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -23,9 +23,9 @@
 #include <linux/spinlock.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -33,7 +33,7 @@
 #include "dlmconvert.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 /* NOTE: __dlmconvert_master is the only function in here that
  * needs a spinlock held on entry (res->spinlock) and it is the
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 4d0b452012b2..c5c6efba7b5e 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -17,9 +17,9 @@
 #include <linux/debugfs.h>
 #include <linux/export.h>
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -27,7 +27,7 @@
 #include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static int stringify_lockname(const char *lockname, int locklen, char *buf,
 			      int len);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index ee6f459f9770..357cfc702ce3 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -20,9 +20,9 @@
 #include <linux/debugfs.h>
 #include <linux/sched/signal.h>
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -30,7 +30,7 @@
 #include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_DOMAIN)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 /*
  * ocfs2 node maps are array of long int, which limits to send them freely
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index baff087f3863..83f0760e4fba 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -25,9 +25,9 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -35,7 +35,7 @@
 #include "dlmconvert.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static struct kmem_cache *dlm_lock_cache;
 
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 74b768ca1cd8..900f7e466d11 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -25,9 +25,9 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
@@ -35,7 +35,7 @@
 #include "dlmdebug.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_MASTER)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static void dlm_mle_node_down(struct dlm_ctxt *dlm,
 			      struct dlm_master_list_entry *mle,
@@ -2554,8 +2554,6 @@ static int dlm_migrate_lockres(struct dlm_ctxt *dlm,
 	if (!dlm_grab(dlm))
 		return -EINVAL;
 
-	BUG_ON(target == O2NM_MAX_NODES);
-
 	name = res->lockname.name;
 	namelen = res->lockname.len;
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 064ce5bbc3f6..4b566e88582f 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -26,16 +26,16 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 #include "dlmdomain.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_RECOVERY)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node);
 
@@ -1668,7 +1668,7 @@ static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
 int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 			  u8 nodenum, u8 *real_master)
 {
-	int ret = -EINVAL;
+	int ret;
 	struct dlm_master_requery req;
 	int status = DLM_LOCK_RES_OWNER_UNKNOWN;
 
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 61c51c268460..fd40c17cd022 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -25,16 +25,16 @@
 #include <linux/delay.h>
 
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 #include "dlmdomain.h"
 
 #define MLOG_MASK_PREFIX (ML_DLM|ML_DLM_THREAD)
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 static int dlm_thread(void *data);
 static void dlm_flush_asts(struct dlm_ctxt *dlm);
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 3883633e82eb..dcb17ca8ae74 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -23,15 +23,15 @@
 #include <linux/spinlock.h>
 #include <linux/delay.h>
 
-#include "cluster/heartbeat.h"
-#include "cluster/nodemanager.h"
-#include "cluster/tcp.h"
+#include "../cluster/heartbeat.h"
+#include "../cluster/nodemanager.h"
+#include "../cluster/tcp.h"
 
 #include "dlmapi.h"
 #include "dlmcommon.h"
 
 #define MLOG_MASK_PREFIX ML_DLM
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 #define DLM_UNLOCK_FREE_LOCK           0x00000001
 #define DLM_UNLOCK_CALL_AST            0x00000002
diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile
index a9874e441bd4..c7895f65be0e 100644
--- a/fs/ocfs2/dlmfs/Makefile
+++ b/fs/ocfs2/dlmfs/Makefile
@@ -1,6 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-ccflags-y := -I $(srctree)/$(src)/..
-
 obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o
 
 ocfs2_dlmfs-objs := userdlm.o dlmfs.o
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 4f1668c81e1f..8e4f1ace467c 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -33,11 +33,11 @@
 
 #include <linux/uaccess.h>
 
-#include "stackglue.h"
+#include "../stackglue.h"
 #include "userdlm.h"
 
 #define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 
 static const struct super_operations dlmfs_ops;
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index 525b14ddfba5..3df5be25bfb1 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -21,12 +21,12 @@
 #include <linux/types.h>
 #include <linux/crc32.h>
 
-#include "ocfs2_lockingver.h"
-#include "stackglue.h"
+#include "../ocfs2_lockingver.h"
+#include "../stackglue.h"
 #include "userdlm.h"
 
 #define MLOG_MASK_PREFIX ML_DLMFS
-#include "cluster/masklog.h"
+#include "../cluster/masklog.h"
 
 
 static inline struct user_lock_res *user_lksb_to_lock_res(struct ocfs2_dlm_lksb *lksb)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index cda1027d0819..cb9e6a73bea9 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -570,7 +570,7 @@ void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
 			mlog_bug_on_msg(1, "type: %d\n", type);
 			ops = NULL; /* thanks, gcc */
 			break;
-	};
+	}
 
 	ocfs2_build_lock_name(type, OCFS2_I(inode)->ip_blkno,
 			      generation, res->l_name);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 9876db52913a..6cd5e4924e4d 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2101,17 +2101,15 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
 static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
 					    struct buffer_head **di_bh,
 					    int meta_level,
-					    int overwrite_io,
 					    int write_sem,
 					    int wait)
 {
 	int ret = 0;
 
 	if (wait)
-		ret = ocfs2_inode_lock(inode, NULL, meta_level);
+		ret = ocfs2_inode_lock(inode, di_bh, meta_level);
 	else
-		ret = ocfs2_try_inode_lock(inode,
-			overwrite_io ? NULL : di_bh, meta_level);
+		ret = ocfs2_try_inode_lock(inode, di_bh, meta_level);
 	if (ret < 0)
 		goto out;
 
@@ -2136,6 +2134,7 @@ static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
 
 out_unlock:
 	brelse(*di_bh);
+	*di_bh = NULL;
 	ocfs2_inode_unlock(inode, meta_level);
 out:
 	return ret;
@@ -2177,7 +2176,6 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		ret = ocfs2_inode_lock_for_extent_tree(inode,
 						       &di_bh,
 						       meta_level,
-						       overwrite_io,
 						       write_sem,
 						       wait);
 		if (ret < 0) {
@@ -2233,13 +2231,13 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 							   &di_bh,
 							   meta_level,
 							   write_sem);
+			meta_level = 1;
+			write_sem = 1;
 			ret = ocfs2_inode_lock_for_extent_tree(inode,
 							       &di_bh,
 							       meta_level,
-							       overwrite_io,
-							       1,
+							       write_sem,
 							       wait);
-			write_sem = 1;
 			if (ret < 0) {
 				if (ret != -EAGAIN)
 					mlog_errno(ret);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 3103ba7f97a2..bfe611ed1b1d 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -597,9 +597,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	oi->i_sync_tid = handle->h_transaction->t_tid;
-	if (datasync)
-		oi->i_datasync_tid = handle->h_transaction->t_tid;
+	if (!is_handle_aborted(handle)) {
+		oi->i_sync_tid = handle->h_transaction->t_tid;
+		if (datasync)
+			oi->i_datasync_tid = handle->h_transaction->t_tid;
+	}
 }
 
 #endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8ea51cf27b97..da65251ef815 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -586,8 +586,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 			mlog_errno(status);
 	}
 
-	oi->i_sync_tid = handle->h_transaction->t_tid;
-	oi->i_datasync_tid = handle->h_transaction->t_tid;
+	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 
 leave:
 	if (status < 0) {
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 4180c3ef0a68..939df99d2dec 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -696,7 +696,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 
 	bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode,
 					       ac, cl);
-	if (IS_ERR(bg_bh) && (PTR_ERR(bg_bh) == -ENOSPC))
+	if (PTR_ERR(bg_bh) == -ENOSPC)
 		bg_bh = ocfs2_block_group_alloc_discontig(handle,
 							  alloc_inode,
 							  ac, cl);
diff --git a/fs/open.c b/fs/open.c
index 8cdb2b675867..0788b3715731 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -958,7 +958,7 @@ EXPORT_SYMBOL(open_with_fake_path);
 #define WILL_CREATE(flags)	(flags & (O_CREAT | __O_TMPFILE))
 #define O_PATH_FLAGS		(O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
 
-static inline struct open_how build_open_how(int flags, umode_t mode)
+inline struct open_how build_open_how(int flags, umode_t mode)
 {
 	struct open_how how = {
 		.flags = flags & VALID_OPEN_FLAGS,
@@ -974,8 +974,7 @@ static inline struct open_how build_open_how(int flags, umode_t mode)
 	return how;
 }
 
-static inline int build_open_flags(const struct open_how *how,
-				   struct open_flags *op)
+inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 {
 	int flags = how->flags;
 	int lookup_flags = 0;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 6220642fe113..9fc47c2e078d 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -24,7 +24,7 @@
 
 static int ovl_ccup_set(const char *buf, const struct kernel_param *param)
 {
-	pr_warn("overlayfs: \"check_copy_up\" module option is obsolete\n");
+	pr_warn("\"check_copy_up\" module option is obsolete\n");
 	return 0;
 }
 
@@ -123,6 +123,9 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 	loff_t old_pos = 0;
 	loff_t new_pos = 0;
 	loff_t cloned;
+	loff_t data_pos = -1;
+	loff_t hole_len;
+	bool skip_hole = false;
 	int error = 0;
 
 	if (len == 0)
@@ -144,7 +147,11 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 		goto out;
 	/* Couldn't clone, so now we try to copy the data */
 
-	/* FIXME: copy up sparse files efficiently */
+	/* Check if lower fs supports seek operation */
+	if (old_file->f_mode & FMODE_LSEEK &&
+	    old_file->f_op->llseek)
+		skip_hole = true;
+
 	while (len) {
 		size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
 		long bytes;
@@ -157,6 +164,36 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
 			break;
 		}
 
+		/*
+		 * Fill zero for hole will cost unnecessary disk space
+		 * and meanwhile slow down the copy-up speed, so we do
+		 * an optimization for hole during copy-up, it relies
+		 * on SEEK_DATA implementation in lower fs so if lower
+		 * fs does not support it, copy-up will behave as before.
+		 *
+		 * Detail logic of hole detection as below:
+		 * When we detect next data position is larger than current
+		 * position we will skip that hole, otherwise we copy
+		 * data in the size of OVL_COPY_UP_CHUNK_SIZE. Actually,
+		 * it may not recognize all kind of holes and sometimes
+		 * only skips partial of hole area. However, it will be
+		 * enough for most of the use cases.
+		 */
+
+		if (skip_hole && data_pos < old_pos) {
+			data_pos = vfs_llseek(old_file, old_pos, SEEK_DATA);
+			if (data_pos > old_pos) {
+				hole_len = data_pos - old_pos;
+				len -= hole_len;
+				old_pos = new_pos = data_pos;
+				continue;
+			} else if (data_pos == -ENXIO) {
+				break;
+			} else if (data_pos < 0) {
+				skip_hole = false;
+			}
+		}
+
 		bytes = do_splice_direct(old_file, &old_pos,
 					 new_file, &new_pos,
 					 this_len, SPLICE_F_MOVE);
@@ -480,7 +517,7 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 	}
 
 	inode_lock(temp->d_inode);
-	if (c->metacopy)
+	if (S_ISREG(c->stat.mode))
 		err = ovl_set_size(temp, &c->stat);
 	if (!err)
 		err = ovl_set_attr(temp, &c->stat);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 29abdb1d3b5c..8e57d5372b8f 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -35,7 +35,7 @@ int ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
 	dput(wdentry);
 
 	if (err) {
-		pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n",
+		pr_err("cleanup of '%pd2' failed (%i)\n",
 		       wdentry, err);
 	}
 
@@ -53,7 +53,7 @@ static struct dentry *ovl_lookup_temp(struct dentry *workdir)
 
 	temp = lookup_one_len(name, workdir, strlen(name));
 	if (!IS_ERR(temp) && temp->d_inode) {
-		pr_err("overlayfs: workdir/%s already exists\n", name);
+		pr_err("workdir/%s already exists\n", name);
 		dput(temp);
 		temp = ERR_PTR(-EIO);
 	}
@@ -134,7 +134,7 @@ static int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry,
 	d = lookup_one_len(dentry->d_name.name, dentry->d_parent,
 			   dentry->d_name.len);
 	if (IS_ERR(d)) {
-		pr_warn("overlayfs: failed lookup after mkdir (%pd2, err=%i).\n",
+		pr_warn("failed lookup after mkdir (%pd2, err=%i).\n",
 			dentry, err);
 		return PTR_ERR(d);
 	}
@@ -267,7 +267,7 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode,
 
 	d_instantiate(dentry, inode);
 	if (inode != oip.newinode) {
-		pr_warn_ratelimited("overlayfs: newly created inode found in cache (%pd2)\n",
+		pr_warn_ratelimited("newly created inode found in cache (%pd2)\n",
 				    dentry);
 	}
 
@@ -1009,7 +1009,7 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir)
 		spin_unlock(&dentry->d_lock);
 	} else {
 		kfree(redirect);
-		pr_warn_ratelimited("overlayfs: failed to set redirect (%i)\n",
+		pr_warn_ratelimited("failed to set redirect (%i)\n",
 				    err);
 		/* Fall back to userspace copy-up */
 		err = -EXDEV;
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 70e55588aedc..6f54d70cef27 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -30,7 +30,7 @@ static int ovl_encode_maybe_copy_up(struct dentry *dentry)
 	}
 
 	if (err) {
-		pr_warn_ratelimited("overlayfs: failed to copy up on encode (%pd2, err=%i)\n",
+		pr_warn_ratelimited("failed to copy up on encode (%pd2, err=%i)\n",
 				    dentry, err);
 	}
 
@@ -244,7 +244,7 @@ out:
 	return err;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to encode file handle (%pd2, err=%i, buflen=%d, len=%d, type=%d)\n",
+	pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i, buflen=%d, len=%d, type=%d)\n",
 			    dentry, err, buflen, fh ? (int)fh->fb.len : 0,
 			    fh ? fh->fb.type : 0);
 	goto out;
@@ -358,7 +358,7 @@ static struct dentry *ovl_dentry_real_at(struct dentry *dentry, int idx)
  */
 static struct dentry *ovl_lookup_real_one(struct dentry *connected,
 					  struct dentry *real,
-					  struct ovl_layer *layer)
+					  const struct ovl_layer *layer)
 {
 	struct inode *dir = d_inode(connected);
 	struct dentry *this, *parent = NULL;
@@ -406,7 +406,7 @@ out:
 	return this;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to lookup one by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
+	pr_warn_ratelimited("failed to lookup one by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
 			    real, layer->idx, connected, err);
 	this = ERR_PTR(err);
 	goto out;
@@ -414,17 +414,16 @@ fail:
 
 static struct dentry *ovl_lookup_real(struct super_block *sb,
 				      struct dentry *real,
-				      struct ovl_layer *layer);
+				      const struct ovl_layer *layer);
 
 /*
  * Lookup an indexed or hashed overlay dentry by real inode.
  */
 static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 					    struct dentry *real,
-					    struct ovl_layer *layer)
+					    const struct ovl_layer *layer)
 {
 	struct ovl_fs *ofs = sb->s_fs_info;
-	struct ovl_layer upper_layer = { .mnt = ofs->upper_mnt };
 	struct dentry *index = NULL;
 	struct dentry *this = NULL;
 	struct inode *inode;
@@ -466,7 +465,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
 		 * recursive call walks back from indexed upper to the topmost
 		 * connected/hashed upper parent (or up to root).
 		 */
-		this = ovl_lookup_real(sb, upper, &upper_layer);
+		this = ovl_lookup_real(sb, upper, &ofs->layers[0]);
 		dput(upper);
 	}
 
@@ -487,7 +486,7 @@ static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
  */
 static struct dentry *ovl_lookup_real_ancestor(struct super_block *sb,
 					       struct dentry *real,
-					       struct ovl_layer *layer)
+					       const struct ovl_layer *layer)
 {
 	struct dentry *next, *parent = NULL;
 	struct dentry *ancestor = ERR_PTR(-EIO);
@@ -540,7 +539,7 @@ static struct dentry *ovl_lookup_real_ancestor(struct super_block *sb,
  */
 static struct dentry *ovl_lookup_real(struct super_block *sb,
 				      struct dentry *real,
-				      struct ovl_layer *layer)
+				      const struct ovl_layer *layer)
 {
 	struct dentry *connected;
 	int err = 0;
@@ -631,7 +630,7 @@ static struct dentry *ovl_lookup_real(struct super_block *sb,
 	return connected;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to lookup by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
+	pr_warn_ratelimited("failed to lookup by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
 			    real, layer->idx, connected, err);
 	dput(connected);
 	return ERR_PTR(err);
@@ -646,8 +645,7 @@ static struct dentry *ovl_get_dentry(struct super_block *sb,
 				     struct dentry *index)
 {
 	struct ovl_fs *ofs = sb->s_fs_info;
-	struct ovl_layer upper_layer = { .mnt = ofs->upper_mnt };
-	struct ovl_layer *layer = upper ? &upper_layer : lowerpath->layer;
+	const struct ovl_layer *layer = upper ? &ofs->layers[0] : lowerpath->layer;
 	struct dentry *real = upper ?: (index ?: lowerpath->dentry);
 
 	/*
@@ -822,7 +820,7 @@ out:
 	return dentry;
 
 out_err:
-	pr_warn_ratelimited("overlayfs: failed to decode file handle (len=%d, type=%d, flags=%x, err=%i)\n",
+	pr_warn_ratelimited("failed to decode file handle (len=%d, type=%d, flags=%x, err=%i)\n",
 			    fh_len, fh_type, flags, err);
 	dentry = ERR_PTR(err);
 	goto out;
@@ -831,7 +829,7 @@ out_err:
 static struct dentry *ovl_fh_to_parent(struct super_block *sb, struct fid *fid,
 				       int fh_len, int fh_type)
 {
-	pr_warn_ratelimited("overlayfs: connectable file handles not supported; use 'no_subtree_check' exportfs option.\n");
+	pr_warn_ratelimited("connectable file handles not supported; use 'no_subtree_check' exportfs option.\n");
 	return ERR_PTR(-EACCES);
 }
 
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index e235a635d9ec..a5317216de73 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -9,8 +9,19 @@
 #include <linux/xattr.h>
 #include <linux/uio.h>
 #include <linux/uaccess.h>
+#include <linux/splice.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
 #include "overlayfs.h"
 
+struct ovl_aio_req {
+	struct kiocb iocb;
+	struct kiocb *orig_iocb;
+	struct fd fd;
+};
+
+static struct kmem_cache *ovl_aio_request_cachep;
+
 static char ovl_whatisit(struct inode *inode, struct inode *realinode)
 {
 	if (realinode != ovl_inode_upper(inode))
@@ -146,7 +157,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 	struct inode *inode = file_inode(file);
 	struct fd real;
 	const struct cred *old_cred;
-	ssize_t ret;
+	loff_t ret;
 
 	/*
 	 * The two special cases below do not need to involve real fs,
@@ -171,7 +182,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 	 * limitations that are more strict than ->s_maxbytes for specific
 	 * files, so we use the real file to perform seeks.
 	 */
-	inode_lock(inode);
+	ovl_inode_lock(inode);
 	real.file->f_pos = file->f_pos;
 
 	old_cred = ovl_override_creds(inode->i_sb);
@@ -179,7 +190,7 @@ static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 	revert_creds(old_cred);
 
 	file->f_pos = real.file->f_pos;
-	inode_unlock(inode);
+	ovl_inode_unlock(inode);
 
 	fdput(real);
 
@@ -225,6 +236,33 @@ static rwf_t ovl_iocb_to_rwf(struct kiocb *iocb)
 	return flags;
 }
 
+static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
+{
+	struct kiocb *iocb = &aio_req->iocb;
+	struct kiocb *orig_iocb = aio_req->orig_iocb;
+
+	if (iocb->ki_flags & IOCB_WRITE) {
+		struct inode *inode = file_inode(orig_iocb->ki_filp);
+
+		file_end_write(iocb->ki_filp);
+		ovl_copyattr(ovl_inode_real(inode), inode);
+	}
+
+	orig_iocb->ki_pos = iocb->ki_pos;
+	fdput(aio_req->fd);
+	kmem_cache_free(ovl_aio_request_cachep, aio_req);
+}
+
+static void ovl_aio_rw_complete(struct kiocb *iocb, long res, long res2)
+{
+	struct ovl_aio_req *aio_req = container_of(iocb,
+						   struct ovl_aio_req, iocb);
+	struct kiocb *orig_iocb = aio_req->orig_iocb;
+
+	ovl_aio_cleanup_handler(aio_req);
+	orig_iocb->ki_complete(orig_iocb, res, res2);
+}
+
 static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
@@ -240,10 +278,28 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		return ret;
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	ret = vfs_iter_read(real.file, iter, &iocb->ki_pos,
-			    ovl_iocb_to_rwf(iocb));
+	if (is_sync_kiocb(iocb)) {
+		ret = vfs_iter_read(real.file, iter, &iocb->ki_pos,
+				    ovl_iocb_to_rwf(iocb));
+	} else {
+		struct ovl_aio_req *aio_req;
+
+		ret = -ENOMEM;
+		aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
+		if (!aio_req)
+			goto out;
+
+		aio_req->fd = real;
+		real.flags = 0;
+		aio_req->orig_iocb = iocb;
+		kiocb_clone(&aio_req->iocb, iocb, real.file);
+		aio_req->iocb.ki_complete = ovl_aio_rw_complete;
+		ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);
+		if (ret != -EIOCBQUEUED)
+			ovl_aio_cleanup_handler(aio_req);
+	}
+out:
 	revert_creds(old_cred);
-
 	ovl_file_accessed(file);
 
 	fdput(real);
@@ -274,15 +330,33 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 		goto out_unlock;
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
-	file_start_write(real.file);
-	ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
-			     ovl_iocb_to_rwf(iocb));
-	file_end_write(real.file);
+	if (is_sync_kiocb(iocb)) {
+		file_start_write(real.file);
+		ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
+				     ovl_iocb_to_rwf(iocb));
+		file_end_write(real.file);
+		/* Update size */
+		ovl_copyattr(ovl_inode_real(inode), inode);
+	} else {
+		struct ovl_aio_req *aio_req;
+
+		ret = -ENOMEM;
+		aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
+		if (!aio_req)
+			goto out;
+
+		file_start_write(real.file);
+		aio_req->fd = real;
+		real.flags = 0;
+		aio_req->orig_iocb = iocb;
+		kiocb_clone(&aio_req->iocb, iocb, real.file);
+		aio_req->iocb.ki_complete = ovl_aio_rw_complete;
+		ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter);
+		if (ret != -EIOCBQUEUED)
+			ovl_aio_cleanup_handler(aio_req);
+	}
+out:
 	revert_creds(old_cred);
-
-	/* Update size */
-	ovl_copyattr(ovl_inode_real(inode), inode);
-
 	fdput(real);
 
 out_unlock:
@@ -291,6 +365,48 @@ out_unlock:
 	return ret;
 }
 
+static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
+			 struct pipe_inode_info *pipe, size_t len,
+			 unsigned int flags)
+{
+	ssize_t ret;
+	struct fd real;
+	const struct cred *old_cred;
+
+	ret = ovl_real_fdget(in, &real);
+	if (ret)
+		return ret;
+
+	old_cred = ovl_override_creds(file_inode(in)->i_sb);
+	ret = generic_file_splice_read(real.file, ppos, pipe, len, flags);
+	revert_creds(old_cred);
+
+	ovl_file_accessed(in);
+	fdput(real);
+	return ret;
+}
+
+static ssize_t
+ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
+			  loff_t *ppos, size_t len, unsigned int flags)
+{
+	struct fd real;
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	ret = ovl_real_fdget(out, &real);
+	if (ret)
+		return ret;
+
+	old_cred = ovl_override_creds(file_inode(out)->i_sb);
+	ret = iter_file_splice_write(pipe, real.file, ppos, len, flags);
+	revert_creds(old_cred);
+
+	ovl_file_accessed(out);
+	fdput(real);
+	return ret;
+}
+
 static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct fd real;
@@ -647,7 +763,25 @@ const struct file_operations ovl_file_operations = {
 	.fadvise	= ovl_fadvise,
 	.unlocked_ioctl	= ovl_ioctl,
 	.compat_ioctl	= ovl_compat_ioctl,
+	.splice_read    = ovl_splice_read,
+	.splice_write   = ovl_splice_write,
 
 	.copy_file_range	= ovl_copy_file_range,
 	.remap_file_range	= ovl_remap_file_range,
 };
+
+int __init ovl_aio_request_cache_init(void)
+{
+	ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req",
+						   sizeof(struct ovl_aio_req),
+						   0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!ovl_aio_request_cachep)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void ovl_aio_request_cache_destroy(void)
+{
+	kmem_cache_destroy(ovl_aio_request_cachep);
+}
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index b045cf1826fc..79e8994e3bc1 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -75,10 +75,9 @@ out:
 	return err;
 }
 
-static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat,
-			   struct ovl_layer *lower_layer)
+static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat, int fsid)
 {
-	bool samefs = ovl_same_sb(dentry->d_sb);
+	bool samefs = ovl_same_fs(dentry->d_sb);
 	unsigned int xinobits = ovl_xino_bits(dentry->d_sb);
 
 	if (samefs) {
@@ -100,12 +99,10 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat,
 		 * persistent for a given layer configuration.
 		 */
 		if (stat->ino >> shift) {
-			pr_warn_ratelimited("overlayfs: inode number too big (%pd2, ino=%llu, xinobits=%d)\n",
+			pr_warn_ratelimited("inode number too big (%pd2, ino=%llu, xinobits=%d)\n",
 					    dentry, stat->ino, xinobits);
 		} else {
-			if (lower_layer)
-				stat->ino |= ((u64)lower_layer->fsid) << shift;
-
+			stat->ino |= ((u64)fsid) << shift;
 			stat->dev = dentry->d_sb->s_dev;
 			return 0;
 		}
@@ -124,15 +121,14 @@ static int ovl_map_dev_ino(struct dentry *dentry, struct kstat *stat,
 		 */
 		stat->dev = dentry->d_sb->s_dev;
 		stat->ino = dentry->d_inode->i_ino;
-	} else if (lower_layer && lower_layer->fsid) {
+	} else {
 		/*
 		 * For non-samefs setup, if we cannot map all layers st_ino
 		 * to a unified address space, we need to make sure that st_dev
-		 * is unique per lower fs. Upper layer uses real st_dev and
-		 * lower layers use the unique anonymous bdev assigned to the
-		 * lower fs.
+		 * is unique per underlying fs, so we use the unique anonymous
+		 * bdev assigned to the underlying fs.
 		 */
-		stat->dev = lower_layer->fs->pseudo_dev;
+		stat->dev = OVL_FS(dentry->d_sb)->fs[fsid].pseudo_dev;
 	}
 
 	return 0;
@@ -146,8 +142,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 	struct path realpath;
 	const struct cred *old_cred;
 	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
-	bool samefs = ovl_same_sb(dentry->d_sb);
-	struct ovl_layer *lower_layer = NULL;
+	int fsid = 0;
 	int err;
 	bool metacopy_blocks = false;
 
@@ -168,9 +163,9 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 	 * If lower filesystem supports NFS file handles, this also guaranties
 	 * persistent st_ino across mount cycle.
 	 */
-	if (!is_dir || samefs || ovl_xino_bits(dentry->d_sb)) {
+	if (!is_dir || ovl_same_dev(dentry->d_sb)) {
 		if (!OVL_TYPE_UPPER(type)) {
-			lower_layer = ovl_layer_lower(dentry);
+			fsid = ovl_layer_lower(dentry)->fsid;
 		} else if (OVL_TYPE_ORIGIN(type)) {
 			struct kstat lowerstat;
 			u32 lowermask = STATX_INO | STATX_BLOCKS |
@@ -200,14 +195,8 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 			if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) ||
 			    (!ovl_verify_lower(dentry->d_sb) &&
 			     (is_dir || lowerstat.nlink == 1))) {
-				lower_layer = ovl_layer_lower(dentry);
-				/*
-				 * Cannot use origin st_dev;st_ino because
-				 * origin inode content may differ from overlay
-				 * inode content.
-				 */
-				if (samefs || lower_layer->fsid)
-					stat->ino = lowerstat.ino;
+				fsid = ovl_layer_lower(dentry)->fsid;
+				stat->ino = lowerstat.ino;
 			}
 
 			/*
@@ -241,7 +230,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
 		}
 	}
 
-	err = ovl_map_dev_ino(dentry, stat, lower_layer);
+	err = ovl_map_dev_ino(dentry, stat, fsid);
 	if (err)
 		goto out;
 
@@ -527,6 +516,27 @@ static const struct address_space_operations ovl_aops = {
  * [...] &ovl_i_mutex_dir_key[depth]   (stack_depth=2)
  * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
  * [...] &type->i_mutex_dir_key        (stack_depth=0)
+ *
+ * Locking order w.r.t ovl_want_write() is important for nested overlayfs.
+ *
+ * This chain is valid:
+ * - inode->i_rwsem			(inode_lock[2])
+ * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
+ * - OVL_I(inode)->lock			(ovl_inode_lock[2])
+ * - OVL_I(lowerinode)->lock		(ovl_inode_lock[1])
+ *
+ * And this chain is valid:
+ * - inode->i_rwsem			(inode_lock[2])
+ * - OVL_I(inode)->lock			(ovl_inode_lock[2])
+ * - lowerinode->i_rwsem		(inode_lock[1])
+ * - OVL_I(lowerinode)->lock		(ovl_inode_lock[1])
+ *
+ * But lowerinode->i_rwsem SHOULD NOT be acquired while ovl_want_write() is
+ * held, because it is in reverse order of the non-nested case using the same
+ * upper fs:
+ * - inode->i_rwsem			(inode_lock[1])
+ * - upper_mnt->mnt_sb->s_writers	(ovl_want_write[0])
+ * - OVL_I(inode)->lock			(ovl_inode_lock[1])
  */
 #define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH
 
@@ -565,7 +575,7 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev,
 	 * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real
 	 * upper inode i_ino on ovl_inode_init() or ovl_inode_update().
 	 */
-	if (ovl_same_sb(inode->i_sb) || xinobits) {
+	if (ovl_same_dev(inode->i_sb)) {
 		inode->i_ino = ino;
 		if (xinobits && fsid && !(ino >> (64 - xinobits)))
 			inode->i_ino |= (unsigned long)fsid << (64 - xinobits);
@@ -698,7 +708,7 @@ unsigned int ovl_get_nlink(struct dentry *lowerdentry,
 	return nlink;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n",
+	pr_warn_ratelimited("failed to get index nlink (%pd2, err=%i)\n",
 			    upperdentry, err);
 	return fallback;
 }
@@ -969,7 +979,7 @@ out:
 	return inode;
 
 out_err:
-	pr_warn_ratelimited("overlayfs: failed to get inode (%i)\n", err);
+	pr_warn_ratelimited("failed to get inode (%i)\n", err);
 	inode = ERR_PTR(err);
 	goto out;
 }
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 76ff66339173..ed9e129fae04 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -141,10 +141,10 @@ out:
 	return NULL;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res);
+	pr_warn_ratelimited("failed to get origin (%i)\n", res);
 	goto out;
 invalid:
-	pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh);
+	pr_warn_ratelimited("invalid origin (%*phN)\n", res, fh);
 	goto out;
 }
 
@@ -322,16 +322,16 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected,
 	struct dentry *origin = NULL;
 	int i;
 
-	for (i = 0; i < ofs->numlower; i++) {
+	for (i = 1; i < ofs->numlayer; i++) {
 		/*
 		 * If lower fs uuid is not unique among lower fs we cannot match
 		 * fh->uuid to layer.
 		 */
-		if (ofs->lower_layers[i].fsid &&
-		    ofs->lower_layers[i].fs->bad_uuid)
+		if (ofs->layers[i].fsid &&
+		    ofs->layers[i].fs->bad_uuid)
 			continue;
 
-		origin = ovl_decode_real_fh(fh, ofs->lower_layers[i].mnt,
+		origin = ovl_decode_real_fh(fh, ofs->layers[i].mnt,
 					    connected);
 		if (origin)
 			break;
@@ -354,13 +354,13 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected,
 	}
 	**stackp = (struct ovl_path){
 		.dentry = origin,
-		.layer = &ofs->lower_layers[i]
+		.layer = &ofs->layers[i]
 	};
 
 	return 0;
 
 invalid:
-	pr_warn_ratelimited("overlayfs: invalid origin (%pd2, ftype=%x, origin ftype=%x).\n",
+	pr_warn_ratelimited("invalid origin (%pd2, ftype=%x, origin ftype=%x).\n",
 			    upperdentry, d_inode(upperdentry)->i_mode & S_IFMT,
 			    d_inode(origin)->i_mode & S_IFMT);
 	dput(origin);
@@ -449,7 +449,7 @@ out:
 
 fail:
 	inode = d_inode(real);
-	pr_warn_ratelimited("overlayfs: failed to verify %s (%pd2, ino=%lu, err=%i)\n",
+	pr_warn_ratelimited("failed to verify %s (%pd2, ino=%lu, err=%i)\n",
 			    is_upper ? "upper" : "origin", real,
 			    inode ? inode->i_ino : 0, err);
 	goto out;
@@ -475,7 +475,7 @@ struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index)
 		return upper ?: ERR_PTR(-ESTALE);
 
 	if (!d_is_dir(upper)) {
-		pr_warn_ratelimited("overlayfs: invalid index upper (%pd2, upper=%pd2).\n",
+		pr_warn_ratelimited("invalid index upper (%pd2, upper=%pd2).\n",
 				    index, upper);
 		dput(upper);
 		return ERR_PTR(-EIO);
@@ -589,12 +589,12 @@ out:
 	return err;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n",
+	pr_warn_ratelimited("failed to verify index (%pd2, ftype=%x, err=%i)\n",
 			    index, d_inode(index)->i_mode & S_IFMT, err);
 	goto out;
 
 orphan:
-	pr_warn_ratelimited("overlayfs: orphan index entry (%pd2, ftype=%x, nlink=%u)\n",
+	pr_warn_ratelimited("orphan index entry (%pd2, ftype=%x, nlink=%u)\n",
 			    index, d_inode(index)->i_mode & S_IFMT,
 			    d_inode(index)->i_nlink);
 	err = -ENOENT;
@@ -696,7 +696,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 			index = NULL;
 			goto out;
 		}
-		pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n"
+		pr_warn_ratelimited("failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n"
 				    "overlayfs: mount with '-o index=off' to disable inodes index.\n",
 				    d_inode(origin)->i_ino, name.len, name.name,
 				    err);
@@ -723,13 +723,13 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 		 * unlinked, which means that finding a lower origin on lookup
 		 * whose index is a whiteout should be treated as an error.
 		 */
-		pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n",
+		pr_warn_ratelimited("bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n",
 				    index, d_inode(index)->i_mode & S_IFMT,
 				    d_inode(origin)->i_mode & S_IFMT);
 		goto fail;
 	} else if (is_dir && verify) {
 		if (!upper) {
-			pr_warn_ratelimited("overlayfs: suspected uncovered redirected dir found (origin=%pd2, index=%pd2).\n",
+			pr_warn_ratelimited("suspected uncovered redirected dir found (origin=%pd2, index=%pd2).\n",
 					    origin, index);
 			goto fail;
 		}
@@ -738,7 +738,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
 		err = ovl_verify_upper(index, upper, false);
 		if (err) {
 			if (err == -ESTALE) {
-				pr_warn_ratelimited("overlayfs: suspected multiply redirected dir found (upper=%pd2, origin=%pd2, index=%pd2).\n",
+				pr_warn_ratelimited("suspected multiply redirected dir found (upper=%pd2, origin=%pd2, index=%pd2).\n",
 						    upper, origin, index);
 			}
 			goto fail;
@@ -885,7 +885,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 	if (!d.stop && poe->numlower) {
 		err = -ENOMEM;
-		stack = kcalloc(ofs->numlower, sizeof(struct ovl_path),
+		stack = kcalloc(ofs->numlayer - 1, sizeof(struct ovl_path),
 				GFP_KERNEL);
 		if (!stack)
 			goto out_put_upper;
@@ -967,7 +967,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		 */
 		err = -EPERM;
 		if (d.redirect && !ofs->config.redirect_follow) {
-			pr_warn_ratelimited("overlayfs: refusing to follow redirect for (%pd2)\n",
+			pr_warn_ratelimited("refusing to follow redirect for (%pd2)\n",
 					    dentry);
 			goto out_put;
 		}
@@ -994,7 +994,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 
 		err = -EPERM;
 		if (!ofs->config.metacopy) {
-			pr_warn_ratelimited("overlay: refusing to follow metacopy origin for (%pd2)\n",
+			pr_warn_ratelimited("refusing to follow metacopy origin for (%pd2)\n",
 					    dentry);
 			goto out_put;
 		}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index f283b1d69a9e..3623d28aa4fa 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -9,6 +9,9 @@
 #include <linux/fs.h>
 #include "ovl_entry.h"
 
+#undef pr_fmt
+#define pr_fmt(fmt) "overlayfs: " fmt
+
 enum ovl_path_type {
 	__OVL_PATH_UPPER	= (1 << 0),
 	__OVL_PATH_MERGE	= (1 << 1),
@@ -221,7 +224,6 @@ int ovl_want_write(struct dentry *dentry);
 void ovl_drop_write(struct dentry *dentry);
 struct dentry *ovl_workdir(struct dentry *dentry);
 const struct cred *ovl_override_creds(struct super_block *sb);
-struct super_block *ovl_same_sb(struct super_block *sb);
 int ovl_can_decode_fh(struct super_block *sb);
 struct dentry *ovl_indexdir(struct super_block *sb);
 bool ovl_index_all(struct super_block *sb);
@@ -237,7 +239,7 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_lowerdata(struct dentry *dentry);
-struct ovl_layer *ovl_layer_lower(struct dentry *dentry);
+const struct ovl_layer *ovl_layer_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
 struct dentry *ovl_i_dentry_upper(struct inode *inode);
 struct inode *ovl_inode_upper(struct inode *inode);
@@ -299,11 +301,21 @@ static inline bool ovl_is_impuredir(struct dentry *dentry)
 	return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE);
 }
 
-static inline unsigned int ovl_xino_bits(struct super_block *sb)
+/* All layers on same fs? */
+static inline bool ovl_same_fs(struct super_block *sb)
+{
+	return OVL_FS(sb)->xino_mode == 0;
+}
+
+/* All overlay inodes have same st_dev? */
+static inline bool ovl_same_dev(struct super_block *sb)
 {
-	struct ovl_fs *ofs = sb->s_fs_info;
+	return OVL_FS(sb)->xino_mode >= 0;
+}
 
-	return ofs->xino_bits;
+static inline unsigned int ovl_xino_bits(struct super_block *sb)
+{
+	return ovl_same_dev(sb) ? OVL_FS(sb)->xino_mode : 0;
 }
 
 static inline int ovl_inode_lock(struct inode *inode)
@@ -438,6 +450,8 @@ struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr);
 
 /* file.c */
 extern const struct file_operations ovl_file_operations;
+int __init ovl_aio_request_cache_init(void);
+void ovl_aio_request_cache_destroy(void);
 
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 28348c44ea5b..89015ea822e7 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -24,6 +24,8 @@ struct ovl_sb {
 	dev_t pseudo_dev;
 	/* Unusable (conflicting) uuid */
 	bool bad_uuid;
+	/* Used as a lower layer (but maybe also as upper) */
+	bool is_lower;
 };
 
 struct ovl_layer {
@@ -38,18 +40,18 @@ struct ovl_layer {
 };
 
 struct ovl_path {
-	struct ovl_layer *layer;
+	const struct ovl_layer *layer;
 	struct dentry *dentry;
 };
 
 /* private information held for overlayfs's superblock */
 struct ovl_fs {
 	struct vfsmount *upper_mnt;
-	unsigned int numlower;
-	/* Number of unique lower sb that differ from upper sb */
-	unsigned int numlowerfs;
-	struct ovl_layer *lower_layers;
-	struct ovl_sb *lower_fs;
+	unsigned int numlayer;
+	/* Number of unique fs among layers including upper fs */
+	unsigned int numfs;
+	const struct ovl_layer *layers;
+	struct ovl_sb *fs;
 	/* workbasedir is the path at workdir= mount option */
 	struct dentry *workbasedir;
 	/* workdir is the 'work' directory under workbasedir */
@@ -71,10 +73,15 @@ struct ovl_fs {
 	struct inode *workbasedir_trap;
 	struct inode *workdir_trap;
 	struct inode *indexdir_trap;
-	/* Inode numbers in all layers do not use the high xino_bits */
-	unsigned int xino_bits;
+	/* -1: disabled, 0: same fs, 1..32: number of unused ino bits */
+	int xino_mode;
 };
 
+static inline struct ovl_fs *OVL_FS(struct super_block *sb)
+{
+	return (struct ovl_fs *)sb->s_fs_info;
+}
+
 /* private information held for every overlayfs dentry */
 struct ovl_entry {
 	union {
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 47a91c9733a5..40ac9ce2465a 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -441,7 +441,7 @@ static u64 ovl_remap_lower_ino(u64 ino, int xinobits, int fsid,
 			       const char *name, int namelen)
 {
 	if (ino >> (64 - xinobits)) {
-		pr_warn_ratelimited("overlayfs: d_ino too big (%.*s, ino=%llu, xinobits=%d)\n",
+		pr_warn_ratelimited("d_ino too big (%.*s, ino=%llu, xinobits=%d)\n",
 				    namelen, name, ino, xinobits);
 		return ino;
 	}
@@ -469,7 +469,7 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p)
 	int xinobits = ovl_xino_bits(dir->d_sb);
 	int err = 0;
 
-	if (!ovl_same_sb(dir->d_sb) && !xinobits)
+	if (!ovl_same_dev(dir->d_sb))
 		goto out;
 
 	if (p->name[0] == '.') {
@@ -504,7 +504,13 @@ get:
 		if (err)
 			goto fail;
 
-		WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev);
+		/*
+		 * Directory inode is always on overlay st_dev.
+		 * Non-dir with ovl_same_dev() could be on pseudo st_dev in case
+		 * of xino bits overflow.
+		 */
+		WARN_ON_ONCE(S_ISDIR(stat.mode) &&
+			     dir->d_sb->s_dev != stat.dev);
 		ino = stat.ino;
 	} else if (xinobits && !OVL_TYPE_UPPER(type)) {
 		ino = ovl_remap_lower_ino(ino, xinobits,
@@ -518,7 +524,7 @@ out:
 	return err;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to look up (%s) for ino (%i)\n",
+	pr_warn_ratelimited("failed to look up (%s) for ino (%i)\n",
 			    p->name, err);
 	goto out;
 }
@@ -685,7 +691,7 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
 	int err;
 	struct ovl_dir_file *od = file->private_data;
 	struct dentry *dir = file->f_path.dentry;
-	struct ovl_layer *lower_layer = ovl_layer_lower(dir);
+	const struct ovl_layer *lower_layer = ovl_layer_lower(dir);
 	struct ovl_readdir_translate rdt = {
 		.ctx.actor = ovl_fill_real,
 		.orig_ctx = ctx,
@@ -738,7 +744,7 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 		 * entries.
 		 */
 		if (ovl_xino_bits(dentry->d_sb) ||
-		    (ovl_same_sb(dentry->d_sb) &&
+		    (ovl_same_fs(dentry->d_sb) &&
 		     (ovl_is_impure_dir(file) ||
 		      OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent))))) {
 			return ovl_iterate_real(file, ctx);
@@ -965,7 +971,7 @@ void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
 
 		dentry = lookup_one_len(p->name, upper, p->len);
 		if (IS_ERR(dentry)) {
-			pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n",
+			pr_err("lookup '%s/%.*s' failed (%i)\n",
 			       upper->d_name.name, p->len, p->name,
 			       (int) PTR_ERR(dentry));
 			continue;
@@ -1147,6 +1153,6 @@ next:
 out:
 	ovl_cache_free(&list);
 	if (err)
-		pr_err("overlayfs: failed index dir cleanup (%i)\n", err);
+		pr_err("failed index dir cleanup (%i)\n", err);
 	return err;
 }
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 7621ff176d15..319fe0d355b0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -224,14 +224,14 @@ static void ovl_free_fs(struct ovl_fs *ofs)
 	if (ofs->upperdir_locked)
 		ovl_inuse_unlock(ofs->upper_mnt->mnt_root);
 	mntput(ofs->upper_mnt);
-	for (i = 0; i < ofs->numlower; i++) {
-		iput(ofs->lower_layers[i].trap);
-		mntput(ofs->lower_layers[i].mnt);
+	for (i = 1; i < ofs->numlayer; i++) {
+		iput(ofs->layers[i].trap);
+		mntput(ofs->layers[i].mnt);
 	}
-	for (i = 0; i < ofs->numlowerfs; i++)
-		free_anon_bdev(ofs->lower_fs[i].pseudo_dev);
-	kfree(ofs->lower_layers);
-	kfree(ofs->lower_fs);
+	kfree(ofs->layers);
+	for (i = 0; i < ofs->numfs; i++)
+		free_anon_bdev(ofs->fs[i].pseudo_dev);
+	kfree(ofs->fs);
 
 	kfree(ofs->config.lowerdir);
 	kfree(ofs->config.upperdir);
@@ -358,7 +358,7 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 	if (ofs->config.nfs_export != ovl_nfs_export_def)
 		seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
 						"on" : "off");
-	if (ofs->config.xino != ovl_xino_def())
+	if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(sb))
 		seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]);
 	if (ofs->config.metacopy != ovl_metacopy_def)
 		seq_printf(m, ",metacopy=%s",
@@ -462,7 +462,7 @@ static int ovl_parse_redirect_mode(struct ovl_config *config, const char *mode)
 		if (ovl_redirect_always_follow)
 			config->redirect_follow = true;
 	} else if (strcmp(mode, "nofollow") != 0) {
-		pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n",
+		pr_err("bad mount option \"redirect_dir=%s\"\n",
 		       mode);
 		return -EINVAL;
 	}
@@ -560,14 +560,15 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			break;
 
 		default:
-			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
+			pr_err("unrecognized mount option \"%s\" or missing value\n",
+					p);
 			return -EINVAL;
 		}
 	}
 
 	/* Workdir is useless in non-upper mount */
 	if (!config->upperdir && config->workdir) {
-		pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+		pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
 			config->workdir);
 		kfree(config->workdir);
 		config->workdir = NULL;
@@ -587,7 +588,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 	/* Resolve metacopy -> redirect_dir dependency */
 	if (config->metacopy && !config->redirect_dir) {
 		if (metacopy_opt && redirect_opt) {
-			pr_err("overlayfs: conflicting options: metacopy=on,redirect_dir=%s\n",
+			pr_err("conflicting options: metacopy=on,redirect_dir=%s\n",
 			       config->redirect_mode);
 			return -EINVAL;
 		}
@@ -596,7 +597,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			 * There was an explicit redirect_dir=... that resulted
 			 * in this conflict.
 			 */
-			pr_info("overlayfs: disabling metacopy due to redirect_dir=%s\n",
+			pr_info("disabling metacopy due to redirect_dir=%s\n",
 				config->redirect_mode);
 			config->metacopy = false;
 		} else {
@@ -692,7 +693,7 @@ out_unlock:
 out_dput:
 	dput(work);
 out_err:
-	pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
+	pr_warn("failed to create directory %s/%s (errno: %i); mounting read-only\n",
 		ofs->config.workdir, name, -err);
 	work = NULL;
 	goto out_unlock;
@@ -716,21 +717,21 @@ static int ovl_mount_dir_noesc(const char *name, struct path *path)
 	int err = -EINVAL;
 
 	if (!*name) {
-		pr_err("overlayfs: empty lowerdir\n");
+		pr_err("empty lowerdir\n");
 		goto out;
 	}
 	err = kern_path(name, LOOKUP_FOLLOW, path);
 	if (err) {
-		pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+		pr_err("failed to resolve '%s': %i\n", name, err);
 		goto out;
 	}
 	err = -EINVAL;
 	if (ovl_dentry_weird(path->dentry)) {
-		pr_err("overlayfs: filesystem on '%s' not supported\n", name);
+		pr_err("filesystem on '%s' not supported\n", name);
 		goto out_put;
 	}
 	if (!d_is_dir(path->dentry)) {
-		pr_err("overlayfs: '%s' not a directory\n", name);
+		pr_err("'%s' not a directory\n", name);
 		goto out_put;
 	}
 	return 0;
@@ -752,7 +753,7 @@ static int ovl_mount_dir(const char *name, struct path *path)
 
 		if (!err)
 			if (ovl_dentry_remote(path->dentry)) {
-				pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n",
+				pr_err("filesystem on '%s' not supported as upperdir\n",
 				       tmp);
 				path_put_init(path);
 				err = -EINVAL;
@@ -769,7 +770,7 @@ static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs,
 	int err = vfs_statfs(path, &statfs);
 
 	if (err)
-		pr_err("overlayfs: statfs failed on '%s'\n", name);
+		pr_err("statfs failed on '%s'\n", name);
 	else
 		ofs->namelen = max(ofs->namelen, statfs.f_namelen);
 
@@ -804,13 +805,13 @@ static int ovl_lower_dir(const char *name, struct path *path,
 	     (ofs->config.index && ofs->config.upperdir)) && !fh_type) {
 		ofs->config.index = false;
 		ofs->config.nfs_export = false;
-		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
+		pr_warn("fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
 			name);
 	}
 
 	/* Check if lower fs has 32bit inode numbers */
 	if (fh_type != FILEID_INO32_GEN)
-		ofs->xino_bits = 0;
+		ofs->xino_mode = -1;
 
 	return 0;
 
@@ -996,7 +997,7 @@ static int ovl_setup_trap(struct super_block *sb, struct dentry *dir,
 	err = PTR_ERR_OR_ZERO(trap);
 	if (err) {
 		if (err == -ELOOP)
-			pr_err("overlayfs: conflicting %s path\n", name);
+			pr_err("conflicting %s path\n", name);
 		return err;
 	}
 
@@ -1013,11 +1014,11 @@ static int ovl_setup_trap(struct super_block *sb, struct dentry *dir,
 static int ovl_report_in_use(struct ovl_fs *ofs, const char *name)
 {
 	if (ofs->config.index) {
-		pr_err("overlayfs: %s is in-use as upperdir/workdir of another mount, mount with '-o index=off' to override exclusive upperdir protection.\n",
+		pr_err("%s is in-use as upperdir/workdir of another mount, mount with '-o index=off' to override exclusive upperdir protection.\n",
 		       name);
 		return -EBUSY;
 	} else {
-		pr_warn("overlayfs: %s is in-use as upperdir/workdir of another mount, accessing files from both mounts will result in undefined behavior.\n",
+		pr_warn("%s is in-use as upperdir/workdir of another mount, accessing files from both mounts will result in undefined behavior.\n",
 			name);
 		return 0;
 	}
@@ -1035,7 +1036,7 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
 
 	/* Upper fs should not be r/o */
 	if (sb_rdonly(upperpath->mnt->mnt_sb)) {
-		pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+		pr_err("upper fs is r/o, try multi-lower layers mount\n");
 		err = -EINVAL;
 		goto out;
 	}
@@ -1052,7 +1053,7 @@ static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
 	upper_mnt = clone_private_mount(upperpath);
 	err = PTR_ERR(upper_mnt);
 	if (IS_ERR(upper_mnt)) {
-		pr_err("overlayfs: failed to clone upperpath\n");
+		pr_err("failed to clone upperpath\n");
 		goto out;
 	}
 
@@ -1108,7 +1109,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 	 * kernel upgrade. So warn instead of erroring out.
 	 */
 	if (!err)
-		pr_warn("overlayfs: upper fs needs to support d_type.\n");
+		pr_warn("upper fs needs to support d_type.\n");
 
 	/* Check if upper/work fs supports O_TMPFILE */
 	temp = ovl_do_tmpfile(ofs->workdir, S_IFREG | 0);
@@ -1116,7 +1117,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 	if (ofs->tmpfile)
 		dput(temp);
 	else
-		pr_warn("overlayfs: upper fs does not support tmpfile.\n");
+		pr_warn("upper fs does not support tmpfile.\n");
 
 	/*
 	 * Check if upper/work fs supports trusted.overlay.* xattr
@@ -1126,7 +1127,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 		ofs->noxattr = true;
 		ofs->config.index = false;
 		ofs->config.metacopy = false;
-		pr_warn("overlayfs: upper fs does not support xattr, falling back to index=off and metacopy=off.\n");
+		pr_warn("upper fs does not support xattr, falling back to index=off and metacopy=off.\n");
 		err = 0;
 	} else {
 		vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE);
@@ -1136,16 +1137,16 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
 	fh_type = ovl_can_decode_fh(ofs->workdir->d_sb);
 	if (ofs->config.index && !fh_type) {
 		ofs->config.index = false;
-		pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
+		pr_warn("upper fs does not support file handles, falling back to index=off.\n");
 	}
 
 	/* Check if upper fs has 32bit inode numbers */
 	if (fh_type != FILEID_INO32_GEN)
-		ofs->xino_bits = 0;
+		ofs->xino_mode = -1;
 
 	/* NFS export of r/w mount depends on index */
 	if (ofs->config.nfs_export && !ofs->config.index) {
-		pr_warn("overlayfs: NFS export requires \"index=on\", falling back to nfs_export=off.\n");
+		pr_warn("NFS export requires \"index=on\", falling back to nfs_export=off.\n");
 		ofs->config.nfs_export = false;
 	}
 out:
@@ -1165,11 +1166,11 @@ static int ovl_get_workdir(struct super_block *sb, struct ovl_fs *ofs,
 
 	err = -EINVAL;
 	if (upperpath->mnt != workpath.mnt) {
-		pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
+		pr_err("workdir and upperdir must reside under the same mount\n");
 		goto out;
 	}
 	if (!ovl_workdir_ok(workpath.dentry, upperpath->dentry)) {
-		pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+		pr_err("workdir and upperdir must be separate subtrees\n");
 		goto out;
 	}
 
@@ -1210,7 +1211,7 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 	err = ovl_verify_origin(upperpath->dentry, oe->lowerstack[0].dentry,
 				true);
 	if (err) {
-		pr_err("overlayfs: failed to verify upper root origin\n");
+		pr_err("failed to verify upper root origin\n");
 		goto out;
 	}
 
@@ -1233,18 +1234,18 @@ static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
 			err = ovl_verify_set_fh(ofs->indexdir, OVL_XATTR_ORIGIN,
 						upperpath->dentry, true, false);
 			if (err)
-				pr_err("overlayfs: failed to verify index dir 'origin' xattr\n");
+				pr_err("failed to verify index dir 'origin' xattr\n");
 		}
 		err = ovl_verify_upper(ofs->indexdir, upperpath->dentry, true);
 		if (err)
-			pr_err("overlayfs: failed to verify index dir 'upper' xattr\n");
+			pr_err("failed to verify index dir 'upper' xattr\n");
 
 		/* Cleanup bad/stale/orphan index entries */
 		if (!err)
 			err = ovl_indexdir_cleanup(ofs);
 	}
 	if (err || !ofs->indexdir)
-		pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
+		pr_warn("try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
 
 out:
 	mnt_drop_write(mnt);
@@ -1258,7 +1259,7 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
 	if (!ofs->config.nfs_export && !ofs->upper_mnt)
 		return true;
 
-	for (i = 0; i < ofs->numlowerfs; i++) {
+	for (i = 0; i < ofs->numfs; i++) {
 		/*
 		 * We use uuid to associate an overlay lower file handle with a
 		 * lower layer, so we can accept lower fs with null uuid as long
@@ -1266,8 +1267,9 @@ static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
 		 * if we detect multiple lower fs with the same uuid, we
 		 * disable lower file handle decoding on all of them.
 		 */
-		if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) {
-			ofs->lower_fs[i].bad_uuid = true;
+		if (ofs->fs[i].is_lower &&
+		    uuid_equal(&ofs->fs[i].sb->s_uuid, uuid)) {
+			ofs->fs[i].bad_uuid = true;
 			return false;
 		}
 	}
@@ -1283,13 +1285,9 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
 	int err;
 	bool bad_uuid = false;
 
-	/* fsid 0 is reserved for upper fs even with non upper overlay */
-	if (ofs->upper_mnt && ofs->upper_mnt->mnt_sb == sb)
-		return 0;
-
-	for (i = 0; i < ofs->numlowerfs; i++) {
-		if (ofs->lower_fs[i].sb == sb)
-			return i + 1;
+	for (i = 0; i < ofs->numfs; i++) {
+		if (ofs->fs[i].sb == sb)
+			return i;
 	}
 
 	if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) {
@@ -1297,7 +1295,7 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
 		if (ofs->config.index || ofs->config.nfs_export) {
 			ofs->config.index = false;
 			ofs->config.nfs_export = false;
-			pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n",
+			pr_warn("%s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n",
 				uuid_is_null(&sb->s_uuid) ? "null" :
 							    "conflicting",
 				path->dentry);
@@ -1306,35 +1304,59 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
 
 	err = get_anon_bdev(&dev);
 	if (err) {
-		pr_err("overlayfs: failed to get anonymous bdev for lowerpath\n");
+		pr_err("failed to get anonymous bdev for lowerpath\n");
 		return err;
 	}
 
-	ofs->lower_fs[ofs->numlowerfs].sb = sb;
-	ofs->lower_fs[ofs->numlowerfs].pseudo_dev = dev;
-	ofs->lower_fs[ofs->numlowerfs].bad_uuid = bad_uuid;
-	ofs->numlowerfs++;
+	ofs->fs[ofs->numfs].sb = sb;
+	ofs->fs[ofs->numfs].pseudo_dev = dev;
+	ofs->fs[ofs->numfs].bad_uuid = bad_uuid;
 
-	return ofs->numlowerfs;
+	return ofs->numfs++;
 }
 
-static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
-				struct path *stack, unsigned int numlower)
+static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
+			  struct path *stack, unsigned int numlower)
 {
 	int err;
 	unsigned int i;
+	struct ovl_layer *layers;
 
 	err = -ENOMEM;
-	ofs->lower_layers = kcalloc(numlower, sizeof(struct ovl_layer),
-				    GFP_KERNEL);
-	if (ofs->lower_layers == NULL)
+	layers = kcalloc(numlower + 1, sizeof(struct ovl_layer), GFP_KERNEL);
+	if (!layers)
 		goto out;
+	ofs->layers = layers;
 
-	ofs->lower_fs = kcalloc(numlower, sizeof(struct ovl_sb),
-				GFP_KERNEL);
-	if (ofs->lower_fs == NULL)
+	ofs->fs = kcalloc(numlower + 1, sizeof(struct ovl_sb), GFP_KERNEL);
+	if (ofs->fs == NULL)
 		goto out;
 
+	/* idx/fsid 0 are reserved for upper fs even with lower only overlay */
+	ofs->numfs++;
+
+	layers[0].mnt = ofs->upper_mnt;
+	layers[0].idx = 0;
+	layers[0].fsid = 0;
+	ofs->numlayer = 1;
+
+	/*
+	 * All lower layers that share the same fs as upper layer, use the same
+	 * pseudo_dev as upper layer.  Allocate fs[0].pseudo_dev even for lower
+	 * only overlay to simplify ovl_fs_free().
+	 * is_lower will be set if upper fs is shared with a lower layer.
+	 */
+	err = get_anon_bdev(&ofs->fs[0].pseudo_dev);
+	if (err) {
+		pr_err("failed to get anonymous bdev for upper fs\n");
+		goto out;
+	}
+
+	if (ofs->upper_mnt) {
+		ofs->fs[0].sb = ofs->upper_mnt->mnt_sb;
+		ofs->fs[0].is_lower = false;
+	}
+
 	for (i = 0; i < numlower; i++) {
 		struct vfsmount *mnt;
 		struct inode *trap;
@@ -1357,7 +1379,7 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
 		mnt = clone_private_mount(&stack[i]);
 		err = PTR_ERR(mnt);
 		if (IS_ERR(mnt)) {
-			pr_err("overlayfs: failed to clone lowerpath\n");
+			pr_err("failed to clone lowerpath\n");
 			iput(trap);
 			goto out;
 		}
@@ -1368,15 +1390,13 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
 		 */
 		mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME;
 
-		ofs->lower_layers[ofs->numlower].trap = trap;
-		ofs->lower_layers[ofs->numlower].mnt = mnt;
-		ofs->lower_layers[ofs->numlower].idx = i + 1;
-		ofs->lower_layers[ofs->numlower].fsid = fsid;
-		if (fsid) {
-			ofs->lower_layers[ofs->numlower].fs =
-				&ofs->lower_fs[fsid - 1];
-		}
-		ofs->numlower++;
+		layers[ofs->numlayer].trap = trap;
+		layers[ofs->numlayer].mnt = mnt;
+		layers[ofs->numlayer].idx = ofs->numlayer;
+		layers[ofs->numlayer].fsid = fsid;
+		layers[ofs->numlayer].fs = &ofs->fs[fsid];
+		ofs->numlayer++;
+		ofs->fs[fsid].is_lower = true;
 	}
 
 	/*
@@ -1387,22 +1407,23 @@ static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
 	 * bits reserved for fsid, it emits a warning and uses the original
 	 * inode number.
 	 */
-	if (!ofs->numlowerfs || (ofs->numlowerfs == 1 && !ofs->upper_mnt)) {
-		ofs->xino_bits = 0;
-		ofs->config.xino = OVL_XINO_OFF;
-	} else if (ofs->config.xino == OVL_XINO_ON && !ofs->xino_bits) {
+	if (ofs->numfs - !ofs->upper_mnt == 1) {
+		if (ofs->config.xino == OVL_XINO_ON)
+			pr_info("\"xino=on\" is useless with all layers on same fs, ignore.\n");
+		ofs->xino_mode = 0;
+	} else if (ofs->config.xino == OVL_XINO_ON && ofs->xino_mode < 0) {
 		/*
-		 * This is a roundup of number of bits needed for numlowerfs+1
-		 * (i.e. ilog2(numlowerfs+1 - 1) + 1). fsid 0 is reserved for
-		 * upper fs even with non upper overlay.
+		 * This is a roundup of number of bits needed for encoding
+		 * fsid, where fsid 0 is reserved for upper fs even with
+		 * lower only overlay.
 		 */
 		BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31);
-		ofs->xino_bits = ilog2(ofs->numlowerfs) + 1;
+		ofs->xino_mode = ilog2(ofs->numfs - 1) + 1;
 	}
 
-	if (ofs->xino_bits) {
-		pr_info("overlayfs: \"xino\" feature enabled using %d upper inode bits.\n",
-			ofs->xino_bits);
+	if (ofs->xino_mode > 0) {
+		pr_info("\"xino\" feature enabled using %d upper inode bits.\n",
+			ofs->xino_mode);
 	}
 
 	err = 0;
@@ -1428,15 +1449,15 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 	err = -EINVAL;
 	stacklen = ovl_split_lowerdirs(lowertmp);
 	if (stacklen > OVL_MAX_STACK) {
-		pr_err("overlayfs: too many lower directories, limit is %d\n",
+		pr_err("too many lower directories, limit is %d\n",
 		       OVL_MAX_STACK);
 		goto out_err;
 	} else if (!ofs->config.upperdir && stacklen == 1) {
-		pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
+		pr_err("at least 2 lowerdir are needed while upperdir nonexistent\n");
 		goto out_err;
 	} else if (!ofs->config.upperdir && ofs->config.nfs_export &&
 		   ofs->config.redirect_follow) {
-		pr_warn("overlayfs: NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
+		pr_warn("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
 		ofs->config.nfs_export = false;
 	}
 
@@ -1459,11 +1480,11 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 	err = -EINVAL;
 	sb->s_stack_depth++;
 	if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
-		pr_err("overlayfs: maximum fs stacking depth exceeded\n");
+		pr_err("maximum fs stacking depth exceeded\n");
 		goto out_err;
 	}
 
-	err = ovl_get_lower_layers(sb, ofs, stack, numlower);
+	err = ovl_get_layers(sb, ofs, stack, numlower);
 	if (err)
 		goto out_err;
 
@@ -1474,7 +1495,7 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
 
 	for (i = 0; i < numlower; i++) {
 		oe->lowerstack[i].dentry = dget(stack[i].dentry);
-		oe->lowerstack[i].layer = &ofs->lower_layers[i];
+		oe->lowerstack[i].layer = &ofs->layers[i+1];
 	}
 
 	if (remote)
@@ -1515,7 +1536,7 @@ static int ovl_check_layer(struct super_block *sb, struct ovl_fs *ofs,
 	while (!err && parent != next) {
 		if (ovl_lookup_trap_inode(sb, parent)) {
 			err = -ELOOP;
-			pr_err("overlayfs: overlapping %s path\n", name);
+			pr_err("overlapping %s path\n", name);
 		} else if (ovl_is_inuse(parent)) {
 			err = ovl_report_in_use(ofs, name);
 		}
@@ -1555,9 +1576,9 @@ static int ovl_check_overlapping_layers(struct super_block *sb,
 			return err;
 	}
 
-	for (i = 0; i < ofs->numlower; i++) {
+	for (i = 1; i < ofs->numlayer; i++) {
 		err = ovl_check_layer(sb, ofs,
-				      ofs->lower_layers[i].mnt->mnt_root,
+				      ofs->layers[i].mnt->mnt_root,
 				      "lowerdir");
 		if (err)
 			return err;
@@ -1595,7 +1616,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	err = -EINVAL;
 	if (!ofs->config.lowerdir) {
 		if (!silent)
-			pr_err("overlayfs: missing 'lowerdir'\n");
+			pr_err("missing 'lowerdir'\n");
 		goto out_err;
 	}
 
@@ -1603,14 +1624,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	/* Assume underlaying fs uses 32bit inodes unless proven otherwise */
 	if (ofs->config.xino != OVL_XINO_OFF)
-		ofs->xino_bits = BITS_PER_LONG - 32;
+		ofs->xino_mode = BITS_PER_LONG - 32;
 
 	/* alloc/destroy_inode needed for setting up traps in inode cache */
 	sb->s_op = &ovl_super_operations;
 
 	if (ofs->config.upperdir) {
 		if (!ofs->config.workdir) {
-			pr_err("overlayfs: missing 'workdir'\n");
+			pr_err("missing 'workdir'\n");
 			goto out_err;
 		}
 
@@ -1660,13 +1681,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	if (!ofs->indexdir) {
 		ofs->config.index = false;
 		if (ofs->upper_mnt && ofs->config.nfs_export) {
-			pr_warn("overlayfs: NFS export requires an index dir, falling back to nfs_export=off.\n");
+			pr_warn("NFS export requires an index dir, falling back to nfs_export=off.\n");
 			ofs->config.nfs_export = false;
 		}
 	}
 
 	if (ofs->config.metacopy && ofs->config.nfs_export) {
-		pr_warn("overlayfs: NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n");
+		pr_warn("NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n");
 		ofs->config.nfs_export = false;
 	}
 
@@ -1749,9 +1770,15 @@ static int __init ovl_init(void)
 	if (ovl_inode_cachep == NULL)
 		return -ENOMEM;
 
-	err = register_filesystem(&ovl_fs_type);
-	if (err)
-		kmem_cache_destroy(ovl_inode_cachep);
+	err = ovl_aio_request_cache_init();
+	if (!err) {
+		err = register_filesystem(&ovl_fs_type);
+		if (!err)
+			return 0;
+
+		ovl_aio_request_cache_destroy();
+	}
+	kmem_cache_destroy(ovl_inode_cachep);
 
 	return err;
 }
@@ -1766,7 +1793,7 @@ static void __exit ovl_exit(void)
 	 */
 	rcu_barrier();
 	kmem_cache_destroy(ovl_inode_cachep);
-
+	ovl_aio_request_cache_destroy();
 }
 
 module_init(ovl_init);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index f5678a3f8350..ea005085803f 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -40,18 +40,6 @@ const struct cred *ovl_override_creds(struct super_block *sb)
 	return override_creds(ofs->creator_cred);
 }
 
-struct super_block *ovl_same_sb(struct super_block *sb)
-{
-	struct ovl_fs *ofs = sb->s_fs_info;
-
-	if (!ofs->numlowerfs)
-		return ofs->upper_mnt->mnt_sb;
-	else if (ofs->numlowerfs == 1 && !ofs->upper_mnt)
-		return ofs->lower_fs[0].sb;
-	else
-		return NULL;
-}
-
 /*
  * Check if underlying fs supports file handles and try to determine encoding
  * type, in order to deduce maximum inode number used by fs.
@@ -198,7 +186,7 @@ struct dentry *ovl_dentry_lower(struct dentry *dentry)
 	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
 }
 
-struct ovl_layer *ovl_layer_lower(struct dentry *dentry)
+const struct ovl_layer *ovl_layer_lower(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
@@ -576,7 +564,7 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
 	err = ovl_do_setxattr(upperdentry, name, value, size, 0);
 
 	if (err == -EOPNOTSUPP) {
-		pr_warn("overlayfs: cannot set %s xattr on upper\n", name);
+		pr_warn("cannot set %s xattr on upper\n", name);
 		ofs->noxattr = true;
 		return xerr;
 	}
@@ -700,7 +688,7 @@ static void ovl_cleanup_index(struct dentry *dentry)
 
 	inode = d_inode(upperdentry);
 	if (!S_ISDIR(inode->i_mode) && inode->i_nlink != 1) {
-		pr_warn_ratelimited("overlayfs: cleanup linked index (%pd2, ino=%lu, nlink=%u)\n",
+		pr_warn_ratelimited("cleanup linked index (%pd2, ino=%lu, nlink=%u)\n",
 				    upperdentry, inode->i_ino, inode->i_nlink);
 		/*
 		 * We either have a bug with persistent union nlink or a lower
@@ -739,7 +727,7 @@ out:
 	return;
 
 fail:
-	pr_err("overlayfs: cleanup index of '%pd2' failed (%i)\n", dentry, err);
+	pr_err("cleanup index of '%pd2' failed (%i)\n", dentry, err);
 	goto out;
 }
 
@@ -830,7 +818,7 @@ int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
 err_unlock:
 	unlock_rename(workdir, upperdir);
 err:
-	pr_err("overlayfs: failed to lock workdir+upperdir\n");
+	pr_err("failed to lock workdir+upperdir\n");
 	return -EIO;
 }
 
@@ -852,7 +840,7 @@ int ovl_check_metacopy_xattr(struct dentry *dentry)
 
 	return 1;
 out:
-	pr_warn_ratelimited("overlayfs: failed to get metacopy (%i)\n", res);
+	pr_warn_ratelimited("failed to get metacopy (%i)\n", res);
 	return res;
 }
 
@@ -899,7 +887,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value,
 	return res;
 
 fail:
-	pr_warn_ratelimited("overlayfs: failed to get xattr %s: err=%zi)\n",
+	pr_warn_ratelimited("failed to get xattr %s: err=%zi)\n",
 			    name, res);
 	kfree(buf);
 	return res;
@@ -931,7 +919,7 @@ char *ovl_get_redirect_xattr(struct dentry *dentry, int padding)
 
 	return buf;
 invalid:
-	pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf);
+	pr_warn_ratelimited("invalid redirect (%s)\n", buf);
 	res = -EINVAL;
 	kfree(buf);
 	return ERR_PTR(res);
diff --git a/fs/proc/cpuinfo.c b/fs/proc/cpuinfo.c
index 96f1087e372c..c1dea9b8222e 100644
--- a/fs/proc/cpuinfo.c
+++ b/fs/proc/cpuinfo.c
@@ -16,16 +16,16 @@ static int cpuinfo_open(struct inode *inode, struct file *file)
 	return seq_open(file, &cpuinfo_op);
 }
 
-static const struct file_operations proc_cpuinfo_operations = {
-	.open		= cpuinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops cpuinfo_proc_ops = {
+	.proc_open	= cpuinfo_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static int __init proc_cpuinfo_init(void)
 {
-	proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
+	proc_create("cpuinfo", 0, NULL, &cpuinfo_proc_ops);
 	return 0;
 }
 fs_initcall(proc_cpuinfo_init);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 074e9585c699..3faed94e4b65 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -473,7 +473,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
 	ent = __proc_create(&parent, name, S_IFDIR | mode, 2);
 	if (ent) {
 		ent->data = data;
-		ent->proc_fops = &proc_dir_operations;
+		ent->proc_dir_ops = &proc_dir_operations;
 		ent->proc_iops = &proc_dir_inode_operations;
 		ent = proc_register(parent, ent);
 	}
@@ -503,7 +503,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
 	ent = __proc_create(&parent, name, mode, 2);
 	if (ent) {
 		ent->data = NULL;
-		ent->proc_fops = NULL;
+		ent->proc_dir_ops = NULL;
 		ent->proc_iops = NULL;
 		ent = proc_register(parent, ent);
 	}
@@ -533,25 +533,23 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
 
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 		struct proc_dir_entry *parent,
-		const struct file_operations *proc_fops, void *data)
+		const struct proc_ops *proc_ops, void *data)
 {
 	struct proc_dir_entry *p;
 
-	BUG_ON(proc_fops == NULL);
-
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
-	p->proc_fops = proc_fops;
+	p->proc_ops = proc_ops;
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_data);
  
 struct proc_dir_entry *proc_create(const char *name, umode_t mode,
 				   struct proc_dir_entry *parent,
-				   const struct file_operations *proc_fops)
+				   const struct proc_ops *proc_ops)
 {
-	return proc_create_data(name, mode, parent, proc_fops, NULL);
+	return proc_create_data(name, mode, parent, proc_ops, NULL);
 }
 EXPORT_SYMBOL(proc_create);
 
@@ -573,11 +571,11 @@ static int proc_seq_release(struct inode *inode, struct file *file)
 	return seq_release(inode, file);
 }
 
-static const struct file_operations proc_seq_fops = {
-	.open		= proc_seq_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= proc_seq_release,
+static const struct proc_ops proc_seq_ops = {
+	.proc_open	= proc_seq_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= proc_seq_release,
 };
 
 struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
@@ -589,7 +587,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
-	p->proc_fops = &proc_seq_fops;
+	p->proc_ops = &proc_seq_ops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
 	return proc_register(parent, p);
@@ -603,11 +601,11 @@ static int proc_single_open(struct inode *inode, struct file *file)
 	return single_open(file, de->single_show, de->data);
 }
 
-static const struct file_operations proc_single_fops = {
-	.open		= proc_single_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops proc_single_ops = {
+	.proc_open	= proc_single_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
@@ -619,7 +617,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
 	p = proc_create_reg(name, mode, &parent, data);
 	if (!p)
 		return NULL;
-	p->proc_fops = &proc_single_fops;
+	p->proc_ops = &proc_single_ops;
 	p->single_show = show;
 	return proc_register(parent, p);
 }
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index dbe43a50caf2..6da18316d209 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -163,7 +163,7 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
 		pdeo->closing = true;
 		spin_unlock(&pde->pde_unload_lock);
 		file = pdeo->file;
-		pde->proc_fops->release(file_inode(file), file);
+		pde->proc_ops->proc_release(file_inode(file), file);
 		spin_lock(&pde->pde_unload_lock);
 		/* After ->release. */
 		list_del(&pdeo->lh);
@@ -200,12 +200,12 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	loff_t rv = -EINVAL;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, llseek) llseek;
+		typeof_member(struct proc_ops, proc_lseek) lseek;
 
-		llseek = pde->proc_fops->llseek;
-		if (!llseek)
-			llseek = default_llseek;
-		rv = llseek(file, offset, whence);
+		lseek = pde->proc_ops->proc_lseek;
+		if (!lseek)
+			lseek = default_llseek;
+		rv = lseek(file, offset, whence);
 		unuse_pde(pde);
 	}
 	return rv;
@@ -216,9 +216,9 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count,
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	ssize_t rv = -EIO;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, read) read;
+		typeof_member(struct proc_ops, proc_read) read;
 
-		read = pde->proc_fops->read;
+		read = pde->proc_ops->proc_read;
 		if (read)
 			rv = read(file, buf, count, ppos);
 		unuse_pde(pde);
@@ -231,9 +231,9 @@ static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	ssize_t rv = -EIO;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, write) write;
+		typeof_member(struct proc_ops, proc_write) write;
 
-		write = pde->proc_fops->write;
+		write = pde->proc_ops->proc_write;
 		if (write)
 			rv = write(file, buf, count, ppos);
 		unuse_pde(pde);
@@ -246,9 +246,9 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	__poll_t rv = DEFAULT_POLLMASK;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, poll) poll;
+		typeof_member(struct proc_ops, proc_poll) poll;
 
-		poll = pde->proc_fops->poll;
+		poll = pde->proc_ops->proc_poll;
 		if (poll)
 			rv = poll(file, pts);
 		unuse_pde(pde);
@@ -261,9 +261,9 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	long rv = -ENOTTY;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, unlocked_ioctl) ioctl;
+		typeof_member(struct proc_ops, proc_ioctl) ioctl;
 
-		ioctl = pde->proc_fops->unlocked_ioctl;
+		ioctl = pde->proc_ops->proc_ioctl;
 		if (ioctl)
 			rv = ioctl(file, cmd, arg);
 		unuse_pde(pde);
@@ -277,9 +277,9 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	long rv = -ENOTTY;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, compat_ioctl) compat_ioctl;
+		typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl;
 
-		compat_ioctl = pde->proc_fops->compat_ioctl;
+		compat_ioctl = pde->proc_ops->proc_compat_ioctl;
 		if (compat_ioctl)
 			rv = compat_ioctl(file, cmd, arg);
 		unuse_pde(pde);
@@ -293,9 +293,9 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	int rv = -EIO;
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, mmap) mmap;
+		typeof_member(struct proc_ops, proc_mmap) mmap;
 
-		mmap = pde->proc_fops->mmap;
+		mmap = pde->proc_ops->proc_mmap;
 		if (mmap)
 			rv = mmap(file, vma);
 		unuse_pde(pde);
@@ -312,9 +312,9 @@ proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
 	unsigned long rv = -EIO;
 
 	if (use_pde(pde)) {
-		typeof_member(struct file_operations, get_unmapped_area) get_area;
+		typeof_member(struct proc_ops, proc_get_unmapped_area) get_area;
 
-		get_area = pde->proc_fops->get_unmapped_area;
+		get_area = pde->proc_ops->proc_get_unmapped_area;
 #ifdef CONFIG_MMU
 		if (!get_area)
 			get_area = current->mm->get_unmapped_area;
@@ -333,8 +333,8 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 {
 	struct proc_dir_entry *pde = PDE(inode);
 	int rv = 0;
-	typeof_member(struct file_operations, open) open;
-	typeof_member(struct file_operations, release) release;
+	typeof_member(struct proc_ops, proc_open) open;
+	typeof_member(struct proc_ops, proc_release) release;
 	struct pde_opener *pdeo;
 
 	/*
@@ -351,7 +351,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 	if (!use_pde(pde))
 		return -ENOENT;
 
-	release = pde->proc_fops->release;
+	release = pde->proc_ops->proc_release;
 	if (release) {
 		pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL);
 		if (!pdeo) {
@@ -360,7 +360,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 		}
 	}
 
-	open = pde->proc_fops->open;
+	open = pde->proc_ops->proc_open;
 	if (open)
 		rv = open(inode, file);
 
@@ -468,21 +468,23 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 			inode->i_size = de->size;
 		if (de->nlink)
 			set_nlink(inode, de->nlink);
-		WARN_ON(!de->proc_iops);
-		inode->i_op = de->proc_iops;
-		if (de->proc_fops) {
-			if (S_ISREG(inode->i_mode)) {
+
+		if (S_ISREG(inode->i_mode)) {
+			inode->i_op = de->proc_iops;
+			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-				if (!de->proc_fops->compat_ioctl)
-					inode->i_fop =
-						&proc_reg_file_ops_no_compat;
-				else
-#endif
-					inode->i_fop = &proc_reg_file_ops;
-			} else {
-				inode->i_fop = de->proc_fops;
+			if (!de->proc_ops->proc_compat_ioctl) {
+				inode->i_fop = &proc_reg_file_ops_no_compat;
 			}
-		}
+#endif
+		} else if (S_ISDIR(inode->i_mode)) {
+			inode->i_op = de->proc_iops;
+			inode->i_fop = de->proc_dir_ops;
+		} else if (S_ISLNK(inode->i_mode)) {
+			inode->i_op = de->proc_iops;
+			inode->i_fop = NULL;
+		} else
+			BUG();
 	} else
 	       pde_put(de);
 	return inode;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 0f3b557c9b77..41587276798e 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -39,7 +39,10 @@ struct proc_dir_entry {
 	spinlock_t pde_unload_lock;
 	struct completion *pde_unload_completion;
 	const struct inode_operations *proc_iops;
-	const struct file_operations *proc_fops;
+	union {
+		const struct proc_ops *proc_ops;
+		const struct file_operations *proc_dir_ops;
+	};
 	const struct dentry_operations *proc_dops;
 	union {
 		const struct seq_operations *seq_ops;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e2ed8e08cc7a..8ba492d44e68 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -574,11 +574,11 @@ static int release_kcore(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations proc_kcore_operations = {
-	.read		= read_kcore,
-	.open		= open_kcore,
-	.release	= release_kcore,
-	.llseek		= default_llseek,
+static const struct proc_ops kcore_proc_ops = {
+	.proc_read	= read_kcore,
+	.proc_open	= open_kcore,
+	.proc_release	= release_kcore,
+	.proc_lseek	= default_llseek,
 };
 
 /* just remember that we have to update kcore */
@@ -637,8 +637,7 @@ static void __init add_modules_range(void)
 
 static int __init proc_kcore_init(void)
 {
-	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL,
-				      &proc_kcore_operations);
+	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &kcore_proc_ops);
 	if (!proc_root_kcore) {
 		pr_err("couldn't create /proc/kcore\n");
 		return 0; /* Always returns 0. */
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index 4f4a2abb225e..ec1b7d2fb773 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -49,17 +49,17 @@ static __poll_t kmsg_poll(struct file *file, poll_table *wait)
 }
 
 
-static const struct file_operations proc_kmsg_operations = {
-	.read		= kmsg_read,
-	.poll		= kmsg_poll,
-	.open		= kmsg_open,
-	.release	= kmsg_release,
-	.llseek		= generic_file_llseek,
+static const struct proc_ops kmsg_proc_ops = {
+	.proc_read	= kmsg_read,
+	.proc_poll	= kmsg_poll,
+	.proc_open	= kmsg_open,
+	.proc_release	= kmsg_release,
+	.proc_lseek	= generic_file_llseek,
 };
 
 static int __init proc_kmsg_init(void)
 {
-	proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
+	proc_create("kmsg", S_IRUSR, NULL, &kmsg_proc_ops);
 	return 0;
 }
 fs_initcall(proc_kmsg_init);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 7c952ee732e6..f909243d4a66 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -21,6 +21,21 @@
 #define KPMMASK (KPMSIZE - 1)
 #define KPMBITS (KPMSIZE * BITS_PER_BYTE)
 
+static inline unsigned long get_max_dump_pfn(void)
+{
+#ifdef CONFIG_SPARSEMEM
+	/*
+	 * The memmap of early sections is completely populated and marked
+	 * online even if max_pfn does not fall on a section boundary -
+	 * pfn_to_online_page() will succeed on all pages. Allow inspecting
+	 * these memmaps.
+	 */
+	return round_up(max_pfn, PAGES_PER_SECTION);
+#else
+	return max_pfn;
+#endif
+}
+
 /* /proc/kpagecount - an array exposing page counts
  *
  * Each entry is a u64 representing the corresponding
@@ -29,6 +44,7 @@
 static ssize_t kpagecount_read(struct file *file, char __user *buf,
 			     size_t count, loff_t *ppos)
 {
+	const unsigned long max_dump_pfn = get_max_dump_pfn();
 	u64 __user *out = (u64 __user *)buf;
 	struct page *ppage;
 	unsigned long src = *ppos;
@@ -37,9 +53,11 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 	u64 pcount;
 
 	pfn = src / KPMSIZE;
-	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
 	if (src & KPMMASK || count & KPMMASK)
 		return -EINVAL;
+	if (src >= max_dump_pfn * KPMSIZE)
+		return 0;
+	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
 
 	while (count > 0) {
 		/*
@@ -71,9 +89,9 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 	return ret;
 }
 
-static const struct file_operations proc_kpagecount_operations = {
-	.llseek = mem_lseek,
-	.read = kpagecount_read,
+static const struct proc_ops kpagecount_proc_ops = {
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecount_read,
 };
 
 /* /proc/kpageflags - an array exposing page flags
@@ -206,6 +224,7 @@ u64 stable_page_flags(struct page *page)
 static ssize_t kpageflags_read(struct file *file, char __user *buf,
 			     size_t count, loff_t *ppos)
 {
+	const unsigned long max_dump_pfn = get_max_dump_pfn();
 	u64 __user *out = (u64 __user *)buf;
 	struct page *ppage;
 	unsigned long src = *ppos;
@@ -213,9 +232,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
 	ssize_t ret = 0;
 
 	pfn = src / KPMSIZE;
-	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
 	if (src & KPMMASK || count & KPMMASK)
 		return -EINVAL;
+	if (src >= max_dump_pfn * KPMSIZE)
+		return 0;
+	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
 
 	while (count > 0) {
 		/*
@@ -242,15 +263,16 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
 	return ret;
 }
 
-static const struct file_operations proc_kpageflags_operations = {
-	.llseek = mem_lseek,
-	.read = kpageflags_read,
+static const struct proc_ops kpageflags_proc_ops = {
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpageflags_read,
 };
 
 #ifdef CONFIG_MEMCG
 static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
 				size_t count, loff_t *ppos)
 {
+	const unsigned long max_dump_pfn = get_max_dump_pfn();
 	u64 __user *out = (u64 __user *)buf;
 	struct page *ppage;
 	unsigned long src = *ppos;
@@ -259,9 +281,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
 	u64 ino;
 
 	pfn = src / KPMSIZE;
-	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
 	if (src & KPMMASK || count & KPMMASK)
 		return -EINVAL;
+	if (src >= max_dump_pfn * KPMSIZE)
+		return 0;
+	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
 
 	while (count > 0) {
 		/*
@@ -293,18 +317,18 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
 	return ret;
 }
 
-static const struct file_operations proc_kpagecgroup_operations = {
-	.llseek = mem_lseek,
-	.read = kpagecgroup_read,
+static const struct proc_ops kpagecgroup_proc_ops = {
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecgroup_read,
 };
 #endif /* CONFIG_MEMCG */
 
 static int __init proc_page_init(void)
 {
-	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
-	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
+	proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops);
+	proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops);
 #ifdef CONFIG_MEMCG
-	proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
+	proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops);
 #endif
 	return 0;
 }
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 76ae278df1c4..4888c5224442 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -90,12 +90,12 @@ static int seq_release_net(struct inode *ino, struct file *f)
 	return 0;
 }
 
-static const struct file_operations proc_net_seq_fops = {
-	.open		= seq_open_net,
-	.read		= seq_read,
-	.write		= proc_simple_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release_net,
+static const struct proc_ops proc_net_seq_ops = {
+	.proc_open	= seq_open_net,
+	.proc_read	= seq_read,
+	.proc_write	= proc_simple_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release_net,
 };
 
 struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
@@ -108,7 +108,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode,
 	if (!p)
 		return NULL;
 	pde_force_lookup(p);
-	p->proc_fops = &proc_net_seq_fops;
+	p->proc_ops = &proc_net_seq_ops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
 	return proc_register(parent, p);
@@ -152,7 +152,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode
 	if (!p)
 		return NULL;
 	pde_force_lookup(p);
-	p->proc_fops = &proc_net_seq_fops;
+	p->proc_ops = &proc_net_seq_ops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
 	p->write = write;
@@ -183,12 +183,12 @@ static int single_release_net(struct inode *ino, struct file *f)
 	return single_release(ino, f);
 }
 
-static const struct file_operations proc_net_single_fops = {
-	.open		= single_open_net,
-	.read		= seq_read,
-	.write		= proc_simple_write,
-	.llseek		= seq_lseek,
-	.release	= single_release_net,
+static const struct proc_ops proc_net_single_ops = {
+	.proc_open	= single_open_net,
+	.proc_read	= seq_read,
+	.proc_write	= proc_simple_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release_net,
 };
 
 struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
@@ -201,7 +201,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode,
 	if (!p)
 		return NULL;
 	pde_force_lookup(p);
-	p->proc_fops = &proc_net_single_fops;
+	p->proc_ops = &proc_net_single_ops;
 	p->single_show = show;
 	return proc_register(parent, p);
 }
@@ -244,7 +244,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo
 	if (!p)
 		return NULL;
 	pde_force_lookup(p);
-	p->proc_fops = &proc_net_single_fops;
+	p->proc_ops = &proc_net_single_ops;
 	p->single_show = show;
 	p->write = write;
 	return proc_register(parent, p);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d80989b6c344..c75bb4632ed1 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1720,7 +1720,7 @@ int __init proc_sys_init(void)
 
 	proc_sys_root = proc_mkdir("sys", NULL);
 	proc_sys_root->proc_iops = &proc_sys_dir_operations;
-	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
+	proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations;
 	proc_sys_root->nlink = 0;
 
 	return sysctl_init();
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 0b7c8dffc9ae..72c07a34cff0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -292,7 +292,7 @@ struct proc_dir_entry proc_root = {
 	.nlink		= 2, 
 	.refcnt		= REFCOUNT_INIT(1),
 	.proc_iops	= &proc_root_inode_operations, 
-	.proc_fops	= &proc_root_operations,
+	.proc_dir_ops	= &proc_root_operations,
 	.parent		= &proc_root,
 	.subdir		= RB_ROOT,
 	.name		= "/proc",
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index fd931d3e77be..0449edf460f5 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -223,16 +223,16 @@ static int stat_open(struct inode *inode, struct file *file)
 	return single_open_size(file, show_stat, NULL, size);
 }
 
-static const struct file_operations proc_stat_operations = {
-	.open		= stat_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops stat_proc_ops = {
+	.proc_open	= stat_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 static int __init proc_stat_init(void)
 {
-	proc_create("stat", 0, NULL, &proc_stat_operations);
+	proc_create("stat", 0, NULL, &stat_proc_ops);
 	return 0;
 }
 fs_initcall(proc_stat_init);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 9442631fd4af..3ba9ae83bff5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -505,7 +505,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 
 #ifdef CONFIG_SHMEM
 static int smaps_pte_hole(unsigned long addr, unsigned long end,
-		struct mm_walk *walk)
+			  __always_unused int depth, struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
 
@@ -1282,7 +1282,7 @@ static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
 }
 
 static int pagemap_pte_hole(unsigned long start, unsigned long end,
-				struct mm_walk *walk)
+			    __always_unused int depth, struct mm_walk *walk)
 {
 	struct pagemapread *pm = walk->private;
 	unsigned long addr = start;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 7b13988796e1..7dc800cce354 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -667,10 +667,10 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 }
 #endif
 
-static const struct file_operations proc_vmcore_operations = {
-	.read		= read_vmcore,
-	.llseek		= default_llseek,
-	.mmap		= mmap_vmcore,
+static const struct proc_ops vmcore_proc_ops = {
+	.proc_read	= read_vmcore,
+	.proc_lseek	= default_llseek,
+	.proc_mmap	= mmap_vmcore,
 };
 
 static struct vmcore* __init get_new_element(void)
@@ -1555,7 +1555,7 @@ static int __init vmcore_init(void)
 	elfcorehdr_free(elfcorehdr_addr);
 	elfcorehdr_addr = ELFCORE_ADDR_ERR;
 
-	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
+	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &vmcore_proc_ops);
 	if (proc_vmcore)
 		proc_vmcore->size = vmcore_size;
 	return 0;
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index 53429c29c784..58fc2a7c7fd1 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -22,8 +22,6 @@ MODULE_AUTHOR("Jan Kara");
 MODULE_DESCRIPTION("Quota format v2 support");
 MODULE_LICENSE("GPL");
 
-#define __QUOTA_V2_PARANOIA
-
 static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot);
 static void v2r0_disk2memdqb(struct dquot *dquot, void *dp);
 static int v2r0_is_id(void *dp, struct dquot *dquot);
diff --git a/fs/quota/quotaio_v1.h b/fs/quota/quotaio_v1.h
index bd11e2c08119..31dca9a89176 100644
--- a/fs/quota/quotaio_v1.h
+++ b/fs/quota/quotaio_v1.h
@@ -25,8 +25,10 @@ struct v1_disk_dqblk {
 	__u32 dqb_ihardlimit;	/* absolute limit on allocated inodes */
 	__u32 dqb_isoftlimit;	/* preferred inode limit */
 	__u32 dqb_curinodes;	/* current # allocated inodes */
-	time_t dqb_btime;	/* time limit for excessive disk use */
-	time_t dqb_itime;	/* time limit for excessive inode use */
+
+	/* below fields differ in length on 32-bit vs 64-bit architectures */
+	unsigned long dqb_btime; /* time limit for excessive disk use */
+	unsigned long dqb_itime; /* time limit for excessive inode use */
 };
 
 #define v1_dqoff(UID)      ((loff_t)((UID) * sizeof (struct v1_disk_dqblk)))
diff --git a/fs/read_write.c b/fs/read_write.c
index 7458fccc59e1..59d819c5b92e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -939,6 +939,34 @@ out:
 	return ret;
 }
 
+ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
+			   struct iov_iter *iter)
+{
+	size_t tot_len;
+	ssize_t ret = 0;
+
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		goto out;
+	ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	ret = call_read_iter(file, iocb, iter);
+out:
+	if (ret >= 0)
+		fsnotify_access(file);
+	return ret;
+}
+EXPORT_SYMBOL(vfs_iocb_iter_read);
+
 ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags)
 {
@@ -975,6 +1003,34 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
 	return ret;
 }
 
+ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
+			    struct iov_iter *iter)
+{
+	size_t tot_len;
+	ssize_t ret = 0;
+
+	if (!file->f_op->write_iter)
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EBADF;
+	if (!(file->f_mode & FMODE_CAN_WRITE))
+		return -EINVAL;
+
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		return 0;
+	ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	ret = call_write_iter(file, iocb, iter);
+	if (ret > 0)
+		fsnotify_modify(file);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_iocb_iter_write);
+
 ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags)
 {
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 4b3e3e73b512..072156c4f895 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -56,8 +56,6 @@
 /* gets a struct reiserfs_journal_list * from a list head */
 #define JOURNAL_LIST_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
                                j_list))
-#define JOURNAL_WORK_ENTRY(h) (list_entry((h), struct reiserfs_journal_list, \
-                               j_working_list))
 
 /* must be correct to keep the desc and commit structs at 4k */
 #define JOURNAL_TRANS_HALF 1018
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index f2cf3441fdfc..ff336513c254 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -63,7 +63,6 @@ static int show_version(struct seq_file *m, void *unused)
 #define MAP( i ) D4C( objectid_map( sb, rs )[ i ] )
 
 #define DJF( x ) le32_to_cpu( rs -> x )
-#define DJV( x ) le32_to_cpu( s_v1 -> x )
 #define DJP( x ) le32_to_cpu( jp -> x )
 #define JF( x ) ( r -> s_journal -> x )
 
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index da9ebe33882b..8bf88d690729 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -918,12 +918,6 @@ int comp_items(const struct item_head *stored_ih, const struct treepath *path)
 	return memcmp(stored_ih, ih, IH_SIZE);
 }
 
-/* unformatted nodes are not logged anymore, ever.  This is safe now */
-#define held_by_others(bh) (atomic_read(&(bh)->b_count) > 1)
-
-/* block can not be forgotten as it is in I/O or held by someone */
-#define block_in_use(bh) (buffer_locked(bh) || (held_by_others(bh)))
-
 /* prepare for delete or cut of direct item */
 static inline int prepare_for_direct_item(struct treepath *path,
 					  struct item_head *le_ih,
@@ -2246,7 +2240,8 @@ error_out:
 	/* also releases the path */
 	unfix_nodes(&s_ins_balance);
 #ifdef REISERQUOTA_DEBUG
-	reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
+	if (inode)
+		reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
 		       "reiserquota insert_item(): freeing %u id=%u type=%c",
 		       quota_bytes, inode->i_uid, head2type(ih));
 #endif
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 3244037b1286..a6bce5b1fb1d 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -629,6 +629,7 @@ static void reiserfs_put_super(struct super_block *s)
 	reiserfs_write_unlock(s);
 	mutex_destroy(&REISERFS_SB(s)->lock);
 	destroy_workqueue(REISERFS_SB(s)->commit_wq);
+	kfree(REISERFS_SB(s)->s_jdev);
 	kfree(s->s_fs_info);
 	s->s_fs_info = NULL;
 }
@@ -1947,7 +1948,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 		if (!sbi->s_jdev) {
 			SWARN(silent, s, "", "Cannot allocate memory for "
 				"journal device name");
-			goto error;
+			goto error_unlocked;
 		}
 	}
 #ifdef CONFIG_QUOTA
@@ -2240,6 +2241,7 @@ error_unlocked:
 			kfree(qf_names[j]);
 	}
 #endif
+	kfree(sbi->s_jdev);
 	kfree(sbi);
 
 	s->s_fs_info = NULL;
diff --git a/fs/stat.c b/fs/stat.c
index c38e4c2e1221..030008796479 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -21,6 +21,8 @@
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
+#include "internal.h"
+
 /**
  * generic_fillattr - Fill in the basic attributes from the inode struct
  * @inode: Inode to use as the source
@@ -150,6 +152,23 @@ int vfs_statx_fd(unsigned int fd, struct kstat *stat,
 }
 EXPORT_SYMBOL(vfs_statx_fd);
 
+inline unsigned vfs_stat_set_lookup_flags(unsigned *lookup_flags, int flags)
+{
+	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+		return -EINVAL;
+
+	*lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		*lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_NO_AUTOMOUNT)
+		*lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_EMPTY_PATH)
+		*lookup_flags |= LOOKUP_EMPTY;
+
+	return 0;
+}
+
 /**
  * vfs_statx - Get basic and extra attributes by filename
  * @dfd: A file descriptor representing the base dir for a relative filename
@@ -170,19 +189,10 @@ int vfs_statx(int dfd, const char __user *filename, int flags,
 {
 	struct path path;
 	int error = -EINVAL;
-	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+	unsigned lookup_flags;
 
-	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
-		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+	if (vfs_stat_set_lookup_flags(&lookup_flags, flags))
 		return -EINVAL;
-
-	if (flags & AT_SYMLINK_NOFOLLOW)
-		lookup_flags &= ~LOOKUP_FOLLOW;
-	if (flags & AT_NO_AUTOMOUNT)
-		lookup_flags &= ~LOOKUP_AUTOMOUNT;
-	if (flags & AT_EMPTY_PATH)
-		lookup_flags |= LOOKUP_EMPTY;
-
 retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
@@ -523,7 +533,7 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
-static noinline_for_stack int
+noinline_for_stack int
 cp_statx(const struct kstat *stat, struct statx __user *buffer)
 {
 	struct statx tmp;
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index d41c21fef138..c4ab045926b7 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -449,7 +449,7 @@ int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj,
 	}
 
 	link = kernfs_create_link(kobj->sd, target_name, entry);
-	if (IS_ERR(link) && PTR_ERR(link) == -EEXIST)
+	if (PTR_ERR(link) == -EEXIST)
 		sysfs_warn_dup(kobj->sd, target_name);
 
 	kernfs_put(entry);
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 0caa151cae4e..0ee8c6dfb036 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -330,7 +330,10 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 		parent = tracefs_mount->mnt_root;
 
 	inode_lock(parent->d_inode);
-	dentry = lookup_one_len(name, parent, strlen(name));
+	if (unlikely(IS_DEADDIR(parent->d_inode)))
+		dentry = ERR_PTR(-ENOENT);
+	else
+		dentry = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(dentry) && dentry->d_inode) {
 		dput(dentry);
 		dentry = ERR_PTR(-EEXIST);
@@ -499,122 +502,27 @@ __init struct dentry *tracefs_create_instance_dir(const char *name,
 	return dentry;
 }
 
-static int __tracefs_remove(struct dentry *dentry, struct dentry *parent)
+static void remove_one(struct dentry *victim)
 {
-	int ret = 0;
-
-	if (simple_positive(dentry)) {
-		if (dentry->d_inode) {
-			dget(dentry);
-			switch (dentry->d_inode->i_mode & S_IFMT) {
-			case S_IFDIR:
-				ret = simple_rmdir(parent->d_inode, dentry);
-				if (!ret)
-					fsnotify_rmdir(parent->d_inode, dentry);
-				break;
-			default:
-				simple_unlink(parent->d_inode, dentry);
-				fsnotify_unlink(parent->d_inode, dentry);
-				break;
-			}
-			if (!ret)
-				d_delete(dentry);
-			dput(dentry);
-		}
-	}
-	return ret;
-}
-
-/**
- * tracefs_remove - removes a file or directory from the tracefs filesystem
- * @dentry: a pointer to a the dentry of the file or directory to be
- *          removed.
- *
- * This function removes a file or directory in tracefs that was previously
- * created with a call to another tracefs function (like
- * tracefs_create_file() or variants thereof.)
- */
-void tracefs_remove(struct dentry *dentry)
-{
-	struct dentry *parent;
-	int ret;
-
-	if (IS_ERR_OR_NULL(dentry))
-		return;
-
-	parent = dentry->d_parent;
-	inode_lock(parent->d_inode);
-	ret = __tracefs_remove(dentry, parent);
-	inode_unlock(parent->d_inode);
-	if (!ret)
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
 }
 
 /**
- * tracefs_remove_recursive - recursively removes a directory
+ * tracefs_remove - recursively removes a directory
  * @dentry: a pointer to a the dentry of the directory to be removed.
  *
  * This function recursively removes a directory tree in tracefs that
  * was previously created with a call to another tracefs function
  * (like tracefs_create_file() or variants thereof.)
  */
-void tracefs_remove_recursive(struct dentry *dentry)
+void tracefs_remove(struct dentry *dentry)
 {
-	struct dentry *child, *parent;
-
 	if (IS_ERR_OR_NULL(dentry))
 		return;
 
-	parent = dentry;
- down:
-	inode_lock(parent->d_inode);
- loop:
-	/*
-	 * The parent->d_subdirs is protected by the d_lock. Outside that
-	 * lock, the child can be unlinked and set to be freed which can
-	 * use the d_u.d_child as the rcu head and corrupt this list.
-	 */
-	spin_lock(&parent->d_lock);
-	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!simple_positive(child))
-			continue;
-
-		/* perhaps simple_empty(child) makes more sense */
-		if (!list_empty(&child->d_subdirs)) {
-			spin_unlock(&parent->d_lock);
-			inode_unlock(parent->d_inode);
-			parent = child;
-			goto down;
-		}
-
-		spin_unlock(&parent->d_lock);
-
-		if (!__tracefs_remove(child, parent))
-			simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-
-		/*
-		 * The parent->d_lock protects agaist child from unlinking
-		 * from d_subdirs. When releasing the parent->d_lock we can
-		 * no longer trust that the next pointer is valid.
-		 * Restart the loop. We'll skip this one with the
-		 * simple_positive() check.
-		 */
-		goto loop;
-	}
-	spin_unlock(&parent->d_lock);
-
-	inode_unlock(parent->d_inode);
-	child = parent;
-	parent = parent->d_parent;
-	inode_lock(parent->d_inode);
-
-	if (child != dentry)
-		/* go up */
-		goto loop;
-
-	if (!__tracefs_remove(child, parent))
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	inode_unlock(parent->d_inode);
+	simple_pin_fs(&trace_fs_type, &tracefs_mount, &tracefs_mount_count);
+	simple_recursive_removal(dentry, remove_one);
+	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
 }
 
 /**
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index c8e8f50c6054..743928efffc1 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -786,7 +786,9 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 
 		if (page_offset > end_index)
 			break;
-		page = find_or_create_page(mapping, page_offset, ra_gfp_mask);
+		page = pagecache_get_page(mapping, page_offset,
+				 FGP_LOCK|FGP_ACCESSED|FGP_CREAT|FGP_NOWAIT,
+				 ra_gfp_mask);
 		if (!page)
 			break;
 		if (!PageUptodate(page))
@@ -1078,18 +1080,12 @@ static void do_attr_changes(struct inode *inode, const struct iattr *attr)
 		inode->i_uid = attr->ia_uid;
 	if (attr->ia_valid & ATTR_GID)
 		inode->i_gid = attr->ia_gid;
-	if (attr->ia_valid & ATTR_ATIME) {
-		inode->i_atime = timestamp_truncate(attr->ia_atime,
-						  inode);
-	}
-	if (attr->ia_valid & ATTR_MTIME) {
-		inode->i_mtime = timestamp_truncate(attr->ia_mtime,
-						  inode);
-	}
-	if (attr->ia_valid & ATTR_CTIME) {
-		inode->i_ctime = timestamp_truncate(attr->ia_ctime,
-						  inode);
-	}
+	if (attr->ia_valid & ATTR_ATIME)
+		inode->i_atime = attr->ia_atime;
+	if (attr->ia_valid & ATTR_MTIME)
+		inode->i_mtime = attr->ia_mtime;
+	if (attr->ia_valid & ATTR_CTIME)
+		inode->i_ctime = attr->ia_ctime;
 	if (attr->ia_valid & ATTR_MODE) {
 		umode_t mode = attr->ia_mode;
 
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 5dc5abca11c7..d49fc04f2d7d 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -17,10 +17,14 @@
 #include "ubifs.h"
 
 /* Need to be kept consistent with checked flags in ioctl2ubifs() */
-#define UBIFS_SUPPORTED_IOCTL_FLAGS \
+#define UBIFS_SETTABLE_IOCTL_FLAGS \
 	(FS_COMPR_FL | FS_SYNC_FL | FS_APPEND_FL | \
 	 FS_IMMUTABLE_FL | FS_DIRSYNC_FL)
 
+/* Need to be kept consistent with checked flags in ubifs2ioctl() */
+#define UBIFS_GETTABLE_IOCTL_FLAGS \
+	(UBIFS_SETTABLE_IOCTL_FLAGS | FS_ENCRYPT_FL)
+
 /**
  * ubifs_set_inode_flags - set VFS inode flags.
  * @inode: VFS inode to set flags for
@@ -91,6 +95,8 @@ static int ubifs2ioctl(int ubifs_flags)
 		ioctl_flags |= FS_IMMUTABLE_FL;
 	if (ubifs_flags & UBIFS_DIRSYNC_FL)
 		ioctl_flags |= FS_DIRSYNC_FL;
+	if (ubifs_flags & UBIFS_CRYPT_FL)
+		ioctl_flags |= FS_ENCRYPT_FL;
 
 	return ioctl_flags;
 }
@@ -113,7 +119,8 @@ static int setflags(struct inode *inode, int flags)
 	if (err)
 		goto out_unlock;
 
-	ui->flags = ioctl2ubifs(flags);
+	ui->flags &= ~ioctl2ubifs(UBIFS_SETTABLE_IOCTL_FLAGS);
+	ui->flags |= ioctl2ubifs(flags);
 	ubifs_set_inode_flags(inode);
 	inode->i_ctime = current_time(inode);
 	release = ui->dirty;
@@ -155,8 +162,9 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		if (get_user(flags, (int __user *) arg))
 			return -EFAULT;
 
-		if (flags & ~UBIFS_SUPPORTED_IOCTL_FLAGS)
+		if (flags & ~UBIFS_GETTABLE_IOCTL_FLAGS)
 			return -EOPNOTSUPP;
+		flags &= UBIFS_SETTABLE_IOCTL_FLAGS;
 
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~FS_DIRSYNC_FL;
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index 54d6db61106f..edf43ddd7dce 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -129,7 +129,7 @@ static void __orphan_drop(struct ubifs_info *c, struct ubifs_orphan *o)
 static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 {
 	if (orph->del) {
-		dbg_gen("deleted twice ino %lu", orph->inum);
+		dbg_gen("deleted twice ino %lu", (unsigned long)orph->inum);
 		return;
 	}
 
@@ -137,7 +137,7 @@ static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
 		orph->del = 1;
 		orph->dnext = c->orph_dnext;
 		c->orph_dnext = orph;
-		dbg_gen("delete later ino %lu", orph->inum);
+		dbg_gen("delete later ino %lu", (unsigned long)orph->inum);
 		return;
 	}
 
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 2b7c04bf8983..4b4b65b48c57 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -84,7 +84,6 @@ static int create_default_filesystem(struct ubifs_info *c)
 	int idx_node_size;
 	long long tmp64, main_bytes;
 	__le64 tmp_le64;
-	__le32 tmp_le32;
 	struct timespec64 ts;
 	u8 hash[UBIFS_HASH_ARR_SZ];
 	u8 hash_lpt[UBIFS_HASH_ARR_SZ];
@@ -161,7 +160,7 @@ static int create_default_filesystem(struct ubifs_info *c)
 	sup = kzalloc(ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size), GFP_KERNEL);
 	mst = kzalloc(c->mst_node_alsz, GFP_KERNEL);
 	idx_node_size = ubifs_idx_node_sz(c, 1);
-	idx = kzalloc(ALIGN(tmp, c->min_io_size), GFP_KERNEL);
+	idx = kzalloc(ALIGN(idx_node_size, c->min_io_size), GFP_KERNEL);
 	ino = kzalloc(ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size), GFP_KERNEL);
 	cs = kzalloc(ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size), GFP_KERNEL);
 
@@ -291,16 +290,14 @@ static int create_default_filesystem(struct ubifs_info *c)
 	ino->creat_sqnum = cpu_to_le64(++c->max_sqnum);
 	ino->nlink = cpu_to_le32(2);
 
-	ktime_get_real_ts64(&ts);
-	ts = timespec64_trunc(ts, DEFAULT_TIME_GRAN);
+	ktime_get_coarse_real_ts64(&ts);
 	tmp_le64 = cpu_to_le64(ts.tv_sec);
 	ino->atime_sec   = tmp_le64;
 	ino->ctime_sec   = tmp_le64;
 	ino->mtime_sec   = tmp_le64;
-	tmp_le32 = cpu_to_le32(ts.tv_nsec);
-	ino->atime_nsec  = tmp_le32;
-	ino->ctime_nsec  = tmp_le32;
-	ino->mtime_nsec  = tmp_le32;
+	ino->atime_nsec  = 0;
+	ino->ctime_nsec  = 0;
+	ino->mtime_nsec  = 0;
 	ino->mode = cpu_to_le32(S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO);
 	ino->size = cpu_to_le64(UBIFS_INO_NODE_SZ);
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 5e1e8ec0589e..7fc2f3f07c16 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1599,6 +1599,7 @@ out_free:
 	vfree(c->ileb_buf);
 	vfree(c->sbuf);
 	kfree(c->bottom_up_buf);
+	kfree(c->sup_node);
 	ubifs_debugging_exit(c);
 	return err;
 }
@@ -1641,6 +1642,7 @@ static void ubifs_umount(struct ubifs_info *c)
 	vfree(c->ileb_buf);
 	vfree(c->sbuf);
 	kfree(c->bottom_up_buf);
+	kfree(c->sup_node);
 	ubifs_debugging_exit(c);
 }
 
diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h
index fb7f2c7bec9c..3fd85464abd5 100644
--- a/fs/udf/ecma_167.h
+++ b/fs/udf/ecma_167.h
@@ -4,7 +4,8 @@
  * This file is based on ECMA-167 3rd edition (June 1997)
  * http://www.ecma.ch
  *
- * Copyright (c) 2001-2002  Ben Fennema <bfennema@falcon.csc.calpoly.edu>
+ * Copyright (c) 2001-2002  Ben Fennema
+ * Copyright (c) 2017-2019  Pali Rohár <pali.rohar@gmail.com>
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -32,11 +33,19 @@
  * SUCH DAMAGE.
  */
 
+/**
+ * @file
+ * ECMA-167r3 defines and structure definitions
+ */
+
 #include <linux/types.h>
 
 #ifndef _ECMA_167_H
 #define _ECMA_167_H 1
 
+/* Character sets and coding - d-characters (ECMA 167r3 1/7.2) */
+typedef uint8_t		dchars;
+
 /* Character set specification (ECMA 167r3 1/7.2.1) */
 struct charspec {
 	uint8_t		charSetType;
@@ -54,6 +63,7 @@ struct charspec {
 #define CHARSPEC_TYPE_CS7		0x07	/* (1/7.2.9) */
 #define CHARSPEC_TYPE_CS8		0x08	/* (1/7.2.10) */
 
+/* Fixed-length character fields - d-string (EMCA 167r3 1/7.2.12) */
 typedef uint8_t		dstring;
 
 /* Timestamp (ECMA 167r3 1/7.3) */
@@ -85,22 +95,8 @@ struct regid {
 } __packed;
 
 /* Flags (ECMA 167r3 1/7.4.1) */
-#define ENTITYID_FLAGS_DIRTY		0x00
-#define ENTITYID_FLAGS_PROTECTED	0x01
-
-/* OSTA UDF 2.1.5.2 */
-#define UDF_ID_COMPLIANT "*OSTA UDF Compliant"
-
-/* OSTA UDF 2.1.5.3 */
-struct domainEntityIDSuffix {
-	uint16_t	revision;
-	uint8_t		flags;
-	uint8_t		reserved[5];
-};
-
-/* OSTA UDF 2.1.5.3 */
-#define ENTITYIDSUFFIX_FLAGS_HARDWRITEPROTECT 0
-#define ENTITYIDSUFFIX_FLAGS_SOFTWRITEPROTECT 1
+#define ENTITYID_FLAGS_DIRTY		0x01
+#define ENTITYID_FLAGS_PROTECTED	0x02
 
 /* Volume Structure Descriptor (ECMA 167r3 2/9.1) */
 #define VSD_STD_ID_LEN			5
@@ -202,6 +198,13 @@ struct NSRDesc {
 	uint8_t		structData[2040];
 } __packed;
 
+/* Generic Descriptor */
+struct genericDesc {
+	struct tag	descTag;
+	__le32		volDescSeqNum;
+	uint8_t		reserved[492];
+} __packed;
+
 /* Primary Volume Descriptor (ECMA 167r3 3/10.1) */
 struct primaryVolDesc {
 	struct tag		descTag;
@@ -316,7 +319,7 @@ struct genericPartitionMap {
 
 /* Partition Map Type (ECMA 167r3 3/10.7.1.1) */
 #define GP_PARTITION_MAP_TYPE_UNDEF	0x00
-#define GP_PARTIITON_MAP_TYPE_1		0x01
+#define GP_PARTITION_MAP_TYPE_1		0x01
 #define GP_PARTITION_MAP_TYPE_2		0x02
 
 /* Type 1 Partition Map (ECMA 167r3 3/10.7.2) */
@@ -723,6 +726,7 @@ struct appUseExtAttr {
 #define EXTATTR_DEV_SPEC		12
 #define EXTATTR_IMP_USE			2048
 #define EXTATTR_APP_USE			65536
+#define EXTATTR_SUBTYPE			1
 
 /* Unallocated Space Entry (ECMA 167r3 4/14.11) */
 struct unallocSpaceEntry {
@@ -754,10 +758,12 @@ struct partitionIntegrityEntry {
 /* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */
 
 /* Extent Length (ECMA 167r3 4/14.14.1.1) */
+#define EXT_LENGTH_MASK			0x3FFFFFFF
+#define EXT_TYPE_MASK			0xC0000000
 #define EXT_RECORDED_ALLOCATED		0x00000000
 #define EXT_NOT_RECORDED_ALLOCATED	0x40000000
 #define EXT_NOT_RECORDED_NOT_ALLOCATED	0x80000000
-#define EXT_NEXT_EXTENT_ALLOCDECS	0xC0000000
+#define EXT_NEXT_EXTENT_ALLOCDESCS	0xC0000000
 
 /* Long Allocation Descriptor (ECMA 167r3 4/14.14.2) */
 
@@ -774,7 +780,7 @@ struct pathComponent {
 	uint8_t		componentType;
 	uint8_t		lengthComponentIdent;
 	__le16		componentFileVersionNum;
-	dstring		componentIdent[0];
+	dchars		componentIdent[0];
 } __packed;
 
 /* File Entry (ECMA 167r3 4/14.17) */
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index ea80036d7897..e875bc5668ee 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1981,10 +1981,10 @@ int udf_setup_indirect_aext(struct inode *inode, udf_pblk_t block,
 
 		__udf_add_aext(inode, &nepos, &cp_loc, cp_len, 1);
 		udf_write_aext(inode, epos, &nepos.block,
-			       sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0);
+			       sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDESCS, 0);
 	} else {
 		__udf_add_aext(inode, epos, &nepos.block,
-			       sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDECS, 0);
+			       sb->s_blocksize | EXT_NEXT_EXTENT_ALLOCDESCS, 0);
 	}
 
 	brelse(epos->bh);
@@ -2143,7 +2143,7 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
 	unsigned int indirections = 0;
 
 	while ((etype = udf_current_aext(inode, epos, eloc, elen, inc)) ==
-	       (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
+	       (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) {
 		udf_pblk_t block;
 
 		if (++indirections > UDF_MAX_INDIR_EXTS) {
diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h
index a4da59e38b7f..35e61b2cacfe 100644
--- a/fs/udf/osta_udf.h
+++ b/fs/udf/osta_udf.h
@@ -1,10 +1,11 @@
 /*
  * osta_udf.h
  *
- * This file is based on OSTA UDF(tm) 2.50 (April 30, 2003)
+ * This file is based on OSTA UDF(tm) 2.60 (March 1, 2005)
  * http://www.osta.org
  *
- * Copyright (c) 2001-2004  Ben Fennema <bfennema@falcon.csc.calpoly.edu>
+ * Copyright (c) 2001-2004  Ben Fennema
+ * Copyright (c) 2017-2019  Pali Rohár <pali.rohar@gmail.com>
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -32,38 +33,57 @@
  * SUCH DAMAGE.
  */
 
+/**
+ * @file
+ * OSTA-UDF defines and structure definitions
+ */
+
 #include "ecma_167.h"
 
 #ifndef _OSTA_UDF_H
 #define _OSTA_UDF_H 1
 
-/* OSTA CS0 Charspec (UDF 2.50 2.1.2) */
+/* OSTA CS0 Charspec (UDF 2.60 2.1.2) */
 #define UDF_CHAR_SET_TYPE		0
 #define UDF_CHAR_SET_INFO		"OSTA Compressed Unicode"
 
-/* Entity Identifier (UDF 2.50 2.1.5) */
-/* Identifiers (UDF 2.50 2.1.5.2) */
+/* Entity Identifier (UDF 2.60 2.1.5) */
+/* Identifiers (UDF 2.60 2.1.5.2) */
+/* Implementation Use Extended Attribute (UDF 2.60 3.3.4.5) */
+/* Virtual Allocation Table (UDF 1.50 2.2.10) */
+/* Logical Volume Extended Information (UDF 1.50 Errata, DCN 5003, 3.3.4.5.1.3) */
+/* OS2EA (UDF 1.50 3.3.4.5.3.1) */
+/* MacUniqueIDTable (UDF 1.50 3.3.4.5.4.3) */
+/* MacResourceFork (UDF 1.50 3.3.4.5.4.4) */
 #define UDF_ID_DEVELOPER		"*Linux UDFFS"
 #define	UDF_ID_COMPLIANT		"*OSTA UDF Compliant"
 #define UDF_ID_LV_INFO			"*UDF LV Info"
 #define UDF_ID_FREE_EA			"*UDF FreeEASpace"
 #define UDF_ID_FREE_APP_EA		"*UDF FreeAppEASpace"
 #define UDF_ID_DVD_CGMS			"*UDF DVD CGMS Info"
+#define UDF_ID_VAT_LVEXTENSION		"*UDF VAT LVExtension"
 #define UDF_ID_OS2_EA			"*UDF OS/2 EA"
 #define UDF_ID_OS2_EA_LENGTH		"*UDF OS/2 EALength"
 #define UDF_ID_MAC_VOLUME		"*UDF Mac VolumeInfo"
 #define UDF_ID_MAC_FINDER		"*UDF Mac FinderInfo"
 #define UDF_ID_MAC_UNIQUE		"*UDF Mac UniqueIDTable"
 #define UDF_ID_MAC_RESOURCE		"*UDF Mac ResourceFork"
+#define UDF_ID_OS400_DIRINFO		"*UDF OS/400 DirInfo"
 #define UDF_ID_VIRTUAL			"*UDF Virtual Partition"
 #define UDF_ID_SPARABLE			"*UDF Sparable Partition"
 #define UDF_ID_ALLOC			"*UDF Virtual Alloc Tbl"
 #define UDF_ID_SPARING			"*UDF Sparing Table"
 #define UDF_ID_METADATA			"*UDF Metadata Partition"
 
-/* Identifier Suffix (UDF 2.50 2.1.5.3) */
-#define IS_DF_HARD_WRITE_PROTECT	0x01
-#define IS_DF_SOFT_WRITE_PROTECT	0x02
+/* Identifier Suffix (UDF 2.60 2.1.5.3) */
+#define DOMAIN_FLAGS_HARD_WRITE_PROTECT	0x01
+#define DOMAIN_FLAGS_SOFT_WRITE_PROTECT	0x02
+
+struct domainIdentSuffix {
+	__le16		UDFRevision;
+	uint8_t		domainFlags;
+	uint8_t		reserved[5];
+} __packed;
 
 struct UDFIdentSuffix {
 	__le16		UDFRevision;
@@ -75,15 +95,15 @@ struct UDFIdentSuffix {
 struct impIdentSuffix {
 	uint8_t		OSClass;
 	uint8_t		OSIdentifier;
-	uint8_t		reserved[6];
+	uint8_t		impUse[6];
 } __packed;
 
 struct appIdentSuffix {
 	uint8_t		impUse[8];
 } __packed;
 
-/* Logical Volume Integrity Descriptor (UDF 2.50 2.2.6) */
-/* Implementation Use (UDF 2.50 2.2.6.4) */
+/* Logical Volume Integrity Descriptor (UDF 2.60 2.2.6) */
+/* Implementation Use (UDF 2.60 2.2.6.4) */
 struct logicalVolIntegrityDescImpUse {
 	struct regid	impIdent;
 	__le32		numFiles;
@@ -94,8 +114,8 @@ struct logicalVolIntegrityDescImpUse {
 	uint8_t		impUse[0];
 } __packed;
 
-/* Implementation Use Volume Descriptor (UDF 2.50 2.2.7) */
-/* Implementation Use (UDF 2.50 2.2.7.2) */
+/* Implementation Use Volume Descriptor (UDF 2.60 2.2.7) */
+/* Implementation Use (UDF 2.60 2.2.7.2) */
 struct impUseVolDescImpUse {
 	struct charspec	LVICharset;
 	dstring		logicalVolIdent[128];
@@ -115,7 +135,7 @@ struct udfPartitionMap2 {
 	__le16		partitionNum;
 } __packed;
 
-/* Virtual Partition Map (UDF 2.50 2.2.8) */
+/* Virtual Partition Map (UDF 2.60 2.2.8) */
 struct virtualPartitionMap {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
@@ -126,7 +146,7 @@ struct virtualPartitionMap {
 	uint8_t		reserved2[24];
 } __packed;
 
-/* Sparable Partition Map (UDF 2.50 2.2.9) */
+/* Sparable Partition Map (UDF 2.60 2.2.9) */
 struct sparablePartitionMap {
 	uint8_t partitionMapType;
 	uint8_t partitionMapLength;
@@ -141,7 +161,7 @@ struct sparablePartitionMap {
 	__le32 locSparingTable[4];
 } __packed;
 
-/* Metadata Partition Map (UDF 2.4.0 2.2.10) */
+/* Metadata Partition Map (UDF 2.60 2.2.10) */
 struct metadataPartitionMap {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
@@ -160,14 +180,14 @@ struct metadataPartitionMap {
 
 /* Virtual Allocation Table (UDF 1.5 2.2.10) */
 struct virtualAllocationTable15 {
-	__le32		VirtualSector[0];
+	__le32		vatEntry[0];
 	struct regid	vatIdent;
 	__le32		previousVATICBLoc;
 } __packed;
 
 #define ICBTAG_FILE_TYPE_VAT15		0x00U
 
-/* Virtual Allocation Table (UDF 2.50 2.2.11) */
+/* Virtual Allocation Table (UDF 2.60 2.2.11) */
 struct virtualAllocationTable20 {
 	__le16		lengthHeader;
 	__le16		lengthImpUse;
@@ -175,9 +195,9 @@ struct virtualAllocationTable20 {
 	__le32		previousVATICBLoc;
 	__le32		numFiles;
 	__le32		numDirs;
-	__le16		minReadRevision;
-	__le16		minWriteRevision;
-	__le16		maxWriteRevision;
+	__le16		minUDFReadRev;
+	__le16		minUDFWriteRev;
+	__le16		maxUDFWriteRev;
 	__le16		reserved;
 	uint8_t		impUse[0];
 	__le32		vatEntry[0];
@@ -185,7 +205,7 @@ struct virtualAllocationTable20 {
 
 #define ICBTAG_FILE_TYPE_VAT20		0xF8U
 
-/* Sparing Table (UDF 2.50 2.2.12) */
+/* Sparing Table (UDF 2.60 2.2.12) */
 struct sparingEntry {
 	__le32		origLocation;
 	__le32		mappedLocation;
@@ -201,12 +221,12 @@ struct sparingTable {
 			mapEntry[0];
 } __packed;
 
-/* Metadata File (and Metadata Mirror File) (UDF 2.50 2.2.13.1) */
+/* Metadata File (and Metadata Mirror File) (UDF 2.60 2.2.13.1) */
 #define ICBTAG_FILE_TYPE_MAIN		0xFA
 #define ICBTAG_FILE_TYPE_MIRROR		0xFB
 #define ICBTAG_FILE_TYPE_BITMAP		0xFC
 
-/* struct struct long_ad ICB - ADImpUse (UDF 2.50 2.2.4.3) */
+/* struct struct long_ad ICB - ADImpUse (UDF 2.60 2.2.4.3) */
 struct allocDescImpUse {
 	__le16		flags;
 	uint8_t		impUse[4];
@@ -214,17 +234,17 @@ struct allocDescImpUse {
 
 #define AD_IU_EXT_ERASED		0x0001
 
-/* Real-Time Files (UDF 2.50 6.11) */
+/* Real-Time Files (UDF 2.60 6.11) */
 #define ICBTAG_FILE_TYPE_REALTIME	0xF9U
 
-/* Implementation Use Extended Attribute (UDF 2.50 3.3.4.5) */
-/* FreeEASpace (UDF 2.50 3.3.4.5.1.1) */
+/* Implementation Use Extended Attribute (UDF 2.60 3.3.4.5) */
+/* FreeEASpace (UDF 2.60 3.3.4.5.1.1) */
 struct freeEaSpace {
 	__le16		headerChecksum;
 	uint8_t		freeEASpace[0];
 } __packed;
 
-/* DVD Copyright Management Information (UDF 2.50 3.3.4.5.1.2) */
+/* DVD Copyright Management Information (UDF 2.60 3.3.4.5.1.2) */
 struct DVDCopyrightImpUse {
 	__le16		headerChecksum;
 	uint8_t		CGMSInfo;
@@ -232,20 +252,35 @@ struct DVDCopyrightImpUse {
 	uint8_t		protectionSystemInfo[4];
 } __packed;
 
-/* Application Use Extended Attribute (UDF 2.50 3.3.4.6) */
-/* FreeAppEASpace (UDF 2.50 3.3.4.6.1) */
+/* Logical Volume Extended Information (UDF 1.50 Errata, DCN 5003, 3.3.4.5.1.3) */
+struct LVExtensionEA {
+	__le16		headerChecksum;
+	__le64		verificationID;
+	__le32		numFiles;
+	__le32		numDirs;
+	dstring		logicalVolIdent[128];
+} __packed;
+
+/* Application Use Extended Attribute (UDF 2.60 3.3.4.6) */
+/* FreeAppEASpace (UDF 2.60 3.3.4.6.1) */
 struct freeAppEASpace {
 	__le16		headerChecksum;
 	uint8_t		freeEASpace[0];
 } __packed;
 
-/* UDF Defined System Stream (UDF 2.50 3.3.7) */
+/* UDF Defined System Stream (UDF 2.60 3.3.7) */
 #define UDF_ID_UNIQUE_ID		"*UDF Unique ID Mapping Data"
 #define UDF_ID_NON_ALLOC		"*UDF Non-Allocatable Space"
 #define UDF_ID_POWER_CAL		"*UDF Power Cal Table"
 #define UDF_ID_BACKUP			"*UDF Backup"
 
-/* Operating System Identifiers (UDF 2.50 6.3) */
+/* UDF Defined Non-System Streams (UDF 2.60 3.3.8) */
+#define UDF_ID_MAC_RESOURCE_FORK_STREAM	"*UDF Macintosh Resource Fork"
+/* #define UDF_ID_OS2_EA		"*UDF OS/2 EA" */
+#define UDF_ID_NT_ACL			"*UDF NT ACL"
+#define UDF_ID_UNIX_ACL			"*UDF UNIX ACL"
+
+/* Operating System Identifiers (UDF 2.60 6.3) */
 #define UDF_OS_CLASS_UNDEF		0x00U
 #define UDF_OS_CLASS_DOS		0x01U
 #define UDF_OS_CLASS_OS2		0x02U
@@ -270,6 +305,7 @@ struct freeAppEASpace {
 #define UDF_OS_ID_LINUX			0x05U
 #define UDF_OS_ID_MKLINUX		0x06U
 #define UDF_OS_ID_FREEBSD		0x07U
+#define UDF_OS_ID_NETBSD		0x08U
 #define UDF_OS_ID_WIN9X			0x00U
 #define UDF_OS_ID_WINNT			0x00U
 #define UDF_OS_ID_OS400			0x00U
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 8c28e93e9b73..f747bf72edbe 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -767,20 +767,20 @@ static int udf_check_vsd(struct super_block *sb)
 static int udf_verify_domain_identifier(struct super_block *sb,
 					struct regid *ident, char *dname)
 {
-	struct domainEntityIDSuffix *suffix;
+	struct domainIdentSuffix *suffix;
 
 	if (memcmp(ident->ident, UDF_ID_COMPLIANT, strlen(UDF_ID_COMPLIANT))) {
 		udf_warn(sb, "Not OSTA UDF compliant %s descriptor.\n", dname);
 		goto force_ro;
 	}
-	if (ident->flags & (1 << ENTITYID_FLAGS_DIRTY)) {
+	if (ident->flags & ENTITYID_FLAGS_DIRTY) {
 		udf_warn(sb, "Possibly not OSTA UDF compliant %s descriptor.\n",
 			 dname);
 		goto force_ro;
 	}
-	suffix = (struct domainEntityIDSuffix *)ident->identSuffix;
-	if (suffix->flags & (1 << ENTITYIDSUFFIX_FLAGS_HARDWRITEPROTECT) ||
-	    suffix->flags & (1 << ENTITYIDSUFFIX_FLAGS_SOFTWRITEPROTECT)) {
+	suffix = (struct domainIdentSuffix *)ident->identSuffix;
+	if ((suffix->domainFlags & DOMAIN_FLAGS_HARD_WRITE_PROTECT) ||
+	    (suffix->domainFlags & DOMAIN_FLAGS_SOFT_WRITE_PROTECT)) {
 		if (!sb_rdonly(sb)) {
 			udf_warn(sb, "Descriptor for %s marked write protected."
 				 " Forcing read only mount.\n", dname);
@@ -1035,7 +1035,6 @@ static int check_partition_desc(struct super_block *sb,
 	switch (le32_to_cpu(p->accessType)) {
 	case PD_ACCESS_TYPE_READ_ONLY:
 	case PD_ACCESS_TYPE_WRITE_ONCE:
-	case PD_ACCESS_TYPE_REWRITABLE:
 	case PD_ACCESS_TYPE_NONE:
 		goto force_ro;
 	}
@@ -1063,7 +1062,8 @@ static int check_partition_desc(struct super_block *sb,
 		goto force_ro;
 
 	if (map->s_partition_type == UDF_VIRTUAL_MAP15 ||
-	    map->s_partition_type == UDF_VIRTUAL_MAP20)
+	    map->s_partition_type == UDF_VIRTUAL_MAP20 ||
+	    map->s_partition_type == UDF_METADATA_MAP25)
 		goto force_ro;
 
 	return 0;
@@ -2402,6 +2402,10 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->s_partmaps[sbi->s_partition].s_partition_len;
 	buf->f_bfree = udf_count_free(sb);
 	buf->f_bavail = buf->f_bfree;
+	/*
+	 * Let's pretend each free block is also a free 'inode' since UDF does
+	 * not have separate preallocated table of inodes.
+	 */
 	buf->f_files = (lvidiu != NULL ? (le32_to_cpu(lvidiu->numFiles) +
 					  le32_to_cpu(lvidiu->numDirs)) : 0)
 			+ buf->f_bfree;
@@ -2492,17 +2496,29 @@ static unsigned int udf_count_free_table(struct super_block *sb,
 static unsigned int udf_count_free(struct super_block *sb)
 {
 	unsigned int accum = 0;
-	struct udf_sb_info *sbi;
+	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct udf_part_map *map;
+	unsigned int part = sbi->s_partition;
+	int ptype = sbi->s_partmaps[part].s_partition_type;
+
+	if (ptype == UDF_METADATA_MAP25) {
+		part = sbi->s_partmaps[part].s_type_specific.s_metadata.
+							s_phys_partition_ref;
+	} else if (ptype == UDF_VIRTUAL_MAP15 || ptype == UDF_VIRTUAL_MAP20) {
+		/*
+		 * Filesystems with VAT are append-only and we cannot write to
+ 		 * them. Let's just report 0 here.
+		 */
+		return 0;
+	}
 
-	sbi = UDF_SB(sb);
 	if (sbi->s_lvid_bh) {
 		struct logicalVolIntegrityDesc *lvid =
 			(struct logicalVolIntegrityDesc *)
 			sbi->s_lvid_bh->b_data;
-		if (le32_to_cpu(lvid->numOfPartitions) > sbi->s_partition) {
+		if (le32_to_cpu(lvid->numOfPartitions) > part) {
 			accum = le32_to_cpu(
-					lvid->freeSpaceTable[sbi->s_partition]);
+					lvid->freeSpaceTable[part]);
 			if (accum == 0xFFFFFFFF)
 				accum = 0;
 		}
@@ -2511,7 +2527,7 @@ static unsigned int udf_count_free(struct super_block *sb)
 	if (accum)
 		return accum;
 
-	map = &sbi->s_partmaps[sbi->s_partition];
+	map = &sbi->s_partmaps[part];
 	if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
 		accum += udf_count_free_bitmap(sb,
 					       map->s_uspace.s_bitmap);
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 63a47f1e1d52..532cda99644e 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -241,7 +241,7 @@ int udf_truncate_extents(struct inode *inode)
 
 	while ((etype = udf_current_aext(inode, &epos, &eloc,
 					 &elen, 0)) != -1) {
-		if (etype == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
+		if (etype == (EXT_NEXT_EXTENT_ALLOCDESCS >> 30)) {
 			udf_write_aext(inode, &epos, &neloc, nelen, 0);
 			if (indirect_ext_len) {
 				/* We managed to free all extents in the
diff --git a/fs/utimes.c b/fs/utimes.c
index c952b6b3d8a0..1d17ce98cb80 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -36,14 +36,14 @@ static int utimes_common(const struct path *path, struct timespec64 *times)
 		if (times[0].tv_nsec == UTIME_OMIT)
 			newattrs.ia_valid &= ~ATTR_ATIME;
 		else if (times[0].tv_nsec != UTIME_NOW) {
-			newattrs.ia_atime = timestamp_truncate(times[0], inode);
+			newattrs.ia_atime = times[0];
 			newattrs.ia_valid |= ATTR_ATIME_SET;
 		}
 
 		if (times[1].tv_nsec == UTIME_OMIT)
 			newattrs.ia_valid &= ~ATTR_MTIME;
 		else if (times[1].tv_nsec != UTIME_NOW) {
-			newattrs.ia_mtime = timestamp_truncate(times[1], inode);
+			newattrs.ia_mtime = times[1];
 			newattrs.ia_valid |= ATTR_MTIME_SET;
 		}
 		/*
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 0d7fcc983b3d..e6149720ce02 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -62,6 +62,7 @@ xfs_attr_args_init(
 	struct xfs_da_args	*args,
 	struct xfs_inode	*dp,
 	const unsigned char	*name,
+	size_t			namelen,
 	int			flags)
 {
 
@@ -74,7 +75,7 @@ xfs_attr_args_init(
 	args->dp = dp;
 	args->flags = flags;
 	args->name = name;
-	args->namelen = strlen((const char *)name);
+	args->namelen = namelen;
 	if (args->namelen >= MAXNAMELEN)
 		return -EFAULT;		/* match IRIX behaviour */
 
@@ -139,6 +140,7 @@ int
 xfs_attr_get(
 	struct xfs_inode	*ip,
 	const unsigned char	*name,
+	size_t			namelen,
 	unsigned char		**value,
 	int			*valuelenp,
 	int			flags)
@@ -154,7 +156,7 @@ xfs_attr_get(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	error = xfs_attr_args_init(&args, ip, name, flags);
+	error = xfs_attr_args_init(&args, ip, name, namelen, flags);
 	if (error)
 		return error;
 
@@ -338,6 +340,7 @@ int
 xfs_attr_set(
 	struct xfs_inode	*dp,
 	const unsigned char	*name,
+	size_t			namelen,
 	unsigned char		*value,
 	int			valuelen,
 	int			flags)
@@ -353,7 +356,7 @@ xfs_attr_set(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	error = xfs_attr_args_init(&args, dp, name, flags);
+	error = xfs_attr_args_init(&args, dp, name, namelen, flags);
 	if (error)
 		return error;
 
@@ -442,6 +445,7 @@ int
 xfs_attr_remove(
 	struct xfs_inode	*dp,
 	const unsigned char	*name,
+	size_t			namelen,
 	int			flags)
 {
 	struct xfs_mount	*mp = dp->i_mount;
@@ -453,7 +457,7 @@ xfs_attr_remove(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	error = xfs_attr_args_init(&args, dp, name, flags);
+	error = xfs_attr_args_init(&args, dp, name, namelen, flags);
 	if (error)
 		return error;
 
@@ -1007,7 +1011,7 @@ restart:
 		 * The INCOMPLETE flag means that we will find the "old"
 		 * attr, not the "new" one.
 		 */
-		args->flags |= XFS_ATTR_INCOMPLETE;
+		args->op_flags |= XFS_DA_OP_INCOMPLETE;
 		state = xfs_da_state_alloc();
 		state->args = args;
 		state->mp = mp;
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 94badfa1743e..4243b2272642 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -26,7 +26,7 @@ struct xfs_attr_list_context;
  *========================================================================*/
 
 
-#define ATTR_DONTFOLLOW	0x0001	/* -- unused, from IRIX -- */
+#define ATTR_DONTFOLLOW	0x0001	/* -- ignored, from IRIX -- */
 #define ATTR_ROOT	0x0002	/* use attrs in root (trusted) namespace */
 #define ATTR_TRUST	0x0004	/* -- unused, from IRIX -- */
 #define ATTR_SECURE	0x0008	/* use attrs in security namespace */
@@ -37,7 +37,10 @@ struct xfs_attr_list_context;
 #define ATTR_KERNOVAL	0x2000	/* [kernel] get attr size only, not value */
 
 #define ATTR_INCOMPLETE	0x4000	/* [kernel] return INCOMPLETE attr keys */
-#define ATTR_ALLOC	0x8000	/* allocate xattr buffer on demand */
+#define ATTR_ALLOC	0x8000	/* [kernel] allocate xattr buffer on demand */
+
+#define ATTR_KERNEL_FLAGS \
+	(ATTR_KERNOTIME | ATTR_KERNOVAL | ATTR_INCOMPLETE | ATTR_ALLOC)
 
 #define XFS_ATTR_FLAGS \
 	{ ATTR_DONTFOLLOW, 	"DONTFOLLOW" }, \
@@ -145,11 +148,13 @@ int xfs_attr_list_int(struct xfs_attr_list_context *);
 int xfs_inode_hasattr(struct xfs_inode *ip);
 int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args);
 int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
-		 unsigned char **value, int *valuelenp, int flags);
+		 size_t namelen, unsigned char **value, int *valuelenp,
+		 int flags);
 int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
-		 unsigned char *value, int valuelen, int flags);
+		 size_t namelen, unsigned char *value, int valuelen, int flags);
 int xfs_attr_set_args(struct xfs_da_args *args);
-int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
+int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name,
+		    size_t namelen, int flags);
 int xfs_attr_remove_args(struct xfs_da_args *args);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		  int flags, struct attrlist_cursor_kern *cursor);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 08d4b10ae2d5..fed537a4353d 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -2403,8 +2403,8 @@ xfs_attr3_leaf_lookup_int(
 		 * If we are looking for INCOMPLETE entries, show only those.
 		 * If we are looking for complete entries, show only those.
 		 */
-		if ((args->flags & XFS_ATTR_INCOMPLETE) !=
-		    (entry->flags & XFS_ATTR_INCOMPLETE)) {
+		if (!!(args->op_flags & XFS_DA_OP_INCOMPLETE) !=
+		    !!(entry->flags & XFS_ATTR_INCOMPLETE)) {
 			continue;
 		}
 		if (entry->flags & XFS_ATTR_LOCAL) {
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index f4a188e28b7b..73615b1dd1a8 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -39,15 +39,6 @@ struct xfs_attr3_icleaf_hdr {
 	} freemap[XFS_ATTR_LEAF_MAPSIZE];
 };
 
-/*
- * Used to keep a list of "remote value" extents when unlinking an inode.
- */
-typedef struct xfs_attr_inactive_list {
-	xfs_dablk_t	valueblk;	/* block number of value bytes */
-	int		valuelen;	/* number of bytes in value */
-} xfs_attr_inactive_list_t;
-
-
 /*========================================================================
  * Function prototypes for the kernel.
  *========================================================================*/
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index a6ef5df42669..a266d05df146 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -26,6 +26,23 @@
 #define ATTR_RMTVALUE_MAPSIZE	1	/* # of map entries at once */
 
 /*
+ * Remote Attribute Values
+ * =======================
+ *
+ * Remote extended attribute values are conceptually simple -- they're written
+ * to data blocks mapped by an inode's attribute fork, and they have an upper
+ * size limit of 64k.  Setting a value does not involve the XFS log.
+ *
+ * However, on a v5 filesystem, maximally sized remote attr values require one
+ * block more than 64k worth of space to hold both the remote attribute value
+ * header (64 bytes).  On a 4k block filesystem this results in a 68k buffer;
+ * on a 64k block filesystem, this would be a 128k buffer.  Note that the log
+ * format can only handle a dirty buffer of XFS_MAX_BLOCKSIZE length (64k).
+ * Therefore, we /must/ ensure that remote attribute value buffers never touch
+ * the logging system and therefore never have a log item.
+ */
+
+/*
  * Each contiguous block has a header, so it is not just a simple attribute
  * length to FSB conversion.
  */
@@ -401,17 +418,25 @@ xfs_attr_rmtval_get(
 			       (map[i].br_startblock != HOLESTARTBLOCK));
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			error = xfs_trans_read_buf(mp, args->trans,
-						   mp->m_ddev_targp,
-						   dblkno, dblkcnt, 0, &bp,
-						   &xfs_attr3_rmt_buf_ops);
-			if (error)
+			bp = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, 0,
+					&xfs_attr3_rmt_buf_ops);
+			if (!bp)
+				return -ENOMEM;
+			error = bp->b_error;
+			if (error) {
+				xfs_buf_ioerror_alert(bp, __func__);
+				xfs_buf_relse(bp);
+
+				/* bad CRC means corrupted metadata */
+				if (error == -EFSBADCRC)
+					error = -EFSCORRUPTED;
 				return error;
+			}
 
 			error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
 							&offset, &valuelen,
 							&dst);
-			xfs_trans_brelse(args->trans, bp);
+			xfs_buf_relse(bp);
 			if (error)
 				return error;
 
@@ -552,6 +577,33 @@ xfs_attr_rmtval_set(
 	return 0;
 }
 
+/* Mark stale any incore buffers for the remote value. */
+int
+xfs_attr_rmtval_stale(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*map,
+	xfs_buf_flags_t		incore_flags)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_buf		*bp;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
+	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
+		return -EFSCORRUPTED;
+
+	bp = xfs_buf_incore(mp->m_ddev_targp,
+			XFS_FSB_TO_DADDR(mp, map->br_startblock),
+			XFS_FSB_TO_BB(mp, map->br_blockcount), incore_flags);
+	if (bp) {
+		xfs_buf_stale(bp);
+		xfs_buf_relse(bp);
+	}
+
+	return 0;
+}
+
 /*
  * Remove the value associated with an attribute by deleting the
  * out-of-line buffer that it is stored on.
@@ -560,7 +612,6 @@ int
 xfs_attr_rmtval_remove(
 	struct xfs_da_args	*args)
 {
-	struct xfs_mount	*mp = args->dp->i_mount;
 	xfs_dablk_t		lblkno;
 	int			blkcnt;
 	int			error;
@@ -575,9 +626,6 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	while (blkcnt > 0) {
 		struct xfs_bmbt_irec	map;
-		struct xfs_buf		*bp;
-		xfs_daddr_t		dblkno;
-		int			dblkcnt;
 		int			nmap;
 
 		/*
@@ -588,22 +636,11 @@ xfs_attr_rmtval_remove(
 				       blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
 		if (error)
 			return error;
-		ASSERT(nmap == 1);
-		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
-		       (map.br_startblock != HOLESTARTBLOCK));
-
-		dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
-		dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
-
-		/*
-		 * If the "remote" value is in the cache, remove it.
-		 */
-		bp = xfs_buf_incore(mp->m_ddev_targp, dblkno, dblkcnt, XBF_TRYLOCK);
-		if (bp) {
-			xfs_buf_stale(bp);
-			xfs_buf_relse(bp);
-			bp = NULL;
-		}
+		if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1))
+			return -EFSCORRUPTED;
+		error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK);
+		if (error)
+			return error;
 
 		lblkno += map.br_blockcount;
 		blkcnt -= map.br_blockcount;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.h b/fs/xfs/libxfs/xfs_attr_remote.h
index 9d20b66ad379..6fb4572845ce 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.h
+++ b/fs/xfs/libxfs/xfs_attr_remote.h
@@ -11,5 +11,7 @@ int xfs_attr3_rmt_blocks(struct xfs_mount *mp, int attrlen);
 int xfs_attr_rmtval_get(struct xfs_da_args *args);
 int xfs_attr_rmtval_set(struct xfs_da_args *args);
 int xfs_attr_rmtval_remove(struct xfs_da_args *args);
+int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
+		xfs_buf_flags_t incore_flags);
 
 #endif /* __XFS_ATTR_REMOTE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index e2cc98931552..b22c7e928eb1 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2389,8 +2389,6 @@ xfs_btree_lshift(
 	XFS_BTREE_STATS_ADD(cur, moves, rrecs - 1);
 	if (level > 0) {
 		/* It's a nonleaf. operate on keys and ptrs */
-		int			i;		/* loop index */
-
 		for (i = 0; i < rrecs; i++) {
 			error = xfs_btree_debug_check_ptr(cur, rpp, i + 1, level);
 			if (error)
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index e16610d1c14f..0f4fbb0889ff 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -89,6 +89,7 @@ typedef struct xfs_da_args {
 #define XFS_DA_OP_OKNOENT	0x0008	/* lookup/add op, ENOENT ok, else die */
 #define XFS_DA_OP_CILOOKUP	0x0010	/* lookup to return CI name if found */
 #define XFS_DA_OP_ALLOCVAL	0x0020	/* lookup to alloc buffer if found  */
+#define XFS_DA_OP_INCOMPLETE	0x0040	/* lookup INCOMPLETE attr keys */
 
 #define XFS_DA_OP_FLAGS \
 	{ XFS_DA_OP_JUSTCHECK,	"JUSTCHECK" }, \
@@ -96,7 +97,8 @@ typedef struct xfs_da_args {
 	{ XFS_DA_OP_ADDNAME,	"ADDNAME" }, \
 	{ XFS_DA_OP_OKNOENT,	"OKNOENT" }, \
 	{ XFS_DA_OP_CILOOKUP,	"CILOOKUP" }, \
-	{ XFS_DA_OP_ALLOCVAL,	"ALLOCVAL" }
+	{ XFS_DA_OP_ALLOCVAL,	"ALLOCVAL" }, \
+	{ XFS_DA_OP_INCOMPLETE,	"INCOMPLETE" }
 
 /*
  * Storage for holding state during Btree searches and split/join ops.
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 3dee33043e09..734837a9b51a 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -217,7 +217,7 @@ typedef struct xfs_dir2_sf_entry {
 	 * A 64-bit or 32-bit inode number follows here, at a variable offset
 	 * after the name.
 	 */
-} xfs_dir2_sf_entry_t;
+} __packed xfs_dir2_sf_entry_t;
 
 static inline int xfs_dir2_sf_hdr_size(int i8count)
 {
@@ -683,8 +683,6 @@ struct xfs_attr3_leafblock {
 
 /*
  * Flags used in the leaf_entry[i].flags field.
- * NOTE: the INCOMPLETE bit must not collide with the flags bits specified
- * on the system call, they are "or"ed together for various operations.
  */
 #define	XFS_ATTR_LOCAL_BIT	0	/* attr is stored locally */
 #define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 1b7dcbae051c..77e9fa385980 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1540,6 +1540,13 @@ typedef struct xfs_bmdr_block {
 #define BMBT_BLOCKCOUNT_BITLEN	21
 
 #define BMBT_STARTOFF_MASK	((1ULL << BMBT_STARTOFF_BITLEN) - 1)
+#define BMBT_BLOCKCOUNT_MASK	((1ULL << BMBT_BLOCKCOUNT_BITLEN) - 1)
+
+/*
+ * bmbt records have a file offset (block) field that is 54 bits wide, so this
+ * is the largest xfs_fileoff_t that we ever expect to see.
+ */
+#define XFS_MAX_FILEOFF		(BMBT_STARTOFF_MASK + BMBT_BLOCKCOUNT_MASK)
 
 typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 8ef31d71a9c7..9bac0d2e56dc 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -462,11 +462,20 @@ static inline uint xfs_log_dinode_size(int version)
 #define	XFS_BLF_GDQUOT_BUF	(1<<4)
 
 /*
- * This is the structure used to lay out a buf log item in the
- * log.  The data map describes which 128 byte chunks of the buffer
- * have been logged.
- */
-#define XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+ * This is the structure used to lay out a buf log item in the log.  The data
+ * map describes which 128 byte chunks of the buffer have been logged.
+ *
+ * The placement of blf_map_size causes blf_data_map to start at an odd
+ * multiple of sizeof(unsigned int) offset within the struct.  Because the data
+ * bitmap size will always be an even number, the end of the data_map (and
+ * therefore the structure) will also be at an odd multiple of sizeof(unsigned
+ * int).  Some 64-bit compilers will insert padding at the end of the struct to
+ * ensure 64-bit alignment of blf_blkno, but 32-bit ones will not.  Therefore,
+ * XFS_BLF_DATAMAP_SIZE must be an odd number to make the padding explicit and
+ * keep the structure size consistent between 32-bit and 64-bit platforms.
+ */
+#define __XFS_BLF_DATAMAP_SIZE	((XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK) / NBWORD)
+#define XFS_BLF_DATAMAP_SIZE	(__XFS_BLF_DATAMAP_SIZE + 1)
 
 typedef struct xfs_buf_log_format {
 	unsigned short	blf_type;	/* buf log item type indicator */
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 60c61d7052a8..c3422403b169 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -75,7 +75,6 @@ static inline xfs_extlen_t
 xrep_calc_ag_resblks(
 	struct xfs_scrub	*sc)
 {
-	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 91693fce34a8..cd743fad8478 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -145,7 +145,8 @@ xfs_get_acl(struct inode *inode, int type)
 	 * go out to the disk.
 	 */
 	len = XFS_ACL_MAX_SIZE(ip->i_mount);
-	error = xfs_attr_get(ip, ea_name, (unsigned char **)&xfs_acl, &len,
+	error = xfs_attr_get(ip, ea_name, strlen(ea_name),
+				(unsigned char **)&xfs_acl, &len,
 				ATTR_ALLOC | ATTR_ROOT);
 	if (error) {
 		/*
@@ -196,15 +197,17 @@ __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		len -= sizeof(struct xfs_acl_entry) *
 			 (XFS_ACL_MAX_ENTRIES(ip->i_mount) - acl->a_count);
 
-		error = xfs_attr_set(ip, ea_name, (unsigned char *)xfs_acl,
-				len, ATTR_ROOT);
+		error = xfs_attr_set(ip, ea_name, strlen(ea_name),
+				     (unsigned char *)xfs_acl, len, ATTR_ROOT);
 
 		kmem_free(xfs_acl);
 	} else {
 		/*
 		 * A NULL ACL argument means we want to remove the ACL.
 		 */
-		error = xfs_attr_remove(ip, ea_name, ATTR_ROOT);
+		error = xfs_attr_remove(ip, ea_name,
+					strlen(ea_name),
+					ATTR_ROOT);
 
 		/*
 		 * If the attribute didn't exist to start with that's fine.
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 5ff49523d8ea..8fbb841cd6fe 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -25,22 +25,18 @@
 #include "xfs_error.h"
 
 /*
- * Look at all the extents for this logical region,
- * invalidate any buffers that are incore/in transactions.
+ * Invalidate any incore buffers associated with this remote attribute value
+ * extent.   We never log remote attribute value buffers, which means that they
+ * won't be attached to a transaction and are therefore safe to mark stale.
+ * The actual bunmapi will be taken care of later.
  */
 STATIC int
-xfs_attr3_leaf_freextent(
-	struct xfs_trans	**trans,
+xfs_attr3_rmt_stale(
 	struct xfs_inode	*dp,
 	xfs_dablk_t		blkno,
 	int			blkcnt)
 {
 	struct xfs_bmbt_irec	map;
-	struct xfs_buf		*bp;
-	xfs_dablk_t		tblkno;
-	xfs_daddr_t		dblkno;
-	int			tblkcnt;
-	int			dblkcnt;
 	int			nmap;
 	int			error;
 
@@ -48,47 +44,29 @@ xfs_attr3_leaf_freextent(
 	 * Roll through the "value", invalidating the attribute value's
 	 * blocks.
 	 */
-	tblkno = blkno;
-	tblkcnt = blkcnt;
-	while (tblkcnt > 0) {
+	while (blkcnt > 0) {
 		/*
 		 * Try to remember where we decided to put the value.
 		 */
 		nmap = 1;
-		error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
+		error = xfs_bmapi_read(dp, (xfs_fileoff_t)blkno, blkcnt,
 				       &map, &nmap, XFS_BMAPI_ATTRFORK);
-		if (error) {
+		if (error)
 			return error;
-		}
-		ASSERT(nmap == 1);
-		ASSERT(map.br_startblock != DELAYSTARTBLOCK);
+		if (XFS_IS_CORRUPT(dp->i_mount, nmap != 1))
+			return -EFSCORRUPTED;
 
 		/*
-		 * If it's a hole, these are already unmapped
-		 * so there's nothing to invalidate.
+		 * Mark any incore buffers for the remote value as stale.  We
+		 * never log remote attr value buffers, so the buffer should be
+		 * easy to kill.
 		 */
-		if (map.br_startblock != HOLESTARTBLOCK) {
-
-			dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
-						  map.br_startblock);
-			dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
-						map.br_blockcount);
-			bp = xfs_trans_get_buf(*trans,
-					dp->i_mount->m_ddev_targp,
-					dblkno, dblkcnt, 0);
-			if (!bp)
-				return -ENOMEM;
-			xfs_trans_binval(*trans, bp);
-			/*
-			 * Roll to next transaction.
-			 */
-			error = xfs_trans_roll_inode(trans, dp);
-			if (error)
-				return error;
-		}
+		error = xfs_attr_rmtval_stale(dp, &map, 0);
+		if (error)
+			return error;
 
-		tblkno += map.br_blockcount;
-		tblkcnt -= map.br_blockcount;
+		blkno += map.br_blockcount;
+		blkcnt -= map.br_blockcount;
 	}
 
 	return 0;
@@ -102,86 +80,45 @@ xfs_attr3_leaf_freextent(
  */
 STATIC int
 xfs_attr3_leaf_inactive(
-	struct xfs_trans	**trans,
-	struct xfs_inode	*dp,
-	struct xfs_buf		*bp)
+	struct xfs_trans		**trans,
+	struct xfs_inode		*dp,
+	struct xfs_buf			*bp)
 {
-	struct xfs_attr_leafblock *leaf;
-	struct xfs_attr3_icleaf_hdr ichdr;
-	struct xfs_attr_leaf_entry *entry;
+	struct xfs_attr3_icleaf_hdr	ichdr;
+	struct xfs_mount		*mp = bp->b_mount;
+	struct xfs_attr_leafblock	*leaf = bp->b_addr;
+	struct xfs_attr_leaf_entry	*entry;
 	struct xfs_attr_leaf_name_remote *name_rmt;
-	struct xfs_attr_inactive_list *list;
-	struct xfs_attr_inactive_list *lp;
-	int			error;
-	int			count;
-	int			size;
-	int			tmp;
-	int			i;
-	struct xfs_mount	*mp = bp->b_mount;
+	int				error = 0;
+	int				i;
 
-	leaf = bp->b_addr;
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
 
 	/*
-	 * Count the number of "remote" value extents.
+	 * Find the remote value extents for this leaf and invalidate their
+	 * incore buffers.
 	 */
-	count = 0;
 	entry = xfs_attr3_leaf_entryp(leaf);
 	for (i = 0; i < ichdr.count; entry++, i++) {
-		if (be16_to_cpu(entry->nameidx) &&
-		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
-			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
-			if (name_rmt->valueblk)
-				count++;
-		}
-	}
+		int		blkcnt;
 
-	/*
-	 * If there are no "remote" values, we're done.
-	 */
-	if (count == 0) {
-		xfs_trans_brelse(*trans, bp);
-		return 0;
-	}
-
-	/*
-	 * Allocate storage for a list of all the "remote" value extents.
-	 */
-	size = count * sizeof(xfs_attr_inactive_list_t);
-	list = kmem_alloc(size, 0);
-
-	/*
-	 * Identify each of the "remote" value extents.
-	 */
-	lp = list;
-	entry = xfs_attr3_leaf_entryp(leaf);
-	for (i = 0; i < ichdr.count; entry++, i++) {
-		if (be16_to_cpu(entry->nameidx) &&
-		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
-			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
-			if (name_rmt->valueblk) {
-				lp->valueblk = be32_to_cpu(name_rmt->valueblk);
-				lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount,
-						    be32_to_cpu(name_rmt->valuelen));
-				lp++;
-			}
-		}
-	}
-	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */
+		if (!entry->nameidx || (entry->flags & XFS_ATTR_LOCAL))
+			continue;
 
-	/*
-	 * Invalidate each of the "remote" value extents.
-	 */
-	error = 0;
-	for (lp = list, i = 0; i < count; i++, lp++) {
-		tmp = xfs_attr3_leaf_freextent(trans, dp,
-				lp->valueblk, lp->valuelen);
+		name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
+		if (!name_rmt->valueblk)
+			continue;
 
-		if (error == 0)
-			error = tmp;	/* save only the 1st errno */
+		blkcnt = xfs_attr3_rmt_blocks(dp->i_mount,
+				be32_to_cpu(name_rmt->valuelen));
+		error = xfs_attr3_rmt_stale(dp,
+				be32_to_cpu(name_rmt->valueblk), blkcnt);
+		if (error)
+			goto err;
 	}
 
-	kmem_free(list);
+	xfs_trans_brelse(*trans, bp);
+err:
 	return error;
 }
 
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3984779e5911..5be8973a452c 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -27,6 +27,23 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
 
 STATIC void	xfs_buf_do_callbacks(struct xfs_buf *bp);
 
+/* Is this log iovec plausibly large enough to contain the buffer log format? */
+bool
+xfs_buf_log_check_iovec(
+	struct xfs_log_iovec		*iovec)
+{
+	struct xfs_buf_log_format	*blfp = iovec->i_addr;
+	char				*bmp_end;
+	char				*item_end;
+
+	if (offsetof(struct xfs_buf_log_format, blf_data_map) > iovec->i_len)
+		return false;
+
+	item_end = (char *)iovec->i_addr + iovec->i_len;
+	bmp_end = (char *)&blfp->blf_data_map[blfp->blf_map_size];
+	return bmp_end <= item_end;
+}
+
 static inline int
 xfs_buf_log_format_size(
 	struct xfs_buf_log_format *blfp)
@@ -688,7 +705,7 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_push	= xfs_buf_item_push,
 };
 
-STATIC int
+STATIC void
 xfs_buf_item_get_format(
 	struct xfs_buf_log_item	*bip,
 	int			count)
@@ -698,14 +715,11 @@ xfs_buf_item_get_format(
 
 	if (count == 1) {
 		bip->bli_formats = &bip->__bli_format;
-		return 0;
+		return;
 	}
 
 	bip->bli_formats = kmem_zalloc(count * sizeof(struct xfs_buf_log_format),
 				0);
-	if (!bip->bli_formats)
-		return -ENOMEM;
-	return 0;
 }
 
 STATIC void
@@ -731,7 +745,6 @@ xfs_buf_item_init(
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	int			chunks;
 	int			map_size;
-	int			error;
 	int			i;
 
 	/*
@@ -760,19 +773,22 @@ xfs_buf_item_init(
 	 * Discontiguous buffer support follows the layout of the underlying
 	 * buffer. This makes the implementation as simple as possible.
 	 */
-	error = xfs_buf_item_get_format(bip, bp->b_map_count);
-	ASSERT(error == 0);
-	if (error) {	/* to stop gcc throwing set-but-unused warnings */
-		kmem_cache_free(xfs_buf_item_zone, bip);
-		return error;
-	}
-
+	xfs_buf_item_get_format(bip, bp->b_map_count);
 
 	for (i = 0; i < bip->bli_format_count; i++) {
 		chunks = DIV_ROUND_UP(BBTOB(bp->b_maps[i].bm_len),
 				      XFS_BLF_CHUNK);
 		map_size = DIV_ROUND_UP(chunks, NBWORD);
 
+		if (map_size > XFS_BLF_DATAMAP_SIZE) {
+			kmem_cache_free(xfs_buf_item_zone, bip);
+			xfs_err(mp,
+	"buffer item dirty bitmap (%u uints) too small to reflect %u bytes!",
+					map_size,
+					BBTOB(bp->b_maps[i].bm_len));
+			return -EFSCORRUPTED;
+		}
+
 		bip->bli_formats[i].blf_type = XFS_LI_BUF;
 		bip->bli_formats[i].blf_blkno = bp->b_maps[i].bm_bn;
 		bip->bli_formats[i].blf_len = bp->b_maps[i].bm_len;
@@ -805,6 +821,9 @@ xfs_buf_item_log_segment(
 	uint		end_bit;
 	uint		mask;
 
+	ASSERT(first < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
+	ASSERT(last < XFS_BLF_DATAMAP_SIZE * XFS_BLF_CHUNK * NBWORD);
+
 	/*
 	 * Convert byte offsets to bit numbers.
 	 */
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 4a054b11011a..30114b510332 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -61,6 +61,7 @@ void	xfs_buf_iodone_callbacks(struct xfs_buf *);
 void	xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *);
 bool	xfs_buf_resubmit_failed_buffers(struct xfs_buf *,
 					struct list_head *);
+bool	xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
 
 extern kmem_zone_t	*xfs_buf_item_zone;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 2bff21ca9d78..9cfd3209f52b 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -137,7 +137,7 @@ xfs_qm_adjust_dqtimers(
 		    (d->d_blk_hardlimit &&
 		     (be64_to_cpu(d->d_bcount) >
 		      be64_to_cpu(d->d_blk_hardlimit)))) {
-			d->d_btimer = cpu_to_be32(get_seconds() +
+			d->d_btimer = cpu_to_be32(ktime_get_real_seconds() +
 					mp->m_quotainfo->qi_btimelimit);
 		} else {
 			d->d_bwarns = 0;
@@ -160,7 +160,7 @@ xfs_qm_adjust_dqtimers(
 		    (d->d_ino_hardlimit &&
 		     (be64_to_cpu(d->d_icount) >
 		      be64_to_cpu(d->d_ino_hardlimit)))) {
-			d->d_itimer = cpu_to_be32(get_seconds() +
+			d->d_itimer = cpu_to_be32(ktime_get_real_seconds() +
 					mp->m_quotainfo->qi_itimelimit);
 		} else {
 			d->d_iwarns = 0;
@@ -183,7 +183,7 @@ xfs_qm_adjust_dqtimers(
 		    (d->d_rtb_hardlimit &&
 		     (be64_to_cpu(d->d_rtbcount) >
 		      be64_to_cpu(d->d_rtb_hardlimit)))) {
-			d->d_rtbtimer = cpu_to_be32(get_seconds() +
+			d->d_rtbtimer = cpu_to_be32(ktime_get_real_seconds() +
 					mp->m_quotainfo->qi_rtbtimelimit);
 		} else {
 			d->d_rtbwarns = 0;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index c93250108952..b8a4a3f29b36 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -187,7 +187,12 @@ xfs_file_dio_aio_read(
 
 	file_accessed(iocb->ki_filp);
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED))
+			return -EAGAIN;
+	} else {
+		xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	}
 	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL,
 			is_sync_kiocb(iocb));
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 401da197f012..1979a0055763 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1518,10 +1518,8 @@ xfs_itruncate_extents_flags(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
 	xfs_fileoff_t		first_unmap_block;
-	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
 	int			error = 0;
-	int			done = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
@@ -1541,21 +1539,22 @@ xfs_itruncate_extents_flags(
 	 * the end of the file (in a crash where the space is allocated
 	 * but the inode size is not yet updated), simply remove any
 	 * blocks which show up between the new EOF and the maximum
-	 * possible file size.  If the first block to be removed is
-	 * beyond the maximum file size (ie it is the same as last_block),
-	 * then there is nothing to do.
+	 * possible file size.
+	 *
+	 * We have to free all the blocks to the bmbt maximum offset, even if
+	 * the page cache can't scale that far.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
-	if (first_unmap_block == last_block)
+	if (first_unmap_block >= XFS_MAX_FILEOFF) {
+		WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
 		return 0;
+	}
 
-	ASSERT(first_unmap_block < last_block);
-	unmap_len = last_block - first_unmap_block + 1;
-	while (!done) {
+	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
+	while (unmap_len > 0) {
 		ASSERT(tp->t_firstblock == NULLFSBLOCK);
-		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &done);
+		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
+				flags, XFS_ITRUNC_MAX_EXTENTS);
 		if (error)
 			goto out;
 
@@ -1575,7 +1574,7 @@ xfs_itruncate_extents_flags(
 	if (whichfork == XFS_DATA_FORK) {
 		/* Remove all pending CoW reservations. */
 		error = xfs_reflink_cancel_cow_blocks(ip, &tp,
-				first_unmap_block, last_block, true);
+				first_unmap_block, XFS_MAX_FILEOFF, true);
 		if (error)
 			goto out;
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 7b35d62ede9f..d42de92cb283 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -357,6 +357,7 @@ xfs_attrmulti_attr_get(
 {
 	unsigned char		*kbuf;
 	int			error = -EFAULT;
+	size_t			namelen;
 
 	if (*len > XFS_XATTR_SIZE_MAX)
 		return -EINVAL;
@@ -364,7 +365,9 @@ xfs_attrmulti_attr_get(
 	if (!kbuf)
 		return -ENOMEM;
 
-	error = xfs_attr_get(XFS_I(inode), name, &kbuf, (int *)len, flags);
+	namelen = strlen(name);
+	error = xfs_attr_get(XFS_I(inode), name, namelen, &kbuf, (int *)len,
+			     flags);
 	if (error)
 		goto out_kfree;
 
@@ -386,6 +389,7 @@ xfs_attrmulti_attr_set(
 {
 	unsigned char		*kbuf;
 	int			error;
+	size_t			namelen;
 
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return -EPERM;
@@ -396,7 +400,8 @@ xfs_attrmulti_attr_set(
 	if (IS_ERR(kbuf))
 		return PTR_ERR(kbuf);
 
-	error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
+	namelen = strlen(name);
+	error = xfs_attr_set(XFS_I(inode), name, namelen, kbuf, len, flags);
 	if (!error)
 		xfs_forget_acl(inode, name, flags);
 	kfree(kbuf);
@@ -410,10 +415,12 @@ xfs_attrmulti_attr_remove(
 	uint32_t		flags)
 {
 	int			error;
+	size_t			namelen;
 
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return -EPERM;
-	error = xfs_attr_remove(XFS_I(inode), name, flags);
+	namelen = strlen(name);
+	error = xfs_attr_remove(XFS_I(inode), name, namelen, flags);
 	if (!error)
 		xfs_forget_acl(inode, name, flags);
 	return error;
@@ -462,6 +469,13 @@ xfs_attrmulti_by_handle(
 
 	error = 0;
 	for (i = 0; i < am_hreq.opcount; i++) {
+		if ((ops[i].am_flags & ATTR_ROOT) &&
+		    (ops[i].am_flags & ATTR_SECURE)) {
+			ops[i].am_error = -EINVAL;
+			continue;
+		}
+		ops[i].am_flags &= ~ATTR_KERNEL_FLAGS;
+
 		ops[i].am_error = strncpy_from_user((char *)attr_name,
 				ops[i].am_attrname, MAXNAMELEN);
 		if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c4c4f09113d3..769581a79c58 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -107,7 +107,7 @@ xfs_ioctl32_bstime_copyin(
 	xfs_bstime_t		*bstime,
 	compat_xfs_bstime_t	__user *bstime32)
 {
-	compat_time_t		sec32;	/* tv_sec differs on 64 vs. 32 */
+	old_time32_t		sec32;	/* tv_sec differs on 64 vs. 32 */
 
 	if (get_user(sec32,		&bstime32->tv_sec)	||
 	    get_user(bstime->tv_nsec,	&bstime32->tv_nsec))
@@ -450,6 +450,13 @@ xfs_compat_attrmulti_by_handle(
 
 	error = 0;
 	for (i = 0; i < am_hreq.opcount; i++) {
+		if ((ops[i].am_flags & ATTR_ROOT) &&
+		    (ops[i].am_flags & ATTR_SECURE)) {
+			ops[i].am_error = -EINVAL;
+			continue;
+		}
+		ops[i].am_flags &= ~ATTR_KERNEL_FLAGS;
+
 		ops[i].am_error = strncpy_from_user((char *)attr_name,
 				compat_ptr(ops[i].am_attrname),
 				MAXNAMELEN);
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index 8c7743cd490e..053de7d894cd 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -32,7 +32,7 @@
 #endif
 
 typedef struct compat_xfs_bstime {
-	compat_time_t	tv_sec;		/* seconds		*/
+	old_time32_t	tv_sec;		/* seconds		*/
 	__s32		tv_nsec;	/* and nanoseconds	*/
 } compat_xfs_bstime_t;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 28e2d1f37267..bb590a267a7f 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -923,7 +923,7 @@ xfs_buffered_write_iomap_begin(
 		xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
 
 		/* Trim the mapping to the nearest shared extent boundary. */
-		error = xfs_inode_need_cow(ip, &imap, &shared);
+		error = xfs_bmap_trim_cow(ip, &imap, &shared);
 		if (error)
 			goto out_unlock;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 8afe69ca188b..81f2f93caec0 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -50,8 +50,10 @@ xfs_initxattrs(
 	int			error = 0;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		error = xfs_attr_set(ip, xattr->name, xattr->value,
-				      xattr->value_len, ATTR_SECURE);
+		error = xfs_attr_set(ip, xattr->name,
+				     strlen(xattr->name),
+				     xattr->value, xattr->value_len,
+				     ATTR_SECURE);
 		if (error < 0)
 			break;
 	}
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 99ec3fba4548..0d683fb96396 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1934,6 +1934,12 @@ xlog_recover_buffer_pass1(
 	struct list_head	*bucket;
 	struct xfs_buf_cancel	*bcp;
 
+	if (!xfs_buf_log_check_iovec(&item->ri_buf[0])) {
+		xfs_err(log->l_mp, "bad buffer log item size (%d)",
+				item->ri_buf[0].i_len);
+		return -EFSCORRUPTED;
+	}
+
 	/*
 	 * If this isn't a cancel buffer item, then just return.
 	 */
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index b6701b4f59a9..5f04d8a5ab2a 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -111,6 +111,7 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_STRUCT_SIZE(xfs_dir2_sf_hdr_t,		10);
 
 	/* log structures */
+	XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format,	88);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat,		24);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32,	28);
 	XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64,	32);
diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h
index 7823af39008b..4e57edca8bce 100644
--- a/fs/xfs/xfs_qm.h
+++ b/fs/xfs/xfs_qm.h
@@ -64,9 +64,9 @@ struct xfs_quotainfo {
 	struct xfs_inode	*qi_pquotaip;	/* project quota inode */
 	struct list_lru	 qi_lru;
 	int		 qi_dquots;
-	time_t		 qi_btimelimit;	 /* limit for blks timer */
-	time_t		 qi_itimelimit;	 /* limit for inodes timer */
-	time_t		 qi_rtbtimelimit;/* limit for rt blks timer */
+	time64_t	 qi_btimelimit;	 /* limit for blks timer */
+	time64_t	 qi_itimelimit;	 /* limit for inodes timer */
+	time64_t	 qi_rtbtimelimit;/* limit for rt blks timer */
 	xfs_qwarncnt_t	 qi_bwarnlimit;	 /* limit for blks warnings */
 	xfs_qwarncnt_t	 qi_iwarnlimit;	 /* limit for inodes warnings */
 	xfs_qwarncnt_t	 qi_rtbwarnlimit;/* limit for rt blks warnings */
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index c7de17deeae6..38669e827206 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -37,9 +37,9 @@ xfs_qm_fill_state(
 	tstate->flags |= QCI_SYSFILE;
 	tstate->blocks = ip->i_d.di_nblocks;
 	tstate->nextents = ip->i_d.di_nextents;
-	tstate->spc_timelimit = q->qi_btimelimit;
-	tstate->ino_timelimit = q->qi_itimelimit;
-	tstate->rt_spc_timelimit = q->qi_rtbtimelimit;
+	tstate->spc_timelimit = (u32)q->qi_btimelimit;
+	tstate->ino_timelimit = (u32)q->qi_itimelimit;
+	tstate->rt_spc_timelimit = (u32)q->qi_rtbtimelimit;
 	tstate->spc_warnlimit = q->qi_bwarnlimit;
 	tstate->ino_warnlimit = q->qi_iwarnlimit;
 	tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index de451235c4ee..e723b267a247 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -223,8 +223,8 @@ xfs_reflink_trim_around_shared(
 	}
 }
 
-bool
-xfs_inode_need_cow(
+int
+xfs_bmap_trim_cow(
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*imap,
 	bool			*shared)
@@ -327,7 +327,7 @@ xfs_find_trim_cow_extent(
 	if (cmap->br_startoff > offset_fsb) {
 		xfs_trim_extent(imap, imap->br_startoff,
 				cmap->br_startoff - imap->br_startoff);
-		return xfs_inode_need_cow(ip, imap, shared);
+		return xfs_bmap_trim_cow(ip, imap, shared);
 	}
 
 	*shared = true;
@@ -1457,7 +1457,8 @@ xfs_reflink_clear_inode_flag(
 	 * We didn't find any shared blocks so turn off the reflink flag.
 	 * First, get rid of any leftover CoW mappings.
 	 */
-	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
+	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, XFS_MAX_FILEOFF,
+			true);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index d18ad7f4fb64..3e4fd46373ab 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -22,7 +22,7 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared);
-bool xfs_inode_need_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
+int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
 		bool *shared);
 
 int xfs_reflink_allocate_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d9ae27ddf253..760901783944 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -193,32 +193,6 @@ xfs_fs_show_options(
 	return 0;
 }
 
-static uint64_t
-xfs_max_file_offset(
-	unsigned int		blockshift)
-{
-	unsigned int		pagefactor = 1;
-	unsigned int		bitshift = BITS_PER_LONG - 1;
-
-	/* Figure out maximum filesize, on Linux this can depend on
-	 * the filesystem blocksize (on 32 bit platforms).
-	 * __block_write_begin does this in an [unsigned] long long...
-	 *      page->index << (PAGE_SHIFT - bbits)
-	 * So, for page sized blocks (4K on 32 bit platforms),
-	 * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
-	 *      (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
-	 * but for smaller blocksizes it is less (bbits = log2 bsize).
-	 */
-
-#if BITS_PER_LONG == 32
-	ASSERT(sizeof(sector_t) == 8);
-	pagefactor = PAGE_SIZE;
-	bitshift = BITS_PER_LONG;
-#endif
-
-	return (((uint64_t)pagefactor) << bitshift) - 1;
-}
-
 /*
  * Set parameters for inode allocation heuristics, taking into account
  * filesystem size and inode32/inode64 mount options; i.e. specifically
@@ -1424,6 +1398,26 @@ xfs_fc_fill_super(
 	if (error)
 		goto out_free_sb;
 
+	/*
+	 * XFS block mappings use 54 bits to store the logical block offset.
+	 * This should suffice to handle the maximum file size that the VFS
+	 * supports (currently 2^63 bytes on 64-bit and ULONG_MAX << PAGE_SHIFT
+	 * bytes on 32-bit), but as XFS and VFS have gotten the s_maxbytes
+	 * calculation wrong on 32-bit kernels in the past, we'll add a WARN_ON
+	 * to check this assertion.
+	 *
+	 * Avoid integer overflow by comparing the maximum bmbt offset to the
+	 * maximum pagecache offset in units of fs blocks.
+	 */
+	if (XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE) > XFS_MAX_FILEOFF) {
+		xfs_warn(mp,
+"MAX_LFS_FILESIZE block offset (%llu) exceeds extent map maximum (%llu)!",
+			 XFS_B_TO_FSBT(mp, MAX_LFS_FILESIZE),
+			 XFS_MAX_FILEOFF);
+		error = -EINVAL;
+		goto out_free_sb;
+	}
+
 	error = xfs_filestream_mount(mp);
 	if (error)
 		goto out_free_sb;
@@ -1435,7 +1429,7 @@ xfs_fc_fill_super(
 	sb->s_magic = XFS_SUPER_MAGIC;
 	sb->s_blocksize = mp->m_sb.sb_blocksize;
 	sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
-	sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_max_links = XFS_MAXLINK;
 	sb->s_time_gran = 1;
 	sb->s_time_min = S32_MIN;
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index a6fe2d8dc40f..d1b9869bc5fa 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -580,7 +580,7 @@ xfs_trans_dqresv(
 {
 	xfs_qcnt_t		hardlimit;
 	xfs_qcnt_t		softlimit;
-	time_t			timer;
+	time64_t		timer;
 	xfs_qwarncnt_t		warns;
 	xfs_qwarncnt_t		warnlimit;
 	xfs_qcnt_t		total_count;
@@ -635,7 +635,8 @@ xfs_trans_dqresv(
 				goto error_return;
 			}
 			if (softlimit && total_count > softlimit) {
-				if ((timer != 0 && get_seconds() > timer) ||
+				if ((timer != 0 &&
+				     ktime_get_real_seconds() > timer) ||
 				    (warns != 0 && warns >= warnlimit)) {
 					xfs_quota_warn(mp, dqp,
 						       QUOTA_NL_BSOFTLONGWARN);
@@ -662,7 +663,8 @@ xfs_trans_dqresv(
 				goto error_return;
 			}
 			if (softlimit && total_count > softlimit) {
-				if  ((timer != 0 && get_seconds() > timer) ||
+				if  ((timer != 0 &&
+				      ktime_get_real_seconds() > timer) ||
 				     (warns != 0 && warns >= warnlimit)) {
 					xfs_quota_warn(mp, dqp,
 						       QUOTA_NL_ISOFTLONGWARN);
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 383f0203d103..b0fedb543f97 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -24,6 +24,7 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
 	int xflags = handler->flags;
 	struct xfs_inode *ip = XFS_I(inode);
 	int error, asize = size;
+	size_t namelen = strlen(name);
 
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (!size) {
@@ -31,7 +32,8 @@ xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
 		value = NULL;
 	}
 
-	error = xfs_attr_get(ip, name, (unsigned char **)&value, &asize, xflags);
+	error = xfs_attr_get(ip, name, namelen, (unsigned char **)&value,
+			     &asize, xflags);
 	if (error)
 		return error;
 	return asize;
@@ -67,6 +69,7 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
 	int			xflags = handler->flags;
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error;
+	size_t			namelen = strlen(name);
 
 	/* Convert Linux syscall to XFS internal ATTR flags */
 	if (flags & XATTR_CREATE)
@@ -74,10 +77,11 @@ xfs_xattr_set(const struct xattr_handler *handler, struct dentry *unused,
 	if (flags & XATTR_REPLACE)
 		xflags |= ATTR_REPLACE;
 
-	if (!value)
-		return xfs_attr_remove(ip, (unsigned char *)name, xflags);
-	error = xfs_attr_set(ip, (unsigned char *)name,
-				(void *)value, size, xflags);
+	if (value)
+		error = xfs_attr_set(ip, name, namelen, (void *)value, size,
+				xflags);
+	else
+		error = xfs_attr_remove(ip, name, namelen, xflags);
 	if (!error)
 		xfs_forget_acl(inode, name, xflags);
 
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index ddfee1bd9dc1..cd17d50697cc 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -4,5 +4,6 @@
 # (This file is not included when SRCARCH=um since UML borrows several
 # asm headers from the host architecutre.)
 
+mandatory-y += dma-contiguous.h
 mandatory-y += msi.h
 mandatory-y += simd.h
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index afddc5442e92..365345f9a9e3 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -27,9 +27,11 @@
 .endm
 
 /*
- * note on .section use: @progbits vs %progbits nastiness doesn't matter,
- * since we immediately emit into those sections anyway.
+ * note on .section use: we specify progbits since usage of the "M" (SHF_MERGE)
+ * section flag requires it. Use '%progbits' instead of '@progbits' since the
+ * former apparently works on all arches according to the binutils source.
  */
+
 .macro ___EXPORT_SYMBOL name,val,sec
 #ifdef CONFIG_MODULES
 	.section ___ksymtab\sec+\name,"a"
@@ -37,7 +39,7 @@
 __ksymtab_\name:
 	__put \val, __kstrtab_\name
 	.previous
-	.section __ksymtab_strings,"a"
+	.section __ksymtab_strings,"aMS",%progbits,1
 __kstrtab_\name:
 	.asciz "\name"
 	.previous
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
index 6736ed2f632b..4dbb177d1150 100644
--- a/include/asm-generic/mm_hooks.h
+++ b/include/asm-generic/mm_hooks.h
@@ -22,11 +22,6 @@ static inline void arch_unmap(struct mm_struct *mm,
 {
 }
 
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-				     struct vm_area_struct *vma)
-{
-}
-
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
 {
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index c2de013b2cf4..35e4a53b83e6 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -74,7 +74,7 @@ do {									\
 
 #define raw_cpu_generic_add_return(pcp, val)				\
 ({									\
-	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
 									\
 	*__p += val;							\
 	*__p;								\
@@ -82,7 +82,7 @@ do {									\
 
 #define raw_cpu_generic_xchg(pcp, nval)					\
 ({									\
-	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
 	typeof(pcp) __ret;						\
 	__ret = *__p;							\
 	*__p = nval;							\
@@ -91,7 +91,7 @@ do {									\
 
 #define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
-	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
 	typeof(pcp) __ret;						\
 	__ret = *__p;							\
 	if (__ret == (oval))						\
@@ -101,8 +101,8 @@ do {									\
 
 #define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
 ({									\
-	typeof(&(pcp1)) __p1 = raw_cpu_ptr(&(pcp1));			\
-	typeof(&(pcp2)) __p2 = raw_cpu_ptr(&(pcp2));			\
+	typeof(pcp1) *__p1 = raw_cpu_ptr(&(pcp1));			\
+	typeof(pcp2) *__p2 = raw_cpu_ptr(&(pcp2));			\
 	int __ret = 0;							\
 	if (*__p1 == (oval1) && *__p2  == (oval2)) {			\
 		*__p1 = nval1;						\
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 798ea36a0549..e2e2bef07dd2 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1238,4 +1238,24 @@ static inline bool arch_has_pfn_modify_check(void)
 #define mm_pmd_folded(mm)	__is_defined(__PAGETABLE_PMD_FOLDED)
 #endif
 
+/*
+ * p?d_leaf() - true if this entry is a final mapping to a physical address.
+ * This differs from p?d_huge() by the fact that they are always available (if
+ * the architecture supports large pages at the appropriate level) even
+ * if CONFIG_HUGETLB_PAGE is not defined.
+ * Only meaningful when called on a valid entry.
+ */
+#ifndef pgd_leaf
+#define pgd_leaf(x)	0
+#endif
+#ifndef p4d_leaf
+#define p4d_leaf(x)	0
+#endif
+#ifndef pud_leaf
+#define pud_leaf(x)	0
+#endif
+#ifndef pmd_leaf
+#define pmd_leaf(x)	0
+#endif
+
 #endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 2b10036fefd0..f391f6b500b4 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -56,6 +56,15 @@
  *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
  *    there's large holes between the VMAs.
  *
+ *  - tlb_remove_table()
+ *
+ *    tlb_remove_table() is the basic primitive to free page-table directories
+ *    (__p*_free_tlb()).  In it's most primitive form it is an alias for
+ *    tlb_remove_page() below, for when page directories are pages and have no
+ *    additional constraints.
+ *
+ *    See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE.
+ *
  *  - tlb_remove_page() / __tlb_remove_page()
  *  - tlb_remove_page_size() / __tlb_remove_page_size()
  *
@@ -121,65 +130,53 @@
  *
  * Additionally there are a few opt-in features:
  *
- *  HAVE_MMU_GATHER_PAGE_SIZE
+ *  MMU_GATHER_PAGE_SIZE
  *
  *  This ensures we call tlb_flush() every time tlb_change_page_size() actually
  *  changes the size and provides mmu_gather::page_size to tlb_flush().
  *
- *  HAVE_RCU_TABLE_FREE
+ *  This might be useful if your architecture has size specific TLB
+ *  invalidation instructions.
+ *
+ *  MMU_GATHER_TABLE_FREE
  *
  *  This provides tlb_remove_table(), to be used instead of tlb_remove_page()
- *  for page directores (__p*_free_tlb()). This provides separate freeing of
- *  the page-table pages themselves in a semi-RCU fashion (see comment below).
- *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
- *  and therefore doesn't naturally serialize with software page-table walkers.
+ *  for page directores (__p*_free_tlb()).
+ *
+ *  Useful if your architecture has non-page page directories.
  *
  *  When used, an architecture is expected to provide __tlb_remove_table()
  *  which does the actual freeing of these pages.
  *
- *  HAVE_RCU_TABLE_NO_INVALIDATE
+ *  MMU_GATHER_RCU_TABLE_FREE
  *
- *  This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
- *  freeing the page-table pages. This can be avoided if you use
- *  HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
- *  page-tables natively.
+ *  Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see
+ *  comment below).
+ *
+ *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ *  and therefore doesn't naturally serialize with software page-table walkers.
  *
  *  MMU_GATHER_NO_RANGE
  *
  *  Use this if your architecture lacks an efficient flush_tlb_range().
- */
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-/*
- * Semi RCU freeing of the page directories.
- *
- * This is needed by some architectures to implement software pagetable walkers.
  *
- * gup_fast() and other software pagetable walkers do a lockless page-table
- * walk and therefore needs some synchronization with the freeing of the page
- * directories. The chosen means to accomplish that is by disabling IRQs over
- * the walk.
+ *  MMU_GATHER_NO_GATHER
  *
- * Architectures that use IPIs to flush TLBs will then automagically DTRT,
- * since we unlink the page, flush TLBs, free the page. Since the disabling of
- * IRQs delays the completion of the TLB flush we can never observe an already
- * freed page.
- *
- * Architectures that do not have this (PPC) need to delay the freeing by some
- * other means, this is that means.
- *
- * What we do is batch the freed directory pages (tables) and RCU free them.
- * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
- * holds off grace periods.
- *
- * However, in order to batch these pages we need to allocate storage, this
- * allocation is deep inside the MM code and can thus easily fail on memory
- * pressure. To guarantee progress we fall back to single table freeing, see
- * the implementation of tlb_remove_table_one().
+ *  If the option is set the mmu_gather will not track individual pages for
+ *  delayed page free anymore. A platform that enables the option needs to
+ *  provide its own implementation of the __tlb_remove_page_size() function to
+ *  free pages.
  *
+ *  This is useful if your architecture already flushes TLB entries in the
+ *  various ptep_get_and_clear() functions.
  */
+
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
+
 struct mmu_table_batch {
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
 	struct rcu_head		rcu;
+#endif
 	unsigned int		nr;
 	void			*tables[0];
 };
@@ -189,9 +186,35 @@ struct mmu_table_batch {
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
+#else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */
+
+/*
+ * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based
+ * page directories and we can use the normal page batching to free them.
+ */
+#define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page))
+
+#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
+
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
+/*
+ * This allows an architecture that does not use the linux page-tables for
+ * hardware to skip the TLBI when freeing page tables.
+ */
+#ifndef tlb_needs_table_invalidate
+#define tlb_needs_table_invalidate() (true)
 #endif
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#else
+
+#ifdef tlb_needs_table_invalidate
+#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
+#endif
+
+#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
+
+
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 /*
  * If we can't allocate a page to make a big batch of page pointers
  * to work on, then just handle a few from the on-stack structure.
@@ -227,7 +250,7 @@ extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
 struct mmu_gather {
 	struct mm_struct	*mm;
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
 
@@ -266,22 +289,18 @@ struct mmu_gather {
 
 	unsigned int		batch_count;
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	unsigned int page_size;
 #endif
 #endif
 };
 
-void arch_tlb_gather_mmu(struct mmu_gather *tlb,
-	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			 unsigned long start, unsigned long end, bool force);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address,
@@ -394,7 +413,12 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
+	/*
+	 * Anything calling __tlb_adjust_range() also sets at least one of
+	 * these bits.
+	 */
+	if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds ||
+	      tlb->cleared_puds || tlb->cleared_p4ds))
 		return;
 
 	tlb_flush(tlb);
@@ -426,7 +450,7 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void tlb_change_page_size(struct mmu_gather *tlb,
 						     unsigned int page_size)
 {
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	if (tlb->page_size && tlb->page_size != page_size) {
 		if (!tlb->fullmm && !tlb->need_flush_all)
 			tlb_flush_mmu(tlb);
diff --git a/include/drm/bridge/dw_mipi_dsi.h b/include/drm/bridge/dw_mipi_dsi.h
index 94cc64a342e1..b0e390b3288e 100644
--- a/include/drm/bridge/dw_mipi_dsi.h
+++ b/include/drm/bridge/dw_mipi_dsi.h
@@ -19,6 +19,13 @@ struct dw_mipi_dsi;
 struct mipi_dsi_device;
 struct platform_device;
 
+struct dw_mipi_dsi_dphy_timing {
+	u16 data_hs2lp;
+	u16 data_lp2hs;
+	u16 clk_hs2lp;
+	u16 clk_lp2hs;
+};
+
 struct dw_mipi_dsi_phy_ops {
 	int (*init)(void *priv_data);
 	void (*power_on)(void *priv_data);
@@ -27,6 +34,8 @@ struct dw_mipi_dsi_phy_ops {
 			     const struct drm_display_mode *mode,
 			     unsigned long mode_flags, u32 lanes, u32 format,
 			     unsigned int *lane_mbps);
+	int (*get_timing)(void *priv_data, unsigned int lane_mbps,
+			  struct dw_mipi_dsi_dphy_timing *timing);
 };
 
 struct dw_mipi_dsi_host_ops {
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index 927e1205d7aa..951dfb15c27b 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -35,7 +35,7 @@
  * struct drm_crtc_commit - track modeset commits on a CRTC
  *
  * This structure is used to track pending modeset changes and atomic commit on
- * a per-CRTC basis. Since updating the list should never block this structure
+ * a per-CRTC basis. Since updating the list should never block, this structure
  * is reference counted to allow waiters to safely wait on an event to complete,
  * without holding any locks.
  *
@@ -60,8 +60,8 @@
  * 	wait for flip_done		<----
  * 	clean up atomic state
  *
- * The important bit to know is that cleanup_done is the terminal event, but the
- * ordering between flip_done and hw_done is entirely up to the specific driver
+ * The important bit to know is that &cleanup_done is the terminal event, but the
+ * ordering between &flip_done and &hw_done is entirely up to the specific driver
  * and modeset state change.
  *
  * For an implementation of how to use this look at
@@ -92,6 +92,9 @@ struct drm_crtc_commit {
 	 * commit is sent to userspace, or when an out-fence is singalled. Note
 	 * that for most hardware, in most cases this happens after @hw_done is
 	 * signalled.
+	 *
+	 * Completion of this stage is signalled implicitly by calling
+	 * drm_crtc_send_vblank_event() on &drm_crtc_state.event.
 	 */
 	struct completion flip_done;
 
@@ -107,6 +110,9 @@ struct drm_crtc_commit {
 	 * Note that this does not need to include separately reference-counted
 	 * resources like backing storage buffer pinning, or runtime pm
 	 * management.
+	 *
+	 * Drivers should call drm_atomic_helper_commit_hw_done() to signal
+	 * completion of this stage.
 	 */
 	struct completion hw_done;
 
@@ -118,6 +124,9 @@ struct drm_crtc_commit {
 	 * a vblank wait completed it might be a bit later. This completion is
 	 * useful to throttle updates and avoid hardware updates getting ahead
 	 * of the buffer cleanup too much.
+	 *
+	 * Drivers should call drm_atomic_helper_commit_cleanup_done() to signal
+	 * completion of this stage.
 	 */
 	struct completion cleanup_done;
 
@@ -354,7 +363,7 @@ struct drm_atomic_state {
 	 * When a connector or plane is not bound to any CRTC, it's still important
 	 * to preserve linearity to prevent the atomic states from being freed to early.
 	 *
-	 * This commit (if set) is not bound to any crtc, but will be completed when
+	 * This commit (if set) is not bound to any CRTC, but will be completed when
 	 * drm_atomic_helper_commit_hw_done() is called.
 	 */
 	struct drm_crtc_commit *fake_commit;
@@ -467,12 +476,12 @@ drm_atomic_get_new_connector_for_encoder(struct drm_atomic_state *state,
 					 struct drm_encoder *encoder);
 
 /**
- * drm_atomic_get_existing_crtc_state - get crtc state, if it exists
+ * drm_atomic_get_existing_crtc_state - get CRTC state, if it exists
  * @state: global atomic state object
- * @crtc: crtc to grab
+ * @crtc: CRTC to grab
  *
- * This function returns the crtc state for the given crtc, or NULL
- * if the crtc is not part of the global atomic state.
+ * This function returns the CRTC state for the given CRTC, or NULL
+ * if the CRTC is not part of the global atomic state.
  *
  * This function is deprecated, @drm_atomic_get_old_crtc_state or
  * @drm_atomic_get_new_crtc_state should be used instead.
@@ -485,12 +494,12 @@ drm_atomic_get_existing_crtc_state(struct drm_atomic_state *state,
 }
 
 /**
- * drm_atomic_get_old_crtc_state - get old crtc state, if it exists
+ * drm_atomic_get_old_crtc_state - get old CRTC state, if it exists
  * @state: global atomic state object
- * @crtc: crtc to grab
+ * @crtc: CRTC to grab
  *
- * This function returns the old crtc state for the given crtc, or
- * NULL if the crtc is not part of the global atomic state.
+ * This function returns the old CRTC state for the given CRTC, or
+ * NULL if the CRTC is not part of the global atomic state.
  */
 static inline struct drm_crtc_state *
 drm_atomic_get_old_crtc_state(struct drm_atomic_state *state,
@@ -499,12 +508,12 @@ drm_atomic_get_old_crtc_state(struct drm_atomic_state *state,
 	return state->crtcs[drm_crtc_index(crtc)].old_state;
 }
 /**
- * drm_atomic_get_new_crtc_state - get new crtc state, if it exists
+ * drm_atomic_get_new_crtc_state - get new CRTC state, if it exists
  * @state: global atomic state object
- * @crtc: crtc to grab
+ * @crtc: CRTC to grab
  *
- * This function returns the new crtc state for the given crtc, or
- * NULL if the crtc is not part of the global atomic state.
+ * This function returns the new CRTC state for the given CRTC, or
+ * NULL if the CRTC is not part of the global atomic state.
  */
 static inline struct drm_crtc_state *
 drm_atomic_get_new_crtc_state(struct drm_atomic_state *state,
@@ -693,6 +702,7 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)								\
 		for_each_if ((__state)->connectors[__i].ptr &&			\
 			     ((connector) = (__state)->connectors[__i].ptr,	\
+			     (void)(connector) /* Only to avoid unused-but-set-variable warning */, \
 			     (old_connector_state) = (__state)->connectors[__i].old_state,	\
 			     (new_connector_state) = (__state)->connectors[__i].new_state, 1))
 
@@ -714,6 +724,7 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)								\
 		for_each_if ((__state)->connectors[__i].ptr &&			\
 			     ((connector) = (__state)->connectors[__i].ptr,	\
+			     (void)(connector) /* Only to avoid unused-but-set-variable warning */, \
 			     (old_connector_state) = (__state)->connectors[__i].old_state, 1))
 
 /**
@@ -734,7 +745,9 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)								\
 		for_each_if ((__state)->connectors[__i].ptr &&			\
 			     ((connector) = (__state)->connectors[__i].ptr,	\
-			     (new_connector_state) = (__state)->connectors[__i].new_state, 1))
+			     (void)(connector) /* Only to avoid unused-but-set-variable warning */, \
+			     (new_connector_state) = (__state)->connectors[__i].new_state, \
+			     (void)(new_connector_state) /* Only to avoid unused-but-set-variable warning */, 1))
 
 /**
  * for_each_oldnew_crtc_in_state - iterate over all CRTCs in an atomic update
@@ -754,7 +767,9 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)							\
 		for_each_if ((__state)->crtcs[__i].ptr &&		\
 			     ((crtc) = (__state)->crtcs[__i].ptr,	\
+			      (void)(crtc) /* Only to avoid unused-but-set-variable warning */, \
 			     (old_crtc_state) = (__state)->crtcs[__i].old_state, \
+			     (void)(old_crtc_state) /* Only to avoid unused-but-set-variable warning */, \
 			     (new_crtc_state) = (__state)->crtcs[__i].new_state, 1))
 
 /**
@@ -793,7 +808,9 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)							\
 		for_each_if ((__state)->crtcs[__i].ptr &&		\
 			     ((crtc) = (__state)->crtcs[__i].ptr,	\
-			     (new_crtc_state) = (__state)->crtcs[__i].new_state, 1))
+			     (void)(crtc) /* Only to avoid unused-but-set-variable warning */, \
+			     (new_crtc_state) = (__state)->crtcs[__i].new_state, \
+			     (void)(new_crtc_state) /* Only to avoid unused-but-set-variable warning */, 1))
 
 /**
  * for_each_oldnew_plane_in_state - iterate over all planes in an atomic update
@@ -813,6 +830,7 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)							\
 		for_each_if ((__state)->planes[__i].ptr &&		\
 			     ((plane) = (__state)->planes[__i].ptr,	\
+			      (void)(plane) /* Only to avoid unused-but-set-variable warning */, \
 			      (old_plane_state) = (__state)->planes[__i].old_state,\
 			      (new_plane_state) = (__state)->planes[__i].new_state, 1))
 
@@ -873,7 +891,9 @@ void drm_state_dump(struct drm_device *dev, struct drm_printer *p);
 	     (__i)++)							\
 		for_each_if ((__state)->planes[__i].ptr &&		\
 			     ((plane) = (__state)->planes[__i].ptr,	\
-			      (new_plane_state) = (__state)->planes[__i].new_state, 1))
+			      (void)(plane) /* Only to avoid unused-but-set-variable warning */, \
+			      (new_plane_state) = (__state)->planes[__i].new_state, \
+			      (void)(new_plane_state) /* Only to avoid unused-but-set-variable warning */, 1))
 
 /**
  * for_each_oldnew_private_obj_in_state - iterate over all private objects in an atomic update
@@ -958,11 +978,11 @@ drm_atomic_crtc_needs_modeset(const struct drm_crtc_state *state)
 }
 
 /**
- * drm_atomic_crtc_effectively_active - compute whether crtc is actually active
+ * drm_atomic_crtc_effectively_active - compute whether CRTC is actually active
  * @state: &drm_crtc_state for the CRTC
  *
  * When in self refresh mode, the crtc_state->active value will be false, since
- * the crtc is off. However in some cases we're interested in whether the crtc
+ * the CRTC is off. However in some cases we're interested in whether the CRTC
  * is active, or effectively active (ie: it's connected to an active display).
  * In these cases, use this function instead of just checking active.
  */
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index bf4e07141d81..9db3cac48f4f 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -152,7 +152,7 @@ int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
 /**
  * drm_atomic_crtc_for_each_plane - iterate over planes currently attached to CRTC
  * @plane: the loop cursor
- * @crtc:  the crtc whose planes are iterated
+ * @crtc:  the CRTC whose planes are iterated
  *
  * This iterates over the current state, useful (for example) when applying
  * atomic state after it has been checked and swapped.  To iterate over the
@@ -166,7 +166,7 @@ int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
 /**
  * drm_crtc_atomic_state_for_each_plane - iterate over attached planes in new state
  * @plane: the loop cursor
- * @crtc_state: the incoming crtc-state
+ * @crtc_state: the incoming CRTC state
  *
  * Similar to drm_crtc_for_each_plane(), but iterates the planes that will be
  * attached if the specified state is applied.  Useful during for example
@@ -180,7 +180,7 @@ int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
  * drm_crtc_atomic_state_for_each_plane_state - iterate over attached planes in new state
  * @plane: the loop cursor
  * @plane_state: loop cursor for the plane's state, must be const
- * @crtc_state: the incoming crtc-state
+ * @crtc_state: the incoming CRTC state
  *
  * Similar to drm_crtc_for_each_plane(), but iterates the planes that will be
  * attached if the specified state is applied.  Useful during for example
@@ -189,7 +189,7 @@ int drm_atomic_helper_legacy_gamma_set(struct drm_crtc *crtc,
  *
  * Compared to just drm_atomic_crtc_state_for_each_plane() this also fills in a
  * const plane_state. This is useful when a driver just wants to peek at other
- * active planes on this crtc, but does not need to change it.
+ * active planes on this CRTC, but does not need to change it.
  */
 #define drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) \
 	drm_for_each_plane_mask(plane, (crtc_state)->state->dev, (crtc_state)->plane_mask) \
diff --git a/include/drm/drm_atomic_state_helper.h b/include/drm/drm_atomic_state_helper.h
index e4577cc11689..8171dea4cc22 100644
--- a/include/drm/drm_atomic_state_helper.h
+++ b/include/drm/drm_atomic_state_helper.h
@@ -37,6 +37,8 @@ struct drm_private_state;
 struct drm_modeset_acquire_ctx;
 struct drm_device;
 
+void __drm_atomic_helper_crtc_state_reset(struct drm_crtc_state *state,
+					  struct drm_crtc *crtc);
 void __drm_atomic_helper_crtc_reset(struct drm_crtc *crtc,
 				    struct drm_crtc_state *state);
 void drm_atomic_helper_crtc_reset(struct drm_crtc *crtc);
@@ -48,6 +50,8 @@ void __drm_atomic_helper_crtc_destroy_state(struct drm_crtc_state *state);
 void drm_atomic_helper_crtc_destroy_state(struct drm_crtc *crtc,
 					  struct drm_crtc_state *state);
 
+void __drm_atomic_helper_plane_state_reset(struct drm_plane_state *state,
+					   struct drm_plane *plane);
 void __drm_atomic_helper_plane_reset(struct drm_plane *plane,
 				     struct drm_plane_state *state);
 void drm_atomic_helper_plane_reset(struct drm_plane *plane);
@@ -59,6 +63,8 @@ void __drm_atomic_helper_plane_destroy_state(struct drm_plane_state *state);
 void drm_atomic_helper_plane_destroy_state(struct drm_plane *plane,
 					  struct drm_plane_state *state);
 
+void __drm_atomic_helper_connector_state_reset(struct drm_connector_state *conn_state,
+					       struct drm_connector *connector);
 void __drm_atomic_helper_connector_reset(struct drm_connector *connector,
 					 struct drm_connector_state *conn_state);
 void drm_atomic_helper_connector_reset(struct drm_connector *connector);
diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h
index c0a2286a81e9..694e153a7531 100644
--- a/include/drm/drm_bridge.h
+++ b/include/drm/drm_bridge.h
@@ -25,6 +25,7 @@
 
 #include <linux/list.h>
 #include <linux/ctype.h>
+#include <drm/drm_encoder.h>
 #include <drm/drm_mode_object.h>
 #include <drm/drm_modes.h>
 
@@ -254,14 +255,15 @@ struct drm_bridge_funcs {
 	 * there is one) when this callback is called.
 	 *
 	 * Note that this function will only be invoked in the context of an
-	 * atomic commit. It will not be invoked from &drm_bridge_pre_enable. It
-	 * would be prudent to also provide an implementation of @pre_enable if
-	 * you are expecting driver calls into &drm_bridge_pre_enable.
+	 * atomic commit. It will not be invoked from
+	 * &drm_bridge_chain_pre_enable. It would be prudent to also provide an
+	 * implementation of @pre_enable if you are expecting driver calls into
+	 * &drm_bridge_chain_pre_enable.
 	 *
 	 * The @atomic_pre_enable callback is optional.
 	 */
 	void (*atomic_pre_enable)(struct drm_bridge *bridge,
-				  struct drm_atomic_state *state);
+				  struct drm_atomic_state *old_state);
 
 	/**
 	 * @atomic_enable:
@@ -279,14 +281,14 @@ struct drm_bridge_funcs {
 	 * chain if there is one.
 	 *
 	 * Note that this function will only be invoked in the context of an
-	 * atomic commit. It will not be invoked from &drm_bridge_enable. It
-	 * would be prudent to also provide an implementation of @enable if
-	 * you are expecting driver calls into &drm_bridge_enable.
+	 * atomic commit. It will not be invoked from &drm_bridge_chain_enable.
+	 * It would be prudent to also provide an implementation of @enable if
+	 * you are expecting driver calls into &drm_bridge_chain_enable.
 	 *
 	 * The @atomic_enable callback is optional.
 	 */
 	void (*atomic_enable)(struct drm_bridge *bridge,
-			      struct drm_atomic_state *state);
+			      struct drm_atomic_state *old_state);
 	/**
 	 * @atomic_disable:
 	 *
@@ -301,14 +303,15 @@ struct drm_bridge_funcs {
 	 * signals) feeding it is still running when this callback is called.
 	 *
 	 * Note that this function will only be invoked in the context of an
-	 * atomic commit. It will not be invoked from &drm_bridge_disable. It
-	 * would be prudent to also provide an implementation of @disable if
-	 * you are expecting driver calls into &drm_bridge_disable.
+	 * atomic commit. It will not be invoked from
+	 * &drm_bridge_chain_disable. It would be prudent to also provide an
+	 * implementation of @disable if you are expecting driver calls into
+	 * &drm_bridge_chain_disable.
 	 *
 	 * The @atomic_disable callback is optional.
 	 */
 	void (*atomic_disable)(struct drm_bridge *bridge,
-			       struct drm_atomic_state *state);
+			       struct drm_atomic_state *old_state);
 
 	/**
 	 * @atomic_post_disable:
@@ -325,15 +328,16 @@ struct drm_bridge_funcs {
 	 * called.
 	 *
 	 * Note that this function will only be invoked in the context of an
-	 * atomic commit. It will not be invoked from &drm_bridge_post_disable.
+	 * atomic commit. It will not be invoked from
+	 * &drm_bridge_chain_post_disable.
 	 * It would be prudent to also provide an implementation of
 	 * @post_disable if you are expecting driver calls into
-	 * &drm_bridge_post_disable.
+	 * &drm_bridge_chain_post_disable.
 	 *
 	 * The @atomic_post_disable callback is optional.
 	 */
 	void (*atomic_post_disable)(struct drm_bridge *bridge,
-				    struct drm_atomic_state *state);
+				    struct drm_atomic_state *old_state);
 };
 
 /**
@@ -380,8 +384,8 @@ struct drm_bridge {
 	struct drm_device *dev;
 	/** @encoder: encoder to which this bridge is connected */
 	struct drm_encoder *encoder;
-	/** @next: the next bridge in the encoder chain */
-	struct drm_bridge *next;
+	/** @chain_node: used to form a bridge chain */
+	struct list_head chain_node;
 #ifdef CONFIG_OF
 	/** @of_node: device node pointer to the bridge */
 	struct device_node *of_node;
@@ -406,27 +410,86 @@ struct drm_bridge *of_drm_find_bridge(struct device_node *np);
 int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge,
 		      struct drm_bridge *previous);
 
-bool drm_bridge_mode_fixup(struct drm_bridge *bridge,
-			   const struct drm_display_mode *mode,
-			   struct drm_display_mode *adjusted_mode);
-enum drm_mode_status drm_bridge_mode_valid(struct drm_bridge *bridge,
-					   const struct drm_display_mode *mode);
-void drm_bridge_disable(struct drm_bridge *bridge);
-void drm_bridge_post_disable(struct drm_bridge *bridge);
-void drm_bridge_mode_set(struct drm_bridge *bridge,
-			 const struct drm_display_mode *mode,
-			 const struct drm_display_mode *adjusted_mode);
-void drm_bridge_pre_enable(struct drm_bridge *bridge);
-void drm_bridge_enable(struct drm_bridge *bridge);
+/**
+ * drm_bridge_get_next_bridge() - Get the next bridge in the chain
+ * @bridge: bridge object
+ *
+ * RETURNS:
+ * the next bridge in the chain after @bridge, or NULL if @bridge is the last.
+ */
+static inline struct drm_bridge *
+drm_bridge_get_next_bridge(struct drm_bridge *bridge)
+{
+	if (list_is_last(&bridge->chain_node, &bridge->encoder->bridge_chain))
+		return NULL;
+
+	return list_next_entry(bridge, chain_node);
+}
+
+/**
+ * drm_bridge_get_prev_bridge() - Get the previous bridge in the chain
+ * @bridge: bridge object
+ *
+ * RETURNS:
+ * the previous bridge in the chain, or NULL if @bridge is the first.
+ */
+static inline struct drm_bridge *
+drm_bridge_get_prev_bridge(struct drm_bridge *bridge)
+{
+	if (list_is_first(&bridge->chain_node, &bridge->encoder->bridge_chain))
+		return NULL;
+
+	return list_prev_entry(bridge, chain_node);
+}
+
+/**
+ * drm_bridge_chain_get_first_bridge() - Get the first bridge in the chain
+ * @encoder: encoder object
+ *
+ * RETURNS:
+ * the first bridge in the chain, or NULL if @encoder has no bridge attached
+ * to it.
+ */
+static inline struct drm_bridge *
+drm_bridge_chain_get_first_bridge(struct drm_encoder *encoder)
+{
+	return list_first_entry_or_null(&encoder->bridge_chain,
+					struct drm_bridge, chain_node);
+}
+
+/**
+ * drm_for_each_bridge_in_chain() - Iterate over all bridges present in a chain
+ * @encoder: the encoder to iterate bridges on
+ * @bridge: a bridge pointer updated to point to the current bridge at each
+ *	    iteration
+ *
+ * Iterate over all bridges present in the bridge chain attached to @encoder.
+ */
+#define drm_for_each_bridge_in_chain(encoder, bridge)			\
+	list_for_each_entry(bridge, &(encoder)->bridge_chain, chain_node)
+
+bool drm_bridge_chain_mode_fixup(struct drm_bridge *bridge,
+				 const struct drm_display_mode *mode,
+				 struct drm_display_mode *adjusted_mode);
+enum drm_mode_status
+drm_bridge_chain_mode_valid(struct drm_bridge *bridge,
+			    const struct drm_display_mode *mode);
+void drm_bridge_chain_disable(struct drm_bridge *bridge);
+void drm_bridge_chain_post_disable(struct drm_bridge *bridge);
+void drm_bridge_chain_mode_set(struct drm_bridge *bridge,
+			       const struct drm_display_mode *mode,
+			       const struct drm_display_mode *adjusted_mode);
+void drm_bridge_chain_pre_enable(struct drm_bridge *bridge);
+void drm_bridge_chain_enable(struct drm_bridge *bridge);
 
-void drm_atomic_bridge_disable(struct drm_bridge *bridge,
-			       struct drm_atomic_state *state);
-void drm_atomic_bridge_post_disable(struct drm_bridge *bridge,
+void drm_atomic_bridge_chain_disable(struct drm_bridge *bridge,
+				     struct drm_atomic_state *state);
+void drm_atomic_bridge_chain_post_disable(struct drm_bridge *bridge,
+					  struct drm_atomic_state *state);
+void drm_atomic_bridge_chain_pre_enable(struct drm_bridge *bridge,
+					struct drm_atomic_state *state);
+void drm_atomic_bridge_chain_enable(struct drm_bridge *bridge,
 				    struct drm_atomic_state *state);
-void drm_atomic_bridge_pre_enable(struct drm_bridge *bridge,
-				  struct drm_atomic_state *state);
-void drm_atomic_bridge_enable(struct drm_bridge *bridge,
-			      struct drm_atomic_state *state);
 
 #ifdef CONFIG_DRM_PANEL_BRIDGE
 struct drm_bridge *drm_panel_bridge_add(struct drm_panel *panel);
@@ -438,6 +501,7 @@ struct drm_bridge *devm_drm_panel_bridge_add(struct device *dev,
 struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev,
 						   struct drm_panel *panel,
 						   u32 connector_type);
+struct drm_connector *drm_panel_bridge_connector(struct drm_bridge *bridge);
 #endif
 
 #endif
diff --git a/include/drm/drm_color_mgmt.h b/include/drm/drm_color_mgmt.h
index d1c662d92ab7..81c298488b0c 100644
--- a/include/drm/drm_color_mgmt.h
+++ b/include/drm/drm_color_mgmt.h
@@ -29,7 +29,30 @@
 struct drm_crtc;
 struct drm_plane;
 
-uint32_t drm_color_lut_extract(uint32_t user_input, uint32_t bit_precision);
+/**
+ * drm_color_lut_extract - clamp and round LUT entries
+ * @user_input: input value
+ * @bit_precision: number of bits the hw LUT supports
+ *
+ * Extract a degamma/gamma LUT value provided by user (in the form of
+ * &drm_color_lut entries) and round it to the precision supported by the
+ * hardware.
+ */
+static inline u32 drm_color_lut_extract(u32 user_input, int bit_precision)
+{
+	u32 val = user_input;
+	u32 max = 0xffff >> (16 - bit_precision);
+
+	/* Round only if we're not using full precision. */
+	if (bit_precision < 16) {
+		val += 1UL << (16 - bit_precision - 1);
+		val >>= 16 - bit_precision;
+	}
+
+	return clamp_val(val, 0, max);
+}
+
+u64 drm_color_ctm_s31_32_to_qm_n(u64 user_input, u32 m, u32 n);
 
 void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc,
 				uint degamma_lut_size,
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index 5f8c3389d46f..221910948b37 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -188,19 +188,19 @@ struct drm_hdmi_info {
 
 	/**
 	 * @y420_vdb_modes: bitmap of modes which can support ycbcr420
-	 * output only (not normal RGB/YCBCR444/422 outputs). There are total
-	 * 107 VICs defined by CEA-861-F spec, so the size is 128 bits to map
-	 * upto 128 VICs;
+	 * output only (not normal RGB/YCBCR444/422 outputs). The max VIC
+	 * defined by the CEA-861-G spec is 219, so the size is 256 bits to map
+	 * up to 256 VICs.
 	 */
-	unsigned long y420_vdb_modes[BITS_TO_LONGS(128)];
+	unsigned long y420_vdb_modes[BITS_TO_LONGS(256)];
 
 	/**
 	 * @y420_cmdb_modes: bitmap of modes which can support ycbcr420
-	 * output also, along with normal HDMI outputs. There are total 107
-	 * VICs defined by CEA-861-F spec, so the size is 128 bits to map upto
-	 * 128 VICs;
+	 * output also, along with normal HDMI outputs. The max VIC defined by
+	 * the CEA-861-G spec is 219, so the size is 256 bits to map up to 256
+	 * VICs.
 	 */
-	unsigned long y420_cmdb_modes[BITS_TO_LONGS(128)];
+	unsigned long y420_cmdb_modes[BITS_TO_LONGS(256)];
 
 	/** @y420_cmdb_map: bitmap of SVD index, to extraxt vcb modes */
 	u64 y420_cmdb_map;
@@ -1070,6 +1070,14 @@ struct drm_cmdline_mode {
 	unsigned int rotation_reflection;
 
 	/**
+	 * @panel_orientation:
+	 *
+	 * drm-connector "panel orientation" property override value,
+	 * DRM_MODE_PANEL_ORIENTATION_UNKNOWN if not set.
+	 */
+	enum drm_panel_orientation panel_orientation;
+
+	/**
 	 * @tv_margins: TV margins to apply to the mode.
 	 */
 	struct drm_connector_tv_margins tv_margins;
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index 51ecb5112ef8..bc04467f7c3a 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -307,7 +307,7 @@
 # define DP_DSC_THROUGHPUT_MODE_0_900       (12 << 0)
 # define DP_DSC_THROUGHPUT_MODE_0_950       (13 << 0)
 # define DP_DSC_THROUGHPUT_MODE_0_1000      (14 << 0)
-# define DP_DSC_THROUGHPUT_MODE_0_170       (15 << 4)
+# define DP_DSC_THROUGHPUT_MODE_0_170       (15 << 0) /* 1.4a */
 # define DP_DSC_THROUGHPUT_MODE_1_MASK      (0xf << 4)
 # define DP_DSC_THROUGHPUT_MODE_1_SHIFT     4
 # define DP_DSC_THROUGHPUT_MODE_1_UPSUPPORTED 0
@@ -1042,6 +1042,8 @@
 #define DP_SYMBOL_ERROR_COUNT_LANE2_PHY_REPEATER1	    0xf0039 /* 1.3 */
 #define DP_SYMBOL_ERROR_COUNT_LANE3_PHY_REPEATER1	    0xf003b /* 1.3 */
 #define DP_FEC_STATUS_PHY_REPEATER1			    0xf0290 /* 1.4 */
+#define DP_FEC_ERROR_COUNT_PHY_REPEATER1                    0xf0291 /* 1.4 */
+#define DP_FEC_CAPABILITY_PHY_REPEATER1                     0xf0294 /* 1.4a */
 
 /* Repeater modes */
 #define DP_PHY_REPEATER_MODE_TRANSPARENT		    0x55    /* 1.3 */
@@ -1463,6 +1465,7 @@ int drm_dp_downstream_id(struct drm_dp_aux *aux, char id[6]);
 void drm_dp_downstream_debug(struct seq_file *m, const u8 dpcd[DP_RECEIVER_CAP_SIZE],
 			     const u8 port_cap[4], struct drm_dp_aux *aux);
 
+void drm_dp_remote_aux_init(struct drm_dp_aux *aux);
 void drm_dp_aux_init(struct drm_dp_aux *aux);
 int drm_dp_aux_register(struct drm_dp_aux *aux);
 void drm_dp_aux_unregister(struct drm_dp_aux *aux);
@@ -1520,6 +1523,13 @@ enum drm_dp_quirk {
 	 * The driver should ignore SINK_COUNT during detection.
 	 */
 	DP_DPCD_QUIRK_NO_SINK_COUNT,
+	/**
+	 * @DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD:
+	 *
+	 * The device supports MST DSC despite not supporting Virtual DPCD.
+	 * The DSC caps can be read from the physical aux instead.
+	 */
+	DP_DPCD_QUIRK_DSC_WITHOUT_VIRTUAL_DPCD,
 };
 
 /**
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index c1bda7030e2d..bcb39da9adb4 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -156,6 +156,8 @@ struct drm_dp_mst_port {
 	 * audio-capable.
 	 */
 	bool has_audio;
+
+	bool fec_capable;
 };
 
 /**
@@ -383,6 +385,7 @@ struct drm_dp_port_number_req {
 
 struct drm_dp_enum_path_resources_ack_reply {
 	u8 port_number;
+	bool fec_capable;
 	u16 full_payload_bw_number;
 	u16 avail_payload_bw_number;
 };
@@ -499,6 +502,8 @@ struct drm_dp_payload {
 struct drm_dp_vcpi_allocation {
 	struct drm_dp_mst_port *port;
 	int vcpi;
+	int pbn;
+	bool dsc_enabled;
 	struct list_head next;
 };
 
@@ -561,7 +566,8 @@ struct drm_dp_mst_topology_mgr {
 	struct drm_dp_sideband_msg_rx up_req_recv;
 
 	/**
-	 * @lock: protects mst state, primary, dpcd.
+	 * @lock: protects @mst_state, @mst_primary, @dpcd, and
+	 * @payload_id_table_cleared.
 	 */
 	struct mutex lock;
 
@@ -576,7 +582,14 @@ struct drm_dp_mst_topology_mgr {
 	 * @mst_state: If this manager is enabled for an MST capable port. False
 	 * if no MST sink/branch devices is connected.
 	 */
-	bool mst_state;
+	bool mst_state : 1;
+
+	/**
+	 * @payload_id_table_cleared: Whether or not we've cleared the payload
+	 * ID table for @mst_primary. Protected by @lock.
+	 */
+	bool payload_id_table_cleared : 1;
+
 	/**
 	 * @mst_primary: Pointer to the primary/first branch device.
 	 */
@@ -725,8 +738,7 @@ bool drm_dp_mst_port_has_audio(struct drm_dp_mst_topology_mgr *mgr,
 struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port);
 
 
-int drm_dp_calc_pbn_mode(int clock, int bpp);
-
+int drm_dp_calc_pbn_mode(int clock, int bpp, bool dsc);
 
 bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr,
 			      struct drm_dp_mst_port *port, int pbn, int slots);
@@ -775,7 +787,15 @@ struct drm_dp_mst_topology_state *drm_atomic_get_mst_topology_state(struct drm_a
 int __must_check
 drm_dp_atomic_find_vcpi_slots(struct drm_atomic_state *state,
 			      struct drm_dp_mst_topology_mgr *mgr,
-			      struct drm_dp_mst_port *port, int pbn);
+			      struct drm_dp_mst_port *port, int pbn,
+			      int pbn_div);
+int drm_dp_mst_atomic_enable_dsc(struct drm_atomic_state *state,
+				 struct drm_dp_mst_port *port,
+				 int pbn, int pbn_div,
+				 bool enable);
+int __must_check
+drm_dp_mst_add_affected_dsc_crtcs(struct drm_atomic_state *state,
+				  struct drm_dp_mst_topology_mgr *mgr);
 int __must_check
 drm_dp_atomic_release_vcpi_slots(struct drm_atomic_state *state,
 				 struct drm_dp_mst_topology_mgr *mgr,
@@ -787,6 +807,8 @@ int __must_check drm_dp_mst_atomic_check(struct drm_atomic_state *state);
 void drm_dp_mst_get_port_malloc(struct drm_dp_mst_port *port);
 void drm_dp_mst_put_port_malloc(struct drm_dp_mst_port *port);
 
+struct drm_dp_aux *drm_dp_mst_dsc_aux_for_port(struct drm_dp_mst_port *port);
+
 extern const struct drm_private_state_funcs drm_dp_mst_topology_state_funcs;
 
 /**
diff --git a/include/drm/drm_encoder.h b/include/drm/drm_encoder.h
index f06164f44efe..5623994b6e9e 100644
--- a/include/drm/drm_encoder.h
+++ b/include/drm/drm_encoder.h
@@ -172,7 +172,12 @@ struct drm_encoder {
 	 * &drm_connector_state.crtc.
 	 */
 	struct drm_crtc *crtc;
-	struct drm_bridge *bridge;
+
+	/**
+	 * @bridge_chain: Bridges attached to this encoder.
+	 */
+	struct list_head bridge_chain;
+
 	const struct drm_encoder_funcs *funcs;
 	const struct drm_encoder_helper_funcs *helper_private;
 };
diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h
index 4becb09975a4..795aea1d0a25 100644
--- a/include/drm/drm_fb_cma_helper.h
+++ b/include/drm/drm_fb_cma_helper.h
@@ -2,6 +2,8 @@
 #ifndef __DRM_FB_CMA_HELPER_H__
 #define __DRM_FB_CMA_HELPER_H__
 
+#include <linux/types.h>
+
 struct drm_framebuffer;
 struct drm_plane_state;
 
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 2338e9f94a03..1c6633da0f91 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -231,8 +231,6 @@ void drm_fb_helper_fill_info(struct fb_info *info,
 			     struct drm_fb_helper *fb_helper,
 			     struct drm_fb_helper_surface_size *sizes);
 
-void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper);
-
 void drm_fb_helper_deferred_io(struct fb_info *info,
 			       struct list_head *pagelist);
 
@@ -269,18 +267,9 @@ int drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper, int bpp_sel);
 int drm_fb_helper_debug_enter(struct fb_info *info);
 int drm_fb_helper_debug_leave(struct fb_info *info);
 
-int drm_fb_helper_fbdev_setup(struct drm_device *dev,
-			      struct drm_fb_helper *fb_helper,
-			      const struct drm_fb_helper_funcs *funcs,
-			      unsigned int preferred_bpp,
-			      unsigned int max_conn_count);
-void drm_fb_helper_fbdev_teardown(struct drm_device *dev);
-
 void drm_fb_helper_lastclose(struct drm_device *dev);
 void drm_fb_helper_output_poll_changed(struct drm_device *dev);
 
-int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
-				struct drm_fb_helper_surface_size *sizes);
 int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp);
 #else
 static inline void drm_fb_helper_prepare(struct drm_device *dev,
@@ -363,10 +352,6 @@ static inline int drm_fb_helper_ioctl(struct fb_info *info, unsigned int cmd,
 	return 0;
 }
 
-static inline void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper)
-{
-}
-
 static inline void drm_fb_helper_deferred_io(struct fb_info *info,
 					     struct list_head *pagelist)
 {
@@ -452,24 +437,6 @@ static inline int drm_fb_helper_debug_leave(struct fb_info *info)
 	return 0;
 }
 
-static inline int
-drm_fb_helper_fbdev_setup(struct drm_device *dev,
-			  struct drm_fb_helper *fb_helper,
-			  const struct drm_fb_helper_funcs *funcs,
-			  unsigned int preferred_bpp,
-			  unsigned int max_conn_count)
-{
-	/* So drivers can use it to free the struct */
-	dev->fb_helper = fb_helper;
-
-	return 0;
-}
-
-static inline void drm_fb_helper_fbdev_teardown(struct drm_device *dev)
-{
-	dev->fb_helper = NULL;
-}
-
 static inline void drm_fb_helper_lastclose(struct drm_device *dev)
 {
 }
@@ -479,13 +446,6 @@ static inline void drm_fb_helper_output_poll_changed(struct drm_device *dev)
 }
 
 static inline int
-drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
-			    struct drm_fb_helper_surface_size *sizes)
-{
-	return 0;
-}
-
-static inline int
 drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
 {
 	return 0;
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 67af60bb527a..8b099b347817 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -42,6 +42,7 @@ struct dma_fence;
 struct drm_file;
 struct drm_device;
 struct device;
+struct file;
 
 /*
  * FIXME: Not sure we want to have drm_minor here in the end, but to avoid
@@ -387,4 +388,6 @@ void drm_event_cancel_free(struct drm_device *dev,
 void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e);
 void drm_send_event(struct drm_device *dev, struct drm_pending_event *e);
 
+struct file *mock_drm_getfile(struct drm_minor *minor, unsigned int flags);
+
 #endif /* _DRM_FILE_H_ */
diff --git a/include/drm/drm_fourcc.h b/include/drm/drm_fourcc.h
index 306d1efeb5e0..156b122c0ad5 100644
--- a/include/drm/drm_fourcc.h
+++ b/include/drm/drm_fourcc.h
@@ -78,7 +78,7 @@ struct drm_format_info {
 		 * triplet @char_per_block, @block_w, @block_h for better
 		 * describing the pixel format.
 		 */
-		u8 cpp[3];
+		u8 cpp[4];
 
 		/**
 		 * @char_per_block:
@@ -104,7 +104,7 @@ struct drm_format_info {
 		 * information from their drm_mode_config.get_format_info hook
 		 * if they want the core to be validating the pitch.
 		 */
-		u8 char_per_block[3];
+		u8 char_per_block[4];
 	};
 
 	/**
@@ -113,7 +113,7 @@ struct drm_format_info {
 	 * Block width in pixels, this is intended to be accessed through
 	 * drm_format_info_block_width()
 	 */
-	u8 block_w[3];
+	u8 block_w[4];
 
 	/**
 	 * @block_h:
@@ -121,7 +121,7 @@ struct drm_format_info {
 	 * Block height in pixels, this is intended to be accessed through
 	 * drm_format_info_block_height()
 	 */
-	u8 block_h[3];
+	u8 block_h[4];
 
 	/** @hsub: Horizontal chroma subsampling factor */
 	u8 hsub;
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 97a48165642c..0b375069cd48 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -159,9 +159,7 @@ struct drm_gem_object_funcs {
 	 *
 	 * The callback is used by by both drm_gem_mmap_obj() and
 	 * drm_gem_prime_mmap().  When @mmap is present @vm_ops is not
-	 * used, the @mmap callback must set vma->vm_ops instead. The @mmap
-	 * callback is always called with a 0 offset. The caller will remove
-	 * the fake offset as necessary.
+	 * used, the @mmap callback must set vma->vm_ops instead.
 	 */
 	int (*mmap)(struct drm_gem_object *obj, struct vm_area_struct *vma);
 
diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h
index e040541a105f..573e9fd109bf 100644
--- a/include/drm/drm_gem_vram_helper.h
+++ b/include/drm/drm_gem_vram_helper.h
@@ -16,7 +16,6 @@ struct drm_mode_create_dumb;
 struct drm_plane;
 struct drm_plane_state;
 struct drm_simple_display_pipe;
-struct drm_vram_mm_funcs;
 struct filp;
 struct vm_area_struct;
 
@@ -94,10 +93,8 @@ static inline struct drm_gem_vram_object *drm_gem_vram_of_gem(
 }
 
 struct drm_gem_vram_object *drm_gem_vram_create(struct drm_device *dev,
-						struct ttm_bo_device *bdev,
 						size_t size,
-						unsigned long pg_align,
-						bool interruptible);
+						unsigned long pg_align);
 void drm_gem_vram_put(struct drm_gem_vram_object *gbo);
 u64 drm_gem_vram_mmap_offset(struct drm_gem_vram_object *gbo);
 s64 drm_gem_vram_offset(struct drm_gem_vram_object *gbo);
@@ -111,9 +108,8 @@ void drm_gem_vram_vunmap(struct drm_gem_vram_object *gbo, void *vaddr);
 
 int drm_gem_vram_fill_create_dumb(struct drm_file *file,
 				  struct drm_device *dev,
-				  struct ttm_bo_device *bdev,
 				  unsigned long pg_align,
-				  bool interruptible,
+				  unsigned long pitch_align,
 				  struct drm_mode_create_dumb *args);
 
 /*
diff --git a/include/drm/drm_legacy.h b/include/drm/drm_legacy.h
index 58dc0c04bf99..5745710453c8 100644
--- a/include/drm/drm_legacy.h
+++ b/include/drm/drm_legacy.h
@@ -38,7 +38,9 @@
 #include <drm/drm_hashtab.h>
 
 struct drm_device;
+struct drm_driver;
 struct file;
+struct pci_driver;
 
 /*
  * Legacy Support for palateontologic DRM drivers
@@ -188,8 +190,33 @@ do {										\
 void drm_legacy_idlelock_take(struct drm_lock_data *lock);
 void drm_legacy_idlelock_release(struct drm_lock_data *lock);
 
-/* drm_pci.c dma alloc wrappers */
+/* drm_pci.c */
+
+#ifdef CONFIG_PCI
+
 void __drm_legacy_pci_free(struct drm_device *dev, drm_dma_handle_t * dmah);
+int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver);
+void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver);
+
+#else
+
+static inline void __drm_legacy_pci_free(struct drm_device *dev,
+					 drm_dma_handle_t *dmah)
+{
+}
+
+static inline int drm_legacy_pci_init(struct drm_driver *driver,
+				      struct pci_driver *pdriver)
+{
+	return -EINVAL;
+}
+
+static inline void drm_legacy_pci_exit(struct drm_driver *driver,
+				       struct pci_driver *pdriver)
+{
+}
+
+#endif
 
 /* drm_memory.c */
 void drm_legacy_ioremap(struct drm_local_map *map, struct drm_device *dev);
diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
index 13cf2ae59f6c..360e6377e84b 100644
--- a/include/drm/drm_mipi_dsi.h
+++ b/include/drm/drm_mipi_dsi.h
@@ -13,6 +13,7 @@
 
 struct mipi_dsi_host;
 struct mipi_dsi_device;
+struct drm_dsc_picture_parameter_set;
 
 /* request ACK from peripheral */
 #define MIPI_DSI_MSG_REQ_ACK	BIT(0)
@@ -228,6 +229,9 @@ int mipi_dsi_shutdown_peripheral(struct mipi_dsi_device *dsi);
 int mipi_dsi_turn_on_peripheral(struct mipi_dsi_device *dsi);
 int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi,
 					    u16 value);
+ssize_t mipi_dsi_compression_mode(struct mipi_dsi_device *dsi, bool enable);
+ssize_t mipi_dsi_picture_parameter_set(struct mipi_dsi_device *dsi,
+				       const struct drm_dsc_picture_parameter_set *pps);
 
 ssize_t mipi_dsi_generic_write(struct mipi_dsi_device *dsi, const void *payload,
 			       size_t size);
diff --git a/include/drm/drm_of.h b/include/drm/drm_of.h
index ead34ab5ca4e..b9b093add92e 100644
--- a/include/drm/drm_of.h
+++ b/include/drm/drm_of.h
@@ -16,6 +16,18 @@ struct drm_panel;
 struct drm_bridge;
 struct device_node;
 
+/**
+ * enum drm_lvds_dual_link_pixels - Pixel order of an LVDS dual-link connection
+ * @DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS: Even pixels are expected to be generated
+ *    from the first port, odd pixels from the second port
+ * @DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS: Odd pixels are expected to be generated
+ *    from the first port, even pixels from the second port
+ */
+enum drm_lvds_dual_link_pixels {
+	DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS = 0,
+	DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS = 1,
+};
+
 #ifdef CONFIG_OF
 uint32_t drm_of_crtc_port_mask(struct drm_device *dev,
 			    struct device_node *port);
@@ -35,6 +47,8 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 				int port, int endpoint,
 				struct drm_panel **panel,
 				struct drm_bridge **bridge);
+int drm_of_lvds_get_dual_link_pixel_order(const struct device_node *port1,
+					  const struct device_node *port2);
 #else
 static inline uint32_t drm_of_crtc_port_mask(struct drm_device *dev,
 					  struct device_node *port)
@@ -77,6 +91,13 @@ static inline int drm_of_find_panel_or_bridge(const struct device_node *np,
 {
 	return -EINVAL;
 }
+
+static inline int
+drm_of_lvds_get_dual_link_pixel_order(const struct device_node *port1,
+				      const struct device_node *port2)
+{
+	return -EINVAL;
+}
 #endif
 
 /*
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index ce8da64022b4..121f7aabccd1 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -28,6 +28,7 @@
 #include <linux/errno.h>
 #include <linux/list.h>
 
+struct backlight_device;
 struct device_node;
 struct drm_connector;
 struct drm_device;
@@ -59,12 +60,18 @@ struct display_timing;
  *
  * To save power when no video data is transmitted, a driver can power down
  * the panel. This is the job of the .unprepare() function.
+ *
+ * Backlight can be handled automatically if configured using
+ * drm_panel_of_backlight(). Then the driver does not need to implement the
+ * functionality to enable/disable backlight.
  */
 struct drm_panel_funcs {
 	/**
 	 * @prepare:
 	 *
 	 * Turn on panel and perform set up.
+	 *
+	 * This function is optional.
 	 */
 	int (*prepare)(struct drm_panel *panel);
 
@@ -72,6 +79,8 @@ struct drm_panel_funcs {
 	 * @enable:
 	 *
 	 * Enable panel (turn on back light, etc.).
+	 *
+	 * This function is optional.
 	 */
 	int (*enable)(struct drm_panel *panel);
 
@@ -79,6 +88,8 @@ struct drm_panel_funcs {
 	 * @disable:
 	 *
 	 * Disable panel (turn off back light, etc.).
+	 *
+	 * This function is optional.
 	 */
 	int (*disable)(struct drm_panel *panel);
 
@@ -86,22 +97,29 @@ struct drm_panel_funcs {
 	 * @unprepare:
 	 *
 	 * Turn off panel.
+	 *
+	 * This function is optional.
 	 */
 	int (*unprepare)(struct drm_panel *panel);
 
 	/**
 	 * @get_modes:
 	 *
-	 * Add modes to the connector that the panel is attached to and
-	 * return the number of modes added.
+	 * Add modes to the connector that the panel is attached to
+	 * and returns the number of modes added.
+	 *
+	 * This function is mandatory.
 	 */
-	int (*get_modes)(struct drm_panel *panel);
+	int (*get_modes)(struct drm_panel *panel,
+			 struct drm_connector *connector);
 
 	/**
 	 * @get_timings:
 	 *
 	 * Copy display timings into the provided array and return
 	 * the number of display timings available.
+	 *
+	 * This function is optional.
 	 */
 	int (*get_timings)(struct drm_panel *panel, unsigned int num_timings,
 			   struct display_timing *timings);
@@ -112,25 +130,22 @@ struct drm_panel_funcs {
  */
 struct drm_panel {
 	/**
-	 * @drm:
-	 *
-	 * DRM device owning the panel.
-	 */
-	struct drm_device *drm;
-
-	/**
-	 * @connector:
+	 * @dev:
 	 *
-	 * DRM connector that the panel is attached to.
+	 * Parent device of the panel.
 	 */
-	struct drm_connector *connector;
+	struct device *dev;
 
 	/**
-	 * @dev:
+	 * @backlight:
 	 *
-	 * Parent device of the panel.
+	 * Backlight device, used to turn on backlight after the call
+	 * to enable(), and to turn off backlight before the call to
+	 * disable().
+	 * backlight is set by drm_panel_of_backlight() and drivers
+	 * shall not assign it.
 	 */
-	struct device *dev;
+	struct backlight_device *backlight;
 
 	/**
 	 * @funcs:
@@ -172,7 +187,7 @@ int drm_panel_unprepare(struct drm_panel *panel);
 int drm_panel_enable(struct drm_panel *panel);
 int drm_panel_disable(struct drm_panel *panel);
 
-int drm_panel_get_modes(struct drm_panel *panel);
+int drm_panel_get_modes(struct drm_panel *panel, struct drm_connector *connector);
 
 #if defined(CONFIG_OF) && defined(CONFIG_DRM_PANEL)
 struct drm_panel *of_drm_find_panel(const struct device_node *np);
@@ -183,4 +198,13 @@ static inline struct drm_panel *of_drm_find_panel(const struct device_node *np)
 }
 #endif
 
+#if IS_REACHABLE(CONFIG_BACKLIGHT_CLASS_DEVICE)
+int drm_panel_of_backlight(struct drm_panel *panel);
+#else
+static inline int drm_panel_of_backlight(struct drm_panel *panel)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/include/drm/drm_pci.h b/include/drm/drm_pci.h
index 8181e9e7cf1d..9031e217b506 100644
--- a/include/drm/drm_pci.h
+++ b/include/drm/drm_pci.h
@@ -39,23 +39,36 @@ struct drm_device;
 struct drm_driver;
 struct drm_master;
 
+#ifdef CONFIG_PCI
+
 struct drm_dma_handle *drm_pci_alloc(struct drm_device *dev, size_t size,
 				     size_t align);
 void drm_pci_free(struct drm_device *dev, struct drm_dma_handle * dmah);
 
-int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver);
-void drm_legacy_pci_exit(struct drm_driver *driver, struct pci_driver *pdriver);
-#ifdef CONFIG_PCI
 int drm_get_pci_dev(struct pci_dev *pdev,
 		    const struct pci_device_id *ent,
 		    struct drm_driver *driver);
+
 #else
+
+static inline struct drm_dma_handle *drm_pci_alloc(struct drm_device *dev,
+						   size_t size, size_t align)
+{
+	return NULL;
+}
+
+static inline void drm_pci_free(struct drm_device *dev,
+				struct drm_dma_handle *dmah)
+{
+}
+
 static inline int drm_get_pci_dev(struct pci_dev *pdev,
 				  const struct pci_device_id *ent,
 				  struct drm_driver *driver)
 {
 	return -ENOSYS;
 }
+
 #endif
 
 #endif /* _DRM_PCI_H_ */
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index 5b8049992c24..8f99d389792d 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -34,7 +34,8 @@
 
 #include <drm/drm.h>
 
-extern unsigned int drm_debug;
+/* Do *not* use outside of drm_print.[ch]! */
+extern unsigned int __drm_debug;
 
 /**
  * DOC: print
@@ -248,87 +249,90 @@ static inline struct drm_printer drm_err_printer(const char *prefix)
 	return p;
 }
 
-/*
- * The following categories are defined:
- *
- * CORE: Used in the generic drm code: drm_ioctl.c, drm_mm.c, drm_memory.c, ...
- *	 This is the category used by the DRM_DEBUG() macro.
- *
- * DRIVER: Used in the vendor specific part of the driver: i915, radeon, ...
- *	   This is the category used by the DRM_DEBUG_DRIVER() macro.
- *
- * KMS: used in the modesetting code.
- *	This is the category used by the DRM_DEBUG_KMS() macro.
- *
- * PRIME: used in the prime code.
- *	  This is the category used by the DRM_DEBUG_PRIME() macro.
+/**
+ * enum drm_debug_category - The DRM debug categories
  *
- * ATOMIC: used in the atomic code.
- *	  This is the category used by the DRM_DEBUG_ATOMIC() macro.
+ * Each of the DRM debug logging macros use a specific category, and the logging
+ * is filtered by the drm.debug module parameter. This enum specifies the values
+ * for the interface.
  *
- * VBL: used for verbose debug message in the vblank code
- *	  This is the category used by the DRM_DEBUG_VBL() macro.
+ * Each DRM_DEBUG_<CATEGORY> macro logs to DRM_UT_<CATEGORY> category, except
+ * DRM_DEBUG() logs to DRM_UT_CORE.
  *
- * Enabling verbose debug messages is done through the drm.debug parameter,
- * each category being enabled by a bit.
+ * Enabling verbose debug messages is done through the drm.debug parameter, each
+ * category being enabled by a bit:
  *
- * drm.debug=0x1 will enable CORE messages
- * drm.debug=0x2 will enable DRIVER messages
- * drm.debug=0x3 will enable CORE and DRIVER messages
- * ...
- * drm.debug=0x3f will enable all messages
+ *  - drm.debug=0x1 will enable CORE messages
+ *  - drm.debug=0x2 will enable DRIVER messages
+ *  - drm.debug=0x3 will enable CORE and DRIVER messages
+ *  - ...
+ *  - drm.debug=0x1ff will enable all messages
  *
  * An interesting feature is that it's possible to enable verbose logging at
- * run-time by echoing the debug value in its sysfs node:
+ * run-time by echoing the debug value in its sysfs node::
+ *
  *   # echo 0xf > /sys/module/drm/parameters/debug
+ *
  */
-#define DRM_UT_NONE		0x00
-#define DRM_UT_CORE		0x01
-#define DRM_UT_DRIVER		0x02
-#define DRM_UT_KMS		0x04
-#define DRM_UT_PRIME		0x08
-#define DRM_UT_ATOMIC		0x10
-#define DRM_UT_VBL		0x20
-#define DRM_UT_STATE		0x40
-#define DRM_UT_LEASE		0x80
-#define DRM_UT_DP		0x100
-
-static inline bool drm_debug_enabled(unsigned int category)
+enum drm_debug_category {
+	/**
+	 * @DRM_UT_CORE: Used in the generic drm code: drm_ioctl.c, drm_mm.c,
+	 * drm_memory.c, ...
+	 */
+	DRM_UT_CORE		= 0x01,
+	/**
+	 * @DRM_UT_DRIVER: Used in the vendor specific part of the driver: i915,
+	 * radeon, ... macro.
+	 */
+	DRM_UT_DRIVER		= 0x02,
+	/**
+	 * @DRM_UT_KMS: Used in the modesetting code.
+	 */
+	DRM_UT_KMS		= 0x04,
+	/**
+	 * @DRM_UT_PRIME: Used in the prime code.
+	 */
+	DRM_UT_PRIME		= 0x08,
+	/**
+	 * @DRM_UT_ATOMIC: Used in the atomic code.
+	 */
+	DRM_UT_ATOMIC		= 0x10,
+	/**
+	 * @DRM_UT_VBL: Used for verbose debug message in the vblank code.
+	 */
+	DRM_UT_VBL		= 0x20,
+	/**
+	 * @DRM_UT_STATE: Used for verbose atomic state debugging.
+	 */
+	DRM_UT_STATE		= 0x40,
+	/**
+	 * @DRM_UT_LEASE: Used in the lease code.
+	 */
+	DRM_UT_LEASE		= 0x80,
+	/**
+	 * @DRM_UT_DP: Used in the DP code.
+	 */
+	DRM_UT_DP		= 0x100,
+};
+
+static inline bool drm_debug_enabled(enum drm_debug_category category)
 {
-	return unlikely(drm_debug & category);
+	return unlikely(__drm_debug & category);
 }
 
+/*
+ * struct device based logging
+ *
+ * Prefer drm_device based logging over device or prink based logging.
+ */
+
 __printf(3, 4)
 void drm_dev_printk(const struct device *dev, const char *level,
 		    const char *format, ...);
 __printf(3, 4)
-void drm_dev_dbg(const struct device *dev, unsigned int category,
+void drm_dev_dbg(const struct device *dev, enum drm_debug_category category,
 		 const char *format, ...);
 
-__printf(2, 3)
-void drm_dbg(unsigned int category, const char *format, ...);
-__printf(1, 2)
-void drm_err(const char *format, ...);
-
-/* Macros to make printk easier */
-
-#define _DRM_PRINTK(once, level, fmt, ...)				\
-	printk##once(KERN_##level "[" DRM_NAME "] " fmt, ##__VA_ARGS__)
-
-#define DRM_INFO(fmt, ...)						\
-	_DRM_PRINTK(, INFO, fmt, ##__VA_ARGS__)
-#define DRM_NOTE(fmt, ...)						\
-	_DRM_PRINTK(, NOTICE, fmt, ##__VA_ARGS__)
-#define DRM_WARN(fmt, ...)						\
-	_DRM_PRINTK(, WARNING, fmt, ##__VA_ARGS__)
-
-#define DRM_INFO_ONCE(fmt, ...)						\
-	_DRM_PRINTK(_once, INFO, fmt, ##__VA_ARGS__)
-#define DRM_NOTE_ONCE(fmt, ...)						\
-	_DRM_PRINTK(_once, NOTICE, fmt, ##__VA_ARGS__)
-#define DRM_WARN_ONCE(fmt, ...)						\
-	_DRM_PRINTK(_once, WARNING, fmt, ##__VA_ARGS__)
-
 /**
  * Error output.
  *
@@ -337,8 +341,6 @@ void drm_err(const char *format, ...);
  */
 #define DRM_DEV_ERROR(dev, fmt, ...)					\
 	drm_dev_printk(dev, KERN_ERR, "*ERROR* " fmt, ##__VA_ARGS__)
-#define DRM_ERROR(fmt, ...)						\
-	drm_err(fmt, ##__VA_ARGS__)
 
 /**
  * Rate limited error output.  Like DRM_ERROR() but won't flood the log.
@@ -355,10 +357,8 @@ void drm_err(const char *format, ...);
 	if (__ratelimit(&_rs))						\
 		DRM_DEV_ERROR(dev, fmt, ##__VA_ARGS__);			\
 })
-#define DRM_ERROR_RATELIMITED(fmt, ...)					\
-	DRM_DEV_ERROR_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
 
-#define DRM_DEV_INFO(dev, fmt, ...)					\
+#define DRM_DEV_INFO(dev, fmt, ...)				\
 	drm_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__)
 
 #define DRM_DEV_INFO_ONCE(dev, fmt, ...)				\
@@ -378,41 +378,18 @@ void drm_err(const char *format, ...);
  */
 #define DRM_DEV_DEBUG(dev, fmt, ...)					\
 	drm_dev_dbg(dev, DRM_UT_CORE, fmt, ##__VA_ARGS__)
-#define DRM_DEBUG(fmt, ...)						\
-	drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_DRIVER(dev, fmt, ...)				\
 	drm_dev_dbg(dev, DRM_UT_DRIVER,	fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_DRIVER(fmt, ...)					\
-	drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_KMS(dev, fmt, ...)				\
 	drm_dev_dbg(dev, DRM_UT_KMS, fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_KMS(fmt, ...)						\
-	drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_PRIME(dev, fmt, ...)				\
 	drm_dev_dbg(dev, DRM_UT_PRIME, fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_PRIME(fmt, ...)					\
-	drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_ATOMIC(dev, fmt, ...)				\
 	drm_dev_dbg(dev, DRM_UT_ATOMIC,	fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_ATOMIC(fmt, ...)					\
-	drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_VBL(dev, fmt, ...)				\
 	drm_dev_dbg(dev, DRM_UT_VBL, fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_VBL(fmt, ...)						\
-	drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__)
-
-#define DRM_DEBUG_LEASE(fmt, ...)					\
-	drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
-
 #define	DRM_DEV_DEBUG_DP(dev, fmt, ...)					\
 	drm_dev_dbg(dev, DRM_UT_DP, fmt, ## __VA_ARGS__)
-#define DRM_DEBUG_DP(fmt, ...)						\
-	drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__)
 
 #define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, category, fmt, ...)	\
 ({									\
@@ -432,24 +409,147 @@ void drm_err(const char *format, ...);
 #define DRM_DEV_DEBUG_RATELIMITED(dev, fmt, ...)			\
 	_DEV_DRM_DEFINE_DEBUG_RATELIMITED(dev, DRM_UT_CORE,		\
 					  fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_RATELIMITED(fmt, ...)					\
-	DRM_DEV_DEBUG_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_DRIVER_RATELIMITED(dev, fmt, ...)			\
 	_DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, DRM_UT_DRIVER,		\
 					  fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_DRIVER_RATELIMITED(fmt, ...)				\
-	DRM_DEV_DEBUG_DRIVER_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_KMS_RATELIMITED(dev, fmt, ...)			\
 	_DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, DRM_UT_KMS,		\
 					  fmt, ##__VA_ARGS__)
-#define DRM_DEBUG_KMS_RATELIMITED(fmt, ...)				\
-	DRM_DEV_DEBUG_KMS_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
-
 #define DRM_DEV_DEBUG_PRIME_RATELIMITED(dev, fmt, ...)			\
 	_DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, DRM_UT_PRIME,		\
 					  fmt, ##__VA_ARGS__)
+
+/*
+ * struct drm_device based logging
+ *
+ * Prefer drm_device based logging over device or prink based logging.
+ */
+
+/* Helper for struct drm_device based logging. */
+#define __drm_printk(drm, level, type, fmt, ...)			\
+	dev_##level##type((drm)->dev, "[drm] " fmt, ##__VA_ARGS__)
+
+
+#define drm_info(drm, fmt, ...)					\
+	__drm_printk((drm), info,, fmt, ##__VA_ARGS__)
+
+#define drm_notice(drm, fmt, ...)				\
+	__drm_printk((drm), notice,, fmt, ##__VA_ARGS__)
+
+#define drm_warn(drm, fmt, ...)					\
+	__drm_printk((drm), warn,, fmt, ##__VA_ARGS__)
+
+#define drm_err(drm, fmt, ...)					\
+	__drm_printk((drm), err,, "*ERROR* " fmt, ##__VA_ARGS__)
+
+
+#define drm_info_once(drm, fmt, ...)				\
+	__drm_printk((drm), info, _once, fmt, ##__VA_ARGS__)
+
+#define drm_notice_once(drm, fmt, ...)				\
+	__drm_printk((drm), notice, _once, fmt, ##__VA_ARGS__)
+
+#define drm_warn_once(drm, fmt, ...)				\
+	__drm_printk((drm), warn, _once, fmt, ##__VA_ARGS__)
+
+#define drm_err_once(drm, fmt, ...)				\
+	__drm_printk((drm), err, _once, "*ERROR* " fmt, ##__VA_ARGS__)
+
+
+#define drm_err_ratelimited(drm, fmt, ...)				\
+	__drm_printk((drm), err, _ratelimited, "*ERROR* " fmt, ##__VA_ARGS__)
+
+
+#define drm_dbg_core(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_CORE, fmt, ##__VA_ARGS__)
+#define drm_dbg(drm, fmt, ...)						\
+	drm_dev_dbg((drm)->dev, DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
+#define drm_dbg_kms(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_KMS, fmt, ##__VA_ARGS__)
+#define drm_dbg_prime(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_PRIME, fmt, ##__VA_ARGS__)
+#define drm_dbg_atomic(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
+#define drm_dbg_vbl(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_VBL, fmt, ##__VA_ARGS__)
+#define drm_dbg_state(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_STATE, fmt, ##__VA_ARGS__)
+#define drm_dbg_lease(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_LEASE, fmt, ##__VA_ARGS__)
+#define drm_dbg_dp(drm, fmt, ...)					\
+	drm_dev_dbg((drm)->dev, DRM_UT_DP, fmt, ##__VA_ARGS__)
+
+
+/*
+ * printk based logging
+ *
+ * Prefer drm_device based logging over device or prink based logging.
+ */
+
+__printf(2, 3)
+void __drm_dbg(enum drm_debug_category category, const char *format, ...);
+__printf(1, 2)
+void __drm_err(const char *format, ...);
+
+/* Macros to make printk easier */
+
+#define _DRM_PRINTK(once, level, fmt, ...)				\
+	printk##once(KERN_##level "[" DRM_NAME "] " fmt, ##__VA_ARGS__)
+
+#define DRM_INFO(fmt, ...)						\
+	_DRM_PRINTK(, INFO, fmt, ##__VA_ARGS__)
+#define DRM_NOTE(fmt, ...)						\
+	_DRM_PRINTK(, NOTICE, fmt, ##__VA_ARGS__)
+#define DRM_WARN(fmt, ...)						\
+	_DRM_PRINTK(, WARNING, fmt, ##__VA_ARGS__)
+
+#define DRM_INFO_ONCE(fmt, ...)						\
+	_DRM_PRINTK(_once, INFO, fmt, ##__VA_ARGS__)
+#define DRM_NOTE_ONCE(fmt, ...)						\
+	_DRM_PRINTK(_once, NOTICE, fmt, ##__VA_ARGS__)
+#define DRM_WARN_ONCE(fmt, ...)						\
+	_DRM_PRINTK(_once, WARNING, fmt, ##__VA_ARGS__)
+
+#define DRM_ERROR(fmt, ...)						\
+	__drm_err(fmt, ##__VA_ARGS__)
+
+#define DRM_ERROR_RATELIMITED(fmt, ...)					\
+	DRM_DEV_ERROR_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG(fmt, ...)						\
+	__drm_dbg(DRM_UT_CORE, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_DRIVER(fmt, ...)					\
+	__drm_dbg(DRM_UT_DRIVER, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_KMS(fmt, ...)						\
+	__drm_dbg(DRM_UT_KMS, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_PRIME(fmt, ...)					\
+	__drm_dbg(DRM_UT_PRIME, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_ATOMIC(fmt, ...)					\
+	__drm_dbg(DRM_UT_ATOMIC, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_VBL(fmt, ...)						\
+	__drm_dbg(DRM_UT_VBL, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_LEASE(fmt, ...)					\
+	__drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_DP(fmt, ...)						\
+	__drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__)
+
+
+#define DRM_DEBUG_RATELIMITED(fmt, ...)					\
+	DRM_DEV_DEBUG_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_DRIVER_RATELIMITED(fmt, ...)				\
+	DRM_DEV_DEBUG_DRIVER_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
+
+#define DRM_DEBUG_KMS_RATELIMITED(fmt, ...)				\
+	DRM_DEV_DEBUG_KMS_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
+
 #define DRM_DEBUG_PRIME_RATELIMITED(fmt, ...)				\
 	DRM_DEV_DEBUG_PRIME_RATELIMITED(NULL, fmt, ##__VA_ARGS__)
 
diff --git a/include/drm/drm_rect.h b/include/drm/drm_rect.h
index cd0106135b6a..57a3be9e53e4 100644
--- a/include/drm/drm_rect.h
+++ b/include/drm/drm_rect.h
@@ -24,6 +24,8 @@
 #ifndef DRM_RECT_H
 #define DRM_RECT_H
 
+#include <linux/types.h>
+
 /**
  * DOC: rect utils
  *
diff --git a/include/drm/drm_scdc_helper.h b/include/drm/drm_scdc_helper.h
index f92eb2094d6b..6a483533aae4 100644
--- a/include/drm/drm_scdc_helper.h
+++ b/include/drm/drm_scdc_helper.h
@@ -50,9 +50,9 @@
 #define  SCDC_READ_REQUEST_ENABLE (1 << 0)
 
 #define SCDC_STATUS_FLAGS_0 0x40
-#define  SCDC_CH2_LOCK (1 < 3)
-#define  SCDC_CH1_LOCK (1 < 2)
-#define  SCDC_CH0_LOCK (1 < 1)
+#define  SCDC_CH2_LOCK (1 << 3)
+#define  SCDC_CH1_LOCK (1 << 2)
+#define  SCDC_CH0_LOCK (1 << 1)
 #define  SCDC_CH_LOCK_MASK (SCDC_CH2_LOCK | SCDC_CH1_LOCK | SCDC_CH0_LOCK)
 #define  SCDC_CLOCK_DETECT (1 << 0)
 
diff --git a/include/drm/drm_util.h b/include/drm/drm_util.h
index 07b8e9f04599..79952d8c4bba 100644
--- a/include/drm/drm_util.h
+++ b/include/drm/drm_util.h
@@ -41,7 +41,7 @@
  * Use EXPORT_SYMBOL_FOR_TESTS_ONLY() for functions that shall
  * only be visible for drmselftests.
  */
-#if defined(CONFIG_DRM_DEBUG_SELFTEST_MODULE)
+#if defined(CONFIG_DRM_EXPORT_FOR_TESTS)
 #define EXPORT_SYMBOL_FOR_TESTS_ONLY(x) EXPORT_SYMBOL(x)
 #else
 #define EXPORT_SYMBOL_FOR_TESTS_ONLY(x)
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 684692a8ed76..9e71be129c30 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -52,9 +52,9 @@ enum drm_sched_priority {
  * @list: used to append this struct to the list of entities in the
  *        runqueue.
  * @rq: runqueue on which this entity is currently scheduled.
- * @rq_list: a list of run queues on which jobs from this entity can
- *           be scheduled
- * @num_rq_list: number of run queues in the rq_list
+ * @sched_list: a list of drm_gpu_schedulers on which jobs from this entity can
+ *              be scheduled
+ * @num_sched_list: number of drm_gpu_schedulers in the sched_list.
  * @rq_lock: lock to modify the runqueue to which this entity belongs.
  * @job_queue: the list of jobs of this entity.
  * @fence_seq: a linearly increasing seqno incremented with each
@@ -81,8 +81,9 @@ enum drm_sched_priority {
 struct drm_sched_entity {
 	struct list_head		list;
 	struct drm_sched_rq		*rq;
-	struct drm_sched_rq		**rq_list;
-	unsigned int                    num_rq_list;
+	struct drm_gpu_scheduler        **sched_list;
+	unsigned int                    num_sched_list;
+	enum drm_sched_priority         priority;
 	spinlock_t			rq_lock;
 
 	struct spsc_queue		job_queue;
@@ -260,7 +261,7 @@ struct drm_sched_backend_ops {
  * @job_list_lock: lock to protect the ring_mirror_list.
  * @hang_limit: once the hangs by a job crosses this limit then it is marked
  *              guilty and it will be considered for scheduling further.
- * @num_jobs: the number of jobs in queue in the scheduler
+ * @score: score to help loadbalancer pick a idle sched
  * @ready: marks if the underlying HW is ready to work
  * @free_guilty: A hit to time out handler to free the guilty job.
  *
@@ -281,8 +282,8 @@ struct drm_gpu_scheduler {
 	struct list_head		ring_mirror_list;
 	spinlock_t			job_list_lock;
 	int				hang_limit;
-	atomic_t                        num_jobs;
-	bool			ready;
+	atomic_t                        score;
+	bool				ready;
 	bool				free_guilty;
 };
 
@@ -312,8 +313,9 @@ void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 				struct drm_sched_entity *entity);
 
 int drm_sched_entity_init(struct drm_sched_entity *entity,
-			  struct drm_sched_rq **rq_list,
-			  unsigned int num_rq_list,
+			  enum drm_sched_priority priority,
+			  struct drm_gpu_scheduler **sched_list,
+			  unsigned int num_sched_list,
 			  atomic_t *guilty);
 long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout);
 void drm_sched_entity_fini(struct drm_sched_entity *entity);
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index b1f66b117c74..1d2c12219f44 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -446,23 +446,18 @@
 
 /* CML GT1 */
 #define INTEL_CML_GT1_IDS(info)	\
-	INTEL_VGA_DEVICE(0x9B21, info), \
-	INTEL_VGA_DEVICE(0x9BAA, info), \
-	INTEL_VGA_DEVICE(0x9BAB, info), \
-	INTEL_VGA_DEVICE(0x9BAC, info), \
-	INTEL_VGA_DEVICE(0x9BA0, info), \
 	INTEL_VGA_DEVICE(0x9BA5, info), \
 	INTEL_VGA_DEVICE(0x9BA8, info), \
 	INTEL_VGA_DEVICE(0x9BA4, info), \
 	INTEL_VGA_DEVICE(0x9BA2, info)
 
+#define INTEL_CML_U_GT1_IDS(info) \
+	INTEL_VGA_DEVICE(0x9B21, info), \
+	INTEL_VGA_DEVICE(0x9BAA, info), \
+	INTEL_VGA_DEVICE(0x9BAC, info)
+
 /* CML GT2 */
 #define INTEL_CML_GT2_IDS(info)	\
-	INTEL_VGA_DEVICE(0x9B41, info), \
-	INTEL_VGA_DEVICE(0x9BCA, info), \
-	INTEL_VGA_DEVICE(0x9BCB, info), \
-	INTEL_VGA_DEVICE(0x9BCC, info), \
-	INTEL_VGA_DEVICE(0x9BC0, info), \
 	INTEL_VGA_DEVICE(0x9BC5, info), \
 	INTEL_VGA_DEVICE(0x9BC8, info), \
 	INTEL_VGA_DEVICE(0x9BC4, info), \
@@ -471,6 +466,11 @@
 	INTEL_VGA_DEVICE(0x9BE6, info), \
 	INTEL_VGA_DEVICE(0x9BF6, info)
 
+#define INTEL_CML_U_GT2_IDS(info) \
+	INTEL_VGA_DEVICE(0x9B41, info), \
+	INTEL_VGA_DEVICE(0x9BCA, info), \
+	INTEL_VGA_DEVICE(0x9BCC, info)
+
 #define INTEL_KBL_IDS(info) \
 	INTEL_KBL_GT1_IDS(info), \
 	INTEL_KBL_GT2_IDS(info), \
@@ -536,7 +536,9 @@
 	INTEL_WHL_U_GT3_IDS(info), \
 	INTEL_AML_CFL_GT2_IDS(info), \
 	INTEL_CML_GT1_IDS(info), \
-	INTEL_CML_GT2_IDS(info)
+	INTEL_CML_GT2_IDS(info), \
+	INTEL_CML_U_GT1_IDS(info), \
+	INTEL_CML_U_GT2_IDS(info)
 
 /* CNL */
 #define INTEL_CNL_PORT_F_IDS(info) \
@@ -579,12 +581,15 @@
 	INTEL_VGA_DEVICE(0x8A51, info), \
 	INTEL_VGA_DEVICE(0x8A5D, info)
 
-/* EHL */
+/* EHL/JSL */
 #define INTEL_EHL_IDS(info) \
 	INTEL_VGA_DEVICE(0x4500, info),	\
 	INTEL_VGA_DEVICE(0x4571, info), \
 	INTEL_VGA_DEVICE(0x4551, info), \
-	INTEL_VGA_DEVICE(0x4541, info)
+	INTEL_VGA_DEVICE(0x4541, info), \
+	INTEL_VGA_DEVICE(0x4E71, info), \
+	INTEL_VGA_DEVICE(0x4E61, info), \
+	INTEL_VGA_DEVICE(0x4E51, info)
 
 /* TGL */
 #define INTEL_TGL_12_IDS(info) \
diff --git a/include/drm/task_barrier.h b/include/drm/task_barrier.h
new file mode 100644
index 000000000000..087e3f649c52
--- /dev/null
+++ b/include/drm/task_barrier.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include <linux/semaphore.h>
+#include <linux/atomic.h>
+
+/*
+ * Reusable 2 PHASE task barrier (randevouz point) implementation for N tasks.
+ * Based on the Little book of sempahores - https://greenteapress.com/wp/semaphores/
+ */
+
+
+
+#ifndef DRM_TASK_BARRIER_H_
+#define DRM_TASK_BARRIER_H_
+
+/*
+ * Represents an instance of a task barrier.
+ */
+struct task_barrier {
+	unsigned int n;
+	atomic_t count;
+	struct semaphore enter_turnstile;
+	struct semaphore exit_turnstile;
+};
+
+static inline void task_barrier_signal_turnstile(struct semaphore *turnstile,
+						 unsigned int n)
+{
+	int i;
+
+	for (i = 0 ; i < n; i++)
+		up(turnstile);
+}
+
+static inline void task_barrier_init(struct task_barrier *tb)
+{
+	tb->n = 0;
+	atomic_set(&tb->count, 0);
+	sema_init(&tb->enter_turnstile, 0);
+	sema_init(&tb->exit_turnstile, 0);
+}
+
+static inline void task_barrier_add_task(struct task_barrier *tb)
+{
+	tb->n++;
+}
+
+static inline void task_barrier_rem_task(struct task_barrier *tb)
+{
+	tb->n--;
+}
+
+/*
+ * Lines up all the threads BEFORE the critical point.
+ *
+ * When all thread passed this code the entry barrier is back to locked state.
+ */
+static inline void task_barrier_enter(struct task_barrier *tb)
+{
+	if (atomic_inc_return(&tb->count) == tb->n)
+		task_barrier_signal_turnstile(&tb->enter_turnstile, tb->n);
+
+	down(&tb->enter_turnstile);
+}
+
+/*
+ * Lines up all the threads AFTER the critical point.
+ *
+ * This function is used to avoid any one thread running ahead if the barrier is
+ *  used repeatedly .
+ */
+static inline void task_barrier_exit(struct task_barrier *tb)
+{
+	if (atomic_dec_return(&tb->count) == 0)
+		task_barrier_signal_turnstile(&tb->exit_turnstile, tb->n);
+
+	down(&tb->exit_turnstile);
+}
+
+/* Convinieince function when nothing to be done in between entry and exit */
+static inline void task_barrier_full(struct task_barrier *tb)
+{
+	task_barrier_enter(tb);
+	task_barrier_exit(tb);
+}
+
+#endif
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 65e399d280f7..66ca49db9633 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -154,7 +154,6 @@ struct ttm_tt;
  * @offset: The current GPU offset, which can have different meanings
  * depending on the memory type. For SYSTEM type memory, it should be 0.
  * @cur_placement: Hint of current placement.
- * @wu_mutex: Wait unreserved mutex.
  *
  * Base class for TTM buffer object, that deals with data placement and CPU
  * mappings. GPU mappings are really up to the driver, but for simpler GPUs
@@ -222,8 +221,6 @@ struct ttm_buffer_object {
 	uint64_t offset; /* GPU address space is independent of CPU word size */
 
 	struct sg_table *sg;
-
-	struct mutex wu_mutex;
 };
 
 /**
@@ -707,7 +704,6 @@ ssize_t ttm_bo_io(struct ttm_bo_device *bdev, struct file *filp,
 int ttm_bo_swapout(struct ttm_bo_global *glob,
 			struct ttm_operation_ctx *ctx);
 void ttm_bo_swapout_all(struct ttm_bo_device *bdev);
-int ttm_bo_wait_unreserved(struct ttm_buffer_object *bo);
 
 /**
  * ttm_bo_uses_embedded_gem_object - check if the given bo uses the
@@ -738,7 +734,13 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 				    pgprot_t prot,
 				    pgoff_t num_prefault);
 
+vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf);
+
 void ttm_bo_vm_open(struct vm_area_struct *vma);
 
 void ttm_bo_vm_close(struct vm_area_struct *vma);
+
+int ttm_bo_vm_access(struct vm_area_struct *vma, unsigned long addr,
+		     void *buf, int len, int write);
+
 #endif
diff --git a/include/dt-bindings/clock/dra7.h b/include/dt-bindings/clock/dra7.h
index 72f2e8411523..8cec5a1e1806 100644
--- a/include/dt-bindings/clock/dra7.h
+++ b/include/dt-bindings/clock/dra7.h
@@ -29,6 +29,16 @@
 #define DRA7_RTC_CLKCTRL_INDEX(offset)	((offset) - DRA7_RTC_CLKCTRL_OFFSET)
 #define DRA7_RTCSS_CLKCTRL	DRA7_RTC_CLKCTRL_INDEX(0x44)
 
+/* vip clocks */
+#define DRA7_VIP1_CLKCTRL	DRA7_CLKCTRL_INDEX(0x20)
+#define DRA7_VIP2_CLKCTRL	DRA7_CLKCTRL_INDEX(0x28)
+#define DRA7_VIP3_CLKCTRL	DRA7_CLKCTRL_INDEX(0x30)
+
+/* vpe clocks */
+#define DRA7_VPE_CLKCTRL_OFFSET	0x60
+#define DRA7_VPE_CLKCTRL_INDEX(offset)	((offset) - DRA7_VPE_CLKCTRL_OFFSET)
+#define DRA7_VPE_CLKCTRL	DRA7_VPE_CLKCTRL_INDEX(0x64)
+
 /* coreaon clocks */
 #define DRA7_SMARTREFLEX_MPU_CLKCTRL	DRA7_CLKCTRL_INDEX(0x28)
 #define DRA7_SMARTREFLEX_CORE_CLKCTRL	DRA7_CLKCTRL_INDEX(0x38)
@@ -78,6 +88,9 @@
 #define DRA7_DSS_CORE_CLKCTRL	DRA7_CLKCTRL_INDEX(0x20)
 #define DRA7_BB2D_CLKCTRL	DRA7_CLKCTRL_INDEX(0x30)
 
+/* gpu clocks */
+#define DRA7_GPU_CLKCTRL	DRA7_CLKCTRL_INDEX(0x20)
+
 /* l3init clocks */
 #define DRA7_MMC1_CLKCTRL	DRA7_CLKCTRL_INDEX(0x28)
 #define DRA7_MMC2_CLKCTRL	DRA7_CLKCTRL_INDEX(0x30)
@@ -192,6 +205,16 @@
 /* rtc clocks */
 #define DRA7_RTC_RTCSS_CLKCTRL	DRA7_CLKCTRL_INDEX(0x44)
 
+/* vip clocks */
+#define DRA7_CAM_VIP1_CLKCTRL	DRA7_CLKCTRL_INDEX(0x20)
+#define DRA7_CAM_VIP2_CLKCTRL	DRA7_CLKCTRL_INDEX(0x28)
+#define DRA7_CAM_VIP3_CLKCTRL	DRA7_CLKCTRL_INDEX(0x30)
+
+/* vpe clocks */
+#define DRA7_VPE_CLKCTRL_OFFSET	0x60
+#define DRA7_VPE_CLKCTRL_INDEX(offset)	((offset) - DRA7_VPE_CLKCTRL_OFFSET)
+#define DRA7_VPE_VPE_CLKCTRL	DRA7_VPE_CLKCTRL_INDEX(0x64)
+
 /* coreaon clocks */
 #define DRA7_COREAON_SMARTREFLEX_MPU_CLKCTRL	DRA7_CLKCTRL_INDEX(0x28)
 #define DRA7_COREAON_SMARTREFLEX_CORE_CLKCTRL	DRA7_CLKCTRL_INDEX(0x38)
diff --git a/include/dt-bindings/clock/imx8mp-clock.h b/include/dt-bindings/clock/imx8mp-clock.h
new file mode 100644
index 000000000000..2fab63186bca
--- /dev/null
+++ b/include/dt-bindings/clock/imx8mp-clock.h
@@ -0,0 +1,300 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 NXP
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_IMX8MP_H
+#define __DT_BINDINGS_CLOCK_IMX8MP_H
+
+#define IMX8MP_CLK_DUMMY			0
+#define IMX8MP_CLK_32K				1
+#define IMX8MP_CLK_24M				2
+#define IMX8MP_OSC_HDMI_CLK			3
+#define IMX8MP_CLK_EXT1				4
+#define IMX8MP_CLK_EXT2				5
+#define IMX8MP_CLK_EXT3				6
+#define IMX8MP_CLK_EXT4				7
+#define IMX8MP_AUDIO_PLL1_REF_SEL		8
+#define IMX8MP_AUDIO_PLL2_REF_SEL		9
+#define IMX8MP_VIDEO_PLL1_REF_SEL		10
+#define IMX8MP_DRAM_PLL_REF_SEL			11
+#define IMX8MP_GPU_PLL_REF_SEL			12
+#define IMX8MP_VPU_PLL_REF_SEL			13
+#define IMX8MP_ARM_PLL_REF_SEL			14
+#define IMX8MP_SYS_PLL1_REF_SEL			15
+#define IMX8MP_SYS_PLL2_REF_SEL			16
+#define IMX8MP_SYS_PLL3_REF_SEL			17
+#define IMX8MP_AUDIO_PLL1			18
+#define IMX8MP_AUDIO_PLL2			19
+#define IMX8MP_VIDEO_PLL1			20
+#define IMX8MP_DRAM_PLL				21
+#define IMX8MP_GPU_PLL				22
+#define IMX8MP_VPU_PLL				23
+#define IMX8MP_ARM_PLL				24
+#define IMX8MP_SYS_PLL1				25
+#define IMX8MP_SYS_PLL2				26
+#define IMX8MP_SYS_PLL3				27
+#define IMX8MP_AUDIO_PLL1_BYPASS		28
+#define IMX8MP_AUDIO_PLL2_BYPASS		29
+#define IMX8MP_VIDEO_PLL1_BYPASS		30
+#define IMX8MP_DRAM_PLL_BYPASS			31
+#define IMX8MP_GPU_PLL_BYPASS			32
+#define IMX8MP_VPU_PLL_BYPASS			33
+#define IMX8MP_ARM_PLL_BYPASS			34
+#define IMX8MP_SYS_PLL1_BYPASS			35
+#define IMX8MP_SYS_PLL2_BYPASS			36
+#define IMX8MP_SYS_PLL3_BYPASS			37
+#define IMX8MP_AUDIO_PLL1_OUT			38
+#define IMX8MP_AUDIO_PLL2_OUT			39
+#define IMX8MP_VIDEO_PLL1_OUT			40
+#define IMX8MP_DRAM_PLL_OUT			41
+#define IMX8MP_GPU_PLL_OUT			42
+#define IMX8MP_VPU_PLL_OUT			43
+#define IMX8MP_ARM_PLL_OUT			44
+#define IMX8MP_SYS_PLL1_OUT			45
+#define IMX8MP_SYS_PLL2_OUT			46
+#define IMX8MP_SYS_PLL3_OUT			47
+#define IMX8MP_SYS_PLL1_40M			48
+#define IMX8MP_SYS_PLL1_80M			49
+#define IMX8MP_SYS_PLL1_100M			50
+#define IMX8MP_SYS_PLL1_133M			51
+#define IMX8MP_SYS_PLL1_160M			52
+#define IMX8MP_SYS_PLL1_200M			53
+#define IMX8MP_SYS_PLL1_266M			54
+#define IMX8MP_SYS_PLL1_400M			55
+#define IMX8MP_SYS_PLL1_800M			56
+#define IMX8MP_SYS_PLL2_50M			57
+#define IMX8MP_SYS_PLL2_100M			58
+#define IMX8MP_SYS_PLL2_125M			59
+#define IMX8MP_SYS_PLL2_166M			60
+#define IMX8MP_SYS_PLL2_200M			61
+#define IMX8MP_SYS_PLL2_250M			62
+#define IMX8MP_SYS_PLL2_333M			63
+#define IMX8MP_SYS_PLL2_500M			64
+#define IMX8MP_SYS_PLL2_1000M			65
+#define IMX8MP_CLK_A53_SRC			66
+#define IMX8MP_CLK_M7_SRC			67
+#define IMX8MP_CLK_ML_SRC			68
+#define IMX8MP_CLK_GPU3D_CORE_SRC		69
+#define IMX8MP_CLK_GPU3D_SHADER_SRC		70
+#define IMX8MP_CLK_GPU2D_SRC			71
+#define IMX8MP_CLK_AUDIO_AXI_SRC		72
+#define IMX8MP_CLK_HSIO_AXI_SRC			73
+#define IMX8MP_CLK_MEDIA_ISP_SRC		74
+#define IMX8MP_CLK_A53_CG			75
+#define IMX8MP_CLK_M4_CG			76
+#define IMX8MP_CLK_ML_CG			77
+#define IMX8MP_CLK_GPU3D_CORE_CG		78
+#define IMX8MP_CLK_GPU3D_SHADER_CG		79
+#define IMX8MP_CLK_GPU2D_CG			80
+#define IMX8MP_CLK_AUDIO_AXI_CG			81
+#define IMX8MP_CLK_HSIO_AXI_CG			82
+#define IMX8MP_CLK_MEDIA_ISP_CG			83
+#define IMX8MP_CLK_A53_DIV			84
+#define IMX8MP_CLK_M7_DIV			85
+#define IMX8MP_CLK_ML_DIV			86
+#define IMX8MP_CLK_GPU3D_CORE_DIV		87
+#define IMX8MP_CLK_GPU3D_SHADER_DIV		88
+#define IMX8MP_CLK_GPU2D_DIV			89
+#define IMX8MP_CLK_AUDIO_AXI_DIV		90
+#define IMX8MP_CLK_HSIO_AXI_DIV			91
+#define IMX8MP_CLK_MEDIA_ISP_DIV		92
+#define IMX8MP_CLK_MAIN_AXI			93
+#define IMX8MP_CLK_ENET_AXI			94
+#define IMX8MP_CLK_NAND_USDHC_BUS		95
+#define IMX8MP_CLK_VPU_BUS			96
+#define IMX8MP_CLK_MEDIA_AXI			97
+#define IMX8MP_CLK_MEDIA_APB			98
+#define IMX8MP_CLK_HDMI_APB			99
+#define IMX8MP_CLK_HDMI_AXI			100
+#define IMX8MP_CLK_GPU_AXI			101
+#define IMX8MP_CLK_GPU_AHB			102
+#define IMX8MP_CLK_NOC				103
+#define IMX8MP_CLK_NOC_IO			104
+#define IMX8MP_CLK_ML_AXI			105
+#define IMX8MP_CLK_ML_AHB			106
+#define IMX8MP_CLK_AHB				107
+#define IMX8MP_CLK_AUDIO_AHB			108
+#define IMX8MP_CLK_MIPI_DSI_ESC_RX		109
+#define IMX8MP_CLK_IPG_ROOT			110
+#define IMX8MP_CLK_IPG_AUDIO_ROOT		111
+#define IMX8MP_CLK_DRAM_ALT			112
+#define IMX8MP_CLK_DRAM_APB			113
+#define IMX8MP_CLK_VPU_G1			114
+#define IMX8MP_CLK_VPU_G2			115
+#define IMX8MP_CLK_CAN1				116
+#define IMX8MP_CLK_CAN2				117
+#define IMX8MP_CLK_MEMREPAIR			118
+#define IMX8MP_CLK_PCIE_PHY			119
+#define IMX8MP_CLK_PCIE_AUX			120
+#define IMX8MP_CLK_I2C5				121
+#define IMX8MP_CLK_I2C6				122
+#define IMX8MP_CLK_SAI1				123
+#define IMX8MP_CLK_SAI2				124
+#define IMX8MP_CLK_SAI3				125
+#define IMX8MP_CLK_SAI4				126
+#define IMX8MP_CLK_SAI5				127
+#define IMX8MP_CLK_SAI6				128
+#define IMX8MP_CLK_ENET_QOS			129
+#define IMX8MP_CLK_ENET_QOS_TIMER		130
+#define IMX8MP_CLK_ENET_REF			131
+#define IMX8MP_CLK_ENET_TIMER			132
+#define IMX8MP_CLK_ENET_PHY_REF			133
+#define IMX8MP_CLK_NAND				134
+#define IMX8MP_CLK_QSPI				135
+#define IMX8MP_CLK_USDHC1			136
+#define IMX8MP_CLK_USDHC2			137
+#define IMX8MP_CLK_I2C1				138
+#define IMX8MP_CLK_I2C2				139
+#define IMX8MP_CLK_I2C3				140
+#define IMX8MP_CLK_I2C4				141
+#define IMX8MP_CLK_UART1			142
+#define IMX8MP_CLK_UART2			143
+#define IMX8MP_CLK_UART3			144
+#define IMX8MP_CLK_UART4			145
+#define IMX8MP_CLK_USB_CORE_REF			146
+#define IMX8MP_CLK_USB_PHY_REF			147
+#define IMX8MP_CLK_GIC				148
+#define IMX8MP_CLK_ECSPI1			149
+#define IMX8MP_CLK_ECSPI2			150
+#define IMX8MP_CLK_PWM1				151
+#define IMX8MP_CLK_PWM2				152
+#define IMX8MP_CLK_PWM3				153
+#define IMX8MP_CLK_PWM4				154
+#define IMX8MP_CLK_GPT1				155
+#define IMX8MP_CLK_GPT2				156
+#define IMX8MP_CLK_GPT3				157
+#define IMX8MP_CLK_GPT4				158
+#define IMX8MP_CLK_GPT5				159
+#define IMX8MP_CLK_GPT6				160
+#define IMX8MP_CLK_TRACE			161
+#define IMX8MP_CLK_WDOG				162
+#define IMX8MP_CLK_WRCLK			163
+#define IMX8MP_CLK_IPP_DO_CLKO1			164
+#define IMX8MP_CLK_IPP_DO_CLKO2			165
+#define IMX8MP_CLK_HDMI_FDCC_TST		166
+#define IMX8MP_CLK_HDMI_27M			167
+#define IMX8MP_CLK_HDMI_REF_266M		168
+#define IMX8MP_CLK_USDHC3			169
+#define IMX8MP_CLK_MEDIA_CAM1_PIX		170
+#define IMX8MP_CLK_MEDIA_MIPI_PHY1_REF		171
+#define IMX8MP_CLK_MEDIA_DISP1_PIX		172
+#define IMX8MP_CLK_MEDIA_CAM2_PIX		173
+#define IMX8MP_CLK_MEDIA_MIPI_PHY2_REF		174
+#define IMX8MP_CLK_MEDIA_MIPI_CSI2_ESC		175
+#define IMX8MP_CLK_PCIE2_CTRL			176
+#define IMX8MP_CLK_PCIE2_PHY			177
+#define IMX8MP_CLK_MEDIA_MIPI_TEST_BYTE		178
+#define IMX8MP_CLK_ECSPI3			179
+#define IMX8MP_CLK_PDM				180
+#define IMX8MP_CLK_VPU_VC8000E			181
+#define IMX8MP_CLK_SAI7				182
+#define IMX8MP_CLK_GPC_ROOT			183
+#define IMX8MP_CLK_ANAMIX_ROOT			184
+#define IMX8MP_CLK_CPU_ROOT			185
+#define IMX8MP_CLK_CSU_ROOT			186
+#define IMX8MP_CLK_DEBUG_ROOT			187
+#define IMX8MP_CLK_DRAM1_ROOT			188
+#define IMX8MP_CLK_ECSPI1_ROOT			189
+#define IMX8MP_CLK_ECSPI2_ROOT			190
+#define IMX8MP_CLK_ECSPI3_ROOT			191
+#define IMX8MP_CLK_ENET1_ROOT			192
+#define IMX8MP_CLK_GPIO1_ROOT			193
+#define IMX8MP_CLK_GPIO2_ROOT			194
+#define IMX8MP_CLK_GPIO3_ROOT			195
+#define IMX8MP_CLK_GPIO4_ROOT			196
+#define IMX8MP_CLK_GPIO5_ROOT			197
+#define IMX8MP_CLK_GPT1_ROOT			198
+#define IMX8MP_CLK_GPT2_ROOT			199
+#define IMX8MP_CLK_GPT3_ROOT			200
+#define IMX8MP_CLK_GPT4_ROOT			201
+#define IMX8MP_CLK_GPT5_ROOT			202
+#define IMX8MP_CLK_GPT6_ROOT			203
+#define IMX8MP_CLK_HS_ROOT			204
+#define IMX8MP_CLK_I2C1_ROOT			205
+#define IMX8MP_CLK_I2C2_ROOT			206
+#define IMX8MP_CLK_I2C3_ROOT			207
+#define IMX8MP_CLK_I2C4_ROOT			208
+#define IMX8MP_CLK_IOMUX_ROOT			209
+#define IMX8MP_CLK_IPMUX1_ROOT			210
+#define IMX8MP_CLK_IPMUX2_ROOT			211
+#define IMX8MP_CLK_IPMUX3_ROOT			212
+#define IMX8MP_CLK_MU_ROOT			213
+#define IMX8MP_CLK_OCOTP_ROOT			214
+#define IMX8MP_CLK_OCRAM_ROOT			215
+#define IMX8MP_CLK_OCRAM_S_ROOT			216
+#define IMX8MP_CLK_PCIE_ROOT			217
+#define IMX8MP_CLK_PERFMON1_ROOT		218
+#define IMX8MP_CLK_PERFMON2_ROOT		219
+#define IMX8MP_CLK_PWM1_ROOT			220
+#define IMX8MP_CLK_PWM2_ROOT			221
+#define IMX8MP_CLK_PWM3_ROOT			222
+#define IMX8MP_CLK_PWM4_ROOT			223
+#define IMX8MP_CLK_QOS_ROOT			224
+#define IMX8MP_CLK_QOS_ENET_ROOT		225
+#define IMX8MP_CLK_QSPI_ROOT			226
+#define IMX8MP_CLK_NAND_ROOT			227
+#define IMX8MP_CLK_NAND_USDHC_BUS_RAWNAND_CLK	228
+#define IMX8MP_CLK_RDC_ROOT			229
+#define IMX8MP_CLK_ROM_ROOT			230
+#define IMX8MP_CLK_I2C5_ROOT			231
+#define IMX8MP_CLK_I2C6_ROOT			232
+#define IMX8MP_CLK_CAN1_ROOT			233
+#define IMX8MP_CLK_CAN2_ROOT			234
+#define IMX8MP_CLK_SCTR_ROOT			235
+#define IMX8MP_CLK_SDMA1_ROOT			236
+#define IMX8MP_CLK_ENET_QOS_ROOT		237
+#define IMX8MP_CLK_SEC_DEBUG_ROOT		238
+#define IMX8MP_CLK_SEMA1_ROOT			239
+#define IMX8MP_CLK_SEMA2_ROOT			240
+#define IMX8MP_CLK_IRQ_STEER_ROOT		241
+#define IMX8MP_CLK_SIM_ENET_ROOT		242
+#define IMX8MP_CLK_SIM_M_ROOT			243
+#define IMX8MP_CLK_SIM_MAIN_ROOT		244
+#define IMX8MP_CLK_SIM_S_ROOT			245
+#define IMX8MP_CLK_SIM_WAKEUP_ROOT		246
+#define IMX8MP_CLK_GPU2D_ROOT			247
+#define IMX8MP_CLK_GPU3D_ROOT			248
+#define IMX8MP_CLK_SNVS_ROOT			249
+#define IMX8MP_CLK_TRACE_ROOT			250
+#define IMX8MP_CLK_UART1_ROOT			251
+#define IMX8MP_CLK_UART2_ROOT			252
+#define IMX8MP_CLK_UART3_ROOT			253
+#define IMX8MP_CLK_UART4_ROOT			254
+#define IMX8MP_CLK_USB_ROOT			255
+#define IMX8MP_CLK_USB_PHY_ROOT			256
+#define IMX8MP_CLK_USDHC1_ROOT			257
+#define IMX8MP_CLK_USDHC2_ROOT			258
+#define IMX8MP_CLK_WDOG1_ROOT			259
+#define IMX8MP_CLK_WDOG2_ROOT			260
+#define IMX8MP_CLK_WDOG3_ROOT			261
+#define IMX8MP_CLK_VPU_G1_ROOT			262
+#define IMX8MP_CLK_GPU_ROOT			263
+#define IMX8MP_CLK_NOC_WRAPPER_ROOT		264
+#define IMX8MP_CLK_VPU_VC8KE_ROOT		265
+#define IMX8MP_CLK_VPU_G2_ROOT			266
+#define IMX8MP_CLK_NPU_ROOT			267
+#define IMX8MP_CLK_HSIO_ROOT			268
+#define IMX8MP_CLK_MEDIA_APB_ROOT		269
+#define IMX8MP_CLK_MEDIA_AXI_ROOT		270
+#define IMX8MP_CLK_MEDIA_CAM1_PIX_ROOT		271
+#define IMX8MP_CLK_MEDIA_CAM2_PIX_ROOT		272
+#define IMX8MP_CLK_MEDIA_DISP1_PIX_ROOT		273
+#define IMX8MP_CLK_MEDIA_DISP2_PIX_ROOT		274
+#define IMX8MP_CLK_MEDIA_MIPI_PHY1_REF_ROOT	275
+#define IMX8MP_CLK_MEDIA_ISP_ROOT		276
+#define IMX8MP_CLK_USDHC3_ROOT			277
+#define IMX8MP_CLK_HDMI_ROOT			278
+#define IMX8MP_CLK_XTAL_ROOT			279
+#define IMX8MP_CLK_PLL_ROOT			280
+#define IMX8MP_CLK_TSENSOR_ROOT			281
+#define IMX8MP_CLK_VPU_ROOT			282
+#define IMX8MP_CLK_MRPR_ROOT			283
+#define IMX8MP_CLK_AUDIO_ROOT			284
+#define IMX8MP_CLK_DRAM_ALT_ROOT		285
+#define IMX8MP_CLK_DRAM_CORE			286
+#define IMX8MP_CLK_ARM				287
+
+#define IMX8MP_CLK_END				288
+
+#endif
diff --git a/include/dt-bindings/clock/meson8-ddr-clkc.h b/include/dt-bindings/clock/meson8-ddr-clkc.h
new file mode 100644
index 000000000000..a8e0fa2987ab
--- /dev/null
+++ b/include/dt-bindings/clock/meson8-ddr-clkc.h
@@ -0,0 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define DDR_CLKID_DDR_PLL_DCO			0
+#define DDR_CLKID_DDR_PLL			1
diff --git a/include/dt-bindings/clock/omap5.h b/include/dt-bindings/clock/omap5.h
index ba672064ccb4..2b4fd9a96b91 100644
--- a/include/dt-bindings/clock/omap5.h
+++ b/include/dt-bindings/clock/omap5.h
@@ -16,6 +16,7 @@
 
 /* abe clocks */
 #define OMAP5_L4_ABE_CLKCTRL	OMAP5_CLKCTRL_INDEX(0x20)
+#define OMAP5_AESS_CLKCTRL	OMAP5_CLKCTRL_INDEX(0x28)
 #define OMAP5_MCPDM_CLKCTRL	OMAP5_CLKCTRL_INDEX(0x30)
 #define OMAP5_DMIC_CLKCTRL	OMAP5_CLKCTRL_INDEX(0x38)
 #define OMAP5_MCBSP1_CLKCTRL	OMAP5_CLKCTRL_INDEX(0x48)
diff --git a/include/dt-bindings/clock/qcom,dispcc-sc7180.h b/include/dt-bindings/clock/qcom,dispcc-sc7180.h
new file mode 100644
index 000000000000..b9b51617a335
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,dispcc-sc7180.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_DISP_CC_SC7180_H
+#define _DT_BINDINGS_CLK_QCOM_DISP_CC_SC7180_H
+
+#define DISP_CC_PLL0				0
+#define DISP_CC_PLL0_OUT_EVEN			1
+#define DISP_CC_MDSS_AHB_CLK			2
+#define DISP_CC_MDSS_AHB_CLK_SRC		3
+#define DISP_CC_MDSS_BYTE0_CLK			4
+#define DISP_CC_MDSS_BYTE0_CLK_SRC		5
+#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC		6
+#define DISP_CC_MDSS_BYTE0_INTF_CLK		7
+#define DISP_CC_MDSS_DP_AUX_CLK			8
+#define DISP_CC_MDSS_DP_AUX_CLK_SRC		9
+#define DISP_CC_MDSS_DP_CRYPTO_CLK		10
+#define DISP_CC_MDSS_DP_CRYPTO_CLK_SRC		11
+#define DISP_CC_MDSS_DP_LINK_CLK		12
+#define DISP_CC_MDSS_DP_LINK_CLK_SRC		13
+#define DISP_CC_MDSS_DP_LINK_DIV_CLK_SRC	14
+#define DISP_CC_MDSS_DP_LINK_INTF_CLK		15
+#define DISP_CC_MDSS_DP_PIXEL_CLK		16
+#define DISP_CC_MDSS_DP_PIXEL_CLK_SRC		17
+#define DISP_CC_MDSS_ESC0_CLK			18
+#define DISP_CC_MDSS_ESC0_CLK_SRC		19
+#define DISP_CC_MDSS_MDP_CLK			20
+#define DISP_CC_MDSS_MDP_CLK_SRC		21
+#define DISP_CC_MDSS_MDP_LUT_CLK		22
+#define DISP_CC_MDSS_NON_GDSC_AHB_CLK		23
+#define DISP_CC_MDSS_PCLK0_CLK			24
+#define DISP_CC_MDSS_PCLK0_CLK_SRC		25
+#define DISP_CC_MDSS_ROT_CLK			26
+#define DISP_CC_MDSS_ROT_CLK_SRC		27
+#define DISP_CC_MDSS_RSCC_AHB_CLK		28
+#define DISP_CC_MDSS_RSCC_VSYNC_CLK		29
+#define DISP_CC_MDSS_VSYNC_CLK			30
+#define DISP_CC_MDSS_VSYNC_CLK_SRC		31
+#define DISP_CC_XO_CLK				32
+
+/* DISP_CC GDSCR */
+#define MDSS_GDSC				0
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,dispcc-sdm845.h b/include/dt-bindings/clock/qcom,dispcc-sdm845.h
index 11eed4bc9646..4016fd1d5b46 100644
--- a/include/dt-bindings/clock/qcom,dispcc-sdm845.h
+++ b/include/dt-bindings/clock/qcom,dispcc-sdm845.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  */
 
 #ifndef _DT_BINDINGS_CLK_SDM_DISP_CC_SDM845_H
@@ -35,6 +35,17 @@
 #define DISP_CC_PLL0						25
 #define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC				26
 #define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC				27
+#define DISP_CC_MDSS_DP_AUX_CLK					28
+#define DISP_CC_MDSS_DP_AUX_CLK_SRC				29
+#define DISP_CC_MDSS_DP_CRYPTO_CLK				30
+#define DISP_CC_MDSS_DP_CRYPTO_CLK_SRC				31
+#define DISP_CC_MDSS_DP_LINK_CLK				32
+#define DISP_CC_MDSS_DP_LINK_CLK_SRC				33
+#define DISP_CC_MDSS_DP_LINK_INTF_CLK				34
+#define DISP_CC_MDSS_DP_PIXEL1_CLK				35
+#define DISP_CC_MDSS_DP_PIXEL1_CLK_SRC				36
+#define DISP_CC_MDSS_DP_PIXEL_CLK				37
+#define DISP_CC_MDSS_DP_PIXEL_CLK_SRC				38
 
 /* DISP_CC Reset */
 #define DISP_CC_MDSS_RSCC_BCR					0
diff --git a/include/dt-bindings/clock/qcom,gcc-ipq6018.h b/include/dt-bindings/clock/qcom,gcc-ipq6018.h
new file mode 100644
index 000000000000..6f4be3aa0acf
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gcc-ipq6018.h
@@ -0,0 +1,262 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLOCK_IPQ_GCC_6018_H
+#define _DT_BINDINGS_CLOCK_IPQ_GCC_6018_H
+
+#define GPLL0					0
+#define UBI32_PLL				1
+#define GPLL6					2
+#define GPLL4					3
+#define PCNOC_BFDCD_CLK_SRC			4
+#define GPLL2					5
+#define NSS_CRYPTO_PLL				6
+#define NSS_PPE_CLK_SRC				7
+#define GCC_XO_CLK_SRC				8
+#define NSS_CE_CLK_SRC				9
+#define GCC_SLEEP_CLK_SRC			10
+#define APSS_AHB_CLK_SRC			11
+#define NSS_PORT5_RX_CLK_SRC			12
+#define NSS_PORT5_TX_CLK_SRC			13
+#define PCIE0_AXI_CLK_SRC			14
+#define USB0_MASTER_CLK_SRC			15
+#define APSS_AHB_POSTDIV_CLK_SRC		16
+#define NSS_PORT1_RX_CLK_SRC			17
+#define NSS_PORT1_TX_CLK_SRC			18
+#define NSS_PORT2_RX_CLK_SRC			19
+#define NSS_PORT2_TX_CLK_SRC			20
+#define NSS_PORT3_RX_CLK_SRC			21
+#define NSS_PORT3_TX_CLK_SRC			22
+#define NSS_PORT4_RX_CLK_SRC			23
+#define NSS_PORT4_TX_CLK_SRC			24
+#define NSS_PORT5_RX_DIV_CLK_SRC		25
+#define NSS_PORT5_TX_DIV_CLK_SRC		26
+#define APSS_AXI_CLK_SRC			27
+#define NSS_CRYPTO_CLK_SRC			28
+#define NSS_PORT1_RX_DIV_CLK_SRC		29
+#define NSS_PORT1_TX_DIV_CLK_SRC		30
+#define NSS_PORT2_RX_DIV_CLK_SRC		31
+#define NSS_PORT2_TX_DIV_CLK_SRC		32
+#define NSS_PORT3_RX_DIV_CLK_SRC		33
+#define NSS_PORT3_TX_DIV_CLK_SRC		34
+#define NSS_PORT4_RX_DIV_CLK_SRC		35
+#define NSS_PORT4_TX_DIV_CLK_SRC		36
+#define NSS_UBI0_CLK_SRC			37
+#define BLSP1_QUP1_I2C_APPS_CLK_SRC		38
+#define BLSP1_QUP1_SPI_APPS_CLK_SRC		39
+#define BLSP1_QUP2_I2C_APPS_CLK_SRC		40
+#define BLSP1_QUP2_SPI_APPS_CLK_SRC		41
+#define BLSP1_QUP3_I2C_APPS_CLK_SRC		42
+#define BLSP1_QUP3_SPI_APPS_CLK_SRC		43
+#define BLSP1_QUP4_I2C_APPS_CLK_SRC		44
+#define BLSP1_QUP4_SPI_APPS_CLK_SRC		45
+#define BLSP1_QUP5_I2C_APPS_CLK_SRC		46
+#define BLSP1_QUP5_SPI_APPS_CLK_SRC		47
+#define BLSP1_QUP6_I2C_APPS_CLK_SRC		48
+#define BLSP1_QUP6_SPI_APPS_CLK_SRC		49
+#define BLSP1_UART1_APPS_CLK_SRC		50
+#define BLSP1_UART2_APPS_CLK_SRC		51
+#define BLSP1_UART3_APPS_CLK_SRC		52
+#define BLSP1_UART4_APPS_CLK_SRC		53
+#define BLSP1_UART5_APPS_CLK_SRC		54
+#define BLSP1_UART6_APPS_CLK_SRC		55
+#define CRYPTO_CLK_SRC				56
+#define NSS_UBI0_DIV_CLK_SRC			57
+#define PCIE0_AUX_CLK_SRC			58
+#define PCIE0_PIPE_CLK_SRC			59
+#define SDCC1_APPS_CLK_SRC			60
+#define USB0_AUX_CLK_SRC			61
+#define USB0_MOCK_UTMI_CLK_SRC			62
+#define USB0_PIPE_CLK_SRC			63
+#define USB1_MOCK_UTMI_CLK_SRC			64
+#define GCC_APSS_AHB_CLK			65
+#define GCC_APSS_AXI_CLK			66
+#define GCC_BLSP1_AHB_CLK			67
+#define GCC_BLSP1_QUP1_I2C_APPS_CLK		68
+#define GCC_BLSP1_QUP1_SPI_APPS_CLK		69
+#define GCC_BLSP1_QUP2_I2C_APPS_CLK		70
+#define GCC_BLSP1_QUP2_SPI_APPS_CLK		71
+#define GCC_BLSP1_QUP3_I2C_APPS_CLK		72
+#define GCC_BLSP1_QUP3_SPI_APPS_CLK		73
+#define GCC_BLSP1_QUP4_I2C_APPS_CLK		74
+#define GCC_BLSP1_QUP4_SPI_APPS_CLK		75
+#define GCC_BLSP1_QUP5_I2C_APPS_CLK		76
+#define GCC_BLSP1_QUP5_SPI_APPS_CLK		77
+#define GCC_BLSP1_QUP6_I2C_APPS_CLK		78
+#define GCC_BLSP1_QUP6_SPI_APPS_CLK		79
+#define GCC_BLSP1_UART1_APPS_CLK		80
+#define GCC_BLSP1_UART2_APPS_CLK		81
+#define GCC_BLSP1_UART3_APPS_CLK		82
+#define GCC_BLSP1_UART4_APPS_CLK		83
+#define GCC_BLSP1_UART5_APPS_CLK		84
+#define GCC_BLSP1_UART6_APPS_CLK		85
+#define GCC_CRYPTO_AHB_CLK			86
+#define GCC_CRYPTO_AXI_CLK			87
+#define GCC_CRYPTO_CLK				88
+#define GCC_XO_CLK				89
+#define GCC_XO_DIV4_CLK				90
+#define GCC_MDIO_AHB_CLK			91
+#define GCC_CRYPTO_PPE_CLK			92
+#define GCC_NSS_CE_APB_CLK			93
+#define GCC_NSS_CE_AXI_CLK			94
+#define GCC_NSS_CFG_CLK				95
+#define GCC_NSS_CRYPTO_CLK			96
+#define GCC_NSS_CSR_CLK				97
+#define GCC_NSS_EDMA_CFG_CLK			98
+#define GCC_NSS_EDMA_CLK			99
+#define GCC_NSS_NOC_CLK				100
+#define GCC_NSS_PORT1_RX_CLK			101
+#define GCC_NSS_PORT1_TX_CLK			102
+#define GCC_NSS_PORT2_RX_CLK			103
+#define GCC_NSS_PORT2_TX_CLK			104
+#define GCC_NSS_PORT3_RX_CLK			105
+#define GCC_NSS_PORT3_TX_CLK			106
+#define GCC_NSS_PORT4_RX_CLK			107
+#define GCC_NSS_PORT4_TX_CLK			108
+#define GCC_NSS_PORT5_RX_CLK			109
+#define GCC_NSS_PORT5_TX_CLK			110
+#define GCC_NSS_PPE_CFG_CLK			111
+#define GCC_NSS_PPE_CLK				112
+#define GCC_NSS_PPE_IPE_CLK			113
+#define GCC_NSS_PTP_REF_CLK			114
+#define GCC_NSSNOC_CE_APB_CLK			115
+#define GCC_NSSNOC_CE_AXI_CLK			116
+#define GCC_NSSNOC_CRYPTO_CLK			117
+#define GCC_NSSNOC_PPE_CFG_CLK			118
+#define GCC_NSSNOC_PPE_CLK			119
+#define GCC_NSSNOC_QOSGEN_REF_CLK		120
+#define GCC_NSSNOC_TIMEOUT_REF_CLK		121
+#define GCC_NSSNOC_UBI0_AHB_CLK			122
+#define GCC_PORT1_MAC_CLK			123
+#define GCC_PORT2_MAC_CLK			124
+#define GCC_PORT3_MAC_CLK			125
+#define GCC_PORT4_MAC_CLK			126
+#define GCC_PORT5_MAC_CLK			127
+#define GCC_UBI0_AHB_CLK			128
+#define GCC_UBI0_AXI_CLK			129
+#define GCC_UBI0_CORE_CLK			130
+#define GCC_PCIE0_AHB_CLK			131
+#define GCC_PCIE0_AUX_CLK			132
+#define GCC_PCIE0_AXI_M_CLK			133
+#define GCC_PCIE0_AXI_S_CLK			134
+#define GCC_PCIE0_PIPE_CLK			135
+#define GCC_PRNG_AHB_CLK			136
+#define GCC_QPIC_AHB_CLK			137
+#define GCC_QPIC_CLK				138
+#define GCC_SDCC1_AHB_CLK			139
+#define GCC_SDCC1_APPS_CLK			140
+#define GCC_UNIPHY0_AHB_CLK			141
+#define GCC_UNIPHY0_PORT1_RX_CLK		142
+#define GCC_UNIPHY0_PORT1_TX_CLK		143
+#define GCC_UNIPHY0_PORT2_RX_CLK		144
+#define GCC_UNIPHY0_PORT2_TX_CLK		145
+#define GCC_UNIPHY0_PORT3_RX_CLK		146
+#define GCC_UNIPHY0_PORT3_TX_CLK		147
+#define GCC_UNIPHY0_PORT4_RX_CLK		148
+#define GCC_UNIPHY0_PORT4_TX_CLK		149
+#define GCC_UNIPHY0_PORT5_RX_CLK		150
+#define GCC_UNIPHY0_PORT5_TX_CLK		151
+#define GCC_UNIPHY0_SYS_CLK			152
+#define GCC_UNIPHY1_AHB_CLK			153
+#define GCC_UNIPHY1_PORT5_RX_CLK		154
+#define GCC_UNIPHY1_PORT5_TX_CLK		155
+#define GCC_UNIPHY1_SYS_CLK			156
+#define GCC_USB0_AUX_CLK			157
+#define GCC_USB0_MASTER_CLK			158
+#define GCC_USB0_MOCK_UTMI_CLK			159
+#define GCC_USB0_PHY_CFG_AHB_CLK		160
+#define GCC_USB0_PIPE_CLK			161
+#define GCC_USB0_SLEEP_CLK			162
+#define GCC_USB1_MASTER_CLK			163
+#define GCC_USB1_MOCK_UTMI_CLK			164
+#define GCC_USB1_PHY_CFG_AHB_CLK		165
+#define GCC_USB1_SLEEP_CLK			166
+#define GP1_CLK_SRC				167
+#define GP2_CLK_SRC				168
+#define GP3_CLK_SRC				169
+#define GCC_GP1_CLK				170
+#define GCC_GP2_CLK				171
+#define GCC_GP3_CLK				172
+#define SYSTEM_NOC_BFDCD_CLK_SRC		173
+#define GCC_NSSNOC_SNOC_CLK			174
+#define GCC_UBI0_NC_AXI_CLK			175
+#define GCC_UBI1_NC_AXI_CLK			176
+#define GPLL0_MAIN				177
+#define UBI32_PLL_MAIN				178
+#define GPLL6_MAIN				179
+#define GPLL4_MAIN				180
+#define GPLL2_MAIN				181
+#define NSS_CRYPTO_PLL_MAIN			182
+#define GCC_CMN_12GPLL_AHB_CLK			183
+#define GCC_CMN_12GPLL_SYS_CLK			184
+#define GCC_SNOC_BUS_TIMEOUT2_AHB_CLK		185
+#define GCC_SYS_NOC_USB0_AXI_CLK		186
+#define GCC_SYS_NOC_PCIE0_AXI_CLK		187
+#define QDSS_TSCTR_CLK_SRC			188
+#define QDSS_AT_CLK_SRC				189
+#define GCC_QDSS_AT_CLK				190
+#define GCC_QDSS_DAP_CLK			191
+#define ADSS_PWM_CLK_SRC			192
+#define GCC_ADSS_PWM_CLK			193
+#define SDCC1_ICE_CORE_CLK_SRC			194
+#define GCC_SDCC1_ICE_CORE_CLK			195
+#define GCC_DCC_CLK				196
+#define PCIE0_RCHNG_CLK_SRC			197
+#define GCC_PCIE0_AXI_S_BRIDGE_CLK		198
+#define PCIE0_RCHNG_CLK				199
+#define UBI32_MEM_NOC_BFDCD_CLK_SRC		200
+#define WCSS_AHB_CLK_SRC			201
+#define Q6_AXI_CLK_SRC				202
+#define GCC_Q6SS_PCLKDBG_CLK			203
+#define GCC_Q6_TSCTR_1TO2_CLK			204
+#define GCC_WCSS_CORE_TBU_CLK			205
+#define GCC_WCSS_AXI_M_CLK			206
+#define GCC_SYS_NOC_WCSS_AHB_CLK		207
+#define GCC_Q6_AXIM_CLK				208
+#define GCC_Q6SS_ATBM_CLK			209
+#define GCC_WCSS_Q6_TBU_CLK			210
+#define GCC_Q6_AXIM2_CLK			211
+#define GCC_Q6_AHB_CLK				212
+#define GCC_Q6_AHB_S_CLK			213
+#define GCC_WCSS_DBG_IFC_APB_CLK		214
+#define GCC_WCSS_DBG_IFC_ATB_CLK		215
+#define GCC_WCSS_DBG_IFC_NTS_CLK		216
+#define GCC_WCSS_DBG_IFC_DAPBUS_CLK		217
+#define GCC_WCSS_DBG_IFC_APB_BDG_CLK		218
+#define GCC_WCSS_DBG_IFC_ATB_BDG_CLK		219
+#define GCC_WCSS_DBG_IFC_NTS_BDG_CLK		220
+#define GCC_WCSS_DBG_IFC_DAPBUS_BDG_CLK		221
+#define GCC_WCSS_ECAHB_CLK			222
+#define GCC_WCSS_ACMT_CLK			223
+#define GCC_WCSS_AHB_S_CLK			224
+#define GCC_RBCPR_WCSS_CLK			225
+#define RBCPR_WCSS_CLK_SRC			226
+#define GCC_RBCPR_WCSS_AHB_CLK			227
+#define GCC_LPASS_CORE_AXIM_CLK			228
+#define GCC_LPASS_SNOC_CFG_CLK			229
+#define GCC_LPASS_Q6_AXIM_CLK			230
+#define GCC_LPASS_Q6_ATBM_AT_CLK		231
+#define GCC_LPASS_Q6_PCLKDBG_CLK		232
+#define GCC_LPASS_Q6SS_TSCTR_1TO2_CLK		233
+#define GCC_LPASS_Q6SS_TRIG_CLK			234
+#define GCC_LPASS_TBU_CLK			235
+#define LPASS_CORE_AXIM_CLK_SRC			236
+#define LPASS_SNOC_CFG_CLK_SRC			237
+#define LPASS_Q6_AXIM_CLK_SRC			238
+#define GCC_PCNOC_LPASS_CLK			239
+#define GCC_UBI0_UTCM_CLK			240
+#define SNOC_NSSNOC_BFDCD_CLK_SRC		241
+#define GCC_SNOC_NSSNOC_CLK			242
+#define GCC_MEM_NOC_Q6_AXI_CLK			243
+#define GCC_MEM_NOC_UBI32_CLK			244
+#define GCC_MEM_NOC_LPASS_CLK			245
+#define GCC_SNOC_LPASS_CFG_CLK			246
+#define GCC_SYS_NOC_QDSS_STM_AXI_CLK		247
+#define GCC_QDSS_STM_CLK			248
+#define GCC_QDSS_TRACECLKIN_CLK			249
+#define QDSS_STM_CLK_SRC			250
+#define QDSS_TRACECLKIN_CLK_SRC			251
+#define GCC_NSSNOC_ATB_CLK			252
+#endif
diff --git a/include/dt-bindings/clock/qcom,gcc-msm8998.h b/include/dt-bindings/clock/qcom,gcc-msm8998.h
index de1d8a1f5966..63e02dc32a0b 100644
--- a/include/dt-bindings/clock/qcom,gcc-msm8998.h
+++ b/include/dt-bindings/clock/qcom,gcc-msm8998.h
@@ -182,6 +182,7 @@
 #define GCC_MSS_GPLL0_DIV_CLK_SRC				173
 #define GCC_MSS_SNOC_AXI_CLK					174
 #define GCC_MSS_MNOC_BIMC_AXI_CLK				175
+#define GCC_BIMC_GFX_CLK					176
 
 #define PCIE_0_GDSC						0
 #define UFS_GDSC						1
diff --git a/include/dt-bindings/clock/qcom,gpucc-sc7180.h b/include/dt-bindings/clock/qcom,gpucc-sc7180.h
new file mode 100644
index 000000000000..0e4643b08b49
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,gpucc-sc7180.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_GPU_CC_SC7180_H
+#define _DT_BINDINGS_CLK_QCOM_GPU_CC_SC7180_H
+
+#define GPU_CC_PLL1			0
+#define GPU_CC_AHB_CLK			1
+#define GPU_CC_CRC_AHB_CLK		2
+#define GPU_CC_CX_GMU_CLK		3
+#define GPU_CC_CX_SNOC_DVM_CLK		4
+#define GPU_CC_CXO_AON_CLK		5
+#define GPU_CC_CXO_CLK			6
+#define GPU_CC_GMU_CLK_SRC		7
+
+/* CAM_CC GDSCRs */
+#define CX_GDSC				0
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,mmcc-msm8998.h b/include/dt-bindings/clock/qcom,mmcc-msm8998.h
new file mode 100644
index 000000000000..ecbafdb930aa
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,mmcc-msm8998.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_MSM_MMCC_8998_H
+#define _DT_BINDINGS_CLK_MSM_MMCC_8998_H
+
+#define MMPLL0						0
+#define MMPLL0_OUT_EVEN					1
+#define MMPLL1						2
+#define MMPLL1_OUT_EVEN					3
+#define MMPLL3						4
+#define MMPLL3_OUT_EVEN					5
+#define MMPLL4						6
+#define MMPLL4_OUT_EVEN					7
+#define MMPLL5						8
+#define MMPLL5_OUT_EVEN					9
+#define MMPLL6						10
+#define MMPLL6_OUT_EVEN					11
+#define MMPLL7						12
+#define MMPLL7_OUT_EVEN					13
+#define MMPLL10						14
+#define MMPLL10_OUT_EVEN				15
+#define BYTE0_CLK_SRC					16
+#define BYTE1_CLK_SRC					17
+#define CCI_CLK_SRC					18
+#define CPP_CLK_SRC					19
+#define CSI0_CLK_SRC					20
+#define CSI1_CLK_SRC					21
+#define CSI2_CLK_SRC					22
+#define CSI3_CLK_SRC					23
+#define CSIPHY_CLK_SRC					24
+#define CSI0PHYTIMER_CLK_SRC				25
+#define CSI1PHYTIMER_CLK_SRC				26
+#define CSI2PHYTIMER_CLK_SRC				27
+#define DP_AUX_CLK_SRC					28
+#define DP_CRYPTO_CLK_SRC				29
+#define DP_LINK_CLK_SRC					30
+#define DP_PIXEL_CLK_SRC				31
+#define ESC0_CLK_SRC					32
+#define ESC1_CLK_SRC					33
+#define EXTPCLK_CLK_SRC					34
+#define FD_CORE_CLK_SRC					35
+#define HDMI_CLK_SRC					36
+#define JPEG0_CLK_SRC					37
+#define MAXI_CLK_SRC					38
+#define MCLK0_CLK_SRC					39
+#define MCLK1_CLK_SRC					40
+#define MCLK2_CLK_SRC					41
+#define MCLK3_CLK_SRC					42
+#define MDP_CLK_SRC					43
+#define VSYNC_CLK_SRC					44
+#define AHB_CLK_SRC					45
+#define AXI_CLK_SRC					46
+#define PCLK0_CLK_SRC					47
+#define PCLK1_CLK_SRC					48
+#define ROT_CLK_SRC					49
+#define VIDEO_CORE_CLK_SRC				50
+#define VIDEO_SUBCORE0_CLK_SRC				51
+#define VIDEO_SUBCORE1_CLK_SRC				52
+#define VFE0_CLK_SRC					53
+#define VFE1_CLK_SRC					54
+#define MISC_AHB_CLK					55
+#define VIDEO_CORE_CLK					56
+#define VIDEO_AHB_CLK					57
+#define VIDEO_AXI_CLK					58
+#define VIDEO_MAXI_CLK					59
+#define VIDEO_SUBCORE0_CLK				60
+#define VIDEO_SUBCORE1_CLK				61
+#define MDSS_AHB_CLK					62
+#define MDSS_HDMI_DP_AHB_CLK				63
+#define MDSS_AXI_CLK					64
+#define MDSS_PCLK0_CLK					65
+#define MDSS_PCLK1_CLK					66
+#define MDSS_MDP_CLK					67
+#define MDSS_MDP_LUT_CLK				68
+#define MDSS_EXTPCLK_CLK				69
+#define MDSS_VSYNC_CLK					70
+#define MDSS_HDMI_CLK					71
+#define MDSS_BYTE0_CLK					72
+#define MDSS_BYTE1_CLK					73
+#define MDSS_ESC0_CLK					74
+#define MDSS_ESC1_CLK					75
+#define MDSS_ROT_CLK					76
+#define MDSS_DP_LINK_CLK				77
+#define MDSS_DP_LINK_INTF_CLK				78
+#define MDSS_DP_CRYPTO_CLK				79
+#define MDSS_DP_PIXEL_CLK				80
+#define MDSS_DP_AUX_CLK					81
+#define MDSS_BYTE0_INTF_CLK				82
+#define MDSS_BYTE1_INTF_CLK				83
+#define CAMSS_CSI0PHYTIMER_CLK				84
+#define CAMSS_CSI1PHYTIMER_CLK				85
+#define CAMSS_CSI2PHYTIMER_CLK				86
+#define CAMSS_CSI0_CLK					87
+#define CAMSS_CSI0_AHB_CLK				88
+#define CAMSS_CSI0RDI_CLK				89
+#define CAMSS_CSI0PIX_CLK				90
+#define CAMSS_CSI1_CLK					91
+#define CAMSS_CSI1_AHB_CLK				92
+#define CAMSS_CSI1RDI_CLK				93
+#define CAMSS_CSI1PIX_CLK				94
+#define CAMSS_CSI2_CLK					95
+#define CAMSS_CSI2_AHB_CLK				96
+#define CAMSS_CSI2RDI_CLK				97
+#define CAMSS_CSI2PIX_CLK				98
+#define CAMSS_CSI3_CLK					99
+#define CAMSS_CSI3_AHB_CLK				100
+#define CAMSS_CSI3RDI_CLK				101
+#define CAMSS_CSI3PIX_CLK				102
+#define CAMSS_ISPIF_AHB_CLK				103
+#define CAMSS_CCI_CLK					104
+#define CAMSS_CCI_AHB_CLK				105
+#define CAMSS_MCLK0_CLK					106
+#define CAMSS_MCLK1_CLK					107
+#define CAMSS_MCLK2_CLK					108
+#define CAMSS_MCLK3_CLK					109
+#define CAMSS_TOP_AHB_CLK				110
+#define CAMSS_AHB_CLK					111
+#define CAMSS_MICRO_AHB_CLK				112
+#define CAMSS_JPEG0_CLK					113
+#define CAMSS_JPEG_AHB_CLK				114
+#define CAMSS_JPEG_AXI_CLK				115
+#define CAMSS_VFE0_AHB_CLK				116
+#define CAMSS_VFE1_AHB_CLK				117
+#define CAMSS_VFE0_CLK					118
+#define CAMSS_VFE1_CLK					119
+#define CAMSS_CPP_CLK					120
+#define CAMSS_CPP_AHB_CLK				121
+#define CAMSS_VFE_VBIF_AHB_CLK				122
+#define CAMSS_VFE_VBIF_AXI_CLK				123
+#define CAMSS_CPP_AXI_CLK				124
+#define CAMSS_CPP_VBIF_AHB_CLK				125
+#define CAMSS_CSI_VFE0_CLK				126
+#define CAMSS_CSI_VFE1_CLK				127
+#define CAMSS_VFE0_STREAM_CLK				128
+#define CAMSS_VFE1_STREAM_CLK				129
+#define CAMSS_CPHY_CSID0_CLK				130
+#define CAMSS_CPHY_CSID1_CLK				131
+#define CAMSS_CPHY_CSID2_CLK				132
+#define CAMSS_CPHY_CSID3_CLK				133
+#define CAMSS_CSIPHY0_CLK				134
+#define CAMSS_CSIPHY1_CLK				135
+#define CAMSS_CSIPHY2_CLK				136
+#define FD_CORE_CLK					137
+#define FD_CORE_UAR_CLK					138
+#define FD_AHB_CLK					139
+#define MNOC_AHB_CLK					140
+#define BIMC_SMMU_AHB_CLK				141
+#define BIMC_SMMU_AXI_CLK				142
+#define MNOC_MAXI_CLK					143
+#define VMEM_MAXI_CLK					144
+#define VMEM_AHB_CLK					145
+
+#define SPDM_BCR					0
+#define SPDM_RM_BCR					1
+#define MISC_BCR					2
+#define VIDEO_TOP_BCR					3
+#define THROTTLE_VIDEO_BCR				4
+#define MDSS_BCR					5
+#define THROTTLE_MDSS_BCR				6
+#define CAMSS_PHY0_BCR					7
+#define CAMSS_PHY1_BCR					8
+#define CAMSS_PHY2_BCR					9
+#define CAMSS_CSI0_BCR					10
+#define CAMSS_CSI0RDI_BCR				11
+#define CAMSS_CSI0PIX_BCR				12
+#define CAMSS_CSI1_BCR					13
+#define CAMSS_CSI1RDI_BCR				14
+#define CAMSS_CSI1PIX_BCR				15
+#define CAMSS_CSI2_BCR					16
+#define CAMSS_CSI2RDI_BCR				17
+#define CAMSS_CSI2PIX_BCR				18
+#define CAMSS_CSI3_BCR					19
+#define CAMSS_CSI3RDI_BCR				20
+#define CAMSS_CSI3PIX_BCR				21
+#define CAMSS_ISPIF_BCR					22
+#define CAMSS_CCI_BCR					23
+#define CAMSS_TOP_BCR					24
+#define CAMSS_AHB_BCR					25
+#define CAMSS_MICRO_BCR					26
+#define CAMSS_JPEG_BCR					27
+#define CAMSS_VFE0_BCR					28
+#define CAMSS_VFE1_BCR					29
+#define CAMSS_VFE_VBIF_BCR				30
+#define CAMSS_CPP_TOP_BCR				31
+#define CAMSS_CPP_BCR					32
+#define CAMSS_CSI_VFE0_BCR				33
+#define CAMSS_CSI_VFE1_BCR				34
+#define CAMSS_FD_BCR					35
+#define THROTTLE_CAMSS_BCR				36
+#define MNOCAHB_BCR					37
+#define MNOCAXI_BCR					38
+#define BMIC_SMMU_BCR					39
+#define MNOC_MAXI_BCR					40
+#define VMEM_BCR					41
+#define BTO_BCR						42
+
+#define VIDEO_TOP_GDSC		1
+#define VIDEO_SUBCORE0_GDSC	2
+#define VIDEO_SUBCORE1_GDSC	3
+#define MDSS_GDSC		4
+#define CAMSS_TOP_GDSC		5
+#define CAMSS_VFE0_GDSC		6
+#define CAMSS_VFE1_GDSC		7
+#define CAMSS_CPP_GDSC		8
+#define BIMC_SMMU_GDSC		9
+
+#endif
diff --git a/include/dt-bindings/clock/qcom,videocc-sc7180.h b/include/dt-bindings/clock/qcom,videocc-sc7180.h
new file mode 100644
index 000000000000..7acaf1366b13
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,videocc-sc7180.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SC7180_H
+#define _DT_BINDINGS_CLK_QCOM_VIDEO_CC_SC7180_H
+
+/* VIDEO_CC clocks */
+#define VIDEO_PLL0				0
+#define VIDEO_CC_VCODEC0_AXI_CLK		1
+#define VIDEO_CC_VCODEC0_CORE_CLK		2
+#define VIDEO_CC_VENUS_AHB_CLK			3
+#define VIDEO_CC_VENUS_CLK_SRC			4
+#define VIDEO_CC_VENUS_CTL_AXI_CLK		5
+#define VIDEO_CC_VENUS_CTL_CORE_CLK		6
+#define VIDEO_CC_XO_CLK				7
+
+/* VIDEO_CC GDSCRs */
+#define VENUS_GDSC				0
+#define VCODEC0_GDSC				1
+
+#endif
diff --git a/include/dt-bindings/clock/sun50i-a64-ccu.h b/include/dt-bindings/clock/sun50i-a64-ccu.h
index a8ac4cfcdcbc..e512a1c9b0fc 100644
--- a/include/dt-bindings/clock/sun50i-a64-ccu.h
+++ b/include/dt-bindings/clock/sun50i-a64-ccu.h
@@ -46,6 +46,7 @@
 #define CLK_PLL_VIDEO0		7
 #define CLK_PLL_PERIPH0		11
 
+#define CLK_CPUX		21
 #define CLK_BUS_MIPI_DSI	28
 #define CLK_BUS_CE		29
 #define CLK_BUS_DMA		30
diff --git a/include/dt-bindings/clock/sun6i-a31-ccu.h b/include/dt-bindings/clock/sun6i-a31-ccu.h
index c5d13340184a..39878d9dce9f 100644
--- a/include/dt-bindings/clock/sun6i-a31-ccu.h
+++ b/include/dt-bindings/clock/sun6i-a31-ccu.h
@@ -49,6 +49,8 @@
 
 #define CLK_PLL_VIDEO1_2X	13
 
+#define CLK_PLL_MIPI		15
+
 #define CLK_CPU			18
 
 #define CLK_AHB1_MIPIDSI	23
diff --git a/include/dt-bindings/clock/sun8i-a23-a33-ccu.h b/include/dt-bindings/clock/sun8i-a23-a33-ccu.h
index f8222b6b2cc3..eb524d0bbd01 100644
--- a/include/dt-bindings/clock/sun8i-a23-a33-ccu.h
+++ b/include/dt-bindings/clock/sun8i-a23-a33-ccu.h
@@ -43,6 +43,8 @@
 #ifndef _DT_BINDINGS_CLK_SUN8I_A23_A33_H_
 #define _DT_BINDINGS_CLK_SUN8I_A23_A33_H_
 
+#define CLK_PLL_MIPI		13
+
 #define CLK_CPUX		18
 
 #define CLK_BUS_MIPI_DSI	23
diff --git a/include/dt-bindings/clock/sun8i-r40-ccu.h b/include/dt-bindings/clock/sun8i-r40-ccu.h
index f9e15a235626..d7337b55a4ef 100644
--- a/include/dt-bindings/clock/sun8i-r40-ccu.h
+++ b/include/dt-bindings/clock/sun8i-r40-ccu.h
@@ -176,7 +176,7 @@
 #define CLK_AVS			152
 #define CLK_HDMI		153
 #define CLK_HDMI_SLOW		154
-
+#define CLK_MBUS		155
 #define CLK_DSI_DPHY		156
 #define CLK_TVE0		157
 #define CLK_TVE1		158
diff --git a/include/dt-bindings/clk/ti-dra7-atl.h b/include/dt-bindings/clock/ti-dra7-atl.h
index 42dd4164f6f4..42dd4164f6f4 100644
--- a/include/dt-bindings/clk/ti-dra7-atl.h
+++ b/include/dt-bindings/clock/ti-dra7-atl.h
diff --git a/include/dt-bindings/clock/xlnx-versal-clk.h b/include/dt-bindings/clock/xlnx-versal-clk.h
new file mode 100644
index 000000000000..264d634d226e
--- /dev/null
+++ b/include/dt-bindings/clock/xlnx-versal-clk.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (C) 2019 Xilinx Inc.
+ *
+ */
+
+#ifndef _DT_BINDINGS_CLK_VERSAL_H
+#define _DT_BINDINGS_CLK_VERSAL_H
+
+#define PMC_PLL					1
+#define APU_PLL					2
+#define RPU_PLL					3
+#define CPM_PLL					4
+#define NOC_PLL					5
+#define PLL_MAX					6
+#define PMC_PRESRC				7
+#define PMC_POSTCLK				8
+#define PMC_PLL_OUT				9
+#define PPLL					10
+#define NOC_PRESRC				11
+#define NOC_POSTCLK				12
+#define NOC_PLL_OUT				13
+#define NPLL					14
+#define APU_PRESRC				15
+#define APU_POSTCLK				16
+#define APU_PLL_OUT				17
+#define APLL					18
+#define RPU_PRESRC				19
+#define RPU_POSTCLK				20
+#define RPU_PLL_OUT				21
+#define RPLL					22
+#define CPM_PRESRC				23
+#define CPM_POSTCLK				24
+#define CPM_PLL_OUT				25
+#define CPLL					26
+#define PPLL_TO_XPD				27
+#define NPLL_TO_XPD				28
+#define APLL_TO_XPD				29
+#define RPLL_TO_XPD				30
+#define EFUSE_REF				31
+#define SYSMON_REF				32
+#define IRO_SUSPEND_REF				33
+#define USB_SUSPEND				34
+#define SWITCH_TIMEOUT				35
+#define RCLK_PMC				36
+#define RCLK_LPD				37
+#define WDT					38
+#define TTC0					39
+#define TTC1					40
+#define TTC2					41
+#define TTC3					42
+#define GEM_TSU					43
+#define GEM_TSU_LB				44
+#define MUXED_IRO_DIV2				45
+#define MUXED_IRO_DIV4				46
+#define PSM_REF					47
+#define GEM0_RX					48
+#define GEM0_TX					49
+#define GEM1_RX					50
+#define GEM1_TX					51
+#define CPM_CORE_REF				52
+#define CPM_LSBUS_REF				53
+#define CPM_DBG_REF				54
+#define CPM_AUX0_REF				55
+#define CPM_AUX1_REF				56
+#define QSPI_REF				57
+#define OSPI_REF				58
+#define SDIO0_REF				59
+#define SDIO1_REF				60
+#define PMC_LSBUS_REF				61
+#define I2C_REF					62
+#define TEST_PATTERN_REF			63
+#define DFT_OSC_REF				64
+#define PMC_PL0_REF				65
+#define PMC_PL1_REF				66
+#define PMC_PL2_REF				67
+#define PMC_PL3_REF				68
+#define CFU_REF					69
+#define SPARE_REF				70
+#define NPI_REF					71
+#define HSM0_REF				72
+#define HSM1_REF				73
+#define SD_DLL_REF				74
+#define FPD_TOP_SWITCH				75
+#define FPD_LSBUS				76
+#define ACPU					77
+#define DBG_TRACE				78
+#define DBG_FPD					79
+#define LPD_TOP_SWITCH				80
+#define ADMA					81
+#define LPD_LSBUS				82
+#define CPU_R5					83
+#define CPU_R5_CORE				84
+#define CPU_R5_OCM				85
+#define CPU_R5_OCM2				86
+#define IOU_SWITCH				87
+#define GEM0_REF				88
+#define GEM1_REF				89
+#define GEM_TSU_REF				90
+#define USB0_BUS_REF				91
+#define UART0_REF				92
+#define UART1_REF				93
+#define SPI0_REF				94
+#define SPI1_REF				95
+#define CAN0_REF				96
+#define CAN1_REF				97
+#define I2C0_REF				98
+#define I2C1_REF				99
+#define DBG_LPD					100
+#define TIMESTAMP_REF				101
+#define DBG_TSTMP				102
+#define CPM_TOPSW_REF				103
+#define USB3_DUAL_REF				104
+#define OUTCLK_MAX				105
+#define REF_CLK					106
+#define PL_ALT_REF_CLK				107
+#define MUXED_IRO				108
+#define PL_EXT					109
+#define PL_LB					110
+#define MIO_50_OR_51				111
+#define MIO_24_OR_25				112
+
+#endif
diff --git a/include/dt-bindings/reset/qcom,gcc-ipq6018.h b/include/dt-bindings/reset/qcom,gcc-ipq6018.h
new file mode 100644
index 000000000000..02a220ad0105
--- /dev/null
+++ b/include/dt-bindings/reset/qcom,gcc-ipq6018.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_RESET_IPQ_GCC_6018_H
+#define _DT_BINDINGS_RESET_IPQ_GCC_6018_H
+
+#define GCC_BLSP1_BCR				0
+#define GCC_BLSP1_QUP1_BCR			1
+#define GCC_BLSP1_UART1_BCR			2
+#define GCC_BLSP1_QUP2_BCR			3
+#define GCC_BLSP1_UART2_BCR			4
+#define GCC_BLSP1_QUP3_BCR			5
+#define GCC_BLSP1_UART3_BCR			6
+#define GCC_BLSP1_QUP4_BCR			7
+#define GCC_BLSP1_UART4_BCR			8
+#define GCC_BLSP1_QUP5_BCR			9
+#define GCC_BLSP1_UART5_BCR			10
+#define GCC_BLSP1_QUP6_BCR			11
+#define GCC_BLSP1_UART6_BCR			12
+#define GCC_IMEM_BCR				13
+#define GCC_SMMU_BCR				14
+#define GCC_APSS_TCU_BCR			15
+#define GCC_SMMU_XPU_BCR			16
+#define GCC_PCNOC_TBU_BCR			17
+#define GCC_SMMU_CFG_BCR			18
+#define GCC_PRNG_BCR				19
+#define GCC_BOOT_ROM_BCR			20
+#define GCC_CRYPTO_BCR				21
+#define GCC_WCSS_BCR				22
+#define GCC_WCSS_Q6_BCR				23
+#define GCC_NSS_BCR				24
+#define GCC_SEC_CTRL_BCR			25
+#define GCC_DDRSS_BCR				26
+#define GCC_SYSTEM_NOC_BCR			27
+#define GCC_PCNOC_BCR				28
+#define GCC_TCSR_BCR				29
+#define GCC_QDSS_BCR				30
+#define GCC_DCD_BCR				31
+#define GCC_MSG_RAM_BCR				32
+#define GCC_MPM_BCR				33
+#define GCC_SPDM_BCR				34
+#define GCC_RBCPR_BCR				35
+#define GCC_RBCPR_MX_BCR			36
+#define GCC_TLMM_BCR				37
+#define GCC_RBCPR_WCSS_BCR			38
+#define GCC_USB0_PHY_BCR			39
+#define GCC_USB3PHY_0_PHY_BCR			40
+#define GCC_USB0_BCR				41
+#define GCC_USB1_BCR				42
+#define GCC_QUSB2_0_PHY_BCR			43
+#define GCC_QUSB2_1_PHY_BCR			44
+#define GCC_SDCC1_BCR				45
+#define GCC_SNOC_BUS_TIMEOUT0_BCR		46
+#define GCC_SNOC_BUS_TIMEOUT1_BCR		47
+#define GCC_SNOC_BUS_TIMEOUT2_BCR		48
+#define GCC_PCNOC_BUS_TIMEOUT0_BCR		49
+#define GCC_PCNOC_BUS_TIMEOUT1_BCR		50
+#define GCC_PCNOC_BUS_TIMEOUT2_BCR		51
+#define GCC_PCNOC_BUS_TIMEOUT3_BCR		52
+#define GCC_PCNOC_BUS_TIMEOUT4_BCR		53
+#define GCC_PCNOC_BUS_TIMEOUT5_BCR		54
+#define GCC_PCNOC_BUS_TIMEOUT6_BCR		55
+#define GCC_PCNOC_BUS_TIMEOUT7_BCR		56
+#define GCC_PCNOC_BUS_TIMEOUT8_BCR		57
+#define GCC_PCNOC_BUS_TIMEOUT9_BCR		58
+#define GCC_UNIPHY0_BCR				59
+#define GCC_UNIPHY1_BCR				60
+#define GCC_CMN_12GPLL_BCR			61
+#define GCC_QPIC_BCR				62
+#define GCC_MDIO_BCR				63
+#define GCC_WCSS_CORE_TBU_BCR			64
+#define GCC_WCSS_Q6_TBU_BCR			65
+#define GCC_USB0_TBU_BCR			66
+#define GCC_PCIE0_TBU_BCR			67
+#define GCC_PCIE0_BCR				68
+#define GCC_PCIE0_PHY_BCR			69
+#define GCC_PCIE0PHY_PHY_BCR			70
+#define GCC_PCIE0_LINK_DOWN_BCR			71
+#define GCC_DCC_BCR				72
+#define GCC_APC0_VOLTAGE_DROOP_DETECTOR_BCR	73
+#define GCC_SMMU_CATS_BCR			74
+#define GCC_UBI0_AXI_ARES			75
+#define GCC_UBI0_AHB_ARES			76
+#define GCC_UBI0_NC_AXI_ARES			77
+#define GCC_UBI0_DBG_ARES			78
+#define GCC_UBI0_CORE_CLAMP_ENABLE		79
+#define GCC_UBI0_CLKRST_CLAMP_ENABLE		80
+#define GCC_UBI0_UTCM_ARES			81
+#define GCC_NSS_CFG_ARES			82
+#define GCC_NSS_NOC_ARES			83
+#define GCC_NSS_CRYPTO_ARES			84
+#define GCC_NSS_CSR_ARES			85
+#define GCC_NSS_CE_APB_ARES			86
+#define GCC_NSS_CE_AXI_ARES			87
+#define GCC_NSSNOC_CE_APB_ARES			88
+#define GCC_NSSNOC_CE_AXI_ARES			89
+#define GCC_NSSNOC_UBI0_AHB_ARES		90
+#define GCC_NSSNOC_SNOC_ARES			91
+#define GCC_NSSNOC_CRYPTO_ARES			92
+#define GCC_NSSNOC_ATB_ARES			93
+#define GCC_NSSNOC_QOSGEN_REF_ARES		94
+#define GCC_NSSNOC_TIMEOUT_REF_ARES		95
+#define GCC_PCIE0_PIPE_ARES			96
+#define GCC_PCIE0_SLEEP_ARES			97
+#define GCC_PCIE0_CORE_STICKY_ARES		98
+#define GCC_PCIE0_AXI_MASTER_ARES		99
+#define GCC_PCIE0_AXI_SLAVE_ARES		100
+#define GCC_PCIE0_AHB_ARES			101
+#define GCC_PCIE0_AXI_MASTER_STICKY_ARES	102
+#define GCC_PCIE0_AXI_SLAVE_STICKY_ARES		103
+#define GCC_PPE_FULL_RESET			104
+#define GCC_UNIPHY0_SOFT_RESET			105
+#define GCC_UNIPHY0_XPCS_RESET			106
+#define GCC_UNIPHY1_SOFT_RESET			107
+#define GCC_UNIPHY1_XPCS_RESET			108
+#define GCC_EDMA_HW_RESET			109
+#define GCC_ADSS_BCR				110
+#define GCC_NSS_NOC_TBU_BCR			111
+#define GCC_NSSPORT1_RESET			112
+#define GCC_NSSPORT2_RESET			113
+#define GCC_NSSPORT3_RESET			114
+#define GCC_NSSPORT4_RESET			115
+#define GCC_NSSPORT5_RESET			116
+#define GCC_UNIPHY0_PORT1_ARES			117
+#define GCC_UNIPHY0_PORT2_ARES			118
+#define GCC_UNIPHY0_PORT3_ARES			119
+#define GCC_UNIPHY0_PORT4_ARES			120
+#define GCC_UNIPHY0_PORT5_ARES			121
+#define GCC_UNIPHY0_PORT_4_5_RESET		122
+#define GCC_UNIPHY0_PORT_4_RESET		123
+#define GCC_LPASS_BCR				124
+#define GCC_UBI32_TBU_BCR			125
+#define GCC_LPASS_TBU_BCR			126
+#define GCC_WCSSAON_RESET			127
+#define GCC_LPASS_Q6_AXIM_ARES			128
+#define GCC_LPASS_Q6SS_TSCTR_1TO2_ARES		129
+#define GCC_LPASS_Q6SS_TRIG_ARES		130
+#define GCC_LPASS_Q6_ATBM_AT_ARES		131
+#define GCC_LPASS_Q6_PCLKDBG_ARES		132
+#define GCC_LPASS_CORE_AXIM_ARES		133
+#define GCC_LPASS_SNOC_CFG_ARES			134
+#define GCC_WCSS_DBG_ARES			135
+#define GCC_WCSS_ECAHB_ARES			136
+#define GCC_WCSS_ACMT_ARES			137
+#define GCC_WCSS_DBG_BDG_ARES			138
+#define GCC_WCSS_AHB_S_ARES			139
+#define GCC_WCSS_AXI_M_ARES			140
+#define GCC_Q6SS_DBG_ARES			141
+#define GCC_Q6_AHB_S_ARES			142
+#define GCC_Q6_AHB_ARES				143
+#define GCC_Q6_AXIM2_ARES			144
+#define GCC_Q6_AXIM_ARES			145
+#define GCC_UBI0_CORE_ARES			146
+
+#endif
diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h
index d12bb2153cd6..e4004d1e6725 100644
--- a/include/linux/attribute_container.h
+++ b/include/linux/attribute_container.h
@@ -54,6 +54,13 @@ void attribute_container_device_trigger(struct device *dev,
 					int (*fn)(struct attribute_container *,
 						  struct device *,
 						  struct device *));
+int attribute_container_device_trigger_safe(struct device *dev,
+					    int (*fn)(struct attribute_container *,
+						      struct device *,
+						      struct device *),
+					    int (*undo)(struct attribute_container *,
+							struct device *,
+							struct device *));
 void attribute_container_trigger(struct device *dev, 
 				 int (*fn)(struct attribute_container *,
 					   struct device *));
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 97967ce06de3..f88197c1ffc2 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,7 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/blkdev.h>
+#include <linux/device.h>
 #include <linux/writeback.h>
 #include <linux/blk-cgroup.h>
 #include <linux/backing-dev-defs.h>
@@ -504,4 +505,13 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << WB_async_congested));
 }
 
+extern const char *bdi_unknown_name;
+
+static inline const char *bdi_dev_name(struct backing_dev_info *bdi)
+{
+	if (!bdi || !bdi->dev)
+		return bdi_unknown_name;
+	return dev_name(bdi->dev);
+}
+
 #endif	/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 80ad521116d7..e52ceb1a73d3 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -186,7 +186,7 @@ bitmap_find_next_zero_area(unsigned long *map,
 					      align_mask, 0);
 }
 
-extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user,
+extern int bitmap_parse(const char *buf, unsigned int buflen,
 			unsigned long *dst, int nbits);
 extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
 			unsigned long *dst, int nbits);
@@ -454,12 +454,6 @@ static inline void bitmap_replace(unsigned long *dst,
 		__bitmap_replace(dst, old, new, mask, nbits);
 }
 
-static inline int bitmap_parse(const char *buf, unsigned int buflen,
-			unsigned long *maskp, int nmaskbits)
-{
-	return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
-}
-
 static inline void bitmap_next_clear_region(unsigned long *bitmap,
 					    unsigned int *rs, unsigned int *re,
 					    unsigned int end)
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index e479067c202c..47f54b459c26 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -11,8 +11,11 @@
 #  define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
 #endif
 
-#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
+#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
+#define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
+#define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
+#define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4c636c42ad68..053ea4b51988 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1711,6 +1711,13 @@ struct block_device_operations {
 	const struct pr_ops *pr_ops;
 };
 
+#ifdef CONFIG_COMPAT
+extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t,
+				      unsigned int, unsigned long);
+#else
+#define blkdev_compat_ptr_ioctl NULL
+#endif
+
 extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 				 unsigned long);
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index caf4b9df16eb..952ac035bab9 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -190,8 +190,14 @@ struct clk_duty {
  *
  * @init:	Perform platform-specific initialization magic.
  *		This is not not used by any of the basic clock types.
- *		Please consider other ways of solving initialization problems
- *		before using this callback, as its use is discouraged.
+ *		This callback exist for HW which needs to perform some
+ *		initialisation magic for CCF to get an accurate view of the
+ *		clock. It may also be used dynamic resource allocation is
+ *		required. It shall not used to deal with clock parameters,
+ *		such as rate or parents.
+ *		Returns 0 on success, -EERROR otherwise.
+ *
+ * @terminate:  Free any resource allocated by init.
  *
  * @debug_init:	Set up type-specific debugfs entries for this clock.  This
  *		is called once, after the debugfs directory entry for this
@@ -243,7 +249,8 @@ struct clk_ops {
 					  struct clk_duty *duty);
 	int		(*set_duty_cycle)(struct clk_hw *hw,
 					  struct clk_duty *duty);
-	void		(*init)(struct clk_hw *hw);
+	int		(*init)(struct clk_hw *hw);
+	void		(*terminate)(struct clk_hw *hw);
 	void		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
 };
 
@@ -321,29 +328,119 @@ struct clk_hw {
  * struct clk_fixed_rate - fixed-rate clock
  * @hw:		handle between common and hardware-specific interfaces
  * @fixed_rate:	constant frequency of clock
+ * @fixed_accuracy: constant accuracy of clock in ppb (parts per billion)
+ * @flags:	hardware specific flags
+ *
+ * Flags:
+ * * CLK_FIXED_RATE_PARENT_ACCURACY - Use the accuracy of the parent clk
+ *                                    instead of what's set in @fixed_accuracy.
  */
 struct clk_fixed_rate {
 	struct		clk_hw hw;
 	unsigned long	fixed_rate;
 	unsigned long	fixed_accuracy;
+	unsigned long	flags;
 };
 
-#define to_clk_fixed_rate(_hw) container_of(_hw, struct clk_fixed_rate, hw)
+#define CLK_FIXED_RATE_PARENT_ACCURACY		BIT(0)
 
 extern const struct clk_ops clk_fixed_rate_ops;
+struct clk_hw *__clk_hw_register_fixed_rate(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		unsigned long fixed_rate, unsigned long fixed_accuracy,
+		unsigned long clk_fixed_flags);
 struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		unsigned long fixed_rate);
-struct clk_hw *clk_hw_register_fixed_rate(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate);
-struct clk *clk_register_fixed_rate_with_accuracy(struct device *dev,
-		const char *name, const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate, unsigned long fixed_accuracy);
+/**
+ * clk_hw_register_fixed_rate - register fixed-rate clock with the clock
+ * framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ */
+#define clk_hw_register_fixed_rate(dev, name, parent_name, flags, fixed_rate)  \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \
+				     NULL, (flags), (fixed_rate), 0, 0)
+/**
+ * clk_hw_register_fixed_rate_parent_hw - register fixed-rate clock with
+ * the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_hw: pointer to parent clk
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ */
+#define clk_hw_register_fixed_rate_parent_hw(dev, name, parent_hw, flags,     \
+					     fixed_rate)		      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw),  \
+				     NULL, (flags), (fixed_rate), 0, 0)
+/**
+ * clk_hw_register_fixed_rate_parent_data - register fixed-rate clock with
+ * the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_data: parent clk data
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ */
+#define clk_hw_register_fixed_rate_parent_data(dev, name, parent_hw, flags,   \
+					     fixed_rate)		      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL,	      \
+				     (parent_data), (flags), (fixed_rate), 0, \
+				     0)
+/**
+ * clk_hw_register_fixed_rate_with_accuracy - register fixed-rate clock with
+ * the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ * @fixed_accuracy: non-adjustable clock accuracy
+ */
+#define clk_hw_register_fixed_rate_with_accuracy(dev, name, parent_name,      \
+						 flags, fixed_rate,	      \
+						 fixed_accuracy)	      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name),      \
+				     NULL, NULL, (flags), (fixed_rate),       \
+				     (fixed_accuracy), 0)
+/**
+ * clk_hw_register_fixed_rate_with_accuracy_parent_hw - register fixed-rate
+ * clock with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_hw: pointer to parent clk
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ * @fixed_accuracy: non-adjustable clock accuracy
+ */
+#define clk_hw_register_fixed_rate_with_accuracy_parent_hw(dev, name,	      \
+		parent_hw, flags, fixed_rate, fixed_accuracy)		      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw)   \
+				     NULL, NULL, (flags), (fixed_rate),	      \
+				     (fixed_accuracy), 0)
+/**
+ * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate
+ * clock with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ * @fixed_accuracy: non-adjustable clock accuracy
+ */
+#define clk_hw_register_fixed_rate_with_accuracy_parent_data(dev, name,	      \
+		parent_data, flags, fixed_rate, fixed_accuracy)		      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL,	      \
+				     (parent_data), NULL, (flags),	      \
+				     (fixed_rate), (fixed_accuracy), 0)
+
 void clk_unregister_fixed_rate(struct clk *clk);
-struct clk_hw *clk_hw_register_fixed_rate_with_accuracy(struct device *dev,
-		const char *name, const char *parent_name, unsigned long flags,
-		unsigned long fixed_rate, unsigned long fixed_accuracy);
 void clk_hw_unregister_fixed_rate(struct clk_hw *hw);
 
 void of_fixed_clk_setup(struct device_node *np);
@@ -386,14 +483,67 @@ struct clk_gate {
 #define CLK_GATE_BIG_ENDIAN		BIT(2)
 
 extern const struct clk_ops clk_gate_ops;
-struct clk *clk_register_gate(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
+struct clk_hw *__clk_hw_register_gate(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data,
+		unsigned long flags,
 		void __iomem *reg, u8 bit_idx,
 		u8 clk_gate_flags, spinlock_t *lock);
-struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name,
+struct clk *clk_register_gate(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 bit_idx,
 		u8 clk_gate_flags, spinlock_t *lock);
+/**
+ * clk_hw_register_gate - register a gate clock with the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_name: name of this clock's parent
+ * @flags: framework-specific flags for this clock
+ * @reg: register address to control gating of this clock
+ * @bit_idx: which bit in the register controls gating of this clock
+ * @clk_gate_flags: gate-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_gate(dev, name, parent_name, flags, reg, bit_idx,     \
+			     clk_gate_flags, lock)			      \
+	__clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL,      \
+			       NULL, (flags), (reg), (bit_idx),		      \
+			       (clk_gate_flags), (lock))
+/**
+ * clk_hw_register_gate_parent_hw - register a gate clock with the clock
+ * framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_hw: pointer to parent clk
+ * @flags: framework-specific flags for this clock
+ * @reg: register address to control gating of this clock
+ * @bit_idx: which bit in the register controls gating of this clock
+ * @clk_gate_flags: gate-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_gate_parent_hw(dev, name, parent_name, flags, reg,    \
+				       bit_idx, clk_gate_flags, lock)	      \
+	__clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL,      \
+			       NULL, (flags), (reg), (bit_idx),		      \
+			       (clk_gate_flags), (lock))
+/**
+ * clk_hw_register_gate_parent_data - register a gate clock with the clock
+ * framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_data: parent clk data
+ * @flags: framework-specific flags for this clock
+ * @reg: register address to control gating of this clock
+ * @bit_idx: which bit in the register controls gating of this clock
+ * @clk_gate_flags: gate-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_gate_parent_data(dev, name, parent_name, flags, reg,  \
+				       bit_idx, clk_gate_flags, lock)	      \
+	__clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL,      \
+			       NULL, (flags), (reg), (bit_idx),		      \
+			       (clk_gate_flags), (lock))
 void clk_unregister_gate(struct clk *clk);
 void clk_hw_unregister_gate(struct clk_hw *hw);
 int clk_gate_is_enabled(struct clk_hw *hw);
@@ -483,24 +633,153 @@ int divider_get_val(unsigned long rate, unsigned long parent_rate,
 		const struct clk_div_table *table, u8 width,
 		unsigned long flags);
 
-struct clk *clk_register_divider(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, spinlock_t *lock);
-struct clk_hw *clk_hw_register_divider(struct device *dev, const char *name,
-		const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, spinlock_t *lock);
+struct clk_hw *__clk_hw_register_divider(struct device *dev,
+		struct device_node *np, const char *name,
+		const char *parent_name, const struct clk_hw *parent_hw,
+		const struct clk_parent_data *parent_data, unsigned long flags,
+		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock);
 struct clk *clk_register_divider_table(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
 		u8 clk_divider_flags, const struct clk_div_table *table,
 		spinlock_t *lock);
-struct clk_hw *clk_hw_register_divider_table(struct device *dev,
-		const char *name, const char *parent_name, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, const struct clk_div_table *table,
-		spinlock_t *lock);
+/**
+ * clk_register_divider - register a divider clock with the clock framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_register_divider(dev, name, parent_name, flags, reg, shift, width, \
+			     clk_divider_flags, lock)			       \
+	clk_register_divider_table((dev), (name), (parent_name), (flags),      \
+				   (reg), (shift), (width),		       \
+				   (clk_divider_flags), NULL, (lock))
+/**
+ * clk_hw_register_divider - register a divider clock with the clock framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_divider(dev, name, parent_name, flags, reg, shift,    \
+				width, clk_divider_flags, lock)		      \
+	__clk_hw_register_divider((dev), NULL, (name), (parent_name), NULL,   \
+				  NULL, (flags), (reg), (shift), (width),     \
+				  (clk_divider_flags), NULL, (lock))
+/**
+ * clk_hw_register_divider_parent_hw - register a divider clock with the clock
+ * framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_hw: pointer to parent clk
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_divider_parent_hw(dev, name, parent_hw, flags, reg,   \
+					  shift, width, clk_divider_flags,    \
+					  lock)				      \
+	__clk_hw_register_divider((dev), NULL, (name), NULL, (parent_hw),     \
+				  NULL, (flags), (reg), (shift), (width),     \
+				  (clk_divider_flags), NULL, (lock))
+/**
+ * clk_hw_register_divider_parent_data - register a divider clock with the clock
+ * framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_data: parent clk data
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_divider_parent_data(dev, name, parent_data, flags,    \
+					    reg, shift, width,		      \
+					    clk_divider_flags, lock)	      \
+	__clk_hw_register_divider((dev), NULL, (name), NULL, NULL,	      \
+				  (parent_data), (flags), (reg), (shift),     \
+				  (width), (clk_divider_flags), NULL, (lock))
+/**
+ * clk_hw_register_divider_table - register a table based divider clock with
+ * the clock framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_name: name of clock's parent
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @table: array of divider/value pairs ending with a div set to 0
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_divider_table(dev, name, parent_name, flags, reg,     \
+				      shift, width, clk_divider_flags, table, \
+				      lock)				      \
+	__clk_hw_register_divider((dev), NULL, (name), (parent_name), NULL,   \
+				  NULL, (flags), (reg), (shift), (width),     \
+				  (clk_divider_flags), (table), (lock))
+/**
+ * clk_hw_register_divider_table_parent_hw - register a table based divider
+ * clock with the clock framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_hw: pointer to parent clk
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @table: array of divider/value pairs ending with a div set to 0
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_divider_table_parent_hw(dev, name, parent_hw, flags,  \
+						reg, shift, width,	      \
+						clk_divider_flags, table,     \
+						lock)			      \
+	__clk_hw_register_divider((dev), NULL, (name), NULL, (parent_hw),     \
+				  NULL, (flags), (reg), (shift), (width),     \
+				  (clk_divider_flags), (table), (lock))
+/**
+ * clk_hw_register_divider_table_parent_data - register a table based divider
+ * clock with the clock framework
+ * @dev: device registering this clock
+ * @name: name of this clock
+ * @parent_data: parent clk data
+ * @flags: framework-specific flags
+ * @reg: register address to adjust divider
+ * @shift: number of bits to shift the bitfield
+ * @width: width of the bitfield
+ * @clk_divider_flags: divider-specific flags for this clock
+ * @table: array of divider/value pairs ending with a div set to 0
+ * @lock: shared register lock for this clock
+ */
+#define clk_hw_register_divider_table_parent_data(dev, name, parent_data,     \
+						  flags, reg, shift, width,   \
+						  clk_divider_flags, table,   \
+						  lock)			      \
+	__clk_hw_register_divider((dev), NULL, (name), NULL, NULL,	      \
+				  (parent_data), (flags), (reg), (shift),     \
+				  (width), (clk_divider_flags), (table),      \
+				  (lock))
+
 void clk_unregister_divider(struct clk *clk);
 void clk_hw_unregister_divider(struct clk_hw *hw);
 
@@ -555,28 +834,48 @@ struct clk_mux {
 extern const struct clk_ops clk_mux_ops;
 extern const struct clk_ops clk_mux_ro_ops;
 
-struct clk *clk_register_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_mux_flags, spinlock_t *lock);
-struct clk_hw *clk_hw_register_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_mux_flags, spinlock_t *lock);
-
-struct clk *clk_register_mux_table(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u32 mask,
+struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np,
+		const char *name, u8 num_parents,
+		const char * const *parent_names,
+		const struct clk_hw **parent_hws,
+		const struct clk_parent_data *parent_data,
+		unsigned long flags, void __iomem *reg, u8 shift, u32 mask,
 		u8 clk_mux_flags, u32 *table, spinlock_t *lock);
-struct clk_hw *clk_hw_register_mux_table(struct device *dev, const char *name,
+struct clk *clk_register_mux_table(struct device *dev, const char *name,
 		const char * const *parent_names, u8 num_parents,
-		unsigned long flags,
-		void __iomem *reg, u8 shift, u32 mask,
+		unsigned long flags, void __iomem *reg, u8 shift, u32 mask,
 		u8 clk_mux_flags, u32 *table, spinlock_t *lock);
 
+#define clk_register_mux(dev, name, parent_names, num_parents, flags, reg,    \
+			 shift, width, clk_mux_flags, lock)		      \
+	clk_register_mux_table((dev), (name), (parent_names), (num_parents),  \
+			       (flags), (reg), (shift), BIT((width)) - 1,     \
+			       (clk_mux_flags), NULL, (lock))
+#define clk_hw_register_mux_table(dev, name, parent_names, num_parents,	      \
+				  flags, reg, shift, mask, clk_mux_flags,     \
+				  table, lock)				      \
+	__clk_hw_register_mux((dev), NULL, (name), (num_parents),	      \
+			      (parent_names), NULL, NULL, (flags), (reg),     \
+			      (shift), (mask), (clk_mux_flags), (table),      \
+			      (lock))
+#define clk_hw_register_mux(dev, name, parent_names, num_parents, flags, reg, \
+			    shift, width, clk_mux_flags, lock)		      \
+	__clk_hw_register_mux((dev), NULL, (name), (num_parents),	      \
+			      (parent_names), NULL, NULL, (flags), (reg),     \
+			      (shift), BIT((width)) - 1, (clk_mux_flags),     \
+			      NULL, (lock))
+#define clk_hw_register_mux_hws(dev, name, parent_hws, num_parents, flags,    \
+				reg, shift, width, clk_mux_flags, lock)	      \
+	__clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL,	      \
+			      (parent_hws), NULL, (flags), (reg), (shift),    \
+			      BIT((width)) - 1, (clk_mux_flags), NULL, (lock))
+#define clk_hw_register_mux_parent_data(dev, name, parent_data, num_parents,  \
+					flags, reg, shift, width,	      \
+					clk_mux_flags, lock)		      \
+	__clk_hw_register_mux((dev), NULL, (name), (num_parents), NULL, NULL, \
+			      (parent_data), (flags), (reg), (shift),	      \
+			      BIT((width)) - 1, (clk_mux_flags), NULL, (lock))
+
 int clk_mux_val_to_index(struct clk_hw *hw, u32 *table, unsigned int flags,
 			 unsigned int val);
 unsigned int clk_mux_index_to_val(u32 *table, unsigned int flags, u8 index);
@@ -743,6 +1042,12 @@ struct clk *clk_register_composite(struct device *dev, const char *name,
 		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
+struct clk *clk_register_composite_pdata(struct device *dev, const char *name,
+		const struct clk_parent_data *parent_data, int num_parents,
+		struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
+		unsigned long flags);
 void clk_unregister_composite(struct clk *clk);
 struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name,
 		const char * const *parent_names, int num_parents,
@@ -750,45 +1055,14 @@ struct clk_hw *clk_hw_register_composite(struct device *dev, const char *name,
 		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
 		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
-void clk_hw_unregister_composite(struct clk_hw *hw);
-
-/**
- * struct clk_gpio - gpio gated clock
- *
- * @hw:		handle between common and hardware-specific interfaces
- * @gpiod:	gpio descriptor
- *
- * Clock with a gpio control for enabling and disabling the parent clock
- * or switching between two parents by asserting or deasserting the gpio.
- *
- * Implements .enable, .disable and .is_enabled or
- * .get_parent, .set_parent and .determine_rate depending on which clk_ops
- * is used.
- */
-struct clk_gpio {
-	struct clk_hw	hw;
-	struct gpio_desc *gpiod;
-};
-
-#define to_clk_gpio(_hw) container_of(_hw, struct clk_gpio, hw)
-
-extern const struct clk_ops clk_gpio_gate_ops;
-struct clk *clk_register_gpio_gate(struct device *dev, const char *name,
-		const char *parent_name, struct gpio_desc *gpiod,
-		unsigned long flags);
-struct clk_hw *clk_hw_register_gpio_gate(struct device *dev, const char *name,
-		const char *parent_name, struct gpio_desc *gpiod,
-		unsigned long flags);
-void clk_hw_unregister_gpio_gate(struct clk_hw *hw);
-
-extern const struct clk_ops clk_gpio_mux_ops;
-struct clk *clk_register_gpio_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod,
-		unsigned long flags);
-struct clk_hw *clk_hw_register_gpio_mux(struct device *dev, const char *name,
-		const char * const *parent_names, u8 num_parents, struct gpio_desc *gpiod,
+struct clk_hw *clk_hw_register_composite_pdata(struct device *dev,
+		const char *name,
+		const struct clk_parent_data *parent_data, int num_parents,
+		struct clk_hw *mux_hw, const struct clk_ops *mux_ops,
+		struct clk_hw *rate_hw, const struct clk_ops *rate_ops,
+		struct clk_hw *gate_hw, const struct clk_ops *gate_ops,
 		unsigned long flags);
-void clk_hw_unregister_gpio_mux(struct clk_hw *hw);
+void clk_hw_unregister_composite(struct clk_hw *hw);
 
 struct clk *clk_register(struct device *dev, struct clk_hw *hw);
 struct clk *devm_clk_register(struct device *dev, struct clk_hw *hw);
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 18b7b95a8253..7fd6a1febcf4 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -627,6 +627,9 @@ long clk_round_rate(struct clk *clk, unsigned long rate);
  * @clk: clock source
  * @rate: desired clock rate in Hz
  *
+ * Updating the rate starts at the top-most affected clock and then
+ * walks the tree down to the bottom-most clock that needs updating.
+ *
  * Returns success (0) or negative errno.
  */
 int clk_set_rate(struct clk *clk, unsigned long rate);
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 68f79d855c3d..11083d84eb23 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -958,4 +958,22 @@ static inline bool in_compat_syscall(void) { return false; }
 
 #endif /* CONFIG_COMPAT */
 
+/*
+ * A pointer passed in from user mode. This should not
+ * be used for syscall parameters, just declare them
+ * as pointers because the syscall entry code will have
+ * appropriately converted them already.
+ */
+#ifndef compat_ptr
+static inline void __user *compat_ptr(compat_uptr_t uptr)
+{
+	return (void __user *)(unsigned long)uptr;
+}
+#endif
+
+static inline compat_uptr_t ptr_to_compat(void __user *uptr)
+{
+	return (u32)(unsigned long)uptr;
+}
+
 #endif /* _LINUX_COMPAT_H */
diff --git a/include/linux/console.h b/include/linux/console.h
index d09951d5a94e..f33016b3a401 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -101,7 +101,6 @@ extern const struct consw *conswitchp;
 extern const struct consw dummy_con;	/* dummy console buffer */
 extern const struct consw vga_con;	/* VGA text console */
 extern const struct consw newport_con;	/* SGI Newport console  */
-extern const struct consw prom_con;	/* SPARC PROM console */
 
 int con_is_bound(const struct consw *csw);
 int do_unregister_con_driver(const struct consw *csw);
@@ -201,7 +200,6 @@ extern void suspend_console(void);
 extern void resume_console(void);
 
 int mda_console_init(void);
-void prom_con_init(void);
 
 void vcs_make_sysfs(int index);
 void vcs_remove_sysfs(int index);
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 64ec82851aa3..8150f5ac176c 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -154,15 +154,6 @@ static inline void guest_exit_irqoff(void)
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
 
-static inline void guest_enter(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	guest_enter_irqoff();
-	local_irq_restore(flags);
-}
-
 static inline void guest_exit(void)
 {
 	unsigned long flags;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 31b1b0e03df8..018dce868de6 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -148,6 +148,20 @@ struct cpufreq_policy {
 	struct notifier_block nb_max;
 };
 
+/*
+ * Used for passing new cpufreq policy data to the cpufreq driver's ->verify()
+ * callback for sanitization.  That callback is only expected to modify the min
+ * and max values, if necessary, and specifically it must not update the
+ * frequency table.
+ */
+struct cpufreq_policy_data {
+	struct cpufreq_cpuinfo		cpuinfo;
+	struct cpufreq_frequency_table	*freq_table;
+	unsigned int			cpu;
+	unsigned int			min;    /* in kHz */
+	unsigned int			max;    /* in kHz */
+};
+
 struct cpufreq_freqs {
 	struct cpufreq_policy *policy;
 	unsigned int old;
@@ -201,8 +215,6 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
 struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu);
 void cpufreq_cpu_release(struct cpufreq_policy *policy);
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
-int cpufreq_set_policy(struct cpufreq_policy *policy,
-		       struct cpufreq_policy *new_policy);
 void refresh_frequency_limits(struct cpufreq_policy *policy);
 void cpufreq_update_policy(unsigned int cpu);
 void cpufreq_update_limits(unsigned int cpu);
@@ -284,7 +296,7 @@ struct cpufreq_driver {
 
 	/* needed by all drivers */
 	int		(*init)(struct cpufreq_policy *policy);
-	int		(*verify)(struct cpufreq_policy *policy);
+	int		(*verify)(struct cpufreq_policy_data *policy);
 
 	/* define one out of two */
 	int		(*setpolicy)(struct cpufreq_policy *policy);
@@ -415,8 +427,9 @@ static inline int cpufreq_thermal_control_enabled(struct cpufreq_driver *drv)
 		(drv->flags & CPUFREQ_IS_COOLING_DEV);
 }
 
-static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
-		unsigned int min, unsigned int max)
+static inline void cpufreq_verify_within_limits(struct cpufreq_policy_data *policy,
+						unsigned int min,
+						unsigned int max)
 {
 	if (policy->min < min)
 		policy->min = min;
@@ -432,10 +445,10 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy *policy,
 }
 
 static inline void
-cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy)
+cpufreq_verify_within_cpu_limits(struct cpufreq_policy_data *policy)
 {
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
-			policy->cpuinfo.max_freq);
+				     policy->cpuinfo.max_freq);
 }
 
 #ifdef CONFIG_CPU_FREQ
@@ -513,6 +526,7 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
  *                          CPUFREQ GOVERNORS                        *
  *********************************************************************/
 
+#define CPUFREQ_POLICY_UNKNOWN		(0)
 /*
  * If (cpufreq_driver->target) exists, the ->governor decides what frequency
  * within the limits is used. If (cpufreq_driver->setpolicy> exists, these
@@ -684,9 +698,9 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev,
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table);
 
-int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
+int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy,
 				   struct cpufreq_frequency_table *table);
-int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy);
+int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy);
 
 int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
 				 unsigned int target_freq,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 78a73eba64dd..d5cc88514aee 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -663,9 +663,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
  */
 static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
-	unsigned int len = strchrnul(buf, '\n') - buf;
-
-	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
+	return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index bf9b6cafa4c2..3d013de64f70 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -83,7 +83,7 @@ struct dentry *debugfs_create_automount(const char *name,
 					void *data);
 
 void debugfs_remove(struct dentry *dentry);
-void debugfs_remove_recursive(struct dentry *dentry);
+#define debugfs_remove_recursive debugfs_remove
 
 const struct file_operations *debugfs_real_fops(const struct file *filp);
 
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index af73f835c51c..abf5459a5b9d 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -249,31 +249,6 @@ struct dma_buf_ops {
 	 */
 	int (*mmap)(struct dma_buf *, struct vm_area_struct *vma);
 
-	/**
-	 * @map:
-	 *
-	 * Maps a page from the buffer into kernel address space. The page is
-	 * specified by offset into the buffer in PAGE_SIZE units.
-	 *
-	 * This callback is optional.
-	 *
-	 * Returns:
-	 *
-	 * Virtual address pointer where requested page can be accessed. NULL
-	 * on error or when this function is unimplemented by the exporter.
-	 */
-	void *(*map)(struct dma_buf *, unsigned long);
-
-	/**
-	 * @unmap:
-	 *
-	 * Unmaps a page from the buffer. Page offset and address pointer should
-	 * be the same as the one passed to and returned by matching call to map.
-	 *
-	 * This callback is optional.
-	 */
-	void (*unmap)(struct dma_buf *, unsigned long, void *);
-
 	void *(*vmap)(struct dma_buf *);
 	void (*vunmap)(struct dma_buf *, void *vaddr);
 };
@@ -464,8 +439,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 			     enum dma_data_direction dir);
 int dma_buf_end_cpu_access(struct dma_buf *dma_buf,
 			   enum dma_data_direction dir);
-void *dma_buf_kmap(struct dma_buf *, unsigned long);
-void dma_buf_kunmap(struct dma_buf *, unsigned long, void *);
 
 int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *,
 		 unsigned long);
diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h
new file mode 100644
index 000000000000..454e354d1ffb
--- /dev/null
+++ b/include/linux/dma-heap.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DMABUF Heaps Allocation Infrastructure
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+
+#ifndef _DMA_HEAPS_H
+#define _DMA_HEAPS_H
+
+#include <linux/cdev.h>
+#include <linux/types.h>
+
+struct dma_heap;
+
+/**
+ * struct dma_heap_ops - ops to operate on a given heap
+ * @allocate:		allocate dmabuf and return fd
+ *
+ * allocate returns dmabuf fd  on success, -errno on error.
+ */
+struct dma_heap_ops {
+	int (*allocate)(struct dma_heap *heap,
+			unsigned long len,
+			unsigned long fd_flags,
+			unsigned long heap_flags);
+};
+
+/**
+ * struct dma_heap_export_info - information needed to export a new dmabuf heap
+ * @name:	used for debugging/device-node name
+ * @ops:	ops struct for this heap
+ * @priv:	heap exporter private data
+ *
+ * Information needed to export a new dmabuf heap.
+ */
+struct dma_heap_export_info {
+	const char *name;
+	const struct dma_heap_ops *ops;
+	void *priv;
+};
+
+/**
+ * dma_heap_get_drvdata() - get per-heap driver data
+ * @heap: DMA-Heap to retrieve private data for
+ *
+ * Returns:
+ * The per-heap data for the heap.
+ */
+void *dma_heap_get_drvdata(struct dma_heap *heap);
+
+/**
+ * dma_heap_add - adds a heap to dmabuf heaps
+ * @exp_info:		information needed to register this heap
+ */
+struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info);
+
+#endif /* _DMA_HEAPS_H */
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index bc6d79b00c4e..8f000fada5a4 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -61,6 +61,15 @@ static inline void eventpoll_release(struct file *file)
 	eventpoll_release_file(file);
 }
 
+int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
+		 bool nonblock);
+
+/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
+static inline int ep_op_has_event(int op)
+{
+	return op != EPOLL_CTL_DEL;
+}
+
 #else
 
 static inline void eventpoll_init_file(struct file *file) {}
diff --git a/include/linux/export.h b/include/linux/export.h
index 627841448293..fceb5e855717 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -82,16 +82,29 @@ struct kernel_symbol {
 
 #else
 
-/* For every exported symbol, place a struct in the __ksymtab section */
-#define ___EXPORT_SYMBOL(sym, sec, ns)					\
-	extern typeof(sym) sym;						\
-	__CRC_SYMBOL(sym, sec);						\
-	static const char __kstrtab_##sym[]				\
-	__attribute__((section("__ksymtab_strings"), used, aligned(1)))	\
-	= #sym;								\
-	static const char __kstrtabns_##sym[]				\
-	__attribute__((section("__ksymtab_strings"), used, aligned(1)))	\
-	= ns;								\
+/*
+ * For every exported symbol, do the following:
+ *
+ * - If applicable, place a CRC entry in the __kcrctab section.
+ * - Put the name of the symbol and namespace (empty string "" for none) in
+ *   __ksymtab_strings.
+ * - Place a struct kernel_symbol entry in the __ksymtab section.
+ *
+ * note on .section use: we specify progbits since usage of the "M" (SHF_MERGE)
+ * section flag requires it. Use '%progbits' instead of '@progbits' since the
+ * former apparently works on all arches according to the binutils source.
+ */
+#define ___EXPORT_SYMBOL(sym, sec, ns)						\
+	extern typeof(sym) sym;							\
+	extern const char __kstrtab_##sym[];					\
+	extern const char __kstrtabns_##sym[];					\
+	__CRC_SYMBOL(sym, sec);							\
+	asm("	.section \"__ksymtab_strings\",\"aMS\",%progbits,1	\n"	\
+	    "__kstrtab_" #sym ":					\n"	\
+	    "	.asciz 	\"" #sym "\"					\n"	\
+	    "__kstrtabns_" #sym ":					\n"	\
+	    "	.asciz 	\"" ns "\"					\n"	\
+	    "	.previous						\n");	\
 	__KSYMTAB_ENTRY(sym, sec)
 
 #endif
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 284738996028..ac3f4888b3df 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -23,6 +23,7 @@
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
+#define COMPRESS_ADDR		((block_t)-2)	/* used as compressed data flag */
 
 #define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
 #define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
@@ -271,6 +272,10 @@ struct f2fs_inode {
 			__le32 i_inode_checksum;/* inode meta checksum */
 			__le64 i_crtime;	/* creation time */
 			__le32 i_crtime_nsec;	/* creation time in nano scale */
+			__le64 i_compr_blocks;	/* # of compressed blocks */
+			__u8 i_compress_algorithm;	/* compress algorithm */
+			__u8 i_log_cluster_size;	/* log of cluster size */
+			__le16 i_padding;		/* padding */
 			__le32 i_extra_end[0];	/* for attribute size calculation */
 		} __packed;
 		__le32 i_addr[DEF_ADDRS_PER_INODE];	/* Pointers to data blocks */
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
index 8bf3d79f3e82..f3f0b97b1675 100644
--- a/include/linux/falloc.h
+++ b/include/linux/falloc.h
@@ -51,8 +51,6 @@ struct space_resv_32 {
 #define FS_IOC_UNRESVSP64_32	_IOW ('X', 43, struct space_resv_32)
 #define FS_IOC_ZERO_RANGE_32	_IOW ('X', 57, struct space_resv_32)
 
-int compat_ioctl_preallocate(struct file *, int, struct space_resv_32 __user *);
-
 #endif
 
 #endif /* _FALLOC_H_ */
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 41e0069eca0a..3b4b2f0c6994 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -472,7 +472,7 @@ struct fb_info {
 	struct fb_deferred_io *fbdefio;
 #endif
 
-	struct fb_ops *fbops;
+	const struct fb_ops *fbops;
 	struct device *device;		/* This is the parent */
 	struct device *dev;		/* This is this fb device */
 	int class_flag;                    /* private sysfs flags */
@@ -606,7 +606,6 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf,
 /* drivers/video/fbmem.c */
 extern int register_framebuffer(struct fb_info *fb_info);
 extern void unregister_framebuffer(struct fb_info *fb_info);
-extern void unlink_framebuffer(struct fb_info *fb_info);
 extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
 					       const char *name);
 extern int remove_conflicting_framebuffers(struct apertures_struct *a,
@@ -626,6 +625,7 @@ extern int fb_new_modelist(struct fb_info *info);
 extern struct fb_info *registered_fb[FB_MAX];
 extern int num_registered_fb;
 extern bool fb_center_logo;
+extern int fb_logo_count;
 extern struct class *fb_class;
 
 #define for_each_registered_fb(i)		\
diff --git a/include/linux/file.h b/include/linux/file.h
index 3fcddff56bc4..c6c7b24ea9f7 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -16,6 +16,7 @@ extern void fput(struct file *);
 extern void fput_many(struct file *, unsigned int);
 
 struct file_operations;
+struct task_struct;
 struct vfsmount;
 struct dentry;
 struct inode;
@@ -47,6 +48,7 @@ static inline void fdput(struct fd fd)
 extern struct file *fget(unsigned int fd);
 extern struct file *fget_many(unsigned int fd, unsigned int refs);
 extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_task(struct task_struct *task, unsigned int fd);
 extern unsigned long __fdget(unsigned int fd);
 extern unsigned long __fdget_raw(unsigned int fd);
 extern unsigned long __fdget_pos(unsigned int fd);
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index e41ad9e37136..1b9549d02544 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -89,6 +89,7 @@ enum pm_ret_status {
 	XST_PM_INVALID_NODE,
 	XST_PM_DOUBLE_REQ,
 	XST_PM_ABORT_SUSPEND,
+	XST_PM_MULT_USER = 2008,
 };
 
 enum pm_ioctl_id {
@@ -107,6 +108,7 @@ enum pm_query_id {
 	PM_QID_CLOCK_GET_PARENTS,
 	PM_QID_CLOCK_GET_ATTRIBUTES,
 	PM_QID_CLOCK_GET_NUM_CLOCKS = 12,
+	PM_QID_CLOCK_GET_MAX_DIVISOR,
 };
 
 enum zynqmp_pm_reset_action {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dddfcbb140a7..6eae91c0668f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1575,7 +1575,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid)
 	inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid);
 }
 
-extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran);
 extern struct timespec64 current_time(struct inode *inode);
 
 /*
@@ -2078,6 +2077,18 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 	};
 }
 
+static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
+			       struct file *filp)
+{
+	*kiocb = (struct kiocb) {
+		.ki_filp = filp,
+		.ki_flags = kiocb_src->ki_flags,
+		.ki_hint = kiocb_src->ki_hint,
+		.ki_ioprio = kiocb_src->ki_ioprio,
+		.ki_pos = kiocb_src->ki_pos,
+	};
+}
+
 /*
  * Inode state bits.  Protected by inode->i_lock
  *
@@ -2552,10 +2563,6 @@ extern int finish_open(struct file *file, struct dentry *dentry,
 			int (*open)(struct inode *, struct file *));
 extern int finish_no_open(struct file *file, struct dentry *dentry);
 
-/* fs/ioctl.c */
-
-extern int ioctl_preallocate(struct file *filp, int mode, void __user *argp);
-
 /* fs/dcache.c */
 extern void __init vfs_caches_init_early(void);
 extern void __init vfs_caches_init(void);
@@ -2741,7 +2748,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 
 extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
 				  loff_t lend);
-extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
 extern int __filemap_fdatawrite_range(struct address_space *mapping,
@@ -2751,6 +2757,11 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
 extern int filemap_check_errors(struct address_space *mapping);
 extern void __filemap_set_wb_err(struct address_space *mapping, int err);
 
+static inline int filemap_write_and_wait(struct address_space *mapping)
+{
+	return filemap_write_and_wait_range(mapping, 0, LLONG_MAX);
+}
+
 extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
 						loff_t lend);
 extern int __must_check file_check_and_advance_wb_err(struct file *file);
@@ -3108,6 +3119,10 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags);
 ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
 		rwf_t flags);
+ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
+			   struct iov_iter *iter);
+ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
+			    struct iov_iter *iter);
 
 /* fs/block_dev.c */
 extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
@@ -3303,6 +3318,8 @@ extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
 extern int simple_rename(struct inode *, struct dentry *,
 			 struct inode *, struct dentry *, unsigned int);
+extern void simple_recursive_removal(struct dentry *,
+                              void (*callback)(struct dentry *));
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern int noop_set_page_dirty(struct page *page);
 extern void noop_invalidatepage(struct page *page, unsigned int offset,
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 6f8d772591ba..62d216ff1097 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -24,16 +24,20 @@ struct iommu_group;
  * struct host1x_client_ops - host1x client operations
  * @init: host1x client initialization code
  * @exit: host1x client tear down code
+ * @suspend: host1x client suspend code
+ * @resume: host1x client resume code
  */
 struct host1x_client_ops {
 	int (*init)(struct host1x_client *client);
 	int (*exit)(struct host1x_client *client);
+	int (*suspend)(struct host1x_client *client);
+	int (*resume)(struct host1x_client *client);
 };
 
 /**
  * struct host1x_client - host1x client structure
  * @list: list node for the host1x client
- * @parent: pointer to struct device representing the host1x controller
+ * @host: pointer to struct device representing the host1x controller
  * @dev: pointer to struct device backing this host1x client
  * @group: IOMMU group that this client is a member of
  * @ops: host1x client operations
@@ -44,7 +48,7 @@ struct host1x_client_ops {
  */
 struct host1x_client {
 	struct list_head list;
-	struct device *parent;
+	struct device *host;
 	struct device *dev;
 	struct iommu_group *group;
 
@@ -55,6 +59,10 @@ struct host1x_client {
 
 	struct host1x_syncpt **syncpts;
 	unsigned int num_syncpts;
+
+	struct host1x_client *parent;
+	unsigned int usecount;
+	struct mutex lock;
 };
 
 /*
@@ -72,8 +80,6 @@ struct host1x_bo_ops {
 	void (*unpin)(struct device *dev, struct sg_table *sgt);
 	void *(*mmap)(struct host1x_bo *bo);
 	void (*munmap)(struct host1x_bo *bo, void *addr);
-	void *(*kmap)(struct host1x_bo *bo, unsigned int pagenum);
-	void (*kunmap)(struct host1x_bo *bo, unsigned int pagenum, void *addr);
 };
 
 struct host1x_bo {
@@ -119,17 +125,6 @@ static inline void host1x_bo_munmap(struct host1x_bo *bo, void *addr)
 	bo->ops->munmap(bo, addr);
 }
 
-static inline void *host1x_bo_kmap(struct host1x_bo *bo, unsigned int pagenum)
-{
-	return bo->ops->kmap(bo, pagenum);
-}
-
-static inline void host1x_bo_kunmap(struct host1x_bo *bo,
-				    unsigned int pagenum, void *addr)
-{
-	bo->ops->kunmap(bo, pagenum, addr);
-}
-
 /*
  * host1x syncpoints
  */
@@ -322,6 +317,9 @@ int host1x_device_exit(struct host1x_device *device);
 int host1x_client_register(struct host1x_client *client);
 int host1x_client_unregister(struct host1x_client *client);
 
+int host1x_client_suspend(struct host1x_client *client);
+int host1x_client_resume(struct host1x_client *client);
+
 struct tegra_mipi_device;
 
 struct tegra_mipi_device *tegra_mipi_request(struct device *device);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 0b84e13e88e2..5aca3d1bdb32 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -160,6 +160,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp,
 
 extern void prep_transhuge_page(struct page *page);
 extern void free_transhuge_page(struct page *page);
+bool is_transparent_hugepage(struct page *page);
 
 bool can_split_huge_page(struct page *page, int *pextra_pins);
 int split_huge_page_to_list(struct page *page, struct list_head *list);
@@ -308,6 +309,11 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
 
 static inline void prep_transhuge_page(struct page *page) {}
 
+static inline bool is_transparent_hugepage(struct page *page)
+{
+	return false;
+}
+
 #define transparent_hugepage_flags 0UL
 
 #define thp_get_unmapped_area	NULL
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 26f3aeeae1ca..692c89ccf5df 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -425,6 +425,8 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_19				= 19,
 	CHANNELMSG_20				= 20,
 	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
+	CHANNELMSG_22				= 22,
+	CHANNELMSG_TL_CONNECT_RESULT		= 23,
 	CHANNELMSG_COUNT
 };
 
@@ -1433,6 +1435,8 @@ struct hv_util_service {
 	void (*util_cb)(void *);
 	int (*util_init)(struct hv_util_service *);
 	void (*util_deinit)(void);
+	int (*util_pre_suspend)(void);
+	int (*util_pre_resume)(void);
 };
 
 struct vmbuspipe_hdr {
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 46b771d6999e..a254841bd315 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -413,6 +413,8 @@ struct ide_disk_ops {
 				      sector_t);
 	int		(*ioctl)(struct ide_drive_s *, struct block_device *,
 				 fmode_t, unsigned int, unsigned long);
+	int		(*compat_ioctl)(struct ide_drive_s *, struct block_device *,
+					fmode_t, unsigned int, unsigned long);
 };
 
 /* ATAPI device flags */
@@ -943,6 +945,10 @@ ide_devset_get(_name, _field); \
 ide_devset_set(_name, _field); \
 IDE_DEVSET(_name, DS_SYNC, get_##_name, set_##_name)
 
+#define ide_devset_ro_field(_name, _field) \
+ide_devset_get(_name, _field); \
+IDE_DEVSET(_name, 0, get_##_name, NULL)
+
 #define ide_devset_rw_flag(_name, _field) \
 ide_devset_get_flag(_name, _field); \
 ide_devset_set_flag(_name, _field); \
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 6d8bf4bdf240..4a16b39ae353 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -34,10 +34,13 @@
 #define VTD_STRIDE_SHIFT        (9)
 #define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
 
-#define DMA_PTE_READ (1)
-#define DMA_PTE_WRITE (2)
-#define DMA_PTE_LARGE_PAGE (1 << 7)
-#define DMA_PTE_SNP (1 << 11)
+#define DMA_PTE_READ		BIT_ULL(0)
+#define DMA_PTE_WRITE		BIT_ULL(1)
+#define DMA_PTE_LARGE_PAGE	BIT_ULL(7)
+#define DMA_PTE_SNP		BIT_ULL(11)
+
+#define DMA_FL_PTE_PRESENT	BIT_ULL(0)
+#define DMA_FL_PTE_XD		BIT_ULL(63)
 
 #define CONTEXT_TT_MULTI_LEVEL	0
 #define CONTEXT_TT_DEV_IOTLB	1
@@ -435,8 +438,10 @@ enum {
 
 #define VTD_FLAG_TRANS_PRE_ENABLED	(1 << 0)
 #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED	(1 << 1)
+#define VTD_FLAG_SVM_CAPABLE		(1 << 2)
 
 extern int intel_iommu_sm;
+extern spinlock_t device_domain_lock;
 
 #define sm_supported(iommu)	(intel_iommu_sm && ecap_smts((iommu)->ecap))
 #define pasid_supported(iommu)	(sm_supported(iommu) &&			\
@@ -609,10 +614,11 @@ static inline void dma_clear_pte(struct dma_pte *pte)
 static inline u64 dma_pte_addr(struct dma_pte *pte)
 {
 #ifdef CONFIG_64BIT
-	return pte->val & VTD_PAGE_MASK;
+	return pte->val & VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
 #else
 	/* Must have a full atomic 64-bit read */
-	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
+	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) &
+			VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
 #endif
 }
 
@@ -645,6 +651,8 @@ extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 			  unsigned int size_order, u64 type);
 extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 			u16 qdep, u64 addr, unsigned mask);
+void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
+		     unsigned long npages, bool ih);
 extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 extern int dmar_ir_support(void);
@@ -656,9 +664,10 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info,
 				     void *data), void *data);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev);
+struct dmar_domain *find_domain(struct device *dev);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
-int intel_svm_init(struct intel_iommu *iommu);
+extern void intel_svm_check(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);
 
@@ -686,6 +695,8 @@ struct intel_svm {
 };
 
 extern struct intel_iommu *intel_svm_device_to_iommu(struct device *dev);
+#else
+static inline void intel_svm_check(struct intel_iommu *iommu) {}
 #endif
 
 #ifdef CONFIG_INTEL_IOMMU_DEBUGFS
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 6e125e9b4187..837058bc1c9f 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -28,6 +28,7 @@ struct io_mapping {
 
 #ifdef CONFIG_HAVE_ATOMIC_IOMAP
 
+#include <linux/pfn.h>
 #include <asm/iomap.h>
 /*
  * For small address space machines, mapping large objects
@@ -64,12 +65,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping,
 			 unsigned long offset)
 {
 	resource_size_t phys_addr;
-	unsigned long pfn;
 
 	BUG_ON(offset >= mapping->size);
 	phys_addr = mapping->base + offset;
-	pfn = (unsigned long) (phys_addr >> PAGE_SHIFT);
-	return iomap_atomic_prot_pfn(pfn, mapping->prot);
+	return iomap_atomic_prot_pfn(PHYS_PFN(phys_addr), mapping->prot);
 }
 
 static inline void
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index ee21eedafe98..53d53c6c2be9 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -83,12 +83,16 @@ struct io_pgtable_cfg {
 	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
 	 *	on unmap, for DMA domains using the flush queue mechanism for
 	 *	delayed invalidation.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_TTBR1: (ARM LPAE format) Configure the table
+	 *	for use in the upper half of a split address space.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
 	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_EXT	BIT(3)
 	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(4)
+	#define IO_PGTABLE_QUIRK_ARM_TTBR1	BIT(5)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
@@ -100,18 +104,33 @@ struct io_pgtable_cfg {
 	/* Low-level data specific to the table format */
 	union {
 		struct {
-			u64	ttbr[2];
-			u64	tcr;
+			u64	ttbr;
+			struct {
+				u32	ips:3;
+				u32	tg:2;
+				u32	sh:2;
+				u32	orgn:2;
+				u32	irgn:2;
+				u32	tsz:6;
+			}	tcr;
 			u64	mair;
 		} arm_lpae_s1_cfg;
 
 		struct {
 			u64	vttbr;
-			u64	vtcr;
+			struct {
+				u32	ps:3;
+				u32	tg:2;
+				u32	sh:2;
+				u32	orgn:2;
+				u32	irgn:2;
+				u32	sl:2;
+				u32	tsz:6;
+			}	vtcr;
 		} arm_lpae_s2_cfg;
 
 		struct {
-			u32	ttbr[2];
+			u32	ttbr;
 			u32	tcr;
 			u32	nmrr;
 			u32	prrr;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index f2223cbb5fd5..d1b5f4d98569 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -246,9 +246,10 @@ struct iommu_iotlb_gather {
  * @sva_get_pasid: Get PASID associated to a SVA handle
  * @page_response: handle page request response
  * @cache_invalidate: invalidate translation caches
- * @pgsize_bitmap: bitmap of all possible supported page sizes
  * @sva_bind_gpasid: bind guest pasid and mm
  * @sva_unbind_gpasid: unbind guest pasid and mm
+ * @pgsize_bitmap: bitmap of all possible supported page sizes
+ * @owner: Driver module providing these ops
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
@@ -318,6 +319,7 @@ struct iommu_ops {
 	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
 
 	unsigned long pgsize_bitmap;
+	struct module *owner;
 };
 
 /**
@@ -386,12 +388,19 @@ void iommu_device_sysfs_remove(struct iommu_device *iommu);
 int  iommu_device_link(struct iommu_device   *iommu, struct device *link);
 void iommu_device_unlink(struct iommu_device *iommu, struct device *link);
 
-static inline void iommu_device_set_ops(struct iommu_device *iommu,
-					const struct iommu_ops *ops)
+static inline void __iommu_device_set_ops(struct iommu_device *iommu,
+					  const struct iommu_ops *ops)
 {
 	iommu->ops = ops;
 }
 
+#define iommu_device_set_ops(iommu, ops)				\
+do {									\
+	struct iommu_ops *__ops = (struct iommu_ops *)(ops);		\
+	__ops->owner = THIS_MODULE;					\
+	__iommu_device_set_ops(iommu, __ops);				\
+} while (0)
+
 static inline void iommu_device_set_fwnode(struct iommu_device *iommu,
 					   struct fwnode_handle *fwnode)
 {
@@ -456,6 +465,8 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain,
 
 extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
+extern void generic_iommu_put_resv_regions(struct device *dev,
+					   struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
 extern int iommu_request_dma_domain_for_dev(struct device *dev);
 extern void iommu_set_default_passthrough(bool cmd_line);
@@ -570,6 +581,7 @@ struct iommu_group *fsl_mc_device_group(struct device *dev);
  * @ops: ops for this device's IOMMU
  * @iommu_fwnode: firmware handle for this device's IOMMU
  * @iommu_priv: IOMMU driver private data for this device
+ * @num_pasid_bits: number of PASID bits supported by this device
  * @num_ids: number of associated device IDs
  * @ids: IDs which this device may present to the IOMMU
  */
@@ -578,6 +590,7 @@ struct iommu_fwspec {
 	struct fwnode_handle	*iommu_fwnode;
 	void			*iommu_priv;
 	u32			flags;
+	u32			num_pasid_bits;
 	unsigned int		num_ids;
 	u32			ids[1];
 };
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index ce44b687d02b..f613d8529863 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1403,7 +1403,6 @@ extern int	   jbd2_journal_skip_recovery	(journal_t *);
 extern void	   jbd2_journal_update_sb_errno(journal_t *);
 extern int	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
 				unsigned long, int);
-extern void	   __jbd2_journal_abort_hard	(journal_t *);
 extern void	   jbd2_journal_abort      (journal_t *, int);
 extern int	   jbd2_journal_errno      (journal_t *);
 extern void	   jbd2_journal_ack_err    (journal_t *);
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 68bd88223417..24cd447659e0 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -183,8 +183,6 @@ int kdb_process_cpu(const struct task_struct *p)
 	return cpu;
 }
 
-/* kdb access to register set for stack dumping */
-extern struct pt_regs *kdb_current_regs;
 #ifdef CONFIG_KALLSYMS
 extern const char *kdb_walk_kallsyms(loff_t *pos);
 #else /* ! CONFIG_KALLSYMS */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 538c25e778c0..e89eb67356cb 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -157,8 +157,6 @@ static inline bool is_error_page(struct page *page)
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
-extern struct kmem_cache *kvm_vcpu_cache;
-
 extern struct mutex kvm_lock;
 extern struct list_head vm_list;
 
@@ -204,7 +202,7 @@ struct kvm_async_pf {
 	struct list_head queue;
 	struct kvm_vcpu *vcpu;
 	struct mm_struct *mm;
-	gva_t gva;
+	gpa_t cr2_or_gpa;
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
 	bool   wakeup_all;
@@ -212,8 +210,8 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
-		       struct kvm_arch_async_pf *arch);
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+		       unsigned long hva, struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
@@ -579,8 +577,7 @@ static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
 	      memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
 		memslot++)
 
-int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
-void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
+void kvm_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
@@ -723,10 +720,9 @@ void kvm_set_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_accessed(kvm_pfn_t pfn);
 void kvm_get_pfn(kvm_pfn_t pfn);
 
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
-int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
-			  unsigned long len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
 int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			   void *data, unsigned long len);
@@ -767,7 +763,7 @@ int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
@@ -775,8 +771,12 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
 kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
 kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
+int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
+		struct gfn_to_pfn_cache *cache, bool atomic);
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
+int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
+		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
 int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
@@ -867,16 +867,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 int kvm_arch_init(void *opaque);
 void kvm_arch_exit(void);
 
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
-
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
 
-void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id);
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
@@ -982,10 +978,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
 bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
 bool kvm_is_zone_device_pfn(kvm_pfn_t pfn);
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn);
 
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
@@ -1109,9 +1105,8 @@ enum kvm_stat_kind {
 };
 
 struct kvm_stat_data {
-	int offset;
-	int mode;
 	struct kvm *kvm;
+	struct kvm_stats_debugfs_item *dbgfs_item;
 };
 
 struct kvm_stats_debugfs_item {
@@ -1120,6 +1115,10 @@ struct kvm_stats_debugfs_item {
 	enum kvm_stat_kind kind;
 	int mode;
 };
+
+#define KVM_DBGFS_GET_MODE(dbgfs_item)                                         \
+	((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644)
+
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 
@@ -1342,6 +1341,9 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
 }
 #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
 
+struct kvm_vcpu *kvm_get_running_vcpu(void);
+struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+
 #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
 bool kvm_arch_has_irq_bypass(void);
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 1c88e69db3d9..68e84cf42a3f 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -18,7 +18,7 @@ struct kvm_memslots;
 
 enum kvm_mr_change;
 
-#include <asm/types.h>
+#include <linux/types.h>
 
 /*
  * Address types:
@@ -51,4 +51,11 @@ struct gfn_to_hva_cache {
 	struct kvm_memory_slot *memslot;
 };
 
+struct gfn_to_pfn_cache {
+	u64 generation;
+	gfn_t gfn;
+	kvm_pfn_t pfn;
+	bool dirty;
+};
+
 #endif /* __KVM_TYPES_H__ */
diff --git a/include/linux/leds-bd2802.h b/include/linux/leds-bd2802.h
index dd93c8d787b4..ec577f5f8707 100644
--- a/include/linux/leds-bd2802.h
+++ b/include/linux/leds-bd2802.h
@@ -11,7 +11,6 @@
 #define _LEDS_BD2802_H_
 
 struct bd2802_led_platform_data{
-	int	reset_gpio;
 	u8	rgb_time;
 };
 
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 242258f7d837..75353e5f9d13 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -20,6 +20,7 @@
 
 struct device;
 struct led_pattern;
+struct device_node;
 /*
  * LED Core
  */
@@ -196,6 +197,11 @@ void devm_led_classdev_unregister(struct device *parent,
 void led_classdev_suspend(struct led_classdev *led_cdev);
 void led_classdev_resume(struct led_classdev *led_cdev);
 
+extern struct led_classdev *of_led_get(struct device_node *np, int index);
+extern void led_put(struct led_classdev *led_cdev);
+struct led_classdev *__must_check devm_of_led_get(struct device *dev,
+						  int index);
+
 /**
  * led_blink_set - set blinking with software fallback
  * @led_cdev: the LED to start blinking
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 2dbde119721d..2ca9b7056a82 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1109,6 +1109,11 @@ extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_op
 extern int ata_scsi_detect(struct scsi_host_template *sht);
 extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd,
 			  void __user *arg);
+#ifdef CONFIG_COMPAT
+#define ATA_SCSI_COMPAT_IOCTL .compat_ioctl = ata_scsi_ioctl,
+#else
+#define ATA_SCSI_COMPAT_IOCTL /* empty */
+#endif
 extern int ata_scsi_queuecmd(struct Scsi_Host *h, struct scsi_cmnd *cmd);
 extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev,
 			    unsigned int cmd, void __user *arg);
@@ -1221,6 +1226,7 @@ struct pci_bits {
 };
 
 extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits);
+extern void ata_pci_shutdown_one(struct pci_dev *pdev);
 extern void ata_pci_remove_one(struct pci_dev *pdev);
 
 #ifdef CONFIG_PM
@@ -1341,6 +1347,7 @@ extern struct device_attribute *ata_common_sdev_attrs[];
 	.module			= THIS_MODULE,			\
 	.name			= drv_name,			\
 	.ioctl			= ata_scsi_ioctl,		\
+	ATA_SCSI_COMPAT_IOCTL					\
 	.queuecommand		= ata_scsi_queuecmd,		\
 	.can_queue		= ATA_DEF_QUEUE,		\
 	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index c50d01ef1414..664f52c6dd4c 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -627,6 +627,13 @@ do {									\
 	lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_);	\
 	lock_release(&(lock)->dep_map, _THIS_IP_);			\
 } while (0)
+# define might_lock_nested(lock, subclass) 				\
+do {									\
+	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
+	lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL,		\
+		     _THIS_IP_);					\
+	lock_release(&(lock)->dep_map, _THIS_IP_);			\
+} while (0)
 
 #define lockdep_assert_irqs_enabled()	do {				\
 		WARN_ONCE(debug_locks && !current->lockdep_recursion &&	\
@@ -649,6 +656,7 @@ do {									\
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
+# define might_lock_nested(lock, subclass) do { } while (0)
 # define lockdep_assert_irqs_enabled() do { } while (0)
 # define lockdep_assert_irqs_disabled() do { } while (0)
 # define lockdep_assert_in_irq() do { } while (0)
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index e6f54ef6698b..a4dc45fbec0a 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -20,6 +20,16 @@
 #define CMDQ_WFE_WAIT			BIT(15)
 #define CMDQ_WFE_WAIT_VALUE		0x1
 
+/*
+ * WFE arg_b
+ * bit 0-11: wait value
+ * bit 15: 1 - wait, 0 - no wait
+ * bit 16-27: update value
+ * bit 31: 1 - update, 0 - no update
+ */
+#define CMDQ_WFE_OPTION			(CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | \
+					CMDQ_WFE_WAIT_VALUE)
+
 /** cmdq event maximum */
 #define CMDQ_MAX_EVENT			0x3ff
 
@@ -45,6 +55,7 @@
 enum cmdq_code {
 	CMDQ_CODE_MASK = 0x02,
 	CMDQ_CODE_WRITE = 0x04,
+	CMDQ_CODE_POLL = 0x08,
 	CMDQ_CODE_JUMP = 0x10,
 	CMDQ_CODE_WFE = 0x20,
 	CMDQ_CODE_EOC = 0x40,
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b38bbefabfab..079d17d96410 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -113,6 +113,9 @@ int memblock_add(phys_addr_t base, phys_addr_t size);
 int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_free(phys_addr_t base, phys_addr_t size);
 int memblock_reserve(phys_addr_t base, phys_addr_t size);
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
+#endif
 void memblock_trim_memory(phys_addr_t align);
 bool memblock_overlaps_region(struct memblock_type *type,
 			      phys_addr_t base, phys_addr_t size);
@@ -127,10 +130,6 @@ void reset_node_managed_pages(pg_data_t *pgdat);
 void reset_all_zones_managed_pages(void);
 
 /* Low level functions */
-int memblock_add_range(struct memblock_type *type,
-		       phys_addr_t base, phys_addr_t size,
-		       int nid, enum memblock_flags flags);
-
 void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
 		      struct memblock_type *type_a,
 		      struct memblock_type *type_b, phys_addr_t *out_start,
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 4c75dae8dd29..0b8d791b6669 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -29,8 +29,6 @@ struct memory_block {
 	int section_count;		/* serialized by mem_sysfs_mutex */
 	int online_type;		/* for passing data to online routine */
 	int phys_device;		/* to which fru does this belong? */
-	void *hw;			/* optional pointer to fw/hw data */
-	int (*phys_callback)(struct memory_block *);
 	struct device dev;
 	int nid;			/* NID for this memory block */
 };
@@ -55,19 +53,6 @@ struct memory_notify {
 	int status_change_nid;
 };
 
-/*
- * During pageblock isolation, count the number of pages within the
- * range [start_pfn, start_pfn + nr_pages) which are owned by code
- * in the notifier chain.
- */
-#define MEM_ISOLATE_COUNT	(1<<0)
-
-struct memory_isolate_notify {
-	unsigned long start_pfn;	/* Start of range to check */
-	unsigned int nr_pages;		/* # pages in range to check */
-	unsigned int pages_found;	/* # pages owned found by callbacks */
-};
-
 struct notifier_block;
 struct mem_section;
 
@@ -94,27 +79,13 @@ static inline int memory_notify(unsigned long val, void *v)
 {
 	return 0;
 }
-static inline int register_memory_isolate_notifier(struct notifier_block *nb)
-{
-	return 0;
-}
-static inline void unregister_memory_isolate_notifier(struct notifier_block *nb)
-{
-}
-static inline int memory_isolate_notify(unsigned long val, void *v)
-{
-	return 0;
-}
 #else
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
-extern int register_memory_isolate_notifier(struct notifier_block *nb);
-extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
-extern int memory_isolate_notify(unsigned long val, void *v);
 extern struct memory_block *find_memory_block(struct mem_section *);
 typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
 extern int walk_memory_blocks(unsigned long start, unsigned long size,
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index ba0dca6aac6e..f4d59155f3d4 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -94,9 +94,10 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
 extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
-extern int online_pages(unsigned long, unsigned long, int);
-extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
-	unsigned long *valid_start, unsigned long *valid_end);
+extern int online_pages(unsigned long pfn, unsigned long nr_pages,
+			int online_type, int nid);
+extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
+					 unsigned long end_pfn);
 extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
 						unsigned long end_pfn);
 
diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h
deleted file mode 100644
index 61c2875c2a40..000000000000
--- a/include/linux/mfd/cros_ec.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * ChromeOS EC multi-function device
- *
- * Copyright (C) 2012 Google, Inc
- */
-
-#ifndef __LINUX_MFD_CROS_EC_H
-#define __LINUX_MFD_CROS_EC_H
-
-#include <linux/device.h>
-
-/**
- * struct cros_ec_dev - ChromeOS EC device entry point.
- * @class_dev: Device structure used in sysfs.
- * @ec_dev: cros_ec_device structure to talk to the physical device.
- * @dev: Pointer to the platform device.
- * @debug_info: cros_ec_debugfs structure for debugging information.
- * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC.
- * @cmd_offset: Offset to apply for each command.
- * @features: Features supported by the EC.
- */
-struct cros_ec_dev {
-	struct device class_dev;
-	struct cros_ec_device *ec_dev;
-	struct device *dev;
-	struct cros_ec_debugfs *debug_info;
-	bool has_kb_wake_angle;
-	u16 cmd_offset;
-	u32 features[2];
-};
-
-#define to_cros_ec_dev(dev)  container_of(dev, struct cros_ec_dev, class_dev)
-
-#endif /* __LINUX_MFD_CROS_EC_H */
diff --git a/include/linux/mfd/db8500-prcmu.h b/include/linux/mfd/db8500-prcmu.h
index 1fc75d2b4a38..4b63d3ecdcff 100644
--- a/include/linux/mfd/db8500-prcmu.h
+++ b/include/linux/mfd/db8500-prcmu.h
@@ -525,9 +525,6 @@ u8 db8500_prcmu_get_power_state_result(void);
 void db8500_prcmu_enable_wakeups(u32 wakeups);
 int db8500_prcmu_set_epod(u16 epod_id, u8 epod_state);
 int db8500_prcmu_request_clock(u8 clock, bool enable);
-int db8500_prcmu_set_display_clocks(void);
-int db8500_prcmu_disable_dsipll(void);
-int db8500_prcmu_enable_dsipll(void);
 void db8500_prcmu_config_abb_event_readout(u32 abb_events);
 void db8500_prcmu_get_abb_event_buffer(void __iomem **buf);
 int db8500_prcmu_config_esram0_deep_sleep(u8 state);
@@ -682,21 +679,6 @@ static inline int db8500_prcmu_request_clock(u8 clock, bool enable)
 	return 0;
 }
 
-static inline int db8500_prcmu_set_display_clocks(void)
-{
-	return 0;
-}
-
-static inline int db8500_prcmu_disable_dsipll(void)
-{
-	return 0;
-}
-
-static inline int db8500_prcmu_enable_dsipll(void)
-{
-	return 0;
-}
-
 static inline int db8500_prcmu_config_esram0_deep_sleep(u8 state)
 {
 	return 0;
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index e2571040c7e8..e6ee2ec35de9 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -321,21 +321,6 @@ static inline bool prcmu_is_ac_wake_requested(void)
 	return db8500_prcmu_is_ac_wake_requested();
 }
 
-static inline int prcmu_set_display_clocks(void)
-{
-	return db8500_prcmu_set_display_clocks();
-}
-
-static inline int prcmu_disable_dsipll(void)
-{
-	return db8500_prcmu_disable_dsipll();
-}
-
-static inline int prcmu_enable_dsipll(void)
-{
-	return db8500_prcmu_enable_dsipll();
-}
-
 static inline int prcmu_config_esram0_deep_sleep(u8 state)
 {
 	return db8500_prcmu_config_esram0_deep_sleep(state);
@@ -511,21 +496,6 @@ static inline bool prcmu_is_ac_wake_requested(void)
 	return false;
 }
 
-static inline int prcmu_set_display_clocks(void)
-{
-	return 0;
-}
-
-static inline int prcmu_disable_dsipll(void)
-{
-	return 0;
-}
-
-static inline int prcmu_enable_dsipll(void)
-{
-	return 0;
-}
-
 static inline int prcmu_config_esram0_deep_sleep(u8 state)
 {
 	return 0;
diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h
index 1013e60c5b25..a57af878fd0c 100644
--- a/include/linux/mfd/rohm-bd70528.h
+++ b/include/linux/mfd/rohm-bd70528.h
@@ -7,6 +7,7 @@
 #include <linux/bits.h>
 #include <linux/device.h>
 #include <linux/mfd/rohm-generic.h>
+#include <linux/mfd/rohm-shared.h>
 #include <linux/regmap.h>
 
 enum {
@@ -89,10 +90,6 @@ struct bd70528_data {
 #define BD70528_REG_GPIO3_OUT	0x52
 #define BD70528_REG_GPIO4_OUT	0x54
 
-/* clk control */
-
-#define BD70528_REG_CLK_OUT	0x2c
-
 /* RTC */
 
 #define BD70528_REG_RTC_COUNT_H		0x2d
@@ -309,21 +306,8 @@ enum {
 
 #define BD70528_GPIO_IN_STATE_BASE 1
 
-#define BD70528_CLK_OUT_EN_MASK 0x1
-
 /* RTC masks to mask out reserved bits */
 
-#define BD70528_MASK_RTC_SEC		0x7f
-#define BD70528_MASK_RTC_MINUTE		0x7f
-#define BD70528_MASK_RTC_HOUR_24H	0x80
-#define BD70528_MASK_RTC_HOUR_PM	0x20
-#define BD70528_MASK_RTC_HOUR		0x1f
-#define BD70528_MASK_RTC_DAY		0x3f
-#define BD70528_MASK_RTC_WEEK		0x07
-#define BD70528_MASK_RTC_MONTH		0x1f
-#define BD70528_MASK_RTC_YEAR		0xff
-#define BD70528_MASK_RTC_COUNT_L	0x7f
-
 #define BD70528_MASK_ELAPSED_TIMER_EN	0x1
 /* Mask second, min and hour fields
  * HW would support ALM irq for over 24h
@@ -332,7 +316,6 @@ enum {
  * wake-up we limit ALM to 24H and only
  * unmask sec, min and hour
  */
-#define BD70528_MASK_ALM_EN		0x7
 #define BD70528_MASK_WAKE_EN		0x1
 
 /* WDT masks */
diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h
new file mode 100644
index 000000000000..017a4c01cb31
--- /dev/null
+++ b/include/linux/mfd/rohm-bd71828.h
@@ -0,0 +1,423 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (C) 2019 ROHM Semiconductors */
+
+#ifndef __LINUX_MFD_BD71828_H__
+#define __LINUX_MFD_BD71828_H__
+
+#include <linux/mfd/rohm-generic.h>
+#include <linux/mfd/rohm-shared.h>
+
+/* Regulator IDs */
+enum {
+	BD71828_BUCK1,
+	BD71828_BUCK2,
+	BD71828_BUCK3,
+	BD71828_BUCK4,
+	BD71828_BUCK5,
+	BD71828_BUCK6,
+	BD71828_BUCK7,
+	BD71828_LDO1,
+	BD71828_LDO2,
+	BD71828_LDO3,
+	BD71828_LDO4,
+	BD71828_LDO5,
+	BD71828_LDO6,
+	BD71828_LDO_SNVS,
+	BD71828_REGULATOR_AMOUNT,
+};
+
+#define BD71828_BUCK1267_VOLTS		0xEF
+#define BD71828_BUCK3_VOLTS		0x10
+#define BD71828_BUCK4_VOLTS		0x20
+#define BD71828_BUCK5_VOLTS		0x10
+#define BD71828_LDO_VOLTS		0x32
+/* LDO6 is fixed 1.8V voltage */
+#define BD71828_LDO_6_VOLTAGE		1800000
+
+/* Registers and masks*/
+
+/* MODE control */
+#define BD71828_REG_PS_CTRL_1		0x04
+#define BD71828_REG_PS_CTRL_2		0x05
+#define BD71828_REG_PS_CTRL_3		0x06
+
+//#define BD71828_REG_SWRESET		0x06
+#define BD71828_MASK_RUN_LVL_CTRL	0x30
+
+/* Regulator control masks */
+
+#define BD71828_MASK_RAMP_DELAY		0x6
+
+#define BD71828_MASK_RUN_EN		0x08
+#define BD71828_MASK_SUSP_EN		0x04
+#define BD71828_MASK_IDLE_EN		0x02
+#define BD71828_MASK_LPSR_EN		0x01
+
+#define BD71828_MASK_RUN0_EN		0x01
+#define BD71828_MASK_RUN1_EN		0x02
+#define BD71828_MASK_RUN2_EN		0x04
+#define BD71828_MASK_RUN3_EN		0x08
+
+#define BD71828_MASK_DVS_BUCK1_CTRL	0x10
+#define BD71828_DVS_BUCK1_CTRL_I2C	0
+#define BD71828_DVS_BUCK1_USE_RUNLVL	0x10
+
+#define BD71828_MASK_DVS_BUCK2_CTRL	0x20
+#define BD71828_DVS_BUCK2_CTRL_I2C	0
+#define BD71828_DVS_BUCK2_USE_RUNLVL	0x20
+
+#define BD71828_MASK_DVS_BUCK6_CTRL	0x40
+#define BD71828_DVS_BUCK6_CTRL_I2C	0
+#define BD71828_DVS_BUCK6_USE_RUNLVL	0x40
+
+#define BD71828_MASK_DVS_BUCK7_CTRL	0x80
+#define BD71828_DVS_BUCK7_CTRL_I2C	0
+#define BD71828_DVS_BUCK7_USE_RUNLVL	0x80
+
+#define BD71828_MASK_BUCK1267_VOLT	0xff
+#define BD71828_MASK_BUCK3_VOLT		0x1f
+#define BD71828_MASK_BUCK4_VOLT		0x3f
+#define BD71828_MASK_BUCK5_VOLT		0x1f
+#define BD71828_MASK_LDO_VOLT		0x3f
+
+/* Regulator control regs */
+#define BD71828_REG_BUCK1_EN		0x08
+#define BD71828_REG_BUCK1_CTRL		0x09
+#define BD71828_REG_BUCK1_MODE		0x0a
+#define BD71828_REG_BUCK1_IDLE_VOLT	0x0b
+#define BD71828_REG_BUCK1_SUSP_VOLT	0x0c
+#define BD71828_REG_BUCK1_VOLT		0x0d
+
+#define BD71828_REG_BUCK2_EN		0x12
+#define BD71828_REG_BUCK2_CTRL		0x13
+#define BD71828_REG_BUCK2_MODE		0x14
+#define BD71828_REG_BUCK2_IDLE_VOLT	0x15
+#define BD71828_REG_BUCK2_SUSP_VOLT	0x16
+#define BD71828_REG_BUCK2_VOLT		0x17
+
+#define BD71828_REG_BUCK3_EN		0x1c
+#define BD71828_REG_BUCK3_MODE		0x1d
+#define BD71828_REG_BUCK3_VOLT		0x1e
+
+#define BD71828_REG_BUCK4_EN		0x1f
+#define BD71828_REG_BUCK4_MODE		0x20
+#define BD71828_REG_BUCK4_VOLT		0x21
+
+#define BD71828_REG_BUCK5_EN		0x22
+#define BD71828_REG_BUCK5_MODE		0x23
+#define BD71828_REG_BUCK5_VOLT		0x24
+
+#define BD71828_REG_BUCK6_EN		0x25
+#define BD71828_REG_BUCK6_CTRL		0x26
+#define BD71828_REG_BUCK6_MODE		0x27
+#define BD71828_REG_BUCK6_IDLE_VOLT	0x28
+#define BD71828_REG_BUCK6_SUSP_VOLT	0x29
+#define BD71828_REG_BUCK6_VOLT		0x2a
+
+#define BD71828_REG_BUCK7_EN		0x2f
+#define BD71828_REG_BUCK7_CTRL		0x30
+#define BD71828_REG_BUCK7_MODE		0x31
+#define BD71828_REG_BUCK7_IDLE_VOLT	0x32
+#define BD71828_REG_BUCK7_SUSP_VOLT	0x33
+#define BD71828_REG_BUCK7_VOLT		0x34
+
+#define BD71828_REG_LDO1_EN		0x39
+#define BD71828_REG_LDO1_VOLT		0x3a
+#define BD71828_REG_LDO2_EN		0x3b
+#define BD71828_REG_LDO2_VOLT		0x3c
+#define BD71828_REG_LDO3_EN		0x3d
+#define BD71828_REG_LDO3_VOLT		0x3e
+#define BD71828_REG_LDO4_EN		0x3f
+#define BD71828_REG_LDO4_VOLT		0x40
+#define BD71828_REG_LDO5_EN		0x41
+#define BD71828_REG_LDO5_VOLT		0x43
+#define BD71828_REG_LDO5_VOLT_OPT	0x42
+#define BD71828_REG_LDO6_EN		0x44
+//#define BD71828_REG_LDO6_VOLT		0x4
+#define BD71828_REG_LDO7_EN		0x45
+#define BD71828_REG_LDO7_VOLT		0x46
+
+/* GPIO */
+
+#define BD71828_GPIO_DRIVE_MASK		0x2
+#define BD71828_GPIO_OPEN_DRAIN		0x0
+#define BD71828_GPIO_PUSH_PULL		0x2
+#define BD71828_GPIO_OUT_HI		0x1
+#define BD71828_GPIO_OUT_LO		0x0
+#define BD71828_GPIO_OUT_MASK		0x1
+
+#define BD71828_REG_GPIO_CTRL1		0x47
+#define BD71828_REG_GPIO_CTRL2		0x48
+#define BD71828_REG_GPIO_CTRL3		0x49
+#define BD71828_REG_IO_STAT		0xed
+
+/* RTC */
+#define BD71828_REG_RTC_SEC		0x4c
+#define BD71828_REG_RTC_MINUTE		0x4d
+#define BD71828_REG_RTC_HOUR		0x4e
+#define BD71828_REG_RTC_WEEK		0x4f
+#define BD71828_REG_RTC_DAY		0x50
+#define BD71828_REG_RTC_MONTH		0x51
+#define BD71828_REG_RTC_YEAR		0x52
+
+#define BD71828_REG_RTC_ALM0_SEC	0x53
+#define BD71828_REG_RTC_ALM_START	BD71828_REG_RTC_ALM0_SEC
+#define BD71828_REG_RTC_ALM0_MINUTE	0x54
+#define BD71828_REG_RTC_ALM0_HOUR	0x55
+#define BD71828_REG_RTC_ALM0_WEEK	0x56
+#define BD71828_REG_RTC_ALM0_DAY	0x57
+#define BD71828_REG_RTC_ALM0_MONTH	0x58
+#define BD71828_REG_RTC_ALM0_YEAR	0x59
+#define BD71828_REG_RTC_ALM0_MASK	0x61
+
+#define BD71828_REG_RTC_ALM1_SEC	0x5a
+#define BD71828_REG_RTC_ALM1_MINUTE	0x5b
+#define BD71828_REG_RTC_ALM1_HOUR	0x5c
+#define BD71828_REG_RTC_ALM1_WEEK	0x5d
+#define BD71828_REG_RTC_ALM1_DAY	0x5e
+#define BD71828_REG_RTC_ALM1_MONTH	0x5f
+#define BD71828_REG_RTC_ALM1_YEAR	0x60
+#define BD71828_REG_RTC_ALM1_MASK	0x62
+
+#define BD71828_REG_RTC_ALM2		0x63
+#define BD71828_REG_RTC_START		BD71828_REG_RTC_SEC
+
+/* Charger/Battey */
+#define BD71828_REG_CHG_STATE		0x65
+#define BD71828_REG_CHG_FULL		0xd2
+
+/* LEDs */
+#define BD71828_REG_LED_CTRL		0x4A
+#define BD71828_MASK_LED_AMBER		0x80
+#define BD71828_MASK_LED_GREEN		0x40
+#define BD71828_LED_ON			0xff
+#define BD71828_LED_OFF			0x0
+
+/* IRQ registers */
+#define BD71828_REG_INT_MASK_BUCK	0xd3
+#define BD71828_REG_INT_MASK_DCIN1	0xd4
+#define BD71828_REG_INT_MASK_DCIN2	0xd5
+#define BD71828_REG_INT_MASK_VSYS	0xd6
+#define BD71828_REG_INT_MASK_CHG	0xd7
+#define BD71828_REG_INT_MASK_BAT	0xd8
+#define BD71828_REG_INT_MASK_BAT_MON1	0xd9
+#define BD71828_REG_INT_MASK_BAT_MON2	0xda
+#define BD71828_REG_INT_MASK_BAT_MON3	0xdb
+#define BD71828_REG_INT_MASK_BAT_MON4	0xdc
+#define BD71828_REG_INT_MASK_TEMP	0xdd
+#define BD71828_REG_INT_MASK_RTC	0xde
+
+#define BD71828_REG_INT_MAIN		0xdf
+#define BD71828_REG_INT_BUCK		0xe0
+#define BD71828_REG_INT_DCIN1		0xe1
+#define BD71828_REG_INT_DCIN2		0xe2
+#define BD71828_REG_INT_VSYS		0xe3
+#define BD71828_REG_INT_CHG		0xe4
+#define BD71828_REG_INT_BAT		0xe5
+#define BD71828_REG_INT_BAT_MON1	0xe6
+#define BD71828_REG_INT_BAT_MON2	0xe7
+#define BD71828_REG_INT_BAT_MON3	0xe8
+#define BD71828_REG_INT_BAT_MON4	0xe9
+#define BD71828_REG_INT_TEMP		0xea
+#define BD71828_REG_INT_RTC		0xeb
+#define BD71828_REG_INT_UPDATE		0xec
+
+#define BD71828_MAX_REGISTER BD71828_REG_IO_STAT
+
+/* Masks for main IRQ register bits */
+enum {
+	BD71828_INT_BUCK,
+#define BD71828_INT_BUCK_MASK BIT(BD71828_INT_BUCK)
+	BD71828_INT_DCIN,
+#define BD71828_INT_DCIN_MASK BIT(BD71828_INT_DCIN)
+	BD71828_INT_VSYS,
+#define BD71828_INT_VSYS_MASK BIT(BD71828_INT_VSYS)
+	BD71828_INT_CHG,
+#define BD71828_INT_CHG_MASK BIT(BD71828_INT_CHG)
+	BD71828_INT_BAT,
+#define BD71828_INT_BAT_MASK BIT(BD71828_INT_BAT)
+	BD71828_INT_BAT_MON,
+#define BD71828_INT_BAT_MON_MASK BIT(BD71828_INT_BAT_MON)
+	BD71828_INT_TEMP,
+#define BD71828_INT_TEMP_MASK BIT(BD71828_INT_TEMP)
+	BD71828_INT_RTC,
+#define BD71828_INT_RTC_MASK BIT(BD71828_INT_RTC)
+};
+
+/* Interrupts */
+enum {
+	/* BUCK reg interrupts */
+	BD71828_INT_BUCK1_OCP,
+	BD71828_INT_BUCK2_OCP,
+	BD71828_INT_BUCK3_OCP,
+	BD71828_INT_BUCK4_OCP,
+	BD71828_INT_BUCK5_OCP,
+	BD71828_INT_BUCK6_OCP,
+	BD71828_INT_BUCK7_OCP,
+	BD71828_INT_PGFAULT,
+	/* DCIN1 interrupts */
+	BD71828_INT_DCIN_DET,
+	BD71828_INT_DCIN_RMV,
+	BD71828_INT_CLPS_OUT,
+	BD71828_INT_CLPS_IN,
+	/* DCIN2 interrupts */
+	BD71828_INT_DCIN_MON_RES,
+	BD71828_INT_DCIN_MON_DET,
+	BD71828_INT_LONGPUSH,
+	BD71828_INT_MIDPUSH,
+	BD71828_INT_SHORTPUSH,
+	BD71828_INT_PUSH,
+	BD71828_INT_WDOG,
+	BD71828_INT_SWRESET,
+	/* Vsys */
+	BD71828_INT_VSYS_UV_RES,
+	BD71828_INT_VSYS_UV_DET,
+	BD71828_INT_VSYS_LOW_RES,
+	BD71828_INT_VSYS_LOW_DET,
+	BD71828_INT_VSYS_HALL_IN,
+	BD71828_INT_VSYS_HALL_TOGGLE,
+	BD71828_INT_VSYS_MON_RES,
+	BD71828_INT_VSYS_MON_DET,
+	/* Charger */
+	BD71828_INT_CHG_DCIN_ILIM,
+	BD71828_INT_CHG_TOPOFF_TO_DONE,
+	BD71828_INT_CHG_WDG_TEMP,
+	BD71828_INT_CHG_WDG_TIME,
+	BD71828_INT_CHG_RECHARGE_RES,
+	BD71828_INT_CHG_RECHARGE_DET,
+	BD71828_INT_CHG_RANGED_TEMP_TRANSITION,
+	BD71828_INT_CHG_STATE_TRANSITION,
+	/* Battery */
+	BD71828_INT_BAT_TEMP_NORMAL,
+	BD71828_INT_BAT_TEMP_ERANGE,
+	BD71828_INT_BAT_TEMP_WARN,
+	BD71828_INT_BAT_REMOVED,
+	BD71828_INT_BAT_DETECTED,
+	BD71828_INT_THERM_REMOVED,
+	BD71828_INT_THERM_DETECTED,
+	/* Battery Mon 1 */
+	BD71828_INT_BAT_DEAD,
+	BD71828_INT_BAT_SHORTC_RES,
+	BD71828_INT_BAT_SHORTC_DET,
+	BD71828_INT_BAT_LOW_VOLT_RES,
+	BD71828_INT_BAT_LOW_VOLT_DET,
+	BD71828_INT_BAT_OVER_VOLT_RES,
+	BD71828_INT_BAT_OVER_VOLT_DET,
+	/* Battery Mon 2 */
+	BD71828_INT_BAT_MON_RES,
+	BD71828_INT_BAT_MON_DET,
+	/* Battery Mon 3 (Coulomb counter) */
+	BD71828_INT_BAT_CC_MON1,
+	BD71828_INT_BAT_CC_MON2,
+	BD71828_INT_BAT_CC_MON3,
+	/* Battery Mon 4 */
+	BD71828_INT_BAT_OVER_CURR_1_RES,
+	BD71828_INT_BAT_OVER_CURR_1_DET,
+	BD71828_INT_BAT_OVER_CURR_2_RES,
+	BD71828_INT_BAT_OVER_CURR_2_DET,
+	BD71828_INT_BAT_OVER_CURR_3_RES,
+	BD71828_INT_BAT_OVER_CURR_3_DET,
+	/* Temperature */
+	BD71828_INT_TEMP_BAT_LOW_RES,
+	BD71828_INT_TEMP_BAT_LOW_DET,
+	BD71828_INT_TEMP_BAT_HI_RES,
+	BD71828_INT_TEMP_BAT_HI_DET,
+	BD71828_INT_TEMP_CHIP_OVER_125_RES,
+	BD71828_INT_TEMP_CHIP_OVER_125_DET,
+	BD71828_INT_TEMP_CHIP_OVER_VF_DET,
+	BD71828_INT_TEMP_CHIP_OVER_VF_RES,
+	/* RTC Alarm */
+	BD71828_INT_RTC0,
+	BD71828_INT_RTC1,
+	BD71828_INT_RTC2,
+};
+
+#define BD71828_INT_BUCK1_OCP_MASK			0x1
+#define BD71828_INT_BUCK2_OCP_MASK			0x2
+#define BD71828_INT_BUCK3_OCP_MASK			0x4
+#define BD71828_INT_BUCK4_OCP_MASK			0x8
+#define BD71828_INT_BUCK5_OCP_MASK			0x10
+#define BD71828_INT_BUCK6_OCP_MASK			0x20
+#define BD71828_INT_BUCK7_OCP_MASK			0x40
+#define BD71828_INT_PGFAULT_MASK			0x80
+
+#define BD71828_INT_DCIN_DET_MASK			0x1
+#define BD71828_INT_DCIN_RMV_MASK			0x2
+#define BD71828_INT_CLPS_OUT_MASK			0x4
+#define BD71828_INT_CLPS_IN_MASK			0x8
+	/* DCIN2 interrupts */
+#define BD71828_INT_DCIN_MON_RES_MASK			0x1
+#define BD71828_INT_DCIN_MON_DET_MASK			0x2
+#define BD71828_INT_LONGPUSH_MASK			0x4
+#define BD71828_INT_MIDPUSH_MASK			0x8
+#define BD71828_INT_SHORTPUSH_MASK			0x10
+#define BD71828_INT_PUSH_MASK				0x20
+#define BD71828_INT_WDOG_MASK				0x40
+#define BD71828_INT_SWRESET_MASK			0x80
+	/* Vsys */
+#define BD71828_INT_VSYS_UV_RES_MASK			0x1
+#define BD71828_INT_VSYS_UV_DET_MASK			0x2
+#define BD71828_INT_VSYS_LOW_RES_MASK			0x4
+#define BD71828_INT_VSYS_LOW_DET_MASK			0x8
+#define BD71828_INT_VSYS_HALL_IN_MASK			0x10
+#define BD71828_INT_VSYS_HALL_TOGGLE_MASK		0x20
+#define BD71828_INT_VSYS_MON_RES_MASK			0x40
+#define BD71828_INT_VSYS_MON_DET_MASK			0x80
+	/* Charger */
+#define BD71828_INT_CHG_DCIN_ILIM_MASK			0x1
+#define BD71828_INT_CHG_TOPOFF_TO_DONE_MASK		0x2
+#define BD71828_INT_CHG_WDG_TEMP_MASK			0x4
+#define BD71828_INT_CHG_WDG_TIME_MASK			0x8
+#define BD71828_INT_CHG_RECHARGE_RES_MASK		0x10
+#define BD71828_INT_CHG_RECHARGE_DET_MASK		0x20
+#define BD71828_INT_CHG_RANGED_TEMP_TRANSITION_MASK	0x40
+#define BD71828_INT_CHG_STATE_TRANSITION_MASK		0x80
+	/* Battery */
+#define BD71828_INT_BAT_TEMP_NORMAL_MASK		0x1
+#define BD71828_INT_BAT_TEMP_ERANGE_MASK		0x2
+#define BD71828_INT_BAT_TEMP_WARN_MASK			0x4
+#define BD71828_INT_BAT_REMOVED_MASK			0x10
+#define BD71828_INT_BAT_DETECTED_MASK			0x20
+#define BD71828_INT_THERM_REMOVED_MASK			0x40
+#define BD71828_INT_THERM_DETECTED_MASK			0x80
+	/* Battery Mon 1 */
+#define BD71828_INT_BAT_DEAD_MASK			0x2
+#define BD71828_INT_BAT_SHORTC_RES_MASK			0x4
+#define BD71828_INT_BAT_SHORTC_DET_MASK			0x8
+#define BD71828_INT_BAT_LOW_VOLT_RES_MASK		0x10
+#define BD71828_INT_BAT_LOW_VOLT_DET_MASK		0x20
+#define BD71828_INT_BAT_OVER_VOLT_RES_MASK		0x40
+#define BD71828_INT_BAT_OVER_VOLT_DET_MASK		0x80
+	/* Battery Mon 2 */
+#define BD71828_INT_BAT_MON_RES_MASK			0x1
+#define BD71828_INT_BAT_MON_DET_MASK			0x2
+	/* Battery Mon 3 (Coulomb counter) */
+#define BD71828_INT_BAT_CC_MON1_MASK			0x1
+#define BD71828_INT_BAT_CC_MON2_MASK			0x2
+#define BD71828_INT_BAT_CC_MON3_MASK			0x4
+	/* Battery Mon 4 */
+#define BD71828_INT_BAT_OVER_CURR_1_RES_MASK		0x1
+#define BD71828_INT_BAT_OVER_CURR_1_DET_MASK		0x2
+#define BD71828_INT_BAT_OVER_CURR_2_RES_MASK		0x4
+#define BD71828_INT_BAT_OVER_CURR_2_DET_MASK		0x8
+#define BD71828_INT_BAT_OVER_CURR_3_RES_MASK		0x10
+#define BD71828_INT_BAT_OVER_CURR_3_DET_MASK		0x20
+	/* Temperature */
+#define BD71828_INT_TEMP_BAT_LOW_RES_MASK		0x1
+#define BD71828_INT_TEMP_BAT_LOW_DET_MASK		0x2
+#define BD71828_INT_TEMP_BAT_HI_RES_MASK		0x4
+#define BD71828_INT_TEMP_BAT_HI_DET_MASK		0x8
+#define BD71828_INT_TEMP_CHIP_OVER_125_RES_MASK		0x10
+#define BD71828_INT_TEMP_CHIP_OVER_125_DET_MASK		0x20
+#define BD71828_INT_TEMP_CHIP_OVER_VF_RES_MASK		0x40
+#define BD71828_INT_TEMP_CHIP_OVER_VF_DET_MASK		0x80
+	/* RTC Alarm */
+#define BD71828_INT_RTC0_MASK				0x1
+#define BD71828_INT_RTC1_MASK				0x2
+#define BD71828_INT_RTC2_MASK				0x4
+
+#define BD71828_OUT_TYPE_MASK				0x2
+#define BD71828_OUT_TYPE_OPEN_DRAIN			0x0
+#define BD71828_OUT_TYPE_CMOS				0x2
+
+#endif /* __LINUX_MFD_BD71828_H__ */
diff --git a/include/linux/mfd/rohm-bd718x7.h b/include/linux/mfd/rohm-bd718x7.h
index 7f2dbde402a1..bee2474a8f9f 100644
--- a/include/linux/mfd/rohm-bd718x7.h
+++ b/include/linux/mfd/rohm-bd718x7.h
@@ -191,12 +191,6 @@ enum {
 #define IRQ_ON_REQ		0x02
 #define IRQ_STBY_REQ		0x01
 
-/* BD718XX_REG_OUT32K bits */
-#define BD718XX_OUT32K_EN	0x01
-
-/* BD7183XX gated clock rate */
-#define BD718XX_CLK_RATE 32768
-
 /* ROHM BD718XX irqs */
 enum {
 	BD718XX_INT_STBY_REQ,
diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h
index bff15ac26f2c..4283b5b33e04 100644
--- a/include/linux/mfd/rohm-generic.h
+++ b/include/linux/mfd/rohm-generic.h
@@ -4,17 +4,83 @@
 #ifndef __LINUX_MFD_ROHM_H__
 #define __LINUX_MFD_ROHM_H__
 
-enum {
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+
+enum rohm_chip_type {
 	ROHM_CHIP_TYPE_BD71837 = 0,
 	ROHM_CHIP_TYPE_BD71847,
 	ROHM_CHIP_TYPE_BD70528,
+	ROHM_CHIP_TYPE_BD71828,
 	ROHM_CHIP_TYPE_AMOUNT
 };
 
 struct rohm_regmap_dev {
-	unsigned int chip_type;
 	struct device *dev;
 	struct regmap *regmap;
 };
 
+enum {
+	ROHM_DVS_LEVEL_UNKNOWN,
+	ROHM_DVS_LEVEL_RUN,
+	ROHM_DVS_LEVEL_IDLE,
+	ROHM_DVS_LEVEL_SUSPEND,
+	ROHM_DVS_LEVEL_LPSR,
+	ROHM_DVS_LEVEL_MAX = ROHM_DVS_LEVEL_LPSR,
+};
+
+/**
+ * struct rohm_dvs_config - dynamic voltage scaling register descriptions
+ *
+ * @level_map:		bitmap representing supported run-levels for this
+ *			regulator
+ * @run_reg:		register address for regulator config at 'run' state
+ * @run_mask:		value mask for regulator voltages at 'run' state
+ * @run_on_mask:	enable mask for regulator at 'run' state
+ * @idle_reg:		register address for regulator config at 'idle' state
+ * @idle_mask:		value mask for regulator voltages at 'idle' state
+ * @idle_on_mask:	enable mask for regulator at 'idle' state
+ * @suspend_reg:	register address for regulator config at 'suspend' state
+ * @suspend_mask:	value mask for regulator voltages at 'suspend' state
+ * @suspend_on_mask:	enable mask for regulator at 'suspend' state
+ * @lpsr_reg:		register address for regulator config at 'lpsr' state
+ * @lpsr_mask:		value mask for regulator voltages at 'lpsr' state
+ * @lpsr_on_mask:	enable mask for regulator at 'lpsr' state
+ *
+ * Description of ROHM PMICs voltage configuration registers for different
+ * system states. This is used to correctly configure the PMIC at startup
+ * based on values read from DT.
+ */
+struct rohm_dvs_config {
+	uint64_t level_map;
+	unsigned int run_reg;
+	unsigned int run_mask;
+	unsigned int run_on_mask;
+	unsigned int idle_reg;
+	unsigned int idle_mask;
+	unsigned int idle_on_mask;
+	unsigned int suspend_reg;
+	unsigned int suspend_mask;
+	unsigned int suspend_on_mask;
+	unsigned int lpsr_reg;
+	unsigned int lpsr_mask;
+	unsigned int lpsr_on_mask;
+};
+
+#if IS_ENABLED(CONFIG_REGULATOR_ROHM)
+int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs,
+				  struct device_node *np,
+				  const struct regulator_desc *desc,
+				  struct regmap *regmap);
+
+#else
+static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs,
+						struct device_node *np,
+						const struct regulator_desc *desc,
+						struct regmap *regmap)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/include/linux/mfd/rohm-shared.h b/include/linux/mfd/rohm-shared.h
new file mode 100644
index 000000000000..53dd7f638bfd
--- /dev/null
+++ b/include/linux/mfd/rohm-shared.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (C) 2020 ROHM Semiconductors */
+
+
+#ifndef __LINUX_MFD_ROHM_SHARED_H__
+#define __LINUX_MFD_ROHM_SHARED_H__
+
+/* RTC definitions shared between BD70528 and BD71828 */
+
+#define BD70528_MASK_RTC_SEC		0x7f
+#define BD70528_MASK_RTC_MINUTE		0x7f
+#define BD70528_MASK_RTC_HOUR_24H	0x80
+#define BD70528_MASK_RTC_HOUR_PM	0x20
+#define BD70528_MASK_RTC_HOUR		0x3f
+#define BD70528_MASK_RTC_DAY		0x3f
+#define BD70528_MASK_RTC_WEEK		0x07
+#define BD70528_MASK_RTC_MONTH		0x1f
+#define BD70528_MASK_RTC_YEAR		0xff
+#define BD70528_MASK_ALM_EN		0x7
+
+#endif /* __LINUX_MFD_ROHM_SHARED_H__ */
diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h
index 112dc66262cc..7f20e9b502a5 100644
--- a/include/linux/mfd/syscon.h
+++ b/include/linux/mfd/syscon.h
@@ -23,6 +23,11 @@ extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s);
 extern struct regmap *syscon_regmap_lookup_by_phandle(
 					struct device_node *np,
 					const char *property);
+extern struct regmap *syscon_regmap_lookup_by_phandle_args(
+					struct device_node *np,
+					const char *property,
+					int arg_count,
+					unsigned int *out_args);
 #else
 static inline struct regmap *device_node_to_regmap(struct device_node *np)
 {
@@ -45,6 +50,15 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle(
 {
 	return ERR_PTR(-ENOTSUPP);
 }
+
+static inline struct regmap *syscon_regmap_lookup_by_phandle_args(
+					struct device_node *np,
+					const char *property,
+					int arg_count,
+					unsigned int *out_args)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
 #endif
 
 #endif /* __LINUX_MFD_SYSCON_H__ */
diff --git a/include/linux/mfd/wcd934x/registers.h b/include/linux/mfd/wcd934x/registers.h
new file mode 100644
index 000000000000..bb8d2e276668
--- /dev/null
+++ b/include/linux/mfd/wcd934x/registers.h
@@ -0,0 +1,531 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _WCD934X_REGISTERS_H
+#define _WCD934X_REGISTERS_H
+
+#define WCD934X_CODEC_RPM_CLK_GATE				0x0002
+#define WCD934X_CODEC_RPM_CLK_GATE_MASK				GENMASK(1, 0)
+#define WCD934X_CODEC_RPM_CLK_MCLK_CFG				0x0003
+#define WCD934X_CODEC_RPM_CLK_MCLK_CFG_9P6MHZ			BIT(0)
+#define WCD934X_CODEC_RPM_CLK_MCLK_CFG_12P288MHZ		BIT(1)
+#define WCD934X_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK		GENMASK(1, 0)
+#define WCD934X_CODEC_RPM_RST_CTL				0x0009
+#define WCD934X_CODEC_RPM_PWR_CDC_DIG_HM_CTL			0x0011
+#define WCD934X_CHIP_TIER_CTRL_CHIP_ID_BYTE0			0x0021
+#define WCD934X_CHIP_TIER_CTRL_CHIP_ID_BYTE2			0x0023
+#define WCD934X_CHIP_TIER_CTRL_EFUSE_CTL			0x0025
+#define WCD934X_EFUSE_SENSE_STATE_MASK				GENMASK(4, 1)
+#define WCD934X_EFUSE_SENSE_STATE_DEF				0x10
+#define WCD934X_EFUSE_SENSE_EN_MASK				BIT(0)
+#define WCD934X_EFUSE_SENSE_ENABLE				BIT(0)
+#define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT14			0x0037
+#define WCD934X_CHIP_TIER_CTRL_EFUSE_VAL_OUT15			0x0038
+#define WCD934X_CHIP_TIER_CTRL_EFUSE_STATUS			0x0039
+#define WCD934X_DATA_HUB_SB_TX10_INP_CFG			0x006b
+#define WCD934X_DATA_HUB_SB_TX11_INP_CFG			0x006c
+#define WCD934X_DATA_HUB_SB_TX13_INP_CFG			0x006e
+#define WCD934X_CPE_FLL_CONFIG_CTL_2				0x0111
+#define WCD934X_CPE_SS_CPARMAD_BUFRDY_INT_PERIOD		0x0213
+#define WCD934X_CPE_SS_SVA_CFG					0x0214
+#define WCD934X_CPE_SS_DMIC0_CTL				0x0218
+#define WCD934X_CPE_SS_DMIC1_CTL				0x0219
+#define WCD934X_DMIC_RATE_MASK					GENMASK(3, 1)
+#define WCD934X_CPE_SS_DMIC2_CTL				0x021a
+#define WCD934X_CPE_SS_DMIC_CFG					0x021b
+#define WCD934X_CPE_SS_DMIC_CFG					0x021b
+#define WCD934X_CPE_SS_CPAR_CFG					0x021c
+#define WCD934X_INTR_PIN1_MASK0					0x0409
+#define WCD934X_INTR_PIN1_STATUS0				0x0411
+#define WCD934X_INTR_PIN1_CLEAR0				0x0419
+#define WCD934X_INTR_PIN2_CLEAR3				0x0434
+#define WCD934X_INTR_LEVEL0					0x0461
+/* INTR_REG 0 */
+#define	WCD934X_IRQ_SLIMBUS			0
+#define	WCD934X_IRQ_MISC			1
+#define	WCD934X_IRQ_HPH_PA_OCPL_FAULT		2
+#define	WCD934X_IRQ_HPH_PA_OCPR_FAULT		3
+#define	WCD934X_IRQ_EAR_PA_OCP_FAULT		4
+#define	WCD934X_IRQ_HPH_PA_CNPL_COMPLETE	5
+#define	WCD934X_IRQ_HPH_PA_CNPR_COMPLETE	6
+#define	WCD934X_IRQ_EAR_PA_CNP_COMPLETE		7
+/* INTR_REG 1 */
+#define	WCD934X_IRQ_MBHC_SW_DET			8
+#define	WCD934X_IRQ_MBHC_ELECT_INS_REM_DET	9
+#define	WCD934X_IRQ_MBHC_BUTTON_PRESS_DET	10
+#define	WCD934X_IRQ_MBHC_BUTTON_RELEASE_DET	11
+#define	WCD934X_IRQ_MBHC_ELECT_INS_REM_LEG_DET	12
+#define	WCD934X_IRQ_RESERVED_0			13
+#define	WCD934X_IRQ_RESERVED_1			14
+#define	WCD934X_IRQ_RESERVED_2			15
+/* INTR_REG 2 */
+#define	WCD934X_IRQ_LINE_PA1_CNP_COMPLETE	16
+#define	WCD934X_IRQ_LINE_PA2_CNP_COMPLETE	17
+#define	WCD934X_IRQ_SLNQ_ANALOG_ERROR		18
+#define	WCD934X_IRQ_RESERVED_3			19
+#define	WCD934X_IRQ_SOUNDWIRE			20
+#define	WCD934X_IRQ_VDD_DIG_RAMP_COMPLETE	21
+#define	WCD934X_IRQ_RCO_ERROR			22
+#define	WCD934X_IRQ_CPE_ERROR			23
+/* INTR_REG 3 */
+#define	WCD934X_IRQ_MAD_AUDIO			24
+#define	WCD934X_IRQ_MAD_BEACON			25
+#define	WCD934X_IRQ_MAD_ULTRASOUND		26
+#define	WCD934X_IRQ_VBAT_ATTACK			27
+#define	WCD934X_IRQ_VBAT_RESTORE		28
+#define	WCD934X_IRQ_CPE1_INTR			29
+#define	WCD934X_IRQ_RESERVED_4			30
+#define	WCD934X_IRQ_SLNQ_DIGITAL		31
+#define WCD934X_NUM_IRQS			32
+#define WCD934X_ANA_BIAS					0x0601
+#define WCD934X_ANA_BIAS_EN_MASK				BIT(7)
+#define WCD934X_ANA_BIAS_EN					BIT(7)
+#define WCD934X_ANA_PRECHRG_EN_MASK				BIT(6)
+#define WCD934X_ANA_PRECHRG_EN					BIT(6)
+#define WCD934X_ANA_PRECHRG_MODE_MASK				BIT(5)
+#define WCD934X_ANA_PRECHRG_MODE_AUTO				BIT(5)
+#define WCD934X_ANA_RCO						0x0603
+#define WCD934X_ANA_RCO_BG_EN_MASK				BIT(7)
+#define WCD934X_ANA_RCO_BG_ENABLE				BIT(7)
+#define WCD934X_ANA_BUCK_CTL					0x0606
+#define WCD934X_ANA_BUCK_HI_ACCU_PRE_ENX_MASK			GENMASK(1, 0)
+#define WCD934X_ANA_BUCK_PRE_EN2_MASK				BIT(0)
+#define WCD934X_ANA_BUCK_PRE_EN2_ENABLE				BIT(0)
+#define WCD934X_ANA_BUCK_PRE_EN1_MASK				BIT(1)
+#define WCD934X_ANA_BUCK_PRE_EN1_ENABLE				BIT(1)
+#define WCD934X_ANA_BUCK_HI_ACCU_EN_MASK			BIT(2)
+#define WCD934X_ANA_BUCK_HI_ACCU_ENABLE				BIT(2)
+#define WCD934X_ANA_RX_SUPPLIES					0x0608
+#define WCD934X_ANA_HPH						0x0609
+#define WCD934X_ANA_EAR						0x060a
+#define WCD934X_ANA_LO_1_2					0x060b
+#define WCD934X_ANA_AMIC1					0x060e
+#define WCD934X_ANA_AMIC2					0x060f
+#define WCD934X_ANA_AMIC3					0x0610
+#define WCD934X_ANA_AMIC4					0x0611
+#define WCD934X_ANA_MBHC_MECH					0x0614
+#define WCD934X_ANA_MBHC_ELECT					0x0615
+#define WCD934X_ANA_MBHC_ZDET					0x0616
+#define WCD934X_ANA_MBHC_RESULT_1				0x0617
+#define WCD934X_ANA_MBHC_RESULT_2				0x0618
+#define WCD934X_ANA_MBHC_RESULT_3				0x0619
+#define WCD934X_ANA_MICB1					0x0622
+#define WCD934X_MICB_VAL_MASK					GENMASK(5, 0)
+#define WCD934X_ANA_MICB_EN_MASK				GENMASK(7, 6)
+#define WCD934X_ANA_MICB_PULL_UP				0x80
+#define WCD934X_ANA_MICB_ENABLE					0x40
+#define WCD934X_ANA_MICB_DISABLE				0x0
+#define WCD934X_ANA_MICB2					0x0623
+#define WCD934X_ANA_MICB3					0x0625
+#define WCD934X_ANA_MICB4					0x0626
+#define WCD934X_BIAS_VBG_FINE_ADJ				0x0629
+#define WCD934X_MICB1_TEST_CTL_1				0x066b
+#define WCD934X_MICB1_TEST_CTL_2				0x066c
+#define WCD934X_MICB2_TEST_CTL_1				0x066e
+#define WCD934X_MICB3_TEST_CTL_1				0x0671
+#define WCD934X_MICB4_TEST_CTL_1				0x0674
+#define WCD934X_CLASSH_MODE_1					0x0697
+#define WCD934X_CLASSH_MODE_2					0x0698
+#define WCD934X_CLASSH_MODE_3					0x0699
+#define WCD934X_CLASSH_CTRL_VCL_1				0x069a
+#define WCD934X_CLASSH_CTRL_VCL_2				0x069b
+#define WCD934X_CLASSH_CTRL_CCL_1				0x069c
+#define WCD934X_CLASSH_CTRL_CCL_2				0x069d
+#define WCD934X_CLASSH_CTRL_CCL_3				0x069e
+#define WCD934X_CLASSH_CTRL_CCL_4				0x069f
+#define WCD934X_CLASSH_CTRL_CCL_5				0x06a0
+#define WCD934X_CLASSH_BUCK_TMUX_A_D				0x06a1
+#define WCD934X_CLASSH_BUCK_SW_DRV_CNTL				0x06a2
+#define WCD934X_RX_OCP_CTL					0x06b6
+#define WCD934X_RX_OCP_COUNT					0x06b7
+#define WCD934X_HPH_CNP_EN					0x06cb
+#define WCD934X_HPH_CNP_WG_CTL					0x06cc
+#define WCD934X_HPH_GM3_BOOST_EN_MASK				BIT(7)
+#define WCD934X_HPH_GM3_BOOST_ENABLE				BIT(7)
+#define WCD934X_HPH_OCP_CTL					0x06ce
+#define WCD934X_HPH_L_EN					0x06d3
+#define WCD934X_HPH_GAIN_SRC_SEL_MASK				BIT(5)
+#define WCD934X_HPH_GAIN_SRC_SEL_COMPANDER			0
+#define WCD934X_HPH_GAIN_SRC_SEL_REGISTER			BIT(5)
+#define WCD934X_HPH_L_TEST					0x06d4
+#define WCD934X_HPH_R_EN					0x06d6
+#define WCD934X_HPH_R_TEST					0x06d7
+#define WCD934X_HPH_OCP_DET_MASK				BIT(0)
+#define WCD934X_HPH_OCP_DET_ENABLE				BIT(0)
+#define WCD934X_HPH_OCP_DET_DISABLE				0
+#define WCD934X_DIFF_LO_LO2_COMPANDER				0x06ea
+#define WCD934X_DIFF_LO_LO1_COMPANDER				0x06eb
+#define WCD934X_CLK_SYS_MCLK_PRG				0x0711
+#define WCD934X_EXT_CLK_BUF_EN_MASK	BIT(7)
+#define WCD934X_EXT_CLK_BUF_EN		BIT(7)
+#define WCD934X_EXT_CLK_DIV_RATIO_MASK	GENMASK(5, 4)
+#define WCD934X_EXT_CLK_DIV_BY_2	0x10
+#define WCD934X_MCLK_SRC_MASK		BIT(1)
+#define WCD934X_MCLK_SRC_EXT_CLK	0
+#define WCD934X_MCLK_SRC_MASK		BIT(1)
+#define WCD934X_MCLK_EN_MASK		BIT(0)
+#define WCD934X_MCLK_EN			BIT(0)
+#define WCD934X_CLK_SYS_MCLK2_PRG1				0x0712
+#define WCD934X_CLK_SYS_MCLK2_PRG2				0x0713
+#define WCD934X_SIDO_NEW_VOUT_A_STARTUP				0x071b
+#define WCD934X_SIDO_NEW_VOUT_D_STARTUP				0x071c
+#define WCD934X_SIDO_NEW_VOUT_D_FREQ1				0x071d
+#define WCD934X_SIDO_NEW_VOUT_D_FREQ2				0x071e
+#define WCD934X_SIDO_RIPPLE_FREQ_EN_MASK			BIT(0)
+#define WCD934X_SIDO_RIPPLE_FREQ_ENABLE				BIT(0)
+#define WCD934X_MBHC_NEW_CTL_2					0x0721
+#define WCD934X_TX_NEW_AMIC_4_5_SEL				0x0727
+#define WCD934X_HPH_NEW_INT_RDAC_HD2_CTL_L			0x0733
+#define WCD934X_HPH_NEW_INT_RDAC_OVERRIDE_CTL			0x0735
+#define WCD934X_HPH_NEW_INT_RDAC_HD2_CTL_R			0x0736
+#define WCD934X_HPH_NEW_INT_HPH_TIMER1				0x073a
+#define WCD934X_HPH_AUTOCHOP_TIMER_EN_MASK			BIT(1)
+#define WCD934X_HPH_AUTOCHOP_TIMER_ENABLE			BIT(1)
+#define WCD934X_CDC_TX0_TX_PATH_CTL				0x0a31
+#define WCD934X_CDC_TX_PATH_CTL_PCM_RATE_MASK			GENMASK(3, 0)
+#define WCD934X_CDC_TX_PATH_CTL(dec)			(0xa31 + dec * 0x10)
+#define WCD934X_CDC_TX0_TX_PATH_CFG0				0x0a32
+#define WCD934X_CDC_TX0_TX_PATH_CFG1				0x0a33
+#define WCD934X_CDC_TX0_TX_VOL_CTL				0x0a34
+#define WCD934X_CDC_TX0_TX_PATH_192_CTL				0x0a35
+#define WCD934X_CDC_TX0_TX_PATH_192_CFG				0x0a36
+#define WCD934X_CDC_TX0_TX_PATH_SEC2				0x0a39
+#define WCD934X_HPH_CUTOFF_FREQ_CHANGE_REQ_MASK			BIT(1)
+#define WCD934X_HPH_CUTOFF_FREQ_CHANGE_REQ			BIT(1)
+#define WCD934X_CDC_TX1_TX_PATH_CTL				0x0a41
+#define WCD934X_CDC_TX1_TX_PATH_CFG0				0x0a42
+#define WCD934X_CDC_TX1_TX_PATH_CFG1				0x0a43
+#define WCD934X_CDC_TX1_TX_VOL_CTL				0x0a44
+#define WCD934X_CDC_TX2_TX_PATH_CTL				0x0a51
+#define WCD934X_CDC_TX2_TX_PATH_CFG0				0x0a52
+#define WCD934X_CDC_TX2_TX_PATH_CFG1				0x0a53
+#define WCD934X_CDC_TX2_TX_VOL_CTL				0x0a54
+#define WCD934X_CDC_TX3_TX_PATH_CTL				0x0a61
+#define WCD934X_CDC_TX3_TX_PATH_CFG0				0x0a62
+#define WCD934X_CDC_TX3_TX_PATH_CFG1				0x0a63
+#define WCD934X_CDC_TX3_TX_VOL_CTL				0x0a64
+#define WCD934X_CDC_TX3_TX_PATH_192_CTL				0x0a65
+#define WCD934X_CDC_TX3_TX_PATH_192_CFG				0x0a66
+#define WCD934X_CDC_TX4_TX_PATH_CTL				0x0a71
+#define WCD934X_CDC_TX4_TX_PATH_CFG0				0x0a72
+#define WCD934X_CDC_TX4_TX_PATH_CFG1				0x0a73
+#define WCD934X_CDC_TX4_TX_VOL_CTL				0x0a74
+#define WCD934X_CDC_TX4_TX_PATH_192_CTL				0x0a75
+#define WCD934X_CDC_TX4_TX_PATH_192_CFG				0x0a76
+#define WCD934X_CDC_TX5_TX_PATH_CTL				0x0a81
+#define WCD934X_CDC_TX5_TX_PATH_CFG0				0x0a82
+#define WCD934X_CDC_TX5_TX_PATH_CFG1				0x0a83
+#define WCD934X_CDC_TX5_TX_VOL_CTL				0x0a84
+#define WCD934X_CDC_TX5_TX_PATH_192_CTL				0x0a85
+#define WCD934X_CDC_TX5_TX_PATH_192_CFG				0x0a86
+#define WCD934X_CDC_TX6_TX_PATH_CTL				0x0a91
+#define WCD934X_CDC_TX6_TX_PATH_CFG0				0x0a92
+#define WCD934X_CDC_TX6_TX_PATH_CFG1				0x0a93
+#define WCD934X_CDC_TX6_TX_VOL_CTL				0x0a94
+#define WCD934X_CDC_TX6_TX_PATH_192_CTL				0x0a95
+#define WCD934X_CDC_TX6_TX_PATH_192_CFG				0x0a96
+#define WCD934X_CDC_TX7_TX_PATH_CTL				0x0aa1
+#define WCD934X_CDC_TX7_TX_PATH_CFG0				0x0aa2
+#define WCD934X_CDC_TX7_TX_PATH_CFG1				0x0aa3
+#define WCD934X_CDC_TX7_TX_VOL_CTL				0x0aa4
+#define WCD934X_CDC_TX7_TX_PATH_192_CTL				0x0aa5
+#define WCD934X_CDC_TX7_TX_PATH_192_CFG				0x0aa6
+#define WCD934X_CDC_TX8_TX_PATH_CTL				0x0ab1
+#define WCD934X_CDC_TX8_TX_PATH_CFG0				0x0ab2
+#define WCD934X_CDC_TX8_TX_PATH_CFG1				0x0ab3
+#define WCD934X_CDC_TX8_TX_VOL_CTL				0x0ab4
+#define WCD934X_CDC_TX8_TX_PATH_192_CTL				0x0ab5
+#define WCD934X_CDC_TX8_TX_PATH_192_CFG				0x0ab6
+#define WCD934X_CDC_TX9_SPKR_PROT_PATH_CFG0			0x0ac3
+#define WCD934X_CDC_TX10_SPKR_PROT_PATH_CFG0			0x0ac7
+#define WCD934X_CDC_TX11_SPKR_PROT_PATH_CFG0			0x0acb
+#define WCD934X_CDC_TX12_SPKR_PROT_PATH_CFG0			0x0acf
+#define WCD934X_CDC_COMPANDER1_CTL0				0x0b01
+#define WCD934X_COMP_CLK_EN_MASK				BIT(0)
+#define WCD934X_COMP_CLK_ENABLE					BIT(0)
+#define WCD934X_COMP_SOFT_RST_MASK				BIT(1)
+#define WCD934X_COMP_SOFT_RST_ENABLE				BIT(1)
+#define WCD934X_COMP_HALT_MASK					BIT(2)
+#define WCD934X_COMP_HALT					BIT(2)
+#define WCD934X_COMP_SOFT_RST_DISABLE				0
+#define WCD934X_CDC_COMPANDER1_CTL7				0x0b08
+#define WCD934X_HPH_LOW_PWR_MODE_EN_MASK			BIT(5)
+#define WCD934X_CDC_COMPANDER2_CTL7				0x0b10
+#define WCD934X_CDC_COMPANDER7_CTL3				0x0b34
+#define WCD934X_CDC_COMPANDER7_CTL7				0x0b38
+#define WCD934X_CDC_COMPANDER8_CTL3				0x0b3c
+#define WCD934X_CDC_COMPANDER8_CTL7				0x0b40
+#define WCD934X_CDC_RX0_RX_PATH_CTL				0x0b41
+#define WCD934X_CDC_RX_PGA_MUTE_EN_MASK				BIT(4)
+#define WCD934X_CDC_RX_PGA_MUTE_ENABLE				BIT(4)
+#define WCD934X_CDC_RX_PGA_MUTE_DISABLE				0
+#define WCD934X_RX_CLK_EN_MASK					BIT(5)
+#define WCD934X_RX_CLK_ENABLE					BIT(5)
+#define WCD934X_RX_RESET_MASK					BIT(6)
+#define WCD934X_RX_RESET_ENABLE					BIT(6)
+#define WCD934X_RX_RESET_DISABLE				0
+#define WCD934X_RX_PCM_RATE_MASK				GENMASK(3, 0)
+#define WCD934X_RX_PCM_RATE_F_48K				0x04
+#define WCD934X_CDC_RX_PATH_CTL(rx)			(0xb41 + rx * 0x14)
+#define WCD934X_CDC_MIX_PCM_RATE_MASK				GENMASK(3, 0)
+#define WCD934X_CDC_RX0_RX_PATH_CFG0				0x0b42
+#define WCD934X_RX_DLY_ZN_EN_MASK				BIT(3)
+#define WCD934X_RX_DLY_ZN_ENABLE				BIT(3)
+#define WCD934X_RX_DLY_ZN_DISABLE				0
+#define WCD934X_CDC_RX0_RX_PATH_CFG1				0x0b43
+#define WCD934X_CDC_RX0_RX_PATH_CFG2				0x0b44
+#define WCD934X_CDC_RX0_RX_VOL_CTL				0x0b45
+#define WCD934X_CDC_RX0_RX_PATH_MIX_CTL				0x0b46
+#define WCD934X_CDC_RX_MIX_CLK_EN_MASK				BIT(5)
+#define WCD934X_CDC_RX_MIX_CLK_ENABLE				BIT(5)
+#define WCD934X_CDC_RX_PATH_MIX_CTL(rx)			(0xb46 + rx * 0x14)
+#define WCD934X_CDC_RX0_RX_PATH_MIX_CFG				0x0b47
+#define WCD934X_CDC_RX0_RX_VOL_MIX_CTL				0x0b48
+#define WCD934X_CDC_RX0_RX_PATH_SEC0				0x0b49
+#define WCD934X_CDC_RX0_RX_PATH_DSMDEM_CTL			0x0b53
+#define WCD934X_CDC_RX1_RX_PATH_CTL				0x0b55
+#define WCD934X_RX_PATH_PGA_MUTE_EN_MASK			BIT(4)
+#define WCD934X_RX_PATH_PGA_MUTE_ENABLE				BIT(4)
+#define WCD934X_CDC_RX_PATH_PGA_MUTE_DISABLE			0
+#define WCD934X_CDC_RX_PATH_CLK_EN_MASK				BIT(5)
+#define WCD934X_CDC_RX_PATH_CLK_ENABLE				BIT(5)
+#define WCD934X_CDC_RX_PATH_CLK_DISABLE				0
+#define WCD934X_CDC_RX1_RX_PATH_CFG0				0x0b56
+#define WCD934X_HPH_CMP_EN_MASK					BIT(1)
+#define WCD934X_HPH_CMP_ENABLE					BIT(1)
+#define WCD934X_HPH_CMP_DISABLE					0
+#define WCD934X_CDC_RX1_RX_PATH_CFG2				0x0b58
+#define WCD934X_CDC_RX1_RX_VOL_CTL				0x0b59
+#define WCD934X_CDC_RX1_RX_PATH_MIX_CTL				0x0b5a
+#define WCD934X_CDC_RX1_RX_PATH_MIX_CFG				0x0b5b
+#define WCD934X_CDC_RX1_RX_VOL_MIX_CTL				0x0b5c
+#define WCD934X_CDC_RX1_RX_PATH_SEC0				0x0b5d
+#define WCD934X_CDC_RX1_RX_PATH_SEC3				0x0b60
+#define WCD934X_CDC_RX_PATH_SEC_HD2_ALPHA_MASK			GENMASK(5, 2)
+#define WCD934X_CDC_RX_PATH_SEC_HD2_ALPHA_0P3125		0x14
+#define WCD934X_CDC_RX_PATH_SEC_HD2_ALPHA_0P0000		0
+#define WCD934X_CDC_RX1_RX_PATH_DSMDEM_CTL			0x0b67
+#define WCD934X_CDC_RX2_RX_PATH_CTL				0x0b69
+#define WCD934X_CDC_RX2_RX_PATH_CFG0				0x0b6a
+#define WCD934X_CDC_RX_PATH_CFG_HD2_EN_MASK			BIT(2)
+#define WCD934X_CDC_RX_PATH_CFG_HD2_ENABLE			BIT(2)
+#define WCD934X_CDC_RX_PATH_CFG_HD2_DISABLE			0
+#define WCD934X_CDC_RX2_RX_PATH_CFG2				0x0b6c
+#define WCD934X_CDC_RX2_RX_VOL_CTL				0x0b6d
+#define WCD934X_CDC_RX2_RX_PATH_MIX_CTL				0x0b6e
+#define WCD934X_CDC_RX2_RX_PATH_MIX_CFG				0x0b6f
+#define WCD934X_CDC_RX2_RX_VOL_MIX_CTL				0x0b70
+#define WCD934X_CDC_RX2_RX_PATH_SEC0				0x0b71
+#define WCD934X_CDC_RX2_RX_PATH_SEC3				0x0b74
+#define WCD934X_CDC_RX2_RX_PATH_DSMDEM_CTL			0x0b7b
+#define WCD934X_CDC_RX3_RX_PATH_CTL				0x0b7d
+#define WCD934X_CDC_RX3_RX_PATH_CFG0				0x0b6e
+#define WCD934X_CDC_RX3_RX_PATH_CFG2				0x0b80
+#define WCD934X_CDC_RX3_RX_VOL_CTL				0x0b81
+#define WCD934X_CDC_RX3_RX_PATH_MIX_CTL				0x0b82
+#define WCD934X_CDC_RX3_RX_PATH_MIX_CFG				0x0b83
+#define WCD934X_CDC_RX3_RX_VOL_MIX_CTL				0x0b84
+#define WCD934X_CDC_RX3_RX_PATH_SEC0				0x0b85
+#define WCD934X_CDC_RX3_RX_PATH_DSMDEM_CTL			0x0b8f
+#define WCD934X_CDC_RX4_RX_PATH_CTL				0x0b91
+#define WCD934X_CDC_RX4_RX_PATH_CFG0				0x0b92
+#define WCD934X_CDC_RX4_RX_PATH_CFG2				0x0b94
+#define WCD934X_CDC_RX4_RX_VOL_CTL				0x0b95
+#define WCD934X_CDC_RX4_RX_PATH_MIX_CTL				0x0b96
+#define WCD934X_CDC_RX4_RX_PATH_MIX_CFG				0x0b97
+#define WCD934X_CDC_RX4_RX_VOL_MIX_CTL				0x0b98
+#define WCD934X_CDC_RX4_RX_PATH_SEC0				0x0b99
+#define WCD934X_CDC_RX4_RX_PATH_DSMDEM_CTL			0x0ba3
+#define WCD934X_CDC_RX7_RX_PATH_CTL				0x0bcd
+#define WCD934X_CDC_RX7_RX_PATH_CFG0				0x0bce
+#define WCD934X_CDC_RX7_RX_PATH_CFG1				0x0bcf
+#define WCD934X_CDC_RX7_RX_PATH_CFG2				0x0bd0
+#define WCD934X_CDC_RX7_RX_VOL_CTL				0x0bd1
+#define WCD934X_CDC_RX7_RX_PATH_MIX_CTL				0x0bd2
+#define WCD934X_CDC_RX7_RX_PATH_MIX_CFG				0x0bd3
+#define WCD934X_CDC_RX7_RX_VOL_MIX_CTL				0x0bd4
+#define WCD934X_CDC_RX7_RX_PATH_SEC1				0x0bd6
+#define WCD934X_CDC_RX7_RX_PATH_MIX_SEC0			0x0bdd
+#define WCD934X_CDC_RX7_RX_PATH_DSMDEM_CTL			0x0bdf
+#define WCD934X_CDC_RX8_RX_PATH_CTL				0x0be1
+#define WCD934X_CDC_RX8_RX_PATH_CFG0				0x0be2
+#define WCD934X_CDC_RX8_RX_PATH_CFG1				0x0be3
+#define WCD934X_RX_SMART_BOOST_EN_MASK				BIT(0)
+#define WCD934X_RX_SMART_BOOST_ENABLE				BIT(0)
+#define WCD934X_RX_SMART_BOOST_DISABLE			0
+#define WCD934X_CDC_RX8_RX_PATH_CFG2				0x0be4
+#define WCD934X_CDC_RX8_RX_VOL_CTL				0x0be5
+#define WCD934X_CDC_RX8_RX_PATH_MIX_CTL				0x0be6
+#define WCD934X_CDC_RX8_RX_PATH_MIX_CFG				0x0be7
+#define WCD934X_CDC_RX8_RX_VOL_MIX_CTL				0x0be8
+#define WCD934X_CDC_RX8_RX_PATH_SEC1				0x0bea
+#define WCD934X_CDC_RX8_RX_PATH_MIX_SEC0			0x0bf1
+#define WCD934X_CDC_RX8_RX_PATH_DSMDEM_CTL			0x0bf3
+#define WCD934X_CDC_CLSH_DECAY_CTRL				0x0c03
+#define WCD934X_CDC_CLSH_K2_MSB					0x0c0a
+#define WCD934X_CDC_CLSH_K2_LSB					0x0c0b
+#define WCD934X_CDC_CLSH_TEST0					0x0c0f
+#define WCD934X_CDC_BOOST0_BOOST_PATH_CTL			0x0c19
+#define WCD934X_BOOST_PATH_CLK_EN_MASK				BIT(4)
+#define WCD934X_BOOST_PATH_CLK_ENABLE				BIT(4)
+#define WCD934X_BOOST_PATH_CLK_DISABLE				0
+#define WCD934X_CDC_BOOST0_BOOST_CTL				0x0c1a
+#define WCD934X_CDC_BOOST0_BOOST_CFG1				0x0c1b
+#define WCD934X_CDC_BOOST0_BOOST_CFG2				0x0c1c
+#define WCD934X_CDC_BOOST1_BOOST_PATH_CTL			0x0c21
+#define WCD934X_CDC_BOOST1_BOOST_CTL				0x0c22
+#define WCD934X_CDC_BOOST1_BOOST_CFG1				0x0c23
+#define WCD934X_CDC_BOOST1_BOOST_CFG2				0x0c24
+#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_0			0x0c91
+#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_1			0x0c92
+#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_2			0x0c93
+#define WCD934X_SWR_AHB_BRIDGE_RD_DATA_3			0x0c94
+#define WCD934X_SWR_AHB_BRIDGE_ACCESS_STATUS			0x0c96
+#define WCD934X_CDC_SIDETONE_SRC0_ST_SRC_PATH_CTL		0x0cb5
+#define WCD934X_CDC_SIDETONE_SRC1_ST_SRC_PATH_CTL		0x0cb9
+#define WCD934X_CDC_RX_INP_MUX_RX_INT0_CFG0			0x0d01
+#define WCD934X_CDC_RX_INP_MUX_RX_INT_CFG0(i)		(0xd01 + i * 0x2)
+#define WCD934X_CDC_RX_INP_MUX_RX_INT_SEL_MASK			GENMASK(3, 0)
+#define WCD934X_CDC_RX_INP_MUX_RX_INT0_CFG1			0x0d02
+#define WCD934X_CDC_RX_INP_MUX_RX_INT_CFG1(i)		(0xd02 + i * 0x2)
+#define WCD934X_CDC_RX_INP_MUX_RX_INT1_CFG0			0x0d03
+#define WCD934X_CDC_RX_INP_MUX_RX_INT1_CFG1			0x0d04
+#define WCD934X_CDC_RX_INP_MUX_RX_INT2_CFG0			0x0d05
+#define WCD934X_CDC_RX_INP_MUX_RX_INT2_CFG1			0x0d06
+#define WCD934X_CDC_RX_INP_MUX_RX_INT3_CFG0			0x0d07
+#define WCD934X_CDC_RX_INP_MUX_RX_INT3_CFG1			0x0d08
+#define WCD934X_CDC_RX_INP_MUX_RX_INT4_CFG0			0x0d09
+#define WCD934X_CDC_RX_INP_MUX_RX_INT4_CFG1			0x0d0a
+#define WCD934X_CDC_RX_INP_MUX_RX_INT7_CFG0			0x0d0f
+#define WCD934X_CDC_RX_INP_MUX_RX_INT7_CFG1			0x0d10
+#define WCD934X_CDC_RX_INP_MUX_RX_INT8_CFG0			0x0d11
+#define WCD934X_CDC_RX_INP_MUX_RX_INT8_CFG1			0x0d12
+#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG0			0x0d13
+#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG1			0x0d14
+#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG2			0x0d15
+#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG3			0x0d16
+#define WCD934X_CDC_RX_INP_MUX_RX_MIX_CFG4			0x0d17
+#define WCD934X_CDC_RX_INP_MUX_SIDETONE_SRC_CFG0		0x0d18
+#define WCD934X_CDC_RX_INP_MUX_SIDETONE_SRC_CFG1		0x0d19
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX0_CFG0			0x0d1d
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX0_CFG1			0x0d1e
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX1_CFG0			0x0d1f
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX1_CFG1			0x0d20
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX2_CFG0			0x0d21
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX2_CFG1			0x0d22
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX3_CFG0			0x0d23
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX3_CFG1			0x0d25
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX4_CFG0			0x0d26
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX5_CFG0			0x0d27
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX6_CFG0			0x0d28
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX7_CFG0			0x0d29
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX8_CFG0			0x0d2a
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX10_CFG0			0x0d2b
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX11_CFG0			0x0d2c
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX12_CFG0			0x0d2d
+#define WCD934X_CDC_TX_INP_MUX_ADC_MUX13_CFG0			0x0d2e
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG0		0x0d31
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG1		0x0d32
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG2		0x0d33
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR0_MIX_CFG3		0x0d34
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG0		0x0d35
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG1		0x0d36
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG2		0x0d37
+#define WCD934X_CDC_SIDETONE_IIR_INP_MUX_IIR1_MIX_CFG3		0x0d38
+#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG0			0x0d3a
+#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG1			0x0d3b
+#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG2			0x0d3c
+#define WCD934X_CDC_IF_ROUTER_TX_MUX_CFG3			0x0d3d
+#define WCD934X_CDC_CLK_RST_CTRL_MCLK_CONTROL			0x0d41
+#define WCD934X_CDC_MCLK_EN_MASK				BIT(0)
+#define WCD934X_CDC_MCLK_EN_ENABLE				BIT(0)
+#define WCD934X_CDC_CLK_RST_CTRL_FS_CNT_CONTROL			0x0d42
+#define WCD934X_CDC_FS_MCLK_CNT_EN_MASK				BIT(0)
+#define WCD934X_CDC_FS_MCLK_CNT_ENABLE				BIT(0)
+#define WCD934X_CDC_CLK_RST_CTRL_SWR_CONTROL			0x0d43
+#define WCD934X_CDC_SWR_CLK_EN_MASK				BIT(0)
+#define WCD934X_CDC_SWR_CLK_ENABLE				BIT(0)
+#define WCD934X_CDC_CLK_RST_CTRL_DSD_CONTROL			0x0d44
+#define WCD934X_CDC_CLK_RST_CTRL_ASRC_SHARE_CONTROL		0x0d45
+#define WCD934X_CDC_CLK_RST_CTRL_GFM_CONTROL			0x0d46
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_PATH_CTL			0x0d55
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B1_CTL		0x0d56
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B2_CTL		0x0d57
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B3_CTL		0x0d58
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B4_CTL		0x0d59
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B5_CTL		0x0d5a
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B6_CTL		0x0d5b
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B7_CTL		0x0d5c
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_B8_CTL		0x0d5d
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_CTL			0x0d5e
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_GAIN_TIMER_CTL		0x0d5f
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_COEF_B1_CTL		0x0d60
+#define WCD934X_CDC_SIDETONE_IIR0_IIR_COEF_B2_CTL		0x0d61
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_PATH_CTL			0x0d65
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B1_CTL		0x0d66
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B2_CTL		0x0d67
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B3_CTL		0x0d68
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B4_CTL		0x0d69
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B5_CTL		0x0d6a
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B6_CTL		0x0d6b
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B7_CTL		0x0d6c
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_B8_CTL		0x0d6d
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_CTL			0x0d6e
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_GAIN_TIMER_CTL		0x0d6f
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_COEF_B1_CTL		0x0d70
+#define WCD934X_CDC_SIDETONE_IIR1_IIR_COEF_B2_CTL		0x0d71
+#define WCD934X_CDC_TOP_TOP_CFG1				0x0d82
+#define WCD934X_CDC_TOP_TOP_CFG7				0x0d88
+#define WCD934X_CDC_TOP_HPHL_COMP_LUT				0x0d8b
+#define WCD934X_CDC_TOP_HPHR_COMP_LUT				0x0d90
+#define WCD934X_HPH_LUT_BYPASS_MASK				BIT(7)
+#define WCD934X_HPH_LUT_BYPASS_ENABLE				BIT(7)
+#define WCD934X_HPH_LUT_BYPASS_DISABLE				0
+#define WCD934X_CODEC_CPR_WR_DATA_0				0x5001
+#define WCD934X_CODEC_CPR_WR_ADDR_0				0x5005
+#define WCD934X_CODEC_CPR_SVS_CX_VDD				0x5022
+#define WCD934X_CODEC_CPR_SVS2_CX_VDD				0x5023
+#define WCD934X_CODEC_CPR_SVS2_MIN_CX_VDD			0x5027
+#define WCD934X_TLMM_DMIC1_CLK_PINCFG				0x8015
+#define WCD934X_TLMM_DMIC1_DATA_PINCFG				0x8016
+#define WCD934X_TLMM_DMIC2_CLK_PINCFG				0x8017
+#define WCD934X_TLMM_DMIC2_DATA_PINCFG				0x8018
+#define WCD934X_TLMM_DMIC3_CLK_PINCFG				0x8019
+#define WCD934X_TLMM_DMIC3_DATA_PINCFG				0x801a
+#define WCD934X_TEST_DEBUG_PAD_DRVCTL_0				0x803b
+#define WCD934X_TEST_DEBUG_NPL_DLY_TEST_1			0x803e
+
+#define WCD934X_MAX_REGISTER					0xffff
+#define WCD934X_SEL_REGISTER					0x800
+#define WCD934X_SEL_MASK					0xff
+#define WCD934X_SEL_SHIFT					0x0
+#define WCD934X_WINDOW_START					0x800
+#define WCD934X_WINDOW_LENGTH					0x100
+
+/* SLIMBUS Slave Registers */
+#define WCD934X_SLIM_PGD_PORT_INT_EN0				0x30
+#define WCD934X_SLIM_PGD_PORT_INT_STATUS_RX_0			0x34
+#define WCD934X_SLIM_PGD_PORT_INT_STATUS_RX_1			0x35
+#define WCD934X_SLIM_PGD_PORT_INT_STATUS_TX_0			0x36
+#define WCD934X_SLIM_PGD_PORT_INT_STATUS_TX_1			0x37
+#define WCD934X_SLIM_PGD_PORT_INT_CLR_RX_0			0x38
+#define WCD934X_SLIM_PGD_PORT_INT_CLR_RX_1			0x39
+#define WCD934X_SLIM_PGD_PORT_INT_CLR_TX_0			0x3A
+#define WCD934X_SLIM_PGD_PORT_INT_CLR_TX_1			0x3B
+#define WCD934X_SLIM_PGD_PORT_INT_RX_SOURCE0			0x60
+#define WCD934X_SLIM_PGD_PORT_INT_TX_SOURCE0			0x70
+#define WCD934X_SLIM_PGD_RX_PORT_CFG(p)				(0x30 + p)
+#define WCD934X_SLIM_PGD_PORT_CFG(p)				(0x40 + p)
+#define WCD934X_SLIM_PGD_TX_PORT_CFG(p)				(0x50 + p)
+#define WCD934X_SLIM_PGD_PORT_INT_SRC(p)			(0x60 + p)
+#define WCD934X_SLIM_PGD_PORT_INT_STATUS(p)			(0x80 + p)
+#define WCD934X_SLIM_PGD_TX_PORT_MULTI_CHNL_0(p)		(0x100 + 4 * p)
+/* ports range from 10-16 */
+#define WCD934X_SLIM_PGD_TX_PORT_MULTI_CHNL_1(p)		(0x101 + 4 * p)
+#define WCD934X_SLIM_PGD_RX_PORT_MULTI_CHNL_0(p)		(0x140 + 4 * p)
+
+#define SLIM_MANF_ID_QCOM			0x217
+#define SLIM_PROD_CODE_WCD9340			0x250
+#define SLIM_DEV_IDX_WCD9340			0x1
+#define SLIM_DEV_INSTANCE_ID_WCD9340		0
+
+#endif
diff --git a/include/linux/mfd/wcd934x/wcd934x.h b/include/linux/mfd/wcd934x/wcd934x.h
new file mode 100644
index 000000000000..f3c65a035150
--- /dev/null
+++ b/include/linux/mfd/wcd934x/wcd934x.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __WCD934X_H__
+#define __WCD934X_H__
+#include <linux/clk.h>
+#include <linux/regulator/consumer.h>
+#include <linux/regmap.h>
+#include <linux/slimbus.h>
+
+#define WCD934X_MAX_SUPPLY	5
+
+/**
+ * struct wcd934x_ddata - wcd934x driver data
+ *
+ * @supplies:	wcd934x regulator supplies
+ * @irq_data:	wcd934x irq_chip data
+ * @regmap:	wcd934x regmap pointer
+ * @extclk:	External clock
+ * @dev:	device instance of wcd934x slim device
+ * @irq:	irq for wcd934x.
+ */
+struct wcd934x_ddata {
+	struct regulator_bulk_data supplies[WCD934X_MAX_SUPPLY];
+	struct regmap_irq_chip_data *irq_data;
+	struct regmap *regmap;
+	struct clk *extclk;
+	struct device *dev;
+	int irq;
+};
+
+#endif /* __WCD934X_H__ */
diff --git a/include/linux/mlx4/cq.h b/include/linux/mlx4/cq.h
index 508e8cc5ee86..653d2a0aa44c 100644
--- a/include/linux/mlx4/cq.h
+++ b/include/linux/mlx4/cq.h
@@ -130,6 +130,11 @@ enum {
 	MLX4_CQE_STATUS_IPOK		= 1 << 12,
 };
 
+/* L4_CSUM is logically part of status, but has to checked against badfcs_enc */
+enum {
+	MLX4_CQE_STATUS_L4_CSUM		= 1 << 2,
+};
+
 enum {
 	MLX4_CQE_LLC                     = 1,
 	MLX4_CQE_SNAP                    = 1 << 1,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 22bd0d5024c8..277a51d3ec40 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -463,6 +463,11 @@ struct mlx5_vf_context {
 	int	enabled;
 	u64	port_guid;
 	u64	node_guid;
+	/* Valid bits are used to validate administrative guid only.
+	 * Enabled after ndo_set_vf_guid
+	 */
+	u8	port_guid_valid:1;
+	u8	node_guid_valid:1;
 	enum port_state_policy	policy;
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ee0a34d66c7c..032cd6630720 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1188,7 +1188,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_cq[0x5];
 
 	u8         log_max_eq_sz[0x8];
-	u8         reserved_at_e8[0x2];
+	u8         relaxed_ordering_write[0x1];
+	u8         relaxed_ordering_read[0x1];
 	u8         log_max_mkey[0x6];
 	u8         reserved_at_f0[0x8];
 	u8         dump_fill_mkey[0x1];
@@ -1211,7 +1212,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_130[0xa];
 	u8         log_max_ra_res_dc[0x6];
 
-	u8         reserved_at_140[0xa];
+	u8         reserved_at_140[0x9];
+	u8         roce_accl[0x1];
 	u8         log_max_ra_req_qp[0x6];
 	u8         reserved_at_150[0xa];
 	u8         log_max_ra_res_qp[0x6];
@@ -3428,7 +3430,9 @@ struct mlx5_ifc_mkc_bits {
 
 	u8         translations_octword_size[0x20];
 
-	u8         reserved_at_1c0[0x1b];
+	u8         reserved_at_1c0[0x19];
+	u8         relaxed_ordering_read[0x1];
+	u8         reserved_at_1d9[0x1];
 	u8         log_page_size[0x5];
 
 	u8         reserved_at_1e0[0x20];
@@ -4889,7 +4893,19 @@ struct mlx5_ifc_query_q_counter_out_bits {
 
 	u8         req_cqe_flush_error[0x20];
 
-	u8         reserved_at_620[0x1e0];
+	u8         reserved_at_620[0x20];
+
+	u8         roce_adp_retrans[0x20];
+
+	u8         roce_adp_retrans_to[0x20];
+
+	u8         roce_slow_restart[0x20];
+
+	u8         roce_slow_restart_cnps[0x20];
+
+	u8         roce_slow_restart_trans[0x20];
+
+	u8         reserved_at_6e0[0x120];
 };
 
 struct mlx5_ifc_query_q_counter_in_bits {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 67f8451b9a12..52269e56c514 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -70,11 +70,6 @@ static inline void totalram_pages_add(long count)
 	atomic_long_add(count, &_totalram_pages);
 }
 
-static inline void totalram_pages_set(long val)
-{
-	atomic_long_set(&_totalram_pages, val);
-}
-
 extern void * high_memory;
 extern int page_cluster;
 
@@ -916,10 +911,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 
 #define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))
 
-#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
-#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
-#endif
-
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
@@ -947,9 +938,10 @@ static inline bool is_zone_device_page(const struct page *page)
 #endif
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page);
+void free_devmap_managed_page(struct page *page);
 DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-static inline bool put_devmap_managed_page(struct page *page)
+
+static inline bool page_is_devmap_managed(struct page *page)
 {
 	if (!static_branch_unlikely(&devmap_managed_key))
 		return false;
@@ -958,7 +950,6 @@ static inline bool put_devmap_managed_page(struct page *page)
 	switch (page->pgmap->type) {
 	case MEMORY_DEVICE_PRIVATE:
 	case MEMORY_DEVICE_FS_DAX:
-		__put_devmap_managed_page(page);
 		return true;
 	default:
 		break;
@@ -966,11 +957,17 @@ static inline bool put_devmap_managed_page(struct page *page)
 	return false;
 }
 
+void put_devmap_managed_page(struct page *page);
+
 #else /* CONFIG_DEV_PAGEMAP_OPS */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool page_is_devmap_managed(struct page *page)
 {
 	return false;
 }
+
+static inline void put_devmap_managed_page(struct page *page)
+{
+}
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static inline bool is_device_private_page(const struct page *page)
@@ -1023,37 +1020,37 @@ static inline void put_page(struct page *page)
 	 * need to inform the device driver through callback. See
 	 * include/linux/memremap.h and HMM for details.
 	 */
-	if (put_devmap_managed_page(page))
+	if (page_is_devmap_managed(page)) {
+		put_devmap_managed_page(page);
 		return;
+	}
 
 	if (put_page_testzero(page))
 		__put_page(page);
 }
 
 /**
- * put_user_page() - release a gup-pinned page
+ * unpin_user_page() - release a gup-pinned page
  * @page:            pointer to page to be released
  *
- * Pages that were pinned via get_user_pages*() must be released via
- * either put_user_page(), or one of the put_user_pages*() routines
- * below. This is so that eventually, pages that are pinned via
- * get_user_pages*() can be separately tracked and uniquely handled. In
- * particular, interactions with RDMA and filesystems need special
- * handling.
+ * Pages that were pinned via pin_user_pages*() must be released via either
+ * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so
+ * that eventually such pages can be separately tracked and uniquely handled. In
+ * particular, interactions with RDMA and filesystems need special handling.
  *
- * put_user_page() and put_page() are not interchangeable, despite this early
- * implementation that makes them look the same. put_user_page() calls must
- * be perfectly matched up with get_user_page() calls.
+ * unpin_user_page() and put_page() are not interchangeable, despite this early
+ * implementation that makes them look the same. unpin_user_page() calls must
+ * be perfectly matched up with pin*() calls.
  */
-static inline void put_user_page(struct page *page)
+static inline void unpin_user_page(struct page *page)
 {
 	put_page(page);
 }
 
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty);
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+				 bool make_dirty);
 
-void put_user_pages(struct page **pages, unsigned long npages);
+void unpin_user_pages(struct page **pages, unsigned long npages);
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define SECTION_IN_PAGE_FLAGS
@@ -1501,9 +1498,16 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			    unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas, int *locked);
+long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   struct vm_area_struct **vmas, int *locked);
 long get_user_pages(unsigned long start, unsigned long nr_pages,
 			    unsigned int gup_flags, struct page **pages,
 			    struct vm_area_struct **vmas);
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+		    unsigned int gup_flags, struct page **pages,
+		    struct vm_area_struct **vmas);
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages, int *locked);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
@@ -1511,6 +1515,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages);
 
 int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
 int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
@@ -2176,12 +2182,6 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 					struct mminit_pfnnid_cache *state);
 #endif
 
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-void zero_resv_unavail(void);
-#else
-static inline void zero_resv_unavail(void) {}
-#endif
-
 extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long,
 		enum memmap_context, struct vmem_altmap *);
@@ -2323,6 +2323,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
+extern int do_madvise(unsigned long start, size_t len_in, int behavior);
 
 static inline unsigned long
 do_mmap_pgoff(struct file *file, unsigned long addr,
@@ -2528,6 +2529,8 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot);
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
+vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
+			pfn_t pfn, pgprot_t pgprot);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
@@ -2574,13 +2577,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
 #define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
+#define FOLL_PIN	0x40000	/* pages must be released via unpin_user_page */
 
 /*
- * NOTE on FOLL_LONGTERM:
+ * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
+ * other. Here is what they mean, and how to use them:
  *
  * FOLL_LONGTERM indicates that the page will be held for an indefinite time
- * period _often_ under userspace control.  This is contrasted with
- * iov_iter_get_pages() where usages which are transient.
+ * period _often_ under userspace control.  This is in contrast to
+ * iov_iter_get_pages(), whose usages are transient.
  *
  * FIXME: For pages which are part of a filesystem, mappings are subject to the
  * lifetime enforced by the filesystem and we need guarantees that longterm
@@ -2595,11 +2600,39 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
  * Currently only get_user_pages() and get_user_pages_fast() support this flag
  * and calls to get_user_pages_[un]locked are specifically not allowed.  This
  * is due to an incompatibility with the FS DAX check and
- * FAULT_FLAG_ALLOW_RETRY
+ * FAULT_FLAG_ALLOW_RETRY.
  *
- * In the CMA case: longterm pins in a CMA region would unnecessarily fragment
- * that region.  And so CMA attempts to migrate the page before pinning when
+ * In the CMA case: long term pins in a CMA region would unnecessarily fragment
+ * that region.  And so, CMA attempts to migrate the page before pinning, when
  * FOLL_LONGTERM is specified.
+ *
+ * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount,
+ * but an additional pin counting system) will be invoked. This is intended for
+ * anything that gets a page reference and then touches page data (for example,
+ * Direct IO). This lets the filesystem know that some non-file-system entity is
+ * potentially changing the pages' data. In contrast to FOLL_GET (whose pages
+ * are released via put_page()), FOLL_PIN pages must be released, ultimately, by
+ * a call to unpin_user_page().
+ *
+ * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different
+ * and separate refcounting mechanisms, however, and that means that each has
+ * its own acquire and release mechanisms:
+ *
+ *     FOLL_GET: get_user_pages*() to acquire, and put_page() to release.
+ *
+ *     FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release.
+ *
+ * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call.
+ * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based
+ * calls applied to them, and that's perfectly OK. This is a constraint on the
+ * callers, not on the pages.)
+ *
+ * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never
+ * directly by the caller. That's in order to help avoid mismatches when
+ * releasing pages: get_user_pages*() pages must be released via put_page(),
+ * while pin_user_pages*() pages must be released via unpin_user_page().
+ *
+ * Please see Documentation/vm/pin_user_pages.rst for more information.
  */
 
 static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 270aa8fd2800..c28911c3afa8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -312,7 +312,12 @@ struct vm_area_struct {
 	/* Second cache line starts here. */
 
 	struct mm_struct *vm_mm;	/* The address space we belong to. */
-	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
+
+	/*
+	 * Access permissions of this VMA.
+	 * See vmf_insert_mixed_prot() for discussion.
+	 */
+	pgprot_t vm_page_prot;
 	unsigned long vm_flags;		/* Flags, see mm.h. */
 
 	/*
@@ -490,7 +495,7 @@ struct mm_struct {
 		/* store ref to file /proc/<pid>/exe symlink points to */
 		struct file __rcu *exe_file;
 #ifdef CONFIG_MMU_NOTIFIER
-		struct mmu_notifier_mm *mmu_notifier_mm;
+		struct mmu_notifier_subscriptions *notifier_subscriptions;
 #endif
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 9e6caa8ecd19..736f6918335e 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -8,7 +8,7 @@
 #include <linux/srcu.h>
 #include <linux/interval_tree.h>
 
-struct mmu_notifier_mm;
+struct mmu_notifier_subscriptions;
 struct mmu_notifier;
 struct mmu_notifier_range;
 struct mmu_interval_notifier;
@@ -73,7 +73,7 @@ struct mmu_notifier_ops {
 	 * through the gart alias address, so leading to memory
 	 * corruption.
 	 */
-	void (*release)(struct mmu_notifier *mn,
+	void (*release)(struct mmu_notifier *subscription,
 			struct mm_struct *mm);
 
 	/*
@@ -85,7 +85,7 @@ struct mmu_notifier_ops {
 	 * Start-end is necessary in case the secondary MMU is mapping the page
 	 * at a smaller granularity than the primary MMU.
 	 */
-	int (*clear_flush_young)(struct mmu_notifier *mn,
+	int (*clear_flush_young)(struct mmu_notifier *subscription,
 				 struct mm_struct *mm,
 				 unsigned long start,
 				 unsigned long end);
@@ -95,7 +95,7 @@ struct mmu_notifier_ops {
 	 * latter, it is supposed to test-and-clear the young/accessed bitflag
 	 * in the secondary pte, but it may omit flushing the secondary tlb.
 	 */
-	int (*clear_young)(struct mmu_notifier *mn,
+	int (*clear_young)(struct mmu_notifier *subscription,
 			   struct mm_struct *mm,
 			   unsigned long start,
 			   unsigned long end);
@@ -106,7 +106,7 @@ struct mmu_notifier_ops {
 	 * frequently used without actually clearing the flag or tearing
 	 * down the secondary mapping on the page.
 	 */
-	int (*test_young)(struct mmu_notifier *mn,
+	int (*test_young)(struct mmu_notifier *subscription,
 			  struct mm_struct *mm,
 			  unsigned long address);
 
@@ -114,7 +114,7 @@ struct mmu_notifier_ops {
 	 * change_pte is called in cases that pte mapping to page is changed:
 	 * for example, when ksm remaps pte to point to a new shared page.
 	 */
-	void (*change_pte)(struct mmu_notifier *mn,
+	void (*change_pte)(struct mmu_notifier *subscription,
 			   struct mm_struct *mm,
 			   unsigned long address,
 			   pte_t pte);
@@ -169,9 +169,9 @@ struct mmu_notifier_ops {
 	 * invalidate_range_end.
 	 *
 	 */
-	int (*invalidate_range_start)(struct mmu_notifier *mn,
+	int (*invalidate_range_start)(struct mmu_notifier *subscription,
 				      const struct mmu_notifier_range *range);
-	void (*invalidate_range_end)(struct mmu_notifier *mn,
+	void (*invalidate_range_end)(struct mmu_notifier *subscription,
 				     const struct mmu_notifier_range *range);
 
 	/*
@@ -192,8 +192,10 @@ struct mmu_notifier_ops {
 	 * of what was passed to invalidate_range_start()/end(), if
 	 * called between those functions.
 	 */
-	void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm,
-				 unsigned long start, unsigned long end);
+	void (*invalidate_range)(struct mmu_notifier *subscription,
+				 struct mm_struct *mm,
+				 unsigned long start,
+				 unsigned long end);
 
 	/*
 	 * These callbacks are used with the get/put interface to manage the
@@ -206,7 +208,7 @@ struct mmu_notifier_ops {
 	 * and cannot sleep.
 	 */
 	struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm);
-	void (*free_notifier)(struct mmu_notifier *mn);
+	void (*free_notifier)(struct mmu_notifier *subscription);
 };
 
 /*
@@ -235,7 +237,7 @@ struct mmu_notifier {
  *              was required but mmu_notifier_range_blockable(range) is false.
  */
 struct mmu_interval_notifier_ops {
-	bool (*invalidate)(struct mmu_interval_notifier *mni,
+	bool (*invalidate)(struct mmu_interval_notifier *interval_sub,
 			   const struct mmu_notifier_range *range,
 			   unsigned long cur_seq);
 };
@@ -265,7 +267,7 @@ struct mmu_notifier_range {
 
 static inline int mm_has_notifiers(struct mm_struct *mm)
 {
-	return unlikely(mm->mmu_notifier_mm);
+	return unlikely(mm->notifier_subscriptions);
 }
 
 struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops,
@@ -280,30 +282,31 @@ mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm)
 	up_write(&mm->mmap_sem);
 	return ret;
 }
-void mmu_notifier_put(struct mmu_notifier *mn);
+void mmu_notifier_put(struct mmu_notifier *subscription);
 void mmu_notifier_synchronize(void);
 
-extern int mmu_notifier_register(struct mmu_notifier *mn,
+extern int mmu_notifier_register(struct mmu_notifier *subscription,
 				 struct mm_struct *mm);
-extern int __mmu_notifier_register(struct mmu_notifier *mn,
+extern int __mmu_notifier_register(struct mmu_notifier *subscription,
 				   struct mm_struct *mm);
-extern void mmu_notifier_unregister(struct mmu_notifier *mn,
+extern void mmu_notifier_unregister(struct mmu_notifier *subscription,
 				    struct mm_struct *mm);
 
-unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni);
-int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni,
+unsigned long
+mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub);
+int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub,
 				 struct mm_struct *mm, unsigned long start,
 				 unsigned long length,
 				 const struct mmu_interval_notifier_ops *ops);
 int mmu_interval_notifier_insert_locked(
-	struct mmu_interval_notifier *mni, struct mm_struct *mm,
+	struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
 	unsigned long start, unsigned long length,
 	const struct mmu_interval_notifier_ops *ops);
-void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni);
+void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub);
 
 /**
  * mmu_interval_set_seq - Save the invalidation sequence
- * @mni - The mni passed to invalidate
+ * @interval_sub - The subscription passed to invalidate
  * @cur_seq - The cur_seq passed to the invalidate() callback
  *
  * This must be called unconditionally from the invalidate callback of a
@@ -314,15 +317,16 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni);
  * If the caller does not call mmu_interval_read_begin() or
  * mmu_interval_read_retry() then this call is not required.
  */
-static inline void mmu_interval_set_seq(struct mmu_interval_notifier *mni,
-					unsigned long cur_seq)
+static inline void
+mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub,
+		     unsigned long cur_seq)
 {
-	WRITE_ONCE(mni->invalidate_seq, cur_seq);
+	WRITE_ONCE(interval_sub->invalidate_seq, cur_seq);
 }
 
 /**
  * mmu_interval_read_retry - End a read side critical section against a VA range
- * mni: The range
+ * interval_sub: The subscription
  * seq: The return of the paired mmu_interval_read_begin()
  *
  * This MUST be called under a user provided lock that is also held
@@ -334,15 +338,16 @@ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *mni,
  * Returns true if an invalidation collided with this critical section, and
  * the caller should retry.
  */
-static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *mni,
-					   unsigned long seq)
+static inline bool
+mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub,
+			unsigned long seq)
 {
-	return mni->invalidate_seq != seq;
+	return interval_sub->invalidate_seq != seq;
 }
 
 /**
  * mmu_interval_check_retry - Test if a collision has occurred
- * mni: The range
+ * interval_sub: The subscription
  * seq: The return of the matching mmu_interval_read_begin()
  *
  * This can be used in the critical section between mmu_interval_read_begin()
@@ -357,14 +362,15 @@ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *mni,
  * This call can be used as part of loops and other expensive operations to
  * expedite a retry.
  */
-static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *mni,
-					    unsigned long seq)
+static inline bool
+mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub,
+			 unsigned long seq)
 {
 	/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
-	return READ_ONCE(mni->invalidate_seq) != seq;
+	return READ_ONCE(interval_sub->invalidate_seq) != seq;
 }
 
-extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
+extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm);
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					  unsigned long start,
@@ -480,15 +486,15 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 		__mmu_notifier_invalidate_range(mm, start, end);
 }
 
-static inline void mmu_notifier_mm_init(struct mm_struct *mm)
+static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
 {
-	mm->mmu_notifier_mm = NULL;
+	mm->notifier_subscriptions = NULL;
 }
 
-static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
+static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 {
 	if (mm_has_notifiers(mm))
-		__mmu_notifier_mm_destroy(mm);
+		__mmu_notifier_subscriptions_destroy(mm);
 }
 
 
@@ -692,11 +698,11 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 {
 }
 
-static inline void mmu_notifier_mm_init(struct mm_struct *mm)
+static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
 {
 }
 
-static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
+static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 {
 }
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5334ad8fc7bd..462f6873905a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -758,7 +758,7 @@ typedef struct pglist_data {
 
 #ifdef CONFIG_NUMA
 	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
+	 * node reclaim becomes active if more unmapped pages exist.
 	 */
 	unsigned long		min_unmapped_pages;
 	unsigned long		min_slab_pages;
@@ -1379,6 +1379,16 @@ static inline int pfn_present(unsigned long pfn)
 	return present_section(__nr_to_section(pfn_to_section_nr(pfn)));
 }
 
+static inline unsigned long next_present_section_nr(unsigned long section_nr)
+{
+	while (++section_nr <= __highest_present_section_nr) {
+		if (present_section_nr(section_nr))
+			return section_nr;
+	}
+
+	return -1;
+}
+
 /*
  * These are _only_ used during initialisation, therefore they
  * can use __initdata ...  They could have names to indicate
diff --git a/include/linux/module.h b/include/linux/module.h
index 0c7366c317bd..1ad393e62bef 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -170,6 +170,16 @@ extern void cleanup_module(void);
 #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep)
 
 /*
+ * MODULE_FILE is used for generating modules.builtin
+ * So, make it no-op when this is being built as a module
+ */
+#ifdef MODULE
+#define MODULE_FILE
+#else
+#define MODULE_FILE	MODULE_INFO(file, KBUILD_MODFILE);
+#endif
+
+/*
  * The following license idents are currently accepted as indicating free
  * software modules
  *
@@ -213,7 +223,7 @@ extern void cleanup_module(void);
  * 2.	So the community can ignore bug reports including proprietary modules
  * 3.	So vendors can do likewise based on their own policies
  */
-#define MODULE_LICENSE(_license) MODULE_INFO(license, _license)
+#define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license)
 
 /*
  * Author(s), use "Name <email>" or just "Name", for multiple
@@ -429,7 +439,7 @@ struct module {
 
 #ifdef CONFIG_KALLSYMS
 	/* Protected by RCU and/or module_mutex: use rcu_dereference() */
-	struct mod_kallsyms *kallsyms;
+	struct mod_kallsyms __rcu *kallsyms;
 	struct mod_kallsyms core_kallsyms;
 
 	/* Section attributes */
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index e5c3e23919b8..3ef917ff0964 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -128,6 +128,9 @@ struct kparam_array
 
 /**
  * module_param_unsafe - same as module_param but taints kernel
+ * @name: the variable to alter, and exposed parameter name.
+ * @type: the type of the parameter
+ * @perm: visibility in sysfs.
  */
 #define module_param_unsafe(name, type, perm)			\
 	module_param_named_unsafe(name, name, type, perm)
@@ -150,6 +153,10 @@ struct kparam_array
 
 /**
  * module_param_named_unsafe - same as module_param_named but taints kernel
+ * @name: a valid C identifier which is the parameter name.
+ * @value: the actual lvalue to alter.
+ * @type: the type of the parameter
+ * @perm: visibility in sysfs.
  */
 #define module_param_named_unsafe(name, value, type, perm)		\
 	param_check_##type(name, &(value));				\
@@ -160,6 +167,7 @@ struct kparam_array
  * module_param_cb - general callback for a module/cmdline parameter
  * @name: a valid C identifier which is the parameter name.
  * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
  * @perm: visibility in sysfs.
  *
  * The ops can have NULL set or get functions.
@@ -171,36 +179,96 @@ struct kparam_array
 	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, -1,    \
 			    KERNEL_PARAM_FL_UNSAFE)
 
+#define __level_param_cb(name, ops, arg, perm, level)			\
+	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level, 0)
 /**
- * <level>_param_cb - general callback for a module/cmdline parameter
- *                    to be evaluated before certain initcall level
+ * core_param_cb - general callback for a module/cmdline parameter
+ *                 to be evaluated before core initcall level
  * @name: a valid C identifier which is the parameter name.
  * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
  * @perm: visibility in sysfs.
  *
  * The ops can have NULL set or get functions.
  */
-#define __level_param_cb(name, ops, arg, perm, level)			\
-	__module_param_call(MODULE_PARAM_PREFIX, name, ops, arg, perm, level, 0)
-
 #define core_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 1)
 
+/**
+ * postcore_param_cb - general callback for a module/cmdline parameter
+ *                     to be evaluated before postcore initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
 #define postcore_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 2)
 
+/**
+ * arch_param_cb - general callback for a module/cmdline parameter
+ *                 to be evaluated before arch initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
 #define arch_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 3)
 
+/**
+ * subsys_param_cb - general callback for a module/cmdline parameter
+ *                   to be evaluated before subsys initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
 #define subsys_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 4)
 
+/**
+ * fs_param_cb - general callback for a module/cmdline parameter
+ *               to be evaluated before fs initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
 #define fs_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 5)
 
+/**
+ * device_param_cb - general callback for a module/cmdline parameter
+ *                   to be evaluated before device initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
 #define device_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 6)
 
+/**
+ * late_param_cb - general callback for a module/cmdline parameter
+ *                 to be evaluated before late initcall level
+ * @name: a valid C identifier which is the parameter name.
+ * @ops: the set & get operations for this parameter.
+ * @arg: args for @ops
+ * @perm: visibility in sysfs.
+ *
+ * The ops can have NULL set or get functions.
+ */
 #define late_param_cb(name, ops, arg, perm)		\
 	__level_param_cb(name, ops, arg, perm, 7)
 
@@ -263,6 +331,10 @@ static inline void kernel_param_unlock(struct module *mod)
 
 /**
  * core_param_unsafe - same as core_param but taints kernel
+ * @name: the name of the cmdline and sysfs parameter (often the same as var)
+ * @var: the variable
+ * @type: the type of the parameter
+ * @perm: visibility in sysfs
  */
 #define core_param_unsafe(name, var, type, perm)		\
 	param_check_##type(name, &(var));				\
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index 5a4623fc586b..5abd91cc6dfa 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -128,7 +128,8 @@
 #define SR_BP0			BIT(2)	/* Block protect 0 */
 #define SR_BP1			BIT(3)	/* Block protect 1 */
 #define SR_BP2			BIT(4)	/* Block protect 2 */
-#define SR_TB			BIT(5)	/* Top/Bottom protect */
+#define SR_TB_BIT5		BIT(5)	/* Top/Bottom protect */
+#define SR_TB_BIT6		BIT(6)	/* Top/Bottom protect */
 #define SR_SRWD			BIT(7)	/* SR write protect */
 /* Spansion/Cypress specific status bits */
 #define SR_E_ERR		BIT(5)
@@ -224,14 +225,6 @@ static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto)
 	return spi_nor_get_protocol_data_nbits(proto);
 }
 
-enum spi_nor_ops {
-	SPI_NOR_OPS_READ = 0,
-	SPI_NOR_OPS_WRITE,
-	SPI_NOR_OPS_ERASE,
-	SPI_NOR_OPS_LOCK,
-	SPI_NOR_OPS_UNLOCK,
-};
-
 enum spi_nor_option_flags {
 	SNOR_F_USE_FSR		= BIT(0),
 	SNOR_F_HAS_SR_TB	= BIT(1),
@@ -244,6 +237,7 @@ enum spi_nor_option_flags {
 	SNOR_F_HAS_LOCK		= BIT(8),
 	SNOR_F_HAS_16BIT_SR	= BIT(9),
 	SNOR_F_NO_READ_CR	= BIT(10),
+	SNOR_F_HAS_SR_TB_BIT6	= BIT(11),
 
 };
 
@@ -483,8 +477,8 @@ struct spi_nor;
  *			opcode via write_reg().
  */
 struct spi_nor_controller_ops {
-	int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops);
-	void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops);
+	int (*prepare)(struct spi_nor *nor);
+	void (*unprepare)(struct spi_nor *nor);
 	int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len);
 	int (*write_reg)(struct spi_nor *nor, u8 opcode, const u8 *buf,
 			 size_t len);
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 6861df759fad..572458016331 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype)
 #define MEMORY_OFFLINE	0x1
 #define REPORT_FAILURE	0x2
 
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
-			 int migratetype, int flags);
+struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+				 int migratetype, int flags);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype, int *num_movable);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 37a4d9e32cd3..ccb14b6a16b5 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -636,4 +636,32 @@ static inline unsigned long dir_pages(struct inode *inode)
 			       PAGE_SHIFT;
 }
 
+/**
+ * page_mkwrite_check_truncate - check if page was truncated
+ * @page: the page to check
+ * @inode: the inode to check the page against
+ *
+ * Returns the number of bytes in the page up to EOF,
+ * or -EFAULT if the page was truncated.
+ */
+static inline int page_mkwrite_check_truncate(struct page *page,
+					      struct inode *inode)
+{
+	loff_t size = i_size_read(inode);
+	pgoff_t index = size >> PAGE_SHIFT;
+	int offset = offset_in_page(size);
+
+	if (page->mapping != inode->i_mapping)
+		return -EFAULT;
+
+	/* page is wholly inside EOF */
+	if (page->index < index)
+		return PAGE_SIZE;
+	/* page is wholly past EOF */
+	if (page->index > index || !offset)
+		return -EFAULT;
+	/* page is partially inside EOF */
+	return offset;
+}
+
 #endif /* _LINUX_PAGEMAP_H */
diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 6ec82e92c87f..b1cb6b753abb 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -8,16 +8,19 @@ struct mm_walk;
 
 /**
  * mm_walk_ops - callbacks for walk_page_range
- * @pud_entry:		if set, called for each non-empty PUD (2nd-level) entry
- *			this handler should only handle pud_trans_huge() puds.
- *			the pmd_entry or pte_entry callbacks will be used for
- *			regular PUDs.
- * @pmd_entry:		if set, called for each non-empty PMD (3rd-level) entry
+ * @pgd_entry:		if set, called for each non-empty PGD (top-level) entry
+ * @p4d_entry:		if set, called for each non-empty P4D entry
+ * @pud_entry:		if set, called for each non-empty PUD entry
+ * @pmd_entry:		if set, called for each non-empty PMD entry
  *			this handler is required to be able to handle
  *			pmd_trans_huge() pmds.  They may simply choose to
  *			split_huge_page() instead of handling it explicitly.
- * @pte_entry:		if set, called for each non-empty PTE (4th-level) entry
- * @pte_hole:		if set, called for each hole at all levels
+ * @pte_entry:		if set, called for each non-empty PTE (lowest-level)
+ *			entry
+ * @pte_hole:		if set, called for each hole at all levels,
+ *			depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD
+ *			4:PTE. Any folded depths (where PTRS_PER_P?D is equal
+ *			to 1) are skipped.
  * @hugetlb_entry:	if set, called for each hugetlb entry
  * @test_walk:		caller specific callback function to determine whether
  *			we walk over the current vma or not. Returning 0 means
@@ -27,8 +30,15 @@ struct mm_walk;
  * @pre_vma:            if set, called before starting walk on a non-null vma.
  * @post_vma:           if set, called after a walk on a non-null vma, provided
  *                      that @pre_vma and the vma walk succeeded.
+ *
+ * p?d_entry callbacks are called even if those levels are folded on a
+ * particular architecture/configuration.
  */
 struct mm_walk_ops {
+	int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
+	int (*p4d_entry)(p4d_t *p4d, unsigned long addr,
+			 unsigned long next, struct mm_walk *walk);
 	int (*pud_entry)(pud_t *pud, unsigned long addr,
 			 unsigned long next, struct mm_walk *walk);
 	int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
@@ -36,7 +46,7 @@ struct mm_walk_ops {
 	int (*pte_entry)(pte_t *pte, unsigned long addr,
 			 unsigned long next, struct mm_walk *walk);
 	int (*pte_hole)(unsigned long addr, unsigned long next,
-			struct mm_walk *walk);
+			int depth, struct mm_walk *walk);
 	int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
 			     unsigned long addr, unsigned long next,
 			     struct mm_walk *walk);
@@ -47,11 +57,27 @@ struct mm_walk_ops {
 	void (*post_vma)(struct mm_walk *walk);
 };
 
+/*
+ * Action for pud_entry / pmd_entry callbacks.
+ * ACTION_SUBTREE is the default
+ */
+enum page_walk_action {
+	/* Descend to next level, splitting huge pages if needed and possible */
+	ACTION_SUBTREE = 0,
+	/* Continue to next entry at this level (ignoring any subtree) */
+	ACTION_CONTINUE = 1,
+	/* Call again for this entry */
+	ACTION_AGAIN = 2
+};
+
 /**
  * mm_walk - walk_page_range data
  * @ops:	operation to call during the walk
  * @mm:		mm_struct representing the target process of page table walk
+ * @pgd:	pointer to PGD; only valid with no_vma (otherwise set to NULL)
  * @vma:	vma currently walked (NULL if walking outside vmas)
+ * @action:	next action to perform (see enum page_walk_action)
+ * @no_vma:	walk ignoring vmas (vma will always be NULL)
  * @private:	private data for callbacks' usage
  *
  * (see the comment on walk_page_range() for more details)
@@ -59,13 +85,20 @@ struct mm_walk_ops {
 struct mm_walk {
 	const struct mm_walk_ops *ops;
 	struct mm_struct *mm;
+	pgd_t *pgd;
 	struct vm_area_struct *vma;
+	enum page_walk_action action;
+	bool no_vma;
 	void *private;
 };
 
 int walk_page_range(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  pgd_t *pgd,
+			  void *private);
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private);
 int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index 5d62e78946a3..d08f0869f121 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -33,6 +33,9 @@ void pci_disable_pasid(struct pci_dev *pdev);
 int pci_pasid_features(struct pci_dev *pdev);
 int pci_max_pasids(struct pci_dev *pdev);
 #else /* CONFIG_PCI_PASID */
+static inline int pci_enable_pasid(struct pci_dev *pdev, int features)
+{ return -EINVAL; }
+static inline void pci_disable_pasid(struct pci_dev *pdev) { }
 static inline int pci_pasid_features(struct pci_dev *pdev)
 { return -EINVAL; }
 static inline int pci_max_pasids(struct pci_dev *pdev)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c393dff2d66f..3840a541a9de 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1202,6 +1202,7 @@ int __must_check pci_resize_resource(struct pci_dev *dev, int i, int size);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
 bool pci_device_is_present(struct pci_dev *pdev);
 void pci_ignore_hotplug(struct pci_dev *dev);
+struct pci_dev *pci_real_dma_dev(struct pci_dev *dev);
 
 int __printf(6, 7) pci_request_irq(struct pci_dev *dev, unsigned int nr,
 		irq_handler_t handler, irq_handler_t thread_fn, void *dev_id,
@@ -2310,7 +2311,7 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev)
 }
 #endif
 
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn);
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns);
 bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2);
 int pci_for_each_dma_alias(struct pci_dev *pdev,
 			   int (*fn)(struct pci_dev *pdev,
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index a6fabd865211..176bfbd52d97 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -175,8 +175,7 @@
  * Declaration/definition used for per-CPU variables that should be accessed
  * as decrypted when memory encryption is enabled in the guest.
  */
-#if defined(CONFIG_VIRTUALIZATION) && defined(CONFIG_AMD_MEM_ENCRYPT)
-
+#ifdef CONFIG_AMD_MEM_ENCRYPT
 #define DECLARE_PER_CPU_DECRYPTED(type, name)				\
 	DECLARE_PER_CPU_SECTION(type, name, "..decrypted")
 
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 390031e816dc..22d9d183950d 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -210,15 +210,17 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 }
 
 /**
- * percpu_ref_tryget - try to increment a percpu refcount
+ * percpu_ref_tryget_many - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
+ * @nr: number of references to get
  *
- * Increment a percpu refcount unless its count already reached zero.
+ * Increment a percpu refcount  by @nr unless its count already reached zero.
  * Returns %true on success; %false on failure.
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline bool percpu_ref_tryget(struct percpu_ref *ref)
+static inline bool percpu_ref_tryget_many(struct percpu_ref *ref,
+					  unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 	bool ret;
@@ -226,10 +228,10 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 	rcu_read_lock();
 
 	if (__ref_is_percpu(ref, &percpu_count)) {
-		this_cpu_inc(*percpu_count);
+		this_cpu_add(*percpu_count, nr);
 		ret = true;
 	} else {
-		ret = atomic_long_inc_not_zero(&ref->count);
+		ret = atomic_long_add_unless(&ref->count, nr, 0);
 	}
 
 	rcu_read_unlock();
@@ -238,6 +240,20 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 }
 
 /**
+ * percpu_ref_tryget - try to increment a percpu refcount
+ * @ref: percpu_ref to try-get
+ *
+ * Increment a percpu refcount unless its count already reached zero.
+ * Returns %true on success; %false on failure.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline bool percpu_ref_tryget(struct percpu_ref *ref)
+{
+	return percpu_ref_tryget_many(ref, 1);
+}
+
+/**
  * percpu_ref_tryget_live - try to increment a live percpu refcount
  * @ref: percpu_ref to try-get
  *
diff --git a/include/linux/platform_data/bd6107.h b/include/linux/platform_data/bd6107.h
index 3bd019037eb3..54a06a4d2618 100644
--- a/include/linux/platform_data/bd6107.h
+++ b/include/linux/platform_data/bd6107.h
@@ -9,7 +9,6 @@ struct device;
 
 struct bd6107_platform_data {
 	struct device *fbdev;
-	int reset;			/* Reset GPIO */
 	unsigned int def_value;
 };
 
diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h
index 30098a551523..ba5914770191 100644
--- a/include/linux/platform_data/cros_ec_proto.h
+++ b/include/linux/platform_data/cros_ec_proto.h
@@ -12,7 +12,6 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 
-#include <linux/mfd/cros_ec.h>
 #include <linux/platform_data/cros_ec_commands.h>
 
 #define CROS_EC_DEV_NAME	"cros_ec"
@@ -185,9 +184,27 @@ struct cros_ec_platform {
 	u16 cmd_offset;
 };
 
-int cros_ec_suspend(struct cros_ec_device *ec_dev);
+/**
+ * struct cros_ec_dev - ChromeOS EC device entry point.
+ * @class_dev: Device structure used in sysfs.
+ * @ec_dev: cros_ec_device structure to talk to the physical device.
+ * @dev: Pointer to the platform device.
+ * @debug_info: cros_ec_debugfs structure for debugging information.
+ * @has_kb_wake_angle: True if at least 2 accelerometer are connected to the EC.
+ * @cmd_offset: Offset to apply for each command.
+ * @features: Features supported by the EC.
+ */
+struct cros_ec_dev {
+	struct device class_dev;
+	struct cros_ec_device *ec_dev;
+	struct device *dev;
+	struct cros_ec_debugfs *debug_info;
+	bool has_kb_wake_angle;
+	u16 cmd_offset;
+	u32 features[2];
+};
 
-int cros_ec_resume(struct cros_ec_device *ec_dev);
+#define to_cros_ec_dev(dev)  container_of(dev, struct cros_ec_dev, class_dev)
 
 int cros_ec_prepare_tx(struct cros_ec_device *ec_dev,
 		       struct cros_ec_command *msg);
@@ -201,10 +218,6 @@ int cros_ec_cmd_xfer(struct cros_ec_device *ec_dev,
 int cros_ec_cmd_xfer_status(struct cros_ec_device *ec_dev,
 			    struct cros_ec_command *msg);
 
-int cros_ec_register(struct cros_ec_device *ec_dev);
-
-int cros_ec_unregister(struct cros_ec_device *ec_dev);
-
 int cros_ec_query_all(struct cros_ec_device *ec_dev);
 
 int cros_ec_get_next_event(struct cros_ec_device *ec_dev,
@@ -217,8 +230,6 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature);
 
 int cros_ec_get_sensor_count(struct cros_ec_dev *ec);
 
-bool cros_ec_handle_event(struct cros_ec_device *ec_dev);
-
 /**
  * cros_ec_get_time_ns() - Return time in ns.
  *
diff --git a/include/linux/platform_data/tc35876x.h b/include/linux/platform_data/tc35876x.h
deleted file mode 100644
index cd6a51c71e7e..000000000000
--- a/include/linux/platform_data/tc35876x.h
+++ /dev/null
@@ -1,11 +0,0 @@
-
-#ifndef _TC35876X_H
-#define _TC35876X_H
-
-struct tc35876x_platform_data {
-	int gpio_bridge_reset;
-	int gpio_panel_bl_en;
-	int gpio_panel_vadd;
-};
-
-#endif /* _TC35876X_H */
diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h
index 4badd5322949..d55c746ac56e 100644
--- a/include/linux/power/max17042_battery.h
+++ b/include/linux/power/max17042_battery.h
@@ -105,11 +105,56 @@ enum max17042_register {
 
 	MAX17042_OCV		= 0xEE,
 
-	MAX17042_OCVInternal	= 0xFB,
+	MAX17042_OCVInternal	= 0xFB,  /* MAX17055 VFOCV */
 
 	MAX17042_VFSOC		= 0xFF,
 };
 
+enum max17055_register {
+	MAX17055_QRes		= 0x0C,
+	MAX17055_TTF		= 0x20,
+	MAX17055_V_empty	= 0x3A,
+	MAX17055_TIMER		= 0x3E,
+	MAX17055_USER_MEM	= 0x40,
+	MAX17055_RGAIN		= 0x42,
+
+	MAX17055_ConvgCfg	= 0x49,
+	MAX17055_VFRemCap	= 0x4A,
+
+	MAX17055_STATUS2	= 0xB0,
+	MAX17055_POWER		= 0xB1,
+	MAX17055_ID		= 0xB2,
+	MAX17055_AvgPower	= 0xB3,
+	MAX17055_IAlrtTh	= 0xB4,
+	MAX17055_TTFCfg		= 0xB5,
+	MAX17055_CVMixCap	= 0xB6,
+	MAX17055_CVHalfTime	= 0xB7,
+	MAX17055_CGTempCo	= 0xB8,
+	MAX17055_Curve		= 0xB9,
+	MAX17055_HibCfg		= 0xBA,
+	MAX17055_Config2	= 0xBB,
+	MAX17055_VRipple	= 0xBC,
+	MAX17055_RippleCfg	= 0xBD,
+	MAX17055_TimerH		= 0xBE,
+
+	MAX17055_RSense		= 0xD0,
+	MAX17055_ScOcvLim	= 0xD1,
+
+	MAX17055_SOCHold	= 0xD3,
+	MAX17055_MaxPeakPwr	= 0xD4,
+	MAX17055_SusPeakPwr	= 0xD5,
+	MAX17055_PackResistance	= 0xD6,
+	MAX17055_SysResistance	= 0xD7,
+	MAX17055_MinSysV	= 0xD8,
+	MAX17055_MPPCurrent	= 0xD9,
+	MAX17055_SPPCurrent	= 0xDA,
+	MAX17055_ModelCfg	= 0xDB,
+	MAX17055_AtQResidual	= 0xDC,
+	MAX17055_AtTTE		= 0xDD,
+	MAX17055_AtAvSOC	= 0xDE,
+	MAX17055_AtAvCap	= 0xDF,
+};
+
 /* Registers specific to max17047/50 */
 enum max17047_register {
 	MAX17047_QRTbl00	= 0x12,
@@ -125,6 +170,7 @@ enum max170xx_chip_type {
 	MAXIM_DEVICE_TYPE_MAX17042,
 	MAXIM_DEVICE_TYPE_MAX17047,
 	MAXIM_DEVICE_TYPE_MAX17050,
+	MAXIM_DEVICE_TYPE_MAX17055,
 
 	MAXIM_DEVICE_TYPE_NUM
 };
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 28413f737e7d..dcd5a71e6c67 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -325,6 +325,11 @@ struct power_supply_battery_ocv_table {
 	int capacity;	/* percent */
 };
 
+struct power_supply_resistance_temp_table {
+	int temp;	/* celsius */
+	int resistance;	/* internal resistance percent */
+};
+
 #define POWER_SUPPLY_OCV_TEMP_MAX 20
 
 /*
@@ -349,6 +354,8 @@ struct power_supply_battery_info {
 	int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX];/* celsius */
 	struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX];
 	int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX];
+	struct power_supply_resistance_temp_table *resist_table;
+	int resist_table_size;
 };
 
 extern struct atomic_notifier_head power_supply_notifier;
@@ -381,6 +388,9 @@ power_supply_find_ocv2cap_table(struct power_supply_battery_info *info,
 				int temp, int *table_len);
 extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info,
 					int ocv, int temp);
+extern int
+power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table,
+				int table_len, int temp);
 extern void power_supply_changed(struct power_supply *psy);
 extern int power_supply_am_i_supplied(struct power_supply *psy);
 extern int power_supply_set_input_current_limit_from_supplier(
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 0640be56dcbd..3dfa92633af3 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -12,6 +12,21 @@ struct proc_dir_entry;
 struct seq_file;
 struct seq_operations;
 
+struct proc_ops {
+	int	(*proc_open)(struct inode *, struct file *);
+	ssize_t	(*proc_read)(struct file *, char __user *, size_t, loff_t *);
+	ssize_t	(*proc_write)(struct file *, const char __user *, size_t, loff_t *);
+	loff_t	(*proc_lseek)(struct file *, loff_t, int);
+	int	(*proc_release)(struct inode *, struct file *);
+	__poll_t (*proc_poll)(struct file *, struct poll_table_struct *);
+	long	(*proc_ioctl)(struct file *, unsigned int, unsigned long);
+#ifdef CONFIG_COMPAT
+	long	(*proc_compat_ioctl)(struct file *, unsigned int, unsigned long);
+#endif
+	int	(*proc_mmap)(struct file *, struct vm_area_struct *);
+	unsigned long (*proc_get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+};
+
 #ifdef CONFIG_PROC_FS
 
 typedef int (*proc_write_t)(struct file *, char *, size_t);
@@ -43,10 +58,10 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
  
 extern struct proc_dir_entry *proc_create_data(const char *, umode_t,
 					       struct proc_dir_entry *,
-					       const struct file_operations *,
+					       const struct proc_ops *,
 					       void *);
 
-struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops);
+struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops);
 extern void proc_set_size(struct proc_dir_entry *, loff_t);
 extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t);
 extern void *PDE_DATA(const struct inode *);
@@ -108,8 +123,8 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name,
 #define proc_create_seq(name, mode, parent, ops) ({NULL;})
 #define proc_create_single(name, mode, parent, show) ({NULL;})
 #define proc_create_single_data(name, mode, parent, show, data) ({NULL;})
-#define proc_create(name, mode, parent, proc_fops) ({NULL;})
-#define proc_create_data(name, mode, parent, proc_fops, data) ({NULL;})
+#define proc_create(name, mode, parent, proc_ops) ({NULL;})
+#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;})
 
 static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {}
 static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {}
diff --git a/include/linux/ptdump.h b/include/linux/ptdump.h
new file mode 100644
index 000000000000..a67065c403c3
--- /dev/null
+++ b/include/linux/ptdump.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PTDUMP_H
+#define _LINUX_PTDUMP_H
+
+#include <linux/mm_types.h>
+
+struct ptdump_range {
+	unsigned long start;
+	unsigned long end;
+};
+
+struct ptdump_state {
+	/* level is 0:PGD to 4:PTE, or -1 if unknown */
+	void (*note_page)(struct ptdump_state *st, unsigned long addr,
+			  int level, unsigned long val);
+	const struct ptdump_range *range;
+};
+
+void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd);
+
+#endif /* _LINUX_PTDUMP_H */
diff --git a/include/linux/random.h b/include/linux/random.h
index f189c927fdea..d319f9a1e429 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -167,29 +167,21 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 #ifdef CONFIG_ARCH_RANDOM
 # include <asm/archrandom.h>
 #else
-static inline bool arch_get_random_long(unsigned long *v)
+static inline bool __must_check arch_get_random_long(unsigned long *v)
 {
-	return 0;
+	return false;
 }
-static inline bool arch_get_random_int(unsigned int *v)
+static inline bool __must_check arch_get_random_int(unsigned int *v)
 {
-	return 0;
+	return false;
 }
-static inline bool arch_has_random(void)
+static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
-	return 0;
+	return false;
 }
-static inline bool arch_get_random_seed_long(unsigned long *v)
+static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
-	return 0;
-}
-static inline bool arch_get_random_seed_int(unsigned int *v)
-{
-	return 0;
-}
-static inline bool arch_has_random_seed(void)
-{
-	return 0;
+	return false;
 }
 #endif
 
diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h
new file mode 100644
index 000000000000..b47416f7aeb8
--- /dev/null
+++ b/include/linux/remoteproc/mtk_scp.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019 MediaTek Inc.
+ */
+
+#ifndef _MTK_SCP_H
+#define _MTK_SCP_H
+
+#include <linux/platform_device.h>
+
+typedef void (*scp_ipi_handler_t) (void *data,
+				   unsigned int len,
+				   void *priv);
+struct mtk_scp;
+
+/**
+ * enum ipi_id - the id of inter-processor interrupt
+ *
+ * @SCP_IPI_INIT:	 The interrupt from scp is to notfiy kernel
+ *			 SCP initialization completed.
+ *			 IPI_SCP_INIT is sent from SCP when firmware is
+ *			 loaded. AP doesn't need to send IPI_SCP_INIT
+ *			 command to SCP.
+ *			 For other IPI below, AP should send the request
+ *			 to SCP to trigger the interrupt.
+ * @SCP_IPI_MAX:	 The maximum IPI number
+ */
+
+enum scp_ipi_id {
+	SCP_IPI_INIT = 0,
+	SCP_IPI_VDEC_H264,
+	SCP_IPI_VDEC_VP8,
+	SCP_IPI_VDEC_VP9,
+	SCP_IPI_VENC_H264,
+	SCP_IPI_VENC_VP8,
+	SCP_IPI_MDP_INIT,
+	SCP_IPI_MDP_DEINIT,
+	SCP_IPI_MDP_FRAME,
+	SCP_IPI_DIP,
+	SCP_IPI_ISP_CMD,
+	SCP_IPI_ISP_FRAME,
+	SCP_IPI_FD_CMD,
+	SCP_IPI_CROS_HOST_CMD,
+	SCP_IPI_NS_SERVICE = 0xFF,
+	SCP_IPI_MAX = 0x100,
+};
+
+struct mtk_scp *scp_get(struct platform_device *pdev);
+void scp_put(struct mtk_scp *scp);
+
+struct device *scp_get_device(struct mtk_scp *scp);
+struct rproc *scp_get_rproc(struct mtk_scp *scp);
+
+int scp_ipi_register(struct mtk_scp *scp, u32 id, scp_ipi_handler_t handler,
+		     void *priv);
+void scp_ipi_unregister(struct mtk_scp *scp, u32 id);
+
+int scp_ipi_send(struct mtk_scp *scp, u32 id, void *buf, unsigned int len,
+		 unsigned int wait);
+
+unsigned int scp_get_vdec_hw_capa(struct mtk_scp *scp);
+unsigned int scp_get_venc_hw_capa(struct mtk_scp *scp);
+
+void *scp_mapping_dm_addr(struct mtk_scp *scp, u32 mem_addr);
+
+#endif /* _MTK_SCP_H */
diff --git a/include/linux/rpmsg/mtk_rpmsg.h b/include/linux/rpmsg/mtk_rpmsg.h
new file mode 100644
index 000000000000..363b60178040
--- /dev/null
+++ b/include/linux/rpmsg/mtk_rpmsg.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC.
+ */
+
+#ifndef __LINUX_RPMSG_MTK_RPMSG_H
+#define __LINUX_RPMSG_MTK_RPMSG_H
+
+#include <linux/platform_device.h>
+#include <linux/remoteproc.h>
+
+typedef void (*ipi_handler_t)(void *data, unsigned int len, void *priv);
+
+/*
+ * struct mtk_rpmsg_info - IPI functions tied to the rpmsg device.
+ * @register_ipi: register IPI handler for an IPI id.
+ * @unregister_ipi: unregister IPI handler for a registered IPI id.
+ * @send_ipi: send IPI to an IPI id. wait is the timeout (in msecs) to wait
+ *            until response, or 0 if there's no timeout.
+ * @ns_ipi_id: the IPI id used for name service, or -1 if name service isn't
+ *             supported.
+ */
+struct mtk_rpmsg_info {
+	int (*register_ipi)(struct platform_device *pdev, u32 id,
+			    ipi_handler_t handler, void *priv);
+	void (*unregister_ipi)(struct platform_device *pdev, u32 id);
+	int (*send_ipi)(struct platform_device *pdev, u32 id,
+			void *buf, unsigned int len, unsigned int wait);
+	int ns_ipi_id;
+};
+
+struct rproc_subdev *
+mtk_rpmsg_create_rproc_subdev(struct platform_device *pdev,
+			      struct mtk_rpmsg_info *info);
+
+void mtk_rpmsg_destroy_rproc_subdev(struct rproc_subdev *subdev);
+
+#endif
diff --git a/include/linux/rtc.h b/include/linux/rtc.h
index 4e9d3c71addb..23990bd29040 100644
--- a/include/linux/rtc.h
+++ b/include/linux/rtc.h
@@ -167,6 +167,7 @@ struct rtc_device {
 #define RTC_TIMESTAMP_BEGIN_1900	-2208988800LL /* 1900-01-01 00:00:00 */
 #define RTC_TIMESTAMP_BEGIN_2000	946684800LL /* 2000-01-01 00:00:00 */
 #define RTC_TIMESTAMP_END_2063		2966371199LL /* 2063-12-31 23:59:59 */
+#define RTC_TIMESTAMP_END_2079		3471292799LL /* 2079-12-31 23:59:59 */
 #define RTC_TIMESTAMP_END_2099		4102444799LL /* 2099-12-31 23:59:59 */
 #define RTC_TIMESTAMP_END_2199		7258118399LL /* 2199-12-31 23:59:59 */
 #define RTC_TIMESTAMP_END_9999		253402300799LL /* 9999-12-31 23:59:59 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 716ad1d8d95e..04278493bf15 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -917,7 +917,7 @@ struct task_struct {
 
 	/* Signal handlers: */
 	struct signal_struct		*signal;
-	struct sighand_struct		*sighand;
+	struct sighand_struct __rcu		*sighand;
 	sigset_t			blocked;
 	sigset_t			real_blocked;
 	/* Restored if set_restore_sigmask() was used: */
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index 5998e1f4ff06..770c2bf3aa43 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -160,6 +160,19 @@ static const struct file_operations __name ## _fops = {			\
 	.release	= single_release,				\
 }
 
+#define DEFINE_PROC_SHOW_ATTRIBUTE(__name)				\
+static int __name ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __name ## _show, inode->i_private);	\
+}									\
+									\
+static const struct proc_ops __name ## _proc_ops = {			\
+	.proc_open	= __name ## _open,				\
+	.proc_read	= seq_read,					\
+	.proc_lseek	= seq_lseek,					\
+	.proc_release	= single_release,				\
+}
+
 static inline struct user_namespace *seq_user_ns(struct seq_file *seq)
 {
 #ifdef CONFIG_USER_NS
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 877a95c6a2d2..03a389358562 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -184,7 +184,6 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *, struct mem_cgroup *);
 /*
  * Common kmalloc functions provided by all allocators
  */
-void * __must_check __krealloc(const void *, size_t, gfp_t);
 void * __must_check krealloc(const void *, size_t, gfp_t);
 void kfree(const void *);
 void kzfree(const void *);
diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h
index 9618debb9ceb..a74c1d5acdf3 100644
--- a/include/linux/soc/mediatek/mtk-cmdq.h
+++ b/include/linux/soc/mediatek/mtk-cmdq.h
@@ -15,6 +15,12 @@
 
 struct cmdq_pkt;
 
+struct cmdq_client_reg {
+	u8 subsys;
+	u16 offset;
+	u16 size;
+};
+
 struct cmdq_client {
 	spinlock_t lock;
 	u32 pkt_cnt;
@@ -25,6 +31,21 @@ struct cmdq_client {
 };
 
 /**
+ * cmdq_dev_get_client_reg() - parse cmdq client reg from the device
+ *			       node of CMDQ client
+ * @dev:	device of CMDQ mailbox client
+ * @client_reg: CMDQ client reg pointer
+ * @idx:	the index of desired reg
+ *
+ * Return: 0 for success; else the error code is returned
+ *
+ * Help CMDQ client parsing the cmdq client reg
+ * from the device node of CMDQ client.
+ */
+int cmdq_dev_get_client_reg(struct device *dev,
+			    struct cmdq_client_reg *client_reg, int idx);
+
+/**
  * cmdq_mbox_create() - create CMDQ mailbox client and channel
  * @dev:	device of CMDQ mailbox client
  * @index:	index of CMDQ mailbox channel
@@ -100,6 +121,38 @@ int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event);
 int cmdq_pkt_clear_event(struct cmdq_pkt *pkt, u16 event);
 
 /**
+ * cmdq_pkt_poll() - Append polling command to the CMDQ packet, ask GCE to
+ *		     execute an instruction that wait for a specified
+ *		     hardware register to check for the value w/o mask.
+ *		     All GCE hardware threads will be blocked by this
+ *		     instruction.
+ * @pkt:	the CMDQ packet
+ * @subsys:	the CMDQ sub system code
+ * @offset:	register offset from CMDQ sub system
+ * @value:	the specified target register value
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_poll(struct cmdq_pkt *pkt, u8 subsys,
+		  u16 offset, u32 value);
+
+/**
+ * cmdq_pkt_poll_mask() - Append polling command to the CMDQ packet, ask GCE to
+ *		          execute an instruction that wait for a specified
+ *		          hardware register to check for the value w/ mask.
+ *		          All GCE hardware threads will be blocked by this
+ *		          instruction.
+ * @pkt:	the CMDQ packet
+ * @subsys:	the CMDQ sub system code
+ * @offset:	register offset from CMDQ sub system
+ * @value:	the specified target register value
+ * @mask:	the specified target register mask
+ *
+ * Return: 0 for success; else the error code is returned
+ */
+int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys,
+		       u16 offset, u32 value, u32 mask);
+/**
  * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ
  *                          packet and call back at the end of done packet
  * @pkt:	the CMDQ packet
diff --git a/include/linux/soc/mediatek/mtk_sip_svc.h b/include/linux/soc/mediatek/mtk_sip_svc.h
new file mode 100644
index 000000000000..082398e0cfb1
--- /dev/null
+++ b/include/linux/soc/mediatek/mtk_sip_svc.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 MediaTek Inc.
+ */
+#ifndef __MTK_SIP_SVC_H
+#define __MTK_SIP_SVC_H
+
+/* Error Code */
+#define SIP_SVC_E_SUCCESS               0
+#define SIP_SVC_E_NOT_SUPPORTED         -1
+#define SIP_SVC_E_INVALID_PARAMS        -2
+#define SIP_SVC_E_INVALID_RANGE         -3
+#define SIP_SVC_E_PERMISSION_DENIED     -4
+
+#ifdef CONFIG_ARM64
+#define MTK_SIP_SMC_CONVENTION          ARM_SMCCC_SMC_64
+#else
+#define MTK_SIP_SMC_CONVENTION          ARM_SMCCC_SMC_32
+#endif
+
+#define MTK_SIP_SMC_CMD(fn_id) \
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, MTK_SIP_SMC_CONVENTION, \
+			   ARM_SMCCC_OWNER_SIP, fn_id)
+
+#endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 02894e417565..6dfbb2efa815 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -62,6 +62,7 @@ extern char * strchr(const char *,int);
 #ifndef __HAVE_ARCH_STRCHRNUL
 extern char * strchrnul(const char *,int);
 #endif
+extern char * strnchrnul(const char *, size_t, int);
 #ifndef __HAVE_ARCH_STRNCHR
 extern char * strnchr(const char *, size_t, int);
 #endif
diff --git a/include/linux/sunrpc/stats.h b/include/linux/sunrpc/stats.h
index 84b92b4ad1c0..d94d4f410507 100644
--- a/include/linux/sunrpc/stats.h
+++ b/include/linux/sunrpc/stats.h
@@ -63,7 +63,7 @@ struct proc_dir_entry *	rpc_proc_register(struct net *,struct rpc_stat *);
 void			rpc_proc_unregister(struct net *,const char *);
 void			rpc_proc_zero(const struct rpc_program *);
 struct proc_dir_entry *	svc_proc_register(struct net *, struct svc_stat *,
-					  const struct file_operations *);
+					  const struct proc_ops *);
 void			svc_proc_unregister(struct net *, const char *);
 
 void			svc_seq_show(struct seq_file *,
@@ -75,7 +75,7 @@ static inline void rpc_proc_unregister(struct net *net, const char *p) {}
 static inline void rpc_proc_zero(const struct rpc_program *p) {}
 
 static inline struct proc_dir_entry *svc_proc_register(struct net *net, struct svc_stat *s,
-						       const struct file_operations *f) { return NULL; }
+						       const struct proc_ops *proc_ops) { return NULL; }
 static inline void svc_proc_unregister(struct net *net, const char *p) {}
 
 static inline void svc_seq_show(struct seq_file *seq,
diff --git a/include/linux/swab.h b/include/linux/swab.h
index e466fd159c85..bcff5149861a 100644
--- a/include/linux/swab.h
+++ b/include/linux/swab.h
@@ -7,6 +7,7 @@
 # define swab16 __swab16
 # define swab32 __swab32
 # define swab64 __swab64
+# define swab __swab
 # define swahw32 __swahw32
 # define swahb32 __swahb32
 # define swab16p __swab16p
diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h
index e295515bc3f3..082f1d51957a 100644
--- a/include/linux/switchtec.h
+++ b/include/linux/switchtec.h
@@ -21,6 +21,11 @@
 #define SWITCHTEC_EVENT_FATAL    BIT(4)
 
 #define SWITCHTEC_DMA_MRPC_EN	BIT(0)
+
+#define MRPC_GAS_READ		0x29
+#define MRPC_GAS_WRITE		0x87
+#define MRPC_CMD_ID(x)		((x) & 0xffff)
+
 enum {
 	SWITCHTEC_GAS_MRPC_OFFSET       = 0x0000,
 	SWITCHTEC_GAS_TOP_CFG_OFFSET    = 0x1000,
@@ -32,6 +37,11 @@ enum {
 	SWITCHTEC_GAS_PFF_CSR_OFFSET    = 0x134000,
 };
 
+enum switchtec_gen {
+	SWITCHTEC_GEN3,
+	SWITCHTEC_GEN4,
+};
+
 struct mrpc_regs {
 	u8 input_data[SWITCHTEC_MRPC_PAYLOAD_SIZE];
 	u8 output_data[SWITCHTEC_MRPC_PAYLOAD_SIZE];
@@ -98,16 +108,37 @@ struct sw_event_regs {
 } __packed;
 
 enum {
-	SWITCHTEC_CFG0_RUNNING = 0x04,
-	SWITCHTEC_CFG1_RUNNING = 0x05,
-	SWITCHTEC_IMG0_RUNNING = 0x03,
-	SWITCHTEC_IMG1_RUNNING = 0x07,
+	SWITCHTEC_GEN3_CFG0_RUNNING = 0x04,
+	SWITCHTEC_GEN3_CFG1_RUNNING = 0x05,
+	SWITCHTEC_GEN3_IMG0_RUNNING = 0x03,
+	SWITCHTEC_GEN3_IMG1_RUNNING = 0x07,
 };
 
-struct sys_info_regs {
-	u32 device_id;
-	u32 device_version;
-	u32 firmware_version;
+enum {
+	SWITCHTEC_GEN4_MAP0_RUNNING = 0x00,
+	SWITCHTEC_GEN4_MAP1_RUNNING = 0x01,
+	SWITCHTEC_GEN4_KEY0_RUNNING = 0x02,
+	SWITCHTEC_GEN4_KEY1_RUNNING = 0x03,
+	SWITCHTEC_GEN4_BL2_0_RUNNING = 0x04,
+	SWITCHTEC_GEN4_BL2_1_RUNNING = 0x05,
+	SWITCHTEC_GEN4_CFG0_RUNNING = 0x06,
+	SWITCHTEC_GEN4_CFG1_RUNNING = 0x07,
+	SWITCHTEC_GEN4_IMG0_RUNNING = 0x08,
+	SWITCHTEC_GEN4_IMG1_RUNNING = 0x09,
+};
+
+enum {
+	SWITCHTEC_GEN4_KEY0_ACTIVE = 0,
+	SWITCHTEC_GEN4_KEY1_ACTIVE = 1,
+	SWITCHTEC_GEN4_BL2_0_ACTIVE = 0,
+	SWITCHTEC_GEN4_BL2_1_ACTIVE = 1,
+	SWITCHTEC_GEN4_CFG0_ACTIVE = 0,
+	SWITCHTEC_GEN4_CFG1_ACTIVE = 1,
+	SWITCHTEC_GEN4_IMG0_ACTIVE = 0,
+	SWITCHTEC_GEN4_IMG1_ACTIVE = 1,
+};
+
+struct sys_info_regs_gen3 {
 	u32 reserved1;
 	u32 vendor_table_revision;
 	u32 table_format_version;
@@ -124,26 +155,105 @@ struct sys_info_regs {
 	u8 component_revision;
 } __packed;
 
-struct flash_info_regs {
+struct sys_info_regs_gen4 {
+	u16 gas_layout_ver;
+	u8 evlist_ver;
+	u8 reserved1;
+	u16 mgmt_cmd_set_ver;
+	u16 fabric_cmd_set_ver;
+	u32 reserved2[2];
+	u8 mrpc_uart_ver;
+	u8 mrpc_twi_ver;
+	u8 mrpc_eth_ver;
+	u8 mrpc_inband_ver;
+	u32 reserved3[7];
+	u32 fw_update_tmo;
+	u32 xml_version_cfg;
+	u32 xml_version_img;
+	u32 partition_id;
+	u16 bl2_running;
+	u16 cfg_running;
+	u16 img_running;
+	u16 key_running;
+	u32 reserved4[43];
+	u32 vendor_seeprom_twi;
+	u32 vendor_table_revision;
+	u32 vendor_specific_info[2];
+	u16 p2p_vendor_id;
+	u16 p2p_device_id;
+	u8 p2p_revision_id;
+	u8 reserved5[3];
+	u32 p2p_class_id;
+	u16 subsystem_vendor_id;
+	u16 subsystem_id;
+	u32 p2p_serial_number[2];
+	u8 mac_addr[6];
+	u8 reserved6[2];
+	u32 reserved7[3];
+	char vendor_id[8];
+	char product_id[24];
+	char  product_revision[2];
+	u16 reserved8;
+} __packed;
+
+struct sys_info_regs {
+	u32 device_id;
+	u32 device_version;
+	u32 firmware_version;
+	union {
+		struct sys_info_regs_gen3 gen3;
+		struct sys_info_regs_gen4 gen4;
+	};
+} __packed;
+
+struct partition_info {
+	u32 address;
+	u32 length;
+};
+
+struct flash_info_regs_gen3 {
 	u32 flash_part_map_upd_idx;
 
-	struct active_partition_info {
+	struct active_partition_info_gen3 {
 		u32 address;
 		u32 build_version;
 		u32 build_string;
 	} active_img;
 
-	struct active_partition_info active_cfg;
-	struct active_partition_info inactive_img;
-	struct active_partition_info inactive_cfg;
+	struct active_partition_info_gen3 active_cfg;
+	struct active_partition_info_gen3 inactive_img;
+	struct active_partition_info_gen3 inactive_cfg;
 
 	u32 flash_length;
 
-	struct partition_info {
-		u32 address;
-		u32 length;
-	} cfg0;
+	struct partition_info cfg0;
+	struct partition_info cfg1;
+	struct partition_info img0;
+	struct partition_info img1;
+	struct partition_info nvlog;
+	struct partition_info vendor[8];
+};
 
+struct flash_info_regs_gen4 {
+	u32 flash_address;
+	u32 flash_length;
+
+	struct active_partition_info_gen4 {
+		unsigned char bl2;
+		unsigned char cfg;
+		unsigned char img;
+		unsigned char key;
+	} active_flag;
+
+	u32 reserved[3];
+
+	struct partition_info map0;
+	struct partition_info map1;
+	struct partition_info key0;
+	struct partition_info key1;
+	struct partition_info bl2_0;
+	struct partition_info bl2_1;
+	struct partition_info cfg0;
 	struct partition_info cfg1;
 	struct partition_info img0;
 	struct partition_info img1;
@@ -151,6 +261,13 @@ struct flash_info_regs {
 	struct partition_info vendor[8];
 };
 
+struct flash_info_regs {
+	union {
+		struct flash_info_regs_gen3 gen3;
+		struct flash_info_regs_gen4 gen4;
+	};
+};
+
 enum {
 	SWITCHTEC_NTB_REG_INFO_OFFSET   = 0x0000,
 	SWITCHTEC_NTB_REG_CTRL_OFFSET   = 0x4000,
@@ -196,7 +313,9 @@ struct part_cfg_regs {
 	u32 mrpc_comp_async_data[5];
 	u32 dyn_binding_hdr;
 	u32 dyn_binding_data[5];
-	u32 reserved4[159];
+	u32 intercomm_notify_hdr;
+	u32 intercomm_notify_data[5];
+	u32 reserved4[153];
 } __packed;
 
 enum {
@@ -320,7 +439,8 @@ struct pff_csr_regs {
 	u32 dpc_data[5];
 	u32 cts_hdr;
 	u32 cts_data[5];
-	u32 reserved3[6];
+	u32 uec_hdr;
+	u32 uec_data[5];
 	u32 hotplug_hdr;
 	u32 hotplug_data[5];
 	u32 ier_hdr;
@@ -355,6 +475,8 @@ struct switchtec_dev {
 	struct device dev;
 	struct cdev cdev;
 
+	enum switchtec_gen gen;
+
 	int partition;
 	int partition_count;
 	int pff_csr_count;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index ac3a663137b6..1815065d52f3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1002,6 +1002,7 @@ asmlinkage long sys_fspick(int dfd, const char __user *path, unsigned int flags)
 asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 				       siginfo_t __user *info,
 				       unsigned int flags);
+asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
 
 /*
  * Architecture-specific system calls
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1cf73e6f85ca..3dc964010fef 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -148,9 +148,7 @@ struct tcp_request_sock {
 	const struct tcp_request_sock_ops *af_specific;
 	u64				snt_synack; /* first SYNACK sent time */
 	bool				tfo_listener;
-#if IS_ENABLED(CONFIG_MPTCP)
 	bool				is_mptcp;
-#endif
 	u32				txhash;
 	u32				rcv_isn;
 	u32				snt_isn;
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index d9111aebb97d..126913c6a53b 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -32,17 +32,6 @@
 /* use value, which < 0K, to indicate an invalid/uninitialized temperature */
 #define THERMAL_TEMP_INVALID	-274000
 
-/* Unit conversion macros */
-#define DECI_KELVIN_TO_CELSIUS(t)	({			\
-	long _t = (t);						\
-	((_t-2732 >= 0) ? (_t-2732+5)/10 : (_t-2732-5)/10);	\
-})
-#define CELSIUS_TO_DECI_KELVIN(t)	((t)*10+2732)
-#define DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, off) (((t) - (off)) * 100)
-#define DECI_KELVIN_TO_MILLICELSIUS(t) DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, 2732)
-#define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off))
-#define MILLICELSIUS_TO_DECI_KELVIN(t) MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, 2732)
-
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
 #define DEFAULT_THERMAL_GOVERNOR       "step_wise"
diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h
index 88d279c1b863..99912445974c 100644
--- a/include/linux/tracefs.h
+++ b/include/linux/tracefs.h
@@ -28,7 +28,6 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 struct dentry *tracefs_create_dir(const char *name, struct dentry *parent);
 
 void tracefs_remove(struct dentry *dentry);
-void tracefs_remove_recursive(struct dentry *dentry);
 
 struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *parent,
 					   int (*mkdir)(const char *name),
diff --git a/include/linux/transport_class.h b/include/linux/transport_class.h
index a9c59761927b..63076fb835e3 100644
--- a/include/linux/transport_class.h
+++ b/include/linux/transport_class.h
@@ -62,16 +62,16 @@ struct transport_container {
 	container_of(x, struct transport_container, ac)
 
 void transport_remove_device(struct device *);
-void transport_add_device(struct device *);
+int transport_add_device(struct device *);
 void transport_setup_device(struct device *);
 void transport_configure_device(struct device *);
 void transport_destroy_device(struct device *);
 
-static inline void
+static inline int
 transport_register_device(struct device *dev)
 {
 	transport_setup_device(dev);
-	transport_add_device(dev);
+	return transport_add_device(dev);
 }
 
 static inline void
diff --git a/include/linux/units.h b/include/linux/units.h
new file mode 100644
index 000000000000..aaf716364ec3
--- /dev/null
+++ b/include/linux/units.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNITS_H
+#define _LINUX_UNITS_H
+
+#include <linux/kernel.h>
+
+#define ABSOLUTE_ZERO_MILLICELSIUS -273150
+
+static inline long milli_kelvin_to_millicelsius(long t)
+{
+	return t + ABSOLUTE_ZERO_MILLICELSIUS;
+}
+
+static inline long millicelsius_to_milli_kelvin(long t)
+{
+	return t - ABSOLUTE_ZERO_MILLICELSIUS;
+}
+
+#define MILLIDEGREE_PER_DEGREE 1000
+#define MILLIDEGREE_PER_DECIDEGREE 100
+
+static inline long kelvin_to_millicelsius(long t)
+{
+	return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long millicelsius_to_kelvin(long t)
+{
+	t = millicelsius_to_milli_kelvin(t);
+
+	return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long deci_kelvin_to_celsius(long t)
+{
+	t = milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE);
+
+	return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long celsius_to_deci_kelvin(long t)
+{
+	t = millicelsius_to_milli_kelvin(t * MILLIDEGREE_PER_DEGREE);
+
+	return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE);
+}
+
+/**
+ * deci_kelvin_to_millicelsius_with_offset - convert Kelvin to Celsius
+ * @t: temperature value in decidegrees Kelvin
+ * @offset: difference between Kelvin and Celsius in millidegrees
+ *
+ * Return: temperature value in millidegrees Celsius
+ */
+static inline long deci_kelvin_to_millicelsius_with_offset(long t, long offset)
+{
+	return t * MILLIDEGREE_PER_DECIDEGREE - offset;
+}
+
+static inline long deci_kelvin_to_millicelsius(long t)
+{
+	return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE);
+}
+
+static inline long millicelsius_to_deci_kelvin(long t)
+{
+	t = millicelsius_to_milli_kelvin(t);
+
+	return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE);
+}
+
+static inline long kelvin_to_celsius(long t)
+{
+	return t + DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS,
+				     MILLIDEGREE_PER_DEGREE);
+}
+
+static inline long celsius_to_kelvin(long t)
+{
+	return t - DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS,
+				     MILLIDEGREE_PER_DEGREE);
+}
+
+#endif /* _LINUX_UNITS_H */
diff --git a/include/linux/zlib.h b/include/linux/zlib.h
index 92dbbd3f6c75..c757d848a758 100644
--- a/include/linux/zlib.h
+++ b/include/linux/zlib.h
@@ -191,6 +191,12 @@ extern int zlib_deflate_workspacesize (int windowBits, int memLevel);
    exceed those passed here.
 */
 
+extern int zlib_deflate_dfltcc_enabled (void);
+/*
+   Returns 1 if Deflate-Conversion facility is installed and enabled,
+   otherwise 0.
+*/
+
 /* 
 extern int deflateInit (z_streamp strm, int level);
 
diff --git a/include/media/cec-notifier.h b/include/media/cec-notifier.h
index 985afea1ee36..139e93be13b0 100644
--- a/include/media/cec-notifier.h
+++ b/include/media/cec-notifier.h
@@ -37,12 +37,6 @@ struct cec_notifier *cec_notifier_get_conn(struct device *dev,
 					   const char *conn);
 
 /**
- * cec_notifier_put - decrease refcount and delete when the refcount reaches 0.
- * @n: notifier
- */
-void cec_notifier_put(struct cec_notifier *n);
-
-/**
  * cec_notifier_conn_register - find or create a new cec_notifier for the given
  * HDMI device and connector tuple.
  * @hdmi_dev: HDMI device that sends the events.
@@ -138,10 +132,6 @@ static inline struct cec_notifier *cec_notifier_get_conn(struct device *dev,
 	return (struct cec_notifier *)0xdeadfeed;
 }
 
-static inline void cec_notifier_put(struct cec_notifier *n)
-{
-}
-
 static inline struct cec_notifier *
 cec_notifier_conn_register(struct device *hdmi_dev, const char *conn_name,
 			   const struct cec_connector_info *conn_info)
@@ -184,23 +174,6 @@ static inline struct device *cec_notifier_parse_hdmi_phandle(struct device *dev)
 #endif
 
 /**
- * cec_notifier_get - find or create a new cec_notifier for the given device.
- * @dev: device that sends the events.
- *
- * If a notifier for device @dev already exists, then increase the refcount
- * and return that notifier.
- *
- * If it doesn't exist, then allocate a new notifier struct and return a
- * pointer to that new struct.
- *
- * Return NULL if the memory could not be allocated.
- */
-static inline struct cec_notifier *cec_notifier_get(struct device *dev)
-{
-	return cec_notifier_get_conn(dev, NULL);
-}
-
-/**
  * cec_notifier_phys_addr_invalidate() - set the physical address to INVALID
  *
  * @n: the CEC notifier
diff --git a/include/media/cec.h b/include/media/cec.h
index 0a4f69cc9dd4..972bc8cd4384 100644
--- a/include/media/cec.h
+++ b/include/media/cec.h
@@ -386,52 +386,6 @@ cec_fill_conn_info_from_drm(struct cec_connector_info *conn_info,
 
 #endif
 
-#if IS_REACHABLE(CONFIG_CEC_CORE) && IS_ENABLED(CONFIG_CEC_NOTIFIER)
-
-/**
- * cec_notifier_register - register a callback with the notifier
- * @n: the CEC notifier
- * @adap: the CEC adapter, passed as argument to the callback function
- * @callback: the callback function
- */
-void cec_notifier_register(struct cec_notifier *n,
-			   struct cec_adapter *adap,
-			   void (*callback)(struct cec_adapter *adap, u16 pa));
-
-/**
- * cec_notifier_unregister - unregister the callback from the notifier.
- * @n: the CEC notifier
- */
-void cec_notifier_unregister(struct cec_notifier *n);
-
-/**
- * cec_register_cec_notifier - register the notifier with the cec adapter.
- * @adap: the CEC adapter
- * @notifier: the CEC notifier
- */
-void cec_register_cec_notifier(struct cec_adapter *adap,
-			       struct cec_notifier *notifier);
-
-#else
-
-static inline void
-cec_notifier_register(struct cec_notifier *n,
-		      struct cec_adapter *adap,
-		      void (*callback)(struct cec_adapter *adap, u16 pa))
-{
-}
-
-static inline void cec_notifier_unregister(struct cec_notifier *n)
-{
-}
-
-static inline void cec_register_cec_notifier(struct cec_adapter *adap,
-					     struct cec_notifier *notifier)
-{
-}
-
-#endif
-
 /**
  * cec_phys_addr_invalidate() - set the physical address to INVALID
  *
diff --git a/include/media/dvb-usb-ids.h b/include/media/dvb-usb-ids.h
index 1409230ad3a4..800d473b03c4 100644
--- a/include/media/dvb-usb-ids.h
+++ b/include/media/dvb-usb-ids.h
@@ -180,6 +180,7 @@
 #define USB_PID_TERRATEC_CINERGY_T_STICK_RC		0x0097
 #define USB_PID_TERRATEC_CINERGY_T_STICK_DUAL_RC	0x0099
 #define USB_PID_TERRATEC_CINERGY_T_STICK_BLACK_REV1	0x00a9
+#define USB_PID_TERRATEC_CINERGY_TC2_STICK		0x10b2
 #define USB_PID_TWINHAN_VP7041_COLD			0x3201
 #define USB_PID_TWINHAN_VP7041_WARM			0x3202
 #define USB_PID_TWINHAN_VP7020_COLD			0x3203
@@ -425,4 +426,5 @@
 #define USB_PID_EVOLVEO_XTRATV_STICK			0xa115
 #define USB_PID_HAMA_DVBT_HYBRID			0x2758
 #define USB_PID_XBOX_ONE_TUNER                          0x02d5
+#define USB_PID_PROLECTRIX_DV107669                     0xd803
 #endif
diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index d8c29e089000..150ee16ebd81 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -14,6 +14,7 @@
 #ifndef V4L2_COMMON_H_
 #define V4L2_COMMON_H_
 
+#include <linux/time.h>
 #include <media/v4l2-dev.h>
 
 /* Common printk constructs for v4l-i2c drivers. These macros create a unique
@@ -518,4 +519,24 @@ int v4l2_fill_pixfmt(struct v4l2_pix_format *pixfmt, u32 pixelformat,
 int v4l2_fill_pixfmt_mp(struct v4l2_pix_format_mplane *pixfmt, u32 pixelformat,
 			u32 width, u32 height);
 
+static inline u64 v4l2_buffer_get_timestamp(const struct v4l2_buffer *buf)
+{
+	/*
+	 * When the timestamp comes from 32-bit user space, there may be
+	 * uninitialized data in tv_usec, so cast it to u32.
+	 * Otherwise allow invalid input for backwards compatibility.
+	 */
+	return buf->timestamp.tv_sec * NSEC_PER_SEC +
+		(u32)buf->timestamp.tv_usec * NSEC_PER_USEC;
+}
+
+static inline void v4l2_buffer_set_timestamp(struct v4l2_buffer *buf,
+					     u64 timestamp)
+{
+	struct timespec64 ts = ns_to_timespec64(timestamp);
+
+	buf->timestamp.tv_sec  = ts.tv_sec;
+	buf->timestamp.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+}
+
 #endif /* V4L2_COMMON_H_ */
diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h
index 5f36e0d2ede6..95353ae476a1 100644
--- a/include/media/v4l2-device.h
+++ b/include/media/v4l2-device.h
@@ -371,7 +371,7 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 		struct v4l2_subdev *__sd;				\
 									\
 		__v4l2_device_call_subdevs_p(v4l2_dev, __sd,		\
-			!(grpid) || __sd->grp_id == (grpid), o, f ,	\
+			(grpid) == 0 || __sd->grp_id == (grpid), o, f ,	\
 			##args);					\
 	} while (0)
 
@@ -403,7 +403,7 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 ({									\
 	struct v4l2_subdev *__sd;					\
 	__v4l2_device_call_subdevs_until_err_p(v4l2_dev, __sd,		\
-			!(grpid) || __sd->grp_id == (grpid), o, f ,	\
+			(grpid) == 0 || __sd->grp_id == (grpid), o, f ,	\
 			##args);					\
 })
 
@@ -431,8 +431,8 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 		struct v4l2_subdev *__sd;				\
 									\
 		__v4l2_device_call_subdevs_p(v4l2_dev, __sd,		\
-			!(grpmsk) || (__sd->grp_id & (grpmsk)), o, f ,	\
-			##args);					\
+			(grpmsk) == 0 || (__sd->grp_id & (grpmsk)), o,	\
+			f , ##args);					\
 	} while (0)
 
 /**
@@ -462,8 +462,8 @@ static inline bool v4l2_device_supports_requests(struct v4l2_device *v4l2_dev)
 ({									\
 	struct v4l2_subdev *__sd;					\
 	__v4l2_device_call_subdevs_until_err_p(v4l2_dev, __sd,		\
-			!(grpmsk) || (__sd->grp_id & (grpmsk)), o, f ,	\
-			##args);					\
+			(grpmsk) == 0 || (__sd->grp_id & (grpmsk)), o,	\
+			f , ##args);					\
 })
 
 
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index 4bba65a59d46..86878fba332b 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -724,4 +724,59 @@ long int video_usercopy(struct file *file, unsigned int cmd,
 long int video_ioctl2(struct file *file,
 		      unsigned int cmd, unsigned long int arg);
 
+/*
+ * The user space interpretation of the 'v4l2_event' differs
+ * based on the 'time_t' definition on 32-bit architectures, so
+ * the kernel has to handle both.
+ * This is the old version for 32-bit architectures.
+ */
+struct v4l2_event_time32 {
+	__u32				type;
+	union {
+		struct v4l2_event_vsync		vsync;
+		struct v4l2_event_ctrl		ctrl;
+		struct v4l2_event_frame_sync	frame_sync;
+		struct v4l2_event_src_change	src_change;
+		struct v4l2_event_motion_det	motion_det;
+		__u8				data[64];
+	} u;
+	__u32				pending;
+	__u32				sequence;
+	struct old_timespec32		timestamp;
+	__u32				id;
+	__u32				reserved[8];
+};
+
+#define	VIDIOC_DQEVENT_TIME32	 _IOR('V', 89, struct v4l2_event_time32)
+
+struct v4l2_buffer_time32 {
+	__u32			index;
+	__u32			type;
+	__u32			bytesused;
+	__u32			flags;
+	__u32			field;
+	struct old_timeval32	timestamp;
+	struct v4l2_timecode	timecode;
+	__u32			sequence;
+
+	/* memory location */
+	__u32			memory;
+	union {
+		__u32           offset;
+		unsigned long   userptr;
+		struct v4l2_plane *planes;
+		__s32		fd;
+	} m;
+	__u32			length;
+	__u32			reserved2;
+	union {
+		__s32		request_fd;
+		__u32		reserved;
+	};
+};
+#define VIDIOC_QUERYBUF_TIME32	_IOWR('V',  9, struct v4l2_buffer_time32)
+#define VIDIOC_QBUF_TIME32	_IOWR('V', 15, struct v4l2_buffer_time32)
+#define VIDIOC_DQBUF_TIME32	_IOWR('V', 17, struct v4l2_buffer_time32)
+#define VIDIOC_PREPARE_BUF_TIME32 _IOWR('V', 93, struct v4l2_buffer_time32)
+
 #endif /* _V4L2_IOCTL_H */
diff --git a/include/media/v4l2-rect.h b/include/media/v4l2-rect.h
index c86474dc7b55..8800a640c224 100644
--- a/include/media/v4l2-rect.h
+++ b/include/media/v4l2-rect.h
@@ -63,10 +63,10 @@ static inline void v4l2_rect_map_inside(struct v4l2_rect *r,
 		r->left = boundary->left;
 	if (r->top < boundary->top)
 		r->top = boundary->top;
-	if (r->left + r->width > boundary->width)
-		r->left = boundary->width - r->width;
-	if (r->top + r->height > boundary->height)
-		r->top = boundary->height - r->height;
+	if (r->left + r->width > boundary->left + boundary->width)
+		r->left = boundary->left + boundary->width - r->width;
+	if (r->top + r->height > boundary->top + boundary->height)
+		r->top = boundary->top + boundary->height - r->height;
 }
 
 /**
diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h
index 71f1f2f0da53..761aa83a3f3c 100644
--- a/include/media/v4l2-subdev.h
+++ b/include/media/v4l2-subdev.h
@@ -1090,7 +1090,7 @@ extern const struct v4l2_subdev_ops v4l2_subdev_call_wrappers;
  * @sd: pointer to the &struct v4l2_subdev
  * @o: name of the element at &struct v4l2_subdev_ops that contains @f.
  *     Each element there groups a set of callbacks functions.
- * @f: callback function that will be called if @cond matches.
+ * @f: callback function to be called.
  *     The callback functions are defined in groups, according to
  *     each element at &struct v4l2_subdev_ops.
  * @args...: arguments for @f.
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 27627e2d1bc2..c971d25431ea 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -174,15 +174,12 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,
 
 #endif /* CONFIG_MPTCP */
 
-void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped);
-
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 int mptcpv6_init(void);
+void mptcpv6_handle_mapped(struct sock *sk, bool mapped);
 #elif IS_ENABLED(CONFIG_IPV6)
-static inline int mptcpv6_init(void)
-{
-	return 0;
-}
+static inline int mptcpv6_init(void) { return 0; }
+static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { }
 #endif
 
 #endif /* __NET_MPTCP_H */
diff --git a/include/net/udp.h b/include/net/udp.h
index 4a180f2a13e3..e55d5f765807 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -476,6 +476,13 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	if (!inet_get_convert_csum(sk))
 		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 
+	/* UDP segmentation expects packets of type CHECKSUM_PARTIAL or
+	 * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
+	 * packets in udp_gro_complete_segment. As does UDP GSO, verified by
+	 * udp_send_skb. But when those packets are looped in dev_loopback_xmit
+	 * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
+	 * specific case, where PARTIAL is both correct and required.
+	 */
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		skb->ip_summed = CHECKSUM_PARTIAL;
 
diff --git a/include/rdma/ib_cm.h b/include/rdma/ib_cm.h
index b01a8a8d4de9..8ec482e391aa 100644
--- a/include/rdma/ib_cm.h
+++ b/include/rdma/ib_cm.h
@@ -500,21 +500,6 @@ int ib_send_cm_mra(struct ib_cm_id *cm_id,
 		   u8 private_data_len);
 
 /**
- * ib_send_cm_lap - Sends a load alternate path request.
- * @cm_id: Connection identifier associated with the load alternate path
- *   message.
- * @alternate_path: A path record that identifies the alternate path to
- *   load.
- * @private_data: Optional user-defined private data sent with the
- *   load alternate path message.
- * @private_data_len: Size of the private data buffer, in bytes.
- */
-int ib_send_cm_lap(struct ib_cm_id *cm_id,
-		   struct sa_path_rec *alternate_path,
-		   const void *private_data,
-		   u8 private_data_len);
-
-/**
  * ib_cm_init_qp_attr - Initializes the QP attributes for use in transitioning
  *   to a specified QP state.
  * @cm_id: Communication identifier associated with the QP attributes to
@@ -534,25 +519,6 @@ int ib_cm_init_qp_attr(struct ib_cm_id *cm_id,
 		       struct ib_qp_attr *qp_attr,
 		       int *qp_attr_mask);
 
-/**
- * ib_send_cm_apr - Sends an alternate path response message in response to
- *   a load alternate path request.
- * @cm_id: Connection identifier associated with the alternate path response.
- * @status: Reply status sent with the alternate path response.
- * @info: Optional additional information sent with the alternate path
- *   response.
- * @info_length: Size of the additional information, in bytes.
- * @private_data: Optional user-defined private data sent with the
- *   alternate path response message.
- * @private_data_len: Size of the private data buffer, in bytes.
- */
-int ib_send_cm_apr(struct ib_cm_id *cm_id,
-		   enum ib_cm_apr_status status,
-		   void *info,
-		   u8 info_length,
-		   const void *private_data,
-		   u8 private_data_len);
-
 struct ib_cm_sidr_req_param {
 	struct sa_path_rec	*path;
 	const struct ib_gid_attr *sgid_attr;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index e2cc62217cc2..1f779fad3a1e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -72,11 +72,16 @@
 #define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
 
 struct ib_umem_odp;
+struct ib_uqp_object;
+struct ib_usrq_object;
+struct ib_uwq_object;
 
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
 extern struct workqueue_struct *ib_comp_unbound_wq;
 
+struct ib_ucq_object;
+
 __printf(3, 4) __cold
 void ibdev_printk(const char *level, const struct ib_device *ibdev,
 		  const char *format, ...);
@@ -1413,8 +1418,11 @@ enum ib_access_flags {
 	IB_ZERO_BASED = IB_UVERBS_ACCESS_ZERO_BASED,
 	IB_ACCESS_ON_DEMAND = IB_UVERBS_ACCESS_ON_DEMAND,
 	IB_ACCESS_HUGETLB = IB_UVERBS_ACCESS_HUGETLB,
+	IB_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_RELAXED_ORDERING,
 
-	IB_ACCESS_SUPPORTED = ((IB_ACCESS_HUGETLB << 1) - 1)
+	IB_ACCESS_OPTIONAL = IB_UVERBS_ACCESS_OPTIONAL_RANGE,
+	IB_ACCESS_SUPPORTED =
+		((IB_ACCESS_HUGETLB << 1) - 1) | IB_ACCESS_OPTIONAL,
 };
 
 /*
@@ -1544,7 +1552,7 @@ enum ib_poll_context {
 
 struct ib_cq {
 	struct ib_device       *device;
-	struct ib_uobject      *uobject;
+	struct ib_ucq_object   *uobject;
 	ib_comp_handler   	comp_handler;
 	void                  (*event_handler)(struct ib_event *, void *);
 	void                   *cq_context;
@@ -1558,6 +1566,11 @@ struct ib_cq {
 	};
 	struct workqueue_struct *comp_wq;
 	struct dim *dim;
+
+	/* updated only by trace points */
+	ktime_t timestamp;
+	bool interrupt;
+
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
 	 */
@@ -1567,7 +1580,7 @@ struct ib_cq {
 struct ib_srq {
 	struct ib_device       *device;
 	struct ib_pd	       *pd;
-	struct ib_uobject      *uobject;
+	struct ib_usrq_object  *uobject;
 	void		      (*event_handler)(struct ib_event *, void *);
 	void		       *srq_context;
 	enum ib_srq_type	srq_type;
@@ -1612,7 +1625,7 @@ enum ib_wq_state {
 
 struct ib_wq {
 	struct ib_device       *device;
-	struct ib_uobject      *uobject;
+	struct ib_uwq_object   *uobject;
 	void		    *wq_context;
 	void		    (*event_handler)(struct ib_event *, void *);
 	struct ib_pd	       *pd;
@@ -1728,7 +1741,7 @@ struct ib_qp {
 	atomic_t		usecnt;
 	struct list_head	open_list;
 	struct ib_qp           *real_qp;
-	struct ib_uobject      *uobject;
+	struct ib_uqp_object   *uobject;
 	void                  (*event_handler)(struct ib_event *, void *);
 	void		       *qp_context;
 	/* sgid_attrs associated with the AV's */
@@ -2147,11 +2160,6 @@ struct ib_port_cache {
 	enum ib_port_state     port_state;
 };
 
-struct ib_cache {
-	rwlock_t                lock;
-	struct ib_event_handler event_handler;
-};
-
 struct ib_port_immutable {
 	int                           pkey_tbl_len;
 	int                           gid_tbl_len;
@@ -2627,13 +2635,18 @@ struct ib_device {
 	struct rcu_head rcu_head;
 
 	struct list_head              event_handler_list;
-	spinlock_t                    event_handler_lock;
+	/* Protects event_handler_list */
+	struct rw_semaphore event_handler_rwsem;
+
+	/* Protects QP's event_handler calls and open_qp list */
+	spinlock_t qp_open_list_lock;
 
 	struct rw_semaphore	      client_data_rwsem;
 	struct xarray                 client_data;
 	struct mutex                  unregistration_lock;
 
-	struct ib_cache               cache;
+	/* Synchronize GID, Pkey cache entries, subnet prefix, LMC */
+	rwlock_t cache_lock;
 	/**
 	 * port_data is indexed by port number
 	 */
@@ -2942,7 +2955,7 @@ bool ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 
 void ib_register_event_handler(struct ib_event_handler *event_handler);
 void ib_unregister_event_handler(struct ib_event_handler *event_handler);
-void ib_dispatch_event(struct ib_event *event);
+void ib_dispatch_event(const struct ib_event *event);
 
 int ib_query_port(struct ib_device *device,
 		  u8 port_num, struct ib_port_attr *port_attr);
@@ -4309,6 +4322,9 @@ static inline int ib_check_mr_access(int flags)
 	    !(flags & IB_ACCESS_LOCAL_WRITE))
 		return -EINVAL;
 
+	if (flags & ~IB_ACCESS_SUPPORTED)
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/include/rdma/iba.h b/include/rdma/iba.h
new file mode 100644
index 000000000000..6a1115b02a0d
--- /dev/null
+++ b/include/rdma/iba.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2020, Mellanox Technologies inc.  All rights reserved.
+ */
+#ifndef _IBA_DEFS_H_
+#define _IBA_DEFS_H_
+
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
+#include <asm/unaligned.h>
+
+static inline u32 _iba_get8(const u8 *ptr)
+{
+	return *ptr;
+}
+
+static inline void _iba_set8(u8 *ptr, u32 mask, u32 prep_value)
+{
+	*ptr = (*ptr & ~mask) | prep_value;
+}
+
+static inline u16 _iba_get16(const __be16 *ptr)
+{
+	return be16_to_cpu(*ptr);
+}
+
+static inline void _iba_set16(__be16 *ptr, u16 mask, u16 prep_value)
+{
+	*ptr = cpu_to_be16((be16_to_cpu(*ptr) & ~mask) | prep_value);
+}
+
+static inline u32 _iba_get32(const __be32 *ptr)
+{
+	return be32_to_cpu(*ptr);
+}
+
+static inline void _iba_set32(__be32 *ptr, u32 mask, u32 prep_value)
+{
+	*ptr = cpu_to_be32((be32_to_cpu(*ptr) & ~mask) | prep_value);
+}
+
+static inline u64 _iba_get64(const __be64 *ptr)
+{
+	/*
+	 * The mads are constructed so that 32 bit and smaller are naturally
+	 * aligned, everything larger has a max alignment of 4 bytes.
+	 */
+	return be64_to_cpu(get_unaligned(ptr));
+}
+
+static inline void _iba_set64(__be64 *ptr, u64 mask, u64 prep_value)
+{
+	put_unaligned(cpu_to_be64((_iba_get64(ptr) & ~mask) | prep_value), ptr);
+}
+
+#define _IBA_SET(field_struct, field_offset, field_mask, num_bits, ptr, value) \
+	({                                                                     \
+		field_struct *_ptr = ptr;                                      \
+		_iba_set##num_bits((void *)_ptr + (field_offset), field_mask,  \
+				   FIELD_PREP(field_mask, value));             \
+	})
+#define IBA_SET(field, ptr, value) _IBA_SET(field, ptr, value)
+
+#define _IBA_GET_MEM_PTR(field_struct, field_offset, type, num_bits, ptr)      \
+	({                                                                     \
+		field_struct *_ptr = ptr;                                      \
+		(type *)((void *)_ptr + (field_offset));                       \
+	})
+#define IBA_GET_MEM_PTR(field, ptr) _IBA_GET_MEM_PTR(field, ptr)
+
+/* FIXME: A set should always set the entire field, meaning we should zero the trailing bytes */
+#define _IBA_SET_MEM(field_struct, field_offset, type, num_bits, ptr, in,      \
+		     bytes)                                                    \
+	({                                                                     \
+		const type *_in_ptr = in;                                      \
+		WARN_ON(bytes * 8 > num_bits);                                 \
+		if (in && bytes)                                               \
+			memcpy(_IBA_GET_MEM_PTR(field_struct, field_offset,    \
+						type, num_bits, ptr),          \
+			       _in_ptr, bytes);                                \
+	})
+#define IBA_SET_MEM(field, ptr, in, bytes) _IBA_SET_MEM(field, ptr, in, bytes)
+
+#define _IBA_GET(field_struct, field_offset, field_mask, num_bits, ptr)        \
+	({                                                                     \
+		const field_struct *_ptr = ptr;                                \
+		(u##num_bits) FIELD_GET(                                       \
+			field_mask, _iba_get##num_bits((const void *)_ptr +    \
+						       (field_offset)));       \
+	})
+#define IBA_GET(field, ptr) _IBA_GET(field, ptr)
+
+#define _IBA_GET_MEM(field_struct, field_offset, type, num_bits, ptr, out,     \
+		     bytes)                                                    \
+	({                                                                     \
+		type *_out_ptr = out;                                          \
+		WARN_ON(bytes * 8 > num_bits);                                 \
+		if (out && bytes)                                              \
+			memcpy(_out_ptr,                                       \
+			       _IBA_GET_MEM_PTR(field_struct, field_offset,    \
+						type, num_bits, ptr),          \
+			       bytes);                                         \
+	})
+#define IBA_GET_MEM(field, ptr, out, bytes) _IBA_GET_MEM(field, ptr, out, bytes)
+
+/*
+ * The generated list becomes the parameters to the macros, the order is:
+ *  - struct this applies to
+ *  - starting offset of the max
+ *  - GENMASK or GENMASK_ULL in CPU order
+ *  - The width of data the mask operations should work on, in bits
+ */
+
+/*
+ * Extraction using a tabular description like table 106. bit_offset is from
+ * the Byte[Bit] notation.
+ */
+#define IBA_FIELD_BLOC(field_struct, byte_offset, bit_offset, num_bits)        \
+	field_struct, byte_offset,                                             \
+		GENMASK(7 - (bit_offset), 7 - (bit_offset) - (num_bits - 1)),  \
+		8
+#define IBA_FIELD8_LOC(field_struct, byte_offset, num_bits)                    \
+	IBA_FIELD_BLOC(field_struct, byte_offset, 0, num_bits)
+
+#define IBA_FIELD16_LOC(field_struct, byte_offset, num_bits)                   \
+	field_struct, (byte_offset)&0xFFFE,                                    \
+		GENMASK(15 - (((byte_offset) % 2) * 8),                        \
+			15 - (((byte_offset) % 2) * 8) - (num_bits - 1)),      \
+		16
+
+#define IBA_FIELD32_LOC(field_struct, byte_offset, num_bits)                   \
+	field_struct, (byte_offset)&0xFFFC,                                    \
+		GENMASK(31 - (((byte_offset) % 4) * 8),                        \
+			31 - (((byte_offset) % 4) * 8) - (num_bits - 1)),      \
+		32
+
+#define IBA_FIELD64_LOC(field_struct, byte_offset)                             \
+	field_struct, byte_offset, GENMASK_ULL(63, 0), 64
+/*
+ * In IBTA spec, everything that is more than 64bits is multiple
+ * of bytes without leftover bits.
+ */
+#define IBA_FIELD_MLOC(field_struct, byte_offset, num_bits, type)              \
+	field_struct, byte_offset, type, num_bits
+
+#endif /* _IBA_DEFS_H_ */
diff --git a/include/rdma/ibta_vol1_c12.h b/include/rdma/ibta_vol1_c12.h
new file mode 100644
index 000000000000..269904425d3f
--- /dev/null
+++ b/include/rdma/ibta_vol1_c12.h
@@ -0,0 +1,213 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2020, Mellanox Technologies inc. All rights reserved.
+ *
+ * This file is IBTA volume 1, chapter 12 declarations:
+ *  CHAPTER 12: COMMUNICATION MANAGEMENT
+ */
+#ifndef _IBTA_VOL1_C12_H_
+#define _IBTA_VOL1_C12_H_
+
+#include <rdma/iba.h>
+
+#define CM_FIELD_BLOC(field_struct, byte_offset, bits_offset, width)           \
+	IBA_FIELD_BLOC(field_struct,                                           \
+		       (byte_offset + sizeof(struct ib_mad_hdr)), bits_offset, \
+		       width)
+#define CM_FIELD8_LOC(field_struct, byte_offset, width)                        \
+	IBA_FIELD8_LOC(field_struct,                                           \
+		       (byte_offset + sizeof(struct ib_mad_hdr)), width)
+#define CM_FIELD16_LOC(field_struct, byte_offset, width)                       \
+	IBA_FIELD16_LOC(field_struct,                                          \
+			(byte_offset + sizeof(struct ib_mad_hdr)), width)
+#define CM_FIELD32_LOC(field_struct, byte_offset, width)                       \
+	IBA_FIELD32_LOC(field_struct,                                          \
+			(byte_offset + sizeof(struct ib_mad_hdr)), width)
+#define CM_FIELD64_LOC(field_struct, byte_offset)                              \
+	IBA_FIELD64_LOC(field_struct, (byte_offset + sizeof(struct ib_mad_hdr)))
+#define CM_FIELD_MLOC(field_struct, byte_offset, width, type)                  \
+	IBA_FIELD_MLOC(field_struct,                                           \
+		       (byte_offset + sizeof(struct ib_mad_hdr)), width, type)
+#define CM_STRUCT(field_struct, total_len)                                     \
+	field_struct                                                           \
+	{                                                                      \
+		struct ib_mad_hdr hdr;                                         \
+		u32 _data[(total_len) / 32 +                                   \
+			  BUILD_BUG_ON_ZERO((total_len) % 32 != 0)];           \
+	}
+
+/* Table 106 REQ Message Contents */
+#define CM_REQ_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_req_msg, 0, 32)
+#define CM_REQ_SERVICE_ID CM_FIELD64_LOC(struct cm_req_msg, 8)
+#define CM_REQ_LOCAL_CA_GUID CM_FIELD64_LOC(struct cm_req_msg, 16)
+#define CM_REQ_LOCAL_Q_KEY CM_FIELD32_LOC(struct cm_req_msg, 28, 32)
+#define CM_REQ_LOCAL_QPN CM_FIELD32_LOC(struct cm_req_msg, 32, 24)
+#define CM_REQ_RESPONDER_RESOURCES CM_FIELD8_LOC(struct cm_req_msg, 35, 8)
+#define CM_REQ_LOCAL_EECN CM_FIELD32_LOC(struct cm_req_msg, 36, 24)
+#define CM_REQ_INITIATOR_DEPTH CM_FIELD8_LOC(struct cm_req_msg, 39, 8)
+#define CM_REQ_REMOTE_EECN CM_FIELD32_LOC(struct cm_req_msg, 40, 24)
+#define CM_REQ_REMOTE_CM_RESPONSE_TIMEOUT                                      \
+	CM_FIELD8_LOC(struct cm_req_msg, 43, 5)
+#define CM_REQ_TRANSPORT_SERVICE_TYPE CM_FIELD_BLOC(struct cm_req_msg, 43, 5, 2)
+#define CM_REQ_END_TO_END_FLOW_CONTROL                                         \
+	CM_FIELD_BLOC(struct cm_req_msg, 43, 7, 1)
+#define CM_REQ_STARTING_PSN CM_FIELD32_LOC(struct cm_req_msg, 44, 24)
+#define CM_REQ_LOCAL_CM_RESPONSE_TIMEOUT CM_FIELD8_LOC(struct cm_req_msg, 47, 5)
+#define CM_REQ_RETRY_COUNT CM_FIELD_BLOC(struct cm_req_msg, 47, 5, 3)
+#define CM_REQ_PARTITION_KEY CM_FIELD16_LOC(struct cm_req_msg, 48, 16)
+#define CM_REQ_PATH_PACKET_PAYLOAD_MTU CM_FIELD8_LOC(struct cm_req_msg, 50, 4)
+#define CM_REQ_RDC_EXISTS CM_FIELD_BLOC(struct cm_req_msg, 50, 4, 1)
+#define CM_REQ_RNR_RETRY_COUNT CM_FIELD_BLOC(struct cm_req_msg, 50, 5, 3)
+#define CM_REQ_MAX_CM_RETRIES CM_FIELD8_LOC(struct cm_req_msg, 51, 4)
+#define CM_REQ_SRQ CM_FIELD_BLOC(struct cm_req_msg, 51, 4, 1)
+#define CM_REQ_EXTENDED_TRANSPORT_TYPE                                         \
+	CM_FIELD_BLOC(struct cm_req_msg, 51, 5, 3)
+#define CM_REQ_PRIMARY_LOCAL_PORT_LID CM_FIELD16_LOC(struct cm_req_msg, 52, 16)
+#define CM_REQ_PRIMARY_REMOTE_PORT_LID CM_FIELD16_LOC(struct cm_req_msg, 54, 16)
+#define CM_REQ_PRIMARY_LOCAL_PORT_GID                                          \
+	CM_FIELD_MLOC(struct cm_req_msg, 56, 128, union ib_gid)
+#define CM_REQ_PRIMARY_REMOTE_PORT_GID                                         \
+	CM_FIELD_MLOC(struct cm_req_msg, 72, 128, union ib_gid)
+#define CM_REQ_PRIMARY_FLOW_LABEL CM_FIELD32_LOC(struct cm_req_msg, 88, 20)
+#define CM_REQ_PRIMARY_PACKET_RATE CM_FIELD_BLOC(struct cm_req_msg, 91, 2, 6)
+#define CM_REQ_PRIMARY_TRAFFIC_CLASS CM_FIELD8_LOC(struct cm_req_msg, 92, 8)
+#define CM_REQ_PRIMARY_HOP_LIMIT CM_FIELD8_LOC(struct cm_req_msg, 93, 8)
+#define CM_REQ_PRIMARY_SL CM_FIELD8_LOC(struct cm_req_msg, 94, 4)
+#define CM_REQ_PRIMARY_SUBNET_LOCAL CM_FIELD_BLOC(struct cm_req_msg, 94, 4, 1)
+#define CM_REQ_PRIMARY_LOCAL_ACK_TIMEOUT CM_FIELD8_LOC(struct cm_req_msg, 95, 5)
+#define CM_REQ_ALTERNATE_LOCAL_PORT_LID                                        \
+	CM_FIELD16_LOC(struct cm_req_msg, 96, 16)
+#define CM_REQ_ALTERNATE_REMOTE_PORT_LID                                       \
+	CM_FIELD16_LOC(struct cm_req_msg, 98, 16)
+#define CM_REQ_ALTERNATE_LOCAL_PORT_GID                                        \
+	CM_FIELD_MLOC(struct cm_req_msg, 100, 128, union ib_gid)
+#define CM_REQ_ALTERNATE_REMOTE_PORT_GID                                       \
+	CM_FIELD_MLOC(struct cm_req_msg, 116, 128, union ib_gid)
+#define CM_REQ_ALTERNATE_FLOW_LABEL CM_FIELD32_LOC(struct cm_req_msg, 132, 20)
+#define CM_REQ_ALTERNATE_PACKET_RATE CM_FIELD_BLOC(struct cm_req_msg, 135, 2, 6)
+#define CM_REQ_ALTERNATE_TRAFFIC_CLASS CM_FIELD8_LOC(struct cm_req_msg, 136, 8)
+#define CM_REQ_ALTERNATE_HOP_LIMIT CM_FIELD8_LOC(struct cm_req_msg, 137, 8)
+#define CM_REQ_ALTERNATE_SL CM_FIELD8_LOC(struct cm_req_msg, 138, 4)
+#define CM_REQ_ALTERNATE_SUBNET_LOCAL                                          \
+	CM_FIELD_BLOC(struct cm_req_msg, 138, 4, 1)
+#define CM_REQ_ALTERNATE_LOCAL_ACK_TIMEOUT                                     \
+	CM_FIELD8_LOC(struct cm_req_msg, 139, 5)
+#define CM_REQ_SAP_SUPPORTED CM_FIELD_BLOC(struct cm_req_msg, 139, 5, 1)
+#define CM_REQ_PRIVATE_DATA CM_FIELD_MLOC(struct cm_req_msg, 140, 736, void)
+CM_STRUCT(struct cm_req_msg, 140 * 8 + 736);
+
+/* Table 107 MRA Message Contents */
+#define CM_MRA_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_mra_msg, 0, 32)
+#define CM_MRA_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_mra_msg, 4, 32)
+#define CM_MRA_MESSAGE_MRAED CM_FIELD8_LOC(struct cm_mra_msg, 8, 2)
+#define CM_MRA_SERVICE_TIMEOUT CM_FIELD8_LOC(struct cm_mra_msg, 9, 5)
+#define CM_MRA_PRIVATE_DATA CM_FIELD_MLOC(struct cm_mra_msg, 10, 1776, void)
+CM_STRUCT(struct cm_mra_msg, 10 * 8 + 1776);
+
+/* Table 108 REJ Message Contents */
+#define CM_REJ_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_rej_msg, 0, 32)
+#define CM_REJ_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_rej_msg, 4, 32)
+#define CM_REJ_MESSAGE_REJECTED CM_FIELD8_LOC(struct cm_rej_msg, 8, 2)
+#define CM_REJ_REJECTED_INFO_LENGTH CM_FIELD8_LOC(struct cm_rej_msg, 9, 7)
+#define CM_REJ_REASON CM_FIELD16_LOC(struct cm_rej_msg, 10, 16)
+#define CM_REJ_ARI CM_FIELD_MLOC(struct cm_rej_msg, 12, 576, void)
+#define CM_REJ_PRIVATE_DATA CM_FIELD_MLOC(struct cm_rej_msg, 84, 1184, void)
+CM_STRUCT(struct cm_rej_msg, 84 * 8 + 1184);
+
+/* Table 110 REP Message Contents */
+#define CM_REP_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_rep_msg, 0, 32)
+#define CM_REP_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_rep_msg, 4, 32)
+#define CM_REP_LOCAL_Q_KEY CM_FIELD32_LOC(struct cm_rep_msg, 8, 32)
+#define CM_REP_LOCAL_QPN CM_FIELD32_LOC(struct cm_rep_msg, 12, 24)
+#define CM_REP_LOCAL_EE_CONTEXT_NUMBER CM_FIELD32_LOC(struct cm_rep_msg, 16, 24)
+#define CM_REP_STARTING_PSN CM_FIELD32_LOC(struct cm_rep_msg, 20, 24)
+#define CM_REP_RESPONDER_RESOURCES CM_FIELD8_LOC(struct cm_rep_msg, 24, 8)
+#define CM_REP_INITIATOR_DEPTH CM_FIELD8_LOC(struct cm_rep_msg, 25, 8)
+#define CM_REP_TARGET_ACK_DELAY CM_FIELD8_LOC(struct cm_rep_msg, 26, 5)
+#define CM_REP_FAILOVER_ACCEPTED CM_FIELD_BLOC(struct cm_rep_msg, 26, 5, 2)
+#define CM_REP_END_TO_END_FLOW_CONTROL                                         \
+	CM_FIELD_BLOC(struct cm_rep_msg, 26, 7, 1)
+#define CM_REP_RNR_RETRY_COUNT CM_FIELD8_LOC(struct cm_rep_msg, 27, 3)
+#define CM_REP_SRQ CM_FIELD_BLOC(struct cm_rep_msg, 27, 3, 1)
+#define CM_REP_LOCAL_CA_GUID CM_FIELD64_LOC(struct cm_rep_msg, 28)
+#define CM_REP_PRIVATE_DATA CM_FIELD_MLOC(struct cm_rep_msg, 36, 1568, void)
+CM_STRUCT(struct cm_rep_msg, 36 * 8 + 1568);
+
+/* Table 111 RTU Message Contents */
+#define CM_RTU_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_rtu_msg, 0, 32)
+#define CM_RTU_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_rtu_msg, 4, 32)
+#define CM_RTU_PRIVATE_DATA CM_FIELD_MLOC(struct cm_rtu_msg, 8, 1792, void)
+CM_STRUCT(struct cm_rtu_msg, 8 * 8 + 1792);
+
+/* Table 112 DREQ Message Contents */
+#define CM_DREQ_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_dreq_msg, 0, 32)
+#define CM_DREQ_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_dreq_msg, 4, 32)
+#define CM_DREQ_REMOTE_QPN_EECN CM_FIELD32_LOC(struct cm_dreq_msg, 8, 24)
+#define CM_DREQ_PRIVATE_DATA CM_FIELD_MLOC(struct cm_dreq_msg, 12, 1760, void)
+CM_STRUCT(struct cm_dreq_msg, 12 * 8 + 1760);
+
+/* Table 113 DREP Message Contents */
+#define CM_DREP_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_drep_msg, 0, 32)
+#define CM_DREP_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_drep_msg, 4, 32)
+#define CM_DREP_PRIVATE_DATA CM_FIELD_MLOC(struct cm_drep_msg, 8, 1792, void)
+CM_STRUCT(struct cm_drep_msg, 8 * 8 + 1792);
+
+/* Table 115 LAP Message Contents */
+#define CM_LAP_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_lap_msg, 0, 32)
+#define CM_LAP_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_lap_msg, 4, 32)
+#define CM_LAP_REMOTE_QPN_EECN CM_FIELD32_LOC(struct cm_lap_msg, 12, 24)
+#define CM_LAP_REMOTE_CM_RESPONSE_TIMEOUT                                      \
+	CM_FIELD8_LOC(struct cm_lap_msg, 15, 5)
+#define CM_LAP_ALTERNATE_LOCAL_PORT_LID                                        \
+	CM_FIELD16_LOC(struct cm_lap_msg, 20, 16)
+#define CM_LAP_ALTERNATE_REMOTE_PORT_LID                                       \
+	CM_FIELD16_LOC(struct cm_lap_msg, 22, 16)
+#define CM_LAP_ALTERNATE_LOCAL_PORT_GID                                        \
+	CM_FIELD_MLOC(struct cm_lap_msg, 24, 128, union ib_gid)
+#define CM_LAP_ALTERNATE_REMOTE_PORT_GID                                       \
+	CM_FIELD_MLOC(struct cm_lap_msg, 40, 128, union ib_gid)
+#define CM_LAP_ALTERNATE_FLOW_LABEL CM_FIELD32_LOC(struct cm_lap_msg, 56, 20)
+#define CM_LAP_ALTERNATE_TRAFFIC_CLASS CM_FIELD8_LOC(struct cm_lap_msg, 59, 8)
+#define CM_LAP_ALTERNATE_HOP_LIMIT CM_FIELD8_LOC(struct cm_lap_msg, 60, 8)
+#define CM_LAP_ALTERNATE_PACKET_RATE CM_FIELD_BLOC(struct cm_lap_msg, 61, 2, 6)
+#define CM_LAP_ALTERNATE_SL CM_FIELD8_LOC(struct cm_lap_msg, 62, 4)
+#define CM_LAP_ALTERNATE_SUBNET_LOCAL CM_FIELD_BLOC(struct cm_lap_msg, 62, 4, 1)
+#define CM_LAP_ALTERNATE_LOCAL_ACK_TIMEOUT                                     \
+	CM_FIELD8_LOC(struct cm_lap_msg, 63, 5)
+#define CM_LAP_PRIVATE_DATA CM_FIELD_MLOC(struct cm_lap_msg, 64, 1344, void)
+CM_STRUCT(struct cm_lap_msg, 64 * 8 + 1344);
+
+/* Table 116 APR Message Contents */
+#define CM_APR_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_apr_msg, 0, 32)
+#define CM_APR_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_apr_msg, 4, 32)
+#define CM_APR_ADDITIONAL_INFORMATION_LENGTH                                   \
+	CM_FIELD8_LOC(struct cm_apr_msg, 8, 8)
+#define CM_APR_AR_STATUS CM_FIELD8_LOC(struct cm_apr_msg, 9, 8)
+#define CM_APR_ADDITIONAL_INFORMATION                                          \
+	CM_FIELD_MLOC(struct cm_apr_msg, 12, 576, void)
+#define CM_APR_PRIVATE_DATA CM_FIELD_MLOC(struct cm_apr_msg, 84, 1184, void)
+CM_STRUCT(struct cm_apr_msg, 84 * 8 + 1184);
+
+/* Table 119 SIDR_REQ Message Contents */
+#define CM_SIDR_REQ_REQUESTID CM_FIELD32_LOC(struct cm_sidr_req_msg, 0, 32)
+#define CM_SIDR_REQ_PARTITION_KEY CM_FIELD16_LOC(struct cm_sidr_req_msg, 4, 16)
+#define CM_SIDR_REQ_SERVICEID CM_FIELD64_LOC(struct cm_sidr_req_msg, 8)
+#define CM_SIDR_REQ_PRIVATE_DATA                                               \
+	CM_FIELD_MLOC(struct cm_sidr_req_msg, 16, 1728, void)
+CM_STRUCT(struct cm_sidr_req_msg, 16 * 8 + 1728);
+
+/* Table 120 SIDR_REP Message Contents */
+#define CM_SIDR_REP_REQUESTID CM_FIELD32_LOC(struct cm_sidr_rep_msg, 0, 32)
+#define CM_SIDR_REP_STATUS CM_FIELD8_LOC(struct cm_sidr_rep_msg, 4, 8)
+#define CM_SIDR_REP_ADDITIONAL_INFORMATION_LENGTH                              \
+	CM_FIELD8_LOC(struct cm_sidr_rep_msg, 5, 8)
+#define CM_SIDR_REP_QPN CM_FIELD32_LOC(struct cm_sidr_rep_msg, 8, 24)
+#define CM_SIDR_REP_SERVICEID CM_FIELD64_LOC(struct cm_sidr_rep_msg, 12)
+#define CM_SIDR_REP_Q_KEY CM_FIELD32_LOC(struct cm_sidr_rep_msg, 20, 32)
+#define CM_SIDR_REP_ADDITIONAL_INFORMATION                                     \
+	CM_FIELD_MLOC(struct cm_sidr_rep_msg, 24, 576, void)
+#define CM_SIDR_REP_PRIVATE_DATA                                               \
+	CM_FIELD_MLOC(struct cm_sidr_rep_msg, 96, 1088, void)
+CM_STRUCT(struct cm_sidr_rep_msg, 96 * 8 + 1088);
+
+#endif /* _IBTA_VOL1_C12_H_ */
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index b550ae89bf85..0d5c70e2d8ab 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -640,34 +640,14 @@ static inline int rvt_cmp_msn(u32 a, u32 b)
 	return (((int)a) - ((int)b)) << 8;
 }
 
-/**
- * rvt_compute_aeth - compute the AETH (syndrome + MSN)
- * @qp: the queue pair to compute the AETH for
- *
- * Returns the AETH.
- */
 __be32 rvt_compute_aeth(struct rvt_qp *qp);
 
-/**
- * rvt_get_credit - flush the send work queue of a QP
- * @qp: the qp who's send work queue to flush
- * @aeth: the Acknowledge Extended Transport Header
- *
- * The QP s_lock should be held.
- */
 void rvt_get_credit(struct rvt_qp *qp, u32 aeth);
 
-/**
- * rvt_restart_sge - rewind the sge state for a wqe
- * @ss: the sge state pointer
- * @wqe: the wqe to rewind
- * @len: the data length from the start of the wqe in bytes
- *
- * Returns the remaining data length.
- */
 u32 rvt_restart_sge(struct rvt_sge_state *ss, struct rvt_swqe *wqe, u32 len);
 
 /**
+ * rvt_div_round_up_mtu - round up divide
  * @qp - the qp pair
  * @len - the length
  *
diff --git a/include/rdma/uverbs_named_ioctl.h b/include/rdma/uverbs_named_ioctl.h
index 3447bfe356d6..6ae6cf8e4c2e 100644
--- a/include/rdma/uverbs_named_ioctl.h
+++ b/include/rdma/uverbs_named_ioctl.h
@@ -76,7 +76,7 @@
 #define DECLARE_UVERBS_NAMED_OBJECT(_object_id, _type_attrs, ...)              \
 	static const struct uverbs_method_def *const UVERBS_OBJECT_METHODS(    \
 		_object_id)[] = { __VA_ARGS__ };                               \
-	const struct uverbs_object_def UVERBS_OBJECT(_object_id) = {           \
+	static const struct uverbs_object_def UVERBS_OBJECT(_object_id) = {    \
 		.id = _object_id,                                              \
 		.type_attrs = &_type_attrs,                                    \
 		.num_methods = ARRAY_SIZE(UVERBS_OBJECT_METHODS(_object_id)),  \
@@ -88,10 +88,10 @@
  * identify all uapi methods with a (object,method) tuple. However, they have
  * no type pointer.
  */
-#define DECLARE_UVERBS_GLOBAL_METHODS(_object_id, ...)	\
+#define DECLARE_UVERBS_GLOBAL_METHODS(_object_id, ...)                         \
 	static const struct uverbs_method_def *const UVERBS_OBJECT_METHODS(    \
 		_object_id)[] = { __VA_ARGS__ };                               \
-	const struct uverbs_object_def UVERBS_OBJECT(_object_id) = {           \
+	static const struct uverbs_object_def UVERBS_OBJECT(_object_id) = {    \
 		.id = _object_id,                                              \
 		.num_methods = ARRAY_SIZE(UVERBS_OBJECT_METHODS(_object_id)),  \
 		.methods = &UVERBS_OBJECT_METHODS(_object_id)                  \
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index 05eabfd5d0d3..1b28ce1aba07 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -104,16 +104,6 @@ static inline void uobj_put_write(struct ib_uobject *uobj)
 	rdma_lookup_put_uobject(uobj, UVERBS_LOOKUP_WRITE);
 }
 
-static inline int __must_check
-uobj_alloc_commit(struct ib_uobject *uobj, struct uverbs_attr_bundle *attrs)
-{
-	int ret = rdma_alloc_commit_uobject(uobj, attrs);
-
-	if (ret)
-		return ret;
-	return 0;
-}
-
 static inline void uobj_alloc_abort(struct ib_uobject *uobj,
 				    struct uverbs_attr_bundle *attrs)
 {
@@ -124,8 +114,7 @@ static inline struct ib_uobject *
 __uobj_alloc(const struct uverbs_api_object *obj,
 	     struct uverbs_attr_bundle *attrs, struct ib_device **ib_dev)
 {
-	struct ib_uobject *uobj =
-		rdma_alloc_begin_uobject(obj, attrs->ufile, attrs);
+	struct ib_uobject *uobj = rdma_alloc_begin_uobject(obj, attrs);
 
 	if (!IS_ERR(uobj))
 		*ib_dev = attrs->context->device;
diff --git a/include/rdma/uverbs_types.h b/include/rdma/uverbs_types.h
index d57a5ba00c74..f1cbdae67250 100644
--- a/include/rdma/uverbs_types.h
+++ b/include/rdma/uverbs_types.h
@@ -83,9 +83,9 @@ enum rdma_lookup_mode {
  */
 struct uverbs_obj_type_class {
 	struct ib_uobject *(*alloc_begin)(const struct uverbs_api_object *obj,
-					  struct ib_uverbs_file *ufile);
+					  struct uverbs_attr_bundle *attrs);
 	/* This consumes the kref on uobj */
-	int (*alloc_commit)(struct ib_uobject *uobj);
+	void (*alloc_commit)(struct ib_uobject *uobj);
 	/* This does not consume the kref on uobj */
 	void (*alloc_abort)(struct ib_uobject *uobj);
 
@@ -98,7 +98,6 @@ struct uverbs_obj_type_class {
 				       enum rdma_remove_reason why,
 				       struct uverbs_attr_bundle *attrs);
 	void (*remove_handle)(struct ib_uobject *uobj);
-	u8    needs_kfree_rcu;
 };
 
 struct uverbs_obj_type {
@@ -138,23 +137,34 @@ struct ib_uobject *rdma_lookup_get_uobject(const struct uverbs_api_object *obj,
 void rdma_lookup_put_uobject(struct ib_uobject *uobj,
 			     enum rdma_lookup_mode mode);
 struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_api_object *obj,
-					    struct ib_uverbs_file *ufile,
 					    struct uverbs_attr_bundle *attrs);
 void rdma_alloc_abort_uobject(struct ib_uobject *uobj,
 			      struct uverbs_attr_bundle *attrs);
-int __must_check rdma_alloc_commit_uobject(struct ib_uobject *uobj,
-					   struct uverbs_attr_bundle *attrs);
+void rdma_alloc_commit_uobject(struct ib_uobject *uobj,
+			       struct uverbs_attr_bundle *attrs);
+
+/*
+ * uverbs_uobject_get is called in order to increase the reference count on
+ * an uobject. This is useful when a handler wants to keep the uobject's memory
+ * alive, regardless if this uobject is still alive in the context's objects
+ * repository. Objects are put via uverbs_uobject_put.
+ */
+static inline void uverbs_uobject_get(struct ib_uobject *uobject)
+{
+	kref_get(&uobject->ref);
+}
+void uverbs_uobject_put(struct ib_uobject *uobject);
 
 struct uverbs_obj_fd_type {
 	/*
 	 * In fd based objects, uverbs_obj_type_ops points to generic
 	 * fd operations. In order to specialize the underlying types (e.g.
 	 * completion_channel), we use fops, name and flags for fd creation.
-	 * context_closed is called when the context is closed either when
-	 * the driver is removed or the process terminated.
+	 * destroy_object is called when the uobject is to be destroyed,
+	 * because the driver is removed or the FD is closed.
 	 */
 	struct uverbs_obj_type  type;
-	int (*context_closed)(struct ib_uobject *uobj,
+	int (*destroy_object)(struct ib_uobject *uobj,
 			      enum rdma_remove_reason why);
 	const struct file_operations	*fops;
 	const char			*name;
@@ -163,11 +173,11 @@ struct uverbs_obj_fd_type {
 
 extern const struct uverbs_obj_type_class uverbs_idr_class;
 extern const struct uverbs_obj_type_class uverbs_fd_class;
-void uverbs_close_fd(struct file *f);
+int uverbs_uobject_fd_release(struct inode *inode, struct file *filp);
 
 #define UVERBS_BUILD_BUG_ON(cond) (sizeof(char[1 - 2 * !!(cond)]) -	\
 				   sizeof(char))
-#define UVERBS_TYPE_ALLOC_FD(_obj_size, _context_closed, _fops, _name, _flags)\
+#define UVERBS_TYPE_ALLOC_FD(_obj_size, _destroy_object, _fops, _name, _flags) \
 	((&((const struct uverbs_obj_fd_type)				\
 	 {.type = {							\
 		.type_class = &uverbs_fd_class,				\
@@ -175,7 +185,7 @@ void uverbs_close_fd(struct file *f);
 			UVERBS_BUILD_BUG_ON((_obj_size) <               \
 					    sizeof(struct ib_uobject)), \
 	 },								\
-	 .context_closed = _context_closed,				\
+	 .destroy_object = _destroy_object,				\
 	 .fops = _fops,							\
 	 .name = _name,							\
 	 .flags = _flags}))->type)
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 3ed836db5306..f8312a3e5b42 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -172,6 +172,7 @@ struct scsi_device {
 				     * because we did a bus reset. */
 	unsigned use_10_for_rw:1; /* first try 10-byte read / write */
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
+	unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */
 	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
 	unsigned no_write_same:1;	/* no WRITE SAME command */
 	unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */
diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h
index 5101e987c0ef..4fe69d863b5d 100644
--- a/include/scsi/scsi_ioctl.h
+++ b/include/scsi/scsi_ioctl.h
@@ -44,6 +44,7 @@ typedef struct scsi_fctargaddress {
 int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev,
 		int cmd, bool ndelay);
 extern int scsi_ioctl(struct scsi_device *, int, void __user *);
+extern int scsi_compat_ioctl(struct scsi_device *sdev, int cmd, void __user *arg);
 
 #endif /* __KERNEL__ */
 #endif /* _SCSI_IOCTL_H */
diff --git a/include/scsi/sg.h b/include/scsi/sg.h
index f91bcca604e4..29c7ad04d2e2 100644
--- a/include/scsi/sg.h
+++ b/include/scsi/sg.h
@@ -68,6 +68,36 @@ typedef struct sg_io_hdr
     unsigned int info;          /* [o] auxiliary information */
 } sg_io_hdr_t;  /* 64 bytes long (on i386) */
 
+#if defined(__KERNEL__)
+#include <linux/compat.h>
+
+struct compat_sg_io_hdr {
+	compat_int_t interface_id;	/* [i] 'S' for SCSI generic (required) */
+	compat_int_t dxfer_direction;	/* [i] data transfer direction  */
+	unsigned char cmd_len;		/* [i] SCSI command length ( <= 16 bytes) */
+	unsigned char mx_sb_len;	/* [i] max length to write to sbp */
+	unsigned short iovec_count;	/* [i] 0 implies no scatter gather */
+	compat_uint_t dxfer_len;	/* [i] byte count of data transfer */
+	compat_uint_t dxferp;		/* [i], [*io] points to data transfer memory
+						or scatter gather list */
+	compat_uptr_t cmdp;		/* [i], [*i] points to command to perform */
+	compat_uptr_t sbp;		/* [i], [*o] points to sense_buffer memory */
+	compat_uint_t timeout;		/* [i] MAX_UINT->no timeout (unit: millisec) */
+	compat_uint_t flags;		/* [i] 0 -> default, see SG_FLAG... */
+	compat_int_t pack_id;		/* [i->o] unused internally (normally) */
+	compat_uptr_t usr_ptr;		/* [i->o] unused internally */
+	unsigned char status;		/* [o] scsi status */
+	unsigned char masked_status;	/* [o] shifted, masked scsi status */
+	unsigned char msg_status;	/* [o] messaging level data (optional) */
+	unsigned char sb_len_wr;	/* [o] byte count actually written to sbp */
+	unsigned short host_status;	/* [o] errors from host adapter */
+	unsigned short driver_status;	/* [o] errors from software driver */
+	compat_int_t resid;		/* [o] dxfer_len - actual_transferred */
+	compat_uint_t duration;		/* [o] time taken by cmd (unit: millisec) */
+	compat_uint_t info;		/* [o] auxiliary information */
+};
+#endif
+
 #define SG_INTERFACE_ID_ORIG 'S'
 
 /* Use negative values to flag difference from original sg_header structure */
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 182c9fe9c0e9..19c87661eeec 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -48,6 +48,16 @@ struct partial_cluster;
 	{ EXT4_GET_BLOCKS_KEEP_SIZE,		"KEEP_SIZE" },		\
 	{ EXT4_GET_BLOCKS_ZERO,			"ZERO" })
 
+/*
+ * __print_flags() requires that all enum values be wrapped in the
+ * TRACE_DEFINE_ENUM macro so that the enum value can be encoded in the ftrace
+ * ring buffer.
+ */
+TRACE_DEFINE_ENUM(BH_New);
+TRACE_DEFINE_ENUM(BH_Mapped);
+TRACE_DEFINE_ENUM(BH_Unwritten);
+TRACE_DEFINE_ENUM(BH_Boundary);
+
 #define show_mflags(flags) __print_flags(flags, "",	\
 	{ EXT4_MAP_NEW,		"N" },			\
 	{ EXT4_MAP_MAPPED,	"M" },			\
@@ -62,11 +72,18 @@ struct partial_cluster;
 	{ EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\
 	{ EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER,	"LAST_CLUSTER" })
 
+TRACE_DEFINE_ENUM(ES_WRITTEN_B);
+TRACE_DEFINE_ENUM(ES_UNWRITTEN_B);
+TRACE_DEFINE_ENUM(ES_DELAYED_B);
+TRACE_DEFINE_ENUM(ES_HOLE_B);
+TRACE_DEFINE_ENUM(ES_REFERENCED_B);
+
 #define show_extent_status(status) __print_flags(status, "",	\
 	{ EXTENT_STATUS_WRITTEN,	"W" },			\
 	{ EXTENT_STATUS_UNWRITTEN,	"U" },			\
 	{ EXTENT_STATUS_DELAYED,	"D" },			\
-	{ EXTENT_STATUS_HOLE,		"H" })
+	{ EXTENT_STATUS_HOLE,		"H" },			\
+	{ EXTENT_STATUS_REFERENCED,	"R" })
 
 #define show_falloc_mode(mode) __print_flags(mode, "|",		\
 	{ FALLOC_FL_KEEP_SIZE,		"KEEP_SIZE"},		\
@@ -2265,7 +2282,7 @@ DECLARE_EVENT_CLASS(ext4__es_extent,
 		__entry->ino	= inode->i_ino;
 		__entry->lblk	= es->es_lblk;
 		__entry->len	= es->es_len;
-		__entry->pblk	= ext4_es_pblock(es);
+		__entry->pblk	= ext4_es_show_pblock(es);
 		__entry->status	= ext4_es_status(es);
 	),
 
@@ -2354,7 +2371,7 @@ TRACE_EVENT(ext4_es_find_extent_range_exit,
 		__entry->ino	= inode->i_ino;
 		__entry->lblk	= es->es_lblk;
 		__entry->len	= es->es_len;
-		__entry->pblk	= ext4_es_pblock(es);
+		__entry->pblk	= ext4_es_show_pblock(es);
 		__entry->status	= ext4_es_status(es);
 	),
 
@@ -2408,7 +2425,7 @@ TRACE_EVENT(ext4_es_lookup_extent_exit,
 		__entry->ino	= inode->i_ino;
 		__entry->lblk	= es->es_lblk;
 		__entry->len	= es->es_len;
-		__entry->pblk	= ext4_es_pblock(es);
+		__entry->pblk	= ext4_es_show_pblock(es);
 		__entry->status	= ext4_es_status(es);
 		__entry->found	= found;
 	),
@@ -2576,7 +2593,7 @@ TRACE_EVENT(ext4_es_insert_delayed_block,
 		__entry->ino		= inode->i_ino;
 		__entry->lblk		= es->es_lblk;
 		__entry->len		= es->es_len;
-		__entry->pblk		= ext4_es_pblock(es);
+		__entry->pblk		= ext4_es_show_pblock(es);
 		__entry->status		= ext4_es_status(es);
 		__entry->allocated	= allocated;
 	),
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 1796ff99c3e9..67a97838c2a0 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -49,6 +49,7 @@ TRACE_DEFINE_ENUM(CP_SYNC);
 TRACE_DEFINE_ENUM(CP_RECOVERY);
 TRACE_DEFINE_ENUM(CP_DISCARD);
 TRACE_DEFINE_ENUM(CP_TRIMMED);
+TRACE_DEFINE_ENUM(CP_PAUSE);
 
 #define show_block_type(type)						\
 	__print_symbolic(type,						\
@@ -124,13 +125,14 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ CP_SYNC,	"Sync" },				\
 		{ CP_RECOVERY,	"Recovery" },				\
 		{ CP_DISCARD,	"Discard" },				\
-		{ CP_UMOUNT,	"Umount" },				\
+		{ CP_PAUSE,	"Pause" },				\
 		{ CP_TRIMMED,	"Trimmed" })
 
 #define show_fsync_cpreason(type)					\
 	__print_symbolic(type,						\
 		{ CP_NO_NEEDED,		"no needed" },			\
 		{ CP_NON_REGULAR,	"non regular" },		\
+		{ CP_COMPRESSED,	"compreesed" },			\
 		{ CP_HARDLINK,		"hardlink" },			\
 		{ CP_SB_NEED_CP,	"sb needs cp" },		\
 		{ CP_WRONG_PINO,	"wrong pino" },			\
@@ -148,6 +150,11 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ F2FS_GOING_DOWN_METAFLUSH,	"meta flush" },		\
 		{ F2FS_GOING_DOWN_NEED_FSCK,	"need fsck" })
 
+#define show_compress_algorithm(type)					\
+	__print_symbolic(type,						\
+		{ COMPRESS_LZO,		"LZO" },			\
+		{ COMPRESS_LZ4,		"LZ4" })
+
 struct f2fs_sb_info;
 struct f2fs_io_info;
 struct extent_info;
@@ -1710,6 +1717,100 @@ TRACE_EVENT(f2fs_shutdown,
 		__entry->ret)
 );
 
+DECLARE_EVENT_CLASS(f2fs_zip_start,
+
+	TP_PROTO(struct inode *inode, pgoff_t cluster_idx,
+			unsigned int cluster_size, unsigned char algtype),
+
+	TP_ARGS(inode, cluster_idx, cluster_size, algtype),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(pgoff_t, idx)
+		__field(unsigned int, size)
+		__field(unsigned int, algtype)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->idx = cluster_idx;
+		__entry->size = cluster_size;
+		__entry->algtype = algtype;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, cluster_idx:%lu, "
+		"cluster_size = %u, algorithm = %s",
+		show_dev_ino(__entry),
+		__entry->idx,
+		__entry->size,
+		show_compress_algorithm(__entry->algtype))
+);
+
+DECLARE_EVENT_CLASS(f2fs_zip_end,
+
+	TP_PROTO(struct inode *inode, pgoff_t cluster_idx,
+			unsigned int compressed_size, int ret),
+
+	TP_ARGS(inode, cluster_idx, compressed_size, ret),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(pgoff_t, idx)
+		__field(unsigned int, size)
+		__field(unsigned int, ret)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->idx = cluster_idx;
+		__entry->size = compressed_size;
+		__entry->ret = ret;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, cluster_idx:%lu, "
+		"compressed_size = %u, ret = %d",
+		show_dev_ino(__entry),
+		__entry->idx,
+		__entry->size,
+		__entry->ret)
+);
+
+DEFINE_EVENT(f2fs_zip_start, f2fs_compress_pages_start,
+
+	TP_PROTO(struct inode *inode, pgoff_t cluster_idx,
+		unsigned int cluster_size, unsigned char algtype),
+
+	TP_ARGS(inode, cluster_idx, cluster_size, algtype)
+);
+
+DEFINE_EVENT(f2fs_zip_start, f2fs_decompress_pages_start,
+
+	TP_PROTO(struct inode *inode, pgoff_t cluster_idx,
+		unsigned int cluster_size, unsigned char algtype),
+
+	TP_ARGS(inode, cluster_idx, cluster_size, algtype)
+);
+
+DEFINE_EVENT(f2fs_zip_end, f2fs_compress_pages_end,
+
+	TP_PROTO(struct inode *inode, pgoff_t cluster_idx,
+			unsigned int compressed_size, int ret),
+
+	TP_ARGS(inode, cluster_idx, compressed_size, ret)
+);
+
+DEFINE_EVENT(f2fs_zip_end, f2fs_decompress_pages_end,
+
+	TP_PROTO(struct inode *inode, pgoff_t cluster_idx,
+			unsigned int compressed_size, int ret),
+
+	TP_ARGS(inode, cluster_idx, compressed_size, ret)
+);
+
 #endif /* _TRACE_F2FS_H */
 
  /* This part must be outside protection */
diff --git a/include/trace/events/intel_iommu.h b/include/trace/events/intel_iommu.h
index 54e61d456cdf..112bd06487bf 100644
--- a/include/trace/events/intel_iommu.h
+++ b/include/trace/events/intel_iommu.h
@@ -49,12 +49,6 @@ DEFINE_EVENT(dma_map, map_single,
 	TP_ARGS(dev, dev_addr, phys_addr, size)
 );
 
-DEFINE_EVENT(dma_map, map_sg,
-	TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
-		 size_t size),
-	TP_ARGS(dev, dev_addr, phys_addr, size)
-);
-
 DEFINE_EVENT(dma_map, bounce_map_single,
 	TP_PROTO(struct device *dev, dma_addr_t dev_addr, phys_addr_t phys_addr,
 		 size_t size),
@@ -99,6 +93,48 @@ DEFINE_EVENT(dma_unmap, bounce_unmap_single,
 	TP_ARGS(dev, dev_addr, size)
 );
 
+DECLARE_EVENT_CLASS(dma_map_sg,
+	TP_PROTO(struct device *dev, int index, int total,
+		 struct scatterlist *sg),
+
+	TP_ARGS(dev, index, total, sg),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(dev))
+		__field(dma_addr_t, dev_addr)
+		__field(phys_addr_t, phys_addr)
+		__field(size_t,	size)
+		__field(int, index)
+		__field(int, total)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(dev));
+		__entry->dev_addr = sg->dma_address;
+		__entry->phys_addr = sg_phys(sg);
+		__entry->size = sg->dma_length;
+		__entry->index = index;
+		__entry->total = total;
+	),
+
+	TP_printk("dev=%s [%d/%d] dev_addr=0x%llx phys_addr=0x%llx size=%zu",
+		  __get_str(dev_name), __entry->index, __entry->total,
+		  (unsigned long long)__entry->dev_addr,
+		  (unsigned long long)__entry->phys_addr,
+		  __entry->size)
+);
+
+DEFINE_EVENT(dma_map_sg, map_sg,
+	TP_PROTO(struct device *dev, int index, int total,
+		 struct scatterlist *sg),
+	TP_ARGS(dev, index, total, sg)
+);
+
+DEFINE_EVENT(dma_map_sg, bounce_map_sg,
+	TP_PROTO(struct device *dev, int index, int total,
+		 struct scatterlist *sg),
+	TP_ARGS(dev, index, total, sg)
+);
 #endif /* _TRACE_INTEL_IOMMU_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index b352d66b5d51..27bd9e4f927b 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -320,6 +320,7 @@ TRACE_EVENT(io_uring_complete,
  * io_uring_submit_sqe - called before submitting one SQE
  *
  * @ctx:		pointer to a ring context structure
+ * @opcode:		opcode of request
  * @user_data:		user data associated with the request
  * @force_nonblock:	whether a context blocking or not
  * @sq_thread:		true if sq_thread has submitted this SQE
@@ -329,12 +330,14 @@ TRACE_EVENT(io_uring_complete,
  */
 TRACE_EVENT(io_uring_submit_sqe,
 
-	TP_PROTO(void *ctx, u64 user_data, bool force_nonblock, bool sq_thread),
+	TP_PROTO(void *ctx, u8 opcode, u64 user_data, bool force_nonblock,
+		 bool sq_thread),
 
-	TP_ARGS(ctx, user_data, force_nonblock, sq_thread),
+	TP_ARGS(ctx, opcode, user_data, force_nonblock, sq_thread),
 
 	TP_STRUCT__entry (
 		__field(  void *,	ctx		)
+		__field(  u8,		opcode		)
 		__field(  u64,		user_data	)
 		__field(  bool,		force_nonblock	)
 		__field(  bool,		sq_thread	)
@@ -342,13 +345,15 @@ TRACE_EVENT(io_uring_submit_sqe,
 
 	TP_fast_assign(
 		__entry->ctx		= ctx;
+		__entry->opcode		= opcode;
 		__entry->user_data	= user_data;
 		__entry->force_nonblock	= force_nonblock;
 		__entry->sq_thread	= sq_thread;
 	),
 
-	TP_printk("ring %p, user data 0x%llx, non block %d, sq_thread %d",
-			  __entry->ctx, (unsigned long long) __entry->user_data,
+	TP_printk("ring %p, op %d, data 0x%llx, non block %d, sq_thread %d",
+			  __entry->ctx, __entry->opcode,
+			  (unsigned long long) __entry->user_data,
 			  __entry->force_nonblock, __entry->sq_thread)
 );
 
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index ad7e642bd497..f65b1f6db22d 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -88,8 +88,8 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__entry->node		= node;
 	),
 
-	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
-		__entry->call_site,
+	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		(void *)__entry->call_site,
 		__entry->ptr,
 		__entry->bytes_req,
 		__entry->bytes_alloc,
diff --git a/include/trace/events/pwm.h b/include/trace/events/pwm.h
new file mode 100644
index 000000000000..cf243de41cc8
--- /dev/null
+++ b/include/trace/events/pwm.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM pwm
+
+#if !defined(_TRACE_PWM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PWM_H
+
+#include <linux/pwm.h>
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(pwm,
+
+	TP_PROTO(struct pwm_device *pwm, const struct pwm_state *state),
+
+	TP_ARGS(pwm, state),
+
+	TP_STRUCT__entry(
+		__field(struct pwm_device *, pwm)
+		__field(u64, period)
+		__field(u64, duty_cycle)
+		__field(enum pwm_polarity, polarity)
+		__field(bool, enabled)
+	),
+
+	TP_fast_assign(
+		__entry->pwm = pwm;
+		__entry->period = state->period;
+		__entry->duty_cycle = state->duty_cycle;
+		__entry->polarity = state->polarity;
+		__entry->enabled = state->enabled;
+	),
+
+	TP_printk("%p: period=%llu duty_cycle=%llu polarity=%d enabled=%d",
+		  __entry->pwm, __entry->period, __entry->duty_cycle,
+		  __entry->polarity, __entry->enabled)
+
+);
+
+DEFINE_EVENT(pwm, pwm_apply,
+
+	TP_PROTO(struct pwm_device *pwm, const struct pwm_state *state),
+
+	TP_ARGS(pwm, state)
+
+);
+
+DEFINE_EVENT(pwm, pwm_get,
+
+	TP_PROTO(struct pwm_device *pwm, const struct pwm_state *state),
+
+	TP_ARGS(pwm, state)
+
+);
+
+#endif /* _TRACE_PWM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/rdma_core.h b/include/trace/events/rdma_core.h
new file mode 100644
index 000000000000..17642aa54437
--- /dev/null
+++ b/include/trace/events/rdma_core.h
@@ -0,0 +1,394 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Trace point definitions for core RDMA functions.
+ *
+ * Author: Chuck Lever <chuck.lever@oracle.com>
+ *
+ * Copyright (c) 2019, Oracle and/or its affiliates. All rights reserved.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rdma_core
+
+#if !defined(_TRACE_RDMA_CORE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RDMA_CORE_H
+
+#include <linux/tracepoint.h>
+#include <rdma/ib_verbs.h>
+
+/*
+ * enum ib_poll_context, from include/rdma/ib_verbs.h
+ */
+#define IB_POLL_CTX_LIST			\
+	ib_poll_ctx(DIRECT)			\
+	ib_poll_ctx(SOFTIRQ)			\
+	ib_poll_ctx(WORKQUEUE)			\
+	ib_poll_ctx_end(UNBOUND_WORKQUEUE)
+
+#undef ib_poll_ctx
+#undef ib_poll_ctx_end
+
+#define ib_poll_ctx(x)		TRACE_DEFINE_ENUM(IB_POLL_##x);
+#define ib_poll_ctx_end(x)	TRACE_DEFINE_ENUM(IB_POLL_##x);
+
+IB_POLL_CTX_LIST
+
+#undef ib_poll_ctx
+#undef ib_poll_ctx_end
+
+#define ib_poll_ctx(x)		{ IB_POLL_##x, #x },
+#define ib_poll_ctx_end(x)	{ IB_POLL_##x, #x }
+
+#define rdma_show_ib_poll_ctx(x) \
+		__print_symbolic(x, IB_POLL_CTX_LIST)
+
+/**
+ ** Completion Queue events
+ **/
+
+TRACE_EVENT(cq_schedule,
+	TP_PROTO(
+		struct ib_cq *cq
+	),
+
+	TP_ARGS(cq),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+	),
+
+	TP_fast_assign(
+		cq->timestamp = ktime_get();
+		cq->interrupt = true;
+
+		__entry->cq_id = cq->res.id;
+	),
+
+	TP_printk("cq.id=%u", __entry->cq_id)
+);
+
+TRACE_EVENT(cq_reschedule,
+	TP_PROTO(
+		struct ib_cq *cq
+	),
+
+	TP_ARGS(cq),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+	),
+
+	TP_fast_assign(
+		cq->timestamp = ktime_get();
+		cq->interrupt = false;
+
+		__entry->cq_id = cq->res.id;
+	),
+
+	TP_printk("cq.id=%u", __entry->cq_id)
+);
+
+TRACE_EVENT(cq_process,
+	TP_PROTO(
+		const struct ib_cq *cq
+	),
+
+	TP_ARGS(cq),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(bool, interrupt)
+		__field(s64, latency)
+	),
+
+	TP_fast_assign(
+		ktime_t latency = ktime_sub(ktime_get(), cq->timestamp);
+
+		__entry->cq_id = cq->res.id;
+		__entry->latency = ktime_to_us(latency);
+		__entry->interrupt = cq->interrupt;
+	),
+
+	TP_printk("cq.id=%u wake-up took %lld [us] from %s",
+		__entry->cq_id, __entry->latency,
+		__entry->interrupt ? "interrupt" : "reschedule"
+	)
+);
+
+TRACE_EVENT(cq_poll,
+	TP_PROTO(
+		const struct ib_cq *cq,
+		int requested,
+		int rc
+	),
+
+	TP_ARGS(cq, requested, rc),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, requested)
+		__field(int, rc)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cq->res.id;
+		__entry->requested = requested;
+		__entry->rc = rc;
+	),
+
+	TP_printk("cq.id=%u requested %d, returned %d",
+		__entry->cq_id, __entry->requested, __entry->rc
+	)
+);
+
+TRACE_EVENT(cq_drain_complete,
+	TP_PROTO(
+		const struct ib_cq *cq
+	),
+
+	TP_ARGS(cq),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cq->res.id;
+	),
+
+	TP_printk("cq.id=%u",
+		__entry->cq_id
+	)
+);
+
+
+TRACE_EVENT(cq_modify,
+	TP_PROTO(
+		const struct ib_cq *cq,
+		u16 comps,
+		u16 usec
+	),
+
+	TP_ARGS(cq, comps, usec),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(unsigned int, comps)
+		__field(unsigned int, usec)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cq->res.id;
+		__entry->comps = comps;
+		__entry->usec = usec;
+	),
+
+	TP_printk("cq.id=%u comps=%u usec=%u",
+		__entry->cq_id, __entry->comps, __entry->usec
+	)
+);
+
+TRACE_EVENT(cq_alloc,
+	TP_PROTO(
+		const struct ib_cq *cq,
+		int nr_cqe,
+		int comp_vector,
+		enum ib_poll_context poll_ctx
+	),
+
+	TP_ARGS(cq, nr_cqe, comp_vector, poll_ctx),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+		__field(int, nr_cqe)
+		__field(int, comp_vector)
+		__field(unsigned long, poll_ctx)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cq->res.id;
+		__entry->nr_cqe = nr_cqe;
+		__entry->comp_vector = comp_vector;
+		__entry->poll_ctx = poll_ctx;
+	),
+
+	TP_printk("cq.id=%u nr_cqe=%d comp_vector=%d poll_ctx=%s",
+		__entry->cq_id, __entry->nr_cqe, __entry->comp_vector,
+		rdma_show_ib_poll_ctx(__entry->poll_ctx)
+	)
+);
+
+TRACE_EVENT(cq_alloc_error,
+	TP_PROTO(
+		int nr_cqe,
+		int comp_vector,
+		enum ib_poll_context poll_ctx,
+		int rc
+	),
+
+	TP_ARGS(nr_cqe, comp_vector, poll_ctx, rc),
+
+	TP_STRUCT__entry(
+		__field(int, rc)
+		__field(int, nr_cqe)
+		__field(int, comp_vector)
+		__field(unsigned long, poll_ctx)
+	),
+
+	TP_fast_assign(
+		__entry->rc = rc;
+		__entry->nr_cqe = nr_cqe;
+		__entry->comp_vector = comp_vector;
+		__entry->poll_ctx = poll_ctx;
+	),
+
+	TP_printk("nr_cqe=%d comp_vector=%d poll_ctx=%s rc=%d",
+		__entry->nr_cqe, __entry->comp_vector,
+		rdma_show_ib_poll_ctx(__entry->poll_ctx), __entry->rc
+	)
+);
+
+TRACE_EVENT(cq_free,
+	TP_PROTO(
+		const struct ib_cq *cq
+	),
+
+	TP_ARGS(cq),
+
+	TP_STRUCT__entry(
+		__field(u32, cq_id)
+	),
+
+	TP_fast_assign(
+		__entry->cq_id = cq->res.id;
+	),
+
+	TP_printk("cq.id=%u", __entry->cq_id)
+);
+
+/**
+ ** Memory Region events
+ **/
+
+/*
+ * enum ib_mr_type, from include/rdma/ib_verbs.h
+ */
+#define IB_MR_TYPE_LIST				\
+	ib_mr_type_item(MEM_REG)		\
+	ib_mr_type_item(SG_GAPS)		\
+	ib_mr_type_item(DM)			\
+	ib_mr_type_item(USER)			\
+	ib_mr_type_item(DMA)			\
+	ib_mr_type_end(INTEGRITY)
+
+#undef ib_mr_type_item
+#undef ib_mr_type_end
+
+#define ib_mr_type_item(x)	TRACE_DEFINE_ENUM(IB_MR_TYPE_##x);
+#define ib_mr_type_end(x)	TRACE_DEFINE_ENUM(IB_MR_TYPE_##x);
+
+IB_MR_TYPE_LIST
+
+#undef ib_mr_type_item
+#undef ib_mr_type_end
+
+#define ib_mr_type_item(x)	{ IB_MR_TYPE_##x, #x },
+#define ib_mr_type_end(x)	{ IB_MR_TYPE_##x, #x }
+
+#define rdma_show_ib_mr_type(x) \
+		__print_symbolic(x, IB_MR_TYPE_LIST)
+
+TRACE_EVENT(mr_alloc,
+	TP_PROTO(
+		const struct ib_pd *pd,
+		enum ib_mr_type mr_type,
+		u32 max_num_sg,
+		const struct ib_mr *mr
+	),
+
+	TP_ARGS(pd, mr_type, max_num_sg, mr),
+
+	TP_STRUCT__entry(
+		__field(u32, pd_id)
+		__field(u32, mr_id)
+		__field(u32, max_num_sg)
+		__field(int, rc)
+		__field(unsigned long, mr_type)
+	),
+
+	TP_fast_assign(
+		__entry->pd_id = pd->res.id;
+		if (IS_ERR(mr)) {
+			__entry->mr_id = 0;
+			__entry->rc = PTR_ERR(mr);
+		} else {
+			__entry->mr_id = mr->res.id;
+			__entry->rc = 0;
+		}
+		__entry->max_num_sg = max_num_sg;
+		__entry->mr_type = mr_type;
+	),
+
+	TP_printk("pd.id=%u mr.id=%u type=%s max_num_sg=%u rc=%d",
+		__entry->pd_id, __entry->mr_id,
+		rdma_show_ib_mr_type(__entry->mr_type),
+		__entry->max_num_sg, __entry->rc)
+);
+
+TRACE_EVENT(mr_integ_alloc,
+	TP_PROTO(
+		const struct ib_pd *pd,
+		u32 max_num_data_sg,
+		u32 max_num_meta_sg,
+		const struct ib_mr *mr
+	),
+
+	TP_ARGS(pd, max_num_data_sg, max_num_meta_sg, mr),
+
+	TP_STRUCT__entry(
+		__field(u32, pd_id)
+		__field(u32, mr_id)
+		__field(u32, max_num_data_sg)
+		__field(u32, max_num_meta_sg)
+		__field(int, rc)
+	),
+
+	TP_fast_assign(
+		__entry->pd_id = pd->res.id;
+		if (IS_ERR(mr)) {
+			__entry->mr_id = 0;
+			__entry->rc = PTR_ERR(mr);
+		} else {
+			__entry->mr_id = mr->res.id;
+			__entry->rc = 0;
+		}
+		__entry->max_num_data_sg = max_num_data_sg;
+		__entry->max_num_meta_sg = max_num_meta_sg;
+	),
+
+	TP_printk("pd.id=%u mr.id=%u max_num_data_sg=%u max_num_meta_sg=%u rc=%d",
+		__entry->pd_id, __entry->mr_id, __entry->max_num_data_sg,
+		__entry->max_num_meta_sg, __entry->rc)
+);
+
+TRACE_EVENT(mr_dereg,
+	TP_PROTO(
+		const struct ib_mr *mr
+	),
+
+	TP_ARGS(mr),
+
+	TP_STRUCT__entry(
+		__field(u32, id)
+	),
+
+	TP_fast_assign(
+		__entry->id = mr->res.id;
+	),
+
+	TP_printk("mr.id=%u", __entry->id)
+);
+
+#endif /* _TRACE_RDMA_CORE_H */
+
+#include <trace/define_trace.h>
diff --git a/include/trace/events/v4l2.h b/include/trace/events/v4l2.h
index 83860de120e3..248bc09bfc99 100644
--- a/include/trace/events/v4l2.h
+++ b/include/trace/events/v4l2.h
@@ -130,7 +130,7 @@ DECLARE_EVENT_CLASS(v4l2_event_class,
 		__entry->bytesused = buf->bytesused;
 		__entry->flags = buf->flags;
 		__entry->field = buf->field;
-		__entry->timestamp = timeval_to_ns(&buf->timestamp);
+		__entry->timestamp = v4l2_buffer_get_timestamp(buf);
 		__entry->timecode_type = buf->timecode.type;
 		__entry->timecode_flags = buf->timecode.flags;
 		__entry->timecode_frames = buf->timecode.frames;
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index ef50be4e5e6c..d94def25e4dc 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -67,8 +67,8 @@ DECLARE_EVENT_CLASS(writeback_page_template,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)",
-			    32);
+			    bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
+					 NULL), 32);
 		__entry->ino = mapping ? mapping->host->i_ino : 0;
 		__entry->index = page->index;
 	),
@@ -111,8 +111,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
 		struct backing_dev_info *bdi = inode_to_bdi(inode);
 
 		/* may be called for files on pseudo FSes w/ unregistered bdi */
-		strscpy_pad(__entry->name,
-			    bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32);
+		strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->flags		= flags;
@@ -193,7 +192,7 @@ TRACE_EVENT(inode_foreign_history,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(inode_to_bdi(inode)->dev), 32);
+		strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 		__entry->history	= history;
@@ -222,7 +221,7 @@ TRACE_EVENT(inode_switch_wbs,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name,	dev_name(old_wb->bdi->dev), 32);
+		strncpy(__entry->name,	bdi_dev_name(old_wb->bdi), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->old_cgroup_ino	= __trace_wb_assign_cgroup(old_wb);
 		__entry->new_cgroup_ino	= __trace_wb_assign_cgroup(new_wb);
@@ -255,7 +254,7 @@ TRACE_EVENT(track_foreign_dirty,
 		struct address_space *mapping = page_mapping(page);
 		struct inode *inode = mapping ? mapping->host : NULL;
 
-		strncpy(__entry->name,	dev_name(wb->bdi->dev), 32);
+		strncpy(__entry->name,	bdi_dev_name(wb->bdi), 32);
 		__entry->bdi_id		= wb->bdi->id;
 		__entry->ino		= inode ? inode->i_ino : 0;
 		__entry->memcg_id	= wb->memcg_css->id;
@@ -288,7 +287,7 @@ TRACE_EVENT(flush_foreign,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name,	dev_name(wb->bdi->dev), 32);
+		strncpy(__entry->name,	bdi_dev_name(wb->bdi), 32);
 		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 		__entry->frn_bdi_id	= frn_bdi_id;
 		__entry->frn_memcg_id	= frn_memcg_id;
@@ -318,7 +317,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    dev_name(inode_to_bdi(inode)->dev), 32);
+			    bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->sync_mode	= wbc->sync_mode;
 		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
@@ -361,9 +360,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(ino_t, cgroup_ino)
 	),
 	TP_fast_assign(
-		strscpy_pad(__entry->name,
-			    wb->bdi->dev ? dev_name(wb->bdi->dev) :
-			    "(unknown)", 32);
+		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
 		__entry->nr_pages = work->nr_pages;
 		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
 		__entry->sync_mode = work->sync_mode;
@@ -416,7 +413,7 @@ DECLARE_EVENT_CLASS(writeback_class,
 		__field(ino_t, cgroup_ino)
 	),
 	TP_fast_assign(
-		strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
 		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: cgroup_ino=%lu",
@@ -438,7 +435,7 @@ TRACE_EVENT(writeback_bdi_register,
 		__array(char, name, 32)
 	),
 	TP_fast_assign(
-		strscpy_pad(__entry->name, dev_name(bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
 	),
 	TP_printk("bdi %s",
 		__entry->name
@@ -463,7 +460,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 	),
 
 	TP_fast_assign(
-		strscpy_pad(__entry->name, dev_name(bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(bdi), 32);
 		__entry->nr_to_write	= wbc->nr_to_write;
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->sync_mode	= wbc->sync_mode;
@@ -514,7 +511,7 @@ TRACE_EVENT(writeback_queue_io,
 	),
 	TP_fast_assign(
 		unsigned long *older_than_this = work->older_than_this;
-		strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
 		__entry->older	= older_than_this ?  *older_than_this : 0;
 		__entry->age	= older_than_this ?
 				  (jiffies - *older_than_this) * 1000 / HZ : -1;
@@ -600,7 +597,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 	),
 
 	TP_fast_assign(
-		strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32);
 		__entry->write_bw	= KBps(wb->write_bandwidth);
 		__entry->avg_write_bw	= KBps(wb->avg_write_bandwidth);
 		__entry->dirty_rate	= KBps(dirty_rate);
@@ -665,7 +662,7 @@ TRACE_EVENT(balance_dirty_pages,
 
 	TP_fast_assign(
 		unsigned long freerun = (thresh + bg_thresh) / 2;
-		strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32);
+		strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32);
 
 		__entry->limit		= global_wb_domain.dirty_limit;
 		__entry->setpoint	= (global_wb_domain.dirty_limit +
@@ -726,7 +723,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    dev_name(inode_to_bdi(inode)->dev), 32);
+			    bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;
@@ -800,7 +797,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 
 	TP_fast_assign(
 		strscpy_pad(__entry->name,
-			    dev_name(inode_to_bdi(inode)->dev), 32);
+			    bdi_dev_name(inode_to_bdi(inode)), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index d4122c091472..3a3201e4618e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -853,9 +853,11 @@ __SYSCALL(__NR_clone3, sys_clone3)
 
 #define __NR_openat2 437
 __SYSCALL(__NR_openat2, sys_openat2)
+#define __NR_pidfd_getfd 438
+__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
 
 #undef __NR_syscalls
-#define __NR_syscalls 438
+#define __NR_syscalls 439
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index bbdad866e3fe..ac3879829bb5 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -703,6 +703,9 @@ struct drm_amdgpu_cs_chunk_data {
 	/* Subquery id: Query DMCU firmware version */
 	#define AMDGPU_INFO_FW_DMCU		0x12
 	#define AMDGPU_INFO_FW_TA		0x13
+	/* Subquery id: Query DMCUB firmware version */
+	#define AMDGPU_INFO_FW_DMCUB		0x14
+
 /* number of bytes moved for TTM migration */
 #define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
 /* the used VRAM size */
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 8caaaf7ff91b..8bc0b31597d8 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -411,6 +411,30 @@ extern "C" {
 #define I915_FORMAT_MOD_Yf_TILED_CCS	fourcc_mod_code(INTEL, 5)
 
 /*
+ * Intel color control surfaces (CCS) for Gen-12 render compression.
+ *
+ * The main surface is Y-tiled and at plane index 0, the CCS is linear and
+ * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in
+ * main surface. In other words, 4 bits in CCS map to a main surface cache
+ * line pair. The main surface pitch is required to be a multiple of four
+ * Y-tile widths.
+ */
+#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS fourcc_mod_code(INTEL, 6)
+
+/*
+ * Intel color control surfaces (CCS) for Gen-12 media compression
+ *
+ * The main surface is Y-tiled and at plane index 0, the CCS is linear and
+ * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in
+ * main surface. In other words, 4 bits in CCS map to a main surface cache
+ * line pair. The main surface pitch is required to be a multiple of four
+ * Y-tile widths. For semi-planar formats like NV12, CCS planes follow the
+ * Y and UV planes i.e., planes 0 and 1 are used for Y and UV surfaces,
+ * planes 2 and 3 for the respective CCS.
+ */
+#define I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS fourcc_mod_code(INTEL, 7)
+
+/*
  * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
  *
  * Macroblocks are laid in a Z-shape, and each pixel data is following the
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index 45c6582b3df3..a51aa1c618c1 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -394,7 +394,7 @@ struct drm_exynos_ioctl_ipp_commit {
 #define DRM_IOCTL_EXYNOS_IPP_COMMIT		DRM_IOWR(DRM_COMMAND_BASE + \
 		DRM_EXYNOS_IPP_COMMIT, struct drm_exynos_ioctl_ipp_commit)
 
-/* EXYNOS specific events */
+/* Exynos specific events */
 #define DRM_EXYNOS_G2D_EVENT		0x80000000
 #define DRM_EXYNOS_IPP_EVENT		0x80000002
 
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 5400d7e057f1..829c0a48577f 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -395,6 +395,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
 #define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
 #define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
 #define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
 #define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
 #define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
@@ -793,6 +794,37 @@ struct drm_i915_gem_mmap_gtt {
 	__u64 offset;
 };
 
+struct drm_i915_gem_mmap_offset {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/**
+	 * Fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+
+	/**
+	 * Flags for extended behaviour.
+	 *
+	 * It is mandatory that one of the MMAP_OFFSET types
+	 * (GTT, WC, WB, UC, etc) should be included.
+	 */
+	__u64 flags;
+#define I915_MMAP_OFFSET_GTT 0
+#define I915_MMAP_OFFSET_WC  1
+#define I915_MMAP_OFFSET_WB  2
+#define I915_MMAP_OFFSET_UC  3
+
+	/*
+	 * Zero-terminated chain of extensions.
+	 *
+	 * No current extensions defined; mbz.
+	 */
+	__u64 extensions;
+};
+
 struct drm_i915_gem_set_domain {
 	/** Handle for the object */
 	__u32 handle;
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index 9459a6e3bc1f..853a327433d3 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -110,6 +110,7 @@ struct drm_nouveau_gem_pushbuf {
 	__u64 push;
 	__u32 suffix0;
 	__u32 suffix1;
+#define NOUVEAU_GEM_PUSHBUF_SYNC                                    (1ULL << 0)
 	__u64 vram_available;
 	__u64 gart_available;
 };
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 02cab33f2f25..fcb741e3068f 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -71,6 +71,7 @@ extern "C" {
 #define DRM_VMW_CREATE_EXTENDED_CONTEXT 26
 #define DRM_VMW_GB_SURFACE_CREATE_EXT   27
 #define DRM_VMW_GB_SURFACE_REF_EXT      28
+#define DRM_VMW_MSG                     29
 
 /*************************************************************************/
 /**
@@ -1213,6 +1214,22 @@ union drm_vmw_gb_surface_reference_ext_arg {
 	struct drm_vmw_surface_arg req;
 };
 
+/**
+ * struct drm_vmw_msg_arg
+ *
+ * @send: Pointer to user-space msg string (null terminated).
+ * @receive: Pointer to user-space receive buffer.
+ * @send_only: Boolean whether this is only sending or receiving too.
+ *
+ * Argument to the DRM_VMW_MSG ioctl.
+ */
+struct drm_vmw_msg_arg {
+	__u64 send;
+	__u64 receive;
+	__s32 send_only;
+	__u32 receive_len;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h
index 240fdb9a60f6..272dc69fa080 100644
--- a/include/uapi/linux/capability.h
+++ b/include/uapi/linux/capability.h
@@ -301,6 +301,7 @@ struct vfs_ns_cap_data {
 /* Allow more than 64hz interrupts from the real-time clock */
 /* Override max number of consoles on console allocation */
 /* Override max number of keymaps */
+/* Control memory reclaim behavior */
 
 #define CAP_SYS_RESOURCE     24
 
diff --git a/include/uapi/linux/dma-heap.h b/include/uapi/linux/dma-heap.h
new file mode 100644
index 000000000000..6f84fa08e074
--- /dev/null
+++ b/include/uapi/linux/dma-heap.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * DMABUF Heaps Userspace API
+ *
+ * Copyright (C) 2011 Google, Inc.
+ * Copyright (C) 2019 Linaro Ltd.
+ */
+#ifndef _UAPI_LINUX_DMABUF_POOL_H
+#define _UAPI_LINUX_DMABUF_POOL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * DOC: DMABUF Heaps Userspace API
+ */
+
+/* Valid FD_FLAGS are O_CLOEXEC, O_RDONLY, O_WRONLY, O_RDWR */
+#define DMA_HEAP_VALID_FD_FLAGS (O_CLOEXEC | O_ACCMODE)
+
+/* Currently no heap flags */
+#define DMA_HEAP_VALID_HEAP_FLAGS (0)
+
+/**
+ * struct dma_heap_allocation_data - metadata passed from userspace for
+ *                                      allocations
+ * @len:		size of the allocation
+ * @fd:			will be populated with a fd which provides the
+ *			handle to the allocated dma-buf
+ * @fd_flags:		file descriptor flags used when allocating
+ * @heap_flags:		flags passed to heap
+ *
+ * Provided by userspace as an argument to the ioctl
+ */
+struct dma_heap_allocation_data {
+	__u64 len;
+	__u32 fd;
+	__u32 fd_flags;
+	__u64 heap_flags;
+};
+
+#define DMA_HEAP_IOC_MAGIC		'H'
+
+/**
+ * DOC: DMA_HEAP_IOCTL_ALLOC - allocate memory from pool
+ *
+ * Takes a dma_heap_allocation_data struct and returns it with the fd field
+ * populated with the dmabuf handle of the allocation.
+ */
+#define DMA_HEAP_IOCTL_ALLOC	_IOWR(DMA_HEAP_IOC_MAGIC, 0x0,\
+				      struct dma_heap_allocation_data)
+
+#endif /* _UAPI_LINUX_DMABUF_POOL_H */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 55cfcb71606d..3f7961c1c243 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -34,21 +34,43 @@ struct io_uring_sqe {
 		__u32		timeout_flags;
 		__u32		accept_flags;
 		__u32		cancel_flags;
+		__u32		open_flags;
+		__u32		statx_flags;
+		__u32		fadvise_advice;
 	};
 	__u64	user_data;	/* data to be passed back at completion time */
 	union {
-		__u16	buf_index;	/* index into fixed buffers, if used */
+		struct {
+			/* index into fixed buffers, if used */
+			__u16	buf_index;
+			/* personality to use, if used */
+			__u16	personality;
+		};
 		__u64	__pad2[3];
 	};
 };
 
+enum {
+	IOSQE_FIXED_FILE_BIT,
+	IOSQE_IO_DRAIN_BIT,
+	IOSQE_IO_LINK_BIT,
+	IOSQE_IO_HARDLINK_BIT,
+	IOSQE_ASYNC_BIT,
+};
+
 /*
  * sqe->flags
  */
-#define IOSQE_FIXED_FILE	(1U << 0)	/* use fixed fileset */
-#define IOSQE_IO_DRAIN		(1U << 1)	/* issue after inflight IO */
-#define IOSQE_IO_LINK		(1U << 2)	/* links next sqe */
-#define IOSQE_IO_HARDLINK	(1U << 3)	/* like LINK, but stronger */
+/* use fixed fileset */
+#define IOSQE_FIXED_FILE	(1U << IOSQE_FIXED_FILE_BIT)
+/* issue after inflight IO */
+#define IOSQE_IO_DRAIN		(1U << IOSQE_IO_DRAIN_BIT)
+/* links next sqe */
+#define IOSQE_IO_LINK		(1U << IOSQE_IO_LINK_BIT)
+/* like LINK, but stronger */
+#define IOSQE_IO_HARDLINK	(1U << IOSQE_IO_HARDLINK_BIT)
+/* always go async */
+#define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
 
 /*
  * io_uring_setup() flags
@@ -57,6 +79,8 @@ struct io_uring_sqe {
 #define IORING_SETUP_SQPOLL	(1U << 1)	/* SQ poll thread */
 #define IORING_SETUP_SQ_AFF	(1U << 2)	/* sq_thread_cpu is valid */
 #define IORING_SETUP_CQSIZE	(1U << 3)	/* app defines CQ size */
+#define IORING_SETUP_CLAMP	(1U << 4)	/* clamp SQ/CQ ring sizes */
+#define IORING_SETUP_ATTACH_WQ	(1U << 5)	/* attach to existing wq */
 
 enum {
 	IORING_OP_NOP,
@@ -76,6 +100,19 @@ enum {
 	IORING_OP_ASYNC_CANCEL,
 	IORING_OP_LINK_TIMEOUT,
 	IORING_OP_CONNECT,
+	IORING_OP_FALLOCATE,
+	IORING_OP_OPENAT,
+	IORING_OP_CLOSE,
+	IORING_OP_FILES_UPDATE,
+	IORING_OP_STATX,
+	IORING_OP_READ,
+	IORING_OP_WRITE,
+	IORING_OP_FADVISE,
+	IORING_OP_MADVISE,
+	IORING_OP_SEND,
+	IORING_OP_RECV,
+	IORING_OP_OPENAT2,
+	IORING_OP_EPOLL_CTL,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -153,7 +190,8 @@ struct io_uring_params {
 	__u32 sq_thread_cpu;
 	__u32 sq_thread_idle;
 	__u32 features;
-	__u32 resv[4];
+	__u32 wq_fd;
+	__u32 resv[3];
 	struct io_sqring_offsets sq_off;
 	struct io_cqring_offsets cq_off;
 };
@@ -164,6 +202,8 @@ struct io_uring_params {
 #define IORING_FEAT_SINGLE_MMAP		(1U << 0)
 #define IORING_FEAT_NODROP		(1U << 1)
 #define IORING_FEAT_SUBMIT_STABLE	(1U << 2)
+#define IORING_FEAT_RW_CUR_POS		(1U << 3)
+#define IORING_FEAT_CUR_PERSONALITY	(1U << 4)
 
 /*
  * io_uring_register(2) opcodes and arguments
@@ -175,6 +215,10 @@ struct io_uring_params {
 #define IORING_REGISTER_EVENTFD		4
 #define IORING_UNREGISTER_EVENTFD	5
 #define IORING_REGISTER_FILES_UPDATE	6
+#define IORING_REGISTER_EVENTFD_ASYNC	7
+#define IORING_REGISTER_PROBE		8
+#define IORING_REGISTER_PERSONALITY	9
+#define IORING_UNREGISTER_PERSONALITY	10
 
 struct io_uring_files_update {
 	__u32 offset;
@@ -182,4 +226,21 @@ struct io_uring_files_update {
 	__aligned_u64 /* __s32 * */ fds;
 };
 
+#define IO_URING_OP_SUPPORTED	(1U << 0)
+
+struct io_uring_probe_op {
+	__u8 op;
+	__u8 resv;
+	__u16 flags;	/* IO_URING_OP_* flags */
+	__u32 resv2;
+};
+
+struct io_uring_probe {
+	__u8 last_op;	/* last opcode supported */
+	__u8 ops_len;	/* length of ops[] array below */
+	__u16 resv;
+	__u32 resv2[3];
+	struct io_uring_probe_op ops[0];
+};
+
 #endif
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index acb7d2bdb419..5437690483cd 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -676,6 +676,7 @@
 #define  PCI_EXP_LNKCTL2_TLS_32_0GT	0x0005 /* Supported Speed 32GT/s */
 #define  PCI_EXP_LNKCTL2_ENTER_COMP	0x0010 /* Enter Compliance */
 #define  PCI_EXP_LNKCTL2_TX_MARGIN	0x0380 /* Transmit Margin */
+#define  PCI_EXP_LNKCTL2_HASD		0x0020 /* HW Autonomous Speed Disable */
 #define PCI_EXP_LNKSTA2		50	/* Link Status 2 */
 #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	52	/* v2 endpoints with link end here */
 #define PCI_EXP_SLTCAP2		52	/* Slot Capabilities 2 */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 7da1b37b27aa..07b4f8131e36 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -234,4 +234,8 @@ struct prctl_mm_map {
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
 
+/* Control reclaim behavior when allocating memory */
+#define PR_SET_IO_FLUSHER		57
+#define PR_GET_IO_FLUSHER		58
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h
index 26ee91300e3e..dcc1b3e6106f 100644
--- a/include/uapi/linux/random.h
+++ b/include/uapi/linux/random.h
@@ -48,9 +48,11 @@ struct rand_pool_info {
  * Flags for getrandom(2)
  *
  * GRND_NONBLOCK	Don't block and return EAGAIN instead
- * GRND_RANDOM		Use the /dev/random pool instead of /dev/urandom
+ * GRND_RANDOM		No effect
+ * GRND_INSECURE	Return non-cryptographic random bytes
  */
 #define GRND_NONBLOCK	0x0001
 #define GRND_RANDOM	0x0002
+#define GRND_INSECURE	0x0004
 
 #endif /* _UAPI_LINUX_RANDOM_H */
diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h
index 2ad1788968d0..095af360326a 100644
--- a/include/uapi/linux/rtc.h
+++ b/include/uapi/linux/rtc.h
@@ -92,7 +92,12 @@ struct rtc_pll_info {
 #define RTC_PLL_GET	_IOR('p', 0x11, struct rtc_pll_info)  /* Get PLL correction */
 #define RTC_PLL_SET	_IOW('p', 0x12, struct rtc_pll_info)  /* Set PLL correction */
 
-#define RTC_VL_READ	_IOR('p', 0x13, int)	/* Voltage low detector */
+#define RTC_VL_DATA_INVALID	BIT(0) /* Voltage too low, RTC data is invalid */
+#define RTC_VL_BACKUP_LOW	BIT(1) /* Backup voltage is low */
+#define RTC_VL_BACKUP_EMPTY	BIT(2) /* Backup empty or not present */
+#define RTC_VL_ACCURACY_LOW	BIT(3) /* Voltage is low, RTC accuracy is reduced */
+
+#define RTC_VL_READ	_IOR('p', 0x13, unsigned int)	/* Voltage low detection */
 #define RTC_VL_CLR	_IO('p', 0x14)		/* Clear voltage low information */
 
 /* interrupt flags */
diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h
index 23cd84868cc3..fa7f97da5b76 100644
--- a/include/uapi/linux/swab.h
+++ b/include/uapi/linux/swab.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <asm/bitsperlong.h>
 #include <asm/swab.h>
 
 /*
@@ -132,6 +133,15 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val)
 	__fswab64(x))
 #endif
 
+static __always_inline unsigned long __swab(const unsigned long y)
+{
+#if BITS_PER_LONG == 64
+	return __swab64(y);
+#else /* BITS_PER_LONG == 32 */
+	return __swab32(y);
+#endif
+}
+
 /**
  * __swahw32 - return a word-swapped 32-bit value
  * @x: value to wordswap
diff --git a/include/uapi/linux/switchtec_ioctl.h b/include/uapi/linux/switchtec_ioctl.h
index c912b5a678e4..2c661a3557e5 100644
--- a/include/uapi/linux/switchtec_ioctl.h
+++ b/include/uapi/linux/switchtec_ioctl.h
@@ -32,7 +32,18 @@
 #define SWITCHTEC_IOCTL_PART_VENDOR5	10
 #define SWITCHTEC_IOCTL_PART_VENDOR6	11
 #define SWITCHTEC_IOCTL_PART_VENDOR7	12
-#define SWITCHTEC_IOCTL_NUM_PARTITIONS	13
+#define SWITCHTEC_IOCTL_PART_BL2_0	13
+#define SWITCHTEC_IOCTL_PART_BL2_1	14
+#define SWITCHTEC_IOCTL_PART_MAP_0	15
+#define SWITCHTEC_IOCTL_PART_MAP_1	16
+#define SWITCHTEC_IOCTL_PART_KEY_0	17
+#define SWITCHTEC_IOCTL_PART_KEY_1	18
+
+#define SWITCHTEC_NUM_PARTITIONS_GEN3	13
+#define SWITCHTEC_NUM_PARTITIONS_GEN4	19
+
+/* obsolete: for compatibility with old userspace software */
+#define SWITCHTEC_IOCTL_NUM_PARTITIONS	SWITCHTEC_NUM_PARTITIONS_GEN3
 
 struct switchtec_ioctl_flash_info {
 	__u64 flash_length;
@@ -98,7 +109,9 @@ struct switchtec_ioctl_event_summary {
 #define SWITCHTEC_IOCTL_EVENT_CREDIT_TIMEOUT		27
 #define SWITCHTEC_IOCTL_EVENT_LINK_STATE		28
 #define SWITCHTEC_IOCTL_EVENT_GFMS			29
-#define SWITCHTEC_IOCTL_MAX_EVENTS			30
+#define SWITCHTEC_IOCTL_EVENT_INTERCOMM_REQ_NOTIFY	30
+#define SWITCHTEC_IOCTL_EVENT_UEC			31
+#define SWITCHTEC_IOCTL_MAX_EVENTS			32
 
 #define SWITCHTEC_IOCTL_EVENT_LOCAL_PART_IDX -1
 #define SWITCHTEC_IOCTL_EVENT_IDX_ALL -2
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 87aa2a6d9125..27c1ed2822e6 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -195,7 +195,7 @@ enum
 	VM_MIN_UNMAPPED=32,	/* Set min percent of unmapped pages */
 	VM_PANIC_ON_OOM=33,	/* panic at out-of-memory */
 	VM_VDSO_ENABLED=34,	/* map VDSO into new processes? */
-	VM_MIN_SLAB=35,		 /* Percent pages ignored by zone reclaim */
+	VM_MIN_SLAB=35,		 /* Percent pages ignored by node reclaim */
 };
 
 
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 04481c717fee..5f9357dcb060 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -912,6 +912,25 @@ struct v4l2_jpegcompression {
 /*
  *	M E M O R Y - M A P P I N G   B U F F E R S
  */
+
+#ifdef __KERNEL__
+/*
+ * This corresponds to the user space version of timeval
+ * for 64-bit time_t. sparc64 is different from everyone
+ * else, using the microseconds in the wrong half of the
+ * second 64-bit word.
+ */
+struct __kernel_v4l2_timeval {
+	long long	tv_sec;
+#if defined(__sparc__) && defined(__arch64__)
+	int		tv_usec;
+	int		__pad;
+#else
+	long long	tv_usec;
+#endif
+};
+#endif
+
 struct v4l2_requestbuffers {
 	__u32			count;
 	__u32			type;		/* enum v4l2_buf_type */
@@ -997,7 +1016,11 @@ struct v4l2_buffer {
 	__u32			bytesused;
 	__u32			flags;
 	__u32			field;
+#ifdef __KERNEL__
+	struct __kernel_v4l2_timeval timestamp;
+#else
 	struct timeval		timestamp;
+#endif
 	struct v4l2_timecode	timecode;
 	__u32			sequence;
 
@@ -1017,6 +1040,7 @@ struct v4l2_buffer {
 	};
 };
 
+#ifndef __KERNEL__
 /**
  * v4l2_timeval_to_ns - Convert timeval to nanoseconds
  * @ts:		pointer to the timeval variable to be converted
@@ -1028,6 +1052,7 @@ static inline __u64 v4l2_timeval_to_ns(const struct timeval *tv)
 {
 	return (__u64)tv->tv_sec * 1000000000ULL + tv->tv_usec * 1000;
 }
+#endif
 
 /*  Flags for 'flags' field */
 /* Buffer is mapped (flag) */
@@ -2339,7 +2364,11 @@ struct v4l2_event {
 	} u;
 	__u32				pending;
 	__u32				sequence;
+#ifdef __KERNEL__
+	struct __kernel_timespec	timestamp;
+#else
 	struct timespec			timestamp;
+#endif
 	__u32				id;
 	__u32				reserved[8];
 };
diff --git a/include/uapi/rdma/ib_user_ioctl_cmds.h b/include/uapi/rdma/ib_user_ioctl_cmds.h
index 64f0e3aacd3f..d4ddbe4e696c 100644
--- a/include/uapi/rdma/ib_user_ioctl_cmds.h
+++ b/include/uapi/rdma/ib_user_ioctl_cmds.h
@@ -56,6 +56,7 @@ enum uverbs_default_objects {
 	UVERBS_OBJECT_FLOW_ACTION,
 	UVERBS_OBJECT_DM,
 	UVERBS_OBJECT_COUNTERS,
+	UVERBS_OBJECT_ASYNC_EVENT,
 };
 
 enum {
@@ -67,6 +68,7 @@ enum uverbs_methods_device {
 	UVERBS_METHOD_INVOKE_WRITE,
 	UVERBS_METHOD_INFO_HANDLES,
 	UVERBS_METHOD_QUERY_PORT,
+	UVERBS_METHOD_GET_CONTEXT,
 };
 
 enum uverbs_attrs_invoke_write_cmd_attr_ids {
@@ -80,6 +82,11 @@ enum uverbs_attrs_query_port_cmd_attr_ids {
 	UVERBS_ATTR_QUERY_PORT_RESP,
 };
 
+enum uverbs_attrs_get_context_attr_ids {
+	UVERBS_ATTR_GET_CONTEXT_NUM_COMP_VECTORS,
+	UVERBS_ATTR_GET_CONTEXT_CORE_SUPPORT,
+};
+
 enum uverbs_attrs_create_cq_cmd_attr_ids {
 	UVERBS_ATTR_CREATE_CQ_HANDLE,
 	UVERBS_ATTR_CREATE_CQ_CQE,
@@ -241,4 +248,12 @@ enum uverbs_attrs_flow_destroy_ids {
 	UVERBS_ATTR_DESTROY_FLOW_HANDLE,
 };
 
+enum uverbs_method_async_event {
+	UVERBS_METHOD_ASYNC_EVENT_ALLOC,
+};
+
+enum uverbs_attrs_async_event_create {
+	UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE,
+};
+
 #endif
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 9019b2d906ea..a640bb814be0 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -41,6 +41,13 @@
 #define RDMA_UAPI_PTR(_type, _name)	__aligned_u64 _name
 #endif
 
+#define IB_UVERBS_ACCESS_OPTIONAL_FIRST (1 << 20)
+#define IB_UVERBS_ACCESS_OPTIONAL_LAST (1 << 29)
+
+enum ib_uverbs_core_support {
+	IB_UVERBS_CORE_SUPPORT_OPTIONAL_MR_ACCESS = 1 << 0,
+};
+
 enum ib_uverbs_access_flags {
 	IB_UVERBS_ACCESS_LOCAL_WRITE = 1 << 0,
 	IB_UVERBS_ACCESS_REMOTE_WRITE = 1 << 1,
@@ -50,6 +57,11 @@ enum ib_uverbs_access_flags {
 	IB_UVERBS_ACCESS_ZERO_BASED = 1 << 5,
 	IB_UVERBS_ACCESS_ON_DEMAND = 1 << 6,
 	IB_UVERBS_ACCESS_HUGETLB = 1 << 7,
+
+	IB_UVERBS_ACCESS_RELAXED_ORDERING = IB_UVERBS_ACCESS_OPTIONAL_FIRST,
+	IB_UVERBS_ACCESS_OPTIONAL_RANGE =
+		((IB_UVERBS_ACCESS_OPTIONAL_LAST << 1) - 1) &
+		~(IB_UVERBS_ACCESS_OPTIONAL_FIRST - 1)
 };
 
 enum ib_uverbs_query_port_cap_flags {
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 20d88307f75f..afe7da6f2b8e 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -115,6 +115,22 @@ enum mlx5_ib_devx_obj_methods {
 	MLX5_IB_METHOD_DEVX_OBJ_ASYNC_QUERY,
 };
 
+enum mlx5_ib_var_alloc_attrs {
+	MLX5_IB_ATTR_VAR_OBJ_ALLOC_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_VAR_OBJ_ALLOC_MMAP_OFFSET,
+	MLX5_IB_ATTR_VAR_OBJ_ALLOC_MMAP_LENGTH,
+	MLX5_IB_ATTR_VAR_OBJ_ALLOC_PAGE_ID,
+};
+
+enum mlx5_ib_var_obj_destroy_attrs {
+	MLX5_IB_ATTR_VAR_OBJ_DESTROY_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+};
+
+enum mlx5_ib_var_obj_methods {
+	MLX5_IB_METHOD_VAR_OBJ_ALLOC = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_METHOD_VAR_OBJ_DESTROY,
+};
+
 enum mlx5_ib_devx_umem_reg_attrs {
 	MLX5_IB_ATTR_DEVX_UMEM_REG_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_ATTR_DEVX_UMEM_REG_ADDR,
@@ -156,6 +172,7 @@ enum mlx5_ib_objects {
 	MLX5_IB_OBJECT_FLOW_MATCHER,
 	MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD,
 	MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD,
+	MLX5_IB_OBJECT_VAR,
 };
 
 enum mlx5_ib_flow_matcher_create_attrs {
diff --git a/include/uapi/rdma/qedr-abi.h b/include/uapi/rdma/qedr-abi.h
index c022ee26089b..a0b83c9d4498 100644
--- a/include/uapi/rdma/qedr-abi.h
+++ b/include/uapi/rdma/qedr-abi.h
@@ -48,6 +48,18 @@ struct qedr_alloc_ucontext_req {
 	__u32 reserved;
 };
 
+#define QEDR_LDPM_MAX_SIZE	(8192)
+#define QEDR_EDPM_TRANS_SIZE	(64)
+
+enum qedr_rdma_dpm_type {
+	QEDR_DPM_TYPE_NONE		= 0,
+	QEDR_DPM_TYPE_ROCE_ENHANCED	= 1 << 0,
+	QEDR_DPM_TYPE_ROCE_LEGACY	= 1 << 1,
+	QEDR_DPM_TYPE_IWARP_LEGACY	= 1 << 2,
+	QEDR_DPM_TYPE_RESERVED		= 1 << 3,
+	QEDR_DPM_SIZES_SET		= 1 << 4,
+};
+
 struct qedr_alloc_ucontext_resp {
 	__aligned_u64 db_pa;
 	__u32 db_size;
@@ -59,10 +71,12 @@ struct qedr_alloc_ucontext_resp {
 	__u32 sges_per_recv_wr;
 	__u32 sges_per_srq_wr;
 	__u32 max_cqes;
-	__u8 dpm_enabled;
+	__u8 dpm_flags;
 	__u8 wids_enabled;
 	__u16 wid_count;
-	__u32 reserved;
+	__u16 ldpm_limit_size;
+	__u8 edpm_trans_size;
+	__u8 reserved;
 };
 
 struct qedr_alloc_pd_ureq {
diff --git a/include/uapi/scsi/scsi_bsg_ufs.h b/include/uapi/scsi/scsi_bsg_ufs.h
index 9988db6ad244..d55f2176dfd4 100644
--- a/include/uapi/scsi/scsi_bsg_ufs.h
+++ b/include/uapi/scsi/scsi_bsg_ufs.h
@@ -68,14 +68,13 @@ struct utp_upiu_cmd {
  * @header:UPIU header structure DW-0 to DW-2
  * @sc: fields structure for scsi command DW-3 to DW-7
  * @qr: fields structure for query request DW-3 to DW-7
+ * @uc: use utp_upiu_query to host the 4 dwords of uic command
  */
 struct utp_upiu_req {
 	struct utp_upiu_header header;
 	union {
 		struct utp_upiu_cmd		sc;
 		struct utp_upiu_query		qr;
-		struct utp_upiu_query		tr;
-		/* use utp_upiu_query to host the 4 dwords of uic command */
 		struct utp_upiu_query		uc;
 	};
 };
diff --git a/include/video/mipi_display.h b/include/video/mipi_display.h
index cba57a678daf..b6d8b874233f 100644
--- a/include/video/mipi_display.h
+++ b/include/video/mipi_display.h
@@ -17,6 +17,9 @@ enum {
 	MIPI_DSI_H_SYNC_START				= 0x21,
 	MIPI_DSI_H_SYNC_END				= 0x31,
 
+	MIPI_DSI_COMPRESSION_MODE			= 0x07,
+	MIPI_DSI_END_OF_TRANSMISSION			= 0x08,
+
 	MIPI_DSI_COLOR_MODE_OFF				= 0x02,
 	MIPI_DSI_COLOR_MODE_ON				= 0x12,
 	MIPI_DSI_SHUTDOWN_PERIPHERAL			= 0x22,
@@ -34,19 +37,18 @@ enum {
 	MIPI_DSI_DCS_SHORT_WRITE_PARAM			= 0x15,
 
 	MIPI_DSI_DCS_READ				= 0x06,
-
-	MIPI_DSI_DCS_COMPRESSION_MODE                   = 0x07,
-	MIPI_DSI_PPS_LONG_WRITE                         = 0x0A,
+	MIPI_DSI_EXECUTE_QUEUE				= 0x16,
 
 	MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE		= 0x37,
 
-	MIPI_DSI_END_OF_TRANSMISSION			= 0x08,
-
 	MIPI_DSI_NULL_PACKET				= 0x09,
 	MIPI_DSI_BLANKING_PACKET			= 0x19,
 	MIPI_DSI_GENERIC_LONG_WRITE			= 0x29,
 	MIPI_DSI_DCS_LONG_WRITE				= 0x39,
 
+	MIPI_DSI_PICTURE_PARAMETER_SET			= 0x0a,
+	MIPI_DSI_COMPRESSED_PIXEL_STREAM		= 0x0b,
+
 	MIPI_DSI_LOOSELY_PACKED_PIXEL_STREAM_YCBCR20	= 0x0c,
 	MIPI_DSI_PACKED_PIXEL_STREAM_YCBCR24		= 0x1c,
 	MIPI_DSI_PACKED_PIXEL_STREAM_YCBCR16		= 0x2c,
@@ -77,7 +79,9 @@ enum {
 enum {
 	MIPI_DCS_NOP			= 0x00,
 	MIPI_DCS_SOFT_RESET		= 0x01,
+	MIPI_DCS_GET_COMPRESSION_MODE	= 0x03,
 	MIPI_DCS_GET_DISPLAY_ID		= 0x04,
+	MIPI_DCS_GET_ERROR_COUNT_ON_DSI	= 0x05,
 	MIPI_DCS_GET_RED_CHANNEL	= 0x06,
 	MIPI_DCS_GET_GREEN_CHANNEL	= 0x07,
 	MIPI_DCS_GET_BLUE_CHANNEL	= 0x08,
@@ -92,6 +96,8 @@ enum {
 	MIPI_DCS_EXIT_SLEEP_MODE	= 0x11,
 	MIPI_DCS_ENTER_PARTIAL_MODE	= 0x12,
 	MIPI_DCS_ENTER_NORMAL_MODE	= 0x13,
+	MIPI_DCS_GET_IMAGE_CHECKSUM_RGB	= 0x14,
+	MIPI_DCS_GET_IMAGE_CHECKSUM_CT	= 0x15,
 	MIPI_DCS_EXIT_INVERT_MODE	= 0x20,
 	MIPI_DCS_ENTER_INVERT_MODE	= 0x21,
 	MIPI_DCS_SET_GAMMA_CURVE	= 0x26,
@@ -102,7 +108,8 @@ enum {
 	MIPI_DCS_WRITE_MEMORY_START	= 0x2C,
 	MIPI_DCS_WRITE_LUT		= 0x2D,
 	MIPI_DCS_READ_MEMORY_START	= 0x2E,
-	MIPI_DCS_SET_PARTIAL_AREA	= 0x30,
+	MIPI_DCS_SET_PARTIAL_ROWS	= 0x30,		/* MIPI DCS 1.02 - MIPI_DCS_SET_PARTIAL_AREA before that */
+	MIPI_DCS_SET_PARTIAL_COLUMNS	= 0x31,
 	MIPI_DCS_SET_SCROLL_AREA	= 0x33,
 	MIPI_DCS_SET_TEAR_OFF		= 0x34,
 	MIPI_DCS_SET_TEAR_ON		= 0x35,
@@ -112,7 +119,10 @@ enum {
 	MIPI_DCS_ENTER_IDLE_MODE	= 0x39,
 	MIPI_DCS_SET_PIXEL_FORMAT	= 0x3A,
 	MIPI_DCS_WRITE_MEMORY_CONTINUE	= 0x3C,
+	MIPI_DCS_SET_3D_CONTROL		= 0x3D,
 	MIPI_DCS_READ_MEMORY_CONTINUE	= 0x3E,
+	MIPI_DCS_GET_3D_CONTROL		= 0x3F,
+	MIPI_DCS_SET_VSYNC_TIMING	= 0x40,
 	MIPI_DCS_SET_TEAR_SCANLINE	= 0x44,
 	MIPI_DCS_GET_SCANLINE		= 0x45,
 	MIPI_DCS_SET_DISPLAY_BRIGHTNESS = 0x51,		/* MIPI DCS 1.3 */
@@ -124,7 +134,9 @@ enum {
 	MIPI_DCS_SET_CABC_MIN_BRIGHTNESS = 0x5E,	/* MIPI DCS 1.3 */
 	MIPI_DCS_GET_CABC_MIN_BRIGHTNESS = 0x5F,	/* MIPI DCS 1.3 */
 	MIPI_DCS_READ_DDB_START		= 0xA1,
+	MIPI_DCS_READ_PPS_START		= 0xA2,
 	MIPI_DCS_READ_DDB_CONTINUE	= 0xA8,
+	MIPI_DCS_READ_PPS_CONTINUE	= 0xA9,
 };
 
 /* MIPI DCS pixel formats */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 24228a102141..89a889585ba0 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -76,6 +76,7 @@ struct xenbus_device {
 	enum xenbus_state state;
 	struct completion down;
 	struct work_struct work;
+	spinlock_t reclaim_lock;
 };
 
 static inline struct xenbus_device *to_xenbus_device(struct device *dev)
@@ -105,6 +106,7 @@ struct xenbus_driver {
 	struct device_driver driver;
 	int (*read_otherend_details)(struct xenbus_device *dev);
 	int (*is_ready)(struct xenbus_device *dev);
+	void (*reclaim_memory)(struct xenbus_device *dev);
 };
 
 static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv)
diff --git a/init/main.c b/init/main.c
index db13a76c036e..d8c7e86c2d28 100644
--- a/init/main.c
+++ b/init/main.c
@@ -246,8 +246,7 @@ static int __init loglevel(char *str)
 early_param("loglevel", loglevel);
 
 /* Change NUL term back to "=", to make "param" the whole string. */
-static int __init repair_env_string(char *param, char *val,
-				    const char *unused, void *arg)
+static void __init repair_env_string(char *param, char *val)
 {
 	if (val) {
 		/* param=val or param="val"? */
@@ -256,11 +255,9 @@ static int __init repair_env_string(char *param, char *val,
 		else if (val == param+strlen(param)+2) {
 			val[-2] = '=';
 			memmove(val-1, val, strlen(val)+1);
-			val--;
 		} else
 			BUG();
 	}
-	return 0;
 }
 
 /* Anything after -- gets handed straight to init. */
@@ -272,7 +269,7 @@ static int __init set_init_arg(char *param, char *val,
 	if (panic_later)
 		return 0;
 
-	repair_env_string(param, val, unused, NULL);
+	repair_env_string(param, val);
 
 	for (i = 0; argv_init[i]; i++) {
 		if (i == MAX_INIT_ARGS) {
@@ -292,14 +289,16 @@ static int __init set_init_arg(char *param, char *val,
 static int __init unknown_bootoption(char *param, char *val,
 				     const char *unused, void *arg)
 {
-	repair_env_string(param, val, unused, NULL);
+	size_t len = strlen(param);
+
+	repair_env_string(param, val);
 
 	/* Handle obsolete-style parameters */
 	if (obsolete_checksetup(param))
 		return 0;
 
 	/* Unused module parameter. */
-	if (strchr(param, '.') && (!val || strchr(param, '.') < val))
+	if (strnchr(param, len, '.'))
 		return 0;
 
 	if (panic_later)
@@ -313,7 +312,7 @@ static int __init unknown_bootoption(char *param, char *val,
 				panic_later = "env";
 				panic_param = param;
 			}
-			if (!strncmp(param, envp_init[i], val - param))
+			if (!strncmp(param, envp_init[i], len+1))
 				break;
 		}
 		envp_init[i] = param;
@@ -991,6 +990,12 @@ static const char *initcall_level_names[] __initdata = {
 	"late",
 };
 
+static int __init ignore_unknown_bootoption(char *param, char *val,
+			       const char *unused, void *arg)
+{
+	return 0;
+}
+
 static void __init do_initcall_level(int level)
 {
 	initcall_entry_t *fn;
@@ -1000,7 +1005,7 @@ static void __init do_initcall_level(int level)
 		   initcall_command_line, __start___param,
 		   __stop___param - __start___param,
 		   level, level,
-		   NULL, &repair_env_string);
+		   NULL, ignore_unknown_bootoption);
 
 	trace_initcall_level(initcall_level_names[level]);
 	for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
@@ -1043,8 +1048,16 @@ static void __init do_pre_smp_initcalls(void)
 
 static int run_init_process(const char *init_filename)
 {
+	const char *const *p;
+
 	argv_init[0] = init_filename;
 	pr_info("Run %s as init process\n", init_filename);
+	pr_debug("  with arguments:\n");
+	for (p = argv_init; *p; p++)
+		pr_debug("    %s\n", *p);
+	pr_debug("  with environment:\n");
+	for (p = envp_init; *p; p++)
+		pr_debug("    %s\n", *p);
 	return do_execve(getname_kernel(init_filename),
 		(const char __user *const __user *)argv_init,
 		(const char __user *const __user *)envp_init);
@@ -1091,6 +1104,11 @@ static void mark_readonly(void)
 	} else
 		pr_info("Kernel memory protection disabled.\n");
 }
+#elif defined(CONFIG_ARCH_HAS_STRICT_KERNEL_RWX)
+static inline void mark_readonly(void)
+{
+	pr_warn("Kernel memory protection not selected by kernel config.\n");
+}
 #else
 static inline void mark_readonly(void)
 {
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 3d920ff15c80..49a05ba3000d 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -63,6 +63,66 @@ struct posix_msg_tree_node {
 	int			priority;
 };
 
+/*
+ * Locking:
+ *
+ * Accesses to a message queue are synchronized by acquiring info->lock.
+ *
+ * There are two notable exceptions:
+ * - The actual wakeup of a sleeping task is performed using the wake_q
+ *   framework. info->lock is already released when wake_up_q is called.
+ * - The exit codepaths after sleeping check ext_wait_queue->state without
+ *   any locks. If it is STATE_READY, then the syscall is completed without
+ *   acquiring info->lock.
+ *
+ * MQ_BARRIER:
+ * To achieve proper release/acquire memory barrier pairing, the state is set to
+ * STATE_READY with smp_store_release(), and it is read with READ_ONCE followed
+ * by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used.
+ *
+ * This prevents the following races:
+ *
+ * 1) With the simple wake_q_add(), the task could be gone already before
+ *    the increase of the reference happens
+ * Thread A
+ *				Thread B
+ * WRITE_ONCE(wait.state, STATE_NONE);
+ * schedule_hrtimeout()
+ *				wake_q_add(A)
+ *				if (cmpxchg()) // success
+ *				   ->state = STATE_READY (reordered)
+ * <timeout returns>
+ * if (wait.state == STATE_READY) return;
+ * sysret to user space
+ * sys_exit()
+ *				get_task_struct() // UaF
+ *
+ * Solution: Use wake_q_add_safe() and perform the get_task_struct() before
+ * the smp_store_release() that does ->state = STATE_READY.
+ *
+ * 2) Without proper _release/_acquire barriers, the woken up task
+ *    could read stale data
+ *
+ * Thread A
+ *				Thread B
+ * do_mq_timedreceive
+ * WRITE_ONCE(wait.state, STATE_NONE);
+ * schedule_hrtimeout()
+ *				state = STATE_READY;
+ * <timeout returns>
+ * if (wait.state == STATE_READY) return;
+ * msg_ptr = wait.msg;		// Access to stale data!
+ *				receiver->msg = message; (reordered)
+ *
+ * Solution: use _release and _acquire barriers.
+ *
+ * 3) There is intentionally no barrier when setting current->state
+ *    to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the
+ *    release memory barrier, and the wakeup is triggered when holding
+ *    info->lock, i.e. spin_lock(&info->lock) provided a pairing
+ *    acquire memory barrier.
+ */
+
 struct ext_wait_queue {		/* queue of sleeping tasks */
 	struct task_struct *task;
 	struct list_head list;
@@ -646,18 +706,23 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr,
 	wq_add(info, sr, ewp);
 
 	for (;;) {
+		/* memory barrier not required, we hold info->lock */
 		__set_current_state(TASK_INTERRUPTIBLE);
 
 		spin_unlock(&info->lock);
 		time = schedule_hrtimeout_range_clock(timeout, 0,
 			HRTIMER_MODE_ABS, CLOCK_REALTIME);
 
-		if (ewp->state == STATE_READY) {
+		if (READ_ONCE(ewp->state) == STATE_READY) {
+			/* see MQ_BARRIER for purpose/pairing */
+			smp_acquire__after_ctrl_dep();
 			retval = 0;
 			goto out;
 		}
 		spin_lock(&info->lock);
-		if (ewp->state == STATE_READY) {
+
+		/* we hold info->lock, so no memory barrier required */
+		if (READ_ONCE(ewp->state) == STATE_READY) {
 			retval = 0;
 			goto out_unlock;
 		}
@@ -918,6 +983,18 @@ out_name:
  * The same algorithm is used for senders.
  */
 
+static inline void __pipelined_op(struct wake_q_head *wake_q,
+				  struct mqueue_inode_info *info,
+				  struct ext_wait_queue *this)
+{
+	list_del(&this->list);
+	get_task_struct(this->task);
+
+	/* see MQ_BARRIER for purpose/pairing */
+	smp_store_release(&this->state, STATE_READY);
+	wake_q_add_safe(wake_q, this->task);
+}
+
 /* pipelined_send() - send a message directly to the task waiting in
  * sys_mq_timedreceive() (without inserting message into a queue).
  */
@@ -927,17 +1004,7 @@ static inline void pipelined_send(struct wake_q_head *wake_q,
 				  struct ext_wait_queue *receiver)
 {
 	receiver->msg = message;
-	list_del(&receiver->list);
-	wake_q_add(wake_q, receiver->task);
-	/*
-	 * Rely on the implicit cmpxchg barrier from wake_q_add such
-	 * that we can ensure that updating receiver->state is the last
-	 * write operation: As once set, the receiver can continue,
-	 * and if we don't have the reference count from the wake_q,
-	 * yet, at that point we can later have a use-after-free
-	 * condition and bogus wakeup.
-	 */
-	receiver->state = STATE_READY;
+	__pipelined_op(wake_q, info, receiver);
 }
 
 /* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
@@ -955,9 +1022,7 @@ static inline void pipelined_receive(struct wake_q_head *wake_q,
 	if (msg_insert(sender->msg, info))
 		return;
 
-	list_del(&sender->list);
-	wake_q_add(wake_q, sender->task);
-	sender->state = STATE_READY;
+	__pipelined_op(wake_q, info, sender);
 }
 
 static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
@@ -1044,7 +1109,9 @@ static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
 		} else {
 			wait.task = current;
 			wait.msg = (void *) msg_ptr;
-			wait.state = STATE_NONE;
+
+			/* memory barrier not required, we hold info->lock */
+			WRITE_ONCE(wait.state, STATE_NONE);
 			ret = wq_sleep(info, SEND, timeout, &wait);
 			/*
 			 * wq_sleep must be called with info->lock held, and
@@ -1147,7 +1214,9 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
 			ret = -EAGAIN;
 		} else {
 			wait.task = current;
-			wait.state = STATE_NONE;
+
+			/* memory barrier not required, we hold info->lock */
+			WRITE_ONCE(wait.state, STATE_NONE);
 			ret = wq_sleep(info, RECV, timeout, &wait);
 			msg_ptr = wait.msg;
 		}
diff --git a/ipc/msg.c b/ipc/msg.c
index 8dec945fa030..caca67368cb5 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -61,6 +61,16 @@ struct msg_queue {
 	struct list_head q_senders;
 } __randomize_layout;
 
+/*
+ * MSG_BARRIER Locking:
+ *
+ * Similar to the optimization used in ipc/mqueue.c, one syscall return path
+ * does not acquire any locks when it sees that a message exists in
+ * msg_receiver.r_msg. Therefore r_msg is set using smp_store_release()
+ * and accessed using READ_ONCE()+smp_acquire__after_ctrl_dep(). In addition,
+ * wake_q_add_safe() is used. See ipc/mqueue.c for more details
+ */
+
 /* one msg_receiver structure for each sleeping receiver */
 struct msg_receiver {
 	struct list_head	r_list;
@@ -184,6 +194,10 @@ static inline void ss_add(struct msg_queue *msq,
 {
 	mss->tsk = current;
 	mss->msgsz = msgsz;
+	/*
+	 * No memory barrier required: we did ipc_lock_object(),
+	 * and the waker obtains that lock before calling wake_q_add().
+	 */
 	__set_current_state(TASK_INTERRUPTIBLE);
 	list_add_tail(&mss->list, &msq->q_senders);
 }
@@ -237,8 +251,11 @@ static void expunge_all(struct msg_queue *msq, int res,
 	struct msg_receiver *msr, *t;
 
 	list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
-		wake_q_add(wake_q, msr->r_tsk);
-		WRITE_ONCE(msr->r_msg, ERR_PTR(res));
+		get_task_struct(msr->r_tsk);
+
+		/* see MSG_BARRIER for purpose/pairing */
+		smp_store_release(&msr->r_msg, ERR_PTR(res));
+		wake_q_add_safe(wake_q, msr->r_tsk);
 	}
 }
 
@@ -377,7 +394,7 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
  * NOTE: no locks must be held, the rwsem is taken inside this function.
  */
 static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
-			struct msqid64_ds *msqid64)
+			struct ipc64_perm *perm, int msg_qbytes)
 {
 	struct kern_ipc_perm *ipcp;
 	struct msg_queue *msq;
@@ -387,7 +404,7 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 	rcu_read_lock();
 
 	ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd,
-				      &msqid64->msg_perm, msqid64->msg_qbytes);
+				      perm, msg_qbytes);
 	if (IS_ERR(ipcp)) {
 		err = PTR_ERR(ipcp);
 		goto out_unlock1;
@@ -409,18 +426,18 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 	{
 		DEFINE_WAKE_Q(wake_q);
 
-		if (msqid64->msg_qbytes > ns->msg_ctlmnb &&
+		if (msg_qbytes > ns->msg_ctlmnb &&
 		    !capable(CAP_SYS_RESOURCE)) {
 			err = -EPERM;
 			goto out_unlock1;
 		}
 
 		ipc_lock_object(&msq->q_perm);
-		err = ipc_update_perm(&msqid64->msg_perm, ipcp);
+		err = ipc_update_perm(perm, ipcp);
 		if (err)
 			goto out_unlock0;
 
-		msq->q_qbytes = msqid64->msg_qbytes;
+		msq->q_qbytes = msg_qbytes;
 
 		msq->q_ctime = ktime_get_real_seconds();
 		/*
@@ -601,9 +618,10 @@ static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int ver
 	case IPC_SET:
 		if (copy_msqid_from_user(&msqid64, buf, version))
 			return -EFAULT;
-		/* fallthru */
+		return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm,
+				   msqid64.msg_qbytes);
 	case IPC_RMID:
-		return msgctl_down(ns, msqid, cmd, &msqid64);
+		return msgctl_down(ns, msqid, cmd, NULL, 0);
 	default:
 		return  -EINVAL;
 	}
@@ -735,9 +753,9 @@ static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int versio
 	case IPC_SET:
 		if (copy_compat_msqid_from_user(&msqid64, uptr, version))
 			return -EFAULT;
-		/* fallthru */
+		return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes);
 	case IPC_RMID:
-		return msgctl_down(ns, msqid, cmd, &msqid64);
+		return msgctl_down(ns, msqid, cmd, NULL, 0);
 	default:
 		return -EINVAL;
 	}
@@ -798,13 +816,17 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg,
 			list_del(&msr->r_list);
 			if (msr->r_maxsize < msg->m_ts) {
 				wake_q_add(wake_q, msr->r_tsk);
-				WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG));
+
+				/* See expunge_all regarding memory barrier */
+				smp_store_release(&msr->r_msg, ERR_PTR(-E2BIG));
 			} else {
 				ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk));
 				msq->q_rtime = ktime_get_real_seconds();
 
 				wake_q_add(wake_q, msr->r_tsk);
-				WRITE_ONCE(msr->r_msg, msg);
+
+				/* See expunge_all regarding memory barrier */
+				smp_store_release(&msr->r_msg, msg);
 				return 1;
 			}
 		}
@@ -1154,7 +1176,11 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in
 			msr_d.r_maxsize = INT_MAX;
 		else
 			msr_d.r_maxsize = bufsz;
-		msr_d.r_msg = ERR_PTR(-EAGAIN);
+
+		/* memory barrier not require due to ipc_lock_object() */
+		WRITE_ONCE(msr_d.r_msg, ERR_PTR(-EAGAIN));
+
+		/* memory barrier not required, we own ipc_lock_object() */
 		__set_current_state(TASK_INTERRUPTIBLE);
 
 		ipc_unlock_object(&msq->q_perm);
@@ -1183,8 +1209,12 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in
 		 * signal) it will either see the message and continue ...
 		 */
 		msg = READ_ONCE(msr_d.r_msg);
-		if (msg != ERR_PTR(-EAGAIN))
+		if (msg != ERR_PTR(-EAGAIN)) {
+			/* see MSG_BARRIER for purpose/pairing */
+			smp_acquire__after_ctrl_dep();
+
 			goto out_unlock1;
+		}
 
 		 /*
 		  * ... or see -EAGAIN, acquire the lock to check the message
@@ -1192,7 +1222,7 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in
 		  */
 		ipc_lock_object(&msq->q_perm);
 
-		msg = msr_d.r_msg;
+		msg = READ_ONCE(msr_d.r_msg);
 		if (msg != ERR_PTR(-EAGAIN))
 			goto out_unlock0;
 
diff --git a/ipc/sem.c b/ipc/sem.c
index ec97a7072413..4f4303f32077 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -205,15 +205,38 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
  *
  * Memory ordering:
  * Most ordering is enforced by using spin_lock() and spin_unlock().
- * The special case is use_global_lock:
+ *
+ * Exceptions:
+ * 1) use_global_lock: (SEM_BARRIER_1)
  * Setting it from non-zero to 0 is a RELEASE, this is ensured by
- * using smp_store_release().
+ * using smp_store_release(): Immediately after setting it to 0,
+ * a simple op can start.
  * Testing if it is non-zero is an ACQUIRE, this is ensured by using
  * smp_load_acquire().
  * Setting it from 0 to non-zero must be ordered with regards to
  * this smp_load_acquire(), this is guaranteed because the smp_load_acquire()
  * is inside a spin_lock() and after a write from 0 to non-zero a
  * spin_lock()+spin_unlock() is done.
+ *
+ * 2) queue.status: (SEM_BARRIER_2)
+ * Initialization is done while holding sem_lock(), so no further barrier is
+ * required.
+ * Setting it to a result code is a RELEASE, this is ensured by both a
+ * smp_store_release() (for case a) and while holding sem_lock()
+ * (for case b).
+ * The AQUIRE when reading the result code without holding sem_lock() is
+ * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep().
+ * (case a above).
+ * Reading the result code while holding sem_lock() needs no further barriers,
+ * the locks inside sem_lock() enforce ordering (case b above)
+ *
+ * 3) current->state:
+ * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock().
+ * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may
+ * happen immediately after calling wake_q_add. As wake_q_add_safe() is called
+ * when holding sem_lock(), no further barriers are required.
+ *
+ * See also ipc/mqueue.c for more details on the covered races.
  */
 
 #define sc_semmsl	sem_ctls[0]
@@ -344,12 +367,8 @@ static void complexmode_tryleave(struct sem_array *sma)
 		return;
 	}
 	if (sma->use_global_lock == 1) {
-		/*
-		 * Immediately after setting use_global_lock to 0,
-		 * a simple op can start. Thus: all memory writes
-		 * performed by the current operation must be visible
-		 * before we set use_global_lock to 0.
-		 */
+
+		/* See SEM_BARRIER_1 for purpose/pairing */
 		smp_store_release(&sma->use_global_lock, 0);
 	} else {
 		sma->use_global_lock--;
@@ -400,7 +419,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 		 */
 		spin_lock(&sem->lock);
 
-		/* pairs with smp_store_release() */
+		/* see SEM_BARRIER_1 for purpose/pairing */
 		if (!smp_load_acquire(&sma->use_global_lock)) {
 			/* fast path successful! */
 			return sops->sem_num;
@@ -766,15 +785,12 @@ would_block:
 static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error,
 					     struct wake_q_head *wake_q)
 {
-	wake_q_add(wake_q, q->sleeper);
-	/*
-	 * Rely on the above implicit barrier, such that we can
-	 * ensure that we hold reference to the task before setting
-	 * q->status. Otherwise we could race with do_exit if the
-	 * task is awoken by an external event before calling
-	 * wake_up_process().
-	 */
-	WRITE_ONCE(q->status, error);
+	get_task_struct(q->sleeper);
+
+	/* see SEM_BARRIER_2 for purpuse/pairing */
+	smp_store_release(&q->status, error);
+
+	wake_q_add_safe(wake_q, q->sleeper);
 }
 
 static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
@@ -2148,9 +2164,11 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 	}
 
 	do {
+		/* memory ordering ensured by the lock in sem_lock() */
 		WRITE_ONCE(queue.status, -EINTR);
 		queue.sleeper = current;
 
+		/* memory ordering is ensured by the lock in sem_lock() */
 		__set_current_state(TASK_INTERRUPTIBLE);
 		sem_unlock(sma, locknum);
 		rcu_read_unlock();
@@ -2173,13 +2191,8 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 		 */
 		error = READ_ONCE(queue.status);
 		if (error != -EINTR) {
-			/*
-			 * User space could assume that semop() is a memory
-			 * barrier: Without the mb(), the cpu could
-			 * speculatively read in userspace stale data that was
-			 * overwritten by the previous owner of the semaphore.
-			 */
-			smp_mb();
+			/* see SEM_BARRIER_2 for purpose/pairing */
+			smp_acquire__after_ctrl_dep();
 			goto out_free;
 		}
 
@@ -2189,6 +2202,9 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 		if (!ipc_valid_object(&sma->sem_perm))
 			goto out_unlock_free;
 
+		/*
+		 * No necessity for any barrier: We are protect by sem_lock()
+		 */
 		error = READ_ONCE(queue.status);
 
 		/*
diff --git a/ipc/util.c b/ipc/util.c
index 915eacb9c059..fe61df53775a 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -126,7 +126,7 @@ void ipc_init_ids(struct ipc_ids *ids)
 }
 
 #ifdef CONFIG_PROC_FS
-static const struct file_operations sysvipc_proc_fops;
+static const struct proc_ops sysvipc_proc_ops;
 /**
  * ipc_init_proc_interface -  create a proc interface for sysipc types using a seq_file interface.
  * @path: Path in procfs
@@ -151,7 +151,7 @@ void __init ipc_init_proc_interface(const char *path, const char *header,
 	pde = proc_create_data(path,
 			       S_IRUGO,        /* world readable */
 			       NULL,           /* parent dir */
-			       &sysvipc_proc_fops,
+			       &sysvipc_proc_ops,
 			       iface);
 	if (!pde)
 		kfree(iface);
@@ -884,10 +884,10 @@ static int sysvipc_proc_release(struct inode *inode, struct file *file)
 	return seq_release_private(inode, file);
 }
 
-static const struct file_operations sysvipc_proc_fops = {
-	.open    = sysvipc_proc_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = sysvipc_proc_release,
+static const struct proc_ops sysvipc_proc_ops = {
+	.proc_open	= sysvipc_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= sysvipc_proc_release,
 };
 #endif /* CONFIG_PROC_FS */
diff --git a/kernel/Makefile b/kernel/Makefile
index f2cc0d118a0b..4cb4130ced32 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -27,6 +27,7 @@ KCOV_INSTRUMENT_softirq.o := n
 # and produce insane amounts of uninteresting coverage.
 KCOV_INSTRUMENT_module.o := n
 KCOV_INSTRUMENT_extable.o := n
+KCOV_INSTRUMENT_stacktrace.o := n
 # Don't self-instrument.
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
diff --git a/kernel/configs.c b/kernel/configs.c
index c09ea4c995e1..a28c79c5f713 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -47,10 +47,9 @@ ikconfig_read_current(struct file *file, char __user *buf,
 				       &kernel_config_data);
 }
 
-static const struct file_operations ikconfig_file_ops = {
-	.owner = THIS_MODULE,
-	.read = ikconfig_read_current,
-	.llseek = default_llseek,
+static const struct proc_ops config_gz_proc_ops = {
+	.proc_read	= ikconfig_read_current,
+	.proc_lseek	= default_llseek,
 };
 
 static int __init ikconfig_init(void)
@@ -59,7 +58,7 @@ static int __init ikconfig_init(void)
 
 	/* create the current config file */
 	entry = proc_create("config.gz", S_IFREG | S_IRUGO, NULL,
-			    &ikconfig_file_ops);
+			    &config_gz_proc_ops);
 	if (!entry)
 		return -ENOMEM;
 
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c
index 62c301ad0773..d7ebb2c79cb8 100644
--- a/kernel/debug/kdb/kdb_bp.c
+++ b/kernel/debug/kdb/kdb_bp.c
@@ -412,7 +412,6 @@ static int kdb_bc(int argc, const char **argv)
 		 * assume that the breakpoint number is desired.
 		 */
 		if (addr < KDB_MAXBPT) {
-			bp = &kdb_breakpoints[addr];
 			lowbp = highbp = addr;
 			highbp++;
 		} else {
diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c
index 4af48ac53625..3de0cc780c16 100644
--- a/kernel/debug/kdb/kdb_bt.c
+++ b/kernel/debug/kdb/kdb_bt.c
@@ -119,7 +119,6 @@ kdb_bt_cpu(unsigned long cpu)
 		return;
 	}
 
-	kdb_set_current_task(kdb_tsk);
 	kdb_bt1(kdb_tsk, ~0UL, false);
 }
 
@@ -166,10 +165,8 @@ kdb_bt(int argc, const char **argv)
 		if (diag)
 			return diag;
 		p = find_task_by_pid_ns(pid, &init_pid_ns);
-		if (p) {
-			kdb_set_current_task(p);
+		if (p)
 			return kdb_bt1(p, ~0UL, false);
-		}
 		kdb_printf("No process with pid == %ld found\n", pid);
 		return 0;
 	} else if (strcmp(argv[0], "btt") == 0) {
@@ -178,11 +175,9 @@ kdb_bt(int argc, const char **argv)
 		diag = kdbgetularg((char *)argv[1], &addr);
 		if (diag)
 			return diag;
-		kdb_set_current_task((struct task_struct *)addr);
 		return kdb_bt1((struct task_struct *)addr, ~0UL, false);
 	} else if (strcmp(argv[0], "btc") == 0) {
 		unsigned long cpu = ~0;
-		struct task_struct *save_current_task = kdb_current_task;
 		if (argc > 1)
 			return KDB_ARGCOUNT;
 		if (argc == 1) {
@@ -204,7 +199,6 @@ kdb_bt(int argc, const char **argv)
 				kdb_bt_cpu(cpu);
 				touch_nmi_watchdog();
 			}
-			kdb_set_current_task(save_current_task);
 		}
 		return 0;
 	} else {
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 8bcdded5d61f..924bc9298a42 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -553,7 +553,7 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
 	int this_cpu, old_cpu;
 	char *cp, *cp2, *cphold = NULL, replaced_byte = ' ';
 	char *moreprompt = "more> ";
-	struct console *c = console_drivers;
+	struct console *c;
 	unsigned long uninitialized_var(flags);
 
 	/* Serialize kdb_printf if multiple cpus try to write at once.
@@ -698,10 +698,9 @@ kdb_printit:
 				cp2++;
 			}
 		}
-		while (c) {
+		for_each_console(c) {
 			c->write(c, cp, retlen - (cp - kdb_buffer));
 			touch_nmi_watchdog();
-			c = c->next;
 		}
 	}
 	if (logging) {
@@ -752,7 +751,6 @@ kdb_printit:
 			moreprompt = "more> ";
 
 		kdb_input_flush();
-		c = console_drivers;
 
 		if (dbg_io_ops && !dbg_io_ops->is_console) {
 			len = strlen(moreprompt);
@@ -762,10 +760,9 @@ kdb_printit:
 				cp++;
 			}
 		}
-		while (c) {
+		for_each_console(c) {
 			c->write(c, moreprompt, strlen(moreprompt));
 			touch_nmi_watchdog();
-			c = c->next;
 		}
 
 		if (logging)
diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
index 4567fe998c30..b22292b649c4 100644
--- a/kernel/debug/kdb/kdb_main.c
+++ b/kernel/debug/kdb/kdb_main.c
@@ -73,7 +73,6 @@ int kdb_nextline = 1;
 int kdb_state;			/* General KDB state */
 
 struct task_struct *kdb_current_task;
-EXPORT_SYMBOL(kdb_current_task);
 struct pt_regs *kdb_current_regs;
 
 const char *kdb_diemsg;
@@ -544,9 +543,8 @@ int kdbgetaddrarg(int argc, const char **argv, int *nextarg,
 		if (diag)
 			return diag;
 	} else if (symname[0] == '%') {
-		diag = kdb_check_regs();
-		if (diag)
-			return diag;
+		if (kdb_check_regs())
+			return 0;
 		/* Implement register values with % at a later time as it is
 		 * arch optional.
 		 */
@@ -1139,7 +1137,7 @@ static void kdb_dumpregs(struct pt_regs *regs)
 	console_loglevel = old_lvl;
 }
 
-void kdb_set_current_task(struct task_struct *p)
+static void kdb_set_current_task(struct task_struct *p)
 {
 	kdb_current_task = p;
 
@@ -1837,8 +1835,7 @@ static int kdb_go(int argc, const char **argv)
  */
 static int kdb_rd(int argc, const char **argv)
 {
-	int len = kdb_check_regs();
-#if DBG_MAX_REG_NUM > 0
+	int len = 0;
 	int i;
 	char *rname;
 	int rsize;
@@ -1847,8 +1844,14 @@ static int kdb_rd(int argc, const char **argv)
 	u16 reg16;
 	u8 reg8;
 
-	if (len)
-		return len;
+	if (kdb_check_regs())
+		return 0;
+
+	/* Fallback to Linux showregs() if we don't have DBG_MAX_REG_NUM */
+	if (DBG_MAX_REG_NUM <= 0) {
+		kdb_dumpregs(kdb_current_regs);
+		return 0;
+	}
 
 	for (i = 0; i < DBG_MAX_REG_NUM; i++) {
 		rsize = dbg_reg_def[i].size * 2;
@@ -1890,12 +1893,7 @@ static int kdb_rd(int argc, const char **argv)
 		}
 	}
 	kdb_printf("\n");
-#else
-	if (len)
-		return len;
 
-	kdb_dumpregs(kdb_current_regs);
-#endif
 	return 0;
 }
 
@@ -1929,9 +1927,8 @@ static int kdb_rm(int argc, const char **argv)
 	if (diag)
 		return diag;
 
-	diag = kdb_check_regs();
-	if (diag)
-		return diag;
+	if (kdb_check_regs())
+		return 0;
 
 	diag = KDB_BADREG;
 	for (i = 0; i < DBG_MAX_REG_NUM; i++) {
diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
index 55d052061ef9..2e296e4a234c 100644
--- a/kernel/debug/kdb/kdb_private.h
+++ b/kernel/debug/kdb/kdb_private.h
@@ -240,8 +240,8 @@ extern void *debug_kmalloc(size_t size, gfp_t flags);
 extern void debug_kfree(void *);
 extern void debug_kusage(void);
 
-extern void kdb_set_current_task(struct task_struct *);
 extern struct task_struct *kdb_current_task;
+extern struct pt_regs *kdb_current_regs;
 
 #ifdef CONFIG_KDB_KEYBOARD
 extern void kdb_kbd_cleanup_state(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index ef82feb4bddc..60a1295f4384 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -692,7 +692,7 @@ void __mmdrop(struct mm_struct *mm)
 	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
-	mmu_notifier_mm_destroy(mm);
+	mmu_notifier_subscriptions_destroy(mm);
 	check_mm(mm);
 	put_user_ns(mm->user_ns);
 	free_mm(mm);
@@ -1025,7 +1025,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
 	RCU_INIT_POINTER(mm->exe_file, NULL);
-	mmu_notifier_mm_init(mm);
+	mmu_notifier_subscriptions_init(mm);
 	init_tlb_flush_pending(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index cfc4f088a0e7..9e5783d98033 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -176,20 +176,20 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode));
 }
 
-static const struct file_operations irq_affinity_proc_fops = {
-	.open		= irq_affinity_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= irq_affinity_proc_write,
+static const struct proc_ops irq_affinity_proc_ops = {
+	.proc_open	= irq_affinity_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= irq_affinity_proc_write,
 };
 
-static const struct file_operations irq_affinity_list_proc_fops = {
-	.open		= irq_affinity_list_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= irq_affinity_list_proc_write,
+static const struct proc_ops irq_affinity_list_proc_ops = {
+	.proc_open	= irq_affinity_list_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= irq_affinity_list_proc_write,
 };
 
 #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -246,12 +246,12 @@ static int default_affinity_open(struct inode *inode, struct file *file)
 	return single_open(file, default_affinity_show, PDE_DATA(inode));
 }
 
-static const struct file_operations default_affinity_proc_fops = {
-	.open		= default_affinity_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= default_affinity_write,
+static const struct proc_ops default_affinity_proc_ops = {
+	.proc_open	= default_affinity_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= default_affinity_write,
 };
 
 static int irq_node_proc_show(struct seq_file *m, void *v)
@@ -342,7 +342,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
 	proc_create_data("smp_affinity", 0644, desc->dir,
-			 &irq_affinity_proc_fops, irqp);
+			 &irq_affinity_proc_ops, irqp);
 
 	/* create /proc/irq/<irq>/affinity_hint */
 	proc_create_single_data("affinity_hint", 0444, desc->dir,
@@ -350,7 +350,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 	/* create /proc/irq/<irq>/smp_affinity_list */
 	proc_create_data("smp_affinity_list", 0644, desc->dir,
-			 &irq_affinity_list_proc_fops, irqp);
+			 &irq_affinity_list_proc_ops, irqp);
 
 	proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show,
 			irqp);
@@ -401,7 +401,7 @@ static void register_default_affinity_proc(void)
 {
 #ifdef CONFIG_SMP
 	proc_create("irq/default_smp_affinity", 0644, NULL,
-		    &default_affinity_proc_fops);
+		    &default_affinity_proc_ops);
 #endif
 }
 
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 136ce049c4ad..d812b90f4c86 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -698,16 +698,16 @@ const char *kdb_walk_kallsyms(loff_t *pos)
 }
 #endif	/* CONFIG_KGDB_KDB */
 
-static const struct file_operations kallsyms_operations = {
-	.open = kallsyms_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = seq_release_private,
+static const struct proc_ops kallsyms_proc_ops = {
+	.proc_open	= kallsyms_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release_private,
 };
 
 static int __init kallsyms_init(void)
 {
-	proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
+	proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops);
 	return 0;
 }
 device_initcall(kallsyms_init);
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index e3acead004e6..8d1c15832e55 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -255,17 +255,17 @@ static int lstats_open(struct inode *inode, struct file *filp)
 	return single_open(filp, lstats_show, NULL);
 }
 
-static const struct file_operations lstats_fops = {
-	.open		= lstats_open,
-	.read		= seq_read,
-	.write		= lstats_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
+static const struct proc_ops lstats_proc_ops = {
+	.proc_open	= lstats_open,
+	.proc_read	= seq_read,
+	.proc_write	= lstats_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 static int __init init_lstats_procfs(void)
 {
-	proc_create("latency_stats", 0644, NULL, &lstats_fops);
+	proc_create("latency_stats", 0644, NULL, &lstats_proc_ops);
 	return 0;
 }
 
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index 9bb6d2497b04..231684cfc5ae 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -643,12 +643,12 @@ static int lock_stat_release(struct inode *inode, struct file *file)
 	return seq_release(inode, file);
 }
 
-static const struct file_operations proc_lock_stat_operations = {
-	.open		= lock_stat_open,
-	.write		= lock_stat_write,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= lock_stat_release,
+static const struct proc_ops lock_stat_proc_ops = {
+	.proc_open	= lock_stat_open,
+	.proc_write	= lock_stat_write,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= lock_stat_release,
 };
 #endif /* CONFIG_LOCK_STAT */
 
@@ -660,8 +660,7 @@ static int __init lockdep_proc_init(void)
 #endif
 	proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show);
 #ifdef CONFIG_LOCK_STAT
-	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL,
-		    &proc_lock_stat_operations);
+	proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, &lock_stat_proc_ops);
 #endif
 
 	return 0;
diff --git a/kernel/module.c b/kernel/module.c
index ac058a5ad1d1..33569a01d6e1 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -214,7 +214,8 @@ static struct module *mod_find(unsigned long addr)
 {
 	struct module *mod;
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
 		if (within_module(addr, mod))
 			return mod;
 	}
@@ -448,7 +449,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
 	if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data))
 		return true;
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
 		struct symsearch arr[] = {
 			{ mod->syms, mod->syms + mod->num_syms, mod->crcs,
 			  NOT_GPL_ONLY, false },
@@ -616,7 +618,8 @@ static struct module *find_module_all(const char *name, size_t len,
 
 	module_assert_mutex_or_preempt();
 
-	list_for_each_entry_rcu(mod, &modules, list) {
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
 			continue;
 		if (strlen(mod->name) == len && !memcmp(mod->name, name, len))
@@ -1781,6 +1784,8 @@ static int module_add_modinfo_attrs(struct module *mod)
 error_out:
 	if (i > 0)
 		module_remove_modinfo_attrs(mod, --i);
+	else
+		kfree(mod->modinfo_attrs);
 	return error;
 }
 
@@ -2834,7 +2839,7 @@ static int module_sig_check(struct load_info *info, int flags)
 		reason = "Loading of module with unavailable key";
 	decide:
 		if (is_module_sig_enforced()) {
-			pr_notice("%s is rejected\n", reason);
+			pr_notice("%s: %s is rejected\n", info->name, reason);
 			return -EKEYREJECTED;
 		}
 
@@ -3011,9 +3016,7 @@ static int setup_load_info(struct load_info *info, int flags)
 
 	/* Try to find a name early so we can log errors with a module name */
 	info->index.info = find_sec(info, ".modinfo");
-	if (!info->index.info)
-		info->name = "(missing .modinfo section)";
-	else
+	if (info->index.info)
 		info->name = get_modinfo(info, "name");
 
 	/* Find internal symbols and strings. */
@@ -3028,14 +3031,15 @@ static int setup_load_info(struct load_info *info, int flags)
 	}
 
 	if (info->index.sym == 0) {
-		pr_warn("%s: module has no symbols (stripped?)\n", info->name);
+		pr_warn("%s: module has no symbols (stripped?)\n",
+			info->name ?: "(missing .modinfo section or name field)");
 		return -ENOEXEC;
 	}
 
 	info->index.mod = find_sec(info, ".gnu.linkonce.this_module");
 	if (!info->index.mod) {
 		pr_warn("%s: No module found in object\n",
-			info->name ?: "(missing .modinfo name field)");
+			info->name ?: "(missing .modinfo section or name field)");
 		return -ENOEXEC;
 	}
 	/* This is temporary: point mod into copy of data. */
@@ -4350,16 +4354,16 @@ static int modules_open(struct inode *inode, struct file *file)
 	return err;
 }
 
-static const struct file_operations proc_modules_operations = {
-	.open		= modules_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops modules_proc_ops = {
+	.proc_open	= modules_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static int __init proc_modules_init(void)
 {
-	proc_create("modules", 0, NULL, &proc_modules_operations);
+	proc_create("modules", 0, NULL, &modules_proc_ops);
 	return 0;
 }
 module_init(proc_modules_init);
diff --git a/kernel/pid.c b/kernel/pid.c
index 2278e249141d..0f4ecb57214c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -578,3 +578,93 @@ void __init pid_idr_init(void)
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 }
+
+static struct file *__pidfd_fget(struct task_struct *task, int fd)
+{
+	struct file *file;
+	int ret;
+
+	ret = mutex_lock_killable(&task->signal->cred_guard_mutex);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS))
+		file = fget_task(task, fd);
+	else
+		file = ERR_PTR(-EPERM);
+
+	mutex_unlock(&task->signal->cred_guard_mutex);
+
+	return file ?: ERR_PTR(-EBADF);
+}
+
+static int pidfd_getfd(struct pid *pid, int fd)
+{
+	struct task_struct *task;
+	struct file *file;
+	int ret;
+
+	task = get_pid_task(pid, PIDTYPE_PID);
+	if (!task)
+		return -ESRCH;
+
+	file = __pidfd_fget(task, fd);
+	put_task_struct(task);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ret = security_file_receive(file);
+	if (ret) {
+		fput(file);
+		return ret;
+	}
+
+	ret = get_unused_fd_flags(O_CLOEXEC);
+	if (ret < 0)
+		fput(file);
+	else
+		fd_install(ret, file);
+
+	return ret;
+}
+
+/**
+ * sys_pidfd_getfd() - Get a file descriptor from another process
+ *
+ * @pidfd:	the pidfd file descriptor of the process
+ * @fd:		the file descriptor number to get
+ * @flags:	flags on how to get the fd (reserved)
+ *
+ * This syscall gets a copy of a file descriptor from another process
+ * based on the pidfd, and file descriptor number. It requires that
+ * the calling process has the ability to ptrace the process represented
+ * by the pidfd. The process which is having its file descriptor copied
+ * is otherwise unaffected.
+ *
+ * Return: On success, a cloexec file descriptor is returned.
+ *         On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd,
+		unsigned int, flags)
+{
+	struct pid *pid;
+	struct fd f;
+	int ret;
+
+	/* flags is currently unused - make sure it's unset */
+	if (flags)
+		return -EINVAL;
+
+	f = fdget(pidfd);
+	if (!f.file)
+		return -EBADF;
+
+	pid = pidfd_pid(f.file);
+	if (IS_ERR(pid))
+		ret = PTR_ERR(pid);
+	else
+		ret = pidfd_getfd(pid, fd);
+
+	fdput(f);
+	return ret;
+}
diff --git a/kernel/profile.c b/kernel/profile.c
index 4b144b02ca5d..6f69a4195d56 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -442,18 +442,18 @@ static ssize_t prof_cpu_mask_proc_write(struct file *file,
 	return err;
 }
 
-static const struct file_operations prof_cpu_mask_proc_fops = {
-	.open		= prof_cpu_mask_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-	.write		= prof_cpu_mask_proc_write,
+static const struct proc_ops prof_cpu_mask_proc_ops = {
+	.proc_open	= prof_cpu_mask_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+	.proc_write	= prof_cpu_mask_proc_write,
 };
 
 void create_prof_cpu_mask(void)
 {
 	/* create /proc/irq/prof_cpu_mask */
-	proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_fops);
+	proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops);
 }
 
 /*
@@ -517,10 +517,10 @@ static ssize_t write_profile(struct file *file, const char __user *buf,
 	return count;
 }
 
-static const struct file_operations proc_profile_operations = {
-	.read		= read_profile,
-	.write		= write_profile,
-	.llseek		= default_llseek,
+static const struct proc_ops profile_proc_ops = {
+	.proc_read	= read_profile,
+	.proc_write	= write_profile,
+	.proc_lseek	= default_llseek,
 };
 
 int __ref create_proc_profile(void)
@@ -548,7 +548,7 @@ int __ref create_proc_profile(void)
 	err = 0;
 #endif
 	entry = proc_create("profile", S_IWUSR | S_IRUGO,
-			    NULL, &proc_profile_operations);
+			    NULL, &profile_proc_ops);
 	if (!entry)
 		goto err_state_onl;
 	proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t));
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index db7b50bba3f1..ac4bd0ca11cc 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -1251,40 +1251,40 @@ static int psi_fop_release(struct inode *inode, struct file *file)
 	return single_release(inode, file);
 }
 
-static const struct file_operations psi_io_fops = {
-	.open           = psi_io_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.write          = psi_io_write,
-	.poll           = psi_fop_poll,
-	.release        = psi_fop_release,
+static const struct proc_ops psi_io_proc_ops = {
+	.proc_open	= psi_io_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_io_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
 };
 
-static const struct file_operations psi_memory_fops = {
-	.open           = psi_memory_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.write          = psi_memory_write,
-	.poll           = psi_fop_poll,
-	.release        = psi_fop_release,
+static const struct proc_ops psi_memory_proc_ops = {
+	.proc_open	= psi_memory_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_memory_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
 };
 
-static const struct file_operations psi_cpu_fops = {
-	.open           = psi_cpu_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.write          = psi_cpu_write,
-	.poll           = psi_fop_poll,
-	.release        = psi_fop_release,
+static const struct proc_ops psi_cpu_proc_ops = {
+	.proc_open	= psi_cpu_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= psi_cpu_write,
+	.proc_poll	= psi_fop_poll,
+	.proc_release	= psi_fop_release,
 };
 
 static int __init psi_proc_init(void)
 {
 	if (psi_enable) {
 		proc_mkdir("pressure", NULL);
-		proc_create("pressure/io", 0, NULL, &psi_io_fops);
-		proc_create("pressure/memory", 0, NULL, &psi_memory_fops);
-		proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops);
+		proc_create("pressure/io", 0, NULL, &psi_io_proc_ops);
+		proc_create("pressure/memory", 0, NULL, &psi_memory_proc_ops);
+		proc_create("pressure/cpu", 0, NULL, &psi_cpu_proc_ops);
 	}
 	return 0;
 }
diff --git a/kernel/signal.c b/kernel/signal.c
index bcd46f547db3..9ad8dea93dbb 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1383,7 +1383,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 		 * must see ->sighand == NULL.
 		 */
 		spin_lock_irqsave(&sighand->siglock, *flags);
-		if (likely(sighand == tsk->sighand))
+		if (likely(sighand == rcu_access_pointer(tsk->sighand)))
 			break;
 		spin_unlock_irqrestore(&sighand->siglock, *flags);
 	}
diff --git a/kernel/sys.c b/kernel/sys.c
index a9331f101883..f9bc5c303e3f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2261,6 +2261,8 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
 	return -EINVAL;
 }
 
+#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE)
+
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		unsigned long, arg4, unsigned long, arg5)
 {
@@ -2488,6 +2490,29 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = GET_TAGGED_ADDR_CTRL();
 		break;
+	case PR_SET_IO_FLUSHER:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		if (arg2 == 1)
+			current->flags |= PR_IO_FLUSHER;
+		else if (!arg2)
+			current->flags &= ~PR_IO_FLUSHER;
+		else
+			return -EINVAL;
+		break;
+	case PR_GET_IO_FLUSHER:
+		if (!capable(CAP_SYS_RESOURCE))
+			return -EPERM;
+
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+
+		error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER;
+		break;
 	default:
 		error = -EINVAL;
 		break;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5b6ee4aadc26..5e02d65505c1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8504,7 +8504,7 @@ static struct trace_array *trace_array_create(const char *name)
 
 	ret = event_trace_add_tracer(tr->dir, tr);
 	if (ret) {
-		tracefs_remove_recursive(tr->dir);
+		tracefs_remove(tr->dir);
 		goto out_free_tr;
 	}
 
@@ -8613,7 +8613,7 @@ static int __remove_instance(struct trace_array *tr)
 	event_trace_del_tracer(tr);
 	ftrace_clear_pids(tr);
 	ftrace_destroy_function_files(tr);
-	tracefs_remove_recursive(tr->dir);
+	tracefs_remove(tr->dir);
 	free_trace_buffers(tr);
 
 	for (i = 0; i < tr->nr_topts; i++) {
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c8622a44d300..fcd3975a88d1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -698,7 +698,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir)
 		return;
 
 	if (!--dir->nr_events) {
-		tracefs_remove_recursive(dir->entry);
+		tracefs_remove(dir->entry);
 		list_del(&dir->list);
 		__put_system_dir(dir);
 	}
@@ -717,7 +717,7 @@ static void remove_event_file_dir(struct trace_event_file *file)
 		}
 		spin_unlock(&dir->d_lock);
 
-		tracefs_remove_recursive(dir);
+		tracefs_remove(dir);
 	}
 
 	list_del(&file->list);
@@ -3082,7 +3082,7 @@ int event_trace_del_tracer(struct trace_array *tr)
 
 	down_write(&trace_event_sem);
 	__trace_remove_event_dirs(tr);
-	tracefs_remove_recursive(tr->event_dir);
+	tracefs_remove(tr->event_dir);
 	up_write(&trace_event_sem);
 
 	tr->event_dir = NULL;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 6638d63f0921..402d022d0229 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -556,7 +556,7 @@ static int init_tracefs(void)
 	return 0;
 
  err:
-	tracefs_remove_recursive(top_dir);
+	tracefs_remove(top_dir);
 	return -ENOMEM;
 }
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 6e790dc55c5b..bc7e56370129 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -278,6 +278,13 @@ config ZLIB_DEFLATE
 	tristate
 	select BITREVERSE
 
+config ZLIB_DFLTCC
+	def_bool y
+	depends on S390
+	prompt "Enable s390x DEFLATE CONVERSION CALL support for kernel zlib"
+	help
+	 Enable s390x hardware support for zlib in the kernel.
+
 config LZO_COMPRESS
 	tristate
 
diff --git a/lib/Makefile b/lib/Makefile
index c20b1debe9b4..23ca78d43d24 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -16,6 +16,7 @@ KCOV_INSTRUMENT_rbtree.o := n
 KCOV_INSTRUMENT_list_debug.o := n
 KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
+KCOV_INSTRUMENT_fault-inject.o := n
 
 # Early boot use of cmdline, don't instrument it
 ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -140,6 +141,7 @@ obj-$(CONFIG_842_COMPRESS) += 842/
 obj-$(CONFIG_842_DECOMPRESS) += 842/
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
+obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_BCH) += bch.o
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 6e175fbd69a9..89260aa342d6 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -431,97 +431,6 @@ EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
  * second version by Paul Jackson, third by Joe Korty.
  */
 
-#define CHUNKSZ				32
-#define nbits_to_hold_value(val)	fls(val)
-#define BASEDEC 10		/* fancier cpuset lists input in decimal */
-
-/**
- * __bitmap_parse - convert an ASCII hex string into a bitmap.
- * @buf: pointer to buffer containing string.
- * @buflen: buffer size in bytes.  If string is smaller than this
- *    then it must be terminated with a \0.
- * @is_user: location of buffer, 0 indicates kernel space
- * @maskp: pointer to bitmap array that will contain result.
- * @nmaskbits: size of bitmap, in bits.
- *
- * Commas group hex digits into chunks.  Each chunk defines exactly 32
- * bits of the resultant bitmask.  No chunk may specify a value larger
- * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value
- * then leading 0-bits are prepended.  %-EINVAL is returned for illegal
- * characters and for grouping errors such as "1,,5", ",44", "," and "".
- * Leading and trailing whitespace accepted, but not embedded whitespace.
- */
-int __bitmap_parse(const char *buf, unsigned int buflen,
-		int is_user, unsigned long *maskp,
-		int nmaskbits)
-{
-	int c, old_c, totaldigits, ndigits, nchunks, nbits;
-	u32 chunk;
-	const char __user __force *ubuf = (const char __user __force *)buf;
-
-	bitmap_zero(maskp, nmaskbits);
-
-	nchunks = nbits = totaldigits = c = 0;
-	do {
-		chunk = 0;
-		ndigits = totaldigits;
-
-		/* Get the next chunk of the bitmap */
-		while (buflen) {
-			old_c = c;
-			if (is_user) {
-				if (__get_user(c, ubuf++))
-					return -EFAULT;
-			}
-			else
-				c = *buf++;
-			buflen--;
-			if (isspace(c))
-				continue;
-
-			/*
-			 * If the last character was a space and the current
-			 * character isn't '\0', we've got embedded whitespace.
-			 * This is a no-no, so throw an error.
-			 */
-			if (totaldigits && c && isspace(old_c))
-				return -EINVAL;
-
-			/* A '\0' or a ',' signal the end of the chunk */
-			if (c == '\0' || c == ',')
-				break;
-
-			if (!isxdigit(c))
-				return -EINVAL;
-
-			/*
-			 * Make sure there are at least 4 free bits in 'chunk'.
-			 * If not, this hexdigit will overflow 'chunk', so
-			 * throw an error.
-			 */
-			if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1))
-				return -EOVERFLOW;
-
-			chunk = (chunk << 4) | hex_to_bin(c);
-			totaldigits++;
-		}
-		if (ndigits == totaldigits)
-			return -EINVAL;
-		if (nchunks == 0 && chunk == 0)
-			continue;
-
-		__bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits);
-		*maskp |= chunk;
-		nchunks++;
-		nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ;
-		if (nbits > nmaskbits)
-			return -EOVERFLOW;
-	} while (buflen && c == ',');
-
-	return 0;
-}
-EXPORT_SYMBOL(__bitmap_parse);
-
 /**
  * bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap
  *
@@ -530,22 +439,22 @@ EXPORT_SYMBOL(__bitmap_parse);
  *    then it must be terminated with a \0.
  * @maskp: pointer to bitmap array that will contain result.
  * @nmaskbits: size of bitmap, in bits.
- *
- * Wrapper for __bitmap_parse(), providing it with user buffer.
- *
- * We cannot have this as an inline function in bitmap.h because it needs
- * linux/uaccess.h to get the access_ok() declaration and this causes
- * cyclic dependencies.
  */
 int bitmap_parse_user(const char __user *ubuf,
 			unsigned int ulen, unsigned long *maskp,
 			int nmaskbits)
 {
-	if (!access_ok(ubuf, ulen))
-		return -EFAULT;
-	return __bitmap_parse((const char __force *)ubuf,
-				ulen, 1, maskp, nmaskbits);
+	char *buf;
+	int ret;
 
+	buf = memdup_user_nul(ubuf, ulen);
+	if (IS_ERR(buf))
+		return PTR_ERR(buf);
+
+	ret = bitmap_parse(buf, UINT_MAX, maskp, nmaskbits);
+
+	kfree(buf);
+	return ret;
 }
 EXPORT_SYMBOL(bitmap_parse_user);
 
@@ -653,6 +562,14 @@ static const char *bitmap_find_region(const char *str)
 	return end_of_str(*str) ? NULL : str;
 }
 
+static const char *bitmap_find_region_reverse(const char *start, const char *end)
+{
+	while (start <= end && __end_of_region(*end))
+		end--;
+
+	return end;
+}
+
 static const char *bitmap_parse_region(const char *str, struct region *r)
 {
 	str = bitmap_getnum(str, &r->start);
@@ -776,6 +693,80 @@ int bitmap_parselist_user(const char __user *ubuf,
 }
 EXPORT_SYMBOL(bitmap_parselist_user);
 
+static const char *bitmap_get_x32_reverse(const char *start,
+					const char *end, u32 *num)
+{
+	u32 ret = 0;
+	int c, i;
+
+	for (i = 0; i < 32; i += 4) {
+		c = hex_to_bin(*end--);
+		if (c < 0)
+			return ERR_PTR(-EINVAL);
+
+		ret |= c << i;
+
+		if (start > end || __end_of_region(*end))
+			goto out;
+	}
+
+	if (hex_to_bin(*end--) >= 0)
+		return ERR_PTR(-EOVERFLOW);
+out:
+	*num = ret;
+	return end;
+}
+
+/**
+ * bitmap_parse - convert an ASCII hex string into a bitmap.
+ * @start: pointer to buffer containing string.
+ * @buflen: buffer size in bytes.  If string is smaller than this
+ *    then it must be terminated with a \0 or \n. In that case,
+ *    UINT_MAX may be provided instead of string length.
+ * @maskp: pointer to bitmap array that will contain result.
+ * @nmaskbits: size of bitmap, in bits.
+ *
+ * Commas group hex digits into chunks.  Each chunk defines exactly 32
+ * bits of the resultant bitmask.  No chunk may specify a value larger
+ * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value
+ * then leading 0-bits are prepended.  %-EINVAL is returned for illegal
+ * characters. Grouping such as "1,,5", ",44", "," or "" is allowed.
+ * Leading, embedded and trailing whitespace accepted.
+ */
+int bitmap_parse(const char *start, unsigned int buflen,
+		unsigned long *maskp, int nmaskbits)
+{
+	const char *end = strnchrnul(start, buflen, '\n') - 1;
+	int chunks = BITS_TO_U32(nmaskbits);
+	u32 *bitmap = (u32 *)maskp;
+	int unset_bit;
+
+	while (1) {
+		end = bitmap_find_region_reverse(start, end);
+		if (start > end)
+			break;
+
+		if (!chunks--)
+			return -EOVERFLOW;
+
+		end = bitmap_get_x32_reverse(start, end, bitmap++);
+		if (IS_ERR(end))
+			return PTR_ERR(end);
+	}
+
+	unset_bit = (BITS_TO_U32(nmaskbits) - chunks) * 32;
+	if (unset_bit < nmaskbits) {
+		bitmap_clear(maskp, unset_bit, nmaskbits - unset_bit);
+		return 0;
+	}
+
+	if (find_next_bit(maskp, unset_bit, nmaskbits) != unset_bit)
+		return -EOVERFLOW;
+
+	return 0;
+}
+EXPORT_SYMBOL(bitmap_parse);
+
 
 #ifdef CONFIG_NUMA
 /**
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index 63b4b7eee138..6130c42b8e59 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -10,6 +10,10 @@
 #include "zlib_inflate/inftrees.c"
 #include "zlib_inflate/inffast.c"
 #include "zlib_inflate/inflate.c"
+#ifdef CONFIG_ZLIB_DFLTCC
+#include "zlib_dfltcc/dfltcc.c"
+#include "zlib_dfltcc/dfltcc_inflate.c"
+#endif
 
 #else /* STATIC */
 /* initramfs et al: linked */
@@ -76,7 +80,12 @@ STATIC int INIT __gunzip(unsigned char *buf, long len,
 	}
 
 	strm->workspace = malloc(flush ? zlib_inflate_workspacesize() :
+#ifdef CONFIG_ZLIB_DFLTCC
+	/* Always allocate the full workspace for DFLTCC */
+				 zlib_inflate_workspacesize());
+#else
 				 sizeof(struct inflate_state));
+#endif
 	if (strm->workspace == NULL) {
 		error("Out of memory while allocating workspace");
 		goto gunzip_nomem4;
@@ -123,10 +132,14 @@ STATIC int INIT __gunzip(unsigned char *buf, long len,
 
 	rc = zlib_inflateInit2(strm, -MAX_WBITS);
 
+#ifdef CONFIG_ZLIB_DFLTCC
+	/* Always keep the window for DFLTCC */
+#else
 	if (!flush) {
 		WS(strm)->inflate_state.wsize = 0;
 		WS(strm)->inflate_state.window = NULL;
 	}
+#endif
 
 	while (rc == Z_OK) {
 		if (strm->avail_in == 0) {
diff --git a/lib/find_bit.c b/lib/find_bit.c
index e35a76b291e6..49f875f1baf7 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -17,9 +17,9 @@
 #include <linux/export.h>
 #include <linux/kernel.h>
 
-#if !defined(find_next_bit) || !defined(find_next_zero_bit) || \
-		!defined(find_next_and_bit)
-
+#if !defined(find_next_bit) || !defined(find_next_zero_bit) ||			\
+	!defined(find_next_bit_le) || !defined(find_next_zero_bit_le) ||	\
+	!defined(find_next_and_bit)
 /*
  * This is a common helper function for find_next_bit, find_next_zero_bit, and
  * find_next_and_bit. The differences are:
@@ -27,11 +27,11 @@
  *    searching it for one bits.
  *  - The optional "addr2", which is anded with "addr1" if present.
  */
-static inline unsigned long _find_next_bit(const unsigned long *addr1,
+static unsigned long _find_next_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long nbits,
-		unsigned long start, unsigned long invert)
+		unsigned long start, unsigned long invert, unsigned long le)
 {
-	unsigned long tmp;
+	unsigned long tmp, mask;
 
 	if (unlikely(start >= nbits))
 		return nbits;
@@ -42,7 +42,12 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
 	tmp ^= invert;
 
 	/* Handle 1st word. */
-	tmp &= BITMAP_FIRST_WORD_MASK(start);
+	mask = BITMAP_FIRST_WORD_MASK(start);
+	if (le)
+		mask = swab(mask);
+
+	tmp &= mask;
+
 	start = round_down(start, BITS_PER_LONG);
 
 	while (!tmp) {
@@ -56,6 +61,9 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
 		tmp ^= invert;
 	}
 
+	if (le)
+		tmp = swab(tmp);
+
 	return min(start + __ffs(tmp), nbits);
 }
 #endif
@@ -67,7 +75,7 @@ static inline unsigned long _find_next_bit(const unsigned long *addr1,
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
-	return _find_next_bit(addr, NULL, size, offset, 0UL);
+	return _find_next_bit(addr, NULL, size, offset, 0UL, 0);
 }
 EXPORT_SYMBOL(find_next_bit);
 #endif
@@ -76,7 +84,7 @@ EXPORT_SYMBOL(find_next_bit);
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
-	return _find_next_bit(addr, NULL, size, offset, ~0UL);
+	return _find_next_bit(addr, NULL, size, offset, ~0UL, 0);
 }
 EXPORT_SYMBOL(find_next_zero_bit);
 #endif
@@ -86,7 +94,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
 {
-	return _find_next_bit(addr1, addr2, size, offset, 0UL);
+	return _find_next_bit(addr1, addr2, size, offset, 0UL, 0);
 }
 EXPORT_SYMBOL(find_next_and_bit);
 #endif
@@ -149,57 +157,11 @@ EXPORT_SYMBOL(find_last_bit);
 
 #ifdef __BIG_ENDIAN
 
-/* include/linux/byteorder does not support "unsigned long" type */
-static inline unsigned long ext2_swab(const unsigned long y)
-{
-#if BITS_PER_LONG == 64
-	return (unsigned long) __swab64((u64) y);
-#elif BITS_PER_LONG == 32
-	return (unsigned long) __swab32((u32) y);
-#else
-#error BITS_PER_LONG not defined
-#endif
-}
-
-#if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le)
-static inline unsigned long _find_next_bit_le(const unsigned long *addr1,
-		const unsigned long *addr2, unsigned long nbits,
-		unsigned long start, unsigned long invert)
-{
-	unsigned long tmp;
-
-	if (unlikely(start >= nbits))
-		return nbits;
-
-	tmp = addr1[start / BITS_PER_LONG];
-	if (addr2)
-		tmp &= addr2[start / BITS_PER_LONG];
-	tmp ^= invert;
-
-	/* Handle 1st word. */
-	tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
-	start = round_down(start, BITS_PER_LONG);
-
-	while (!tmp) {
-		start += BITS_PER_LONG;
-		if (start >= nbits)
-			return nbits;
-
-		tmp = addr1[start / BITS_PER_LONG];
-		if (addr2)
-			tmp &= addr2[start / BITS_PER_LONG];
-		tmp ^= invert;
-	}
-
-	return min(start + __ffs(ext2_swab(tmp)), nbits);
-}
-#endif
-
 #ifndef find_next_zero_bit_le
 unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
-	return _find_next_bit_le(addr, NULL, size, offset, ~0UL);
+	return _find_next_bit(addr, NULL, size, offset, ~0UL, 1);
 }
 EXPORT_SYMBOL(find_next_zero_bit_le);
 #endif
@@ -208,7 +170,7 @@ EXPORT_SYMBOL(find_next_zero_bit_le);
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
-	return _find_next_bit_le(addr, NULL, size, offset, 0UL);
+	return _find_next_bit(addr, NULL, size, offset, 0UL, 1);
 }
 EXPORT_SYMBOL(find_next_bit_le);
 #endif
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index c2cf2c311b7d..5813072bc589 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -311,7 +311,7 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
 			if (prv)
 				table->nents = ++table->orig_nents;
 
- 			return -ENOMEM;
+			return -ENOMEM;
 		}
 
 		sg_init_table(sg, alloc_size);
diff --git a/lib/string.c b/lib/string.c
index 08ec58cc673b..f607b967d978 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -434,6 +434,23 @@ char *strchrnul(const char *s, int c)
 EXPORT_SYMBOL(strchrnul);
 #endif
 
+/**
+ * strnchrnul - Find and return a character in a length limited string,
+ * or end of string
+ * @s: The string to be searched
+ * @count: The number of characters to be searched
+ * @c: The character to search for
+ *
+ * Returns pointer to the first occurrence of 'c' in s. If c is not found,
+ * then return a pointer to the last character of the string.
+ */
+char *strnchrnul(const char *s, size_t count, int c)
+{
+	while (count-- && *s && *s != (char)c)
+		s++;
+	return (char *)s;
+}
+
 #ifndef __HAVE_ARCH_STRRCHR
 /**
  * strrchr - Find the last occurrence of a character in a string
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index e14a15ac250b..61ed71c1daba 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -275,26 +275,28 @@ static void __init test_copy(void)
 static void __init test_replace(void)
 {
 	unsigned int nbits = 64;
+	unsigned int nlongs = DIV_ROUND_UP(nbits, BITS_PER_LONG);
 	DECLARE_BITMAP(bmap, 1024);
 
 	bitmap_zero(bmap, 1024);
-	bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits);
+	bitmap_replace(bmap, &exp2[0 * nlongs], &exp2[1 * nlongs], exp2_to_exp3_mask, nbits);
 	expect_eq_bitmap(bmap, exp3_0_1, nbits);
 
 	bitmap_zero(bmap, 1024);
-	bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits);
+	bitmap_replace(bmap, &exp2[1 * nlongs], &exp2[0 * nlongs], exp2_to_exp3_mask, nbits);
 	expect_eq_bitmap(bmap, exp3_1_0, nbits);
 
 	bitmap_fill(bmap, 1024);
-	bitmap_replace(bmap, &exp2[0], &exp2[1], exp2_to_exp3_mask, nbits);
+	bitmap_replace(bmap, &exp2[0 * nlongs], &exp2[1 * nlongs], exp2_to_exp3_mask, nbits);
 	expect_eq_bitmap(bmap, exp3_0_1, nbits);
 
 	bitmap_fill(bmap, 1024);
-	bitmap_replace(bmap, &exp2[1], &exp2[0], exp2_to_exp3_mask, nbits);
+	bitmap_replace(bmap, &exp2[1 * nlongs], &exp2[0 * nlongs], exp2_to_exp3_mask, nbits);
 	expect_eq_bitmap(bmap, exp3_1_0, nbits);
 }
 
-#define PARSE_TIME 0x1
+#define PARSE_TIME	0x1
+#define NO_LEN		0x2
 
 struct test_bitmap_parselist{
 	const int errno;
@@ -348,7 +350,6 @@ static const struct test_bitmap_parselist parselist_tests[] __initconst = {
 	{-EINVAL, "0-31:a/1", NULL, 8, 0},
 	{-EINVAL, "0-\n", NULL, 8, 0},
 
-#undef step
 };
 
 static void __init __test_bitmap_parselist(int is_user)
@@ -400,6 +401,95 @@ static void __init __test_bitmap_parselist(int is_user)
 	}
 }
 
+static const unsigned long parse_test[] __initconst = {
+	BITMAP_FROM_U64(0),
+	BITMAP_FROM_U64(1),
+	BITMAP_FROM_U64(0xdeadbeef),
+	BITMAP_FROM_U64(0x100000000ULL),
+};
+
+static const unsigned long parse_test2[] __initconst = {
+	BITMAP_FROM_U64(0x100000000ULL), BITMAP_FROM_U64(0xdeadbeef),
+	BITMAP_FROM_U64(0x100000000ULL), BITMAP_FROM_U64(0xbaadf00ddeadbeef),
+	BITMAP_FROM_U64(0x100000000ULL), BITMAP_FROM_U64(0x0badf00ddeadbeef),
+};
+
+static const struct test_bitmap_parselist parse_tests[] __initconst = {
+	{0, "",				&parse_test[0 * step], 32, 0},
+	{0, " ",			&parse_test[0 * step], 32, 0},
+	{0, "0",			&parse_test[0 * step], 32, 0},
+	{0, "0\n",			&parse_test[0 * step], 32, 0},
+	{0, "1",			&parse_test[1 * step], 32, 0},
+	{0, "deadbeef",			&parse_test[2 * step], 32, 0},
+	{0, "1,0",			&parse_test[3 * step], 33, 0},
+	{0, "deadbeef,\n,0,1",		&parse_test[2 * step], 96, 0},
+
+	{0, "deadbeef,1,0",		&parse_test2[0 * 2 * step], 96, 0},
+	{0, "baadf00d,deadbeef,1,0",	&parse_test2[1 * 2 * step], 128, 0},
+	{0, "badf00d,deadbeef,1,0",	&parse_test2[2 * 2 * step], 124, 0},
+	{0, "badf00d,deadbeef,1,0",	&parse_test2[2 * 2 * step], 124, NO_LEN},
+	{0, "  badf00d,deadbeef,1,0  ",	&parse_test2[2 * 2 * step], 124, 0},
+	{0, " , badf00d,deadbeef,1,0 , ",	&parse_test2[2 * 2 * step], 124, 0},
+	{0, " , badf00d, ,, ,,deadbeef,1,0 , ",	&parse_test2[2 * 2 * step], 124, 0},
+
+	{-EINVAL,    "goodfood,deadbeef,1,0",	NULL, 128, 0},
+	{-EOVERFLOW, "3,0",			NULL, 33, 0},
+	{-EOVERFLOW, "123badf00d,deadbeef,1,0",	NULL, 128, 0},
+	{-EOVERFLOW, "badf00d,deadbeef,1,0",	NULL, 90, 0},
+	{-EOVERFLOW, "fbadf00d,deadbeef,1,0",	NULL, 95, 0},
+	{-EOVERFLOW, "badf00d,deadbeef,1,0",	NULL, 100, 0},
+#undef step
+};
+
+static void __init __test_bitmap_parse(int is_user)
+{
+	int i;
+	int err;
+	ktime_t time;
+	DECLARE_BITMAP(bmap, 2048);
+	char *mode = is_user ? "_user"  : "";
+
+	for (i = 0; i < ARRAY_SIZE(parse_tests); i++) {
+		struct test_bitmap_parselist test = parse_tests[i];
+
+		if (is_user) {
+			size_t len = strlen(test.in);
+			mm_segment_t orig_fs = get_fs();
+
+			set_fs(KERNEL_DS);
+			time = ktime_get();
+			err = bitmap_parse_user((__force const char __user *)test.in, len,
+						bmap, test.nbits);
+			time = ktime_get() - time;
+			set_fs(orig_fs);
+		} else {
+			size_t len = test.flags & NO_LEN ?
+				UINT_MAX : strlen(test.in);
+			time = ktime_get();
+			err = bitmap_parse(test.in, len, bmap, test.nbits);
+			time = ktime_get() - time;
+		}
+
+		if (err != test.errno) {
+			pr_err("parse%s: %d: input is %s, errno is %d, expected %d\n",
+					mode, i, test.in, err, test.errno);
+			continue;
+		}
+
+		if (!err && test.expected
+			 && !__bitmap_equal(bmap, test.expected, test.nbits)) {
+			pr_err("parse%s: %d: input is %s, result is 0x%lx, expected 0x%lx\n",
+					mode, i, test.in, bmap[0],
+					*test.expected);
+			continue;
+		}
+
+		if (test.flags & PARSE_TIME)
+			pr_err("parse%s: %d: input is '%s' OK, Time: %llu\n",
+					mode, i, test.in, time);
+	}
+}
+
 static void __init test_bitmap_parselist(void)
 {
 	__test_bitmap_parselist(0);
@@ -410,6 +500,16 @@ static void __init test_bitmap_parselist_user(void)
 	__test_bitmap_parselist(1);
 }
 
+static void __init test_bitmap_parse(void)
+{
+	__test_bitmap_parse(0);
+}
+
+static void __init test_bitmap_parse_user(void)
+{
+	__test_bitmap_parse(1);
+}
+
 #define EXP1_IN_BITS	(sizeof(exp1) * 8)
 
 static void __init test_bitmap_arr32(void)
@@ -515,6 +615,8 @@ static void __init selftest(void)
 	test_copy();
 	test_replace();
 	test_bitmap_arr32();
+	test_bitmap_parse();
+	test_bitmap_parse_user();
 	test_bitmap_parselist();
 	test_bitmap_parselist_user();
 	test_mem_optimisations();
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 328d33beae36..3872d250ed2c 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -158,6 +158,7 @@ static noinline void __init kmalloc_oob_krealloc_more(void)
 	if (!ptr1 || !ptr2) {
 		pr_err("Allocation failed\n");
 		kfree(ptr1);
+		kfree(ptr2);
 		return;
 	}
 
diff --git a/lib/zlib_deflate/deflate.c b/lib/zlib_deflate/deflate.c
index d20ef458f137..8a878d0d892c 100644
--- a/lib/zlib_deflate/deflate.c
+++ b/lib/zlib_deflate/deflate.c
@@ -52,16 +52,19 @@
 #include <linux/zutil.h>
 #include "defutil.h"
 
+/* architecture-specific bits */
+#ifdef CONFIG_ZLIB_DFLTCC
+#  include "../zlib_dfltcc/dfltcc.h"
+#else
+#define DEFLATE_RESET_HOOK(strm) do {} while (0)
+#define DEFLATE_HOOK(strm, flush, bstate) 0
+#define DEFLATE_NEED_CHECKSUM(strm) 1
+#define DEFLATE_DFLTCC_ENABLED() 0
+#endif
 
 /* ===========================================================================
  *  Function prototypes.
  */
-typedef enum {
-    need_more,      /* block not completed, need more input or more output */
-    block_done,     /* block flush performed */
-    finish_started, /* finish started, need only more output at next deflate */
-    finish_done     /* finish done, accept no more input or output */
-} block_state;
 
 typedef block_state (*compress_func) (deflate_state *s, int flush);
 /* Compression function. Returns the block state after the call. */
@@ -72,7 +75,6 @@ static block_state deflate_fast   (deflate_state *s, int flush);
 static block_state deflate_slow   (deflate_state *s, int flush);
 static void lm_init        (deflate_state *s);
 static void putShortMSB    (deflate_state *s, uInt b);
-static void flush_pending  (z_streamp strm);
 static int read_buf        (z_streamp strm, Byte *buf, unsigned size);
 static uInt longest_match  (deflate_state *s, IPos cur_match);
 
@@ -98,6 +100,25 @@ static  void check_match (deflate_state *s, IPos start, IPos match,
  * See deflate.c for comments about the MIN_MATCH+1.
  */
 
+/* Workspace to be allocated for deflate processing */
+typedef struct deflate_workspace {
+    /* State memory for the deflator */
+    deflate_state deflate_memory;
+#ifdef CONFIG_ZLIB_DFLTCC
+    /* State memory for s390 hardware deflate */
+    struct dfltcc_state dfltcc_memory;
+#endif
+    Byte *window_memory;
+    Pos *prev_memory;
+    Pos *head_memory;
+    char *overlay_memory;
+} deflate_workspace;
+
+#ifdef CONFIG_ZLIB_DFLTCC
+/* dfltcc_state must be doubleword aligned for DFLTCC call */
+static_assert(offsetof(struct deflate_workspace, dfltcc_memory) % 8 == 0);
+#endif
+
 /* Values for max_lazy_match, good_match and max_chain_length, depending on
  * the desired pack level (0..9). The values given below have been tuned to
  * exclude worst case performance for pathological files. Better values may be
@@ -207,7 +228,15 @@ int zlib_deflateInit2(
      */
     next = (char *) mem;
     next += sizeof(*mem);
+#ifdef CONFIG_ZLIB_DFLTCC
+    /*
+     *  DFLTCC requires the window to be page aligned.
+     *  Thus, we overallocate and take the aligned portion of the buffer.
+     */
+    mem->window_memory = (Byte *) PTR_ALIGN(next, PAGE_SIZE);
+#else
     mem->window_memory = (Byte *) next;
+#endif
     next += zlib_deflate_window_memsize(windowBits);
     mem->prev_memory = (Pos *) next;
     next += zlib_deflate_prev_memsize(windowBits);
@@ -277,6 +306,8 @@ int zlib_deflateReset(
     zlib_tr_init(s);
     lm_init(s);
 
+    DEFLATE_RESET_HOOK(strm);
+
     return Z_OK;
 }
 
@@ -294,35 +325,6 @@ static void putShortMSB(
     put_byte(s, (Byte)(b & 0xff));
 }   
 
-/* =========================================================================
- * Flush as much pending output as possible. All deflate() output goes
- * through this function so some applications may wish to modify it
- * to avoid allocating a large strm->next_out buffer and copying into it.
- * (See also read_buf()).
- */
-static void flush_pending(
-	z_streamp strm
-)
-{
-    deflate_state *s = (deflate_state *) strm->state;
-    unsigned len = s->pending;
-
-    if (len > strm->avail_out) len = strm->avail_out;
-    if (len == 0) return;
-
-    if (strm->next_out != NULL) {
-	memcpy(strm->next_out, s->pending_out, len);
-	strm->next_out += len;
-    }
-    s->pending_out += len;
-    strm->total_out += len;
-    strm->avail_out  -= len;
-    s->pending -= len;
-    if (s->pending == 0) {
-        s->pending_out = s->pending_buf;
-    }
-}
-
 /* ========================================================================= */
 int zlib_deflate(
 	z_streamp strm,
@@ -404,7 +406,8 @@ int zlib_deflate(
         (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) {
         block_state bstate;
 
-	bstate = (*(configuration_table[s->level].func))(s, flush);
+	bstate = DEFLATE_HOOK(strm, flush, &bstate) ? bstate :
+		 (*(configuration_table[s->level].func))(s, flush);
 
         if (bstate == finish_started || bstate == finish_done) {
             s->status = FINISH_STATE;
@@ -503,7 +506,8 @@ static int read_buf(
 
     strm->avail_in  -= len;
 
-    if (!((deflate_state *)(strm->state))->noheader) {
+    if (!DEFLATE_NEED_CHECKSUM(strm)) {}
+    else if (!((deflate_state *)(strm->state))->noheader) {
         strm->adler = zlib_adler32(strm->adler, strm->next_in, len);
     }
     memcpy(buf, strm->next_in, len);
@@ -1135,3 +1139,8 @@ int zlib_deflate_workspacesize(int windowBits, int memLevel)
         + zlib_deflate_head_memsize(memLevel)
         + zlib_deflate_overlay_memsize(memLevel);
 }
+
+int zlib_deflate_dfltcc_enabled(void)
+{
+	return DEFLATE_DFLTCC_ENABLED();
+}
diff --git a/lib/zlib_deflate/deflate_syms.c b/lib/zlib_deflate/deflate_syms.c
index 72fe4b73be53..24b740b99678 100644
--- a/lib/zlib_deflate/deflate_syms.c
+++ b/lib/zlib_deflate/deflate_syms.c
@@ -12,6 +12,7 @@
 #include <linux/zlib.h>
 
 EXPORT_SYMBOL(zlib_deflate_workspacesize);
+EXPORT_SYMBOL(zlib_deflate_dfltcc_enabled);
 EXPORT_SYMBOL(zlib_deflate);
 EXPORT_SYMBOL(zlib_deflateInit2);
 EXPORT_SYMBOL(zlib_deflateEnd);
diff --git a/lib/zlib_deflate/deftree.c b/lib/zlib_deflate/deftree.c
index 9b1756b12743..a4a34da512fe 100644
--- a/lib/zlib_deflate/deftree.c
+++ b/lib/zlib_deflate/deftree.c
@@ -76,11 +76,6 @@ static const uch bl_order[BL_CODES]
  * probability, to avoid transmitting the lengths for unused bit length codes.
  */
 
-#define Buf_size (8 * 2*sizeof(char))
-/* Number of bits used within bi_buf. (bi_buf might be implemented on
- * more than 16 bits on some systems.)
- */
-
 /* ===========================================================================
  * Local data. These are initialized only once.
  */
@@ -147,7 +142,6 @@ static void send_all_trees (deflate_state *s, int lcodes, int dcodes,
 static void compress_block (deflate_state *s, ct_data *ltree,
                            ct_data *dtree);
 static void set_data_type  (deflate_state *s);
-static void bi_windup      (deflate_state *s);
 static void bi_flush       (deflate_state *s);
 static void copy_block     (deflate_state *s, char *buf, unsigned len,
                            int header);
@@ -170,54 +164,6 @@ static void copy_block     (deflate_state *s, char *buf, unsigned len,
  */
 
 /* ===========================================================================
- * Send a value on a given number of bits.
- * IN assertion: length <= 16 and value fits in length bits.
- */
-#ifdef DEBUG_ZLIB
-static void send_bits      (deflate_state *s, int value, int length);
-
-static void send_bits(
-	deflate_state *s,
-	int value,  /* value to send */
-	int length  /* number of bits */
-)
-{
-    Tracevv((stderr," l %2d v %4x ", length, value));
-    Assert(length > 0 && length <= 15, "invalid length");
-    s->bits_sent += (ulg)length;
-
-    /* If not enough room in bi_buf, use (valid) bits from bi_buf and
-     * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid))
-     * unused bits in value.
-     */
-    if (s->bi_valid > (int)Buf_size - length) {
-        s->bi_buf |= (value << s->bi_valid);
-        put_short(s, s->bi_buf);
-        s->bi_buf = (ush)value >> (Buf_size - s->bi_valid);
-        s->bi_valid += length - Buf_size;
-    } else {
-        s->bi_buf |= value << s->bi_valid;
-        s->bi_valid += length;
-    }
-}
-#else /* !DEBUG_ZLIB */
-
-#define send_bits(s, value, length) \
-{ int len = length;\
-  if (s->bi_valid > (int)Buf_size - len) {\
-    int val = value;\
-    s->bi_buf |= (val << s->bi_valid);\
-    put_short(s, s->bi_buf);\
-    s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\
-    s->bi_valid += len - Buf_size;\
-  } else {\
-    s->bi_buf |= (value) << s->bi_valid;\
-    s->bi_valid += len;\
-  }\
-}
-#endif /* DEBUG_ZLIB */
-
-/* ===========================================================================
  * Initialize the various 'constant' tables. In a multi-threaded environment,
  * this function may be called by two threads concurrently, but this is
  * harmless since both invocations do exactly the same thing.
diff --git a/lib/zlib_deflate/defutil.h b/lib/zlib_deflate/defutil.h
index a8c370897c9f..385333b22ec6 100644
--- a/lib/zlib_deflate/defutil.h
+++ b/lib/zlib_deflate/defutil.h
@@ -1,5 +1,7 @@
+#ifndef DEFUTIL_H
+#define DEFUTIL_H
 
-
+#include <linux/zutil.h>
 
 #define Assert(err, str) 
 #define Trace(dummy) 
@@ -238,17 +240,13 @@ typedef struct deflate_state {
 
 } deflate_state;
 
-typedef struct deflate_workspace {
-    /* State memory for the deflator */
-    deflate_state deflate_memory;
-    Byte *window_memory;
-    Pos *prev_memory;
-    Pos *head_memory;
-    char *overlay_memory;
-} deflate_workspace;
-
+#ifdef CONFIG_ZLIB_DFLTCC
+#define zlib_deflate_window_memsize(windowBits) \
+	(2 * (1 << (windowBits)) * sizeof(Byte) + PAGE_SIZE)
+#else
 #define zlib_deflate_window_memsize(windowBits) \
 	(2 * (1 << (windowBits)) * sizeof(Byte))
+#endif
 #define zlib_deflate_prev_memsize(windowBits) \
 	((1 << (windowBits)) * sizeof(Pos))
 #define zlib_deflate_head_memsize(memLevel) \
@@ -293,6 +291,24 @@ void zlib_tr_stored_type_only (deflate_state *);
 }
 
 /* ===========================================================================
+ * Reverse the first len bits of a code, using straightforward code (a faster
+ * method would use a table)
+ * IN assertion: 1 <= len <= 15
+ */
+static inline unsigned  bi_reverse(
+    unsigned code, /* the value to invert */
+    int len        /* its bit length */
+)
+{
+    register unsigned res = 0;
+    do {
+        res |= code & 1;
+        code >>= 1, res <<= 1;
+    } while (--len > 0);
+    return res >> 1;
+}
+
+/* ===========================================================================
  * Flush the bit buffer, keeping at most 7 bits in it.
  */
 static inline void bi_flush(deflate_state *s)
@@ -325,3 +341,101 @@ static inline void bi_windup(deflate_state *s)
 #endif
 }
 
+typedef enum {
+    need_more,      /* block not completed, need more input or more output */
+    block_done,     /* block flush performed */
+    finish_started, /* finish started, need only more output at next deflate */
+    finish_done     /* finish done, accept no more input or output */
+} block_state;
+
+#define Buf_size (8 * 2*sizeof(char))
+/* Number of bits used within bi_buf. (bi_buf might be implemented on
+ * more than 16 bits on some systems.)
+ */
+
+/* ===========================================================================
+ * Send a value on a given number of bits.
+ * IN assertion: length <= 16 and value fits in length bits.
+ */
+#ifdef DEBUG_ZLIB
+static void send_bits      (deflate_state *s, int value, int length);
+
+static void send_bits(
+    deflate_state *s,
+    int value,  /* value to send */
+    int length  /* number of bits */
+)
+{
+    Tracevv((stderr," l %2d v %4x ", length, value));
+    Assert(length > 0 && length <= 15, "invalid length");
+    s->bits_sent += (ulg)length;
+
+    /* If not enough room in bi_buf, use (valid) bits from bi_buf and
+     * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid))
+     * unused bits in value.
+     */
+    if (s->bi_valid > (int)Buf_size - length) {
+        s->bi_buf |= (value << s->bi_valid);
+        put_short(s, s->bi_buf);
+        s->bi_buf = (ush)value >> (Buf_size - s->bi_valid);
+        s->bi_valid += length - Buf_size;
+    } else {
+        s->bi_buf |= value << s->bi_valid;
+        s->bi_valid += length;
+    }
+}
+#else /* !DEBUG_ZLIB */
+
+#define send_bits(s, value, length) \
+{ int len = length;\
+  if (s->bi_valid > (int)Buf_size - len) {\
+    int val = value;\
+    s->bi_buf |= (val << s->bi_valid);\
+    put_short(s, s->bi_buf);\
+    s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\
+    s->bi_valid += len - Buf_size;\
+  } else {\
+    s->bi_buf |= (value) << s->bi_valid;\
+    s->bi_valid += len;\
+  }\
+}
+#endif /* DEBUG_ZLIB */
+
+static inline void zlib_tr_send_bits(
+    deflate_state *s,
+    int value,
+    int length
+)
+{
+    send_bits(s, value, length);
+}
+
+/* =========================================================================
+ * Flush as much pending output as possible. All deflate() output goes
+ * through this function so some applications may wish to modify it
+ * to avoid allocating a large strm->next_out buffer and copying into it.
+ * (See also read_buf()).
+ */
+static inline void flush_pending(
+	z_streamp strm
+)
+{
+    deflate_state *s = (deflate_state *) strm->state;
+    unsigned len = s->pending;
+
+    if (len > strm->avail_out) len = strm->avail_out;
+    if (len == 0) return;
+
+    if (strm->next_out != NULL) {
+	memcpy(strm->next_out, s->pending_out, len);
+	strm->next_out += len;
+    }
+    s->pending_out += len;
+    strm->total_out += len;
+    strm->avail_out  -= len;
+    s->pending -= len;
+    if (s->pending == 0) {
+        s->pending_out = s->pending_buf;
+    }
+}
+#endif /* DEFUTIL_H */
diff --git a/lib/zlib_dfltcc/Makefile b/lib/zlib_dfltcc/Makefile
new file mode 100644
index 000000000000..8e4d5afbbb10
--- /dev/null
+++ b/lib/zlib_dfltcc/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This is a modified version of zlib, which does all memory
+# allocation ahead of time.
+#
+# This is the code for s390 zlib hardware support.
+#
+
+obj-$(CONFIG_ZLIB_DFLTCC) += zlib_dfltcc.o
+
+zlib_dfltcc-objs := dfltcc.o dfltcc_deflate.o dfltcc_inflate.o dfltcc_syms.o
diff --git a/lib/zlib_dfltcc/dfltcc.c b/lib/zlib_dfltcc/dfltcc.c
new file mode 100644
index 000000000000..c30de430b30c
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: Zlib
+/* dfltcc.c - SystemZ DEFLATE CONVERSION CALL support. */
+
+#include <linux/zutil.h>
+#include "dfltcc_util.h"
+#include "dfltcc.h"
+
+char *oesc_msg(
+    char *buf,
+    int oesc
+)
+{
+    if (oesc == 0x00)
+        return NULL; /* Successful completion */
+    else {
+#ifdef STATIC
+        return NULL; /* Ignore for pre-boot decompressor */
+#else
+        sprintf(buf, "Operation-Ending-Supplemental Code is 0x%.2X", oesc);
+        return buf;
+#endif
+    }
+}
+
+void dfltcc_reset(
+    z_streamp strm,
+    uInt size
+)
+{
+    struct dfltcc_state *dfltcc_state =
+        (struct dfltcc_state *)((char *)strm->state + size);
+    struct dfltcc_qaf_param *param =
+        (struct dfltcc_qaf_param *)&dfltcc_state->param;
+
+    /* Initialize available functions */
+    if (is_dfltcc_enabled()) {
+        dfltcc(DFLTCC_QAF, param, NULL, NULL, NULL, NULL, NULL);
+        memmove(&dfltcc_state->af, param, sizeof(dfltcc_state->af));
+    } else
+        memset(&dfltcc_state->af, 0, sizeof(dfltcc_state->af));
+
+    /* Initialize parameter block */
+    memset(&dfltcc_state->param, 0, sizeof(dfltcc_state->param));
+    dfltcc_state->param.nt = 1;
+
+    /* Initialize tuning parameters */
+    if (zlib_dfltcc_support == ZLIB_DFLTCC_FULL_DEBUG)
+        dfltcc_state->level_mask = DFLTCC_LEVEL_MASK_DEBUG;
+    else
+        dfltcc_state->level_mask = DFLTCC_LEVEL_MASK;
+    dfltcc_state->block_size = DFLTCC_BLOCK_SIZE;
+    dfltcc_state->block_threshold = DFLTCC_FIRST_FHT_BLOCK_SIZE;
+    dfltcc_state->dht_threshold = DFLTCC_DHT_MIN_SAMPLE_SIZE;
+    dfltcc_state->param.ribm = DFLTCC_RIBM;
+}
diff --git a/lib/zlib_dfltcc/dfltcc.h b/lib/zlib_dfltcc/dfltcc.h
new file mode 100644
index 000000000000..2a2fac1d050a
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc.h
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: Zlib
+#ifndef DFLTCC_H
+#define DFLTCC_H
+
+#include "../zlib_deflate/defutil.h"
+#include <asm/facility.h>
+#include <asm/setup.h>
+
+/*
+ * Tuning parameters.
+ */
+#define DFLTCC_LEVEL_MASK 0x2 /* DFLTCC compression for level 1 only */
+#define DFLTCC_LEVEL_MASK_DEBUG 0x3fe /* DFLTCC compression for all levels */
+#define DFLTCC_BLOCK_SIZE 1048576
+#define DFLTCC_FIRST_FHT_BLOCK_SIZE 4096
+#define DFLTCC_DHT_MIN_SAMPLE_SIZE 4096
+#define DFLTCC_RIBM 0
+
+#define DFLTCC_FACILITY 151
+
+/*
+ * Parameter Block for Query Available Functions.
+ */
+struct dfltcc_qaf_param {
+    char fns[16];
+    char reserved1[8];
+    char fmts[2];
+    char reserved2[6];
+};
+
+static_assert(sizeof(struct dfltcc_qaf_param) == 32);
+
+#define DFLTCC_FMT0 0
+
+/*
+ * Parameter Block for Generate Dynamic-Huffman Table, Compress and Expand.
+ */
+struct dfltcc_param_v0 {
+    uint16_t pbvn;                     /* Parameter-Block-Version Number */
+    uint8_t mvn;                       /* Model-Version Number */
+    uint8_t ribm;                      /* Reserved for IBM use */
+    unsigned reserved32 : 31;
+    unsigned cf : 1;                   /* Continuation Flag */
+    uint8_t reserved64[8];
+    unsigned nt : 1;                   /* New Task */
+    unsigned reserved129 : 1;
+    unsigned cvt : 1;                  /* Check Value Type */
+    unsigned reserved131 : 1;
+    unsigned htt : 1;                  /* Huffman-Table Type */
+    unsigned bcf : 1;                  /* Block-Continuation Flag */
+    unsigned bcc : 1;                  /* Block Closing Control */
+    unsigned bhf : 1;                  /* Block Header Final */
+    unsigned reserved136 : 1;
+    unsigned reserved137 : 1;
+    unsigned dhtgc : 1;                /* DHT Generation Control */
+    unsigned reserved139 : 5;
+    unsigned reserved144 : 5;
+    unsigned sbb : 3;                  /* Sub-Byte Boundary */
+    uint8_t oesc;                      /* Operation-Ending-Supplemental Code */
+    unsigned reserved160 : 12;
+    unsigned ifs : 4;                  /* Incomplete-Function Status */
+    uint16_t ifl;                      /* Incomplete-Function Length */
+    uint8_t reserved192[8];
+    uint8_t reserved256[8];
+    uint8_t reserved320[4];
+    uint16_t hl;                       /* History Length */
+    unsigned reserved368 : 1;
+    uint16_t ho : 15;                  /* History Offset */
+    uint32_t cv;                       /* Check Value */
+    unsigned eobs : 15;                /* End-of-block Symbol */
+    unsigned reserved431: 1;
+    uint8_t eobl : 4;                  /* End-of-block Length */
+    unsigned reserved436 : 12;
+    unsigned reserved448 : 4;
+    uint16_t cdhtl : 12;               /* Compressed-Dynamic-Huffman Table
+                                          Length */
+    uint8_t reserved464[6];
+    uint8_t cdht[288];
+    uint8_t reserved[32];
+    uint8_t csb[1152];
+};
+
+static_assert(sizeof(struct dfltcc_param_v0) == 1536);
+
+#define CVT_CRC32 0
+#define CVT_ADLER32 1
+#define HTT_FIXED 0
+#define HTT_DYNAMIC 1
+
+/*
+ *  Extension of inflate_state and deflate_state for DFLTCC.
+ */
+struct dfltcc_state {
+    struct dfltcc_param_v0 param;      /* Parameter block */
+    struct dfltcc_qaf_param af;        /* Available functions */
+    uLong level_mask;                  /* Levels on which to use DFLTCC */
+    uLong block_size;                  /* New block each X bytes */
+    uLong block_threshold;             /* New block after total_in > X */
+    uLong dht_threshold;               /* New block only if avail_in >= X */
+    char msg[64];                      /* Buffer for strm->msg */
+};
+
+/* Resides right after inflate_state or deflate_state */
+#define GET_DFLTCC_STATE(state) ((struct dfltcc_state *)((state) + 1))
+
+/* External functions */
+int dfltcc_can_deflate(z_streamp strm);
+int dfltcc_deflate(z_streamp strm,
+                   int flush,
+                   block_state *result);
+void dfltcc_reset(z_streamp strm, uInt size);
+int dfltcc_can_inflate(z_streamp strm);
+typedef enum {
+    DFLTCC_INFLATE_CONTINUE,
+    DFLTCC_INFLATE_BREAK,
+    DFLTCC_INFLATE_SOFTWARE,
+} dfltcc_inflate_action;
+dfltcc_inflate_action dfltcc_inflate(z_streamp strm,
+                                     int flush, int *ret);
+static inline int is_dfltcc_enabled(void)
+{
+return (zlib_dfltcc_support != ZLIB_DFLTCC_DISABLED &&
+        test_facility(DFLTCC_FACILITY));
+}
+
+#define DEFLATE_RESET_HOOK(strm) \
+    dfltcc_reset((strm), sizeof(deflate_state))
+
+#define DEFLATE_HOOK dfltcc_deflate
+
+#define DEFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_deflate((strm)))
+
+#define DEFLATE_DFLTCC_ENABLED() is_dfltcc_enabled()
+
+#define INFLATE_RESET_HOOK(strm) \
+    dfltcc_reset((strm), sizeof(struct inflate_state))
+
+#define INFLATE_TYPEDO_HOOK(strm, flush) \
+    if (dfltcc_can_inflate((strm))) { \
+        dfltcc_inflate_action action; \
+\
+        RESTORE(); \
+        action = dfltcc_inflate((strm), (flush), &ret); \
+        LOAD(); \
+        if (action == DFLTCC_INFLATE_CONTINUE) \
+            break; \
+        else if (action == DFLTCC_INFLATE_BREAK) \
+            goto inf_leave; \
+    }
+
+#define INFLATE_NEED_CHECKSUM(strm) (!dfltcc_can_inflate((strm)))
+
+#define INFLATE_NEED_UPDATEWINDOW(strm) (!dfltcc_can_inflate((strm)))
+
+#endif /* DFLTCC_H */
diff --git a/lib/zlib_dfltcc/dfltcc_deflate.c b/lib/zlib_dfltcc/dfltcc_deflate.c
new file mode 100644
index 000000000000..00c185101c6d
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_deflate.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: Zlib
+
+#include "../zlib_deflate/defutil.h"
+#include "dfltcc_util.h"
+#include "dfltcc.h"
+#include <asm/setup.h>
+#include <linux/zutil.h>
+
+/*
+ * Compress.
+ */
+int dfltcc_can_deflate(
+    z_streamp strm
+)
+{
+    deflate_state *state = (deflate_state *)strm->state;
+    struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+
+    /* Check for kernel dfltcc command line parameter */
+    if (zlib_dfltcc_support == ZLIB_DFLTCC_DISABLED ||
+            zlib_dfltcc_support == ZLIB_DFLTCC_INFLATE_ONLY)
+        return 0;
+
+    /* Unsupported compression settings */
+    if (!dfltcc_are_params_ok(state->level, state->w_bits, state->strategy,
+                              dfltcc_state->level_mask))
+        return 0;
+
+    /* Unsupported hardware */
+    if (!is_bit_set(dfltcc_state->af.fns, DFLTCC_GDHT) ||
+            !is_bit_set(dfltcc_state->af.fns, DFLTCC_CMPR) ||
+            !is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0))
+        return 0;
+
+    return 1;
+}
+
+static void dfltcc_gdht(
+    z_streamp strm
+)
+{
+    deflate_state *state = (deflate_state *)strm->state;
+    struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+    size_t avail_in = avail_in = strm->avail_in;
+
+    dfltcc(DFLTCC_GDHT,
+           param, NULL, NULL,
+           &strm->next_in, &avail_in, NULL);
+}
+
+static dfltcc_cc dfltcc_cmpr(
+    z_streamp strm
+)
+{
+    deflate_state *state = (deflate_state *)strm->state;
+    struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+    size_t avail_in = strm->avail_in;
+    size_t avail_out = strm->avail_out;
+    dfltcc_cc cc;
+
+    cc = dfltcc(DFLTCC_CMPR | HBT_CIRCULAR,
+                param, &strm->next_out, &avail_out,
+                &strm->next_in, &avail_in, state->window);
+    strm->total_in += (strm->avail_in - avail_in);
+    strm->total_out += (strm->avail_out - avail_out);
+    strm->avail_in = avail_in;
+    strm->avail_out = avail_out;
+    return cc;
+}
+
+static void send_eobs(
+    z_streamp strm,
+    const struct dfltcc_param_v0 *param
+)
+{
+    deflate_state *state = (deflate_state *)strm->state;
+
+    zlib_tr_send_bits(
+          state,
+          bi_reverse(param->eobs >> (15 - param->eobl), param->eobl),
+          param->eobl);
+    flush_pending(strm);
+    if (state->pending != 0) {
+        /* The remaining data is located in pending_out[0:pending]. If someone
+         * calls put_byte() - this might happen in deflate() - the byte will be
+         * placed into pending_buf[pending], which is incorrect. Move the
+         * remaining data to the beginning of pending_buf so that put_byte() is
+         * usable again.
+         */
+        memmove(state->pending_buf, state->pending_out, state->pending);
+        state->pending_out = state->pending_buf;
+    }
+#ifdef ZLIB_DEBUG
+    state->compressed_len += param->eobl;
+#endif
+}
+
+int dfltcc_deflate(
+    z_streamp strm,
+    int flush,
+    block_state *result
+)
+{
+    deflate_state *state = (deflate_state *)strm->state;
+    struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+    struct dfltcc_param_v0 *param = &dfltcc_state->param;
+    uInt masked_avail_in;
+    dfltcc_cc cc;
+    int need_empty_block;
+    int soft_bcc;
+    int no_flush;
+
+    if (!dfltcc_can_deflate(strm))
+        return 0;
+
+again:
+    masked_avail_in = 0;
+    soft_bcc = 0;
+    no_flush = flush == Z_NO_FLUSH;
+
+    /* Trailing empty block. Switch to software, except when Continuation Flag
+     * is set, which means that DFLTCC has buffered some output in the
+     * parameter block and needs to be called again in order to flush it.
+     */
+    if (flush == Z_FINISH && strm->avail_in == 0 && !param->cf) {
+        if (param->bcf) {
+            /* A block is still open, and the hardware does not support closing
+             * blocks without adding data. Thus, close it manually.
+             */
+            send_eobs(strm, param);
+            param->bcf = 0;
+        }
+        return 0;
+    }
+
+    if (strm->avail_in == 0 && !param->cf) {
+        *result = need_more;
+        return 1;
+    }
+
+    /* There is an open non-BFINAL block, we are not going to close it just
+     * yet, we have compressed more than DFLTCC_BLOCK_SIZE bytes and we see
+     * more than DFLTCC_DHT_MIN_SAMPLE_SIZE bytes. Open a new block with a new
+     * DHT in order to adapt to a possibly changed input data distribution.
+     */
+    if (param->bcf && no_flush &&
+            strm->total_in > dfltcc_state->block_threshold &&
+            strm->avail_in >= dfltcc_state->dht_threshold) {
+        if (param->cf) {
+            /* We need to flush the DFLTCC buffer before writing the
+             * End-of-block Symbol. Mask the input data and proceed as usual.
+             */
+            masked_avail_in += strm->avail_in;
+            strm->avail_in = 0;
+            no_flush = 0;
+        } else {
+            /* DFLTCC buffer is empty, so we can manually write the
+             * End-of-block Symbol right away.
+             */
+            send_eobs(strm, param);
+            param->bcf = 0;
+            dfltcc_state->block_threshold =
+                strm->total_in + dfltcc_state->block_size;
+            if (strm->avail_out == 0) {
+                *result = need_more;
+                return 1;
+            }
+        }
+    }
+
+    /* The caller gave us too much data. Pass only one block worth of
+     * uncompressed data to DFLTCC and mask the rest, so that on the next
+     * iteration we start a new block.
+     */
+    if (no_flush && strm->avail_in > dfltcc_state->block_size) {
+        masked_avail_in += (strm->avail_in - dfltcc_state->block_size);
+        strm->avail_in = dfltcc_state->block_size;
+    }
+
+    /* When we have an open non-BFINAL deflate block and caller indicates that
+     * the stream is ending, we need to close an open deflate block and open a
+     * BFINAL one.
+     */
+    need_empty_block = flush == Z_FINISH && param->bcf && !param->bhf;
+
+    /* Translate stream to parameter block */
+    param->cvt = CVT_ADLER32;
+    if (!no_flush)
+        /* We need to close a block. Always do this in software - when there is
+         * no input data, the hardware will not nohor BCC. */
+        soft_bcc = 1;
+    if (flush == Z_FINISH && !param->bcf)
+        /* We are about to open a BFINAL block, set Block Header Final bit
+         * until the stream ends.
+         */
+        param->bhf = 1;
+    /* DFLTCC-CMPR will write to next_out, so make sure that buffers with
+     * higher precedence are empty.
+     */
+    Assert(state->pending == 0, "There must be no pending bytes");
+    Assert(state->bi_valid < 8, "There must be less than 8 pending bits");
+    param->sbb = (unsigned int)state->bi_valid;
+    if (param->sbb > 0)
+        *strm->next_out = (Byte)state->bi_buf;
+    if (param->hl)
+        param->nt = 0; /* Honor history */
+    param->cv = strm->adler;
+
+    /* When opening a block, choose a Huffman-Table Type */
+    if (!param->bcf) {
+        if (strm->total_in == 0 && dfltcc_state->block_threshold > 0) {
+            param->htt = HTT_FIXED;
+        }
+        else {
+            param->htt = HTT_DYNAMIC;
+            dfltcc_gdht(strm);
+        }
+    }
+
+    /* Deflate */
+    do {
+        cc = dfltcc_cmpr(strm);
+        if (strm->avail_in < 4096 && masked_avail_in > 0)
+            /* We are about to call DFLTCC with a small input buffer, which is
+             * inefficient. Since there is masked data, there will be at least
+             * one more DFLTCC call, so skip the current one and make the next
+             * one handle more data.
+             */
+            break;
+    } while (cc == DFLTCC_CC_AGAIN);
+
+    /* Translate parameter block to stream */
+    strm->msg = oesc_msg(dfltcc_state->msg, param->oesc);
+    state->bi_valid = param->sbb;
+    if (state->bi_valid == 0)
+        state->bi_buf = 0; /* Avoid accessing next_out */
+    else
+        state->bi_buf = *strm->next_out & ((1 << state->bi_valid) - 1);
+    strm->adler = param->cv;
+
+    /* Unmask the input data */
+    strm->avail_in += masked_avail_in;
+    masked_avail_in = 0;
+
+    /* If we encounter an error, it means there is a bug in DFLTCC call */
+    Assert(cc != DFLTCC_CC_OP2_CORRUPT || param->oesc == 0, "BUG");
+
+    /* Update Block-Continuation Flag. It will be used to check whether to call
+     * GDHT the next time.
+     */
+    if (cc == DFLTCC_CC_OK) {
+        if (soft_bcc) {
+            send_eobs(strm, param);
+            param->bcf = 0;
+            dfltcc_state->block_threshold =
+                strm->total_in + dfltcc_state->block_size;
+        } else
+            param->bcf = 1;
+        if (flush == Z_FINISH) {
+            if (need_empty_block)
+                /* Make the current deflate() call also close the stream */
+                return 0;
+            else {
+                bi_windup(state);
+                *result = finish_done;
+            }
+        } else {
+            if (flush == Z_FULL_FLUSH)
+                param->hl = 0; /* Clear history */
+            *result = flush == Z_NO_FLUSH ? need_more : block_done;
+        }
+    } else {
+        param->bcf = 1;
+        *result = need_more;
+    }
+    if (strm->avail_in != 0 && strm->avail_out != 0)
+        goto again; /* deflate() must use all input or all output */
+    return 1;
+}
diff --git a/lib/zlib_dfltcc/dfltcc_inflate.c b/lib/zlib_dfltcc/dfltcc_inflate.c
new file mode 100644
index 000000000000..aa9ef23474df
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_inflate.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: Zlib
+
+#include "../zlib_inflate/inflate.h"
+#include "dfltcc_util.h"
+#include "dfltcc.h"
+#include <asm/setup.h>
+#include <linux/zutil.h>
+
+/*
+ * Expand.
+ */
+int dfltcc_can_inflate(
+    z_streamp strm
+)
+{
+    struct inflate_state *state = (struct inflate_state *)strm->state;
+    struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+
+    /* Check for kernel dfltcc command line parameter */
+    if (zlib_dfltcc_support == ZLIB_DFLTCC_DISABLED ||
+            zlib_dfltcc_support == ZLIB_DFLTCC_DEFLATE_ONLY)
+        return 0;
+
+    /* Unsupported compression settings */
+    if (state->wbits != HB_BITS)
+        return 0;
+
+    /* Unsupported hardware */
+    return is_bit_set(dfltcc_state->af.fns, DFLTCC_XPND) &&
+               is_bit_set(dfltcc_state->af.fmts, DFLTCC_FMT0);
+}
+
+static int dfltcc_was_inflate_used(
+    z_streamp strm
+)
+{
+    struct inflate_state *state = (struct inflate_state *)strm->state;
+    struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+
+    return !param->nt;
+}
+
+static int dfltcc_inflate_disable(
+    z_streamp strm
+)
+{
+    struct inflate_state *state = (struct inflate_state *)strm->state;
+    struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+
+    if (!dfltcc_can_inflate(strm))
+        return 0;
+    if (dfltcc_was_inflate_used(strm))
+        /* DFLTCC has already decompressed some data. Since there is not
+         * enough information to resume decompression in software, the call
+         * must fail.
+         */
+        return 1;
+    /* DFLTCC was not used yet - decompress in software */
+    memset(&dfltcc_state->af, 0, sizeof(dfltcc_state->af));
+    return 0;
+}
+
+static dfltcc_cc dfltcc_xpnd(
+    z_streamp strm
+)
+{
+    struct inflate_state *state = (struct inflate_state *)strm->state;
+    struct dfltcc_param_v0 *param = &GET_DFLTCC_STATE(state)->param;
+    size_t avail_in = strm->avail_in;
+    size_t avail_out = strm->avail_out;
+    dfltcc_cc cc;
+
+    cc = dfltcc(DFLTCC_XPND | HBT_CIRCULAR,
+                param, &strm->next_out, &avail_out,
+                &strm->next_in, &avail_in, state->window);
+    strm->avail_in = avail_in;
+    strm->avail_out = avail_out;
+    return cc;
+}
+
+dfltcc_inflate_action dfltcc_inflate(
+    z_streamp strm,
+    int flush,
+    int *ret
+)
+{
+    struct inflate_state *state = (struct inflate_state *)strm->state;
+    struct dfltcc_state *dfltcc_state = GET_DFLTCC_STATE(state);
+    struct dfltcc_param_v0 *param = &dfltcc_state->param;
+    dfltcc_cc cc;
+
+    if (flush == Z_BLOCK) {
+        /* DFLTCC does not support stopping on block boundaries */
+        if (dfltcc_inflate_disable(strm)) {
+            *ret = Z_STREAM_ERROR;
+            return DFLTCC_INFLATE_BREAK;
+        } else
+            return DFLTCC_INFLATE_SOFTWARE;
+    }
+
+    if (state->last) {
+        if (state->bits != 0) {
+            strm->next_in++;
+            strm->avail_in--;
+            state->bits = 0;
+        }
+        state->mode = CHECK;
+        return DFLTCC_INFLATE_CONTINUE;
+    }
+
+    if (strm->avail_in == 0 && !param->cf)
+        return DFLTCC_INFLATE_BREAK;
+
+    if (!state->window || state->wsize == 0) {
+        state->mode = MEM;
+        return DFLTCC_INFLATE_CONTINUE;
+    }
+
+    /* Translate stream to parameter block */
+    param->cvt = CVT_ADLER32;
+    param->sbb = state->bits;
+    param->hl = state->whave; /* Software and hardware history formats match */
+    param->ho = (state->write - state->whave) & ((1 << HB_BITS) - 1);
+    if (param->hl)
+        param->nt = 0; /* Honor history for the first block */
+    param->cv = state->flags ? REVERSE(state->check) : state->check;
+
+    /* Inflate */
+    do {
+        cc = dfltcc_xpnd(strm);
+    } while (cc == DFLTCC_CC_AGAIN);
+
+    /* Translate parameter block to stream */
+    strm->msg = oesc_msg(dfltcc_state->msg, param->oesc);
+    state->last = cc == DFLTCC_CC_OK;
+    state->bits = param->sbb;
+    state->whave = param->hl;
+    state->write = (param->ho + param->hl) & ((1 << HB_BITS) - 1);
+    state->check = state->flags ? REVERSE(param->cv) : param->cv;
+    if (cc == DFLTCC_CC_OP2_CORRUPT && param->oesc != 0) {
+        /* Report an error if stream is corrupted */
+        state->mode = BAD;
+        return DFLTCC_INFLATE_CONTINUE;
+    }
+    state->mode = TYPEDO;
+    /* Break if operands are exhausted, otherwise continue looping */
+    return (cc == DFLTCC_CC_OP1_TOO_SHORT || cc == DFLTCC_CC_OP2_TOO_SHORT) ?
+        DFLTCC_INFLATE_BREAK : DFLTCC_INFLATE_CONTINUE;
+}
diff --git a/lib/zlib_dfltcc/dfltcc_syms.c b/lib/zlib_dfltcc/dfltcc_syms.c
new file mode 100644
index 000000000000..6f23481804c1
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_syms.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/lib/zlib_dfltcc/dfltcc_syms.c
+ *
+ * Exported symbols for the s390 zlib dfltcc support.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/zlib.h>
+#include "dfltcc.h"
+
+EXPORT_SYMBOL(dfltcc_can_deflate);
+EXPORT_SYMBOL(dfltcc_deflate);
+EXPORT_SYMBOL(dfltcc_reset);
+MODULE_LICENSE("GPL");
diff --git a/lib/zlib_dfltcc/dfltcc_util.h b/lib/zlib_dfltcc/dfltcc_util.h
new file mode 100644
index 000000000000..4a46b5009f0d
--- /dev/null
+++ b/lib/zlib_dfltcc/dfltcc_util.h
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: Zlib
+#ifndef DFLTCC_UTIL_H
+#define DFLTCC_UTIL_H
+
+#include <linux/zutil.h>
+
+/*
+ * C wrapper for the DEFLATE CONVERSION CALL instruction.
+ */
+typedef enum {
+    DFLTCC_CC_OK = 0,
+    DFLTCC_CC_OP1_TOO_SHORT = 1,
+    DFLTCC_CC_OP2_TOO_SHORT = 2,
+    DFLTCC_CC_OP2_CORRUPT = 2,
+    DFLTCC_CC_AGAIN = 3,
+} dfltcc_cc;
+
+#define DFLTCC_QAF 0
+#define DFLTCC_GDHT 1
+#define DFLTCC_CMPR 2
+#define DFLTCC_XPND 4
+#define HBT_CIRCULAR (1 << 7)
+#define HB_BITS 15
+#define HB_SIZE (1 << HB_BITS)
+
+static inline dfltcc_cc dfltcc(
+    int fn,
+    void *param,
+    Byte **op1,
+    size_t *len1,
+    const Byte **op2,
+    size_t *len2,
+    void *hist
+)
+{
+    Byte *t2 = op1 ? *op1 : NULL;
+    size_t t3 = len1 ? *len1 : 0;
+    const Byte *t4 = op2 ? *op2 : NULL;
+    size_t t5 = len2 ? *len2 : 0;
+    register int r0 __asm__("r0") = fn;
+    register void *r1 __asm__("r1") = param;
+    register Byte *r2 __asm__("r2") = t2;
+    register size_t r3 __asm__("r3") = t3;
+    register const Byte *r4 __asm__("r4") = t4;
+    register size_t r5 __asm__("r5") = t5;
+    int cc;
+
+    __asm__ volatile(
+                     ".insn rrf,0xb9390000,%[r2],%[r4],%[hist],0\n"
+                     "ipm %[cc]\n"
+                     : [r2] "+r" (r2)
+                     , [r3] "+r" (r3)
+                     , [r4] "+r" (r4)
+                     , [r5] "+r" (r5)
+                     , [cc] "=r" (cc)
+                     : [r0] "r" (r0)
+                     , [r1] "r" (r1)
+                     , [hist] "r" (hist)
+                     : "cc", "memory");
+    t2 = r2; t3 = r3; t4 = r4; t5 = r5;
+
+    if (op1)
+        *op1 = t2;
+    if (len1)
+        *len1 = t3;
+    if (op2)
+        *op2 = t4;
+    if (len2)
+        *len2 = t5;
+    return (cc >> 28) & 3;
+}
+
+static inline int is_bit_set(
+    const char *bits,
+    int n
+)
+{
+    return bits[n / 8] & (1 << (7 - (n % 8)));
+}
+
+static inline void turn_bit_off(
+    char *bits,
+    int n
+)
+{
+    bits[n / 8] &= ~(1 << (7 - (n % 8)));
+}
+
+static inline int dfltcc_are_params_ok(
+    int level,
+    uInt window_bits,
+    int strategy,
+    uLong level_mask
+)
+{
+    return (level_mask & (1 << level)) != 0 &&
+        (window_bits == HB_BITS) &&
+        (strategy == Z_DEFAULT_STRATEGY);
+}
+
+char *oesc_msg(char *buf, int oesc);
+
+#endif /* DFLTCC_UTIL_H */
diff --git a/lib/zlib_inflate/inflate.c b/lib/zlib_inflate/inflate.c
index 48f14cd58c77..67cc9b08ae9d 100644
--- a/lib/zlib_inflate/inflate.c
+++ b/lib/zlib_inflate/inflate.c
@@ -15,6 +15,16 @@
 #include "inffast.h"
 #include "infutil.h"
 
+/* architecture-specific bits */
+#ifdef CONFIG_ZLIB_DFLTCC
+#  include "../zlib_dfltcc/dfltcc.h"
+#else
+#define INFLATE_RESET_HOOK(strm) do {} while (0)
+#define INFLATE_TYPEDO_HOOK(strm, flush) do {} while (0)
+#define INFLATE_NEED_UPDATEWINDOW(strm) 1
+#define INFLATE_NEED_CHECKSUM(strm) 1
+#endif
+
 int zlib_inflate_workspacesize(void)
 {
     return sizeof(struct inflate_workspace);
@@ -42,6 +52,7 @@ int zlib_inflateReset(z_streamp strm)
     state->write = 0;
     state->whave = 0;
 
+    INFLATE_RESET_HOOK(strm);
     return Z_OK;
 }
 
@@ -66,7 +77,15 @@ int zlib_inflateInit2(z_streamp strm, int windowBits)
         return Z_STREAM_ERROR;
     }
     state->wbits = (unsigned)windowBits;
+#ifdef CONFIG_ZLIB_DFLTCC
+    /*
+     * DFLTCC requires the window to be page aligned.
+     * Thus, we overallocate and take the aligned portion of the buffer.
+     */
+    state->window = PTR_ALIGN(&WS(strm)->working_window[0], PAGE_SIZE);
+#else
     state->window = &WS(strm)->working_window[0];
+#endif
 
     return zlib_inflateReset(strm);
 }
@@ -227,11 +246,6 @@ static int zlib_inflateSyncPacket(z_streamp strm)
         bits -= bits & 7; \
     } while (0)
 
-/* Reverse the bytes in a 32-bit value */
-#define REVERSE(q) \
-    ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \
-     (((q) & 0xff00) << 8) + (((q) & 0xff) << 24))
-
 /*
    inflate() uses a state machine to process as much input data and generate as
    much output data as possible before returning.  The state machine is
@@ -395,6 +409,7 @@ int zlib_inflate(z_streamp strm, int flush)
             if (flush == Z_BLOCK) goto inf_leave;
 	    /* fall through */
         case TYPEDO:
+            INFLATE_TYPEDO_HOOK(strm, flush);
             if (state->last) {
                 BYTEBITS();
                 state->mode = CHECK;
@@ -692,7 +707,7 @@ int zlib_inflate(z_streamp strm, int flush)
                 out -= left;
                 strm->total_out += out;
                 state->total += out;
-                if (out)
+                if (INFLATE_NEED_CHECKSUM(strm) && out)
                     strm->adler = state->check =
                         UPDATE(state->check, put - out, out);
                 out = left;
@@ -726,7 +741,8 @@ int zlib_inflate(z_streamp strm, int flush)
      */
   inf_leave:
     RESTORE();
-    if (state->wsize || (state->mode < CHECK && out != strm->avail_out))
+    if (INFLATE_NEED_UPDATEWINDOW(strm) &&
+            (state->wsize || (state->mode < CHECK && out != strm->avail_out)))
         zlib_updatewindow(strm, out);
 
     in -= strm->avail_in;
@@ -734,7 +750,7 @@ int zlib_inflate(z_streamp strm, int flush)
     strm->total_in += in;
     strm->total_out += out;
     state->total += out;
-    if (state->wrap && out)
+    if (INFLATE_NEED_CHECKSUM(strm) && state->wrap && out)
         strm->adler = state->check =
             UPDATE(state->check, strm->next_out - out, out);
 
diff --git a/lib/zlib_inflate/inflate.h b/lib/zlib_inflate/inflate.h
index 3d17b3d1b21f..f79337ddf98c 100644
--- a/lib/zlib_inflate/inflate.h
+++ b/lib/zlib_inflate/inflate.h
@@ -11,6 +11,8 @@
    subject to change. Applications should only use zlib.h.
  */
 
+#include "inftrees.h"
+
 /* Possible inflate modes between inflate() calls */
 typedef enum {
     HEAD,       /* i: waiting for magic header */
@@ -108,4 +110,10 @@ struct inflate_state {
     unsigned short work[288];   /* work area for code table building */
     code codes[ENOUGH];         /* space for code tables */
 };
+
+/* Reverse the bytes in a 32-bit value */
+#define REVERSE(q) \
+    ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \
+     (((q) & 0xff00) << 8) + (((q) & 0xff) << 24))
+
 #endif
diff --git a/lib/zlib_inflate/infutil.h b/lib/zlib_inflate/infutil.h
index eb1a9007bd86..784ab33b7842 100644
--- a/lib/zlib_inflate/infutil.h
+++ b/lib/zlib_inflate/infutil.h
@@ -12,14 +12,28 @@
 #define _INFUTIL_H
 
 #include <linux/zlib.h>
+#ifdef CONFIG_ZLIB_DFLTCC
+#include "../zlib_dfltcc/dfltcc.h"
+#include <asm/page.h>
+#endif
 
 /* memory allocation for inflation */
 
 struct inflate_workspace {
 	struct inflate_state inflate_state;
-	unsigned char working_window[1 << MAX_WBITS];
+#ifdef CONFIG_ZLIB_DFLTCC
+	struct dfltcc_state dfltcc_state;
+	unsigned char working_window[(1 << MAX_WBITS) + PAGE_SIZE];
+#else
+	unsigned char working_window[(1 << MAX_WBITS)];
+#endif
 };
 
-#define WS(z) ((struct inflate_workspace *)(z->workspace))
+#ifdef CONFIG_ZLIB_DFLTCC
+/* dfltcc_state must be doubleword aligned for DFLTCC call */
+static_assert(offsetof(struct inflate_workspace, dfltcc_state) % 8 == 0);
+#endif
+
+#define WS(strm) ((struct inflate_workspace *)(strm->workspace))
 
 #endif
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index 327b3ebf23bf..0271b22e063f 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -117,3 +117,24 @@ config DEBUG_RODATA_TEST
     depends on STRICT_KERNEL_RWX
     ---help---
       This option enables a testcase for the setting rodata read-only.
+
+config GENERIC_PTDUMP
+	bool
+
+config PTDUMP_CORE
+	bool
+
+config PTDUMP_DEBUGFS
+	bool "Export kernel pagetable layout to userspace via debugfs"
+	depends on DEBUG_KERNEL
+	depends on DEBUG_FS
+	depends on GENERIC_PTDUMP
+	select PTDUMP_CORE
+	help
+	  Say Y here if you want to show the kernel pagetable layout in a
+	  debugfs file. This information is only useful for kernel developers
+	  who are working in architecture specific areas of the kernel.
+	  It is probably not a good idea to enable this feature in a production
+	  kernel.
+
+	  If in doubt, say N.
diff --git a/mm/Makefile b/mm/Makefile
index 1937cc251883..272e66039e70 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -20,6 +20,7 @@ KCOV_INSTRUMENT_kmemleak.o := n
 KCOV_INSTRUMENT_memcontrol.o := n
 KCOV_INSTRUMENT_mmzone.o := n
 KCOV_INSTRUMENT_vmstat.o := n
+KCOV_INSTRUMENT_failslab.o := n
 
 CFLAGS_init-mm.o += $(call cc-disable-warning, override-init)
 CFLAGS_init-mm.o += $(call cc-disable-warning, initializer-overrides)
@@ -108,3 +109,4 @@ obj-$(CONFIG_ZONE_DEVICE) += memremap.o
 obj-$(CONFIG_HMM_MIRROR) += hmm.o
 obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
+obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c360f6a6c844..62f05f605fb5 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -21,6 +21,7 @@ struct backing_dev_info noop_backing_dev_info = {
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
 static struct class *bdi_class;
+const char *bdi_unknown_name = "(unknown)";
 
 /*
  * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU
diff --git a/mm/debug.c b/mm/debug.c
index 0461df1207cb..ecccd9f17801 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -46,7 +46,15 @@ void __dump_page(struct page *page, const char *reason)
 {
 	struct address_space *mapping;
 	bool page_poisoned = PagePoisoned(page);
+	/*
+	 * Accessing the pageblock without the zone lock. It could change to
+	 * "isolate" again in the meantime, but since we are just dumping the
+	 * state for debugging, it should be fine to accept a bit of
+	 * inaccuracy here due to racing.
+	 */
+	bool page_cma = is_migrate_cma_page(page);
 	int mapcount;
+	char *type = "";
 
 	/*
 	 * If struct page is poisoned don't access Page*() functions as that
@@ -78,9 +86,9 @@ void __dump_page(struct page *page, const char *reason)
 			page, page_ref_count(page), mapcount,
 			page->mapping, page_to_pgoff(page));
 	if (PageKsm(page))
-		pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags);
+		type = "ksm ";
 	else if (PageAnon(page))
-		pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags);
+		type = "anon ";
 	else if (mapping) {
 		if (mapping->host && mapping->host->i_dentry.first) {
 			struct dentry *dentry;
@@ -88,10 +96,12 @@ void __dump_page(struct page *page, const char *reason)
 			pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry);
 		} else
 			pr_warn("%ps\n", mapping->a_ops);
-		pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 	}
 	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
 
+	pr_warn("%sflags: %#lx(%pGp)%s\n", type, page->flags, &page->flags,
+		page_cma ? " CMA" : "");
+
 hex_only:
 	print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
@@ -153,7 +163,7 @@ void dump_mm(const struct mm_struct *mm)
 #endif
 		"exe_file %px\n"
 #ifdef CONFIG_MMU_NOTIFIER
-		"mmu_notifier_mm %px\n"
+		"notifier_subscriptions %px\n"
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 		"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
@@ -185,7 +195,7 @@ void dump_mm(const struct mm_struct *mm)
 #endif
 		mm->exe_file,
 #ifdef CONFIG_MMU_NOTIFIER
-		mm->mmu_notifier_mm,
+		mm->notifier_subscriptions,
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 		mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 1826f191e72c..a0018ad1a1f6 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -121,8 +121,8 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 		}
 	}
 
-	if (WARN(slot < 0, "%s(%08llx, %08lx) not found slot\n",
-		 __func__, (u64)phys_addr, size))
+	if (WARN(slot < 0, "%s(%pa, %08lx) not found slot\n",
+		 __func__, &phys_addr, size))
 		return NULL;
 
 	/* Don't allow wraparound or zero size */
@@ -158,8 +158,8 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 		--idx;
 		--nrpages;
 	}
-	WARN(early_ioremap_debug, "%s(%08llx, %08lx) [%d] => %08lx + %08lx\n",
-	     __func__, (u64)phys_addr, size, slot, offset, slot_virt[slot]);
+	WARN(early_ioremap_debug, "%s(%pa, %08lx) [%d] => %08lx + %08lx\n",
+	     __func__, &phys_addr, size, slot, offset, slot_virt[slot]);
 
 	prev_map[slot] = (void __iomem *)(offset + slot_virt[slot]);
 	return prev_map[slot];
diff --git a/mm/filemap.c b/mm/filemap.c
index bf6aa30be58d..1784478270e1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -632,33 +632,6 @@ static bool mapping_needs_writeback(struct address_space *mapping)
 	return mapping->nrpages;
 }
 
-int filemap_write_and_wait(struct address_space *mapping)
-{
-	int err = 0;
-
-	if (mapping_needs_writeback(mapping)) {
-		err = filemap_fdatawrite(mapping);
-		/*
-		 * Even if the above returned error, the pages may be
-		 * written partially (e.g. -ENOSPC), so we wait for it.
-		 * But the -EIO is special case, it may indicate the worst
-		 * thing (e.g. bug) happened, so we avoid waiting for it.
-		 */
-		if (err != -EIO) {
-			int err2 = filemap_fdatawait(mapping);
-			if (!err)
-				err = err2;
-		} else {
-			/* Clear any previously stored errors */
-			filemap_check_errors(mapping);
-		}
-	} else {
-		err = filemap_check_errors(mapping);
-	}
-	return err;
-}
-EXPORT_SYMBOL(filemap_write_and_wait);
-
 /**
  * filemap_write_and_wait_range - write out & wait on a file range
  * @mapping:	the address_space for the pages
@@ -680,7 +653,12 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 	if (mapping_needs_writeback(mapping)) {
 		err = __filemap_fdatawrite_range(mapping, lstart, lend,
 						 WB_SYNC_ALL);
-		/* See comment of filemap_write_and_wait() */
+		/*
+		 * Even if the above returned error, the pages may be
+		 * written partially (e.g. -ENOSPC), so we wait for it.
+		 * But the -EIO is special case, it may indicate the worst
+		 * thing (e.g. bug) happened, so we avoid waiting for it.
+		 */
 		if (err != -EIO) {
 			int err2 = filemap_fdatawait_range(mapping,
 						lstart, lend);
diff --git a/mm/gup.c b/mm/gup.c
index 7646bf993b25..1b521e0ac1de 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -29,8 +29,23 @@ struct follow_page_context {
 	unsigned int page_mask;
 };
 
+/*
+ * Return the compound head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+	struct page *head = compound_head(page);
+
+	if (WARN_ON_ONCE(page_ref_count(head) < 0))
+		return NULL;
+	if (unlikely(!page_cache_add_speculative(head, refs)))
+		return NULL;
+	return head;
+}
+
 /**
- * put_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
+ * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages
  * @pages:  array of pages to be maybe marked dirty, and definitely released.
  * @npages: number of pages in the @pages array.
  * @make_dirty: whether to mark the pages dirty
@@ -40,19 +55,19 @@ struct follow_page_context {
  *
  * For each page in the @pages array, make that page (or its head page, if a
  * compound page) dirty, if @make_dirty is true, and if the page was previously
- * listed as clean. In any case, releases all pages using put_user_page(),
- * possibly via put_user_pages(), for the non-dirty case.
+ * listed as clean. In any case, releases all pages using unpin_user_page(),
+ * possibly via unpin_user_pages(), for the non-dirty case.
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  *
  * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is
  * required, then the caller should a) verify that this is really correct,
  * because _lock() is usually required, and b) hand code it:
- * set_page_dirty_lock(), put_user_page().
+ * set_page_dirty_lock(), unpin_user_page().
  *
  */
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
-			       bool make_dirty)
+void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+				 bool make_dirty)
 {
 	unsigned long index;
 
@@ -63,7 +78,7 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 	 */
 
 	if (!make_dirty) {
-		put_user_pages(pages, npages);
+		unpin_user_pages(pages, npages);
 		return;
 	}
 
@@ -91,21 +106,21 @@ void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 		 */
 		if (!PageDirty(page))
 			set_page_dirty_lock(page);
-		put_user_page(page);
+		unpin_user_page(page);
 	}
 }
-EXPORT_SYMBOL(put_user_pages_dirty_lock);
+EXPORT_SYMBOL(unpin_user_pages_dirty_lock);
 
 /**
- * put_user_pages() - release an array of gup-pinned pages.
+ * unpin_user_pages() - release an array of gup-pinned pages.
  * @pages:  array of pages to be marked dirty and released.
  * @npages: number of pages in the @pages array.
  *
- * For each page in the @pages array, release the page using put_user_page().
+ * For each page in the @pages array, release the page using unpin_user_page().
  *
- * Please see the put_user_page() documentation for details.
+ * Please see the unpin_user_page() documentation for details.
  */
-void put_user_pages(struct page **pages, unsigned long npages)
+void unpin_user_pages(struct page **pages, unsigned long npages)
 {
 	unsigned long index;
 
@@ -115,9 +130,9 @@ void put_user_pages(struct page **pages, unsigned long npages)
 	 * single operation to the head page should suffice.
 	 */
 	for (index = 0; index < npages; index++)
-		put_user_page(pages[index]);
+		unpin_user_page(pages[index]);
 }
-EXPORT_SYMBOL(put_user_pages);
+EXPORT_SYMBOL(unpin_user_pages);
 
 #ifdef CONFIG_MMU
 static struct page *no_page_table(struct vm_area_struct *vma,
@@ -179,6 +194,10 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	pte_t *ptep, pte;
 
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
+			 (FOLL_PIN | FOLL_GET)))
+		return ERR_PTR(-EINVAL);
 retry:
 	if (unlikely(pmd_bad(*pmd)))
 		return no_page_table(vma, flags);
@@ -323,7 +342,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 	pmdval = READ_ONCE(*pmd);
 	if (pmd_none(pmdval))
 		return no_page_table(vma, flags);
-	if (pmd_huge(pmdval) && vma->vm_flags & VM_HUGETLB) {
+	if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
 		page = follow_huge_pmd(mm, address, pmd, flags);
 		if (page)
 			return page;
@@ -433,7 +452,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 	pud = pud_offset(p4dp, address);
 	if (pud_none(*pud))
 		return no_page_table(vma, flags);
-	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
+	if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) {
 		page = follow_huge_pud(mm, address, pud, flags);
 		if (page)
 			return page;
@@ -796,7 +815,7 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 	start = untagged_addr(start);
 
-	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+	VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN)));
 
 	/*
 	 * If FOLL_FORCE is set then do not force a full fault as the hinting
@@ -1020,7 +1039,16 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 		BUG_ON(*locked != 1);
 	}
 
-	if (pages)
+	/*
+	 * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior
+	 * is to set FOLL_GET if the caller wants pages[] filled in (but has
+	 * carelessly failed to specify FOLL_GET), so keep doing that, but only
+	 * for FOLL_GET, not for the newer FOLL_PIN.
+	 *
+	 * FOLL_PIN always expects pages to be non-null, but no need to assert
+	 * that here, as any failures will be obvious enough.
+	 */
+	if (pages && !(flags & FOLL_PIN))
 		flags |= FOLL_GET;
 
 	pages_done = 0;
@@ -1096,88 +1124,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
 	return pages_done;
 }
 
-/*
- * get_user_pages_remote() - pin user pages in memory
- * @tsk:	the task_struct to use for page fault accounting, or
- *		NULL if faults are not to be recorded.
- * @mm:		mm_struct of target mm
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @gup_flags:	flags modifying lookup behaviour
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long. Or NULL, if caller
- *		only intends to ensure the pages are faulted in.
- * @vmas:	array of pointers to vmas corresponding to each page.
- *		Or NULL if the caller does not require them.
- * @locked:	pointer to lock flag indicating whether lock is held and
- *		subsequently whether VM_FAULT_RETRY functionality can be
- *		utilised. Lock must initially be held.
- *
- * Returns either number of pages pinned (which may be less than the
- * number requested), or an error. Details about the return value:
- *
- * -- If nr_pages is 0, returns 0.
- * -- If nr_pages is >0, but no pages were pinned, returns -errno.
- * -- If nr_pages is >0, and some pages were pinned, returns the number of
- *    pages pinned. Again, this may be less than nr_pages.
- *
- * The caller is responsible for releasing returned @pages, via put_page().
- *
- * @vmas are valid only as long as mmap_sem is held.
- *
- * Must be called with mmap_sem held for read or write.
- *
- * get_user_pages walks a process's page tables and takes a reference to
- * each struct page that each user address corresponds to at a given
- * instant. That is, it takes the page that would be accessed if a user
- * thread accesses the given user virtual address at that instant.
- *
- * This does not guarantee that the page exists in the user mappings when
- * get_user_pages returns, and there may even be a completely different
- * page there in some cases (eg. if mmapped pagecache has been invalidated
- * and subsequently re faulted). However it does guarantee that the page
- * won't be freed completely. And mostly callers simply care that the page
- * contains data that was valid *at some point in time*. Typically, an IO
- * or similar operation cannot guarantee anything stronger anyway because
- * locks can't be held over the syscall boundary.
- *
- * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
- * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
- * be called after the page is finished with, and before put_page is called.
- *
- * get_user_pages is typically used for fewer-copy IO operations, to get a
- * handle on the memory by some means other than accesses via the user virtual
- * addresses. The pages may be submitted for DMA to devices or accessed via
- * their kernel linear mapping (via the kmap APIs). Care should be taken to
- * use the correct cache flushing APIs.
- *
- * See also get_user_pages_fast, for performance critical applications.
- *
- * get_user_pages should be phased out in favor of
- * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
- * should use get_user_pages because it cannot pass
- * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
- */
-long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, unsigned long nr_pages,
-		unsigned int gup_flags, struct page **pages,
-		struct vm_area_struct **vmas, int *locked)
-{
-	/*
-	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
-	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
-	 * vmas.  As there are no users of this flag in this call we simply
-	 * disallow this option for now.
-	 */
-	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
-		return -EINVAL;
-
-	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
-				       locked,
-				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
-}
-EXPORT_SYMBOL(get_user_pages_remote);
-
 /**
  * populate_vma_page_range() -  populate a range of pages in the vma.
  * @vma:   target vma
@@ -1612,6 +1558,116 @@ static __always_inline long __gup_longterm_locked(struct task_struct *tsk,
 #endif /* CONFIG_FS_DAX || CONFIG_CMA */
 
 /*
+ * get_user_pages_remote() - pin user pages in memory
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying lookup behaviour
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long. Or NULL, if caller
+ *		only intends to ensure the pages are faulted in.
+ * @vmas:	array of pointers to vmas corresponding to each page.
+ *		Or NULL if the caller does not require them.
+ * @locked:	pointer to lock flag indicating whether lock is held and
+ *		subsequently whether VM_FAULT_RETRY functionality can be
+ *		utilised. Lock must initially be held.
+ *
+ * Returns either number of pages pinned (which may be less than the
+ * number requested), or an error. Details about the return value:
+ *
+ * -- If nr_pages is 0, returns 0.
+ * -- If nr_pages is >0, but no pages were pinned, returns -errno.
+ * -- If nr_pages is >0, and some pages were pinned, returns the number of
+ *    pages pinned. Again, this may be less than nr_pages.
+ *
+ * The caller is responsible for releasing returned @pages, via put_page().
+ *
+ * @vmas are valid only as long as mmap_sem is held.
+ *
+ * Must be called with mmap_sem held for read or write.
+ *
+ * get_user_pages walks a process's page tables and takes a reference to
+ * each struct page that each user address corresponds to at a given
+ * instant. That is, it takes the page that would be accessed if a user
+ * thread accesses the given user virtual address at that instant.
+ *
+ * This does not guarantee that the page exists in the user mappings when
+ * get_user_pages returns, and there may even be a completely different
+ * page there in some cases (eg. if mmapped pagecache has been invalidated
+ * and subsequently re faulted). However it does guarantee that the page
+ * won't be freed completely. And mostly callers simply care that the page
+ * contains data that was valid *at some point in time*. Typically, an IO
+ * or similar operation cannot guarantee anything stronger anyway because
+ * locks can't be held over the syscall boundary.
+ *
+ * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page
+ * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must
+ * be called after the page is finished with, and before put_page is called.
+ *
+ * get_user_pages is typically used for fewer-copy IO operations, to get a
+ * handle on the memory by some means other than accesses via the user virtual
+ * addresses. The pages may be submitted for DMA to devices or accessed via
+ * their kernel linear mapping (via the kmap APIs). Care should be taken to
+ * use the correct cache flushing APIs.
+ *
+ * See also get_user_pages_fast, for performance critical applications.
+ *
+ * get_user_pages should be phased out in favor of
+ * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing
+ * should use get_user_pages because it cannot pass
+ * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault.
+ */
+#ifdef CONFIG_MMU
+long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, unsigned long nr_pages,
+		unsigned int gup_flags, struct page **pages,
+		struct vm_area_struct **vmas, int *locked)
+{
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that with an assertion:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
+
+	/*
+	 * Parts of FOLL_LONGTERM behavior are incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas. However, this only comes up if locked is set, and there are
+	 * callers that do request FOLL_LONGTERM, but do not set locked. So,
+	 * allow what we can.
+	 */
+	if (gup_flags & FOLL_LONGTERM) {
+		if (WARN_ON_ONCE(locked))
+			return -EINVAL;
+		/*
+		 * This will check the vmas (even if our vmas arg is NULL)
+		 * and return -ENOTSUPP if DAX isn't allowed in this case:
+		 */
+		return __gup_longterm_locked(tsk, mm, start, nr_pages, pages,
+					     vmas, gup_flags | FOLL_TOUCH |
+					     FOLL_REMOTE);
+	}
+
+	return __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas,
+				       locked,
+				       gup_flags | FOLL_TOUCH | FOLL_REMOTE);
+}
+EXPORT_SYMBOL(get_user_pages_remote);
+
+#else /* CONFIG_MMU */
+long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   struct vm_area_struct **vmas, int *locked)
+{
+	return 0;
+}
+#endif /* !CONFIG_MMU */
+
+/*
  * This is the same as get_user_pages_remote(), just with a
  * less-flexible calling convention where we assume that the task
  * and mm being operated on are the current task's and don't allow
@@ -1622,6 +1678,13 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas)
 {
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that with an assertion:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
+
 	return __gup_longterm_locked(current, current->mm, start, nr_pages,
 				     pages, vmas, gup_flags | FOLL_TOUCH);
 }
@@ -1729,7 +1792,7 @@ EXPORT_SYMBOL(get_user_pages_unlocked);
  * Before activating this code, please be aware that the following assumptions
  * are currently made:
  *
- *  *) Either HAVE_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
+ *  *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to
  *  free pages containing page tables or TLB flushing requires IPI broadcast.
  *
  *  *) ptes can be read atomically by the architecture.
@@ -1807,20 +1870,6 @@ static void __maybe_unused undo_dev_pagemap(int *nr, int nr_start,
 	}
 }
 
-/*
- * Return the compund head page with ref appropriately incremented,
- * or NULL if that failed.
- */
-static inline struct page *try_get_compound_head(struct page *page, int refs)
-{
-	struct page *head = compound_head(page);
-	if (WARN_ON_ONCE(page_ref_count(head) < 0))
-		return NULL;
-	if (unlikely(!page_cache_add_speculative(head, refs)))
-		return NULL;
-	return head;
-}
-
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 unsigned int flags, struct page **pages, int *nr)
@@ -1978,6 +2027,29 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
+static void put_compound_head(struct page *page, int refs)
+{
+	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
+	/*
+	 * Calling put_page() for each ref is unnecessarily slow. Only the last
+	 * ref needs a put_page().
+	 */
+	if (refs > 1)
+		page_ref_sub(page, refs - 1);
+	put_page(page);
+}
+
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
@@ -2007,32 +2079,20 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	/* hugepages are never "special" */
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
-
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(head, refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2079,28 +2139,19 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2120,28 +2171,19 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2157,28 +2199,20 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 
 	BUILD_BUG_ON(pgd_devmap(orig));
-	refs = 0;
+
 	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pgd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2237,7 +2271,7 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end,
 		pud_t pud = READ_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
+		if (unlikely(!pud_present(pud)))
 			return 0;
 		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, flags,
@@ -2393,29 +2427,15 @@ static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
 	return ret;
 }
 
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @gup_flags:	flags modifying pin behaviour
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages,
-			unsigned int gup_flags, struct page **pages)
+static int internal_get_user_pages_fast(unsigned long start, int nr_pages,
+					unsigned int gup_flags,
+					struct page **pages)
 {
 	unsigned long addr, len, end;
 	int nr = 0, ret = 0;
 
-	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
+	if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM |
+				       FOLL_FORCE | FOLL_PIN)))
 		return -EINVAL;
 
 	start = untagged_addr(start) & PAGE_MASK;
@@ -2455,4 +2475,103 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
 
 	return ret;
 }
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @gup_flags:	flags modifying pin behaviour
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number requested.
+ * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns
+ * -errno.
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages)
+{
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
+
+	return internal_get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+/**
+ * pin_user_pages_fast() - pin user pages in memory without taking locks
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages_fast().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+int pin_user_pages_fast(unsigned long start, int nr_pages,
+			unsigned int gup_flags, struct page **pages)
+{
+	/*
+	 * This is a placeholder, until the pin functionality is activated.
+	 * Until then, just behave like the corresponding get_user_pages*()
+	 * routine.
+	 */
+	return get_user_pages_fast(start, nr_pages, gup_flags, pages);
+}
+EXPORT_SYMBOL_GPL(pin_user_pages_fast);
+
+/**
+ * pin_user_pages_remote() - pin pages of a remote process (task != current)
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages_remote().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
+			   unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   struct vm_area_struct **vmas, int *locked)
+{
+	/*
+	 * This is a placeholder, until the pin functionality is activated.
+	 * Until then, just behave like the corresponding get_user_pages*()
+	 * routine.
+	 */
+	return get_user_pages_remote(tsk, mm, start, nr_pages, gup_flags, pages,
+				     vmas, locked);
+}
+EXPORT_SYMBOL(pin_user_pages_remote);
+
+/**
+ * pin_user_pages() - pin user pages in memory for use by other devices
+ *
+ * For now, this is a placeholder function, until various call sites are
+ * converted to use the correct get_user_pages*() or pin_user_pages*() API. So,
+ * this is identical to get_user_pages().
+ *
+ * This is intended for Case 1 (DIO) in Documentation/vm/pin_user_pages.rst. It
+ * is NOT intended for Case 2 (RDMA: long-term pins).
+ */
+long pin_user_pages(unsigned long start, unsigned long nr_pages,
+		    unsigned int gup_flags, struct page **pages,
+		    struct vm_area_struct **vmas)
+{
+	/*
+	 * This is a placeholder, until the pin functionality is activated.
+	 * Until then, just behave like the corresponding get_user_pages*()
+	 * routine.
+	 */
+	return get_user_pages(start, nr_pages, gup_flags, pages, vmas);
+}
+EXPORT_SYMBOL(pin_user_pages);
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index ad9d5b1c4473..8dba38e79a9f 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -49,18 +49,21 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 			nr = (next - addr) / PAGE_SIZE;
 		}
 
+		/* Filter out most gup flags: only allow a tiny subset here: */
+		gup->flags &= FOLL_WRITE;
+
 		switch (cmd) {
 		case GUP_FAST_BENCHMARK:
-			nr = get_user_pages_fast(addr, nr, gup->flags & 1,
+			nr = get_user_pages_fast(addr, nr, gup->flags,
 						 pages + i);
 			break;
 		case GUP_LONGTERM_BENCHMARK:
 			nr = get_user_pages(addr, nr,
-					    (gup->flags & 1) | FOLL_LONGTERM,
+					    gup->flags | FOLL_LONGTERM,
 					    pages + i, NULL);
 			break;
 		case GUP_BENCHMARK:
-			nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
+			nr = get_user_pages(addr, nr, gup->flags, pages + i,
 					    NULL);
 			break;
 		default:
diff --git a/mm/hmm.c b/mm/hmm.c
index d379cb6496ae..72e5a6d9a417 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -186,7 +186,7 @@ static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
 }
 
 static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
-			     struct mm_walk *walk)
+			     __always_unused int depth, struct mm_walk *walk)
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
@@ -380,7 +380,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 again:
 	pmd = READ_ONCE(*pmdp);
 	if (pmd_none(pmd))
-		return hmm_vma_walk_hole(start, end, walk);
+		return hmm_vma_walk_hole(start, end, -1, walk);
 
 	if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
 		bool fault, write_fault;
@@ -474,23 +474,32 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	unsigned long addr = start, next;
-	pmd_t *pmdp;
+	unsigned long addr = start;
 	pud_t pud;
-	int ret;
+	int ret = 0;
+	spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
+
+	if (!ptl)
+		return 0;
+
+	/* Normally we don't want to split the huge page */
+	walk->action = ACTION_CONTINUE;
 
-again:
 	pud = READ_ONCE(*pudp);
-	if (pud_none(pud))
-		return hmm_vma_walk_hole(start, end, walk);
+	if (pud_none(pud)) {
+		ret = hmm_vma_walk_hole(start, end, -1, walk);
+		goto out_unlock;
+	}
 
 	if (pud_huge(pud) && pud_devmap(pud)) {
 		unsigned long i, npages, pfn;
 		uint64_t *pfns, cpu_flags;
 		bool fault, write_fault;
 
-		if (!pud_present(pud))
-			return hmm_vma_walk_hole(start, end, walk);
+		if (!pud_present(pud)) {
+			ret = hmm_vma_walk_hole(start, end, -1, walk);
+			goto out_unlock;
+		}
 
 		i = (addr - range->start) >> PAGE_SHIFT;
 		npages = (end - addr) >> PAGE_SHIFT;
@@ -499,16 +508,20 @@ again:
 		cpu_flags = pud_to_hmm_pfn_flags(range, pud);
 		hmm_range_need_fault(hmm_vma_walk, pfns, npages,
 				     cpu_flags, &fault, &write_fault);
-		if (fault || write_fault)
-			return hmm_vma_walk_hole_(addr, end, fault,
-						write_fault, walk);
+		if (fault || write_fault) {
+			ret = hmm_vma_walk_hole_(addr, end, fault,
+						 write_fault, walk);
+			goto out_unlock;
+		}
 
 		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 		for (i = 0; i < npages; ++i, ++pfn) {
 			hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
 					      hmm_vma_walk->pgmap);
-			if (unlikely(!hmm_vma_walk->pgmap))
-				return -EBUSY;
+			if (unlikely(!hmm_vma_walk->pgmap)) {
+				ret = -EBUSY;
+				goto out_unlock;
+			}
 			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
 				  cpu_flags;
 		}
@@ -517,22 +530,15 @@ again:
 			hmm_vma_walk->pgmap = NULL;
 		}
 		hmm_vma_walk->last = end;
-		return 0;
+		goto out_unlock;
 	}
 
-	split_huge_pud(walk->vma, pudp, addr);
-	if (pud_none(*pudp))
-		goto again;
+	/* Ask for the PUD to be split */
+	walk->action = ACTION_SUBTREE;
 
-	pmdp = pmd_offset(pudp, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
-		if (ret)
-			return ret;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 0;
+out_unlock:
+	spin_unlock(ptl);
+	return ret;
 }
 #else
 #define hmm_vma_walk_pud	NULL
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a88093213674..b08b199f9a11 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -177,16 +177,13 @@ static ssize_t enabled_store(struct kobject *kobj,
 {
 	ssize_t ret = count;
 
-	if (!memcmp("always", buf,
-		    min(sizeof("always")-1, count))) {
+	if (sysfs_streq(buf, "always")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("madvise", buf,
-			   min(sizeof("madvise")-1, count))) {
+	} else if (sysfs_streq(buf, "madvise")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("never", buf,
-			   min(sizeof("never")-1, count))) {
+	} else if (sysfs_streq(buf, "never")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags);
 	} else
@@ -250,32 +247,27 @@ static ssize_t defrag_store(struct kobject *kobj,
 			    struct kobj_attribute *attr,
 			    const char *buf, size_t count)
 {
-	if (!memcmp("always", buf,
-		    min(sizeof("always")-1, count))) {
+	if (sysfs_streq(buf, "always")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("defer+madvise", buf,
-		    min(sizeof("defer+madvise")-1, count))) {
+	} else if (sysfs_streq(buf, "defer+madvise")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("defer", buf,
-		    min(sizeof("defer")-1, count))) {
+	} else if (sysfs_streq(buf, "defer")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("madvise", buf,
-			   min(sizeof("madvise")-1, count))) {
+	} else if (sysfs_streq(buf, "madvise")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
 		set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
-	} else if (!memcmp("never", buf,
-			   min(sizeof("never")-1, count))) {
+	} else if (sysfs_streq(buf, "never")) {
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
 		clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
@@ -527,6 +519,17 @@ void prep_transhuge_page(struct page *page)
 	set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
 }
 
+bool is_transparent_hugepage(struct page *page)
+{
+	if (!PageCompound(page))
+		return 0;
+
+	page = compound_head(page);
+	return is_huge_zero_page(page) ||
+	       page[1].compound_dtor == TRANSHUGE_PAGE_DTOR;
+}
+EXPORT_SYMBOL_GPL(is_transparent_hugepage);
+
 static unsigned long __thp_get_unmapped_area(struct file *filp,
 		unsigned long addr, unsigned long len,
 		loff_t off, unsigned long flags, unsigned long size)
@@ -2704,7 +2707,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct page *head = compound_head(page);
 	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
-	struct deferred_split *ds_queue = get_deferred_split_queue(page);
+	struct deferred_split *ds_queue = get_deferred_split_queue(head);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
 	int count, mapcount, extra_pins, ret;
@@ -2712,11 +2715,11 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	unsigned long flags;
 	pgoff_t end;
 
-	VM_BUG_ON_PAGE(is_huge_zero_page(page), page);
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE(!PageCompound(page), page);
+	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
+	VM_BUG_ON_PAGE(!PageLocked(head), head);
+	VM_BUG_ON_PAGE(!PageCompound(head), head);
 
-	if (PageWriteback(page))
+	if (PageWriteback(head))
 		return -EBUSY;
 
 	if (PageAnon(head)) {
@@ -2767,7 +2770,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		goto out_unlock;
 	}
 
-	mlocked = PageMlocked(page);
+	mlocked = PageMlocked(head);
 	unmap_page(head);
 	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
@@ -2799,14 +2802,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
+		spin_unlock(&ds_queue->split_queue_lock);
 		if (mapping) {
-			if (PageSwapBacked(page))
-				__dec_node_page_state(page, NR_SHMEM_THPS);
+			if (PageSwapBacked(head))
+				__dec_node_page_state(head, NR_SHMEM_THPS);
 			else
-				__dec_node_page_state(page, NR_FILE_THPS);
+				__dec_node_page_state(head, NR_FILE_THPS);
 		}
 
-		spin_unlock(&ds_queue->split_queue_lock);
 		__split_huge_page(page, list, end, flags);
 		if (PageSwapCache(head)) {
 			swp_entry_t entry = { .val = page_private(head) };
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index c15d8ae68c96..6aa51723b92b 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -110,6 +110,7 @@ void *memset(void *addr, int c, size_t len)
 	return __memset(addr, c, len);
 }
 
+#ifdef __HAVE_ARCH_MEMMOVE
 #undef memmove
 void *memmove(void *dest, const void *src, size_t len)
 {
@@ -118,6 +119,7 @@ void *memmove(void *dest, const void *src, size_t len)
 
 	return __memmove(dest, src, len);
 }
+#endif
 
 #undef memcpy
 void *memcpy(void *dest, const void *src, size_t len)
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 244607663363..3a4259eeb5a0 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -13,7 +13,7 @@
  *
  * The following locks and mutexes are used by kmemleak:
  *
- * - kmemleak_lock (rwlock): protects the object_list modifications and
+ * - kmemleak_lock (raw_spinlock_t): protects the object_list modifications and
  *   accesses to the object_tree_root. The object_list is the main list
  *   holding the metadata (struct kmemleak_object) for the allocated memory
  *   blocks. The object_tree_root is a red black tree used to look-up
@@ -22,13 +22,13 @@
  *   object_tree_root in the create_object() function called from the
  *   kmemleak_alloc() callback and removed in delete_object() called from the
  *   kmemleak_free() callback
- * - kmemleak_object.lock (spinlock): protects a kmemleak_object. Accesses to
- *   the metadata (e.g. count) are protected by this lock. Note that some
- *   members of this structure may be protected by other means (atomic or
- *   kmemleak_lock). This lock is also held when scanning the corresponding
- *   memory block to avoid the kernel freeing it via the kmemleak_free()
- *   callback. This is less heavyweight than holding a global lock like
- *   kmemleak_lock during scanning
+ * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object.
+ *   Accesses to the metadata (e.g. count) are protected by this lock. Note
+ *   that some members of this structure may be protected by other means
+ *   (atomic or kmemleak_lock). This lock is also held when scanning the
+ *   corresponding memory block to avoid the kernel freeing it via the
+ *   kmemleak_free() callback. This is less heavyweight than holding a global
+ *   lock like kmemleak_lock during scanning.
  * - scan_mutex (mutex): ensures that only one thread may scan the memory for
  *   unreferenced objects at a time. The gray_list contains the objects which
  *   are already referenced or marked as false positives and need to be
@@ -135,7 +135,7 @@ struct kmemleak_scan_area {
  * (use_count) and freed using the RCU mechanism.
  */
 struct kmemleak_object {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	unsigned int flags;		/* object status flags */
 	struct list_head object_list;
 	struct list_head gray_list;
@@ -191,8 +191,8 @@ static int mem_pool_free_count = ARRAY_SIZE(mem_pool);
 static LIST_HEAD(mem_pool_free_list);
 /* search tree for object boundaries */
 static struct rb_root object_tree_root = RB_ROOT;
-/* rw_lock protecting the access to object_list and object_tree_root */
-static DEFINE_RWLOCK(kmemleak_lock);
+/* protecting the access to object_list and object_tree_root */
+static DEFINE_RAW_SPINLOCK(kmemleak_lock);
 
 /* allocation caches for kmemleak internal data */
 static struct kmem_cache *object_cache;
@@ -426,7 +426,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
 	}
 
 	/* slab allocation failed, try the memory pool */
-	write_lock_irqsave(&kmemleak_lock, flags);
+	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 	object = list_first_entry_or_null(&mem_pool_free_list,
 					  typeof(*object), object_list);
 	if (object)
@@ -435,7 +435,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp)
 		object = &mem_pool[--mem_pool_free_count];
 	else
 		pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n");
-	write_unlock_irqrestore(&kmemleak_lock, flags);
+	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 
 	return object;
 }
@@ -453,9 +453,9 @@ static void mem_pool_free(struct kmemleak_object *object)
 	}
 
 	/* add the object to the memory pool free list */
-	write_lock_irqsave(&kmemleak_lock, flags);
+	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 	list_add(&object->object_list, &mem_pool_free_list);
-	write_unlock_irqrestore(&kmemleak_lock, flags);
+	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 }
 
 /*
@@ -514,9 +514,9 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
 	struct kmemleak_object *object;
 
 	rcu_read_lock();
-	read_lock_irqsave(&kmemleak_lock, flags);
+	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 	object = lookup_object(ptr, alias);
-	read_unlock_irqrestore(&kmemleak_lock, flags);
+	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 
 	/* check whether the object is still available */
 	if (object && !get_object(object))
@@ -546,11 +546,11 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
 	unsigned long flags;
 	struct kmemleak_object *object;
 
-	write_lock_irqsave(&kmemleak_lock, flags);
+	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 	object = lookup_object(ptr, alias);
 	if (object)
 		__remove_object(object);
-	write_unlock_irqrestore(&kmemleak_lock, flags);
+	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 
 	return object;
 }
@@ -585,7 +585,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	INIT_LIST_HEAD(&object->object_list);
 	INIT_LIST_HEAD(&object->gray_list);
 	INIT_HLIST_HEAD(&object->area_list);
-	spin_lock_init(&object->lock);
+	raw_spin_lock_init(&object->lock);
 	atomic_set(&object->use_count, 1);
 	object->flags = OBJECT_ALLOCATED;
 	object->pointer = ptr;
@@ -617,7 +617,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	/* kernel backtrace */
 	object->trace_len = __save_stack_trace(object->trace);
 
-	write_lock_irqsave(&kmemleak_lock, flags);
+	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 
 	untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr);
 	min_addr = min(min_addr, untagged_ptr);
@@ -649,7 +649,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 
 	list_add_tail_rcu(&object->object_list, &object_list);
 out:
-	write_unlock_irqrestore(&kmemleak_lock, flags);
+	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 	return object;
 }
 
@@ -667,9 +667,9 @@ static void __delete_object(struct kmemleak_object *object)
 	 * Locking here also ensures that the corresponding memory block
 	 * cannot be freed when it is being scanned.
 	 */
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->flags &= ~OBJECT_ALLOCATED;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 
@@ -739,9 +739,9 @@ static void paint_it(struct kmemleak_object *object, int color)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	__paint_it(object, color);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 }
 
 static void paint_ptr(unsigned long ptr, int color)
@@ -798,7 +798,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 	if (scan_area_cache)
 		area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp));
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	if (!area) {
 		pr_warn_once("Cannot allocate a scan area, scanning the full object\n");
 		/* mark the object for full scan to avoid false positives */
@@ -820,7 +820,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 
 	hlist_add_head(&area->node, &object->area_list);
 out_unlock:
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 
@@ -842,9 +842,9 @@ static void object_set_excess_ref(unsigned long ptr, unsigned long excess_ref)
 		return;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->excess_ref = excess_ref;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 
@@ -864,9 +864,9 @@ static void object_no_scan(unsigned long ptr)
 		return;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->flags |= OBJECT_NO_SCAN;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 
@@ -1026,9 +1026,9 @@ void __ref kmemleak_update_trace(const void *ptr)
 		return;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->trace_len = __save_stack_trace(object->trace);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
 }
@@ -1233,7 +1233,7 @@ static void scan_block(void *_start, void *_end,
 	unsigned long flags;
 	unsigned long untagged_ptr;
 
-	read_lock_irqsave(&kmemleak_lock, flags);
+	raw_spin_lock_irqsave(&kmemleak_lock, flags);
 	for (ptr = start; ptr < end; ptr++) {
 		struct kmemleak_object *object;
 		unsigned long pointer;
@@ -1268,7 +1268,7 @@ static void scan_block(void *_start, void *_end,
 		 * previously acquired in scan_object(). These locks are
 		 * enclosed by scan_mutex.
 		 */
-		spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
+		raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
 		/* only pass surplus references (object already gray) */
 		if (color_gray(object)) {
 			excess_ref = object->excess_ref;
@@ -1277,7 +1277,7 @@ static void scan_block(void *_start, void *_end,
 			excess_ref = 0;
 			update_refs(object);
 		}
-		spin_unlock(&object->lock);
+		raw_spin_unlock(&object->lock);
 
 		if (excess_ref) {
 			object = lookup_object(excess_ref, 0);
@@ -1286,12 +1286,12 @@ static void scan_block(void *_start, void *_end,
 			if (object == scanned)
 				/* circular reference, ignore */
 				continue;
-			spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
+			raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
 			update_refs(object);
-			spin_unlock(&object->lock);
+			raw_spin_unlock(&object->lock);
 		}
 	}
-	read_unlock_irqrestore(&kmemleak_lock, flags);
+	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);
 }
 
 /*
@@ -1324,7 +1324,7 @@ static void scan_object(struct kmemleak_object *object)
 	 * Once the object->lock is acquired, the corresponding memory block
 	 * cannot be freed (the same lock is acquired in delete_object).
 	 */
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	if (object->flags & OBJECT_NO_SCAN)
 		goto out;
 	if (!(object->flags & OBJECT_ALLOCATED))
@@ -1344,9 +1344,9 @@ static void scan_object(struct kmemleak_object *object)
 			if (start >= end)
 				break;
 
-			spin_unlock_irqrestore(&object->lock, flags);
+			raw_spin_unlock_irqrestore(&object->lock, flags);
 			cond_resched();
-			spin_lock_irqsave(&object->lock, flags);
+			raw_spin_lock_irqsave(&object->lock, flags);
 		} while (object->flags & OBJECT_ALLOCATED);
 	} else
 		hlist_for_each_entry(area, &object->area_list, node)
@@ -1354,7 +1354,7 @@ static void scan_object(struct kmemleak_object *object)
 				   (void *)(area->start + area->size),
 				   object);
 out:
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 }
 
 /*
@@ -1407,7 +1407,7 @@ static void kmemleak_scan(void)
 	/* prepare the kmemleak_object's */
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 #ifdef DEBUG
 		/*
 		 * With a few exceptions there should be a maximum of
@@ -1424,7 +1424,7 @@ static void kmemleak_scan(void)
 		if (color_gray(object) && get_object(object))
 			list_add_tail(&object->gray_list, &gray_list);
 
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 
@@ -1492,14 +1492,14 @@ static void kmemleak_scan(void)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 		if (color_white(object) && (object->flags & OBJECT_ALLOCATED)
 		    && update_checksum(object) && get_object(object)) {
 			/* color it gray temporarily */
 			object->count = object->min_count;
 			list_add_tail(&object->gray_list, &gray_list);
 		}
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 
@@ -1519,7 +1519,7 @@ static void kmemleak_scan(void)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 		if (unreferenced_object(object) &&
 		    !(object->flags & OBJECT_REPORTED)) {
 			object->flags |= OBJECT_REPORTED;
@@ -1529,7 +1529,7 @@ static void kmemleak_scan(void)
 
 			new_leaks++;
 		}
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 
@@ -1681,10 +1681,10 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v)
 	struct kmemleak_object *object = v;
 	unsigned long flags;
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object))
 		print_unreferenced(seq, object);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	return 0;
 }
 
@@ -1714,9 +1714,9 @@ static int dump_str_object_info(const char *str)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	dump_object_info(object);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
 	return 0;
@@ -1735,11 +1735,11 @@ static void kmemleak_clear(void)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 		if ((object->flags & OBJECT_REPORTED) &&
 		    unreferenced_object(object))
 			__paint_it(object, KMEMLEAK_GREY);
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 
diff --git a/mm/madvise.c b/mm/madvise.c
index bcdb6a042787..43b47d3fae02 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1044,7 +1044,7 @@ madvise_behavior_valid(int behavior)
  *  -EBADF  - map exists, but area maps something that isn't a file.
  *  -EAGAIN - a kernel resource was temporarily unavailable.
  */
-SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
+int do_madvise(unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1141,3 +1141,8 @@ out:
 
 	return error;
 }
+
+SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
+{
+	return do_madvise(start, len_in, behavior);
+}
diff --git a/mm/memblock.c b/mm/memblock.c
index 4bc2c7d8bf42..eba94ee3de0b 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -575,7 +575,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * Return:
  * 0 on success, -errno on failure.
  */
-int __init_memblock memblock_add_range(struct memblock_type *type,
+static int __init_memblock memblock_add_range(struct memblock_type *type,
 				phys_addr_t base, phys_addr_t size,
 				int nid, enum memblock_flags flags)
 {
@@ -694,7 +694,7 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
 
-	memblock_dbg("memblock_add: [%pa-%pa] %pS\n",
+	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
 		     &base, &end, (void *)_RET_IP_);
 
 	return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
@@ -795,7 +795,7 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
 
-	memblock_dbg("memblock_remove: [%pa-%pa] %pS\n",
+	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
 		     &base, &end, (void *)_RET_IP_);
 
 	return memblock_remove_range(&memblock.memory, base, size);
@@ -813,7 +813,7 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
 
-	memblock_dbg("   memblock_free: [%pa-%pa] %pS\n",
+	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
 		     &base, &end, (void *)_RET_IP_);
 
 	kmemleak_free_part_phys(base, size);
@@ -824,12 +824,24 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
 
-	memblock_dbg("memblock_reserve: [%pa-%pa] %pS\n",
+	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
 		     &base, &end, (void *)_RET_IP_);
 
 	return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0);
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
+int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size)
+{
+	phys_addr_t end = base + size - 1;
+
+	memblock_dbg("%s: [%pa-%pa] %pS\n", __func__,
+		     &base, &end, (void *)_RET_IP_);
+
+	return memblock_add_range(&memblock.physmem, base, size, MAX_NUMNODES, 0);
+}
+#endif
+
 /**
  * memblock_setclr_flag - set or clear flag for a memory region
  * @base: base address of the region
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6c83cf4ed970..6f6dc8712e39 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5340,14 +5340,6 @@ static int mem_cgroup_move_account(struct page *page,
 		__mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
 	}
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (compound && !list_empty(page_deferred_list(page))) {
-		spin_lock(&from->deferred_split_queue.split_queue_lock);
-		list_del_init(page_deferred_list(page));
-		from->deferred_split_queue.split_queue_len--;
-		spin_unlock(&from->deferred_split_queue.split_queue_lock);
-	}
-#endif
 	/*
 	 * It is safe to change page->mem_cgroup here because the page
 	 * is referenced, charged, and isolated - we can't race with
@@ -5357,16 +5349,6 @@ static int mem_cgroup_move_account(struct page *page,
 	/* caller should have done css_get */
 	page->mem_cgroup = to;
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (compound && list_empty(page_deferred_list(page))) {
-		spin_lock(&to->deferred_split_queue.split_queue_lock);
-		list_add_tail(page_deferred_list(page),
-			      &to->deferred_split_queue.split_queue);
-		to->deferred_split_queue.split_queue_len++;
-		spin_unlock(&to->deferred_split_queue.split_queue_lock);
-	}
-#endif
-
 	spin_unlock_irqrestore(&from->move_lock, flags);
 
 	ret = 0;
@@ -6651,7 +6633,6 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 {
 	struct mem_cgroup *memcg;
 	unsigned int nr_pages;
-	bool compound;
 	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
@@ -6673,8 +6654,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 		return;
 
 	/* Force-charge the new page. The old one will be freed soon */
-	compound = PageTransHuge(newpage);
-	nr_pages = compound ? hpage_nr_pages(newpage) : 1;
+	nr_pages = hpage_nr_pages(newpage);
 
 	page_counter_charge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
@@ -6684,7 +6664,8 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 	commit_charge(newpage, memcg, false);
 
 	local_irq_save(flags);
-	mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
+	mem_cgroup_charge_statistics(memcg, newpage, PageTransHuge(newpage),
+			nr_pages);
 	memcg_check_events(memcg, newpage);
 	local_irq_restore(flags);
 }
diff --git a/mm/memory.c b/mm/memory.c
index 1c4be871a237..0bccc622e482 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1664,6 +1664,9 @@ out_unlock:
  * vmf_insert_pfn_prot should only be used if using multiple VMAs is
  * impractical.
  *
+ * See vmf_insert_mixed_prot() for a discussion of the implication of using
+ * a value of @pgprot different from that of @vma->vm_page_prot.
+ *
  * Context: Process context.  May allocate using %GFP_KERNEL.
  * Return: vm_fault_t value.
  */
@@ -1737,9 +1740,9 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
 }
 
 static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn, bool mkwrite)
+		unsigned long addr, pfn_t pfn, pgprot_t pgprot,
+		bool mkwrite)
 {
-	pgprot_t pgprot = vma->vm_page_prot;
 	int err;
 
 	BUG_ON(!vm_mixed_ok(vma, pfn));
@@ -1782,10 +1785,43 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
+/**
+ * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vmf_insert_mixed(), except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * Typically this function should be used by drivers to set caching- and
+ * encryption bits different than those of @vma->vm_page_prot, because
+ * the caching- or encryption mode may not be known at mmap() time.
+ * This is ok as long as @vma->vm_page_prot is not used by the core vm
+ * to set caching and encryption bits for those vmas (except for COW pages).
+ * This is ensured by core vm only modifying these page table entries using
+ * functions that don't touch caching- or encryption bits, using pte_modify()
+ * if needed. (See for example mprotect()).
+ * Also when new page-table entries are created, this is only done using the
+ * fault() callback, and never using the value of vma->vm_page_prot,
+ * except for page-table entries that point to anonymous pages as the result
+ * of COW.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
+				 pfn_t pfn, pgprot_t pgprot)
+{
+	return __vm_insert_mixed(vma, addr, pfn, pgprot, false);
+}
+EXPORT_SYMBOL(vmf_insert_mixed_prot);
+
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 		pfn_t pfn)
 {
-	return __vm_insert_mixed(vma, addr, pfn, false);
+	return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false);
 }
 EXPORT_SYMBOL(vmf_insert_mixed);
 
@@ -1797,7 +1833,7 @@ EXPORT_SYMBOL(vmf_insert_mixed);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn)
 {
-	return __vm_insert_mixed(vma, addr, pfn, true);
+	return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true);
 }
 EXPORT_SYMBOL(vmf_insert_mixed_mkwrite);
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a91a072f2b2c..0a54ffac8c68 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -355,7 +355,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 		if (unlikely(pfn_to_nid(start_pfn) != nid))
 			continue;
 
-		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
+		if (zone != page_zone(pfn_to_page(start_pfn)))
 			continue;
 
 		return start_pfn;
@@ -380,7 +380,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 		if (unlikely(pfn_to_nid(pfn) != nid))
 			continue;
 
-		if (zone && zone != page_zone(pfn_to_page(pfn)))
+		if (zone != page_zone(pfn_to_page(pfn)))
 			continue;
 
 		return pfn;
@@ -392,14 +392,11 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 			     unsigned long end_pfn)
 {
-	unsigned long zone_start_pfn = zone->zone_start_pfn;
-	unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
-	unsigned long zone_end_pfn = z;
 	unsigned long pfn;
 	int nid = zone_to_nid(zone);
 
 	zone_span_writelock(zone);
-	if (zone_start_pfn == start_pfn) {
+	if (zone->zone_start_pfn == start_pfn) {
 		/*
 		 * If the section is smallest section in the zone, it need
 		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
@@ -407,50 +404,30 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 		 * for shrinking zone.
 		 */
 		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
-						zone_end_pfn);
+						zone_end_pfn(zone));
 		if (pfn) {
+			zone->spanned_pages = zone_end_pfn(zone) - pfn;
 			zone->zone_start_pfn = pfn;
-			zone->spanned_pages = zone_end_pfn - pfn;
+		} else {
+			zone->zone_start_pfn = 0;
+			zone->spanned_pages = 0;
 		}
-	} else if (zone_end_pfn == end_pfn) {
+	} else if (zone_end_pfn(zone) == end_pfn) {
 		/*
 		 * If the section is biggest section in the zone, it need
 		 * shrink zone->spanned_pages.
 		 * In this case, we find second biggest valid mem_section for
 		 * shrinking zone.
 		 */
-		pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
+		pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn,
 					       start_pfn);
 		if (pfn)
-			zone->spanned_pages = pfn - zone_start_pfn + 1;
-	}
-
-	/*
-	 * The section is not biggest or smallest mem_section in the zone, it
-	 * only creates a hole in the zone. So in this case, we need not
-	 * change the zone. But perhaps, the zone has only hole data. Thus
-	 * it check the zone has only hole or not.
-	 */
-	pfn = zone_start_pfn;
-	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_to_online_page(pfn)))
-			continue;
-
-		if (page_zone(pfn_to_page(pfn)) != zone)
-			continue;
-
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
-			continue;
-
-		/* If we find valid section, we have nothing to do */
-		zone_span_writeunlock(zone);
-		return;
+			zone->spanned_pages = pfn - zone->zone_start_pfn + 1;
+		else {
+			zone->zone_start_pfn = 0;
+			zone->spanned_pages = 0;
+		}
 	}
-
-	/* The zone has no valid section */
-	zone->zone_start_pfn = 0;
-	zone->spanned_pages = 0;
 	zone_span_writeunlock(zone);
 }
 
@@ -490,6 +467,9 @@ void __ref remove_pfn_range_from_zone(struct zone *zone,
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long flags;
 
+	/* Poison struct pages because they are now uninitialized again. */
+	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+
 #ifdef CONFIG_ZONE_DEVICE
 	/*
 	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
@@ -536,25 +516,20 @@ static void __remove_section(unsigned long pfn, unsigned long nr_pages,
 void __remove_pages(unsigned long pfn, unsigned long nr_pages,
 		    struct vmem_altmap *altmap)
 {
+	const unsigned long end_pfn = pfn + nr_pages;
+	unsigned long cur_nr_pages;
 	unsigned long map_offset = 0;
-	unsigned long nr, start_sec, end_sec;
 
 	map_offset = vmem_altmap_offset(altmap);
 
 	if (check_pfn_span(pfn, nr_pages, "remove"))
 		return;
 
-	start_sec = pfn_to_section_nr(pfn);
-	end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
-	for (nr = start_sec; nr <= end_sec; nr++) {
-		unsigned long pfns;
-
+	for (; pfn < end_pfn; pfn += cur_nr_pages) {
 		cond_resched();
-		pfns = min(nr_pages, PAGES_PER_SECTION
-				- (pfn & ~PAGE_SECTION_MASK));
-		__remove_section(pfn, pfns, map_offset, altmap);
-		pfn += pfns;
-		nr_pages -= pfns;
+		/* Select all remaining pages up to the next section boundary */
+		cur_nr_pages = min(end_pfn - pfn, -(pfn | PAGE_SECTION_MASK));
+		__remove_section(pfn, cur_nr_pages, map_offset, altmap);
 		map_offset = 0;
 	}
 }
@@ -783,27 +758,18 @@ struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
 	return default_zone_for_pfn(nid, start_pfn, nr_pages);
 }
 
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
+		       int online_type, int nid)
 {
 	unsigned long flags;
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
 	int need_zonelists_rebuild = 0;
-	int nid;
 	int ret;
 	struct memory_notify arg;
-	struct memory_block *mem;
 
 	mem_hotplug_begin();
 
-	/*
-	 * We can't use pfn_to_nid() because nid might be stored in struct page
-	 * which is not yet initialized. Instead, we find nid from memory block.
-	 */
-	mem = find_memory_block(__pfn_to_section(pfn));
-	nid = mem->nid;
-	put_device(&mem->dev);
-
 	/* associate pfn range with the zone */
 	zone = zone_for_pfn_range(online_type, nid, pfn, nr_pages);
 	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL);
@@ -1182,7 +1148,7 @@ static bool is_pageblock_removable_nolock(unsigned long pfn)
 	if (!zone_spans_pfn(zone, pfn))
 		return false;
 
-	return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE,
+	return !has_unmovable_pages(zone, page, MIGRATE_MOVABLE,
 				    MEMORY_OFFLINE);
 }
 
@@ -1206,14 +1172,13 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 }
 
 /*
- * Confirm all pages in a range [start, end) belong to the same zone.
- * When true, return its valid [start, end).
+ * Confirm all pages in a range [start, end) belong to the same zone (skipping
+ * memory holes). When true, return the zone.
  */
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
-			 unsigned long *valid_start, unsigned long *valid_end)
+struct zone *test_pages_in_a_zone(unsigned long start_pfn,
+				  unsigned long end_pfn)
 {
 	unsigned long pfn, sec_end_pfn;
-	unsigned long start, end;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
@@ -1234,24 +1199,15 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
 				continue;
 			/* Check if we got outside of the zone */
 			if (zone && !zone_spans_pfn(zone, pfn + i))
-				return 0;
+				return NULL;
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
-				return 0;
-			if (!zone)
-				start = pfn + i;
+				return NULL;
 			zone = page_zone(page);
-			end = pfn + MAX_ORDER_NR_PAGES;
 		}
 	}
 
-	if (zone) {
-		*valid_start = start;
-		*valid_end = min(end, end_pfn);
-		return 1;
-	} else {
-		return 0;
-	}
+	return zone;
 }
 
 /*
@@ -1496,7 +1452,6 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	unsigned long offlined_pages = 0;
 	int ret, node, nr_isolate_pageblock;
 	unsigned long flags;
-	unsigned long valid_start, valid_end;
 	struct zone *zone;
 	struct memory_notify arg;
 	char *reason;
@@ -1521,14 +1476,12 @@ static int __ref __offline_pages(unsigned long start_pfn,
 
 	/* This makes hotplug much easier...and readable.
 	   we assume this for now. .*/
-	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start,
-				  &valid_end)) {
+	zone = test_pages_in_a_zone(start_pfn, end_pfn);
+	if (!zone) {
 		ret = -EINVAL;
 		reason = "multizone range";
 		goto failed_removal;
 	}
-
-	zone = page_zone(pfn_to_page(valid_start));
 	node = zone_to_nid(zone);
 
 	/* set above range as isolated */
@@ -1764,8 +1717,6 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 
 	BUG_ON(check_hotplug_memory_range(start, size));
 
-	mem_hotplug_begin();
-
 	/*
 	 * All memory blocks must be offlined before removing memory.  Check
 	 * whether all memory blocks in question are offline and return error
@@ -1778,9 +1729,14 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size)
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
 
-	/* remove memory block devices before removing memory */
+	/*
+	 * Memory block device removal under the device_hotplug_lock is
+	 * a barrier against racing online attempts.
+	 */
 	remove_memory_block_devices(start, size);
 
+	mem_hotplug_begin();
+
 	arch_remove_memory(nid, start, size, NULL);
 	memblock_free(start, size);
 	memblock_remove(start, size);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b2920ae87a61..977c641f78cf 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2821,6 +2821,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 	char *flags = strchr(str, '=');
 	int err = 1, mode;
 
+	if (flags)
+		*flags++ = '\0';	/* terminate mode string */
+
 	if (nodelist) {
 		/* NUL-terminate mode or flags string */
 		*nodelist++ = '\0';
@@ -2831,9 +2834,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
 	} else
 		nodes_clear(nodes);
 
-	if (flags)
-		*flags++ = '\0';	/* terminate mode string */
-
 	mode = match_string(policy_modes, MPOL_MAX, str);
 	if (mode < 0)
 		goto out;
diff --git a/mm/memremap.c b/mm/memremap.c
index c51c6bd2fe34..09b5b7adc773 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -27,7 +27,8 @@ static void devmap_managed_enable_put(void)
 
 static int devmap_managed_enable_get(struct dev_pagemap *pgmap)
 {
-	if (!pgmap->ops || !pgmap->ops->page_free) {
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE &&
+	    (!pgmap->ops || !pgmap->ops->page_free)) {
 		WARN(1, "Missing page_free method\n");
 		return -EINVAL;
 	}
@@ -119,6 +120,8 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 	nid = page_to_nid(first_page);
 
 	mem_hotplug_begin();
+	remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(res->start),
+				   PHYS_PFN(resource_size(res)));
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		__remove_pages(PHYS_PFN(res->start),
 			       PHYS_PFN(resource_size(res)), NULL);
@@ -410,48 +413,42 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
+void free_devmap_managed_page(struct page *page)
 {
-	int count = page_ref_dec_return(page);
-
-	/*
-	 * If refcount is 1 then page is freed and refcount is stable as nobody
-	 * holds a reference on the page.
-	 */
-	if (count == 1) {
-		/* Clear Active bit in case of parallel mark_page_accessed */
-		__ClearPageActive(page);
-		__ClearPageWaiters(page);
+	/* notify page idle for dax */
+	if (!is_device_private_page(page)) {
+		wake_up_var(&page->_refcount);
+		return;
+	}
 
-		mem_cgroup_uncharge(page);
+	/* Clear Active bit in case of parallel mark_page_accessed */
+	__ClearPageActive(page);
+	__ClearPageWaiters(page);
 
-		/*
-		 * When a device_private page is freed, the page->mapping field
-		 * may still contain a (stale) mapping value. For example, the
-		 * lower bits of page->mapping may still identify the page as
-		 * an anonymous page. Ultimately, this entire field is just
-		 * stale and wrong, and it will cause errors if not cleared.
-		 * One example is:
-		 *
-		 *  migrate_vma_pages()
-		 *    migrate_vma_insert_page()
-		 *      page_add_new_anon_rmap()
-		 *        __page_set_anon_rmap()
-		 *          ...checks page->mapping, via PageAnon(page) call,
-		 *            and incorrectly concludes that the page is an
-		 *            anonymous page. Therefore, it incorrectly,
-		 *            silently fails to set up the new anon rmap.
-		 *
-		 * For other types of ZONE_DEVICE pages, migration is either
-		 * handled differently or not done at all, so there is no need
-		 * to clear page->mapping.
-		 */
-		if (is_device_private_page(page))
-			page->mapping = NULL;
+	mem_cgroup_uncharge(page);
 
-		page->pgmap->ops->page_free(page);
-	} else if (!count)
-		__put_page(page);
+	/*
+	 * When a device_private page is freed, the page->mapping field
+	 * may still contain a (stale) mapping value. For example, the
+	 * lower bits of page->mapping may still identify the page as an
+	 * anonymous page. Ultimately, this entire field is just stale
+	 * and wrong, and it will cause errors if not cleared.  One
+	 * example is:
+	 *
+	 *  migrate_vma_pages()
+	 *    migrate_vma_insert_page()
+	 *      page_add_new_anon_rmap()
+	 *        __page_set_anon_rmap()
+	 *          ...checks page->mapping, via PageAnon(page) call,
+	 *            and incorrectly concludes that the page is an
+	 *            anonymous page. Therefore, it incorrectly,
+	 *            silently fails to set up the new anon rmap.
+	 *
+	 * For other types of ZONE_DEVICE pages, migration is either
+	 * handled differently or not done at all, so there is no need
+	 * to clear page->mapping.
+	 */
+	page->mapping = NULL;
+	page->pgmap->ops->page_free(page);
 }
-EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/mm/migrate.c b/mm/migrate.c
index 86873b6f38a7..b1092876e537 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -48,6 +48,7 @@
 #include <linux/page_owner.h>
 #include <linux/sched/mm.h>
 #include <linux/ptrace.h>
+#include <linux/oom.h>
 
 #include <asm/tlbflush.h>
 
@@ -986,7 +987,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		}
 
 		/*
-		 * Anonymous and movable page->mapping will be cleard by
+		 * Anonymous and movable page->mapping will be cleared by
 		 * free_pages_prepare so don't reset it here for keeping
 		 * the type to work PageAnon, for example.
 		 */
@@ -1199,8 +1200,7 @@ out:
 		/*
 		 * A page that has been migrated has all references
 		 * removed and will be freed. A page that has not been
-		 * migrated will have kepts its references and be
-		 * restored.
+		 * migrated will have kept its references and be restored.
 		 */
 		list_del(&page->lru);
 
@@ -1627,8 +1627,19 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			start = i;
 		} else if (node != current_node) {
 			err = do_move_pages_to_node(mm, &pagelist, current_node);
-			if (err)
+			if (err) {
+				/*
+				 * Positive err means the number of failed
+				 * pages to migrate.  Since we are going to
+				 * abort and return the number of non-migrated
+				 * pages, so need to incude the rest of the
+				 * nr_pages that have not been attempted as
+				 * well.
+				 */
+				if (err > 0)
+					err += nr_pages - i - 1;
 				goto out;
+			}
 			err = store_status(status, start, current_node, i - start);
 			if (err)
 				goto out;
@@ -1659,8 +1670,11 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			goto out_flush;
 
 		err = do_move_pages_to_node(mm, &pagelist, current_node);
-		if (err)
+		if (err) {
+			if (err > 0)
+				err += nr_pages - i - 1;
 			goto out;
+		}
 		if (i > start) {
 			err = store_status(status, start, current_node, i - start);
 			if (err)
@@ -1674,9 +1688,16 @@ out_flush:
 
 	/* Make sure we do not overwrite the existing error */
 	err1 = do_move_pages_to_node(mm, &pagelist, current_node);
+	/*
+	 * Don't have to report non-attempted pages here since:
+	 *     - If the above loop is done gracefully all pages have been
+	 *       attempted.
+	 *     - If the above loop is aborted it means a fatal error
+	 *       happened, should return ret.
+	 */
 	if (!err1)
 		err1 = store_status(status, start, current_node, i - start);
-	if (!err)
+	if (err >= 0)
 		err = err1;
 out:
 	return err;
@@ -2130,12 +2151,13 @@ out_unlock:
 #ifdef CONFIG_DEVICE_PRIVATE
 static int migrate_vma_collect_hole(unsigned long start,
 				    unsigned long end,
+				    __always_unused int depth,
 				    struct mm_walk *walk)
 {
 	struct migrate_vma *migrate = walk->private;
 	unsigned long addr;
 
-	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
 		migrate->dst[migrate->npages] = 0;
 		migrate->npages++;
@@ -2152,7 +2174,7 @@ static int migrate_vma_collect_skip(unsigned long start,
 	struct migrate_vma *migrate = walk->private;
 	unsigned long addr;
 
-	for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) {
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		migrate->dst[migrate->npages] = 0;
 		migrate->src[migrate->npages++] = 0;
 	}
@@ -2174,7 +2196,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
 
 again:
 	if (pmd_none(*pmdp))
-		return migrate_vma_collect_hole(start, end, walk);
+		return migrate_vma_collect_hole(start, end, -1, walk);
 
 	if (pmd_trans_huge(*pmdp)) {
 		struct page *page;
@@ -2207,7 +2229,7 @@ again:
 				return migrate_vma_collect_skip(start, end,
 								walk);
 			if (pmd_none(*pmdp))
-				return migrate_vma_collect_hole(start, end,
+				return migrate_vma_collect_hole(start, end, -1,
 								walk);
 		}
 	}
@@ -2675,6 +2697,14 @@ int migrate_vma_setup(struct migrate_vma *args)
 }
 EXPORT_SYMBOL(migrate_vma_setup);
 
+/*
+ * This code closely matches the code in:
+ *   __handle_mm_fault()
+ *     handle_pte_fault()
+ *       do_anonymous_page()
+ * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
+ * private page.
+ */
 static void migrate_vma_insert_page(struct migrate_vma *migrate,
 				    unsigned long addr,
 				    struct page *page,
@@ -2755,30 +2785,24 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 
 	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
 
+	if (check_stable_address_space(mm))
+		goto unlock_abort;
+
 	if (pte_present(*ptep)) {
 		unsigned long pfn = pte_pfn(*ptep);
 
-		if (!is_zero_pfn(pfn)) {
-			pte_unmap_unlock(ptep, ptl);
-			mem_cgroup_cancel_charge(page, memcg, false);
-			goto abort;
-		}
+		if (!is_zero_pfn(pfn))
+			goto unlock_abort;
 		flush = true;
-	} else if (!pte_none(*ptep)) {
-		pte_unmap_unlock(ptep, ptl);
-		mem_cgroup_cancel_charge(page, memcg, false);
-		goto abort;
-	}
+	} else if (!pte_none(*ptep))
+		goto unlock_abort;
 
 	/*
-	 * Check for usefaultfd but do not deliver the fault. Instead,
+	 * Check for userfaultfd but do not deliver the fault. Instead,
 	 * just back off.
 	 */
-	if (userfaultfd_missing(vma)) {
-		pte_unmap_unlock(ptep, ptl);
-		mem_cgroup_cancel_charge(page, memcg, false);
-		goto abort;
-	}
+	if (userfaultfd_missing(vma))
+		goto unlock_abort;
 
 	inc_mm_counter(mm, MM_ANONPAGES);
 	page_add_new_anon_rmap(page, vma, addr, false);
@@ -2802,6 +2826,9 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	*src = MIGRATE_PFN_MIGRATE;
 	return;
 
+unlock_abort:
+	pte_unmap_unlock(ptep, ptl);
+	mem_cgroup_cancel_charge(page, memcg, false);
 abort:
 	*src &= ~MIGRATE_PFN_MIGRATE;
 }
@@ -2834,9 +2861,8 @@ void migrate_vma_pages(struct migrate_vma *migrate)
 		}
 
 		if (!page) {
-			if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) {
+			if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
 				continue;
-			}
 			if (!notified) {
 				notified = true;
 
diff --git a/mm/mincore.c b/mm/mincore.c
index 49b6fa2f6aa1..0e6dd9948f1a 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -112,6 +112,7 @@ static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
 }
 
 static int mincore_unmapped_range(unsigned long addr, unsigned long end,
+				   __always_unused int depth,
 				   struct mm_walk *walk)
 {
 	walk->private += __mincore_unmapped_range(addr, end,
diff --git a/mm/mmap.c b/mm/mmap.c
index bc788548c4e5..6756b8bb0033 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1270,26 +1270,22 @@ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_
  */
 struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
 {
-	struct anon_vma *anon_vma;
-	struct vm_area_struct *near;
-
-	near = vma->vm_next;
-	if (!near)
-		goto try_prev;
-
-	anon_vma = reusable_anon_vma(near, vma, near);
-	if (anon_vma)
-		return anon_vma;
-try_prev:
-	near = vma->vm_prev;
-	if (!near)
-		goto none;
-
-	anon_vma = reusable_anon_vma(near, near, vma);
-	if (anon_vma)
-		return anon_vma;
-none:
+	struct anon_vma *anon_vma = NULL;
+
+	/* Try next first. */
+	if (vma->vm_next) {
+		anon_vma = reusable_anon_vma(vma->vm_next, vma, vma->vm_next);
+		if (anon_vma)
+			return anon_vma;
+	}
+
+	/* Try prev next. */
+	if (vma->vm_prev)
+		anon_vma = reusable_anon_vma(vma->vm_prev, vma->vm_prev, vma);
+
 	/*
+	 * We might reach here with anon_vma == NULL if we can't find
+	 * any reusable anon_vma.
 	 * There's no absolute need to look only at touching neighbours:
 	 * we could search further afield for "compatible" anon_vmas.
 	 * But it would probably just be a waste of time searching,
@@ -1297,7 +1293,7 @@ none:
 	 * We're trying to allow mprotect remerging later on,
 	 * not trying to minimize memory used for anon_vmas.
 	 */
-	return NULL;
+	return anon_vma;
 }
 
 /*
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 7d70e5c78f97..a3538cb2bcbe 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -11,7 +11,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 
 static bool tlb_next_batch(struct mmu_gather *tlb)
 {
@@ -69,7 +69,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 
 	VM_BUG_ON(!tlb->end);
 
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	VM_WARN_ON(tlb->page_size != page_size);
 #endif
 
@@ -89,58 +89,108 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 	return false;
 }
 
-#endif /* HAVE_MMU_GATHER_NO_GATHER */
+#endif /* MMU_GATHER_NO_GATHER */
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
 
-/*
- * See the comment near struct mmu_table_batch.
- */
+static void __tlb_remove_table_free(struct mmu_table_batch *batch)
+{
+	int i;
+
+	for (i = 0; i < batch->nr; i++)
+		__tlb_remove_table(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
 
 /*
- * If we want tlb_remove_table() to imply TLB invalidates.
+ * Semi RCU freeing of the page directories.
+ *
+ * This is needed by some architectures to implement software pagetable walkers.
+ *
+ * gup_fast() and other software pagetable walkers do a lockless page-table
+ * walk and therefore needs some synchronization with the freeing of the page
+ * directories. The chosen means to accomplish that is by disabling IRQs over
+ * the walk.
+ *
+ * Architectures that use IPIs to flush TLBs will then automagically DTRT,
+ * since we unlink the page, flush TLBs, free the page. Since the disabling of
+ * IRQs delays the completion of the TLB flush we can never observe an already
+ * freed page.
+ *
+ * Architectures that do not have this (PPC) need to delay the freeing by some
+ * other means, this is that means.
+ *
+ * What we do is batch the freed directory pages (tables) and RCU free them.
+ * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
+ * holds off grace periods.
+ *
+ * However, in order to batch these pages we need to allocate storage, this
+ * allocation is deep inside the MM code and can thus easily fail on memory
+ * pressure. To guarantee progress we fall back to single table freeing, see
+ * the implementation of tlb_remove_table_one().
+ *
  */
-static inline void tlb_table_invalidate(struct mmu_gather *tlb)
-{
-#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
-	/*
-	 * Invalidate page-table caches used by hardware walkers. Then we still
-	 * need to RCU-sched wait while freeing the pages because software
-	 * walkers can still be in-flight.
-	 */
-	tlb_flush_mmu_tlbonly(tlb);
-#endif
-}
 
 static void tlb_remove_table_smp_sync(void *arg)
 {
 	/* Simply deliver the interrupt */
 }
 
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_sync_one(void)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
 	 * assumed to be actually RCU-freed.
 	 *
 	 * It is however sufficient for software page-table walkers that rely on
-	 * IRQ disabling. See the comment near struct mmu_table_batch.
+	 * IRQ disabling.
 	 */
 	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
 }
 
 static void tlb_remove_table_rcu(struct rcu_head *head)
 {
-	struct mmu_table_batch *batch;
-	int i;
+	__tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu));
+}
+
+static void tlb_remove_table_free(struct mmu_table_batch *batch)
+{
+	call_rcu(&batch->rcu, tlb_remove_table_rcu);
+}
 
-	batch = container_of(head, struct mmu_table_batch, rcu);
+#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
+static void tlb_remove_table_sync_one(void) { }
 
-	free_page((unsigned long)batch);
+static void tlb_remove_table_free(struct mmu_table_batch *batch)
+{
+	__tlb_remove_table_free(batch);
+}
+
+#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
+
+/*
+ * If we want tlb_remove_table() to imply TLB invalidates.
+ */
+static inline void tlb_table_invalidate(struct mmu_gather *tlb)
+{
+	if (tlb_needs_table_invalidate()) {
+		/*
+		 * Invalidate page-table caches used by hardware walkers. Then
+		 * we still need to RCU-sched wait while freeing the pages
+		 * because software walkers can still be in-flight.
+		 */
+		tlb_flush_mmu_tlbonly(tlb);
+	}
+}
+
+static void tlb_remove_table_one(void *table)
+{
+	tlb_remove_table_sync_one();
+	__tlb_remove_table(table);
 }
 
 static void tlb_table_flush(struct mmu_gather *tlb)
@@ -149,7 +199,7 @@ static void tlb_table_flush(struct mmu_gather *tlb)
 
 	if (*batch) {
 		tlb_table_invalidate(tlb);
-		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
+		tlb_remove_table_free(*batch);
 		*batch = NULL;
 	}
 }
@@ -173,14 +223,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 		tlb_table_flush(tlb);
 }
 
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+static inline void tlb_table_init(struct mmu_gather *tlb)
+{
+	tlb->batch = NULL;
+}
+
+#else /* !CONFIG_MMU_GATHER_TABLE_FREE */
+
+static inline void tlb_table_flush(struct mmu_gather *tlb) { }
+static inline void tlb_table_init(struct mmu_gather *tlb) { }
+
+#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
 
 static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
-#endif
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb_batch_pages_flush(tlb);
 #endif
 }
@@ -211,7 +269,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	/* Is it from 0 to ~0? */
 	tlb->fullmm     = !(start | (end+1));
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb->need_flush_all = 0;
 	tlb->local.next = NULL;
 	tlb->local.nr   = 0;
@@ -220,10 +278,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	tlb->batch_count = 0;
 #endif
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
-#endif
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	tlb_table_init(tlb);
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	tlb->page_size = 0;
 #endif
 
@@ -271,7 +327,7 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
 
 	tlb_flush_mmu(tlb);
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	tlb_batch_list_free(tlb);
 #endif
 	dec_tlb_flush_pending(tlb->mm);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index f76ea05b1cb0..ef3973a5d34a 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -29,12 +29,12 @@ struct lockdep_map __mmu_notifier_invalidate_range_start_map = {
 #endif
 
 /*
- * The mmu notifier_mm structure is allocated and installed in
- * mm->mmu_notifier_mm inside the mm_take_all_locks() protected
+ * The mmu_notifier_subscriptions structure is allocated and installed in
+ * mm->notifier_subscriptions inside the mm_take_all_locks() protected
  * critical section and it's released only when mm_count reaches zero
  * in mmdrop().
  */
-struct mmu_notifier_mm {
+struct mmu_notifier_subscriptions {
 	/* all mmu notifiers registered in this mm are queued in this list */
 	struct hlist_head list;
 	bool has_itree;
@@ -65,80 +65,81 @@ struct mmu_notifier_mm {
  *
  * The write side has two states, fully excluded:
  *  - mm->active_invalidate_ranges != 0
- *  - mnn->invalidate_seq & 1 == True (odd)
+ *  - subscriptions->invalidate_seq & 1 == True (odd)
  *  - some range on the mm_struct is being invalidated
  *  - the itree is not allowed to change
  *
  * And partially excluded:
  *  - mm->active_invalidate_ranges != 0
- *  - mnn->invalidate_seq & 1 == False (even)
+ *  - subscriptions->invalidate_seq & 1 == False (even)
  *  - some range on the mm_struct is being invalidated
  *  - the itree is allowed to change
  *
- * Operations on mmu_notifier_mm->invalidate_seq (under spinlock):
+ * Operations on notifier_subscriptions->invalidate_seq (under spinlock):
  *    seq |= 1  # Begin writing
  *    seq++     # Release the writing state
  *    seq & 1   # True if a writer exists
  *
  * The later state avoids some expensive work on inv_end in the common case of
- * no mni monitoring the VA.
+ * no mmu_interval_notifier monitoring the VA.
  */
-static bool mn_itree_is_invalidating(struct mmu_notifier_mm *mmn_mm)
+static bool
+mn_itree_is_invalidating(struct mmu_notifier_subscriptions *subscriptions)
 {
-	lockdep_assert_held(&mmn_mm->lock);
-	return mmn_mm->invalidate_seq & 1;
+	lockdep_assert_held(&subscriptions->lock);
+	return subscriptions->invalidate_seq & 1;
 }
 
 static struct mmu_interval_notifier *
-mn_itree_inv_start_range(struct mmu_notifier_mm *mmn_mm,
+mn_itree_inv_start_range(struct mmu_notifier_subscriptions *subscriptions,
 			 const struct mmu_notifier_range *range,
 			 unsigned long *seq)
 {
 	struct interval_tree_node *node;
 	struct mmu_interval_notifier *res = NULL;
 
-	spin_lock(&mmn_mm->lock);
-	mmn_mm->active_invalidate_ranges++;
-	node = interval_tree_iter_first(&mmn_mm->itree, range->start,
+	spin_lock(&subscriptions->lock);
+	subscriptions->active_invalidate_ranges++;
+	node = interval_tree_iter_first(&subscriptions->itree, range->start,
 					range->end - 1);
 	if (node) {
-		mmn_mm->invalidate_seq |= 1;
+		subscriptions->invalidate_seq |= 1;
 		res = container_of(node, struct mmu_interval_notifier,
 				   interval_tree);
 	}
 
-	*seq = mmn_mm->invalidate_seq;
-	spin_unlock(&mmn_mm->lock);
+	*seq = subscriptions->invalidate_seq;
+	spin_unlock(&subscriptions->lock);
 	return res;
 }
 
 static struct mmu_interval_notifier *
-mn_itree_inv_next(struct mmu_interval_notifier *mni,
+mn_itree_inv_next(struct mmu_interval_notifier *interval_sub,
 		  const struct mmu_notifier_range *range)
 {
 	struct interval_tree_node *node;
 
-	node = interval_tree_iter_next(&mni->interval_tree, range->start,
-				       range->end - 1);
+	node = interval_tree_iter_next(&interval_sub->interval_tree,
+				       range->start, range->end - 1);
 	if (!node)
 		return NULL;
 	return container_of(node, struct mmu_interval_notifier, interval_tree);
 }
 
-static void mn_itree_inv_end(struct mmu_notifier_mm *mmn_mm)
+static void mn_itree_inv_end(struct mmu_notifier_subscriptions *subscriptions)
 {
-	struct mmu_interval_notifier *mni;
+	struct mmu_interval_notifier *interval_sub;
 	struct hlist_node *next;
 
-	spin_lock(&mmn_mm->lock);
-	if (--mmn_mm->active_invalidate_ranges ||
-	    !mn_itree_is_invalidating(mmn_mm)) {
-		spin_unlock(&mmn_mm->lock);
+	spin_lock(&subscriptions->lock);
+	if (--subscriptions->active_invalidate_ranges ||
+	    !mn_itree_is_invalidating(subscriptions)) {
+		spin_unlock(&subscriptions->lock);
 		return;
 	}
 
 	/* Make invalidate_seq even */
-	mmn_mm->invalidate_seq++;
+	subscriptions->invalidate_seq++;
 
 	/*
 	 * The inv_end incorporates a deferred mechanism like rtnl_unlock().
@@ -146,30 +147,31 @@ static void mn_itree_inv_end(struct mmu_notifier_mm *mmn_mm)
 	 * they are progressed. This arrangement for tree updates is used to
 	 * avoid using a blocking lock during invalidate_range_start.
 	 */
-	hlist_for_each_entry_safe(mni, next, &mmn_mm->deferred_list,
+	hlist_for_each_entry_safe(interval_sub, next,
+				  &subscriptions->deferred_list,
 				  deferred_item) {
-		if (RB_EMPTY_NODE(&mni->interval_tree.rb))
-			interval_tree_insert(&mni->interval_tree,
-					     &mmn_mm->itree);
+		if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb))
+			interval_tree_insert(&interval_sub->interval_tree,
+					     &subscriptions->itree);
 		else
-			interval_tree_remove(&mni->interval_tree,
-					     &mmn_mm->itree);
-		hlist_del(&mni->deferred_item);
+			interval_tree_remove(&interval_sub->interval_tree,
+					     &subscriptions->itree);
+		hlist_del(&interval_sub->deferred_item);
 	}
-	spin_unlock(&mmn_mm->lock);
+	spin_unlock(&subscriptions->lock);
 
-	wake_up_all(&mmn_mm->wq);
+	wake_up_all(&subscriptions->wq);
 }
 
 /**
  * mmu_interval_read_begin - Begin a read side critical section against a VA
  *                           range
- * mni: The range to use
+ * interval_sub: The interval subscription
  *
  * mmu_iterval_read_begin()/mmu_iterval_read_retry() implement a
- * collision-retry scheme similar to seqcount for the VA range under mni. If
- * the mm invokes invalidation during the critical section then
- * mmu_interval_read_retry() will return true.
+ * collision-retry scheme similar to seqcount for the VA range under
+ * subscription. If the mm invokes invalidation during the critical section
+ * then mmu_interval_read_retry() will return true.
  *
  * This is useful to obtain shadow PTEs where teardown or setup of the SPTEs
  * require a blocking context.  The critical region formed by this can sleep,
@@ -180,68 +182,71 @@ static void mn_itree_inv_end(struct mmu_notifier_mm *mmn_mm)
  *
  * The return value should be passed to mmu_interval_read_retry().
  */
-unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni)
+unsigned long
+mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub)
 {
-	struct mmu_notifier_mm *mmn_mm = mni->mm->mmu_notifier_mm;
+	struct mmu_notifier_subscriptions *subscriptions =
+		interval_sub->mm->notifier_subscriptions;
 	unsigned long seq;
 	bool is_invalidating;
 
 	/*
-	 * If the mni has a different seq value under the user_lock than we
-	 * started with then it has collided.
+	 * If the subscription has a different seq value under the user_lock
+	 * than we started with then it has collided.
 	 *
-	 * If the mni currently has the same seq value as the mmn_mm seq, then
-	 * it is currently between invalidate_start/end and is colliding.
+	 * If the subscription currently has the same seq value as the
+	 * subscriptions seq, then it is currently between
+	 * invalidate_start/end and is colliding.
 	 *
 	 * The locking looks broadly like this:
 	 *   mn_tree_invalidate_start():          mmu_interval_read_begin():
 	 *                                         spin_lock
-	 *                                          seq = READ_ONCE(mni->invalidate_seq);
-	 *                                          seq == mmn_mm->invalidate_seq
+	 *                                          seq = READ_ONCE(interval_sub->invalidate_seq);
+	 *                                          seq == subs->invalidate_seq
 	 *                                         spin_unlock
 	 *    spin_lock
-	 *     seq = ++mmn_mm->invalidate_seq
+	 *     seq = ++subscriptions->invalidate_seq
 	 *    spin_unlock
 	 *     op->invalidate_range():
 	 *       user_lock
 	 *        mmu_interval_set_seq()
-	 *         mni->invalidate_seq = seq
+	 *         interval_sub->invalidate_seq = seq
 	 *       user_unlock
 	 *
 	 *                          [Required: mmu_interval_read_retry() == true]
 	 *
 	 *   mn_itree_inv_end():
 	 *    spin_lock
-	 *     seq = ++mmn_mm->invalidate_seq
+	 *     seq = ++subscriptions->invalidate_seq
 	 *    spin_unlock
 	 *
 	 *                                        user_lock
 	 *                                         mmu_interval_read_retry():
-	 *                                          mni->invalidate_seq != seq
+	 *                                          interval_sub->invalidate_seq != seq
 	 *                                        user_unlock
 	 *
 	 * Barriers are not needed here as any races here are closed by an
 	 * eventual mmu_interval_read_retry(), which provides a barrier via the
 	 * user_lock.
 	 */
-	spin_lock(&mmn_mm->lock);
+	spin_lock(&subscriptions->lock);
 	/* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */
-	seq = READ_ONCE(mni->invalidate_seq);
-	is_invalidating = seq == mmn_mm->invalidate_seq;
-	spin_unlock(&mmn_mm->lock);
+	seq = READ_ONCE(interval_sub->invalidate_seq);
+	is_invalidating = seq == subscriptions->invalidate_seq;
+	spin_unlock(&subscriptions->lock);
 
 	/*
-	 * mni->invalidate_seq must always be set to an odd value via
+	 * interval_sub->invalidate_seq must always be set to an odd value via
 	 * mmu_interval_set_seq() using the provided cur_seq from
 	 * mn_itree_inv_start_range(). This ensures that if seq does wrap we
 	 * will always clear the below sleep in some reasonable time as
-	 * mmn_mm->invalidate_seq is even in the idle state.
+	 * subscriptions->invalidate_seq is even in the idle state.
 	 */
 	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 	if (is_invalidating)
-		wait_event(mmn_mm->wq,
-			   READ_ONCE(mmn_mm->invalidate_seq) != seq);
+		wait_event(subscriptions->wq,
+			   READ_ONCE(subscriptions->invalidate_seq) != seq);
 
 	/*
 	 * Notice that mmu_interval_read_retry() can already be true at this
@@ -253,7 +258,7 @@ unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *mni)
 }
 EXPORT_SYMBOL_GPL(mmu_interval_read_begin);
 
-static void mn_itree_release(struct mmu_notifier_mm *mmn_mm,
+static void mn_itree_release(struct mmu_notifier_subscriptions *subscriptions,
 			     struct mm_struct *mm)
 {
 	struct mmu_notifier_range range = {
@@ -263,17 +268,20 @@ static void mn_itree_release(struct mmu_notifier_mm *mmn_mm,
 		.start = 0,
 		.end = ULONG_MAX,
 	};
-	struct mmu_interval_notifier *mni;
+	struct mmu_interval_notifier *interval_sub;
 	unsigned long cur_seq;
 	bool ret;
 
-	for (mni = mn_itree_inv_start_range(mmn_mm, &range, &cur_seq); mni;
-	     mni = mn_itree_inv_next(mni, &range)) {
-		ret = mni->ops->invalidate(mni, &range, cur_seq);
+	for (interval_sub =
+		     mn_itree_inv_start_range(subscriptions, &range, &cur_seq);
+	     interval_sub;
+	     interval_sub = mn_itree_inv_next(interval_sub, &range)) {
+		ret = interval_sub->ops->invalidate(interval_sub, &range,
+						    cur_seq);
 		WARN_ON(!ret);
 	}
 
-	mn_itree_inv_end(mmn_mm);
+	mn_itree_inv_end(subscriptions);
 }
 
 /*
@@ -283,15 +291,15 @@ static void mn_itree_release(struct mmu_notifier_mm *mmn_mm,
  * in parallel despite there being no task using this mm any more,
  * through the vmas outside of the exit_mmap context, such as with
  * vmtruncate. This serializes against mmu_notifier_unregister with
- * the mmu_notifier_mm->lock in addition to SRCU and it serializes
- * against the other mmu notifiers with SRCU. struct mmu_notifier_mm
+ * the notifier_subscriptions->lock in addition to SRCU and it serializes
+ * against the other mmu notifiers with SRCU. struct mmu_notifier_subscriptions
  * can't go away from under us as exit_mmap holds an mm_count pin
  * itself.
  */
-static void mn_hlist_release(struct mmu_notifier_mm *mmn_mm,
+static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions,
 			     struct mm_struct *mm)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int id;
 
 	/*
@@ -299,29 +307,29 @@ static void mn_hlist_release(struct mmu_notifier_mm *mmn_mm,
 	 * ->release returns.
 	 */
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist)
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist)
 		/*
 		 * If ->release runs before mmu_notifier_unregister it must be
 		 * handled, as it's the only way for the driver to flush all
 		 * existing sptes and stop the driver from establishing any more
 		 * sptes before all the pages in the mm are freed.
 		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
+		if (subscription->ops->release)
+			subscription->ops->release(subscription, mm);
 
-	spin_lock(&mmn_mm->lock);
-	while (unlikely(!hlist_empty(&mmn_mm->list))) {
-		mn = hlist_entry(mmn_mm->list.first, struct mmu_notifier,
-				 hlist);
+	spin_lock(&subscriptions->lock);
+	while (unlikely(!hlist_empty(&subscriptions->list))) {
+		subscription = hlist_entry(subscriptions->list.first,
+					   struct mmu_notifier, hlist);
 		/*
 		 * We arrived before mmu_notifier_unregister so
 		 * mmu_notifier_unregister will do nothing other than to wait
 		 * for ->release to finish and for mmu_notifier_unregister to
 		 * return.
 		 */
-		hlist_del_init_rcu(&mn->hlist);
+		hlist_del_init_rcu(&subscription->hlist);
 	}
-	spin_unlock(&mmn_mm->lock);
+	spin_unlock(&subscriptions->lock);
 	srcu_read_unlock(&srcu, id);
 
 	/*
@@ -330,21 +338,22 @@ static void mn_hlist_release(struct mmu_notifier_mm *mmn_mm,
 	 * until the ->release method returns, if it was invoked by
 	 * mmu_notifier_unregister.
 	 *
-	 * The mmu_notifier_mm can't go away from under us because one mm_count
-	 * is held by exit_mmap.
+	 * The notifier_subscriptions can't go away from under us because
+	 * one mm_count is held by exit_mmap.
 	 */
 	synchronize_srcu(&srcu);
 }
 
 void __mmu_notifier_release(struct mm_struct *mm)
 {
-	struct mmu_notifier_mm *mmn_mm = mm->mmu_notifier_mm;
+	struct mmu_notifier_subscriptions *subscriptions =
+		mm->notifier_subscriptions;
 
-	if (mmn_mm->has_itree)
-		mn_itree_release(mmn_mm, mm);
+	if (subscriptions->has_itree)
+		mn_itree_release(subscriptions, mm);
 
-	if (!hlist_empty(&mmn_mm->list))
-		mn_hlist_release(mmn_mm, mm);
+	if (!hlist_empty(&subscriptions->list))
+		mn_hlist_release(subscriptions, mm);
 }
 
 /*
@@ -356,13 +365,15 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long end)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int young = 0, id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops->clear_flush_young)
-			young |= mn->ops->clear_flush_young(mn, mm, start, end);
+	hlist_for_each_entry_rcu(subscription,
+				 &mm->notifier_subscriptions->list, hlist) {
+		if (subscription->ops->clear_flush_young)
+			young |= subscription->ops->clear_flush_young(
+				subscription, mm, start, end);
 	}
 	srcu_read_unlock(&srcu, id);
 
@@ -373,13 +384,15 @@ int __mmu_notifier_clear_young(struct mm_struct *mm,
 			       unsigned long start,
 			       unsigned long end)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int young = 0, id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops->clear_young)
-			young |= mn->ops->clear_young(mn, mm, start, end);
+	hlist_for_each_entry_rcu(subscription,
+				 &mm->notifier_subscriptions->list, hlist) {
+		if (subscription->ops->clear_young)
+			young |= subscription->ops->clear_young(subscription,
+								mm, start, end);
 	}
 	srcu_read_unlock(&srcu, id);
 
@@ -389,13 +402,15 @@ int __mmu_notifier_clear_young(struct mm_struct *mm,
 int __mmu_notifier_test_young(struct mm_struct *mm,
 			      unsigned long address)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int young = 0, id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops->test_young) {
-			young = mn->ops->test_young(mn, mm, address);
+	hlist_for_each_entry_rcu(subscription,
+				 &mm->notifier_subscriptions->list, hlist) {
+		if (subscription->ops->test_young) {
+			young = subscription->ops->test_young(subscription, mm,
+							      address);
 			if (young)
 				break;
 		}
@@ -408,28 +423,33 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 			       pte_t pte)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops->change_pte)
-			mn->ops->change_pte(mn, mm, address, pte);
+	hlist_for_each_entry_rcu(subscription,
+				 &mm->notifier_subscriptions->list, hlist) {
+		if (subscription->ops->change_pte)
+			subscription->ops->change_pte(subscription, mm, address,
+						      pte);
 	}
 	srcu_read_unlock(&srcu, id);
 }
 
-static int mn_itree_invalidate(struct mmu_notifier_mm *mmn_mm,
+static int mn_itree_invalidate(struct mmu_notifier_subscriptions *subscriptions,
 			       const struct mmu_notifier_range *range)
 {
-	struct mmu_interval_notifier *mni;
+	struct mmu_interval_notifier *interval_sub;
 	unsigned long cur_seq;
 
-	for (mni = mn_itree_inv_start_range(mmn_mm, range, &cur_seq); mni;
-	     mni = mn_itree_inv_next(mni, range)) {
+	for (interval_sub =
+		     mn_itree_inv_start_range(subscriptions, range, &cur_seq);
+	     interval_sub;
+	     interval_sub = mn_itree_inv_next(interval_sub, range)) {
 		bool ret;
 
-		ret = mni->ops->invalidate(mni, range, cur_seq);
+		ret = interval_sub->ops->invalidate(interval_sub, range,
+						    cur_seq);
 		if (!ret) {
 			if (WARN_ON(mmu_notifier_range_blockable(range)))
 				continue;
@@ -443,31 +463,36 @@ out_would_block:
 	 * On -EAGAIN the non-blocking caller is not allowed to call
 	 * invalidate_range_end()
 	 */
-	mn_itree_inv_end(mmn_mm);
+	mn_itree_inv_end(subscriptions);
 	return -EAGAIN;
 }
 
-static int mn_hlist_invalidate_range_start(struct mmu_notifier_mm *mmn_mm,
-					   struct mmu_notifier_range *range)
+static int mn_hlist_invalidate_range_start(
+	struct mmu_notifier_subscriptions *subscriptions,
+	struct mmu_notifier_range *range)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int ret = 0;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) {
-		if (mn->ops->invalidate_range_start) {
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) {
+		const struct mmu_notifier_ops *ops = subscription->ops;
+
+		if (ops->invalidate_range_start) {
 			int _ret;
 
 			if (!mmu_notifier_range_blockable(range))
 				non_block_start();
-			_ret = mn->ops->invalidate_range_start(mn, range);
+			_ret = ops->invalidate_range_start(subscription, range);
 			if (!mmu_notifier_range_blockable(range))
 				non_block_end();
 			if (_ret) {
 				pr_info("%pS callback failed with %d in %sblockable context.\n",
-					mn->ops->invalidate_range_start, _ret,
-					!mmu_notifier_range_blockable(range) ? "non-" : "");
+					ops->invalidate_range_start, _ret,
+					!mmu_notifier_range_blockable(range) ?
+						"non-" :
+						"");
 				WARN_ON(mmu_notifier_range_blockable(range) ||
 					_ret != -EAGAIN);
 				ret = _ret;
@@ -481,28 +506,29 @@ static int mn_hlist_invalidate_range_start(struct mmu_notifier_mm *mmn_mm,
 
 int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 {
-	struct mmu_notifier_mm *mmn_mm = range->mm->mmu_notifier_mm;
+	struct mmu_notifier_subscriptions *subscriptions =
+		range->mm->notifier_subscriptions;
 	int ret;
 
-	if (mmn_mm->has_itree) {
-		ret = mn_itree_invalidate(mmn_mm, range);
+	if (subscriptions->has_itree) {
+		ret = mn_itree_invalidate(subscriptions, range);
 		if (ret)
 			return ret;
 	}
-	if (!hlist_empty(&mmn_mm->list))
-		return mn_hlist_invalidate_range_start(mmn_mm, range);
+	if (!hlist_empty(&subscriptions->list))
+		return mn_hlist_invalidate_range_start(subscriptions, range);
 	return 0;
 }
 
-static void mn_hlist_invalidate_end(struct mmu_notifier_mm *mmn_mm,
-				    struct mmu_notifier_range *range,
-				    bool only_end)
+static void
+mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions,
+			struct mmu_notifier_range *range, bool only_end)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mmn_mm->list, hlist) {
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) {
 		/*
 		 * Call invalidate_range here too to avoid the need for the
 		 * subsystem of having to register an invalidate_range_end
@@ -516,14 +542,16 @@ static void mn_hlist_invalidate_end(struct mmu_notifier_mm *mmn_mm,
 		 * is safe to do when we know that a call to invalidate_range()
 		 * already happen under page table lock.
 		 */
-		if (!only_end && mn->ops->invalidate_range)
-			mn->ops->invalidate_range(mn, range->mm,
-						  range->start,
-						  range->end);
-		if (mn->ops->invalidate_range_end) {
+		if (!only_end && subscription->ops->invalidate_range)
+			subscription->ops->invalidate_range(subscription,
+							    range->mm,
+							    range->start,
+							    range->end);
+		if (subscription->ops->invalidate_range_end) {
 			if (!mmu_notifier_range_blockable(range))
 				non_block_start();
-			mn->ops->invalidate_range_end(mn, range);
+			subscription->ops->invalidate_range_end(subscription,
+								range);
 			if (!mmu_notifier_range_blockable(range))
 				non_block_end();
 		}
@@ -534,27 +562,30 @@ static void mn_hlist_invalidate_end(struct mmu_notifier_mm *mmn_mm,
 void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range,
 					 bool only_end)
 {
-	struct mmu_notifier_mm *mmn_mm = range->mm->mmu_notifier_mm;
+	struct mmu_notifier_subscriptions *subscriptions =
+		range->mm->notifier_subscriptions;
 
 	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
-	if (mmn_mm->has_itree)
-		mn_itree_inv_end(mmn_mm);
+	if (subscriptions->has_itree)
+		mn_itree_inv_end(subscriptions);
 
-	if (!hlist_empty(&mmn_mm->list))
-		mn_hlist_invalidate_end(mmn_mm, range, only_end);
+	if (!hlist_empty(&subscriptions->list))
+		mn_hlist_invalidate_end(subscriptions, range, only_end);
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 }
 
 void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops->invalidate_range)
-			mn->ops->invalidate_range(mn, mm, start, end);
+	hlist_for_each_entry_rcu(subscription,
+				 &mm->notifier_subscriptions->list, hlist) {
+		if (subscription->ops->invalidate_range)
+			subscription->ops->invalidate_range(subscription, mm,
+							    start, end);
 	}
 	srcu_read_unlock(&srcu, id);
 }
@@ -564,9 +595,10 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm,
  * write mode. A NULL mn signals the notifier is being registered for itree
  * mode.
  */
-int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+int __mmu_notifier_register(struct mmu_notifier *subscription,
+			    struct mm_struct *mm)
 {
-	struct mmu_notifier_mm *mmu_notifier_mm = NULL;
+	struct mmu_notifier_subscriptions *subscriptions = NULL;
 	int ret;
 
 	lockdep_assert_held_write(&mm->mmap_sem);
@@ -579,23 +611,23 @@ int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
 		fs_reclaim_release(GFP_KERNEL);
 	}
 
-	if (!mm->mmu_notifier_mm) {
+	if (!mm->notifier_subscriptions) {
 		/*
 		 * kmalloc cannot be called under mm_take_all_locks(), but we
-		 * know that mm->mmu_notifier_mm can't change while we hold
-		 * the write side of the mmap_sem.
+		 * know that mm->notifier_subscriptions can't change while we
+		 * hold the write side of the mmap_sem.
 		 */
-		mmu_notifier_mm =
-			kzalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
-		if (!mmu_notifier_mm)
+		subscriptions = kzalloc(
+			sizeof(struct mmu_notifier_subscriptions), GFP_KERNEL);
+		if (!subscriptions)
 			return -ENOMEM;
 
-		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
-		spin_lock_init(&mmu_notifier_mm->lock);
-		mmu_notifier_mm->invalidate_seq = 2;
-		mmu_notifier_mm->itree = RB_ROOT_CACHED;
-		init_waitqueue_head(&mmu_notifier_mm->wq);
-		INIT_HLIST_HEAD(&mmu_notifier_mm->deferred_list);
+		INIT_HLIST_HEAD(&subscriptions->list);
+		spin_lock_init(&subscriptions->lock);
+		subscriptions->invalidate_seq = 2;
+		subscriptions->itree = RB_ROOT_CACHED;
+		init_waitqueue_head(&subscriptions->wq);
+		INIT_HLIST_HEAD(&subscriptions->deferred_list);
 	}
 
 	ret = mm_take_all_locks(mm);
@@ -610,34 +642,36 @@ int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * We can't race against any other mmu notifier method either
 	 * thanks to mm_take_all_locks().
 	 *
-	 * release semantics on the initialization of the mmu_notifier_mm's
-	 * contents are provided for unlocked readers.  acquire can only be
-	 * used while holding the mmgrab or mmget, and is safe because once
-	 * created the mmu_notififer_mm is not freed until the mm is
-	 * destroyed.  As above, users holding the mmap_sem or one of the
+	 * release semantics on the initialization of the
+	 * mmu_notifier_subscriptions's contents are provided for unlocked
+	 * readers.  acquire can only be used while holding the mmgrab or
+	 * mmget, and is safe because once created the
+	 * mmu_notifier_subscriptions is not freed until the mm is destroyed.
+	 * As above, users holding the mmap_sem or one of the
 	 * mm_take_all_locks() do not need to use acquire semantics.
 	 */
-	if (mmu_notifier_mm)
-		smp_store_release(&mm->mmu_notifier_mm, mmu_notifier_mm);
+	if (subscriptions)
+		smp_store_release(&mm->notifier_subscriptions, subscriptions);
 
-	if (mn) {
+	if (subscription) {
 		/* Pairs with the mmdrop in mmu_notifier_unregister_* */
 		mmgrab(mm);
-		mn->mm = mm;
-		mn->users = 1;
+		subscription->mm = mm;
+		subscription->users = 1;
 
-		spin_lock(&mm->mmu_notifier_mm->lock);
-		hlist_add_head_rcu(&mn->hlist, &mm->mmu_notifier_mm->list);
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+		spin_lock(&mm->notifier_subscriptions->lock);
+		hlist_add_head_rcu(&subscription->hlist,
+				   &mm->notifier_subscriptions->list);
+		spin_unlock(&mm->notifier_subscriptions->lock);
 	} else
-		mm->mmu_notifier_mm->has_itree = true;
+		mm->notifier_subscriptions->has_itree = true;
 
 	mm_drop_all_locks(mm);
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 	return 0;
 
 out_clean:
-	kfree(mmu_notifier_mm);
+	kfree(subscriptions);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__mmu_notifier_register);
@@ -658,15 +692,16 @@ EXPORT_SYMBOL_GPL(__mmu_notifier_register);
  * mmu_notifier_unregister() or mmu_notifier_put() must be always called to
  * unregister the notifier.
  *
- * While the caller has a mmu_notifier get the mn->mm pointer will remain
+ * While the caller has a mmu_notifier get the subscription->mm pointer will remain
  * valid, and can be converted to an active mm pointer via mmget_not_zero().
  */
-int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm)
+int mmu_notifier_register(struct mmu_notifier *subscription,
+			  struct mm_struct *mm)
 {
 	int ret;
 
 	down_write(&mm->mmap_sem);
-	ret = __mmu_notifier_register(mn, mm);
+	ret = __mmu_notifier_register(subscription, mm);
 	up_write(&mm->mmap_sem);
 	return ret;
 }
@@ -675,21 +710,22 @@ EXPORT_SYMBOL_GPL(mmu_notifier_register);
 static struct mmu_notifier *
 find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
-	hlist_for_each_entry_rcu (mn, &mm->mmu_notifier_mm->list, hlist) {
-		if (mn->ops != ops)
+	spin_lock(&mm->notifier_subscriptions->lock);
+	hlist_for_each_entry_rcu(subscription,
+				 &mm->notifier_subscriptions->list, hlist) {
+		if (subscription->ops != ops)
 			continue;
 
-		if (likely(mn->users != UINT_MAX))
-			mn->users++;
+		if (likely(subscription->users != UINT_MAX))
+			subscription->users++;
 		else
-			mn = ERR_PTR(-EOVERFLOW);
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		return mn;
+			subscription = ERR_PTR(-EOVERFLOW);
+		spin_unlock(&mm->notifier_subscriptions->lock);
+		return subscription;
 	}
-	spin_unlock(&mm->mmu_notifier_mm->lock);
+	spin_unlock(&mm->notifier_subscriptions->lock);
 	return NULL;
 }
 
@@ -713,37 +749,37 @@ find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops)
 struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops,
 					     struct mm_struct *mm)
 {
-	struct mmu_notifier *mn;
+	struct mmu_notifier *subscription;
 	int ret;
 
 	lockdep_assert_held_write(&mm->mmap_sem);
 
-	if (mm->mmu_notifier_mm) {
-		mn = find_get_mmu_notifier(mm, ops);
-		if (mn)
-			return mn;
+	if (mm->notifier_subscriptions) {
+		subscription = find_get_mmu_notifier(mm, ops);
+		if (subscription)
+			return subscription;
 	}
 
-	mn = ops->alloc_notifier(mm);
-	if (IS_ERR(mn))
-		return mn;
-	mn->ops = ops;
-	ret = __mmu_notifier_register(mn, mm);
+	subscription = ops->alloc_notifier(mm);
+	if (IS_ERR(subscription))
+		return subscription;
+	subscription->ops = ops;
+	ret = __mmu_notifier_register(subscription, mm);
 	if (ret)
 		goto out_free;
-	return mn;
+	return subscription;
 out_free:
-	mn->ops->free_notifier(mn);
+	subscription->ops->free_notifier(subscription);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(mmu_notifier_get_locked);
 
 /* this is called after the last mmu_notifier_unregister() returned */
-void __mmu_notifier_mm_destroy(struct mm_struct *mm)
+void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 {
-	BUG_ON(!hlist_empty(&mm->mmu_notifier_mm->list));
-	kfree(mm->mmu_notifier_mm);
-	mm->mmu_notifier_mm = LIST_POISON1; /* debug */
+	BUG_ON(!hlist_empty(&mm->notifier_subscriptions->list));
+	kfree(mm->notifier_subscriptions);
+	mm->notifier_subscriptions = LIST_POISON1; /* debug */
 }
 
 /*
@@ -756,11 +792,12 @@ void __mmu_notifier_mm_destroy(struct mm_struct *mm)
  * and only after mmu_notifier_unregister returned we're guaranteed
  * that ->release or any other method can't run anymore.
  */
-void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
+void mmu_notifier_unregister(struct mmu_notifier *subscription,
+			     struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	if (!hlist_unhashed(&mn->hlist)) {
+	if (!hlist_unhashed(&subscription->hlist)) {
 		/*
 		 * SRCU here will force exit_mmap to wait for ->release to
 		 * finish before freeing the pages.
@@ -772,17 +809,17 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 		 * exit_mmap will block in mmu_notifier_release to guarantee
 		 * that ->release is called before freeing the pages.
 		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
+		if (subscription->ops->release)
+			subscription->ops->release(subscription, mm);
 		srcu_read_unlock(&srcu, id);
 
-		spin_lock(&mm->mmu_notifier_mm->lock);
+		spin_lock(&mm->notifier_subscriptions->lock);
 		/*
 		 * Can not use list_del_rcu() since __mmu_notifier_release
 		 * can delete it before we hold the lock.
 		 */
-		hlist_del_init_rcu(&mn->hlist);
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+		hlist_del_init_rcu(&subscription->hlist);
+		spin_unlock(&mm->notifier_subscriptions->lock);
 	}
 
 	/*
@@ -799,10 +836,11 @@ EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
 
 static void mmu_notifier_free_rcu(struct rcu_head *rcu)
 {
-	struct mmu_notifier *mn = container_of(rcu, struct mmu_notifier, rcu);
-	struct mm_struct *mm = mn->mm;
+	struct mmu_notifier *subscription =
+		container_of(rcu, struct mmu_notifier, rcu);
+	struct mm_struct *mm = subscription->mm;
 
-	mn->ops->free_notifier(mn);
+	subscription->ops->free_notifier(subscription);
 	/* Pairs with the get in __mmu_notifier_register() */
 	mmdrop(mm);
 }
@@ -829,39 +867,40 @@ static void mmu_notifier_free_rcu(struct rcu_head *rcu)
  * Modules calling this function must call mmu_notifier_synchronize() in
  * their __exit functions to ensure the async work is completed.
  */
-void mmu_notifier_put(struct mmu_notifier *mn)
+void mmu_notifier_put(struct mmu_notifier *subscription)
 {
-	struct mm_struct *mm = mn->mm;
+	struct mm_struct *mm = subscription->mm;
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
-	if (WARN_ON(!mn->users) || --mn->users)
+	spin_lock(&mm->notifier_subscriptions->lock);
+	if (WARN_ON(!subscription->users) || --subscription->users)
 		goto out_unlock;
-	hlist_del_init_rcu(&mn->hlist);
-	spin_unlock(&mm->mmu_notifier_mm->lock);
+	hlist_del_init_rcu(&subscription->hlist);
+	spin_unlock(&mm->notifier_subscriptions->lock);
 
-	call_srcu(&srcu, &mn->rcu, mmu_notifier_free_rcu);
+	call_srcu(&srcu, &subscription->rcu, mmu_notifier_free_rcu);
 	return;
 
 out_unlock:
-	spin_unlock(&mm->mmu_notifier_mm->lock);
+	spin_unlock(&mm->notifier_subscriptions->lock);
 }
 EXPORT_SYMBOL_GPL(mmu_notifier_put);
 
 static int __mmu_interval_notifier_insert(
-	struct mmu_interval_notifier *mni, struct mm_struct *mm,
-	struct mmu_notifier_mm *mmn_mm, unsigned long start,
+	struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
+	struct mmu_notifier_subscriptions *subscriptions, unsigned long start,
 	unsigned long length, const struct mmu_interval_notifier_ops *ops)
 {
-	mni->mm = mm;
-	mni->ops = ops;
-	RB_CLEAR_NODE(&mni->interval_tree.rb);
-	mni->interval_tree.start = start;
+	interval_sub->mm = mm;
+	interval_sub->ops = ops;
+	RB_CLEAR_NODE(&interval_sub->interval_tree.rb);
+	interval_sub->interval_tree.start = start;
 	/*
 	 * Note that the representation of the intervals in the interval tree
 	 * considers the ending point as contained in the interval.
 	 */
 	if (length == 0 ||
-	    check_add_overflow(start, length - 1, &mni->interval_tree.last))
+	    check_add_overflow(start, length - 1,
+			       &interval_sub->interval_tree.last))
 		return -EOVERFLOW;
 
 	/* Must call with a mmget() held */
@@ -881,38 +920,40 @@ static int __mmu_interval_notifier_insert(
 	 * possibility for live lock, instead defer the add to
 	 * mn_itree_inv_end() so this algorithm is deterministic.
 	 *
-	 * In all cases the value for the mni->invalidate_seq should be
+	 * In all cases the value for the interval_sub->invalidate_seq should be
 	 * odd, see mmu_interval_read_begin()
 	 */
-	spin_lock(&mmn_mm->lock);
-	if (mmn_mm->active_invalidate_ranges) {
-		if (mn_itree_is_invalidating(mmn_mm))
-			hlist_add_head(&mni->deferred_item,
-				       &mmn_mm->deferred_list);
+	spin_lock(&subscriptions->lock);
+	if (subscriptions->active_invalidate_ranges) {
+		if (mn_itree_is_invalidating(subscriptions))
+			hlist_add_head(&interval_sub->deferred_item,
+				       &subscriptions->deferred_list);
 		else {
-			mmn_mm->invalidate_seq |= 1;
-			interval_tree_insert(&mni->interval_tree,
-					     &mmn_mm->itree);
+			subscriptions->invalidate_seq |= 1;
+			interval_tree_insert(&interval_sub->interval_tree,
+					     &subscriptions->itree);
 		}
-		mni->invalidate_seq = mmn_mm->invalidate_seq;
+		interval_sub->invalidate_seq = subscriptions->invalidate_seq;
 	} else {
-		WARN_ON(mn_itree_is_invalidating(mmn_mm));
+		WARN_ON(mn_itree_is_invalidating(subscriptions));
 		/*
-		 * The starting seq for a mni not under invalidation should be
-		 * odd, not equal to the current invalidate_seq and
+		 * The starting seq for a subscription not under invalidation
+		 * should be odd, not equal to the current invalidate_seq and
 		 * invalidate_seq should not 'wrap' to the new seq any time
 		 * soon.
 		 */
-		mni->invalidate_seq = mmn_mm->invalidate_seq - 1;
-		interval_tree_insert(&mni->interval_tree, &mmn_mm->itree);
+		interval_sub->invalidate_seq =
+			subscriptions->invalidate_seq - 1;
+		interval_tree_insert(&interval_sub->interval_tree,
+				     &subscriptions->itree);
 	}
-	spin_unlock(&mmn_mm->lock);
+	spin_unlock(&subscriptions->lock);
 	return 0;
 }
 
 /**
  * mmu_interval_notifier_insert - Insert an interval notifier
- * @mni: Interval notifier to register
+ * @interval_sub: Interval subscription to register
  * @start: Starting virtual address to monitor
  * @length: Length of the range to monitor
  * @mm : mm_struct to attach to
@@ -925,53 +966,53 @@ static int __mmu_interval_notifier_insert(
  * The caller must use the normal interval notifier read flow via
  * mmu_interval_read_begin() to establish SPTEs for this range.
  */
-int mmu_interval_notifier_insert(struct mmu_interval_notifier *mni,
+int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub,
 				 struct mm_struct *mm, unsigned long start,
 				 unsigned long length,
 				 const struct mmu_interval_notifier_ops *ops)
 {
-	struct mmu_notifier_mm *mmn_mm;
+	struct mmu_notifier_subscriptions *subscriptions;
 	int ret;
 
 	might_lock(&mm->mmap_sem);
 
-	mmn_mm = smp_load_acquire(&mm->mmu_notifier_mm);
-	if (!mmn_mm || !mmn_mm->has_itree) {
+	subscriptions = smp_load_acquire(&mm->notifier_subscriptions);
+	if (!subscriptions || !subscriptions->has_itree) {
 		ret = mmu_notifier_register(NULL, mm);
 		if (ret)
 			return ret;
-		mmn_mm = mm->mmu_notifier_mm;
+		subscriptions = mm->notifier_subscriptions;
 	}
-	return __mmu_interval_notifier_insert(mni, mm, mmn_mm, start, length,
-					      ops);
+	return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions,
+					      start, length, ops);
 }
 EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert);
 
 int mmu_interval_notifier_insert_locked(
-	struct mmu_interval_notifier *mni, struct mm_struct *mm,
+	struct mmu_interval_notifier *interval_sub, struct mm_struct *mm,
 	unsigned long start, unsigned long length,
 	const struct mmu_interval_notifier_ops *ops)
 {
-	struct mmu_notifier_mm *mmn_mm;
+	struct mmu_notifier_subscriptions *subscriptions =
+		mm->notifier_subscriptions;
 	int ret;
 
 	lockdep_assert_held_write(&mm->mmap_sem);
 
-	mmn_mm = mm->mmu_notifier_mm;
-	if (!mmn_mm || !mmn_mm->has_itree) {
+	if (!subscriptions || !subscriptions->has_itree) {
 		ret = __mmu_notifier_register(NULL, mm);
 		if (ret)
 			return ret;
-		mmn_mm = mm->mmu_notifier_mm;
+		subscriptions = mm->notifier_subscriptions;
 	}
-	return __mmu_interval_notifier_insert(mni, mm, mmn_mm, start, length,
-					      ops);
+	return __mmu_interval_notifier_insert(interval_sub, mm, subscriptions,
+					      start, length, ops);
 }
 EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked);
 
 /**
  * mmu_interval_notifier_remove - Remove a interval notifier
- * @mni: Interval notifier to unregister
+ * @interval_sub: Interval subscription to unregister
  *
  * This function must be paired with mmu_interval_notifier_insert(). It cannot
  * be called from any ops callback.
@@ -979,32 +1020,34 @@ EXPORT_SYMBOL_GPL(mmu_interval_notifier_insert_locked);
  * Once this returns ops callbacks are no longer running on other CPUs and
  * will not be called in future.
  */
-void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni)
+void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub)
 {
-	struct mm_struct *mm = mni->mm;
-	struct mmu_notifier_mm *mmn_mm = mm->mmu_notifier_mm;
+	struct mm_struct *mm = interval_sub->mm;
+	struct mmu_notifier_subscriptions *subscriptions =
+		mm->notifier_subscriptions;
 	unsigned long seq = 0;
 
 	might_sleep();
 
-	spin_lock(&mmn_mm->lock);
-	if (mn_itree_is_invalidating(mmn_mm)) {
+	spin_lock(&subscriptions->lock);
+	if (mn_itree_is_invalidating(subscriptions)) {
 		/*
 		 * remove is being called after insert put this on the
 		 * deferred list, but before the deferred list was processed.
 		 */
-		if (RB_EMPTY_NODE(&mni->interval_tree.rb)) {
-			hlist_del(&mni->deferred_item);
+		if (RB_EMPTY_NODE(&interval_sub->interval_tree.rb)) {
+			hlist_del(&interval_sub->deferred_item);
 		} else {
-			hlist_add_head(&mni->deferred_item,
-				       &mmn_mm->deferred_list);
-			seq = mmn_mm->invalidate_seq;
+			hlist_add_head(&interval_sub->deferred_item,
+				       &subscriptions->deferred_list);
+			seq = subscriptions->invalidate_seq;
 		}
 	} else {
-		WARN_ON(RB_EMPTY_NODE(&mni->interval_tree.rb));
-		interval_tree_remove(&mni->interval_tree, &mmn_mm->itree);
+		WARN_ON(RB_EMPTY_NODE(&interval_sub->interval_tree.rb));
+		interval_tree_remove(&interval_sub->interval_tree,
+				     &subscriptions->itree);
 	}
-	spin_unlock(&mmn_mm->lock);
+	spin_unlock(&subscriptions->lock);
 
 	/*
 	 * The possible sleep on progress in the invalidation requires the
@@ -1013,8 +1056,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *mni)
 	lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 	if (seq)
-		wait_event(mmn_mm->wq,
-			   READ_ONCE(mmn_mm->invalidate_seq) != seq);
+		wait_event(subscriptions->wq,
+			   READ_ONCE(subscriptions->invalidate_seq) != seq);
 
 	/* pairs with mmgrab in mmu_interval_notifier_insert() */
 	mmdrop(mm);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d58c481b3df8..dfc357614e56 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -26,6 +26,7 @@
 #include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/task.h>
+#include <linux/sched/debug.h>
 #include <linux/swap.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
@@ -620,6 +621,7 @@ static void oom_reap_task(struct task_struct *tsk)
 
 	pr_info("oom_reaper: unable to reap pid:%d (%s)\n",
 		task_pid_nr(tsk), tsk->comm);
+	sched_show_task(tsk);
 	debug_show_all_locks();
 
 done:
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d047bf7d8fd4..3c4eb750a199 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5848,6 +5848,23 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn)
 	return false;
 }
 
+#ifdef CONFIG_SPARSEMEM
+/* Skip PFNs that belong to non-present sections */
+static inline __meminit unsigned long next_pfn(unsigned long pfn)
+{
+	const unsigned long section_nr = pfn_to_section_nr(++pfn);
+
+	if (present_section_nr(section_nr))
+		return pfn;
+	return section_nr_to_pfn(next_present_section_nr(section_nr));
+}
+#else
+static inline __meminit unsigned long next_pfn(unsigned long pfn)
+{
+	return pfn++;
+}
+#endif
+
 /*
  * Initially all pages are reserved - free ones are freed
  * up by memblock_free_all() once the early boot process is
@@ -5881,16 +5898,20 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	}
 #endif
 
-	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+	for (pfn = start_pfn; pfn < end_pfn; ) {
 		/*
 		 * There can be holes in boot-time mem_map[]s handed to this
 		 * function.  They do not exist on hotplugged memory.
 		 */
 		if (context == MEMMAP_EARLY) {
-			if (!early_pfn_valid(pfn))
+			if (!early_pfn_valid(pfn)) {
+				pfn = next_pfn(pfn);
 				continue;
-			if (!early_pfn_in_nid(pfn, nid))
+			}
+			if (!early_pfn_in_nid(pfn, nid)) {
+				pfn++;
 				continue;
+			}
 			if (overlap_memmap_init(zone, &pfn))
 				continue;
 			if (defer_init(nid, pfn, end_pfn))
@@ -5918,16 +5939,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 			cond_resched();
 		}
+		pfn++;
 	}
 }
 
 #ifdef CONFIG_ZONE_DEVICE
 void __ref memmap_init_zone_device(struct zone *zone,
 				   unsigned long start_pfn,
-				   unsigned long size,
+				   unsigned long nr_pages,
 				   struct dev_pagemap *pgmap)
 {
-	unsigned long pfn, end_pfn = start_pfn + size;
+	unsigned long pfn, end_pfn = start_pfn + nr_pages;
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	struct vmem_altmap *altmap = pgmap_altmap(pgmap);
 	unsigned long zone_idx = zone_idx(zone);
@@ -5944,7 +5966,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	 */
 	if (altmap) {
 		start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
-		size = end_pfn - start_pfn;
+		nr_pages = end_pfn - start_pfn;
 	}
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
@@ -5991,7 +6013,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
 	}
 
 	pr_info("%s initialised %lu pages in %ums\n", __func__,
-		size, jiffies_to_msecs(jiffies - start));
+		nr_pages, jiffies_to_msecs(jiffies - start));
 }
 
 #endif
@@ -6890,10 +6912,10 @@ void __init free_area_init_node(int nid, unsigned long *zones_size,
 
 #if !defined(CONFIG_FLAT_NODE_MEM_MAP)
 /*
- * Zero all valid struct pages in range [spfn, epfn), return number of struct
- * pages zeroed
+ * Initialize all valid struct pages in the range [spfn, epfn) and mark them
+ * PageReserved(). Return the number of struct pages that were initialized.
  */
-static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
+static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
 {
 	unsigned long pfn;
 	u64 pgcnt = 0;
@@ -6904,7 +6926,13 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
 				+ pageblock_nr_pages - 1;
 			continue;
 		}
-		mm_zero_struct_page(pfn_to_page(pfn));
+		/*
+		 * Use a fake node/zone (0) for now. Some of these pages
+		 * (in memblock.reserved but not in memblock.memory) will
+		 * get re-initialized via reserve_bootmem_region() later.
+		 */
+		__init_single_page(pfn_to_page(pfn), pfn, 0, 0);
+		__SetPageReserved(pfn_to_page(pfn));
 		pgcnt++;
 	}
 
@@ -6916,14 +6944,15 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
  * initialized by going through __init_single_page(). But, there are some
  * struct pages which are reserved in memblock allocator and their fields
  * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly zero those struct pages.
+ * flags). We must explicitly initialize those struct pages.
  *
  * This function also addresses a similar issue where struct pages are left
  * uninitialized because the physical address range is not covered by
  * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=.
+ * layout is manually configured via memmap=, or when the highest physical
+ * address (max_pfn) does not end on a section boundary.
  */
-void __init zero_resv_unavail(void)
+static void __init init_unavailable_mem(void)
 {
 	phys_addr_t start, end;
 	u64 i, pgcnt;
@@ -6936,10 +6965,20 @@ void __init zero_resv_unavail(void)
 	for_each_mem_range(i, &memblock.memory, NULL,
 			NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
 		if (next < start)
-			pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start));
+			pgcnt += init_unavailable_range(PFN_DOWN(next),
+							PFN_UP(start));
 		next = end;
 	}
-	pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn);
+
+	/*
+	 * Early sections always have a fully populated memmap for the whole
+	 * section - see pfn_valid(). If the last section has holes at the
+	 * end and that section is marked "online", the memmap will be
+	 * considered initialized. Make sure that memmap has a well defined
+	 * state.
+	 */
+	pgcnt += init_unavailable_range(PFN_DOWN(next),
+					round_up(max_pfn, PAGES_PER_SECTION));
 
 	/*
 	 * Struct pages that do not have backing memory. This could be because
@@ -6948,6 +6987,10 @@ void __init zero_resv_unavail(void)
 	if (pgcnt)
 		pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
 }
+#else
+static inline void __init init_unavailable_mem(void)
+{
+}
 #endif /* !CONFIG_FLAT_NODE_MEM_MAP */
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -7377,7 +7420,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
-	zero_resv_unavail();
+	init_unavailable_mem();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, NULL,
@@ -7572,7 +7615,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 
 void __init free_area_init(unsigned long *zones_size)
 {
-	zero_resv_unavail();
+	init_unavailable_mem();
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
 }
@@ -8154,20 +8197,22 @@ void *__init alloc_large_system_hash(const char *tablename,
 
 /*
  * This function checks whether pageblock includes unmovable pages or not.
- * If @count is not zero, it is okay to include less @count unmovable pages
  *
  * PageLRU check without isolation or lru_lock could race so that
  * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
  * check without lock_page also may miss some movable non-lru pages at
  * race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
  */
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
-			 int migratetype, int flags)
+struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+				 int migratetype, int flags)
 {
-	unsigned long found;
 	unsigned long iter = 0;
 	unsigned long pfn = page_to_pfn(page);
-	const char *reason = "unmovable page";
 
 	/*
 	 * TODO we could make this much more efficient by not checking every
@@ -8184,22 +8229,19 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * so consider them movable here.
 		 */
 		if (is_migrate_cma(migratetype))
-			return false;
+			return NULL;
 
-		reason = "CMA page";
-		goto unmovable;
+		return page;
 	}
 
-	for (found = 0; iter < pageblock_nr_pages; iter++) {
-		unsigned long check = pfn + iter;
-
-		if (!pfn_valid_within(check))
+	for (; iter < pageblock_nr_pages; iter++) {
+		if (!pfn_valid_within(pfn + iter))
 			continue;
 
-		page = pfn_to_page(check);
+		page = pfn_to_page(pfn + iter);
 
 		if (PageReserved(page))
-			goto unmovable;
+			return page;
 
 		/*
 		 * If the zone is movable and we have ruled out all reserved
@@ -8219,7 +8261,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 			unsigned int skip_pages;
 
 			if (!hugepage_migration_supported(page_hstate(head)))
-				goto unmovable;
+				return page;
 
 			skip_pages = compound_nr(head) - (page - head);
 			iter += skip_pages - 1;
@@ -8245,11 +8287,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
 			continue;
 
-		if (__PageMovable(page))
+		if (__PageMovable(page) || PageLRU(page))
 			continue;
 
-		if (!PageLRU(page))
-			found++;
 		/*
 		 * If there are RECLAIMABLE pages, we need to check
 		 * it.  But now, memory offline itself doesn't call
@@ -8263,15 +8303,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 		 * is set to both of a memory hole page and a _used_ kernel
 		 * page at boot.
 		 */
-		if (found > count)
-			goto unmovable;
+		return page;
 	}
-	return false;
-unmovable:
-	WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
-	if (flags & REPORT_FAILURE)
-		dump_page(pfn_to_page(pfn + iter), reason);
-	return true;
+	return NULL;
 }
 
 #ifdef CONFIG_CONTIG_ALLOC
@@ -8675,10 +8709,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		BUG_ON(!PageBuddy(page));
 		order = page_order(page);
 		offlined_pages += 1 << order;
-#ifdef CONFIG_DEBUG_VM
-		pr_info("remove from free list %lx %d %lx\n",
-			pfn, 1 << order, end_pfn);
-#endif
 		del_page_from_free_area(page, &zone->free_area[order]);
 		pfn += (1 << order);
 	}
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 04ee1663cdbe..a9fd7c740c23 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -17,10 +17,9 @@
 
 static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
 {
+	struct page *unmovable = NULL;
 	struct zone *zone;
-	unsigned long flags, pfn;
-	struct memory_isolate_notify arg;
-	int notifier_ret;
+	unsigned long flags;
 	int ret = -EBUSY;
 
 	zone = page_zone(page);
@@ -35,41 +34,12 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	if (is_migrate_isolate_page(page))
 		goto out;
 
-	pfn = page_to_pfn(page);
-	arg.start_pfn = pfn;
-	arg.nr_pages = pageblock_nr_pages;
-	arg.pages_found = 0;
-
-	/*
-	 * It may be possible to isolate a pageblock even if the
-	 * migratetype is not MIGRATE_MOVABLE. The memory isolation
-	 * notifier chain is used by balloon drivers to return the
-	 * number of pages in a range that are held by the balloon
-	 * driver to shrink memory. If all the pages are accounted for
-	 * by balloons, are free, or on the LRU, isolation can continue.
-	 * Later, for example, when memory hotplug notifier runs, these
-	 * pages reported as "can be isolated" should be isolated(freed)
-	 * by the balloon driver through the memory notifier chain.
-	 */
-	notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
-	notifier_ret = notifier_to_errno(notifier_ret);
-	if (notifier_ret)
-		goto out;
 	/*
 	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
 	 * We just check MOVABLE pages.
 	 */
-	if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype,
-				 isol_flags))
-		ret = 0;
-
-	/*
-	 * immobile means "not-on-lru" pages. If immobile is larger than
-	 * removable-by-driver pages reported by notifier, we'll fail.
-	 */
-
-out:
-	if (!ret) {
+	unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags);
+	if (!unmovable) {
 		unsigned long nr_pages;
 		int mt = get_pageblock_migratetype(page);
 
@@ -79,11 +49,24 @@ out:
 									NULL);
 
 		__mod_zone_freepage_state(zone, -nr_pages, mt);
+		ret = 0;
 	}
 
+out:
 	spin_unlock_irqrestore(&zone->lock, flags);
-	if (!ret)
+	if (!ret) {
 		drain_all_pages(zone);
+	} else {
+		WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+
+		if ((isol_flags & REPORT_FAILURE) && unmovable)
+			/*
+			 * printk() with zone->lock held will likely trigger a
+			 * lockdep splat, so defer it here.
+			 */
+			dump_page(unmovable, "unmovable page");
+	}
+
 	return ret;
 }
 
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index eff4b4520c8d..719c35246cfa 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -52,12 +52,16 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
 	return true;
 }
 
-static inline bool pfn_in_hpage(struct page *hpage, unsigned long pfn)
+static inline bool pfn_is_match(struct page *page, unsigned long pfn)
 {
-	unsigned long hpage_pfn = page_to_pfn(hpage);
+	unsigned long page_pfn = page_to_pfn(page);
+
+	/* normal page and hugetlbfs page */
+	if (!PageTransCompound(page) || PageHuge(page))
+		return page_pfn == pfn;
 
 	/* THP can be referenced by any subpage */
-	return pfn >= hpage_pfn && pfn - hpage_pfn < hpage_nr_pages(hpage);
+	return pfn >= page_pfn && pfn - page_pfn < hpage_nr_pages(page);
 }
 
 /**
@@ -108,7 +112,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 		pfn = pte_pfn(*pvmw->pte);
 	}
 
-	return pfn_in_hpage(pvmw->page, pfn);
+	return pfn_is_match(pvmw->page, pfn);
 }
 
 /**
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ea0b9e606ad1..928df1638c30 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -4,26 +4,57 @@
 #include <linux/sched.h>
 #include <linux/hugetlb.h>
 
-static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			  struct mm_walk *walk)
+/*
+ * We want to know the real level where a entry is located ignoring any
+ * folding of levels which may be happening. For example if p4d is folded then
+ * a missing entry found at level 1 (p4d) is actually at level 0 (pgd).
+ */
+static int real_depth(int depth)
+{
+	if (depth == 3 && PTRS_PER_PMD == 1)
+		depth = 2;
+	if (depth == 2 && PTRS_PER_PUD == 1)
+		depth = 1;
+	if (depth == 1 && PTRS_PER_P4D == 1)
+		depth = 0;
+	return depth;
+}
+
+static int walk_pte_range_inner(pte_t *pte, unsigned long addr,
+				unsigned long end, struct mm_walk *walk)
 {
-	pte_t *pte;
-	int err = 0;
 	const struct mm_walk_ops *ops = walk->ops;
-	spinlock_t *ptl;
+	int err = 0;
 
-	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (;;) {
 		err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
 		if (err)
 		       break;
-		addr += PAGE_SIZE;
-		if (addr == end)
+		if (addr >= end - PAGE_SIZE)
 			break;
+		addr += PAGE_SIZE;
 		pte++;
 	}
+	return err;
+}
+
+static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			  struct mm_walk *walk)
+{
+	pte_t *pte;
+	int err = 0;
+	spinlock_t *ptl;
+
+	if (walk->no_vma) {
+		pte = pte_offset_map(pmd, addr);
+		err = walk_pte_range_inner(pte, addr, end, walk);
+		pte_unmap(pte);
+	} else {
+		pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+		err = walk_pte_range_inner(pte, addr, end, walk);
+		pte_unmap_unlock(pte, ptl);
+	}
 
-	pte_unmap_unlock(pte, ptl);
 	return err;
 }
 
@@ -34,18 +65,22 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	unsigned long next;
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
+	int depth = real_depth(3);
 
 	pmd = pmd_offset(pud, addr);
 	do {
 again:
 		next = pmd_addr_end(addr, end);
-		if (pmd_none(*pmd) || !walk->vma) {
+		if (pmd_none(*pmd) || (!walk->vma && !walk->no_vma)) {
 			if (ops->pte_hole)
-				err = ops->pte_hole(addr, next, walk);
+				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
 				break;
 			continue;
 		}
+
+		walk->action = ACTION_SUBTREE;
+
 		/*
 		 * This implies that each ->pmd_entry() handler
 		 * needs to know about pmd_trans_huge() pmds
@@ -55,16 +90,24 @@ again:
 		if (err)
 			break;
 
+		if (walk->action == ACTION_AGAIN)
+			goto again;
+
 		/*
 		 * Check this here so we only break down trans_huge
 		 * pages when we _need_ to
 		 */
-		if (!ops->pte_entry)
+		if ((!walk->vma && (pmd_leaf(*pmd) || !pmd_present(*pmd))) ||
+		    walk->action == ACTION_CONTINUE ||
+		    !(ops->pte_entry))
 			continue;
 
-		split_huge_pmd(walk->vma, pmd, addr);
-		if (pmd_trans_unstable(pmd))
-			goto again;
+		if (walk->vma) {
+			split_huge_pmd(walk->vma, pmd, addr);
+			if (pmd_trans_unstable(pmd))
+				goto again;
+		}
+
 		err = walk_pte_range(pmd, addr, next, walk);
 		if (err)
 			break;
@@ -80,37 +123,41 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 	unsigned long next;
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
+	int depth = real_depth(2);
 
 	pud = pud_offset(p4d, addr);
 	do {
  again:
 		next = pud_addr_end(addr, end);
-		if (pud_none(*pud) || !walk->vma) {
+		if (pud_none(*pud) || (!walk->vma && !walk->no_vma)) {
 			if (ops->pte_hole)
-				err = ops->pte_hole(addr, next, walk);
+				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
 				break;
 			continue;
 		}
 
-		if (ops->pud_entry) {
-			spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma);
+		walk->action = ACTION_SUBTREE;
 
-			if (ptl) {
-				err = ops->pud_entry(pud, addr, next, walk);
-				spin_unlock(ptl);
-				if (err)
-					break;
-				continue;
-			}
-		}
+		if (ops->pud_entry)
+			err = ops->pud_entry(pud, addr, next, walk);
+		if (err)
+			break;
+
+		if (walk->action == ACTION_AGAIN)
+			goto again;
 
-		split_huge_pud(walk->vma, pud, addr);
+		if ((!walk->vma && (pud_leaf(*pud) || !pud_present(*pud))) ||
+		    walk->action == ACTION_CONTINUE ||
+		    !(ops->pmd_entry || ops->pte_entry))
+			continue;
+
+		if (walk->vma)
+			split_huge_pud(walk->vma, pud, addr);
 		if (pud_none(*pud))
 			goto again;
 
-		if (ops->pmd_entry || ops->pte_entry)
-			err = walk_pmd_range(pud, addr, next, walk);
+		err = walk_pmd_range(pud, addr, next, walk);
 		if (err)
 			break;
 	} while (pud++, addr = next, addr != end);
@@ -125,18 +172,24 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	unsigned long next;
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
+	int depth = real_depth(1);
 
 	p4d = p4d_offset(pgd, addr);
 	do {
 		next = p4d_addr_end(addr, end);
 		if (p4d_none_or_clear_bad(p4d)) {
 			if (ops->pte_hole)
-				err = ops->pte_hole(addr, next, walk);
+				err = ops->pte_hole(addr, next, depth, walk);
 			if (err)
 				break;
 			continue;
 		}
-		if (ops->pmd_entry || ops->pte_entry)
+		if (ops->p4d_entry) {
+			err = ops->p4d_entry(p4d, addr, next, walk);
+			if (err)
+				break;
+		}
+		if (ops->pud_entry || ops->pmd_entry || ops->pte_entry)
 			err = walk_pud_range(p4d, addr, next, walk);
 		if (err)
 			break;
@@ -153,17 +206,26 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
 	const struct mm_walk_ops *ops = walk->ops;
 	int err = 0;
 
-	pgd = pgd_offset(walk->mm, addr);
+	if (walk->pgd)
+		pgd = walk->pgd + pgd_index(addr);
+	else
+		pgd = pgd_offset(walk->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd)) {
 			if (ops->pte_hole)
-				err = ops->pte_hole(addr, next, walk);
+				err = ops->pte_hole(addr, next, 0, walk);
 			if (err)
 				break;
 			continue;
 		}
-		if (ops->pmd_entry || ops->pte_entry)
+		if (ops->pgd_entry) {
+			err = ops->pgd_entry(pgd, addr, next, walk);
+			if (err)
+				break;
+		}
+		if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry ||
+		    ops->pte_entry)
 			err = walk_p4d_range(pgd, addr, next, walk);
 		if (err)
 			break;
@@ -199,7 +261,7 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end,
 		if (pte)
 			err = ops->hugetlb_entry(pte, hmask, addr, next, walk);
 		else if (ops->pte_hole)
-			err = ops->pte_hole(addr, next, walk);
+			err = ops->pte_hole(addr, next, -1, walk);
 
 		if (err)
 			break;
@@ -243,7 +305,7 @@ static int walk_page_test(unsigned long start, unsigned long end,
 	if (vma->vm_flags & VM_PFNMAP) {
 		int err = 1;
 		if (ops->pte_hole)
-			err = ops->pte_hole(start, end, walk);
+			err = ops->pte_hole(start, end, -1, walk);
 		return err ? err : 1;
 	}
 	return 0;
@@ -369,6 +431,33 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
+/*
+ * Similar to walk_page_range() but can walk any page tables even if they are
+ * not backed by VMAs. Because 'unusual' entries may be walked this function
+ * will also not lock the PTEs for the pte_entry() callback. This is useful for
+ * walking the kernel pages tables or page tables for firmware.
+ */
+int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  pgd_t *pgd,
+			  void *private)
+{
+	struct mm_walk walk = {
+		.ops		= ops,
+		.mm		= mm,
+		.pgd		= pgd,
+		.private	= private,
+		.no_vma		= true
+	};
+
+	if (start >= end || !walk.mm)
+		return -EINVAL;
+
+	lockdep_assert_held(&walk.mm->mmap_sem);
+
+	return __walk_page_range(start, end, &walk);
+}
+
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private)
 {
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 357aa7bef6c0..de41e830cdac 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -42,12 +42,11 @@ static int process_vm_rw_pages(struct page **pages,
 		if (copy > len)
 			copy = len;
 
-		if (vm_write) {
+		if (vm_write)
 			copied = copy_page_from_iter(page, offset, copy, iter);
-			set_page_dirty_lock(page);
-		} else {
+		else
 			copied = copy_page_to_iter(page, offset, copy, iter);
-		}
+
 		len -= copied;
 		if (copied < copy && iov_iter_count(iter))
 			return -EFAULT;
@@ -96,7 +95,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		flags |= FOLL_WRITE;
 
 	while (!rc && nr_pages && iov_iter_count(iter)) {
-		int pages = min(nr_pages, max_pages_per_loop);
+		int pinned_pages = min(nr_pages, max_pages_per_loop);
 		int locked = 1;
 		size_t bytes;
 
@@ -106,14 +105,15 @@ static int process_vm_rw_single_vec(unsigned long addr,
 		 * current/current->mm
 		 */
 		down_read(&mm->mmap_sem);
-		pages = get_user_pages_remote(task, mm, pa, pages, flags,
-					      process_pages, NULL, &locked);
+		pinned_pages = pin_user_pages_remote(task, mm, pa, pinned_pages,
+						     flags, process_pages,
+						     NULL, &locked);
 		if (locked)
 			up_read(&mm->mmap_sem);
-		if (pages <= 0)
+		if (pinned_pages <= 0)
 			return -EFAULT;
 
-		bytes = pages * PAGE_SIZE - start_offset;
+		bytes = pinned_pages * PAGE_SIZE - start_offset;
 		if (bytes > len)
 			bytes = len;
 
@@ -122,10 +122,12 @@ static int process_vm_rw_single_vec(unsigned long addr,
 					 vm_write);
 		len -= bytes;
 		start_offset = 0;
-		nr_pages -= pages;
-		pa += pages * PAGE_SIZE;
-		while (pages)
-			put_page(process_pages[--pages]);
+		nr_pages -= pinned_pages;
+		pa += pinned_pages * PAGE_SIZE;
+
+		/* If vm_write is set, the pages need to be made dirty: */
+		unpin_user_pages_dirty_lock(process_pages, pinned_pages,
+					    vm_write);
 	}
 
 	return rc;
diff --git a/mm/ptdump.c b/mm/ptdump.c
new file mode 100644
index 000000000000..26208d0d03b7
--- /dev/null
+++ b/mm/ptdump.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pagewalk.h>
+#include <linux/ptdump.h>
+#include <linux/kasan.h>
+
+#ifdef CONFIG_KASAN
+/*
+ * This is an optimization for KASAN=y case. Since all kasan page tables
+ * eventually point to the kasan_early_shadow_page we could call note_page()
+ * right away without walking through lower level page tables. This saves
+ * us dozens of seconds (minutes for 5-level config) while checking for
+ * W+X mapping or reading kernel_page_tables debugfs file.
+ */
+static inline int note_kasan_page_table(struct mm_walk *walk,
+					unsigned long addr)
+{
+	struct ptdump_state *st = walk->private;
+
+	st->note_page(st, addr, 4, pte_val(kasan_early_shadow_pte[0]));
+
+	walk->action = ACTION_CONTINUE;
+
+	return 0;
+}
+#endif
+
+static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	pgd_t val = READ_ONCE(*pgd);
+
+#if CONFIG_PGTABLE_LEVELS > 4 && defined(CONFIG_KASAN)
+	if (pgd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_p4d)))
+		return note_kasan_page_table(walk, addr);
+#endif
+
+	if (pgd_leaf(val))
+		st->note_page(st, addr, 0, pgd_val(val));
+
+	return 0;
+}
+
+static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	p4d_t val = READ_ONCE(*p4d);
+
+#if CONFIG_PGTABLE_LEVELS > 3 && defined(CONFIG_KASAN)
+	if (p4d_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pud)))
+		return note_kasan_page_table(walk, addr);
+#endif
+
+	if (p4d_leaf(val))
+		st->note_page(st, addr, 1, p4d_val(val));
+
+	return 0;
+}
+
+static int ptdump_pud_entry(pud_t *pud, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	pud_t val = READ_ONCE(*pud);
+
+#if CONFIG_PGTABLE_LEVELS > 2 && defined(CONFIG_KASAN)
+	if (pud_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pmd)))
+		return note_kasan_page_table(walk, addr);
+#endif
+
+	if (pud_leaf(val))
+		st->note_page(st, addr, 2, pud_val(val));
+
+	return 0;
+}
+
+static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+	pmd_t val = READ_ONCE(*pmd);
+
+#if defined(CONFIG_KASAN)
+	if (pmd_page(val) == virt_to_page(lm_alias(kasan_early_shadow_pte)))
+		return note_kasan_page_table(walk, addr);
+#endif
+
+	if (pmd_leaf(val))
+		st->note_page(st, addr, 3, pmd_val(val));
+
+	return 0;
+}
+
+static int ptdump_pte_entry(pte_t *pte, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+
+	st->note_page(st, addr, 4, pte_val(READ_ONCE(*pte)));
+
+	return 0;
+}
+
+static int ptdump_hole(unsigned long addr, unsigned long next,
+		       int depth, struct mm_walk *walk)
+{
+	struct ptdump_state *st = walk->private;
+
+	st->note_page(st, addr, depth, 0);
+
+	return 0;
+}
+
+static const struct mm_walk_ops ptdump_ops = {
+	.pgd_entry	= ptdump_pgd_entry,
+	.p4d_entry	= ptdump_p4d_entry,
+	.pud_entry	= ptdump_pud_entry,
+	.pmd_entry	= ptdump_pmd_entry,
+	.pte_entry	= ptdump_pte_entry,
+	.pte_hole	= ptdump_hole,
+};
+
+void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd)
+{
+	const struct ptdump_range *range = st->range;
+
+	down_read(&mm->mmap_sem);
+	while (range->start != range->end) {
+		walk_page_range_novma(mm, range->start, range->end,
+				      &ptdump_ops, pgd, st);
+		range++;
+	}
+	up_read(&mm->mmap_sem);
+
+	/* Flush out the last page */
+	st->note_page(st, 0, -1, 0);
+}
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 0d95ddea13b0..1907cb2903c7 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1580,18 +1580,17 @@ static int slabinfo_open(struct inode *inode, struct file *file)
 	return seq_open(file, &slabinfo_op);
 }
 
-static const struct file_operations proc_slabinfo_operations = {
-	.open		= slabinfo_open,
-	.read		= seq_read,
-	.write          = slabinfo_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
+static const struct proc_ops slabinfo_proc_ops = {
+	.proc_open	= slabinfo_open,
+	.proc_read	= seq_read,
+	.proc_write	= slabinfo_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 static int __init slab_proc_init(void)
 {
-	proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
-						&proc_slabinfo_operations);
+	proc_create("slabinfo", SLABINFO_RIGHTS, NULL, &slabinfo_proc_ops);
 	return 0;
 }
 module_init(slab_proc_init);
@@ -1677,28 +1676,6 @@ static __always_inline void *__do_krealloc(const void *p, size_t new_size,
 }
 
 /**
- * __krealloc - like krealloc() but don't free @p.
- * @p: object to reallocate memory for.
- * @new_size: how many bytes of memory are required.
- * @flags: the type of memory to allocate.
- *
- * This function is like krealloc() except it never frees the originally
- * allocated buffer. Use this if you don't want to free the buffer immediately
- * like, for example, with RCU.
- *
- * Return: pointer to the allocated memory or %NULL in case of error
- */
-void *__krealloc(const void *p, size_t new_size, gfp_t flags)
-{
-	if (unlikely(!new_size))
-		return ZERO_SIZE_PTR;
-
-	return __do_krealloc(p, new_size, flags);
-
-}
-EXPORT_SYMBOL(__krealloc);
-
-/**
  * krealloc - reallocate memory. The contents will remain unchanged.
  * @p: object to reallocate memory for.
  * @new_size: how many bytes of memory are required.
diff --git a/mm/slub.c b/mm/slub.c
index 0ab92ec8c2a6..17dc00e33115 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -439,19 +439,38 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
 }
 
 #ifdef CONFIG_SLUB_DEBUG
+static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
+static DEFINE_SPINLOCK(object_map_lock);
+
 /*
  * Determine a map of object in use on a page.
  *
  * Node listlock must be held to guarantee that the page does
  * not vanish from under us.
  */
-static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
+static unsigned long *get_map(struct kmem_cache *s, struct page *page)
 {
 	void *p;
 	void *addr = page_address(page);
 
+	VM_BUG_ON(!irqs_disabled());
+
+	spin_lock(&object_map_lock);
+
+	bitmap_zero(object_map, page->objects);
+
 	for (p = page->freelist; p; p = get_freepointer(s, p))
-		set_bit(slab_index(p, s, addr), map);
+		set_bit(slab_index(p, s, addr), object_map);
+
+	return object_map;
+}
+
+static void put_map(unsigned long *map)
+{
+	VM_BUG_ON(map != object_map);
+	lockdep_assert_held(&object_map_lock);
+
+	spin_unlock(&object_map_lock);
 }
 
 static inline unsigned int size_from_object(struct kmem_cache *s)
@@ -3675,13 +3694,12 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 #ifdef CONFIG_SLUB_DEBUG
 	void *addr = page_address(page);
 	void *p;
-	unsigned long *map = bitmap_zalloc(page->objects, GFP_ATOMIC);
-	if (!map)
-		return;
+	unsigned long *map;
+
 	slab_err(s, page, text, s->name);
 	slab_lock(page);
 
-	get_map(s, page, map);
+	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects) {
 
 		if (!test_bit(slab_index(p, s, addr), map)) {
@@ -3689,8 +3707,9 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 			print_tracking(s, p);
 		}
 	}
+	put_map(map);
+
 	slab_unlock(page);
-	bitmap_free(map);
 #endif
 }
 
@@ -4384,19 +4403,19 @@ static int count_total(struct page *page)
 #endif
 
 #ifdef CONFIG_SLUB_DEBUG
-static void validate_slab(struct kmem_cache *s, struct page *page,
-						unsigned long *map)
+static void validate_slab(struct kmem_cache *s, struct page *page)
 {
 	void *p;
 	void *addr = page_address(page);
+	unsigned long *map;
+
+	slab_lock(page);
 
 	if (!check_slab(s, page) || !on_freelist(s, page, NULL))
-		return;
+		goto unlock;
 
 	/* Now we know that a valid freelist exists */
-	bitmap_zero(map, page->objects);
-
-	get_map(s, page, map);
+	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects) {
 		u8 val = test_bit(slab_index(p, s, addr), map) ?
 			 SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
@@ -4404,18 +4423,13 @@ static void validate_slab(struct kmem_cache *s, struct page *page,
 		if (!check_object(s, page, p, val))
 			break;
 	}
-}
-
-static void validate_slab_slab(struct kmem_cache *s, struct page *page,
-						unsigned long *map)
-{
-	slab_lock(page);
-	validate_slab(s, page, map);
+	put_map(map);
+unlock:
 	slab_unlock(page);
 }
 
 static int validate_slab_node(struct kmem_cache *s,
-		struct kmem_cache_node *n, unsigned long *map)
+		struct kmem_cache_node *n)
 {
 	unsigned long count = 0;
 	struct page *page;
@@ -4424,7 +4438,7 @@ static int validate_slab_node(struct kmem_cache *s,
 	spin_lock_irqsave(&n->list_lock, flags);
 
 	list_for_each_entry(page, &n->partial, slab_list) {
-		validate_slab_slab(s, page, map);
+		validate_slab(s, page);
 		count++;
 	}
 	if (count != n->nr_partial)
@@ -4435,7 +4449,7 @@ static int validate_slab_node(struct kmem_cache *s,
 		goto out;
 
 	list_for_each_entry(page, &n->full, slab_list) {
-		validate_slab_slab(s, page, map);
+		validate_slab(s, page);
 		count++;
 	}
 	if (count != atomic_long_read(&n->nr_slabs))
@@ -4452,15 +4466,11 @@ static long validate_slab_cache(struct kmem_cache *s)
 	int node;
 	unsigned long count = 0;
 	struct kmem_cache_node *n;
-	unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);
-
-	if (!map)
-		return -ENOMEM;
 
 	flush_all(s);
 	for_each_kmem_cache_node(s, node, n)
-		count += validate_slab_node(s, n, map);
-	bitmap_free(map);
+		count += validate_slab_node(s, n);
+
 	return count;
 }
 /*
@@ -4590,18 +4600,17 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 }
 
 static void process_slab(struct loc_track *t, struct kmem_cache *s,
-		struct page *page, enum track_item alloc,
-		unsigned long *map)
+		struct page *page, enum track_item alloc)
 {
 	void *addr = page_address(page);
 	void *p;
+	unsigned long *map;
 
-	bitmap_zero(map, page->objects);
-	get_map(s, page, map);
-
+	map = get_map(s, page);
 	for_each_object(p, s, addr, page->objects)
 		if (!test_bit(slab_index(p, s, addr), map))
 			add_location(t, s, get_track(s, p, alloc));
+	put_map(map);
 }
 
 static int list_locations(struct kmem_cache *s, char *buf,
@@ -4612,11 +4621,9 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	struct loc_track t = { 0, 0, NULL };
 	int node;
 	struct kmem_cache_node *n;
-	unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL);
 
-	if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
-				     GFP_KERNEL)) {
-		bitmap_free(map);
+	if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
+			     GFP_KERNEL)) {
 		return sprintf(buf, "Out of memory\n");
 	}
 	/* Push back cpu slabs */
@@ -4631,9 +4638,9 @@ static int list_locations(struct kmem_cache *s, char *buf,
 
 		spin_lock_irqsave(&n->list_lock, flags);
 		list_for_each_entry(page, &n->partial, slab_list)
-			process_slab(&t, s, page, alloc, map);
+			process_slab(&t, s, page, alloc);
 		list_for_each_entry(page, &n->full, slab_list)
-			process_slab(&t, s, page, alloc, map);
+			process_slab(&t, s, page, alloc);
 		spin_unlock_irqrestore(&n->list_lock, flags);
 	}
 
@@ -4682,7 +4689,6 @@ static int list_locations(struct kmem_cache *s, char *buf,
 	}
 
 	free_loc_track(&t);
-	bitmap_free(map);
 	if (!t.count)
 		len += sprintf(buf, "No data\n");
 	return len;
diff --git a/mm/sparse.c b/mm/sparse.c
index 3822ecbd8a1f..c184b69460b7 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -198,16 +198,6 @@ static void section_mark_present(struct mem_section *ms)
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 }
 
-static inline unsigned long next_present_section_nr(unsigned long section_nr)
-{
-	do {
-		section_nr++;
-		if (present_section_nr(section_nr))
-			return section_nr;
-	} while ((section_nr <= __highest_present_section_nr));
-
-	return -1;
-}
 #define for_each_present_section_nr(start, section_nr)		\
 	for (section_nr = next_present_section_nr(start-1);	\
 	     ((section_nr != -1) &&				\
@@ -789,7 +779,7 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 			ms->usage = NULL;
 		}
 		memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-		ms->section_mem_map = sparse_encode_mem_map(NULL, section_nr);
+		ms->section_mem_map = (unsigned long)NULL;
 	}
 
 	if (section_is_early && memmap)
diff --git a/mm/swap.c b/mm/swap.c
index 5341ae93861f..cf39d24ada2a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -813,8 +813,10 @@ void release_pages(struct page **pages, int nr)
 			 * processing, and instead, expect a call to
 			 * put_page_testzero().
 			 */
-			if (put_devmap_managed_page(page))
+			if (page_is_devmap_managed(page)) {
+				put_devmap_managed_page(page);
 				continue;
+			}
 		}
 
 		page = compound_head(page);
@@ -1102,3 +1104,26 @@ void __init swap_setup(void)
 	 * _really_ don't want to cluster much more
 	 */
 }
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void put_devmap_managed_page(struct page *page)
+{
+	int count;
+
+	if (WARN_ON_ONCE(!page_is_devmap_managed(page)))
+		return;
+
+	count = page_ref_dec_return(page);
+
+	/*
+	 * devmap page refcounts are 1-based, rather than 0-based: if
+	 * refcount is 1, then the page is free and the refcount is
+	 * stable because nobody holds a reference on the page.
+	 */
+	if (count == 1)
+		free_devmap_managed_page(page);
+	else if (!count)
+		__put_page(page);
+}
+EXPORT_SYMBOL(put_devmap_managed_page);
+#endif
diff --git a/mm/swapfile.c b/mm/swapfile.c
index bb3261d45b6a..2c33ff456ed5 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2737,10 +2737,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
 	else
 		type = si->type + 1;
 
+	++(*pos);
 	for (; (si = swap_type_to_swap_info(type)); type++) {
 		if (!(si->flags & SWP_USED) || !si->swap_map)
 			continue;
-		++*pos;
 		return si;
 	}
 
@@ -2796,17 +2796,17 @@ static int swaps_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations proc_swaps_operations = {
-	.open		= swaps_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-	.poll		= swaps_poll,
+static const struct proc_ops swaps_proc_ops = {
+	.proc_open	= swaps_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
+	.proc_poll	= swaps_poll,
 };
 
 static int __init procswaps_init(void)
 {
-	proc_create("swaps", 0, NULL, &proc_swaps_operations);
+	proc_create("swaps", 0, NULL, &swaps_proc_ops);
 	return 0;
 }
 __initcall(procswaps_init);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 572fb17c6273..c05eb9efec07 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -146,20 +146,6 @@ struct scan_control {
 	struct reclaim_state reclaim_state;
 };
 
-#ifdef ARCH_HAS_PREFETCH
-#define prefetch_prev_lru_page(_page, _base, _field)			\
-	do {								\
-		if ((_page)->lru.prev != _base) {			\
-			struct page *prev;				\
-									\
-			prev = lru_to_page(&(_page->lru));		\
-			prefetch(&prev->_field);			\
-		}							\
-	} while (0)
-#else
-#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
-#endif
-
 #ifdef ARCH_HAS_PREFETCHW
 #define prefetchw_prev_lru_page(_page, _base, _field)			\
 	do {								\
@@ -2695,7 +2681,7 @@ static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
 	} while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
 }
 
-static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 {
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long nr_reclaimed, nr_scanned;
@@ -2874,8 +2860,6 @@ again:
 	 */
 	if (reclaimable)
 		pgdat->kswapd_failures = 0;
-
-	return reclaimable;
 }
 
 /*
@@ -4126,10 +4110,8 @@ module_init(kswapd_init)
  */
 int node_reclaim_mode __read_mostly;
 
-#define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
-#define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
-#define RECLAIM_UNMAP (1<<2)	/* Unmap pages during reclaim */
+#define RECLAIM_WRITE (1<<0)	/* Writeout pages during reclaim */
+#define RECLAIM_UNMAP (1<<1)	/* Unmap pages during reclaim */
 
 /*
  * Priority for NODE_RECLAIM. This determines the fraction of pages
diff --git a/mm/zswap.c b/mm/zswap.c
index 46a322316e52..55094e63b72d 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -32,6 +32,7 @@
 #include <linux/swapops.h>
 #include <linux/writeback.h>
 #include <linux/pagemap.h>
+#include <linux/workqueue.h>
 
 /*********************************
 * statistics
@@ -65,6 +66,11 @@ static u64 zswap_reject_kmemcache_fail;
 /* Duplicate store was encountered (rare) */
 static u64 zswap_duplicate_entry;
 
+/* Shrinker work queue */
+static struct workqueue_struct *shrink_wq;
+/* Pool limit was hit, we need to calm down */
+static bool zswap_pool_reached_full;
+
 /*********************************
 * tunables
 **********************************/
@@ -109,6 +115,11 @@ module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_type, 0644);
 static unsigned int zswap_max_pool_percent = 20;
 module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644);
 
+/* The threshold for accepting new pages after the max_pool_percent was hit */
+static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */
+module_param_named(accept_threshold_percent, zswap_accept_thr_percent,
+		   uint, 0644);
+
 /* Enable/disable handling same-value filled pages (enabled by default) */
 static bool zswap_same_filled_pages_enabled = true;
 module_param_named(same_filled_pages_enabled, zswap_same_filled_pages_enabled,
@@ -123,7 +134,8 @@ struct zswap_pool {
 	struct crypto_comp * __percpu *tfm;
 	struct kref kref;
 	struct list_head list;
-	struct work_struct work;
+	struct work_struct release_work;
+	struct work_struct shrink_work;
 	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
@@ -214,6 +226,13 @@ static bool zswap_is_full(void)
 			DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
 }
 
+static bool zswap_can_accept(void)
+{
+	return totalram_pages() * zswap_accept_thr_percent / 100 *
+				zswap_max_pool_percent / 100 >
+			DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+}
+
 static void zswap_update_total_size(void)
 {
 	struct zswap_pool *pool;
@@ -501,6 +520,16 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
 	return NULL;
 }
 
+static void shrink_worker(struct work_struct *w)
+{
+	struct zswap_pool *pool = container_of(w, typeof(*pool),
+						shrink_work);
+
+	if (zpool_shrink(pool->zpool, 1, NULL))
+		zswap_reject_reclaim_fail++;
+	zswap_pool_put(pool);
+}
+
 static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 {
 	struct zswap_pool *pool;
@@ -551,6 +580,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	 */
 	kref_init(&pool->kref);
 	INIT_LIST_HEAD(&pool->list);
+	INIT_WORK(&pool->shrink_work, shrink_worker);
 
 	zswap_pool_debug("created", pool);
 
@@ -624,7 +654,8 @@ static int __must_check zswap_pool_get(struct zswap_pool *pool)
 
 static void __zswap_pool_release(struct work_struct *work)
 {
-	struct zswap_pool *pool = container_of(work, typeof(*pool), work);
+	struct zswap_pool *pool = container_of(work, typeof(*pool),
+						release_work);
 
 	synchronize_rcu();
 
@@ -647,8 +678,8 @@ static void __zswap_pool_empty(struct kref *kref)
 
 	list_del_rcu(&pool->list);
 
-	INIT_WORK(&pool->work, __zswap_pool_release);
-	schedule_work(&pool->work);
+	INIT_WORK(&pool->release_work, __zswap_pool_release);
+	schedule_work(&pool->release_work);
 
 	spin_unlock(&zswap_pools_lock);
 }
@@ -942,22 +973,6 @@ end:
 	return ret;
 }
 
-static int zswap_shrink(void)
-{
-	struct zswap_pool *pool;
-	int ret;
-
-	pool = zswap_pool_last_get();
-	if (!pool)
-		return -ENOENT;
-
-	ret = zpool_shrink(pool->zpool, 1, NULL);
-
-	zswap_pool_put(pool);
-
-	return ret;
-}
-
 static int zswap_is_page_same_filled(void *ptr, unsigned long *value)
 {
 	unsigned int pos;
@@ -1011,21 +1026,23 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 
 	/* reclaim space if needed */
 	if (zswap_is_full()) {
+		struct zswap_pool *pool;
+
 		zswap_pool_limit_hit++;
-		if (zswap_shrink()) {
-			zswap_reject_reclaim_fail++;
-			ret = -ENOMEM;
-			goto reject;
-		}
+		zswap_pool_reached_full = true;
+		pool = zswap_pool_last_get();
+		if (pool)
+			queue_work(shrink_wq, &pool->shrink_work);
+		ret = -ENOMEM;
+		goto reject;
+	}
 
-		/* A second zswap_is_full() check after
-		 * zswap_shrink() to make sure it's now
-		 * under the max_pool_percent
-		 */
-		if (zswap_is_full()) {
+	if (zswap_pool_reached_full) {
+	       if (!zswap_can_accept()) {
 			ret = -ENOMEM;
 			goto reject;
-		}
+		} else
+			zswap_pool_reached_full = false;
 	}
 
 	/* allocate entry */
@@ -1332,11 +1349,18 @@ static int __init init_zswap(void)
 		zswap_enabled = false;
 	}
 
+	shrink_wq = create_workqueue("zswap-shrink");
+	if (!shrink_wq)
+		goto fallback_fail;
+
 	frontswap_register_ops(&zswap_frontswap_ops);
 	if (zswap_debugfs_init())
 		pr_warn("debugfs initialization failed\n");
 	return 0;
 
+fallback_fail:
+	if (pool)
+		zswap_pool_destroy(pool);
 hp_fail:
 	cpuhp_remove_state(CPUHP_MM_ZSWP_MEM_PREPARE);
 dstmem_fail:
diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c
index 46d6cd9a36ae..829db9eba0cb 100644
--- a/net/atm/mpoa_proc.c
+++ b/net/atm/mpoa_proc.c
@@ -53,15 +53,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff,
 
 static int parse_qos(const char *buff);
 
-/*
- *   Define allowed FILE OPERATIONS
- */
-static const struct file_operations mpc_file_operations = {
-	.open =		proc_mpc_open,
-	.read =		seq_read,
-	.llseek =	seq_lseek,
-	.write =	proc_mpc_write,
-	.release =	seq_release,
+static const struct proc_ops mpc_proc_ops = {
+	.proc_open	= proc_mpc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= proc_mpc_write,
+	.proc_release	= seq_release,
 };
 
 /*
@@ -290,7 +287,7 @@ int mpc_proc_init(void)
 {
 	struct proc_dir_entry *p;
 
-	p = proc_create(STAT_FILE_NAME, 0, atm_proc_root, &mpc_file_operations);
+	p = proc_create(STAT_FILE_NAME, 0, atm_proc_root, &mpc_proc_ops);
 	if (!p) {
 		pr_err("Unable to initialize /proc/atm/%s\n", STAT_FILE_NAME);
 		return -ENOMEM;
diff --git a/net/atm/proc.c b/net/atm/proc.c
index c31896707313..4369ffa3302a 100644
--- a/net/atm/proc.c
+++ b/net/atm/proc.c
@@ -36,9 +36,9 @@
 static ssize_t proc_dev_atm_read(struct file *file, char __user *buf,
 				 size_t count, loff_t *pos);
 
-static const struct file_operations proc_atm_dev_ops = {
-	.read =		proc_dev_atm_read,
-	.llseek =	noop_llseek,
+static const struct proc_ops atm_dev_proc_ops = {
+	.proc_read	= proc_dev_atm_read,
+	.proc_lseek	= noop_llseek,
 };
 
 static void add_stats(struct seq_file *seq, const char *aal,
@@ -359,7 +359,7 @@ int atm_proc_dev_register(struct atm_dev *dev)
 		goto err_out;
 
 	dev->proc_entry = proc_create_data(dev->proc_name, 0, atm_proc_root,
-					   &proc_atm_dev_ops, dev);
+					   &atm_dev_proc_ops, dev);
 	if (!dev->proc_entry)
 		goto err_free_name;
 	return 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index 17529d49faec..a69e8bd7ed74 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5792,7 +5792,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (&ptype->list == head)
 		goto normal;
 
-	if (IS_ERR(pp) && PTR_ERR(pp) == -EINPROGRESS) {
+	if (PTR_ERR(pp) == -EINPROGRESS) {
 		ret = GRO_CONSUMED;
 		goto ok;
 	}
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 536e032d95c8..ea46fc6aa883 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -802,16 +802,12 @@ net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata)
 	if (!n_hw_metadata)
 		return NULL;
 
-	trap_group_name = kmemdup(hw_metadata->trap_group_name,
-				  strlen(hw_metadata->trap_group_name) + 1,
-				  GFP_ATOMIC | __GFP_ZERO);
+	trap_group_name = kstrdup(hw_metadata->trap_group_name, GFP_ATOMIC);
 	if (!trap_group_name)
 		goto free_hw_metadata;
 	n_hw_metadata->trap_group_name = trap_group_name;
 
-	trap_name = kmemdup(hw_metadata->trap_name,
-			    strlen(hw_metadata->trap_name) + 1,
-			    GFP_ATOMIC | __GFP_ZERO);
+	trap_name = kstrdup(hw_metadata->trap_name, GFP_ATOMIC);
 	if (!trap_name)
 		goto free_trap_group;
 	n_hw_metadata->trap_name = trap_name;
diff --git a/net/core/filter.c b/net/core/filter.c
index 792e3744b915..c180871e606d 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1573,7 +1573,7 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 		return -EPERM;
 
 	prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
-	if (IS_ERR(prog) && PTR_ERR(prog) == -EINVAL)
+	if (PTR_ERR(prog) == -EINVAL)
 		prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 294bfcf0ce0e..acc849df60b5 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -535,12 +535,12 @@ static int pgctrl_open(struct inode *inode, struct file *file)
 	return single_open(file, pgctrl_show, PDE_DATA(inode));
 }
 
-static const struct file_operations pktgen_fops = {
-	.open    = pgctrl_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.write   = pgctrl_write,
-	.release = single_release,
+static const struct proc_ops pktgen_proc_ops = {
+	.proc_open	= pgctrl_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= pgctrl_write,
+	.proc_release	= single_release,
 };
 
 static int pktgen_if_show(struct seq_file *seq, void *v)
@@ -1707,12 +1707,12 @@ static int pktgen_if_open(struct inode *inode, struct file *file)
 	return single_open(file, pktgen_if_show, PDE_DATA(inode));
 }
 
-static const struct file_operations pktgen_if_fops = {
-	.open    = pktgen_if_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.write   = pktgen_if_write,
-	.release = single_release,
+static const struct proc_ops pktgen_if_proc_ops = {
+	.proc_open	= pktgen_if_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= pktgen_if_write,
+	.proc_release	= single_release,
 };
 
 static int pktgen_thread_show(struct seq_file *seq, void *v)
@@ -1844,12 +1844,12 @@ static int pktgen_thread_open(struct inode *inode, struct file *file)
 	return single_open(file, pktgen_thread_show, PDE_DATA(inode));
 }
 
-static const struct file_operations pktgen_thread_fops = {
-	.open    = pktgen_thread_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.write   = pktgen_thread_write,
-	.release = single_release,
+static const struct proc_ops pktgen_thread_proc_ops = {
+	.proc_open	= pktgen_thread_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_write	= pktgen_thread_write,
+	.proc_release	= single_release,
 };
 
 /* Think find or remove for NN */
@@ -1926,7 +1926,7 @@ static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *d
 
 			pkt_dev->entry = proc_create_data(dev->name, 0600,
 							  pn->proc_dir,
-							  &pktgen_if_fops,
+							  &pktgen_if_proc_ops,
 							  pkt_dev);
 			if (!pkt_dev->entry)
 				pr_err("can't move proc entry for '%s'\n",
@@ -3638,7 +3638,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 		pkt_dev->clone_skb = pg_clone_skb_d;
 
 	pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir,
-					  &pktgen_if_fops, pkt_dev);
+					  &pktgen_if_proc_ops, pkt_dev);
 	if (!pkt_dev->entry) {
 		pr_err("cannot create %s/%s procfs entry\n",
 		       PG_PROC_DIR, ifname);
@@ -3708,7 +3708,7 @@ static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn)
 	t->tsk = p;
 
 	pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir,
-			      &pktgen_thread_fops, t);
+			      &pktgen_thread_proc_ops, t);
 	if (!pe) {
 		pr_err("cannot create %s/%s procfs entry\n",
 		       PG_PROC_DIR, t->tsk->comm);
@@ -3793,7 +3793,7 @@ static int __net_init pg_net_init(struct net *net)
 		pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR);
 		return -ENODEV;
 	}
-	pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops);
+	pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_proc_ops);
 	if (pe == NULL) {
 		pr_err("cannot create %s procfs entry\n", PGCTRL);
 		ret = -EINVAL;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cdad6ed532c4..09c44bf2e1d2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1242,6 +1242,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 		return 0;
 
 	memset(&vf_vlan_info, 0, sizeof(vf_vlan_info));
+	memset(&node_guid, 0, sizeof(node_guid));
+	memset(&port_guid, 0, sizeof(port_guid));
 
 	vf_mac.vf =
 		vf_vlan.vf =
@@ -1290,8 +1292,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 		    sizeof(vf_trust), &vf_trust))
 		goto nla_put_vf_failure;
 
-	memset(&node_guid, 0, sizeof(node_guid));
-	memset(&port_guid, 0, sizeof(port_guid));
 	if (dev->netdev_ops->ndo_get_vf_guid &&
 	    !dev->netdev_ops->ndo_get_vf_guid(dev, vfs_num, &node_guid,
 					      &port_guid)) {
diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index ee561297d8a7..fbfd0db182b7 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -27,6 +27,8 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 
 	rcu_read_lock(); /* hsr->node_db, hsr->ports */
 	port = hsr_port_get_rcu(skb->dev);
+	if (!port)
+		goto finish_pass;
 
 	if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) {
 		/* Directly kill frames sent by ourselves */
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index f35308ff84c3..4438f6b12335 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1334,7 +1334,7 @@ static int __init ipconfig_proc_net_init(void)
 
 /* Create a new file under /proc/net/ipconfig */
 static int ipconfig_proc_net_create(const char *name,
-				    const struct file_operations *fops)
+				    const struct proc_ops *proc_ops)
 {
 	char *pname;
 	struct proc_dir_entry *p;
@@ -1346,7 +1346,7 @@ static int ipconfig_proc_net_create(const char *name,
 	if (!pname)
 		return -ENOMEM;
 
-	p = proc_create(pname, 0444, init_net.proc_net, fops);
+	p = proc_create(pname, 0444, init_net.proc_net, proc_ops);
 	kfree(pname);
 	if (!p)
 		return -ENOMEM;
@@ -1355,7 +1355,7 @@ static int ipconfig_proc_net_create(const char *name,
 }
 
 /* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */
-static int ntp_servers_seq_show(struct seq_file *seq, void *v)
+static int ntp_servers_show(struct seq_file *seq, void *v)
 {
 	int i;
 
@@ -1365,7 +1365,7 @@ static int ntp_servers_seq_show(struct seq_file *seq, void *v)
 	}
 	return 0;
 }
-DEFINE_SHOW_ATTRIBUTE(ntp_servers_seq);
+DEFINE_PROC_SHOW_ATTRIBUTE(ntp_servers);
 #endif /* CONFIG_PROC_FS */
 
 /*
@@ -1456,7 +1456,7 @@ static int __init ip_auto_config(void)
 	proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show);
 
 	if (ipconfig_proc_net_init() == 0)
-		ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops);
+		ipconfig_proc_net_create("ntp_servers", &ntp_servers_proc_ops);
 #endif /* CONFIG_PROC_FS */
 
 	if (!ic_enable)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 6bdb1ab8af61..f8755a4ae9d4 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -58,7 +58,7 @@ struct clusterip_config {
 };
 
 #ifdef CONFIG_PROC_FS
-static const struct file_operations clusterip_proc_fops;
+static const struct proc_ops clusterip_proc_ops;
 #endif
 
 struct clusterip_net {
@@ -280,7 +280,7 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i,
 		mutex_lock(&cn->mutex);
 		c->pde = proc_create_data(buffer, 0600,
 					  cn->procdir,
-					  &clusterip_proc_fops, c);
+					  &clusterip_proc_ops, c);
 		mutex_unlock(&cn->mutex);
 		if (!c->pde) {
 			err = -ENOMEM;
@@ -804,12 +804,12 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input,
 	return size;
 }
 
-static const struct file_operations clusterip_proc_fops = {
-	.open	 = clusterip_proc_open,
-	.read	 = seq_read,
-	.write	 = clusterip_proc_write,
-	.llseek	 = seq_lseek,
-	.release = clusterip_proc_release,
+static const struct proc_ops clusterip_proc_ops = {
+	.proc_open	= clusterip_proc_open,
+	.proc_read	= seq_read,
+	.proc_write	= clusterip_proc_write,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= clusterip_proc_release,
 };
 
 #endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d5c57b3f77d5..ebe7060d0fc9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -237,11 +237,11 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file)
 	return seq_open(file, &rt_cache_seq_ops);
 }
 
-static const struct file_operations rt_cache_seq_fops = {
-	.open	 = rt_cache_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
+static const struct proc_ops rt_cache_proc_ops = {
+	.proc_open	= rt_cache_seq_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 
@@ -328,11 +328,11 @@ static int rt_cpu_seq_open(struct inode *inode, struct file *file)
 	return seq_open(file, &rt_cpu_seq_ops);
 }
 
-static const struct file_operations rt_cpu_seq_fops = {
-	.open	 = rt_cpu_seq_open,
-	.read	 = seq_read,
-	.llseek	 = seq_lseek,
-	.release = seq_release,
+static const struct proc_ops rt_cpu_proc_ops = {
+	.proc_open	= rt_cpu_seq_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
 };
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -366,12 +366,12 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
 	struct proc_dir_entry *pde;
 
 	pde = proc_create("rt_cache", 0444, net->proc_net,
-			  &rt_cache_seq_fops);
+			  &rt_cache_proc_ops);
 	if (!pde)
 		goto err1;
 
 	pde = proc_create("rt_cache", 0444,
-			  net->proc_net_stat, &rt_cpu_seq_fops);
+			  net->proc_net_stat, &rt_cpu_proc_ops);
 	if (!pde)
 		goto err2;
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 345b2b0ff618..9a4f6b16c9bc 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -349,6 +349,10 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 	treq->snt_synack	= 0;
 	treq->tfo_listener	= false;
+
+	if (IS_ENABLED(CONFIG_MPTCP))
+		treq->is_mptcp = 0;
+
 	if (IS_ENABLED(CONFIG_SMC))
 		ireq->smc_ok = 0;
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 484485ae74c2..eb2d80519f8e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2622,10 +2622,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
+	tp->delivered = 0;
 	tp->delivered_ce = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
+	tp->total_retrans = 0;
 	inet_csk_delack_init(sk);
 	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
 	 * issue in __tcp_select_window()
@@ -2637,10 +2639,14 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
+	tp->segs_in = 0;
+	tp->segs_out = 0;
 	tp->bytes_sent = 0;
 	tp->bytes_acked = 0;
 	tp->bytes_received = 0;
 	tp->bytes_retrans = 0;
+	tp->data_segs_in = 0;
+	tp->data_segs_out = 0;
 	tp->duplicate_sack[0].start_seq = 0;
 	tp->duplicate_sack[0].end_seq = 0;
 	tp->dsack_dups = 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e8b840a4767e..316ebdf8151d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5908,8 +5908,14 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 *        the segment and return)"
 		 */
 		if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) ||
-		    after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt))
+		    after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
+			/* Previous FIN/ACK or RST/ACK might be ignored. */
+			if (icsk->icsk_retransmits == 0)
+				inet_csk_reset_xmit_timer(sk,
+						ICSK_TIME_RETRANS,
+						TCP_TIMEOUT_MIN, TCP_RTO_MAX);
 			goto reset_and_undo;
+		}
 
 		if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 		    !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp,
@@ -6637,6 +6643,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	af_ops->init_req(req, sk, skb);
 
+	if (IS_ENABLED(CONFIG_MPTCP) && want_cookie)
+		tcp_rsk(req)->is_mptcp = 0;
+
 	if (security_inet_conn_request(sk, skb, req))
 		goto drop_and_free;
 
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 30915f6f31e3..13235a012388 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -178,6 +178,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	treq = tcp_rsk(req);
 	treq->tfo_listener = false;
 
+	if (IS_ENABLED(CONFIG_MPTCP))
+		treq->is_mptcp = 0;
+
 	if (security_inet_conn_request(sk, skb, req))
 		goto out_free;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 33a578a3eb3a..eaf09e6b7844 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -239,7 +239,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 		icsk->icsk_af_ops = &ipv6_mapped;
 		if (sk_is_mptcp(sk))
-			mptcp_handle_ipv6_mapped(sk, true);
+			mptcpv6_handle_mapped(sk, true);
 		sk->sk_backlog_rcv = tcp_v4_do_rcv;
 #ifdef CONFIG_TCP_MD5SIG
 		tp->af_specific = &tcp_sock_ipv6_mapped_specific;
@@ -251,7 +251,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			icsk->icsk_ext_hdr_len = exthdrlen;
 			icsk->icsk_af_ops = &ipv6_specific;
 			if (sk_is_mptcp(sk))
-				mptcp_handle_ipv6_mapped(sk, false);
+				mptcpv6_handle_mapped(sk, false);
 			sk->sk_backlog_rcv = tcp_v6_do_rcv;
 #ifdef CONFIG_TCP_MD5SIG
 			tp->af_specific = &tcp_sock_ipv6_specific;
@@ -1208,7 +1208,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
 		if (sk_is_mptcp(newsk))
-			mptcp_handle_ipv6_mapped(newsk, true);
+			mptcpv6_handle_mapped(newsk, true);
 		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
 #ifdef CONFIG_TCP_MD5SIG
 		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c99223cb3338..fcb53ed1c4fb 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -320,8 +320,13 @@ int l2tp_session_register(struct l2tp_session *session,
 
 		spin_lock_bh(&pn->l2tp_session_hlist_lock);
 
+		/* IP encap expects session IDs to be globally unique, while
+		 * UDP encap doesn't.
+		 */
 		hlist_for_each_entry(session_walk, g_head, global_hlist)
-			if (session_walk->session_id == session->session_id) {
+			if (session_walk->session_id == session->session_id &&
+			    (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP ||
+			     tunnel->encap == L2TP_ENCAPTYPE_IP)) {
 				err = -EEXIST;
 				goto err_tlock_pnlock;
 			}
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig
index 5db56d2218c5..49f6054e7f4e 100644
--- a/net/mptcp/Kconfig
+++ b/net/mptcp/Kconfig
@@ -10,17 +10,19 @@ config MPTCP
 	  uses the TCP protocol, and TCP options carry header information for
 	  MPTCP.
 
+if MPTCP
+
 config MPTCP_IPV6
 	bool "MPTCP: IPv6 support for Multipath TCP"
-	depends on MPTCP
 	select IPV6
 	default y
 
 config MPTCP_HMAC_TEST
 	bool "Tests for MPTCP HMAC implementation"
-	default n
 	help
 	  This option enable boot time self-test for the HMAC implementation
 	  used by the MPTCP code
 
 	  Say N if you are unsure.
+
+endif
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 39fdca79ce90..3bccee455688 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -28,7 +28,7 @@ static void __mptcp_close(struct sock *sk, long timeout);
 
 static const struct proto_ops *tcp_proto_ops(struct sock *sk)
 {
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	if (sk->sk_family == AF_INET6)
 		return &inet6_stream_ops;
 #endif
@@ -644,19 +644,21 @@ static void __mptcp_close(struct sock *sk, long timeout)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	LIST_HEAD(conn_list);
 
 	mptcp_token_destroy(msk->token);
 	inet_sk_state_store(sk, TCP_CLOSE);
 
-	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+	list_splice_init(&msk->conn_list, &conn_list);
+
+	release_sock(sk);
+
+	list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
 		__mptcp_close_ssk(sk, ssk, subflow, timeout);
 	}
 
-	if (msk->cached_ext)
-		__skb_ext_put(msk->cached_ext);
-	release_sock(sk);
 	sk_common_release(sk);
 }
 
@@ -776,18 +778,19 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 
 static void mptcp_destroy(struct sock *sk)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (msk->cached_ext)
+		__skb_ext_put(msk->cached_ext);
 }
 
 static int mptcp_setsockopt(struct sock *sk, int level, int optname,
-			    char __user *uoptval, unsigned int optlen)
+			    char __user *optval, unsigned int optlen)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	char __kernel *optval;
 	int ret = -EOPNOTSUPP;
 	struct socket *ssock;
-
-	/* will be treated as __user in tcp_setsockopt */
-	optval = (char __kernel __force *)uoptval;
+	struct sock *ssk;
 
 	pr_debug("msk=%p", msk);
 
@@ -796,27 +799,28 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname,
 	 */
 	lock_sock(sk);
 	ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
-	if (!IS_ERR(ssock)) {
-		pr_debug("subflow=%p", ssock->sk);
-		ret = kernel_setsockopt(ssock, level, optname, optval, optlen);
+	if (IS_ERR(ssock)) {
+		release_sock(sk);
+		return ret;
 	}
+
+	ssk = ssock->sk;
+	sock_hold(ssk);
 	release_sock(sk);
 
+	ret = tcp_setsockopt(ssk, level, optname, optval, optlen);
+	sock_put(ssk);
+
 	return ret;
 }
 
 static int mptcp_getsockopt(struct sock *sk, int level, int optname,
-			    char __user *uoptval, int __user *uoption)
+			    char __user *optval, int __user *option)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	char __kernel *optval;
 	int ret = -EOPNOTSUPP;
-	int __kernel *option;
 	struct socket *ssock;
-
-	/* will be treated as __user in tcp_getsockopt */
-	optval = (char __kernel __force *)uoptval;
-	option = (int __kernel __force *)uoption;
+	struct sock *ssk;
 
 	pr_debug("msk=%p", msk);
 
@@ -825,12 +829,18 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	 */
 	lock_sock(sk);
 	ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE);
-	if (!IS_ERR(ssock)) {
-		pr_debug("subflow=%p", ssock->sk);
-		ret = kernel_getsockopt(ssock, level, optname, optval, option);
+	if (IS_ERR(ssock)) {
+		release_sock(sk);
+		return ret;
 	}
+
+	ssk = ssock->sk;
+	sock_hold(ssk);
 	release_sock(sk);
 
+	ret = tcp_getsockopt(ssk, level, optname, optval, option);
+	sock_put(ssk);
+
 	return ret;
 }
 
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 1662e1178949..65122edf60aa 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -186,6 +186,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
 
+	if (tcp_rsk(req)->is_mptcp == 0)
+		goto create_child;
+
 	/* if the sk is MP_CAPABLE, we try to fetch the client key */
 	subflow_req = mptcp_subflow_rsk(req);
 	if (subflow_req->mp_capable) {
@@ -582,9 +585,9 @@ subflow_default_af_ops(struct sock *sk)
 	return &subflow_specific;
 }
 
-void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped)
-{
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
+void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
+{
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_connection_sock_af_ops *target;
@@ -599,8 +602,8 @@ void mptcp_handle_ipv6_mapped(struct sock *sk, bool mapped)
 
 	subflow->icsk_af_ops = icsk->icsk_af_ops;
 	icsk->icsk_af_ops = target;
-#endif
 }
+#endif
 
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 {
@@ -621,7 +624,9 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 	 */
 	sf->sk->sk_net_refcnt = 1;
 	get_net(net);
+#ifdef CONFIG_PROC_FS
 	this_cpu_add(*net->core.sock_inuse, 1);
+#endif
 	err = tcp_set_ulp(sf->sk, "mptcp");
 	release_sock(sf->sk);
 
@@ -767,7 +772,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
 	struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk);
 	struct mptcp_subflow_context *new_ctx;
 
-	if (!subflow_req->mp_capable) {
+	if (!tcp_rsk(req)->is_mptcp || !subflow_req->mp_capable) {
 		subflow_ulp_fallback(newsk, old_ctx);
 		return;
 	}
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index cf895bc80871..69c107f9ba8d 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1483,31 +1483,34 @@ ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = {
 };
 
 static int
-dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
+ip_set_dump_start(struct netlink_callback *cb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
 	int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
 	struct nlattr *cda[IPSET_ATTR_CMD_MAX + 1];
 	struct nlattr *attr = (void *)nlh + min_len;
+	struct sk_buff *skb = cb->skb;
+	struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk));
 	u32 dump_type;
-	ip_set_id_t index;
 	int ret;
 
 	ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr,
 			nlh->nlmsg_len - min_len,
 			ip_set_dump_policy, NULL);
 	if (ret)
-		return ret;
+		goto error;
 
 	cb->args[IPSET_CB_PROTO] = nla_get_u8(cda[IPSET_ATTR_PROTOCOL]);
 	if (cda[IPSET_ATTR_SETNAME]) {
+		ip_set_id_t index;
 		struct ip_set *set;
 
 		set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]),
 				      &index);
-		if (!set)
-			return -ENOENT;
-
+		if (!set) {
+			ret = -ENOENT;
+			goto error;
+		}
 		dump_type = DUMP_ONE;
 		cb->args[IPSET_CB_INDEX] = index;
 	} else {
@@ -1523,10 +1526,17 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 	cb->args[IPSET_CB_DUMP] = dump_type;
 
 	return 0;
+
+error:
+	/* We have to create and send the error message manually :-( */
+	if (nlh->nlmsg_flags & NLM_F_ACK) {
+		netlink_ack(cb->skb, nlh, ret, NULL);
+	}
+	return ret;
 }
 
 static int
-ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
+ip_set_dump_do(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	ip_set_id_t index = IPSET_INVALID_ID, max;
 	struct ip_set *set = NULL;
@@ -1537,18 +1547,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
 	bool is_destroyed;
 	int ret = 0;
 
-	if (!cb->args[IPSET_CB_DUMP]) {
-		ret = dump_init(cb, inst);
-		if (ret < 0) {
-			nlh = nlmsg_hdr(cb->skb);
-			/* We have to create and send the error message
-			 * manually :-(
-			 */
-			if (nlh->nlmsg_flags & NLM_F_ACK)
-				netlink_ack(cb->skb, nlh, ret, NULL);
-			return ret;
-		}
-	}
+	if (!cb->args[IPSET_CB_DUMP])
+		return -EINVAL;
 
 	if (cb->args[IPSET_CB_INDEX] >= inst->ip_set_max)
 		goto out;
@@ -1684,7 +1684,8 @@ static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 
 	{
 		struct netlink_dump_control c = {
-			.dump = ip_set_dump_start,
+			.start = ip_set_dump_start,
+			.dump = ip_set_dump_do,
 			.done = ip_set_dump_done,
 		};
 		return netlink_dump_start(ctnl, skb, nlh, &c);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f4c4b467c87e..d1305423640f 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2248,8 +2248,7 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
 	BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
 	nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
 
-	hash = kvmalloc_array(nr_slots, sizeof(struct hlist_nulls_head),
-			      GFP_KERNEL | __GFP_ZERO);
+	hash = kvcalloc(nr_slots, sizeof(struct hlist_nulls_head), GFP_KERNEL);
 
 	if (hash && nulls)
 		for (i = 0; i < nr_slots; i++)
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 7e91989a1b55..8af28e10b4e6 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -529,9 +529,9 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
 static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
 					  struct net_device *dev)
 {
-	nf_flow_table_offload_flush(flowtable);
 	nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
 	flush_delayed_work(&flowtable->gc_work);
+	nf_flow_table_offload_flush(flowtable);
 }
 
 void nf_flow_table_cleanup(struct net_device *dev)
@@ -553,6 +553,7 @@ void nf_flow_table_free(struct nf_flowtable *flow_table)
 	cancel_delayed_work_sync(&flow_table->gc_work);
 	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
 	nf_flow_table_iterate(flow_table, nf_flow_offload_gc_step, flow_table);
+	nf_flow_table_offload_flush(flow_table);
 	rhashtable_destroy(&flow_table->rhashtable);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_free);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index c8b70ffeef0c..83e1db37c3b0 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -675,6 +675,7 @@ static void flow_offload_work_del(struct flow_offload_work *offload)
 {
 	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL);
 	flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY);
+	set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags);
 }
 
 static void flow_offload_tuple_stats(struct flow_offload_work *offload,
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index ce70c2576bb2..e27c6c5ba9df 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -939,14 +939,14 @@ EXPORT_SYMBOL(xt_check_entry_offsets);
  *
  * @size: number of entries
  *
- * Return: NULL or kmalloc'd or vmalloc'd array
+ * Return: NULL or zeroed kmalloc'd or vmalloc'd array
  */
 unsigned int *xt_alloc_entry_offsets(unsigned int size)
 {
 	if (size > XT_MAX_TABLE_SIZE / sizeof(unsigned int))
 		return NULL;
 
-	return kvmalloc_array(size, sizeof(unsigned int), GFP_KERNEL | __GFP_ZERO);
+	return kvcalloc(size, sizeof(unsigned int), GFP_KERNEL);
 
 }
 EXPORT_SYMBOL(xt_alloc_entry_offsets);
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 781e0b482189..0a9708004e20 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -103,7 +103,7 @@ static DEFINE_SPINLOCK(recent_lock);
 static DEFINE_MUTEX(recent_mutex);
 
 #ifdef CONFIG_PROC_FS
-static const struct file_operations recent_mt_fops;
+static const struct proc_ops recent_mt_proc_ops;
 #endif
 
 static u_int32_t hash_rnd __read_mostly;
@@ -405,7 +405,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par,
 		goto out;
 	}
 	pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent,
-		  &recent_mt_fops, t);
+			       &recent_mt_proc_ops, t);
 	if (pde == NULL) {
 		recent_table_free(t);
 		ret = -ENOMEM;
@@ -616,13 +616,12 @@ recent_mt_proc_write(struct file *file, const char __user *input,
 	return size + 1;
 }
 
-static const struct file_operations recent_mt_fops = {
-	.open    = recent_seq_open,
-	.read    = seq_read,
-	.write   = recent_mt_proc_write,
-	.release = seq_release_private,
-	.owner   = THIS_MODULE,
-	.llseek = seq_lseek,
+static const struct proc_ops recent_mt_proc_ops = {
+	.proc_open	= recent_seq_open,
+	.proc_read	= seq_read,
+	.proc_write	= recent_mt_proc_write,
+	.proc_release	= seq_release_private,
+	.proc_lseek	= seq_lseek,
 };
 
 static int __net_init recent_proc_net_init(struct net *net)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9d3c4d2d893a..fe42f986cd94 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -194,6 +194,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 service_in_use:
 	write_unlock(&local->services_lock);
 	rxrpc_unuse_local(local);
+	rxrpc_put_local(local);
 	ret = -EADDRINUSE;
 error_unlock:
 	release_sock(&rx->sk);
@@ -899,6 +900,7 @@ static int rxrpc_release_sock(struct sock *sk)
 	rxrpc_purge_queue(&sk->sk_receive_queue);
 
 	rxrpc_unuse_local(rx->local);
+	rxrpc_put_local(rx->local);
 	rx->local = NULL;
 	key_put(rx->key);
 	rx->key = NULL;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5e99df80e80a..7d730c438404 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -490,6 +490,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
 	RXRPC_CALL_IS_INTR,		/* The call is interruptible */
+	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
 };
 
 /*
@@ -1021,6 +1022,16 @@ void rxrpc_unuse_local(struct rxrpc_local *);
 void rxrpc_queue_local(struct rxrpc_local *);
 void rxrpc_destroy_all_locals(struct rxrpc_net *);
 
+static inline bool __rxrpc_unuse_local(struct rxrpc_local *local)
+{
+	return atomic_dec_return(&local->active_users) == 0;
+}
+
+static inline bool __rxrpc_use_local(struct rxrpc_local *local)
+{
+	return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0;
+}
+
 /*
  * misc.c
  */
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index a31c18c09894..dbdbc4f18b5e 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -493,7 +493,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
 
-	if (conn)
+	if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		rxrpc_disconnect_call(call);
 	if (call->security)
 		call->security->free_call_crypto(call);
@@ -569,6 +569,7 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
 	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
 	struct rxrpc_net *rxnet = call->rxnet;
 
+	rxrpc_put_connection(call->conn);
 	rxrpc_put_peer(call->peer);
 	kfree(call->rxtx_buffer);
 	kfree(call->rxtx_annotations);
@@ -590,7 +591,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call)
 
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
 	ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
-	ASSERTCMP(call->conn, ==, NULL);
 
 	rxrpc_cleanup_ring(call);
 	rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 376370cd9285..ea7d4c21f889 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -785,6 +785,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	u32 cid;
 
 	spin_lock(&conn->channel_lock);
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 
 	cid = call->cid;
 	if (cid) {
@@ -792,7 +793,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 		chan = &conn->channels[channel];
 	}
 	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
-	call->conn = NULL;
 
 	/* Calls that have never actually been assigned a channel can simply be
 	 * discarded.  If the conn didn't get used either, it will follow
@@ -908,7 +908,6 @@ out:
 	spin_unlock(&rxnet->client_conn_cache_lock);
 out_2:
 	spin_unlock(&conn->channel_lock);
-	rxrpc_put_connection(conn);
 	_leave("");
 	return;
 
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 808a4723f868..06fcff2ebbba 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -438,16 +438,12 @@ again:
 /*
  * connection-level event processor
  */
-void rxrpc_process_connection(struct work_struct *work)
+static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
 {
-	struct rxrpc_connection *conn =
-		container_of(work, struct rxrpc_connection, processor);
 	struct sk_buff *skb;
 	u32 abort_code = RX_PROTOCOL_ERROR;
 	int ret;
 
-	rxrpc_see_connection(conn);
-
 	if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
 		rxrpc_secure_connection(conn);
 
@@ -475,18 +471,32 @@ void rxrpc_process_connection(struct work_struct *work)
 		}
 	}
 
-out:
-	rxrpc_put_connection(conn);
-	_leave("");
 	return;
 
 requeue_and_leave:
 	skb_queue_head(&conn->rx_queue, skb);
-	goto out;
+	return;
 
 protocol_error:
 	if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
 		goto requeue_and_leave;
 	rxrpc_free_skb(skb, rxrpc_skb_freed);
-	goto out;
+	return;
+}
+
+void rxrpc_process_connection(struct work_struct *work)
+{
+	struct rxrpc_connection *conn =
+		container_of(work, struct rxrpc_connection, processor);
+
+	rxrpc_see_connection(conn);
+
+	if (__rxrpc_use_local(conn->params.local)) {
+		rxrpc_do_process_connection(conn);
+		rxrpc_unuse_local(conn->params.local);
+	}
+
+	rxrpc_put_connection(conn);
+	_leave("");
+	return;
 }
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 38d718e90dc6..c0b3154f7a7e 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -171,6 +171,8 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
 
 	_enter("%d,%x", conn->debug_id, call->cid);
 
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+
 	if (rcu_access_pointer(chan->call) == call) {
 		/* Save the result of the call so that we can repeat it if necessary
 		 * through the channel, whilst disposing of the actual call record.
@@ -223,9 +225,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	__rxrpc_disconnect_call(conn, call);
 	spin_unlock(&conn->channel_lock);
 
-	call->conn = NULL;
 	conn->idle_timestamp = jiffies;
-	rxrpc_put_connection(conn);
 }
 
 /*
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 96d54e5bf7bc..ef10fbf71b15 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -599,10 +599,8 @@ ack:
 				  false, true,
 				  rxrpc_propose_ack_input_data);
 
-	if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) {
-		trace_rxrpc_notify_socket(call->debug_id, serial);
-		rxrpc_notify_socket(call);
-	}
+	trace_rxrpc_notify_socket(call->debug_id, serial);
+	rxrpc_notify_socket(call);
 
 unlock:
 	spin_unlock(&call->input_lock);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 36587260cabd..a6c1349e965d 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -364,11 +364,14 @@ void rxrpc_queue_local(struct rxrpc_local *local)
 void rxrpc_put_local(struct rxrpc_local *local)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id;
 	int n;
 
 	if (local) {
+		debug_id = local->debug_id;
+
 		n = atomic_dec_return(&local->usage);
-		trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
+		trace_rxrpc_local(debug_id, rxrpc_local_put, n, here);
 
 		if (n == 0)
 			call_rcu(&local->rcu, rxrpc_local_rcu);
@@ -380,14 +383,11 @@ void rxrpc_put_local(struct rxrpc_local *local)
  */
 struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	local = rxrpc_get_local_maybe(local);
 	if (!local)
 		return NULL;
 
-	au = atomic_fetch_add_unless(&local->active_users, 1, 0);
-	if (au == 0) {
+	if (!__rxrpc_use_local(local)) {
 		rxrpc_put_local(local);
 		return NULL;
 	}
@@ -401,14 +401,11 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
  */
 void rxrpc_unuse_local(struct rxrpc_local *local)
 {
-	unsigned int au;
-
 	if (local) {
-		au = atomic_dec_return(&local->active_users);
-		if (au == 0)
+		if (__rxrpc_unuse_local(local)) {
+			rxrpc_get_local(local);
 			rxrpc_queue_local(local);
-		else
-			rxrpc_put_local(local);
+		}
 	}
 }
 
@@ -465,7 +462,7 @@ static void rxrpc_local_processor(struct work_struct *work)
 
 	do {
 		again = false;
-		if (atomic_read(&local->active_users) == 0) {
+		if (!__rxrpc_use_local(local)) {
 			rxrpc_local_destroyer(local);
 			break;
 		}
@@ -479,6 +476,8 @@ static void rxrpc_local_processor(struct work_struct *work)
 			rxrpc_process_local_events(local);
 			again = true;
 		}
+
+		__rxrpc_unuse_local(local);
 	} while (again);
 
 	rxrpc_put_local(local);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 935bb60fff56..bad3d2420344 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -129,7 +129,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
 int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			  rxrpc_serial_t *_serial)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_ack_buffer *pkt;
 	struct msghdr msg;
 	struct kvec iov[2];
@@ -139,18 +139,14 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	int ret;
 	u8 reason;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
 	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
-	if (!pkt) {
-		rxrpc_put_connection(conn);
+	if (!pkt)
 		return -ENOMEM;
-	}
+
+	conn = call->conn;
 
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
@@ -244,7 +240,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	}
 
 out:
-	rxrpc_put_connection(conn);
 	kfree(pkt);
 	return ret;
 }
@@ -254,7 +249,7 @@ out:
  */
 int rxrpc_send_abort_packet(struct rxrpc_call *call)
 {
-	struct rxrpc_connection *conn = NULL;
+	struct rxrpc_connection *conn;
 	struct rxrpc_abort_buffer pkt;
 	struct msghdr msg;
 	struct kvec iov[1];
@@ -271,13 +266,11 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	    test_bit(RXRPC_CALL_TX_LAST, &call->flags))
 		return 0;
 
-	spin_lock_bh(&call->lock);
-	if (call->conn)
-		conn = rxrpc_get_connection_maybe(call->conn);
-	spin_unlock_bh(&call->lock);
-	if (!conn)
+	if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
 		return -ECONNRESET;
 
+	conn = call->conn;
+
 	msg.msg_name	= &call->peer->srx.transport;
 	msg.msg_namelen	= call->peer->srx.transport_len;
 	msg.msg_control	= NULL;
@@ -312,8 +305,6 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
 	rxrpc_tx_backoff(call, ret);
-
-	rxrpc_put_connection(conn);
 	return ret;
 }
 
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 48f67a9b1037..923b263c401b 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -364,27 +364,31 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
 		if (!rxrpc_get_peer_maybe(peer))
 			continue;
 
-		spin_unlock_bh(&rxnet->peer_hash_lock);
-
-		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
-		slot = keepalive_at - base;
-		_debug("%02x peer %u t=%d {%pISp}",
-		       cursor, peer->debug_id, slot, &peer->srx.transport);
+		if (__rxrpc_use_local(peer->local)) {
+			spin_unlock_bh(&rxnet->peer_hash_lock);
+
+			keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
+			slot = keepalive_at - base;
+			_debug("%02x peer %u t=%d {%pISp}",
+			       cursor, peer->debug_id, slot, &peer->srx.transport);
+
+			if (keepalive_at <= base ||
+			    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
+				rxrpc_send_keepalive(peer);
+				slot = RXRPC_KEEPALIVE_TIME;
+			}
 
-		if (keepalive_at <= base ||
-		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
-			rxrpc_send_keepalive(peer);
-			slot = RXRPC_KEEPALIVE_TIME;
+			/* A transmission to this peer occurred since last we
+			 * examined it so put it into the appropriate future
+			 * bucket.
+			 */
+			slot += cursor;
+			slot &= mask;
+			spin_lock_bh(&rxnet->peer_hash_lock);
+			list_add_tail(&peer->keepalive_link,
+				      &rxnet->peer_keepalive[slot & mask]);
+			rxrpc_unuse_local(peer->local);
 		}
-
-		/* A transmission to this peer occurred since last we examined
-		 * it so put it into the appropriate future bucket.
-		 */
-		slot += cursor;
-		slot &= mask;
-		spin_lock_bh(&rxnet->peer_hash_lock);
-		list_add_tail(&peer->keepalive_link,
-			      &rxnet->peer_keepalive[slot & mask]);
 		rxrpc_put_peer_locked(peer);
 	}
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index c22624131949..d36949d9382c 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -463,10 +463,8 @@ static u32 gen_tunnel(struct rsvp_head *data)
 
 static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = {
 	[TCA_RSVP_CLASSID]	= { .type = NLA_U32 },
-	[TCA_RSVP_DST]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
-	[TCA_RSVP_SRC]		= { .type = NLA_BINARY,
-				    .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_DST]		= { .len = RSVP_DST_LEN * sizeof(u32) },
+	[TCA_RSVP_SRC]		= { .len = RSVP_DST_LEN * sizeof(u32) },
 	[TCA_RSVP_PINFO]	= { .len = sizeof(struct tc_rsvp_pinfo) },
 };
 
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 3d4a1280352f..0323aee03de7 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -333,12 +333,31 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	cp->fall_through = p->fall_through;
 	cp->tp = tp;
 
+	if (tb[TCA_TCINDEX_HASH])
+		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
+
+	if (tb[TCA_TCINDEX_MASK])
+		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
+
+	if (tb[TCA_TCINDEX_SHIFT])
+		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
+
+	if (!cp->hash) {
+		/* Hash not specified, use perfect hash if the upper limit
+		 * of the hashing index is below the threshold.
+		 */
+		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
+			cp->hash = (cp->mask >> cp->shift) + 1;
+		else
+			cp->hash = DEFAULT_HASH_SIZE;
+	}
+
 	if (p->perfect) {
 		int i;
 
 		if (tcindex_alloc_perfect_hash(net, cp) < 0)
 			goto errout;
-		for (i = 0; i < cp->hash; i++)
+		for (i = 0; i < min(cp->hash, p->hash); i++)
 			cp->perfect[i].res = p->perfect[i].res;
 		balloc = 1;
 	}
@@ -350,15 +369,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (old_r)
 		cr = r->res;
 
-	if (tb[TCA_TCINDEX_HASH])
-		cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
-
-	if (tb[TCA_TCINDEX_MASK])
-		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
-
-	if (tb[TCA_TCINDEX_SHIFT])
-		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-
 	err = -EBUSY;
 
 	/* Hash already allocated, make sure that we still meet the
@@ -376,16 +386,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (tb[TCA_TCINDEX_FALL_THROUGH])
 		cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]);
 
-	if (!cp->hash) {
-		/* Hash not specified, use perfect hash if the upper limit
-		 * of the hashing index is below the threshold.
-		 */
-		if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD)
-			cp->hash = (cp->mask >> cp->shift) + 1;
-		else
-			cp->hash = DEFAULT_HASH_SIZE;
-	}
-
 	if (!cp->perfect && !cp->h)
 		cp->alloc_hash = cp->hash;
 
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index dba70377bbd9..a36974e9c601 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -377,7 +377,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 	if (mask != q->tab_mask) {
 		struct sk_buff **ntab;
 
-		ntab = kvmalloc_array((mask + 1), sizeof(struct sk_buff *), GFP_KERNEL | __GFP_ZERO);
+		ntab = kvcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL);
 		if (!ntab)
 			return -ENOMEM;
 
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 311181720d79..7511a68aadf0 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1428,10 +1428,10 @@ static ssize_t read_gssp(struct file *file, char __user *buf,
 	return len;
 }
 
-static const struct file_operations use_gss_proxy_ops = {
-	.open = nonseekable_open,
-	.write = write_gssp,
-	.read = read_gssp,
+static const struct proc_ops use_gss_proxy_proc_ops = {
+	.proc_open	= nonseekable_open,
+	.proc_write	= write_gssp,
+	.proc_read	= read_gssp,
 };
 
 static int create_use_gss_proxy_proc_entry(struct net *net)
@@ -1442,7 +1442,7 @@ static int create_use_gss_proxy_proc_entry(struct net *net)
 	sn->use_gss_proxy = -1;
 	*p = proc_create_data("use-gss-proxy", S_IFREG | 0600,
 			      sn->proc_net_rpc,
-			      &use_gss_proxy_ops, net);
+			      &use_gss_proxy_proc_ops, net);
 	if (!*p)
 		return -ENOMEM;
 	init_gssp_clnt(sn);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index d996bf872a7c..375914c7a7b1 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1571,15 +1571,14 @@ static int cache_release_procfs(struct inode *inode, struct file *filp)
 	return cache_release(inode, filp, cd);
 }
 
-static const struct file_operations cache_file_operations_procfs = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.read		= cache_read_procfs,
-	.write		= cache_write_procfs,
-	.poll		= cache_poll_procfs,
-	.unlocked_ioctl	= cache_ioctl_procfs, /* for FIONREAD */
-	.open		= cache_open_procfs,
-	.release	= cache_release_procfs,
+static const struct proc_ops cache_channel_proc_ops = {
+	.proc_lseek	= no_llseek,
+	.proc_read	= cache_read_procfs,
+	.proc_write	= cache_write_procfs,
+	.proc_poll	= cache_poll_procfs,
+	.proc_ioctl	= cache_ioctl_procfs, /* for FIONREAD */
+	.proc_open	= cache_open_procfs,
+	.proc_release	= cache_release_procfs,
 };
 
 static int content_open_procfs(struct inode *inode, struct file *filp)
@@ -1596,11 +1595,11 @@ static int content_release_procfs(struct inode *inode, struct file *filp)
 	return content_release(inode, filp, cd);
 }
 
-static const struct file_operations content_file_operations_procfs = {
-	.open		= content_open_procfs,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= content_release_procfs,
+static const struct proc_ops content_proc_ops = {
+	.proc_open	= content_open_procfs,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= content_release_procfs,
 };
 
 static int open_flush_procfs(struct inode *inode, struct file *filp)
@@ -1634,12 +1633,12 @@ static ssize_t write_flush_procfs(struct file *filp,
 	return write_flush(filp, buf, count, ppos, cd);
 }
 
-static const struct file_operations cache_flush_operations_procfs = {
-	.open		= open_flush_procfs,
-	.read		= read_flush_procfs,
-	.write		= write_flush_procfs,
-	.release	= release_flush_procfs,
-	.llseek		= no_llseek,
+static const struct proc_ops cache_flush_proc_ops = {
+	.proc_open	= open_flush_procfs,
+	.proc_read	= read_flush_procfs,
+	.proc_write	= write_flush_procfs,
+	.proc_release	= release_flush_procfs,
+	.proc_lseek	= no_llseek,
 };
 
 static void remove_cache_proc_entries(struct cache_detail *cd)
@@ -1662,19 +1661,19 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
 		goto out_nomem;
 
 	p = proc_create_data("flush", S_IFREG | 0600,
-			     cd->procfs, &cache_flush_operations_procfs, cd);
+			     cd->procfs, &cache_flush_proc_ops, cd);
 	if (p == NULL)
 		goto out_nomem;
 
 	if (cd->cache_request || cd->cache_parse) {
 		p = proc_create_data("channel", S_IFREG | 0600, cd->procfs,
-				     &cache_file_operations_procfs, cd);
+				     &cache_channel_proc_ops, cd);
 		if (p == NULL)
 			goto out_nomem;
 	}
 	if (cd->cache_show) {
 		p = proc_create_data("content", S_IFREG | 0400, cd->procfs,
-				     &content_file_operations_procfs, cd);
+				     &content_proc_ops, cd);
 		if (p == NULL)
 			goto out_nomem;
 	}
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 7c74197c2ecf..c964b48eaaba 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -69,12 +69,11 @@ static int rpc_proc_open(struct inode *inode, struct file *file)
 	return single_open(file, rpc_proc_show, PDE_DATA(inode));
 }
 
-static const struct file_operations rpc_proc_fops = {
-	.owner = THIS_MODULE,
-	.open = rpc_proc_open,
-	.read  = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
+static const struct proc_ops rpc_proc_ops = {
+	.proc_open	= rpc_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
 };
 
 /*
@@ -281,19 +280,19 @@ EXPORT_SYMBOL_GPL(rpc_clnt_show_stats);
  */
 static inline struct proc_dir_entry *
 do_register(struct net *net, const char *name, void *data,
-	    const struct file_operations *fops)
+	    const struct proc_ops *proc_ops)
 {
 	struct sunrpc_net *sn;
 
 	dprintk("RPC:       registering /proc/net/rpc/%s\n", name);
 	sn = net_generic(net, sunrpc_net_id);
-	return proc_create_data(name, 0, sn->proc_net_rpc, fops, data);
+	return proc_create_data(name, 0, sn->proc_net_rpc, proc_ops, data);
 }
 
 struct proc_dir_entry *
 rpc_proc_register(struct net *net, struct rpc_stat *statp)
 {
-	return do_register(net, statp->program->name, statp, &rpc_proc_fops);
+	return do_register(net, statp->program->name, statp, &rpc_proc_ops);
 }
 EXPORT_SYMBOL_GPL(rpc_proc_register);
 
@@ -308,9 +307,9 @@ rpc_proc_unregister(struct net *net, const char *name)
 EXPORT_SYMBOL_GPL(rpc_proc_unregister);
 
 struct proc_dir_entry *
-svc_proc_register(struct net *net, struct svc_stat *statp, const struct file_operations *fops)
+svc_proc_register(struct net *net, struct svc_stat *statp, const struct proc_ops *proc_ops)
 {
-	return do_register(net, statp->program->pg_name, statp, fops);
+	return do_register(net, statp->program->pg_name, statp, proc_ops);
 }
 EXPORT_SYMBOL_GPL(svc_proc_register);
 
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index f93e917e0929..fa7bb5e060d0 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -212,7 +212,7 @@ static int xdp_umem_map_pages(struct xdp_umem *umem)
 
 static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
-	put_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
+	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
 
 	kfree(umem->pgs);
 	umem->pgs = NULL;
@@ -291,7 +291,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
 		return -ENOMEM;
 
 	down_read(&current->mm->mmap_sem);
-	npgs = get_user_pages(umem->address, umem->npgs,
+	npgs = pin_user_pages(umem->address, umem->npgs,
 			      gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
 	up_read(&current->mm->mmap_sem);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 297d1eb79e5c..dbda08ec566e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3189,7 +3189,7 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
 					    flags | XFRM_LOOKUP_QUEUE |
 					    XFRM_LOOKUP_KEEP_DST_REF);
 
-	if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE)
+	if (PTR_ERR(dst) == -EREMOTE)
 		return make_blackhole(net, dst_orig->ops->family, dst_orig);
 
 	if (IS_ERR(dst))
diff --git a/samples/kfifo/bytestream-example.c b/samples/kfifo/bytestream-example.c
index 9ca3e4400c98..c406f03ee551 100644
--- a/samples/kfifo/bytestream-example.c
+++ b/samples/kfifo/bytestream-example.c
@@ -142,11 +142,10 @@ static ssize_t fifo_read(struct file *file, char __user *buf,
 	return ret ? ret : copied;
 }
 
-static const struct file_operations fifo_fops = {
-	.owner		= THIS_MODULE,
-	.read		= fifo_read,
-	.write		= fifo_write,
-	.llseek		= noop_llseek,
+static const struct proc_ops fifo_proc_ops = {
+	.proc_read	= fifo_read,
+	.proc_write	= fifo_write,
+	.proc_lseek	= noop_llseek,
 };
 
 static int __init example_init(void)
@@ -169,7 +168,7 @@ static int __init example_init(void)
 		return -EIO;
 	}
 
-	if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) {
+	if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) {
 #ifdef DYNAMIC
 		kfifo_free(&test);
 #endif
diff --git a/samples/kfifo/inttype-example.c b/samples/kfifo/inttype-example.c
index 6cdeb72f83f1..78977fc4a23f 100644
--- a/samples/kfifo/inttype-example.c
+++ b/samples/kfifo/inttype-example.c
@@ -135,11 +135,10 @@ static ssize_t fifo_read(struct file *file, char __user *buf,
 	return ret ? ret : copied;
 }
 
-static const struct file_operations fifo_fops = {
-	.owner		= THIS_MODULE,
-	.read		= fifo_read,
-	.write		= fifo_write,
-	.llseek		= noop_llseek,
+static const struct proc_ops fifo_proc_ops = {
+	.proc_read	= fifo_read,
+	.proc_write	= fifo_write,
+	.proc_lseek	= noop_llseek,
 };
 
 static int __init example_init(void)
@@ -160,7 +159,7 @@ static int __init example_init(void)
 		return -EIO;
 	}
 
-	if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) {
+	if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) {
 #ifdef DYNAMIC
 		kfifo_free(&test);
 #endif
diff --git a/samples/kfifo/record-example.c b/samples/kfifo/record-example.c
index 79ae8bb04120..c507998a2617 100644
--- a/samples/kfifo/record-example.c
+++ b/samples/kfifo/record-example.c
@@ -149,11 +149,10 @@ static ssize_t fifo_read(struct file *file, char __user *buf,
 	return ret ? ret : copied;
 }
 
-static const struct file_operations fifo_fops = {
-	.owner		= THIS_MODULE,
-	.read		= fifo_read,
-	.write		= fifo_write,
-	.llseek		= noop_llseek,
+static const struct proc_ops fifo_proc_ops = {
+	.proc_read	= fifo_read,
+	.proc_write	= fifo_write,
+	.proc_lseek	= noop_llseek,
 };
 
 static int __init example_init(void)
@@ -176,7 +175,7 @@ static int __init example_init(void)
 		return -EIO;
 	}
 
-	if (proc_create(PROC_FIFO, 0, NULL, &fifo_fops) == NULL) {
+	if (proc_create(PROC_FIFO, 0, NULL, &fifo_proc_ops) == NULL) {
 #ifdef DYNAMIC
 		kfifo_free(&test);
 #endif
diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c
index ac5c8c17b1ff..3cc5e5921682 100644
--- a/samples/vfio-mdev/mbochs.c
+++ b/samples/vfio-mdev/mbochs.c
@@ -891,26 +891,10 @@ static void mbochs_release_dmabuf(struct dma_buf *buf)
 	mutex_unlock(&mdev_state->ops_lock);
 }
 
-static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
-{
-	struct mbochs_dmabuf *dmabuf = buf->priv;
-	struct page *page = dmabuf->pages[page_num];
-
-	return kmap(page);
-}
-
-static void mbochs_kunmap_dmabuf(struct dma_buf *buf, unsigned long page_num,
-				 void *vaddr)
-{
-	kunmap(vaddr);
-}
-
 static struct dma_buf_ops mbochs_dmabuf_ops = {
 	.map_dma_buf	  = mbochs_map_dmabuf,
 	.unmap_dma_buf	  = mbochs_unmap_dmabuf,
 	.release	  = mbochs_release_dmabuf,
-	.map		  = mbochs_kmap_dmabuf,
-	.unmap		  = mbochs_kunmap_dmabuf,
 	.mmap		  = mbochs_mmap_dmabuf,
 };
 
diff --git a/samples/vfio-mdev/mdpy-fb.c b/samples/vfio-mdev/mdpy-fb.c
index 2719bb259653..21dbf63d6e41 100644
--- a/samples/vfio-mdev/mdpy-fb.c
+++ b/samples/vfio-mdev/mdpy-fb.c
@@ -86,7 +86,7 @@ static void mdpy_fb_destroy(struct fb_info *info)
 		iounmap(info->screen_base);
 }
 
-static struct fb_ops mdpy_fb_ops = {
+static const struct fb_ops mdpy_fb_ops = {
 	.owner		= THIS_MODULE,
 	.fb_destroy	= mdpy_fb_destroy,
 	.fb_setcolreg	= mdpy_fb_setcolreg,
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index bc5f25763c1b..6cabf20ce66a 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -33,6 +33,10 @@ real-prereqs = $(filter-out $(PHONY), $^)
 escsq = $(subst $(squote),'\$(squote)',$1)
 
 ###
+# Quote a string to pass it to C files. foo => '"foo"'
+stringify = $(squote)$(quote)$1$(quote)$(squote)
+
+###
 # Easy method for doing a status message
        kecho := :
  quiet_kecho := echo
@@ -55,14 +59,13 @@ kecho := $($(quiet)kecho)
 # - stdin is piped in from the first prerequisite ($<) so one has
 #   to specify a valid file as first prerequisite (often the kbuild file)
 define filechk
-	$(Q)set -e;				\
-	mkdir -p $(dir $@);			\
-	{ $(filechk_$(1)); } > $@.tmp;		\
-	if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
-		rm -f $@.tmp;			\
-	else					\
-		$(kecho) '  UPD     $@';	\
-		mv -f $@.tmp $@;		\
+	$(Q)set -e;						\
+	mkdir -p $(dir $@);					\
+	trap "rm -f $(dot-target).tmp" EXIT;			\
+	{ $(filechk_$(1)); } > $(dot-target).tmp;		\
+	if [ ! -r $@ ] || ! cmp -s $@ $(dot-target).tmp; then	\
+		$(kecho) '  UPD     $@';			\
+		mv -f $(dot-target).tmp $@;			\
 	fi
 endef
 
@@ -160,12 +163,6 @@ ld-ifversion = $(shell [ $(ld-version) $(1) $(2) ] && echo $(3) || echo $(4))
 build := -f $(srctree)/scripts/Makefile.build obj
 
 ###
-# Shorthand for $(Q)$(MAKE) -f scripts/Makefile.modbuiltin obj=
-# Usage:
-# $(Q)$(MAKE) $(modbuiltin)=dir
-modbuiltin := -f $(srctree)/scripts/Makefile.modbuiltin obj
-
-###
 # Shorthand for $(Q)$(MAKE) -f scripts/Makefile.dtbinst obj=
 # Usage:
 # $(Q)$(MAKE) $(dtbinst)=dir
diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
index 9d07e59cbdf7..85334dc8c997 100644
--- a/scripts/Kconfig.include
+++ b/scripts/Kconfig.include
@@ -25,7 +25,7 @@ failure = $(if-success,$(1),n,y)
 
 # $(cc-option,<flag>)
 # Return y if the compiler supports <flag>, n otherwise
-cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /dev/null)
+cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -S -x c /dev/null -o /dev/null)
 
 # $(ld-option,<flag>)
 # Return y if the linker supports <flag>, n otherwise
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index b734ac8a654e..a562d695f0fa 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -66,7 +66,7 @@ lib-target := $(obj)/lib.a
 real-obj-y += $(obj)/lib-ksyms.o
 endif
 
-ifneq ($(strip $(real-obj-y) $(need-builtin)),)
+ifdef need-builtin
 builtin-target := $(obj)/built-in.a
 endif
 
@@ -372,7 +372,7 @@ $(obj)/%.asn1.c $(obj)/%.asn1.h: $(src)/%.asn1 $(objtree)/scripts/asn1_compiler
 # ---------------------------------------------------------------------------
 
 # To build objects in subdirs, we need to descend into the directories
-$(sort $(subdir-obj-y)): $(subdir-ym) ;
+$(obj)/%/built-in.a: $(obj)/% ;
 
 #
 # Rule to compile a set of .o files into one .a file (without symbol table)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 3fa32f83b2d7..d10f7a03e0ee 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -35,7 +35,11 @@ __subdir-y	:= $(patsubst %/,%,$(filter %/, $(obj-y)))
 subdir-y	+= $(__subdir-y)
 __subdir-m	:= $(patsubst %/,%,$(filter %/, $(obj-m)))
 subdir-m	+= $(__subdir-m)
+ifdef need-builtin
 obj-y		:= $(patsubst %/, %/built-in.a, $(obj-y))
+else
+obj-y		:= $(filter-out %/, $(obj-y))
+endif
 obj-m		:= $(filter-out %/, $(obj-m))
 
 # Subdirectories we need to descend into
@@ -80,12 +84,14 @@ multi-used-m	:= $(addprefix $(obj)/,$(multi-used-m))
 subdir-ym	:= $(addprefix $(obj)/,$(subdir-ym))
 
 # Finds the multi-part object the current object will be linked into.
-# If the object belongs to two or more multi-part objects, all of them are
-# concatenated with a colon separator.
-modname-multi = $(subst $(space),:,$(sort $(foreach m,$(multi-used),\
-		$(if $(filter $*.o, $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m))),$(m:.o=)))))
+# If the object belongs to two or more multi-part objects, list them all.
+modname-multi = $(sort $(foreach m,$(multi-used),\
+		$(if $(filter $*.o, $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m))),$(m:.o=))))
+
+__modname = $(if $(modname-multi),$(modname-multi),$(basetarget))
 
-modname = $(if $(modname-multi),$(modname-multi),$(basetarget))
+modname = $(subst $(space),:,$(__modname))
+modfile = $(addprefix $(obj)/,$(__modname))
 
 # target with $(obj)/ and its suffix stripped
 target-stem = $(basename $(patsubst $(obj)/%,%,$@))
@@ -93,9 +99,10 @@ target-stem = $(basename $(patsubst $(obj)/%,%,$@))
 # These flags are needed for modversions and compiling, so we define them here
 # $(modname_flags) defines KBUILD_MODNAME as the name of the module it will
 # end up in (or would, if it gets compiled in)
-name-fix = $(squote)$(quote)$(subst $(comma),_,$(subst -,_,$1))$(quote)$(squote)
+name-fix = $(call stringify,$(subst $(comma),_,$(subst -,_,$1)))
 basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
 modname_flags  = -DKBUILD_MODNAME=$(call name-fix,$(modname))
+modfile_flags  = -DKBUILD_MODFILE=$(call stringify,$(modfile))
 
 orig_c_flags   = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) \
                  $(ccflags-y) $(CFLAGS_$(target-stem).o)
@@ -154,7 +161,7 @@ quiet_modtag = $(if $(part-of-module),[M],   )
 modkern_cflags =                                          \
 	$(if $(part-of-module),                           \
 		$(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE), \
-		$(KBUILD_CFLAGS_KERNEL) $(CFLAGS_KERNEL))
+		$(KBUILD_CFLAGS_KERNEL) $(CFLAGS_KERNEL) $(modfile_flags))
 
 modkern_aflags = $(if $(part-of-module),				\
 			$(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE),	\
diff --git a/scripts/Makefile.modbuiltin b/scripts/Makefile.modbuiltin
deleted file mode 100644
index 7d4711b88656..000000000000
--- a/scripts/Makefile.modbuiltin
+++ /dev/null
@@ -1,57 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-# ==========================================================================
-# Generating modules.builtin
-# ==========================================================================
-
-src := $(obj)
-
-PHONY := __modbuiltin
-__modbuiltin:
-
-include include/config/auto.conf
-# tristate.conf sets tristate variables to uppercase 'Y' or 'M'
-# That way, we get the list of built-in modules in obj-Y
-include include/config/tristate.conf
-
-include scripts/Kbuild.include
-
-ifdef building_out_of_srctree
-# Create output directory if not already present
-_dummy := $(shell [ -d $(obj) ] || mkdir -p $(obj))
-endif
-
-# The filename Kbuild has precedence over Makefile
-kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src))
-kbuild-file := $(if $(wildcard $(kbuild-dir)/Kbuild),$(kbuild-dir)/Kbuild,$(kbuild-dir)/Makefile)
-include $(kbuild-file)
-
-include scripts/Makefile.lib
-__subdir-Y     := $(patsubst %/,%,$(filter %/, $(obj-Y)))
-subdir-Y       += $(__subdir-Y)
-subdir-ym      := $(sort $(subdir-y) $(subdir-Y) $(subdir-m))
-subdir-ym      := $(addprefix $(obj)/,$(subdir-ym))
-obj-Y          := $(addprefix $(obj)/,$(obj-Y))
-
-modbuiltin-subdirs := $(patsubst %,%/modules.builtin, $(subdir-ym))
-modbuiltin-mods    := $(filter %.ko, $(obj-Y:.o=.ko))
-modbuiltin-target  := $(obj)/modules.builtin
-
-__modbuiltin: $(modbuiltin-target) $(subdir-ym)
-	@:
-
-$(modbuiltin-target): $(subdir-ym) FORCE
-	$(Q)(for m in $(modbuiltin-mods); do echo $$m; done;	\
-	cat /dev/null $(modbuiltin-subdirs)) > $@
-
-PHONY += FORCE
-
-FORCE:
-
-# Descending
-# ---------------------------------------------------------------------------
-
-PHONY += $(subdir-ym)
-$(subdir-ym):
-	$(Q)$(MAKE) $(modbuiltin)=$@
-
-.PHONY: $(PHONY)
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 69897d5d3a70..b4d3f2d122ac 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -90,7 +90,6 @@ quiet_cmd_modpost = MODPOST $(words $(modules)) modules
       cmd_modpost = sed 's/ko$$/o/' $(MODORDER) | $(MODPOST)
 
 __modpost:
-	@$(kecho) '  Building modules, stage 2.'
 	$(call cmd,modpost)
 ifneq ($(KBUILD_MODPOST_NOFINAL),1)
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal
diff --git a/scripts/coccinelle/free/devm_free.cocci b/scripts/coccinelle/free/devm_free.cocci
index 9330d4294b74..3357bf4dbd7c 100644
--- a/scripts/coccinelle/free/devm_free.cocci
+++ b/scripts/coccinelle/free/devm_free.cocci
@@ -91,8 +91,6 @@ position p;
 |
  kzfree@p(x)
 |
- __krealloc@p(x, ...)
-|
  krealloc@p(x, ...)
 |
  free_pages@p(x, ...)
@@ -116,8 +114,6 @@ position p != safe.p;
 |
 * kzfree@p(x)
 |
-* __krealloc@p(x, ...)
-|
 * krealloc@p(x, ...)
 |
 * free_pages@p(x, ...)
diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c
index d7986ee18012..756f0fa9203f 100644
--- a/scripts/dtc/checks.c
+++ b/scripts/dtc/checks.c
@@ -691,6 +691,11 @@ static void check_alias_paths(struct check *c, struct dt_info *dti,
 		return;
 
 	for_each_property(node, prop) {
+		if (streq(prop->name, "phandle")
+		    || streq(prop->name, "linux,phandle")) {
+			continue;
+		}
+
 		if (!prop->val.val || !get_node_by_path(dti->dt, prop->val.val)) {
 			FAIL_PROP(c, dti, node, prop, "aliases property is not a valid node (%s)",
 				  prop->val.val);
diff --git a/scripts/dtc/dtc-parser.y b/scripts/dtc/dtc-parser.y
index 2ed4dc1f07fd..40dcf4f149da 100644
--- a/scripts/dtc/dtc-parser.y
+++ b/scripts/dtc/dtc-parser.y
@@ -2,6 +2,8 @@
 /*
  * (C) Copyright David Gibson <dwg@au1.ibm.com>, IBM Corporation.  2005.
  */
+%locations
+
 %{
 #include <stdio.h>
 #include <inttypes.h>
@@ -17,6 +19,8 @@ extern void yyerror(char const *s);
 		treesource_error = true; \
 	} while (0)
 
+#define YYERROR_CALL(msg) yyerror(msg)
+
 extern struct dt_info *parser_output;
 extern bool treesource_error;
 %}
diff --git a/scripts/dtc/fstree.c b/scripts/dtc/fstree.c
index 9871689b4afb..5e59594ab301 100644
--- a/scripts/dtc/fstree.c
+++ b/scripts/dtc/fstree.c
@@ -30,7 +30,7 @@ static struct node *read_fstree(const char *dirname)
 
 		tmpname = join_path(dirname, de->d_name);
 
-		if (lstat(tmpname, &st) < 0)
+		if (stat(tmpname, &st) < 0)
 			die("stat(%s): %s\n", tmpname, strerror(errno));
 
 		if (S_ISREG(st.st_mode)) {
diff --git a/scripts/dtc/libfdt/fdt.c b/scripts/dtc/libfdt/fdt.c
index 179168ec63e9..d6ce7c052dc8 100644
--- a/scripts/dtc/libfdt/fdt.c
+++ b/scripts/dtc/libfdt/fdt.c
@@ -15,8 +15,10 @@
  * that the given buffer contains what appears to be a flattened
  * device tree with sane information in its header.
  */
-int fdt_ro_probe_(const void *fdt)
+int32_t fdt_ro_probe_(const void *fdt)
 {
+	uint32_t totalsize = fdt_totalsize(fdt);
+
 	if (fdt_magic(fdt) == FDT_MAGIC) {
 		/* Complete tree */
 		if (fdt_version(fdt) < FDT_FIRST_SUPPORTED_VERSION)
@@ -31,7 +33,10 @@ int fdt_ro_probe_(const void *fdt)
 		return -FDT_ERR_BADMAGIC;
 	}
 
-	return 0;
+	if (totalsize < INT32_MAX)
+		return totalsize;
+	else
+		return -FDT_ERR_TRUNCATED;
 }
 
 static int check_off_(uint32_t hdrsize, uint32_t totalsize, uint32_t off)
diff --git a/scripts/dtc/libfdt/fdt_addresses.c b/scripts/dtc/libfdt/fdt_addresses.c
index d8ba8ec60c6c..9a82cd0ba2f9 100644
--- a/scripts/dtc/libfdt/fdt_addresses.c
+++ b/scripts/dtc/libfdt/fdt_addresses.c
@@ -14,7 +14,7 @@
 static int fdt_cells(const void *fdt, int nodeoffset, const char *name)
 {
 	const fdt32_t *c;
-	int val;
+	uint32_t val;
 	int len;
 
 	c = fdt_getprop(fdt, nodeoffset, name, &len);
@@ -25,10 +25,10 @@ static int fdt_cells(const void *fdt, int nodeoffset, const char *name)
 		return -FDT_ERR_BADNCELLS;
 
 	val = fdt32_to_cpu(*c);
-	if ((val <= 0) || (val > FDT_MAX_NCELLS))
+	if (val > FDT_MAX_NCELLS)
 		return -FDT_ERR_BADNCELLS;
 
-	return val;
+	return (int)val;
 }
 
 int fdt_address_cells(const void *fdt, int nodeoffset)
@@ -36,6 +36,8 @@ int fdt_address_cells(const void *fdt, int nodeoffset)
 	int val;
 
 	val = fdt_cells(fdt, nodeoffset, "#address-cells");
+	if (val == 0)
+		return -FDT_ERR_BADNCELLS;
 	if (val == -FDT_ERR_NOTFOUND)
 		return 2;
 	return val;
diff --git a/scripts/dtc/libfdt/fdt_overlay.c b/scripts/dtc/libfdt/fdt_overlay.c
index e97f12b1a780..b310e49a698e 100644
--- a/scripts/dtc/libfdt/fdt_overlay.c
+++ b/scripts/dtc/libfdt/fdt_overlay.c
@@ -733,26 +733,36 @@ static int overlay_symbol_update(void *fdt, void *fdto)
 		/* keep end marker to avoid strlen() */
 		e = path + path_len;
 
-		/* format: /<fragment-name>/__overlay__/<relative-subnode-path> */
-
 		if (*path != '/')
 			return -FDT_ERR_BADVALUE;
 
 		/* get fragment name first */
 		s = strchr(path + 1, '/');
-		if (!s)
-			return -FDT_ERR_BADOVERLAY;
+		if (!s) {
+			/* Symbol refers to something that won't end
+			 * up in the target tree */
+			continue;
+		}
 
 		frag_name = path + 1;
 		frag_name_len = s - path - 1;
 
 		/* verify format; safe since "s" lies in \0 terminated prop */
 		len = sizeof("/__overlay__/") - 1;
-		if ((e - s) < len || memcmp(s, "/__overlay__/", len))
-			return -FDT_ERR_BADOVERLAY;
-
-		rel_path = s + len;
-		rel_path_len = e - rel_path;
+		if ((e - s) > len && (memcmp(s, "/__overlay__/", len) == 0)) {
+			/* /<fragment-name>/__overlay__/<relative-subnode-path> */
+			rel_path = s + len;
+			rel_path_len = e - rel_path - 1;
+		} else if ((e - s) == len
+			   && (memcmp(s, "/__overlay__", len - 1) == 0)) {
+			/* /<fragment-name>/__overlay__ */
+			rel_path = "";
+			rel_path_len = 0;
+		} else {
+			/* Symbol refers to something that won't end
+			 * up in the target tree */
+			continue;
+		}
 
 		/* find the fragment index in which the symbol lies */
 		ret = fdt_subnode_offset_namelen(fdto, 0, frag_name,
diff --git a/scripts/dtc/libfdt/fdt_ro.c b/scripts/dtc/libfdt/fdt_ro.c
index 6fd9ec170dbe..a5c2797cde65 100644
--- a/scripts/dtc/libfdt/fdt_ro.c
+++ b/scripts/dtc/libfdt/fdt_ro.c
@@ -33,19 +33,20 @@ static int fdt_nodename_eq_(const void *fdt, int offset,
 
 const char *fdt_get_string(const void *fdt, int stroffset, int *lenp)
 {
+	int32_t totalsize = fdt_ro_probe_(fdt);
 	uint32_t absoffset = stroffset + fdt_off_dt_strings(fdt);
 	size_t len;
 	int err;
 	const char *s, *n;
 
-	err = fdt_ro_probe_(fdt);
-	if (err != 0)
+	err = totalsize;
+	if (totalsize < 0)
 		goto fail;
 
 	err = -FDT_ERR_BADOFFSET;
-	if (absoffset >= fdt_totalsize(fdt))
+	if (absoffset >= totalsize)
 		goto fail;
-	len = fdt_totalsize(fdt) - absoffset;
+	len = totalsize - absoffset;
 
 	if (fdt_magic(fdt) == FDT_MAGIC) {
 		if (stroffset < 0)
@@ -288,7 +289,7 @@ const char *fdt_get_name(const void *fdt, int nodeoffset, int *len)
 	const char *nameptr;
 	int err;
 
-	if (((err = fdt_ro_probe_(fdt)) != 0)
+	if (((err = fdt_ro_probe_(fdt)) < 0)
 	    || ((err = fdt_check_node_offset_(fdt, nodeoffset)) < 0))
 			goto fail;
 
diff --git a/scripts/dtc/libfdt/libfdt.h b/scripts/dtc/libfdt/libfdt.h
index 7b5ffd13a887..8907b09b86cc 100644
--- a/scripts/dtc/libfdt/libfdt.h
+++ b/scripts/dtc/libfdt/libfdt.h
@@ -136,7 +136,7 @@ static inline uint32_t fdt32_ld(const fdt32_t *p)
 
 static inline void fdt32_st(void *property, uint32_t value)
 {
-	uint8_t *bp = property;
+	uint8_t *bp = (uint8_t *)property;
 
 	bp[0] = value >> 24;
 	bp[1] = (value >> 16) & 0xff;
@@ -160,7 +160,7 @@ static inline uint64_t fdt64_ld(const fdt64_t *p)
 
 static inline void fdt64_st(void *property, uint64_t value)
 {
-	uint8_t *bp = property;
+	uint8_t *bp = (uint8_t *)property;
 
 	bp[0] = value >> 56;
 	bp[1] = (value >> 48) & 0xff;
diff --git a/scripts/dtc/libfdt/libfdt_internal.h b/scripts/dtc/libfdt/libfdt_internal.h
index 7830e550c37a..058c7358d441 100644
--- a/scripts/dtc/libfdt/libfdt_internal.h
+++ b/scripts/dtc/libfdt/libfdt_internal.h
@@ -10,12 +10,12 @@
 #define FDT_ALIGN(x, a)		(((x) + (a) - 1) & ~((a) - 1))
 #define FDT_TAGALIGN(x)		(FDT_ALIGN((x), FDT_TAGSIZE))
 
-int fdt_ro_probe_(const void *fdt);
-#define FDT_RO_PROBE(fdt)			\
-	{ \
-		int err_; \
-		if ((err_ = fdt_ro_probe_(fdt)) != 0)	\
-			return err_; \
+int32_t fdt_ro_probe_(const void *fdt);
+#define FDT_RO_PROBE(fdt)					\
+	{							\
+		int32_t totalsize_;				\
+		if ((totalsize_ = fdt_ro_probe_(fdt)) < 0)	\
+			return totalsize_;			\
 	}
 
 int fdt_check_node_offset_(const void *fdt, int offset);
diff --git a/scripts/dtc/livetree.c b/scripts/dtc/livetree.c
index 0c039993953a..032df5878ccc 100644
--- a/scripts/dtc/livetree.c
+++ b/scripts/dtc/livetree.c
@@ -526,8 +526,7 @@ struct node *get_node_by_path(struct node *tree, const char *path)
 	p = strchr(path, '/');
 
 	for_each_child(tree, child) {
-		if (p && (strlen(child->name) == p-path) &&
-		    strprefixeq(path, p - path, child->name))
+		if (p && strprefixeq(path, p - path, child->name))
 			return get_node_by_path(child, p+1);
 		else if (!p && streq(path, child->name))
 			return child;
diff --git a/scripts/dtc/util.c b/scripts/dtc/util.c
index 48af961dcc8c..40274fb79236 100644
--- a/scripts/dtc/util.c
+++ b/scripts/dtc/util.c
@@ -13,6 +13,7 @@
 #include <stdarg.h>
 #include <string.h>
 #include <assert.h>
+#include <inttypes.h>
 
 #include <errno.h>
 #include <fcntl.h>
@@ -393,7 +394,7 @@ void utilfdt_print_data(const char *data, int len)
 
 		printf(" = <");
 		for (i = 0, len /= 4; i < len; i++)
-			printf("0x%08x%s", fdt32_to_cpu(cell[i]),
+			printf("0x%08" PRIx32 "%s", fdt32_to_cpu(cell[i]),
 			       i < (len - 1) ? " " : "");
 		printf(">");
 	} else {
diff --git a/scripts/dtc/util.h b/scripts/dtc/util.h
index ca5cb52928e3..5a4172dd0f84 100644
--- a/scripts/dtc/util.h
+++ b/scripts/dtc/util.h
@@ -12,7 +12,11 @@
  */
 
 #ifdef __GNUC__
+#ifdef __clang__
 #define PRINTF(i, j)	__attribute__((format (printf, i, j)))
+#else
+#define PRINTF(i, j)	__attribute__((format (gnu_printf, i, j)))
+#endif
 #define NORETURN	__attribute__((noreturn))
 #else
 #define PRINTF(i, j)
diff --git a/scripts/dtc/version_gen.h b/scripts/dtc/version_gen.h
index f2761e24cf40..6dba95d23207 100644
--- a/scripts/dtc/version_gen.h
+++ b/scripts/dtc/version_gen.h
@@ -1 +1 @@
-#define DTC_VERSION "DTC 1.5.0-g702c1b6c"
+#define DTC_VERSION "DTC 1.5.0-gc40aeb60"
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 2f1a59fa5169..fbeb62ae3401 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -47,16 +47,16 @@ build_gconfig: $(obj)/gconf
 build_xconfig: $(obj)/qconf
 
 localyesconfig localmodconfig: $(obj)/conf
-	$(Q)perl $(srctree)/$(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config
-	$(Q)if [ -f .config ]; then 					\
-			cmp -s .tmp.config .config ||			\
-			(mv -f .config .config.old.1;			\
-			 mv -f .tmp.config .config;			\
-			 $< $(silent) --oldconfig $(Kconfig);		\
-			 mv -f .config.old.1 .config.old)		\
-	else								\
-			mv -f .tmp.config .config;			\
-			$< $(silent) --oldconfig $(Kconfig);		\
+	$(Q)$(PERL) $(srctree)/$(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config
+	$(Q)if [ -f .config ]; then 				\
+		cmp -s .tmp.config .config ||			\
+		(mv -f .config .config.old.1;			\
+		 mv -f .tmp.config .config;			\
+		 $< $(silent) --oldconfig $(Kconfig);		\
+		 mv -f .config.old.1 .config.old)		\
+	else							\
+		mv -f .tmp.config .config;			\
+		$< $(silent) --oldconfig $(Kconfig);		\
 	fi
 	$(Q)rm -f .tmp.config
 
@@ -67,7 +67,7 @@ localyesconfig localmodconfig: $(obj)/conf
 #  deprecated for external use
 simple-targets := oldconfig allnoconfig allyesconfig allmodconfig \
 	alldefconfig randconfig listnewconfig olddefconfig syncconfig \
-	helpnewconfig
+	helpnewconfig yes2modconfig mod2yesconfig
 
 PHONY += $(simple-targets)
 
@@ -135,6 +135,8 @@ help:
 	@echo  '  allmodconfig	  - New config selecting modules when possible'
 	@echo  '  alldefconfig    - New config with all symbols set to default'
 	@echo  '  randconfig	  - New config with random answer to all options'
+	@echo  '  yes2modconfig	  - Change answers from yes to mod if possible'
+	@echo  '  mod2yesconfig	  - Change answers from mod to yes if possible'
 	@echo  '  listnewconfig   - List new options'
 	@echo  '  helpnewconfig   - List new options and help text'
 	@echo  '  olddefconfig	  - Same as oldconfig but sets new symbols to their'
diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 1f89bf1558ce..f6e548b8f795 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -34,6 +34,8 @@ enum input_mode {
 	listnewconfig,
 	helpnewconfig,
 	olddefconfig,
+	yes2modconfig,
+	mod2yesconfig,
 };
 static enum input_mode input_mode = oldaskconfig;
 
@@ -467,6 +469,8 @@ static struct option long_opts[] = {
 	{"listnewconfig",   no_argument,       NULL, listnewconfig},
 	{"helpnewconfig",   no_argument,       NULL, helpnewconfig},
 	{"olddefconfig",    no_argument,       NULL, olddefconfig},
+	{"yes2modconfig",   no_argument,       NULL, yes2modconfig},
+	{"mod2yesconfig",   no_argument,       NULL, mod2yesconfig},
 	{NULL, 0, NULL, 0}
 };
 
@@ -489,6 +493,8 @@ static void conf_usage(const char *progname)
 	printf("  --allmodconfig          New config where all options are answered with mod\n");
 	printf("  --alldefconfig          New config with all symbols set to default\n");
 	printf("  --randconfig            New config with random answer to all options\n");
+	printf("  --yes2modconfig         Change answers from yes to mod if possible\n");
+	printf("  --mod2yesconfig         Change answers from mod to yes if possible\n");
 }
 
 int main(int ac, char **av)
@@ -553,6 +559,8 @@ int main(int ac, char **av)
 		case listnewconfig:
 		case helpnewconfig:
 		case olddefconfig:
+		case yes2modconfig:
+		case mod2yesconfig:
 			break;
 		case '?':
 			conf_usage(progname);
@@ -587,6 +595,8 @@ int main(int ac, char **av)
 	case listnewconfig:
 	case helpnewconfig:
 	case olddefconfig:
+	case yes2modconfig:
+	case mod2yesconfig:
 		conf_read(NULL);
 		break;
 	case allnoconfig:
@@ -660,6 +670,12 @@ int main(int ac, char **av)
 		break;
 	case savedefconfig:
 		break;
+	case yes2modconfig:
+		conf_rewrite_mod_or_yes(def_y2m);
+		break;
+	case mod2yesconfig:
+		conf_rewrite_mod_or_yes(def_m2y);
+		break;
 	case oldaskconfig:
 		rootEntry = &rootmenu;
 		conf(&rootmenu);
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 3569d2dec37c..11f6c72c2eee 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -710,25 +710,6 @@ static struct conf_printer header_printer_cb =
 	.print_comment = header_print_comment,
 };
 
-/*
- * Tristate printer
- *
- * This printer is used when generating the `include/config/tristate.conf' file.
- */
-static void
-tristate_print_symbol(FILE *fp, struct symbol *sym, const char *value, void *arg)
-{
-
-	if (sym->type == S_TRISTATE && *value != 'n')
-		fprintf(fp, "%s%s=%c\n", CONFIG_, sym->name, (char)toupper(*value));
-}
-
-static struct conf_printer tristate_printer_cb =
-{
-	.print_symbol = tristate_print_symbol,
-	.print_comment = kconfig_print_comment,
-};
-
 static void conf_write_symbol(FILE *fp, struct symbol *sym,
 			      struct conf_printer *printer, void *printer_arg)
 {
@@ -1062,7 +1043,7 @@ int conf_write_autoconf(int overwrite)
 	struct symbol *sym;
 	const char *name;
 	const char *autoconf_name = conf_get_autoconfig_name();
-	FILE *out, *tristate, *out_h;
+	FILE *out, *out_h;
 	int i;
 
 	if (!overwrite && is_present(autoconf_name))
@@ -1077,23 +1058,13 @@ int conf_write_autoconf(int overwrite)
 	if (!out)
 		return 1;
 
-	tristate = fopen(".tmpconfig_tristate", "w");
-	if (!tristate) {
-		fclose(out);
-		return 1;
-	}
-
 	out_h = fopen(".tmpconfig.h", "w");
 	if (!out_h) {
 		fclose(out);
-		fclose(tristate);
 		return 1;
 	}
 
 	conf_write_heading(out, &kconfig_printer_cb, NULL);
-
-	conf_write_heading(tristate, &tristate_printer_cb, NULL);
-
 	conf_write_heading(out_h, &header_printer_cb, NULL);
 
 	for_all_symbols(i, sym) {
@@ -1101,15 +1072,11 @@ int conf_write_autoconf(int overwrite)
 		if (!(sym->flags & SYMBOL_WRITE) || !sym->name)
 			continue;
 
-		/* write symbol to auto.conf, tristate and header files */
+		/* write symbols to auto.conf and autoconf.h */
 		conf_write_symbol(out, sym, &kconfig_printer_cb, (void *)1);
-
-		conf_write_symbol(tristate, sym, &tristate_printer_cb, (void *)1);
-
 		conf_write_symbol(out_h, sym, &header_printer_cb, NULL);
 	}
 	fclose(out);
-	fclose(tristate);
 	fclose(out_h);
 
 	name = getenv("KCONFIG_AUTOHEADER");
@@ -1120,14 +1087,6 @@ int conf_write_autoconf(int overwrite)
 	if (rename(".tmpconfig.h", name))
 		return 1;
 
-	name = getenv("KCONFIG_TRISTATE");
-	if (!name)
-		name = "include/config/tristate.conf";
-	if (make_parent_dir(name))
-		return 1;
-	if (rename(".tmpconfig_tristate", name))
-		return 1;
-
 	if (make_parent_dir(autoconf_name))
 		return 1;
 	/*
@@ -1362,3 +1321,19 @@ bool conf_set_all_new_symbols(enum conf_def_mode mode)
 
 	return has_changed;
 }
+
+void conf_rewrite_mod_or_yes(enum conf_def_mode mode)
+{
+	struct symbol *sym;
+	int i;
+	tristate old_val = (mode == def_y2m) ? yes : mod;
+	tristate new_val = (mode == def_y2m) ? mod : yes;
+
+	for_all_symbols(i, sym) {
+		if (sym_get_type(sym) == S_TRISTATE &&
+		    sym->def[S_DEF_USER].tri == old_val) {
+			sym->def[S_DEF_USER].tri = new_val;
+			sym_add_change_count(1);
+		}
+	}
+}
diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c
index 9f1de58e9f0c..81ebf8108ca7 100644
--- a/scripts/kconfig/expr.c
+++ b/scripts/kconfig/expr.c
@@ -13,7 +13,6 @@
 
 #define DEBUG_EXPR	0
 
-static int expr_eq(struct expr *e1, struct expr *e2);
 static struct expr *expr_eliminate_yn(struct expr *e);
 
 struct expr *expr_alloc_symbol(struct symbol *sym)
@@ -250,7 +249,7 @@ void expr_eliminate_eq(struct expr **ep1, struct expr **ep2)
  * equals some operand in the other (operands do not need to appear in the same
  * order), recursively.
  */
-static int expr_eq(struct expr *e1, struct expr *e2)
+int expr_eq(struct expr *e1, struct expr *e2)
 {
 	int res, old_count;
 
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index 017843c9a4f4..5c3443692f34 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -191,7 +191,6 @@ enum prop_type {
 
 struct property {
 	struct property *next;     /* next property - null if last */
-	struct symbol *sym;        /* the symbol for which the property is associated */
 	enum prop_type type;       /* type of property */
 	const char *text;          /* the prompt value - P_PROMPT, P_MENU, P_COMMENT */
 	struct expr_value visible;
@@ -301,6 +300,7 @@ struct expr *expr_alloc_or(struct expr *e1, struct expr *e2);
 struct expr *expr_copy(const struct expr *org);
 void expr_free(struct expr *e);
 void expr_eliminate_eq(struct expr **ep1, struct expr **ep2);
+int expr_eq(struct expr *e1, struct expr *e2);
 tristate expr_calc_value(struct expr *e);
 struct expr *expr_trans_bool(struct expr *e);
 struct expr *expr_eliminate_dups(struct expr *e);
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index e36b342f1065..5527482c3077 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -18,6 +18,7 @@
 
 #include <stdio.h>
 #include <string.h>
+#include <strings.h>
 #include <unistd.h>
 #include <time.h>
 
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index 4fb16f316626..d4ca8297364f 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -34,6 +34,8 @@ enum conf_def_mode {
 	def_default,
 	def_yes,
 	def_mod,
+	def_y2m,
+	def_m2y,
 	def_no,
 	def_random
 };
@@ -52,6 +54,7 @@ const char *conf_get_configname(void);
 void sym_set_change_count(int count);
 void sym_add_change_count(int count);
 bool conf_set_all_new_symbols(enum conf_def_mode mode);
+void conf_rewrite_mod_or_yes(enum conf_def_mode mode);
 void set_all_choice_values(struct symbol *csym);
 
 /* confdata.c and expr.c */
@@ -112,7 +115,6 @@ struct symbol *sym_choice_default(struct symbol *sym);
 struct property *sym_get_range_prop(struct symbol *sym);
 const char *sym_get_string_default(struct symbol *sym);
 struct symbol *sym_check_deps(struct symbol *sym);
-struct property *prop_alloc(enum prop_type type, struct symbol *sym);
 struct symbol *prop_get_symbol(struct property *prop);
 
 static inline tristate sym_get_tristate_value(struct symbol *sym)
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index 49c26ea9dd98..4063dbc1b927 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -15,6 +15,7 @@
 #include <stdarg.h>
 #include <stdlib.h>
 #include <string.h>
+#include <strings.h>
 #include <signal.h>
 #include <unistd.h>
 
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index d9d16469859a..e436ba44c9c5 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -124,61 +124,76 @@ void menu_set_type(int type)
 		sym_type_name(sym->type), sym_type_name(type));
 }
 
-static struct property *menu_add_prop(enum prop_type type, char *prompt, struct expr *expr, struct expr *dep)
+static struct property *menu_add_prop(enum prop_type type, struct expr *expr,
+				      struct expr *dep)
 {
-	struct property *prop = prop_alloc(type, current_entry->sym);
+	struct property *prop;
 
+	prop = xmalloc(sizeof(*prop));
+	memset(prop, 0, sizeof(*prop));
+	prop->type = type;
+	prop->file = current_file;
+	prop->lineno = zconf_lineno();
 	prop->menu = current_entry;
 	prop->expr = expr;
 	prop->visible.expr = dep;
 
-	if (prompt) {
-		if (isspace(*prompt)) {
-			prop_warn(prop, "leading whitespace ignored");
-			while (isspace(*prompt))
-				prompt++;
-		}
-		if (current_entry->prompt && current_entry != &rootmenu)
-			prop_warn(prop, "prompt redefined");
+	/* append property to the prop list of symbol */
+	if (current_entry->sym) {
+		struct property **propp;
 
-		/* Apply all upper menus' visibilities to actual prompts. */
-		if(type == P_PROMPT) {
-			struct menu *menu = current_entry;
+		for (propp = &current_entry->sym->prop;
+		     *propp;
+		     propp = &(*propp)->next)
+			;
+		*propp = prop;
+	}
 
-			while ((menu = menu->parent) != NULL) {
-				struct expr *dup_expr;
+	return prop;
+}
 
-				if (!menu->visibility)
-					continue;
-				/*
-				 * Do not add a reference to the
-				 * menu's visibility expression but
-				 * use a copy of it.  Otherwise the
-				 * expression reduction functions
-				 * will modify expressions that have
-				 * multiple references which can
-				 * cause unwanted side effects.
-				 */
-				dup_expr = expr_copy(menu->visibility);
+struct property *menu_add_prompt(enum prop_type type, char *prompt,
+				 struct expr *dep)
+{
+	struct property *prop = menu_add_prop(type, NULL, dep);
 
-				prop->visible.expr
-					= expr_alloc_and(prop->visible.expr,
-							 dup_expr);
-			}
-		}
+	if (isspace(*prompt)) {
+		prop_warn(prop, "leading whitespace ignored");
+		while (isspace(*prompt))
+			prompt++;
+	}
+	if (current_entry->prompt)
+		prop_warn(prop, "prompt redefined");
 
-		current_entry->prompt = prop;
+	/* Apply all upper menus' visibilities to actual prompts. */
+	if (type == P_PROMPT) {
+		struct menu *menu = current_entry;
+
+		while ((menu = menu->parent) != NULL) {
+			struct expr *dup_expr;
+
+			if (!menu->visibility)
+				continue;
+			/*
+			 * Do not add a reference to the menu's visibility
+			 * expression but use a copy of it. Otherwise the
+			 * expression reduction functions will modify
+			 * expressions that have multiple references which
+			 * can cause unwanted side effects.
+			 */
+			dup_expr = expr_copy(menu->visibility);
+
+			prop->visible.expr = expr_alloc_and(prop->visible.expr,
+							    dup_expr);
+		}
 	}
+
+	current_entry->prompt = prop;
 	prop->text = prompt;
 
 	return prop;
 }
 
-struct property *menu_add_prompt(enum prop_type type, char *prompt, struct expr *dep)
-{
-	return menu_add_prop(type, prompt, NULL, dep);
-}
-
 void menu_add_visibility(struct expr *expr)
 {
 	current_entry->visibility = expr_alloc_and(current_entry->visibility,
@@ -187,12 +202,12 @@ void menu_add_visibility(struct expr *expr)
 
 void menu_add_expr(enum prop_type type, struct expr *expr, struct expr *dep)
 {
-	menu_add_prop(type, NULL, expr, dep);
+	menu_add_prop(type, expr, dep);
 }
 
 void menu_add_symbol(enum prop_type type, struct symbol *sym, struct expr *dep)
 {
-	menu_add_prop(type, NULL, expr_alloc_symbol(sym), dep);
+	menu_add_prop(type, expr_alloc_symbol(sym), dep);
 }
 
 void menu_add_option_modules(void)
@@ -326,12 +341,10 @@ void menu_finalize(struct menu *parent)
 			 * choice value symbols.
 			 */
 			parentdep = expr_alloc_symbol(sym);
-		} else if (parent->prompt)
-			/* Menu node for 'menu' */
-			parentdep = parent->prompt->visible.expr;
-		else
-			/* Menu node for 'if' */
+		} else {
+			/* Menu node for 'menu', 'if' */
 			parentdep = parent->dep;
+		}
 
 		/* For each child menu node... */
 		for (menu = parent->list; menu; menu = menu->next) {
@@ -698,6 +711,21 @@ const char *menu_get_help(struct menu *menu)
 		return "";
 }
 
+static void get_def_str(struct gstr *r, struct menu *menu)
+{
+	str_printf(r, "Defined at %s:%d\n",
+		   menu->file->name, menu->lineno);
+}
+
+static void get_dep_str(struct gstr *r, struct expr *expr, const char *prefix)
+{
+	if (!expr_is_yes(expr)) {
+		str_append(r, prefix);
+		expr_gstr_print(expr, r);
+		str_append(r, "\n");
+	}
+}
+
 static void get_prompt_str(struct gstr *r, struct property *prop,
 			   struct list_head *head)
 {
@@ -705,7 +733,20 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
 	struct menu *submenu[8], *menu, *location = NULL;
 	struct jump_key *jump = NULL;
 
-	str_printf(r, "Prompt: %s\n", prop->text);
+	str_printf(r, "  Prompt: %s\n", prop->text);
+
+	get_dep_str(r, prop->menu->dep, "  Depends on: ");
+	/*
+	 * Most prompts in Linux have visibility that exactly matches their
+	 * dependencies. For these, we print only the dependencies to improve
+	 * readability. However, prompts with inline "if" expressions and
+	 * prompts with a parent that has a "visible if" expression have
+	 * differing dependencies and visibility. In these rare cases, we
+	 * print both.
+	 */
+	if (!expr_eq(prop->menu->dep, prop->visible.expr))
+		get_dep_str(r, prop->visible.expr, "  Visible if: ");
+
 	menu = prop->menu->parent;
 	for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) {
 		bool accessible = menu_is_visible(menu);
@@ -755,18 +796,6 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
 	}
 }
 
-/*
- * get property of type P_SYMBOL
- */
-static struct property *get_symbol_prop(struct symbol *sym)
-{
-	struct property *prop = NULL;
-
-	for_all_properties(sym, prop, P_SYMBOL)
-		break;
-	return prop;
-}
-
 static void get_symbol_props_str(struct gstr *r, struct symbol *sym,
 				 enum prop_type tok, const char *prefix)
 {
@@ -806,32 +835,34 @@ static void get_symbol_str(struct gstr *r, struct symbol *sym,
 			}
 		}
 	}
-	for_all_prompts(sym, prop)
-		get_prompt_str(r, prop, head);
-
-	prop = get_symbol_prop(sym);
-	if (prop) {
-		str_printf(r, "  Defined at %s:%d\n", prop->menu->file->name,
-			prop->menu->lineno);
-		if (!expr_is_yes(prop->visible.expr)) {
-			str_append(r, "  Depends on: ");
-			expr_gstr_print(prop->visible.expr, r);
-			str_append(r, "\n");
+
+	/* Print the definitions with prompts before the ones without */
+	for_all_properties(sym, prop, P_SYMBOL) {
+		if (prop->menu->prompt) {
+			get_def_str(r, prop->menu);
+			get_prompt_str(r, prop->menu->prompt, head);
+		}
+	}
+
+	for_all_properties(sym, prop, P_SYMBOL) {
+		if (!prop->menu->prompt) {
+			get_def_str(r, prop->menu);
+			get_dep_str(r, prop->menu->dep, "  Depends on: ");
 		}
 	}
 
-	get_symbol_props_str(r, sym, P_SELECT, "  Selects: ");
+	get_symbol_props_str(r, sym, P_SELECT, "Selects: ");
 	if (sym->rev_dep.expr) {
-		expr_gstr_print_revdep(sym->rev_dep.expr, r, yes, "  Selected by [y]:\n");
-		expr_gstr_print_revdep(sym->rev_dep.expr, r, mod, "  Selected by [m]:\n");
-		expr_gstr_print_revdep(sym->rev_dep.expr, r, no, "  Selected by [n]:\n");
+		expr_gstr_print_revdep(sym->rev_dep.expr, r, yes, "Selected by [y]:\n");
+		expr_gstr_print_revdep(sym->rev_dep.expr, r, mod, "Selected by [m]:\n");
+		expr_gstr_print_revdep(sym->rev_dep.expr, r, no, "Selected by [n]:\n");
 	}
 
-	get_symbol_props_str(r, sym, P_IMPLY, "  Implies: ");
+	get_symbol_props_str(r, sym, P_IMPLY, "Implies: ");
 	if (sym->implied.expr) {
-		expr_gstr_print_revdep(sym->implied.expr, r, yes, "  Implied by [y]:\n");
-		expr_gstr_print_revdep(sym->implied.expr, r, mod, "  Implied by [m]:\n");
-		expr_gstr_print_revdep(sym->implied.expr, r, no, "  Implied by [n]:\n");
+		expr_gstr_print_revdep(sym->implied.expr, r, yes, "Implied by [y]:\n");
+		expr_gstr_print_revdep(sym->implied.expr, r, mod, "Implied by [m]:\n");
+		expr_gstr_print_revdep(sym->implied.expr, r, no, "Implied by [n]:\n");
 	}
 
 	str_append(r, "\n\n");
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index b7c1ef757178..daf1c1506ec4 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -8,6 +8,7 @@
 #define _GNU_SOURCE
 #endif
 #include <string.h>
+#include <strings.h>
 #include <stdlib.h>
 
 #include "lkc.h"
diff --git a/scripts/kconfig/parser.y b/scripts/kconfig/parser.y
index b3eff9613cf8..708b6c4b13ca 100644
--- a/scripts/kconfig/parser.y
+++ b/scripts/kconfig/parser.y
@@ -90,7 +90,6 @@ static struct menu *current_menu, *current_entry;
 %left T_LESS T_LESS_EQUAL T_GREATER T_GREATER_EQUAL
 %nonassoc T_NOT
 
-%type <string> prompt
 %type <symbol> nonconst_symbol
 %type <symbol> symbol
 %type <type> type logic_type default
@@ -113,7 +112,7 @@ input: mainmenu_stmt stmt_list | stmt_list;
 
 /* mainmenu entry */
 
-mainmenu_stmt: T_MAINMENU prompt T_EOL
+mainmenu_stmt: T_MAINMENU T_WORD_QUOTE T_EOL
 {
 	menu_add_prompt(P_MENU, $2, NULL);
 };
@@ -181,7 +180,7 @@ config_option: type prompt_stmt_opt T_EOL
 		$1);
 };
 
-config_option: T_PROMPT prompt if_expr T_EOL
+config_option: T_PROMPT T_WORD_QUOTE if_expr T_EOL
 {
 	menu_add_prompt(P_PROMPT, $2, $3);
 	printd(DEBUG_PARSE, "%s:%d:prompt\n", zconf_curname(), zconf_lineno());
@@ -265,7 +264,7 @@ choice_option_list:
 	| choice_option_list help
 ;
 
-choice_option: T_PROMPT prompt if_expr T_EOL
+choice_option: T_PROMPT T_WORD_QUOTE if_expr T_EOL
 {
 	menu_add_prompt(P_PROMPT, $2, $3);
 	printd(DEBUG_PARSE, "%s:%d:prompt\n", zconf_curname(), zconf_lineno());
@@ -334,7 +333,7 @@ if_stmt: if_entry stmt_list if_end
 
 /* menu entry */
 
-menu: T_MENU prompt T_EOL
+menu: T_MENU T_WORD_QUOTE T_EOL
 {
 	menu_add_entry(NULL);
 	menu_add_prompt(P_MENU, $2, NULL);
@@ -363,7 +362,7 @@ menu_option_list:
 	| menu_option_list depends
 ;
 
-source_stmt: T_SOURCE prompt T_EOL
+source_stmt: T_SOURCE T_WORD_QUOTE T_EOL
 {
 	printd(DEBUG_PARSE, "%s:%d:source %s\n", zconf_curname(), zconf_lineno(), $2);
 	zconf_nextfile($2);
@@ -372,7 +371,7 @@ source_stmt: T_SOURCE prompt T_EOL
 
 /* comment entry */
 
-comment: T_COMMENT prompt T_EOL
+comment: T_COMMENT T_WORD_QUOTE T_EOL
 {
 	menu_add_entry(NULL);
 	menu_add_prompt(P_COMMENT, $2, NULL);
@@ -429,15 +428,11 @@ visible: T_VISIBLE if_expr T_EOL
 
 prompt_stmt_opt:
 	  /* empty */
-	| prompt if_expr
+	| T_WORD_QUOTE if_expr
 {
 	menu_add_prompt(P_PROMPT, $1, $2);
 };
 
-prompt:	  T_WORD
-	| T_WORD_QUOTE
-;
-
 end:	  T_ENDMENU T_EOL	{ $$ = "menu"; }
 	| T_ENDCHOICE T_EOL	{ $$ = "choice"; }
 	| T_ENDIF T_EOL		{ $$ = "if"; }
@@ -665,7 +660,7 @@ static void print_symbol(FILE *out, struct menu *menu)
 			break;
 		case P_SYMBOL:
 			fputs( "  symbol ", out);
-			fprintf(out, "%s\n", prop->sym->name);
+			fprintf(out, "%s\n", prop->menu->sym->name);
 			break;
 		default:
 			fprintf(out, "  unknown prop %d!\n", prop->type);
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 08d76d7b3b81..e2f8504f5a2d 100755
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -56,8 +56,6 @@ sub dprint {
     print STDERR @_;
 }
 
-my $config = ".config";
-
 my $uname = `uname -r`;
 chomp $uname;
 
@@ -374,7 +372,7 @@ if (defined($lsmod_file)) {
 	    $lsmod = "$dir/lsmod";
 	    last;
 	}
-}
+    }
     if (!defined($lsmod)) {
 	# try just the path
 	$lsmod = "lsmod";
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index f56eec5ea4c7..8d38b700b314 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -1273,28 +1273,6 @@ struct symbol *sym_check_deps(struct symbol *sym)
 	return sym2;
 }
 
-struct property *prop_alloc(enum prop_type type, struct symbol *sym)
-{
-	struct property *prop;
-	struct property **propp;
-
-	prop = xmalloc(sizeof(*prop));
-	memset(prop, 0, sizeof(*prop));
-	prop->type = type;
-	prop->sym = sym;
-	prop->file = current_file;
-	prop->lineno = zconf_lineno();
-
-	/* append property to the prop list of symbol */
-	if (sym) {
-		for (propp = &sym->prop; *propp; propp = &(*propp)->next)
-			;
-		*propp = prop;
-	}
-
-	return prop;
-}
-
 struct symbol *prop_get_symbol(struct property *prop)
 {
 	if (prop->expr && (prop->expr->type == E_SYMBOL ||
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index bbe9be2bf5ff..1919c311c149 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -250,6 +250,10 @@ ${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1
 
 info MODINFO modules.builtin.modinfo
 ${OBJCOPY} -j .modinfo -O binary vmlinux.o modules.builtin.modinfo
+info GEN modules.builtin
+# The second line aids cases where multiple modules share the same object.
+tr '\0' '\n' < modules.builtin.modinfo | sed -n 's/^[[:alnum:]:_]*\.file=//p' |
+	tr ' ' '\n' | uniq | sed -e 's:^:kernel/:' -e 's/$/.ko/' > modules.builtin
 
 btf_vmlinux_bin_o=""
 if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 6e892c93d104..7edfdb2f4497 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -12,6 +12,7 @@
  */
 
 #define _GNU_SOURCE
+#include <elf.h>
 #include <stdio.h>
 #include <ctype.h>
 #include <string.h>
@@ -729,12 +730,6 @@ static void handle_symbol(struct module *mod, struct elf_info *info,
 			break;
 		if (ignore_undef_symbol(info, symname))
 			break;
-/* cope with newer glibc (2.3.4 or higher) STT_ definition in elf.h */
-#if defined(STT_REGISTER) || defined(STT_SPARC_REGISTER)
-/* add compatibility with older glibc */
-#ifndef STT_SPARC_REGISTER
-#define STT_SPARC_REGISTER STT_REGISTER
-#endif
 		if (info->hdr->e_machine == EM_SPARC ||
 		    info->hdr->e_machine == EM_SPARCV9) {
 			/* Ignore register directives. */
@@ -747,7 +742,6 @@ static void handle_symbol(struct module *mod, struct elf_info *info,
 				symname = munged;
 			}
 		}
-#endif
 
 		mod->unres = alloc_symbol(symname,
 					  ELF_ST_BIND(sym->st_info) == STB_WEAK,
diff --git a/scripts/package/builddeb b/scripts/package/builddeb
index c4c580f547ef..6df3c9f8b2da 100755
--- a/scripts/package/builddeb
+++ b/scripts/package/builddeb
@@ -43,17 +43,66 @@ create_package() {
 
 	# Create the package
 	dpkg-gencontrol -p$pname -P"$pdir"
-	dpkg --build "$pdir" ..
+	dpkg-deb ${KDEB_COMPRESS:+-Z$KDEB_COMPRESS} --build "$pdir" ..
+}
+
+deploy_kernel_headers () {
+	pdir=$1
+
+	rm -rf $pdir
+
+	(
+		cd $srctree
+		find . arch/$SRCARCH -maxdepth 1 -name Makefile\*
+		find include scripts -type f -o -type l
+		find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform
+		find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f
+	) > debian/hdrsrcfiles
+
+	{
+		if is_enabled CONFIG_STACK_VALIDATION; then
+			echo tools/objtool/objtool
+		fi
+
+		find arch/$SRCARCH/include Module.symvers include scripts -type f
+
+		if is_enabled CONFIG_GCC_PLUGINS; then
+			find scripts/gcc-plugins -name \*.so
+		fi
+	} > debian/hdrobjfiles
+
+	destdir=$pdir/usr/src/linux-headers-$version
+	mkdir -p $destdir
+	tar -c -f - -C $srctree -T debian/hdrsrcfiles | tar -xf - -C $destdir
+	tar -c -f - -T debian/hdrobjfiles | tar -xf - -C $destdir
+	rm -f debian/hdrsrcfiles debian/hdrobjfiles
+
+	# copy .config manually to be where it's expected to be
+	cp $KCONFIG_CONFIG $destdir/.config
+
+	mkdir -p $pdir/lib/modules/$version/
+	ln -s /usr/src/linux-headers-$version $pdir/lib/modules/$version/build
+}
+
+deploy_libc_headers () {
+	pdir=$1
+
+	rm -rf $pdir
+
+	$MAKE -f $srctree/Makefile headers
+	$MAKE -f $srctree/Makefile headers_install INSTALL_HDR_PATH=$pdir/usr
+
+	# move asm headers to /usr/include/<libc-machine>/asm to match the structure
+	# used by Debian-based distros (to support multi-arch)
+	host_arch=$(dpkg-architecture -a$(cat debian/arch) -qDEB_HOST_MULTIARCH)
+	mkdir $pdir/usr/include/$host_arch
+	mv $pdir/usr/include/asm $pdir/usr/include/$host_arch/
 }
 
 version=$KERNELRELEASE
-tmpdir="$objtree/debian/tmp"
-kernel_headers_dir="$objtree/debian/hdrtmp"
-libc_headers_dir="$objtree/debian/headertmp"
-dbg_dir="$objtree/debian/dbgtmp"
+tmpdir=debian/linux-image
+dbg_dir=debian/linux-image-dbg
 packagename=linux-image-$version
-kernel_headers_packagename=linux-headers-$version
-libc_headers_packagename=linux-libc-dev
 dbg_packagename=$packagename-dbg
 
 if [ "$ARCH" = "um" ] ; then
@@ -77,15 +126,13 @@ esac
 BUILD_DEBUG=$(if_enabled_echo CONFIG_DEBUG_INFO Yes)
 
 # Setup the directory structure
-rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files
+rm -rf "$tmpdir" "$dbg_dir" debian/files
 mkdir -m 755 -p "$tmpdir/DEBIAN"
 mkdir -p "$tmpdir/lib" "$tmpdir/boot"
-mkdir -p "$kernel_headers_dir/lib/modules/$version/"
 
-# Build and install the kernel
+# Install the kernel
 if [ "$ARCH" = "um" ] ; then
 	mkdir -p "$tmpdir/usr/lib/uml/modules/$version" "$tmpdir/usr/bin" "$tmpdir/usr/share/doc/$packagename"
-	$MAKE linux
 	cp System.map "$tmpdir/usr/lib/uml/modules/$version/System.map"
 	cp $KCONFIG_CONFIG "$tmpdir/usr/share/doc/$packagename/config"
 	gzip "$tmpdir/usr/share/doc/$packagename/config"
@@ -129,16 +176,6 @@ if is_enabled CONFIG_MODULES; then
 	fi
 fi
 
-if [ "$ARCH" != "um" ]; then
-	$MAKE -f $srctree/Makefile headers
-	$MAKE -f $srctree/Makefile headers_install INSTALL_HDR_PATH="$libc_headers_dir/usr"
-	# move asm headers to /usr/include/<libc-machine>/asm to match the structure
-	# used by Debian-based distros (to support multi-arch)
-	host_arch=$(dpkg-architecture -a$(cat debian/arch) -qDEB_HOST_MULTIARCH)
-	mkdir $libc_headers_dir/usr/include/$host_arch
-	mv $libc_headers_dir/usr/include/asm $libc_headers_dir/usr/include/$host_arch/
-fi
-
 # Install the maintainer scripts
 # Note: hook scripts under /etc/kernel are also executed by official Debian
 # kernel packages, as well as kernel packages built using make-kpkg.
@@ -164,29 +201,12 @@ EOF
 	chmod 755 "$tmpdir/DEBIAN/$script"
 done
 
-# Build kernel header package
-(cd $srctree; find . -name Makefile\* -o -name Kconfig\* -o -name \*.pl) > "$objtree/debian/hdrsrcfiles"
-(cd $srctree; find arch/*/include include scripts -type f -o -type l) >> "$objtree/debian/hdrsrcfiles"
-(cd $srctree; find arch/$SRCARCH -name module.lds -o -name Kbuild.platforms -o -name Platform) >> "$objtree/debian/hdrsrcfiles"
-(cd $srctree; find $(find arch/$SRCARCH -name include -o -name scripts -type d) -type f) >> "$objtree/debian/hdrsrcfiles"
-if is_enabled CONFIG_STACK_VALIDATION; then
-	(cd $objtree; find tools/objtool -type f -executable) >> "$objtree/debian/hdrobjfiles"
-fi
-(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f) >> "$objtree/debian/hdrobjfiles"
-if is_enabled CONFIG_GCC_PLUGINS; then
-	(cd $objtree; find scripts/gcc-plugins -name \*.so -o -name gcc-common.h) >> "$objtree/debian/hdrobjfiles"
-fi
-destdir=$kernel_headers_dir/usr/src/linux-headers-$version
-mkdir -p "$destdir"
-(cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -)
-(cd $objtree; tar -c -f - -T -) < "$objtree/debian/hdrobjfiles" | (cd $destdir; tar -xf -)
-(cd $objtree; cp $KCONFIG_CONFIG $destdir/.config) # copy .config manually to be where it's expected to be
-ln -sf "/usr/src/linux-headers-$version" "$kernel_headers_dir/lib/modules/$version/build"
-rm -f "$objtree/debian/hdrsrcfiles" "$objtree/debian/hdrobjfiles"
-
 if [ "$ARCH" != "um" ]; then
-	create_package "$kernel_headers_packagename" "$kernel_headers_dir"
-	create_package "$libc_headers_packagename" "$libc_headers_dir"
+	deploy_kernel_headers debian/linux-headers
+	create_package linux-headers-$version debian/linux-headers
+
+	deploy_libc_headers debian/linux-libc-dev
+	create_package linux-libc-dev debian/linux-libc-dev
 fi
 
 create_package "$packagename" "$tmpdir"
diff --git a/scripts/spelling.txt b/scripts/spelling.txt
index 672b5931bc8d..ffa838f3a2b5 100644
--- a/scripts/spelling.txt
+++ b/scripts/spelling.txt
@@ -39,6 +39,8 @@ accout||account
 accquire||acquire
 accquired||acquired
 accross||across
+accumalate||accumulate
+accumalator||accumulator
 acessable||accessible
 acess||access
 acessing||accessing
@@ -106,6 +108,7 @@ alogrithm||algorithm
 alot||a lot
 alow||allow
 alows||allows
+alreay||already
 alredy||already
 altough||although
 alue||value
@@ -241,6 +244,7 @@ calender||calendar
 calescing||coalescing
 calle||called
 callibration||calibration
+callled||called
 calucate||calculate
 calulate||calculate
 cancelation||cancellation
@@ -311,6 +315,7 @@ compaibility||compatibility
 comparsion||comparison
 compatability||compatibility
 compatable||compatible
+compatibililty||compatibility
 compatibiliy||compatibility
 compatibilty||compatibility
 compatiblity||compatibility
@@ -330,6 +335,7 @@ comunication||communication
 conbination||combination
 conditionaly||conditionally
 conditon||condition
+condtion||condition
 conected||connected
 conector||connector
 connecetd||connected
@@ -388,6 +394,8 @@ dafault||default
 deafult||default
 deamon||daemon
 debouce||debounce
+decendant||descendant
+decendants||descendants
 decompres||decompress
 decsribed||described
 decription||description
@@ -411,11 +419,13 @@ delare||declare
 delares||declares
 delaring||declaring
 delemiter||delimiter
+delievered||delivered
 demodualtor||demodulator
 demension||dimension
 dependancies||dependencies
 dependancy||dependency
 dependant||dependent
+dependend||dependent
 depreacted||deprecated
 depreacte||deprecate
 desactivate||deactivate
@@ -791,6 +801,7 @@ ireelevant||irrelevant
 irrelevent||irrelevant
 isnt||isn't
 isssue||issue
+issus||issues
 iternations||iterations
 itertation||iteration
 itslef||itself
@@ -995,6 +1006,7 @@ peice||piece
 pendantic||pedantic
 peprocessor||preprocessor
 perfoming||performing
+perfomring||performing
 peripherial||peripheral
 permissons||permissions
 peroid||period
@@ -1166,6 +1178,8 @@ retreive||retrieve
 retreiving||retrieving
 retrive||retrieve
 retrived||retrieved
+retrun||return
+retun||return
 retuned||returned
 reudce||reduce
 reuest||request
diff --git a/sound/core/info.c b/sound/core/info.c
index 6801d8160866..ca87ae4c30ba 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -282,17 +282,16 @@ static int snd_info_entry_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations snd_info_entry_operations =
-{
-	.owner =		THIS_MODULE,
-	.llseek =		snd_info_entry_llseek,
-	.read =			snd_info_entry_read,
-	.write =		snd_info_entry_write,
-	.poll =			snd_info_entry_poll,
-	.unlocked_ioctl =	snd_info_entry_ioctl,
-	.mmap =			snd_info_entry_mmap,
-	.open =			snd_info_entry_open,
-	.release =		snd_info_entry_release,
+static const struct proc_ops snd_info_entry_operations =
+{
+	.proc_lseek	= snd_info_entry_llseek,
+	.proc_read	= snd_info_entry_read,
+	.proc_write	= snd_info_entry_write,
+	.proc_poll	= snd_info_entry_poll,
+	.proc_ioctl	= snd_info_entry_ioctl,
+	.proc_mmap	= snd_info_entry_mmap,
+	.proc_open	= snd_info_entry_open,
+	.proc_release	= snd_info_entry_release,
 };
 
 /*
@@ -421,14 +420,13 @@ static int snd_info_text_entry_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations snd_info_text_entry_ops =
+static const struct proc_ops snd_info_text_entry_ops =
 {
-	.owner =		THIS_MODULE,
-	.open =			snd_info_text_entry_open,
-	.release =		snd_info_text_entry_release,
-	.write =		snd_info_text_entry_write,
-	.llseek =		seq_lseek,
-	.read =			seq_read,
+	.proc_open	= snd_info_text_entry_open,
+	.proc_release	= snd_info_text_entry_release,
+	.proc_write	= snd_info_text_entry_write,
+	.proc_lseek	= seq_lseek,
+	.proc_read	= seq_read,
 };
 
 static struct snd_info_entry *create_subdir(struct module *mod,
@@ -810,7 +808,7 @@ static int __snd_info_register(struct snd_info_entry *entry)
 			return -ENOMEM;
 		}
 	} else {
-		const struct file_operations *ops;
+		const struct proc_ops *ops;
 		if (entry->content == SNDRV_INFO_CONTENT_DATA)
 			ops = &snd_info_entry_operations;
 		else
diff --git a/sound/soc/codecs/ak4104.c b/sound/soc/codecs/ak4104.c
index e8c5fda82e08..979cfb165eed 100644
--- a/sound/soc/codecs/ak4104.c
+++ b/sound/soc/codecs/ak4104.c
@@ -295,8 +295,7 @@ static int ak4104_spi_probe(struct spi_device *spi)
 
 	reset_gpiod = devm_gpiod_get_optional(&spi->dev, "reset",
 					      GPIOD_OUT_HIGH);
-	if (IS_ERR(reset_gpiod) &&
-	    PTR_ERR(reset_gpiod) == -EPROBE_DEFER)
+	if (PTR_ERR(reset_gpiod) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
 	/* read the 'reserved' register - according to the datasheet, it
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 793a14d58667..5f25b9f872bd 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -681,8 +681,7 @@ static int cs4270_i2c_probe(struct i2c_client *i2c_client,
 
 	reset_gpiod = devm_gpiod_get_optional(&i2c_client->dev, "reset",
 					      GPIOD_OUT_HIGH);
-	if (IS_ERR(reset_gpiod) &&
-	    PTR_ERR(reset_gpiod) == -EPROBE_DEFER)
+	if (PTR_ERR(reset_gpiod) == -EPROBE_DEFER)
 		return -EPROBE_DEFER;
 
 	cs4270->regmap = devm_regmap_init_i2c(i2c_client, &cs4270_regmap);
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index b4e9a6c73f90..d087f3b20b1d 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -1098,11 +1098,9 @@ static int aic32x4_setup_regulators(struct device *dev,
 			return PTR_ERR(aic32x4->supply_av);
 		}
 	} else {
-		if (IS_ERR(aic32x4->supply_dv) &&
-				PTR_ERR(aic32x4->supply_dv) == -EPROBE_DEFER)
+		if (PTR_ERR(aic32x4->supply_dv) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
-		if (IS_ERR(aic32x4->supply_av) &&
-				PTR_ERR(aic32x4->supply_av) == -EPROBE_DEFER)
+		if (PTR_ERR(aic32x4->supply_av) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 	}
 
diff --git a/sound/soc/sunxi/sun4i-spdif.c b/sound/soc/sunxi/sun4i-spdif.c
index cbe598b0fb10..98a9fe645521 100644
--- a/sound/soc/sunxi/sun4i-spdif.c
+++ b/sound/soc/sunxi/sun4i-spdif.c
@@ -555,7 +555,7 @@ static int sun4i_spdif_probe(struct platform_device *pdev)
 	if (quirks->has_reset) {
 		host->rst = devm_reset_control_get_optional_exclusive(&pdev->dev,
 								      NULL);
-		if (IS_ERR(host->rst) && PTR_ERR(host->rst) == -EPROBE_DEFER) {
+		if (PTR_ERR(host->rst) == -EPROBE_DEFER) {
 			ret = -EPROBE_DEFER;
 			dev_err(&pdev->dev, "Failed to get reset: %d\n", ret);
 			return ret;
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 3eb8411ab60e..e95b72ec19bc 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -33,7 +33,7 @@
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
 
-#define EXIT_REASON_PENDING_INTERRUPT   7
+#define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
 #define EXIT_REASON_TASK_SWITCH         9
 #define EXIT_REASON_CPUID               10
@@ -94,7 +94,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
-	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
+	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
 	{ EXIT_REASON_CPUID,                 "CPUID" }, \
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index 8908c58bd6cd..53adc1762ec0 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -929,7 +929,7 @@ EndTable
 
 GrpTable: Grp3_2
 0: TEST Ev,Iz
-1:
+1: TEST Ev,Iz
 2: NOT Ev
 3: NEG Ev
 4: MUL rAX,Ev
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index aea2d91ab364..16d629b22c25 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -80,6 +80,8 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 
 	error = 0;
 done:
+	if (error)
+		target_fname[0] = '\0';
 	return error;
 }
 
@@ -108,15 +110,29 @@ static int hv_copy_data(struct hv_do_fcopy *cpmsg)
 	return ret;
 }
 
+/*
+ * Reset target_fname to "" in the two below functions for hibernation: if
+ * the fcopy operation is aborted by hibernation, the daemon should remove the
+ * partially-copied file; to achieve this, the hv_utils driver always fakes a
+ * CANCEL_FCOPY message upon suspend, and later when the VM resumes back,
+ * the daemon calls hv_copy_cancel() to remove the file; if a file is copied
+ * successfully before suspend, hv_copy_finished() must reset target_fname to
+ * avoid that the file can be incorrectly removed upon resume, since the faked
+ * CANCEL_FCOPY message is spurious in this case.
+ */
 static int hv_copy_finished(void)
 {
 	close(target_fd);
+	target_fname[0] = '\0';
 	return 0;
 }
 static int hv_copy_cancel(void)
 {
 	close(target_fd);
-	unlink(target_fname);
+	if (strlen(target_fname) > 0) {
+		unlink(target_fname);
+		target_fname[0] = '\0';
+	}
 	return 0;
 
 }
@@ -131,7 +147,7 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int fcopy_fd;
+	int fcopy_fd = -1;
 	int error;
 	int daemonize = 1, long_index = 0, opt;
 	int version = FCOPY_CURRENT_VERSION;
@@ -141,7 +157,7 @@ int main(int argc, char *argv[])
 		struct hv_do_fcopy copy;
 		__u32 kernel_modver;
 	} buffer = { };
-	int in_handshake = 1;
+	int in_handshake;
 
 	static struct option long_options[] = {
 		{"help",	no_argument,	   0,  'h' },
@@ -170,6 +186,12 @@ int main(int argc, char *argv[])
 	openlog("HV_FCOPY", 0, LOG_USER);
 	syslog(LOG_INFO, "starting; pid is:%d", getpid());
 
+reopen_fcopy_fd:
+	if (fcopy_fd != -1)
+		close(fcopy_fd);
+	/* Remove any possible partially-copied file on error */
+	hv_copy_cancel();
+	in_handshake = 1;
 	fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR);
 
 	if (fcopy_fd < 0) {
@@ -196,7 +218,7 @@ int main(int argc, char *argv[])
 		len = pread(fcopy_fd, &buffer, sizeof(buffer), 0);
 		if (len < 0) {
 			syslog(LOG_ERR, "pread failed: %s", strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_fcopy_fd;
 		}
 
 		if (in_handshake) {
@@ -231,9 +253,14 @@ int main(int argc, char *argv[])
 
 		}
 
+		/*
+		 * pwrite() may return an error due to the faked CANCEL_FCOPY
+		 * message upon hibernation. Ignore the error by resetting the
+		 * dev file, i.e. closing and re-opening it.
+		 */
 		if (pwrite(fcopy_fd, &error, sizeof(int), 0) != sizeof(int)) {
 			syslog(LOG_ERR, "pwrite failed: %s", strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_fcopy_fd;
 		}
 	}
 }
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index e9ef4ca6a655..ee9c1bb2293e 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -76,7 +76,7 @@ enum {
 	DNS
 };
 
-static int in_hand_shake = 1;
+static int in_hand_shake;
 
 static char *os_name = "";
 static char *os_major = "";
@@ -1360,7 +1360,7 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int kvp_fd, len;
+	int kvp_fd = -1, len;
 	int error;
 	struct pollfd pfd;
 	char    *p;
@@ -1400,14 +1400,6 @@ int main(int argc, char *argv[])
 	openlog("KVP", 0, LOG_USER);
 	syslog(LOG_INFO, "KVP starting; pid is:%d", getpid());
 
-	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
-
-	if (kvp_fd < 0) {
-		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
-			errno, strerror(errno));
-		exit(EXIT_FAILURE);
-	}
-
 	/*
 	 * Retrieve OS release information.
 	 */
@@ -1423,6 +1415,18 @@ int main(int argc, char *argv[])
 		exit(EXIT_FAILURE);
 	}
 
+reopen_kvp_fd:
+	if (kvp_fd != -1)
+		close(kvp_fd);
+	in_hand_shake = 1;
+	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
+
+	if (kvp_fd < 0) {
+		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
+		       errno, strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
 	/*
 	 * Register ourselves with the kernel.
 	 */
@@ -1456,9 +1460,7 @@ int main(int argc, char *argv[])
 		if (len != sizeof(struct hv_kvp_msg)) {
 			syslog(LOG_ERR, "read failed; error:%d %s",
 			       errno, strerror(errno));
-
-			close(kvp_fd);
-			return EXIT_FAILURE;
+			goto reopen_kvp_fd;
 		}
 
 		/*
@@ -1617,13 +1619,17 @@ int main(int argc, char *argv[])
 			break;
 		}
 
-		/* Send the value back to the kernel. */
+		/*
+		 * Send the value back to the kernel. Note: the write() may
+		 * return an error due to hibernation; we can ignore the error
+		 * by resetting the dev file, i.e. closing and re-opening it.
+		 */
 kvp_done:
 		len = write(kvp_fd, hv_msg, sizeof(struct hv_kvp_msg));
 		if (len != sizeof(struct hv_kvp_msg)) {
 			syslog(LOG_ERR, "write failed; error: %d %s", errno,
 			       strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_kvp_fd;
 		}
 	}
 
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 92902a88f671..dd111870beee 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -28,6 +28,8 @@
 #include <stdbool.h>
 #include <dirent.h>
 
+static bool fs_frozen;
+
 /* Don't use syslog() in the function since that can cause write to disk */
 static int vss_do_freeze(char *dir, unsigned int cmd)
 {
@@ -155,18 +157,27 @@ static int vss_operate(int operation)
 			continue;
 		}
 		error |= vss_do_freeze(ent->mnt_dir, cmd);
-		if (error && operation == VSS_OP_FREEZE)
-			goto err;
+		if (operation == VSS_OP_FREEZE) {
+			if (error)
+				goto err;
+			fs_frozen = true;
+		}
 	}
 
 	endmntent(mounts);
 
 	if (root_seen) {
 		error |= vss_do_freeze("/", cmd);
-		if (error && operation == VSS_OP_FREEZE)
-			goto err;
+		if (operation == VSS_OP_FREEZE) {
+			if (error)
+				goto err;
+			fs_frozen = true;
+		}
 	}
 
+	if (operation == VSS_OP_THAW && !error)
+		fs_frozen = false;
+
 	goto out;
 err:
 	save_errno = errno;
@@ -175,6 +186,7 @@ err:
 		endmntent(mounts);
 	}
 	vss_operate(VSS_OP_THAW);
+	fs_frozen = false;
 	/* Call syslog after we thaw all filesystems */
 	if (ent)
 		syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s",
@@ -196,13 +208,13 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int vss_fd, len;
+	int vss_fd = -1, len;
 	int error;
 	struct pollfd pfd;
 	int	op;
 	struct hv_vss_msg vss_msg[1];
 	int daemonize = 1, long_index = 0, opt;
-	int in_handshake = 1;
+	int in_handshake;
 	__u32 kernel_modver;
 
 	static struct option long_options[] = {
@@ -232,6 +244,18 @@ int main(int argc, char *argv[])
 	openlog("Hyper-V VSS", 0, LOG_USER);
 	syslog(LOG_INFO, "VSS starting; pid is:%d", getpid());
 
+reopen_vss_fd:
+	if (vss_fd != -1)
+		close(vss_fd);
+	if (fs_frozen) {
+		if (vss_operate(VSS_OP_THAW) || fs_frozen) {
+			syslog(LOG_ERR, "failed to thaw file system: err=%d",
+			       errno);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	in_handshake = 1;
 	vss_fd = open("/dev/vmbus/hv_vss", O_RDWR);
 	if (vss_fd < 0) {
 		syslog(LOG_ERR, "open /dev/vmbus/hv_vss failed; error: %d %s",
@@ -284,8 +308,7 @@ int main(int argc, char *argv[])
 		if (len != sizeof(struct hv_vss_msg)) {
 			syslog(LOG_ERR, "read failed; error:%d %s",
 			       errno, strerror(errno));
-			close(vss_fd);
-			return EXIT_FAILURE;
+			goto reopen_vss_fd;
 		}
 
 		op = vss_msg->vss_hdr.operation;
@@ -312,14 +335,18 @@ int main(int argc, char *argv[])
 		default:
 			syslog(LOG_ERR, "Illegal op:%d\n", op);
 		}
+
+		/*
+		 * The write() may return an error due to the faked VSS_OP_THAW
+		 * message upon hibernation. Ignore the error by resetting the
+		 * dev file, i.e. closing and re-opening it.
+		 */
 		vss_msg->error = error;
 		len = write(vss_fd, vss_msg, sizeof(struct hv_vss_msg));
 		if (len != sizeof(struct hv_vss_msg)) {
 			syslog(LOG_ERR, "write failed; error: %d %s", errno,
 			       strerror(errno));
-
-			if (op == VSS_OP_FREEZE)
-				vss_operate(VSS_OP_THAW);
+			goto reopen_vss_fd;
 		}
 	}
 
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 140c8362f113..5fca38fe1ba8 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -14,10 +14,11 @@
 #include <linux/bits.h>
 #include <linux/compiler.h>
 
-#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
-#define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
-#define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE)
+#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
+#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
+#define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
+#define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
+#define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index ad1b9e646c49..4cf93110c259 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -270,6 +270,7 @@ class ArchX86(Arch):
     def __init__(self, exit_reasons):
         self.sc_perf_evt_open = 298
         self.ioctl_numbers = IOCTL_NUMBERS
+        self.exit_reason_field = 'exit_reason'
         self.exit_reasons = exit_reasons
 
     def debugfs_is_child(self, field):
@@ -289,6 +290,7 @@ class ArchPPC(Arch):
         # numbers depend on the wordsize.
         char_ptr_size = ctypes.sizeof(ctypes.c_char_p)
         self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
+        self.exit_reason_field = 'exit_nr'
         self.exit_reasons = {}
 
     def debugfs_is_child(self, field):
@@ -300,6 +302,7 @@ class ArchA64(Arch):
     def __init__(self):
         self.sc_perf_evt_open = 241
         self.ioctl_numbers = IOCTL_NUMBERS
+        self.exit_reason_field = 'esr_ec'
         self.exit_reasons = AARCH64_EXIT_REASONS
 
     def debugfs_is_child(self, field):
@@ -311,6 +314,7 @@ class ArchS390(Arch):
     def __init__(self):
         self.sc_perf_evt_open = 331
         self.ioctl_numbers = IOCTL_NUMBERS
+        self.exit_reason_field = None
         self.exit_reasons = None
 
     def debugfs_is_child(self, field):
@@ -541,8 +545,8 @@ class TracepointProvider(Provider):
         """
         filters = {}
         filters['kvm_userspace_exit'] = ('reason', USERSPACE_EXIT_REASONS)
-        if ARCH.exit_reasons:
-            filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
+        if ARCH.exit_reason_field and ARCH.exit_reasons:
+            filters['kvm_exit'] = (ARCH.exit_reason_field, ARCH.exit_reasons)
         return filters
 
     def _get_available_fields(self):
diff --git a/tools/power/cpupower/lib/cpufreq.c b/tools/power/cpupower/lib/cpufreq.c
index 2f55d4d23446..6e04304560ca 100644
--- a/tools/power/cpupower/lib/cpufreq.c
+++ b/tools/power/cpupower/lib/cpufreq.c
@@ -332,21 +332,74 @@ void cpufreq_put_available_governors(struct cpufreq_available_governors *any)
 }
 
 
-struct cpufreq_frequencies
-*cpufreq_get_frequencies(const char *type, unsigned int cpu)
+struct cpufreq_available_frequencies
+*cpufreq_get_available_frequencies(unsigned int cpu)
 {
-	struct cpufreq_frequencies *first = NULL;
-	struct cpufreq_frequencies *current = NULL;
+	struct cpufreq_available_frequencies *first = NULL;
+	struct cpufreq_available_frequencies *current = NULL;
 	char one_value[SYSFS_PATH_MAX];
 	char linebuf[MAX_LINE_LEN];
-	char fname[MAX_LINE_LEN];
 	unsigned int pos, i;
 	unsigned int len;
 
-	snprintf(fname, MAX_LINE_LEN, "scaling_%s_frequencies", type);
+	len = sysfs_cpufreq_read_file(cpu, "scaling_available_frequencies",
+				      linebuf, sizeof(linebuf));
+	if (len == 0)
+		return NULL;
 
-	len = sysfs_cpufreq_read_file(cpu, fname,
-				linebuf, sizeof(linebuf));
+	pos = 0;
+	for (i = 0; i < len; i++) {
+		if (linebuf[i] == ' ' || linebuf[i] == '\n') {
+			if (i - pos < 2)
+				continue;
+			if (i - pos >= SYSFS_PATH_MAX)
+				goto error_out;
+			if (current) {
+				current->next = malloc(sizeof(*current));
+				if (!current->next)
+					goto error_out;
+				current = current->next;
+			} else {
+				first = malloc(sizeof(*first));
+				if (!first)
+					goto error_out;
+				current = first;
+			}
+			current->first = first;
+			current->next = NULL;
+
+			memcpy(one_value, linebuf + pos, i - pos);
+			one_value[i - pos] = '\0';
+			if (sscanf(one_value, "%lu", &current->frequency) != 1)
+				goto error_out;
+
+			pos = i + 1;
+		}
+	}
+
+	return first;
+
+ error_out:
+	while (first) {
+		current = first->next;
+		free(first);
+		first = current;
+	}
+	return NULL;
+}
+
+struct cpufreq_available_frequencies
+*cpufreq_get_boost_frequencies(unsigned int cpu)
+{
+	struct cpufreq_available_frequencies *first = NULL;
+	struct cpufreq_available_frequencies *current = NULL;
+	char one_value[SYSFS_PATH_MAX];
+	char linebuf[MAX_LINE_LEN];
+	unsigned int pos, i;
+	unsigned int len;
+
+	len = sysfs_cpufreq_read_file(cpu, "scaling_boost_frequencies",
+				      linebuf, sizeof(linebuf));
 	if (len == 0)
 		return NULL;
 
@@ -391,9 +444,9 @@ struct cpufreq_frequencies
 	return NULL;
 }
 
-void cpufreq_put_frequencies(struct cpufreq_frequencies *any)
+void cpufreq_put_available_frequencies(struct cpufreq_available_frequencies *any)
 {
-	struct cpufreq_frequencies *tmp, *next;
+	struct cpufreq_available_frequencies *tmp, *next;
 
 	if (!any)
 		return;
@@ -406,6 +459,11 @@ void cpufreq_put_frequencies(struct cpufreq_frequencies *any)
 	}
 }
 
+void cpufreq_put_boost_frequencies(struct cpufreq_available_frequencies *any)
+{
+	cpufreq_put_available_frequencies(any);
+}
+
 static struct cpufreq_affected_cpus *sysfs_get_cpu_list(unsigned int cpu,
 							const char *file)
 {
diff --git a/tools/power/cpupower/lib/cpufreq.h b/tools/power/cpupower/lib/cpufreq.h
index a55f0d19215b..95f4fd9e2656 100644
--- a/tools/power/cpupower/lib/cpufreq.h
+++ b/tools/power/cpupower/lib/cpufreq.h
@@ -20,10 +20,10 @@ struct cpufreq_available_governors {
 	struct cpufreq_available_governors *first;
 };
 
-struct cpufreq_frequencies {
+struct cpufreq_available_frequencies {
 	unsigned long frequency;
-	struct cpufreq_frequencies *next;
-	struct cpufreq_frequencies *first;
+	struct cpufreq_available_frequencies *next;
+	struct cpufreq_available_frequencies *first;
 };
 
 
@@ -124,11 +124,17 @@ void cpufreq_put_available_governors(
  * cpufreq_put_frequencies after use.
  */
 
-struct cpufreq_frequencies
-*cpufreq_get_frequencies(const char *type, unsigned int cpu);
+struct cpufreq_available_frequencies
+*cpufreq_get_available_frequencies(unsigned int cpu);
 
-void cpufreq_put_frequencies(
-		struct cpufreq_frequencies *first);
+void cpufreq_put_available_frequencies(
+		struct cpufreq_available_frequencies *first);
+
+struct cpufreq_available_frequencies
+*cpufreq_get_boost_frequencies(unsigned int cpu);
+
+void cpufreq_put_boost_frequencies(
+		struct cpufreq_available_frequencies *first);
 
 
 /* determine affected CPUs
diff --git a/tools/power/cpupower/man/cpupower.1 b/tools/power/cpupower/man/cpupower.1
index baf741d06e82..a5e4523a219b 100644
--- a/tools/power/cpupower/man/cpupower.1
+++ b/tools/power/cpupower/man/cpupower.1
@@ -62,9 +62,9 @@ all cores
 Print the package name and version number.
 
 .SH "SEE ALSO"
-cpupower-set(1), cpupower-info(1), cpupower-idle(1),
-cpupower-frequency-set(1), cpupower-frequency-info(1), cpupower-monitor(1),
-powertop(1)
+cpupower-set(1), cpupower-info(1), cpupower-idle-info(1),
+cpupower-idle-set(1), cpupower-frequency-set(1), cpupower-frequency-info(1),
+cpupower-monitor(1), powertop(1)
 .PP
 .SH AUTHORS
 .nf
diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c
index e63cf55f81cf..6efc0f6b1b11 100644
--- a/tools/power/cpupower/utils/cpufreq-info.c
+++ b/tools/power/cpupower/utils/cpufreq-info.c
@@ -244,14 +244,14 @@ static int get_boost_mode_x86(unsigned int cpu)
 
 static int get_boost_mode(unsigned int cpu)
 {
-	struct cpufreq_frequencies *freqs;
+	struct cpufreq_available_frequencies *freqs;
 
 	if (cpupower_cpu_info.vendor == X86_VENDOR_AMD ||
 	    cpupower_cpu_info.vendor == X86_VENDOR_HYGON ||
 	    cpupower_cpu_info.vendor == X86_VENDOR_INTEL)
 		return get_boost_mode_x86(cpu);
 
-	freqs = cpufreq_get_frequencies("boost", cpu);
+	freqs = cpufreq_get_boost_frequencies(cpu);
 	if (freqs) {
 		printf(_("  boost frequency steps: "));
 		while (freqs->next) {
@@ -261,7 +261,7 @@ static int get_boost_mode(unsigned int cpu)
 		}
 		print_speed(freqs->frequency);
 		printf("\n");
-		cpufreq_put_frequencies(freqs);
+		cpufreq_put_available_frequencies(freqs);
 	}
 
 	return 0;
@@ -475,7 +475,7 @@ static int get_latency(unsigned int cpu, unsigned int human)
 
 static void debug_output_one(unsigned int cpu)
 {
-	struct cpufreq_frequencies *freqs;
+	struct cpufreq_available_frequencies *freqs;
 
 	get_driver(cpu);
 	get_related_cpus(cpu);
@@ -483,7 +483,7 @@ static void debug_output_one(unsigned int cpu)
 	get_latency(cpu, 1);
 	get_hardware_limits(cpu, 1);
 
-	freqs = cpufreq_get_frequencies("available", cpu);
+	freqs = cpufreq_get_available_frequencies(cpu);
 	if (freqs) {
 		printf(_("  available frequency steps:  "));
 		while (freqs->next) {
@@ -493,7 +493,7 @@ static void debug_output_one(unsigned int cpu)
 		}
 		print_speed(freqs->frequency);
 		printf("\n");
-		cpufreq_put_frequencies(freqs);
+		cpufreq_put_available_frequencies(freqs);
 	}
 
 	get_available_governors(cpu);
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
index 2d6d342b148f..256199c7a182 100755
--- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -11,11 +11,11 @@ then this utility enables and collects trace data for a user specified interval
 and generates performance plots.
 
 Prerequisites:
-    Python version 2.7.x
+    Python version 2.7.x or higher
     gnuplot 5.0 or higher
-    gnuplot-py 1.8
+    gnuplot-py 1.8 or higher
     (Most of the distributions have these required packages. They may be called
-     gnuplot-py, phython-gnuplot. )
+     gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... )
 
     HWP (Hardware P-States are disabled)
     Kernel config for Linux trace is enabled
@@ -104,7 +104,7 @@ def plot_perf_busy_with_sample(cpu_index):
     if os.path.exists(file_name):
         output_png = "cpu%03d_perf_busy_vs_samples.png" % cpu_index
         g_plot = common_all_gnuplot_settings(output_png)
-        g_plot('set yrange [0:40]')
+#   autoscale this one, no set y1 range
         g_plot('set y2range [0:200]')
         g_plot('set y2tics 0, 10')
         g_plot('set title "{} : cpu perf busy vs. sample : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
@@ -125,7 +125,7 @@ def plot_perf_busy(cpu_index):
     if os.path.exists(file_name):
         output_png = "cpu%03d_perf_busy.png" % cpu_index
         g_plot = common_all_gnuplot_settings(output_png)
-        g_plot('set yrange [0:40]')
+#   autoscale this one, no set y1 range
         g_plot('set y2range [0:200]')
         g_plot('set y2tics 0, 10')
         g_plot('set title "{} : perf busy : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
@@ -144,9 +144,7 @@ def plot_durations(cpu_index):
     if os.path.exists(file_name):
         output_png = "cpu%03d_durations.png" % cpu_index
         g_plot = common_all_gnuplot_settings(output_png)
-#       Should autoscale be used here? Should seconds be used here?
-        g_plot('set yrange [0:5000]')
-        g_plot('set ytics 0, 500')
+#       autoscale this one, no set y range
         g_plot('set title "{} : durations : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
         g_plot('set ylabel "Timer Duration (MilliSeconds)"')
 #       override common
@@ -176,12 +174,12 @@ def plot_pstate_cpu_with_sample():
     if os.path.exists('cpu.csv'):
         output_png = 'all_cpu_pstates_vs_samples.png'
         g_plot = common_all_gnuplot_settings(output_png)
-        g_plot('set yrange [0:40]')
+#       autoscale this one, no set y range
 #       override common
         g_plot('set xlabel "Samples"')
         g_plot('set ylabel "P-State"')
         g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now()))
-        title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+        title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
         plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO)
         g_plot('title_list = "{}"'.format(title_list))
         g_plot(plot_str)
@@ -191,14 +189,14 @@ def plot_pstate_cpu():
 
     output_png = 'all_cpu_pstates.png'
     g_plot = common_all_gnuplot_settings(output_png)
-    g_plot('set yrange [0:40]')
+#   autoscale this one, no set y range
     g_plot('set ylabel "P-State"')
     g_plot('set title "{} : cpu pstates : {:%F %H:%M}"'.format(testname, datetime.now()))
 
 #    the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file.
 #    plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s'
 #
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -212,7 +210,7 @@ def plot_load_cpu():
     g_plot('set ylabel "CPU load (percent)"')
     g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -222,11 +220,11 @@ def plot_frequency_cpu():
 
     output_png = 'all_cpu_frequencies.png'
     g_plot = common_all_gnuplot_settings(output_png)
-    g_plot('set yrange [0:4]')
+#   autoscale this one, no set y range
     g_plot('set ylabel "CPU Frequency (GHz)"')
     g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -236,12 +234,12 @@ def plot_duration_cpu():
 
     output_png = 'all_cpu_durations.png'
     g_plot = common_all_gnuplot_settings(output_png)
-    g_plot('set yrange [0:5000]')
+#   autoscale this one, no set y range
     g_plot('set ytics 0, 500')
     g_plot('set ylabel "Timer Duration (MilliSeconds)"')
     g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -255,7 +253,7 @@ def plot_scaled_cpu():
     g_plot('set ylabel "Scaled Busy (Unitless)"')
     g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -269,7 +267,7 @@ def plot_boost_cpu():
     g_plot('set ylabel "CPU IO Boost (percent)"')
     g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
@@ -283,7 +281,7 @@ def plot_ghz_cpu():
     g_plot('set ylabel "TSC Frequency (GHz)"')
     g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now()))
 
-    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).decode('utf-8').replace('\n', ' ')
     plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ)
     g_plot('title_list = "{}"'.format(title_list))
     g_plot(plot_str)
diff --git a/tools/testing/selftests/dmabuf-heaps/Makefile b/tools/testing/selftests/dmabuf-heaps/Makefile
new file mode 100644
index 000000000000..607c2acd2082
--- /dev/null
+++ b/tools/testing/selftests/dmabuf-heaps/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -static -O3 -Wl,-no-as-needed -Wall -I../../../../usr/include
+
+TEST_GEN_PROGS = dmabuf-heap
+
+include ../lib.mk
diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
new file mode 100644
index 000000000000..cd5e1f602ac9
--- /dev/null
+++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <dirent.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+
+#include <linux/dma-buf.h>
+#include <drm/drm.h>
+
+#include "../../../../include/uapi/linux/dma-heap.h"
+
+#define DEVPATH "/dev/dma_heap"
+
+static int check_vgem(int fd)
+{
+	drm_version_t version = { 0 };
+	char name[5];
+	int ret;
+
+	version.name_len = 4;
+	version.name = name;
+
+	ret = ioctl(fd, DRM_IOCTL_VERSION, &version);
+	if (ret)
+		return 0;
+
+	return !strcmp(name, "vgem");
+}
+
+static int open_vgem(void)
+{
+	int i, fd;
+	const char *drmstr = "/dev/dri/card";
+
+	fd = -1;
+	for (i = 0; i < 16; i++) {
+		char name[80];
+
+		snprintf(name, 80, "%s%u", drmstr, i);
+
+		fd = open(name, O_RDWR);
+		if (fd < 0)
+			continue;
+
+		if (!check_vgem(fd)) {
+			close(fd);
+			fd = -1;
+			continue;
+		} else {
+			break;
+		}
+	}
+	return fd;
+}
+
+static int import_vgem_fd(int vgem_fd, int dma_buf_fd, uint32_t *handle)
+{
+	struct drm_prime_handle import_handle = {
+		.fd = dma_buf_fd,
+		.flags = 0,
+		.handle = 0,
+	 };
+	int ret;
+
+	ret = ioctl(vgem_fd, DRM_IOCTL_PRIME_FD_TO_HANDLE, &import_handle);
+	if (ret == 0)
+		*handle = import_handle.handle;
+	return ret;
+}
+
+static void close_handle(int vgem_fd, uint32_t handle)
+{
+	struct drm_gem_close close = {
+		.handle = handle,
+	};
+
+	ioctl(vgem_fd, DRM_IOCTL_GEM_CLOSE, &close);
+}
+
+static int dmabuf_heap_open(char *name)
+{
+	int ret, fd;
+	char buf[256];
+
+	ret = snprintf(buf, 256, "%s/%s", DEVPATH, name);
+	if (ret < 0) {
+		printf("snprintf failed!\n");
+		return ret;
+	}
+
+	fd = open(buf, O_RDWR);
+	if (fd < 0)
+		printf("open %s failed!\n", buf);
+	return fd;
+}
+
+static int dmabuf_heap_alloc_fdflags(int fd, size_t len, unsigned int fd_flags,
+				     unsigned int heap_flags, int *dmabuf_fd)
+{
+	struct dma_heap_allocation_data data = {
+		.len = len,
+		.fd = 0,
+		.fd_flags = fd_flags,
+		.heap_flags = heap_flags,
+	};
+	int ret;
+
+	if (!dmabuf_fd)
+		return -EINVAL;
+
+	ret = ioctl(fd, DMA_HEAP_IOCTL_ALLOC, &data);
+	if (ret < 0)
+		return ret;
+	*dmabuf_fd = (int)data.fd;
+	return ret;
+}
+
+static int dmabuf_heap_alloc(int fd, size_t len, unsigned int flags,
+			     int *dmabuf_fd)
+{
+	return dmabuf_heap_alloc_fdflags(fd, len, O_RDWR | O_CLOEXEC, flags,
+					 dmabuf_fd);
+}
+
+static void dmabuf_sync(int fd, int start_stop)
+{
+	struct dma_buf_sync sync = {
+		.flags = start_stop | DMA_BUF_SYNC_RW,
+	};
+	int ret;
+
+	ret = ioctl(fd, DMA_BUF_IOCTL_SYNC, &sync);
+	if (ret)
+		printf("sync failed %d\n", errno);
+}
+
+#define ONE_MEG (1024 * 1024)
+
+static int test_alloc_and_import(char *heap_name)
+{
+	int heap_fd = -1, dmabuf_fd = -1, importer_fd = -1;
+	uint32_t handle = 0;
+	void *p = NULL;
+	int ret;
+
+	printf("Testing heap: %s\n", heap_name);
+
+	heap_fd = dmabuf_heap_open(heap_name);
+	if (heap_fd < 0)
+		return -1;
+
+	printf("Allocating 1 MEG\n");
+	ret = dmabuf_heap_alloc(heap_fd, ONE_MEG, 0, &dmabuf_fd);
+	if (ret) {
+		printf("Allocation Failed!\n");
+		ret = -1;
+		goto out;
+	}
+	/* mmap and write a simple pattern */
+	p = mmap(NULL,
+		 ONE_MEG,
+		 PROT_READ | PROT_WRITE,
+		 MAP_SHARED,
+		 dmabuf_fd,
+		 0);
+	if (p == MAP_FAILED) {
+		printf("mmap() failed: %m\n");
+		ret = -1;
+		goto out;
+	}
+	printf("mmap passed\n");
+
+	dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_START);
+	memset(p, 1, ONE_MEG / 2);
+	memset((char *)p + ONE_MEG / 2, 0, ONE_MEG / 2);
+	dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_END);
+
+	importer_fd = open_vgem();
+	if (importer_fd < 0) {
+		ret = importer_fd;
+		printf("Failed to open vgem\n");
+		goto out;
+	}
+
+	ret = import_vgem_fd(importer_fd, dmabuf_fd, &handle);
+	if (ret < 0) {
+		printf("Failed to import buffer\n");
+		goto out;
+	}
+	printf("import passed\n");
+
+	dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_START);
+	memset(p, 0xff, ONE_MEG);
+	dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_END);
+	printf("syncs passed\n");
+
+	close_handle(importer_fd, handle);
+	ret = 0;
+
+out:
+	if (p)
+		munmap(p, ONE_MEG);
+	if (importer_fd >= 0)
+		close(importer_fd);
+	if (dmabuf_fd >= 0)
+		close(dmabuf_fd);
+	if (heap_fd >= 0)
+		close(heap_fd);
+
+	return ret;
+}
+
+/* Test the ioctl version compatibility w/ a smaller structure then expected */
+static int dmabuf_heap_alloc_older(int fd, size_t len, unsigned int flags,
+				   int *dmabuf_fd)
+{
+	int ret;
+	unsigned int older_alloc_ioctl;
+	struct dma_heap_allocation_data_smaller {
+		__u64 len;
+		__u32 fd;
+		__u32 fd_flags;
+	} data = {
+		.len = len,
+		.fd = 0,
+		.fd_flags = O_RDWR | O_CLOEXEC,
+	};
+
+	older_alloc_ioctl = _IOWR(DMA_HEAP_IOC_MAGIC, 0x0,
+				  struct dma_heap_allocation_data_smaller);
+	if (!dmabuf_fd)
+		return -EINVAL;
+
+	ret = ioctl(fd, older_alloc_ioctl, &data);
+	if (ret < 0)
+		return ret;
+	*dmabuf_fd = (int)data.fd;
+	return ret;
+}
+
+/* Test the ioctl version compatibility w/ a larger structure then expected */
+static int dmabuf_heap_alloc_newer(int fd, size_t len, unsigned int flags,
+				   int *dmabuf_fd)
+{
+	int ret;
+	unsigned int newer_alloc_ioctl;
+	struct dma_heap_allocation_data_bigger {
+		__u64 len;
+		__u32 fd;
+		__u32 fd_flags;
+		__u64 heap_flags;
+		__u64 garbage1;
+		__u64 garbage2;
+		__u64 garbage3;
+	} data = {
+		.len = len,
+		.fd = 0,
+		.fd_flags = O_RDWR | O_CLOEXEC,
+		.heap_flags = flags,
+		.garbage1 = 0xffffffff,
+		.garbage2 = 0x88888888,
+		.garbage3 = 0x11111111,
+	};
+
+	newer_alloc_ioctl = _IOWR(DMA_HEAP_IOC_MAGIC, 0x0,
+				  struct dma_heap_allocation_data_bigger);
+	if (!dmabuf_fd)
+		return -EINVAL;
+
+	ret = ioctl(fd, newer_alloc_ioctl, &data);
+	if (ret < 0)
+		return ret;
+
+	*dmabuf_fd = (int)data.fd;
+	return ret;
+}
+
+static int test_alloc_compat(char *heap_name)
+{
+	int heap_fd = -1, dmabuf_fd = -1;
+	int ret;
+
+	heap_fd = dmabuf_heap_open(heap_name);
+	if (heap_fd < 0)
+		return -1;
+
+	printf("Testing (theoretical)older alloc compat\n");
+	ret = dmabuf_heap_alloc_older(heap_fd, ONE_MEG, 0, &dmabuf_fd);
+	if (ret) {
+		printf("Older compat allocation failed!\n");
+		ret = -1;
+		goto out;
+	}
+	close(dmabuf_fd);
+
+	printf("Testing (theoretical)newer alloc compat\n");
+	ret = dmabuf_heap_alloc_newer(heap_fd, ONE_MEG, 0, &dmabuf_fd);
+	if (ret) {
+		printf("Newer compat allocation failed!\n");
+		ret = -1;
+		goto out;
+	}
+	printf("Ioctl compatibility tests passed\n");
+out:
+	if (dmabuf_fd >= 0)
+		close(dmabuf_fd);
+	if (heap_fd >= 0)
+		close(heap_fd);
+
+	return ret;
+}
+
+static int test_alloc_errors(char *heap_name)
+{
+	int heap_fd = -1, dmabuf_fd = -1;
+	int ret;
+
+	heap_fd = dmabuf_heap_open(heap_name);
+	if (heap_fd < 0)
+		return -1;
+
+	printf("Testing expected error cases\n");
+	ret = dmabuf_heap_alloc(0, ONE_MEG, 0x111111, &dmabuf_fd);
+	if (!ret) {
+		printf("Did not see expected error (invalid fd)!\n");
+		ret = -1;
+		goto out;
+	}
+
+	ret = dmabuf_heap_alloc(heap_fd, ONE_MEG, 0x111111, &dmabuf_fd);
+	if (!ret) {
+		printf("Did not see expected error (invalid heap flags)!\n");
+		ret = -1;
+		goto out;
+	}
+
+	ret = dmabuf_heap_alloc_fdflags(heap_fd, ONE_MEG,
+					~(O_RDWR | O_CLOEXEC), 0, &dmabuf_fd);
+	if (!ret) {
+		printf("Did not see expected error (invalid fd flags)!\n");
+		ret = -1;
+		goto out;
+	}
+
+	printf("Expected error checking passed\n");
+out:
+	if (dmabuf_fd >= 0)
+		close(dmabuf_fd);
+	if (heap_fd >= 0)
+		close(heap_fd);
+
+	return ret;
+}
+
+int main(void)
+{
+	DIR *d;
+	struct dirent *dir;
+	int ret = -1;
+
+	d = opendir(DEVPATH);
+	if (!d) {
+		printf("No %s directory?\n", DEVPATH);
+		return -1;
+	}
+
+	while ((dir = readdir(d)) != NULL) {
+		if (!strncmp(dir->d_name, ".", 2))
+			continue;
+		if (!strncmp(dir->d_name, "..", 3))
+			continue;
+
+		ret = test_alloc_and_import(dir->d_name);
+		if (ret)
+			break;
+
+		ret = test_alloc_compat(dir->d_name);
+		if (ret)
+			break;
+
+		ret = test_alloc_errors(dir->d_name);
+		if (ret)
+			break;
+	}
+	closedir(d);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index f52e0ba84fed..3d27069b9ed9 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -18,8 +18,8 @@
 /*
  * Definitions of Primary Processor-Based VM-Execution Controls.
  */
-#define CPU_BASED_VIRTUAL_INTR_PENDING		0x00000004
-#define CPU_BASED_USE_TSC_OFFSETING		0x00000008
+#define CPU_BASED_INTR_WINDOW_EXITING		0x00000004
+#define CPU_BASED_USE_TSC_OFFSETTING		0x00000008
 #define CPU_BASED_HLT_EXITING			0x00000080
 #define CPU_BASED_INVLPG_EXITING		0x00000200
 #define CPU_BASED_MWAIT_EXITING			0x00000400
@@ -30,7 +30,7 @@
 #define CPU_BASED_CR8_LOAD_EXITING		0x00080000
 #define CPU_BASED_CR8_STORE_EXITING		0x00100000
 #define CPU_BASED_TPR_SHADOW			0x00200000
-#define CPU_BASED_VIRTUAL_NMI_PENDING		0x00400000
+#define CPU_BASED_NMI_WINDOW_EXITING		0x00400000
 #define CPU_BASED_MOV_DR_EXITING		0x00800000
 #define CPU_BASED_UNCOND_IO_EXITING		0x01000000
 #define CPU_BASED_USE_IO_BITMAPS		0x02000000
@@ -103,7 +103,7 @@
 #define EXIT_REASON_EXCEPTION_NMI	0
 #define EXIT_REASON_EXTERNAL_INTERRUPT	1
 #define EXIT_REASON_TRIPLE_FAULT	2
-#define EXIT_REASON_PENDING_INTERRUPT	7
+#define EXIT_REASON_INTERRUPT_WINDOW	7
 #define EXIT_REASON_NMI_WINDOW		8
 #define EXIT_REASON_TASK_SWITCH		9
 #define EXIT_REASON_CPUID		10
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index 5590fd2bcf87..69e482a95c47 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -98,7 +98,7 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 	prepare_vmcs(vmx_pages, l2_guest_code,
 		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
 	control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
-	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+	control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETTING;
 	vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
 	vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
 
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 8aefd81fbc86..ecc52d4c034d 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -22,3 +22,4 @@ ipv6_flowlabel_mgr
 so_txtime
 tcp_fastopen_backup_key
 nettest
+fin_ack_lat
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index a8e04d665b69..b5694196430a 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -11,6 +11,7 @@ TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
 TEST_PROGS += test_vxlan_fdb_changelink.sh so_txtime.sh ipv6_flowlabel.sh
 TEST_PROGS += tcp_fastopen_backup_key.sh fcnal-test.sh l2tp.sh traceroute.sh
+TEST_PROGS += fin_ack_lat.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -18,6 +19,7 @@ TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag
 TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr
 TEST_GEN_FILES += tcp_fastopen_backup_key
+TEST_GEN_FILES += fin_ack_lat
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
diff --git a/tools/testing/selftests/net/fin_ack_lat.c b/tools/testing/selftests/net/fin_ack_lat.c
new file mode 100644
index 000000000000..70187494b57a
--- /dev/null
+++ b/tools/testing/selftests/net/fin_ack_lat.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <unistd.h>
+
+static int child_pid;
+
+static unsigned long timediff(struct timeval s, struct timeval e)
+{
+	unsigned long s_us, e_us;
+
+	s_us = s.tv_sec * 1000000 + s.tv_usec;
+	e_us = e.tv_sec * 1000000 + e.tv_usec;
+	if (s_us > e_us)
+		return 0;
+	return e_us - s_us;
+}
+
+static void client(int port)
+{
+	int sock = 0;
+	struct sockaddr_in addr, laddr;
+	socklen_t len = sizeof(laddr);
+	struct linger sl;
+	int flag = 1;
+	int buffer;
+	struct timeval start, end;
+	unsigned long lat, sum_lat = 0, nr_lat = 0;
+
+	while (1) {
+		gettimeofday(&start, NULL);
+
+		sock = socket(AF_INET, SOCK_STREAM, 0);
+		if (sock < 0)
+			error(-1, errno, "socket creation");
+
+		sl.l_onoff = 1;
+		sl.l_linger = 0;
+		if (setsockopt(sock, SOL_SOCKET, SO_LINGER, &sl, sizeof(sl)))
+			error(-1, errno, "setsockopt(linger)");
+
+		if (setsockopt(sock, IPPROTO_TCP, TCP_NODELAY,
+					&flag, sizeof(flag)))
+			error(-1, errno, "setsockopt(nodelay)");
+
+		addr.sin_family = AF_INET;
+		addr.sin_port = htons(port);
+
+		if (inet_pton(AF_INET, "127.0.0.1", &addr.sin_addr) <= 0)
+			error(-1, errno, "inet_pton");
+
+		if (connect(sock, (struct sockaddr *)&addr, sizeof(addr)) < 0)
+			error(-1, errno, "connect");
+
+		send(sock, &buffer, sizeof(buffer), 0);
+		if (read(sock, &buffer, sizeof(buffer)) == -1)
+			error(-1, errno, "waiting read");
+
+		gettimeofday(&end, NULL);
+		lat = timediff(start, end);
+		sum_lat += lat;
+		nr_lat++;
+		if (lat < 100000)
+			goto close;
+
+		if (getsockname(sock, (struct sockaddr *)&laddr, &len) == -1)
+			error(-1, errno, "getsockname");
+		printf("port: %d, lat: %lu, avg: %lu, nr: %lu\n",
+				ntohs(laddr.sin_port), lat,
+				sum_lat / nr_lat, nr_lat);
+close:
+		fflush(stdout);
+		close(sock);
+	}
+}
+
+static void server(int sock, struct sockaddr_in address)
+{
+	int accepted;
+	int addrlen = sizeof(address);
+	int buffer;
+
+	while (1) {
+		accepted = accept(sock, (struct sockaddr *)&address,
+				(socklen_t *)&addrlen);
+		if (accepted < 0)
+			error(-1, errno, "accept");
+
+		if (read(accepted, &buffer, sizeof(buffer)) == -1)
+			error(-1, errno, "read");
+		close(accepted);
+	}
+}
+
+static void sig_handler(int signum)
+{
+	kill(SIGTERM, child_pid);
+	exit(0);
+}
+
+int main(int argc, char const *argv[])
+{
+	int sock;
+	int opt = 1;
+	struct sockaddr_in address;
+	struct sockaddr_in laddr;
+	socklen_t len = sizeof(laddr);
+
+	if (signal(SIGTERM, sig_handler) == SIG_ERR)
+		error(-1, errno, "signal");
+
+	sock = socket(AF_INET, SOCK_STREAM, 0);
+	if (sock < 0)
+		error(-1, errno, "socket");
+
+	if (setsockopt(sock, SOL_SOCKET, SO_REUSEADDR | SO_REUSEPORT,
+				&opt, sizeof(opt)) == -1)
+		error(-1, errno, "setsockopt");
+
+	address.sin_family = AF_INET;
+	address.sin_addr.s_addr = INADDR_ANY;
+	/* dynamically allocate unused port */
+	address.sin_port = 0;
+
+	if (bind(sock, (struct sockaddr *)&address, sizeof(address)) < 0)
+		error(-1, errno, "bind");
+
+	if (listen(sock, 3) < 0)
+		error(-1, errno, "listen");
+
+	if (getsockname(sock, (struct sockaddr *)&laddr, &len) == -1)
+		error(-1, errno, "getsockname");
+
+	fprintf(stderr, "server port: %d\n", ntohs(laddr.sin_port));
+	child_pid = fork();
+	if (!child_pid)
+		client(ntohs(laddr.sin_port));
+	else
+		server(sock, laddr);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/net/fin_ack_lat.sh b/tools/testing/selftests/net/fin_ack_lat.sh
new file mode 100755
index 000000000000..a3ff6e0b2c7a
--- /dev/null
+++ b/tools/testing/selftests/net/fin_ack_lat.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test latency spikes caused by FIN/ACK handling race.
+
+set +x
+set -e
+
+tmpfile=$(mktemp /tmp/fin_ack_latency.XXXX.log)
+
+cleanup() {
+	kill $(pidof fin_ack_lat)
+	rm -f $tmpfile
+}
+
+trap cleanup EXIT
+
+do_test() {
+	RUNTIME=$1
+
+	./fin_ack_lat | tee $tmpfile &
+	PID=$!
+
+	sleep $RUNTIME
+	NR_SPIKES=$(wc -l $tmpfile | awk '{print $1}')
+	if [ $NR_SPIKES -gt 0 ]
+	then
+		echo "FAIL: $NR_SPIKES spikes detected"
+		return 1
+	fi
+	return 0
+}
+
+do_test "30"
+echo "test done"
diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 8d069490e17b..3a779c084d96 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -2,3 +2,4 @@ pidfd_open_test
 pidfd_poll_test
 pidfd_test
 pidfd_wait
+pidfd_getfd_test
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 43db1b98e845..75a545861375 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 CFLAGS += -g -I../../../../usr/include/ -pthread
 
-TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait
+TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test pidfd_poll_test pidfd_wait pidfd_getfd_test
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index c6bc68329f4b..d482515604db 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -36,6 +36,10 @@
 #define __NR_clone3 -1
 #endif
 
+#ifndef __NR_pidfd_getfd
+#define __NR_pidfd_getfd -1
+#endif
+
 /*
  * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c
  * That means, when it wraps around any pid < 300 will be skipped.
@@ -84,4 +88,9 @@ static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info,
 	return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags);
 }
 
+static inline int sys_pidfd_getfd(int pidfd, int fd, int flags)
+{
+	return syscall(__NR_pidfd_getfd, pidfd, fd, flags);
+}
+
 #endif /* __PIDFD_H */
diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
new file mode 100644
index 000000000000..401a7c1d0312
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <linux/kcmp.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+/*
+ * UNKNOWN_FD is an fd number that should never exist in the child, as it is
+ * used to check the negative case.
+ */
+#define UNKNOWN_FD 111
+#define UID_NOBODY 65535
+
+static int sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1,
+		    unsigned long idx2)
+{
+	return syscall(__NR_kcmp, pid1, pid2, type, idx1, idx2);
+}
+
+static int sys_memfd_create(const char *name, unsigned int flags)
+{
+	return syscall(__NR_memfd_create, name, flags);
+}
+
+static int __child(int sk, int memfd)
+{
+	int ret;
+	char buf;
+
+	/*
+	 * Ensure we don't leave around a bunch of orphaned children if our
+	 * tests fail.
+	 */
+	ret = prctl(PR_SET_PDEATHSIG, SIGKILL);
+	if (ret) {
+		fprintf(stderr, "%s: Child could not set DEATHSIG\n",
+			strerror(errno));
+		return -1;
+	}
+
+	ret = send(sk, &memfd, sizeof(memfd), 0);
+	if (ret != sizeof(memfd)) {
+		fprintf(stderr, "%s: Child failed to send fd number\n",
+			strerror(errno));
+		return -1;
+	}
+
+	/*
+	 * The fixture setup is completed at this point. The tests will run.
+	 *
+	 * This blocking recv enables the parent to message the child.
+	 * Either we will read 'P' off of the sk, indicating that we need
+	 * to disable ptrace, or we will read a 0, indicating that the other
+	 * side has closed the sk. This occurs during fixture teardown time,
+	 * indicating that the child should exit.
+	 */
+	while ((ret = recv(sk, &buf, sizeof(buf), 0)) > 0) {
+		if (buf == 'P') {
+			ret = prctl(PR_SET_DUMPABLE, 0);
+			if (ret < 0) {
+				fprintf(stderr,
+					"%s: Child failed to disable ptrace\n",
+					strerror(errno));
+				return -1;
+			}
+		} else {
+			fprintf(stderr, "Child received unknown command %c\n",
+				buf);
+			return -1;
+		}
+		ret = send(sk, &buf, sizeof(buf), 0);
+		if (ret != 1) {
+			fprintf(stderr, "%s: Child failed to ack\n",
+				strerror(errno));
+			return -1;
+		}
+	}
+	if (ret < 0) {
+		fprintf(stderr, "%s: Child failed to read from socket\n",
+			strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int child(int sk)
+{
+	int memfd, ret;
+
+	memfd = sys_memfd_create("test", 0);
+	if (memfd < 0) {
+		fprintf(stderr, "%s: Child could not create memfd\n",
+			strerror(errno));
+		ret = -1;
+	} else {
+		ret = __child(sk, memfd);
+		close(memfd);
+	}
+
+	close(sk);
+	return ret;
+}
+
+FIXTURE(child)
+{
+	/*
+	 * remote_fd is the number of the FD which we are trying to retrieve
+	 * from the child.
+	 */
+	int remote_fd;
+	/* pid points to the child which we are fetching FDs from */
+	pid_t pid;
+	/* pidfd is the pidfd of the child */
+	int pidfd;
+	/*
+	 * sk is our side of the socketpair used to communicate with the child.
+	 * When it is closed, the child will exit.
+	 */
+	int sk;
+};
+
+FIXTURE_SETUP(child)
+{
+	int ret, sk_pair[2];
+
+	ASSERT_EQ(0, socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair)) {
+		TH_LOG("%s: failed to create socketpair", strerror(errno));
+	}
+	self->sk = sk_pair[0];
+
+	self->pid = fork();
+	ASSERT_GE(self->pid, 0);
+
+	if (self->pid == 0) {
+		close(sk_pair[0]);
+		if (child(sk_pair[1]))
+			_exit(EXIT_FAILURE);
+		_exit(EXIT_SUCCESS);
+	}
+
+	close(sk_pair[1]);
+
+	self->pidfd = sys_pidfd_open(self->pid, 0);
+	ASSERT_GE(self->pidfd, 0);
+
+	/*
+	 * Wait for the child to complete setup. It'll send the remote memfd's
+	 * number when ready.
+	 */
+	ret = recv(sk_pair[0], &self->remote_fd, sizeof(self->remote_fd), 0);
+	ASSERT_EQ(sizeof(self->remote_fd), ret);
+}
+
+FIXTURE_TEARDOWN(child)
+{
+	EXPECT_EQ(0, close(self->pidfd));
+	EXPECT_EQ(0, close(self->sk));
+
+	EXPECT_EQ(0, wait_for_pid(self->pid));
+}
+
+TEST_F(child, disable_ptrace)
+{
+	int uid, fd;
+	char c;
+
+	/*
+	 * Turn into nobody if we're root, to avoid CAP_SYS_PTRACE
+	 *
+	 * The tests should run in their own process, so even this test fails,
+	 * it shouldn't result in subsequent tests failing.
+	 */
+	uid = getuid();
+	if (uid == 0)
+		ASSERT_EQ(0, seteuid(UID_NOBODY));
+
+	ASSERT_EQ(1, send(self->sk, "P", 1, 0));
+	ASSERT_EQ(1, recv(self->sk, &c, 1, 0));
+
+	fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
+	EXPECT_EQ(-1, fd);
+	EXPECT_EQ(EPERM, errno);
+
+	if (uid == 0)
+		ASSERT_EQ(0, seteuid(0));
+}
+
+TEST_F(child, fetch_fd)
+{
+	int fd, ret;
+
+	fd = sys_pidfd_getfd(self->pidfd, self->remote_fd, 0);
+	ASSERT_GE(fd, 0);
+
+	EXPECT_EQ(0, sys_kcmp(getpid(), self->pid, KCMP_FILE, fd, self->remote_fd));
+
+	ret = fcntl(fd, F_GETFD);
+	ASSERT_GE(ret, 0);
+	EXPECT_GE(ret & FD_CLOEXEC, 0);
+
+	close(fd);
+}
+
+TEST_F(child, test_unknown_fd)
+{
+	int fd;
+
+	fd = sys_pidfd_getfd(self->pidfd, UNKNOWN_FD, 0);
+	EXPECT_EQ(-1, fd) {
+		TH_LOG("getfd succeeded while fetching unknown fd");
+	};
+	EXPECT_EQ(EBADF, errno) {
+		TH_LOG("%s: getfd did not get EBADF", strerror(errno));
+	}
+}
+
+TEST(flags_set)
+{
+	ASSERT_EQ(-1, sys_pidfd_getfd(0, 0, 1));
+	EXPECT_EQ(errno, EINVAL);
+}
+
+#if __NR_pidfd_getfd == -1
+int main(void)
+{
+	fprintf(stderr, "__NR_pidfd_getfd undefined. The pidfd_getfd syscall is unavailable. Test aborting\n");
+	return KSFT_SKIP;
+}
+#else
+TEST_HARNESS_MAIN
+#endif
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
index 26112ab5cdf4..f52ed92b53e7 100755
--- a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
+++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
@@ -53,9 +53,13 @@ eeh_one_dev() {
 	# is a no-op.
 	echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check
 
-	# Enforce a 30s timeout for recovery. Even the IPR, which is infamously
-	# slow to reset, should recover within 30s.
-	max_wait=30
+	# Default to a 60s timeout when waiting for a device to recover. This
+	# is an arbitrary default which can be overridden by setting the
+	# EEH_MAX_WAIT environmental variable when required.
+
+	# The current record holder for longest recovery time is:
+	#  "Adaptec Series 8 12G SAS/PCIe 3" at 39 seconds
+	max_wait=${EEH_MAX_WAIT:=60}
 
 	for i in `seq 0 ${max_wait}` ; do
 		if pe_ok $dev ; then
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 7101ffd08d66..0ebeaea22641 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -5,3 +5,4 @@ prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation
+bad_accesses
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index ed1565809d2b..b9103c4bb414 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -3,7 +3,7 @@ noarg:
 	$(MAKE) -C ../
 
 TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
-		  large_vm_fork_separation
+		  large_vm_fork_separation bad_accesses
 TEST_GEN_PROGS_EXTENDED := tlbie_test
 TEST_GEN_FILES := tempfile
 
@@ -16,6 +16,7 @@ $(OUTPUT)/prot_sao: ../utils.c
 
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
+$(OUTPUT)/bad_accesses: CFLAGS += -m64
 
 $(OUTPUT)/tempfile:
 	dd if=/dev/zero of=$@ bs=64k count=1
diff --git a/tools/testing/selftests/powerpc/mm/bad_accesses.c b/tools/testing/selftests/powerpc/mm/bad_accesses.c
new file mode 100644
index 000000000000..adc465f499ef
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/bad_accesses.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2019, Michael Ellerman, IBM Corp.
+//
+// Test that out-of-bounds reads/writes behave as expected.
+
+#include <setjmp.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "utils.h"
+
+// Old distros (Ubuntu 16.04 at least) don't define this
+#ifndef SEGV_BNDERR
+#define SEGV_BNDERR	3
+#endif
+
+// 64-bit kernel is always here
+#define PAGE_OFFSET	(0xcul << 60)
+
+static unsigned long kernel_virt_end;
+
+static volatile int fault_code;
+static volatile unsigned long fault_addr;
+static jmp_buf setjmp_env;
+
+static void segv_handler(int n, siginfo_t *info, void *ctxt_v)
+{
+	fault_code = info->si_code;
+	fault_addr = (unsigned long)info->si_addr;
+	siglongjmp(setjmp_env, 1);
+}
+
+int bad_access(char *p, bool write)
+{
+	char x;
+
+	fault_code = 0;
+	fault_addr = 0;
+
+	if (sigsetjmp(setjmp_env, 1) == 0) {
+		if (write)
+			*p = 1;
+		else
+			x = *p;
+
+		printf("Bad - no SEGV! (%c)\n", x);
+		return 1;
+	}
+
+	// If we see MAPERR that means we took a page fault rather than an SLB
+	// miss. We only expect to take page faults for addresses within the
+	// valid kernel range.
+	FAIL_IF(fault_code == SEGV_MAPERR && \
+		(fault_addr < PAGE_OFFSET || fault_addr >= kernel_virt_end));
+
+	FAIL_IF(fault_code != SEGV_MAPERR && fault_code != SEGV_BNDERR);
+
+	return 0;
+}
+
+static int using_hash_mmu(bool *using_hash)
+{
+	char line[128];
+	FILE *f;
+	int rc;
+
+	f = fopen("/proc/cpuinfo", "r");
+	FAIL_IF(!f);
+
+	rc = 0;
+	while (fgets(line, sizeof(line), f) != NULL) {
+		if (strcmp(line, "MMU		: Hash\n") == 0) {
+			*using_hash = true;
+			goto out;
+		}
+
+		if (strcmp(line, "MMU		: Radix\n") == 0) {
+			*using_hash = false;
+			goto out;
+		}
+	}
+
+	rc = -1;
+out:
+	fclose(f);
+	return rc;
+}
+
+static int test(void)
+{
+	unsigned long i, j, addr, region_shift, page_shift, page_size;
+	struct sigaction sig;
+	bool hash_mmu;
+
+	sig = (struct sigaction) {
+		.sa_sigaction = segv_handler,
+		.sa_flags = SA_SIGINFO,
+	};
+
+	FAIL_IF(sigaction(SIGSEGV, &sig, NULL) != 0);
+
+	FAIL_IF(using_hash_mmu(&hash_mmu));
+
+	page_size = sysconf(_SC_PAGESIZE);
+	if (page_size == (64 * 1024))
+		page_shift = 16;
+	else
+		page_shift = 12;
+
+	if (page_size == (64 * 1024) || !hash_mmu) {
+		region_shift = 52;
+
+		// We have 7 512T regions (4 kernel linear, vmalloc, io, vmemmap)
+		kernel_virt_end = PAGE_OFFSET + (7 * (512ul << 40));
+	} else if (page_size == (4 * 1024) && hash_mmu) {
+		region_shift = 46;
+
+		// We have 7 64T regions (4 kernel linear, vmalloc, io, vmemmap)
+		kernel_virt_end = PAGE_OFFSET + (7 * (64ul << 40));
+	} else
+		FAIL_IF(true);
+
+	printf("Using %s MMU, PAGE_SIZE = %dKB start address 0x%016lx\n",
+	       hash_mmu ? "hash" : "radix",
+	       (1 << page_shift) >> 10,
+	       1ul << region_shift);
+
+	// This generates access patterns like:
+	//   0x0010000000000000
+	//   0x0010000000010000
+	//   0x0010000000020000
+	//   ...
+	//   0x0014000000000000
+	//   0x0018000000000000
+	//   0x0020000000000000
+	//   0x0020000000010000
+	//   0x0020000000020000
+	//   ...
+	//   0xf400000000000000
+	//   0xf800000000000000
+
+	for (i = 1; i <= ((0xful << 60) >> region_shift); i++) {
+		for (j = page_shift - 1; j < 60; j++) {
+			unsigned long base, delta;
+
+			base  = i << region_shift;
+			delta = 1ul << j;
+
+			if (delta >= base)
+				break;
+
+			addr = (base | delta) & ~((1 << page_shift) - 1);
+
+			FAIL_IF(bad_access((char *)addr, false));
+			FAIL_IF(bad_access((char *)addr, true));
+		}
+	}
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test, "bad_accesses");
+}
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
index 7deedbc16b0b..fc477dfe86a2 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
@@ -455,9 +455,8 @@ run_tests(pid_t child_pid, struct ppc_debug_info *dbginfo, bool dawr)
 	if (dbginfo->features & PPC_DEBUG_FEATURE_DATA_BP_RANGE) {
 		test_sethwdebug_exact(child_pid);
 
-		if (!is_8xx)
-			test_sethwdebug_range_aligned(child_pid);
-		if (dawr && !is_8xx) {
+		test_sethwdebug_range_aligned(child_pid);
+		if (dawr || is_8xx) {
 			test_sethwdebug_range_unaligned(child_pid);
 			test_sethwdebug_range_unaligned_dar(child_pid);
 			test_sethwdebug_dawr_max_range(child_pid);
diff --git a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
index e98c36750fae..d34fe06268d2 100644
--- a/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
+++ b/tools/testing/selftests/tc-testing/plugin-lib/buildebpfPlugin.py
@@ -54,7 +54,7 @@ class SubPlugin(TdcPlugin):
             shell=True,
             stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,
-            env=ENVIR)
+            env=os.environ.copy())
         (rawout, serr) = proc.communicate()
 
         if proc.returncode != 0 and len(serr) > 0:
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
index 2e361cea63bc..98a20faf3198 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json
@@ -6,6 +6,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -25,6 +28,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -44,6 +50,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -63,6 +72,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -82,6 +94,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -101,6 +116,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -120,6 +138,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -139,6 +160,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -158,6 +182,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -177,6 +204,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -196,6 +226,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -215,6 +248,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -234,6 +270,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -253,6 +292,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -272,6 +314,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -291,6 +336,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
@@ -310,6 +358,9 @@
             "filter",
             "basic"
         ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 485cf06ef013..389327e9b30a 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -18,6 +18,9 @@
 #define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
 #define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE	0x01	/* check pte is writable */
+
 struct gup_benchmark {
 	__u64 get_delta_usec;
 	__u64 put_delta_usec;
@@ -85,7 +88,8 @@ int main(int argc, char **argv)
 	}
 
 	gup.nr_pages_per_call = nr_pages;
-	gup.flags = write;
+	if (write)
+		gup.flags |= FOLL_WRITE;
 
 	fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
 	if (fd == -1)
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 68092d15e12b..9b68658b6bb8 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -720,11 +720,11 @@ static void slab_debug(struct slabinfo *s)
 		return;
 
 	if (sanity && !s->sanity_checks) {
-		set_obj(s, "sanity", 1);
+		set_obj(s, "sanity_checks", 1);
 	}
 	if (!sanity && s->sanity_checks) {
 		if (slab_empty(s))
-			set_obj(s, "sanity", 0);
+			set_obj(s, "sanity_checks", 0);
 		else
 			fprintf(stderr, "%s not empty cannot disable sanity checks\n", s->name);
 	}
diff --git a/usr/.gitignore b/usr/.gitignore
index be5eae1df7eb..610de736b75e 100644
--- a/usr/.gitignore
+++ b/usr/.gitignore
@@ -1,9 +1,3 @@
-#
-# Generated files
-#
 gen_init_cpio
 initramfs_data.cpio
-initramfs_data.cpio.gz
-initramfs_data.cpio.bz2
-initramfs_data.cpio.lzma
-initramfs_list
+/initramfs_inc_data
diff --git a/usr/Kconfig b/usr/Kconfig
index a6b68503d177..bdf5bbd40727 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -54,7 +54,6 @@ config INITRAMFS_ROOT_GID
 
 config RD_GZIP
 	bool "Support initial ramdisk/ramfs compressed using gzip"
-	depends on BLK_DEV_INITRD
 	default y
 	select DECOMPRESS_GZIP
 	help
@@ -64,7 +63,6 @@ config RD_GZIP
 config RD_BZIP2
 	bool "Support initial ramdisk/ramfs compressed using bzip2"
 	default y
-	depends on BLK_DEV_INITRD
 	select DECOMPRESS_BZIP2
 	help
 	  Support loading of a bzip2 encoded initial ramdisk or cpio buffer
@@ -73,7 +71,6 @@ config RD_BZIP2
 config RD_LZMA
 	bool "Support initial ramdisk/ramfs compressed using LZMA"
 	default y
-	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZMA
 	help
 	  Support loading of a LZMA encoded initial ramdisk or cpio buffer
@@ -81,7 +78,6 @@ config RD_LZMA
 
 config RD_XZ
 	bool "Support initial ramdisk/ramfs compressed using XZ"
-	depends on BLK_DEV_INITRD
 	default y
 	select DECOMPRESS_XZ
 	help
@@ -91,7 +87,6 @@ config RD_XZ
 config RD_LZO
 	bool "Support initial ramdisk/ramfs compressed using LZO"
 	default y
-	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZO
 	help
 	  Support loading of a LZO encoded initial ramdisk or cpio buffer
@@ -100,7 +95,6 @@ config RD_LZO
 config RD_LZ4
 	bool "Support initial ramdisk/ramfs compressed using LZ4"
 	default y
-	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZ4
 	help
 	  Support loading of a LZ4 encoded initial ramdisk or cpio buffer
@@ -108,8 +102,7 @@ config RD_LZ4
 
 choice
 	prompt "Built-in initramfs compression mode"
-	depends on INITRAMFS_SOURCE!=""
-	optional
+	depends on INITRAMFS_SOURCE != ""
 	help
 	  This option allows you to decide by which algorithm the builtin
 	  initramfs will be compressed.  Several compression algorithms are
@@ -215,21 +208,3 @@ config INITRAMFS_COMPRESSION_LZ4
 	  by default which could cause a build failure.
 
 endchoice
-
-config INITRAMFS_COMPRESSION
-	depends on INITRAMFS_SOURCE!=""
-	string
-	default ""      if INITRAMFS_COMPRESSION_NONE
-	default ".gz"   if INITRAMFS_COMPRESSION_GZIP
-	default ".bz2"  if INITRAMFS_COMPRESSION_BZIP2
-	default ".lzma" if INITRAMFS_COMPRESSION_LZMA
-	default ".xz"   if INITRAMFS_COMPRESSION_XZ
-	default ".lzo"  if INITRAMFS_COMPRESSION_LZO
-	default ".lz4"  if INITRAMFS_COMPRESSION_LZ4
-	default ".gz"   if RD_GZIP
-	default ".lz4"  if RD_LZ4
-	default ".lzo"  if RD_LZO
-	default ".xz"   if RD_XZ
-	default ".lzma" if RD_LZMA
-	default ".bz2"  if RD_BZIP2
-	default ""
diff --git a/usr/Makefile b/usr/Makefile
index e6f7cb2f81db..b6081bb2cc72 100644
--- a/usr/Makefile
+++ b/usr/Makefile
@@ -3,61 +3,86 @@
 # kbuild file for usr/ - including initramfs image
 #
 
-klibcdirs:;
-PHONY += klibcdirs
+# cmd_bzip2, cmd_lzma, cmd_lzo, cmd_lz4 from scripts/Makefile.lib appends the
+# size at the end of the compressed file, which unfortunately does not work
+# with unpack_to_rootfs(). Make size_append no-op.
+override size_append := :
 
-suffix_y = $(subst $\",,$(CONFIG_INITRAMFS_COMPRESSION))
-datafile_y = initramfs_data.cpio$(suffix_y)
-datafile_d_y = .$(datafile_y).d
-AFLAGS_initramfs_data.o += -DINITRAMFS_IMAGE="usr/$(datafile_y)"
+compress-y					:= shipped
+compress-$(CONFIG_INITRAMFS_COMPRESSION_GZIP)	:= gzip
+compress-$(CONFIG_INITRAMFS_COMPRESSION_BZIP2)	:= bzip2
+compress-$(CONFIG_INITRAMFS_COMPRESSION_LZMA)	:= lzma
+compress-$(CONFIG_INITRAMFS_COMPRESSION_XZ)	:= xzmisc
+compress-$(CONFIG_INITRAMFS_COMPRESSION_LZO)	:= lzo
+compress-$(CONFIG_INITRAMFS_COMPRESSION_LZ4)	:= lz4
 
-# clean rules do not have CONFIG_INITRAMFS_COMPRESSION.  So clean up after all
-# possible compression formats.
-clean-files += initramfs_data.cpio*
-
-# Generate builtin.o based on initramfs_data.o
 obj-$(CONFIG_BLK_DEV_INITRD) := initramfs_data.o
 
-# initramfs_data.o contains the compressed initramfs_data.cpio image.
-# The image is included using .incbin, a dependency which is not
-# tracked automatically.
-$(obj)/initramfs_data.o: $(obj)/$(datafile_y) FORCE
+$(obj)/initramfs_data.o: $(obj)/initramfs_inc_data
+
+ramfs-input := $(strip $(shell echo $(CONFIG_INITRAMFS_SOURCE)))
+cpio-data :=
+
+# If CONFIG_INITRAMFS_SOURCE is empty, generate a small initramfs with the
+# default contents.
+ifeq ($(ramfs-input),)
+ramfs-input := $(srctree)/$(src)/default_cpio_list
+endif
+
+ifeq ($(words $(ramfs-input)),1)
+
+# If CONFIG_INITRAMFS_SOURCE specifies a single file, and it is suffixed with
+# .cpio, use it directly as an initramfs.
+ifneq ($(filter %.cpio,$(ramfs-input)),)
+cpio-data := $(ramfs-input)
+endif
+
+# If CONFIG_INITRAMFS_SOURCE specifies a single file, and it is suffixed with
+# .cpio.*, use it directly as an initramfs, and avoid double compression.
+ifeq ($(words $(subst .cpio.,$(space),$(ramfs-input))),2)
+cpio-data := $(ramfs-input)
+compress-y := shipped
+endif
+
+endif
+
+# For other cases, generate the initramfs cpio archive based on the contents
+# specified by CONFIG_INITRAMFS_SOURCE.
+ifeq ($(cpio-data),)
 
-#####
-# Generate the initramfs cpio archive
+cpio-data := $(obj)/initramfs_data.cpio
 
 hostprogs-y := gen_init_cpio
-initramfs   := $(CONFIG_SHELL) $(srctree)/$(src)/gen_initramfs_list.sh
-ramfs-input := $(if $(filter-out "",$(CONFIG_INITRAMFS_SOURCE)), \
-			$(shell echo $(CONFIG_INITRAMFS_SOURCE)),-d)
-ramfs-args  := \
-        $(if $(CONFIG_INITRAMFS_ROOT_UID), -u $(CONFIG_INITRAMFS_ROOT_UID)) \
-        $(if $(CONFIG_INITRAMFS_ROOT_GID), -g $(CONFIG_INITRAMFS_ROOT_GID))
-
-# $(datafile_d_y) is used to identify all files included
+
+# .initramfs_data.cpio.d is used to identify all files included
 # in initramfs and to detect if any files are added/removed.
 # Removed files are identified by directory timestamp being updated
 # The dependency list is generated by gen_initramfs.sh -l
-ifneq ($(wildcard $(obj)/$(datafile_d_y)),)
-	include $(obj)/$(datafile_d_y)
-endif
-
-quiet_cmd_initfs = GEN     $@
-      cmd_initfs = $(initramfs) -o $@ $(ramfs-args) $(ramfs-input)
-
-targets := $(datafile_y)
+-include $(obj)/.initramfs_data.cpio.d
 
 # do not try to update files included in initramfs
 $(deps_initramfs): ;
 
-$(deps_initramfs): klibcdirs
+quiet_cmd_initfs = GEN     $@
+      cmd_initfs = \
+	$(CONFIG_SHELL) $< -o $@ -l $(obj)/.initramfs_data.cpio.d \
+	$(if $(CONFIG_INITRAMFS_ROOT_UID), -u $(CONFIG_INITRAMFS_ROOT_UID)) \
+	$(if $(CONFIG_INITRAMFS_ROOT_GID), -g $(CONFIG_INITRAMFS_ROOT_GID)) \
+	$(ramfs-input)
+
 # We rebuild initramfs_data.cpio if:
 # 1) Any included file is newer than initramfs_data.cpio
 # 2) There are changes in which files are included (added or deleted)
 # 3) If gen_init_cpio are newer than initramfs_data.cpio
 # 4) Arguments to gen_initramfs.sh changes
-$(obj)/$(datafile_y): $(obj)/gen_init_cpio $(deps_initramfs) klibcdirs
-	$(Q)$(initramfs) -l $(ramfs-input) > $(obj)/$(datafile_d_y)
+$(obj)/initramfs_data.cpio: $(src)/gen_initramfs.sh $(obj)/gen_init_cpio $(deps_initramfs) FORCE
 	$(call if_changed,initfs)
 
+endif
+
+$(obj)/initramfs_inc_data: $(cpio-data) FORCE
+	$(call if_changed,$(compress-y))
+
+targets += initramfs_data.cpio initramfs_inc_data
+
 subdir-$(CONFIG_UAPI_HEADER_TEST) += include
diff --git a/usr/default_cpio_list b/usr/default_cpio_list
new file mode 100644
index 000000000000..37b3864066e8
--- /dev/null
+++ b/usr/default_cpio_list
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# This is a very simple, default initramfs
+
+dir /dev 0755 0 0
+nod /dev/console 0600 0 0 c 5 1
+dir /root 0700 0 0
diff --git a/usr/gen_initramfs_list.sh b/usr/gen_initramfs.sh
index 2bbac73e6477..8ae831657e5d 100755
--- a/usr/gen_initramfs_list.sh
+++ b/usr/gen_initramfs.sh
@@ -5,8 +5,7 @@
 # Released under the terms of the GNU GPL
 #
 # Generate a cpio packed initramfs. It uses gen_init_cpio to generate
-# the cpio archive, and then compresses it.
-# The script may also be used to generate the inputfile used for gen_init_cpio
+# the cpio archive.
 # This script assumes that gen_init_cpio is located in usr/ directory
 
 # error out on errors
@@ -15,9 +14,9 @@ set -e
 usage() {
 cat << EOF
 Usage:
-$0 [-o <file>] [-u <uid>] [-g <gid>] {-d | <cpio_source>} ...
-	-o <file>      Create compressed initramfs file named <file> using
-		       gen_init_cpio and compressor depending on the extension
+$0 [-o <file>] [-l <dep_list>] [-u <uid>] [-g <gid>] {-d | <cpio_source>} ...
+	-o <file>      Create initramfs file named <file> by using gen_init_cpio
+	-l <dep_list>  Create dependency list named <dep_list>
 	-u <uid>       User ID to map to user ID 0 (root).
 		       <uid> is only meaningful if <cpio_source> is a
 		       directory.  "squash" forces all files to uid 0.
@@ -27,7 +26,6 @@ $0 [-o <file>] [-u <uid>] [-g <gid>] {-d | <cpio_source>} ...
 	<cpio_source>  File list or directory for cpio archive.
 		       If <cpio_source> is a .cpio file it will be used
 		       as direct input to initramfs.
-	-d             Output the default cpio list.
 
 All options except -o and -l may be repeated and are interpreted
 sequentially and immediately.  -u and -g states are preserved across
@@ -42,23 +40,6 @@ field() {
 	shift $1 ; echo $1
 }
 
-list_default_initramfs() {
-	# echo usr/kinit/kinit
-	:
-}
-
-default_initramfs() {
-	cat <<-EOF >> ${output}
-		# This is a very simple, default initramfs
-
-		dir /dev 0755 0 0
-		nod /dev/console 0600 0 0 c 5 1
-		dir /root 0700 0 0
-		# file /kinit usr/kinit/kinit 0755 0 0
-		# slink /init kinit 0755 0 0
-	EOF
-}
-
 filetype() {
 	local argv1="$1"
 
@@ -81,10 +62,6 @@ filetype() {
 	return 0
 }
 
-list_print_mtime() {
-	:
-}
-
 print_mtime() {
 	local my_mtime="0"
 
@@ -92,15 +69,15 @@ print_mtime() {
 		my_mtime=$(find "$1" -printf "%T@\n" | sort -r | head -n 1)
 	fi
 
-	echo "# Last modified: ${my_mtime}" >> ${output}
-	echo "" >> ${output}
+	echo "# Last modified: ${my_mtime}" >> $cpio_list
+	echo "" >> $cpio_list
 }
 
 list_parse() {
-	if [ -L "$1" ]; then
+	if [ -z "$dep_list" -o -L "$1" ]; then
 		return
 	fi
-	echo "$1" | sed 's/:/\\:/g; s/$/ \\/'
+	echo "$1" | sed 's/:/\\:/g; s/$/ \\/' >> $dep_list
 }
 
 # for each file print a line in following format
@@ -146,7 +123,7 @@ parse() {
 			;;
 	esac
 
-	echo "${str}" >> ${output}
+	echo "${str}" >> $cpio_list
 
 	return 0
 }
@@ -161,58 +138,47 @@ unknown_option() {
 	exit 1
 }
 
-list_header() {
-	:
-}
-
 header() {
-	printf "\n#####################\n# $1\n" >> ${output}
+	printf "\n#####################\n# $1\n" >> $cpio_list
 }
 
 # process one directory (incl sub-directories)
 dir_filelist() {
-	${dep_list}header "$1"
+	header "$1"
 
 	srcdir=$(echo "$1" | sed -e 's://*:/:g')
 	dirlist=$(find "${srcdir}" -printf "%p %m %U %G\n" | LANG=C sort)
 
 	# If $dirlist is only one line, then the directory is empty
 	if [  "$(echo "${dirlist}" | wc -l)" -gt 1 ]; then
-		${dep_list}print_mtime "$1"
+		print_mtime "$1"
 
 		echo "${dirlist}" | \
 		while read x; do
-			${dep_list}parse ${x}
+			list_parse $x
+			parse $x
 		done
 	fi
 }
 
-# if only one file is specified and it is .cpio file then use it direct as fs
-# if a directory is specified then add all files in given direcotry to fs
-# if a regular file is specified assume it is in gen_initramfs format
 input_file() {
 	source="$1"
 	if [ -f "$1" ]; then
-		${dep_list}header "$1"
-		is_cpio="$(echo "$1" | sed 's/^.*\.cpio\(\..*\)\{0,1\}/cpio/')"
-		if [ $2 -eq 0 -a ${is_cpio} = "cpio" ]; then
-			cpio_file=$1
-			echo "$1" | grep -q '^.*\.cpio\..*' && is_cpio_compressed="compressed"
-			[ ! -z ${dep_list} ] && echo "$1"
-			return 0
-		fi
-		if [ -z ${dep_list} ]; then
-			print_mtime "$1" >> ${output}
-			cat "$1"         >> ${output}
-		else
-		        echo "$1 \\"
+		# If a regular file is specified, assume it is in
+		# gen_init_cpio format
+		header "$1"
+		print_mtime "$1" >> $cpio_list
+		cat "$1"         >> $cpio_list
+		if [ -n "$dep_list" ]; then
+		        echo "$1 \\"  >> $dep_list
 			cat "$1" | while read type dir file perm ; do
 				if [ "$type" = "file" ]; then
-					echo "$file \\";
+					echo "$file \\" >> $dep_list
 				fi
 			done
 		fi
 	elif [ -d "$1" ]; then
+		# If a directory is specified then add all files in it to fs
 		dir_filelist "$1"
 	else
 		echo "  ${prog}: Cannot open '$1'" >&2
@@ -224,51 +190,24 @@ prog=$0
 root_uid=0
 root_gid=0
 dep_list=
-cpio_file=
-cpio_list=
+cpio_list=$(mktemp ${TMPDIR:-/tmp}/cpiolist.XXXXXX)
 output="/dev/stdout"
-output_file=""
-is_cpio_compressed=
-compr="gzip -n -9 -f"
 
-arg="$1"
-case "$arg" in
-	"-l")	# files included in initramfs - used by kbuild
-		dep_list="list_"
-		echo "deps_initramfs := $0 \\"
-		shift
-		;;
-	"-o")	# generate compressed cpio image named $1
-		shift
-		output_file="$1"
-		cpio_list="$(mktemp ${TMPDIR:-/tmp}/cpiolist.XXXXXX)"
-		output=${cpio_list}
-		echo "$output_file" | grep -q "\.gz$" \
-                && [ -x "`which gzip 2> /dev/null`" ] \
-                && compr="gzip -n -9 -f"
-		echo "$output_file" | grep -q "\.bz2$" \
-                && [ -x "`which bzip2 2> /dev/null`" ] \
-                && compr="bzip2 -9 -f"
-		echo "$output_file" | grep -q "\.lzma$" \
-                && [ -x "`which lzma 2> /dev/null`" ] \
-                && compr="lzma -9 -f"
-		echo "$output_file" | grep -q "\.xz$" \
-                && [ -x "`which xz 2> /dev/null`" ] \
-                && compr="xz --check=crc32 --lzma2=dict=1MiB"
-		echo "$output_file" | grep -q "\.lzo$" \
-                && [ -x "`which lzop 2> /dev/null`" ] \
-                && compr="lzop -9 -f"
-		echo "$output_file" | grep -q "\.lz4$" \
-                && [ -x "`which lz4 2> /dev/null`" ] \
-                && compr="lz4 -l -9 -f"
-		echo "$output_file" | grep -q "\.cpio$" && compr="cat"
-		shift
-		;;
-esac
+trap "rm -f $cpio_list" EXIT
+
 while [ $# -gt 0 ]; do
 	arg="$1"
 	shift
 	case "$arg" in
+		"-l")	# files included in initramfs - used by kbuild
+			dep_list="$1"
+			echo "deps_initramfs := \\" > $dep_list
+			shift
+			;;
+		"-o")	# generate cpio image named $1
+			output="$1"
+			shift
+			;;
 		"-u")	# map $1 to uid=0 (root)
 			root_uid="$1"
 			[ "$root_uid" = "-1" ] && root_uid=$(id -u || echo 0)
@@ -279,10 +218,6 @@ while [ $# -gt 0 ]; do
 			[ "$root_gid" = "-1" ] && root_gid=$(id -g || echo 0)
 			shift
 			;;
-		"-d")	# display default initramfs list
-			default_list="$arg"
-			${dep_list}default_initramfs
-			;;
 		"-h")
 			usage
 			exit 0
@@ -293,36 +228,20 @@ while [ $# -gt 0 ]; do
 					unknown_option
 					;;
 				*)	# input file/dir - process it
-					input_file "$arg" "$#"
+					input_file "$arg"
 					;;
 			esac
 			;;
 	esac
 done
 
-# If output_file is set we will generate cpio archive and compress it
+# If output_file is set we will generate cpio archive
 # we are careful to delete tmp files
-if [ ! -z ${output_file} ]; then
-	if [ -z ${cpio_file} ]; then
-		timestamp=
-		if test -n "$KBUILD_BUILD_TIMESTAMP"; then
-			timestamp="$(date -d"$KBUILD_BUILD_TIMESTAMP" +%s || :)"
-			if test -n "$timestamp"; then
-				timestamp="-t $timestamp"
-			fi
-		fi
-		cpio_tfile="$(mktemp ${TMPDIR:-/tmp}/cpiofile.XXXXXX)"
-		usr/gen_init_cpio $timestamp ${cpio_list} > ${cpio_tfile}
-	else
-		cpio_tfile=${cpio_file}
-	fi
-	rm ${cpio_list}
-	if [ "${is_cpio_compressed}" = "compressed" ]; then
-		cat ${cpio_tfile} > ${output_file}
-	else
-		(cat ${cpio_tfile} | ${compr}  - > ${output_file}) \
-		|| (rm -f ${output_file} ; false)
+timestamp=
+if test -n "$KBUILD_BUILD_TIMESTAMP"; then
+	timestamp="$(date -d"$KBUILD_BUILD_TIMESTAMP" +%s || :)"
+	if test -n "$timestamp"; then
+		timestamp="-t $timestamp"
 	fi
-	[ -z ${cpio_file} ] && rm ${cpio_tfile}
 fi
-exit 0
+usr/gen_init_cpio $timestamp $cpio_list > $output
diff --git a/usr/include/Makefile b/usr/include/Makefile
index 84598469e6ff..a339ef325aa5 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -16,87 +16,88 @@ override c_flags = $(UAPI_CFLAGS) -Wp,-MD,$(depfile) -I$(objtree)/usr/include
 # Please consider to fix the header first.
 #
 # Sorted alphabetically.
-header-test- += asm/shmbuf.h
-header-test- += asm/signal.h
-header-test- += asm/ucontext.h
-header-test- += drm/vmwgfx_drm.h
-header-test- += linux/am437x-vpfe.h
-header-test- += linux/android/binder.h
-header-test- += linux/android/binderfs.h
-header-test- += linux/coda.h
-header-test- += linux/elfcore.h
-header-test- += linux/errqueue.h
-header-test- += linux/fsmap.h
-header-test- += linux/hdlc/ioctl.h
-header-test- += linux/ivtv.h
-header-test- += linux/kexec.h
-header-test- += linux/matroxfb.h
-header-test- += linux/nfc.h
-header-test- += linux/omap3isp.h
-header-test- += linux/omapfb.h
-header-test- += linux/patchkey.h
-header-test- += linux/phonet.h
-header-test- += linux/reiserfs_xattr.h
-header-test- += linux/sctp.h
-header-test- += linux/signal.h
-header-test- += linux/sysctl.h
-header-test- += linux/usb/audio.h
-header-test- += linux/v4l2-mediabus.h
-header-test- += linux/v4l2-subdev.h
-header-test- += linux/videodev2.h
-header-test- += linux/vm_sockets.h
-header-test- += sound/asequencer.h
-header-test- += sound/asoc.h
-header-test- += sound/asound.h
-header-test- += sound/compress_offload.h
-header-test- += sound/emu10k1.h
-header-test- += sound/sfnt_info.h
-header-test- += xen/evtchn.h
-header-test- += xen/gntdev.h
-header-test- += xen/privcmd.h
+no-header-test += asm/shmbuf.h
+no-header-test += asm/signal.h
+no-header-test += asm/ucontext.h
+no-header-test += drm/vmwgfx_drm.h
+no-header-test += linux/am437x-vpfe.h
+no-header-test += linux/android/binder.h
+no-header-test += linux/android/binderfs.h
+no-header-test += linux/coda.h
+no-header-test += linux/elfcore.h
+no-header-test += linux/errqueue.h
+no-header-test += linux/fsmap.h
+no-header-test += linux/hdlc/ioctl.h
+no-header-test += linux/ivtv.h
+no-header-test += linux/kexec.h
+no-header-test += linux/matroxfb.h
+no-header-test += linux/nfc.h
+no-header-test += linux/omap3isp.h
+no-header-test += linux/omapfb.h
+no-header-test += linux/patchkey.h
+no-header-test += linux/phonet.h
+no-header-test += linux/reiserfs_xattr.h
+no-header-test += linux/sctp.h
+no-header-test += linux/signal.h
+no-header-test += linux/sysctl.h
+no-header-test += linux/usb/audio.h
+no-header-test += linux/v4l2-mediabus.h
+no-header-test += linux/v4l2-subdev.h
+no-header-test += linux/videodev2.h
+no-header-test += linux/vm_sockets.h
+no-header-test += sound/asequencer.h
+no-header-test += sound/asoc.h
+no-header-test += sound/asound.h
+no-header-test += sound/compress_offload.h
+no-header-test += sound/emu10k1.h
+no-header-test += sound/sfnt_info.h
+no-header-test += xen/evtchn.h
+no-header-test += xen/gntdev.h
+no-header-test += xen/privcmd.h
 
 # More headers are broken in some architectures
 
 ifeq ($(SRCARCH),arc)
-header-test- += linux/bpf_perf_event.h
+no-header-test += linux/bpf_perf_event.h
 endif
 
 ifeq ($(SRCARCH),ia64)
-header-test- += asm/setup.h
-header-test- += asm/sigcontext.h
-header-test- += asm/perfmon.h
-header-test- += asm/perfmon_default_smpl.h
-header-test- += linux/if_bonding.h
+no-header-test += asm/setup.h
+no-header-test += asm/sigcontext.h
+no-header-test += asm/perfmon.h
+no-header-test += asm/perfmon_default_smpl.h
+no-header-test += linux/if_bonding.h
 endif
 
 ifeq ($(SRCARCH),mips)
-header-test- += asm/stat.h
+no-header-test += asm/stat.h
 endif
 
 ifeq ($(SRCARCH),powerpc)
-header-test- += asm/stat.h
-header-test- += linux/bpf_perf_event.h
+no-header-test += asm/stat.h
+no-header-test += linux/bpf_perf_event.h
 endif
 
 ifeq ($(SRCARCH),riscv)
-header-test- += linux/bpf_perf_event.h
+no-header-test += linux/bpf_perf_event.h
 endif
 
 ifeq ($(SRCARCH),sparc)
-header-test- += asm/stat.h
-header-test- += asm/uctx.h
-header-test- += asm/fbio.h
+no-header-test += asm/stat.h
+no-header-test += asm/uctx.h
+no-header-test += asm/fbio.h
 endif
 
 # asm-generic/*.h is used by asm/*.h, and should not be included directly
-header-test- += asm-generic/%
+no-header-test += asm-generic/%
 
 extra-y := $(patsubst $(obj)/%.h,%.hdrtest, $(shell find $(obj) -name '*.h' 2>/dev/null))
 
+# Include the header to detect missing include guard.
 quiet_cmd_hdrtest = HDRTEST $<
       cmd_hdrtest = \
 		$(CC) $(c_flags) -S -o /dev/null -x c /dev/null \
-			$(if $(filter-out $(header-test-), $*.h), -include $<); \
+			$(if $(filter-out $(no-header-test), $*.h), -include $< -include $<); \
 		$(PERL) $(srctree)/scripts/headers_check.pl $(obj) $(SRCARCH) $<; \
 		touch $@
 
diff --git a/usr/initramfs_data.S b/usr/initramfs_data.S
index d07648f05bbf..cd67edc38797 100644
--- a/usr/initramfs_data.S
+++ b/usr/initramfs_data.S
@@ -22,12 +22,9 @@
   in the ELF header, as required by certain architectures.
 */
 
-#include <linux/stringify.h>
-#include <asm-generic/vmlinux.lds.h>
-
 .section .init.ramfs,"a"
 __irf_start:
-.incbin __stringify(INITRAMFS_IMAGE)
+.incbin "usr/initramfs_inc_data"
 __irf_end:
 .section .init.ramfs.info,"a"
 .globl __initramfs_size
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index c4c57ba99e90..0a356aa91aa1 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -10,10 +10,15 @@
  * Author: Christoffer Dall <c.dall@virtualopensystems.com>
  */
 
+#include <linux/bits.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 
+#define DFSR_FSC_EXTABT_LPAE	0x10
+#define DFSR_FSC_EXTABT_nLPAE	0x08
+#define DFSR_LPAE		BIT(9)
+
 /*
  * Table taken from ARMv8 ARM DDI0487B-B, table G1-10.
  */
@@ -28,25 +33,115 @@ static const u8 return_offsets[8][2] = {
 	[7] = { 4, 4 },		/* FIQ, unused */
 };
 
+/*
+ * When an exception is taken, most CPSR fields are left unchanged in the
+ * handler. However, some are explicitly overridden (e.g. M[4:0]).
+ *
+ * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with
+ * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was
+ * obsoleted by the ARMv7 virtualization extensions and is RES0.
+ *
+ * For the SPSR layout seen from AArch32, see:
+ * - ARM DDI 0406C.d, page B1-1148
+ * - ARM DDI 0487E.a, page G8-6264
+ *
+ * For the SPSR_ELx layout for AArch32 seen from AArch64, see:
+ * - ARM DDI 0487E.a, page C5-426
+ *
+ * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from
+ * MSB to LSB.
+ */
+static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode)
+{
+	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
+	unsigned long old, new;
+
+	old = *vcpu_cpsr(vcpu);
+	new = 0;
+
+	new |= (old & PSR_AA32_N_BIT);
+	new |= (old & PSR_AA32_Z_BIT);
+	new |= (old & PSR_AA32_C_BIT);
+	new |= (old & PSR_AA32_V_BIT);
+	new |= (old & PSR_AA32_Q_BIT);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See ARM DDI 0487E.a, section G1.12.3
+	// See ARM DDI 0406C.d, section B1.8.3
+
+	new |= (old & PSR_AA32_DIT_BIT);
+
+	// CPSR.SSBS is set to SCTLR.DSSBS upon any exception
+	// See ARM DDI 0487E.a, page G8-6244
+	if (sctlr & BIT(31))
+		new |= PSR_AA32_SSBS_BIT;
+
+	// CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0
+	// SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented
+	// See ARM DDI 0487E.a, page G8-6246
+	new |= (old & PSR_AA32_PAN_BIT);
+	if (!(sctlr & BIT(23)))
+		new |= PSR_AA32_PAN_BIT;
+
+	// SS does not exist in AArch32, so ignore
+
+	// CPSR.IL is set to zero upon any exception
+	// See ARM DDI 0487E.a, page G1-5527
+
+	new |= (old & PSR_AA32_GE_MASK);
+
+	// CPSR.IT[7:0] are set to zero upon any exception
+	// See prior comment above
+
+	// CPSR.E is set to SCTLR.EE upon any exception
+	// See ARM DDI 0487E.a, page G8-6245
+	// See ARM DDI 0406C.d, page B4-1701
+	if (sctlr & BIT(25))
+		new |= PSR_AA32_E_BIT;
+
+	// CPSR.A is unchanged upon an exception to Undefined, Supervisor
+	// CPSR.A is set upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_A_BIT);
+	if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC)
+		new |= PSR_AA32_A_BIT;
+
+	// CPSR.I is set upon any exception
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= PSR_AA32_I_BIT;
+
+	// CPSR.F is set upon an exception to FIQ
+	// CPSR.F is unchanged upon an exception to other modes
+	// See ARM DDI 0487E.a, pages G1-5515 to G1-5516
+	// See ARM DDI 0406C.d, page B1-1182
+	new |= (old & PSR_AA32_F_BIT);
+	if (mode == PSR_AA32_MODE_FIQ)
+		new |= PSR_AA32_F_BIT;
+
+	// CPSR.T is set to SCTLR.TE upon any exception
+	// See ARM DDI 0487E.a, page G8-5514
+	// See ARM DDI 0406C.d, page B1-1181
+	if (sctlr & BIT(30))
+		new |= PSR_AA32_T_BIT;
+
+	new |= mode;
+
+	return new;
+}
+
 static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
-	unsigned long cpsr;
-	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
-	bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT);
+	unsigned long spsr = *vcpu_cpsr(vcpu);
+	bool is_thumb = (spsr & PSR_AA32_T_BIT);
 	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
-	cpsr = mode | PSR_AA32_I_BIT;
-
-	if (sctlr & (1 << 30))
-		cpsr |= PSR_AA32_T_BIT;
-	if (sctlr & (1 << 25))
-		cpsr |= PSR_AA32_E_BIT;
-
-	*vcpu_cpsr(vcpu) = cpsr;
+	*vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode);
 
 	/* Note: These now point to the banked copies */
-	vcpu_write_spsr(vcpu, new_spsr_value);
+	vcpu_write_spsr(vcpu, host_spsr_to_spsr32(spsr));
 	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
@@ -84,16 +179,18 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		fsr = &vcpu_cp15(vcpu, c5_DFSR);
 	}
 
-	prepare_fault32(vcpu, PSR_AA32_MODE_ABT | PSR_AA32_A_BIT, vect_offset);
+	prepare_fault32(vcpu, PSR_AA32_MODE_ABT, vect_offset);
 
 	*far = addr;
 
 	/* Give the guest an IMPLEMENTATION DEFINED exception */
 	is_lpae = (vcpu_cp15(vcpu, c2_TTBCR) >> 31);
-	if (is_lpae)
-		*fsr = 1 << 9 | 0x34;
-	else
-		*fsr = 0x14;
+	if (is_lpae) {
+		*fsr = DFSR_LPAE | DFSR_FSC_EXTABT_LPAE;
+	} else {
+		/* no need to shuffle FS[4] into DFSR[10] as its 0 */
+		*fsr = DFSR_FSC_EXTABT_nLPAE;
+	}
 }
 
 void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr)
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index f182b2380345..0d9438e9de2a 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -805,6 +805,7 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 	switch (treg) {
 	case TIMER_REG_TVAL:
 		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
+		val &= lower_32_bits(val);
 		break;
 
 	case TIMER_REG_CTL:
@@ -850,7 +851,7 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val;
+		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val;
 		break;
 
 	case TIMER_REG_CTL:
@@ -1022,7 +1023,7 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
 
 bool kvm_arch_timer_get_input_level(int vintid)
 {
-	struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu();
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	struct arch_timer_context *timer;
 
 	if (vintid == vcpu_vtimer(vcpu)->irq.irq)
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 8de4daf25097..d65a0faa46d8 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -20,8 +20,6 @@
 #include <linux/irqbypass.h>
 #include <linux/sched/stat.h>
 #include <trace/events/kvm.h>
-#include <kvm/arm_pmu.h>
-#include <kvm/arm_psci.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -51,9 +49,6 @@ __asm__(".arch_extension	virt");
 DEFINE_PER_CPU(kvm_host_data_t, kvm_host_data);
 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
 
-/* Per-CPU variable containing the currently running vcpu. */
-static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);
-
 /* The VMID used in the VTTBR */
 static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
 static u32 kvm_next_vmid;
@@ -62,31 +57,8 @@ static DEFINE_SPINLOCK(kvm_vmid_lock);
 static bool vgic_present;
 
 static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);
-
-static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
-{
-	__this_cpu_write(kvm_arm_running_vcpu, vcpu);
-}
-
 DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
-/**
- * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU.
- * Must be called from non-preemptible context
- */
-struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
-{
-	return __this_cpu_read(kvm_arm_running_vcpu);
-}
-
-/**
- * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
- */
-struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
-{
-	return &kvm_arm_running_vcpu;
-}
-
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
@@ -194,7 +166,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
-			kvm_arch_vcpu_free(kvm->vcpus[i]);
+			kvm_vcpu_destroy(kvm->vcpus[i]);
 			kvm->vcpus[i] = NULL;
 		}
 	}
@@ -279,49 +251,46 @@ void kvm_arch_free_vm(struct kvm *kvm)
 		vfree(kvm);
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
+{
+	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
+		return -EBUSY;
+
+	if (id >= kvm->arch.max_vcpus)
+		return -EINVAL;
+
+	return 0;
+}
+
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	int err;
-	struct kvm_vcpu *vcpu;
 
-	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
-		err = -EBUSY;
-		goto out;
-	}
+	/* Force users to call KVM_ARM_VCPU_INIT */
+	vcpu->arch.target = -1;
+	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
 
-	if (id >= kvm->arch.max_vcpus) {
-		err = -EINVAL;
-		goto out;
-	}
+	/* Set up the timer */
+	kvm_timer_vcpu_init(vcpu);
 
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu) {
-		err = -ENOMEM;
-		goto out;
-	}
+	kvm_pmu_vcpu_init(vcpu);
 
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
+	kvm_arm_reset_debug_ptr(vcpu);
+
+	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
 
-	err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
+	err = kvm_vgic_vcpu_init(vcpu);
 	if (err)
-		goto vcpu_uninit;
+		return err;
 
-	return vcpu;
-vcpu_uninit:
-	kvm_vcpu_uninit(vcpu);
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
-out:
-	return ERR_PTR(err);
+	return create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->arch.has_run_once && unlikely(!irqchip_in_kernel(vcpu->kvm)))
 		static_branch_dec(&userspace_irqchip_in_use);
@@ -329,13 +298,8 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
 	kvm_pmu_vcpu_destroy(vcpu);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
-}
 
-void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
-{
-	kvm_arch_vcpu_free(vcpu);
+	kvm_arm_vcpu_destroy(vcpu);
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -368,24 +332,6 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	/* Force users to call KVM_ARM_VCPU_INIT */
-	vcpu->arch.target = -1;
-	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
-
-	/* Set up the timer */
-	kvm_timer_vcpu_init(vcpu);
-
-	kvm_pmu_vcpu_init(vcpu);
-
-	kvm_arm_reset_debug_ptr(vcpu);
-
-	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
-
-	return kvm_vgic_vcpu_init(vcpu);
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	int *last_ran;
@@ -406,7 +352,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->cpu = cpu;
 	vcpu->arch.host_cpu_context = &cpu_data->host_ctxt;
 
-	kvm_arm_set_running_vcpu(vcpu);
 	kvm_vgic_load(vcpu);
 	kvm_timer_vcpu_load(vcpu);
 	kvm_vcpu_load_sysregs(vcpu);
@@ -432,8 +377,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	kvm_vcpu_pmu_restore_host(vcpu);
 
 	vcpu->cpu = -1;
-
-	kvm_arm_set_running_vcpu(NULL);
 }
 
 static void vcpu_power_off(struct kvm_vcpu *vcpu)
@@ -1537,7 +1480,6 @@ static void teardown_hyp_mode(void)
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu)
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
-	hyp_cpu_pm_exit();
 }
 
 /**
@@ -1751,6 +1693,7 @@ int kvm_arch_init(void *opaque)
 	return 0;
 
 out_hyp:
+	hyp_cpu_pm_exit();
 	if (!in_hyp_mode)
 		teardown_hyp_mode();
 out_err:
diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c
index 70d3b449692c..aedfcff99ac5 100644
--- a/virt/kvm/arm/mmio.c
+++ b/virt/kvm/arm/mmio.c
@@ -5,7 +5,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include <asm/kvm_mmio.h>
 #include <asm/kvm_emulate.h>
 #include <trace/events/kvm.h>
 
@@ -92,23 +91,23 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	vcpu->mmio_needed = 0;
 
-	if (!run->mmio.is_write) {
-		len = run->mmio.len;
-		if (len > sizeof(unsigned long))
-			return -EINVAL;
-
+	if (!kvm_vcpu_dabt_iswrite(vcpu)) {
+		len = kvm_vcpu_dabt_get_as(vcpu);
 		data = kvm_mmio_read_buf(run->mmio.data, len);
 
-		if (vcpu->arch.mmio_decode.sign_extend &&
+		if (kvm_vcpu_dabt_issext(vcpu) &&
 		    len < sizeof(unsigned long)) {
 			mask = 1U << ((len * 8) - 1);
 			data = (data ^ mask) - mask;
 		}
 
+		if (!kvm_vcpu_dabt_issf(vcpu))
+			data = data & 0xffffffff;
+
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       &data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
-		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
+		vcpu_set_reg(vcpu, kvm_vcpu_dabt_get_rd(vcpu), data);
 	}
 
 	/*
@@ -120,33 +119,6 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 0;
 }
 
-static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len)
-{
-	unsigned long rt;
-	int access_size;
-	bool sign_extend;
-
-	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
-		/* page table accesses IO mem: tell guest to fix its TTBR */
-		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
-		return 1;
-	}
-
-	access_size = kvm_vcpu_dabt_get_as(vcpu);
-	if (unlikely(access_size < 0))
-		return access_size;
-
-	*is_write = kvm_vcpu_dabt_iswrite(vcpu);
-	sign_extend = kvm_vcpu_dabt_issext(vcpu);
-	rt = kvm_vcpu_dabt_get_rd(vcpu);
-
-	*len = access_size;
-	vcpu->arch.mmio_decode.sign_extend = sign_extend;
-	vcpu->arch.mmio_decode.rt = rt;
-
-	return 0;
-}
-
 int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		 phys_addr_t fault_ipa)
 {
@@ -158,15 +130,10 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	u8 data_buf[8];
 
 	/*
-	 * Prepare MMIO operation. First decode the syndrome data we get
-	 * from the CPU. Then try if some in-kernel emulation feels
-	 * responsible, otherwise let user space do its magic.
+	 * No valid syndrome? Ask userspace for help if it has
+	 * voluntered to do so, and bail out otherwise.
 	 */
-	if (kvm_vcpu_dabt_isvalid(vcpu)) {
-		ret = decode_hsr(vcpu, &is_write, &len);
-		if (ret)
-			return ret;
-	} else {
+	if (!kvm_vcpu_dabt_isvalid(vcpu)) {
 		if (vcpu->kvm->arch.return_nisv_io_abort_to_user) {
 			run->exit_reason = KVM_EXIT_ARM_NISV;
 			run->arm_nisv.esr_iss = kvm_vcpu_dabt_iss_nisv_sanitized(vcpu);
@@ -178,7 +145,20 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return -ENOSYS;
 	}
 
-	rt = vcpu->arch.mmio_decode.rt;
+	/* Page table accesses IO mem: tell guest to fix its TTBR */
+	if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+		return 1;
+	}
+
+	/*
+	 * Prepare MMIO operation. First decode the syndrome data we get
+	 * from the CPU. Then try if some in-kernel emulation feels
+	 * responsible, otherwise let user space do its magic.
+	 */
+	is_write = kvm_vcpu_dabt_iswrite(vcpu);
+	len = kvm_vcpu_dabt_get_as(vcpu);
+	rt = kvm_vcpu_dabt_get_rd(vcpu);
 
 	if (is_write) {
 		data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 0b32a904a1bb..19c961ac4e3c 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -14,7 +14,6 @@
 #include <asm/cacheflush.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
-#include <asm/kvm_mmio.h>
 #include <asm/kvm_ras.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
@@ -1377,14 +1376,8 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)
 {
 	kvm_pfn_t pfn = *pfnp;
 	gfn_t gfn = *ipap >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(pfn);
 
-	/*
-	 * PageTransCompoundMap() returns true for THP and
-	 * hugetlbfs. Make sure the adjustment is done only for THP
-	 * pages.
-	 */
-	if (!PageHuge(page) && PageTransCompoundMap(page)) {
+	if (kvm_is_transparent_hugepage(pfn)) {
 		unsigned long mask;
 		/*
 		 * The address we faulted on is backed by a transparent huge
@@ -1596,16 +1589,8 @@ static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size)
 	__invalidate_icache_guest_page(pfn, size);
 }
 
-static void kvm_send_hwpoison_signal(unsigned long address,
-				     struct vm_area_struct *vma)
+static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
 {
-	short lsb;
-
-	if (is_vm_hugetlb_page(vma))
-		lsb = huge_page_shift(hstate_vma(vma));
-	else
-		lsb = PAGE_SHIFT;
-
 	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
 }
 
@@ -1678,6 +1663,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
+	short vma_shift;
 	kvm_pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
 	bool logging_active = memslot_is_logging(memslot);
@@ -1701,7 +1687,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	vma_pagesize = vma_kernel_pagesize(vma);
+	if (is_vm_hugetlb_page(vma))
+		vma_shift = huge_page_shift(hstate_vma(vma));
+	else
+		vma_shift = PAGE_SHIFT;
+
+	vma_pagesize = 1ULL << vma_shift;
 	if (logging_active ||
 	    (vma->vm_flags & VM_PFNMAP) ||
 	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
@@ -1741,7 +1732,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
 	if (pfn == KVM_PFN_ERR_HWPOISON) {
-		kvm_send_hwpoison_signal(hva, vma);
+		kvm_send_hwpoison_signal(hva, vma_shift);
 		return 0;
 	}
 	if (is_error_noslot_pfn(pfn))
@@ -2147,7 +2138,8 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 	if (!kvm->arch.pgd)
 		return 0;
 	trace_kvm_test_age_hva(hva);
-	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
+	return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
+				 kvm_test_age_hva_handler, NULL);
 }
 
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/arm/perf.c b/virt/kvm/arm/perf.c
index 918cdc3839ea..d45b8b9a4415 100644
--- a/virt/kvm/arm/perf.c
+++ b/virt/kvm/arm/perf.c
@@ -13,14 +13,14 @@
 
 static int kvm_is_in_guest(void)
 {
-        return kvm_arm_get_running_vcpu() != NULL;
+        return kvm_get_running_vcpu() != NULL;
 }
 
 static int kvm_is_user_mode(void)
 {
 	struct kvm_vcpu *vcpu;
 
-	vcpu = kvm_arm_get_running_vcpu();
+	vcpu = kvm_get_running_vcpu();
 
 	if (vcpu)
 		return !vcpu_mode_priv(vcpu);
@@ -32,7 +32,7 @@ static unsigned long kvm_get_guest_ip(void)
 {
 	struct kvm_vcpu *vcpu;
 
-	vcpu = kvm_arm_get_running_vcpu();
+	vcpu = kvm_get_running_vcpu();
 
 	if (vcpu)
 		return *vcpu_pc(vcpu);
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 8731dfeced8b..f0d0312c0a55 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -15,6 +15,8 @@
 #include <kvm/arm_vgic.h>
 
 static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
+static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx);
+static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
 
 #define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
 
@@ -75,6 +77,13 @@ static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
 
 	return pmc;
 }
+static struct kvm_pmc *kvm_pmu_get_alternate_pmc(struct kvm_pmc *pmc)
+{
+	if (kvm_pmu_idx_is_high_counter(pmc->idx))
+		return pmc - 1;
+	else
+		return pmc + 1;
+}
 
 /**
  * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
@@ -238,10 +247,11 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
  */
 void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 {
-	int i;
+	unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
+	int i;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+	for_each_set_bit(i, &mask, 32)
 		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
 
 	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
@@ -294,15 +304,9 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 
 		pmc = &pmu->pmc[i];
 
-		/*
-		 * For high counters of chained events we must recreate the
-		 * perf event with the long (64bit) attribute set.
-		 */
-		if (kvm_pmu_pmc_is_chained(pmc) &&
-		    kvm_pmu_idx_is_high_counter(i)) {
-			kvm_pmu_create_perf_event(vcpu, i);
-			continue;
-		}
+		/* A change in the enable state may affect the chain state */
+		kvm_pmu_update_pmc_chained(vcpu, i);
+		kvm_pmu_create_perf_event(vcpu, i);
 
 		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event) {
@@ -335,15 +339,9 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 
 		pmc = &pmu->pmc[i];
 
-		/*
-		 * For high counters of chained events we must recreate the
-		 * perf event with the long (64bit) attribute unset.
-		 */
-		if (kvm_pmu_pmc_is_chained(pmc) &&
-		    kvm_pmu_idx_is_high_counter(i)) {
-			kvm_pmu_create_perf_event(vcpu, i);
-			continue;
-		}
+		/* A change in the enable state may affect the chain state */
+		kvm_pmu_update_pmc_chained(vcpu, i);
+		kvm_pmu_create_perf_event(vcpu, i);
 
 		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event)
@@ -480,25 +478,45 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
  */
 void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 {
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	int i;
-	u64 type, enable, reg;
 
-	if (val == 0)
+	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
 		return;
 
-	enable = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	/* Weed out disabled counters */
+	val &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+
 	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
+		u64 type, reg;
+
 		if (!(val & BIT(i)))
 			continue;
-		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
-		       & ARMV8_PMU_EVTYPE_EVENT;
-		if ((type == ARMV8_PMUV3_PERFCTR_SW_INCR)
-		    && (enable & BIT(i))) {
-			reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+
+		/* PMSWINC only applies to ... SW_INC! */
+		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i);
+		type &= ARMV8_PMU_EVTYPE_EVENT;
+		if (type != ARMV8_PMUV3_PERFCTR_SW_INCR)
+			continue;
+
+		/* increment this even SW_INC counter */
+		reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+		reg = lower_32_bits(reg);
+		__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
+
+		if (reg) /* no overflow on the low part */
+			continue;
+
+		if (kvm_pmu_pmc_is_chained(&pmu->pmc[i])) {
+			/* increment the high counter */
+			reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) + 1;
 			reg = lower_32_bits(reg);
-			__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
-			if (!reg)
-				__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+			__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) = reg;
+			if (!reg) /* mark overflow on the high counter */
+				__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i + 1);
+		} else {
+			/* mark overflow on low counter */
+			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
 		}
 	}
 }
@@ -510,10 +528,9 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
  */
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 {
-	u64 mask;
+	unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
 	int i;
 
-	mask = kvm_pmu_valid_counter_mask(vcpu);
 	if (val & ARMV8_PMU_PMCR_E) {
 		kvm_pmu_enable_counter_mask(vcpu,
 		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
@@ -525,7 +542,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
 
 	if (val & ARMV8_PMU_PMCR_P) {
-		for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++)
+		for_each_set_bit(i, &mask, 32)
 			kvm_pmu_set_counter_value(vcpu, i, 0);
 	}
 }
@@ -582,15 +599,14 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
-	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+	if (kvm_pmu_pmc_is_chained(pmc)) {
 		/**
 		 * The initial sample period (overflow count) of an event. For
 		 * chained counters we only support overflow interrupts on the
 		 * high counter.
 		 */
 		attr.sample_period = (-counter) & GENMASK(63, 0);
-		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
-			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+		attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
 
 		event = perf_event_create_kernel_counter(&attr, -1, current,
 							 kvm_pmu_perf_overflow,
@@ -621,25 +637,33 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
  * @select_idx: The number of selected counter
  *
  * Update the chained bitmap based on the event type written in the
- * typer register.
+ * typer register and the enable state of the odd register.
  */
 static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
 {
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
+	struct kvm_pmc *pmc = &pmu->pmc[select_idx], *canonical_pmc;
+	bool new_state, old_state;
+
+	old_state = kvm_pmu_pmc_is_chained(pmc);
+	new_state = kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx) &&
+		    kvm_pmu_counter_is_enabled(vcpu, pmc->idx | 0x1);
+
+	if (old_state == new_state)
+		return;
 
-	if (kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx)) {
+	canonical_pmc = kvm_pmu_get_canonical_pmc(pmc);
+	kvm_pmu_stop_counter(vcpu, canonical_pmc);
+	if (new_state) {
 		/*
 		 * During promotion from !chained to chained we must ensure
 		 * the adjacent counter is stopped and its event destroyed
 		 */
-		if (!kvm_pmu_pmc_is_chained(pmc))
-			kvm_pmu_stop_counter(vcpu, pmc);
-
+		kvm_pmu_stop_counter(vcpu, kvm_pmu_get_alternate_pmc(pmc));
 		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
-	} else {
-		clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+		return;
 	}
+	clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
 }
 
 /**
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 98c7360d9fb7..d53d34a33e35 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -839,9 +839,8 @@ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
 	u32 event_id = its_cmd_get_id(its_cmd);
 	struct its_ite *ite;
 
-
 	ite = find_ite(its, device_id, event_id);
-	if (ite && ite->collection) {
+	if (ite && its_is_collection_mapped(ite->collection)) {
 		/*
 		 * Though the spec talks about removing the pending state, we
 		 * don't bother here since we clear the ITTE anyway and the
@@ -2475,7 +2474,8 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
 	target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT);
 	coll_id = val & KVM_ITS_CTE_ICID_MASK;
 
-	if (target_addr >= atomic_read(&kvm->online_vcpus))
+	if (target_addr != COLLECTION_NOT_MAPPED &&
+	    target_addr >= atomic_read(&kvm->online_vcpus))
 		return -EINVAL;
 
 	collection = find_collection(its, coll_id);
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 7dfd15dbb308..ebc218840fc2 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -414,8 +414,11 @@ static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu,
 					     gpa_t addr, unsigned int len)
 {
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	u64 value = vgic_cpu->pendbaser;
 
-	return extract_bytes(vgic_cpu->pendbaser, addr & 7, len);
+	value &= ~GICR_PENDBASER_PTZ;
+
+	return extract_bytes(value, addr & 7, len);
 }
 
 static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 0d090482720d..d656ebd5f9d4 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -190,15 +190,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
  * value later will give us the same value as we update the per-CPU variable
  * in the preempt notifier handlers.
  */
-static struct kvm_vcpu *vgic_get_mmio_requester_vcpu(void)
-{
-	struct kvm_vcpu *vcpu;
-
-	preempt_disable();
-	vcpu = kvm_arm_get_running_vcpu();
-	preempt_enable();
-	return vcpu;
-}
 
 /* Must be called with irq->irq_lock held */
 static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
@@ -221,7 +212,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
-	bool is_uaccess = !vgic_get_mmio_requester_vcpu();
+	bool is_uaccess = !kvm_get_running_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -274,7 +265,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
 			      gpa_t addr, unsigned int len,
 			      unsigned long val)
 {
-	bool is_uaccess = !vgic_get_mmio_requester_vcpu();
+	bool is_uaccess = !kvm_get_running_vcpu();
 	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
 	int i;
 	unsigned long flags;
@@ -335,7 +326,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
 				    bool active)
 {
 	unsigned long flags;
-	struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu();
+	struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu();
 
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 836f418f1ee8..5af2aefad435 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -98,11 +98,6 @@ extern struct kvm_io_device_ops kvm_io_gic_ops;
 		.uaccess_write = uwr,					\
 	}
 
-int kvm_vgic_register_mmio_region(struct kvm *kvm, struct kvm_vcpu *vcpu,
-				  struct vgic_register_region *reg_desc,
-				  struct vgic_io_device *region,
-				  int nr_irqs, bool offset_private);
-
 unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len);
 
 void vgic_data_host_to_mmio_bus(void *buf, unsigned int len,
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 35305d6e68cc..15e5b037f92d 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -17,21 +17,6 @@
 #include "async_pf.h"
 #include <trace/events/kvm.h>
 
-static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu,
-					       struct kvm_async_pf *work)
-{
-#ifdef CONFIG_KVM_ASYNC_PF_SYNC
-	kvm_arch_async_page_present(vcpu, work);
-#endif
-}
-static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu,
-						struct kvm_async_pf *work)
-{
-#ifndef CONFIG_KVM_ASYNC_PF_SYNC
-	kvm_arch_async_page_present(vcpu, work);
-#endif
-}
-
 static struct kmem_cache *async_pf_cache;
 
 int kvm_async_pf_init(void)
@@ -64,7 +49,7 @@ static void async_pf_execute(struct work_struct *work)
 	struct mm_struct *mm = apf->mm;
 	struct kvm_vcpu *vcpu = apf->vcpu;
 	unsigned long addr = apf->addr;
-	gva_t gva = apf->gva;
+	gpa_t cr2_or_gpa = apf->cr2_or_gpa;
 	int locked = 1;
 
 	might_sleep();
@@ -80,7 +65,8 @@ static void async_pf_execute(struct work_struct *work)
 	if (locked)
 		up_read(&mm->mmap_sem);
 
-	kvm_async_page_present_sync(vcpu, apf);
+	if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
+		kvm_arch_async_page_present(vcpu, apf);
 
 	spin_lock(&vcpu->async_pf.lock);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
@@ -92,7 +78,7 @@ static void async_pf_execute(struct work_struct *work)
 	 * this point
 	 */
 
-	trace_kvm_async_pf_completed(addr, gva);
+	trace_kvm_async_pf_completed(addr, cr2_or_gpa);
 
 	if (swq_has_sleeper(&vcpu->wq))
 		swake_up_one(&vcpu->wq);
@@ -157,7 +143,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 		spin_unlock(&vcpu->async_pf.lock);
 
 		kvm_arch_async_page_ready(vcpu, work);
-		kvm_async_page_present_async(vcpu, work);
+		if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
+			kvm_arch_async_page_present(vcpu, work);
 
 		list_del(&work->queue);
 		vcpu->async_pf.queued--;
@@ -165,8 +152,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
-		       struct kvm_arch_async_pf *arch)
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+		       unsigned long hva, struct kvm_arch_async_pf *arch)
 {
 	struct kvm_async_pf *work;
 
@@ -185,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 
 	work->wakeup_all = false;
 	work->vcpu = vcpu;
-	work->gva = gva;
+	work->cr2_or_gpa = cr2_or_gpa;
 	work->addr = hva;
 	work->arch = *arch;
 	work->mm = current->mm;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 00268290dcbd..7e63a3236364 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -104,16 +104,16 @@ static cpumask_var_t cpus_hardware_enabled;
 static int kvm_usage_count;
 static atomic_t hardware_enable_failed;
 
-struct kmem_cache *kvm_vcpu_cache;
-EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
+static struct kmem_cache *kvm_vcpu_cache;
 
 static __read_mostly struct preempt_ops kvm_preempt_ops;
+static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);
 
 struct dentry *kvm_debugfs_dir;
 EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
 
 static int kvm_debugfs_num_entries;
-static const struct file_operations *stat_fops_per_vm[];
+static const struct file_operations stat_fops_per_vm;
 
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
@@ -191,12 +191,24 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 	return true;
 }
 
+bool kvm_is_transparent_hugepage(kvm_pfn_t pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+
+	if (!PageTransCompoundMap(page))
+		return false;
+
+	return is_transparent_hugepage(compound_head(page));
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */
 void vcpu_load(struct kvm_vcpu *vcpu)
 {
 	int cpu = get_cpu();
+
+	__this_cpu_write(kvm_running_vcpu, vcpu);
 	preempt_notifier_register(&vcpu->preempt_notifier);
 	kvm_arch_vcpu_load(vcpu, cpu);
 	put_cpu();
@@ -208,6 +220,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
 	preempt_notifier_unregister(&vcpu->preempt_notifier);
+	__this_cpu_write(kvm_running_vcpu, NULL);
 	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(vcpu_put);
@@ -322,11 +335,8 @@ void kvm_reload_remote_mmus(struct kvm *kvm)
 	kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
 }
 
-int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
+static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
-	struct page *page;
-	int r;
-
 	mutex_init(&vcpu->mutex);
 	vcpu->cpu = -1;
 	vcpu->kvm = kvm;
@@ -338,42 +348,28 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->pre_pcpu = -1;
 	INIT_LIST_HEAD(&vcpu->blocked_vcpu_list);
 
-	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!page) {
-		r = -ENOMEM;
-		goto fail;
-	}
-	vcpu->run = page_address(page);
-
 	kvm_vcpu_set_in_spin_loop(vcpu, false);
 	kvm_vcpu_set_dy_eligible(vcpu, false);
 	vcpu->preempted = false;
 	vcpu->ready = false;
-
-	r = kvm_arch_vcpu_init(vcpu);
-	if (r < 0)
-		goto fail_free_run;
-	return 0;
-
-fail_free_run:
-	free_page((unsigned long)vcpu->run);
-fail:
-	return r;
+	preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_init);
 
-void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
+void kvm_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	kvm_arch_vcpu_destroy(vcpu);
+
 	/*
-	 * no need for rcu_read_lock as VCPU_RUN is the only place that
-	 * will change the vcpu->pid pointer and on uninit all file
-	 * descriptors are already gone.
+	 * No need for rcu_read_lock as VCPU_RUN is the only place that changes
+	 * the vcpu->pid pointer, and at destruction time all file descriptors
+	 * are already gone.
 	 */
 	put_pid(rcu_dereference_protected(vcpu->pid, 1));
-	kvm_arch_vcpu_uninit(vcpu);
+
 	free_page((unsigned long)vcpu->run);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
-EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);
+EXPORT_SYMBOL_GPL(kvm_vcpu_destroy);
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
@@ -650,11 +646,11 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 			return -ENOMEM;
 
 		stat_data->kvm = kvm;
-		stat_data->offset = p->offset;
-		stat_data->mode = p->mode ? p->mode : 0644;
+		stat_data->dbgfs_item = p;
 		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
-		debugfs_create_file(p->name, stat_data->mode, kvm->debugfs_dentry,
-				    stat_data, stat_fops_per_vm[p->kind]);
+		debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
+				    kvm->debugfs_dentry, stat_data,
+				    &stat_fops_per_vm);
 	}
 	return 0;
 }
@@ -964,7 +960,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
 
 	/*
 	 * Increment the new memslot generation a second time, dropping the
-	 * update in-progress flag and incrementing then generation based on
+	 * update in-progress flag and incrementing the generation based on
 	 * the number of address spaces.  This provides a unique and easily
 	 * identifiable generation number while the memslots are in flux.
 	 */
@@ -1117,7 +1113,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		 *
 		 * validation of sp->gfn happens in:
 		 *	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
-		 *	- kvm_is_visible_gfn (mmu_check_roots)
+		 *	- kvm_is_visible_gfn (mmu_check_root)
 		 */
 		kvm_arch_flush_shadow_memslot(kvm, slot);
 
@@ -1406,14 +1402,14 @@ bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
 
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	struct vm_area_struct *vma;
 	unsigned long addr, size;
 
 	size = PAGE_SIZE;
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
 	if (kvm_is_error_hva(addr))
 		return PAGE_SIZE;
 
@@ -1519,7 +1515,7 @@ static inline int check_user_page_hwpoison(unsigned long addr)
 /*
  * The fast path to get the writable pfn which will be stored in @pfn,
  * true indicates success, otherwise false is returned.  It's also the
- * only part that runs if we can are in atomic context.
+ * only part that runs if we can in atomic context.
  */
 static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
 			    bool *writable, kvm_pfn_t *pfn)
@@ -1821,26 +1817,72 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
-static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn,
-			 struct kvm_host_map *map)
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+{
+	if (pfn == 0)
+		return;
+
+	if (cache)
+		cache->pfn = cache->gfn = 0;
+
+	if (dirty)
+		kvm_release_pfn_dirty(pfn);
+	else
+		kvm_release_pfn_clean(pfn);
+}
+
+static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
+				 struct gfn_to_pfn_cache *cache, u64 gen)
+{
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
+
+	cache->pfn = gfn_to_pfn_memslot(slot, gfn);
+	cache->gfn = gfn;
+	cache->dirty = false;
+	cache->generation = gen;
+}
+
+static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
+			 struct kvm_host_map *map,
+			 struct gfn_to_pfn_cache *cache,
+			 bool atomic)
 {
 	kvm_pfn_t pfn;
 	void *hva = NULL;
 	struct page *page = KVM_UNMAPPED_PAGE;
+	struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
+	u64 gen = slots->generation;
 
 	if (!map)
 		return -EINVAL;
 
-	pfn = gfn_to_pfn_memslot(slot, gfn);
+	if (cache) {
+		if (!cache->pfn || cache->gfn != gfn ||
+			cache->generation != gen) {
+			if (atomic)
+				return -EAGAIN;
+			kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
+		}
+		pfn = cache->pfn;
+	} else {
+		if (atomic)
+			return -EAGAIN;
+		pfn = gfn_to_pfn_memslot(slot, gfn);
+	}
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 
 	if (pfn_valid(pfn)) {
 		page = pfn_to_page(pfn);
-		hva = kmap(page);
+		if (atomic)
+			hva = kmap_atomic(page);
+		else
+			hva = kmap(page);
 #ifdef CONFIG_HAS_IOMEM
-	} else {
+	} else if (!atomic) {
 		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+	} else {
+		return -EINVAL;
 #endif
 	}
 
@@ -1855,14 +1897,25 @@ static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn,
 	return 0;
 }
 
+int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
+		struct gfn_to_pfn_cache *cache, bool atomic)
+{
+	return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
+			cache, atomic);
+}
+EXPORT_SYMBOL_GPL(kvm_map_gfn);
+
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 {
-	return __kvm_map_gfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, map);
+	return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
+		NULL, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
-		    bool dirty)
+static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+			struct kvm_host_map *map,
+			struct gfn_to_pfn_cache *cache,
+			bool dirty, bool atomic)
 {
 	if (!map)
 		return;
@@ -1870,23 +1923,45 @@ void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
 	if (!map->hva)
 		return;
 
-	if (map->page != KVM_UNMAPPED_PAGE)
-		kunmap(map->page);
+	if (map->page != KVM_UNMAPPED_PAGE) {
+		if (atomic)
+			kunmap_atomic(map->hva);
+		else
+			kunmap(map->page);
+	}
 #ifdef CONFIG_HAS_IOMEM
-	else
+	else if (!atomic)
 		memunmap(map->hva);
+	else
+		WARN_ONCE(1, "Unexpected unmapping in atomic context");
 #endif
 
-	if (dirty) {
-		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
-		kvm_release_pfn_dirty(map->pfn);
-	} else {
-		kvm_release_pfn_clean(map->pfn);
-	}
+	if (dirty)
+		mark_page_dirty_in_slot(memslot, map->gfn);
+
+	if (cache)
+		cache->dirty |= dirty;
+	else
+		kvm_release_pfn(map->pfn, dirty, NULL);
 
 	map->hva = NULL;
 	map->page = NULL;
 }
+
+int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
+		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
+{
+	__kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+			cache, dirty, atomic);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
+
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
+{
+	__kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
+			dirty, false);
+}
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
@@ -1931,11 +2006,8 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
 
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) {
-		struct page *page = pfn_to_page(pfn);
-
-		SetPageDirty(page);
-	}
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
+		SetPageDirty(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
@@ -2051,17 +2123,6 @@ static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
 	return 0;
 }
 
-int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
-			  unsigned long len)
-{
-	gfn_t gfn = gpa >> PAGE_SHIFT;
-	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
-	int offset = offset_in_page(gpa);
-
-	return __kvm_read_guest_atomic(slot, gfn, data, offset, len);
-}
-EXPORT_SYMBOL_GPL(kvm_read_guest_atomic);
-
 int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
 			       void *data, unsigned long len)
 {
@@ -2158,33 +2219,36 @@ static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots,
 	gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
 	gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
 	gfn_t nr_pages_avail;
-	int r = start_gfn <= end_gfn ? 0 : -EINVAL;
 
-	ghc->gpa = gpa;
+	/* Update ghc->generation before performing any error checks. */
 	ghc->generation = slots->generation;
-	ghc->len = len;
-	ghc->hva = KVM_HVA_ERR_BAD;
+
+	if (start_gfn > end_gfn) {
+		ghc->hva = KVM_HVA_ERR_BAD;
+		return -EINVAL;
+	}
 
 	/*
 	 * If the requested region crosses two memslots, we still
 	 * verify that the entire region is valid here.
 	 */
-	while (!r && start_gfn <= end_gfn) {
+	for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) {
 		ghc->memslot = __gfn_to_memslot(slots, start_gfn);
 		ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
 					   &nr_pages_avail);
 		if (kvm_is_error_hva(ghc->hva))
-			r = -EFAULT;
-		start_gfn += nr_pages_avail;
+			return -EFAULT;
 	}
 
 	/* Use the slow path for cross page reads and writes. */
-	if (!r && nr_pages_needed == 1)
+	if (nr_pages_needed == 1)
 		ghc->hva += offset;
 	else
 		ghc->memslot = NULL;
 
-	return r;
+	ghc->gpa = gpa;
+	ghc->len = len;
+	return 0;
 }
 
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
@@ -2205,15 +2269,17 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 
 	BUG_ON(len + offset > ghc->len);
 
-	if (slots->generation != ghc->generation)
-		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
-
-	if (unlikely(!ghc->memslot))
-		return kvm_write_guest(kvm, gpa, data, len);
+	if (slots->generation != ghc->generation) {
+		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
+			return -EFAULT;
+	}
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
+	if (unlikely(!ghc->memslot))
+		return kvm_write_guest(kvm, gpa, data, len);
+
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
@@ -2238,15 +2304,17 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 
 	BUG_ON(len > ghc->len);
 
-	if (slots->generation != ghc->generation)
-		__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
-
-	if (unlikely(!ghc->memslot))
-		return kvm_read_guest(kvm, ghc->gpa, data, len);
+	if (slots->generation != ghc->generation) {
+		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
+			return -EFAULT;
+	}
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
+	if (unlikely(!ghc->memslot))
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
+
 	r = __copy_from_user(data, (void __user *)ghc->hva, len);
 	if (r)
 		return -EFAULT;
@@ -2718,6 +2786,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 {
 	int r;
 	struct kvm_vcpu *vcpu;
+	struct page *page;
 
 	if (id >= KVM_MAX_VCPU_ID)
 		return -EINVAL;
@@ -2731,17 +2800,29 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	kvm->created_vcpus++;
 	mutex_unlock(&kvm->lock);
 
-	vcpu = kvm_arch_vcpu_create(kvm, id);
-	if (IS_ERR(vcpu)) {
-		r = PTR_ERR(vcpu);
+	r = kvm_arch_vcpu_precreate(kvm, id);
+	if (r)
+		goto vcpu_decrement;
+
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	if (!vcpu) {
+		r = -ENOMEM;
 		goto vcpu_decrement;
 	}
 
-	preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
+	BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE);
+	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	if (!page) {
+		r = -ENOMEM;
+		goto vcpu_free;
+	}
+	vcpu->run = page_address(page);
+
+	kvm_vcpu_init(vcpu, kvm, id);
 
-	r = kvm_arch_vcpu_setup(vcpu);
+	r = kvm_arch_vcpu_create(vcpu);
 	if (r)
-		goto vcpu_destroy;
+		goto vcpu_free_run_page;
 
 	kvm_create_vcpu_debugfs(vcpu);
 
@@ -2778,8 +2859,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 unlock_vcpu_destroy:
 	mutex_unlock(&kvm->lock);
 	debugfs_remove_recursive(vcpu->debugfs_dentry);
-vcpu_destroy:
 	kvm_arch_vcpu_destroy(vcpu);
+vcpu_free_run_page:
+	free_page((unsigned long)vcpu->run);
+vcpu_free:
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 vcpu_decrement:
 	mutex_lock(&kvm->lock);
 	kvm->created_vcpus--;
@@ -4013,8 +4097,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 		return -ENOENT;
 
 	if (simple_attr_open(inode, file, get,
-			     stat_data->mode & S_IWUGO ? set : NULL,
-			     fmt)) {
+		    KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222
+		    ? set : NULL,
+		    fmt)) {
 		kvm_put_kvm(stat_data->kvm);
 		return -ENOMEM;
 	}
@@ -4033,105 +4118,111 @@ static int kvm_debugfs_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int vm_stat_get_per_vm(void *data, u64 *val)
+static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val)
 {
-	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+	*val = *(ulong *)((void *)kvm + offset);
+
+	return 0;
+}
 
-	*val = *(ulong *)((void *)stat_data->kvm + stat_data->offset);
+static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset)
+{
+	*(ulong *)((void *)kvm + offset) = 0;
 
 	return 0;
 }
 
-static int vm_stat_clear_per_vm(void *data, u64 val)
+static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val)
 {
-	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+	int i;
+	struct kvm_vcpu *vcpu;
 
-	if (val)
-		return -EINVAL;
+	*val = 0;
 
-	*(ulong *)((void *)stat_data->kvm + stat_data->offset) = 0;
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		*val += *(u64 *)((void *)vcpu + offset);
 
 	return 0;
 }
 
-static int vm_stat_get_per_vm_open(struct inode *inode, struct file *file)
+static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset)
 {
-	__simple_attr_check_format("%llu\n", 0ull);
-	return kvm_debugfs_open(inode, file, vm_stat_get_per_vm,
-				vm_stat_clear_per_vm, "%llu\n");
-}
+	int i;
+	struct kvm_vcpu *vcpu;
 
-static const struct file_operations vm_stat_get_per_vm_fops = {
-	.owner   = THIS_MODULE,
-	.open    = vm_stat_get_per_vm_open,
-	.release = kvm_debugfs_release,
-	.read    = simple_attr_read,
-	.write   = simple_attr_write,
-	.llseek  = no_llseek,
-};
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		*(u64 *)((void *)vcpu + offset) = 0;
+
+	return 0;
+}
 
-static int vcpu_stat_get_per_vm(void *data, u64 *val)
+static int kvm_stat_data_get(void *data, u64 *val)
 {
-	int i;
+	int r = -EFAULT;
 	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
-	struct kvm_vcpu *vcpu;
-
-	*val = 0;
 
-	kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
-		*val += *(u64 *)((void *)vcpu + stat_data->offset);
+	switch (stat_data->dbgfs_item->kind) {
+	case KVM_STAT_VM:
+		r = kvm_get_stat_per_vm(stat_data->kvm,
+					stat_data->dbgfs_item->offset, val);
+		break;
+	case KVM_STAT_VCPU:
+		r = kvm_get_stat_per_vcpu(stat_data->kvm,
+					  stat_data->dbgfs_item->offset, val);
+		break;
+	}
 
-	return 0;
+	return r;
 }
 
-static int vcpu_stat_clear_per_vm(void *data, u64 val)
+static int kvm_stat_data_clear(void *data, u64 val)
 {
-	int i;
+	int r = -EFAULT;
 	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
-	struct kvm_vcpu *vcpu;
 
 	if (val)
 		return -EINVAL;
 
-	kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
-		*(u64 *)((void *)vcpu + stat_data->offset) = 0;
+	switch (stat_data->dbgfs_item->kind) {
+	case KVM_STAT_VM:
+		r = kvm_clear_stat_per_vm(stat_data->kvm,
+					  stat_data->dbgfs_item->offset);
+		break;
+	case KVM_STAT_VCPU:
+		r = kvm_clear_stat_per_vcpu(stat_data->kvm,
+					    stat_data->dbgfs_item->offset);
+		break;
+	}
 
-	return 0;
+	return r;
 }
 
-static int vcpu_stat_get_per_vm_open(struct inode *inode, struct file *file)
+static int kvm_stat_data_open(struct inode *inode, struct file *file)
 {
 	__simple_attr_check_format("%llu\n", 0ull);
-	return kvm_debugfs_open(inode, file, vcpu_stat_get_per_vm,
-				 vcpu_stat_clear_per_vm, "%llu\n");
+	return kvm_debugfs_open(inode, file, kvm_stat_data_get,
+				kvm_stat_data_clear, "%llu\n");
 }
 
-static const struct file_operations vcpu_stat_get_per_vm_fops = {
-	.owner   = THIS_MODULE,
-	.open    = vcpu_stat_get_per_vm_open,
+static const struct file_operations stat_fops_per_vm = {
+	.owner = THIS_MODULE,
+	.open = kvm_stat_data_open,
 	.release = kvm_debugfs_release,
-	.read    = simple_attr_read,
-	.write   = simple_attr_write,
-	.llseek  = no_llseek,
-};
-
-static const struct file_operations *stat_fops_per_vm[] = {
-	[KVM_STAT_VCPU] = &vcpu_stat_get_per_vm_fops,
-	[KVM_STAT_VM]   = &vm_stat_get_per_vm_fops,
+	.read = simple_attr_read,
+	.write = simple_attr_write,
+	.llseek = no_llseek,
 };
 
 static int vm_stat_get(void *_offset, u64 *val)
 {
 	unsigned offset = (long)_offset;
 	struct kvm *kvm;
-	struct kvm_stat_data stat_tmp = {.offset = offset};
 	u64 tmp_val;
 
 	*val = 0;
 	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		stat_tmp.kvm = kvm;
-		vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
+		kvm_get_stat_per_vm(kvm, offset, &tmp_val);
 		*val += tmp_val;
 	}
 	mutex_unlock(&kvm_lock);
@@ -4142,15 +4233,13 @@ static int vm_stat_clear(void *_offset, u64 val)
 {
 	unsigned offset = (long)_offset;
 	struct kvm *kvm;
-	struct kvm_stat_data stat_tmp = {.offset = offset};
 
 	if (val)
 		return -EINVAL;
 
 	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		stat_tmp.kvm = kvm;
-		vm_stat_clear_per_vm((void *)&stat_tmp, 0);
+		kvm_clear_stat_per_vm(kvm, offset);
 	}
 	mutex_unlock(&kvm_lock);
 
@@ -4163,14 +4252,12 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 {
 	unsigned offset = (long)_offset;
 	struct kvm *kvm;
-	struct kvm_stat_data stat_tmp = {.offset = offset};
 	u64 tmp_val;
 
 	*val = 0;
 	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		stat_tmp.kvm = kvm;
-		vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
+		kvm_get_stat_per_vcpu(kvm, offset, &tmp_val);
 		*val += tmp_val;
 	}
 	mutex_unlock(&kvm_lock);
@@ -4181,15 +4268,13 @@ static int vcpu_stat_clear(void *_offset, u64 val)
 {
 	unsigned offset = (long)_offset;
 	struct kvm *kvm;
-	struct kvm_stat_data stat_tmp = {.offset = offset};
 
 	if (val)
 		return -EINVAL;
 
 	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
-		stat_tmp.kvm = kvm;
-		vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
+		kvm_clear_stat_per_vcpu(kvm, offset);
 	}
 	mutex_unlock(&kvm_lock);
 
@@ -4262,9 +4347,8 @@ static void kvm_init_debug(void)
 
 	kvm_debugfs_num_entries = 0;
 	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
-		int mode = p->mode ? p->mode : 0644;
-		debugfs_create_file(p->name, mode, kvm_debugfs_dir,
-				    (void *)(long)p->offset,
+		debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
+				    kvm_debugfs_dir, (void *)(long)p->offset,
 				    stat_fops[p->kind]);
 	}
 }
@@ -4304,8 +4388,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 	WRITE_ONCE(vcpu->preempted, false);
 	WRITE_ONCE(vcpu->ready, false);
 
+	__this_cpu_write(kvm_running_vcpu, vcpu);
 	kvm_arch_sched_in(vcpu, cpu);
-
 	kvm_arch_vcpu_load(vcpu, cpu);
 }
 
@@ -4319,6 +4403,25 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 		WRITE_ONCE(vcpu->ready, true);
 	}
 	kvm_arch_vcpu_put(vcpu);
+	__this_cpu_write(kvm_running_vcpu, NULL);
+}
+
+/**
+ * kvm_get_running_vcpu - get the vcpu running on the current CPU.
+ * Thanks to preempt notifiers, this can also be called from
+ * preemptible context.
+ */
+struct kvm_vcpu *kvm_get_running_vcpu(void)
+{
+        return __this_cpu_read(kvm_running_vcpu);
+}
+
+/**
+ * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus.
+ */
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
+{
+        return &kvm_running_vcpu;
 }
 
 static void check_processor_compat(void *rtn)
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index 43de8ae78fa1..28fda42e471b 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -85,6 +85,7 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer)
 {
 	struct irq_bypass_producer *tmp;
 	struct irq_bypass_consumer *consumer;
+	int ret;
 
 	if (!producer->token)
 		return -EINVAL;
@@ -98,20 +99,16 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer)
 
 	list_for_each_entry(tmp, &producers, node) {
 		if (tmp->token == producer->token) {
-			mutex_unlock(&lock);
-			module_put(THIS_MODULE);
-			return -EBUSY;
+			ret = -EBUSY;
+			goto out_err;
 		}
 	}
 
 	list_for_each_entry(consumer, &consumers, node) {
 		if (consumer->token == producer->token) {
-			int ret = __connect(producer, consumer);
-			if (ret) {
-				mutex_unlock(&lock);
-				module_put(THIS_MODULE);
-				return ret;
-			}
+			ret = __connect(producer, consumer);
+			if (ret)
+				goto out_err;
 			break;
 		}
 	}
@@ -121,6 +118,10 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer)
 	mutex_unlock(&lock);
 
 	return 0;
+out_err:
+	mutex_unlock(&lock);
+	module_put(THIS_MODULE);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(irq_bypass_register_producer);
 
@@ -179,6 +180,7 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
 {
 	struct irq_bypass_consumer *tmp;
 	struct irq_bypass_producer *producer;
+	int ret;
 
 	if (!consumer->token ||
 	    !consumer->add_producer || !consumer->del_producer)
@@ -193,20 +195,16 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
 
 	list_for_each_entry(tmp, &consumers, node) {
 		if (tmp->token == consumer->token || tmp == consumer) {
-			mutex_unlock(&lock);
-			module_put(THIS_MODULE);
-			return -EBUSY;
+			ret = -EBUSY;
+			goto out_err;
 		}
 	}
 
 	list_for_each_entry(producer, &producers, node) {
 		if (producer->token == consumer->token) {
-			int ret = __connect(producer, consumer);
-			if (ret) {
-				mutex_unlock(&lock);
-				module_put(THIS_MODULE);
-				return ret;
-			}
+			ret = __connect(producer, consumer);
+			if (ret)
+				goto out_err;
 			break;
 		}
 	}
@@ -216,6 +214,10 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
 	mutex_unlock(&lock);
 
 	return 0;
+out_err:
+	mutex_unlock(&lock);
+	module_put(THIS_MODULE);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(irq_bypass_register_consumer);